diff options
545 files changed, 12790 insertions, 8760 deletions
diff --git a/Documentation/RCU/Design/Data-Structures/Data-Structures.html b/Documentation/RCU/Design/Data-Structures/Data-Structures.html index 6c06e10bd04b..f5120a00f511 100644 --- a/Documentation/RCU/Design/Data-Structures/Data-Structures.html +++ b/Documentation/RCU/Design/Data-Structures/Data-Structures.html @@ -380,31 +380,26 @@ and therefore need no protection. as follows: <pre> - 1 unsigned long gpnum; - 2 unsigned long completed; + 1 unsigned long gp_seq; </pre> <p>RCU grace periods are numbered, and -the <tt>->gpnum</tt> field contains the number of the grace -period that started most recently. -The <tt>->completed</tt> field contains the number of the -grace period that completed most recently. -If the two fields are equal, the RCU grace period that most recently -started has already completed, and therefore the corresponding -flavor of RCU is idle. -If <tt>->gpnum</tt> is one greater than <tt>->completed</tt>, -then <tt>->gpnum</tt> gives the number of the current RCU -grace period, which has not yet completed. -Any other combination of values indicates that something is broken. -These two fields are protected by the root <tt>rcu_node</tt>'s +the <tt>->gp_seq</tt> field contains the current grace-period +sequence number. +The bottom two bits are the state of the current grace period, +which can be zero for not yet started or one for in progress. +In other words, if the bottom two bits of <tt>->gp_seq</tt> are +zero, the corresponding flavor of RCU is idle. +Any other value in the bottom two bits indicates that something is broken. +This field is protected by the root <tt>rcu_node</tt> structure's <tt>->lock</tt> field. -</p><p>There are <tt>->gpnum</tt> and <tt>->completed</tt> fields +</p><p>There are <tt>->gp_seq</tt> fields in the <tt>rcu_node</tt> and <tt>rcu_data</tt> structures as well. The fields in the <tt>rcu_state</tt> structure represent the -most current values, and those of the other structures are compared -in order to detect the start of a new grace period in a distributed +most current value, and those of the other structures are compared +in order to detect the beginnings and ends of grace periods in a distributed fashion. The values flow from <tt>rcu_state</tt> to <tt>rcu_node</tt> (down the tree from the root to the leaves) to <tt>rcu_data</tt>. @@ -512,27 +507,47 @@ than to be heisenbugged out of existence. as follows: <pre> - 1 unsigned long gpnum; - 2 unsigned long completed; + 1 unsigned long gp_seq; + 2 unsigned long gp_seq_needed; </pre> -<p>These fields are the counterparts of the fields of the same name in -the <tt>rcu_state</tt> structure. -They each may lag up to one behind their <tt>rcu_state</tt> -counterparts. -If a given <tt>rcu_node</tt> structure's <tt>->gpnum</tt> and -<tt>->complete</tt> fields are equal, then this <tt>rcu_node</tt> +<p>The <tt>rcu_node</tt> structures' <tt>->gp_seq</tt> fields are +the counterparts of the field of the same name in the <tt>rcu_state</tt> +structure. +They each may lag up to one step behind their <tt>rcu_state</tt> +counterpart. +If the bottom two bits of a given <tt>rcu_node</tt> structure's +<tt>->gp_seq</tt> field is zero, then this <tt>rcu_node</tt> structure believes that RCU is idle. -Otherwise, as with the <tt>rcu_state</tt> structure, -the <tt>->gpnum</tt> field will be one greater than the -<tt>->complete</tt> fields, with <tt>->gpnum</tt> -indicating which grace period this <tt>rcu_node</tt> believes -is still being waited for. +</p><p>The <tt>>gp_seq</tt> field of each <tt>rcu_node</tt> +structure is updated at the beginning and the end +of each grace period. + +<p>The <tt>->gp_seq_needed</tt> fields record the +furthest-in-the-future grace period request seen by the corresponding +<tt>rcu_node</tt> structure. The request is considered fulfilled when +the value of the <tt>->gp_seq</tt> field equals or exceeds that of +the <tt>->gp_seq_needed</tt> field. -</p><p>The <tt>>gpnum</tt> field of each <tt>rcu_node</tt> -structure is updated at the beginning -of each grace period, and the <tt>->completed</tt> fields are -updated at the end of each grace period. +<table> +<tr><th> </th></tr> +<tr><th align="left">Quick Quiz:</th></tr> +<tr><td> + Suppose that this <tt>rcu_node</tt> structure doesn't see + a request for a very long time. + Won't wrapping of the <tt>->gp_seq</tt> field cause + problems? +</td></tr> +<tr><th align="left">Answer:</th></tr> +<tr><td bgcolor="#ffffff"><font color="ffffff"> + No, because if the <tt>->gp_seq_needed</tt> field lags behind the + <tt>->gp_seq</tt> field, the <tt>->gp_seq_needed</tt> field + will be updated at the end of the grace period. + Modulo-arithmetic comparisons therefore will always get the + correct answer, even with wrapping. +</font></td></tr> +<tr><td> </td></tr> +</table> <h5>Quiescent-State Tracking</h5> @@ -626,9 +641,8 @@ normal and expedited grace periods, respectively. </ol> <p><font color="ffffff">So the locking is absolutely required in - order to coordinate - clearing of the bits with the grace-period numbers in - <tt>->gpnum</tt> and <tt>->completed</tt>. + order to coordinate clearing of the bits with updating of the + grace-period sequence number in <tt>->gp_seq</tt>. </font></td></tr> <tr><td> </td></tr> </table> @@ -1038,15 +1052,15 @@ out any <tt>rcu_data</tt> structure for which this flag is not set. as follows: <pre> - 1 unsigned long completed; - 2 unsigned long gpnum; + 1 unsigned long gp_seq; + 2 unsigned long gp_seq_needed; 3 bool cpu_no_qs; 4 bool core_needs_qs; 5 bool gpwrap; 6 unsigned long rcu_qs_ctr_snap; </pre> -<p>The <tt>completed</tt> and <tt>gpnum</tt> +<p>The <tt>->gp_seq</tt> and <tt>->gp_seq_needed</tt> fields are the counterparts of the fields of the same name in the <tt>rcu_state</tt> and <tt>rcu_node</tt> structures. They may each lag up to one behind their <tt>rcu_node</tt> @@ -1054,15 +1068,9 @@ counterparts, but in <tt>CONFIG_NO_HZ_IDLE</tt> and <tt>CONFIG_NO_HZ_FULL</tt> kernels can lag arbitrarily far behind for CPUs in dyntick-idle mode (but these counters will catch up upon exit from dyntick-idle mode). -If a given <tt>rcu_data</tt> structure's <tt>->gpnum</tt> and -<tt>->complete</tt> fields are equal, then this <tt>rcu_data</tt> +If the lower two bits of a given <tt>rcu_data</tt> structure's +<tt>->gp_seq</tt> are zero, then this <tt>rcu_data</tt> structure believes that RCU is idle. -Otherwise, as with the <tt>rcu_state</tt> and <tt>rcu_node</tt> -structure, -the <tt>->gpnum</tt> field will be one greater than the -<tt>->complete</tt> fields, with <tt>->gpnum</tt> -indicating which grace period this <tt>rcu_data</tt> believes -is still being waited for. <table> <tr><th> </th></tr> @@ -1070,13 +1078,13 @@ is still being waited for. <tr><td> All this replication of the grace period numbers can only cause massive confusion. - Why not just keep a global pair of counters and be done with it??? + Why not just keep a global sequence number and be done with it??? </td></tr> <tr><th align="left">Answer:</th></tr> <tr><td bgcolor="#ffffff"><font color="ffffff"> - Because if there was only a single global pair of grace-period + Because if there was only a single global sequence numbers, there would need to be a single global lock to allow - safely accessing and updating them. + safely accessing and updating it. And if we are not going to have a single global lock, we need to carefully manage the numbers on a per-node basis. Recall from the answer to a previous Quick Quiz that the consequences @@ -1091,8 +1099,8 @@ CPU has not yet passed through a quiescent state, while the <tt>->core_needs_qs</tt> flag indicates that the RCU core needs a quiescent state from the corresponding CPU. The <tt>->gpwrap</tt> field indicates that the corresponding -CPU has remained idle for so long that the <tt>completed</tt> -and <tt>gpnum</tt> counters are in danger of overflow, which +CPU has remained idle for so long that the +<tt>gp_seq</tt> counter is in danger of overflow, which will cause the CPU to disregard the values of its counters on its next exit from idle. Finally, the <tt>rcu_qs_ctr_snap</tt> field is used to detect @@ -1130,10 +1138,10 @@ The CPU advances the callbacks in its <tt>rcu_data</tt> structure whenever it notices that another RCU grace period has completed. The CPU detects the completion of an RCU grace period by noticing that the value of its <tt>rcu_data</tt> structure's -<tt>->completed</tt> field differs from that of its leaf +<tt>->gp_seq</tt> field differs from that of its leaf <tt>rcu_node</tt> structure. Recall that each <tt>rcu_node</tt> structure's -<tt>->completed</tt> field is updated at the end of each +<tt>->gp_seq</tt> field is updated at the beginnings and ends of each grace period. <p> diff --git a/Documentation/RCU/Design/Memory-Ordering/Tree-RCU-Memory-Ordering.html b/Documentation/RCU/Design/Memory-Ordering/Tree-RCU-Memory-Ordering.html index 8651b0b4fd79..a346ce0116eb 100644 --- a/Documentation/RCU/Design/Memory-Ordering/Tree-RCU-Memory-Ordering.html +++ b/Documentation/RCU/Design/Memory-Ordering/Tree-RCU-Memory-Ordering.html @@ -357,7 +357,7 @@ parts, starting in this section with the various phases of grace-period initialization. <p>The first ordering-related grace-period initialization action is to -increment the <tt>rcu_state</tt> structure's <tt>->gpnum</tt> +advance the <tt>rcu_state</tt> structure's <tt>->gp_seq</tt> grace-period-number counter, as shown below: </p><p><img src="TreeRCU-gp-init-1.svg" alt="TreeRCU-gp-init-1.svg" width="75%"> @@ -388,7 +388,7 @@ its last CPU and if the next <tt>rcu_node</tt> structure has no online CPUs). <p>The final <tt>rcu_gp_init()</tt> pass through the <tt>rcu_node</tt> tree traverses breadth-first, setting each <tt>rcu_node</tt> structure's -<tt>->gpnum</tt> field to the newly incremented value from the +<tt>->gp_seq</tt> field to the newly advanced value from the <tt>rcu_state</tt> structure, as shown in the following diagram. </p><p><img src="TreeRCU-gp-init-3.svg" alt="TreeRCU-gp-init-1.svg" width="75%"> @@ -398,9 +398,9 @@ tree traverses breadth-first, setting each <tt>rcu_node</tt> structure's to notice that a new grace period has started, as described in the next section. But because the grace-period kthread started the grace period at the -root (with the increment of the <tt>rcu_state</tt> structure's -<tt>->gpnum</tt> field) before setting each leaf <tt>rcu_node</tt> -structure's <tt>->gpnum</tt> field, each CPU's observation of +root (with the advancing of the <tt>rcu_state</tt> structure's +<tt>->gp_seq</tt> field) before setting each leaf <tt>rcu_node</tt> +structure's <tt>->gp_seq</tt> field, each CPU's observation of the start of the grace period will happen after the actual start of the grace period. @@ -466,7 +466,7 @@ section that the grace period must wait on. <tr><td> But a RCU read-side critical section might have started after the beginning of the grace period - (the <tt>->gpnum++</tt> from earlier), so why should + (the advancing of <tt>->gp_seq</tt> from earlier), so why should the grace period wait on such a critical section? </td></tr> <tr><th align="left">Answer:</th></tr> @@ -609,10 +609,8 @@ states outstanding from other CPUs. <h4><a name="Grace-Period Cleanup">Grace-Period Cleanup</a></h4> <p>Grace-period cleanup first scans the <tt>rcu_node</tt> tree -breadth-first setting all the <tt>->completed</tt> fields equal -to the number of the newly completed grace period, then it sets -the <tt>rcu_state</tt> structure's <tt>->completed</tt> field, -again to the number of the newly completed grace period. +breadth-first advancing all the <tt>->gp_seq</tt> fields, then it +advances the <tt>rcu_state</tt> structure's <tt>->gp_seq</tt> field. The ordering effects are shown below: </p><p><img src="TreeRCU-gp-cleanup.svg" alt="TreeRCU-gp-cleanup.svg" width="75%"> @@ -634,7 +632,7 @@ grace-period cleanup is complete, the next grace period can begin. CPU has reported its quiescent state, but it may be some milliseconds before RCU becomes aware of this. The latest reasonable candidate is once the <tt>rcu_state</tt> - structure's <tt>->completed</tt> field has been updated, + structure's <tt>->gp_seq</tt> field has been updated, but it is quite possible that some CPUs have already completed phase two of their updates by that time. In short, if you are going to work with RCU, you need to @@ -647,7 +645,7 @@ grace-period cleanup is complete, the next grace period can begin. <h4><a name="Callback Invocation">Callback Invocation</a></h4> <p>Once a given CPU's leaf <tt>rcu_node</tt> structure's -<tt>->completed</tt> field has been updated, that CPU can begin +<tt>->gp_seq</tt> field has been updated, that CPU can begin invoking its RCU callbacks that were waiting for this grace period to end. These callbacks are identified by <tt>rcu_advance_cbs()</tt>, diff --git a/Documentation/RCU/Design/Memory-Ordering/TreeRCU-gp-cleanup.svg b/Documentation/RCU/Design/Memory-Ordering/TreeRCU-gp-cleanup.svg index 754f426b297a..bf84fbab27ee 100644 --- a/Documentation/RCU/Design/Memory-Ordering/TreeRCU-gp-cleanup.svg +++ b/Documentation/RCU/Design/Memory-Ordering/TreeRCU-gp-cleanup.svg @@ -384,11 +384,11 @@ inkscape:window-height="1144" id="namedview208" showgrid="true" - inkscape:zoom="0.70710678" - inkscape:cx="617.89017" - inkscape:cy="542.52419" - inkscape:window-x="86" - inkscape:window-y="28" + inkscape:zoom="0.78716603" + inkscape:cx="513.06403" + inkscape:cy="623.1214" + inkscape:window-x="102" + inkscape:window-y="38" inkscape:window-maximized="0" inkscape:current-layer="g3188-3" fit-margin-top="5" @@ -417,13 +417,15 @@ id="g3188"> <text xml:space="preserve" - x="3199.1516" + x="3145.9592" y="13255.592" font-style="normal" font-weight="bold" font-size="192" id="text202" - style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;font-family:Courier">->completed = ->gpnum</text> + style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;font-family:Courier"><tspan + style="font-size:172.87567139px" + id="tspan3143">rcu_seq_end(&rnp->gp_seq)</tspan></text> <g id="g3107" transform="translate(947.90548,11584.029)"> @@ -502,13 +504,15 @@ </g> <text xml:space="preserve" - x="5324.5371" - y="15414.598" + x="5264.4731" + y="15428.84" font-style="normal" font-weight="bold" font-size="192" - id="text202-753" - style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->completed = ->gpnum</text> + id="text202-36-7" + style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"><tspan + style="font-size:172.87567139px" + id="tspan3166-5">rcu_seq_end(&rnp->gp_seq)</tspan></text> </g> <g style="fill:none;stroke-width:0.025in" @@ -547,15 +551,6 @@ sodipodi:linespacing="125%"><tspan style="font-size:159.57754517px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:start;line-height:125%;writing-mode:lr-tb;text-anchor:start;font-family:Liberation Sans;-inkscape-font-specification:Liberation Sans" id="tspan3104-6-5-6-0">Leaf</tspan></text> - <text - xml:space="preserve" - x="7479.5796" - y="17699.943" - font-style="normal" - font-weight="bold" - font-size="192" - id="text202-9" - style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->completed = ->gpnum</text> <path sodipodi:nodetypes="cc" inkscape:connector-curvature="0" @@ -566,15 +561,6 @@ style="fill:none;stroke-width:0.025in" transform="translate(-737.93887,7732.6672)" id="g3188-3"> - <text - xml:space="preserve" - x="3225.7478" - y="13175.802" - font-style="normal" - font-weight="bold" - font-size="192" - id="text202-60" - style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;font-family:Courier">rsp->completed =</text> <g id="g3107-62" transform="translate(947.90548,11584.029)"> @@ -607,15 +593,6 @@ sodipodi:linespacing="125%"><tspan style="font-size:159.57754517px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:start;line-height:125%;writing-mode:lr-tb;text-anchor:start;font-family:Liberation Sans;-inkscape-font-specification:Liberation Sans" id="tspan3104-6-5-7">Root</tspan></text> - <text - xml:space="preserve" - x="3225.7478" - y="13390.038" - font-style="normal" - font-weight="bold" - font-size="192" - id="text202-60-3" - style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"> rnp->completed</text> <flowRoot xml:space="preserve" id="flowRoot3356" @@ -627,7 +604,18 @@ height="63.63961" x="332.34018" y="681.87292" /></flowRegion><flowPara - id="flowPara3362" /></flowRoot> </g> + id="flowPara3362" /></flowRoot> <text + xml:space="preserve" + x="3156.6121" + y="13317.754" + font-style="normal" + font-weight="bold" + font-size="192" + id="text202-36-6" + style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"><tspan + style="font-size:172.87567139px" + id="tspan3166-0">rcu_seq_end(&rsp->gp_seq)</tspan></text> + </g> <g style="fill:none;stroke-width:0.025in" transform="translate(-858.40227,7769.0342)" @@ -859,6 +847,17 @@ id="path3414-8-3-6-6" inkscape:connector-curvature="0" sodipodi:nodetypes="cc" /> + <text + xml:space="preserve" + x="7418.769" + y="17646.104" + font-style="normal" + font-weight="bold" + font-size="192" + id="text202-36-70" + style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"><tspan + style="font-size:172.87567139px" + id="tspan3166-93">rcu_seq_end(&rnp->gp_seq)</tspan></text> </g> <g transform="translate(-1642.5377,-11611.245)" @@ -887,13 +886,15 @@ </g> <text xml:space="preserve" - x="5327.3057" + x="5274.1133" y="15428.84" font-style="normal" font-weight="bold" font-size="192" id="text202-36" - style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->completed = ->gpnum</text> + style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"><tspan + style="font-size:172.87567139px" + id="tspan3166">rcu_seq_end(&rnp->gp_seq)</tspan></text> </g> <g transform="translate(-151.71746,-11647.612)" @@ -972,13 +973,15 @@ id="tspan3104-6-5-6-0-92">Leaf</tspan></text> <text xml:space="preserve" - x="7486.4907" - y="17670.119" + x="7408.5918" + y="17619.504" font-style="normal" font-weight="bold" font-size="192" - id="text202-6" - style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->completed = ->gpnum</text> + id="text202-36-2" + style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"><tspan + style="font-size:172.87567139px" + id="tspan3166-9">rcu_seq_end(&rnp->gp_seq)</tspan></text> </g> <g transform="translate(-6817.1997,-11647.612)" @@ -1019,13 +1022,15 @@ id="tspan3104-6-5-6-0-1">Leaf</tspan></text> <text xml:space="preserve" - x="7474.1382" - y="17688.926" + x="7416.8003" + y="17619.504" font-style="normal" font-weight="bold" font-size="192" - id="text202-5" - style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->completed = ->gpnum</text> + id="text202-36-3" + style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"><tspan + style="font-size:172.87567139px" + id="tspan3166-56">rcu_seq_end(&rnp->gp_seq)</tspan></text> </g> <path style="fill:none;stroke:#000000;stroke-width:13.29812908px;stroke-linecap:butt;stroke-linejoin:miter;stroke-opacity:1;marker-end:url(#Arrow2Lend)" @@ -1059,15 +1064,6 @@ id="path3414-8-3-6" inkscape:connector-curvature="0" sodipodi:nodetypes="cc" /> - <text - xml:space="preserve" - x="7318.9653" - y="6031.6353" - font-style="normal" - font-weight="bold" - font-size="192" - id="text202-2" - style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->completed = ->gpnum</text> <g style="fill:none;stroke-width:0.025in" id="g4504-3-9" @@ -1123,4 +1119,15 @@ id="path3134-9-0-3-5" d="m 6875.6003,15833.906 1595.7755,0" style="fill:none;stroke:#969696;stroke-width:53.19251633;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;marker-end:url(#Arrow1Send-36)" /> + <text + xml:space="preserve" + x="7275.2612" + y="5971.8916" + font-style="normal" + font-weight="bold" + font-size="192" + id="text202-36-1" + style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"><tspan + style="font-size:172.87567139px" + id="tspan3166-2">rcu_seq_end(&rnp->gp_seq)</tspan></text> </svg> diff --git a/Documentation/RCU/Design/Memory-Ordering/TreeRCU-gp-init-1.svg b/Documentation/RCU/Design/Memory-Ordering/TreeRCU-gp-init-1.svg index 0161262904ec..8c207550818f 100644 --- a/Documentation/RCU/Design/Memory-Ordering/TreeRCU-gp-init-1.svg +++ b/Documentation/RCU/Design/Memory-Ordering/TreeRCU-gp-init-1.svg @@ -272,13 +272,13 @@ inkscape:window-height="1144" id="namedview208" showgrid="true" - inkscape:zoom="0.70710678" - inkscape:cx="617.89019" - inkscape:cy="636.57143" - inkscape:window-x="697" + inkscape:zoom="2.6330492" + inkscape:cx="524.82797" + inkscape:cy="519.31194" + inkscape:window-x="79" inkscape:window-y="28" inkscape:window-maximized="0" - inkscape:current-layer="svg2" + inkscape:current-layer="g3188" fit-margin-top="5" fit-margin-right="5" fit-margin-left="5" @@ -305,13 +305,15 @@ id="g3188"> <text xml:space="preserve" - x="3305.5364" + x="3119.363" y="13255.592" font-style="normal" font-weight="bold" font-size="192" id="text202" - style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;font-family:Courier">rsp->gpnum++</text> + style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;font-family:Courier"><tspan + style="font-size:172.87567139px" + id="tspan3071">rcu_seq_start(rsp->gp_seq)</tspan></text> <g id="g3107" transform="translate(947.90548,11584.029)"> diff --git a/Documentation/RCU/Design/Memory-Ordering/TreeRCU-gp-init-3.svg b/Documentation/RCU/Design/Memory-Ordering/TreeRCU-gp-init-3.svg index de6ecc51b00e..d24d7d555dbc 100644 --- a/Documentation/RCU/Design/Memory-Ordering/TreeRCU-gp-init-3.svg +++ b/Documentation/RCU/Design/Memory-Ordering/TreeRCU-gp-init-3.svg @@ -19,7 +19,7 @@ id="svg2" version="1.1" inkscape:version="0.48.4 r9939" - sodipodi:docname="TreeRCU-gp-init-2.svg"> + sodipodi:docname="TreeRCU-gp-init-3.svg"> <metadata id="metadata212"> <rdf:RDF> @@ -257,18 +257,22 @@ inkscape:window-width="1087" inkscape:window-height="1144" id="namedview208" - showgrid="false" - inkscape:zoom="0.70710678" + showgrid="true" + inkscape:zoom="0.68224756" inkscape:cx="617.89019" inkscape:cy="625.84293" - inkscape:window-x="697" + inkscape:window-x="54" inkscape:window-y="28" inkscape:window-maximized="0" - inkscape:current-layer="svg2" + inkscape:current-layer="g3153" fit-margin-top="5" fit-margin-right="5" fit-margin-left="5" - fit-margin-bottom="5" /> + fit-margin-bottom="5"> + <inkscape:grid + type="xygrid" + id="grid3090" /> + </sodipodi:namedview> <path sodipodi:nodetypes="cccccccccccccccccccccccc" inkscape:connector-curvature="0" @@ -281,13 +285,13 @@ id="g3188"> <text xml:space="preserve" - x="3305.5364" + x="3145.9592" y="13255.592" font-style="normal" font-weight="bold" font-size="192" id="text202" - style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;font-family:Courier">->gpnum = rsp->gpnum</text> + style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;font-family:Courier">->gp_seq = rsp->gp_seq</text> <g id="g3107" transform="translate(947.90548,11584.029)"> @@ -366,13 +370,13 @@ </g> <text xml:space="preserve" - x="5392.3345" - y="15407.104" + x="5253.6904" + y="15407.032" font-style="normal" font-weight="bold" font-size="192" id="text202-6" - style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->gpnum = rsp->gpnum</text> + style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->gp_seq = rsp->gp_seq</text> </g> <g style="fill:none;stroke-width:0.025in" @@ -413,13 +417,13 @@ id="tspan3104-6-5-6-0">Leaf</tspan></text> <text xml:space="preserve" - x="7536.4883" - y="17640.934" + x="7415.4365" + y="17670.572" font-style="normal" font-weight="bold" font-size="192" id="text202-9" - style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->gpnum = rsp->gpnum</text> + style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->gp_seq = rsp->gp_seq</text> </g> <g transform="translate(-1642.5375,-11610.962)" @@ -448,13 +452,13 @@ </g> <text xml:space="preserve" - x="5378.4146" - y="15436.927" + x="5258.0688" + y="15412.313" font-style="normal" font-weight="bold" font-size="192" id="text202-3" - style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->gpnum = rsp->gpnum</text> + style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->gp_seq = rsp->gp_seq</text> </g> <g transform="translate(-151.71726,-11647.329)" @@ -533,13 +537,13 @@ id="tspan3104-6-5-6-0-92">Leaf</tspan></text> <text xml:space="preserve" - x="7520.1294" - y="17673.639" + x="7405.2607" + y="17670.572" font-style="normal" font-weight="bold" font-size="192" id="text202-35" - style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->gpnum = rsp->gpnum</text> + style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->gp_seq = rsp->gp_seq</text> </g> <g transform="translate(-6817.1998,-11647.329)" @@ -580,13 +584,13 @@ id="tspan3104-6-5-6-0-1">Leaf</tspan></text> <text xml:space="preserve" - x="7521.4663" - y="17666.062" + x="7413.4688" + y="17670.566" font-style="normal" font-weight="bold" font-size="192" id="text202-75" - style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->gpnum = rsp->gpnum</text> + style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->gp_seq = rsp->gp_seq</text> </g> <path style="fill:none;stroke:#000000;stroke-width:13.29812908px;stroke-linecap:butt;stroke-linejoin:miter;stroke-opacity:1;marker-end:url(#Arrow2Lend)" @@ -622,11 +626,11 @@ sodipodi:nodetypes="cc" /> <text xml:space="preserve" - x="7370.856" - y="5997.5972" + x="7271.9297" + y="6023.2412" font-style="normal" font-weight="bold" font-size="192" id="text202-62" - style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->gpnum = rsp->gpnum</text> + style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->gp_seq = rsp->gp_seq</text> </svg> diff --git a/Documentation/RCU/Design/Memory-Ordering/TreeRCU-gp.svg b/Documentation/RCU/Design/Memory-Ordering/TreeRCU-gp.svg index b13b7b01bb3a..acd73c7ad0f4 100644 --- a/Documentation/RCU/Design/Memory-Ordering/TreeRCU-gp.svg +++ b/Documentation/RCU/Design/Memory-Ordering/TreeRCU-gp.svg @@ -1070,13 +1070,13 @@ inkscape:window-height="1144" id="namedview208" showgrid="true" - inkscape:zoom="0.6004608" - inkscape:cx="826.65969" - inkscape:cy="483.3047" - inkscape:window-x="66" - inkscape:window-y="28" + inkscape:zoom="0.81932583" + inkscape:cx="840.45848" + inkscape:cy="5052.4242" + inkscape:window-x="787" + inkscape:window-y="24" inkscape:window-maximized="0" - inkscape:current-layer="svg2" + inkscape:current-layer="g4" fit-margin-top="5" fit-margin-right="5" fit-margin-left="5" @@ -1543,15 +1543,6 @@ style="fill:none;stroke-width:0.025in" transform="translate(1749.0282,658.72243)" id="g3188"> - <text - xml:space="preserve" - x="3305.5364" - y="13255.592" - font-style="normal" - font-weight="bold" - font-size="192" - id="text202-5" - style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;font-family:Courier">rsp->gpnum++</text> <g id="g3107-62" transform="translate(947.90548,11584.029)"> @@ -1584,6 +1575,17 @@ sodipodi:linespacing="125%"><tspan style="font-size:159.57754517px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:start;line-height:125%;writing-mode:lr-tb;text-anchor:start;font-family:Liberation Sans;-inkscape-font-specification:Liberation Sans" id="tspan3104-6-5-7">Root</tspan></text> + <text + xml:space="preserve" + x="3137.9988" + y="13271.316" + font-style="normal" + font-weight="bold" + font-size="192" + id="text202-626" + style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"><tspan + style="font-size:172.87567139px" + id="tspan3071">rcu_seq_start(rsp->gp_seq)</tspan></text> </g> <rect ry="0" @@ -2318,15 +2320,6 @@ style="fill:none;stroke-width:0.025in" transform="translate(1739.0986,17188.625)" id="g3188-6"> - <text - xml:space="preserve" - x="3305.5364" - y="13255.592" - font-style="normal" - font-weight="bold" - font-size="192" - id="text202-1" - style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;font-family:Courier">->gpnum = rsp->gpnum</text> <g id="g3107-5" transform="translate(947.90548,11584.029)"> @@ -2359,6 +2352,15 @@ sodipodi:linespacing="125%"><tspan style="font-size:159.57754517px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:start;line-height:125%;writing-mode:lr-tb;text-anchor:start;font-family:Liberation Sans;-inkscape-font-specification:Liberation Sans" id="tspan3104-6-5-1">Root</tspan></text> + <text + xml:space="preserve" + x="3147.9268" + y="13240.524" + font-style="normal" + font-weight="bold" + font-size="192" + id="text202-1" + style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->gp_seq = rsp->gp_seq</text> </g> <g style="fill:none;stroke-width:0.025in" @@ -2387,13 +2389,13 @@ </g> <text xml:space="preserve" - x="5392.3345" - y="15407.104" + x="5263.1094" + y="15411.646" font-style="normal" font-weight="bold" font-size="192" - id="text202-6-7" - style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->gpnum = rsp->gpnum</text> + id="text202-92" + style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->gp_seq = rsp->gp_seq</text> </g> <g style="fill:none;stroke-width:0.025in" @@ -2434,13 +2436,13 @@ id="tspan3104-6-5-6-0-94">Leaf</tspan></text> <text xml:space="preserve" - x="7536.4883" - y="17640.934" + x="7417.4053" + y="17655.502" font-style="normal" font-weight="bold" font-size="192" - id="text202-9" - style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->gpnum = rsp->gpnum</text> + id="text202-759" + style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->gp_seq = rsp->gp_seq</text> </g> <g transform="translate(-2353.8462,17224.992)" @@ -2469,13 +2471,13 @@ </g> <text xml:space="preserve" - x="5378.4146" - y="15436.927" + x="5246.1548" + y="15411.648" font-style="normal" font-weight="bold" font-size="192" - id="text202-3" - style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->gpnum = rsp->gpnum</text> + id="text202-87" + style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->gp_seq = rsp->gp_seq</text> </g> <g transform="translate(-863.02613,17188.625)" @@ -2554,13 +2556,13 @@ id="tspan3104-6-5-6-0-92-6">Leaf</tspan></text> <text xml:space="preserve" - x="7520.1294" - y="17673.639" + x="7433.8257" + y="17682.098" font-style="normal" font-weight="bold" font-size="192" - id="text202-35" - style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->gpnum = rsp->gpnum</text> + id="text202-2" + style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->gp_seq = rsp->gp_seq</text> </g> <g transform="translate(-7528.5085,17188.625)" @@ -2601,13 +2603,13 @@ id="tspan3104-6-5-6-0-1-8">Leaf</tspan></text> <text xml:space="preserve" - x="7521.4663" - y="17666.062" + x="7415.4404" + y="17682.098" font-style="normal" font-weight="bold" font-size="192" - id="text202-75-1" - style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->gpnum = rsp->gpnum</text> + id="text202-0" + style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->gp_seq = rsp->gp_seq</text> </g> <path style="fill:none;stroke:#000000;stroke-width:13.29812813px;stroke-linecap:butt;stroke-linejoin:miter;stroke-opacity:1;marker-end:url(#Arrow2Lend)" @@ -2641,15 +2643,6 @@ id="path3414-8-3-6-4" inkscape:connector-curvature="0" sodipodi:nodetypes="cc" /> - <text - xml:space="preserve" - x="6659.5469" - y="34833.551" - font-style="normal" - font-weight="bold" - font-size="192" - id="text202-62" - style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->gpnum = rsp->gpnum</text> <path sodipodi:nodetypes="ccc" inkscape:connector-curvature="0" @@ -3844,7 +3837,7 @@ font-weight="bold" font-size="192" id="text202-6-6-5" - style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">rdp->gpnum</text> + style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">rdp->gp_seq</text> <text xml:space="preserve" x="5035.4155" @@ -4284,15 +4277,6 @@ style="fill:none;stroke-width:0.025in" transform="translate(1874.038,53203.538)" id="g3188-7"> - <text - xml:space="preserve" - x="3199.1516" - y="13255.592" - font-style="normal" - font-weight="bold" - font-size="192" - id="text202-82" - style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;font-family:Courier">->completed = ->gpnum</text> <g id="g3107-53" transform="translate(947.90548,11584.029)"> @@ -4325,6 +4309,17 @@ sodipodi:linespacing="125%"><tspan style="font-size:159.57754517px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:start;line-height:125%;writing-mode:lr-tb;text-anchor:start;font-family:Liberation Sans;-inkscape-font-specification:Liberation Sans" id="tspan3104-6-5-19">Root</tspan></text> + <text + xml:space="preserve" + x="3175.896" + y="13240.11" + font-style="normal" + font-weight="bold" + font-size="192" + id="text202-36-3" + style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"><tspan + style="font-size:172.87567139px" + id="tspan3166">rcu_seq_end(&rnp->gp_seq)</tspan></text> </g> <rect ry="0" @@ -4371,13 +4366,15 @@ </g> <text xml:space="preserve" - x="5324.5371" - y="15414.598" + x="5264.4829" + y="15411.231" font-style="normal" font-weight="bold" font-size="192" - id="text202-753" - style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->completed = ->gpnum</text> + id="text202-36-7" + style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"><tspan + style="font-size:172.87567139px" + id="tspan3166-5">rcu_seq_end(&rnp->gp_seq)</tspan></text> </g> <g style="fill:none;stroke-width:0.025in" @@ -4412,30 +4409,12 @@ sodipodi:linespacing="125%"><tspan style="font-size:159.57754517px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:start;line-height:125%;writing-mode:lr-tb;text-anchor:start;font-family:Liberation Sans;-inkscape-font-specification:Liberation Sans" id="tspan3104-6-5-6-0-4">Leaf</tspan></text> - <text - xml:space="preserve" - x="10084.225" - y="70903.312" - font-style="normal" - font-weight="bold" - font-size="192" - id="text202-9-0" - style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->completed = ->gpnum</text> <path sodipodi:nodetypes="ccc" inkscape:connector-curvature="0" id="path3134-9-0-3-9" d="m 6315.6122,72629.054 -20.9533,8108.684 1648.968,0" style="fill:none;stroke:#969696;stroke-width:53.19251251;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;marker-end:url(#Arrow1Send)" /> - <text - xml:space="preserve" - x="5092.4683" - y="74111.672" - font-style="normal" - font-weight="bold" - font-size="192" - id="text202-60" - style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">rsp->completed =</text> <g style="fill:none;stroke-width:0.025in" id="g3107-62-6" @@ -4469,15 +4448,6 @@ sodipodi:linespacing="125%"><tspan style="font-size:159.57754517px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:start;line-height:125%;writing-mode:lr-tb;text-anchor:start;font-family:Liberation Sans;-inkscape-font-specification:Liberation Sans" id="tspan3104-6-5-7-7">Root</tspan></text> - <text - xml:space="preserve" - x="5092.4683" - y="74325.906" - font-style="normal" - font-weight="bold" - font-size="192" - id="text202-60-3" - style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"> rnp->completed</text> <g style="fill:none;stroke-width:0.025in" transform="translate(1746.2528,60972.572)" @@ -4736,13 +4706,15 @@ </g> <text xml:space="preserve" - x="5327.3057" - y="15428.84" + x="5274.1216" + y="15411.231" font-style="normal" font-weight="bold" font-size="192" id="text202-36" - style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->completed = ->gpnum</text> + style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"><tspan + style="font-size:172.87567139px" + id="tspan3166-6">rcu_seq_end(&rnp->gp_seq)</tspan></text> </g> <g transform="translate(-728.08545,53203.538)" @@ -4821,13 +4793,15 @@ id="tspan3104-6-5-6-0-92-5">Leaf</tspan></text> <text xml:space="preserve" - x="7486.4907" - y="17670.119" + x="7435.1987" + y="17708.281" font-style="normal" font-weight="bold" font-size="192" - id="text202-6-2" - style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->completed = ->gpnum</text> + id="text202-36-9" + style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"><tspan + style="font-size:172.87567139px" + id="tspan3166-1">rcu_seq_end(&rnp->gp_seq)</tspan></text> </g> <g transform="translate(-7393.5687,53203.538)" @@ -4868,13 +4842,15 @@ id="tspan3104-6-5-6-0-1-5">Leaf</tspan></text> <text xml:space="preserve" - x="7474.1382" - y="17688.926" + x="7416.8125" + y="17708.281" font-style="normal" font-weight="bold" font-size="192" - id="text202-5-1" - style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->completed = ->gpnum</text> + id="text202-36-35" + style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"><tspan + style="font-size:172.87567139px" + id="tspan3166-62">rcu_seq_end(&rnp->gp_seq)</tspan></text> </g> <path style="fill:none;stroke:#000000;stroke-width:13.29812813px;stroke-linecap:butt;stroke-linejoin:miter;stroke-opacity:1;marker-end:url(#Arrow2Lend)" @@ -4908,15 +4884,6 @@ id="path3414-8-3-6-67" inkscape:connector-curvature="0" sodipodi:nodetypes="cc" /> - <text - xml:space="preserve" - x="6742.6001" - y="70882.617" - font-style="normal" - font-weight="bold" - font-size="192" - id="text202-2" - style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->completed = ->gpnum</text> <g style="fill:none;stroke-width:0.025in" id="g4504-3-9-6" @@ -5131,5 +5098,47 @@ font-size="192" id="text202-7-9-6-6-7" style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">rcu_do_batch()</text> + <text + xml:space="preserve" + x="6698.9019" + y="70885.211" + font-style="normal" + font-weight="bold" + font-size="192" + id="text202-36-2" + style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"><tspan + style="font-size:172.87567139px" + id="tspan3166-7">rcu_seq_end(&rnp->gp_seq)</tspan></text> + <text + xml:space="preserve" + x="10023.457" + y="70885.234" + font-style="normal" + font-weight="bold" + font-size="192" + id="text202-36-0" + style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"><tspan + style="font-size:172.87567139px" + id="tspan3166-9">rcu_seq_end(&rnp->gp_seq)</tspan></text> + <text + xml:space="preserve" + x="5023.3389" + y="74209.773" + font-style="normal" + font-weight="bold" + font-size="192" + id="text202-36-36" + style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"><tspan + style="font-size:172.87567139px" + id="tspan3166-0">rcu_seq_end(&rsp->gp_seq)</tspan></text> + <text + xml:space="preserve" + x="6562.5884" + y="34870.727" + font-style="normal" + font-weight="bold" + font-size="192" + id="text202-3" + style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">->gp_seq = rsp->gp_seq</text> </g> </svg> diff --git a/Documentation/RCU/Design/Memory-Ordering/TreeRCU-qs.svg b/Documentation/RCU/Design/Memory-Ordering/TreeRCU-qs.svg index de3992f4cbe1..149bec2a4493 100644 --- a/Documentation/RCU/Design/Memory-Ordering/TreeRCU-qs.svg +++ b/Documentation/RCU/Design/Memory-Ordering/TreeRCU-qs.svg @@ -300,13 +300,13 @@ inkscape:window-height="1144" id="namedview208" showgrid="true" - inkscape:zoom="0.70710678" - inkscape:cx="616.47598" - inkscape:cy="595.41964" - inkscape:window-x="813" + inkscape:zoom="0.96484375" + inkscape:cx="507.0191" + inkscape:cy="885.62207" + inkscape:window-x="47" inkscape:window-y="28" inkscape:window-maximized="0" - inkscape:current-layer="g4405" + inkscape:current-layer="g3115" fit-margin-top="5" fit-margin-right="5" fit-margin-left="5" @@ -710,7 +710,7 @@ font-weight="bold" font-size="192" id="text202-6-6" - style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">rdp->gpnum</text> + style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">rdp->gp_seq</text> <text xml:space="preserve" x="5035.4155" diff --git a/Documentation/RCU/stallwarn.txt b/Documentation/RCU/stallwarn.txt index 4259f95c3261..f99cf11b314b 100644 --- a/Documentation/RCU/stallwarn.txt +++ b/Documentation/RCU/stallwarn.txt @@ -172,7 +172,7 @@ it will print a message similar to the following: INFO: rcu_sched detected stalls on CPUs/tasks: 2-...: (3 GPs behind) idle=06c/0/0 softirq=1453/1455 fqs=0 16-...: (0 ticks this GP) idle=81c/0/0 softirq=764/764 fqs=0 - (detected by 32, t=2603 jiffies, g=7073, c=7072, q=625) + (detected by 32, t=2603 jiffies, g=7075, q=625) This message indicates that CPU 32 detected that CPUs 2 and 16 were both causing stalls, and that the stall was affecting RCU-sched. This message @@ -215,11 +215,10 @@ CPU since the last time that this CPU noted the beginning of a grace period. The "detected by" line indicates which CPU detected the stall (in this -case, CPU 32), how many jiffies have elapsed since the start of the -grace period (in this case 2603), the number of the last grace period -to start and to complete (7073 and 7072, respectively), and an estimate -of the total number of RCU callbacks queued across all CPUs (625 in -this case). +case, CPU 32), how many jiffies have elapsed since the start of the grace +period (in this case 2603), the grace-period sequence number (7075), and +an estimate of the total number of RCU callbacks queued across all CPUs +(625 in this case). In kernels with CONFIG_RCU_FAST_NO_HZ, more information is printed for each CPU: @@ -266,15 +265,16 @@ If the relevant grace-period kthread has been unable to run prior to the stall warning, as was the case in the "All QSes seen" line above, the following additional line is printed: - kthread starved for 23807 jiffies! g7073 c7072 f0x0 RCU_GP_WAIT_FQS(3) ->state=0x1 + kthread starved for 23807 jiffies! g7075 f0x0 RCU_GP_WAIT_FQS(3) ->state=0x1 ->cpu=5 Starving the grace-period kthreads of CPU time can of course result in RCU CPU stall warnings even when all CPUs and tasks have passed -through the required quiescent states. The "g" and "c" numbers flag the -number of the last grace period started and completed, respectively, -the "f" precedes the ->gp_flags command to the grace-period kthread, -the "RCU_GP_WAIT_FQS" indicates that the kthread is waiting for a short -timeout, and the "state" precedes value of the task_struct ->state field. +through the required quiescent states. The "g" number shows the current +grace-period sequence number, the "f" precedes the ->gp_flags command +to the grace-period kthread, the "RCU_GP_WAIT_FQS" indicates that the +kthread is waiting for a short timeout, the "state" precedes value of the +task_struct ->state field, and the "cpu" indicates that the grace-period +kthread last ran on CPU 5. Multiple Warnings From One Stall diff --git a/Documentation/RCU/whatisRCU.txt b/Documentation/RCU/whatisRCU.txt index 65eb856526b7..c2a7facf7ff9 100644 --- a/Documentation/RCU/whatisRCU.txt +++ b/Documentation/RCU/whatisRCU.txt @@ -588,6 +588,7 @@ It is extremely simple: void synchronize_rcu(void) { write_lock(&rcu_gp_mutex); + smp_mb__after_spinlock(); write_unlock(&rcu_gp_mutex); } @@ -609,12 +610,15 @@ don't forget about them when submitting patches making use of RCU!] The rcu_read_lock() and rcu_read_unlock() primitive read-acquire and release a global reader-writer lock. The synchronize_rcu() -primitive write-acquires this same lock, then immediately releases -it. This means that once synchronize_rcu() exits, all RCU read-side -critical sections that were in progress before synchronize_rcu() was -called are guaranteed to have completed -- there is no way that -synchronize_rcu() would have been able to write-acquire the lock -otherwise. +primitive write-acquires this same lock, then releases it. This means +that once synchronize_rcu() exits, all RCU read-side critical sections +that were in progress before synchronize_rcu() was called are guaranteed +to have completed -- there is no way that synchronize_rcu() would have +been able to write-acquire the lock otherwise. The smp_mb__after_spinlock() +promotes synchronize_rcu() to a full memory barrier in compliance with +the "Memory-Barrier Guarantees" listed in: + + Documentation/RCU/Design/Requirements/Requirements.html. It is possible to nest rcu_read_lock(), since reader-writer locks may be recursively acquired. Note also that rcu_read_lock() is immune @@ -816,11 +820,13 @@ RCU list traversal: list_next_rcu list_for_each_entry_rcu list_for_each_entry_continue_rcu + list_for_each_entry_from_rcu hlist_first_rcu hlist_next_rcu hlist_pprev_rcu hlist_for_each_entry_rcu hlist_for_each_entry_rcu_bh + hlist_for_each_entry_from_rcu hlist_for_each_entry_continue_rcu hlist_for_each_entry_continue_rcu_bh hlist_nulls_first_rcu diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 533ff5c68970..c370f5f0eb38 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -3632,8 +3632,8 @@ Set time (s) after boot for CPU-hotplug testing. rcutorture.onoff_interval= [KNL] - Set time (s) between CPU-hotplug operations, or - zero to disable CPU-hotplug testing. + Set time (jiffies) between CPU-hotplug operations, + or zero to disable CPU-hotplug testing. rcutorture.shuffle_interval= [KNL] Set task-shuffle interval (s). Shuffling tasks diff --git a/Documentation/core-api/atomic_ops.rst b/Documentation/core-api/atomic_ops.rst index 2e7165f86f55..724583453e1f 100644 --- a/Documentation/core-api/atomic_ops.rst +++ b/Documentation/core-api/atomic_ops.rst @@ -29,7 +29,7 @@ updated by one CPU, local_t is probably more appropriate. Please see local_t. The first operations to implement for atomic_t's are the initializers and -plain reads. :: +plain writes. :: #define ATOMIC_INIT(i) { (i) } #define atomic_set(v, i) ((v)->counter = (i)) diff --git a/Documentation/devicetree/bindings/interrupt-controller/ingenic,intc.txt b/Documentation/devicetree/bindings/interrupt-controller/ingenic,intc.txt index 5f89fb635a1b..f97fd8ab5e45 100644 --- a/Documentation/devicetree/bindings/interrupt-controller/ingenic,intc.txt +++ b/Documentation/devicetree/bindings/interrupt-controller/ingenic,intc.txt @@ -4,6 +4,7 @@ Required properties: - compatible : should be "ingenic,<socname>-intc". Valid strings are: ingenic,jz4740-intc + ingenic,jz4725b-intc ingenic,jz4770-intc ingenic,jz4775-intc ingenic,jz4780-intc diff --git a/Documentation/devicetree/bindings/interrupt-controller/renesas,irqc.txt b/Documentation/devicetree/bindings/interrupt-controller/renesas,irqc.txt index 20f121daa910..697ca2f26d1b 100644 --- a/Documentation/devicetree/bindings/interrupt-controller/renesas,irqc.txt +++ b/Documentation/devicetree/bindings/interrupt-controller/renesas,irqc.txt @@ -7,6 +7,7 @@ Required properties: - "renesas,irqc-r8a73a4" (R-Mobile APE6) - "renesas,irqc-r8a7743" (RZ/G1M) - "renesas,irqc-r8a7745" (RZ/G1E) + - "renesas,irqc-r8a77470" (RZ/G1C) - "renesas,irqc-r8a7790" (R-Car H2) - "renesas,irqc-r8a7791" (R-Car M2-W) - "renesas,irqc-r8a7792" (R-Car V2H) @@ -16,6 +17,7 @@ Required properties: - "renesas,intc-ex-r8a7796" (R-Car M3-W) - "renesas,intc-ex-r8a77965" (R-Car M3-N) - "renesas,intc-ex-r8a77970" (R-Car V3M) + - "renesas,intc-ex-r8a77980" (R-Car V3H) - "renesas,intc-ex-r8a77995" (R-Car D3) - #interrupt-cells: has to be <2>: an interrupt index and flags, as defined in interrupts.txt in this directory diff --git a/Documentation/devicetree/bindings/timer/mediatek,mtk-timer.txt b/Documentation/devicetree/bindings/timer/mediatek,mtk-timer.txt index b1fe7e9de1b4..18d4d0166c76 100644 --- a/Documentation/devicetree/bindings/timer/mediatek,mtk-timer.txt +++ b/Documentation/devicetree/bindings/timer/mediatek,mtk-timer.txt @@ -1,19 +1,25 @@ -Mediatek MT6577, MT6572 and MT6589 Timers ---------------------------------------- +Mediatek Timers +--------------- + +Mediatek SoCs have two different timers on different platforms, +- GPT (General Purpose Timer) +- SYST (System Timer) + +The proper timer will be selected automatically by driver. Required properties: - compatible should contain: - * "mediatek,mt2701-timer" for MT2701 compatible timers - * "mediatek,mt6580-timer" for MT6580 compatible timers - * "mediatek,mt6589-timer" for MT6589 compatible timers - * "mediatek,mt7623-timer" for MT7623 compatible timers - * "mediatek,mt8127-timer" for MT8127 compatible timers - * "mediatek,mt8135-timer" for MT8135 compatible timers - * "mediatek,mt8173-timer" for MT8173 compatible timers - * "mediatek,mt6577-timer" for MT6577 and all above compatible timers -- reg: Should contain location and length for timers register. -- clocks: Clocks driving the timer hardware. This list should include two - clocks. The order is system clock and as second clock the RTC clock. + * "mediatek,mt2701-timer" for MT2701 compatible timers (GPT) + * "mediatek,mt6580-timer" for MT6580 compatible timers (GPT) + * "mediatek,mt6589-timer" for MT6589 compatible timers (GPT) + * "mediatek,mt7623-timer" for MT7623 compatible timers (GPT) + * "mediatek,mt8127-timer" for MT8127 compatible timers (GPT) + * "mediatek,mt8135-timer" for MT8135 compatible timers (GPT) + * "mediatek,mt8173-timer" for MT8173 compatible timers (GPT) + * "mediatek,mt6577-timer" for MT6577 and all above compatible timers (GPT) + * "mediatek,mt6765-timer" for MT6765 compatible timers (SYST) +- reg: Should contain location and length for timer register. +- clocks: Should contain system clock. Examples: @@ -21,5 +27,5 @@ Examples: compatible = "mediatek,mt6577-timer"; reg = <0x10008000 0x80>; interrupts = <GIC_SPI 113 IRQ_TYPE_LEVEL_LOW>; - clocks = <&system_clk>, <&rtc_clk>; + clocks = <&system_clk>; }; diff --git a/Documentation/kprobes.txt b/Documentation/kprobes.txt index cb3b0de83fc6..10f4499e677c 100644 --- a/Documentation/kprobes.txt +++ b/Documentation/kprobes.txt @@ -80,6 +80,26 @@ After the instruction is single-stepped, Kprobes executes the "post_handler," if any, that is associated with the kprobe. Execution then continues with the instruction following the probepoint. +Changing Execution Path +----------------------- + +Since kprobes can probe into a running kernel code, it can change the +register set, including instruction pointer. This operation requires +maximum care, such as keeping the stack frame, recovering the execution +path etc. Since it operates on a running kernel and needs deep knowledge +of computer architecture and concurrent computing, you can easily shoot +your foot. + +If you change the instruction pointer (and set up other related +registers) in pre_handler, you must return !0 so that kprobes stops +single stepping and just returns to the given address. +This also means post_handler should not be called anymore. + +Note that this operation may be harder on some architectures which use +TOC (Table of Contents) for function call, since you have to setup a new +TOC for your function in your module, and recover the old one after +returning from it. + Return Probes ------------- @@ -262,7 +282,7 @@ is optimized, that modification is ignored. Thus, if you want to tweak the kernel's execution path, you need to suppress optimization, using one of the following techniques: -- Specify an empty function for the kprobe's post_handler or break_handler. +- Specify an empty function for the kprobe's post_handler. or @@ -474,7 +494,7 @@ error occurs during registration, all probes in the array, up to the bad probe, are safely unregistered before the register_*probes function returns. -- kps/rps/jps: an array of pointers to ``*probe`` data structures +- kps/rps: an array of pointers to ``*probe`` data structures - num: the number of the array entries. .. note:: @@ -566,12 +586,11 @@ the same handler) may run concurrently on different CPUs. Kprobes does not use mutexes or allocate memory except during registration and unregistration. -Probe handlers are run with preemption disabled. Depending on the -architecture and optimization state, handlers may also run with -interrupts disabled (e.g., kretprobe handlers and optimized kprobe -handlers run without interrupt disabled on x86/x86-64). In any case, -your handler should not yield the CPU (e.g., by attempting to acquire -a semaphore). +Probe handlers are run with preemption disabled or interrupt disabled, +which depends on the architecture and optimization state. (e.g., +kretprobe handlers and optimized kprobe handlers run without interrupt +disabled on x86/x86-64). In any case, your handler should not yield +the CPU (e.g., by attempting to acquire a semaphore, or waiting I/O). Since a return probe is implemented by replacing the return address with the trampoline's address, stack backtraces and calls diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt index a02d6bbfc9d0..0d8d7ef131e9 100644 --- a/Documentation/memory-barriers.txt +++ b/Documentation/memory-barriers.txt @@ -2179,32 +2179,41 @@ or: event_indicated = 1; wake_up_process(event_daemon); -A write memory barrier is implied by wake_up() and co. if and only if they -wake something up. The barrier occurs before the task state is cleared, and so -sits between the STORE to indicate the event and the STORE to set TASK_RUNNING: +A general memory barrier is executed by wake_up() if it wakes something up. +If it doesn't wake anything up then a memory barrier may or may not be +executed; you must not rely on it. The barrier occurs before the task state +is accessed, in particular, it sits between the STORE to indicate the event +and the STORE to set TASK_RUNNING: - CPU 1 CPU 2 + CPU 1 (Sleeper) CPU 2 (Waker) =============================== =============================== set_current_state(); STORE event_indicated smp_store_mb(); wake_up(); - STORE current->state <write barrier> - <general barrier> STORE current->state - LOAD event_indicated + STORE current->state ... + <general barrier> <general barrier> + LOAD event_indicated if ((LOAD task->state) & TASK_NORMAL) + STORE task->state -To repeat, this write memory barrier is present if and only if something -is actually awakened. To see this, consider the following sequence of -events, where X and Y are both initially zero: +where "task" is the thread being woken up and it equals CPU 1's "current". + +To repeat, a general memory barrier is guaranteed to be executed by wake_up() +if something is actually awakened, but otherwise there is no such guarantee. +To see this, consider the following sequence of events, where X and Y are both +initially zero: CPU 1 CPU 2 =============================== =============================== - X = 1; STORE event_indicated + X = 1; Y = 1; smp_mb(); wake_up(); - Y = 1; wait_event(wq, Y == 1); - wake_up(); load from Y sees 1, no memory barrier - load from X might see 0 + LOAD Y LOAD X + +If a wakeup does occur, one (at least) of the two loads must see 1. If, on +the other hand, a wakeup does not occur, both loads might see 0. -In contrast, if a wakeup does occur, CPU 2's load from X would be guaranteed -to see 1. +wake_up_process() always executes a general memory barrier. The barrier again +occurs before the task state is accessed. In particular, if the wake_up() in +the previous snippet were replaced by a call to wake_up_process() then one of +the two loads would be guaranteed to see 1. The available waker functions include: @@ -2224,6 +2233,8 @@ The available waker functions include: wake_up_poll(); wake_up_process(); +In terms of memory ordering, these functions all provide the same guarantees of +a wake_up() (or stronger). [!] Note that the memory barriers implied by the sleeper and the waker do _not_ order multiple stores before the wake-up with respect to loads of those stored diff --git a/Documentation/translations/ko_KR/memory-barriers.txt b/Documentation/translations/ko_KR/memory-barriers.txt index 921739d00f69..7f01fb1c1084 100644 --- a/Documentation/translations/ko_KR/memory-barriers.txt +++ b/Documentation/translations/ko_KR/memory-barriers.txt @@ -1891,22 +1891,22 @@ Mandatory ë°°ë¦¬ì–´ë“¤ì€ SMP 시스템ì—ì„œë„ UP 시스템ì—ì„œë„ SMP íš¨ê³ /* ì†Œìœ ê¶Œì„ ìˆ˜ì • */ desc->status = DEVICE_OWN; - /* MMIO 를 통해 디바ì´ìŠ¤ì— 공지를 하기 ì „ì— ë©”ëª¨ë¦¬ë¥¼ ë™ê¸°í™” */ - wmb(); - /* ì—…ë°ì´íŠ¸ëœ 디스í¬ë¦½í„°ì˜ 디바ì´ìŠ¤ì— 공지 */ writel(DESC_NOTIFY, doorbell); } dma_rmb() 는 디스í¬ë¦½í„°ë¡œë¶€í„° ë°ì´í„°ë¥¼ ì½ì–´ì˜¤ê¸° ì „ì— ë””ë°”ì´ìŠ¤ê°€ ì†Œìœ ê¶Œì„ - 내놓았ìŒì„ 보장하게 í•˜ê³ , dma_wmb() 는 디바ì´ìŠ¤ê°€ ìžì‹ ì´ ì†Œìœ ê¶Œì„ ë‹¤ì‹œ - 가졌ìŒì„ 보기 ì „ì— ë””ìŠ¤í¬ë¦½í„°ì— ë°ì´í„°ê°€ 쓰였ìŒì„ 보장합니다. wmb() 는 - ìºì‹œ ì¼ê´€ì„±ì´ 없는 (cache incoherent) MMIO ì˜ì—ì— ì“°ê¸°ë¥¼ ì‹œë„하기 ì „ì— - ìºì‹œ ì¼ê´€ì„±ì´ 있는 메모리 (cache coherent memory) 쓰기가 완료ë˜ì—ˆìŒì„ - 보장해주기 위해 필요합니다. - - consistent memory ì— ëŒ€í•œ ìžì„¸í•œ ë‚´ìš©ì„ ìœ„í•´ì„ Documentation/DMA-API.txt - 문서를 ì°¸ê³ í•˜ì„¸ìš”. + ë‚´ë ¤ë†“ì•˜ì„ ê²ƒì„ ë³´ìž¥í•˜ê³ , dma_wmb() 는 디바ì´ìŠ¤ê°€ ìžì‹ ì´ ì†Œìœ ê¶Œì„ ë‹¤ì‹œ + 가졌ìŒì„ 보기 ì „ì— ë””ìŠ¤í¬ë¦½í„°ì— ë°ì´í„°ê°€ ì“°ì˜€ì„ ê²ƒì„ ë³´ìž¥í•©ë‹ˆë‹¤. ì°¸ê³ ë¡œ, + writel() ì„ ì‚¬ìš©í•˜ë©´ ìºì‹œ ì¼ê´€ì„±ì´ 있는 메모리 (cache coherent memory) + 쓰기가 MMIO ì˜ì—ì—ì˜ ì“°ê¸° ì „ì— ì™„ë£Œë˜ì—ˆì„ ê²ƒì„ ë³´ìž¥í•˜ë¯€ë¡œ writel() ì•žì— + wmb() 를 ì‹¤í–‰í• í•„ìš”ê°€ ì—†ìŒì„ 알아ë‘시기 ë°”ëžë‹ˆë‹¤. writel() 보다 ë¹„ìš©ì´ + ì €ë ´í•œ writel_relaxed() 는 ì´ëŸ° ë³´ìž¥ì„ ì œê³µí•˜ì§€ 않으므로 ì—¬ê¸°ì„ ì‚¬ìš©ë˜ì§€ + 않아야 합니다. + + writel_relaxed() 와 ê°™ì€ ì™„í™”ëœ I/O ì ‘ê·¼ìžë“¤ì— 대한 ìžì„¸í•œ ë‚´ìš©ì„ ìœ„í•´ì„œëŠ” + "ì»¤ë„ I/O ë°°ë¦¬ì–´ì˜ íš¨ê³¼" 섹션ì„, consistent memory ì— ëŒ€í•œ ìžì„¸í•œ ë‚´ìš©ì„ + ìœ„í•´ì„ Documentation/DMA-API.txt 문서를 ì°¸ê³ í•˜ì„¸ìš”. MMIO 쓰기 배리어 diff --git a/Documentation/x86/intel_rdt_ui.txt b/Documentation/x86/intel_rdt_ui.txt index a16aa2113840..f662d3c530e5 100644 --- a/Documentation/x86/intel_rdt_ui.txt +++ b/Documentation/x86/intel_rdt_ui.txt @@ -29,7 +29,11 @@ mount options are: L2 and L3 CDP are controlled seperately. RDT features are orthogonal. A particular system may support only -monitoring, only control, or both monitoring and control. +monitoring, only control, or both monitoring and control. Cache +pseudo-locking is a unique way of using cache control to "pin" or +"lock" data in the cache. Details can be found in +"Cache Pseudo-Locking". + The mount succeeds if either of allocation or monitoring is present, but only those files and directories supported by the system will be created. @@ -65,6 +69,29 @@ related to allocation: some platforms support devices that have their own settings for cache use which can over-ride these bits. +"bit_usage": Annotated capacity bitmasks showing how all + instances of the resource are used. The legend is: + "0" - Corresponding region is unused. When the system's + resources have been allocated and a "0" is found + in "bit_usage" it is a sign that resources are + wasted. + "H" - Corresponding region is used by hardware only + but available for software use. If a resource + has bits set in "shareable_bits" but not all + of these bits appear in the resource groups' + schematas then the bits appearing in + "shareable_bits" but no resource group will + be marked as "H". + "X" - Corresponding region is available for sharing and + used by hardware and software. These are the + bits that appear in "shareable_bits" as + well as a resource group's allocation. + "S" - Corresponding region is used by software + and available for sharing. + "E" - Corresponding region is used exclusively by + one resource group. No sharing allowed. + "P" - Corresponding region is pseudo-locked. No + sharing allowed. Memory bandwitdh(MB) subdirectory contains the following files with respect to allocation: @@ -151,6 +178,9 @@ All groups contain the following files: CPUs to/from this group. As with the tasks file a hierarchy is maintained where MON groups may only include CPUs owned by the parent CTRL_MON group. + When the resouce group is in pseudo-locked mode this file will + only be readable, reflecting the CPUs associated with the + pseudo-locked region. "cpus_list": @@ -163,6 +193,21 @@ When control is enabled all CTRL_MON groups will also contain: A list of all the resources available to this group. Each resource has its own line and format - see below for details. +"size": + Mirrors the display of the "schemata" file to display the size in + bytes of each allocation instead of the bits representing the + allocation. + +"mode": + The "mode" of the resource group dictates the sharing of its + allocations. A "shareable" resource group allows sharing of its + allocations while an "exclusive" resource group does not. A + cache pseudo-locked region is created by first writing + "pseudo-locksetup" to the "mode" file before writing the cache + pseudo-locked region's schemata to the resource group's "schemata" + file. On successful pseudo-locked region creation the mode will + automatically change to "pseudo-locked". + When monitoring is enabled all MON groups will also contain: "mon_data": @@ -379,6 +424,170 @@ L3CODE:0=fffff;1=fffff;2=fffff;3=fffff L3DATA:0=fffff;1=fffff;2=3c0;3=fffff L3CODE:0=fffff;1=fffff;2=fffff;3=fffff +Cache Pseudo-Locking +-------------------- +CAT enables a user to specify the amount of cache space that an +application can fill. Cache pseudo-locking builds on the fact that a +CPU can still read and write data pre-allocated outside its current +allocated area on a cache hit. With cache pseudo-locking, data can be +preloaded into a reserved portion of cache that no application can +fill, and from that point on will only serve cache hits. The cache +pseudo-locked memory is made accessible to user space where an +application can map it into its virtual address space and thus have +a region of memory with reduced average read latency. + +The creation of a cache pseudo-locked region is triggered by a request +from the user to do so that is accompanied by a schemata of the region +to be pseudo-locked. The cache pseudo-locked region is created as follows: +- Create a CAT allocation CLOSNEW with a CBM matching the schemata + from the user of the cache region that will contain the pseudo-locked + memory. This region must not overlap with any current CAT allocation/CLOS + on the system and no future overlap with this cache region is allowed + while the pseudo-locked region exists. +- Create a contiguous region of memory of the same size as the cache + region. +- Flush the cache, disable hardware prefetchers, disable preemption. +- Make CLOSNEW the active CLOS and touch the allocated memory to load + it into the cache. +- Set the previous CLOS as active. +- At this point the closid CLOSNEW can be released - the cache + pseudo-locked region is protected as long as its CBM does not appear in + any CAT allocation. Even though the cache pseudo-locked region will from + this point on not appear in any CBM of any CLOS an application running with + any CLOS will be able to access the memory in the pseudo-locked region since + the region continues to serve cache hits. +- The contiguous region of memory loaded into the cache is exposed to + user-space as a character device. + +Cache pseudo-locking increases the probability that data will remain +in the cache via carefully configuring the CAT feature and controlling +application behavior. There is no guarantee that data is placed in +cache. Instructions like INVD, WBINVD, CLFLUSH, etc. can still evict +“locked†data from cache. Power management C-states may shrink or +power off cache. Deeper C-states will automatically be restricted on +pseudo-locked region creation. + +It is required that an application using a pseudo-locked region runs +with affinity to the cores (or a subset of the cores) associated +with the cache on which the pseudo-locked region resides. A sanity check +within the code will not allow an application to map pseudo-locked memory +unless it runs with affinity to cores associated with the cache on which the +pseudo-locked region resides. The sanity check is only done during the +initial mmap() handling, there is no enforcement afterwards and the +application self needs to ensure it remains affine to the correct cores. + +Pseudo-locking is accomplished in two stages: +1) During the first stage the system administrator allocates a portion + of cache that should be dedicated to pseudo-locking. At this time an + equivalent portion of memory is allocated, loaded into allocated + cache portion, and exposed as a character device. +2) During the second stage a user-space application maps (mmap()) the + pseudo-locked memory into its address space. + +Cache Pseudo-Locking Interface +------------------------------ +A pseudo-locked region is created using the resctrl interface as follows: + +1) Create a new resource group by creating a new directory in /sys/fs/resctrl. +2) Change the new resource group's mode to "pseudo-locksetup" by writing + "pseudo-locksetup" to the "mode" file. +3) Write the schemata of the pseudo-locked region to the "schemata" file. All + bits within the schemata should be "unused" according to the "bit_usage" + file. + +On successful pseudo-locked region creation the "mode" file will contain +"pseudo-locked" and a new character device with the same name as the resource +group will exist in /dev/pseudo_lock. This character device can be mmap()'ed +by user space in order to obtain access to the pseudo-locked memory region. + +An example of cache pseudo-locked region creation and usage can be found below. + +Cache Pseudo-Locking Debugging Interface +--------------------------------------- +The pseudo-locking debugging interface is enabled by default (if +CONFIG_DEBUG_FS is enabled) and can be found in /sys/kernel/debug/resctrl. + +There is no explicit way for the kernel to test if a provided memory +location is present in the cache. The pseudo-locking debugging interface uses +the tracing infrastructure to provide two ways to measure cache residency of +the pseudo-locked region: +1) Memory access latency using the pseudo_lock_mem_latency tracepoint. Data + from these measurements are best visualized using a hist trigger (see + example below). In this test the pseudo-locked region is traversed at + a stride of 32 bytes while hardware prefetchers and preemption + are disabled. This also provides a substitute visualization of cache + hits and misses. +2) Cache hit and miss measurements using model specific precision counters if + available. Depending on the levels of cache on the system the pseudo_lock_l2 + and pseudo_lock_l3 tracepoints are available. + WARNING: triggering this measurement uses from two (for just L2 + measurements) to four (for L2 and L3 measurements) precision counters on + the system, if any other measurements are in progress the counters and + their corresponding event registers will be clobbered. + +When a pseudo-locked region is created a new debugfs directory is created for +it in debugfs as /sys/kernel/debug/resctrl/<newdir>. A single +write-only file, pseudo_lock_measure, is present in this directory. The +measurement on the pseudo-locked region depends on the number, 1 or 2, +written to this debugfs file. Since the measurements are recorded with the +tracing infrastructure the relevant tracepoints need to be enabled before the +measurement is triggered. + +Example of latency debugging interface: +In this example a pseudo-locked region named "newlock" was created. Here is +how we can measure the latency in cycles of reading from this region and +visualize this data with a histogram that is available if CONFIG_HIST_TRIGGERS +is set: +# :> /sys/kernel/debug/tracing/trace +# echo 'hist:keys=latency' > /sys/kernel/debug/tracing/events/resctrl/pseudo_lock_mem_latency/trigger +# echo 1 > /sys/kernel/debug/tracing/events/resctrl/pseudo_lock_mem_latency/enable +# echo 1 > /sys/kernel/debug/resctrl/newlock/pseudo_lock_measure +# echo 0 > /sys/kernel/debug/tracing/events/resctrl/pseudo_lock_mem_latency/enable +# cat /sys/kernel/debug/tracing/events/resctrl/pseudo_lock_mem_latency/hist + +# event histogram +# +# trigger info: hist:keys=latency:vals=hitcount:sort=hitcount:size=2048 [active] +# + +{ latency: 456 } hitcount: 1 +{ latency: 50 } hitcount: 83 +{ latency: 36 } hitcount: 96 +{ latency: 44 } hitcount: 174 +{ latency: 48 } hitcount: 195 +{ latency: 46 } hitcount: 262 +{ latency: 42 } hitcount: 693 +{ latency: 40 } hitcount: 3204 +{ latency: 38 } hitcount: 3484 + +Totals: + Hits: 8192 + Entries: 9 + Dropped: 0 + +Example of cache hits/misses debugging: +In this example a pseudo-locked region named "newlock" was created on the L2 +cache of a platform. Here is how we can obtain details of the cache hits +and misses using the platform's precision counters. + +# :> /sys/kernel/debug/tracing/trace +# echo 1 > /sys/kernel/debug/tracing/events/resctrl/pseudo_lock_l2/enable +# echo 2 > /sys/kernel/debug/resctrl/newlock/pseudo_lock_measure +# echo 0 > /sys/kernel/debug/tracing/events/resctrl/pseudo_lock_l2/enable +# cat /sys/kernel/debug/tracing/trace + +# tracer: nop +# +# _-----=> irqs-off +# / _----=> need-resched +# | / _---=> hardirq/softirq +# || / _--=> preempt-depth +# ||| / delay +# TASK-PID CPU# |||| TIMESTAMP FUNCTION +# | | | |||| | | + pseudo_lock_mea-1672 [002] .... 3132.860500: pseudo_lock_l2: hits=4097 miss=0 + + Examples for RDT allocation usage: Example 1 @@ -502,7 +711,172 @@ siblings and only the real time threads are scheduled on the cores 4-7. # echo F0 > p0/cpus -4) Locking between applications +Example 4 +--------- + +The resource groups in previous examples were all in the default "shareable" +mode allowing sharing of their cache allocations. If one resource group +configures a cache allocation then nothing prevents another resource group +to overlap with that allocation. + +In this example a new exclusive resource group will be created on a L2 CAT +system with two L2 cache instances that can be configured with an 8-bit +capacity bitmask. The new exclusive resource group will be configured to use +25% of each cache instance. + +# mount -t resctrl resctrl /sys/fs/resctrl/ +# cd /sys/fs/resctrl + +First, we observe that the default group is configured to allocate to all L2 +cache: + +# cat schemata +L2:0=ff;1=ff + +We could attempt to create the new resource group at this point, but it will +fail because of the overlap with the schemata of the default group: +# mkdir p0 +# echo 'L2:0=0x3;1=0x3' > p0/schemata +# cat p0/mode +shareable +# echo exclusive > p0/mode +-sh: echo: write error: Invalid argument +# cat info/last_cmd_status +schemata overlaps + +To ensure that there is no overlap with another resource group the default +resource group's schemata has to change, making it possible for the new +resource group to become exclusive. +# echo 'L2:0=0xfc;1=0xfc' > schemata +# echo exclusive > p0/mode +# grep . p0/* +p0/cpus:0 +p0/mode:exclusive +p0/schemata:L2:0=03;1=03 +p0/size:L2:0=262144;1=262144 + +A new resource group will on creation not overlap with an exclusive resource +group: +# mkdir p1 +# grep . p1/* +p1/cpus:0 +p1/mode:shareable +p1/schemata:L2:0=fc;1=fc +p1/size:L2:0=786432;1=786432 + +The bit_usage will reflect how the cache is used: +# cat info/L2/bit_usage +0=SSSSSSEE;1=SSSSSSEE + +A resource group cannot be forced to overlap with an exclusive resource group: +# echo 'L2:0=0x1;1=0x1' > p1/schemata +-sh: echo: write error: Invalid argument +# cat info/last_cmd_status +overlaps with exclusive group + +Example of Cache Pseudo-Locking +------------------------------- +Lock portion of L2 cache from cache id 1 using CBM 0x3. Pseudo-locked +region is exposed at /dev/pseudo_lock/newlock that can be provided to +application for argument to mmap(). + +# mount -t resctrl resctrl /sys/fs/resctrl/ +# cd /sys/fs/resctrl + +Ensure that there are bits available that can be pseudo-locked, since only +unused bits can be pseudo-locked the bits to be pseudo-locked needs to be +removed from the default resource group's schemata: +# cat info/L2/bit_usage +0=SSSSSSSS;1=SSSSSSSS +# echo 'L2:1=0xfc' > schemata +# cat info/L2/bit_usage +0=SSSSSSSS;1=SSSSSS00 + +Create a new resource group that will be associated with the pseudo-locked +region, indicate that it will be used for a pseudo-locked region, and +configure the requested pseudo-locked region capacity bitmask: + +# mkdir newlock +# echo pseudo-locksetup > newlock/mode +# echo 'L2:1=0x3' > newlock/schemata + +On success the resource group's mode will change to pseudo-locked, the +bit_usage will reflect the pseudo-locked region, and the character device +exposing the pseudo-locked region will exist: + +# cat newlock/mode +pseudo-locked +# cat info/L2/bit_usage +0=SSSSSSSS;1=SSSSSSPP +# ls -l /dev/pseudo_lock/newlock +crw------- 1 root root 243, 0 Apr 3 05:01 /dev/pseudo_lock/newlock + +/* + * Example code to access one page of pseudo-locked cache region + * from user space. + */ +#define _GNU_SOURCE +#include <fcntl.h> +#include <sched.h> +#include <stdio.h> +#include <stdlib.h> +#include <unistd.h> +#include <sys/mman.h> + +/* + * It is required that the application runs with affinity to only + * cores associated with the pseudo-locked region. Here the cpu + * is hardcoded for convenience of example. + */ +static int cpuid = 2; + +int main(int argc, char *argv[]) +{ + cpu_set_t cpuset; + long page_size; + void *mapping; + int dev_fd; + int ret; + + page_size = sysconf(_SC_PAGESIZE); + + CPU_ZERO(&cpuset); + CPU_SET(cpuid, &cpuset); + ret = sched_setaffinity(0, sizeof(cpuset), &cpuset); + if (ret < 0) { + perror("sched_setaffinity"); + exit(EXIT_FAILURE); + } + + dev_fd = open("/dev/pseudo_lock/newlock", O_RDWR); + if (dev_fd < 0) { + perror("open"); + exit(EXIT_FAILURE); + } + + mapping = mmap(0, page_size, PROT_READ | PROT_WRITE, MAP_SHARED, + dev_fd, 0); + if (mapping == MAP_FAILED) { + perror("mmap"); + close(dev_fd); + exit(EXIT_FAILURE); + } + + /* Application interacts with pseudo-locked memory @mapping */ + + ret = munmap(mapping, page_size); + if (ret < 0) { + perror("munmap"); + close(dev_fd); + exit(EXIT_FAILURE); + } + + close(dev_fd); + exit(EXIT_SUCCESS); +} + +Locking between applications +---------------------------- Certain operations on the resctrl filesystem, composed of read/writes to/from multiple files, must be atomic. @@ -510,7 +884,7 @@ to/from multiple files, must be atomic. As an example, the allocation of an exclusive reservation of L3 cache involves: - 1. Read the cbmmasks from each directory + 1. Read the cbmmasks from each directory or the per-resource "bit_usage" 2. Find a contiguous set of bits in the global CBM bitmask that is clear in any of the directory cbmmasks 3. Create a new directory diff --git a/Documentation/x86/x86_64/boot-options.txt b/Documentation/x86/x86_64/boot-options.txt index 8d109ef67ab6..3a2ba436721a 100644 --- a/Documentation/x86/x86_64/boot-options.txt +++ b/Documentation/x86/x86_64/boot-options.txt @@ -156,6 +156,10 @@ NUMA If given as an integer, fills all system RAM with N fake nodes interleaved over physical nodes. + numa=fake=<N>U + If given as an integer followed by 'U', it will divide each + physical node into N emulated nodes. + ACPI acpi=off Don't enable ACPI diff --git a/MAINTAINERS b/MAINTAINERS index 7cebd5bba8a8..629e08703c82 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -5930,7 +5930,7 @@ F: Documentation/dev-tools/gcov.rst GDB KERNEL DEBUGGING HELPER SCRIPTS M: Jan Kiszka <jan.kiszka@siemens.com> -M: Kieran Bingham <kieran@bingham.xyz> +M: Kieran Bingham <kbingham@kernel.org> S: Supported F: scripts/gdb/ @@ -8317,10 +8317,16 @@ M: Jade Alglave <j.alglave@ucl.ac.uk> M: Luc Maranget <luc.maranget@inria.fr> M: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> R: Akira Yokosawa <akiyks@gmail.com> +R: Daniel Lustig <dlustig@nvidia.com> L: linux-kernel@vger.kernel.org +L: linux-arch@vger.kernel.org S: Supported T: git git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu.git F: tools/memory-model/ +F: Documentation/atomic_bitops.txt +F: Documentation/atomic_t.txt +F: Documentation/core-api/atomic_ops.rst +F: Documentation/core-api/refcount-vs-atomic.rst F: Documentation/memory-barriers.txt LINUX SECURITY MODULE (LSM) FRAMEWORK @@ -12039,9 +12045,9 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu.git F: Documentation/RCU/ X: Documentation/RCU/torture.txt F: include/linux/rcu* -X: include/linux/srcu.h +X: include/linux/srcu*.h F: kernel/rcu/ -X: kernel/torture.c +X: kernel/rcu/srcu*.c REAL TIME CLOCK (RTC) SUBSYSTEM M: Alessandro Zummo <a.zummo@towertech.it> @@ -13078,8 +13084,8 @@ L: linux-kernel@vger.kernel.org W: http://www.rdrop.com/users/paulmck/RCU/ S: Supported T: git git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu.git -F: include/linux/srcu.h -F: kernel/rcu/srcu.c +F: include/linux/srcu*.h +F: kernel/rcu/srcu*.c SERIAL LOW-POWER INTER-CHIP MEDIA BUS (SLIMbus) M: Srinivas Kandagatla <srinivas.kandagatla@linaro.org> @@ -14438,6 +14444,7 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu.git F: Documentation/RCU/torture.txt F: kernel/torture.c F: kernel/rcu/rcutorture.c +F: kernel/rcu/rcuperf.c F: kernel/locking/locktorture.c TOSHIBA ACPI EXTRAS DRIVER @@ -2,7 +2,7 @@ VERSION = 4 PATCHLEVEL = 18 SUBLEVEL = 0 -EXTRAVERSION = -rc8 +EXTRAVERSION = NAME = Merciless Moray # *DOCUMENTATION* diff --git a/arch/alpha/include/asm/atomic.h b/arch/alpha/include/asm/atomic.h index 767bfdd42992..150a1c5d6a2c 100644 --- a/arch/alpha/include/asm/atomic.h +++ b/arch/alpha/include/asm/atomic.h @@ -18,11 +18,11 @@ * To ensure dependency ordering is preserved for the _relaxed and * _release atomics, an smp_read_barrier_depends() is unconditionally * inserted into the _relaxed variants, which are used to build the - * barriered versions. To avoid redundant back-to-back fences, we can - * define the _acquire and _fence versions explicitly. + * barriered versions. Avoid redundant back-to-back fences in the + * _acquire and _fence versions. */ -#define __atomic_op_acquire(op, args...) op##_relaxed(args) -#define __atomic_op_fence __atomic_op_release +#define __atomic_acquire_fence() +#define __atomic_post_full_fence() #define ATOMIC_INIT(i) { (i) } #define ATOMIC64_INIT(i) { (i) } @@ -206,7 +206,7 @@ ATOMIC_OPS(xor, xor) #define atomic_xchg(v, new) (xchg(&((v)->counter), new)) /** - * __atomic_add_unless - add unless the number is a given value + * atomic_fetch_add_unless - add unless the number is a given value * @v: pointer of type atomic_t * @a: the amount to add to v... * @u: ...unless v is equal to u. @@ -214,7 +214,7 @@ ATOMIC_OPS(xor, xor) * Atomically adds @a to @v, so long as it was not @u. * Returns the old value of @v. */ -static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u) +static __inline__ int atomic_fetch_add_unless(atomic_t *v, int a, int u) { int c, new, old; smp_mb(); @@ -235,38 +235,39 @@ static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u) smp_mb(); return old; } - +#define atomic_fetch_add_unless atomic_fetch_add_unless /** - * atomic64_add_unless - add unless the number is a given value + * atomic64_fetch_add_unless - add unless the number is a given value * @v: pointer of type atomic64_t * @a: the amount to add to v... * @u: ...unless v is equal to u. * * Atomically adds @a to @v, so long as it was not @u. - * Returns true iff @v was not @u. + * Returns the old value of @v. */ -static __inline__ int atomic64_add_unless(atomic64_t *v, long a, long u) +static __inline__ long atomic64_fetch_add_unless(atomic64_t *v, long a, long u) { - long c, tmp; + long c, new, old; smp_mb(); __asm__ __volatile__( - "1: ldq_l %[tmp],%[mem]\n" - " cmpeq %[tmp],%[u],%[c]\n" - " addq %[tmp],%[a],%[tmp]\n" + "1: ldq_l %[old],%[mem]\n" + " cmpeq %[old],%[u],%[c]\n" + " addq %[old],%[a],%[new]\n" " bne %[c],2f\n" - " stq_c %[tmp],%[mem]\n" - " beq %[tmp],3f\n" + " stq_c %[new],%[mem]\n" + " beq %[new],3f\n" "2:\n" ".subsection 2\n" "3: br 1b\n" ".previous" - : [tmp] "=&r"(tmp), [c] "=&r"(c) + : [old] "=&r"(old), [new] "=&r"(new), [c] "=&r"(c) : [mem] "m"(*v), [a] "rI"(a), [u] "rI"(u) : "memory"); smp_mb(); - return !c; + return old; } +#define atomic64_fetch_add_unless atomic64_fetch_add_unless /* * atomic64_dec_if_positive - decrement by 1 if old value positive @@ -295,31 +296,6 @@ static inline long atomic64_dec_if_positive(atomic64_t *v) smp_mb(); return old - 1; } - -#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0) - -#define atomic_add_negative(a, v) (atomic_add_return((a), (v)) < 0) -#define atomic64_add_negative(a, v) (atomic64_add_return((a), (v)) < 0) - -#define atomic_dec_return(v) atomic_sub_return(1,(v)) -#define atomic64_dec_return(v) atomic64_sub_return(1,(v)) - -#define atomic_inc_return(v) atomic_add_return(1,(v)) -#define atomic64_inc_return(v) atomic64_add_return(1,(v)) - -#define atomic_sub_and_test(i,v) (atomic_sub_return((i), (v)) == 0) -#define atomic64_sub_and_test(i,v) (atomic64_sub_return((i), (v)) == 0) - -#define atomic_inc_and_test(v) (atomic_add_return(1, (v)) == 0) -#define atomic64_inc_and_test(v) (atomic64_add_return(1, (v)) == 0) - -#define atomic_dec_and_test(v) (atomic_sub_return(1, (v)) == 0) -#define atomic64_dec_and_test(v) (atomic64_sub_return(1, (v)) == 0) - -#define atomic_inc(v) atomic_add(1,(v)) -#define atomic64_inc(v) atomic64_add(1,(v)) - -#define atomic_dec(v) atomic_sub(1,(v)) -#define atomic64_dec(v) atomic64_sub(1,(v)) +#define atomic64_dec_if_positive atomic64_dec_if_positive #endif /* _ALPHA_ATOMIC_H */ diff --git a/arch/arc/include/asm/atomic.h b/arch/arc/include/asm/atomic.h index 11859287c52a..4e0072730241 100644 --- a/arch/arc/include/asm/atomic.h +++ b/arch/arc/include/asm/atomic.h @@ -187,7 +187,8 @@ static inline int atomic_fetch_##op(int i, atomic_t *v) \ ATOMIC_OPS(add, +=, add) ATOMIC_OPS(sub, -=, sub) -#define atomic_andnot atomic_andnot +#define atomic_andnot atomic_andnot +#define atomic_fetch_andnot atomic_fetch_andnot #undef ATOMIC_OPS #define ATOMIC_OPS(op, c_op, asm_op) \ @@ -296,8 +297,6 @@ ATOMIC_OPS(add, +=, CTOP_INST_AADD_DI_R2_R2_R3) ATOMIC_FETCH_OP(op, c_op, asm_op) ATOMIC_OPS(and, &=, CTOP_INST_AAND_DI_R2_R2_R3) -#define atomic_andnot(mask, v) atomic_and(~(mask), (v)) -#define atomic_fetch_andnot(mask, v) atomic_fetch_and(~(mask), (v)) ATOMIC_OPS(or, |=, CTOP_INST_AOR_DI_R2_R2_R3) ATOMIC_OPS(xor, ^=, CTOP_INST_AXOR_DI_R2_R2_R3) @@ -308,48 +307,6 @@ ATOMIC_OPS(xor, ^=, CTOP_INST_AXOR_DI_R2_R2_R3) #undef ATOMIC_OP_RETURN #undef ATOMIC_OP -/** - * __atomic_add_unless - add unless the number is a given value - * @v: pointer of type atomic_t - * @a: the amount to add to v... - * @u: ...unless v is equal to u. - * - * Atomically adds @a to @v, so long as it was not @u. - * Returns the old value of @v - */ -#define __atomic_add_unless(v, a, u) \ -({ \ - int c, old; \ - \ - /* \ - * Explicit full memory barrier needed before/after as \ - * LLOCK/SCOND thmeselves don't provide any such semantics \ - */ \ - smp_mb(); \ - \ - c = atomic_read(v); \ - while (c != (u) && (old = atomic_cmpxchg((v), c, c + (a))) != c)\ - c = old; \ - \ - smp_mb(); \ - \ - c; \ -}) - -#define atomic_inc_not_zero(v) atomic_add_unless((v), 1, 0) - -#define atomic_inc(v) atomic_add(1, v) -#define atomic_dec(v) atomic_sub(1, v) - -#define atomic_inc_and_test(v) (atomic_add_return(1, v) == 0) -#define atomic_dec_and_test(v) (atomic_sub_return(1, v) == 0) -#define atomic_inc_return(v) atomic_add_return(1, (v)) -#define atomic_dec_return(v) atomic_sub_return(1, (v)) -#define atomic_sub_and_test(i, v) (atomic_sub_return(i, v) == 0) - -#define atomic_add_negative(i, v) (atomic_add_return(i, v) < 0) - - #ifdef CONFIG_GENERIC_ATOMIC64 #include <asm-generic/atomic64.h> @@ -472,7 +429,8 @@ static inline long long atomic64_fetch_##op(long long a, atomic64_t *v) \ ATOMIC64_OP_RETURN(op, op1, op2) \ ATOMIC64_FETCH_OP(op, op1, op2) -#define atomic64_andnot atomic64_andnot +#define atomic64_andnot atomic64_andnot +#define atomic64_fetch_andnot atomic64_fetch_andnot ATOMIC64_OPS(add, add.f, adc) ATOMIC64_OPS(sub, sub.f, sbc) @@ -559,53 +517,43 @@ static inline long long atomic64_dec_if_positive(atomic64_t *v) return val; } +#define atomic64_dec_if_positive atomic64_dec_if_positive /** - * atomic64_add_unless - add unless the number is a given value + * atomic64_fetch_add_unless - add unless the number is a given value * @v: pointer of type atomic64_t * @a: the amount to add to v... * @u: ...unless v is equal to u. * - * if (v != u) { v += a; ret = 1} else {ret = 0} - * Returns 1 iff @v was not @u (i.e. if add actually happened) + * Atomically adds @a to @v, if it was not @u. + * Returns the old value of @v */ -static inline int atomic64_add_unless(atomic64_t *v, long long a, long long u) +static inline long long atomic64_fetch_add_unless(atomic64_t *v, long long a, + long long u) { - long long val; - int op_done; + long long old, temp; smp_mb(); __asm__ __volatile__( "1: llockd %0, [%2] \n" - " mov %1, 1 \n" " brne %L0, %L4, 2f # continue to add since v != u \n" " breq.d %H0, %H4, 3f # return since v == u \n" - " mov %1, 0 \n" "2: \n" - " add.f %L0, %L0, %L3 \n" - " adc %H0, %H0, %H3 \n" - " scondd %0, [%2] \n" + " add.f %L1, %L0, %L3 \n" + " adc %H1, %H0, %H3 \n" + " scondd %1, [%2] \n" " bnz 1b \n" "3: \n" - : "=&r"(val), "=&r" (op_done) + : "=&r"(old), "=&r" (temp) : "r"(&v->counter), "r"(a), "r"(u) : "cc"); /* memory clobber comes from smp_mb() */ smp_mb(); - return op_done; + return old; } - -#define atomic64_add_negative(a, v) (atomic64_add_return((a), (v)) < 0) -#define atomic64_inc(v) atomic64_add(1LL, (v)) -#define atomic64_inc_return(v) atomic64_add_return(1LL, (v)) -#define atomic64_inc_and_test(v) (atomic64_inc_return(v) == 0) -#define atomic64_sub_and_test(a, v) (atomic64_sub_return((a), (v)) == 0) -#define atomic64_dec(v) atomic64_sub(1LL, (v)) -#define atomic64_dec_return(v) atomic64_sub_return(1LL, (v)) -#define atomic64_dec_and_test(v) (atomic64_dec_return((v)) == 0) -#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1LL, 0LL) +#define atomic64_fetch_add_unless atomic64_fetch_add_unless #endif /* !CONFIG_GENERIC_ATOMIC64 */ diff --git a/arch/arc/include/asm/kprobes.h b/arch/arc/include/asm/kprobes.h index 2e52d18e6bc7..2c1b479d5aea 100644 --- a/arch/arc/include/asm/kprobes.h +++ b/arch/arc/include/asm/kprobes.h @@ -45,8 +45,6 @@ struct prev_kprobe { struct kprobe_ctlblk { unsigned int kprobe_status; - struct pt_regs jprobe_saved_regs; - char jprobes_stack[MAX_STACK_SIZE]; struct prev_kprobe prev_kprobe; }; diff --git a/arch/arc/kernel/kprobes.c b/arch/arc/kernel/kprobes.c index 42b05046fad9..df35d4c0b0b8 100644 --- a/arch/arc/kernel/kprobes.c +++ b/arch/arc/kernel/kprobes.c @@ -225,24 +225,18 @@ int __kprobes arc_kprobe_handler(unsigned long addr, struct pt_regs *regs) /* If we have no pre-handler or it returned 0, we continue with * normal processing. If we have a pre-handler and it returned - * non-zero - which is expected from setjmp_pre_handler for - * jprobe, we return without single stepping and leave that to - * the break-handler which is invoked by a kprobe from - * jprobe_return + * non-zero - which means user handler setup registers to exit + * to another instruction, we must skip the single stepping. */ if (!p->pre_handler || !p->pre_handler(p, regs)) { setup_singlestep(p, regs); kcb->kprobe_status = KPROBE_HIT_SS; + } else { + reset_current_kprobe(); + preempt_enable_no_resched(); } return 1; - } else if (kprobe_running()) { - p = __this_cpu_read(current_kprobe); - if (p->break_handler && p->break_handler(p, regs)) { - setup_singlestep(p, regs); - kcb->kprobe_status = KPROBE_HIT_SS; - return 1; - } } /* no_kprobe: */ @@ -386,38 +380,6 @@ int __kprobes kprobe_exceptions_notify(struct notifier_block *self, return ret; } -int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs) -{ - struct jprobe *jp = container_of(p, struct jprobe, kp); - struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - unsigned long sp_addr = regs->sp; - - kcb->jprobe_saved_regs = *regs; - memcpy(kcb->jprobes_stack, (void *)sp_addr, MIN_STACK_SIZE(sp_addr)); - regs->ret = (unsigned long)(jp->entry); - - return 1; -} - -void __kprobes jprobe_return(void) -{ - __asm__ __volatile__("unimp_s"); - return; -} - -int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs) -{ - struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - unsigned long sp_addr; - - *regs = kcb->jprobe_saved_regs; - sp_addr = regs->sp; - memcpy((void *)sp_addr, kcb->jprobes_stack, MIN_STACK_SIZE(sp_addr)); - preempt_enable_no_resched(); - - return 1; -} - static void __used kretprobe_trampoline_holder(void) { __asm__ __volatile__(".global kretprobe_trampoline\n" @@ -483,9 +445,7 @@ static int __kprobes trampoline_probe_handler(struct kprobe *p, kretprobe_assert(ri, orig_ret_address, trampoline_address); regs->ret = orig_ret_address; - reset_current_kprobe(); kretprobe_hash_unlock(current, &flags); - preempt_enable_no_resched(); hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) { hlist_del(&ri->hlist); diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 843edfd000be..d7a81284c272 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -337,8 +337,8 @@ config ARCH_MULTIPLATFORM select TIMER_OF select COMMON_CLK select GENERIC_CLOCKEVENTS + select GENERIC_IRQ_MULTI_HANDLER select MIGHT_HAVE_PCI - select MULTI_IRQ_HANDLER select PCI_DOMAINS if PCI select SPARSE_IRQ select USE_OF @@ -465,9 +465,9 @@ config ARCH_DOVE bool "Marvell Dove" select CPU_PJ4 select GENERIC_CLOCKEVENTS + select GENERIC_IRQ_MULTI_HANDLER select GPIOLIB select MIGHT_HAVE_PCI - select MULTI_IRQ_HANDLER select MVEBU_MBUS select PINCTRL select PINCTRL_DOVE @@ -512,8 +512,8 @@ config ARCH_LPC32XX select COMMON_CLK select CPU_ARM926T select GENERIC_CLOCKEVENTS + select GENERIC_IRQ_MULTI_HANDLER select GPIOLIB - select MULTI_IRQ_HANDLER select SPARSE_IRQ select USE_OF help @@ -532,11 +532,11 @@ config ARCH_PXA select TIMER_OF select CPU_XSCALE if !CPU_XSC3 select GENERIC_CLOCKEVENTS + select GENERIC_IRQ_MULTI_HANDLER select GPIO_PXA select GPIOLIB select HAVE_IDE select IRQ_DOMAIN - select MULTI_IRQ_HANDLER select PLAT_PXA select SPARSE_IRQ help @@ -572,11 +572,11 @@ config ARCH_SA1100 select CPU_FREQ select CPU_SA1100 select GENERIC_CLOCKEVENTS + select GENERIC_IRQ_MULTI_HANDLER select GPIOLIB select HAVE_IDE select IRQ_DOMAIN select ISA - select MULTI_IRQ_HANDLER select NEED_MACH_MEMORY_H select SPARSE_IRQ help @@ -590,10 +590,10 @@ config ARCH_S3C24XX select GENERIC_CLOCKEVENTS select GPIO_SAMSUNG select GPIOLIB + select GENERIC_IRQ_MULTI_HANDLER select HAVE_S3C2410_I2C if I2C select HAVE_S3C2410_WATCHDOG if WATCHDOG select HAVE_S3C_RTC if RTC_CLASS - select MULTI_IRQ_HANDLER select NEED_MACH_IO_H select SAMSUNG_ATAGS select USE_OF @@ -627,10 +627,10 @@ config ARCH_OMAP1 select CLKSRC_MMIO select GENERIC_CLOCKEVENTS select GENERIC_IRQ_CHIP + select GENERIC_IRQ_MULTI_HANDLER select GPIOLIB select HAVE_IDE select IRQ_DOMAIN - select MULTI_IRQ_HANDLER select NEED_MACH_IO_H if PCCARD select NEED_MACH_MEMORY_H select SPARSE_IRQ @@ -921,11 +921,6 @@ config IWMMXT Enable support for iWMMXt context switching at run time if running on a CPU that supports it. -config MULTI_IRQ_HANDLER - bool - help - Allow each machine to specify it's own IRQ handler at run time. - if !MMU source "arch/arm/Kconfig-nommu" endif diff --git a/arch/arm/include/asm/atomic.h b/arch/arm/include/asm/atomic.h index 66d0e215a773..f74756641410 100644 --- a/arch/arm/include/asm/atomic.h +++ b/arch/arm/include/asm/atomic.h @@ -130,7 +130,7 @@ static inline int atomic_cmpxchg_relaxed(atomic_t *ptr, int old, int new) } #define atomic_cmpxchg_relaxed atomic_cmpxchg_relaxed -static inline int __atomic_add_unless(atomic_t *v, int a, int u) +static inline int atomic_fetch_add_unless(atomic_t *v, int a, int u) { int oldval, newval; unsigned long tmp; @@ -156,6 +156,7 @@ static inline int __atomic_add_unless(atomic_t *v, int a, int u) return oldval; } +#define atomic_fetch_add_unless atomic_fetch_add_unless #else /* ARM_ARCH_6 */ @@ -215,15 +216,7 @@ static inline int atomic_cmpxchg(atomic_t *v, int old, int new) return ret; } -static inline int __atomic_add_unless(atomic_t *v, int a, int u) -{ - int c, old; - - c = atomic_read(v); - while (c != u && (old = atomic_cmpxchg((v), c, c + a)) != c) - c = old; - return c; -} +#define atomic_fetch_andnot atomic_fetch_andnot #endif /* __LINUX_ARM_ARCH__ */ @@ -254,17 +247,6 @@ ATOMIC_OPS(xor, ^=, eor) #define atomic_xchg(v, new) (xchg(&((v)->counter), new)) -#define atomic_inc(v) atomic_add(1, v) -#define atomic_dec(v) atomic_sub(1, v) - -#define atomic_inc_and_test(v) (atomic_add_return(1, v) == 0) -#define atomic_dec_and_test(v) (atomic_sub_return(1, v) == 0) -#define atomic_inc_return_relaxed(v) (atomic_add_return_relaxed(1, v)) -#define atomic_dec_return_relaxed(v) (atomic_sub_return_relaxed(1, v)) -#define atomic_sub_and_test(i, v) (atomic_sub_return(i, v) == 0) - -#define atomic_add_negative(i,v) (atomic_add_return(i, v) < 0) - #ifndef CONFIG_GENERIC_ATOMIC64 typedef struct { long long counter; @@ -494,12 +476,13 @@ static inline long long atomic64_dec_if_positive(atomic64_t *v) return result; } +#define atomic64_dec_if_positive atomic64_dec_if_positive -static inline int atomic64_add_unless(atomic64_t *v, long long a, long long u) +static inline long long atomic64_fetch_add_unless(atomic64_t *v, long long a, + long long u) { - long long val; + long long oldval, newval; unsigned long tmp; - int ret = 1; smp_mb(); prefetchw(&v->counter); @@ -508,33 +491,23 @@ static inline int atomic64_add_unless(atomic64_t *v, long long a, long long u) "1: ldrexd %0, %H0, [%4]\n" " teq %0, %5\n" " teqeq %H0, %H5\n" -" moveq %1, #0\n" " beq 2f\n" -" adds %Q0, %Q0, %Q6\n" -" adc %R0, %R0, %R6\n" -" strexd %2, %0, %H0, [%4]\n" +" adds %Q1, %Q0, %Q6\n" +" adc %R1, %R0, %R6\n" +" strexd %2, %1, %H1, [%4]\n" " teq %2, #0\n" " bne 1b\n" "2:" - : "=&r" (val), "+r" (ret), "=&r" (tmp), "+Qo" (v->counter) + : "=&r" (oldval), "=&r" (newval), "=&r" (tmp), "+Qo" (v->counter) : "r" (&v->counter), "r" (u), "r" (a) : "cc"); - if (ret) + if (oldval != u) smp_mb(); - return ret; + return oldval; } - -#define atomic64_add_negative(a, v) (atomic64_add_return((a), (v)) < 0) -#define atomic64_inc(v) atomic64_add(1LL, (v)) -#define atomic64_inc_return_relaxed(v) atomic64_add_return_relaxed(1LL, (v)) -#define atomic64_inc_and_test(v) (atomic64_inc_return(v) == 0) -#define atomic64_sub_and_test(a, v) (atomic64_sub_return((a), (v)) == 0) -#define atomic64_dec(v) atomic64_sub(1LL, (v)) -#define atomic64_dec_return_relaxed(v) atomic64_sub_return_relaxed(1LL, (v)) -#define atomic64_dec_and_test(v) (atomic64_dec_return((v)) == 0) -#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1LL, 0LL) +#define atomic64_fetch_add_unless atomic64_fetch_add_unless #endif /* !CONFIG_GENERIC_ATOMIC64 */ #endif diff --git a/arch/arm/include/asm/efi.h b/arch/arm/include/asm/efi.h index 17f1f1a814ff..38badaae8d9d 100644 --- a/arch/arm/include/asm/efi.h +++ b/arch/arm/include/asm/efi.h @@ -58,6 +58,9 @@ void efi_virtmap_unload(void); #define efi_call_runtime(f, ...) sys_table_arg->runtime->f(__VA_ARGS__) #define efi_is_64bit() (false) +#define efi_table_attr(table, attr, instance) \ + ((table##_t *)instance)->attr + #define efi_call_proto(protocol, f, instance, ...) \ ((protocol##_t *)instance)->f(instance, ##__VA_ARGS__) diff --git a/arch/arm/include/asm/hw_breakpoint.h b/arch/arm/include/asm/hw_breakpoint.h index e46e4e7bdba3..ac54c06764e6 100644 --- a/arch/arm/include/asm/hw_breakpoint.h +++ b/arch/arm/include/asm/hw_breakpoint.h @@ -111,14 +111,17 @@ static inline void decode_ctrl_reg(u32 reg, asm volatile("mcr p14, 0, %0, " #N "," #M ", " #OP2 : : "r" (VAL));\ } while (0) +struct perf_event_attr; struct notifier_block; struct perf_event; struct pmu; extern int arch_bp_generic_fields(struct arch_hw_breakpoint_ctrl ctrl, int *gen_len, int *gen_type); -extern int arch_check_bp_in_kernelspace(struct perf_event *bp); -extern int arch_validate_hwbkpt_settings(struct perf_event *bp); +extern int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw); +extern int hw_breakpoint_arch_parse(struct perf_event *bp, + const struct perf_event_attr *attr, + struct arch_hw_breakpoint *hw); extern int hw_breakpoint_exceptions_notify(struct notifier_block *unused, unsigned long val, void *data); diff --git a/arch/arm/include/asm/irq.h b/arch/arm/include/asm/irq.h index b6f319606e30..c883fcbe93b6 100644 --- a/arch/arm/include/asm/irq.h +++ b/arch/arm/include/asm/irq.h @@ -31,11 +31,6 @@ extern void asm_do_IRQ(unsigned int, struct pt_regs *); void handle_IRQ(unsigned int, struct pt_regs *); void init_IRQ(void); -#ifdef CONFIG_MULTI_IRQ_HANDLER -extern void (*handle_arch_irq)(struct pt_regs *); -extern void set_handle_irq(void (*handle_irq)(struct pt_regs *)); -#endif - #ifdef CONFIG_SMP extern void arch_trigger_cpumask_backtrace(const cpumask_t *mask, bool exclude_self); diff --git a/arch/arm/include/asm/kprobes.h b/arch/arm/include/asm/kprobes.h index 59655459da59..82290f212d8e 100644 --- a/arch/arm/include/asm/kprobes.h +++ b/arch/arm/include/asm/kprobes.h @@ -44,8 +44,6 @@ struct prev_kprobe { struct kprobe_ctlblk { unsigned int kprobe_status; struct prev_kprobe prev_kprobe; - struct pt_regs jprobe_saved_regs; - char jprobes_stack[MAX_STACK_SIZE]; }; void arch_remove_kprobe(struct kprobe *); diff --git a/arch/arm/include/asm/mach/arch.h b/arch/arm/include/asm/mach/arch.h index 5c1ad11aa392..bb8851208e17 100644 --- a/arch/arm/include/asm/mach/arch.h +++ b/arch/arm/include/asm/mach/arch.h @@ -59,7 +59,7 @@ struct machine_desc { void (*init_time)(void); void (*init_machine)(void); void (*init_late)(void); -#ifdef CONFIG_MULTI_IRQ_HANDLER +#ifdef CONFIG_GENERIC_IRQ_MULTI_HANDLER void (*handle_irq)(struct pt_regs *); #endif void (*restart)(enum reboot_mode, const char *); diff --git a/arch/arm/include/asm/probes.h b/arch/arm/include/asm/probes.h index 1e5b9bb92270..991c9127c650 100644 --- a/arch/arm/include/asm/probes.h +++ b/arch/arm/include/asm/probes.h @@ -51,7 +51,6 @@ struct arch_probes_insn { * We assume one instruction can consume at most 64 bytes stack, which is * 'push {r0-r15}'. Instructions consume more or unknown stack space like * 'str r0, [sp, #-80]' and 'str r0, [sp, r1]' should be prohibit to probe. - * Both kprobe and jprobe use this macro. */ #define MAX_STACK_SIZE 64 diff --git a/arch/arm/include/asm/tlb.h b/arch/arm/include/asm/tlb.h index d5562f9ce600..f854148c8d7c 100644 --- a/arch/arm/include/asm/tlb.h +++ b/arch/arm/include/asm/tlb.h @@ -292,5 +292,13 @@ static inline void tlb_remove_check_page_size_change(struct mmu_gather *tlb, { } +static inline void tlb_flush_remove_tables(struct mm_struct *mm) +{ +} + +static inline void tlb_flush_remove_tables_local(void *arg) +{ +} + #endif /* CONFIG_MMU */ #endif diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S index 179a9f6bd1e3..e85a3af9ddeb 100644 --- a/arch/arm/kernel/entry-armv.S +++ b/arch/arm/kernel/entry-armv.S @@ -22,7 +22,7 @@ #include <asm/glue-df.h> #include <asm/glue-pf.h> #include <asm/vfpmacros.h> -#ifndef CONFIG_MULTI_IRQ_HANDLER +#ifndef CONFIG_GENERIC_IRQ_MULTI_HANDLER #include <mach/entry-macro.S> #endif #include <asm/thread_notify.h> @@ -39,7 +39,7 @@ * Interrupt handling. */ .macro irq_handler -#ifdef CONFIG_MULTI_IRQ_HANDLER +#ifdef CONFIG_GENERIC_IRQ_MULTI_HANDLER ldr r1, =handle_arch_irq mov r0, sp badr lr, 9997f @@ -1226,9 +1226,3 @@ vector_addrexcptn: .globl cr_alignment cr_alignment: .space 4 - -#ifdef CONFIG_MULTI_IRQ_HANDLER - .globl handle_arch_irq -handle_arch_irq: - .space 4 -#endif diff --git a/arch/arm/kernel/hw_breakpoint.c b/arch/arm/kernel/hw_breakpoint.c index 629e25152c0d..1d5fbf1d1c67 100644 --- a/arch/arm/kernel/hw_breakpoint.c +++ b/arch/arm/kernel/hw_breakpoint.c @@ -456,14 +456,13 @@ static int get_hbp_len(u8 hbp_len) /* * Check whether bp virtual address is in kernel space. */ -int arch_check_bp_in_kernelspace(struct perf_event *bp) +int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw) { unsigned int len; unsigned long va; - struct arch_hw_breakpoint *info = counter_arch_bp(bp); - va = info->address; - len = get_hbp_len(info->ctrl.len); + va = hw->address; + len = get_hbp_len(hw->ctrl.len); return (va >= TASK_SIZE) && ((va + len - 1) >= TASK_SIZE); } @@ -518,42 +517,42 @@ int arch_bp_generic_fields(struct arch_hw_breakpoint_ctrl ctrl, /* * Construct an arch_hw_breakpoint from a perf_event. */ -static int arch_build_bp_info(struct perf_event *bp) +static int arch_build_bp_info(struct perf_event *bp, + const struct perf_event_attr *attr, + struct arch_hw_breakpoint *hw) { - struct arch_hw_breakpoint *info = counter_arch_bp(bp); - /* Type */ - switch (bp->attr.bp_type) { + switch (attr->bp_type) { case HW_BREAKPOINT_X: - info->ctrl.type = ARM_BREAKPOINT_EXECUTE; + hw->ctrl.type = ARM_BREAKPOINT_EXECUTE; break; case HW_BREAKPOINT_R: - info->ctrl.type = ARM_BREAKPOINT_LOAD; + hw->ctrl.type = ARM_BREAKPOINT_LOAD; break; case HW_BREAKPOINT_W: - info->ctrl.type = ARM_BREAKPOINT_STORE; + hw->ctrl.type = ARM_BREAKPOINT_STORE; break; case HW_BREAKPOINT_RW: - info->ctrl.type = ARM_BREAKPOINT_LOAD | ARM_BREAKPOINT_STORE; + hw->ctrl.type = ARM_BREAKPOINT_LOAD | ARM_BREAKPOINT_STORE; break; default: return -EINVAL; } /* Len */ - switch (bp->attr.bp_len) { + switch (attr->bp_len) { case HW_BREAKPOINT_LEN_1: - info->ctrl.len = ARM_BREAKPOINT_LEN_1; + hw->ctrl.len = ARM_BREAKPOINT_LEN_1; break; case HW_BREAKPOINT_LEN_2: - info->ctrl.len = ARM_BREAKPOINT_LEN_2; + hw->ctrl.len = ARM_BREAKPOINT_LEN_2; break; case HW_BREAKPOINT_LEN_4: - info->ctrl.len = ARM_BREAKPOINT_LEN_4; + hw->ctrl.len = ARM_BREAKPOINT_LEN_4; break; case HW_BREAKPOINT_LEN_8: - info->ctrl.len = ARM_BREAKPOINT_LEN_8; - if ((info->ctrl.type != ARM_BREAKPOINT_EXECUTE) + hw->ctrl.len = ARM_BREAKPOINT_LEN_8; + if ((hw->ctrl.type != ARM_BREAKPOINT_EXECUTE) && max_watchpoint_len >= 8) break; default: @@ -566,24 +565,24 @@ static int arch_build_bp_info(struct perf_event *bp) * by the hardware and must be aligned to the appropriate number of * bytes. */ - if (info->ctrl.type == ARM_BREAKPOINT_EXECUTE && - info->ctrl.len != ARM_BREAKPOINT_LEN_2 && - info->ctrl.len != ARM_BREAKPOINT_LEN_4) + if (hw->ctrl.type == ARM_BREAKPOINT_EXECUTE && + hw->ctrl.len != ARM_BREAKPOINT_LEN_2 && + hw->ctrl.len != ARM_BREAKPOINT_LEN_4) return -EINVAL; /* Address */ - info->address = bp->attr.bp_addr; + hw->address = attr->bp_addr; /* Privilege */ - info->ctrl.privilege = ARM_BREAKPOINT_USER; - if (arch_check_bp_in_kernelspace(bp)) - info->ctrl.privilege |= ARM_BREAKPOINT_PRIV; + hw->ctrl.privilege = ARM_BREAKPOINT_USER; + if (arch_check_bp_in_kernelspace(hw)) + hw->ctrl.privilege |= ARM_BREAKPOINT_PRIV; /* Enabled? */ - info->ctrl.enabled = !bp->attr.disabled; + hw->ctrl.enabled = !attr->disabled; /* Mismatch */ - info->ctrl.mismatch = 0; + hw->ctrl.mismatch = 0; return 0; } @@ -591,9 +590,10 @@ static int arch_build_bp_info(struct perf_event *bp) /* * Validate the arch-specific HW Breakpoint register settings. */ -int arch_validate_hwbkpt_settings(struct perf_event *bp) +int hw_breakpoint_arch_parse(struct perf_event *bp, + const struct perf_event_attr *attr, + struct arch_hw_breakpoint *hw) { - struct arch_hw_breakpoint *info = counter_arch_bp(bp); int ret = 0; u32 offset, alignment_mask = 0x3; @@ -602,14 +602,14 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp) return -ENODEV; /* Build the arch_hw_breakpoint. */ - ret = arch_build_bp_info(bp); + ret = arch_build_bp_info(bp, attr, hw); if (ret) goto out; /* Check address alignment. */ - if (info->ctrl.len == ARM_BREAKPOINT_LEN_8) + if (hw->ctrl.len == ARM_BREAKPOINT_LEN_8) alignment_mask = 0x7; - offset = info->address & alignment_mask; + offset = hw->address & alignment_mask; switch (offset) { case 0: /* Aligned */ @@ -617,19 +617,19 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp) case 1: case 2: /* Allow halfword watchpoints and breakpoints. */ - if (info->ctrl.len == ARM_BREAKPOINT_LEN_2) + if (hw->ctrl.len == ARM_BREAKPOINT_LEN_2) break; case 3: /* Allow single byte watchpoint. */ - if (info->ctrl.len == ARM_BREAKPOINT_LEN_1) + if (hw->ctrl.len == ARM_BREAKPOINT_LEN_1) break; default: ret = -EINVAL; goto out; } - info->address &= ~alignment_mask; - info->ctrl.len <<= offset; + hw->address &= ~alignment_mask; + hw->ctrl.len <<= offset; if (is_default_overflow_handler(bp)) { /* @@ -640,7 +640,7 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp) return -EINVAL; /* We don't allow mismatch breakpoints in kernel space. */ - if (arch_check_bp_in_kernelspace(bp)) + if (arch_check_bp_in_kernelspace(hw)) return -EPERM; /* @@ -655,8 +655,8 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp) * reports them. */ if (!debug_exception_updates_fsr() && - (info->ctrl.type == ARM_BREAKPOINT_LOAD || - info->ctrl.type == ARM_BREAKPOINT_STORE)) + (hw->ctrl.type == ARM_BREAKPOINT_LOAD || + hw->ctrl.type == ARM_BREAKPOINT_STORE)) return -EINVAL; } diff --git a/arch/arm/kernel/irq.c b/arch/arm/kernel/irq.c index ece04a457486..9908dacf9229 100644 --- a/arch/arm/kernel/irq.c +++ b/arch/arm/kernel/irq.c @@ -102,16 +102,6 @@ void __init init_IRQ(void) uniphier_cache_init(); } -#ifdef CONFIG_MULTI_IRQ_HANDLER -void __init set_handle_irq(void (*handle_irq)(struct pt_regs *)) -{ - if (handle_arch_irq) - return; - - handle_arch_irq = handle_irq; -} -#endif - #ifdef CONFIG_SPARSE_IRQ int __init arch_probe_nr_irqs(void) { diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c index 35ca494c028c..4c249cb261f3 100644 --- a/arch/arm/kernel/setup.c +++ b/arch/arm/kernel/setup.c @@ -1145,7 +1145,7 @@ void __init setup_arch(char **cmdline_p) reserve_crashkernel(); -#ifdef CONFIG_MULTI_IRQ_HANDLER +#ifdef CONFIG_GENERIC_IRQ_MULTI_HANDLER handle_arch_irq = mdesc->handle_irq; #endif diff --git a/arch/arm/probes/kprobes/core.c b/arch/arm/probes/kprobes/core.c index e90cc8a08186..f8bd523d64d1 100644 --- a/arch/arm/probes/kprobes/core.c +++ b/arch/arm/probes/kprobes/core.c @@ -47,9 +47,6 @@ (unsigned long)(addr) + \ (size)) -/* Used as a marker in ARM_pc to note when we're in a jprobe. */ -#define JPROBE_MAGIC_ADDR 0xffffffff - DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL; DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk); @@ -289,8 +286,8 @@ void __kprobes kprobe_handler(struct pt_regs *regs) break; case KPROBE_REENTER: /* A nested probe was hit in FIQ, it is a BUG */ - pr_warn("Unrecoverable kprobe detected at %p.\n", - p->addr); + pr_warn("Unrecoverable kprobe detected.\n"); + dump_kprobe(p); /* fall through */ default: /* impossible cases */ @@ -303,10 +300,10 @@ void __kprobes kprobe_handler(struct pt_regs *regs) /* * If we have no pre-handler or it returned 0, we - * continue with normal processing. If we have a - * pre-handler and it returned non-zero, it prepped - * for calling the break_handler below on re-entry, - * so get out doing nothing more here. + * continue with normal processing. If we have a + * pre-handler and it returned non-zero, it will + * modify the execution path and no need to single + * stepping. Let's just reset current kprobe and exit. */ if (!p->pre_handler || !p->pre_handler(p, regs)) { kcb->kprobe_status = KPROBE_HIT_SS; @@ -315,20 +312,9 @@ void __kprobes kprobe_handler(struct pt_regs *regs) kcb->kprobe_status = KPROBE_HIT_SSDONE; p->post_handler(p, regs, 0); } - reset_current_kprobe(); - } - } - } else if (cur) { - /* We probably hit a jprobe. Call its break handler. */ - if (cur->break_handler && cur->break_handler(cur, regs)) { - kcb->kprobe_status = KPROBE_HIT_SS; - singlestep(cur, regs, kcb); - if (cur->post_handler) { - kcb->kprobe_status = KPROBE_HIT_SSDONE; - cur->post_handler(cur, regs, 0); } + reset_current_kprobe(); } - reset_current_kprobe(); } else { /* * The probe was removed and a race is in progress. @@ -521,117 +507,6 @@ void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri, regs->ARM_lr = (unsigned long)&kretprobe_trampoline; } -int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs) -{ - struct jprobe *jp = container_of(p, struct jprobe, kp); - struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - long sp_addr = regs->ARM_sp; - long cpsr; - - kcb->jprobe_saved_regs = *regs; - memcpy(kcb->jprobes_stack, (void *)sp_addr, MIN_STACK_SIZE(sp_addr)); - regs->ARM_pc = (long)jp->entry; - - cpsr = regs->ARM_cpsr | PSR_I_BIT; -#ifdef CONFIG_THUMB2_KERNEL - /* Set correct Thumb state in cpsr */ - if (regs->ARM_pc & 1) - cpsr |= PSR_T_BIT; - else - cpsr &= ~PSR_T_BIT; -#endif - regs->ARM_cpsr = cpsr; - - preempt_disable(); - return 1; -} - -void __kprobes jprobe_return(void) -{ - struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - - __asm__ __volatile__ ( - /* - * Setup an empty pt_regs. Fill SP and PC fields as - * they're needed by longjmp_break_handler. - * - * We allocate some slack between the original SP and start of - * our fabricated regs. To be precise we want to have worst case - * covered which is STMFD with all 16 regs so we allocate 2 * - * sizeof(struct_pt_regs)). - * - * This is to prevent any simulated instruction from writing - * over the regs when they are accessing the stack. - */ -#ifdef CONFIG_THUMB2_KERNEL - "sub r0, %0, %1 \n\t" - "mov sp, r0 \n\t" -#else - "sub sp, %0, %1 \n\t" -#endif - "ldr r0, ="__stringify(JPROBE_MAGIC_ADDR)"\n\t" - "str %0, [sp, %2] \n\t" - "str r0, [sp, %3] \n\t" - "mov r0, sp \n\t" - "bl kprobe_handler \n\t" - - /* - * Return to the context saved by setjmp_pre_handler - * and restored by longjmp_break_handler. - */ -#ifdef CONFIG_THUMB2_KERNEL - "ldr lr, [sp, %2] \n\t" /* lr = saved sp */ - "ldrd r0, r1, [sp, %5] \n\t" /* r0,r1 = saved lr,pc */ - "ldr r2, [sp, %4] \n\t" /* r2 = saved psr */ - "stmdb lr!, {r0, r1, r2} \n\t" /* push saved lr and */ - /* rfe context */ - "ldmia sp, {r0 - r12} \n\t" - "mov sp, lr \n\t" - "ldr lr, [sp], #4 \n\t" - "rfeia sp! \n\t" -#else - "ldr r0, [sp, %4] \n\t" - "msr cpsr_cxsf, r0 \n\t" - "ldmia sp, {r0 - pc} \n\t" -#endif - : - : "r" (kcb->jprobe_saved_regs.ARM_sp), - "I" (sizeof(struct pt_regs) * 2), - "J" (offsetof(struct pt_regs, ARM_sp)), - "J" (offsetof(struct pt_regs, ARM_pc)), - "J" (offsetof(struct pt_regs, ARM_cpsr)), - "J" (offsetof(struct pt_regs, ARM_lr)) - : "memory", "cc"); -} - -int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs) -{ - struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - long stack_addr = kcb->jprobe_saved_regs.ARM_sp; - long orig_sp = regs->ARM_sp; - struct jprobe *jp = container_of(p, struct jprobe, kp); - - if (regs->ARM_pc == JPROBE_MAGIC_ADDR) { - if (orig_sp != stack_addr) { - struct pt_regs *saved_regs = - (struct pt_regs *)kcb->jprobe_saved_regs.ARM_sp; - printk("current sp %lx does not match saved sp %lx\n", - orig_sp, stack_addr); - printk("Saved registers for jprobe %p\n", jp); - show_regs(saved_regs); - printk("Current registers\n"); - show_regs(regs); - BUG(); - } - *regs = kcb->jprobe_saved_regs; - memcpy((void *)stack_addr, kcb->jprobes_stack, - MIN_STACK_SIZE(stack_addr)); - preempt_enable_no_resched(); - return 1; - } - return 0; -} - int __kprobes arch_trampoline_kprobe(struct kprobe *p) { return 0; diff --git a/arch/arm/probes/kprobes/test-core.c b/arch/arm/probes/kprobes/test-core.c index 14db14152909..cc237fa9b90f 100644 --- a/arch/arm/probes/kprobes/test-core.c +++ b/arch/arm/probes/kprobes/test-core.c @@ -1461,7 +1461,6 @@ fail: print_registers(&result_regs); if (mem) { - pr_err("current_stack=%p\n", current_stack); pr_err("expected_memory:\n"); print_memory(expected_memory, mem_size); pr_err("result_memory:\n"); diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 42c090cf0292..3d1011957823 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -74,6 +74,7 @@ config ARM64 select GENERIC_CPU_AUTOPROBE select GENERIC_EARLY_IOREMAP select GENERIC_IDLE_POLL_SETUP + select GENERIC_IRQ_MULTI_HANDLER select GENERIC_IRQ_PROBE select GENERIC_IRQ_SHOW select GENERIC_IRQ_SHOW_LEVEL @@ -264,9 +265,6 @@ config ARCH_SUPPORTS_UPROBES config ARCH_PROC_KCORE_TEXT def_bool y -config MULTI_IRQ_HANDLER - def_bool y - source "init/Kconfig" source "kernel/Kconfig.freezer" diff --git a/arch/arm64/crypto/aes-ce-ccm-core.S b/arch/arm64/crypto/aes-ce-ccm-core.S index 88f5aef7934c..e3a375c4cb83 100644 --- a/arch/arm64/crypto/aes-ce-ccm-core.S +++ b/arch/arm64/crypto/aes-ce-ccm-core.S @@ -19,33 +19,24 @@ * u32 *macp, u8 const rk[], u32 rounds); */ ENTRY(ce_aes_ccm_auth_data) - frame_push 7 - - mov x19, x0 - mov x20, x1 - mov x21, x2 - mov x22, x3 - mov x23, x4 - mov x24, x5 - - ldr w25, [x22] /* leftover from prev round? */ + ldr w8, [x3] /* leftover from prev round? */ ld1 {v0.16b}, [x0] /* load mac */ - cbz w25, 1f - sub w25, w25, #16 + cbz w8, 1f + sub w8, w8, #16 eor v1.16b, v1.16b, v1.16b -0: ldrb w7, [x20], #1 /* get 1 byte of input */ - subs w21, w21, #1 - add w25, w25, #1 +0: ldrb w7, [x1], #1 /* get 1 byte of input */ + subs w2, w2, #1 + add w8, w8, #1 ins v1.b[0], w7 ext v1.16b, v1.16b, v1.16b, #1 /* rotate in the input bytes */ beq 8f /* out of input? */ - cbnz w25, 0b + cbnz w8, 0b eor v0.16b, v0.16b, v1.16b -1: ld1 {v3.4s}, [x23] /* load first round key */ - prfm pldl1strm, [x20] - cmp w24, #12 /* which key size? */ - add x6, x23, #16 - sub w7, w24, #2 /* modified # of rounds */ +1: ld1 {v3.4s}, [x4] /* load first round key */ + prfm pldl1strm, [x1] + cmp w5, #12 /* which key size? */ + add x6, x4, #16 + sub w7, w5, #2 /* modified # of rounds */ bmi 2f bne 5f mov v5.16b, v3.16b @@ -64,43 +55,33 @@ ENTRY(ce_aes_ccm_auth_data) ld1 {v5.4s}, [x6], #16 /* load next round key */ bpl 3b aese v0.16b, v4.16b - subs w21, w21, #16 /* last data? */ + subs w2, w2, #16 /* last data? */ eor v0.16b, v0.16b, v5.16b /* final round */ bmi 6f - ld1 {v1.16b}, [x20], #16 /* load next input block */ + ld1 {v1.16b}, [x1], #16 /* load next input block */ eor v0.16b, v0.16b, v1.16b /* xor with mac */ - beq 6f - - if_will_cond_yield_neon - st1 {v0.16b}, [x19] /* store mac */ - do_cond_yield_neon - ld1 {v0.16b}, [x19] /* reload mac */ - endif_yield_neon - - b 1b -6: st1 {v0.16b}, [x19] /* store mac */ + bne 1b +6: st1 {v0.16b}, [x0] /* store mac */ beq 10f - adds w21, w21, #16 + adds w2, w2, #16 beq 10f - mov w25, w21 -7: ldrb w7, [x20], #1 + mov w8, w2 +7: ldrb w7, [x1], #1 umov w6, v0.b[0] eor w6, w6, w7 - strb w6, [x19], #1 - subs w21, w21, #1 + strb w6, [x0], #1 + subs w2, w2, #1 beq 10f ext v0.16b, v0.16b, v0.16b, #1 /* rotate out the mac bytes */ b 7b -8: mov w7, w25 - add w25, w25, #16 +8: mov w7, w8 + add w8, w8, #16 9: ext v1.16b, v1.16b, v1.16b, #1 adds w7, w7, #1 bne 9b eor v0.16b, v0.16b, v1.16b - st1 {v0.16b}, [x19] -10: str w25, [x22] - - frame_pop + st1 {v0.16b}, [x0] +10: str w8, [x3] ret ENDPROC(ce_aes_ccm_auth_data) @@ -145,29 +126,19 @@ ENTRY(ce_aes_ccm_final) ENDPROC(ce_aes_ccm_final) .macro aes_ccm_do_crypt,enc - frame_push 8 - - mov x19, x0 - mov x20, x1 - mov x21, x2 - mov x22, x3 - mov x23, x4 - mov x24, x5 - mov x25, x6 - - ldr x26, [x25, #8] /* load lower ctr */ - ld1 {v0.16b}, [x24] /* load mac */ -CPU_LE( rev x26, x26 ) /* keep swabbed ctr in reg */ + ldr x8, [x6, #8] /* load lower ctr */ + ld1 {v0.16b}, [x5] /* load mac */ +CPU_LE( rev x8, x8 ) /* keep swabbed ctr in reg */ 0: /* outer loop */ - ld1 {v1.8b}, [x25] /* load upper ctr */ - prfm pldl1strm, [x20] - add x26, x26, #1 - rev x9, x26 - cmp w23, #12 /* which key size? */ - sub w7, w23, #2 /* get modified # of rounds */ + ld1 {v1.8b}, [x6] /* load upper ctr */ + prfm pldl1strm, [x1] + add x8, x8, #1 + rev x9, x8 + cmp w4, #12 /* which key size? */ + sub w7, w4, #2 /* get modified # of rounds */ ins v1.d[1], x9 /* no carry in lower ctr */ - ld1 {v3.4s}, [x22] /* load first round key */ - add x10, x22, #16 + ld1 {v3.4s}, [x3] /* load first round key */ + add x10, x3, #16 bmi 1f bne 4f mov v5.16b, v3.16b @@ -194,9 +165,9 @@ CPU_LE( rev x26, x26 ) /* keep swabbed ctr in reg */ bpl 2b aese v0.16b, v4.16b aese v1.16b, v4.16b - subs w21, w21, #16 - bmi 7f /* partial block? */ - ld1 {v2.16b}, [x20], #16 /* load next input block */ + subs w2, w2, #16 + bmi 6f /* partial block? */ + ld1 {v2.16b}, [x1], #16 /* load next input block */ .if \enc == 1 eor v2.16b, v2.16b, v5.16b /* final round enc+mac */ eor v1.16b, v1.16b, v2.16b /* xor with crypted ctr */ @@ -205,29 +176,18 @@ CPU_LE( rev x26, x26 ) /* keep swabbed ctr in reg */ eor v1.16b, v2.16b, v5.16b /* final round enc */ .endif eor v0.16b, v0.16b, v2.16b /* xor mac with pt ^ rk[last] */ - st1 {v1.16b}, [x19], #16 /* write output block */ - beq 5f - - if_will_cond_yield_neon - st1 {v0.16b}, [x24] /* store mac */ - do_cond_yield_neon - ld1 {v0.16b}, [x24] /* reload mac */ - endif_yield_neon - - b 0b -5: -CPU_LE( rev x26, x26 ) - st1 {v0.16b}, [x24] /* store mac */ - str x26, [x25, #8] /* store lsb end of ctr (BE) */ - -6: frame_pop - ret - -7: eor v0.16b, v0.16b, v5.16b /* final round mac */ + st1 {v1.16b}, [x0], #16 /* write output block */ + bne 0b +CPU_LE( rev x8, x8 ) + st1 {v0.16b}, [x5] /* store mac */ + str x8, [x6, #8] /* store lsb end of ctr (BE) */ +5: ret + +6: eor v0.16b, v0.16b, v5.16b /* final round mac */ eor v1.16b, v1.16b, v5.16b /* final round enc */ - st1 {v0.16b}, [x24] /* store mac */ - add w21, w21, #16 /* process partial tail block */ -8: ldrb w9, [x20], #1 /* get 1 byte of input */ + st1 {v0.16b}, [x5] /* store mac */ + add w2, w2, #16 /* process partial tail block */ +7: ldrb w9, [x1], #1 /* get 1 byte of input */ umov w6, v1.b[0] /* get top crypted ctr byte */ umov w7, v0.b[0] /* get top mac byte */ .if \enc == 1 @@ -237,13 +197,13 @@ CPU_LE( rev x26, x26 ) eor w9, w9, w6 eor w7, w7, w9 .endif - strb w9, [x19], #1 /* store out byte */ - strb w7, [x24], #1 /* store mac byte */ - subs w21, w21, #1 - beq 6b + strb w9, [x0], #1 /* store out byte */ + strb w7, [x5], #1 /* store mac byte */ + subs w2, w2, #1 + beq 5b ext v0.16b, v0.16b, v0.16b, #1 /* shift out mac byte */ ext v1.16b, v1.16b, v1.16b, #1 /* shift out ctr byte */ - b 8b + b 7b .endm /* diff --git a/arch/arm64/crypto/ghash-ce-core.S b/arch/arm64/crypto/ghash-ce-core.S index dcffb9e77589..c723647b37db 100644 --- a/arch/arm64/crypto/ghash-ce-core.S +++ b/arch/arm64/crypto/ghash-ce-core.S @@ -322,55 +322,41 @@ ENDPROC(pmull_ghash_update_p8) .endm .macro pmull_gcm_do_crypt, enc - frame_push 10 + ld1 {SHASH.2d}, [x4] + ld1 {XL.2d}, [x1] + ldr x8, [x5, #8] // load lower counter - mov x19, x0 - mov x20, x1 - mov x21, x2 - mov x22, x3 - mov x23, x4 - mov x24, x5 - mov x25, x6 - mov x26, x7 - .if \enc == 1 - ldr x27, [sp, #96] // first stacked arg - .endif - - ldr x28, [x24, #8] // load lower counter -CPU_LE( rev x28, x28 ) - -0: mov x0, x25 - load_round_keys w26, x0 - ld1 {SHASH.2d}, [x23] - ld1 {XL.2d}, [x20] + load_round_keys w7, x6 movi MASK.16b, #0xe1 ext SHASH2.16b, SHASH.16b, SHASH.16b, #8 +CPU_LE( rev x8, x8 ) shl MASK.2d, MASK.2d, #57 eor SHASH2.16b, SHASH2.16b, SHASH.16b .if \enc == 1 - ld1 {KS.16b}, [x27] + ldr x10, [sp] + ld1 {KS.16b}, [x10] .endif -1: ld1 {CTR.8b}, [x24] // load upper counter - ld1 {INP.16b}, [x22], #16 - rev x9, x28 - add x28, x28, #1 - sub w19, w19, #1 +0: ld1 {CTR.8b}, [x5] // load upper counter + ld1 {INP.16b}, [x3], #16 + rev x9, x8 + add x8, x8, #1 + sub w0, w0, #1 ins CTR.d[1], x9 // set lower counter .if \enc == 1 eor INP.16b, INP.16b, KS.16b // encrypt input - st1 {INP.16b}, [x21], #16 + st1 {INP.16b}, [x2], #16 .endif rev64 T1.16b, INP.16b - cmp w26, #12 - b.ge 4f // AES-192/256? + cmp w7, #12 + b.ge 2f // AES-192/256? -2: enc_round CTR, v21 +1: enc_round CTR, v21 ext T2.16b, XL.16b, XL.16b, #8 ext IN1.16b, T1.16b, T1.16b, #8 @@ -425,39 +411,27 @@ CPU_LE( rev x28, x28 ) .if \enc == 0 eor INP.16b, INP.16b, KS.16b - st1 {INP.16b}, [x21], #16 + st1 {INP.16b}, [x2], #16 .endif - cbz w19, 3f + cbnz w0, 0b - if_will_cond_yield_neon - st1 {XL.2d}, [x20] - .if \enc == 1 - st1 {KS.16b}, [x27] - .endif - do_cond_yield_neon - b 0b - endif_yield_neon +CPU_LE( rev x8, x8 ) + st1 {XL.2d}, [x1] + str x8, [x5, #8] // store lower counter - b 1b - -3: st1 {XL.2d}, [x20] .if \enc == 1 - st1 {KS.16b}, [x27] + st1 {KS.16b}, [x10] .endif -CPU_LE( rev x28, x28 ) - str x28, [x24, #8] // store lower counter - - frame_pop ret -4: b.eq 5f // AES-192? +2: b.eq 3f // AES-192? enc_round CTR, v17 enc_round CTR, v18 -5: enc_round CTR, v19 +3: enc_round CTR, v19 enc_round CTR, v20 - b 2b + b 1b .endm /* diff --git a/arch/arm64/include/asm/atomic.h b/arch/arm64/include/asm/atomic.h index c0235e0ff849..9bca54dda75c 100644 --- a/arch/arm64/include/asm/atomic.h +++ b/arch/arm64/include/asm/atomic.h @@ -40,17 +40,6 @@ #include <asm/cmpxchg.h> -#define ___atomic_add_unless(v, a, u, sfx) \ -({ \ - typeof((v)->counter) c, old; \ - \ - c = atomic##sfx##_read(v); \ - while (c != (u) && \ - (old = atomic##sfx##_cmpxchg((v), c, c + (a))) != c) \ - c = old; \ - c; \ - }) - #define ATOMIC_INIT(i) { (i) } #define atomic_read(v) READ_ONCE((v)->counter) @@ -61,21 +50,11 @@ #define atomic_add_return_release atomic_add_return_release #define atomic_add_return atomic_add_return -#define atomic_inc_return_relaxed(v) atomic_add_return_relaxed(1, (v)) -#define atomic_inc_return_acquire(v) atomic_add_return_acquire(1, (v)) -#define atomic_inc_return_release(v) atomic_add_return_release(1, (v)) -#define atomic_inc_return(v) atomic_add_return(1, (v)) - #define atomic_sub_return_relaxed atomic_sub_return_relaxed #define atomic_sub_return_acquire atomic_sub_return_acquire #define atomic_sub_return_release atomic_sub_return_release #define atomic_sub_return atomic_sub_return -#define atomic_dec_return_relaxed(v) atomic_sub_return_relaxed(1, (v)) -#define atomic_dec_return_acquire(v) atomic_sub_return_acquire(1, (v)) -#define atomic_dec_return_release(v) atomic_sub_return_release(1, (v)) -#define atomic_dec_return(v) atomic_sub_return(1, (v)) - #define atomic_fetch_add_relaxed atomic_fetch_add_relaxed #define atomic_fetch_add_acquire atomic_fetch_add_acquire #define atomic_fetch_add_release atomic_fetch_add_release @@ -119,13 +98,6 @@ cmpxchg_release(&((v)->counter), (old), (new)) #define atomic_cmpxchg(v, old, new) cmpxchg(&((v)->counter), (old), (new)) -#define atomic_inc(v) atomic_add(1, (v)) -#define atomic_dec(v) atomic_sub(1, (v)) -#define atomic_inc_and_test(v) (atomic_inc_return(v) == 0) -#define atomic_dec_and_test(v) (atomic_dec_return(v) == 0) -#define atomic_sub_and_test(i, v) (atomic_sub_return((i), (v)) == 0) -#define atomic_add_negative(i, v) (atomic_add_return((i), (v)) < 0) -#define __atomic_add_unless(v, a, u) ___atomic_add_unless(v, a, u,) #define atomic_andnot atomic_andnot /* @@ -140,21 +112,11 @@ #define atomic64_add_return_release atomic64_add_return_release #define atomic64_add_return atomic64_add_return -#define atomic64_inc_return_relaxed(v) atomic64_add_return_relaxed(1, (v)) -#define atomic64_inc_return_acquire(v) atomic64_add_return_acquire(1, (v)) -#define atomic64_inc_return_release(v) atomic64_add_return_release(1, (v)) -#define atomic64_inc_return(v) atomic64_add_return(1, (v)) - #define atomic64_sub_return_relaxed atomic64_sub_return_relaxed #define atomic64_sub_return_acquire atomic64_sub_return_acquire #define atomic64_sub_return_release atomic64_sub_return_release #define atomic64_sub_return atomic64_sub_return -#define atomic64_dec_return_relaxed(v) atomic64_sub_return_relaxed(1, (v)) -#define atomic64_dec_return_acquire(v) atomic64_sub_return_acquire(1, (v)) -#define atomic64_dec_return_release(v) atomic64_sub_return_release(1, (v)) -#define atomic64_dec_return(v) atomic64_sub_return(1, (v)) - #define atomic64_fetch_add_relaxed atomic64_fetch_add_relaxed #define atomic64_fetch_add_acquire atomic64_fetch_add_acquire #define atomic64_fetch_add_release atomic64_fetch_add_release @@ -195,16 +157,9 @@ #define atomic64_cmpxchg_release atomic_cmpxchg_release #define atomic64_cmpxchg atomic_cmpxchg -#define atomic64_inc(v) atomic64_add(1, (v)) -#define atomic64_dec(v) atomic64_sub(1, (v)) -#define atomic64_inc_and_test(v) (atomic64_inc_return(v) == 0) -#define atomic64_dec_and_test(v) (atomic64_dec_return(v) == 0) -#define atomic64_sub_and_test(i, v) (atomic64_sub_return((i), (v)) == 0) -#define atomic64_add_negative(i, v) (atomic64_add_return((i), (v)) < 0) -#define atomic64_add_unless(v, a, u) (___atomic_add_unless(v, a, u, 64) != u) #define atomic64_andnot atomic64_andnot -#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0) +#define atomic64_dec_if_positive atomic64_dec_if_positive #endif #endif diff --git a/arch/arm64/include/asm/bitops.h b/arch/arm64/include/asm/bitops.h index 9c19594ce7cb..10d536b1af74 100644 --- a/arch/arm64/include/asm/bitops.h +++ b/arch/arm64/include/asm/bitops.h @@ -17,22 +17,11 @@ #define __ASM_BITOPS_H #include <linux/compiler.h> -#include <asm/barrier.h> #ifndef _LINUX_BITOPS_H #error only <linux/bitops.h> can be included directly #endif -/* - * Little endian assembly atomic bitops. - */ -extern void set_bit(int nr, volatile unsigned long *p); -extern void clear_bit(int nr, volatile unsigned long *p); -extern void change_bit(int nr, volatile unsigned long *p); -extern int test_and_set_bit(int nr, volatile unsigned long *p); -extern int test_and_clear_bit(int nr, volatile unsigned long *p); -extern int test_and_change_bit(int nr, volatile unsigned long *p); - #include <asm-generic/bitops/builtin-__ffs.h> #include <asm-generic/bitops/builtin-ffs.h> #include <asm-generic/bitops/builtin-__fls.h> @@ -44,15 +33,11 @@ extern int test_and_change_bit(int nr, volatile unsigned long *p); #include <asm-generic/bitops/sched.h> #include <asm-generic/bitops/hweight.h> -#include <asm-generic/bitops/lock.h> +#include <asm-generic/bitops/atomic.h> +#include <asm-generic/bitops/lock.h> #include <asm-generic/bitops/non-atomic.h> #include <asm-generic/bitops/le.h> - -/* - * Ext2 is defined to use little-endian byte ordering. - */ -#define ext2_set_bit_atomic(lock, nr, p) test_and_set_bit_le(nr, p) -#define ext2_clear_bit_atomic(lock, nr, p) test_and_clear_bit_le(nr, p) +#include <asm-generic/bitops/ext2-atomic-setbit.h> #endif /* __ASM_BITOPS_H */ diff --git a/arch/arm64/include/asm/efi.h b/arch/arm64/include/asm/efi.h index 192d791f1103..7ed320895d1f 100644 --- a/arch/arm64/include/asm/efi.h +++ b/arch/arm64/include/asm/efi.h @@ -87,6 +87,9 @@ static inline unsigned long efi_get_max_initrd_addr(unsigned long dram_base, #define efi_call_runtime(f, ...) sys_table_arg->runtime->f(__VA_ARGS__) #define efi_is_64bit() (true) +#define efi_table_attr(table, attr, instance) \ + ((table##_t *)instance)->attr + #define efi_call_proto(protocol, f, instance, ...) \ ((protocol##_t *)instance)->f(instance, ##__VA_ARGS__) diff --git a/arch/arm64/include/asm/hw_breakpoint.h b/arch/arm64/include/asm/hw_breakpoint.h index 41770766d964..6a53e59ced95 100644 --- a/arch/arm64/include/asm/hw_breakpoint.h +++ b/arch/arm64/include/asm/hw_breakpoint.h @@ -119,13 +119,16 @@ static inline void decode_ctrl_reg(u32 reg, struct task_struct; struct notifier_block; +struct perf_event_attr; struct perf_event; struct pmu; extern int arch_bp_generic_fields(struct arch_hw_breakpoint_ctrl ctrl, int *gen_len, int *gen_type, int *offset); -extern int arch_check_bp_in_kernelspace(struct perf_event *bp); -extern int arch_validate_hwbkpt_settings(struct perf_event *bp); +extern int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw); +extern int hw_breakpoint_arch_parse(struct perf_event *bp, + const struct perf_event_attr *attr, + struct arch_hw_breakpoint *hw); extern int hw_breakpoint_exceptions_notify(struct notifier_block *unused, unsigned long val, void *data); diff --git a/arch/arm64/include/asm/irq.h b/arch/arm64/include/asm/irq.h index a0fee6985e6a..b2b0c6405eb0 100644 --- a/arch/arm64/include/asm/irq.h +++ b/arch/arm64/include/asm/irq.h @@ -8,8 +8,6 @@ struct pt_regs; -extern void set_handle_irq(void (*handle_irq)(struct pt_regs *)); - static inline int nr_legacy_irqs(void) { return 0; diff --git a/arch/arm64/include/asm/kprobes.h b/arch/arm64/include/asm/kprobes.h index 6deb8d726041..d5a44cf859e9 100644 --- a/arch/arm64/include/asm/kprobes.h +++ b/arch/arm64/include/asm/kprobes.h @@ -48,7 +48,6 @@ struct kprobe_ctlblk { unsigned long saved_irqflag; struct prev_kprobe prev_kprobe; struct kprobe_step_ctx ss_ctx; - struct pt_regs jprobe_saved_regs; }; void arch_remove_kprobe(struct kprobe *); diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c index 413dbe530da8..8c9644376326 100644 --- a/arch/arm64/kernel/hw_breakpoint.c +++ b/arch/arm64/kernel/hw_breakpoint.c @@ -343,14 +343,13 @@ static int get_hbp_len(u8 hbp_len) /* * Check whether bp virtual address is in kernel space. */ -int arch_check_bp_in_kernelspace(struct perf_event *bp) +int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw) { unsigned int len; unsigned long va; - struct arch_hw_breakpoint *info = counter_arch_bp(bp); - va = info->address; - len = get_hbp_len(info->ctrl.len); + va = hw->address; + len = get_hbp_len(hw->ctrl.len); return (va >= TASK_SIZE) && ((va + len - 1) >= TASK_SIZE); } @@ -421,53 +420,53 @@ int arch_bp_generic_fields(struct arch_hw_breakpoint_ctrl ctrl, /* * Construct an arch_hw_breakpoint from a perf_event. */ -static int arch_build_bp_info(struct perf_event *bp) +static int arch_build_bp_info(struct perf_event *bp, + const struct perf_event_attr *attr, + struct arch_hw_breakpoint *hw) { - struct arch_hw_breakpoint *info = counter_arch_bp(bp); - /* Type */ - switch (bp->attr.bp_type) { + switch (attr->bp_type) { case HW_BREAKPOINT_X: - info->ctrl.type = ARM_BREAKPOINT_EXECUTE; + hw->ctrl.type = ARM_BREAKPOINT_EXECUTE; break; case HW_BREAKPOINT_R: - info->ctrl.type = ARM_BREAKPOINT_LOAD; + hw->ctrl.type = ARM_BREAKPOINT_LOAD; break; case HW_BREAKPOINT_W: - info->ctrl.type = ARM_BREAKPOINT_STORE; + hw->ctrl.type = ARM_BREAKPOINT_STORE; break; case HW_BREAKPOINT_RW: - info->ctrl.type = ARM_BREAKPOINT_LOAD | ARM_BREAKPOINT_STORE; + hw->ctrl.type = ARM_BREAKPOINT_LOAD | ARM_BREAKPOINT_STORE; break; default: return -EINVAL; } /* Len */ - switch (bp->attr.bp_len) { + switch (attr->bp_len) { case HW_BREAKPOINT_LEN_1: - info->ctrl.len = ARM_BREAKPOINT_LEN_1; + hw->ctrl.len = ARM_BREAKPOINT_LEN_1; break; case HW_BREAKPOINT_LEN_2: - info->ctrl.len = ARM_BREAKPOINT_LEN_2; + hw->ctrl.len = ARM_BREAKPOINT_LEN_2; break; case HW_BREAKPOINT_LEN_3: - info->ctrl.len = ARM_BREAKPOINT_LEN_3; + hw->ctrl.len = ARM_BREAKPOINT_LEN_3; break; case HW_BREAKPOINT_LEN_4: - info->ctrl.len = ARM_BREAKPOINT_LEN_4; + hw->ctrl.len = ARM_BREAKPOINT_LEN_4; break; case HW_BREAKPOINT_LEN_5: - info->ctrl.len = ARM_BREAKPOINT_LEN_5; + hw->ctrl.len = ARM_BREAKPOINT_LEN_5; break; case HW_BREAKPOINT_LEN_6: - info->ctrl.len = ARM_BREAKPOINT_LEN_6; + hw->ctrl.len = ARM_BREAKPOINT_LEN_6; break; case HW_BREAKPOINT_LEN_7: - info->ctrl.len = ARM_BREAKPOINT_LEN_7; + hw->ctrl.len = ARM_BREAKPOINT_LEN_7; break; case HW_BREAKPOINT_LEN_8: - info->ctrl.len = ARM_BREAKPOINT_LEN_8; + hw->ctrl.len = ARM_BREAKPOINT_LEN_8; break; default: return -EINVAL; @@ -478,37 +477,37 @@ static int arch_build_bp_info(struct perf_event *bp) * AArch32 also requires breakpoints of length 2 for Thumb. * Watchpoints can be of length 1, 2, 4 or 8 bytes. */ - if (info->ctrl.type == ARM_BREAKPOINT_EXECUTE) { + if (hw->ctrl.type == ARM_BREAKPOINT_EXECUTE) { if (is_compat_bp(bp)) { - if (info->ctrl.len != ARM_BREAKPOINT_LEN_2 && - info->ctrl.len != ARM_BREAKPOINT_LEN_4) + if (hw->ctrl.len != ARM_BREAKPOINT_LEN_2 && + hw->ctrl.len != ARM_BREAKPOINT_LEN_4) return -EINVAL; - } else if (info->ctrl.len != ARM_BREAKPOINT_LEN_4) { + } else if (hw->ctrl.len != ARM_BREAKPOINT_LEN_4) { /* * FIXME: Some tools (I'm looking at you perf) assume * that breakpoints should be sizeof(long). This * is nonsense. For now, we fix up the parameter * but we should probably return -EINVAL instead. */ - info->ctrl.len = ARM_BREAKPOINT_LEN_4; + hw->ctrl.len = ARM_BREAKPOINT_LEN_4; } } /* Address */ - info->address = bp->attr.bp_addr; + hw->address = attr->bp_addr; /* * Privilege * Note that we disallow combined EL0/EL1 breakpoints because * that would complicate the stepping code. */ - if (arch_check_bp_in_kernelspace(bp)) - info->ctrl.privilege = AARCH64_BREAKPOINT_EL1; + if (arch_check_bp_in_kernelspace(hw)) + hw->ctrl.privilege = AARCH64_BREAKPOINT_EL1; else - info->ctrl.privilege = AARCH64_BREAKPOINT_EL0; + hw->ctrl.privilege = AARCH64_BREAKPOINT_EL0; /* Enabled? */ - info->ctrl.enabled = !bp->attr.disabled; + hw->ctrl.enabled = !attr->disabled; return 0; } @@ -516,14 +515,15 @@ static int arch_build_bp_info(struct perf_event *bp) /* * Validate the arch-specific HW Breakpoint register settings. */ -int arch_validate_hwbkpt_settings(struct perf_event *bp) +int hw_breakpoint_arch_parse(struct perf_event *bp, + const struct perf_event_attr *attr, + struct arch_hw_breakpoint *hw) { - struct arch_hw_breakpoint *info = counter_arch_bp(bp); int ret; u64 alignment_mask, offset; /* Build the arch_hw_breakpoint. */ - ret = arch_build_bp_info(bp); + ret = arch_build_bp_info(bp, attr, hw); if (ret) return ret; @@ -537,42 +537,42 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp) * that here. */ if (is_compat_bp(bp)) { - if (info->ctrl.len == ARM_BREAKPOINT_LEN_8) + if (hw->ctrl.len == ARM_BREAKPOINT_LEN_8) alignment_mask = 0x7; else alignment_mask = 0x3; - offset = info->address & alignment_mask; + offset = hw->address & alignment_mask; switch (offset) { case 0: /* Aligned */ break; case 1: /* Allow single byte watchpoint. */ - if (info->ctrl.len == ARM_BREAKPOINT_LEN_1) + if (hw->ctrl.len == ARM_BREAKPOINT_LEN_1) break; case 2: /* Allow halfword watchpoints and breakpoints. */ - if (info->ctrl.len == ARM_BREAKPOINT_LEN_2) + if (hw->ctrl.len == ARM_BREAKPOINT_LEN_2) break; default: return -EINVAL; } } else { - if (info->ctrl.type == ARM_BREAKPOINT_EXECUTE) + if (hw->ctrl.type == ARM_BREAKPOINT_EXECUTE) alignment_mask = 0x3; else alignment_mask = 0x7; - offset = info->address & alignment_mask; + offset = hw->address & alignment_mask; } - info->address &= ~alignment_mask; - info->ctrl.len <<= offset; + hw->address &= ~alignment_mask; + hw->ctrl.len <<= offset; /* * Disallow per-task kernel breakpoints since these would * complicate the stepping code. */ - if (info->ctrl.privilege == AARCH64_BREAKPOINT_EL1 && bp->hw.target) + if (hw->ctrl.privilege == AARCH64_BREAKPOINT_EL1 && bp->hw.target) return -EINVAL; return 0; diff --git a/arch/arm64/kernel/irq.c b/arch/arm64/kernel/irq.c index 60e5fc661f74..780a12f59a8f 100644 --- a/arch/arm64/kernel/irq.c +++ b/arch/arm64/kernel/irq.c @@ -42,16 +42,6 @@ int arch_show_interrupts(struct seq_file *p, int prec) return 0; } -void (*handle_arch_irq)(struct pt_regs *) = NULL; - -void __init set_handle_irq(void (*handle_irq)(struct pt_regs *)) -{ - if (handle_arch_irq) - return; - - handle_arch_irq = handle_irq; -} - #ifdef CONFIG_VMAP_STACK static void init_irq_stacks(void) { diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c index d849d9804011..e78c3ef04d95 100644 --- a/arch/arm64/kernel/probes/kprobes.c +++ b/arch/arm64/kernel/probes/kprobes.c @@ -275,7 +275,7 @@ static int __kprobes reenter_kprobe(struct kprobe *p, break; case KPROBE_HIT_SS: case KPROBE_REENTER: - pr_warn("Unrecoverable kprobe detected at %p.\n", p->addr); + pr_warn("Unrecoverable kprobe detected.\n"); dump_kprobe(p); BUG(); break; @@ -395,9 +395,9 @@ static void __kprobes kprobe_handler(struct pt_regs *regs) /* * If we have no pre-handler or it returned 0, we * continue with normal processing. If we have a - * pre-handler and it returned non-zero, it prepped - * for calling the break_handler below on re-entry, - * so get out doing nothing more here. + * pre-handler and it returned non-zero, it will + * modify the execution path and no need to single + * stepping. Let's just reset current kprobe and exit. * * pre_handler can hit a breakpoint and can step thru * before return, keep PSTATE D-flag enabled until @@ -405,16 +405,8 @@ static void __kprobes kprobe_handler(struct pt_regs *regs) */ if (!p->pre_handler || !p->pre_handler(p, regs)) { setup_singlestep(p, regs, kcb, 0); - return; - } - } - } else if ((le32_to_cpu(*(kprobe_opcode_t *) addr) == - BRK64_OPCODE_KPROBES) && cur_kprobe) { - /* We probably hit a jprobe. Call its break handler. */ - if (cur_kprobe->break_handler && - cur_kprobe->break_handler(cur_kprobe, regs)) { - setup_singlestep(cur_kprobe, regs, kcb, 0); - return; + } else + reset_current_kprobe(); } } /* @@ -465,74 +457,6 @@ kprobe_breakpoint_handler(struct pt_regs *regs, unsigned int esr) return DBG_HOOK_HANDLED; } -int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs) -{ - struct jprobe *jp = container_of(p, struct jprobe, kp); - struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - - kcb->jprobe_saved_regs = *regs; - /* - * Since we can't be sure where in the stack frame "stacked" - * pass-by-value arguments are stored we just don't try to - * duplicate any of the stack. Do not use jprobes on functions that - * use more than 64 bytes (after padding each to an 8 byte boundary) - * of arguments, or pass individual arguments larger than 16 bytes. - */ - - instruction_pointer_set(regs, (unsigned long) jp->entry); - preempt_disable(); - pause_graph_tracing(); - return 1; -} - -void __kprobes jprobe_return(void) -{ - struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - - /* - * Jprobe handler return by entering break exception, - * encoded same as kprobe, but with following conditions - * -a special PC to identify it from the other kprobes. - * -restore stack addr to original saved pt_regs - */ - asm volatile(" mov sp, %0 \n" - "jprobe_return_break: brk %1 \n" - : - : "r" (kcb->jprobe_saved_regs.sp), - "I" (BRK64_ESR_KPROBES) - : "memory"); - - unreachable(); -} - -int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs) -{ - struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - long stack_addr = kcb->jprobe_saved_regs.sp; - long orig_sp = kernel_stack_pointer(regs); - struct jprobe *jp = container_of(p, struct jprobe, kp); - extern const char jprobe_return_break[]; - - if (instruction_pointer(regs) != (u64) jprobe_return_break) - return 0; - - if (orig_sp != stack_addr) { - struct pt_regs *saved_regs = - (struct pt_regs *)kcb->jprobe_saved_regs.sp; - pr_err("current sp %lx does not match saved sp %lx\n", - orig_sp, stack_addr); - pr_err("Saved registers for jprobe %p\n", jp); - __show_regs(saved_regs); - pr_err("Current registers\n"); - __show_regs(regs); - BUG(); - } - unpause_graph_tracing(); - *regs = kcb->jprobe_saved_regs; - preempt_enable_no_resched(); - return 1; -} - bool arch_within_kprobe_blacklist(unsigned long addr) { if ((addr >= (unsigned long)__kprobes_text_start && diff --git a/arch/arm64/lib/Makefile b/arch/arm64/lib/Makefile index 137710f4dac3..68755fd70dcf 100644 --- a/arch/arm64/lib/Makefile +++ b/arch/arm64/lib/Makefile @@ -1,5 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 -lib-y := bitops.o clear_user.o delay.o copy_from_user.o \ +lib-y := clear_user.o delay.o copy_from_user.o \ copy_to_user.o copy_in_user.o copy_page.o \ clear_page.o memchr.o memcpy.o memmove.o memset.o \ memcmp.o strcmp.o strncmp.o strlen.o strnlen.o \ diff --git a/arch/arm64/lib/bitops.S b/arch/arm64/lib/bitops.S deleted file mode 100644 index 43ac736baa5b..000000000000 --- a/arch/arm64/lib/bitops.S +++ /dev/null @@ -1,76 +0,0 @@ -/* - * Based on arch/arm/lib/bitops.h - * - * Copyright (C) 2013 ARM Ltd. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program. If not, see <http://www.gnu.org/licenses/>. - */ - -#include <linux/linkage.h> -#include <asm/assembler.h> -#include <asm/lse.h> - -/* - * x0: bits 5:0 bit offset - * bits 31:6 word offset - * x1: address - */ - .macro bitop, name, llsc, lse -ENTRY( \name ) - and w3, w0, #63 // Get bit offset - eor w0, w0, w3 // Clear low bits - mov x2, #1 - add x1, x1, x0, lsr #3 // Get word offset -alt_lse " prfm pstl1strm, [x1]", "nop" - lsl x3, x2, x3 // Create mask - -alt_lse "1: ldxr x2, [x1]", "\lse x3, [x1]" -alt_lse " \llsc x2, x2, x3", "nop" -alt_lse " stxr w0, x2, [x1]", "nop" -alt_lse " cbnz w0, 1b", "nop" - - ret -ENDPROC(\name ) - .endm - - .macro testop, name, llsc, lse -ENTRY( \name ) - and w3, w0, #63 // Get bit offset - eor w0, w0, w3 // Clear low bits - mov x2, #1 - add x1, x1, x0, lsr #3 // Get word offset -alt_lse " prfm pstl1strm, [x1]", "nop" - lsl x4, x2, x3 // Create mask - -alt_lse "1: ldxr x2, [x1]", "\lse x4, x2, [x1]" - lsr x0, x2, x3 -alt_lse " \llsc x2, x2, x4", "nop" -alt_lse " stlxr w5, x2, [x1]", "nop" -alt_lse " cbnz w5, 1b", "nop" -alt_lse " dmb ish", "nop" - - and x0, x0, #1 - ret -ENDPROC(\name ) - .endm - -/* - * Atomic bit operations. - */ - bitop change_bit, eor, steor - bitop clear_bit, bic, stclr - bitop set_bit, orr, stset - - testop test_and_change_bit, eor, ldeoral - testop test_and_clear_bit, bic, ldclral - testop test_and_set_bit, orr, ldsetal diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 493ff75670ff..8ae5d7ae4af3 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -977,12 +977,12 @@ int pmd_clear_huge(pmd_t *pmdp) return 1; } -int pud_free_pmd_page(pud_t *pud) +int pud_free_pmd_page(pud_t *pud, unsigned long addr) { return pud_none(*pud); } -int pmd_free_pte_page(pmd_t *pmd) +int pmd_free_pte_page(pmd_t *pmd, unsigned long addr) { return pmd_none(*pmd); } diff --git a/arch/h8300/include/asm/atomic.h b/arch/h8300/include/asm/atomic.h index 941e7554e886..c6b6a06231b2 100644 --- a/arch/h8300/include/asm/atomic.h +++ b/arch/h8300/include/asm/atomic.h @@ -2,8 +2,10 @@ #ifndef __ARCH_H8300_ATOMIC__ #define __ARCH_H8300_ATOMIC__ +#include <linux/compiler.h> #include <linux/types.h> #include <asm/cmpxchg.h> +#include <asm/irqflags.h> /* * Atomic operations that C can't guarantee us. Useful for @@ -15,8 +17,6 @@ #define atomic_read(v) READ_ONCE((v)->counter) #define atomic_set(v, i) WRITE_ONCE(((v)->counter), (i)) -#include <linux/kernel.h> - #define ATOMIC_OP_RETURN(op, c_op) \ static inline int atomic_##op##_return(int i, atomic_t *v) \ { \ @@ -69,18 +69,6 @@ ATOMIC_OPS(sub, -=) #undef ATOMIC_OP_RETURN #undef ATOMIC_OP -#define atomic_add_negative(a, v) (atomic_add_return((a), (v)) < 0) -#define atomic_sub_and_test(i, v) (atomic_sub_return(i, v) == 0) - -#define atomic_inc_return(v) atomic_add_return(1, v) -#define atomic_dec_return(v) atomic_sub_return(1, v) - -#define atomic_inc(v) (void)atomic_inc_return(v) -#define atomic_inc_and_test(v) (atomic_inc_return(v) == 0) - -#define atomic_dec(v) (void)atomic_dec_return(v) -#define atomic_dec_and_test(v) (atomic_dec_return(v) == 0) - static inline int atomic_cmpxchg(atomic_t *v, int old, int new) { int ret; @@ -94,7 +82,7 @@ static inline int atomic_cmpxchg(atomic_t *v, int old, int new) return ret; } -static inline int __atomic_add_unless(atomic_t *v, int a, int u) +static inline int atomic_fetch_add_unless(atomic_t *v, int a, int u) { int ret; h8300flags flags; @@ -106,5 +94,6 @@ static inline int __atomic_add_unless(atomic_t *v, int a, int u) arch_local_irq_restore(flags); return ret; } +#define atomic_fetch_add_unless atomic_fetch_add_unless #endif /* __ARCH_H8300_ATOMIC __ */ diff --git a/arch/hexagon/include/asm/atomic.h b/arch/hexagon/include/asm/atomic.h index fb3dfb2a667e..311b9894ccc8 100644 --- a/arch/hexagon/include/asm/atomic.h +++ b/arch/hexagon/include/asm/atomic.h @@ -164,7 +164,7 @@ ATOMIC_OPS(xor) #undef ATOMIC_OP /** - * __atomic_add_unless - add unless the number is a given value + * atomic_fetch_add_unless - add unless the number is a given value * @v: pointer to value * @a: amount to add * @u: unless value is equal to u @@ -173,7 +173,7 @@ ATOMIC_OPS(xor) * */ -static inline int __atomic_add_unless(atomic_t *v, int a, int u) +static inline int atomic_fetch_add_unless(atomic_t *v, int a, int u) { int __oldval; register int tmp; @@ -196,18 +196,6 @@ static inline int __atomic_add_unless(atomic_t *v, int a, int u) ); return __oldval; } - -#define atomic_inc_not_zero(v) atomic_add_unless((v), 1, 0) - -#define atomic_inc(v) atomic_add(1, (v)) -#define atomic_dec(v) atomic_sub(1, (v)) - -#define atomic_inc_and_test(v) (atomic_add_return(1, (v)) == 0) -#define atomic_dec_and_test(v) (atomic_sub_return(1, (v)) == 0) -#define atomic_sub_and_test(i, v) (atomic_sub_return(i, (v)) == 0) -#define atomic_add_negative(i, v) (atomic_add_return(i, (v)) < 0) - -#define atomic_inc_return(v) (atomic_add_return(1, v)) -#define atomic_dec_return(v) (atomic_sub_return(1, v)) +#define atomic_fetch_add_unless atomic_fetch_add_unless #endif diff --git a/arch/ia64/include/asm/atomic.h b/arch/ia64/include/asm/atomic.h index 2524fb60fbc2..206530d0751b 100644 --- a/arch/ia64/include/asm/atomic.h +++ b/arch/ia64/include/asm/atomic.h @@ -215,91 +215,10 @@ ATOMIC64_FETCH_OP(xor, ^) (cmpxchg(&((v)->counter), old, new)) #define atomic64_xchg(v, new) (xchg(&((v)->counter), new)) -static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u) -{ - int c, old; - c = atomic_read(v); - for (;;) { - if (unlikely(c == (u))) - break; - old = atomic_cmpxchg((v), c, c + (a)); - if (likely(old == c)) - break; - c = old; - } - return c; -} - - -static __inline__ long atomic64_add_unless(atomic64_t *v, long a, long u) -{ - long c, old; - c = atomic64_read(v); - for (;;) { - if (unlikely(c == (u))) - break; - old = atomic64_cmpxchg((v), c, c + (a)); - if (likely(old == c)) - break; - c = old; - } - return c != (u); -} - -#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0) - -static __inline__ long atomic64_dec_if_positive(atomic64_t *v) -{ - long c, old, dec; - c = atomic64_read(v); - for (;;) { - dec = c - 1; - if (unlikely(dec < 0)) - break; - old = atomic64_cmpxchg((v), c, dec); - if (likely(old == c)) - break; - c = old; - } - return dec; -} - -/* - * Atomically add I to V and return TRUE if the resulting value is - * negative. - */ -static __inline__ int -atomic_add_negative (int i, atomic_t *v) -{ - return atomic_add_return(i, v) < 0; -} - -static __inline__ long -atomic64_add_negative (__s64 i, atomic64_t *v) -{ - return atomic64_add_return(i, v) < 0; -} - -#define atomic_dec_return(v) atomic_sub_return(1, (v)) -#define atomic_inc_return(v) atomic_add_return(1, (v)) -#define atomic64_dec_return(v) atomic64_sub_return(1, (v)) -#define atomic64_inc_return(v) atomic64_add_return(1, (v)) - -#define atomic_sub_and_test(i,v) (atomic_sub_return((i), (v)) == 0) -#define atomic_dec_and_test(v) (atomic_sub_return(1, (v)) == 0) -#define atomic_inc_and_test(v) (atomic_add_return(1, (v)) == 0) -#define atomic64_sub_and_test(i,v) (atomic64_sub_return((i), (v)) == 0) -#define atomic64_dec_and_test(v) (atomic64_sub_return(1, (v)) == 0) -#define atomic64_inc_and_test(v) (atomic64_add_return(1, (v)) == 0) - #define atomic_add(i,v) (void)atomic_add_return((i), (v)) #define atomic_sub(i,v) (void)atomic_sub_return((i), (v)) -#define atomic_inc(v) atomic_add(1, (v)) -#define atomic_dec(v) atomic_sub(1, (v)) #define atomic64_add(i,v) (void)atomic64_add_return((i), (v)) #define atomic64_sub(i,v) (void)atomic64_sub_return((i), (v)) -#define atomic64_inc(v) atomic64_add(1, (v)) -#define atomic64_dec(v) atomic64_sub(1, (v)) #endif /* _ASM_IA64_ATOMIC_H */ diff --git a/arch/ia64/include/asm/kprobes.h b/arch/ia64/include/asm/kprobes.h index 0302b3664789..580356a2eea6 100644 --- a/arch/ia64/include/asm/kprobes.h +++ b/arch/ia64/include/asm/kprobes.h @@ -82,8 +82,6 @@ struct prev_kprobe { #define ARCH_PREV_KPROBE_SZ 2 struct kprobe_ctlblk { unsigned long kprobe_status; - struct pt_regs jprobe_saved_regs; - unsigned long jprobes_saved_stacked_regs[MAX_PARAM_RSE_SIZE]; unsigned long *bsp; unsigned long cfm; atomic_t prev_kprobe_index; diff --git a/arch/ia64/include/uapi/asm/break.h b/arch/ia64/include/uapi/asm/break.h index 5d742bcb0018..4ca110f0a94b 100644 --- a/arch/ia64/include/uapi/asm/break.h +++ b/arch/ia64/include/uapi/asm/break.h @@ -14,7 +14,6 @@ */ #define __IA64_BREAK_KDB 0x80100 #define __IA64_BREAK_KPROBE 0x81000 /* .. 0x81fff */ -#define __IA64_BREAK_JPROBE 0x82000 /* * OS-specific break numbers: diff --git a/arch/ia64/kernel/Makefile b/arch/ia64/kernel/Makefile index 498f3da3f225..d0c0ccdd656a 100644 --- a/arch/ia64/kernel/Makefile +++ b/arch/ia64/kernel/Makefile @@ -25,7 +25,7 @@ obj-$(CONFIG_NUMA) += numa.o obj-$(CONFIG_PERFMON) += perfmon_default_smpl.o obj-$(CONFIG_IA64_CYCLONE) += cyclone.o obj-$(CONFIG_IA64_MCA_RECOVERY) += mca_recovery.o -obj-$(CONFIG_KPROBES) += kprobes.o jprobes.o +obj-$(CONFIG_KPROBES) += kprobes.o obj-$(CONFIG_DYNAMIC_FTRACE) += ftrace.o obj-$(CONFIG_KEXEC) += machine_kexec.o relocate_kernel.o crash.o obj-$(CONFIG_CRASH_DUMP) += crash_dump.o diff --git a/arch/ia64/kernel/jprobes.S b/arch/ia64/kernel/jprobes.S deleted file mode 100644 index f69389c7be1d..000000000000 --- a/arch/ia64/kernel/jprobes.S +++ /dev/null @@ -1,90 +0,0 @@ -/* - * Jprobe specific operations - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. - * - * Copyright (C) Intel Corporation, 2005 - * - * 2005-May Rusty Lynch <rusty.lynch@intel.com> and Anil S Keshavamurthy - * <anil.s.keshavamurthy@intel.com> initial implementation - * - * Jprobes (a.k.a. "jump probes" which is built on-top of kprobes) allow a - * probe to be inserted into the beginning of a function call. The fundamental - * difference between a jprobe and a kprobe is the jprobe handler is executed - * in the same context as the target function, while the kprobe handlers - * are executed in interrupt context. - * - * For jprobes we initially gain control by placing a break point in the - * first instruction of the targeted function. When we catch that specific - * break, we: - * * set the return address to our jprobe_inst_return() function - * * jump to the jprobe handler function - * - * Since we fixed up the return address, the jprobe handler will return to our - * jprobe_inst_return() function, giving us control again. At this point we - * are back in the parents frame marker, so we do yet another call to our - * jprobe_break() function to fix up the frame marker as it would normally - * exist in the target function. - * - * Our jprobe_return function then transfers control back to kprobes.c by - * executing a break instruction using one of our reserved numbers. When we - * catch that break in kprobes.c, we continue like we do for a normal kprobe - * by single stepping the emulated instruction, and then returning execution - * to the correct location. - */ -#include <asm/asmmacro.h> -#include <asm/break.h> - - /* - * void jprobe_break(void) - */ - .section .kprobes.text, "ax" -ENTRY(jprobe_break) - break.m __IA64_BREAK_JPROBE -END(jprobe_break) - - /* - * void jprobe_inst_return(void) - */ -GLOBAL_ENTRY(jprobe_inst_return) - br.call.sptk.many b0=jprobe_break -END(jprobe_inst_return) - -GLOBAL_ENTRY(invalidate_stacked_regs) - movl r16=invalidate_restore_cfm - ;; - mov b6=r16 - ;; - br.ret.sptk.many b6 - ;; -invalidate_restore_cfm: - mov r16=ar.rsc - ;; - mov ar.rsc=r0 - ;; - loadrs - ;; - mov ar.rsc=r16 - ;; - br.cond.sptk.many rp -END(invalidate_stacked_regs) - -GLOBAL_ENTRY(flush_register_stack) - // flush dirty regs to backing store (must be first in insn group) - flushrs - ;; - br.ret.sptk.many rp -END(flush_register_stack) - diff --git a/arch/ia64/kernel/kprobes.c b/arch/ia64/kernel/kprobes.c index f5f3a5e6fcd1..aa41bd5cf9b7 100644 --- a/arch/ia64/kernel/kprobes.c +++ b/arch/ia64/kernel/kprobes.c @@ -35,8 +35,6 @@ #include <asm/sections.h> #include <asm/exception.h> -extern void jprobe_inst_return(void); - DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL; DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk); @@ -480,12 +478,9 @@ int __kprobes trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs) */ break; } - kretprobe_assert(ri, orig_ret_address, trampoline_address); - reset_current_kprobe(); kretprobe_hash_unlock(current, &flags); - preempt_enable_no_resched(); hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) { hlist_del(&ri->hlist); @@ -819,14 +814,6 @@ static int __kprobes pre_kprobes_handler(struct die_args *args) prepare_ss(p, regs); kcb->kprobe_status = KPROBE_REENTER; return 1; - } else if (args->err == __IA64_BREAK_JPROBE) { - /* - * jprobe instrumented function just completed - */ - p = __this_cpu_read(current_kprobe); - if (p->break_handler && p->break_handler(p, regs)) { - goto ss_probe; - } } else if (!is_ia64_break_inst(regs)) { /* The breakpoint instruction was removed by * another cpu right after we hit, no further @@ -861,15 +848,12 @@ static int __kprobes pre_kprobes_handler(struct die_args *args) set_current_kprobe(p, kcb); kcb->kprobe_status = KPROBE_HIT_ACTIVE; - if (p->pre_handler && p->pre_handler(p, regs)) - /* - * Our pre-handler is specifically requesting that we just - * do a return. This is used for both the jprobe pre-handler - * and the kretprobe trampoline - */ + if (p->pre_handler && p->pre_handler(p, regs)) { + reset_current_kprobe(); + preempt_enable_no_resched(); return 1; + } -ss_probe: #if !defined(CONFIG_PREEMPT) if (p->ainsn.inst_flag == INST_FLAG_BOOSTABLE && !p->post_handler) { /* Boost up -- we can execute copied instructions directly */ @@ -992,7 +976,6 @@ int __kprobes kprobe_exceptions_notify(struct notifier_block *self, case DIE_BREAK: /* err is break number from ia64_bad_break() */ if ((args->err >> 12) == (__IA64_BREAK_KPROBE >> 12) - || args->err == __IA64_BREAK_JPROBE || args->err == 0) if (pre_kprobes_handler(args)) ret = NOTIFY_STOP; @@ -1040,74 +1023,6 @@ unsigned long arch_deref_entry_point(void *entry) return ((struct fnptr *)entry)->ip; } -int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs) -{ - struct jprobe *jp = container_of(p, struct jprobe, kp); - unsigned long addr = arch_deref_entry_point(jp->entry); - struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - struct param_bsp_cfm pa; - int bytes; - - /* - * Callee owns the argument space and could overwrite it, eg - * tail call optimization. So to be absolutely safe - * we save the argument space before transferring the control - * to instrumented jprobe function which runs in - * the process context - */ - pa.ip = regs->cr_iip; - unw_init_running(ia64_get_bsp_cfm, &pa); - bytes = (char *)ia64_rse_skip_regs(pa.bsp, pa.cfm & 0x3f) - - (char *)pa.bsp; - memcpy( kcb->jprobes_saved_stacked_regs, - pa.bsp, - bytes ); - kcb->bsp = pa.bsp; - kcb->cfm = pa.cfm; - - /* save architectural state */ - kcb->jprobe_saved_regs = *regs; - - /* after rfi, execute the jprobe instrumented function */ - regs->cr_iip = addr & ~0xFULL; - ia64_psr(regs)->ri = addr & 0xf; - regs->r1 = ((struct fnptr *)(jp->entry))->gp; - - /* - * fix the return address to our jprobe_inst_return() function - * in the jprobes.S file - */ - regs->b0 = ((struct fnptr *)(jprobe_inst_return))->ip; - - return 1; -} - -/* ia64 does not need this */ -void __kprobes jprobe_return(void) -{ -} - -int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs) -{ - struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - int bytes; - - /* restoring architectural state */ - *regs = kcb->jprobe_saved_regs; - - /* restoring the original argument space */ - flush_register_stack(); - bytes = (char *)ia64_rse_skip_regs(kcb->bsp, kcb->cfm & 0x3f) - - (char *)kcb->bsp; - memcpy( kcb->bsp, - kcb->jprobes_saved_stacked_regs, - bytes ); - invalidate_stacked_regs(); - - preempt_enable_no_resched(); - return 1; -} - static struct kprobe trampoline_p = { .pre_handler = trampoline_probe_handler }; diff --git a/arch/m68k/Kconfig b/arch/m68k/Kconfig index 785612b576f7..b29f93774d95 100644 --- a/arch/m68k/Kconfig +++ b/arch/m68k/Kconfig @@ -2,6 +2,7 @@ config M68K bool default y + select ARCH_HAS_SYNC_DMA_FOR_DEVICE if HAS_DMA select ARCH_MIGHT_HAVE_PC_PARPORT if ISA select ARCH_NO_COHERENT_DMA_MMAP if !MMU select HAVE_IDE @@ -24,6 +25,10 @@ config M68K select MODULES_USE_ELF_RELA select OLD_SIGSUSPEND3 select OLD_SIGACTION + select DMA_NONCOHERENT_OPS if HAS_DMA + select HAVE_MEMBLOCK + select ARCH_DISCARD_MEMBLOCK + select NO_BOOTMEM config CPU_BIG_ENDIAN def_bool y diff --git a/arch/m68k/apollo/config.c b/arch/m68k/apollo/config.c index b2a6bc63f8cd..aef8d42e078d 100644 --- a/arch/m68k/apollo/config.c +++ b/arch/m68k/apollo/config.c @@ -31,7 +31,6 @@ extern void dn_sched_init(irq_handler_t handler); extern void dn_init_IRQ(void); extern u32 dn_gettimeoffset(void); extern int dn_dummy_hwclk(int, struct rtc_time *); -extern int dn_dummy_set_clock_mmss(unsigned long); extern void dn_dummy_reset(void); #ifdef CONFIG_HEARTBEAT static void dn_heartbeat(int on); @@ -156,7 +155,6 @@ void __init config_apollo(void) arch_gettimeoffset = dn_gettimeoffset; mach_max_dma_address = 0xffffffff; mach_hwclk = dn_dummy_hwclk; /* */ - mach_set_clock_mmss = dn_dummy_set_clock_mmss; /* */ mach_reset = dn_dummy_reset; /* */ #ifdef CONFIG_HEARTBEAT mach_heartbeat = dn_heartbeat; @@ -240,12 +238,6 @@ int dn_dummy_hwclk(int op, struct rtc_time *t) { } -int dn_dummy_set_clock_mmss(unsigned long nowtime) -{ - pr_info("set_clock_mmss\n"); - return 0; -} - void dn_dummy_reset(void) { dn_serial_print("The end !\n"); diff --git a/arch/m68k/atari/config.c b/arch/m68k/atari/config.c index 565c6f06ab0b..bd96702a1ad0 100644 --- a/arch/m68k/atari/config.c +++ b/arch/m68k/atari/config.c @@ -81,9 +81,6 @@ extern void atari_sched_init(irq_handler_t); extern u32 atari_gettimeoffset(void); extern int atari_mste_hwclk (int, struct rtc_time *); extern int atari_tt_hwclk (int, struct rtc_time *); -extern int atari_mste_set_clock_mmss (unsigned long); -extern int atari_tt_set_clock_mmss (unsigned long); - /* ++roman: This is a more elaborate test for an SCC chip, since the plain * Medusa board generates DTACK at the SCC's standard addresses, but a SCC @@ -362,13 +359,11 @@ void __init config_atari(void) ATARIHW_SET(TT_CLK); pr_cont(" TT_CLK"); mach_hwclk = atari_tt_hwclk; - mach_set_clock_mmss = atari_tt_set_clock_mmss; } if (hwreg_present(&mste_rtc.sec_ones)) { ATARIHW_SET(MSTE_CLK); pr_cont(" MSTE_CLK"); mach_hwclk = atari_mste_hwclk; - mach_set_clock_mmss = atari_mste_set_clock_mmss; } if (!MACH_IS_MEDUSA && hwreg_present(&dma_wd.fdc_speed) && hwreg_write(&dma_wd.fdc_speed, 0)) { diff --git a/arch/m68k/atari/time.c b/arch/m68k/atari/time.c index c549b48174ec..9cca64286464 100644 --- a/arch/m68k/atari/time.c +++ b/arch/m68k/atari/time.c @@ -285,69 +285,6 @@ int atari_tt_hwclk( int op, struct rtc_time *t ) return( 0 ); } - -int atari_mste_set_clock_mmss (unsigned long nowtime) -{ - short real_seconds = nowtime % 60, real_minutes = (nowtime / 60) % 60; - struct MSTE_RTC val; - unsigned char rtc_minutes; - - mste_read(&val); - rtc_minutes= val.min_ones + val.min_tens * 10; - if ((rtc_minutes < real_minutes - ? real_minutes - rtc_minutes - : rtc_minutes - real_minutes) < 30) - { - val.sec_ones = real_seconds % 10; - val.sec_tens = real_seconds / 10; - val.min_ones = real_minutes % 10; - val.min_tens = real_minutes / 10; - mste_write(&val); - } - else - return -1; - return 0; -} - -int atari_tt_set_clock_mmss (unsigned long nowtime) -{ - int retval = 0; - short real_seconds = nowtime % 60, real_minutes = (nowtime / 60) % 60; - unsigned char save_control, save_freq_select, rtc_minutes; - - save_control = RTC_READ (RTC_CONTROL); /* tell the clock it's being set */ - RTC_WRITE (RTC_CONTROL, save_control | RTC_SET); - - save_freq_select = RTC_READ (RTC_FREQ_SELECT); /* stop and reset prescaler */ - RTC_WRITE (RTC_FREQ_SELECT, save_freq_select | RTC_DIV_RESET2); - - rtc_minutes = RTC_READ (RTC_MINUTES); - if (!(save_control & RTC_DM_BINARY)) - rtc_minutes = bcd2bin(rtc_minutes); - - /* Since we're only adjusting minutes and seconds, don't interfere - with hour overflow. This avoids messing with unknown time zones - but requires your RTC not to be off by more than 30 minutes. */ - if ((rtc_minutes < real_minutes - ? real_minutes - rtc_minutes - : rtc_minutes - real_minutes) < 30) - { - if (!(save_control & RTC_DM_BINARY)) - { - real_seconds = bin2bcd(real_seconds); - real_minutes = bin2bcd(real_minutes); - } - RTC_WRITE (RTC_SECONDS, real_seconds); - RTC_WRITE (RTC_MINUTES, real_minutes); - } - else - retval = -1; - - RTC_WRITE (RTC_FREQ_SELECT, save_freq_select); - RTC_WRITE (RTC_CONTROL, save_control); - return retval; -} - /* * Local variables: * c-indent-level: 4 diff --git a/arch/m68k/bvme6000/config.c b/arch/m68k/bvme6000/config.c index 2cfff4765040..143ee9fa3893 100644 --- a/arch/m68k/bvme6000/config.c +++ b/arch/m68k/bvme6000/config.c @@ -41,7 +41,6 @@ static void bvme6000_get_model(char *model); extern void bvme6000_sched_init(irq_handler_t handler); extern u32 bvme6000_gettimeoffset(void); extern int bvme6000_hwclk (int, struct rtc_time *); -extern int bvme6000_set_clock_mmss (unsigned long); extern void bvme6000_reset (void); void bvme6000_set_vectors (void); @@ -113,7 +112,6 @@ void __init config_bvme6000(void) mach_init_IRQ = bvme6000_init_IRQ; arch_gettimeoffset = bvme6000_gettimeoffset; mach_hwclk = bvme6000_hwclk; - mach_set_clock_mmss = bvme6000_set_clock_mmss; mach_reset = bvme6000_reset; mach_get_model = bvme6000_get_model; @@ -305,46 +303,3 @@ int bvme6000_hwclk(int op, struct rtc_time *t) return 0; } - -/* - * Set the minutes and seconds from seconds value 'nowtime'. Fail if - * clock is out by > 30 minutes. Logic lifted from atari code. - * Algorithm is to wait for the 10ms register to change, and then to - * wait a short while, and then set it. - */ - -int bvme6000_set_clock_mmss (unsigned long nowtime) -{ - int retval = 0; - short real_seconds = nowtime % 60, real_minutes = (nowtime / 60) % 60; - unsigned char rtc_minutes, rtc_tenms; - volatile RtcPtr_t rtc = (RtcPtr_t)BVME_RTC_BASE; - unsigned char msr = rtc->msr & 0xc0; - unsigned long flags; - volatile int i; - - rtc->msr = 0; /* Ensure clock accessible */ - rtc_minutes = bcd2bin (rtc->bcd_min); - - if ((rtc_minutes < real_minutes - ? real_minutes - rtc_minutes - : rtc_minutes - real_minutes) < 30) - { - local_irq_save(flags); - rtc_tenms = rtc->bcd_tenms; - while (rtc_tenms == rtc->bcd_tenms) - ; - for (i = 0; i < 1000; i++) - ; - rtc->bcd_min = bin2bcd(real_minutes); - rtc->bcd_sec = bin2bcd(real_seconds); - local_irq_restore(flags); - } - else - retval = -1; - - rtc->msr = msr; - - return retval; -} - diff --git a/arch/m68k/configs/amiga_defconfig b/arch/m68k/configs/amiga_defconfig index a874e54404d1..1d5483f6e457 100644 --- a/arch/m68k/configs/amiga_defconfig +++ b/arch/m68k/configs/amiga_defconfig @@ -52,6 +52,7 @@ CONFIG_UNIX_DIAG=m CONFIG_TLS=m CONFIG_XFRM_MIGRATE=y CONFIG_NET_KEY=y +CONFIG_XDP_SOCKETS=y CONFIG_INET=y CONFIG_IP_PNP=y CONFIG_IP_PNP_DHCP=y @@ -98,18 +99,14 @@ CONFIG_NF_CONNTRACK_SANE=m CONFIG_NF_CONNTRACK_SIP=m CONFIG_NF_CONNTRACK_TFTP=m CONFIG_NF_TABLES=m +CONFIG_NF_TABLES_SET=m CONFIG_NF_TABLES_INET=y CONFIG_NF_TABLES_NETDEV=y -CONFIG_NFT_EXTHDR=m -CONFIG_NFT_META=m -CONFIG_NFT_RT=m CONFIG_NFT_NUMGEN=m CONFIG_NFT_CT=m CONFIG_NFT_FLOW_OFFLOAD=m -CONFIG_NFT_SET_RBTREE=m -CONFIG_NFT_SET_HASH=m -CONFIG_NFT_SET_BITMAP=m CONFIG_NFT_COUNTER=m +CONFIG_NFT_CONNLIMIT=m CONFIG_NFT_LOG=m CONFIG_NFT_LIMIT=m CONFIG_NFT_MASQ=m @@ -122,6 +119,7 @@ CONFIG_NFT_REJECT=m CONFIG_NFT_COMPAT=m CONFIG_NFT_HASH=m CONFIG_NFT_FIB_INET=m +CONFIG_NFT_SOCKET=m CONFIG_NFT_DUP_NETDEV=m CONFIG_NFT_FWD_NETDEV=m CONFIG_NFT_FIB_NETDEV=m @@ -200,7 +198,6 @@ CONFIG_IP_SET_HASH_NETPORT=m CONFIG_IP_SET_HASH_NETIFACE=m CONFIG_IP_SET_LIST_SET=m CONFIG_NF_CONNTRACK_IPV4=m -CONFIG_NF_SOCKET_IPV4=m CONFIG_NFT_CHAIN_ROUTE_IPV4=m CONFIG_NFT_DUP_IPV4=m CONFIG_NFT_FIB_IPV4=m @@ -231,7 +228,6 @@ CONFIG_IP_NF_ARPTABLES=m CONFIG_IP_NF_ARPFILTER=m CONFIG_IP_NF_ARP_MANGLE=m CONFIG_NF_CONNTRACK_IPV6=m -CONFIG_NF_SOCKET_IPV6=m CONFIG_NFT_CHAIN_ROUTE_IPV6=m CONFIG_NFT_CHAIN_NAT_IPV6=m CONFIG_NFT_MASQ_IPV6=m @@ -260,7 +256,6 @@ CONFIG_IP6_NF_NAT=m CONFIG_IP6_NF_TARGET_MASQUERADE=m CONFIG_IP6_NF_TARGET_NPT=m CONFIG_NF_TABLES_BRIDGE=y -CONFIG_NFT_BRIDGE_META=m CONFIG_NFT_BRIDGE_REJECT=m CONFIG_NF_LOG_BRIDGE=m CONFIG_BRIDGE_NF_EBTABLES=m @@ -301,6 +296,7 @@ CONFIG_6LOWPAN_GHC_EXT_HDR_FRAG=m CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m CONFIG_DNS_RESOLVER=y CONFIG_BATMAN_ADV=m +# CONFIG_BATMAN_ADV_BATMAN_V is not set CONFIG_BATMAN_ADV_DAT=y CONFIG_BATMAN_ADV_NC=y CONFIG_BATMAN_ADV_MCAST=y @@ -356,6 +352,7 @@ CONFIG_A2091_SCSI=y CONFIG_GVP11_SCSI=y CONFIG_SCSI_A4000T=y CONFIG_SCSI_ZORRO7XX=y +CONFIG_SCSI_ZORRO_ESP=y CONFIG_MD=y CONFIG_MD_LINEAR=m CONFIG_BLK_DEV_DM=m @@ -363,6 +360,7 @@ CONFIG_DM_UNSTRIPED=m CONFIG_DM_CRYPT=m CONFIG_DM_SNAPSHOT=m CONFIG_DM_THIN_PROVISIONING=m +CONFIG_DM_WRITECACHE=m CONFIG_DM_ERA=m CONFIG_DM_MIRROR=m CONFIG_DM_RAID=m @@ -402,8 +400,8 @@ CONFIG_A2065=y CONFIG_ARIADNE=y # CONFIG_NET_VENDOR_AQUANTIA is not set # CONFIG_NET_VENDOR_ARC is not set -# CONFIG_NET_CADENCE is not set # CONFIG_NET_VENDOR_BROADCOM is not set +# CONFIG_NET_CADENCE is not set # CONFIG_NET_VENDOR_CIRRUS is not set # CONFIG_NET_VENDOR_CORTINA is not set # CONFIG_NET_VENDOR_EZCHIP is not set @@ -412,8 +410,10 @@ CONFIG_ARIADNE=y # CONFIG_NET_VENDOR_INTEL is not set # CONFIG_NET_VENDOR_MARVELL is not set # CONFIG_NET_VENDOR_MICREL is not set +# CONFIG_NET_VENDOR_MICROSEMI is not set # CONFIG_NET_VENDOR_NETRONOME is not set # CONFIG_NET_VENDOR_NI is not set +CONFIG_XSURF100=y CONFIG_HYDRA=y CONFIG_APNE=y CONFIG_ZORRO8390=y @@ -426,9 +426,9 @@ CONFIG_ZORRO8390=y # CONFIG_NET_VENDOR_SMSC is not set # CONFIG_NET_VENDOR_SOCIONEXT is not set # CONFIG_NET_VENDOR_STMICRO is not set +# CONFIG_NET_VENDOR_SYNOPSYS is not set # CONFIG_NET_VENDOR_VIA is not set # CONFIG_NET_VENDOR_WIZNET is not set -# CONFIG_NET_VENDOR_SYNOPSYS is not set CONFIG_PPP=m CONFIG_PPP_BSDCOMP=m CONFIG_PPP_DEFLATE=m @@ -478,6 +478,7 @@ CONFIG_HIDRAW=y CONFIG_UHID=m # CONFIG_HID_GENERIC is not set # CONFIG_HID_ITE is not set +# CONFIG_HID_REDRAGON is not set # CONFIG_USB_SUPPORT is not set CONFIG_RTC_CLASS=y # CONFIG_RTC_NVMEM is not set @@ -499,7 +500,7 @@ CONFIG_FS_ENCRYPTION=m CONFIG_FANOTIFY=y CONFIG_QUOTA_NETLINK_INTERFACE=y # CONFIG_PRINT_QUOTA_WARNING is not set -CONFIG_AUTOFS4_FS=m +CONFIG_AUTOFS_FS=m CONFIG_FUSE_FS=m CONFIG_CUSE=m CONFIG_OVERLAY_FS=m @@ -600,6 +601,7 @@ CONFIG_TEST_KSTRTOX=m CONFIG_TEST_PRINTF=m CONFIG_TEST_BITMAP=m CONFIG_TEST_UUID=m +CONFIG_TEST_OVERFLOW=m CONFIG_TEST_RHASHTABLE=m CONFIG_TEST_HASH=m CONFIG_TEST_USER_COPY=m @@ -622,6 +624,11 @@ CONFIG_CRYPTO_CRYPTD=m CONFIG_CRYPTO_MCRYPTD=m CONFIG_CRYPTO_TEST=m CONFIG_CRYPTO_CHACHA20POLY1305=m +CONFIG_CRYPTO_AEGIS128=m +CONFIG_CRYPTO_AEGIS128L=m +CONFIG_CRYPTO_AEGIS256=m +CONFIG_CRYPTO_MORUS640=m +CONFIG_CRYPTO_MORUS1280=m CONFIG_CRYPTO_CFB=m CONFIG_CRYPTO_LRW=m CONFIG_CRYPTO_PCBC=m @@ -657,6 +664,7 @@ CONFIG_CRYPTO_LZO=m CONFIG_CRYPTO_842=m CONFIG_CRYPTO_LZ4=m CONFIG_CRYPTO_LZ4HC=m +CONFIG_CRYPTO_ZSTD=m CONFIG_CRYPTO_ANSI_CPRNG=m CONFIG_CRYPTO_DRBG_HASH=y CONFIG_CRYPTO_DRBG_CTR=y diff --git a/arch/m68k/configs/apollo_defconfig b/arch/m68k/configs/apollo_defconfig index 8ce39e23aa42..52a0af127951 100644 --- a/arch/m68k/configs/apollo_defconfig +++ b/arch/m68k/configs/apollo_defconfig @@ -50,6 +50,7 @@ CONFIG_UNIX_DIAG=m CONFIG_TLS=m CONFIG_XFRM_MIGRATE=y CONFIG_NET_KEY=y +CONFIG_XDP_SOCKETS=y CONFIG_INET=y CONFIG_IP_PNP=y CONFIG_IP_PNP_DHCP=y @@ -96,18 +97,14 @@ CONFIG_NF_CONNTRACK_SANE=m CONFIG_NF_CONNTRACK_SIP=m CONFIG_NF_CONNTRACK_TFTP=m CONFIG_NF_TABLES=m +CONFIG_NF_TABLES_SET=m CONFIG_NF_TABLES_INET=y CONFIG_NF_TABLES_NETDEV=y -CONFIG_NFT_EXTHDR=m -CONFIG_NFT_META=m -CONFIG_NFT_RT=m CONFIG_NFT_NUMGEN=m CONFIG_NFT_CT=m CONFIG_NFT_FLOW_OFFLOAD=m -CONFIG_NFT_SET_RBTREE=m -CONFIG_NFT_SET_HASH=m -CONFIG_NFT_SET_BITMAP=m CONFIG_NFT_COUNTER=m +CONFIG_NFT_CONNLIMIT=m CONFIG_NFT_LOG=m CONFIG_NFT_LIMIT=m CONFIG_NFT_MASQ=m @@ -120,6 +117,7 @@ CONFIG_NFT_REJECT=m CONFIG_NFT_COMPAT=m CONFIG_NFT_HASH=m CONFIG_NFT_FIB_INET=m +CONFIG_NFT_SOCKET=m CONFIG_NFT_DUP_NETDEV=m CONFIG_NFT_FWD_NETDEV=m CONFIG_NFT_FIB_NETDEV=m @@ -198,7 +196,6 @@ CONFIG_IP_SET_HASH_NETPORT=m CONFIG_IP_SET_HASH_NETIFACE=m CONFIG_IP_SET_LIST_SET=m CONFIG_NF_CONNTRACK_IPV4=m -CONFIG_NF_SOCKET_IPV4=m CONFIG_NFT_CHAIN_ROUTE_IPV4=m CONFIG_NFT_DUP_IPV4=m CONFIG_NFT_FIB_IPV4=m @@ -229,7 +226,6 @@ CONFIG_IP_NF_ARPTABLES=m CONFIG_IP_NF_ARPFILTER=m CONFIG_IP_NF_ARP_MANGLE=m CONFIG_NF_CONNTRACK_IPV6=m -CONFIG_NF_SOCKET_IPV6=m CONFIG_NFT_CHAIN_ROUTE_IPV6=m CONFIG_NFT_CHAIN_NAT_IPV6=m CONFIG_NFT_MASQ_IPV6=m @@ -258,7 +254,6 @@ CONFIG_IP6_NF_NAT=m CONFIG_IP6_NF_TARGET_MASQUERADE=m CONFIG_IP6_NF_TARGET_NPT=m CONFIG_NF_TABLES_BRIDGE=y -CONFIG_NFT_BRIDGE_META=m CONFIG_NFT_BRIDGE_REJECT=m CONFIG_NF_LOG_BRIDGE=m CONFIG_BRIDGE_NF_EBTABLES=m @@ -299,6 +294,7 @@ CONFIG_6LOWPAN_GHC_EXT_HDR_FRAG=m CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m CONFIG_DNS_RESOLVER=y CONFIG_BATMAN_ADV=m +# CONFIG_BATMAN_ADV_BATMAN_V is not set CONFIG_BATMAN_ADV_DAT=y CONFIG_BATMAN_ADV_NC=y CONFIG_BATMAN_ADV_MCAST=y @@ -345,6 +341,7 @@ CONFIG_DM_UNSTRIPED=m CONFIG_DM_CRYPT=m CONFIG_DM_SNAPSHOT=m CONFIG_DM_THIN_PROVISIONING=m +CONFIG_DM_WRITECACHE=m CONFIG_DM_ERA=m CONFIG_DM_MIRROR=m CONFIG_DM_RAID=m @@ -381,14 +378,15 @@ CONFIG_VETH=m # CONFIG_NET_VENDOR_AMAZON is not set # CONFIG_NET_VENDOR_AQUANTIA is not set # CONFIG_NET_VENDOR_ARC is not set -# CONFIG_NET_CADENCE is not set # CONFIG_NET_VENDOR_BROADCOM is not set +# CONFIG_NET_CADENCE is not set # CONFIG_NET_VENDOR_CORTINA is not set # CONFIG_NET_VENDOR_EZCHIP is not set # CONFIG_NET_VENDOR_HUAWEI is not set # CONFIG_NET_VENDOR_INTEL is not set # CONFIG_NET_VENDOR_MARVELL is not set # CONFIG_NET_VENDOR_MICREL is not set +# CONFIG_NET_VENDOR_MICROSEMI is not set # CONFIG_NET_VENDOR_NATSEMI is not set # CONFIG_NET_VENDOR_NETRONOME is not set # CONFIG_NET_VENDOR_NI is not set @@ -400,9 +398,9 @@ CONFIG_VETH=m # CONFIG_NET_VENDOR_SOLARFLARE is not set # CONFIG_NET_VENDOR_SOCIONEXT is not set # CONFIG_NET_VENDOR_STMICRO is not set +# CONFIG_NET_VENDOR_SYNOPSYS is not set # CONFIG_NET_VENDOR_VIA is not set # CONFIG_NET_VENDOR_WIZNET is not set -# CONFIG_NET_VENDOR_SYNOPSYS is not set CONFIG_PPP=m CONFIG_PPP_BSDCOMP=m CONFIG_PPP_DEFLATE=m @@ -440,6 +438,7 @@ CONFIG_HIDRAW=y CONFIG_UHID=m # CONFIG_HID_GENERIC is not set # CONFIG_HID_ITE is not set +# CONFIG_HID_REDRAGON is not set # CONFIG_USB_SUPPORT is not set CONFIG_RTC_CLASS=y # CONFIG_RTC_NVMEM is not set @@ -458,7 +457,7 @@ CONFIG_FS_ENCRYPTION=m CONFIG_FANOTIFY=y CONFIG_QUOTA_NETLINK_INTERFACE=y # CONFIG_PRINT_QUOTA_WARNING is not set -CONFIG_AUTOFS4_FS=m +CONFIG_AUTOFS_FS=m CONFIG_FUSE_FS=m CONFIG_CUSE=m CONFIG_OVERLAY_FS=m @@ -559,6 +558,7 @@ CONFIG_TEST_KSTRTOX=m CONFIG_TEST_PRINTF=m CONFIG_TEST_BITMAP=m CONFIG_TEST_UUID=m +CONFIG_TEST_OVERFLOW=m CONFIG_TEST_RHASHTABLE=m CONFIG_TEST_HASH=m CONFIG_TEST_USER_COPY=m @@ -581,6 +581,11 @@ CONFIG_CRYPTO_CRYPTD=m CONFIG_CRYPTO_MCRYPTD=m CONFIG_CRYPTO_TEST=m CONFIG_CRYPTO_CHACHA20POLY1305=m +CONFIG_CRYPTO_AEGIS128=m +CONFIG_CRYPTO_AEGIS128L=m +CONFIG_CRYPTO_AEGIS256=m +CONFIG_CRYPTO_MORUS640=m +CONFIG_CRYPTO_MORUS1280=m CONFIG_CRYPTO_CFB=m CONFIG_CRYPTO_LRW=m CONFIG_CRYPTO_PCBC=m @@ -616,6 +621,7 @@ CONFIG_CRYPTO_LZO=m CONFIG_CRYPTO_842=m CONFIG_CRYPTO_LZ4=m CONFIG_CRYPTO_LZ4HC=m +CONFIG_CRYPTO_ZSTD=m CONFIG_CRYPTO_ANSI_CPRNG=m CONFIG_CRYPTO_DRBG_HASH=y CONFIG_CRYPTO_DRBG_CTR=y diff --git a/arch/m68k/configs/atari_defconfig b/arch/m68k/configs/atari_defconfig index 346c4e75edf8..b3103e51268a 100644 --- a/arch/m68k/configs/atari_defconfig +++ b/arch/m68k/configs/atari_defconfig @@ -50,6 +50,7 @@ CONFIG_UNIX_DIAG=m CONFIG_TLS=m CONFIG_XFRM_MIGRATE=y CONFIG_NET_KEY=y +CONFIG_XDP_SOCKETS=y CONFIG_INET=y CONFIG_IP_PNP=y CONFIG_IP_PNP_DHCP=y @@ -96,18 +97,14 @@ CONFIG_NF_CONNTRACK_SANE=m CONFIG_NF_CONNTRACK_SIP=m CONFIG_NF_CONNTRACK_TFTP=m CONFIG_NF_TABLES=m +CONFIG_NF_TABLES_SET=m CONFIG_NF_TABLES_INET=y CONFIG_NF_TABLES_NETDEV=y -CONFIG_NFT_EXTHDR=m -CONFIG_NFT_META=m -CONFIG_NFT_RT=m CONFIG_NFT_NUMGEN=m CONFIG_NFT_CT=m CONFIG_NFT_FLOW_OFFLOAD=m -CONFIG_NFT_SET_RBTREE=m -CONFIG_NFT_SET_HASH=m -CONFIG_NFT_SET_BITMAP=m CONFIG_NFT_COUNTER=m +CONFIG_NFT_CONNLIMIT=m CONFIG_NFT_LOG=m CONFIG_NFT_LIMIT=m CONFIG_NFT_MASQ=m @@ -120,6 +117,7 @@ CONFIG_NFT_REJECT=m CONFIG_NFT_COMPAT=m CONFIG_NFT_HASH=m CONFIG_NFT_FIB_INET=m +CONFIG_NFT_SOCKET=m CONFIG_NFT_DUP_NETDEV=m CONFIG_NFT_FWD_NETDEV=m CONFIG_NFT_FIB_NETDEV=m @@ -198,7 +196,6 @@ CONFIG_IP_SET_HASH_NETPORT=m CONFIG_IP_SET_HASH_NETIFACE=m CONFIG_IP_SET_LIST_SET=m CONFIG_NF_CONNTRACK_IPV4=m -CONFIG_NF_SOCKET_IPV4=m CONFIG_NFT_CHAIN_ROUTE_IPV4=m CONFIG_NFT_DUP_IPV4=m CONFIG_NFT_FIB_IPV4=m @@ -229,7 +226,6 @@ CONFIG_IP_NF_ARPTABLES=m CONFIG_IP_NF_ARPFILTER=m CONFIG_IP_NF_ARP_MANGLE=m CONFIG_NF_CONNTRACK_IPV6=m -CONFIG_NF_SOCKET_IPV6=m CONFIG_NFT_CHAIN_ROUTE_IPV6=m CONFIG_NFT_CHAIN_NAT_IPV6=m CONFIG_NFT_MASQ_IPV6=m @@ -258,7 +254,6 @@ CONFIG_IP6_NF_NAT=m CONFIG_IP6_NF_TARGET_MASQUERADE=m CONFIG_IP6_NF_TARGET_NPT=m CONFIG_NF_TABLES_BRIDGE=y -CONFIG_NFT_BRIDGE_META=m CONFIG_NFT_BRIDGE_REJECT=m CONFIG_NF_LOG_BRIDGE=m CONFIG_BRIDGE_NF_EBTABLES=m @@ -299,6 +294,7 @@ CONFIG_6LOWPAN_GHC_EXT_HDR_FRAG=m CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m CONFIG_DNS_RESOLVER=y CONFIG_BATMAN_ADV=m +# CONFIG_BATMAN_ADV_BATMAN_V is not set CONFIG_BATMAN_ADV_DAT=y CONFIG_BATMAN_ADV_NC=y CONFIG_BATMAN_ADV_MCAST=y @@ -354,6 +350,7 @@ CONFIG_DM_UNSTRIPED=m CONFIG_DM_CRYPT=m CONFIG_DM_SNAPSHOT=m CONFIG_DM_THIN_PROVISIONING=m +CONFIG_DM_WRITECACHE=m CONFIG_DM_ERA=m CONFIG_DM_MIRROR=m CONFIG_DM_RAID=m @@ -391,14 +388,15 @@ CONFIG_VETH=m CONFIG_ATARILANCE=y # CONFIG_NET_VENDOR_AQUANTIA is not set # CONFIG_NET_VENDOR_ARC is not set -# CONFIG_NET_CADENCE is not set # CONFIG_NET_VENDOR_BROADCOM is not set +# CONFIG_NET_CADENCE is not set # CONFIG_NET_VENDOR_CORTINA is not set # CONFIG_NET_VENDOR_EZCHIP is not set # CONFIG_NET_VENDOR_HUAWEI is not set # CONFIG_NET_VENDOR_INTEL is not set # CONFIG_NET_VENDOR_MARVELL is not set # CONFIG_NET_VENDOR_MICREL is not set +# CONFIG_NET_VENDOR_MICROSEMI is not set # CONFIG_NET_VENDOR_NETRONOME is not set # CONFIG_NET_VENDOR_NI is not set CONFIG_NE2000=y @@ -411,9 +409,9 @@ CONFIG_NE2000=y CONFIG_SMC91X=y # CONFIG_NET_VENDOR_SOCIONEXT is not set # CONFIG_NET_VENDOR_STMICRO is not set +# CONFIG_NET_VENDOR_SYNOPSYS is not set # CONFIG_NET_VENDOR_VIA is not set # CONFIG_NET_VENDOR_WIZNET is not set -# CONFIG_NET_VENDOR_SYNOPSYS is not set CONFIG_PPP=m CONFIG_PPP_BSDCOMP=m CONFIG_PPP_DEFLATE=m @@ -480,7 +478,7 @@ CONFIG_FS_ENCRYPTION=m CONFIG_FANOTIFY=y CONFIG_QUOTA_NETLINK_INTERFACE=y # CONFIG_PRINT_QUOTA_WARNING is not set -CONFIG_AUTOFS4_FS=m +CONFIG_AUTOFS_FS=m CONFIG_FUSE_FS=m CONFIG_CUSE=m CONFIG_OVERLAY_FS=m @@ -581,6 +579,7 @@ CONFIG_TEST_KSTRTOX=m CONFIG_TEST_PRINTF=m CONFIG_TEST_BITMAP=m CONFIG_TEST_UUID=m +CONFIG_TEST_OVERFLOW=m CONFIG_TEST_RHASHTABLE=m CONFIG_TEST_HASH=m CONFIG_TEST_USER_COPY=m @@ -603,6 +602,11 @@ CONFIG_CRYPTO_CRYPTD=m CONFIG_CRYPTO_MCRYPTD=m CONFIG_CRYPTO_TEST=m CONFIG_CRYPTO_CHACHA20POLY1305=m +CONFIG_CRYPTO_AEGIS128=m +CONFIG_CRYPTO_AEGIS128L=m +CONFIG_CRYPTO_AEGIS256=m +CONFIG_CRYPTO_MORUS640=m +CONFIG_CRYPTO_MORUS1280=m CONFIG_CRYPTO_CFB=m CONFIG_CRYPTO_LRW=m CONFIG_CRYPTO_PCBC=m @@ -638,6 +642,7 @@ CONFIG_CRYPTO_LZO=m CONFIG_CRYPTO_842=m CONFIG_CRYPTO_LZ4=m CONFIG_CRYPTO_LZ4HC=m +CONFIG_CRYPTO_ZSTD=m CONFIG_CRYPTO_ANSI_CPRNG=m CONFIG_CRYPTO_DRBG_HASH=y CONFIG_CRYPTO_DRBG_CTR=y diff --git a/arch/m68k/configs/bvme6000_defconfig b/arch/m68k/configs/bvme6000_defconfig index fca9c7aa71a3..fb7d651a4cab 100644 --- a/arch/m68k/configs/bvme6000_defconfig +++ b/arch/m68k/configs/bvme6000_defconfig @@ -48,6 +48,7 @@ CONFIG_UNIX_DIAG=m CONFIG_TLS=m CONFIG_XFRM_MIGRATE=y CONFIG_NET_KEY=y +CONFIG_XDP_SOCKETS=y CONFIG_INET=y CONFIG_IP_PNP=y CONFIG_IP_PNP_DHCP=y @@ -94,18 +95,14 @@ CONFIG_NF_CONNTRACK_SANE=m CONFIG_NF_CONNTRACK_SIP=m CONFIG_NF_CONNTRACK_TFTP=m CONFIG_NF_TABLES=m +CONFIG_NF_TABLES_SET=m CONFIG_NF_TABLES_INET=y CONFIG_NF_TABLES_NETDEV=y -CONFIG_NFT_EXTHDR=m -CONFIG_NFT_META=m -CONFIG_NFT_RT=m CONFIG_NFT_NUMGEN=m CONFIG_NFT_CT=m CONFIG_NFT_FLOW_OFFLOAD=m -CONFIG_NFT_SET_RBTREE=m -CONFIG_NFT_SET_HASH=m -CONFIG_NFT_SET_BITMAP=m CONFIG_NFT_COUNTER=m +CONFIG_NFT_CONNLIMIT=m CONFIG_NFT_LOG=m CONFIG_NFT_LIMIT=m CONFIG_NFT_MASQ=m @@ -118,6 +115,7 @@ CONFIG_NFT_REJECT=m CONFIG_NFT_COMPAT=m CONFIG_NFT_HASH=m CONFIG_NFT_FIB_INET=m +CONFIG_NFT_SOCKET=m CONFIG_NFT_DUP_NETDEV=m CONFIG_NFT_FWD_NETDEV=m CONFIG_NFT_FIB_NETDEV=m @@ -196,7 +194,6 @@ CONFIG_IP_SET_HASH_NETPORT=m CONFIG_IP_SET_HASH_NETIFACE=m CONFIG_IP_SET_LIST_SET=m CONFIG_NF_CONNTRACK_IPV4=m -CONFIG_NF_SOCKET_IPV4=m CONFIG_NFT_CHAIN_ROUTE_IPV4=m CONFIG_NFT_DUP_IPV4=m CONFIG_NFT_FIB_IPV4=m @@ -227,7 +224,6 @@ CONFIG_IP_NF_ARPTABLES=m CONFIG_IP_NF_ARPFILTER=m CONFIG_IP_NF_ARP_MANGLE=m CONFIG_NF_CONNTRACK_IPV6=m -CONFIG_NF_SOCKET_IPV6=m CONFIG_NFT_CHAIN_ROUTE_IPV6=m CONFIG_NFT_CHAIN_NAT_IPV6=m CONFIG_NFT_MASQ_IPV6=m @@ -256,7 +252,6 @@ CONFIG_IP6_NF_NAT=m CONFIG_IP6_NF_TARGET_MASQUERADE=m CONFIG_IP6_NF_TARGET_NPT=m CONFIG_NF_TABLES_BRIDGE=y -CONFIG_NFT_BRIDGE_META=m CONFIG_NFT_BRIDGE_REJECT=m CONFIG_NF_LOG_BRIDGE=m CONFIG_BRIDGE_NF_EBTABLES=m @@ -297,6 +292,7 @@ CONFIG_6LOWPAN_GHC_EXT_HDR_FRAG=m CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m CONFIG_DNS_RESOLVER=y CONFIG_BATMAN_ADV=m +# CONFIG_BATMAN_ADV_BATMAN_V is not set CONFIG_BATMAN_ADV_DAT=y CONFIG_BATMAN_ADV_NC=y CONFIG_BATMAN_ADV_MCAST=y @@ -344,6 +340,7 @@ CONFIG_DM_UNSTRIPED=m CONFIG_DM_CRYPT=m CONFIG_DM_SNAPSHOT=m CONFIG_DM_THIN_PROVISIONING=m +CONFIG_DM_WRITECACHE=m CONFIG_DM_ERA=m CONFIG_DM_MIRROR=m CONFIG_DM_RAID=m @@ -380,14 +377,15 @@ CONFIG_VETH=m # CONFIG_NET_VENDOR_AMAZON is not set # CONFIG_NET_VENDOR_AQUANTIA is not set # CONFIG_NET_VENDOR_ARC is not set -# CONFIG_NET_CADENCE is not set # CONFIG_NET_VENDOR_BROADCOM is not set +# CONFIG_NET_CADENCE is not set # CONFIG_NET_VENDOR_CORTINA is not set # CONFIG_NET_VENDOR_EZCHIP is not set # CONFIG_NET_VENDOR_HUAWEI is not set CONFIG_BVME6000_NET=y # CONFIG_NET_VENDOR_MARVELL is not set # CONFIG_NET_VENDOR_MICREL is not set +# CONFIG_NET_VENDOR_MICROSEMI is not set # CONFIG_NET_VENDOR_NATSEMI is not set # CONFIG_NET_VENDOR_NETRONOME is not set # CONFIG_NET_VENDOR_NI is not set @@ -399,9 +397,9 @@ CONFIG_BVME6000_NET=y # CONFIG_NET_VENDOR_SOLARFLARE is not set # CONFIG_NET_VENDOR_SOCIONEXT is not set # CONFIG_NET_VENDOR_STMICRO is not set +# CONFIG_NET_VENDOR_SYNOPSYS is not set # CONFIG_NET_VENDOR_VIA is not set # CONFIG_NET_VENDOR_WIZNET is not set -# CONFIG_NET_VENDOR_SYNOPSYS is not set CONFIG_PPP=m CONFIG_PPP_BSDCOMP=m CONFIG_PPP_DEFLATE=m @@ -433,6 +431,7 @@ CONFIG_HIDRAW=y CONFIG_UHID=m # CONFIG_HID_GENERIC is not set # CONFIG_HID_ITE is not set +# CONFIG_HID_REDRAGON is not set # CONFIG_USB_SUPPORT is not set CONFIG_RTC_CLASS=y # CONFIG_RTC_NVMEM is not set @@ -450,7 +449,7 @@ CONFIG_FS_ENCRYPTION=m CONFIG_FANOTIFY=y CONFIG_QUOTA_NETLINK_INTERFACE=y # CONFIG_PRINT_QUOTA_WARNING is not set -CONFIG_AUTOFS4_FS=m +CONFIG_AUTOFS_FS=m CONFIG_FUSE_FS=m CONFIG_CUSE=m CONFIG_OVERLAY_FS=m @@ -551,6 +550,7 @@ CONFIG_TEST_KSTRTOX=m CONFIG_TEST_PRINTF=m CONFIG_TEST_BITMAP=m CONFIG_TEST_UUID=m +CONFIG_TEST_OVERFLOW=m CONFIG_TEST_RHASHTABLE=m CONFIG_TEST_HASH=m CONFIG_TEST_USER_COPY=m @@ -573,6 +573,11 @@ CONFIG_CRYPTO_CRYPTD=m CONFIG_CRYPTO_MCRYPTD=m CONFIG_CRYPTO_TEST=m CONFIG_CRYPTO_CHACHA20POLY1305=m +CONFIG_CRYPTO_AEGIS128=m +CONFIG_CRYPTO_AEGIS128L=m +CONFIG_CRYPTO_AEGIS256=m +CONFIG_CRYPTO_MORUS640=m +CONFIG_CRYPTO_MORUS1280=m CONFIG_CRYPTO_CFB=m CONFIG_CRYPTO_LRW=m CONFIG_CRYPTO_PCBC=m @@ -608,6 +613,7 @@ CONFIG_CRYPTO_LZO=m CONFIG_CRYPTO_842=m CONFIG_CRYPTO_LZ4=m CONFIG_CRYPTO_LZ4HC=m +CONFIG_CRYPTO_ZSTD=m CONFIG_CRYPTO_ANSI_CPRNG=m CONFIG_CRYPTO_DRBG_HASH=y CONFIG_CRYPTO_DRBG_CTR=y diff --git a/arch/m68k/configs/hp300_defconfig b/arch/m68k/configs/hp300_defconfig index f9eab174915c..6b37f5537c39 100644 --- a/arch/m68k/configs/hp300_defconfig +++ b/arch/m68k/configs/hp300_defconfig @@ -50,6 +50,7 @@ CONFIG_UNIX_DIAG=m CONFIG_TLS=m CONFIG_XFRM_MIGRATE=y CONFIG_NET_KEY=y +CONFIG_XDP_SOCKETS=y CONFIG_INET=y CONFIG_IP_PNP=y CONFIG_IP_PNP_DHCP=y @@ -96,18 +97,14 @@ CONFIG_NF_CONNTRACK_SANE=m CONFIG_NF_CONNTRACK_SIP=m CONFIG_NF_CONNTRACK_TFTP=m CONFIG_NF_TABLES=m +CONFIG_NF_TABLES_SET=m CONFIG_NF_TABLES_INET=y CONFIG_NF_TABLES_NETDEV=y -CONFIG_NFT_EXTHDR=m -CONFIG_NFT_META=m -CONFIG_NFT_RT=m CONFIG_NFT_NUMGEN=m CONFIG_NFT_CT=m CONFIG_NFT_FLOW_OFFLOAD=m -CONFIG_NFT_SET_RBTREE=m -CONFIG_NFT_SET_HASH=m -CONFIG_NFT_SET_BITMAP=m CONFIG_NFT_COUNTER=m +CONFIG_NFT_CONNLIMIT=m CONFIG_NFT_LOG=m CONFIG_NFT_LIMIT=m CONFIG_NFT_MASQ=m @@ -120,6 +117,7 @@ CONFIG_NFT_REJECT=m CONFIG_NFT_COMPAT=m CONFIG_NFT_HASH=m CONFIG_NFT_FIB_INET=m +CONFIG_NFT_SOCKET=m CONFIG_NFT_DUP_NETDEV=m CONFIG_NFT_FWD_NETDEV=m CONFIG_NFT_FIB_NETDEV=m @@ -198,7 +196,6 @@ CONFIG_IP_SET_HASH_NETPORT=m CONFIG_IP_SET_HASH_NETIFACE=m CONFIG_IP_SET_LIST_SET=m CONFIG_NF_CONNTRACK_IPV4=m -CONFIG_NF_SOCKET_IPV4=m CONFIG_NFT_CHAIN_ROUTE_IPV4=m CONFIG_NFT_DUP_IPV4=m CONFIG_NFT_FIB_IPV4=m @@ -229,7 +226,6 @@ CONFIG_IP_NF_ARPTABLES=m CONFIG_IP_NF_ARPFILTER=m CONFIG_IP_NF_ARP_MANGLE=m CONFIG_NF_CONNTRACK_IPV6=m -CONFIG_NF_SOCKET_IPV6=m CONFIG_NFT_CHAIN_ROUTE_IPV6=m CONFIG_NFT_CHAIN_NAT_IPV6=m CONFIG_NFT_MASQ_IPV6=m @@ -258,7 +254,6 @@ CONFIG_IP6_NF_NAT=m CONFIG_IP6_NF_TARGET_MASQUERADE=m CONFIG_IP6_NF_TARGET_NPT=m CONFIG_NF_TABLES_BRIDGE=y -CONFIG_NFT_BRIDGE_META=m CONFIG_NFT_BRIDGE_REJECT=m CONFIG_NF_LOG_BRIDGE=m CONFIG_BRIDGE_NF_EBTABLES=m @@ -299,6 +294,7 @@ CONFIG_6LOWPAN_GHC_EXT_HDR_FRAG=m CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m CONFIG_DNS_RESOLVER=y CONFIG_BATMAN_ADV=m +# CONFIG_BATMAN_ADV_BATMAN_V is not set CONFIG_BATMAN_ADV_DAT=y CONFIG_BATMAN_ADV_NC=y CONFIG_BATMAN_ADV_MCAST=y @@ -345,6 +341,7 @@ CONFIG_DM_UNSTRIPED=m CONFIG_DM_CRYPT=m CONFIG_DM_SNAPSHOT=m CONFIG_DM_THIN_PROVISIONING=m +CONFIG_DM_WRITECACHE=m CONFIG_DM_ERA=m CONFIG_DM_MIRROR=m CONFIG_DM_RAID=m @@ -382,14 +379,15 @@ CONFIG_VETH=m CONFIG_HPLANCE=y # CONFIG_NET_VENDOR_AQUANTIA is not set # CONFIG_NET_VENDOR_ARC is not set -# CONFIG_NET_CADENCE is not set # CONFIG_NET_VENDOR_BROADCOM is not set +# CONFIG_NET_CADENCE is not set # CONFIG_NET_VENDOR_CORTINA is not set # CONFIG_NET_VENDOR_EZCHIP is not set # CONFIG_NET_VENDOR_HUAWEI is not set # CONFIG_NET_VENDOR_INTEL is not set # CONFIG_NET_VENDOR_MARVELL is not set # CONFIG_NET_VENDOR_MICREL is not set +# CONFIG_NET_VENDOR_MICROSEMI is not set # CONFIG_NET_VENDOR_NATSEMI is not set # CONFIG_NET_VENDOR_NETRONOME is not set # CONFIG_NET_VENDOR_NI is not set @@ -401,9 +399,9 @@ CONFIG_HPLANCE=y # CONFIG_NET_VENDOR_SOLARFLARE is not set # CONFIG_NET_VENDOR_SOCIONEXT is not set # CONFIG_NET_VENDOR_STMICRO is not set +# CONFIG_NET_VENDOR_SYNOPSYS is not set # CONFIG_NET_VENDOR_VIA is not set # CONFIG_NET_VENDOR_WIZNET is not set -# CONFIG_NET_VENDOR_SYNOPSYS is not set CONFIG_PPP=m CONFIG_PPP_BSDCOMP=m CONFIG_PPP_DEFLATE=m @@ -443,6 +441,7 @@ CONFIG_HIDRAW=y CONFIG_UHID=m # CONFIG_HID_GENERIC is not set # CONFIG_HID_ITE is not set +# CONFIG_HID_REDRAGON is not set # CONFIG_USB_SUPPORT is not set CONFIG_RTC_CLASS=y # CONFIG_RTC_NVMEM is not set @@ -460,7 +459,7 @@ CONFIG_FS_ENCRYPTION=m CONFIG_FANOTIFY=y CONFIG_QUOTA_NETLINK_INTERFACE=y # CONFIG_PRINT_QUOTA_WARNING is not set -CONFIG_AUTOFS4_FS=m +CONFIG_AUTOFS_FS=m CONFIG_FUSE_FS=m CONFIG_CUSE=m CONFIG_OVERLAY_FS=m @@ -561,6 +560,7 @@ CONFIG_TEST_KSTRTOX=m CONFIG_TEST_PRINTF=m CONFIG_TEST_BITMAP=m CONFIG_TEST_UUID=m +CONFIG_TEST_OVERFLOW=m CONFIG_TEST_RHASHTABLE=m CONFIG_TEST_HASH=m CONFIG_TEST_USER_COPY=m @@ -583,6 +583,11 @@ CONFIG_CRYPTO_CRYPTD=m CONFIG_CRYPTO_MCRYPTD=m CONFIG_CRYPTO_TEST=m CONFIG_CRYPTO_CHACHA20POLY1305=m +CONFIG_CRYPTO_AEGIS128=m +CONFIG_CRYPTO_AEGIS128L=m +CONFIG_CRYPTO_AEGIS256=m +CONFIG_CRYPTO_MORUS640=m +CONFIG_CRYPTO_MORUS1280=m CONFIG_CRYPTO_CFB=m CONFIG_CRYPTO_LRW=m CONFIG_CRYPTO_PCBC=m @@ -618,6 +623,7 @@ CONFIG_CRYPTO_LZO=m CONFIG_CRYPTO_842=m CONFIG_CRYPTO_LZ4=m CONFIG_CRYPTO_LZ4HC=m +CONFIG_CRYPTO_ZSTD=m CONFIG_CRYPTO_ANSI_CPRNG=m CONFIG_CRYPTO_DRBG_HASH=y CONFIG_CRYPTO_DRBG_CTR=y diff --git a/arch/m68k/configs/mac_defconfig b/arch/m68k/configs/mac_defconfig index b52e597899eb..930cc2965a11 100644 --- a/arch/m68k/configs/mac_defconfig +++ b/arch/m68k/configs/mac_defconfig @@ -49,6 +49,7 @@ CONFIG_UNIX_DIAG=m CONFIG_TLS=m CONFIG_XFRM_MIGRATE=y CONFIG_NET_KEY=y +CONFIG_XDP_SOCKETS=y CONFIG_INET=y CONFIG_IP_PNP=y CONFIG_IP_PNP_DHCP=y @@ -95,18 +96,14 @@ CONFIG_NF_CONNTRACK_SANE=m CONFIG_NF_CONNTRACK_SIP=m CONFIG_NF_CONNTRACK_TFTP=m CONFIG_NF_TABLES=m +CONFIG_NF_TABLES_SET=m CONFIG_NF_TABLES_INET=y CONFIG_NF_TABLES_NETDEV=y -CONFIG_NFT_EXTHDR=m -CONFIG_NFT_META=m -CONFIG_NFT_RT=m CONFIG_NFT_NUMGEN=m CONFIG_NFT_CT=m CONFIG_NFT_FLOW_OFFLOAD=m -CONFIG_NFT_SET_RBTREE=m -CONFIG_NFT_SET_HASH=m -CONFIG_NFT_SET_BITMAP=m CONFIG_NFT_COUNTER=m +CONFIG_NFT_CONNLIMIT=m CONFIG_NFT_LOG=m CONFIG_NFT_LIMIT=m CONFIG_NFT_MASQ=m @@ -119,6 +116,7 @@ CONFIG_NFT_REJECT=m CONFIG_NFT_COMPAT=m CONFIG_NFT_HASH=m CONFIG_NFT_FIB_INET=m +CONFIG_NFT_SOCKET=m CONFIG_NFT_DUP_NETDEV=m CONFIG_NFT_FWD_NETDEV=m CONFIG_NFT_FIB_NETDEV=m @@ -197,7 +195,6 @@ CONFIG_IP_SET_HASH_NETPORT=m CONFIG_IP_SET_HASH_NETIFACE=m CONFIG_IP_SET_LIST_SET=m CONFIG_NF_CONNTRACK_IPV4=m -CONFIG_NF_SOCKET_IPV4=m CONFIG_NFT_CHAIN_ROUTE_IPV4=m CONFIG_NFT_DUP_IPV4=m CONFIG_NFT_FIB_IPV4=m @@ -228,7 +225,6 @@ CONFIG_IP_NF_ARPTABLES=m CONFIG_IP_NF_ARPFILTER=m CONFIG_IP_NF_ARP_MANGLE=m CONFIG_NF_CONNTRACK_IPV6=m -CONFIG_NF_SOCKET_IPV6=m CONFIG_NFT_CHAIN_ROUTE_IPV6=m CONFIG_NFT_CHAIN_NAT_IPV6=m CONFIG_NFT_MASQ_IPV6=m @@ -257,7 +253,6 @@ CONFIG_IP6_NF_NAT=m CONFIG_IP6_NF_TARGET_MASQUERADE=m CONFIG_IP6_NF_TARGET_NPT=m CONFIG_NF_TABLES_BRIDGE=y -CONFIG_NFT_BRIDGE_META=m CONFIG_NFT_BRIDGE_REJECT=m CONFIG_NF_LOG_BRIDGE=m CONFIG_BRIDGE_NF_EBTABLES=m @@ -301,6 +296,7 @@ CONFIG_6LOWPAN_GHC_EXT_HDR_FRAG=m CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m CONFIG_DNS_RESOLVER=y CONFIG_BATMAN_ADV=m +# CONFIG_BATMAN_ADV_BATMAN_V is not set CONFIG_BATMAN_ADV_DAT=y CONFIG_BATMAN_ADV_NC=y CONFIG_BATMAN_ADV_MCAST=y @@ -354,6 +350,7 @@ CONFIG_DM_UNSTRIPED=m CONFIG_DM_CRYPT=m CONFIG_DM_SNAPSHOT=m CONFIG_DM_THIN_PROVISIONING=m +CONFIG_DM_WRITECACHE=m CONFIG_DM_ERA=m CONFIG_DM_MIRROR=m CONFIG_DM_RAID=m @@ -398,8 +395,8 @@ CONFIG_VETH=m CONFIG_MACMACE=y # CONFIG_NET_VENDOR_AQUANTIA is not set # CONFIG_NET_VENDOR_ARC is not set -# CONFIG_NET_CADENCE is not set # CONFIG_NET_VENDOR_BROADCOM is not set +# CONFIG_NET_CADENCE is not set CONFIG_MAC89x0=y # CONFIG_NET_VENDOR_CORTINA is not set # CONFIG_NET_VENDOR_EZCHIP is not set @@ -407,6 +404,7 @@ CONFIG_MAC89x0=y # CONFIG_NET_VENDOR_INTEL is not set # CONFIG_NET_VENDOR_MARVELL is not set # CONFIG_NET_VENDOR_MICREL is not set +# CONFIG_NET_VENDOR_MICROSEMI is not set CONFIG_MACSONIC=y # CONFIG_NET_VENDOR_NETRONOME is not set # CONFIG_NET_VENDOR_NI is not set @@ -420,9 +418,9 @@ CONFIG_MAC8390=y # CONFIG_NET_VENDOR_SMSC is not set # CONFIG_NET_VENDOR_SOCIONEXT is not set # CONFIG_NET_VENDOR_STMICRO is not set +# CONFIG_NET_VENDOR_SYNOPSYS is not set # CONFIG_NET_VENDOR_VIA is not set # CONFIG_NET_VENDOR_WIZNET is not set -# CONFIG_NET_VENDOR_SYNOPSYS is not set CONFIG_PPP=m CONFIG_PPP_BSDCOMP=m CONFIG_PPP_DEFLATE=m @@ -465,6 +463,7 @@ CONFIG_HIDRAW=y CONFIG_UHID=m # CONFIG_HID_GENERIC is not set # CONFIG_HID_ITE is not set +# CONFIG_HID_REDRAGON is not set # CONFIG_USB_SUPPORT is not set CONFIG_RTC_CLASS=y # CONFIG_RTC_NVMEM is not set @@ -482,7 +481,7 @@ CONFIG_FS_ENCRYPTION=m CONFIG_FANOTIFY=y CONFIG_QUOTA_NETLINK_INTERFACE=y # CONFIG_PRINT_QUOTA_WARNING is not set -CONFIG_AUTOFS4_FS=m +CONFIG_AUTOFS_FS=m CONFIG_FUSE_FS=m CONFIG_CUSE=m CONFIG_OVERLAY_FS=m @@ -583,6 +582,7 @@ CONFIG_TEST_KSTRTOX=m CONFIG_TEST_PRINTF=m CONFIG_TEST_BITMAP=m CONFIG_TEST_UUID=m +CONFIG_TEST_OVERFLOW=m CONFIG_TEST_RHASHTABLE=m CONFIG_TEST_HASH=m CONFIG_TEST_USER_COPY=m @@ -605,6 +605,11 @@ CONFIG_CRYPTO_CRYPTD=m CONFIG_CRYPTO_MCRYPTD=m CONFIG_CRYPTO_TEST=m CONFIG_CRYPTO_CHACHA20POLY1305=m +CONFIG_CRYPTO_AEGIS128=m +CONFIG_CRYPTO_AEGIS128L=m +CONFIG_CRYPTO_AEGIS256=m +CONFIG_CRYPTO_MORUS640=m +CONFIG_CRYPTO_MORUS1280=m CONFIG_CRYPTO_CFB=m CONFIG_CRYPTO_LRW=m CONFIG_CRYPTO_PCBC=m @@ -640,6 +645,7 @@ CONFIG_CRYPTO_LZO=m CONFIG_CRYPTO_842=m CONFIG_CRYPTO_LZ4=m CONFIG_CRYPTO_LZ4HC=m +CONFIG_CRYPTO_ZSTD=m CONFIG_CRYPTO_ANSI_CPRNG=m CONFIG_CRYPTO_DRBG_HASH=y CONFIG_CRYPTO_DRBG_CTR=y diff --git a/arch/m68k/configs/multi_defconfig b/arch/m68k/configs/multi_defconfig index 2a84eeec5b02..e7dd25300127 100644 --- a/arch/m68k/configs/multi_defconfig +++ b/arch/m68k/configs/multi_defconfig @@ -59,6 +59,7 @@ CONFIG_UNIX_DIAG=m CONFIG_TLS=m CONFIG_XFRM_MIGRATE=y CONFIG_NET_KEY=y +CONFIG_XDP_SOCKETS=y CONFIG_INET=y CONFIG_IP_PNP=y CONFIG_IP_PNP_DHCP=y @@ -105,18 +106,14 @@ CONFIG_NF_CONNTRACK_SANE=m CONFIG_NF_CONNTRACK_SIP=m CONFIG_NF_CONNTRACK_TFTP=m CONFIG_NF_TABLES=m +CONFIG_NF_TABLES_SET=m CONFIG_NF_TABLES_INET=y CONFIG_NF_TABLES_NETDEV=y -CONFIG_NFT_EXTHDR=m -CONFIG_NFT_META=m -CONFIG_NFT_RT=m CONFIG_NFT_NUMGEN=m CONFIG_NFT_CT=m CONFIG_NFT_FLOW_OFFLOAD=m -CONFIG_NFT_SET_RBTREE=m -CONFIG_NFT_SET_HASH=m -CONFIG_NFT_SET_BITMAP=m CONFIG_NFT_COUNTER=m +CONFIG_NFT_CONNLIMIT=m CONFIG_NFT_LOG=m CONFIG_NFT_LIMIT=m CONFIG_NFT_MASQ=m @@ -129,6 +126,7 @@ CONFIG_NFT_REJECT=m CONFIG_NFT_COMPAT=m CONFIG_NFT_HASH=m CONFIG_NFT_FIB_INET=m +CONFIG_NFT_SOCKET=m CONFIG_NFT_DUP_NETDEV=m CONFIG_NFT_FWD_NETDEV=m CONFIG_NFT_FIB_NETDEV=m @@ -207,7 +205,6 @@ CONFIG_IP_SET_HASH_NETPORT=m CONFIG_IP_SET_HASH_NETIFACE=m CONFIG_IP_SET_LIST_SET=m CONFIG_NF_CONNTRACK_IPV4=m -CONFIG_NF_SOCKET_IPV4=m CONFIG_NFT_CHAIN_ROUTE_IPV4=m CONFIG_NFT_DUP_IPV4=m CONFIG_NFT_FIB_IPV4=m @@ -238,7 +235,6 @@ CONFIG_IP_NF_ARPTABLES=m CONFIG_IP_NF_ARPFILTER=m CONFIG_IP_NF_ARP_MANGLE=m CONFIG_NF_CONNTRACK_IPV6=m -CONFIG_NF_SOCKET_IPV6=m CONFIG_NFT_CHAIN_ROUTE_IPV6=m CONFIG_NFT_CHAIN_NAT_IPV6=m CONFIG_NFT_MASQ_IPV6=m @@ -267,7 +263,6 @@ CONFIG_IP6_NF_NAT=m CONFIG_IP6_NF_TARGET_MASQUERADE=m CONFIG_IP6_NF_TARGET_NPT=m CONFIG_NF_TABLES_BRIDGE=y -CONFIG_NFT_BRIDGE_META=m CONFIG_NFT_BRIDGE_REJECT=m CONFIG_NF_LOG_BRIDGE=m CONFIG_BRIDGE_NF_EBTABLES=m @@ -311,6 +306,7 @@ CONFIG_6LOWPAN_GHC_EXT_HDR_FRAG=m CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m CONFIG_DNS_RESOLVER=y CONFIG_BATMAN_ADV=m +# CONFIG_BATMAN_ADV_BATMAN_V is not set CONFIG_BATMAN_ADV_DAT=y CONFIG_BATMAN_ADV_NC=y CONFIG_BATMAN_ADV_MCAST=y @@ -373,6 +369,7 @@ CONFIG_A2091_SCSI=y CONFIG_GVP11_SCSI=y CONFIG_SCSI_A4000T=y CONFIG_SCSI_ZORRO7XX=y +CONFIG_SCSI_ZORRO_ESP=y CONFIG_ATARI_SCSI=y CONFIG_MAC_SCSI=y CONFIG_SCSI_MAC_ESP=y @@ -387,6 +384,7 @@ CONFIG_DM_UNSTRIPED=m CONFIG_DM_CRYPT=m CONFIG_DM_SNAPSHOT=m CONFIG_DM_THIN_PROVISIONING=m +CONFIG_DM_WRITECACHE=m CONFIG_DM_ERA=m CONFIG_DM_MIRROR=m CONFIG_DM_RAID=m @@ -438,8 +436,8 @@ CONFIG_SUN3LANCE=y CONFIG_MACMACE=y # CONFIG_NET_VENDOR_AQUANTIA is not set # CONFIG_NET_VENDOR_ARC is not set -# CONFIG_NET_CADENCE is not set # CONFIG_NET_VENDOR_BROADCOM is not set +# CONFIG_NET_CADENCE is not set CONFIG_MAC89x0=y # CONFIG_NET_VENDOR_CORTINA is not set # CONFIG_NET_VENDOR_EZCHIP is not set @@ -449,9 +447,11 @@ CONFIG_BVME6000_NET=y CONFIG_MVME16x_NET=y # CONFIG_NET_VENDOR_MARVELL is not set # CONFIG_NET_VENDOR_MICREL is not set +# CONFIG_NET_VENDOR_MICROSEMI is not set CONFIG_MACSONIC=y # CONFIG_NET_VENDOR_NETRONOME is not set # CONFIG_NET_VENDOR_NI is not set +CONFIG_XSURF100=y CONFIG_HYDRA=y CONFIG_MAC8390=y CONFIG_NE2000=y @@ -466,9 +466,9 @@ CONFIG_ZORRO8390=y CONFIG_SMC91X=y # CONFIG_NET_VENDOR_SOCIONEXT is not set # CONFIG_NET_VENDOR_STMICRO is not set +# CONFIG_NET_VENDOR_SYNOPSYS is not set # CONFIG_NET_VENDOR_VIA is not set # CONFIG_NET_VENDOR_WIZNET is not set -# CONFIG_NET_VENDOR_SYNOPSYS is not set CONFIG_PLIP=m CONFIG_PPP=m CONFIG_PPP_BSDCOMP=m @@ -533,6 +533,7 @@ CONFIG_HIDRAW=y CONFIG_UHID=m # CONFIG_HID_GENERIC is not set # CONFIG_HID_ITE is not set +# CONFIG_HID_REDRAGON is not set # CONFIG_USB_SUPPORT is not set CONFIG_RTC_CLASS=y # CONFIG_RTC_NVMEM is not set @@ -562,7 +563,7 @@ CONFIG_FS_ENCRYPTION=m CONFIG_FANOTIFY=y CONFIG_QUOTA_NETLINK_INTERFACE=y # CONFIG_PRINT_QUOTA_WARNING is not set -CONFIG_AUTOFS4_FS=m +CONFIG_AUTOFS_FS=m CONFIG_FUSE_FS=m CONFIG_CUSE=m CONFIG_OVERLAY_FS=m @@ -663,6 +664,7 @@ CONFIG_TEST_KSTRTOX=m CONFIG_TEST_PRINTF=m CONFIG_TEST_BITMAP=m CONFIG_TEST_UUID=m +CONFIG_TEST_OVERFLOW=m CONFIG_TEST_RHASHTABLE=m CONFIG_TEST_HASH=m CONFIG_TEST_USER_COPY=m @@ -685,6 +687,11 @@ CONFIG_CRYPTO_CRYPTD=m CONFIG_CRYPTO_MCRYPTD=m CONFIG_CRYPTO_TEST=m CONFIG_CRYPTO_CHACHA20POLY1305=m +CONFIG_CRYPTO_AEGIS128=m +CONFIG_CRYPTO_AEGIS128L=m +CONFIG_CRYPTO_AEGIS256=m +CONFIG_CRYPTO_MORUS640=m +CONFIG_CRYPTO_MORUS1280=m CONFIG_CRYPTO_CFB=m CONFIG_CRYPTO_LRW=m CONFIG_CRYPTO_PCBC=m @@ -720,6 +727,7 @@ CONFIG_CRYPTO_LZO=m CONFIG_CRYPTO_842=m CONFIG_CRYPTO_LZ4=m CONFIG_CRYPTO_LZ4HC=m +CONFIG_CRYPTO_ZSTD=m CONFIG_CRYPTO_ANSI_CPRNG=m CONFIG_CRYPTO_DRBG_HASH=y CONFIG_CRYPTO_DRBG_CTR=y diff --git a/arch/m68k/configs/mvme147_defconfig b/arch/m68k/configs/mvme147_defconfig index 476e69994340..b383327fd77a 100644 --- a/arch/m68k/configs/mvme147_defconfig +++ b/arch/m68k/configs/mvme147_defconfig @@ -47,6 +47,7 @@ CONFIG_UNIX_DIAG=m CONFIG_TLS=m CONFIG_XFRM_MIGRATE=y CONFIG_NET_KEY=y +CONFIG_XDP_SOCKETS=y CONFIG_INET=y CONFIG_IP_PNP=y CONFIG_IP_PNP_DHCP=y @@ -93,18 +94,14 @@ CONFIG_NF_CONNTRACK_SANE=m CONFIG_NF_CONNTRACK_SIP=m CONFIG_NF_CONNTRACK_TFTP=m CONFIG_NF_TABLES=m +CONFIG_NF_TABLES_SET=m CONFIG_NF_TABLES_INET=y CONFIG_NF_TABLES_NETDEV=y -CONFIG_NFT_EXTHDR=m -CONFIG_NFT_META=m -CONFIG_NFT_RT=m CONFIG_NFT_NUMGEN=m CONFIG_NFT_CT=m CONFIG_NFT_FLOW_OFFLOAD=m -CONFIG_NFT_SET_RBTREE=m -CONFIG_NFT_SET_HASH=m -CONFIG_NFT_SET_BITMAP=m CONFIG_NFT_COUNTER=m +CONFIG_NFT_CONNLIMIT=m CONFIG_NFT_LOG=m CONFIG_NFT_LIMIT=m CONFIG_NFT_MASQ=m @@ -117,6 +114,7 @@ CONFIG_NFT_REJECT=m CONFIG_NFT_COMPAT=m CONFIG_NFT_HASH=m CONFIG_NFT_FIB_INET=m +CONFIG_NFT_SOCKET=m CONFIG_NFT_DUP_NETDEV=m CONFIG_NFT_FWD_NETDEV=m CONFIG_NFT_FIB_NETDEV=m @@ -195,7 +193,6 @@ CONFIG_IP_SET_HASH_NETPORT=m CONFIG_IP_SET_HASH_NETIFACE=m CONFIG_IP_SET_LIST_SET=m CONFIG_NF_CONNTRACK_IPV4=m -CONFIG_NF_SOCKET_IPV4=m CONFIG_NFT_CHAIN_ROUTE_IPV4=m CONFIG_NFT_DUP_IPV4=m CONFIG_NFT_FIB_IPV4=m @@ -226,7 +223,6 @@ CONFIG_IP_NF_ARPTABLES=m CONFIG_IP_NF_ARPFILTER=m CONFIG_IP_NF_ARP_MANGLE=m CONFIG_NF_CONNTRACK_IPV6=m -CONFIG_NF_SOCKET_IPV6=m CONFIG_NFT_CHAIN_ROUTE_IPV6=m CONFIG_NFT_CHAIN_NAT_IPV6=m CONFIG_NFT_MASQ_IPV6=m @@ -255,7 +251,6 @@ CONFIG_IP6_NF_NAT=m CONFIG_IP6_NF_TARGET_MASQUERADE=m CONFIG_IP6_NF_TARGET_NPT=m CONFIG_NF_TABLES_BRIDGE=y -CONFIG_NFT_BRIDGE_META=m CONFIG_NFT_BRIDGE_REJECT=m CONFIG_NF_LOG_BRIDGE=m CONFIG_BRIDGE_NF_EBTABLES=m @@ -296,6 +291,7 @@ CONFIG_6LOWPAN_GHC_EXT_HDR_FRAG=m CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m CONFIG_DNS_RESOLVER=y CONFIG_BATMAN_ADV=m +# CONFIG_BATMAN_ADV_BATMAN_V is not set CONFIG_BATMAN_ADV_DAT=y CONFIG_BATMAN_ADV_NC=y CONFIG_BATMAN_ADV_MCAST=y @@ -343,6 +339,7 @@ CONFIG_DM_UNSTRIPED=m CONFIG_DM_CRYPT=m CONFIG_DM_SNAPSHOT=m CONFIG_DM_THIN_PROVISIONING=m +CONFIG_DM_WRITECACHE=m CONFIG_DM_ERA=m CONFIG_DM_MIRROR=m CONFIG_DM_RAID=m @@ -380,14 +377,15 @@ CONFIG_VETH=m CONFIG_MVME147_NET=y # CONFIG_NET_VENDOR_AQUANTIA is not set # CONFIG_NET_VENDOR_ARC is not set -# CONFIG_NET_CADENCE is not set # CONFIG_NET_VENDOR_BROADCOM is not set +# CONFIG_NET_CADENCE is not set # CONFIG_NET_VENDOR_CORTINA is not set # CONFIG_NET_VENDOR_EZCHIP is not set # CONFIG_NET_VENDOR_HUAWEI is not set # CONFIG_NET_VENDOR_INTEL is not set # CONFIG_NET_VENDOR_MARVELL is not set # CONFIG_NET_VENDOR_MICREL is not set +# CONFIG_NET_VENDOR_MICROSEMI is not set # CONFIG_NET_VENDOR_NATSEMI is not set # CONFIG_NET_VENDOR_NETRONOME is not set # CONFIG_NET_VENDOR_NI is not set @@ -399,9 +397,9 @@ CONFIG_MVME147_NET=y # CONFIG_NET_VENDOR_SOLARFLARE is not set # CONFIG_NET_VENDOR_SOCIONEXT is not set # CONFIG_NET_VENDOR_STMICRO is not set +# CONFIG_NET_VENDOR_SYNOPSYS is not set # CONFIG_NET_VENDOR_VIA is not set # CONFIG_NET_VENDOR_WIZNET is not set -# CONFIG_NET_VENDOR_SYNOPSYS is not set CONFIG_PPP=m CONFIG_PPP_BSDCOMP=m CONFIG_PPP_DEFLATE=m @@ -433,6 +431,7 @@ CONFIG_HIDRAW=y CONFIG_UHID=m # CONFIG_HID_GENERIC is not set # CONFIG_HID_ITE is not set +# CONFIG_HID_REDRAGON is not set # CONFIG_USB_SUPPORT is not set CONFIG_RTC_CLASS=y # CONFIG_RTC_NVMEM is not set @@ -450,7 +449,7 @@ CONFIG_FS_ENCRYPTION=m CONFIG_FANOTIFY=y CONFIG_QUOTA_NETLINK_INTERFACE=y # CONFIG_PRINT_QUOTA_WARNING is not set -CONFIG_AUTOFS4_FS=m +CONFIG_AUTOFS_FS=m CONFIG_FUSE_FS=m CONFIG_CUSE=m CONFIG_OVERLAY_FS=m @@ -551,6 +550,7 @@ CONFIG_TEST_KSTRTOX=m CONFIG_TEST_PRINTF=m CONFIG_TEST_BITMAP=m CONFIG_TEST_UUID=m +CONFIG_TEST_OVERFLOW=m CONFIG_TEST_RHASHTABLE=m CONFIG_TEST_HASH=m CONFIG_TEST_USER_COPY=m @@ -573,6 +573,11 @@ CONFIG_CRYPTO_CRYPTD=m CONFIG_CRYPTO_MCRYPTD=m CONFIG_CRYPTO_TEST=m CONFIG_CRYPTO_CHACHA20POLY1305=m +CONFIG_CRYPTO_AEGIS128=m +CONFIG_CRYPTO_AEGIS128L=m +CONFIG_CRYPTO_AEGIS256=m +CONFIG_CRYPTO_MORUS640=m +CONFIG_CRYPTO_MORUS1280=m CONFIG_CRYPTO_CFB=m CONFIG_CRYPTO_LRW=m CONFIG_CRYPTO_PCBC=m @@ -608,6 +613,7 @@ CONFIG_CRYPTO_LZO=m CONFIG_CRYPTO_842=m CONFIG_CRYPTO_LZ4=m CONFIG_CRYPTO_LZ4HC=m +CONFIG_CRYPTO_ZSTD=m CONFIG_CRYPTO_ANSI_CPRNG=m CONFIG_CRYPTO_DRBG_HASH=y CONFIG_CRYPTO_DRBG_CTR=y diff --git a/arch/m68k/configs/mvme16x_defconfig b/arch/m68k/configs/mvme16x_defconfig index 1477cda9146e..9783d3deb9e9 100644 --- a/arch/m68k/configs/mvme16x_defconfig +++ b/arch/m68k/configs/mvme16x_defconfig @@ -48,6 +48,7 @@ CONFIG_UNIX_DIAG=m CONFIG_TLS=m CONFIG_XFRM_MIGRATE=y CONFIG_NET_KEY=y +CONFIG_XDP_SOCKETS=y CONFIG_INET=y CONFIG_IP_PNP=y CONFIG_IP_PNP_DHCP=y @@ -94,18 +95,14 @@ CONFIG_NF_CONNTRACK_SANE=m CONFIG_NF_CONNTRACK_SIP=m CONFIG_NF_CONNTRACK_TFTP=m CONFIG_NF_TABLES=m +CONFIG_NF_TABLES_SET=m CONFIG_NF_TABLES_INET=y CONFIG_NF_TABLES_NETDEV=y -CONFIG_NFT_EXTHDR=m -CONFIG_NFT_META=m -CONFIG_NFT_RT=m CONFIG_NFT_NUMGEN=m CONFIG_NFT_CT=m CONFIG_NFT_FLOW_OFFLOAD=m -CONFIG_NFT_SET_RBTREE=m -CONFIG_NFT_SET_HASH=m -CONFIG_NFT_SET_BITMAP=m CONFIG_NFT_COUNTER=m +CONFIG_NFT_CONNLIMIT=m CONFIG_NFT_LOG=m CONFIG_NFT_LIMIT=m CONFIG_NFT_MASQ=m @@ -118,6 +115,7 @@ CONFIG_NFT_REJECT=m CONFIG_NFT_COMPAT=m CONFIG_NFT_HASH=m CONFIG_NFT_FIB_INET=m +CONFIG_NFT_SOCKET=m CONFIG_NFT_DUP_NETDEV=m CONFIG_NFT_FWD_NETDEV=m CONFIG_NFT_FIB_NETDEV=m @@ -196,7 +194,6 @@ CONFIG_IP_SET_HASH_NETPORT=m CONFIG_IP_SET_HASH_NETIFACE=m CONFIG_IP_SET_LIST_SET=m CONFIG_NF_CONNTRACK_IPV4=m -CONFIG_NF_SOCKET_IPV4=m CONFIG_NFT_CHAIN_ROUTE_IPV4=m CONFIG_NFT_DUP_IPV4=m CONFIG_NFT_FIB_IPV4=m @@ -227,7 +224,6 @@ CONFIG_IP_NF_ARPTABLES=m CONFIG_IP_NF_ARPFILTER=m CONFIG_IP_NF_ARP_MANGLE=m CONFIG_NF_CONNTRACK_IPV6=m -CONFIG_NF_SOCKET_IPV6=m CONFIG_NFT_CHAIN_ROUTE_IPV6=m CONFIG_NFT_CHAIN_NAT_IPV6=m CONFIG_NFT_MASQ_IPV6=m @@ -256,7 +252,6 @@ CONFIG_IP6_NF_NAT=m CONFIG_IP6_NF_TARGET_MASQUERADE=m CONFIG_IP6_NF_TARGET_NPT=m CONFIG_NF_TABLES_BRIDGE=y -CONFIG_NFT_BRIDGE_META=m CONFIG_NFT_BRIDGE_REJECT=m CONFIG_NF_LOG_BRIDGE=m CONFIG_BRIDGE_NF_EBTABLES=m @@ -297,6 +292,7 @@ CONFIG_6LOWPAN_GHC_EXT_HDR_FRAG=m CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m CONFIG_DNS_RESOLVER=y CONFIG_BATMAN_ADV=m +# CONFIG_BATMAN_ADV_BATMAN_V is not set CONFIG_BATMAN_ADV_DAT=y CONFIG_BATMAN_ADV_NC=y CONFIG_BATMAN_ADV_MCAST=y @@ -344,6 +340,7 @@ CONFIG_DM_UNSTRIPED=m CONFIG_DM_CRYPT=m CONFIG_DM_SNAPSHOT=m CONFIG_DM_THIN_PROVISIONING=m +CONFIG_DM_WRITECACHE=m CONFIG_DM_ERA=m CONFIG_DM_MIRROR=m CONFIG_DM_RAID=m @@ -380,14 +377,15 @@ CONFIG_VETH=m # CONFIG_NET_VENDOR_AMAZON is not set # CONFIG_NET_VENDOR_AQUANTIA is not set # CONFIG_NET_VENDOR_ARC is not set -# CONFIG_NET_CADENCE is not set # CONFIG_NET_VENDOR_BROADCOM is not set +# CONFIG_NET_CADENCE is not set # CONFIG_NET_VENDOR_CORTINA is not set # CONFIG_NET_VENDOR_EZCHIP is not set # CONFIG_NET_VENDOR_HUAWEI is not set CONFIG_MVME16x_NET=y # CONFIG_NET_VENDOR_MARVELL is not set # CONFIG_NET_VENDOR_MICREL is not set +# CONFIG_NET_VENDOR_MICROSEMI is not set # CONFIG_NET_VENDOR_NATSEMI is not set # CONFIG_NET_VENDOR_NETRONOME is not set # CONFIG_NET_VENDOR_NI is not set @@ -399,9 +397,9 @@ CONFIG_MVME16x_NET=y # CONFIG_NET_VENDOR_SOLARFLARE is not set # CONFIG_NET_VENDOR_SOCIONEXT is not set # CONFIG_NET_VENDOR_STMICRO is not set +# CONFIG_NET_VENDOR_SYNOPSYS is not set # CONFIG_NET_VENDOR_VIA is not set # CONFIG_NET_VENDOR_WIZNET is not set -# CONFIG_NET_VENDOR_SYNOPSYS is not set CONFIG_PPP=m CONFIG_PPP_BSDCOMP=m CONFIG_PPP_DEFLATE=m @@ -433,6 +431,7 @@ CONFIG_HIDRAW=y CONFIG_UHID=m # CONFIG_HID_GENERIC is not set # CONFIG_HID_ITE is not set +# CONFIG_HID_REDRAGON is not set # CONFIG_USB_SUPPORT is not set CONFIG_RTC_CLASS=y # CONFIG_RTC_NVMEM is not set @@ -450,7 +449,7 @@ CONFIG_FS_ENCRYPTION=m CONFIG_FANOTIFY=y CONFIG_QUOTA_NETLINK_INTERFACE=y # CONFIG_PRINT_QUOTA_WARNING is not set -CONFIG_AUTOFS4_FS=m +CONFIG_AUTOFS_FS=m CONFIG_FUSE_FS=m CONFIG_CUSE=m CONFIG_OVERLAY_FS=m @@ -551,6 +550,7 @@ CONFIG_TEST_KSTRTOX=m CONFIG_TEST_PRINTF=m CONFIG_TEST_BITMAP=m CONFIG_TEST_UUID=m +CONFIG_TEST_OVERFLOW=m CONFIG_TEST_RHASHTABLE=m CONFIG_TEST_HASH=m CONFIG_TEST_USER_COPY=m @@ -573,6 +573,11 @@ CONFIG_CRYPTO_CRYPTD=m CONFIG_CRYPTO_MCRYPTD=m CONFIG_CRYPTO_TEST=m CONFIG_CRYPTO_CHACHA20POLY1305=m +CONFIG_CRYPTO_AEGIS128=m +CONFIG_CRYPTO_AEGIS128L=m +CONFIG_CRYPTO_AEGIS256=m +CONFIG_CRYPTO_MORUS640=m +CONFIG_CRYPTO_MORUS1280=m CONFIG_CRYPTO_CFB=m CONFIG_CRYPTO_LRW=m CONFIG_CRYPTO_PCBC=m @@ -608,6 +613,7 @@ CONFIG_CRYPTO_LZO=m CONFIG_CRYPTO_842=m CONFIG_CRYPTO_LZ4=m CONFIG_CRYPTO_LZ4HC=m +CONFIG_CRYPTO_ZSTD=m CONFIG_CRYPTO_ANSI_CPRNG=m CONFIG_CRYPTO_DRBG_HASH=y CONFIG_CRYPTO_DRBG_CTR=y diff --git a/arch/m68k/configs/q40_defconfig b/arch/m68k/configs/q40_defconfig index b3a543dc48a0..a35d10ee10cb 100644 --- a/arch/m68k/configs/q40_defconfig +++ b/arch/m68k/configs/q40_defconfig @@ -48,6 +48,7 @@ CONFIG_UNIX_DIAG=m CONFIG_TLS=m CONFIG_XFRM_MIGRATE=y CONFIG_NET_KEY=y +CONFIG_XDP_SOCKETS=y CONFIG_INET=y CONFIG_IP_PNP=y CONFIG_IP_PNP_DHCP=y @@ -94,18 +95,14 @@ CONFIG_NF_CONNTRACK_SANE=m CONFIG_NF_CONNTRACK_SIP=m CONFIG_NF_CONNTRACK_TFTP=m CONFIG_NF_TABLES=m +CONFIG_NF_TABLES_SET=m CONFIG_NF_TABLES_INET=y CONFIG_NF_TABLES_NETDEV=y -CONFIG_NFT_EXTHDR=m -CONFIG_NFT_META=m -CONFIG_NFT_RT=m CONFIG_NFT_NUMGEN=m CONFIG_NFT_CT=m CONFIG_NFT_FLOW_OFFLOAD=m -CONFIG_NFT_SET_RBTREE=m -CONFIG_NFT_SET_HASH=m -CONFIG_NFT_SET_BITMAP=m CONFIG_NFT_COUNTER=m +CONFIG_NFT_CONNLIMIT=m CONFIG_NFT_LOG=m CONFIG_NFT_LIMIT=m CONFIG_NFT_MASQ=m @@ -118,6 +115,7 @@ CONFIG_NFT_REJECT=m CONFIG_NFT_COMPAT=m CONFIG_NFT_HASH=m CONFIG_NFT_FIB_INET=m +CONFIG_NFT_SOCKET=m CONFIG_NFT_DUP_NETDEV=m CONFIG_NFT_FWD_NETDEV=m CONFIG_NFT_FIB_NETDEV=m @@ -196,7 +194,6 @@ CONFIG_IP_SET_HASH_NETPORT=m CONFIG_IP_SET_HASH_NETIFACE=m CONFIG_IP_SET_LIST_SET=m CONFIG_NF_CONNTRACK_IPV4=m -CONFIG_NF_SOCKET_IPV4=m CONFIG_NFT_CHAIN_ROUTE_IPV4=m CONFIG_NFT_DUP_IPV4=m CONFIG_NFT_FIB_IPV4=m @@ -227,7 +224,6 @@ CONFIG_IP_NF_ARPTABLES=m CONFIG_IP_NF_ARPFILTER=m CONFIG_IP_NF_ARP_MANGLE=m CONFIG_NF_CONNTRACK_IPV6=m -CONFIG_NF_SOCKET_IPV6=m CONFIG_NFT_CHAIN_ROUTE_IPV6=m CONFIG_NFT_CHAIN_NAT_IPV6=m CONFIG_NFT_MASQ_IPV6=m @@ -256,7 +252,6 @@ CONFIG_IP6_NF_NAT=m CONFIG_IP6_NF_TARGET_MASQUERADE=m CONFIG_IP6_NF_TARGET_NPT=m CONFIG_NF_TABLES_BRIDGE=y -CONFIG_NFT_BRIDGE_META=m CONFIG_NFT_BRIDGE_REJECT=m CONFIG_NF_LOG_BRIDGE=m CONFIG_BRIDGE_NF_EBTABLES=m @@ -297,6 +292,7 @@ CONFIG_6LOWPAN_GHC_EXT_HDR_FRAG=m CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m CONFIG_DNS_RESOLVER=y CONFIG_BATMAN_ADV=m +# CONFIG_BATMAN_ADV_BATMAN_V is not set CONFIG_BATMAN_ADV_DAT=y CONFIG_BATMAN_ADV_NC=y CONFIG_BATMAN_ADV_MCAST=y @@ -350,6 +346,7 @@ CONFIG_DM_UNSTRIPED=m CONFIG_DM_CRYPT=m CONFIG_DM_SNAPSHOT=m CONFIG_DM_THIN_PROVISIONING=m +CONFIG_DM_WRITECACHE=m CONFIG_DM_ERA=m CONFIG_DM_MIRROR=m CONFIG_DM_RAID=m @@ -388,8 +385,8 @@ CONFIG_VETH=m # CONFIG_NET_VENDOR_AMD is not set # CONFIG_NET_VENDOR_AQUANTIA is not set # CONFIG_NET_VENDOR_ARC is not set -# CONFIG_NET_CADENCE is not set # CONFIG_NET_VENDOR_BROADCOM is not set +# CONFIG_NET_CADENCE is not set # CONFIG_NET_VENDOR_CIRRUS is not set # CONFIG_NET_VENDOR_CORTINA is not set # CONFIG_NET_VENDOR_EZCHIP is not set @@ -398,6 +395,7 @@ CONFIG_VETH=m # CONFIG_NET_VENDOR_INTEL is not set # CONFIG_NET_VENDOR_MARVELL is not set # CONFIG_NET_VENDOR_MICREL is not set +# CONFIG_NET_VENDOR_MICROSEMI is not set # CONFIG_NET_VENDOR_NETRONOME is not set # CONFIG_NET_VENDOR_NI is not set CONFIG_NE2000=y @@ -410,9 +408,9 @@ CONFIG_NE2000=y # CONFIG_NET_VENDOR_SMSC is not set # CONFIG_NET_VENDOR_SOCIONEXT is not set # CONFIG_NET_VENDOR_STMICRO is not set +# CONFIG_NET_VENDOR_SYNOPSYS is not set # CONFIG_NET_VENDOR_VIA is not set # CONFIG_NET_VENDOR_WIZNET is not set -# CONFIG_NET_VENDOR_SYNOPSYS is not set CONFIG_PLIP=m CONFIG_PPP=m CONFIG_PPP_BSDCOMP=m @@ -455,6 +453,7 @@ CONFIG_HIDRAW=y CONFIG_UHID=m # CONFIG_HID_GENERIC is not set # CONFIG_HID_ITE is not set +# CONFIG_HID_REDRAGON is not set # CONFIG_USB_SUPPORT is not set CONFIG_RTC_CLASS=y # CONFIG_RTC_NVMEM is not set @@ -473,7 +472,7 @@ CONFIG_FS_ENCRYPTION=m CONFIG_FANOTIFY=y CONFIG_QUOTA_NETLINK_INTERFACE=y # CONFIG_PRINT_QUOTA_WARNING is not set -CONFIG_AUTOFS4_FS=m +CONFIG_AUTOFS_FS=m CONFIG_FUSE_FS=m CONFIG_CUSE=m CONFIG_OVERLAY_FS=m @@ -574,6 +573,7 @@ CONFIG_TEST_KSTRTOX=m CONFIG_TEST_PRINTF=m CONFIG_TEST_BITMAP=m CONFIG_TEST_UUID=m +CONFIG_TEST_OVERFLOW=m CONFIG_TEST_RHASHTABLE=m CONFIG_TEST_HASH=m CONFIG_TEST_USER_COPY=m @@ -596,6 +596,11 @@ CONFIG_CRYPTO_CRYPTD=m CONFIG_CRYPTO_MCRYPTD=m CONFIG_CRYPTO_TEST=m CONFIG_CRYPTO_CHACHA20POLY1305=m +CONFIG_CRYPTO_AEGIS128=m +CONFIG_CRYPTO_AEGIS128L=m +CONFIG_CRYPTO_AEGIS256=m +CONFIG_CRYPTO_MORUS640=m +CONFIG_CRYPTO_MORUS1280=m CONFIG_CRYPTO_CFB=m CONFIG_CRYPTO_LRW=m CONFIG_CRYPTO_PCBC=m @@ -631,6 +636,7 @@ CONFIG_CRYPTO_LZO=m CONFIG_CRYPTO_842=m CONFIG_CRYPTO_LZ4=m CONFIG_CRYPTO_LZ4HC=m +CONFIG_CRYPTO_ZSTD=m CONFIG_CRYPTO_ANSI_CPRNG=m CONFIG_CRYPTO_DRBG_HASH=y CONFIG_CRYPTO_DRBG_CTR=y diff --git a/arch/m68k/configs/sun3_defconfig b/arch/m68k/configs/sun3_defconfig index d543ed5dfa96..573bf922d448 100644 --- a/arch/m68k/configs/sun3_defconfig +++ b/arch/m68k/configs/sun3_defconfig @@ -45,6 +45,7 @@ CONFIG_UNIX_DIAG=m CONFIG_TLS=m CONFIG_XFRM_MIGRATE=y CONFIG_NET_KEY=y +CONFIG_XDP_SOCKETS=y CONFIG_INET=y CONFIG_IP_PNP=y CONFIG_IP_PNP_DHCP=y @@ -91,18 +92,14 @@ CONFIG_NF_CONNTRACK_SANE=m CONFIG_NF_CONNTRACK_SIP=m CONFIG_NF_CONNTRACK_TFTP=m CONFIG_NF_TABLES=m +CONFIG_NF_TABLES_SET=m CONFIG_NF_TABLES_INET=y CONFIG_NF_TABLES_NETDEV=y -CONFIG_NFT_EXTHDR=m -CONFIG_NFT_META=m -CONFIG_NFT_RT=m CONFIG_NFT_NUMGEN=m CONFIG_NFT_CT=m CONFIG_NFT_FLOW_OFFLOAD=m -CONFIG_NFT_SET_RBTREE=m -CONFIG_NFT_SET_HASH=m -CONFIG_NFT_SET_BITMAP=m CONFIG_NFT_COUNTER=m +CONFIG_NFT_CONNLIMIT=m CONFIG_NFT_LOG=m CONFIG_NFT_LIMIT=m CONFIG_NFT_MASQ=m @@ -115,6 +112,7 @@ CONFIG_NFT_REJECT=m CONFIG_NFT_COMPAT=m CONFIG_NFT_HASH=m CONFIG_NFT_FIB_INET=m +CONFIG_NFT_SOCKET=m CONFIG_NFT_DUP_NETDEV=m CONFIG_NFT_FWD_NETDEV=m CONFIG_NFT_FIB_NETDEV=m @@ -193,7 +191,6 @@ CONFIG_IP_SET_HASH_NETPORT=m CONFIG_IP_SET_HASH_NETIFACE=m CONFIG_IP_SET_LIST_SET=m CONFIG_NF_CONNTRACK_IPV4=m -CONFIG_NF_SOCKET_IPV4=m CONFIG_NFT_CHAIN_ROUTE_IPV4=m CONFIG_NFT_DUP_IPV4=m CONFIG_NFT_FIB_IPV4=m @@ -224,7 +221,6 @@ CONFIG_IP_NF_ARPTABLES=m CONFIG_IP_NF_ARPFILTER=m CONFIG_IP_NF_ARP_MANGLE=m CONFIG_NF_CONNTRACK_IPV6=m -CONFIG_NF_SOCKET_IPV6=m CONFIG_NFT_CHAIN_ROUTE_IPV6=m CONFIG_NFT_CHAIN_NAT_IPV6=m CONFIG_NFT_MASQ_IPV6=m @@ -253,7 +249,6 @@ CONFIG_IP6_NF_NAT=m CONFIG_IP6_NF_TARGET_MASQUERADE=m CONFIG_IP6_NF_TARGET_NPT=m CONFIG_NF_TABLES_BRIDGE=y -CONFIG_NFT_BRIDGE_META=m CONFIG_NFT_BRIDGE_REJECT=m CONFIG_NF_LOG_BRIDGE=m CONFIG_BRIDGE_NF_EBTABLES=m @@ -294,6 +289,7 @@ CONFIG_6LOWPAN_GHC_EXT_HDR_FRAG=m CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m CONFIG_DNS_RESOLVER=y CONFIG_BATMAN_ADV=m +# CONFIG_BATMAN_ADV_BATMAN_V is not set CONFIG_BATMAN_ADV_DAT=y CONFIG_BATMAN_ADV_NC=y CONFIG_BATMAN_ADV_MCAST=y @@ -341,6 +337,7 @@ CONFIG_DM_UNSTRIPED=m CONFIG_DM_CRYPT=m CONFIG_DM_SNAPSHOT=m CONFIG_DM_THIN_PROVISIONING=m +CONFIG_DM_WRITECACHE=m CONFIG_DM_ERA=m CONFIG_DM_MIRROR=m CONFIG_DM_RAID=m @@ -385,6 +382,7 @@ CONFIG_SUN3LANCE=y CONFIG_SUN3_82586=y # CONFIG_NET_VENDOR_MARVELL is not set # CONFIG_NET_VENDOR_MICREL is not set +# CONFIG_NET_VENDOR_MICROSEMI is not set # CONFIG_NET_VENDOR_NATSEMI is not set # CONFIG_NET_VENDOR_NETRONOME is not set # CONFIG_NET_VENDOR_NI is not set @@ -397,9 +395,9 @@ CONFIG_SUN3_82586=y # CONFIG_NET_VENDOR_SOCIONEXT is not set # CONFIG_NET_VENDOR_STMICRO is not set # CONFIG_NET_VENDOR_SUN is not set +# CONFIG_NET_VENDOR_SYNOPSYS is not set # CONFIG_NET_VENDOR_VIA is not set # CONFIG_NET_VENDOR_WIZNET is not set -# CONFIG_NET_VENDOR_SYNOPSYS is not set CONFIG_PPP=m CONFIG_PPP_BSDCOMP=m CONFIG_PPP_DEFLATE=m @@ -435,6 +433,7 @@ CONFIG_HIDRAW=y CONFIG_UHID=m # CONFIG_HID_GENERIC is not set # CONFIG_HID_ITE is not set +# CONFIG_HID_REDRAGON is not set # CONFIG_USB_SUPPORT is not set CONFIG_RTC_CLASS=y # CONFIG_RTC_NVMEM is not set @@ -452,7 +451,7 @@ CONFIG_FS_ENCRYPTION=m CONFIG_FANOTIFY=y CONFIG_QUOTA_NETLINK_INTERFACE=y # CONFIG_PRINT_QUOTA_WARNING is not set -CONFIG_AUTOFS4_FS=m +CONFIG_AUTOFS_FS=m CONFIG_FUSE_FS=m CONFIG_CUSE=m CONFIG_OVERLAY_FS=m @@ -553,6 +552,7 @@ CONFIG_TEST_KSTRTOX=m CONFIG_TEST_PRINTF=m CONFIG_TEST_BITMAP=m CONFIG_TEST_UUID=m +CONFIG_TEST_OVERFLOW=m CONFIG_TEST_RHASHTABLE=m CONFIG_TEST_HASH=m CONFIG_TEST_USER_COPY=m @@ -574,6 +574,11 @@ CONFIG_CRYPTO_CRYPTD=m CONFIG_CRYPTO_MCRYPTD=m CONFIG_CRYPTO_TEST=m CONFIG_CRYPTO_CHACHA20POLY1305=m +CONFIG_CRYPTO_AEGIS128=m +CONFIG_CRYPTO_AEGIS128L=m +CONFIG_CRYPTO_AEGIS256=m +CONFIG_CRYPTO_MORUS640=m +CONFIG_CRYPTO_MORUS1280=m CONFIG_CRYPTO_CFB=m CONFIG_CRYPTO_LRW=m CONFIG_CRYPTO_PCBC=m @@ -609,6 +614,7 @@ CONFIG_CRYPTO_LZO=m CONFIG_CRYPTO_842=m CONFIG_CRYPTO_LZ4=m CONFIG_CRYPTO_LZ4HC=m +CONFIG_CRYPTO_ZSTD=m CONFIG_CRYPTO_ANSI_CPRNG=m CONFIG_CRYPTO_DRBG_HASH=y CONFIG_CRYPTO_DRBG_CTR=y diff --git a/arch/m68k/configs/sun3x_defconfig b/arch/m68k/configs/sun3x_defconfig index a67e54246023..efb27a7fcc55 100644 --- a/arch/m68k/configs/sun3x_defconfig +++ b/arch/m68k/configs/sun3x_defconfig @@ -45,6 +45,7 @@ CONFIG_UNIX_DIAG=m CONFIG_TLS=m CONFIG_XFRM_MIGRATE=y CONFIG_NET_KEY=y +CONFIG_XDP_SOCKETS=y CONFIG_INET=y CONFIG_IP_PNP=y CONFIG_IP_PNP_DHCP=y @@ -91,18 +92,14 @@ CONFIG_NF_CONNTRACK_SANE=m CONFIG_NF_CONNTRACK_SIP=m CONFIG_NF_CONNTRACK_TFTP=m CONFIG_NF_TABLES=m +CONFIG_NF_TABLES_SET=m CONFIG_NF_TABLES_INET=y CONFIG_NF_TABLES_NETDEV=y -CONFIG_NFT_EXTHDR=m -CONFIG_NFT_META=m -CONFIG_NFT_RT=m CONFIG_NFT_NUMGEN=m CONFIG_NFT_CT=m CONFIG_NFT_FLOW_OFFLOAD=m -CONFIG_NFT_SET_RBTREE=m -CONFIG_NFT_SET_HASH=m -CONFIG_NFT_SET_BITMAP=m CONFIG_NFT_COUNTER=m +CONFIG_NFT_CONNLIMIT=m CONFIG_NFT_LOG=m CONFIG_NFT_LIMIT=m CONFIG_NFT_MASQ=m @@ -115,6 +112,7 @@ CONFIG_NFT_REJECT=m CONFIG_NFT_COMPAT=m CONFIG_NFT_HASH=m CONFIG_NFT_FIB_INET=m +CONFIG_NFT_SOCKET=m CONFIG_NFT_DUP_NETDEV=m CONFIG_NFT_FWD_NETDEV=m CONFIG_NFT_FIB_NETDEV=m @@ -193,7 +191,6 @@ CONFIG_IP_SET_HASH_NETPORT=m CONFIG_IP_SET_HASH_NETIFACE=m CONFIG_IP_SET_LIST_SET=m CONFIG_NF_CONNTRACK_IPV4=m -CONFIG_NF_SOCKET_IPV4=m CONFIG_NFT_CHAIN_ROUTE_IPV4=m CONFIG_NFT_DUP_IPV4=m CONFIG_NFT_FIB_IPV4=m @@ -224,7 +221,6 @@ CONFIG_IP_NF_ARPTABLES=m CONFIG_IP_NF_ARPFILTER=m CONFIG_IP_NF_ARP_MANGLE=m CONFIG_NF_CONNTRACK_IPV6=m -CONFIG_NF_SOCKET_IPV6=m CONFIG_NFT_CHAIN_ROUTE_IPV6=m CONFIG_NFT_CHAIN_NAT_IPV6=m CONFIG_NFT_MASQ_IPV6=m @@ -253,7 +249,6 @@ CONFIG_IP6_NF_NAT=m CONFIG_IP6_NF_TARGET_MASQUERADE=m CONFIG_IP6_NF_TARGET_NPT=m CONFIG_NF_TABLES_BRIDGE=y -CONFIG_NFT_BRIDGE_META=m CONFIG_NFT_BRIDGE_REJECT=m CONFIG_NF_LOG_BRIDGE=m CONFIG_BRIDGE_NF_EBTABLES=m @@ -294,6 +289,7 @@ CONFIG_6LOWPAN_GHC_EXT_HDR_FRAG=m CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m CONFIG_DNS_RESOLVER=y CONFIG_BATMAN_ADV=m +# CONFIG_BATMAN_ADV_BATMAN_V is not set CONFIG_BATMAN_ADV_DAT=y CONFIG_BATMAN_ADV_NC=y CONFIG_BATMAN_ADV_MCAST=y @@ -341,6 +337,7 @@ CONFIG_DM_UNSTRIPED=m CONFIG_DM_CRYPT=m CONFIG_DM_SNAPSHOT=m CONFIG_DM_THIN_PROVISIONING=m +CONFIG_DM_WRITECACHE=m CONFIG_DM_ERA=m CONFIG_DM_MIRROR=m CONFIG_DM_RAID=m @@ -378,14 +375,15 @@ CONFIG_VETH=m CONFIG_SUN3LANCE=y # CONFIG_NET_VENDOR_AQUANTIA is not set # CONFIG_NET_VENDOR_ARC is not set -# CONFIG_NET_CADENCE is not set # CONFIG_NET_VENDOR_BROADCOM is not set +# CONFIG_NET_CADENCE is not set # CONFIG_NET_VENDOR_CORTINA is not set # CONFIG_NET_VENDOR_EZCHIP is not set # CONFIG_NET_VENDOR_HUAWEI is not set # CONFIG_NET_VENDOR_INTEL is not set # CONFIG_NET_VENDOR_MARVELL is not set # CONFIG_NET_VENDOR_MICREL is not set +# CONFIG_NET_VENDOR_MICROSEMI is not set # CONFIG_NET_VENDOR_NATSEMI is not set # CONFIG_NET_VENDOR_NETRONOME is not set # CONFIG_NET_VENDOR_NI is not set @@ -397,9 +395,9 @@ CONFIG_SUN3LANCE=y # CONFIG_NET_VENDOR_SOLARFLARE is not set # CONFIG_NET_VENDOR_SOCIONEXT is not set # CONFIG_NET_VENDOR_STMICRO is not set +# CONFIG_NET_VENDOR_SYNOPSYS is not set # CONFIG_NET_VENDOR_VIA is not set # CONFIG_NET_VENDOR_WIZNET is not set -# CONFIG_NET_VENDOR_SYNOPSYS is not set CONFIG_PPP=m CONFIG_PPP_BSDCOMP=m CONFIG_PPP_DEFLATE=m @@ -435,6 +433,7 @@ CONFIG_HIDRAW=y CONFIG_UHID=m # CONFIG_HID_GENERIC is not set # CONFIG_HID_ITE is not set +# CONFIG_HID_REDRAGON is not set # CONFIG_USB_SUPPORT is not set CONFIG_RTC_CLASS=y # CONFIG_RTC_NVMEM is not set @@ -452,7 +451,7 @@ CONFIG_FS_ENCRYPTION=m CONFIG_FANOTIFY=y CONFIG_QUOTA_NETLINK_INTERFACE=y # CONFIG_PRINT_QUOTA_WARNING is not set -CONFIG_AUTOFS4_FS=m +CONFIG_AUTOFS_FS=m CONFIG_FUSE_FS=m CONFIG_CUSE=m CONFIG_OVERLAY_FS=m @@ -553,6 +552,7 @@ CONFIG_TEST_KSTRTOX=m CONFIG_TEST_PRINTF=m CONFIG_TEST_BITMAP=m CONFIG_TEST_UUID=m +CONFIG_TEST_OVERFLOW=m CONFIG_TEST_RHASHTABLE=m CONFIG_TEST_HASH=m CONFIG_TEST_USER_COPY=m @@ -575,6 +575,11 @@ CONFIG_CRYPTO_CRYPTD=m CONFIG_CRYPTO_MCRYPTD=m CONFIG_CRYPTO_TEST=m CONFIG_CRYPTO_CHACHA20POLY1305=m +CONFIG_CRYPTO_AEGIS128=m +CONFIG_CRYPTO_AEGIS128L=m +CONFIG_CRYPTO_AEGIS256=m +CONFIG_CRYPTO_MORUS640=m +CONFIG_CRYPTO_MORUS1280=m CONFIG_CRYPTO_CFB=m CONFIG_CRYPTO_LRW=m CONFIG_CRYPTO_PCBC=m @@ -610,6 +615,7 @@ CONFIG_CRYPTO_LZO=m CONFIG_CRYPTO_842=m CONFIG_CRYPTO_LZ4=m CONFIG_CRYPTO_LZ4HC=m +CONFIG_CRYPTO_ZSTD=m CONFIG_CRYPTO_ANSI_CPRNG=m CONFIG_CRYPTO_DRBG_HASH=y CONFIG_CRYPTO_DRBG_CTR=y diff --git a/arch/m68k/include/asm/Kbuild b/arch/m68k/include/asm/Kbuild index 4d8d68c4e3dd..a4b8d3331a9e 100644 --- a/arch/m68k/include/asm/Kbuild +++ b/arch/m68k/include/asm/Kbuild @@ -1,6 +1,7 @@ generic-y += barrier.h generic-y += compat.h generic-y += device.h +generic-y += dma-mapping.h generic-y += emergency-restart.h generic-y += exec.h generic-y += extable.h diff --git a/arch/m68k/include/asm/atomic.h b/arch/m68k/include/asm/atomic.h index e993e2860ee1..47228b0d4163 100644 --- a/arch/m68k/include/asm/atomic.h +++ b/arch/m68k/include/asm/atomic.h @@ -126,11 +126,13 @@ static inline void atomic_inc(atomic_t *v) { __asm__ __volatile__("addql #1,%0" : "+m" (*v)); } +#define atomic_inc atomic_inc static inline void atomic_dec(atomic_t *v) { __asm__ __volatile__("subql #1,%0" : "+m" (*v)); } +#define atomic_dec atomic_dec static inline int atomic_dec_and_test(atomic_t *v) { @@ -138,6 +140,7 @@ static inline int atomic_dec_and_test(atomic_t *v) __asm__ __volatile__("subql #1,%1; seq %0" : "=d" (c), "+m" (*v)); return c != 0; } +#define atomic_dec_and_test atomic_dec_and_test static inline int atomic_dec_and_test_lt(atomic_t *v) { @@ -155,6 +158,7 @@ static inline int atomic_inc_and_test(atomic_t *v) __asm__ __volatile__("addql #1,%1; seq %0" : "=d" (c), "+m" (*v)); return c != 0; } +#define atomic_inc_and_test atomic_inc_and_test #ifdef CONFIG_RMW_INSNS @@ -190,9 +194,6 @@ static inline int atomic_xchg(atomic_t *v, int new) #endif /* !CONFIG_RMW_INSNS */ -#define atomic_dec_return(v) atomic_sub_return(1, (v)) -#define atomic_inc_return(v) atomic_add_return(1, (v)) - static inline int atomic_sub_and_test(int i, atomic_t *v) { char c; @@ -201,6 +202,7 @@ static inline int atomic_sub_and_test(int i, atomic_t *v) : ASM_DI (i)); return c != 0; } +#define atomic_sub_and_test atomic_sub_and_test static inline int atomic_add_negative(int i, atomic_t *v) { @@ -210,20 +212,6 @@ static inline int atomic_add_negative(int i, atomic_t *v) : ASM_DI (i)); return c != 0; } - -static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u) -{ - int c, old; - c = atomic_read(v); - for (;;) { - if (unlikely(c == (u))) - break; - old = atomic_cmpxchg((v), c, c + (a)); - if (likely(old == c)) - break; - c = old; - } - return c; -} +#define atomic_add_negative atomic_add_negative #endif /* __ARCH_M68K_ATOMIC __ */ diff --git a/arch/m68k/include/asm/bitops.h b/arch/m68k/include/asm/bitops.h index 93b47b1f6fb4..d979f38af751 100644 --- a/arch/m68k/include/asm/bitops.h +++ b/arch/m68k/include/asm/bitops.h @@ -454,7 +454,7 @@ static inline unsigned long ffz(unsigned long word) */ #if (defined(__mcfisaaplus__) || defined(__mcfisac__)) && \ !defined(CONFIG_M68000) && !defined(CONFIG_MCPU32) -static inline int __ffs(int x) +static inline unsigned long __ffs(unsigned long x) { __asm__ __volatile__ ("bitrev %0; ff1 %0" : "=d" (x) @@ -493,7 +493,11 @@ static inline int ffs(int x) : "dm" (x & -x)); return 32 - cnt; } -#define __ffs(x) (ffs(x) - 1) + +static inline unsigned long __ffs(unsigned long x) +{ + return ffs(x) - 1; +} /* * fls: find last bit set. @@ -515,12 +519,16 @@ static inline int __fls(int x) #endif +/* Simple test-and-set bit locks */ +#define test_and_set_bit_lock test_and_set_bit +#define clear_bit_unlock clear_bit +#define __clear_bit_unlock clear_bit_unlock + #include <asm-generic/bitops/ext2-atomic.h> #include <asm-generic/bitops/le.h> #include <asm-generic/bitops/fls64.h> #include <asm-generic/bitops/sched.h> #include <asm-generic/bitops/hweight.h> -#include <asm-generic/bitops/lock.h> #endif /* __KERNEL__ */ #endif /* _M68K_BITOPS_H */ diff --git a/arch/m68k/include/asm/dma-mapping.h b/arch/m68k/include/asm/dma-mapping.h deleted file mode 100644 index e3722ed04fbb..000000000000 --- a/arch/m68k/include/asm/dma-mapping.h +++ /dev/null @@ -1,12 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _M68K_DMA_MAPPING_H -#define _M68K_DMA_MAPPING_H - -extern const struct dma_map_ops m68k_dma_ops; - -static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus) -{ - return &m68k_dma_ops; -} - -#endif /* _M68K_DMA_MAPPING_H */ diff --git a/arch/m68k/include/asm/io.h b/arch/m68k/include/asm/io.h index ca2849afb087..aabe6420ead2 100644 --- a/arch/m68k/include/asm/io.h +++ b/arch/m68k/include/asm/io.h @@ -1,6 +1,13 @@ /* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _M68K_IO_H +#define _M68K_IO_H + #if defined(__uClinux__) || defined(CONFIG_COLDFIRE) #include <asm/io_no.h> #else #include <asm/io_mm.h> #endif + +#include <asm-generic/io.h> + +#endif /* _M68K_IO_H */ diff --git a/arch/m68k/include/asm/io_mm.h b/arch/m68k/include/asm/io_mm.h index fe485f4f5fac..782b78f8a048 100644 --- a/arch/m68k/include/asm/io_mm.h +++ b/arch/m68k/include/asm/io_mm.h @@ -16,13 +16,11 @@ * isa_readX(),isa_writeX() are for ISA memory */ -#ifndef _IO_H -#define _IO_H +#ifndef _M68K_IO_MM_H +#define _M68K_IO_MM_H #ifdef __KERNEL__ -#define ARCH_HAS_IOREMAP_WT - #include <linux/compiler.h> #include <asm/raw_io.h> #include <asm/virtconvert.h> @@ -369,40 +367,6 @@ static inline void isa_delay(void) #define writew(val, addr) out_le16((addr), (val)) #endif /* CONFIG_ATARI_ROM_ISA */ -#if !defined(CONFIG_ISA) && !defined(CONFIG_ATARI_ROM_ISA) -/* - * We need to define dummy functions for GENERIC_IOMAP support. - */ -#define inb(port) 0xff -#define inb_p(port) 0xff -#define outb(val,port) ((void)0) -#define outb_p(val,port) ((void)0) -#define inw(port) 0xffff -#define inw_p(port) 0xffff -#define outw(val,port) ((void)0) -#define outw_p(val,port) ((void)0) -#define inl(port) 0xffffffffUL -#define inl_p(port) 0xffffffffUL -#define outl(val,port) ((void)0) -#define outl_p(val,port) ((void)0) - -#define insb(port,buf,nr) ((void)0) -#define outsb(port,buf,nr) ((void)0) -#define insw(port,buf,nr) ((void)0) -#define outsw(port,buf,nr) ((void)0) -#define insl(port,buf,nr) ((void)0) -#define outsl(port,buf,nr) ((void)0) - -/* - * These should be valid on any ioremap()ed region - */ -#define readb(addr) in_8(addr) -#define writeb(val,addr) out_8((addr),(val)) -#define readw(addr) in_le16(addr) -#define writew(val,addr) out_le16((addr),(val)) - -#endif /* !CONFIG_ISA && !CONFIG_ATARI_ROM_ISA */ - #define readl(addr) in_le32(addr) #define writel(val,addr) out_le32((addr),(val)) @@ -444,4 +408,4 @@ static inline void isa_delay(void) #define writew_relaxed(b, addr) writew(b, addr) #define writel_relaxed(b, addr) writel(b, addr) -#endif /* _IO_H */ +#endif /* _M68K_IO_MM_H */ diff --git a/arch/m68k/include/asm/io_no.h b/arch/m68k/include/asm/io_no.h index 83a0a6d449f4..0498192e1d98 100644 --- a/arch/m68k/include/asm/io_no.h +++ b/arch/m68k/include/asm/io_no.h @@ -131,19 +131,7 @@ static inline void writel(u32 value, volatile void __iomem *addr) #define PCI_SPACE_LIMIT PCI_IO_MASK #endif /* CONFIG_PCI */ -/* - * These are defined in kmap.h as static inline functions. To maintain - * previous behavior we put these define guards here so io_mm.h doesn't - * see them. - */ -#ifdef CONFIG_MMU -#define memset_io memset_io -#define memcpy_fromio memcpy_fromio -#define memcpy_toio memcpy_toio -#endif - #include <asm/kmap.h> #include <asm/virtconvert.h> -#include <asm-generic/io.h> #endif /* _M68KNOMMU_IO_H */ diff --git a/arch/m68k/include/asm/kmap.h b/arch/m68k/include/asm/kmap.h index 84b8333db8ad..aac7f045f7f0 100644 --- a/arch/m68k/include/asm/kmap.h +++ b/arch/m68k/include/asm/kmap.h @@ -4,6 +4,8 @@ #ifdef CONFIG_MMU +#define ARCH_HAS_IOREMAP_WT + /* Values for nocacheflag and cmode */ #define IOMAP_FULL_CACHING 0 #define IOMAP_NOCACHE_SER 1 @@ -16,6 +18,7 @@ */ extern void __iomem *__ioremap(unsigned long physaddr, unsigned long size, int cacheflag); +#define iounmap iounmap extern void iounmap(void __iomem *addr); extern void __iounmap(void *addr, unsigned long size); @@ -33,31 +36,35 @@ static inline void __iomem *ioremap_nocache(unsigned long physaddr, } #define ioremap_uc ioremap_nocache +#define ioremap_wt ioremap_wt static inline void __iomem *ioremap_wt(unsigned long physaddr, unsigned long size) { return __ioremap(physaddr, size, IOMAP_WRITETHROUGH); } -#define ioremap_fillcache ioremap_fullcache +#define ioremap_fullcache ioremap_fullcache static inline void __iomem *ioremap_fullcache(unsigned long physaddr, unsigned long size) { return __ioremap(physaddr, size, IOMAP_FULL_CACHING); } +#define memset_io memset_io static inline void memset_io(volatile void __iomem *addr, unsigned char val, int count) { __builtin_memset((void __force *) addr, val, count); } +#define memcpy_fromio memcpy_fromio static inline void memcpy_fromio(void *dst, const volatile void __iomem *src, int count) { __builtin_memcpy(dst, (void __force *) src, count); } +#define memcpy_toio memcpy_toio static inline void memcpy_toio(volatile void __iomem *dst, const void *src, int count) { diff --git a/arch/m68k/include/asm/machdep.h b/arch/m68k/include/asm/machdep.h index 1605da48ebf2..49bd3266b4b1 100644 --- a/arch/m68k/include/asm/machdep.h +++ b/arch/m68k/include/asm/machdep.h @@ -22,7 +22,6 @@ extern int (*mach_hwclk)(int, struct rtc_time*); extern unsigned int (*mach_get_ss)(void); extern int (*mach_get_rtc_pll)(struct rtc_pll_info *); extern int (*mach_set_rtc_pll)(struct rtc_pll_info *); -extern int (*mach_set_clock_mmss)(unsigned long); extern void (*mach_reset)( void ); extern void (*mach_halt)( void ); extern void (*mach_power_off)( void ); diff --git a/arch/m68k/include/asm/macintosh.h b/arch/m68k/include/asm/macintosh.h index 9b840c03ebb7..08cee11180e6 100644 --- a/arch/m68k/include/asm/macintosh.h +++ b/arch/m68k/include/asm/macintosh.h @@ -57,7 +57,6 @@ struct mac_model #define MAC_SCSI_IIFX 5 #define MAC_SCSI_DUO 6 #define MAC_SCSI_LC 7 -#define MAC_SCSI_LATE 8 #define MAC_IDE_NONE 0 #define MAC_IDE_QUADRA 1 diff --git a/arch/m68k/include/asm/page_no.h b/arch/m68k/include/asm/page_no.h index e644c4daf540..6bbe52025de3 100644 --- a/arch/m68k/include/asm/page_no.h +++ b/arch/m68k/include/asm/page_no.h @@ -18,7 +18,7 @@ extern unsigned long memory_end; #define __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE #define __pa(vaddr) ((unsigned long)(vaddr)) -#define __va(paddr) ((void *)(paddr)) +#define __va(paddr) ((void *)((unsigned long)(paddr))) #define virt_to_pfn(kaddr) (__pa(kaddr) >> PAGE_SHIFT) #define pfn_to_virt(pfn) __va((pfn) << PAGE_SHIFT) diff --git a/arch/m68k/kernel/dma.c b/arch/m68k/kernel/dma.c index 463572c4943f..e99993c57d6b 100644 --- a/arch/m68k/kernel/dma.c +++ b/arch/m68k/kernel/dma.c @@ -6,7 +6,7 @@ #undef DEBUG -#include <linux/dma-mapping.h> +#include <linux/dma-noncoherent.h> #include <linux/device.h> #include <linux/kernel.h> #include <linux/platform_device.h> @@ -19,7 +19,7 @@ #if defined(CONFIG_MMU) && !defined(CONFIG_COLDFIRE) -static void *m68k_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, +void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, gfp_t flag, unsigned long attrs) { struct page *page, **map; @@ -62,7 +62,7 @@ static void *m68k_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, return addr; } -static void m68k_dma_free(struct device *dev, size_t size, void *addr, +void arch_dma_free(struct device *dev, size_t size, void *addr, dma_addr_t handle, unsigned long attrs) { pr_debug("dma_free_coherent: %p, %x\n", addr, handle); @@ -73,8 +73,8 @@ static void m68k_dma_free(struct device *dev, size_t size, void *addr, #include <asm/cacheflush.h> -static void *m68k_dma_alloc(struct device *dev, size_t size, - dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs) +void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, + gfp_t gfp, unsigned long attrs) { void *ret; @@ -89,7 +89,7 @@ static void *m68k_dma_alloc(struct device *dev, size_t size, return ret; } -static void m68k_dma_free(struct device *dev, size_t size, void *vaddr, +void arch_dma_free(struct device *dev, size_t size, void *vaddr, dma_addr_t dma_handle, unsigned long attrs) { free_pages((unsigned long)vaddr, get_order(size)); @@ -97,8 +97,8 @@ static void m68k_dma_free(struct device *dev, size_t size, void *vaddr, #endif /* CONFIG_MMU && !CONFIG_COLDFIRE */ -static void m68k_dma_sync_single_for_device(struct device *dev, - dma_addr_t handle, size_t size, enum dma_data_direction dir) +void arch_sync_dma_for_device(struct device *dev, phys_addr_t handle, + size_t size, enum dma_data_direction dir) { switch (dir) { case DMA_BIDIRECTIONAL: @@ -115,58 +115,6 @@ static void m68k_dma_sync_single_for_device(struct device *dev, } } -static void m68k_dma_sync_sg_for_device(struct device *dev, - struct scatterlist *sglist, int nents, enum dma_data_direction dir) -{ - int i; - struct scatterlist *sg; - - for_each_sg(sglist, sg, nents, i) { - dma_sync_single_for_device(dev, sg->dma_address, sg->length, - dir); - } -} - -static dma_addr_t m68k_dma_map_page(struct device *dev, struct page *page, - unsigned long offset, size_t size, enum dma_data_direction dir, - unsigned long attrs) -{ - dma_addr_t handle = page_to_phys(page) + offset; - - if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC)) - dma_sync_single_for_device(dev, handle, size, dir); - - return handle; -} - -static int m68k_dma_map_sg(struct device *dev, struct scatterlist *sglist, - int nents, enum dma_data_direction dir, unsigned long attrs) -{ - int i; - struct scatterlist *sg; - - for_each_sg(sglist, sg, nents, i) { - sg->dma_address = sg_phys(sg); - - if (attrs & DMA_ATTR_SKIP_CPU_SYNC) - continue; - - dma_sync_single_for_device(dev, sg->dma_address, sg->length, - dir); - } - return nents; -} - -const struct dma_map_ops m68k_dma_ops = { - .alloc = m68k_dma_alloc, - .free = m68k_dma_free, - .map_page = m68k_dma_map_page, - .map_sg = m68k_dma_map_sg, - .sync_single_for_device = m68k_dma_sync_single_for_device, - .sync_sg_for_device = m68k_dma_sync_sg_for_device, -}; -EXPORT_SYMBOL(m68k_dma_ops); - void arch_setup_pdev_archdata(struct platform_device *pdev) { if (pdev->dev.coherent_dma_mask == DMA_MASK_NONE && diff --git a/arch/m68k/kernel/setup_mm.c b/arch/m68k/kernel/setup_mm.c index f35e3ebd6331..5d3596c180f9 100644 --- a/arch/m68k/kernel/setup_mm.c +++ b/arch/m68k/kernel/setup_mm.c @@ -21,6 +21,7 @@ #include <linux/string.h> #include <linux/init.h> #include <linux/bootmem.h> +#include <linux/memblock.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/module.h> @@ -88,7 +89,6 @@ void (*mach_get_hardware_list) (struct seq_file *m); /* machine dependent timer functions */ int (*mach_hwclk) (int, struct rtc_time*); EXPORT_SYMBOL(mach_hwclk); -int (*mach_set_clock_mmss) (unsigned long); unsigned int (*mach_get_ss)(void); int (*mach_get_rtc_pll)(struct rtc_pll_info *); int (*mach_set_rtc_pll)(struct rtc_pll_info *); @@ -165,6 +165,8 @@ static void __init m68k_parse_bootinfo(const struct bi_record *record) be32_to_cpu(m->addr); m68k_memory[m68k_num_memory].size = be32_to_cpu(m->size); + memblock_add(m68k_memory[m68k_num_memory].addr, + m68k_memory[m68k_num_memory].size); m68k_num_memory++; } else pr_warn("%s: too many memory chunks\n", @@ -224,10 +226,6 @@ static void __init m68k_parse_bootinfo(const struct bi_record *record) void __init setup_arch(char **cmdline_p) { -#ifndef CONFIG_SUN3 - int i; -#endif - /* The bootinfo is located right after the kernel */ if (!CPU_IS_COLDFIRE) m68k_parse_bootinfo((const struct bi_record *)_end); @@ -356,14 +354,9 @@ void __init setup_arch(char **cmdline_p) #endif #ifndef CONFIG_SUN3 - for (i = 1; i < m68k_num_memory; i++) - free_bootmem_node(NODE_DATA(i), m68k_memory[i].addr, - m68k_memory[i].size); #ifdef CONFIG_BLK_DEV_INITRD if (m68k_ramdisk.size) { - reserve_bootmem_node(__virt_to_node(phys_to_virt(m68k_ramdisk.addr)), - m68k_ramdisk.addr, m68k_ramdisk.size, - BOOTMEM_DEFAULT); + memblock_reserve(m68k_ramdisk.addr, m68k_ramdisk.size); initrd_start = (unsigned long)phys_to_virt(m68k_ramdisk.addr); initrd_end = initrd_start + m68k_ramdisk.size; pr_info("initrd: %08lx - %08lx\n", initrd_start, initrd_end); diff --git a/arch/m68k/kernel/setup_no.c b/arch/m68k/kernel/setup_no.c index a98af1018201..cfd5475bfc31 100644 --- a/arch/m68k/kernel/setup_no.c +++ b/arch/m68k/kernel/setup_no.c @@ -28,6 +28,7 @@ #include <linux/errno.h> #include <linux/string.h> #include <linux/bootmem.h> +#include <linux/memblock.h> #include <linux/seq_file.h> #include <linux/init.h> #include <linux/initrd.h> @@ -51,7 +52,6 @@ char __initdata command_line[COMMAND_LINE_SIZE]; /* machine dependent timer functions */ void (*mach_sched_init)(irq_handler_t handler) __initdata = NULL; -int (*mach_set_clock_mmss)(unsigned long); int (*mach_hwclk) (int, struct rtc_time*); /* machine dependent reboot functions */ @@ -86,8 +86,6 @@ void (*mach_power_off)(void); void __init setup_arch(char **cmdline_p) { - int bootmap_size; - memory_start = PAGE_ALIGN(_ramstart); memory_end = _ramend; @@ -142,6 +140,8 @@ void __init setup_arch(char **cmdline_p) pr_debug("MEMORY -> ROMFS=0x%p-0x%06lx MEM=0x%06lx-0x%06lx\n ", __bss_stop, memory_start, memory_start, memory_end); + memblock_add(memory_start, memory_end - memory_start); + /* Keep a copy of command line */ *cmdline_p = &command_line[0]; memcpy(boot_command_line, command_line, COMMAND_LINE_SIZE); @@ -158,23 +158,10 @@ void __init setup_arch(char **cmdline_p) min_low_pfn = PFN_DOWN(memory_start); max_pfn = max_low_pfn = PFN_DOWN(memory_end); - bootmap_size = init_bootmem_node( - NODE_DATA(0), - min_low_pfn, /* map goes here */ - PFN_DOWN(PAGE_OFFSET), - max_pfn); - /* - * Free the usable memory, we have to make sure we do not free - * the bootmem bitmap so we then reserve it after freeing it :-) - */ - free_bootmem(memory_start, memory_end - memory_start); - reserve_bootmem(memory_start, bootmap_size, BOOTMEM_DEFAULT); - #if defined(CONFIG_UBOOT) && defined(CONFIG_BLK_DEV_INITRD) if ((initrd_start > 0) && (initrd_start < initrd_end) && (initrd_end < memory_end)) - reserve_bootmem(initrd_start, initrd_end - initrd_start, - BOOTMEM_DEFAULT); + memblock_reserve(initrd_start, initrd_end - initrd_start); #endif /* if defined(CONFIG_BLK_DEV_INITRD) */ /* diff --git a/arch/m68k/mac/config.c b/arch/m68k/mac/config.c index e522307db47c..b02d7254b73a 100644 --- a/arch/m68k/mac/config.c +++ b/arch/m68k/mac/config.c @@ -57,7 +57,6 @@ static unsigned long mac_orig_videoaddr; /* Mac specific timer functions */ extern u32 mac_gettimeoffset(void); extern int mac_hwclk(int, struct rtc_time *); -extern int mac_set_clock_mmss(unsigned long); extern void iop_preinit(void); extern void iop_init(void); extern void via_init(void); @@ -158,7 +157,6 @@ void __init config_mac(void) mach_get_model = mac_get_model; arch_gettimeoffset = mac_gettimeoffset; mach_hwclk = mac_hwclk; - mach_set_clock_mmss = mac_set_clock_mmss; mach_reset = mac_reset; mach_halt = mac_poweroff; mach_power_off = mac_poweroff; @@ -709,7 +707,7 @@ static struct mac_model mac_data_table[] = { .name = "PowerBook 520", .adb_type = MAC_ADB_PB2, .via_type = MAC_VIA_QUADRA, - .scsi_type = MAC_SCSI_LATE, + .scsi_type = MAC_SCSI_OLD, .scc_type = MAC_SCC_QUADRA, .ether_type = MAC_ETHER_SONIC, .floppy_type = MAC_FLOPPY_SWIM_ADDR2, @@ -943,18 +941,6 @@ static const struct resource mac_scsi_old_rsrc[] __initconst = { }, }; -static const struct resource mac_scsi_late_rsrc[] __initconst = { - { - .flags = IORESOURCE_IRQ, - .start = IRQ_MAC_SCSI, - .end = IRQ_MAC_SCSI, - }, { - .flags = IORESOURCE_MEM, - .start = 0x50010000, - .end = 0x50011FFF, - }, -}; - static const struct resource mac_scsi_ccl_rsrc[] __initconst = { { .flags = IORESOURCE_IRQ, @@ -1064,11 +1050,6 @@ int __init mac_platform_init(void) platform_device_register_simple("mac_scsi", 0, mac_scsi_old_rsrc, ARRAY_SIZE(mac_scsi_old_rsrc)); break; - case MAC_SCSI_LATE: - /* XXX PDMA support for PowerBook 500 series needs testing */ - platform_device_register_simple("mac_scsi", 0, - mac_scsi_late_rsrc, ARRAY_SIZE(mac_scsi_late_rsrc)); - break; case MAC_SCSI_LC: /* Addresses from Mac LC data in Designing Cards & Drivers 3ed. * Also from the Developer Notes for Classic II, LC III, diff --git a/arch/m68k/mac/misc.c b/arch/m68k/mac/misc.c index c68054361615..19e9d8eef1f2 100644 --- a/arch/m68k/mac/misc.c +++ b/arch/m68k/mac/misc.c @@ -26,33 +26,38 @@ #include <asm/machdep.h> -/* Offset between Unix time (1970-based) and Mac time (1904-based) */ +/* + * Offset between Unix time (1970-based) and Mac time (1904-based). Cuda and PMU + * times wrap in 2040. If we need to handle later times, the read_time functions + * need to be changed to interpret wrapped times as post-2040. + */ #define RTC_OFFSET 2082844800 static void (*rom_reset)(void); #ifdef CONFIG_ADB_CUDA -static long cuda_read_time(void) +static time64_t cuda_read_time(void) { struct adb_request req; - long time; + time64_t time; if (cuda_request(&req, NULL, 2, CUDA_PACKET, CUDA_GET_TIME) < 0) return 0; while (!req.complete) cuda_poll(); - time = (req.reply[3] << 24) | (req.reply[4] << 16) | - (req.reply[5] << 8) | req.reply[6]; + time = (u32)((req.reply[3] << 24) | (req.reply[4] << 16) | + (req.reply[5] << 8) | req.reply[6]); + return time - RTC_OFFSET; } -static void cuda_write_time(long data) +static void cuda_write_time(time64_t time) { struct adb_request req; + u32 data = lower_32_bits(time + RTC_OFFSET); - data += RTC_OFFSET; if (cuda_request(&req, NULL, 6, CUDA_PACKET, CUDA_SET_TIME, (data >> 24) & 0xFF, (data >> 16) & 0xFF, (data >> 8) & 0xFF, data & 0xFF) < 0) @@ -86,26 +91,27 @@ static void cuda_write_pram(int offset, __u8 data) #endif /* CONFIG_ADB_CUDA */ #ifdef CONFIG_ADB_PMU68K -static long pmu_read_time(void) +static time64_t pmu_read_time(void) { struct adb_request req; - long time; + time64_t time; if (pmu_request(&req, NULL, 1, PMU_READ_RTC) < 0) return 0; while (!req.complete) pmu_poll(); - time = (req.reply[1] << 24) | (req.reply[2] << 16) | - (req.reply[3] << 8) | req.reply[4]; + time = (u32)((req.reply[1] << 24) | (req.reply[2] << 16) | + (req.reply[3] << 8) | req.reply[4]); + return time - RTC_OFFSET; } -static void pmu_write_time(long data) +static void pmu_write_time(time64_t time) { struct adb_request req; + u32 data = lower_32_bits(time + RTC_OFFSET); - data += RTC_OFFSET; if (pmu_request(&req, NULL, 5, PMU_SET_RTC, (data >> 24) & 0xFF, (data >> 16) & 0xFF, (data >> 8) & 0xFF, data & 0xFF) < 0) @@ -245,11 +251,11 @@ static void via_write_pram(int offset, __u8 data) * is basically any machine with Mac II-style ADB. */ -static long via_read_time(void) +static time64_t via_read_time(void) { union { __u8 cdata[4]; - long idata; + __u32 idata; } result, last_result; int count = 1; @@ -270,7 +276,7 @@ static long via_read_time(void) via_pram_command(0x8D, &result.cdata[0]); if (result.idata == last_result.idata) - return result.idata - RTC_OFFSET; + return (time64_t)result.idata - RTC_OFFSET; if (++count > 10) break; @@ -278,8 +284,8 @@ static long via_read_time(void) last_result.idata = result.idata; } - pr_err("via_read_time: failed to read a stable value; got 0x%08lx then 0x%08lx\n", - last_result.idata, result.idata); + pr_err("%s: failed to read a stable value; got 0x%08x then 0x%08x\n", + __func__, last_result.idata, result.idata); return 0; } @@ -291,11 +297,11 @@ static long via_read_time(void) * is basically any machine with Mac II-style ADB. */ -static void via_write_time(long time) +static void via_write_time(time64_t time) { union { __u8 cdata[4]; - long idata; + __u32 idata; } data; __u8 temp; @@ -304,7 +310,7 @@ static void via_write_time(long time) temp = 0x55; via_pram_command(0x35, &temp); - data.idata = time + RTC_OFFSET; + data.idata = lower_32_bits(time + RTC_OFFSET); via_pram_command(0x01, &data.cdata[3]); via_pram_command(0x05, &data.cdata[2]); via_pram_command(0x09, &data.cdata[1]); @@ -585,12 +591,15 @@ void mac_reset(void) * This function translates seconds since 1970 into a proper date. * * Algorithm cribbed from glibc2.1, __offtime(). + * + * This is roughly same as rtc_time64_to_tm(), which we should probably + * use here, but it's only available when CONFIG_RTC_LIB is enabled. */ #define SECS_PER_MINUTE (60) #define SECS_PER_HOUR (SECS_PER_MINUTE * 60) #define SECS_PER_DAY (SECS_PER_HOUR * 24) -static void unmktime(unsigned long time, long offset, +static void unmktime(time64_t time, long offset, int *yearp, int *monp, int *dayp, int *hourp, int *minp, int *secp) { @@ -602,11 +611,10 @@ static void unmktime(unsigned long time, long offset, /* Leap years. */ { 0, 31, 60, 91, 121, 152, 182, 213, 244, 274, 305, 335, 366 } }; - long int days, rem, y, wday, yday; + int days, rem, y, wday, yday; const unsigned short int *ip; - days = time / SECS_PER_DAY; - rem = time % SECS_PER_DAY; + days = div_u64_rem(time, SECS_PER_DAY, &rem); rem += offset; while (rem < 0) { rem += SECS_PER_DAY; @@ -657,7 +665,7 @@ static void unmktime(unsigned long time, long offset, int mac_hwclk(int op, struct rtc_time *t) { - unsigned long now; + time64_t now; if (!op) { /* read */ switch (macintosh_config->adb_type) { @@ -693,8 +701,8 @@ int mac_hwclk(int op, struct rtc_time *t) __func__, t->tm_year + 1900, t->tm_mon + 1, t->tm_mday, t->tm_hour, t->tm_min, t->tm_sec); - now = mktime(t->tm_year + 1900, t->tm_mon + 1, t->tm_mday, - t->tm_hour, t->tm_min, t->tm_sec); + now = mktime64(t->tm_year + 1900, t->tm_mon + 1, t->tm_mday, + t->tm_hour, t->tm_min, t->tm_sec); switch (macintosh_config->adb_type) { case MAC_ADB_IOP: @@ -719,19 +727,3 @@ int mac_hwclk(int op, struct rtc_time *t) } return 0; } - -/* - * Set minutes/seconds in the hardware clock - */ - -int mac_set_clock_mmss (unsigned long nowtime) -{ - struct rtc_time now; - - mac_hwclk(0, &now); - now.tm_sec = nowtime % 60; - now.tm_min = (nowtime / 60) % 60; - mac_hwclk(1, &now); - - return 0; -} diff --git a/arch/m68k/mm/init.c b/arch/m68k/mm/init.c index 8827b7f91402..38e2b272c220 100644 --- a/arch/m68k/mm/init.c +++ b/arch/m68k/mm/init.c @@ -71,7 +71,6 @@ void __init m68k_setup_node(int node) pg_data_table[i] = pg_data_map + node; } #endif - pg_data_map[node].bdata = bootmem_node_data + node; node_set_online(node); } diff --git a/arch/m68k/mm/mcfmmu.c b/arch/m68k/mm/mcfmmu.c index 2925d795d71a..70dde040779b 100644 --- a/arch/m68k/mm/mcfmmu.c +++ b/arch/m68k/mm/mcfmmu.c @@ -14,6 +14,7 @@ #include <linux/init.h> #include <linux/string.h> #include <linux/bootmem.h> +#include <linux/memblock.h> #include <asm/setup.h> #include <asm/page.h> @@ -153,31 +154,31 @@ int cf_tlb_miss(struct pt_regs *regs, int write, int dtlb, int extension_word) void __init cf_bootmem_alloc(void) { - unsigned long start_pfn; unsigned long memstart; /* _rambase and _ramend will be naturally page aligned */ m68k_memory[0].addr = _rambase; m68k_memory[0].size = _ramend - _rambase; + memblock_add(m68k_memory[0].addr, m68k_memory[0].size); + /* compute total pages in system */ num_pages = PFN_DOWN(_ramend - _rambase); /* page numbers */ memstart = PAGE_ALIGN(_ramstart); min_low_pfn = PFN_DOWN(_rambase); - start_pfn = PFN_DOWN(memstart); max_pfn = max_low_pfn = PFN_DOWN(_ramend); high_memory = (void *)_ramend; + /* Reserve kernel text/data/bss */ + memblock_reserve(memstart, memstart - _rambase); + m68k_virt_to_node_shift = fls(_ramend - 1) - 6; module_fixup(NULL, __start_fixup, __stop_fixup); - /* setup bootmem data */ + /* setup node data */ m68k_setup_node(0); - memstart += init_bootmem_node(NODE_DATA(0), start_pfn, - min_low_pfn, max_low_pfn); - free_bootmem_node(NODE_DATA(0), memstart, _ramend - memstart); } /* diff --git a/arch/m68k/mm/motorola.c b/arch/m68k/mm/motorola.c index e490ecc7842c..4e17ecb5928a 100644 --- a/arch/m68k/mm/motorola.c +++ b/arch/m68k/mm/motorola.c @@ -19,6 +19,7 @@ #include <linux/types.h> #include <linux/init.h> #include <linux/bootmem.h> +#include <linux/memblock.h> #include <linux/gfp.h> #include <asm/setup.h> @@ -208,7 +209,7 @@ void __init paging_init(void) { unsigned long zones_size[MAX_NR_ZONES] = { 0, }; unsigned long min_addr, max_addr; - unsigned long addr, size, end; + unsigned long addr; int i; #ifdef DEBUG @@ -253,34 +254,20 @@ void __init paging_init(void) min_low_pfn = availmem >> PAGE_SHIFT; max_pfn = max_low_pfn = max_addr >> PAGE_SHIFT; - for (i = 0; i < m68k_num_memory; i++) { - addr = m68k_memory[i].addr; - end = addr + m68k_memory[i].size; - m68k_setup_node(i); - availmem = PAGE_ALIGN(availmem); - availmem += init_bootmem_node(NODE_DATA(i), - availmem >> PAGE_SHIFT, - addr >> PAGE_SHIFT, - end >> PAGE_SHIFT); - } + /* Reserve kernel text/data/bss and the memory allocated in head.S */ + memblock_reserve(m68k_memory[0].addr, availmem - m68k_memory[0].addr); /* * Map the physical memory available into the kernel virtual - * address space. First initialize the bootmem allocator with - * the memory we already mapped, so map_node() has something - * to allocate. + * address space. Make sure memblock will not try to allocate + * pages beyond the memory we already mapped in head.S */ - addr = m68k_memory[0].addr; - size = m68k_memory[0].size; - free_bootmem_node(NODE_DATA(0), availmem, - min(m68k_init_mapped_size, size) - (availmem - addr)); - map_node(0); - if (size > m68k_init_mapped_size) - free_bootmem_node(NODE_DATA(0), addr + m68k_init_mapped_size, - size - m68k_init_mapped_size); - - for (i = 1; i < m68k_num_memory; i++) + memblock_set_bottom_up(true); + + for (i = 0; i < m68k_num_memory; i++) { + m68k_setup_node(i); map_node(i); + } flush_tlb_all(); diff --git a/arch/m68k/mvme147/config.c b/arch/m68k/mvme147/config.c index f8a710fd84cd..adea549d240e 100644 --- a/arch/m68k/mvme147/config.c +++ b/arch/m68k/mvme147/config.c @@ -40,7 +40,6 @@ static void mvme147_get_model(char *model); extern void mvme147_sched_init(irq_handler_t handler); extern u32 mvme147_gettimeoffset(void); extern int mvme147_hwclk (int, struct rtc_time *); -extern int mvme147_set_clock_mmss (unsigned long); extern void mvme147_reset (void); @@ -92,7 +91,6 @@ void __init config_mvme147(void) mach_init_IRQ = mvme147_init_IRQ; arch_gettimeoffset = mvme147_gettimeoffset; mach_hwclk = mvme147_hwclk; - mach_set_clock_mmss = mvme147_set_clock_mmss; mach_reset = mvme147_reset; mach_get_model = mvme147_get_model; @@ -164,8 +162,3 @@ int mvme147_hwclk(int op, struct rtc_time *t) } return 0; } - -int mvme147_set_clock_mmss (unsigned long nowtime) -{ - return 0; -} diff --git a/arch/m68k/mvme16x/config.c b/arch/m68k/mvme16x/config.c index 4ffd9ef98de4..6ee36a5b528d 100644 --- a/arch/m68k/mvme16x/config.c +++ b/arch/m68k/mvme16x/config.c @@ -46,7 +46,6 @@ static void mvme16x_get_model(char *model); extern void mvme16x_sched_init(irq_handler_t handler); extern u32 mvme16x_gettimeoffset(void); extern int mvme16x_hwclk (int, struct rtc_time *); -extern int mvme16x_set_clock_mmss (unsigned long); extern void mvme16x_reset (void); int bcd2int (unsigned char b); @@ -280,7 +279,6 @@ void __init config_mvme16x(void) mach_init_IRQ = mvme16x_init_IRQ; arch_gettimeoffset = mvme16x_gettimeoffset; mach_hwclk = mvme16x_hwclk; - mach_set_clock_mmss = mvme16x_set_clock_mmss; mach_reset = mvme16x_reset; mach_get_model = mvme16x_get_model; mach_get_hardware_list = mvme16x_get_hardware_list; @@ -411,9 +409,3 @@ int mvme16x_hwclk(int op, struct rtc_time *t) } return 0; } - -int mvme16x_set_clock_mmss (unsigned long nowtime) -{ - return 0; -} - diff --git a/arch/m68k/q40/config.c b/arch/m68k/q40/config.c index 71c0867ecf20..96810d91da2b 100644 --- a/arch/m68k/q40/config.c +++ b/arch/m68k/q40/config.c @@ -43,7 +43,6 @@ extern void q40_sched_init(irq_handler_t handler); static u32 q40_gettimeoffset(void); static int q40_hwclk(int, struct rtc_time *); static unsigned int q40_get_ss(void); -static int q40_set_clock_mmss(unsigned long); static int q40_get_rtc_pll(struct rtc_pll_info *pll); static int q40_set_rtc_pll(struct rtc_pll_info *pll); @@ -175,7 +174,6 @@ void __init config_q40(void) mach_get_ss = q40_get_ss; mach_get_rtc_pll = q40_get_rtc_pll; mach_set_rtc_pll = q40_set_rtc_pll; - mach_set_clock_mmss = q40_set_clock_mmss; mach_reset = q40_reset; mach_get_model = q40_get_model; @@ -267,34 +265,6 @@ static unsigned int q40_get_ss(void) return bcd2bin(Q40_RTC_SECS); } -/* - * Set the minutes and seconds from seconds value 'nowtime'. Fail if - * clock is out by > 30 minutes. Logic lifted from atari code. - */ - -static int q40_set_clock_mmss(unsigned long nowtime) -{ - int retval = 0; - short real_seconds = nowtime % 60, real_minutes = (nowtime / 60) % 60; - - int rtc_minutes; - - rtc_minutes = bcd2bin(Q40_RTC_MINS); - - if ((rtc_minutes < real_minutes ? - real_minutes - rtc_minutes : - rtc_minutes - real_minutes) < 30) { - Q40_RTC_CTRL |= Q40_RTC_WRITE; - Q40_RTC_MINS = bin2bcd(real_minutes); - Q40_RTC_SECS = bin2bcd(real_seconds); - Q40_RTC_CTRL &= ~(Q40_RTC_WRITE); - } else - retval = -1; - - return retval; -} - - /* get and set PLL calibration of RTC clock */ #define Q40_RTC_PLL_MASK ((1<<5)-1) #define Q40_RTC_PLL_SIGN (1<<5) diff --git a/arch/m68k/sun3/config.c b/arch/m68k/sun3/config.c index 1d28d380e8cc..79a2bb857906 100644 --- a/arch/m68k/sun3/config.c +++ b/arch/m68k/sun3/config.c @@ -123,10 +123,6 @@ static void __init sun3_bootmem_alloc(unsigned long memory_start, availmem = memory_start; m68k_setup_node(0); - availmem += init_bootmem(start_page, num_pages); - availmem = (availmem + (PAGE_SIZE-1)) & PAGE_MASK; - - free_bootmem(__pa(availmem), memory_end - (availmem)); } diff --git a/arch/mips/include/asm/atomic.h b/arch/mips/include/asm/atomic.h index 0ab176bdb8e8..79be687de4ab 100644 --- a/arch/mips/include/asm/atomic.h +++ b/arch/mips/include/asm/atomic.h @@ -274,97 +274,12 @@ static __inline__ int atomic_sub_if_positive(int i, atomic_t * v) #define atomic_cmpxchg(v, o, n) (cmpxchg(&((v)->counter), (o), (n))) #define atomic_xchg(v, new) (xchg(&((v)->counter), (new))) -/** - * __atomic_add_unless - add unless the number is a given value - * @v: pointer of type atomic_t - * @a: the amount to add to v... - * @u: ...unless v is equal to u. - * - * Atomically adds @a to @v, so long as it was not @u. - * Returns the old value of @v. - */ -static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u) -{ - int c, old; - c = atomic_read(v); - for (;;) { - if (unlikely(c == (u))) - break; - old = atomic_cmpxchg((v), c, c + (a)); - if (likely(old == c)) - break; - c = old; - } - return c; -} - -#define atomic_dec_return(v) atomic_sub_return(1, (v)) -#define atomic_inc_return(v) atomic_add_return(1, (v)) - -/* - * atomic_sub_and_test - subtract value from variable and test result - * @i: integer value to subtract - * @v: pointer of type atomic_t - * - * Atomically subtracts @i from @v and returns - * true if the result is zero, or false for all - * other cases. - */ -#define atomic_sub_and_test(i, v) (atomic_sub_return((i), (v)) == 0) - -/* - * atomic_inc_and_test - increment and test - * @v: pointer of type atomic_t - * - * Atomically increments @v by 1 - * and returns true if the result is zero, or false for all - * other cases. - */ -#define atomic_inc_and_test(v) (atomic_inc_return(v) == 0) - -/* - * atomic_dec_and_test - decrement by 1 and test - * @v: pointer of type atomic_t - * - * Atomically decrements @v by 1 and - * returns true if the result is 0, or false for all other - * cases. - */ -#define atomic_dec_and_test(v) (atomic_sub_return(1, (v)) == 0) - /* * atomic_dec_if_positive - decrement by 1 if old value positive * @v: pointer of type atomic_t */ #define atomic_dec_if_positive(v) atomic_sub_if_positive(1, v) -/* - * atomic_inc - increment atomic variable - * @v: pointer of type atomic_t - * - * Atomically increments @v by 1. - */ -#define atomic_inc(v) atomic_add(1, (v)) - -/* - * atomic_dec - decrement and test - * @v: pointer of type atomic_t - * - * Atomically decrements @v by 1. - */ -#define atomic_dec(v) atomic_sub(1, (v)) - -/* - * atomic_add_negative - add and test if negative - * @v: pointer of type atomic_t - * @i: integer value to add - * - * Atomically adds @i to @v and returns true - * if the result is negative, or false when - * result is greater than or equal to zero. - */ -#define atomic_add_negative(i, v) (atomic_add_return(i, (v)) < 0) - #ifdef CONFIG_64BIT #define ATOMIC64_INIT(i) { (i) } @@ -620,99 +535,12 @@ static __inline__ long atomic64_sub_if_positive(long i, atomic64_t * v) ((__typeof__((v)->counter))cmpxchg(&((v)->counter), (o), (n))) #define atomic64_xchg(v, new) (xchg(&((v)->counter), (new))) -/** - * atomic64_add_unless - add unless the number is a given value - * @v: pointer of type atomic64_t - * @a: the amount to add to v... - * @u: ...unless v is equal to u. - * - * Atomically adds @a to @v, so long as it was not @u. - * Returns true iff @v was not @u. - */ -static __inline__ int atomic64_add_unless(atomic64_t *v, long a, long u) -{ - long c, old; - c = atomic64_read(v); - for (;;) { - if (unlikely(c == (u))) - break; - old = atomic64_cmpxchg((v), c, c + (a)); - if (likely(old == c)) - break; - c = old; - } - return c != (u); -} - -#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0) - -#define atomic64_dec_return(v) atomic64_sub_return(1, (v)) -#define atomic64_inc_return(v) atomic64_add_return(1, (v)) - -/* - * atomic64_sub_and_test - subtract value from variable and test result - * @i: integer value to subtract - * @v: pointer of type atomic64_t - * - * Atomically subtracts @i from @v and returns - * true if the result is zero, or false for all - * other cases. - */ -#define atomic64_sub_and_test(i, v) (atomic64_sub_return((i), (v)) == 0) - -/* - * atomic64_inc_and_test - increment and test - * @v: pointer of type atomic64_t - * - * Atomically increments @v by 1 - * and returns true if the result is zero, or false for all - * other cases. - */ -#define atomic64_inc_and_test(v) (atomic64_inc_return(v) == 0) - -/* - * atomic64_dec_and_test - decrement by 1 and test - * @v: pointer of type atomic64_t - * - * Atomically decrements @v by 1 and - * returns true if the result is 0, or false for all other - * cases. - */ -#define atomic64_dec_and_test(v) (atomic64_sub_return(1, (v)) == 0) - /* * atomic64_dec_if_positive - decrement by 1 if old value positive * @v: pointer of type atomic64_t */ #define atomic64_dec_if_positive(v) atomic64_sub_if_positive(1, v) -/* - * atomic64_inc - increment atomic variable - * @v: pointer of type atomic64_t - * - * Atomically increments @v by 1. - */ -#define atomic64_inc(v) atomic64_add(1, (v)) - -/* - * atomic64_dec - decrement and test - * @v: pointer of type atomic64_t - * - * Atomically decrements @v by 1. - */ -#define atomic64_dec(v) atomic64_sub(1, (v)) - -/* - * atomic64_add_negative - add and test if negative - * @v: pointer of type atomic64_t - * @i: integer value to add - * - * Atomically adds @i to @v and returns true - * if the result is negative, or false when - * result is greater than or equal to zero. - */ -#define atomic64_add_negative(i, v) (atomic64_add_return(i, (v)) < 0) - #endif /* CONFIG_64BIT */ #endif /* _ASM_ATOMIC_H */ diff --git a/arch/mips/include/asm/kprobes.h b/arch/mips/include/asm/kprobes.h index ad1a99948f27..a72dfbf1babb 100644 --- a/arch/mips/include/asm/kprobes.h +++ b/arch/mips/include/asm/kprobes.h @@ -68,16 +68,6 @@ struct prev_kprobe { unsigned long saved_epc; }; -#define MAX_JPROBES_STACK_SIZE 128 -#define MAX_JPROBES_STACK_ADDR \ - (((unsigned long)current_thread_info()) + THREAD_SIZE - 32 - sizeof(struct pt_regs)) - -#define MIN_JPROBES_STACK_SIZE(ADDR) \ - ((((ADDR) + MAX_JPROBES_STACK_SIZE) > MAX_JPROBES_STACK_ADDR) \ - ? MAX_JPROBES_STACK_ADDR - (ADDR) \ - : MAX_JPROBES_STACK_SIZE) - - #define SKIP_DELAYSLOT 0x0001 /* per-cpu kprobe control block */ @@ -86,12 +76,9 @@ struct kprobe_ctlblk { unsigned long kprobe_old_SR; unsigned long kprobe_saved_SR; unsigned long kprobe_saved_epc; - unsigned long jprobe_saved_sp; - struct pt_regs jprobe_saved_regs; /* Per-thread fields, used while emulating branches */ unsigned long flags; unsigned long target_epc; - u8 jprobes_stack[MAX_JPROBES_STACK_SIZE]; struct prev_kprobe prev_kprobe; }; diff --git a/arch/mips/kernel/kprobes.c b/arch/mips/kernel/kprobes.c index f5c8bce70db2..54cd675c5d1d 100644 --- a/arch/mips/kernel/kprobes.c +++ b/arch/mips/kernel/kprobes.c @@ -326,19 +326,13 @@ static int __kprobes kprobe_handler(struct pt_regs *regs) preempt_enable_no_resched(); } return 1; - } else { - if (addr->word != breakpoint_insn.word) { - /* - * The breakpoint instruction was removed by - * another cpu right after we hit, no further - * handling of this interrupt is appropriate - */ - ret = 1; - goto no_kprobe; - } - p = __this_cpu_read(current_kprobe); - if (p->break_handler && p->break_handler(p, regs)) - goto ss_probe; + } else if (addr->word != breakpoint_insn.word) { + /* + * The breakpoint instruction was removed by + * another cpu right after we hit, no further + * handling of this interrupt is appropriate + */ + ret = 1; } goto no_kprobe; } @@ -364,10 +358,11 @@ static int __kprobes kprobe_handler(struct pt_regs *regs) if (p->pre_handler && p->pre_handler(p, regs)) { /* handler has already set things up, so skip ss setup */ + reset_current_kprobe(); + preempt_enable_no_resched(); return 1; } -ss_probe: prepare_singlestep(p, regs, kcb); if (kcb->flags & SKIP_DELAYSLOT) { kcb->kprobe_status = KPROBE_HIT_SSDONE; @@ -468,51 +463,6 @@ int __kprobes kprobe_exceptions_notify(struct notifier_block *self, return ret; } -int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs) -{ - struct jprobe *jp = container_of(p, struct jprobe, kp); - struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - - kcb->jprobe_saved_regs = *regs; - kcb->jprobe_saved_sp = regs->regs[29]; - - memcpy(kcb->jprobes_stack, (void *)kcb->jprobe_saved_sp, - MIN_JPROBES_STACK_SIZE(kcb->jprobe_saved_sp)); - - regs->cp0_epc = (unsigned long)(jp->entry); - - return 1; -} - -/* Defined in the inline asm below. */ -void jprobe_return_end(void); - -void __kprobes jprobe_return(void) -{ - /* Assembler quirk necessitates this '0,code' business. */ - asm volatile( - "break 0,%0\n\t" - ".globl jprobe_return_end\n" - "jprobe_return_end:\n" - : : "n" (BRK_KPROBE_BP) : "memory"); -} - -int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs) -{ - struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - - if (regs->cp0_epc >= (unsigned long)jprobe_return && - regs->cp0_epc <= (unsigned long)jprobe_return_end) { - *regs = kcb->jprobe_saved_regs; - memcpy((void *)kcb->jprobe_saved_sp, kcb->jprobes_stack, - MIN_JPROBES_STACK_SIZE(kcb->jprobe_saved_sp)); - preempt_enable_no_resched(); - - return 1; - } - return 0; -} - /* * Function return probe trampoline: * - init_kprobes() establishes a probepoint here @@ -595,9 +545,7 @@ static int __kprobes trampoline_probe_handler(struct kprobe *p, kretprobe_assert(ri, orig_ret_address, trampoline_address); instruction_pointer(regs) = orig_ret_address; - reset_current_kprobe(); kretprobe_hash_unlock(current, &flags); - preempt_enable_no_resched(); hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) { hlist_del(&ri->hlist); diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c index 7cd76f93a438..f7ea8e21656b 100644 --- a/arch/mips/kvm/mips.c +++ b/arch/mips/kvm/mips.c @@ -515,7 +515,7 @@ int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu, dvcpu->arch.wait = 0; if (swq_has_sleeper(&dvcpu->wq)) - swake_up(&dvcpu->wq); + swake_up_one(&dvcpu->wq); return 0; } @@ -1204,7 +1204,7 @@ static void kvm_mips_comparecount_func(unsigned long data) vcpu->arch.wait = 0; if (swq_has_sleeper(&vcpu->wq)) - swake_up(&vcpu->wq); + swake_up_one(&vcpu->wq); } /* low level hrtimer wake routine */ diff --git a/arch/openrisc/Kconfig b/arch/openrisc/Kconfig index 9ecad05bfc73..dfb6a79ba7ff 100644 --- a/arch/openrisc/Kconfig +++ b/arch/openrisc/Kconfig @@ -27,7 +27,6 @@ config OPENRISC select GENERIC_STRNLEN_USER select GENERIC_SMP_IDLE_THREAD select MODULES_USE_ELF_RELA - select MULTI_IRQ_HANDLER select HAVE_DEBUG_STACKOVERFLOW select OR1K_PIC select CPU_NO_EFFICIENT_FFS if !OPENRISC_HAVE_INST_FF1 @@ -36,6 +35,7 @@ config OPENRISC select ARCH_USE_QUEUED_RWLOCKS select OMPIC if SMP select ARCH_WANT_FRAME_POINTERS + select GENERIC_IRQ_MULTI_HANDLER config CPU_BIG_ENDIAN def_bool y @@ -69,9 +69,6 @@ config STACKTRACE_SUPPORT config LOCKDEP_SUPPORT def_bool y -config MULTI_IRQ_HANDLER - def_bool y - source "init/Kconfig" source "kernel/Kconfig.freezer" diff --git a/arch/openrisc/include/asm/atomic.h b/arch/openrisc/include/asm/atomic.h index 146e1660f00e..b589fac39b92 100644 --- a/arch/openrisc/include/asm/atomic.h +++ b/arch/openrisc/include/asm/atomic.h @@ -100,7 +100,7 @@ ATOMIC_OP(xor) * * This is often used through atomic_inc_not_zero() */ -static inline int __atomic_add_unless(atomic_t *v, int a, int u) +static inline int atomic_fetch_add_unless(atomic_t *v, int a, int u) { int old, tmp; @@ -119,7 +119,7 @@ static inline int __atomic_add_unless(atomic_t *v, int a, int u) return old; } -#define __atomic_add_unless __atomic_add_unless +#define atomic_fetch_add_unless atomic_fetch_add_unless #include <asm-generic/atomic.h> diff --git a/arch/openrisc/include/asm/cmpxchg.h b/arch/openrisc/include/asm/cmpxchg.h index d29f7db53906..f9cd43a39d72 100644 --- a/arch/openrisc/include/asm/cmpxchg.h +++ b/arch/openrisc/include/asm/cmpxchg.h @@ -16,8 +16,9 @@ #ifndef __ASM_OPENRISC_CMPXCHG_H #define __ASM_OPENRISC_CMPXCHG_H +#include <linux/bits.h> +#include <linux/compiler.h> #include <linux/types.h> -#include <linux/bitops.h> #define __HAVE_ARCH_CMPXCHG 1 diff --git a/arch/openrisc/include/asm/irq.h b/arch/openrisc/include/asm/irq.h index d9eee0a2b7b4..eb612b1865d2 100644 --- a/arch/openrisc/include/asm/irq.h +++ b/arch/openrisc/include/asm/irq.h @@ -24,6 +24,4 @@ #define NO_IRQ (-1) -extern void set_handle_irq(void (*handle_irq)(struct pt_regs *)); - #endif /* __ASM_OPENRISC_IRQ_H__ */ diff --git a/arch/openrisc/kernel/irq.c b/arch/openrisc/kernel/irq.c index 35e478a93116..5f9445effaf8 100644 --- a/arch/openrisc/kernel/irq.c +++ b/arch/openrisc/kernel/irq.c @@ -41,13 +41,6 @@ void __init init_IRQ(void) irqchip_init(); } -static void (*handle_arch_irq)(struct pt_regs *); - -void __init set_handle_irq(void (*handle_irq)(struct pt_regs *)) -{ - handle_arch_irq = handle_irq; -} - void __irq_entry do_IRQ(struct pt_regs *regs) { handle_arch_irq(regs); diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig index 17526bebcbd2..e7705dde953f 100644 --- a/arch/parisc/Kconfig +++ b/arch/parisc/Kconfig @@ -11,7 +11,6 @@ config PARISC select ARCH_HAS_ELF_RANDOMIZE select ARCH_HAS_STRICT_KERNEL_RWX select ARCH_HAS_UBSAN_SANITIZE_ALL - select ARCH_WANTS_UBSAN_NO_NULL select ARCH_SUPPORTS_MEMORY_FAILURE select RTC_CLASS select RTC_DRV_GENERIC @@ -195,7 +194,7 @@ config PREFETCH config MLONGCALLS bool "Enable the -mlong-calls compiler option for big kernels" - def_bool y if (!MODULES) + default y depends on PA8X00 help If you configure the kernel to include many drivers built-in instead diff --git a/arch/parisc/include/asm/atomic.h b/arch/parisc/include/asm/atomic.h index 88bae6676c9b..118953d41763 100644 --- a/arch/parisc/include/asm/atomic.h +++ b/arch/parisc/include/asm/atomic.h @@ -77,30 +77,6 @@ static __inline__ int atomic_read(const atomic_t *v) #define atomic_cmpxchg(v, o, n) (cmpxchg(&((v)->counter), (o), (n))) #define atomic_xchg(v, new) (xchg(&((v)->counter), new)) -/** - * __atomic_add_unless - add unless the number is a given value - * @v: pointer of type atomic_t - * @a: the amount to add to v... - * @u: ...unless v is equal to u. - * - * Atomically adds @a to @v, so long as it was not @u. - * Returns the old value of @v. - */ -static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u) -{ - int c, old; - c = atomic_read(v); - for (;;) { - if (unlikely(c == (u))) - break; - old = atomic_cmpxchg((v), c, c + (a)); - if (likely(old == c)) - break; - c = old; - } - return c; -} - #define ATOMIC_OP(op, c_op) \ static __inline__ void atomic_##op(int i, atomic_t *v) \ { \ @@ -160,28 +136,6 @@ ATOMIC_OPS(xor, ^=) #undef ATOMIC_OP_RETURN #undef ATOMIC_OP -#define atomic_inc(v) (atomic_add( 1,(v))) -#define atomic_dec(v) (atomic_add( -1,(v))) - -#define atomic_inc_return(v) (atomic_add_return( 1,(v))) -#define atomic_dec_return(v) (atomic_add_return( -1,(v))) - -#define atomic_add_negative(a, v) (atomic_add_return((a), (v)) < 0) - -/* - * atomic_inc_and_test - increment and test - * @v: pointer of type atomic_t - * - * Atomically increments @v by 1 - * and returns true if the result is zero, or false for all - * other cases. - */ -#define atomic_inc_and_test(v) (atomic_inc_return(v) == 0) - -#define atomic_dec_and_test(v) (atomic_dec_return(v) == 0) - -#define atomic_sub_and_test(i,v) (atomic_sub_return((i),(v)) == 0) - #define ATOMIC_INIT(i) { (i) } #ifdef CONFIG_64BIT @@ -264,72 +218,11 @@ atomic64_read(const atomic64_t *v) return READ_ONCE((v)->counter); } -#define atomic64_inc(v) (atomic64_add( 1,(v))) -#define atomic64_dec(v) (atomic64_add( -1,(v))) - -#define atomic64_inc_return(v) (atomic64_add_return( 1,(v))) -#define atomic64_dec_return(v) (atomic64_add_return( -1,(v))) - -#define atomic64_add_negative(a, v) (atomic64_add_return((a), (v)) < 0) - -#define atomic64_inc_and_test(v) (atomic64_inc_return(v) == 0) -#define atomic64_dec_and_test(v) (atomic64_dec_return(v) == 0) -#define atomic64_sub_and_test(i,v) (atomic64_sub_return((i),(v)) == 0) - /* exported interface */ #define atomic64_cmpxchg(v, o, n) \ ((__typeof__((v)->counter))cmpxchg(&((v)->counter), (o), (n))) #define atomic64_xchg(v, new) (xchg(&((v)->counter), new)) -/** - * atomic64_add_unless - add unless the number is a given value - * @v: pointer of type atomic64_t - * @a: the amount to add to v... - * @u: ...unless v is equal to u. - * - * Atomically adds @a to @v, so long as it was not @u. - * Returns the old value of @v. - */ -static __inline__ int atomic64_add_unless(atomic64_t *v, long a, long u) -{ - long c, old; - c = atomic64_read(v); - for (;;) { - if (unlikely(c == (u))) - break; - old = atomic64_cmpxchg((v), c, c + (a)); - if (likely(old == c)) - break; - c = old; - } - return c != (u); -} - -#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0) - -/* - * atomic64_dec_if_positive - decrement by 1 if old value positive - * @v: pointer of type atomic_t - * - * The function returns the old value of *v minus 1, even if - * the atomic variable, v, was not decremented. - */ -static inline long atomic64_dec_if_positive(atomic64_t *v) -{ - long c, old, dec; - c = atomic64_read(v); - for (;;) { - dec = c - 1; - if (unlikely(dec < 0)) - break; - old = atomic64_cmpxchg((v), c, dec); - if (likely(old == c)) - break; - c = old; - } - return dec; -} - #endif /* !CONFIG_64BIT */ diff --git a/arch/parisc/include/asm/barrier.h b/arch/parisc/include/asm/barrier.h new file mode 100644 index 000000000000..dbaaca84f27f --- /dev/null +++ b/arch/parisc/include/asm/barrier.h @@ -0,0 +1,32 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __ASM_BARRIER_H +#define __ASM_BARRIER_H + +#ifndef __ASSEMBLY__ + +/* The synchronize caches instruction executes as a nop on systems in + which all memory references are performed in order. */ +#define synchronize_caches() __asm__ __volatile__ ("sync" : : : "memory") + +#if defined(CONFIG_SMP) +#define mb() do { synchronize_caches(); } while (0) +#define rmb() mb() +#define wmb() mb() +#define dma_rmb() mb() +#define dma_wmb() mb() +#else +#define mb() barrier() +#define rmb() barrier() +#define wmb() barrier() +#define dma_rmb() barrier() +#define dma_wmb() barrier() +#endif + +#define __smp_mb() mb() +#define __smp_rmb() mb() +#define __smp_wmb() mb() + +#include <asm-generic/barrier.h> + +#endif /* !__ASSEMBLY__ */ +#endif /* __ASM_BARRIER_H */ diff --git a/arch/parisc/kernel/entry.S b/arch/parisc/kernel/entry.S index e95207c0565e..1b4732e20137 100644 --- a/arch/parisc/kernel/entry.S +++ b/arch/parisc/kernel/entry.S @@ -482,6 +482,8 @@ .macro tlb_unlock0 spc,tmp #ifdef CONFIG_SMP or,COND(=) %r0,\spc,%r0 + sync + or,COND(=) %r0,\spc,%r0 stw \spc,0(\tmp) #endif .endm diff --git a/arch/parisc/kernel/pacache.S b/arch/parisc/kernel/pacache.S index 22e6374ece44..97451e67d35b 100644 --- a/arch/parisc/kernel/pacache.S +++ b/arch/parisc/kernel/pacache.S @@ -353,6 +353,7 @@ ENDPROC_CFI(flush_data_cache_local) .macro tlb_unlock la,flags,tmp #ifdef CONFIG_SMP ldi 1,\tmp + sync stw \tmp,0(\la) mtsm \flags #endif diff --git a/arch/parisc/kernel/syscall.S b/arch/parisc/kernel/syscall.S index e775f80ae28c..4886a6db42e9 100644 --- a/arch/parisc/kernel/syscall.S +++ b/arch/parisc/kernel/syscall.S @@ -633,6 +633,7 @@ cas_action: sub,<> %r28, %r25, %r0 2: stw,ma %r24, 0(%r26) /* Free lock */ + sync stw,ma %r20, 0(%sr2,%r20) #if ENABLE_LWS_DEBUG /* Clear thread register indicator */ @@ -647,6 +648,7 @@ cas_action: 3: /* Error occurred on load or store */ /* Free lock */ + sync stw %r20, 0(%sr2,%r20) #if ENABLE_LWS_DEBUG stw %r0, 4(%sr2,%r20) @@ -848,6 +850,7 @@ cas2_action: cas2_end: /* Free lock */ + sync stw,ma %r20, 0(%sr2,%r20) /* Enable interrupts */ ssm PSW_SM_I, %r0 @@ -858,6 +861,7 @@ cas2_end: 22: /* Error occurred on load or store */ /* Free lock */ + sync stw %r20, 0(%sr2,%r20) ssm PSW_SM_I, %r0 ldo 1(%r0),%r28 diff --git a/arch/powerpc/include/asm/atomic.h b/arch/powerpc/include/asm/atomic.h index 682b3e6a1e21..963abf8bf1c0 100644 --- a/arch/powerpc/include/asm/atomic.h +++ b/arch/powerpc/include/asm/atomic.h @@ -18,18 +18,11 @@ * a "bne-" instruction at the end, so an isync is enough as a acquire barrier * on the platform without lwsync. */ -#define __atomic_op_acquire(op, args...) \ -({ \ - typeof(op##_relaxed(args)) __ret = op##_relaxed(args); \ - __asm__ __volatile__(PPC_ACQUIRE_BARRIER "" : : : "memory"); \ - __ret; \ -}) - -#define __atomic_op_release(op, args...) \ -({ \ - __asm__ __volatile__(PPC_RELEASE_BARRIER "" : : : "memory"); \ - op##_relaxed(args); \ -}) +#define __atomic_acquire_fence() \ + __asm__ __volatile__(PPC_ACQUIRE_BARRIER "" : : : "memory") + +#define __atomic_release_fence() \ + __asm__ __volatile__(PPC_RELEASE_BARRIER "" : : : "memory") static __inline__ int atomic_read(const atomic_t *v) { @@ -129,8 +122,6 @@ ATOMIC_OPS(xor, xor) #undef ATOMIC_OP_RETURN_RELAXED #undef ATOMIC_OP -#define atomic_add_negative(a, v) (atomic_add_return((a), (v)) < 0) - static __inline__ void atomic_inc(atomic_t *v) { int t; @@ -145,6 +136,7 @@ static __inline__ void atomic_inc(atomic_t *v) : "r" (&v->counter) : "cc", "xer"); } +#define atomic_inc atomic_inc static __inline__ int atomic_inc_return_relaxed(atomic_t *v) { @@ -163,16 +155,6 @@ static __inline__ int atomic_inc_return_relaxed(atomic_t *v) return t; } -/* - * atomic_inc_and_test - increment and test - * @v: pointer of type atomic_t - * - * Atomically increments @v by 1 - * and returns true if the result is zero, or false for all - * other cases. - */ -#define atomic_inc_and_test(v) (atomic_inc_return(v) == 0) - static __inline__ void atomic_dec(atomic_t *v) { int t; @@ -187,6 +169,7 @@ static __inline__ void atomic_dec(atomic_t *v) : "r" (&v->counter) : "cc", "xer"); } +#define atomic_dec atomic_dec static __inline__ int atomic_dec_return_relaxed(atomic_t *v) { @@ -218,7 +201,7 @@ static __inline__ int atomic_dec_return_relaxed(atomic_t *v) #define atomic_xchg_relaxed(v, new) xchg_relaxed(&((v)->counter), (new)) /** - * __atomic_add_unless - add unless the number is a given value + * atomic_fetch_add_unless - add unless the number is a given value * @v: pointer of type atomic_t * @a: the amount to add to v... * @u: ...unless v is equal to u. @@ -226,13 +209,13 @@ static __inline__ int atomic_dec_return_relaxed(atomic_t *v) * Atomically adds @a to @v, so long as it was not @u. * Returns the old value of @v. */ -static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u) +static __inline__ int atomic_fetch_add_unless(atomic_t *v, int a, int u) { int t; __asm__ __volatile__ ( PPC_ATOMIC_ENTRY_BARRIER -"1: lwarx %0,0,%1 # __atomic_add_unless\n\ +"1: lwarx %0,0,%1 # atomic_fetch_add_unless\n\ cmpw 0,%0,%3 \n\ beq 2f \n\ add %0,%2,%0 \n" @@ -248,6 +231,7 @@ static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u) return t; } +#define atomic_fetch_add_unless atomic_fetch_add_unless /** * atomic_inc_not_zero - increment unless the number is zero @@ -280,9 +264,6 @@ static __inline__ int atomic_inc_not_zero(atomic_t *v) } #define atomic_inc_not_zero(v) atomic_inc_not_zero((v)) -#define atomic_sub_and_test(a, v) (atomic_sub_return((a), (v)) == 0) -#define atomic_dec_and_test(v) (atomic_dec_return((v)) == 0) - /* * Atomically test *v and decrement if it is greater than 0. * The function returns the old value of *v minus 1, even if @@ -412,8 +393,6 @@ ATOMIC64_OPS(xor, xor) #undef ATOMIC64_OP_RETURN_RELAXED #undef ATOMIC64_OP -#define atomic64_add_negative(a, v) (atomic64_add_return((a), (v)) < 0) - static __inline__ void atomic64_inc(atomic64_t *v) { long t; @@ -427,6 +406,7 @@ static __inline__ void atomic64_inc(atomic64_t *v) : "r" (&v->counter) : "cc", "xer"); } +#define atomic64_inc atomic64_inc static __inline__ long atomic64_inc_return_relaxed(atomic64_t *v) { @@ -444,16 +424,6 @@ static __inline__ long atomic64_inc_return_relaxed(atomic64_t *v) return t; } -/* - * atomic64_inc_and_test - increment and test - * @v: pointer of type atomic64_t - * - * Atomically increments @v by 1 - * and returns true if the result is zero, or false for all - * other cases. - */ -#define atomic64_inc_and_test(v) (atomic64_inc_return(v) == 0) - static __inline__ void atomic64_dec(atomic64_t *v) { long t; @@ -467,6 +437,7 @@ static __inline__ void atomic64_dec(atomic64_t *v) : "r" (&v->counter) : "cc", "xer"); } +#define atomic64_dec atomic64_dec static __inline__ long atomic64_dec_return_relaxed(atomic64_t *v) { @@ -487,9 +458,6 @@ static __inline__ long atomic64_dec_return_relaxed(atomic64_t *v) #define atomic64_inc_return_relaxed atomic64_inc_return_relaxed #define atomic64_dec_return_relaxed atomic64_dec_return_relaxed -#define atomic64_sub_and_test(a, v) (atomic64_sub_return((a), (v)) == 0) -#define atomic64_dec_and_test(v) (atomic64_dec_return((v)) == 0) - /* * Atomically test *v and decrement if it is greater than 0. * The function returns the old value of *v minus 1. @@ -513,6 +481,7 @@ static __inline__ long atomic64_dec_if_positive(atomic64_t *v) return t; } +#define atomic64_dec_if_positive atomic64_dec_if_positive #define atomic64_cmpxchg(v, o, n) (cmpxchg(&((v)->counter), (o), (n))) #define atomic64_cmpxchg_relaxed(v, o, n) \ @@ -524,7 +493,7 @@ static __inline__ long atomic64_dec_if_positive(atomic64_t *v) #define atomic64_xchg_relaxed(v, new) xchg_relaxed(&((v)->counter), (new)) /** - * atomic64_add_unless - add unless the number is a given value + * atomic64_fetch_add_unless - add unless the number is a given value * @v: pointer of type atomic64_t * @a: the amount to add to v... * @u: ...unless v is equal to u. @@ -532,13 +501,13 @@ static __inline__ long atomic64_dec_if_positive(atomic64_t *v) * Atomically adds @a to @v, so long as it was not @u. * Returns the old value of @v. */ -static __inline__ int atomic64_add_unless(atomic64_t *v, long a, long u) +static __inline__ long atomic64_fetch_add_unless(atomic64_t *v, long a, long u) { long t; __asm__ __volatile__ ( PPC_ATOMIC_ENTRY_BARRIER -"1: ldarx %0,0,%1 # __atomic_add_unless\n\ +"1: ldarx %0,0,%1 # atomic64_fetch_add_unless\n\ cmpd 0,%0,%3 \n\ beq 2f \n\ add %0,%2,%0 \n" @@ -551,8 +520,9 @@ static __inline__ int atomic64_add_unless(atomic64_t *v, long a, long u) : "r" (&v->counter), "r" (a), "r" (u) : "cc", "memory"); - return t != u; + return t; } +#define atomic64_fetch_add_unless atomic64_fetch_add_unless /** * atomic_inc64_not_zero - increment unless the number is zero @@ -582,6 +552,7 @@ static __inline__ int atomic64_inc_not_zero(atomic64_t *v) return t1 != 0; } +#define atomic64_inc_not_zero(v) atomic64_inc_not_zero((v)) #endif /* __powerpc64__ */ diff --git a/arch/powerpc/include/asm/hw_breakpoint.h b/arch/powerpc/include/asm/hw_breakpoint.h index 8e7b09703ca4..27d6e3c8fde9 100644 --- a/arch/powerpc/include/asm/hw_breakpoint.h +++ b/arch/powerpc/include/asm/hw_breakpoint.h @@ -52,6 +52,7 @@ struct arch_hw_breakpoint { #include <asm/reg.h> #include <asm/debug.h> +struct perf_event_attr; struct perf_event; struct pmu; struct perf_sample_data; @@ -60,8 +61,10 @@ struct perf_sample_data; extern int hw_breakpoint_slots(int type); extern int arch_bp_generic_fields(int type, int *gen_bp_type); -extern int arch_check_bp_in_kernelspace(struct perf_event *bp); -extern int arch_validate_hwbkpt_settings(struct perf_event *bp); +extern int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw); +extern int hw_breakpoint_arch_parse(struct perf_event *bp, + const struct perf_event_attr *attr, + struct arch_hw_breakpoint *hw); extern int hw_breakpoint_exceptions_notify(struct notifier_block *unused, unsigned long val, void *data); int arch_install_hw_breakpoint(struct perf_event *bp); diff --git a/arch/powerpc/include/asm/kprobes.h b/arch/powerpc/include/asm/kprobes.h index 9f3be5c8a4a3..785c464b6588 100644 --- a/arch/powerpc/include/asm/kprobes.h +++ b/arch/powerpc/include/asm/kprobes.h @@ -88,7 +88,6 @@ struct prev_kprobe { struct kprobe_ctlblk { unsigned long kprobe_status; unsigned long kprobe_saved_msr; - struct pt_regs jprobe_saved_regs; struct prev_kprobe prev_kprobe; }; @@ -103,17 +102,6 @@ extern int kprobe_exceptions_notify(struct notifier_block *self, extern int kprobe_fault_handler(struct pt_regs *regs, int trapnr); extern int kprobe_handler(struct pt_regs *regs); extern int kprobe_post_handler(struct pt_regs *regs); -#ifdef CONFIG_KPROBES_ON_FTRACE -extern int __is_active_jprobe(unsigned long addr); -extern int skip_singlestep(struct kprobe *p, struct pt_regs *regs, - struct kprobe_ctlblk *kcb); -#else -static inline int skip_singlestep(struct kprobe *p, struct pt_regs *regs, - struct kprobe_ctlblk *kcb) -{ - return 0; -} -#endif #else static inline int kprobe_handler(struct pt_regs *regs) { return 0; } static inline int kprobe_post_handler(struct pt_regs *regs) { return 0; } diff --git a/arch/powerpc/kernel/hw_breakpoint.c b/arch/powerpc/kernel/hw_breakpoint.c index 80547dad37da..fec8a6773119 100644 --- a/arch/powerpc/kernel/hw_breakpoint.c +++ b/arch/powerpc/kernel/hw_breakpoint.c @@ -119,11 +119,9 @@ void arch_unregister_hw_breakpoint(struct perf_event *bp) /* * Check for virtual address in kernel space. */ -int arch_check_bp_in_kernelspace(struct perf_event *bp) +int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw) { - struct arch_hw_breakpoint *info = counter_arch_bp(bp); - - return is_kernel_addr(info->address); + return is_kernel_addr(hw->address); } int arch_bp_generic_fields(int type, int *gen_bp_type) @@ -141,30 +139,31 @@ int arch_bp_generic_fields(int type, int *gen_bp_type) /* * Validate the arch-specific HW Breakpoint register settings */ -int arch_validate_hwbkpt_settings(struct perf_event *bp) +int hw_breakpoint_arch_parse(struct perf_event *bp, + const struct perf_event_attr *attr, + struct arch_hw_breakpoint *hw) { int ret = -EINVAL, length_max; - struct arch_hw_breakpoint *info = counter_arch_bp(bp); if (!bp) return ret; - info->type = HW_BRK_TYPE_TRANSLATE; - if (bp->attr.bp_type & HW_BREAKPOINT_R) - info->type |= HW_BRK_TYPE_READ; - if (bp->attr.bp_type & HW_BREAKPOINT_W) - info->type |= HW_BRK_TYPE_WRITE; - if (info->type == HW_BRK_TYPE_TRANSLATE) + hw->type = HW_BRK_TYPE_TRANSLATE; + if (attr->bp_type & HW_BREAKPOINT_R) + hw->type |= HW_BRK_TYPE_READ; + if (attr->bp_type & HW_BREAKPOINT_W) + hw->type |= HW_BRK_TYPE_WRITE; + if (hw->type == HW_BRK_TYPE_TRANSLATE) /* must set alteast read or write */ return ret; - if (!(bp->attr.exclude_user)) - info->type |= HW_BRK_TYPE_USER; - if (!(bp->attr.exclude_kernel)) - info->type |= HW_BRK_TYPE_KERNEL; - if (!(bp->attr.exclude_hv)) - info->type |= HW_BRK_TYPE_HYP; - info->address = bp->attr.bp_addr; - info->len = bp->attr.bp_len; + if (!attr->exclude_user) + hw->type |= HW_BRK_TYPE_USER; + if (!attr->exclude_kernel) + hw->type |= HW_BRK_TYPE_KERNEL; + if (!attr->exclude_hv) + hw->type |= HW_BRK_TYPE_HYP; + hw->address = attr->bp_addr; + hw->len = attr->bp_len; /* * Since breakpoint length can be a maximum of HW_BREAKPOINT_LEN(8) @@ -178,12 +177,12 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp) if (cpu_has_feature(CPU_FTR_DAWR)) { length_max = 512 ; /* 64 doublewords */ /* DAWR region can't cross 512 boundary */ - if ((bp->attr.bp_addr >> 9) != - ((bp->attr.bp_addr + bp->attr.bp_len - 1) >> 9)) + if ((attr->bp_addr >> 9) != + ((attr->bp_addr + attr->bp_len - 1) >> 9)) return -EINVAL; } - if (info->len > - (length_max - (info->address & HW_BREAKPOINT_ALIGN))) + if (hw->len > + (length_max - (hw->address & HW_BREAKPOINT_ALIGN))) return -EINVAL; return 0; } diff --git a/arch/powerpc/kernel/kprobes-ftrace.c b/arch/powerpc/kernel/kprobes-ftrace.c index 7a1f99f1b47f..e4a49c051325 100644 --- a/arch/powerpc/kernel/kprobes-ftrace.c +++ b/arch/powerpc/kernel/kprobes-ftrace.c @@ -25,50 +25,6 @@ #include <linux/preempt.h> #include <linux/ftrace.h> -/* - * This is called from ftrace code after invoking registered handlers to - * disambiguate regs->nip changes done by jprobes and livepatch. We check if - * there is an active jprobe at the provided address (mcount location). - */ -int __is_active_jprobe(unsigned long addr) -{ - if (!preemptible()) { - struct kprobe *p = raw_cpu_read(current_kprobe); - return (p && (unsigned long)p->addr == addr) ? 1 : 0; - } - - return 0; -} - -static nokprobe_inline -int __skip_singlestep(struct kprobe *p, struct pt_regs *regs, - struct kprobe_ctlblk *kcb, unsigned long orig_nip) -{ - /* - * Emulate singlestep (and also recover regs->nip) - * as if there is a nop - */ - regs->nip = (unsigned long)p->addr + MCOUNT_INSN_SIZE; - if (unlikely(p->post_handler)) { - kcb->kprobe_status = KPROBE_HIT_SSDONE; - p->post_handler(p, regs, 0); - } - __this_cpu_write(current_kprobe, NULL); - if (orig_nip) - regs->nip = orig_nip; - return 1; -} - -int skip_singlestep(struct kprobe *p, struct pt_regs *regs, - struct kprobe_ctlblk *kcb) -{ - if (kprobe_ftrace(p)) - return __skip_singlestep(p, regs, kcb, 0); - else - return 0; -} -NOKPROBE_SYMBOL(skip_singlestep); - /* Ftrace callback handler for kprobes */ void kprobe_ftrace_handler(unsigned long nip, unsigned long parent_nip, struct ftrace_ops *ops, struct pt_regs *regs) @@ -76,18 +32,14 @@ void kprobe_ftrace_handler(unsigned long nip, unsigned long parent_nip, struct kprobe *p; struct kprobe_ctlblk *kcb; - preempt_disable(); - p = get_kprobe((kprobe_opcode_t *)nip); if (unlikely(!p) || kprobe_disabled(p)) - goto end; + return; kcb = get_kprobe_ctlblk(); if (kprobe_running()) { kprobes_inc_nmissed_count(p); } else { - unsigned long orig_nip = regs->nip; - /* * On powerpc, NIP is *before* this instruction for the * pre handler @@ -96,19 +48,23 @@ void kprobe_ftrace_handler(unsigned long nip, unsigned long parent_nip, __this_cpu_write(current_kprobe, p); kcb->kprobe_status = KPROBE_HIT_ACTIVE; - if (!p->pre_handler || !p->pre_handler(p, regs)) - __skip_singlestep(p, regs, kcb, orig_nip); - else { + if (!p->pre_handler || !p->pre_handler(p, regs)) { /* - * If pre_handler returns !0, it sets regs->nip and - * resets current kprobe. In this case, we should not - * re-enable preemption. + * Emulate singlestep (and also recover regs->nip) + * as if there is a nop */ - return; + regs->nip += MCOUNT_INSN_SIZE; + if (unlikely(p->post_handler)) { + kcb->kprobe_status = KPROBE_HIT_SSDONE; + p->post_handler(p, regs, 0); + } } + /* + * If pre_handler returns !0, it changes regs->nip. We have to + * skip emulating post_handler. + */ + __this_cpu_write(current_kprobe, NULL); } -end: - preempt_enable_no_resched(); } NOKPROBE_SYMBOL(kprobe_ftrace_handler); diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c index e4c5bf33970b..5c60bb0f927f 100644 --- a/arch/powerpc/kernel/kprobes.c +++ b/arch/powerpc/kernel/kprobes.c @@ -317,25 +317,17 @@ int kprobe_handler(struct pt_regs *regs) } prepare_singlestep(p, regs); return 1; - } else { - if (*addr != BREAKPOINT_INSTRUCTION) { - /* If trap variant, then it belongs not to us */ - kprobe_opcode_t cur_insn = *addr; - if (is_trap(cur_insn)) - goto no_kprobe; - /* The breakpoint instruction was removed by - * another cpu right after we hit, no further - * handling of this interrupt is appropriate - */ - ret = 1; + } else if (*addr != BREAKPOINT_INSTRUCTION) { + /* If trap variant, then it belongs not to us */ + kprobe_opcode_t cur_insn = *addr; + + if (is_trap(cur_insn)) goto no_kprobe; - } - p = __this_cpu_read(current_kprobe); - if (p->break_handler && p->break_handler(p, regs)) { - if (!skip_singlestep(p, regs, kcb)) - goto ss_probe; - ret = 1; - } + /* The breakpoint instruction was removed by + * another cpu right after we hit, no further + * handling of this interrupt is appropriate + */ + ret = 1; } goto no_kprobe; } @@ -350,7 +342,7 @@ int kprobe_handler(struct pt_regs *regs) */ kprobe_opcode_t cur_insn = *addr; if (is_trap(cur_insn)) - goto no_kprobe; + goto no_kprobe; /* * The breakpoint instruction was removed right * after we hit it. Another cpu has removed @@ -366,11 +358,13 @@ int kprobe_handler(struct pt_regs *regs) kcb->kprobe_status = KPROBE_HIT_ACTIVE; set_current_kprobe(p, regs, kcb); - if (p->pre_handler && p->pre_handler(p, regs)) - /* handler has already set things up, so skip ss setup */ + if (p->pre_handler && p->pre_handler(p, regs)) { + /* handler changed execution path, so skip ss setup */ + reset_current_kprobe(); + preempt_enable_no_resched(); return 1; + } -ss_probe: if (p->ainsn.boostable >= 0) { ret = try_to_emulate(p, regs); @@ -611,60 +605,6 @@ unsigned long arch_deref_entry_point(void *entry) } NOKPROBE_SYMBOL(arch_deref_entry_point); -int setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs) -{ - struct jprobe *jp = container_of(p, struct jprobe, kp); - struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - - memcpy(&kcb->jprobe_saved_regs, regs, sizeof(struct pt_regs)); - - /* setup return addr to the jprobe handler routine */ - regs->nip = arch_deref_entry_point(jp->entry); -#ifdef PPC64_ELF_ABI_v2 - regs->gpr[12] = (unsigned long)jp->entry; -#elif defined(PPC64_ELF_ABI_v1) - regs->gpr[2] = (unsigned long)(((func_descr_t *)jp->entry)->toc); -#endif - - /* - * jprobes use jprobe_return() which skips the normal return - * path of the function, and this messes up the accounting of the - * function graph tracer. - * - * Pause function graph tracing while performing the jprobe function. - */ - pause_graph_tracing(); - - return 1; -} -NOKPROBE_SYMBOL(setjmp_pre_handler); - -void __used jprobe_return(void) -{ - asm volatile("jprobe_return_trap:\n" - "trap\n" - ::: "memory"); -} -NOKPROBE_SYMBOL(jprobe_return); - -int longjmp_break_handler(struct kprobe *p, struct pt_regs *regs) -{ - struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - - if (regs->nip != ppc_kallsyms_lookup_name("jprobe_return_trap")) { - pr_debug("longjmp_break_handler NIP (0x%lx) does not match jprobe_return_trap (0x%lx)\n", - regs->nip, ppc_kallsyms_lookup_name("jprobe_return_trap")); - return 0; - } - - memcpy(regs, &kcb->jprobe_saved_regs, sizeof(struct pt_regs)); - /* It's OK to start function graph tracing again */ - unpause_graph_tracing(); - preempt_enable_no_resched(); - return 1; -} -NOKPROBE_SYMBOL(longjmp_break_handler); - static struct kprobe trampoline_p = { .addr = (kprobe_opcode_t *) &kretprobe_trampoline, .pre_handler = trampoline_probe_handler diff --git a/arch/powerpc/kernel/trace/ftrace_64_mprofile.S b/arch/powerpc/kernel/trace/ftrace_64_mprofile.S index 9a5b5a513604..32476a6e4e9c 100644 --- a/arch/powerpc/kernel/trace/ftrace_64_mprofile.S +++ b/arch/powerpc/kernel/trace/ftrace_64_mprofile.S @@ -104,39 +104,13 @@ ftrace_regs_call: bl ftrace_stub nop - /* Load the possibly modified NIP */ - ld r15, _NIP(r1) - + /* Load ctr with the possibly modified NIP */ + ld r3, _NIP(r1) + mtctr r3 #ifdef CONFIG_LIVEPATCH - cmpd r14, r15 /* has NIP been altered? */ + cmpd r14, r3 /* has NIP been altered? */ #endif -#if defined(CONFIG_LIVEPATCH) && defined(CONFIG_KPROBES_ON_FTRACE) - /* NIP has not been altered, skip over further checks */ - beq 1f - - /* Check if there is an active jprobe on us */ - subi r3, r14, 4 - bl __is_active_jprobe - nop - - /* - * If r3 == 1, then this is a kprobe/jprobe. - * else, this is livepatched function. - * - * The conditional branch for livepatch_handler below will use the - * result of this comparison. For kprobe/jprobe, we just need to branch to - * the new NIP, not call livepatch_handler. The branch below is bne, so we - * want CR0[EQ] to be true if this is a kprobe/jprobe. Which means we want - * CR0[EQ] = (r3 == 1). - */ - cmpdi r3, 1 -1: -#endif - - /* Load CTR with the possibly modified NIP */ - mtctr r15 - /* Restore gprs */ REST_GPR(0,r1) REST_10GPRS(2,r1) @@ -154,10 +128,7 @@ ftrace_regs_call: addi r1, r1, SWITCH_FRAME_SIZE #ifdef CONFIG_LIVEPATCH - /* - * Based on the cmpd or cmpdi above, if the NIP was altered and we're - * not on a kprobe/jprobe, then handle livepatch. - */ + /* Based on the cmpd above, if the NIP was altered handle livepatch */ bne- livepatch_handler #endif diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index de686b340f4a..ee4a8854985e 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -216,7 +216,7 @@ static void kvmppc_fast_vcpu_kick_hv(struct kvm_vcpu *vcpu) wqp = kvm_arch_vcpu_wq(vcpu); if (swq_has_sleeper(wqp)) { - swake_up(wqp); + swake_up_one(wqp); ++vcpu->stat.halt_wakeup; } @@ -3188,7 +3188,7 @@ static void kvmppc_vcore_blocked(struct kvmppc_vcore *vc) } } - prepare_to_swait(&vc->wq, &wait, TASK_INTERRUPTIBLE); + prepare_to_swait_exclusive(&vc->wq, &wait, TASK_INTERRUPTIBLE); if (kvmppc_vcore_check_block(vc)) { finish_swait(&vc->wq, &wait); @@ -3311,7 +3311,7 @@ static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) kvmppc_start_thread(vcpu, vc); trace_kvm_guest_enter(vcpu); } else if (vc->vcore_state == VCORE_SLEEPING) { - swake_up(&vc->wq); + swake_up_one(&vc->wq); } } diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c index 3f66fcf8ad99..19d8ab49d1bd 100644 --- a/arch/powerpc/perf/core-book3s.c +++ b/arch/powerpc/perf/core-book3s.c @@ -1469,7 +1469,7 @@ static int collect_events(struct perf_event *group, int max_count, } /* - * Add a event to the PMU. + * Add an event to the PMU. * If all events are not already frozen, then we disable and * re-enable the PMU in order to get hw_perf_enable to do the * actual work of reconfiguring the PMU. @@ -1548,7 +1548,7 @@ nocheck: } /* - * Remove a event from the PMU. + * Remove an event from the PMU. */ static void power_pmu_del(struct perf_event *event, int ef_flags) { @@ -1742,7 +1742,7 @@ static int power_pmu_commit_txn(struct pmu *pmu) /* * Return 1 if we might be able to put event on a limited PMC, * or 0 if not. - * A event can only go on a limited PMC if it counts something + * An event can only go on a limited PMC if it counts something * that a limited PMC can count, doesn't require interrupts, and * doesn't exclude any processor mode. */ diff --git a/arch/riscv/include/asm/atomic.h b/arch/riscv/include/asm/atomic.h index 855115ace98c..c452359c9cb8 100644 --- a/arch/riscv/include/asm/atomic.h +++ b/arch/riscv/include/asm/atomic.h @@ -25,18 +25,11 @@ #define ATOMIC_INIT(i) { (i) } -#define __atomic_op_acquire(op, args...) \ -({ \ - typeof(op##_relaxed(args)) __ret = op##_relaxed(args); \ - __asm__ __volatile__(RISCV_ACQUIRE_BARRIER "" ::: "memory"); \ - __ret; \ -}) - -#define __atomic_op_release(op, args...) \ -({ \ - __asm__ __volatile__(RISCV_RELEASE_BARRIER "" ::: "memory"); \ - op##_relaxed(args); \ -}) +#define __atomic_acquire_fence() \ + __asm__ __volatile__(RISCV_ACQUIRE_BARRIER "" ::: "memory") + +#define __atomic_release_fence() \ + __asm__ __volatile__(RISCV_RELEASE_BARRIER "" ::: "memory"); static __always_inline int atomic_read(const atomic_t *v) { @@ -209,130 +202,8 @@ ATOMIC_OPS(xor, xor, i) #undef ATOMIC_FETCH_OP #undef ATOMIC_OP_RETURN -/* - * The extra atomic operations that are constructed from one of the core - * AMO-based operations above (aside from sub, which is easier to fit above). - * These are required to perform a full barrier, but they're OK this way - * because atomic_*_return is also required to perform a full barrier. - * - */ -#define ATOMIC_OP(op, func_op, comp_op, I, c_type, prefix) \ -static __always_inline \ -bool atomic##prefix##_##op(c_type i, atomic##prefix##_t *v) \ -{ \ - return atomic##prefix##_##func_op##_return(i, v) comp_op I; \ -} - -#ifdef CONFIG_GENERIC_ATOMIC64 -#define ATOMIC_OPS(op, func_op, comp_op, I) \ - ATOMIC_OP(op, func_op, comp_op, I, int, ) -#else -#define ATOMIC_OPS(op, func_op, comp_op, I) \ - ATOMIC_OP(op, func_op, comp_op, I, int, ) \ - ATOMIC_OP(op, func_op, comp_op, I, long, 64) -#endif - -ATOMIC_OPS(add_and_test, add, ==, 0) -ATOMIC_OPS(sub_and_test, sub, ==, 0) -ATOMIC_OPS(add_negative, add, <, 0) - -#undef ATOMIC_OP -#undef ATOMIC_OPS - -#define ATOMIC_OP(op, func_op, I, c_type, prefix) \ -static __always_inline \ -void atomic##prefix##_##op(atomic##prefix##_t *v) \ -{ \ - atomic##prefix##_##func_op(I, v); \ -} - -#define ATOMIC_FETCH_OP(op, func_op, I, c_type, prefix) \ -static __always_inline \ -c_type atomic##prefix##_fetch_##op##_relaxed(atomic##prefix##_t *v) \ -{ \ - return atomic##prefix##_fetch_##func_op##_relaxed(I, v); \ -} \ -static __always_inline \ -c_type atomic##prefix##_fetch_##op(atomic##prefix##_t *v) \ -{ \ - return atomic##prefix##_fetch_##func_op(I, v); \ -} - -#define ATOMIC_OP_RETURN(op, asm_op, c_op, I, c_type, prefix) \ -static __always_inline \ -c_type atomic##prefix##_##op##_return_relaxed(atomic##prefix##_t *v) \ -{ \ - return atomic##prefix##_fetch_##op##_relaxed(v) c_op I; \ -} \ -static __always_inline \ -c_type atomic##prefix##_##op##_return(atomic##prefix##_t *v) \ -{ \ - return atomic##prefix##_fetch_##op(v) c_op I; \ -} - -#ifdef CONFIG_GENERIC_ATOMIC64 -#define ATOMIC_OPS(op, asm_op, c_op, I) \ - ATOMIC_OP( op, asm_op, I, int, ) \ - ATOMIC_FETCH_OP( op, asm_op, I, int, ) \ - ATOMIC_OP_RETURN(op, asm_op, c_op, I, int, ) -#else -#define ATOMIC_OPS(op, asm_op, c_op, I) \ - ATOMIC_OP( op, asm_op, I, int, ) \ - ATOMIC_FETCH_OP( op, asm_op, I, int, ) \ - ATOMIC_OP_RETURN(op, asm_op, c_op, I, int, ) \ - ATOMIC_OP( op, asm_op, I, long, 64) \ - ATOMIC_FETCH_OP( op, asm_op, I, long, 64) \ - ATOMIC_OP_RETURN(op, asm_op, c_op, I, long, 64) -#endif - -ATOMIC_OPS(inc, add, +, 1) -ATOMIC_OPS(dec, add, +, -1) - -#define atomic_inc_return_relaxed atomic_inc_return_relaxed -#define atomic_dec_return_relaxed atomic_dec_return_relaxed -#define atomic_inc_return atomic_inc_return -#define atomic_dec_return atomic_dec_return - -#define atomic_fetch_inc_relaxed atomic_fetch_inc_relaxed -#define atomic_fetch_dec_relaxed atomic_fetch_dec_relaxed -#define atomic_fetch_inc atomic_fetch_inc -#define atomic_fetch_dec atomic_fetch_dec - -#ifndef CONFIG_GENERIC_ATOMIC64 -#define atomic64_inc_return_relaxed atomic64_inc_return_relaxed -#define atomic64_dec_return_relaxed atomic64_dec_return_relaxed -#define atomic64_inc_return atomic64_inc_return -#define atomic64_dec_return atomic64_dec_return - -#define atomic64_fetch_inc_relaxed atomic64_fetch_inc_relaxed -#define atomic64_fetch_dec_relaxed atomic64_fetch_dec_relaxed -#define atomic64_fetch_inc atomic64_fetch_inc -#define atomic64_fetch_dec atomic64_fetch_dec -#endif - -#undef ATOMIC_OPS -#undef ATOMIC_OP -#undef ATOMIC_FETCH_OP -#undef ATOMIC_OP_RETURN - -#define ATOMIC_OP(op, func_op, comp_op, I, prefix) \ -static __always_inline \ -bool atomic##prefix##_##op(atomic##prefix##_t *v) \ -{ \ - return atomic##prefix##_##func_op##_return(v) comp_op I; \ -} - -ATOMIC_OP(inc_and_test, inc, ==, 0, ) -ATOMIC_OP(dec_and_test, dec, ==, 0, ) -#ifndef CONFIG_GENERIC_ATOMIC64 -ATOMIC_OP(inc_and_test, inc, ==, 0, 64) -ATOMIC_OP(dec_and_test, dec, ==, 0, 64) -#endif - -#undef ATOMIC_OP - /* This is required to provide a full barrier on success. */ -static __always_inline int __atomic_add_unless(atomic_t *v, int a, int u) +static __always_inline int atomic_fetch_add_unless(atomic_t *v, int a, int u) { int prev, rc; @@ -349,9 +220,10 @@ static __always_inline int __atomic_add_unless(atomic_t *v, int a, int u) : "memory"); return prev; } +#define atomic_fetch_add_unless atomic_fetch_add_unless #ifndef CONFIG_GENERIC_ATOMIC64 -static __always_inline long __atomic64_add_unless(atomic64_t *v, long a, long u) +static __always_inline long atomic64_fetch_add_unless(atomic64_t *v, long a, long u) { long prev, rc; @@ -368,27 +240,7 @@ static __always_inline long __atomic64_add_unless(atomic64_t *v, long a, long u) : "memory"); return prev; } - -static __always_inline int atomic64_add_unless(atomic64_t *v, long a, long u) -{ - return __atomic64_add_unless(v, a, u) != u; -} -#endif - -/* - * The extra atomic operations that are constructed from one of the core - * LR/SC-based operations above. - */ -static __always_inline int atomic_inc_not_zero(atomic_t *v) -{ - return __atomic_add_unless(v, 1, 0); -} - -#ifndef CONFIG_GENERIC_ATOMIC64 -static __always_inline long atomic64_inc_not_zero(atomic64_t *v) -{ - return atomic64_add_unless(v, 1, 0); -} +#define atomic64_fetch_add_unless atomic64_fetch_add_unless #endif /* diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index 8a1863d9ed53..4fe5b2affa23 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -106,7 +106,6 @@ config S390 select ARCH_USE_BUILTIN_BSWAP select ARCH_USE_CMPXCHG_LOCKREF select ARCH_WANTS_DYNAMIC_TASK_STRUCT - select ARCH_WANTS_UBSAN_NO_NULL select ARCH_WANT_IPC_PARSE_VERSION select BUILDTIME_EXTABLE_SORT select CLONE_BACKWARDS2 diff --git a/arch/s390/include/asm/atomic.h b/arch/s390/include/asm/atomic.h index 4b55532f15c4..fd20ab5d4cf7 100644 --- a/arch/s390/include/asm/atomic.h +++ b/arch/s390/include/asm/atomic.h @@ -55,17 +55,9 @@ static inline void atomic_add(int i, atomic_t *v) __atomic_add(i, &v->counter); } -#define atomic_add_negative(_i, _v) (atomic_add_return(_i, _v) < 0) -#define atomic_inc(_v) atomic_add(1, _v) -#define atomic_inc_return(_v) atomic_add_return(1, _v) -#define atomic_inc_and_test(_v) (atomic_add_return(1, _v) == 0) #define atomic_sub(_i, _v) atomic_add(-(int)(_i), _v) #define atomic_sub_return(_i, _v) atomic_add_return(-(int)(_i), _v) #define atomic_fetch_sub(_i, _v) atomic_fetch_add(-(int)(_i), _v) -#define atomic_sub_and_test(_i, _v) (atomic_sub_return(_i, _v) == 0) -#define atomic_dec(_v) atomic_sub(1, _v) -#define atomic_dec_return(_v) atomic_sub_return(1, _v) -#define atomic_dec_and_test(_v) (atomic_sub_return(1, _v) == 0) #define ATOMIC_OPS(op) \ static inline void atomic_##op(int i, atomic_t *v) \ @@ -90,21 +82,6 @@ static inline int atomic_cmpxchg(atomic_t *v, int old, int new) return __atomic_cmpxchg(&v->counter, old, new); } -static inline int __atomic_add_unless(atomic_t *v, int a, int u) -{ - int c, old; - c = atomic_read(v); - for (;;) { - if (unlikely(c == u)) - break; - old = atomic_cmpxchg(v, c, c + a); - if (likely(old == c)) - break; - c = old; - } - return c; -} - #define ATOMIC64_INIT(i) { (i) } static inline long atomic64_read(const atomic64_t *v) @@ -168,50 +145,8 @@ ATOMIC64_OPS(xor) #undef ATOMIC64_OPS -static inline int atomic64_add_unless(atomic64_t *v, long i, long u) -{ - long c, old; - - c = atomic64_read(v); - for (;;) { - if (unlikely(c == u)) - break; - old = atomic64_cmpxchg(v, c, c + i); - if (likely(old == c)) - break; - c = old; - } - return c != u; -} - -static inline long atomic64_dec_if_positive(atomic64_t *v) -{ - long c, old, dec; - - c = atomic64_read(v); - for (;;) { - dec = c - 1; - if (unlikely(dec < 0)) - break; - old = atomic64_cmpxchg((v), c, dec); - if (likely(old == c)) - break; - c = old; - } - return dec; -} - -#define atomic64_add_negative(_i, _v) (atomic64_add_return(_i, _v) < 0) -#define atomic64_inc(_v) atomic64_add(1, _v) -#define atomic64_inc_return(_v) atomic64_add_return(1, _v) -#define atomic64_inc_and_test(_v) (atomic64_add_return(1, _v) == 0) #define atomic64_sub_return(_i, _v) atomic64_add_return(-(long)(_i), _v) #define atomic64_fetch_sub(_i, _v) atomic64_fetch_add(-(long)(_i), _v) #define atomic64_sub(_i, _v) atomic64_add(-(long)(_i), _v) -#define atomic64_sub_and_test(_i, _v) (atomic64_sub_return(_i, _v) == 0) -#define atomic64_dec(_v) atomic64_sub(1, _v) -#define atomic64_dec_return(_v) atomic64_sub_return(1, _v) -#define atomic64_dec_and_test(_v) (atomic64_sub_return(1, _v) == 0) -#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0) #endif /* __ARCH_S390_ATOMIC__ */ diff --git a/arch/s390/include/asm/kprobes.h b/arch/s390/include/asm/kprobes.h index 13de80cf741c..b106aa29bf55 100644 --- a/arch/s390/include/asm/kprobes.h +++ b/arch/s390/include/asm/kprobes.h @@ -68,8 +68,6 @@ struct kprobe_ctlblk { unsigned long kprobe_saved_imask; unsigned long kprobe_saved_ctl[3]; struct prev_kprobe prev_kprobe; - struct pt_regs jprobe_saved_regs; - kprobe_opcode_t jprobes_stack[MAX_STACK_SIZE]; }; void arch_remove_kprobe(struct kprobe *p); diff --git a/arch/s390/kernel/kprobes.c b/arch/s390/kernel/kprobes.c index 60f60afa645c..7c0a095e9c5f 100644 --- a/arch/s390/kernel/kprobes.c +++ b/arch/s390/kernel/kprobes.c @@ -321,38 +321,20 @@ static int kprobe_handler(struct pt_regs *regs) * If we have no pre-handler or it returned 0, we * continue with single stepping. If we have a * pre-handler and it returned non-zero, it prepped - * for calling the break_handler below on re-entry - * for jprobe processing, so get out doing nothing - * more here. + * for changing execution path, so get out doing + * nothing more here. */ push_kprobe(kcb, p); kcb->kprobe_status = KPROBE_HIT_ACTIVE; - if (p->pre_handler && p->pre_handler(p, regs)) + if (p->pre_handler && p->pre_handler(p, regs)) { + pop_kprobe(kcb); + preempt_enable_no_resched(); return 1; + } kcb->kprobe_status = KPROBE_HIT_SS; } enable_singlestep(kcb, regs, (unsigned long) p->ainsn.insn); return 1; - } else if (kprobe_running()) { - p = __this_cpu_read(current_kprobe); - if (p->break_handler && p->break_handler(p, regs)) { - /* - * Continuation after the jprobe completed and - * caused the jprobe_return trap. The jprobe - * break_handler "returns" to the original - * function that still has the kprobe breakpoint - * installed. We continue with single stepping. - */ - kcb->kprobe_status = KPROBE_HIT_SS; - enable_singlestep(kcb, regs, - (unsigned long) p->ainsn.insn); - return 1; - } /* else: - * No kprobe at this address and the current kprobe - * has no break handler (no jprobe!). The kernel just - * exploded, let the standard trap handler pick up the - * pieces. - */ } /* else: * No kprobe at this address and no active kprobe. The trap has * not been caused by a kprobe breakpoint. The race of breakpoint @@ -452,9 +434,7 @@ static int trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs) regs->psw.addr = orig_ret_address; - pop_kprobe(get_kprobe_ctlblk()); kretprobe_hash_unlock(current, &flags); - preempt_enable_no_resched(); hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) { hlist_del(&ri->hlist); @@ -661,60 +641,6 @@ int kprobe_exceptions_notify(struct notifier_block *self, } NOKPROBE_SYMBOL(kprobe_exceptions_notify); -int setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs) -{ - struct jprobe *jp = container_of(p, struct jprobe, kp); - struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - unsigned long stack; - - memcpy(&kcb->jprobe_saved_regs, regs, sizeof(struct pt_regs)); - - /* setup return addr to the jprobe handler routine */ - regs->psw.addr = (unsigned long) jp->entry; - regs->psw.mask &= ~(PSW_MASK_IO | PSW_MASK_EXT); - - /* r15 is the stack pointer */ - stack = (unsigned long) regs->gprs[15]; - - memcpy(kcb->jprobes_stack, (void *) stack, MIN_STACK_SIZE(stack)); - - /* - * jprobes use jprobe_return() which skips the normal return - * path of the function, and this messes up the accounting of the - * function graph tracer to get messed up. - * - * Pause function graph tracing while performing the jprobe function. - */ - pause_graph_tracing(); - return 1; -} -NOKPROBE_SYMBOL(setjmp_pre_handler); - -void jprobe_return(void) -{ - asm volatile(".word 0x0002"); -} -NOKPROBE_SYMBOL(jprobe_return); - -int longjmp_break_handler(struct kprobe *p, struct pt_regs *regs) -{ - struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - unsigned long stack; - - /* It's OK to start function graph tracing again */ - unpause_graph_tracing(); - - stack = (unsigned long) kcb->jprobe_saved_regs.gprs[15]; - - /* Put the regs back */ - memcpy(regs, &kcb->jprobe_saved_regs, sizeof(struct pt_regs)); - /* put the stack back */ - memcpy((void *) stack, kcb->jprobes_stack, MIN_STACK_SIZE(stack)); - preempt_enable_no_resched(); - return 1; -} -NOKPROBE_SYMBOL(longjmp_break_handler); - static struct kprobe trampoline = { .addr = (kprobe_opcode_t *) &kretprobe_trampoline, .pre_handler = trampoline_probe_handler diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index daa09f89ca2d..fcb55b02990e 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -1145,7 +1145,7 @@ void kvm_s390_vcpu_wakeup(struct kvm_vcpu *vcpu) * yield-candidate. */ vcpu->preempted = true; - swake_up(&vcpu->wq); + swake_up_one(&vcpu->wq); vcpu->stat.halt_wakeup++; } /* diff --git a/arch/sh/include/asm/atomic.h b/arch/sh/include/asm/atomic.h index 0fd0099f43cc..f37b95a80232 100644 --- a/arch/sh/include/asm/atomic.h +++ b/arch/sh/include/asm/atomic.h @@ -32,44 +32,9 @@ #include <asm/atomic-irq.h> #endif -#define atomic_add_negative(a, v) (atomic_add_return((a), (v)) < 0) -#define atomic_dec_return(v) atomic_sub_return(1, (v)) -#define atomic_inc_return(v) atomic_add_return(1, (v)) -#define atomic_inc_and_test(v) (atomic_inc_return(v) == 0) -#define atomic_sub_and_test(i,v) (atomic_sub_return((i), (v)) == 0) -#define atomic_dec_and_test(v) (atomic_sub_return(1, (v)) == 0) - -#define atomic_inc(v) atomic_add(1, (v)) -#define atomic_dec(v) atomic_sub(1, (v)) - #define atomic_xchg(v, new) (xchg(&((v)->counter), new)) #define atomic_cmpxchg(v, o, n) (cmpxchg(&((v)->counter), (o), (n))) -/** - * __atomic_add_unless - add unless the number is a given value - * @v: pointer of type atomic_t - * @a: the amount to add to v... - * @u: ...unless v is equal to u. - * - * Atomically adds @a to @v, so long as it was not @u. - * Returns the old value of @v. - */ -static inline int __atomic_add_unless(atomic_t *v, int a, int u) -{ - int c, old; - c = atomic_read(v); - for (;;) { - if (unlikely(c == (u))) - break; - old = atomic_cmpxchg((v), c, c + (a)); - if (likely(old == c)) - break; - c = old; - } - - return c; -} - #endif /* CONFIG_CPU_J2 */ #endif /* __ASM_SH_ATOMIC_H */ diff --git a/arch/sh/include/asm/cmpxchg-xchg.h b/arch/sh/include/asm/cmpxchg-xchg.h index 1e881f5db659..593a9704782b 100644 --- a/arch/sh/include/asm/cmpxchg-xchg.h +++ b/arch/sh/include/asm/cmpxchg-xchg.h @@ -8,7 +8,8 @@ * This work is licensed under the terms of the GNU GPL, version 2. See the * file "COPYING" in the main directory of this archive for more details. */ -#include <linux/bitops.h> +#include <linux/bits.h> +#include <linux/compiler.h> #include <asm/byteorder.h> /* diff --git a/arch/sh/include/asm/hw_breakpoint.h b/arch/sh/include/asm/hw_breakpoint.h index 7431c172c0cb..199d17b765f2 100644 --- a/arch/sh/include/asm/hw_breakpoint.h +++ b/arch/sh/include/asm/hw_breakpoint.h @@ -10,7 +10,6 @@ #include <linux/types.h> struct arch_hw_breakpoint { - char *name; /* Contains name of the symbol to set bkpt */ unsigned long address; u16 len; u16 type; @@ -41,6 +40,7 @@ struct sh_ubc { struct clk *clk; /* optional interface clock / MSTP bit */ }; +struct perf_event_attr; struct perf_event; struct task_struct; struct pmu; @@ -54,8 +54,10 @@ static inline int hw_breakpoint_slots(int type) } /* arch/sh/kernel/hw_breakpoint.c */ -extern int arch_check_bp_in_kernelspace(struct perf_event *bp); -extern int arch_validate_hwbkpt_settings(struct perf_event *bp); +extern int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw); +extern int hw_breakpoint_arch_parse(struct perf_event *bp, + const struct perf_event_attr *attr, + struct arch_hw_breakpoint *hw); extern int hw_breakpoint_exceptions_notify(struct notifier_block *unused, unsigned long val, void *data); diff --git a/arch/sh/include/asm/kprobes.h b/arch/sh/include/asm/kprobes.h index 85d8bcaa8493..6171682f7798 100644 --- a/arch/sh/include/asm/kprobes.h +++ b/arch/sh/include/asm/kprobes.h @@ -27,7 +27,6 @@ struct kprobe; void arch_remove_kprobe(struct kprobe *); void kretprobe_trampoline(void); -void jprobe_return_end(void); /* Architecture specific copy of original instruction*/ struct arch_specific_insn { @@ -43,9 +42,6 @@ struct prev_kprobe { /* per-cpu kprobe control block */ struct kprobe_ctlblk { unsigned long kprobe_status; - unsigned long jprobe_saved_r15; - struct pt_regs jprobe_saved_regs; - kprobe_opcode_t jprobes_stack[MAX_STACK_SIZE]; struct prev_kprobe prev_kprobe; }; diff --git a/arch/sh/kernel/hw_breakpoint.c b/arch/sh/kernel/hw_breakpoint.c index 8648ed05ccf0..d9ff3b42da7c 100644 --- a/arch/sh/kernel/hw_breakpoint.c +++ b/arch/sh/kernel/hw_breakpoint.c @@ -124,14 +124,13 @@ static int get_hbp_len(u16 hbp_len) /* * Check for virtual address in kernel space. */ -int arch_check_bp_in_kernelspace(struct perf_event *bp) +int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw) { unsigned int len; unsigned long va; - struct arch_hw_breakpoint *info = counter_arch_bp(bp); - va = info->address; - len = get_hbp_len(info->len); + va = hw->address; + len = get_hbp_len(hw->len); return (va >= TASK_SIZE) && ((va + len - 1) >= TASK_SIZE); } @@ -174,40 +173,40 @@ int arch_bp_generic_fields(int sh_len, int sh_type, return 0; } -static int arch_build_bp_info(struct perf_event *bp) +static int arch_build_bp_info(struct perf_event *bp, + const struct perf_event_attr *attr, + struct arch_hw_breakpoint *hw) { - struct arch_hw_breakpoint *info = counter_arch_bp(bp); - - info->address = bp->attr.bp_addr; + hw->address = attr->bp_addr; /* Len */ - switch (bp->attr.bp_len) { + switch (attr->bp_len) { case HW_BREAKPOINT_LEN_1: - info->len = SH_BREAKPOINT_LEN_1; + hw->len = SH_BREAKPOINT_LEN_1; break; case HW_BREAKPOINT_LEN_2: - info->len = SH_BREAKPOINT_LEN_2; + hw->len = SH_BREAKPOINT_LEN_2; break; case HW_BREAKPOINT_LEN_4: - info->len = SH_BREAKPOINT_LEN_4; + hw->len = SH_BREAKPOINT_LEN_4; break; case HW_BREAKPOINT_LEN_8: - info->len = SH_BREAKPOINT_LEN_8; + hw->len = SH_BREAKPOINT_LEN_8; break; default: return -EINVAL; } /* Type */ - switch (bp->attr.bp_type) { + switch (attr->bp_type) { case HW_BREAKPOINT_R: - info->type = SH_BREAKPOINT_READ; + hw->type = SH_BREAKPOINT_READ; break; case HW_BREAKPOINT_W: - info->type = SH_BREAKPOINT_WRITE; + hw->type = SH_BREAKPOINT_WRITE; break; case HW_BREAKPOINT_W | HW_BREAKPOINT_R: - info->type = SH_BREAKPOINT_RW; + hw->type = SH_BREAKPOINT_RW; break; default: return -EINVAL; @@ -219,19 +218,20 @@ static int arch_build_bp_info(struct perf_event *bp) /* * Validate the arch-specific HW Breakpoint register settings */ -int arch_validate_hwbkpt_settings(struct perf_event *bp) +int hw_breakpoint_arch_parse(struct perf_event *bp, + const struct perf_event_attr *attr, + struct arch_hw_breakpoint *hw) { - struct arch_hw_breakpoint *info = counter_arch_bp(bp); unsigned int align; int ret; - ret = arch_build_bp_info(bp); + ret = arch_build_bp_info(bp, attr, hw); if (ret) return ret; ret = -EINVAL; - switch (info->len) { + switch (hw->len) { case SH_BREAKPOINT_LEN_1: align = 0; break; @@ -249,17 +249,10 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp) } /* - * For kernel-addresses, either the address or symbol name can be - * specified. - */ - if (info->name) - info->address = (unsigned long)kallsyms_lookup_name(info->name); - - /* * Check that the low-order bits of the address are appropriate * for the alignment implied by len. */ - if (info->address & align) + if (hw->address & align) return -EINVAL; return 0; @@ -346,7 +339,7 @@ static int __kprobes hw_breakpoint_handler(struct die_args *args) perf_bp_event(bp, args->regs); /* Deliver the signal to userspace */ - if (!arch_check_bp_in_kernelspace(bp)) { + if (!arch_check_bp_in_kernelspace(&bp->hw.info)) { force_sig_fault(SIGTRAP, TRAP_HWBKPT, (void __user *)NULL, current); } diff --git a/arch/sh/kernel/kprobes.c b/arch/sh/kernel/kprobes.c index 52a5e11247d1..241e903dd3ee 100644 --- a/arch/sh/kernel/kprobes.c +++ b/arch/sh/kernel/kprobes.c @@ -248,11 +248,6 @@ static int __kprobes kprobe_handler(struct pt_regs *regs) prepare_singlestep(p, regs); kcb->kprobe_status = KPROBE_REENTER; return 1; - } else { - p = __this_cpu_read(current_kprobe); - if (p->break_handler && p->break_handler(p, regs)) { - goto ss_probe; - } } goto no_kprobe; } @@ -277,11 +272,13 @@ static int __kprobes kprobe_handler(struct pt_regs *regs) set_current_kprobe(p, regs, kcb); kcb->kprobe_status = KPROBE_HIT_ACTIVE; - if (p->pre_handler && p->pre_handler(p, regs)) + if (p->pre_handler && p->pre_handler(p, regs)) { /* handler has already set things up, so skip ss setup */ + reset_current_kprobe(); + preempt_enable_no_resched(); return 1; + } -ss_probe: prepare_singlestep(p, regs); kcb->kprobe_status = KPROBE_HIT_SS; return 1; @@ -358,8 +355,6 @@ int __kprobes trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs) regs->pc = orig_ret_address; kretprobe_hash_unlock(current, &flags); - preempt_enable_no_resched(); - hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) { hlist_del(&ri->hlist); kfree(ri); @@ -508,14 +503,8 @@ int __kprobes kprobe_exceptions_notify(struct notifier_block *self, if (post_kprobe_handler(args->regs)) ret = NOTIFY_STOP; } else { - if (kprobe_handler(args->regs)) { + if (kprobe_handler(args->regs)) ret = NOTIFY_STOP; - } else { - p = __this_cpu_read(current_kprobe); - if (p->break_handler && - p->break_handler(p, args->regs)) - ret = NOTIFY_STOP; - } } } } @@ -523,57 +512,6 @@ int __kprobes kprobe_exceptions_notify(struct notifier_block *self, return ret; } -int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs) -{ - struct jprobe *jp = container_of(p, struct jprobe, kp); - unsigned long addr; - struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - - kcb->jprobe_saved_regs = *regs; - kcb->jprobe_saved_r15 = regs->regs[15]; - addr = kcb->jprobe_saved_r15; - - /* - * TBD: As Linus pointed out, gcc assumes that the callee - * owns the argument space and could overwrite it, e.g. - * tailcall optimization. So, to be absolutely safe - * we also save and restore enough stack bytes to cover - * the argument area. - */ - memcpy(kcb->jprobes_stack, (kprobe_opcode_t *) addr, - MIN_STACK_SIZE(addr)); - - regs->pc = (unsigned long)(jp->entry); - - return 1; -} - -void __kprobes jprobe_return(void) -{ - asm volatile ("trapa #0x3a\n\t" "jprobe_return_end:\n\t" "nop\n\t"); -} - -int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs) -{ - struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - unsigned long stack_addr = kcb->jprobe_saved_r15; - u8 *addr = (u8 *)regs->pc; - - if ((addr >= (u8 *)jprobe_return) && - (addr <= (u8 *)jprobe_return_end)) { - *regs = kcb->jprobe_saved_regs; - - memcpy((kprobe_opcode_t *)stack_addr, kcb->jprobes_stack, - MIN_STACK_SIZE(stack_addr)); - - kcb->kprobe_status = KPROBE_HIT_SS; - preempt_enable_no_resched(); - return 1; - } - - return 0; -} - static struct kprobe trampoline_p = { .addr = (kprobe_opcode_t *)&kretprobe_trampoline, .pre_handler = trampoline_probe_handler diff --git a/arch/sparc/include/asm/atomic_32.h b/arch/sparc/include/asm/atomic_32.h index d13ce517f4b9..94c930f0bc62 100644 --- a/arch/sparc/include/asm/atomic_32.h +++ b/arch/sparc/include/asm/atomic_32.h @@ -27,17 +27,17 @@ int atomic_fetch_or(int, atomic_t *); int atomic_fetch_xor(int, atomic_t *); int atomic_cmpxchg(atomic_t *, int, int); int atomic_xchg(atomic_t *, int); -int __atomic_add_unless(atomic_t *, int, int); +int atomic_fetch_add_unless(atomic_t *, int, int); void atomic_set(atomic_t *, int); +#define atomic_fetch_add_unless atomic_fetch_add_unless + #define atomic_set_release(v, i) atomic_set((v), (i)) #define atomic_read(v) READ_ONCE((v)->counter) #define atomic_add(i, v) ((void)atomic_add_return( (int)(i), (v))) #define atomic_sub(i, v) ((void)atomic_add_return(-(int)(i), (v))) -#define atomic_inc(v) ((void)atomic_add_return( 1, (v))) -#define atomic_dec(v) ((void)atomic_add_return( -1, (v))) #define atomic_and(i, v) ((void)atomic_fetch_and((i), (v))) #define atomic_or(i, v) ((void)atomic_fetch_or((i), (v))) @@ -46,22 +46,4 @@ void atomic_set(atomic_t *, int); #define atomic_sub_return(i, v) (atomic_add_return(-(int)(i), (v))) #define atomic_fetch_sub(i, v) (atomic_fetch_add (-(int)(i), (v))) -#define atomic_inc_return(v) (atomic_add_return( 1, (v))) -#define atomic_dec_return(v) (atomic_add_return( -1, (v))) - -#define atomic_add_negative(a, v) (atomic_add_return((a), (v)) < 0) - -/* - * atomic_inc_and_test - increment and test - * @v: pointer of type atomic_t - * - * Atomically increments @v by 1 - * and returns true if the result is zero, or false for all - * other cases. - */ -#define atomic_inc_and_test(v) (atomic_inc_return(v) == 0) - -#define atomic_dec_and_test(v) (atomic_dec_return(v) == 0) -#define atomic_sub_and_test(i, v) (atomic_sub_return(i, v) == 0) - #endif /* !(__ARCH_SPARC_ATOMIC__) */ diff --git a/arch/sparc/include/asm/atomic_64.h b/arch/sparc/include/asm/atomic_64.h index 28db058d471b..6963482c81d8 100644 --- a/arch/sparc/include/asm/atomic_64.h +++ b/arch/sparc/include/asm/atomic_64.h @@ -50,38 +50,6 @@ ATOMIC_OPS(xor) #undef ATOMIC_OP_RETURN #undef ATOMIC_OP -#define atomic_dec_return(v) atomic_sub_return(1, v) -#define atomic64_dec_return(v) atomic64_sub_return(1, v) - -#define atomic_inc_return(v) atomic_add_return(1, v) -#define atomic64_inc_return(v) atomic64_add_return(1, v) - -/* - * atomic_inc_and_test - increment and test - * @v: pointer of type atomic_t - * - * Atomically increments @v by 1 - * and returns true if the result is zero, or false for all - * other cases. - */ -#define atomic_inc_and_test(v) (atomic_inc_return(v) == 0) -#define atomic64_inc_and_test(v) (atomic64_inc_return(v) == 0) - -#define atomic_sub_and_test(i, v) (atomic_sub_return(i, v) == 0) -#define atomic64_sub_and_test(i, v) (atomic64_sub_return(i, v) == 0) - -#define atomic_dec_and_test(v) (atomic_sub_return(1, v) == 0) -#define atomic64_dec_and_test(v) (atomic64_sub_return(1, v) == 0) - -#define atomic_inc(v) atomic_add(1, v) -#define atomic64_inc(v) atomic64_add(1, v) - -#define atomic_dec(v) atomic_sub(1, v) -#define atomic64_dec(v) atomic64_sub(1, v) - -#define atomic_add_negative(i, v) (atomic_add_return(i, v) < 0) -#define atomic64_add_negative(i, v) (atomic64_add_return(i, v) < 0) - #define atomic_cmpxchg(v, o, n) (cmpxchg(&((v)->counter), (o), (n))) static inline int atomic_xchg(atomic_t *v, int new) @@ -89,42 +57,11 @@ static inline int atomic_xchg(atomic_t *v, int new) return xchg(&v->counter, new); } -static inline int __atomic_add_unless(atomic_t *v, int a, int u) -{ - int c, old; - c = atomic_read(v); - for (;;) { - if (unlikely(c == (u))) - break; - old = atomic_cmpxchg((v), c, c + (a)); - if (likely(old == c)) - break; - c = old; - } - return c; -} - #define atomic64_cmpxchg(v, o, n) \ ((__typeof__((v)->counter))cmpxchg(&((v)->counter), (o), (n))) #define atomic64_xchg(v, new) (xchg(&((v)->counter), new)) -static inline long atomic64_add_unless(atomic64_t *v, long a, long u) -{ - long c, old; - c = atomic64_read(v); - for (;;) { - if (unlikely(c == (u))) - break; - old = atomic64_cmpxchg((v), c, c + (a)); - if (likely(old == c)) - break; - c = old; - } - return c != (u); -} - -#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0) - long atomic64_dec_if_positive(atomic64_t *v); +#define atomic64_dec_if_positive atomic64_dec_if_positive #endif /* !(__ARCH_SPARC64_ATOMIC__) */ diff --git a/arch/sparc/include/asm/kprobes.h b/arch/sparc/include/asm/kprobes.h index 3704490b4488..bfcaa6326c20 100644 --- a/arch/sparc/include/asm/kprobes.h +++ b/arch/sparc/include/asm/kprobes.h @@ -44,7 +44,6 @@ struct kprobe_ctlblk { unsigned long kprobe_status; unsigned long kprobe_orig_tnpc; unsigned long kprobe_orig_tstate_pil; - struct pt_regs jprobe_saved_regs; struct prev_kprobe prev_kprobe; }; diff --git a/arch/sparc/kernel/kprobes.c b/arch/sparc/kernel/kprobes.c index ab4ba4347941..dfbca2470536 100644 --- a/arch/sparc/kernel/kprobes.c +++ b/arch/sparc/kernel/kprobes.c @@ -147,18 +147,12 @@ static int __kprobes kprobe_handler(struct pt_regs *regs) kcb->kprobe_status = KPROBE_REENTER; prepare_singlestep(p, regs, kcb); return 1; - } else { - if (*(u32 *)addr != BREAKPOINT_INSTRUCTION) { + } else if (*(u32 *)addr != BREAKPOINT_INSTRUCTION) { /* The breakpoint instruction was removed by * another cpu right after we hit, no further * handling of this interrupt is appropriate */ - ret = 1; - goto no_kprobe; - } - p = __this_cpu_read(current_kprobe); - if (p->break_handler && p->break_handler(p, regs)) - goto ss_probe; + ret = 1; } goto no_kprobe; } @@ -181,10 +175,12 @@ static int __kprobes kprobe_handler(struct pt_regs *regs) set_current_kprobe(p, regs, kcb); kcb->kprobe_status = KPROBE_HIT_ACTIVE; - if (p->pre_handler && p->pre_handler(p, regs)) + if (p->pre_handler && p->pre_handler(p, regs)) { + reset_current_kprobe(); + preempt_enable_no_resched(); return 1; + } -ss_probe: prepare_singlestep(p, regs, kcb); kcb->kprobe_status = KPROBE_HIT_SS; return 1; @@ -441,53 +437,6 @@ out: exception_exit(prev_state); } -/* Jprobes support. */ -int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs) -{ - struct jprobe *jp = container_of(p, struct jprobe, kp); - struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - - memcpy(&(kcb->jprobe_saved_regs), regs, sizeof(*regs)); - - regs->tpc = (unsigned long) jp->entry; - regs->tnpc = ((unsigned long) jp->entry) + 0x4UL; - regs->tstate |= TSTATE_PIL; - - return 1; -} - -void __kprobes jprobe_return(void) -{ - struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - register unsigned long orig_fp asm("g1"); - - orig_fp = kcb->jprobe_saved_regs.u_regs[UREG_FP]; - __asm__ __volatile__("\n" -"1: cmp %%sp, %0\n\t" - "blu,a,pt %%xcc, 1b\n\t" - " restore\n\t" - ".globl jprobe_return_trap_instruction\n" -"jprobe_return_trap_instruction:\n\t" - "ta 0x70" - : /* no outputs */ - : "r" (orig_fp)); -} - -extern void jprobe_return_trap_instruction(void); - -int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs) -{ - u32 *addr = (u32 *) regs->tpc; - struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - - if (addr == (u32 *) jprobe_return_trap_instruction) { - memcpy(regs, &(kcb->jprobe_saved_regs), sizeof(*regs)); - preempt_enable_no_resched(); - return 1; - } - return 0; -} - /* The value stored in the return address register is actually 2 * instructions before where the callee will return to. * Sequences usually look something like this @@ -562,9 +511,7 @@ static int __kprobes trampoline_probe_handler(struct kprobe *p, regs->tpc = orig_ret_address; regs->tnpc = orig_ret_address + 4; - reset_current_kprobe(); kretprobe_hash_unlock(current, &flags); - preempt_enable_no_resched(); hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) { hlist_del(&ri->hlist); diff --git a/arch/sparc/lib/atomic32.c b/arch/sparc/lib/atomic32.c index 465a901a0ada..281fa634bb1a 100644 --- a/arch/sparc/lib/atomic32.c +++ b/arch/sparc/lib/atomic32.c @@ -95,7 +95,7 @@ int atomic_cmpxchg(atomic_t *v, int old, int new) } EXPORT_SYMBOL(atomic_cmpxchg); -int __atomic_add_unless(atomic_t *v, int a, int u) +int atomic_fetch_add_unless(atomic_t *v, int a, int u) { int ret; unsigned long flags; @@ -107,7 +107,7 @@ int __atomic_add_unless(atomic_t *v, int a, int u) spin_unlock_irqrestore(ATOMIC_HASH(v), flags); return ret; } -EXPORT_SYMBOL(__atomic_add_unless); +EXPORT_SYMBOL(atomic_fetch_add_unless); /* Atomic operations are already serializing */ void atomic_set(atomic_t *v, int i) diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 887d3a7bb646..6d4774f203d0 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -180,7 +180,7 @@ config X86 select HAVE_PERF_USER_STACK_DUMP select HAVE_RCU_TABLE_FREE select HAVE_REGS_AND_STACK_ACCESS_API - select HAVE_RELIABLE_STACKTRACE if X86_64 && UNWINDER_FRAME_POINTER && STACK_VALIDATION + select HAVE_RELIABLE_STACKTRACE if X86_64 && (UNWINDER_FRAME_POINTER || UNWINDER_ORC) && STACK_VALIDATION select HAVE_STACKPROTECTOR if CC_HAS_SANE_STACKPROTECTOR select HAVE_STACK_VALIDATION if X86_64 select HAVE_RSEQ diff --git a/arch/x86/Makefile b/arch/x86/Makefile index a08e82856563..7e3c07d6ad42 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -80,11 +80,6 @@ ifeq ($(CONFIG_X86_32),y) # alignment instructions. KBUILD_CFLAGS += $(call cc-option,$(cc_stack_align4)) - # Disable unit-at-a-time mode on pre-gcc-4.0 compilers, it makes gcc use - # a lot more stack due to the lack of sharing of stacklots: - KBUILD_CFLAGS += $(call cc-ifversion, -lt, 0400, \ - $(call cc-option,-fno-unit-at-a-time)) - # CPU-specific tuning. Anything which can be shared with UML should go here. include arch/x86/Makefile_32.cpu KBUILD_CFLAGS += $(cflags-y) diff --git a/arch/x86/boot/bitops.h b/arch/x86/boot/bitops.h index 0d41d68131cc..2e1382486e91 100644 --- a/arch/x86/boot/bitops.h +++ b/arch/x86/boot/bitops.h @@ -17,6 +17,7 @@ #define _LINUX_BITOPS_H /* Inhibit inclusion of <linux/bitops.h> */ #include <linux/types.h> +#include <asm/asm.h> static inline bool constant_test_bit(int nr, const void *addr) { @@ -28,7 +29,7 @@ static inline bool variable_test_bit(int nr, const void *addr) bool v; const u32 *p = (const u32 *)addr; - asm("btl %2,%1; setc %0" : "=qm" (v) : "m" (*p), "Ir" (nr)); + asm("btl %2,%1" CC_SET(c) : CC_OUT(c) (v) : "m" (*p), "Ir" (nr)); return v; } diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c index e98522ea6f09..1458b1700fc7 100644 --- a/arch/x86/boot/compressed/eboot.c +++ b/arch/x86/boot/compressed/eboot.c @@ -34,74 +34,13 @@ static void setup_boot_services##bits(struct efi_config *c) \ \ table = (typeof(table))sys_table; \ \ - c->runtime_services = table->runtime; \ - c->boot_services = table->boottime; \ - c->text_output = table->con_out; \ + c->runtime_services = table->runtime; \ + c->boot_services = table->boottime; \ + c->text_output = table->con_out; \ } BOOT_SERVICES(32); BOOT_SERVICES(64); -static inline efi_status_t __open_volume32(void *__image, void **__fh) -{ - efi_file_io_interface_t *io; - efi_loaded_image_32_t *image = __image; - efi_file_handle_32_t *fh; - efi_guid_t fs_proto = EFI_FILE_SYSTEM_GUID; - efi_status_t status; - void *handle = (void *)(unsigned long)image->device_handle; - unsigned long func; - - status = efi_call_early(handle_protocol, handle, - &fs_proto, (void **)&io); - if (status != EFI_SUCCESS) { - efi_printk(sys_table, "Failed to handle fs_proto\n"); - return status; - } - - func = (unsigned long)io->open_volume; - status = efi_early->call(func, io, &fh); - if (status != EFI_SUCCESS) - efi_printk(sys_table, "Failed to open volume\n"); - - *__fh = fh; - return status; -} - -static inline efi_status_t __open_volume64(void *__image, void **__fh) -{ - efi_file_io_interface_t *io; - efi_loaded_image_64_t *image = __image; - efi_file_handle_64_t *fh; - efi_guid_t fs_proto = EFI_FILE_SYSTEM_GUID; - efi_status_t status; - void *handle = (void *)(unsigned long)image->device_handle; - unsigned long func; - - status = efi_call_early(handle_protocol, handle, - &fs_proto, (void **)&io); - if (status != EFI_SUCCESS) { - efi_printk(sys_table, "Failed to handle fs_proto\n"); - return status; - } - - func = (unsigned long)io->open_volume; - status = efi_early->call(func, io, &fh); - if (status != EFI_SUCCESS) - efi_printk(sys_table, "Failed to open volume\n"); - - *__fh = fh; - return status; -} - -efi_status_t -efi_open_volume(efi_system_table_t *sys_table, void *__image, void **__fh) -{ - if (efi_early->is64) - return __open_volume64(__image, __fh); - - return __open_volume32(__image, __fh); -} - void efi_char16_printk(efi_system_table_t *table, efi_char16_t *str) { efi_call_proto(efi_simple_text_output_protocol, output_string, @@ -109,7 +48,7 @@ void efi_char16_printk(efi_system_table_t *table, efi_char16_t *str) } static efi_status_t -__setup_efi_pci(efi_pci_io_protocol_t *pci, struct pci_setup_rom **__rom) +preserve_pci_rom_image(efi_pci_io_protocol_t *pci, struct pci_setup_rom **__rom) { struct pci_setup_rom *rom = NULL; efi_status_t status; @@ -134,16 +73,16 @@ __setup_efi_pci(efi_pci_io_protocol_t *pci, struct pci_setup_rom **__rom) status = efi_call_early(allocate_pool, EFI_LOADER_DATA, size, &rom); if (status != EFI_SUCCESS) { - efi_printk(sys_table, "Failed to alloc mem for rom\n"); + efi_printk(sys_table, "Failed to allocate memory for 'rom'\n"); return status; } memset(rom, 0, sizeof(*rom)); - rom->data.type = SETUP_PCI; - rom->data.len = size - sizeof(struct setup_data); - rom->data.next = 0; - rom->pcilen = pci->romsize; + rom->data.type = SETUP_PCI; + rom->data.len = size - sizeof(struct setup_data); + rom->data.next = 0; + rom->pcilen = pci->romsize; *__rom = rom; status = efi_call_proto(efi_pci_io_protocol, pci.read, pci, @@ -179,96 +118,6 @@ free_struct: return status; } -static void -setup_efi_pci32(struct boot_params *params, void **pci_handle, - unsigned long size) -{ - efi_pci_io_protocol_t *pci = NULL; - efi_guid_t pci_proto = EFI_PCI_IO_PROTOCOL_GUID; - u32 *handles = (u32 *)(unsigned long)pci_handle; - efi_status_t status; - unsigned long nr_pci; - struct setup_data *data; - int i; - - data = (struct setup_data *)(unsigned long)params->hdr.setup_data; - - while (data && data->next) - data = (struct setup_data *)(unsigned long)data->next; - - nr_pci = size / sizeof(u32); - for (i = 0; i < nr_pci; i++) { - struct pci_setup_rom *rom = NULL; - u32 h = handles[i]; - - status = efi_call_early(handle_protocol, h, - &pci_proto, (void **)&pci); - - if (status != EFI_SUCCESS) - continue; - - if (!pci) - continue; - - status = __setup_efi_pci(pci, &rom); - if (status != EFI_SUCCESS) - continue; - - if (data) - data->next = (unsigned long)rom; - else - params->hdr.setup_data = (unsigned long)rom; - - data = (struct setup_data *)rom; - - } -} - -static void -setup_efi_pci64(struct boot_params *params, void **pci_handle, - unsigned long size) -{ - efi_pci_io_protocol_t *pci = NULL; - efi_guid_t pci_proto = EFI_PCI_IO_PROTOCOL_GUID; - u64 *handles = (u64 *)(unsigned long)pci_handle; - efi_status_t status; - unsigned long nr_pci; - struct setup_data *data; - int i; - - data = (struct setup_data *)(unsigned long)params->hdr.setup_data; - - while (data && data->next) - data = (struct setup_data *)(unsigned long)data->next; - - nr_pci = size / sizeof(u64); - for (i = 0; i < nr_pci; i++) { - struct pci_setup_rom *rom = NULL; - u64 h = handles[i]; - - status = efi_call_early(handle_protocol, h, - &pci_proto, (void **)&pci); - - if (status != EFI_SUCCESS) - continue; - - if (!pci) - continue; - - status = __setup_efi_pci(pci, &rom); - if (status != EFI_SUCCESS) - continue; - - if (data) - data->next = (unsigned long)rom; - else - params->hdr.setup_data = (unsigned long)rom; - - data = (struct setup_data *)rom; - - } -} - /* * There's no way to return an informative status from this function, * because any analysis (and printing of error messages) needs to be @@ -284,6 +133,9 @@ static void setup_efi_pci(struct boot_params *params) void **pci_handle = NULL; efi_guid_t pci_proto = EFI_PCI_IO_PROTOCOL_GUID; unsigned long size = 0; + unsigned long nr_pci; + struct setup_data *data; + int i; status = efi_call_early(locate_handle, EFI_LOCATE_BY_PROTOCOL, @@ -295,7 +147,7 @@ static void setup_efi_pci(struct boot_params *params) size, (void **)&pci_handle); if (status != EFI_SUCCESS) { - efi_printk(sys_table, "Failed to alloc mem for pci_handle\n"); + efi_printk(sys_table, "Failed to allocate memory for 'pci_handle'\n"); return; } @@ -307,10 +159,34 @@ static void setup_efi_pci(struct boot_params *params) if (status != EFI_SUCCESS) goto free_handle; - if (efi_early->is64) - setup_efi_pci64(params, pci_handle, size); - else - setup_efi_pci32(params, pci_handle, size); + data = (struct setup_data *)(unsigned long)params->hdr.setup_data; + + while (data && data->next) + data = (struct setup_data *)(unsigned long)data->next; + + nr_pci = size / (efi_is_64bit() ? sizeof(u64) : sizeof(u32)); + for (i = 0; i < nr_pci; i++) { + efi_pci_io_protocol_t *pci = NULL; + struct pci_setup_rom *rom; + + status = efi_call_early(handle_protocol, + efi_is_64bit() ? ((u64 *)pci_handle)[i] + : ((u32 *)pci_handle)[i], + &pci_proto, (void **)&pci); + if (status != EFI_SUCCESS || !pci) + continue; + + status = preserve_pci_rom_image(pci, &rom); + if (status != EFI_SUCCESS) + continue; + + if (data) + data->next = (unsigned long)rom; + else + params->hdr.setup_data = (unsigned long)rom; + + data = (struct setup_data *)rom; + } free_handle: efi_call_early(free_pool, pci_handle); @@ -341,8 +217,7 @@ static void retrieve_apple_device_properties(struct boot_params *boot_params) status = efi_call_early(allocate_pool, EFI_LOADER_DATA, size + sizeof(struct setup_data), &new); if (status != EFI_SUCCESS) { - efi_printk(sys_table, - "Failed to alloc mem for properties\n"); + efi_printk(sys_table, "Failed to allocate memory for 'properties'\n"); return; } @@ -358,9 +233,9 @@ static void retrieve_apple_device_properties(struct boot_params *boot_params) new->next = 0; data = (struct setup_data *)(unsigned long)boot_params->hdr.setup_data; - if (!data) + if (!data) { boot_params->hdr.setup_data = (unsigned long)new; - else { + } else { while (data->next) data = (struct setup_data *)(unsigned long)data->next; data->next = (unsigned long)new; @@ -380,81 +255,55 @@ static void setup_quirks(struct boot_params *boot_params) } } +/* + * See if we have Universal Graphics Adapter (UGA) protocol + */ static efi_status_t -setup_uga32(void **uga_handle, unsigned long size, u32 *width, u32 *height) +setup_uga(struct screen_info *si, efi_guid_t *uga_proto, unsigned long size) { - struct efi_uga_draw_protocol *uga = NULL, *first_uga; - efi_guid_t uga_proto = EFI_UGA_PROTOCOL_GUID; + efi_status_t status; + u32 width, height; + void **uga_handle = NULL; + efi_uga_draw_protocol_t *uga = NULL, *first_uga; unsigned long nr_ugas; - u32 *handles = (u32 *)uga_handle; - efi_status_t status = EFI_INVALID_PARAMETER; int i; - first_uga = NULL; - nr_ugas = size / sizeof(u32); - for (i = 0; i < nr_ugas; i++) { - efi_guid_t pciio_proto = EFI_PCI_IO_PROTOCOL_GUID; - u32 w, h, depth, refresh; - void *pciio; - u32 handle = handles[i]; - - status = efi_call_early(handle_protocol, handle, - &uga_proto, (void **)&uga); - if (status != EFI_SUCCESS) - continue; - - efi_call_early(handle_protocol, handle, &pciio_proto, &pciio); - - status = efi_early->call((unsigned long)uga->get_mode, uga, - &w, &h, &depth, &refresh); - if (status == EFI_SUCCESS && (!first_uga || pciio)) { - *width = w; - *height = h; - - /* - * Once we've found a UGA supporting PCIIO, - * don't bother looking any further. - */ - if (pciio) - break; - - first_uga = uga; - } - } + status = efi_call_early(allocate_pool, EFI_LOADER_DATA, + size, (void **)&uga_handle); + if (status != EFI_SUCCESS) + return status; - return status; -} + status = efi_call_early(locate_handle, + EFI_LOCATE_BY_PROTOCOL, + uga_proto, NULL, &size, uga_handle); + if (status != EFI_SUCCESS) + goto free_handle; -static efi_status_t -setup_uga64(void **uga_handle, unsigned long size, u32 *width, u32 *height) -{ - struct efi_uga_draw_protocol *uga = NULL, *first_uga; - efi_guid_t uga_proto = EFI_UGA_PROTOCOL_GUID; - unsigned long nr_ugas; - u64 *handles = (u64 *)uga_handle; - efi_status_t status = EFI_INVALID_PARAMETER; - int i; + height = 0; + width = 0; first_uga = NULL; - nr_ugas = size / sizeof(u64); + nr_ugas = size / (efi_is_64bit() ? sizeof(u64) : sizeof(u32)); for (i = 0; i < nr_ugas; i++) { efi_guid_t pciio_proto = EFI_PCI_IO_PROTOCOL_GUID; u32 w, h, depth, refresh; void *pciio; - u64 handle = handles[i]; + unsigned long handle = efi_is_64bit() ? ((u64 *)uga_handle)[i] + : ((u32 *)uga_handle)[i]; status = efi_call_early(handle_protocol, handle, - &uga_proto, (void **)&uga); + uga_proto, (void **)&uga); if (status != EFI_SUCCESS) continue; + pciio = NULL; efi_call_early(handle_protocol, handle, &pciio_proto, &pciio); - status = efi_early->call((unsigned long)uga->get_mode, uga, - &w, &h, &depth, &refresh); + status = efi_call_proto(efi_uga_draw_protocol, get_mode, uga, + &w, &h, &depth, &refresh); if (status == EFI_SUCCESS && (!first_uga || pciio)) { - *width = w; - *height = h; + width = w; + height = h; /* * Once we've found a UGA supporting PCIIO, @@ -467,59 +316,28 @@ setup_uga64(void **uga_handle, unsigned long size, u32 *width, u32 *height) } } - return status; -} - -/* - * See if we have Universal Graphics Adapter (UGA) protocol - */ -static efi_status_t setup_uga(struct screen_info *si, efi_guid_t *uga_proto, - unsigned long size) -{ - efi_status_t status; - u32 width, height; - void **uga_handle = NULL; - - status = efi_call_early(allocate_pool, EFI_LOADER_DATA, - size, (void **)&uga_handle); - if (status != EFI_SUCCESS) - return status; - - status = efi_call_early(locate_handle, - EFI_LOCATE_BY_PROTOCOL, - uga_proto, NULL, &size, uga_handle); - if (status != EFI_SUCCESS) - goto free_handle; - - height = 0; - width = 0; - - if (efi_early->is64) - status = setup_uga64(uga_handle, size, &width, &height); - else - status = setup_uga32(uga_handle, size, &width, &height); - if (!width && !height) goto free_handle; /* EFI framebuffer */ - si->orig_video_isVGA = VIDEO_TYPE_EFI; + si->orig_video_isVGA = VIDEO_TYPE_EFI; - si->lfb_depth = 32; - si->lfb_width = width; - si->lfb_height = height; + si->lfb_depth = 32; + si->lfb_width = width; + si->lfb_height = height; - si->red_size = 8; - si->red_pos = 16; - si->green_size = 8; - si->green_pos = 8; - si->blue_size = 8; - si->blue_pos = 0; - si->rsvd_size = 8; - si->rsvd_pos = 24; + si->red_size = 8; + si->red_pos = 16; + si->green_size = 8; + si->green_pos = 8; + si->blue_size = 8; + si->blue_pos = 0; + si->rsvd_size = 8; + si->rsvd_pos = 24; free_handle: efi_call_early(free_pool, uga_handle); + return status; } @@ -586,7 +404,7 @@ struct boot_params *make_boot_params(struct efi_config *c) if (sys_table->hdr.signature != EFI_SYSTEM_TABLE_SIGNATURE) return NULL; - if (efi_early->is64) + if (efi_is_64bit()) setup_boot_services64(efi_early); else setup_boot_services32(efi_early); @@ -601,7 +419,7 @@ struct boot_params *make_boot_params(struct efi_config *c) status = efi_low_alloc(sys_table, 0x4000, 1, (unsigned long *)&boot_params); if (status != EFI_SUCCESS) { - efi_printk(sys_table, "Failed to alloc lowmem for boot params\n"); + efi_printk(sys_table, "Failed to allocate lowmem for boot params\n"); return NULL; } @@ -617,9 +435,9 @@ struct boot_params *make_boot_params(struct efi_config *c) * Fill out some of the header fields ourselves because the * EFI firmware loader doesn't load the first sector. */ - hdr->root_flags = 1; - hdr->vid_mode = 0xffff; - hdr->boot_flag = 0xAA55; + hdr->root_flags = 1; + hdr->vid_mode = 0xffff; + hdr->boot_flag = 0xAA55; hdr->type_of_loader = 0x21; @@ -627,6 +445,7 @@ struct boot_params *make_boot_params(struct efi_config *c) cmdline_ptr = efi_convert_cmdline(sys_table, image, &options_size); if (!cmdline_ptr) goto fail; + hdr->cmd_line_ptr = (unsigned long)cmdline_ptr; /* Fill in upper bits of command line address, NOP on 32 bit */ boot_params->ext_cmd_line_ptr = (u64)(unsigned long)cmdline_ptr >> 32; @@ -663,10 +482,12 @@ struct boot_params *make_boot_params(struct efi_config *c) boot_params->ext_ramdisk_size = (u64)ramdisk_size >> 32; return boot_params; + fail2: efi_free(sys_table, options_size, hdr->cmd_line_ptr); fail: efi_free(sys_table, 0x4000, (unsigned long)boot_params); + return NULL; } @@ -678,7 +499,7 @@ static void add_e820ext(struct boot_params *params, unsigned long size; e820ext->type = SETUP_E820_EXT; - e820ext->len = nr_entries * sizeof(struct boot_e820_entry); + e820ext->len = nr_entries * sizeof(struct boot_e820_entry); e820ext->next = 0; data = (struct setup_data *)(unsigned long)params->hdr.setup_data; @@ -692,8 +513,8 @@ static void add_e820ext(struct boot_params *params, params->hdr.setup_data = (unsigned long)e820ext; } -static efi_status_t setup_e820(struct boot_params *params, - struct setup_data *e820ext, u32 e820ext_size) +static efi_status_t +setup_e820(struct boot_params *params, struct setup_data *e820ext, u32 e820ext_size) { struct boot_e820_entry *entry = params->e820_table; struct efi_info *efi = ¶ms->efi_info; @@ -814,11 +635,10 @@ static efi_status_t alloc_e820ext(u32 nr_desc, struct setup_data **e820ext, } struct exit_boot_struct { - struct boot_params *boot_params; - struct efi_info *efi; - struct setup_data *e820ext; - __u32 e820ext_size; - bool is64; + struct boot_params *boot_params; + struct efi_info *efi; + struct setup_data *e820ext; + __u32 e820ext_size; }; static efi_status_t exit_boot_func(efi_system_table_t *sys_table_arg, @@ -845,25 +665,25 @@ static efi_status_t exit_boot_func(efi_system_table_t *sys_table_arg, first = false; } - signature = p->is64 ? EFI64_LOADER_SIGNATURE : EFI32_LOADER_SIGNATURE; + signature = efi_is_64bit() ? EFI64_LOADER_SIGNATURE + : EFI32_LOADER_SIGNATURE; memcpy(&p->efi->efi_loader_signature, signature, sizeof(__u32)); - p->efi->efi_systab = (unsigned long)sys_table_arg; - p->efi->efi_memdesc_size = *map->desc_size; - p->efi->efi_memdesc_version = *map->desc_ver; - p->efi->efi_memmap = (unsigned long)*map->map; - p->efi->efi_memmap_size = *map->map_size; + p->efi->efi_systab = (unsigned long)sys_table_arg; + p->efi->efi_memdesc_size = *map->desc_size; + p->efi->efi_memdesc_version = *map->desc_ver; + p->efi->efi_memmap = (unsigned long)*map->map; + p->efi->efi_memmap_size = *map->map_size; #ifdef CONFIG_X86_64 - p->efi->efi_systab_hi = (unsigned long)sys_table_arg >> 32; - p->efi->efi_memmap_hi = (unsigned long)*map->map >> 32; + p->efi->efi_systab_hi = (unsigned long)sys_table_arg >> 32; + p->efi->efi_memmap_hi = (unsigned long)*map->map >> 32; #endif return EFI_SUCCESS; } -static efi_status_t exit_boot(struct boot_params *boot_params, - void *handle, bool is64) +static efi_status_t exit_boot(struct boot_params *boot_params, void *handle) { unsigned long map_sz, key, desc_size, buff_size; efi_memory_desc_t *mem_map; @@ -874,17 +694,16 @@ static efi_status_t exit_boot(struct boot_params *boot_params, struct efi_boot_memmap map; struct exit_boot_struct priv; - map.map = &mem_map; - map.map_size = &map_sz; - map.desc_size = &desc_size; - map.desc_ver = &desc_version; - map.key_ptr = &key; - map.buff_size = &buff_size; - priv.boot_params = boot_params; - priv.efi = &boot_params->efi_info; - priv.e820ext = NULL; - priv.e820ext_size = 0; - priv.is64 = is64; + map.map = &mem_map; + map.map_size = &map_sz; + map.desc_size = &desc_size; + map.desc_ver = &desc_version; + map.key_ptr = &key; + map.buff_size = &buff_size; + priv.boot_params = boot_params; + priv.efi = &boot_params->efi_info; + priv.e820ext = NULL; + priv.e820ext_size = 0; /* Might as well exit boot services now */ status = efi_exit_boot_services(sys_table, handle, &map, &priv, @@ -892,10 +711,11 @@ static efi_status_t exit_boot(struct boot_params *boot_params, if (status != EFI_SUCCESS) return status; - e820ext = priv.e820ext; - e820ext_size = priv.e820ext_size; + e820ext = priv.e820ext; + e820ext_size = priv.e820ext_size; + /* Historic? */ - boot_params->alt_mem_k = 32 * 1024; + boot_params->alt_mem_k = 32 * 1024; status = setup_e820(boot_params, e820ext, e820ext_size); if (status != EFI_SUCCESS) @@ -908,8 +728,8 @@ static efi_status_t exit_boot(struct boot_params *boot_params, * On success we return a pointer to a boot_params structure, and NULL * on failure. */ -struct boot_params *efi_main(struct efi_config *c, - struct boot_params *boot_params) +struct boot_params * +efi_main(struct efi_config *c, struct boot_params *boot_params) { struct desc_ptr *gdt = NULL; efi_loaded_image_t *image; @@ -918,13 +738,11 @@ struct boot_params *efi_main(struct efi_config *c, struct desc_struct *desc; void *handle; efi_system_table_t *_table; - bool is64; efi_early = c; _table = (efi_system_table_t *)(unsigned long)efi_early->table; handle = (void *)(unsigned long)efi_early->image_handle; - is64 = efi_early->is64; sys_table = _table; @@ -932,7 +750,7 @@ struct boot_params *efi_main(struct efi_config *c, if (sys_table->hdr.signature != EFI_SYSTEM_TABLE_SIGNATURE) goto fail; - if (is64) + if (efi_is_64bit()) setup_boot_services64(efi_early); else setup_boot_services32(efi_early); @@ -957,7 +775,7 @@ struct boot_params *efi_main(struct efi_config *c, status = efi_call_early(allocate_pool, EFI_LOADER_DATA, sizeof(*gdt), (void **)&gdt); if (status != EFI_SUCCESS) { - efi_printk(sys_table, "Failed to alloc mem for gdt structure\n"); + efi_printk(sys_table, "Failed to allocate memory for 'gdt' structure\n"); goto fail; } @@ -965,7 +783,7 @@ struct boot_params *efi_main(struct efi_config *c, status = efi_low_alloc(sys_table, gdt->size, 8, (unsigned long *)&gdt->address); if (status != EFI_SUCCESS) { - efi_printk(sys_table, "Failed to alloc mem for gdt\n"); + efi_printk(sys_table, "Failed to allocate memory for 'gdt'\n"); goto fail; } @@ -988,7 +806,7 @@ struct boot_params *efi_main(struct efi_config *c, hdr->code32_start = bzimage_addr; } - status = exit_boot(boot_params, handle, is64); + status = exit_boot(boot_params, handle); if (status != EFI_SUCCESS) { efi_printk(sys_table, "exit_boot() failed!\n"); goto fail; @@ -1002,19 +820,20 @@ struct boot_params *efi_main(struct efi_config *c, if (IS_ENABLED(CONFIG_X86_64)) { /* __KERNEL32_CS */ - desc->limit0 = 0xffff; - desc->base0 = 0x0000; - desc->base1 = 0x0000; - desc->type = SEG_TYPE_CODE | SEG_TYPE_EXEC_READ; - desc->s = DESC_TYPE_CODE_DATA; - desc->dpl = 0; - desc->p = 1; - desc->limit1 = 0xf; - desc->avl = 0; - desc->l = 0; - desc->d = SEG_OP_SIZE_32BIT; - desc->g = SEG_GRANULARITY_4KB; - desc->base2 = 0x00; + desc->limit0 = 0xffff; + desc->base0 = 0x0000; + desc->base1 = 0x0000; + desc->type = SEG_TYPE_CODE | SEG_TYPE_EXEC_READ; + desc->s = DESC_TYPE_CODE_DATA; + desc->dpl = 0; + desc->p = 1; + desc->limit1 = 0xf; + desc->avl = 0; + desc->l = 0; + desc->d = SEG_OP_SIZE_32BIT; + desc->g = SEG_GRANULARITY_4KB; + desc->base2 = 0x00; + desc++; } else { /* Second entry is unused on 32-bit */ @@ -1022,15 +841,16 @@ struct boot_params *efi_main(struct efi_config *c, } /* __KERNEL_CS */ - desc->limit0 = 0xffff; - desc->base0 = 0x0000; - desc->base1 = 0x0000; - desc->type = SEG_TYPE_CODE | SEG_TYPE_EXEC_READ; - desc->s = DESC_TYPE_CODE_DATA; - desc->dpl = 0; - desc->p = 1; - desc->limit1 = 0xf; - desc->avl = 0; + desc->limit0 = 0xffff; + desc->base0 = 0x0000; + desc->base1 = 0x0000; + desc->type = SEG_TYPE_CODE | SEG_TYPE_EXEC_READ; + desc->s = DESC_TYPE_CODE_DATA; + desc->dpl = 0; + desc->p = 1; + desc->limit1 = 0xf; + desc->avl = 0; + if (IS_ENABLED(CONFIG_X86_64)) { desc->l = 1; desc->d = 0; @@ -1038,41 +858,41 @@ struct boot_params *efi_main(struct efi_config *c, desc->l = 0; desc->d = SEG_OP_SIZE_32BIT; } - desc->g = SEG_GRANULARITY_4KB; - desc->base2 = 0x00; + desc->g = SEG_GRANULARITY_4KB; + desc->base2 = 0x00; desc++; /* __KERNEL_DS */ - desc->limit0 = 0xffff; - desc->base0 = 0x0000; - desc->base1 = 0x0000; - desc->type = SEG_TYPE_DATA | SEG_TYPE_READ_WRITE; - desc->s = DESC_TYPE_CODE_DATA; - desc->dpl = 0; - desc->p = 1; - desc->limit1 = 0xf; - desc->avl = 0; - desc->l = 0; - desc->d = SEG_OP_SIZE_32BIT; - desc->g = SEG_GRANULARITY_4KB; - desc->base2 = 0x00; + desc->limit0 = 0xffff; + desc->base0 = 0x0000; + desc->base1 = 0x0000; + desc->type = SEG_TYPE_DATA | SEG_TYPE_READ_WRITE; + desc->s = DESC_TYPE_CODE_DATA; + desc->dpl = 0; + desc->p = 1; + desc->limit1 = 0xf; + desc->avl = 0; + desc->l = 0; + desc->d = SEG_OP_SIZE_32BIT; + desc->g = SEG_GRANULARITY_4KB; + desc->base2 = 0x00; desc++; if (IS_ENABLED(CONFIG_X86_64)) { /* Task segment value */ - desc->limit0 = 0x0000; - desc->base0 = 0x0000; - desc->base1 = 0x0000; - desc->type = SEG_TYPE_TSS; - desc->s = 0; - desc->dpl = 0; - desc->p = 1; - desc->limit1 = 0x0; - desc->avl = 0; - desc->l = 0; - desc->d = 0; - desc->g = SEG_GRANULARITY_4KB; - desc->base2 = 0x00; + desc->limit0 = 0x0000; + desc->base0 = 0x0000; + desc->base1 = 0x0000; + desc->type = SEG_TYPE_TSS; + desc->s = 0; + desc->dpl = 0; + desc->p = 1; + desc->limit1 = 0x0; + desc->avl = 0; + desc->l = 0; + desc->d = 0; + desc->g = SEG_GRANULARITY_4KB; + desc->base2 = 0x00; desc++; } @@ -1082,5 +902,6 @@ struct boot_params *efi_main(struct efi_config *c, return boot_params; fail: efi_printk(sys_table, "efi_main() failed!\n"); + return NULL; } diff --git a/arch/x86/boot/compressed/eboot.h b/arch/x86/boot/compressed/eboot.h index e799dc5c6448..8297387c4676 100644 --- a/arch/x86/boot/compressed/eboot.h +++ b/arch/x86/boot/compressed/eboot.h @@ -12,22 +12,22 @@ #define DESC_TYPE_CODE_DATA (1 << 0) -struct efi_uga_draw_protocol_32 { +typedef struct { u32 get_mode; u32 set_mode; u32 blt; -}; +} efi_uga_draw_protocol_32_t; -struct efi_uga_draw_protocol_64 { +typedef struct { u64 get_mode; u64 set_mode; u64 blt; -}; +} efi_uga_draw_protocol_64_t; -struct efi_uga_draw_protocol { +typedef struct { void *get_mode; void *set_mode; void *blt; -}; +} efi_uga_draw_protocol_t; #endif /* BOOT_COMPRESSED_EBOOT_H */ diff --git a/arch/x86/boot/compressed/kaslr.c b/arch/x86/boot/compressed/kaslr.c index b87a7582853d..302517929932 100644 --- a/arch/x86/boot/compressed/kaslr.c +++ b/arch/x86/boot/compressed/kaslr.c @@ -102,7 +102,7 @@ static bool memmap_too_large; /* Store memory limit specified by "mem=nn[KMG]" or "memmap=nn[KMG]" */ -unsigned long long mem_limit = ULLONG_MAX; +static unsigned long long mem_limit = ULLONG_MAX; enum mem_avoid_index { @@ -215,7 +215,36 @@ static void mem_avoid_memmap(char *str) memmap_too_large = true; } -static int handle_mem_memmap(void) +/* Store the number of 1GB huge pages which users specified: */ +static unsigned long max_gb_huge_pages; + +static void parse_gb_huge_pages(char *param, char *val) +{ + static bool gbpage_sz; + char *p; + + if (!strcmp(param, "hugepagesz")) { + p = val; + if (memparse(p, &p) != PUD_SIZE) { + gbpage_sz = false; + return; + } + + if (gbpage_sz) + warn("Repeatedly set hugeTLB page size of 1G!\n"); + gbpage_sz = true; + return; + } + + if (!strcmp(param, "hugepages") && gbpage_sz) { + p = val; + max_gb_huge_pages = simple_strtoull(p, &p, 0); + return; + } +} + + +static int handle_mem_options(void) { char *args = (char *)get_cmd_line_ptr(); size_t len = strlen((char *)args); @@ -223,7 +252,8 @@ static int handle_mem_memmap(void) char *param, *val; u64 mem_size; - if (!strstr(args, "memmap=") && !strstr(args, "mem=")) + if (!strstr(args, "memmap=") && !strstr(args, "mem=") && + !strstr(args, "hugepages")) return 0; tmp_cmdline = malloc(len + 1); @@ -248,6 +278,8 @@ static int handle_mem_memmap(void) if (!strcmp(param, "memmap")) { mem_avoid_memmap(val); + } else if (strstr(param, "hugepages")) { + parse_gb_huge_pages(param, val); } else if (!strcmp(param, "mem")) { char *p = val; @@ -387,7 +419,7 @@ static void mem_avoid_init(unsigned long input, unsigned long input_size, /* We don't need to set a mapping for setup_data. */ /* Mark the memmap regions we need to avoid */ - handle_mem_memmap(); + handle_mem_options(); #ifdef CONFIG_X86_VERBOSE_BOOTUP /* Make sure video RAM can be used. */ @@ -466,6 +498,60 @@ static void store_slot_info(struct mem_vector *region, unsigned long image_size) } } +/* + * Skip as many 1GB huge pages as possible in the passed region + * according to the number which users specified: + */ +static void +process_gb_huge_pages(struct mem_vector *region, unsigned long image_size) +{ + unsigned long addr, size = 0; + struct mem_vector tmp; + int i = 0; + + if (!max_gb_huge_pages) { + store_slot_info(region, image_size); + return; + } + + addr = ALIGN(region->start, PUD_SIZE); + /* Did we raise the address above the passed in memory entry? */ + if (addr < region->start + region->size) + size = region->size - (addr - region->start); + + /* Check how many 1GB huge pages can be filtered out: */ + while (size > PUD_SIZE && max_gb_huge_pages) { + size -= PUD_SIZE; + max_gb_huge_pages--; + i++; + } + + /* No good 1GB huge pages found: */ + if (!i) { + store_slot_info(region, image_size); + return; + } + + /* + * Skip those 'i'*1GB good huge pages, and continue checking and + * processing the remaining head or tail part of the passed region + * if available. + */ + + if (addr >= region->start + image_size) { + tmp.start = region->start; + tmp.size = addr - region->start; + store_slot_info(&tmp, image_size); + } + + size = region->size - (addr - region->start) - i * PUD_SIZE; + if (size >= image_size) { + tmp.start = addr + i * PUD_SIZE; + tmp.size = size; + store_slot_info(&tmp, image_size); + } +} + static unsigned long slots_fetch_random(void) { unsigned long slot; @@ -546,7 +632,7 @@ static void process_mem_region(struct mem_vector *entry, /* If nothing overlaps, store the region and return. */ if (!mem_avoid_overlap(®ion, &overlap)) { - store_slot_info(®ion, image_size); + process_gb_huge_pages(®ion, image_size); return; } @@ -556,7 +642,7 @@ static void process_mem_region(struct mem_vector *entry, beginning.start = region.start; beginning.size = overlap.start - region.start; - store_slot_info(&beginning, image_size); + process_gb_huge_pages(&beginning, image_size); } /* Return if overlap extends to or past end of region. */ diff --git a/arch/x86/boot/string.c b/arch/x86/boot/string.c index 16f49123d747..c4428a176973 100644 --- a/arch/x86/boot/string.c +++ b/arch/x86/boot/string.c @@ -13,6 +13,7 @@ */ #include <linux/types.h> +#include <asm/asm.h> #include "ctype.h" #include "string.h" @@ -28,8 +29,8 @@ int memcmp(const void *s1, const void *s2, size_t len) { bool diff; - asm("repe; cmpsb; setnz %0" - : "=qm" (diff), "+D" (s1), "+S" (s2), "+c" (len)); + asm("repe; cmpsb" CC_SET(nz) + : CC_OUT(nz) (diff), "+D" (s1), "+S" (s2), "+c" (len)); return diff; } diff --git a/arch/x86/crypto/aegis128-aesni-asm.S b/arch/x86/crypto/aegis128-aesni-asm.S index 717bf0776421..5f7e43d4f64a 100644 --- a/arch/x86/crypto/aegis128-aesni-asm.S +++ b/arch/x86/crypto/aegis128-aesni-asm.S @@ -75,7 +75,7 @@ * %r9 */ __load_partial: - xor %r9, %r9 + xor %r9d, %r9d pxor MSG, MSG mov LEN, %r8 diff --git a/arch/x86/crypto/aegis128-aesni-glue.c b/arch/x86/crypto/aegis128-aesni-glue.c index 5de7c0d46edf..acd11b3bf639 100644 --- a/arch/x86/crypto/aegis128-aesni-glue.c +++ b/arch/x86/crypto/aegis128-aesni-glue.c @@ -375,16 +375,12 @@ static struct aead_alg crypto_aegis128_aesni_alg[] = { } }; -static const struct x86_cpu_id aesni_cpu_id[] = { - X86_FEATURE_MATCH(X86_FEATURE_AES), - X86_FEATURE_MATCH(X86_FEATURE_XMM2), - {} -}; -MODULE_DEVICE_TABLE(x86cpu, aesni_cpu_id); - static int __init crypto_aegis128_aesni_module_init(void) { - if (!x86_match_cpu(aesni_cpu_id)) + if (!boot_cpu_has(X86_FEATURE_XMM2) || + !boot_cpu_has(X86_FEATURE_AES) || + !boot_cpu_has(X86_FEATURE_OSXSAVE) || + !cpu_has_xfeatures(XFEATURE_MASK_SSE, NULL)) return -ENODEV; return crypto_register_aeads(crypto_aegis128_aesni_alg, diff --git a/arch/x86/crypto/aegis128l-aesni-asm.S b/arch/x86/crypto/aegis128l-aesni-asm.S index 4eda2b8db9e1..491dd61c845c 100644 --- a/arch/x86/crypto/aegis128l-aesni-asm.S +++ b/arch/x86/crypto/aegis128l-aesni-asm.S @@ -66,7 +66,7 @@ * %r9 */ __load_partial: - xor %r9, %r9 + xor %r9d, %r9d pxor MSG0, MSG0 pxor MSG1, MSG1 diff --git a/arch/x86/crypto/aegis128l-aesni-glue.c b/arch/x86/crypto/aegis128l-aesni-glue.c index 876e4866e633..2071c3d1ae07 100644 --- a/arch/x86/crypto/aegis128l-aesni-glue.c +++ b/arch/x86/crypto/aegis128l-aesni-glue.c @@ -375,16 +375,12 @@ static struct aead_alg crypto_aegis128l_aesni_alg[] = { } }; -static const struct x86_cpu_id aesni_cpu_id[] = { - X86_FEATURE_MATCH(X86_FEATURE_AES), - X86_FEATURE_MATCH(X86_FEATURE_XMM2), - {} -}; -MODULE_DEVICE_TABLE(x86cpu, aesni_cpu_id); - static int __init crypto_aegis128l_aesni_module_init(void) { - if (!x86_match_cpu(aesni_cpu_id)) + if (!boot_cpu_has(X86_FEATURE_XMM2) || + !boot_cpu_has(X86_FEATURE_AES) || + !boot_cpu_has(X86_FEATURE_OSXSAVE) || + !cpu_has_xfeatures(XFEATURE_MASK_SSE, NULL)) return -ENODEV; return crypto_register_aeads(crypto_aegis128l_aesni_alg, diff --git a/arch/x86/crypto/aegis256-aesni-asm.S b/arch/x86/crypto/aegis256-aesni-asm.S index 32aae8397268..8870c7c5d9a4 100644 --- a/arch/x86/crypto/aegis256-aesni-asm.S +++ b/arch/x86/crypto/aegis256-aesni-asm.S @@ -59,7 +59,7 @@ * %r9 */ __load_partial: - xor %r9, %r9 + xor %r9d, %r9d pxor MSG, MSG mov LEN, %r8 diff --git a/arch/x86/crypto/aegis256-aesni-glue.c b/arch/x86/crypto/aegis256-aesni-glue.c index 2b5dd3af8f4d..b5f2a8fd5a71 100644 --- a/arch/x86/crypto/aegis256-aesni-glue.c +++ b/arch/x86/crypto/aegis256-aesni-glue.c @@ -375,16 +375,12 @@ static struct aead_alg crypto_aegis256_aesni_alg[] = { } }; -static const struct x86_cpu_id aesni_cpu_id[] = { - X86_FEATURE_MATCH(X86_FEATURE_AES), - X86_FEATURE_MATCH(X86_FEATURE_XMM2), - {} -}; -MODULE_DEVICE_TABLE(x86cpu, aesni_cpu_id); - static int __init crypto_aegis256_aesni_module_init(void) { - if (!x86_match_cpu(aesni_cpu_id)) + if (!boot_cpu_has(X86_FEATURE_XMM2) || + !boot_cpu_has(X86_FEATURE_AES) || + !boot_cpu_has(X86_FEATURE_OSXSAVE) || + !cpu_has_xfeatures(XFEATURE_MASK_SSE, NULL)) return -ENODEV; return crypto_register_aeads(crypto_aegis256_aesni_alg, diff --git a/arch/x86/crypto/aesni-intel_asm.S b/arch/x86/crypto/aesni-intel_asm.S index e762ef417562..9bd139569b41 100644 --- a/arch/x86/crypto/aesni-intel_asm.S +++ b/arch/x86/crypto/aesni-intel_asm.S @@ -258,7 +258,7 @@ ALL_F: .octa 0xffffffffffffffffffffffffffffffff .macro GCM_INIT Iv SUBKEY AAD AADLEN mov \AADLEN, %r11 mov %r11, AadLen(%arg2) # ctx_data.aad_length = aad_length - xor %r11, %r11 + xor %r11d, %r11d mov %r11, InLen(%arg2) # ctx_data.in_length = 0 mov %r11, PBlockLen(%arg2) # ctx_data.partial_block_length = 0 mov %r11, PBlockEncKey(%arg2) # ctx_data.partial_block_enc_key = 0 @@ -286,7 +286,7 @@ ALL_F: .octa 0xffffffffffffffffffffffffffffffff movdqu HashKey(%arg2), %xmm13 add %arg5, InLen(%arg2) - xor %r11, %r11 # initialise the data pointer offset as zero + xor %r11d, %r11d # initialise the data pointer offset as zero PARTIAL_BLOCK %arg3 %arg4 %arg5 %r11 %xmm8 \operation sub %r11, %arg5 # sub partial block data used @@ -702,7 +702,7 @@ _no_extra_mask_1_\@: # GHASH computation for the last <16 Byte block GHASH_MUL \AAD_HASH, %xmm13, %xmm0, %xmm10, %xmm11, %xmm5, %xmm6 - xor %rax,%rax + xor %eax, %eax mov %rax, PBlockLen(%arg2) jmp _dec_done_\@ @@ -737,7 +737,7 @@ _no_extra_mask_2_\@: # GHASH computation for the last <16 Byte block GHASH_MUL \AAD_HASH, %xmm13, %xmm0, %xmm10, %xmm11, %xmm5, %xmm6 - xor %rax,%rax + xor %eax, %eax mov %rax, PBlockLen(%arg2) jmp _encode_done_\@ diff --git a/arch/x86/crypto/aesni-intel_avx-x86_64.S b/arch/x86/crypto/aesni-intel_avx-x86_64.S index faecb1518bf8..1985ea0b551b 100644 --- a/arch/x86/crypto/aesni-intel_avx-x86_64.S +++ b/arch/x86/crypto/aesni-intel_avx-x86_64.S @@ -463,7 +463,7 @@ _get_AAD_rest_final\@: _get_AAD_done\@: # initialize the data pointer offset as zero - xor %r11, %r11 + xor %r11d, %r11d # start AES for num_initial_blocks blocks mov arg5, %rax # rax = *Y0 @@ -1770,7 +1770,7 @@ _get_AAD_rest_final\@: _get_AAD_done\@: # initialize the data pointer offset as zero - xor %r11, %r11 + xor %r11d, %r11d # start AES for num_initial_blocks blocks mov arg5, %rax # rax = *Y0 diff --git a/arch/x86/crypto/morus1280-avx2-asm.S b/arch/x86/crypto/morus1280-avx2-asm.S index 07653d4582a6..de182c460f82 100644 --- a/arch/x86/crypto/morus1280-avx2-asm.S +++ b/arch/x86/crypto/morus1280-avx2-asm.S @@ -113,7 +113,7 @@ ENDPROC(__morus1280_update_zero) * %r9 */ __load_partial: - xor %r9, %r9 + xor %r9d, %r9d vpxor MSG, MSG, MSG mov %rcx, %r8 diff --git a/arch/x86/crypto/morus1280-avx2-glue.c b/arch/x86/crypto/morus1280-avx2-glue.c index f111f36d26dc..6634907d6ccd 100644 --- a/arch/x86/crypto/morus1280-avx2-glue.c +++ b/arch/x86/crypto/morus1280-avx2-glue.c @@ -37,15 +37,11 @@ asmlinkage void crypto_morus1280_avx2_final(void *state, void *tag_xor, MORUS1280_DECLARE_ALGS(avx2, "morus1280-avx2", 400); -static const struct x86_cpu_id avx2_cpu_id[] = { - X86_FEATURE_MATCH(X86_FEATURE_AVX2), - {} -}; -MODULE_DEVICE_TABLE(x86cpu, avx2_cpu_id); - static int __init crypto_morus1280_avx2_module_init(void) { - if (!x86_match_cpu(avx2_cpu_id)) + if (!boot_cpu_has(X86_FEATURE_AVX2) || + !boot_cpu_has(X86_FEATURE_OSXSAVE) || + !cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL)) return -ENODEV; return crypto_register_aeads(crypto_morus1280_avx2_algs, diff --git a/arch/x86/crypto/morus1280-sse2-asm.S b/arch/x86/crypto/morus1280-sse2-asm.S index bd1aa1b60869..da5d2905db60 100644 --- a/arch/x86/crypto/morus1280-sse2-asm.S +++ b/arch/x86/crypto/morus1280-sse2-asm.S @@ -235,7 +235,7 @@ ENDPROC(__morus1280_update_zero) * %r9 */ __load_partial: - xor %r9, %r9 + xor %r9d, %r9d pxor MSG_LO, MSG_LO pxor MSG_HI, MSG_HI diff --git a/arch/x86/crypto/morus1280-sse2-glue.c b/arch/x86/crypto/morus1280-sse2-glue.c index 839270aa713c..95cf857d2cbb 100644 --- a/arch/x86/crypto/morus1280-sse2-glue.c +++ b/arch/x86/crypto/morus1280-sse2-glue.c @@ -37,15 +37,11 @@ asmlinkage void crypto_morus1280_sse2_final(void *state, void *tag_xor, MORUS1280_DECLARE_ALGS(sse2, "morus1280-sse2", 350); -static const struct x86_cpu_id sse2_cpu_id[] = { - X86_FEATURE_MATCH(X86_FEATURE_XMM2), - {} -}; -MODULE_DEVICE_TABLE(x86cpu, sse2_cpu_id); - static int __init crypto_morus1280_sse2_module_init(void) { - if (!x86_match_cpu(sse2_cpu_id)) + if (!boot_cpu_has(X86_FEATURE_XMM2) || + !boot_cpu_has(X86_FEATURE_OSXSAVE) || + !cpu_has_xfeatures(XFEATURE_MASK_SSE, NULL)) return -ENODEV; return crypto_register_aeads(crypto_morus1280_sse2_algs, diff --git a/arch/x86/crypto/morus640-sse2-asm.S b/arch/x86/crypto/morus640-sse2-asm.S index efa02816d921..414db480250e 100644 --- a/arch/x86/crypto/morus640-sse2-asm.S +++ b/arch/x86/crypto/morus640-sse2-asm.S @@ -113,7 +113,7 @@ ENDPROC(__morus640_update_zero) * %r9 */ __load_partial: - xor %r9, %r9 + xor %r9d, %r9d pxor MSG, MSG mov %rcx, %r8 diff --git a/arch/x86/crypto/morus640-sse2-glue.c b/arch/x86/crypto/morus640-sse2-glue.c index 26b47e2db8d2..615fb7bc9a32 100644 --- a/arch/x86/crypto/morus640-sse2-glue.c +++ b/arch/x86/crypto/morus640-sse2-glue.c @@ -37,15 +37,11 @@ asmlinkage void crypto_morus640_sse2_final(void *state, void *tag_xor, MORUS640_DECLARE_ALGS(sse2, "morus640-sse2", 400); -static const struct x86_cpu_id sse2_cpu_id[] = { - X86_FEATURE_MATCH(X86_FEATURE_XMM2), - {} -}; -MODULE_DEVICE_TABLE(x86cpu, sse2_cpu_id); - static int __init crypto_morus640_sse2_module_init(void) { - if (!x86_match_cpu(sse2_cpu_id)) + if (!boot_cpu_has(X86_FEATURE_XMM2) || + !boot_cpu_has(X86_FEATURE_OSXSAVE) || + !cpu_has_xfeatures(XFEATURE_MASK_SSE, NULL)) return -ENODEV; return crypto_register_aeads(crypto_morus640_sse2_algs, diff --git a/arch/x86/crypto/sha1_ssse3_asm.S b/arch/x86/crypto/sha1_ssse3_asm.S index 6204bd53528c..613d0bfc3d84 100644 --- a/arch/x86/crypto/sha1_ssse3_asm.S +++ b/arch/x86/crypto/sha1_ssse3_asm.S @@ -96,7 +96,7 @@ # cleanup workspace mov $8, %ecx mov %rsp, %rdi - xor %rax, %rax + xor %eax, %eax rep stosq mov %rbp, %rsp # deallocate workspace diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 8ae7ffda8f98..957dfb693ecc 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -92,7 +92,7 @@ END(native_usergs_sysret64) .endm .macro TRACE_IRQS_IRETQ_DEBUG - bt $9, EFLAGS(%rsp) /* interrupts off? */ + btl $9, EFLAGS(%rsp) /* interrupts off? */ jnc 1f TRACE_IRQS_ON_DEBUG 1: @@ -408,6 +408,7 @@ ENTRY(ret_from_fork) 1: /* kernel thread */ + UNWIND_HINT_EMPTY movq %r12, %rdi CALL_NOSPEC %rbx /* @@ -701,7 +702,7 @@ retint_kernel: #ifdef CONFIG_PREEMPT /* Interrupts are off */ /* Check if we need preemption */ - bt $9, EFLAGS(%rsp) /* were interrupts off? */ + btl $9, EFLAGS(%rsp) /* were interrupts off? */ jnc 1f 0: cmpl $0, PER_CPU_VAR(__preempt_count) jnz 1f diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile index 261802b1cc50..9f695f517747 100644 --- a/arch/x86/entry/vdso/Makefile +++ b/arch/x86/entry/vdso/Makefile @@ -46,10 +46,8 @@ targets += $(vdso_img_sodbg) $(vdso_img-y:%=vdso%.so) CPPFLAGS_vdso.lds += -P -C -VDSO_LDFLAGS_vdso.lds = -m64 -Wl,-soname=linux-vdso.so.1 \ - -Wl,--no-undefined \ - -Wl,-z,max-page-size=4096 -Wl,-z,common-page-size=4096 \ - $(DISABLE_LTO) +VDSO_LDFLAGS_vdso.lds = -m elf_x86_64 -soname linux-vdso.so.1 --no-undefined \ + -z max-page-size=4096 -z common-page-size=4096 $(obj)/vdso64.so.dbg: $(obj)/vdso.lds $(vobjs) FORCE $(call if_changed,vdso) @@ -58,9 +56,7 @@ HOST_EXTRACFLAGS += -I$(srctree)/tools/include -I$(srctree)/include/uapi -I$(src hostprogs-y += vdso2c quiet_cmd_vdso2c = VDSO2C $@ -define cmd_vdso2c - $(obj)/vdso2c $< $(<:%.dbg=%) $@ -endef + cmd_vdso2c = $(obj)/vdso2c $< $(<:%.dbg=%) $@ $(obj)/vdso-image-%.c: $(obj)/vdso%.so.dbg $(obj)/vdso%.so $(obj)/vdso2c FORCE $(call if_changed,vdso2c) @@ -95,10 +91,8 @@ CFLAGS_REMOVE_vvar.o = -pg # CPPFLAGS_vdsox32.lds = $(CPPFLAGS_vdso.lds) -VDSO_LDFLAGS_vdsox32.lds = -Wl,-m,elf32_x86_64 \ - -Wl,-soname=linux-vdso.so.1 \ - -Wl,-z,max-page-size=4096 \ - -Wl,-z,common-page-size=4096 +VDSO_LDFLAGS_vdsox32.lds = -m elf32_x86_64 -soname linux-vdso.so.1 \ + -z max-page-size=4096 -z common-page-size=4096 # x32-rebranded versions vobjx32s-y := $(vobjs-y:.o=-x32.o) @@ -123,7 +117,7 @@ $(obj)/vdsox32.so.dbg: $(obj)/vdsox32.lds $(vobjx32s) FORCE $(call if_changed,vdso) CPPFLAGS_vdso32.lds = $(CPPFLAGS_vdso.lds) -VDSO_LDFLAGS_vdso32.lds = -m32 -Wl,-m,elf_i386 -Wl,-soname=linux-gate.so.1 +VDSO_LDFLAGS_vdso32.lds = -m elf_i386 -soname linux-gate.so.1 targets += vdso32/vdso32.lds targets += vdso32/note.o vdso32/system_call.o vdso32/sigreturn.o @@ -157,13 +151,13 @@ $(obj)/vdso32.so.dbg: FORCE \ # The DSO images are built using a special linker script. # quiet_cmd_vdso = VDSO $@ - cmd_vdso = $(CC) -nostdlib -o $@ \ + cmd_vdso = $(LD) -nostdlib -o $@ \ $(VDSO_LDFLAGS) $(VDSO_LDFLAGS_$(filter %.lds,$(^F))) \ - -Wl,-T,$(filter %.lds,$^) $(filter %.o,$^) && \ + -T $(filter %.lds,$^) $(filter %.o,$^) && \ sh $(srctree)/$(src)/checkundef.sh '$(NM)' '$@' -VDSO_LDFLAGS = -fPIC -shared $(call cc-ldoption, -Wl$(comma)--hash-style=both) \ - $(call cc-ldoption, -Wl$(comma)--build-id) -Wl,-Bsymbolic $(LTO_CFLAGS) +VDSO_LDFLAGS = -shared $(call ld-option, --hash-style=both) \ + $(call ld-option, --build-id) -Bsymbolic GCOV_PROFILE := n # diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 86f0c15dcc2d..035c37481f57 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -2041,15 +2041,15 @@ static void intel_pmu_disable_event(struct perf_event *event) cpuc->intel_ctrl_host_mask &= ~(1ull << hwc->idx); cpuc->intel_cp_status &= ~(1ull << hwc->idx); + if (unlikely(event->attr.precise_ip)) + intel_pmu_pebs_disable(event); + if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) { intel_pmu_disable_fixed(hwc); return; } x86_pmu_disable_event(event); - - if (unlikely(event->attr.precise_ip)) - intel_pmu_pebs_disable(event); } static void intel_pmu_del_event(struct perf_event *event) @@ -2068,17 +2068,19 @@ static void intel_pmu_read_event(struct perf_event *event) x86_perf_event_update(event); } -static void intel_pmu_enable_fixed(struct hw_perf_event *hwc) +static void intel_pmu_enable_fixed(struct perf_event *event) { + struct hw_perf_event *hwc = &event->hw; int idx = hwc->idx - INTEL_PMC_IDX_FIXED; - u64 ctrl_val, bits, mask; + u64 ctrl_val, mask, bits = 0; /* - * Enable IRQ generation (0x8), + * Enable IRQ generation (0x8), if not PEBS, * and enable ring-3 counting (0x2) and ring-0 counting (0x1) * if requested: */ - bits = 0x8ULL; + if (!event->attr.precise_ip) + bits |= 0x8; if (hwc->config & ARCH_PERFMON_EVENTSEL_USR) bits |= 0x2; if (hwc->config & ARCH_PERFMON_EVENTSEL_OS) @@ -2120,14 +2122,14 @@ static void intel_pmu_enable_event(struct perf_event *event) if (unlikely(event_is_checkpointed(event))) cpuc->intel_cp_status |= (1ull << hwc->idx); + if (unlikely(event->attr.precise_ip)) + intel_pmu_pebs_enable(event); + if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) { - intel_pmu_enable_fixed(hwc); + intel_pmu_enable_fixed(event); return; } - if (unlikely(event->attr.precise_ip)) - intel_pmu_pebs_enable(event); - __x86_pmu_enable_event(hwc, ARCH_PERFMON_EVENTSEL_ENABLE); } @@ -2280,7 +2282,10 @@ again: * counters from the GLOBAL_STATUS mask and we always process PEBS * events via drain_pebs(). */ - status &= ~(cpuc->pebs_enabled & PEBS_COUNTER_MASK); + if (x86_pmu.flags & PMU_FL_PEBS_ALL) + status &= ~cpuc->pebs_enabled; + else + status &= ~(cpuc->pebs_enabled & PEBS_COUNTER_MASK); /* * PEBS overflow sets bit 62 in the global status register @@ -4072,7 +4077,6 @@ __init int intel_pmu_init(void) intel_pmu_lbr_init_skl(); x86_pmu.event_constraints = intel_slm_event_constraints; - x86_pmu.pebs_constraints = intel_glp_pebs_event_constraints; x86_pmu.extra_regs = intel_glm_extra_regs; /* * It's recommended to use CPU_CLK_UNHALTED.CORE_P + NPEBS @@ -4082,6 +4086,7 @@ __init int intel_pmu_init(void) x86_pmu.pebs_prec_dist = true; x86_pmu.lbr_pt_coexist = true; x86_pmu.flags |= PMU_FL_HAS_RSP_1; + x86_pmu.flags |= PMU_FL_PEBS_ALL; x86_pmu.get_event_constraints = glp_get_event_constraints; x86_pmu.cpu_events = glm_events_attrs; /* Goldmont Plus has 4-wide pipeline */ diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index 8dbba77e0518..b7b01d762d32 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -713,12 +713,6 @@ struct event_constraint intel_glm_pebs_event_constraints[] = { EVENT_CONSTRAINT_END }; -struct event_constraint intel_glp_pebs_event_constraints[] = { - /* Allow all events as PEBS with no flags */ - INTEL_ALL_EVENT_CONSTRAINT(0, 0xf), - EVENT_CONSTRAINT_END -}; - struct event_constraint intel_nehalem_pebs_event_constraints[] = { INTEL_PLD_CONSTRAINT(0x100b, 0xf), /* MEM_INST_RETIRED.* */ INTEL_FLAGS_EVENT_CONSTRAINT(0x0f, 0xf), /* MEM_UNCORE_RETIRED.* */ @@ -871,6 +865,13 @@ struct event_constraint *intel_pebs_constraints(struct perf_event *event) } } + /* + * Extended PEBS support + * Makes the PEBS code search the normal constraints. + */ + if (x86_pmu.flags & PMU_FL_PEBS_ALL) + return NULL; + return &emptyconstraint; } @@ -896,10 +897,16 @@ static inline void pebs_update_threshold(struct cpu_hw_events *cpuc) { struct debug_store *ds = cpuc->ds; u64 threshold; + int reserved; + + if (x86_pmu.flags & PMU_FL_PEBS_ALL) + reserved = x86_pmu.max_pebs_events + x86_pmu.num_counters_fixed; + else + reserved = x86_pmu.max_pebs_events; if (cpuc->n_pebs == cpuc->n_large_pebs) { threshold = ds->pebs_absolute_maximum - - x86_pmu.max_pebs_events * x86_pmu.pebs_record_size; + reserved * x86_pmu.pebs_record_size; } else { threshold = ds->pebs_buffer_base + x86_pmu.pebs_record_size; } @@ -963,7 +970,11 @@ void intel_pmu_pebs_enable(struct perf_event *event) * This must be done in pmu::start(), because PERF_EVENT_IOC_PERIOD. */ if (hwc->flags & PERF_X86_EVENT_AUTO_RELOAD) { - ds->pebs_event_reset[hwc->idx] = + unsigned int idx = hwc->idx; + + if (idx >= INTEL_PMC_IDX_FIXED) + idx = MAX_PEBS_EVENTS + (idx - INTEL_PMC_IDX_FIXED); + ds->pebs_event_reset[idx] = (u64)(-hwc->sample_period) & x86_pmu.cntval_mask; } else { ds->pebs_event_reset[hwc->idx] = 0; @@ -1481,9 +1492,10 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs) struct debug_store *ds = cpuc->ds; struct perf_event *event; void *base, *at, *top; - short counts[MAX_PEBS_EVENTS] = {}; - short error[MAX_PEBS_EVENTS] = {}; - int bit, i; + short counts[INTEL_PMC_IDX_FIXED + MAX_FIXED_PEBS_EVENTS] = {}; + short error[INTEL_PMC_IDX_FIXED + MAX_FIXED_PEBS_EVENTS] = {}; + int bit, i, size; + u64 mask; if (!x86_pmu.pebs_active) return; @@ -1493,6 +1505,13 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs) ds->pebs_index = ds->pebs_buffer_base; + mask = (1ULL << x86_pmu.max_pebs_events) - 1; + size = x86_pmu.max_pebs_events; + if (x86_pmu.flags & PMU_FL_PEBS_ALL) { + mask |= ((1ULL << x86_pmu.num_counters_fixed) - 1) << INTEL_PMC_IDX_FIXED; + size = INTEL_PMC_IDX_FIXED + x86_pmu.num_counters_fixed; + } + if (unlikely(base >= top)) { /* * The drain_pebs() could be called twice in a short period @@ -1502,7 +1521,7 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs) * update the event->count for this case. */ for_each_set_bit(bit, (unsigned long *)&cpuc->pebs_enabled, - x86_pmu.max_pebs_events) { + size) { event = cpuc->events[bit]; if (event->hw.flags & PERF_X86_EVENT_AUTO_RELOAD) intel_pmu_save_and_restart_reload(event, 0); @@ -1515,12 +1534,12 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs) u64 pebs_status; pebs_status = p->status & cpuc->pebs_enabled; - pebs_status &= (1ULL << x86_pmu.max_pebs_events) - 1; + pebs_status &= mask; /* PEBS v3 has more accurate status bits */ if (x86_pmu.intel_cap.pebs_format >= 3) { for_each_set_bit(bit, (unsigned long *)&pebs_status, - x86_pmu.max_pebs_events) + size) counts[bit]++; continue; @@ -1568,7 +1587,7 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs) counts[bit]++; } - for (bit = 0; bit < x86_pmu.max_pebs_events; bit++) { + for (bit = 0; bit < size; bit++) { if ((counts[bit] == 0) && (error[bit] == 0)) continue; diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c index cf372b90557e..f3e006bed9a7 100644 --- a/arch/x86/events/intel/lbr.c +++ b/arch/x86/events/intel/lbr.c @@ -216,6 +216,8 @@ static void intel_pmu_lbr_reset_64(void) void intel_pmu_lbr_reset(void) { + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + if (!x86_pmu.lbr_nr) return; @@ -223,6 +225,9 @@ void intel_pmu_lbr_reset(void) intel_pmu_lbr_reset_32(); else intel_pmu_lbr_reset_64(); + + cpuc->last_task_ctx = NULL; + cpuc->last_log_id = 0; } /* @@ -334,6 +339,7 @@ static inline u64 rdlbr_to(unsigned int idx) static void __intel_pmu_lbr_restore(struct x86_perf_task_context *task_ctx) { + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); int i; unsigned lbr_idx, mask; u64 tos; @@ -344,9 +350,21 @@ static void __intel_pmu_lbr_restore(struct x86_perf_task_context *task_ctx) return; } - mask = x86_pmu.lbr_nr - 1; tos = task_ctx->tos; - for (i = 0; i < tos; i++) { + /* + * Does not restore the LBR registers, if + * - No one else touched them, and + * - Did not enter C6 + */ + if ((task_ctx == cpuc->last_task_ctx) && + (task_ctx->log_id == cpuc->last_log_id) && + rdlbr_from(tos)) { + task_ctx->lbr_stack_state = LBR_NONE; + return; + } + + mask = x86_pmu.lbr_nr - 1; + for (i = 0; i < task_ctx->valid_lbrs; i++) { lbr_idx = (tos - i) & mask; wrlbr_from(lbr_idx, task_ctx->lbr_from[i]); wrlbr_to (lbr_idx, task_ctx->lbr_to[i]); @@ -354,14 +372,24 @@ static void __intel_pmu_lbr_restore(struct x86_perf_task_context *task_ctx) if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO) wrmsrl(MSR_LBR_INFO_0 + lbr_idx, task_ctx->lbr_info[i]); } + + for (; i < x86_pmu.lbr_nr; i++) { + lbr_idx = (tos - i) & mask; + wrlbr_from(lbr_idx, 0); + wrlbr_to(lbr_idx, 0); + if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO) + wrmsrl(MSR_LBR_INFO_0 + lbr_idx, 0); + } + wrmsrl(x86_pmu.lbr_tos, tos); task_ctx->lbr_stack_state = LBR_NONE; } static void __intel_pmu_lbr_save(struct x86_perf_task_context *task_ctx) { + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); unsigned lbr_idx, mask; - u64 tos; + u64 tos, from; int i; if (task_ctx->lbr_callstack_users == 0) { @@ -371,15 +399,22 @@ static void __intel_pmu_lbr_save(struct x86_perf_task_context *task_ctx) mask = x86_pmu.lbr_nr - 1; tos = intel_pmu_lbr_tos(); - for (i = 0; i < tos; i++) { + for (i = 0; i < x86_pmu.lbr_nr; i++) { lbr_idx = (tos - i) & mask; - task_ctx->lbr_from[i] = rdlbr_from(lbr_idx); + from = rdlbr_from(lbr_idx); + if (!from) + break; + task_ctx->lbr_from[i] = from; task_ctx->lbr_to[i] = rdlbr_to(lbr_idx); if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO) rdmsrl(MSR_LBR_INFO_0 + lbr_idx, task_ctx->lbr_info[i]); } + task_ctx->valid_lbrs = i; task_ctx->tos = tos; task_ctx->lbr_stack_state = LBR_VALID; + + cpuc->last_task_ctx = task_ctx; + cpuc->last_log_id = ++task_ctx->log_id; } void intel_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in) @@ -531,7 +566,7 @@ static void intel_pmu_lbr_read_32(struct cpu_hw_events *cpuc) */ static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc) { - bool need_info = false; + bool need_info = false, call_stack = false; unsigned long mask = x86_pmu.lbr_nr - 1; int lbr_format = x86_pmu.intel_cap.lbr_format; u64 tos = intel_pmu_lbr_tos(); @@ -542,7 +577,7 @@ static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc) if (cpuc->lbr_sel) { need_info = !(cpuc->lbr_sel->config & LBR_NO_INFO); if (cpuc->lbr_sel->config & LBR_CALL_STACK) - num = tos; + call_stack = true; } for (i = 0; i < num; i++) { @@ -555,6 +590,13 @@ static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc) from = rdlbr_from(lbr_idx); to = rdlbr_to(lbr_idx); + /* + * Read LBR call stack entries + * until invalid entry (0s) is detected. + */ + if (call_stack && !from) + break; + if (lbr_format == LBR_FORMAT_INFO && need_info) { u64 info; diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index 9f3711470ec1..156286335351 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -163,6 +163,7 @@ struct intel_excl_cntrs { unsigned core_id; /* per-core: core id */ }; +struct x86_perf_task_context; #define MAX_LBR_ENTRIES 32 enum { @@ -214,6 +215,8 @@ struct cpu_hw_events { struct perf_branch_entry lbr_entries[MAX_LBR_ENTRIES]; struct er_account *lbr_sel; u64 br_sel; + struct x86_perf_task_context *last_task_ctx; + int last_log_id; /* * Intel host/guest exclude bits @@ -648,8 +651,10 @@ struct x86_perf_task_context { u64 lbr_to[MAX_LBR_ENTRIES]; u64 lbr_info[MAX_LBR_ENTRIES]; int tos; + int valid_lbrs; int lbr_callstack_users; int lbr_stack_state; + int log_id; }; #define x86_add_quirk(func_) \ @@ -668,6 +673,7 @@ do { \ #define PMU_FL_HAS_RSP_1 0x2 /* has 2 equivalent offcore_rsp regs */ #define PMU_FL_EXCL_CNTRS 0x4 /* has exclusive counter requirements */ #define PMU_FL_EXCL_ENABLED 0x8 /* exclusive counter active */ +#define PMU_FL_PEBS_ALL 0x10 /* all events are valid PEBS events */ #define EVENT_VAR(_id) event_attr_##_id #define EVENT_PTR(_id) &event_attr_##_id.attr.attr diff --git a/arch/x86/hyperv/hv_apic.c b/arch/x86/hyperv/hv_apic.c index 402338365651..5b0f613428c2 100644 --- a/arch/x86/hyperv/hv_apic.c +++ b/arch/x86/hyperv/hv_apic.c @@ -31,6 +31,8 @@ #include <asm/mshyperv.h> #include <asm/apic.h> +#include <asm/trace/hyperv.h> + static struct apic orig_apic; static u64 hv_apic_icr_read(void) @@ -99,6 +101,9 @@ static bool __send_ipi_mask_ex(const struct cpumask *mask, int vector) int nr_bank = 0; int ret = 1; + if (!(ms_hyperv.hints & HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED)) + return false; + local_irq_save(flags); arg = (struct ipi_arg_ex **)this_cpu_ptr(hyperv_pcpu_input_arg); @@ -130,10 +135,10 @@ ipi_mask_ex_done: static bool __send_ipi_mask(const struct cpumask *mask, int vector) { int cur_cpu, vcpu; - struct ipi_arg_non_ex **arg; - struct ipi_arg_non_ex *ipi_arg; + struct ipi_arg_non_ex ipi_arg; int ret = 1; - unsigned long flags; + + trace_hyperv_send_ipi_mask(mask, vector); if (cpumask_empty(mask)) return true; @@ -144,40 +149,43 @@ static bool __send_ipi_mask(const struct cpumask *mask, int vector) if ((vector < HV_IPI_LOW_VECTOR) || (vector > HV_IPI_HIGH_VECTOR)) return false; - if ((ms_hyperv.hints & HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED)) - return __send_ipi_mask_ex(mask, vector); - - local_irq_save(flags); - arg = (struct ipi_arg_non_ex **)this_cpu_ptr(hyperv_pcpu_input_arg); - - ipi_arg = *arg; - if (unlikely(!ipi_arg)) - goto ipi_mask_done; - - ipi_arg->vector = vector; - ipi_arg->reserved = 0; - ipi_arg->cpu_mask = 0; + /* + * From the supplied CPU set we need to figure out if we can get away + * with cheaper HVCALL_SEND_IPI hypercall. This is possible when the + * highest VP number in the set is < 64. As VP numbers are usually in + * ascending order and match Linux CPU ids, here is an optimization: + * we check the VP number for the highest bit in the supplied set first + * so we can quickly find out if using HVCALL_SEND_IPI_EX hypercall is + * a must. We will also check all VP numbers when walking the supplied + * CPU set to remain correct in all cases. + */ + if (hv_cpu_number_to_vp_number(cpumask_last(mask)) >= 64) + goto do_ex_hypercall; + + ipi_arg.vector = vector; + ipi_arg.cpu_mask = 0; for_each_cpu(cur_cpu, mask) { vcpu = hv_cpu_number_to_vp_number(cur_cpu); if (vcpu == VP_INVAL) - goto ipi_mask_done; + return false; /* * This particular version of the IPI hypercall can * only target upto 64 CPUs. */ if (vcpu >= 64) - goto ipi_mask_done; + goto do_ex_hypercall; - __set_bit(vcpu, (unsigned long *)&ipi_arg->cpu_mask); + __set_bit(vcpu, (unsigned long *)&ipi_arg.cpu_mask); } - ret = hv_do_hypercall(HVCALL_SEND_IPI, ipi_arg, NULL); - -ipi_mask_done: - local_irq_restore(flags); + ret = hv_do_fast_hypercall16(HVCALL_SEND_IPI, ipi_arg.vector, + ipi_arg.cpu_mask); return ((ret == 0) ? true : false); + +do_ex_hypercall: + return __send_ipi_mask_ex(mask, vector); } static bool __send_ipi_one(int cpu, int vector) @@ -233,10 +241,7 @@ static void hv_send_ipi_self(int vector) void __init hv_apic_init(void) { if (ms_hyperv.hints & HV_X64_CLUSTER_IPI_RECOMMENDED) { - if ((ms_hyperv.hints & HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED)) - pr_info("Hyper-V: Using ext hypercalls for IPI\n"); - else - pr_info("Hyper-V: Using IPI hypercalls\n"); + pr_info("Hyper-V: Using IPI hypercalls\n"); /* * Set the IPI entry points. */ diff --git a/arch/x86/hyperv/mmu.c b/arch/x86/hyperv/mmu.c index de27615c51ea..1147e1fed7ff 100644 --- a/arch/x86/hyperv/mmu.c +++ b/arch/x86/hyperv/mmu.c @@ -16,6 +16,8 @@ /* Each gva in gva_list encodes up to 4096 pages to flush */ #define HV_TLB_FLUSH_UNIT (4096 * PAGE_SIZE) +static u64 hyperv_flush_tlb_others_ex(const struct cpumask *cpus, + const struct flush_tlb_info *info); /* * Fills in gva_list starting from offset. Returns the number of items added. @@ -93,10 +95,29 @@ static void hyperv_flush_tlb_others(const struct cpumask *cpus, if (cpumask_equal(cpus, cpu_present_mask)) { flush->flags |= HV_FLUSH_ALL_PROCESSORS; } else { + /* + * From the supplied CPU set we need to figure out if we can get + * away with cheaper HVCALL_FLUSH_VIRTUAL_ADDRESS_{LIST,SPACE} + * hypercalls. This is possible when the highest VP number in + * the set is < 64. As VP numbers are usually in ascending order + * and match Linux CPU ids, here is an optimization: we check + * the VP number for the highest bit in the supplied set first + * so we can quickly find out if using *_EX hypercalls is a + * must. We will also check all VP numbers when walking the + * supplied CPU set to remain correct in all cases. + */ + if (hv_cpu_number_to_vp_number(cpumask_last(cpus)) >= 64) + goto do_ex_hypercall; + for_each_cpu(cpu, cpus) { vcpu = hv_cpu_number_to_vp_number(cpu); - if (vcpu >= 64) + if (vcpu == VP_INVAL) { + local_irq_restore(flags); goto do_native; + } + + if (vcpu >= 64) + goto do_ex_hypercall; __set_bit(vcpu, (unsigned long *) &flush->processor_mask); @@ -123,7 +144,12 @@ static void hyperv_flush_tlb_others(const struct cpumask *cpus, status = hv_do_rep_hypercall(HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST, gva_n, 0, flush, NULL); } + goto check_status; + +do_ex_hypercall: + status = hyperv_flush_tlb_others_ex(cpus, info); +check_status: local_irq_restore(flags); if (!(status & HV_HYPERCALL_RESULT_MASK)) @@ -132,35 +158,22 @@ do_native: native_flush_tlb_others(cpus, info); } -static void hyperv_flush_tlb_others_ex(const struct cpumask *cpus, - const struct flush_tlb_info *info) +static u64 hyperv_flush_tlb_others_ex(const struct cpumask *cpus, + const struct flush_tlb_info *info) { int nr_bank = 0, max_gvas, gva_n; struct hv_tlb_flush_ex **flush_pcpu; struct hv_tlb_flush_ex *flush; - u64 status = U64_MAX; - unsigned long flags; + u64 status; - trace_hyperv_mmu_flush_tlb_others(cpus, info); - - if (!hv_hypercall_pg) - goto do_native; - - if (cpumask_empty(cpus)) - return; - - local_irq_save(flags); + if (!(ms_hyperv.hints & HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED)) + return U64_MAX; flush_pcpu = (struct hv_tlb_flush_ex **) this_cpu_ptr(hyperv_pcpu_input_arg); flush = *flush_pcpu; - if (unlikely(!flush)) { - local_irq_restore(flags); - goto do_native; - } - if (info->mm) { /* * AddressSpace argument must match the CR3 with PCID bits @@ -176,15 +189,10 @@ static void hyperv_flush_tlb_others_ex(const struct cpumask *cpus, flush->hv_vp_set.valid_bank_mask = 0; - if (!cpumask_equal(cpus, cpu_present_mask)) { - flush->hv_vp_set.format = HV_GENERIC_SET_SPARSE_4K; - nr_bank = cpumask_to_vpset(&(flush->hv_vp_set), cpus); - } - - if (!nr_bank) { - flush->hv_vp_set.format = HV_GENERIC_SET_ALL; - flush->flags |= HV_FLUSH_ALL_PROCESSORS; - } + flush->hv_vp_set.format = HV_GENERIC_SET_SPARSE_4K; + nr_bank = cpumask_to_vpset(&(flush->hv_vp_set), cpus); + if (nr_bank < 0) + return U64_MAX; /* * We can flush not more than max_gvas with one hypercall. Flush the @@ -213,12 +221,7 @@ static void hyperv_flush_tlb_others_ex(const struct cpumask *cpus, gva_n, nr_bank, flush, NULL); } - local_irq_restore(flags); - - if (!(status & HV_HYPERCALL_RESULT_MASK)) - return; -do_native: - native_flush_tlb_others(cpus, info); + return status; } void hyperv_setup_mmu_ops(void) @@ -226,11 +229,6 @@ void hyperv_setup_mmu_ops(void) if (!(ms_hyperv.hints & HV_X64_REMOTE_TLB_FLUSH_RECOMMENDED)) return; - if (!(ms_hyperv.hints & HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED)) { - pr_info("Using hypercall for remote TLB flush\n"); - pv_mmu_ops.flush_tlb_others = hyperv_flush_tlb_others; - } else { - pr_info("Using ext hypercall for remote TLB flush\n"); - pv_mmu_ops.flush_tlb_others = hyperv_flush_tlb_others_ex; - } + pr_info("Using hypercall for remote TLB flush\n"); + pv_mmu_ops.flush_tlb_others = hyperv_flush_tlb_others; } diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h index 0db6bec95489..b143717b92b3 100644 --- a/arch/x86/include/asm/atomic.h +++ b/arch/x86/include/asm/atomic.h @@ -80,6 +80,7 @@ static __always_inline void arch_atomic_sub(int i, atomic_t *v) * true if the result is zero, or false for all * other cases. */ +#define arch_atomic_sub_and_test arch_atomic_sub_and_test static __always_inline bool arch_atomic_sub_and_test(int i, atomic_t *v) { GEN_BINARY_RMWcc(LOCK_PREFIX "subl", v->counter, "er", i, "%0", e); @@ -91,6 +92,7 @@ static __always_inline bool arch_atomic_sub_and_test(int i, atomic_t *v) * * Atomically increments @v by 1. */ +#define arch_atomic_inc arch_atomic_inc static __always_inline void arch_atomic_inc(atomic_t *v) { asm volatile(LOCK_PREFIX "incl %0" @@ -103,6 +105,7 @@ static __always_inline void arch_atomic_inc(atomic_t *v) * * Atomically decrements @v by 1. */ +#define arch_atomic_dec arch_atomic_dec static __always_inline void arch_atomic_dec(atomic_t *v) { asm volatile(LOCK_PREFIX "decl %0" @@ -117,6 +120,7 @@ static __always_inline void arch_atomic_dec(atomic_t *v) * returns true if the result is 0, or false for all other * cases. */ +#define arch_atomic_dec_and_test arch_atomic_dec_and_test static __always_inline bool arch_atomic_dec_and_test(atomic_t *v) { GEN_UNARY_RMWcc(LOCK_PREFIX "decl", v->counter, "%0", e); @@ -130,6 +134,7 @@ static __always_inline bool arch_atomic_dec_and_test(atomic_t *v) * and returns true if the result is zero, or false for all * other cases. */ +#define arch_atomic_inc_and_test arch_atomic_inc_and_test static __always_inline bool arch_atomic_inc_and_test(atomic_t *v) { GEN_UNARY_RMWcc(LOCK_PREFIX "incl", v->counter, "%0", e); @@ -144,6 +149,7 @@ static __always_inline bool arch_atomic_inc_and_test(atomic_t *v) * if the result is negative, or false when * result is greater than or equal to zero. */ +#define arch_atomic_add_negative arch_atomic_add_negative static __always_inline bool arch_atomic_add_negative(int i, atomic_t *v) { GEN_BINARY_RMWcc(LOCK_PREFIX "addl", v->counter, "er", i, "%0", s); @@ -173,9 +179,6 @@ static __always_inline int arch_atomic_sub_return(int i, atomic_t *v) return arch_atomic_add_return(-i, v); } -#define arch_atomic_inc_return(v) (arch_atomic_add_return(1, v)) -#define arch_atomic_dec_return(v) (arch_atomic_sub_return(1, v)) - static __always_inline int arch_atomic_fetch_add(int i, atomic_t *v) { return xadd(&v->counter, i); @@ -199,7 +202,7 @@ static __always_inline bool arch_atomic_try_cmpxchg(atomic_t *v, int *old, int n static inline int arch_atomic_xchg(atomic_t *v, int new) { - return xchg(&v->counter, new); + return arch_xchg(&v->counter, new); } static inline void arch_atomic_and(int i, atomic_t *v) @@ -253,27 +256,6 @@ static inline int arch_atomic_fetch_xor(int i, atomic_t *v) return val; } -/** - * __arch_atomic_add_unless - add unless the number is already a given value - * @v: pointer of type atomic_t - * @a: the amount to add to v... - * @u: ...unless v is equal to u. - * - * Atomically adds @a to @v, so long as @v was not already @u. - * Returns the old value of @v. - */ -static __always_inline int __arch_atomic_add_unless(atomic_t *v, int a, int u) -{ - int c = arch_atomic_read(v); - - do { - if (unlikely(c == u)) - break; - } while (!arch_atomic_try_cmpxchg(v, &c, c + a)); - - return c; -} - #ifdef CONFIG_X86_32 # include <asm/atomic64_32.h> #else diff --git a/arch/x86/include/asm/atomic64_32.h b/arch/x86/include/asm/atomic64_32.h index 92212bf0484f..ef959f02d070 100644 --- a/arch/x86/include/asm/atomic64_32.h +++ b/arch/x86/include/asm/atomic64_32.h @@ -158,6 +158,7 @@ static inline long long arch_atomic64_inc_return(atomic64_t *v) "S" (v) : "memory", "ecx"); return a; } +#define arch_atomic64_inc_return arch_atomic64_inc_return static inline long long arch_atomic64_dec_return(atomic64_t *v) { @@ -166,6 +167,7 @@ static inline long long arch_atomic64_dec_return(atomic64_t *v) "S" (v) : "memory", "ecx"); return a; } +#define arch_atomic64_dec_return arch_atomic64_dec_return /** * arch_atomic64_add - add integer to atomic64 variable @@ -198,25 +200,12 @@ static inline long long arch_atomic64_sub(long long i, atomic64_t *v) } /** - * arch_atomic64_sub_and_test - subtract value from variable and test result - * @i: integer value to subtract - * @v: pointer to type atomic64_t - * - * Atomically subtracts @i from @v and returns - * true if the result is zero, or false for all - * other cases. - */ -static inline int arch_atomic64_sub_and_test(long long i, atomic64_t *v) -{ - return arch_atomic64_sub_return(i, v) == 0; -} - -/** * arch_atomic64_inc - increment atomic64 variable * @v: pointer to type atomic64_t * * Atomically increments @v by 1. */ +#define arch_atomic64_inc arch_atomic64_inc static inline void arch_atomic64_inc(atomic64_t *v) { __alternative_atomic64(inc, inc_return, /* no output */, @@ -229,6 +218,7 @@ static inline void arch_atomic64_inc(atomic64_t *v) * * Atomically decrements @v by 1. */ +#define arch_atomic64_dec arch_atomic64_dec static inline void arch_atomic64_dec(atomic64_t *v) { __alternative_atomic64(dec, dec_return, /* no output */, @@ -236,46 +226,6 @@ static inline void arch_atomic64_dec(atomic64_t *v) } /** - * arch_atomic64_dec_and_test - decrement and test - * @v: pointer to type atomic64_t - * - * Atomically decrements @v by 1 and - * returns true if the result is 0, or false for all other - * cases. - */ -static inline int arch_atomic64_dec_and_test(atomic64_t *v) -{ - return arch_atomic64_dec_return(v) == 0; -} - -/** - * atomic64_inc_and_test - increment and test - * @v: pointer to type atomic64_t - * - * Atomically increments @v by 1 - * and returns true if the result is zero, or false for all - * other cases. - */ -static inline int arch_atomic64_inc_and_test(atomic64_t *v) -{ - return arch_atomic64_inc_return(v) == 0; -} - -/** - * arch_atomic64_add_negative - add and test if negative - * @i: integer value to add - * @v: pointer to type atomic64_t - * - * Atomically adds @i to @v and returns true - * if the result is negative, or false when - * result is greater than or equal to zero. - */ -static inline int arch_atomic64_add_negative(long long i, atomic64_t *v) -{ - return arch_atomic64_add_return(i, v) < 0; -} - -/** * arch_atomic64_add_unless - add unless the number is a given value * @v: pointer of type atomic64_t * @a: the amount to add to v... @@ -295,7 +245,7 @@ static inline int arch_atomic64_add_unless(atomic64_t *v, long long a, return (int)a; } - +#define arch_atomic64_inc_not_zero arch_atomic64_inc_not_zero static inline int arch_atomic64_inc_not_zero(atomic64_t *v) { int r; @@ -304,6 +254,7 @@ static inline int arch_atomic64_inc_not_zero(atomic64_t *v) return r; } +#define arch_atomic64_dec_if_positive arch_atomic64_dec_if_positive static inline long long arch_atomic64_dec_if_positive(atomic64_t *v) { long long r; diff --git a/arch/x86/include/asm/atomic64_64.h b/arch/x86/include/asm/atomic64_64.h index 6106b59d3260..4343d9b4f30e 100644 --- a/arch/x86/include/asm/atomic64_64.h +++ b/arch/x86/include/asm/atomic64_64.h @@ -71,6 +71,7 @@ static inline void arch_atomic64_sub(long i, atomic64_t *v) * true if the result is zero, or false for all * other cases. */ +#define arch_atomic64_sub_and_test arch_atomic64_sub_and_test static inline bool arch_atomic64_sub_and_test(long i, atomic64_t *v) { GEN_BINARY_RMWcc(LOCK_PREFIX "subq", v->counter, "er", i, "%0", e); @@ -82,6 +83,7 @@ static inline bool arch_atomic64_sub_and_test(long i, atomic64_t *v) * * Atomically increments @v by 1. */ +#define arch_atomic64_inc arch_atomic64_inc static __always_inline void arch_atomic64_inc(atomic64_t *v) { asm volatile(LOCK_PREFIX "incq %0" @@ -95,6 +97,7 @@ static __always_inline void arch_atomic64_inc(atomic64_t *v) * * Atomically decrements @v by 1. */ +#define arch_atomic64_dec arch_atomic64_dec static __always_inline void arch_atomic64_dec(atomic64_t *v) { asm volatile(LOCK_PREFIX "decq %0" @@ -110,6 +113,7 @@ static __always_inline void arch_atomic64_dec(atomic64_t *v) * returns true if the result is 0, or false for all other * cases. */ +#define arch_atomic64_dec_and_test arch_atomic64_dec_and_test static inline bool arch_atomic64_dec_and_test(atomic64_t *v) { GEN_UNARY_RMWcc(LOCK_PREFIX "decq", v->counter, "%0", e); @@ -123,6 +127,7 @@ static inline bool arch_atomic64_dec_and_test(atomic64_t *v) * and returns true if the result is zero, or false for all * other cases. */ +#define arch_atomic64_inc_and_test arch_atomic64_inc_and_test static inline bool arch_atomic64_inc_and_test(atomic64_t *v) { GEN_UNARY_RMWcc(LOCK_PREFIX "incq", v->counter, "%0", e); @@ -137,6 +142,7 @@ static inline bool arch_atomic64_inc_and_test(atomic64_t *v) * if the result is negative, or false when * result is greater than or equal to zero. */ +#define arch_atomic64_add_negative arch_atomic64_add_negative static inline bool arch_atomic64_add_negative(long i, atomic64_t *v) { GEN_BINARY_RMWcc(LOCK_PREFIX "addq", v->counter, "er", i, "%0", s); @@ -169,9 +175,6 @@ static inline long arch_atomic64_fetch_sub(long i, atomic64_t *v) return xadd(&v->counter, -i); } -#define arch_atomic64_inc_return(v) (arch_atomic64_add_return(1, (v))) -#define arch_atomic64_dec_return(v) (arch_atomic64_sub_return(1, (v))) - static inline long arch_atomic64_cmpxchg(atomic64_t *v, long old, long new) { return arch_cmpxchg(&v->counter, old, new); @@ -185,46 +188,7 @@ static __always_inline bool arch_atomic64_try_cmpxchg(atomic64_t *v, s64 *old, l static inline long arch_atomic64_xchg(atomic64_t *v, long new) { - return xchg(&v->counter, new); -} - -/** - * arch_atomic64_add_unless - add unless the number is a given value - * @v: pointer of type atomic64_t - * @a: the amount to add to v... - * @u: ...unless v is equal to u. - * - * Atomically adds @a to @v, so long as it was not @u. - * Returns the old value of @v. - */ -static inline bool arch_atomic64_add_unless(atomic64_t *v, long a, long u) -{ - s64 c = arch_atomic64_read(v); - do { - if (unlikely(c == u)) - return false; - } while (!arch_atomic64_try_cmpxchg(v, &c, c + a)); - return true; -} - -#define arch_atomic64_inc_not_zero(v) arch_atomic64_add_unless((v), 1, 0) - -/* - * arch_atomic64_dec_if_positive - decrement by 1 if old value positive - * @v: pointer of type atomic_t - * - * The function returns the old value of *v minus 1, even if - * the atomic variable, v, was not decremented. - */ -static inline long arch_atomic64_dec_if_positive(atomic64_t *v) -{ - s64 dec, c = arch_atomic64_read(v); - do { - dec = c - 1; - if (unlikely(dec < 0)) - break; - } while (!arch_atomic64_try_cmpxchg(v, &c, dec)); - return dec; + return arch_xchg(&v->counter, new); } static inline void arch_atomic64_and(long i, atomic64_t *v) diff --git a/arch/x86/include/asm/cmpxchg.h b/arch/x86/include/asm/cmpxchg.h index e3efd8a06066..a55d79b233d3 100644 --- a/arch/x86/include/asm/cmpxchg.h +++ b/arch/x86/include/asm/cmpxchg.h @@ -75,7 +75,7 @@ extern void __add_wrong_size(void) * use "asm volatile" and "memory" clobbers to prevent gcc from moving * information around. */ -#define xchg(ptr, v) __xchg_op((ptr), (v), xchg, "") +#define arch_xchg(ptr, v) __xchg_op((ptr), (v), xchg, "") /* * Atomic compare and exchange. Compare OLD with MEM, if identical, diff --git a/arch/x86/include/asm/cmpxchg_64.h b/arch/x86/include/asm/cmpxchg_64.h index bfca3b346c74..072e5459fe2f 100644 --- a/arch/x86/include/asm/cmpxchg_64.h +++ b/arch/x86/include/asm/cmpxchg_64.h @@ -10,13 +10,13 @@ static inline void set_64bit(volatile u64 *ptr, u64 val) #define arch_cmpxchg64(ptr, o, n) \ ({ \ BUILD_BUG_ON(sizeof(*(ptr)) != 8); \ - cmpxchg((ptr), (o), (n)); \ + arch_cmpxchg((ptr), (o), (n)); \ }) #define arch_cmpxchg64_local(ptr, o, n) \ ({ \ BUILD_BUG_ON(sizeof(*(ptr)) != 8); \ - cmpxchg_local((ptr), (o), (n)); \ + arch_cmpxchg_local((ptr), (o), (n)); \ }) #define system_has_cmpxchg_double() boot_cpu_has(X86_FEATURE_CX16) diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 2687cd8e8d58..b5c60faf8429 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -230,7 +230,7 @@ #define X86_FEATURE_VMMCALL ( 8*32+15) /* Prefer VMMCALL to VMCALL */ #define X86_FEATURE_XENPV ( 8*32+16) /* "" Xen paravirtual guest */ - +#define X86_FEATURE_EPT_AD ( 8*32+17) /* Intel Extended Page Table access-dirty bit */ /* Intel-defined CPU features, CPUID level 0x00000007:0 (EBX), word 9 */ #define X86_FEATURE_FSGSBASE ( 9*32+ 0) /* RDFSBASE, WRFSBASE, RDGSBASE, WRGSBASE instructions*/ diff --git a/arch/x86/include/asm/hw_breakpoint.h b/arch/x86/include/asm/hw_breakpoint.h index f59c39835a5a..a1f0e90d0818 100644 --- a/arch/x86/include/asm/hw_breakpoint.h +++ b/arch/x86/include/asm/hw_breakpoint.h @@ -49,11 +49,14 @@ static inline int hw_breakpoint_slots(int type) return HBP_NUM; } +struct perf_event_attr; struct perf_event; struct pmu; -extern int arch_check_bp_in_kernelspace(struct perf_event *bp); -extern int arch_validate_hwbkpt_settings(struct perf_event *bp); +extern int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw); +extern int hw_breakpoint_arch_parse(struct perf_event *bp, + const struct perf_event_attr *attr, + struct arch_hw_breakpoint *hw); extern int hw_breakpoint_exceptions_notify(struct notifier_block *unused, unsigned long val, void *data); diff --git a/arch/x86/include/asm/intel_ds.h b/arch/x86/include/asm/intel_ds.h index 62a9f4966b42..ae26df1c2789 100644 --- a/arch/x86/include/asm/intel_ds.h +++ b/arch/x86/include/asm/intel_ds.h @@ -8,6 +8,7 @@ /* The maximal number of PEBS events: */ #define MAX_PEBS_EVENTS 8 +#define MAX_FIXED_PEBS_EVENTS 3 /* * A debug store configuration. @@ -23,7 +24,7 @@ struct debug_store { u64 pebs_index; u64 pebs_absolute_maximum; u64 pebs_interrupt_threshold; - u64 pebs_event_reset[MAX_PEBS_EVENTS]; + u64 pebs_event_reset[MAX_PEBS_EVENTS + MAX_FIXED_PEBS_EVENTS]; } __aligned(PAGE_SIZE); DECLARE_PER_CPU_PAGE_ALIGNED(struct debug_store, cpu_debug_store); diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h index c4fc17220df9..c14f2a74b2be 100644 --- a/arch/x86/include/asm/irqflags.h +++ b/arch/x86/include/asm/irqflags.h @@ -13,6 +13,8 @@ * Interrupt control: */ +/* Declaration required for gcc < 4.9 to prevent -Werror=missing-prototypes */ +extern inline unsigned long native_save_fl(void); extern inline unsigned long native_save_fl(void) { unsigned long flags; diff --git a/arch/x86/include/asm/kprobes.h b/arch/x86/include/asm/kprobes.h index 367d99cff426..c8cec1b39b88 100644 --- a/arch/x86/include/asm/kprobes.h +++ b/arch/x86/include/asm/kprobes.h @@ -78,7 +78,7 @@ struct arch_specific_insn { * boostable = true: This instruction has been boosted: we have * added a relative jump after the instruction copy in insn, * so no single-step and fixup are needed (unless there's - * a post_handler or break_handler). + * a post_handler). */ bool boostable; bool if_modifier; @@ -111,9 +111,6 @@ struct kprobe_ctlblk { unsigned long kprobe_status; unsigned long kprobe_old_flags; unsigned long kprobe_saved_flags; - unsigned long *jprobe_saved_sp; - struct pt_regs jprobe_saved_regs; - kprobe_opcode_t jprobes_stack[MAX_STACK_SIZE]; struct prev_kprobe prev_kprobe; }; diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h index 5a7375ed5f7c..19886fef1dfc 100644 --- a/arch/x86/include/asm/mshyperv.h +++ b/arch/x86/include/asm/mshyperv.h @@ -194,6 +194,40 @@ static inline u64 hv_do_fast_hypercall8(u16 code, u64 input1) return hv_status; } +/* Fast hypercall with 16 bytes of input */ +static inline u64 hv_do_fast_hypercall16(u16 code, u64 input1, u64 input2) +{ + u64 hv_status, control = (u64)code | HV_HYPERCALL_FAST_BIT; + +#ifdef CONFIG_X86_64 + { + __asm__ __volatile__("mov %4, %%r8\n" + CALL_NOSPEC + : "=a" (hv_status), ASM_CALL_CONSTRAINT, + "+c" (control), "+d" (input1) + : "r" (input2), + THUNK_TARGET(hv_hypercall_pg) + : "cc", "r8", "r9", "r10", "r11"); + } +#else + { + u32 input1_hi = upper_32_bits(input1); + u32 input1_lo = lower_32_bits(input1); + u32 input2_hi = upper_32_bits(input2); + u32 input2_lo = lower_32_bits(input2); + + __asm__ __volatile__ (CALL_NOSPEC + : "=A"(hv_status), + "+c"(input1_lo), ASM_CALL_CONSTRAINT + : "A" (control), "b" (input1_hi), + "D"(input2_hi), "S"(input2_lo), + THUNK_TARGET(hv_hypercall_pg) + : "cc"); + } +#endif + return hv_status; +} + /* * Rep hypercalls. Callers of this functions are supposed to ensure that * rep_count and varhead_size comply with Hyper-V hypercall definition. diff --git a/arch/x86/include/asm/orc_types.h b/arch/x86/include/asm/orc_types.h index 9c9dc579bd7d..46f516dd80ce 100644 --- a/arch/x86/include/asm/orc_types.h +++ b/arch/x86/include/asm/orc_types.h @@ -88,6 +88,7 @@ struct orc_entry { unsigned sp_reg:4; unsigned bp_reg:4; unsigned type:2; + unsigned end:1; } __packed; /* @@ -101,6 +102,7 @@ struct unwind_hint { s16 sp_offset; u8 sp_reg; u8 type; + u8 end; }; #endif /* __ASSEMBLY__ */ diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h index a06b07399d17..e9202a0de8f0 100644 --- a/arch/x86/include/asm/percpu.h +++ b/arch/x86/include/asm/percpu.h @@ -450,9 +450,10 @@ do { \ bool __ret; \ typeof(pcp1) __o1 = (o1), __n1 = (n1); \ typeof(pcp2) __o2 = (o2), __n2 = (n2); \ - asm volatile("cmpxchg8b "__percpu_arg(1)"\n\tsetz %0\n\t" \ - : "=a" (__ret), "+m" (pcp1), "+m" (pcp2), "+d" (__o2) \ - : "b" (__n1), "c" (__n2), "a" (__o1)); \ + asm volatile("cmpxchg8b "__percpu_arg(1) \ + CC_SET(z) \ + : CC_OUT(z) (__ret), "+m" (pcp1), "+m" (pcp2), "+a" (__o1), "+d" (__o2) \ + : "b" (__n1), "c" (__n2)); \ __ret; \ }) diff --git a/arch/x86/include/asm/refcount.h b/arch/x86/include/asm/refcount.h index 4cf11d88d3b3..19b90521954c 100644 --- a/arch/x86/include/asm/refcount.h +++ b/arch/x86/include/asm/refcount.h @@ -5,6 +5,7 @@ * PaX/grsecurity. */ #include <linux/refcount.h> +#include <asm/bug.h> /* * This is the first portion of the refcount error handling, which lives in diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h index 6690cd3fc8b1..511bf5fae8b8 100644 --- a/arch/x86/include/asm/tlbflush.h +++ b/arch/x86/include/asm/tlbflush.h @@ -148,22 +148,6 @@ static inline unsigned long build_cr3_noflush(pgd_t *pgd, u16 asid) #define __flush_tlb_one_user(addr) __native_flush_tlb_one_user(addr) #endif -static inline bool tlb_defer_switch_to_init_mm(void) -{ - /* - * If we have PCID, then switching to init_mm is reasonably - * fast. If we don't have PCID, then switching to init_mm is - * quite slow, so we try to defer it in the hopes that we can - * avoid it entirely. The latter approach runs the risk of - * receiving otherwise unnecessary IPIs. - * - * This choice is just a heuristic. The tlb code can handle this - * function returning true or false regardless of whether we have - * PCID. - */ - return !static_cpu_has(X86_FEATURE_PCID); -} - struct tlb_context { u64 ctx_id; u64 tlb_gen; @@ -554,4 +538,9 @@ extern void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch); native_flush_tlb_others(mask, info) #endif +extern void tlb_flush_remove_tables(struct mm_struct *mm); +extern void tlb_flush_remove_tables_local(void *arg); + +#define HAVE_TLB_FLUSH_REMOVE_TABLES + #endif /* _ASM_X86_TLBFLUSH_H */ diff --git a/arch/x86/include/asm/trace/hyperv.h b/arch/x86/include/asm/trace/hyperv.h index 4253bca99989..9c0d4b588e3f 100644 --- a/arch/x86/include/asm/trace/hyperv.h +++ b/arch/x86/include/asm/trace/hyperv.h @@ -28,6 +28,21 @@ TRACE_EVENT(hyperv_mmu_flush_tlb_others, __entry->addr, __entry->end) ); +TRACE_EVENT(hyperv_send_ipi_mask, + TP_PROTO(const struct cpumask *cpus, + int vector), + TP_ARGS(cpus, vector), + TP_STRUCT__entry( + __field(unsigned int, ncpus) + __field(int, vector) + ), + TP_fast_assign(__entry->ncpus = cpumask_weight(cpus); + __entry->vector = vector; + ), + TP_printk("ncpus %d vector %x", + __entry->ncpus, __entry->vector) + ); + #endif /* CONFIG_HYPERV */ #undef TRACE_INCLUDE_PATH diff --git a/arch/x86/include/asm/unwind_hints.h b/arch/x86/include/asm/unwind_hints.h index bae46fc6b9de..0bcdb1279361 100644 --- a/arch/x86/include/asm/unwind_hints.h +++ b/arch/x86/include/asm/unwind_hints.h @@ -26,7 +26,7 @@ * the debuginfo as necessary. It will also warn if it sees any * inconsistencies. */ -.macro UNWIND_HINT sp_reg=ORC_REG_SP sp_offset=0 type=ORC_TYPE_CALL +.macro UNWIND_HINT sp_reg=ORC_REG_SP sp_offset=0 type=ORC_TYPE_CALL end=0 #ifdef CONFIG_STACK_VALIDATION .Lunwind_hint_ip_\@: .pushsection .discard.unwind_hints @@ -35,12 +35,14 @@ .short \sp_offset .byte \sp_reg .byte \type + .byte \end + .balign 4 .popsection #endif .endm .macro UNWIND_HINT_EMPTY - UNWIND_HINT sp_reg=ORC_REG_UNDEFINED + UNWIND_HINT sp_reg=ORC_REG_UNDEFINED end=1 .endm .macro UNWIND_HINT_REGS base=%rsp offset=0 indirect=0 extra=1 iret=0 @@ -86,19 +88,21 @@ #else /* !__ASSEMBLY__ */ -#define UNWIND_HINT(sp_reg, sp_offset, type) \ +#define UNWIND_HINT(sp_reg, sp_offset, type, end) \ "987: \n\t" \ ".pushsection .discard.unwind_hints\n\t" \ /* struct unwind_hint */ \ ".long 987b - .\n\t" \ - ".short " __stringify(sp_offset) "\n\t" \ + ".short " __stringify(sp_offset) "\n\t" \ ".byte " __stringify(sp_reg) "\n\t" \ ".byte " __stringify(type) "\n\t" \ + ".byte " __stringify(end) "\n\t" \ + ".balign 4 \n\t" \ ".popsection\n\t" -#define UNWIND_HINT_SAVE UNWIND_HINT(0, 0, UNWIND_HINT_TYPE_SAVE) +#define UNWIND_HINT_SAVE UNWIND_HINT(0, 0, UNWIND_HINT_TYPE_SAVE, 0) -#define UNWIND_HINT_RESTORE UNWIND_HINT(0, 0, UNWIND_HINT_TYPE_RESTORE) +#define UNWIND_HINT_RESTORE UNWIND_HINT(0, 0, UNWIND_HINT_TYPE_RESTORE, 0) #endif /* __ASSEMBLY__ */ diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index adbda5847b14..07fa222f0c52 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -940,7 +940,7 @@ static int __init calibrate_APIC_clock(void) if (levt->features & CLOCK_EVT_FEAT_DUMMY) { pr_warning("APIC timer disabled due to verification failure\n"); - return -1; + return -1; } return 0; diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c index 35aaee4fc028..0954315842c0 100644 --- a/arch/x86/kernel/apic/vector.c +++ b/arch/x86/kernel/apic/vector.c @@ -218,7 +218,8 @@ static int reserve_irq_vector(struct irq_data *irqd) return 0; } -static int allocate_vector(struct irq_data *irqd, const struct cpumask *dest) +static int +assign_vector_locked(struct irq_data *irqd, const struct cpumask *dest) { struct apic_chip_data *apicd = apic_chip_data(irqd); bool resvd = apicd->has_reserved; @@ -245,22 +246,12 @@ static int allocate_vector(struct irq_data *irqd, const struct cpumask *dest) return -EBUSY; vector = irq_matrix_alloc(vector_matrix, dest, resvd, &cpu); - if (vector > 0) - apic_update_vector(irqd, vector, cpu); trace_vector_alloc(irqd->irq, vector, resvd, vector); - return vector; -} - -static int assign_vector_locked(struct irq_data *irqd, - const struct cpumask *dest) -{ - struct apic_chip_data *apicd = apic_chip_data(irqd); - int vector = allocate_vector(irqd, dest); - if (vector < 0) return vector; + apic_update_vector(irqd, vector, cpu); + apic_update_irq_cfg(irqd, vector, cpu); - apic_update_irq_cfg(irqd, apicd->vector, apicd->cpu); return 0; } @@ -433,7 +424,7 @@ static int activate_managed(struct irq_data *irqd) pr_err("Managed startup irq %u, no vector available\n", irqd->irq); } - return ret; + return ret; } static int x86_vector_activate(struct irq_domain *dom, struct irq_data *irqd, diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index d492752f79e1..391f358ebb4c 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -394,10 +394,10 @@ extern int uv_hub_info_version(void) EXPORT_SYMBOL(uv_hub_info_version); /* Default UV memory block size is 2GB */ -static unsigned long mem_block_size = (2UL << 30); +static unsigned long mem_block_size __initdata = (2UL << 30); /* Kernel parameter to specify UV mem block size */ -static int parse_mem_block_size(char *ptr) +static int __init parse_mem_block_size(char *ptr) { unsigned long size = memparse(ptr, NULL); diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile index 7a40196967cb..347137e80bf5 100644 --- a/arch/x86/kernel/cpu/Makefile +++ b/arch/x86/kernel/cpu/Makefile @@ -35,7 +35,9 @@ obj-$(CONFIG_CPU_SUP_CENTAUR) += centaur.o obj-$(CONFIG_CPU_SUP_TRANSMETA_32) += transmeta.o obj-$(CONFIG_CPU_SUP_UMC_32) += umc.o -obj-$(CONFIG_INTEL_RDT) += intel_rdt.o intel_rdt_rdtgroup.o intel_rdt_monitor.o intel_rdt_ctrlmondata.o +obj-$(CONFIG_INTEL_RDT) += intel_rdt.o intel_rdt_rdtgroup.o intel_rdt_monitor.o +obj-$(CONFIG_INTEL_RDT) += intel_rdt_ctrlmondata.o intel_rdt_pseudo_lock.o +CFLAGS_intel_rdt_pseudo_lock.o = -I$(src) obj-$(CONFIG_X86_MCE) += mcheck/ obj-$(CONFIG_MTRR) += mtrr/ diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index eb75564f2d25..c050cd6066af 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -465,14 +465,17 @@ static void detect_vmx_virtcap(struct cpuinfo_x86 *c) #define X86_VMX_FEATURE_PROC_CTLS2_VIRT_APIC 0x00000001 #define X86_VMX_FEATURE_PROC_CTLS2_EPT 0x00000002 #define X86_VMX_FEATURE_PROC_CTLS2_VPID 0x00000020 +#define x86_VMX_FEATURE_EPT_CAP_AD 0x00200000 u32 vmx_msr_low, vmx_msr_high, msr_ctl, msr_ctl2; + u32 msr_vpid_cap, msr_ept_cap; clear_cpu_cap(c, X86_FEATURE_TPR_SHADOW); clear_cpu_cap(c, X86_FEATURE_VNMI); clear_cpu_cap(c, X86_FEATURE_FLEXPRIORITY); clear_cpu_cap(c, X86_FEATURE_EPT); clear_cpu_cap(c, X86_FEATURE_VPID); + clear_cpu_cap(c, X86_FEATURE_EPT_AD); rdmsr(MSR_IA32_VMX_PROCBASED_CTLS, vmx_msr_low, vmx_msr_high); msr_ctl = vmx_msr_high | vmx_msr_low; @@ -487,8 +490,13 @@ static void detect_vmx_virtcap(struct cpuinfo_x86 *c) if ((msr_ctl2 & X86_VMX_FEATURE_PROC_CTLS2_VIRT_APIC) && (msr_ctl & X86_VMX_FEATURE_PROC_CTLS_TPR_SHADOW)) set_cpu_cap(c, X86_FEATURE_FLEXPRIORITY); - if (msr_ctl2 & X86_VMX_FEATURE_PROC_CTLS2_EPT) + if (msr_ctl2 & X86_VMX_FEATURE_PROC_CTLS2_EPT) { set_cpu_cap(c, X86_FEATURE_EPT); + rdmsr(MSR_IA32_VMX_EPT_VPID_CAP, + msr_ept_cap, msr_vpid_cap); + if (msr_ept_cap & x86_VMX_FEATURE_EPT_CAP_AD) + set_cpu_cap(c, X86_FEATURE_EPT_AD); + } if (msr_ctl2 & X86_VMX_FEATURE_PROC_CTLS2_VPID) set_cpu_cap(c, X86_FEATURE_VPID); } diff --git a/arch/x86/kernel/cpu/intel_rdt.c b/arch/x86/kernel/cpu/intel_rdt.c index ec4754f81cbd..abb71ac70443 100644 --- a/arch/x86/kernel/cpu/intel_rdt.c +++ b/arch/x86/kernel/cpu/intel_rdt.c @@ -859,6 +859,8 @@ static __init bool get_rdt_resources(void) return (rdt_mon_capable || rdt_alloc_capable); } +static enum cpuhp_state rdt_online; + static int __init intel_rdt_late_init(void) { struct rdt_resource *r; @@ -880,6 +882,7 @@ static int __init intel_rdt_late_init(void) cpuhp_remove_state(state); return ret; } + rdt_online = state; for_each_alloc_capable_rdt_resource(r) pr_info("Intel RDT %s allocation detected\n", r->name); @@ -891,3 +894,11 @@ static int __init intel_rdt_late_init(void) } late_initcall(intel_rdt_late_init); + +static void __exit intel_rdt_exit(void) +{ + cpuhp_remove_state(rdt_online); + rdtgroup_exit(); +} + +__exitcall(intel_rdt_exit); diff --git a/arch/x86/kernel/cpu/intel_rdt.h b/arch/x86/kernel/cpu/intel_rdt.h index 39752825e376..4e588f36228f 100644 --- a/arch/x86/kernel/cpu/intel_rdt.h +++ b/arch/x86/kernel/cpu/intel_rdt.h @@ -81,6 +81,34 @@ enum rdt_group_type { }; /** + * enum rdtgrp_mode - Mode of a RDT resource group + * @RDT_MODE_SHAREABLE: This resource group allows sharing of its allocations + * @RDT_MODE_EXCLUSIVE: No sharing of this resource group's allocations allowed + * @RDT_MODE_PSEUDO_LOCKSETUP: Resource group will be used for Pseudo-Locking + * @RDT_MODE_PSEUDO_LOCKED: No sharing of this resource group's allocations + * allowed AND the allocations are Cache Pseudo-Locked + * + * The mode of a resource group enables control over the allowed overlap + * between allocations associated with different resource groups (classes + * of service). User is able to modify the mode of a resource group by + * writing to the "mode" resctrl file associated with the resource group. + * + * The "shareable", "exclusive", and "pseudo-locksetup" modes are set by + * writing the appropriate text to the "mode" file. A resource group enters + * "pseudo-locked" mode after the schemata is written while the resource + * group is in "pseudo-locksetup" mode. + */ +enum rdtgrp_mode { + RDT_MODE_SHAREABLE = 0, + RDT_MODE_EXCLUSIVE, + RDT_MODE_PSEUDO_LOCKSETUP, + RDT_MODE_PSEUDO_LOCKED, + + /* Must be last */ + RDT_NUM_MODES, +}; + +/** * struct mongroup - store mon group's data in resctrl fs. * @mon_data_kn kernlfs node for the mon_data directory * @parent: parent rdtgrp @@ -95,6 +123,43 @@ struct mongroup { }; /** + * struct pseudo_lock_region - pseudo-lock region information + * @r: RDT resource to which this pseudo-locked region + * belongs + * @d: RDT domain to which this pseudo-locked region + * belongs + * @cbm: bitmask of the pseudo-locked region + * @lock_thread_wq: waitqueue used to wait on the pseudo-locking thread + * completion + * @thread_done: variable used by waitqueue to test if pseudo-locking + * thread completed + * @cpu: core associated with the cache on which the setup code + * will be run + * @line_size: size of the cache lines + * @size: size of pseudo-locked region in bytes + * @kmem: the kernel memory associated with pseudo-locked region + * @minor: minor number of character device associated with this + * region + * @debugfs_dir: pointer to this region's directory in the debugfs + * filesystem + * @pm_reqs: Power management QoS requests related to this region + */ +struct pseudo_lock_region { + struct rdt_resource *r; + struct rdt_domain *d; + u32 cbm; + wait_queue_head_t lock_thread_wq; + int thread_done; + int cpu; + unsigned int line_size; + unsigned int size; + void *kmem; + unsigned int minor; + struct dentry *debugfs_dir; + struct list_head pm_reqs; +}; + +/** * struct rdtgroup - store rdtgroup's data in resctrl file system. * @kn: kernfs node * @rdtgroup_list: linked list for all rdtgroups @@ -106,16 +171,20 @@ struct mongroup { * @type: indicates type of this rdtgroup - either * monitor only or ctrl_mon group * @mon: mongroup related data + * @mode: mode of resource group + * @plr: pseudo-locked region */ struct rdtgroup { - struct kernfs_node *kn; - struct list_head rdtgroup_list; - u32 closid; - struct cpumask cpu_mask; - int flags; - atomic_t waitcount; - enum rdt_group_type type; - struct mongroup mon; + struct kernfs_node *kn; + struct list_head rdtgroup_list; + u32 closid; + struct cpumask cpu_mask; + int flags; + atomic_t waitcount; + enum rdt_group_type type; + struct mongroup mon; + enum rdtgrp_mode mode; + struct pseudo_lock_region *plr; }; /* rdtgroup.flags */ @@ -148,6 +217,7 @@ extern struct list_head rdt_all_groups; extern int max_name_width, max_data_width; int __init rdtgroup_init(void); +void __exit rdtgroup_exit(void); /** * struct rftype - describe each file in the resctrl file system @@ -216,22 +286,24 @@ struct mbm_state { * @mbps_val: When mba_sc is enabled, this holds the bandwidth in MBps * @new_ctrl: new ctrl value to be loaded * @have_new_ctrl: did user provide new_ctrl for this domain + * @plr: pseudo-locked region (if any) associated with domain */ struct rdt_domain { - struct list_head list; - int id; - struct cpumask cpu_mask; - unsigned long *rmid_busy_llc; - struct mbm_state *mbm_total; - struct mbm_state *mbm_local; - struct delayed_work mbm_over; - struct delayed_work cqm_limbo; - int mbm_work_cpu; - int cqm_work_cpu; - u32 *ctrl_val; - u32 *mbps_val; - u32 new_ctrl; - bool have_new_ctrl; + struct list_head list; + int id; + struct cpumask cpu_mask; + unsigned long *rmid_busy_llc; + struct mbm_state *mbm_total; + struct mbm_state *mbm_local; + struct delayed_work mbm_over; + struct delayed_work cqm_limbo; + int mbm_work_cpu; + int cqm_work_cpu; + u32 *ctrl_val; + u32 *mbps_val; + u32 new_ctrl; + bool have_new_ctrl; + struct pseudo_lock_region *plr; }; /** @@ -351,7 +423,7 @@ struct rdt_resource { struct rdt_cache cache; struct rdt_membw membw; const char *format_str; - int (*parse_ctrlval) (char *buf, struct rdt_resource *r, + int (*parse_ctrlval) (void *data, struct rdt_resource *r, struct rdt_domain *d); struct list_head evt_list; int num_rmid; @@ -359,8 +431,8 @@ struct rdt_resource { unsigned long fflags; }; -int parse_cbm(char *buf, struct rdt_resource *r, struct rdt_domain *d); -int parse_bw(char *buf, struct rdt_resource *r, struct rdt_domain *d); +int parse_cbm(void *_data, struct rdt_resource *r, struct rdt_domain *d); +int parse_bw(void *_buf, struct rdt_resource *r, struct rdt_domain *d); extern struct mutex rdtgroup_mutex; @@ -368,7 +440,7 @@ extern struct rdt_resource rdt_resources_all[]; extern struct rdtgroup rdtgroup_default; DECLARE_STATIC_KEY_FALSE(rdt_alloc_enable_key); -int __init rdtgroup_init(void); +extern struct dentry *debugfs_resctrl; enum { RDT_RESOURCE_L3, @@ -439,13 +511,32 @@ void rdt_last_cmd_printf(const char *fmt, ...); void rdt_ctrl_update(void *arg); struct rdtgroup *rdtgroup_kn_lock_live(struct kernfs_node *kn); void rdtgroup_kn_unlock(struct kernfs_node *kn); +int rdtgroup_kn_mode_restrict(struct rdtgroup *r, const char *name); +int rdtgroup_kn_mode_restore(struct rdtgroup *r, const char *name, + umode_t mask); struct rdt_domain *rdt_find_domain(struct rdt_resource *r, int id, struct list_head **pos); ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off); int rdtgroup_schemata_show(struct kernfs_open_file *of, struct seq_file *s, void *v); +bool rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_domain *d, + u32 _cbm, int closid, bool exclusive); +unsigned int rdtgroup_cbm_to_size(struct rdt_resource *r, struct rdt_domain *d, + u32 cbm); +enum rdtgrp_mode rdtgroup_mode_by_closid(int closid); +int rdtgroup_tasks_assigned(struct rdtgroup *r); +int rdtgroup_locksetup_enter(struct rdtgroup *rdtgrp); +int rdtgroup_locksetup_exit(struct rdtgroup *rdtgrp); +bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_domain *d, u32 _cbm); +bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_domain *d); +int rdt_pseudo_lock_init(void); +void rdt_pseudo_lock_release(void); +int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp); +void rdtgroup_pseudo_lock_remove(struct rdtgroup *rdtgrp); struct rdt_domain *get_domain_from_cpu(int cpu, struct rdt_resource *r); +int update_domains(struct rdt_resource *r, int closid); +void closid_free(int closid); int alloc_rmid(void); void free_rmid(u32 rmid); int rdt_get_mon_l3_config(struct rdt_resource *r); diff --git a/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c b/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c index 116d57b248d3..af358ca05160 100644 --- a/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c +++ b/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c @@ -64,9 +64,10 @@ static bool bw_validate(char *buf, unsigned long *data, struct rdt_resource *r) return true; } -int parse_bw(char *buf, struct rdt_resource *r, struct rdt_domain *d) +int parse_bw(void *_buf, struct rdt_resource *r, struct rdt_domain *d) { unsigned long data; + char *buf = _buf; if (d->have_new_ctrl) { rdt_last_cmd_printf("duplicate domain %d\n", d->id); @@ -87,7 +88,7 @@ int parse_bw(char *buf, struct rdt_resource *r, struct rdt_domain *d) * are allowed (e.g. FFFFH, 0FF0H, 003CH, etc.). * Additionally Haswell requires at least two bits set. */ -static bool cbm_validate(char *buf, unsigned long *data, struct rdt_resource *r) +static bool cbm_validate(char *buf, u32 *data, struct rdt_resource *r) { unsigned long first_bit, zero_bit, val; unsigned int cbm_len = r->cache.cbm_len; @@ -122,22 +123,64 @@ static bool cbm_validate(char *buf, unsigned long *data, struct rdt_resource *r) return true; } +struct rdt_cbm_parse_data { + struct rdtgroup *rdtgrp; + char *buf; +}; + /* * Read one cache bit mask (hex). Check that it is valid for the current * resource type. */ -int parse_cbm(char *buf, struct rdt_resource *r, struct rdt_domain *d) +int parse_cbm(void *_data, struct rdt_resource *r, struct rdt_domain *d) { - unsigned long data; + struct rdt_cbm_parse_data *data = _data; + struct rdtgroup *rdtgrp = data->rdtgrp; + u32 cbm_val; if (d->have_new_ctrl) { rdt_last_cmd_printf("duplicate domain %d\n", d->id); return -EINVAL; } - if(!cbm_validate(buf, &data, r)) + /* + * Cannot set up more than one pseudo-locked region in a cache + * hierarchy. + */ + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP && + rdtgroup_pseudo_locked_in_hierarchy(d)) { + rdt_last_cmd_printf("pseudo-locked region in hierarchy\n"); return -EINVAL; - d->new_ctrl = data; + } + + if (!cbm_validate(data->buf, &cbm_val, r)) + return -EINVAL; + + if ((rdtgrp->mode == RDT_MODE_EXCLUSIVE || + rdtgrp->mode == RDT_MODE_SHAREABLE) && + rdtgroup_cbm_overlaps_pseudo_locked(d, cbm_val)) { + rdt_last_cmd_printf("CBM overlaps with pseudo-locked region\n"); + return -EINVAL; + } + + /* + * The CBM may not overlap with the CBM of another closid if + * either is exclusive. + */ + if (rdtgroup_cbm_overlaps(r, d, cbm_val, rdtgrp->closid, true)) { + rdt_last_cmd_printf("overlaps with exclusive group\n"); + return -EINVAL; + } + + if (rdtgroup_cbm_overlaps(r, d, cbm_val, rdtgrp->closid, false)) { + if (rdtgrp->mode == RDT_MODE_EXCLUSIVE || + rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) { + rdt_last_cmd_printf("overlaps with other group\n"); + return -EINVAL; + } + } + + d->new_ctrl = cbm_val; d->have_new_ctrl = true; return 0; @@ -149,8 +192,10 @@ int parse_cbm(char *buf, struct rdt_resource *r, struct rdt_domain *d) * separated by ";". The "id" is in decimal, and must match one of * the "id"s for this resource. */ -static int parse_line(char *line, struct rdt_resource *r) +static int parse_line(char *line, struct rdt_resource *r, + struct rdtgroup *rdtgrp) { + struct rdt_cbm_parse_data data; char *dom = NULL, *id; struct rdt_domain *d; unsigned long dom_id; @@ -167,15 +212,32 @@ next: dom = strim(dom); list_for_each_entry(d, &r->domains, list) { if (d->id == dom_id) { - if (r->parse_ctrlval(dom, r, d)) + data.buf = dom; + data.rdtgrp = rdtgrp; + if (r->parse_ctrlval(&data, r, d)) return -EINVAL; + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) { + /* + * In pseudo-locking setup mode and just + * parsed a valid CBM that should be + * pseudo-locked. Only one locked region per + * resource group and domain so just do + * the required initialization for single + * region and return. + */ + rdtgrp->plr->r = r; + rdtgrp->plr->d = d; + rdtgrp->plr->cbm = d->new_ctrl; + d->plr = rdtgrp->plr; + return 0; + } goto next; } } return -EINVAL; } -static int update_domains(struct rdt_resource *r, int closid) +int update_domains(struct rdt_resource *r, int closid) { struct msr_param msr_param; cpumask_var_t cpu_mask; @@ -220,13 +282,14 @@ done: return 0; } -static int rdtgroup_parse_resource(char *resname, char *tok, int closid) +static int rdtgroup_parse_resource(char *resname, char *tok, + struct rdtgroup *rdtgrp) { struct rdt_resource *r; for_each_alloc_enabled_rdt_resource(r) { - if (!strcmp(resname, r->name) && closid < r->num_closid) - return parse_line(tok, r); + if (!strcmp(resname, r->name) && rdtgrp->closid < r->num_closid) + return parse_line(tok, r, rdtgrp); } rdt_last_cmd_printf("unknown/unsupported resource name '%s'\n", resname); return -EINVAL; @@ -239,7 +302,7 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of, struct rdt_domain *dom; struct rdt_resource *r; char *tok, *resname; - int closid, ret = 0; + int ret = 0; /* Valid input requires a trailing newline */ if (nbytes == 0 || buf[nbytes - 1] != '\n') @@ -253,7 +316,15 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of, } rdt_last_cmd_clear(); - closid = rdtgrp->closid; + /* + * No changes to pseudo-locked region allowed. It has to be removed + * and re-created instead. + */ + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) { + ret = -EINVAL; + rdt_last_cmd_puts("resource group is pseudo-locked\n"); + goto out; + } for_each_alloc_enabled_rdt_resource(r) { list_for_each_entry(dom, &r->domains, list) @@ -272,17 +343,27 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of, ret = -EINVAL; goto out; } - ret = rdtgroup_parse_resource(resname, tok, closid); + ret = rdtgroup_parse_resource(resname, tok, rdtgrp); if (ret) goto out; } for_each_alloc_enabled_rdt_resource(r) { - ret = update_domains(r, closid); + ret = update_domains(r, rdtgrp->closid); if (ret) goto out; } + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) { + /* + * If pseudo-locking fails we keep the resource group in + * mode RDT_MODE_PSEUDO_LOCKSETUP with its class of service + * active and updated for just the domain the pseudo-locked + * region was requested for. + */ + ret = rdtgroup_pseudo_lock_create(rdtgrp); + } + out: rdtgroup_kn_unlock(of->kn); return ret ?: nbytes; @@ -318,10 +399,18 @@ int rdtgroup_schemata_show(struct kernfs_open_file *of, rdtgrp = rdtgroup_kn_lock_live(of->kn); if (rdtgrp) { - closid = rdtgrp->closid; - for_each_alloc_enabled_rdt_resource(r) { - if (closid < r->num_closid) - show_doms(s, r, closid); + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) { + for_each_alloc_enabled_rdt_resource(r) + seq_printf(s, "%s:uninitialized\n", r->name); + } else if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) { + seq_printf(s, "%s:%d=%x\n", rdtgrp->plr->r->name, + rdtgrp->plr->d->id, rdtgrp->plr->cbm); + } else { + closid = rdtgrp->closid; + for_each_alloc_enabled_rdt_resource(r) { + if (closid < r->num_closid) + show_doms(s, r, closid); + } } } else { ret = -ENOENT; diff --git a/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c new file mode 100644 index 000000000000..40f3903ae5d9 --- /dev/null +++ b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c @@ -0,0 +1,1522 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Resource Director Technology (RDT) + * + * Pseudo-locking support built on top of Cache Allocation Technology (CAT) + * + * Copyright (C) 2018 Intel Corporation + * + * Author: Reinette Chatre <reinette.chatre@intel.com> + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/cacheinfo.h> +#include <linux/cpu.h> +#include <linux/cpumask.h> +#include <linux/debugfs.h> +#include <linux/kthread.h> +#include <linux/mman.h> +#include <linux/pm_qos.h> +#include <linux/slab.h> +#include <linux/uaccess.h> + +#include <asm/cacheflush.h> +#include <asm/intel-family.h> +#include <asm/intel_rdt_sched.h> +#include <asm/perf_event.h> + +#include "intel_rdt.h" + +#define CREATE_TRACE_POINTS +#include "intel_rdt_pseudo_lock_event.h" + +/* + * MSR_MISC_FEATURE_CONTROL register enables the modification of hardware + * prefetcher state. Details about this register can be found in the MSR + * tables for specific platforms found in Intel's SDM. + */ +#define MSR_MISC_FEATURE_CONTROL 0x000001a4 + +/* + * The bits needed to disable hardware prefetching varies based on the + * platform. During initialization we will discover which bits to use. + */ +static u64 prefetch_disable_bits; + +/* + * Major number assigned to and shared by all devices exposing + * pseudo-locked regions. + */ +static unsigned int pseudo_lock_major; +static unsigned long pseudo_lock_minor_avail = GENMASK(MINORBITS, 0); +static struct class *pseudo_lock_class; + +/** + * get_prefetch_disable_bits - prefetch disable bits of supported platforms + * + * Capture the list of platforms that have been validated to support + * pseudo-locking. This includes testing to ensure pseudo-locked regions + * with low cache miss rates can be created under variety of load conditions + * as well as that these pseudo-locked regions can maintain their low cache + * miss rates under variety of load conditions for significant lengths of time. + * + * After a platform has been validated to support pseudo-locking its + * hardware prefetch disable bits are included here as they are documented + * in the SDM. + * + * When adding a platform here also add support for its cache events to + * measure_cycles_perf_fn() + * + * Return: + * If platform is supported, the bits to disable hardware prefetchers, 0 + * if platform is not supported. + */ +static u64 get_prefetch_disable_bits(void) +{ + if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL || + boot_cpu_data.x86 != 6) + return 0; + + switch (boot_cpu_data.x86_model) { + case INTEL_FAM6_BROADWELL_X: + /* + * SDM defines bits of MSR_MISC_FEATURE_CONTROL register + * as: + * 0 L2 Hardware Prefetcher Disable (R/W) + * 1 L2 Adjacent Cache Line Prefetcher Disable (R/W) + * 2 DCU Hardware Prefetcher Disable (R/W) + * 3 DCU IP Prefetcher Disable (R/W) + * 63:4 Reserved + */ + return 0xF; + case INTEL_FAM6_ATOM_GOLDMONT: + case INTEL_FAM6_ATOM_GEMINI_LAKE: + /* + * SDM defines bits of MSR_MISC_FEATURE_CONTROL register + * as: + * 0 L2 Hardware Prefetcher Disable (R/W) + * 1 Reserved + * 2 DCU Hardware Prefetcher Disable (R/W) + * 63:3 Reserved + */ + return 0x5; + } + + return 0; +} + +/* + * Helper to write 64bit value to MSR without tracing. Used when + * use of the cache should be restricted and use of registers used + * for local variables avoided. + */ +static inline void pseudo_wrmsrl_notrace(unsigned int msr, u64 val) +{ + __wrmsr(msr, (u32)(val & 0xffffffffULL), (u32)(val >> 32)); +} + +/** + * pseudo_lock_minor_get - Obtain available minor number + * @minor: Pointer to where new minor number will be stored + * + * A bitmask is used to track available minor numbers. Here the next free + * minor number is marked as unavailable and returned. + * + * Return: 0 on success, <0 on failure. + */ +static int pseudo_lock_minor_get(unsigned int *minor) +{ + unsigned long first_bit; + + first_bit = find_first_bit(&pseudo_lock_minor_avail, MINORBITS); + + if (first_bit == MINORBITS) + return -ENOSPC; + + __clear_bit(first_bit, &pseudo_lock_minor_avail); + *minor = first_bit; + + return 0; +} + +/** + * pseudo_lock_minor_release - Return minor number to available + * @minor: The minor number made available + */ +static void pseudo_lock_minor_release(unsigned int minor) +{ + __set_bit(minor, &pseudo_lock_minor_avail); +} + +/** + * region_find_by_minor - Locate a pseudo-lock region by inode minor number + * @minor: The minor number of the device representing pseudo-locked region + * + * When the character device is accessed we need to determine which + * pseudo-locked region it belongs to. This is done by matching the minor + * number of the device to the pseudo-locked region it belongs. + * + * Minor numbers are assigned at the time a pseudo-locked region is associated + * with a cache instance. + * + * Return: On success return pointer to resource group owning the pseudo-locked + * region, NULL on failure. + */ +static struct rdtgroup *region_find_by_minor(unsigned int minor) +{ + struct rdtgroup *rdtgrp, *rdtgrp_match = NULL; + + list_for_each_entry(rdtgrp, &rdt_all_groups, rdtgroup_list) { + if (rdtgrp->plr && rdtgrp->plr->minor == minor) { + rdtgrp_match = rdtgrp; + break; + } + } + return rdtgrp_match; +} + +/** + * pseudo_lock_pm_req - A power management QoS request list entry + * @list: Entry within the @pm_reqs list for a pseudo-locked region + * @req: PM QoS request + */ +struct pseudo_lock_pm_req { + struct list_head list; + struct dev_pm_qos_request req; +}; + +static void pseudo_lock_cstates_relax(struct pseudo_lock_region *plr) +{ + struct pseudo_lock_pm_req *pm_req, *next; + + list_for_each_entry_safe(pm_req, next, &plr->pm_reqs, list) { + dev_pm_qos_remove_request(&pm_req->req); + list_del(&pm_req->list); + kfree(pm_req); + } +} + +/** + * pseudo_lock_cstates_constrain - Restrict cores from entering C6 + * + * To prevent the cache from being affected by power management entering + * C6 has to be avoided. This is accomplished by requesting a latency + * requirement lower than lowest C6 exit latency of all supported + * platforms as found in the cpuidle state tables in the intel_idle driver. + * At this time it is possible to do so with a single latency requirement + * for all supported platforms. + * + * Since Goldmont is supported, which is affected by X86_BUG_MONITOR, + * the ACPI latencies need to be considered while keeping in mind that C2 + * may be set to map to deeper sleep states. In this case the latency + * requirement needs to prevent entering C2 also. + */ +static int pseudo_lock_cstates_constrain(struct pseudo_lock_region *plr) +{ + struct pseudo_lock_pm_req *pm_req; + int cpu; + int ret; + + for_each_cpu(cpu, &plr->d->cpu_mask) { + pm_req = kzalloc(sizeof(*pm_req), GFP_KERNEL); + if (!pm_req) { + rdt_last_cmd_puts("fail allocating mem for PM QoS\n"); + ret = -ENOMEM; + goto out_err; + } + ret = dev_pm_qos_add_request(get_cpu_device(cpu), + &pm_req->req, + DEV_PM_QOS_RESUME_LATENCY, + 30); + if (ret < 0) { + rdt_last_cmd_printf("fail to add latency req cpu%d\n", + cpu); + kfree(pm_req); + ret = -1; + goto out_err; + } + list_add(&pm_req->list, &plr->pm_reqs); + } + + return 0; + +out_err: + pseudo_lock_cstates_relax(plr); + return ret; +} + +/** + * pseudo_lock_region_clear - Reset pseudo-lock region data + * @plr: pseudo-lock region + * + * All content of the pseudo-locked region is reset - any memory allocated + * freed. + * + * Return: void + */ +static void pseudo_lock_region_clear(struct pseudo_lock_region *plr) +{ + plr->size = 0; + plr->line_size = 0; + kfree(plr->kmem); + plr->kmem = NULL; + plr->r = NULL; + if (plr->d) + plr->d->plr = NULL; + plr->d = NULL; + plr->cbm = 0; + plr->debugfs_dir = NULL; +} + +/** + * pseudo_lock_region_init - Initialize pseudo-lock region information + * @plr: pseudo-lock region + * + * Called after user provided a schemata to be pseudo-locked. From the + * schemata the &struct pseudo_lock_region is on entry already initialized + * with the resource, domain, and capacity bitmask. Here the information + * required for pseudo-locking is deduced from this data and &struct + * pseudo_lock_region initialized further. This information includes: + * - size in bytes of the region to be pseudo-locked + * - cache line size to know the stride with which data needs to be accessed + * to be pseudo-locked + * - a cpu associated with the cache instance on which the pseudo-locking + * flow can be executed + * + * Return: 0 on success, <0 on failure. Descriptive error will be written + * to last_cmd_status buffer. + */ +static int pseudo_lock_region_init(struct pseudo_lock_region *plr) +{ + struct cpu_cacheinfo *ci; + int ret; + int i; + + /* Pick the first cpu we find that is associated with the cache. */ + plr->cpu = cpumask_first(&plr->d->cpu_mask); + + if (!cpu_online(plr->cpu)) { + rdt_last_cmd_printf("cpu %u associated with cache not online\n", + plr->cpu); + ret = -ENODEV; + goto out_region; + } + + ci = get_cpu_cacheinfo(plr->cpu); + + plr->size = rdtgroup_cbm_to_size(plr->r, plr->d, plr->cbm); + + for (i = 0; i < ci->num_leaves; i++) { + if (ci->info_list[i].level == plr->r->cache_level) { + plr->line_size = ci->info_list[i].coherency_line_size; + return 0; + } + } + + ret = -1; + rdt_last_cmd_puts("unable to determine cache line size\n"); +out_region: + pseudo_lock_region_clear(plr); + return ret; +} + +/** + * pseudo_lock_init - Initialize a pseudo-lock region + * @rdtgrp: resource group to which new pseudo-locked region will belong + * + * A pseudo-locked region is associated with a resource group. When this + * association is created the pseudo-locked region is initialized. The + * details of the pseudo-locked region are not known at this time so only + * allocation is done and association established. + * + * Return: 0 on success, <0 on failure + */ +static int pseudo_lock_init(struct rdtgroup *rdtgrp) +{ + struct pseudo_lock_region *plr; + + plr = kzalloc(sizeof(*plr), GFP_KERNEL); + if (!plr) + return -ENOMEM; + + init_waitqueue_head(&plr->lock_thread_wq); + INIT_LIST_HEAD(&plr->pm_reqs); + rdtgrp->plr = plr; + return 0; +} + +/** + * pseudo_lock_region_alloc - Allocate kernel memory that will be pseudo-locked + * @plr: pseudo-lock region + * + * Initialize the details required to set up the pseudo-locked region and + * allocate the contiguous memory that will be pseudo-locked to the cache. + * + * Return: 0 on success, <0 on failure. Descriptive error will be written + * to last_cmd_status buffer. + */ +static int pseudo_lock_region_alloc(struct pseudo_lock_region *plr) +{ + int ret; + + ret = pseudo_lock_region_init(plr); + if (ret < 0) + return ret; + + /* + * We do not yet support contiguous regions larger than + * KMALLOC_MAX_SIZE. + */ + if (plr->size > KMALLOC_MAX_SIZE) { + rdt_last_cmd_puts("requested region exceeds maximum size\n"); + ret = -E2BIG; + goto out_region; + } + + plr->kmem = kzalloc(plr->size, GFP_KERNEL); + if (!plr->kmem) { + rdt_last_cmd_puts("unable to allocate memory\n"); + ret = -ENOMEM; + goto out_region; + } + + ret = 0; + goto out; +out_region: + pseudo_lock_region_clear(plr); +out: + return ret; +} + +/** + * pseudo_lock_free - Free a pseudo-locked region + * @rdtgrp: resource group to which pseudo-locked region belonged + * + * The pseudo-locked region's resources have already been released, or not + * yet created at this point. Now it can be freed and disassociated from the + * resource group. + * + * Return: void + */ +static void pseudo_lock_free(struct rdtgroup *rdtgrp) +{ + pseudo_lock_region_clear(rdtgrp->plr); + kfree(rdtgrp->plr); + rdtgrp->plr = NULL; +} + +/** + * pseudo_lock_fn - Load kernel memory into cache + * @_rdtgrp: resource group to which pseudo-lock region belongs + * + * This is the core pseudo-locking flow. + * + * First we ensure that the kernel memory cannot be found in the cache. + * Then, while taking care that there will be as little interference as + * possible, the memory to be loaded is accessed while core is running + * with class of service set to the bitmask of the pseudo-locked region. + * After this is complete no future CAT allocations will be allowed to + * overlap with this bitmask. + * + * Local register variables are utilized to ensure that the memory region + * to be locked is the only memory access made during the critical locking + * loop. + * + * Return: 0. Waiter on waitqueue will be woken on completion. + */ +static int pseudo_lock_fn(void *_rdtgrp) +{ + struct rdtgroup *rdtgrp = _rdtgrp; + struct pseudo_lock_region *plr = rdtgrp->plr; + u32 rmid_p, closid_p; + unsigned long i; +#ifdef CONFIG_KASAN + /* + * The registers used for local register variables are also used + * when KASAN is active. When KASAN is active we use a regular + * variable to ensure we always use a valid pointer, but the cost + * is that this variable will enter the cache through evicting the + * memory we are trying to lock into the cache. Thus expect lower + * pseudo-locking success rate when KASAN is active. + */ + unsigned int line_size; + unsigned int size; + void *mem_r; +#else + register unsigned int line_size asm("esi"); + register unsigned int size asm("edi"); +#ifdef CONFIG_X86_64 + register void *mem_r asm("rbx"); +#else + register void *mem_r asm("ebx"); +#endif /* CONFIG_X86_64 */ +#endif /* CONFIG_KASAN */ + + /* + * Make sure none of the allocated memory is cached. If it is we + * will get a cache hit in below loop from outside of pseudo-locked + * region. + * wbinvd (as opposed to clflush/clflushopt) is required to + * increase likelihood that allocated cache portion will be filled + * with associated memory. + */ + native_wbinvd(); + + /* + * Always called with interrupts enabled. By disabling interrupts + * ensure that we will not be preempted during this critical section. + */ + local_irq_disable(); + + /* + * Call wrmsr and rdmsr as directly as possible to avoid tracing + * clobbering local register variables or affecting cache accesses. + * + * Disable the hardware prefetcher so that when the end of the memory + * being pseudo-locked is reached the hardware will not read beyond + * the buffer and evict pseudo-locked memory read earlier from the + * cache. + */ + __wrmsr(MSR_MISC_FEATURE_CONTROL, prefetch_disable_bits, 0x0); + closid_p = this_cpu_read(pqr_state.cur_closid); + rmid_p = this_cpu_read(pqr_state.cur_rmid); + mem_r = plr->kmem; + size = plr->size; + line_size = plr->line_size; + /* + * Critical section begin: start by writing the closid associated + * with the capacity bitmask of the cache region being + * pseudo-locked followed by reading of kernel memory to load it + * into the cache. + */ + __wrmsr(IA32_PQR_ASSOC, rmid_p, rdtgrp->closid); + /* + * Cache was flushed earlier. Now access kernel memory to read it + * into cache region associated with just activated plr->closid. + * Loop over data twice: + * - In first loop the cache region is shared with the page walker + * as it populates the paging structure caches (including TLB). + * - In the second loop the paging structure caches are used and + * cache region is populated with the memory being referenced. + */ + for (i = 0; i < size; i += PAGE_SIZE) { + /* + * Add a barrier to prevent speculative execution of this + * loop reading beyond the end of the buffer. + */ + rmb(); + asm volatile("mov (%0,%1,1), %%eax\n\t" + : + : "r" (mem_r), "r" (i) + : "%eax", "memory"); + } + for (i = 0; i < size; i += line_size) { + /* + * Add a barrier to prevent speculative execution of this + * loop reading beyond the end of the buffer. + */ + rmb(); + asm volatile("mov (%0,%1,1), %%eax\n\t" + : + : "r" (mem_r), "r" (i) + : "%eax", "memory"); + } + /* + * Critical section end: restore closid with capacity bitmask that + * does not overlap with pseudo-locked region. + */ + __wrmsr(IA32_PQR_ASSOC, rmid_p, closid_p); + + /* Re-enable the hardware prefetcher(s) */ + wrmsr(MSR_MISC_FEATURE_CONTROL, 0x0, 0x0); + local_irq_enable(); + + plr->thread_done = 1; + wake_up_interruptible(&plr->lock_thread_wq); + return 0; +} + +/** + * rdtgroup_monitor_in_progress - Test if monitoring in progress + * @r: resource group being queried + * + * Return: 1 if monitor groups have been created for this resource + * group, 0 otherwise. + */ +static int rdtgroup_monitor_in_progress(struct rdtgroup *rdtgrp) +{ + return !list_empty(&rdtgrp->mon.crdtgrp_list); +} + +/** + * rdtgroup_locksetup_user_restrict - Restrict user access to group + * @rdtgrp: resource group needing access restricted + * + * A resource group used for cache pseudo-locking cannot have cpus or tasks + * assigned to it. This is communicated to the user by restricting access + * to all the files that can be used to make such changes. + * + * Permissions restored with rdtgroup_locksetup_user_restore() + * + * Return: 0 on success, <0 on failure. If a failure occurs during the + * restriction of access an attempt will be made to restore permissions but + * the state of the mode of these files will be uncertain when a failure + * occurs. + */ +static int rdtgroup_locksetup_user_restrict(struct rdtgroup *rdtgrp) +{ + int ret; + + ret = rdtgroup_kn_mode_restrict(rdtgrp, "tasks"); + if (ret) + return ret; + + ret = rdtgroup_kn_mode_restrict(rdtgrp, "cpus"); + if (ret) + goto err_tasks; + + ret = rdtgroup_kn_mode_restrict(rdtgrp, "cpus_list"); + if (ret) + goto err_cpus; + + if (rdt_mon_capable) { + ret = rdtgroup_kn_mode_restrict(rdtgrp, "mon_groups"); + if (ret) + goto err_cpus_list; + } + + ret = 0; + goto out; + +err_cpus_list: + rdtgroup_kn_mode_restore(rdtgrp, "cpus_list", 0777); +err_cpus: + rdtgroup_kn_mode_restore(rdtgrp, "cpus", 0777); +err_tasks: + rdtgroup_kn_mode_restore(rdtgrp, "tasks", 0777); +out: + return ret; +} + +/** + * rdtgroup_locksetup_user_restore - Restore user access to group + * @rdtgrp: resource group needing access restored + * + * Restore all file access previously removed using + * rdtgroup_locksetup_user_restrict() + * + * Return: 0 on success, <0 on failure. If a failure occurs during the + * restoration of access an attempt will be made to restrict permissions + * again but the state of the mode of these files will be uncertain when + * a failure occurs. + */ +static int rdtgroup_locksetup_user_restore(struct rdtgroup *rdtgrp) +{ + int ret; + + ret = rdtgroup_kn_mode_restore(rdtgrp, "tasks", 0777); + if (ret) + return ret; + + ret = rdtgroup_kn_mode_restore(rdtgrp, "cpus", 0777); + if (ret) + goto err_tasks; + + ret = rdtgroup_kn_mode_restore(rdtgrp, "cpus_list", 0777); + if (ret) + goto err_cpus; + + if (rdt_mon_capable) { + ret = rdtgroup_kn_mode_restore(rdtgrp, "mon_groups", 0777); + if (ret) + goto err_cpus_list; + } + + ret = 0; + goto out; + +err_cpus_list: + rdtgroup_kn_mode_restrict(rdtgrp, "cpus_list"); +err_cpus: + rdtgroup_kn_mode_restrict(rdtgrp, "cpus"); +err_tasks: + rdtgroup_kn_mode_restrict(rdtgrp, "tasks"); +out: + return ret; +} + +/** + * rdtgroup_locksetup_enter - Resource group enters locksetup mode + * @rdtgrp: resource group requested to enter locksetup mode + * + * A resource group enters locksetup mode to reflect that it would be used + * to represent a pseudo-locked region and is in the process of being set + * up to do so. A resource group used for a pseudo-locked region would + * lose the closid associated with it so we cannot allow it to have any + * tasks or cpus assigned nor permit tasks or cpus to be assigned in the + * future. Monitoring of a pseudo-locked region is not allowed either. + * + * The above and more restrictions on a pseudo-locked region are checked + * for and enforced before the resource group enters the locksetup mode. + * + * Returns: 0 if the resource group successfully entered locksetup mode, <0 + * on failure. On failure the last_cmd_status buffer is updated with text to + * communicate details of failure to the user. + */ +int rdtgroup_locksetup_enter(struct rdtgroup *rdtgrp) +{ + int ret; + + /* + * The default resource group can neither be removed nor lose the + * default closid associated with it. + */ + if (rdtgrp == &rdtgroup_default) { + rdt_last_cmd_puts("cannot pseudo-lock default group\n"); + return -EINVAL; + } + + /* + * Cache Pseudo-locking not supported when CDP is enabled. + * + * Some things to consider if you would like to enable this + * support (using L3 CDP as example): + * - When CDP is enabled two separate resources are exposed, + * L3DATA and L3CODE, but they are actually on the same cache. + * The implication for pseudo-locking is that if a + * pseudo-locked region is created on a domain of one + * resource (eg. L3CODE), then a pseudo-locked region cannot + * be created on that same domain of the other resource + * (eg. L3DATA). This is because the creation of a + * pseudo-locked region involves a call to wbinvd that will + * affect all cache allocations on particular domain. + * - Considering the previous, it may be possible to only + * expose one of the CDP resources to pseudo-locking and + * hide the other. For example, we could consider to only + * expose L3DATA and since the L3 cache is unified it is + * still possible to place instructions there are execute it. + * - If only one region is exposed to pseudo-locking we should + * still keep in mind that availability of a portion of cache + * for pseudo-locking should take into account both resources. + * Similarly, if a pseudo-locked region is created in one + * resource, the portion of cache used by it should be made + * unavailable to all future allocations from both resources. + */ + if (rdt_resources_all[RDT_RESOURCE_L3DATA].alloc_enabled || + rdt_resources_all[RDT_RESOURCE_L2DATA].alloc_enabled) { + rdt_last_cmd_puts("CDP enabled\n"); + return -EINVAL; + } + + /* + * Not knowing the bits to disable prefetching implies that this + * platform does not support Cache Pseudo-Locking. + */ + prefetch_disable_bits = get_prefetch_disable_bits(); + if (prefetch_disable_bits == 0) { + rdt_last_cmd_puts("pseudo-locking not supported\n"); + return -EINVAL; + } + + if (rdtgroup_monitor_in_progress(rdtgrp)) { + rdt_last_cmd_puts("monitoring in progress\n"); + return -EINVAL; + } + + if (rdtgroup_tasks_assigned(rdtgrp)) { + rdt_last_cmd_puts("tasks assigned to resource group\n"); + return -EINVAL; + } + + if (!cpumask_empty(&rdtgrp->cpu_mask)) { + rdt_last_cmd_puts("CPUs assigned to resource group\n"); + return -EINVAL; + } + + if (rdtgroup_locksetup_user_restrict(rdtgrp)) { + rdt_last_cmd_puts("unable to modify resctrl permissions\n"); + return -EIO; + } + + ret = pseudo_lock_init(rdtgrp); + if (ret) { + rdt_last_cmd_puts("unable to init pseudo-lock region\n"); + goto out_release; + } + + /* + * If this system is capable of monitoring a rmid would have been + * allocated when the control group was created. This is not needed + * anymore when this group would be used for pseudo-locking. This + * is safe to call on platforms not capable of monitoring. + */ + free_rmid(rdtgrp->mon.rmid); + + ret = 0; + goto out; + +out_release: + rdtgroup_locksetup_user_restore(rdtgrp); +out: + return ret; +} + +/** + * rdtgroup_locksetup_exit - resource group exist locksetup mode + * @rdtgrp: resource group + * + * When a resource group exits locksetup mode the earlier restrictions are + * lifted. + * + * Return: 0 on success, <0 on failure + */ +int rdtgroup_locksetup_exit(struct rdtgroup *rdtgrp) +{ + int ret; + + if (rdt_mon_capable) { + ret = alloc_rmid(); + if (ret < 0) { + rdt_last_cmd_puts("out of RMIDs\n"); + return ret; + } + rdtgrp->mon.rmid = ret; + } + + ret = rdtgroup_locksetup_user_restore(rdtgrp); + if (ret) { + free_rmid(rdtgrp->mon.rmid); + return ret; + } + + pseudo_lock_free(rdtgrp); + return 0; +} + +/** + * rdtgroup_cbm_overlaps_pseudo_locked - Test if CBM or portion is pseudo-locked + * @d: RDT domain + * @_cbm: CBM to test + * + * @d represents a cache instance and @_cbm a capacity bitmask that is + * considered for it. Determine if @_cbm overlaps with any existing + * pseudo-locked region on @d. + * + * Return: true if @_cbm overlaps with pseudo-locked region on @d, false + * otherwise. + */ +bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_domain *d, u32 _cbm) +{ + unsigned long *cbm = (unsigned long *)&_cbm; + unsigned long *cbm_b; + unsigned int cbm_len; + + if (d->plr) { + cbm_len = d->plr->r->cache.cbm_len; + cbm_b = (unsigned long *)&d->plr->cbm; + if (bitmap_intersects(cbm, cbm_b, cbm_len)) + return true; + } + return false; +} + +/** + * rdtgroup_pseudo_locked_in_hierarchy - Pseudo-locked region in cache hierarchy + * @d: RDT domain under test + * + * The setup of a pseudo-locked region affects all cache instances within + * the hierarchy of the region. It is thus essential to know if any + * pseudo-locked regions exist within a cache hierarchy to prevent any + * attempts to create new pseudo-locked regions in the same hierarchy. + * + * Return: true if a pseudo-locked region exists in the hierarchy of @d or + * if it is not possible to test due to memory allocation issue, + * false otherwise. + */ +bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_domain *d) +{ + cpumask_var_t cpu_with_psl; + struct rdt_resource *r; + struct rdt_domain *d_i; + bool ret = false; + + if (!zalloc_cpumask_var(&cpu_with_psl, GFP_KERNEL)) + return true; + + /* + * First determine which cpus have pseudo-locked regions + * associated with them. + */ + for_each_alloc_enabled_rdt_resource(r) { + list_for_each_entry(d_i, &r->domains, list) { + if (d_i->plr) + cpumask_or(cpu_with_psl, cpu_with_psl, + &d_i->cpu_mask); + } + } + + /* + * Next test if new pseudo-locked region would intersect with + * existing region. + */ + if (cpumask_intersects(&d->cpu_mask, cpu_with_psl)) + ret = true; + + free_cpumask_var(cpu_with_psl); + return ret; +} + +/** + * measure_cycles_lat_fn - Measure cycle latency to read pseudo-locked memory + * @_plr: pseudo-lock region to measure + * + * There is no deterministic way to test if a memory region is cached. One + * way is to measure how long it takes to read the memory, the speed of + * access is a good way to learn how close to the cpu the data was. Even + * more, if the prefetcher is disabled and the memory is read at a stride + * of half the cache line, then a cache miss will be easy to spot since the + * read of the first half would be significantly slower than the read of + * the second half. + * + * Return: 0. Waiter on waitqueue will be woken on completion. + */ +static int measure_cycles_lat_fn(void *_plr) +{ + struct pseudo_lock_region *plr = _plr; + unsigned long i; + u64 start, end; +#ifdef CONFIG_KASAN + /* + * The registers used for local register variables are also used + * when KASAN is active. When KASAN is active we use a regular + * variable to ensure we always use a valid pointer to access memory. + * The cost is that accessing this pointer, which could be in + * cache, will be included in the measurement of memory read latency. + */ + void *mem_r; +#else +#ifdef CONFIG_X86_64 + register void *mem_r asm("rbx"); +#else + register void *mem_r asm("ebx"); +#endif /* CONFIG_X86_64 */ +#endif /* CONFIG_KASAN */ + + local_irq_disable(); + /* + * The wrmsr call may be reordered with the assignment below it. + * Call wrmsr as directly as possible to avoid tracing clobbering + * local register variable used for memory pointer. + */ + __wrmsr(MSR_MISC_FEATURE_CONTROL, prefetch_disable_bits, 0x0); + mem_r = plr->kmem; + /* + * Dummy execute of the time measurement to load the needed + * instructions into the L1 instruction cache. + */ + start = rdtsc_ordered(); + for (i = 0; i < plr->size; i += 32) { + start = rdtsc_ordered(); + asm volatile("mov (%0,%1,1), %%eax\n\t" + : + : "r" (mem_r), "r" (i) + : "%eax", "memory"); + end = rdtsc_ordered(); + trace_pseudo_lock_mem_latency((u32)(end - start)); + } + wrmsr(MSR_MISC_FEATURE_CONTROL, 0x0, 0x0); + local_irq_enable(); + plr->thread_done = 1; + wake_up_interruptible(&plr->lock_thread_wq); + return 0; +} + +static int measure_cycles_perf_fn(void *_plr) +{ + unsigned long long l3_hits = 0, l3_miss = 0; + u64 l3_hit_bits = 0, l3_miss_bits = 0; + struct pseudo_lock_region *plr = _plr; + unsigned long long l2_hits, l2_miss; + u64 l2_hit_bits, l2_miss_bits; + unsigned long i; +#ifdef CONFIG_KASAN + /* + * The registers used for local register variables are also used + * when KASAN is active. When KASAN is active we use regular variables + * at the cost of including cache access latency to these variables + * in the measurements. + */ + unsigned int line_size; + unsigned int size; + void *mem_r; +#else + register unsigned int line_size asm("esi"); + register unsigned int size asm("edi"); +#ifdef CONFIG_X86_64 + register void *mem_r asm("rbx"); +#else + register void *mem_r asm("ebx"); +#endif /* CONFIG_X86_64 */ +#endif /* CONFIG_KASAN */ + + /* + * Non-architectural event for the Goldmont Microarchitecture + * from Intel x86 Architecture Software Developer Manual (SDM): + * MEM_LOAD_UOPS_RETIRED D1H (event number) + * Umask values: + * L1_HIT 01H + * L2_HIT 02H + * L1_MISS 08H + * L2_MISS 10H + * + * On Broadwell Microarchitecture the MEM_LOAD_UOPS_RETIRED event + * has two "no fix" errata associated with it: BDM35 and BDM100. On + * this platform we use the following events instead: + * L2_RQSTS 24H (Documented in https://download.01.org/perfmon/BDW/) + * REFERENCES FFH + * MISS 3FH + * LONGEST_LAT_CACHE 2EH (Documented in SDM) + * REFERENCE 4FH + * MISS 41H + */ + + /* + * Start by setting flags for IA32_PERFEVTSELx: + * OS (Operating system mode) 0x2 + * INT (APIC interrupt enable) 0x10 + * EN (Enable counter) 0x40 + * + * Then add the Umask value and event number to select performance + * event. + */ + + switch (boot_cpu_data.x86_model) { + case INTEL_FAM6_ATOM_GOLDMONT: + case INTEL_FAM6_ATOM_GEMINI_LAKE: + l2_hit_bits = (0x52ULL << 16) | (0x2 << 8) | 0xd1; + l2_miss_bits = (0x52ULL << 16) | (0x10 << 8) | 0xd1; + break; + case INTEL_FAM6_BROADWELL_X: + /* On BDW the l2_hit_bits count references, not hits */ + l2_hit_bits = (0x52ULL << 16) | (0xff << 8) | 0x24; + l2_miss_bits = (0x52ULL << 16) | (0x3f << 8) | 0x24; + /* On BDW the l3_hit_bits count references, not hits */ + l3_hit_bits = (0x52ULL << 16) | (0x4f << 8) | 0x2e; + l3_miss_bits = (0x52ULL << 16) | (0x41 << 8) | 0x2e; + break; + default: + goto out; + } + + local_irq_disable(); + /* + * Call wrmsr direcly to avoid the local register variables from + * being overwritten due to reordering of their assignment with + * the wrmsr calls. + */ + __wrmsr(MSR_MISC_FEATURE_CONTROL, prefetch_disable_bits, 0x0); + /* Disable events and reset counters */ + pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0, 0x0); + pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 1, 0x0); + pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_PERFCTR0, 0x0); + pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_PERFCTR0 + 1, 0x0); + if (l3_hit_bits > 0) { + pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 2, 0x0); + pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 3, 0x0); + pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_PERFCTR0 + 2, 0x0); + pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_PERFCTR0 + 3, 0x0); + } + /* Set and enable the L2 counters */ + pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0, l2_hit_bits); + pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 1, l2_miss_bits); + if (l3_hit_bits > 0) { + pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 2, + l3_hit_bits); + pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 3, + l3_miss_bits); + } + mem_r = plr->kmem; + size = plr->size; + line_size = plr->line_size; + for (i = 0; i < size; i += line_size) { + asm volatile("mov (%0,%1,1), %%eax\n\t" + : + : "r" (mem_r), "r" (i) + : "%eax", "memory"); + } + /* + * Call wrmsr directly (no tracing) to not influence + * the cache access counters as they are disabled. + */ + pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0, + l2_hit_bits & ~(0x40ULL << 16)); + pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 1, + l2_miss_bits & ~(0x40ULL << 16)); + if (l3_hit_bits > 0) { + pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 2, + l3_hit_bits & ~(0x40ULL << 16)); + pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 3, + l3_miss_bits & ~(0x40ULL << 16)); + } + l2_hits = native_read_pmc(0); + l2_miss = native_read_pmc(1); + if (l3_hit_bits > 0) { + l3_hits = native_read_pmc(2); + l3_miss = native_read_pmc(3); + } + wrmsr(MSR_MISC_FEATURE_CONTROL, 0x0, 0x0); + local_irq_enable(); + /* + * On BDW we count references and misses, need to adjust. Sometimes + * the "hits" counter is a bit more than the references, for + * example, x references but x + 1 hits. To not report invalid + * hit values in this case we treat that as misses eaqual to + * references. + */ + if (boot_cpu_data.x86_model == INTEL_FAM6_BROADWELL_X) + l2_hits -= (l2_miss > l2_hits ? l2_hits : l2_miss); + trace_pseudo_lock_l2(l2_hits, l2_miss); + if (l3_hit_bits > 0) { + if (boot_cpu_data.x86_model == INTEL_FAM6_BROADWELL_X) + l3_hits -= (l3_miss > l3_hits ? l3_hits : l3_miss); + trace_pseudo_lock_l3(l3_hits, l3_miss); + } + +out: + plr->thread_done = 1; + wake_up_interruptible(&plr->lock_thread_wq); + return 0; +} + +/** + * pseudo_lock_measure_cycles - Trigger latency measure to pseudo-locked region + * + * The measurement of latency to access a pseudo-locked region should be + * done from a cpu that is associated with that pseudo-locked region. + * Determine which cpu is associated with this region and start a thread on + * that cpu to perform the measurement, wait for that thread to complete. + * + * Return: 0 on success, <0 on failure + */ +static int pseudo_lock_measure_cycles(struct rdtgroup *rdtgrp, int sel) +{ + struct pseudo_lock_region *plr = rdtgrp->plr; + struct task_struct *thread; + unsigned int cpu; + int ret = -1; + + cpus_read_lock(); + mutex_lock(&rdtgroup_mutex); + + if (rdtgrp->flags & RDT_DELETED) { + ret = -ENODEV; + goto out; + } + + plr->thread_done = 0; + cpu = cpumask_first(&plr->d->cpu_mask); + if (!cpu_online(cpu)) { + ret = -ENODEV; + goto out; + } + + if (sel == 1) + thread = kthread_create_on_node(measure_cycles_lat_fn, plr, + cpu_to_node(cpu), + "pseudo_lock_measure/%u", + cpu); + else if (sel == 2) + thread = kthread_create_on_node(measure_cycles_perf_fn, plr, + cpu_to_node(cpu), + "pseudo_lock_measure/%u", + cpu); + else + goto out; + + if (IS_ERR(thread)) { + ret = PTR_ERR(thread); + goto out; + } + kthread_bind(thread, cpu); + wake_up_process(thread); + + ret = wait_event_interruptible(plr->lock_thread_wq, + plr->thread_done == 1); + if (ret < 0) + goto out; + + ret = 0; + +out: + mutex_unlock(&rdtgroup_mutex); + cpus_read_unlock(); + return ret; +} + +static ssize_t pseudo_lock_measure_trigger(struct file *file, + const char __user *user_buf, + size_t count, loff_t *ppos) +{ + struct rdtgroup *rdtgrp = file->private_data; + size_t buf_size; + char buf[32]; + int ret; + int sel; + + buf_size = min(count, (sizeof(buf) - 1)); + if (copy_from_user(buf, user_buf, buf_size)) + return -EFAULT; + + buf[buf_size] = '\0'; + ret = kstrtoint(buf, 10, &sel); + if (ret == 0) { + if (sel != 1) + return -EINVAL; + ret = debugfs_file_get(file->f_path.dentry); + if (ret) + return ret; + ret = pseudo_lock_measure_cycles(rdtgrp, sel); + if (ret == 0) + ret = count; + debugfs_file_put(file->f_path.dentry); + } + + return ret; +} + +static const struct file_operations pseudo_measure_fops = { + .write = pseudo_lock_measure_trigger, + .open = simple_open, + .llseek = default_llseek, +}; + +/** + * rdtgroup_pseudo_lock_create - Create a pseudo-locked region + * @rdtgrp: resource group to which pseudo-lock region belongs + * + * Called when a resource group in the pseudo-locksetup mode receives a + * valid schemata that should be pseudo-locked. Since the resource group is + * in pseudo-locksetup mode the &struct pseudo_lock_region has already been + * allocated and initialized with the essential information. If a failure + * occurs the resource group remains in the pseudo-locksetup mode with the + * &struct pseudo_lock_region associated with it, but cleared from all + * information and ready for the user to re-attempt pseudo-locking by + * writing the schemata again. + * + * Return: 0 if the pseudo-locked region was successfully pseudo-locked, <0 + * on failure. Descriptive error will be written to last_cmd_status buffer. + */ +int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp) +{ + struct pseudo_lock_region *plr = rdtgrp->plr; + struct task_struct *thread; + unsigned int new_minor; + struct device *dev; + int ret; + + ret = pseudo_lock_region_alloc(plr); + if (ret < 0) + return ret; + + ret = pseudo_lock_cstates_constrain(plr); + if (ret < 0) { + ret = -EINVAL; + goto out_region; + } + + plr->thread_done = 0; + + thread = kthread_create_on_node(pseudo_lock_fn, rdtgrp, + cpu_to_node(plr->cpu), + "pseudo_lock/%u", plr->cpu); + if (IS_ERR(thread)) { + ret = PTR_ERR(thread); + rdt_last_cmd_printf("locking thread returned error %d\n", ret); + goto out_cstates; + } + + kthread_bind(thread, plr->cpu); + wake_up_process(thread); + + ret = wait_event_interruptible(plr->lock_thread_wq, + plr->thread_done == 1); + if (ret < 0) { + /* + * If the thread does not get on the CPU for whatever + * reason and the process which sets up the region is + * interrupted then this will leave the thread in runnable + * state and once it gets on the CPU it will derefence + * the cleared, but not freed, plr struct resulting in an + * empty pseudo-locking loop. + */ + rdt_last_cmd_puts("locking thread interrupted\n"); + goto out_cstates; + } + + ret = pseudo_lock_minor_get(&new_minor); + if (ret < 0) { + rdt_last_cmd_puts("unable to obtain a new minor number\n"); + goto out_cstates; + } + + /* + * Unlock access but do not release the reference. The + * pseudo-locked region will still be here on return. + * + * The mutex has to be released temporarily to avoid a potential + * deadlock with the mm->mmap_sem semaphore which is obtained in + * the device_create() and debugfs_create_dir() callpath below + * as well as before the mmap() callback is called. + */ + mutex_unlock(&rdtgroup_mutex); + + if (!IS_ERR_OR_NULL(debugfs_resctrl)) { + plr->debugfs_dir = debugfs_create_dir(rdtgrp->kn->name, + debugfs_resctrl); + if (!IS_ERR_OR_NULL(plr->debugfs_dir)) + debugfs_create_file("pseudo_lock_measure", 0200, + plr->debugfs_dir, rdtgrp, + &pseudo_measure_fops); + } + + dev = device_create(pseudo_lock_class, NULL, + MKDEV(pseudo_lock_major, new_minor), + rdtgrp, "%s", rdtgrp->kn->name); + + mutex_lock(&rdtgroup_mutex); + + if (IS_ERR(dev)) { + ret = PTR_ERR(dev); + rdt_last_cmd_printf("failed to create character device: %d\n", + ret); + goto out_debugfs; + } + + /* We released the mutex - check if group was removed while we did so */ + if (rdtgrp->flags & RDT_DELETED) { + ret = -ENODEV; + goto out_device; + } + + plr->minor = new_minor; + + rdtgrp->mode = RDT_MODE_PSEUDO_LOCKED; + closid_free(rdtgrp->closid); + rdtgroup_kn_mode_restore(rdtgrp, "cpus", 0444); + rdtgroup_kn_mode_restore(rdtgrp, "cpus_list", 0444); + + ret = 0; + goto out; + +out_device: + device_destroy(pseudo_lock_class, MKDEV(pseudo_lock_major, new_minor)); +out_debugfs: + debugfs_remove_recursive(plr->debugfs_dir); + pseudo_lock_minor_release(new_minor); +out_cstates: + pseudo_lock_cstates_relax(plr); +out_region: + pseudo_lock_region_clear(plr); +out: + return ret; +} + +/** + * rdtgroup_pseudo_lock_remove - Remove a pseudo-locked region + * @rdtgrp: resource group to which the pseudo-locked region belongs + * + * The removal of a pseudo-locked region can be initiated when the resource + * group is removed from user space via a "rmdir" from userspace or the + * unmount of the resctrl filesystem. On removal the resource group does + * not go back to pseudo-locksetup mode before it is removed, instead it is + * removed directly. There is thus assymmetry with the creation where the + * &struct pseudo_lock_region is removed here while it was not created in + * rdtgroup_pseudo_lock_create(). + * + * Return: void + */ +void rdtgroup_pseudo_lock_remove(struct rdtgroup *rdtgrp) +{ + struct pseudo_lock_region *plr = rdtgrp->plr; + + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) { + /* + * Default group cannot be a pseudo-locked region so we can + * free closid here. + */ + closid_free(rdtgrp->closid); + goto free; + } + + pseudo_lock_cstates_relax(plr); + debugfs_remove_recursive(rdtgrp->plr->debugfs_dir); + device_destroy(pseudo_lock_class, MKDEV(pseudo_lock_major, plr->minor)); + pseudo_lock_minor_release(plr->minor); + +free: + pseudo_lock_free(rdtgrp); +} + +static int pseudo_lock_dev_open(struct inode *inode, struct file *filp) +{ + struct rdtgroup *rdtgrp; + + mutex_lock(&rdtgroup_mutex); + + rdtgrp = region_find_by_minor(iminor(inode)); + if (!rdtgrp) { + mutex_unlock(&rdtgroup_mutex); + return -ENODEV; + } + + filp->private_data = rdtgrp; + atomic_inc(&rdtgrp->waitcount); + /* Perform a non-seekable open - llseek is not supported */ + filp->f_mode &= ~(FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE); + + mutex_unlock(&rdtgroup_mutex); + + return 0; +} + +static int pseudo_lock_dev_release(struct inode *inode, struct file *filp) +{ + struct rdtgroup *rdtgrp; + + mutex_lock(&rdtgroup_mutex); + rdtgrp = filp->private_data; + WARN_ON(!rdtgrp); + if (!rdtgrp) { + mutex_unlock(&rdtgroup_mutex); + return -ENODEV; + } + filp->private_data = NULL; + atomic_dec(&rdtgrp->waitcount); + mutex_unlock(&rdtgroup_mutex); + return 0; +} + +static int pseudo_lock_dev_mremap(struct vm_area_struct *area) +{ + /* Not supported */ + return -EINVAL; +} + +static const struct vm_operations_struct pseudo_mmap_ops = { + .mremap = pseudo_lock_dev_mremap, +}; + +static int pseudo_lock_dev_mmap(struct file *filp, struct vm_area_struct *vma) +{ + unsigned long vsize = vma->vm_end - vma->vm_start; + unsigned long off = vma->vm_pgoff << PAGE_SHIFT; + struct pseudo_lock_region *plr; + struct rdtgroup *rdtgrp; + unsigned long physical; + unsigned long psize; + + mutex_lock(&rdtgroup_mutex); + + rdtgrp = filp->private_data; + WARN_ON(!rdtgrp); + if (!rdtgrp) { + mutex_unlock(&rdtgroup_mutex); + return -ENODEV; + } + + plr = rdtgrp->plr; + + /* + * Task is required to run with affinity to the cpus associated + * with the pseudo-locked region. If this is not the case the task + * may be scheduled elsewhere and invalidate entries in the + * pseudo-locked region. + */ + if (!cpumask_subset(¤t->cpus_allowed, &plr->d->cpu_mask)) { + mutex_unlock(&rdtgroup_mutex); + return -EINVAL; + } + + physical = __pa(plr->kmem) >> PAGE_SHIFT; + psize = plr->size - off; + + if (off > plr->size) { + mutex_unlock(&rdtgroup_mutex); + return -ENOSPC; + } + + /* + * Ensure changes are carried directly to the memory being mapped, + * do not allow copy-on-write mapping. + */ + if (!(vma->vm_flags & VM_SHARED)) { + mutex_unlock(&rdtgroup_mutex); + return -EINVAL; + } + + if (vsize > psize) { + mutex_unlock(&rdtgroup_mutex); + return -ENOSPC; + } + + memset(plr->kmem + off, 0, vsize); + + if (remap_pfn_range(vma, vma->vm_start, physical + vma->vm_pgoff, + vsize, vma->vm_page_prot)) { + mutex_unlock(&rdtgroup_mutex); + return -EAGAIN; + } + vma->vm_ops = &pseudo_mmap_ops; + mutex_unlock(&rdtgroup_mutex); + return 0; +} + +static const struct file_operations pseudo_lock_dev_fops = { + .owner = THIS_MODULE, + .llseek = no_llseek, + .read = NULL, + .write = NULL, + .open = pseudo_lock_dev_open, + .release = pseudo_lock_dev_release, + .mmap = pseudo_lock_dev_mmap, +}; + +static char *pseudo_lock_devnode(struct device *dev, umode_t *mode) +{ + struct rdtgroup *rdtgrp; + + rdtgrp = dev_get_drvdata(dev); + if (mode) + *mode = 0600; + return kasprintf(GFP_KERNEL, "pseudo_lock/%s", rdtgrp->kn->name); +} + +int rdt_pseudo_lock_init(void) +{ + int ret; + + ret = register_chrdev(0, "pseudo_lock", &pseudo_lock_dev_fops); + if (ret < 0) + return ret; + + pseudo_lock_major = ret; + + pseudo_lock_class = class_create(THIS_MODULE, "pseudo_lock"); + if (IS_ERR(pseudo_lock_class)) { + ret = PTR_ERR(pseudo_lock_class); + unregister_chrdev(pseudo_lock_major, "pseudo_lock"); + return ret; + } + + pseudo_lock_class->devnode = pseudo_lock_devnode; + return 0; +} + +void rdt_pseudo_lock_release(void) +{ + class_destroy(pseudo_lock_class); + pseudo_lock_class = NULL; + unregister_chrdev(pseudo_lock_major, "pseudo_lock"); + pseudo_lock_major = 0; +} diff --git a/arch/x86/kernel/cpu/intel_rdt_pseudo_lock_event.h b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock_event.h new file mode 100644 index 000000000000..2c041e6d9f05 --- /dev/null +++ b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock_event.h @@ -0,0 +1,43 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM resctrl + +#if !defined(_TRACE_PSEUDO_LOCK_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_PSEUDO_LOCK_H + +#include <linux/tracepoint.h> + +TRACE_EVENT(pseudo_lock_mem_latency, + TP_PROTO(u32 latency), + TP_ARGS(latency), + TP_STRUCT__entry(__field(u32, latency)), + TP_fast_assign(__entry->latency = latency), + TP_printk("latency=%u", __entry->latency) + ); + +TRACE_EVENT(pseudo_lock_l2, + TP_PROTO(u64 l2_hits, u64 l2_miss), + TP_ARGS(l2_hits, l2_miss), + TP_STRUCT__entry(__field(u64, l2_hits) + __field(u64, l2_miss)), + TP_fast_assign(__entry->l2_hits = l2_hits; + __entry->l2_miss = l2_miss;), + TP_printk("hits=%llu miss=%llu", + __entry->l2_hits, __entry->l2_miss)); + +TRACE_EVENT(pseudo_lock_l3, + TP_PROTO(u64 l3_hits, u64 l3_miss), + TP_ARGS(l3_hits, l3_miss), + TP_STRUCT__entry(__field(u64, l3_hits) + __field(u64, l3_miss)), + TP_fast_assign(__entry->l3_hits = l3_hits; + __entry->l3_miss = l3_miss;), + TP_printk("hits=%llu miss=%llu", + __entry->l3_hits, __entry->l3_miss)); + +#endif /* _TRACE_PSEUDO_LOCK_H */ + +#undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH . +#define TRACE_INCLUDE_FILE intel_rdt_pseudo_lock_event +#include <trace/define_trace.h> diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c index 749856a2e736..d6d7ea7349d0 100644 --- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c +++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c @@ -20,7 +20,9 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include <linux/cacheinfo.h> #include <linux/cpu.h> +#include <linux/debugfs.h> #include <linux/fs.h> #include <linux/sysfs.h> #include <linux/kernfs.h> @@ -55,6 +57,8 @@ static struct kernfs_node *kn_mondata; static struct seq_buf last_cmd_status; static char last_cmd_status_buf[512]; +struct dentry *debugfs_resctrl; + void rdt_last_cmd_clear(void) { lockdep_assert_held(&rdtgroup_mutex); @@ -121,11 +125,65 @@ static int closid_alloc(void) return closid; } -static void closid_free(int closid) +void closid_free(int closid) { closid_free_map |= 1 << closid; } +/** + * closid_allocated - test if provided closid is in use + * @closid: closid to be tested + * + * Return: true if @closid is currently associated with a resource group, + * false if @closid is free + */ +static bool closid_allocated(unsigned int closid) +{ + return (closid_free_map & (1 << closid)) == 0; +} + +/** + * rdtgroup_mode_by_closid - Return mode of resource group with closid + * @closid: closid if the resource group + * + * Each resource group is associated with a @closid. Here the mode + * of a resource group can be queried by searching for it using its closid. + * + * Return: mode as &enum rdtgrp_mode of resource group with closid @closid + */ +enum rdtgrp_mode rdtgroup_mode_by_closid(int closid) +{ + struct rdtgroup *rdtgrp; + + list_for_each_entry(rdtgrp, &rdt_all_groups, rdtgroup_list) { + if (rdtgrp->closid == closid) + return rdtgrp->mode; + } + + return RDT_NUM_MODES; +} + +static const char * const rdt_mode_str[] = { + [RDT_MODE_SHAREABLE] = "shareable", + [RDT_MODE_EXCLUSIVE] = "exclusive", + [RDT_MODE_PSEUDO_LOCKSETUP] = "pseudo-locksetup", + [RDT_MODE_PSEUDO_LOCKED] = "pseudo-locked", +}; + +/** + * rdtgroup_mode_str - Return the string representation of mode + * @mode: the resource group mode as &enum rdtgroup_mode + * + * Return: string representation of valid mode, "unknown" otherwise + */ +static const char *rdtgroup_mode_str(enum rdtgrp_mode mode) +{ + if (mode < RDT_MODE_SHAREABLE || mode >= RDT_NUM_MODES) + return "unknown"; + + return rdt_mode_str[mode]; +} + /* set uid and gid of rdtgroup dirs and files to that of the creator */ static int rdtgroup_kn_set_ugid(struct kernfs_node *kn) { @@ -207,8 +265,12 @@ static int rdtgroup_cpus_show(struct kernfs_open_file *of, rdtgrp = rdtgroup_kn_lock_live(of->kn); if (rdtgrp) { - seq_printf(s, is_cpu_list(of) ? "%*pbl\n" : "%*pb\n", - cpumask_pr_args(&rdtgrp->cpu_mask)); + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) + seq_printf(s, is_cpu_list(of) ? "%*pbl\n" : "%*pb\n", + cpumask_pr_args(&rdtgrp->plr->d->cpu_mask)); + else + seq_printf(s, is_cpu_list(of) ? "%*pbl\n" : "%*pb\n", + cpumask_pr_args(&rdtgrp->cpu_mask)); } else { ret = -ENOENT; } @@ -394,6 +456,13 @@ static ssize_t rdtgroup_cpus_write(struct kernfs_open_file *of, goto unlock; } + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED || + rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) { + ret = -EINVAL; + rdt_last_cmd_puts("pseudo-locking in progress\n"); + goto unlock; + } + if (is_cpu_list(of)) ret = cpulist_parse(buf, newmask); else @@ -509,6 +578,32 @@ static int __rdtgroup_move_task(struct task_struct *tsk, return ret; } +/** + * rdtgroup_tasks_assigned - Test if tasks have been assigned to resource group + * @r: Resource group + * + * Return: 1 if tasks have been assigned to @r, 0 otherwise + */ +int rdtgroup_tasks_assigned(struct rdtgroup *r) +{ + struct task_struct *p, *t; + int ret = 0; + + lockdep_assert_held(&rdtgroup_mutex); + + rcu_read_lock(); + for_each_process_thread(p, t) { + if ((r->type == RDTCTRL_GROUP && t->closid == r->closid) || + (r->type == RDTMON_GROUP && t->rmid == r->mon.rmid)) { + ret = 1; + break; + } + } + rcu_read_unlock(); + + return ret; +} + static int rdtgroup_task_write_permission(struct task_struct *task, struct kernfs_open_file *of) { @@ -570,13 +665,22 @@ static ssize_t rdtgroup_tasks_write(struct kernfs_open_file *of, if (kstrtoint(strstrip(buf), 0, &pid) || pid < 0) return -EINVAL; rdtgrp = rdtgroup_kn_lock_live(of->kn); + if (!rdtgrp) { + rdtgroup_kn_unlock(of->kn); + return -ENOENT; + } rdt_last_cmd_clear(); - if (rdtgrp) - ret = rdtgroup_move_task(pid, rdtgrp, of); - else - ret = -ENOENT; + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED || + rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) { + ret = -EINVAL; + rdt_last_cmd_puts("pseudo-locking in progress\n"); + goto unlock; + } + ret = rdtgroup_move_task(pid, rdtgrp, of); + +unlock: rdtgroup_kn_unlock(of->kn); return ret ?: nbytes; @@ -662,6 +766,94 @@ static int rdt_shareable_bits_show(struct kernfs_open_file *of, return 0; } +/** + * rdt_bit_usage_show - Display current usage of resources + * + * A domain is a shared resource that can now be allocated differently. Here + * we display the current regions of the domain as an annotated bitmask. + * For each domain of this resource its allocation bitmask + * is annotated as below to indicate the current usage of the corresponding bit: + * 0 - currently unused + * X - currently available for sharing and used by software and hardware + * H - currently used by hardware only but available for software use + * S - currently used and shareable by software only + * E - currently used exclusively by one resource group + * P - currently pseudo-locked by one resource group + */ +static int rdt_bit_usage_show(struct kernfs_open_file *of, + struct seq_file *seq, void *v) +{ + struct rdt_resource *r = of->kn->parent->priv; + u32 sw_shareable = 0, hw_shareable = 0; + u32 exclusive = 0, pseudo_locked = 0; + struct rdt_domain *dom; + int i, hwb, swb, excl, psl; + enum rdtgrp_mode mode; + bool sep = false; + u32 *ctrl; + + mutex_lock(&rdtgroup_mutex); + hw_shareable = r->cache.shareable_bits; + list_for_each_entry(dom, &r->domains, list) { + if (sep) + seq_putc(seq, ';'); + ctrl = dom->ctrl_val; + sw_shareable = 0; + exclusive = 0; + seq_printf(seq, "%d=", dom->id); + for (i = 0; i < r->num_closid; i++, ctrl++) { + if (!closid_allocated(i)) + continue; + mode = rdtgroup_mode_by_closid(i); + switch (mode) { + case RDT_MODE_SHAREABLE: + sw_shareable |= *ctrl; + break; + case RDT_MODE_EXCLUSIVE: + exclusive |= *ctrl; + break; + case RDT_MODE_PSEUDO_LOCKSETUP: + /* + * RDT_MODE_PSEUDO_LOCKSETUP is possible + * here but not included since the CBM + * associated with this CLOSID in this mode + * is not initialized and no task or cpu can be + * assigned this CLOSID. + */ + break; + case RDT_MODE_PSEUDO_LOCKED: + case RDT_NUM_MODES: + WARN(1, + "invalid mode for closid %d\n", i); + break; + } + } + for (i = r->cache.cbm_len - 1; i >= 0; i--) { + pseudo_locked = dom->plr ? dom->plr->cbm : 0; + hwb = test_bit(i, (unsigned long *)&hw_shareable); + swb = test_bit(i, (unsigned long *)&sw_shareable); + excl = test_bit(i, (unsigned long *)&exclusive); + psl = test_bit(i, (unsigned long *)&pseudo_locked); + if (hwb && swb) + seq_putc(seq, 'X'); + else if (hwb && !swb) + seq_putc(seq, 'H'); + else if (!hwb && swb) + seq_putc(seq, 'S'); + else if (excl) + seq_putc(seq, 'E'); + else if (psl) + seq_putc(seq, 'P'); + else /* Unused bits remain */ + seq_putc(seq, '0'); + } + sep = true; + } + seq_putc(seq, '\n'); + mutex_unlock(&rdtgroup_mutex); + return 0; +} + static int rdt_min_bw_show(struct kernfs_open_file *of, struct seq_file *seq, void *v) { @@ -740,6 +932,269 @@ static ssize_t max_threshold_occ_write(struct kernfs_open_file *of, return nbytes; } +/* + * rdtgroup_mode_show - Display mode of this resource group + */ +static int rdtgroup_mode_show(struct kernfs_open_file *of, + struct seq_file *s, void *v) +{ + struct rdtgroup *rdtgrp; + + rdtgrp = rdtgroup_kn_lock_live(of->kn); + if (!rdtgrp) { + rdtgroup_kn_unlock(of->kn); + return -ENOENT; + } + + seq_printf(s, "%s\n", rdtgroup_mode_str(rdtgrp->mode)); + + rdtgroup_kn_unlock(of->kn); + return 0; +} + +/** + * rdtgroup_cbm_overlaps - Does CBM for intended closid overlap with other + * @r: Resource to which domain instance @d belongs. + * @d: The domain instance for which @closid is being tested. + * @cbm: Capacity bitmask being tested. + * @closid: Intended closid for @cbm. + * @exclusive: Only check if overlaps with exclusive resource groups + * + * Checks if provided @cbm intended to be used for @closid on domain + * @d overlaps with any other closids or other hardware usage associated + * with this domain. If @exclusive is true then only overlaps with + * resource groups in exclusive mode will be considered. If @exclusive + * is false then overlaps with any resource group or hardware entities + * will be considered. + * + * Return: false if CBM does not overlap, true if it does. + */ +bool rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_domain *d, + u32 _cbm, int closid, bool exclusive) +{ + unsigned long *cbm = (unsigned long *)&_cbm; + unsigned long *ctrl_b; + enum rdtgrp_mode mode; + u32 *ctrl; + int i; + + /* Check for any overlap with regions used by hardware directly */ + if (!exclusive) { + if (bitmap_intersects(cbm, + (unsigned long *)&r->cache.shareable_bits, + r->cache.cbm_len)) + return true; + } + + /* Check for overlap with other resource groups */ + ctrl = d->ctrl_val; + for (i = 0; i < r->num_closid; i++, ctrl++) { + ctrl_b = (unsigned long *)ctrl; + mode = rdtgroup_mode_by_closid(i); + if (closid_allocated(i) && i != closid && + mode != RDT_MODE_PSEUDO_LOCKSETUP) { + if (bitmap_intersects(cbm, ctrl_b, r->cache.cbm_len)) { + if (exclusive) { + if (mode == RDT_MODE_EXCLUSIVE) + return true; + continue; + } + return true; + } + } + } + + return false; +} + +/** + * rdtgroup_mode_test_exclusive - Test if this resource group can be exclusive + * + * An exclusive resource group implies that there should be no sharing of + * its allocated resources. At the time this group is considered to be + * exclusive this test can determine if its current schemata supports this + * setting by testing for overlap with all other resource groups. + * + * Return: true if resource group can be exclusive, false if there is overlap + * with allocations of other resource groups and thus this resource group + * cannot be exclusive. + */ +static bool rdtgroup_mode_test_exclusive(struct rdtgroup *rdtgrp) +{ + int closid = rdtgrp->closid; + struct rdt_resource *r; + struct rdt_domain *d; + + for_each_alloc_enabled_rdt_resource(r) { + list_for_each_entry(d, &r->domains, list) { + if (rdtgroup_cbm_overlaps(r, d, d->ctrl_val[closid], + rdtgrp->closid, false)) + return false; + } + } + + return true; +} + +/** + * rdtgroup_mode_write - Modify the resource group's mode + * + */ +static ssize_t rdtgroup_mode_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) +{ + struct rdtgroup *rdtgrp; + enum rdtgrp_mode mode; + int ret = 0; + + /* Valid input requires a trailing newline */ + if (nbytes == 0 || buf[nbytes - 1] != '\n') + return -EINVAL; + buf[nbytes - 1] = '\0'; + + rdtgrp = rdtgroup_kn_lock_live(of->kn); + if (!rdtgrp) { + rdtgroup_kn_unlock(of->kn); + return -ENOENT; + } + + rdt_last_cmd_clear(); + + mode = rdtgrp->mode; + + if ((!strcmp(buf, "shareable") && mode == RDT_MODE_SHAREABLE) || + (!strcmp(buf, "exclusive") && mode == RDT_MODE_EXCLUSIVE) || + (!strcmp(buf, "pseudo-locksetup") && + mode == RDT_MODE_PSEUDO_LOCKSETUP) || + (!strcmp(buf, "pseudo-locked") && mode == RDT_MODE_PSEUDO_LOCKED)) + goto out; + + if (mode == RDT_MODE_PSEUDO_LOCKED) { + rdt_last_cmd_printf("cannot change pseudo-locked group\n"); + ret = -EINVAL; + goto out; + } + + if (!strcmp(buf, "shareable")) { + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) { + ret = rdtgroup_locksetup_exit(rdtgrp); + if (ret) + goto out; + } + rdtgrp->mode = RDT_MODE_SHAREABLE; + } else if (!strcmp(buf, "exclusive")) { + if (!rdtgroup_mode_test_exclusive(rdtgrp)) { + rdt_last_cmd_printf("schemata overlaps\n"); + ret = -EINVAL; + goto out; + } + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) { + ret = rdtgroup_locksetup_exit(rdtgrp); + if (ret) + goto out; + } + rdtgrp->mode = RDT_MODE_EXCLUSIVE; + } else if (!strcmp(buf, "pseudo-locksetup")) { + ret = rdtgroup_locksetup_enter(rdtgrp); + if (ret) + goto out; + rdtgrp->mode = RDT_MODE_PSEUDO_LOCKSETUP; + } else { + rdt_last_cmd_printf("unknown/unsupported mode\n"); + ret = -EINVAL; + } + +out: + rdtgroup_kn_unlock(of->kn); + return ret ?: nbytes; +} + +/** + * rdtgroup_cbm_to_size - Translate CBM to size in bytes + * @r: RDT resource to which @d belongs. + * @d: RDT domain instance. + * @cbm: bitmask for which the size should be computed. + * + * The bitmask provided associated with the RDT domain instance @d will be + * translated into how many bytes it represents. The size in bytes is + * computed by first dividing the total cache size by the CBM length to + * determine how many bytes each bit in the bitmask represents. The result + * is multiplied with the number of bits set in the bitmask. + */ +unsigned int rdtgroup_cbm_to_size(struct rdt_resource *r, + struct rdt_domain *d, u32 cbm) +{ + struct cpu_cacheinfo *ci; + unsigned int size = 0; + int num_b, i; + + num_b = bitmap_weight((unsigned long *)&cbm, r->cache.cbm_len); + ci = get_cpu_cacheinfo(cpumask_any(&d->cpu_mask)); + for (i = 0; i < ci->num_leaves; i++) { + if (ci->info_list[i].level == r->cache_level) { + size = ci->info_list[i].size / r->cache.cbm_len * num_b; + break; + } + } + + return size; +} + +/** + * rdtgroup_size_show - Display size in bytes of allocated regions + * + * The "size" file mirrors the layout of the "schemata" file, printing the + * size in bytes of each region instead of the capacity bitmask. + * + */ +static int rdtgroup_size_show(struct kernfs_open_file *of, + struct seq_file *s, void *v) +{ + struct rdtgroup *rdtgrp; + struct rdt_resource *r; + struct rdt_domain *d; + unsigned int size; + bool sep = false; + u32 cbm; + + rdtgrp = rdtgroup_kn_lock_live(of->kn); + if (!rdtgrp) { + rdtgroup_kn_unlock(of->kn); + return -ENOENT; + } + + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) { + seq_printf(s, "%*s:", max_name_width, rdtgrp->plr->r->name); + size = rdtgroup_cbm_to_size(rdtgrp->plr->r, + rdtgrp->plr->d, + rdtgrp->plr->cbm); + seq_printf(s, "%d=%u\n", rdtgrp->plr->d->id, size); + goto out; + } + + for_each_alloc_enabled_rdt_resource(r) { + seq_printf(s, "%*s:", max_name_width, r->name); + list_for_each_entry(d, &r->domains, list) { + if (sep) + seq_putc(s, ';'); + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) { + size = 0; + } else { + cbm = d->ctrl_val[rdtgrp->closid]; + size = rdtgroup_cbm_to_size(r, d, cbm); + } + seq_printf(s, "%d=%u", d->id, size); + sep = true; + } + seq_putc(s, '\n'); + } + +out: + rdtgroup_kn_unlock(of->kn); + + return 0; +} + /* rdtgroup information files for one cache resource. */ static struct rftype res_common_files[] = { { @@ -792,6 +1247,13 @@ static struct rftype res_common_files[] = { .fflags = RF_CTRL_INFO | RFTYPE_RES_CACHE, }, { + .name = "bit_usage", + .mode = 0444, + .kf_ops = &rdtgroup_kf_single_ops, + .seq_show = rdt_bit_usage_show, + .fflags = RF_CTRL_INFO | RFTYPE_RES_CACHE, + }, + { .name = "min_bandwidth", .mode = 0444, .kf_ops = &rdtgroup_kf_single_ops, @@ -853,6 +1315,22 @@ static struct rftype res_common_files[] = { .seq_show = rdtgroup_schemata_show, .fflags = RF_CTRL_BASE, }, + { + .name = "mode", + .mode = 0644, + .kf_ops = &rdtgroup_kf_single_ops, + .write = rdtgroup_mode_write, + .seq_show = rdtgroup_mode_show, + .fflags = RF_CTRL_BASE, + }, + { + .name = "size", + .mode = 0444, + .kf_ops = &rdtgroup_kf_single_ops, + .seq_show = rdtgroup_size_show, + .fflags = RF_CTRL_BASE, + }, + }; static int rdtgroup_add_files(struct kernfs_node *kn, unsigned long fflags) @@ -883,6 +1361,103 @@ error: return ret; } +/** + * rdtgroup_kn_mode_restrict - Restrict user access to named resctrl file + * @r: The resource group with which the file is associated. + * @name: Name of the file + * + * The permissions of named resctrl file, directory, or link are modified + * to not allow read, write, or execute by any user. + * + * WARNING: This function is intended to communicate to the user that the + * resctrl file has been locked down - that it is not relevant to the + * particular state the system finds itself in. It should not be relied + * on to protect from user access because after the file's permissions + * are restricted the user can still change the permissions using chmod + * from the command line. + * + * Return: 0 on success, <0 on failure. + */ +int rdtgroup_kn_mode_restrict(struct rdtgroup *r, const char *name) +{ + struct iattr iattr = {.ia_valid = ATTR_MODE,}; + struct kernfs_node *kn; + int ret = 0; + + kn = kernfs_find_and_get_ns(r->kn, name, NULL); + if (!kn) + return -ENOENT; + + switch (kernfs_type(kn)) { + case KERNFS_DIR: + iattr.ia_mode = S_IFDIR; + break; + case KERNFS_FILE: + iattr.ia_mode = S_IFREG; + break; + case KERNFS_LINK: + iattr.ia_mode = S_IFLNK; + break; + } + + ret = kernfs_setattr(kn, &iattr); + kernfs_put(kn); + return ret; +} + +/** + * rdtgroup_kn_mode_restore - Restore user access to named resctrl file + * @r: The resource group with which the file is associated. + * @name: Name of the file + * @mask: Mask of permissions that should be restored + * + * Restore the permissions of the named file. If @name is a directory the + * permissions of its parent will be used. + * + * Return: 0 on success, <0 on failure. + */ +int rdtgroup_kn_mode_restore(struct rdtgroup *r, const char *name, + umode_t mask) +{ + struct iattr iattr = {.ia_valid = ATTR_MODE,}; + struct kernfs_node *kn, *parent; + struct rftype *rfts, *rft; + int ret, len; + + rfts = res_common_files; + len = ARRAY_SIZE(res_common_files); + + for (rft = rfts; rft < rfts + len; rft++) { + if (!strcmp(rft->name, name)) + iattr.ia_mode = rft->mode & mask; + } + + kn = kernfs_find_and_get_ns(r->kn, name, NULL); + if (!kn) + return -ENOENT; + + switch (kernfs_type(kn)) { + case KERNFS_DIR: + parent = kernfs_get_parent(kn); + if (parent) { + iattr.ia_mode |= parent->mode; + kernfs_put(parent); + } + iattr.ia_mode |= S_IFDIR; + break; + case KERNFS_FILE: + iattr.ia_mode |= S_IFREG; + break; + case KERNFS_LINK: + iattr.ia_mode |= S_IFLNK; + break; + } + + ret = kernfs_setattr(kn, &iattr); + kernfs_put(kn); + return ret; +} + static int rdtgroup_mkdir_info_resdir(struct rdt_resource *r, char *name, unsigned long fflags) { @@ -1224,6 +1799,9 @@ void rdtgroup_kn_unlock(struct kernfs_node *kn) if (atomic_dec_and_test(&rdtgrp->waitcount) && (rdtgrp->flags & RDT_DELETED)) { + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP || + rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) + rdtgroup_pseudo_lock_remove(rdtgrp); kernfs_unbreak_active_protection(kn); kernfs_put(rdtgrp->kn); kfree(rdtgrp); @@ -1289,10 +1867,16 @@ static struct dentry *rdt_mount(struct file_system_type *fs_type, rdtgroup_default.mon.mon_data_kn = kn_mondata; } + ret = rdt_pseudo_lock_init(); + if (ret) { + dentry = ERR_PTR(ret); + goto out_mondata; + } + dentry = kernfs_mount(fs_type, flags, rdt_root, RDTGROUP_SUPER_MAGIC, NULL); if (IS_ERR(dentry)) - goto out_mondata; + goto out_psl; if (rdt_alloc_capable) static_branch_enable_cpuslocked(&rdt_alloc_enable_key); @@ -1310,6 +1894,8 @@ static struct dentry *rdt_mount(struct file_system_type *fs_type, goto out; +out_psl: + rdt_pseudo_lock_release(); out_mondata: if (rdt_mon_capable) kernfs_remove(kn_mondata); @@ -1447,6 +2033,10 @@ static void rmdir_all_sub(void) if (rdtgrp == &rdtgroup_default) continue; + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP || + rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) + rdtgroup_pseudo_lock_remove(rdtgrp); + /* * Give any CPUs back to the default group. We cannot copy * cpu_online_mask because a CPU might have executed the @@ -1483,6 +2073,8 @@ static void rdt_kill_sb(struct super_block *sb) reset_all_ctrls(r); cdp_disable_all(); rmdir_all_sub(); + rdt_pseudo_lock_release(); + rdtgroup_default.mode = RDT_MODE_SHAREABLE; static_branch_disable_cpuslocked(&rdt_alloc_enable_key); static_branch_disable_cpuslocked(&rdt_mon_enable_key); static_branch_disable_cpuslocked(&rdt_enable_key); @@ -1682,6 +2274,114 @@ out_destroy: return ret; } +/** + * cbm_ensure_valid - Enforce validity on provided CBM + * @_val: Candidate CBM + * @r: RDT resource to which the CBM belongs + * + * The provided CBM represents all cache portions available for use. This + * may be represented by a bitmap that does not consist of contiguous ones + * and thus be an invalid CBM. + * Here the provided CBM is forced to be a valid CBM by only considering + * the first set of contiguous bits as valid and clearing all bits. + * The intention here is to provide a valid default CBM with which a new + * resource group is initialized. The user can follow this with a + * modification to the CBM if the default does not satisfy the + * requirements. + */ +static void cbm_ensure_valid(u32 *_val, struct rdt_resource *r) +{ + /* + * Convert the u32 _val to an unsigned long required by all the bit + * operations within this function. No more than 32 bits of this + * converted value can be accessed because all bit operations are + * additionally provided with cbm_len that is initialized during + * hardware enumeration using five bits from the EAX register and + * thus never can exceed 32 bits. + */ + unsigned long *val = (unsigned long *)_val; + unsigned int cbm_len = r->cache.cbm_len; + unsigned long first_bit, zero_bit; + + if (*val == 0) + return; + + first_bit = find_first_bit(val, cbm_len); + zero_bit = find_next_zero_bit(val, cbm_len, first_bit); + + /* Clear any remaining bits to ensure contiguous region */ + bitmap_clear(val, zero_bit, cbm_len - zero_bit); +} + +/** + * rdtgroup_init_alloc - Initialize the new RDT group's allocations + * + * A new RDT group is being created on an allocation capable (CAT) + * supporting system. Set this group up to start off with all usable + * allocations. That is, all shareable and unused bits. + * + * All-zero CBM is invalid. If there are no more shareable bits available + * on any domain then the entire allocation will fail. + */ +static int rdtgroup_init_alloc(struct rdtgroup *rdtgrp) +{ + u32 used_b = 0, unused_b = 0; + u32 closid = rdtgrp->closid; + struct rdt_resource *r; + enum rdtgrp_mode mode; + struct rdt_domain *d; + int i, ret; + u32 *ctrl; + + for_each_alloc_enabled_rdt_resource(r) { + list_for_each_entry(d, &r->domains, list) { + d->have_new_ctrl = false; + d->new_ctrl = r->cache.shareable_bits; + used_b = r->cache.shareable_bits; + ctrl = d->ctrl_val; + for (i = 0; i < r->num_closid; i++, ctrl++) { + if (closid_allocated(i) && i != closid) { + mode = rdtgroup_mode_by_closid(i); + if (mode == RDT_MODE_PSEUDO_LOCKSETUP) + break; + used_b |= *ctrl; + if (mode == RDT_MODE_SHAREABLE) + d->new_ctrl |= *ctrl; + } + } + if (d->plr && d->plr->cbm > 0) + used_b |= d->plr->cbm; + unused_b = used_b ^ (BIT_MASK(r->cache.cbm_len) - 1); + unused_b &= BIT_MASK(r->cache.cbm_len) - 1; + d->new_ctrl |= unused_b; + /* + * Force the initial CBM to be valid, user can + * modify the CBM based on system availability. + */ + cbm_ensure_valid(&d->new_ctrl, r); + if (bitmap_weight((unsigned long *) &d->new_ctrl, + r->cache.cbm_len) < + r->cache.min_cbm_bits) { + rdt_last_cmd_printf("no space on %s:%d\n", + r->name, d->id); + return -ENOSPC; + } + d->have_new_ctrl = true; + } + } + + for_each_alloc_enabled_rdt_resource(r) { + ret = update_domains(r, rdtgrp->closid); + if (ret < 0) { + rdt_last_cmd_puts("failed to initialize allocations\n"); + return ret; + } + rdtgrp->mode = RDT_MODE_SHAREABLE; + } + + return 0; +} + static int mkdir_rdt_prepare(struct kernfs_node *parent_kn, struct kernfs_node *prgrp_kn, const char *name, umode_t mode, @@ -1700,6 +2400,14 @@ static int mkdir_rdt_prepare(struct kernfs_node *parent_kn, goto out_unlock; } + if (rtype == RDTMON_GROUP && + (prdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP || + prdtgrp->mode == RDT_MODE_PSEUDO_LOCKED)) { + ret = -EINVAL; + rdt_last_cmd_puts("pseudo-locking in progress\n"); + goto out_unlock; + } + /* allocate the rdtgroup. */ rdtgrp = kzalloc(sizeof(*rdtgrp), GFP_KERNEL); if (!rdtgrp) { @@ -1840,6 +2548,10 @@ static int rdtgroup_mkdir_ctrl_mon(struct kernfs_node *parent_kn, ret = 0; rdtgrp->closid = closid; + ret = rdtgroup_init_alloc(rdtgrp); + if (ret < 0) + goto out_id_free; + list_add(&rdtgrp->rdtgroup_list, &rdt_all_groups); if (rdt_mon_capable) { @@ -1850,15 +2562,16 @@ static int rdtgroup_mkdir_ctrl_mon(struct kernfs_node *parent_kn, ret = mongroup_create_dir(kn, NULL, "mon_groups", NULL); if (ret) { rdt_last_cmd_puts("kernfs subdir error\n"); - goto out_id_free; + goto out_del_list; } } goto out_unlock; +out_del_list: + list_del(&rdtgrp->rdtgroup_list); out_id_free: closid_free(closid); - list_del(&rdtgrp->rdtgroup_list); out_common_fail: mkdir_rdt_prepare_clean(rdtgrp); out_unlock: @@ -1945,6 +2658,21 @@ static int rdtgroup_rmdir_mon(struct kernfs_node *kn, struct rdtgroup *rdtgrp, return 0; } +static int rdtgroup_ctrl_remove(struct kernfs_node *kn, + struct rdtgroup *rdtgrp) +{ + rdtgrp->flags = RDT_DELETED; + list_del(&rdtgrp->rdtgroup_list); + + /* + * one extra hold on this, will drop when we kfree(rdtgrp) + * in rdtgroup_kn_unlock() + */ + kernfs_get(kn); + kernfs_remove(rdtgrp->kn); + return 0; +} + static int rdtgroup_rmdir_ctrl(struct kernfs_node *kn, struct rdtgroup *rdtgrp, cpumask_var_t tmpmask) { @@ -1970,7 +2698,6 @@ static int rdtgroup_rmdir_ctrl(struct kernfs_node *kn, struct rdtgroup *rdtgrp, cpumask_or(tmpmask, tmpmask, &rdtgrp->cpu_mask); update_closid_rmid(tmpmask, NULL); - rdtgrp->flags = RDT_DELETED; closid_free(rdtgrp->closid); free_rmid(rdtgrp->mon.rmid); @@ -1979,14 +2706,7 @@ static int rdtgroup_rmdir_ctrl(struct kernfs_node *kn, struct rdtgroup *rdtgrp, */ free_all_child_rdtgrp(rdtgrp); - list_del(&rdtgrp->rdtgroup_list); - - /* - * one extra hold on this, will drop when we kfree(rdtgrp) - * in rdtgroup_kn_unlock() - */ - kernfs_get(kn); - kernfs_remove(rdtgrp->kn); + rdtgroup_ctrl_remove(kn, rdtgrp); return 0; } @@ -2014,13 +2734,19 @@ static int rdtgroup_rmdir(struct kernfs_node *kn) * If the rdtgroup is a mon group and parent directory * is a valid "mon_groups" directory, remove the mon group. */ - if (rdtgrp->type == RDTCTRL_GROUP && parent_kn == rdtgroup_default.kn) - ret = rdtgroup_rmdir_ctrl(kn, rdtgrp, tmpmask); - else if (rdtgrp->type == RDTMON_GROUP && - is_mon_groups(parent_kn, kn->name)) + if (rdtgrp->type == RDTCTRL_GROUP && parent_kn == rdtgroup_default.kn) { + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP || + rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) { + ret = rdtgroup_ctrl_remove(kn, rdtgrp); + } else { + ret = rdtgroup_rmdir_ctrl(kn, rdtgrp, tmpmask); + } + } else if (rdtgrp->type == RDTMON_GROUP && + is_mon_groups(parent_kn, kn->name)) { ret = rdtgroup_rmdir_mon(kn, rdtgrp, tmpmask); - else + } else { ret = -EPERM; + } out: rdtgroup_kn_unlock(kn); @@ -2046,7 +2772,8 @@ static int __init rdtgroup_setup_root(void) int ret; rdt_root = kernfs_create_root(&rdtgroup_kf_syscall_ops, - KERNFS_ROOT_CREATE_DEACTIVATED, + KERNFS_ROOT_CREATE_DEACTIVATED | + KERNFS_ROOT_EXTRA_OPEN_PERM_CHECK, &rdtgroup_default); if (IS_ERR(rdt_root)) return PTR_ERR(rdt_root); @@ -2102,6 +2829,29 @@ int __init rdtgroup_init(void) if (ret) goto cleanup_mountpoint; + /* + * Adding the resctrl debugfs directory here may not be ideal since + * it would let the resctrl debugfs directory appear on the debugfs + * filesystem before the resctrl filesystem is mounted. + * It may also be ok since that would enable debugging of RDT before + * resctrl is mounted. + * The reason why the debugfs directory is created here and not in + * rdt_mount() is because rdt_mount() takes rdtgroup_mutex and + * during the debugfs directory creation also &sb->s_type->i_mutex_key + * (the lockdep class of inode->i_rwsem). Other filesystem + * interactions (eg. SyS_getdents) have the lock ordering: + * &sb->s_type->i_mutex_key --> &mm->mmap_sem + * During mmap(), called with &mm->mmap_sem, the rdtgroup_mutex + * is taken, thus creating dependency: + * &mm->mmap_sem --> rdtgroup_mutex for the latter that can cause + * issues considering the other two lock dependencies. + * By creating the debugfs directory here we avoid a dependency + * that may cause deadlock (even though file operations cannot + * occur until the filesystem is mounted, but I do not know how to + * tell lockdep that). + */ + debugfs_resctrl = debugfs_create_dir("resctrl", NULL); + return 0; cleanup_mountpoint: @@ -2111,3 +2861,11 @@ cleanup_root: return ret; } + +void __exit rdtgroup_exit(void) +{ + debugfs_remove_recursive(debugfs_resctrl); + unregister_filesystem(&rdt_fs_type); + sysfs_remove_mount_point(fs_kobj, "resctrl"); + kernfs_destroy_root(rdt_root); +} diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 8c50754c09c1..4b767284b7f5 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -123,8 +123,8 @@ void mce_setup(struct mce *m) { memset(m, 0, sizeof(struct mce)); m->cpu = m->extcpu = smp_processor_id(); - /* We hope get_seconds stays lockless */ - m->time = get_seconds(); + /* need the internal __ version to avoid deadlocks */ + m->time = __ktime_get_real_seconds(); m->cpuvendor = boot_cpu_data.x86_vendor; m->cpuid = cpuid_eax(1); m->socketid = cpu_data(m->extcpu).phys_proc_id; @@ -1104,6 +1104,101 @@ static void mce_unmap_kpfn(unsigned long pfn) } #endif + +/* + * Cases where we avoid rendezvous handler timeout: + * 1) If this CPU is offline. + * + * 2) If crashing_cpu was set, e.g. we're entering kdump and we need to + * skip those CPUs which remain looping in the 1st kernel - see + * crash_nmi_callback(). + * + * Note: there still is a small window between kexec-ing and the new, + * kdump kernel establishing a new #MC handler where a broadcasted MCE + * might not get handled properly. + */ +static bool __mc_check_crashing_cpu(int cpu) +{ + if (cpu_is_offline(cpu) || + (crashing_cpu != -1 && crashing_cpu != cpu)) { + u64 mcgstatus; + + mcgstatus = mce_rdmsrl(MSR_IA32_MCG_STATUS); + if (mcgstatus & MCG_STATUS_RIPV) { + mce_wrmsrl(MSR_IA32_MCG_STATUS, 0); + return true; + } + } + return false; +} + +static void __mc_scan_banks(struct mce *m, struct mce *final, + unsigned long *toclear, unsigned long *valid_banks, + int no_way_out, int *worst) +{ + struct mca_config *cfg = &mca_cfg; + int severity, i; + + for (i = 0; i < cfg->banks; i++) { + __clear_bit(i, toclear); + if (!test_bit(i, valid_banks)) + continue; + + if (!mce_banks[i].ctl) + continue; + + m->misc = 0; + m->addr = 0; + m->bank = i; + + m->status = mce_rdmsrl(msr_ops.status(i)); + if (!(m->status & MCI_STATUS_VAL)) + continue; + + /* + * Corrected or non-signaled errors are handled by + * machine_check_poll(). Leave them alone, unless this panics. + */ + if (!(m->status & (cfg->ser ? MCI_STATUS_S : MCI_STATUS_UC)) && + !no_way_out) + continue; + + /* Set taint even when machine check was not enabled. */ + add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE); + + severity = mce_severity(m, cfg->tolerant, NULL, true); + + /* + * When machine check was for corrected/deferred handler don't + * touch, unless we're panicking. + */ + if ((severity == MCE_KEEP_SEVERITY || + severity == MCE_UCNA_SEVERITY) && !no_way_out) + continue; + + __set_bit(i, toclear); + + /* Machine check event was not enabled. Clear, but ignore. */ + if (severity == MCE_NO_SEVERITY) + continue; + + mce_read_aux(m, i); + + /* assuming valid severity level != 0 */ + m->severity = severity; + + mce_log(m); + + if (severity > *worst) { + *final = *m; + *worst = severity; + } + } + + /* mce_clear_state will clear *final, save locally for use later */ + *m = *final; +} + /* * The actual machine check handler. This only handles real * exceptions when something got corrupted coming in through int 18. @@ -1118,68 +1213,45 @@ static void mce_unmap_kpfn(unsigned long pfn) */ void do_machine_check(struct pt_regs *regs, long error_code) { + DECLARE_BITMAP(valid_banks, MAX_NR_BANKS); + DECLARE_BITMAP(toclear, MAX_NR_BANKS); struct mca_config *cfg = &mca_cfg; + int cpu = smp_processor_id(); + char *msg = "Unknown"; struct mce m, *final; - int i; int worst = 0; - int severity; /* * Establish sequential order between the CPUs entering the machine * check handler. */ int order = -1; + /* * If no_way_out gets set, there is no safe way to recover from this * MCE. If mca_cfg.tolerant is cranked up, we'll try anyway. */ int no_way_out = 0; + /* * If kill_it gets set, there might be a way to recover from this * error. */ int kill_it = 0; - DECLARE_BITMAP(toclear, MAX_NR_BANKS); - DECLARE_BITMAP(valid_banks, MAX_NR_BANKS); - char *msg = "Unknown"; /* * MCEs are always local on AMD. Same is determined by MCG_STATUS_LMCES * on Intel. */ int lmce = 1; - int cpu = smp_processor_id(); - /* - * Cases where we avoid rendezvous handler timeout: - * 1) If this CPU is offline. - * - * 2) If crashing_cpu was set, e.g. we're entering kdump and we need to - * skip those CPUs which remain looping in the 1st kernel - see - * crash_nmi_callback(). - * - * Note: there still is a small window between kexec-ing and the new, - * kdump kernel establishing a new #MC handler where a broadcasted MCE - * might not get handled properly. - */ - if (cpu_is_offline(cpu) || - (crashing_cpu != -1 && crashing_cpu != cpu)) { - u64 mcgstatus; - - mcgstatus = mce_rdmsrl(MSR_IA32_MCG_STATUS); - if (mcgstatus & MCG_STATUS_RIPV) { - mce_wrmsrl(MSR_IA32_MCG_STATUS, 0); - return; - } - } + if (__mc_check_crashing_cpu(cpu)) + return; ist_enter(regs); this_cpu_inc(mce_exception_count); - if (!cfg->banks) - goto out; - mce_gather_info(&m, regs); m.tsc = rdtsc(); @@ -1220,67 +1292,7 @@ void do_machine_check(struct pt_regs *regs, long error_code) order = mce_start(&no_way_out); } - for (i = 0; i < cfg->banks; i++) { - __clear_bit(i, toclear); - if (!test_bit(i, valid_banks)) - continue; - if (!mce_banks[i].ctl) - continue; - - m.misc = 0; - m.addr = 0; - m.bank = i; - - m.status = mce_rdmsrl(msr_ops.status(i)); - if ((m.status & MCI_STATUS_VAL) == 0) - continue; - - /* - * Non uncorrected or non signaled errors are handled by - * machine_check_poll. Leave them alone, unless this panics. - */ - if (!(m.status & (cfg->ser ? MCI_STATUS_S : MCI_STATUS_UC)) && - !no_way_out) - continue; - - /* - * Set taint even when machine check was not enabled. - */ - add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE); - - severity = mce_severity(&m, cfg->tolerant, NULL, true); - - /* - * When machine check was for corrected/deferred handler don't - * touch, unless we're panicing. - */ - if ((severity == MCE_KEEP_SEVERITY || - severity == MCE_UCNA_SEVERITY) && !no_way_out) - continue; - __set_bit(i, toclear); - if (severity == MCE_NO_SEVERITY) { - /* - * Machine check event was not enabled. Clear, but - * ignore. - */ - continue; - } - - mce_read_aux(&m, i); - - /* assuming valid severity level != 0 */ - m.severity = severity; - - mce_log(&m); - - if (severity > worst) { - *final = m; - worst = severity; - } - } - - /* mce_clear_state will clear *final, save locally for use later */ - m = *final; + __mc_scan_banks(&m, final, toclear, valid_banks, no_way_out, &worst); if (!no_way_out) mce_clear_state(toclear); @@ -1319,7 +1331,7 @@ void do_machine_check(struct pt_regs *regs, long error_code) if (worst > 0) mce_report_event(regs); mce_wrmsrl(MSR_IA32_MCG_STATUS, 0); -out: + sync_core(); if (worst != MCE_AR_SEVERITY && !kill_it) diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index 666a284116ac..9c8652974f8e 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -22,8 +22,6 @@ #include <asm/stacktrace.h> #include <asm/unwind.h> -#define OPCODE_BUFSIZE 64 - int panic_on_unrecovered_nmi; int panic_on_io_nmi; static int die_counter; @@ -93,26 +91,18 @@ static void printk_stack_address(unsigned long address, int reliable, */ void show_opcodes(u8 *rip, const char *loglvl) { - unsigned int code_prologue = OPCODE_BUFSIZE * 2 / 3; +#define PROLOGUE_SIZE 42 +#define EPILOGUE_SIZE 21 +#define OPCODE_BUFSIZE (PROLOGUE_SIZE + 1 + EPILOGUE_SIZE) u8 opcodes[OPCODE_BUFSIZE]; - u8 *ip; - int i; - - printk("%sCode: ", loglvl); - - ip = (u8 *)rip - code_prologue; - if (probe_kernel_read(opcodes, ip, OPCODE_BUFSIZE)) { - pr_cont("Bad RIP value.\n"); - return; - } - for (i = 0; i < OPCODE_BUFSIZE; i++, ip++) { - if (ip == rip) - pr_cont("<%02x> ", opcodes[i]); - else - pr_cont("%02x ", opcodes[i]); + if (probe_kernel_read(opcodes, rip - PROLOGUE_SIZE, OPCODE_BUFSIZE)) { + printk("%sCode: Bad RIP value.\n", loglvl); + } else { + printk("%sCode: %" __stringify(PROLOGUE_SIZE) "ph <%02x> %" + __stringify(EPILOGUE_SIZE) "ph\n", loglvl, opcodes, + opcodes[PROLOGUE_SIZE], opcodes + PROLOGUE_SIZE + 1); } - pr_cont("\n"); } void show_ip(struct pt_regs *regs, const char *loglvl) diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 8344dd2f310a..15ebc2fc166e 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -235,7 +235,7 @@ ENTRY(secondary_startup_64) * address given in m16:64. */ pushq $.Lafter_lret # put return address on stack for unwinder - xorq %rbp, %rbp # clear frame pointer + xorl %ebp, %ebp # clear frame pointer movq initial_code(%rip), %rax pushq $__KERNEL_CS # set correct cs pushq %rax # target address in negative space diff --git a/arch/x86/kernel/hw_breakpoint.c b/arch/x86/kernel/hw_breakpoint.c index 8771766d46b6..34a5c1715148 100644 --- a/arch/x86/kernel/hw_breakpoint.c +++ b/arch/x86/kernel/hw_breakpoint.c @@ -169,28 +169,29 @@ void arch_uninstall_hw_breakpoint(struct perf_event *bp) set_dr_addr_mask(0, i); } -/* - * Check for virtual address in kernel space. - */ -int arch_check_bp_in_kernelspace(struct perf_event *bp) +static int arch_bp_generic_len(int x86_len) { - unsigned int len; - unsigned long va; - struct arch_hw_breakpoint *info = counter_arch_bp(bp); - - va = info->address; - len = bp->attr.bp_len; - - /* - * We don't need to worry about va + len - 1 overflowing: - * we already require that va is aligned to a multiple of len. - */ - return (va >= TASK_SIZE_MAX) || ((va + len - 1) >= TASK_SIZE_MAX); + switch (x86_len) { + case X86_BREAKPOINT_LEN_1: + return HW_BREAKPOINT_LEN_1; + case X86_BREAKPOINT_LEN_2: + return HW_BREAKPOINT_LEN_2; + case X86_BREAKPOINT_LEN_4: + return HW_BREAKPOINT_LEN_4; +#ifdef CONFIG_X86_64 + case X86_BREAKPOINT_LEN_8: + return HW_BREAKPOINT_LEN_8; +#endif + default: + return -EINVAL; + } } int arch_bp_generic_fields(int x86_len, int x86_type, int *gen_len, int *gen_type) { + int len; + /* Type */ switch (x86_type) { case X86_BREAKPOINT_EXECUTE: @@ -211,42 +212,47 @@ int arch_bp_generic_fields(int x86_len, int x86_type, } /* Len */ - switch (x86_len) { - case X86_BREAKPOINT_LEN_1: - *gen_len = HW_BREAKPOINT_LEN_1; - break; - case X86_BREAKPOINT_LEN_2: - *gen_len = HW_BREAKPOINT_LEN_2; - break; - case X86_BREAKPOINT_LEN_4: - *gen_len = HW_BREAKPOINT_LEN_4; - break; -#ifdef CONFIG_X86_64 - case X86_BREAKPOINT_LEN_8: - *gen_len = HW_BREAKPOINT_LEN_8; - break; -#endif - default: + len = arch_bp_generic_len(x86_len); + if (len < 0) return -EINVAL; - } + *gen_len = len; return 0; } - -static int arch_build_bp_info(struct perf_event *bp) +/* + * Check for virtual address in kernel space. + */ +int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw) { - struct arch_hw_breakpoint *info = counter_arch_bp(bp); + unsigned long va; + int len; - info->address = bp->attr.bp_addr; + va = hw->address; + len = arch_bp_generic_len(hw->len); + WARN_ON_ONCE(len < 0); + + /* + * We don't need to worry about va + len - 1 overflowing: + * we already require that va is aligned to a multiple of len. + */ + return (va >= TASK_SIZE_MAX) || ((va + len - 1) >= TASK_SIZE_MAX); +} + +static int arch_build_bp_info(struct perf_event *bp, + const struct perf_event_attr *attr, + struct arch_hw_breakpoint *hw) +{ + hw->address = attr->bp_addr; + hw->mask = 0; /* Type */ - switch (bp->attr.bp_type) { + switch (attr->bp_type) { case HW_BREAKPOINT_W: - info->type = X86_BREAKPOINT_WRITE; + hw->type = X86_BREAKPOINT_WRITE; break; case HW_BREAKPOINT_W | HW_BREAKPOINT_R: - info->type = X86_BREAKPOINT_RW; + hw->type = X86_BREAKPOINT_RW; break; case HW_BREAKPOINT_X: /* @@ -254,23 +260,23 @@ static int arch_build_bp_info(struct perf_event *bp) * acceptable for kprobes. On non-kprobes kernels, we don't * allow kernel breakpoints at all. */ - if (bp->attr.bp_addr >= TASK_SIZE_MAX) { + if (attr->bp_addr >= TASK_SIZE_MAX) { #ifdef CONFIG_KPROBES - if (within_kprobe_blacklist(bp->attr.bp_addr)) + if (within_kprobe_blacklist(attr->bp_addr)) return -EINVAL; #else return -EINVAL; #endif } - info->type = X86_BREAKPOINT_EXECUTE; + hw->type = X86_BREAKPOINT_EXECUTE; /* * x86 inst breakpoints need to have a specific undefined len. * But we still need to check userspace is not trying to setup * an unsupported length, to get a range breakpoint for example. */ - if (bp->attr.bp_len == sizeof(long)) { - info->len = X86_BREAKPOINT_LEN_X; + if (attr->bp_len == sizeof(long)) { + hw->len = X86_BREAKPOINT_LEN_X; return 0; } default: @@ -278,28 +284,26 @@ static int arch_build_bp_info(struct perf_event *bp) } /* Len */ - info->mask = 0; - - switch (bp->attr.bp_len) { + switch (attr->bp_len) { case HW_BREAKPOINT_LEN_1: - info->len = X86_BREAKPOINT_LEN_1; + hw->len = X86_BREAKPOINT_LEN_1; break; case HW_BREAKPOINT_LEN_2: - info->len = X86_BREAKPOINT_LEN_2; + hw->len = X86_BREAKPOINT_LEN_2; break; case HW_BREAKPOINT_LEN_4: - info->len = X86_BREAKPOINT_LEN_4; + hw->len = X86_BREAKPOINT_LEN_4; break; #ifdef CONFIG_X86_64 case HW_BREAKPOINT_LEN_8: - info->len = X86_BREAKPOINT_LEN_8; + hw->len = X86_BREAKPOINT_LEN_8; break; #endif default: /* AMD range breakpoint */ - if (!is_power_of_2(bp->attr.bp_len)) + if (!is_power_of_2(attr->bp_len)) return -EINVAL; - if (bp->attr.bp_addr & (bp->attr.bp_len - 1)) + if (attr->bp_addr & (attr->bp_len - 1)) return -EINVAL; if (!boot_cpu_has(X86_FEATURE_BPEXT)) @@ -312,8 +316,8 @@ static int arch_build_bp_info(struct perf_event *bp) * breakpoints, then we'll have to check for kprobe-blacklisted * addresses anywhere in the range. */ - info->mask = bp->attr.bp_len - 1; - info->len = X86_BREAKPOINT_LEN_1; + hw->mask = attr->bp_len - 1; + hw->len = X86_BREAKPOINT_LEN_1; } return 0; @@ -322,22 +326,23 @@ static int arch_build_bp_info(struct perf_event *bp) /* * Validate the arch-specific HW Breakpoint register settings */ -int arch_validate_hwbkpt_settings(struct perf_event *bp) +int hw_breakpoint_arch_parse(struct perf_event *bp, + const struct perf_event_attr *attr, + struct arch_hw_breakpoint *hw) { - struct arch_hw_breakpoint *info = counter_arch_bp(bp); unsigned int align; int ret; - ret = arch_build_bp_info(bp); + ret = arch_build_bp_info(bp, attr, hw); if (ret) return ret; - switch (info->len) { + switch (hw->len) { case X86_BREAKPOINT_LEN_1: align = 0; - if (info->mask) - align = info->mask; + if (hw->mask) + align = hw->mask; break; case X86_BREAKPOINT_LEN_2: align = 1; @@ -358,7 +363,7 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp) * Check that the low-order bits of the address are appropriate * for the alignment implied by len. */ - if (info->address & align) + if (hw->address & align) return -EINVAL; return 0; diff --git a/arch/x86/kernel/kprobes/common.h b/arch/x86/kernel/kprobes/common.h index ae38dccf0c8f..2b949f4fd4d8 100644 --- a/arch/x86/kernel/kprobes/common.h +++ b/arch/x86/kernel/kprobes/common.h @@ -105,14 +105,4 @@ static inline unsigned long __recover_optprobed_insn(kprobe_opcode_t *buf, unsig } #endif -#ifdef CONFIG_KPROBES_ON_FTRACE -extern int skip_singlestep(struct kprobe *p, struct pt_regs *regs, - struct kprobe_ctlblk *kcb); -#else -static inline int skip_singlestep(struct kprobe *p, struct pt_regs *regs, - struct kprobe_ctlblk *kcb) -{ - return 0; -} -#endif #endif diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index 6f4d42377fe5..b0d1e81c96bb 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -66,8 +66,6 @@ #include "common.h" -void jprobe_return_end(void); - DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL; DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk); @@ -395,8 +393,6 @@ int __copy_instruction(u8 *dest, u8 *src, u8 *real, struct insn *insn) - (u8 *) real; if ((s64) (s32) newdisp != newdisp) { pr_err("Kprobes error: new displacement does not fit into s32 (%llx)\n", newdisp); - pr_err("\tSrc: %p, Dest: %p, old disp: %x\n", - src, real, insn->displacement.value); return 0; } disp = (u8 *) dest + insn_offset_displacement(insn); @@ -596,7 +592,6 @@ static void setup_singlestep(struct kprobe *p, struct pt_regs *regs, * stepping. */ regs->ip = (unsigned long)p->ainsn.insn; - preempt_enable_no_resched(); return; } #endif @@ -640,8 +635,7 @@ static int reenter_kprobe(struct kprobe *p, struct pt_regs *regs, * Raise a BUG or we'll continue in an endless reentering loop * and eventually a stack overflow. */ - printk(KERN_WARNING "Unrecoverable kprobe detected at %p.\n", - p->addr); + pr_err("Unrecoverable kprobe detected.\n"); dump_kprobe(p); BUG(); default: @@ -669,12 +663,10 @@ int kprobe_int3_handler(struct pt_regs *regs) addr = (kprobe_opcode_t *)(regs->ip - sizeof(kprobe_opcode_t)); /* - * We don't want to be preempted for the entire - * duration of kprobe processing. We conditionally - * re-enable preemption at the end of this function, - * and also in reenter_kprobe() and setup_singlestep(). + * We don't want to be preempted for the entire duration of kprobe + * processing. Since int3 and debug trap disables irqs and we clear + * IF while singlestepping, it must be no preemptible. */ - preempt_disable(); kcb = get_kprobe_ctlblk(); p = get_kprobe(addr); @@ -690,13 +682,14 @@ int kprobe_int3_handler(struct pt_regs *regs) /* * If we have no pre-handler or it returned 0, we * continue with normal processing. If we have a - * pre-handler and it returned non-zero, it prepped - * for calling the break_handler below on re-entry - * for jprobe processing, so get out doing nothing - * more here. + * pre-handler and it returned non-zero, that means + * user handler setup registers to exit to another + * instruction, we must skip the single stepping. */ if (!p->pre_handler || !p->pre_handler(p, regs)) setup_singlestep(p, regs, kcb, 0); + else + reset_current_kprobe(); return 1; } } else if (*addr != BREAKPOINT_INSTRUCTION) { @@ -710,18 +703,9 @@ int kprobe_int3_handler(struct pt_regs *regs) * the original instruction. */ regs->ip = (unsigned long)addr; - preempt_enable_no_resched(); return 1; - } else if (kprobe_running()) { - p = __this_cpu_read(current_kprobe); - if (p->break_handler && p->break_handler(p, regs)) { - if (!skip_singlestep(p, regs, kcb)) - setup_singlestep(p, regs, kcb, 0); - return 1; - } } /* else: not a kprobe fault; let the kernel handle it */ - preempt_enable_no_resched(); return 0; } NOKPROBE_SYMBOL(kprobe_int3_handler); @@ -972,8 +956,6 @@ int kprobe_debug_handler(struct pt_regs *regs) } reset_current_kprobe(); out: - preempt_enable_no_resched(); - /* * if somebody else is singlestepping across a probe point, flags * will have TF set, in which case, continue the remaining processing @@ -1020,7 +1002,6 @@ int kprobe_fault_handler(struct pt_regs *regs, int trapnr) restore_previous_kprobe(kcb); else reset_current_kprobe(); - preempt_enable_no_resched(); } else if (kcb->kprobe_status == KPROBE_HIT_ACTIVE || kcb->kprobe_status == KPROBE_HIT_SSDONE) { /* @@ -1083,93 +1064,6 @@ int kprobe_exceptions_notify(struct notifier_block *self, unsigned long val, } NOKPROBE_SYMBOL(kprobe_exceptions_notify); -int setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs) -{ - struct jprobe *jp = container_of(p, struct jprobe, kp); - unsigned long addr; - struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - - kcb->jprobe_saved_regs = *regs; - kcb->jprobe_saved_sp = stack_addr(regs); - addr = (unsigned long)(kcb->jprobe_saved_sp); - - /* - * As Linus pointed out, gcc assumes that the callee - * owns the argument space and could overwrite it, e.g. - * tailcall optimization. So, to be absolutely safe - * we also save and restore enough stack bytes to cover - * the argument area. - * Use __memcpy() to avoid KASAN stack out-of-bounds reports as we copy - * raw stack chunk with redzones: - */ - __memcpy(kcb->jprobes_stack, (kprobe_opcode_t *)addr, MIN_STACK_SIZE(addr)); - regs->ip = (unsigned long)(jp->entry); - - /* - * jprobes use jprobe_return() which skips the normal return - * path of the function, and this messes up the accounting of the - * function graph tracer to get messed up. - * - * Pause function graph tracing while performing the jprobe function. - */ - pause_graph_tracing(); - return 1; -} -NOKPROBE_SYMBOL(setjmp_pre_handler); - -void jprobe_return(void) -{ - struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - - /* Unpoison stack redzones in the frames we are going to jump over. */ - kasan_unpoison_stack_above_sp_to(kcb->jprobe_saved_sp); - - asm volatile ( -#ifdef CONFIG_X86_64 - " xchg %%rbx,%%rsp \n" -#else - " xchgl %%ebx,%%esp \n" -#endif - " int3 \n" - " .globl jprobe_return_end\n" - " jprobe_return_end: \n" - " nop \n"::"b" - (kcb->jprobe_saved_sp):"memory"); -} -NOKPROBE_SYMBOL(jprobe_return); -NOKPROBE_SYMBOL(jprobe_return_end); - -int longjmp_break_handler(struct kprobe *p, struct pt_regs *regs) -{ - struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - u8 *addr = (u8 *) (regs->ip - 1); - struct jprobe *jp = container_of(p, struct jprobe, kp); - void *saved_sp = kcb->jprobe_saved_sp; - - if ((addr > (u8 *) jprobe_return) && - (addr < (u8 *) jprobe_return_end)) { - if (stack_addr(regs) != saved_sp) { - struct pt_regs *saved_regs = &kcb->jprobe_saved_regs; - printk(KERN_ERR - "current sp %p does not match saved sp %p\n", - stack_addr(regs), saved_sp); - printk(KERN_ERR "Saved registers for jprobe %p\n", jp); - show_regs(saved_regs); - printk(KERN_ERR "Current registers\n"); - show_regs(regs); - BUG(); - } - /* It's OK to start function graph tracing again */ - unpause_graph_tracing(); - *regs = kcb->jprobe_saved_regs; - __memcpy(saved_sp, kcb->jprobes_stack, MIN_STACK_SIZE(saved_sp)); - preempt_enable_no_resched(); - return 1; - } - return 0; -} -NOKPROBE_SYMBOL(longjmp_break_handler); - bool arch_within_kprobe_blacklist(unsigned long addr) { bool is_in_entry_trampoline_section = false; diff --git a/arch/x86/kernel/kprobes/ftrace.c b/arch/x86/kernel/kprobes/ftrace.c index 8dc0161cec8f..ef819e19650b 100644 --- a/arch/x86/kernel/kprobes/ftrace.c +++ b/arch/x86/kernel/kprobes/ftrace.c @@ -25,36 +25,6 @@ #include "common.h" -static nokprobe_inline -void __skip_singlestep(struct kprobe *p, struct pt_regs *regs, - struct kprobe_ctlblk *kcb, unsigned long orig_ip) -{ - /* - * Emulate singlestep (and also recover regs->ip) - * as if there is a 5byte nop - */ - regs->ip = (unsigned long)p->addr + MCOUNT_INSN_SIZE; - if (unlikely(p->post_handler)) { - kcb->kprobe_status = KPROBE_HIT_SSDONE; - p->post_handler(p, regs, 0); - } - __this_cpu_write(current_kprobe, NULL); - if (orig_ip) - regs->ip = orig_ip; -} - -int skip_singlestep(struct kprobe *p, struct pt_regs *regs, - struct kprobe_ctlblk *kcb) -{ - if (kprobe_ftrace(p)) { - __skip_singlestep(p, regs, kcb, 0); - preempt_enable_no_resched(); - return 1; - } - return 0; -} -NOKPROBE_SYMBOL(skip_singlestep); - /* Ftrace callback handler for kprobes -- called under preepmt disabed */ void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *ops, struct pt_regs *regs) @@ -75,18 +45,25 @@ void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip, /* Kprobe handler expects regs->ip = ip + 1 as breakpoint hit */ regs->ip = ip + sizeof(kprobe_opcode_t); - /* To emulate trap based kprobes, preempt_disable here */ - preempt_disable(); __this_cpu_write(current_kprobe, p); kcb->kprobe_status = KPROBE_HIT_ACTIVE; if (!p->pre_handler || !p->pre_handler(p, regs)) { - __skip_singlestep(p, regs, kcb, orig_ip); - preempt_enable_no_resched(); + /* + * Emulate singlestep (and also recover regs->ip) + * as if there is a 5byte nop + */ + regs->ip = (unsigned long)p->addr + MCOUNT_INSN_SIZE; + if (unlikely(p->post_handler)) { + kcb->kprobe_status = KPROBE_HIT_SSDONE; + p->post_handler(p, regs, 0); + } + regs->ip = orig_ip; } /* - * If pre_handler returns !0, it sets regs->ip and - * resets current kprobe, and keep preempt count +1. + * If pre_handler returns !0, it changes regs->ip. We have to + * skip emulating post_handler. */ + __this_cpu_write(current_kprobe, NULL); } } NOKPROBE_SYMBOL(kprobe_ftrace_handler); diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c index 203d398802a3..eaf02f2e7300 100644 --- a/arch/x86/kernel/kprobes/opt.c +++ b/arch/x86/kernel/kprobes/opt.c @@ -491,7 +491,6 @@ int setup_detour_execution(struct kprobe *p, struct pt_regs *regs, int reenter) regs->ip = (unsigned long)op->optinsn.insn + TMPL_END_IDX; if (!reenter) reset_current_kprobe(); - preempt_enable_no_resched(); return 1; } return 0; diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 5b2300b818af..a37bda38d205 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -154,7 +154,7 @@ void kvm_async_pf_task_wait(u32 token, int interrupt_kernel) for (;;) { if (!n.halted) - prepare_to_swait(&n.wq, &wait, TASK_UNINTERRUPTIBLE); + prepare_to_swait_exclusive(&n.wq, &wait, TASK_UNINTERRUPTIBLE); if (hlist_unhashed(&n.link)) break; @@ -188,7 +188,7 @@ static void apf_task_wake_one(struct kvm_task_sleep_node *n) if (n->halted) smp_send_reschedule(n->cpu); else if (swq_has_sleeper(&n->wq)) - swake_up(&n->wq); + swake_up_one(&n->wq); } static void apf_task_wake_all(void) diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index 99dc79e76bdc..930c88341e4e 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -88,10 +88,12 @@ unsigned paravirt_patch_call(void *insnbuf, struct branch *b = insnbuf; unsigned long delta = (unsigned long)target - (addr+5); - if (tgt_clobbers & ~site_clobbers) - return len; /* target would clobber too much for this site */ - if (len < 5) + if (len < 5) { +#ifdef CONFIG_RETPOLINE + WARN_ONCE("Failing to patch indirect CALL in %ps\n", (void *)addr); +#endif return len; /* call too long for patch site */ + } b->opcode = 0xe8; /* call */ b->delta = delta; @@ -106,8 +108,12 @@ unsigned paravirt_patch_jmp(void *insnbuf, const void *target, struct branch *b = insnbuf; unsigned long delta = (unsigned long)target - (addr+5); - if (len < 5) + if (len < 5) { +#ifdef CONFIG_RETPOLINE + WARN_ONCE("Failing to patch indirect JMP in %ps\n", (void *)addr); +#endif return len; /* call too long for patch site */ + } b->opcode = 0xe9; /* jmp */ b->delta = delta; diff --git a/arch/x86/kernel/paravirt_patch_64.c b/arch/x86/kernel/paravirt_patch_64.c index 9edadabf04f6..9cb98f7b07c9 100644 --- a/arch/x86/kernel/paravirt_patch_64.c +++ b/arch/x86/kernel/paravirt_patch_64.c @@ -20,7 +20,7 @@ DEF_NATIVE(, mov64, "mov %rdi, %rax"); #if defined(CONFIG_PARAVIRT_SPINLOCKS) DEF_NATIVE(pv_lock_ops, queued_spin_unlock, "movb $0, (%rdi)"); -DEF_NATIVE(pv_lock_ops, vcpu_is_preempted, "xor %rax, %rax"); +DEF_NATIVE(pv_lock_ops, vcpu_is_preempted, "xor %eax, %eax"); #endif unsigned paravirt_patch_ident_32(void *insnbuf, unsigned len) diff --git a/arch/x86/kernel/pci-iommu_table.c b/arch/x86/kernel/pci-iommu_table.c index 4dfd90a75e63..2e9006c1e240 100644 --- a/arch/x86/kernel/pci-iommu_table.c +++ b/arch/x86/kernel/pci-iommu_table.c @@ -60,7 +60,7 @@ void __init check_iommu_entries(struct iommu_table_entry *start, printk(KERN_ERR "CYCLIC DEPENDENCY FOUND! %pS depends on %pS and vice-versa. BREAKING IT.\n", p->detect, q->detect); /* Heavy handed way..*/ - x->depend = 0; + x->depend = NULL; } } diff --git a/arch/x86/kernel/pcspeaker.c b/arch/x86/kernel/pcspeaker.c index da5190a1ea16..4a710ffffd9a 100644 --- a/arch/x86/kernel/pcspeaker.c +++ b/arch/x86/kernel/pcspeaker.c @@ -9,6 +9,6 @@ static __init int add_pcspkr(void) pd = platform_device_register_simple("pcspkr", -1, NULL, 0); - return IS_ERR(pd) ? PTR_ERR(pd) : 0; + return PTR_ERR_OR_ZERO(pd); } device_initcall(add_pcspkr); diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c index 093f2ea5dd56..7627455047c2 100644 --- a/arch/x86/kernel/stacktrace.c +++ b/arch/x86/kernel/stacktrace.c @@ -81,16 +81,6 @@ EXPORT_SYMBOL_GPL(save_stack_trace_tsk); #ifdef CONFIG_HAVE_RELIABLE_STACKTRACE -#define STACKTRACE_DUMP_ONCE(task) ({ \ - static bool __section(.data.unlikely) __dumped; \ - \ - if (!__dumped) { \ - __dumped = true; \ - WARN_ON(1); \ - show_stack(task, NULL); \ - } \ -}) - static int __always_inline __save_stack_trace_reliable(struct stack_trace *trace, struct task_struct *task) @@ -99,30 +89,25 @@ __save_stack_trace_reliable(struct stack_trace *trace, struct pt_regs *regs; unsigned long addr; - for (unwind_start(&state, task, NULL, NULL); !unwind_done(&state); + for (unwind_start(&state, task, NULL, NULL); + !unwind_done(&state) && !unwind_error(&state); unwind_next_frame(&state)) { regs = unwind_get_entry_regs(&state, NULL); if (regs) { + /* Success path for user tasks */ + if (user_mode(regs)) + goto success; + /* * Kernel mode registers on the stack indicate an * in-kernel interrupt or exception (e.g., preemption * or a page fault), which can make frame pointers * unreliable. */ - if (!user_mode(regs)) - return -EINVAL; - /* - * The last frame contains the user mode syscall - * pt_regs. Skip it and finish the unwind. - */ - unwind_next_frame(&state); - if (!unwind_done(&state)) { - STACKTRACE_DUMP_ONCE(task); + if (IS_ENABLED(CONFIG_FRAME_POINTER)) return -EINVAL; - } - break; } addr = unwind_get_return_address(&state); @@ -132,21 +117,22 @@ __save_stack_trace_reliable(struct stack_trace *trace, * generated code which __kernel_text_address() doesn't know * about. */ - if (!addr) { - STACKTRACE_DUMP_ONCE(task); + if (!addr) return -EINVAL; - } if (save_stack_address(trace, addr, false)) return -EINVAL; } /* Check for stack corruption */ - if (unwind_error(&state)) { - STACKTRACE_DUMP_ONCE(task); + if (unwind_error(&state)) + return -EINVAL; + + /* Success path for non-user tasks, i.e. kthreads and idle tasks */ + if (!(task->flags & (PF_KTHREAD | PF_IDLE))) return -EINVAL; - } +success: if (trace->nr_entries < trace->max_entries) trace->entries[trace->nr_entries++] = ULONG_MAX; diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c index feb28fee6cea..26038eacf74a 100644 --- a/arch/x86/kernel/unwind_orc.c +++ b/arch/x86/kernel/unwind_orc.c @@ -198,7 +198,7 @@ static int orc_sort_cmp(const void *_a, const void *_b) * whitelisted .o files which didn't get objtool generation. */ orc_a = cur_orc_table + (a - cur_orc_ip_table); - return orc_a->sp_reg == ORC_REG_UNDEFINED ? -1 : 1; + return orc_a->sp_reg == ORC_REG_UNDEFINED && !orc_a->end ? -1 : 1; } #ifdef CONFIG_MODULES @@ -352,7 +352,7 @@ static bool deref_stack_iret_regs(struct unwind_state *state, unsigned long addr bool unwind_next_frame(struct unwind_state *state) { - unsigned long ip_p, sp, orig_ip, prev_sp = state->sp; + unsigned long ip_p, sp, orig_ip = state->ip, prev_sp = state->sp; enum stack_type prev_type = state->stack_info.type; struct orc_entry *orc; bool indirect = false; @@ -363,9 +363,9 @@ bool unwind_next_frame(struct unwind_state *state) /* Don't let modules unload while we're reading their ORC data. */ preempt_disable(); - /* Have we reached the end? */ + /* End-of-stack check for user tasks: */ if (state->regs && user_mode(state->regs)) - goto done; + goto the_end; /* * Find the orc_entry associated with the text address. @@ -374,9 +374,16 @@ bool unwind_next_frame(struct unwind_state *state) * calls and calls to noreturn functions. */ orc = orc_find(state->signal ? state->ip : state->ip - 1); - if (!orc || orc->sp_reg == ORC_REG_UNDEFINED) - goto done; - orig_ip = state->ip; + if (!orc) + goto err; + + /* End-of-stack check for kernel threads: */ + if (orc->sp_reg == ORC_REG_UNDEFINED) { + if (!orc->end) + goto err; + + goto the_end; + } /* Find the previous frame's stack: */ switch (orc->sp_reg) { @@ -402,7 +409,7 @@ bool unwind_next_frame(struct unwind_state *state) if (!state->regs || !state->full_regs) { orc_warn("missing regs for base reg R10 at ip %pB\n", (void *)state->ip); - goto done; + goto err; } sp = state->regs->r10; break; @@ -411,7 +418,7 @@ bool unwind_next_frame(struct unwind_state *state) if (!state->regs || !state->full_regs) { orc_warn("missing regs for base reg R13 at ip %pB\n", (void *)state->ip); - goto done; + goto err; } sp = state->regs->r13; break; @@ -420,7 +427,7 @@ bool unwind_next_frame(struct unwind_state *state) if (!state->regs || !state->full_regs) { orc_warn("missing regs for base reg DI at ip %pB\n", (void *)state->ip); - goto done; + goto err; } sp = state->regs->di; break; @@ -429,7 +436,7 @@ bool unwind_next_frame(struct unwind_state *state) if (!state->regs || !state->full_regs) { orc_warn("missing regs for base reg DX at ip %pB\n", (void *)state->ip); - goto done; + goto err; } sp = state->regs->dx; break; @@ -437,12 +444,12 @@ bool unwind_next_frame(struct unwind_state *state) default: orc_warn("unknown SP base reg %d for ip %pB\n", orc->sp_reg, (void *)state->ip); - goto done; + goto err; } if (indirect) { if (!deref_stack_reg(state, sp, &sp)) - goto done; + goto err; } /* Find IP, SP and possibly regs: */ @@ -451,7 +458,7 @@ bool unwind_next_frame(struct unwind_state *state) ip_p = sp - sizeof(long); if (!deref_stack_reg(state, ip_p, &state->ip)) - goto done; + goto err; state->ip = ftrace_graph_ret_addr(state->task, &state->graph_idx, state->ip, (void *)ip_p); @@ -465,7 +472,7 @@ bool unwind_next_frame(struct unwind_state *state) if (!deref_stack_regs(state, sp, &state->ip, &state->sp)) { orc_warn("can't dereference registers at %p for ip %pB\n", (void *)sp, (void *)orig_ip); - goto done; + goto err; } state->regs = (struct pt_regs *)sp; @@ -477,7 +484,7 @@ bool unwind_next_frame(struct unwind_state *state) if (!deref_stack_iret_regs(state, sp, &state->ip, &state->sp)) { orc_warn("can't dereference iret registers at %p for ip %pB\n", (void *)sp, (void *)orig_ip); - goto done; + goto err; } state->regs = (void *)sp - IRET_FRAME_OFFSET; @@ -500,18 +507,18 @@ bool unwind_next_frame(struct unwind_state *state) case ORC_REG_PREV_SP: if (!deref_stack_reg(state, sp + orc->bp_offset, &state->bp)) - goto done; + goto err; break; case ORC_REG_BP: if (!deref_stack_reg(state, state->bp + orc->bp_offset, &state->bp)) - goto done; + goto err; break; default: orc_warn("unknown BP base reg %d for ip %pB\n", orc->bp_reg, (void *)orig_ip); - goto done; + goto err; } /* Prevent a recursive loop due to bad ORC data: */ @@ -520,13 +527,16 @@ bool unwind_next_frame(struct unwind_state *state) state->sp <= prev_sp) { orc_warn("stack going in the wrong direction? ip=%pB\n", (void *)orig_ip); - goto done; + goto err; } preempt_enable(); return true; -done: +err: + state->error = true; + +the_end: preempt_enable(); state->stack_info.type = STACK_TYPE_UNKNOWN; return false; diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index b5cd8465d44f..d536d457517b 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -1379,7 +1379,7 @@ static void apic_timer_expired(struct kvm_lapic *apic) * using swait_active() is safe. */ if (swait_active(q)) - swake_up(q); + swake_up_one(q); if (apic_lvtt_tscdeadline(apic)) ktimer->expired_tscdeadline = ktimer->tscdeadline; diff --git a/arch/x86/lib/memcpy_64.S b/arch/x86/lib/memcpy_64.S index 298ef1479240..3b24dc05251c 100644 --- a/arch/x86/lib/memcpy_64.S +++ b/arch/x86/lib/memcpy_64.S @@ -256,7 +256,7 @@ ENTRY(__memcpy_mcsafe) /* Copy successful. Return zero */ .L_done_memcpy_trap: - xorq %rax, %rax + xorl %eax, %eax ret ENDPROC(__memcpy_mcsafe) EXPORT_SYMBOL_GPL(__memcpy_mcsafe) diff --git a/arch/x86/mm/numa_emulation.c b/arch/x86/mm/numa_emulation.c index 34a2a3bfde9c..b54d52a2d00a 100644 --- a/arch/x86/mm/numa_emulation.c +++ b/arch/x86/mm/numa_emulation.c @@ -61,7 +61,7 @@ static int __init emu_setup_memblk(struct numa_meminfo *ei, eb->nid = nid; if (emu_nid_to_phys[nid] == NUMA_NO_NODE) - emu_nid_to_phys[nid] = nid; + emu_nid_to_phys[nid] = pb->nid; pb->start += size; if (pb->start >= pb->end) { @@ -198,40 +198,73 @@ static u64 __init find_end_of_node(u64 start, u64 max_addr, u64 size) return end; } +static u64 uniform_size(u64 max_addr, u64 base, u64 hole, int nr_nodes) +{ + unsigned long max_pfn = PHYS_PFN(max_addr); + unsigned long base_pfn = PHYS_PFN(base); + unsigned long hole_pfns = PHYS_PFN(hole); + + return PFN_PHYS((max_pfn - base_pfn - hole_pfns) / nr_nodes); +} + /* * Sets up fake nodes of `size' interleaved over physical nodes ranging from * `addr' to `max_addr'. * * Returns zero on success or negative on error. */ -static int __init split_nodes_size_interleave(struct numa_meminfo *ei, +static int __init split_nodes_size_interleave_uniform(struct numa_meminfo *ei, struct numa_meminfo *pi, - u64 addr, u64 max_addr, u64 size) + u64 addr, u64 max_addr, u64 size, + int nr_nodes, struct numa_memblk *pblk, + int nid) { nodemask_t physnode_mask = numa_nodes_parsed; + int i, ret, uniform = 0; u64 min_size; - int nid = 0; - int i, ret; - if (!size) + if ((!size && !nr_nodes) || (nr_nodes && !pblk)) return -1; + /* - * The limit on emulated nodes is MAX_NUMNODES, so the size per node is - * increased accordingly if the requested size is too small. This - * creates a uniform distribution of node sizes across the entire - * machine (but not necessarily over physical nodes). + * In the 'uniform' case split the passed in physical node by + * nr_nodes, in the non-uniform case, ignore the passed in + * physical block and try to create nodes of at least size + * @size. + * + * In the uniform case, split the nodes strictly by physical + * capacity, i.e. ignore holes. In the non-uniform case account + * for holes and treat @size as a minimum floor. */ - min_size = (max_addr - addr - mem_hole_size(addr, max_addr)) / MAX_NUMNODES; - min_size = max(min_size, FAKE_NODE_MIN_SIZE); - if ((min_size & FAKE_NODE_MIN_HASH_MASK) < min_size) - min_size = (min_size + FAKE_NODE_MIN_SIZE) & - FAKE_NODE_MIN_HASH_MASK; + if (!nr_nodes) + nr_nodes = MAX_NUMNODES; + else { + nodes_clear(physnode_mask); + node_set(pblk->nid, physnode_mask); + uniform = 1; + } + + if (uniform) { + min_size = uniform_size(max_addr, addr, 0, nr_nodes); + size = min_size; + } else { + /* + * The limit on emulated nodes is MAX_NUMNODES, so the + * size per node is increased accordingly if the + * requested size is too small. This creates a uniform + * distribution of node sizes across the entire machine + * (but not necessarily over physical nodes). + */ + min_size = uniform_size(max_addr, addr, + mem_hole_size(addr, max_addr), nr_nodes); + } + min_size = ALIGN(max(min_size, FAKE_NODE_MIN_SIZE), FAKE_NODE_MIN_SIZE); if (size < min_size) { pr_err("Fake node size %LuMB too small, increasing to %LuMB\n", size >> 20, min_size >> 20); size = min_size; } - size &= FAKE_NODE_MIN_HASH_MASK; + size = ALIGN_DOWN(size, FAKE_NODE_MIN_SIZE); /* * Fill physical nodes with fake nodes of size until there is no memory @@ -248,10 +281,14 @@ static int __init split_nodes_size_interleave(struct numa_meminfo *ei, node_clear(i, physnode_mask); continue; } + start = pi->blk[phys_blk].start; limit = pi->blk[phys_blk].end; - end = find_end_of_node(start, limit, size); + if (uniform) + end = start + size; + else + end = find_end_of_node(start, limit, size); /* * If there won't be at least FAKE_NODE_MIN_SIZE of * non-reserved memory in ZONE_DMA32 for the next node, @@ -266,7 +303,8 @@ static int __init split_nodes_size_interleave(struct numa_meminfo *ei, * next node, this one must extend to the end of the * physical node. */ - if (limit - end - mem_hole_size(end, limit) < size) + if ((limit - end - mem_hole_size(end, limit) < size) + && !uniform) end = limit; ret = emu_setup_memblk(ei, pi, nid++ % MAX_NUMNODES, @@ -276,7 +314,15 @@ static int __init split_nodes_size_interleave(struct numa_meminfo *ei, return ret; } } - return 0; + return nid; +} + +static int __init split_nodes_size_interleave(struct numa_meminfo *ei, + struct numa_meminfo *pi, + u64 addr, u64 max_addr, u64 size) +{ + return split_nodes_size_interleave_uniform(ei, pi, addr, max_addr, size, + 0, NULL, NUMA_NO_NODE); } int __init setup_emu2phys_nid(int *dfl_phys_nid) @@ -346,7 +392,28 @@ void __init numa_emulation(struct numa_meminfo *numa_meminfo, int numa_dist_cnt) * the fixed node size. Otherwise, if it is just a single number N, * split the system RAM into N fake nodes. */ - if (strchr(emu_cmdline, 'M') || strchr(emu_cmdline, 'G')) { + if (strchr(emu_cmdline, 'U')) { + nodemask_t physnode_mask = numa_nodes_parsed; + unsigned long n; + int nid = 0; + + n = simple_strtoul(emu_cmdline, &emu_cmdline, 0); + ret = -1; + for_each_node_mask(i, physnode_mask) { + ret = split_nodes_size_interleave_uniform(&ei, &pi, + pi.blk[i].start, pi.blk[i].end, 0, + n, &pi.blk[i], nid); + if (ret < 0) + break; + if (ret < n) { + pr_info("%s: phys: %d only got %d of %ld nodes, failing\n", + __func__, i, ret, n); + ret = -1; + break; + } + nid = ret; + } + } else if (strchr(emu_cmdline, 'M') || strchr(emu_cmdline, 'G')) { u64 size; size = memparse(emu_cmdline, &emu_cmdline); diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index 8e4e63d46d81..3ef095c70ae3 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -384,9 +384,6 @@ static int __init pgd_cache_init(void) */ pgd_cache = kmem_cache_create("pgd_cache", PGD_SIZE, PGD_ALIGN, SLAB_PANIC, NULL); - if (!pgd_cache) - return -ENOMEM; - return 0; } core_initcall(pgd_cache_init); @@ -782,28 +779,50 @@ int pmd_clear_huge(pmd_t *pmd) return 0; } +#ifdef CONFIG_X86_64 /** * pud_free_pmd_page - Clear pud entry and free pmd page. * @pud: Pointer to a PUD. + * @addr: Virtual address associated with pud. * - * Context: The pud range has been unmaped and TLB purged. + * Context: The pud range has been unmapped and TLB purged. * Return: 1 if clearing the entry succeeded. 0 otherwise. + * + * NOTE: Callers must allow a single page allocation. */ -int pud_free_pmd_page(pud_t *pud) +int pud_free_pmd_page(pud_t *pud, unsigned long addr) { - pmd_t *pmd; + pmd_t *pmd, *pmd_sv; + pte_t *pte; int i; if (pud_none(*pud)) return 1; pmd = (pmd_t *)pud_page_vaddr(*pud); + pmd_sv = (pmd_t *)__get_free_page(GFP_KERNEL); + if (!pmd_sv) + return 0; - for (i = 0; i < PTRS_PER_PMD; i++) - if (!pmd_free_pte_page(&pmd[i])) - return 0; + for (i = 0; i < PTRS_PER_PMD; i++) { + pmd_sv[i] = pmd[i]; + if (!pmd_none(pmd[i])) + pmd_clear(&pmd[i]); + } pud_clear(pud); + + /* INVLPG to clear all paging-structure caches */ + flush_tlb_kernel_range(addr, addr + PAGE_SIZE-1); + + for (i = 0; i < PTRS_PER_PMD; i++) { + if (!pmd_none(pmd_sv[i])) { + pte = (pte_t *)pmd_page_vaddr(pmd_sv[i]); + free_page((unsigned long)pte); + } + } + + free_page((unsigned long)pmd_sv); free_page((unsigned long)pmd); return 1; @@ -812,11 +831,12 @@ int pud_free_pmd_page(pud_t *pud) /** * pmd_free_pte_page - Clear pmd entry and free pte page. * @pmd: Pointer to a PMD. + * @addr: Virtual address associated with pmd. * - * Context: The pmd range has been unmaped and TLB purged. + * Context: The pmd range has been unmapped and TLB purged. * Return: 1 if clearing the entry succeeded. 0 otherwise. */ -int pmd_free_pte_page(pmd_t *pmd) +int pmd_free_pte_page(pmd_t *pmd, unsigned long addr) { pte_t *pte; @@ -825,8 +845,30 @@ int pmd_free_pte_page(pmd_t *pmd) pte = (pte_t *)pmd_page_vaddr(*pmd); pmd_clear(pmd); + + /* INVLPG to clear all paging-structure caches */ + flush_tlb_kernel_range(addr, addr + PAGE_SIZE-1); + free_page((unsigned long)pte); return 1; } + +#else /* !CONFIG_X86_64 */ + +int pud_free_pmd_page(pud_t *pud, unsigned long addr) +{ + return pud_none(*pud); +} + +/* + * Disable free page handling on x86-PAE. This assures that ioremap() + * does not update sync'd pmd entries. See vmalloc_sync_one(). + */ +int pmd_free_pte_page(pmd_t *pmd, unsigned long addr) +{ + return pmd_none(*pmd); +} + +#endif /* CONFIG_X86_64 */ #endif /* CONFIG_HAVE_ARCH_HUGE_VMAP */ diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 6eb1f34c3c85..752dbf4e0e50 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -7,6 +7,7 @@ #include <linux/export.h> #include <linux/cpu.h> #include <linux/debugfs.h> +#include <linux/gfp.h> #include <asm/tlbflush.h> #include <asm/mmu_context.h> @@ -35,7 +36,7 @@ * necessary invalidation by clearing out the 'ctx_id' which * forces a TLB flush when the context is loaded. */ -void clear_asid_other(void) +static void clear_asid_other(void) { u16 asid; @@ -185,8 +186,11 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, { struct mm_struct *real_prev = this_cpu_read(cpu_tlbstate.loaded_mm); u16 prev_asid = this_cpu_read(cpu_tlbstate.loaded_mm_asid); + bool was_lazy = this_cpu_read(cpu_tlbstate.is_lazy); unsigned cpu = smp_processor_id(); u64 next_tlb_gen; + bool need_flush; + u16 new_asid; /* * NB: The scheduler will call us with prev == next when switching @@ -240,20 +244,41 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, next->context.ctx_id); /* - * We don't currently support having a real mm loaded without - * our cpu set in mm_cpumask(). We have all the bookkeeping - * in place to figure out whether we would need to flush - * if our cpu were cleared in mm_cpumask(), but we don't - * currently use it. + * Even in lazy TLB mode, the CPU should stay set in the + * mm_cpumask. The TLB shootdown code can figure out from + * from cpu_tlbstate.is_lazy whether or not to send an IPI. */ if (WARN_ON_ONCE(real_prev != &init_mm && !cpumask_test_cpu(cpu, mm_cpumask(next)))) cpumask_set_cpu(cpu, mm_cpumask(next)); - return; + /* + * If the CPU is not in lazy TLB mode, we are just switching + * from one thread in a process to another thread in the same + * process. No TLB flush required. + */ + if (!was_lazy) + return; + + /* + * Read the tlb_gen to check whether a flush is needed. + * If the TLB is up to date, just use it. + * The barrier synchronizes with the tlb_gen increment in + * the TLB shootdown code. + */ + smp_mb(); + next_tlb_gen = atomic64_read(&next->context.tlb_gen); + if (this_cpu_read(cpu_tlbstate.ctxs[prev_asid].tlb_gen) == + next_tlb_gen) + return; + + /* + * TLB contents went out of date while we were in lazy + * mode. Fall through to the TLB switching code below. + */ + new_asid = prev_asid; + need_flush = true; } else { - u16 new_asid; - bool need_flush; u64 last_ctx_id = this_cpu_read(cpu_tlbstate.last_ctx_id); /* @@ -285,53 +310,60 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, sync_current_stack_to_mm(next); } - /* Stop remote flushes for the previous mm */ - VM_WARN_ON_ONCE(!cpumask_test_cpu(cpu, mm_cpumask(real_prev)) && - real_prev != &init_mm); - cpumask_clear_cpu(cpu, mm_cpumask(real_prev)); + /* + * Stop remote flushes for the previous mm. + * Skip kernel threads; we never send init_mm TLB flushing IPIs, + * but the bitmap manipulation can cause cache line contention. + */ + if (real_prev != &init_mm) { + VM_WARN_ON_ONCE(!cpumask_test_cpu(cpu, + mm_cpumask(real_prev))); + cpumask_clear_cpu(cpu, mm_cpumask(real_prev)); + } /* * Start remote flushes and then read tlb_gen. */ - cpumask_set_cpu(cpu, mm_cpumask(next)); + if (next != &init_mm) + cpumask_set_cpu(cpu, mm_cpumask(next)); next_tlb_gen = atomic64_read(&next->context.tlb_gen); choose_new_asid(next, next_tlb_gen, &new_asid, &need_flush); + } - if (need_flush) { - this_cpu_write(cpu_tlbstate.ctxs[new_asid].ctx_id, next->context.ctx_id); - this_cpu_write(cpu_tlbstate.ctxs[new_asid].tlb_gen, next_tlb_gen); - load_new_mm_cr3(next->pgd, new_asid, true); - - /* - * NB: This gets called via leave_mm() in the idle path - * where RCU functions differently. Tracing normally - * uses RCU, so we need to use the _rcuidle variant. - * - * (There is no good reason for this. The idle code should - * be rearranged to call this before rcu_idle_enter().) - */ - trace_tlb_flush_rcuidle(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL); - } else { - /* The new ASID is already up to date. */ - load_new_mm_cr3(next->pgd, new_asid, false); - - /* See above wrt _rcuidle. */ - trace_tlb_flush_rcuidle(TLB_FLUSH_ON_TASK_SWITCH, 0); - } + if (need_flush) { + this_cpu_write(cpu_tlbstate.ctxs[new_asid].ctx_id, next->context.ctx_id); + this_cpu_write(cpu_tlbstate.ctxs[new_asid].tlb_gen, next_tlb_gen); + load_new_mm_cr3(next->pgd, new_asid, true); /* - * Record last user mm's context id, so we can avoid - * flushing branch buffer with IBPB if we switch back - * to the same user. + * NB: This gets called via leave_mm() in the idle path + * where RCU functions differently. Tracing normally + * uses RCU, so we need to use the _rcuidle variant. + * + * (There is no good reason for this. The idle code should + * be rearranged to call this before rcu_idle_enter().) */ - if (next != &init_mm) - this_cpu_write(cpu_tlbstate.last_ctx_id, next->context.ctx_id); + trace_tlb_flush_rcuidle(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL); + } else { + /* The new ASID is already up to date. */ + load_new_mm_cr3(next->pgd, new_asid, false); - this_cpu_write(cpu_tlbstate.loaded_mm, next); - this_cpu_write(cpu_tlbstate.loaded_mm_asid, new_asid); + /* See above wrt _rcuidle. */ + trace_tlb_flush_rcuidle(TLB_FLUSH_ON_TASK_SWITCH, 0); } + /* + * Record last user mm's context id, so we can avoid + * flushing branch buffer with IBPB if we switch back + * to the same user. + */ + if (next != &init_mm) + this_cpu_write(cpu_tlbstate.last_ctx_id, next->context.ctx_id); + + this_cpu_write(cpu_tlbstate.loaded_mm, next); + this_cpu_write(cpu_tlbstate.loaded_mm_asid, new_asid); + load_mm_cr4(next); switch_ldt(real_prev, next); } @@ -354,20 +386,7 @@ void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk) if (this_cpu_read(cpu_tlbstate.loaded_mm) == &init_mm) return; - if (tlb_defer_switch_to_init_mm()) { - /* - * There's a significant optimization that may be possible - * here. We have accurate enough TLB flush tracking that we - * don't need to maintain coherence of TLB per se when we're - * lazy. We do, however, need to maintain coherence of - * paging-structure caches. We could, in principle, leave our - * old mm loaded and only switch to init_mm when - * tlb_remove_page() happens. - */ - this_cpu_write(cpu_tlbstate.is_lazy, true); - } else { - switch_mm(NULL, &init_mm, NULL); - } + this_cpu_write(cpu_tlbstate.is_lazy, true); } /* @@ -454,6 +473,9 @@ static void flush_tlb_func_common(const struct flush_tlb_info *f, * paging-structure cache to avoid speculatively reading * garbage into our TLB. Since switching to init_mm is barely * slower than a minimal flush, just switch to init_mm. + * + * This should be rare, with native_flush_tlb_others skipping + * IPIs to lazy TLB mode CPUs. */ switch_mm_irqs_off(NULL, &init_mm, NULL); return; @@ -560,6 +582,9 @@ static void flush_tlb_func_remote(void *info) void native_flush_tlb_others(const struct cpumask *cpumask, const struct flush_tlb_info *info) { + cpumask_var_t lazymask; + unsigned int cpu; + count_vm_tlb_event(NR_TLB_REMOTE_FLUSH); if (info->end == TLB_FLUSH_ALL) trace_tlb_flush(TLB_REMOTE_SEND_IPI, TLB_FLUSH_ALL); @@ -583,8 +608,6 @@ void native_flush_tlb_others(const struct cpumask *cpumask, * that UV should be updated so that smp_call_function_many(), * etc, are optimal on UV. */ - unsigned int cpu; - cpu = smp_processor_id(); cpumask = uv_flush_tlb_others(cpumask, info); if (cpumask) @@ -592,8 +615,29 @@ void native_flush_tlb_others(const struct cpumask *cpumask, (void *)info, 1); return; } - smp_call_function_many(cpumask, flush_tlb_func_remote, + + /* + * A temporary cpumask is used in order to skip sending IPIs + * to CPUs in lazy TLB state, while keeping them in mm_cpumask(mm). + * If the allocation fails, simply IPI every CPU in mm_cpumask. + */ + if (!alloc_cpumask_var(&lazymask, GFP_ATOMIC)) { + smp_call_function_many(cpumask, flush_tlb_func_remote, (void *)info, 1); + return; + } + + cpumask_copy(lazymask, cpumask); + + for_each_cpu(cpu, lazymask) { + if (per_cpu(cpu_tlbstate.is_lazy, cpu)) + cpumask_clear_cpu(cpu, lazymask); + } + + smp_call_function_many(lazymask, flush_tlb_func_remote, + (void *)info, 1); + + free_cpumask_var(lazymask); } /* @@ -646,6 +690,68 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start, put_cpu(); } +void tlb_flush_remove_tables_local(void *arg) +{ + struct mm_struct *mm = arg; + + if (this_cpu_read(cpu_tlbstate.loaded_mm) == mm && + this_cpu_read(cpu_tlbstate.is_lazy)) { + /* + * We're in lazy mode. We need to at least flush our + * paging-structure cache to avoid speculatively reading + * garbage into our TLB. Since switching to init_mm is barely + * slower than a minimal flush, just switch to init_mm. + */ + switch_mm_irqs_off(NULL, &init_mm, NULL); + } +} + +static void mm_fill_lazy_tlb_cpu_mask(struct mm_struct *mm, + struct cpumask *lazy_cpus) +{ + int cpu; + + for_each_cpu(cpu, mm_cpumask(mm)) { + if (!per_cpu(cpu_tlbstate.is_lazy, cpu)) + cpumask_set_cpu(cpu, lazy_cpus); + } +} + +void tlb_flush_remove_tables(struct mm_struct *mm) +{ + int cpu = get_cpu(); + cpumask_var_t lazy_cpus; + + if (cpumask_any_but(mm_cpumask(mm), cpu) >= nr_cpu_ids) { + put_cpu(); + return; + } + + if (!zalloc_cpumask_var(&lazy_cpus, GFP_ATOMIC)) { + /* + * If the cpumask allocation fails, do a brute force flush + * on all the CPUs that have this mm loaded. + */ + smp_call_function_many(mm_cpumask(mm), + tlb_flush_remove_tables_local, (void *)mm, 1); + put_cpu(); + return; + } + + /* + * CPUs with !is_lazy either received a TLB flush IPI while the user + * pages in this address range were unmapped, or have context switched + * and reloaded %CR3 since then. + * + * Shootdown IPIs at page table freeing time only need to be sent to + * CPUs that may have out of date TLB contents. + */ + mm_fill_lazy_tlb_cpu_mask(mm, lazy_cpus); + smp_call_function_many(lazy_cpus, + tlb_flush_remove_tables_local, (void *)mm, 1); + free_cpumask_var(lazy_cpus); + put_cpu(); +} static void do_flush_tlb_all(void *info) { diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c index 5f2eb3231607..ee5d08f25ce4 100644 --- a/arch/x86/platform/efi/efi_64.c +++ b/arch/x86/platform/efi/efi_64.c @@ -636,6 +636,8 @@ void efi_switch_mm(struct mm_struct *mm) #ifdef CONFIG_EFI_MIXED extern efi_status_t efi64_thunk(u32, ...); +static DEFINE_SPINLOCK(efi_runtime_lock); + #define runtime_service32(func) \ ({ \ u32 table = (u32)(unsigned long)efi.systab; \ @@ -657,17 +659,14 @@ extern efi_status_t efi64_thunk(u32, ...); #define efi_thunk(f, ...) \ ({ \ efi_status_t __s; \ - unsigned long __flags; \ u32 __func; \ \ - local_irq_save(__flags); \ arch_efi_call_virt_setup(); \ \ __func = runtime_service32(f); \ __s = efi64_thunk(__func, __VA_ARGS__); \ \ arch_efi_call_virt_teardown(); \ - local_irq_restore(__flags); \ \ __s; \ }) @@ -702,14 +701,17 @@ static efi_status_t efi_thunk_get_time(efi_time_t *tm, efi_time_cap_t *tc) { efi_status_t status; u32 phys_tm, phys_tc; + unsigned long flags; spin_lock(&rtc_lock); + spin_lock_irqsave(&efi_runtime_lock, flags); phys_tm = virt_to_phys_or_null(tm); phys_tc = virt_to_phys_or_null(tc); status = efi_thunk(get_time, phys_tm, phys_tc); + spin_unlock_irqrestore(&efi_runtime_lock, flags); spin_unlock(&rtc_lock); return status; @@ -719,13 +721,16 @@ static efi_status_t efi_thunk_set_time(efi_time_t *tm) { efi_status_t status; u32 phys_tm; + unsigned long flags; spin_lock(&rtc_lock); + spin_lock_irqsave(&efi_runtime_lock, flags); phys_tm = virt_to_phys_or_null(tm); status = efi_thunk(set_time, phys_tm); + spin_unlock_irqrestore(&efi_runtime_lock, flags); spin_unlock(&rtc_lock); return status; @@ -737,8 +742,10 @@ efi_thunk_get_wakeup_time(efi_bool_t *enabled, efi_bool_t *pending, { efi_status_t status; u32 phys_enabled, phys_pending, phys_tm; + unsigned long flags; spin_lock(&rtc_lock); + spin_lock_irqsave(&efi_runtime_lock, flags); phys_enabled = virt_to_phys_or_null(enabled); phys_pending = virt_to_phys_or_null(pending); @@ -747,6 +754,7 @@ efi_thunk_get_wakeup_time(efi_bool_t *enabled, efi_bool_t *pending, status = efi_thunk(get_wakeup_time, phys_enabled, phys_pending, phys_tm); + spin_unlock_irqrestore(&efi_runtime_lock, flags); spin_unlock(&rtc_lock); return status; @@ -757,13 +765,16 @@ efi_thunk_set_wakeup_time(efi_bool_t enabled, efi_time_t *tm) { efi_status_t status; u32 phys_tm; + unsigned long flags; spin_lock(&rtc_lock); + spin_lock_irqsave(&efi_runtime_lock, flags); phys_tm = virt_to_phys_or_null(tm); status = efi_thunk(set_wakeup_time, enabled, phys_tm); + spin_unlock_irqrestore(&efi_runtime_lock, flags); spin_unlock(&rtc_lock); return status; @@ -781,6 +792,9 @@ efi_thunk_get_variable(efi_char16_t *name, efi_guid_t *vendor, efi_status_t status; u32 phys_name, phys_vendor, phys_attr; u32 phys_data_size, phys_data; + unsigned long flags; + + spin_lock_irqsave(&efi_runtime_lock, flags); phys_data_size = virt_to_phys_or_null(data_size); phys_vendor = virt_to_phys_or_null(vendor); @@ -791,6 +805,8 @@ efi_thunk_get_variable(efi_char16_t *name, efi_guid_t *vendor, status = efi_thunk(get_variable, phys_name, phys_vendor, phys_attr, phys_data_size, phys_data); + spin_unlock_irqrestore(&efi_runtime_lock, flags); + return status; } @@ -800,6 +816,34 @@ efi_thunk_set_variable(efi_char16_t *name, efi_guid_t *vendor, { u32 phys_name, phys_vendor, phys_data; efi_status_t status; + unsigned long flags; + + spin_lock_irqsave(&efi_runtime_lock, flags); + + phys_name = virt_to_phys_or_null_size(name, efi_name_size(name)); + phys_vendor = virt_to_phys_or_null(vendor); + phys_data = virt_to_phys_or_null_size(data, data_size); + + /* If data_size is > sizeof(u32) we've got problems */ + status = efi_thunk(set_variable, phys_name, phys_vendor, + attr, data_size, phys_data); + + spin_unlock_irqrestore(&efi_runtime_lock, flags); + + return status; +} + +static efi_status_t +efi_thunk_set_variable_nonblocking(efi_char16_t *name, efi_guid_t *vendor, + u32 attr, unsigned long data_size, + void *data) +{ + u32 phys_name, phys_vendor, phys_data; + efi_status_t status; + unsigned long flags; + + if (!spin_trylock_irqsave(&efi_runtime_lock, flags)) + return EFI_NOT_READY; phys_name = virt_to_phys_or_null_size(name, efi_name_size(name)); phys_vendor = virt_to_phys_or_null(vendor); @@ -809,6 +853,8 @@ efi_thunk_set_variable(efi_char16_t *name, efi_guid_t *vendor, status = efi_thunk(set_variable, phys_name, phys_vendor, attr, data_size, phys_data); + spin_unlock_irqrestore(&efi_runtime_lock, flags); + return status; } @@ -819,6 +865,9 @@ efi_thunk_get_next_variable(unsigned long *name_size, { efi_status_t status; u32 phys_name_size, phys_name, phys_vendor; + unsigned long flags; + + spin_lock_irqsave(&efi_runtime_lock, flags); phys_name_size = virt_to_phys_or_null(name_size); phys_vendor = virt_to_phys_or_null(vendor); @@ -827,6 +876,8 @@ efi_thunk_get_next_variable(unsigned long *name_size, status = efi_thunk(get_next_variable, phys_name_size, phys_name, phys_vendor); + spin_unlock_irqrestore(&efi_runtime_lock, flags); + return status; } @@ -835,10 +886,15 @@ efi_thunk_get_next_high_mono_count(u32 *count) { efi_status_t status; u32 phys_count; + unsigned long flags; + + spin_lock_irqsave(&efi_runtime_lock, flags); phys_count = virt_to_phys_or_null(count); status = efi_thunk(get_next_high_mono_count, phys_count); + spin_unlock_irqrestore(&efi_runtime_lock, flags); + return status; } @@ -847,10 +903,15 @@ efi_thunk_reset_system(int reset_type, efi_status_t status, unsigned long data_size, efi_char16_t *data) { u32 phys_data; + unsigned long flags; + + spin_lock_irqsave(&efi_runtime_lock, flags); phys_data = virt_to_phys_or_null_size(data, data_size); efi_thunk(reset_system, reset_type, status, data_size, phys_data); + + spin_unlock_irqrestore(&efi_runtime_lock, flags); } static efi_status_t @@ -872,10 +933,13 @@ efi_thunk_query_variable_info(u32 attr, u64 *storage_space, { efi_status_t status; u32 phys_storage, phys_remaining, phys_max; + unsigned long flags; if (efi.runtime_version < EFI_2_00_SYSTEM_TABLE_REVISION) return EFI_UNSUPPORTED; + spin_lock_irqsave(&efi_runtime_lock, flags); + phys_storage = virt_to_phys_or_null(storage_space); phys_remaining = virt_to_phys_or_null(remaining_space); phys_max = virt_to_phys_or_null(max_variable_size); @@ -883,6 +947,35 @@ efi_thunk_query_variable_info(u32 attr, u64 *storage_space, status = efi_thunk(query_variable_info, attr, phys_storage, phys_remaining, phys_max); + spin_unlock_irqrestore(&efi_runtime_lock, flags); + + return status; +} + +static efi_status_t +efi_thunk_query_variable_info_nonblocking(u32 attr, u64 *storage_space, + u64 *remaining_space, + u64 *max_variable_size) +{ + efi_status_t status; + u32 phys_storage, phys_remaining, phys_max; + unsigned long flags; + + if (efi.runtime_version < EFI_2_00_SYSTEM_TABLE_REVISION) + return EFI_UNSUPPORTED; + + if (!spin_trylock_irqsave(&efi_runtime_lock, flags)) + return EFI_NOT_READY; + + phys_storage = virt_to_phys_or_null(storage_space); + phys_remaining = virt_to_phys_or_null(remaining_space); + phys_max = virt_to_phys_or_null(max_variable_size); + + status = efi_thunk(query_variable_info, attr, phys_storage, + phys_remaining, phys_max); + + spin_unlock_irqrestore(&efi_runtime_lock, flags); + return status; } @@ -908,9 +1001,11 @@ void efi_thunk_runtime_setup(void) efi.get_variable = efi_thunk_get_variable; efi.get_next_variable = efi_thunk_get_next_variable; efi.set_variable = efi_thunk_set_variable; + efi.set_variable_nonblocking = efi_thunk_set_variable_nonblocking; efi.get_next_high_mono_count = efi_thunk_get_next_high_mono_count; efi.reset_system = efi_thunk_reset_system; efi.query_variable_info = efi_thunk_query_variable_info; + efi.query_variable_info_nonblocking = efi_thunk_query_variable_info_nonblocking; efi.update_capsule = efi_thunk_update_capsule; efi.query_capsule_caps = efi_thunk_query_capsule_caps; } diff --git a/arch/x86/platform/efi/quirks.c b/arch/x86/platform/efi/quirks.c index 36c1f8b9f7e0..844d31cb8a0c 100644 --- a/arch/x86/platform/efi/quirks.c +++ b/arch/x86/platform/efi/quirks.c @@ -105,12 +105,11 @@ early_param("efi_no_storage_paranoia", setup_storage_paranoia); */ void efi_delete_dummy_variable(void) { - efi.set_variable((efi_char16_t *)efi_dummy_name, - &EFI_DUMMY_GUID, - EFI_VARIABLE_NON_VOLATILE | - EFI_VARIABLE_BOOTSERVICE_ACCESS | - EFI_VARIABLE_RUNTIME_ACCESS, - 0, NULL); + efi.set_variable_nonblocking((efi_char16_t *)efi_dummy_name, + &EFI_DUMMY_GUID, + EFI_VARIABLE_NON_VOLATILE | + EFI_VARIABLE_BOOTSERVICE_ACCESS | + EFI_VARIABLE_RUNTIME_ACCESS, 0, NULL); } /* @@ -249,7 +248,8 @@ void __init efi_arch_mem_reserve(phys_addr_t addr, u64 size) int num_entries; void *new; - if (efi_mem_desc_lookup(addr, &md)) { + if (efi_mem_desc_lookup(addr, &md) || + md.type != EFI_BOOT_SERVICES_DATA) { pr_err("Failed to lookup EFI memory descriptor for %pa\n", &addr); return; } diff --git a/arch/x86/platform/olpc/olpc.c b/arch/x86/platform/olpc/olpc.c index 7c3077e58fa0..f0e920fb98ad 100644 --- a/arch/x86/platform/olpc/olpc.c +++ b/arch/x86/platform/olpc/olpc.c @@ -311,10 +311,8 @@ static int __init add_xo1_platform_devices(void) return PTR_ERR(pdev); pdev = platform_device_register_simple("olpc-xo1", -1, NULL, 0); - if (IS_ERR(pdev)) - return PTR_ERR(pdev); - return 0; + return PTR_ERR_OR_ZERO(pdev); } static int olpc_xo1_ec_probe(struct platform_device *pdev) diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c index ca446da48fd2..e26dfad507c8 100644 --- a/arch/x86/platform/uv/tlb_uv.c +++ b/arch/x86/platform/uv/tlb_uv.c @@ -1607,8 +1607,6 @@ static int parse_tunables_write(struct bau_control *bcp, char *instr, *tunables[cnt].tunp = val; continue; } - if (q == p) - break; } return 0; } diff --git a/arch/x86/power/hibernate_asm_64.S b/arch/x86/power/hibernate_asm_64.S index ce8da3a0412c..fd369a6e9ff8 100644 --- a/arch/x86/power/hibernate_asm_64.S +++ b/arch/x86/power/hibernate_asm_64.S @@ -137,7 +137,7 @@ ENTRY(restore_registers) /* Saved in save_processor_state. */ lgdt saved_context_gdt_desc(%rax) - xorq %rax, %rax + xorl %eax, %eax /* tell the hibernation core that we've just restored the memory */ movq %rax, in_suspend(%rip) diff --git a/arch/x86/um/vdso/.gitignore b/arch/x86/um/vdso/.gitignore index 9cac6d072199..f8b69d84238e 100644 --- a/arch/x86/um/vdso/.gitignore +++ b/arch/x86/um/vdso/.gitignore @@ -1,2 +1 @@ -vdso-syms.lds vdso.lds diff --git a/arch/x86/um/vdso/Makefile b/arch/x86/um/vdso/Makefile index b2d6967262b2..822ccdba93ad 100644 --- a/arch/x86/um/vdso/Makefile +++ b/arch/x86/um/vdso/Makefile @@ -53,22 +53,6 @@ $(vobjs): KBUILD_CFLAGS += $(CFL) CFLAGS_REMOVE_vdso-note.o = -pg -fprofile-arcs -ftest-coverage CFLAGS_REMOVE_um_vdso.o = -pg -fprofile-arcs -ftest-coverage -targets += vdso-syms.lds -extra-$(VDSO64-y) += vdso-syms.lds - -# -# Match symbols in the DSO that look like VDSO*; produce a file of constants. -# -sed-vdsosym := -e 's/^00*/0/' \ - -e 's/^\([0-9a-fA-F]*\) . \(VDSO[a-zA-Z0-9_]*\)$$/\2 = 0x\1;/p' -quiet_cmd_vdsosym = VDSOSYM $@ -define cmd_vdsosym - $(NM) $< | LC_ALL=C sed -n $(sed-vdsosym) | LC_ALL=C sort > $@ -endef - -$(obj)/%-syms.lds: $(obj)/%.so.dbg FORCE - $(call if_changed,vdsosym) - # # The DSO images are built using a special linker script. # diff --git a/arch/xtensa/include/asm/atomic.h b/arch/xtensa/include/asm/atomic.h index e7a23f2a519a..7de0149e1cf7 100644 --- a/arch/xtensa/include/asm/atomic.h +++ b/arch/xtensa/include/asm/atomic.h @@ -197,107 +197,9 @@ ATOMIC_OPS(xor) #undef ATOMIC_OP_RETURN #undef ATOMIC_OP -/** - * atomic_sub_and_test - subtract value from variable and test result - * @i: integer value to subtract - * @v: pointer of type atomic_t - * - * Atomically subtracts @i from @v and returns - * true if the result is zero, or false for all - * other cases. - */ -#define atomic_sub_and_test(i,v) (atomic_sub_return((i),(v)) == 0) - -/** - * atomic_inc - increment atomic variable - * @v: pointer of type atomic_t - * - * Atomically increments @v by 1. - */ -#define atomic_inc(v) atomic_add(1,(v)) - -/** - * atomic_inc - increment atomic variable - * @v: pointer of type atomic_t - * - * Atomically increments @v by 1. - */ -#define atomic_inc_return(v) atomic_add_return(1,(v)) - -/** - * atomic_dec - decrement atomic variable - * @v: pointer of type atomic_t - * - * Atomically decrements @v by 1. - */ -#define atomic_dec(v) atomic_sub(1,(v)) - -/** - * atomic_dec_return - decrement atomic variable - * @v: pointer of type atomic_t - * - * Atomically decrements @v by 1. - */ -#define atomic_dec_return(v) atomic_sub_return(1,(v)) - -/** - * atomic_dec_and_test - decrement and test - * @v: pointer of type atomic_t - * - * Atomically decrements @v by 1 and - * returns true if the result is 0, or false for all other - * cases. - */ -#define atomic_dec_and_test(v) (atomic_sub_return(1,(v)) == 0) - -/** - * atomic_inc_and_test - increment and test - * @v: pointer of type atomic_t - * - * Atomically increments @v by 1 - * and returns true if the result is zero, or false for all - * other cases. - */ -#define atomic_inc_and_test(v) (atomic_add_return(1,(v)) == 0) - -/** - * atomic_add_negative - add and test if negative - * @v: pointer of type atomic_t - * @i: integer value to add - * - * Atomically adds @i to @v and returns true - * if the result is negative, or false when - * result is greater than or equal to zero. - */ -#define atomic_add_negative(i,v) (atomic_add_return((i),(v)) < 0) - #define atomic_cmpxchg(v, o, n) ((int)cmpxchg(&((v)->counter), (o), (n))) #define atomic_xchg(v, new) (xchg(&((v)->counter), new)) -/** - * __atomic_add_unless - add unless the number is a given value - * @v: pointer of type atomic_t - * @a: the amount to add to v... - * @u: ...unless v is equal to u. - * - * Atomically adds @a to @v, so long as it was not @u. - * Returns the old value of @v. - */ -static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u) -{ - int c, old; - c = atomic_read(v); - for (;;) { - if (unlikely(c == (u))) - break; - old = atomic_cmpxchg((v), c, c + (a)); - if (likely(old == c)) - break; - c = old; - } - return c; -} - #endif /* __KERNEL__ */ #endif /* _XTENSA_ATOMIC_H */ diff --git a/arch/xtensa/include/asm/hw_breakpoint.h b/arch/xtensa/include/asm/hw_breakpoint.h index dbe3053b284a..9f119c1ca0b5 100644 --- a/arch/xtensa/include/asm/hw_breakpoint.h +++ b/arch/xtensa/include/asm/hw_breakpoint.h @@ -30,13 +30,16 @@ struct arch_hw_breakpoint { u16 type; }; +struct perf_event_attr; struct perf_event; struct pt_regs; struct task_struct; int hw_breakpoint_slots(int type); -int arch_check_bp_in_kernelspace(struct perf_event *bp); -int arch_validate_hwbkpt_settings(struct perf_event *bp); +int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw); +int hw_breakpoint_arch_parse(struct perf_event *bp, + const struct perf_event_attr *attr, + struct arch_hw_breakpoint *hw); int hw_breakpoint_exceptions_notify(struct notifier_block *unused, unsigned long val, void *data); diff --git a/arch/xtensa/kernel/hw_breakpoint.c b/arch/xtensa/kernel/hw_breakpoint.c index b35656ab7dbd..c2e387c19cda 100644 --- a/arch/xtensa/kernel/hw_breakpoint.c +++ b/arch/xtensa/kernel/hw_breakpoint.c @@ -33,14 +33,13 @@ int hw_breakpoint_slots(int type) } } -int arch_check_bp_in_kernelspace(struct perf_event *bp) +int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw) { unsigned int len; unsigned long va; - struct arch_hw_breakpoint *info = counter_arch_bp(bp); - va = info->address; - len = bp->attr.bp_len; + va = hw->address; + len = hw->len; return (va >= TASK_SIZE) && ((va + len - 1) >= TASK_SIZE); } @@ -48,50 +47,41 @@ int arch_check_bp_in_kernelspace(struct perf_event *bp) /* * Construct an arch_hw_breakpoint from a perf_event. */ -static int arch_build_bp_info(struct perf_event *bp) +int hw_breakpoint_arch_parse(struct perf_event *bp, + const struct perf_event_attr *attr, + struct arch_hw_breakpoint *hw) { - struct arch_hw_breakpoint *info = counter_arch_bp(bp); - /* Type */ - switch (bp->attr.bp_type) { + switch (attr->bp_type) { case HW_BREAKPOINT_X: - info->type = XTENSA_BREAKPOINT_EXECUTE; + hw->type = XTENSA_BREAKPOINT_EXECUTE; break; case HW_BREAKPOINT_R: - info->type = XTENSA_BREAKPOINT_LOAD; + hw->type = XTENSA_BREAKPOINT_LOAD; break; case HW_BREAKPOINT_W: - info->type = XTENSA_BREAKPOINT_STORE; + hw->type = XTENSA_BREAKPOINT_STORE; break; case HW_BREAKPOINT_RW: - info->type = XTENSA_BREAKPOINT_LOAD | XTENSA_BREAKPOINT_STORE; + hw->type = XTENSA_BREAKPOINT_LOAD | XTENSA_BREAKPOINT_STORE; break; default: return -EINVAL; } /* Len */ - info->len = bp->attr.bp_len; - if (info->len < 1 || info->len > 64 || !is_power_of_2(info->len)) + hw->len = attr->bp_len; + if (hw->len < 1 || hw->len > 64 || !is_power_of_2(hw->len)) return -EINVAL; /* Address */ - info->address = bp->attr.bp_addr; - if (info->address & (info->len - 1)) + hw->address = attr->bp_addr; + if (hw->address & (hw->len - 1)) return -EINVAL; return 0; } -int arch_validate_hwbkpt_settings(struct perf_event *bp) -{ - int ret; - - /* Build the arch_hw_breakpoint. */ - ret = arch_build_bp_info(bp); - return ret; -} - int hw_breakpoint_exceptions_notify(struct notifier_block *unused, unsigned long val, void *data) { diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index fa0729c1e776..d81c653b9bf6 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -61,7 +61,7 @@ static int atomic_inc_return_safe(atomic_t *v) { unsigned int counter; - counter = (unsigned int)__atomic_add_unless(v, 1, 0); + counter = (unsigned int)atomic_fetch_add_unless(v, 1, 0); if (counter <= (unsigned int)INT_MAX) return (int)counter; diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index 7436b2d27fa3..a390c6d4f72d 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -298,7 +298,8 @@ static void reset_bdev(struct zram *zram) zram->backing_dev = NULL; zram->old_block_size = 0; zram->bdev = NULL; - + zram->disk->queue->backing_dev_info->capabilities |= + BDI_CAP_SYNCHRONOUS_IO; kvfree(zram->bitmap); zram->bitmap = NULL; } @@ -400,6 +401,18 @@ static ssize_t backing_dev_store(struct device *dev, zram->backing_dev = backing_dev; zram->bitmap = bitmap; zram->nr_pages = nr_pages; + /* + * With writeback feature, zram does asynchronous IO so it's no longer + * synchronous device so let's remove synchronous io flag. Othewise, + * upper layer(e.g., swap) could wait IO completion rather than + * (submit and return), which will cause system sluggish. + * Furthermore, when the IO function returns(e.g., swap_readpage), + * upper layer expects IO was done so it could deallocate the page + * freely but in fact, IO is going on so finally could cause + * use-after-free when the IO is really done. + */ + zram->disk->queue->backing_dev_info->capabilities &= + ~BDI_CAP_SYNCHRONOUS_IO; up_write(&zram->init_lock); pr_info("setup backing device %s\n", file_name); diff --git a/drivers/clocksource/Makefile b/drivers/clocksource/Makefile index 00caf37e52f9..c070cc7992e9 100644 --- a/drivers/clocksource/Makefile +++ b/drivers/clocksource/Makefile @@ -49,7 +49,7 @@ obj-$(CONFIG_CLKSRC_SAMSUNG_PWM) += samsung_pwm_timer.o obj-$(CONFIG_FSL_FTM_TIMER) += fsl_ftm_timer.o obj-$(CONFIG_VF_PIT_TIMER) += vf_pit_timer.o obj-$(CONFIG_CLKSRC_QCOM) += qcom-timer.o -obj-$(CONFIG_MTK_TIMER) += mtk_timer.o +obj-$(CONFIG_MTK_TIMER) += timer-mediatek.o obj-$(CONFIG_CLKSRC_PISTACHIO) += time-pistachio.o obj-$(CONFIG_CLKSRC_TI_32K) += timer-ti-32k.o obj-$(CONFIG_CLKSRC_NPS) += timer-nps.o diff --git a/drivers/clocksource/mtk_timer.c b/drivers/clocksource/mtk_timer.c deleted file mode 100644 index f9b724fd9950..000000000000 --- a/drivers/clocksource/mtk_timer.c +++ /dev/null @@ -1,268 +0,0 @@ -/* - * Mediatek SoCs General-Purpose Timer handling. - * - * Copyright (C) 2014 Matthias Brugger - * - * Matthias Brugger <matthias.bgg@gmail.com> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - */ - -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt - -#include <linux/clk.h> -#include <linux/clockchips.h> -#include <linux/interrupt.h> -#include <linux/irq.h> -#include <linux/irqreturn.h> -#include <linux/of.h> -#include <linux/of_address.h> -#include <linux/of_irq.h> -#include <linux/sched_clock.h> -#include <linux/slab.h> - -#define GPT_IRQ_EN_REG 0x00 -#define GPT_IRQ_ENABLE(val) BIT((val) - 1) -#define GPT_IRQ_ACK_REG 0x08 -#define GPT_IRQ_ACK(val) BIT((val) - 1) - -#define TIMER_CTRL_REG(val) (0x10 * (val)) -#define TIMER_CTRL_OP(val) (((val) & 0x3) << 4) -#define TIMER_CTRL_OP_ONESHOT (0) -#define TIMER_CTRL_OP_REPEAT (1) -#define TIMER_CTRL_OP_FREERUN (3) -#define TIMER_CTRL_CLEAR (2) -#define TIMER_CTRL_ENABLE (1) -#define TIMER_CTRL_DISABLE (0) - -#define TIMER_CLK_REG(val) (0x04 + (0x10 * (val))) -#define TIMER_CLK_SRC(val) (((val) & 0x1) << 4) -#define TIMER_CLK_SRC_SYS13M (0) -#define TIMER_CLK_SRC_RTC32K (1) -#define TIMER_CLK_DIV1 (0x0) -#define TIMER_CLK_DIV2 (0x1) - -#define TIMER_CNT_REG(val) (0x08 + (0x10 * (val))) -#define TIMER_CMP_REG(val) (0x0C + (0x10 * (val))) - -#define GPT_CLK_EVT 1 -#define GPT_CLK_SRC 2 - -struct mtk_clock_event_device { - void __iomem *gpt_base; - u32 ticks_per_jiffy; - struct clock_event_device dev; -}; - -static void __iomem *gpt_sched_reg __read_mostly; - -static u64 notrace mtk_read_sched_clock(void) -{ - return readl_relaxed(gpt_sched_reg); -} - -static inline struct mtk_clock_event_device *to_mtk_clk( - struct clock_event_device *c) -{ - return container_of(c, struct mtk_clock_event_device, dev); -} - -static void mtk_clkevt_time_stop(struct mtk_clock_event_device *evt, u8 timer) -{ - u32 val; - - val = readl(evt->gpt_base + TIMER_CTRL_REG(timer)); - writel(val & ~TIMER_CTRL_ENABLE, evt->gpt_base + - TIMER_CTRL_REG(timer)); -} - -static void mtk_clkevt_time_setup(struct mtk_clock_event_device *evt, - unsigned long delay, u8 timer) -{ - writel(delay, evt->gpt_base + TIMER_CMP_REG(timer)); -} - -static void mtk_clkevt_time_start(struct mtk_clock_event_device *evt, - bool periodic, u8 timer) -{ - u32 val; - - /* Acknowledge interrupt */ - writel(GPT_IRQ_ACK(timer), evt->gpt_base + GPT_IRQ_ACK_REG); - - val = readl(evt->gpt_base + TIMER_CTRL_REG(timer)); - - /* Clear 2 bit timer operation mode field */ - val &= ~TIMER_CTRL_OP(0x3); - - if (periodic) - val |= TIMER_CTRL_OP(TIMER_CTRL_OP_REPEAT); - else - val |= TIMER_CTRL_OP(TIMER_CTRL_OP_ONESHOT); - - writel(val | TIMER_CTRL_ENABLE | TIMER_CTRL_CLEAR, - evt->gpt_base + TIMER_CTRL_REG(timer)); -} - -static int mtk_clkevt_shutdown(struct clock_event_device *clk) -{ - mtk_clkevt_time_stop(to_mtk_clk(clk), GPT_CLK_EVT); - return 0; -} - -static int mtk_clkevt_set_periodic(struct clock_event_device *clk) -{ - struct mtk_clock_event_device *evt = to_mtk_clk(clk); - - mtk_clkevt_time_stop(evt, GPT_CLK_EVT); - mtk_clkevt_time_setup(evt, evt->ticks_per_jiffy, GPT_CLK_EVT); - mtk_clkevt_time_start(evt, true, GPT_CLK_EVT); - return 0; -} - -static int mtk_clkevt_next_event(unsigned long event, - struct clock_event_device *clk) -{ - struct mtk_clock_event_device *evt = to_mtk_clk(clk); - - mtk_clkevt_time_stop(evt, GPT_CLK_EVT); - mtk_clkevt_time_setup(evt, event, GPT_CLK_EVT); - mtk_clkevt_time_start(evt, false, GPT_CLK_EVT); - - return 0; -} - -static irqreturn_t mtk_timer_interrupt(int irq, void *dev_id) -{ - struct mtk_clock_event_device *evt = dev_id; - - /* Acknowledge timer0 irq */ - writel(GPT_IRQ_ACK(GPT_CLK_EVT), evt->gpt_base + GPT_IRQ_ACK_REG); - evt->dev.event_handler(&evt->dev); - - return IRQ_HANDLED; -} - -static void -__init mtk_timer_setup(struct mtk_clock_event_device *evt, u8 timer, u8 option) -{ - writel(TIMER_CTRL_CLEAR | TIMER_CTRL_DISABLE, - evt->gpt_base + TIMER_CTRL_REG(timer)); - - writel(TIMER_CLK_SRC(TIMER_CLK_SRC_SYS13M) | TIMER_CLK_DIV1, - evt->gpt_base + TIMER_CLK_REG(timer)); - - writel(0x0, evt->gpt_base + TIMER_CMP_REG(timer)); - - writel(TIMER_CTRL_OP(option) | TIMER_CTRL_ENABLE, - evt->gpt_base + TIMER_CTRL_REG(timer)); -} - -static void mtk_timer_enable_irq(struct mtk_clock_event_device *evt, u8 timer) -{ - u32 val; - - /* Disable all interrupts */ - writel(0x0, evt->gpt_base + GPT_IRQ_EN_REG); - - /* Acknowledge all spurious pending interrupts */ - writel(0x3f, evt->gpt_base + GPT_IRQ_ACK_REG); - - val = readl(evt->gpt_base + GPT_IRQ_EN_REG); - writel(val | GPT_IRQ_ENABLE(timer), - evt->gpt_base + GPT_IRQ_EN_REG); -} - -static int __init mtk_timer_init(struct device_node *node) -{ - struct mtk_clock_event_device *evt; - struct resource res; - unsigned long rate = 0; - struct clk *clk; - - evt = kzalloc(sizeof(*evt), GFP_KERNEL); - if (!evt) - return -ENOMEM; - - evt->dev.name = "mtk_tick"; - evt->dev.rating = 300; - evt->dev.features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT; - evt->dev.set_state_shutdown = mtk_clkevt_shutdown; - evt->dev.set_state_periodic = mtk_clkevt_set_periodic; - evt->dev.set_state_oneshot = mtk_clkevt_shutdown; - evt->dev.tick_resume = mtk_clkevt_shutdown; - evt->dev.set_next_event = mtk_clkevt_next_event; - evt->dev.cpumask = cpu_possible_mask; - - evt->gpt_base = of_io_request_and_map(node, 0, "mtk-timer"); - if (IS_ERR(evt->gpt_base)) { - pr_err("Can't get resource\n"); - goto err_kzalloc; - } - - evt->dev.irq = irq_of_parse_and_map(node, 0); - if (evt->dev.irq <= 0) { - pr_err("Can't parse IRQ\n"); - goto err_mem; - } - - clk = of_clk_get(node, 0); - if (IS_ERR(clk)) { - pr_err("Can't get timer clock\n"); - goto err_irq; - } - - if (clk_prepare_enable(clk)) { - pr_err("Can't prepare clock\n"); - goto err_clk_put; - } - rate = clk_get_rate(clk); - - if (request_irq(evt->dev.irq, mtk_timer_interrupt, - IRQF_TIMER | IRQF_IRQPOLL, "mtk_timer", evt)) { - pr_err("failed to setup irq %d\n", evt->dev.irq); - goto err_clk_disable; - } - - evt->ticks_per_jiffy = DIV_ROUND_UP(rate, HZ); - - /* Configure clock source */ - mtk_timer_setup(evt, GPT_CLK_SRC, TIMER_CTRL_OP_FREERUN); - clocksource_mmio_init(evt->gpt_base + TIMER_CNT_REG(GPT_CLK_SRC), - node->name, rate, 300, 32, clocksource_mmio_readl_up); - gpt_sched_reg = evt->gpt_base + TIMER_CNT_REG(GPT_CLK_SRC); - sched_clock_register(mtk_read_sched_clock, 32, rate); - - /* Configure clock event */ - mtk_timer_setup(evt, GPT_CLK_EVT, TIMER_CTRL_OP_REPEAT); - clockevents_config_and_register(&evt->dev, rate, 0x3, - 0xffffffff); - - mtk_timer_enable_irq(evt, GPT_CLK_EVT); - - return 0; - -err_clk_disable: - clk_disable_unprepare(clk); -err_clk_put: - clk_put(clk); -err_irq: - irq_dispose_mapping(evt->dev.irq); -err_mem: - iounmap(evt->gpt_base); - of_address_to_resource(node, 0, &res); - release_mem_region(res.start, resource_size(&res)); -err_kzalloc: - kfree(evt); - - return -EINVAL; -} -TIMER_OF_DECLARE(mtk_mt6577, "mediatek,mt6577-timer", mtk_timer_init); diff --git a/drivers/clocksource/tegra20_timer.c b/drivers/clocksource/tegra20_timer.c index c337a8100a7b..dabf0a103567 100644 --- a/drivers/clocksource/tegra20_timer.c +++ b/drivers/clocksource/tegra20_timer.c @@ -230,7 +230,7 @@ static int __init tegra20_init_timer(struct device_node *np) return ret; } - tegra_clockevent.cpumask = cpu_all_mask; + tegra_clockevent.cpumask = cpu_possible_mask; tegra_clockevent.irq = tegra_timer_irq.irq; clockevents_config_and_register(&tegra_clockevent, 1000000, 0x1, 0x1fffffff); diff --git a/drivers/clocksource/timer-atcpit100.c b/drivers/clocksource/timer-atcpit100.c index 5e23d7b4a722..b4bd2f5b801d 100644 --- a/drivers/clocksource/timer-atcpit100.c +++ b/drivers/clocksource/timer-atcpit100.c @@ -185,7 +185,7 @@ static struct timer_of to = { .set_state_oneshot = atcpit100_clkevt_set_oneshot, .tick_resume = atcpit100_clkevt_shutdown, .set_next_event = atcpit100_clkevt_next_event, - .cpumask = cpu_all_mask, + .cpumask = cpu_possible_mask, }, .of_irq = { diff --git a/drivers/clocksource/timer-keystone.c b/drivers/clocksource/timer-keystone.c index 0eee03250cfc..f5b2eda30bf3 100644 --- a/drivers/clocksource/timer-keystone.c +++ b/drivers/clocksource/timer-keystone.c @@ -211,7 +211,7 @@ static int __init keystone_timer_init(struct device_node *np) event_dev->set_state_shutdown = keystone_shutdown; event_dev->set_state_periodic = keystone_set_periodic; event_dev->set_state_oneshot = keystone_shutdown; - event_dev->cpumask = cpu_all_mask; + event_dev->cpumask = cpu_possible_mask; event_dev->owner = THIS_MODULE; event_dev->name = TIMER_NAME; event_dev->irq = irq; diff --git a/drivers/clocksource/timer-mediatek.c b/drivers/clocksource/timer-mediatek.c new file mode 100644 index 000000000000..eb10321f8517 --- /dev/null +++ b/drivers/clocksource/timer-mediatek.c @@ -0,0 +1,328 @@ +/* + * Mediatek SoCs General-Purpose Timer handling. + * + * Copyright (C) 2014 Matthias Brugger + * + * Matthias Brugger <matthias.bgg@gmail.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/clockchips.h> +#include <linux/clocksource.h> +#include <linux/interrupt.h> +#include <linux/irqreturn.h> +#include <linux/sched_clock.h> +#include <linux/slab.h> +#include "timer-of.h" + +#define TIMER_CLK_EVT (1) +#define TIMER_CLK_SRC (2) + +#define TIMER_SYNC_TICKS (3) + +/* gpt */ +#define GPT_IRQ_EN_REG 0x00 +#define GPT_IRQ_ENABLE(val) BIT((val) - 1) +#define GPT_IRQ_ACK_REG 0x08 +#define GPT_IRQ_ACK(val) BIT((val) - 1) + +#define GPT_CTRL_REG(val) (0x10 * (val)) +#define GPT_CTRL_OP(val) (((val) & 0x3) << 4) +#define GPT_CTRL_OP_ONESHOT (0) +#define GPT_CTRL_OP_REPEAT (1) +#define GPT_CTRL_OP_FREERUN (3) +#define GPT_CTRL_CLEAR (2) +#define GPT_CTRL_ENABLE (1) +#define GPT_CTRL_DISABLE (0) + +#define GPT_CLK_REG(val) (0x04 + (0x10 * (val))) +#define GPT_CLK_SRC(val) (((val) & 0x1) << 4) +#define GPT_CLK_SRC_SYS13M (0) +#define GPT_CLK_SRC_RTC32K (1) +#define GPT_CLK_DIV1 (0x0) +#define GPT_CLK_DIV2 (0x1) + +#define GPT_CNT_REG(val) (0x08 + (0x10 * (val))) +#define GPT_CMP_REG(val) (0x0C + (0x10 * (val))) + +/* system timer */ +#define SYST_BASE (0x40) + +#define SYST_CON (SYST_BASE + 0x0) +#define SYST_VAL (SYST_BASE + 0x4) + +#define SYST_CON_REG(to) (timer_of_base(to) + SYST_CON) +#define SYST_VAL_REG(to) (timer_of_base(to) + SYST_VAL) + +/* + * SYST_CON_EN: Clock enable. Shall be set to + * - Start timer countdown. + * - Allow timeout ticks being updated. + * - Allow changing interrupt functions. + * + * SYST_CON_IRQ_EN: Set to allow interrupt. + * + * SYST_CON_IRQ_CLR: Set to clear interrupt. + */ +#define SYST_CON_EN BIT(0) +#define SYST_CON_IRQ_EN BIT(1) +#define SYST_CON_IRQ_CLR BIT(4) + +static void __iomem *gpt_sched_reg __read_mostly; + +static void mtk_syst_ack_irq(struct timer_of *to) +{ + /* Clear and disable interrupt */ + writel(SYST_CON_IRQ_CLR | SYST_CON_EN, SYST_CON_REG(to)); +} + +static irqreturn_t mtk_syst_handler(int irq, void *dev_id) +{ + struct clock_event_device *clkevt = dev_id; + struct timer_of *to = to_timer_of(clkevt); + + mtk_syst_ack_irq(to); + clkevt->event_handler(clkevt); + + return IRQ_HANDLED; +} + +static int mtk_syst_clkevt_next_event(unsigned long ticks, + struct clock_event_device *clkevt) +{ + struct timer_of *to = to_timer_of(clkevt); + + /* Enable clock to allow timeout tick update later */ + writel(SYST_CON_EN, SYST_CON_REG(to)); + + /* + * Write new timeout ticks. Timer shall start countdown + * after timeout ticks are updated. + */ + writel(ticks, SYST_VAL_REG(to)); + + /* Enable interrupt */ + writel(SYST_CON_EN | SYST_CON_IRQ_EN, SYST_CON_REG(to)); + + return 0; +} + +static int mtk_syst_clkevt_shutdown(struct clock_event_device *clkevt) +{ + /* Disable timer */ + writel(0, SYST_CON_REG(to_timer_of(clkevt))); + + return 0; +} + +static int mtk_syst_clkevt_resume(struct clock_event_device *clkevt) +{ + return mtk_syst_clkevt_shutdown(clkevt); +} + +static int mtk_syst_clkevt_oneshot(struct clock_event_device *clkevt) +{ + return 0; +} + +static u64 notrace mtk_gpt_read_sched_clock(void) +{ + return readl_relaxed(gpt_sched_reg); +} + +static void mtk_gpt_clkevt_time_stop(struct timer_of *to, u8 timer) +{ + u32 val; + + val = readl(timer_of_base(to) + GPT_CTRL_REG(timer)); + writel(val & ~GPT_CTRL_ENABLE, timer_of_base(to) + + GPT_CTRL_REG(timer)); +} + +static void mtk_gpt_clkevt_time_setup(struct timer_of *to, + unsigned long delay, u8 timer) +{ + writel(delay, timer_of_base(to) + GPT_CMP_REG(timer)); +} + +static void mtk_gpt_clkevt_time_start(struct timer_of *to, + bool periodic, u8 timer) +{ + u32 val; + + /* Acknowledge interrupt */ + writel(GPT_IRQ_ACK(timer), timer_of_base(to) + GPT_IRQ_ACK_REG); + + val = readl(timer_of_base(to) + GPT_CTRL_REG(timer)); + + /* Clear 2 bit timer operation mode field */ + val &= ~GPT_CTRL_OP(0x3); + + if (periodic) + val |= GPT_CTRL_OP(GPT_CTRL_OP_REPEAT); + else + val |= GPT_CTRL_OP(GPT_CTRL_OP_ONESHOT); + + writel(val | GPT_CTRL_ENABLE | GPT_CTRL_CLEAR, + timer_of_base(to) + GPT_CTRL_REG(timer)); +} + +static int mtk_gpt_clkevt_shutdown(struct clock_event_device *clk) +{ + mtk_gpt_clkevt_time_stop(to_timer_of(clk), TIMER_CLK_EVT); + + return 0; +} + +static int mtk_gpt_clkevt_set_periodic(struct clock_event_device *clk) +{ + struct timer_of *to = to_timer_of(clk); + + mtk_gpt_clkevt_time_stop(to, TIMER_CLK_EVT); + mtk_gpt_clkevt_time_setup(to, to->of_clk.period, TIMER_CLK_EVT); + mtk_gpt_clkevt_time_start(to, true, TIMER_CLK_EVT); + + return 0; +} + +static int mtk_gpt_clkevt_next_event(unsigned long event, + struct clock_event_device *clk) +{ + struct timer_of *to = to_timer_of(clk); + + mtk_gpt_clkevt_time_stop(to, TIMER_CLK_EVT); + mtk_gpt_clkevt_time_setup(to, event, TIMER_CLK_EVT); + mtk_gpt_clkevt_time_start(to, false, TIMER_CLK_EVT); + + return 0; +} + +static irqreturn_t mtk_gpt_interrupt(int irq, void *dev_id) +{ + struct clock_event_device *clkevt = (struct clock_event_device *)dev_id; + struct timer_of *to = to_timer_of(clkevt); + + /* Acknowledge timer0 irq */ + writel(GPT_IRQ_ACK(TIMER_CLK_EVT), timer_of_base(to) + GPT_IRQ_ACK_REG); + clkevt->event_handler(clkevt); + + return IRQ_HANDLED; +} + +static void +__init mtk_gpt_setup(struct timer_of *to, u8 timer, u8 option) +{ + writel(GPT_CTRL_CLEAR | GPT_CTRL_DISABLE, + timer_of_base(to) + GPT_CTRL_REG(timer)); + + writel(GPT_CLK_SRC(GPT_CLK_SRC_SYS13M) | GPT_CLK_DIV1, + timer_of_base(to) + GPT_CLK_REG(timer)); + + writel(0x0, timer_of_base(to) + GPT_CMP_REG(timer)); + + writel(GPT_CTRL_OP(option) | GPT_CTRL_ENABLE, + timer_of_base(to) + GPT_CTRL_REG(timer)); +} + +static void mtk_gpt_enable_irq(struct timer_of *to, u8 timer) +{ + u32 val; + + /* Disable all interrupts */ + writel(0x0, timer_of_base(to) + GPT_IRQ_EN_REG); + + /* Acknowledge all spurious pending interrupts */ + writel(0x3f, timer_of_base(to) + GPT_IRQ_ACK_REG); + + val = readl(timer_of_base(to) + GPT_IRQ_EN_REG); + writel(val | GPT_IRQ_ENABLE(timer), + timer_of_base(to) + GPT_IRQ_EN_REG); +} + +static struct timer_of to = { + .flags = TIMER_OF_IRQ | TIMER_OF_BASE | TIMER_OF_CLOCK, + + .clkevt = { + .name = "mtk-clkevt", + .rating = 300, + .cpumask = cpu_possible_mask, + }, + + .of_irq = { + .flags = IRQF_TIMER | IRQF_IRQPOLL, + }, +}; + +static int __init mtk_syst_init(struct device_node *node) +{ + int ret; + + to.clkevt.features = CLOCK_EVT_FEAT_DYNIRQ | CLOCK_EVT_FEAT_ONESHOT; + to.clkevt.set_state_shutdown = mtk_syst_clkevt_shutdown; + to.clkevt.set_state_oneshot = mtk_syst_clkevt_oneshot; + to.clkevt.tick_resume = mtk_syst_clkevt_resume; + to.clkevt.set_next_event = mtk_syst_clkevt_next_event; + to.of_irq.handler = mtk_syst_handler; + + ret = timer_of_init(node, &to); + if (ret) + goto err; + + clockevents_config_and_register(&to.clkevt, timer_of_rate(&to), + TIMER_SYNC_TICKS, 0xffffffff); + + return 0; +err: + timer_of_cleanup(&to); + return ret; +} + +static int __init mtk_gpt_init(struct device_node *node) +{ + int ret; + + to.clkevt.features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT; + to.clkevt.set_state_shutdown = mtk_gpt_clkevt_shutdown; + to.clkevt.set_state_periodic = mtk_gpt_clkevt_set_periodic; + to.clkevt.set_state_oneshot = mtk_gpt_clkevt_shutdown; + to.clkevt.tick_resume = mtk_gpt_clkevt_shutdown; + to.clkevt.set_next_event = mtk_gpt_clkevt_next_event; + to.of_irq.handler = mtk_gpt_interrupt; + + ret = timer_of_init(node, &to); + if (ret) + goto err; + + /* Configure clock source */ + mtk_gpt_setup(&to, TIMER_CLK_SRC, GPT_CTRL_OP_FREERUN); + clocksource_mmio_init(timer_of_base(&to) + GPT_CNT_REG(TIMER_CLK_SRC), + node->name, timer_of_rate(&to), 300, 32, + clocksource_mmio_readl_up); + gpt_sched_reg = timer_of_base(&to) + GPT_CNT_REG(TIMER_CLK_SRC); + sched_clock_register(mtk_gpt_read_sched_clock, 32, timer_of_rate(&to)); + + /* Configure clock event */ + mtk_gpt_setup(&to, TIMER_CLK_EVT, GPT_CTRL_OP_REPEAT); + clockevents_config_and_register(&to.clkevt, timer_of_rate(&to), + TIMER_SYNC_TICKS, 0xffffffff); + + mtk_gpt_enable_irq(&to, TIMER_CLK_EVT); + + return 0; +err: + timer_of_cleanup(&to); + return ret; +} +TIMER_OF_DECLARE(mtk_mt6577, "mediatek,mt6577-timer", mtk_gpt_init); +TIMER_OF_DECLARE(mtk_mt6765, "mediatek,mt6765-timer", mtk_syst_init); diff --git a/drivers/clocksource/timer-sprd.c b/drivers/clocksource/timer-sprd.c index ef9ebeafb3ed..430cb99d8d79 100644 --- a/drivers/clocksource/timer-sprd.c +++ b/drivers/clocksource/timer-sprd.c @@ -156,4 +156,54 @@ static int __init sprd_timer_init(struct device_node *np) return 0; } +static struct timer_of suspend_to = { + .flags = TIMER_OF_BASE | TIMER_OF_CLOCK, +}; + +static u64 sprd_suspend_timer_read(struct clocksource *cs) +{ + return ~(u64)readl_relaxed(timer_of_base(&suspend_to) + + TIMER_VALUE_SHDW_LO) & cs->mask; +} + +static int sprd_suspend_timer_enable(struct clocksource *cs) +{ + sprd_timer_update_counter(timer_of_base(&suspend_to), + TIMER_VALUE_LO_MASK); + sprd_timer_enable(timer_of_base(&suspend_to), TIMER_CTL_PERIOD_MODE); + + return 0; +} + +static void sprd_suspend_timer_disable(struct clocksource *cs) +{ + sprd_timer_disable(timer_of_base(&suspend_to)); +} + +static struct clocksource suspend_clocksource = { + .name = "sprd_suspend_timer", + .rating = 200, + .read = sprd_suspend_timer_read, + .enable = sprd_suspend_timer_enable, + .disable = sprd_suspend_timer_disable, + .mask = CLOCKSOURCE_MASK(32), + .flags = CLOCK_SOURCE_IS_CONTINUOUS | CLOCK_SOURCE_SUSPEND_NONSTOP, +}; + +static int __init sprd_suspend_timer_init(struct device_node *np) +{ + int ret; + + ret = timer_of_init(np, &suspend_to); + if (ret) + return ret; + + clocksource_register_hz(&suspend_clocksource, + timer_of_rate(&suspend_to)); + + return 0; +} + TIMER_OF_DECLARE(sc9860_timer, "sprd,sc9860-timer", sprd_timer_init); +TIMER_OF_DECLARE(sc9860_persistent_timer, "sprd,sc9860-suspend-timer", + sprd_suspend_timer_init); diff --git a/drivers/clocksource/timer-ti-32k.c b/drivers/clocksource/timer-ti-32k.c index 880a861ab3c8..29e2e1a78a43 100644 --- a/drivers/clocksource/timer-ti-32k.c +++ b/drivers/clocksource/timer-ti-32k.c @@ -78,8 +78,7 @@ static struct ti_32k ti_32k_timer = { .rating = 250, .read = ti_32k_read_cycles, .mask = CLOCKSOURCE_MASK(32), - .flags = CLOCK_SOURCE_IS_CONTINUOUS | - CLOCK_SOURCE_SUSPEND_NONSTOP, + .flags = CLOCK_SOURCE_IS_CONTINUOUS, }, }; diff --git a/drivers/clocksource/zevio-timer.c b/drivers/clocksource/zevio-timer.c index a6a0338eea77..f74689334f7c 100644 --- a/drivers/clocksource/zevio-timer.c +++ b/drivers/clocksource/zevio-timer.c @@ -162,7 +162,7 @@ static int __init zevio_timer_add(struct device_node *node) timer->clkevt.set_state_oneshot = zevio_timer_set_oneshot; timer->clkevt.tick_resume = zevio_timer_set_oneshot; timer->clkevt.rating = 200; - timer->clkevt.cpumask = cpu_all_mask; + timer->clkevt.cpumask = cpu_possible_mask; timer->clkevt.features = CLOCK_EVT_FEAT_ONESHOT; timer->clkevt.irq = irqnr; diff --git a/drivers/firmware/efi/Kconfig b/drivers/firmware/efi/Kconfig index 781a4a337557..d8e159feb573 100644 --- a/drivers/firmware/efi/Kconfig +++ b/drivers/firmware/efi/Kconfig @@ -87,6 +87,18 @@ config EFI_RUNTIME_WRAPPERS config EFI_ARMSTUB bool +config EFI_ARMSTUB_DTB_LOADER + bool "Enable the DTB loader" + depends on EFI_ARMSTUB + help + Select this config option to add support for the dtb= command + line parameter, allowing a device tree blob to be loaded into + memory from the EFI System Partition by the stub. + + The device tree is typically provided by the platform or by + the bootloader, so this option is mostly for development + purposes only. + config EFI_BOOTLOADER_CONTROL tristate "EFI Bootloader Control" depends on EFI_VARS diff --git a/drivers/firmware/efi/cper.c b/drivers/firmware/efi/cper.c index 3bf0dca378a6..a7902fccdcfa 100644 --- a/drivers/firmware/efi/cper.c +++ b/drivers/firmware/efi/cper.c @@ -48,8 +48,21 @@ u64 cper_next_record_id(void) { static atomic64_t seq; - if (!atomic64_read(&seq)) - atomic64_set(&seq, ((u64)get_seconds()) << 32); + if (!atomic64_read(&seq)) { + time64_t time = ktime_get_real_seconds(); + + /* + * This code is unlikely to still be needed in year 2106, + * but just in case, let's use a few more bits for timestamps + * after y2038 to be sure they keep increasing monotonically + * for the next few hundred years... + */ + if (time < 0x80000000) + atomic64_set(&seq, (ktime_get_real_seconds()) << 32); + else + atomic64_set(&seq, 0x8000000000000000ull | + ktime_get_real_seconds() << 24); + } return atomic64_inc_return(&seq); } @@ -459,7 +472,7 @@ cper_estatus_print_section(const char *pfx, struct acpi_hest_generic_data *gdata else goto err_section_too_small; #if defined(CONFIG_ARM64) || defined(CONFIG_ARM) - } else if (!uuid_le_cmp(*sec_type, CPER_SEC_PROC_ARM)) { + } else if (guid_equal(sec_type, &CPER_SEC_PROC_ARM)) { struct cper_sec_proc_arm *arm_err = acpi_hest_get_payload(gdata); printk("%ssection_type: ARM processor error\n", newpfx); diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c index 232f4915223b..2a29dd9c986d 100644 --- a/drivers/firmware/efi/efi.c +++ b/drivers/firmware/efi/efi.c @@ -82,8 +82,11 @@ struct mm_struct efi_mm = { .mmap_sem = __RWSEM_INITIALIZER(efi_mm.mmap_sem), .page_table_lock = __SPIN_LOCK_UNLOCKED(efi_mm.page_table_lock), .mmlist = LIST_HEAD_INIT(efi_mm.mmlist), + .cpu_bitmap = { [BITS_TO_LONGS(NR_CPUS)] = 0}, }; +struct workqueue_struct *efi_rts_wq; + static bool disable_runtime; static int __init setup_noefi(char *arg) { @@ -337,6 +340,18 @@ static int __init efisubsys_init(void) if (!efi_enabled(EFI_BOOT)) return 0; + /* + * Since we process only one efi_runtime_service() at a time, an + * ordered workqueue (which creates only one execution context) + * should suffice all our needs. + */ + efi_rts_wq = alloc_ordered_workqueue("efi_rts_wq", 0); + if (!efi_rts_wq) { + pr_err("Creating efi_rts_wq failed, EFI runtime services disabled.\n"); + clear_bit(EFI_RUNTIME_SERVICES, &efi.flags); + return 0; + } + /* We register the efi directory at /sys/firmware/efi */ efi_kobj = kobject_create_and_add("efi", firmware_kobj); if (!efi_kobj) { @@ -388,7 +403,7 @@ subsys_initcall(efisubsys_init); * and if so, populate the supplied memory descriptor with the appropriate * data. */ -int __init efi_mem_desc_lookup(u64 phys_addr, efi_memory_desc_t *out_md) +int efi_mem_desc_lookup(u64 phys_addr, efi_memory_desc_t *out_md) { efi_memory_desc_t *md; @@ -406,12 +421,6 @@ int __init efi_mem_desc_lookup(u64 phys_addr, efi_memory_desc_t *out_md) u64 size; u64 end; - if (!(md->attribute & EFI_MEMORY_RUNTIME) && - md->type != EFI_BOOT_SERVICES_DATA && - md->type != EFI_RUNTIME_SERVICES_DATA) { - continue; - } - size = md->num_pages << EFI_PAGE_SHIFT; end = md->phys_addr + size; if (phys_addr >= md->phys_addr && phys_addr < end) { diff --git a/drivers/firmware/efi/esrt.c b/drivers/firmware/efi/esrt.c index 1ab80e06e7c5..5d06bd247d07 100644 --- a/drivers/firmware/efi/esrt.c +++ b/drivers/firmware/efi/esrt.c @@ -250,7 +250,10 @@ void __init efi_esrt_init(void) return; rc = efi_mem_desc_lookup(efi.esrt, &md); - if (rc < 0) { + if (rc < 0 || + (!(md.attribute & EFI_MEMORY_RUNTIME) && + md.type != EFI_BOOT_SERVICES_DATA && + md.type != EFI_RUNTIME_SERVICES_DATA)) { pr_warn("ESRT header is not in the memory map.\n"); return; } @@ -326,7 +329,8 @@ void __init efi_esrt_init(void) end = esrt_data + size; pr_info("Reserving ESRT space from %pa to %pa.\n", &esrt_data, &end); - efi_mem_reserve(esrt_data, esrt_data_size); + if (md.type == EFI_BOOT_SERVICES_DATA) + efi_mem_reserve(esrt_data, esrt_data_size); pr_debug("esrt-init: loaded.\n"); } diff --git a/drivers/firmware/efi/libstub/arm-stub.c b/drivers/firmware/efi/libstub/arm-stub.c index 01a9d78ee415..6920033de6d4 100644 --- a/drivers/firmware/efi/libstub/arm-stub.c +++ b/drivers/firmware/efi/libstub/arm-stub.c @@ -40,31 +40,6 @@ static u64 virtmap_base = EFI_RT_VIRTUAL_BASE; -efi_status_t efi_open_volume(efi_system_table_t *sys_table_arg, - void *__image, void **__fh) -{ - efi_file_io_interface_t *io; - efi_loaded_image_t *image = __image; - efi_file_handle_t *fh; - efi_guid_t fs_proto = EFI_FILE_SYSTEM_GUID; - efi_status_t status; - void *handle = (void *)(unsigned long)image->device_handle; - - status = sys_table_arg->boottime->handle_protocol(handle, - &fs_proto, (void **)&io); - if (status != EFI_SUCCESS) { - efi_printk(sys_table_arg, "Failed to handle fs_proto\n"); - return status; - } - - status = io->open_volume(io, &fh); - if (status != EFI_SUCCESS) - efi_printk(sys_table_arg, "Failed to open volume\n"); - - *__fh = fh; - return status; -} - void efi_char16_printk(efi_system_table_t *sys_table_arg, efi_char16_t *str) { @@ -202,9 +177,10 @@ unsigned long efi_entry(void *handle, efi_system_table_t *sys_table, * 'dtb=' unless UEFI Secure Boot is disabled. We assume that secure * boot is enabled if we can't determine its state. */ - if (secure_boot != efi_secureboot_mode_disabled && - strstr(cmdline_ptr, "dtb=")) { - pr_efi(sys_table, "Ignoring DTB from command line.\n"); + if (!IS_ENABLED(CONFIG_EFI_ARMSTUB_DTB_LOADER) || + secure_boot != efi_secureboot_mode_disabled) { + if (strstr(cmdline_ptr, "dtb=")) + pr_efi(sys_table, "Ignoring DTB from command line.\n"); } else { status = handle_cmdline_files(sys_table, image, cmdline_ptr, "dtb=", diff --git a/drivers/firmware/efi/libstub/efi-stub-helper.c b/drivers/firmware/efi/libstub/efi-stub-helper.c index 50a9cab5a834..e94975f4655b 100644 --- a/drivers/firmware/efi/libstub/efi-stub-helper.c +++ b/drivers/firmware/efi/libstub/efi-stub-helper.c @@ -413,6 +413,34 @@ static efi_status_t efi_file_close(void *handle) return efi_call_proto(efi_file_handle, close, handle); } +static efi_status_t efi_open_volume(efi_system_table_t *sys_table_arg, + efi_loaded_image_t *image, + efi_file_handle_t **__fh) +{ + efi_file_io_interface_t *io; + efi_file_handle_t *fh; + efi_guid_t fs_proto = EFI_FILE_SYSTEM_GUID; + efi_status_t status; + void *handle = (void *)(unsigned long)efi_table_attr(efi_loaded_image, + device_handle, + image); + + status = efi_call_early(handle_protocol, handle, + &fs_proto, (void **)&io); + if (status != EFI_SUCCESS) { + efi_printk(sys_table_arg, "Failed to handle fs_proto\n"); + return status; + } + + status = efi_call_proto(efi_file_io_interface, open_volume, io, &fh); + if (status != EFI_SUCCESS) + efi_printk(sys_table_arg, "Failed to open volume\n"); + else + *__fh = fh; + + return status; +} + /* * Parse the ASCII string 'cmdline' for EFI options, denoted by the efi= * option, e.g. efi=nochunk. @@ -563,8 +591,7 @@ efi_status_t handle_cmdline_files(efi_system_table_t *sys_table_arg, /* Only open the volume once. */ if (!i) { - status = efi_open_volume(sys_table_arg, image, - (void **)&fh); + status = efi_open_volume(sys_table_arg, image, &fh); if (status != EFI_SUCCESS) goto free_files; } diff --git a/drivers/firmware/efi/libstub/efistub.h b/drivers/firmware/efi/libstub/efistub.h index f59564b72ddc..32799cf039ef 100644 --- a/drivers/firmware/efi/libstub/efistub.h +++ b/drivers/firmware/efi/libstub/efistub.h @@ -36,9 +36,6 @@ extern int __pure is_quiet(void); void efi_char16_printk(efi_system_table_t *, efi_char16_t *); -efi_status_t efi_open_volume(efi_system_table_t *sys_table_arg, void *__image, - void **__fh); - unsigned long get_dram_base(efi_system_table_t *sys_table_arg); efi_status_t allocate_new_fdt_and_exit_boot(efi_system_table_t *sys_table, diff --git a/drivers/firmware/efi/runtime-wrappers.c b/drivers/firmware/efi/runtime-wrappers.c index ae54870b2788..aa66cbf23512 100644 --- a/drivers/firmware/efi/runtime-wrappers.c +++ b/drivers/firmware/efi/runtime-wrappers.c @@ -1,6 +1,15 @@ /* * runtime-wrappers.c - Runtime Services function call wrappers * + * Implementation summary: + * ----------------------- + * 1. When user/kernel thread requests to execute efi_runtime_service(), + * enqueue work to efi_rts_wq. + * 2. Caller thread waits for completion until the work is finished + * because it's dependent on the return status and execution of + * efi_runtime_service(). + * For instance, get_variable() and get_next_variable(). + * * Copyright (C) 2014 Linaro Ltd. <ard.biesheuvel@linaro.org> * * Split off from arch/x86/platform/efi/efi.c @@ -22,6 +31,9 @@ #include <linux/mutex.h> #include <linux/semaphore.h> #include <linux/stringify.h> +#include <linux/workqueue.h> +#include <linux/completion.h> + #include <asm/efi.h> /* @@ -33,6 +45,76 @@ #define __efi_call_virt(f, args...) \ __efi_call_virt_pointer(efi.systab->runtime, f, args) +/* efi_runtime_service() function identifiers */ +enum efi_rts_ids { + GET_TIME, + SET_TIME, + GET_WAKEUP_TIME, + SET_WAKEUP_TIME, + GET_VARIABLE, + GET_NEXT_VARIABLE, + SET_VARIABLE, + QUERY_VARIABLE_INFO, + GET_NEXT_HIGH_MONO_COUNT, + UPDATE_CAPSULE, + QUERY_CAPSULE_CAPS, +}; + +/* + * efi_runtime_work: Details of EFI Runtime Service work + * @arg<1-5>: EFI Runtime Service function arguments + * @status: Status of executing EFI Runtime Service + * @efi_rts_id: EFI Runtime Service function identifier + * @efi_rts_comp: Struct used for handling completions + */ +struct efi_runtime_work { + void *arg1; + void *arg2; + void *arg3; + void *arg4; + void *arg5; + efi_status_t status; + struct work_struct work; + enum efi_rts_ids efi_rts_id; + struct completion efi_rts_comp; +}; + +/* + * efi_queue_work: Queue efi_runtime_service() and wait until it's done + * @rts: efi_runtime_service() function identifier + * @rts_arg<1-5>: efi_runtime_service() function arguments + * + * Accesses to efi_runtime_services() are serialized by a binary + * semaphore (efi_runtime_lock) and caller waits until the work is + * finished, hence _only_ one work is queued at a time and the caller + * thread waits for completion. + */ +#define efi_queue_work(_rts, _arg1, _arg2, _arg3, _arg4, _arg5) \ +({ \ + struct efi_runtime_work efi_rts_work; \ + efi_rts_work.status = EFI_ABORTED; \ + \ + init_completion(&efi_rts_work.efi_rts_comp); \ + INIT_WORK_ONSTACK(&efi_rts_work.work, efi_call_rts); \ + efi_rts_work.arg1 = _arg1; \ + efi_rts_work.arg2 = _arg2; \ + efi_rts_work.arg3 = _arg3; \ + efi_rts_work.arg4 = _arg4; \ + efi_rts_work.arg5 = _arg5; \ + efi_rts_work.efi_rts_id = _rts; \ + \ + /* \ + * queue_work() returns 0 if work was already on queue, \ + * _ideally_ this should never happen. \ + */ \ + if (queue_work(efi_rts_wq, &efi_rts_work.work)) \ + wait_for_completion(&efi_rts_work.efi_rts_comp); \ + else \ + pr_err("Failed to queue work to efi_rts_wq.\n"); \ + \ + efi_rts_work.status; \ +}) + void efi_call_virt_check_flags(unsigned long flags, const char *call) { unsigned long cur_flags, mismatch; @@ -90,13 +172,98 @@ void efi_call_virt_check_flags(unsigned long flags, const char *call) */ static DEFINE_SEMAPHORE(efi_runtime_lock); +/* + * Calls the appropriate efi_runtime_service() with the appropriate + * arguments. + * + * Semantics followed by efi_call_rts() to understand efi_runtime_work: + * 1. If argument was a pointer, recast it from void pointer to original + * pointer type. + * 2. If argument was a value, recast it from void pointer to original + * pointer type and dereference it. + */ +static void efi_call_rts(struct work_struct *work) +{ + struct efi_runtime_work *efi_rts_work; + void *arg1, *arg2, *arg3, *arg4, *arg5; + efi_status_t status = EFI_NOT_FOUND; + + efi_rts_work = container_of(work, struct efi_runtime_work, work); + arg1 = efi_rts_work->arg1; + arg2 = efi_rts_work->arg2; + arg3 = efi_rts_work->arg3; + arg4 = efi_rts_work->arg4; + arg5 = efi_rts_work->arg5; + + switch (efi_rts_work->efi_rts_id) { + case GET_TIME: + status = efi_call_virt(get_time, (efi_time_t *)arg1, + (efi_time_cap_t *)arg2); + break; + case SET_TIME: + status = efi_call_virt(set_time, (efi_time_t *)arg1); + break; + case GET_WAKEUP_TIME: + status = efi_call_virt(get_wakeup_time, (efi_bool_t *)arg1, + (efi_bool_t *)arg2, (efi_time_t *)arg3); + break; + case SET_WAKEUP_TIME: + status = efi_call_virt(set_wakeup_time, *(efi_bool_t *)arg1, + (efi_time_t *)arg2); + break; + case GET_VARIABLE: + status = efi_call_virt(get_variable, (efi_char16_t *)arg1, + (efi_guid_t *)arg2, (u32 *)arg3, + (unsigned long *)arg4, (void *)arg5); + break; + case GET_NEXT_VARIABLE: + status = efi_call_virt(get_next_variable, (unsigned long *)arg1, + (efi_char16_t *)arg2, + (efi_guid_t *)arg3); + break; + case SET_VARIABLE: + status = efi_call_virt(set_variable, (efi_char16_t *)arg1, + (efi_guid_t *)arg2, *(u32 *)arg3, + *(unsigned long *)arg4, (void *)arg5); + break; + case QUERY_VARIABLE_INFO: + status = efi_call_virt(query_variable_info, *(u32 *)arg1, + (u64 *)arg2, (u64 *)arg3, (u64 *)arg4); + break; + case GET_NEXT_HIGH_MONO_COUNT: + status = efi_call_virt(get_next_high_mono_count, (u32 *)arg1); + break; + case UPDATE_CAPSULE: + status = efi_call_virt(update_capsule, + (efi_capsule_header_t **)arg1, + *(unsigned long *)arg2, + *(unsigned long *)arg3); + break; + case QUERY_CAPSULE_CAPS: + status = efi_call_virt(query_capsule_caps, + (efi_capsule_header_t **)arg1, + *(unsigned long *)arg2, (u64 *)arg3, + (int *)arg4); + break; + default: + /* + * Ideally, we should never reach here because a caller of this + * function should have put the right efi_runtime_service() + * function identifier into efi_rts_work->efi_rts_id + */ + pr_err("Requested executing invalid EFI Runtime Service.\n"); + } + efi_rts_work->status = status; + complete(&efi_rts_work->efi_rts_comp); +} + static efi_status_t virt_efi_get_time(efi_time_t *tm, efi_time_cap_t *tc) { efi_status_t status; if (down_interruptible(&efi_runtime_lock)) return EFI_ABORTED; - status = efi_call_virt(get_time, tm, tc); + status = efi_queue_work(GET_TIME, tm, tc, NULL, NULL, NULL); up(&efi_runtime_lock); return status; } @@ -107,7 +274,7 @@ static efi_status_t virt_efi_set_time(efi_time_t *tm) if (down_interruptible(&efi_runtime_lock)) return EFI_ABORTED; - status = efi_call_virt(set_time, tm); + status = efi_queue_work(SET_TIME, tm, NULL, NULL, NULL, NULL); up(&efi_runtime_lock); return status; } @@ -120,7 +287,8 @@ static efi_status_t virt_efi_get_wakeup_time(efi_bool_t *enabled, if (down_interruptible(&efi_runtime_lock)) return EFI_ABORTED; - status = efi_call_virt(get_wakeup_time, enabled, pending, tm); + status = efi_queue_work(GET_WAKEUP_TIME, enabled, pending, tm, NULL, + NULL); up(&efi_runtime_lock); return status; } @@ -131,7 +299,8 @@ static efi_status_t virt_efi_set_wakeup_time(efi_bool_t enabled, efi_time_t *tm) if (down_interruptible(&efi_runtime_lock)) return EFI_ABORTED; - status = efi_call_virt(set_wakeup_time, enabled, tm); + status = efi_queue_work(SET_WAKEUP_TIME, &enabled, tm, NULL, NULL, + NULL); up(&efi_runtime_lock); return status; } @@ -146,8 +315,8 @@ static efi_status_t virt_efi_get_variable(efi_char16_t *name, if (down_interruptible(&efi_runtime_lock)) return EFI_ABORTED; - status = efi_call_virt(get_variable, name, vendor, attr, data_size, - data); + status = efi_queue_work(GET_VARIABLE, name, vendor, attr, data_size, + data); up(&efi_runtime_lock); return status; } @@ -160,7 +329,8 @@ static efi_status_t virt_efi_get_next_variable(unsigned long *name_size, if (down_interruptible(&efi_runtime_lock)) return EFI_ABORTED; - status = efi_call_virt(get_next_variable, name_size, name, vendor); + status = efi_queue_work(GET_NEXT_VARIABLE, name_size, name, vendor, + NULL, NULL); up(&efi_runtime_lock); return status; } @@ -175,8 +345,8 @@ static efi_status_t virt_efi_set_variable(efi_char16_t *name, if (down_interruptible(&efi_runtime_lock)) return EFI_ABORTED; - status = efi_call_virt(set_variable, name, vendor, attr, data_size, - data); + status = efi_queue_work(SET_VARIABLE, name, vendor, &attr, &data_size, + data); up(&efi_runtime_lock); return status; } @@ -210,8 +380,8 @@ static efi_status_t virt_efi_query_variable_info(u32 attr, if (down_interruptible(&efi_runtime_lock)) return EFI_ABORTED; - status = efi_call_virt(query_variable_info, attr, storage_space, - remaining_space, max_variable_size); + status = efi_queue_work(QUERY_VARIABLE_INFO, &attr, storage_space, + remaining_space, max_variable_size, NULL); up(&efi_runtime_lock); return status; } @@ -242,7 +412,8 @@ static efi_status_t virt_efi_get_next_high_mono_count(u32 *count) if (down_interruptible(&efi_runtime_lock)) return EFI_ABORTED; - status = efi_call_virt(get_next_high_mono_count, count); + status = efi_queue_work(GET_NEXT_HIGH_MONO_COUNT, count, NULL, NULL, + NULL, NULL); up(&efi_runtime_lock); return status; } @@ -272,7 +443,8 @@ static efi_status_t virt_efi_update_capsule(efi_capsule_header_t **capsules, if (down_interruptible(&efi_runtime_lock)) return EFI_ABORTED; - status = efi_call_virt(update_capsule, capsules, count, sg_list); + status = efi_queue_work(UPDATE_CAPSULE, capsules, &count, &sg_list, + NULL, NULL); up(&efi_runtime_lock); return status; } @@ -289,8 +461,8 @@ static efi_status_t virt_efi_query_capsule_caps(efi_capsule_header_t **capsules, if (down_interruptible(&efi_runtime_lock)) return EFI_ABORTED; - status = efi_call_virt(query_capsule_caps, capsules, count, max_size, - reset_type); + status = efi_queue_work(QUERY_CAPSULE_CAPS, capsules, &count, + max_size, reset_type, NULL); up(&efi_runtime_lock); return status; } diff --git a/drivers/gpio/gpiolib-acpi.c b/drivers/gpio/gpiolib-acpi.c index e2232cbcec8b..addd9fecc198 100644 --- a/drivers/gpio/gpiolib-acpi.c +++ b/drivers/gpio/gpiolib-acpi.c @@ -25,6 +25,7 @@ struct acpi_gpio_event { struct list_head node; + struct list_head initial_sync_list; acpi_handle handle; unsigned int pin; unsigned int irq; @@ -50,6 +51,9 @@ struct acpi_gpio_chip { struct list_head events; }; +static LIST_HEAD(acpi_gpio_initial_sync_list); +static DEFINE_MUTEX(acpi_gpio_initial_sync_list_lock); + static int acpi_gpiochip_find(struct gpio_chip *gc, void *data) { if (!gc->parent) @@ -85,6 +89,21 @@ static struct gpio_desc *acpi_get_gpiod(char *path, int pin) return gpiochip_get_desc(chip, pin); } +static void acpi_gpio_add_to_initial_sync_list(struct acpi_gpio_event *event) +{ + mutex_lock(&acpi_gpio_initial_sync_list_lock); + list_add(&event->initial_sync_list, &acpi_gpio_initial_sync_list); + mutex_unlock(&acpi_gpio_initial_sync_list_lock); +} + +static void acpi_gpio_del_from_initial_sync_list(struct acpi_gpio_event *event) +{ + mutex_lock(&acpi_gpio_initial_sync_list_lock); + if (!list_empty(&event->initial_sync_list)) + list_del_init(&event->initial_sync_list); + mutex_unlock(&acpi_gpio_initial_sync_list_lock); +} + static irqreturn_t acpi_gpio_irq_handler(int irq, void *data) { struct acpi_gpio_event *event = data; @@ -136,7 +155,7 @@ static acpi_status acpi_gpiochip_request_interrupt(struct acpi_resource *ares, irq_handler_t handler = NULL; struct gpio_desc *desc; unsigned long irqflags; - int ret, pin, irq; + int ret, pin, irq, value; if (!acpi_gpio_get_irq_resource(ares, &agpio)) return AE_OK; @@ -167,6 +186,8 @@ static acpi_status acpi_gpiochip_request_interrupt(struct acpi_resource *ares, gpiod_direction_input(desc); + value = gpiod_get_value(desc); + ret = gpiochip_lock_as_irq(chip, pin); if (ret) { dev_err(chip->parent, "Failed to lock GPIO as interrupt\n"); @@ -208,6 +229,7 @@ static acpi_status acpi_gpiochip_request_interrupt(struct acpi_resource *ares, event->irq = irq; event->pin = pin; event->desc = desc; + INIT_LIST_HEAD(&event->initial_sync_list); ret = request_threaded_irq(event->irq, NULL, handler, irqflags, "ACPI:Event", event); @@ -222,6 +244,18 @@ static acpi_status acpi_gpiochip_request_interrupt(struct acpi_resource *ares, enable_irq_wake(irq); list_add_tail(&event->node, &acpi_gpio->events); + + /* + * Make sure we trigger the initial state of the IRQ when using RISING + * or FALLING. Note we run the handlers on late_init, the AML code + * may refer to OperationRegions from other (builtin) drivers which + * may be probed after us. + */ + if (handler == acpi_gpio_irq_handler && + (((irqflags & IRQF_TRIGGER_RISING) && value == 1) || + ((irqflags & IRQF_TRIGGER_FALLING) && value == 0))) + acpi_gpio_add_to_initial_sync_list(event); + return AE_OK; fail_free_event: @@ -294,6 +328,8 @@ void acpi_gpiochip_free_interrupts(struct gpio_chip *chip) list_for_each_entry_safe_reverse(event, ep, &acpi_gpio->events, node) { struct gpio_desc *desc; + acpi_gpio_del_from_initial_sync_list(event); + if (irqd_is_wakeup_set(irq_get_irq_data(event->irq))) disable_irq_wake(event->irq); @@ -1158,3 +1194,21 @@ bool acpi_can_fallback_to_crs(struct acpi_device *adev, const char *con_id) return con_id == NULL; } + +/* Sync the initial state of handlers after all builtin drivers have probed */ +static int acpi_gpio_initial_sync(void) +{ + struct acpi_gpio_event *event, *ep; + + mutex_lock(&acpi_gpio_initial_sync_list_lock); + list_for_each_entry_safe(event, ep, &acpi_gpio_initial_sync_list, + initial_sync_list) { + acpi_evaluate_object(event->handle, NULL, NULL, NULL); + list_del_init(&event->initial_sync_list); + } + mutex_unlock(&acpi_gpio_initial_sync_list_lock); + + return 0; +} +/* We must use _sync so that this runs after the first deferred_probe run */ +late_initcall_sync(acpi_gpio_initial_sync); diff --git a/drivers/i2c/busses/i2c-xlp9xx.c b/drivers/i2c/busses/i2c-xlp9xx.c index 1f41a4f89c08..8a873975cf12 100644 --- a/drivers/i2c/busses/i2c-xlp9xx.c +++ b/drivers/i2c/busses/i2c-xlp9xx.c @@ -191,28 +191,43 @@ static void xlp9xx_i2c_drain_rx_fifo(struct xlp9xx_i2c_dev *priv) if (priv->len_recv) { /* read length byte */ rlen = xlp9xx_read_i2c_reg(priv, XLP9XX_I2C_MRXFIFO); + + /* + * We expect at least 2 interrupts for I2C_M_RECV_LEN + * transactions. The length is updated during the first + * interrupt, and the buffer contents are only copied + * during subsequent interrupts. If in case the interrupts + * get merged we would complete the transaction without + * copying out the bytes from RX fifo. To avoid this now we + * drain the fifo as and when data is available. + * We drained the rlen byte already, decrement total length + * by one. + */ + + len--; if (rlen > I2C_SMBUS_BLOCK_MAX || rlen == 0) { rlen = 0; /*abort transfer */ priv->msg_buf_remaining = 0; priv->msg_len = 0; - } else { - *buf++ = rlen; - if (priv->client_pec) - ++rlen; /* account for error check byte */ - /* update remaining bytes and message length */ - priv->msg_buf_remaining = rlen; - priv->msg_len = rlen + 1; + xlp9xx_i2c_update_rlen(priv); + return; } + + *buf++ = rlen; + if (priv->client_pec) + ++rlen; /* account for error check byte */ + /* update remaining bytes and message length */ + priv->msg_buf_remaining = rlen; + priv->msg_len = rlen + 1; xlp9xx_i2c_update_rlen(priv); priv->len_recv = false; - } else { - len = min(priv->msg_buf_remaining, len); - for (i = 0; i < len; i++, buf++) - *buf = xlp9xx_read_i2c_reg(priv, XLP9XX_I2C_MRXFIFO); - - priv->msg_buf_remaining -= len; } + len = min(priv->msg_buf_remaining, len); + for (i = 0; i < len; i++, buf++) + *buf = xlp9xx_read_i2c_reg(priv, XLP9XX_I2C_MRXFIFO); + + priv->msg_buf_remaining -= len; priv->msg_buf = buf; if (priv->msg_buf_remaining) diff --git a/drivers/infiniband/core/rdma_core.c b/drivers/infiniband/core/rdma_core.c index a6e904973ba8..475910ffbcb6 100644 --- a/drivers/infiniband/core/rdma_core.c +++ b/drivers/infiniband/core/rdma_core.c @@ -121,7 +121,7 @@ static int uverbs_try_lock_object(struct ib_uobject *uobj, bool exclusive) * this lock. */ if (!exclusive) - return __atomic_add_unless(&uobj->usecnt, 1, -1) == -1 ? + return atomic_fetch_add_unless(&uobj->usecnt, 1, -1) == -1 ? -EBUSY : 0; /* lock is either WRITE or DESTROY - should be exclusive */ diff --git a/drivers/input/keyboard/hilkbd.c b/drivers/input/keyboard/hilkbd.c index a4e404aaf64b..5c7afdec192c 100644 --- a/drivers/input/keyboard/hilkbd.c +++ b/drivers/input/keyboard/hilkbd.c @@ -57,8 +57,8 @@ MODULE_LICENSE("GPL v2"); #define HIL_DATA 0x1 #define HIL_CMD 0x3 #define HIL_IRQ 2 - #define hil_readb(p) readb(p) - #define hil_writeb(v,p) writeb((v),(p)) + #define hil_readb(p) readb((const volatile void __iomem *)(p)) + #define hil_writeb(v, p) writeb((v), (volatile void __iomem *)(p)) #else #error "HIL is not supported on this platform" diff --git a/drivers/irqchip/Kconfig b/drivers/irqchip/Kconfig index e9233db16e03..d564d21245c5 100644 --- a/drivers/irqchip/Kconfig +++ b/drivers/irqchip/Kconfig @@ -8,7 +8,7 @@ config ARM_GIC bool select IRQ_DOMAIN select IRQ_DOMAIN_HIERARCHY - select MULTI_IRQ_HANDLER + select GENERIC_IRQ_MULTI_HANDLER select GENERIC_IRQ_EFFECTIVE_AFF_MASK config ARM_GIC_PM @@ -34,7 +34,7 @@ config GIC_NON_BANKED config ARM_GIC_V3 bool select IRQ_DOMAIN - select MULTI_IRQ_HANDLER + select GENERIC_IRQ_MULTI_HANDLER select IRQ_DOMAIN_HIERARCHY select PARTITION_PERCPU select GENERIC_IRQ_EFFECTIVE_AFF_MASK @@ -66,7 +66,7 @@ config ARM_NVIC config ARM_VIC bool select IRQ_DOMAIN - select MULTI_IRQ_HANDLER + select GENERIC_IRQ_MULTI_HANDLER config ARM_VIC_NR int @@ -93,14 +93,14 @@ config ATMEL_AIC_IRQ bool select GENERIC_IRQ_CHIP select IRQ_DOMAIN - select MULTI_IRQ_HANDLER + select GENERIC_IRQ_MULTI_HANDLER select SPARSE_IRQ config ATMEL_AIC5_IRQ bool select GENERIC_IRQ_CHIP select IRQ_DOMAIN - select MULTI_IRQ_HANDLER + select GENERIC_IRQ_MULTI_HANDLER select SPARSE_IRQ config I8259 @@ -137,7 +137,7 @@ config DW_APB_ICTL config FARADAY_FTINTC010 bool select IRQ_DOMAIN - select MULTI_IRQ_HANDLER + select GENERIC_IRQ_MULTI_HANDLER select SPARSE_IRQ config HISILICON_IRQ_MBIGEN @@ -162,7 +162,7 @@ config CLPS711X_IRQCHIP bool depends on ARCH_CLPS711X select IRQ_DOMAIN - select MULTI_IRQ_HANDLER + select GENERIC_IRQ_MULTI_HANDLER select SPARSE_IRQ default y @@ -181,7 +181,7 @@ config OMAP_IRQCHIP config ORION_IRQCHIP bool select IRQ_DOMAIN - select MULTI_IRQ_HANDLER + select GENERIC_IRQ_MULTI_HANDLER config PIC32_EVIC bool diff --git a/drivers/irqchip/irq-gic-v3-its-fsl-mc-msi.c b/drivers/irqchip/irq-gic-v3-its-fsl-mc-msi.c index 4eca5c763766..606efa64adff 100644 --- a/drivers/irqchip/irq-gic-v3-its-fsl-mc-msi.c +++ b/drivers/irqchip/irq-gic-v3-its-fsl-mc-msi.c @@ -45,6 +45,9 @@ static int its_fsl_mc_msi_prepare(struct irq_domain *msi_domain, */ info->scratchpad[0].ul = mc_bus_dev->icid; msi_info = msi_get_domain_info(msi_domain->parent); + + /* Allocate at least 32 MSIs, and always as a power of 2 */ + nvec = max_t(int, 32, roundup_pow_of_two(nvec)); return msi_info->ops->msi_prepare(msi_domain->parent, dev, nvec, info); } diff --git a/drivers/irqchip/irq-gic-v3-its-pci-msi.c b/drivers/irqchip/irq-gic-v3-its-pci-msi.c index 25a98de5cfb2..8d6d009d1d58 100644 --- a/drivers/irqchip/irq-gic-v3-its-pci-msi.c +++ b/drivers/irqchip/irq-gic-v3-its-pci-msi.c @@ -66,7 +66,7 @@ static int its_pci_msi_prepare(struct irq_domain *domain, struct device *dev, { struct pci_dev *pdev, *alias_dev; struct msi_domain_info *msi_info; - int alias_count = 0; + int alias_count = 0, minnvec = 1; if (!dev_is_pci(dev)) return -EINVAL; @@ -86,8 +86,18 @@ static int its_pci_msi_prepare(struct irq_domain *domain, struct device *dev, /* ITS specific DeviceID, as the core ITS ignores dev. */ info->scratchpad[0].ul = pci_msi_domain_get_msi_rid(domain, pdev); - return msi_info->ops->msi_prepare(domain->parent, - dev, max(nvec, alias_count), info); + /* + * Always allocate a power of 2, and special case device 0 for + * broken systems where the DevID is not wired (and all devices + * appear as DevID 0). For that reason, we generously allocate a + * minimum of 32 MSIs for DevID 0. If you want more because all + * your devices are aliasing to DevID 0, consider fixing your HW. + */ + nvec = max(nvec, alias_count); + if (!info->scratchpad[0].ul) + minnvec = 32; + nvec = max_t(int, minnvec, roundup_pow_of_two(nvec)); + return msi_info->ops->msi_prepare(domain->parent, dev, nvec, info); } static struct msi_domain_ops its_pci_msi_ops = { diff --git a/drivers/irqchip/irq-gic-v3-its-platform-msi.c b/drivers/irqchip/irq-gic-v3-its-platform-msi.c index 8881a053c173..7b8e87b493fe 100644 --- a/drivers/irqchip/irq-gic-v3-its-platform-msi.c +++ b/drivers/irqchip/irq-gic-v3-its-platform-msi.c @@ -73,6 +73,8 @@ static int its_pmsi_prepare(struct irq_domain *domain, struct device *dev, /* ITS specific DeviceID, as the core ITS ignores dev. */ info->scratchpad[0].ul = dev_id; + /* Allocate at least 32 MSIs, and always as a power of 2 */ + nvec = max_t(int, 32, roundup_pow_of_two(nvec)); return msi_info->ops->msi_prepare(domain->parent, dev, nvec, info); } diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index d7842d312d3e..316a57530f6d 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -23,6 +23,8 @@ #include <linux/dma-iommu.h> #include <linux/interrupt.h> #include <linux/irqdomain.h> +#include <linux/list.h> +#include <linux/list_sort.h> #include <linux/log2.h> #include <linux/mm.h> #include <linux/msi.h> @@ -160,7 +162,7 @@ static struct { } vpe_proxy; static LIST_HEAD(its_nodes); -static DEFINE_SPINLOCK(its_lock); +static DEFINE_RAW_SPINLOCK(its_lock); static struct rdists *gic_rdists; static struct irq_domain *its_parent; @@ -1421,112 +1423,176 @@ static struct irq_chip its_irq_chip = { .irq_set_vcpu_affinity = its_irq_set_vcpu_affinity, }; + /* * How we allocate LPIs: * - * The GIC has id_bits bits for interrupt identifiers. From there, we - * must subtract 8192 which are reserved for SGIs/PPIs/SPIs. Then, as - * we allocate LPIs by chunks of 32, we can shift the whole thing by 5 - * bits to the right. + * lpi_range_list contains ranges of LPIs that are to available to + * allocate from. To allocate LPIs, just pick the first range that + * fits the required allocation, and reduce it by the required + * amount. Once empty, remove the range from the list. + * + * To free a range of LPIs, add a free range to the list, sort it and + * merge the result if the new range happens to be adjacent to an + * already free block. * - * This gives us (((1UL << id_bits) - 8192) >> 5) possible allocations. + * The consequence of the above is that allocation is cost is low, but + * freeing is expensive. We assumes that freeing rarely occurs. */ -#define IRQS_PER_CHUNK_SHIFT 5 -#define IRQS_PER_CHUNK (1UL << IRQS_PER_CHUNK_SHIFT) -#define ITS_MAX_LPI_NRBITS 16 /* 64K LPIs */ -static unsigned long *lpi_bitmap; -static u32 lpi_chunks; -static DEFINE_SPINLOCK(lpi_lock); +static DEFINE_MUTEX(lpi_range_lock); +static LIST_HEAD(lpi_range_list); + +struct lpi_range { + struct list_head entry; + u32 base_id; + u32 span; +}; -static int its_lpi_to_chunk(int lpi) +static struct lpi_range *mk_lpi_range(u32 base, u32 span) { - return (lpi - 8192) >> IRQS_PER_CHUNK_SHIFT; + struct lpi_range *range; + + range = kzalloc(sizeof(*range), GFP_KERNEL); + if (range) { + INIT_LIST_HEAD(&range->entry); + range->base_id = base; + range->span = span; + } + + return range; } -static int its_chunk_to_lpi(int chunk) +static int lpi_range_cmp(void *priv, struct list_head *a, struct list_head *b) { - return (chunk << IRQS_PER_CHUNK_SHIFT) + 8192; + struct lpi_range *ra, *rb; + + ra = container_of(a, struct lpi_range, entry); + rb = container_of(b, struct lpi_range, entry); + + return rb->base_id - ra->base_id; } -static int __init its_lpi_init(u32 id_bits) +static void merge_lpi_ranges(void) { - lpi_chunks = its_lpi_to_chunk(1UL << id_bits); + struct lpi_range *range, *tmp; - lpi_bitmap = kcalloc(BITS_TO_LONGS(lpi_chunks), sizeof(long), - GFP_KERNEL); - if (!lpi_bitmap) { - lpi_chunks = 0; - return -ENOMEM; + list_for_each_entry_safe(range, tmp, &lpi_range_list, entry) { + if (!list_is_last(&range->entry, &lpi_range_list) && + (tmp->base_id == (range->base_id + range->span))) { + tmp->base_id = range->base_id; + tmp->span += range->span; + list_del(&range->entry); + kfree(range); + } } +} - pr_info("ITS: Allocated %d chunks for LPIs\n", (int)lpi_chunks); - return 0; +static int alloc_lpi_range(u32 nr_lpis, u32 *base) +{ + struct lpi_range *range, *tmp; + int err = -ENOSPC; + + mutex_lock(&lpi_range_lock); + + list_for_each_entry_safe(range, tmp, &lpi_range_list, entry) { + if (range->span >= nr_lpis) { + *base = range->base_id; + range->base_id += nr_lpis; + range->span -= nr_lpis; + + if (range->span == 0) { + list_del(&range->entry); + kfree(range); + } + + err = 0; + break; + } + } + + mutex_unlock(&lpi_range_lock); + + pr_debug("ITS: alloc %u:%u\n", *base, nr_lpis); + return err; } -static unsigned long *its_lpi_alloc_chunks(int nr_irqs, int *base, int *nr_ids) +static int free_lpi_range(u32 base, u32 nr_lpis) { - unsigned long *bitmap = NULL; - int chunk_id; - int nr_chunks; - int i; + struct lpi_range *new; + int err = 0; + + mutex_lock(&lpi_range_lock); + + new = mk_lpi_range(base, nr_lpis); + if (!new) { + err = -ENOMEM; + goto out; + } + + list_add(&new->entry, &lpi_range_list); + list_sort(NULL, &lpi_range_list, lpi_range_cmp); + merge_lpi_ranges(); +out: + mutex_unlock(&lpi_range_lock); + return err; +} + +static int __init its_lpi_init(u32 id_bits) +{ + u32 lpis = (1UL << id_bits) - 8192; + u32 numlpis; + int err; + + numlpis = 1UL << GICD_TYPER_NUM_LPIS(gic_rdists->gicd_typer); + + if (numlpis > 2 && !WARN_ON(numlpis > lpis)) { + lpis = numlpis; + pr_info("ITS: Using hypervisor restricted LPI range [%u]\n", + lpis); + } - nr_chunks = DIV_ROUND_UP(nr_irqs, IRQS_PER_CHUNK); + /* + * Initializing the allocator is just the same as freeing the + * full range of LPIs. + */ + err = free_lpi_range(8192, lpis); + pr_debug("ITS: Allocator initialized for %u LPIs\n", lpis); + return err; +} - spin_lock(&lpi_lock); +static unsigned long *its_lpi_alloc(int nr_irqs, u32 *base, int *nr_ids) +{ + unsigned long *bitmap = NULL; + int err = 0; do { - chunk_id = bitmap_find_next_zero_area(lpi_bitmap, lpi_chunks, - 0, nr_chunks, 0); - if (chunk_id < lpi_chunks) + err = alloc_lpi_range(nr_irqs, base); + if (!err) break; - nr_chunks--; - } while (nr_chunks > 0); + nr_irqs /= 2; + } while (nr_irqs > 0); - if (!nr_chunks) + if (err) goto out; - bitmap = kcalloc(BITS_TO_LONGS(nr_chunks * IRQS_PER_CHUNK), - sizeof(long), - GFP_ATOMIC); + bitmap = kcalloc(BITS_TO_LONGS(nr_irqs), sizeof (long), GFP_ATOMIC); if (!bitmap) goto out; - for (i = 0; i < nr_chunks; i++) - set_bit(chunk_id + i, lpi_bitmap); - - *base = its_chunk_to_lpi(chunk_id); - *nr_ids = nr_chunks * IRQS_PER_CHUNK; + *nr_ids = nr_irqs; out: - spin_unlock(&lpi_lock); - if (!bitmap) *base = *nr_ids = 0; return bitmap; } -static void its_lpi_free_chunks(unsigned long *bitmap, int base, int nr_ids) +static void its_lpi_free(unsigned long *bitmap, u32 base, u32 nr_ids) { - int lpi; - - spin_lock(&lpi_lock); - - for (lpi = base; lpi < (base + nr_ids); lpi += IRQS_PER_CHUNK) { - int chunk = its_lpi_to_chunk(lpi); - - BUG_ON(chunk > lpi_chunks); - if (test_bit(chunk, lpi_bitmap)) { - clear_bit(chunk, lpi_bitmap); - } else { - pr_err("Bad LPI chunk %d\n", chunk); - } - } - - spin_unlock(&lpi_lock); - + WARN_ON(free_lpi_range(base, nr_ids)); kfree(bitmap); } @@ -1559,7 +1625,7 @@ static int __init its_alloc_lpi_tables(void) { phys_addr_t paddr; - lpi_id_bits = min_t(u32, gic_rdists->id_bits, ITS_MAX_LPI_NRBITS); + lpi_id_bits = GICD_TYPER_ID_BITS(gic_rdists->gicd_typer); gic_rdists->prop_page = its_allocate_prop_table(GFP_NOWAIT); if (!gic_rdists->prop_page) { pr_err("Failed to allocate PROPBASE\n"); @@ -1997,12 +2063,12 @@ static void its_cpu_init_collections(void) { struct its_node *its; - spin_lock(&its_lock); + raw_spin_lock(&its_lock); list_for_each_entry(its, &its_nodes, entry) its_cpu_init_collection(its); - spin_unlock(&its_lock); + raw_spin_unlock(&its_lock); } static struct its_device *its_find_device(struct its_node *its, u32 dev_id) @@ -2134,17 +2200,20 @@ static struct its_device *its_create_device(struct its_node *its, u32 dev_id, if (!its_alloc_device_table(its, dev_id)) return NULL; + if (WARN_ON(!is_power_of_2(nvecs))) + nvecs = roundup_pow_of_two(nvecs); + dev = kzalloc(sizeof(*dev), GFP_KERNEL); /* - * We allocate at least one chunk worth of LPIs bet device, - * and thus that many ITEs. The device may require less though. + * Even if the device wants a single LPI, the ITT must be + * sized as a power of two (and you need at least one bit...). */ - nr_ites = max(IRQS_PER_CHUNK, roundup_pow_of_two(nvecs)); + nr_ites = max(2, nvecs); sz = nr_ites * its->ite_size; sz = max(sz, ITS_ITT_ALIGN) + ITS_ITT_ALIGN - 1; itt = kzalloc(sz, GFP_KERNEL); if (alloc_lpis) { - lpi_map = its_lpi_alloc_chunks(nvecs, &lpi_base, &nr_lpis); + lpi_map = its_lpi_alloc(nvecs, &lpi_base, &nr_lpis); if (lpi_map) col_map = kcalloc(nr_lpis, sizeof(*col_map), GFP_KERNEL); @@ -2379,9 +2448,9 @@ static void its_irq_domain_free(struct irq_domain *domain, unsigned int virq, /* If all interrupts have been freed, start mopping the floor */ if (bitmap_empty(its_dev->event_map.lpi_map, its_dev->event_map.nr_lpis)) { - its_lpi_free_chunks(its_dev->event_map.lpi_map, - its_dev->event_map.lpi_base, - its_dev->event_map.nr_lpis); + its_lpi_free(its_dev->event_map.lpi_map, + its_dev->event_map.lpi_base, + its_dev->event_map.nr_lpis); kfree(its_dev->event_map.col_map); /* Unmap device/itt */ @@ -2780,7 +2849,7 @@ static void its_vpe_irq_domain_free(struct irq_domain *domain, } if (bitmap_empty(vm->db_bitmap, vm->nr_db_lpis)) { - its_lpi_free_chunks(vm->db_bitmap, vm->db_lpi_base, vm->nr_db_lpis); + its_lpi_free(vm->db_bitmap, vm->db_lpi_base, vm->nr_db_lpis); its_free_prop_table(vm->vprop_page); } } @@ -2795,18 +2864,18 @@ static int its_vpe_irq_domain_alloc(struct irq_domain *domain, unsigned int virq BUG_ON(!vm); - bitmap = its_lpi_alloc_chunks(nr_irqs, &base, &nr_ids); + bitmap = its_lpi_alloc(roundup_pow_of_two(nr_irqs), &base, &nr_ids); if (!bitmap) return -ENOMEM; if (nr_ids < nr_irqs) { - its_lpi_free_chunks(bitmap, base, nr_ids); + its_lpi_free(bitmap, base, nr_ids); return -ENOMEM; } vprop_page = its_allocate_prop_table(GFP_KERNEL); if (!vprop_page) { - its_lpi_free_chunks(bitmap, base, nr_ids); + its_lpi_free(bitmap, base, nr_ids); return -ENOMEM; } @@ -2833,7 +2902,7 @@ static int its_vpe_irq_domain_alloc(struct irq_domain *domain, unsigned int virq if (i > 0) its_vpe_irq_domain_free(domain, virq, i - 1); - its_lpi_free_chunks(bitmap, base, nr_ids); + its_lpi_free(bitmap, base, nr_ids); its_free_prop_table(vprop_page); } @@ -3070,7 +3139,7 @@ static int its_save_disable(void) struct its_node *its; int err = 0; - spin_lock(&its_lock); + raw_spin_lock(&its_lock); list_for_each_entry(its, &its_nodes, entry) { void __iomem *base; @@ -3102,7 +3171,7 @@ err: writel_relaxed(its->ctlr_save, base + GITS_CTLR); } } - spin_unlock(&its_lock); + raw_spin_unlock(&its_lock); return err; } @@ -3112,7 +3181,7 @@ static void its_restore_enable(void) struct its_node *its; int ret; - spin_lock(&its_lock); + raw_spin_lock(&its_lock); list_for_each_entry(its, &its_nodes, entry) { void __iomem *base; int i; @@ -3164,7 +3233,7 @@ static void its_restore_enable(void) GITS_TYPER_HCC(gic_read_typer(base + GITS_TYPER))) its_cpu_init_collection(its); } - spin_unlock(&its_lock); + raw_spin_unlock(&its_lock); } static struct syscore_ops its_syscore_ops = { @@ -3398,9 +3467,9 @@ static int __init its_probe_one(struct resource *res, if (err) goto out_free_tables; - spin_lock(&its_lock); + raw_spin_lock(&its_lock); list_add(&its->entry, &its_nodes); - spin_unlock(&its_lock); + raw_spin_unlock(&its_lock); return 0; diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c index 76ea56d779a1..e214181b77b7 100644 --- a/drivers/irqchip/irq-gic-v3.c +++ b/drivers/irqchip/irq-gic-v3.c @@ -877,7 +877,7 @@ static struct irq_chip gic_eoimode1_chip = { .flags = IRQCHIP_SET_TYPE_MASKED, }; -#define GIC_ID_NR (1U << gic_data.rdists.id_bits) +#define GIC_ID_NR (1U << GICD_TYPER_ID_BITS(gic_data.rdists.gicd_typer)) static int gic_irq_domain_map(struct irq_domain *d, unsigned int irq, irq_hw_number_t hw) @@ -1091,7 +1091,7 @@ static int __init gic_init_bases(void __iomem *dist_base, * The GIC only supports up to 1020 interrupt sources (SGI+PPI+SPI) */ typer = readl_relaxed(gic_data.dist_base + GICD_TYPER); - gic_data.rdists.id_bits = GICD_TYPER_ID_BITS(typer); + gic_data.rdists.gicd_typer = typer; gic_irqs = GICD_TYPER_IRQS(typer); if (gic_irqs > 1020) gic_irqs = 1020; diff --git a/drivers/irqchip/irq-ingenic.c b/drivers/irqchip/irq-ingenic.c index fc5953dea509..2ff08986b536 100644 --- a/drivers/irqchip/irq-ingenic.c +++ b/drivers/irqchip/irq-ingenic.c @@ -165,6 +165,7 @@ static int __init intc_1chip_of_init(struct device_node *node, return ingenic_intc_of_init(node, 1); } IRQCHIP_DECLARE(jz4740_intc, "ingenic,jz4740-intc", intc_1chip_of_init); +IRQCHIP_DECLARE(jz4725b_intc, "ingenic,jz4725b-intc", intc_1chip_of_init); static int __init intc_2chip_of_init(struct device_node *node, struct device_node *parent) diff --git a/drivers/irqchip/irq-stm32-exti.c b/drivers/irqchip/irq-stm32-exti.c index 3a7e8905a97e..3df527fcf4e1 100644 --- a/drivers/irqchip/irq-stm32-exti.c +++ b/drivers/irqchip/irq-stm32-exti.c @@ -159,6 +159,7 @@ static const struct stm32_exti_bank *stm32mp1_exti_banks[] = { }; static const struct stm32_desc_irq stm32mp1_desc_irq[] = { + { .exti = 0, .irq_parent = 6 }, { .exti = 1, .irq_parent = 7 }, { .exti = 2, .irq_parent = 8 }, { .exti = 3, .irq_parent = 9 }, diff --git a/drivers/net/ethernet/8390/mac8390.c b/drivers/net/ethernet/8390/mac8390.c index b6d735bf8011..342ae08ec3c2 100644 --- a/drivers/net/ethernet/8390/mac8390.c +++ b/drivers/net/ethernet/8390/mac8390.c @@ -153,9 +153,6 @@ static void dayna_block_input(struct net_device *dev, int count, static void dayna_block_output(struct net_device *dev, int count, const unsigned char *buf, int start_page); -#define memcpy_fromio(a, b, c) memcpy((a), (void *)(b), (c)) -#define memcpy_toio(a, b, c) memcpy((void *)(a), (b), (c)) - #define memcmp_withio(a, b, c) memcmp((a), (void *)(b), (c)) /* Slow Sane (16-bit chunk memory read/write) Cabletron uses this */ @@ -239,7 +236,7 @@ static enum mac8390_access mac8390_testio(unsigned long membase) unsigned long outdata = 0xA5A0B5B0; unsigned long indata = 0x00000000; /* Try writing 32 bits */ - memcpy_toio(membase, &outdata, 4); + memcpy_toio((void __iomem *)membase, &outdata, 4); /* Now compare them */ if (memcmp_withio(&outdata, membase, 4) == 0) return ACCESS_32; @@ -711,7 +708,7 @@ static void sane_get_8390_hdr(struct net_device *dev, struct e8390_pkt_hdr *hdr, int ring_page) { unsigned long hdr_start = (ring_page - WD_START_PG)<<8; - memcpy_fromio(hdr, dev->mem_start + hdr_start, 4); + memcpy_fromio(hdr, (void __iomem *)dev->mem_start + hdr_start, 4); /* Fix endianness */ hdr->count = swab16(hdr->count); } @@ -725,13 +722,16 @@ static void sane_block_input(struct net_device *dev, int count, if (xfer_start + count > ei_status.rmem_end) { /* We must wrap the input move. */ int semi_count = ei_status.rmem_end - xfer_start; - memcpy_fromio(skb->data, dev->mem_start + xfer_base, + memcpy_fromio(skb->data, + (void __iomem *)dev->mem_start + xfer_base, semi_count); count -= semi_count; - memcpy_fromio(skb->data + semi_count, ei_status.rmem_start, - count); + memcpy_fromio(skb->data + semi_count, + (void __iomem *)ei_status.rmem_start, count); } else { - memcpy_fromio(skb->data, dev->mem_start + xfer_base, count); + memcpy_fromio(skb->data, + (void __iomem *)dev->mem_start + xfer_base, + count); } } @@ -740,7 +740,7 @@ static void sane_block_output(struct net_device *dev, int count, { long shmem = (start_page - WD_START_PG)<<8; - memcpy_toio(dev->mem_start + shmem, buf, count); + memcpy_toio((void __iomem *)dev->mem_start + shmem, buf, count); } /* dayna block input/output */ diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c index 956860a69797..3bdab972420b 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c @@ -762,7 +762,7 @@ static int hw_atl_b0_hw_packet_filter_set(struct aq_hw_s *self, hw_atl_rpfl2promiscuous_mode_en_set(self, IS_FILTER_ENABLED(IFF_PROMISC)); hw_atl_rpfl2multicast_flr_en_set(self, - IS_FILTER_ENABLED(IFF_MULTICAST), 0); + IS_FILTER_ENABLED(IFF_ALLMULTI), 0); hw_atl_rpfl2_accept_all_mc_packets_set(self, IS_FILTER_ENABLED(IFF_ALLMULTI)); diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c index 5d08d2aeb172..e337da6ba2a4 100644 --- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c +++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c @@ -1083,6 +1083,8 @@ static int bgx_lmac_enable(struct bgx *bgx, u8 lmacid) lmac->dmacs_count = (RX_DMAC_COUNT / bgx->lmac_count); lmac->dmacs = kcalloc(lmac->dmacs_count, sizeof(*lmac->dmacs), GFP_KERNEL); + if (!lmac->dmacs) + return -ENOMEM; /* Enable lmac */ bgx_reg_modify(bgx, lmacid, BGX_CMRX_CFG, CMR_EN); diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c index 00fc5f1afb1d..7dddb9e748b8 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c @@ -1038,10 +1038,8 @@ static void mk_act_open_req(struct filter_entry *f, struct sk_buff *skb, OPCODE_TID(req) = htonl(MK_OPCODE_TID(CPL_ACT_OPEN_REQ, qid_filterid)); req->local_port = cpu_to_be16(f->fs.val.lport); req->peer_port = cpu_to_be16(f->fs.val.fport); - req->local_ip = f->fs.val.lip[0] | f->fs.val.lip[1] << 8 | - f->fs.val.lip[2] << 16 | f->fs.val.lip[3] << 24; - req->peer_ip = f->fs.val.fip[0] | f->fs.val.fip[1] << 8 | - f->fs.val.fip[2] << 16 | f->fs.val.fip[3] << 24; + memcpy(&req->local_ip, f->fs.val.lip, 4); + memcpy(&req->peer_ip, f->fs.val.fip, 4); req->opt0 = cpu_to_be64(NAGLE_V(f->fs.newvlan == VLAN_REMOVE || f->fs.newvlan == VLAN_REWRITE) | DELACK_V(f->fs.hitcnts) | diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index eb9eb7aa953a..405236cf0b04 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -858,8 +858,6 @@ struct mlx5e_profile { mlx5e_fp_handle_rx_cqe handle_rx_cqe; mlx5e_fp_handle_rx_cqe handle_rx_cqe_mpwqe; } rx_handlers; - void (*netdev_registered_init)(struct mlx5e_priv *priv); - void (*netdev_registered_remove)(struct mlx5e_priv *priv); int max_tc; }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c index e33afa8d2417..722998d68564 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c @@ -443,16 +443,12 @@ static int mlx5e_dcbnl_ieee_setapp(struct net_device *dev, struct dcb_app *app) bool is_new; int err; - if (app->selector != IEEE_8021QAZ_APP_SEL_DSCP) - return -EINVAL; - - if (!MLX5_CAP_GEN(priv->mdev, vport_group_manager)) - return -EINVAL; - - if (!MLX5_DSCP_SUPPORTED(priv->mdev)) - return -EINVAL; + if (!MLX5_CAP_GEN(priv->mdev, vport_group_manager) || + !MLX5_DSCP_SUPPORTED(priv->mdev)) + return -EOPNOTSUPP; - if (app->protocol >= MLX5E_MAX_DSCP) + if ((app->selector != IEEE_8021QAZ_APP_SEL_DSCP) || + (app->protocol >= MLX5E_MAX_DSCP)) return -EINVAL; /* Save the old entry info */ @@ -500,16 +496,12 @@ static int mlx5e_dcbnl_ieee_delapp(struct net_device *dev, struct dcb_app *app) struct mlx5e_priv *priv = netdev_priv(dev); int err; - if (app->selector != IEEE_8021QAZ_APP_SEL_DSCP) - return -EINVAL; - - if (!MLX5_CAP_GEN(priv->mdev, vport_group_manager)) - return -EINVAL; - - if (!MLX5_DSCP_SUPPORTED(priv->mdev)) - return -EINVAL; + if (!MLX5_CAP_GEN(priv->mdev, vport_group_manager) || + !MLX5_DSCP_SUPPORTED(priv->mdev)) + return -EOPNOTSUPP; - if (app->protocol >= MLX5E_MAX_DSCP) + if ((app->selector != IEEE_8021QAZ_APP_SEL_DSCP) || + (app->protocol >= MLX5E_MAX_DSCP)) return -EINVAL; /* Skip if no dscp app entry */ @@ -1146,7 +1138,7 @@ static int mlx5e_set_trust_state(struct mlx5e_priv *priv, u8 trust_state) { int err; - err = mlx5_set_trust_state(priv->mdev, trust_state); + err = mlx5_set_trust_state(priv->mdev, trust_state); if (err) return err; priv->dcbx_dp.trust_state = trust_state; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 3a2c4e548226..dfbcda0d0e08 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -1970,15 +1970,15 @@ static bool actions_match_supported(struct mlx5e_priv *priv, static bool same_hw_devs(struct mlx5e_priv *priv, struct mlx5e_priv *peer_priv) { struct mlx5_core_dev *fmdev, *pmdev; - u16 func_id, peer_id; + u64 fsystem_guid, psystem_guid; fmdev = priv->mdev; pmdev = peer_priv->mdev; - func_id = (u16)((fmdev->pdev->bus->number << 8) | PCI_SLOT(fmdev->pdev->devfn)); - peer_id = (u16)((pmdev->pdev->bus->number << 8) | PCI_SLOT(pmdev->pdev->devfn)); + mlx5_query_nic_vport_system_image_guid(fmdev, &fsystem_guid); + mlx5_query_nic_vport_system_image_guid(pmdev, &psystem_guid); - return (func_id == peer_id); + return (fsystem_guid == psystem_guid); } static int parse_tc_nic_actions(struct mlx5e_priv *priv, struct tcf_exts *exts, diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c index 358edab9e72e..3e34cb8ac1d3 100644 --- a/drivers/net/ethernet/ti/cpsw.c +++ b/drivers/net/ethernet/ti/cpsw.c @@ -2086,14 +2086,16 @@ static int cpsw_ndo_vlan_rx_add_vid(struct net_device *ndev, int i; for (i = 0; i < cpsw->data.slaves; i++) { - if (vid == cpsw->slaves[i].port_vlan) - return -EINVAL; + if (vid == cpsw->slaves[i].port_vlan) { + ret = -EINVAL; + goto err; + } } } dev_info(priv->dev, "Adding vlanid %d to vlan filter\n", vid); ret = cpsw_add_vlan_ale_entry(priv, vid); - +err: pm_runtime_put(cpsw->dev); return ret; } @@ -2119,22 +2121,17 @@ static int cpsw_ndo_vlan_rx_kill_vid(struct net_device *ndev, for (i = 0; i < cpsw->data.slaves; i++) { if (vid == cpsw->slaves[i].port_vlan) - return -EINVAL; + goto err; } } dev_info(priv->dev, "removing vlanid %d from vlan filter\n", vid); ret = cpsw_ale_del_vlan(cpsw->ale, vid, 0); - if (ret != 0) - return ret; - - ret = cpsw_ale_del_ucast(cpsw->ale, priv->mac_addr, - HOST_PORT_NUM, ALE_VLAN, vid); - if (ret != 0) - return ret; - - ret = cpsw_ale_del_mcast(cpsw->ale, priv->ndev->broadcast, - 0, ALE_VLAN, vid); + ret |= cpsw_ale_del_ucast(cpsw->ale, priv->mac_addr, + HOST_PORT_NUM, ALE_VLAN, vid); + ret |= cpsw_ale_del_mcast(cpsw->ale, priv->ndev->broadcast, + 0, ALE_VLAN, vid); +err: pm_runtime_put(cpsw->dev); return ret; } diff --git a/drivers/net/ethernet/ti/cpsw_ale.c b/drivers/net/ethernet/ti/cpsw_ale.c index 93dc05c194d3..5766225a4ce1 100644 --- a/drivers/net/ethernet/ti/cpsw_ale.c +++ b/drivers/net/ethernet/ti/cpsw_ale.c @@ -394,7 +394,7 @@ int cpsw_ale_del_mcast(struct cpsw_ale *ale, u8 *addr, int port_mask, idx = cpsw_ale_match_addr(ale, addr, (flags & ALE_VLAN) ? vid : 0); if (idx < 0) - return -EINVAL; + return -ENOENT; cpsw_ale_read(ale, idx, ale_entry); diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c index 2d8812dd1534..9dd2ca62d84a 100644 --- a/drivers/net/xen-netfront.c +++ b/drivers/net/xen-netfront.c @@ -894,7 +894,6 @@ static RING_IDX xennet_fill_frags(struct netfront_queue *queue, struct sk_buff *skb, struct sk_buff_head *list) { - struct skb_shared_info *shinfo = skb_shinfo(skb); RING_IDX cons = queue->rx.rsp_cons; struct sk_buff *nskb; @@ -903,15 +902,16 @@ static RING_IDX xennet_fill_frags(struct netfront_queue *queue, RING_GET_RESPONSE(&queue->rx, ++cons); skb_frag_t *nfrag = &skb_shinfo(nskb)->frags[0]; - if (shinfo->nr_frags == MAX_SKB_FRAGS) { + if (skb_shinfo(skb)->nr_frags == MAX_SKB_FRAGS) { unsigned int pull_to = NETFRONT_SKB_CB(skb)->pull_to; BUG_ON(pull_to <= skb_headlen(skb)); __pskb_pull_tail(skb, pull_to - skb_headlen(skb)); } - BUG_ON(shinfo->nr_frags >= MAX_SKB_FRAGS); + BUG_ON(skb_shinfo(skb)->nr_frags >= MAX_SKB_FRAGS); - skb_add_rx_frag(skb, shinfo->nr_frags, skb_frag_page(nfrag), + skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, + skb_frag_page(nfrag), rx->offset, rx->status, PAGE_SIZE); skb_shinfo(nskb)->nr_frags = 0; diff --git a/drivers/nubus/bus.c b/drivers/nubus/bus.c index a59b6c4bb5b8..ad3d17c42e23 100644 --- a/drivers/nubus/bus.c +++ b/drivers/nubus/bus.c @@ -5,6 +5,7 @@ // Copyright (C) 2017 Finn Thain #include <linux/device.h> +#include <linux/dma-mapping.h> #include <linux/list.h> #include <linux/nubus.h> #include <linux/seq_file.h> @@ -93,6 +94,8 @@ int nubus_device_register(struct nubus_board *board) board->dev.release = nubus_device_release; board->dev.bus = &nubus_bus_type; dev_set_name(&board->dev, "slot.%X", board->slot); + board->dev.dma_mask = &board->dev.coherent_dma_mask; + dma_set_mask(&board->dev, DMA_BIT_MASK(32)); return device_register(&board->dev); } diff --git a/drivers/scsi/fcoe/fcoe_ctlr.c b/drivers/scsi/fcoe/fcoe_ctlr.c index ea23c8dffc25..ffec695e0bfb 100644 --- a/drivers/scsi/fcoe/fcoe_ctlr.c +++ b/drivers/scsi/fcoe/fcoe_ctlr.c @@ -754,9 +754,9 @@ int fcoe_ctlr_els_send(struct fcoe_ctlr *fip, struct fc_lport *lport, case ELS_LOGO: if (fip->mode == FIP_MODE_VN2VN) { if (fip->state != FIP_ST_VNMP_UP) - return -EINVAL; + goto drop; if (ntoh24(fh->fh_d_id) == FC_FID_FLOGI) - return -EINVAL; + goto drop; } else { if (fip->state != FIP_ST_ENABLED) return 0; @@ -799,9 +799,9 @@ int fcoe_ctlr_els_send(struct fcoe_ctlr *fip, struct fc_lport *lport, fip->send(fip, skb); return -EINPROGRESS; drop: - kfree_skb(skb); LIBFCOE_FIP_DBG(fip, "drop els_send op %u d_id %x\n", op, ntoh24(fh->fh_d_id)); + kfree_skb(skb); return -EINVAL; } EXPORT_SYMBOL(fcoe_ctlr_els_send); diff --git a/drivers/scsi/libfc/fc_rport.c b/drivers/scsi/libfc/fc_rport.c index 31d31aad3de1..89b1f1af2fd4 100644 --- a/drivers/scsi/libfc/fc_rport.c +++ b/drivers/scsi/libfc/fc_rport.c @@ -2164,6 +2164,7 @@ static void fc_rport_recv_logo_req(struct fc_lport *lport, struct fc_frame *fp) FC_RPORT_DBG(rdata, "Received LOGO request while in state %s\n", fc_rport_state(rdata)); + rdata->flags &= ~FC_RP_STARTED; fc_rport_enter_delete(rdata, RPORT_EV_STOP); mutex_unlock(&rdata->rp_mutex); kref_put(&rdata->kref, fc_rport_destroy); diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c index 569392d0d4c9..e44c91edf92d 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_base.c +++ b/drivers/scsi/mpt3sas/mpt3sas_base.c @@ -3343,11 +3343,10 @@ _base_mpi_ep_writeq(__u64 b, volatile void __iomem *addr, spinlock_t *writeq_lock) { unsigned long flags; - __u64 data_out = b; spin_lock_irqsave(writeq_lock, flags); - writel((u32)(data_out), addr); - writel((u32)(data_out >> 32), (addr + 4)); + __raw_writel((u32)(b), addr); + __raw_writel((u32)(b >> 32), (addr + 4)); mmiowb(); spin_unlock_irqrestore(writeq_lock, flags); } @@ -3367,7 +3366,8 @@ _base_mpi_ep_writeq(__u64 b, volatile void __iomem *addr, static inline void _base_writeq(__u64 b, volatile void __iomem *addr, spinlock_t *writeq_lock) { - writeq(b, addr); + __raw_writeq(b, addr); + mmiowb(); } #else static inline void @@ -5268,7 +5268,7 @@ _base_handshake_req_reply_wait(struct MPT3SAS_ADAPTER *ioc, int request_bytes, /* send message 32-bits at a time */ for (i = 0, failed = 0; i < request_bytes/4 && !failed; i++) { - writel((u32)(request[i]), &ioc->chip->Doorbell); + writel(cpu_to_le32(request[i]), &ioc->chip->Doorbell); if ((_base_wait_for_doorbell_ack(ioc, 5))) failed = 1; } @@ -5289,7 +5289,7 @@ _base_handshake_req_reply_wait(struct MPT3SAS_ADAPTER *ioc, int request_bytes, } /* read the first two 16-bits, it gives the total length of the reply */ - reply[0] = (u16)(readl(&ioc->chip->Doorbell) + reply[0] = le16_to_cpu(readl(&ioc->chip->Doorbell) & MPI2_DOORBELL_DATA_MASK); writel(0, &ioc->chip->HostInterruptStatus); if ((_base_wait_for_doorbell_int(ioc, 5))) { @@ -5298,7 +5298,7 @@ _base_handshake_req_reply_wait(struct MPT3SAS_ADAPTER *ioc, int request_bytes, ioc->name, __LINE__); return -EFAULT; } - reply[1] = (u16)(readl(&ioc->chip->Doorbell) + reply[1] = le16_to_cpu(readl(&ioc->chip->Doorbell) & MPI2_DOORBELL_DATA_MASK); writel(0, &ioc->chip->HostInterruptStatus); @@ -5312,7 +5312,7 @@ _base_handshake_req_reply_wait(struct MPT3SAS_ADAPTER *ioc, int request_bytes, if (i >= reply_bytes/2) /* overflow case */ readl(&ioc->chip->Doorbell); else - reply[i] = (u16)(readl(&ioc->chip->Doorbell) + reply[i] = le16_to_cpu(readl(&ioc->chip->Doorbell) & MPI2_DOORBELL_DATA_MASK); writel(0, &ioc->chip->HostInterruptStatus); } diff --git a/drivers/scsi/qedi/qedi_main.c b/drivers/scsi/qedi/qedi_main.c index 091ec1207bea..cff83b9457f7 100644 --- a/drivers/scsi/qedi/qedi_main.c +++ b/drivers/scsi/qedi/qedi_main.c @@ -888,7 +888,7 @@ static void qedi_get_boot_tgt_info(struct nvm_iscsi_block *block, ipv6_en = !!(block->generic.ctrl_flags & NVM_ISCSI_CFG_GEN_IPV6_ENABLED); - snprintf(tgt->iscsi_name, NVM_ISCSI_CFG_ISCSI_NAME_MAX_LEN, "%s\n", + snprintf(tgt->iscsi_name, sizeof(tgt->iscsi_name), "%s\n", block->target[index].target_name.byte); tgt->ipv6_en = ipv6_en; diff --git a/drivers/scsi/qla2xxx/qla_iocb.c b/drivers/scsi/qla2xxx/qla_iocb.c index a91cca52b5d5..dd93a22fe843 100644 --- a/drivers/scsi/qla2xxx/qla_iocb.c +++ b/drivers/scsi/qla2xxx/qla_iocb.c @@ -2130,34 +2130,11 @@ __qla2x00_alloc_iocbs(struct qla_qpair *qpair, srb_t *sp) req_cnt = 1; handle = 0; - if (!sp) - goto skip_cmd_array; - - /* Check for room in outstanding command list. */ - handle = req->current_outstanding_cmd; - for (index = 1; index < req->num_outstanding_cmds; index++) { - handle++; - if (handle == req->num_outstanding_cmds) - handle = 1; - if (!req->outstanding_cmds[handle]) - break; - } - if (index == req->num_outstanding_cmds) { - ql_log(ql_log_warn, vha, 0x700b, - "No room on outstanding cmd array.\n"); - goto queuing_error; - } - - /* Prep command array. */ - req->current_outstanding_cmd = handle; - req->outstanding_cmds[handle] = sp; - sp->handle = handle; - - /* Adjust entry-counts as needed. */ - if (sp->type != SRB_SCSI_CMD) + if (sp && (sp->type != SRB_SCSI_CMD)) { + /* Adjust entry-counts as needed. */ req_cnt = sp->iocbs; + } -skip_cmd_array: /* Check for room on request queue. */ if (req->cnt < req_cnt + 2) { if (qpair->use_shadow_reg) @@ -2183,6 +2160,28 @@ skip_cmd_array: if (req->cnt < req_cnt + 2) goto queuing_error; + if (sp) { + /* Check for room in outstanding command list. */ + handle = req->current_outstanding_cmd; + for (index = 1; index < req->num_outstanding_cmds; index++) { + handle++; + if (handle == req->num_outstanding_cmds) + handle = 1; + if (!req->outstanding_cmds[handle]) + break; + } + if (index == req->num_outstanding_cmds) { + ql_log(ql_log_warn, vha, 0x700b, + "No room on outstanding cmd array.\n"); + goto queuing_error; + } + + /* Prep command array. */ + req->current_outstanding_cmd = handle; + req->outstanding_cmds[handle] = sp; + sp->handle = handle; + } + /* Prep packet */ req->cnt -= req_cnt; pkt = req->ring_ptr; @@ -2195,6 +2194,8 @@ skip_cmd_array: pkt->handle = handle; } + return pkt; + queuing_error: qpair->tgt_counters.num_alloc_iocb_failed++; return pkt; diff --git a/drivers/scsi/sr.c b/drivers/scsi/sr.c index 3f3cb72e0c0c..d0389b20574d 100644 --- a/drivers/scsi/sr.c +++ b/drivers/scsi/sr.c @@ -523,18 +523,26 @@ static int sr_init_command(struct scsi_cmnd *SCpnt) static int sr_block_open(struct block_device *bdev, fmode_t mode) { struct scsi_cd *cd; + struct scsi_device *sdev; int ret = -ENXIO; + cd = scsi_cd_get(bdev->bd_disk); + if (!cd) + goto out; + + sdev = cd->device; + scsi_autopm_get_device(sdev); check_disk_change(bdev); mutex_lock(&sr_mutex); - cd = scsi_cd_get(bdev->bd_disk); - if (cd) { - ret = cdrom_open(&cd->cdi, bdev, mode); - if (ret) - scsi_cd_put(cd); - } + ret = cdrom_open(&cd->cdi, bdev, mode); mutex_unlock(&sr_mutex); + + scsi_autopm_put_device(sdev); + if (ret) + scsi_cd_put(cd); + +out: return ret; } @@ -562,6 +570,8 @@ static int sr_block_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd, if (ret) goto out; + scsi_autopm_get_device(sdev); + /* * Send SCSI addressing ioctls directly to mid level, send other * ioctls to cdrom/block level. @@ -570,15 +580,18 @@ static int sr_block_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd, case SCSI_IOCTL_GET_IDLUN: case SCSI_IOCTL_GET_BUS_NUMBER: ret = scsi_ioctl(sdev, cmd, argp); - goto out; + goto put; } ret = cdrom_ioctl(&cd->cdi, bdev, mode, cmd, arg); if (ret != -ENOSYS) - goto out; + goto put; ret = scsi_ioctl(sdev, cmd, argp); +put: + scsi_autopm_put_device(sdev); + out: mutex_unlock(&sr_mutex); return ret; diff --git a/drivers/scsi/vmw_pvscsi.c b/drivers/scsi/vmw_pvscsi.c index 777e5f1e52d1..0cd947f78b5b 100644 --- a/drivers/scsi/vmw_pvscsi.c +++ b/drivers/scsi/vmw_pvscsi.c @@ -561,9 +561,14 @@ static void pvscsi_complete_request(struct pvscsi_adapter *adapter, (btstat == BTSTAT_SUCCESS || btstat == BTSTAT_LINKED_COMMAND_COMPLETED || btstat == BTSTAT_LINKED_COMMAND_COMPLETED_WITH_FLAG)) { - cmd->result = (DID_OK << 16) | sdstat; - if (sdstat == SAM_STAT_CHECK_CONDITION && cmd->sense_buffer) - cmd->result |= (DRIVER_SENSE << 24); + if (sdstat == SAM_STAT_COMMAND_TERMINATED) { + cmd->result = (DID_RESET << 16); + } else { + cmd->result = (DID_OK << 16) | sdstat; + if (sdstat == SAM_STAT_CHECK_CONDITION && + cmd->sense_buffer) + cmd->result |= (DRIVER_SENSE << 24); + } } else switch (btstat) { case BTSTAT_SUCCESS: diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index a502f1af4a21..ed3114556fda 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -1560,9 +1560,12 @@ int vhost_init_device_iotlb(struct vhost_dev *d, bool enabled) d->iotlb = niotlb; for (i = 0; i < d->nvqs; ++i) { - mutex_lock(&d->vqs[i]->mutex); - d->vqs[i]->iotlb = niotlb; - mutex_unlock(&d->vqs[i]->mutex); + struct vhost_virtqueue *vq = d->vqs[i]; + + mutex_lock(&vq->mutex); + vq->iotlb = niotlb; + __vhost_vq_meta_reset(vq); + mutex_unlock(&vq->mutex); } vhost_umem_clean(oiotlb); diff --git a/drivers/video/fbdev/efifb.c b/drivers/video/fbdev/efifb.c index 46a4484e3da7..c6f78d27947b 100644 --- a/drivers/video/fbdev/efifb.c +++ b/drivers/video/fbdev/efifb.c @@ -20,7 +20,7 @@ #include <drm/drm_connector.h> /* For DRM_MODE_PANEL_ORIENTATION_* */ static bool request_mem_succeeded = false; -static bool nowc = false; +static u64 mem_flags = EFI_MEMORY_WC | EFI_MEMORY_UC; static struct fb_var_screeninfo efifb_defined = { .activate = FB_ACTIVATE_NOW, @@ -68,8 +68,12 @@ static int efifb_setcolreg(unsigned regno, unsigned red, unsigned green, static void efifb_destroy(struct fb_info *info) { - if (info->screen_base) - iounmap(info->screen_base); + if (info->screen_base) { + if (mem_flags & (EFI_MEMORY_UC | EFI_MEMORY_WC)) + iounmap(info->screen_base); + else + memunmap(info->screen_base); + } if (request_mem_succeeded) release_mem_region(info->apertures->ranges[0].base, info->apertures->ranges[0].size); @@ -104,7 +108,7 @@ static int efifb_setup(char *options) else if (!strncmp(this_opt, "width:", 6)) screen_info.lfb_width = simple_strtoul(this_opt+6, NULL, 0); else if (!strcmp(this_opt, "nowc")) - nowc = true; + mem_flags &= ~EFI_MEMORY_WC; } } @@ -164,6 +168,7 @@ static int efifb_probe(struct platform_device *dev) unsigned int size_remap; unsigned int size_total; char *option = NULL; + efi_memory_desc_t md; if (screen_info.orig_video_isVGA != VIDEO_TYPE_EFI || pci_dev_disabled) return -ENODEV; @@ -272,12 +277,35 @@ static int efifb_probe(struct platform_device *dev) info->apertures->ranges[0].base = efifb_fix.smem_start; info->apertures->ranges[0].size = size_remap; - if (nowc) - info->screen_base = ioremap(efifb_fix.smem_start, efifb_fix.smem_len); - else - info->screen_base = ioremap_wc(efifb_fix.smem_start, efifb_fix.smem_len); + if (!efi_mem_desc_lookup(efifb_fix.smem_start, &md)) { + if ((efifb_fix.smem_start + efifb_fix.smem_len) > + (md.phys_addr + (md.num_pages << EFI_PAGE_SHIFT))) { + pr_err("efifb: video memory @ 0x%lx spans multiple EFI memory regions\n", + efifb_fix.smem_start); + err = -EIO; + goto err_release_fb; + } + /* + * If the UEFI memory map covers the efifb region, we may only + * remap it using the attributes the memory map prescribes. + */ + mem_flags |= EFI_MEMORY_WT | EFI_MEMORY_WB; + mem_flags &= md.attribute; + } + if (mem_flags & EFI_MEMORY_WC) + info->screen_base = ioremap_wc(efifb_fix.smem_start, + efifb_fix.smem_len); + else if (mem_flags & EFI_MEMORY_UC) + info->screen_base = ioremap(efifb_fix.smem_start, + efifb_fix.smem_len); + else if (mem_flags & EFI_MEMORY_WT) + info->screen_base = memremap(efifb_fix.smem_start, + efifb_fix.smem_len, MEMREMAP_WT); + else if (mem_flags & EFI_MEMORY_WB) + info->screen_base = memremap(efifb_fix.smem_start, + efifb_fix.smem_len, MEMREMAP_WB); if (!info->screen_base) { - pr_err("efifb: abort, cannot ioremap video memory 0x%x @ 0x%lx\n", + pr_err("efifb: abort, cannot remap video memory 0x%x @ 0x%lx\n", efifb_fix.smem_len, efifb_fix.smem_start); err = -EIO; goto err_release_fb; @@ -371,7 +399,10 @@ err_fb_dealoc: err_groups: sysfs_remove_groups(&dev->dev.kobj, efifb_groups); err_unmap: - iounmap(info->screen_base); + if (mem_flags & (EFI_MEMORY_UC | EFI_MEMORY_WC)) + iounmap(info->screen_base); + else + memunmap(info->screen_base); err_release_fb: framebuffer_release(info); err_release_mem: diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c index a1b18082991b..183cc5418722 100644 --- a/fs/afs/rxrpc.c +++ b/fs/afs/rxrpc.c @@ -648,7 +648,7 @@ static void afs_wake_up_async_call(struct sock *sk, struct rxrpc_call *rxcall, trace_afs_notify_call(rxcall, call); call->need_attention = true; - u = __atomic_add_unless(&call->usage, 1, 0); + u = atomic_fetch_add_unless(&call->usage, 1, 0); if (u != 0) { trace_afs_call(call, afs_call_trace_wake, u, atomic_read(&call->net->nr_outstanding_calls), diff --git a/fs/dcache.c b/fs/dcache.c index 0e8e5de3c48a..ceb7b491d1b9 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -358,14 +358,11 @@ static void dentry_unlink_inode(struct dentry * dentry) __releases(dentry->d_inode->i_lock) { struct inode *inode = dentry->d_inode; - bool hashed = !d_unhashed(dentry); - if (hashed) - raw_write_seqcount_begin(&dentry->d_seq); + raw_write_seqcount_begin(&dentry->d_seq); __d_clear_type_and_inode(dentry); hlist_del_init(&dentry->d_u.d_alias); - if (hashed) - raw_write_seqcount_end(&dentry->d_seq); + raw_write_seqcount_end(&dentry->d_seq); spin_unlock(&dentry->d_lock); spin_unlock(&inode->i_lock); if (!inode->i_nlink) @@ -1932,10 +1929,12 @@ struct dentry *d_make_root(struct inode *root_inode) if (root_inode) { res = d_alloc_anon(root_inode->i_sb); - if (res) + if (res) { + res->d_flags |= DCACHE_RCUACCESS; d_instantiate(res, root_inode); - else + } else { iput(root_inode); + } } return res; } diff --git a/fs/efivarfs/inode.c b/fs/efivarfs/inode.c index 71fccccf317e..8c6ab6c95727 100644 --- a/fs/efivarfs/inode.c +++ b/fs/efivarfs/inode.c @@ -86,7 +86,9 @@ static int efivarfs_create(struct inode *dir, struct dentry *dentry, /* length of the variable name itself: remove GUID and separator */ namelen = dentry->d_name.len - EFI_VARIABLE_GUID_LEN - 1; - uuid_le_to_bin(dentry->d_name.name + namelen + 1, &var->var.VendorGuid); + err = guid_parse(dentry->d_name.name + namelen + 1, &var->var.VendorGuid); + if (err) + goto out; if (efivar_variable_is_removable(var->var.VendorGuid, dentry->d_name.name, namelen)) diff --git a/fs/namespace.c b/fs/namespace.c index 8ddd14806799..bd2f4c68506a 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -659,12 +659,21 @@ int __legitimize_mnt(struct vfsmount *bastard, unsigned seq) return 0; mnt = real_mount(bastard); mnt_add_count(mnt, 1); + smp_mb(); // see mntput_no_expire() if (likely(!read_seqretry(&mount_lock, seq))) return 0; if (bastard->mnt_flags & MNT_SYNC_UMOUNT) { mnt_add_count(mnt, -1); return 1; } + lock_mount_hash(); + if (unlikely(bastard->mnt_flags & MNT_DOOMED)) { + mnt_add_count(mnt, -1); + unlock_mount_hash(); + return 1; + } + unlock_mount_hash(); + /* caller will mntput() */ return -1; } @@ -1195,12 +1204,27 @@ static DECLARE_DELAYED_WORK(delayed_mntput_work, delayed_mntput); static void mntput_no_expire(struct mount *mnt) { rcu_read_lock(); - mnt_add_count(mnt, -1); - if (likely(mnt->mnt_ns)) { /* shouldn't be the last one */ + if (likely(READ_ONCE(mnt->mnt_ns))) { + /* + * Since we don't do lock_mount_hash() here, + * ->mnt_ns can change under us. However, if it's + * non-NULL, then there's a reference that won't + * be dropped until after an RCU delay done after + * turning ->mnt_ns NULL. So if we observe it + * non-NULL under rcu_read_lock(), the reference + * we are dropping is not the final one. + */ + mnt_add_count(mnt, -1); rcu_read_unlock(); return; } lock_mount_hash(); + /* + * make sure that if __legitimize_mnt() has not seen us grab + * mount_lock, we'll see their refcount increment here. + */ + smp_mb(); + mnt_add_count(mnt, -1); if (mnt_get_count(mnt)) { rcu_read_unlock(); unlock_mount_hash(); diff --git a/fs/timerfd.c b/fs/timerfd.c index cdad49da3ff7..38c695ce385b 100644 --- a/fs/timerfd.c +++ b/fs/timerfd.c @@ -533,8 +533,8 @@ static int do_timerfd_gettime(int ufd, struct itimerspec64 *t) } SYSCALL_DEFINE4(timerfd_settime, int, ufd, int, flags, - const struct itimerspec __user *, utmr, - struct itimerspec __user *, otmr) + const struct __kernel_itimerspec __user *, utmr, + struct __kernel_itimerspec __user *, otmr) { struct itimerspec64 new, old; int ret; @@ -550,7 +550,7 @@ SYSCALL_DEFINE4(timerfd_settime, int, ufd, int, flags, return ret; } -SYSCALL_DEFINE2(timerfd_gettime, int, ufd, struct itimerspec __user *, otmr) +SYSCALL_DEFINE2(timerfd_gettime, int, ufd, struct __kernel_itimerspec __user *, otmr) { struct itimerspec64 kotmr; int ret = do_timerfd_gettime(ufd, &kotmr); @@ -559,7 +559,7 @@ SYSCALL_DEFINE2(timerfd_gettime, int, ufd, struct itimerspec __user *, otmr) return put_itimerspec64(&kotmr, otmr) ? -EFAULT : 0; } -#ifdef CONFIG_COMPAT +#ifdef CONFIG_COMPAT_32BIT_TIME COMPAT_SYSCALL_DEFINE4(timerfd_settime, int, ufd, int, flags, const struct compat_itimerspec __user *, utmr, struct compat_itimerspec __user *, otmr) diff --git a/include/asm-generic/atomic-instrumented.h b/include/asm-generic/atomic-instrumented.h index ec07f23678ea..0d4b1d3dbc1e 100644 --- a/include/asm-generic/atomic-instrumented.h +++ b/include/asm-generic/atomic-instrumented.h @@ -84,42 +84,59 @@ static __always_inline bool atomic64_try_cmpxchg(atomic64_t *v, s64 *old, s64 ne } #endif -static __always_inline int __atomic_add_unless(atomic_t *v, int a, int u) +#ifdef arch_atomic_fetch_add_unless +#define atomic_fetch_add_unless atomic_fetch_add_unless +static __always_inline int atomic_fetch_add_unless(atomic_t *v, int a, int u) { kasan_check_write(v, sizeof(*v)); - return __arch_atomic_add_unless(v, a, u); + return arch_atomic_fetch_add_unless(v, a, u); } +#endif - -static __always_inline bool atomic64_add_unless(atomic64_t *v, s64 a, s64 u) +#ifdef arch_atomic64_fetch_add_unless +#define atomic64_fetch_add_unless atomic64_fetch_add_unless +static __always_inline s64 atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u) { kasan_check_write(v, sizeof(*v)); - return arch_atomic64_add_unless(v, a, u); + return arch_atomic64_fetch_add_unless(v, a, u); } +#endif +#ifdef arch_atomic_inc +#define atomic_inc atomic_inc static __always_inline void atomic_inc(atomic_t *v) { kasan_check_write(v, sizeof(*v)); arch_atomic_inc(v); } +#endif +#ifdef arch_atomic64_inc +#define atomic64_inc atomic64_inc static __always_inline void atomic64_inc(atomic64_t *v) { kasan_check_write(v, sizeof(*v)); arch_atomic64_inc(v); } +#endif +#ifdef arch_atomic_dec +#define atomic_dec atomic_dec static __always_inline void atomic_dec(atomic_t *v) { kasan_check_write(v, sizeof(*v)); arch_atomic_dec(v); } +#endif +#ifdef atch_atomic64_dec +#define atomic64_dec static __always_inline void atomic64_dec(atomic64_t *v) { kasan_check_write(v, sizeof(*v)); arch_atomic64_dec(v); } +#endif static __always_inline void atomic_add(int i, atomic_t *v) { @@ -181,65 +198,95 @@ static __always_inline void atomic64_xor(s64 i, atomic64_t *v) arch_atomic64_xor(i, v); } +#ifdef arch_atomic_inc_return +#define atomic_inc_return atomic_inc_return static __always_inline int atomic_inc_return(atomic_t *v) { kasan_check_write(v, sizeof(*v)); return arch_atomic_inc_return(v); } +#endif +#ifdef arch_atomic64_in_return +#define atomic64_inc_return atomic64_inc_return static __always_inline s64 atomic64_inc_return(atomic64_t *v) { kasan_check_write(v, sizeof(*v)); return arch_atomic64_inc_return(v); } +#endif +#ifdef arch_atomic_dec_return +#define atomic_dec_return atomic_dec_return static __always_inline int atomic_dec_return(atomic_t *v) { kasan_check_write(v, sizeof(*v)); return arch_atomic_dec_return(v); } +#endif +#ifdef arch_atomic64_dec_return +#define atomic64_dec_return atomic64_dec_return static __always_inline s64 atomic64_dec_return(atomic64_t *v) { kasan_check_write(v, sizeof(*v)); return arch_atomic64_dec_return(v); } +#endif -static __always_inline s64 atomic64_inc_not_zero(atomic64_t *v) +#ifdef arch_atomic64_inc_not_zero +#define atomic64_inc_not_zero atomic64_inc_not_zero +static __always_inline bool atomic64_inc_not_zero(atomic64_t *v) { kasan_check_write(v, sizeof(*v)); return arch_atomic64_inc_not_zero(v); } +#endif +#ifdef arch_atomic64_dec_if_positive +#define atomic64_dec_if_positive atomic64_dec_if_positive static __always_inline s64 atomic64_dec_if_positive(atomic64_t *v) { kasan_check_write(v, sizeof(*v)); return arch_atomic64_dec_if_positive(v); } +#endif +#ifdef arch_atomic_dec_and_test +#define atomic_dec_and_test atomic_dec_and_test static __always_inline bool atomic_dec_and_test(atomic_t *v) { kasan_check_write(v, sizeof(*v)); return arch_atomic_dec_and_test(v); } +#endif +#ifdef arch_atomic64_dec_and_test +#define atomic64_dec_and_test atomic64_dec_and_test static __always_inline bool atomic64_dec_and_test(atomic64_t *v) { kasan_check_write(v, sizeof(*v)); return arch_atomic64_dec_and_test(v); } +#endif +#ifdef arch_atomic_inc_and_test +#define atomic_inc_and_test atomic_inc_and_test static __always_inline bool atomic_inc_and_test(atomic_t *v) { kasan_check_write(v, sizeof(*v)); return arch_atomic_inc_and_test(v); } +#endif +#ifdef arch_atomic64_inc_and_test +#define atomic64_inc_and_test atomic64_inc_and_test static __always_inline bool atomic64_inc_and_test(atomic64_t *v) { kasan_check_write(v, sizeof(*v)); return arch_atomic64_inc_and_test(v); } +#endif static __always_inline int atomic_add_return(int i, atomic_t *v) { @@ -325,152 +372,96 @@ static __always_inline s64 atomic64_fetch_xor(s64 i, atomic64_t *v) return arch_atomic64_fetch_xor(i, v); } +#ifdef arch_atomic_sub_and_test +#define atomic_sub_and_test atomic_sub_and_test static __always_inline bool atomic_sub_and_test(int i, atomic_t *v) { kasan_check_write(v, sizeof(*v)); return arch_atomic_sub_and_test(i, v); } +#endif +#ifdef arch_atomic64_sub_and_test +#define atomic64_sub_and_test atomic64_sub_and_test static __always_inline bool atomic64_sub_and_test(s64 i, atomic64_t *v) { kasan_check_write(v, sizeof(*v)); return arch_atomic64_sub_and_test(i, v); } +#endif +#ifdef arch_atomic_add_negative +#define atomic_add_negative atomic_add_negative static __always_inline bool atomic_add_negative(int i, atomic_t *v) { kasan_check_write(v, sizeof(*v)); return arch_atomic_add_negative(i, v); } +#endif +#ifdef arch_atomic64_add_negative +#define atomic64_add_negative atomic64_add_negative static __always_inline bool atomic64_add_negative(s64 i, atomic64_t *v) { kasan_check_write(v, sizeof(*v)); return arch_atomic64_add_negative(i, v); } +#endif -static __always_inline unsigned long -cmpxchg_size(volatile void *ptr, unsigned long old, unsigned long new, int size) -{ - kasan_check_write(ptr, size); - switch (size) { - case 1: - return arch_cmpxchg((u8 *)ptr, (u8)old, (u8)new); - case 2: - return arch_cmpxchg((u16 *)ptr, (u16)old, (u16)new); - case 4: - return arch_cmpxchg((u32 *)ptr, (u32)old, (u32)new); - case 8: - BUILD_BUG_ON(sizeof(unsigned long) != 8); - return arch_cmpxchg((u64 *)ptr, (u64)old, (u64)new); - } - BUILD_BUG(); - return 0; -} +#define xchg(ptr, new) \ +({ \ + typeof(ptr) __ai_ptr = (ptr); \ + kasan_check_write(__ai_ptr, sizeof(*__ai_ptr)); \ + arch_xchg(__ai_ptr, (new)); \ +}) #define cmpxchg(ptr, old, new) \ ({ \ - ((__typeof__(*(ptr)))cmpxchg_size((ptr), (unsigned long)(old), \ - (unsigned long)(new), sizeof(*(ptr)))); \ + typeof(ptr) __ai_ptr = (ptr); \ + kasan_check_write(__ai_ptr, sizeof(*__ai_ptr)); \ + arch_cmpxchg(__ai_ptr, (old), (new)); \ }) -static __always_inline unsigned long -sync_cmpxchg_size(volatile void *ptr, unsigned long old, unsigned long new, - int size) -{ - kasan_check_write(ptr, size); - switch (size) { - case 1: - return arch_sync_cmpxchg((u8 *)ptr, (u8)old, (u8)new); - case 2: - return arch_sync_cmpxchg((u16 *)ptr, (u16)old, (u16)new); - case 4: - return arch_sync_cmpxchg((u32 *)ptr, (u32)old, (u32)new); - case 8: - BUILD_BUG_ON(sizeof(unsigned long) != 8); - return arch_sync_cmpxchg((u64 *)ptr, (u64)old, (u64)new); - } - BUILD_BUG(); - return 0; -} - #define sync_cmpxchg(ptr, old, new) \ ({ \ - ((__typeof__(*(ptr)))sync_cmpxchg_size((ptr), \ - (unsigned long)(old), (unsigned long)(new), \ - sizeof(*(ptr)))); \ + typeof(ptr) __ai_ptr = (ptr); \ + kasan_check_write(__ai_ptr, sizeof(*__ai_ptr)); \ + arch_sync_cmpxchg(__ai_ptr, (old), (new)); \ }) -static __always_inline unsigned long -cmpxchg_local_size(volatile void *ptr, unsigned long old, unsigned long new, - int size) -{ - kasan_check_write(ptr, size); - switch (size) { - case 1: - return arch_cmpxchg_local((u8 *)ptr, (u8)old, (u8)new); - case 2: - return arch_cmpxchg_local((u16 *)ptr, (u16)old, (u16)new); - case 4: - return arch_cmpxchg_local((u32 *)ptr, (u32)old, (u32)new); - case 8: - BUILD_BUG_ON(sizeof(unsigned long) != 8); - return arch_cmpxchg_local((u64 *)ptr, (u64)old, (u64)new); - } - BUILD_BUG(); - return 0; -} - #define cmpxchg_local(ptr, old, new) \ ({ \ - ((__typeof__(*(ptr)))cmpxchg_local_size((ptr), \ - (unsigned long)(old), (unsigned long)(new), \ - sizeof(*(ptr)))); \ + typeof(ptr) __ai_ptr = (ptr); \ + kasan_check_write(__ai_ptr, sizeof(*__ai_ptr)); \ + arch_cmpxchg_local(__ai_ptr, (old), (new)); \ }) -static __always_inline u64 -cmpxchg64_size(volatile u64 *ptr, u64 old, u64 new) -{ - kasan_check_write(ptr, sizeof(*ptr)); - return arch_cmpxchg64(ptr, old, new); -} - #define cmpxchg64(ptr, old, new) \ ({ \ - ((__typeof__(*(ptr)))cmpxchg64_size((ptr), (u64)(old), \ - (u64)(new))); \ + typeof(ptr) __ai_ptr = (ptr); \ + kasan_check_write(__ai_ptr, sizeof(*__ai_ptr)); \ + arch_cmpxchg64(__ai_ptr, (old), (new)); \ }) -static __always_inline u64 -cmpxchg64_local_size(volatile u64 *ptr, u64 old, u64 new) -{ - kasan_check_write(ptr, sizeof(*ptr)); - return arch_cmpxchg64_local(ptr, old, new); -} - #define cmpxchg64_local(ptr, old, new) \ ({ \ - ((__typeof__(*(ptr)))cmpxchg64_local_size((ptr), (u64)(old), \ - (u64)(new))); \ + typeof(ptr) __ai_ptr = (ptr); \ + kasan_check_write(__ai_ptr, sizeof(*__ai_ptr)); \ + arch_cmpxchg64_local(__ai_ptr, (old), (new)); \ }) -/* - * Originally we had the following code here: - * __typeof__(p1) ____p1 = (p1); - * kasan_check_write(____p1, 2 * sizeof(*____p1)); - * arch_cmpxchg_double(____p1, (p2), (o1), (o2), (n1), (n2)); - * But it leads to compilation failures (see gcc issue 72873). - * So for now it's left non-instrumented. - * There are few callers of cmpxchg_double(), so it's not critical. - */ #define cmpxchg_double(p1, p2, o1, o2, n1, n2) \ ({ \ - arch_cmpxchg_double((p1), (p2), (o1), (o2), (n1), (n2)); \ + typeof(p1) __ai_p1 = (p1); \ + kasan_check_write(__ai_p1, 2 * sizeof(*__ai_p1)); \ + arch_cmpxchg_double(__ai_p1, (p2), (o1), (o2), (n1), (n2)); \ }) -#define cmpxchg_double_local(p1, p2, o1, o2, n1, n2) \ -({ \ - arch_cmpxchg_double_local((p1), (p2), (o1), (o2), (n1), (n2)); \ +#define cmpxchg_double_local(p1, p2, o1, o2, n1, n2) \ +({ \ + typeof(p1) __ai_p1 = (p1); \ + kasan_check_write(__ai_p1, 2 * sizeof(*__ai_p1)); \ + arch_cmpxchg_double_local(__ai_p1, (p2), (o1), (o2), (n1), (n2)); \ }) #endif /* _LINUX_ATOMIC_INSTRUMENTED_H */ diff --git a/include/asm-generic/atomic.h b/include/asm-generic/atomic.h index abe6dd9ca2a8..13324aa828eb 100644 --- a/include/asm-generic/atomic.h +++ b/include/asm-generic/atomic.h @@ -186,11 +186,6 @@ ATOMIC_OP(xor, ^) #include <linux/irqflags.h> -static inline int atomic_add_negative(int i, atomic_t *v) -{ - return atomic_add_return(i, v) < 0; -} - static inline void atomic_add(int i, atomic_t *v) { atomic_add_return(i, v); @@ -201,35 +196,7 @@ static inline void atomic_sub(int i, atomic_t *v) atomic_sub_return(i, v); } -static inline void atomic_inc(atomic_t *v) -{ - atomic_add_return(1, v); -} - -static inline void atomic_dec(atomic_t *v) -{ - atomic_sub_return(1, v); -} - -#define atomic_dec_return(v) atomic_sub_return(1, (v)) -#define atomic_inc_return(v) atomic_add_return(1, (v)) - -#define atomic_sub_and_test(i, v) (atomic_sub_return((i), (v)) == 0) -#define atomic_dec_and_test(v) (atomic_dec_return(v) == 0) -#define atomic_inc_and_test(v) (atomic_inc_return(v) == 0) - #define atomic_xchg(ptr, v) (xchg(&(ptr)->counter, (v))) #define atomic_cmpxchg(v, old, new) (cmpxchg(&((v)->counter), (old), (new))) -#ifndef __atomic_add_unless -static inline int __atomic_add_unless(atomic_t *v, int a, int u) -{ - int c, old; - c = atomic_read(v); - while (c != u && (old = atomic_cmpxchg(v, c, c + a)) != c) - c = old; - return c; -} -#endif - #endif /* __ASM_GENERIC_ATOMIC_H */ diff --git a/include/asm-generic/atomic64.h b/include/asm-generic/atomic64.h index 8d28eb010d0d..97b28b7f1f29 100644 --- a/include/asm-generic/atomic64.h +++ b/include/asm-generic/atomic64.h @@ -11,6 +11,7 @@ */ #ifndef _ASM_GENERIC_ATOMIC64_H #define _ASM_GENERIC_ATOMIC64_H +#include <linux/types.h> typedef struct { long long counter; @@ -50,18 +51,10 @@ ATOMIC64_OPS(xor) #undef ATOMIC64_OP extern long long atomic64_dec_if_positive(atomic64_t *v); +#define atomic64_dec_if_positive atomic64_dec_if_positive extern long long atomic64_cmpxchg(atomic64_t *v, long long o, long long n); extern long long atomic64_xchg(atomic64_t *v, long long new); -extern int atomic64_add_unless(atomic64_t *v, long long a, long long u); - -#define atomic64_add_negative(a, v) (atomic64_add_return((a), (v)) < 0) -#define atomic64_inc(v) atomic64_add(1LL, (v)) -#define atomic64_inc_return(v) atomic64_add_return(1LL, (v)) -#define atomic64_inc_and_test(v) (atomic64_inc_return(v) == 0) -#define atomic64_sub_and_test(a, v) (atomic64_sub_return((a), (v)) == 0) -#define atomic64_dec(v) atomic64_sub(1LL, (v)) -#define atomic64_dec_return(v) atomic64_sub_return(1LL, (v)) -#define atomic64_dec_and_test(v) (atomic64_dec_return((v)) == 0) -#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1LL, 0LL) +extern long long atomic64_fetch_add_unless(atomic64_t *v, long long a, long long u); +#define atomic64_fetch_add_unless atomic64_fetch_add_unless #endif /* _ASM_GENERIC_ATOMIC64_H */ diff --git a/include/asm-generic/bitops/atomic.h b/include/asm-generic/bitops/atomic.h index 04deffaf5f7d..dd90c9792909 100644 --- a/include/asm-generic/bitops/atomic.h +++ b/include/asm-generic/bitops/atomic.h @@ -2,189 +2,67 @@ #ifndef _ASM_GENERIC_BITOPS_ATOMIC_H_ #define _ASM_GENERIC_BITOPS_ATOMIC_H_ -#include <asm/types.h> -#include <linux/irqflags.h> - -#ifdef CONFIG_SMP -#include <asm/spinlock.h> -#include <asm/cache.h> /* we use L1_CACHE_BYTES */ - -/* Use an array of spinlocks for our atomic_ts. - * Hash function to index into a different SPINLOCK. - * Since "a" is usually an address, use one spinlock per cacheline. - */ -# define ATOMIC_HASH_SIZE 4 -# define ATOMIC_HASH(a) (&(__atomic_hash[ (((unsigned long) a)/L1_CACHE_BYTES) & (ATOMIC_HASH_SIZE-1) ])) - -extern arch_spinlock_t __atomic_hash[ATOMIC_HASH_SIZE] __lock_aligned; - -/* Can't use raw_spin_lock_irq because of #include problems, so - * this is the substitute */ -#define _atomic_spin_lock_irqsave(l,f) do { \ - arch_spinlock_t *s = ATOMIC_HASH(l); \ - local_irq_save(f); \ - arch_spin_lock(s); \ -} while(0) - -#define _atomic_spin_unlock_irqrestore(l,f) do { \ - arch_spinlock_t *s = ATOMIC_HASH(l); \ - arch_spin_unlock(s); \ - local_irq_restore(f); \ -} while(0) - - -#else -# define _atomic_spin_lock_irqsave(l,f) do { local_irq_save(f); } while (0) -# define _atomic_spin_unlock_irqrestore(l,f) do { local_irq_restore(f); } while (0) -#endif +#include <linux/atomic.h> +#include <linux/compiler.h> +#include <asm/barrier.h> /* - * NMI events can occur at any time, including when interrupts have been - * disabled by *_irqsave(). So you can get NMI events occurring while a - * *_bit function is holding a spin lock. If the NMI handler also wants - * to do bit manipulation (and they do) then you can get a deadlock - * between the original caller of *_bit() and the NMI handler. - * - * by Keith Owens + * Implementation of atomic bitops using atomic-fetch ops. + * See Documentation/atomic_bitops.txt for details. */ -/** - * set_bit - Atomically set a bit in memory - * @nr: the bit to set - * @addr: the address to start counting from - * - * This function is atomic and may not be reordered. See __set_bit() - * if you do not require the atomic guarantees. - * - * Note: there are no guarantees that this function will not be reordered - * on non x86 architectures, so if you are writing portable code, - * make sure not to rely on its reordering guarantees. - * - * Note that @nr may be almost arbitrarily large; this function is not - * restricted to acting on a single-word quantity. - */ -static inline void set_bit(int nr, volatile unsigned long *addr) +static inline void set_bit(unsigned int nr, volatile unsigned long *p) { - unsigned long mask = BIT_MASK(nr); - unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); - unsigned long flags; - - _atomic_spin_lock_irqsave(p, flags); - *p |= mask; - _atomic_spin_unlock_irqrestore(p, flags); + p += BIT_WORD(nr); + atomic_long_or(BIT_MASK(nr), (atomic_long_t *)p); } -/** - * clear_bit - Clears a bit in memory - * @nr: Bit to clear - * @addr: Address to start counting from - * - * clear_bit() is atomic and may not be reordered. However, it does - * not contain a memory barrier, so if it is used for locking purposes, - * you should call smp_mb__before_atomic() and/or smp_mb__after_atomic() - * in order to ensure changes are visible on other processors. - */ -static inline void clear_bit(int nr, volatile unsigned long *addr) +static inline void clear_bit(unsigned int nr, volatile unsigned long *p) { - unsigned long mask = BIT_MASK(nr); - unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); - unsigned long flags; - - _atomic_spin_lock_irqsave(p, flags); - *p &= ~mask; - _atomic_spin_unlock_irqrestore(p, flags); + p += BIT_WORD(nr); + atomic_long_andnot(BIT_MASK(nr), (atomic_long_t *)p); } -/** - * change_bit - Toggle a bit in memory - * @nr: Bit to change - * @addr: Address to start counting from - * - * change_bit() is atomic and may not be reordered. It may be - * reordered on other architectures than x86. - * Note that @nr may be almost arbitrarily large; this function is not - * restricted to acting on a single-word quantity. - */ -static inline void change_bit(int nr, volatile unsigned long *addr) +static inline void change_bit(unsigned int nr, volatile unsigned long *p) { - unsigned long mask = BIT_MASK(nr); - unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); - unsigned long flags; - - _atomic_spin_lock_irqsave(p, flags); - *p ^= mask; - _atomic_spin_unlock_irqrestore(p, flags); + p += BIT_WORD(nr); + atomic_long_xor(BIT_MASK(nr), (atomic_long_t *)p); } -/** - * test_and_set_bit - Set a bit and return its old value - * @nr: Bit to set - * @addr: Address to count from - * - * This operation is atomic and cannot be reordered. - * It may be reordered on other architectures than x86. - * It also implies a memory barrier. - */ -static inline int test_and_set_bit(int nr, volatile unsigned long *addr) +static inline int test_and_set_bit(unsigned int nr, volatile unsigned long *p) { + long old; unsigned long mask = BIT_MASK(nr); - unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); - unsigned long old; - unsigned long flags; - _atomic_spin_lock_irqsave(p, flags); - old = *p; - *p = old | mask; - _atomic_spin_unlock_irqrestore(p, flags); + p += BIT_WORD(nr); + if (READ_ONCE(*p) & mask) + return 1; - return (old & mask) != 0; + old = atomic_long_fetch_or(mask, (atomic_long_t *)p); + return !!(old & mask); } -/** - * test_and_clear_bit - Clear a bit and return its old value - * @nr: Bit to clear - * @addr: Address to count from - * - * This operation is atomic and cannot be reordered. - * It can be reorderdered on other architectures other than x86. - * It also implies a memory barrier. - */ -static inline int test_and_clear_bit(int nr, volatile unsigned long *addr) +static inline int test_and_clear_bit(unsigned int nr, volatile unsigned long *p) { + long old; unsigned long mask = BIT_MASK(nr); - unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); - unsigned long old; - unsigned long flags; - _atomic_spin_lock_irqsave(p, flags); - old = *p; - *p = old & ~mask; - _atomic_spin_unlock_irqrestore(p, flags); + p += BIT_WORD(nr); + if (!(READ_ONCE(*p) & mask)) + return 0; - return (old & mask) != 0; + old = atomic_long_fetch_andnot(mask, (atomic_long_t *)p); + return !!(old & mask); } -/** - * test_and_change_bit - Change a bit and return its old value - * @nr: Bit to change - * @addr: Address to count from - * - * This operation is atomic and cannot be reordered. - * It also implies a memory barrier. - */ -static inline int test_and_change_bit(int nr, volatile unsigned long *addr) +static inline int test_and_change_bit(unsigned int nr, volatile unsigned long *p) { + long old; unsigned long mask = BIT_MASK(nr); - unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); - unsigned long old; - unsigned long flags; - - _atomic_spin_lock_irqsave(p, flags); - old = *p; - *p = old ^ mask; - _atomic_spin_unlock_irqrestore(p, flags); - return (old & mask) != 0; + p += BIT_WORD(nr); + old = atomic_long_fetch_xor(mask, (atomic_long_t *)p); + return !!(old & mask); } #endif /* _ASM_GENERIC_BITOPS_ATOMIC_H */ diff --git a/include/asm-generic/bitops/lock.h b/include/asm-generic/bitops/lock.h index 67ab280ad134..3ae021368f48 100644 --- a/include/asm-generic/bitops/lock.h +++ b/include/asm-generic/bitops/lock.h @@ -2,6 +2,10 @@ #ifndef _ASM_GENERIC_BITOPS_LOCK_H_ #define _ASM_GENERIC_BITOPS_LOCK_H_ +#include <linux/atomic.h> +#include <linux/compiler.h> +#include <asm/barrier.h> + /** * test_and_set_bit_lock - Set a bit and return its old value, for lock * @nr: Bit to set @@ -11,7 +15,20 @@ * the returned value is 0. * It can be used to implement bit locks. */ -#define test_and_set_bit_lock(nr, addr) test_and_set_bit(nr, addr) +static inline int test_and_set_bit_lock(unsigned int nr, + volatile unsigned long *p) +{ + long old; + unsigned long mask = BIT_MASK(nr); + + p += BIT_WORD(nr); + if (READ_ONCE(*p) & mask) + return 1; + + old = atomic_long_fetch_or_acquire(mask, (atomic_long_t *)p); + return !!(old & mask); +} + /** * clear_bit_unlock - Clear a bit in memory, for unlock @@ -20,11 +37,11 @@ * * This operation is atomic and provides release barrier semantics. */ -#define clear_bit_unlock(nr, addr) \ -do { \ - smp_mb__before_atomic(); \ - clear_bit(nr, addr); \ -} while (0) +static inline void clear_bit_unlock(unsigned int nr, volatile unsigned long *p) +{ + p += BIT_WORD(nr); + atomic_long_fetch_andnot_release(BIT_MASK(nr), (atomic_long_t *)p); +} /** * __clear_bit_unlock - Clear a bit in memory, for unlock @@ -37,11 +54,38 @@ do { \ * * See for example x86's implementation. */ -#define __clear_bit_unlock(nr, addr) \ -do { \ - smp_mb__before_atomic(); \ - clear_bit(nr, addr); \ -} while (0) +static inline void __clear_bit_unlock(unsigned int nr, + volatile unsigned long *p) +{ + unsigned long old; -#endif /* _ASM_GENERIC_BITOPS_LOCK_H_ */ + p += BIT_WORD(nr); + old = READ_ONCE(*p); + old &= ~BIT_MASK(nr); + atomic_long_set_release((atomic_long_t *)p, old); +} + +/** + * clear_bit_unlock_is_negative_byte - Clear a bit in memory and test if bottom + * byte is negative, for unlock. + * @nr: the bit to clear + * @addr: the address to start counting from + * + * This is a bit of a one-trick-pony for the filemap code, which clears + * PG_locked and tests PG_waiters, + */ +#ifndef clear_bit_unlock_is_negative_byte +static inline bool clear_bit_unlock_is_negative_byte(unsigned int nr, + volatile unsigned long *p) +{ + long old; + unsigned long mask = BIT_MASK(nr); + + p += BIT_WORD(nr); + old = atomic_long_fetch_andnot_release(mask, (atomic_long_t *)p); + return !!(old & BIT(7)); +} +#define clear_bit_unlock_is_negative_byte clear_bit_unlock_is_negative_byte +#endif +#endif /* _ASM_GENERIC_BITOPS_LOCK_H_ */ diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h index f59639afaa39..b081794ba135 100644 --- a/include/asm-generic/pgtable.h +++ b/include/asm-generic/pgtable.h @@ -1019,8 +1019,8 @@ int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot); int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot); int pud_clear_huge(pud_t *pud); int pmd_clear_huge(pmd_t *pmd); -int pud_free_pmd_page(pud_t *pud); -int pmd_free_pte_page(pmd_t *pmd); +int pud_free_pmd_page(pud_t *pud, unsigned long addr); +int pmd_free_pte_page(pmd_t *pmd, unsigned long addr); #else /* !CONFIG_HAVE_ARCH_HUGE_VMAP */ static inline int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot) { @@ -1046,11 +1046,11 @@ static inline int pmd_clear_huge(pmd_t *pmd) { return 0; } -static inline int pud_free_pmd_page(pud_t *pud) +static inline int pud_free_pmd_page(pud_t *pud, unsigned long addr) { return 0; } -static inline int pmd_free_pte_page(pmd_t *pmd) +static inline int pmd_free_pte_page(pmd_t *pmd, unsigned long addr) { return 0; } diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h index 3063125197ad..e811ef7b8350 100644 --- a/include/asm-generic/tlb.h +++ b/include/asm-generic/tlb.h @@ -303,4 +303,14 @@ static inline void tlb_remove_check_page_size_change(struct mmu_gather *tlb, #define tlb_migrate_finish(mm) do {} while (0) +/* + * Used to flush the TLB when page tables are removed, when lazy + * TLB mode may cause a CPU to retain intermediate translations + * pointing to about-to-be-freed page table memory. + */ +#ifndef HAVE_TLB_FLUSH_REMOVE_TABLES +#define tlb_flush_remove_tables(mm) do {} while (0) +#define tlb_flush_remove_tables_local(mm) do {} while (0) +#endif + #endif /* _ASM_GENERIC__TLB_H */ diff --git a/include/linux/atomic.h b/include/linux/atomic.h index 01ce3997cb42..1e8e88bdaf09 100644 --- a/include/linux/atomic.h +++ b/include/linux/atomic.h @@ -2,6 +2,8 @@ /* Atomic operations usable in machine independent code */ #ifndef _LINUX_ATOMIC_H #define _LINUX_ATOMIC_H +#include <linux/types.h> + #include <asm/atomic.h> #include <asm/barrier.h> @@ -36,40 +38,46 @@ * barriers on top of the relaxed variant. In the case where the relaxed * variant is already fully ordered, no additional barriers are needed. * - * Besides, if an arch has a special barrier for acquire/release, it could - * implement its own __atomic_op_* and use the same framework for building - * variants - * - * If an architecture overrides __atomic_op_acquire() it will probably want - * to define smp_mb__after_spinlock(). + * If an architecture overrides __atomic_acquire_fence() it will probably + * want to define smp_mb__after_spinlock(). */ -#ifndef __atomic_op_acquire +#ifndef __atomic_acquire_fence +#define __atomic_acquire_fence smp_mb__after_atomic +#endif + +#ifndef __atomic_release_fence +#define __atomic_release_fence smp_mb__before_atomic +#endif + +#ifndef __atomic_pre_full_fence +#define __atomic_pre_full_fence smp_mb__before_atomic +#endif + +#ifndef __atomic_post_full_fence +#define __atomic_post_full_fence smp_mb__after_atomic +#endif + #define __atomic_op_acquire(op, args...) \ ({ \ typeof(op##_relaxed(args)) __ret = op##_relaxed(args); \ - smp_mb__after_atomic(); \ + __atomic_acquire_fence(); \ __ret; \ }) -#endif -#ifndef __atomic_op_release #define __atomic_op_release(op, args...) \ ({ \ - smp_mb__before_atomic(); \ + __atomic_release_fence(); \ op##_relaxed(args); \ }) -#endif -#ifndef __atomic_op_fence #define __atomic_op_fence(op, args...) \ ({ \ typeof(op##_relaxed(args)) __ret; \ - smp_mb__before_atomic(); \ + __atomic_pre_full_fence(); \ __ret = op##_relaxed(args); \ - smp_mb__after_atomic(); \ + __atomic_post_full_fence(); \ __ret; \ }) -#endif /* atomic_add_return_relaxed */ #ifndef atomic_add_return_relaxed @@ -95,11 +103,23 @@ #endif #endif /* atomic_add_return_relaxed */ +#ifndef atomic_inc +#define atomic_inc(v) atomic_add(1, (v)) +#endif + /* atomic_inc_return_relaxed */ #ifndef atomic_inc_return_relaxed + +#ifndef atomic_inc_return +#define atomic_inc_return(v) atomic_add_return(1, (v)) +#define atomic_inc_return_relaxed(v) atomic_add_return_relaxed(1, (v)) +#define atomic_inc_return_acquire(v) atomic_add_return_acquire(1, (v)) +#define atomic_inc_return_release(v) atomic_add_return_release(1, (v)) +#else /* atomic_inc_return */ #define atomic_inc_return_relaxed atomic_inc_return #define atomic_inc_return_acquire atomic_inc_return #define atomic_inc_return_release atomic_inc_return +#endif /* atomic_inc_return */ #else /* atomic_inc_return_relaxed */ @@ -143,11 +163,23 @@ #endif #endif /* atomic_sub_return_relaxed */ +#ifndef atomic_dec +#define atomic_dec(v) atomic_sub(1, (v)) +#endif + /* atomic_dec_return_relaxed */ #ifndef atomic_dec_return_relaxed + +#ifndef atomic_dec_return +#define atomic_dec_return(v) atomic_sub_return(1, (v)) +#define atomic_dec_return_relaxed(v) atomic_sub_return_relaxed(1, (v)) +#define atomic_dec_return_acquire(v) atomic_sub_return_acquire(1, (v)) +#define atomic_dec_return_release(v) atomic_sub_return_release(1, (v)) +#else /* atomic_dec_return */ #define atomic_dec_return_relaxed atomic_dec_return #define atomic_dec_return_acquire atomic_dec_return #define atomic_dec_return_release atomic_dec_return +#endif /* atomic_dec_return */ #else /* atomic_dec_return_relaxed */ @@ -328,12 +360,22 @@ #endif #endif /* atomic_fetch_and_relaxed */ -#ifdef atomic_andnot -/* atomic_fetch_andnot_relaxed */ +#ifndef atomic_andnot +#define atomic_andnot(i, v) atomic_and(~(int)(i), (v)) +#endif + #ifndef atomic_fetch_andnot_relaxed -#define atomic_fetch_andnot_relaxed atomic_fetch_andnot -#define atomic_fetch_andnot_acquire atomic_fetch_andnot -#define atomic_fetch_andnot_release atomic_fetch_andnot + +#ifndef atomic_fetch_andnot +#define atomic_fetch_andnot(i, v) atomic_fetch_and(~(int)(i), (v)) +#define atomic_fetch_andnot_relaxed(i, v) atomic_fetch_and_relaxed(~(int)(i), (v)) +#define atomic_fetch_andnot_acquire(i, v) atomic_fetch_and_acquire(~(int)(i), (v)) +#define atomic_fetch_andnot_release(i, v) atomic_fetch_and_release(~(int)(i), (v)) +#else /* atomic_fetch_andnot */ +#define atomic_fetch_andnot_relaxed atomic_fetch_andnot +#define atomic_fetch_andnot_acquire atomic_fetch_andnot +#define atomic_fetch_andnot_release atomic_fetch_andnot +#endif /* atomic_fetch_andnot */ #else /* atomic_fetch_andnot_relaxed */ @@ -352,7 +394,6 @@ __atomic_op_fence(atomic_fetch_andnot, __VA_ARGS__) #endif #endif /* atomic_fetch_andnot_relaxed */ -#endif /* atomic_andnot */ /* atomic_fetch_xor_relaxed */ #ifndef atomic_fetch_xor_relaxed @@ -520,112 +561,140 @@ #endif /* xchg_relaxed */ /** + * atomic_fetch_add_unless - add unless the number is already a given value + * @v: pointer of type atomic_t + * @a: the amount to add to v... + * @u: ...unless v is equal to u. + * + * Atomically adds @a to @v, if @v was not already @u. + * Returns the original value of @v. + */ +#ifndef atomic_fetch_add_unless +static inline int atomic_fetch_add_unless(atomic_t *v, int a, int u) +{ + int c = atomic_read(v); + + do { + if (unlikely(c == u)) + break; + } while (!atomic_try_cmpxchg(v, &c, c + a)); + + return c; +} +#endif + +/** * atomic_add_unless - add unless the number is already a given value * @v: pointer of type atomic_t * @a: the amount to add to v... * @u: ...unless v is equal to u. * - * Atomically adds @a to @v, so long as @v was not already @u. - * Returns non-zero if @v was not @u, and zero otherwise. + * Atomically adds @a to @v, if @v was not already @u. + * Returns true if the addition was done. */ -static inline int atomic_add_unless(atomic_t *v, int a, int u) +static inline bool atomic_add_unless(atomic_t *v, int a, int u) { - return __atomic_add_unless(v, a, u) != u; + return atomic_fetch_add_unless(v, a, u) != u; } /** * atomic_inc_not_zero - increment unless the number is zero * @v: pointer of type atomic_t * - * Atomically increments @v by 1, so long as @v is non-zero. - * Returns non-zero if @v was non-zero, and zero otherwise. + * Atomically increments @v by 1, if @v is non-zero. + * Returns true if the increment was done. */ #ifndef atomic_inc_not_zero #define atomic_inc_not_zero(v) atomic_add_unless((v), 1, 0) #endif -#ifndef atomic_andnot -static inline void atomic_andnot(int i, atomic_t *v) -{ - atomic_and(~i, v); -} - -static inline int atomic_fetch_andnot(int i, atomic_t *v) -{ - return atomic_fetch_and(~i, v); -} - -static inline int atomic_fetch_andnot_relaxed(int i, atomic_t *v) +/** + * atomic_inc_and_test - increment and test + * @v: pointer of type atomic_t + * + * Atomically increments @v by 1 + * and returns true if the result is zero, or false for all + * other cases. + */ +#ifndef atomic_inc_and_test +static inline bool atomic_inc_and_test(atomic_t *v) { - return atomic_fetch_and_relaxed(~i, v); + return atomic_inc_return(v) == 0; } +#endif -static inline int atomic_fetch_andnot_acquire(int i, atomic_t *v) +/** + * atomic_dec_and_test - decrement and test + * @v: pointer of type atomic_t + * + * Atomically decrements @v by 1 and + * returns true if the result is 0, or false for all other + * cases. + */ +#ifndef atomic_dec_and_test +static inline bool atomic_dec_and_test(atomic_t *v) { - return atomic_fetch_and_acquire(~i, v); + return atomic_dec_return(v) == 0; } +#endif -static inline int atomic_fetch_andnot_release(int i, atomic_t *v) +/** + * atomic_sub_and_test - subtract value from variable and test result + * @i: integer value to subtract + * @v: pointer of type atomic_t + * + * Atomically subtracts @i from @v and returns + * true if the result is zero, or false for all + * other cases. + */ +#ifndef atomic_sub_and_test +static inline bool atomic_sub_and_test(int i, atomic_t *v) { - return atomic_fetch_and_release(~i, v); + return atomic_sub_return(i, v) == 0; } #endif /** - * atomic_inc_not_zero_hint - increment if not null + * atomic_add_negative - add and test if negative + * @i: integer value to add * @v: pointer of type atomic_t - * @hint: probable value of the atomic before the increment - * - * This version of atomic_inc_not_zero() gives a hint of probable - * value of the atomic. This helps processor to not read the memory - * before doing the atomic read/modify/write cycle, lowering - * number of bus transactions on some arches. * - * Returns: 0 if increment was not done, 1 otherwise. + * Atomically adds @i to @v and returns true + * if the result is negative, or false when + * result is greater than or equal to zero. */ -#ifndef atomic_inc_not_zero_hint -static inline int atomic_inc_not_zero_hint(atomic_t *v, int hint) +#ifndef atomic_add_negative +static inline bool atomic_add_negative(int i, atomic_t *v) { - int val, c = hint; - - /* sanity test, should be removed by compiler if hint is a constant */ - if (!hint) - return atomic_inc_not_zero(v); - - do { - val = atomic_cmpxchg(v, c, c + 1); - if (val == c) - return 1; - c = val; - } while (c); - - return 0; + return atomic_add_return(i, v) < 0; } #endif #ifndef atomic_inc_unless_negative -static inline int atomic_inc_unless_negative(atomic_t *p) +static inline bool atomic_inc_unless_negative(atomic_t *v) { - int v, v1; - for (v = 0; v >= 0; v = v1) { - v1 = atomic_cmpxchg(p, v, v + 1); - if (likely(v1 == v)) - return 1; - } - return 0; + int c = atomic_read(v); + + do { + if (unlikely(c < 0)) + return false; + } while (!atomic_try_cmpxchg(v, &c, c + 1)); + + return true; } #endif #ifndef atomic_dec_unless_positive -static inline int atomic_dec_unless_positive(atomic_t *p) +static inline bool atomic_dec_unless_positive(atomic_t *v) { - int v, v1; - for (v = 0; v <= 0; v = v1) { - v1 = atomic_cmpxchg(p, v, v - 1); - if (likely(v1 == v)) - return 1; - } - return 0; + int c = atomic_read(v); + + do { + if (unlikely(c > 0)) + return false; + } while (!atomic_try_cmpxchg(v, &c, c - 1)); + + return true; } #endif @@ -639,17 +708,14 @@ static inline int atomic_dec_unless_positive(atomic_t *p) #ifndef atomic_dec_if_positive static inline int atomic_dec_if_positive(atomic_t *v) { - int c, old, dec; - c = atomic_read(v); - for (;;) { + int dec, c = atomic_read(v); + + do { dec = c - 1; if (unlikely(dec < 0)) break; - old = atomic_cmpxchg((v), c, dec); - if (likely(old == c)) - break; - c = old; - } + } while (!atomic_try_cmpxchg(v, &c, dec)); + return dec; } #endif @@ -693,11 +759,23 @@ static inline int atomic_dec_if_positive(atomic_t *v) #endif #endif /* atomic64_add_return_relaxed */ +#ifndef atomic64_inc +#define atomic64_inc(v) atomic64_add(1, (v)) +#endif + /* atomic64_inc_return_relaxed */ #ifndef atomic64_inc_return_relaxed + +#ifndef atomic64_inc_return +#define atomic64_inc_return(v) atomic64_add_return(1, (v)) +#define atomic64_inc_return_relaxed(v) atomic64_add_return_relaxed(1, (v)) +#define atomic64_inc_return_acquire(v) atomic64_add_return_acquire(1, (v)) +#define atomic64_inc_return_release(v) atomic64_add_return_release(1, (v)) +#else /* atomic64_inc_return */ #define atomic64_inc_return_relaxed atomic64_inc_return #define atomic64_inc_return_acquire atomic64_inc_return #define atomic64_inc_return_release atomic64_inc_return +#endif /* atomic64_inc_return */ #else /* atomic64_inc_return_relaxed */ @@ -742,11 +820,23 @@ static inline int atomic_dec_if_positive(atomic_t *v) #endif #endif /* atomic64_sub_return_relaxed */ +#ifndef atomic64_dec +#define atomic64_dec(v) atomic64_sub(1, (v)) +#endif + /* atomic64_dec_return_relaxed */ #ifndef atomic64_dec_return_relaxed + +#ifndef atomic64_dec_return +#define atomic64_dec_return(v) atomic64_sub_return(1, (v)) +#define atomic64_dec_return_relaxed(v) atomic64_sub_return_relaxed(1, (v)) +#define atomic64_dec_return_acquire(v) atomic64_sub_return_acquire(1, (v)) +#define atomic64_dec_return_release(v) atomic64_sub_return_release(1, (v)) +#else /* atomic64_dec_return */ #define atomic64_dec_return_relaxed atomic64_dec_return #define atomic64_dec_return_acquire atomic64_dec_return #define atomic64_dec_return_release atomic64_dec_return +#endif /* atomic64_dec_return */ #else /* atomic64_dec_return_relaxed */ @@ -927,12 +1017,22 @@ static inline int atomic_dec_if_positive(atomic_t *v) #endif #endif /* atomic64_fetch_and_relaxed */ -#ifdef atomic64_andnot -/* atomic64_fetch_andnot_relaxed */ +#ifndef atomic64_andnot +#define atomic64_andnot(i, v) atomic64_and(~(long long)(i), (v)) +#endif + #ifndef atomic64_fetch_andnot_relaxed -#define atomic64_fetch_andnot_relaxed atomic64_fetch_andnot -#define atomic64_fetch_andnot_acquire atomic64_fetch_andnot -#define atomic64_fetch_andnot_release atomic64_fetch_andnot + +#ifndef atomic64_fetch_andnot +#define atomic64_fetch_andnot(i, v) atomic64_fetch_and(~(long long)(i), (v)) +#define atomic64_fetch_andnot_relaxed(i, v) atomic64_fetch_and_relaxed(~(long long)(i), (v)) +#define atomic64_fetch_andnot_acquire(i, v) atomic64_fetch_and_acquire(~(long long)(i), (v)) +#define atomic64_fetch_andnot_release(i, v) atomic64_fetch_and_release(~(long long)(i), (v)) +#else /* atomic64_fetch_andnot */ +#define atomic64_fetch_andnot_relaxed atomic64_fetch_andnot +#define atomic64_fetch_andnot_acquire atomic64_fetch_andnot +#define atomic64_fetch_andnot_release atomic64_fetch_andnot +#endif /* atomic64_fetch_andnot */ #else /* atomic64_fetch_andnot_relaxed */ @@ -951,7 +1051,6 @@ static inline int atomic_dec_if_positive(atomic_t *v) __atomic_op_fence(atomic64_fetch_andnot, __VA_ARGS__) #endif #endif /* atomic64_fetch_andnot_relaxed */ -#endif /* atomic64_andnot */ /* atomic64_fetch_xor_relaxed */ #ifndef atomic64_fetch_xor_relaxed @@ -1049,30 +1148,164 @@ static inline int atomic_dec_if_positive(atomic_t *v) #define atomic64_try_cmpxchg_release atomic64_try_cmpxchg #endif /* atomic64_try_cmpxchg */ -#ifndef atomic64_andnot -static inline void atomic64_andnot(long long i, atomic64_t *v) +/** + * atomic64_fetch_add_unless - add unless the number is already a given value + * @v: pointer of type atomic64_t + * @a: the amount to add to v... + * @u: ...unless v is equal to u. + * + * Atomically adds @a to @v, if @v was not already @u. + * Returns the original value of @v. + */ +#ifndef atomic64_fetch_add_unless +static inline long long atomic64_fetch_add_unless(atomic64_t *v, long long a, + long long u) { - atomic64_and(~i, v); + long long c = atomic64_read(v); + + do { + if (unlikely(c == u)) + break; + } while (!atomic64_try_cmpxchg(v, &c, c + a)); + + return c; } +#endif -static inline long long atomic64_fetch_andnot(long long i, atomic64_t *v) +/** + * atomic64_add_unless - add unless the number is already a given value + * @v: pointer of type atomic_t + * @a: the amount to add to v... + * @u: ...unless v is equal to u. + * + * Atomically adds @a to @v, if @v was not already @u. + * Returns true if the addition was done. + */ +static inline bool atomic64_add_unless(atomic64_t *v, long long a, long long u) { - return atomic64_fetch_and(~i, v); + return atomic64_fetch_add_unless(v, a, u) != u; } -static inline long long atomic64_fetch_andnot_relaxed(long long i, atomic64_t *v) +/** + * atomic64_inc_not_zero - increment unless the number is zero + * @v: pointer of type atomic64_t + * + * Atomically increments @v by 1, if @v is non-zero. + * Returns true if the increment was done. + */ +#ifndef atomic64_inc_not_zero +#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0) +#endif + +/** + * atomic64_inc_and_test - increment and test + * @v: pointer of type atomic64_t + * + * Atomically increments @v by 1 + * and returns true if the result is zero, or false for all + * other cases. + */ +#ifndef atomic64_inc_and_test +static inline bool atomic64_inc_and_test(atomic64_t *v) { - return atomic64_fetch_and_relaxed(~i, v); + return atomic64_inc_return(v) == 0; } +#endif -static inline long long atomic64_fetch_andnot_acquire(long long i, atomic64_t *v) +/** + * atomic64_dec_and_test - decrement and test + * @v: pointer of type atomic64_t + * + * Atomically decrements @v by 1 and + * returns true if the result is 0, or false for all other + * cases. + */ +#ifndef atomic64_dec_and_test +static inline bool atomic64_dec_and_test(atomic64_t *v) { - return atomic64_fetch_and_acquire(~i, v); + return atomic64_dec_return(v) == 0; } +#endif -static inline long long atomic64_fetch_andnot_release(long long i, atomic64_t *v) +/** + * atomic64_sub_and_test - subtract value from variable and test result + * @i: integer value to subtract + * @v: pointer of type atomic64_t + * + * Atomically subtracts @i from @v and returns + * true if the result is zero, or false for all + * other cases. + */ +#ifndef atomic64_sub_and_test +static inline bool atomic64_sub_and_test(long long i, atomic64_t *v) +{ + return atomic64_sub_return(i, v) == 0; +} +#endif + +/** + * atomic64_add_negative - add and test if negative + * @i: integer value to add + * @v: pointer of type atomic64_t + * + * Atomically adds @i to @v and returns true + * if the result is negative, or false when + * result is greater than or equal to zero. + */ +#ifndef atomic64_add_negative +static inline bool atomic64_add_negative(long long i, atomic64_t *v) { - return atomic64_fetch_and_release(~i, v); + return atomic64_add_return(i, v) < 0; +} +#endif + +#ifndef atomic64_inc_unless_negative +static inline bool atomic64_inc_unless_negative(atomic64_t *v) +{ + long long c = atomic64_read(v); + + do { + if (unlikely(c < 0)) + return false; + } while (!atomic64_try_cmpxchg(v, &c, c + 1)); + + return true; +} +#endif + +#ifndef atomic64_dec_unless_positive +static inline bool atomic64_dec_unless_positive(atomic64_t *v) +{ + long long c = atomic64_read(v); + + do { + if (unlikely(c > 0)) + return false; + } while (!atomic64_try_cmpxchg(v, &c, c - 1)); + + return true; +} +#endif + +/* + * atomic64_dec_if_positive - decrement by 1 if old value positive + * @v: pointer of type atomic64_t + * + * The function returns the old value of *v minus 1, even if + * the atomic64 variable, v, was not decremented. + */ +#ifndef atomic64_dec_if_positive +static inline long long atomic64_dec_if_positive(atomic64_t *v) +{ + long long dec, c = atomic64_read(v); + + do { + dec = c - 1; + if (unlikely(dec < 0)) + break; + } while (!atomic64_try_cmpxchg(v, &c, dec)); + + return dec; } #endif diff --git a/include/linux/bitops.h b/include/linux/bitops.h index 4cac4e1a72ff..af419012d77d 100644 --- a/include/linux/bitops.h +++ b/include/linux/bitops.h @@ -2,29 +2,9 @@ #ifndef _LINUX_BITOPS_H #define _LINUX_BITOPS_H #include <asm/types.h> +#include <linux/bits.h> -#ifdef __KERNEL__ -#define BIT(nr) (1UL << (nr)) -#define BIT_ULL(nr) (1ULL << (nr)) -#define BIT_MASK(nr) (1UL << ((nr) % BITS_PER_LONG)) -#define BIT_WORD(nr) ((nr) / BITS_PER_LONG) -#define BIT_ULL_MASK(nr) (1ULL << ((nr) % BITS_PER_LONG_LONG)) -#define BIT_ULL_WORD(nr) ((nr) / BITS_PER_LONG_LONG) -#define BITS_PER_BYTE 8 #define BITS_TO_LONGS(nr) DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(long)) -#endif - -/* - * Create a contiguous bitmask starting at bit position @l and ending at - * position @h. For example - * GENMASK_ULL(39, 21) gives us the 64bit vector 0x000000ffffe00000. - */ -#define GENMASK(h, l) \ - (((~0UL) - (1UL << (l)) + 1) & (~0UL >> (BITS_PER_LONG - 1 - (h)))) - -#define GENMASK_ULL(h, l) \ - (((~0ULL) - (1ULL << (l)) + 1) & \ - (~0ULL >> (BITS_PER_LONG_LONG - 1 - (h)))) extern unsigned int __sw_hweight8(unsigned int w); extern unsigned int __sw_hweight16(unsigned int w); diff --git a/include/linux/bits.h b/include/linux/bits.h new file mode 100644 index 000000000000..2b7b532c1d51 --- /dev/null +++ b/include/linux/bits.h @@ -0,0 +1,26 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LINUX_BITS_H +#define __LINUX_BITS_H +#include <asm/bitsperlong.h> + +#define BIT(nr) (1UL << (nr)) +#define BIT_ULL(nr) (1ULL << (nr)) +#define BIT_MASK(nr) (1UL << ((nr) % BITS_PER_LONG)) +#define BIT_WORD(nr) ((nr) / BITS_PER_LONG) +#define BIT_ULL_MASK(nr) (1ULL << ((nr) % BITS_PER_LONG_LONG)) +#define BIT_ULL_WORD(nr) ((nr) / BITS_PER_LONG_LONG) +#define BITS_PER_BYTE 8 + +/* + * Create a contiguous bitmask starting at bit position @l and ending at + * position @h. For example + * GENMASK_ULL(39, 21) gives us the 64bit vector 0x000000ffffe00000. + */ +#define GENMASK(h, l) \ + (((~0UL) - (1UL << (l)) + 1) & (~0UL >> (BITS_PER_LONG - 1 - (h)))) + +#define GENMASK_ULL(h, l) \ + (((~0ULL) - (1ULL << (l)) + 1) & \ + (~0ULL >> (BITS_PER_LONG_LONG - 1 - (h)))) + +#endif /* __LINUX_BITS_H */ diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h index 7dff1963c185..308918928767 100644 --- a/include/linux/clocksource.h +++ b/include/linux/clocksource.h @@ -194,6 +194,9 @@ extern void clocksource_suspend(void); extern void clocksource_resume(void); extern struct clocksource * __init clocksource_default_clock(void); extern void clocksource_mark_unstable(struct clocksource *cs); +extern void +clocksource_start_suspend_timing(struct clocksource *cs, u64 start_cycles); +extern u64 clocksource_stop_suspend_timing(struct clocksource *cs, u64 now); extern u64 clocks_calc_max_nsecs(u32 mult, u32 shift, u32 maxadj, u64 mask, u64 *max_cycles); diff --git a/include/linux/compat.h b/include/linux/compat.h index c68acc47da57..df45ee8413d6 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -115,11 +115,6 @@ typedef compat_ulong_t compat_aio_context_t; struct compat_sel_arg_struct; struct rusage; -struct compat_itimerspec { - struct compat_timespec it_interval; - struct compat_timespec it_value; -}; - struct compat_utimbuf { compat_time_t actime; compat_time_t modtime; @@ -300,10 +295,6 @@ extern int compat_get_timespec(struct timespec *, const void __user *); extern int compat_put_timespec(const struct timespec *, void __user *); extern int compat_get_timeval(struct timeval *, const void __user *); extern int compat_put_timeval(const struct timeval *, void __user *); -extern int get_compat_itimerspec64(struct itimerspec64 *its, - const struct compat_itimerspec __user *uits); -extern int put_compat_itimerspec64(const struct itimerspec64 *its, - struct compat_itimerspec __user *uits); struct compat_iovec { compat_uptr_t iov_base; diff --git a/include/linux/compat_time.h b/include/linux/compat_time.h index 31f2774f1994..e70bfd1d2c3f 100644 --- a/include/linux/compat_time.h +++ b/include/linux/compat_time.h @@ -17,7 +17,16 @@ struct compat_timeval { s32 tv_usec; }; +struct compat_itimerspec { + struct compat_timespec it_interval; + struct compat_timespec it_value; +}; + extern int compat_get_timespec64(struct timespec64 *, const void __user *); extern int compat_put_timespec64(const struct timespec64 *, void __user *); +extern int get_compat_itimerspec64(struct itimerspec64 *its, + const struct compat_itimerspec __user *uits); +extern int put_compat_itimerspec64(const struct itimerspec64 *its, + struct compat_itimerspec __user *uits); #endif /* _LINUX_COMPAT_TIME_H */ diff --git a/include/linux/cpu.h b/include/linux/cpu.h index a97a63eef59f..3233fbe23594 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -30,7 +30,7 @@ struct cpu { }; extern void boot_cpu_init(void); -extern void boot_cpu_state_init(void); +extern void boot_cpu_hotplug_init(void); extern void cpu_init(void); extern void trap_init(void); diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 8796ba387152..4cf06a64bc02 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -164,6 +164,7 @@ enum cpuhp_state { CPUHP_AP_PERF_POWERPC_NEST_IMC_ONLINE, CPUHP_AP_PERF_POWERPC_CORE_IMC_ONLINE, CPUHP_AP_PERF_POWERPC_THREAD_IMC_ONLINE, + CPUHP_AP_WATCHDOG_ONLINE, CPUHP_AP_WORKQUEUE_ONLINE, CPUHP_AP_RCUTREE_ONLINE, CPUHP_AP_ONLINE_DYN, diff --git a/include/linux/efi.h b/include/linux/efi.h index 56add823f190..401e4b254e30 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -894,6 +894,16 @@ typedef struct _efi_file_handle { void *flush; } efi_file_handle_t; +typedef struct { + u64 revision; + u32 open_volume; +} efi_file_io_interface_32_t; + +typedef struct { + u64 revision; + u64 open_volume; +} efi_file_io_interface_64_t; + typedef struct _efi_file_io_interface { u64 revision; int (*open_volume)(struct _efi_file_io_interface *, @@ -988,14 +998,12 @@ extern void efi_memmap_walk (efi_freemem_callback_t callback, void *arg); extern void efi_gettimeofday (struct timespec64 *ts); extern void efi_enter_virtual_mode (void); /* switch EFI to virtual mode, if possible */ #ifdef CONFIG_X86 -extern void efi_late_init(void); extern void efi_free_boot_services(void); extern efi_status_t efi_query_variable_store(u32 attributes, unsigned long size, bool nonblocking); extern void efi_find_mirror(void); #else -static inline void efi_late_init(void) {} static inline void efi_free_boot_services(void) {} static inline efi_status_t efi_query_variable_store(u32 attributes, @@ -1651,4 +1659,7 @@ struct linux_efi_tpm_eventlog { extern int efi_tpm_eventlog_init(void); +/* Workqueue to queue EFI Runtime Services */ +extern struct workqueue_struct *efi_rts_wq; + #endif /* _LINUX_EFI_H */ diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index cbb872c1b607..9d2ea3e907d0 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -73,6 +73,7 @@ #define GICD_TYPER_MBIS (1U << 16) #define GICD_TYPER_ID_BITS(typer) ((((typer) >> 19) & 0x1f) + 1) +#define GICD_TYPER_NUM_LPIS(typer) ((((typer) >> 11) & 0x1f) + 1) #define GICD_TYPER_IRQS(typer) ((((typer) & 0x1f) + 1) * 32) #define GICD_IROUTER_SPI_MODE_ONE (0U << 31) @@ -576,8 +577,8 @@ struct rdists { phys_addr_t phys_base; } __percpu *rdist; struct page *prop_page; - int id_bits; u64 flags; + u32 gicd_typer; bool has_vlpis; bool has_direct_lpi; }; diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index 9440a2fc8893..e909413e4e38 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -63,7 +63,6 @@ struct pt_regs; struct kretprobe; struct kretprobe_instance; typedef int (*kprobe_pre_handler_t) (struct kprobe *, struct pt_regs *); -typedef int (*kprobe_break_handler_t) (struct kprobe *, struct pt_regs *); typedef void (*kprobe_post_handler_t) (struct kprobe *, struct pt_regs *, unsigned long flags); typedef int (*kprobe_fault_handler_t) (struct kprobe *, struct pt_regs *, @@ -101,12 +100,6 @@ struct kprobe { */ kprobe_fault_handler_t fault_handler; - /* - * ... called if breakpoint trap occurs in probe handler. - * Return 1 if it handled break, otherwise kernel will see it. - */ - kprobe_break_handler_t break_handler; - /* Saved opcode (which has been replaced with breakpoint) */ kprobe_opcode_t opcode; @@ -155,24 +148,6 @@ static inline int kprobe_ftrace(struct kprobe *p) } /* - * Special probe type that uses setjmp-longjmp type tricks to resume - * execution at a specified entry with a matching prototype corresponding - * to the probed function - a trick to enable arguments to become - * accessible seamlessly by probe handling logic. - * Note: - * Because of the way compilers allocate stack space for local variables - * etc upfront, regardless of sub-scopes within a function, this mirroring - * principle currently works only for probes placed on function entry points. - */ -struct jprobe { - struct kprobe kp; - void *entry; /* probe handling code to jump to */ -}; - -/* For backward compatibility with old code using JPROBE_ENTRY() */ -#define JPROBE_ENTRY(handler) (handler) - -/* * Function-return probe - * Note: * User needs to provide a handler function, and initialize maxactive. @@ -389,9 +364,6 @@ int register_kprobe(struct kprobe *p); void unregister_kprobe(struct kprobe *p); int register_kprobes(struct kprobe **kps, int num); void unregister_kprobes(struct kprobe **kps, int num); -int setjmp_pre_handler(struct kprobe *, struct pt_regs *); -int longjmp_break_handler(struct kprobe *, struct pt_regs *); -void jprobe_return(void); unsigned long arch_deref_entry_point(void *); int register_kretprobe(struct kretprobe *rp); @@ -439,9 +411,6 @@ static inline void unregister_kprobe(struct kprobe *p) static inline void unregister_kprobes(struct kprobe **kps, int num) { } -static inline void jprobe_return(void) -{ -} static inline int register_kretprobe(struct kretprobe *rp) { return -ENOSYS; @@ -468,20 +437,6 @@ static inline int enable_kprobe(struct kprobe *kp) return -ENOSYS; } #endif /* CONFIG_KPROBES */ -static inline int register_jprobe(struct jprobe *p) -{ - return -ENOSYS; -} -static inline int register_jprobes(struct jprobe **jps, int num) -{ - return -ENOSYS; -} -static inline void unregister_jprobe(struct jprobe *p) -{ -} -static inline void unregister_jprobes(struct jprobe **jps, int num) -{ -} static inline int disable_kretprobe(struct kretprobe *rp) { return disable_kprobe(&rp->kp); @@ -490,14 +445,6 @@ static inline int enable_kretprobe(struct kretprobe *rp) { return enable_kprobe(&rp->kp); } -static inline int disable_jprobe(struct jprobe *jp) -{ - return -ENOSYS; -} -static inline int enable_jprobe(struct jprobe *jp) -{ - return -ENOSYS; -} #ifndef CONFIG_KPROBES static inline bool is_kprobe_insn_slot(unsigned long addr) diff --git a/include/linux/ktime.h b/include/linux/ktime.h index 5b9fddbaac41..b2bb44f87f5a 100644 --- a/include/linux/ktime.h +++ b/include/linux/ktime.h @@ -93,8 +93,11 @@ static inline ktime_t timeval_to_ktime(struct timeval tv) /* Map the ktime_t to timeval conversion to ns_to_timeval function */ #define ktime_to_timeval(kt) ns_to_timeval((kt)) -/* Convert ktime_t to nanoseconds - NOP in the scalar storage format: */ -#define ktime_to_ns(kt) (kt) +/* Convert ktime_t to nanoseconds */ +static inline s64 ktime_to_ns(const ktime_t kt) +{ + return kt; +} /** * ktime_compare - Compares two ktime_t variables for less, greater or equal diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 99ce070e7dcb..efdc24dd9e97 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -335,176 +335,183 @@ struct core_state { struct kioctx_table; struct mm_struct { - struct vm_area_struct *mmap; /* list of VMAs */ - struct rb_root mm_rb; - u32 vmacache_seqnum; /* per-thread vmacache */ + struct { + struct vm_area_struct *mmap; /* list of VMAs */ + struct rb_root mm_rb; + u32 vmacache_seqnum; /* per-thread vmacache */ #ifdef CONFIG_MMU - unsigned long (*get_unmapped_area) (struct file *filp, + unsigned long (*get_unmapped_area) (struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags); #endif - unsigned long mmap_base; /* base of mmap area */ - unsigned long mmap_legacy_base; /* base of mmap area in bottom-up allocations */ + unsigned long mmap_base; /* base of mmap area */ + unsigned long mmap_legacy_base; /* base of mmap area in bottom-up allocations */ #ifdef CONFIG_HAVE_ARCH_COMPAT_MMAP_BASES - /* Base adresses for compatible mmap() */ - unsigned long mmap_compat_base; - unsigned long mmap_compat_legacy_base; + /* Base adresses for compatible mmap() */ + unsigned long mmap_compat_base; + unsigned long mmap_compat_legacy_base; #endif - unsigned long task_size; /* size of task vm space */ - unsigned long highest_vm_end; /* highest vma end address */ - pgd_t * pgd; - - /** - * @mm_users: The number of users including userspace. - * - * Use mmget()/mmget_not_zero()/mmput() to modify. When this drops - * to 0 (i.e. when the task exits and there are no other temporary - * reference holders), we also release a reference on @mm_count - * (which may then free the &struct mm_struct if @mm_count also - * drops to 0). - */ - atomic_t mm_users; - - /** - * @mm_count: The number of references to &struct mm_struct - * (@mm_users count as 1). - * - * Use mmgrab()/mmdrop() to modify. When this drops to 0, the - * &struct mm_struct is freed. - */ - atomic_t mm_count; + unsigned long task_size; /* size of task vm space */ + unsigned long highest_vm_end; /* highest vma end address */ + pgd_t * pgd; + + /** + * @mm_users: The number of users including userspace. + * + * Use mmget()/mmget_not_zero()/mmput() to modify. When this + * drops to 0 (i.e. when the task exits and there are no other + * temporary reference holders), we also release a reference on + * @mm_count (which may then free the &struct mm_struct if + * @mm_count also drops to 0). + */ + atomic_t mm_users; + + /** + * @mm_count: The number of references to &struct mm_struct + * (@mm_users count as 1). + * + * Use mmgrab()/mmdrop() to modify. When this drops to 0, the + * &struct mm_struct is freed. + */ + atomic_t mm_count; #ifdef CONFIG_MMU - atomic_long_t pgtables_bytes; /* PTE page table pages */ + atomic_long_t pgtables_bytes; /* PTE page table pages */ #endif - int map_count; /* number of VMAs */ + int map_count; /* number of VMAs */ - spinlock_t page_table_lock; /* Protects page tables and some counters */ - struct rw_semaphore mmap_sem; + spinlock_t page_table_lock; /* Protects page tables and some + * counters + */ + struct rw_semaphore mmap_sem; - struct list_head mmlist; /* List of maybe swapped mm's. These are globally strung - * together off init_mm.mmlist, and are protected - * by mmlist_lock - */ + struct list_head mmlist; /* List of maybe swapped mm's. These + * are globally strung together off + * init_mm.mmlist, and are protected + * by mmlist_lock + */ - unsigned long hiwater_rss; /* High-watermark of RSS usage */ - unsigned long hiwater_vm; /* High-water virtual memory usage */ + unsigned long hiwater_rss; /* High-watermark of RSS usage */ + unsigned long hiwater_vm; /* High-water virtual memory usage */ - unsigned long total_vm; /* Total pages mapped */ - unsigned long locked_vm; /* Pages that have PG_mlocked set */ - unsigned long pinned_vm; /* Refcount permanently increased */ - unsigned long data_vm; /* VM_WRITE & ~VM_SHARED & ~VM_STACK */ - unsigned long exec_vm; /* VM_EXEC & ~VM_WRITE & ~VM_STACK */ - unsigned long stack_vm; /* VM_STACK */ - unsigned long def_flags; + unsigned long total_vm; /* Total pages mapped */ + unsigned long locked_vm; /* Pages that have PG_mlocked set */ + unsigned long pinned_vm; /* Refcount permanently increased */ + unsigned long data_vm; /* VM_WRITE & ~VM_SHARED & ~VM_STACK */ + unsigned long exec_vm; /* VM_EXEC & ~VM_WRITE & ~VM_STACK */ + unsigned long stack_vm; /* VM_STACK */ + unsigned long def_flags; - spinlock_t arg_lock; /* protect the below fields */ - unsigned long start_code, end_code, start_data, end_data; - unsigned long start_brk, brk, start_stack; - unsigned long arg_start, arg_end, env_start, env_end; + spinlock_t arg_lock; /* protect the below fields */ + unsigned long start_code, end_code, start_data, end_data; + unsigned long start_brk, brk, start_stack; + unsigned long arg_start, arg_end, env_start, env_end; - unsigned long saved_auxv[AT_VECTOR_SIZE]; /* for /proc/PID/auxv */ + unsigned long saved_auxv[AT_VECTOR_SIZE]; /* for /proc/PID/auxv */ - /* - * Special counters, in some configurations protected by the - * page_table_lock, in other configurations by being atomic. - */ - struct mm_rss_stat rss_stat; - - struct linux_binfmt *binfmt; + /* + * Special counters, in some configurations protected by the + * page_table_lock, in other configurations by being atomic. + */ + struct mm_rss_stat rss_stat; - cpumask_var_t cpu_vm_mask_var; + struct linux_binfmt *binfmt; - /* Architecture-specific MM context */ - mm_context_t context; + /* Architecture-specific MM context */ + mm_context_t context; - unsigned long flags; /* Must use atomic bitops to access the bits */ + unsigned long flags; /* Must use atomic bitops to access */ - struct core_state *core_state; /* coredumping support */ + struct core_state *core_state; /* coredumping support */ #ifdef CONFIG_MEMBARRIER - atomic_t membarrier_state; + atomic_t membarrier_state; #endif #ifdef CONFIG_AIO - spinlock_t ioctx_lock; - struct kioctx_table __rcu *ioctx_table; + spinlock_t ioctx_lock; + struct kioctx_table __rcu *ioctx_table; #endif #ifdef CONFIG_MEMCG - /* - * "owner" points to a task that is regarded as the canonical - * user/owner of this mm. All of the following must be true in - * order for it to be changed: - * - * current == mm->owner - * current->mm != mm - * new_owner->mm == mm - * new_owner->alloc_lock is held - */ - struct task_struct __rcu *owner; + /* + * "owner" points to a task that is regarded as the canonical + * user/owner of this mm. All of the following must be true in + * order for it to be changed: + * + * current == mm->owner + * current->mm != mm + * new_owner->mm == mm + * new_owner->alloc_lock is held + */ + struct task_struct __rcu *owner; #endif - struct user_namespace *user_ns; + struct user_namespace *user_ns; - /* store ref to file /proc/<pid>/exe symlink points to */ - struct file __rcu *exe_file; + /* store ref to file /proc/<pid>/exe symlink points to */ + struct file __rcu *exe_file; #ifdef CONFIG_MMU_NOTIFIER - struct mmu_notifier_mm *mmu_notifier_mm; + struct mmu_notifier_mm *mmu_notifier_mm; #endif #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !USE_SPLIT_PMD_PTLOCKS - pgtable_t pmd_huge_pte; /* protected by page_table_lock */ -#endif -#ifdef CONFIG_CPUMASK_OFFSTACK - struct cpumask cpumask_allocation; + pgtable_t pmd_huge_pte; /* protected by page_table_lock */ #endif #ifdef CONFIG_NUMA_BALANCING - /* - * numa_next_scan is the next time that the PTEs will be marked - * pte_numa. NUMA hinting faults will gather statistics and migrate - * pages to new nodes if necessary. - */ - unsigned long numa_next_scan; + /* + * numa_next_scan is the next time that the PTEs will be marked + * pte_numa. NUMA hinting faults will gather statistics and + * migrate pages to new nodes if necessary. + */ + unsigned long numa_next_scan; - /* Restart point for scanning and setting pte_numa */ - unsigned long numa_scan_offset; + /* Restart point for scanning and setting pte_numa */ + unsigned long numa_scan_offset; - /* numa_scan_seq prevents two threads setting pte_numa */ - int numa_scan_seq; + /* numa_scan_seq prevents two threads setting pte_numa */ + int numa_scan_seq; #endif - /* - * An operation with batched TLB flushing is going on. Anything that - * can move process memory needs to flush the TLB when moving a - * PROT_NONE or PROT_NUMA mapped page. - */ - atomic_t tlb_flush_pending; + /* + * An operation with batched TLB flushing is going on. Anything + * that can move process memory needs to flush the TLB when + * moving a PROT_NONE or PROT_NUMA mapped page. + */ + atomic_t tlb_flush_pending; #ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH - /* See flush_tlb_batched_pending() */ - bool tlb_flush_batched; + /* See flush_tlb_batched_pending() */ + bool tlb_flush_batched; #endif - struct uprobes_state uprobes_state; + struct uprobes_state uprobes_state; #ifdef CONFIG_HUGETLB_PAGE - atomic_long_t hugetlb_usage; + atomic_long_t hugetlb_usage; #endif - struct work_struct async_put_work; + struct work_struct async_put_work; #if IS_ENABLED(CONFIG_HMM) - /* HMM needs to track a few things per mm */ - struct hmm *hmm; + /* HMM needs to track a few things per mm */ + struct hmm *hmm; #endif -} __randomize_layout; + } __randomize_layout; + + /* + * The mm_cpumask needs to be at the end of mm_struct, because it + * is dynamically sized based on nr_cpu_ids. + */ + unsigned long cpu_bitmap[]; +}; extern struct mm_struct init_mm; +/* Pointer magic because the dynamic array size confuses some compilers. */ static inline void mm_init_cpumask(struct mm_struct *mm) { -#ifdef CONFIG_CPUMASK_OFFSTACK - mm->cpu_vm_mask_var = &mm->cpumask_allocation; -#endif - cpumask_clear(mm->cpu_vm_mask_var); + unsigned long cpu_bitmap = (unsigned long)mm; + + cpu_bitmap += offsetof(struct mm_struct, cpu_bitmap); + cpumask_clear((struct cpumask *)cpu_bitmap); } /* Future-safe accessor for struct mm_struct's cpu_vm_mask. */ static inline cpumask_t *mm_cpumask(struct mm_struct *mm) { - return mm->cpu_vm_mask_var; + return (struct cpumask *)&mm->cpu_bitmap; } struct mmu_gather; diff --git a/include/linux/nmi.h b/include/linux/nmi.h index b8d868d23e79..08f9247e9827 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -45,12 +45,18 @@ extern void touch_softlockup_watchdog(void); extern void touch_softlockup_watchdog_sync(void); extern void touch_all_softlockup_watchdogs(void); extern unsigned int softlockup_panic; -#else + +extern int lockup_detector_online_cpu(unsigned int cpu); +extern int lockup_detector_offline_cpu(unsigned int cpu); +#else /* CONFIG_SOFTLOCKUP_DETECTOR */ static inline void touch_softlockup_watchdog_sched(void) { } static inline void touch_softlockup_watchdog(void) { } static inline void touch_softlockup_watchdog_sync(void) { } static inline void touch_all_softlockup_watchdogs(void) { } -#endif + +#define lockup_detector_online_cpu NULL +#define lockup_detector_offline_cpu NULL +#endif /* CONFIG_SOFTLOCKUP_DETECTOR */ #ifdef CONFIG_DETECT_HUNG_TASK void reset_hung_task_detector(void); diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 87f6db437e4a..53c500f0ca79 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -490,7 +490,7 @@ struct perf_addr_filters_head { }; /** - * enum perf_event_state - the states of a event + * enum perf_event_state - the states of an event: */ enum perf_event_state { PERF_EVENT_STATE_DEAD = -4, diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h index c85704fcdbd2..ee7e987ea1b4 100644 --- a/include/linux/posix-timers.h +++ b/include/linux/posix-timers.h @@ -95,8 +95,8 @@ struct k_itimer { clockid_t it_clock; timer_t it_id; int it_active; - int it_overrun; - int it_overrun_last; + s64 it_overrun; + s64 it_overrun_last; int it_requeue_pending; int it_sigev_notify; ktime_t it_interval; diff --git a/include/linux/rculist.h b/include/linux/rculist.h index 36df6ccbc874..4786c2235b98 100644 --- a/include/linux/rculist.h +++ b/include/linux/rculist.h @@ -396,7 +396,16 @@ static inline void list_splice_tail_init_rcu(struct list_head *list, * @member: the name of the list_head within the struct. * * Continue to iterate over list of given type, continuing after - * the current position. + * the current position which must have been in the list when the RCU read + * lock was taken. + * This would typically require either that you obtained the node from a + * previous walk of the list in the same RCU read-side critical section, or + * that you held some sort of non-RCU reference (such as a reference count) + * to keep the node alive *and* in the list. + * + * This iterator is similar to list_for_each_entry_from_rcu() except + * this starts after the given position and that one starts at the given + * position. */ #define list_for_each_entry_continue_rcu(pos, head, member) \ for (pos = list_entry_rcu(pos->member.next, typeof(*pos), member); \ @@ -411,6 +420,14 @@ static inline void list_splice_tail_init_rcu(struct list_head *list, * * Iterate over the tail of a list starting from a given position, * which must have been in the list when the RCU read lock was taken. + * This would typically require either that you obtained the node from a + * previous walk of the list in the same RCU read-side critical section, or + * that you held some sort of non-RCU reference (such as a reference count) + * to keep the node alive *and* in the list. + * + * This iterator is similar to list_for_each_entry_continue_rcu() except + * this starts from the given position and that one starts from the position + * after the given position. */ #define list_for_each_entry_from_rcu(pos, head, member) \ for (; &(pos)->member != (head); \ diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 65163aa0bb04..75e5b393cf44 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -64,7 +64,6 @@ void rcu_barrier_tasks(void); void __rcu_read_lock(void); void __rcu_read_unlock(void); -void rcu_read_unlock_special(struct task_struct *t); void synchronize_rcu(void); /* @@ -159,11 +158,11 @@ static inline void rcu_init_nohz(void) { } } while (0) /* - * Note a voluntary context switch for RCU-tasks benefit. This is a - * macro rather than an inline function to avoid #include hell. + * Note a quasi-voluntary context switch for RCU-tasks's benefit. + * This is a macro rather than an inline function to avoid #include hell. */ #ifdef CONFIG_TASKS_RCU -#define rcu_note_voluntary_context_switch_lite(t) \ +#define rcu_tasks_qs(t) \ do { \ if (READ_ONCE((t)->rcu_tasks_holdout)) \ WRITE_ONCE((t)->rcu_tasks_holdout, false); \ @@ -171,14 +170,14 @@ static inline void rcu_init_nohz(void) { } #define rcu_note_voluntary_context_switch(t) \ do { \ rcu_all_qs(); \ - rcu_note_voluntary_context_switch_lite(t); \ + rcu_tasks_qs(t); \ } while (0) void call_rcu_tasks(struct rcu_head *head, rcu_callback_t func); void synchronize_rcu_tasks(void); void exit_tasks_rcu_start(void); void exit_tasks_rcu_finish(void); #else /* #ifdef CONFIG_TASKS_RCU */ -#define rcu_note_voluntary_context_switch_lite(t) do { } while (0) +#define rcu_tasks_qs(t) do { } while (0) #define rcu_note_voluntary_context_switch(t) rcu_all_qs() #define call_rcu_tasks call_rcu_sched #define synchronize_rcu_tasks synchronize_sched @@ -195,8 +194,8 @@ static inline void exit_tasks_rcu_finish(void) { } */ #define cond_resched_tasks_rcu_qs() \ do { \ - if (!cond_resched()) \ - rcu_note_voluntary_context_switch_lite(current); \ + rcu_tasks_qs(current); \ + cond_resched(); \ } while (0) /* @@ -567,8 +566,8 @@ static inline void rcu_preempt_sleep_check(void) { } * This is simply an identity function, but it documents where a pointer * is handed off from RCU to some other synchronization mechanism, for * example, reference counting or locking. In C11, it would map to - * kill_dependency(). It could be used as follows: - * `` + * kill_dependency(). It could be used as follows:: + * * rcu_read_lock(); * p = rcu_dereference(gp); * long_lived = is_long_lived(p); @@ -579,7 +578,6 @@ static inline void rcu_preempt_sleep_check(void) { } * p = rcu_pointer_handoff(p); * } * rcu_read_unlock(); - *`` */ #define rcu_pointer_handoff(p) (p) diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index 7b3c82e8a625..8d9a0ea8f0b5 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -93,7 +93,7 @@ static inline void kfree_call_rcu(struct rcu_head *head, #define rcu_note_context_switch(preempt) \ do { \ rcu_sched_qs(); \ - rcu_note_voluntary_context_switch_lite(current); \ + rcu_tasks_qs(current); \ } while (0) static inline int rcu_needs_cpu(u64 basemono, u64 *nextevt) diff --git a/include/linux/refcount.h b/include/linux/refcount.h index a685da2c4522..e28cce21bad6 100644 --- a/include/linux/refcount.h +++ b/include/linux/refcount.h @@ -3,9 +3,10 @@ #define _LINUX_REFCOUNT_H #include <linux/atomic.h> -#include <linux/mutex.h> -#include <linux/spinlock.h> -#include <linux/kernel.h> +#include <linux/compiler.h> +#include <linux/spinlock_types.h> + +struct mutex; /** * struct refcount_t - variant of atomic_t specialized for reference counts @@ -42,17 +43,30 @@ static inline unsigned int refcount_read(const refcount_t *r) return atomic_read(&r->refs); } +extern __must_check bool refcount_add_not_zero_checked(unsigned int i, refcount_t *r); +extern void refcount_add_checked(unsigned int i, refcount_t *r); + +extern __must_check bool refcount_inc_not_zero_checked(refcount_t *r); +extern void refcount_inc_checked(refcount_t *r); + +extern __must_check bool refcount_sub_and_test_checked(unsigned int i, refcount_t *r); + +extern __must_check bool refcount_dec_and_test_checked(refcount_t *r); +extern void refcount_dec_checked(refcount_t *r); + #ifdef CONFIG_REFCOUNT_FULL -extern __must_check bool refcount_add_not_zero(unsigned int i, refcount_t *r); -extern void refcount_add(unsigned int i, refcount_t *r); -extern __must_check bool refcount_inc_not_zero(refcount_t *r); -extern void refcount_inc(refcount_t *r); +#define refcount_add_not_zero refcount_add_not_zero_checked +#define refcount_add refcount_add_checked + +#define refcount_inc_not_zero refcount_inc_not_zero_checked +#define refcount_inc refcount_inc_checked + +#define refcount_sub_and_test refcount_sub_and_test_checked -extern __must_check bool refcount_sub_and_test(unsigned int i, refcount_t *r); +#define refcount_dec_and_test refcount_dec_and_test_checked +#define refcount_dec refcount_dec_checked -extern __must_check bool refcount_dec_and_test(refcount_t *r); -extern void refcount_dec(refcount_t *r); #else # ifdef CONFIG_ARCH_HAS_REFCOUNT # include <asm/refcount.h> diff --git a/include/linux/sched.h b/include/linux/sched.h index 43731fe51c97..dac5086e3815 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -167,8 +167,8 @@ struct task_group; * need_sleep = false; * wake_up_state(p, TASK_UNINTERRUPTIBLE); * - * Where wake_up_state() (and all other wakeup primitives) imply enough - * barriers to order the store of the variable against wakeup. + * where wake_up_state() executes a full memory barrier before accessing the + * task state. * * Wakeup will do: if (@state & p->state) p->state = TASK_RUNNING, that is, * once it observes the TASK_UNINTERRUPTIBLE store the waking CPU can issue a @@ -1017,7 +1017,6 @@ struct task_struct { u64 last_sum_exec_runtime; struct callback_head numa_work; - struct list_head numa_entry; struct numa_group *numa_group; /* diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h index 1c1a1512ec55..913488d828cb 100644 --- a/include/linux/sched/sysctl.h +++ b/include/linux/sched/sysctl.h @@ -40,7 +40,6 @@ extern unsigned int sysctl_numa_balancing_scan_size; #ifdef CONFIG_SCHED_DEBUG extern __read_mostly unsigned int sysctl_sched_migration_cost; extern __read_mostly unsigned int sysctl_sched_nr_migrate; -extern __read_mostly unsigned int sysctl_sched_time_avg; int sched_proc_update_handler(struct ctl_table *table, int write, void __user *buffer, size_t *length, diff --git a/include/linux/smpboot.h b/include/linux/smpboot.h index c174844cf663..d0884b525001 100644 --- a/include/linux/smpboot.h +++ b/include/linux/smpboot.h @@ -25,8 +25,6 @@ struct smpboot_thread_data; * parked (cpu offline) * @unpark: Optional unpark function, called when the thread is * unparked (cpu online) - * @cpumask: Internal state. To update which threads are unparked, - * call smpboot_update_cpumask_percpu_thread(). * @selfparking: Thread is not parked by the park function. * @thread_comm: The base name of the thread */ @@ -40,23 +38,12 @@ struct smp_hotplug_thread { void (*cleanup)(unsigned int cpu, bool online); void (*park)(unsigned int cpu); void (*unpark)(unsigned int cpu); - cpumask_var_t cpumask; bool selfparking; const char *thread_comm; }; -int smpboot_register_percpu_thread_cpumask(struct smp_hotplug_thread *plug_thread, - const struct cpumask *cpumask); - -static inline int -smpboot_register_percpu_thread(struct smp_hotplug_thread *plug_thread) -{ - return smpboot_register_percpu_thread_cpumask(plug_thread, - cpu_possible_mask); -} +int smpboot_register_percpu_thread(struct smp_hotplug_thread *plug_thread); void smpboot_unregister_percpu_thread(struct smp_hotplug_thread *plug_thread); -void smpboot_update_cpumask_percpu_thread(struct smp_hotplug_thread *plug_thread, - const struct cpumask *); #endif diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h index fd57888d4942..3190997df9ca 100644 --- a/include/linux/spinlock.h +++ b/include/linux/spinlock.h @@ -114,29 +114,48 @@ do { \ #endif /*arch_spin_is_contended*/ /* - * This barrier must provide two things: + * smp_mb__after_spinlock() provides the equivalent of a full memory barrier + * between program-order earlier lock acquisitions and program-order later + * memory accesses. * - * - it must guarantee a STORE before the spin_lock() is ordered against a - * LOAD after it, see the comments at its two usage sites. + * This guarantees that the following two properties hold: * - * - it must ensure the critical section is RCsc. + * 1) Given the snippet: * - * The latter is important for cases where we observe values written by other - * CPUs in spin-loops, without barriers, while being subject to scheduling. + * { X = 0; Y = 0; } * - * CPU0 CPU1 CPU2 + * CPU0 CPU1 * - * for (;;) { - * if (READ_ONCE(X)) - * break; - * } - * X=1 - * <sched-out> - * <sched-in> - * r = X; + * WRITE_ONCE(X, 1); WRITE_ONCE(Y, 1); + * spin_lock(S); smp_mb(); + * smp_mb__after_spinlock(); r1 = READ_ONCE(X); + * r0 = READ_ONCE(Y); + * spin_unlock(S); * - * without transitivity it could be that CPU1 observes X!=0 breaks the loop, - * we get migrated and CPU2 sees X==0. + * it is forbidden that CPU0 does not observe CPU1's store to Y (r0 = 0) + * and CPU1 does not observe CPU0's store to X (r1 = 0); see the comments + * preceding the call to smp_mb__after_spinlock() in __schedule() and in + * try_to_wake_up(). + * + * 2) Given the snippet: + * + * { X = 0; Y = 0; } + * + * CPU0 CPU1 CPU2 + * + * spin_lock(S); spin_lock(S); r1 = READ_ONCE(Y); + * WRITE_ONCE(X, 1); smp_mb__after_spinlock(); smp_rmb(); + * spin_unlock(S); r0 = READ_ONCE(X); r2 = READ_ONCE(X); + * WRITE_ONCE(Y, 1); + * spin_unlock(S); + * + * it is forbidden that CPU0's critical section executes before CPU1's + * critical section (r0 = 1), CPU2 observes CPU1's store to Y (r1 = 1) + * and CPU2 does not observe CPU0's store to X (r2 = 0); see the comments + * preceding the calls to smp_rmb() in try_to_wake_up() for similar + * snippets but "projected" onto two CPUs. + * + * Property (2) upgrades the lock to an RCsc lock. * * Since most load-store architectures implement ACQUIRE with an smp_mb() after * the LL/SC loop, they need no further barriers. Similarly all our TSO diff --git a/include/linux/srcu.h b/include/linux/srcu.h index 91494d7e8e41..3e72a291c401 100644 --- a/include/linux/srcu.h +++ b/include/linux/srcu.h @@ -195,6 +195,16 @@ static inline int srcu_read_lock(struct srcu_struct *sp) __acquires(sp) return retval; } +/* Used by tracing, cannot be traced and cannot invoke lockdep. */ +static inline notrace int +srcu_read_lock_notrace(struct srcu_struct *sp) __acquires(sp) +{ + int retval; + + retval = __srcu_read_lock(sp); + return retval; +} + /** * srcu_read_unlock - unregister a old reader from an SRCU-protected structure. * @sp: srcu_struct in which to unregister the old reader. @@ -209,6 +219,13 @@ static inline void srcu_read_unlock(struct srcu_struct *sp, int idx) __srcu_read_unlock(sp, idx); } +/* Used by tracing, cannot be traced and cannot call lockdep. */ +static inline notrace void +srcu_read_unlock_notrace(struct srcu_struct *sp, int idx) __releases(sp) +{ + __srcu_read_unlock(sp, idx); +} + /** * smp_mb__after_srcu_read_unlock - ensure full ordering after srcu_read_unlock * diff --git a/include/linux/swait.h b/include/linux/swait.h index bf8cb0dee23c..73e06e9986d4 100644 --- a/include/linux/swait.h +++ b/include/linux/swait.h @@ -16,7 +16,7 @@ * wait-queues, but the semantics are actually completely different, and * every single user we have ever had has been buggy (or pointless). * - * A "swake_up()" only wakes up _one_ waiter, which is not at all what + * A "swake_up_one()" only wakes up _one_ waiter, which is not at all what * "wake_up()" does, and has led to problems. In other cases, it has * been fine, because there's only ever one waiter (kvm), but in that * case gthe whole "simple" wait-queue is just pointless to begin with, @@ -38,8 +38,8 @@ * all wakeups are TASK_NORMAL in order to avoid O(n) lookups for the right * sleeper state. * - * - the exclusive mode; because this requires preserving the list order - * and this is hard. + * - the !exclusive mode; because that leads to O(n) wakeups, everything is + * exclusive. * * - custom wake callback functions; because you cannot give any guarantees * about random code. This also allows swait to be used in RT, such that @@ -115,7 +115,7 @@ extern void __init_swait_queue_head(struct swait_queue_head *q, const char *name * CPU0 - waker CPU1 - waiter * * for (;;) { - * @cond = true; prepare_to_swait(&wq_head, &wait, state); + * @cond = true; prepare_to_swait_exclusive(&wq_head, &wait, state); * smp_mb(); // smp_mb() from set_current_state() * if (swait_active(wq_head)) if (@cond) * wake_up(wq_head); break; @@ -157,20 +157,20 @@ static inline bool swq_has_sleeper(struct swait_queue_head *wq) return swait_active(wq); } -extern void swake_up(struct swait_queue_head *q); +extern void swake_up_one(struct swait_queue_head *q); extern void swake_up_all(struct swait_queue_head *q); extern void swake_up_locked(struct swait_queue_head *q); -extern void __prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait); -extern void prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait, int state); +extern void prepare_to_swait_exclusive(struct swait_queue_head *q, struct swait_queue *wait, int state); extern long prepare_to_swait_event(struct swait_queue_head *q, struct swait_queue *wait, int state); extern void __finish_swait(struct swait_queue_head *q, struct swait_queue *wait); extern void finish_swait(struct swait_queue_head *q, struct swait_queue *wait); -/* as per ___wait_event() but for swait, therefore "exclusive == 0" */ +/* as per ___wait_event() but for swait, therefore "exclusive == 1" */ #define ___swait_event(wq, condition, state, ret, cmd) \ ({ \ + __label__ __out; \ struct swait_queue __wait; \ long __ret = ret; \ \ @@ -183,20 +183,20 @@ extern void finish_swait(struct swait_queue_head *q, struct swait_queue *wait); \ if (___wait_is_interruptible(state) && __int) { \ __ret = __int; \ - break; \ + goto __out; \ } \ \ cmd; \ } \ finish_swait(&wq, &__wait); \ - __ret; \ +__out: __ret; \ }) #define __swait_event(wq, condition) \ (void)___swait_event(wq, condition, TASK_UNINTERRUPTIBLE, 0, \ schedule()) -#define swait_event(wq, condition) \ +#define swait_event_exclusive(wq, condition) \ do { \ if (condition) \ break; \ @@ -208,7 +208,7 @@ do { \ TASK_UNINTERRUPTIBLE, timeout, \ __ret = schedule_timeout(__ret)) -#define swait_event_timeout(wq, condition, timeout) \ +#define swait_event_timeout_exclusive(wq, condition, timeout) \ ({ \ long __ret = timeout; \ if (!___wait_cond_timeout(condition)) \ @@ -220,7 +220,7 @@ do { \ ___swait_event(wq, condition, TASK_INTERRUPTIBLE, 0, \ schedule()) -#define swait_event_interruptible(wq, condition) \ +#define swait_event_interruptible_exclusive(wq, condition) \ ({ \ int __ret = 0; \ if (!(condition)) \ @@ -233,7 +233,7 @@ do { \ TASK_INTERRUPTIBLE, timeout, \ __ret = schedule_timeout(__ret)) -#define swait_event_interruptible_timeout(wq, condition, timeout) \ +#define swait_event_interruptible_timeout_exclusive(wq, condition, timeout)\ ({ \ long __ret = timeout; \ if (!___wait_cond_timeout(condition)) \ @@ -246,7 +246,7 @@ do { \ (void)___swait_event(wq, condition, TASK_IDLE, 0, schedule()) /** - * swait_event_idle - wait without system load contribution + * swait_event_idle_exclusive - wait without system load contribution * @wq: the waitqueue to wait on * @condition: a C expression for the event to wait for * @@ -257,7 +257,7 @@ do { \ * condition and doesn't want to contribute to system load. Signals are * ignored. */ -#define swait_event_idle(wq, condition) \ +#define swait_event_idle_exclusive(wq, condition) \ do { \ if (condition) \ break; \ @@ -270,7 +270,7 @@ do { \ __ret = schedule_timeout(__ret)) /** - * swait_event_idle_timeout - wait up to timeout without load contribution + * swait_event_idle_timeout_exclusive - wait up to timeout without load contribution * @wq: the waitqueue to wait on * @condition: a C expression for the event to wait for * @timeout: timeout at which we'll give up in jiffies @@ -288,7 +288,7 @@ do { \ * or the remaining jiffies (at least 1) if the @condition evaluated * to %true before the @timeout elapsed. */ -#define swait_event_idle_timeout(wq, condition, timeout) \ +#define swait_event_idle_timeout_exclusive(wq, condition, timeout) \ ({ \ long __ret = timeout; \ if (!___wait_cond_timeout(condition)) \ diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 5c1a0933768e..ebb2f24027e8 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -506,9 +506,9 @@ asmlinkage long sys_sync_file_range(int fd, loff_t offset, loff_t nbytes, /* fs/timerfd.c */ asmlinkage long sys_timerfd_create(int clockid, int flags); asmlinkage long sys_timerfd_settime(int ufd, int flags, - const struct itimerspec __user *utmr, - struct itimerspec __user *otmr); -asmlinkage long sys_timerfd_gettime(int ufd, struct itimerspec __user *otmr); + const struct __kernel_itimerspec __user *utmr, + struct __kernel_itimerspec __user *otmr); +asmlinkage long sys_timerfd_gettime(int ufd, struct __kernel_itimerspec __user *otmr); /* fs/utimes.c */ asmlinkage long sys_utimensat(int dfd, const char __user *filename, @@ -573,10 +573,10 @@ asmlinkage long sys_timer_create(clockid_t which_clock, struct sigevent __user *timer_event_spec, timer_t __user * created_timer_id); asmlinkage long sys_timer_gettime(timer_t timer_id, - struct itimerspec __user *setting); + struct __kernel_itimerspec __user *setting); asmlinkage long sys_timer_getoverrun(timer_t timer_id); asmlinkage long sys_timer_settime(timer_t timer_id, int flags, - const struct itimerspec __user *new_setting, + const struct __kernel_itimerspec __user *new_setting, struct itimerspec __user *old_setting); asmlinkage long sys_timer_delete(timer_t timer_id); asmlinkage long sys_clock_settime(clockid_t which_clock, diff --git a/include/linux/time.h b/include/linux/time.h index aed74463592d..27d83fd2ae61 100644 --- a/include/linux/time.h +++ b/include/linux/time.h @@ -14,9 +14,9 @@ int get_timespec64(struct timespec64 *ts, int put_timespec64(const struct timespec64 *ts, struct __kernel_timespec __user *uts); int get_itimerspec64(struct itimerspec64 *it, - const struct itimerspec __user *uit); + const struct __kernel_itimerspec __user *uit); int put_itimerspec64(const struct itimerspec64 *it, - struct itimerspec __user *uit); + struct __kernel_itimerspec __user *uit); extern time64_t mktime64(const unsigned int year, const unsigned int mon, const unsigned int day, const unsigned int hour, diff --git a/include/linux/time64.h b/include/linux/time64.h index 0a7b2f79cec7..05634afba0db 100644 --- a/include/linux/time64.h +++ b/include/linux/time64.h @@ -12,6 +12,7 @@ typedef __u64 timeu64_t; */ #ifndef CONFIG_64BIT_TIME #define __kernel_timespec timespec +#define __kernel_itimerspec itimerspec #endif #include <uapi/linux/time.h> diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h index 86bc2026efce..edace6b656e9 100644 --- a/include/linux/timekeeping.h +++ b/include/linux/timekeeping.h @@ -177,7 +177,7 @@ static inline time64_t ktime_get_clocktai_seconds(void) extern bool timekeeping_rtc_skipsuspend(void); extern bool timekeeping_rtc_skipresume(void); -extern void timekeeping_inject_sleeptime64(struct timespec64 *delta); +extern void timekeeping_inject_sleeptime64(const struct timespec64 *delta); /* * struct system_time_snapshot - simultaneous raw/real time capture with diff --git a/include/linux/torture.h b/include/linux/torture.h index 66272862070b..61dfd93b6ee4 100644 --- a/include/linux/torture.h +++ b/include/linux/torture.h @@ -64,6 +64,8 @@ struct torture_random_state { long trs_count; }; #define DEFINE_TORTURE_RANDOM(name) struct torture_random_state name = { 0, 0 } +#define DEFINE_TORTURE_RANDOM_PERCPU(name) \ + DEFINE_PER_CPU(struct torture_random_state, name) unsigned long torture_random(struct torture_random_state *trsp); /* Task shuffler, which causes CPUs to occasionally go idle. */ @@ -79,7 +81,7 @@ void stutter_wait(const char *title); int torture_stutter_init(int s); /* Initialization and cleanup. */ -bool torture_init_begin(char *ttype, bool v); +bool torture_init_begin(char *ttype, int v); void torture_init_end(void); bool torture_cleanup_begin(void); void torture_cleanup_end(void); diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h index 9324ac2d9ff2..43913ae79f64 100644 --- a/include/net/af_vsock.h +++ b/include/net/af_vsock.h @@ -64,7 +64,8 @@ struct vsock_sock { struct list_head pending_links; struct list_head accept_queue; bool rejected; - struct delayed_work dwork; + struct delayed_work connect_work; + struct delayed_work pending_work; struct delayed_work close_work; bool close_work_scheduled; u32 peer_shutdown; @@ -77,7 +78,6 @@ struct vsock_sock { s64 vsock_stream_has_data(struct vsock_sock *vsk); s64 vsock_stream_has_space(struct vsock_sock *vsk); -void vsock_pending_work(struct work_struct *work); struct sock *__vsock_create(struct net *net, struct socket *sock, struct sock *parent, diff --git a/include/net/llc.h b/include/net/llc.h index dc35f25eb679..890a87318014 100644 --- a/include/net/llc.h +++ b/include/net/llc.h @@ -116,6 +116,11 @@ static inline void llc_sap_hold(struct llc_sap *sap) refcount_inc(&sap->refcnt); } +static inline bool llc_sap_hold_safe(struct llc_sap *sap) +{ + return refcount_inc_not_zero(&sap->refcnt); +} + void llc_sap_close(struct llc_sap *sap); static inline void llc_sap_put(struct llc_sap *sap) diff --git a/include/trace/events/rcu.h b/include/trace/events/rcu.h index 5936aac357ab..a8d07feff6a0 100644 --- a/include/trace/events/rcu.h +++ b/include/trace/events/rcu.h @@ -52,6 +52,7 @@ TRACE_EVENT(rcu_utilization, * "cpuqs": CPU passes through a quiescent state. * "cpuonl": CPU comes online. * "cpuofl": CPU goes offline. + * "cpuofl-bgp": CPU goes offline while blocking a grace period. * "reqwait": GP kthread sleeps waiting for grace-period request. * "reqwaitsig": GP kthread awakened by signal from reqwait state. * "fqswait": GP kthread waiting until time to force quiescent states. @@ -63,24 +64,24 @@ TRACE_EVENT(rcu_utilization, */ TRACE_EVENT(rcu_grace_period, - TP_PROTO(const char *rcuname, unsigned long gpnum, const char *gpevent), + TP_PROTO(const char *rcuname, unsigned long gp_seq, const char *gpevent), - TP_ARGS(rcuname, gpnum, gpevent), + TP_ARGS(rcuname, gp_seq, gpevent), TP_STRUCT__entry( __field(const char *, rcuname) - __field(unsigned long, gpnum) + __field(unsigned long, gp_seq) __field(const char *, gpevent) ), TP_fast_assign( __entry->rcuname = rcuname; - __entry->gpnum = gpnum; + __entry->gp_seq = gp_seq; __entry->gpevent = gpevent; ), TP_printk("%s %lu %s", - __entry->rcuname, __entry->gpnum, __entry->gpevent) + __entry->rcuname, __entry->gp_seq, __entry->gpevent) ); /* @@ -90,8 +91,8 @@ TRACE_EVENT(rcu_grace_period, * * "Startleaf": Request a grace period based on leaf-node data. * "Prestarted": Someone beat us to the request - * "Startedleaf": Leaf-node start proved sufficient. - * "Startedleafroot": Leaf-node start proved sufficient after checking root. + * "Startedleaf": Leaf node marked for future GP. + * "Startedleafroot": All nodes from leaf to root marked for future GP. * "Startedroot": Requested a nocb grace period based on root-node data. * "NoGPkthread": The RCU grace-period kthread has not yet started. * "StartWait": Start waiting for the requested grace period. @@ -102,17 +103,16 @@ TRACE_EVENT(rcu_grace_period, */ TRACE_EVENT(rcu_future_grace_period, - TP_PROTO(const char *rcuname, unsigned long gpnum, unsigned long completed, - unsigned long c, u8 level, int grplo, int grphi, + TP_PROTO(const char *rcuname, unsigned long gp_seq, + unsigned long gp_seq_req, u8 level, int grplo, int grphi, const char *gpevent), - TP_ARGS(rcuname, gpnum, completed, c, level, grplo, grphi, gpevent), + TP_ARGS(rcuname, gp_seq, gp_seq_req, level, grplo, grphi, gpevent), TP_STRUCT__entry( __field(const char *, rcuname) - __field(unsigned long, gpnum) - __field(unsigned long, completed) - __field(unsigned long, c) + __field(unsigned long, gp_seq) + __field(unsigned long, gp_seq_req) __field(u8, level) __field(int, grplo) __field(int, grphi) @@ -121,19 +121,17 @@ TRACE_EVENT(rcu_future_grace_period, TP_fast_assign( __entry->rcuname = rcuname; - __entry->gpnum = gpnum; - __entry->completed = completed; - __entry->c = c; + __entry->gp_seq = gp_seq; + __entry->gp_seq_req = gp_seq_req; __entry->level = level; __entry->grplo = grplo; __entry->grphi = grphi; __entry->gpevent = gpevent; ), - TP_printk("%s %lu %lu %lu %u %d %d %s", - __entry->rcuname, __entry->gpnum, __entry->completed, - __entry->c, __entry->level, __entry->grplo, __entry->grphi, - __entry->gpevent) + TP_printk("%s %lu %lu %u %d %d %s", + __entry->rcuname, __entry->gp_seq, __entry->gp_seq_req, __entry->level, + __entry->grplo, __entry->grphi, __entry->gpevent) ); /* @@ -145,14 +143,14 @@ TRACE_EVENT(rcu_future_grace_period, */ TRACE_EVENT(rcu_grace_period_init, - TP_PROTO(const char *rcuname, unsigned long gpnum, u8 level, + TP_PROTO(const char *rcuname, unsigned long gp_seq, u8 level, int grplo, int grphi, unsigned long qsmask), - TP_ARGS(rcuname, gpnum, level, grplo, grphi, qsmask), + TP_ARGS(rcuname, gp_seq, level, grplo, grphi, qsmask), TP_STRUCT__entry( __field(const char *, rcuname) - __field(unsigned long, gpnum) + __field(unsigned long, gp_seq) __field(u8, level) __field(int, grplo) __field(int, grphi) @@ -161,7 +159,7 @@ TRACE_EVENT(rcu_grace_period_init, TP_fast_assign( __entry->rcuname = rcuname; - __entry->gpnum = gpnum; + __entry->gp_seq = gp_seq; __entry->level = level; __entry->grplo = grplo; __entry->grphi = grphi; @@ -169,7 +167,7 @@ TRACE_EVENT(rcu_grace_period_init, ), TP_printk("%s %lu %u %d %d %lx", - __entry->rcuname, __entry->gpnum, __entry->level, + __entry->rcuname, __entry->gp_seq, __entry->level, __entry->grplo, __entry->grphi, __entry->qsmask) ); @@ -301,24 +299,24 @@ TRACE_EVENT(rcu_nocb_wake, */ TRACE_EVENT(rcu_preempt_task, - TP_PROTO(const char *rcuname, int pid, unsigned long gpnum), + TP_PROTO(const char *rcuname, int pid, unsigned long gp_seq), - TP_ARGS(rcuname, pid, gpnum), + TP_ARGS(rcuname, pid, gp_seq), TP_STRUCT__entry( __field(const char *, rcuname) - __field(unsigned long, gpnum) + __field(unsigned long, gp_seq) __field(int, pid) ), TP_fast_assign( __entry->rcuname = rcuname; - __entry->gpnum = gpnum; + __entry->gp_seq = gp_seq; __entry->pid = pid; ), TP_printk("%s %lu %d", - __entry->rcuname, __entry->gpnum, __entry->pid) + __entry->rcuname, __entry->gp_seq, __entry->pid) ); /* @@ -328,23 +326,23 @@ TRACE_EVENT(rcu_preempt_task, */ TRACE_EVENT(rcu_unlock_preempted_task, - TP_PROTO(const char *rcuname, unsigned long gpnum, int pid), + TP_PROTO(const char *rcuname, unsigned long gp_seq, int pid), - TP_ARGS(rcuname, gpnum, pid), + TP_ARGS(rcuname, gp_seq, pid), TP_STRUCT__entry( __field(const char *, rcuname) - __field(unsigned long, gpnum) + __field(unsigned long, gp_seq) __field(int, pid) ), TP_fast_assign( __entry->rcuname = rcuname; - __entry->gpnum = gpnum; + __entry->gp_seq = gp_seq; __entry->pid = pid; ), - TP_printk("%s %lu %d", __entry->rcuname, __entry->gpnum, __entry->pid) + TP_printk("%s %lu %d", __entry->rcuname, __entry->gp_seq, __entry->pid) ); /* @@ -357,15 +355,15 @@ TRACE_EVENT(rcu_unlock_preempted_task, */ TRACE_EVENT(rcu_quiescent_state_report, - TP_PROTO(const char *rcuname, unsigned long gpnum, + TP_PROTO(const char *rcuname, unsigned long gp_seq, unsigned long mask, unsigned long qsmask, u8 level, int grplo, int grphi, int gp_tasks), - TP_ARGS(rcuname, gpnum, mask, qsmask, level, grplo, grphi, gp_tasks), + TP_ARGS(rcuname, gp_seq, mask, qsmask, level, grplo, grphi, gp_tasks), TP_STRUCT__entry( __field(const char *, rcuname) - __field(unsigned long, gpnum) + __field(unsigned long, gp_seq) __field(unsigned long, mask) __field(unsigned long, qsmask) __field(u8, level) @@ -376,7 +374,7 @@ TRACE_EVENT(rcu_quiescent_state_report, TP_fast_assign( __entry->rcuname = rcuname; - __entry->gpnum = gpnum; + __entry->gp_seq = gp_seq; __entry->mask = mask; __entry->qsmask = qsmask; __entry->level = level; @@ -386,41 +384,41 @@ TRACE_EVENT(rcu_quiescent_state_report, ), TP_printk("%s %lu %lx>%lx %u %d %d %u", - __entry->rcuname, __entry->gpnum, + __entry->rcuname, __entry->gp_seq, __entry->mask, __entry->qsmask, __entry->level, __entry->grplo, __entry->grphi, __entry->gp_tasks) ); /* * Tracepoint for quiescent states detected by force_quiescent_state(). - * These trace events include the type of RCU, the grace-period number that - * was blocked by the CPU, the CPU itself, and the type of quiescent state, - * which can be "dti" for dyntick-idle mode, "ofl" for CPU offline, "kick" - * when kicking a CPU that has been in dyntick-idle mode for too long, or - * "rqc" if the CPU got a quiescent state via its rcu_qs_ctr. + * These trace events include the type of RCU, the grace-period number + * that was blocked by the CPU, the CPU itself, and the type of quiescent + * state, which can be "dti" for dyntick-idle mode, "kick" when kicking + * a CPU that has been in dyntick-idle mode for too long, or "rqc" if the + * CPU got a quiescent state via its rcu_qs_ctr. */ TRACE_EVENT(rcu_fqs, - TP_PROTO(const char *rcuname, unsigned long gpnum, int cpu, const char *qsevent), + TP_PROTO(const char *rcuname, unsigned long gp_seq, int cpu, const char *qsevent), - TP_ARGS(rcuname, gpnum, cpu, qsevent), + TP_ARGS(rcuname, gp_seq, cpu, qsevent), TP_STRUCT__entry( __field(const char *, rcuname) - __field(unsigned long, gpnum) + __field(unsigned long, gp_seq) __field(int, cpu) __field(const char *, qsevent) ), TP_fast_assign( __entry->rcuname = rcuname; - __entry->gpnum = gpnum; + __entry->gp_seq = gp_seq; __entry->cpu = cpu; __entry->qsevent = qsevent; ), TP_printk("%s %lu %d %s", - __entry->rcuname, __entry->gpnum, + __entry->rcuname, __entry->gp_seq, __entry->cpu, __entry->qsevent) ); @@ -753,23 +751,23 @@ TRACE_EVENT(rcu_barrier, #else /* #ifdef CONFIG_RCU_TRACE */ -#define trace_rcu_grace_period(rcuname, gpnum, gpevent) do { } while (0) -#define trace_rcu_future_grace_period(rcuname, gpnum, completed, c, \ +#define trace_rcu_grace_period(rcuname, gp_seq, gpevent) do { } while (0) +#define trace_rcu_future_grace_period(rcuname, gp_seq, gp_seq_req, \ level, grplo, grphi, event) \ do { } while (0) -#define trace_rcu_grace_period_init(rcuname, gpnum, level, grplo, grphi, \ +#define trace_rcu_grace_period_init(rcuname, gp_seq, level, grplo, grphi, \ qsmask) do { } while (0) #define trace_rcu_exp_grace_period(rcuname, gqseq, gpevent) \ do { } while (0) #define trace_rcu_exp_funnel_lock(rcuname, level, grplo, grphi, gpevent) \ do { } while (0) #define trace_rcu_nocb_wake(rcuname, cpu, reason) do { } while (0) -#define trace_rcu_preempt_task(rcuname, pid, gpnum) do { } while (0) -#define trace_rcu_unlock_preempted_task(rcuname, gpnum, pid) do { } while (0) -#define trace_rcu_quiescent_state_report(rcuname, gpnum, mask, qsmask, level, \ +#define trace_rcu_preempt_task(rcuname, pid, gp_seq) do { } while (0) +#define trace_rcu_unlock_preempted_task(rcuname, gp_seq, pid) do { } while (0) +#define trace_rcu_quiescent_state_report(rcuname, gp_seq, mask, qsmask, level, \ grplo, grphi, gp_tasks) do { } \ while (0) -#define trace_rcu_fqs(rcuname, gpnum, cpu, qsevent) do { } while (0) +#define trace_rcu_fqs(rcuname, gp_seq, cpu, qsevent) do { } while (0) #define trace_rcu_dyntick(polarity, oldnesting, newnesting, dyntick) do { } while (0) #define trace_rcu_callback(rcuname, rhp, qlen_lazy, qlen) do { } while (0) #define trace_rcu_kfree_callback(rcuname, rhp, offset, qlen_lazy, qlen) \ diff --git a/include/uapi/linux/time.h b/include/uapi/linux/time.h index fcf936656493..6b56a2208be7 100644 --- a/include/uapi/linux/time.h +++ b/include/uapi/linux/time.h @@ -49,6 +49,13 @@ struct __kernel_timespec { }; #endif +#ifndef __kernel_itimerspec +struct __kernel_itimerspec { + struct __kernel_timespec it_interval; /* timer period */ + struct __kernel_timespec it_value; /* timer expiration */ +}; +#endif + /* * legacy timeval structure, only embedded in structures that * traditionally used 'timeval' to pass time intervals (not absolute diff --git a/init/main.c b/init/main.c index fcfef46c935a..f86b64c35d38 100644 --- a/init/main.c +++ b/init/main.c @@ -561,8 +561,8 @@ asmlinkage __visible void __init start_kernel(void) setup_command_line(command_line); setup_nr_cpu_ids(); setup_per_cpu_areas(); - boot_cpu_state_init(); smp_prepare_boot_cpu(); /* arch-specific boot-cpu hooks */ + boot_cpu_hotplug_init(); build_all_zonelists(NULL); page_alloc_init(); diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c index e0918d180f08..46f5f29605d4 100644 --- a/kernel/bpf/cpumap.c +++ b/kernel/bpf/cpumap.c @@ -69,7 +69,7 @@ struct bpf_cpu_map { }; static int bq_flush_to_queue(struct bpf_cpu_map_entry *rcpu, - struct xdp_bulk_queue *bq); + struct xdp_bulk_queue *bq, bool in_napi_ctx); static u64 cpu_map_bitmap_size(const union bpf_attr *attr) { @@ -375,7 +375,7 @@ static void __cpu_map_entry_free(struct rcu_head *rcu) struct xdp_bulk_queue *bq = per_cpu_ptr(rcpu->bulkq, cpu); /* No concurrent bq_enqueue can run at this point */ - bq_flush_to_queue(rcpu, bq); + bq_flush_to_queue(rcpu, bq, false); } free_percpu(rcpu->bulkq); /* Cannot kthread_stop() here, last put free rcpu resources */ @@ -558,7 +558,7 @@ const struct bpf_map_ops cpu_map_ops = { }; static int bq_flush_to_queue(struct bpf_cpu_map_entry *rcpu, - struct xdp_bulk_queue *bq) + struct xdp_bulk_queue *bq, bool in_napi_ctx) { unsigned int processed = 0, drops = 0; const int to_cpu = rcpu->cpu; @@ -578,7 +578,10 @@ static int bq_flush_to_queue(struct bpf_cpu_map_entry *rcpu, err = __ptr_ring_produce(q, xdpf); if (err) { drops++; - xdp_return_frame_rx_napi(xdpf); + if (likely(in_napi_ctx)) + xdp_return_frame_rx_napi(xdpf); + else + xdp_return_frame(xdpf); } processed++; } @@ -598,7 +601,7 @@ static int bq_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_frame *xdpf) struct xdp_bulk_queue *bq = this_cpu_ptr(rcpu->bulkq); if (unlikely(bq->count == CPU_MAP_BULK_SIZE)) - bq_flush_to_queue(rcpu, bq); + bq_flush_to_queue(rcpu, bq, true); /* Notice, xdp_buff/page MUST be queued here, long enough for * driver to code invoking us to finished, due to driver @@ -661,7 +664,7 @@ void __cpu_map_flush(struct bpf_map *map) /* Flush all frames in bulkq to real queue */ bq = this_cpu_ptr(rcpu->bulkq); - bq_flush_to_queue(rcpu, bq); + bq_flush_to_queue(rcpu, bq, true); /* If already running, costs spin_lock_irqsave + smb_mb */ wake_up_process(rcpu->kthread); diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c index d361fc1e3bf3..750d45edae79 100644 --- a/kernel/bpf/devmap.c +++ b/kernel/bpf/devmap.c @@ -217,7 +217,8 @@ void __dev_map_insert_ctx(struct bpf_map *map, u32 bit) } static int bq_xmit_all(struct bpf_dtab_netdev *obj, - struct xdp_bulk_queue *bq, u32 flags) + struct xdp_bulk_queue *bq, u32 flags, + bool in_napi_ctx) { struct net_device *dev = obj->dev; int sent = 0, drops = 0, err = 0; @@ -254,7 +255,10 @@ error: struct xdp_frame *xdpf = bq->q[i]; /* RX path under NAPI protection, can return frames faster */ - xdp_return_frame_rx_napi(xdpf); + if (likely(in_napi_ctx)) + xdp_return_frame_rx_napi(xdpf); + else + xdp_return_frame(xdpf); drops++; } goto out; @@ -286,7 +290,7 @@ void __dev_map_flush(struct bpf_map *map) __clear_bit(bit, bitmap); bq = this_cpu_ptr(dev->bulkq); - bq_xmit_all(dev, bq, XDP_XMIT_FLUSH); + bq_xmit_all(dev, bq, XDP_XMIT_FLUSH, true); } } @@ -316,7 +320,7 @@ static int bq_enqueue(struct bpf_dtab_netdev *obj, struct xdp_frame *xdpf, struct xdp_bulk_queue *bq = this_cpu_ptr(obj->bulkq); if (unlikely(bq->count == DEV_MAP_BULK_SIZE)) - bq_xmit_all(obj, bq, 0); + bq_xmit_all(obj, bq, 0, true); /* Ingress dev_rx will be the same for all xdp_frame's in * bulk_queue, because bq stored per-CPU and must be flushed @@ -385,7 +389,7 @@ static void dev_map_flush_old(struct bpf_dtab_netdev *dev) __clear_bit(dev->bit, bitmap); bq = per_cpu_ptr(dev->bulkq, cpu); - bq_xmit_all(dev, bq, XDP_XMIT_FLUSH); + bq_xmit_all(dev, bq, XDP_XMIT_FLUSH, false); } } } diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c index 98fb7938beea..c4d75c52b4fc 100644 --- a/kernel/bpf/sockmap.c +++ b/kernel/bpf/sockmap.c @@ -1048,12 +1048,12 @@ static int bpf_tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT); while (msg_data_left(msg)) { - struct sk_msg_buff *m; + struct sk_msg_buff *m = NULL; bool enospc = false; int copy; if (sk->sk_err) { - err = sk->sk_err; + err = -sk->sk_err; goto out_err; } @@ -1116,8 +1116,11 @@ wait_for_sndbuf: set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); wait_for_memory: err = sk_stream_wait_memory(sk, &timeo); - if (err) + if (err) { + if (m && m != psock->cork) + free_start_sg(sk, m); goto out_err; + } } out_err: if (err < 0) diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index a31a1ba0f8ea..b41c6cf2eb88 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -575,7 +575,7 @@ static struct bpf_map *bpf_map_inc_not_zero(struct bpf_map *map, { int refold; - refold = __atomic_add_unless(&map->refcnt, 1, 0); + refold = atomic_fetch_add_unless(&map->refcnt, 1, 0); if (refold >= BPF_MAX_REFCNT) { __bpf_map_put(map, false); @@ -1144,7 +1144,7 @@ struct bpf_prog *bpf_prog_inc_not_zero(struct bpf_prog *prog) { int refold; - refold = __atomic_add_unless(&prog->aux->refcnt, 1, 0); + refold = atomic_fetch_add_unless(&prog->aux->refcnt, 1, 0); if (refold >= BPF_MAX_REFCNT) { __bpf_prog_put(prog, false); diff --git a/kernel/compat.c b/kernel/compat.c index 702aa846ddac..8e40efc2928a 100644 --- a/kernel/compat.c +++ b/kernel/compat.c @@ -324,35 +324,6 @@ COMPAT_SYSCALL_DEFINE3(sched_getaffinity, compat_pid_t, pid, unsigned int, len, return ret; } -/* Todo: Delete these extern declarations when get/put_compat_itimerspec64() - * are moved to kernel/time/time.c . - */ -extern int __compat_get_timespec64(struct timespec64 *ts64, - const struct compat_timespec __user *cts); -extern int __compat_put_timespec64(const struct timespec64 *ts64, - struct compat_timespec __user *cts); - -int get_compat_itimerspec64(struct itimerspec64 *its, - const struct compat_itimerspec __user *uits) -{ - - if (__compat_get_timespec64(&its->it_interval, &uits->it_interval) || - __compat_get_timespec64(&its->it_value, &uits->it_value)) - return -EFAULT; - return 0; -} -EXPORT_SYMBOL_GPL(get_compat_itimerspec64); - -int put_compat_itimerspec64(const struct itimerspec64 *its, - struct compat_itimerspec __user *uits) -{ - if (__compat_put_timespec64(&its->it_interval, &uits->it_interval) || - __compat_put_timespec64(&its->it_value, &uits->it_value)) - return -EFAULT; - return 0; -} -EXPORT_SYMBOL_GPL(put_compat_itimerspec64); - /* * We currently only need the following fields from the sigevent * structure: sigev_value, sigev_signo, sig_notify and (sometimes diff --git a/kernel/cpu.c b/kernel/cpu.c index 0db8938fbb23..dd8634dde1ae 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -1274,7 +1274,7 @@ static struct cpuhp_step cpuhp_hp_states[] = { * otherwise a RCU stall occurs. */ [CPUHP_TIMERS_PREPARE] = { - .name = "timers:dead", + .name = "timers:prepare", .startup.single = timers_prepare_cpu, .teardown.single = timers_dead_cpu, }, @@ -1344,6 +1344,11 @@ static struct cpuhp_step cpuhp_hp_states[] = { .startup.single = perf_event_init_cpu, .teardown.single = perf_event_exit_cpu, }, + [CPUHP_AP_WATCHDOG_ONLINE] = { + .name = "lockup_detector:online", + .startup.single = lockup_detector_online_cpu, + .teardown.single = lockup_detector_offline_cpu, + }, [CPUHP_AP_WORKQUEUE_ONLINE] = { .name = "workqueue:online", .startup.single = workqueue_online_cpu, @@ -2010,7 +2015,7 @@ void __init boot_cpu_init(void) /* * Must be called _AFTER_ setting up the per_cpu areas */ -void __init boot_cpu_state_init(void) +void __init boot_cpu_hotplug_init(void) { per_cpu_ptr(&cpuhp_state, smp_processor_id())->state = CPUHP_ONLINE; } diff --git a/kernel/events/core.c b/kernel/events/core.c index eec2d5fb676b..f6ea33a9f904 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -1656,7 +1656,7 @@ perf_event_groups_next(struct perf_event *event) typeof(*event), group_node)) /* - * Add a event from the lists for its context. + * Add an event from the lists for its context. * Must be called with ctx->mutex and ctx->lock held. */ static void @@ -1844,7 +1844,7 @@ static void perf_group_attach(struct perf_event *event) } /* - * Remove a event from the lists for its context. + * Remove an event from the lists for its context. * Must be called with ctx->mutex and ctx->lock held. */ static void @@ -2148,7 +2148,7 @@ static void __perf_event_disable(struct perf_event *event, } /* - * Disable a event. + * Disable an event. * * If event->ctx is a cloned context, callers must make sure that * every task struct that event->ctx->task could possibly point to @@ -2677,7 +2677,7 @@ static void __perf_event_enable(struct perf_event *event, } /* - * Enable a event. + * Enable an event. * * If event->ctx is a cloned context, callers must make sure that * every task struct that event->ctx->task could possibly point to @@ -2755,7 +2755,7 @@ static int __perf_event_stop(void *info) * events will refuse to restart because of rb::aux_mmap_count==0, * see comments in perf_aux_output_begin(). * - * Since this is happening on a event-local CPU, no trace is lost + * Since this is happening on an event-local CPU, no trace is lost * while restarting. */ if (sd->restart) @@ -4827,7 +4827,7 @@ __perf_read(struct perf_event *event, char __user *buf, size_t count) int ret; /* - * Return end-of-file for a read on a event that is in + * Return end-of-file for a read on an event that is in * error state (i.e. because it was pinned but it couldn't be * scheduled on to the CPU at some point). */ @@ -5273,11 +5273,11 @@ unlock: } EXPORT_SYMBOL_GPL(perf_event_update_userpage); -static int perf_mmap_fault(struct vm_fault *vmf) +static vm_fault_t perf_mmap_fault(struct vm_fault *vmf) { struct perf_event *event = vmf->vma->vm_file->private_data; struct ring_buffer *rb; - int ret = VM_FAULT_SIGBUS; + vm_fault_t ret = VM_FAULT_SIGBUS; if (vmf->flags & FAULT_FLAG_MKWRITE) { if (vmf->pgoff == 0) @@ -9904,7 +9904,7 @@ enabled: } /* - * Allocate and initialize a event structure + * Allocate and initialize an event structure */ static struct perf_event * perf_event_alloc(struct perf_event_attr *attr, int cpu, @@ -11235,7 +11235,7 @@ const struct perf_event_attr *perf_event_attrs(struct perf_event *event) } /* - * Inherit a event from parent task to child task. + * Inherit an event from parent task to child task. * * Returns: * - valid pointer on success diff --git a/kernel/events/hw_breakpoint.c b/kernel/events/hw_breakpoint.c index 6e28d2866be5..b3814fce5ecb 100644 --- a/kernel/events/hw_breakpoint.c +++ b/kernel/events/hw_breakpoint.c @@ -345,13 +345,13 @@ void release_bp_slot(struct perf_event *bp) mutex_unlock(&nr_bp_mutex); } -static int __modify_bp_slot(struct perf_event *bp, u64 old_type) +static int __modify_bp_slot(struct perf_event *bp, u64 old_type, u64 new_type) { int err; __release_bp_slot(bp, old_type); - err = __reserve_bp_slot(bp, bp->attr.bp_type); + err = __reserve_bp_slot(bp, new_type); if (err) { /* * Reserve the old_type slot back in case @@ -367,12 +367,12 @@ static int __modify_bp_slot(struct perf_event *bp, u64 old_type) return err; } -static int modify_bp_slot(struct perf_event *bp, u64 old_type) +static int modify_bp_slot(struct perf_event *bp, u64 old_type, u64 new_type) { int ret; mutex_lock(&nr_bp_mutex); - ret = __modify_bp_slot(bp, old_type); + ret = __modify_bp_slot(bp, old_type, new_type); mutex_unlock(&nr_bp_mutex); return ret; } @@ -400,16 +400,18 @@ int dbg_release_bp_slot(struct perf_event *bp) return 0; } -static int validate_hw_breakpoint(struct perf_event *bp) +static int hw_breakpoint_parse(struct perf_event *bp, + const struct perf_event_attr *attr, + struct arch_hw_breakpoint *hw) { - int ret; + int err; - ret = arch_validate_hwbkpt_settings(bp); - if (ret) - return ret; + err = hw_breakpoint_arch_parse(bp, attr, hw); + if (err) + return err; - if (arch_check_bp_in_kernelspace(bp)) { - if (bp->attr.exclude_kernel) + if (arch_check_bp_in_kernelspace(hw)) { + if (attr->exclude_kernel) return -EINVAL; /* * Don't let unprivileged users set a breakpoint in the trap @@ -424,19 +426,22 @@ static int validate_hw_breakpoint(struct perf_event *bp) int register_perf_hw_breakpoint(struct perf_event *bp) { - int ret; - - ret = reserve_bp_slot(bp); - if (ret) - return ret; + struct arch_hw_breakpoint hw; + int err; - ret = validate_hw_breakpoint(bp); + err = reserve_bp_slot(bp); + if (err) + return err; - /* if arch_validate_hwbkpt_settings() fails then release bp slot */ - if (ret) + err = hw_breakpoint_parse(bp, &bp->attr, &hw); + if (err) { release_bp_slot(bp); + return err; + } - return ret; + bp->hw.info = hw; + + return 0; } /** @@ -456,35 +461,44 @@ register_user_hw_breakpoint(struct perf_event_attr *attr, } EXPORT_SYMBOL_GPL(register_user_hw_breakpoint); +static void hw_breakpoint_copy_attr(struct perf_event_attr *to, + struct perf_event_attr *from) +{ + to->bp_addr = from->bp_addr; + to->bp_type = from->bp_type; + to->bp_len = from->bp_len; + to->disabled = from->disabled; +} + int modify_user_hw_breakpoint_check(struct perf_event *bp, struct perf_event_attr *attr, bool check) { - u64 old_addr = bp->attr.bp_addr; - u64 old_len = bp->attr.bp_len; - int old_type = bp->attr.bp_type; - bool modify = attr->bp_type != old_type; - int err = 0; + struct arch_hw_breakpoint hw; + int err; - bp->attr.bp_addr = attr->bp_addr; - bp->attr.bp_type = attr->bp_type; - bp->attr.bp_len = attr->bp_len; + err = hw_breakpoint_parse(bp, attr, &hw); + if (err) + return err; - if (check && memcmp(&bp->attr, attr, sizeof(*attr))) - return -EINVAL; + if (check) { + struct perf_event_attr old_attr; - err = validate_hw_breakpoint(bp); - if (!err && modify) - err = modify_bp_slot(bp, old_type); + old_attr = bp->attr; + hw_breakpoint_copy_attr(&old_attr, attr); + if (memcmp(&old_attr, attr, sizeof(*attr))) + return -EINVAL; + } - if (err) { - bp->attr.bp_addr = old_addr; - bp->attr.bp_type = old_type; - bp->attr.bp_len = old_len; - return err; + if (bp->attr.bp_type != attr->bp_type) { + err = modify_bp_slot(bp, bp->attr.bp_type, attr->bp_type); + if (err) + return err; } - bp->attr.disabled = attr->disabled; + hw_breakpoint_copy_attr(&bp->attr, attr); + bp->hw.info = hw; + return 0; } diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index ccc579a7d32e..aed1ba569954 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -918,7 +918,7 @@ int uprobe_register(struct inode *inode, loff_t offset, struct uprobe_consumer * EXPORT_SYMBOL_GPL(uprobe_register); /* - * uprobe_apply - unregister a already registered probe. + * uprobe_apply - unregister an already registered probe. * @inode: the file in which the probe has to be removed. * @offset: offset from the start of the file. * @uc: consumer which wants to add more or remove some breakpoints @@ -947,7 +947,7 @@ int uprobe_apply(struct inode *inode, loff_t offset, } /* - * uprobe_unregister - unregister a already registered probe. + * uprobe_unregister - unregister an already registered probe. * @inode: the file in which the probe has to be removed. * @offset: offset from the start of the file. * @uc: identify which probe if multiple probes are colocated. @@ -1403,7 +1403,7 @@ static struct return_instance *free_ret_instance(struct return_instance *ri) /* * Called with no locks held. - * Called in context of a exiting or a exec-ing thread. + * Called in context of an exiting or an exec-ing thread. */ void uprobe_free_utask(struct task_struct *t) { diff --git a/kernel/fail_function.c b/kernel/fail_function.c index 5349c91c2298..bc80a4e268c0 100644 --- a/kernel/fail_function.c +++ b/kernel/fail_function.c @@ -184,9 +184,6 @@ static int fei_kprobe_handler(struct kprobe *kp, struct pt_regs *regs) if (should_fail(&fei_fault_attr, 1)) { regs_set_return_value(regs, attr->retval); override_function_with_return(regs); - /* Kprobe specific fixup */ - reset_current_kprobe(); - preempt_enable_no_resched(); return 1; } diff --git a/kernel/fork.c b/kernel/fork.c index 1b27babc4c78..9d8d0e016fc6 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -2276,6 +2276,8 @@ static void sighand_ctor(void *data) void __init proc_caches_init(void) { + unsigned int mm_size; + sighand_cachep = kmem_cache_create("sighand_cache", sizeof(struct sighand_struct), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_TYPESAFE_BY_RCU| @@ -2292,15 +2294,16 @@ void __init proc_caches_init(void) sizeof(struct fs_struct), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT, NULL); + /* - * FIXME! The "sizeof(struct mm_struct)" currently includes the - * whole struct cpumask for the OFFSTACK case. We could change - * this to *only* allocate as much of it as required by the - * maximum number of CPU's we can ever have. The cpumask_allocation - * is at the end of the structure, exactly for that reason. + * The mm_cpumask is located at the end of mm_struct, and is + * dynamically sized based on the maximum CPU number this system + * can have, taking hotplug into account (nr_cpu_ids). */ + mm_size = sizeof(struct mm_struct) + cpumask_size(); + mm_cachep = kmem_cache_create_usercopy("mm_struct", - sizeof(struct mm_struct), ARCH_MIN_MMSTRUCT_ALIGN, + mm_size, ARCH_MIN_MMSTRUCT_ALIGN, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT, offsetof(struct mm_struct, saved_auxv), sizeof_field(struct mm_struct, saved_auxv), diff --git a/kernel/irq/Kconfig b/kernel/irq/Kconfig index c6766f326072..5f3e2baefca9 100644 --- a/kernel/irq/Kconfig +++ b/kernel/irq/Kconfig @@ -134,7 +134,6 @@ config GENERIC_IRQ_DEBUGFS endmenu config GENERIC_IRQ_MULTI_HANDLER - depends on !MULTI_IRQ_HANDLER bool help Allow to specify the low level IRQ handler at run time. diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c index afc7f902d74a..578d0e5f1b5b 100644 --- a/kernel/irq/irqdesc.c +++ b/kernel/irq/irqdesc.c @@ -443,6 +443,7 @@ static void free_desc(unsigned int irq) * We free the descriptor, masks and stat fields via RCU. That * allows demultiplex interrupts to do rcu based management of * the child interrupts. + * This also allows us to use rcu in kstat_irqs_usr(). */ call_rcu(&desc->rcu, delayed_free_desc); } @@ -928,17 +929,17 @@ unsigned int kstat_irqs(unsigned int irq) * kstat_irqs_usr - Get the statistics for an interrupt * @irq: The interrupt number * - * Returns the sum of interrupt counts on all cpus since boot for - * @irq. Contrary to kstat_irqs() this can be called from any - * preemptible context. It's protected against concurrent removal of - * an interrupt descriptor when sparse irqs are enabled. + * Returns the sum of interrupt counts on all cpus since boot for @irq. + * Contrary to kstat_irqs() this can be called from any context. + * It uses rcu since a concurrent removal of an interrupt descriptor is + * observing an rcu grace period before delayed_free_desc()/irq_kobj_release(). */ unsigned int kstat_irqs_usr(unsigned int irq) { unsigned int sum; - irq_lock_sparse(); + rcu_read_lock(); sum = kstat_irqs(irq); - irq_unlock_sparse(); + rcu_read_unlock(); return sum; } diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 9a8b7ba9aa88..fb86146037a7 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -790,9 +790,19 @@ static irqreturn_t irq_forced_secondary_handler(int irq, void *dev_id) static int irq_wait_for_interrupt(struct irqaction *action) { - set_current_state(TASK_INTERRUPTIBLE); + for (;;) { + set_current_state(TASK_INTERRUPTIBLE); - while (!kthread_should_stop()) { + if (kthread_should_stop()) { + /* may need to run one last time */ + if (test_and_clear_bit(IRQTF_RUNTHREAD, + &action->thread_flags)) { + __set_current_state(TASK_RUNNING); + return 0; + } + __set_current_state(TASK_RUNNING); + return -1; + } if (test_and_clear_bit(IRQTF_RUNTHREAD, &action->thread_flags)) { @@ -800,10 +810,7 @@ static int irq_wait_for_interrupt(struct irqaction *action) return 0; } schedule(); - set_current_state(TASK_INTERRUPTIBLE); } - __set_current_state(TASK_RUNNING); - return -1; } /* @@ -1024,11 +1031,8 @@ static int irq_thread(void *data) /* * This is the regular exit path. __free_irq() is stopping the * thread via kthread_stop() after calling - * synchronize_irq(). So neither IRQTF_RUNTHREAD nor the - * oneshot mask bit can be set. We cannot verify that as we - * cannot touch the oneshot mask at this point anymore as - * __setup_irq() might have given out currents thread_mask - * again. + * synchronize_hardirq(). So neither IRQTF_RUNTHREAD nor the + * oneshot mask bit can be set. */ task_work_cancel(current, irq_thread_dtor); return 0; @@ -1251,8 +1255,10 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) /* * Protects against a concurrent __free_irq() call which might wait - * for synchronize_irq() to complete without holding the optional - * chip bus lock and desc->lock. + * for synchronize_hardirq() to complete without holding the optional + * chip bus lock and desc->lock. Also protects against handing out + * a recycled oneshot thread_mask bit while it's still in use by + * its previous owner. */ mutex_lock(&desc->request_mutex); @@ -1571,9 +1577,6 @@ static struct irqaction *__free_irq(struct irq_desc *desc, void *dev_id) WARN(in_interrupt(), "Trying to free IRQ %d from IRQ context!\n", irq); - if (!desc) - return NULL; - mutex_lock(&desc->request_mutex); chip_bus_lock(desc); raw_spin_lock_irqsave(&desc->lock, flags); @@ -1620,11 +1623,11 @@ static struct irqaction *__free_irq(struct irq_desc *desc, void *dev_id) /* * Drop bus_lock here so the changes which were done in the chip * callbacks above are synced out to the irq chips which hang - * behind a slow bus (I2C, SPI) before calling synchronize_irq(). + * behind a slow bus (I2C, SPI) before calling synchronize_hardirq(). * * Aside of that the bus_lock can also be taken from the threaded * handler in irq_finalize_oneshot() which results in a deadlock - * because synchronize_irq() would wait forever for the thread to + * because kthread_stop() would wait forever for the thread to * complete, which is blocked on the bus lock. * * The still held desc->request_mutex() protects against a @@ -1636,7 +1639,7 @@ static struct irqaction *__free_irq(struct irq_desc *desc, void *dev_id) unregister_handler_proc(irq, action); /* Make sure it's not being used on another CPU: */ - synchronize_irq(irq); + synchronize_hardirq(irq); #ifdef CONFIG_DEBUG_SHIRQ /* @@ -1645,7 +1648,7 @@ static struct irqaction *__free_irq(struct irq_desc *desc, void *dev_id) * is so by doing an extra call to the handler .... * * ( We do this after actually deregistering it, to make sure that a - * 'real' IRQ doesn't run in * parallel with our fake. ) + * 'real' IRQ doesn't run in parallel with our fake. ) */ if (action->flags & IRQF_SHARED) { local_irq_save(flags); @@ -1654,6 +1657,12 @@ static struct irqaction *__free_irq(struct irq_desc *desc, void *dev_id) } #endif + /* + * The action has already been removed above, but the thread writes + * its oneshot mask bit when it completes. Though request_mutex is + * held across this which prevents __setup_irq() from handing out + * the same bit to a newly requested action. + */ if (action->thread) { kthread_stop(action->thread); put_task_struct(action->thread); diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c index 37eda10f5c36..da9addb8d655 100644 --- a/kernel/irq/proc.c +++ b/kernel/irq/proc.c @@ -475,22 +475,24 @@ int show_interrupts(struct seq_file *p, void *v) seq_putc(p, '\n'); } - irq_lock_sparse(); + rcu_read_lock(); desc = irq_to_desc(i); if (!desc) goto outsparse; - raw_spin_lock_irqsave(&desc->lock, flags); - for_each_online_cpu(j) - any_count |= kstat_irqs_cpu(i, j); - action = desc->action; - if ((!action || irq_desc_is_chained(desc)) && !any_count) - goto out; + if (desc->kstat_irqs) + for_each_online_cpu(j) + any_count |= *per_cpu_ptr(desc->kstat_irqs, j); + + if ((!desc->action || irq_desc_is_chained(desc)) && !any_count) + goto outsparse; seq_printf(p, "%*d: ", prec, i); for_each_online_cpu(j) - seq_printf(p, "%10u ", kstat_irqs_cpu(i, j)); + seq_printf(p, "%10u ", desc->kstat_irqs ? + *per_cpu_ptr(desc->kstat_irqs, j) : 0); + raw_spin_lock_irqsave(&desc->lock, flags); if (desc->irq_data.chip) { if (desc->irq_data.chip->irq_print_chip) desc->irq_data.chip->irq_print_chip(&desc->irq_data, p); @@ -511,6 +513,7 @@ int show_interrupts(struct seq_file *p, void *v) if (desc->name) seq_printf(p, "-%-8s", desc->name); + action = desc->action; if (action) { seq_printf(p, " %s", action->name); while ((action = action->next) != NULL) @@ -518,10 +521,9 @@ int show_interrupts(struct seq_file *p, void *v) } seq_putc(p, '\n'); -out: raw_spin_unlock_irqrestore(&desc->lock, flags); outsparse: - irq_unlock_sparse(); + rcu_read_unlock(); return 0; } #endif diff --git a/kernel/kprobes.c b/kernel/kprobes.c index ea619021d901..ab257be4d924 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -627,8 +627,8 @@ static void optimize_kprobe(struct kprobe *p) (kprobe_disabled(p) || kprobes_all_disarmed)) return; - /* Both of break_handler and post_handler are not supported. */ - if (p->break_handler || p->post_handler) + /* kprobes with post_handler can not be optimized */ + if (p->post_handler) return; op = container_of(p, struct optimized_kprobe, kp); @@ -710,9 +710,7 @@ static void reuse_unused_kprobe(struct kprobe *ap) * there is still a relative jump) and disabled. */ op = container_of(ap, struct optimized_kprobe, kp); - if (unlikely(list_empty(&op->list))) - printk(KERN_WARNING "Warning: found a stray unused " - "aggrprobe@%p\n", ap->addr); + WARN_ON_ONCE(list_empty(&op->list)); /* Enable the probe again */ ap->flags &= ~KPROBE_FLAG_DISABLED; /* Optimize it again (remove from op->list) */ @@ -985,7 +983,8 @@ static int arm_kprobe_ftrace(struct kprobe *p) ret = ftrace_set_filter_ip(&kprobe_ftrace_ops, (unsigned long)p->addr, 0, 0); if (ret) { - pr_debug("Failed to arm kprobe-ftrace at %p (%d)\n", p->addr, ret); + pr_debug("Failed to arm kprobe-ftrace at %pS (%d)\n", + p->addr, ret); return ret; } @@ -1025,7 +1024,8 @@ static int disarm_kprobe_ftrace(struct kprobe *p) ret = ftrace_set_filter_ip(&kprobe_ftrace_ops, (unsigned long)p->addr, 1, 0); - WARN(ret < 0, "Failed to disarm kprobe-ftrace at %p (%d)\n", p->addr, ret); + WARN_ONCE(ret < 0, "Failed to disarm kprobe-ftrace at %pS (%d)\n", + p->addr, ret); return ret; } #else /* !CONFIG_KPROBES_ON_FTRACE */ @@ -1116,20 +1116,6 @@ static int aggr_fault_handler(struct kprobe *p, struct pt_regs *regs, } NOKPROBE_SYMBOL(aggr_fault_handler); -static int aggr_break_handler(struct kprobe *p, struct pt_regs *regs) -{ - struct kprobe *cur = __this_cpu_read(kprobe_instance); - int ret = 0; - - if (cur && cur->break_handler) { - if (cur->break_handler(cur, regs)) - ret = 1; - } - reset_kprobe_instance(); - return ret; -} -NOKPROBE_SYMBOL(aggr_break_handler); - /* Walks the list and increments nmissed count for multiprobe case */ void kprobes_inc_nmissed_count(struct kprobe *p) { @@ -1270,24 +1256,15 @@ static void cleanup_rp_inst(struct kretprobe *rp) } NOKPROBE_SYMBOL(cleanup_rp_inst); -/* -* Add the new probe to ap->list. Fail if this is the -* second jprobe at the address - two jprobes can't coexist -*/ +/* Add the new probe to ap->list */ static int add_new_kprobe(struct kprobe *ap, struct kprobe *p) { BUG_ON(kprobe_gone(ap) || kprobe_gone(p)); - if (p->break_handler || p->post_handler) + if (p->post_handler) unoptimize_kprobe(ap, true); /* Fall back to normal kprobe */ - if (p->break_handler) { - if (ap->break_handler) - return -EEXIST; - list_add_tail_rcu(&p->list, &ap->list); - ap->break_handler = aggr_break_handler; - } else - list_add_rcu(&p->list, &ap->list); + list_add_rcu(&p->list, &ap->list); if (p->post_handler && !ap->post_handler) ap->post_handler = aggr_post_handler; @@ -1310,8 +1287,6 @@ static void init_aggr_kprobe(struct kprobe *ap, struct kprobe *p) /* We don't care the kprobe which has gone. */ if (p->post_handler && !kprobe_gone(p)) ap->post_handler = aggr_post_handler; - if (p->break_handler && !kprobe_gone(p)) - ap->break_handler = aggr_break_handler; INIT_LIST_HEAD(&ap->list); INIT_HLIST_NODE(&ap->hlist); @@ -1706,8 +1681,6 @@ static int __unregister_kprobe_top(struct kprobe *p) goto disarmed; else { /* If disabling probe has special handlers, update aggrprobe */ - if (p->break_handler && !kprobe_gone(p)) - ap->break_handler = NULL; if (p->post_handler && !kprobe_gone(p)) { list_for_each_entry_rcu(list_p, &ap->list, list) { if ((list_p != p) && (list_p->post_handler)) @@ -1812,77 +1785,6 @@ unsigned long __weak arch_deref_entry_point(void *entry) return (unsigned long)entry; } -#if 0 -int register_jprobes(struct jprobe **jps, int num) -{ - int ret = 0, i; - - if (num <= 0) - return -EINVAL; - - for (i = 0; i < num; i++) { - ret = register_jprobe(jps[i]); - - if (ret < 0) { - if (i > 0) - unregister_jprobes(jps, i); - break; - } - } - - return ret; -} -EXPORT_SYMBOL_GPL(register_jprobes); - -int register_jprobe(struct jprobe *jp) -{ - unsigned long addr, offset; - struct kprobe *kp = &jp->kp; - - /* - * Verify probepoint as well as the jprobe handler are - * valid function entry points. - */ - addr = arch_deref_entry_point(jp->entry); - - if (kallsyms_lookup_size_offset(addr, NULL, &offset) && offset == 0 && - kprobe_on_func_entry(kp->addr, kp->symbol_name, kp->offset)) { - kp->pre_handler = setjmp_pre_handler; - kp->break_handler = longjmp_break_handler; - return register_kprobe(kp); - } - - return -EINVAL; -} -EXPORT_SYMBOL_GPL(register_jprobe); - -void unregister_jprobe(struct jprobe *jp) -{ - unregister_jprobes(&jp, 1); -} -EXPORT_SYMBOL_GPL(unregister_jprobe); - -void unregister_jprobes(struct jprobe **jps, int num) -{ - int i; - - if (num <= 0) - return; - mutex_lock(&kprobe_mutex); - for (i = 0; i < num; i++) - if (__unregister_kprobe_top(&jps[i]->kp) < 0) - jps[i]->kp.addr = NULL; - mutex_unlock(&kprobe_mutex); - - synchronize_sched(); - for (i = 0; i < num; i++) { - if (jps[i]->kp.addr) - __unregister_kprobe_bottom(&jps[i]->kp); - } -} -EXPORT_SYMBOL_GPL(unregister_jprobes); -#endif - #ifdef CONFIG_KRETPROBES /* * This kprobe pre_handler is registered with every kretprobe. When probe @@ -1982,7 +1884,6 @@ int register_kretprobe(struct kretprobe *rp) rp->kp.pre_handler = pre_handler_kretprobe; rp->kp.post_handler = NULL; rp->kp.fault_handler = NULL; - rp->kp.break_handler = NULL; /* Pre-allocate memory for max kretprobe instances */ if (rp->maxactive <= 0) { @@ -2105,7 +2006,6 @@ static void kill_kprobe(struct kprobe *p) list_for_each_entry_rcu(kp, &p->list, list) kp->flags |= KPROBE_FLAG_GONE; p->post_handler = NULL; - p->break_handler = NULL; kill_optimized_kprobe(p); } /* @@ -2169,11 +2069,12 @@ out: } EXPORT_SYMBOL_GPL(enable_kprobe); +/* Caller must NOT call this in usual path. This is only for critical case */ void dump_kprobe(struct kprobe *kp) { - printk(KERN_WARNING "Dumping kprobe:\n"); - printk(KERN_WARNING "Name: %s\nAddress: %p\nOffset: %x\n", - kp->symbol_name, kp->addr, kp->offset); + pr_err("Dumping kprobe:\n"); + pr_err("Name: %s\nOffset: %x\nAddress: %pS\n", + kp->symbol_name, kp->offset, kp->addr); } NOKPROBE_SYMBOL(dump_kprobe); @@ -2196,11 +2097,8 @@ static int __init populate_kprobe_blacklist(unsigned long *start, entry = arch_deref_entry_point((void *)*iter); if (!kernel_text_address(entry) || - !kallsyms_lookup_size_offset(entry, &size, &offset)) { - pr_err("Failed to find blacklist at %p\n", - (void *)entry); + !kallsyms_lookup_size_offset(entry, &size, &offset)) continue; - } ent = kmalloc(sizeof(*ent), GFP_KERNEL); if (!ent) @@ -2326,21 +2224,23 @@ static void report_probe(struct seq_file *pi, struct kprobe *p, const char *sym, int offset, char *modname, struct kprobe *pp) { char *kprobe_type; + void *addr = p->addr; if (p->pre_handler == pre_handler_kretprobe) kprobe_type = "r"; - else if (p->pre_handler == setjmp_pre_handler) - kprobe_type = "j"; else kprobe_type = "k"; + if (!kallsyms_show_value()) + addr = NULL; + if (sym) - seq_printf(pi, "%p %s %s+0x%x %s ", - p->addr, kprobe_type, sym, offset, + seq_printf(pi, "%px %s %s+0x%x %s ", + addr, kprobe_type, sym, offset, (modname ? modname : " ")); - else - seq_printf(pi, "%p %s %p ", - p->addr, kprobe_type, p->addr); + else /* try to use %pS */ + seq_printf(pi, "%px %s %pS ", + addr, kprobe_type, p->addr); if (!pp) pp = p; @@ -2428,8 +2328,16 @@ static int kprobe_blacklist_seq_show(struct seq_file *m, void *v) struct kprobe_blacklist_entry *ent = list_entry(v, struct kprobe_blacklist_entry, list); - seq_printf(m, "0x%px-0x%px\t%ps\n", (void *)ent->start_addr, - (void *)ent->end_addr, (void *)ent->start_addr); + /* + * If /proc/kallsyms is not showing kernel address, we won't + * show them here either. + */ + if (!kallsyms_show_value()) + seq_printf(m, "0x%px-0x%px\t%ps\n", NULL, NULL, + (void *)ent->start_addr); + else + seq_printf(m, "0x%px-0x%px\t%ps\n", (void *)ent->start_addr, + (void *)ent->end_addr, (void *)ent->start_addr); return 0; } @@ -2611,7 +2519,7 @@ static int __init debugfs_kprobe_init(void) if (!dir) return -ENOMEM; - file = debugfs_create_file("list", 0444, dir, NULL, + file = debugfs_create_file("list", 0400, dir, NULL, &debugfs_kprobes_operations); if (!file) goto error; @@ -2621,7 +2529,7 @@ static int __init debugfs_kprobe_init(void) if (!file) goto error; - file = debugfs_create_file("blacklist", 0444, dir, NULL, + file = debugfs_create_file("blacklist", 0400, dir, NULL, &debugfs_kprobe_blacklist_ops); if (!file) goto error; @@ -2637,6 +2545,3 @@ late_initcall(debugfs_kprobe_init); #endif /* CONFIG_DEBUG_FS */ module_init(init_kprobes); - -/* defined in arch/.../kernel/kprobes.c */ -EXPORT_SYMBOL_GPL(jprobe_return); diff --git a/kernel/kthread.c b/kernel/kthread.c index 486dedbd9af5..087d18d771b5 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -190,7 +190,7 @@ static void __kthread_parkme(struct kthread *self) if (!test_bit(KTHREAD_SHOULD_PARK, &self->flags)) break; - complete_all(&self->parked); + complete(&self->parked); schedule(); } __set_current_state(TASK_RUNNING); @@ -471,7 +471,6 @@ void kthread_unpark(struct task_struct *k) if (test_bit(KTHREAD_IS_PER_CPU, &kthread->flags)) __kthread_bind(k, kthread->cpu, TASK_PARKED); - reinit_completion(&kthread->parked); clear_bit(KTHREAD_SHOULD_PARK, &kthread->flags); /* * __kthread_parkme() will either see !SHOULD_PARK or get the wakeup. @@ -499,6 +498,9 @@ int kthread_park(struct task_struct *k) if (WARN_ON(k->flags & PF_EXITING)) return -ENOSYS; + if (WARN_ON_ONCE(test_bit(KTHREAD_SHOULD_PARK, &kthread->flags))) + return -EBUSY; + set_bit(KTHREAD_SHOULD_PARK, &kthread->flags); if (k != current) { wake_up_process(k); diff --git a/kernel/locking/locktorture.c b/kernel/locking/locktorture.c index 8402b3349dca..57bef4fbfb31 100644 --- a/kernel/locking/locktorture.c +++ b/kernel/locking/locktorture.c @@ -21,6 +21,9 @@ * Davidlohr Bueso <dave@stgolabs.net> * Based on kernel/rcu/torture.c. */ + +#define pr_fmt(fmt) fmt + #include <linux/kernel.h> #include <linux/module.h> #include <linux/kthread.h> @@ -57,7 +60,7 @@ torture_param(int, shutdown_secs, 0, "Shutdown time (j), <= zero to disable."); torture_param(int, stat_interval, 60, "Number of seconds between stats printk()s"); torture_param(int, stutter, 5, "Number of jiffies to run/halt test, 0=disable"); -torture_param(bool, verbose, true, +torture_param(int, verbose, 1, "Enable verbose debugging printk()s"); static char *torture_type = "spin_lock"; diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c index 87331565e505..70178f6ffdc4 100644 --- a/kernel/power/suspend.c +++ b/kernel/power/suspend.c @@ -92,7 +92,7 @@ static void s2idle_enter(void) /* Push all the CPUs into the idle loop. */ wake_up_all_idle_cpus(); /* Make the current CPU wait so it can enter the idle loop too. */ - swait_event(s2idle_wait_head, + swait_event_exclusive(s2idle_wait_head, s2idle_state == S2IDLE_STATE_WAKE); cpuidle_pause(); @@ -160,7 +160,7 @@ void s2idle_wake(void) raw_spin_lock_irqsave(&s2idle_lock, flags); if (s2idle_state > S2IDLE_STATE_NONE) { s2idle_state = S2IDLE_STATE_WAKE; - swake_up(&s2idle_wait_head); + swake_up_one(&s2idle_wait_head); } raw_spin_unlock_irqrestore(&s2idle_lock, flags); } diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h index 40cea6735c2d..4d04683c31b2 100644 --- a/kernel/rcu/rcu.h +++ b/kernel/rcu/rcu.h @@ -91,7 +91,17 @@ static inline void rcu_seq_end(unsigned long *sp) WRITE_ONCE(*sp, rcu_seq_endval(sp)); } -/* Take a snapshot of the update side's sequence number. */ +/* + * rcu_seq_snap - Take a snapshot of the update side's sequence number. + * + * This function returns the earliest value of the grace-period sequence number + * that will indicate that a full grace period has elapsed since the current + * time. Once the grace-period sequence number has reached this value, it will + * be safe to invoke all callbacks that have been registered prior to the + * current time. This value is the current grace-period number plus two to the + * power of the number of low-order bits reserved for state, then rounded up to + * the next value in which the state bits are all zero. + */ static inline unsigned long rcu_seq_snap(unsigned long *sp) { unsigned long s; @@ -108,6 +118,15 @@ static inline unsigned long rcu_seq_current(unsigned long *sp) } /* + * Given a snapshot from rcu_seq_snap(), determine whether or not the + * corresponding update-side operation has started. + */ +static inline bool rcu_seq_started(unsigned long *sp, unsigned long s) +{ + return ULONG_CMP_LT((s - 1) & ~RCU_SEQ_STATE_MASK, READ_ONCE(*sp)); +} + +/* * Given a snapshot from rcu_seq_snap(), determine whether or not a * full update-side operation has occurred. */ @@ -117,6 +136,45 @@ static inline bool rcu_seq_done(unsigned long *sp, unsigned long s) } /* + * Has a grace period completed since the time the old gp_seq was collected? + */ +static inline bool rcu_seq_completed_gp(unsigned long old, unsigned long new) +{ + return ULONG_CMP_LT(old, new & ~RCU_SEQ_STATE_MASK); +} + +/* + * Has a grace period started since the time the old gp_seq was collected? + */ +static inline bool rcu_seq_new_gp(unsigned long old, unsigned long new) +{ + return ULONG_CMP_LT((old + RCU_SEQ_STATE_MASK) & ~RCU_SEQ_STATE_MASK, + new); +} + +/* + * Roughly how many full grace periods have elapsed between the collection + * of the two specified grace periods? + */ +static inline unsigned long rcu_seq_diff(unsigned long new, unsigned long old) +{ + unsigned long rnd_diff; + + if (old == new) + return 0; + /* + * Compute the number of grace periods (still shifted up), plus + * one if either of new and old is not an exact grace period. + */ + rnd_diff = (new & ~RCU_SEQ_STATE_MASK) - + ((old + RCU_SEQ_STATE_MASK) & ~RCU_SEQ_STATE_MASK) + + ((new & RCU_SEQ_STATE_MASK) || (old & RCU_SEQ_STATE_MASK)); + if (ULONG_CMP_GE(RCU_SEQ_STATE_MASK, rnd_diff)) + return 1; /* Definitely no grace period has elapsed. */ + return ((rnd_diff - RCU_SEQ_STATE_MASK - 1) >> RCU_SEQ_CTR_SHIFT) + 2; +} + +/* * debug_rcu_head_queue()/debug_rcu_head_unqueue() are used internally * by call_rcu() and rcu callback execution, and are therefore not part of the * RCU API. Leaving in rcupdate.h because they are used by all RCU flavors. @@ -276,6 +334,9 @@ static inline void rcu_init_levelspread(int *levelspread, const int *levelcnt) /* Is this rcu_node a leaf? */ #define rcu_is_leaf_node(rnp) ((rnp)->level == rcu_num_lvls - 1) +/* Is this rcu_node the last leaf? */ +#define rcu_is_last_leaf_node(rsp, rnp) ((rnp) == &(rsp)->node[rcu_num_nodes - 1]) + /* * Do a full breadth-first scan of the rcu_node structures for the * specified rcu_state structure. @@ -405,8 +466,7 @@ enum rcutorture_type { #if defined(CONFIG_TREE_RCU) || defined(CONFIG_PREEMPT_RCU) void rcutorture_get_gp_data(enum rcutorture_type test_type, int *flags, - unsigned long *gpnum, unsigned long *completed); -void rcutorture_record_test_transition(void); + unsigned long *gp_seq); void rcutorture_record_progress(unsigned long vernum); void do_trace_rcu_torture_read(const char *rcutorturename, struct rcu_head *rhp, @@ -415,15 +475,11 @@ void do_trace_rcu_torture_read(const char *rcutorturename, unsigned long c); #else static inline void rcutorture_get_gp_data(enum rcutorture_type test_type, - int *flags, - unsigned long *gpnum, - unsigned long *completed) + int *flags, unsigned long *gp_seq) { *flags = 0; - *gpnum = 0; - *completed = 0; + *gp_seq = 0; } -static inline void rcutorture_record_test_transition(void) { } static inline void rcutorture_record_progress(unsigned long vernum) { } #ifdef CONFIG_RCU_TRACE void do_trace_rcu_torture_read(const char *rcutorturename, @@ -441,31 +497,26 @@ void do_trace_rcu_torture_read(const char *rcutorturename, static inline void srcutorture_get_gp_data(enum rcutorture_type test_type, struct srcu_struct *sp, int *flags, - unsigned long *gpnum, - unsigned long *completed) + unsigned long *gp_seq) { if (test_type != SRCU_FLAVOR) return; *flags = 0; - *completed = sp->srcu_idx; - *gpnum = *completed; + *gp_seq = sp->srcu_idx; } #elif defined(CONFIG_TREE_SRCU) void srcutorture_get_gp_data(enum rcutorture_type test_type, struct srcu_struct *sp, int *flags, - unsigned long *gpnum, unsigned long *completed); + unsigned long *gp_seq); #endif #ifdef CONFIG_TINY_RCU -static inline unsigned long rcu_batches_started(void) { return 0; } -static inline unsigned long rcu_batches_started_bh(void) { return 0; } -static inline unsigned long rcu_batches_started_sched(void) { return 0; } -static inline unsigned long rcu_batches_completed(void) { return 0; } -static inline unsigned long rcu_batches_completed_bh(void) { return 0; } -static inline unsigned long rcu_batches_completed_sched(void) { return 0; } +static inline unsigned long rcu_get_gp_seq(void) { return 0; } +static inline unsigned long rcu_bh_get_gp_seq(void) { return 0; } +static inline unsigned long rcu_sched_get_gp_seq(void) { return 0; } static inline unsigned long rcu_exp_batches_completed(void) { return 0; } static inline unsigned long rcu_exp_batches_completed_sched(void) { return 0; } static inline unsigned long @@ -474,19 +525,16 @@ static inline void rcu_force_quiescent_state(void) { } static inline void rcu_bh_force_quiescent_state(void) { } static inline void rcu_sched_force_quiescent_state(void) { } static inline void show_rcu_gp_kthreads(void) { } +static inline int rcu_get_gp_kthreads_prio(void) { return 0; } #else /* #ifdef CONFIG_TINY_RCU */ -extern unsigned long rcutorture_testseq; -extern unsigned long rcutorture_vernum; -unsigned long rcu_batches_started(void); -unsigned long rcu_batches_started_bh(void); -unsigned long rcu_batches_started_sched(void); -unsigned long rcu_batches_completed(void); -unsigned long rcu_batches_completed_bh(void); -unsigned long rcu_batches_completed_sched(void); +unsigned long rcu_get_gp_seq(void); +unsigned long rcu_bh_get_gp_seq(void); +unsigned long rcu_sched_get_gp_seq(void); unsigned long rcu_exp_batches_completed(void); unsigned long rcu_exp_batches_completed_sched(void); unsigned long srcu_batches_completed(struct srcu_struct *sp); void show_rcu_gp_kthreads(void); +int rcu_get_gp_kthreads_prio(void); void rcu_force_quiescent_state(void); void rcu_bh_force_quiescent_state(void); void rcu_sched_force_quiescent_state(void); diff --git a/kernel/rcu/rcuperf.c b/kernel/rcu/rcuperf.c index e232846516b3..34244523550e 100644 --- a/kernel/rcu/rcuperf.c +++ b/kernel/rcu/rcuperf.c @@ -19,6 +19,9 @@ * * Authors: Paul E. McKenney <paulmck@us.ibm.com> */ + +#define pr_fmt(fmt) fmt + #include <linux/types.h> #include <linux/kernel.h> #include <linux/init.h> @@ -88,7 +91,7 @@ torture_param(int, nreaders, -1, "Number of RCU reader threads"); torture_param(int, nwriters, -1, "Number of RCU updater threads"); torture_param(bool, shutdown, !IS_ENABLED(MODULE), "Shutdown at end of performance tests."); -torture_param(bool, verbose, true, "Enable verbose debugging printk()s"); +torture_param(int, verbose, 1, "Enable verbose debugging printk()s"); torture_param(int, writer_holdoff, 0, "Holdoff (us) between GPs, zero to disable"); static char *perf_type = "rcu"; @@ -135,8 +138,8 @@ struct rcu_perf_ops { void (*cleanup)(void); int (*readlock)(void); void (*readunlock)(int idx); - unsigned long (*started)(void); - unsigned long (*completed)(void); + unsigned long (*get_gp_seq)(void); + unsigned long (*gp_diff)(unsigned long new, unsigned long old); unsigned long (*exp_completed)(void); void (*async)(struct rcu_head *head, rcu_callback_t func); void (*gp_barrier)(void); @@ -176,8 +179,8 @@ static struct rcu_perf_ops rcu_ops = { .init = rcu_sync_perf_init, .readlock = rcu_perf_read_lock, .readunlock = rcu_perf_read_unlock, - .started = rcu_batches_started, - .completed = rcu_batches_completed, + .get_gp_seq = rcu_get_gp_seq, + .gp_diff = rcu_seq_diff, .exp_completed = rcu_exp_batches_completed, .async = call_rcu, .gp_barrier = rcu_barrier, @@ -206,8 +209,8 @@ static struct rcu_perf_ops rcu_bh_ops = { .init = rcu_sync_perf_init, .readlock = rcu_bh_perf_read_lock, .readunlock = rcu_bh_perf_read_unlock, - .started = rcu_batches_started_bh, - .completed = rcu_batches_completed_bh, + .get_gp_seq = rcu_bh_get_gp_seq, + .gp_diff = rcu_seq_diff, .exp_completed = rcu_exp_batches_completed_sched, .async = call_rcu_bh, .gp_barrier = rcu_barrier_bh, @@ -263,8 +266,8 @@ static struct rcu_perf_ops srcu_ops = { .init = rcu_sync_perf_init, .readlock = srcu_perf_read_lock, .readunlock = srcu_perf_read_unlock, - .started = NULL, - .completed = srcu_perf_completed, + .get_gp_seq = srcu_perf_completed, + .gp_diff = rcu_seq_diff, .exp_completed = srcu_perf_completed, .async = srcu_call_rcu, .gp_barrier = srcu_rcu_barrier, @@ -292,8 +295,8 @@ static struct rcu_perf_ops srcud_ops = { .cleanup = srcu_sync_perf_cleanup, .readlock = srcu_perf_read_lock, .readunlock = srcu_perf_read_unlock, - .started = NULL, - .completed = srcu_perf_completed, + .get_gp_seq = srcu_perf_completed, + .gp_diff = rcu_seq_diff, .exp_completed = srcu_perf_completed, .async = srcu_call_rcu, .gp_barrier = srcu_rcu_barrier, @@ -322,8 +325,8 @@ static struct rcu_perf_ops sched_ops = { .init = rcu_sync_perf_init, .readlock = sched_perf_read_lock, .readunlock = sched_perf_read_unlock, - .started = rcu_batches_started_sched, - .completed = rcu_batches_completed_sched, + .get_gp_seq = rcu_sched_get_gp_seq, + .gp_diff = rcu_seq_diff, .exp_completed = rcu_exp_batches_completed_sched, .async = call_rcu_sched, .gp_barrier = rcu_barrier_sched, @@ -350,8 +353,8 @@ static struct rcu_perf_ops tasks_ops = { .init = rcu_sync_perf_init, .readlock = tasks_perf_read_lock, .readunlock = tasks_perf_read_unlock, - .started = rcu_no_completed, - .completed = rcu_no_completed, + .get_gp_seq = rcu_no_completed, + .gp_diff = rcu_seq_diff, .async = call_rcu_tasks, .gp_barrier = rcu_barrier_tasks, .sync = synchronize_rcu_tasks, @@ -359,9 +362,11 @@ static struct rcu_perf_ops tasks_ops = { .name = "tasks" }; -static bool __maybe_unused torturing_tasks(void) +static unsigned long rcuperf_seq_diff(unsigned long new, unsigned long old) { - return cur_ops == &tasks_ops; + if (!cur_ops->gp_diff) + return new - old; + return cur_ops->gp_diff(new, old); } /* @@ -444,8 +449,7 @@ rcu_perf_writer(void *arg) b_rcu_perf_writer_started = cur_ops->exp_completed() / 2; } else { - b_rcu_perf_writer_started = - cur_ops->completed(); + b_rcu_perf_writer_started = cur_ops->get_gp_seq(); } } @@ -502,7 +506,7 @@ retry: cur_ops->exp_completed() / 2; } else { b_rcu_perf_writer_finished = - cur_ops->completed(); + cur_ops->get_gp_seq(); } if (shutdown) { smp_mb(); /* Assign before wake. */ @@ -527,7 +531,7 @@ retry: return 0; } -static inline void +static void rcu_perf_print_module_parms(struct rcu_perf_ops *cur_ops, const char *tag) { pr_alert("%s" PERF_FLAG @@ -582,8 +586,8 @@ rcu_perf_cleanup(void) t_rcu_perf_writer_finished - t_rcu_perf_writer_started, ngps, - b_rcu_perf_writer_finished - - b_rcu_perf_writer_started); + rcuperf_seq_diff(b_rcu_perf_writer_finished, + b_rcu_perf_writer_started)); for (i = 0; i < nrealwriters; i++) { if (!writer_durations) break; @@ -671,12 +675,11 @@ rcu_perf_init(void) break; } if (i == ARRAY_SIZE(perf_ops)) { - pr_alert("rcu-perf: invalid perf type: \"%s\"\n", - perf_type); + pr_alert("rcu-perf: invalid perf type: \"%s\"\n", perf_type); pr_alert("rcu-perf types:"); for (i = 0; i < ARRAY_SIZE(perf_ops); i++) - pr_alert(" %s", perf_ops[i]->name); - pr_alert("\n"); + pr_cont(" %s", perf_ops[i]->name); + pr_cont("\n"); firsterr = -EINVAL; goto unwind; } diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c index 42fcb7f05fac..c596c6f1e457 100644 --- a/kernel/rcu/rcutorture.c +++ b/kernel/rcu/rcutorture.c @@ -22,6 +22,9 @@ * * See also: Documentation/RCU/torture.txt */ + +#define pr_fmt(fmt) fmt + #include <linux/types.h> #include <linux/kernel.h> #include <linux/init.h> @@ -52,6 +55,7 @@ #include <linux/torture.h> #include <linux/vmalloc.h> #include <linux/sched/debug.h> +#include <linux/sched/sysctl.h> #include "rcu.h" @@ -59,6 +63,19 @@ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Paul E. McKenney <paulmck@us.ibm.com> and Josh Triplett <josh@joshtriplett.org>"); +/* Bits for ->extendables field, extendables param, and related definitions. */ +#define RCUTORTURE_RDR_SHIFT 8 /* Put SRCU index in upper bits. */ +#define RCUTORTURE_RDR_MASK ((1 << RCUTORTURE_RDR_SHIFT) - 1) +#define RCUTORTURE_RDR_BH 0x1 /* Extend readers by disabling bh. */ +#define RCUTORTURE_RDR_IRQ 0x2 /* ... disabling interrupts. */ +#define RCUTORTURE_RDR_PREEMPT 0x4 /* ... disabling preemption. */ +#define RCUTORTURE_RDR_RCU 0x8 /* ... entering another RCU reader. */ +#define RCUTORTURE_RDR_NBITS 4 /* Number of bits defined above. */ +#define RCUTORTURE_MAX_EXTEND (RCUTORTURE_RDR_BH | RCUTORTURE_RDR_IRQ | \ + RCUTORTURE_RDR_PREEMPT) +#define RCUTORTURE_RDR_MAX_LOOPS 0x7 /* Maximum reader extensions. */ + /* Must be power of two minus one. */ + torture_param(int, cbflood_inter_holdoff, HZ, "Holdoff between floods (jiffies)"); torture_param(int, cbflood_intra_holdoff, 1, @@ -66,6 +83,8 @@ torture_param(int, cbflood_intra_holdoff, 1, torture_param(int, cbflood_n_burst, 3, "# bursts in flood, zero to disable"); torture_param(int, cbflood_n_per_burst, 20000, "# callbacks per burst in flood"); +torture_param(int, extendables, RCUTORTURE_MAX_EXTEND, + "Extend readers by disabling bh (1), irqs (2), or preempt (4)"); torture_param(int, fqs_duration, 0, "Duration of fqs bursts (us), 0 to disable"); torture_param(int, fqs_holdoff, 0, "Holdoff time within fqs bursts (us)"); @@ -84,7 +103,7 @@ torture_param(int, object_debug, 0, "Enable debug-object double call_rcu() testing"); torture_param(int, onoff_holdoff, 0, "Time after boot before CPU hotplugs (s)"); torture_param(int, onoff_interval, 0, - "Time between CPU hotplugs (s), 0=disable"); + "Time between CPU hotplugs (jiffies), 0=disable"); torture_param(int, shuffle_interval, 3, "Number of seconds between shuffles"); torture_param(int, shutdown_secs, 0, "Shutdown time (s), <= zero to disable."); torture_param(int, stall_cpu, 0, "Stall duration (s), zero to disable."); @@ -101,7 +120,7 @@ torture_param(int, test_boost_interval, 7, "Interval between boost tests, seconds."); torture_param(bool, test_no_idle_hz, true, "Test support for tickless idle CPUs"); -torture_param(bool, verbose, true, +torture_param(int, verbose, 1, "Enable verbose debugging printk()s"); static char *torture_type = "rcu"; @@ -148,9 +167,9 @@ static long n_rcu_torture_boost_ktrerror; static long n_rcu_torture_boost_rterror; static long n_rcu_torture_boost_failure; static long n_rcu_torture_boosts; -static long n_rcu_torture_timers; +static atomic_long_t n_rcu_torture_timers; static long n_barrier_attempts; -static long n_barrier_successes; +static long n_barrier_successes; /* did rcu_barrier test succeed? */ static atomic_long_t n_cbfloods; static struct list_head rcu_torture_removed; @@ -261,8 +280,8 @@ struct rcu_torture_ops { int (*readlock)(void); void (*read_delay)(struct torture_random_state *rrsp); void (*readunlock)(int idx); - unsigned long (*started)(void); - unsigned long (*completed)(void); + unsigned long (*get_gp_seq)(void); + unsigned long (*gp_diff)(unsigned long new, unsigned long old); void (*deferred_free)(struct rcu_torture *p); void (*sync)(void); void (*exp_sync)(void); @@ -274,6 +293,8 @@ struct rcu_torture_ops { void (*stats)(void); int irq_capable; int can_boost; + int extendables; + int ext_irq_conflict; const char *name; }; @@ -302,10 +323,10 @@ static void rcu_read_delay(struct torture_random_state *rrsp) * force_quiescent_state. */ if (!(torture_random(rrsp) % (nrealreaders * 2000 * longdelay_ms))) { - started = cur_ops->completed(); + started = cur_ops->get_gp_seq(); ts = rcu_trace_clock_local(); mdelay(longdelay_ms); - completed = cur_ops->completed(); + completed = cur_ops->get_gp_seq(); do_trace_rcu_torture_read(cur_ops->name, NULL, ts, started, completed); } @@ -397,8 +418,8 @@ static struct rcu_torture_ops rcu_ops = { .readlock = rcu_torture_read_lock, .read_delay = rcu_read_delay, .readunlock = rcu_torture_read_unlock, - .started = rcu_batches_started, - .completed = rcu_batches_completed, + .get_gp_seq = rcu_get_gp_seq, + .gp_diff = rcu_seq_diff, .deferred_free = rcu_torture_deferred_free, .sync = synchronize_rcu, .exp_sync = synchronize_rcu_expedited, @@ -439,8 +460,8 @@ static struct rcu_torture_ops rcu_bh_ops = { .readlock = rcu_bh_torture_read_lock, .read_delay = rcu_read_delay, /* just reuse rcu's version. */ .readunlock = rcu_bh_torture_read_unlock, - .started = rcu_batches_started_bh, - .completed = rcu_batches_completed_bh, + .get_gp_seq = rcu_bh_get_gp_seq, + .gp_diff = rcu_seq_diff, .deferred_free = rcu_bh_torture_deferred_free, .sync = synchronize_rcu_bh, .exp_sync = synchronize_rcu_bh_expedited, @@ -449,6 +470,8 @@ static struct rcu_torture_ops rcu_bh_ops = { .fqs = rcu_bh_force_quiescent_state, .stats = NULL, .irq_capable = 1, + .extendables = (RCUTORTURE_RDR_BH | RCUTORTURE_RDR_IRQ), + .ext_irq_conflict = RCUTORTURE_RDR_RCU, .name = "rcu_bh" }; @@ -483,8 +506,7 @@ static struct rcu_torture_ops rcu_busted_ops = { .readlock = rcu_torture_read_lock, .read_delay = rcu_read_delay, /* just reuse rcu's version. */ .readunlock = rcu_torture_read_unlock, - .started = rcu_no_completed, - .completed = rcu_no_completed, + .get_gp_seq = rcu_no_completed, .deferred_free = rcu_busted_torture_deferred_free, .sync = synchronize_rcu_busted, .exp_sync = synchronize_rcu_busted, @@ -572,8 +594,7 @@ static struct rcu_torture_ops srcu_ops = { .readlock = srcu_torture_read_lock, .read_delay = srcu_read_delay, .readunlock = srcu_torture_read_unlock, - .started = NULL, - .completed = srcu_torture_completed, + .get_gp_seq = srcu_torture_completed, .deferred_free = srcu_torture_deferred_free, .sync = srcu_torture_synchronize, .exp_sync = srcu_torture_synchronize_expedited, @@ -610,8 +631,7 @@ static struct rcu_torture_ops srcud_ops = { .readlock = srcu_torture_read_lock, .read_delay = srcu_read_delay, .readunlock = srcu_torture_read_unlock, - .started = NULL, - .completed = srcu_torture_completed, + .get_gp_seq = srcu_torture_completed, .deferred_free = srcu_torture_deferred_free, .sync = srcu_torture_synchronize, .exp_sync = srcu_torture_synchronize_expedited, @@ -622,6 +642,26 @@ static struct rcu_torture_ops srcud_ops = { .name = "srcud" }; +/* As above, but broken due to inappropriate reader extension. */ +static struct rcu_torture_ops busted_srcud_ops = { + .ttype = SRCU_FLAVOR, + .init = srcu_torture_init, + .cleanup = srcu_torture_cleanup, + .readlock = srcu_torture_read_lock, + .read_delay = rcu_read_delay, + .readunlock = srcu_torture_read_unlock, + .get_gp_seq = srcu_torture_completed, + .deferred_free = srcu_torture_deferred_free, + .sync = srcu_torture_synchronize, + .exp_sync = srcu_torture_synchronize_expedited, + .call = srcu_torture_call, + .cb_barrier = srcu_torture_barrier, + .stats = srcu_torture_stats, + .irq_capable = 1, + .extendables = RCUTORTURE_MAX_EXTEND, + .name = "busted_srcud" +}; + /* * Definitions for sched torture testing. */ @@ -648,8 +688,8 @@ static struct rcu_torture_ops sched_ops = { .readlock = sched_torture_read_lock, .read_delay = rcu_read_delay, /* just reuse rcu's version. */ .readunlock = sched_torture_read_unlock, - .started = rcu_batches_started_sched, - .completed = rcu_batches_completed_sched, + .get_gp_seq = rcu_sched_get_gp_seq, + .gp_diff = rcu_seq_diff, .deferred_free = rcu_sched_torture_deferred_free, .sync = synchronize_sched, .exp_sync = synchronize_sched_expedited, @@ -660,6 +700,7 @@ static struct rcu_torture_ops sched_ops = { .fqs = rcu_sched_force_quiescent_state, .stats = NULL, .irq_capable = 1, + .extendables = RCUTORTURE_MAX_EXTEND, .name = "sched" }; @@ -687,8 +728,7 @@ static struct rcu_torture_ops tasks_ops = { .readlock = tasks_torture_read_lock, .read_delay = rcu_read_delay, /* just reuse rcu's version. */ .readunlock = tasks_torture_read_unlock, - .started = rcu_no_completed, - .completed = rcu_no_completed, + .get_gp_seq = rcu_no_completed, .deferred_free = rcu_tasks_torture_deferred_free, .sync = synchronize_rcu_tasks, .exp_sync = synchronize_rcu_tasks, @@ -700,6 +740,13 @@ static struct rcu_torture_ops tasks_ops = { .name = "tasks" }; +static unsigned long rcutorture_seq_diff(unsigned long new, unsigned long old) +{ + if (!cur_ops->gp_diff) + return new - old; + return cur_ops->gp_diff(new, old); +} + static bool __maybe_unused torturing_tasks(void) { return cur_ops == &tasks_ops; @@ -726,6 +773,44 @@ static void rcu_torture_boost_cb(struct rcu_head *head) smp_store_release(&rbip->inflight, 0); } +static int old_rt_runtime = -1; + +static void rcu_torture_disable_rt_throttle(void) +{ + /* + * Disable RT throttling so that rcutorture's boost threads don't get + * throttled. Only possible if rcutorture is built-in otherwise the + * user should manually do this by setting the sched_rt_period_us and + * sched_rt_runtime sysctls. + */ + if (!IS_BUILTIN(CONFIG_RCU_TORTURE_TEST) || old_rt_runtime != -1) + return; + + old_rt_runtime = sysctl_sched_rt_runtime; + sysctl_sched_rt_runtime = -1; +} + +static void rcu_torture_enable_rt_throttle(void) +{ + if (!IS_BUILTIN(CONFIG_RCU_TORTURE_TEST) || old_rt_runtime == -1) + return; + + sysctl_sched_rt_runtime = old_rt_runtime; + old_rt_runtime = -1; +} + +static bool rcu_torture_boost_failed(unsigned long start, unsigned long end) +{ + if (end - start > test_boost_duration * HZ - HZ / 2) { + VERBOSE_TOROUT_STRING("rcu_torture_boost boosting failed"); + n_rcu_torture_boost_failure++; + + return true; /* failed */ + } + + return false; /* passed */ +} + static int rcu_torture_boost(void *arg) { unsigned long call_rcu_time; @@ -746,6 +831,21 @@ static int rcu_torture_boost(void *arg) init_rcu_head_on_stack(&rbi.rcu); /* Each pass through the following loop does one boost-test cycle. */ do { + /* Track if the test failed already in this test interval? */ + bool failed = false; + + /* Increment n_rcu_torture_boosts once per boost-test */ + while (!kthread_should_stop()) { + if (mutex_trylock(&boost_mutex)) { + n_rcu_torture_boosts++; + mutex_unlock(&boost_mutex); + break; + } + schedule_timeout_uninterruptible(1); + } + if (kthread_should_stop()) + goto checkwait; + /* Wait for the next test interval. */ oldstarttime = boost_starttime; while (ULONG_CMP_LT(jiffies, oldstarttime)) { @@ -764,11 +864,10 @@ static int rcu_torture_boost(void *arg) /* RCU core before ->inflight = 1. */ smp_store_release(&rbi.inflight, 1); call_rcu(&rbi.rcu, rcu_torture_boost_cb); - if (jiffies - call_rcu_time > - test_boost_duration * HZ - HZ / 2) { - VERBOSE_TOROUT_STRING("rcu_torture_boost boosting failed"); - n_rcu_torture_boost_failure++; - } + /* Check if the boost test failed */ + failed = failed || + rcu_torture_boost_failed(call_rcu_time, + jiffies); call_rcu_time = jiffies; } stutter_wait("rcu_torture_boost"); @@ -777,6 +876,14 @@ static int rcu_torture_boost(void *arg) } /* + * If boost never happened, then inflight will always be 1, in + * this case the boost check would never happen in the above + * loop so do another one here. + */ + if (!failed && smp_load_acquire(&rbi.inflight)) + rcu_torture_boost_failed(call_rcu_time, jiffies); + + /* * Set the start time of the next test interval. * Yes, this is vulnerable to long delays, but such * delays simply cause a false negative for the next @@ -788,7 +895,6 @@ static int rcu_torture_boost(void *arg) if (mutex_trylock(&boost_mutex)) { boost_starttime = jiffies + test_boost_interval * HZ; - n_rcu_torture_boosts++; mutex_unlock(&boost_mutex); break; } @@ -1010,7 +1116,7 @@ rcu_torture_writer(void *arg) break; } } - rcutorture_record_progress(++rcu_torture_current_version); + rcu_torture_current_version++; /* Cycle through nesting levels of rcu_expedite_gp() calls. */ if (can_expedite && !(torture_random(&rand) & 0xff & (!!expediting - 1))) { @@ -1084,27 +1190,133 @@ static void rcu_torture_timer_cb(struct rcu_head *rhp) } /* - * RCU torture reader from timer handler. Dereferences rcu_torture_current, - * incrementing the corresponding element of the pipeline array. The - * counter in the element should never be greater than 1, otherwise, the - * RCU implementation is broken. + * Do one extension of an RCU read-side critical section using the + * current reader state in readstate (set to zero for initial entry + * to extended critical section), set the new state as specified by + * newstate (set to zero for final exit from extended critical section), + * and random-number-generator state in trsp. If this is neither the + * beginning or end of the critical section and if there was actually a + * change, do a ->read_delay(). */ -static void rcu_torture_timer(struct timer_list *unused) +static void rcutorture_one_extend(int *readstate, int newstate, + struct torture_random_state *trsp) +{ + int idxnew = -1; + int idxold = *readstate; + int statesnew = ~*readstate & newstate; + int statesold = *readstate & ~newstate; + + WARN_ON_ONCE(idxold < 0); + WARN_ON_ONCE((idxold >> RCUTORTURE_RDR_SHIFT) > 1); + + /* First, put new protection in place to avoid critical-section gap. */ + if (statesnew & RCUTORTURE_RDR_BH) + local_bh_disable(); + if (statesnew & RCUTORTURE_RDR_IRQ) + local_irq_disable(); + if (statesnew & RCUTORTURE_RDR_PREEMPT) + preempt_disable(); + if (statesnew & RCUTORTURE_RDR_RCU) + idxnew = cur_ops->readlock() << RCUTORTURE_RDR_SHIFT; + + /* Next, remove old protection, irq first due to bh conflict. */ + if (statesold & RCUTORTURE_RDR_IRQ) + local_irq_enable(); + if (statesold & RCUTORTURE_RDR_BH) + local_bh_enable(); + if (statesold & RCUTORTURE_RDR_PREEMPT) + preempt_enable(); + if (statesold & RCUTORTURE_RDR_RCU) + cur_ops->readunlock(idxold >> RCUTORTURE_RDR_SHIFT); + + /* Delay if neither beginning nor end and there was a change. */ + if ((statesnew || statesold) && *readstate && newstate) + cur_ops->read_delay(trsp); + + /* Update the reader state. */ + if (idxnew == -1) + idxnew = idxold & ~RCUTORTURE_RDR_MASK; + WARN_ON_ONCE(idxnew < 0); + WARN_ON_ONCE((idxnew >> RCUTORTURE_RDR_SHIFT) > 1); + *readstate = idxnew | newstate; + WARN_ON_ONCE((*readstate >> RCUTORTURE_RDR_SHIFT) < 0); + WARN_ON_ONCE((*readstate >> RCUTORTURE_RDR_SHIFT) > 1); +} + +/* Return the biggest extendables mask given current RCU and boot parameters. */ +static int rcutorture_extend_mask_max(void) +{ + int mask; + + WARN_ON_ONCE(extendables & ~RCUTORTURE_MAX_EXTEND); + mask = extendables & RCUTORTURE_MAX_EXTEND & cur_ops->extendables; + mask = mask | RCUTORTURE_RDR_RCU; + return mask; +} + +/* Return a random protection state mask, but with at least one bit set. */ +static int +rcutorture_extend_mask(int oldmask, struct torture_random_state *trsp) +{ + int mask = rcutorture_extend_mask_max(); + unsigned long randmask1 = torture_random(trsp) >> 8; + unsigned long randmask2 = randmask1 >> 1; + + WARN_ON_ONCE(mask >> RCUTORTURE_RDR_SHIFT); + /* Half the time lots of bits, half the time only one bit. */ + if (randmask1 & 0x1) + mask = mask & randmask2; + else + mask = mask & (1 << (randmask2 % RCUTORTURE_RDR_NBITS)); + if ((mask & RCUTORTURE_RDR_IRQ) && + !(mask & RCUTORTURE_RDR_BH) && + (oldmask & RCUTORTURE_RDR_BH)) + mask |= RCUTORTURE_RDR_BH; /* Can't enable bh w/irq disabled. */ + if ((mask & RCUTORTURE_RDR_IRQ) && + !(mask & cur_ops->ext_irq_conflict) && + (oldmask & cur_ops->ext_irq_conflict)) + mask |= cur_ops->ext_irq_conflict; /* Or if readers object. */ + return mask ?: RCUTORTURE_RDR_RCU; +} + +/* + * Do a randomly selected number of extensions of an existing RCU read-side + * critical section. + */ +static void rcutorture_loop_extend(int *readstate, + struct torture_random_state *trsp) +{ + int i; + int mask = rcutorture_extend_mask_max(); + + WARN_ON_ONCE(!*readstate); /* -Existing- RCU read-side critsect! */ + if (!((mask - 1) & mask)) + return; /* Current RCU flavor not extendable. */ + i = (torture_random(trsp) >> 3) & RCUTORTURE_RDR_MAX_LOOPS; + while (i--) { + mask = rcutorture_extend_mask(*readstate, trsp); + rcutorture_one_extend(readstate, mask, trsp); + } +} + +/* + * Do one read-side critical section, returning false if there was + * no data to read. Can be invoked both from process context and + * from a timer handler. + */ +static bool rcu_torture_one_read(struct torture_random_state *trsp) { - int idx; unsigned long started; unsigned long completed; - static DEFINE_TORTURE_RANDOM(rand); - static DEFINE_SPINLOCK(rand_lock); + int newstate; struct rcu_torture *p; int pipe_count; + int readstate = 0; unsigned long long ts; - idx = cur_ops->readlock(); - if (cur_ops->started) - started = cur_ops->started(); - else - started = cur_ops->completed(); + newstate = rcutorture_extend_mask(readstate, trsp); + rcutorture_one_extend(&readstate, newstate, trsp); + started = cur_ops->get_gp_seq(); ts = rcu_trace_clock_local(); p = rcu_dereference_check(rcu_torture_current, rcu_read_lock_bh_held() || @@ -1112,39 +1324,50 @@ static void rcu_torture_timer(struct timer_list *unused) srcu_read_lock_held(srcu_ctlp) || torturing_tasks()); if (p == NULL) { - /* Leave because rcu_torture_writer is not yet underway */ - cur_ops->readunlock(idx); - return; + /* Wait for rcu_torture_writer to get underway */ + rcutorture_one_extend(&readstate, 0, trsp); + return false; } if (p->rtort_mbtest == 0) atomic_inc(&n_rcu_torture_mberror); - spin_lock(&rand_lock); - cur_ops->read_delay(&rand); - n_rcu_torture_timers++; - spin_unlock(&rand_lock); + rcutorture_loop_extend(&readstate, trsp); preempt_disable(); pipe_count = p->rtort_pipe_count; if (pipe_count > RCU_TORTURE_PIPE_LEN) { /* Should not happen, but... */ pipe_count = RCU_TORTURE_PIPE_LEN; } - completed = cur_ops->completed(); + completed = cur_ops->get_gp_seq(); if (pipe_count > 1) { - do_trace_rcu_torture_read(cur_ops->name, &p->rtort_rcu, ts, - started, completed); + do_trace_rcu_torture_read(cur_ops->name, &p->rtort_rcu, + ts, started, completed); rcu_ftrace_dump(DUMP_ALL); } __this_cpu_inc(rcu_torture_count[pipe_count]); - completed = completed - started; - if (cur_ops->started) - completed++; + completed = rcutorture_seq_diff(completed, started); if (completed > RCU_TORTURE_PIPE_LEN) { /* Should not happen, but... */ completed = RCU_TORTURE_PIPE_LEN; } __this_cpu_inc(rcu_torture_batch[completed]); preempt_enable(); - cur_ops->readunlock(idx); + rcutorture_one_extend(&readstate, 0, trsp); + WARN_ON_ONCE(readstate & RCUTORTURE_RDR_MASK); + return true; +} + +static DEFINE_TORTURE_RANDOM_PERCPU(rcu_torture_timer_rand); + +/* + * RCU torture reader from timer handler. Dereferences rcu_torture_current, + * incrementing the corresponding element of the pipeline array. The + * counter in the element should never be greater than 1, otherwise, the + * RCU implementation is broken. + */ +static void rcu_torture_timer(struct timer_list *unused) +{ + atomic_long_inc(&n_rcu_torture_timers); + (void)rcu_torture_one_read(this_cpu_ptr(&rcu_torture_timer_rand)); /* Test call_rcu() invocation from interrupt handler. */ if (cur_ops->call) { @@ -1164,14 +1387,8 @@ static void rcu_torture_timer(struct timer_list *unused) static int rcu_torture_reader(void *arg) { - unsigned long started; - unsigned long completed; - int idx; DEFINE_TORTURE_RANDOM(rand); - struct rcu_torture *p; - int pipe_count; struct timer_list t; - unsigned long long ts; VERBOSE_TOROUT_STRING("rcu_torture_reader task started"); set_user_nice(current, MAX_NICE); @@ -1183,49 +1400,8 @@ rcu_torture_reader(void *arg) if (!timer_pending(&t)) mod_timer(&t, jiffies + 1); } - idx = cur_ops->readlock(); - if (cur_ops->started) - started = cur_ops->started(); - else - started = cur_ops->completed(); - ts = rcu_trace_clock_local(); - p = rcu_dereference_check(rcu_torture_current, - rcu_read_lock_bh_held() || - rcu_read_lock_sched_held() || - srcu_read_lock_held(srcu_ctlp) || - torturing_tasks()); - if (p == NULL) { - /* Wait for rcu_torture_writer to get underway */ - cur_ops->readunlock(idx); + if (!rcu_torture_one_read(&rand)) schedule_timeout_interruptible(HZ); - continue; - } - if (p->rtort_mbtest == 0) - atomic_inc(&n_rcu_torture_mberror); - cur_ops->read_delay(&rand); - preempt_disable(); - pipe_count = p->rtort_pipe_count; - if (pipe_count > RCU_TORTURE_PIPE_LEN) { - /* Should not happen, but... */ - pipe_count = RCU_TORTURE_PIPE_LEN; - } - completed = cur_ops->completed(); - if (pipe_count > 1) { - do_trace_rcu_torture_read(cur_ops->name, &p->rtort_rcu, - ts, started, completed); - rcu_ftrace_dump(DUMP_ALL); - } - __this_cpu_inc(rcu_torture_count[pipe_count]); - completed = completed - started; - if (cur_ops->started) - completed++; - if (completed > RCU_TORTURE_PIPE_LEN) { - /* Should not happen, but... */ - completed = RCU_TORTURE_PIPE_LEN; - } - __this_cpu_inc(rcu_torture_batch[completed]); - preempt_enable(); - cur_ops->readunlock(idx); stutter_wait("rcu_torture_reader"); } while (!torture_must_stop()); if (irqreader && cur_ops->irq_capable) { @@ -1282,7 +1458,7 @@ rcu_torture_stats_print(void) pr_cont("rtbf: %ld rtb: %ld nt: %ld ", n_rcu_torture_boost_failure, n_rcu_torture_boosts, - n_rcu_torture_timers); + atomic_long_read(&n_rcu_torture_timers)); torture_onoff_stats(); pr_cont("barrier: %ld/%ld:%ld ", n_barrier_successes, @@ -1324,18 +1500,16 @@ rcu_torture_stats_print(void) if (rtcv_snap == rcu_torture_current_version && rcu_torture_current != NULL) { int __maybe_unused flags = 0; - unsigned long __maybe_unused gpnum = 0; - unsigned long __maybe_unused completed = 0; + unsigned long __maybe_unused gp_seq = 0; rcutorture_get_gp_data(cur_ops->ttype, - &flags, &gpnum, &completed); + &flags, &gp_seq); srcutorture_get_gp_data(cur_ops->ttype, srcu_ctlp, - &flags, &gpnum, &completed); + &flags, &gp_seq); wtp = READ_ONCE(writer_task); - pr_alert("??? Writer stall state %s(%d) g%lu c%lu f%#x ->state %#lx cpu %d\n", + pr_alert("??? Writer stall state %s(%d) g%lu f%#x ->state %#lx cpu %d\n", rcu_torture_writer_state_getname(), - rcu_torture_writer_state, - gpnum, completed, flags, + rcu_torture_writer_state, gp_seq, flags, wtp == NULL ? ~0UL : wtp->state, wtp == NULL ? -1 : (int)task_cpu(wtp)); if (!splatted && wtp) { @@ -1365,7 +1539,7 @@ rcu_torture_stats(void *arg) return 0; } -static inline void +static void rcu_torture_print_module_parms(struct rcu_torture_ops *cur_ops, const char *tag) { pr_alert("%s" TORTURE_FLAG @@ -1397,6 +1571,7 @@ static int rcutorture_booster_cleanup(unsigned int cpu) mutex_lock(&boost_mutex); t = boost_tasks[cpu]; boost_tasks[cpu] = NULL; + rcu_torture_enable_rt_throttle(); mutex_unlock(&boost_mutex); /* This must be outside of the mutex, otherwise deadlock! */ @@ -1413,6 +1588,7 @@ static int rcutorture_booster_init(unsigned int cpu) /* Don't allow time recalculation while creating a new task. */ mutex_lock(&boost_mutex); + rcu_torture_disable_rt_throttle(); VERBOSE_TOROUT_STRING("Creating rcu_torture_boost task"); boost_tasks[cpu] = kthread_create_on_node(rcu_torture_boost, NULL, cpu_to_node(cpu), @@ -1446,7 +1622,7 @@ static int rcu_torture_stall(void *args) VERBOSE_TOROUT_STRING("rcu_torture_stall end holdoff"); } if (!kthread_should_stop()) { - stop_at = get_seconds() + stall_cpu; + stop_at = ktime_get_seconds() + stall_cpu; /* RCU CPU stall is expected behavior in following code. */ rcu_read_lock(); if (stall_cpu_irqsoff) @@ -1455,7 +1631,8 @@ static int rcu_torture_stall(void *args) preempt_disable(); pr_alert("rcu_torture_stall start on CPU %d.\n", smp_processor_id()); - while (ULONG_CMP_LT(get_seconds(), stop_at)) + while (ULONG_CMP_LT((unsigned long)ktime_get_seconds(), + stop_at)) continue; /* Induce RCU CPU stall warning. */ if (stall_cpu_irqsoff) local_irq_enable(); @@ -1546,8 +1723,9 @@ static int rcu_torture_barrier(void *arg) atomic_read(&barrier_cbs_invoked), n_barrier_cbs); WARN_ON_ONCE(1); + } else { + n_barrier_successes++; } - n_barrier_successes++; schedule_timeout_interruptible(HZ / 10); } while (!torture_must_stop()); torture_kthread_stopping("rcu_torture_barrier"); @@ -1610,17 +1788,39 @@ static void rcu_torture_barrier_cleanup(void) } } +static bool rcu_torture_can_boost(void) +{ + static int boost_warn_once; + int prio; + + if (!(test_boost == 1 && cur_ops->can_boost) && test_boost != 2) + return false; + + prio = rcu_get_gp_kthreads_prio(); + if (!prio) + return false; + + if (prio < 2) { + if (boost_warn_once == 1) + return false; + + pr_alert("%s: WARN: RCU kthread priority too low to test boosting. Skipping RCU boost test. Try passing rcutree.kthread_prio > 1 on the kernel command line.\n", KBUILD_MODNAME); + boost_warn_once = 1; + return false; + } + + return true; +} + static enum cpuhp_state rcutor_hp; static void rcu_torture_cleanup(void) { int flags = 0; - unsigned long gpnum = 0; - unsigned long completed = 0; + unsigned long gp_seq = 0; int i; - rcutorture_record_test_transition(); if (torture_cleanup_begin()) { if (cur_ops->cb_barrier != NULL) cur_ops->cb_barrier(); @@ -1648,17 +1848,15 @@ rcu_torture_cleanup(void) fakewriter_tasks = NULL; } - rcutorture_get_gp_data(cur_ops->ttype, &flags, &gpnum, &completed); - srcutorture_get_gp_data(cur_ops->ttype, srcu_ctlp, - &flags, &gpnum, &completed); - pr_alert("%s: End-test grace-period state: g%lu c%lu f%#x\n", - cur_ops->name, gpnum, completed, flags); + rcutorture_get_gp_data(cur_ops->ttype, &flags, &gp_seq); + srcutorture_get_gp_data(cur_ops->ttype, srcu_ctlp, &flags, &gp_seq); + pr_alert("%s: End-test grace-period state: g%lu f%#x\n", + cur_ops->name, gp_seq, flags); torture_stop_kthread(rcu_torture_stats, stats_task); torture_stop_kthread(rcu_torture_fqs, fqs_task); for (i = 0; i < ncbflooders; i++) torture_stop_kthread(rcu_torture_cbflood, cbflood_task[i]); - if ((test_boost == 1 && cur_ops->can_boost) || - test_boost == 2) + if (rcu_torture_can_boost()) cpuhp_remove_state(rcutor_hp); /* @@ -1746,7 +1944,7 @@ rcu_torture_init(void) int firsterr = 0; static struct rcu_torture_ops *torture_ops[] = { &rcu_ops, &rcu_bh_ops, &rcu_busted_ops, &srcu_ops, &srcud_ops, - &sched_ops, &tasks_ops, + &busted_srcud_ops, &sched_ops, &tasks_ops, }; if (!torture_init_begin(torture_type, verbose)) @@ -1763,8 +1961,8 @@ rcu_torture_init(void) torture_type); pr_alert("rcu-torture types:"); for (i = 0; i < ARRAY_SIZE(torture_ops); i++) - pr_alert(" %s", torture_ops[i]->name); - pr_alert("\n"); + pr_cont(" %s", torture_ops[i]->name); + pr_cont("\n"); firsterr = -EINVAL; goto unwind; } @@ -1882,8 +2080,7 @@ rcu_torture_init(void) test_boost_interval = 1; if (test_boost_duration < 2) test_boost_duration = 2; - if ((test_boost == 1 && cur_ops->can_boost) || - test_boost == 2) { + if (rcu_torture_can_boost()) { boost_starttime = jiffies + test_boost_interval * HZ; @@ -1897,7 +2094,7 @@ rcu_torture_init(void) firsterr = torture_shutdown_init(shutdown_secs, rcu_torture_cleanup); if (firsterr) goto unwind; - firsterr = torture_onoff_init(onoff_holdoff * HZ, onoff_interval * HZ); + firsterr = torture_onoff_init(onoff_holdoff * HZ, onoff_interval); if (firsterr) goto unwind; firsterr = rcu_torture_stall_init(); @@ -1926,7 +2123,6 @@ rcu_torture_init(void) goto unwind; } } - rcutorture_record_test_transition(); torture_init_end(); return 0; diff --git a/kernel/rcu/srcutiny.c b/kernel/rcu/srcutiny.c index 622792abe41a..04fc2ed71af8 100644 --- a/kernel/rcu/srcutiny.c +++ b/kernel/rcu/srcutiny.c @@ -110,7 +110,7 @@ void __srcu_read_unlock(struct srcu_struct *sp, int idx) WRITE_ONCE(sp->srcu_lock_nesting[idx], newval); if (!newval && READ_ONCE(sp->srcu_gp_waiting)) - swake_up(&sp->srcu_wq); + swake_up_one(&sp->srcu_wq); } EXPORT_SYMBOL_GPL(__srcu_read_unlock); @@ -140,7 +140,7 @@ void srcu_drive_gp(struct work_struct *wp) idx = sp->srcu_idx; WRITE_ONCE(sp->srcu_idx, !sp->srcu_idx); WRITE_ONCE(sp->srcu_gp_waiting, true); /* srcu_read_unlock() wakes! */ - swait_event(sp->srcu_wq, !READ_ONCE(sp->srcu_lock_nesting[idx])); + swait_event_exclusive(sp->srcu_wq, !READ_ONCE(sp->srcu_lock_nesting[idx])); WRITE_ONCE(sp->srcu_gp_waiting, false); /* srcu_read_unlock() cheap. */ /* Invoke the callbacks we removed above. */ diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c index b4123d7a2cec..6c9866a854b1 100644 --- a/kernel/rcu/srcutree.c +++ b/kernel/rcu/srcutree.c @@ -26,6 +26,8 @@ * */ +#define pr_fmt(fmt) "rcu: " fmt + #include <linux/export.h> #include <linux/mutex.h> #include <linux/percpu.h> @@ -390,7 +392,8 @@ void _cleanup_srcu_struct(struct srcu_struct *sp, bool quiesced) } if (WARN_ON(rcu_seq_state(READ_ONCE(sp->srcu_gp_seq)) != SRCU_STATE_IDLE) || WARN_ON(srcu_readers_active(sp))) { - pr_info("%s: Active srcu_struct %p state: %d\n", __func__, sp, rcu_seq_state(READ_ONCE(sp->srcu_gp_seq))); + pr_info("%s: Active srcu_struct %p state: %d\n", + __func__, sp, rcu_seq_state(READ_ONCE(sp->srcu_gp_seq))); return; /* Caller forgot to stop doing call_srcu()? */ } free_percpu(sp->sda); @@ -641,6 +644,9 @@ static void srcu_funnel_exp_start(struct srcu_struct *sp, struct srcu_node *snp, * period s. Losers must either ensure that their desired grace-period * number is recorded on at least their leaf srcu_node structure, or they * must take steps to invoke their own callbacks. + * + * Note that this function also does the work of srcu_funnel_exp_start(), + * in some cases by directly invoking it. */ static void srcu_funnel_gp_start(struct srcu_struct *sp, struct srcu_data *sdp, unsigned long s, bool do_norm) @@ -823,17 +829,17 @@ static void srcu_leak_callback(struct rcu_head *rhp) * more than one CPU, this means that when "func()" is invoked, each CPU * is guaranteed to have executed a full memory barrier since the end of * its last corresponding SRCU read-side critical section whose beginning - * preceded the call to call_rcu(). It also means that each CPU executing + * preceded the call to call_srcu(). It also means that each CPU executing * an SRCU read-side critical section that continues beyond the start of - * "func()" must have executed a memory barrier after the call_rcu() + * "func()" must have executed a memory barrier after the call_srcu() * but before the beginning of that SRCU read-side critical section. * Note that these guarantees include CPUs that are offline, idle, or * executing in user mode, as well as CPUs that are executing in the kernel. * - * Furthermore, if CPU A invoked call_rcu() and CPU B invoked the + * Furthermore, if CPU A invoked call_srcu() and CPU B invoked the * resulting SRCU callback function "func()", then both CPU A and CPU * B are guaranteed to execute a full memory barrier during the time - * interval between the call to call_rcu() and the invocation of "func()". + * interval between the call to call_srcu() and the invocation of "func()". * This guarantee applies even if CPU A and CPU B are the same CPU (but * again only if the system has more than one CPU). * @@ -1246,13 +1252,12 @@ static void process_srcu(struct work_struct *work) void srcutorture_get_gp_data(enum rcutorture_type test_type, struct srcu_struct *sp, int *flags, - unsigned long *gpnum, unsigned long *completed) + unsigned long *gp_seq) { if (test_type != SRCU_FLAVOR) return; *flags = 0; - *completed = rcu_seq_ctr(sp->srcu_gp_seq); - *gpnum = rcu_seq_ctr(sp->srcu_gp_seq_needed); + *gp_seq = rcu_seq_current(&sp->srcu_gp_seq); } EXPORT_SYMBOL_GPL(srcutorture_get_gp_data); @@ -1263,16 +1268,17 @@ void srcu_torture_stats_print(struct srcu_struct *sp, char *tt, char *tf) unsigned long s0 = 0, s1 = 0; idx = sp->srcu_idx & 0x1; - pr_alert("%s%s Tree SRCU per-CPU(idx=%d):", tt, tf, idx); + pr_alert("%s%s Tree SRCU g%ld per-CPU(idx=%d):", + tt, tf, rcu_seq_current(&sp->srcu_gp_seq), idx); for_each_possible_cpu(cpu) { unsigned long l0, l1; unsigned long u0, u1; long c0, c1; - struct srcu_data *counts; + struct srcu_data *sdp; - counts = per_cpu_ptr(sp->sda, cpu); - u0 = counts->srcu_unlock_count[!idx]; - u1 = counts->srcu_unlock_count[idx]; + sdp = per_cpu_ptr(sp->sda, cpu); + u0 = sdp->srcu_unlock_count[!idx]; + u1 = sdp->srcu_unlock_count[idx]; /* * Make sure that a lock is always counted if the corresponding @@ -1280,12 +1286,13 @@ void srcu_torture_stats_print(struct srcu_struct *sp, char *tt, char *tf) */ smp_rmb(); - l0 = counts->srcu_lock_count[!idx]; - l1 = counts->srcu_lock_count[idx]; + l0 = sdp->srcu_lock_count[!idx]; + l1 = sdp->srcu_lock_count[idx]; c0 = l0 - u0; c1 = l1 - u1; - pr_cont(" %d(%ld,%ld)", cpu, c0, c1); + pr_cont(" %d(%ld,%ld %1p)", + cpu, c0, c1, rcu_segcblist_head(&sdp->srcu_cblist)); s0 += c0; s1 += c1; } diff --git a/kernel/rcu/tiny.c b/kernel/rcu/tiny.c index a64eee0db39e..befc9321a89c 100644 --- a/kernel/rcu/tiny.c +++ b/kernel/rcu/tiny.c @@ -122,10 +122,8 @@ void rcu_check_callbacks(int user) { if (user) rcu_sched_qs(); - else if (!in_softirq()) + if (user || !in_softirq()) rcu_bh_qs(); - if (user) - rcu_note_voluntary_context_switch(current); } /* diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index aa7cade1b9f3..0b760c1369f7 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -27,6 +27,9 @@ * For detailed explanation of Read-Copy Update mechanism see - * Documentation/RCU */ + +#define pr_fmt(fmt) "rcu: " fmt + #include <linux/types.h> #include <linux/kernel.h> #include <linux/init.h> @@ -95,13 +98,13 @@ struct rcu_state sname##_state = { \ .rda = &sname##_data, \ .call = cr, \ .gp_state = RCU_GP_IDLE, \ - .gpnum = 0UL - 300UL, \ - .completed = 0UL - 300UL, \ + .gp_seq = (0UL - 300UL) << RCU_SEQ_CTR_SHIFT, \ .barrier_mutex = __MUTEX_INITIALIZER(sname##_state.barrier_mutex), \ .name = RCU_STATE_NAME(sname), \ .abbr = sabbr, \ .exp_mutex = __MUTEX_INITIALIZER(sname##_state.exp_mutex), \ .exp_wake_mutex = __MUTEX_INITIALIZER(sname##_state.exp_wake_mutex), \ + .ofl_lock = __SPIN_LOCK_UNLOCKED(sname##_state.ofl_lock), \ } RCU_STATE_INITIALIZER(rcu_sched, 's', call_rcu_sched); @@ -155,6 +158,9 @@ EXPORT_SYMBOL_GPL(rcu_scheduler_active); */ static int rcu_scheduler_fully_active __read_mostly; +static void +rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp, + struct rcu_node *rnp, unsigned long gps, unsigned long flags); static void rcu_init_new_rnp(struct rcu_node *rnp_leaf); static void rcu_cleanup_dead_rnp(struct rcu_node *rnp_leaf); static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu); @@ -177,6 +183,13 @@ module_param(gp_init_delay, int, 0444); static int gp_cleanup_delay; module_param(gp_cleanup_delay, int, 0444); +/* Retreive RCU kthreads priority for rcutorture */ +int rcu_get_gp_kthreads_prio(void) +{ + return kthread_prio; +} +EXPORT_SYMBOL_GPL(rcu_get_gp_kthreads_prio); + /* * Number of grace periods between delays, normalized by the duration of * the delay. The longer the delay, the more the grace periods between @@ -189,18 +202,6 @@ module_param(gp_cleanup_delay, int, 0444); #define PER_RCU_NODE_PERIOD 3 /* Number of grace periods between delays. */ /* - * Track the rcutorture test sequence number and the update version - * number within a given test. The rcutorture_testseq is incremented - * on every rcutorture module load and unload, so has an odd value - * when a test is running. The rcutorture_vernum is set to zero - * when rcutorture starts and is incremented on each rcutorture update. - * These variables enable correlating rcutorture output with the - * RCU tracing information. - */ -unsigned long rcutorture_testseq; -unsigned long rcutorture_vernum; - -/* * Compute the mask of online CPUs for the specified rcu_node structure. * This will not be stable unless the rcu_node structure's ->lock is * held, but the bit corresponding to the current CPU will be stable @@ -218,7 +219,7 @@ unsigned long rcu_rnp_online_cpus(struct rcu_node *rnp) */ static int rcu_gp_in_progress(struct rcu_state *rsp) { - return READ_ONCE(rsp->completed) != READ_ONCE(rsp->gpnum); + return rcu_seq_state(rcu_seq_current(&rsp->gp_seq)); } /* @@ -233,7 +234,7 @@ void rcu_sched_qs(void) if (!__this_cpu_read(rcu_sched_data.cpu_no_qs.s)) return; trace_rcu_grace_period(TPS("rcu_sched"), - __this_cpu_read(rcu_sched_data.gpnum), + __this_cpu_read(rcu_sched_data.gp_seq), TPS("cpuqs")); __this_cpu_write(rcu_sched_data.cpu_no_qs.b.norm, false); if (!__this_cpu_read(rcu_sched_data.cpu_no_qs.b.exp)) @@ -248,7 +249,7 @@ void rcu_bh_qs(void) RCU_LOCKDEP_WARN(preemptible(), "rcu_bh_qs() invoked with preemption enabled!!!"); if (__this_cpu_read(rcu_bh_data.cpu_no_qs.s)) { trace_rcu_grace_period(TPS("rcu_bh"), - __this_cpu_read(rcu_bh_data.gpnum), + __this_cpu_read(rcu_bh_data.gp_seq), TPS("cpuqs")); __this_cpu_write(rcu_bh_data.cpu_no_qs.b.norm, false); } @@ -380,20 +381,6 @@ static bool rcu_dynticks_in_eqs_since(struct rcu_dynticks *rdtp, int snap) } /* - * Do a double-increment of the ->dynticks counter to emulate a - * momentary idle-CPU quiescent state. - */ -static void rcu_dynticks_momentary_idle(void) -{ - struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks); - int special = atomic_add_return(2 * RCU_DYNTICK_CTRL_CTR, - &rdtp->dynticks); - - /* It is illegal to call this from idle state. */ - WARN_ON_ONCE(!(special & RCU_DYNTICK_CTRL_CTR)); -} - -/* * Set the special (bottom) bit of the specified CPU so that it * will take special action (such as flushing its TLB) on the * next exit from an extended quiescent state. Returns true if @@ -424,12 +411,17 @@ bool rcu_eqs_special_set(int cpu) * * We inform the RCU core by emulating a zero-duration dyntick-idle period. * - * The caller must have disabled interrupts. + * The caller must have disabled interrupts and must not be idle. */ static void rcu_momentary_dyntick_idle(void) { + struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks); + int special; + raw_cpu_write(rcu_dynticks.rcu_need_heavy_qs, false); - rcu_dynticks_momentary_idle(); + special = atomic_add_return(2 * RCU_DYNTICK_CTRL_CTR, &rdtp->dynticks); + /* It is illegal to call this from idle state. */ + WARN_ON_ONCE(!(special & RCU_DYNTICK_CTRL_CTR)); } /* @@ -451,7 +443,7 @@ void rcu_note_context_switch(bool preempt) rcu_momentary_dyntick_idle(); this_cpu_inc(rcu_dynticks.rcu_qs_ctr); if (!preempt) - rcu_note_voluntary_context_switch_lite(current); + rcu_tasks_qs(current); out: trace_rcu_utilization(TPS("End context switch")); barrier(); /* Avoid RCU read-side critical sections leaking up. */ @@ -513,8 +505,38 @@ static ulong jiffies_till_first_fqs = ULONG_MAX; static ulong jiffies_till_next_fqs = ULONG_MAX; static bool rcu_kick_kthreads; -module_param(jiffies_till_first_fqs, ulong, 0644); -module_param(jiffies_till_next_fqs, ulong, 0644); +static int param_set_first_fqs_jiffies(const char *val, const struct kernel_param *kp) +{ + ulong j; + int ret = kstrtoul(val, 0, &j); + + if (!ret) + WRITE_ONCE(*(ulong *)kp->arg, (j > HZ) ? HZ : j); + return ret; +} + +static int param_set_next_fqs_jiffies(const char *val, const struct kernel_param *kp) +{ + ulong j; + int ret = kstrtoul(val, 0, &j); + + if (!ret) + WRITE_ONCE(*(ulong *)kp->arg, (j > HZ) ? HZ : (j ?: 1)); + return ret; +} + +static struct kernel_param_ops first_fqs_jiffies_ops = { + .set = param_set_first_fqs_jiffies, + .get = param_get_ulong, +}; + +static struct kernel_param_ops next_fqs_jiffies_ops = { + .set = param_set_next_fqs_jiffies, + .get = param_get_ulong, +}; + +module_param_cb(jiffies_till_first_fqs, &first_fqs_jiffies_ops, &jiffies_till_first_fqs, 0644); +module_param_cb(jiffies_till_next_fqs, &next_fqs_jiffies_ops, &jiffies_till_next_fqs, 0644); module_param(rcu_kick_kthreads, bool, 0644); /* @@ -529,58 +551,31 @@ static void force_quiescent_state(struct rcu_state *rsp); static int rcu_pending(void); /* - * Return the number of RCU batches started thus far for debug & stats. + * Return the number of RCU GPs completed thus far for debug & stats. */ -unsigned long rcu_batches_started(void) +unsigned long rcu_get_gp_seq(void) { - return rcu_state_p->gpnum; + return READ_ONCE(rcu_state_p->gp_seq); } -EXPORT_SYMBOL_GPL(rcu_batches_started); +EXPORT_SYMBOL_GPL(rcu_get_gp_seq); /* - * Return the number of RCU-sched batches started thus far for debug & stats. + * Return the number of RCU-sched GPs completed thus far for debug & stats. */ -unsigned long rcu_batches_started_sched(void) +unsigned long rcu_sched_get_gp_seq(void) { - return rcu_sched_state.gpnum; + return READ_ONCE(rcu_sched_state.gp_seq); } -EXPORT_SYMBOL_GPL(rcu_batches_started_sched); +EXPORT_SYMBOL_GPL(rcu_sched_get_gp_seq); /* - * Return the number of RCU BH batches started thus far for debug & stats. + * Return the number of RCU-bh GPs completed thus far for debug & stats. */ -unsigned long rcu_batches_started_bh(void) +unsigned long rcu_bh_get_gp_seq(void) { - return rcu_bh_state.gpnum; + return READ_ONCE(rcu_bh_state.gp_seq); } -EXPORT_SYMBOL_GPL(rcu_batches_started_bh); - -/* - * Return the number of RCU batches completed thus far for debug & stats. - */ -unsigned long rcu_batches_completed(void) -{ - return rcu_state_p->completed; -} -EXPORT_SYMBOL_GPL(rcu_batches_completed); - -/* - * Return the number of RCU-sched batches completed thus far for debug & stats. - */ -unsigned long rcu_batches_completed_sched(void) -{ - return rcu_sched_state.completed; -} -EXPORT_SYMBOL_GPL(rcu_batches_completed_sched); - -/* - * Return the number of RCU BH batches completed thus far for debug & stats. - */ -unsigned long rcu_batches_completed_bh(void) -{ - return rcu_bh_state.completed; -} -EXPORT_SYMBOL_GPL(rcu_batches_completed_bh); +EXPORT_SYMBOL_GPL(rcu_bh_get_gp_seq); /* * Return the number of RCU expedited batches completed thus far for @@ -636,35 +631,42 @@ EXPORT_SYMBOL_GPL(rcu_sched_force_quiescent_state); */ void show_rcu_gp_kthreads(void) { + int cpu; + struct rcu_data *rdp; + struct rcu_node *rnp; struct rcu_state *rsp; for_each_rcu_flavor(rsp) { pr_info("%s: wait state: %d ->state: %#lx\n", rsp->name, rsp->gp_state, rsp->gp_kthread->state); + rcu_for_each_node_breadth_first(rsp, rnp) { + if (ULONG_CMP_GE(rsp->gp_seq, rnp->gp_seq_needed)) + continue; + pr_info("\trcu_node %d:%d ->gp_seq %lu ->gp_seq_needed %lu\n", + rnp->grplo, rnp->grphi, rnp->gp_seq, + rnp->gp_seq_needed); + if (!rcu_is_leaf_node(rnp)) + continue; + for_each_leaf_node_possible_cpu(rnp, cpu) { + rdp = per_cpu_ptr(rsp->rda, cpu); + if (rdp->gpwrap || + ULONG_CMP_GE(rsp->gp_seq, + rdp->gp_seq_needed)) + continue; + pr_info("\tcpu %d ->gp_seq_needed %lu\n", + cpu, rdp->gp_seq_needed); + } + } /* sched_show_task(rsp->gp_kthread); */ } } EXPORT_SYMBOL_GPL(show_rcu_gp_kthreads); /* - * Record the number of times rcutorture tests have been initiated and - * terminated. This information allows the debugfs tracing stats to be - * correlated to the rcutorture messages, even when the rcutorture module - * is being repeatedly loaded and unloaded. In other words, we cannot - * store this state in rcutorture itself. - */ -void rcutorture_record_test_transition(void) -{ - rcutorture_testseq++; - rcutorture_vernum = 0; -} -EXPORT_SYMBOL_GPL(rcutorture_record_test_transition); - -/* * Send along grace-period-related data for rcutorture diagnostics. */ void rcutorture_get_gp_data(enum rcutorture_type test_type, int *flags, - unsigned long *gpnum, unsigned long *completed) + unsigned long *gp_seq) { struct rcu_state *rsp = NULL; @@ -684,23 +686,11 @@ void rcutorture_get_gp_data(enum rcutorture_type test_type, int *flags, if (rsp == NULL) return; *flags = READ_ONCE(rsp->gp_flags); - *gpnum = READ_ONCE(rsp->gpnum); - *completed = READ_ONCE(rsp->completed); + *gp_seq = rcu_seq_current(&rsp->gp_seq); } EXPORT_SYMBOL_GPL(rcutorture_get_gp_data); /* - * Record the number of writer passes through the current rcutorture test. - * This is also used to correlate debugfs tracing stats with the rcutorture - * messages. - */ -void rcutorture_record_progress(unsigned long vernum) -{ - rcutorture_vernum++; -} -EXPORT_SYMBOL_GPL(rcutorture_record_progress); - -/* * Return the root node of the specified rcu_state structure. */ static struct rcu_node *rcu_get_root(struct rcu_state *rsp) @@ -1059,41 +1049,41 @@ void rcu_request_urgent_qs_task(struct task_struct *t) #if defined(CONFIG_PROVE_RCU) && defined(CONFIG_HOTPLUG_CPU) /* - * Is the current CPU online? Disable preemption to avoid false positives - * that could otherwise happen due to the current CPU number being sampled, - * this task being preempted, its old CPU being taken offline, resuming - * on some other CPU, then determining that its old CPU is now offline. - * It is OK to use RCU on an offline processor during initial boot, hence - * the check for rcu_scheduler_fully_active. Note also that it is OK - * for a CPU coming online to use RCU for one jiffy prior to marking itself - * online in the cpu_online_mask. Similarly, it is OK for a CPU going - * offline to continue to use RCU for one jiffy after marking itself - * offline in the cpu_online_mask. This leniency is necessary given the - * non-atomic nature of the online and offline processing, for example, - * the fact that a CPU enters the scheduler after completing the teardown - * of the CPU. + * Is the current CPU online as far as RCU is concerned? * - * This is also why RCU internally marks CPUs online during in the - * preparation phase and offline after the CPU has been taken down. + * Disable preemption to avoid false positives that could otherwise + * happen due to the current CPU number being sampled, this task being + * preempted, its old CPU being taken offline, resuming on some other CPU, + * then determining that its old CPU is now offline. Because there are + * multiple flavors of RCU, and because this function can be called in the + * midst of updating the flavors while a given CPU coming online or going + * offline, it is necessary to check all flavors. If any of the flavors + * believe that given CPU is online, it is considered to be online. * - * Disable checking if in an NMI handler because we cannot safely report - * errors from NMI handlers anyway. + * Disable checking if in an NMI handler because we cannot safely + * report errors from NMI handlers anyway. In addition, it is OK to use + * RCU on an offline processor during initial boot, hence the check for + * rcu_scheduler_fully_active. */ bool rcu_lockdep_current_cpu_online(void) { struct rcu_data *rdp; struct rcu_node *rnp; - bool ret; + struct rcu_state *rsp; - if (in_nmi()) + if (in_nmi() || !rcu_scheduler_fully_active) return true; preempt_disable(); - rdp = this_cpu_ptr(&rcu_sched_data); - rnp = rdp->mynode; - ret = (rdp->grpmask & rcu_rnp_online_cpus(rnp)) || - !rcu_scheduler_fully_active; + for_each_rcu_flavor(rsp) { + rdp = this_cpu_ptr(rsp->rda); + rnp = rdp->mynode; + if (rdp->grpmask & rcu_rnp_online_cpus(rnp)) { + preempt_enable(); + return true; + } + } preempt_enable(); - return ret; + return false; } EXPORT_SYMBOL_GPL(rcu_lockdep_current_cpu_online); @@ -1115,17 +1105,18 @@ static int rcu_is_cpu_rrupt_from_idle(void) /* * We are reporting a quiescent state on behalf of some other CPU, so * it is our responsibility to check for and handle potential overflow - * of the rcu_node ->gpnum counter with respect to the rcu_data counters. + * of the rcu_node ->gp_seq counter with respect to the rcu_data counters. * After all, the CPU might be in deep idle state, and thus executing no * code whatsoever. */ static void rcu_gpnum_ovf(struct rcu_node *rnp, struct rcu_data *rdp) { raw_lockdep_assert_held_rcu_node(rnp); - if (ULONG_CMP_LT(READ_ONCE(rdp->gpnum) + ULONG_MAX / 4, rnp->gpnum)) + if (ULONG_CMP_LT(rcu_seq_current(&rdp->gp_seq) + ULONG_MAX / 4, + rnp->gp_seq)) WRITE_ONCE(rdp->gpwrap, true); - if (ULONG_CMP_LT(rdp->rcu_iw_gpnum + ULONG_MAX / 4, rnp->gpnum)) - rdp->rcu_iw_gpnum = rnp->gpnum + ULONG_MAX / 4; + if (ULONG_CMP_LT(rdp->rcu_iw_gp_seq + ULONG_MAX / 4, rnp->gp_seq)) + rdp->rcu_iw_gp_seq = rnp->gp_seq + ULONG_MAX / 4; } /* @@ -1137,7 +1128,7 @@ static int dyntick_save_progress_counter(struct rcu_data *rdp) { rdp->dynticks_snap = rcu_dynticks_snap(rdp->dynticks); if (rcu_dynticks_in_eqs(rdp->dynticks_snap)) { - trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, TPS("dti")); + trace_rcu_fqs(rdp->rsp->name, rdp->gp_seq, rdp->cpu, TPS("dti")); rcu_gpnum_ovf(rdp->mynode, rdp); return 1; } @@ -1159,7 +1150,7 @@ static void rcu_iw_handler(struct irq_work *iwp) rnp = rdp->mynode; raw_spin_lock_rcu_node(rnp); if (!WARN_ON_ONCE(!rdp->rcu_iw_pending)) { - rdp->rcu_iw_gpnum = rnp->gpnum; + rdp->rcu_iw_gp_seq = rnp->gp_seq; rdp->rcu_iw_pending = false; } raw_spin_unlock_rcu_node(rnp); @@ -1187,7 +1178,7 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp) * of the current RCU grace period. */ if (rcu_dynticks_in_eqs_since(rdp->dynticks, rdp->dynticks_snap)) { - trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, TPS("dti")); + trace_rcu_fqs(rdp->rsp->name, rdp->gp_seq, rdp->cpu, TPS("dti")); rdp->dynticks_fqs++; rcu_gpnum_ovf(rnp, rdp); return 1; @@ -1203,8 +1194,8 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp) ruqp = per_cpu_ptr(&rcu_dynticks.rcu_urgent_qs, rdp->cpu); if (time_after(jiffies, rdp->rsp->gp_start + jtsq) && READ_ONCE(rdp->rcu_qs_ctr_snap) != per_cpu(rcu_dynticks.rcu_qs_ctr, rdp->cpu) && - READ_ONCE(rdp->gpnum) == rnp->gpnum && !rdp->gpwrap) { - trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, TPS("rqc")); + rcu_seq_current(&rdp->gp_seq) == rnp->gp_seq && !rdp->gpwrap) { + trace_rcu_fqs(rdp->rsp->name, rdp->gp_seq, rdp->cpu, TPS("rqc")); rcu_gpnum_ovf(rnp, rdp); return 1; } else if (time_after(jiffies, rdp->rsp->gp_start + jtsq)) { @@ -1212,12 +1203,25 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp) smp_store_release(ruqp, true); } - /* Check for the CPU being offline. */ - if (!(rdp->grpmask & rcu_rnp_online_cpus(rnp))) { - trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, TPS("ofl")); - rdp->offline_fqs++; - rcu_gpnum_ovf(rnp, rdp); - return 1; + /* If waiting too long on an offline CPU, complain. */ + if (!(rdp->grpmask & rcu_rnp_online_cpus(rnp)) && + time_after(jiffies, rdp->rsp->gp_start + HZ)) { + bool onl; + struct rcu_node *rnp1; + + WARN_ON(1); /* Offline CPUs are supposed to report QS! */ + pr_info("%s: grp: %d-%d level: %d ->gp_seq %ld ->completedqs %ld\n", + __func__, rnp->grplo, rnp->grphi, rnp->level, + (long)rnp->gp_seq, (long)rnp->completedqs); + for (rnp1 = rnp; rnp1; rnp1 = rnp1->parent) + pr_info("%s: %d:%d ->qsmask %#lx ->qsmaskinit %#lx ->qsmaskinitnext %#lx ->rcu_gp_init_mask %#lx\n", + __func__, rnp1->grplo, rnp1->grphi, rnp1->qsmask, rnp1->qsmaskinit, rnp1->qsmaskinitnext, rnp1->rcu_gp_init_mask); + onl = !!(rdp->grpmask & rcu_rnp_online_cpus(rnp)); + pr_info("%s %d: %c online: %ld(%d) offline: %ld(%d)\n", + __func__, rdp->cpu, ".o"[onl], + (long)rdp->rcu_onl_gp_seq, rdp->rcu_onl_gp_flags, + (long)rdp->rcu_ofl_gp_seq, rdp->rcu_ofl_gp_flags); + return 1; /* Break things loose after complaining. */ } /* @@ -1256,11 +1260,11 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp) if (jiffies - rdp->rsp->gp_start > rcu_jiffies_till_stall_check() / 2) { resched_cpu(rdp->cpu); if (IS_ENABLED(CONFIG_IRQ_WORK) && - !rdp->rcu_iw_pending && rdp->rcu_iw_gpnum != rnp->gpnum && + !rdp->rcu_iw_pending && rdp->rcu_iw_gp_seq != rnp->gp_seq && (rnp->ffmask & rdp->grpmask)) { init_irq_work(&rdp->rcu_iw, rcu_iw_handler); rdp->rcu_iw_pending = true; - rdp->rcu_iw_gpnum = rnp->gpnum; + rdp->rcu_iw_gp_seq = rnp->gp_seq; irq_work_queue_on(&rdp->rcu_iw, rdp->cpu); } } @@ -1274,9 +1278,9 @@ static void record_gp_stall_check_time(struct rcu_state *rsp) unsigned long j1; rsp->gp_start = j; - smp_wmb(); /* Record start time before stall time. */ j1 = rcu_jiffies_till_stall_check(); - WRITE_ONCE(rsp->jiffies_stall, j + j1); + /* Record ->gp_start before ->jiffies_stall. */ + smp_store_release(&rsp->jiffies_stall, j + j1); /* ^^^ */ rsp->jiffies_resched = j + j1 / 2; rsp->n_force_qs_gpstart = READ_ONCE(rsp->n_force_qs); } @@ -1302,9 +1306,9 @@ static void rcu_check_gp_kthread_starvation(struct rcu_state *rsp) j = jiffies; gpa = READ_ONCE(rsp->gp_activity); if (j - gpa > 2 * HZ) { - pr_err("%s kthread starved for %ld jiffies! g%lu c%lu f%#x %s(%d) ->state=%#lx ->cpu=%d\n", + pr_err("%s kthread starved for %ld jiffies! g%ld f%#x %s(%d) ->state=%#lx ->cpu=%d\n", rsp->name, j - gpa, - rsp->gpnum, rsp->completed, + (long)rcu_seq_current(&rsp->gp_seq), rsp->gp_flags, gp_state_getname(rsp->gp_state), rsp->gp_state, rsp->gp_kthread ? rsp->gp_kthread->state : ~0, @@ -1359,16 +1363,15 @@ static void rcu_stall_kick_kthreads(struct rcu_state *rsp) } } -static inline void panic_on_rcu_stall(void) +static void panic_on_rcu_stall(void) { if (sysctl_panic_on_rcu_stall) panic("RCU Stall\n"); } -static void print_other_cpu_stall(struct rcu_state *rsp, unsigned long gpnum) +static void print_other_cpu_stall(struct rcu_state *rsp, unsigned long gp_seq) { int cpu; - long delta; unsigned long flags; unsigned long gpa; unsigned long j; @@ -1381,25 +1384,12 @@ static void print_other_cpu_stall(struct rcu_state *rsp, unsigned long gpnum) if (rcu_cpu_stall_suppress) return; - /* Only let one CPU complain about others per time interval. */ - - raw_spin_lock_irqsave_rcu_node(rnp, flags); - delta = jiffies - READ_ONCE(rsp->jiffies_stall); - if (delta < RCU_STALL_RAT_DELAY || !rcu_gp_in_progress(rsp)) { - raw_spin_unlock_irqrestore_rcu_node(rnp, flags); - return; - } - WRITE_ONCE(rsp->jiffies_stall, - jiffies + 3 * rcu_jiffies_till_stall_check() + 3); - raw_spin_unlock_irqrestore_rcu_node(rnp, flags); - /* * OK, time to rat on our buddy... * See Documentation/RCU/stallwarn.txt for info on how to debug * RCU CPU stall warnings. */ - pr_err("INFO: %s detected stalls on CPUs/tasks:", - rsp->name); + pr_err("INFO: %s detected stalls on CPUs/tasks:", rsp->name); print_cpu_stall_info_begin(); rcu_for_each_leaf_node(rsp, rnp) { raw_spin_lock_irqsave_rcu_node(rnp, flags); @@ -1418,17 +1408,16 @@ static void print_other_cpu_stall(struct rcu_state *rsp, unsigned long gpnum) for_each_possible_cpu(cpu) totqlen += rcu_segcblist_n_cbs(&per_cpu_ptr(rsp->rda, cpu)->cblist); - pr_cont("(detected by %d, t=%ld jiffies, g=%ld, c=%ld, q=%lu)\n", + pr_cont("(detected by %d, t=%ld jiffies, g=%ld, q=%lu)\n", smp_processor_id(), (long)(jiffies - rsp->gp_start), - (long)rsp->gpnum, (long)rsp->completed, totqlen); + (long)rcu_seq_current(&rsp->gp_seq), totqlen); if (ndetected) { rcu_dump_cpu_stacks(rsp); /* Complain about tasks blocking the grace period. */ rcu_print_detail_task_stall(rsp); } else { - if (READ_ONCE(rsp->gpnum) != gpnum || - READ_ONCE(rsp->completed) == gpnum) { + if (rcu_seq_current(&rsp->gp_seq) != gp_seq) { pr_err("INFO: Stall ended before state dump start\n"); } else { j = jiffies; @@ -1441,6 +1430,10 @@ static void print_other_cpu_stall(struct rcu_state *rsp, unsigned long gpnum) sched_show_task(current); } } + /* Rewrite if needed in case of slow consoles. */ + if (ULONG_CMP_GE(jiffies, READ_ONCE(rsp->jiffies_stall))) + WRITE_ONCE(rsp->jiffies_stall, + jiffies + 3 * rcu_jiffies_till_stall_check() + 3); rcu_check_gp_kthread_starvation(rsp); @@ -1476,15 +1469,16 @@ static void print_cpu_stall(struct rcu_state *rsp) for_each_possible_cpu(cpu) totqlen += rcu_segcblist_n_cbs(&per_cpu_ptr(rsp->rda, cpu)->cblist); - pr_cont(" (t=%lu jiffies g=%ld c=%ld q=%lu)\n", + pr_cont(" (t=%lu jiffies g=%ld q=%lu)\n", jiffies - rsp->gp_start, - (long)rsp->gpnum, (long)rsp->completed, totqlen); + (long)rcu_seq_current(&rsp->gp_seq), totqlen); rcu_check_gp_kthread_starvation(rsp); rcu_dump_cpu_stacks(rsp); raw_spin_lock_irqsave_rcu_node(rnp, flags); + /* Rewrite if needed in case of slow consoles. */ if (ULONG_CMP_GE(jiffies, READ_ONCE(rsp->jiffies_stall))) WRITE_ONCE(rsp->jiffies_stall, jiffies + 3 * rcu_jiffies_till_stall_check() + 3); @@ -1504,10 +1498,11 @@ static void print_cpu_stall(struct rcu_state *rsp) static void check_cpu_stall(struct rcu_state *rsp, struct rcu_data *rdp) { - unsigned long completed; - unsigned long gpnum; + unsigned long gs1; + unsigned long gs2; unsigned long gps; unsigned long j; + unsigned long jn; unsigned long js; struct rcu_node *rnp; @@ -1520,43 +1515,46 @@ static void check_cpu_stall(struct rcu_state *rsp, struct rcu_data *rdp) /* * Lots of memory barriers to reject false positives. * - * The idea is to pick up rsp->gpnum, then rsp->jiffies_stall, - * then rsp->gp_start, and finally rsp->completed. These values - * are updated in the opposite order with memory barriers (or - * equivalent) during grace-period initialization and cleanup. - * Now, a false positive can occur if we get an new value of - * rsp->gp_start and a old value of rsp->jiffies_stall. But given - * the memory barriers, the only way that this can happen is if one - * grace period ends and another starts between these two fetches. - * Detect this by comparing rsp->completed with the previous fetch - * from rsp->gpnum. + * The idea is to pick up rsp->gp_seq, then rsp->jiffies_stall, + * then rsp->gp_start, and finally another copy of rsp->gp_seq. + * These values are updated in the opposite order with memory + * barriers (or equivalent) during grace-period initialization + * and cleanup. Now, a false positive can occur if we get an new + * value of rsp->gp_start and a old value of rsp->jiffies_stall. + * But given the memory barriers, the only way that this can happen + * is if one grace period ends and another starts between these + * two fetches. This is detected by comparing the second fetch + * of rsp->gp_seq with the previous fetch from rsp->gp_seq. * * Given this check, comparisons of jiffies, rsp->jiffies_stall, * and rsp->gp_start suffice to forestall false positives. */ - gpnum = READ_ONCE(rsp->gpnum); - smp_rmb(); /* Pick up ->gpnum first... */ + gs1 = READ_ONCE(rsp->gp_seq); + smp_rmb(); /* Pick up ->gp_seq first... */ js = READ_ONCE(rsp->jiffies_stall); smp_rmb(); /* ...then ->jiffies_stall before the rest... */ gps = READ_ONCE(rsp->gp_start); - smp_rmb(); /* ...and finally ->gp_start before ->completed. */ - completed = READ_ONCE(rsp->completed); - if (ULONG_CMP_GE(completed, gpnum) || + smp_rmb(); /* ...and finally ->gp_start before ->gp_seq again. */ + gs2 = READ_ONCE(rsp->gp_seq); + if (gs1 != gs2 || ULONG_CMP_LT(j, js) || ULONG_CMP_GE(gps, js)) return; /* No stall or GP completed since entering function. */ rnp = rdp->mynode; + jn = jiffies + 3 * rcu_jiffies_till_stall_check() + 3; if (rcu_gp_in_progress(rsp) && - (READ_ONCE(rnp->qsmask) & rdp->grpmask)) { + (READ_ONCE(rnp->qsmask) & rdp->grpmask) && + cmpxchg(&rsp->jiffies_stall, js, jn) == js) { /* We haven't checked in, so go dump stack. */ print_cpu_stall(rsp); } else if (rcu_gp_in_progress(rsp) && - ULONG_CMP_GE(j, js + RCU_STALL_RAT_DELAY)) { + ULONG_CMP_GE(j, js + RCU_STALL_RAT_DELAY) && + cmpxchg(&rsp->jiffies_stall, js, jn) == js) { /* They had a few time units to dump stack, so complain. */ - print_other_cpu_stall(rsp, gpnum); + print_other_cpu_stall(rsp, gs2); } } @@ -1577,123 +1575,99 @@ void rcu_cpu_stall_reset(void) WRITE_ONCE(rsp->jiffies_stall, jiffies + ULONG_MAX / 2); } -/* - * Determine the value that ->completed will have at the end of the - * next subsequent grace period. This is used to tag callbacks so that - * a CPU can invoke callbacks in a timely fashion even if that CPU has - * been dyntick-idle for an extended period with callbacks under the - * influence of RCU_FAST_NO_HZ. - * - * The caller must hold rnp->lock with interrupts disabled. - */ -static unsigned long rcu_cbs_completed(struct rcu_state *rsp, - struct rcu_node *rnp) -{ - raw_lockdep_assert_held_rcu_node(rnp); - - /* - * If RCU is idle, we just wait for the next grace period. - * But we can only be sure that RCU is idle if we are looking - * at the root rcu_node structure -- otherwise, a new grace - * period might have started, but just not yet gotten around - * to initializing the current non-root rcu_node structure. - */ - if (rcu_get_root(rsp) == rnp && rnp->gpnum == rnp->completed) - return rnp->completed + 1; - - /* - * If the current rcu_node structure believes that RCU is - * idle, and if the rcu_state structure does not yet reflect - * the start of a new grace period, then the next grace period - * will suffice. The memory barrier is needed to accurately - * sample the rsp->gpnum, and pairs with the second lock - * acquisition in rcu_gp_init(), which is augmented with - * smp_mb__after_unlock_lock() for this purpose. - */ - if (rnp->gpnum == rnp->completed) { - smp_mb(); /* See above block comment. */ - if (READ_ONCE(rsp->gpnum) == rnp->completed) - return rnp->completed + 1; - } - - /* - * Otherwise, wait for a possible partial grace period and - * then the subsequent full grace period. - */ - return rnp->completed + 2; -} - /* Trace-event wrapper function for trace_rcu_future_grace_period. */ static void trace_rcu_this_gp(struct rcu_node *rnp, struct rcu_data *rdp, - unsigned long c, const char *s) + unsigned long gp_seq_req, const char *s) { - trace_rcu_future_grace_period(rdp->rsp->name, rnp->gpnum, - rnp->completed, c, rnp->level, - rnp->grplo, rnp->grphi, s); + trace_rcu_future_grace_period(rdp->rsp->name, rnp->gp_seq, gp_seq_req, + rnp->level, rnp->grplo, rnp->grphi, s); } /* + * rcu_start_this_gp - Request the start of a particular grace period + * @rnp_start: The leaf node of the CPU from which to start. + * @rdp: The rcu_data corresponding to the CPU from which to start. + * @gp_seq_req: The gp_seq of the grace period to start. + * * Start the specified grace period, as needed to handle newly arrived * callbacks. The required future grace periods are recorded in each - * rcu_node structure's ->need_future_gp[] field. Returns true if there + * rcu_node structure's ->gp_seq_needed field. Returns true if there * is reason to awaken the grace-period kthread. * * The caller must hold the specified rcu_node structure's ->lock, which * is why the caller is responsible for waking the grace-period kthread. + * + * Returns true if the GP thread needs to be awakened else false. */ -static bool rcu_start_this_gp(struct rcu_node *rnp, struct rcu_data *rdp, - unsigned long c) +static bool rcu_start_this_gp(struct rcu_node *rnp_start, struct rcu_data *rdp, + unsigned long gp_seq_req) { bool ret = false; struct rcu_state *rsp = rdp->rsp; - struct rcu_node *rnp_root; + struct rcu_node *rnp; /* * Use funnel locking to either acquire the root rcu_node * structure's lock or bail out if the need for this grace period - * has already been recorded -- or has already started. If there - * is already a grace period in progress in a non-leaf node, no - * recording is needed because the end of the grace period will - * scan the leaf rcu_node structures. Note that rnp->lock must - * not be released. + * has already been recorded -- or if that grace period has in + * fact already started. If there is already a grace period in + * progress in a non-leaf node, no recording is needed because the + * end of the grace period will scan the leaf rcu_node structures. + * Note that rnp_start->lock must not be released. */ - raw_lockdep_assert_held_rcu_node(rnp); - trace_rcu_this_gp(rnp, rdp, c, TPS("Startleaf")); - for (rnp_root = rnp; 1; rnp_root = rnp_root->parent) { - if (rnp_root != rnp) - raw_spin_lock_rcu_node(rnp_root); - WARN_ON_ONCE(ULONG_CMP_LT(rnp_root->gpnum + - need_future_gp_mask(), c)); - if (need_future_gp_element(rnp_root, c) || - ULONG_CMP_GE(rnp_root->gpnum, c) || - (rnp != rnp_root && - rnp_root->gpnum != rnp_root->completed)) { - trace_rcu_this_gp(rnp_root, rdp, c, TPS("Prestarted")); + raw_lockdep_assert_held_rcu_node(rnp_start); + trace_rcu_this_gp(rnp_start, rdp, gp_seq_req, TPS("Startleaf")); + for (rnp = rnp_start; 1; rnp = rnp->parent) { + if (rnp != rnp_start) + raw_spin_lock_rcu_node(rnp); + if (ULONG_CMP_GE(rnp->gp_seq_needed, gp_seq_req) || + rcu_seq_started(&rnp->gp_seq, gp_seq_req) || + (rnp != rnp_start && + rcu_seq_state(rcu_seq_current(&rnp->gp_seq)))) { + trace_rcu_this_gp(rnp, rdp, gp_seq_req, + TPS("Prestarted")); goto unlock_out; } - need_future_gp_element(rnp_root, c) = true; - if (rnp_root != rnp && rnp_root->parent != NULL) - raw_spin_unlock_rcu_node(rnp_root); - if (!rnp_root->parent) + rnp->gp_seq_needed = gp_seq_req; + if (rcu_seq_state(rcu_seq_current(&rnp->gp_seq))) { + /* + * We just marked the leaf or internal node, and a + * grace period is in progress, which means that + * rcu_gp_cleanup() will see the marking. Bail to + * reduce contention. + */ + trace_rcu_this_gp(rnp_start, rdp, gp_seq_req, + TPS("Startedleaf")); + goto unlock_out; + } + if (rnp != rnp_start && rnp->parent != NULL) + raw_spin_unlock_rcu_node(rnp); + if (!rnp->parent) break; /* At root, and perhaps also leaf. */ } /* If GP already in progress, just leave, otherwise start one. */ - if (rnp_root->gpnum != rnp_root->completed) { - trace_rcu_this_gp(rnp_root, rdp, c, TPS("Startedleafroot")); + if (rcu_gp_in_progress(rsp)) { + trace_rcu_this_gp(rnp, rdp, gp_seq_req, TPS("Startedleafroot")); goto unlock_out; } - trace_rcu_this_gp(rnp_root, rdp, c, TPS("Startedroot")); + trace_rcu_this_gp(rnp, rdp, gp_seq_req, TPS("Startedroot")); WRITE_ONCE(rsp->gp_flags, rsp->gp_flags | RCU_GP_FLAG_INIT); + rsp->gp_req_activity = jiffies; if (!rsp->gp_kthread) { - trace_rcu_this_gp(rnp_root, rdp, c, TPS("NoGPkthread")); + trace_rcu_this_gp(rnp, rdp, gp_seq_req, TPS("NoGPkthread")); goto unlock_out; } - trace_rcu_grace_period(rsp->name, READ_ONCE(rsp->gpnum), TPS("newreq")); + trace_rcu_grace_period(rsp->name, READ_ONCE(rsp->gp_seq), TPS("newreq")); ret = true; /* Caller must wake GP kthread. */ unlock_out: - if (rnp != rnp_root) - raw_spin_unlock_rcu_node(rnp_root); + /* Push furthest requested GP to leaf node and rcu_data structure. */ + if (ULONG_CMP_LT(gp_seq_req, rnp->gp_seq_needed)) { + rnp_start->gp_seq_needed = rnp->gp_seq_needed; + rdp->gp_seq_needed = rnp->gp_seq_needed; + } + if (rnp != rnp_start) + raw_spin_unlock_rcu_node(rnp); return ret; } @@ -1703,13 +1677,13 @@ unlock_out: */ static bool rcu_future_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp) { - unsigned long c = rnp->completed; bool needmore; struct rcu_data *rdp = this_cpu_ptr(rsp->rda); - need_future_gp_element(rnp, c) = false; - needmore = need_any_future_gp(rnp); - trace_rcu_this_gp(rnp, rdp, c, + needmore = ULONG_CMP_LT(rnp->gp_seq, rnp->gp_seq_needed); + if (!needmore) + rnp->gp_seq_needed = rnp->gp_seq; /* Avoid counter wrap. */ + trace_rcu_this_gp(rnp, rdp, rnp->gp_seq, needmore ? TPS("CleanupMore") : TPS("Cleanup")); return needmore; } @@ -1727,25 +1701,25 @@ static void rcu_gp_kthread_wake(struct rcu_state *rsp) !READ_ONCE(rsp->gp_flags) || !rsp->gp_kthread) return; - swake_up(&rsp->gp_wq); + swake_up_one(&rsp->gp_wq); } /* - * If there is room, assign a ->completed number to any callbacks on - * this CPU that have not already been assigned. Also accelerate any - * callbacks that were previously assigned a ->completed number that has - * since proven to be too conservative, which can happen if callbacks get - * assigned a ->completed number while RCU is idle, but with reference to - * a non-root rcu_node structure. This function is idempotent, so it does - * not hurt to call it repeatedly. Returns an flag saying that we should - * awaken the RCU grace-period kthread. + * If there is room, assign a ->gp_seq number to any callbacks on this + * CPU that have not already been assigned. Also accelerate any callbacks + * that were previously assigned a ->gp_seq number that has since proven + * to be too conservative, which can happen if callbacks get assigned a + * ->gp_seq number while RCU is idle, but with reference to a non-root + * rcu_node structure. This function is idempotent, so it does not hurt + * to call it repeatedly. Returns an flag saying that we should awaken + * the RCU grace-period kthread. * * The caller must hold rnp->lock with interrupts disabled. */ static bool rcu_accelerate_cbs(struct rcu_state *rsp, struct rcu_node *rnp, struct rcu_data *rdp) { - unsigned long c; + unsigned long gp_seq_req; bool ret = false; raw_lockdep_assert_held_rcu_node(rnp); @@ -1764,22 +1738,50 @@ static bool rcu_accelerate_cbs(struct rcu_state *rsp, struct rcu_node *rnp, * accelerating callback invocation to an earlier grace-period * number. */ - c = rcu_cbs_completed(rsp, rnp); - if (rcu_segcblist_accelerate(&rdp->cblist, c)) - ret = rcu_start_this_gp(rnp, rdp, c); + gp_seq_req = rcu_seq_snap(&rsp->gp_seq); + if (rcu_segcblist_accelerate(&rdp->cblist, gp_seq_req)) + ret = rcu_start_this_gp(rnp, rdp, gp_seq_req); /* Trace depending on how much we were able to accelerate. */ if (rcu_segcblist_restempty(&rdp->cblist, RCU_WAIT_TAIL)) - trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("AccWaitCB")); + trace_rcu_grace_period(rsp->name, rdp->gp_seq, TPS("AccWaitCB")); else - trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("AccReadyCB")); + trace_rcu_grace_period(rsp->name, rdp->gp_seq, TPS("AccReadyCB")); return ret; } /* + * Similar to rcu_accelerate_cbs(), but does not require that the leaf + * rcu_node structure's ->lock be held. It consults the cached value + * of ->gp_seq_needed in the rcu_data structure, and if that indicates + * that a new grace-period request be made, invokes rcu_accelerate_cbs() + * while holding the leaf rcu_node structure's ->lock. + */ +static void rcu_accelerate_cbs_unlocked(struct rcu_state *rsp, + struct rcu_node *rnp, + struct rcu_data *rdp) +{ + unsigned long c; + bool needwake; + + lockdep_assert_irqs_disabled(); + c = rcu_seq_snap(&rsp->gp_seq); + if (!rdp->gpwrap && ULONG_CMP_GE(rdp->gp_seq_needed, c)) { + /* Old request still live, so mark recent callbacks. */ + (void)rcu_segcblist_accelerate(&rdp->cblist, c); + return; + } + raw_spin_lock_rcu_node(rnp); /* irqs already disabled. */ + needwake = rcu_accelerate_cbs(rsp, rnp, rdp); + raw_spin_unlock_rcu_node(rnp); /* irqs remain disabled. */ + if (needwake) + rcu_gp_kthread_wake(rsp); +} + +/* * Move any callbacks whose grace period has completed to the * RCU_DONE_TAIL sublist, then compact the remaining sublists and - * assign ->completed numbers to any callbacks in the RCU_NEXT_TAIL + * assign ->gp_seq numbers to any callbacks in the RCU_NEXT_TAIL * sublist. This function is idempotent, so it does not hurt to * invoke it repeatedly. As long as it is not invoked -too- often... * Returns true if the RCU grace-period kthread needs to be awakened. @@ -1796,10 +1798,10 @@ static bool rcu_advance_cbs(struct rcu_state *rsp, struct rcu_node *rnp, return false; /* - * Find all callbacks whose ->completed numbers indicate that they + * Find all callbacks whose ->gp_seq numbers indicate that they * are ready to invoke, and put them into the RCU_DONE_TAIL sublist. */ - rcu_segcblist_advance(&rdp->cblist, rnp->completed); + rcu_segcblist_advance(&rdp->cblist, rnp->gp_seq); /* Classify any remaining callbacks. */ return rcu_accelerate_cbs(rsp, rnp, rdp); @@ -1819,39 +1821,38 @@ static bool __note_gp_changes(struct rcu_state *rsp, struct rcu_node *rnp, raw_lockdep_assert_held_rcu_node(rnp); - /* Handle the ends of any preceding grace periods first. */ - if (rdp->completed == rnp->completed && - !unlikely(READ_ONCE(rdp->gpwrap))) { - - /* No grace period end, so just accelerate recent callbacks. */ - ret = rcu_accelerate_cbs(rsp, rnp, rdp); + if (rdp->gp_seq == rnp->gp_seq) + return false; /* Nothing to do. */ + /* Handle the ends of any preceding grace periods first. */ + if (rcu_seq_completed_gp(rdp->gp_seq, rnp->gp_seq) || + unlikely(READ_ONCE(rdp->gpwrap))) { + ret = rcu_advance_cbs(rsp, rnp, rdp); /* Advance callbacks. */ + trace_rcu_grace_period(rsp->name, rdp->gp_seq, TPS("cpuend")); } else { - - /* Advance callbacks. */ - ret = rcu_advance_cbs(rsp, rnp, rdp); - - /* Remember that we saw this grace-period completion. */ - rdp->completed = rnp->completed; - trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("cpuend")); + ret = rcu_accelerate_cbs(rsp, rnp, rdp); /* Recent callbacks. */ } - if (rdp->gpnum != rnp->gpnum || unlikely(READ_ONCE(rdp->gpwrap))) { + /* Now handle the beginnings of any new-to-this-CPU grace periods. */ + if (rcu_seq_new_gp(rdp->gp_seq, rnp->gp_seq) || + unlikely(READ_ONCE(rdp->gpwrap))) { /* * If the current grace period is waiting for this CPU, * set up to detect a quiescent state, otherwise don't * go looking for one. */ - rdp->gpnum = rnp->gpnum; - trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("cpustart")); + trace_rcu_grace_period(rsp->name, rnp->gp_seq, TPS("cpustart")); need_gp = !!(rnp->qsmask & rdp->grpmask); rdp->cpu_no_qs.b.norm = need_gp; rdp->rcu_qs_ctr_snap = __this_cpu_read(rcu_dynticks.rcu_qs_ctr); rdp->core_needs_qs = need_gp; zero_cpu_stall_ticks(rdp); - WRITE_ONCE(rdp->gpwrap, false); - rcu_gpnum_ovf(rnp, rdp); } + rdp->gp_seq = rnp->gp_seq; /* Remember new grace-period state. */ + if (ULONG_CMP_GE(rnp->gp_seq_needed, rdp->gp_seq_needed) || rdp->gpwrap) + rdp->gp_seq_needed = rnp->gp_seq_needed; + WRITE_ONCE(rdp->gpwrap, false); + rcu_gpnum_ovf(rnp, rdp); return ret; } @@ -1863,8 +1864,7 @@ static void note_gp_changes(struct rcu_state *rsp, struct rcu_data *rdp) local_irq_save(flags); rnp = rdp->mynode; - if ((rdp->gpnum == READ_ONCE(rnp->gpnum) && - rdp->completed == READ_ONCE(rnp->completed) && + if ((rdp->gp_seq == rcu_seq_current(&rnp->gp_seq) && !unlikely(READ_ONCE(rdp->gpwrap))) || /* w/out lock. */ !raw_spin_trylock_rcu_node(rnp)) { /* irqs already off, so later. */ local_irq_restore(flags); @@ -1879,7 +1879,8 @@ static void note_gp_changes(struct rcu_state *rsp, struct rcu_data *rdp) static void rcu_gp_slow(struct rcu_state *rsp, int delay) { if (delay > 0 && - !(rsp->gpnum % (rcu_num_nodes * PER_RCU_NODE_PERIOD * delay))) + !(rcu_seq_ctr(rsp->gp_seq) % + (rcu_num_nodes * PER_RCU_NODE_PERIOD * delay))) schedule_timeout_uninterruptible(delay); } @@ -1888,7 +1889,9 @@ static void rcu_gp_slow(struct rcu_state *rsp, int delay) */ static bool rcu_gp_init(struct rcu_state *rsp) { + unsigned long flags; unsigned long oldmask; + unsigned long mask; struct rcu_data *rdp; struct rcu_node *rnp = rcu_get_root(rsp); @@ -1912,9 +1915,9 @@ static bool rcu_gp_init(struct rcu_state *rsp) /* Advance to a new grace period and initialize state. */ record_gp_stall_check_time(rsp); - /* Record GP times before starting GP, hence smp_store_release(). */ - smp_store_release(&rsp->gpnum, rsp->gpnum + 1); - trace_rcu_grace_period(rsp->name, rsp->gpnum, TPS("start")); + /* Record GP times before starting GP, hence rcu_seq_start(). */ + rcu_seq_start(&rsp->gp_seq); + trace_rcu_grace_period(rsp->name, rsp->gp_seq, TPS("start")); raw_spin_unlock_irq_rcu_node(rnp); /* @@ -1923,13 +1926,15 @@ static bool rcu_gp_init(struct rcu_state *rsp) * for subsequent online CPUs, and that quiescent-state forcing * will handle subsequent offline CPUs. */ + rsp->gp_state = RCU_GP_ONOFF; rcu_for_each_leaf_node(rsp, rnp) { - rcu_gp_slow(rsp, gp_preinit_delay); + spin_lock(&rsp->ofl_lock); raw_spin_lock_irq_rcu_node(rnp); if (rnp->qsmaskinit == rnp->qsmaskinitnext && !rnp->wait_blkd_tasks) { /* Nothing to do on this leaf rcu_node structure. */ raw_spin_unlock_irq_rcu_node(rnp); + spin_unlock(&rsp->ofl_lock); continue; } @@ -1939,12 +1944,14 @@ static bool rcu_gp_init(struct rcu_state *rsp) /* If zero-ness of ->qsmaskinit changed, propagate up tree. */ if (!oldmask != !rnp->qsmaskinit) { - if (!oldmask) /* First online CPU for this rcu_node. */ - rcu_init_new_rnp(rnp); - else if (rcu_preempt_has_tasks(rnp)) /* blocked tasks */ - rnp->wait_blkd_tasks = true; - else /* Last offline CPU and can propagate. */ + if (!oldmask) { /* First online CPU for rcu_node. */ + if (!rnp->wait_blkd_tasks) /* Ever offline? */ + rcu_init_new_rnp(rnp); + } else if (rcu_preempt_has_tasks(rnp)) { + rnp->wait_blkd_tasks = true; /* blocked tasks */ + } else { /* Last offline CPU and can propagate. */ rcu_cleanup_dead_rnp(rnp); + } } /* @@ -1953,18 +1960,19 @@ static bool rcu_gp_init(struct rcu_state *rsp) * still offline, propagate up the rcu_node tree and * clear ->wait_blkd_tasks. Otherwise, if one of this * rcu_node structure's CPUs has since come back online, - * simply clear ->wait_blkd_tasks (but rcu_cleanup_dead_rnp() - * checks for this, so just call it unconditionally). + * simply clear ->wait_blkd_tasks. */ if (rnp->wait_blkd_tasks && - (!rcu_preempt_has_tasks(rnp) || - rnp->qsmaskinit)) { + (!rcu_preempt_has_tasks(rnp) || rnp->qsmaskinit)) { rnp->wait_blkd_tasks = false; - rcu_cleanup_dead_rnp(rnp); + if (!rnp->qsmaskinit) + rcu_cleanup_dead_rnp(rnp); } raw_spin_unlock_irq_rcu_node(rnp); + spin_unlock(&rsp->ofl_lock); } + rcu_gp_slow(rsp, gp_preinit_delay); /* Races with CPU hotplug. */ /* * Set the quiescent-state-needed bits in all the rcu_node @@ -1978,22 +1986,27 @@ static bool rcu_gp_init(struct rcu_state *rsp) * The grace period cannot complete until the initialization * process finishes, because this kthread handles both. */ + rsp->gp_state = RCU_GP_INIT; rcu_for_each_node_breadth_first(rsp, rnp) { rcu_gp_slow(rsp, gp_init_delay); - raw_spin_lock_irq_rcu_node(rnp); + raw_spin_lock_irqsave_rcu_node(rnp, flags); rdp = this_cpu_ptr(rsp->rda); - rcu_preempt_check_blocked_tasks(rnp); + rcu_preempt_check_blocked_tasks(rsp, rnp); rnp->qsmask = rnp->qsmaskinit; - WRITE_ONCE(rnp->gpnum, rsp->gpnum); - if (WARN_ON_ONCE(rnp->completed != rsp->completed)) - WRITE_ONCE(rnp->completed, rsp->completed); + WRITE_ONCE(rnp->gp_seq, rsp->gp_seq); if (rnp == rdp->mynode) (void)__note_gp_changes(rsp, rnp, rdp); rcu_preempt_boost_start_gp(rnp); - trace_rcu_grace_period_init(rsp->name, rnp->gpnum, + trace_rcu_grace_period_init(rsp->name, rnp->gp_seq, rnp->level, rnp->grplo, rnp->grphi, rnp->qsmask); - raw_spin_unlock_irq_rcu_node(rnp); + /* Quiescent states for tasks on any now-offline CPUs. */ + mask = rnp->qsmask & ~rnp->qsmaskinitnext; + rnp->rcu_gp_init_mask = mask; + if ((mask || rnp->wait_blkd_tasks) && rcu_is_leaf_node(rnp)) + rcu_report_qs_rnp(mask, rsp, rnp, rnp->gp_seq, flags); + else + raw_spin_unlock_irq_rcu_node(rnp); cond_resched_tasks_rcu_qs(); WRITE_ONCE(rsp->gp_activity, jiffies); } @@ -2002,7 +2015,7 @@ static bool rcu_gp_init(struct rcu_state *rsp) } /* - * Helper function for swait_event_idle() wakeup at force-quiescent-state + * Helper function for swait_event_idle_exclusive() wakeup at force-quiescent-state * time. */ static bool rcu_gp_fqs_check_wake(struct rcu_state *rsp, int *gfp) @@ -2053,6 +2066,7 @@ static void rcu_gp_cleanup(struct rcu_state *rsp) { unsigned long gp_duration; bool needgp = false; + unsigned long new_gp_seq; struct rcu_data *rdp; struct rcu_node *rnp = rcu_get_root(rsp); struct swait_queue_head *sq; @@ -2074,19 +2088,22 @@ static void rcu_gp_cleanup(struct rcu_state *rsp) raw_spin_unlock_irq_rcu_node(rnp); /* - * Propagate new ->completed value to rcu_node structures so - * that other CPUs don't have to wait until the start of the next - * grace period to process their callbacks. This also avoids - * some nasty RCU grace-period initialization races by forcing - * the end of the current grace period to be completely recorded in - * all of the rcu_node structures before the beginning of the next - * grace period is recorded in any of the rcu_node structures. + * Propagate new ->gp_seq value to rcu_node structures so that + * other CPUs don't have to wait until the start of the next grace + * period to process their callbacks. This also avoids some nasty + * RCU grace-period initialization races by forcing the end of + * the current grace period to be completely recorded in all of + * the rcu_node structures before the beginning of the next grace + * period is recorded in any of the rcu_node structures. */ + new_gp_seq = rsp->gp_seq; + rcu_seq_end(&new_gp_seq); rcu_for_each_node_breadth_first(rsp, rnp) { raw_spin_lock_irq_rcu_node(rnp); - WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp)); + if (WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp))) + dump_blkd_tasks(rsp, rnp, 10); WARN_ON_ONCE(rnp->qsmask); - WRITE_ONCE(rnp->completed, rsp->gpnum); + WRITE_ONCE(rnp->gp_seq, new_gp_seq); rdp = this_cpu_ptr(rsp->rda); if (rnp == rdp->mynode) needgp = __note_gp_changes(rsp, rnp, rdp) || needgp; @@ -2100,26 +2117,28 @@ static void rcu_gp_cleanup(struct rcu_state *rsp) rcu_gp_slow(rsp, gp_cleanup_delay); } rnp = rcu_get_root(rsp); - raw_spin_lock_irq_rcu_node(rnp); /* Order GP before ->completed update. */ + raw_spin_lock_irq_rcu_node(rnp); /* GP before rsp->gp_seq update. */ /* Declare grace period done. */ - WRITE_ONCE(rsp->completed, rsp->gpnum); - trace_rcu_grace_period(rsp->name, rsp->completed, TPS("end")); + rcu_seq_end(&rsp->gp_seq); + trace_rcu_grace_period(rsp->name, rsp->gp_seq, TPS("end")); rsp->gp_state = RCU_GP_IDLE; /* Check for GP requests since above loop. */ rdp = this_cpu_ptr(rsp->rda); - if (need_any_future_gp(rnp)) { - trace_rcu_this_gp(rnp, rdp, rsp->completed - 1, + if (!needgp && ULONG_CMP_LT(rnp->gp_seq, rnp->gp_seq_needed)) { + trace_rcu_this_gp(rnp, rdp, rnp->gp_seq_needed, TPS("CleanupMore")); needgp = true; } /* Advance CBs to reduce false positives below. */ if (!rcu_accelerate_cbs(rsp, rnp, rdp) && needgp) { WRITE_ONCE(rsp->gp_flags, RCU_GP_FLAG_INIT); - trace_rcu_grace_period(rsp->name, READ_ONCE(rsp->gpnum), + rsp->gp_req_activity = jiffies; + trace_rcu_grace_period(rsp->name, READ_ONCE(rsp->gp_seq), TPS("newreq")); + } else { + WRITE_ONCE(rsp->gp_flags, rsp->gp_flags & RCU_GP_FLAG_INIT); } - WRITE_ONCE(rsp->gp_flags, rsp->gp_flags & RCU_GP_FLAG_INIT); raw_spin_unlock_irq_rcu_node(rnp); } @@ -2141,10 +2160,10 @@ static int __noreturn rcu_gp_kthread(void *arg) /* Handle grace-period start. */ for (;;) { trace_rcu_grace_period(rsp->name, - READ_ONCE(rsp->gpnum), + READ_ONCE(rsp->gp_seq), TPS("reqwait")); rsp->gp_state = RCU_GP_WAIT_GPS; - swait_event_idle(rsp->gp_wq, READ_ONCE(rsp->gp_flags) & + swait_event_idle_exclusive(rsp->gp_wq, READ_ONCE(rsp->gp_flags) & RCU_GP_FLAG_INIT); rsp->gp_state = RCU_GP_DONE_GPS; /* Locking provides needed memory barrier. */ @@ -2154,17 +2173,13 @@ static int __noreturn rcu_gp_kthread(void *arg) WRITE_ONCE(rsp->gp_activity, jiffies); WARN_ON(signal_pending(current)); trace_rcu_grace_period(rsp->name, - READ_ONCE(rsp->gpnum), + READ_ONCE(rsp->gp_seq), TPS("reqwaitsig")); } /* Handle quiescent-state forcing. */ first_gp_fqs = true; j = jiffies_till_first_fqs; - if (j > HZ) { - j = HZ; - jiffies_till_first_fqs = HZ; - } ret = 0; for (;;) { if (!ret) { @@ -2173,10 +2188,10 @@ static int __noreturn rcu_gp_kthread(void *arg) jiffies + 3 * j); } trace_rcu_grace_period(rsp->name, - READ_ONCE(rsp->gpnum), + READ_ONCE(rsp->gp_seq), TPS("fqswait")); rsp->gp_state = RCU_GP_WAIT_FQS; - ret = swait_event_idle_timeout(rsp->gp_wq, + ret = swait_event_idle_timeout_exclusive(rsp->gp_wq, rcu_gp_fqs_check_wake(rsp, &gf), j); rsp->gp_state = RCU_GP_DOING_FQS; /* Locking provides needed memory barriers. */ @@ -2188,31 +2203,24 @@ static int __noreturn rcu_gp_kthread(void *arg) if (ULONG_CMP_GE(jiffies, rsp->jiffies_force_qs) || (gf & RCU_GP_FLAG_FQS)) { trace_rcu_grace_period(rsp->name, - READ_ONCE(rsp->gpnum), + READ_ONCE(rsp->gp_seq), TPS("fqsstart")); rcu_gp_fqs(rsp, first_gp_fqs); first_gp_fqs = false; trace_rcu_grace_period(rsp->name, - READ_ONCE(rsp->gpnum), + READ_ONCE(rsp->gp_seq), TPS("fqsend")); cond_resched_tasks_rcu_qs(); WRITE_ONCE(rsp->gp_activity, jiffies); ret = 0; /* Force full wait till next FQS. */ j = jiffies_till_next_fqs; - if (j > HZ) { - j = HZ; - jiffies_till_next_fqs = HZ; - } else if (j < 1) { - j = 1; - jiffies_till_next_fqs = 1; - } } else { /* Deal with stray signal. */ cond_resched_tasks_rcu_qs(); WRITE_ONCE(rsp->gp_activity, jiffies); WARN_ON(signal_pending(current)); trace_rcu_grace_period(rsp->name, - READ_ONCE(rsp->gpnum), + READ_ONCE(rsp->gp_seq), TPS("fqswaitsig")); ret = 1; /* Keep old FQS timing. */ j = jiffies; @@ -2256,8 +2264,12 @@ static void rcu_report_qs_rsp(struct rcu_state *rsp, unsigned long flags) * must be represented by the same rcu_node structure (which need not be a * leaf rcu_node structure, though it often will be). The gps parameter * is the grace-period snapshot, which means that the quiescent states - * are valid only if rnp->gpnum is equal to gps. That structure's lock + * are valid only if rnp->gp_seq is equal to gps. That structure's lock * must be held upon entry, and it is released before return. + * + * As a special case, if mask is zero, the bit-already-cleared check is + * disabled. This allows propagating quiescent state due to resumed tasks + * during grace-period initialization. */ static void rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp, @@ -2271,7 +2283,7 @@ rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp, /* Walk up the rcu_node hierarchy. */ for (;;) { - if (!(rnp->qsmask & mask) || rnp->gpnum != gps) { + if ((!(rnp->qsmask & mask) && mask) || rnp->gp_seq != gps) { /* * Our bit has already been cleared, or the @@ -2284,7 +2296,7 @@ rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp, WARN_ON_ONCE(!rcu_is_leaf_node(rnp) && rcu_preempt_blocked_readers_cgp(rnp)); rnp->qsmask &= ~mask; - trace_rcu_quiescent_state_report(rsp->name, rnp->gpnum, + trace_rcu_quiescent_state_report(rsp->name, rnp->gp_seq, mask, rnp->qsmask, rnp->level, rnp->grplo, rnp->grphi, !!rnp->gp_tasks); @@ -2294,6 +2306,7 @@ rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp, raw_spin_unlock_irqrestore_rcu_node(rnp, flags); return; } + rnp->completedqs = rnp->gp_seq; mask = rnp->grpmask; if (rnp->parent == NULL) { @@ -2323,8 +2336,9 @@ rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp, * irqs disabled, and this lock is released upon return, but irqs remain * disabled. */ -static void rcu_report_unblock_qs_rnp(struct rcu_state *rsp, - struct rcu_node *rnp, unsigned long flags) +static void __maybe_unused +rcu_report_unblock_qs_rnp(struct rcu_state *rsp, + struct rcu_node *rnp, unsigned long flags) __releases(rnp->lock) { unsigned long gps; @@ -2332,12 +2346,15 @@ static void rcu_report_unblock_qs_rnp(struct rcu_state *rsp, struct rcu_node *rnp_p; raw_lockdep_assert_held_rcu_node(rnp); - if (rcu_state_p == &rcu_sched_state || rsp != rcu_state_p || - rnp->qsmask != 0 || rcu_preempt_blocked_readers_cgp(rnp)) { + if (WARN_ON_ONCE(rcu_state_p == &rcu_sched_state) || + WARN_ON_ONCE(rsp != rcu_state_p) || + WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp)) || + rnp->qsmask != 0) { raw_spin_unlock_irqrestore_rcu_node(rnp, flags); return; /* Still need more quiescent states! */ } + rnp->completedqs = rnp->gp_seq; rnp_p = rnp->parent; if (rnp_p == NULL) { /* @@ -2348,8 +2365,8 @@ static void rcu_report_unblock_qs_rnp(struct rcu_state *rsp, return; } - /* Report up the rest of the hierarchy, tracking current ->gpnum. */ - gps = rnp->gpnum; + /* Report up the rest of the hierarchy, tracking current ->gp_seq. */ + gps = rnp->gp_seq; mask = rnp->grpmask; raw_spin_unlock_rcu_node(rnp); /* irqs remain disabled. */ raw_spin_lock_rcu_node(rnp_p); /* irqs already disabled. */ @@ -2370,8 +2387,8 @@ rcu_report_qs_rdp(int cpu, struct rcu_state *rsp, struct rcu_data *rdp) rnp = rdp->mynode; raw_spin_lock_irqsave_rcu_node(rnp, flags); - if (rdp->cpu_no_qs.b.norm || rdp->gpnum != rnp->gpnum || - rnp->completed == rnp->gpnum || rdp->gpwrap) { + if (rdp->cpu_no_qs.b.norm || rdp->gp_seq != rnp->gp_seq || + rdp->gpwrap) { /* * The grace period in which this quiescent state was @@ -2396,7 +2413,7 @@ rcu_report_qs_rdp(int cpu, struct rcu_state *rsp, struct rcu_data *rdp) */ needwake = rcu_accelerate_cbs(rsp, rnp, rdp); - rcu_report_qs_rnp(mask, rsp, rnp, rnp->gpnum, flags); + rcu_report_qs_rnp(mask, rsp, rnp, rnp->gp_seq, flags); /* ^^^ Released rnp->lock */ if (needwake) rcu_gp_kthread_wake(rsp); @@ -2441,17 +2458,16 @@ rcu_check_quiescent_state(struct rcu_state *rsp, struct rcu_data *rdp) */ static void rcu_cleanup_dying_cpu(struct rcu_state *rsp) { - RCU_TRACE(unsigned long mask;) + RCU_TRACE(bool blkd;) RCU_TRACE(struct rcu_data *rdp = this_cpu_ptr(rsp->rda);) RCU_TRACE(struct rcu_node *rnp = rdp->mynode;) if (!IS_ENABLED(CONFIG_HOTPLUG_CPU)) return; - RCU_TRACE(mask = rdp->grpmask;) - trace_rcu_grace_period(rsp->name, - rnp->gpnum + 1 - !!(rnp->qsmask & mask), - TPS("cpuofl")); + RCU_TRACE(blkd = !!(rnp->qsmask & rdp->grpmask);) + trace_rcu_grace_period(rsp->name, rnp->gp_seq, + blkd ? TPS("cpuofl") : TPS("cpuofl-bgp")); } /* @@ -2463,7 +2479,7 @@ static void rcu_cleanup_dying_cpu(struct rcu_state *rsp) * This function therefore goes up the tree of rcu_node structures, * clearing the corresponding bits in the ->qsmaskinit fields. Note that * the leaf rcu_node structure's ->qsmaskinit field has already been - * updated + * updated. * * This function does check that the specified rcu_node structure has * all CPUs offline and no blocked tasks, so it is OK to invoke it @@ -2476,9 +2492,10 @@ static void rcu_cleanup_dead_rnp(struct rcu_node *rnp_leaf) long mask; struct rcu_node *rnp = rnp_leaf; - raw_lockdep_assert_held_rcu_node(rnp); + raw_lockdep_assert_held_rcu_node(rnp_leaf); if (!IS_ENABLED(CONFIG_HOTPLUG_CPU) || - rnp->qsmaskinit || rcu_preempt_has_tasks(rnp)) + WARN_ON_ONCE(rnp_leaf->qsmaskinit) || + WARN_ON_ONCE(rcu_preempt_has_tasks(rnp_leaf))) return; for (;;) { mask = rnp->grpmask; @@ -2487,7 +2504,8 @@ static void rcu_cleanup_dead_rnp(struct rcu_node *rnp_leaf) break; raw_spin_lock_rcu_node(rnp); /* irqs already disabled. */ rnp->qsmaskinit &= ~mask; - rnp->qsmask &= ~mask; + /* Between grace periods, so better already be zero! */ + WARN_ON_ONCE(rnp->qsmask); if (rnp->qsmaskinit) { raw_spin_unlock_rcu_node(rnp); /* irqs remain disabled. */ @@ -2630,6 +2648,7 @@ void rcu_check_callbacks(int user) rcu_sched_qs(); rcu_bh_qs(); + rcu_note_voluntary_context_switch(current); } else if (!in_softirq()) { @@ -2645,8 +2664,7 @@ void rcu_check_callbacks(int user) rcu_preempt_check_callbacks(); if (rcu_pending()) invoke_rcu_core(); - if (user) - rcu_note_voluntary_context_switch(current); + trace_rcu_utilization(TPS("End scheduler-tick")); } @@ -2681,17 +2699,8 @@ static void force_qs_rnp(struct rcu_state *rsp, int (*f)(struct rcu_data *rsp)) /* rcu_initiate_boost() releases rnp->lock */ continue; } - if (rnp->parent && - (rnp->parent->qsmask & rnp->grpmask)) { - /* - * Race between grace-period - * initialization and task exiting RCU - * read-side critical section: Report. - */ - rcu_report_unblock_qs_rnp(rsp, rnp, flags); - /* rcu_report_unblock_qs_rnp() rlses ->lock */ - continue; - } + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); + continue; } for_each_leaf_node_possible_cpu(rnp, cpu) { unsigned long bit = leaf_node_cpu_bit(rnp, cpu); @@ -2701,8 +2710,8 @@ static void force_qs_rnp(struct rcu_state *rsp, int (*f)(struct rcu_data *rsp)) } } if (mask != 0) { - /* Idle/offline CPUs, report (releases rnp->lock. */ - rcu_report_qs_rnp(mask, rsp, rnp, rnp->gpnum, flags); + /* Idle/offline CPUs, report (releases rnp->lock). */ + rcu_report_qs_rnp(mask, rsp, rnp, rnp->gp_seq, flags); } else { /* Nothing to do here, so just drop the lock. */ raw_spin_unlock_irqrestore_rcu_node(rnp, flags); @@ -2747,6 +2756,65 @@ static void force_quiescent_state(struct rcu_state *rsp) } /* + * This function checks for grace-period requests that fail to motivate + * RCU to come out of its idle mode. + */ +static void +rcu_check_gp_start_stall(struct rcu_state *rsp, struct rcu_node *rnp, + struct rcu_data *rdp) +{ + const unsigned long gpssdelay = rcu_jiffies_till_stall_check() * HZ; + unsigned long flags; + unsigned long j; + struct rcu_node *rnp_root = rcu_get_root(rsp); + static atomic_t warned = ATOMIC_INIT(0); + + if (!IS_ENABLED(CONFIG_PROVE_RCU) || rcu_gp_in_progress(rsp) || + ULONG_CMP_GE(rnp_root->gp_seq, rnp_root->gp_seq_needed)) + return; + j = jiffies; /* Expensive access, and in common case don't get here. */ + if (time_before(j, READ_ONCE(rsp->gp_req_activity) + gpssdelay) || + time_before(j, READ_ONCE(rsp->gp_activity) + gpssdelay) || + atomic_read(&warned)) + return; + + raw_spin_lock_irqsave_rcu_node(rnp, flags); + j = jiffies; + if (rcu_gp_in_progress(rsp) || + ULONG_CMP_GE(rnp_root->gp_seq, rnp_root->gp_seq_needed) || + time_before(j, READ_ONCE(rsp->gp_req_activity) + gpssdelay) || + time_before(j, READ_ONCE(rsp->gp_activity) + gpssdelay) || + atomic_read(&warned)) { + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); + return; + } + /* Hold onto the leaf lock to make others see warned==1. */ + + if (rnp_root != rnp) + raw_spin_lock_rcu_node(rnp_root); /* irqs already disabled. */ + j = jiffies; + if (rcu_gp_in_progress(rsp) || + ULONG_CMP_GE(rnp_root->gp_seq, rnp_root->gp_seq_needed) || + time_before(j, rsp->gp_req_activity + gpssdelay) || + time_before(j, rsp->gp_activity + gpssdelay) || + atomic_xchg(&warned, 1)) { + raw_spin_unlock_rcu_node(rnp_root); /* irqs remain disabled. */ + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); + return; + } + pr_alert("%s: g%ld->%ld gar:%lu ga:%lu f%#x gs:%d %s->state:%#lx\n", + __func__, (long)READ_ONCE(rsp->gp_seq), + (long)READ_ONCE(rnp_root->gp_seq_needed), + j - rsp->gp_req_activity, j - rsp->gp_activity, + rsp->gp_flags, rsp->gp_state, rsp->name, + rsp->gp_kthread ? rsp->gp_kthread->state : 0x1ffffL); + WARN_ON(1); + if (rnp_root != rnp) + raw_spin_unlock_rcu_node(rnp_root); + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); +} + +/* * This does the RCU core processing work for the specified rcu_state * and rcu_data structures. This may be called only from the CPU to * whom the rdp belongs. @@ -2755,9 +2823,8 @@ static void __rcu_process_callbacks(struct rcu_state *rsp) { unsigned long flags; - bool needwake; struct rcu_data *rdp = raw_cpu_ptr(rsp->rda); - struct rcu_node *rnp; + struct rcu_node *rnp = rdp->mynode; WARN_ON_ONCE(!rdp->beenonline); @@ -2768,18 +2835,13 @@ __rcu_process_callbacks(struct rcu_state *rsp) if (!rcu_gp_in_progress(rsp) && rcu_segcblist_is_enabled(&rdp->cblist)) { local_irq_save(flags); - if (rcu_segcblist_restempty(&rdp->cblist, RCU_NEXT_READY_TAIL)) { - local_irq_restore(flags); - } else { - rnp = rdp->mynode; - raw_spin_lock_rcu_node(rnp); /* irqs disabled. */ - needwake = rcu_accelerate_cbs(rsp, rnp, rdp); - raw_spin_unlock_irqrestore_rcu_node(rnp, flags); - if (needwake) - rcu_gp_kthread_wake(rsp); - } + if (!rcu_segcblist_restempty(&rdp->cblist, RCU_NEXT_READY_TAIL)) + rcu_accelerate_cbs_unlocked(rsp, rnp, rdp); + local_irq_restore(flags); } + rcu_check_gp_start_stall(rsp, rnp, rdp); + /* If there are callbacks ready, invoke them. */ if (rcu_segcblist_ready_cbs(&rdp->cblist)) invoke_rcu_callbacks(rsp, rdp); @@ -2833,8 +2895,6 @@ static void invoke_rcu_core(void) static void __call_rcu_core(struct rcu_state *rsp, struct rcu_data *rdp, struct rcu_head *head, unsigned long flags) { - bool needwake; - /* * If called from an extended quiescent state, invoke the RCU * core in order to force a re-evaluation of RCU's idleness. @@ -2861,13 +2921,7 @@ static void __call_rcu_core(struct rcu_state *rsp, struct rcu_data *rdp, /* Start a new grace period if one not already started. */ if (!rcu_gp_in_progress(rsp)) { - struct rcu_node *rnp = rdp->mynode; - - raw_spin_lock_rcu_node(rnp); - needwake = rcu_accelerate_cbs(rsp, rnp, rdp); - raw_spin_unlock_rcu_node(rnp); - if (needwake) - rcu_gp_kthread_wake(rsp); + rcu_accelerate_cbs_unlocked(rsp, rdp->mynode, rdp); } else { /* Give the grace period a kick. */ rdp->blimit = LONG_MAX; @@ -3037,7 +3091,7 @@ EXPORT_SYMBOL_GPL(kfree_call_rcu); * when there was in fact only one the whole time, as this just adds * some overhead: RCU still operates correctly. */ -static inline int rcu_blocking_is_gp(void) +static int rcu_blocking_is_gp(void) { int ret; @@ -3136,16 +3190,10 @@ unsigned long get_state_synchronize_rcu(void) { /* * Any prior manipulation of RCU-protected data must happen - * before the load from ->gpnum. + * before the load from ->gp_seq. */ smp_mb(); /* ^^^ */ - - /* - * Make sure this load happens before the purportedly - * time-consuming work between get_state_synchronize_rcu() - * and cond_synchronize_rcu(). - */ - return smp_load_acquire(&rcu_state_p->gpnum); + return rcu_seq_snap(&rcu_state_p->gp_seq); } EXPORT_SYMBOL_GPL(get_state_synchronize_rcu); @@ -3165,15 +3213,10 @@ EXPORT_SYMBOL_GPL(get_state_synchronize_rcu); */ void cond_synchronize_rcu(unsigned long oldstate) { - unsigned long newstate; - - /* - * Ensure that this load happens before any RCU-destructive - * actions the caller might carry out after we return. - */ - newstate = smp_load_acquire(&rcu_state_p->completed); - if (ULONG_CMP_GE(oldstate, newstate)) + if (!rcu_seq_done(&rcu_state_p->gp_seq, oldstate)) synchronize_rcu(); + else + smp_mb(); /* Ensure GP ends before subsequent accesses. */ } EXPORT_SYMBOL_GPL(cond_synchronize_rcu); @@ -3188,16 +3231,10 @@ unsigned long get_state_synchronize_sched(void) { /* * Any prior manipulation of RCU-protected data must happen - * before the load from ->gpnum. + * before the load from ->gp_seq. */ smp_mb(); /* ^^^ */ - - /* - * Make sure this load happens before the purportedly - * time-consuming work between get_state_synchronize_sched() - * and cond_synchronize_sched(). - */ - return smp_load_acquire(&rcu_sched_state.gpnum); + return rcu_seq_snap(&rcu_sched_state.gp_seq); } EXPORT_SYMBOL_GPL(get_state_synchronize_sched); @@ -3217,15 +3254,10 @@ EXPORT_SYMBOL_GPL(get_state_synchronize_sched); */ void cond_synchronize_sched(unsigned long oldstate) { - unsigned long newstate; - - /* - * Ensure that this load happens before any RCU-destructive - * actions the caller might carry out after we return. - */ - newstate = smp_load_acquire(&rcu_sched_state.completed); - if (ULONG_CMP_GE(oldstate, newstate)) + if (!rcu_seq_done(&rcu_sched_state.gp_seq, oldstate)) synchronize_sched(); + else + smp_mb(); /* Ensure GP ends before subsequent accesses. */ } EXPORT_SYMBOL_GPL(cond_synchronize_sched); @@ -3261,12 +3293,8 @@ static int __rcu_pending(struct rcu_state *rsp, struct rcu_data *rdp) !rcu_segcblist_restempty(&rdp->cblist, RCU_NEXT_READY_TAIL)) return 1; - /* Has another RCU grace period completed? */ - if (READ_ONCE(rnp->completed) != rdp->completed) /* outside lock */ - return 1; - - /* Has a new RCU grace period started? */ - if (READ_ONCE(rnp->gpnum) != rdp->gpnum || + /* Have RCU grace period completed or started? */ + if (rcu_seq_current(&rnp->gp_seq) != rdp->gp_seq || unlikely(READ_ONCE(rdp->gpwrap))) /* outside lock */ return 1; @@ -3298,7 +3326,7 @@ static int rcu_pending(void) * non-NULL, store an indication of whether all callbacks are lazy. * (If there are no callbacks, all of them are deemed to be lazy.) */ -static bool __maybe_unused rcu_cpu_has_callbacks(bool *all_lazy) +static bool rcu_cpu_has_callbacks(bool *all_lazy) { bool al = true; bool hc = false; @@ -3484,17 +3512,22 @@ EXPORT_SYMBOL_GPL(rcu_barrier_sched); static void rcu_init_new_rnp(struct rcu_node *rnp_leaf) { long mask; + long oldmask; struct rcu_node *rnp = rnp_leaf; - raw_lockdep_assert_held_rcu_node(rnp); + raw_lockdep_assert_held_rcu_node(rnp_leaf); + WARN_ON_ONCE(rnp->wait_blkd_tasks); for (;;) { mask = rnp->grpmask; rnp = rnp->parent; if (rnp == NULL) return; raw_spin_lock_rcu_node(rnp); /* Interrupts already disabled. */ + oldmask = rnp->qsmaskinit; rnp->qsmaskinit |= mask; raw_spin_unlock_rcu_node(rnp); /* Interrupts remain disabled. */ + if (oldmask) + return; } } @@ -3511,6 +3544,10 @@ rcu_boot_init_percpu_data(int cpu, struct rcu_state *rsp) rdp->dynticks = &per_cpu(rcu_dynticks, cpu); WARN_ON_ONCE(rdp->dynticks->dynticks_nesting != 1); WARN_ON_ONCE(rcu_dynticks_in_eqs(rcu_dynticks_snap(rdp->dynticks))); + rdp->rcu_ofl_gp_seq = rsp->gp_seq; + rdp->rcu_ofl_gp_flags = RCU_GP_CLEANED; + rdp->rcu_onl_gp_seq = rsp->gp_seq; + rdp->rcu_onl_gp_flags = RCU_GP_CLEANED; rdp->cpu = cpu; rdp->rsp = rsp; rcu_boot_init_nocb_percpu_data(rdp); @@ -3518,9 +3555,9 @@ rcu_boot_init_percpu_data(int cpu, struct rcu_state *rsp) /* * Initialize a CPU's per-CPU RCU data. Note that only one online or - * offline event can be happening at a given time. Note also that we - * can accept some slop in the rsp->completed access due to the fact - * that this CPU cannot possibly have any RCU callbacks in flight yet. + * offline event can be happening at a given time. Note also that we can + * accept some slop in the rsp->gp_seq access due to the fact that this + * CPU cannot possibly have any RCU callbacks in flight yet. */ static void rcu_init_percpu_data(int cpu, struct rcu_state *rsp) @@ -3549,14 +3586,14 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp) rnp = rdp->mynode; raw_spin_lock_rcu_node(rnp); /* irqs already disabled. */ rdp->beenonline = true; /* We have now been online. */ - rdp->gpnum = rnp->completed; /* Make CPU later note any new GP. */ - rdp->completed = rnp->completed; + rdp->gp_seq = rnp->gp_seq; + rdp->gp_seq_needed = rnp->gp_seq; rdp->cpu_no_qs.b.norm = true; rdp->rcu_qs_ctr_snap = per_cpu(rcu_dynticks.rcu_qs_ctr, cpu); rdp->core_needs_qs = false; rdp->rcu_iw_pending = false; - rdp->rcu_iw_gpnum = rnp->gpnum - 1; - trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("cpuonl")); + rdp->rcu_iw_gp_seq = rnp->gp_seq - 1; + trace_rcu_grace_period(rsp->name, rdp->gp_seq, TPS("cpuonl")); raw_spin_unlock_irqrestore_rcu_node(rnp, flags); } @@ -3705,7 +3742,15 @@ void rcu_cpu_starting(unsigned int cpu) nbits = bitmap_weight(&oldmask, BITS_PER_LONG); /* Allow lockless access for expedited grace periods. */ smp_store_release(&rsp->ncpus, rsp->ncpus + nbits); /* ^^^ */ - raw_spin_unlock_irqrestore_rcu_node(rnp, flags); + rcu_gpnum_ovf(rnp, rdp); /* Offline-induced counter wrap? */ + rdp->rcu_onl_gp_seq = READ_ONCE(rsp->gp_seq); + rdp->rcu_onl_gp_flags = READ_ONCE(rsp->gp_flags); + if (rnp->qsmask & mask) { /* RCU waiting on incoming CPU? */ + /* Report QS -after- changing ->qsmaskinitnext! */ + rcu_report_qs_rnp(mask, rsp, rnp, rnp->gp_seq, flags); + } else { + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); + } } smp_mb(); /* Ensure RCU read-side usage follows above initialization. */ } @@ -3713,7 +3758,7 @@ void rcu_cpu_starting(unsigned int cpu) #ifdef CONFIG_HOTPLUG_CPU /* * The CPU is exiting the idle loop into the arch_cpu_idle_dead() - * function. We now remove it from the rcu_node tree's ->qsmaskinit + * function. We now remove it from the rcu_node tree's ->qsmaskinitnext * bit masks. */ static void rcu_cleanup_dying_idle_cpu(int cpu, struct rcu_state *rsp) @@ -3725,9 +3770,18 @@ static void rcu_cleanup_dying_idle_cpu(int cpu, struct rcu_state *rsp) /* Remove outgoing CPU from mask in the leaf rcu_node structure. */ mask = rdp->grpmask; + spin_lock(&rsp->ofl_lock); raw_spin_lock_irqsave_rcu_node(rnp, flags); /* Enforce GP memory-order guarantee. */ + rdp->rcu_ofl_gp_seq = READ_ONCE(rsp->gp_seq); + rdp->rcu_ofl_gp_flags = READ_ONCE(rsp->gp_flags); + if (rnp->qsmask & mask) { /* RCU waiting on outgoing CPU? */ + /* Report quiescent state -before- changing ->qsmaskinitnext! */ + rcu_report_qs_rnp(mask, rsp, rnp, rnp->gp_seq, flags); + raw_spin_lock_irqsave_rcu_node(rnp, flags); + } rnp->qsmaskinitnext &= ~mask; raw_spin_unlock_irqrestore_rcu_node(rnp, flags); + spin_unlock(&rsp->ofl_lock); } /* @@ -3839,12 +3893,16 @@ static int __init rcu_spawn_gp_kthread(void) struct task_struct *t; /* Force priority into range. */ - if (IS_ENABLED(CONFIG_RCU_BOOST) && kthread_prio < 1) + if (IS_ENABLED(CONFIG_RCU_BOOST) && kthread_prio < 2 + && IS_BUILTIN(CONFIG_RCU_TORTURE_TEST)) + kthread_prio = 2; + else if (IS_ENABLED(CONFIG_RCU_BOOST) && kthread_prio < 1) kthread_prio = 1; else if (kthread_prio < 0) kthread_prio = 0; else if (kthread_prio > 99) kthread_prio = 99; + if (kthread_prio != kthread_prio_in) pr_alert("rcu_spawn_gp_kthread(): Limited prio to %d from %d\n", kthread_prio, kthread_prio_in); @@ -3928,8 +3986,9 @@ static void __init rcu_init_one(struct rcu_state *rsp) raw_spin_lock_init(&rnp->fqslock); lockdep_set_class_and_name(&rnp->fqslock, &rcu_fqs_class[i], fqs[i]); - rnp->gpnum = rsp->gpnum; - rnp->completed = rsp->completed; + rnp->gp_seq = rsp->gp_seq; + rnp->gp_seq_needed = rsp->gp_seq; + rnp->completedqs = rsp->gp_seq; rnp->qsmask = 0; rnp->qsmaskinit = 0; rnp->grplo = j * cpustride; @@ -3997,7 +4056,7 @@ static void __init rcu_init_geometry(void) if (rcu_fanout_leaf == RCU_FANOUT_LEAF && nr_cpu_ids == NR_CPUS) return; - pr_info("RCU: Adjusting geometry for rcu_fanout_leaf=%d, nr_cpu_ids=%u\n", + pr_info("Adjusting geometry for rcu_fanout_leaf=%d, nr_cpu_ids=%u\n", rcu_fanout_leaf, nr_cpu_ids); /* diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index 78e051dffc5b..4e74df768c57 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -81,18 +81,16 @@ struct rcu_node { raw_spinlock_t __private lock; /* Root rcu_node's lock protects */ /* some rcu_state fields as well as */ /* following. */ - unsigned long gpnum; /* Current grace period for this node. */ - /* This will either be equal to or one */ - /* behind the root rcu_node's gpnum. */ - unsigned long completed; /* Last GP completed for this node. */ - /* This will either be equal to or one */ - /* behind the root rcu_node's gpnum. */ + unsigned long gp_seq; /* Track rsp->rcu_gp_seq. */ + unsigned long gp_seq_needed; /* Track rsp->rcu_gp_seq_needed. */ + unsigned long completedqs; /* All QSes done for this node. */ unsigned long qsmask; /* CPUs or groups that need to switch in */ /* order for current grace period to proceed.*/ /* In leaf rcu_node, each bit corresponds to */ /* an rcu_data structure, otherwise, each */ /* bit corresponds to a child rcu_node */ /* structure. */ + unsigned long rcu_gp_init_mask; /* Mask of offline CPUs at GP init. */ unsigned long qsmaskinit; /* Per-GP initial value for qsmask. */ /* Initialized from ->qsmaskinitnext at the */ @@ -158,7 +156,6 @@ struct rcu_node { struct swait_queue_head nocb_gp_wq[2]; /* Place for rcu_nocb_kthread() to wait GP. */ #endif /* #ifdef CONFIG_RCU_NOCB_CPU */ - u8 need_future_gp[4]; /* Counts of upcoming GP requests. */ raw_spinlock_t fqslock ____cacheline_internodealigned_in_smp; spinlock_t exp_lock ____cacheline_internodealigned_in_smp; @@ -168,22 +165,6 @@ struct rcu_node { bool exp_need_flush; /* Need to flush workitem? */ } ____cacheline_internodealigned_in_smp; -/* Accessors for ->need_future_gp[] array. */ -#define need_future_gp_mask() \ - (ARRAY_SIZE(((struct rcu_node *)NULL)->need_future_gp) - 1) -#define need_future_gp_element(rnp, c) \ - ((rnp)->need_future_gp[(c) & need_future_gp_mask()]) -#define need_any_future_gp(rnp) \ -({ \ - int __i; \ - bool __nonzero = false; \ - \ - for (__i = 0; __i < ARRAY_SIZE((rnp)->need_future_gp); __i++) \ - __nonzero = __nonzero || \ - READ_ONCE((rnp)->need_future_gp[__i]); \ - __nonzero; \ -}) - /* * Bitmasks in an rcu_node cover the interval [grplo, grphi] of CPU IDs, and * are indexed relative to this interval rather than the global CPU ID space. @@ -206,16 +187,14 @@ union rcu_noqs { /* Per-CPU data for read-copy update. */ struct rcu_data { /* 1) quiescent-state and grace-period handling : */ - unsigned long completed; /* Track rsp->completed gp number */ - /* in order to detect GP end. */ - unsigned long gpnum; /* Highest gp number that this CPU */ - /* is aware of having started. */ + unsigned long gp_seq; /* Track rsp->rcu_gp_seq counter. */ + unsigned long gp_seq_needed; /* Track rsp->rcu_gp_seq_needed ctr. */ unsigned long rcu_qs_ctr_snap;/* Snapshot of rcu_qs_ctr to check */ /* for rcu_all_qs() invocations. */ union rcu_noqs cpu_no_qs; /* No QSes yet for this CPU. */ bool core_needs_qs; /* Core waits for quiesc state. */ bool beenonline; /* CPU online at least once. */ - bool gpwrap; /* Possible gpnum/completed wrap. */ + bool gpwrap; /* Possible ->gp_seq wrap. */ struct rcu_node *mynode; /* This CPU's leaf of hierarchy */ unsigned long grpmask; /* Mask to apply to leaf qsmask. */ unsigned long ticks_this_gp; /* The number of scheduling-clock */ @@ -239,7 +218,6 @@ struct rcu_data { /* 4) reasons this CPU needed to be kicked by force_quiescent_state */ unsigned long dynticks_fqs; /* Kicked due to dynticks idle. */ - unsigned long offline_fqs; /* Kicked due to being offline. */ unsigned long cond_resched_completed; /* Grace period that needs help */ /* from cond_resched(). */ @@ -278,12 +256,16 @@ struct rcu_data { /* Leader CPU takes GP-end wakeups. */ #endif /* #ifdef CONFIG_RCU_NOCB_CPU */ - /* 7) RCU CPU stall data. */ + /* 7) Diagnostic data, including RCU CPU stall warnings. */ unsigned int softirq_snap; /* Snapshot of softirq activity. */ /* ->rcu_iw* fields protected by leaf rcu_node ->lock. */ struct irq_work rcu_iw; /* Check for non-irq activity. */ bool rcu_iw_pending; /* Is ->rcu_iw pending? */ - unsigned long rcu_iw_gpnum; /* ->gpnum associated with ->rcu_iw. */ + unsigned long rcu_iw_gp_seq; /* ->gp_seq associated with ->rcu_iw. */ + unsigned long rcu_ofl_gp_seq; /* ->gp_seq at last offline. */ + short rcu_ofl_gp_flags; /* ->gp_flags at last offline. */ + unsigned long rcu_onl_gp_seq; /* ->gp_seq at last online. */ + short rcu_onl_gp_flags; /* ->gp_flags at last online. */ int cpu; struct rcu_state *rsp; @@ -340,8 +322,7 @@ struct rcu_state { u8 boost ____cacheline_internodealigned_in_smp; /* Subject to priority boost. */ - unsigned long gpnum; /* Current gp number. */ - unsigned long completed; /* # of last completed gp. */ + unsigned long gp_seq; /* Grace-period sequence #. */ struct task_struct *gp_kthread; /* Task for grace periods. */ struct swait_queue_head gp_wq; /* Where GP task waits. */ short gp_flags; /* Commands for GP task. */ @@ -373,6 +354,8 @@ struct rcu_state { /* but in jiffies. */ unsigned long gp_activity; /* Time of last GP kthread */ /* activity in jiffies. */ + unsigned long gp_req_activity; /* Time of last GP request */ + /* in jiffies. */ unsigned long jiffies_stall; /* Time at which to check */ /* for CPU stalls. */ unsigned long jiffies_resched; /* Time at which to resched */ @@ -384,6 +367,10 @@ struct rcu_state { const char *name; /* Name of structure. */ char abbr; /* Abbreviated name. */ struct list_head flavors; /* List of RCU flavors. */ + + spinlock_t ofl_lock ____cacheline_internodealigned_in_smp; + /* Synchronize offline with */ + /* GP pre-initialization. */ }; /* Values for rcu_state structure's gp_flags field. */ @@ -394,16 +381,20 @@ struct rcu_state { #define RCU_GP_IDLE 0 /* Initial state and no GP in progress. */ #define RCU_GP_WAIT_GPS 1 /* Wait for grace-period start. */ #define RCU_GP_DONE_GPS 2 /* Wait done for grace-period start. */ -#define RCU_GP_WAIT_FQS 3 /* Wait for force-quiescent-state time. */ -#define RCU_GP_DOING_FQS 4 /* Wait done for force-quiescent-state time. */ -#define RCU_GP_CLEANUP 5 /* Grace-period cleanup started. */ -#define RCU_GP_CLEANED 6 /* Grace-period cleanup complete. */ +#define RCU_GP_ONOFF 3 /* Grace-period initialization hotplug. */ +#define RCU_GP_INIT 4 /* Grace-period initialization. */ +#define RCU_GP_WAIT_FQS 5 /* Wait for force-quiescent-state time. */ +#define RCU_GP_DOING_FQS 6 /* Wait done for force-quiescent-state time. */ +#define RCU_GP_CLEANUP 7 /* Grace-period cleanup started. */ +#define RCU_GP_CLEANED 8 /* Grace-period cleanup complete. */ #ifndef RCU_TREE_NONCORE static const char * const gp_state_names[] = { "RCU_GP_IDLE", "RCU_GP_WAIT_GPS", "RCU_GP_DONE_GPS", + "RCU_GP_ONOFF", + "RCU_GP_INIT", "RCU_GP_WAIT_FQS", "RCU_GP_DOING_FQS", "RCU_GP_CLEANUP", @@ -449,10 +440,13 @@ static bool rcu_preempt_has_tasks(struct rcu_node *rnp); static void rcu_print_detail_task_stall(struct rcu_state *rsp); static int rcu_print_task_stall(struct rcu_node *rnp); static int rcu_print_task_exp_stall(struct rcu_node *rnp); -static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp); +static void rcu_preempt_check_blocked_tasks(struct rcu_state *rsp, + struct rcu_node *rnp); static void rcu_preempt_check_callbacks(void); void call_rcu(struct rcu_head *head, rcu_callback_t func); static void __init __rcu_init_preempt(void); +static void dump_blkd_tasks(struct rcu_state *rsp, struct rcu_node *rnp, + int ncheck); static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags); static void rcu_preempt_boost_start_gp(struct rcu_node *rnp); static void invoke_rcu_callbacks_kthread(void); @@ -489,7 +483,6 @@ static void __init rcu_spawn_nocb_kthreads(void); #ifdef CONFIG_RCU_NOCB_CPU static void __init rcu_organize_nocb_kthreads(struct rcu_state *rsp); #endif /* #ifdef CONFIG_RCU_NOCB_CPU */ -static void __maybe_unused rcu_kick_nohz_cpu(int cpu); static bool init_nocb_callback_list(struct rcu_data *rdp); static void rcu_bind_gp_kthread(void); static bool rcu_nohz_full_cpu(struct rcu_state *rsp); diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h index d40708e8c5d6..0b2c2ad69629 100644 --- a/kernel/rcu/tree_exp.h +++ b/kernel/rcu/tree_exp.h @@ -212,7 +212,7 @@ static void __rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp, raw_spin_unlock_irqrestore_rcu_node(rnp, flags); if (wake) { smp_mb(); /* EGP done before wake_up(). */ - swake_up(&rsp->expedited_wq); + swake_up_one(&rsp->expedited_wq); } break; } @@ -472,6 +472,7 @@ retry_ipi: static void sync_rcu_exp_select_cpus(struct rcu_state *rsp, smp_call_func_t func) { + int cpu; struct rcu_node *rnp; trace_rcu_exp_grace_period(rsp->name, rcu_exp_gp_seq_endval(rsp), TPS("reset")); @@ -486,13 +487,20 @@ static void sync_rcu_exp_select_cpus(struct rcu_state *rsp, rnp->rew.rew_func = func; rnp->rew.rew_rsp = rsp; if (!READ_ONCE(rcu_par_gp_wq) || - rcu_scheduler_active != RCU_SCHEDULER_RUNNING) { - /* No workqueues yet. */ + rcu_scheduler_active != RCU_SCHEDULER_RUNNING || + rcu_is_last_leaf_node(rsp, rnp)) { + /* No workqueues yet or last leaf, do direct call. */ sync_rcu_exp_select_node_cpus(&rnp->rew.rew_work); continue; } INIT_WORK(&rnp->rew.rew_work, sync_rcu_exp_select_node_cpus); - queue_work_on(rnp->grplo, rcu_par_gp_wq, &rnp->rew.rew_work); + preempt_disable(); + cpu = cpumask_next(rnp->grplo - 1, cpu_online_mask); + /* If all offline, queue the work on an unbound CPU. */ + if (unlikely(cpu > rnp->grphi)) + cpu = WORK_CPU_UNBOUND; + queue_work_on(cpu, rcu_par_gp_wq, &rnp->rew.rew_work); + preempt_enable(); rnp->exp_need_flush = true; } @@ -518,7 +526,7 @@ static void synchronize_sched_expedited_wait(struct rcu_state *rsp) jiffies_start = jiffies; for (;;) { - ret = swait_event_timeout( + ret = swait_event_timeout_exclusive( rsp->expedited_wq, sync_rcu_preempt_exp_done_unlocked(rnp_root), jiffies_stall); diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index 7fd12039e512..a97c20ea9bce 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -74,8 +74,8 @@ static void __init rcu_bootup_announce_oddness(void) pr_info("\tRCU event tracing is enabled.\n"); if ((IS_ENABLED(CONFIG_64BIT) && RCU_FANOUT != 64) || (!IS_ENABLED(CONFIG_64BIT) && RCU_FANOUT != 32)) - pr_info("\tCONFIG_RCU_FANOUT set to non-default value of %d\n", - RCU_FANOUT); + pr_info("\tCONFIG_RCU_FANOUT set to non-default value of %d.\n", + RCU_FANOUT); if (rcu_fanout_exact) pr_info("\tHierarchical RCU autobalancing is disabled.\n"); if (IS_ENABLED(CONFIG_RCU_FAST_NO_HZ)) @@ -88,11 +88,13 @@ static void __init rcu_bootup_announce_oddness(void) pr_info("\tBuild-time adjustment of leaf fanout to %d.\n", RCU_FANOUT_LEAF); if (rcu_fanout_leaf != RCU_FANOUT_LEAF) - pr_info("\tBoot-time adjustment of leaf fanout to %d.\n", rcu_fanout_leaf); + pr_info("\tBoot-time adjustment of leaf fanout to %d.\n", + rcu_fanout_leaf); if (nr_cpu_ids != NR_CPUS) pr_info("\tRCU restricting CPUs from NR_CPUS=%d to nr_cpu_ids=%u.\n", NR_CPUS, nr_cpu_ids); #ifdef CONFIG_RCU_BOOST - pr_info("\tRCU priority boosting: priority %d delay %d ms.\n", kthread_prio, CONFIG_RCU_BOOST_DELAY); + pr_info("\tRCU priority boosting: priority %d delay %d ms.\n", + kthread_prio, CONFIG_RCU_BOOST_DELAY); #endif if (blimit != DEFAULT_RCU_BLIMIT) pr_info("\tBoot-time adjustment of callback invocation limit to %ld.\n", blimit); @@ -127,6 +129,7 @@ static struct rcu_data __percpu *const rcu_data_p = &rcu_preempt_data; static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp, bool wake); +static void rcu_read_unlock_special(struct task_struct *t); /* * Tell them what RCU they are running. @@ -183,6 +186,9 @@ static void rcu_preempt_ctxt_queue(struct rcu_node *rnp, struct rcu_data *rdp) raw_lockdep_assert_held_rcu_node(rnp); WARN_ON_ONCE(rdp->mynode != rnp); WARN_ON_ONCE(!rcu_is_leaf_node(rnp)); + /* RCU better not be waiting on newly onlined CPUs! */ + WARN_ON_ONCE(rnp->qsmaskinitnext & ~rnp->qsmaskinit & rnp->qsmask & + rdp->grpmask); /* * Decide where to queue the newly blocked task. In theory, @@ -260,8 +266,10 @@ static void rcu_preempt_ctxt_queue(struct rcu_node *rnp, struct rcu_data *rdp) * ->exp_tasks pointers, respectively, to reference the newly * blocked tasks. */ - if (!rnp->gp_tasks && (blkd_state & RCU_GP_BLKD)) + if (!rnp->gp_tasks && (blkd_state & RCU_GP_BLKD)) { rnp->gp_tasks = &t->rcu_node_entry; + WARN_ON_ONCE(rnp->completedqs == rnp->gp_seq); + } if (!rnp->exp_tasks && (blkd_state & RCU_EXP_BLKD)) rnp->exp_tasks = &t->rcu_node_entry; WARN_ON_ONCE(!(blkd_state & RCU_GP_BLKD) != @@ -286,20 +294,24 @@ static void rcu_preempt_ctxt_queue(struct rcu_node *rnp, struct rcu_data *rdp) } /* - * Record a preemptible-RCU quiescent state for the specified CPU. Note - * that this just means that the task currently running on the CPU is - * not in a quiescent state. There might be any number of tasks blocked - * while in an RCU read-side critical section. + * Record a preemptible-RCU quiescent state for the specified CPU. + * Note that this does not necessarily mean that the task currently running + * on the CPU is in a quiescent state: Instead, it means that the current + * grace period need not wait on any RCU read-side critical section that + * starts later on this CPU. It also means that if the current task is + * in an RCU read-side critical section, it has already added itself to + * some leaf rcu_node structure's ->blkd_tasks list. In addition to the + * current task, there might be any number of other tasks blocked while + * in an RCU read-side critical section. * - * As with the other rcu_*_qs() functions, callers to this function - * must disable preemption. + * Callers to this function must disable preemption. */ static void rcu_preempt_qs(void) { RCU_LOCKDEP_WARN(preemptible(), "rcu_preempt_qs() invoked with preemption enabled!!!\n"); if (__this_cpu_read(rcu_data_p->cpu_no_qs.s)) { trace_rcu_grace_period(TPS("rcu_preempt"), - __this_cpu_read(rcu_data_p->gpnum), + __this_cpu_read(rcu_data_p->gp_seq), TPS("cpuqs")); __this_cpu_write(rcu_data_p->cpu_no_qs.b.norm, false); barrier(); /* Coordinate with rcu_preempt_check_callbacks(). */ @@ -348,8 +360,8 @@ static void rcu_preempt_note_context_switch(bool preempt) trace_rcu_preempt_task(rdp->rsp->name, t->pid, (rnp->qsmask & rdp->grpmask) - ? rnp->gpnum - : rnp->gpnum + 1); + ? rnp->gp_seq + : rcu_seq_snap(&rnp->gp_seq)); rcu_preempt_ctxt_queue(rnp, rdp); } else if (t->rcu_read_lock_nesting < 0 && t->rcu_read_unlock_special.s) { @@ -456,7 +468,7 @@ static bool rcu_preempt_has_tasks(struct rcu_node *rnp) * notify RCU core processing or task having blocked during the RCU * read-side critical section. */ -void rcu_read_unlock_special(struct task_struct *t) +static void rcu_read_unlock_special(struct task_struct *t) { bool empty_exp; bool empty_norm; @@ -535,13 +547,15 @@ void rcu_read_unlock_special(struct task_struct *t) WARN_ON_ONCE(rnp != t->rcu_blocked_node); WARN_ON_ONCE(!rcu_is_leaf_node(rnp)); empty_norm = !rcu_preempt_blocked_readers_cgp(rnp); + WARN_ON_ONCE(rnp->completedqs == rnp->gp_seq && + (!empty_norm || rnp->qsmask)); empty_exp = sync_rcu_preempt_exp_done(rnp); smp_mb(); /* ensure expedited fastpath sees end of RCU c-s. */ np = rcu_next_node_entry(t, rnp); list_del_init(&t->rcu_node_entry); t->rcu_blocked_node = NULL; trace_rcu_unlock_preempted_task(TPS("rcu_preempt"), - rnp->gpnum, t->pid); + rnp->gp_seq, t->pid); if (&t->rcu_node_entry == rnp->gp_tasks) rnp->gp_tasks = np; if (&t->rcu_node_entry == rnp->exp_tasks) @@ -562,7 +576,7 @@ void rcu_read_unlock_special(struct task_struct *t) empty_exp_now = sync_rcu_preempt_exp_done(rnp); if (!empty_norm && !rcu_preempt_blocked_readers_cgp(rnp)) { trace_rcu_quiescent_state_report(TPS("preempt_rcu"), - rnp->gpnum, + rnp->gp_seq, 0, rnp->qsmask, rnp->level, rnp->grplo, @@ -686,24 +700,27 @@ static int rcu_print_task_exp_stall(struct rcu_node *rnp) * Check that the list of blocked tasks for the newly completed grace * period is in fact empty. It is a serious bug to complete a grace * period that still has RCU readers blocked! This function must be - * invoked -before- updating this rnp's ->gpnum, and the rnp's ->lock + * invoked -before- updating this rnp's ->gp_seq, and the rnp's ->lock * must be held by the caller. * * Also, if there are blocked tasks on the list, they automatically * block the newly created grace period, so set up ->gp_tasks accordingly. */ -static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp) +static void +rcu_preempt_check_blocked_tasks(struct rcu_state *rsp, struct rcu_node *rnp) { struct task_struct *t; RCU_LOCKDEP_WARN(preemptible(), "rcu_preempt_check_blocked_tasks() invoked with preemption enabled!!!\n"); - WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp)); - if (rcu_preempt_has_tasks(rnp)) { + if (WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp))) + dump_blkd_tasks(rsp, rnp, 10); + if (rcu_preempt_has_tasks(rnp) && + (rnp->qsmaskinit || rnp->wait_blkd_tasks)) { rnp->gp_tasks = rnp->blkd_tasks.next; t = container_of(rnp->gp_tasks, struct task_struct, rcu_node_entry); trace_rcu_unlock_preempted_task(TPS("rcu_preempt-GPS"), - rnp->gpnum, t->pid); + rnp->gp_seq, t->pid); } WARN_ON_ONCE(rnp->qsmask); } @@ -717,6 +734,7 @@ static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp) */ static void rcu_preempt_check_callbacks(void) { + struct rcu_state *rsp = &rcu_preempt_state; struct task_struct *t = current; if (t->rcu_read_lock_nesting == 0) { @@ -725,7 +743,9 @@ static void rcu_preempt_check_callbacks(void) } if (t->rcu_read_lock_nesting > 0 && __this_cpu_read(rcu_data_p->core_needs_qs) && - __this_cpu_read(rcu_data_p->cpu_no_qs.b.norm)) + __this_cpu_read(rcu_data_p->cpu_no_qs.b.norm) && + !t->rcu_read_unlock_special.b.need_qs && + time_after(jiffies, rsp->gp_start + HZ)) t->rcu_read_unlock_special.b.need_qs = true; } @@ -841,6 +861,47 @@ void exit_rcu(void) __rcu_read_unlock(); } +/* + * Dump the blocked-tasks state, but limit the list dump to the + * specified number of elements. + */ +static void +dump_blkd_tasks(struct rcu_state *rsp, struct rcu_node *rnp, int ncheck) +{ + int cpu; + int i; + struct list_head *lhp; + bool onl; + struct rcu_data *rdp; + struct rcu_node *rnp1; + + raw_lockdep_assert_held_rcu_node(rnp); + pr_info("%s: grp: %d-%d level: %d ->gp_seq %ld ->completedqs %ld\n", + __func__, rnp->grplo, rnp->grphi, rnp->level, + (long)rnp->gp_seq, (long)rnp->completedqs); + for (rnp1 = rnp; rnp1; rnp1 = rnp1->parent) + pr_info("%s: %d:%d ->qsmask %#lx ->qsmaskinit %#lx ->qsmaskinitnext %#lx\n", + __func__, rnp1->grplo, rnp1->grphi, rnp1->qsmask, rnp1->qsmaskinit, rnp1->qsmaskinitnext); + pr_info("%s: ->gp_tasks %p ->boost_tasks %p ->exp_tasks %p\n", + __func__, rnp->gp_tasks, rnp->boost_tasks, rnp->exp_tasks); + pr_info("%s: ->blkd_tasks", __func__); + i = 0; + list_for_each(lhp, &rnp->blkd_tasks) { + pr_cont(" %p", lhp); + if (++i >= 10) + break; + } + pr_cont("\n"); + for (cpu = rnp->grplo; cpu <= rnp->grphi; cpu++) { + rdp = per_cpu_ptr(rsp->rda, cpu); + onl = !!(rdp->grpmask & rcu_rnp_online_cpus(rnp)); + pr_info("\t%d: %c online: %ld(%d) offline: %ld(%d)\n", + cpu, ".o"[onl], + (long)rdp->rcu_onl_gp_seq, rdp->rcu_onl_gp_flags, + (long)rdp->rcu_ofl_gp_seq, rdp->rcu_ofl_gp_flags); + } +} + #else /* #ifdef CONFIG_PREEMPT_RCU */ static struct rcu_state *const rcu_state_p = &rcu_sched_state; @@ -911,7 +972,8 @@ static int rcu_print_task_exp_stall(struct rcu_node *rnp) * so there is no need to check for blocked tasks. So check only for * bogus qsmask values. */ -static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp) +static void +rcu_preempt_check_blocked_tasks(struct rcu_state *rsp, struct rcu_node *rnp) { WARN_ON_ONCE(rnp->qsmask); } @@ -949,6 +1011,15 @@ void exit_rcu(void) { } +/* + * Dump the guaranteed-empty blocked-tasks state. Trust but verify. + */ +static void +dump_blkd_tasks(struct rcu_state *rsp, struct rcu_node *rnp, int ncheck) +{ + WARN_ON_ONCE(!list_empty(&rnp->blkd_tasks)); +} + #endif /* #else #ifdef CONFIG_PREEMPT_RCU */ #ifdef CONFIG_RCU_BOOST @@ -1433,7 +1504,8 @@ static bool __maybe_unused rcu_try_advance_all_cbs(void) * completed since we last checked and there are * callbacks not yet ready to invoke. */ - if ((rdp->completed != rnp->completed || + if ((rcu_seq_completed_gp(rdp->gp_seq, + rcu_seq_current(&rnp->gp_seq)) || unlikely(READ_ONCE(rdp->gpwrap))) && rcu_segcblist_pend_cbs(&rdp->cblist)) note_gp_changes(rsp, rdp); @@ -1720,16 +1792,16 @@ static void print_cpu_stall_info(struct rcu_state *rsp, int cpu) */ touch_nmi_watchdog(); - if (rsp->gpnum == rdp->gpnum) { + ticks_value = rcu_seq_ctr(rsp->gp_seq - rdp->gp_seq); + if (ticks_value) { + ticks_title = "GPs behind"; + } else { ticks_title = "ticks this GP"; ticks_value = rdp->ticks_this_gp; - } else { - ticks_title = "GPs behind"; - ticks_value = rsp->gpnum - rdp->gpnum; } print_cpu_stall_fast_no_hz(fast_no_hz, cpu); - delta = rdp->mynode->gpnum - rdp->rcu_iw_gpnum; - pr_err("\t%d-%c%c%c%c: (%lu %s) idle=%03x/%ld/%ld softirq=%u/%u fqs=%ld %s\n", + delta = rcu_seq_ctr(rdp->mynode->gp_seq - rdp->rcu_iw_gp_seq); + pr_err("\t%d-%c%c%c%c: (%lu %s) idle=%03x/%ld/%#lx softirq=%u/%u fqs=%ld %s\n", cpu, "O."[!!cpu_online(cpu)], "o."[!!(rdp->grpmask & rdp->mynode->qsmaskinit)], @@ -1817,7 +1889,7 @@ static void rcu_nocb_gp_cleanup(struct swait_queue_head *sq) static struct swait_queue_head *rcu_nocb_gp_get(struct rcu_node *rnp) { - return &rnp->nocb_gp_wq[rnp->completed & 0x1]; + return &rnp->nocb_gp_wq[rcu_seq_ctr(rnp->gp_seq) & 0x1]; } static void rcu_init_one_nocb(struct rcu_node *rnp) @@ -1854,8 +1926,8 @@ static void __wake_nocb_leader(struct rcu_data *rdp, bool force, WRITE_ONCE(rdp_leader->nocb_leader_sleep, false); del_timer(&rdp->nocb_timer); raw_spin_unlock_irqrestore(&rdp->nocb_lock, flags); - smp_mb(); /* ->nocb_leader_sleep before swake_up(). */ - swake_up(&rdp_leader->nocb_wq); + smp_mb(); /* ->nocb_leader_sleep before swake_up_one(). */ + swake_up_one(&rdp_leader->nocb_wq); } else { raw_spin_unlock_irqrestore(&rdp->nocb_lock, flags); } @@ -2069,12 +2141,17 @@ static void rcu_nocb_wait_gp(struct rcu_data *rdp) bool needwake; struct rcu_node *rnp = rdp->mynode; - raw_spin_lock_irqsave_rcu_node(rnp, flags); - c = rcu_cbs_completed(rdp->rsp, rnp); - needwake = rcu_start_this_gp(rnp, rdp, c); - raw_spin_unlock_irqrestore_rcu_node(rnp, flags); - if (needwake) - rcu_gp_kthread_wake(rdp->rsp); + local_irq_save(flags); + c = rcu_seq_snap(&rdp->rsp->gp_seq); + if (!rdp->gpwrap && ULONG_CMP_GE(rdp->gp_seq_needed, c)) { + local_irq_restore(flags); + } else { + raw_spin_lock_rcu_node(rnp); /* irqs already disabled. */ + needwake = rcu_start_this_gp(rnp, rdp, c); + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); + if (needwake) + rcu_gp_kthread_wake(rdp->rsp); + } /* * Wait for the grace period. Do so interruptibly to avoid messing @@ -2082,9 +2159,9 @@ static void rcu_nocb_wait_gp(struct rcu_data *rdp) */ trace_rcu_this_gp(rnp, rdp, c, TPS("StartWait")); for (;;) { - swait_event_interruptible( - rnp->nocb_gp_wq[c & 0x1], - (d = ULONG_CMP_GE(READ_ONCE(rnp->completed), c))); + swait_event_interruptible_exclusive( + rnp->nocb_gp_wq[rcu_seq_ctr(c) & 0x1], + (d = rcu_seq_done(&rnp->gp_seq, c))); if (likely(d)) break; WARN_ON(signal_pending(current)); @@ -2111,7 +2188,7 @@ wait_again: /* Wait for callbacks to appear. */ if (!rcu_nocb_poll) { trace_rcu_nocb_wake(my_rdp->rsp->name, my_rdp->cpu, TPS("Sleep")); - swait_event_interruptible(my_rdp->nocb_wq, + swait_event_interruptible_exclusive(my_rdp->nocb_wq, !READ_ONCE(my_rdp->nocb_leader_sleep)); raw_spin_lock_irqsave(&my_rdp->nocb_lock, flags); my_rdp->nocb_leader_sleep = true; @@ -2176,7 +2253,7 @@ wait_again: raw_spin_unlock_irqrestore(&rdp->nocb_lock, flags); if (rdp != my_rdp && tail == &rdp->nocb_follower_head) { /* List was empty, so wake up the follower. */ - swake_up(&rdp->nocb_wq); + swake_up_one(&rdp->nocb_wq); } } @@ -2193,7 +2270,7 @@ static void nocb_follower_wait(struct rcu_data *rdp) { for (;;) { trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, TPS("FollowerSleep")); - swait_event_interruptible(rdp->nocb_wq, + swait_event_interruptible_exclusive(rdp->nocb_wq, READ_ONCE(rdp->nocb_follower_head)); if (smp_load_acquire(&rdp->nocb_follower_head)) { /* ^^^ Ensure CB invocation follows _head test. */ @@ -2569,23 +2646,6 @@ static bool init_nocb_callback_list(struct rcu_data *rdp) #endif /* #else #ifdef CONFIG_RCU_NOCB_CPU */ /* - * An adaptive-ticks CPU can potentially execute in kernel mode for an - * arbitrarily long period of time with the scheduling-clock tick turned - * off. RCU will be paying attention to this CPU because it is in the - * kernel, but the CPU cannot be guaranteed to be executing the RCU state - * machine because the scheduling-clock tick has been disabled. Therefore, - * if an adaptive-ticks CPU is failing to respond to the current grace - * period and has not be idle from an RCU perspective, kick it. - */ -static void __maybe_unused rcu_kick_nohz_cpu(int cpu) -{ -#ifdef CONFIG_NO_HZ_FULL - if (tick_nohz_full_cpu(cpu)) - smp_send_reschedule(cpu); -#endif /* #ifdef CONFIG_NO_HZ_FULL */ -} - -/* * Is this CPU a NO_HZ_FULL CPU that should ignore RCU so that the * grace-period kthread will do force_quiescent_state() processing? * The idea is to avoid waking up RCU core processing on such a @@ -2610,8 +2670,6 @@ static bool rcu_nohz_full_cpu(struct rcu_state *rsp) */ static void rcu_bind_gp_kthread(void) { - int __maybe_unused cpu; - if (!tick_nohz_full_enabled()) return; housekeeping_affine(current, HK_FLAG_RCU); diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c index 4c230a60ece4..39cb23d22109 100644 --- a/kernel/rcu/update.c +++ b/kernel/rcu/update.c @@ -507,14 +507,15 @@ early_initcall(check_cpu_stall_init); #ifdef CONFIG_TASKS_RCU /* - * Simple variant of RCU whose quiescent states are voluntary context switch, - * user-space execution, and idle. As such, grace periods can take one good - * long time. There are no read-side primitives similar to rcu_read_lock() - * and rcu_read_unlock() because this implementation is intended to get - * the system into a safe state for some of the manipulations involved in - * tracing and the like. Finally, this implementation does not support - * high call_rcu_tasks() rates from multiple CPUs. If this is required, - * per-CPU callback lists will be needed. + * Simple variant of RCU whose quiescent states are voluntary context + * switch, cond_resched_rcu_qs(), user-space execution, and idle. + * As such, grace periods can take one good long time. There are no + * read-side primitives similar to rcu_read_lock() and rcu_read_unlock() + * because this implementation is intended to get the system into a safe + * state for some of the manipulations involved in tracing and the like. + * Finally, this implementation does not support high call_rcu_tasks() + * rates from multiple CPUs. If this is required, per-CPU callback lists + * will be needed. */ /* Global list of callbacks and associated lock. */ @@ -542,11 +543,11 @@ static struct task_struct *rcu_tasks_kthread_ptr; * period elapses, in other words after all currently executing RCU * read-side critical sections have completed. call_rcu_tasks() assumes * that the read-side critical sections end at a voluntary context - * switch (not a preemption!), entry into idle, or transition to usermode - * execution. As such, there are no read-side primitives analogous to - * rcu_read_lock() and rcu_read_unlock() because this primitive is intended - * to determine that all tasks have passed through a safe state, not so - * much for data-strcuture synchronization. + * switch (not a preemption!), cond_resched_rcu_qs(), entry into idle, + * or transition to usermode execution. As such, there are no read-side + * primitives analogous to rcu_read_lock() and rcu_read_unlock() because + * this primitive is intended to determine that all tasks have passed + * through a safe state, not so much for data-strcuture synchronization. * * See the description of call_rcu() for more detailed information on * memory ordering guarantees. @@ -667,6 +668,7 @@ static int __noreturn rcu_tasks_kthread(void *arg) struct rcu_head *list; struct rcu_head *next; LIST_HEAD(rcu_tasks_holdouts); + int fract; /* Run on housekeeping CPUs by default. Sysadm can move if desired. */ housekeeping_affine(current, HK_FLAG_RCU); @@ -748,13 +750,25 @@ static int __noreturn rcu_tasks_kthread(void *arg) * holdouts. When the list is empty, we are done. */ lastreport = jiffies; - while (!list_empty(&rcu_tasks_holdouts)) { + + /* Start off with HZ/10 wait and slowly back off to 1 HZ wait*/ + fract = 10; + + for (;;) { bool firstreport; bool needreport; int rtst; struct task_struct *t1; - schedule_timeout_interruptible(HZ); + if (list_empty(&rcu_tasks_holdouts)) + break; + + /* Slowly back off waiting for holdouts */ + schedule_timeout_interruptible(HZ/fract); + + if (fract > 1) + fract--; + rtst = READ_ONCE(rcu_task_stall_timeout); needreport = rtst > 0 && time_after(jiffies, lastreport + rtst); @@ -800,6 +814,7 @@ static int __noreturn rcu_tasks_kthread(void *arg) list = next; cond_resched(); } + /* Paranoid sleep to keep this from entering a tight loop */ schedule_timeout_uninterruptible(HZ/10); } } diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile index d9a02b318108..7fe183404c38 100644 --- a/kernel/sched/Makefile +++ b/kernel/sched/Makefile @@ -20,7 +20,7 @@ obj-y += core.o loadavg.o clock.o cputime.o obj-y += idle.o fair.o rt.o deadline.o obj-y += wait.o wait_bit.o swait.o completion.o -obj-$(CONFIG_SMP) += cpupri.o cpudeadline.o topology.o stop_task.o +obj-$(CONFIG_SMP) += cpupri.o cpudeadline.o topology.o stop_task.o pelt.o obj-$(CONFIG_SCHED_AUTOGROUP) += autogroup.o obj-$(CONFIG_SCHEDSTATS) += stats.o obj-$(CONFIG_SCHED_DEBUG) += debug.o diff --git a/kernel/sched/completion.c b/kernel/sched/completion.c index e426b0cb9ac6..a1ad5b7d5521 100644 --- a/kernel/sched/completion.c +++ b/kernel/sched/completion.c @@ -22,8 +22,8 @@ * * See also complete_all(), wait_for_completion() and related routines. * - * It may be assumed that this function implies a write memory barrier before - * changing the task state if and only if any tasks are woken up. + * If this function wakes up a task, it executes a full memory barrier before + * accessing the task state. */ void complete(struct completion *x) { @@ -44,8 +44,8 @@ EXPORT_SYMBOL(complete); * * This will wake up all threads waiting on this particular completion event. * - * It may be assumed that this function implies a write memory barrier before - * changing the task state if and only if any tasks are woken up. + * If this function wakes up a task, it executes a full memory barrier before + * accessing the task state. * * Since complete_all() sets the completion of @x permanently to done * to allow multiple waiters to finish, a call to reinit_completion() diff --git a/kernel/sched/core.c b/kernel/sched/core.c index fe365c9a08e9..d17d99778356 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -17,6 +17,8 @@ #include "../workqueue_internal.h" #include "../smpboot.h" +#include "pelt.h" + #define CREATE_TRACE_POINTS #include <trace/events/sched.h> @@ -45,14 +47,6 @@ const_debug unsigned int sysctl_sched_features = const_debug unsigned int sysctl_sched_nr_migrate = 32; /* - * period over which we average the RT time consumption, measured - * in ms. - * - * default: 1s - */ -const_debug unsigned int sysctl_sched_time_avg = MSEC_PER_SEC; - -/* * period over which we measure -rt task CPU usage in us. * default: 1s */ @@ -183,9 +177,9 @@ static void update_rq_clock_task(struct rq *rq, s64 delta) rq->clock_task += delta; -#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING) +#ifdef HAVE_SCHED_AVG_IRQ if ((irq_delta + steal) && sched_feat(NONTASK_CAPACITY)) - sched_rt_avg_update(rq, irq_delta + steal); + update_irq_load_avg(rq, irq_delta + steal); #endif } @@ -412,8 +406,8 @@ void wake_q_add(struct wake_q_head *head, struct task_struct *task) * its already queued (either by us or someone else) and will get the * wakeup due to that. * - * This cmpxchg() implies a full barrier, which pairs with the write - * barrier implied by the wakeup in wake_up_q(). + * This cmpxchg() executes a full barrier, which pairs with the full + * barrier executed by the wakeup in wake_up_q(). */ if (cmpxchg(&node->next, NULL, WAKE_Q_TAIL)) return; @@ -441,8 +435,8 @@ void wake_up_q(struct wake_q_head *head) task->wake_q.next = NULL; /* - * wake_up_process() implies a wmb() to pair with the queueing - * in wake_q_add() so as not to miss wakeups. + * wake_up_process() executes a full barrier, which pairs with + * the queueing in wake_q_add() so as not to miss wakeups. */ wake_up_process(task); put_task_struct(task); @@ -649,23 +643,6 @@ bool sched_can_stop_tick(struct rq *rq) return true; } #endif /* CONFIG_NO_HZ_FULL */ - -void sched_avg_update(struct rq *rq) -{ - s64 period = sched_avg_period(); - - while ((s64)(rq_clock(rq) - rq->age_stamp) > period) { - /* - * Inline assembly required to prevent the compiler - * optimising this loop into a divmod call. - * See __iter_div_u64_rem() for another example of this. - */ - asm("" : "+rm" (rq->age_stamp)); - rq->age_stamp += period; - rq->rt_avg /= 2; - } -} - #endif /* CONFIG_SMP */ #if defined(CONFIG_RT_GROUP_SCHED) || (defined(CONFIG_FAIR_GROUP_SCHED) && \ @@ -1199,6 +1176,7 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu) __set_task_cpu(p, new_cpu); } +#ifdef CONFIG_NUMA_BALANCING static void __migrate_swap_task(struct task_struct *p, int cpu) { if (task_on_rq_queued(p)) { @@ -1280,16 +1258,17 @@ unlock: /* * Cross migrate two tasks */ -int migrate_swap(struct task_struct *cur, struct task_struct *p) +int migrate_swap(struct task_struct *cur, struct task_struct *p, + int target_cpu, int curr_cpu) { struct migration_swap_arg arg; int ret = -EINVAL; arg = (struct migration_swap_arg){ .src_task = cur, - .src_cpu = task_cpu(cur), + .src_cpu = curr_cpu, .dst_task = p, - .dst_cpu = task_cpu(p), + .dst_cpu = target_cpu, }; if (arg.src_cpu == arg.dst_cpu) @@ -1314,6 +1293,7 @@ int migrate_swap(struct task_struct *cur, struct task_struct *p) out: return ret; } +#endif /* CONFIG_NUMA_BALANCING */ /* * wait_task_inactive - wait for a thread to unschedule. @@ -1879,8 +1859,7 @@ static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags) * rq(c1)->lock (if not at the same time, then in that order). * C) LOCK of the rq(c1)->lock scheduling in task * - * Transitivity guarantees that B happens after A and C after B. - * Note: we only require RCpc transitivity. + * Release/acquire chaining guarantees that B happens after A and C after B. * Note: the CPU doing B need not be c0 or c1 * * Example: @@ -1942,16 +1921,9 @@ static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags) * UNLOCK rq(0)->lock * * - * However; for wakeups there is a second guarantee we must provide, namely we - * must observe the state that lead to our wakeup. That is, not only must our - * task observe its own prior state, it must also observe the stores prior to - * its wakeup. - * - * This means that any means of doing remote wakeups must order the CPU doing - * the wakeup against the CPU the task is going to end up running on. This, - * however, is already required for the regular Program-Order guarantee above, - * since the waking CPU is the one issueing the ACQUIRE (smp_cond_load_acquire). - * + * However, for wakeups there is a second guarantee we must provide, namely we + * must ensure that CONDITION=1 done by the caller can not be reordered with + * accesses to the task state; see try_to_wake_up() and set_current_state(). */ /** @@ -1967,6 +1939,9 @@ static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags) * Atomic against schedule() which would dequeue a task, also see * set_current_state(). * + * This function executes a full memory barrier before accessing the task + * state; see set_current_state(). + * * Return: %true if @p->state changes (an actual wakeup was done), * %false otherwise. */ @@ -1998,21 +1973,20 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) * be possible to, falsely, observe p->on_rq == 0 and get stuck * in smp_cond_load_acquire() below. * - * sched_ttwu_pending() try_to_wake_up() - * [S] p->on_rq = 1; [L] P->state - * UNLOCK rq->lock -----. - * \ - * +--- RMB - * schedule() / - * LOCK rq->lock -----' - * UNLOCK rq->lock + * sched_ttwu_pending() try_to_wake_up() + * STORE p->on_rq = 1 LOAD p->state + * UNLOCK rq->lock + * + * __schedule() (switch to task 'p') + * LOCK rq->lock smp_rmb(); + * smp_mb__after_spinlock(); + * UNLOCK rq->lock * * [task p] - * [S] p->state = UNINTERRUPTIBLE [L] p->on_rq + * STORE p->state = UNINTERRUPTIBLE LOAD p->on_rq * - * Pairs with the UNLOCK+LOCK on rq->lock from the - * last wakeup of our task and the schedule that got our task - * current. + * Pairs with the LOCK+smp_mb__after_spinlock() on rq->lock in + * __schedule(). See the comment for smp_mb__after_spinlock(). */ smp_rmb(); if (p->on_rq && ttwu_remote(p, wake_flags)) @@ -2026,15 +2000,17 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) * One must be running (->on_cpu == 1) in order to remove oneself * from the runqueue. * - * [S] ->on_cpu = 1; [L] ->on_rq - * UNLOCK rq->lock - * RMB - * LOCK rq->lock - * [S] ->on_rq = 0; [L] ->on_cpu + * __schedule() (switch to task 'p') try_to_wake_up() + * STORE p->on_cpu = 1 LOAD p->on_rq + * UNLOCK rq->lock + * + * __schedule() (put 'p' to sleep) + * LOCK rq->lock smp_rmb(); + * smp_mb__after_spinlock(); + * STORE p->on_rq = 0 LOAD p->on_cpu * - * Pairs with the full barrier implied in the UNLOCK+LOCK on rq->lock - * from the consecutive calls to schedule(); the first switching to our - * task, the second putting it to sleep. + * Pairs with the LOCK+smp_mb__after_spinlock() on rq->lock in + * __schedule(). See the comment for smp_mb__after_spinlock(). */ smp_rmb(); @@ -2140,8 +2116,7 @@ out: * * Return: 1 if the process was woken up, 0 if it was already running. * - * It may be assumed that this function implies a write memory barrier before - * changing the task state if and only if any tasks are woken up. + * This function executes a full memory barrier before accessing the task state. */ int wake_up_process(struct task_struct *p) { @@ -2317,7 +2292,6 @@ static inline void init_schedstats(void) {} int sched_fork(unsigned long clone_flags, struct task_struct *p) { unsigned long flags; - int cpu = get_cpu(); __sched_fork(clone_flags, p); /* @@ -2353,14 +2327,12 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p) p->sched_reset_on_fork = 0; } - if (dl_prio(p->prio)) { - put_cpu(); + if (dl_prio(p->prio)) return -EAGAIN; - } else if (rt_prio(p->prio)) { + else if (rt_prio(p->prio)) p->sched_class = &rt_sched_class; - } else { + else p->sched_class = &fair_sched_class; - } init_entity_runnable_average(&p->se); @@ -2376,7 +2348,7 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p) * We're setting the CPU for the first time, we don't migrate, * so use __set_task_cpu(). */ - __set_task_cpu(p, cpu); + __set_task_cpu(p, smp_processor_id()); if (p->sched_class->task_fork) p->sched_class->task_fork(p); raw_spin_unlock_irqrestore(&p->pi_lock, flags); @@ -2393,8 +2365,6 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p) plist_node_init(&p->pushable_tasks, MAX_PRIO); RB_CLEAR_NODE(&p->pushable_dl_tasks); #endif - - put_cpu(); return 0; } @@ -5714,13 +5684,6 @@ void set_rq_offline(struct rq *rq) } } -static void set_cpu_rq_start_time(unsigned int cpu) -{ - struct rq *rq = cpu_rq(cpu); - - rq->age_stamp = sched_clock_cpu(cpu); -} - /* * used to mark begin/end of suspend/resume: */ @@ -5838,7 +5801,6 @@ static void sched_rq_cpu_starting(unsigned int cpu) int sched_cpu_starting(unsigned int cpu) { - set_cpu_rq_start_time(cpu); sched_rq_cpu_starting(cpu); sched_tick_start(cpu); return 0; @@ -6106,7 +6068,6 @@ void __init sched_init(void) #ifdef CONFIG_SMP idle_thread_set_boot_cpu(); - set_cpu_rq_start_time(smp_processor_id()); #endif init_sched_fair_class(); @@ -6785,6 +6746,16 @@ static int cpu_cfs_stat_show(struct seq_file *sf, void *v) seq_printf(sf, "nr_throttled %d\n", cfs_b->nr_throttled); seq_printf(sf, "throttled_time %llu\n", cfs_b->throttled_time); + if (schedstat_enabled() && tg != &root_task_group) { + u64 ws = 0; + int i; + + for_each_possible_cpu(i) + ws += schedstat_val(tg->se[i]->statistics.wait_sum); + + seq_printf(sf, "wait_sum %llu\n", ws); + } + return 0; } #endif /* CONFIG_CFS_BANDWIDTH */ diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c index c907fde01eaa..3fffad3bc8a8 100644 --- a/kernel/sched/cpufreq_schedutil.c +++ b/kernel/sched/cpufreq_schedutil.c @@ -53,9 +53,7 @@ struct sugov_cpu { unsigned int iowait_boost_max; u64 last_update; - /* The fields below are only needed when sharing a policy: */ - unsigned long util_cfs; - unsigned long util_dl; + unsigned long bw_dl; unsigned long max; /* The field below is for single-CPU policies only: */ @@ -179,33 +177,90 @@ static unsigned int get_next_freq(struct sugov_policy *sg_policy, return cpufreq_driver_resolve_freq(policy, freq); } -static void sugov_get_util(struct sugov_cpu *sg_cpu) +/* + * This function computes an effective utilization for the given CPU, to be + * used for frequency selection given the linear relation: f = u * f_max. + * + * The scheduler tracks the following metrics: + * + * cpu_util_{cfs,rt,dl,irq}() + * cpu_bw_dl() + * + * Where the cfs,rt and dl util numbers are tracked with the same metric and + * synchronized windows and are thus directly comparable. + * + * The cfs,rt,dl utilization are the running times measured with rq->clock_task + * which excludes things like IRQ and steal-time. These latter are then accrued + * in the irq utilization. + * + * The DL bandwidth number otoh is not a measured metric but a value computed + * based on the task model parameters and gives the minimal utilization + * required to meet deadlines. + */ +static unsigned long sugov_get_util(struct sugov_cpu *sg_cpu) { struct rq *rq = cpu_rq(sg_cpu->cpu); + unsigned long util, irq, max; - sg_cpu->max = arch_scale_cpu_capacity(NULL, sg_cpu->cpu); - sg_cpu->util_cfs = cpu_util_cfs(rq); - sg_cpu->util_dl = cpu_util_dl(rq); -} - -static unsigned long sugov_aggregate_util(struct sugov_cpu *sg_cpu) -{ - struct rq *rq = cpu_rq(sg_cpu->cpu); + sg_cpu->max = max = arch_scale_cpu_capacity(NULL, sg_cpu->cpu); + sg_cpu->bw_dl = cpu_bw_dl(rq); if (rt_rq_is_runnable(&rq->rt)) - return sg_cpu->max; + return max; + + /* + * Early check to see if IRQ/steal time saturates the CPU, can be + * because of inaccuracies in how we track these -- see + * update_irq_load_avg(). + */ + irq = cpu_util_irq(rq); + if (unlikely(irq >= max)) + return max; + + /* + * Because the time spend on RT/DL tasks is visible as 'lost' time to + * CFS tasks and we use the same metric to track the effective + * utilization (PELT windows are synchronized) we can directly add them + * to obtain the CPU's actual utilization. + */ + util = cpu_util_cfs(rq); + util += cpu_util_rt(rq); + + /* + * We do not make cpu_util_dl() a permanent part of this sum because we + * want to use cpu_bw_dl() later on, but we need to check if the + * CFS+RT+DL sum is saturated (ie. no idle time) such that we select + * f_max when there is no idle time. + * + * NOTE: numerical errors or stop class might cause us to not quite hit + * saturation when we should -- something for later. + */ + if ((util + cpu_util_dl(rq)) >= max) + return max; + + /* + * There is still idle time; further improve the number by using the + * irq metric. Because IRQ/steal time is hidden from the task clock we + * need to scale the task numbers: + * + * 1 - irq + * U' = irq + ------- * U + * max + */ + util = scale_irq_capacity(util, irq, max); + util += irq; /* - * Utilization required by DEADLINE must always be granted while, for - * FAIR, we use blocked utilization of IDLE CPUs as a mechanism to - * gracefully reduce the frequency when no tasks show up for longer + * Bandwidth required by DEADLINE must always be granted while, for + * FAIR and RT, we use blocked utilization of IDLE CPUs as a mechanism + * to gracefully reduce the frequency when no tasks show up for longer * periods of time. * - * Ideally we would like to set util_dl as min/guaranteed freq and - * util_cfs + util_dl as requested freq. However, cpufreq is not yet - * ready for such an interface. So, we only do the latter for now. + * Ideally we would like to set bw_dl as min/guaranteed freq and util + + * bw_dl as requested freq. However, cpufreq is not yet ready for such + * an interface. So, we only do the latter for now. */ - return min(sg_cpu->max, (sg_cpu->util_dl + sg_cpu->util_cfs)); + return min(max, util + sg_cpu->bw_dl); } /** @@ -360,7 +415,7 @@ static inline bool sugov_cpu_is_busy(struct sugov_cpu *sg_cpu) { return false; } */ static inline void ignore_dl_rate_limit(struct sugov_cpu *sg_cpu, struct sugov_policy *sg_policy) { - if (cpu_util_dl(cpu_rq(sg_cpu->cpu)) > sg_cpu->util_dl) + if (cpu_bw_dl(cpu_rq(sg_cpu->cpu)) > sg_cpu->bw_dl) sg_policy->need_freq_update = true; } @@ -383,9 +438,8 @@ static void sugov_update_single(struct update_util_data *hook, u64 time, busy = sugov_cpu_is_busy(sg_cpu); - sugov_get_util(sg_cpu); + util = sugov_get_util(sg_cpu); max = sg_cpu->max; - util = sugov_aggregate_util(sg_cpu); sugov_iowait_apply(sg_cpu, time, &util, &max); next_f = get_next_freq(sg_policy, util, max); /* @@ -424,9 +478,8 @@ static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu, u64 time) struct sugov_cpu *j_sg_cpu = &per_cpu(sugov_cpu, j); unsigned long j_util, j_max; - sugov_get_util(j_sg_cpu); + j_util = sugov_get_util(j_sg_cpu); j_max = j_sg_cpu->max; - j_util = sugov_aggregate_util(j_sg_cpu); sugov_iowait_apply(j_sg_cpu, time, &j_util, &j_max); if (j_util * max > j_max * util) { diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index b5fbdde6afa9..997ea7b839fa 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -16,6 +16,7 @@ * Fabio Checconi <fchecconi@gmail.com> */ #include "sched.h" +#include "pelt.h" struct dl_bandwidth def_dl_bandwidth; @@ -1179,8 +1180,6 @@ static void update_curr_dl(struct rq *rq) curr->se.exec_start = now; cgroup_account_cputime(curr, delta_exec); - sched_rt_avg_update(rq, delta_exec); - if (dl_entity_is_special(dl_se)) return; @@ -1761,6 +1760,9 @@ pick_next_task_dl(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) deadline_queue_push_tasks(rq); + if (rq->curr->sched_class != &dl_sched_class) + update_dl_rq_load_avg(rq_clock_task(rq), rq, 0); + return p; } @@ -1768,6 +1770,7 @@ static void put_prev_task_dl(struct rq *rq, struct task_struct *p) { update_curr_dl(rq); + update_dl_rq_load_avg(rq_clock_task(rq), rq, 1); if (on_dl_rq(&p->dl) && p->nr_cpus_allowed > 1) enqueue_pushable_dl_task(rq, p); } @@ -1784,6 +1787,7 @@ static void task_tick_dl(struct rq *rq, struct task_struct *p, int queued) { update_curr_dl(rq); + update_dl_rq_load_avg(rq_clock_task(rq), rq, 1); /* * Even when we have runtime, update_curr_dl() might have resulted in us * not being the leftmost task anymore. In that case NEED_RESCHED will diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index e593b4118578..870d4f3da285 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -111,20 +111,19 @@ static int sched_feat_set(char *cmp) cmp += 3; } - for (i = 0; i < __SCHED_FEAT_NR; i++) { - if (strcmp(cmp, sched_feat_names[i]) == 0) { - if (neg) { - sysctl_sched_features &= ~(1UL << i); - sched_feat_disable(i); - } else { - sysctl_sched_features |= (1UL << i); - sched_feat_enable(i); - } - break; - } + i = match_string(sched_feat_names, __SCHED_FEAT_NR, cmp); + if (i < 0) + return i; + + if (neg) { + sysctl_sched_features &= ~(1UL << i); + sched_feat_disable(i); + } else { + sysctl_sched_features |= (1UL << i); + sched_feat_enable(i); } - return i; + return 0; } static ssize_t @@ -133,7 +132,7 @@ sched_feat_write(struct file *filp, const char __user *ubuf, { char buf[64]; char *cmp; - int i; + int ret; struct inode *inode; if (cnt > 63) @@ -148,10 +147,10 @@ sched_feat_write(struct file *filp, const char __user *ubuf, /* Ensure the static_key remains in a consistent state */ inode = file_inode(filp); inode_lock(inode); - i = sched_feat_set(cmp); + ret = sched_feat_set(cmp); inode_unlock(inode); - if (i == __SCHED_FEAT_NR) - return -EINVAL; + if (ret < 0) + return ret; *ppos += cnt; @@ -843,8 +842,8 @@ void print_numa_stats(struct seq_file *m, int node, unsigned long tsf, unsigned long tpf, unsigned long gsf, unsigned long gpf) { SEQ_printf(m, "numa_faults node=%d ", node); - SEQ_printf(m, "task_private=%lu task_shared=%lu ", tsf, tpf); - SEQ_printf(m, "group_private=%lu group_shared=%lu\n", gsf, gpf); + SEQ_printf(m, "task_private=%lu task_shared=%lu ", tpf, tsf); + SEQ_printf(m, "group_private=%lu group_shared=%lu\n", gpf, gsf); } #endif diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 2f0a0be4d344..309c93fcc604 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -255,9 +255,6 @@ static inline struct rq *rq_of(struct cfs_rq *cfs_rq) return cfs_rq->rq; } -/* An entity is a task if it doesn't "own" a runqueue */ -#define entity_is_task(se) (!se->my_q) - static inline struct task_struct *task_of(struct sched_entity *se) { SCHED_WARN_ON(!entity_is_task(se)); @@ -419,7 +416,6 @@ static inline struct rq *rq_of(struct cfs_rq *cfs_rq) return container_of(cfs_rq, struct rq, cfs); } -#define entity_is_task(se) 1 #define for_each_sched_entity(se) \ for (; se; se = NULL) @@ -692,7 +688,7 @@ static u64 sched_vslice(struct cfs_rq *cfs_rq, struct sched_entity *se) } #ifdef CONFIG_SMP - +#include "pelt.h" #include "sched-pelt.h" static int select_idle_sibling(struct task_struct *p, int prev_cpu, int cpu); @@ -735,11 +731,12 @@ static void attach_entity_cfs_rq(struct sched_entity *se); * To solve this problem, we also cap the util_avg of successive tasks to * only 1/2 of the left utilization budget: * - * util_avg_cap = (1024 - cfs_rq->avg.util_avg) / 2^n + * util_avg_cap = (cpu_scale - cfs_rq->avg.util_avg) / 2^n * - * where n denotes the nth task. + * where n denotes the nth task and cpu_scale the CPU capacity. * - * For example, a simplest series from the beginning would be like: + * For example, for a CPU with 1024 of capacity, a simplest series from + * the beginning would be like: * * task util_avg: 512, 256, 128, 64, 32, 16, 8, ... * cfs_rq util_avg: 512, 768, 896, 960, 992, 1008, 1016, ... @@ -751,7 +748,8 @@ void post_init_entity_util_avg(struct sched_entity *se) { struct cfs_rq *cfs_rq = cfs_rq_of(se); struct sched_avg *sa = &se->avg; - long cap = (long)(SCHED_CAPACITY_SCALE - cfs_rq->avg.util_avg) / 2; + long cpu_scale = arch_scale_cpu_capacity(NULL, cpu_of(rq_of(cfs_rq))); + long cap = (long)(cpu_scale - cfs_rq->avg.util_avg) / 2; if (cap > 0) { if (cfs_rq->avg.util_avg != 0) { @@ -1314,7 +1312,7 @@ static unsigned long score_nearby_nodes(struct task_struct *p, int nid, * of each group. Skip other nodes. */ if (sched_numa_topology_type == NUMA_BACKPLANE && - dist > maxdist) + dist >= maxdist) continue; /* Add up the faults from nearby nodes. */ @@ -1452,15 +1450,12 @@ static unsigned long capacity_of(int cpu); /* Cached statistics for all CPUs within a node */ struct numa_stats { - unsigned long nr_running; unsigned long load; /* Total compute capacity of CPUs on a node */ unsigned long compute_capacity; - /* Approximate capacity in terms of runnable tasks on a node */ - unsigned long task_capacity; - int has_free_capacity; + unsigned int nr_running; }; /* @@ -1487,8 +1482,7 @@ static void update_numa_stats(struct numa_stats *ns, int nid) * the @ns structure is NULL'ed and task_numa_compare() will * not find this node attractive. * - * We'll either bail at !has_free_capacity, or we'll detect a huge - * imbalance and bail there. + * We'll detect a huge imbalance and bail there. */ if (!cpus) return; @@ -1497,9 +1491,8 @@ static void update_numa_stats(struct numa_stats *ns, int nid) smt = DIV_ROUND_UP(SCHED_CAPACITY_SCALE * cpus, ns->compute_capacity); capacity = cpus / smt; /* cores */ - ns->task_capacity = min_t(unsigned, capacity, + capacity = min_t(unsigned, capacity, DIV_ROUND_CLOSEST(ns->compute_capacity, SCHED_CAPACITY_SCALE)); - ns->has_free_capacity = (ns->nr_running < ns->task_capacity); } struct task_numa_env { @@ -1548,28 +1541,12 @@ static bool load_too_imbalanced(long src_load, long dst_load, src_capacity = env->src_stats.compute_capacity; dst_capacity = env->dst_stats.compute_capacity; - /* We care about the slope of the imbalance, not the direction. */ - if (dst_load < src_load) - swap(dst_load, src_load); + imb = abs(dst_load * src_capacity - src_load * dst_capacity); - /* Is the difference below the threshold? */ - imb = dst_load * src_capacity * 100 - - src_load * dst_capacity * env->imbalance_pct; - if (imb <= 0) - return false; - - /* - * The imbalance is above the allowed threshold. - * Compare it with the old imbalance. - */ orig_src_load = env->src_stats.load; orig_dst_load = env->dst_stats.load; - if (orig_dst_load < orig_src_load) - swap(orig_dst_load, orig_src_load); - - old_imb = orig_dst_load * src_capacity * 100 - - orig_src_load * dst_capacity * env->imbalance_pct; + old_imb = abs(orig_dst_load * src_capacity - orig_src_load * dst_capacity); /* Would this change make things worse? */ return (imb > old_imb); @@ -1582,9 +1559,8 @@ static bool load_too_imbalanced(long src_load, long dst_load, * be exchanged with the source task */ static void task_numa_compare(struct task_numa_env *env, - long taskimp, long groupimp) + long taskimp, long groupimp, bool maymove) { - struct rq *src_rq = cpu_rq(env->src_cpu); struct rq *dst_rq = cpu_rq(env->dst_cpu); struct task_struct *cur; long src_load, dst_load; @@ -1605,97 +1581,73 @@ static void task_numa_compare(struct task_numa_env *env, if (cur == env->p) goto unlock; + if (!cur) { + if (maymove || imp > env->best_imp) + goto assign; + else + goto unlock; + } + /* * "imp" is the fault differential for the source task between the * source and destination node. Calculate the total differential for * the source task and potential destination task. The more negative - * the value is, the more rmeote accesses that would be expected to + * the value is, the more remote accesses that would be expected to * be incurred if the tasks were swapped. */ - if (cur) { - /* Skip this swap candidate if cannot move to the source CPU: */ - if (!cpumask_test_cpu(env->src_cpu, &cur->cpus_allowed)) - goto unlock; + /* Skip this swap candidate if cannot move to the source cpu */ + if (!cpumask_test_cpu(env->src_cpu, &cur->cpus_allowed)) + goto unlock; + /* + * If dst and source tasks are in the same NUMA group, or not + * in any group then look only at task weights. + */ + if (cur->numa_group == env->p->numa_group) { + imp = taskimp + task_weight(cur, env->src_nid, dist) - + task_weight(cur, env->dst_nid, dist); /* - * If dst and source tasks are in the same NUMA group, or not - * in any group then look only at task weights. + * Add some hysteresis to prevent swapping the + * tasks within a group over tiny differences. */ - if (cur->numa_group == env->p->numa_group) { - imp = taskimp + task_weight(cur, env->src_nid, dist) - - task_weight(cur, env->dst_nid, dist); - /* - * Add some hysteresis to prevent swapping the - * tasks within a group over tiny differences. - */ - if (cur->numa_group) - imp -= imp/16; - } else { - /* - * Compare the group weights. If a task is all by - * itself (not part of a group), use the task weight - * instead. - */ - if (cur->numa_group) - imp += group_weight(cur, env->src_nid, dist) - - group_weight(cur, env->dst_nid, dist); - else - imp += task_weight(cur, env->src_nid, dist) - - task_weight(cur, env->dst_nid, dist); - } + if (cur->numa_group) + imp -= imp / 16; + } else { + /* + * Compare the group weights. If a task is all by itself + * (not part of a group), use the task weight instead. + */ + if (cur->numa_group && env->p->numa_group) + imp += group_weight(cur, env->src_nid, dist) - + group_weight(cur, env->dst_nid, dist); + else + imp += task_weight(cur, env->src_nid, dist) - + task_weight(cur, env->dst_nid, dist); } - if (imp <= env->best_imp && moveimp <= env->best_imp) + if (imp <= env->best_imp) goto unlock; - if (!cur) { - /* Is there capacity at our destination? */ - if (env->src_stats.nr_running <= env->src_stats.task_capacity && - !env->dst_stats.has_free_capacity) - goto unlock; - - goto balance; - } - - /* Balance doesn't matter much if we're running a task per CPU: */ - if (imp > env->best_imp && src_rq->nr_running == 1 && - dst_rq->nr_running == 1) + if (maymove && moveimp > imp && moveimp > env->best_imp) { + imp = moveimp - 1; + cur = NULL; goto assign; + } /* * In the overloaded case, try and keep the load balanced. */ -balance: - load = task_h_load(env->p); + load = task_h_load(env->p) - task_h_load(cur); + if (!load) + goto assign; + dst_load = env->dst_stats.load + load; src_load = env->src_stats.load - load; - if (moveimp > imp && moveimp > env->best_imp) { - /* - * If the improvement from just moving env->p direction is - * better than swapping tasks around, check if a move is - * possible. Store a slightly smaller score than moveimp, - * so an actually idle CPU will win. - */ - if (!load_too_imbalanced(src_load, dst_load, env)) { - imp = moveimp - 1; - cur = NULL; - goto assign; - } - } - - if (imp <= env->best_imp) - goto unlock; - - if (cur) { - load = task_h_load(cur); - dst_load -= load; - src_load += load; - } - if (load_too_imbalanced(src_load, dst_load, env)) goto unlock; +assign: /* * One idle CPU per node is evaluated for a task numa move. * Call select_idle_sibling to maybe find a better one. @@ -1711,7 +1663,6 @@ balance: local_irq_enable(); } -assign: task_numa_assign(env, cur, imp); unlock: rcu_read_unlock(); @@ -1720,43 +1671,30 @@ unlock: static void task_numa_find_cpu(struct task_numa_env *env, long taskimp, long groupimp) { + long src_load, dst_load, load; + bool maymove = false; int cpu; + load = task_h_load(env->p); + dst_load = env->dst_stats.load + load; + src_load = env->src_stats.load - load; + + /* + * If the improvement from just moving env->p direction is better + * than swapping tasks around, check if a move is possible. + */ + maymove = !load_too_imbalanced(src_load, dst_load, env); + for_each_cpu(cpu, cpumask_of_node(env->dst_nid)) { /* Skip this CPU if the source task cannot migrate */ if (!cpumask_test_cpu(cpu, &env->p->cpus_allowed)) continue; env->dst_cpu = cpu; - task_numa_compare(env, taskimp, groupimp); + task_numa_compare(env, taskimp, groupimp, maymove); } } -/* Only move tasks to a NUMA node less busy than the current node. */ -static bool numa_has_capacity(struct task_numa_env *env) -{ - struct numa_stats *src = &env->src_stats; - struct numa_stats *dst = &env->dst_stats; - - if (src->has_free_capacity && !dst->has_free_capacity) - return false; - - /* - * Only consider a task move if the source has a higher load - * than the destination, corrected for CPU capacity on each node. - * - * src->load dst->load - * --------------------- vs --------------------- - * src->compute_capacity dst->compute_capacity - */ - if (src->load * dst->compute_capacity * env->imbalance_pct > - - dst->load * src->compute_capacity * 100) - return true; - - return false; -} - static int task_numa_migrate(struct task_struct *p) { struct task_numa_env env = { @@ -1797,7 +1735,7 @@ static int task_numa_migrate(struct task_struct *p) * elsewhere, so there is no point in (re)trying. */ if (unlikely(!sd)) { - p->numa_preferred_nid = task_node(p); + sched_setnuma(p, task_node(p)); return -EINVAL; } @@ -1811,8 +1749,7 @@ static int task_numa_migrate(struct task_struct *p) update_numa_stats(&env.dst_stats, env.dst_nid); /* Try to find a spot on the preferred nid. */ - if (numa_has_capacity(&env)) - task_numa_find_cpu(&env, taskimp, groupimp); + task_numa_find_cpu(&env, taskimp, groupimp); /* * Look at other nodes in these cases: @@ -1842,8 +1779,7 @@ static int task_numa_migrate(struct task_struct *p) env.dist = dist; env.dst_nid = nid; update_numa_stats(&env.dst_stats, env.dst_nid); - if (numa_has_capacity(&env)) - task_numa_find_cpu(&env, taskimp, groupimp); + task_numa_find_cpu(&env, taskimp, groupimp); } } @@ -1856,15 +1792,13 @@ static int task_numa_migrate(struct task_struct *p) * trying for a better one later. Do not set the preferred node here. */ if (p->numa_group) { - struct numa_group *ng = p->numa_group; - if (env.best_cpu == -1) nid = env.src_nid; else - nid = env.dst_nid; + nid = cpu_to_node(env.best_cpu); - if (ng->active_nodes > 1 && numa_is_active_node(env.dst_nid, ng)) - sched_setnuma(p, env.dst_nid); + if (nid != p->numa_preferred_nid) + sched_setnuma(p, nid); } /* No better CPU than the current one was found. */ @@ -1884,7 +1818,8 @@ static int task_numa_migrate(struct task_struct *p) return ret; } - ret = migrate_swap(p, env.best_task); + ret = migrate_swap(p, env.best_task, env.best_cpu, env.src_cpu); + if (ret != 0) trace_sched_stick_numa(p, env.src_cpu, task_cpu(env.best_task)); put_task_struct(env.best_task); @@ -2144,8 +2079,8 @@ static int preferred_group_nid(struct task_struct *p, int nid) static void task_numa_placement(struct task_struct *p) { - int seq, nid, max_nid = -1, max_group_nid = -1; - unsigned long max_faults = 0, max_group_faults = 0; + int seq, nid, max_nid = -1; + unsigned long max_faults = 0; unsigned long fault_types[2] = { 0, 0 }; unsigned long total_faults; u64 runtime, period; @@ -2224,33 +2159,30 @@ static void task_numa_placement(struct task_struct *p) } } - if (faults > max_faults) { - max_faults = faults; + if (!p->numa_group) { + if (faults > max_faults) { + max_faults = faults; + max_nid = nid; + } + } else if (group_faults > max_faults) { + max_faults = group_faults; max_nid = nid; } - - if (group_faults > max_group_faults) { - max_group_faults = group_faults; - max_group_nid = nid; - } } - update_task_scan_period(p, fault_types[0], fault_types[1]); - if (p->numa_group) { numa_group_count_active_nodes(p->numa_group); spin_unlock_irq(group_lock); - max_nid = preferred_group_nid(p, max_group_nid); + max_nid = preferred_group_nid(p, max_nid); } if (max_faults) { /* Set the new preferred node */ if (max_nid != p->numa_preferred_nid) sched_setnuma(p, max_nid); - - if (task_node(p) != p->numa_preferred_nid) - numa_migrate_preferred(p); } + + update_task_scan_period(p, fault_types[0], fault_types[1]); } static inline int get_numa_group(struct numa_group *grp) @@ -2450,14 +2382,14 @@ void task_numa_fault(int last_cpupid, int mem_node, int pages, int flags) numa_is_active_node(mem_node, ng)) local = 1; - task_numa_placement(p); - /* * Retry task to preferred node migration periodically, in case it * case it previously failed, or the scheduler moved us. */ - if (time_after(jiffies, p->numa_migrate_retry)) + if (time_after(jiffies, p->numa_migrate_retry)) { + task_numa_placement(p); numa_migrate_preferred(p); + } if (migrated) p->numa_pages_migrated += pages; @@ -2749,19 +2681,6 @@ account_entity_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se) } while (0) #ifdef CONFIG_SMP -/* - * XXX we want to get rid of these helpers and use the full load resolution. - */ -static inline long se_weight(struct sched_entity *se) -{ - return scale_load_down(se->load.weight); -} - -static inline long se_runnable(struct sched_entity *se) -{ - return scale_load_down(se->runnable_weight); -} - static inline void enqueue_runnable_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) { @@ -3062,314 +2981,6 @@ static inline void cfs_rq_util_change(struct cfs_rq *cfs_rq, int flags) } #ifdef CONFIG_SMP -/* - * Approximate: - * val * y^n, where y^32 ~= 0.5 (~1 scheduling period) - */ -static u64 decay_load(u64 val, u64 n) -{ - unsigned int local_n; - - if (unlikely(n > LOAD_AVG_PERIOD * 63)) - return 0; - - /* after bounds checking we can collapse to 32-bit */ - local_n = n; - - /* - * As y^PERIOD = 1/2, we can combine - * y^n = 1/2^(n/PERIOD) * y^(n%PERIOD) - * With a look-up table which covers y^n (n<PERIOD) - * - * To achieve constant time decay_load. - */ - if (unlikely(local_n >= LOAD_AVG_PERIOD)) { - val >>= local_n / LOAD_AVG_PERIOD; - local_n %= LOAD_AVG_PERIOD; - } - - val = mul_u64_u32_shr(val, runnable_avg_yN_inv[local_n], 32); - return val; -} - -static u32 __accumulate_pelt_segments(u64 periods, u32 d1, u32 d3) -{ - u32 c1, c2, c3 = d3; /* y^0 == 1 */ - - /* - * c1 = d1 y^p - */ - c1 = decay_load((u64)d1, periods); - - /* - * p-1 - * c2 = 1024 \Sum y^n - * n=1 - * - * inf inf - * = 1024 ( \Sum y^n - \Sum y^n - y^0 ) - * n=0 n=p - */ - c2 = LOAD_AVG_MAX - decay_load(LOAD_AVG_MAX, periods) - 1024; - - return c1 + c2 + c3; -} - -/* - * Accumulate the three separate parts of the sum; d1 the remainder - * of the last (incomplete) period, d2 the span of full periods and d3 - * the remainder of the (incomplete) current period. - * - * d1 d2 d3 - * ^ ^ ^ - * | | | - * |<->|<----------------->|<--->| - * ... |---x---|------| ... |------|-----x (now) - * - * p-1 - * u' = (u + d1) y^p + 1024 \Sum y^n + d3 y^0 - * n=1 - * - * = u y^p + (Step 1) - * - * p-1 - * d1 y^p + 1024 \Sum y^n + d3 y^0 (Step 2) - * n=1 - */ -static __always_inline u32 -accumulate_sum(u64 delta, int cpu, struct sched_avg *sa, - unsigned long load, unsigned long runnable, int running) -{ - unsigned long scale_freq, scale_cpu; - u32 contrib = (u32)delta; /* p == 0 -> delta < 1024 */ - u64 periods; - - scale_freq = arch_scale_freq_capacity(cpu); - scale_cpu = arch_scale_cpu_capacity(NULL, cpu); - - delta += sa->period_contrib; - periods = delta / 1024; /* A period is 1024us (~1ms) */ - - /* - * Step 1: decay old *_sum if we crossed period boundaries. - */ - if (periods) { - sa->load_sum = decay_load(sa->load_sum, periods); - sa->runnable_load_sum = - decay_load(sa->runnable_load_sum, periods); - sa->util_sum = decay_load((u64)(sa->util_sum), periods); - - /* - * Step 2 - */ - delta %= 1024; - contrib = __accumulate_pelt_segments(periods, - 1024 - sa->period_contrib, delta); - } - sa->period_contrib = delta; - - contrib = cap_scale(contrib, scale_freq); - if (load) - sa->load_sum += load * contrib; - if (runnable) - sa->runnable_load_sum += runnable * contrib; - if (running) - sa->util_sum += contrib * scale_cpu; - - return periods; -} - -/* - * We can represent the historical contribution to runnable average as the - * coefficients of a geometric series. To do this we sub-divide our runnable - * history into segments of approximately 1ms (1024us); label the segment that - * occurred N-ms ago p_N, with p_0 corresponding to the current period, e.g. - * - * [<- 1024us ->|<- 1024us ->|<- 1024us ->| ... - * p0 p1 p2 - * (now) (~1ms ago) (~2ms ago) - * - * Let u_i denote the fraction of p_i that the entity was runnable. - * - * We then designate the fractions u_i as our co-efficients, yielding the - * following representation of historical load: - * u_0 + u_1*y + u_2*y^2 + u_3*y^3 + ... - * - * We choose y based on the with of a reasonably scheduling period, fixing: - * y^32 = 0.5 - * - * This means that the contribution to load ~32ms ago (u_32) will be weighted - * approximately half as much as the contribution to load within the last ms - * (u_0). - * - * When a period "rolls over" and we have new u_0`, multiplying the previous - * sum again by y is sufficient to update: - * load_avg = u_0` + y*(u_0 + u_1*y + u_2*y^2 + ... ) - * = u_0 + u_1*y + u_2*y^2 + ... [re-labeling u_i --> u_{i+1}] - */ -static __always_inline int -___update_load_sum(u64 now, int cpu, struct sched_avg *sa, - unsigned long load, unsigned long runnable, int running) -{ - u64 delta; - - delta = now - sa->last_update_time; - /* - * This should only happen when time goes backwards, which it - * unfortunately does during sched clock init when we swap over to TSC. - */ - if ((s64)delta < 0) { - sa->last_update_time = now; - return 0; - } - - /* - * Use 1024ns as the unit of measurement since it's a reasonable - * approximation of 1us and fast to compute. - */ - delta >>= 10; - if (!delta) - return 0; - - sa->last_update_time += delta << 10; - - /* - * running is a subset of runnable (weight) so running can't be set if - * runnable is clear. But there are some corner cases where the current - * se has been already dequeued but cfs_rq->curr still points to it. - * This means that weight will be 0 but not running for a sched_entity - * but also for a cfs_rq if the latter becomes idle. As an example, - * this happens during idle_balance() which calls - * update_blocked_averages() - */ - if (!load) - runnable = running = 0; - - /* - * Now we know we crossed measurement unit boundaries. The *_avg - * accrues by two steps: - * - * Step 1: accumulate *_sum since last_update_time. If we haven't - * crossed period boundaries, finish. - */ - if (!accumulate_sum(delta, cpu, sa, load, runnable, running)) - return 0; - - return 1; -} - -static __always_inline void -___update_load_avg(struct sched_avg *sa, unsigned long load, unsigned long runnable) -{ - u32 divider = LOAD_AVG_MAX - 1024 + sa->period_contrib; - - /* - * Step 2: update *_avg. - */ - sa->load_avg = div_u64(load * sa->load_sum, divider); - sa->runnable_load_avg = div_u64(runnable * sa->runnable_load_sum, divider); - sa->util_avg = sa->util_sum / divider; -} - -/* - * When a task is dequeued, its estimated utilization should not be update if - * its util_avg has not been updated at least once. - * This flag is used to synchronize util_avg updates with util_est updates. - * We map this information into the LSB bit of the utilization saved at - * dequeue time (i.e. util_est.dequeued). - */ -#define UTIL_AVG_UNCHANGED 0x1 - -static inline void cfs_se_util_change(struct sched_avg *avg) -{ - unsigned int enqueued; - - if (!sched_feat(UTIL_EST)) - return; - - /* Avoid store if the flag has been already set */ - enqueued = avg->util_est.enqueued; - if (!(enqueued & UTIL_AVG_UNCHANGED)) - return; - - /* Reset flag to report util_avg has been updated */ - enqueued &= ~UTIL_AVG_UNCHANGED; - WRITE_ONCE(avg->util_est.enqueued, enqueued); -} - -/* - * sched_entity: - * - * task: - * se_runnable() == se_weight() - * - * group: [ see update_cfs_group() ] - * se_weight() = tg->weight * grq->load_avg / tg->load_avg - * se_runnable() = se_weight(se) * grq->runnable_load_avg / grq->load_avg - * - * load_sum := runnable_sum - * load_avg = se_weight(se) * runnable_avg - * - * runnable_load_sum := runnable_sum - * runnable_load_avg = se_runnable(se) * runnable_avg - * - * XXX collapse load_sum and runnable_load_sum - * - * cfq_rs: - * - * load_sum = \Sum se_weight(se) * se->avg.load_sum - * load_avg = \Sum se->avg.load_avg - * - * runnable_load_sum = \Sum se_runnable(se) * se->avg.runnable_load_sum - * runnable_load_avg = \Sum se->avg.runable_load_avg - */ - -static int -__update_load_avg_blocked_se(u64 now, int cpu, struct sched_entity *se) -{ - if (entity_is_task(se)) - se->runnable_weight = se->load.weight; - - if (___update_load_sum(now, cpu, &se->avg, 0, 0, 0)) { - ___update_load_avg(&se->avg, se_weight(se), se_runnable(se)); - return 1; - } - - return 0; -} - -static int -__update_load_avg_se(u64 now, int cpu, struct cfs_rq *cfs_rq, struct sched_entity *se) -{ - if (entity_is_task(se)) - se->runnable_weight = se->load.weight; - - if (___update_load_sum(now, cpu, &se->avg, !!se->on_rq, !!se->on_rq, - cfs_rq->curr == se)) { - - ___update_load_avg(&se->avg, se_weight(se), se_runnable(se)); - cfs_se_util_change(&se->avg); - return 1; - } - - return 0; -} - -static int -__update_load_avg_cfs_rq(u64 now, int cpu, struct cfs_rq *cfs_rq) -{ - if (___update_load_sum(now, cpu, &cfs_rq->avg, - scale_load_down(cfs_rq->load.weight), - scale_load_down(cfs_rq->runnable_weight), - cfs_rq->curr != NULL)) { - - ___update_load_avg(&cfs_rq->avg, 1, 1); - return 1; - } - - return 0; -} - #ifdef CONFIG_FAIR_GROUP_SCHED /** * update_tg_load_avg - update the tg's load avg @@ -4037,12 +3648,6 @@ util_est_dequeue(struct cfs_rq *cfs_rq, struct task_struct *p, bool task_sleep) #else /* CONFIG_SMP */ -static inline int -update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq) -{ - return 0; -} - #define UPDATE_TG 0x0 #define SKIP_AGE_LOAD 0x0 #define DO_ATTACH 0x0 @@ -4726,7 +4331,6 @@ static inline int throttled_lb_pair(struct task_group *tg, throttled_hierarchy(dest_cfs_rq); } -/* updated child weight may affect parent so we have to do this bottom up */ static int tg_unthrottle_up(struct task_group *tg, void *data) { struct rq *rq = data; @@ -5653,8 +5257,6 @@ static void cpu_load_update(struct rq *this_rq, unsigned long this_load, this_rq->cpu_load[i] = (old_load * (scale - 1) + new_load) >> i; } - - sched_avg_update(this_rq); } /* Used instead of source_load when we know the type == 0 */ @@ -7294,8 +6896,8 @@ static int task_hot(struct task_struct *p, struct lb_env *env) static int migrate_degrades_locality(struct task_struct *p, struct lb_env *env) { struct numa_group *numa_group = rcu_dereference(p->numa_group); - unsigned long src_faults, dst_faults; - int src_nid, dst_nid; + unsigned long src_weight, dst_weight; + int src_nid, dst_nid, dist; if (!static_branch_likely(&sched_numa_balancing)) return -1; @@ -7322,18 +6924,19 @@ static int migrate_degrades_locality(struct task_struct *p, struct lb_env *env) return 0; /* Leaving a core idle is often worse than degrading locality. */ - if (env->idle != CPU_NOT_IDLE) + if (env->idle == CPU_IDLE) return -1; + dist = node_distance(src_nid, dst_nid); if (numa_group) { - src_faults = group_faults(p, src_nid); - dst_faults = group_faults(p, dst_nid); + src_weight = group_weight(p, src_nid, dist); + dst_weight = group_weight(p, dst_nid, dist); } else { - src_faults = task_faults(p, src_nid); - dst_faults = task_faults(p, dst_nid); + src_weight = task_weight(p, src_nid, dist); + dst_weight = task_weight(p, dst_nid, dist); } - return dst_faults < src_faults; + return dst_weight < src_weight; } #else @@ -7620,6 +7223,22 @@ static inline bool cfs_rq_has_blocked(struct cfs_rq *cfs_rq) return false; } +static inline bool others_have_blocked(struct rq *rq) +{ + if (READ_ONCE(rq->avg_rt.util_avg)) + return true; + + if (READ_ONCE(rq->avg_dl.util_avg)) + return true; + +#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING) + if (READ_ONCE(rq->avg_irq.util_avg)) + return true; +#endif + + return false; +} + #ifdef CONFIG_FAIR_GROUP_SCHED static inline bool cfs_rq_is_decayed(struct cfs_rq *cfs_rq) @@ -7679,6 +7298,12 @@ static void update_blocked_averages(int cpu) if (cfs_rq_has_blocked(cfs_rq)) done = false; } + update_rt_rq_load_avg(rq_clock_task(rq), rq, 0); + update_dl_rq_load_avg(rq_clock_task(rq), rq, 0); + update_irq_load_avg(rq, 0); + /* Don't need periodic decay once load/util_avg are null */ + if (others_have_blocked(rq)) + done = false; #ifdef CONFIG_NO_HZ_COMMON rq->last_blocked_load_update_tick = jiffies; @@ -7744,9 +7369,12 @@ static inline void update_blocked_averages(int cpu) rq_lock_irqsave(rq, &rf); update_rq_clock(rq); update_cfs_rq_load_avg(cfs_rq_clock_task(cfs_rq), cfs_rq); + update_rt_rq_load_avg(rq_clock_task(rq), rq, 0); + update_dl_rq_load_avg(rq_clock_task(rq), rq, 0); + update_irq_load_avg(rq, 0); #ifdef CONFIG_NO_HZ_COMMON rq->last_blocked_load_update_tick = jiffies; - if (!cfs_rq_has_blocked(cfs_rq)) + if (!cfs_rq_has_blocked(cfs_rq) && !others_have_blocked(rq)) rq->has_blocked_load = 0; #endif rq_unlock_irqrestore(rq, &rf); @@ -7856,39 +7484,32 @@ static inline int get_sd_load_idx(struct sched_domain *sd, static unsigned long scale_rt_capacity(int cpu) { struct rq *rq = cpu_rq(cpu); - u64 total, used, age_stamp, avg; - s64 delta; + unsigned long max = arch_scale_cpu_capacity(NULL, cpu); + unsigned long used, free; + unsigned long irq; - /* - * Since we're reading these variables without serialization make sure - * we read them once before doing sanity checks on them. - */ - age_stamp = READ_ONCE(rq->age_stamp); - avg = READ_ONCE(rq->rt_avg); - delta = __rq_clock_broken(rq) - age_stamp; + irq = cpu_util_irq(rq); - if (unlikely(delta < 0)) - delta = 0; + if (unlikely(irq >= max)) + return 1; - total = sched_avg_period() + delta; + used = READ_ONCE(rq->avg_rt.util_avg); + used += READ_ONCE(rq->avg_dl.util_avg); - used = div_u64(avg, total); + if (unlikely(used >= max)) + return 1; - if (likely(used < SCHED_CAPACITY_SCALE)) - return SCHED_CAPACITY_SCALE - used; + free = max - used; - return 1; + return scale_irq_capacity(free, irq, max); } static void update_cpu_capacity(struct sched_domain *sd, int cpu) { - unsigned long capacity = arch_scale_cpu_capacity(sd, cpu); + unsigned long capacity = scale_rt_capacity(cpu); struct sched_group *sdg = sd->groups; - cpu_rq(cpu)->cpu_capacity_orig = capacity; - - capacity *= scale_rt_capacity(cpu); - capacity >>= SCHED_CAPACITY_SHIFT; + cpu_rq(cpu)->cpu_capacity_orig = arch_scale_cpu_capacity(sd, cpu); if (!capacity) capacity = 1; diff --git a/kernel/sched/pelt.c b/kernel/sched/pelt.c new file mode 100644 index 000000000000..35475c0c5419 --- /dev/null +++ b/kernel/sched/pelt.c @@ -0,0 +1,399 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Per Entity Load Tracking + * + * Copyright (C) 2007 Red Hat, Inc., Ingo Molnar <mingo@redhat.com> + * + * Interactivity improvements by Mike Galbraith + * (C) 2007 Mike Galbraith <efault@gmx.de> + * + * Various enhancements by Dmitry Adamushko. + * (C) 2007 Dmitry Adamushko <dmitry.adamushko@gmail.com> + * + * Group scheduling enhancements by Srivatsa Vaddagiri + * Copyright IBM Corporation, 2007 + * Author: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com> + * + * Scaled math optimizations by Thomas Gleixner + * Copyright (C) 2007, Thomas Gleixner <tglx@linutronix.de> + * + * Adaptive scheduling granularity, math enhancements by Peter Zijlstra + * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra + * + * Move PELT related code from fair.c into this pelt.c file + * Author: Vincent Guittot <vincent.guittot@linaro.org> + */ + +#include <linux/sched.h> +#include "sched.h" +#include "sched-pelt.h" +#include "pelt.h" + +/* + * Approximate: + * val * y^n, where y^32 ~= 0.5 (~1 scheduling period) + */ +static u64 decay_load(u64 val, u64 n) +{ + unsigned int local_n; + + if (unlikely(n > LOAD_AVG_PERIOD * 63)) + return 0; + + /* after bounds checking we can collapse to 32-bit */ + local_n = n; + + /* + * As y^PERIOD = 1/2, we can combine + * y^n = 1/2^(n/PERIOD) * y^(n%PERIOD) + * With a look-up table which covers y^n (n<PERIOD) + * + * To achieve constant time decay_load. + */ + if (unlikely(local_n >= LOAD_AVG_PERIOD)) { + val >>= local_n / LOAD_AVG_PERIOD; + local_n %= LOAD_AVG_PERIOD; + } + + val = mul_u64_u32_shr(val, runnable_avg_yN_inv[local_n], 32); + return val; +} + +static u32 __accumulate_pelt_segments(u64 periods, u32 d1, u32 d3) +{ + u32 c1, c2, c3 = d3; /* y^0 == 1 */ + + /* + * c1 = d1 y^p + */ + c1 = decay_load((u64)d1, periods); + + /* + * p-1 + * c2 = 1024 \Sum y^n + * n=1 + * + * inf inf + * = 1024 ( \Sum y^n - \Sum y^n - y^0 ) + * n=0 n=p + */ + c2 = LOAD_AVG_MAX - decay_load(LOAD_AVG_MAX, periods) - 1024; + + return c1 + c2 + c3; +} + +#define cap_scale(v, s) ((v)*(s) >> SCHED_CAPACITY_SHIFT) + +/* + * Accumulate the three separate parts of the sum; d1 the remainder + * of the last (incomplete) period, d2 the span of full periods and d3 + * the remainder of the (incomplete) current period. + * + * d1 d2 d3 + * ^ ^ ^ + * | | | + * |<->|<----------------->|<--->| + * ... |---x---|------| ... |------|-----x (now) + * + * p-1 + * u' = (u + d1) y^p + 1024 \Sum y^n + d3 y^0 + * n=1 + * + * = u y^p + (Step 1) + * + * p-1 + * d1 y^p + 1024 \Sum y^n + d3 y^0 (Step 2) + * n=1 + */ +static __always_inline u32 +accumulate_sum(u64 delta, int cpu, struct sched_avg *sa, + unsigned long load, unsigned long runnable, int running) +{ + unsigned long scale_freq, scale_cpu; + u32 contrib = (u32)delta; /* p == 0 -> delta < 1024 */ + u64 periods; + + scale_freq = arch_scale_freq_capacity(cpu); + scale_cpu = arch_scale_cpu_capacity(NULL, cpu); + + delta += sa->period_contrib; + periods = delta / 1024; /* A period is 1024us (~1ms) */ + + /* + * Step 1: decay old *_sum if we crossed period boundaries. + */ + if (periods) { + sa->load_sum = decay_load(sa->load_sum, periods); + sa->runnable_load_sum = + decay_load(sa->runnable_load_sum, periods); + sa->util_sum = decay_load((u64)(sa->util_sum), periods); + + /* + * Step 2 + */ + delta %= 1024; + contrib = __accumulate_pelt_segments(periods, + 1024 - sa->period_contrib, delta); + } + sa->period_contrib = delta; + + contrib = cap_scale(contrib, scale_freq); + if (load) + sa->load_sum += load * contrib; + if (runnable) + sa->runnable_load_sum += runnable * contrib; + if (running) + sa->util_sum += contrib * scale_cpu; + + return periods; +} + +/* + * We can represent the historical contribution to runnable average as the + * coefficients of a geometric series. To do this we sub-divide our runnable + * history into segments of approximately 1ms (1024us); label the segment that + * occurred N-ms ago p_N, with p_0 corresponding to the current period, e.g. + * + * [<- 1024us ->|<- 1024us ->|<- 1024us ->| ... + * p0 p1 p2 + * (now) (~1ms ago) (~2ms ago) + * + * Let u_i denote the fraction of p_i that the entity was runnable. + * + * We then designate the fractions u_i as our co-efficients, yielding the + * following representation of historical load: + * u_0 + u_1*y + u_2*y^2 + u_3*y^3 + ... + * + * We choose y based on the with of a reasonably scheduling period, fixing: + * y^32 = 0.5 + * + * This means that the contribution to load ~32ms ago (u_32) will be weighted + * approximately half as much as the contribution to load within the last ms + * (u_0). + * + * When a period "rolls over" and we have new u_0`, multiplying the previous + * sum again by y is sufficient to update: + * load_avg = u_0` + y*(u_0 + u_1*y + u_2*y^2 + ... ) + * = u_0 + u_1*y + u_2*y^2 + ... [re-labeling u_i --> u_{i+1}] + */ +static __always_inline int +___update_load_sum(u64 now, int cpu, struct sched_avg *sa, + unsigned long load, unsigned long runnable, int running) +{ + u64 delta; + + delta = now - sa->last_update_time; + /* + * This should only happen when time goes backwards, which it + * unfortunately does during sched clock init when we swap over to TSC. + */ + if ((s64)delta < 0) { + sa->last_update_time = now; + return 0; + } + + /* + * Use 1024ns as the unit of measurement since it's a reasonable + * approximation of 1us and fast to compute. + */ + delta >>= 10; + if (!delta) + return 0; + + sa->last_update_time += delta << 10; + + /* + * running is a subset of runnable (weight) so running can't be set if + * runnable is clear. But there are some corner cases where the current + * se has been already dequeued but cfs_rq->curr still points to it. + * This means that weight will be 0 but not running for a sched_entity + * but also for a cfs_rq if the latter becomes idle. As an example, + * this happens during idle_balance() which calls + * update_blocked_averages() + */ + if (!load) + runnable = running = 0; + + /* + * Now we know we crossed measurement unit boundaries. The *_avg + * accrues by two steps: + * + * Step 1: accumulate *_sum since last_update_time. If we haven't + * crossed period boundaries, finish. + */ + if (!accumulate_sum(delta, cpu, sa, load, runnable, running)) + return 0; + + return 1; +} + +static __always_inline void +___update_load_avg(struct sched_avg *sa, unsigned long load, unsigned long runnable) +{ + u32 divider = LOAD_AVG_MAX - 1024 + sa->period_contrib; + + /* + * Step 2: update *_avg. + */ + sa->load_avg = div_u64(load * sa->load_sum, divider); + sa->runnable_load_avg = div_u64(runnable * sa->runnable_load_sum, divider); + WRITE_ONCE(sa->util_avg, sa->util_sum / divider); +} + +/* + * sched_entity: + * + * task: + * se_runnable() == se_weight() + * + * group: [ see update_cfs_group() ] + * se_weight() = tg->weight * grq->load_avg / tg->load_avg + * se_runnable() = se_weight(se) * grq->runnable_load_avg / grq->load_avg + * + * load_sum := runnable_sum + * load_avg = se_weight(se) * runnable_avg + * + * runnable_load_sum := runnable_sum + * runnable_load_avg = se_runnable(se) * runnable_avg + * + * XXX collapse load_sum and runnable_load_sum + * + * cfq_rq: + * + * load_sum = \Sum se_weight(se) * se->avg.load_sum + * load_avg = \Sum se->avg.load_avg + * + * runnable_load_sum = \Sum se_runnable(se) * se->avg.runnable_load_sum + * runnable_load_avg = \Sum se->avg.runable_load_avg + */ + +int __update_load_avg_blocked_se(u64 now, int cpu, struct sched_entity *se) +{ + if (entity_is_task(se)) + se->runnable_weight = se->load.weight; + + if (___update_load_sum(now, cpu, &se->avg, 0, 0, 0)) { + ___update_load_avg(&se->avg, se_weight(se), se_runnable(se)); + return 1; + } + + return 0; +} + +int __update_load_avg_se(u64 now, int cpu, struct cfs_rq *cfs_rq, struct sched_entity *se) +{ + if (entity_is_task(se)) + se->runnable_weight = se->load.weight; + + if (___update_load_sum(now, cpu, &se->avg, !!se->on_rq, !!se->on_rq, + cfs_rq->curr == se)) { + + ___update_load_avg(&se->avg, se_weight(se), se_runnable(se)); + cfs_se_util_change(&se->avg); + return 1; + } + + return 0; +} + +int __update_load_avg_cfs_rq(u64 now, int cpu, struct cfs_rq *cfs_rq) +{ + if (___update_load_sum(now, cpu, &cfs_rq->avg, + scale_load_down(cfs_rq->load.weight), + scale_load_down(cfs_rq->runnable_weight), + cfs_rq->curr != NULL)) { + + ___update_load_avg(&cfs_rq->avg, 1, 1); + return 1; + } + + return 0; +} + +/* + * rt_rq: + * + * util_sum = \Sum se->avg.util_sum but se->avg.util_sum is not tracked + * util_sum = cpu_scale * load_sum + * runnable_load_sum = load_sum + * + * load_avg and runnable_load_avg are not supported and meaningless. + * + */ + +int update_rt_rq_load_avg(u64 now, struct rq *rq, int running) +{ + if (___update_load_sum(now, rq->cpu, &rq->avg_rt, + running, + running, + running)) { + + ___update_load_avg(&rq->avg_rt, 1, 1); + return 1; + } + + return 0; +} + +/* + * dl_rq: + * + * util_sum = \Sum se->avg.util_sum but se->avg.util_sum is not tracked + * util_sum = cpu_scale * load_sum + * runnable_load_sum = load_sum + * + */ + +int update_dl_rq_load_avg(u64 now, struct rq *rq, int running) +{ + if (___update_load_sum(now, rq->cpu, &rq->avg_dl, + running, + running, + running)) { + + ___update_load_avg(&rq->avg_dl, 1, 1); + return 1; + } + + return 0; +} + +#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING) +/* + * irq: + * + * util_sum = \Sum se->avg.util_sum but se->avg.util_sum is not tracked + * util_sum = cpu_scale * load_sum + * runnable_load_sum = load_sum + * + */ + +int update_irq_load_avg(struct rq *rq, u64 running) +{ + int ret = 0; + /* + * We know the time that has been used by interrupt since last update + * but we don't when. Let be pessimistic and assume that interrupt has + * happened just before the update. This is not so far from reality + * because interrupt will most probably wake up task and trig an update + * of rq clock during which the metric si updated. + * We start to decay with normal context time and then we add the + * interrupt context time. + * We can safely remove running from rq->clock because + * rq->clock += delta with delta >= running + */ + ret = ___update_load_sum(rq->clock - running, rq->cpu, &rq->avg_irq, + 0, + 0, + 0); + ret += ___update_load_sum(rq->clock, rq->cpu, &rq->avg_irq, + 1, + 1, + 1); + + if (ret) + ___update_load_avg(&rq->avg_irq, 1, 1); + + return ret; +} +#endif diff --git a/kernel/sched/pelt.h b/kernel/sched/pelt.h new file mode 100644 index 000000000000..d2894db28955 --- /dev/null +++ b/kernel/sched/pelt.h @@ -0,0 +1,72 @@ +#ifdef CONFIG_SMP + +int __update_load_avg_blocked_se(u64 now, int cpu, struct sched_entity *se); +int __update_load_avg_se(u64 now, int cpu, struct cfs_rq *cfs_rq, struct sched_entity *se); +int __update_load_avg_cfs_rq(u64 now, int cpu, struct cfs_rq *cfs_rq); +int update_rt_rq_load_avg(u64 now, struct rq *rq, int running); +int update_dl_rq_load_avg(u64 now, struct rq *rq, int running); + +#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING) +int update_irq_load_avg(struct rq *rq, u64 running); +#else +static inline int +update_irq_load_avg(struct rq *rq, u64 running) +{ + return 0; +} +#endif + +/* + * When a task is dequeued, its estimated utilization should not be update if + * its util_avg has not been updated at least once. + * This flag is used to synchronize util_avg updates with util_est updates. + * We map this information into the LSB bit of the utilization saved at + * dequeue time (i.e. util_est.dequeued). + */ +#define UTIL_AVG_UNCHANGED 0x1 + +static inline void cfs_se_util_change(struct sched_avg *avg) +{ + unsigned int enqueued; + + if (!sched_feat(UTIL_EST)) + return; + + /* Avoid store if the flag has been already set */ + enqueued = avg->util_est.enqueued; + if (!(enqueued & UTIL_AVG_UNCHANGED)) + return; + + /* Reset flag to report util_avg has been updated */ + enqueued &= ~UTIL_AVG_UNCHANGED; + WRITE_ONCE(avg->util_est.enqueued, enqueued); +} + +#else + +static inline int +update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq) +{ + return 0; +} + +static inline int +update_rt_rq_load_avg(u64 now, struct rq *rq, int running) +{ + return 0; +} + +static inline int +update_dl_rq_load_avg(u64 now, struct rq *rq, int running) +{ + return 0; +} + +static inline int +update_irq_load_avg(struct rq *rq, u64 running) +{ + return 0; +} +#endif + + diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index eaaec8364f96..2e2955a8cf8f 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -5,6 +5,8 @@ */ #include "sched.h" +#include "pelt.h" + int sched_rr_timeslice = RR_TIMESLICE; int sysctl_sched_rr_timeslice = (MSEC_PER_SEC / HZ) * RR_TIMESLICE; @@ -973,8 +975,6 @@ static void update_curr_rt(struct rq *rq) curr->se.exec_start = now; cgroup_account_cputime(curr, delta_exec); - sched_rt_avg_update(rq, delta_exec); - if (!rt_bandwidth_enabled()) return; @@ -1578,6 +1578,14 @@ pick_next_task_rt(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) rt_queue_push_tasks(rq); + /* + * If prev task was rt, put_prev_task() has already updated the + * utilization. We only care of the case where we start to schedule a + * rt task + */ + if (rq->curr->sched_class != &rt_sched_class) + update_rt_rq_load_avg(rq_clock_task(rq), rq, 0); + return p; } @@ -1585,6 +1593,8 @@ static void put_prev_task_rt(struct rq *rq, struct task_struct *p) { update_curr_rt(rq); + update_rt_rq_load_avg(rq_clock_task(rq), rq, 1); + /* * The previous task needs to be made eligible for pushing * if it is still active @@ -2314,6 +2324,7 @@ static void task_tick_rt(struct rq *rq, struct task_struct *p, int queued) struct sched_rt_entity *rt_se = &p->rt; update_curr_rt(rq); + update_rt_rq_load_avg(rq_clock_task(rq), rq, 1); watchdog(rq, p); diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index c7742dcc136c..4a2e8cae63c4 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -594,6 +594,7 @@ struct rt_rq { unsigned long rt_nr_total; int overloaded; struct plist_head pushable_tasks; + #endif /* CONFIG_SMP */ int rt_queued; @@ -673,7 +674,26 @@ struct dl_rq { u64 bw_ratio; }; +#ifdef CONFIG_FAIR_GROUP_SCHED +/* An entity is a task if it doesn't "own" a runqueue */ +#define entity_is_task(se) (!se->my_q) +#else +#define entity_is_task(se) 1 +#endif + #ifdef CONFIG_SMP +/* + * XXX we want to get rid of these helpers and use the full load resolution. + */ +static inline long se_weight(struct sched_entity *se) +{ + return scale_load_down(se->load.weight); +} + +static inline long se_runnable(struct sched_entity *se) +{ + return scale_load_down(se->runnable_weight); +} static inline bool sched_asym_prefer(int a, int b) { @@ -833,8 +853,12 @@ struct rq { struct list_head cfs_tasks; - u64 rt_avg; - u64 age_stamp; + struct sched_avg avg_rt; + struct sched_avg avg_dl; +#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING) +#define HAVE_SCHED_AVG_IRQ + struct sched_avg avg_irq; +#endif u64 idle_stamp; u64 avg_idle; @@ -1075,7 +1099,8 @@ enum numa_faults_stats { }; extern void sched_setnuma(struct task_struct *p, int node); extern int migrate_task_to(struct task_struct *p, int cpu); -extern int migrate_swap(struct task_struct *, struct task_struct *); +extern int migrate_swap(struct task_struct *p, struct task_struct *t, + int cpu, int scpu); extern void init_numa_balancing(unsigned long clone_flags, struct task_struct *p); #else static inline void @@ -1690,15 +1715,9 @@ extern void deactivate_task(struct rq *rq, struct task_struct *p, int flags); extern void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags); -extern const_debug unsigned int sysctl_sched_time_avg; extern const_debug unsigned int sysctl_sched_nr_migrate; extern const_debug unsigned int sysctl_sched_migration_cost; -static inline u64 sched_avg_period(void) -{ - return (u64)sysctl_sched_time_avg * NSEC_PER_MSEC / 2; -} - #ifdef CONFIG_SCHED_HRTICK /* @@ -1735,8 +1754,6 @@ unsigned long arch_scale_freq_capacity(int cpu) #endif #ifdef CONFIG_SMP -extern void sched_avg_update(struct rq *rq); - #ifndef arch_scale_cpu_capacity static __always_inline unsigned long arch_scale_cpu_capacity(struct sched_domain *sd, int cpu) @@ -1747,12 +1764,6 @@ unsigned long arch_scale_cpu_capacity(struct sched_domain *sd, int cpu) return SCHED_CAPACITY_SCALE; } #endif - -static inline void sched_rt_avg_update(struct rq *rq, u64 rt_delta) -{ - rq->rt_avg += rt_delta * arch_scale_freq_capacity(cpu_of(rq)); - sched_avg_update(rq); -} #else #ifndef arch_scale_cpu_capacity static __always_inline @@ -1761,8 +1772,6 @@ unsigned long arch_scale_cpu_capacity(void __always_unused *sd, int cpu) return SCHED_CAPACITY_SCALE; } #endif -static inline void sched_rt_avg_update(struct rq *rq, u64 rt_delta) { } -static inline void sched_avg_update(struct rq *rq) { } #endif struct rq *__task_rq_lock(struct task_struct *p, struct rq_flags *rf) @@ -2177,11 +2186,16 @@ static inline void cpufreq_update_util(struct rq *rq, unsigned int flags) {} #endif #ifdef CONFIG_CPU_FREQ_GOV_SCHEDUTIL -static inline unsigned long cpu_util_dl(struct rq *rq) +static inline unsigned long cpu_bw_dl(struct rq *rq) { return (rq->dl.running_bw * SCHED_CAPACITY_SCALE) >> BW_SHIFT; } +static inline unsigned long cpu_util_dl(struct rq *rq) +{ + return READ_ONCE(rq->avg_dl.util_avg); +} + static inline unsigned long cpu_util_cfs(struct rq *rq) { unsigned long util = READ_ONCE(rq->cfs.avg.util_avg); @@ -2193,4 +2207,37 @@ static inline unsigned long cpu_util_cfs(struct rq *rq) return util; } + +static inline unsigned long cpu_util_rt(struct rq *rq) +{ + return READ_ONCE(rq->avg_rt.util_avg); +} +#endif + +#ifdef HAVE_SCHED_AVG_IRQ +static inline unsigned long cpu_util_irq(struct rq *rq) +{ + return rq->avg_irq.util_avg; +} + +static inline +unsigned long scale_irq_capacity(unsigned long util, unsigned long irq, unsigned long max) +{ + util *= (max - irq); + util /= max; + + return util; + +} +#else +static inline unsigned long cpu_util_irq(struct rq *rq) +{ + return 0; +} + +static inline +unsigned long scale_irq_capacity(unsigned long util, unsigned long irq, unsigned long max) +{ + return util; +} #endif diff --git a/kernel/sched/swait.c b/kernel/sched/swait.c index b6fb2c3b3ff7..66b59ac77c22 100644 --- a/kernel/sched/swait.c +++ b/kernel/sched/swait.c @@ -32,7 +32,7 @@ void swake_up_locked(struct swait_queue_head *q) } EXPORT_SYMBOL(swake_up_locked); -void swake_up(struct swait_queue_head *q) +void swake_up_one(struct swait_queue_head *q) { unsigned long flags; @@ -40,7 +40,7 @@ void swake_up(struct swait_queue_head *q) swake_up_locked(q); raw_spin_unlock_irqrestore(&q->lock, flags); } -EXPORT_SYMBOL(swake_up); +EXPORT_SYMBOL(swake_up_one); /* * Does not allow usage from IRQ disabled, since we must be able to @@ -69,14 +69,14 @@ void swake_up_all(struct swait_queue_head *q) } EXPORT_SYMBOL(swake_up_all); -void __prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait) +static void __prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait) { wait->task = current; if (list_empty(&wait->task_list)) - list_add(&wait->task_list, &q->task_list); + list_add_tail(&wait->task_list, &q->task_list); } -void prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait, int state) +void prepare_to_swait_exclusive(struct swait_queue_head *q, struct swait_queue *wait, int state) { unsigned long flags; @@ -85,16 +85,28 @@ void prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait, int set_current_state(state); raw_spin_unlock_irqrestore(&q->lock, flags); } -EXPORT_SYMBOL(prepare_to_swait); +EXPORT_SYMBOL(prepare_to_swait_exclusive); long prepare_to_swait_event(struct swait_queue_head *q, struct swait_queue *wait, int state) { - if (signal_pending_state(state, current)) - return -ERESTARTSYS; + unsigned long flags; + long ret = 0; - prepare_to_swait(q, wait, state); + raw_spin_lock_irqsave(&q->lock, flags); + if (unlikely(signal_pending_state(state, current))) { + /* + * See prepare_to_wait_event(). TL;DR, subsequent swake_up_one() + * must not see us. + */ + list_del_init(&wait->task_list); + ret = -ERESTARTSYS; + } else { + __prepare_to_swait(q, wait); + set_current_state(state); + } + raw_spin_unlock_irqrestore(&q->lock, flags); - return 0; + return ret; } EXPORT_SYMBOL(prepare_to_swait_event); diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c index 928be527477e..870f97b313e3 100644 --- a/kernel/sched/wait.c +++ b/kernel/sched/wait.c @@ -134,8 +134,8 @@ static void __wake_up_common_lock(struct wait_queue_head *wq_head, unsigned int * @nr_exclusive: how many wake-one or wake-many threads to wake up * @key: is directly passed to the wakeup function * - * It may be assumed that this function implies a write memory barrier before - * changing the task state if and only if any tasks are woken up. + * If this function wakes up a task, it executes a full memory barrier before + * accessing the task state. */ void __wake_up(struct wait_queue_head *wq_head, unsigned int mode, int nr_exclusive, void *key) @@ -180,8 +180,8 @@ EXPORT_SYMBOL_GPL(__wake_up_locked_key_bookmark); * * On UP it can prevent extra preemption. * - * It may be assumed that this function implies a write memory barrier before - * changing the task state if and only if any tasks are woken up. + * If this function wakes up a task, it executes a full memory barrier before + * accessing the task state. */ void __wake_up_sync_key(struct wait_queue_head *wq_head, unsigned int mode, int nr_exclusive, void *key) @@ -392,35 +392,36 @@ static inline bool is_kthread_should_stop(void) * if (condition) * break; * - * p->state = mode; condition = true; - * smp_mb(); // A smp_wmb(); // C - * if (!wq_entry->flags & WQ_FLAG_WOKEN) wq_entry->flags |= WQ_FLAG_WOKEN; - * schedule() try_to_wake_up(); - * p->state = TASK_RUNNING; ~~~~~~~~~~~~~~~~~~ - * wq_entry->flags &= ~WQ_FLAG_WOKEN; condition = true; - * smp_mb() // B smp_wmb(); // C - * wq_entry->flags |= WQ_FLAG_WOKEN; - * } - * remove_wait_queue(&wq_head, &wait); + * // in wait_woken() // in woken_wake_function() * + * p->state = mode; wq_entry->flags |= WQ_FLAG_WOKEN; + * smp_mb(); // A try_to_wake_up(): + * if (!(wq_entry->flags & WQ_FLAG_WOKEN)) <full barrier> + * schedule() if (p->state & mode) + * p->state = TASK_RUNNING; p->state = TASK_RUNNING; + * wq_entry->flags &= ~WQ_FLAG_WOKEN; ~~~~~~~~~~~~~~~~~~ + * smp_mb(); // B condition = true; + * } smp_mb(); // C + * remove_wait_queue(&wq_head, &wait); wq_entry->flags |= WQ_FLAG_WOKEN; */ long wait_woken(struct wait_queue_entry *wq_entry, unsigned mode, long timeout) { - set_current_state(mode); /* A */ /* - * The above implies an smp_mb(), which matches with the smp_wmb() from - * woken_wake_function() such that if we observe WQ_FLAG_WOKEN we must - * also observe all state before the wakeup. + * The below executes an smp_mb(), which matches with the full barrier + * executed by the try_to_wake_up() in woken_wake_function() such that + * either we see the store to wq_entry->flags in woken_wake_function() + * or woken_wake_function() sees our store to current->state. */ + set_current_state(mode); /* A */ if (!(wq_entry->flags & WQ_FLAG_WOKEN) && !is_kthread_should_stop()) timeout = schedule_timeout(timeout); __set_current_state(TASK_RUNNING); /* - * The below implies an smp_mb(), it too pairs with the smp_wmb() from - * woken_wake_function() such that we must either observe the wait - * condition being true _OR_ WQ_FLAG_WOKEN such that we will not miss - * an event. + * The below executes an smp_mb(), which matches with the smp_mb() (C) + * in woken_wake_function() such that either we see the wait condition + * being true or the store to wq_entry->flags in woken_wake_function() + * follows ours in the coherence order. */ smp_store_mb(wq_entry->flags, wq_entry->flags & ~WQ_FLAG_WOKEN); /* B */ @@ -430,14 +431,8 @@ EXPORT_SYMBOL(wait_woken); int woken_wake_function(struct wait_queue_entry *wq_entry, unsigned mode, int sync, void *key) { - /* - * Although this function is called under waitqueue lock, LOCK - * doesn't imply write barrier and the users expects write - * barrier semantics on wakeup functions. The following - * smp_wmb() is equivalent to smp_wmb() in try_to_wake_up() - * and is paired with smp_store_mb() in wait_woken(). - */ - smp_wmb(); /* C */ + /* Pairs with the smp_store_mb() in wait_woken(). */ + smp_mb(); /* C */ wq_entry->flags |= WQ_FLAG_WOKEN; return default_wake_function(wq_entry, mode, sync, key); diff --git a/kernel/smpboot.c b/kernel/smpboot.c index 5043e7433f4b..c230c2dd48e1 100644 --- a/kernel/smpboot.c +++ b/kernel/smpboot.c @@ -238,8 +238,7 @@ int smpboot_unpark_threads(unsigned int cpu) mutex_lock(&smpboot_threads_lock); list_for_each_entry(cur, &hotplug_threads, list) - if (cpumask_test_cpu(cpu, cur->cpumask)) - smpboot_unpark_thread(cur, cpu); + smpboot_unpark_thread(cur, cpu); mutex_unlock(&smpboot_threads_lock); return 0; } @@ -280,34 +279,26 @@ static void smpboot_destroy_threads(struct smp_hotplug_thread *ht) } /** - * smpboot_register_percpu_thread_cpumask - Register a per_cpu thread related + * smpboot_register_percpu_thread - Register a per_cpu thread related * to hotplug * @plug_thread: Hotplug thread descriptor - * @cpumask: The cpumask where threads run * * Creates and starts the threads on all online cpus. */ -int smpboot_register_percpu_thread_cpumask(struct smp_hotplug_thread *plug_thread, - const struct cpumask *cpumask) +int smpboot_register_percpu_thread(struct smp_hotplug_thread *plug_thread) { unsigned int cpu; int ret = 0; - if (!alloc_cpumask_var(&plug_thread->cpumask, GFP_KERNEL)) - return -ENOMEM; - cpumask_copy(plug_thread->cpumask, cpumask); - get_online_cpus(); mutex_lock(&smpboot_threads_lock); for_each_online_cpu(cpu) { ret = __smpboot_create_thread(plug_thread, cpu); if (ret) { smpboot_destroy_threads(plug_thread); - free_cpumask_var(plug_thread->cpumask); goto out; } - if (cpumask_test_cpu(cpu, cpumask)) - smpboot_unpark_thread(plug_thread, cpu); + smpboot_unpark_thread(plug_thread, cpu); } list_add(&plug_thread->list, &hotplug_threads); out: @@ -315,7 +306,7 @@ out: put_online_cpus(); return ret; } -EXPORT_SYMBOL_GPL(smpboot_register_percpu_thread_cpumask); +EXPORT_SYMBOL_GPL(smpboot_register_percpu_thread); /** * smpboot_unregister_percpu_thread - Unregister a per_cpu thread related to hotplug @@ -331,44 +322,9 @@ void smpboot_unregister_percpu_thread(struct smp_hotplug_thread *plug_thread) smpboot_destroy_threads(plug_thread); mutex_unlock(&smpboot_threads_lock); put_online_cpus(); - free_cpumask_var(plug_thread->cpumask); } EXPORT_SYMBOL_GPL(smpboot_unregister_percpu_thread); -/** - * smpboot_update_cpumask_percpu_thread - Adjust which per_cpu hotplug threads stay parked - * @plug_thread: Hotplug thread descriptor - * @new: Revised mask to use - * - * The cpumask field in the smp_hotplug_thread must not be updated directly - * by the client, but only by calling this function. - * This function can only be called on a registered smp_hotplug_thread. - */ -void smpboot_update_cpumask_percpu_thread(struct smp_hotplug_thread *plug_thread, - const struct cpumask *new) -{ - struct cpumask *old = plug_thread->cpumask; - static struct cpumask tmp; - unsigned int cpu; - - lockdep_assert_cpus_held(); - mutex_lock(&smpboot_threads_lock); - - /* Park threads that were exclusively enabled on the old mask. */ - cpumask_andnot(&tmp, old, new); - for_each_cpu_and(cpu, &tmp, cpu_online_mask) - smpboot_park_thread(plug_thread, cpu); - - /* Unpark threads that are exclusively enabled on the new mask. */ - cpumask_andnot(&tmp, new, old); - for_each_cpu_and(cpu, &tmp, cpu_online_mask) - smpboot_unpark_thread(plug_thread, cpu); - - cpumask_copy(old, new); - - mutex_unlock(&smpboot_threads_lock); -} - static DEFINE_PER_CPU(atomic_t, cpu_hotplug_state) = ATOMIC_INIT(CPU_POST_DEAD); /* diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c index e190d1ef3a23..067cb83f37ea 100644 --- a/kernel/stop_machine.c +++ b/kernel/stop_machine.c @@ -81,6 +81,7 @@ static bool cpu_stop_queue_work(unsigned int cpu, struct cpu_stop_work *work) unsigned long flags; bool enabled; + preempt_disable(); raw_spin_lock_irqsave(&stopper->lock, flags); enabled = stopper->enabled; if (enabled) @@ -90,6 +91,7 @@ static bool cpu_stop_queue_work(unsigned int cpu, struct cpu_stop_work *work) raw_spin_unlock_irqrestore(&stopper->lock, flags); wake_up_q(&wakeq); + preempt_enable(); return enabled; } @@ -236,13 +238,24 @@ static int cpu_stop_queue_two_works(int cpu1, struct cpu_stop_work *work1, struct cpu_stopper *stopper2 = per_cpu_ptr(&cpu_stopper, cpu2); DEFINE_WAKE_Q(wakeq); int err; + retry: + /* + * The waking up of stopper threads has to happen in the same + * scheduling context as the queueing. Otherwise, there is a + * possibility of one of the above stoppers being woken up by another + * CPU, and preempting us. This will cause us to not wake up the other + * stopper forever. + */ + preempt_disable(); raw_spin_lock_irq(&stopper1->lock); raw_spin_lock_nested(&stopper2->lock, SINGLE_DEPTH_NESTING); - err = -ENOENT; - if (!stopper1->enabled || !stopper2->enabled) + if (!stopper1->enabled || !stopper2->enabled) { + err = -ENOENT; goto unlock; + } + /* * Ensure that if we race with __stop_cpus() the stoppers won't get * queued up in reverse order leading to system deadlock. @@ -253,36 +266,30 @@ retry: * It can be falsely true but it is safe to spin until it is cleared, * queue_stop_cpus_work() does everything under preempt_disable(). */ - err = -EDEADLK; - if (unlikely(stop_cpus_in_progress)) - goto unlock; + if (unlikely(stop_cpus_in_progress)) { + err = -EDEADLK; + goto unlock; + } err = 0; __cpu_stop_queue_work(stopper1, work1, &wakeq); __cpu_stop_queue_work(stopper2, work2, &wakeq); - /* - * The waking up of stopper threads has to happen - * in the same scheduling context as the queueing. - * Otherwise, there is a possibility of one of the - * above stoppers being woken up by another CPU, - * and preempting us. This will cause us to n ot - * wake up the other stopper forever. - */ - preempt_disable(); + unlock: raw_spin_unlock(&stopper2->lock); raw_spin_unlock_irq(&stopper1->lock); if (unlikely(err == -EDEADLK)) { + preempt_enable(); + while (stop_cpus_in_progress) cpu_relax(); + goto retry; } - if (!err) { - wake_up_q(&wakeq); - preempt_enable(); - } + wake_up_q(&wakeq); + preempt_enable(); return err; } diff --git a/kernel/sys.c b/kernel/sys.c index 38509dc1f77b..e27b51d3facd 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -2512,11 +2512,11 @@ static int do_sysinfo(struct sysinfo *info) { unsigned long mem_total, sav_total; unsigned int mem_unit, bitcount; - struct timespec tp; + struct timespec64 tp; memset(info, 0, sizeof(struct sysinfo)); - get_monotonic_boottime(&tp); + ktime_get_boottime_ts64(&tp); info->uptime = tp.tv_sec + (tp.tv_nsec ? 1 : 0); get_avenrun(info->loads, 0, SI_LOAD_SHIFT - FSHIFT); diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 2d9837c0aff4..f22f76b7a138 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -368,14 +368,6 @@ static struct ctl_table kern_table[] = { .mode = 0644, .proc_handler = proc_dointvec, }, - { - .procname = "sched_time_avg_ms", - .data = &sysctl_sched_time_avg, - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = &one, - }, #ifdef CONFIG_SCHEDSTATS { .procname = "sched_schedstats", diff --git a/kernel/test_kprobes.c b/kernel/test_kprobes.c index dd53e354f630..7bca480151b0 100644 --- a/kernel/test_kprobes.c +++ b/kernel/test_kprobes.c @@ -162,90 +162,6 @@ static int test_kprobes(void) } -#if 0 -static u32 jph_val; - -static u32 j_kprobe_target(u32 value) -{ - if (preemptible()) { - handler_errors++; - pr_err("jprobe-handler is preemptible\n"); - } - if (value != rand1) { - handler_errors++; - pr_err("incorrect value in jprobe handler\n"); - } - - jph_val = rand1; - jprobe_return(); - return 0; -} - -static struct jprobe jp = { - .entry = j_kprobe_target, - .kp.symbol_name = "kprobe_target" -}; - -static int test_jprobe(void) -{ - int ret; - - ret = register_jprobe(&jp); - if (ret < 0) { - pr_err("register_jprobe returned %d\n", ret); - return ret; - } - - ret = target(rand1); - unregister_jprobe(&jp); - if (jph_val == 0) { - pr_err("jprobe handler not called\n"); - handler_errors++; - } - - return 0; -} - -static struct jprobe jp2 = { - .entry = j_kprobe_target, - .kp.symbol_name = "kprobe_target2" -}; - -static int test_jprobes(void) -{ - int ret; - struct jprobe *jps[2] = {&jp, &jp2}; - - /* addr and flags should be cleard for reusing kprobe. */ - jp.kp.addr = NULL; - jp.kp.flags = 0; - ret = register_jprobes(jps, 2); - if (ret < 0) { - pr_err("register_jprobes returned %d\n", ret); - return ret; - } - - jph_val = 0; - ret = target(rand1); - if (jph_val == 0) { - pr_err("jprobe handler not called\n"); - handler_errors++; - } - - jph_val = 0; - ret = target2(rand1); - if (jph_val == 0) { - pr_err("jprobe handler2 not called\n"); - handler_errors++; - } - unregister_jprobes(jps, 2); - - return 0; -} -#else -#define test_jprobe() (0) -#define test_jprobes() (0) -#endif #ifdef CONFIG_KRETPROBES static u32 krph_val; @@ -383,16 +299,6 @@ int init_test_probes(void) if (ret < 0) errors++; - num_tests++; - ret = test_jprobe(); - if (ret < 0) - errors++; - - num_tests++; - ret = test_jprobes(); - if (ret < 0) - errors++; - #ifdef CONFIG_KRETPROBES num_tests++; ret = test_kretprobe(); diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c index 639321bf2e39..fa5de5e8de61 100644 --- a/kernel/time/alarmtimer.c +++ b/kernel/time/alarmtimer.c @@ -581,11 +581,11 @@ static void alarm_timer_rearm(struct k_itimer *timr) * @timr: Pointer to the posixtimer data struct * @now: Current time to forward the timer against */ -static int alarm_timer_forward(struct k_itimer *timr, ktime_t now) +static s64 alarm_timer_forward(struct k_itimer *timr, ktime_t now) { struct alarm *alarm = &timr->it.alarm.alarmtimer; - return (int) alarm_forward(alarm, timr->it_interval, now); + return alarm_forward(alarm, timr->it_interval, now); } /** @@ -808,7 +808,8 @@ static int alarm_timer_nsleep(const clockid_t which_clock, int flags, /* Convert (if necessary) to absolute time */ if (flags != TIMER_ABSTIME) { ktime_t now = alarm_bases[type].gettime(); - exp = ktime_add(now, exp); + + exp = ktime_add_safe(now, exp); } ret = alarmtimer_do_nsleep(&alarm, exp, type); diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c index 16c027e9cc73..8c0e4092f661 100644 --- a/kernel/time/clockevents.c +++ b/kernel/time/clockevents.c @@ -463,6 +463,12 @@ void clockevents_register_device(struct clock_event_device *dev) dev->cpumask = cpumask_of(smp_processor_id()); } + if (dev->cpumask == cpu_all_mask) { + WARN(1, "%s cpumask == cpu_all_mask, using cpu_possible_mask instead\n", + dev->name); + dev->cpumask = cpu_possible_mask; + } + raw_spin_lock_irqsave(&clockevents_lock, flags); list_add(&dev->list, &clockevent_devices); diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index f89a78e2792b..f74fb00d8064 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -94,6 +94,8 @@ EXPORT_SYMBOL_GPL(clocks_calc_mult_shift); /*[Clocksource internal variables]--------- * curr_clocksource: * currently selected clocksource. + * suspend_clocksource: + * used to calculate the suspend time. * clocksource_list: * linked list with the registered clocksources * clocksource_mutex: @@ -102,10 +104,12 @@ EXPORT_SYMBOL_GPL(clocks_calc_mult_shift); * Name of the user-specified clocksource. */ static struct clocksource *curr_clocksource; +static struct clocksource *suspend_clocksource; static LIST_HEAD(clocksource_list); static DEFINE_MUTEX(clocksource_mutex); static char override_name[CS_NAME_LEN]; static int finished_booting; +static u64 suspend_start; #ifdef CONFIG_CLOCKSOURCE_WATCHDOG static void clocksource_watchdog_work(struct work_struct *work); @@ -447,6 +451,140 @@ static inline void clocksource_watchdog_unlock(unsigned long *flags) { } #endif /* CONFIG_CLOCKSOURCE_WATCHDOG */ +static bool clocksource_is_suspend(struct clocksource *cs) +{ + return cs == suspend_clocksource; +} + +static void __clocksource_suspend_select(struct clocksource *cs) +{ + /* + * Skip the clocksource which will be stopped in suspend state. + */ + if (!(cs->flags & CLOCK_SOURCE_SUSPEND_NONSTOP)) + return; + + /* + * The nonstop clocksource can be selected as the suspend clocksource to + * calculate the suspend time, so it should not supply suspend/resume + * interfaces to suspend the nonstop clocksource when system suspends. + */ + if (cs->suspend || cs->resume) { + pr_warn("Nonstop clocksource %s should not supply suspend/resume interfaces\n", + cs->name); + } + + /* Pick the best rating. */ + if (!suspend_clocksource || cs->rating > suspend_clocksource->rating) + suspend_clocksource = cs; +} + +/** + * clocksource_suspend_select - Select the best clocksource for suspend timing + * @fallback: if select a fallback clocksource + */ +static void clocksource_suspend_select(bool fallback) +{ + struct clocksource *cs, *old_suspend; + + old_suspend = suspend_clocksource; + if (fallback) + suspend_clocksource = NULL; + + list_for_each_entry(cs, &clocksource_list, list) { + /* Skip current if we were requested for a fallback. */ + if (fallback && cs == old_suspend) + continue; + + __clocksource_suspend_select(cs); + } +} + +/** + * clocksource_start_suspend_timing - Start measuring the suspend timing + * @cs: current clocksource from timekeeping + * @start_cycles: current cycles from timekeeping + * + * This function will save the start cycle values of suspend timer to calculate + * the suspend time when resuming system. + * + * This function is called late in the suspend process from timekeeping_suspend(), + * that means processes are freezed, non-boot cpus and interrupts are disabled + * now. It is therefore possible to start the suspend timer without taking the + * clocksource mutex. + */ +void clocksource_start_suspend_timing(struct clocksource *cs, u64 start_cycles) +{ + if (!suspend_clocksource) + return; + + /* + * If current clocksource is the suspend timer, we should use the + * tkr_mono.cycle_last value as suspend_start to avoid same reading + * from suspend timer. + */ + if (clocksource_is_suspend(cs)) { + suspend_start = start_cycles; + return; + } + + if (suspend_clocksource->enable && + suspend_clocksource->enable(suspend_clocksource)) { + pr_warn_once("Failed to enable the non-suspend-able clocksource.\n"); + return; + } + + suspend_start = suspend_clocksource->read(suspend_clocksource); +} + +/** + * clocksource_stop_suspend_timing - Stop measuring the suspend timing + * @cs: current clocksource from timekeeping + * @cycle_now: current cycles from timekeeping + * + * This function will calculate the suspend time from suspend timer. + * + * Returns nanoseconds since suspend started, 0 if no usable suspend clocksource. + * + * This function is called early in the resume process from timekeeping_resume(), + * that means there is only one cpu, no processes are running and the interrupts + * are disabled. It is therefore possible to stop the suspend timer without + * taking the clocksource mutex. + */ +u64 clocksource_stop_suspend_timing(struct clocksource *cs, u64 cycle_now) +{ + u64 now, delta, nsec = 0; + + if (!suspend_clocksource) + return 0; + + /* + * If current clocksource is the suspend timer, we should use the + * tkr_mono.cycle_last value from timekeeping as current cycle to + * avoid same reading from suspend timer. + */ + if (clocksource_is_suspend(cs)) + now = cycle_now; + else + now = suspend_clocksource->read(suspend_clocksource); + + if (now > suspend_start) { + delta = clocksource_delta(now, suspend_start, + suspend_clocksource->mask); + nsec = mul_u64_u32_shr(delta, suspend_clocksource->mult, + suspend_clocksource->shift); + } + + /* + * Disable the suspend timer to save power if current clocksource is + * not the suspend timer. + */ + if (!clocksource_is_suspend(cs) && suspend_clocksource->disable) + suspend_clocksource->disable(suspend_clocksource); + + return nsec; +} + /** * clocksource_suspend - suspend the clocksource(s) */ @@ -792,6 +930,7 @@ int __clocksource_register_scale(struct clocksource *cs, u32 scale, u32 freq) clocksource_select(); clocksource_select_watchdog(false); + __clocksource_suspend_select(cs); mutex_unlock(&clocksource_mutex); return 0; } @@ -820,6 +959,7 @@ void clocksource_change_rating(struct clocksource *cs, int rating) clocksource_select(); clocksource_select_watchdog(false); + clocksource_suspend_select(false); mutex_unlock(&clocksource_mutex); } EXPORT_SYMBOL(clocksource_change_rating); @@ -845,6 +985,15 @@ static int clocksource_unbind(struct clocksource *cs) return -EBUSY; } + if (clocksource_is_suspend(cs)) { + /* + * Select and try to install a replacement suspend clocksource. + * If no replacement suspend clocksource, we will just let the + * clocksource go and have no suspend clocksource. + */ + clocksource_suspend_select(true); + } + clocksource_watchdog_lock(&flags); clocksource_dequeue_watchdog(cs); list_del_init(&cs->list); diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index 3e93c54bd3a1..e1a549c9e399 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -718,8 +718,8 @@ static void hrtimer_switch_to_hres(void) struct hrtimer_cpu_base *base = this_cpu_ptr(&hrtimer_bases); if (tick_init_highres()) { - printk(KERN_WARNING "Could not switch to high resolution " - "mode on CPU %d\n", base->cpu); + pr_warn("Could not switch to high resolution mode on CPU %u\n", + base->cpu); return; } base->hres_active = 1; @@ -1573,8 +1573,7 @@ retry: else expires_next = ktime_add(now, delta); tick_program_event(expires_next, 1); - printk_once(KERN_WARNING "hrtimer: interrupt took %llu ns\n", - ktime_to_ns(delta)); + pr_warn_once("hrtimer: interrupt took %llu ns\n", ktime_to_ns(delta)); } /* called with interrupts disabled */ diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c index a09ded765f6c..c5e0cba3b39c 100644 --- a/kernel/time/ntp.c +++ b/kernel/time/ntp.c @@ -502,7 +502,7 @@ static void sched_sync_hw_clock(struct timespec64 now, { struct timespec64 next; - getnstimeofday64(&next); + ktime_get_real_ts64(&next); if (!fail) next.tv_sec = 659; else { @@ -537,7 +537,7 @@ static void sync_rtc_clock(void) if (!IS_ENABLED(CONFIG_RTC_SYSTOHC)) return; - getnstimeofday64(&now); + ktime_get_real_ts64(&now); adjust = now; if (persistent_clock_is_local) @@ -591,7 +591,7 @@ static bool sync_cmos_clock(void) * Architectures are strongly encouraged to use rtclib and not * implement this legacy API. */ - getnstimeofday64(&now); + ktime_get_real_ts64(&now); if (rtc_tv_nsec_ok(-1 * target_nsec, &adjust, &now)) { if (persistent_clock_is_local) adjust.tv_sec -= (sys_tz.tz_minuteswest * 60); @@ -642,7 +642,7 @@ void ntp_notify_cmos_timer(void) /* * Propagate a new txc->status value into the NTP state: */ -static inline void process_adj_status(struct timex *txc, struct timespec64 *ts) +static inline void process_adj_status(const struct timex *txc) { if ((time_status & STA_PLL) && !(txc->status & STA_PLL)) { time_state = TIME_OK; @@ -665,12 +665,10 @@ static inline void process_adj_status(struct timex *txc, struct timespec64 *ts) } -static inline void process_adjtimex_modes(struct timex *txc, - struct timespec64 *ts, - s32 *time_tai) +static inline void process_adjtimex_modes(const struct timex *txc, s32 *time_tai) { if (txc->modes & ADJ_STATUS) - process_adj_status(txc, ts); + process_adj_status(txc); if (txc->modes & ADJ_NANO) time_status |= STA_NANO; @@ -718,7 +716,7 @@ static inline void process_adjtimex_modes(struct timex *txc, * adjtimex mainly allows reading (and writing, if superuser) of * kernel time-keeping variables. used by xntpd. */ -int __do_adjtimex(struct timex *txc, struct timespec64 *ts, s32 *time_tai) +int __do_adjtimex(struct timex *txc, const struct timespec64 *ts, s32 *time_tai) { int result; @@ -735,7 +733,7 @@ int __do_adjtimex(struct timex *txc, struct timespec64 *ts, s32 *time_tai) /* If there are input parameters, then process them: */ if (txc->modes) - process_adjtimex_modes(txc, ts, time_tai); + process_adjtimex_modes(txc, time_tai); txc->offset = shift_right(time_offset * NTP_INTERVAL_FREQ, NTP_SCALE_SHIFT); @@ -1022,12 +1020,11 @@ void __hardpps(const struct timespec64 *phase_ts, const struct timespec64 *raw_t static int __init ntp_tick_adj_setup(char *str) { - int rc = kstrtol(str, 0, (long *)&ntp_tick_adj); - + int rc = kstrtos64(str, 0, &ntp_tick_adj); if (rc) return rc; - ntp_tick_adj <<= NTP_SCALE_SHIFT; + ntp_tick_adj <<= NTP_SCALE_SHIFT; return 1; } diff --git a/kernel/time/ntp_internal.h b/kernel/time/ntp_internal.h index 909bd1f1bfb1..c24b0e13f011 100644 --- a/kernel/time/ntp_internal.h +++ b/kernel/time/ntp_internal.h @@ -8,6 +8,6 @@ extern void ntp_clear(void); extern u64 ntp_tick_length(void); extern ktime_t ntp_get_next_leap(void); extern int second_overflow(time64_t secs); -extern int __do_adjtimex(struct timex *, struct timespec64 *, s32 *); -extern void __hardpps(const struct timespec64 *, const struct timespec64 *); +extern int __do_adjtimex(struct timex *txc, const struct timespec64 *ts, s32 *time_tai); +extern void __hardpps(const struct timespec64 *phase_ts, const struct timespec64 *raw_ts); #endif /* _LINUX_NTP_INTERNAL_H */ diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c index 9cdf54b04ca8..294d7b65af33 100644 --- a/kernel/time/posix-cpu-timers.c +++ b/kernel/time/posix-cpu-timers.c @@ -85,7 +85,7 @@ static void bump_cpu_timer(struct k_itimer *timer, u64 now) continue; timer->it.cpu.expires += incr; - timer->it_overrun += 1 << i; + timer->it_overrun += 1LL << i; delta -= incr; } } diff --git a/kernel/time/posix-stubs.c b/kernel/time/posix-stubs.c index 26aa9569e24a..2c6847d5d69b 100644 --- a/kernel/time/posix-stubs.c +++ b/kernel/time/posix-stubs.c @@ -81,7 +81,7 @@ int do_clock_gettime(clockid_t which_clock, struct timespec64 *tp) ktime_get_ts64(tp); break; case CLOCK_BOOTTIME: - get_monotonic_boottime64(tp); + ktime_get_boottime_ts64(tp); break; default: return -EINVAL; diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c index e08ce3f27447..3ac7295306dc 100644 --- a/kernel/time/posix-timers.c +++ b/kernel/time/posix-timers.c @@ -228,21 +228,21 @@ static int posix_ktime_get_ts(clockid_t which_clock, struct timespec64 *tp) */ static int posix_get_monotonic_raw(clockid_t which_clock, struct timespec64 *tp) { - getrawmonotonic64(tp); + ktime_get_raw_ts64(tp); return 0; } static int posix_get_realtime_coarse(clockid_t which_clock, struct timespec64 *tp) { - *tp = current_kernel_time64(); + ktime_get_coarse_real_ts64(tp); return 0; } static int posix_get_monotonic_coarse(clockid_t which_clock, struct timespec64 *tp) { - *tp = get_monotonic_coarse64(); + ktime_get_coarse_ts64(tp); return 0; } @@ -254,13 +254,13 @@ static int posix_get_coarse_res(const clockid_t which_clock, struct timespec64 * static int posix_get_boottime(const clockid_t which_clock, struct timespec64 *tp) { - get_monotonic_boottime64(tp); + ktime_get_boottime_ts64(tp); return 0; } static int posix_get_tai(clockid_t which_clock, struct timespec64 *tp) { - timekeeping_clocktai64(tp); + ktime_get_clocktai_ts64(tp); return 0; } @@ -283,6 +283,17 @@ static __init int init_posix_timers(void) } __initcall(init_posix_timers); +/* + * The siginfo si_overrun field and the return value of timer_getoverrun(2) + * are of type int. Clamp the overrun value to INT_MAX + */ +static inline int timer_overrun_to_int(struct k_itimer *timr, int baseval) +{ + s64 sum = timr->it_overrun_last + (s64)baseval; + + return sum > (s64)INT_MAX ? INT_MAX : (int)sum; +} + static void common_hrtimer_rearm(struct k_itimer *timr) { struct hrtimer *timer = &timr->it.real.timer; @@ -290,9 +301,8 @@ static void common_hrtimer_rearm(struct k_itimer *timr) if (!timr->it_interval) return; - timr->it_overrun += (unsigned int) hrtimer_forward(timer, - timer->base->get_time(), - timr->it_interval); + timr->it_overrun += hrtimer_forward(timer, timer->base->get_time(), + timr->it_interval); hrtimer_restart(timer); } @@ -321,10 +331,10 @@ void posixtimer_rearm(struct siginfo *info) timr->it_active = 1; timr->it_overrun_last = timr->it_overrun; - timr->it_overrun = -1; + timr->it_overrun = -1LL; ++timr->it_requeue_pending; - info->si_overrun += timr->it_overrun_last; + info->si_overrun = timer_overrun_to_int(timr, info->si_overrun); } unlock_timer(timr, flags); @@ -418,9 +428,8 @@ static enum hrtimer_restart posix_timer_fn(struct hrtimer *timer) now = ktime_add(now, kj); } #endif - timr->it_overrun += (unsigned int) - hrtimer_forward(timer, now, - timr->it_interval); + timr->it_overrun += hrtimer_forward(timer, now, + timr->it_interval); ret = HRTIMER_RESTART; ++timr->it_requeue_pending; timr->it_active = 1; @@ -524,7 +533,7 @@ static int do_timer_create(clockid_t which_clock, struct sigevent *event, new_timer->it_id = (timer_t) new_timer_id; new_timer->it_clock = which_clock; new_timer->kclock = kc; - new_timer->it_overrun = -1; + new_timer->it_overrun = -1LL; if (event) { rcu_read_lock(); @@ -645,11 +654,11 @@ static ktime_t common_hrtimer_remaining(struct k_itimer *timr, ktime_t now) return __hrtimer_expires_remaining_adjusted(timer, now); } -static int common_hrtimer_forward(struct k_itimer *timr, ktime_t now) +static s64 common_hrtimer_forward(struct k_itimer *timr, ktime_t now) { struct hrtimer *timer = &timr->it.real.timer; - return (int)hrtimer_forward(timer, now, timr->it_interval); + return hrtimer_forward(timer, now, timr->it_interval); } /* @@ -743,7 +752,7 @@ static int do_timer_gettime(timer_t timer_id, struct itimerspec64 *setting) /* Get the time remaining on a POSIX.1b interval timer. */ SYSCALL_DEFINE2(timer_gettime, timer_t, timer_id, - struct itimerspec __user *, setting) + struct __kernel_itimerspec __user *, setting) { struct itimerspec64 cur_setting; @@ -755,7 +764,8 @@ SYSCALL_DEFINE2(timer_gettime, timer_t, timer_id, return ret; } -#ifdef CONFIG_COMPAT +#ifdef CONFIG_COMPAT_32BIT_TIME + COMPAT_SYSCALL_DEFINE2(timer_gettime, timer_t, timer_id, struct compat_itimerspec __user *, setting) { @@ -768,6 +778,7 @@ COMPAT_SYSCALL_DEFINE2(timer_gettime, timer_t, timer_id, } return ret; } + #endif /* @@ -789,7 +800,7 @@ SYSCALL_DEFINE1(timer_getoverrun, timer_t, timer_id) if (!timr) return -EINVAL; - overrun = timr->it_overrun_last; + overrun = timer_overrun_to_int(timr, 0); unlock_timer(timr, flags); return overrun; @@ -906,8 +917,8 @@ retry: /* Set a POSIX.1b interval timer */ SYSCALL_DEFINE4(timer_settime, timer_t, timer_id, int, flags, - const struct itimerspec __user *, new_setting, - struct itimerspec __user *, old_setting) + const struct __kernel_itimerspec __user *, new_setting, + struct __kernel_itimerspec __user *, old_setting) { struct itimerspec64 new_spec, old_spec; struct itimerspec64 *rtn = old_setting ? &old_spec : NULL; @@ -927,7 +938,7 @@ SYSCALL_DEFINE4(timer_settime, timer_t, timer_id, int, flags, return error; } -#ifdef CONFIG_COMPAT +#ifdef CONFIG_COMPAT_32BIT_TIME COMPAT_SYSCALL_DEFINE4(timer_settime, timer_t, timer_id, int, flags, struct compat_itimerspec __user *, new, struct compat_itimerspec __user *, old) diff --git a/kernel/time/posix-timers.h b/kernel/time/posix-timers.h index 151e28f5bf30..ddb21145211a 100644 --- a/kernel/time/posix-timers.h +++ b/kernel/time/posix-timers.h @@ -19,7 +19,7 @@ struct k_clock { void (*timer_get)(struct k_itimer *timr, struct itimerspec64 *cur_setting); void (*timer_rearm)(struct k_itimer *timr); - int (*timer_forward)(struct k_itimer *timr, ktime_t now); + s64 (*timer_forward)(struct k_itimer *timr, ktime_t now); ktime_t (*timer_remaining)(struct k_itimer *timr, ktime_t now); int (*timer_try_to_cancel)(struct k_itimer *timr); void (*timer_arm)(struct k_itimer *timr, ktime_t expires, diff --git a/kernel/time/tick-broadcast-hrtimer.c b/kernel/time/tick-broadcast-hrtimer.c index 58045eb976c3..a59641fb88b6 100644 --- a/kernel/time/tick-broadcast-hrtimer.c +++ b/kernel/time/tick-broadcast-hrtimer.c @@ -90,7 +90,7 @@ static struct clock_event_device ce_broadcast_hrtimer = { .max_delta_ticks = ULONG_MAX, .mult = 1, .shift = 0, - .cpumask = cpu_all_mask, + .cpumask = cpu_possible_mask, }; static enum hrtimer_restart bc_handler(struct hrtimer *t) diff --git a/kernel/time/time.c b/kernel/time/time.c index 2b41e8e2d31d..ccdb351277ee 100644 --- a/kernel/time/time.c +++ b/kernel/time/time.c @@ -64,7 +64,7 @@ EXPORT_SYMBOL(sys_tz); */ SYSCALL_DEFINE1(time, time_t __user *, tloc) { - time_t i = get_seconds(); + time_t i = (time_t)ktime_get_real_seconds(); if (tloc) { if (put_user(i,tloc)) @@ -107,11 +107,9 @@ SYSCALL_DEFINE1(stime, time_t __user *, tptr) /* compat_time_t is a 32 bit "long" and needs to get converted. */ COMPAT_SYSCALL_DEFINE1(time, compat_time_t __user *, tloc) { - struct timeval tv; compat_time_t i; - do_gettimeofday(&tv); - i = tv.tv_sec; + i = (compat_time_t)ktime_get_real_seconds(); if (tloc) { if (put_user(i,tloc)) @@ -931,7 +929,7 @@ int compat_put_timespec64(const struct timespec64 *ts, void __user *uts) EXPORT_SYMBOL_GPL(compat_put_timespec64); int get_itimerspec64(struct itimerspec64 *it, - const struct itimerspec __user *uit) + const struct __kernel_itimerspec __user *uit) { int ret; @@ -946,7 +944,7 @@ int get_itimerspec64(struct itimerspec64 *it, EXPORT_SYMBOL_GPL(get_itimerspec64); int put_itimerspec64(const struct itimerspec64 *it, - struct itimerspec __user *uit) + struct __kernel_itimerspec __user *uit) { int ret; @@ -959,3 +957,24 @@ int put_itimerspec64(const struct itimerspec64 *it, return ret; } EXPORT_SYMBOL_GPL(put_itimerspec64); + +int get_compat_itimerspec64(struct itimerspec64 *its, + const struct compat_itimerspec __user *uits) +{ + + if (__compat_get_timespec64(&its->it_interval, &uits->it_interval) || + __compat_get_timespec64(&its->it_value, &uits->it_value)) + return -EFAULT; + return 0; +} +EXPORT_SYMBOL_GPL(get_compat_itimerspec64); + +int put_compat_itimerspec64(const struct itimerspec64 *its, + struct compat_itimerspec __user *uits) +{ + if (__compat_put_timespec64(&its->it_interval, &uits->it_interval) || + __compat_put_timespec64(&its->it_value, &uits->it_value)) + return -EFAULT; + return 0; +} +EXPORT_SYMBOL_GPL(put_compat_itimerspec64); diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 4786df904c22..d9e659a12c76 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -34,6 +34,14 @@ #define TK_MIRROR (1 << 1) #define TK_CLOCK_WAS_SET (1 << 2) +enum timekeeping_adv_mode { + /* Update timekeeper when a tick has passed */ + TK_ADV_TICK, + + /* Update timekeeper on a direct frequency change */ + TK_ADV_FREQ +}; + /* * The most important data for readout fits into a single 64 byte * cache line. @@ -97,7 +105,7 @@ static inline void tk_normalize_xtime(struct timekeeper *tk) } } -static inline struct timespec64 tk_xtime(struct timekeeper *tk) +static inline struct timespec64 tk_xtime(const struct timekeeper *tk) { struct timespec64 ts; @@ -154,7 +162,7 @@ static inline void tk_update_sleep_time(struct timekeeper *tk, ktime_t delta) * a read of the fast-timekeeper tkrs (which is protected by its own locking * and update logic). */ -static inline u64 tk_clock_read(struct tk_read_base *tkr) +static inline u64 tk_clock_read(const struct tk_read_base *tkr) { struct clocksource *clock = READ_ONCE(tkr->clock); @@ -203,7 +211,7 @@ static void timekeeping_check_update(struct timekeeper *tk, u64 offset) } } -static inline u64 timekeeping_get_delta(struct tk_read_base *tkr) +static inline u64 timekeeping_get_delta(const struct tk_read_base *tkr) { struct timekeeper *tk = &tk_core.timekeeper; u64 now, last, mask, max, delta; @@ -247,7 +255,7 @@ static inline u64 timekeeping_get_delta(struct tk_read_base *tkr) static inline void timekeeping_check_update(struct timekeeper *tk, u64 offset) { } -static inline u64 timekeeping_get_delta(struct tk_read_base *tkr) +static inline u64 timekeeping_get_delta(const struct tk_read_base *tkr) { u64 cycle_now, delta; @@ -344,7 +352,7 @@ u32 (*arch_gettimeoffset)(void) = default_arch_gettimeoffset; static inline u32 arch_gettimeoffset(void) { return 0; } #endif -static inline u64 timekeeping_delta_to_ns(struct tk_read_base *tkr, u64 delta) +static inline u64 timekeeping_delta_to_ns(const struct tk_read_base *tkr, u64 delta) { u64 nsec; @@ -355,7 +363,7 @@ static inline u64 timekeeping_delta_to_ns(struct tk_read_base *tkr, u64 delta) return nsec + arch_gettimeoffset(); } -static inline u64 timekeeping_get_ns(struct tk_read_base *tkr) +static inline u64 timekeeping_get_ns(const struct tk_read_base *tkr) { u64 delta; @@ -363,7 +371,7 @@ static inline u64 timekeeping_get_ns(struct tk_read_base *tkr) return timekeeping_delta_to_ns(tkr, delta); } -static inline u64 timekeeping_cycles_to_ns(struct tk_read_base *tkr, u64 cycles) +static inline u64 timekeeping_cycles_to_ns(const struct tk_read_base *tkr, u64 cycles) { u64 delta; @@ -386,7 +394,8 @@ static inline u64 timekeeping_cycles_to_ns(struct tk_read_base *tkr, u64 cycles) * slightly wrong timestamp (a few nanoseconds). See * @ktime_get_mono_fast_ns. */ -static void update_fast_timekeeper(struct tk_read_base *tkr, struct tk_fast *tkf) +static void update_fast_timekeeper(const struct tk_read_base *tkr, + struct tk_fast *tkf) { struct tk_read_base *base = tkf->base; @@ -541,10 +550,10 @@ EXPORT_SYMBOL_GPL(ktime_get_real_fast_ns); * number of cycles every time until timekeeping is resumed at which time the * proper readout base for the fast timekeeper will be restored automatically. */ -static void halt_fast_timekeeper(struct timekeeper *tk) +static void halt_fast_timekeeper(const struct timekeeper *tk) { static struct tk_read_base tkr_dummy; - struct tk_read_base *tkr = &tk->tkr_mono; + const struct tk_read_base *tkr = &tk->tkr_mono; memcpy(&tkr_dummy, tkr, sizeof(tkr_dummy)); cycles_at_suspend = tk_clock_read(tkr); @@ -1269,7 +1278,7 @@ EXPORT_SYMBOL(do_settimeofday64); * * Adds or subtracts an offset value from the current time. */ -static int timekeeping_inject_offset(struct timespec64 *ts) +static int timekeeping_inject_offset(const struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; unsigned long flags; @@ -1510,8 +1519,20 @@ void __weak read_boot_clock64(struct timespec64 *ts) ts->tv_nsec = 0; } -/* Flag for if timekeeping_resume() has injected sleeptime */ -static bool sleeptime_injected; +/* + * Flag reflecting whether timekeeping_resume() has injected sleeptime. + * + * The flag starts of false and is only set when a suspend reaches + * timekeeping_suspend(), timekeeping_resume() sets it to false when the + * timekeeper clocksource is not stopping across suspend and has been + * used to update sleep time. If the timekeeper clocksource has stopped + * then the flag stays true and is used by the RTC resume code to decide + * whether sleeptime must be injected and if so the flag gets false then. + * + * If a suspend fails before reaching timekeeping_resume() then the flag + * stays false and prevents erroneous sleeptime injection. + */ +static bool suspend_timing_needed; /* Flag for if there is a persistent clock on this platform */ static bool persistent_clock_exists; @@ -1577,7 +1598,7 @@ static struct timespec64 timekeeping_suspend_time; * adds the sleep offset to the timekeeping variables. */ static void __timekeeping_inject_sleeptime(struct timekeeper *tk, - struct timespec64 *delta) + const struct timespec64 *delta) { if (!timespec64_valid_strict(delta)) { printk_deferred(KERN_WARNING @@ -1610,7 +1631,7 @@ static void __timekeeping_inject_sleeptime(struct timekeeper *tk, */ bool timekeeping_rtc_skipresume(void) { - return sleeptime_injected; + return !suspend_timing_needed; } /** @@ -1638,7 +1659,7 @@ bool timekeeping_rtc_skipsuspend(void) * This function should only be called by rtc_resume(), and allows * a suspend offset to be injected into the timekeeping values. */ -void timekeeping_inject_sleeptime64(struct timespec64 *delta) +void timekeeping_inject_sleeptime64(const struct timespec64 *delta) { struct timekeeper *tk = &tk_core.timekeeper; unsigned long flags; @@ -1646,6 +1667,8 @@ void timekeeping_inject_sleeptime64(struct timespec64 *delta) raw_spin_lock_irqsave(&timekeeper_lock, flags); write_seqcount_begin(&tk_core.seq); + suspend_timing_needed = false; + timekeeping_forward_now(tk); __timekeeping_inject_sleeptime(tk, delta); @@ -1669,9 +1692,9 @@ void timekeeping_resume(void) struct clocksource *clock = tk->tkr_mono.clock; unsigned long flags; struct timespec64 ts_new, ts_delta; - u64 cycle_now; + u64 cycle_now, nsec; + bool inject_sleeptime = false; - sleeptime_injected = false; read_persistent_clock64(&ts_new); clockevents_resume(); @@ -1693,22 +1716,19 @@ void timekeeping_resume(void) * usable source. The rtc part is handled separately in rtc core code. */ cycle_now = tk_clock_read(&tk->tkr_mono); - if ((clock->flags & CLOCK_SOURCE_SUSPEND_NONSTOP) && - cycle_now > tk->tkr_mono.cycle_last) { - u64 nsec, cyc_delta; - - cyc_delta = clocksource_delta(cycle_now, tk->tkr_mono.cycle_last, - tk->tkr_mono.mask); - nsec = mul_u64_u32_shr(cyc_delta, clock->mult, clock->shift); + nsec = clocksource_stop_suspend_timing(clock, cycle_now); + if (nsec > 0) { ts_delta = ns_to_timespec64(nsec); - sleeptime_injected = true; + inject_sleeptime = true; } else if (timespec64_compare(&ts_new, &timekeeping_suspend_time) > 0) { ts_delta = timespec64_sub(ts_new, timekeeping_suspend_time); - sleeptime_injected = true; + inject_sleeptime = true; } - if (sleeptime_injected) + if (inject_sleeptime) { + suspend_timing_needed = false; __timekeeping_inject_sleeptime(tk, &ts_delta); + } /* Re-base the last cycle value */ tk->tkr_mono.cycle_last = cycle_now; @@ -1732,6 +1752,8 @@ int timekeeping_suspend(void) unsigned long flags; struct timespec64 delta, delta_delta; static struct timespec64 old_delta; + struct clocksource *curr_clock; + u64 cycle_now; read_persistent_clock64(&timekeeping_suspend_time); @@ -1743,11 +1765,22 @@ int timekeeping_suspend(void) if (timekeeping_suspend_time.tv_sec || timekeeping_suspend_time.tv_nsec) persistent_clock_exists = true; + suspend_timing_needed = true; + raw_spin_lock_irqsave(&timekeeper_lock, flags); write_seqcount_begin(&tk_core.seq); timekeeping_forward_now(tk); timekeeping_suspended = 1; + /* + * Since we've called forward_now, cycle_last stores the value + * just read from the current clocksource. Save this to potentially + * use in suspend timing. + */ + curr_clock = tk->tkr_mono.clock; + cycle_now = tk->tkr_mono.cycle_last; + clocksource_start_suspend_timing(curr_clock, cycle_now); + if (persistent_clock_exists) { /* * To avoid drift caused by repeated suspend/resumes, @@ -2021,11 +2054,11 @@ static u64 logarithmic_accumulation(struct timekeeper *tk, u64 offset, return offset; } -/** - * update_wall_time - Uses the current clocksource to increment the wall time - * +/* + * timekeeping_advance - Updates the timekeeper to the current time and + * current NTP tick length */ -void update_wall_time(void) +static void timekeeping_advance(enum timekeeping_adv_mode mode) { struct timekeeper *real_tk = &tk_core.timekeeper; struct timekeeper *tk = &shadow_timekeeper; @@ -2042,14 +2075,17 @@ void update_wall_time(void) #ifdef CONFIG_ARCH_USES_GETTIMEOFFSET offset = real_tk->cycle_interval; + + if (mode != TK_ADV_TICK) + goto out; #else offset = clocksource_delta(tk_clock_read(&tk->tkr_mono), tk->tkr_mono.cycle_last, tk->tkr_mono.mask); -#endif /* Check if there's really nothing to do */ - if (offset < real_tk->cycle_interval) + if (offset < real_tk->cycle_interval && mode == TK_ADV_TICK) goto out; +#endif /* Do some additional sanity checking */ timekeeping_check_update(tk, offset); @@ -2106,6 +2142,15 @@ out: } /** + * update_wall_time - Uses the current clocksource to increment the wall time + * + */ +void update_wall_time(void) +{ + timekeeping_advance(TK_ADV_TICK); +} + +/** * getboottime64 - Return the real time of system boot. * @ts: pointer to the timespec64 to be set * @@ -2220,7 +2265,7 @@ ktime_t ktime_get_update_offsets_now(unsigned int *cwsseq, ktime_t *offs_real, /** * timekeeping_validate_timex - Ensures the timex is ok for use in do_adjtimex */ -static int timekeeping_validate_timex(struct timex *txc) +static int timekeeping_validate_timex(const struct timex *txc) { if (txc->modes & ADJ_ADJTIME) { /* singleshot must not be used with any other mode bits */ @@ -2310,7 +2355,7 @@ int do_adjtimex(struct timex *txc) return ret; } - getnstimeofday64(&ts); + ktime_get_real_ts64(&ts); raw_spin_lock_irqsave(&timekeeper_lock, flags); write_seqcount_begin(&tk_core.seq); @@ -2327,6 +2372,10 @@ int do_adjtimex(struct timex *txc) write_seqcount_end(&tk_core.seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); + /* Update the multiplier immediately if frequency was set directly */ + if (txc->modes & (ADJ_FREQUENCY | ADJ_TICK)) + timekeeping_advance(TK_ADV_FREQ); + if (tai != orig_tai) clock_was_set(); diff --git a/kernel/time/timekeeping_debug.c b/kernel/time/timekeeping_debug.c index 0754cadfa9e6..238e4be60229 100644 --- a/kernel/time/timekeeping_debug.c +++ b/kernel/time/timekeeping_debug.c @@ -70,7 +70,7 @@ static int __init tk_debug_sleep_time_init(void) } late_initcall(tk_debug_sleep_time_init); -void tk_debug_account_sleep_time(struct timespec64 *t) +void tk_debug_account_sleep_time(const struct timespec64 *t) { /* Cap bin index so we don't overflow the array */ int bin = min(fls(t->tv_sec), NUM_BINS-1); diff --git a/kernel/time/timekeeping_internal.h b/kernel/time/timekeeping_internal.h index cf5c0828ee31..bcbb52db2256 100644 --- a/kernel/time/timekeeping_internal.h +++ b/kernel/time/timekeeping_internal.h @@ -8,7 +8,7 @@ #include <linux/time.h> #ifdef CONFIG_DEBUG_FS -extern void tk_debug_account_sleep_time(struct timespec64 *t); +extern void tk_debug_account_sleep_time(const struct timespec64 *t); #else #define tk_debug_account_sleep_time(x) #endif diff --git a/kernel/time/timer.c b/kernel/time/timer.c index cc2d23e6ff61..fa49cd753dea 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -581,7 +581,7 @@ trigger_dyntick_cpu(struct timer_base *base, struct timer_list *timer) * wheel: */ base->next_expiry = timer->expires; - wake_up_nohz_cpu(base->cpu); + wake_up_nohz_cpu(base->cpu); } static void @@ -1657,6 +1657,22 @@ static inline void __run_timers(struct timer_base *base) raw_spin_lock_irq(&base->lock); + /* + * timer_base::must_forward_clk must be cleared before running + * timers so that any timer functions that call mod_timer() will + * not try to forward the base. Idle tracking / clock forwarding + * logic is only used with BASE_STD timers. + * + * The must_forward_clk flag is cleared unconditionally also for + * the deferrable base. The deferrable base is not affected by idle + * tracking and never forwarded, so clearing the flag is a NOOP. + * + * The fact that the deferrable base is never forwarded can cause + * large variations in granularity for deferrable timers, but they + * can be deferred for long periods due to idle anyway. + */ + base->must_forward_clk = false; + while (time_after_eq(jiffies, base->clk)) { levels = collect_expired_timers(base, heads); @@ -1676,19 +1692,6 @@ static __latent_entropy void run_timer_softirq(struct softirq_action *h) { struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]); - /* - * must_forward_clk must be cleared before running timers so that any - * timer functions that call mod_timer will not try to forward the - * base. idle trcking / clock forwarding logic is only used with - * BASE_STD timers. - * - * The deferrable base does not do idle tracking at all, so we do - * not forward it. This can result in very large variations in - * granularity for deferrable timers, but they can be deferred for - * long periods due to idle. - */ - base->must_forward_clk = false; - __run_timers(base); if (IS_ENABLED(CONFIG_NO_HZ_COMMON)) __run_timers(this_cpu_ptr(&timer_bases[BASE_DEF])); diff --git a/kernel/torture.c b/kernel/torture.c index 3de1efbecd6a..1ac24a826589 100644 --- a/kernel/torture.c +++ b/kernel/torture.c @@ -20,6 +20,9 @@ * Author: Paul E. McKenney <paulmck@us.ibm.com> * Based on kernel/rcu/torture.c. */ + +#define pr_fmt(fmt) fmt + #include <linux/types.h> #include <linux/kernel.h> #include <linux/init.h> @@ -53,7 +56,7 @@ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Paul E. McKenney <paulmck@us.ibm.com>"); static char *torture_type; -static bool verbose; +static int verbose; /* Mediate rmmod and system shutdown. Concurrent rmmod & shutdown illegal! */ #define FULLSTOP_DONTSTOP 0 /* Normal operation. */ @@ -98,7 +101,7 @@ bool torture_offline(int cpu, long *n_offl_attempts, long *n_offl_successes, if (!cpu_online(cpu) || !cpu_is_hotpluggable(cpu)) return false; - if (verbose) + if (verbose > 1) pr_alert("%s" TORTURE_FLAG "torture_onoff task: offlining %d\n", torture_type, cpu); @@ -111,7 +114,7 @@ bool torture_offline(int cpu, long *n_offl_attempts, long *n_offl_successes, "torture_onoff task: offline %d failed: errno %d\n", torture_type, cpu, ret); } else { - if (verbose) + if (verbose > 1) pr_alert("%s" TORTURE_FLAG "torture_onoff task: offlined %d\n", torture_type, cpu); @@ -147,7 +150,7 @@ bool torture_online(int cpu, long *n_onl_attempts, long *n_onl_successes, if (cpu_online(cpu) || !cpu_is_hotpluggable(cpu)) return false; - if (verbose) + if (verbose > 1) pr_alert("%s" TORTURE_FLAG "torture_onoff task: onlining %d\n", torture_type, cpu); @@ -160,7 +163,7 @@ bool torture_online(int cpu, long *n_onl_attempts, long *n_onl_successes, "torture_onoff task: online %d failed: errno %d\n", torture_type, cpu, ret); } else { - if (verbose) + if (verbose > 1) pr_alert("%s" TORTURE_FLAG "torture_onoff task: onlined %d\n", torture_type, cpu); @@ -647,7 +650,7 @@ static void torture_stutter_cleanup(void) * The runnable parameter points to a flag that controls whether or not * the test is currently runnable. If there is no such flag, pass in NULL. */ -bool torture_init_begin(char *ttype, bool v) +bool torture_init_begin(char *ttype, int v) { mutex_lock(&fullstop_mutex); if (torture_type != NULL) { diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 6b71860f3998..e9d99463e5df 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -1228,16 +1228,11 @@ kprobe_perf_func(struct trace_kprobe *tk, struct pt_regs *regs) /* * We need to check and see if we modified the pc of the - * pt_regs, and if so clear the kprobe and return 1 so that we - * don't do the single stepping. - * The ftrace kprobe handler leaves it up to us to re-enable - * preemption here before returning if we've modified the ip. + * pt_regs, and if so return 1 so that we don't do the + * single stepping. */ - if (orig_ip != instruction_pointer(regs)) { - reset_current_kprobe(); - preempt_enable_no_resched(); + if (orig_ip != instruction_pointer(regs)) return 1; - } if (!ret) return 0; } diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 576d18045811..5470dce212c0 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -18,18 +18,14 @@ #include <linux/init.h> #include <linux/module.h> #include <linux/sysctl.h> -#include <linux/smpboot.h> -#include <linux/sched/rt.h> -#include <uapi/linux/sched/types.h> #include <linux/tick.h> -#include <linux/workqueue.h> #include <linux/sched/clock.h> #include <linux/sched/debug.h> #include <linux/sched/isolation.h> +#include <linux/stop_machine.h> #include <asm/irq_regs.h> #include <linux/kvm_para.h> -#include <linux/kthread.h> static DEFINE_MUTEX(watchdog_mutex); @@ -169,11 +165,10 @@ static void lockup_detector_update_enable(void) unsigned int __read_mostly softlockup_panic = CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE; -static bool softlockup_threads_initialized __read_mostly; +static bool softlockup_initialized __read_mostly; static u64 __read_mostly sample_period; static DEFINE_PER_CPU(unsigned long, watchdog_touch_ts); -static DEFINE_PER_CPU(struct task_struct *, softlockup_watchdog); static DEFINE_PER_CPU(struct hrtimer, watchdog_hrtimer); static DEFINE_PER_CPU(bool, softlockup_touch_sync); static DEFINE_PER_CPU(bool, soft_watchdog_warn); @@ -335,6 +330,27 @@ static void watchdog_interrupt_count(void) __this_cpu_inc(hrtimer_interrupts); } +static DEFINE_PER_CPU(struct completion, softlockup_completion); +static DEFINE_PER_CPU(struct cpu_stop_work, softlockup_stop_work); + +/* + * The watchdog thread function - touches the timestamp. + * + * It only runs once every sample_period seconds (4 seconds by + * default) to reset the softlockup timestamp. If this gets delayed + * for more than 2*watchdog_thresh seconds then the debug-printout + * triggers in watchdog_timer_fn(). + */ +static int softlockup_fn(void *data) +{ + __this_cpu_write(soft_lockup_hrtimer_cnt, + __this_cpu_read(hrtimer_interrupts)); + __touch_watchdog(); + complete(this_cpu_ptr(&softlockup_completion)); + + return 0; +} + /* watchdog kicker functions */ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) { @@ -350,7 +366,12 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) watchdog_interrupt_count(); /* kick the softlockup detector */ - wake_up_process(__this_cpu_read(softlockup_watchdog)); + if (completion_done(this_cpu_ptr(&softlockup_completion))) { + reinit_completion(this_cpu_ptr(&softlockup_completion)); + stop_one_cpu_nowait(smp_processor_id(), + softlockup_fn, NULL, + this_cpu_ptr(&softlockup_stop_work)); + } /* .. and repeat */ hrtimer_forward_now(hrtimer, ns_to_ktime(sample_period)); @@ -448,16 +469,15 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) return HRTIMER_RESTART; } -static void watchdog_set_prio(unsigned int policy, unsigned int prio) -{ - struct sched_param param = { .sched_priority = prio }; - - sched_setscheduler(current, policy, ¶m); -} - static void watchdog_enable(unsigned int cpu) { struct hrtimer *hrtimer = this_cpu_ptr(&watchdog_hrtimer); + struct completion *done = this_cpu_ptr(&softlockup_completion); + + WARN_ON_ONCE(cpu != smp_processor_id()); + + init_completion(done); + complete(done); /* * Start the timer first to prevent the NMI watchdog triggering @@ -473,15 +493,14 @@ static void watchdog_enable(unsigned int cpu) /* Enable the perf event */ if (watchdog_enabled & NMI_WATCHDOG_ENABLED) watchdog_nmi_enable(cpu); - - watchdog_set_prio(SCHED_FIFO, MAX_RT_PRIO - 1); } static void watchdog_disable(unsigned int cpu) { struct hrtimer *hrtimer = this_cpu_ptr(&watchdog_hrtimer); - watchdog_set_prio(SCHED_NORMAL, 0); + WARN_ON_ONCE(cpu != smp_processor_id()); + /* * Disable the perf event first. That prevents that a large delay * between disabling the timer and disabling the perf event causes @@ -489,79 +508,66 @@ static void watchdog_disable(unsigned int cpu) */ watchdog_nmi_disable(cpu); hrtimer_cancel(hrtimer); + wait_for_completion(this_cpu_ptr(&softlockup_completion)); } -static void watchdog_cleanup(unsigned int cpu, bool online) +static int softlockup_stop_fn(void *data) { - watchdog_disable(cpu); + watchdog_disable(smp_processor_id()); + return 0; } -static int watchdog_should_run(unsigned int cpu) +static void softlockup_stop_all(void) { - return __this_cpu_read(hrtimer_interrupts) != - __this_cpu_read(soft_lockup_hrtimer_cnt); + int cpu; + + if (!softlockup_initialized) + return; + + for_each_cpu(cpu, &watchdog_allowed_mask) + smp_call_on_cpu(cpu, softlockup_stop_fn, NULL, false); + + cpumask_clear(&watchdog_allowed_mask); } -/* - * The watchdog thread function - touches the timestamp. - * - * It only runs once every sample_period seconds (4 seconds by - * default) to reset the softlockup timestamp. If this gets delayed - * for more than 2*watchdog_thresh seconds then the debug-printout - * triggers in watchdog_timer_fn(). - */ -static void watchdog(unsigned int cpu) +static int softlockup_start_fn(void *data) { - __this_cpu_write(soft_lockup_hrtimer_cnt, - __this_cpu_read(hrtimer_interrupts)); - __touch_watchdog(); + watchdog_enable(smp_processor_id()); + return 0; } -static struct smp_hotplug_thread watchdog_threads = { - .store = &softlockup_watchdog, - .thread_should_run = watchdog_should_run, - .thread_fn = watchdog, - .thread_comm = "watchdog/%u", - .setup = watchdog_enable, - .cleanup = watchdog_cleanup, - .park = watchdog_disable, - .unpark = watchdog_enable, -}; - -static void softlockup_update_smpboot_threads(void) +static void softlockup_start_all(void) { - lockdep_assert_held(&watchdog_mutex); - - if (!softlockup_threads_initialized) - return; + int cpu; - smpboot_update_cpumask_percpu_thread(&watchdog_threads, - &watchdog_allowed_mask); + cpumask_copy(&watchdog_allowed_mask, &watchdog_cpumask); + for_each_cpu(cpu, &watchdog_allowed_mask) + smp_call_on_cpu(cpu, softlockup_start_fn, NULL, false); } -/* Temporarily park all watchdog threads */ -static void softlockup_park_all_threads(void) +int lockup_detector_online_cpu(unsigned int cpu) { - cpumask_clear(&watchdog_allowed_mask); - softlockup_update_smpboot_threads(); + watchdog_enable(cpu); + return 0; } -/* Unpark enabled threads */ -static void softlockup_unpark_threads(void) +int lockup_detector_offline_cpu(unsigned int cpu) { - cpumask_copy(&watchdog_allowed_mask, &watchdog_cpumask); - softlockup_update_smpboot_threads(); + watchdog_disable(cpu); + return 0; } static void lockup_detector_reconfigure(void) { cpus_read_lock(); watchdog_nmi_stop(); - softlockup_park_all_threads(); + + softlockup_stop_all(); set_sample_period(); lockup_detector_update_enable(); if (watchdog_enabled && watchdog_thresh) - softlockup_unpark_threads(); + softlockup_start_all(); + watchdog_nmi_start(); cpus_read_unlock(); /* @@ -580,8 +586,6 @@ static void lockup_detector_reconfigure(void) */ static __init void lockup_detector_setup(void) { - int ret; - /* * If sysctl is off and watchdog got disabled on the command line, * nothing to do here. @@ -592,24 +596,13 @@ static __init void lockup_detector_setup(void) !(watchdog_enabled && watchdog_thresh)) return; - ret = smpboot_register_percpu_thread_cpumask(&watchdog_threads, - &watchdog_allowed_mask); - if (ret) { - pr_err("Failed to initialize soft lockup detector threads\n"); - return; - } - mutex_lock(&watchdog_mutex); - softlockup_threads_initialized = true; lockup_detector_reconfigure(); + softlockup_initialized = true; mutex_unlock(&watchdog_mutex); } #else /* CONFIG_SOFTLOCKUP_DETECTOR */ -static inline int watchdog_park_threads(void) { return 0; } -static inline void watchdog_unpark_threads(void) { } -static inline int watchdog_enable_all_cpus(void) { return 0; } -static inline void watchdog_disable_all_cpus(void) { } static void lockup_detector_reconfigure(void) { cpus_read_lock(); diff --git a/kernel/watchdog_hld.c b/kernel/watchdog_hld.c index e449a23e9d59..1f7020d65d0a 100644 --- a/kernel/watchdog_hld.c +++ b/kernel/watchdog_hld.c @@ -175,8 +175,8 @@ static int hardlockup_detector_event_create(void) evt = perf_event_create_kernel_counter(wd_attr, cpu, NULL, watchdog_overflow_callback, NULL); if (IS_ERR(evt)) { - pr_info("Perf event create on CPU %d failed with %ld\n", cpu, - PTR_ERR(evt)); + pr_debug("Perf event create on CPU %d failed with %ld\n", cpu, + PTR_ERR(evt)); return PTR_ERR(evt); } this_cpu_write(watchdog_ev, evt); diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 8838d1158d19..0b066b3c9284 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -1718,7 +1718,7 @@ config KPROBES_SANITY_TEST default n help This option provides for testing basic kprobes functionality on - boot. A sample kprobe, jprobe and kretprobe are inserted and + boot. Samples of kprobe and kretprobe are inserted and verified for functionality. Say N if you are unsure. diff --git a/lib/Kconfig.ubsan b/lib/Kconfig.ubsan index 19d42ea75ec2..98fa559ebd80 100644 --- a/lib/Kconfig.ubsan +++ b/lib/Kconfig.ubsan @@ -1,9 +1,6 @@ config ARCH_HAS_UBSAN_SANITIZE_ALL bool -config ARCH_WANTS_UBSAN_NO_NULL - def_bool n - config UBSAN bool "Undefined behaviour sanity checker" help @@ -39,14 +36,6 @@ config UBSAN_ALIGNMENT Enabling this option on architectures that support unaligned accesses may produce a lot of false positives. -config UBSAN_NULL - bool "Enable checking of null pointers" - depends on UBSAN - default y if !ARCH_WANTS_UBSAN_NO_NULL - help - This option enables detection of memory accesses via a - null pointer. - config TEST_UBSAN tristate "Module for testing for undefined behavior detection" depends on m && UBSAN diff --git a/lib/atomic64.c b/lib/atomic64.c index 53c2d5edc826..1d91e31eceec 100644 --- a/lib/atomic64.c +++ b/lib/atomic64.c @@ -178,18 +178,18 @@ long long atomic64_xchg(atomic64_t *v, long long new) } EXPORT_SYMBOL(atomic64_xchg); -int atomic64_add_unless(atomic64_t *v, long long a, long long u) +long long atomic64_fetch_add_unless(atomic64_t *v, long long a, long long u) { unsigned long flags; raw_spinlock_t *lock = lock_addr(v); - int ret = 0; + long long val; raw_spin_lock_irqsave(lock, flags); - if (v->counter != u) { + val = v->counter; + if (val != u) v->counter += a; - ret = 1; - } raw_spin_unlock_irqrestore(lock, flags); - return ret; + + return val; } -EXPORT_SYMBOL(atomic64_add_unless); +EXPORT_SYMBOL(atomic64_fetch_add_unless); diff --git a/lib/debugobjects.c b/lib/debugobjects.c index 994be4805cec..70935ed91125 100644 --- a/lib/debugobjects.c +++ b/lib/debugobjects.c @@ -360,9 +360,12 @@ static void debug_object_is_on_stack(void *addr, int onstack) limit++; if (is_on_stack) - pr_warn("object is on stack, but not annotated\n"); + pr_warn("object %p is on stack %p, but NOT annotated.\n", addr, + task_stack_page(current)); else - pr_warn("object is not on stack, but annotated\n"); + pr_warn("object %p is NOT on stack %p, but annotated.\n", addr, + task_stack_page(current)); + WARN_ON(1); } @@ -1185,8 +1188,7 @@ void __init debug_objects_mem_init(void) if (!obj_cache || debug_objects_replace_static_objects()) { debug_objects_enabled = 0; - if (obj_cache) - kmem_cache_destroy(obj_cache); + kmem_cache_destroy(obj_cache); pr_warn("out of memory.\n"); } else debug_objects_selftest(); diff --git a/lib/ioremap.c b/lib/ioremap.c index 54e5bbaa3200..517f5853ffed 100644 --- a/lib/ioremap.c +++ b/lib/ioremap.c @@ -92,7 +92,7 @@ static inline int ioremap_pmd_range(pud_t *pud, unsigned long addr, if (ioremap_pmd_enabled() && ((next - addr) == PMD_SIZE) && IS_ALIGNED(phys_addr + addr, PMD_SIZE) && - pmd_free_pte_page(pmd)) { + pmd_free_pte_page(pmd, addr)) { if (pmd_set_huge(pmd, phys_addr + addr, prot)) continue; } @@ -119,7 +119,7 @@ static inline int ioremap_pud_range(p4d_t *p4d, unsigned long addr, if (ioremap_pud_enabled() && ((next - addr) == PUD_SIZE) && IS_ALIGNED(phys_addr + addr, PUD_SIZE) && - pud_free_pmd_page(pud)) { + pud_free_pmd_page(pud, addr)) { if (pud_set_huge(pud, phys_addr + addr, prot)) continue; } diff --git a/lib/refcount.c b/lib/refcount.c index d3b81cefce91..ebcf8cd49e05 100644 --- a/lib/refcount.c +++ b/lib/refcount.c @@ -35,13 +35,13 @@ * */ +#include <linux/mutex.h> #include <linux/refcount.h> +#include <linux/spinlock.h> #include <linux/bug.h> -#ifdef CONFIG_REFCOUNT_FULL - /** - * refcount_add_not_zero - add a value to a refcount unless it is 0 + * refcount_add_not_zero_checked - add a value to a refcount unless it is 0 * @i: the value to add to the refcount * @r: the refcount * @@ -58,7 +58,7 @@ * * Return: false if the passed refcount is 0, true otherwise */ -bool refcount_add_not_zero(unsigned int i, refcount_t *r) +bool refcount_add_not_zero_checked(unsigned int i, refcount_t *r) { unsigned int new, val = atomic_read(&r->refs); @@ -79,10 +79,10 @@ bool refcount_add_not_zero(unsigned int i, refcount_t *r) return true; } -EXPORT_SYMBOL(refcount_add_not_zero); +EXPORT_SYMBOL(refcount_add_not_zero_checked); /** - * refcount_add - add a value to a refcount + * refcount_add_checked - add a value to a refcount * @i: the value to add to the refcount * @r: the refcount * @@ -97,14 +97,14 @@ EXPORT_SYMBOL(refcount_add_not_zero); * cases, refcount_inc(), or one of its variants, should instead be used to * increment a reference count. */ -void refcount_add(unsigned int i, refcount_t *r) +void refcount_add_checked(unsigned int i, refcount_t *r) { - WARN_ONCE(!refcount_add_not_zero(i, r), "refcount_t: addition on 0; use-after-free.\n"); + WARN_ONCE(!refcount_add_not_zero_checked(i, r), "refcount_t: addition on 0; use-after-free.\n"); } -EXPORT_SYMBOL(refcount_add); +EXPORT_SYMBOL(refcount_add_checked); /** - * refcount_inc_not_zero - increment a refcount unless it is 0 + * refcount_inc_not_zero_checked - increment a refcount unless it is 0 * @r: the refcount to increment * * Similar to atomic_inc_not_zero(), but will saturate at UINT_MAX and WARN. @@ -115,7 +115,7 @@ EXPORT_SYMBOL(refcount_add); * * Return: true if the increment was successful, false otherwise */ -bool refcount_inc_not_zero(refcount_t *r) +bool refcount_inc_not_zero_checked(refcount_t *r) { unsigned int new, val = atomic_read(&r->refs); @@ -134,10 +134,10 @@ bool refcount_inc_not_zero(refcount_t *r) return true; } -EXPORT_SYMBOL(refcount_inc_not_zero); +EXPORT_SYMBOL(refcount_inc_not_zero_checked); /** - * refcount_inc - increment a refcount + * refcount_inc_checked - increment a refcount * @r: the refcount to increment * * Similar to atomic_inc(), but will saturate at UINT_MAX and WARN. @@ -148,14 +148,14 @@ EXPORT_SYMBOL(refcount_inc_not_zero); * Will WARN if the refcount is 0, as this represents a possible use-after-free * condition. */ -void refcount_inc(refcount_t *r) +void refcount_inc_checked(refcount_t *r) { - WARN_ONCE(!refcount_inc_not_zero(r), "refcount_t: increment on 0; use-after-free.\n"); + WARN_ONCE(!refcount_inc_not_zero_checked(r), "refcount_t: increment on 0; use-after-free.\n"); } -EXPORT_SYMBOL(refcount_inc); +EXPORT_SYMBOL(refcount_inc_checked); /** - * refcount_sub_and_test - subtract from a refcount and test if it is 0 + * refcount_sub_and_test_checked - subtract from a refcount and test if it is 0 * @i: amount to subtract from the refcount * @r: the refcount * @@ -174,7 +174,7 @@ EXPORT_SYMBOL(refcount_inc); * * Return: true if the resulting refcount is 0, false otherwise */ -bool refcount_sub_and_test(unsigned int i, refcount_t *r) +bool refcount_sub_and_test_checked(unsigned int i, refcount_t *r) { unsigned int new, val = atomic_read(&r->refs); @@ -192,10 +192,10 @@ bool refcount_sub_and_test(unsigned int i, refcount_t *r) return !new; } -EXPORT_SYMBOL(refcount_sub_and_test); +EXPORT_SYMBOL(refcount_sub_and_test_checked); /** - * refcount_dec_and_test - decrement a refcount and test if it is 0 + * refcount_dec_and_test_checked - decrement a refcount and test if it is 0 * @r: the refcount * * Similar to atomic_dec_and_test(), it will WARN on underflow and fail to @@ -207,14 +207,14 @@ EXPORT_SYMBOL(refcount_sub_and_test); * * Return: true if the resulting refcount is 0, false otherwise */ -bool refcount_dec_and_test(refcount_t *r) +bool refcount_dec_and_test_checked(refcount_t *r) { - return refcount_sub_and_test(1, r); + return refcount_sub_and_test_checked(1, r); } -EXPORT_SYMBOL(refcount_dec_and_test); +EXPORT_SYMBOL(refcount_dec_and_test_checked); /** - * refcount_dec - decrement a refcount + * refcount_dec_checked - decrement a refcount * @r: the refcount * * Similar to atomic_dec(), it will WARN on underflow and fail to decrement @@ -223,12 +223,11 @@ EXPORT_SYMBOL(refcount_dec_and_test); * Provides release memory ordering, such that prior loads and stores are done * before. */ -void refcount_dec(refcount_t *r) +void refcount_dec_checked(refcount_t *r) { - WARN_ONCE(refcount_dec_and_test(r), "refcount_t: decrement hit 0; leaking memory.\n"); + WARN_ONCE(refcount_dec_and_test_checked(r), "refcount_t: decrement hit 0; leaking memory.\n"); } -EXPORT_SYMBOL(refcount_dec); -#endif /* CONFIG_REFCOUNT_FULL */ +EXPORT_SYMBOL(refcount_dec_checked); /** * refcount_dec_if_one - decrement a refcount if it is 1 diff --git a/mm/init-mm.c b/mm/init-mm.c index f0179c9c04c2..a787a319211e 100644 --- a/mm/init-mm.c +++ b/mm/init-mm.c @@ -15,6 +15,16 @@ #define INIT_MM_CONTEXT(name) #endif +/* + * For dynamically allocated mm_structs, there is a dynamically sized cpumask + * at the end of the structure, the size of which depends on the maximum CPU + * number the system can see. That way we allocate only as much memory for + * mm_cpumask() as needed for the hundreds, or thousands of processes that + * a system typically runs. + * + * Since there is only one init_mm in the entire system, keep it simple + * and size this cpu_bitmask to NR_CPUS. + */ struct mm_struct init_mm = { .mm_rb = RB_ROOT, .pgd = swapper_pg_dir, @@ -25,5 +35,6 @@ struct mm_struct init_mm = { .arg_lock = __SPIN_LOCK_UNLOCKED(init_mm.arg_lock), .mmlist = LIST_HEAD_INIT(init_mm.mmlist), .user_ns = &init_user_ns, + .cpu_bitmap = { [BITS_TO_LONGS(NR_CPUS)] = 0}, INIT_MM_CONTEXT(init_mm) }; diff --git a/mm/memory.c b/mm/memory.c index dab1511294ad..3d0a74ab70f2 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -326,16 +326,20 @@ bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page, int page_ #ifdef CONFIG_HAVE_RCU_TABLE_FREE -/* - * See the comment near struct mmu_table_batch. - */ - static void tlb_remove_table_smp_sync(void *arg) { - /* Simply deliver the interrupt */ + struct mm_struct __maybe_unused *mm = arg; + /* + * On most architectures this does nothing. Simply delivering the + * interrupt is enough to prevent races with software page table + * walking like that done in get_user_pages_fast. + * + * See the comment near struct mmu_table_batch. + */ + tlb_flush_remove_tables_local(mm); } -static void tlb_remove_table_one(void *table) +static void tlb_remove_table_one(void *table, struct mmu_gather *tlb) { /* * This isn't an RCU grace period and hence the page-tables cannot be @@ -344,7 +348,7 @@ static void tlb_remove_table_one(void *table) * It is however sufficient for software page-table walkers that rely on * IRQ disabling. See the comment near struct mmu_table_batch. */ - smp_call_function(tlb_remove_table_smp_sync, NULL, 1); + smp_call_function(tlb_remove_table_smp_sync, tlb->mm, 1); __tlb_remove_table(table); } @@ -365,6 +369,8 @@ void tlb_table_flush(struct mmu_gather *tlb) { struct mmu_table_batch **batch = &tlb->batch; + tlb_flush_remove_tables(tlb->mm); + if (*batch) { call_rcu_sched(&(*batch)->rcu, tlb_remove_table_rcu); *batch = NULL; @@ -387,7 +393,7 @@ void tlb_remove_table(struct mmu_gather *tlb, void *table) if (*batch == NULL) { *batch = (struct mmu_table_batch *)__get_free_page(GFP_NOWAIT | __GFP_NOWARN); if (*batch == NULL) { - tlb_remove_table_one(table); + tlb_remove_table_one(table, tlb); return; } (*batch)->nr = 0; @@ -4395,6 +4401,9 @@ int generic_access_phys(struct vm_area_struct *vma, unsigned long addr, return -EINVAL; maddr = ioremap_prot(phys_addr, PAGE_ALIGN(len + offset), prot); + if (!maddr) + return -ENOMEM; + if (write) memcpy_toio(maddr + offset, buf, len); else diff --git a/net/atm/pppoatm.c b/net/atm/pppoatm.c index af8c4b38b746..d84227d75717 100644 --- a/net/atm/pppoatm.c +++ b/net/atm/pppoatm.c @@ -244,7 +244,7 @@ static int pppoatm_may_send(struct pppoatm_vcc *pvcc, int size) * the packet count limit, so... */ if (atm_may_send(pvcc->atmvcc, size) && - atomic_inc_not_zero_hint(&pvcc->inflight, NONE_INFLIGHT)) + atomic_inc_not_zero(&pvcc->inflight)) return 1; /* diff --git a/net/dccp/ccids/ccid2.c b/net/dccp/ccids/ccid2.c index 2b75df469220..842a9c7c73a3 100644 --- a/net/dccp/ccids/ccid2.c +++ b/net/dccp/ccids/ccid2.c @@ -229,14 +229,16 @@ static void ccid2_cwnd_restart(struct sock *sk, const u32 now) struct ccid2_hc_tx_sock *hc = ccid2_hc_tx_sk(sk); u32 cwnd = hc->tx_cwnd, restart_cwnd, iwnd = rfc3390_bytes_to_packets(dccp_sk(sk)->dccps_mss_cache); + s32 delta = now - hc->tx_lsndtime; hc->tx_ssthresh = max(hc->tx_ssthresh, (cwnd >> 1) + (cwnd >> 2)); /* don't reduce cwnd below the initial window (IW) */ restart_cwnd = min(cwnd, iwnd); - cwnd >>= (now - hc->tx_lsndtime) / hc->tx_rto; - hc->tx_cwnd = max(cwnd, restart_cwnd); + while ((delta -= hc->tx_rto) >= 0 && cwnd > restart_cwnd) + cwnd >>= 1; + hc->tx_cwnd = max(cwnd, restart_cwnd); hc->tx_cwnd_stamp = now; hc->tx_cwnd_used = 0; diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 732369c80644..9864bcd3d317 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -639,7 +639,7 @@ static int dsa_slave_set_eee(struct net_device *dev, struct ethtool_eee *e) int ret; /* Port's PHY and MAC both need to be EEE capable */ - if (!dev->phydev) + if (!dev->phydev && !dp->pl) return -ENODEV; if (!ds->ops->set_mac_eee) @@ -659,7 +659,7 @@ static int dsa_slave_get_eee(struct net_device *dev, struct ethtool_eee *e) int ret; /* Port's PHY and MAC both need to be EEE capable */ - if (!dev->phydev) + if (!dev->phydev && !dp->pl) return -ENODEV; if (!ds->ops->get_mac_eee) diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 00e138a44cbb..1cc9650af9fb 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1133,12 +1133,8 @@ route_lookup: max_headroom += 8; mtu -= 8; } - if (skb->protocol == htons(ETH_P_IPV6)) { - if (mtu < IPV6_MIN_MTU) - mtu = IPV6_MIN_MTU; - } else if (mtu < 576) { - mtu = 576; - } + mtu = max(mtu, skb->protocol == htons(ETH_P_IPV6) ? + IPV6_MIN_MTU : IPV4_MIN_MTU); skb_dst_update_pmtu(skb, mtu); if (skb->len - t->tun_hlen - eth_hlen > mtu && !skb_is_gso(skb)) { diff --git a/net/ipv6/route.c b/net/ipv6/route.c index ec18b3ce8b6d..7208c16302f6 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -978,10 +978,6 @@ static void rt6_set_from(struct rt6_info *rt, struct fib6_info *from) rt->rt6i_flags &= ~RTF_EXPIRES; rcu_assign_pointer(rt->from, from); dst_init_metrics(&rt->dst, from->fib6_metrics->metrics, true); - if (from->fib6_metrics != &dst_default_metrics) { - rt->dst._metrics |= DST_METRICS_REFCOUNTED; - refcount_inc(&from->fib6_metrics->refcnt); - } } /* Caller must already hold reference to @ort */ diff --git a/net/llc/llc_core.c b/net/llc/llc_core.c index 89041260784c..260b3dc1b4a2 100644 --- a/net/llc/llc_core.c +++ b/net/llc/llc_core.c @@ -73,8 +73,8 @@ struct llc_sap *llc_sap_find(unsigned char sap_value) rcu_read_lock_bh(); sap = __llc_sap_find(sap_value); - if (sap) - llc_sap_hold(sap); + if (!sap || !llc_sap_hold_safe(sap)) + sap = NULL; rcu_read_unlock_bh(); return sap; } diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 9b27d0cd766d..e6445d8f3f57 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -4226,6 +4226,8 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, } if (req->tp_block_nr) { + unsigned int min_frame_size; + /* Sanity tests and some calculations */ err = -EBUSY; if (unlikely(rb->pg_vec)) @@ -4248,12 +4250,12 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, goto out; if (unlikely(!PAGE_ALIGNED(req->tp_block_size))) goto out; + min_frame_size = po->tp_hdrlen + po->tp_reserve; if (po->tp_version >= TPACKET_V3 && - req->tp_block_size <= - BLK_PLUS_PRIV((u64)req_u->req3.tp_sizeof_priv) + sizeof(struct tpacket3_hdr)) + req->tp_block_size < + BLK_PLUS_PRIV((u64)req_u->req3.tp_sizeof_priv) + min_frame_size) goto out; - if (unlikely(req->tp_frame_size < po->tp_hdrlen + - po->tp_reserve)) + if (unlikely(req->tp_frame_size < min_frame_size)) goto out; if (unlikely(req->tp_frame_size & (TPACKET_ALIGNMENT - 1))) goto out; diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 5fb7d3254d9e..707630ab4713 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -104,9 +104,9 @@ struct rxrpc_net { #define RXRPC_KEEPALIVE_TIME 20 /* NAT keepalive time in seconds */ u8 peer_keepalive_cursor; - ktime_t peer_keepalive_base; - struct hlist_head peer_keepalive[RXRPC_KEEPALIVE_TIME + 1]; - struct hlist_head peer_keepalive_new; + time64_t peer_keepalive_base; + struct list_head peer_keepalive[32]; + struct list_head peer_keepalive_new; struct timer_list peer_keepalive_timer; struct work_struct peer_keepalive_work; }; @@ -295,7 +295,7 @@ struct rxrpc_peer { struct hlist_head error_targets; /* targets for net error distribution */ struct work_struct error_distributor; struct rb_root service_conns; /* Service connections */ - struct hlist_node keepalive_link; /* Link in net->peer_keepalive[] */ + struct list_head keepalive_link; /* Link in net->peer_keepalive[] */ time64_t last_tx_at; /* Last time packet sent here */ seqlock_t service_conn_lock; spinlock_t lock; /* access lock */ diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index f6734d8cb01a..9486293fef5c 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -415,7 +415,7 @@ void rxrpc_incoming_call(struct rxrpc_sock *rx, bool rxrpc_queue_call(struct rxrpc_call *call) { const void *here = __builtin_return_address(0); - int n = __atomic_add_unless(&call->usage, 1, 0); + int n = atomic_fetch_add_unless(&call->usage, 1, 0); if (n == 0) return false; if (rxrpc_queue_work(&call->processor)) diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c index 8229a52c2acd..3fde001fcc39 100644 --- a/net/rxrpc/conn_event.c +++ b/net/rxrpc/conn_event.c @@ -136,7 +136,7 @@ static void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn, } ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, ioc, len); - conn->params.peer->last_tx_at = ktime_get_real(); + conn->params.peer->last_tx_at = ktime_get_seconds(); if (ret < 0) trace_rxrpc_tx_fail(conn->debug_id, serial, ret, rxrpc_tx_fail_call_final_resend); @@ -245,7 +245,7 @@ static int rxrpc_abort_connection(struct rxrpc_connection *conn, return -EAGAIN; } - conn->params.peer->last_tx_at = ktime_get_real(); + conn->params.peer->last_tx_at = ktime_get_seconds(); _leave(" = 0"); return 0; diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c index 4c77a78a252a..77440a356b14 100644 --- a/net/rxrpc/conn_object.c +++ b/net/rxrpc/conn_object.c @@ -266,7 +266,7 @@ void rxrpc_kill_connection(struct rxrpc_connection *conn) bool rxrpc_queue_conn(struct rxrpc_connection *conn) { const void *here = __builtin_return_address(0); - int n = __atomic_add_unless(&conn->usage, 1, 0); + int n = atomic_fetch_add_unless(&conn->usage, 1, 0); if (n == 0) return false; if (rxrpc_queue_work(&conn->processor)) @@ -309,7 +309,7 @@ rxrpc_get_connection_maybe(struct rxrpc_connection *conn) const void *here = __builtin_return_address(0); if (conn) { - int n = __atomic_add_unless(&conn->usage, 1, 0); + int n = atomic_fetch_add_unless(&conn->usage, 1, 0); if (n > 0) trace_rxrpc_conn(conn, rxrpc_conn_got, n + 1, here); else diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c index b493e6b62740..777c3ed4cfc0 100644 --- a/net/rxrpc/local_object.c +++ b/net/rxrpc/local_object.c @@ -305,7 +305,7 @@ struct rxrpc_local *rxrpc_get_local_maybe(struct rxrpc_local *local) const void *here = __builtin_return_address(0); if (local) { - int n = __atomic_add_unless(&local->usage, 1, 0); + int n = atomic_fetch_add_unless(&local->usage, 1, 0); if (n > 0) trace_rxrpc_local(local, rxrpc_local_got, n + 1, here); else diff --git a/net/rxrpc/net_ns.c b/net/rxrpc/net_ns.c index 5d6a773db973..417d80867c4f 100644 --- a/net/rxrpc/net_ns.c +++ b/net/rxrpc/net_ns.c @@ -85,12 +85,12 @@ static __net_init int rxrpc_init_net(struct net *net) hash_init(rxnet->peer_hash); spin_lock_init(&rxnet->peer_hash_lock); for (i = 0; i < ARRAY_SIZE(rxnet->peer_keepalive); i++) - INIT_HLIST_HEAD(&rxnet->peer_keepalive[i]); - INIT_HLIST_HEAD(&rxnet->peer_keepalive_new); + INIT_LIST_HEAD(&rxnet->peer_keepalive[i]); + INIT_LIST_HEAD(&rxnet->peer_keepalive_new); timer_setup(&rxnet->peer_keepalive_timer, rxrpc_peer_keepalive_timeout, 0); INIT_WORK(&rxnet->peer_keepalive_work, rxrpc_peer_keepalive_worker); - rxnet->peer_keepalive_base = ktime_add(ktime_get_real(), NSEC_PER_SEC); + rxnet->peer_keepalive_base = ktime_get_seconds(); ret = -ENOMEM; rxnet->proc_net = proc_net_mkdir(net, "rxrpc", net->proc_net); diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c index f03de1c59ba3..4774c8f5634d 100644 --- a/net/rxrpc/output.c +++ b/net/rxrpc/output.c @@ -209,7 +209,7 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping, now = ktime_get_real(); if (ping) call->ping_time = now; - conn->params.peer->last_tx_at = ktime_get_real(); + conn->params.peer->last_tx_at = ktime_get_seconds(); if (ret < 0) trace_rxrpc_tx_fail(call->debug_id, serial, ret, rxrpc_tx_fail_call_ack); @@ -296,7 +296,7 @@ int rxrpc_send_abort_packet(struct rxrpc_call *call) ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, 1, sizeof(pkt)); - conn->params.peer->last_tx_at = ktime_get_real(); + conn->params.peer->last_tx_at = ktime_get_seconds(); if (ret < 0) trace_rxrpc_tx_fail(call->debug_id, serial, ret, rxrpc_tx_fail_call_abort); @@ -391,7 +391,7 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb, * message and update the peer record */ ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, 2, len); - conn->params.peer->last_tx_at = ktime_get_real(); + conn->params.peer->last_tx_at = ktime_get_seconds(); up_read(&conn->params.local->defrag_sem); if (ret < 0) @@ -457,7 +457,7 @@ send_fragmentable: if (ret == 0) { ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, 2, len); - conn->params.peer->last_tx_at = ktime_get_real(); + conn->params.peer->last_tx_at = ktime_get_seconds(); opt = IP_PMTUDISC_DO; kernel_setsockopt(conn->params.local->socket, SOL_IP, @@ -475,7 +475,7 @@ send_fragmentable: if (ret == 0) { ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, 2, len); - conn->params.peer->last_tx_at = ktime_get_real(); + conn->params.peer->last_tx_at = ktime_get_seconds(); opt = IPV6_PMTUDISC_DO; kernel_setsockopt(conn->params.local->socket, @@ -599,6 +599,6 @@ void rxrpc_send_keepalive(struct rxrpc_peer *peer) trace_rxrpc_tx_fail(peer->debug_id, 0, ret, rxrpc_tx_fail_version_keepalive); - peer->last_tx_at = ktime_get_real(); + peer->last_tx_at = ktime_get_seconds(); _leave(""); } diff --git a/net/rxrpc/peer_event.c b/net/rxrpc/peer_event.c index 0ed8b651cec2..4f9da2f51c69 100644 --- a/net/rxrpc/peer_event.c +++ b/net/rxrpc/peer_event.c @@ -350,97 +350,117 @@ void rxrpc_peer_add_rtt(struct rxrpc_call *call, enum rxrpc_rtt_rx_trace why, } /* - * Perform keep-alive pings with VERSION packets to keep any NAT alive. + * Perform keep-alive pings. */ -void rxrpc_peer_keepalive_worker(struct work_struct *work) +static void rxrpc_peer_keepalive_dispatch(struct rxrpc_net *rxnet, + struct list_head *collector, + time64_t base, + u8 cursor) { - struct rxrpc_net *rxnet = - container_of(work, struct rxrpc_net, peer_keepalive_work); struct rxrpc_peer *peer; - unsigned long delay; - ktime_t base, now = ktime_get_real(); - s64 diff; - u8 cursor, slot; + const u8 mask = ARRAY_SIZE(rxnet->peer_keepalive) - 1; + time64_t keepalive_at; + int slot; - base = rxnet->peer_keepalive_base; - cursor = rxnet->peer_keepalive_cursor; + spin_lock_bh(&rxnet->peer_hash_lock); - _enter("%u,%lld", cursor, ktime_sub(now, base)); + while (!list_empty(collector)) { + peer = list_entry(collector->next, + struct rxrpc_peer, keepalive_link); -next_bucket: - diff = ktime_to_ns(ktime_sub(now, base)); - if (diff < 0) - goto resched; + list_del_init(&peer->keepalive_link); + if (!rxrpc_get_peer_maybe(peer)) + continue; - _debug("at %u", cursor); - spin_lock_bh(&rxnet->peer_hash_lock); -next_peer: - if (!rxnet->live) { spin_unlock_bh(&rxnet->peer_hash_lock); - goto out; - } - /* Everything in the bucket at the cursor is processed this second; the - * bucket at cursor + 1 goes now + 1s and so on... - */ - if (hlist_empty(&rxnet->peer_keepalive[cursor])) { - if (hlist_empty(&rxnet->peer_keepalive_new)) { - spin_unlock_bh(&rxnet->peer_hash_lock); - goto emptied_bucket; + keepalive_at = peer->last_tx_at + RXRPC_KEEPALIVE_TIME; + slot = keepalive_at - base; + _debug("%02x peer %u t=%d {%pISp}", + cursor, peer->debug_id, slot, &peer->srx.transport); + + if (keepalive_at <= base || + keepalive_at > base + RXRPC_KEEPALIVE_TIME) { + rxrpc_send_keepalive(peer); + slot = RXRPC_KEEPALIVE_TIME; } - hlist_move_list(&rxnet->peer_keepalive_new, - &rxnet->peer_keepalive[cursor]); + /* A transmission to this peer occurred since last we examined + * it so put it into the appropriate future bucket. + */ + slot += cursor; + slot &= mask; + spin_lock_bh(&rxnet->peer_hash_lock); + list_add_tail(&peer->keepalive_link, + &rxnet->peer_keepalive[slot & mask]); + rxrpc_put_peer(peer); } - peer = hlist_entry(rxnet->peer_keepalive[cursor].first, - struct rxrpc_peer, keepalive_link); - hlist_del_init(&peer->keepalive_link); - if (!rxrpc_get_peer_maybe(peer)) - goto next_peer; - spin_unlock_bh(&rxnet->peer_hash_lock); +} - _debug("peer %u {%pISp}", peer->debug_id, &peer->srx.transport); +/* + * Perform keep-alive pings with VERSION packets to keep any NAT alive. + */ +void rxrpc_peer_keepalive_worker(struct work_struct *work) +{ + struct rxrpc_net *rxnet = + container_of(work, struct rxrpc_net, peer_keepalive_work); + const u8 mask = ARRAY_SIZE(rxnet->peer_keepalive) - 1; + time64_t base, now, delay; + u8 cursor, stop; + LIST_HEAD(collector); -recalc: - diff = ktime_divns(ktime_sub(peer->last_tx_at, base), NSEC_PER_SEC); - if (diff < -30 || diff > 30) - goto send; /* LSW of 64-bit time probably wrapped on 32-bit */ - diff += RXRPC_KEEPALIVE_TIME - 1; - if (diff < 0) - goto send; + now = ktime_get_seconds(); + base = rxnet->peer_keepalive_base; + cursor = rxnet->peer_keepalive_cursor; + _enter("%lld,%u", base - now, cursor); - slot = (diff > RXRPC_KEEPALIVE_TIME - 1) ? RXRPC_KEEPALIVE_TIME - 1 : diff; - if (slot == 0) - goto send; + if (!rxnet->live) + return; - /* A transmission to this peer occurred since last we examined it so - * put it into the appropriate future bucket. + /* Remove to a temporary list all the peers that are currently lodged + * in expired buckets plus all new peers. + * + * Everything in the bucket at the cursor is processed this + * second; the bucket at cursor + 1 goes at now + 1s and so + * on... */ - slot = (slot + cursor) % ARRAY_SIZE(rxnet->peer_keepalive); spin_lock_bh(&rxnet->peer_hash_lock); - hlist_add_head(&peer->keepalive_link, &rxnet->peer_keepalive[slot]); - rxrpc_put_peer(peer); - goto next_peer; - -send: - rxrpc_send_keepalive(peer); - now = ktime_get_real(); - goto recalc; + list_splice_init(&rxnet->peer_keepalive_new, &collector); + + stop = cursor + ARRAY_SIZE(rxnet->peer_keepalive); + while (base <= now && (s8)(cursor - stop) < 0) { + list_splice_tail_init(&rxnet->peer_keepalive[cursor & mask], + &collector); + base++; + cursor++; + } -emptied_bucket: - cursor++; - if (cursor >= ARRAY_SIZE(rxnet->peer_keepalive)) - cursor = 0; - base = ktime_add_ns(base, NSEC_PER_SEC); - goto next_bucket; + base = now; + spin_unlock_bh(&rxnet->peer_hash_lock); -resched: rxnet->peer_keepalive_base = base; rxnet->peer_keepalive_cursor = cursor; - delay = nsecs_to_jiffies(-diff) + 1; - timer_reduce(&rxnet->peer_keepalive_timer, jiffies + delay); -out: + rxrpc_peer_keepalive_dispatch(rxnet, &collector, base, cursor); + ASSERT(list_empty(&collector)); + + /* Schedule the timer for the next occupied timeslot. */ + cursor = rxnet->peer_keepalive_cursor; + stop = cursor + RXRPC_KEEPALIVE_TIME - 1; + for (; (s8)(cursor - stop) < 0; cursor++) { + if (!list_empty(&rxnet->peer_keepalive[cursor & mask])) + break; + base++; + } + + now = ktime_get_seconds(); + delay = base - now; + if (delay < 1) + delay = 1; + delay *= HZ; + if (rxnet->live) + timer_reduce(&rxnet->peer_keepalive_timer, jiffies + delay); + _leave(""); } diff --git a/net/rxrpc/peer_object.c b/net/rxrpc/peer_object.c index 1b7e8107b3ae..1dc7648e3eff 100644 --- a/net/rxrpc/peer_object.c +++ b/net/rxrpc/peer_object.c @@ -322,7 +322,7 @@ struct rxrpc_peer *rxrpc_lookup_incoming_peer(struct rxrpc_local *local, if (!peer) { peer = prealloc; hash_add_rcu(rxnet->peer_hash, &peer->hash_link, hash_key); - hlist_add_head(&peer->keepalive_link, &rxnet->peer_keepalive_new); + list_add_tail(&peer->keepalive_link, &rxnet->peer_keepalive_new); } spin_unlock(&rxnet->peer_hash_lock); @@ -367,8 +367,8 @@ struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_local *local, if (!peer) { hash_add_rcu(rxnet->peer_hash, &candidate->hash_link, hash_key); - hlist_add_head(&candidate->keepalive_link, - &rxnet->peer_keepalive_new); + list_add_tail(&candidate->keepalive_link, + &rxnet->peer_keepalive_new); } spin_unlock_bh(&rxnet->peer_hash_lock); @@ -406,7 +406,7 @@ struct rxrpc_peer *rxrpc_get_peer_maybe(struct rxrpc_peer *peer) const void *here = __builtin_return_address(0); if (peer) { - int n = __atomic_add_unless(&peer->usage, 1, 0); + int n = atomic_fetch_add_unless(&peer->usage, 1, 0); if (n > 0) trace_rxrpc_peer(peer, rxrpc_peer_got, n + 1, here); else @@ -441,7 +441,7 @@ static void __rxrpc_put_peer(struct rxrpc_peer *peer) spin_lock_bh(&rxnet->peer_hash_lock); hash_del_rcu(&peer->hash_link); - hlist_del_init(&peer->keepalive_link); + list_del_init(&peer->keepalive_link); spin_unlock_bh(&rxnet->peer_hash_lock); kfree_rcu(peer, rcu); diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c index 278ac0807a60..47cb019c521a 100644 --- a/net/rxrpc/rxkad.c +++ b/net/rxrpc/rxkad.c @@ -669,7 +669,7 @@ static int rxkad_issue_challenge(struct rxrpc_connection *conn) return -EAGAIN; } - conn->params.peer->last_tx_at = ktime_get_real(); + conn->params.peer->last_tx_at = ktime_get_seconds(); _leave(" = 0"); return 0; } @@ -725,7 +725,7 @@ static int rxkad_send_response(struct rxrpc_connection *conn, return -EAGAIN; } - conn->params.peer->last_tx_at = ktime_get_real(); + conn->params.peer->last_tx_at = ktime_get_seconds(); _leave(" = 0"); return 0; } diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 05e4ffe5aabd..e7de5f282722 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -1122,6 +1122,8 @@ static void smc_tcp_listen_work(struct work_struct *work) sock_hold(lsk); /* sock_put in smc_listen_work */ INIT_WORK(&new_smc->smc_listen_work, smc_listen_work); smc_copy_sock_settings_to_smc(new_smc); + new_smc->sk.sk_sndbuf = lsmc->sk.sk_sndbuf; + new_smc->sk.sk_rcvbuf = lsmc->sk.sk_rcvbuf; sock_hold(&new_smc->sk); /* sock_put in passive closing */ if (!schedule_work(&new_smc->smc_listen_work)) sock_put(&new_smc->sk); @@ -1397,8 +1399,7 @@ static int smc_shutdown(struct socket *sock, int how) lock_sock(sk); rc = -ENOTCONN; - if ((sk->sk_state != SMC_LISTEN) && - (sk->sk_state != SMC_ACTIVE) && + if ((sk->sk_state != SMC_ACTIVE) && (sk->sk_state != SMC_PEERCLOSEWAIT1) && (sk->sk_state != SMC_PEERCLOSEWAIT2) && (sk->sk_state != SMC_APPCLOSEWAIT1) && @@ -1521,12 +1522,16 @@ static int smc_ioctl(struct socket *sock, unsigned int cmd, smc = smc_sk(sock->sk); conn = &smc->conn; + lock_sock(&smc->sk); if (smc->use_fallback) { - if (!smc->clcsock) + if (!smc->clcsock) { + release_sock(&smc->sk); return -EBADF; - return smc->clcsock->ops->ioctl(smc->clcsock, cmd, arg); + } + answ = smc->clcsock->ops->ioctl(smc->clcsock, cmd, arg); + release_sock(&smc->sk); + return answ; } - lock_sock(&smc->sk); switch (cmd) { case SIOCINQ: /* same as FIONREAD */ if (smc->sk.sk_state == SMC_LISTEN) { diff --git a/net/tipc/net.c b/net/tipc/net.c index a7f6964c3a4b..62199cf5a56c 100644 --- a/net/tipc/net.c +++ b/net/tipc/net.c @@ -123,15 +123,13 @@ void tipc_net_finalize(struct net *net, u32 addr) { struct tipc_net *tn = tipc_net(net); - spin_lock_bh(&tn->node_list_lock); - if (!tipc_own_addr(net)) { + if (!cmpxchg(&tn->node_addr, 0, addr)) { tipc_set_node_addr(net, addr); tipc_named_reinit(net); tipc_sk_reinit(net); tipc_nametbl_publish(net, TIPC_CFG_SRV, addr, addr, TIPC_CLUSTER_SCOPE, 0, addr); } - spin_unlock_bh(&tn->node_list_lock); } void tipc_net_stop(struct net *net) diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index c1076c19b858..ab27a2872935 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -451,14 +451,14 @@ static int vsock_send_shutdown(struct sock *sk, int mode) return transport->shutdown(vsock_sk(sk), mode); } -void vsock_pending_work(struct work_struct *work) +static void vsock_pending_work(struct work_struct *work) { struct sock *sk; struct sock *listener; struct vsock_sock *vsk; bool cleanup; - vsk = container_of(work, struct vsock_sock, dwork.work); + vsk = container_of(work, struct vsock_sock, pending_work.work); sk = sk_vsock(vsk); listener = vsk->listener; cleanup = true; @@ -498,7 +498,6 @@ out: sock_put(sk); sock_put(listener); } -EXPORT_SYMBOL_GPL(vsock_pending_work); /**** SOCKET OPERATIONS ****/ @@ -597,6 +596,8 @@ static int __vsock_bind(struct sock *sk, struct sockaddr_vm *addr) return retval; } +static void vsock_connect_timeout(struct work_struct *work); + struct sock *__vsock_create(struct net *net, struct socket *sock, struct sock *parent, @@ -638,6 +639,8 @@ struct sock *__vsock_create(struct net *net, vsk->sent_request = false; vsk->ignore_connecting_rst = false; vsk->peer_shutdown = 0; + INIT_DELAYED_WORK(&vsk->connect_work, vsock_connect_timeout); + INIT_DELAYED_WORK(&vsk->pending_work, vsock_pending_work); psk = parent ? vsock_sk(parent) : NULL; if (parent) { @@ -1117,7 +1120,7 @@ static void vsock_connect_timeout(struct work_struct *work) struct vsock_sock *vsk; int cancel = 0; - vsk = container_of(work, struct vsock_sock, dwork.work); + vsk = container_of(work, struct vsock_sock, connect_work.work); sk = sk_vsock(vsk); lock_sock(sk); @@ -1221,9 +1224,7 @@ static int vsock_stream_connect(struct socket *sock, struct sockaddr *addr, * timeout fires. */ sock_hold(sk); - INIT_DELAYED_WORK(&vsk->dwork, - vsock_connect_timeout); - schedule_delayed_work(&vsk->dwork, timeout); + schedule_delayed_work(&vsk->connect_work, timeout); /* Skip ahead to preserve error code set above. */ goto out_wait; diff --git a/net/vmw_vsock/vmci_transport.c b/net/vmw_vsock/vmci_transport.c index a7a73ffe675b..cb332adb84cd 100644 --- a/net/vmw_vsock/vmci_transport.c +++ b/net/vmw_vsock/vmci_transport.c @@ -1094,8 +1094,7 @@ static int vmci_transport_recv_listen(struct sock *sk, vpending->listener = sk; sock_hold(sk); sock_hold(pending); - INIT_DELAYED_WORK(&vpending->dwork, vsock_pending_work); - schedule_delayed_work(&vpending->dwork, HZ); + schedule_delayed_work(&vpending->pending_work, HZ); out: return err; diff --git a/samples/bpf/xdp_redirect_cpu_kern.c b/samples/bpf/xdp_redirect_cpu_kern.c index 303e9e7161f3..4938dcbaecbf 100644 --- a/samples/bpf/xdp_redirect_cpu_kern.c +++ b/samples/bpf/xdp_redirect_cpu_kern.c @@ -14,7 +14,7 @@ #include <uapi/linux/bpf.h> #include "bpf_helpers.h" -#define MAX_CPUS 12 /* WARNING - sync with _user.c */ +#define MAX_CPUS 64 /* WARNING - sync with _user.c */ /* Special map type that can XDP_REDIRECT frames to another CPU */ struct bpf_map_def SEC("maps") cpu_map = { diff --git a/samples/bpf/xdp_redirect_cpu_user.c b/samples/bpf/xdp_redirect_cpu_user.c index f6efaefd485b..4b4d78fffe30 100644 --- a/samples/bpf/xdp_redirect_cpu_user.c +++ b/samples/bpf/xdp_redirect_cpu_user.c @@ -19,7 +19,7 @@ static const char *__doc__ = #include <arpa/inet.h> #include <linux/if_link.h> -#define MAX_CPUS 12 /* WARNING - sync with _kern.c */ +#define MAX_CPUS 64 /* WARNING - sync with _kern.c */ /* How many xdp_progs are defined in _kern.c */ #define MAX_PROG 5 @@ -527,7 +527,7 @@ static void stress_cpumap(void) * procedure. */ create_cpu_entry(1, 1024, 0, false); - create_cpu_entry(1, 128, 0, false); + create_cpu_entry(1, 8, 0, false); create_cpu_entry(1, 16000, 0, false); } diff --git a/scripts/Makefile.ubsan b/scripts/Makefile.ubsan index b593b36ccff8..38b2b4818e8e 100644 --- a/scripts/Makefile.ubsan +++ b/scripts/Makefile.ubsan @@ -14,10 +14,6 @@ ifdef CONFIG_UBSAN_ALIGNMENT CFLAGS_UBSAN += $(call cc-option, -fsanitize=alignment) endif -ifdef CONFIG_UBSAN_NULL - CFLAGS_UBSAN += $(call cc-option, -fsanitize=null) -endif - # -fsanitize=* options makes GCC less smart than usual and # increase number of 'maybe-uninitialized false-positives CFLAGS_UBSAN += $(call cc-option, -Wno-maybe-uninitialized) diff --git a/tools/arch/arm64/include/uapi/asm/unistd.h b/tools/arch/arm64/include/uapi/asm/unistd.h new file mode 100644 index 000000000000..5072cbd15c82 --- /dev/null +++ b/tools/arch/arm64/include/uapi/asm/unistd.h @@ -0,0 +1,20 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* + * Copyright (C) 2012 ARM Ltd. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#define __ARCH_WANT_RENAMEAT + +#include <asm-generic/unistd.h> diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h new file mode 100644 index 000000000000..42990676a55e --- /dev/null +++ b/tools/include/uapi/asm-generic/unistd.h @@ -0,0 +1,783 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#include <asm/bitsperlong.h> + +/* + * This file contains the system call numbers, based on the + * layout of the x86-64 architecture, which embeds the + * pointer to the syscall in the table. + * + * As a basic principle, no duplication of functionality + * should be added, e.g. we don't use lseek when llseek + * is present. New architectures should use this file + * and implement the less feature-full calls in user space. + */ + +#ifndef __SYSCALL +#define __SYSCALL(x, y) +#endif + +#if __BITS_PER_LONG == 32 || defined(__SYSCALL_COMPAT) +#define __SC_3264(_nr, _32, _64) __SYSCALL(_nr, _32) +#else +#define __SC_3264(_nr, _32, _64) __SYSCALL(_nr, _64) +#endif + +#ifdef __SYSCALL_COMPAT +#define __SC_COMP(_nr, _sys, _comp) __SYSCALL(_nr, _comp) +#define __SC_COMP_3264(_nr, _32, _64, _comp) __SYSCALL(_nr, _comp) +#else +#define __SC_COMP(_nr, _sys, _comp) __SYSCALL(_nr, _sys) +#define __SC_COMP_3264(_nr, _32, _64, _comp) __SC_3264(_nr, _32, _64) +#endif + +#define __NR_io_setup 0 +__SC_COMP(__NR_io_setup, sys_io_setup, compat_sys_io_setup) +#define __NR_io_destroy 1 +__SYSCALL(__NR_io_destroy, sys_io_destroy) +#define __NR_io_submit 2 +__SC_COMP(__NR_io_submit, sys_io_submit, compat_sys_io_submit) +#define __NR_io_cancel 3 +__SYSCALL(__NR_io_cancel, sys_io_cancel) +#define __NR_io_getevents 4 +__SC_COMP(__NR_io_getevents, sys_io_getevents, compat_sys_io_getevents) + +/* fs/xattr.c */ +#define __NR_setxattr 5 +__SYSCALL(__NR_setxattr, sys_setxattr) +#define __NR_lsetxattr 6 +__SYSCALL(__NR_lsetxattr, sys_lsetxattr) +#define __NR_fsetxattr 7 +__SYSCALL(__NR_fsetxattr, sys_fsetxattr) +#define __NR_getxattr 8 +__SYSCALL(__NR_getxattr, sys_getxattr) +#define __NR_lgetxattr 9 +__SYSCALL(__NR_lgetxattr, sys_lgetxattr) +#define __NR_fgetxattr 10 +__SYSCALL(__NR_fgetxattr, sys_fgetxattr) +#define __NR_listxattr 11 +__SYSCALL(__NR_listxattr, sys_listxattr) +#define __NR_llistxattr 12 +__SYSCALL(__NR_llistxattr, sys_llistxattr) +#define __NR_flistxattr 13 +__SYSCALL(__NR_flistxattr, sys_flistxattr) +#define __NR_removexattr 14 +__SYSCALL(__NR_removexattr, sys_removexattr) +#define __NR_lremovexattr 15 +__SYSCALL(__NR_lremovexattr, sys_lremovexattr) +#define __NR_fremovexattr 16 +__SYSCALL(__NR_fremovexattr, sys_fremovexattr) + +/* fs/dcache.c */ +#define __NR_getcwd 17 +__SYSCALL(__NR_getcwd, sys_getcwd) + +/* fs/cookies.c */ +#define __NR_lookup_dcookie 18 +__SC_COMP(__NR_lookup_dcookie, sys_lookup_dcookie, compat_sys_lookup_dcookie) + +/* fs/eventfd.c */ +#define __NR_eventfd2 19 +__SYSCALL(__NR_eventfd2, sys_eventfd2) + +/* fs/eventpoll.c */ +#define __NR_epoll_create1 20 +__SYSCALL(__NR_epoll_create1, sys_epoll_create1) +#define __NR_epoll_ctl 21 +__SYSCALL(__NR_epoll_ctl, sys_epoll_ctl) +#define __NR_epoll_pwait 22 +__SC_COMP(__NR_epoll_pwait, sys_epoll_pwait, compat_sys_epoll_pwait) + +/* fs/fcntl.c */ +#define __NR_dup 23 +__SYSCALL(__NR_dup, sys_dup) +#define __NR_dup3 24 +__SYSCALL(__NR_dup3, sys_dup3) +#define __NR3264_fcntl 25 +__SC_COMP_3264(__NR3264_fcntl, sys_fcntl64, sys_fcntl, compat_sys_fcntl64) + +/* fs/inotify_user.c */ +#define __NR_inotify_init1 26 +__SYSCALL(__NR_inotify_init1, sys_inotify_init1) +#define __NR_inotify_add_watch 27 +__SYSCALL(__NR_inotify_add_watch, sys_inotify_add_watch) +#define __NR_inotify_rm_watch 28 +__SYSCALL(__NR_inotify_rm_watch, sys_inotify_rm_watch) + +/* fs/ioctl.c */ +#define __NR_ioctl 29 +__SC_COMP(__NR_ioctl, sys_ioctl, compat_sys_ioctl) + +/* fs/ioprio.c */ +#define __NR_ioprio_set 30 +__SYSCALL(__NR_ioprio_set, sys_ioprio_set) +#define __NR_ioprio_get 31 +__SYSCALL(__NR_ioprio_get, sys_ioprio_get) + +/* fs/locks.c */ +#define __NR_flock 32 +__SYSCALL(__NR_flock, sys_flock) + +/* fs/namei.c */ +#define __NR_mknodat 33 +__SYSCALL(__NR_mknodat, sys_mknodat) +#define __NR_mkdirat 34 +__SYSCALL(__NR_mkdirat, sys_mkdirat) +#define __NR_unlinkat 35 +__SYSCALL(__NR_unlinkat, sys_unlinkat) +#define __NR_symlinkat 36 +__SYSCALL(__NR_symlinkat, sys_symlinkat) +#define __NR_linkat 37 +__SYSCALL(__NR_linkat, sys_linkat) +#ifdef __ARCH_WANT_RENAMEAT +/* renameat is superseded with flags by renameat2 */ +#define __NR_renameat 38 +__SYSCALL(__NR_renameat, sys_renameat) +#endif /* __ARCH_WANT_RENAMEAT */ + +/* fs/namespace.c */ +#define __NR_umount2 39 +__SYSCALL(__NR_umount2, sys_umount) +#define __NR_mount 40 +__SC_COMP(__NR_mount, sys_mount, compat_sys_mount) +#define __NR_pivot_root 41 +__SYSCALL(__NR_pivot_root, sys_pivot_root) + +/* fs/nfsctl.c */ +#define __NR_nfsservctl 42 +__SYSCALL(__NR_nfsservctl, sys_ni_syscall) + +/* fs/open.c */ +#define __NR3264_statfs 43 +__SC_COMP_3264(__NR3264_statfs, sys_statfs64, sys_statfs, \ + compat_sys_statfs64) +#define __NR3264_fstatfs 44 +__SC_COMP_3264(__NR3264_fstatfs, sys_fstatfs64, sys_fstatfs, \ + compat_sys_fstatfs64) +#define __NR3264_truncate 45 +__SC_COMP_3264(__NR3264_truncate, sys_truncate64, sys_truncate, \ + compat_sys_truncate64) +#define __NR3264_ftruncate 46 +__SC_COMP_3264(__NR3264_ftruncate, sys_ftruncate64, sys_ftruncate, \ + compat_sys_ftruncate64) + +#define __NR_fallocate 47 +__SC_COMP(__NR_fallocate, sys_fallocate, compat_sys_fallocate) +#define __NR_faccessat 48 +__SYSCALL(__NR_faccessat, sys_faccessat) +#define __NR_chdir 49 +__SYSCALL(__NR_chdir, sys_chdir) +#define __NR_fchdir 50 +__SYSCALL(__NR_fchdir, sys_fchdir) +#define __NR_chroot 51 +__SYSCALL(__NR_chroot, sys_chroot) +#define __NR_fchmod 52 +__SYSCALL(__NR_fchmod, sys_fchmod) +#define __NR_fchmodat 53 +__SYSCALL(__NR_fchmodat, sys_fchmodat) +#define __NR_fchownat 54 +__SYSCALL(__NR_fchownat, sys_fchownat) +#define __NR_fchown 55 +__SYSCALL(__NR_fchown, sys_fchown) +#define __NR_openat 56 +__SC_COMP(__NR_openat, sys_openat, compat_sys_openat) +#define __NR_close 57 +__SYSCALL(__NR_close, sys_close) +#define __NR_vhangup 58 +__SYSCALL(__NR_vhangup, sys_vhangup) + +/* fs/pipe.c */ +#define __NR_pipe2 59 +__SYSCALL(__NR_pipe2, sys_pipe2) + +/* fs/quota.c */ +#define __NR_quotactl 60 +__SYSCALL(__NR_quotactl, sys_quotactl) + +/* fs/readdir.c */ +#define __NR_getdents64 61 +__SYSCALL(__NR_getdents64, sys_getdents64) + +/* fs/read_write.c */ +#define __NR3264_lseek 62 +__SC_3264(__NR3264_lseek, sys_llseek, sys_lseek) +#define __NR_read 63 +__SYSCALL(__NR_read, sys_read) +#define __NR_write 64 +__SYSCALL(__NR_write, sys_write) +#define __NR_readv 65 +__SC_COMP(__NR_readv, sys_readv, compat_sys_readv) +#define __NR_writev 66 +__SC_COMP(__NR_writev, sys_writev, compat_sys_writev) +#define __NR_pread64 67 +__SC_COMP(__NR_pread64, sys_pread64, compat_sys_pread64) +#define __NR_pwrite64 68 +__SC_COMP(__NR_pwrite64, sys_pwrite64, compat_sys_pwrite64) +#define __NR_preadv 69 +__SC_COMP(__NR_preadv, sys_preadv, compat_sys_preadv) +#define __NR_pwritev 70 +__SC_COMP(__NR_pwritev, sys_pwritev, compat_sys_pwritev) + +/* fs/sendfile.c */ +#define __NR3264_sendfile 71 +__SYSCALL(__NR3264_sendfile, sys_sendfile64) + +/* fs/select.c */ +#define __NR_pselect6 72 +__SC_COMP(__NR_pselect6, sys_pselect6, compat_sys_pselect6) +#define __NR_ppoll 73 +__SC_COMP(__NR_ppoll, sys_ppoll, compat_sys_ppoll) + +/* fs/signalfd.c */ +#define __NR_signalfd4 74 +__SC_COMP(__NR_signalfd4, sys_signalfd4, compat_sys_signalfd4) + +/* fs/splice.c */ +#define __NR_vmsplice 75 +__SC_COMP(__NR_vmsplice, sys_vmsplice, compat_sys_vmsplice) +#define __NR_splice 76 +__SYSCALL(__NR_splice, sys_splice) +#define __NR_tee 77 +__SYSCALL(__NR_tee, sys_tee) + +/* fs/stat.c */ +#define __NR_readlinkat 78 +__SYSCALL(__NR_readlinkat, sys_readlinkat) +#define __NR3264_fstatat 79 +__SC_3264(__NR3264_fstatat, sys_fstatat64, sys_newfstatat) +#define __NR3264_fstat 80 +__SC_3264(__NR3264_fstat, sys_fstat64, sys_newfstat) + +/* fs/sync.c */ +#define __NR_sync 81 +__SYSCALL(__NR_sync, sys_sync) +#define __NR_fsync 82 +__SYSCALL(__NR_fsync, sys_fsync) +#define __NR_fdatasync 83 +__SYSCALL(__NR_fdatasync, sys_fdatasync) +#ifdef __ARCH_WANT_SYNC_FILE_RANGE2 +#define __NR_sync_file_range2 84 +__SC_COMP(__NR_sync_file_range2, sys_sync_file_range2, \ + compat_sys_sync_file_range2) +#else +#define __NR_sync_file_range 84 +__SC_COMP(__NR_sync_file_range, sys_sync_file_range, \ + compat_sys_sync_file_range) +#endif + +/* fs/timerfd.c */ +#define __NR_timerfd_create 85 +__SYSCALL(__NR_timerfd_create, sys_timerfd_create) +#define __NR_timerfd_settime 86 +__SC_COMP(__NR_timerfd_settime, sys_timerfd_settime, \ + compat_sys_timerfd_settime) +#define __NR_timerfd_gettime 87 +__SC_COMP(__NR_timerfd_gettime, sys_timerfd_gettime, \ + compat_sys_timerfd_gettime) + +/* fs/utimes.c */ +#define __NR_utimensat 88 +__SC_COMP(__NR_utimensat, sys_utimensat, compat_sys_utimensat) + +/* kernel/acct.c */ +#define __NR_acct 89 +__SYSCALL(__NR_acct, sys_acct) + +/* kernel/capability.c */ +#define __NR_capget 90 +__SYSCALL(__NR_capget, sys_capget) +#define __NR_capset 91 +__SYSCALL(__NR_capset, sys_capset) + +/* kernel/exec_domain.c */ +#define __NR_personality 92 +__SYSCALL(__NR_personality, sys_personality) + +/* kernel/exit.c */ +#define __NR_exit 93 +__SYSCALL(__NR_exit, sys_exit) +#define __NR_exit_group 94 +__SYSCALL(__NR_exit_group, sys_exit_group) +#define __NR_waitid 95 +__SC_COMP(__NR_waitid, sys_waitid, compat_sys_waitid) + +/* kernel/fork.c */ +#define __NR_set_tid_address 96 +__SYSCALL(__NR_set_tid_address, sys_set_tid_address) +#define __NR_unshare 97 +__SYSCALL(__NR_unshare, sys_unshare) + +/* kernel/futex.c */ +#define __NR_futex 98 +__SC_COMP(__NR_futex, sys_futex, compat_sys_futex) +#define __NR_set_robust_list 99 +__SC_COMP(__NR_set_robust_list, sys_set_robust_list, \ + compat_sys_set_robust_list) +#define __NR_get_robust_list 100 +__SC_COMP(__NR_get_robust_list, sys_get_robust_list, \ + compat_sys_get_robust_list) + +/* kernel/hrtimer.c */ +#define __NR_nanosleep 101 +__SC_COMP(__NR_nanosleep, sys_nanosleep, compat_sys_nanosleep) + +/* kernel/itimer.c */ +#define __NR_getitimer 102 +__SC_COMP(__NR_getitimer, sys_getitimer, compat_sys_getitimer) +#define __NR_setitimer 103 +__SC_COMP(__NR_setitimer, sys_setitimer, compat_sys_setitimer) + +/* kernel/kexec.c */ +#define __NR_kexec_load 104 +__SC_COMP(__NR_kexec_load, sys_kexec_load, compat_sys_kexec_load) + +/* kernel/module.c */ +#define __NR_init_module 105 +__SYSCALL(__NR_init_module, sys_init_module) +#define __NR_delete_module 106 +__SYSCALL(__NR_delete_module, sys_delete_module) + +/* kernel/posix-timers.c */ +#define __NR_timer_create 107 +__SC_COMP(__NR_timer_create, sys_timer_create, compat_sys_timer_create) +#define __NR_timer_gettime 108 +__SC_COMP(__NR_timer_gettime, sys_timer_gettime, compat_sys_timer_gettime) +#define __NR_timer_getoverrun 109 +__SYSCALL(__NR_timer_getoverrun, sys_timer_getoverrun) +#define __NR_timer_settime 110 +__SC_COMP(__NR_timer_settime, sys_timer_settime, compat_sys_timer_settime) +#define __NR_timer_delete 111 +__SYSCALL(__NR_timer_delete, sys_timer_delete) +#define __NR_clock_settime 112 +__SC_COMP(__NR_clock_settime, sys_clock_settime, compat_sys_clock_settime) +#define __NR_clock_gettime 113 +__SC_COMP(__NR_clock_gettime, sys_clock_gettime, compat_sys_clock_gettime) +#define __NR_clock_getres 114 +__SC_COMP(__NR_clock_getres, sys_clock_getres, compat_sys_clock_getres) +#define __NR_clock_nanosleep 115 +__SC_COMP(__NR_clock_nanosleep, sys_clock_nanosleep, \ + compat_sys_clock_nanosleep) + +/* kernel/printk.c */ +#define __NR_syslog 116 +__SYSCALL(__NR_syslog, sys_syslog) + +/* kernel/ptrace.c */ +#define __NR_ptrace 117 +__SYSCALL(__NR_ptrace, sys_ptrace) + +/* kernel/sched/core.c */ +#define __NR_sched_setparam 118 +__SYSCALL(__NR_sched_setparam, sys_sched_setparam) +#define __NR_sched_setscheduler 119 +__SYSCALL(__NR_sched_setscheduler, sys_sched_setscheduler) +#define __NR_sched_getscheduler 120 +__SYSCALL(__NR_sched_getscheduler, sys_sched_getscheduler) +#define __NR_sched_getparam 121 +__SYSCALL(__NR_sched_getparam, sys_sched_getparam) +#define __NR_sched_setaffinity 122 +__SC_COMP(__NR_sched_setaffinity, sys_sched_setaffinity, \ + compat_sys_sched_setaffinity) +#define __NR_sched_getaffinity 123 +__SC_COMP(__NR_sched_getaffinity, sys_sched_getaffinity, \ + compat_sys_sched_getaffinity) +#define __NR_sched_yield 124 +__SYSCALL(__NR_sched_yield, sys_sched_yield) +#define __NR_sched_get_priority_max 125 +__SYSCALL(__NR_sched_get_priority_max, sys_sched_get_priority_max) +#define __NR_sched_get_priority_min 126 +__SYSCALL(__NR_sched_get_priority_min, sys_sched_get_priority_min) +#define __NR_sched_rr_get_interval 127 +__SC_COMP(__NR_sched_rr_get_interval, sys_sched_rr_get_interval, \ + compat_sys_sched_rr_get_interval) + +/* kernel/signal.c */ +#define __NR_restart_syscall 128 +__SYSCALL(__NR_restart_syscall, sys_restart_syscall) +#define __NR_kill 129 +__SYSCALL(__NR_kill, sys_kill) +#define __NR_tkill 130 +__SYSCALL(__NR_tkill, sys_tkill) +#define __NR_tgkill 131 +__SYSCALL(__NR_tgkill, sys_tgkill) +#define __NR_sigaltstack 132 +__SC_COMP(__NR_sigaltstack, sys_sigaltstack, compat_sys_sigaltstack) +#define __NR_rt_sigsuspend 133 +__SC_COMP(__NR_rt_sigsuspend, sys_rt_sigsuspend, compat_sys_rt_sigsuspend) +#define __NR_rt_sigaction 134 +__SC_COMP(__NR_rt_sigaction, sys_rt_sigaction, compat_sys_rt_sigaction) +#define __NR_rt_sigprocmask 135 +__SC_COMP(__NR_rt_sigprocmask, sys_rt_sigprocmask, compat_sys_rt_sigprocmask) +#define __NR_rt_sigpending 136 +__SC_COMP(__NR_rt_sigpending, sys_rt_sigpending, compat_sys_rt_sigpending) +#define __NR_rt_sigtimedwait 137 +__SC_COMP(__NR_rt_sigtimedwait, sys_rt_sigtimedwait, \ + compat_sys_rt_sigtimedwait) +#define __NR_rt_sigqueueinfo 138 +__SC_COMP(__NR_rt_sigqueueinfo, sys_rt_sigqueueinfo, \ + compat_sys_rt_sigqueueinfo) +#define __NR_rt_sigreturn 139 +__SC_COMP(__NR_rt_sigreturn, sys_rt_sigreturn, compat_sys_rt_sigreturn) + +/* kernel/sys.c */ +#define __NR_setpriority 140 +__SYSCALL(__NR_setpriority, sys_setpriority) +#define __NR_getpriority 141 +__SYSCALL(__NR_getpriority, sys_getpriority) +#define __NR_reboot 142 +__SYSCALL(__NR_reboot, sys_reboot) +#define __NR_setregid 143 +__SYSCALL(__NR_setregid, sys_setregid) +#define __NR_setgid 144 +__SYSCALL(__NR_setgid, sys_setgid) +#define __NR_setreuid 145 +__SYSCALL(__NR_setreuid, sys_setreuid) +#define __NR_setuid 146 +__SYSCALL(__NR_setuid, sys_setuid) +#define __NR_setresuid 147 +__SYSCALL(__NR_setresuid, sys_setresuid) +#define __NR_getresuid 148 +__SYSCALL(__NR_getresuid, sys_getresuid) +#define __NR_setresgid 149 +__SYSCALL(__NR_setresgid, sys_setresgid) +#define __NR_getresgid 150 +__SYSCALL(__NR_getresgid, sys_getresgid) +#define __NR_setfsuid 151 +__SYSCALL(__NR_setfsuid, sys_setfsuid) +#define __NR_setfsgid 152 +__SYSCALL(__NR_setfsgid, sys_setfsgid) +#define __NR_times 153 +__SC_COMP(__NR_times, sys_times, compat_sys_times) +#define __NR_setpgid 154 +__SYSCALL(__NR_setpgid, sys_setpgid) +#define __NR_getpgid 155 +__SYSCALL(__NR_getpgid, sys_getpgid) +#define __NR_getsid 156 +__SYSCALL(__NR_getsid, sys_getsid) +#define __NR_setsid 157 +__SYSCALL(__NR_setsid, sys_setsid) +#define __NR_getgroups 158 +__SYSCALL(__NR_getgroups, sys_getgroups) +#define __NR_setgroups 159 +__SYSCALL(__NR_setgroups, sys_setgroups) +#define __NR_uname 160 +__SYSCALL(__NR_uname, sys_newuname) +#define __NR_sethostname 161 +__SYSCALL(__NR_sethostname, sys_sethostname) +#define __NR_setdomainname 162 +__SYSCALL(__NR_setdomainname, sys_setdomainname) +#define __NR_getrlimit 163 +__SC_COMP(__NR_getrlimit, sys_getrlimit, compat_sys_getrlimit) +#define __NR_setrlimit 164 +__SC_COMP(__NR_setrlimit, sys_setrlimit, compat_sys_setrlimit) +#define __NR_getrusage 165 +__SC_COMP(__NR_getrusage, sys_getrusage, compat_sys_getrusage) +#define __NR_umask 166 +__SYSCALL(__NR_umask, sys_umask) +#define __NR_prctl 167 +__SYSCALL(__NR_prctl, sys_prctl) +#define __NR_getcpu 168 +__SYSCALL(__NR_getcpu, sys_getcpu) + +/* kernel/time.c */ +#define __NR_gettimeofday 169 +__SC_COMP(__NR_gettimeofday, sys_gettimeofday, compat_sys_gettimeofday) +#define __NR_settimeofday 170 +__SC_COMP(__NR_settimeofday, sys_settimeofday, compat_sys_settimeofday) +#define __NR_adjtimex 171 +__SC_COMP(__NR_adjtimex, sys_adjtimex, compat_sys_adjtimex) + +/* kernel/timer.c */ +#define __NR_getpid 172 +__SYSCALL(__NR_getpid, sys_getpid) +#define __NR_getppid 173 +__SYSCALL(__NR_getppid, sys_getppid) +#define __NR_getuid 174 +__SYSCALL(__NR_getuid, sys_getuid) +#define __NR_geteuid 175 +__SYSCALL(__NR_geteuid, sys_geteuid) +#define __NR_getgid 176 +__SYSCALL(__NR_getgid, sys_getgid) +#define __NR_getegid 177 +__SYSCALL(__NR_getegid, sys_getegid) +#define __NR_gettid 178 +__SYSCALL(__NR_gettid, sys_gettid) +#define __NR_sysinfo 179 +__SC_COMP(__NR_sysinfo, sys_sysinfo, compat_sys_sysinfo) + +/* ipc/mqueue.c */ +#define __NR_mq_open 180 +__SC_COMP(__NR_mq_open, sys_mq_open, compat_sys_mq_open) +#define __NR_mq_unlink 181 +__SYSCALL(__NR_mq_unlink, sys_mq_unlink) +#define __NR_mq_timedsend 182 +__SC_COMP(__NR_mq_timedsend, sys_mq_timedsend, compat_sys_mq_timedsend) +#define __NR_mq_timedreceive 183 +__SC_COMP(__NR_mq_timedreceive, sys_mq_timedreceive, \ + compat_sys_mq_timedreceive) +#define __NR_mq_notify 184 +__SC_COMP(__NR_mq_notify, sys_mq_notify, compat_sys_mq_notify) +#define __NR_mq_getsetattr 185 +__SC_COMP(__NR_mq_getsetattr, sys_mq_getsetattr, compat_sys_mq_getsetattr) + +/* ipc/msg.c */ +#define __NR_msgget 186 +__SYSCALL(__NR_msgget, sys_msgget) +#define __NR_msgctl 187 +__SC_COMP(__NR_msgctl, sys_msgctl, compat_sys_msgctl) +#define __NR_msgrcv 188 +__SC_COMP(__NR_msgrcv, sys_msgrcv, compat_sys_msgrcv) +#define __NR_msgsnd 189 +__SC_COMP(__NR_msgsnd, sys_msgsnd, compat_sys_msgsnd) + +/* ipc/sem.c */ +#define __NR_semget 190 +__SYSCALL(__NR_semget, sys_semget) +#define __NR_semctl 191 +__SC_COMP(__NR_semctl, sys_semctl, compat_sys_semctl) +#define __NR_semtimedop 192 +__SC_COMP(__NR_semtimedop, sys_semtimedop, compat_sys_semtimedop) +#define __NR_semop 193 +__SYSCALL(__NR_semop, sys_semop) + +/* ipc/shm.c */ +#define __NR_shmget 194 +__SYSCALL(__NR_shmget, sys_shmget) +#define __NR_shmctl 195 +__SC_COMP(__NR_shmctl, sys_shmctl, compat_sys_shmctl) +#define __NR_shmat 196 +__SC_COMP(__NR_shmat, sys_shmat, compat_sys_shmat) +#define __NR_shmdt 197 +__SYSCALL(__NR_shmdt, sys_shmdt) + +/* net/socket.c */ +#define __NR_socket 198 +__SYSCALL(__NR_socket, sys_socket) +#define __NR_socketpair 199 +__SYSCALL(__NR_socketpair, sys_socketpair) +#define __NR_bind 200 +__SYSCALL(__NR_bind, sys_bind) +#define __NR_listen 201 +__SYSCALL(__NR_listen, sys_listen) +#define __NR_accept 202 +__SYSCALL(__NR_accept, sys_accept) +#define __NR_connect 203 +__SYSCALL(__NR_connect, sys_connect) +#define __NR_getsockname 204 +__SYSCALL(__NR_getsockname, sys_getsockname) +#define __NR_getpeername 205 +__SYSCALL(__NR_getpeername, sys_getpeername) +#define __NR_sendto 206 +__SYSCALL(__NR_sendto, sys_sendto) +#define __NR_recvfrom 207 +__SC_COMP(__NR_recvfrom, sys_recvfrom, compat_sys_recvfrom) +#define __NR_setsockopt 208 +__SC_COMP(__NR_setsockopt, sys_setsockopt, compat_sys_setsockopt) +#define __NR_getsockopt 209 +__SC_COMP(__NR_getsockopt, sys_getsockopt, compat_sys_getsockopt) +#define __NR_shutdown 210 +__SYSCALL(__NR_shutdown, sys_shutdown) +#define __NR_sendmsg 211 +__SC_COMP(__NR_sendmsg, sys_sendmsg, compat_sys_sendmsg) +#define __NR_recvmsg 212 +__SC_COMP(__NR_recvmsg, sys_recvmsg, compat_sys_recvmsg) + +/* mm/filemap.c */ +#define __NR_readahead 213 +__SC_COMP(__NR_readahead, sys_readahead, compat_sys_readahead) + +/* mm/nommu.c, also with MMU */ +#define __NR_brk 214 +__SYSCALL(__NR_brk, sys_brk) +#define __NR_munmap 215 +__SYSCALL(__NR_munmap, sys_munmap) +#define __NR_mremap 216 +__SYSCALL(__NR_mremap, sys_mremap) + +/* security/keys/keyctl.c */ +#define __NR_add_key 217 +__SYSCALL(__NR_add_key, sys_add_key) +#define __NR_request_key 218 +__SYSCALL(__NR_request_key, sys_request_key) +#define __NR_keyctl 219 +__SC_COMP(__NR_keyctl, sys_keyctl, compat_sys_keyctl) + +/* arch/example/kernel/sys_example.c */ +#define __NR_clone 220 +__SYSCALL(__NR_clone, sys_clone) +#define __NR_execve 221 +__SC_COMP(__NR_execve, sys_execve, compat_sys_execve) + +#define __NR3264_mmap 222 +__SC_3264(__NR3264_mmap, sys_mmap2, sys_mmap) +/* mm/fadvise.c */ +#define __NR3264_fadvise64 223 +__SC_COMP(__NR3264_fadvise64, sys_fadvise64_64, compat_sys_fadvise64_64) + +/* mm/, CONFIG_MMU only */ +#ifndef __ARCH_NOMMU +#define __NR_swapon 224 +__SYSCALL(__NR_swapon, sys_swapon) +#define __NR_swapoff 225 +__SYSCALL(__NR_swapoff, sys_swapoff) +#define __NR_mprotect 226 +__SYSCALL(__NR_mprotect, sys_mprotect) +#define __NR_msync 227 +__SYSCALL(__NR_msync, sys_msync) +#define __NR_mlock 228 +__SYSCALL(__NR_mlock, sys_mlock) +#define __NR_munlock 229 +__SYSCALL(__NR_munlock, sys_munlock) +#define __NR_mlockall 230 +__SYSCALL(__NR_mlockall, sys_mlockall) +#define __NR_munlockall 231 +__SYSCALL(__NR_munlockall, sys_munlockall) +#define __NR_mincore 232 +__SYSCALL(__NR_mincore, sys_mincore) +#define __NR_madvise 233 +__SYSCALL(__NR_madvise, sys_madvise) +#define __NR_remap_file_pages 234 +__SYSCALL(__NR_remap_file_pages, sys_remap_file_pages) +#define __NR_mbind 235 +__SC_COMP(__NR_mbind, sys_mbind, compat_sys_mbind) +#define __NR_get_mempolicy 236 +__SC_COMP(__NR_get_mempolicy, sys_get_mempolicy, compat_sys_get_mempolicy) +#define __NR_set_mempolicy 237 +__SC_COMP(__NR_set_mempolicy, sys_set_mempolicy, compat_sys_set_mempolicy) +#define __NR_migrate_pages 238 +__SC_COMP(__NR_migrate_pages, sys_migrate_pages, compat_sys_migrate_pages) +#define __NR_move_pages 239 +__SC_COMP(__NR_move_pages, sys_move_pages, compat_sys_move_pages) +#endif + +#define __NR_rt_tgsigqueueinfo 240 +__SC_COMP(__NR_rt_tgsigqueueinfo, sys_rt_tgsigqueueinfo, \ + compat_sys_rt_tgsigqueueinfo) +#define __NR_perf_event_open 241 +__SYSCALL(__NR_perf_event_open, sys_perf_event_open) +#define __NR_accept4 242 +__SYSCALL(__NR_accept4, sys_accept4) +#define __NR_recvmmsg 243 +__SC_COMP(__NR_recvmmsg, sys_recvmmsg, compat_sys_recvmmsg) + +/* + * Architectures may provide up to 16 syscalls of their own + * starting with this value. + */ +#define __NR_arch_specific_syscall 244 + +#define __NR_wait4 260 +__SC_COMP(__NR_wait4, sys_wait4, compat_sys_wait4) +#define __NR_prlimit64 261 +__SYSCALL(__NR_prlimit64, sys_prlimit64) +#define __NR_fanotify_init 262 +__SYSCALL(__NR_fanotify_init, sys_fanotify_init) +#define __NR_fanotify_mark 263 +__SYSCALL(__NR_fanotify_mark, sys_fanotify_mark) +#define __NR_name_to_handle_at 264 +__SYSCALL(__NR_name_to_handle_at, sys_name_to_handle_at) +#define __NR_open_by_handle_at 265 +__SC_COMP(__NR_open_by_handle_at, sys_open_by_handle_at, \ + compat_sys_open_by_handle_at) +#define __NR_clock_adjtime 266 +__SC_COMP(__NR_clock_adjtime, sys_clock_adjtime, compat_sys_clock_adjtime) +#define __NR_syncfs 267 +__SYSCALL(__NR_syncfs, sys_syncfs) +#define __NR_setns 268 +__SYSCALL(__NR_setns, sys_setns) +#define __NR_sendmmsg 269 +__SC_COMP(__NR_sendmmsg, sys_sendmmsg, compat_sys_sendmmsg) +#define __NR_process_vm_readv 270 +__SC_COMP(__NR_process_vm_readv, sys_process_vm_readv, \ + compat_sys_process_vm_readv) +#define __NR_process_vm_writev 271 +__SC_COMP(__NR_process_vm_writev, sys_process_vm_writev, \ + compat_sys_process_vm_writev) +#define __NR_kcmp 272 +__SYSCALL(__NR_kcmp, sys_kcmp) +#define __NR_finit_module 273 +__SYSCALL(__NR_finit_module, sys_finit_module) +#define __NR_sched_setattr 274 +__SYSCALL(__NR_sched_setattr, sys_sched_setattr) +#define __NR_sched_getattr 275 +__SYSCALL(__NR_sched_getattr, sys_sched_getattr) +#define __NR_renameat2 276 +__SYSCALL(__NR_renameat2, sys_renameat2) +#define __NR_seccomp 277 +__SYSCALL(__NR_seccomp, sys_seccomp) +#define __NR_getrandom 278 +__SYSCALL(__NR_getrandom, sys_getrandom) +#define __NR_memfd_create 279 +__SYSCALL(__NR_memfd_create, sys_memfd_create) +#define __NR_bpf 280 +__SYSCALL(__NR_bpf, sys_bpf) +#define __NR_execveat 281 +__SC_COMP(__NR_execveat, sys_execveat, compat_sys_execveat) +#define __NR_userfaultfd 282 +__SYSCALL(__NR_userfaultfd, sys_userfaultfd) +#define __NR_membarrier 283 +__SYSCALL(__NR_membarrier, sys_membarrier) +#define __NR_mlock2 284 +__SYSCALL(__NR_mlock2, sys_mlock2) +#define __NR_copy_file_range 285 +__SYSCALL(__NR_copy_file_range, sys_copy_file_range) +#define __NR_preadv2 286 +__SC_COMP(__NR_preadv2, sys_preadv2, compat_sys_preadv2) +#define __NR_pwritev2 287 +__SC_COMP(__NR_pwritev2, sys_pwritev2, compat_sys_pwritev2) +#define __NR_pkey_mprotect 288 +__SYSCALL(__NR_pkey_mprotect, sys_pkey_mprotect) +#define __NR_pkey_alloc 289 +__SYSCALL(__NR_pkey_alloc, sys_pkey_alloc) +#define __NR_pkey_free 290 +__SYSCALL(__NR_pkey_free, sys_pkey_free) +#define __NR_statx 291 +__SYSCALL(__NR_statx, sys_statx) +#define __NR_io_pgetevents 292 +__SC_COMP(__NR_io_pgetevents, sys_io_pgetevents, compat_sys_io_pgetevents) + +#undef __NR_syscalls +#define __NR_syscalls 293 + +/* + * 32 bit systems traditionally used different + * syscalls for off_t and loff_t arguments, while + * 64 bit systems only need the off_t version. + * For new 32 bit platforms, there is no need to + * implement the old 32 bit off_t syscalls, so + * they take different names. + * Here we map the numbers so that both versions + * use the same syscall table layout. + */ +#if __BITS_PER_LONG == 64 && !defined(__SYSCALL_COMPAT) +#define __NR_fcntl __NR3264_fcntl +#define __NR_statfs __NR3264_statfs +#define __NR_fstatfs __NR3264_fstatfs +#define __NR_truncate __NR3264_truncate +#define __NR_ftruncate __NR3264_ftruncate +#define __NR_lseek __NR3264_lseek +#define __NR_sendfile __NR3264_sendfile +#define __NR_newfstatat __NR3264_fstatat +#define __NR_fstat __NR3264_fstat +#define __NR_mmap __NR3264_mmap +#define __NR_fadvise64 __NR3264_fadvise64 +#ifdef __NR3264_stat +#define __NR_stat __NR3264_stat +#define __NR_lstat __NR3264_lstat +#endif +#else +#define __NR_fcntl64 __NR3264_fcntl +#define __NR_statfs64 __NR3264_statfs +#define __NR_fstatfs64 __NR3264_fstatfs +#define __NR_truncate64 __NR3264_truncate +#define __NR_ftruncate64 __NR3264_ftruncate +#define __NR_llseek __NR3264_lseek +#define __NR_sendfile64 __NR3264_sendfile +#define __NR_fstatat64 __NR3264_fstatat +#define __NR_fstat64 __NR3264_fstat +#define __NR_mmap2 __NR3264_mmap +#define __NR_fadvise64_64 __NR3264_fadvise64 +#ifdef __NR3264_stat +#define __NR_stat64 __NR3264_stat +#define __NR_lstat64 __NR3264_lstat +#endif +#endif diff --git a/tools/include/uapi/linux/in.h b/tools/include/uapi/linux/in.h new file mode 100644 index 000000000000..48e8a225b985 --- /dev/null +++ b/tools/include/uapi/linux/in.h @@ -0,0 +1,301 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ +/* + * INET An implementation of the TCP/IP protocol suite for the LINUX + * operating system. INET is implemented using the BSD Socket + * interface as the means of communication with the user level. + * + * Definitions of the Internet Protocol. + * + * Version: @(#)in.h 1.0.1 04/21/93 + * + * Authors: Original taken from the GNU Project <netinet/in.h> file. + * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ +#ifndef _UAPI_LINUX_IN_H +#define _UAPI_LINUX_IN_H + +#include <linux/types.h> +#include <linux/libc-compat.h> +#include <linux/socket.h> + +#if __UAPI_DEF_IN_IPPROTO +/* Standard well-defined IP protocols. */ +enum { + IPPROTO_IP = 0, /* Dummy protocol for TCP */ +#define IPPROTO_IP IPPROTO_IP + IPPROTO_ICMP = 1, /* Internet Control Message Protocol */ +#define IPPROTO_ICMP IPPROTO_ICMP + IPPROTO_IGMP = 2, /* Internet Group Management Protocol */ +#define IPPROTO_IGMP IPPROTO_IGMP + IPPROTO_IPIP = 4, /* IPIP tunnels (older KA9Q tunnels use 94) */ +#define IPPROTO_IPIP IPPROTO_IPIP + IPPROTO_TCP = 6, /* Transmission Control Protocol */ +#define IPPROTO_TCP IPPROTO_TCP + IPPROTO_EGP = 8, /* Exterior Gateway Protocol */ +#define IPPROTO_EGP IPPROTO_EGP + IPPROTO_PUP = 12, /* PUP protocol */ +#define IPPROTO_PUP IPPROTO_PUP + IPPROTO_UDP = 17, /* User Datagram Protocol */ +#define IPPROTO_UDP IPPROTO_UDP + IPPROTO_IDP = 22, /* XNS IDP protocol */ +#define IPPROTO_IDP IPPROTO_IDP + IPPROTO_TP = 29, /* SO Transport Protocol Class 4 */ +#define IPPROTO_TP IPPROTO_TP + IPPROTO_DCCP = 33, /* Datagram Congestion Control Protocol */ +#define IPPROTO_DCCP IPPROTO_DCCP + IPPROTO_IPV6 = 41, /* IPv6-in-IPv4 tunnelling */ +#define IPPROTO_IPV6 IPPROTO_IPV6 + IPPROTO_RSVP = 46, /* RSVP Protocol */ +#define IPPROTO_RSVP IPPROTO_RSVP + IPPROTO_GRE = 47, /* Cisco GRE tunnels (rfc 1701,1702) */ +#define IPPROTO_GRE IPPROTO_GRE + IPPROTO_ESP = 50, /* Encapsulation Security Payload protocol */ +#define IPPROTO_ESP IPPROTO_ESP + IPPROTO_AH = 51, /* Authentication Header protocol */ +#define IPPROTO_AH IPPROTO_AH + IPPROTO_MTP = 92, /* Multicast Transport Protocol */ +#define IPPROTO_MTP IPPROTO_MTP + IPPROTO_BEETPH = 94, /* IP option pseudo header for BEET */ +#define IPPROTO_BEETPH IPPROTO_BEETPH + IPPROTO_ENCAP = 98, /* Encapsulation Header */ +#define IPPROTO_ENCAP IPPROTO_ENCAP + IPPROTO_PIM = 103, /* Protocol Independent Multicast */ +#define IPPROTO_PIM IPPROTO_PIM + IPPROTO_COMP = 108, /* Compression Header Protocol */ +#define IPPROTO_COMP IPPROTO_COMP + IPPROTO_SCTP = 132, /* Stream Control Transport Protocol */ +#define IPPROTO_SCTP IPPROTO_SCTP + IPPROTO_UDPLITE = 136, /* UDP-Lite (RFC 3828) */ +#define IPPROTO_UDPLITE IPPROTO_UDPLITE + IPPROTO_MPLS = 137, /* MPLS in IP (RFC 4023) */ +#define IPPROTO_MPLS IPPROTO_MPLS + IPPROTO_RAW = 255, /* Raw IP packets */ +#define IPPROTO_RAW IPPROTO_RAW + IPPROTO_MAX +}; +#endif + +#if __UAPI_DEF_IN_ADDR +/* Internet address. */ +struct in_addr { + __be32 s_addr; +}; +#endif + +#define IP_TOS 1 +#define IP_TTL 2 +#define IP_HDRINCL 3 +#define IP_OPTIONS 4 +#define IP_ROUTER_ALERT 5 +#define IP_RECVOPTS 6 +#define IP_RETOPTS 7 +#define IP_PKTINFO 8 +#define IP_PKTOPTIONS 9 +#define IP_MTU_DISCOVER 10 +#define IP_RECVERR 11 +#define IP_RECVTTL 12 +#define IP_RECVTOS 13 +#define IP_MTU 14 +#define IP_FREEBIND 15 +#define IP_IPSEC_POLICY 16 +#define IP_XFRM_POLICY 17 +#define IP_PASSSEC 18 +#define IP_TRANSPARENT 19 + +/* BSD compatibility */ +#define IP_RECVRETOPTS IP_RETOPTS + +/* TProxy original addresses */ +#define IP_ORIGDSTADDR 20 +#define IP_RECVORIGDSTADDR IP_ORIGDSTADDR + +#define IP_MINTTL 21 +#define IP_NODEFRAG 22 +#define IP_CHECKSUM 23 +#define IP_BIND_ADDRESS_NO_PORT 24 +#define IP_RECVFRAGSIZE 25 + +/* IP_MTU_DISCOVER values */ +#define IP_PMTUDISC_DONT 0 /* Never send DF frames */ +#define IP_PMTUDISC_WANT 1 /* Use per route hints */ +#define IP_PMTUDISC_DO 2 /* Always DF */ +#define IP_PMTUDISC_PROBE 3 /* Ignore dst pmtu */ +/* Always use interface mtu (ignores dst pmtu) but don't set DF flag. + * Also incoming ICMP frag_needed notifications will be ignored on + * this socket to prevent accepting spoofed ones. + */ +#define IP_PMTUDISC_INTERFACE 4 +/* weaker version of IP_PMTUDISC_INTERFACE, which allos packets to get + * fragmented if they exeed the interface mtu + */ +#define IP_PMTUDISC_OMIT 5 + +#define IP_MULTICAST_IF 32 +#define IP_MULTICAST_TTL 33 +#define IP_MULTICAST_LOOP 34 +#define IP_ADD_MEMBERSHIP 35 +#define IP_DROP_MEMBERSHIP 36 +#define IP_UNBLOCK_SOURCE 37 +#define IP_BLOCK_SOURCE 38 +#define IP_ADD_SOURCE_MEMBERSHIP 39 +#define IP_DROP_SOURCE_MEMBERSHIP 40 +#define IP_MSFILTER 41 +#define MCAST_JOIN_GROUP 42 +#define MCAST_BLOCK_SOURCE 43 +#define MCAST_UNBLOCK_SOURCE 44 +#define MCAST_LEAVE_GROUP 45 +#define MCAST_JOIN_SOURCE_GROUP 46 +#define MCAST_LEAVE_SOURCE_GROUP 47 +#define MCAST_MSFILTER 48 +#define IP_MULTICAST_ALL 49 +#define IP_UNICAST_IF 50 + +#define MCAST_EXCLUDE 0 +#define MCAST_INCLUDE 1 + +/* These need to appear somewhere around here */ +#define IP_DEFAULT_MULTICAST_TTL 1 +#define IP_DEFAULT_MULTICAST_LOOP 1 + +/* Request struct for multicast socket ops */ + +#if __UAPI_DEF_IP_MREQ +struct ip_mreq { + struct in_addr imr_multiaddr; /* IP multicast address of group */ + struct in_addr imr_interface; /* local IP address of interface */ +}; + +struct ip_mreqn { + struct in_addr imr_multiaddr; /* IP multicast address of group */ + struct in_addr imr_address; /* local IP address of interface */ + int imr_ifindex; /* Interface index */ +}; + +struct ip_mreq_source { + __be32 imr_multiaddr; + __be32 imr_interface; + __be32 imr_sourceaddr; +}; + +struct ip_msfilter { + __be32 imsf_multiaddr; + __be32 imsf_interface; + __u32 imsf_fmode; + __u32 imsf_numsrc; + __be32 imsf_slist[1]; +}; + +#define IP_MSFILTER_SIZE(numsrc) \ + (sizeof(struct ip_msfilter) - sizeof(__u32) \ + + (numsrc) * sizeof(__u32)) + +struct group_req { + __u32 gr_interface; /* interface index */ + struct __kernel_sockaddr_storage gr_group; /* group address */ +}; + +struct group_source_req { + __u32 gsr_interface; /* interface index */ + struct __kernel_sockaddr_storage gsr_group; /* group address */ + struct __kernel_sockaddr_storage gsr_source; /* source address */ +}; + +struct group_filter { + __u32 gf_interface; /* interface index */ + struct __kernel_sockaddr_storage gf_group; /* multicast address */ + __u32 gf_fmode; /* filter mode */ + __u32 gf_numsrc; /* number of sources */ + struct __kernel_sockaddr_storage gf_slist[1]; /* interface index */ +}; + +#define GROUP_FILTER_SIZE(numsrc) \ + (sizeof(struct group_filter) - sizeof(struct __kernel_sockaddr_storage) \ + + (numsrc) * sizeof(struct __kernel_sockaddr_storage)) +#endif + +#if __UAPI_DEF_IN_PKTINFO +struct in_pktinfo { + int ipi_ifindex; + struct in_addr ipi_spec_dst; + struct in_addr ipi_addr; +}; +#endif + +/* Structure describing an Internet (IP) socket address. */ +#if __UAPI_DEF_SOCKADDR_IN +#define __SOCK_SIZE__ 16 /* sizeof(struct sockaddr) */ +struct sockaddr_in { + __kernel_sa_family_t sin_family; /* Address family */ + __be16 sin_port; /* Port number */ + struct in_addr sin_addr; /* Internet address */ + + /* Pad to size of `struct sockaddr'. */ + unsigned char __pad[__SOCK_SIZE__ - sizeof(short int) - + sizeof(unsigned short int) - sizeof(struct in_addr)]; +}; +#define sin_zero __pad /* for BSD UNIX comp. -FvK */ +#endif + +#if __UAPI_DEF_IN_CLASS +/* + * Definitions of the bits in an Internet address integer. + * On subnets, host and network parts are found according + * to the subnet mask, not these masks. + */ +#define IN_CLASSA(a) ((((long int) (a)) & 0x80000000) == 0) +#define IN_CLASSA_NET 0xff000000 +#define IN_CLASSA_NSHIFT 24 +#define IN_CLASSA_HOST (0xffffffff & ~IN_CLASSA_NET) +#define IN_CLASSA_MAX 128 + +#define IN_CLASSB(a) ((((long int) (a)) & 0xc0000000) == 0x80000000) +#define IN_CLASSB_NET 0xffff0000 +#define IN_CLASSB_NSHIFT 16 +#define IN_CLASSB_HOST (0xffffffff & ~IN_CLASSB_NET) +#define IN_CLASSB_MAX 65536 + +#define IN_CLASSC(a) ((((long int) (a)) & 0xe0000000) == 0xc0000000) +#define IN_CLASSC_NET 0xffffff00 +#define IN_CLASSC_NSHIFT 8 +#define IN_CLASSC_HOST (0xffffffff & ~IN_CLASSC_NET) + +#define IN_CLASSD(a) ((((long int) (a)) & 0xf0000000) == 0xe0000000) +#define IN_MULTICAST(a) IN_CLASSD(a) +#define IN_MULTICAST_NET 0xF0000000 + +#define IN_EXPERIMENTAL(a) ((((long int) (a)) & 0xf0000000) == 0xf0000000) +#define IN_BADCLASS(a) IN_EXPERIMENTAL((a)) + +/* Address to accept any incoming messages. */ +#define INADDR_ANY ((unsigned long int) 0x00000000) + +/* Address to send to all hosts. */ +#define INADDR_BROADCAST ((unsigned long int) 0xffffffff) + +/* Address indicating an error return. */ +#define INADDR_NONE ((unsigned long int) 0xffffffff) + +/* Network number for local host loopback. */ +#define IN_LOOPBACKNET 127 + +/* Address to loopback in software to local host. */ +#define INADDR_LOOPBACK 0x7f000001 /* 127.0.0.1 */ +#define IN_LOOPBACK(a) ((((long int) (a)) & 0xff000000) == 0x7f000000) + +/* Defines for Multicast INADDR */ +#define INADDR_UNSPEC_GROUP 0xe0000000U /* 224.0.0.0 */ +#define INADDR_ALLHOSTS_GROUP 0xe0000001U /* 224.0.0.1 */ +#define INADDR_ALLRTRS_GROUP 0xe0000002U /* 224.0.0.2 */ +#define INADDR_MAX_LOCAL_GROUP 0xe00000ffU /* 224.0.0.255 */ +#endif + +/* <asm/byteorder.h> contains the htonl type stuff.. */ +#include <asm/byteorder.h> + + +#endif /* _UAPI_LINUX_IN_H */ diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c index 2d270c560df3..c36a3a76986a 100644 --- a/tools/lib/bpf/btf.c +++ b/tools/lib/bpf/btf.c @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +// SPDX-License-Identifier: LGPL-2.1 /* Copyright (c) 2018 Facebook */ #include <stdlib.h> diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h index e2a09a155f84..caac3a404dc5 100644 --- a/tools/lib/bpf/btf.h +++ b/tools/lib/bpf/btf.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: LGPL-2.1 */ /* Copyright (c) 2018 Facebook */ #ifndef __BPF_BTF_H diff --git a/tools/memory-model/Documentation/explanation.txt b/tools/memory-model/Documentation/explanation.txt index 1b09f3175a1f..0cbd1ef8f86d 100644 --- a/tools/memory-model/Documentation/explanation.txt +++ b/tools/memory-model/Documentation/explanation.txt @@ -804,7 +804,7 @@ type of fence: Second, some types of fence affect the way the memory subsystem propagates stores. When a fence instruction is executed on CPU C: - For each other CPU C', smb_wmb() forces all po-earlier stores + For each other CPU C', smp_wmb() forces all po-earlier stores on C to propagate to C' before any po-later stores do. For each other CPU C', any store which propagates to C before diff --git a/tools/memory-model/Documentation/recipes.txt b/tools/memory-model/Documentation/recipes.txt index ee4309a87fc4..af72700cc20a 100644 --- a/tools/memory-model/Documentation/recipes.txt +++ b/tools/memory-model/Documentation/recipes.txt @@ -126,7 +126,7 @@ However, it is not necessarily the case that accesses ordered by locking will be seen as ordered by CPUs not holding that lock. Consider this example: - /* See Z6.0+pooncelock+pooncelock+pombonce.litmus. */ + /* See Z6.0+pooncerelease+poacquirerelease+fencembonceonce.litmus. */ void CPU0(void) { spin_lock(&mylock); @@ -292,7 +292,7 @@ and to use smp_load_acquire() instead of smp_rmb(). However, the older smp_wmb() and smp_rmb() APIs are still heavily used, so it is important to understand their use cases. The general approach is shown below: - /* See MP+wmbonceonce+rmbonceonce.litmus. */ + /* See MP+fencewmbonceonce+fencermbonceonce.litmus. */ void CPU0(void) { WRITE_ONCE(x, 1); @@ -322,9 +322,9 @@ the following write-side code fragment: And the xlog_valid_lsn() function in fs/xfs/xfs_log_priv.h contains the corresponding read-side code fragment: - cur_cycle = ACCESS_ONCE(log->l_curr_cycle); + cur_cycle = READ_ONCE(log->l_curr_cycle); smp_rmb(); - cur_block = ACCESS_ONCE(log->l_curr_block); + cur_block = READ_ONCE(log->l_curr_block); Alternatively, consider the following comment in function perf_output_put_handle() in kernel/events/ring_buffer.c: @@ -360,7 +360,7 @@ can be seen in the LB+poonceonces.litmus litmus test. One way of avoiding the counter-intuitive outcome is through the use of a control dependency paired with a full memory barrier: - /* See LB+ctrlonceonce+mbonceonce.litmus. */ + /* See LB+fencembonceonce+ctrlonceonce.litmus. */ void CPU0(void) { r0 = READ_ONCE(x); @@ -476,7 +476,7 @@ that one CPU first stores to one variable and then loads from a second, while another CPU stores to the second variable and then loads from the first. Preserving order requires nothing less than full barriers: - /* See SB+mbonceonces.litmus. */ + /* See SB+fencembonceonces.litmus. */ void CPU0(void) { WRITE_ONCE(x, 1); diff --git a/tools/memory-model/README b/tools/memory-model/README index 734f7feaa5dc..ee987ce20aae 100644 --- a/tools/memory-model/README +++ b/tools/memory-model/README @@ -35,13 +35,13 @@ BASIC USAGE: HERD7 The memory model is used, in conjunction with "herd7", to exhaustively explore the state space of small litmus tests. -For example, to run SB+mbonceonces.litmus against the memory model: +For example, to run SB+fencembonceonces.litmus against the memory model: - $ herd7 -conf linux-kernel.cfg litmus-tests/SB+mbonceonces.litmus + $ herd7 -conf linux-kernel.cfg litmus-tests/SB+fencembonceonces.litmus Here is the corresponding output: - Test SB+mbonceonces Allowed + Test SB+fencembonceonces Allowed States 3 0:r0=0; 1:r0=1; 0:r0=1; 1:r0=0; @@ -50,8 +50,8 @@ Here is the corresponding output: Witnesses Positive: 0 Negative: 3 Condition exists (0:r0=0 /\ 1:r0=0) - Observation SB+mbonceonces Never 0 3 - Time SB+mbonceonces 0.01 + Observation SB+fencembonceonces Never 0 3 + Time SB+fencembonceonces 0.01 Hash=d66d99523e2cac6b06e66f4c995ebb48 The "Positive: 0 Negative: 3" and the "Never 0 3" each indicate that @@ -67,16 +67,16 @@ BASIC USAGE: KLITMUS7 The "klitmus7" tool converts a litmus test into a Linux kernel module, which may then be loaded and run. -For example, to run SB+mbonceonces.litmus against hardware: +For example, to run SB+fencembonceonces.litmus against hardware: $ mkdir mymodules - $ klitmus7 -o mymodules litmus-tests/SB+mbonceonces.litmus + $ klitmus7 -o mymodules litmus-tests/SB+fencembonceonces.litmus $ cd mymodules ; make $ sudo sh run.sh The corresponding output includes: - Test SB+mbonceonces Allowed + Test SB+fencembonceonces Allowed Histogram (3 states) 644580 :>0:r0=1; 1:r0=0; 644328 :>0:r0=0; 1:r0=1; @@ -86,8 +86,8 @@ The corresponding output includes: Positive: 0, Negative: 2000000 Condition exists (0:r0=0 /\ 1:r0=0) is NOT validated Hash=d66d99523e2cac6b06e66f4c995ebb48 - Observation SB+mbonceonces Never 0 2000000 - Time SB+mbonceonces 0.16 + Observation SB+fencembonceonces Never 0 2000000 + Time SB+fencembonceonces 0.16 The "Positive: 0 Negative: 2000000" and the "Never 0 2000000" indicate that during two million trials, the state specified in this litmus diff --git a/tools/memory-model/linux-kernel.bell b/tools/memory-model/linux-kernel.bell index 64f5740e0e75..b84fb2f67109 100644 --- a/tools/memory-model/linux-kernel.bell +++ b/tools/memory-model/linux-kernel.bell @@ -13,7 +13,7 @@ "Linux-kernel memory consistency model" -enum Accesses = 'once (*READ_ONCE,WRITE_ONCE,ACCESS_ONCE*) || +enum Accesses = 'once (*READ_ONCE,WRITE_ONCE*) || 'release (*smp_store_release*) || 'acquire (*smp_load_acquire*) || 'noreturn (* R of non-return RMW *) diff --git a/tools/memory-model/litmus-tests/IRIW+mbonceonces+OnceOnce.litmus b/tools/memory-model/litmus-tests/IRIW+fencembonceonces+OnceOnce.litmus index 98a3716efa37..e729d2776e89 100644 --- a/tools/memory-model/litmus-tests/IRIW+mbonceonces+OnceOnce.litmus +++ b/tools/memory-model/litmus-tests/IRIW+fencembonceonces+OnceOnce.litmus @@ -1,4 +1,4 @@ -C IRIW+mbonceonces+OnceOnce +C IRIW+fencembonceonces+OnceOnce (* * Result: Never diff --git a/tools/memory-model/litmus-tests/ISA2+pooncelock+pooncelock+pombonce.litmus b/tools/memory-model/litmus-tests/ISA2+pooncelock+pooncelock+pombonce.litmus index 7a39a0aaa976..0f749e419b34 100644 --- a/tools/memory-model/litmus-tests/ISA2+pooncelock+pooncelock+pombonce.litmus +++ b/tools/memory-model/litmus-tests/ISA2+pooncelock+pooncelock+pombonce.litmus @@ -1,4 +1,4 @@ -C ISA2+pooncelock+pooncelock+pombonce.litmus +C ISA2+pooncelock+pooncelock+pombonce (* * Result: Sometimes diff --git a/tools/memory-model/litmus-tests/LB+ctrlonceonce+mbonceonce.litmus b/tools/memory-model/litmus-tests/LB+fencembonceonce+ctrlonceonce.litmus index de6708229dd1..4727f5aaf03b 100644 --- a/tools/memory-model/litmus-tests/LB+ctrlonceonce+mbonceonce.litmus +++ b/tools/memory-model/litmus-tests/LB+fencembonceonce+ctrlonceonce.litmus @@ -1,4 +1,4 @@ -C LB+ctrlonceonce+mbonceonce +C LB+fencembonceonce+ctrlonceonce (* * Result: Never diff --git a/tools/memory-model/litmus-tests/MP+wmbonceonce+rmbonceonce.litmus b/tools/memory-model/litmus-tests/MP+fencewmbonceonce+fencermbonceonce.litmus index c078f38ff27a..a273da9faa6d 100644 --- a/tools/memory-model/litmus-tests/MP+wmbonceonce+rmbonceonce.litmus +++ b/tools/memory-model/litmus-tests/MP+fencewmbonceonce+fencermbonceonce.litmus @@ -1,4 +1,4 @@ -C MP+wmbonceonce+rmbonceonce +C MP+fencewmbonceonce+fencermbonceonce (* * Result: Never diff --git a/tools/memory-model/litmus-tests/R+mbonceonces.litmus b/tools/memory-model/litmus-tests/R+fencembonceonces.litmus index a0e884ad2132..222a0b850b4a 100644 --- a/tools/memory-model/litmus-tests/R+mbonceonces.litmus +++ b/tools/memory-model/litmus-tests/R+fencembonceonces.litmus @@ -1,4 +1,4 @@ -C R+mbonceonces +C R+fencembonceonces (* * Result: Never diff --git a/tools/memory-model/litmus-tests/README b/tools/memory-model/litmus-tests/README index 17eb9a8c222d..4581ec2d3c57 100644 --- a/tools/memory-model/litmus-tests/README +++ b/tools/memory-model/litmus-tests/README @@ -18,7 +18,7 @@ CoWW+poonceonce.litmus Test of write-write coherence, that is, whether or not two successive writes to the same variable are ordered. -IRIW+mbonceonces+OnceOnce.litmus +IRIW+fencembonceonces+OnceOnce.litmus Test of independent reads from independent writes with smp_mb() between each pairs of reads. In other words, is smp_mb() sufficient to cause two different reading processes to agree on @@ -47,7 +47,7 @@ ISA2+pooncerelease+poacquirerelease+poacquireonce.litmus Can a release-acquire chain order a prior store against a later load? -LB+ctrlonceonce+mbonceonce.litmus +LB+fencembonceonce+ctrlonceonce.litmus Does a control dependency and an smp_mb() suffice for the load-buffering litmus test, where each process reads from one of two variables then writes to the other? @@ -88,14 +88,14 @@ MP+porevlocks.litmus As below, but with the first access of the writer process and the second access of reader process protected by a lock. -MP+wmbonceonce+rmbonceonce.litmus +MP+fencewmbonceonce+fencermbonceonce.litmus Does a smp_wmb() (between the stores) and an smp_rmb() (between the loads) suffice for the message-passing litmus test, where one process writes data and then a flag, and the other process reads the flag and then the data. (This is similar to the ISA2 tests, but with two processes instead of three.) -R+mbonceonces.litmus +R+fencembonceonces.litmus This is the fully ordered (via smp_mb()) version of one of the classic counterintuitive litmus tests that illustrates the effects of store propagation delays. @@ -103,7 +103,7 @@ R+mbonceonces.litmus R+poonceonces.litmus As above, but without the smp_mb() invocations. -SB+mbonceonces.litmus +SB+fencembonceonces.litmus This is the fully ordered (again, via smp_mb() version of store buffering, which forms the core of Dekker's mutual-exclusion algorithm. @@ -111,15 +111,24 @@ SB+mbonceonces.litmus SB+poonceonces.litmus As above, but without the smp_mb() invocations. +SB+rfionceonce-poonceonces.litmus + This litmus test demonstrates that LKMM is not fully multicopy + atomic. (Neither is it other multicopy atomic.) This litmus test + also demonstrates the "locations" debugging aid, which designates + additional registers and locations to be printed out in the dump + of final states in the herd7 output. Without the "locations" + statement, only those registers and locations mentioned in the + "exists" clause will be printed. + S+poonceonces.litmus As below, but without the smp_wmb() and acquire load. -S+wmbonceonce+poacquireonce.litmus +S+fencewmbonceonce+poacquireonce.litmus Can a smp_wmb(), instead of a release, and an acquire order a prior store against a subsequent store? WRC+poonceonces+Once.litmus -WRC+pooncerelease+rmbonceonce+Once.litmus +WRC+pooncerelease+fencermbonceonce+Once.litmus These two are members of an extension of the MP litmus-test class in which the first write is moved to a separate process. The second is forbidden because smp_store_release() is @@ -134,7 +143,7 @@ Z6.0+pooncelock+poonceLock+pombonce.litmus As above, but with smp_mb__after_spinlock() immediately following the spin_lock(). -Z6.0+pooncerelease+poacquirerelease+mbonceonce.litmus +Z6.0+pooncerelease+poacquirerelease+fencembonceonce.litmus Is the ordering provided by a release-acquire chain sufficient to make ordering apparent to accesses by a process that does not participate in that release-acquire chain? diff --git a/tools/memory-model/litmus-tests/S+wmbonceonce+poacquireonce.litmus b/tools/memory-model/litmus-tests/S+fencewmbonceonce+poacquireonce.litmus index c53350205d28..18479823cd6c 100644 --- a/tools/memory-model/litmus-tests/S+wmbonceonce+poacquireonce.litmus +++ b/tools/memory-model/litmus-tests/S+fencewmbonceonce+poacquireonce.litmus @@ -1,4 +1,4 @@ -C S+wmbonceonce+poacquireonce +C S+fencewmbonceonce+poacquireonce (* * Result: Never diff --git a/tools/memory-model/litmus-tests/SB+mbonceonces.litmus b/tools/memory-model/litmus-tests/SB+fencembonceonces.litmus index 74b874ffa8da..ed5fff18d223 100644 --- a/tools/memory-model/litmus-tests/SB+mbonceonces.litmus +++ b/tools/memory-model/litmus-tests/SB+fencembonceonces.litmus @@ -1,4 +1,4 @@ -C SB+mbonceonces +C SB+fencembonceonces (* * Result: Never diff --git a/tools/memory-model/litmus-tests/SB+rfionceonce-poonceonces.litmus b/tools/memory-model/litmus-tests/SB+rfionceonce-poonceonces.litmus new file mode 100644 index 000000000000..04a16603660b --- /dev/null +++ b/tools/memory-model/litmus-tests/SB+rfionceonce-poonceonces.litmus @@ -0,0 +1,32 @@ +C SB+rfionceonce-poonceonces + +(* + * Result: Sometimes + * + * This litmus test demonstrates that LKMM is not fully multicopy atomic. + *) + +{} + +P0(int *x, int *y) +{ + int r1; + int r2; + + WRITE_ONCE(*x, 1); + r1 = READ_ONCE(*x); + r2 = READ_ONCE(*y); +} + +P1(int *x, int *y) +{ + int r3; + int r4; + + WRITE_ONCE(*y, 1); + r3 = READ_ONCE(*y); + r4 = READ_ONCE(*x); +} + +locations [0:r1; 1:r3; x; y] (* Debug aid: Print things not in "exists". *) +exists (0:r2=0 /\ 1:r4=0) diff --git a/tools/memory-model/litmus-tests/WRC+pooncerelease+rmbonceonce+Once.litmus b/tools/memory-model/litmus-tests/WRC+pooncerelease+fencermbonceonce+Once.litmus index ad3448b941e6..e9947250d7de 100644 --- a/tools/memory-model/litmus-tests/WRC+pooncerelease+rmbonceonce+Once.litmus +++ b/tools/memory-model/litmus-tests/WRC+pooncerelease+fencermbonceonce+Once.litmus @@ -1,4 +1,4 @@ -C WRC+pooncerelease+rmbonceonce+Once +C WRC+pooncerelease+fencermbonceonce+Once (* * Result: Never diff --git a/tools/memory-model/litmus-tests/Z6.0+pooncerelease+poacquirerelease+mbonceonce.litmus b/tools/memory-model/litmus-tests/Z6.0+pooncerelease+poacquirerelease+fencembonceonce.litmus index a20fc3fafb53..88e70b87a683 100644 --- a/tools/memory-model/litmus-tests/Z6.0+pooncerelease+poacquirerelease+mbonceonce.litmus +++ b/tools/memory-model/litmus-tests/Z6.0+pooncerelease+poacquirerelease+fencembonceonce.litmus @@ -1,4 +1,4 @@ -C Z6.0+pooncerelease+poacquirerelease+mbonceonce +C Z6.0+pooncerelease+poacquirerelease+fencembonceonce (* * Result: Sometimes diff --git a/tools/memory-model/scripts/checkalllitmus.sh b/tools/memory-model/scripts/checkalllitmus.sh index af0aa15ab84e..ca528f9a24d4 100644..100755 --- a/tools/memory-model/scripts/checkalllitmus.sh +++ b/tools/memory-model/scripts/checkalllitmus.sh @@ -9,7 +9,7 @@ # appended. # # Usage: -# sh checkalllitmus.sh [ directory ] +# checkalllitmus.sh [ directory ] # # The LINUX_HERD_OPTIONS environment variable may be used to specify # arguments to herd, whose default is defined by the checklitmus.sh script. diff --git a/tools/memory-model/scripts/checklitmus.sh b/tools/memory-model/scripts/checklitmus.sh index e2e477472844..bf12a75c0719 100644..100755 --- a/tools/memory-model/scripts/checklitmus.sh +++ b/tools/memory-model/scripts/checklitmus.sh @@ -8,7 +8,7 @@ # with ".out" appended. # # Usage: -# sh checklitmus.sh file.litmus +# checklitmus.sh file.litmus # # The LINUX_HERD_OPTIONS environment variable may be used to specify # arguments to herd, which default to "-conf linux-kernel.cfg". Thus, diff --git a/tools/objtool/arch/x86/include/asm/orc_types.h b/tools/objtool/arch/x86/include/asm/orc_types.h index 9c9dc579bd7d..46f516dd80ce 100644 --- a/tools/objtool/arch/x86/include/asm/orc_types.h +++ b/tools/objtool/arch/x86/include/asm/orc_types.h @@ -88,6 +88,7 @@ struct orc_entry { unsigned sp_reg:4; unsigned bp_reg:4; unsigned type:2; + unsigned end:1; } __packed; /* @@ -101,6 +102,7 @@ struct unwind_hint { s16 sp_offset; u8 sp_reg; u8 type; + u8 end; }; #endif /* __ASSEMBLY__ */ diff --git a/tools/objtool/check.c b/tools/objtool/check.c index f4a25bd1871f..2928939b98ec 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -1157,6 +1157,7 @@ static int read_unwind_hints(struct objtool_file *file) cfa->offset = hint->sp_offset; insn->state.type = hint->type; + insn->state.end = hint->end; } return 0; diff --git a/tools/objtool/check.h b/tools/objtool/check.h index c6b68fcb926f..95700a2bcb7c 100644 --- a/tools/objtool/check.h +++ b/tools/objtool/check.h @@ -31,7 +31,7 @@ struct insn_state { int stack_size; unsigned char type; bool bp_scratch; - bool drap; + bool drap, end; int drap_reg, drap_offset; struct cfi_reg vals[CFI_NUM_REGS]; }; diff --git a/tools/objtool/orc_dump.c b/tools/objtool/orc_dump.c index c3343820916a..faa444270ee3 100644 --- a/tools/objtool/orc_dump.c +++ b/tools/objtool/orc_dump.c @@ -203,7 +203,8 @@ int orc_dump(const char *_objname) print_reg(orc[i].bp_reg, orc[i].bp_offset); - printf(" type:%s\n", orc_type_name(orc[i].type)); + printf(" type:%s end:%d\n", + orc_type_name(orc[i].type), orc[i].end); } elf_end(elf); diff --git a/tools/objtool/orc_gen.c b/tools/objtool/orc_gen.c index 18384d9be4e1..3f98dcfbc177 100644 --- a/tools/objtool/orc_gen.c +++ b/tools/objtool/orc_gen.c @@ -31,6 +31,8 @@ int create_orc(struct objtool_file *file) struct cfi_reg *cfa = &insn->state.cfa; struct cfi_reg *bp = &insn->state.regs[CFI_BP]; + orc->end = insn->state.end; + if (cfa->base == CFI_UNDEFINED) { orc->sp_reg = ORC_REG_UNDEFINED; continue; diff --git a/tools/perf/Documentation/perf-list.txt b/tools/perf/Documentation/perf-list.txt index 11300dbe35c5..236b9b97dfdb 100644 --- a/tools/perf/Documentation/perf-list.txt +++ b/tools/perf/Documentation/perf-list.txt @@ -18,6 +18,10 @@ various perf commands with the -e option. OPTIONS ------- +-d:: +--desc:: +Print extra event descriptions. (default) + --no-desc:: Don't print descriptions. @@ -25,11 +29,13 @@ Don't print descriptions. --long-desc:: Print longer event descriptions. +--debug:: +Enable debugging output. + --details:: Print how named events are resolved internally into perf events, and also any extra expressions computed by perf stat. - [[EVENT_MODIFIERS]] EVENT MODIFIERS --------------- @@ -234,7 +240,7 @@ perf also supports group leader sampling using the :S specifier. perf record -e '{cycles,instructions}:S' ... perf report --group -Normally all events in a event group sample, but with :S only +Normally all events in an event group sample, but with :S only the first event (the leader) samples, and it only reads the values of the other events in the group. diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt index 04168da4268e..246dee081efd 100644 --- a/tools/perf/Documentation/perf-record.txt +++ b/tools/perf/Documentation/perf-record.txt @@ -94,7 +94,7 @@ OPTIONS "perf report" to view group events together. --filter=<filter>:: - Event filter. This option should follow a event selector (-e) which + Event filter. This option should follow an event selector (-e) which selects either tracepoint event(s) or a hardware trace PMU (e.g. Intel PT or CoreSight). @@ -153,7 +153,7 @@ OPTIONS --exclude-perf:: Don't record events issued by perf itself. This option should follow - a event selector (-e) which selects tracepoint event(s). It adds a + an event selector (-e) which selects tracepoint event(s). It adds a filter expression 'common_pid != $PERFPID' to filters. If other '--filter' exists, the new filter expression will be combined with them by '&&'. diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index f5a3b402589e..f6d1a03c7523 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -54,6 +54,8 @@ endif ifeq ($(SRCARCH),arm64) NO_PERF_REGS := 0 + NO_SYSCALL_TABLE := 0 + CFLAGS += -I$(OUTPUT)arch/arm64/include/generated LIBUNWIND_LIBS = -lunwind -lunwind-aarch64 endif @@ -905,8 +907,8 @@ bindir = $(abspath $(prefix)/$(bindir_relative)) mandir = share/man infodir = share/info perfexecdir = libexec/perf-core -perf_include_dir = lib/include/perf -perf_examples_dir = lib/examples/perf +perf_include_dir = lib/perf/include +perf_examples_dir = lib/perf/examples sharedir = $(prefix)/share template_dir = share/perf-core/templates STRACE_GROUPS_DIR = share/perf-core/strace/groups diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index ecc9fc952655..b3d1b12a5081 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -384,6 +384,8 @@ export INSTALL SHELL_PATH SHELL = $(SHELL_PATH) +linux_uapi_dir := $(srctree)/tools/include/uapi/linux + beauty_outdir := $(OUTPUT)trace/beauty/generated beauty_ioctl_outdir := $(beauty_outdir)/ioctl drm_ioctl_array := $(beauty_ioctl_outdir)/drm_ioctl_array.c @@ -431,6 +433,12 @@ kvm_ioctl_tbl := $(srctree)/tools/perf/trace/beauty/kvm_ioctl.sh $(kvm_ioctl_array): $(kvm_hdr_dir)/kvm.h $(kvm_ioctl_tbl) $(Q)$(SHELL) '$(kvm_ioctl_tbl)' $(kvm_hdr_dir) > $@ +socket_ipproto_array := $(beauty_outdir)/socket_ipproto_array.c +socket_ipproto_tbl := $(srctree)/tools/perf/trace/beauty/socket_ipproto.sh + +$(socket_ipproto_array): $(linux_uapi_dir)/in.h $(socket_ipproto_tbl) + $(Q)$(SHELL) '$(socket_ipproto_tbl)' $(linux_uapi_dir) > $@ + vhost_virtio_ioctl_array := $(beauty_ioctl_outdir)/vhost_virtio_ioctl_array.c vhost_virtio_hdr_dir := $(srctree)/tools/include/uapi/linux vhost_virtio_ioctl_tbl := $(srctree)/tools/perf/trace/beauty/vhost_virtio_ioctl.sh @@ -566,6 +574,7 @@ prepare: $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)common-cmds.h archheaders $(drm_ioc $(sndrv_ctl_ioctl_array) \ $(kcmp_type_array) \ $(kvm_ioctl_array) \ + $(socket_ipproto_array) \ $(vhost_virtio_ioctl_array) \ $(madvise_behavior_array) \ $(perf_ioctl_array) \ @@ -860,6 +869,7 @@ clean:: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clea $(OUTPUT)$(sndrv_pcm_ioctl_array) \ $(OUTPUT)$(kvm_ioctl_array) \ $(OUTPUT)$(kcmp_type_array) \ + $(OUTPUT)$(socket_ipproto_array) \ $(OUTPUT)$(vhost_virtio_ioctl_array) \ $(OUTPUT)$(perf_ioctl_array) \ $(OUTPUT)$(prctl_option_array) \ diff --git a/tools/perf/arch/arm64/Makefile b/tools/perf/arch/arm64/Makefile index 91de4860faad..f013b115dc86 100644 --- a/tools/perf/arch/arm64/Makefile +++ b/tools/perf/arch/arm64/Makefile @@ -4,3 +4,24 @@ PERF_HAVE_DWARF_REGS := 1 endif PERF_HAVE_JITDUMP := 1 PERF_HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET := 1 + +# +# Syscall table generation for perf +# + +out := $(OUTPUT)arch/arm64/include/generated/asm +header := $(out)/syscalls.c +sysdef := $(srctree)/tools/include/uapi/asm-generic/unistd.h +sysprf := $(srctree)/tools/perf/arch/arm64/entry/syscalls/ +systbl := $(sysprf)/mksyscalltbl + +# Create output directory if not already present +_dummy := $(shell [ -d '$(out)' ] || mkdir -p '$(out)') + +$(header): $(sysdef) $(systbl) + $(Q)$(SHELL) '$(systbl)' '$(CC)' '$(HOSTCC)' $(sysdef) > $@ + +clean:: + $(call QUIET_CLEAN, arm64) $(RM) $(header) + +archheaders: $(header) diff --git a/tools/perf/arch/arm64/entry/syscalls/mksyscalltbl b/tools/perf/arch/arm64/entry/syscalls/mksyscalltbl new file mode 100755 index 000000000000..52e197317d3e --- /dev/null +++ b/tools/perf/arch/arm64/entry/syscalls/mksyscalltbl @@ -0,0 +1,62 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 +# +# Generate system call table for perf. Derived from +# powerpc script. +# +# Copyright IBM Corp. 2017 +# Author(s): Hendrik Brueckner <brueckner@linux.vnet.ibm.com> +# Changed by: Ravi Bangoria <ravi.bangoria@linux.vnet.ibm.com> +# Changed by: Kim Phillips <kim.phillips@arm.com> + +gcc=$1 +hostcc=$2 +input=$3 + +if ! test -r $input; then + echo "Could not read input file" >&2 + exit 1 +fi + +create_table_from_c() +{ + local sc nr last_sc + + create_table_exe=`mktemp /tmp/create-table-XXXXXX` + + { + + cat <<-_EoHEADER + #include <stdio.h> + #define __ARCH_WANT_RENAMEAT + #include "$input" + int main(int argc, char *argv[]) + { + _EoHEADER + + while read sc nr; do + printf "%s\n" " printf(\"\\t[%d] = \\\"$sc\\\",\\n\", __NR_$sc);" + last_sc=$sc + done + + printf "%s\n" " printf(\"#define SYSCALLTBL_ARM64_MAX_ID %d\\n\", __NR_$last_sc);" + printf "}\n" + + } | $hostcc -o $create_table_exe -x c - + + $create_table_exe + + rm -f $create_table_exe +} + +create_table() +{ + echo "static const char *syscalltbl_arm64[] = {" + create_table_from_c + echo "};" +} + +$gcc -E -dM -x c $input \ + |sed -ne 's/^#define __NR_//p' \ + |sort -t' ' -k2 -nu \ + |create_table diff --git a/tools/perf/arch/powerpc/util/skip-callchain-idx.c b/tools/perf/arch/powerpc/util/skip-callchain-idx.c index ef5d59a5742e..7c6eeb4633fe 100644 --- a/tools/perf/arch/powerpc/util/skip-callchain-idx.c +++ b/tools/perf/arch/powerpc/util/skip-callchain-idx.c @@ -58,9 +58,13 @@ static int check_return_reg(int ra_regno, Dwarf_Frame *frame) } /* - * Check if return address is on the stack. + * Check if return address is on the stack. If return address + * is in a register (typically R0), it is yet to be saved on + * the stack. */ - if (nops != 0 || ops != NULL) + if ((nops != 0 || ops != NULL) && + !(nops == 1 && ops[0].atom == DW_OP_regx && + ops[0].number2 == 0 && ops[0].offset == 0)) return 0; /* @@ -246,7 +250,7 @@ int arch_skip_callchain_idx(struct thread *thread, struct ip_callchain *chain) if (!chain || chain->nr < 3) return skip_slot; - ip = chain->ips[2]; + ip = chain->ips[1]; thread__find_symbol(thread, PERF_RECORD_MISC_USER, ip, &al); diff --git a/tools/perf/arch/s390/util/kvm-stat.c b/tools/perf/arch/s390/util/kvm-stat.c index d233e2eb9592..aaabab5e2830 100644 --- a/tools/perf/arch/s390/util/kvm-stat.c +++ b/tools/perf/arch/s390/util/kvm-stat.c @@ -102,7 +102,7 @@ const char * const kvm_skip_events[] = { int cpu_isa_init(struct perf_kvm_stat *kvm, const char *cpuid) { - if (strstr(cpuid, "IBM/S390")) { + if (strstr(cpuid, "IBM")) { kvm->exit_reasons = sie_exit_reasons; kvm->exit_reasons_isa = "SIE"; } else diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c index 6a8738f7ead3..f3aa9d02a5ab 100644 --- a/tools/perf/builtin-c2c.c +++ b/tools/perf/builtin-c2c.c @@ -2193,7 +2193,7 @@ static void print_cacheline(struct c2c_hists *c2c_hists, fprintf(out, "%s\n", bf); fprintf(out, " -------------------------------------------------------------\n"); - hists__fprintf(&c2c_hists->hists, false, 0, 0, 0, out, true); + hists__fprintf(&c2c_hists->hists, false, 0, 0, 0, out, false); } static void print_pareto(FILE *out) @@ -2268,7 +2268,7 @@ static void perf_c2c__hists_fprintf(FILE *out, struct perf_session *session) fprintf(out, "=================================================\n"); fprintf(out, "#\n"); - hists__fprintf(&c2c.hists.hists, true, 0, 0, 0, stdout, false); + hists__fprintf(&c2c.hists.hists, true, 0, 0, 0, stdout, true); fprintf(out, "\n"); fprintf(out, "=================================================\n"); @@ -2349,6 +2349,9 @@ static int perf_c2c__browse_cacheline(struct hist_entry *he) " s Toggle full length of symbol and source line columns \n" " q Return back to cacheline list \n"; + if (!he) + return 0; + /* Display compact version first. */ c2c.symbol_full = false; diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c index d660cb7b222b..39db2ee32d48 100644 --- a/tools/perf/builtin-diff.c +++ b/tools/perf/builtin-diff.c @@ -696,7 +696,7 @@ static void hists__process(struct hists *hists) hists__output_resort(hists, NULL); hists__fprintf(hists, !quiet, 0, 0, 0, stdout, - symbol_conf.use_callchain); + !symbol_conf.use_callchain); } static void data__fprintf(void) diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index c04dc7b53797..02f7a3c27761 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -478,8 +478,8 @@ static int perf_evlist__tty_browse_hists(struct perf_evlist *evlist, hists__fprintf_nr_sample_events(hists, rep, evname, stdout); hists__fprintf(hists, !quiet, 0, 0, rep->min_percent, stdout, - symbol_conf.use_callchain || - symbol_conf.show_branchflag_count); + !(symbol_conf.use_callchain || + symbol_conf.show_branchflag_count)); fprintf(stdout, "\n\n"); } diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 05be023c3f0e..d097b5b47eb8 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -296,18 +296,6 @@ static int create_perf_stat_counter(struct perf_evsel *evsel) return perf_evsel__open_per_thread(evsel, evsel_list->threads); } -/* - * Does the counter have nsecs as a unit? - */ -static inline int nsec_counter(struct perf_evsel *evsel) -{ - if (perf_evsel__match(evsel, SOFTWARE, SW_CPU_CLOCK) || - perf_evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK)) - return 1; - - return 0; -} - static int process_synthesized_event(struct perf_tool *tool __maybe_unused, union perf_event *event, struct perf_sample *sample __maybe_unused, @@ -1058,34 +1046,6 @@ static void print_metric_header(void *ctx, const char *color __maybe_unused, fprintf(os->fh, "%*s ", metric_only_len, unit); } -static void nsec_printout(int id, int nr, struct perf_evsel *evsel, double avg) -{ - FILE *output = stat_config.output; - double msecs = avg / NSEC_PER_MSEC; - const char *fmt_v, *fmt_n; - char name[25]; - - fmt_v = csv_output ? "%.6f%s" : "%18.6f%s"; - fmt_n = csv_output ? "%s" : "%-25s"; - - aggr_printout(evsel, id, nr); - - scnprintf(name, sizeof(name), "%s%s", - perf_evsel__name(evsel), csv_output ? "" : " (msec)"); - - fprintf(output, fmt_v, msecs, csv_sep); - - if (csv_output) - fprintf(output, "%s%s", evsel->unit, csv_sep); - else - fprintf(output, "%-*s%s", unit_width, evsel->unit, csv_sep); - - fprintf(output, fmt_n, name); - - if (evsel->cgrp) - fprintf(output, "%s%s", csv_sep, evsel->cgrp->name); -} - static int first_shadow_cpu(struct perf_evsel *evsel, int id) { int i; @@ -1241,11 +1201,7 @@ static void printout(int id, int nr, struct perf_evsel *counter, double uval, return; } - if (metric_only) - /* nothing */; - else if (nsec_counter(counter)) - nsec_printout(id, nr, counter, uval); - else + if (!metric_only) abs_printout(id, nr, counter, uval); out.print_metric = pm; @@ -1331,7 +1287,7 @@ static void collect_all_aliases(struct perf_evsel *counter, alias->scale != counter->scale || alias->cgrp != counter->cgrp || strcmp(alias->unit, counter->unit) || - nsec_counter(alias) != nsec_counter(counter)) + perf_evsel__is_clock(alias) != perf_evsel__is_clock(counter)) break; alias->merged_stat = true; cb(alias, data, false); @@ -2449,6 +2405,18 @@ static int add_default_attributes(void) return 0; if (transaction_run) { + /* Handle -T as -M transaction. Once platform specific metrics + * support has been added to the json files, all archictures + * will use this approach. To determine transaction support + * on an architecture test for such a metric name. + */ + if (metricgroup__has_metric("transaction")) { + struct option opt = { .value = &evsel_list }; + + return metricgroup__parse_groups(&opt, "transaction", + &metric_events); + } + if (pmu_have_event("cpu", "cycles-ct") && pmu_have_event("cpu", "el-start")) err = parse_events(evsel_list, transaction_attrs, diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index ffdc2769ff9f..d21d8751e749 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -307,7 +307,7 @@ static void perf_top__print_sym_table(struct perf_top *top) hists__output_recalc_col_len(hists, top->print_entries - printed); putchar('\n'); hists__fprintf(hists, false, top->print_entries - printed, win_width, - top->min_percent, stdout, symbol_conf.use_callchain); + top->min_percent, stdout, !symbol_conf.use_callchain); } static void prompt_integer(int *target, const char *msg) diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index 6a748eca2edb..88561eed7950 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -291,7 +291,7 @@ size_t strarray__scnprintf(struct strarray *sa, char *bf, size_t size, const cha { int idx = val - sa->offset; - if (idx < 0 || idx >= sa->nr_entries) + if (idx < 0 || idx >= sa->nr_entries || sa->entries[idx] == NULL) return scnprintf(bf, size, intfmt, val); return scnprintf(bf, size, "%s", sa->entries[idx]); @@ -761,10 +761,12 @@ static struct syscall_fmt { .arg = { [0] = STRARRAY(resource, rlimit_resources), }, }, { .name = "socket", .arg = { [0] = STRARRAY(family, socket_families), - [1] = { .scnprintf = SCA_SK_TYPE, /* type */ }, }, }, + [1] = { .scnprintf = SCA_SK_TYPE, /* type */ }, + [2] = { .scnprintf = SCA_SK_PROTO, /* protocol */ }, }, }, { .name = "socketpair", .arg = { [0] = STRARRAY(family, socket_families), - [1] = { .scnprintf = SCA_SK_TYPE, /* type */ }, }, }, + [1] = { .scnprintf = SCA_SK_TYPE, /* type */ }, + [2] = { .scnprintf = SCA_SK_PROTO, /* protocol */ }, }, }, { .name = "stat", .alias = "newstat", }, { .name = "statx", .arg = { [0] = { .scnprintf = SCA_FDAT, /* fdat */ }, @@ -2990,6 +2992,7 @@ static int trace__parse_events_option(const struct option *opt, const char *str, if (trace__validate_ev_qualifier(trace)) goto out; + trace->trace_syscalls = true; } err = 0; @@ -3045,7 +3048,7 @@ int cmd_trace(int argc, const char **argv) }, .output = stderr, .show_comm = true, - .trace_syscalls = true, + .trace_syscalls = false, .kernel_syscallchains = false, .max_stack = UINT_MAX, }; @@ -3191,13 +3194,7 @@ int cmd_trace(int argc, const char **argv) if (!trace.trace_syscalls && !trace.trace_pgfaults && trace.evlist->nr_entries == 0 /* Was --events used? */) { - pr_err("Please specify something to trace.\n"); - return -1; - } - - if (!trace.trace_syscalls && trace.ev_qualifier) { - pr_err("The -e option can't be used with --no-syscalls.\n"); - goto out; + trace.trace_syscalls = true; } if (output_name != NULL) { diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh index 10f333e2e825..de28466c0186 100755 --- a/tools/perf/check-headers.sh +++ b/tools/perf/check-headers.sh @@ -7,6 +7,7 @@ include/uapi/drm/i915_drm.h include/uapi/linux/fcntl.h include/uapi/linux/kcmp.h include/uapi/linux/kvm.h +include/uapi/linux/in.h include/uapi/linux/perf_event.h include/uapi/linux/prctl.h include/uapi/linux/sched.h @@ -35,6 +36,7 @@ arch/s390/include/uapi/asm/ptrace.h arch/s390/include/uapi/asm/sie.h arch/arm/include/uapi/asm/kvm.h arch/arm64/include/uapi/asm/kvm.h +arch/arm64/include/uapi/asm/unistd.h arch/alpha/include/uapi/asm/errno.h arch/mips/include/asm/errno.h arch/mips/include/uapi/asm/errno.h @@ -53,6 +55,7 @@ include/uapi/asm-generic/errno.h include/uapi/asm-generic/errno-base.h include/uapi/asm-generic/ioctls.h include/uapi/asm-generic/mman-common.h +include/uapi/asm-generic/unistd.h ' check_2 () { diff --git a/tools/perf/include/bpf/bpf.h b/tools/perf/include/bpf/bpf.h index dd764ad5efdf..a63aa6241b7f 100644 --- a/tools/perf/include/bpf/bpf.h +++ b/tools/perf/include/bpf/bpf.h @@ -1,6 +1,9 @@ // SPDX-License-Identifier: GPL-2.0 #ifndef _PERF_BPF_H #define _PERF_BPF_H + +#include <uapi/linux/bpf.h> + #define SEC(NAME) __attribute__((section(NAME), used)) #define probe(function, vars) \ diff --git a/tools/perf/perf.h b/tools/perf/perf.h index d215714f48df..21bf7f5a3cf5 100644 --- a/tools/perf/perf.h +++ b/tools/perf/perf.h @@ -25,7 +25,9 @@ static inline unsigned long long rdclock(void) return ts.tv_sec * 1000000000ULL + ts.tv_nsec; } +#ifndef MAX_NR_CPUS #define MAX_NR_CPUS 1024 +#endif extern const char *input_name; extern bool perf_host, perf_guest; diff --git a/tools/perf/pmu-events/arch/arm64/cavium/thunderx2/core-imp-def.json b/tools/perf/pmu-events/arch/arm64/cavium/thunderx2/core-imp-def.json index bc03c06c3918..752e47eb6977 100644 --- a/tools/perf/pmu-events/arch/arm64/cavium/thunderx2/core-imp-def.json +++ b/tools/perf/pmu-events/arch/arm64/cavium/thunderx2/core-imp-def.json @@ -12,6 +12,21 @@ "ArchStdEvent": "L1D_CACHE_REFILL_WR", }, { + "ArchStdEvent": "L1D_CACHE_REFILL_INNER", + }, + { + "ArchStdEvent": "L1D_CACHE_REFILL_OUTER", + }, + { + "ArchStdEvent": "L1D_CACHE_WB_VICTIM", + }, + { + "ArchStdEvent": "L1D_CACHE_WB_CLEAN", + }, + { + "ArchStdEvent": "L1D_CACHE_INVAL", + }, + { "ArchStdEvent": "L1D_TLB_REFILL_RD", }, { @@ -24,9 +39,75 @@ "ArchStdEvent": "L1D_TLB_WR", }, { + "ArchStdEvent": "L2D_TLB_REFILL_RD", + }, + { + "ArchStdEvent": "L2D_TLB_REFILL_WR", + }, + { + "ArchStdEvent": "L2D_TLB_RD", + }, + { + "ArchStdEvent": "L2D_TLB_WR", + }, + { "ArchStdEvent": "BUS_ACCESS_RD", - }, - { + }, + { "ArchStdEvent": "BUS_ACCESS_WR", - } + }, + { + "ArchStdEvent": "MEM_ACCESS_RD", + }, + { + "ArchStdEvent": "MEM_ACCESS_WR", + }, + { + "ArchStdEvent": "UNALIGNED_LD_SPEC", + }, + { + "ArchStdEvent": "UNALIGNED_ST_SPEC", + }, + { + "ArchStdEvent": "UNALIGNED_LDST_SPEC", + }, + { + "ArchStdEvent": "EXC_UNDEF", + }, + { + "ArchStdEvent": "EXC_SVC", + }, + { + "ArchStdEvent": "EXC_PABORT", + }, + { + "ArchStdEvent": "EXC_DABORT", + }, + { + "ArchStdEvent": "EXC_IRQ", + }, + { + "ArchStdEvent": "EXC_FIQ", + }, + { + "ArchStdEvent": "EXC_SMC", + }, + { + "ArchStdEvent": "EXC_HVC", + }, + { + "ArchStdEvent": "EXC_TRAP_PABORT", + }, + { + "ArchStdEvent": "EXC_TRAP_DABORT", + }, + { + "ArchStdEvent": "EXC_TRAP_OTHER", + }, + { + "ArchStdEvent": "EXC_TRAP_IRQ", + }, + { + "ArchStdEvent": "EXC_TRAP_FIQ", + } ] diff --git a/tools/perf/pmu-events/arch/s390/cf_z10/basic.json b/tools/perf/pmu-events/arch/s390/cf_z10/basic.json index 8bf16759ca53..2dd8dafff2ef 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z10/basic.json +++ b/tools/perf/pmu-events/arch/s390/cf_z10/basic.json @@ -1,71 +1,83 @@ [ { + "Unit": "CPU-M-CF", "EventCode": "0", "EventName": "CPU_CYCLES", "BriefDescription": "CPU Cycles", "PublicDescription": "Cycle Count" }, { + "Unit": "CPU-M-CF", "EventCode": "1", "EventName": "INSTRUCTIONS", "BriefDescription": "Instructions", "PublicDescription": "Instruction Count" }, { + "Unit": "CPU-M-CF", "EventCode": "2", "EventName": "L1I_DIR_WRITES", "BriefDescription": "L1I Directory Writes", "PublicDescription": "Level-1 I-Cache Directory Write Count" }, { + "Unit": "CPU-M-CF", "EventCode": "3", "EventName": "L1I_PENALTY_CYCLES", "BriefDescription": "L1I Penalty Cycles", "PublicDescription": "Level-1 I-Cache Penalty Cycle Count" }, { + "Unit": "CPU-M-CF", "EventCode": "4", "EventName": "L1D_DIR_WRITES", "BriefDescription": "L1D Directory Writes", "PublicDescription": "Level-1 D-Cache Directory Write Count" }, { + "Unit": "CPU-M-CF", "EventCode": "5", "EventName": "L1D_PENALTY_CYCLES", "BriefDescription": "L1D Penalty Cycles", "PublicDescription": "Level-1 D-Cache Penalty Cycle Count" }, { + "Unit": "CPU-M-CF", "EventCode": "32", "EventName": "PROBLEM_STATE_CPU_CYCLES", "BriefDescription": "Problem-State CPU Cycles", "PublicDescription": "Problem-State Cycle Count" }, { + "Unit": "CPU-M-CF", "EventCode": "33", "EventName": "PROBLEM_STATE_INSTRUCTIONS", "BriefDescription": "Problem-State Instructions", "PublicDescription": "Problem-State Instruction Count" }, { + "Unit": "CPU-M-CF", "EventCode": "34", "EventName": "PROBLEM_STATE_L1I_DIR_WRITES", "BriefDescription": "Problem-State L1I Directory Writes", "PublicDescription": "Problem-State Level-1 I-Cache Directory Write Count" }, { + "Unit": "CPU-M-CF", "EventCode": "35", "EventName": "PROBLEM_STATE_L1I_PENALTY_CYCLES", "BriefDescription": "Problem-State L1I Penalty Cycles", "PublicDescription": "Problem-State Level-1 I-Cache Penalty Cycle Count" }, { + "Unit": "CPU-M-CF", "EventCode": "36", "EventName": "PROBLEM_STATE_L1D_DIR_WRITES", "BriefDescription": "Problem-State L1D Directory Writes", "PublicDescription": "Problem-State Level-1 D-Cache Directory Write Count" }, { + "Unit": "CPU-M-CF", "EventCode": "37", "EventName": "PROBLEM_STATE_L1D_PENALTY_CYCLES", "BriefDescription": "Problem-State L1D Penalty Cycles", diff --git a/tools/perf/pmu-events/arch/s390/cf_z10/crypto.json b/tools/perf/pmu-events/arch/s390/cf_z10/crypto.json index 7e5b72492141..db286f19e7b6 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z10/crypto.json +++ b/tools/perf/pmu-events/arch/s390/cf_z10/crypto.json @@ -1,95 +1,111 @@ [ { + "Unit": "CPU-M-CF", "EventCode": "64", "EventName": "PRNG_FUNCTIONS", "BriefDescription": "PRNG Functions", "PublicDescription": "Total number of the PRNG functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "65", "EventName": "PRNG_CYCLES", "BriefDescription": "PRNG Cycles", "PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing PRNG functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "66", "EventName": "PRNG_BLOCKED_FUNCTIONS", "BriefDescription": "PRNG Blocked Functions", "PublicDescription": "Total number of the PRNG functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "67", "EventName": "PRNG_BLOCKED_CYCLES", "BriefDescription": "PRNG Blocked Cycles", "PublicDescription": "Total number of CPU cycles blocked for the PRNG functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "68", "EventName": "SHA_FUNCTIONS", "BriefDescription": "SHA Functions", "PublicDescription": "Total number of SHA functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "69", "EventName": "SHA_CYCLES", "BriefDescription": "SHA Cycles", "PublicDescription": "Total number of CPU cycles when the SHA coprocessor is busy performing the SHA functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "70", "EventName": "SHA_BLOCKED_FUNCTIONS", "BriefDescription": "SHA Blocked Functions", "PublicDescription": "Total number of the SHA functions that are issued by the CPU and are blocked because the SHA coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "71", "EventName": "SHA_BLOCKED_CYCLES", "BriefDescription": "SHA Bloced Cycles", "PublicDescription": "Total number of CPU cycles blocked for the SHA functions issued by the CPU because the SHA coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "72", "EventName": "DEA_FUNCTIONS", "BriefDescription": "DEA Functions", "PublicDescription": "Total number of the DEA functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "73", "EventName": "DEA_CYCLES", "BriefDescription": "DEA Cycles", "PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the DEA functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "74", "EventName": "DEA_BLOCKED_FUNCTIONS", "BriefDescription": "DEA Blocked Functions", "PublicDescription": "Total number of the DEA functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "75", "EventName": "DEA_BLOCKED_CYCLES", "BriefDescription": "DEA Blocked Cycles", "PublicDescription": "Total number of CPU cycles blocked for the DEA functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "76", "EventName": "AES_FUNCTIONS", "BriefDescription": "AES Functions", "PublicDescription": "Total number of AES functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "77", "EventName": "AES_CYCLES", "BriefDescription": "AES Cycles", "PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the AES functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "78", "EventName": "AES_BLOCKED_FUNCTIONS", "BriefDescription": "AES Blocked Functions", "PublicDescription": "Total number of AES functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "79", "EventName": "AES_BLOCKED_CYCLES", "BriefDescription": "AES Blocked Cycles", diff --git a/tools/perf/pmu-events/arch/s390/cf_z10/extended.json b/tools/perf/pmu-events/arch/s390/cf_z10/extended.json index 0feedb40f30f..b6b7f29ca831 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z10/extended.json +++ b/tools/perf/pmu-events/arch/s390/cf_z10/extended.json @@ -1,107 +1,125 @@ [ { + "Unit": "CPU-M-CF", "EventCode": "128", "EventName": "L1I_L2_SOURCED_WRITES", "BriefDescription": "L1I L2 Sourced Writes", "PublicDescription": "A directory write to the Level-1 I-Cache directory where the returned cache line was sourced from the Level-2 (L1.5) cache" }, { + "Unit": "CPU-M-CF", "EventCode": "129", "EventName": "L1D_L2_SOURCED_WRITES", "BriefDescription": "L1D L2 Sourced Writes", "PublicDescription": "A directory write to the Level-1 D-Cache directory where the installed cache line was sourced from the Level-2 (L1.5) cache" }, { + "Unit": "CPU-M-CF", "EventCode": "130", "EventName": "L1I_L3_LOCAL_WRITES", "BriefDescription": "L1I L3 Local Writes", "PublicDescription": "A directory write to the Level-1 I-Cache directory where the installed cache line was sourced from the Level-3 cache that is on the same book as the Instruction cache (Local L2 cache)" }, { + "Unit": "CPU-M-CF", "EventCode": "131", "EventName": "L1D_L3_LOCAL_WRITES", "BriefDescription": "L1D L3 Local Writes", "PublicDescription": "A directory write to the Level-1 D-Cache directory where the installtion cache line was source from the Level-3 cache that is on the same book as the Data cache (Local L2 cache)" }, { + "Unit": "CPU-M-CF", "EventCode": "132", "EventName": "L1I_L3_REMOTE_WRITES", "BriefDescription": "L1I L3 Remote Writes", "PublicDescription": "A directory write to the Level-1 I-Cache directory where the installed cache line was sourced from a Level-3 cache that is not on the same book as the Instruction cache (Remote L2 cache)" }, { + "Unit": "CPU-M-CF", "EventCode": "133", "EventName": "L1D_L3_REMOTE_WRITES", "BriefDescription": "L1D L3 Remote Writes", "PublicDescription": "A directory write to the Level-1 D-Cache directory where the installed cache line was sourced from a Level-3 cache that is not on the same book as the Data cache (Remote L2 cache)" }, { + "Unit": "CPU-M-CF", "EventCode": "134", "EventName": "L1D_LMEM_SOURCED_WRITES", "BriefDescription": "L1D Local Memory Sourced Writes", "PublicDescription": "A directory write to the Level-1 D-Cache directory where the installed cache line was sourced from memory that is attached to the same book as the Data cache (Local Memory)" }, { + "Unit": "CPU-M-CF", "EventCode": "135", "EventName": "L1I_LMEM_SOURCED_WRITES", "BriefDescription": "L1I Local Memory Sourced Writes", "PublicDescription": "A directory write to the Level-1 I-Cache where the installed cache line was sourced from memory that is attached to the s ame book as the Instruction cache (Local Memory)" }, { + "Unit": "CPU-M-CF", "EventCode": "136", "EventName": "L1D_RO_EXCL_WRITES", "BriefDescription": "L1D Read-only Exclusive Writes", "PublicDescription": "A directory write to the Level-1 D-Cache where the line was originally in a Read-Only state in the cache but has been updated to be in the Exclusive state that allows stores to the cache line" }, { + "Unit": "CPU-M-CF", "EventCode": "137", "EventName": "L1I_CACHELINE_INVALIDATES", "BriefDescription": "L1I Cacheline Invalidates", "PublicDescription": "A cache line in the Level-1 I-Cache has been invalidated by a store on the same CPU as the Level-1 I-Cache" }, { + "Unit": "CPU-M-CF", "EventCode": "138", "EventName": "ITLB1_WRITES", "BriefDescription": "ITLB1 Writes", "PublicDescription": "A translation entry has been written into the Level-1 Instruction Translation Lookaside Buffer" }, { + "Unit": "CPU-M-CF", "EventCode": "139", "EventName": "DTLB1_WRITES", "BriefDescription": "DTLB1 Writes", "PublicDescription": "A translation entry has been written to the Level-1 Data Translation Lookaside Buffer" }, { + "Unit": "CPU-M-CF", "EventCode": "140", "EventName": "TLB2_PTE_WRITES", "BriefDescription": "TLB2 PTE Writes", "PublicDescription": "A translation entry has been written to the Level-2 TLB Page Table Entry arrays" }, { + "Unit": "CPU-M-CF", "EventCode": "141", "EventName": "TLB2_CRSTE_WRITES", "BriefDescription": "TLB2 CRSTE Writes", "PublicDescription": "A translation entry has been written to the Level-2 TLB Common Region Segment Table Entry arrays" }, { + "Unit": "CPU-M-CF", "EventCode": "142", "EventName": "TLB2_CRSTE_HPAGE_WRITES", "BriefDescription": "TLB2 CRSTE One-Megabyte Page Writes", "PublicDescription": "A translation entry has been written to the Level-2 TLB Common Region Segment Table Entry arrays for a one-megabyte large page translation" }, { + "Unit": "CPU-M-CF", "EventCode": "145", "EventName": "ITLB1_MISSES", "BriefDescription": "ITLB1 Misses", "PublicDescription": "Level-1 Instruction TLB miss in progress. Incremented by one for every cycle an ITLB1 miss is in progress" }, { + "Unit": "CPU-M-CF", "EventCode": "146", "EventName": "DTLB1_MISSES", "BriefDescription": "DTLB1 Misses", "PublicDescription": "Level-1 Data TLB miss in progress. Incremented by one for every cycle an DTLB1 miss is in progress" }, { + "Unit": "CPU-M-CF", "EventCode": "147", "EventName": "L2C_STORES_SENT", "BriefDescription": "L2C Stores Sent", diff --git a/tools/perf/pmu-events/arch/s390/cf_z13/basic.json b/tools/perf/pmu-events/arch/s390/cf_z13/basic.json index 8bf16759ca53..2dd8dafff2ef 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z13/basic.json +++ b/tools/perf/pmu-events/arch/s390/cf_z13/basic.json @@ -1,71 +1,83 @@ [ { + "Unit": "CPU-M-CF", "EventCode": "0", "EventName": "CPU_CYCLES", "BriefDescription": "CPU Cycles", "PublicDescription": "Cycle Count" }, { + "Unit": "CPU-M-CF", "EventCode": "1", "EventName": "INSTRUCTIONS", "BriefDescription": "Instructions", "PublicDescription": "Instruction Count" }, { + "Unit": "CPU-M-CF", "EventCode": "2", "EventName": "L1I_DIR_WRITES", "BriefDescription": "L1I Directory Writes", "PublicDescription": "Level-1 I-Cache Directory Write Count" }, { + "Unit": "CPU-M-CF", "EventCode": "3", "EventName": "L1I_PENALTY_CYCLES", "BriefDescription": "L1I Penalty Cycles", "PublicDescription": "Level-1 I-Cache Penalty Cycle Count" }, { + "Unit": "CPU-M-CF", "EventCode": "4", "EventName": "L1D_DIR_WRITES", "BriefDescription": "L1D Directory Writes", "PublicDescription": "Level-1 D-Cache Directory Write Count" }, { + "Unit": "CPU-M-CF", "EventCode": "5", "EventName": "L1D_PENALTY_CYCLES", "BriefDescription": "L1D Penalty Cycles", "PublicDescription": "Level-1 D-Cache Penalty Cycle Count" }, { + "Unit": "CPU-M-CF", "EventCode": "32", "EventName": "PROBLEM_STATE_CPU_CYCLES", "BriefDescription": "Problem-State CPU Cycles", "PublicDescription": "Problem-State Cycle Count" }, { + "Unit": "CPU-M-CF", "EventCode": "33", "EventName": "PROBLEM_STATE_INSTRUCTIONS", "BriefDescription": "Problem-State Instructions", "PublicDescription": "Problem-State Instruction Count" }, { + "Unit": "CPU-M-CF", "EventCode": "34", "EventName": "PROBLEM_STATE_L1I_DIR_WRITES", "BriefDescription": "Problem-State L1I Directory Writes", "PublicDescription": "Problem-State Level-1 I-Cache Directory Write Count" }, { + "Unit": "CPU-M-CF", "EventCode": "35", "EventName": "PROBLEM_STATE_L1I_PENALTY_CYCLES", "BriefDescription": "Problem-State L1I Penalty Cycles", "PublicDescription": "Problem-State Level-1 I-Cache Penalty Cycle Count" }, { + "Unit": "CPU-M-CF", "EventCode": "36", "EventName": "PROBLEM_STATE_L1D_DIR_WRITES", "BriefDescription": "Problem-State L1D Directory Writes", "PublicDescription": "Problem-State Level-1 D-Cache Directory Write Count" }, { + "Unit": "CPU-M-CF", "EventCode": "37", "EventName": "PROBLEM_STATE_L1D_PENALTY_CYCLES", "BriefDescription": "Problem-State L1D Penalty Cycles", diff --git a/tools/perf/pmu-events/arch/s390/cf_z13/crypto.json b/tools/perf/pmu-events/arch/s390/cf_z13/crypto.json index 7e5b72492141..db286f19e7b6 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z13/crypto.json +++ b/tools/perf/pmu-events/arch/s390/cf_z13/crypto.json @@ -1,95 +1,111 @@ [ { + "Unit": "CPU-M-CF", "EventCode": "64", "EventName": "PRNG_FUNCTIONS", "BriefDescription": "PRNG Functions", "PublicDescription": "Total number of the PRNG functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "65", "EventName": "PRNG_CYCLES", "BriefDescription": "PRNG Cycles", "PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing PRNG functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "66", "EventName": "PRNG_BLOCKED_FUNCTIONS", "BriefDescription": "PRNG Blocked Functions", "PublicDescription": "Total number of the PRNG functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "67", "EventName": "PRNG_BLOCKED_CYCLES", "BriefDescription": "PRNG Blocked Cycles", "PublicDescription": "Total number of CPU cycles blocked for the PRNG functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "68", "EventName": "SHA_FUNCTIONS", "BriefDescription": "SHA Functions", "PublicDescription": "Total number of SHA functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "69", "EventName": "SHA_CYCLES", "BriefDescription": "SHA Cycles", "PublicDescription": "Total number of CPU cycles when the SHA coprocessor is busy performing the SHA functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "70", "EventName": "SHA_BLOCKED_FUNCTIONS", "BriefDescription": "SHA Blocked Functions", "PublicDescription": "Total number of the SHA functions that are issued by the CPU and are blocked because the SHA coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "71", "EventName": "SHA_BLOCKED_CYCLES", "BriefDescription": "SHA Bloced Cycles", "PublicDescription": "Total number of CPU cycles blocked for the SHA functions issued by the CPU because the SHA coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "72", "EventName": "DEA_FUNCTIONS", "BriefDescription": "DEA Functions", "PublicDescription": "Total number of the DEA functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "73", "EventName": "DEA_CYCLES", "BriefDescription": "DEA Cycles", "PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the DEA functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "74", "EventName": "DEA_BLOCKED_FUNCTIONS", "BriefDescription": "DEA Blocked Functions", "PublicDescription": "Total number of the DEA functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "75", "EventName": "DEA_BLOCKED_CYCLES", "BriefDescription": "DEA Blocked Cycles", "PublicDescription": "Total number of CPU cycles blocked for the DEA functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "76", "EventName": "AES_FUNCTIONS", "BriefDescription": "AES Functions", "PublicDescription": "Total number of AES functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "77", "EventName": "AES_CYCLES", "BriefDescription": "AES Cycles", "PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the AES functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "78", "EventName": "AES_BLOCKED_FUNCTIONS", "BriefDescription": "AES Blocked Functions", "PublicDescription": "Total number of AES functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "79", "EventName": "AES_BLOCKED_CYCLES", "BriefDescription": "AES Blocked Cycles", diff --git a/tools/perf/pmu-events/arch/s390/cf_z13/extended.json b/tools/perf/pmu-events/arch/s390/cf_z13/extended.json index 9a002b6967f1..436ce33f1182 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z13/extended.json +++ b/tools/perf/pmu-events/arch/s390/cf_z13/extended.json @@ -1,335 +1,391 @@ [ { + "Unit": "CPU-M-CF", "EventCode": "128", "EventName": "L1D_RO_EXCL_WRITES", "BriefDescription": "L1D Read-only Exclusive Writes", "PublicDescription": "A directory write to the Level-1 Data cache where the line was originally in a Read-Only state in the cache but has been updated to be in the Exclusive state that allows stores to the cache line." }, { + "Unit": "CPU-M-CF", "EventCode": "129", "EventName": "DTLB1_WRITES", "BriefDescription": "DTLB1 Writes", "PublicDescription": "A translation entry has been written to the Level-1 Data Translation Lookaside Buffer" }, { + "Unit": "CPU-M-CF", "EventCode": "130", "EventName": "DTLB1_MISSES", "BriefDescription": "DTLB1 Misses", "PublicDescription": "Level-1 Data TLB miss in progress. Incremented by one for every cycle a DTLB1 miss is in progress." }, { + "Unit": "CPU-M-CF", "EventCode": "131", "EventName": "DTLB1_HPAGE_WRITES", "BriefDescription": "DTLB1 One-Megabyte Page Writes", "PublicDescription": "A translation entry has been written to the Level-1 Data Translation Lookaside Buffer for a one-megabyte page" }, { + "Unit": "CPU-M-CF", "EventCode": "132", "EventName": "DTLB1_GPAGE_WRITES", "BriefDescription": "DTLB1 Two-Gigabyte Page Writes", "PublicDescription": "Counter:132 Name:DTLB1_GPAGE_WRITES A translation entry has been written to the Level-1 Data Translation Lookaside Buffer for a two-gigabyte page." }, { + "Unit": "CPU-M-CF", "EventCode": "133", "EventName": "L1D_L2D_SOURCED_WRITES", "BriefDescription": "L1D L2D Sourced Writes", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from the Level-2 Data cache" }, { + "Unit": "CPU-M-CF", "EventCode": "134", "EventName": "ITLB1_WRITES", "BriefDescription": "ITLB1 Writes", "PublicDescription": "A translation entry has been written to the Level-1 Instruction Translation Lookaside Buffer" }, { + "Unit": "CPU-M-CF", "EventCode": "135", "EventName": "ITLB1_MISSES", "BriefDescription": "ITLB1 Misses", "PublicDescription": "Level-1 Instruction TLB miss in progress. Incremented by one for every cycle an ITLB1 miss is in progress" }, { + "Unit": "CPU-M-CF", "EventCode": "136", "EventName": "L1I_L2I_SOURCED_WRITES", "BriefDescription": "L1I L2I Sourced Writes", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from the Level-2 Instruction cache" }, { + "Unit": "CPU-M-CF", "EventCode": "137", "EventName": "TLB2_PTE_WRITES", "BriefDescription": "TLB2 PTE Writes", "PublicDescription": "A translation entry has been written to the Level-2 TLB Page Table Entry arrays" }, { + "Unit": "CPU-M-CF", "EventCode": "138", "EventName": "TLB2_CRSTE_HPAGE_WRITES", "BriefDescription": "TLB2 CRSTE One-Megabyte Page Writes", "PublicDescription": "A translation entry has been written to the Level-2 TLB Combined Region Segment Table Entry arrays for a one-megabyte large page translation" }, { + "Unit": "CPU-M-CF", "EventCode": "139", "EventName": "TLB2_CRSTE_WRITES", "BriefDescription": "TLB2 CRSTE Writes", "PublicDescription": "A translation entry has been written to the Level-2 TLB Combined Region Segment Table Entry arrays" }, { + "Unit": "CPU-M-CF", "EventCode": "140", "EventName": "TX_C_TEND", "BriefDescription": "Completed TEND instructions in constrained TX mode", "PublicDescription": "A TEND instruction has completed in a constrained transactional-execution mode" }, { + "Unit": "CPU-M-CF", "EventCode": "141", "EventName": "TX_NC_TEND", "BriefDescription": "Completed TEND instructions in non-constrained TX mode", "PublicDescription": "A TEND instruction has completed in a non-constrained transactional-execution mode" }, { + "Unit": "CPU-M-CF", "EventCode": "143", "EventName": "L1C_TLB1_MISSES", "BriefDescription": "L1C TLB1 Misses", "PublicDescription": "Increments by one for any cycle where a Level-1 cache or Level-1 TLB miss is in progress." }, { + "Unit": "CPU-M-CF", "EventCode": "144", "EventName": "L1D_ONCHIP_L3_SOURCED_WRITES", "BriefDescription": "L1D On-Chip L3 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Chip Level-3 cache without intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "145", "EventName": "L1D_ONCHIP_L3_SOURCED_WRITES_IV", "BriefDescription": "L1D On-Chip L3 Sourced Writes with Intervention", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Chip Level-3 cache with intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "146", "EventName": "L1D_ONNODE_L4_SOURCED_WRITES", "BriefDescription": "L1D On-Node L4 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Node Level-4 cache" }, { + "Unit": "CPU-M-CF", "EventCode": "147", "EventName": "L1D_ONNODE_L3_SOURCED_WRITES_IV", "BriefDescription": "L1D On-Node L3 Sourced Writes with Intervention", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Node Level-3 cache with intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "148", "EventName": "L1D_ONNODE_L3_SOURCED_WRITES", "BriefDescription": "L1D On-Node L3 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Node Level-3 cache without intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "149", "EventName": "L1D_ONDRAWER_L4_SOURCED_WRITES", "BriefDescription": "L1D On-Drawer L4 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Drawer Level-4 cache" }, { + "Unit": "CPU-M-CF", "EventCode": "150", "EventName": "L1D_ONDRAWER_L3_SOURCED_WRITES_IV", "BriefDescription": "L1D On-Drawer L3 Sourced Writes with Intervention", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Drawer Level-3 cache with intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "151", "EventName": "L1D_ONDRAWER_L3_SOURCED_WRITES", "BriefDescription": "L1D On-Drawer L3 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Drawer Level-3 cache without intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "152", "EventName": "L1D_OFFDRAWER_SCOL_L4_SOURCED_WRITES", "BriefDescription": "L1D Off-Drawer Same-Column L4 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Same-Column Level-4 cache" }, { + "Unit": "CPU-M-CF", "EventCode": "153", "EventName": "L1D_OFFDRAWER_SCOL_L3_SOURCED_WRITES_IV", "BriefDescription": "L1D Off-Drawer Same-Column L3 Sourced Writes with Intervention", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Same-Column Level-3 cache with intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "154", "EventName": "L1D_OFFDRAWER_SCOL_L3_SOURCED_WRITES", "BriefDescription": "L1D Off-Drawer Same-Column L3 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Same-Column Level-3 cache without intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "155", "EventName": "L1D_OFFDRAWER_FCOL_L4_SOURCED_WRITES", "BriefDescription": "L1D Off-Drawer Far-Column L3 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Far-Column Level-4 cache" }, { + "Unit": "CPU-M-CF", "EventCode": "156", "EventName": "L1D_OFFDRAWER_FCOL_L3_SOURCED_WRITES_IV", "BriefDescription": "L1D Off-Drawer Far-Column L3 Sourced Writes with Intervention", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Far-Column Level-3 cache with intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "157", "EventName": "L1D_OFFDRAWER_FCOL_L3_SOURCED_WRITES", "BriefDescription": "L1D Off-Drawer Far-Column L3 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Far-Column Level-3 cache without intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "158", "EventName": "L1D_ONNODE_MEM_SOURCED_WRITES", "BriefDescription": "L1D On-Node Memory Sourced Writes", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Node memory" }, { + "Unit": "CPU-M-CF", "EventCode": "159", "EventName": "L1D_ONDRAWER_MEM_SOURCED_WRITES", "BriefDescription": "L1D On-Drawer Memory Sourced Writes", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Drawer memory" }, { + "Unit": "CPU-M-CF", "EventCode": "160", "EventName": "L1D_OFFDRAWER_MEM_SOURCED_WRITES", "BriefDescription": "L1D Off-Drawer Memory Sourced Writes", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Drawer memory" }, { + "Unit": "CPU-M-CF", "EventCode": "161", "EventName": "L1D_ONCHIP_MEM_SOURCED_WRITES", "BriefDescription": "L1D On-Chip Memory Sourced Writes", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Chip memory" }, { + "Unit": "CPU-M-CF", "EventCode": "162", "EventName": "L1I_ONCHIP_L3_SOURCED_WRITES", "BriefDescription": "L1I On-Chip L3 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Chip Level-3 cache without intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "163", "EventName": "L1I_ONCHIP_L3_SOURCED_WRITES_IV", "BriefDescription": "L1I On-Chip L3 Sourced Writes with Intervention", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On Chip Level-3 cache with intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "164", "EventName": "L1I_ONNODE_L4_SOURCED_WRITES", "BriefDescription": "L1I On-Chip L4 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Node Level-4 cache" }, { + "Unit": "CPU-M-CF", "EventCode": "165", "EventName": "L1I_ONNODE_L3_SOURCED_WRITES_IV", "BriefDescription": "L1I On-Node L3 Sourced Writes with Intervention", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Node Level-3 cache with intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "166", "EventName": "L1I_ONNODE_L3_SOURCED_WRITES", "BriefDescription": "L1I On-Node L3 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Node Level-3 cache without intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "167", "EventName": "L1I_ONDRAWER_L4_SOURCED_WRITES", "BriefDescription": "L1I On-Drawer L4 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Drawer Level-4 cache" }, { + "Unit": "CPU-M-CF", "EventCode": "168", "EventName": "L1I_ONDRAWER_L3_SOURCED_WRITES_IV", "BriefDescription": "L1I On-Drawer L3 Sourced Writes with Intervention", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Drawer Level-3 cache with intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "169", "EventName": "L1I_ONDRAWER_L3_SOURCED_WRITES", "BriefDescription": "L1I On-Drawer L3 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Drawer Level-3 cache without intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "170", "EventName": "L1I_OFFDRAWER_SCOL_L4_SOURCED_WRITES", "BriefDescription": "L1I Off-Drawer Same-Column L4 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Same-Column Level-4 cache" }, { + "Unit": "CPU-M-CF", "EventCode": "171", "EventName": "L1I_OFFDRAWER_SCOL_L3_SOURCED_WRITES_IV", "BriefDescription": "L1I Off-Drawer Same-Column L3 Sourced Writes with Intervention", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Same-Column Level-3 cache with intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "172", "EventName": "L1I_OFFDRAWER_SCOL_L3_SOURCED_WRITES", "BriefDescription": "L1I Off-Drawer Same-Column L3 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Same-Column Level-3 cache without intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "173", "EventName": "L1I_OFFDRAWER_FCOL_L4_SOURCED_WRITES", "BriefDescription": "L1I Off-Drawer Far-Column L4 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Far-Column Level-4 cache" }, { + "Unit": "CPU-M-CF", "EventCode": "174", "EventName": "L1I_OFFDRAWER_FCOL_L3_SOURCED_WRITES_IV", "BriefDescription": "L1I Off-Drawer Far-Column L3 Sourced Writes with Intervention", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Far-Column Level-3 cache with intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "175", "EventName": "L1I_OFFDRAWER_FCOL_L3_SOURCED_WRITES", "BriefDescription": "L1I Off-Drawer Far-Column L3 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Far-Column Level-3 cache without intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "176", "EventName": "L1I_ONNODE_MEM_SOURCED_WRITES", "BriefDescription": "L1I On-Node Memory Sourced Writes", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from On-Node memory" }, { + "Unit": "CPU-M-CF", "EventCode": "177", "EventName": "L1I_ONDRAWER_MEM_SOURCED_WRITES", "BriefDescription": "L1I On-Drawer Memory Sourced Writes", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from On-Drawer memory" }, { + "Unit": "CPU-M-CF", "EventCode": "178", "EventName": "L1I_OFFDRAWER_MEM_SOURCED_WRITES", "BriefDescription": "L1I Off-Drawer Memory Sourced Writes", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from On-Drawer memory" }, { + "Unit": "CPU-M-CF", "EventCode": "179", "EventName": "L1I_ONCHIP_MEM_SOURCED_WRITES", "BriefDescription": "L1I On-Chip Memory Sourced Writes", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from On-Chip memory" }, { + "Unit": "CPU-M-CF", "EventCode": "218", "EventName": "TX_NC_TABORT", "BriefDescription": "Aborted transactions in non-constrained TX mode", "PublicDescription": "A transaction abort has occurred in a non-constrained transactional-execution mode" }, { + "Unit": "CPU-M-CF", "EventCode": "219", "EventName": "TX_C_TABORT_NO_SPECIAL", "BriefDescription": "Aborted transactions in constrained TX mode not using special completion logic", "PublicDescription": "A transaction abort has occurred in a constrained transactional-execution mode and the CPU is not using any special logic to allow the transaction to complete" }, { + "Unit": "CPU-M-CF", "EventCode": "220", "EventName": "TX_C_TABORT_SPECIAL", "BriefDescription": "Aborted transactions in constrained TX mode using special completion logic", "PublicDescription": "A transaction abort has occurred in a constrained transactional-execution mode and the CPU is using special logic to allow the transaction to complete" }, { + "Unit": "CPU-M-CF", "EventCode": "448", "EventName": "MT_DIAG_CYCLES_ONE_THR_ACTIVE", "BriefDescription": "Cycle count with one thread active", "PublicDescription": "Cycle count with one thread active" }, { + "Unit": "CPU-M-CF", "EventCode": "449", "EventName": "MT_DIAG_CYCLES_TWO_THR_ACTIVE", "BriefDescription": "Cycle count with two threads active", diff --git a/tools/perf/pmu-events/arch/s390/cf_z13/transaction.json b/tools/perf/pmu-events/arch/s390/cf_z13/transaction.json new file mode 100644 index 000000000000..1a0034f79f73 --- /dev/null +++ b/tools/perf/pmu-events/arch/s390/cf_z13/transaction.json @@ -0,0 +1,7 @@ +[ + { + "BriefDescription": "Transaction count", + "MetricName": "transaction", + "MetricExpr": "TX_C_TEND + TX_NC_TEND + TX_NC_TABORT + TX_C_TABORT_SPECIAL + TX_C_TABORT_NO_SPECIAL" + } +] diff --git a/tools/perf/pmu-events/arch/s390/cf_z14/basic.json b/tools/perf/pmu-events/arch/s390/cf_z14/basic.json index 8f653c9d899d..17fb5241928b 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z14/basic.json +++ b/tools/perf/pmu-events/arch/s390/cf_z14/basic.json @@ -1,47 +1,55 @@ [ { + "Unit": "CPU-M-CF", "EventCode": "0", "EventName": "CPU_CYCLES", "BriefDescription": "CPU Cycles", "PublicDescription": "Cycle Count" }, { + "Unit": "CPU-M-CF", "EventCode": "1", "EventName": "INSTRUCTIONS", "BriefDescription": "Instructions", "PublicDescription": "Instruction Count" }, { + "Unit": "CPU-M-CF", "EventCode": "2", "EventName": "L1I_DIR_WRITES", "BriefDescription": "L1I Directory Writes", "PublicDescription": "Level-1 I-Cache Directory Write Count" }, { + "Unit": "CPU-M-CF", "EventCode": "3", "EventName": "L1I_PENALTY_CYCLES", "BriefDescription": "L1I Penalty Cycles", "PublicDescription": "Level-1 I-Cache Penalty Cycle Count" }, { + "Unit": "CPU-M-CF", "EventCode": "4", "EventName": "L1D_DIR_WRITES", "BriefDescription": "L1D Directory Writes", "PublicDescription": "Level-1 D-Cache Directory Write Count" }, { + "Unit": "CPU-M-CF", "EventCode": "5", "EventName": "L1D_PENALTY_CYCLES", "BriefDescription": "L1D Penalty Cycles", "PublicDescription": "Level-1 D-Cache Penalty Cycle Count" }, { + "Unit": "CPU-M-CF", "EventCode": "32", "EventName": "PROBLEM_STATE_CPU_CYCLES", "BriefDescription": "Problem-State CPU Cycles", "PublicDescription": "Problem-State Cycle Count" }, { + "Unit": "CPU-M-CF", "EventCode": "33", "EventName": "PROBLEM_STATE_INSTRUCTIONS", "BriefDescription": "Problem-State Instructions", diff --git a/tools/perf/pmu-events/arch/s390/cf_z14/crypto.json b/tools/perf/pmu-events/arch/s390/cf_z14/crypto.json index 7e5b72492141..db286f19e7b6 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z14/crypto.json +++ b/tools/perf/pmu-events/arch/s390/cf_z14/crypto.json @@ -1,95 +1,111 @@ [ { + "Unit": "CPU-M-CF", "EventCode": "64", "EventName": "PRNG_FUNCTIONS", "BriefDescription": "PRNG Functions", "PublicDescription": "Total number of the PRNG functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "65", "EventName": "PRNG_CYCLES", "BriefDescription": "PRNG Cycles", "PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing PRNG functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "66", "EventName": "PRNG_BLOCKED_FUNCTIONS", "BriefDescription": "PRNG Blocked Functions", "PublicDescription": "Total number of the PRNG functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "67", "EventName": "PRNG_BLOCKED_CYCLES", "BriefDescription": "PRNG Blocked Cycles", "PublicDescription": "Total number of CPU cycles blocked for the PRNG functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "68", "EventName": "SHA_FUNCTIONS", "BriefDescription": "SHA Functions", "PublicDescription": "Total number of SHA functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "69", "EventName": "SHA_CYCLES", "BriefDescription": "SHA Cycles", "PublicDescription": "Total number of CPU cycles when the SHA coprocessor is busy performing the SHA functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "70", "EventName": "SHA_BLOCKED_FUNCTIONS", "BriefDescription": "SHA Blocked Functions", "PublicDescription": "Total number of the SHA functions that are issued by the CPU and are blocked because the SHA coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "71", "EventName": "SHA_BLOCKED_CYCLES", "BriefDescription": "SHA Bloced Cycles", "PublicDescription": "Total number of CPU cycles blocked for the SHA functions issued by the CPU because the SHA coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "72", "EventName": "DEA_FUNCTIONS", "BriefDescription": "DEA Functions", "PublicDescription": "Total number of the DEA functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "73", "EventName": "DEA_CYCLES", "BriefDescription": "DEA Cycles", "PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the DEA functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "74", "EventName": "DEA_BLOCKED_FUNCTIONS", "BriefDescription": "DEA Blocked Functions", "PublicDescription": "Total number of the DEA functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "75", "EventName": "DEA_BLOCKED_CYCLES", "BriefDescription": "DEA Blocked Cycles", "PublicDescription": "Total number of CPU cycles blocked for the DEA functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "76", "EventName": "AES_FUNCTIONS", "BriefDescription": "AES Functions", "PublicDescription": "Total number of AES functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "77", "EventName": "AES_CYCLES", "BriefDescription": "AES Cycles", "PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the AES functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "78", "EventName": "AES_BLOCKED_FUNCTIONS", "BriefDescription": "AES Blocked Functions", "PublicDescription": "Total number of AES functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "79", "EventName": "AES_BLOCKED_CYCLES", "BriefDescription": "AES Blocked Cycles", diff --git a/tools/perf/pmu-events/arch/s390/cf_z14/extended.json b/tools/perf/pmu-events/arch/s390/cf_z14/extended.json index aa4dfb46b65b..e7a3524b748f 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z14/extended.json +++ b/tools/perf/pmu-events/arch/s390/cf_z14/extended.json @@ -1,317 +1,370 @@ [ { + "Unit": "CPU-M-CF", "EventCode": "128", "EventName": "L1D_RO_EXCL_WRITES", "BriefDescription": "L1D Read-only Exclusive Writes", "PublicDescription": "Counter:128 Name:L1D_RO_EXCL_WRITES A directory write to the Level-1 Data cache where the line was originally in a Read-Only state in the cache but has been updated to be in the Exclusive state that allows stores to the cache line" }, { + "Unit": "CPU-M-CF", "EventCode": "129", "EventName": "DTLB2_WRITES", "BriefDescription": "DTLB2 Writes", "PublicDescription": "A translation has been written into The Translation Lookaside Buffer 2 (TLB2) and the request was made by the data cache" }, { + "Unit": "CPU-M-CF", "EventCode": "130", "EventName": "DTLB2_MISSES", "BriefDescription": "DTLB2 Misses", "PublicDescription": "A TLB2 miss is in progress for a request made by the data cache. Incremented by one for every TLB2 miss in progress for the Level-1 Data cache on this cycle" }, { + "Unit": "CPU-M-CF", "EventCode": "131", "EventName": "DTLB2_HPAGE_WRITES", "BriefDescription": "DTLB2 One-Megabyte Page Writes", "PublicDescription": "A translation entry was written into the Combined Region and Segment Table Entry array in the Level-2 TLB for a one-megabyte page or a Last Host Translation was done" }, { + "Unit": "CPU-M-CF", "EventCode": "132", "EventName": "DTLB2_GPAGE_WRITES", "BriefDescription": "DTLB2 Two-Gigabyte Page Writes", "PublicDescription": "A translation entry for a two-gigabyte page was written into the Level-2 TLB" }, { + "Unit": "CPU-M-CF", "EventCode": "133", "EventName": "L1D_L2D_SOURCED_WRITES", "BriefDescription": "L1D L2D Sourced Writes", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from the Level-2 Data cache" }, { + "Unit": "CPU-M-CF", "EventCode": "134", "EventName": "ITLB2_WRITES", "BriefDescription": "ITLB2 Writes", "PublicDescription": "A translation entry has been written into the Translation Lookaside Buffer 2 (TLB2) and the request was made by the instruction cache" }, { + "Unit": "CPU-M-CF", "EventCode": "135", "EventName": "ITLB2_MISSES", "BriefDescription": "ITLB2 Misses", "PublicDescription": "A TLB2 miss is in progress for a request made by the instruction cache. Incremented by one for every TLB2 miss in progress for the Level-1 Instruction cache in a cycle" }, { + "Unit": "CPU-M-CF", "EventCode": "136", "EventName": "L1I_L2I_SOURCED_WRITES", "BriefDescription": "L1I L2I Sourced Writes", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from the Level-2 Instruction cache" }, { + "Unit": "CPU-M-CF", "EventCode": "137", "EventName": "TLB2_PTE_WRITES", "BriefDescription": "TLB2 PTE Writes", "PublicDescription": "A translation entry was written into the Page Table Entry array in the Level-2 TLB" }, { + "Unit": "CPU-M-CF", "EventCode": "138", "EventName": "TLB2_CRSTE_WRITES", "BriefDescription": "TLB2 CRSTE Writes", "PublicDescription": "Translation entries were written into the Combined Region and Segment Table Entry array and the Page Table Entry array in the Level-2 TLB" }, { + "Unit": "CPU-M-CF", "EventCode": "139", "EventName": "TLB2_ENGINES_BUSY", "BriefDescription": "TLB2 Engines Busy", "PublicDescription": "The number of Level-2 TLB translation engines busy in a cycle" }, { + "Unit": "CPU-M-CF", "EventCode": "140", "EventName": "TX_C_TEND", "BriefDescription": "Completed TEND instructions in constrained TX mode", "PublicDescription": "A TEND instruction has completed in a constrained transactional-execution mode" }, { + "Unit": "CPU-M-CF", "EventCode": "141", "EventName": "TX_NC_TEND", "BriefDescription": "Completed TEND instructions in non-constrained TX mode", "PublicDescription": "A TEND instruction has completed in a non-constrained transactional-execution mode" }, { + "Unit": "CPU-M-CF", "EventCode": "143", "EventName": "L1C_TLB2_MISSES", "BriefDescription": "L1C TLB2 Misses", "PublicDescription": "Increments by one for any cycle where a level-1 cache or level-2 TLB miss is in progress" }, { + "Unit": "CPU-M-CF", "EventCode": "144", "EventName": "L1D_ONCHIP_L3_SOURCED_WRITES", "BriefDescription": "L1D On-Chip L3 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Chip Level-3 cache without intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "145", "EventName": "L1D_ONCHIP_MEMORY_SOURCED_WRITES", "BriefDescription": "L1D On-Chip Memory Sourced Writes", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Chip memory" }, { + "Unit": "CPU-M-CF", "EventCode": "146", "EventName": "L1D_ONCHIP_L3_SOURCED_WRITES_IV", "BriefDescription": "L1D On-Chip L3 Sourced Writes with Intervention", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Chip Level-3 cache with intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "147", "EventName": "L1D_ONCLUSTER_L3_SOURCED_WRITES", "BriefDescription": "L1D On-Cluster L3 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Cluster Level-3 cache withountervention" }, { + "Unit": "CPU-M-CF", "EventCode": "148", "EventName": "L1D_ONCLUSTER_MEMORY_SOURCED_WRITES", "BriefDescription": "L1D On-Cluster Memory Sourced Writes", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Cluster memory" }, { + "Unit": "CPU-M-CF", "EventCode": "149", "EventName": "L1D_ONCLUSTER_L3_SOURCED_WRITES_IV", "BriefDescription": "L1D On-Cluster L3 Sourced Writes with Intervention", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Cluster Level-3 cache with intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "150", "EventName": "L1D_OFFCLUSTER_L3_SOURCED_WRITES", "BriefDescription": "L1D Off-Cluster L3 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Cluster Level-3 cache without intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "151", "EventName": "L1D_OFFCLUSTER_MEMORY_SOURCED_WRITES", "BriefDescription": "L1D Off-Cluster Memory Sourced Writes", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from Off-Cluster memory" }, { + "Unit": "CPU-M-CF", "EventCode": "152", "EventName": "L1D_OFFCLUSTER_L3_SOURCED_WRITES_IV", "BriefDescription": "L1D Off-Cluster L3 Sourced Writes with Intervention", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Cluster Level-3 cache with intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "153", "EventName": "L1D_OFFDRAWER_L3_SOURCED_WRITES", "BriefDescription": "L1D Off-Drawer L3 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Level-3 cache without intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "154", "EventName": "L1D_OFFDRAWER_MEMORY_SOURCED_WRITES", "BriefDescription": "L1D Off-Drawer Memory Sourced Writes", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from Off-Drawer memory" }, { + "Unit": "CPU-M-CF", "EventCode": "155", "EventName": "L1D_OFFDRAWER_L3_SOURCED_WRITES_IV", "BriefDescription": "L1D Off-Drawer L3 Sourced Writes with Intervention", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Level-3 cache with intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "156", "EventName": "L1D_ONDRAWER_L4_SOURCED_WRITES", "BriefDescription": "L1D On-Drawer L4 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Drawer Level-4 cache" }, { + "Unit": "CPU-M-CF", "EventCode": "157", "EventName": "L1D_OFFDRAWER_L4_SOURCED_WRITES", "BriefDescription": "L1D Off-Drawer L4 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from Off-Drawer Level-4 cache" }, { + "Unit": "CPU-M-CF", "EventCode": "158", "EventName": "L1D_ONCHIP_L3_SOURCED_WRITES_RO", "BriefDescription": "L1D On-Chip L3 Sourced Writes read-only", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Chip L3 but a read-only invalidate was done to remove other copies of the cache line" }, { + "Unit": "CPU-M-CF", "EventCode": "162", "EventName": "L1I_ONCHIP_L3_SOURCED_WRITES", "BriefDescription": "L1I On-Chip L3 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache ine was sourced from an On-Chip Level-3 cache without intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "163", "EventName": "L1I_ONCHIP_MEMORY_SOURCED_WRITES", "BriefDescription": "L1I On-Chip Memory Sourced Writes", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache ine was sourced from On-Chip memory" }, { + "Unit": "CPU-M-CF", "EventCode": "164", "EventName": "L1I_ONCHIP_L3_SOURCED_WRITES_IV", "BriefDescription": "L1I On-Chip L3 Sourced Writes with Intervention", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache ine was sourced from an On-Chip Level-3 cache with intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "165", "EventName": "L1I_ONCLUSTER_L3_SOURCED_WRITES", "BriefDescription": "L1I On-Cluster L3 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Cluster Level-3 cache without intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "166", "EventName": "L1I_ONCLUSTER_MEMORY_SOURCED_WRITES", "BriefDescription": "L1I On-Cluster Memory Sourced Writes", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Cluster memory" }, { + "Unit": "CPU-M-CF", "EventCode": "167", "EventName": "L1I_ONCLUSTER_L3_SOURCED_WRITES_IV", "BriefDescription": "L1I On-Cluster L3 Sourced Writes with Intervention", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from On-Cluster Level-3 cache with intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "168", "EventName": "L1I_OFFCLUSTER_L3_SOURCED_WRITES", "BriefDescription": "L1I Off-Cluster L3 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Cluster Level-3 cache without intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "169", "EventName": "L1I_OFFCLUSTER_MEMORY_SOURCED_WRITES", "BriefDescription": "L1I Off-Cluster Memory Sourced Writes", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from Off-Cluster memory" }, { + "Unit": "CPU-M-CF", "EventCode": "170", "EventName": "L1I_OFFCLUSTER_L3_SOURCED_WRITES_IV", "BriefDescription": "L1I Off-Cluster L3 Sourced Writes with Intervention", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Cluster Level-3 cache with intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "171", "EventName": "L1I_OFFDRAWER_L3_SOURCED_WRITES", "BriefDescription": "L1I Off-Drawer L3 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Level-3 cache without intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "172", "EventName": "L1I_OFFDRAWER_MEMORY_SOURCED_WRITES", "BriefDescription": "L1I Off-Drawer Memory Sourced Writes", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from Off-Drawer memory" }, { + "Unit": "CPU-M-CF", "EventCode": "173", "EventName": "L1I_OFFDRAWER_L3_SOURCED_WRITES_IV", "BriefDescription": "L1I Off-Drawer L3 Sourced Writes with Intervention", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Level-3 cache with intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "174", "EventName": "L1I_ONDRAWER_L4_SOURCED_WRITES", "BriefDescription": "L1I On-Drawer L4 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from On-Drawer Level-4 cache" }, { + "Unit": "CPU-M-CF", "EventCode": "175", "EventName": "L1I_OFFDRAWER_L4_SOURCED_WRITES", "BriefDescription": "L1I Off-Drawer L4 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from Off-Drawer Level-4 cache" }, { + "Unit": "CPU-M-CF", "EventCode": "224", "EventName": "BCD_DFP_EXECUTION_SLOTS", "BriefDescription": "BCD DFP Execution Slots", "PublicDescription": "Count of floating point execution slots used for finished Binary Coded Decimal to Decimal Floating Point conversions. Instructions: CDZT, CXZT, CZDT, CZXT" }, { + "Unit": "CPU-M-CF", "EventCode": "225", "EventName": "VX_BCD_EXECUTION_SLOTS", "BriefDescription": "VX BCD Execution Slots", "PublicDescription": "Count of floating point execution slots used for finished vector arithmetic Binary Coded Decimal instructions. Instructions: VAP, VSP, VMPVMSP, VDP, VSDP, VRP, VLIP, VSRP, VPSOPVCP, VTP, VPKZ, VUPKZ, VCVB, VCVBG, VCVDVCVDG" }, { + "Unit": "CPU-M-CF", "EventCode": "226", "EventName": "DECIMAL_INSTRUCTIONS", "BriefDescription": "Decimal Instructions", "PublicDescription": "Decimal instructions dispatched. Instructions: CVB, CVD, AP, CP, DP, ED, EDMK, MP, SRP, SP, ZAP" }, { + "Unit": "CPU-M-CF", "EventCode": "232", "EventName": "LAST_HOST_TRANSLATIONS", "BriefDescription": "Last host translation done", "PublicDescription": "Last Host Translation done" }, { + "Unit": "CPU-M-CF", "EventCode": "243", "EventName": "TX_NC_TABORT", "BriefDescription": "Aborted transactions in non-constrained TX mode", "PublicDescription": "A transaction abort has occurred in a non-constrained transactional-execution mode" }, { + "Unit": "CPU-M-CF", "EventCode": "244", "EventName": "TX_C_TABORT_NO_SPECIAL", "BriefDescription": "Aborted transactions in constrained TX mode not using special completion logic", "PublicDescription": "A transaction abort has occurred in a constrained transactional-execution mode and the CPU is not using any special logic to allow the transaction to complete" }, { + "Unit": "CPU-M-CF", "EventCode": "245", "EventName": "TX_C_TABORT_SPECIAL", "BriefDescription": "Aborted transactions in constrained TX mode using special completion logic", "PublicDescription": "A transaction abort has occurred in a constrained transactional-execution mode and the CPU is using special logic to allow the transaction to complete" }, { + "Unit": "CPU-M-CF", "EventCode": "448", "EventName": "MT_DIAG_CYCLES_ONE_THR_ACTIVE", "BriefDescription": "Cycle count with one thread active", "PublicDescription": "Cycle count with one thread active" }, { + "Unit": "CPU-M-CF", "EventCode": "449", "EventName": "MT_DIAG_CYCLES_TWO_THR_ACTIVE", "BriefDescription": "Cycle count with two threads active", diff --git a/tools/perf/pmu-events/arch/s390/cf_z14/transaction.json b/tools/perf/pmu-events/arch/s390/cf_z14/transaction.json new file mode 100644 index 000000000000..1a0034f79f73 --- /dev/null +++ b/tools/perf/pmu-events/arch/s390/cf_z14/transaction.json @@ -0,0 +1,7 @@ +[ + { + "BriefDescription": "Transaction count", + "MetricName": "transaction", + "MetricExpr": "TX_C_TEND + TX_NC_TEND + TX_NC_TABORT + TX_C_TABORT_SPECIAL + TX_C_TABORT_NO_SPECIAL" + } +] diff --git a/tools/perf/pmu-events/arch/s390/cf_z196/basic.json b/tools/perf/pmu-events/arch/s390/cf_z196/basic.json index 8bf16759ca53..2dd8dafff2ef 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z196/basic.json +++ b/tools/perf/pmu-events/arch/s390/cf_z196/basic.json @@ -1,71 +1,83 @@ [ { + "Unit": "CPU-M-CF", "EventCode": "0", "EventName": "CPU_CYCLES", "BriefDescription": "CPU Cycles", "PublicDescription": "Cycle Count" }, { + "Unit": "CPU-M-CF", "EventCode": "1", "EventName": "INSTRUCTIONS", "BriefDescription": "Instructions", "PublicDescription": "Instruction Count" }, { + "Unit": "CPU-M-CF", "EventCode": "2", "EventName": "L1I_DIR_WRITES", "BriefDescription": "L1I Directory Writes", "PublicDescription": "Level-1 I-Cache Directory Write Count" }, { + "Unit": "CPU-M-CF", "EventCode": "3", "EventName": "L1I_PENALTY_CYCLES", "BriefDescription": "L1I Penalty Cycles", "PublicDescription": "Level-1 I-Cache Penalty Cycle Count" }, { + "Unit": "CPU-M-CF", "EventCode": "4", "EventName": "L1D_DIR_WRITES", "BriefDescription": "L1D Directory Writes", "PublicDescription": "Level-1 D-Cache Directory Write Count" }, { + "Unit": "CPU-M-CF", "EventCode": "5", "EventName": "L1D_PENALTY_CYCLES", "BriefDescription": "L1D Penalty Cycles", "PublicDescription": "Level-1 D-Cache Penalty Cycle Count" }, { + "Unit": "CPU-M-CF", "EventCode": "32", "EventName": "PROBLEM_STATE_CPU_CYCLES", "BriefDescription": "Problem-State CPU Cycles", "PublicDescription": "Problem-State Cycle Count" }, { + "Unit": "CPU-M-CF", "EventCode": "33", "EventName": "PROBLEM_STATE_INSTRUCTIONS", "BriefDescription": "Problem-State Instructions", "PublicDescription": "Problem-State Instruction Count" }, { + "Unit": "CPU-M-CF", "EventCode": "34", "EventName": "PROBLEM_STATE_L1I_DIR_WRITES", "BriefDescription": "Problem-State L1I Directory Writes", "PublicDescription": "Problem-State Level-1 I-Cache Directory Write Count" }, { + "Unit": "CPU-M-CF", "EventCode": "35", "EventName": "PROBLEM_STATE_L1I_PENALTY_CYCLES", "BriefDescription": "Problem-State L1I Penalty Cycles", "PublicDescription": "Problem-State Level-1 I-Cache Penalty Cycle Count" }, { + "Unit": "CPU-M-CF", "EventCode": "36", "EventName": "PROBLEM_STATE_L1D_DIR_WRITES", "BriefDescription": "Problem-State L1D Directory Writes", "PublicDescription": "Problem-State Level-1 D-Cache Directory Write Count" }, { + "Unit": "CPU-M-CF", "EventCode": "37", "EventName": "PROBLEM_STATE_L1D_PENALTY_CYCLES", "BriefDescription": "Problem-State L1D Penalty Cycles", diff --git a/tools/perf/pmu-events/arch/s390/cf_z196/crypto.json b/tools/perf/pmu-events/arch/s390/cf_z196/crypto.json index 7e5b72492141..db286f19e7b6 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z196/crypto.json +++ b/tools/perf/pmu-events/arch/s390/cf_z196/crypto.json @@ -1,95 +1,111 @@ [ { + "Unit": "CPU-M-CF", "EventCode": "64", "EventName": "PRNG_FUNCTIONS", "BriefDescription": "PRNG Functions", "PublicDescription": "Total number of the PRNG functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "65", "EventName": "PRNG_CYCLES", "BriefDescription": "PRNG Cycles", "PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing PRNG functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "66", "EventName": "PRNG_BLOCKED_FUNCTIONS", "BriefDescription": "PRNG Blocked Functions", "PublicDescription": "Total number of the PRNG functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "67", "EventName": "PRNG_BLOCKED_CYCLES", "BriefDescription": "PRNG Blocked Cycles", "PublicDescription": "Total number of CPU cycles blocked for the PRNG functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "68", "EventName": "SHA_FUNCTIONS", "BriefDescription": "SHA Functions", "PublicDescription": "Total number of SHA functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "69", "EventName": "SHA_CYCLES", "BriefDescription": "SHA Cycles", "PublicDescription": "Total number of CPU cycles when the SHA coprocessor is busy performing the SHA functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "70", "EventName": "SHA_BLOCKED_FUNCTIONS", "BriefDescription": "SHA Blocked Functions", "PublicDescription": "Total number of the SHA functions that are issued by the CPU and are blocked because the SHA coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "71", "EventName": "SHA_BLOCKED_CYCLES", "BriefDescription": "SHA Bloced Cycles", "PublicDescription": "Total number of CPU cycles blocked for the SHA functions issued by the CPU because the SHA coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "72", "EventName": "DEA_FUNCTIONS", "BriefDescription": "DEA Functions", "PublicDescription": "Total number of the DEA functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "73", "EventName": "DEA_CYCLES", "BriefDescription": "DEA Cycles", "PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the DEA functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "74", "EventName": "DEA_BLOCKED_FUNCTIONS", "BriefDescription": "DEA Blocked Functions", "PublicDescription": "Total number of the DEA functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "75", "EventName": "DEA_BLOCKED_CYCLES", "BriefDescription": "DEA Blocked Cycles", "PublicDescription": "Total number of CPU cycles blocked for the DEA functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "76", "EventName": "AES_FUNCTIONS", "BriefDescription": "AES Functions", "PublicDescription": "Total number of AES functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "77", "EventName": "AES_CYCLES", "BriefDescription": "AES Cycles", "PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the AES functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "78", "EventName": "AES_BLOCKED_FUNCTIONS", "BriefDescription": "AES Blocked Functions", "PublicDescription": "Total number of AES functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "79", "EventName": "AES_BLOCKED_CYCLES", "BriefDescription": "AES Blocked Cycles", diff --git a/tools/perf/pmu-events/arch/s390/cf_z196/extended.json b/tools/perf/pmu-events/arch/s390/cf_z196/extended.json index b6d7fec7c2e7..b7b42a870bb0 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z196/extended.json +++ b/tools/perf/pmu-events/arch/s390/cf_z196/extended.json @@ -1,143 +1,167 @@ [ { + "Unit": "CPU-M-CF", "EventCode": "128", "EventName": "L1D_L2_SOURCED_WRITES", "BriefDescription": "L1D L2 Sourced Writes", "PublicDescription": "A directory write to the Level-1 D-Cache directory where the returned cache line was sourced from the Level-2 cache" }, { + "Unit": "CPU-M-CF", "EventCode": "129", "EventName": "L1I_L2_SOURCED_WRITES", "BriefDescription": "L1I L2 Sourced Writes", "PublicDescription": "A directory write to the Level-1 I-Cache directory where the returned cache line was sourced from the Level-2 cache" }, { + "Unit": "CPU-M-CF", "EventCode": "130", "EventName": "DTLB1_MISSES", "BriefDescription": "DTLB1 Misses", "PublicDescription": "Level-1 Data TLB miss in progress. Incremented by one for every cycle a DTLB1 miss is in progress." }, { + "Unit": "CPU-M-CF", "EventCode": "131", "EventName": "ITLB1_MISSES", "BriefDescription": "ITLB1 Misses", "PublicDescription": "Level-1 Instruction TLB miss in progress. Incremented by one for every cycle a ITLB1 miss is in progress." }, { + "Unit": "CPU-M-CF", "EventCode": "133", "EventName": "L2C_STORES_SENT", "BriefDescription": "L2C Stores Sent", "PublicDescription": "Incremented by one for every store sent to Level-2 cache" }, { + "Unit": "CPU-M-CF", "EventCode": "134", "EventName": "L1D_OFFBOOK_L3_SOURCED_WRITES", "BriefDescription": "L1D Off-Book L3 Sourced Writes", "PublicDescription": "A directory write to the Level-1 D-Cache directory where the returned cache line was sourced from an Off Book Level-3 cache" }, { + "Unit": "CPU-M-CF", "EventCode": "135", "EventName": "L1D_ONBOOK_L4_SOURCED_WRITES", "BriefDescription": "L1D On-Book L4 Sourced Writes", "PublicDescription": "A directory write to the Level-1 D-Cache directory where the returned cache line was sourced from an On Book Level-4 cache" }, { + "Unit": "CPU-M-CF", "EventCode": "136", "EventName": "L1I_ONBOOK_L4_SOURCED_WRITES", "BriefDescription": "L1I On-Book L4 Sourced Writes", "PublicDescription": "A directory write to the Level-1 I-Cache directory where the returned cache line was sourced from an On Book Level-4 cache" }, { + "Unit": "CPU-M-CF", "EventCode": "137", "EventName": "L1D_RO_EXCL_WRITES", "BriefDescription": "L1D Read-only Exclusive Writes", "PublicDescription": "A directory write to the Level-1 D-Cache where the line was originally in a Read-Only state in the cache but has been updated to be in the Exclusive state that allows stores to the cache line" }, { + "Unit": "CPU-M-CF", "EventCode": "138", "EventName": "L1D_OFFBOOK_L4_SOURCED_WRITES", "BriefDescription": "L1D Off-Book L4 Sourced Writes", "PublicDescription": "A directory write to the Level-1 D-Cache directory where the returned cache line was sourced from an Off Book Level-4 cache" }, { + "Unit": "CPU-M-CF", "EventCode": "139", "EventName": "L1I_OFFBOOK_L4_SOURCED_WRITES", "BriefDescription": "L1I Off-Book L4 Sourced Writes", "PublicDescription": "A directory write to the Level-1 I-Cache directory where the returned cache line was sourced from an Off Book Level-4 cache" }, { + "Unit": "CPU-M-CF", "EventCode": "140", "EventName": "DTLB1_HPAGE_WRITES", "BriefDescription": "DTLB1 One-Megabyte Page Writes", "PublicDescription": "A translation entry has been written to the Level-1 Data Translation Lookaside Buffer for a one-megabyte page" }, { + "Unit": "CPU-M-CF", "EventCode": "141", "EventName": "L1D_LMEM_SOURCED_WRITES", "BriefDescription": "L1D Local Memory Sourced Writes", "PublicDescription": "A directory write to the Level-1 D-Cache where the installed cache line was sourced from memory that is attached to the same book as the Data cache (Local Memory)" }, { + "Unit": "CPU-M-CF", "EventCode": "142", "EventName": "L1I_LMEM_SOURCED_WRITES", "BriefDescription": "L1I Local Memory Sourced Writes", "PublicDescription": "A directory write to the Level-1 I-Cache where the installed cache line was sourced from memory that is attached to the same book as the Instruction cache (Local Memory)" }, { + "Unit": "CPU-M-CF", "EventCode": "143", "EventName": "L1I_OFFBOOK_L3_SOURCED_WRITES", "BriefDescription": "L1I Off-Book L3 Sourced Writes", "PublicDescription": "A directory write to the Level-1 I-Cache directory where the returned cache line was sourced from an Off Book Level-3 cache" }, { + "Unit": "CPU-M-CF", "EventCode": "144", "EventName": "DTLB1_WRITES", "BriefDescription": "DTLB1 Writes", "PublicDescription": "A translation entry has been written to the Level-1 Data Translation Lookaside Buffer" }, { + "Unit": "CPU-M-CF", "EventCode": "145", "EventName": "ITLB1_WRITES", "BriefDescription": "ITLB1 Writes", "PublicDescription": "A translation entry has been written to the Level-1 Instruction Translation Lookaside Buffer" }, { + "Unit": "CPU-M-CF", "EventCode": "146", "EventName": "TLB2_PTE_WRITES", "BriefDescription": "TLB2 PTE Writes", "PublicDescription": "A translation entry has been written to the Level-2 TLB Page Table Entry arrays" }, { + "Unit": "CPU-M-CF", "EventCode": "147", "EventName": "TLB2_CRSTE_HPAGE_WRITES", "BriefDescription": "TLB2 CRSTE One-Megabyte Page Writes", "PublicDescription": "A translation entry has been written to the Level-2 TLB Common Region Segment Table Entry arrays for a one-megabyte large page translation" }, { + "Unit": "CPU-M-CF", "EventCode": "148", "EventName": "TLB2_CRSTE_WRITES", "BriefDescription": "TLB2 CRSTE Writes", "PublicDescription": "A translation entry has been written to the Level-2 TLB Common Region Segment Table Entry arrays" }, { + "Unit": "CPU-M-CF", "EventCode": "150", "EventName": "L1D_ONCHIP_L3_SOURCED_WRITES", "BriefDescription": "L1D On-Chip L3 Sourced Writes", "PublicDescription": "A directory write to the Level-1 D-Cache directory where the returned cache line was sourced from an On Chip Level-3 cache" }, { + "Unit": "CPU-M-CF", "EventCode": "152", "EventName": "L1D_OFFCHIP_L3_SOURCED_WRITES", "BriefDescription": "L1D Off-Chip L3 Sourced Writes", "PublicDescription": "A directory write to the Level-1 D-Cache directory where the returned cache line was sourced from an Off Chip/On Book Level-3 cache" }, { + "Unit": "CPU-M-CF", "EventCode": "153", "EventName": "L1I_ONCHIP_L3_SOURCED_WRITES", "BriefDescription": "L1I On-Chip L3 Sourced Writes", "PublicDescription": "A directory write to the Level-1 I-Cache directory where the returned cache line was sourced from an On Chip Level-3 cache" }, { + "Unit": "CPU-M-CF", "EventCode": "155", "EventName": "L1I_OFFCHIP_L3_SOURCED_WRITES", "BriefDescription": "L1I Off-Chip L3 Sourced Writes", diff --git a/tools/perf/pmu-events/arch/s390/cf_zec12/basic.json b/tools/perf/pmu-events/arch/s390/cf_zec12/basic.json index 8bf16759ca53..2dd8dafff2ef 100644 --- a/tools/perf/pmu-events/arch/s390/cf_zec12/basic.json +++ b/tools/perf/pmu-events/arch/s390/cf_zec12/basic.json @@ -1,71 +1,83 @@ [ { + "Unit": "CPU-M-CF", "EventCode": "0", "EventName": "CPU_CYCLES", "BriefDescription": "CPU Cycles", "PublicDescription": "Cycle Count" }, { + "Unit": "CPU-M-CF", "EventCode": "1", "EventName": "INSTRUCTIONS", "BriefDescription": "Instructions", "PublicDescription": "Instruction Count" }, { + "Unit": "CPU-M-CF", "EventCode": "2", "EventName": "L1I_DIR_WRITES", "BriefDescription": "L1I Directory Writes", "PublicDescription": "Level-1 I-Cache Directory Write Count" }, { + "Unit": "CPU-M-CF", "EventCode": "3", "EventName": "L1I_PENALTY_CYCLES", "BriefDescription": "L1I Penalty Cycles", "PublicDescription": "Level-1 I-Cache Penalty Cycle Count" }, { + "Unit": "CPU-M-CF", "EventCode": "4", "EventName": "L1D_DIR_WRITES", "BriefDescription": "L1D Directory Writes", "PublicDescription": "Level-1 D-Cache Directory Write Count" }, { + "Unit": "CPU-M-CF", "EventCode": "5", "EventName": "L1D_PENALTY_CYCLES", "BriefDescription": "L1D Penalty Cycles", "PublicDescription": "Level-1 D-Cache Penalty Cycle Count" }, { + "Unit": "CPU-M-CF", "EventCode": "32", "EventName": "PROBLEM_STATE_CPU_CYCLES", "BriefDescription": "Problem-State CPU Cycles", "PublicDescription": "Problem-State Cycle Count" }, { + "Unit": "CPU-M-CF", "EventCode": "33", "EventName": "PROBLEM_STATE_INSTRUCTIONS", "BriefDescription": "Problem-State Instructions", "PublicDescription": "Problem-State Instruction Count" }, { + "Unit": "CPU-M-CF", "EventCode": "34", "EventName": "PROBLEM_STATE_L1I_DIR_WRITES", "BriefDescription": "Problem-State L1I Directory Writes", "PublicDescription": "Problem-State Level-1 I-Cache Directory Write Count" }, { + "Unit": "CPU-M-CF", "EventCode": "35", "EventName": "PROBLEM_STATE_L1I_PENALTY_CYCLES", "BriefDescription": "Problem-State L1I Penalty Cycles", "PublicDescription": "Problem-State Level-1 I-Cache Penalty Cycle Count" }, { + "Unit": "CPU-M-CF", "EventCode": "36", "EventName": "PROBLEM_STATE_L1D_DIR_WRITES", "BriefDescription": "Problem-State L1D Directory Writes", "PublicDescription": "Problem-State Level-1 D-Cache Directory Write Count" }, { + "Unit": "CPU-M-CF", "EventCode": "37", "EventName": "PROBLEM_STATE_L1D_PENALTY_CYCLES", "BriefDescription": "Problem-State L1D Penalty Cycles", diff --git a/tools/perf/pmu-events/arch/s390/cf_zec12/crypto.json b/tools/perf/pmu-events/arch/s390/cf_zec12/crypto.json index 7e5b72492141..db286f19e7b6 100644 --- a/tools/perf/pmu-events/arch/s390/cf_zec12/crypto.json +++ b/tools/perf/pmu-events/arch/s390/cf_zec12/crypto.json @@ -1,95 +1,111 @@ [ { + "Unit": "CPU-M-CF", "EventCode": "64", "EventName": "PRNG_FUNCTIONS", "BriefDescription": "PRNG Functions", "PublicDescription": "Total number of the PRNG functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "65", "EventName": "PRNG_CYCLES", "BriefDescription": "PRNG Cycles", "PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing PRNG functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "66", "EventName": "PRNG_BLOCKED_FUNCTIONS", "BriefDescription": "PRNG Blocked Functions", "PublicDescription": "Total number of the PRNG functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "67", "EventName": "PRNG_BLOCKED_CYCLES", "BriefDescription": "PRNG Blocked Cycles", "PublicDescription": "Total number of CPU cycles blocked for the PRNG functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "68", "EventName": "SHA_FUNCTIONS", "BriefDescription": "SHA Functions", "PublicDescription": "Total number of SHA functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "69", "EventName": "SHA_CYCLES", "BriefDescription": "SHA Cycles", "PublicDescription": "Total number of CPU cycles when the SHA coprocessor is busy performing the SHA functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "70", "EventName": "SHA_BLOCKED_FUNCTIONS", "BriefDescription": "SHA Blocked Functions", "PublicDescription": "Total number of the SHA functions that are issued by the CPU and are blocked because the SHA coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "71", "EventName": "SHA_BLOCKED_CYCLES", "BriefDescription": "SHA Bloced Cycles", "PublicDescription": "Total number of CPU cycles blocked for the SHA functions issued by the CPU because the SHA coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "72", "EventName": "DEA_FUNCTIONS", "BriefDescription": "DEA Functions", "PublicDescription": "Total number of the DEA functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "73", "EventName": "DEA_CYCLES", "BriefDescription": "DEA Cycles", "PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the DEA functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "74", "EventName": "DEA_BLOCKED_FUNCTIONS", "BriefDescription": "DEA Blocked Functions", "PublicDescription": "Total number of the DEA functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "75", "EventName": "DEA_BLOCKED_CYCLES", "BriefDescription": "DEA Blocked Cycles", "PublicDescription": "Total number of CPU cycles blocked for the DEA functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "76", "EventName": "AES_FUNCTIONS", "BriefDescription": "AES Functions", "PublicDescription": "Total number of AES functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "77", "EventName": "AES_CYCLES", "BriefDescription": "AES Cycles", "PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the AES functions issued by the CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "78", "EventName": "AES_BLOCKED_FUNCTIONS", "BriefDescription": "AES Blocked Functions", "PublicDescription": "Total number of AES functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU" }, { + "Unit": "CPU-M-CF", "EventCode": "79", "EventName": "AES_BLOCKED_CYCLES", "BriefDescription": "AES Blocked Cycles", diff --git a/tools/perf/pmu-events/arch/s390/cf_zec12/extended.json b/tools/perf/pmu-events/arch/s390/cf_zec12/extended.json index 8682126aabb2..162251037219 100644 --- a/tools/perf/pmu-events/arch/s390/cf_zec12/extended.json +++ b/tools/perf/pmu-events/arch/s390/cf_zec12/extended.json @@ -1,209 +1,244 @@ [ { + "Unit": "CPU-M-CF", "EventCode": "128", "EventName": "DTLB1_MISSES", "BriefDescription": "DTLB1 Misses", "PublicDescription": "Level-1 Data TLB miss in progress. Incremented by one for every cycle a DTLB1 miss is in progress." }, { + "Unit": "CPU-M-CF", "EventCode": "129", "EventName": "ITLB1_MISSES", "BriefDescription": "ITLB1 Misses", "PublicDescription": "Level-1 Instruction TLB miss in progress. Incremented by one for every cycle a ITLB1 miss is in progress." }, { + "Unit": "CPU-M-CF", "EventCode": "130", "EventName": "L1D_L2I_SOURCED_WRITES", "BriefDescription": "L1D L2I Sourced Writes", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from the Level-2 Instruction cache" }, { + "Unit": "CPU-M-CF", "EventCode": "131", "EventName": "L1I_L2I_SOURCED_WRITES", "BriefDescription": "L1I L2I Sourced Writes", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from the Level-2 Instruction cache" }, { + "Unit": "CPU-M-CF", "EventCode": "132", "EventName": "L1D_L2D_SOURCED_WRITES", "BriefDescription": "L1D L2D Sourced Writes", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from the Level-2 Data cache" }, { + "Unit": "CPU-M-CF", "EventCode": "133", "EventName": "DTLB1_WRITES", "BriefDescription": "DTLB1 Writes", "PublicDescription": "A translation entry has been written to the Level-1 Data Translation Lookaside Buffer" }, { + "Unit": "CPU-M-CF", "EventCode": "135", "EventName": "L1D_LMEM_SOURCED_WRITES", "BriefDescription": "L1D Local Memory Sourced Writes", "PublicDescription": "A directory write to the Level-1 Data cache where the installed cache line was sourced from memory that is attached to the same book as the Data cache (Local Memory)" }, { + "Unit": "CPU-M-CF", "EventCode": "137", "EventName": "L1I_LMEM_SOURCED_WRITES", "BriefDescription": "L1I Local Memory Sourced Writes", "PublicDescription": "A directory write to the Level-1 Instruction cache where the installed cache line was sourced from memory that is attached to the same book as the Instruction cache (Local Memory)" }, { + "Unit": "CPU-M-CF", "EventCode": "138", "EventName": "L1D_RO_EXCL_WRITES", "BriefDescription": "L1D Read-only Exclusive Writes", "PublicDescription": "A directory write to the Level-1 D-Cache where the line was originally in a Read-Only state in the cache but has been updated to be in the Exclusive state that allows stores to the cache line" }, { + "Unit": "CPU-M-CF", "EventCode": "139", "EventName": "DTLB1_HPAGE_WRITES", "BriefDescription": "DTLB1 One-Megabyte Page Writes", "PublicDescription": "A translation entry has been written to the Level-1 Data Translation Lookaside Buffer for a one-megabyte page" }, { + "Unit": "CPU-M-CF", "EventCode": "140", "EventName": "ITLB1_WRITES", "BriefDescription": "ITLB1 Writes", "PublicDescription": "A translation entry has been written to the Level-1 Instruction Translation Lookaside Buffer" }, { + "Unit": "CPU-M-CF", "EventCode": "141", "EventName": "TLB2_PTE_WRITES", "BriefDescription": "TLB2 PTE Writes", "PublicDescription": "A translation entry has been written to the Level-2 TLB Page Table Entry arrays" }, { + "Unit": "CPU-M-CF", "EventCode": "142", "EventName": "TLB2_CRSTE_HPAGE_WRITES", "BriefDescription": "TLB2 CRSTE One-Megabyte Page Writes", "PublicDescription": "A translation entry has been written to the Level-2 TLB Common Region Segment Table Entry arrays for a one-megabyte large page translation" }, { + "Unit": "CPU-M-CF", "EventCode": "143", "EventName": "TLB2_CRSTE_WRITES", "BriefDescription": "TLB2 CRSTE Writes", "PublicDescription": "A translation entry has been written to the Level-2 TLB Common Region Segment Table Entry arrays" }, { + "Unit": "CPU-M-CF", "EventCode": "144", "EventName": "L1D_ONCHIP_L3_SOURCED_WRITES", "BriefDescription": "L1D On-Chip L3 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On Chip Level-3 cache without intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "145", "EventName": "L1D_OFFCHIP_L3_SOURCED_WRITES", "BriefDescription": "L1D Off-Chip L3 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off Chip/On Book Level-3 cache without intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "146", "EventName": "L1D_OFFBOOK_L3_SOURCED_WRITES", "BriefDescription": "L1D Off-Book L3 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off Book Level-3 cache without intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "147", "EventName": "L1D_ONBOOK_L4_SOURCED_WRITES", "BriefDescription": "L1D On-Book L4 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On Book Level-4 cache" }, { + "Unit": "CPU-M-CF", "EventCode": "148", "EventName": "L1D_OFFBOOK_L4_SOURCED_WRITES", "BriefDescription": "L1D Off-Book L4 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off Book Level-4 cache" }, { + "Unit": "CPU-M-CF", "EventCode": "149", "EventName": "TX_NC_TEND", "BriefDescription": "Completed TEND instructions in non-constrained TX mode", "PublicDescription": "A TEND instruction has completed in a nonconstrained transactional-execution mode" }, { + "Unit": "CPU-M-CF", "EventCode": "150", "EventName": "L1D_ONCHIP_L3_SOURCED_WRITES_IV", "BriefDescription": "L1D On-Chip L3 Sourced Writes with Intervention", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from a On Chip Level-3 cache with intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "151", "EventName": "L1D_OFFCHIP_L3_SOURCED_WRITES_IV", "BriefDescription": "L1D Off-Chip L3 Sourced Writes with Intervention", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off Chip/On Book Level-3 cache with intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "152", "EventName": "L1D_OFFBOOK_L3_SOURCED_WRITES_IV", "BriefDescription": "L1D Off-Book L3 Sourced Writes with Intervention", "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off Book Level-3 cache with intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "153", "EventName": "L1I_ONCHIP_L3_SOURCED_WRITES", "BriefDescription": "L1I On-Chip L3 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On Chip Level-3 cache without intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "154", "EventName": "L1I_OFFCHIP_L3_SOURCED_WRITES", "BriefDescription": "L1I Off-Chip L3 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off Chip/On Book Level-3 cache without intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "155", "EventName": "L1I_OFFBOOK_L3_SOURCED_WRITES", "BriefDescription": "L1I Off-Book L3 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off Book Level-3 cache without intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "156", "EventName": "L1I_ONBOOK_L4_SOURCED_WRITES", "BriefDescription": "L1I On-Book L4 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On Book Level-4 cache" }, { + "Unit": "CPU-M-CF", "EventCode": "157", "EventName": "L1I_OFFBOOK_L4_SOURCED_WRITES", "BriefDescription": "L1I Off-Book L4 Sourced Writes", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off Book Level-4 cache" }, { + "Unit": "CPU-M-CF", "EventCode": "158", "EventName": "TX_C_TEND", "BriefDescription": "Completed TEND instructions in constrained TX mode", "PublicDescription": "A TEND instruction has completed in a constrained transactional-execution mode" }, { + "Unit": "CPU-M-CF", "EventCode": "159", "EventName": "L1I_ONCHIP_L3_SOURCED_WRITES_IV", "BriefDescription": "L1I On-Chip L3 Sourced Writes with Intervention", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On Chip Level-3 cache with intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "160", "EventName": "L1I_OFFCHIP_L3_SOURCED_WRITES_IV", "BriefDescription": "L1I Off-Chip L3 Sourced Writes with Intervention", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off Chip/On Book Level-3 cache with intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "161", "EventName": "L1I_OFFBOOK_L3_SOURCED_WRITES_IV", "BriefDescription": "L1I Off-Book L3 Sourced Writes with Intervention", "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off Book Level-3 cache with intervention" }, { + "Unit": "CPU-M-CF", "EventCode": "177", "EventName": "TX_NC_TABORT", "BriefDescription": "Aborted transactions in non-constrained TX mode", "PublicDescription": "A transaction abort has occurred in a nonconstrained transactional-execution mode" }, { + "Unit": "CPU-M-CF", "EventCode": "178", "EventName": "TX_C_TABORT_NO_SPECIAL", "BriefDescription": "Aborted transactions in constrained TX mode not using special completion logic", "PublicDescription": "A transaction abort has occurred in a constrained transactional-execution mode and the CPU is not using any special logic to allow the transaction to complete" }, { + "Unit": "CPU-M-CF", "EventCode": "179", "EventName": "TX_C_TABORT_SPECIAL", "BriefDescription": "Aborted transactions in constrained TX mode using special completion logic", diff --git a/tools/perf/pmu-events/arch/s390/cf_zec12/transaction.json b/tools/perf/pmu-events/arch/s390/cf_zec12/transaction.json new file mode 100644 index 000000000000..1a0034f79f73 --- /dev/null +++ b/tools/perf/pmu-events/arch/s390/cf_zec12/transaction.json @@ -0,0 +1,7 @@ +[ + { + "BriefDescription": "Transaction count", + "MetricName": "transaction", + "MetricExpr": "TX_C_TEND + TX_NC_TEND + TX_NC_TABORT + TX_C_TABORT_SPECIAL + TX_C_TABORT_NO_SPECIAL" + } +] diff --git a/tools/perf/pmu-events/jevents.c b/tools/perf/pmu-events/jevents.c index db3a594ee1e4..68c92bb599ee 100644 --- a/tools/perf/pmu-events/jevents.c +++ b/tools/perf/pmu-events/jevents.c @@ -233,6 +233,8 @@ static struct map { { "QPI LL", "uncore_qpi" }, { "SBO", "uncore_sbox" }, { "iMPH-U", "uncore_arb" }, + { "CPU-M-CF", "cpum_cf" }, + { "CPU-M-SF", "cpum_sf" }, {} }; diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c index dd850a26d579..d7a5e1b9aa6f 100644 --- a/tools/perf/tests/builtin-test.c +++ b/tools/perf/tests/builtin-test.c @@ -385,7 +385,7 @@ static int test_and_print(struct test *t, bool force_skip, int subtest) if (!t->subtest.get_nr) pr_debug("%s:", t->desc); else - pr_debug("%s subtest %d:", t->desc, subtest); + pr_debug("%s subtest %d:", t->desc, subtest + 1); switch (err) { case TEST_OK: diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c index 61211918bfba..3b97ac018d5a 100644 --- a/tools/perf/tests/parse-events.c +++ b/tools/perf/tests/parse-events.c @@ -1322,6 +1322,14 @@ static int test__intel_pt(struct perf_evlist *evlist) return 0; } +static int test__checkevent_complex_name(struct perf_evlist *evlist) +{ + struct perf_evsel *evsel = perf_evlist__first(evlist); + + TEST_ASSERT_VAL("wrong complex name parsing", strcmp(evsel->name, "COMPLEX_CYCLES_NAME:orig=cycles,desc=chip-clock-ticks") == 0); + return 0; +} + static int count_tracepoints(void) { struct dirent *events_ent; @@ -1658,6 +1666,11 @@ static struct evlist_test test__events[] = { .check = test__intel_pt, .id = 52, }, + { + .name = "cycles/name='COMPLEX_CYCLES_NAME:orig=cycles,desc=chip-clock-ticks'/Duk", + .check = test__checkevent_complex_name, + .id = 53 + } }; static struct evlist_test test__events_pmu[] = { @@ -1676,6 +1689,11 @@ static struct evlist_test test__events_pmu[] = { .check = test__checkevent_pmu_partial_time_callgraph, .id = 2, }, + { + .name = "cpu/name='COMPLEX_CYCLES_NAME:orig=cycles,desc=chip-clock-ticks',period=0x1,event=0x2/ukp", + .check = test__checkevent_complex_name, + .id = 3, + } }; struct terms_test { diff --git a/tools/perf/tests/shell/record+probe_libc_inet_pton.sh b/tools/perf/tests/shell/record+probe_libc_inet_pton.sh index 94e513e62b34..3013ac8f83d0 100755 --- a/tools/perf/tests/shell/record+probe_libc_inet_pton.sh +++ b/tools/perf/tests/shell/record+probe_libc_inet_pton.sh @@ -13,11 +13,24 @@ libc=$(grep -w libc /proc/self/maps | head -1 | sed -r 's/.*[[:space:]](\/.*)/\1/g') nm -Dg $libc 2>/dev/null | fgrep -q inet_pton || exit 254 +event_pattern='probe_libc:inet_pton(\_[[:digit:]]+)?' + +add_libc_inet_pton_event() { + + event_name=$(perf probe -f -x $libc -a inet_pton 2>&1 | tail -n +2 | head -n -5 | \ + grep -P -o "$event_pattern(?=[[:space:]]\(on inet_pton in $libc\))") + + if [ $? -ne 0 -o -z "$event_name" ] ; then + printf "FAIL: could not add event\n" + return 1 + fi +} + trace_libc_inet_pton_backtrace() { expected=`mktemp -u /tmp/expected.XXX` - echo "ping[][0-9 \.:]+probe_libc:inet_pton: \([[:xdigit:]]+\)" > $expected + echo "ping[][0-9 \.:]+$event_name: \([[:xdigit:]]+\)" > $expected echo ".*inet_pton\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$" >> $expected case "$(uname -m)" in s390x) @@ -26,6 +39,12 @@ trace_libc_inet_pton_backtrace() { echo "(__GI_)?getaddrinfo\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$" >> $expected echo "main\+0x[[:xdigit:]]+[[:space:]]\(.*/bin/ping.*\)$" >> $expected ;; + ppc64|ppc64le) + eventattr='max-stack=4' + echo "gaih_inet.*\+0x[[:xdigit:]]+[[:space:]]\($libc\)$" >> $expected + echo "getaddrinfo\+0x[[:xdigit:]]+[[:space:]]\($libc\)$" >> $expected + echo ".*\+0x[[:xdigit:]]+[[:space:]]\(.*/bin/ping.*\)$" >> $expected + ;; *) eventattr='max-stack=3' echo "getaddrinfo\+0x[[:xdigit:]]+[[:space:]]\($libc\)$" >> $expected @@ -35,7 +54,7 @@ trace_libc_inet_pton_backtrace() { perf_data=`mktemp -u /tmp/perf.data.XXX` perf_script=`mktemp -u /tmp/perf.script.XXX` - perf record -e probe_libc:inet_pton/$eventattr/ -o $perf_data ping -6 -c 1 ::1 > /dev/null 2>&1 + perf record -e $event_name/$eventattr/ -o $perf_data ping -6 -c 1 ::1 > /dev/null 2>&1 perf script -i $perf_data > $perf_script exec 3<$perf_script @@ -46,7 +65,7 @@ trace_libc_inet_pton_backtrace() { echo "$line" | egrep -q "$pattern" if [ $? -ne 0 ] ; then printf "FAIL: expected backtrace entry \"%s\" got \"%s\"\n" "$pattern" "$line" - exit 1 + return 1 fi done @@ -56,13 +75,20 @@ trace_libc_inet_pton_backtrace() { # even if the perf script output does not match. } +delete_libc_inet_pton_event() { + + if [ -n "$event_name" ] ; then + perf probe -q -d $event_name + fi +} + # Check for IPv6 interface existence ip a sh lo | fgrep -q inet6 || exit 2 skip_if_no_perf_probe && \ -perf probe -q $libc inet_pton && \ +add_libc_inet_pton_event && \ trace_libc_inet_pton_backtrace err=$? rm -f ${perf_data} ${perf_script} ${expected} -perf probe -q -d probe_libc:inet_pton +delete_libc_inet_pton_event exit $err diff --git a/tools/perf/trace/beauty/Build b/tools/perf/trace/beauty/Build index 66330d4b739b..f528ba35e140 100644 --- a/tools/perf/trace/beauty/Build +++ b/tools/perf/trace/beauty/Build @@ -7,4 +7,5 @@ endif libperf-y += kcmp.o libperf-y += pkey_alloc.o libperf-y += prctl.o +libperf-y += socket.o libperf-y += statx.o diff --git a/tools/perf/trace/beauty/beauty.h b/tools/perf/trace/beauty/beauty.h index 984a504d335c..9615af5d412b 100644 --- a/tools/perf/trace/beauty/beauty.h +++ b/tools/perf/trace/beauty/beauty.h @@ -106,6 +106,9 @@ size_t syscall_arg__scnprintf_prctl_arg2(char *bf, size_t size, struct syscall_a size_t syscall_arg__scnprintf_prctl_arg3(char *bf, size_t size, struct syscall_arg *arg); #define SCA_PRCTL_ARG3 syscall_arg__scnprintf_prctl_arg3 +size_t syscall_arg__scnprintf_socket_protocol(char *bf, size_t size, struct syscall_arg *arg); +#define SCA_SK_PROTO syscall_arg__scnprintf_socket_protocol + size_t syscall_arg__scnprintf_statx_flags(char *bf, size_t size, struct syscall_arg *arg); #define SCA_STATX_FLAGS syscall_arg__scnprintf_statx_flags diff --git a/tools/perf/trace/beauty/drm_ioctl.sh b/tools/perf/trace/beauty/drm_ioctl.sh index 2149d3a98e42..9d3816815e60 100755 --- a/tools/perf/trace/beauty/drm_ioctl.sh +++ b/tools/perf/trace/beauty/drm_ioctl.sh @@ -1,13 +1,14 @@ #!/bin/sh -drm_header_dir=$1 +[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/drm/ + printf "#ifndef DRM_COMMAND_BASE\n" -grep "#define DRM_COMMAND_BASE" $drm_header_dir/drm.h +grep "#define DRM_COMMAND_BASE" $header_dir/drm.h printf "#endif\n" printf "static const char *drm_ioctl_cmds[] = {\n" -grep "^#define DRM_IOCTL.*DRM_IO" $drm_header_dir/drm.h | \ +grep "^#define DRM_IOCTL.*DRM_IO" $header_dir/drm.h | \ sed -r 's/^#define +DRM_IOCTL_([A-Z0-9_]+)[ ]+DRM_IO[A-Z]* *\( *(0x[[:xdigit:]]+),*.*/ [\2] = "\1",/g' -grep "^#define DRM_I915_[A-Z_0-9]\+[ ]\+0x" $drm_header_dir/i915_drm.h | \ +grep "^#define DRM_I915_[A-Z_0-9]\+[ ]\+0x" $header_dir/i915_drm.h | \ sed -r 's/^#define +DRM_I915_([A-Z0-9_]+)[ ]+(0x[[:xdigit:]]+)/\t[DRM_COMMAND_BASE + \2] = "I915_\1",/g' printf "};\n" diff --git a/tools/perf/trace/beauty/kcmp_type.sh b/tools/perf/trace/beauty/kcmp_type.sh index 40d063b8c082..a3c304caa336 100755 --- a/tools/perf/trace/beauty/kcmp_type.sh +++ b/tools/perf/trace/beauty/kcmp_type.sh @@ -1,6 +1,6 @@ #!/bin/sh -header_dir=$1 +[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/ printf "static const char *kcmp_types[] = {\n" regex='^[[:space:]]+(KCMP_(\w+)),' diff --git a/tools/perf/trace/beauty/kvm_ioctl.sh b/tools/perf/trace/beauty/kvm_ioctl.sh index bd28817afced..c4699fd46bb6 100755 --- a/tools/perf/trace/beauty/kvm_ioctl.sh +++ b/tools/perf/trace/beauty/kvm_ioctl.sh @@ -1,10 +1,10 @@ #!/bin/sh -kvm_header_dir=$1 +[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/ printf "static const char *kvm_ioctl_cmds[] = {\n" regex='^#[[:space:]]*define[[:space:]]+KVM_(\w+)[[:space:]]+_IO[RW]*\([[:space:]]*KVMIO[[:space:]]*,[[:space:]]*(0x[[:xdigit:]]+).*' -egrep $regex ${kvm_header_dir}/kvm.h | \ +egrep $regex ${header_dir}/kvm.h | \ sed -r "s/$regex/\2 \1/g" | \ egrep -v " ((ARM|PPC|S390)_|[GS]ET_(DEBUGREGS|PIT2|XSAVE|TSC_KHZ)|CREATE_SPAPR_TCE_64)" | \ sort | xargs printf "\t[%s] = \"%s\",\n" diff --git a/tools/perf/trace/beauty/madvise_behavior.sh b/tools/perf/trace/beauty/madvise_behavior.sh index 60ef8640ee70..431639eb4d29 100755 --- a/tools/perf/trace/beauty/madvise_behavior.sh +++ b/tools/perf/trace/beauty/madvise_behavior.sh @@ -1,6 +1,6 @@ #!/bin/sh -header_dir=$1 +[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/asm-generic/ printf "static const char *madvise_advices[] = {\n" regex='^[[:space:]]*#[[:space:]]*define[[:space:]]+MADV_([[:alnum:]_]+)[[:space:]]+([[:digit:]]+)[[:space:]]*.*' diff --git a/tools/perf/trace/beauty/perf_ioctl.sh b/tools/perf/trace/beauty/perf_ioctl.sh index faea4237c793..6492c74df928 100755 --- a/tools/perf/trace/beauty/perf_ioctl.sh +++ b/tools/perf/trace/beauty/perf_ioctl.sh @@ -1,6 +1,6 @@ #!/bin/sh -header_dir=$1 +[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/ printf "static const char *perf_ioctl_cmds[] = {\n" regex='^#[[:space:]]*define[[:space:]]+PERF_EVENT_IOC_(\w+)[[:space:]]+_IO[RW]*[[:space:]]*\([[:space:]]*.\$.[[:space:]]*,[[:space:]]*([[:digit:]]+).*' diff --git a/tools/perf/trace/beauty/pkey_alloc_access_rights.sh b/tools/perf/trace/beauty/pkey_alloc_access_rights.sh index 62e51a02b839..e0a51aeb20b2 100755 --- a/tools/perf/trace/beauty/pkey_alloc_access_rights.sh +++ b/tools/perf/trace/beauty/pkey_alloc_access_rights.sh @@ -1,6 +1,6 @@ #!/bin/sh -header_dir=$1 +[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/asm-generic/ printf "static const char *pkey_alloc_access_rights[] = {\n" regex='^[[:space:]]*#[[:space:]]*define[[:space:]]+PKEY_([[:alnum:]_]+)[[:space:]]+(0x[[:xdigit:]]+)[[:space:]]*' diff --git a/tools/perf/trace/beauty/sndrv_ctl_ioctl.sh b/tools/perf/trace/beauty/sndrv_ctl_ioctl.sh index aad5ab130539..eb511bb5fbd3 100755 --- a/tools/perf/trace/beauty/sndrv_ctl_ioctl.sh +++ b/tools/perf/trace/beauty/sndrv_ctl_ioctl.sh @@ -1,8 +1,8 @@ #!/bin/sh -sound_header_dir=$1 +[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/sound/ printf "static const char *sndrv_ctl_ioctl_cmds[] = {\n" -grep "^#define[\t ]\+SNDRV_CTL_IOCTL_" $sound_header_dir/asound.h | \ +grep "^#define[\t ]\+SNDRV_CTL_IOCTL_" $header_dir/asound.h | \ sed -r 's/^#define +SNDRV_CTL_IOCTL_([A-Z0-9_]+)[\t ]+_IO[RW]*\( *.U., *(0x[[:xdigit:]]+),?.*/\t[\2] = \"\1\",/g' printf "};\n" diff --git a/tools/perf/trace/beauty/sndrv_pcm_ioctl.sh b/tools/perf/trace/beauty/sndrv_pcm_ioctl.sh index b7e9ef6b2f55..6818392968b2 100755 --- a/tools/perf/trace/beauty/sndrv_pcm_ioctl.sh +++ b/tools/perf/trace/beauty/sndrv_pcm_ioctl.sh @@ -1,8 +1,8 @@ #!/bin/sh -sound_header_dir=$1 +[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/sound/ printf "static const char *sndrv_pcm_ioctl_cmds[] = {\n" -grep "^#define[\t ]\+SNDRV_PCM_IOCTL_" $sound_header_dir/asound.h | \ +grep "^#define[\t ]\+SNDRV_PCM_IOCTL_" $header_dir/asound.h | \ sed -r 's/^#define +SNDRV_PCM_IOCTL_([A-Z0-9_]+)[\t ]+_IO[RW]*\( *.A., *(0x[[:xdigit:]]+),?.*/\t[\2] = \"\1\",/g' printf "};\n" diff --git a/tools/perf/trace/beauty/socket.c b/tools/perf/trace/beauty/socket.c new file mode 100644 index 000000000000..65227269384b --- /dev/null +++ b/tools/perf/trace/beauty/socket.c @@ -0,0 +1,28 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * trace/beauty/socket.c + * + * Copyright (C) 2018, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com> + */ + +#include "trace/beauty/beauty.h" +#include <sys/types.h> +#include <sys/socket.h> + +static size_t socket__scnprintf_ipproto(int protocol, char *bf, size_t size) +{ +#include "trace/beauty/generated/socket_ipproto_array.c" + static DEFINE_STRARRAY(socket_ipproto); + + return strarray__scnprintf(&strarray__socket_ipproto, bf, size, "%d", protocol); +} + +size_t syscall_arg__scnprintf_socket_protocol(char *bf, size_t size, struct syscall_arg *arg) +{ + int domain = syscall_arg__val(arg, 0); + + if (domain == AF_INET || domain == AF_INET6) + return socket__scnprintf_ipproto(arg->val, bf, size); + + return syscall_arg__scnprintf_int(bf, size, arg); +} diff --git a/tools/perf/trace/beauty/socket_ipproto.sh b/tools/perf/trace/beauty/socket_ipproto.sh new file mode 100755 index 000000000000..a3cc24633bec --- /dev/null +++ b/tools/perf/trace/beauty/socket_ipproto.sh @@ -0,0 +1,11 @@ +#!/bin/sh + +[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/ + +printf "static const char *socket_ipproto[] = {\n" +regex='^[[:space:]]+IPPROTO_(\w+)[[:space:]]+=[[:space:]]+([[:digit:]]+),.*' + +egrep $regex ${header_dir}/in.h | \ + sed -r "s/$regex/\2 \1/g" | \ + sort | xargs printf "\t[%s] = \"%s\",\n" +printf "};\n" diff --git a/tools/perf/trace/beauty/vhost_virtio_ioctl.sh b/tools/perf/trace/beauty/vhost_virtio_ioctl.sh index 76f1de697787..0f6a5197d0be 100755 --- a/tools/perf/trace/beauty/vhost_virtio_ioctl.sh +++ b/tools/perf/trace/beauty/vhost_virtio_ioctl.sh @@ -1,17 +1,17 @@ #!/bin/sh -vhost_virtio_header_dir=$1 +[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/ printf "static const char *vhost_virtio_ioctl_cmds[] = {\n" regex='^#[[:space:]]*define[[:space:]]+VHOST_(\w+)[[:space:]]+_IOW?\([[:space:]]*VHOST_VIRTIO[[:space:]]*,[[:space:]]*(0x[[:xdigit:]]+).*' -egrep $regex ${vhost_virtio_header_dir}/vhost.h | \ +egrep $regex ${header_dir}/vhost.h | \ sed -r "s/$regex/\2 \1/g" | \ sort | xargs printf "\t[%s] = \"%s\",\n" printf "};\n" printf "static const char *vhost_virtio_ioctl_read_cmds[] = {\n" regex='^#[[:space:]]*define[[:space:]]+VHOST_(\w+)[[:space:]]+_IOW?R\([[:space:]]*VHOST_VIRTIO[[:space:]]*,[[:space:]]*(0x[[:xdigit:]]+).*' -egrep $regex ${vhost_virtio_header_dir}/vhost.h | \ +egrep $regex ${header_dir}/vhost.h | \ sed -r "s/$regex/\2 \1/g" | \ sort | xargs printf "\t[%s] = \"%s\",\n" printf "};\n" diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c index 69b7a28f7a1c..74c4ae1f0a05 100644 --- a/tools/perf/ui/stdio/hist.c +++ b/tools/perf/ui/stdio/hist.c @@ -529,7 +529,7 @@ out: static int hist_entry__fprintf(struct hist_entry *he, size_t size, char *bf, size_t bfsz, FILE *fp, - bool use_callchain) + bool ignore_callchains) { int ret; int callchain_ret = 0; @@ -550,7 +550,7 @@ static int hist_entry__fprintf(struct hist_entry *he, size_t size, ret = fprintf(fp, "%s\n", bf); - if (hist_entry__has_callchains(he) && use_callchain) + if (hist_entry__has_callchains(he) && !ignore_callchains) callchain_ret = hist_entry_callchain__fprintf(he, total_period, 0, fp); @@ -755,7 +755,7 @@ int hists__fprintf_headers(struct hists *hists, FILE *fp) size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows, int max_cols, float min_pcnt, FILE *fp, - bool use_callchain) + bool ignore_callchains) { struct rb_node *nd; size_t ret = 0; @@ -799,7 +799,7 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows, if (percent < min_pcnt) continue; - ret += hist_entry__fprintf(h, max_cols, line, linesz, fp, use_callchain); + ret += hist_entry__fprintf(h, max_cols, line, linesz, fp, ignore_callchains); if (max_rows && ++nr_rows >= max_rows) break; diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c index cee658733e2c..3d02ae38ec56 100644 --- a/tools/perf/util/bpf-loader.c +++ b/tools/perf/util/bpf-loader.c @@ -747,7 +747,9 @@ int bpf__load(struct bpf_object *obj) err = bpf_object__load(obj); if (err) { - pr_debug("bpf: load objects failed\n"); + char bf[128]; + libbpf_strerror(err, bf, sizeof(bf)); + pr_debug("bpf: load objects failed: err=%d: (%s)\n", err, bf); return err; } return 0; diff --git a/tools/perf/util/comm.c b/tools/perf/util/comm.c index 7798a2cc8a86..31279a7bd919 100644 --- a/tools/perf/util/comm.c +++ b/tools/perf/util/comm.c @@ -20,9 +20,10 @@ static struct rw_semaphore comm_str_lock = {.lock = PTHREAD_RWLOCK_INITIALIZER,} static struct comm_str *comm_str__get(struct comm_str *cs) { - if (cs) - refcount_inc(&cs->refcnt); - return cs; + if (cs && refcount_inc_not_zero(&cs->refcnt)) + return cs; + + return NULL; } static void comm_str__put(struct comm_str *cs) @@ -67,9 +68,14 @@ struct comm_str *__comm_str__findnew(const char *str, struct rb_root *root) parent = *p; iter = rb_entry(parent, struct comm_str, rb_node); + /* + * If we race with comm_str__put, iter->refcnt is 0 + * and it will be removed within comm_str__put call + * shortly, ignore it in this search. + */ cmp = strcmp(str, iter->str); - if (!cmp) - return comm_str__get(iter); + if (!cmp && comm_str__get(iter)) + return iter; if (cmp < 0) p = &(*p)->rb_left; diff --git a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c index 4d5fc374e730..938def6d0bb9 100644 --- a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c +++ b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c @@ -31,6 +31,8 @@ #endif #endif +#define CS_ETM_INVAL_ADDR 0xdeadbeefdeadbeefUL + struct cs_etm_decoder { void *data; void (*packet_printer)(const char *msg); @@ -261,8 +263,8 @@ static void cs_etm_decoder__clear_buffer(struct cs_etm_decoder *decoder) decoder->tail = 0; decoder->packet_count = 0; for (i = 0; i < MAX_BUFFER; i++) { - decoder->packet_buffer[i].start_addr = 0xdeadbeefdeadbeefUL; - decoder->packet_buffer[i].end_addr = 0xdeadbeefdeadbeefUL; + decoder->packet_buffer[i].start_addr = CS_ETM_INVAL_ADDR; + decoder->packet_buffer[i].end_addr = CS_ETM_INVAL_ADDR; decoder->packet_buffer[i].last_instr_taken_branch = false; decoder->packet_buffer[i].exc = false; decoder->packet_buffer[i].exc_ret = false; @@ -295,8 +297,8 @@ cs_etm_decoder__buffer_packet(struct cs_etm_decoder *decoder, decoder->packet_buffer[et].exc = false; decoder->packet_buffer[et].exc_ret = false; decoder->packet_buffer[et].cpu = *((int *)inode->priv); - decoder->packet_buffer[et].start_addr = 0xdeadbeefdeadbeefUL; - decoder->packet_buffer[et].end_addr = 0xdeadbeefdeadbeefUL; + decoder->packet_buffer[et].start_addr = CS_ETM_INVAL_ADDR; + decoder->packet_buffer[et].end_addr = CS_ETM_INVAL_ADDR; if (decoder->packet_count == MAX_BUFFER - 1) return OCSD_RESP_WAIT; diff --git a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.h b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.h index 743f5f444304..612b5755f742 100644 --- a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.h +++ b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.h @@ -23,6 +23,7 @@ struct cs_etm_buffer { }; enum cs_etm_sample_type { + CS_ETM_EMPTY = 0, CS_ETM_RANGE = 1 << 0, CS_ETM_TRACE_ON = 1 << 1, }; diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c index 822ba915d144..2ae640257fdb 100644 --- a/tools/perf/util/cs-etm.c +++ b/tools/perf/util/cs-etm.c @@ -494,6 +494,10 @@ static inline void cs_etm__reset_last_branch_rb(struct cs_etm_queue *etmq) static inline u64 cs_etm__last_executed_instr(struct cs_etm_packet *packet) { + /* Returns 0 for the CS_ETM_TRACE_ON packet */ + if (packet->sample_type == CS_ETM_TRACE_ON) + return 0; + /* * The packet records the execution range with an exclusive end address * @@ -505,6 +509,15 @@ static inline u64 cs_etm__last_executed_instr(struct cs_etm_packet *packet) return packet->end_addr - A64_INSTR_SIZE; } +static inline u64 cs_etm__first_executed_instr(struct cs_etm_packet *packet) +{ + /* Returns 0 for the CS_ETM_TRACE_ON packet */ + if (packet->sample_type == CS_ETM_TRACE_ON) + return 0; + + return packet->start_addr; +} + static inline u64 cs_etm__instr_count(const struct cs_etm_packet *packet) { /* @@ -546,7 +559,7 @@ static void cs_etm__update_last_branch_rb(struct cs_etm_queue *etmq) be = &bs->entries[etmq->last_branch_pos]; be->from = cs_etm__last_executed_instr(etmq->prev_packet); - be->to = etmq->packet->start_addr; + be->to = cs_etm__first_executed_instr(etmq->packet); /* No support for mispredict */ be->flags.mispred = 0; be->flags.predicted = 1; @@ -701,7 +714,7 @@ static int cs_etm__synth_branch_sample(struct cs_etm_queue *etmq) sample.ip = cs_etm__last_executed_instr(etmq->prev_packet); sample.pid = etmq->pid; sample.tid = etmq->tid; - sample.addr = etmq->packet->start_addr; + sample.addr = cs_etm__first_executed_instr(etmq->packet); sample.id = etmq->etm->branches_id; sample.stream_id = etmq->etm->branches_id; sample.period = 1; @@ -897,13 +910,23 @@ static int cs_etm__sample(struct cs_etm_queue *etmq) etmq->period_instructions = instrs_over; } - if (etm->sample_branches && - etmq->prev_packet && - etmq->prev_packet->sample_type == CS_ETM_RANGE && - etmq->prev_packet->last_instr_taken_branch) { - ret = cs_etm__synth_branch_sample(etmq); - if (ret) - return ret; + if (etm->sample_branches && etmq->prev_packet) { + bool generate_sample = false; + + /* Generate sample for tracing on packet */ + if (etmq->prev_packet->sample_type == CS_ETM_TRACE_ON) + generate_sample = true; + + /* Generate sample for branch taken packet */ + if (etmq->prev_packet->sample_type == CS_ETM_RANGE && + etmq->prev_packet->last_instr_taken_branch) + generate_sample = true; + + if (generate_sample) { + ret = cs_etm__synth_branch_sample(etmq); + if (ret) + return ret; + } } if (etm->sample_branches || etm->synth_opts.last_branch) { @@ -922,10 +945,17 @@ static int cs_etm__sample(struct cs_etm_queue *etmq) static int cs_etm__flush(struct cs_etm_queue *etmq) { int err = 0; + struct cs_etm_auxtrace *etm = etmq->etm; struct cs_etm_packet *tmp; + if (!etmq->prev_packet) + return 0; + + /* Handle start tracing packet */ + if (etmq->prev_packet->sample_type == CS_ETM_EMPTY) + goto swap_packet; + if (etmq->etm->synth_opts.last_branch && - etmq->prev_packet && etmq->prev_packet->sample_type == CS_ETM_RANGE) { /* * Generate a last branch event for the branches left in the @@ -939,8 +969,22 @@ static int cs_etm__flush(struct cs_etm_queue *etmq) err = cs_etm__synth_instruction_sample( etmq, addr, etmq->period_instructions); + if (err) + return err; + etmq->period_instructions = 0; + } + + if (etm->sample_branches && + etmq->prev_packet->sample_type == CS_ETM_RANGE) { + err = cs_etm__synth_branch_sample(etmq); + if (err) + return err; + } + +swap_packet: + if (etmq->etm->synth_opts.last_branch) { /* * Swap PACKET with PREV_PACKET: PACKET becomes PREV_PACKET for * the next incoming packet. @@ -1020,6 +1064,13 @@ static int cs_etm__run_decoder(struct cs_etm_queue *etmq) */ cs_etm__flush(etmq); break; + case CS_ETM_EMPTY: + /* + * Should not receive empty packet, + * report error. + */ + pr_err("CS ETM Trace: empty packet\n"); + return -EINVAL; default: break; } diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 94fce4f537e9..ddf84b941abf 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -260,6 +260,17 @@ struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx) evsel->attr.sample_period = 1; } + if (perf_evsel__is_clock(evsel)) { + /* + * The evsel->unit points to static alias->unit + * so it's ok to use static string in here. + */ + static const char *unit = "msec"; + + evsel->unit = unit; + evsel->scale = 1e-6; + } + return evsel; } @@ -848,6 +859,12 @@ static void apply_config_terms(struct perf_evsel *evsel, } } +static bool is_dummy_event(struct perf_evsel *evsel) +{ + return (evsel->attr.type == PERF_TYPE_SOFTWARE) && + (evsel->attr.config == PERF_COUNT_SW_DUMMY); +} + /* * The enable_on_exec/disabled value strategy: * @@ -1086,6 +1103,14 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts, else perf_evsel__reset_sample_bit(evsel, PERIOD); } + + /* + * For initial_delay, a dummy event is added implicitly. + * The software event will trigger -EOPNOTSUPP error out, + * if BRANCH_STACK bit is set. + */ + if (opts->initial_delay && is_dummy_event(evsel)) + perf_evsel__reset_sample_bit(evsel, BRANCH_STACK); } static int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads) diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index d277930b19a1..973c03167947 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -402,10 +402,13 @@ bool perf_evsel__is_function_event(struct perf_evsel *evsel); static inline bool perf_evsel__is_bpf_output(struct perf_evsel *evsel) { - struct perf_event_attr *attr = &evsel->attr; + return perf_evsel__match(evsel, SOFTWARE, SW_BPF_OUTPUT); +} - return (attr->config == PERF_COUNT_SW_BPF_OUTPUT) && - (attr->type == PERF_TYPE_SOFTWARE); +static inline bool perf_evsel__is_clock(struct perf_evsel *evsel) +{ + return perf_evsel__match(evsel, SOFTWARE, SW_CPU_CLOCK) || + perf_evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK); } struct perf_attr_details { diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index 653ff65aa2c3..5af58aac91ad 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -2587,7 +2587,7 @@ static const struct feature_ops feat_ops[HEADER_LAST_FEATURE] = { FEAT_OPR(NUMA_TOPOLOGY, numa_topology, true), FEAT_OPN(BRANCH_STACK, branch_stack, false), FEAT_OPR(PMU_MAPPINGS, pmu_mappings, false), - FEAT_OPN(GROUP_DESC, group_desc, false), + FEAT_OPR(GROUP_DESC, group_desc, false), FEAT_OPN(AUXTRACE, auxtrace, false), FEAT_OPN(STAT, stat, false), FEAT_OPN(CACHE, cache, true), diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index 73049f7f0f60..3badd7f1e1b8 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -181,7 +181,7 @@ size_t events_stats__fprintf(struct events_stats *stats, FILE *fp); size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows, int max_cols, float min_pcnt, FILE *fp, - bool use_callchain); + bool ignore_callchains); size_t perf_evlist__fprintf_nr_events(struct perf_evlist *evlist, FILE *fp); void hists__filter_by_dso(struct hists *hists); diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index e7b4a8b513f2..b300a3973448 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -408,23 +408,16 @@ out_err: } /* - * Caller must eventually drop thread->refcnt returned with a successful - * lookup/new thread inserted. + * Front-end cache - TID lookups come in blocks, + * so most of the time we dont have to look up + * the full rbtree: */ -static struct thread *____machine__findnew_thread(struct machine *machine, - struct threads *threads, - pid_t pid, pid_t tid, - bool create) +static struct thread* +__threads__get_last_match(struct threads *threads, struct machine *machine, + int pid, int tid) { - struct rb_node **p = &threads->entries.rb_node; - struct rb_node *parent = NULL; struct thread *th; - /* - * Front-end cache - TID lookups come in blocks, - * so most of the time we dont have to look up - * the full rbtree: - */ th = threads->last_match; if (th != NULL) { if (th->tid == tid) { @@ -435,12 +428,57 @@ static struct thread *____machine__findnew_thread(struct machine *machine, threads->last_match = NULL; } + return NULL; +} + +static struct thread* +threads__get_last_match(struct threads *threads, struct machine *machine, + int pid, int tid) +{ + struct thread *th = NULL; + + if (perf_singlethreaded) + th = __threads__get_last_match(threads, machine, pid, tid); + + return th; +} + +static void +__threads__set_last_match(struct threads *threads, struct thread *th) +{ + threads->last_match = th; +} + +static void +threads__set_last_match(struct threads *threads, struct thread *th) +{ + if (perf_singlethreaded) + __threads__set_last_match(threads, th); +} + +/* + * Caller must eventually drop thread->refcnt returned with a successful + * lookup/new thread inserted. + */ +static struct thread *____machine__findnew_thread(struct machine *machine, + struct threads *threads, + pid_t pid, pid_t tid, + bool create) +{ + struct rb_node **p = &threads->entries.rb_node; + struct rb_node *parent = NULL; + struct thread *th; + + th = threads__get_last_match(threads, machine, pid, tid); + if (th) + return th; + while (*p != NULL) { parent = *p; th = rb_entry(parent, struct thread, rb_node); if (th->tid == tid) { - threads->last_match = th; + threads__set_last_match(threads, th); machine__update_thread_pid(machine, th, pid); return thread__get(th); } @@ -477,7 +515,7 @@ static struct thread *____machine__findnew_thread(struct machine *machine, * It is now in the rbtree, get a ref */ thread__get(th); - threads->last_match = th; + threads__set_last_match(threads, th); ++threads->nr; } @@ -1635,7 +1673,7 @@ static void __machine__remove_thread(struct machine *machine, struct thread *th, struct threads *threads = machine__threads(machine, th->tid); if (threads->last_match == th) - threads->last_match = NULL; + threads__set_last_match(threads, NULL); BUG_ON(refcount_read(&th->refcnt) == 0); if (lock) @@ -2272,6 +2310,7 @@ static int unwind_entry(struct unwind_entry *entry, void *arg) { struct callchain_cursor *cursor = arg; const char *srcline = NULL; + u64 addr; if (symbol_conf.hide_unresolved && entry->sym == NULL) return 0; @@ -2279,7 +2318,13 @@ static int unwind_entry(struct unwind_entry *entry, void *arg) if (append_inlines(cursor, entry->map, entry->sym, entry->ip) == 0) return 0; - srcline = callchain_srcline(entry->map, entry->sym, entry->ip); + /* + * Convert entry->ip from a virtual address to an offset in + * its corresponding binary. + */ + addr = map__map_ip(entry->map, entry->ip); + + srcline = callchain_srcline(entry->map, entry->sym, addr); return callchain_cursor_append(cursor, entry->ip, entry->map, entry->sym, false, NULL, 0, 0, 0, srcline); diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c index 1ddc3d1d0147..a28f9b5cc4ff 100644 --- a/tools/perf/util/metricgroup.c +++ b/tools/perf/util/metricgroup.c @@ -326,8 +326,8 @@ void metricgroup__print(bool metrics, bool metricgroups, char *filter, if (raw) s = (char *)pe->metric_name; else { - if (asprintf(&s, "%s\n\t[%s]", - pe->metric_name, pe->desc) < 0) + if (asprintf(&s, "%s\n%*s%s]", + pe->metric_name, 8, "[", pe->desc) < 0) return; } @@ -490,3 +490,25 @@ out: metricgroup__free_egroups(&group_list); return ret; } + +bool metricgroup__has_metric(const char *metric) +{ + struct pmu_events_map *map = perf_pmu__find_map(NULL); + struct pmu_event *pe; + int i; + + if (!map) + return false; + + for (i = 0; ; i++) { + pe = &map->table[i]; + + if (!pe->name && !pe->metric_group && !pe->metric_name) + break; + if (!pe->metric_expr) + continue; + if (match_metric(pe->metric_name, metric)) + return true; + } + return false; +} diff --git a/tools/perf/util/metricgroup.h b/tools/perf/util/metricgroup.h index 06854e125ee7..8a155dba0581 100644 --- a/tools/perf/util/metricgroup.h +++ b/tools/perf/util/metricgroup.h @@ -28,4 +28,5 @@ int metricgroup__parse_groups(const struct option *opt, struct rblist *metric_events); void metricgroup__print(bool metrics, bool groups, char *filter, bool raw); +bool metricgroup__has_metric(const char *metric); #endif diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index 3ba6a1742f91..afd68524ffa9 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -652,12 +652,6 @@ static int is_arm_pmu_core(const char *name) if (stat(path, &st) == 0) return 1; - /* Look for cpu sysfs (specific to s390) */ - scnprintf(path, PATH_MAX, "%s/bus/event_source/devices/%s", - sysfs, name); - if (stat(path, &st) == 0 && !strncmp(name, "cpum_", 5)) - return 1; - return 0; } diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c index 594d14a02b67..99990f5f2512 100644 --- a/tools/perf/util/stat-shadow.c +++ b/tools/perf/util/stat-shadow.c @@ -913,11 +913,10 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel, ratio = total / avg; print_metric(ctxp, NULL, "%8.0f", "cycles / elision", ratio); - } else if (perf_evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK) || - perf_evsel__match(evsel, SOFTWARE, SW_CPU_CLOCK)) { + } else if (perf_evsel__is_clock(evsel)) { if ((ratio = avg_stats(&walltime_nsecs_stats)) != 0) print_metric(ctxp, NULL, "%8.3f", "CPUs utilized", - avg / ratio); + avg / (ratio * evsel->scale)); else print_metric(ctxp, NULL, NULL, "CPUs utilized", 0); } else if (perf_stat_evsel__is(evsel, TOPDOWN_FETCH_BUBBLES)) { diff --git a/tools/perf/util/syscalltbl.c b/tools/perf/util/syscalltbl.c index 0ee7f568d60c..3393d7ee9401 100644 --- a/tools/perf/util/syscalltbl.c +++ b/tools/perf/util/syscalltbl.c @@ -38,6 +38,10 @@ static const char **syscalltbl_native = syscalltbl_powerpc_64; #include <asm/syscalls_32.c> const int syscalltbl_native_max_id = SYSCALLTBL_POWERPC_32_MAX_ID; static const char **syscalltbl_native = syscalltbl_powerpc_32; +#elif defined(__aarch64__) +#include <asm/syscalls.c> +const int syscalltbl_native_max_id = SYSCALLTBL_ARM64_MAX_ID; +static const char **syscalltbl_native = syscalltbl_arm64; #endif struct syscall { diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c index 538db4e5d1e6..6f318b15950e 100644 --- a/tools/perf/util/unwind-libdw.c +++ b/tools/perf/util/unwind-libdw.c @@ -77,7 +77,7 @@ static int entry(u64 ip, struct unwind_info *ui) if (__report_module(&al, ip, ui)) return -1; - e->ip = al.addr; + e->ip = ip; e->map = al.map; e->sym = al.sym; diff --git a/tools/perf/util/unwind-libunwind-local.c b/tools/perf/util/unwind-libunwind-local.c index 6a11bc7e6b27..79f521a552cf 100644 --- a/tools/perf/util/unwind-libunwind-local.c +++ b/tools/perf/util/unwind-libunwind-local.c @@ -575,7 +575,7 @@ static int entry(u64 ip, struct thread *thread, struct addr_location al; e.sym = thread__find_symbol(thread, PERF_RECORD_MISC_USER, ip, &al); - e.ip = al.addr; + e.ip = ip; e.map = al.map; pr_debug("unwind: %s:ip = 0x%" PRIx64 " (0x%" PRIx64 ")\n", diff --git a/tools/testing/selftests/bpf/test_sockmap.c b/tools/testing/selftests/bpf/test_sockmap.c index 9e78df207919..0c7d9e556b47 100644 --- a/tools/testing/selftests/bpf/test_sockmap.c +++ b/tools/testing/selftests/bpf/test_sockmap.c @@ -354,7 +354,7 @@ static int msg_loop(int fd, int iov_count, int iov_length, int cnt, while (s->bytes_recvd < total_bytes) { if (txmsg_cork) { timeout.tv_sec = 0; - timeout.tv_usec = 1000; + timeout.tv_usec = 300000; } else { timeout.tv_sec = 1; timeout.tv_usec = 0; diff --git a/tools/testing/selftests/rcutorture/bin/configinit.sh b/tools/testing/selftests/rcutorture/bin/configinit.sh index c15f270e121d..65541c21a544 100755 --- a/tools/testing/selftests/rcutorture/bin/configinit.sh +++ b/tools/testing/selftests/rcutorture/bin/configinit.sh @@ -1,6 +1,6 @@ #!/bin/bash # -# Usage: configinit.sh config-spec-file [ build output dir ] +# Usage: configinit.sh config-spec-file build-output-dir results-dir # # Create a .config file from the spec file. Run from the kernel source tree. # Exits with 0 if all went well, with 1 if all went well but the config @@ -40,20 +40,18 @@ mkdir $T c=$1 buildloc=$2 +resdir=$3 builddir= -if test -n $buildloc +if echo $buildloc | grep -q '^O=' then - if echo $buildloc | grep -q '^O=' + builddir=`echo $buildloc | sed -e 's/^O=//'` + if test ! -d $builddir then - builddir=`echo $buildloc | sed -e 's/^O=//'` - if test ! -d $builddir - then - mkdir $builddir - fi - else - echo Bad build directory: \"$buildloc\" - exit 2 + mkdir $builddir fi +else + echo Bad build directory: \"$buildloc\" + exit 2 fi sed -e 's/^\(CONFIG[0-9A-Z_]*\)=.*$/grep -v "^# \1" |/' < $c > $T/u.sh @@ -61,12 +59,12 @@ sed -e 's/^\(CONFIG[0-9A-Z_]*=\).*$/grep -v \1 |/' < $c >> $T/u.sh grep '^grep' < $T/u.sh > $T/upd.sh echo "cat - $c" >> $T/upd.sh make mrproper -make $buildloc distclean > $builddir/Make.distclean 2>&1 -make $buildloc $TORTURE_DEFCONFIG > $builddir/Make.defconfig.out 2>&1 +make $buildloc distclean > $resdir/Make.distclean 2>&1 +make $buildloc $TORTURE_DEFCONFIG > $resdir/Make.defconfig.out 2>&1 mv $builddir/.config $builddir/.config.sav sh $T/upd.sh < $builddir/.config.sav > $builddir/.config cp $builddir/.config $builddir/.config.new -yes '' | make $buildloc oldconfig > $builddir/Make.oldconfig.out 2> $builddir/Make.oldconfig.err +yes '' | make $buildloc oldconfig > $resdir/Make.oldconfig.out 2> $resdir/Make.oldconfig.err # verify new config matches specification. configcheck.sh $builddir/.config $c diff --git a/tools/testing/selftests/rcutorture/bin/kvm-build.sh b/tools/testing/selftests/rcutorture/bin/kvm-build.sh index 34d126734cde..9115fcdb5617 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-build.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-build.sh @@ -2,7 +2,7 @@ # # Build a kvm-ready Linux kernel from the tree in the current directory. # -# Usage: kvm-build.sh config-template build-dir +# Usage: kvm-build.sh config-template build-dir resdir # # This program is free software; you can redistribute it and/or modify # it under the terms of the GNU General Public License as published by @@ -29,6 +29,7 @@ then exit 1 fi builddir=${2} +resdir=${3} T=${TMPDIR-/tmp}/test-linux.sh.$$ trap 'rm -rf $T' 0 @@ -41,19 +42,19 @@ CONFIG_VIRTIO_PCI=y CONFIG_VIRTIO_CONSOLE=y ___EOF___ -configinit.sh $T/config O=$builddir +configinit.sh $T/config O=$builddir $resdir retval=$? if test $retval -gt 1 then exit 2 fi ncpus=`cpus2use.sh` -make O=$builddir -j$ncpus $TORTURE_KMAKE_ARG > $builddir/Make.out 2>&1 +make O=$builddir -j$ncpus $TORTURE_KMAKE_ARG > $resdir/Make.out 2>&1 retval=$? -if test $retval -ne 0 || grep "rcu[^/]*": < $builddir/Make.out | egrep -q "Stop|Error|error:|warning:" || egrep -q "Stop|Error|error:" < $builddir/Make.out +if test $retval -ne 0 || grep "rcu[^/]*": < $resdir/Make.out | egrep -q "Stop|Error|error:|warning:" || egrep -q "Stop|Error|error:" < $resdir/Make.out then echo Kernel build error - egrep "Stop|Error|error:|warning:" < $builddir/Make.out + egrep "Stop|Error|error:|warning:" < $resdir/Make.out echo Run aborted. exit 3 fi diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh index 477ecb1293ab..0fa8a61ccb7b 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh @@ -70,4 +70,5 @@ else else print_warning $nclosecalls "Reader Batch close calls in" $(($dur/60)) minute run: $i fi + echo $nclosecalls "Reader Batch close calls in" $(($dur/60)) minute run: $i > $i/console.log.rcu.diags fi diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh index c27e97824163..c9bab57a77eb 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh @@ -39,6 +39,7 @@ do head -1 $resdir/log fi TORTURE_SUITE="`cat $i/../TORTURE_SUITE`" + rm -f $i/console.log.*.diags kvm-recheck-${TORTURE_SUITE}.sh $i if test -f "$i/console.log" then diff --git a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh index c5b0f94341d9..f7247ee00514 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh @@ -98,14 +98,15 @@ then ln -s $base_resdir/.config $resdir # for kvm-recheck.sh # Arch-independent indicator touch $resdir/builtkernel -elif kvm-build.sh $T/Kc2 $builddir +elif kvm-build.sh $T/Kc2 $builddir $resdir then # Had to build a kernel for this test. QEMU="`identify_qemu $builddir/vmlinux`" BOOT_IMAGE="`identify_boot_image $QEMU`" - cp $builddir/Make*.out $resdir cp $builddir/vmlinux $resdir cp $builddir/.config $resdir + cp $builddir/Module.symvers $resdir > /dev/null || : + cp $builddir/System.map $resdir > /dev/null || : if test -n "$BOOT_IMAGE" then cp $builddir/$BOOT_IMAGE $resdir diff --git a/tools/testing/selftests/rcutorture/bin/kvm.sh b/tools/testing/selftests/rcutorture/bin/kvm.sh index 56610dbbdf73..5a7a62d76a50 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm.sh @@ -347,7 +347,7 @@ function dump(first, pastlast, batchnum) print "needqemurun=" jn=1 for (j = first; j < pastlast; j++) { - builddir=KVM "/b" jn + builddir=KVM "/b1" cpusr[jn] = cpus[j]; if (cfrep[cf[j]] == "") { cfr[jn] = cf[j]; diff --git a/tools/testing/selftests/rcutorture/bin/parse-console.sh b/tools/testing/selftests/rcutorture/bin/parse-console.sh index 17293436f551..84933f6aed77 100755 --- a/tools/testing/selftests/rcutorture/bin/parse-console.sh +++ b/tools/testing/selftests/rcutorture/bin/parse-console.sh @@ -163,6 +163,13 @@ then print_warning Summary: $summary cat $T.diags >> $file.diags fi +for i in $file.*.diags +do + if test -f "$i" + then + cat $i >> $file.diags + fi +done if ! test -s $file.diags then rm -f $file.diags diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE03.boot b/tools/testing/selftests/rcutorture/configs/rcu/TREE03.boot index 5d2cc0bd50a0..5c3213cc3ad7 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE03.boot +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE03.boot @@ -1,5 +1,5 @@ -rcutorture.onoff_interval=1 rcutorture.onoff_holdoff=30 -rcutree.gp_preinit_delay=3 +rcutorture.onoff_interval=200 rcutorture.onoff_holdoff=30 +rcutree.gp_preinit_delay=12 rcutree.gp_init_delay=3 rcutree.gp_cleanup_delay=3 rcutree.kthread_prio=2 diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE08-T.boot b/tools/testing/selftests/rcutorture/configs/rcu/TREE08-T.boot deleted file mode 100644 index 883149b5f2d1..000000000000 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE08-T.boot +++ /dev/null @@ -1 +0,0 @@ -rcutree.rcu_fanout_exact=1 diff --git a/tools/testing/selftests/rcutorture/configs/rcu/ver_functions.sh b/tools/testing/selftests/rcutorture/configs/rcu/ver_functions.sh index 24ec91041957..7bab8246392b 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/ver_functions.sh +++ b/tools/testing/selftests/rcutorture/configs/rcu/ver_functions.sh @@ -39,7 +39,7 @@ rcutorture_param_onoff () { if ! bootparam_hotplug_cpu "$1" && configfrag_hotplug_cpu "$2" then echo CPU-hotplug kernel, adding rcutorture onoff. 1>&2 - echo rcutorture.onoff_interval=3 rcutorture.onoff_holdoff=30 + echo rcutorture.onoff_interval=1000 rcutorture.onoff_holdoff=30 fi } diff --git a/tools/testing/selftests/timers/raw_skew.c b/tools/testing/selftests/timers/raw_skew.c index ca6cd146aafe..dcf73c5dab6e 100644 --- a/tools/testing/selftests/timers/raw_skew.c +++ b/tools/testing/selftests/timers/raw_skew.c @@ -134,6 +134,11 @@ int main(int argv, char **argc) printf(" %lld.%i(act)", ppm/1000, abs((int)(ppm%1000))); if (llabs(eppm - ppm) > 1000) { + if (tx1.offset || tx2.offset || + tx1.freq != tx2.freq || tx1.tick != tx2.tick) { + printf(" [SKIP]\n"); + return ksft_exit_skip("The clock was adjusted externally. Shutdown NTPd or other time sync daemons\n"); + } printf(" [FAILED]\n"); return ksft_exit_fail(); } diff --git a/virt/kvm/arm/arm.c b/virt/kvm/arm/arm.c index 04e554cae3a2..108250e4d376 100644 --- a/virt/kvm/arm/arm.c +++ b/virt/kvm/arm/arm.c @@ -604,7 +604,7 @@ void kvm_arm_resume_guest(struct kvm *kvm) kvm_for_each_vcpu(i, vcpu, kvm) { vcpu->arch.pause = false; - swake_up(kvm_arch_vcpu_wq(vcpu)); + swake_up_one(kvm_arch_vcpu_wq(vcpu)); } } @@ -612,7 +612,7 @@ static void vcpu_req_sleep(struct kvm_vcpu *vcpu) { struct swait_queue_head *wq = kvm_arch_vcpu_wq(vcpu); - swait_event_interruptible(*wq, ((!vcpu->arch.power_off) && + swait_event_interruptible_exclusive(*wq, ((!vcpu->arch.power_off) && (!vcpu->arch.pause))); if (vcpu->arch.power_off || vcpu->arch.pause) { diff --git a/virt/kvm/arm/psci.c b/virt/kvm/arm/psci.c index c95ab4c5a475..9b73d3ad918a 100644 --- a/virt/kvm/arm/psci.c +++ b/virt/kvm/arm/psci.c @@ -155,7 +155,7 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu) smp_mb(); /* Make sure the above is visible */ wq = kvm_arch_vcpu_wq(vcpu); - swake_up(wq); + swake_up_one(wq); return PSCI_RET_SUCCESS; } diff --git a/virt/kvm/async_pf.c b/virt/kvm/async_pf.c index 57bcb27dcf30..23c2519c5b32 100644 --- a/virt/kvm/async_pf.c +++ b/virt/kvm/async_pf.c @@ -107,7 +107,7 @@ static void async_pf_execute(struct work_struct *work) trace_kvm_async_pf_completed(addr, gva); if (swq_has_sleeper(&vcpu->wq)) - swake_up(&vcpu->wq); + swake_up_one(&vcpu->wq); mmput(mm); kvm_put_kvm(vcpu->kvm); diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 8b47507faab5..3d233ebfbee9 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -2172,7 +2172,7 @@ void kvm_vcpu_block(struct kvm_vcpu *vcpu) kvm_arch_vcpu_blocking(vcpu); for (;;) { - prepare_to_swait(&vcpu->wq, &wait, TASK_INTERRUPTIBLE); + prepare_to_swait_exclusive(&vcpu->wq, &wait, TASK_INTERRUPTIBLE); if (kvm_vcpu_check_block(vcpu) < 0) break; @@ -2214,7 +2214,7 @@ bool kvm_vcpu_wake_up(struct kvm_vcpu *vcpu) wqp = kvm_arch_vcpu_wq(vcpu); if (swq_has_sleeper(wqp)) { - swake_up(wqp); + swake_up_one(wqp); ++vcpu->stat.halt_wakeup; return true; } |
