From 392ea5dd0ff265f7557405fcbdf35acd34cf4ab8 Mon Sep 17 00:00:00 2001 From: Tero Kristo Date: Fri, 22 Dec 2017 11:26:03 +0200 Subject: ARM: OMAP2+: hwmod_core: enable optional clocks before main clock The optional clocks must be enabled before the main clock after the transition to clkctrl controlled clocks is done. Otherwise the module we attempt to enable might be stuck in transition. Reported-by: Keerthy Tested-by: Keerthy Signed-off-by: Tero Kristo Signed-off-by: Tony Lindgren --- arch/arm/mach-omap2/omap_hwmod.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'arch') diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c index 5eff27e4f24b..b1d446c57556 100644 --- a/arch/arm/mach-omap2/omap_hwmod.c +++ b/arch/arm/mach-omap2/omap_hwmod.c @@ -975,6 +975,9 @@ static int _enable_clocks(struct omap_hwmod *oh) pr_debug("omap_hwmod: %s: enabling clocks\n", oh->name); + if (oh->flags & HWMOD_OPT_CLKS_NEEDED) + _enable_optional_clocks(oh); + if (oh->_clk) clk_enable(oh->_clk); @@ -983,9 +986,6 @@ static int _enable_clocks(struct omap_hwmod *oh) clk_enable(os->_clk); } - if (oh->flags & HWMOD_OPT_CLKS_NEEDED) - _enable_optional_clocks(oh); - /* The opt clocks are controlled by the device driver. */ return 0; -- cgit v1.2.3-55-g7522 From 8bbfbc2df6e9a37bc5c9ee674c496ea277b0bd39 Mon Sep 17 00:00:00 2001 From: Eugeniy Paltsev Date: Wed, 17 Jan 2018 16:39:17 +0300 Subject: ARCv2: cache: fix slc_entire_op: flush only instead of flush-n-inv slc_entire_op with OP_FLUSH command also invalidates it. This is a preventive fix as the current use of slc_entire_op is only with OP_FLUSH_N_INV where the invalidate is required. Signed-off-by: Eugeniy Paltsev [vgupta: fixed changelog] Signed-off-by: Vineet Gupta --- arch/arc/mm/cache.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/arc/mm/cache.c b/arch/arc/mm/cache.c index eee924dfffa6..2072f3451e9c 100644 --- a/arch/arc/mm/cache.c +++ b/arch/arc/mm/cache.c @@ -780,7 +780,10 @@ noinline static void slc_entire_op(const int op) write_aux_reg(r, ctrl); - write_aux_reg(ARC_REG_SLC_INVALIDATE, 1); + if (op & OP_INV) /* Inv or flush-n-inv use same cmd reg */ + write_aux_reg(ARC_REG_SLC_INVALIDATE, 0x1); + else + write_aux_reg(ARC_REG_SLC_FLUSH, 0x1); /* Make sure "busy" bit reports correct stataus, see STAR 9001165532 */ read_aux_reg(r); -- cgit v1.2.3-55-g7522 From a3142792f79884b867b7bf4c7d5a126a0f913332 Mon Sep 17 00:00:00 2001 From: Alexey Brodkin Date: Thu, 18 Jan 2018 21:07:21 +0300 Subject: ARCv2: Don't pretend we may set L-bit in STATUS32 with kflag instruction As per PRM "kflag" instruction doesn't change state of L-flag ("Zero-Overhead loop disabled") in STATUS32 register so let's not act as if we can affect this bit. Signed-off-by: Alexey Brodkin Signed-off-by: Vineet Gupta --- arch/arc/include/asm/entry-arcv2.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/arc/include/asm/entry-arcv2.h b/arch/arc/include/asm/entry-arcv2.h index 257a68f3c2fe..309f4e6721b3 100644 --- a/arch/arc/include/asm/entry-arcv2.h +++ b/arch/arc/include/asm/entry-arcv2.h @@ -184,7 +184,7 @@ .macro FAKE_RET_FROM_EXCPN lr r9, [status32] bic r9, r9, (STATUS_U_MASK|STATUS_DE_MASK|STATUS_AE_MASK) - or r9, r9, (STATUS_L_MASK|STATUS_IE_MASK) + or r9, r9, STATUS_IE_MASK kflag r9 .endm -- cgit v1.2.3-55-g7522 From 8ff3afc159f26e44471e174077e6d16cd2a2bb91 Mon Sep 17 00:00:00 2001 From: Alexey Brodkin Date: Thu, 18 Jan 2018 16:48:47 +0300 Subject: ARC: Enable fatal signals on boot for dev platforms It's very convenient to have fatal signals enabled on developemnt platform as this allows to catch problems that happen early in user-space (like crashing init or dynamic loader). Otherwise we may either enable it later from alive taregt console by "echo 1 > /proc/sys/kernel/print-fatal-signals" but: 1. We might be unfortunate enough to not reach working console 2. Forget to enable fatal signals and miss something interesting Given we're talking about development platforms here it shouldn't be a problem if a bit more data gets printed to debug console. Moreover this makes behavior of all our dev platforms predictable as today some platforms already have it enabled and some don't - which is way too inconvenient. Signed-off-by: Alexey Brodkin Signed-off-by: Vineet Gupta --- arch/arc/boot/dts/axs101.dts | 2 +- arch/arc/boot/dts/haps_hs_idu.dts | 2 +- arch/arc/boot/dts/nsim_700.dts | 2 +- arch/arc/boot/dts/nsim_hs.dts | 2 +- arch/arc/boot/dts/nsim_hs_idu.dts | 2 +- arch/arc/boot/dts/nsimosci.dts | 2 +- arch/arc/boot/dts/nsimosci_hs.dts | 2 +- arch/arc/boot/dts/nsimosci_hs_idu.dts | 2 +- 8 files changed, 8 insertions(+), 8 deletions(-) (limited to 'arch') diff --git a/arch/arc/boot/dts/axs101.dts b/arch/arc/boot/dts/axs101.dts index 70aec7d6ca60..626b694c7be7 100644 --- a/arch/arc/boot/dts/axs101.dts +++ b/arch/arc/boot/dts/axs101.dts @@ -17,6 +17,6 @@ compatible = "snps,axs101", "snps,arc-sdp"; chosen { - bootargs = "earlycon=uart8250,mmio32,0xe0022000,115200n8 console=tty0 console=ttyS3,115200n8 consoleblank=0 video=1280x720@60"; + bootargs = "earlycon=uart8250,mmio32,0xe0022000,115200n8 console=tty0 console=ttyS3,115200n8 consoleblank=0 video=1280x720@60 print-fatal-signals=1"; }; }; diff --git a/arch/arc/boot/dts/haps_hs_idu.dts b/arch/arc/boot/dts/haps_hs_idu.dts index 215cddd0b63b..0c603308aeb3 100644 --- a/arch/arc/boot/dts/haps_hs_idu.dts +++ b/arch/arc/boot/dts/haps_hs_idu.dts @@ -22,7 +22,7 @@ }; chosen { - bootargs = "earlycon=uart8250,mmio32,0xf0000000,115200n8 console=ttyS0,115200n8 debug"; + bootargs = "earlycon=uart8250,mmio32,0xf0000000,115200n8 console=ttyS0,115200n8 debug print-fatal-signals=1"; }; aliases { diff --git a/arch/arc/boot/dts/nsim_700.dts b/arch/arc/boot/dts/nsim_700.dts index 5ee96b067c08..ff2f2c70c545 100644 --- a/arch/arc/boot/dts/nsim_700.dts +++ b/arch/arc/boot/dts/nsim_700.dts @@ -17,7 +17,7 @@ interrupt-parent = <&core_intc>; chosen { - bootargs = "earlycon=arc_uart,mmio32,0xc0fc1000,115200n8 console=ttyARC0,115200n8"; + bootargs = "earlycon=arc_uart,mmio32,0xc0fc1000,115200n8 console=ttyARC0,115200n8 print-fatal-signals=1"; }; aliases { diff --git a/arch/arc/boot/dts/nsim_hs.dts b/arch/arc/boot/dts/nsim_hs.dts index 8d787b251f73..8e2489b16b0a 100644 --- a/arch/arc/boot/dts/nsim_hs.dts +++ b/arch/arc/boot/dts/nsim_hs.dts @@ -24,7 +24,7 @@ }; chosen { - bootargs = "earlycon=arc_uart,mmio32,0xc0fc1000,115200n8 console=ttyARC0,115200n8"; + bootargs = "earlycon=arc_uart,mmio32,0xc0fc1000,115200n8 console=ttyARC0,115200n8 print-fatal-signals=1"; }; aliases { diff --git a/arch/arc/boot/dts/nsim_hs_idu.dts b/arch/arc/boot/dts/nsim_hs_idu.dts index 4f98ebf71fd8..ed12f494721d 100644 --- a/arch/arc/boot/dts/nsim_hs_idu.dts +++ b/arch/arc/boot/dts/nsim_hs_idu.dts @@ -15,7 +15,7 @@ interrupt-parent = <&core_intc>; chosen { - bootargs = "earlycon=arc_uart,mmio32,0xc0fc1000,115200n8 console=ttyARC0,115200n8"; + bootargs = "earlycon=arc_uart,mmio32,0xc0fc1000,115200n8 console=ttyARC0,115200n8 print-fatal-signals=1"; }; aliases { diff --git a/arch/arc/boot/dts/nsimosci.dts b/arch/arc/boot/dts/nsimosci.dts index 3c391ba565ed..7842e5eb4ab5 100644 --- a/arch/arc/boot/dts/nsimosci.dts +++ b/arch/arc/boot/dts/nsimosci.dts @@ -20,7 +20,7 @@ /* this is for console on PGU */ /* bootargs = "console=tty0 consoleblank=0"; */ /* this is for console on serial */ - bootargs = "earlycon=uart8250,mmio32,0xf0000000,115200n8 console=tty0 console=ttyS0,115200n8 consoleblank=0 debug video=640x480-24"; + bootargs = "earlycon=uart8250,mmio32,0xf0000000,115200n8 console=tty0 console=ttyS0,115200n8 consoleblank=0 debug video=640x480-24 print-fatal-signals=1"; }; aliases { diff --git a/arch/arc/boot/dts/nsimosci_hs.dts b/arch/arc/boot/dts/nsimosci_hs.dts index 14a727cbf4c9..b8838cf2b4ec 100644 --- a/arch/arc/boot/dts/nsimosci_hs.dts +++ b/arch/arc/boot/dts/nsimosci_hs.dts @@ -20,7 +20,7 @@ /* this is for console on PGU */ /* bootargs = "console=tty0 consoleblank=0"; */ /* this is for console on serial */ - bootargs = "earlycon=uart8250,mmio32,0xf0000000,115200n8 console=tty0 console=ttyS0,115200n8 consoleblank=0 debug video=640x480-24"; + bootargs = "earlycon=uart8250,mmio32,0xf0000000,115200n8 console=tty0 console=ttyS0,115200n8 consoleblank=0 debug video=640x480-24 print-fatal-signals=1"; }; aliases { diff --git a/arch/arc/boot/dts/nsimosci_hs_idu.dts b/arch/arc/boot/dts/nsimosci_hs_idu.dts index 5052917d4a99..72a2c723f1f7 100644 --- a/arch/arc/boot/dts/nsimosci_hs_idu.dts +++ b/arch/arc/boot/dts/nsimosci_hs_idu.dts @@ -18,7 +18,7 @@ chosen { /* this is for console on serial */ - bootargs = "earlycon=uart8250,mmio32,0xf0000000,115200n8 console=tty0 console=ttyS0,115200n8 consoleblan=0 debug video=640x480-24"; + bootargs = "earlycon=uart8250,mmio32,0xf0000000,115200n8 console=tty0 console=ttyS0,115200n8 consoleblan=0 debug video=640x480-24 print-fatal-signals=1"; }; aliases { -- cgit v1.2.3-55-g7522 From 7d82c5fa057c813d13e1f828f779727214573723 Mon Sep 17 00:00:00 2001 From: Luis de Bethencourt Date: Tue, 23 Jan 2018 15:16:08 +0000 Subject: ARC: dw2 unwind: Fix trailing semicolon The trailing semicolon is an empty statement that does no operation. Removing it since it doesn't do anything. Signed-off-by: Luis de Bethencourt Signed-off-by: Vineet Gupta --- arch/arc/kernel/unwind.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/arc/kernel/unwind.c b/arch/arc/kernel/unwind.c index 333daab7def0..183391d4d33a 100644 --- a/arch/arc/kernel/unwind.c +++ b/arch/arc/kernel/unwind.c @@ -366,7 +366,7 @@ static void init_unwind_hdr(struct unwind_table *table, return; ret_err: - panic("Attention !!! Dwarf FDE parsing errors\n");; + panic("Attention !!! Dwarf FDE parsing errors\n"); } #ifdef CONFIG_MODULES -- cgit v1.2.3-55-g7522 From a46f24acf8bce70b5fdd6774793d121e54b99e97 Mon Sep 17 00:00:00 2001 From: Luis de Bethencourt Date: Tue, 23 Jan 2018 15:16:09 +0000 Subject: ARC: boot log: Fix trailing semicolon The trailing semicolon is an empty statement that does no operation. Removing it since it doesn't do anything. Signed-off-by: Luis de Bethencourt Signed-off-by: Vineet Gupta --- arch/arc/kernel/setup.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c index 9d27331fe69a..ec12fe1c2f07 100644 --- a/arch/arc/kernel/setup.c +++ b/arch/arc/kernel/setup.c @@ -373,7 +373,7 @@ static void arc_chk_core_config(void) { struct cpuinfo_arc *cpu = &cpuinfo_arc700[smp_processor_id()]; int saved = 0, present = 0; - char *opt_nm = NULL;; + char *opt_nm = NULL; if (!cpu->extn.timer0) panic("Timer0 is not present!\n"); -- cgit v1.2.3-55-g7522 From 827cc2fa024dd6517d62de7a44c7b42f32af371b Mon Sep 17 00:00:00 2001 From: Ulf Magnusson Date: Mon, 5 Feb 2018 02:21:31 +0100 Subject: ARC: Fix malformed ARC_EMUL_UNALIGNED default 'default N' should be 'default n', though they happen to have the same effect here, due to undefined symbols (N in this case) evaluating to n in a tristate sense. Remove the default from ARC_EMUL_UNALIGNED instead of changing it. bool and tristate symbols implicitly default to n. Discovered with the https://urldefense.proofpoint.com/v2/url?u=https-3A__github.com_ulfalizer_Kconfiglib_blob_master_examples_list-5Fundefined.py&d=DwIBAg&c=DPL6_X_6JkXFx7AXWqB0tg&r=c14YS-cH-kdhTOW89KozFhBtBJgs1zXscZojEZQ0THs&m=WxxD8ozR7QQUVzNCBksiznaisBGO_crN7PBOvAoju8s&s=1LmxsNqxwT-7wcInVpZ6Z1J27duZKSoyKxHIJclXU_M&e= script. Signed-off-by: Ulf Magnusson Signed-off-by: Vineet Gupta --- arch/arc/Kconfig | 1 - 1 file changed, 1 deletion(-) (limited to 'arch') diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig index 9d5fd00d9e91..6a232f7c5f62 100644 --- a/arch/arc/Kconfig +++ b/arch/arc/Kconfig @@ -487,7 +487,6 @@ config ARC_CURR_IN_REG config ARC_EMUL_UNALIGNED bool "Emulate unaligned memory access (userspace only)" - default N select SYSCTL_ARCH_UNALIGN_NO_WARN select SYSCTL_ARCH_UNALIGN_ALLOW depends on ISA_ARCOMPACT -- cgit v1.2.3-55-g7522 From 8e1eb3fa009aa7c0b944b3c8b26b07de0efb3200 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Mon, 5 Feb 2018 17:18:05 -0800 Subject: x86/entry/64: Clear extra registers beyond syscall arguments, to reduce speculation attack surface At entry userspace may have (maliciously) populated the extra registers outside the syscall calling convention with arbitrary values that could be useful in a speculative execution (Spectre style) attack. Clear these registers to minimize the kernel's attack surface. Note, this only clears the extra registers and not the unused registers for syscalls less than 6 arguments, since those registers are likely to be clobbered well before their values could be put to use under speculation. Note, Linus found that the XOR instructions can be executed with minimized cost if interleaved with the PUSH instructions, and Ingo's analysis found that R10 and R11 should be included in the register clearing beyond the typical 'extra' syscall calling convention registers. Suggested-by: Linus Torvalds Reported-by: Andi Kleen Signed-off-by: Dan Williams Cc: Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Josh Poimboeuf Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/151787988577.7847.16733592218894189003.stgit@dwillia2-desk3.amr.corp.intel.com [ Made small improvements to the changelog and the code comments. ] Signed-off-by: Ingo Molnar --- arch/x86/entry/entry_64.S | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'arch') diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index c752abe89d80..065a71b90808 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -235,13 +235,26 @@ GLOBAL(entry_SYSCALL_64_after_hwframe) pushq %r8 /* pt_regs->r8 */ pushq %r9 /* pt_regs->r9 */ pushq %r10 /* pt_regs->r10 */ + /* + * Clear extra registers that a speculation attack might + * otherwise want to exploit. Interleave XOR with PUSH + * for better uop scheduling: + */ + xorq %r10, %r10 /* nospec r10 */ pushq %r11 /* pt_regs->r11 */ + xorq %r11, %r11 /* nospec r11 */ pushq %rbx /* pt_regs->rbx */ + xorl %ebx, %ebx /* nospec rbx */ pushq %rbp /* pt_regs->rbp */ + xorl %ebp, %ebp /* nospec rbp */ pushq %r12 /* pt_regs->r12 */ + xorq %r12, %r12 /* nospec r12 */ pushq %r13 /* pt_regs->r13 */ + xorq %r13, %r13 /* nospec r13 */ pushq %r14 /* pt_regs->r14 */ + xorq %r14, %r14 /* nospec r14 */ pushq %r15 /* pt_regs->r15 */ + xorq %r15, %r15 /* nospec r15 */ UNWIND_HINT_REGS TRACE_IRQS_OFF -- cgit v1.2.3-55-g7522 From 5355ccbe02da413df22eb05f89ca2da9959f9147 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 15 Jan 2018 17:21:48 +0100 Subject: x86/cpufeature: Reindent _static_cpu_has() Because its daft.. Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Borislav Petkov Cc: Josh Poimboeuf Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Signed-off-by: Ingo Molnar --- arch/x86/include/asm/cpufeature.h | 78 +++++++++++++++++++-------------------- 1 file changed, 39 insertions(+), 39 deletions(-) (limited to 'arch') diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index 70eddb3922ff..910a30699ffb 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -148,45 +148,45 @@ extern void clear_cpu_cap(struct cpuinfo_x86 *c, unsigned int bit); */ static __always_inline __pure bool _static_cpu_has(u16 bit) { - asm_volatile_goto("1: jmp 6f\n" - "2:\n" - ".skip -(((5f-4f) - (2b-1b)) > 0) * " - "((5f-4f) - (2b-1b)),0x90\n" - "3:\n" - ".section .altinstructions,\"a\"\n" - " .long 1b - .\n" /* src offset */ - " .long 4f - .\n" /* repl offset */ - " .word %P1\n" /* always replace */ - " .byte 3b - 1b\n" /* src len */ - " .byte 5f - 4f\n" /* repl len */ - " .byte 3b - 2b\n" /* pad len */ - ".previous\n" - ".section .altinstr_replacement,\"ax\"\n" - "4: jmp %l[t_no]\n" - "5:\n" - ".previous\n" - ".section .altinstructions,\"a\"\n" - " .long 1b - .\n" /* src offset */ - " .long 0\n" /* no replacement */ - " .word %P0\n" /* feature bit */ - " .byte 3b - 1b\n" /* src len */ - " .byte 0\n" /* repl len */ - " .byte 0\n" /* pad len */ - ".previous\n" - ".section .altinstr_aux,\"ax\"\n" - "6:\n" - " testb %[bitnum],%[cap_byte]\n" - " jnz %l[t_yes]\n" - " jmp %l[t_no]\n" - ".previous\n" - : : "i" (bit), "i" (X86_FEATURE_ALWAYS), - [bitnum] "i" (1 << (bit & 7)), - [cap_byte] "m" (((const char *)boot_cpu_data.x86_capability)[bit >> 3]) - : : t_yes, t_no); - t_yes: - return true; - t_no: - return false; + asm_volatile_goto("1: jmp 6f\n" + "2:\n" + ".skip -(((5f-4f) - (2b-1b)) > 0) * " + "((5f-4f) - (2b-1b)),0x90\n" + "3:\n" + ".section .altinstructions,\"a\"\n" + " .long 1b - .\n" /* src offset */ + " .long 4f - .\n" /* repl offset */ + " .word %P1\n" /* always replace */ + " .byte 3b - 1b\n" /* src len */ + " .byte 5f - 4f\n" /* repl len */ + " .byte 3b - 2b\n" /* pad len */ + ".previous\n" + ".section .altinstr_replacement,\"ax\"\n" + "4: jmp %l[t_no]\n" + "5:\n" + ".previous\n" + ".section .altinstructions,\"a\"\n" + " .long 1b - .\n" /* src offset */ + " .long 0\n" /* no replacement */ + " .word %P0\n" /* feature bit */ + " .byte 3b - 1b\n" /* src len */ + " .byte 0\n" /* repl len */ + " .byte 0\n" /* pad len */ + ".previous\n" + ".section .altinstr_aux,\"ax\"\n" + "6:\n" + " testb %[bitnum],%[cap_byte]\n" + " jnz %l[t_yes]\n" + " jmp %l[t_no]\n" + ".previous\n" + : : "i" (bit), "i" (X86_FEATURE_ALWAYS), + [bitnum] "i" (1 << (bit & 7)), + [cap_byte] "m" (((const char *)boot_cpu_data.x86_capability)[bit >> 3]) + : : t_yes, t_no); +t_yes: + return true; +t_no: + return false; } #define static_cpu_has(bit) \ -- cgit v1.2.3-55-g7522 From 3197b04bb39b596613ff2f8143c5cd0a6908debf Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 16 Jan 2018 09:34:01 +0100 Subject: x86/cpufeature: Update _static_cpu_has() to use all named variables Because more readable.. Requested-by: Josh Poimboeuf Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Signed-off-by: Ingo Molnar --- arch/x86/include/asm/cpufeature.h | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'arch') diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index 910a30699ffb..736771c9822e 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -156,7 +156,7 @@ static __always_inline __pure bool _static_cpu_has(u16 bit) ".section .altinstructions,\"a\"\n" " .long 1b - .\n" /* src offset */ " .long 4f - .\n" /* repl offset */ - " .word %P1\n" /* always replace */ + " .word %P[always]\n" /* always replace */ " .byte 3b - 1b\n" /* src len */ " .byte 5f - 4f\n" /* repl len */ " .byte 3b - 2b\n" /* pad len */ @@ -168,7 +168,7 @@ static __always_inline __pure bool _static_cpu_has(u16 bit) ".section .altinstructions,\"a\"\n" " .long 1b - .\n" /* src offset */ " .long 0\n" /* no replacement */ - " .word %P0\n" /* feature bit */ + " .word %P[feature]\n" /* feature bit */ " .byte 3b - 1b\n" /* src len */ " .byte 0\n" /* repl len */ " .byte 0\n" /* pad len */ @@ -179,8 +179,9 @@ static __always_inline __pure bool _static_cpu_has(u16 bit) " jnz %l[t_yes]\n" " jmp %l[t_no]\n" ".previous\n" - : : "i" (bit), "i" (X86_FEATURE_ALWAYS), - [bitnum] "i" (1 << (bit & 7)), + : : [feature] "i" (bit), + [always] "i" (X86_FEATURE_ALWAYS), + [bitnum] "i" (1 << (bit & 7)), [cap_byte] "m" (((const char *)boot_cpu_data.x86_capability)[bit >> 3]) : : t_yes, t_no); t_yes: -- cgit v1.2.3-55-g7522 From 3ac6d8c787b835b997eb23e43e09aa0895ef7d58 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Mon, 5 Feb 2018 17:18:11 -0800 Subject: x86/entry/64: Clear registers for exceptions/interrupts, to reduce speculation attack surface Clear the 'extra' registers on entering the 64-bit kernel for exceptions and interrupts. The common registers are not cleared since they are likely clobbered well before they can be exploited in a speculative execution attack. Originally-From: Andi Kleen Signed-off-by: Dan Williams Cc: Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Josh Poimboeuf Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/151787989146.7847.15749181712358213254.stgit@dwillia2-desk3.amr.corp.intel.com [ Made small improvements to the changelog and the code comments. ] Signed-off-by: Ingo Molnar --- arch/x86/entry/calling.h | 19 +++++++++++++++++++ arch/x86/entry/entry_64.S | 6 +++++- 2 files changed, 24 insertions(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h index 3f48f695d5e6..f4b129d4af42 100644 --- a/arch/x86/entry/calling.h +++ b/arch/x86/entry/calling.h @@ -147,6 +147,25 @@ For 32-bit we have the following conventions - kernel is built with UNWIND_HINT_REGS offset=\offset .endm + /* + * Sanitize registers of values that a speculation attack + * might otherwise want to exploit. The lower registers are + * likely clobbered well before they could be put to use in + * a speculative execution gadget: + */ + .macro CLEAR_REGS_NOSPEC + xorl %ebp, %ebp + xorl %ebx, %ebx + xorq %r8, %r8 + xorq %r9, %r9 + xorq %r10, %r10 + xorq %r11, %r11 + xorq %r12, %r12 + xorq %r13, %r13 + xorq %r14, %r14 + xorq %r15, %r15 + .endm + .macro POP_EXTRA_REGS popq %r15 popq %r14 diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 065a71b90808..9e48002b953b 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -575,6 +575,7 @@ END(irq_entries_start) ALLOC_PT_GPREGS_ON_STACK SAVE_C_REGS SAVE_EXTRA_REGS + CLEAR_REGS_NOSPEC ENCODE_FRAME_POINTER testb $3, CS(%rsp) @@ -1133,6 +1134,7 @@ ENTRY(xen_failsafe_callback) ALLOC_PT_GPREGS_ON_STACK SAVE_C_REGS SAVE_EXTRA_REGS + CLEAR_REGS_NOSPEC ENCODE_FRAME_POINTER jmp error_exit END(xen_failsafe_callback) @@ -1178,6 +1180,7 @@ ENTRY(paranoid_entry) cld SAVE_C_REGS 8 SAVE_EXTRA_REGS 8 + CLEAR_REGS_NOSPEC ENCODE_FRAME_POINTER 8 movl $1, %ebx movl $MSR_GS_BASE, %ecx @@ -1230,8 +1233,8 @@ ENTRY(error_entry) cld SAVE_C_REGS 8 SAVE_EXTRA_REGS 8 + CLEAR_REGS_NOSPEC ENCODE_FRAME_POINTER 8 - xorl %ebx, %ebx testb $3, CS+8(%rsp) jz .Lerror_kernelspace @@ -1428,6 +1431,7 @@ ENTRY(nmi) pushq %r14 /* pt_regs->r14 */ pushq %r15 /* pt_regs->r15 */ UNWIND_HINT_REGS + CLEAR_REGS_NOSPEC ENCODE_FRAME_POINTER /* -- cgit v1.2.3-55-g7522 From 6b8cf5cc9965673951f1ab3f0e3cf23d06e3e2ee Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Mon, 5 Feb 2018 17:18:17 -0800 Subject: x86/entry/64/compat: Clear registers for compat syscalls, to reduce speculation attack surface At entry userspace may have populated registers with values that could otherwise be useful in a speculative execution attack. Clear them to minimize the kernel's attack surface. Originally-From: Andi Kleen Signed-off-by: Dan Williams Cc: Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Josh Poimboeuf Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/151787989697.7847.4083702787288600552.stgit@dwillia2-desk3.amr.corp.intel.com [ Made small improvements to the changelog. ] Signed-off-by: Ingo Molnar --- arch/x86/entry/entry_64_compat.S | 30 ++++++++++++++++++++++++++++++ 1 file changed, 30 insertions(+) (limited to 'arch') diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S index 98d5358e4041..fd65e016e413 100644 --- a/arch/x86/entry/entry_64_compat.S +++ b/arch/x86/entry/entry_64_compat.S @@ -85,15 +85,25 @@ ENTRY(entry_SYSENTER_compat) pushq %rcx /* pt_regs->cx */ pushq $-ENOSYS /* pt_regs->ax */ pushq $0 /* pt_regs->r8 = 0 */ + xorq %r8, %r8 /* nospec r8 */ pushq $0 /* pt_regs->r9 = 0 */ + xorq %r9, %r9 /* nospec r9 */ pushq $0 /* pt_regs->r10 = 0 */ + xorq %r10, %r10 /* nospec r10 */ pushq $0 /* pt_regs->r11 = 0 */ + xorq %r11, %r11 /* nospec r11 */ pushq %rbx /* pt_regs->rbx */ + xorl %ebx, %ebx /* nospec rbx */ pushq %rbp /* pt_regs->rbp (will be overwritten) */ + xorl %ebp, %ebp /* nospec rbp */ pushq $0 /* pt_regs->r12 = 0 */ + xorq %r12, %r12 /* nospec r12 */ pushq $0 /* pt_regs->r13 = 0 */ + xorq %r13, %r13 /* nospec r13 */ pushq $0 /* pt_regs->r14 = 0 */ + xorq %r14, %r14 /* nospec r14 */ pushq $0 /* pt_regs->r15 = 0 */ + xorq %r15, %r15 /* nospec r15 */ cld /* @@ -214,15 +224,25 @@ GLOBAL(entry_SYSCALL_compat_after_hwframe) pushq %rbp /* pt_regs->cx (stashed in bp) */ pushq $-ENOSYS /* pt_regs->ax */ pushq $0 /* pt_regs->r8 = 0 */ + xorq %r8, %r8 /* nospec r8 */ pushq $0 /* pt_regs->r9 = 0 */ + xorq %r9, %r9 /* nospec r9 */ pushq $0 /* pt_regs->r10 = 0 */ + xorq %r10, %r10 /* nospec r10 */ pushq $0 /* pt_regs->r11 = 0 */ + xorq %r11, %r11 /* nospec r11 */ pushq %rbx /* pt_regs->rbx */ + xorl %ebx, %ebx /* nospec rbx */ pushq %rbp /* pt_regs->rbp (will be overwritten) */ + xorl %ebp, %ebp /* nospec rbp */ pushq $0 /* pt_regs->r12 = 0 */ + xorq %r12, %r12 /* nospec r12 */ pushq $0 /* pt_regs->r13 = 0 */ + xorq %r13, %r13 /* nospec r13 */ pushq $0 /* pt_regs->r14 = 0 */ + xorq %r14, %r14 /* nospec r14 */ pushq $0 /* pt_regs->r15 = 0 */ + xorq %r15, %r15 /* nospec r15 */ /* * User mode is traced as though IRQs are on, and SYSENTER @@ -338,15 +358,25 @@ ENTRY(entry_INT80_compat) pushq %rcx /* pt_regs->cx */ pushq $-ENOSYS /* pt_regs->ax */ pushq $0 /* pt_regs->r8 = 0 */ + xorq %r8, %r8 /* nospec r8 */ pushq $0 /* pt_regs->r9 = 0 */ + xorq %r9, %r9 /* nospec r9 */ pushq $0 /* pt_regs->r10 = 0 */ + xorq %r10, %r10 /* nospec r10 */ pushq $0 /* pt_regs->r11 = 0 */ + xorq %r11, %r11 /* nospec r11 */ pushq %rbx /* pt_regs->rbx */ + xorl %ebx, %ebx /* nospec rbx */ pushq %rbp /* pt_regs->rbp */ + xorl %ebp, %ebp /* nospec rbp */ pushq %r12 /* pt_regs->r12 */ + xorq %r12, %r12 /* nospec r12 */ pushq %r13 /* pt_regs->r13 */ + xorq %r13, %r13 /* nospec r13 */ pushq %r14 /* pt_regs->r14 */ + xorq %r14, %r14 /* nospec r14 */ pushq %r15 /* pt_regs->r15 */ + xorq %r15, %r15 /* nospec r15 */ cld /* -- cgit v1.2.3-55-g7522 From 05382333595612204d6c91820bd77be20119cb9b Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Tue, 6 Feb 2018 12:08:10 +0100 Subject: arc: dts: use 'atmel' as manufacturer for at24 in axs10x_mb Using compatible strings without the part for at24 is deprecated since commit 6da28acf745f ("dt-bindings: at24: consistently document the compatible property"). Use a correct 'atmel,' value. Signed-off-by: Bartosz Golaszewski Acked-by: Alexey Brodkin Signed-off-by: Vineet Gupta --- arch/arc/boot/dts/axs10x_mb.dtsi | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch') diff --git a/arch/arc/boot/dts/axs10x_mb.dtsi b/arch/arc/boot/dts/axs10x_mb.dtsi index 74d070cd3c13..47b74fbc403c 100644 --- a/arch/arc/boot/dts/axs10x_mb.dtsi +++ b/arch/arc/boot/dts/axs10x_mb.dtsi @@ -214,13 +214,13 @@ }; eeprom@0x54{ - compatible = "24c01"; + compatible = "atmel,24c01"; reg = <0x54>; pagesize = <0x8>; }; eeprom@0x57{ - compatible = "24c04"; + compatible = "atmel,24c04"; reg = <0x57>; pagesize = <0x8>; }; -- cgit v1.2.3-55-g7522 From eff84b379089cd8b4e83599639c1f5f6e34ef7bf Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Wed, 24 Jan 2018 00:31:27 -0800 Subject: crypto: sha512-mb - initialize pending lengths correctly The SHA-512 multibuffer code keeps track of the number of blocks pending in each lane. The minimum of these values is used to identify the next lane that will be completed. Unused lanes are set to a large number (0xFFFFFFFF) so that they don't affect this calculation. However, it was forgotten to set the lengths to this value in the initial state, where all lanes are unused. As a result it was possible for sha512_mb_mgr_get_comp_job_avx2() to select an unused lane, causing a NULL pointer dereference. Specifically this could happen in the case where ->update() was passed fewer than SHA512_BLOCK_SIZE bytes of data, so it then called sha_complete_job() without having actually submitted any blocks to the multi-buffer code. This hit a NULL pointer dereference if another task happened to have submitted blocks concurrently to the same CPU and the flush timer had not yet expired. Fix this by initializing sha512_mb_mgr->lens correctly. As usual, this bug was found by syzkaller. Fixes: 45691e2d9b18 ("crypto: sha512-mb - submit/flush routines for AVX2") Reported-by: syzbot Cc: # v4.8+ Signed-off-by: Eric Biggers Signed-off-by: Herbert Xu --- arch/x86/crypto/sha512-mb/sha512_mb_mgr_init_avx2.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'arch') diff --git a/arch/x86/crypto/sha512-mb/sha512_mb_mgr_init_avx2.c b/arch/x86/crypto/sha512-mb/sha512_mb_mgr_init_avx2.c index 36870b26067a..d08805032f01 100644 --- a/arch/x86/crypto/sha512-mb/sha512_mb_mgr_init_avx2.c +++ b/arch/x86/crypto/sha512-mb/sha512_mb_mgr_init_avx2.c @@ -57,10 +57,12 @@ void sha512_mb_mgr_init_avx2(struct sha512_mb_mgr *state) { unsigned int j; - state->lens[0] = 0; - state->lens[1] = 1; - state->lens[2] = 2; - state->lens[3] = 3; + /* initially all lanes are unused */ + state->lens[0] = 0xFFFFFFFF00000000; + state->lens[1] = 0xFFFFFFFF00000001; + state->lens[2] = 0xFFFFFFFF00000002; + state->lens[3] = 0xFFFFFFFF00000003; + state->unused_lanes = 0xFF03020100; for (j = 0; j < 4; j++) state->ldata[j].job_in_lane = NULL; -- cgit v1.2.3-55-g7522 From 1d9a090783bef19fe8cdec878620d22f05191316 Mon Sep 17 00:00:00 2001 From: Nathan Fontenot Date: Fri, 26 Jan 2018 13:41:59 -0600 Subject: powerpc/numa: Invalidate numa_cpu_lookup_table on cpu remove When DLPAR removing a CPU, the unmapping of the cpu from a node in unmap_cpu_from_node() should also invalidate the CPUs entry in the numa_cpu_lookup_table. There is not a guarantee that on a subsequent DLPAR add of the CPU the associativity will be the same and thus could be in a different node. Invalidating the entry in the numa_cpu_lookup_table causes the associativity to be read from the device tree at the time of the add. The current behavior of not invalidating the CPUs entry in the numa_cpu_lookup_table can result in scenarios where the the topology layout of CPUs in the partition does not match the device tree or the topology reported by the HMC. This bug looks like it was introduced in 2004 in the commit titled "ppc64: cpu hotplug notifier for numa", which is 6b15e4e87e32 in the linux-fullhist tree. Hence tag it for all stable releases. Cc: stable@vger.kernel.org Signed-off-by: Nathan Fontenot Reviewed-by: Tyrel Datwyler Signed-off-by: Michael Ellerman --- arch/powerpc/include/asm/topology.h | 5 +++++ arch/powerpc/mm/numa.c | 5 ----- arch/powerpc/platforms/pseries/hotplug-cpu.c | 2 ++ 3 files changed, 7 insertions(+), 5 deletions(-) (limited to 'arch') diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h index 88187c285c70..1c02e6900f78 100644 --- a/arch/powerpc/include/asm/topology.h +++ b/arch/powerpc/include/asm/topology.h @@ -44,6 +44,11 @@ extern int sysfs_add_device_to_node(struct device *dev, int nid); extern void sysfs_remove_device_from_node(struct device *dev, int nid); extern int numa_update_cpu_topology(bool cpus_locked); +static inline void update_numa_cpu_lookup_table(unsigned int cpu, int node) +{ + numa_cpu_lookup_table[cpu] = node; +} + static inline int early_cpu_to_node(int cpu) { int nid; diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index 314d19ab9385..edd8d0bc9364 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -143,11 +143,6 @@ static void reset_numa_cpu_lookup_table(void) numa_cpu_lookup_table[cpu] = -1; } -static void update_numa_cpu_lookup_table(unsigned int cpu, int node) -{ - numa_cpu_lookup_table[cpu] = node; -} - static void map_cpu_to_node(int cpu, int node) { update_numa_cpu_lookup_table(cpu, node); diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c index dceb51454d8d..f78fd2068d56 100644 --- a/arch/powerpc/platforms/pseries/hotplug-cpu.c +++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c @@ -36,6 +36,7 @@ #include #include #include +#include #include "pseries.h" #include "offline_states.h" @@ -331,6 +332,7 @@ static void pseries_remove_processor(struct device_node *np) BUG_ON(cpu_online(cpu)); set_cpu_present(cpu, false); set_hard_smp_processor_id(cpu, -1); + update_numa_cpu_lookup_table(cpu, -1); break; } if (cpu >= nr_cpu_ids) -- cgit v1.2.3-55-g7522 From 5c11d1e52d996749897a8616860b18a084c894f0 Mon Sep 17 00:00:00 2001 From: Madhavan Srinivasan Date: Tue, 6 Feb 2018 18:06:37 +0530 Subject: powerpc/64s: Fix MASKABLE_RELON_EXCEPTION_HV_OOL macro Commit f14e953b191f ("powerpc/64s: Add support to take additional parameter in MASKABLE_* macro") messed up MASKABLE_RELON_EXCEPTION_HV_OOL macro by adding the wrong SOFTEN test which caused guest kernel crash at boot. Patch to fix the macro to use SOFTEN_TEST_HV instead of SOFTEN_NOTEST_HV. Fixes: f14e953b191f ("powerpc/64s: Add support to take additional parameter in MASKABLE_* macro") Reported-by: Alexey Kardashevskiy Fix-Suggested-by: Michael Ellerman Signed-off-by: Madhavan Srinivasan Tested-by: Alexey Kardashevskiy Signed-off-by: Michael Ellerman --- arch/powerpc/include/asm/exception-64s.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h index 176dfb73d42c..471b2274fbeb 100644 --- a/arch/powerpc/include/asm/exception-64s.h +++ b/arch/powerpc/include/asm/exception-64s.h @@ -645,7 +645,7 @@ END_FTR_SECTION_NESTED(ftr,ftr,943) EXC_HV, SOFTEN_TEST_HV, bitmask) #define MASKABLE_RELON_EXCEPTION_HV_OOL(vec, label, bitmask) \ - MASKABLE_EXCEPTION_PROLOG_1(PACA_EXGEN, SOFTEN_NOTEST_HV, vec, bitmask);\ + MASKABLE_EXCEPTION_PROLOG_1(PACA_EXGEN, SOFTEN_TEST_HV, vec, bitmask);\ EXCEPTION_RELON_PROLOG_PSERIES_1(label, EXC_HV) /* -- cgit v1.2.3-55-g7522 From 6cc3f91bf69fc8c1719704607474f9b9df56f348 Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Sat, 3 Feb 2018 17:17:50 +1000 Subject: powerpc/64s: Fix may_hard_irq_enable() for PMI soft masking The soft IRQ masking code has to hard-disable interrupts in cases where the exception is not cleared by the masked handler. External interrupts used this approach for soft masking. Now recently PMU interrupts do the same thing. The soft IRQ masking code additionally allowed for interrupt handlers to hard-enable interrupts after soft-disabling them. The idea is to allow PMU interrupts through to profile interrupt handlers. So when interrupts are being replayed when there is a pending interrupt that requires hard-disabling, there is a test to prevent those handlers from hard-enabling them if there is a pending external interrupt. may_hard_irq_enable() handles this. After f442d00480 ("powerpc/64s: Add support to mask perf interrupts and replay them"), may_hard_irq_enable() could prematurely enable MSR[EE] when a PMU exception exists, which would result in the interrupt firing again while masked, and MSR[EE] being disabled again. I haven't seen that this could cause a serious problem, but it's more consistent to handle these soft-masked interrupts in the same way. So introduce a define for all types of interrupts that require MSR[EE] masking in their soft-disable handlers, and use that in may_hard_irq_enable(). Fixes: f442d004806e ("powerpc/64s: Add support to mask perf interrupts and replay them") Signed-off-by: Nicholas Piggin Reviewed-by: Madhavan Srinivasan Signed-off-by: Michael Ellerman --- arch/powerpc/include/asm/hw_irq.h | 12 +++++++++++- arch/powerpc/kernel/exceptions-64e.S | 2 ++ arch/powerpc/kernel/exceptions-64s.S | 6 +++--- 3 files changed, 16 insertions(+), 4 deletions(-) (limited to 'arch') diff --git a/arch/powerpc/include/asm/hw_irq.h b/arch/powerpc/include/asm/hw_irq.h index 88e5e8f17e98..855e17d158b1 100644 --- a/arch/powerpc/include/asm/hw_irq.h +++ b/arch/powerpc/include/asm/hw_irq.h @@ -29,6 +29,16 @@ #define PACA_IRQ_HMI 0x20 #define PACA_IRQ_PMI 0x40 +/* + * Some soft-masked interrupts must be hard masked until they are replayed + * (e.g., because the soft-masked handler does not clear the exception). + */ +#ifdef CONFIG_PPC_BOOK3S +#define PACA_IRQ_MUST_HARD_MASK (PACA_IRQ_EE|PACA_IRQ_PMI) +#else +#define PACA_IRQ_MUST_HARD_MASK (PACA_IRQ_EE) +#endif + /* * flags for paca->irq_soft_mask */ @@ -244,7 +254,7 @@ static inline bool lazy_irq_pending(void) static inline void may_hard_irq_enable(void) { get_paca()->irq_happened &= ~PACA_IRQ_HARD_DIS; - if (!(get_paca()->irq_happened & PACA_IRQ_EE)) + if (!(get_paca()->irq_happened & PACA_IRQ_MUST_HARD_MASK)) __hard_irq_enable(); } diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S index ee832d344a5a..9b6e653e501a 100644 --- a/arch/powerpc/kernel/exceptions-64e.S +++ b/arch/powerpc/kernel/exceptions-64e.S @@ -943,6 +943,8 @@ kernel_dbg_exc: /* * An interrupt came in while soft-disabled; We mark paca->irq_happened * accordingly and if the interrupt is level sensitive, we hard disable + * hard disable (full_mask) corresponds to PACA_IRQ_MUST_HARD_MASK, so + * keep these in synch. */ .macro masked_interrupt_book3e paca_irq full_mask diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index 243d072a225a..3ac87e53b3da 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -1426,7 +1426,7 @@ EXC_COMMON_BEGIN(soft_nmi_common) * triggered and won't automatically refire. * - If it was a HMI we return immediately since we handled it in realmode * and it won't refire. - * - else we hard disable and return. + * - Else it is one of PACA_IRQ_MUST_HARD_MASK, so hard disable and return. * This is called with r10 containing the value to OR to the paca field. */ #define MASKED_INTERRUPT(_H) \ @@ -1441,8 +1441,8 @@ masked_##_H##interrupt: \ ori r10,r10,0xffff; \ mtspr SPRN_DEC,r10; \ b MASKED_DEC_HANDLER_LABEL; \ -1: andi. r10,r10,(PACA_IRQ_DBELL|PACA_IRQ_HMI); \ - bne 2f; \ +1: andi. r10,r10,PACA_IRQ_MUST_HARD_MASK; \ + beq 2f; \ mfspr r10,SPRN_##_H##SRR1; \ xori r10,r10,MSR_EE; /* clear MSR_EE */ \ mtspr SPRN_##_H##SRR1,r10; \ -- cgit v1.2.3-55-g7522 From eeb715c3e995fbdda0cc05e61216c6c5609bce66 Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Wed, 7 Feb 2018 11:20:02 +1000 Subject: powerpc/64s/radix: Boot-time NULL pointer protection using a guard-PID This change restores and formalises the behaviour that access to NULL or other user addresses by the kernel during boot should fault rather than succeed and modify memory. This was inadvertently broken when fixing another bug, because it was previously not well defined and only worked by chance. powerpc/64s/radix uses high address bits to select an address space "quadrant", which determines which PID and LPID are used to translate the rest of the address (effective PID, effective LPID). The kernel mapping at 0xC... selects quadrant 3, which uses PID=0 and LPID=0. So the kernel page tables are installed in the PID 0 process table entry. An address at 0x0... selects quadrant 0, which uses PID=PIDR for translating the rest of the address (that is, it uses the value of the PIDR register as the effective PID). If PIDR=0, then the translation is performed with the PID 0 process table entry page tables. This is the kernel mapping, so we effectively get another copy of the kernel address space at 0. A NULL pointer access will access physical memory address 0. To prevent duplicating the kernel address space in quadrant 0, this patch allocates a guard PID containing no translations, and initializes PIDR with this during boot, before the MMU is switched on. Any kernel access to quadrant 0 will use this guard PID for translation and find no valid mappings, and therefore fault. After boot, this PID will be switchd away to user context PIDs, but those contain user mappings (and usually NULL pointer protection) rather than kernel mapping, which is much safer (and by design). It may be in future this is tightened further, which the guard PID could be used for. Commit 371b8044 ("powerpc/64s: Initialize ISAv3 MMU registers before setting partition table"), introduced this problem because it zeroes PIDR at boot. However previously the value was inherited from firmware or kexec, which is not robust and can be zero (e.g., mambo). Fixes: 371b80447ff3 ("powerpc/64s: Initialize ISAv3 MMU registers before setting partition table") Cc: stable@vger.kernel.org # v4.15+ Reported-by: Florian Weimer Tested-by: Mauricio Faria de Oliveira Signed-off-by: Nicholas Piggin Signed-off-by: Michael Ellerman --- arch/powerpc/mm/pgtable-radix.c | 21 ++++++++++++++++++++- 1 file changed, 20 insertions(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/powerpc/mm/pgtable-radix.c b/arch/powerpc/mm/pgtable-radix.c index 573a9a2ee455..96e07d1f673d 100644 --- a/arch/powerpc/mm/pgtable-radix.c +++ b/arch/powerpc/mm/pgtable-radix.c @@ -20,6 +20,7 @@ #include #include +#include #include #include #include @@ -333,6 +334,22 @@ static void __init radix_init_pgtable(void) "r" (TLBIEL_INVAL_SET_LPID), "r" (0)); asm volatile("eieio; tlbsync; ptesync" : : : "memory"); trace_tlbie(0, 0, TLBIEL_INVAL_SET_LPID, 0, 2, 1, 1); + + /* + * The init_mm context is given the first available (non-zero) PID, + * which is the "guard PID" and contains no page table. PIDR should + * never be set to zero because that duplicates the kernel address + * space at the 0x0... offset (quadrant 0)! + * + * An arbitrary PID that may later be allocated by the PID allocator + * for userspace processes must not be used either, because that + * would cause stale user mappings for that PID on CPUs outside of + * the TLB invalidation scheme (because it won't be in mm_cpumask). + * + * So permanently carve out one PID for the purpose of a guard PID. + */ + init_mm.context.id = mmu_base_pid; + mmu_base_pid++; } static void __init radix_init_partition_table(void) @@ -579,7 +596,8 @@ void __init radix__early_init_mmu(void) radix_init_iamr(); radix_init_pgtable(); - + /* Switch to the guard PID before turning on MMU */ + radix__switch_mmu_context(NULL, &init_mm); if (cpu_has_feature(CPU_FTR_HVMODE)) tlbiel_all(); } @@ -604,6 +622,7 @@ void radix__early_init_mmu_secondary(void) } radix_init_iamr(); + radix__switch_mmu_context(NULL, &init_mm); if (cpu_has_feature(CPU_FTR_HVMODE)) tlbiel_all(); } -- cgit v1.2.3-55-g7522 From 4dd5f8a99e791a8c6500e3592f3ce81ae7edcde1 Mon Sep 17 00:00:00 2001 From: Balbir Singh Date: Wed, 7 Feb 2018 17:35:51 +1100 Subject: powerpc/mm/radix: Split linear mapping on hot-unplug This patch splits the linear mapping if the hot-unplug range is smaller than the mapping size. The code detects if the mapping needs to be split into a smaller size and if so, uses the stop machine infrastructure to clear the existing mapping and then remap the remaining range using a smaller page size. The code will skip any region of the mapping that overlaps with kernel text and warn about it once. We don't want to remove a mapping where the kernel text and the LMB we intend to remove overlap in the same TLB mapping as it may affect the currently executing code. I've tested these changes under a kvm guest with 2 vcpus, from a split mapping point of view, some of the caveats mentioned above applied to the testing I did. Fixes: 4b5d62ca17a1 ("powerpc/mm: add radix__remove_section_mapping()") Signed-off-by: Balbir Singh [mpe: Tweak change log to match updated behaviour] Signed-off-by: Michael Ellerman --- arch/powerpc/mm/pgtable-radix.c | 95 ++++++++++++++++++++++++++++++++--------- 1 file changed, 74 insertions(+), 21 deletions(-) (limited to 'arch') diff --git a/arch/powerpc/mm/pgtable-radix.c b/arch/powerpc/mm/pgtable-radix.c index 96e07d1f673d..328ff9abc333 100644 --- a/arch/powerpc/mm/pgtable-radix.c +++ b/arch/powerpc/mm/pgtable-radix.c @@ -17,6 +17,7 @@ #include #include #include +#include #include #include @@ -685,6 +686,30 @@ static void free_pmd_table(pmd_t *pmd_start, pud_t *pud) pud_clear(pud); } +struct change_mapping_params { + pte_t *pte; + unsigned long start; + unsigned long end; + unsigned long aligned_start; + unsigned long aligned_end; +}; + +static int stop_machine_change_mapping(void *data) +{ + struct change_mapping_params *params = + (struct change_mapping_params *)data; + + if (!data) + return -1; + + spin_unlock(&init_mm.page_table_lock); + pte_clear(&init_mm, params->aligned_start, params->pte); + create_physical_mapping(params->aligned_start, params->start); + create_physical_mapping(params->end, params->aligned_end); + spin_lock(&init_mm.page_table_lock); + return 0; +} + static void remove_pte_table(pte_t *pte_start, unsigned long addr, unsigned long end) { @@ -713,6 +738,52 @@ static void remove_pte_table(pte_t *pte_start, unsigned long addr, } } +/* + * clear the pte and potentially split the mapping helper + */ +static void split_kernel_mapping(unsigned long addr, unsigned long end, + unsigned long size, pte_t *pte) +{ + unsigned long mask = ~(size - 1); + unsigned long aligned_start = addr & mask; + unsigned long aligned_end = addr + size; + struct change_mapping_params params; + bool split_region = false; + + if ((end - addr) < size) { + /* + * We're going to clear the PTE, but not flushed + * the mapping, time to remap and flush. The + * effects if visible outside the processor or + * if we are running in code close to the + * mapping we cleared, we are in trouble. + */ + if (overlaps_kernel_text(aligned_start, addr) || + overlaps_kernel_text(end, aligned_end)) { + /* + * Hack, just return, don't pte_clear + */ + WARN_ONCE(1, "Linear mapping %lx->%lx overlaps kernel " + "text, not splitting\n", addr, end); + return; + } + split_region = true; + } + + if (split_region) { + params.pte = pte; + params.start = addr; + params.end = end; + params.aligned_start = addr & ~(size - 1); + params.aligned_end = min_t(unsigned long, aligned_end, + (unsigned long)__va(memblock_end_of_DRAM())); + stop_machine(stop_machine_change_mapping, ¶ms, NULL); + return; + } + + pte_clear(&init_mm, addr, pte); +} + static void remove_pmd_table(pmd_t *pmd_start, unsigned long addr, unsigned long end) { @@ -728,13 +799,7 @@ static void remove_pmd_table(pmd_t *pmd_start, unsigned long addr, continue; if (pmd_huge(*pmd)) { - if (!IS_ALIGNED(addr, PMD_SIZE) || - !IS_ALIGNED(next, PMD_SIZE)) { - WARN_ONCE(1, "%s: unaligned range\n", __func__); - continue; - } - - pte_clear(&init_mm, addr, (pte_t *)pmd); + split_kernel_mapping(addr, end, PMD_SIZE, (pte_t *)pmd); continue; } @@ -759,13 +824,7 @@ static void remove_pud_table(pud_t *pud_start, unsigned long addr, continue; if (pud_huge(*pud)) { - if (!IS_ALIGNED(addr, PUD_SIZE) || - !IS_ALIGNED(next, PUD_SIZE)) { - WARN_ONCE(1, "%s: unaligned range\n", __func__); - continue; - } - - pte_clear(&init_mm, addr, (pte_t *)pud); + split_kernel_mapping(addr, end, PUD_SIZE, (pte_t *)pud); continue; } @@ -791,13 +850,7 @@ static void remove_pagetable(unsigned long start, unsigned long end) continue; if (pgd_huge(*pgd)) { - if (!IS_ALIGNED(addr, PGDIR_SIZE) || - !IS_ALIGNED(next, PGDIR_SIZE)) { - WARN_ONCE(1, "%s: unaligned range\n", __func__); - continue; - } - - pte_clear(&init_mm, addr, (pte_t *)pgd); + split_kernel_mapping(addr, end, PGDIR_SIZE, (pte_t *)pgd); continue; } -- cgit v1.2.3-55-g7522 From 791412dafbbfd860e78983d45cf71db603a82f67 Mon Sep 17 00:00:00 2001 From: Paul Burton Date: Fri, 19 Jan 2018 16:40:49 +0100 Subject: MIPS: CPC: Map registers using DT in mips_cpc_default_phys_base() Reading mips_cpc_base value from the DT allows each platform to define it according to its needs. This is especially convenient for MIPS_GENERIC kernel where this kind of information should be determined in runtime. Use mti,mips-cpc compatible string with just a reg property to specify the register location for your platform. Signed-off-by: Paul Burton Signed-off-by: Miodrag Dinic Signed-off-by: Aleksandar Markovic Cc: linux-mips@linux-mips.org Cc: Ralf Baechle Patchwork: https://patchwork.linux-mips.org/patch/18513/ Signed-off-by: James Hogan --- arch/mips/kernel/mips-cpc.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'arch') diff --git a/arch/mips/kernel/mips-cpc.c b/arch/mips/kernel/mips-cpc.c index 19c88d770054..fcf9af492d60 100644 --- a/arch/mips/kernel/mips-cpc.c +++ b/arch/mips/kernel/mips-cpc.c @@ -10,6 +10,8 @@ #include #include +#include +#include #include #include @@ -22,6 +24,17 @@ static DEFINE_PER_CPU_ALIGNED(unsigned long, cpc_core_lock_flags); phys_addr_t __weak mips_cpc_default_phys_base(void) { + struct device_node *cpc_node; + struct resource res; + int err; + + cpc_node = of_find_compatible_node(of_root, NULL, "mti,mips-cpc"); + if (cpc_node) { + err = of_address_to_resource(cpc_node, 0, &res); + if (!err) + return res.start; + } + return 0; } -- cgit v1.2.3-55-g7522 From 14b1fcc62043729d12e8ae00f8297ab2ffe9fa91 Mon Sep 17 00:00:00 2001 From: Nadav Amit Date: Fri, 9 Feb 2018 09:06:38 -0800 Subject: x86/mm/pti: Fix PTI comment in entry_SYSCALL_64() The comment is confusing since the path is taken when CONFIG_PAGE_TABLE_ISOLATION=y is disabled (while the comment says it is not taken). Signed-off-by: Nadav Amit Cc: Andy Lutomirski Cc: Arjan van de Ven Cc: Borislav Petkov Cc: Dan Williams Cc: Dave Hansen Cc: David Woodhouse Cc: Greg Kroah-Hartman Cc: Josh Poimboeuf Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: nadav.amit@gmail.com Link: http://lkml.kernel.org/r/20180209170638.15161-1-namit@vmware.com Signed-off-by: Ingo Molnar --- arch/x86/entry/entry_64.S | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 9e48002b953b..932a445febee 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -213,7 +213,7 @@ ENTRY(entry_SYSCALL_64) swapgs /* - * This path is not taken when PAGE_TABLE_ISOLATION is disabled so it + * This path is only taken when PAGE_TABLE_ISOLATION is disabled so it * is not required to switch CR3. */ movq %rsp, PER_CPU_VAR(rsp_scratch) -- cgit v1.2.3-55-g7522 From 1751342095f0d2b36fa8114d8e12c5688c455ac4 Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Sat, 10 Feb 2018 23:39:22 +0000 Subject: x86/speculation: Update Speculation Control microcode blacklist Intel have retroactively blessed the 0xc2 microcode on Skylake mobile and desktop parts, and the Gemini Lake 0x22 microcode is apparently fine too. We blacklisted the latter purely because it was present with all the other problematic ones in the 2018-01-08 release, but now it's explicitly listed as OK. We still list 0x84 for the various Kaby Lake / Coffee Lake parts, as that appeared in one version of the blacklist and then reverted to 0x80 again. We can change it if 0x84 is actually announced to be safe. Signed-off-by: David Woodhouse Cc: Andy Lutomirski Cc: Arjan van de Ven Cc: Borislav Petkov Cc: Dan Williams Cc: Dave Hansen Cc: David Woodhouse Cc: Greg Kroah-Hartman Cc: Josh Poimboeuf Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: arjan.van.de.ven@intel.com Cc: jmattson@google.com Cc: karahmed@amazon.de Cc: kvm@vger.kernel.org Cc: pbonzini@redhat.com Cc: rkrcmar@redhat.com Cc: sironi@amazon.de Link: http://lkml.kernel.org/r/1518305967-31356-2-git-send-email-dwmw@amazon.co.uk Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/intel.c | 4 ---- 1 file changed, 4 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index 319bf989fad1..f73b8148dd55 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -123,8 +123,6 @@ static const struct sku_microcode spectre_bad_microcodes[] = { { INTEL_FAM6_KABYLAKE_MOBILE, 0x09, 0x84 }, { INTEL_FAM6_SKYLAKE_X, 0x03, 0x0100013e }, { INTEL_FAM6_SKYLAKE_X, 0x04, 0x0200003c }, - { INTEL_FAM6_SKYLAKE_MOBILE, 0x03, 0xc2 }, - { INTEL_FAM6_SKYLAKE_DESKTOP, 0x03, 0xc2 }, { INTEL_FAM6_BROADWELL_CORE, 0x04, 0x28 }, { INTEL_FAM6_BROADWELL_GT3E, 0x01, 0x1b }, { INTEL_FAM6_BROADWELL_XEON_D, 0x02, 0x14 }, @@ -136,8 +134,6 @@ static const struct sku_microcode spectre_bad_microcodes[] = { { INTEL_FAM6_HASWELL_X, 0x02, 0x3b }, { INTEL_FAM6_HASWELL_X, 0x04, 0x10 }, { INTEL_FAM6_IVYBRIDGE_X, 0x04, 0x42a }, - /* Updated in the 20180108 release; blacklist until we know otherwise */ - { INTEL_FAM6_ATOM_GEMINI_LAKE, 0x01, 0x22 }, /* Observed in the wild */ { INTEL_FAM6_SANDYBRIDGE_X, 0x06, 0x61b }, { INTEL_FAM6_SANDYBRIDGE_X, 0x07, 0x712 }, -- cgit v1.2.3-55-g7522 From c80c5ec1b2fa8d3675fc2a6807a64771ea156698 Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Sat, 10 Feb 2018 15:53:14 +0100 Subject: x86/MCE: Fix build warning introduced by "x86: do not use print_symbol()" The following commit: 7b6061627eb8 ("x86: do not use print_symbol()") ... introduced a new build warning on 32-bit x86: arch/x86/kernel/cpu/mcheck/mce.c:237:21: warning: cast to pointer from integer of different size [-Wint-to-pointer-cast] pr_cont("{%pS}", (void *)m->ip); ^ Fix the type mismatch between the 'void *' expected by %pS and the mce->ip field which is u64 by casting to long. Signed-off-by: Borislav Petkov Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Sergey Senozhatsky Cc: Thomas Gleixner Cc: Tony Luck Cc: linux-kernel@vger.kernel.org Fixes: 7b6061627eb8 ("x86: do not use print_symbol()") Link: http://lkml.kernel.org/r/20180210145314.22174-1-bp@alien8.de [ Cleaned up the changelog. ] Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/mcheck/mce.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 3a8e88a611eb..75f405ac085c 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -234,7 +234,7 @@ static void __print_mce(struct mce *m) m->cs, m->ip); if (m->cs == __KERNEL_CS) - pr_cont("{%pS}", (void *)m->ip); + pr_cont("{%pS}", (void *)(unsigned long)m->ip); pr_cont("\n"); } -- cgit v1.2.3-55-g7522 From a0d0bb4deba831085d3eeb32d39fe73713ce6eb2 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Fri, 9 Feb 2018 16:51:03 -0800 Subject: x86/Kconfig: Simplify NR_CPUS config Clean up and simplify the X86 NR_CPUS Kconfig symbol/option by introducing RANGE_BEGIN_CPUS, RANGE_END_CPUS, and DEF_CONFIG_CPUS. Then combine some default values when their conditionals can be reduced. Also move the X86_BIGSMP kconfig option inside an "if X86_32"/"endif" config block and drop its explicit "depends on X86_32". Combine the max. 8192 cases of RANGE_END_CPUS (X86_64 only). Split RANGE_END_CPUS and DEF_CONFIG_CPUS into separate cases for X86_32 and X86_64. Suggested-by: Linus Torvalds Signed-off-by: Randy Dunlap Acked-by: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/0b833246-ed4b-e451-c426-c4464725be92@infradead.org Link: lkml.kernel.org/r/CA+55aFzOd3j6ZUSkEwTdk85qtt1JywOtm3ZAb-qAvt8_hJ6D4A@mail.gmail.com Signed-off-by: Ingo Molnar --- arch/x86/Kconfig | 57 +++++++++++++++++++++++++++++++++++++++++--------------- 1 file changed, 42 insertions(+), 15 deletions(-) (limited to 'arch') diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 63bf349b2b24..9d921b78b145 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -423,12 +423,6 @@ config X86_MPPARSE For old smp systems that do not have proper acpi support. Newer systems (esp with 64bit cpus) with acpi support, MADT and DSDT will override it -config X86_BIGSMP - bool "Support for big SMP systems with more than 8 CPUs" - depends on X86_32 && SMP - ---help--- - This option is needed for the systems that have more than 8 CPUs - config GOLDFISH def_bool y depends on X86_GOLDFISH @@ -460,6 +454,12 @@ config INTEL_RDT Say N if unsure. if X86_32 +config X86_BIGSMP + bool "Support for big SMP systems with more than 8 CPUs" + depends on SMP + ---help--- + This option is needed for the systems that have more than 8 CPUs + config X86_EXTENDED_PLATFORM bool "Support for extended (non-PC) x86 platforms" default y @@ -949,17 +949,44 @@ config MAXSMP Enable maximum number of CPUS and NUMA Nodes for this architecture. If unsure, say N. +config RANGE_END_CPUS + int + depends on X86_32 + default 8 if SMP && !X86_BIGSMP + default 64 if SMP && X86_BIGSMP + default 1 if !SMP + +config RANGE_END_CPUS + int + depends on X86_64 + default 512 if SMP && !MAXSMP && !CPUMASK_OFFSTACK + default 8192 if SMP && (MAXSMP || CPUMASK_OFFSTACK) + default 1 if !SMP + +config RANGE_BEGIN_CPUS + int + default 1 if !SMP + default RANGE_END_CPUS if MAXSMP + default 2 + +config DEF_CONFIG_CPUS + int + depends on X86_32 + default 1 if !SMP + default 32 if X86_BIGSMP + default 8 if SMP + +config DEF_CONFIG_CPUS + int + depends on X86_64 + default 1 if !SMP + default 8192 if MAXSMP + default 64 if SMP + config NR_CPUS int "Maximum number of CPUs" if SMP && !MAXSMP - range 2 8 if SMP && X86_32 && !X86_BIGSMP - range 2 64 if SMP && X86_32 && X86_BIGSMP - range 2 512 if SMP && !MAXSMP && !CPUMASK_OFFSTACK && X86_64 - range 2 8192 if SMP && !MAXSMP && CPUMASK_OFFSTACK && X86_64 - default "1" if !SMP - default "8192" if MAXSMP - default "32" if SMP && X86_BIGSMP - default "8" if SMP && X86_32 - default "64" if SMP + range RANGE_BEGIN_CPUS RANGE_END_CPUS + default DEF_CONFIG_CPUS ---help--- This allows you to specify the maximum number of CPUs which this kernel will support. If CPUMASK_OFFSTACK is enabled, the maximum -- cgit v1.2.3-55-g7522 From aec6487e994d2f625197970a56a4aac40c2c7547 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Sat, 10 Feb 2018 12:36:29 +0100 Subject: x86/Kconfig: Further simplify the NR_CPUS config Clean up various aspects of the x86 CONFIG_NR_CPUS configuration switches: - Rename the three CONFIG_NR_CPUS related variables to create a common namespace for them: RANGE_BEGIN_CPUS => NR_CPUS_RANGE_BEGIN RANGE_END_CPUS => NR_CPUS_RANGE_END DEF_CONFIG_CPUS => NR_CPUS_DEFAULT - Align them vertically, such as: config NR_CPUS_RANGE_END int depends on X86_64 default 8192 if SMP && ( MAXSMP || CPUMASK_OFFSTACK) default 512 if SMP && (!MAXSMP && !CPUMASK_OFFSTACK) default 1 if !SMP - Update help text, add more comments. Test results: # i386 allnoconfig: CONFIG_NR_CPUS_RANGE_BEGIN=1 CONFIG_NR_CPUS_RANGE_END=1 CONFIG_NR_CPUS_DEFAULT=1 CONFIG_NR_CPUS=1 # i386 defconfig: CONFIG_NR_CPUS_RANGE_BEGIN=2 CONFIG_NR_CPUS_RANGE_END=8 CONFIG_NR_CPUS_DEFAULT=8 CONFIG_NR_CPUS=8 # i386 allyesconfig: CONFIG_NR_CPUS_RANGE_BEGIN=2 CONFIG_NR_CPUS_RANGE_END=64 CONFIG_NR_CPUS_DEFAULT=32 CONFIG_NR_CPUS=32 # x86_64 allnoconfig: CONFIG_NR_CPUS_RANGE_BEGIN=1 CONFIG_NR_CPUS_RANGE_END=1 CONFIG_NR_CPUS_DEFAULT=1 CONFIG_NR_CPUS=1 # x86_64 defconfig: CONFIG_NR_CPUS_RANGE_BEGIN=2 CONFIG_NR_CPUS_RANGE_END=512 CONFIG_NR_CPUS_DEFAULT=64 CONFIG_NR_CPUS=64 # x86_64 allyesconfig: CONFIG_NR_CPUS_RANGE_BEGIN=8192 CONFIG_NR_CPUS_RANGE_END=8192 CONFIG_NR_CPUS_DEFAULT=8192 CONFIG_NR_CPUS=8192 Acked-by: Randy Dunlap Acked-by: Linus Torvalds Cc: Peter Zijlstra Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20180210113629.jcv6su3r4suuno63@gmail.com Signed-off-by: Ingo Molnar --- arch/x86/Kconfig | 66 ++++++++++++++++++++++++++++++++++---------------------- 1 file changed, 40 insertions(+), 26 deletions(-) (limited to 'arch') diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 9d921b78b145..a528c14d45a5 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -949,52 +949,66 @@ config MAXSMP Enable maximum number of CPUS and NUMA Nodes for this architecture. If unsure, say N. -config RANGE_END_CPUS +# +# The maximum number of CPUs supported: +# +# The main config value is NR_CPUS, which defaults to NR_CPUS_DEFAULT, +# and which can be configured interactively in the +# [NR_CPUS_RANGE_BEGIN ... NR_CPUS_RANGE_END] range. +# +# The ranges are different on 32-bit and 64-bit kernels, depending on +# hardware capabilities and scalability features of the kernel. +# +# ( If MAXSMP is enabled we just use the highest possible value and disable +# interactive configuration. ) +# + +config NR_CPUS_RANGE_BEGIN int - depends on X86_32 - default 8 if SMP && !X86_BIGSMP - default 64 if SMP && X86_BIGSMP - default 1 if !SMP + default NR_CPUS_RANGE_END if MAXSMP + default 1 if !SMP + default 2 -config RANGE_END_CPUS +config NR_CPUS_RANGE_END int - depends on X86_64 - default 512 if SMP && !MAXSMP && !CPUMASK_OFFSTACK - default 8192 if SMP && (MAXSMP || CPUMASK_OFFSTACK) - default 1 if !SMP + depends on X86_32 + default 64 if SMP && X86_BIGSMP + default 8 if SMP && !X86_BIGSMP + default 1 if !SMP -config RANGE_BEGIN_CPUS +config NR_CPUS_RANGE_END int - default 1 if !SMP - default RANGE_END_CPUS if MAXSMP - default 2 + depends on X86_64 + default 8192 if SMP && ( MAXSMP || CPUMASK_OFFSTACK) + default 512 if SMP && (!MAXSMP && !CPUMASK_OFFSTACK) + default 1 if !SMP -config DEF_CONFIG_CPUS +config NR_CPUS_DEFAULT int depends on X86_32 - default 1 if !SMP - default 32 if X86_BIGSMP - default 8 if SMP + default 32 if X86_BIGSMP + default 8 if SMP + default 1 if !SMP -config DEF_CONFIG_CPUS +config NR_CPUS_DEFAULT int depends on X86_64 - default 1 if !SMP - default 8192 if MAXSMP - default 64 if SMP + default 8192 if MAXSMP + default 64 if SMP + default 1 if !SMP config NR_CPUS int "Maximum number of CPUs" if SMP && !MAXSMP - range RANGE_BEGIN_CPUS RANGE_END_CPUS - default DEF_CONFIG_CPUS + range NR_CPUS_RANGE_BEGIN NR_CPUS_RANGE_END + default NR_CPUS_DEFAULT ---help--- This allows you to specify the maximum number of CPUs which this kernel will support. If CPUMASK_OFFSTACK is enabled, the maximum supported value is 8192, otherwise the maximum value is 512. The minimum value which makes sense is 2. - This is purely to save memory - each supported CPU adds - approximately eight kilobytes to the kernel image. + This is purely to save memory: each supported CPU adds about 8KB + to the kernel image. config SCHED_SMT bool "SMT (Hyperthreading) scheduler support" -- cgit v1.2.3-55-g7522 From 73e42e18669934fa96cf2bb54291da54177076d7 Mon Sep 17 00:00:00 2001 From: Kamil Trzciński Date: Mon, 22 Jan 2018 18:46:22 +0100 Subject: arm64: dts: rockchip: fix rock64 gmac2io stability issues This commit enables thresh dma mode as this forces to disable checksuming, and chooses delay values which make the interface stable. These changes are needed, because ROCK64 is faced with two problems: 1. tx checksuming does not work with packets larger than 1498, 2. the default delays for tx/rx are not stable when using 1Gbps connection. Delays were found out with: https://github.com/ayufan-rock64/linux-build/tree/master/recipes/gmac-delays-test Signed-off-by: Kamil Trzciński Signed-off-by: Heiko Stuebner --- arch/arm64/boot/dts/rockchip/rk3328-rock64.dts | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'arch') diff --git a/arch/arm64/boot/dts/rockchip/rk3328-rock64.dts b/arch/arm64/boot/dts/rockchip/rk3328-rock64.dts index 3890468678ce..28257724a56e 100644 --- a/arch/arm64/boot/dts/rockchip/rk3328-rock64.dts +++ b/arch/arm64/boot/dts/rockchip/rk3328-rock64.dts @@ -132,17 +132,16 @@ assigned-clocks = <&cru SCLK_MAC2IO>, <&cru SCLK_MAC2IO_EXT>; assigned-clock-parents = <&gmac_clkin>, <&gmac_clkin>; clock_in_out = "input"; - /* shows instability at 1GBit right now */ - max-speed = <100>; phy-supply = <&vcc_io>; phy-mode = "rgmii"; pinctrl-names = "default"; pinctrl-0 = <&rgmiim1_pins>; + snps,force_thresh_dma_mode; snps,reset-gpio = <&gpio1 RK_PC2 GPIO_ACTIVE_LOW>; snps,reset-active-low; snps,reset-delays-us = <0 10000 50000>; - tx_delay = <0x26>; - rx_delay = <0x11>; + tx_delay = <0x24>; + rx_delay = <0x18>; status = "okay"; }; -- cgit v1.2.3-55-g7522 From 2b7d2ed1af2e2c0c90a1a8b97926b7b6c6cb03ed Mon Sep 17 00:00:00 2001 From: Shawn Lin Date: Fri, 9 Feb 2018 16:51:48 +0800 Subject: arm64: dts: rockchip: correct ep-gpios for rk3399-sapphire The endpoint control gpio for rk3399-sapphire boards is gpio2_a4, so correct it now. Signed-off-by: Shawn Lin Signed-off-by: Heiko Stuebner --- arch/arm64/boot/dts/rockchip/rk3399-sapphire.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/arm64/boot/dts/rockchip/rk3399-sapphire.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-sapphire.dtsi index 0f873c897d0d..ce592a4c0c4c 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-sapphire.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399-sapphire.dtsi @@ -457,7 +457,7 @@ assigned-clocks = <&cru SCLK_PCIEPHY_REF>; assigned-clock-parents = <&cru SCLK_PCIEPHY_REF100M>; assigned-clock-rates = <100000000>; - ep-gpios = <&gpio3 RK_PB5 GPIO_ACTIVE_HIGH>; + ep-gpios = <&gpio2 RK_PA4 GPIO_ACTIVE_HIGH>; num-lanes = <4>; pinctrl-names = "default"; pinctrl-0 = <&pcie_clkreqn_cpm>; -- cgit v1.2.3-55-g7522 From 7b0390eabdd1dec50f60ad25e7e706875bfa223e Mon Sep 17 00:00:00 2001 From: Yakir Yang Date: Wed, 7 Feb 2018 17:31:48 +0100 Subject: arm64: dts: rockchip: introduce pclk_vio_grf in rk3399-eDP device node The pclk_vio_grf supply power for VIO GRF IOs, if it is disabled, driver would failed to operate the VIO GRF registers. The clock is optional but one of the side effects of don't have this clk is that the Samsung Chromebook Plus fails to recover display after a suspend/resume with following errors: rockchip-dp ff970000.edp: Input stream clock not detected. rockchip-dp ff970000.edp: Timeout of video streamclk ok rockchip-dp ff970000.edp: unable to config video Signed-off-by: Yakir Yang Signed-off-by: Enric Balletbo i Serra [this should also fix display failures when building rockchip-drm as module] Signed-off-by: Heiko Stuebner --- arch/arm64/boot/dts/rockchip/rk3399.dtsi | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch') diff --git a/arch/arm64/boot/dts/rockchip/rk3399.dtsi b/arch/arm64/boot/dts/rockchip/rk3399.dtsi index 7aa2144e0d47..2605118d4b4c 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399.dtsi @@ -1739,8 +1739,8 @@ compatible = "rockchip,rk3399-edp"; reg = <0x0 0xff970000 0x0 0x8000>; interrupts = ; - clocks = <&cru PCLK_EDP>, <&cru PCLK_EDP_CTRL>; - clock-names = "dp", "pclk"; + clocks = <&cru PCLK_EDP>, <&cru PCLK_EDP_CTRL>, <&cru PCLK_VIO_GRF>; + clock-names = "dp", "pclk", "grf"; pinctrl-names = "default"; pinctrl-0 = <&edp_hpd>; power-domains = <&power RK3399_PD_EDP>; -- cgit v1.2.3-55-g7522 From 16e574d762ac5512eb922ac0ac5eed360b7db9d8 Mon Sep 17 00:00:00 2001 From: Shanker Donthineni Date: Sun, 11 Feb 2018 19:16:15 -0600 Subject: arm64: Add missing Falkor part number for branch predictor hardening References to CPU part number MIDR_QCOM_FALKOR were dropped from the mailing list patch due to mainline/arm64 branch dependency. So this patch adds the missing part number. Fixes: ec82b567a74f ("arm64: Implement branch predictor hardening for Falkor") Acked-by: Marc Zyngier Signed-off-by: Shanker Donthineni Signed-off-by: Catalin Marinas --- arch/arm64/kernel/cpu_errata.c | 9 +++++++++ arch/arm64/kvm/hyp/switch.c | 4 +++- 2 files changed, 12 insertions(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index 07823595b7f0..52f15cd896e1 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -406,6 +406,15 @@ const struct arm64_cpu_capabilities arm64_errata[] = { .capability = ARM64_HARDEN_BP_POST_GUEST_EXIT, MIDR_ALL_VERSIONS(MIDR_QCOM_FALKOR_V1), }, + { + .capability = ARM64_HARDEN_BRANCH_PREDICTOR, + MIDR_ALL_VERSIONS(MIDR_QCOM_FALKOR), + .enable = qcom_enable_link_stack_sanitization, + }, + { + .capability = ARM64_HARDEN_BP_POST_GUEST_EXIT, + MIDR_ALL_VERSIONS(MIDR_QCOM_FALKOR), + }, { .capability = ARM64_HARDEN_BRANCH_PREDICTOR, MIDR_ALL_VERSIONS(MIDR_BRCM_VULCAN), diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c index 116252a8d3a5..870f4b1587f9 100644 --- a/arch/arm64/kvm/hyp/switch.c +++ b/arch/arm64/kvm/hyp/switch.c @@ -407,8 +407,10 @@ again: u32 midr = read_cpuid_id(); /* Apply BTAC predictors mitigation to all Falkor chips */ - if ((midr & MIDR_CPU_MODEL_MASK) == MIDR_QCOM_FALKOR_V1) + if (((midr & MIDR_CPU_MODEL_MASK) == MIDR_QCOM_FALKOR) || + ((midr & MIDR_CPU_MODEL_MASK) == MIDR_QCOM_FALKOR_V1)) { __qcom_hyp_sanitize_btac_predictors(); + } } fp_enabled = __fpsimd_enabled(); -- cgit v1.2.3-55-g7522 From 9d37c094dacda531ac3e529dd4dd139e3c0b7811 Mon Sep 17 00:00:00 2001 From: Corentin Labbe Date: Thu, 8 Feb 2018 19:39:20 +0000 Subject: ia64: fix build failure with CONFIG_SWIOTLB arch/ia64/kernel/pci-swiotlb.c is removed in commit 4fac8076df85 ("ia64: clean up swiotlb support") but pci-swiotlb.o is still present in Makefile, and so build fail when CONFIG_SWIOTLB is enabled. Fix the build failure by removing pci-swiotlb.o from makefile Fixes: 4fac8076df85 ("ia64: clean up swiotlb support") Signed-off-by: Corentin Labbe Signed-off-by: Christoph Hellwig --- arch/ia64/kernel/Makefile | 1 - 1 file changed, 1 deletion(-) (limited to 'arch') diff --git a/arch/ia64/kernel/Makefile b/arch/ia64/kernel/Makefile index 0b4c65a1af25..498f3da3f225 100644 --- a/arch/ia64/kernel/Makefile +++ b/arch/ia64/kernel/Makefile @@ -41,7 +41,6 @@ ifneq ($(CONFIG_IA64_ESI),) obj-y += esi_stub.o # must be in kernel proper endif obj-$(CONFIG_INTEL_IOMMU) += pci-dma.o -obj-$(CONFIG_SWIOTLB) += pci-swiotlb.o obj-$(CONFIG_BINFMT_ELF) += elfcore.o -- cgit v1.2.3-55-g7522 From 2363ec931e88ee095e5ac2e87e1c3b3b741f6fdc Mon Sep 17 00:00:00 2001 From: Jerome Brunet Date: Mon, 18 Dec 2017 11:27:13 +0100 Subject: ARM64: dts: meson-gxl: add internal ethernet PHY irq Add the interrupt of the internal ethernet PHY Signed-off-by: Jerome Brunet Signed-off-by: Kevin Hilman --- arch/arm64/boot/dts/amlogic/meson-gxl.dtsi | 1 + 1 file changed, 1 insertion(+) (limited to 'arch') diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi index 4f355f17eed6..c8514110b9da 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi @@ -631,6 +631,7 @@ internal_phy: ethernet-phy@8 { compatible = "ethernet-phy-id0181.4400", "ethernet-phy-ieee802.3-c22"; + interrupts = ; reg = <8>; max-speed = <100>; }; -- cgit v1.2.3-55-g7522 From 77f5cdbd78ec5e17022725a5da476f4ca08b1dfa Mon Sep 17 00:00:00 2001 From: Yixun Lan Date: Thu, 11 Jan 2018 10:33:57 +0800 Subject: ARM64: dts: meson: uart: fix address space range The address space range is actually 0x18, fixed here. Reviewed-by: Jerome Brunet Signed-off-by: Yixun Lan Signed-off-by: Kevin Hilman --- arch/arm64/boot/dts/amlogic/meson-axg.dtsi | 4 ++-- arch/arm64/boot/dts/amlogic/meson-gx.dtsi | 10 +++++----- 2 files changed, 7 insertions(+), 7 deletions(-) (limited to 'arch') diff --git a/arch/arm64/boot/dts/amlogic/meson-axg.dtsi b/arch/arm64/boot/dts/amlogic/meson-axg.dtsi index a80632641b39..70c776ef7aa7 100644 --- a/arch/arm64/boot/dts/amlogic/meson-axg.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-axg.dtsi @@ -165,14 +165,14 @@ uart_A: serial@24000 { compatible = "amlogic,meson-gx-uart", "amlogic,meson-uart"; - reg = <0x0 0x24000 0x0 0x14>; + reg = <0x0 0x24000 0x0 0x18>; interrupts = ; status = "disabled"; }; uart_B: serial@23000 { compatible = "amlogic,meson-gx-uart", "amlogic,meson-uart"; - reg = <0x0 0x23000 0x0 0x14>; + reg = <0x0 0x23000 0x0 0x18>; interrupts = ; status = "disabled"; }; diff --git a/arch/arm64/boot/dts/amlogic/meson-gx.dtsi b/arch/arm64/boot/dts/amlogic/meson-gx.dtsi index 6cb3c2a52baf..4ee2e7951482 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gx.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-gx.dtsi @@ -235,14 +235,14 @@ uart_A: serial@84c0 { compatible = "amlogic,meson-gx-uart"; - reg = <0x0 0x84c0 0x0 0x14>; + reg = <0x0 0x84c0 0x0 0x18>; interrupts = ; status = "disabled"; }; uart_B: serial@84dc { compatible = "amlogic,meson-gx-uart"; - reg = <0x0 0x84dc 0x0 0x14>; + reg = <0x0 0x84dc 0x0 0x18>; interrupts = ; status = "disabled"; }; @@ -287,7 +287,7 @@ uart_C: serial@8700 { compatible = "amlogic,meson-gx-uart"; - reg = <0x0 0x8700 0x0 0x14>; + reg = <0x0 0x8700 0x0 0x18>; interrupts = ; status = "disabled"; }; @@ -404,14 +404,14 @@ uart_AO: serial@4c0 { compatible = "amlogic,meson-gx-uart", "amlogic,meson-ao-uart"; - reg = <0x0 0x004c0 0x0 0x14>; + reg = <0x0 0x004c0 0x0 0x18>; interrupts = ; status = "disabled"; }; uart_AO_B: serial@4e0 { compatible = "amlogic,meson-gx-uart", "amlogic,meson-ao-uart"; - reg = <0x0 0x004e0 0x0 0x14>; + reg = <0x0 0x004e0 0x0 0x18>; interrupts = ; status = "disabled"; }; -- cgit v1.2.3-55-g7522 From c662f77331c98018ed256501557b4dd67133fbd7 Mon Sep 17 00:00:00 2001 From: Paul Mackerras Date: Tue, 13 Feb 2018 15:16:01 +1100 Subject: KVM: PPC: Fix compile error that occurs when CONFIG_ALTIVEC=n Commit accb757d798c ("KVM: Move vcpu_load to arch-specific kvm_arch_vcpu_ioctl_run", 2017-12-04) added a "goto out" statement and an "out:" label to kvm_arch_vcpu_ioctl_run(). Since the only "goto out" is inside a CONFIG_VSX block, compiling with CONFIG_VSX=n gives a warning that label "out" is defined but not used, and because arch/powerpc is compiled with -Werror, that becomes a compile error that makes the kernel build fail. Merge commit 1ab03c072feb ("Merge tag 'kvm-ppc-next-4.16-2' of git://git.kernel.org/pub/scm/linux/kernel/git/paulus/powerpc", 2018-02-09) added a similar block of code inside a #ifdef CONFIG_ALTIVEC, with a "goto out" statement. In order to make the build succeed, this adds a #ifdef around the "out:" label. This is a minimal, ugly fix, to be replaced later by a refactoring of the code. Since CONFIG_VSX depends on CONFIG_ALTIVEC, it is sufficient to use #ifdef CONFIG_ALTIVEC here. Fixes: accb757d798c ("KVM: Move vcpu_load to arch-specific kvm_arch_vcpu_ioctl_run") Reported-by: Christian Zigotzky Signed-off-by: Paul Mackerras --- arch/powerpc/kvm/powerpc.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'arch') diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 403e642c78f5..0083142c2f84 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -1608,7 +1608,9 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run) kvm_sigset_deactivate(vcpu); +#ifdef CONFIG_ALTIVEC out: +#endif vcpu_put(vcpu); return r; } -- cgit v1.2.3-55-g7522 From 6df3877fc962c2bb3d0438633dfd24a185af6838 Mon Sep 17 00:00:00 2001 From: Paul Mackerras Date: Tue, 13 Feb 2018 15:45:21 +1100 Subject: KVM: PPC: Book3S: Fix compile error that occurs with some gcc versions Some versions of gcc generate a warning that the variable "emulated" may be used uninitialized in function kvmppc_handle_load128_by2x64(). It would be used uninitialized if kvmppc_handle_load128_by2x64 was ever called with vcpu->arch.mmio_vmx_copy_nums == 0, but neither of the callers ever do that, so there is no actual bug. When gcc generates a warning, it causes the build to fail because arch/powerpc is compiled with -Werror. This silences the warning by initializing "emulated" to EMULATE_DONE. Fixes: 09f984961c13 ("KVM: PPC: Book3S: Add MMIO emulation for VMX instructions") Reported-by: Michael Ellerman Signed-off-by: Paul Mackerras --- arch/powerpc/kvm/powerpc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 0083142c2f84..52c205373986 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -1345,7 +1345,7 @@ static int kvmppc_emulate_mmio_vsx_loadstore(struct kvm_vcpu *vcpu, int kvmppc_handle_load128_by2x64(struct kvm_run *run, struct kvm_vcpu *vcpu, unsigned int rt, int is_default_endian) { - enum emulation_result emulated; + enum emulation_result emulated = EMULATE_DONE; while (vcpu->arch.mmio_vmx_copy_nums) { emulated = __kvmppc_handle_load(run, vcpu, rt, 8, -- cgit v1.2.3-55-g7522 From d37fc6d360a404b208547ba112e7dabb6533c7fc Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Mon, 12 Feb 2018 15:27:34 +0000 Subject: x86/speculation: Correct Speculation Control microcode blacklist again Arjan points out that the Intel document only clears the 0xc2 microcode on *some* parts with CPUID 506E3 (INTEL_FAM6_SKYLAKE_DESKTOP stepping 3). For the Skylake H/S platform it's OK but for Skylake E3 which has the same CPUID it isn't (yet) cleared. So removing it from the blacklist was premature. Put it back for now. Also, Arjan assures me that the 0x84 microcode for Kaby Lake which was featured in one of the early revisions of the Intel document was never released to the public, and won't be until/unless it is also validated as safe. So those can change to 0x80 which is what all *other* versions of the doc have identified. Once the retrospective testing of existing public microcodes is done, we should be back into a mode where new microcodes are only released in batches and we shouldn't even need to update the blacklist for those anyway, so this tweaking of the list isn't expected to be a thing which keeps happening. Requested-by: Arjan van de Ven Signed-off-by: David Woodhouse Cc: Andy Lutomirski Cc: Arjan van de Ven Cc: Borislav Petkov Cc: Dan Williams Cc: Dave Hansen Cc: David Woodhouse Cc: Greg Kroah-Hartman Cc: Josh Poimboeuf Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: arjan.van.de.ven@intel.com Cc: dave.hansen@intel.com Cc: kvm@vger.kernel.org Cc: pbonzini@redhat.com Link: http://lkml.kernel.org/r/1518449255-2182-1-git-send-email-dwmw@amazon.co.uk Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/intel.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index f73b8148dd55..ef796f14f7ae 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -116,13 +116,14 @@ struct sku_microcode { u32 microcode; }; static const struct sku_microcode spectre_bad_microcodes[] = { - { INTEL_FAM6_KABYLAKE_DESKTOP, 0x0B, 0x84 }, - { INTEL_FAM6_KABYLAKE_DESKTOP, 0x0A, 0x84 }, - { INTEL_FAM6_KABYLAKE_DESKTOP, 0x09, 0x84 }, - { INTEL_FAM6_KABYLAKE_MOBILE, 0x0A, 0x84 }, - { INTEL_FAM6_KABYLAKE_MOBILE, 0x09, 0x84 }, + { INTEL_FAM6_KABYLAKE_DESKTOP, 0x0B, 0x80 }, + { INTEL_FAM6_KABYLAKE_DESKTOP, 0x0A, 0x80 }, + { INTEL_FAM6_KABYLAKE_DESKTOP, 0x09, 0x80 }, + { INTEL_FAM6_KABYLAKE_MOBILE, 0x0A, 0x80 }, + { INTEL_FAM6_KABYLAKE_MOBILE, 0x09, 0x80 }, { INTEL_FAM6_SKYLAKE_X, 0x03, 0x0100013e }, { INTEL_FAM6_SKYLAKE_X, 0x04, 0x0200003c }, + { INTEL_FAM6_SKYLAKE_DESKTOP, 0x03, 0xc2 }, { INTEL_FAM6_BROADWELL_CORE, 0x04, 0x28 }, { INTEL_FAM6_BROADWELL_GT3E, 0x01, 0x1b }, { INTEL_FAM6_BROADWELL_XEON_D, 0x02, 0x14 }, -- cgit v1.2.3-55-g7522 From f208820a321f9b23d77d7eed89945d862d62a3ed Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Sat, 10 Feb 2018 23:39:23 +0000 Subject: Revert "x86/speculation: Simplify indirect_branch_prediction_barrier()" This reverts commit 64e16720ea0879f8ab4547e3b9758936d483909b. We cannot call C functions like that, without marking all the call-clobbered registers as, well, clobbered. We might have got away with it for now because the __ibp_barrier() function was *fairly* unlikely to actually use any other registers. But no. Just no. Signed-off-by: David Woodhouse Cc: Andy Lutomirski Cc: Arjan van de Ven Cc: Borislav Petkov Cc: Dan Williams Cc: Dave Hansen Cc: David Woodhouse Cc: Greg Kroah-Hartman Cc: Josh Poimboeuf Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: arjan.van.de.ven@intel.com Cc: dave.hansen@intel.com Cc: jmattson@google.com Cc: karahmed@amazon.de Cc: kvm@vger.kernel.org Cc: pbonzini@redhat.com Cc: rkrcmar@redhat.com Cc: sironi@amazon.de Link: http://lkml.kernel.org/r/1518305967-31356-3-git-send-email-dwmw@amazon.co.uk Signed-off-by: Ingo Molnar --- arch/x86/include/asm/nospec-branch.h | 13 +++++++++---- arch/x86/include/asm/processor.h | 3 --- arch/x86/kernel/cpu/bugs.c | 6 ------ 3 files changed, 9 insertions(+), 13 deletions(-) (limited to 'arch') diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index 4d57894635f2..300cc159b4a0 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -164,10 +164,15 @@ static inline void vmexit_fill_RSB(void) static inline void indirect_branch_prediction_barrier(void) { - alternative_input("", - "call __ibp_barrier", - X86_FEATURE_USE_IBPB, - ASM_NO_INPUT_CLOBBER("eax", "ecx", "edx", "memory")); + asm volatile(ALTERNATIVE("", + "movl %[msr], %%ecx\n\t" + "movl %[val], %%eax\n\t" + "movl $0, %%edx\n\t" + "wrmsr", + X86_FEATURE_USE_IBPB) + : : [msr] "i" (MSR_IA32_PRED_CMD), + [val] "i" (PRED_CMD_IBPB) + : "eax", "ecx", "edx", "memory"); } #endif /* __ASSEMBLY__ */ diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 513f9604c192..99799fbd0f7e 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -969,7 +969,4 @@ bool xen_set_default_idle(void); void stop_this_cpu(void *dummy); void df_debug(struct pt_regs *regs, long error_code); - -void __ibp_barrier(void); - #endif /* _ASM_X86_PROCESSOR_H */ diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 71949bf2de5a..61152aa53377 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -337,9 +337,3 @@ ssize_t cpu_show_spectre_v2(struct device *dev, spectre_v2_module_string()); } #endif - -void __ibp_barrier(void) -{ - __wrmsr(MSR_IA32_PRED_CMD, PRED_CMD_IBPB, 0); -} -EXPORT_SYMBOL_GPL(__ibp_barrier); -- cgit v1.2.3-55-g7522 From 928a4c39484281f8ca366f53a1db79330d058401 Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Sat, 10 Feb 2018 23:39:24 +0000 Subject: KVM/x86: Reduce retpoline performance impact in slot_handle_level_range(), by always inlining iterator helper methods With retpoline, tight loops of "call this function for every XXX" are very much pessimised by taking a prediction miss *every* time. This one is by far the biggest contributor to the guest launch time with retpoline. By marking the iterator slot_handle_…() functions always_inline, we can ensure that the indirect function call can be optimised away into a direct call and it actually generates slightly smaller code because some of the other conditionals can get optimised away too. Performance is now pretty close to what we see with nospectre_v2 on the command line. Suggested-by: Linus Torvalds Tested-by: Filippo Sironi Signed-off-by: David Woodhouse Reviewed-by: Filippo Sironi Acked-by: Paolo Bonzini Cc: Andy Lutomirski Cc: Arjan van de Ven Cc: Borislav Petkov Cc: Dan Williams Cc: Dave Hansen Cc: David Woodhouse Cc: Greg Kroah-Hartman Cc: Josh Poimboeuf Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: arjan.van.de.ven@intel.com Cc: dave.hansen@intel.com Cc: jmattson@google.com Cc: karahmed@amazon.de Cc: kvm@vger.kernel.org Cc: rkrcmar@redhat.com Link: http://lkml.kernel.org/r/1518305967-31356-4-git-send-email-dwmw@amazon.co.uk Signed-off-by: Ingo Molnar --- arch/x86/kvm/mmu.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'arch') diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 2b8eb4da4d08..cc83bdcb65d1 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -5058,7 +5058,7 @@ void kvm_mmu_uninit_vm(struct kvm *kvm) typedef bool (*slot_level_handler) (struct kvm *kvm, struct kvm_rmap_head *rmap_head); /* The caller should hold mmu-lock before calling this function. */ -static bool +static __always_inline bool slot_handle_level_range(struct kvm *kvm, struct kvm_memory_slot *memslot, slot_level_handler fn, int start_level, int end_level, gfn_t start_gfn, gfn_t end_gfn, bool lock_flush_tlb) @@ -5088,7 +5088,7 @@ slot_handle_level_range(struct kvm *kvm, struct kvm_memory_slot *memslot, return flush; } -static bool +static __always_inline bool slot_handle_level(struct kvm *kvm, struct kvm_memory_slot *memslot, slot_level_handler fn, int start_level, int end_level, bool lock_flush_tlb) @@ -5099,7 +5099,7 @@ slot_handle_level(struct kvm *kvm, struct kvm_memory_slot *memslot, lock_flush_tlb); } -static bool +static __always_inline bool slot_handle_all_level(struct kvm *kvm, struct kvm_memory_slot *memslot, slot_level_handler fn, bool lock_flush_tlb) { @@ -5107,7 +5107,7 @@ slot_handle_all_level(struct kvm *kvm, struct kvm_memory_slot *memslot, PT_MAX_HUGEPAGE_LEVEL, lock_flush_tlb); } -static bool +static __always_inline bool slot_handle_large_level(struct kvm *kvm, struct kvm_memory_slot *memslot, slot_level_handler fn, bool lock_flush_tlb) { @@ -5115,7 +5115,7 @@ slot_handle_large_level(struct kvm *kvm, struct kvm_memory_slot *memslot, PT_MAX_HUGEPAGE_LEVEL, lock_flush_tlb); } -static bool +static __always_inline bool slot_handle_leaf(struct kvm *kvm, struct kvm_memory_slot *memslot, slot_level_handler fn, bool lock_flush_tlb) { -- cgit v1.2.3-55-g7522 From 206587a9fb764d71f035dc7f6d3b6488f5d5b304 Mon Sep 17 00:00:00 2001 From: KarimAllah Ahmed Date: Sat, 10 Feb 2018 23:39:25 +0000 Subject: X86/nVMX: Properly set spec_ctrl and pred_cmd before merging MSRs These two variables should check whether SPEC_CTRL and PRED_CMD are supposed to be passed through to L2 guests or not. While msr_write_intercepted_l01 would return 'true' if it is not passed through. So just invert the result of msr_write_intercepted_l01 to implement the correct semantics. Signed-off-by: KarimAllah Ahmed Signed-off-by: David Woodhouse Reviewed-by: Jim Mattson Acked-by: Paolo Bonzini Cc: Andy Lutomirski Cc: Arjan van de Ven Cc: Borislav Petkov Cc: Dan Williams Cc: Dave Hansen Cc: David Woodhouse Cc: Greg Kroah-Hartman Cc: Josh Poimboeuf Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Radim Krčmář Cc: Thomas Gleixner Cc: arjan.van.de.ven@intel.com Cc: dave.hansen@intel.com Cc: kvm@vger.kernel.org Cc: sironi@amazon.de Fixes: 086e7d4118cc ("KVM: VMX: Allow direct access to MSR_IA32_SPEC_CTRL") Link: http://lkml.kernel.org/r/1518305967-31356-5-git-send-email-dwmw@amazon.co.uk Signed-off-by: Ingo Molnar --- arch/x86/kvm/vmx.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch') diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index bee4c49f6dd0..599179bfb87f 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -10219,8 +10219,8 @@ static inline bool nested_vmx_merge_msr_bitmap(struct kvm_vcpu *vcpu, * updated to reflect this when L1 (or its L2s) actually write to * the MSR. */ - bool pred_cmd = msr_write_intercepted_l01(vcpu, MSR_IA32_PRED_CMD); - bool spec_ctrl = msr_write_intercepted_l01(vcpu, MSR_IA32_SPEC_CTRL); + bool pred_cmd = !msr_write_intercepted_l01(vcpu, MSR_IA32_PRED_CMD); + bool spec_ctrl = !msr_write_intercepted_l01(vcpu, MSR_IA32_SPEC_CTRL); if (!nested_cpu_has_virt_x2apic_mode(vmcs12) && !pred_cmd && !spec_ctrl) -- cgit v1.2.3-55-g7522 From 3712caeb14dcb33fb4d5114f14c0beef10aca101 Mon Sep 17 00:00:00 2001 From: KarimAllah Ahmed Date: Sat, 10 Feb 2018 23:39:26 +0000 Subject: KVM/nVMX: Set the CPU_BASED_USE_MSR_BITMAPS if we have a valid L02 MSR bitmap We either clear the CPU_BASED_USE_MSR_BITMAPS and end up intercepting all MSR accesses or create a valid L02 MSR bitmap and use that. This decision has to be made every time we evaluate whether we are going to generate the L02 MSR bitmap. Before commit: d28b387fb74d ("KVM/VMX: Allow direct access to MSR_IA32_SPEC_CTRL") ... this was probably OK since the decision was always identical. This is no longer the case now since the MSR bitmap might actually change once we decide to not intercept SPEC_CTRL and PRED_CMD. Signed-off-by: KarimAllah Ahmed Signed-off-by: David Woodhouse Acked-by: Paolo Bonzini Cc: Andy Lutomirski Cc: Arjan van de Ven Cc: Borislav Petkov Cc: Dan Williams Cc: Dave Hansen Cc: David Woodhouse Cc: Greg Kroah-Hartman Cc: Josh Poimboeuf Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Radim Krčmář Cc: Thomas Gleixner Cc: arjan.van.de.ven@intel.com Cc: dave.hansen@intel.com Cc: jmattson@google.com Cc: kvm@vger.kernel.org Cc: sironi@amazon.de Link: http://lkml.kernel.org/r/1518305967-31356-6-git-send-email-dwmw@amazon.co.uk Signed-off-by: Ingo Molnar --- arch/x86/kvm/vmx.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 599179bfb87f..91e3539cba02 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -10130,7 +10130,8 @@ static void nested_get_vmcs12_pages(struct kvm_vcpu *vcpu, if (cpu_has_vmx_msr_bitmap() && nested_cpu_has(vmcs12, CPU_BASED_USE_MSR_BITMAPS) && nested_vmx_merge_msr_bitmap(vcpu, vmcs12)) - ; + vmcs_set_bits(CPU_BASED_VM_EXEC_CONTROL, + CPU_BASED_USE_MSR_BITMAPS); else vmcs_clear_bits(CPU_BASED_VM_EXEC_CONTROL, CPU_BASED_USE_MSR_BITMAPS); -- cgit v1.2.3-55-g7522 From 21e433bdb95bdf3aa48226fd3d33af608437f293 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Tue, 13 Feb 2018 09:03:08 +0100 Subject: x86/speculation: Clean up various Spectre related details Harmonize all the Spectre messages so that a: dmesg | grep -i spectre ... gives us most Spectre related kernel boot messages. Also fix a few other details: - clarify a comment about firmware speculation control - s/KPTI/PTI - remove various line-breaks that made the code uglier Acked-by: David Woodhouse Cc: Andy Lutomirski Cc: Arjan van de Ven Cc: Borislav Petkov Cc: Dan Williams Cc: Dave Hansen Cc: David Woodhouse Cc: Greg Kroah-Hartman Cc: Josh Poimboeuf Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/bugs.c | 28 +++++++++++----------------- 1 file changed, 11 insertions(+), 17 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 61152aa53377..4acf16a76d1e 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -162,8 +162,7 @@ static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void) if (cmdline_find_option_bool(boot_command_line, "nospectre_v2")) return SPECTRE_V2_CMD_NONE; else { - ret = cmdline_find_option(boot_command_line, "spectre_v2", arg, - sizeof(arg)); + ret = cmdline_find_option(boot_command_line, "spectre_v2", arg, sizeof(arg)); if (ret < 0) return SPECTRE_V2_CMD_AUTO; @@ -175,8 +174,7 @@ static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void) } if (i >= ARRAY_SIZE(mitigation_options)) { - pr_err("unknown option (%s). Switching to AUTO select\n", - mitigation_options[i].option); + pr_err("unknown option (%s). Switching to AUTO select\n", mitigation_options[i].option); return SPECTRE_V2_CMD_AUTO; } } @@ -185,8 +183,7 @@ static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void) cmd == SPECTRE_V2_CMD_RETPOLINE_AMD || cmd == SPECTRE_V2_CMD_RETPOLINE_GENERIC) && !IS_ENABLED(CONFIG_RETPOLINE)) { - pr_err("%s selected but not compiled in. Switching to AUTO select\n", - mitigation_options[i].option); + pr_err("%s selected but not compiled in. Switching to AUTO select\n", mitigation_options[i].option); return SPECTRE_V2_CMD_AUTO; } @@ -256,14 +253,14 @@ static void __init spectre_v2_select_mitigation(void) goto retpoline_auto; break; } - pr_err("kernel not compiled with retpoline; no mitigation available!"); + pr_err("Spectre mitigation: kernel not compiled with retpoline; no mitigation available!"); return; retpoline_auto: if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) { retpoline_amd: if (!boot_cpu_has(X86_FEATURE_LFENCE_RDTSC)) { - pr_err("LFENCE not serializing. Switching to generic retpoline\n"); + pr_err("Spectre mitigation: LFENCE not serializing, switching to generic retpoline\n"); goto retpoline_generic; } mode = retp_compiler() ? SPECTRE_V2_RETPOLINE_AMD : @@ -281,7 +278,7 @@ retpoline_auto: pr_info("%s\n", spectre_v2_strings[mode]); /* - * If neither SMEP or KPTI are available, there is a risk of + * If neither SMEP nor PTI are available, there is a risk of * hitting userspace addresses in the RSB after a context switch * from a shallow call stack to a deeper one. To prevent this fill * the entire RSB, even when using IBRS. @@ -295,21 +292,20 @@ retpoline_auto: if ((!boot_cpu_has(X86_FEATURE_PTI) && !boot_cpu_has(X86_FEATURE_SMEP)) || is_skylake_era()) { setup_force_cpu_cap(X86_FEATURE_RSB_CTXSW); - pr_info("Filling RSB on context switch\n"); + pr_info("Spectre v2 mitigation: Filling RSB on context switch\n"); } /* Initialize Indirect Branch Prediction Barrier if supported */ if (boot_cpu_has(X86_FEATURE_IBPB)) { setup_force_cpu_cap(X86_FEATURE_USE_IBPB); - pr_info("Enabling Indirect Branch Prediction Barrier\n"); + pr_info("Spectre v2 mitigation: Enabling Indirect Branch Prediction Barrier\n"); } } #undef pr_fmt #ifdef CONFIG_SYSFS -ssize_t cpu_show_meltdown(struct device *dev, - struct device_attribute *attr, char *buf) +ssize_t cpu_show_meltdown(struct device *dev, struct device_attribute *attr, char *buf) { if (!boot_cpu_has_bug(X86_BUG_CPU_MELTDOWN)) return sprintf(buf, "Not affected\n"); @@ -318,16 +314,14 @@ ssize_t cpu_show_meltdown(struct device *dev, return sprintf(buf, "Vulnerable\n"); } -ssize_t cpu_show_spectre_v1(struct device *dev, - struct device_attribute *attr, char *buf) +ssize_t cpu_show_spectre_v1(struct device *dev, struct device_attribute *attr, char *buf) { if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V1)) return sprintf(buf, "Not affected\n"); return sprintf(buf, "Mitigation: __user pointer sanitization\n"); } -ssize_t cpu_show_spectre_v2(struct device *dev, - struct device_attribute *attr, char *buf) +ssize_t cpu_show_spectre_v2(struct device *dev, struct device_attribute *attr, char *buf) { if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2)) return sprintf(buf, "Not affected\n"); -- cgit v1.2.3-55-g7522 From 2e3f0098bc45f710a2f4cbcc94b80a1fae7a99a1 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Sun, 11 Feb 2018 11:49:42 +0100 Subject: x86/entry/64: Merge SAVE_C_REGS and SAVE_EXTRA_REGS, remove unused extensions All current code paths call SAVE_C_REGS and then immediately SAVE_EXTRA_REGS. Therefore, merge these two macros and order the MOV sequeneces properly. While at it, remove the macros to save all except specific registers, as these macros have been unused for a long time. Suggested-by: Linus Torvalds Signed-off-by: Dominik Brodowski Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Josh Poimboeuf Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: dan.j.williams@intel.com Link: http://lkml.kernel.org/r/20180211104949.12992-2-linux@dominikbrodowski.net Signed-off-by: Ingo Molnar --- arch/x86/entry/calling.h | 57 +++++++++++++---------------------------------- arch/x86/entry/entry_64.S | 12 ++++------ 2 files changed, 19 insertions(+), 50 deletions(-) (limited to 'arch') diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h index f4b129d4af42..8907a6593b42 100644 --- a/arch/x86/entry/calling.h +++ b/arch/x86/entry/calling.h @@ -101,49 +101,22 @@ For 32-bit we have the following conventions - kernel is built with addq $-(15*8), %rsp .endm - .macro SAVE_C_REGS_HELPER offset=0 rax=1 rcx=1 r8910=1 r11=1 - .if \r11 - movq %r11, 6*8+\offset(%rsp) - .endif - .if \r8910 - movq %r10, 7*8+\offset(%rsp) - movq %r9, 8*8+\offset(%rsp) - movq %r8, 9*8+\offset(%rsp) - .endif - .if \rax - movq %rax, 10*8+\offset(%rsp) - .endif - .if \rcx - movq %rcx, 11*8+\offset(%rsp) - .endif - movq %rdx, 12*8+\offset(%rsp) - movq %rsi, 13*8+\offset(%rsp) + .macro SAVE_REGS offset=0 movq %rdi, 14*8+\offset(%rsp) - UNWIND_HINT_REGS offset=\offset extra=0 - .endm - .macro SAVE_C_REGS offset=0 - SAVE_C_REGS_HELPER \offset, 1, 1, 1, 1 - .endm - .macro SAVE_C_REGS_EXCEPT_RAX_RCX offset=0 - SAVE_C_REGS_HELPER \offset, 0, 0, 1, 1 - .endm - .macro SAVE_C_REGS_EXCEPT_R891011 - SAVE_C_REGS_HELPER 0, 1, 1, 0, 0 - .endm - .macro SAVE_C_REGS_EXCEPT_RCX_R891011 - SAVE_C_REGS_HELPER 0, 1, 0, 0, 0 - .endm - .macro SAVE_C_REGS_EXCEPT_RAX_RCX_R11 - SAVE_C_REGS_HELPER 0, 0, 0, 1, 0 - .endm - - .macro SAVE_EXTRA_REGS offset=0 - movq %r15, 0*8+\offset(%rsp) - movq %r14, 1*8+\offset(%rsp) - movq %r13, 2*8+\offset(%rsp) - movq %r12, 3*8+\offset(%rsp) - movq %rbp, 4*8+\offset(%rsp) + movq %rsi, 13*8+\offset(%rsp) + movq %rdx, 12*8+\offset(%rsp) + movq %rcx, 11*8+\offset(%rsp) + movq %rax, 10*8+\offset(%rsp) + movq %r8, 9*8+\offset(%rsp) + movq %r9, 8*8+\offset(%rsp) + movq %r10, 7*8+\offset(%rsp) + movq %r11, 6*8+\offset(%rsp) movq %rbx, 5*8+\offset(%rsp) + movq %rbp, 4*8+\offset(%rsp) + movq %r12, 3*8+\offset(%rsp) + movq %r13, 2*8+\offset(%rsp) + movq %r14, 1*8+\offset(%rsp) + movq %r15, 0*8+\offset(%rsp) UNWIND_HINT_REGS offset=\offset .endm @@ -197,7 +170,7 @@ For 32-bit we have the following conventions - kernel is built with * is just setting the LSB, which makes it an invalid stack address and is also * a signal to the unwinder that it's a pt_regs pointer in disguise. * - * NOTE: This macro must be used *after* SAVE_EXTRA_REGS because it corrupts + * NOTE: This macro must be used *after* SAVE_REGS because it corrupts * the original rbp. */ .macro ENCODE_FRAME_POINTER ptregs_offset=0 diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 932a445febee..1a6fc0136225 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -573,8 +573,7 @@ END(irq_entries_start) 1: ALLOC_PT_GPREGS_ON_STACK - SAVE_C_REGS - SAVE_EXTRA_REGS + SAVE_REGS CLEAR_REGS_NOSPEC ENCODE_FRAME_POINTER @@ -1132,8 +1131,7 @@ ENTRY(xen_failsafe_callback) UNWIND_HINT_IRET_REGS pushq $-1 /* orig_ax = -1 => not a system call */ ALLOC_PT_GPREGS_ON_STACK - SAVE_C_REGS - SAVE_EXTRA_REGS + SAVE_REGS CLEAR_REGS_NOSPEC ENCODE_FRAME_POINTER jmp error_exit @@ -1178,8 +1176,7 @@ idtentry machine_check do_mce has_error_code=0 paranoid=1 ENTRY(paranoid_entry) UNWIND_HINT_FUNC cld - SAVE_C_REGS 8 - SAVE_EXTRA_REGS 8 + SAVE_REGS 8 CLEAR_REGS_NOSPEC ENCODE_FRAME_POINTER 8 movl $1, %ebx @@ -1231,8 +1228,7 @@ END(paranoid_exit) ENTRY(error_entry) UNWIND_HINT_FUNC cld - SAVE_C_REGS 8 - SAVE_EXTRA_REGS 8 + SAVE_REGS 8 CLEAR_REGS_NOSPEC ENCODE_FRAME_POINTER 8 testb $3, CS+8(%rsp) -- cgit v1.2.3-55-g7522 From 502af0d70843c2a9405d7ba1f79b4b0305aaf5f5 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Sun, 11 Feb 2018 11:49:43 +0100 Subject: x86/entry/64: Merge the POP_C_REGS and POP_EXTRA_REGS macros into a single POP_REGS macro The two special, opencoded cases for POP_C_REGS can be handled by ASM macros. Signed-off-by: Dominik Brodowski Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Josh Poimboeuf Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: dan.j.williams@intel.com Link: http://lkml.kernel.org/r/20180211104949.12992-3-linux@dominikbrodowski.net Signed-off-by: Ingo Molnar --- arch/x86/entry/calling.h | 15 +++++++++++---- arch/x86/entry/entry_64.S | 26 ++++---------------------- 2 files changed, 15 insertions(+), 26 deletions(-) (limited to 'arch') diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h index 8907a6593b42..3bda31736a7b 100644 --- a/arch/x86/entry/calling.h +++ b/arch/x86/entry/calling.h @@ -139,25 +139,32 @@ For 32-bit we have the following conventions - kernel is built with xorq %r15, %r15 .endm - .macro POP_EXTRA_REGS + .macro POP_REGS pop_rdi=1 skip_r11rcx=0 popq %r15 popq %r14 popq %r13 popq %r12 popq %rbp popq %rbx - .endm - - .macro POP_C_REGS + .if \skip_r11rcx + popq %rsi + .else popq %r11 + .endif popq %r10 popq %r9 popq %r8 popq %rax + .if \skip_r11rcx + popq %rsi + .else popq %rcx + .endif popq %rdx popq %rsi + .if \pop_rdi popq %rdi + .endif .endm .macro icebp diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 1a6fc0136225..7351c91fb7df 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -334,15 +334,7 @@ GLOBAL(entry_SYSCALL_64_after_hwframe) syscall_return_via_sysret: /* rcx and r11 are already restored (see code above) */ UNWIND_HINT_EMPTY - POP_EXTRA_REGS - popq %rsi /* skip r11 */ - popq %r10 - popq %r9 - popq %r8 - popq %rax - popq %rsi /* skip rcx */ - popq %rdx - popq %rsi + POP_REGS pop_rdi=0 skip_r11rcx=1 /* * Now all regs are restored except RSP and RDI. @@ -635,15 +627,7 @@ GLOBAL(swapgs_restore_regs_and_return_to_usermode) ud2 1: #endif - POP_EXTRA_REGS - popq %r11 - popq %r10 - popq %r9 - popq %r8 - popq %rax - popq %rcx - popq %rdx - popq %rsi + POP_REGS pop_rdi=0 /* * The stack is now user RDI, orig_ax, RIP, CS, EFLAGS, RSP, SS. @@ -701,8 +685,7 @@ GLOBAL(restore_regs_and_return_to_kernel) ud2 1: #endif - POP_EXTRA_REGS - POP_C_REGS + POP_REGS addq $8, %rsp /* skip regs->orig_ax */ INTERRUPT_RETURN @@ -1661,8 +1644,7 @@ end_repeat_nmi: nmi_swapgs: SWAPGS_UNSAFE_STACK nmi_restore: - POP_EXTRA_REGS - POP_C_REGS + POP_REGS /* * Skip orig_ax and the "outermost" frame to point RSP at the "iret" -- cgit v1.2.3-55-g7522 From f7bafa2b05ef25eda1d9179fd930b0330cf2b7d1 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Sun, 11 Feb 2018 11:49:44 +0100 Subject: x86/entry/64: Interleave XOR register clearing with PUSH instructions Same as is done for syscalls, interleave XOR with PUSH instructions for exceptions/interrupts, in order to minimize the cost of the additional instructions required for register clearing. Signed-off-by: Dominik Brodowski Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Josh Poimboeuf Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: dan.j.williams@intel.com Link: http://lkml.kernel.org/r/20180211104949.12992-4-linux@dominikbrodowski.net Signed-off-by: Ingo Molnar --- arch/x86/entry/calling.h | 40 +++++++++++++++++++--------------------- arch/x86/entry/entry_64.S | 30 +++++++++++++++++++++--------- 2 files changed, 40 insertions(+), 30 deletions(-) (limited to 'arch') diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h index 3bda31736a7b..a05cbb81268d 100644 --- a/arch/x86/entry/calling.h +++ b/arch/x86/entry/calling.h @@ -101,44 +101,42 @@ For 32-bit we have the following conventions - kernel is built with addq $-(15*8), %rsp .endm - .macro SAVE_REGS offset=0 + .macro SAVE_AND_CLEAR_REGS offset=0 + /* + * Save registers and sanitize registers of values that a + * speculation attack might otherwise want to exploit. The + * lower registers are likely clobbered well before they + * could be put to use in a speculative execution gadget. + * Interleave XOR with PUSH for better uop scheduling: + */ movq %rdi, 14*8+\offset(%rsp) movq %rsi, 13*8+\offset(%rsp) movq %rdx, 12*8+\offset(%rsp) movq %rcx, 11*8+\offset(%rsp) movq %rax, 10*8+\offset(%rsp) movq %r8, 9*8+\offset(%rsp) + xorq %r8, %r8 /* nospec r8 */ movq %r9, 8*8+\offset(%rsp) + xorq %r9, %r9 /* nospec r9 */ movq %r10, 7*8+\offset(%rsp) + xorq %r10, %r10 /* nospec r10 */ movq %r11, 6*8+\offset(%rsp) + xorq %r11, %r11 /* nospec r11 */ movq %rbx, 5*8+\offset(%rsp) + xorl %ebx, %ebx /* nospec rbx */ movq %rbp, 4*8+\offset(%rsp) + xorl %ebp, %ebp /* nospec rbp */ movq %r12, 3*8+\offset(%rsp) + xorq %r12, %r12 /* nospec r12 */ movq %r13, 2*8+\offset(%rsp) + xorq %r13, %r13 /* nospec r13 */ movq %r14, 1*8+\offset(%rsp) + xorq %r14, %r14 /* nospec r14 */ movq %r15, 0*8+\offset(%rsp) + xorq %r15, %r15 /* nospec r15 */ UNWIND_HINT_REGS offset=\offset .endm - /* - * Sanitize registers of values that a speculation attack - * might otherwise want to exploit. The lower registers are - * likely clobbered well before they could be put to use in - * a speculative execution gadget: - */ - .macro CLEAR_REGS_NOSPEC - xorl %ebp, %ebp - xorl %ebx, %ebx - xorq %r8, %r8 - xorq %r9, %r9 - xorq %r10, %r10 - xorq %r11, %r11 - xorq %r12, %r12 - xorq %r13, %r13 - xorq %r14, %r14 - xorq %r15, %r15 - .endm - .macro POP_REGS pop_rdi=1 skip_r11rcx=0 popq %r15 popq %r14 @@ -177,7 +175,7 @@ For 32-bit we have the following conventions - kernel is built with * is just setting the LSB, which makes it an invalid stack address and is also * a signal to the unwinder that it's a pt_regs pointer in disguise. * - * NOTE: This macro must be used *after* SAVE_REGS because it corrupts + * NOTE: This macro must be used *after* SAVE_AND_CLEAR_REGS because it corrupts * the original rbp. */ .macro ENCODE_FRAME_POINTER ptregs_offset=0 diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 7351c91fb7df..07692b44800d 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -565,8 +565,7 @@ END(irq_entries_start) 1: ALLOC_PT_GPREGS_ON_STACK - SAVE_REGS - CLEAR_REGS_NOSPEC + SAVE_AND_CLEAR_REGS ENCODE_FRAME_POINTER testb $3, CS(%rsp) @@ -1114,8 +1113,7 @@ ENTRY(xen_failsafe_callback) UNWIND_HINT_IRET_REGS pushq $-1 /* orig_ax = -1 => not a system call */ ALLOC_PT_GPREGS_ON_STACK - SAVE_REGS - CLEAR_REGS_NOSPEC + SAVE_AND_CLEAR_REGS ENCODE_FRAME_POINTER jmp error_exit END(xen_failsafe_callback) @@ -1159,8 +1157,7 @@ idtentry machine_check do_mce has_error_code=0 paranoid=1 ENTRY(paranoid_entry) UNWIND_HINT_FUNC cld - SAVE_REGS 8 - CLEAR_REGS_NOSPEC + SAVE_AND_CLEAR_REGS 8 ENCODE_FRAME_POINTER 8 movl $1, %ebx movl $MSR_GS_BASE, %ecx @@ -1211,8 +1208,7 @@ END(paranoid_exit) ENTRY(error_entry) UNWIND_HINT_FUNC cld - SAVE_REGS 8 - CLEAR_REGS_NOSPEC + SAVE_AND_CLEAR_REGS 8 ENCODE_FRAME_POINTER 8 testb $3, CS+8(%rsp) jz .Lerror_kernelspace @@ -1399,18 +1395,34 @@ ENTRY(nmi) pushq (%rdx) /* pt_regs->dx */ pushq %rcx /* pt_regs->cx */ pushq %rax /* pt_regs->ax */ + /* + * Sanitize registers of values that a speculation attack + * might otherwise want to exploit. The lower registers are + * likely clobbered well before they could be put to use in + * a speculative execution gadget. Interleave XOR with PUSH + * for better uop scheduling: + */ pushq %r8 /* pt_regs->r8 */ + xorq %r8, %r8 /* nospec r8 */ pushq %r9 /* pt_regs->r9 */ + xorq %r9, %r9 /* nospec r9 */ pushq %r10 /* pt_regs->r10 */ + xorq %r10, %r10 /* nospec r10 */ pushq %r11 /* pt_regs->r11 */ + xorq %r11, %r11 /* nospec r11*/ pushq %rbx /* pt_regs->rbx */ + xorl %ebx, %ebx /* nospec rbx*/ pushq %rbp /* pt_regs->rbp */ + xorl %ebp, %ebp /* nospec rbp*/ pushq %r12 /* pt_regs->r12 */ + xorq %r12, %r12 /* nospec r12*/ pushq %r13 /* pt_regs->r13 */ + xorq %r13, %r13 /* nospec r13*/ pushq %r14 /* pt_regs->r14 */ + xorq %r14, %r14 /* nospec r14*/ pushq %r15 /* pt_regs->r15 */ + xorq %r15, %r15 /* nospec r15*/ UNWIND_HINT_REGS - CLEAR_REGS_NOSPEC ENCODE_FRAME_POINTER /* -- cgit v1.2.3-55-g7522 From 3f01daecd545e818098d84fd1ad43e19a508d705 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Sun, 11 Feb 2018 11:49:45 +0100 Subject: x86/entry/64: Introduce the PUSH_AND_CLEAN_REGS macro Those instances where ALLOC_PT_GPREGS_ON_STACK is called just before SAVE_AND_CLEAR_REGS can trivially be replaced by PUSH_AND_CLEAN_REGS. This macro uses PUSH instead of MOV and should therefore be faster, at least on newer CPUs. Suggested-by: Linus Torvalds Signed-off-by: Dominik Brodowski Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Josh Poimboeuf Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: dan.j.williams@intel.com Link: http://lkml.kernel.org/r/20180211104949.12992-5-linux@dominikbrodowski.net Signed-off-by: Ingo Molnar --- arch/x86/entry/calling.h | 36 ++++++++++++++++++++++++++++++++++++ arch/x86/entry/entry_64.S | 6 ++---- 2 files changed, 38 insertions(+), 4 deletions(-) (limited to 'arch') diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h index a05cbb81268d..57b1b87a04f0 100644 --- a/arch/x86/entry/calling.h +++ b/arch/x86/entry/calling.h @@ -137,6 +137,42 @@ For 32-bit we have the following conventions - kernel is built with UNWIND_HINT_REGS offset=\offset .endm + .macro PUSH_AND_CLEAR_REGS + /* + * Push registers and sanitize registers of values that a + * speculation attack might otherwise want to exploit. The + * lower registers are likely clobbered well before they + * could be put to use in a speculative execution gadget. + * Interleave XOR with PUSH for better uop scheduling: + */ + pushq %rdi /* pt_regs->di */ + pushq %rsi /* pt_regs->si */ + pushq %rdx /* pt_regs->dx */ + pushq %rcx /* pt_regs->cx */ + pushq %rax /* pt_regs->ax */ + pushq %r8 /* pt_regs->r8 */ + xorq %r8, %r8 /* nospec r8 */ + pushq %r9 /* pt_regs->r9 */ + xorq %r9, %r9 /* nospec r9 */ + pushq %r10 /* pt_regs->r10 */ + xorq %r10, %r10 /* nospec r10 */ + pushq %r11 /* pt_regs->r11 */ + xorq %r11, %r11 /* nospec r11*/ + pushq %rbx /* pt_regs->rbx */ + xorl %ebx, %ebx /* nospec rbx*/ + pushq %rbp /* pt_regs->rbp */ + xorl %ebp, %ebp /* nospec rbp*/ + pushq %r12 /* pt_regs->r12 */ + xorq %r12, %r12 /* nospec r12*/ + pushq %r13 /* pt_regs->r13 */ + xorq %r13, %r13 /* nospec r13*/ + pushq %r14 /* pt_regs->r14 */ + xorq %r14, %r14 /* nospec r14*/ + pushq %r15 /* pt_regs->r15 */ + xorq %r15, %r15 /* nospec r15*/ + UNWIND_HINT_REGS + .endm + .macro POP_REGS pop_rdi=1 skip_r11rcx=0 popq %r15 popq %r14 diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 07692b44800d..cf4a9ae558f3 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -564,8 +564,7 @@ END(irq_entries_start) call switch_to_thread_stack 1: - ALLOC_PT_GPREGS_ON_STACK - SAVE_AND_CLEAR_REGS + PUSH_AND_CLEAR_REGS ENCODE_FRAME_POINTER testb $3, CS(%rsp) @@ -1112,8 +1111,7 @@ ENTRY(xen_failsafe_callback) addq $0x30, %rsp UNWIND_HINT_IRET_REGS pushq $-1 /* orig_ax = -1 => not a system call */ - ALLOC_PT_GPREGS_ON_STACK - SAVE_AND_CLEAR_REGS + PUSH_AND_CLEAR_REGS ENCODE_FRAME_POINTER jmp error_exit END(xen_failsafe_callback) -- cgit v1.2.3-55-g7522 From 30907fd13bb593202574bb20af58d67c70a1ee14 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Sun, 11 Feb 2018 11:49:46 +0100 Subject: x86/entry/64: Use PUSH_AND_CLEAN_REGS in more cases entry_SYSCALL_64_after_hwframe() and nmi() can be converted to use PUSH_AND_CLEAN_REGS instead of opencoded variants thereof. Due to the interleaving, the additional XOR-based clearing of R8 and R9 in entry_SYSCALL_64_after_hwframe() should not have any noticeable negative implications. Suggested-by: Linus Torvalds Signed-off-by: Dominik Brodowski Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Josh Poimboeuf Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: dan.j.williams@intel.com Link: http://lkml.kernel.org/r/20180211104949.12992-6-linux@dominikbrodowski.net Signed-off-by: Ingo Molnar --- arch/x86/entry/calling.h | 6 ++--- arch/x86/entry/entry_64.S | 65 +++-------------------------------------------- 2 files changed, 6 insertions(+), 65 deletions(-) (limited to 'arch') diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h index 57b1b87a04f0..d6a97e2945ee 100644 --- a/arch/x86/entry/calling.h +++ b/arch/x86/entry/calling.h @@ -137,7 +137,7 @@ For 32-bit we have the following conventions - kernel is built with UNWIND_HINT_REGS offset=\offset .endm - .macro PUSH_AND_CLEAR_REGS + .macro PUSH_AND_CLEAR_REGS rdx=%rdx rax=%rax /* * Push registers and sanitize registers of values that a * speculation attack might otherwise want to exploit. The @@ -147,9 +147,9 @@ For 32-bit we have the following conventions - kernel is built with */ pushq %rdi /* pt_regs->di */ pushq %rsi /* pt_regs->si */ - pushq %rdx /* pt_regs->dx */ + pushq \rdx /* pt_regs->dx */ pushq %rcx /* pt_regs->cx */ - pushq %rax /* pt_regs->ax */ + pushq \rax /* pt_regs->ax */ pushq %r8 /* pt_regs->r8 */ xorq %r8, %r8 /* nospec r8 */ pushq %r9 /* pt_regs->r9 */ diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index cf4a9ae558f3..b06a4b5864ba 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -227,35 +227,8 @@ ENTRY(entry_SYSCALL_64) pushq %rcx /* pt_regs->ip */ GLOBAL(entry_SYSCALL_64_after_hwframe) pushq %rax /* pt_regs->orig_ax */ - pushq %rdi /* pt_regs->di */ - pushq %rsi /* pt_regs->si */ - pushq %rdx /* pt_regs->dx */ - pushq %rcx /* pt_regs->cx */ - pushq $-ENOSYS /* pt_regs->ax */ - pushq %r8 /* pt_regs->r8 */ - pushq %r9 /* pt_regs->r9 */ - pushq %r10 /* pt_regs->r10 */ - /* - * Clear extra registers that a speculation attack might - * otherwise want to exploit. Interleave XOR with PUSH - * for better uop scheduling: - */ - xorq %r10, %r10 /* nospec r10 */ - pushq %r11 /* pt_regs->r11 */ - xorq %r11, %r11 /* nospec r11 */ - pushq %rbx /* pt_regs->rbx */ - xorl %ebx, %ebx /* nospec rbx */ - pushq %rbp /* pt_regs->rbp */ - xorl %ebp, %ebp /* nospec rbp */ - pushq %r12 /* pt_regs->r12 */ - xorq %r12, %r12 /* nospec r12 */ - pushq %r13 /* pt_regs->r13 */ - xorq %r13, %r13 /* nospec r13 */ - pushq %r14 /* pt_regs->r14 */ - xorq %r14, %r14 /* nospec r14 */ - pushq %r15 /* pt_regs->r15 */ - xorq %r15, %r15 /* nospec r15 */ - UNWIND_HINT_REGS + + PUSH_AND_CLEAR_REGS rax=$-ENOSYS TRACE_IRQS_OFF @@ -1388,39 +1361,7 @@ ENTRY(nmi) pushq 1*8(%rdx) /* pt_regs->rip */ UNWIND_HINT_IRET_REGS pushq $-1 /* pt_regs->orig_ax */ - pushq %rdi /* pt_regs->di */ - pushq %rsi /* pt_regs->si */ - pushq (%rdx) /* pt_regs->dx */ - pushq %rcx /* pt_regs->cx */ - pushq %rax /* pt_regs->ax */ - /* - * Sanitize registers of values that a speculation attack - * might otherwise want to exploit. The lower registers are - * likely clobbered well before they could be put to use in - * a speculative execution gadget. Interleave XOR with PUSH - * for better uop scheduling: - */ - pushq %r8 /* pt_regs->r8 */ - xorq %r8, %r8 /* nospec r8 */ - pushq %r9 /* pt_regs->r9 */ - xorq %r9, %r9 /* nospec r9 */ - pushq %r10 /* pt_regs->r10 */ - xorq %r10, %r10 /* nospec r10 */ - pushq %r11 /* pt_regs->r11 */ - xorq %r11, %r11 /* nospec r11*/ - pushq %rbx /* pt_regs->rbx */ - xorl %ebx, %ebx /* nospec rbx*/ - pushq %rbp /* pt_regs->rbp */ - xorl %ebp, %ebp /* nospec rbp*/ - pushq %r12 /* pt_regs->r12 */ - xorq %r12, %r12 /* nospec r12*/ - pushq %r13 /* pt_regs->r13 */ - xorq %r13, %r13 /* nospec r13*/ - pushq %r14 /* pt_regs->r14 */ - xorq %r14, %r14 /* nospec r14*/ - pushq %r15 /* pt_regs->r15 */ - xorq %r15, %r15 /* nospec r15*/ - UNWIND_HINT_REGS + PUSH_AND_CLEAR_REGS rdx=(%rdx) ENCODE_FRAME_POINTER /* -- cgit v1.2.3-55-g7522 From dde3036d62ba3375840b10ab9ec0d568fd773b07 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Sun, 11 Feb 2018 11:49:47 +0100 Subject: x86/entry/64: Get rid of the ALLOC_PT_GPREGS_ON_STACK and SAVE_AND_CLEAR_REGS macros Previously, error_entry() and paranoid_entry() saved the GP registers onto stack space previously allocated by its callers. Combine these two steps in the callers, and use the generic PUSH_AND_CLEAR_REGS macro for that. This adds a significant amount ot text size. However, Ingo Molnar points out that: "these numbers also _very_ significantly over-represent the extra footprint. The assumptions that resulted in us compressing the IRQ entry code have changed very significantly with the new x86 IRQ allocation code we introduced in the last year: - IRQ vectors are usually populated in tightly clustered groups. With our new vector allocator code the typical per CPU allocation percentage on x86 systems is ~3 device vectors and ~10 fixed vectors out of ~220 vectors - i.e. a very low ~6% utilization (!). [...] The days where we allocated a lot of vectors on every CPU and the compression of the IRQ entry code text mattered are over. - Another issue is that only a small minority of vectors is frequent enough to actually matter to cache utilization in practice: 3-4 key IPIs and 1-2 device IRQs at most - and those vectors tend to be tightly clustered as well into about two groups, and are probably already on 2-3 cache lines in practice. For the common case of 'cache cold' IRQs it's the depth of the call chain and the fragmentation of the resulting I$ that should be the main performance limit - not the overall size of it. - The CPU side cost of IRQ delivery is still very expensive even in the best, most cached case, as in 'over a thousand cycles'. So much stuff is done that maybe contemporary x86 IRQ entry microcode already prefetches the IDT entry and its expected call target address."[*] [*] http://lkml.kernel.org/r/20180208094710.qnjixhm6hybebdv7@gmail.com The "testb $3, CS(%rsp)" instruction in the idtentry macro does not need modification. Previously, %rsp was manually decreased by 15*8; with this patch, %rsp is decreased by 15 pushq instructions. [jpoimboe@redhat.com: unwind hint improvements] Suggested-by: Linus Torvalds Signed-off-by: Dominik Brodowski Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Josh Poimboeuf Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: dan.j.williams@intel.com Link: http://lkml.kernel.org/r/20180211104949.12992-7-linux@dominikbrodowski.net Signed-off-by: Ingo Molnar --- arch/x86/entry/calling.h | 42 +----------------------------------------- arch/x86/entry/entry_64.S | 20 +++++++++----------- 2 files changed, 10 insertions(+), 52 deletions(-) (limited to 'arch') diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h index d6a97e2945ee..59675010c9a0 100644 --- a/arch/x86/entry/calling.h +++ b/arch/x86/entry/calling.h @@ -97,46 +97,6 @@ For 32-bit we have the following conventions - kernel is built with #define SIZEOF_PTREGS 21*8 - .macro ALLOC_PT_GPREGS_ON_STACK - addq $-(15*8), %rsp - .endm - - .macro SAVE_AND_CLEAR_REGS offset=0 - /* - * Save registers and sanitize registers of values that a - * speculation attack might otherwise want to exploit. The - * lower registers are likely clobbered well before they - * could be put to use in a speculative execution gadget. - * Interleave XOR with PUSH for better uop scheduling: - */ - movq %rdi, 14*8+\offset(%rsp) - movq %rsi, 13*8+\offset(%rsp) - movq %rdx, 12*8+\offset(%rsp) - movq %rcx, 11*8+\offset(%rsp) - movq %rax, 10*8+\offset(%rsp) - movq %r8, 9*8+\offset(%rsp) - xorq %r8, %r8 /* nospec r8 */ - movq %r9, 8*8+\offset(%rsp) - xorq %r9, %r9 /* nospec r9 */ - movq %r10, 7*8+\offset(%rsp) - xorq %r10, %r10 /* nospec r10 */ - movq %r11, 6*8+\offset(%rsp) - xorq %r11, %r11 /* nospec r11 */ - movq %rbx, 5*8+\offset(%rsp) - xorl %ebx, %ebx /* nospec rbx */ - movq %rbp, 4*8+\offset(%rsp) - xorl %ebp, %ebp /* nospec rbp */ - movq %r12, 3*8+\offset(%rsp) - xorq %r12, %r12 /* nospec r12 */ - movq %r13, 2*8+\offset(%rsp) - xorq %r13, %r13 /* nospec r13 */ - movq %r14, 1*8+\offset(%rsp) - xorq %r14, %r14 /* nospec r14 */ - movq %r15, 0*8+\offset(%rsp) - xorq %r15, %r15 /* nospec r15 */ - UNWIND_HINT_REGS offset=\offset - .endm - .macro PUSH_AND_CLEAR_REGS rdx=%rdx rax=%rax /* * Push registers and sanitize registers of values that a @@ -211,7 +171,7 @@ For 32-bit we have the following conventions - kernel is built with * is just setting the LSB, which makes it an invalid stack address and is also * a signal to the unwinder that it's a pt_regs pointer in disguise. * - * NOTE: This macro must be used *after* SAVE_AND_CLEAR_REGS because it corrupts + * NOTE: This macro must be used *after* PUSH_AND_CLEAR_REGS because it corrupts * the original rbp. */ .macro ENCODE_FRAME_POINTER ptregs_offset=0 diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index b06a4b5864ba..cfbf43366731 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -871,7 +871,9 @@ ENTRY(\sym) pushq $-1 /* ORIG_RAX: no syscall to restart */ .endif - ALLOC_PT_GPREGS_ON_STACK + /* Save all registers in pt_regs */ + PUSH_AND_CLEAR_REGS + ENCODE_FRAME_POINTER .if \paranoid < 2 testb $3, CS(%rsp) /* If coming from userspace, switch stacks */ @@ -1121,15 +1123,12 @@ idtentry machine_check do_mce has_error_code=0 paranoid=1 #endif /* - * Save all registers in pt_regs, and switch gs if needed. + * Switch gs if needed. * Use slow, but surefire "are we in kernel?" check. * Return: ebx=0: need swapgs on exit, ebx=1: otherwise */ ENTRY(paranoid_entry) - UNWIND_HINT_FUNC cld - SAVE_AND_CLEAR_REGS 8 - ENCODE_FRAME_POINTER 8 movl $1, %ebx movl $MSR_GS_BASE, %ecx rdmsr @@ -1142,7 +1141,7 @@ ENTRY(paranoid_entry) SAVE_AND_SWITCH_TO_KERNEL_CR3 scratch_reg=%rax save_reg=%r14 ret -END(paranoid_entry) +ENDPROC(paranoid_entry) /* * "Paranoid" exit path from exception stack. This is invoked @@ -1173,14 +1172,12 @@ ENTRY(paranoid_exit) END(paranoid_exit) /* - * Save all registers in pt_regs, and switch gs if needed. + * Switch gs if needed. * Return: EBX=0: came from user mode; EBX=1: otherwise */ ENTRY(error_entry) - UNWIND_HINT_FUNC + UNWIND_HINT_REGS offset=8 cld - SAVE_AND_CLEAR_REGS 8 - ENCODE_FRAME_POINTER 8 testb $3, CS+8(%rsp) jz .Lerror_kernelspace @@ -1571,7 +1568,8 @@ end_repeat_nmi: * frame to point back to repeat_nmi. */ pushq $-1 /* ORIG_RAX: no syscall to restart */ - ALLOC_PT_GPREGS_ON_STACK + PUSH_AND_CLEAR_REGS + ENCODE_FRAME_POINTER /* * Use paranoid_entry to handle SWAPGS, but no need to use paranoid_exit -- cgit v1.2.3-55-g7522 From 92816f571af81e9a71cc6f3dc8ce1e2fcdf7b6b8 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Sun, 11 Feb 2018 11:49:48 +0100 Subject: x86/entry/64: Indent PUSH_AND_CLEAR_REGS and POP_REGS properly ... same as the other macros in arch/x86/entry/calling.h Signed-off-by: Dominik Brodowski Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Josh Poimboeuf Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: dan.j.williams@intel.com Link: http://lkml.kernel.org/r/20180211104949.12992-8-linux@dominikbrodowski.net Signed-off-by: Ingo Molnar --- arch/x86/entry/calling.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'arch') diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h index 59675010c9a0..6985440c68fa 100644 --- a/arch/x86/entry/calling.h +++ b/arch/x86/entry/calling.h @@ -97,7 +97,7 @@ For 32-bit we have the following conventions - kernel is built with #define SIZEOF_PTREGS 21*8 - .macro PUSH_AND_CLEAR_REGS rdx=%rdx rax=%rax +.macro PUSH_AND_CLEAR_REGS rdx=%rdx rax=%rax /* * Push registers and sanitize registers of values that a * speculation attack might otherwise want to exploit. The @@ -131,9 +131,9 @@ For 32-bit we have the following conventions - kernel is built with pushq %r15 /* pt_regs->r15 */ xorq %r15, %r15 /* nospec r15*/ UNWIND_HINT_REGS - .endm +.endm - .macro POP_REGS pop_rdi=1 skip_r11rcx=0 +.macro POP_REGS pop_rdi=1 skip_r11rcx=0 popq %r15 popq %r14 popq %r13 @@ -163,7 +163,7 @@ For 32-bit we have the following conventions - kernel is built with .macro icebp .byte 0xf1 - .endm +.endm /* * This is a sneaky trick to help the unwinder find pt_regs on the stack. The -- cgit v1.2.3-55-g7522 From b3ccefaed922529e6a67de7b30af5aa38c76ace9 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Mon, 12 Feb 2018 11:45:03 -0600 Subject: x86/entry/64: Fix paranoid_entry() frame pointer warning With the following commit: f09d160992d1 ("x86/entry/64: Get rid of the ALLOC_PT_GPREGS_ON_STACK and SAVE_AND_CLEAR_REGS macros") ... one of my suggested improvements triggered a frame pointer warning: arch/x86/entry/entry_64.o: warning: objtool: paranoid_entry()+0x11: call without frame pointer save/setup The warning is correct for the build-time code, but it's actually not relevant at runtime because of paravirt patching. The paravirt swapgs call gets replaced with either a SWAPGS instruction or NOPs at runtime. Go back to the previous behavior by removing the ELF function annotation for paranoid_entry() and adding an unwind hint, which effectively silences the warning. Reported-by: kbuild test robot Signed-off-by: Josh Poimboeuf Cc: Dominik Brodowski Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: kbuild-all@01.org Cc: tipbuild@zytor.com Fixes: f09d160992d1 ("x86/entry/64: Get rid of the ALLOC_PT_GPREGS_ON_STACK and SAVE_AND_CLEAR_REGS macros") Link: http://lkml.kernel.org/r/20180212174503.5acbymg5z6p32snu@treble Signed-off-by: Ingo Molnar --- arch/x86/entry/entry_64.S | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index cfbf43366731..1c54204207d8 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -1128,6 +1128,7 @@ idtentry machine_check do_mce has_error_code=0 paranoid=1 * Return: ebx=0: need swapgs on exit, ebx=1: otherwise */ ENTRY(paranoid_entry) + UNWIND_HINT_FUNC cld movl $1, %ebx movl $MSR_GS_BASE, %ecx @@ -1141,7 +1142,7 @@ ENTRY(paranoid_entry) SAVE_AND_SWITCH_TO_KERNEL_CR3 scratch_reg=%rax save_reg=%r14 ret -ENDPROC(paranoid_entry) +END(paranoid_entry) /* * "Paranoid" exit path from exception stack. This is invoked -- cgit v1.2.3-55-g7522 From b498c261107461d5c42140dfddd05df83d8ca078 Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Mon, 12 Feb 2018 21:13:18 +0100 Subject: x86/entry/64: Remove the unused 'icebp' macro That macro was touched around 2.5.8 times, judging by the full history linux repo, but it was unused even then. Get rid of it already. Signed-off-by: Borislav Petkov Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Josh Poimboeuf Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux@dominikbrodowski.net Link: http://lkml.kernel.org/r/20180212201318.GD14640@pd.tnic Signed-off-by: Ingo Molnar --- arch/x86/entry/calling.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'arch') diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h index 6985440c68fa..dce7092ab24a 100644 --- a/arch/x86/entry/calling.h +++ b/arch/x86/entry/calling.h @@ -159,10 +159,6 @@ For 32-bit we have the following conventions - kernel is built with .if \pop_rdi popq %rdi .endif - .endm - - .macro icebp - .byte 0xf1 .endm /* -- cgit v1.2.3-55-g7522 From 595dd46ebfc10be041a365d0a3fa99df50b6ba73 Mon Sep 17 00:00:00 2001 From: Jia Zhang Date: Mon, 12 Feb 2018 22:44:53 +0800 Subject: vfs/proc/kcore, x86/mm/kcore: Fix SMAP fault when dumping vsyscall user page Commit: df04abfd181a ("fs/proc/kcore.c: Add bounce buffer for ktext data") ... introduced a bounce buffer to work around CONFIG_HARDENED_USERCOPY=y. However, accessing the vsyscall user page will cause an SMAP fault. Replace memcpy() with copy_from_user() to fix this bug works, but adding a common way to handle this sort of user page may be useful for future. Currently, only vsyscall page requires KCORE_USER. Signed-off-by: Jia Zhang Reviewed-by: Jiri Olsa Cc: Al Viro Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: jolsa@redhat.com Link: http://lkml.kernel.org/r/1518446694-21124-2-git-send-email-zhang.jia@linux.alibaba.com Signed-off-by: Ingo Molnar --- arch/x86/mm/init_64.c | 3 +-- fs/proc/kcore.c | 4 ++++ include/linux/kcore.h | 1 + 3 files changed, 6 insertions(+), 2 deletions(-) (limited to 'arch') diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 1ab42c852069..6aa33d1e198f 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -1193,8 +1193,7 @@ void __init mem_init(void) register_page_bootmem_info(); /* Register memory areas for /proc/kcore */ - kclist_add(&kcore_vsyscall, (void *)VSYSCALL_ADDR, - PAGE_SIZE, KCORE_OTHER); + kclist_add(&kcore_vsyscall, (void *)VSYSCALL_ADDR, PAGE_SIZE, KCORE_USER); mem_init_print_info(NULL); } diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c index e8a93bc8285d..d1e82761de81 100644 --- a/fs/proc/kcore.c +++ b/fs/proc/kcore.c @@ -510,6 +510,10 @@ read_kcore(struct file *file, char __user *buffer, size_t buflen, loff_t *fpos) /* we have to zero-fill user buffer even if no read */ if (copy_to_user(buffer, buf, tsz)) return -EFAULT; + } else if (m->type == KCORE_USER) { + /* User page is handled prior to normal kernel page: */ + if (copy_to_user(buffer, (char *)start, tsz)) + return -EFAULT; } else { if (kern_addr_valid(start)) { /* diff --git a/include/linux/kcore.h b/include/linux/kcore.h index 7ff25a808fef..80db19d3a505 100644 --- a/include/linux/kcore.h +++ b/include/linux/kcore.h @@ -10,6 +10,7 @@ enum kcore_type { KCORE_VMALLOC, KCORE_RAM, KCORE_VMEMMAP, + KCORE_USER, KCORE_OTHER, }; -- cgit v1.2.3-55-g7522 From cd026ca2861e7f384d677626a483da797c76b9da Mon Sep 17 00:00:00 2001 From: Jia Zhang Date: Mon, 12 Feb 2018 22:44:54 +0800 Subject: x86/mm/kcore: Add vsyscall page to /proc/kcore conditionally The vsyscall page should be visible only if vsyscall=emulate/native when dumping /proc/kcore. Signed-off-by: Jia Zhang Reviewed-by: Jiri Olsa Cc: Al Viro Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: jolsa@redhat.com Link: http://lkml.kernel.org/r/1518446694-21124-3-git-send-email-zhang.jia@linux.alibaba.com Signed-off-by: Ingo Molnar --- arch/x86/mm/init_64.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 6aa33d1e198f..8ba9c3128947 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -1193,7 +1193,8 @@ void __init mem_init(void) register_page_bootmem_info(); /* Register memory areas for /proc/kcore */ - kclist_add(&kcore_vsyscall, (void *)VSYSCALL_ADDR, PAGE_SIZE, KCORE_USER); + if (get_gate_vma(&init_mm)) + kclist_add(&kcore_vsyscall, (void *)VSYSCALL_ADDR, PAGE_SIZE, KCORE_USER); mem_init_print_info(NULL); } -- cgit v1.2.3-55-g7522 From c9dccf1d074a67d36c510845f663980d69e3409b Mon Sep 17 00:00:00 2001 From: Sam Bobroff Date: Mon, 12 Feb 2018 11:19:29 +1100 Subject: powerpc/pseries: Enable RAS hotplug events later Currently if the kernel receives a memory hot-unplug event early enough, it may get stuck in an infinite loop in dissolve_free_huge_pages(). This appears as a stall just after: pseries-hotplug-mem: Attempting to hot-remove XX LMB(s) at YYYYYYYY It appears to be caused by "minimum_order" being uninitialized, due to init_ras_IRQ() executing before hugetlb_init(). To correct this, extract the part of init_ras_IRQ() that enables hotplug event processing and place it in the machine_late_initcall phase, which is guaranteed to be after hugetlb_init() is called. Signed-off-by: Sam Bobroff Acked-by: Balbir Singh [mpe: Reorder the functions to make the diff readable] Signed-off-by: Michael Ellerman --- arch/powerpc/platforms/pseries/ras.c | 31 ++++++++++++++++++++++--------- 1 file changed, 22 insertions(+), 9 deletions(-) (limited to 'arch') diff --git a/arch/powerpc/platforms/pseries/ras.c b/arch/powerpc/platforms/pseries/ras.c index 81d8614e7379..5e1ef9150182 100644 --- a/arch/powerpc/platforms/pseries/ras.c +++ b/arch/powerpc/platforms/pseries/ras.c @@ -48,6 +48,28 @@ static irqreturn_t ras_epow_interrupt(int irq, void *dev_id); static irqreturn_t ras_error_interrupt(int irq, void *dev_id); +/* + * Enable the hotplug interrupt late because processing them may touch other + * devices or systems (e.g. hugepages) that have not been initialized at the + * subsys stage. + */ +int __init init_ras_hotplug_IRQ(void) +{ + struct device_node *np; + + /* Hotplug Events */ + np = of_find_node_by_path("/event-sources/hot-plug-events"); + if (np != NULL) { + if (dlpar_workqueue_init() == 0) + request_event_sources_irqs(np, ras_hotplug_interrupt, + "RAS_HOTPLUG"); + of_node_put(np); + } + + return 0; +} +machine_late_initcall(pseries, init_ras_hotplug_IRQ); + /* * Initialize handlers for the set of interrupts caused by hardware errors * and power system events. @@ -66,15 +88,6 @@ static int __init init_ras_IRQ(void) of_node_put(np); } - /* Hotplug Events */ - np = of_find_node_by_path("/event-sources/hot-plug-events"); - if (np != NULL) { - if (dlpar_workqueue_init() == 0) - request_event_sources_irqs(np, ras_hotplug_interrupt, - "RAS_HOTPLUG"); - of_node_put(np); - } - /* EPOW Events */ np = of_find_node_by_path("/event-sources/epow-events"); if (np != NULL) { -- cgit v1.2.3-55-g7522 From b00b62898631b756c3e123542bbb0487aa343dd9 Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Thu, 8 Feb 2018 19:18:38 +1000 Subject: powerpc/vas: Don't set uses_vas for kernel windows cp_abort is only required for user windows, because kernel context must not be preempted between a copy/paste pair. Without this patch, the init task gets used_vas set when it runs the nx842_powernv_init initcall, which opens windows for kernel usage. used_vas is then never cleared anywhere, so it gets propagated into all other tasks. It's a property of the address space, so it should really be cleared when a new mm is created (or in dup_mmap if the mmaps are marked as VM_DONTCOPY). For now we seem to have no such driver, so leave that for another patch. Fixes: 6c8e6bb2a52d ("powerpc/vas: Add support for user receive window") Cc: stable@vger.kernel.org # v4.15+ Signed-off-by: Nicholas Piggin Reviewed-by: Sukadev Bhattiprolu Signed-off-by: Michael Ellerman --- arch/powerpc/platforms/powernv/vas-window.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) (limited to 'arch') diff --git a/arch/powerpc/platforms/powernv/vas-window.c b/arch/powerpc/platforms/powernv/vas-window.c index 2b3eb01ab110..b7c53a51c31b 100644 --- a/arch/powerpc/platforms/powernv/vas-window.c +++ b/arch/powerpc/platforms/powernv/vas-window.c @@ -1063,16 +1063,16 @@ struct vas_window *vas_tx_win_open(int vasid, enum vas_cop_type cop, rc = PTR_ERR(txwin->paste_kaddr); goto free_window; } + } else { + /* + * A user mapping must ensure that context switch issues + * CP_ABORT for this thread. + */ + rc = set_thread_uses_vas(); + if (rc) + goto free_window; } - /* - * Now that we have a send window, ensure context switch issues - * CP_ABORT for this thread. - */ - rc = -EINVAL; - if (set_thread_uses_vas() < 0) - goto free_window; - set_vinst_win(vinst, txwin); return txwin; -- cgit v1.2.3-55-g7522 From 62e984ddfd6b056d399e24113f5e6a7145e579d8 Mon Sep 17 00:00:00 2001 From: Alexey Kardashevskiy Date: Thu, 1 Feb 2018 16:09:44 +1100 Subject: powerpc/mm: Flush radix process translations when setting MMU type Radix guests do normally invalidate process-scoped translations when a new pid is allocated but migrated guests do not invalidate these so migrated guests crash sometime, especially easy to reproduce with migration happening within first 10 seconds after the guest boot start on the same machine. This adds the "Invalidate process-scoped translations" flush to fix radix guests migration. Fixes: 2ee13be34b13 ("KVM: PPC: Book3S HV: Update kvmppc_set_arch_compat() for ISA v3.00") Cc: stable@vger.kernel.org # v4.10+ Signed-off-by: Alexey Kardashevskiy Tested-by: Laurent Vivier Tested-by: Daniel Henrique Barboza Signed-off-by: Michael Ellerman --- arch/powerpc/mm/pgtable_64.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'arch') diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c index c9a623c2d8a2..d75dd5273d15 100644 --- a/arch/powerpc/mm/pgtable_64.c +++ b/arch/powerpc/mm/pgtable_64.c @@ -471,6 +471,8 @@ void mmu_partition_table_set_entry(unsigned int lpid, unsigned long dw0, if (old & PATB_HR) { asm volatile(PPC_TLBIE_5(%0,%1,2,0,1) : : "r" (TLBIEL_INVAL_SET_LPID), "r" (lpid)); + asm volatile(PPC_TLBIE_5(%0,%1,2,1,1) : : + "r" (TLBIEL_INVAL_SET_LPID), "r" (lpid)); trace_tlbie(lpid, 0, TLBIEL_INVAL_SET_LPID, lpid, 2, 0, 1); } else { asm volatile(PPC_TLBIE_5(%0,%1,2,0,0) : : -- cgit v1.2.3-55-g7522 From fae2211697c9490414e974431051f7fed5506653 Mon Sep 17 00:00:00 2001 From: Aneesh Kumar K.V Date: Sun, 11 Feb 2018 20:30:06 +0530 Subject: powerpc/mm: Fix crashes with 16G huge pages To support memory keys, we moved the hash pte slot information to the second half of the page table. This was ok with PTE entries at level 4 (PTE page) and level 3 (PMD). We already allocate larger page table pages at those levels to accomodate extra details. For level 4 we already have the extra space which was used to track 4k hash page table entry details and at level 3 the extra space was allocated to track the THP details. With hugetlbfs PTE, we used this extra space at the PMD level to store the slot details. But we also support hugetlbfs PTE at PUD level for 16GB pages and PUD level page didn't allocate extra space. This resulted in memory corruption. Fix this by allocating extra space at PUD level when HUGETLB is enabled. Fixes: bf9a95f9a648 ("powerpc: Free up four 64K PTE bits in 64K backed HPTE pages") Signed-off-by: Aneesh Kumar K.V Reviewed-by: Ram Pai Signed-off-by: Michael Ellerman --- arch/powerpc/include/asm/book3s/32/pgtable.h | 1 + arch/powerpc/include/asm/book3s/64/hash-64k.h | 5 +++++ arch/powerpc/include/asm/book3s/64/hash.h | 10 ++++++++++ arch/powerpc/include/asm/book3s/64/pgalloc.h | 6 +++--- arch/powerpc/include/asm/book3s/64/pgtable.h | 2 ++ arch/powerpc/include/asm/nohash/32/pgtable.h | 1 + arch/powerpc/include/asm/nohash/64/pgtable.h | 1 + arch/powerpc/mm/hash_utils_64.c | 1 + arch/powerpc/mm/init-common.c | 4 ++-- arch/powerpc/mm/pgtable-radix.c | 1 + arch/powerpc/mm/pgtable_64.c | 2 ++ 11 files changed, 29 insertions(+), 5 deletions(-) (limited to 'arch') diff --git a/arch/powerpc/include/asm/book3s/32/pgtable.h b/arch/powerpc/include/asm/book3s/32/pgtable.h index 30a155c0a6b0..c615abdce119 100644 --- a/arch/powerpc/include/asm/book3s/32/pgtable.h +++ b/arch/powerpc/include/asm/book3s/32/pgtable.h @@ -16,6 +16,7 @@ #define PGD_INDEX_SIZE (32 - PGDIR_SHIFT) #define PMD_CACHE_INDEX PMD_INDEX_SIZE +#define PUD_CACHE_INDEX PUD_INDEX_SIZE #ifndef __ASSEMBLY__ #define PTE_TABLE_SIZE (sizeof(pte_t) << PTE_INDEX_SIZE) diff --git a/arch/powerpc/include/asm/book3s/64/hash-64k.h b/arch/powerpc/include/asm/book3s/64/hash-64k.h index 338b7da468ce..c08b3b032ec0 100644 --- a/arch/powerpc/include/asm/book3s/64/hash-64k.h +++ b/arch/powerpc/include/asm/book3s/64/hash-64k.h @@ -146,7 +146,12 @@ static inline int hash__remap_4k_pfn(struct vm_area_struct *vma, unsigned long a #else #define H_PMD_TABLE_SIZE (sizeof(pmd_t) << PMD_INDEX_SIZE) #endif +#ifdef CONFIG_HUGETLB_PAGE +#define H_PUD_TABLE_SIZE ((sizeof(pud_t) << PUD_INDEX_SIZE) + \ + (sizeof(unsigned long) << PUD_INDEX_SIZE)) +#else #define H_PUD_TABLE_SIZE (sizeof(pud_t) << PUD_INDEX_SIZE) +#endif #define H_PGD_TABLE_SIZE (sizeof(pgd_t) << PGD_INDEX_SIZE) #ifdef CONFIG_TRANSPARENT_HUGEPAGE diff --git a/arch/powerpc/include/asm/book3s/64/hash.h b/arch/powerpc/include/asm/book3s/64/hash.h index 0920eff731b3..a889457542e8 100644 --- a/arch/powerpc/include/asm/book3s/64/hash.h +++ b/arch/powerpc/include/asm/book3s/64/hash.h @@ -32,6 +32,16 @@ #else #define H_PMD_CACHE_INDEX H_PMD_INDEX_SIZE #endif +/* + * We store the slot details in the second half of page table. + * Increase the pud level table so that hugetlb ptes can be stored + * at pud level. + */ +#if defined(CONFIG_HUGETLB_PAGE) && defined(CONFIG_PPC_64K_PAGES) +#define H_PUD_CACHE_INDEX (H_PUD_INDEX_SIZE + 1) +#else +#define H_PUD_CACHE_INDEX (H_PUD_INDEX_SIZE) +#endif /* * Define the address range of the kernel non-linear virtual area */ diff --git a/arch/powerpc/include/asm/book3s/64/pgalloc.h b/arch/powerpc/include/asm/book3s/64/pgalloc.h index 1fcfa425cefa..827ebce4df90 100644 --- a/arch/powerpc/include/asm/book3s/64/pgalloc.h +++ b/arch/powerpc/include/asm/book3s/64/pgalloc.h @@ -93,13 +93,13 @@ static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, pud_t *pud) static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr) { - return kmem_cache_alloc(PGT_CACHE(PUD_INDEX_SIZE), + return kmem_cache_alloc(PGT_CACHE(PUD_CACHE_INDEX), pgtable_gfp_flags(mm, GFP_KERNEL)); } static inline void pud_free(struct mm_struct *mm, pud_t *pud) { - kmem_cache_free(PGT_CACHE(PUD_INDEX_SIZE), pud); + kmem_cache_free(PGT_CACHE(PUD_CACHE_INDEX), pud); } static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd) @@ -115,7 +115,7 @@ static inline void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pud, * ahead and flush the page walk cache */ flush_tlb_pgtable(tlb, address); - pgtable_free_tlb(tlb, pud, PUD_INDEX_SIZE); + pgtable_free_tlb(tlb, pud, PUD_CACHE_INDEX); } static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr) diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h index 51017726d495..1c8c88e90553 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable.h @@ -232,11 +232,13 @@ extern unsigned long __pmd_index_size; extern unsigned long __pud_index_size; extern unsigned long __pgd_index_size; extern unsigned long __pmd_cache_index; +extern unsigned long __pud_cache_index; #define PTE_INDEX_SIZE __pte_index_size #define PMD_INDEX_SIZE __pmd_index_size #define PUD_INDEX_SIZE __pud_index_size #define PGD_INDEX_SIZE __pgd_index_size #define PMD_CACHE_INDEX __pmd_cache_index +#define PUD_CACHE_INDEX __pud_cache_index /* * Because of use of pte fragments and THP, size of page table * are not always derived out of index size above. diff --git a/arch/powerpc/include/asm/nohash/32/pgtable.h b/arch/powerpc/include/asm/nohash/32/pgtable.h index 504a3c36ce5c..03bbd1149530 100644 --- a/arch/powerpc/include/asm/nohash/32/pgtable.h +++ b/arch/powerpc/include/asm/nohash/32/pgtable.h @@ -24,6 +24,7 @@ extern int icache_44x_need_flush; #define PGD_INDEX_SIZE (32 - PGDIR_SHIFT) #define PMD_CACHE_INDEX PMD_INDEX_SIZE +#define PUD_CACHE_INDEX PUD_INDEX_SIZE #ifndef __ASSEMBLY__ #define PTE_TABLE_SIZE (sizeof(pte_t) << PTE_INDEX_SIZE) diff --git a/arch/powerpc/include/asm/nohash/64/pgtable.h b/arch/powerpc/include/asm/nohash/64/pgtable.h index abddf5830ad5..5c5f75d005ad 100644 --- a/arch/powerpc/include/asm/nohash/64/pgtable.h +++ b/arch/powerpc/include/asm/nohash/64/pgtable.h @@ -27,6 +27,7 @@ #else #define PMD_CACHE_INDEX PMD_INDEX_SIZE #endif +#define PUD_CACHE_INDEX PUD_INDEX_SIZE /* * Define the address range of the kernel non-linear virtual area diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c index 7d07c7e17db6..cf290d415dcd 100644 --- a/arch/powerpc/mm/hash_utils_64.c +++ b/arch/powerpc/mm/hash_utils_64.c @@ -1008,6 +1008,7 @@ void __init hash__early_init_mmu(void) __pmd_index_size = H_PMD_INDEX_SIZE; __pud_index_size = H_PUD_INDEX_SIZE; __pgd_index_size = H_PGD_INDEX_SIZE; + __pud_cache_index = H_PUD_CACHE_INDEX; __pmd_cache_index = H_PMD_CACHE_INDEX; __pte_table_size = H_PTE_TABLE_SIZE; __pmd_table_size = H_PMD_TABLE_SIZE; diff --git a/arch/powerpc/mm/init-common.c b/arch/powerpc/mm/init-common.c index eb8c6c8c4851..2b656e67f2ea 100644 --- a/arch/powerpc/mm/init-common.c +++ b/arch/powerpc/mm/init-common.c @@ -100,6 +100,6 @@ void pgtable_cache_init(void) * same size as either the pgd or pmd index except with THP enabled * on book3s 64 */ - if (PUD_INDEX_SIZE && !PGT_CACHE(PUD_INDEX_SIZE)) - pgtable_cache_add(PUD_INDEX_SIZE, pud_ctor); + if (PUD_CACHE_INDEX && !PGT_CACHE(PUD_CACHE_INDEX)) + pgtable_cache_add(PUD_CACHE_INDEX, pud_ctor); } diff --git a/arch/powerpc/mm/pgtable-radix.c b/arch/powerpc/mm/pgtable-radix.c index 328ff9abc333..2e10a964e290 100644 --- a/arch/powerpc/mm/pgtable-radix.c +++ b/arch/powerpc/mm/pgtable-radix.c @@ -553,6 +553,7 @@ void __init radix__early_init_mmu(void) __pmd_index_size = RADIX_PMD_INDEX_SIZE; __pud_index_size = RADIX_PUD_INDEX_SIZE; __pgd_index_size = RADIX_PGD_INDEX_SIZE; + __pud_cache_index = RADIX_PUD_INDEX_SIZE; __pmd_cache_index = RADIX_PMD_INDEX_SIZE; __pte_table_size = RADIX_PTE_TABLE_SIZE; __pmd_table_size = RADIX_PMD_TABLE_SIZE; diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c index d75dd5273d15..28c980eb4422 100644 --- a/arch/powerpc/mm/pgtable_64.c +++ b/arch/powerpc/mm/pgtable_64.c @@ -82,6 +82,8 @@ unsigned long __pgd_index_size; EXPORT_SYMBOL(__pgd_index_size); unsigned long __pmd_cache_index; EXPORT_SYMBOL(__pmd_cache_index); +unsigned long __pud_cache_index; +EXPORT_SYMBOL(__pud_cache_index); unsigned long __pte_table_size; EXPORT_SYMBOL(__pte_table_size); unsigned long __pmd_table_size; -- cgit v1.2.3-55-g7522 From 4a7aa4fecbbf94b5c6fae8acccc983d919992bde Mon Sep 17 00:00:00 2001 From: Aneesh Kumar K.V Date: Sun, 11 Feb 2018 20:30:07 +0530 Subject: powerpc/mm/hash64: Allocate larger PMD table if hugetlb config is enabled We use the second half of the page table to store slot information, so we must allocate it always if hugetlb is possible. Fixes: bf9a95f9a648 ("powerpc: Free up four 64K PTE bits in 64K backed HPTE pages") Signed-off-by: Aneesh Kumar K.V Reviewed-by: Ram Pai Signed-off-by: Michael Ellerman --- arch/powerpc/include/asm/book3s/64/hash-64k.h | 2 +- arch/powerpc/include/asm/book3s/64/hash.h | 3 ++- 2 files changed, 3 insertions(+), 2 deletions(-) (limited to 'arch') diff --git a/arch/powerpc/include/asm/book3s/64/hash-64k.h b/arch/powerpc/include/asm/book3s/64/hash-64k.h index c08b3b032ec0..ee440fb3d240 100644 --- a/arch/powerpc/include/asm/book3s/64/hash-64k.h +++ b/arch/powerpc/include/asm/book3s/64/hash-64k.h @@ -140,7 +140,7 @@ static inline int hash__remap_4k_pfn(struct vm_area_struct *vma, unsigned long a } #define H_PTE_TABLE_SIZE PTE_FRAG_SIZE -#ifdef CONFIG_TRANSPARENT_HUGEPAGE +#if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined (CONFIG_HUGETLB_PAGE) #define H_PMD_TABLE_SIZE ((sizeof(pmd_t) << PMD_INDEX_SIZE) + \ (sizeof(unsigned long) << PMD_INDEX_SIZE)) #else diff --git a/arch/powerpc/include/asm/book3s/64/hash.h b/arch/powerpc/include/asm/book3s/64/hash.h index a889457542e8..935adcd92a81 100644 --- a/arch/powerpc/include/asm/book3s/64/hash.h +++ b/arch/powerpc/include/asm/book3s/64/hash.h @@ -23,7 +23,8 @@ H_PUD_INDEX_SIZE + H_PGD_INDEX_SIZE + PAGE_SHIFT) #define H_PGTABLE_RANGE (ASM_CONST(1) << H_PGTABLE_EADDR_SIZE) -#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && defined(CONFIG_PPC_64K_PAGES) +#if (defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLB_PAGE)) && \ + defined(CONFIG_PPC_64K_PAGES) /* * only with hash 64k we need to use the second half of pmd page table * to store pointer to deposited pgtable_t -- cgit v1.2.3-55-g7522 From ff31e105464d8c8c973019646827020aed9c2d9f Mon Sep 17 00:00:00 2001 From: Aneesh Kumar K.V Date: Sun, 11 Feb 2018 20:30:08 +0530 Subject: powerpc/mm/hash64: Store the slot information at the right offset for hugetlb The hugetlb pte entries are at the PMD and PUD level, so we can't use PTRS_PER_PTE to find the second half of the page table. Use the right offset for PUD/PMD to get to the second half of the table. Fixes: bf9a95f9a648 ("powerpc: Free up four 64K PTE bits in 64K backed HPTE pages") Signed-off-by: Aneesh Kumar K.V Reviewed-by: Ram Pai Signed-off-by: Michael Ellerman --- arch/powerpc/include/asm/book3s/64/hash-4k.h | 3 ++- arch/powerpc/include/asm/book3s/64/hash-64k.h | 9 +++++---- arch/powerpc/include/asm/book3s/64/pgtable.h | 2 +- arch/powerpc/mm/hash64_4k.c | 4 ++-- arch/powerpc/mm/hash64_64k.c | 8 ++++---- arch/powerpc/mm/hugetlbpage-hash64.c | 10 +++++++--- arch/powerpc/mm/tlb_hash64.c | 9 +++++++-- 7 files changed, 28 insertions(+), 17 deletions(-) (limited to 'arch') diff --git a/arch/powerpc/include/asm/book3s/64/hash-4k.h b/arch/powerpc/include/asm/book3s/64/hash-4k.h index 949d691094a4..67c5475311ee 100644 --- a/arch/powerpc/include/asm/book3s/64/hash-4k.h +++ b/arch/powerpc/include/asm/book3s/64/hash-4k.h @@ -63,7 +63,8 @@ static inline int hash__hugepd_ok(hugepd_t hpd) * keeping the prototype consistent across the two formats. */ static inline unsigned long pte_set_hidx(pte_t *ptep, real_pte_t rpte, - unsigned int subpg_index, unsigned long hidx) + unsigned int subpg_index, unsigned long hidx, + int offset) { return (hidx << H_PAGE_F_GIX_SHIFT) & (H_PAGE_F_SECOND | H_PAGE_F_GIX); diff --git a/arch/powerpc/include/asm/book3s/64/hash-64k.h b/arch/powerpc/include/asm/book3s/64/hash-64k.h index ee440fb3d240..3bcf269f8f55 100644 --- a/arch/powerpc/include/asm/book3s/64/hash-64k.h +++ b/arch/powerpc/include/asm/book3s/64/hash-64k.h @@ -45,7 +45,7 @@ * generic accessors and iterators here */ #define __real_pte __real_pte -static inline real_pte_t __real_pte(pte_t pte, pte_t *ptep) +static inline real_pte_t __real_pte(pte_t pte, pte_t *ptep, int offset) { real_pte_t rpte; unsigned long *hidxp; @@ -59,7 +59,7 @@ static inline real_pte_t __real_pte(pte_t pte, pte_t *ptep) */ smp_rmb(); - hidxp = (unsigned long *)(ptep + PTRS_PER_PTE); + hidxp = (unsigned long *)(ptep + offset); rpte.hidx = *hidxp; return rpte; } @@ -86,9 +86,10 @@ static inline unsigned long __rpte_to_hidx(real_pte_t rpte, unsigned long index) * expected to modify the PTE bits accordingly and commit the PTE to memory. */ static inline unsigned long pte_set_hidx(pte_t *ptep, real_pte_t rpte, - unsigned int subpg_index, unsigned long hidx) + unsigned int subpg_index, + unsigned long hidx, int offset) { - unsigned long *hidxp = (unsigned long *)(ptep + PTRS_PER_PTE); + unsigned long *hidxp = (unsigned long *)(ptep + offset); rpte.hidx &= ~HIDX_BITS(0xfUL, subpg_index); *hidxp = rpte.hidx | HIDX_BITS(HIDX_SHIFT_BY_ONE(hidx), subpg_index); diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h index 1c8c88e90553..a6b9f1d74600 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable.h @@ -350,7 +350,7 @@ extern unsigned long pci_io_base; */ #ifndef __real_pte -#define __real_pte(e,p) ((real_pte_t){(e)}) +#define __real_pte(e, p, o) ((real_pte_t){(e)}) #define __rpte_to_pte(r) ((r).pte) #define __rpte_to_hidx(r,index) (pte_val(__rpte_to_pte(r)) >> H_PAGE_F_GIX_SHIFT) diff --git a/arch/powerpc/mm/hash64_4k.c b/arch/powerpc/mm/hash64_4k.c index 5a69b51d08a3..d573d7d07f25 100644 --- a/arch/powerpc/mm/hash64_4k.c +++ b/arch/powerpc/mm/hash64_4k.c @@ -55,7 +55,7 @@ int __hash_page_4K(unsigned long ea, unsigned long access, unsigned long vsid, * need to add in 0x1 if it's a read-only user page */ rflags = htab_convert_pte_flags(new_pte); - rpte = __real_pte(__pte(old_pte), ptep); + rpte = __real_pte(__pte(old_pte), ptep, PTRS_PER_PTE); if (cpu_has_feature(CPU_FTR_NOEXECUTE) && !cpu_has_feature(CPU_FTR_COHERENT_ICACHE)) @@ -117,7 +117,7 @@ repeat: return -1; } new_pte = (new_pte & ~_PAGE_HPTEFLAGS) | H_PAGE_HASHPTE; - new_pte |= pte_set_hidx(ptep, rpte, 0, slot); + new_pte |= pte_set_hidx(ptep, rpte, 0, slot, PTRS_PER_PTE); } *ptep = __pte(new_pte & ~H_PAGE_BUSY); return 0; diff --git a/arch/powerpc/mm/hash64_64k.c b/arch/powerpc/mm/hash64_64k.c index 2253bbc6a599..e601d95c3b20 100644 --- a/arch/powerpc/mm/hash64_64k.c +++ b/arch/powerpc/mm/hash64_64k.c @@ -86,7 +86,7 @@ int __hash_page_4K(unsigned long ea, unsigned long access, unsigned long vsid, subpg_index = (ea & (PAGE_SIZE - 1)) >> shift; vpn = hpt_vpn(ea, vsid, ssize); - rpte = __real_pte(__pte(old_pte), ptep); + rpte = __real_pte(__pte(old_pte), ptep, PTRS_PER_PTE); /* *None of the sub 4k page is hashed */ @@ -214,7 +214,7 @@ repeat: return -1; } - new_pte |= pte_set_hidx(ptep, rpte, subpg_index, slot); + new_pte |= pte_set_hidx(ptep, rpte, subpg_index, slot, PTRS_PER_PTE); new_pte |= H_PAGE_HASHPTE; *ptep = __pte(new_pte & ~H_PAGE_BUSY); @@ -262,7 +262,7 @@ int __hash_page_64K(unsigned long ea, unsigned long access, } while (!pte_xchg(ptep, __pte(old_pte), __pte(new_pte))); rflags = htab_convert_pte_flags(new_pte); - rpte = __real_pte(__pte(old_pte), ptep); + rpte = __real_pte(__pte(old_pte), ptep, PTRS_PER_PTE); if (cpu_has_feature(CPU_FTR_NOEXECUTE) && !cpu_has_feature(CPU_FTR_COHERENT_ICACHE)) @@ -327,7 +327,7 @@ repeat: } new_pte = (new_pte & ~_PAGE_HPTEFLAGS) | H_PAGE_HASHPTE; - new_pte |= pte_set_hidx(ptep, rpte, 0, slot); + new_pte |= pte_set_hidx(ptep, rpte, 0, slot, PTRS_PER_PTE); } *ptep = __pte(new_pte & ~H_PAGE_BUSY); return 0; diff --git a/arch/powerpc/mm/hugetlbpage-hash64.c b/arch/powerpc/mm/hugetlbpage-hash64.c index 12511f5a015f..b320f5097a06 100644 --- a/arch/powerpc/mm/hugetlbpage-hash64.c +++ b/arch/powerpc/mm/hugetlbpage-hash64.c @@ -27,7 +27,7 @@ int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid, unsigned long vpn; unsigned long old_pte, new_pte; unsigned long rflags, pa, sz; - long slot; + long slot, offset; BUG_ON(shift != mmu_psize_defs[mmu_psize].shift); @@ -63,7 +63,11 @@ int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid, } while(!pte_xchg(ptep, __pte(old_pte), __pte(new_pte))); rflags = htab_convert_pte_flags(new_pte); - rpte = __real_pte(__pte(old_pte), ptep); + if (unlikely(mmu_psize == MMU_PAGE_16G)) + offset = PTRS_PER_PUD; + else + offset = PTRS_PER_PMD; + rpte = __real_pte(__pte(old_pte), ptep, offset); sz = ((1UL) << shift); if (!cpu_has_feature(CPU_FTR_COHERENT_ICACHE)) @@ -104,7 +108,7 @@ int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid, return -1; } - new_pte |= pte_set_hidx(ptep, rpte, 0, slot); + new_pte |= pte_set_hidx(ptep, rpte, 0, slot, offset); } /* diff --git a/arch/powerpc/mm/tlb_hash64.c b/arch/powerpc/mm/tlb_hash64.c index 881ebd53ffc2..9b23f12e863c 100644 --- a/arch/powerpc/mm/tlb_hash64.c +++ b/arch/powerpc/mm/tlb_hash64.c @@ -51,7 +51,7 @@ void hpte_need_flush(struct mm_struct *mm, unsigned long addr, unsigned int psize; int ssize; real_pte_t rpte; - int i; + int i, offset; i = batch->index; @@ -67,6 +67,10 @@ void hpte_need_flush(struct mm_struct *mm, unsigned long addr, psize = get_slice_psize(mm, addr); /* Mask the address for the correct page size */ addr &= ~((1UL << mmu_psize_defs[psize].shift) - 1); + if (unlikely(psize == MMU_PAGE_16G)) + offset = PTRS_PER_PUD; + else + offset = PTRS_PER_PMD; #else BUG(); psize = pte_pagesize_index(mm, addr, pte); /* shutup gcc */ @@ -78,6 +82,7 @@ void hpte_need_flush(struct mm_struct *mm, unsigned long addr, * support 64k pages, this might be different from the * hardware page size encoded in the slice table. */ addr &= PAGE_MASK; + offset = PTRS_PER_PTE; } @@ -91,7 +96,7 @@ void hpte_need_flush(struct mm_struct *mm, unsigned long addr, } WARN_ON(vsid == 0); vpn = hpt_vpn(addr, vsid, ssize); - rpte = __real_pte(__pte(pte), ptep); + rpte = __real_pte(__pte(pte), ptep, offset); /* * Check if we have an active batch on this CPU. If not, just -- cgit v1.2.3-55-g7522 From fc5c2f4a55a2c258e12013cdf287cf266dbcd2a7 Mon Sep 17 00:00:00 2001 From: Aneesh Kumar K.V Date: Tue, 13 Feb 2018 16:39:33 +0530 Subject: powerpc/mm/hash64: Zero PGD pages on allocation On powerpc we allocate page table pages from slab caches of different sizes. Currently we have a constructor that zeroes out the objects when we allocate them for the first time. We expect the objects to be zeroed out when we free the the object back to slab cache. This happens in the unmap path. For hugetlb pages we call huge_pte_get_and_clear() to do that. With the current configuration of page table size, both PUD and PGD level tables are allocated from the same slab cache. At the PUD level, we use the second half of the table to store the slot information. But we never clear that when unmapping. When such a freed object is then allocated for a PGD page, the second half of the page table page will not be zeroed as expected. This results in a kernel crash. Fix it by always clearing PGD pages when they're allocated. Signed-off-by: Aneesh Kumar K.V [mpe: Change log wording and formatting, add whitespace] Signed-off-by: Michael Ellerman --- arch/powerpc/include/asm/book3s/64/pgalloc.h | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) (limited to 'arch') diff --git a/arch/powerpc/include/asm/book3s/64/pgalloc.h b/arch/powerpc/include/asm/book3s/64/pgalloc.h index 827ebce4df90..4746bc68d446 100644 --- a/arch/powerpc/include/asm/book3s/64/pgalloc.h +++ b/arch/powerpc/include/asm/book3s/64/pgalloc.h @@ -73,10 +73,16 @@ static inline void radix__pgd_free(struct mm_struct *mm, pgd_t *pgd) static inline pgd_t *pgd_alloc(struct mm_struct *mm) { + pgd_t *pgd; + if (radix_enabled()) return radix__pgd_alloc(mm); - return kmem_cache_alloc(PGT_CACHE(PGD_INDEX_SIZE), - pgtable_gfp_flags(mm, GFP_KERNEL)); + + pgd = kmem_cache_alloc(PGT_CACHE(PGD_INDEX_SIZE), + pgtable_gfp_flags(mm, GFP_KERNEL)); + memset(pgd, 0, PGD_TABLE_SIZE); + + return pgd; } static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd) -- cgit v1.2.3-55-g7522 From 82343484a2d4c97a03bfd81303b5493c65f05c50 Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Mon, 12 Feb 2018 14:34:08 -0800 Subject: powerpc/pseries: Fix build break for SPLPAR=n and CPU hotplug Commit e67e02a544e9 ("powerpc/pseries: Fix cpu hotplug crash with memoryless nodes") adds an unconditional call to find_and_online_cpu_nid(), which is only declared if CONFIG_PPC_SPLPAR is enabled. This results in the following build error if this is not the case. arch/powerpc/platforms/pseries/hotplug-cpu.o: In function `dlpar_online_cpu': arch/powerpc/platforms/pseries/hotplug-cpu.c:369: undefined reference to `.find_and_online_cpu_nid' Follow the guideline provided by similar functions and provide a dummy function if CONFIG_PPC_SPLPAR is not enabled. This also moves the external function declaration into an include file where it should be. Fixes: e67e02a544e9 ("powerpc/pseries: Fix cpu hotplug crash with memoryless nodes") Signed-off-by: Guenter Roeck [mpe: Change subject to emphasise the build fix] Signed-off-by: Michael Ellerman --- arch/powerpc/include/asm/topology.h | 5 +++++ arch/powerpc/platforms/pseries/hotplug-cpu.c | 2 -- 2 files changed, 5 insertions(+), 2 deletions(-) (limited to 'arch') diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h index 1c02e6900f78..593248110902 100644 --- a/arch/powerpc/include/asm/topology.h +++ b/arch/powerpc/include/asm/topology.h @@ -87,6 +87,7 @@ static inline int numa_update_cpu_topology(bool cpus_locked) extern int start_topology_update(void); extern int stop_topology_update(void); extern int prrn_is_enabled(void); +extern int find_and_online_cpu_nid(int cpu); #else static inline int start_topology_update(void) { @@ -100,6 +101,10 @@ static inline int prrn_is_enabled(void) { return 0; } +static inline int find_and_online_cpu_nid(int cpu) +{ + return 0; +} #endif /* CONFIG_NUMA && CONFIG_PPC_SPLPAR */ #if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_NEED_MULTIPLE_NODES) diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c index f78fd2068d56..652d3e96b812 100644 --- a/arch/powerpc/platforms/pseries/hotplug-cpu.c +++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c @@ -342,8 +342,6 @@ static void pseries_remove_processor(struct device_node *np) cpu_maps_update_done(); } -extern int find_and_online_cpu_nid(int cpu); - static int dlpar_online_cpu(struct device_node *dn) { int rc = 0; -- cgit v1.2.3-55-g7522 From 910961754572a2f4c83ad7e610d180e3e6c29bda Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Mon, 12 Feb 2018 14:34:07 -0800 Subject: powerpc/kdump: Fix powernv build break when KEXEC_CORE=n If KEXEC_CORE is not enabled, powernv builds fail as follows. arch/powerpc/platforms/powernv/smp.c: In function 'pnv_smp_cpu_kill_self': arch/powerpc/platforms/powernv/smp.c:236:4: error: implicit declaration of function 'crash_ipi_callback' Add dummy function calls, similar to kdump_in_progress(), to solve the problem. Fixes: 4145f358644b ("powernv/kdump: Fix cases where the kdump kernel can get HMI's") Signed-off-by: Guenter Roeck Acked-by: Balbir Singh Signed-off-by: Michael Ellerman --- arch/powerpc/include/asm/kexec.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'arch') diff --git a/arch/powerpc/include/asm/kexec.h b/arch/powerpc/include/asm/kexec.h index 9dcbfa6bbb91..d8b1e8e7e035 100644 --- a/arch/powerpc/include/asm/kexec.h +++ b/arch/powerpc/include/asm/kexec.h @@ -140,6 +140,12 @@ static inline bool kdump_in_progress(void) return false; } +static inline void crash_ipi_callback(struct pt_regs *regs) { } + +static inline void crash_send_ipi(void (*crash_ipi_callback)(struct pt_regs *)) +{ +} + #endif /* CONFIG_KEXEC_CORE */ #endif /* ! __ASSEMBLY__ */ #endif /* __KERNEL__ */ -- cgit v1.2.3-55-g7522 From 295cc7eb314eb3321fb6d67ca6f7305f5c50d10f Mon Sep 17 00:00:00 2001 From: Masayoshi Mizuma Date: Thu, 8 Feb 2018 09:19:08 -0500 Subject: x86/smpboot: Fix uncore_pci_remove() indexing bug when hot-removing a physical CPU When a physical CPU is hot-removed, the following warning messages are shown while the uncore device is removed in uncore_pci_remove(): WARNING: CPU: 120 PID: 5 at arch/x86/events/intel/uncore.c:988 uncore_pci_remove+0xf1/0x110 ... CPU: 120 PID: 5 Comm: kworker/u1024:0 Not tainted 4.15.0-rc8 #1 Workqueue: kacpi_hotplug acpi_hotplug_work_fn ... Call Trace: pci_device_remove+0x36/0xb0 device_release_driver_internal+0x145/0x210 pci_stop_bus_device+0x76/0xa0 pci_stop_root_bus+0x44/0x60 acpi_pci_root_remove+0x1f/0x80 acpi_bus_trim+0x54/0x90 acpi_bus_trim+0x2e/0x90 acpi_device_hotplug+0x2bc/0x4b0 acpi_hotplug_work_fn+0x1a/0x30 process_one_work+0x141/0x340 worker_thread+0x47/0x3e0 kthread+0xf5/0x130 When uncore_pci_remove() runs, it tries to get the package ID to clear the value of uncore_extra_pci_dev[].dev[] by using topology_phys_to_logical_pkg(). The warning messesages are shown because topology_phys_to_logical_pkg() returns -1. arch/x86/events/intel/uncore.c: static void uncore_pci_remove(struct pci_dev *pdev) { ... phys_id = uncore_pcibus_to_physid(pdev->bus); ... pkg = topology_phys_to_logical_pkg(phys_id); // returns -1 for (i = 0; i < UNCORE_EXTRA_PCI_DEV_MAX; i++) { if (uncore_extra_pci_dev[pkg].dev[i] == pdev) { uncore_extra_pci_dev[pkg].dev[i] = NULL; break; } } WARN_ON_ONCE(i >= UNCORE_EXTRA_PCI_DEV_MAX); // <=========== HERE!! topology_phys_to_logical_pkg() tries to find cpuinfo_x86->phys_proc_id that matches the phys_pkg argument. arch/x86/kernel/smpboot.c: int topology_phys_to_logical_pkg(unsigned int phys_pkg) { int cpu; for_each_possible_cpu(cpu) { struct cpuinfo_x86 *c = &cpu_data(cpu); if (c->initialized && c->phys_proc_id == phys_pkg) return c->logical_proc_id; } return -1; } However, the phys_proc_id was already set to 0 by remove_siblinginfo() when the CPU was offlined. So, topology_phys_to_logical_pkg() cannot find the correct logical_proc_id and always returns -1. As the result, uncore_pci_remove() calls WARN_ON_ONCE() and the warning messages are shown. What is worse is that the bogus 'pkg' index results in two bugs: - We dereference uncore_extra_pci_dev[] with a negative index - We fail to clean up a stale pointer in uncore_extra_pci_dev[][] To fix these bugs, remove the clearing of ->phys_proc_id from remove_siblinginfo(). This should not cause any problems, because ->phys_proc_id is not used after it is hot-removed and it is re-set while hot-adding. Signed-off-by: Masayoshi Mizuma Acked-by: Thomas Gleixner Cc: Linus Torvalds Cc: Peter Zijlstra Cc: yasu.isimatu@gmail.com Cc: Fixes: 30bb9811856f ("x86/topology: Avoid wasting 128k for package id array") Link: http://lkml.kernel.org/r/ed738d54-0f01-b38b-b794-c31dc118c207@gmail.com Signed-off-by: Ingo Molnar --- arch/x86/kernel/smpboot.c | 1 - 1 file changed, 1 deletion(-) (limited to 'arch') diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 6f27facbaa9b..cfc61e1d45e2 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -1430,7 +1430,6 @@ static void remove_siblinginfo(int cpu) cpumask_clear(cpu_llc_shared_mask(cpu)); cpumask_clear(topology_sibling_cpumask(cpu)); cpumask_clear(topology_core_cpumask(cpu)); - c->phys_proc_id = 0; c->cpu_core_id = 0; cpumask_clear_cpu(cpu, cpu_sibling_setup_mask); recompute_smt_state(); -- cgit v1.2.3-55-g7522 From 627f4a2bdf113ab88abc65cb505c89cbf615eae0 Mon Sep 17 00:00:00 2001 From: Jaedon Shin Date: Tue, 6 Feb 2018 12:13:21 +0900 Subject: MIPS: BMIPS: Fix section mismatch warning Remove the __init annotation from bmips_cpu_setup() to avoid the following warning. WARNING: vmlinux.o(.text+0x35c950): Section mismatch in reference from the function brcmstb_pm_s3() to the function .init.text:bmips_cpu_setup() The function brcmstb_pm_s3() references the function __init bmips_cpu_setup(). This is often because brcmstb_pm_s3 lacks a __init annotation or the annotation of bmips_cpu_setup is wrong. Signed-off-by: Jaedon Shin Cc: Ralf Baechle Cc: Florian Fainelli Cc: Kevin Cernekee Cc: linux-mips@linux-mips.org Reviewed-by: James Hogan Reviewed-by: Florian Fainelli Patchwork: https://patchwork.linux-mips.org/patch/18589/ Signed-off-by: James Hogan --- arch/mips/kernel/smp-bmips.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/mips/kernel/smp-bmips.c b/arch/mips/kernel/smp-bmips.c index 87dcac2447c8..9d41732a9146 100644 --- a/arch/mips/kernel/smp-bmips.c +++ b/arch/mips/kernel/smp-bmips.c @@ -572,7 +572,7 @@ asmlinkage void __weak plat_wired_tlb_setup(void) */ } -void __init bmips_cpu_setup(void) +void bmips_cpu_setup(void) { void __iomem __maybe_unused *cbr = BMIPS_GET_CBR(); u32 __maybe_unused cfg; -- cgit v1.2.3-55-g7522 From 74eb816b21d520ce37ce8aaf03128ca6067bbe22 Mon Sep 17 00:00:00 2001 From: Progyan Bhattacharya Date: Tue, 6 Feb 2018 10:45:23 +0530 Subject: x86/build: Add arch/x86/tools/insn_decoder_test to .gitignore The file was generated by make command and should not be in the source tree. Signed-off-by: Progyan Bhattacharya Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar --- arch/x86/.gitignore | 1 + 1 file changed, 1 insertion(+) (limited to 'arch') diff --git a/arch/x86/.gitignore b/arch/x86/.gitignore index aff152c87cf4..5a82bac5e0bc 100644 --- a/arch/x86/.gitignore +++ b/arch/x86/.gitignore @@ -1,6 +1,7 @@ boot/compressed/vmlinux tools/test_get_len tools/insn_sanity +tools/insn_decoder_test purgatory/kexec-purgatory.c purgatory/purgatory.ro -- cgit v1.2.3-55-g7522 From 67a3ba25aa955198196f40b76b329b3ab9ad415a Mon Sep 17 00:00:00 2001 From: Marcin Nowakowski Date: Thu, 1 Feb 2018 12:37:21 +0100 Subject: MIPS: Fix incorrect mem=X@Y handling Commit 73fbc1eba7ff ("MIPS: fix mem=X@Y commandline processing") added a fix to ensure that the memory range between PHYS_OFFSET and low memory address specified by mem= cmdline argument is not later processed by free_all_bootmem. This change was incorrect for systems where the commandline specifies more than 1 mem argument, as it will cause all memory between PHYS_OFFSET and each of the memory offsets to be marked as reserved, which results in parts of the RAM marked as reserved (Creator CI20's u-boot has a default commandline argument 'mem=256M@0x0 mem=768M@0x30000000'). Change the behaviour to ensure that only the range between PHYS_OFFSET and the lowest start address of the memories is marked as protected. This change also ensures that the range is marked protected even if it's only defined through the devicetree and not only via commandline arguments. Reported-by: Mathieu Malaterre Signed-off-by: Marcin Nowakowski Fixes: 73fbc1eba7ff ("MIPS: fix mem=X@Y commandline processing") Cc: Ralf Baechle Cc: linux-mips@linux-mips.org Cc: # v4.11+ Tested-by: Mathieu Malaterre Patchwork: https://patchwork.linux-mips.org/patch/18562/ Signed-off-by: James Hogan --- arch/mips/kernel/setup.c | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-) (limited to 'arch') diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c index 85bc601e9a0d..5f8b0a9e30b3 100644 --- a/arch/mips/kernel/setup.c +++ b/arch/mips/kernel/setup.c @@ -375,6 +375,7 @@ static void __init bootmem_init(void) unsigned long reserved_end; unsigned long mapstart = ~0UL; unsigned long bootmap_size; + phys_addr_t ramstart = (phys_addr_t)ULLONG_MAX; bool bootmap_valid = false; int i; @@ -395,7 +396,8 @@ static void __init bootmem_init(void) max_low_pfn = 0; /* - * Find the highest page frame number we have available. + * Find the highest page frame number we have available + * and the lowest used RAM address */ for (i = 0; i < boot_mem_map.nr_map; i++) { unsigned long start, end; @@ -407,6 +409,8 @@ static void __init bootmem_init(void) end = PFN_DOWN(boot_mem_map.map[i].addr + boot_mem_map.map[i].size); + ramstart = min(ramstart, boot_mem_map.map[i].addr); + #ifndef CONFIG_HIGHMEM /* * Skip highmem here so we get an accurate max_low_pfn if low @@ -436,6 +440,13 @@ static void __init bootmem_init(void) mapstart = max(reserved_end, start); } + /* + * Reserve any memory between the start of RAM and PHYS_OFFSET + */ + if (ramstart > PHYS_OFFSET) + add_memory_region(PHYS_OFFSET, ramstart - PHYS_OFFSET, + BOOT_MEM_RESERVED); + if (min_low_pfn >= max_low_pfn) panic("Incorrect memory mapping !!!"); if (min_low_pfn > ARCH_PFN_OFFSET) { @@ -664,9 +675,6 @@ static int __init early_parse_mem(char *p) add_memory_region(start, size, BOOT_MEM_RAM); - if (start && start > PHYS_OFFSET) - add_memory_region(PHYS_OFFSET, start - PHYS_OFFSET, - BOOT_MEM_RESERVED); return 0; } early_param("mem", early_parse_mem); -- cgit v1.2.3-55-g7522 From c25d99d20ba69824a1e2cc118e04b877cd427afc Mon Sep 17 00:00:00 2001 From: mike.travis@hpe.com Date: Mon, 5 Feb 2018 16:15:04 -0600 Subject: x86/platform/UV: Fix GAM Range Table entries less than 1GB The latest UV platforms include the new ApachePass NVDIMMs into the UV address space. This has introduced address ranges in the Global Address Map Table that are less than the previous lowest range, which was 2GB. Fix the address calculation so it accommodates address ranges from bytes to exabytes. Signed-off-by: Mike Travis Reviewed-by: Andrew Banman Reviewed-by: Dimitri Sivanich Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Russ Anderson Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20180205221503.190219903@stormcage.americas.sgi.com Signed-off-by: Ingo Molnar --- arch/x86/kernel/apic/x2apic_uv_x.c | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index 46b675aaf20b..f11910b44638 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -1176,16 +1176,25 @@ static void __init decode_gam_rng_tbl(unsigned long ptr) uv_gre_table = gre; for (; gre->type != UV_GAM_RANGE_TYPE_UNUSED; gre++) { + unsigned long size = ((unsigned long)(gre->limit - lgre) + << UV_GAM_RANGE_SHFT); + int order = 0; + char suffix[] = " KMGTPE"; + + while (size > 9999 && order < sizeof(suffix)) { + size /= 1024; + order++; + } + if (!index) { pr_info("UV: GAM Range Table...\n"); pr_info("UV: # %20s %14s %5s %4s %5s %3s %2s\n", "Range", "", "Size", "Type", "NASID", "SID", "PN"); } - pr_info("UV: %2d: 0x%014lx-0x%014lx %5luG %3d %04x %02x %02x\n", + pr_info("UV: %2d: 0x%014lx-0x%014lx %5lu%c %3d %04x %02x %02x\n", index++, (unsigned long)lgre << UV_GAM_RANGE_SHFT, (unsigned long)gre->limit << UV_GAM_RANGE_SHFT, - ((unsigned long)(gre->limit - lgre)) >> - (30 - UV_GAM_RANGE_SHFT), /* 64M -> 1G */ + size, suffix[order], gre->type, gre->nasid, gre->sockid, gre->pnode); lgre = gre->limit; -- cgit v1.2.3-55-g7522 From 01684e72f16727e6ae0aeb1392f478e11ec5b8f7 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 2 Feb 2018 15:56:19 +0100 Subject: x86/error_inject: Make just_return_func() globally visible With link time optimizations enabled, I get a link failure: ./ccLbOEHX.ltrans19.ltrans.o: In function `override_function_with_return': :(.text+0x7f3): undefined reference to `just_return_func' Marking the symbol .globl makes it work as expected. Signed-off-by: Arnd Bergmann Acked-by: Masami Hiramatsu Acked-by: Thomas Gleixner Cc: Alexei Starovoitov Cc: Josef Bacik Cc: Linus Torvalds Cc: Nicolas Pitre Cc: Peter Zijlstra Fixes: 540adea3809f ("error-injection: Separate error-injection from kprobe") Link: http://lkml.kernel.org/r/20180202145634.200291-3-arnd@arndb.de Signed-off-by: Ingo Molnar --- arch/x86/lib/error-inject.c | 1 + 1 file changed, 1 insertion(+) (limited to 'arch') diff --git a/arch/x86/lib/error-inject.c b/arch/x86/lib/error-inject.c index 7b881d03d0dd..3cdf06128d13 100644 --- a/arch/x86/lib/error-inject.c +++ b/arch/x86/lib/error-inject.c @@ -7,6 +7,7 @@ asmlinkage void just_return_func(void); asm( ".type just_return_func, @function\n" + ".globl just_return_func\n" "just_return_func:\n" " ret\n" ".size just_return_func, .-just_return_func\n" -- cgit v1.2.3-55-g7522 From fd0e786d9d09024f67bd71ec094b110237dc3840 Mon Sep 17 00:00:00 2001 From: Tony Luck Date: Thu, 25 Jan 2018 14:23:48 -0800 Subject: x86/mm, mm/hwpoison: Don't unconditionally unmap kernel 1:1 pages In the following commit: ce0fa3e56ad2 ("x86/mm, mm/hwpoison: Clear PRESENT bit for kernel 1:1 mappings of poison pages") ... we added code to memory_failure() to unmap the page from the kernel 1:1 virtual address space to avoid speculative access to the page logging additional errors. But memory_failure() may not always succeed in taking the page offline, especially if the page belongs to the kernel. This can happen if there are too many corrected errors on a page and either mcelog(8) or drivers/ras/cec.c asks to take a page offline. Since we remove the 1:1 mapping early in memory_failure(), we can end up with the page unmapped, but still in use. On the next access the kernel crashes :-( There are also various debug paths that call memory_failure() to simulate occurrence of an error. Since there is no actual error in memory, we don't need to map out the page for those cases. Revert most of the previous attempt and keep the solution local to arch/x86/kernel/cpu/mcheck/mce.c. Unmap the page only when: 1) there is a real error 2) memory_failure() succeeds. All of this only applies to 64-bit systems. 32-bit kernel doesn't map all of memory into kernel space. It isn't worth adding the code to unmap the piece that is mapped because nobody would run a 32-bit kernel on a machine that has recoverable machine checks. Signed-off-by: Tony Luck Cc: Andrew Morton Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: Dave Cc: Denys Vlasenko Cc: Josh Poimboeuf Cc: Linus Torvalds Cc: Naoya Horiguchi Cc: Peter Zijlstra Cc: Robert (Persistent Memory) Cc: Thomas Gleixner Cc: linux-mm@kvack.org Cc: stable@vger.kernel.org #v4.14 Fixes: ce0fa3e56ad2 ("x86/mm, mm/hwpoison: Clear PRESENT bit for kernel 1:1 mappings of poison pages") Signed-off-by: Ingo Molnar --- arch/x86/include/asm/page_64.h | 4 ---- arch/x86/kernel/cpu/mcheck/mce-internal.h | 15 +++++++++++++++ arch/x86/kernel/cpu/mcheck/mce.c | 17 +++++++++++------ include/linux/mm_inline.h | 6 ------ mm/memory-failure.c | 2 -- 5 files changed, 26 insertions(+), 18 deletions(-) (limited to 'arch') diff --git a/arch/x86/include/asm/page_64.h b/arch/x86/include/asm/page_64.h index 4baa6bceb232..d652a3808065 100644 --- a/arch/x86/include/asm/page_64.h +++ b/arch/x86/include/asm/page_64.h @@ -52,10 +52,6 @@ static inline void clear_page(void *page) void copy_page(void *to, void *from); -#ifdef CONFIG_X86_MCE -#define arch_unmap_kpfn arch_unmap_kpfn -#endif - #endif /* !__ASSEMBLY__ */ #ifdef CONFIG_X86_VSYSCALL_EMULATION diff --git a/arch/x86/kernel/cpu/mcheck/mce-internal.h b/arch/x86/kernel/cpu/mcheck/mce-internal.h index aa0d5df9dc60..e956eb267061 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-internal.h +++ b/arch/x86/kernel/cpu/mcheck/mce-internal.h @@ -115,4 +115,19 @@ static inline void mce_unregister_injector_chain(struct notifier_block *nb) { } extern struct mca_config mca_cfg; +#ifndef CONFIG_X86_64 +/* + * On 32-bit systems it would be difficult to safely unmap a poison page + * from the kernel 1:1 map because there are no non-canonical addresses that + * we can use to refer to the address without risking a speculative access. + * However, this isn't much of an issue because: + * 1) Few unmappable pages are in the 1:1 map. Most are in HIGHMEM which + * are only mapped into the kernel as needed + * 2) Few people would run a 32-bit kernel on a machine that supports + * recoverable errors because they have too much memory to boot 32-bit. + */ +static inline void mce_unmap_kpfn(unsigned long pfn) {} +#define mce_unmap_kpfn mce_unmap_kpfn +#endif + #endif /* __X86_MCE_INTERNAL_H__ */ diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 75f405ac085c..8ff94d1e2dce 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -105,6 +105,10 @@ static struct irq_work mce_irq_work; static void (*quirk_no_way_out)(int bank, struct mce *m, struct pt_regs *regs); +#ifndef mce_unmap_kpfn +static void mce_unmap_kpfn(unsigned long pfn); +#endif + /* * CPU/chipset specific EDAC code can register a notifier call here to print * MCE errors in a human-readable form. @@ -590,7 +594,8 @@ static int srao_decode_notifier(struct notifier_block *nb, unsigned long val, if (mce_usable_address(mce) && (mce->severity == MCE_AO_SEVERITY)) { pfn = mce->addr >> PAGE_SHIFT; - memory_failure(pfn, 0); + if (!memory_failure(pfn, 0)) + mce_unmap_kpfn(pfn); } return NOTIFY_OK; @@ -1057,12 +1062,13 @@ static int do_memory_failure(struct mce *m) ret = memory_failure(m->addr >> PAGE_SHIFT, flags); if (ret) pr_err("Memory error not recovered"); + else + mce_unmap_kpfn(m->addr >> PAGE_SHIFT); return ret; } -#if defined(arch_unmap_kpfn) && defined(CONFIG_MEMORY_FAILURE) - -void arch_unmap_kpfn(unsigned long pfn) +#ifndef mce_unmap_kpfn +static void mce_unmap_kpfn(unsigned long pfn) { unsigned long decoy_addr; @@ -1073,7 +1079,7 @@ void arch_unmap_kpfn(unsigned long pfn) * We would like to just call: * set_memory_np((unsigned long)pfn_to_kaddr(pfn), 1); * but doing that would radically increase the odds of a - * speculative access to the posion page because we'd have + * speculative access to the poison page because we'd have * the virtual address of the kernel 1:1 mapping sitting * around in registers. * Instead we get tricky. We create a non-canonical address @@ -1098,7 +1104,6 @@ void arch_unmap_kpfn(unsigned long pfn) if (set_memory_np(decoy_addr, 1)) pr_warn("Could not invalidate pfn=0x%lx from 1:1 map\n", pfn); - } #endif diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h index c30b32e3c862..10191c28fc04 100644 --- a/include/linux/mm_inline.h +++ b/include/linux/mm_inline.h @@ -127,10 +127,4 @@ static __always_inline enum lru_list page_lru(struct page *page) #define lru_to_page(head) (list_entry((head)->prev, struct page, lru)) -#ifdef arch_unmap_kpfn -extern void arch_unmap_kpfn(unsigned long pfn); -#else -static __always_inline void arch_unmap_kpfn(unsigned long pfn) { } -#endif - #endif diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 4b80ccee4535..8291b75f42c8 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1139,8 +1139,6 @@ int memory_failure(unsigned long pfn, int flags) return 0; } - arch_unmap_kpfn(pfn); - orig_head = hpage = compound_head(p); num_poisoned_pages_inc(); -- cgit v1.2.3-55-g7522 From 8aa36a8dcde3183d84db7b0d622ffddcebb61077 Mon Sep 17 00:00:00 2001 From: Ulf Magnusson Date: Mon, 5 Feb 2018 02:21:13 +0100 Subject: ARM: mvebu: Fix broken PL310_ERRATA_753970 selects The MACH_ARMADA_375 and MACH_ARMADA_38X boards select ARM_ERRATA_753970, but it was renamed to PL310_ERRATA_753970 by commit fa0ce4035d48 ("ARM: 7162/1: errata: tidy up Kconfig options for PL310 errata workarounds"). Fix the selects to use the new name. Discovered with the https://github.com/ulfalizer/Kconfiglib/blob/master/examples/list_undefined.py script. Fixes: fa0ce4035d48 ("ARM: 7162/1: errata: tidy up Kconfig options for PL310 errata workarounds" cc: stable@vger.kernel.org Signed-off-by: Ulf Magnusson Signed-off-by: Gregory CLEMENT --- arch/arm/mach-mvebu/Kconfig | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch') diff --git a/arch/arm/mach-mvebu/Kconfig b/arch/arm/mach-mvebu/Kconfig index 6b32dc527edc..2c20599cc350 100644 --- a/arch/arm/mach-mvebu/Kconfig +++ b/arch/arm/mach-mvebu/Kconfig @@ -41,7 +41,7 @@ config MACH_ARMADA_375 depends on ARCH_MULTI_V7 select ARMADA_370_XP_IRQ select ARM_ERRATA_720789 - select ARM_ERRATA_753970 + select PL310_ERRATA_753970 select ARM_GIC select ARMADA_375_CLK select HAVE_ARM_SCU @@ -57,7 +57,7 @@ config MACH_ARMADA_38X bool "Marvell Armada 380/385 boards" depends on ARCH_MULTI_V7 select ARM_ERRATA_720789 - select ARM_ERRATA_753970 + select PL310_ERRATA_753970 select ARM_GIC select ARM_GLOBAL_TIMER select CLKSRC_ARM_GLOBAL_TIMER_SCHED_CLOCK -- cgit v1.2.3-55-g7522 From a9810327726b01404ecde082c075a7468c433ddf Mon Sep 17 00:00:00 2001 From: Christian Borntraeger Date: Mon, 29 Jan 2018 12:22:45 +0100 Subject: KVM: s390: optimize wakeup for exitless interrupts For interrupt injection of floating interrupts we queue the interrupt either in the GISA or in the floating interrupt list. The first CPU that looks at these data structures - either in KVM code or hardware will then deliver that interrupt. To minimize latency we also: -a: choose a VCPU to deliver that interrupt. We prefer idle CPUs -b: we wake up the host thread that runs the VCPU -c: set an I/O intervention bit for that CPU so that it exits guest context as soon as the PSW I/O mask is enabled This will make sure that this CPU will execute the interrupt delivery code of KVM very soon. We can now optimize the injection case if we have exitless interrupts. The wakeup is still necessary in case the target CPU sleeps. We can avoid the I/O intervention request bit though. Whenever this intervention request would be handled, the hardware could also directly inject the interrupt on that CPU, no need to go through the interrupt injection loop of KVM. Cc: Michael Mueller Reviewed-by: Halil Pasic Reviewed-by: David Hildenbrand Reviewed-by: Cornelia Huck Signed-off-by: Christian Borntraeger --- arch/s390/kvm/interrupt.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index aabf46f5f883..337a69bc04db 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -1701,7 +1701,8 @@ static void __floating_irq_kick(struct kvm *kvm, u64 type) kvm_s390_set_cpuflags(dst_vcpu, CPUSTAT_STOP_INT); break; case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX: - kvm_s390_set_cpuflags(dst_vcpu, CPUSTAT_IO_INT); + if (!(type & KVM_S390_INT_IO_AI_MASK && kvm->arch.gisa)) + kvm_s390_set_cpuflags(dst_vcpu, CPUSTAT_IO_INT); break; default: kvm_s390_set_cpuflags(dst_vcpu, CPUSTAT_EXT_INT); -- cgit v1.2.3-55-g7522 From 8846f3175c6bf16382b06a4b9755e5296c0f921c Mon Sep 17 00:00:00 2001 From: Christian Borntraeger Date: Mon, 12 Feb 2018 12:33:39 +0000 Subject: KVM: s390: do not set intervention requests for GISA interrupts If GISA is available, we do not have to kick CPUs out of SIE to deliver interrupts. The hardware can deliver such interrupts while running. Cc: Michael Mueller Reviewed-by: David Hildenbrand Reviewed-by: Cornelia Huck Signed-off-by: Christian Borntraeger --- arch/s390/kvm/interrupt.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) (limited to 'arch') diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index 337a69bc04db..e399495001ca 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -236,10 +236,15 @@ static inline int kvm_s390_gisa_tac_ipm_gisc(struct kvm_s390_gisa *gisa, u32 gis return test_and_clear_bit_inv(IPM_BIT_OFFSET + gisc, (unsigned long *) gisa); } -static inline unsigned long pending_irqs(struct kvm_vcpu *vcpu) +static inline unsigned long pending_irqs_no_gisa(struct kvm_vcpu *vcpu) { return vcpu->kvm->arch.float_int.pending_irqs | - vcpu->arch.local_int.pending_irqs | + vcpu->arch.local_int.pending_irqs; +} + +static inline unsigned long pending_irqs(struct kvm_vcpu *vcpu) +{ + return pending_irqs_no_gisa(vcpu) | kvm_s390_gisa_get_ipm(vcpu->kvm->arch.gisa) << IRQ_PEND_IO_ISC_7; } @@ -337,7 +342,7 @@ static void __reset_intercept_indicators(struct kvm_vcpu *vcpu) static void set_intercept_indicators_io(struct kvm_vcpu *vcpu) { - if (!(pending_irqs(vcpu) & IRQ_PEND_IO_MASK)) + if (!(pending_irqs_no_gisa(vcpu) & IRQ_PEND_IO_MASK)) return; else if (psw_ioint_disabled(vcpu)) kvm_s390_set_cpuflags(vcpu, CPUSTAT_IO_INT); -- cgit v1.2.3-55-g7522 From f315104ad8b0c32be13eac628569ae707c332cb5 Mon Sep 17 00:00:00 2001 From: Christian Borntraeger Date: Tue, 13 Feb 2018 13:55:49 +0000 Subject: KVM: s390: force bp isolation for VSIE If the guest runs with bp isolation when doing a SIE instruction, we must also run the nested guest with bp isolation when emulating that SIE instruction. This is done by activating BPBC in the lpar, which acts as an override for lower level guests. Signed-off-by: Christian Borntraeger Reviewed-by: Janosch Frank Reviewed-by: David Hildenbrand Signed-off-by: Christian Borntraeger --- arch/s390/kvm/vsie.c | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'arch') diff --git a/arch/s390/kvm/vsie.c b/arch/s390/kvm/vsie.c index ec772700ff96..8961e3970901 100644 --- a/arch/s390/kvm/vsie.c +++ b/arch/s390/kvm/vsie.c @@ -821,6 +821,7 @@ static int do_vsie_run(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page) { struct kvm_s390_sie_block *scb_s = &vsie_page->scb_s; struct kvm_s390_sie_block *scb_o = vsie_page->scb_o; + int guest_bp_isolation; int rc; handle_last_fault(vcpu, vsie_page); @@ -831,6 +832,20 @@ static int do_vsie_run(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page) s390_handle_mcck(); srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); + + /* save current guest state of bp isolation override */ + guest_bp_isolation = test_thread_flag(TIF_ISOLATE_BP_GUEST); + + /* + * The guest is running with BPBC, so we have to force it on for our + * nested guest. This is done by enabling BPBC globally, so the BPBC + * control in the SCB (which the nested guest can modify) is simply + * ignored. + */ + if (test_kvm_facility(vcpu->kvm, 82) && + vcpu->arch.sie_block->fpf & FPF_BPBC) + set_thread_flag(TIF_ISOLATE_BP_GUEST); + local_irq_disable(); guest_enter_irqoff(); local_irq_enable(); @@ -840,6 +855,11 @@ static int do_vsie_run(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page) local_irq_disable(); guest_exit_irqoff(); local_irq_enable(); + + /* restore guest state for bp isolation override */ + if (!guest_bp_isolation) + clear_thread_flag(TIF_ISOLATE_BP_GUEST); + vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); if (rc == -EINTR) { -- cgit v1.2.3-55-g7522 From 6db4263fec9e550e0cdaed732f4af77a44c10f5f Mon Sep 17 00:00:00 2001 From: Christian Borntraeger Date: Fri, 8 Apr 2016 17:52:39 +0200 Subject: KVM: s390: use switch vs jump table in priv.c Instead of having huge jump tables for function selection, let's use normal switch/case statements for the instruction handlers in priv.c This allows the compiler to make the right decision depending on the situation (e.g. avoid jump-tables for thunks). Signed-off-by: Christian Borntraeger Reviewed-by: Cornelia Huck Reviewed-by: Janosch Frank Reviewed-by: David Hildenbrand Signed-off-by: Christian Borntraeger --- arch/s390/kvm/priv.c | 183 +++++++++++++++++++++++++-------------------------- 1 file changed, 91 insertions(+), 92 deletions(-) (limited to 'arch') diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c index c4c4e157c036..a74578cdd3f3 100644 --- a/arch/s390/kvm/priv.c +++ b/arch/s390/kvm/priv.c @@ -795,55 +795,60 @@ out: return rc; } -static const intercept_handler_t b2_handlers[256] = { - [0x02] = handle_stidp, - [0x04] = handle_set_clock, - [0x10] = handle_set_prefix, - [0x11] = handle_store_prefix, - [0x12] = handle_store_cpu_address, - [0x14] = kvm_s390_handle_vsie, - [0x21] = handle_ipte_interlock, - [0x29] = handle_iske, - [0x2a] = handle_rrbe, - [0x2b] = handle_sske, - [0x2c] = handle_test_block, - [0x30] = handle_io_inst, - [0x31] = handle_io_inst, - [0x32] = handle_io_inst, - [0x33] = handle_io_inst, - [0x34] = handle_io_inst, - [0x35] = handle_io_inst, - [0x36] = handle_io_inst, - [0x37] = handle_io_inst, - [0x38] = handle_io_inst, - [0x39] = handle_io_inst, - [0x3a] = handle_io_inst, - [0x3b] = handle_io_inst, - [0x3c] = handle_io_inst, - [0x50] = handle_ipte_interlock, - [0x56] = handle_sthyi, - [0x5f] = handle_io_inst, - [0x74] = handle_io_inst, - [0x76] = handle_io_inst, - [0x7d] = handle_stsi, - [0xb1] = handle_stfl, - [0xb2] = handle_lpswe, -}; - int kvm_s390_handle_b2(struct kvm_vcpu *vcpu) { - intercept_handler_t handler; - - /* - * A lot of B2 instructions are priviledged. Here we check for - * the privileged ones, that we can handle in the kernel. - * Anything else goes to userspace. - */ - handler = b2_handlers[vcpu->arch.sie_block->ipa & 0x00ff]; - if (handler) - return handler(vcpu); - - return -EOPNOTSUPP; + switch (vcpu->arch.sie_block->ipa & 0x00ff) { + case 0x02: + return handle_stidp(vcpu); + case 0x04: + return handle_set_clock(vcpu); + case 0x10: + return handle_set_prefix(vcpu); + case 0x11: + return handle_store_prefix(vcpu); + case 0x12: + return handle_store_cpu_address(vcpu); + case 0x14: + return kvm_s390_handle_vsie(vcpu); + case 0x21: + case 0x50: + return handle_ipte_interlock(vcpu); + case 0x29: + return handle_iske(vcpu); + case 0x2a: + return handle_rrbe(vcpu); + case 0x2b: + return handle_sske(vcpu); + case 0x2c: + return handle_test_block(vcpu); + case 0x30: + case 0x31: + case 0x32: + case 0x33: + case 0x34: + case 0x35: + case 0x36: + case 0x37: + case 0x38: + case 0x39: + case 0x3a: + case 0x3b: + case 0x3c: + case 0x5f: + case 0x74: + case 0x76: + return handle_io_inst(vcpu); + case 0x56: + return handle_sthyi(vcpu); + case 0x7d: + return handle_stsi(vcpu); + case 0xb1: + return handle_stfl(vcpu); + case 0xb2: + return handle_lpswe(vcpu); + default: + return -EOPNOTSUPP; + } } static int handle_epsw(struct kvm_vcpu *vcpu) @@ -1105,25 +1110,22 @@ static int handle_essa(struct kvm_vcpu *vcpu) return 0; } -static const intercept_handler_t b9_handlers[256] = { - [0x8a] = handle_ipte_interlock, - [0x8d] = handle_epsw, - [0x8e] = handle_ipte_interlock, - [0x8f] = handle_ipte_interlock, - [0xab] = handle_essa, - [0xaf] = handle_pfmf, -}; - int kvm_s390_handle_b9(struct kvm_vcpu *vcpu) { - intercept_handler_t handler; - - /* This is handled just as for the B2 instructions. */ - handler = b9_handlers[vcpu->arch.sie_block->ipa & 0x00ff]; - if (handler) - return handler(vcpu); - - return -EOPNOTSUPP; + switch (vcpu->arch.sie_block->ipa & 0x00ff) { + case 0x8a: + case 0x8e: + case 0x8f: + return handle_ipte_interlock(vcpu); + case 0x8d: + return handle_epsw(vcpu); + case 0xab: + return handle_essa(vcpu); + case 0xaf: + return handle_pfmf(vcpu); + default: + return -EOPNOTSUPP; + } } int kvm_s390_handle_lctl(struct kvm_vcpu *vcpu) @@ -1271,22 +1273,20 @@ static int handle_stctg(struct kvm_vcpu *vcpu) return rc ? kvm_s390_inject_prog_cond(vcpu, rc) : 0; } -static const intercept_handler_t eb_handlers[256] = { - [0x2f] = handle_lctlg, - [0x25] = handle_stctg, - [0x60] = handle_ri, - [0x61] = handle_ri, - [0x62] = handle_ri, -}; - int kvm_s390_handle_eb(struct kvm_vcpu *vcpu) { - intercept_handler_t handler; - - handler = eb_handlers[vcpu->arch.sie_block->ipb & 0xff]; - if (handler) - return handler(vcpu); - return -EOPNOTSUPP; + switch (vcpu->arch.sie_block->ipb & 0x000000ff) { + case 0x25: + return handle_stctg(vcpu); + case 0x2f: + return handle_lctlg(vcpu); + case 0x60: + case 0x61: + case 0x62: + return handle_ri(vcpu); + default: + return -EOPNOTSUPP; + } } static int handle_tprot(struct kvm_vcpu *vcpu) @@ -1346,10 +1346,12 @@ out_unlock: int kvm_s390_handle_e5(struct kvm_vcpu *vcpu) { - /* For e5xx... instructions we only handle TPROT */ - if ((vcpu->arch.sie_block->ipa & 0x00ff) == 0x01) + switch (vcpu->arch.sie_block->ipa & 0x00ff) { + case 0x01: return handle_tprot(vcpu); - return -EOPNOTSUPP; + default: + return -EOPNOTSUPP; + } } static int handle_sckpf(struct kvm_vcpu *vcpu) @@ -1380,17 +1382,14 @@ static int handle_ptff(struct kvm_vcpu *vcpu) return 0; } -static const intercept_handler_t x01_handlers[256] = { - [0x04] = handle_ptff, - [0x07] = handle_sckpf, -}; - int kvm_s390_handle_01(struct kvm_vcpu *vcpu) { - intercept_handler_t handler; - - handler = x01_handlers[vcpu->arch.sie_block->ipa & 0x00ff]; - if (handler) - return handler(vcpu); - return -EOPNOTSUPP; + switch (vcpu->arch.sie_block->ipa & 0x00ff) { + case 0x04: + return handle_ptff(vcpu); + case 0x07: + return handle_sckpf(vcpu); + default: + return -EOPNOTSUPP; + } } -- cgit v1.2.3-55-g7522 From cb7485da3ed1ac4ef6c71d4b2b715f8b87f118c8 Mon Sep 17 00:00:00 2001 From: Christian Borntraeger Date: Tue, 6 Feb 2018 10:19:28 +0000 Subject: KVM: s390: use switch vs jump table in intercept.c Instead of having huge jump tables for function selection, let's use normal switch/case statements for the instruction handlers in intercept.c We can now also get rid of intercept_handler_t. This allows the compiler to make the right decision depending on the situation (e.g. avoid jump-tables for thunks). Signed-off-by: Christian Borntraeger Reviewed-by: Janosch Frank Reviewed-by: David Hildenbrand Reviewed-by: Cornelia Huck Signed-off-by: Christian Borntraeger --- arch/s390/kvm/intercept.c | 51 +++++++++++++++++++++++++++-------------------- arch/s390/kvm/kvm-s390.h | 2 -- 2 files changed, 29 insertions(+), 24 deletions(-) (limited to 'arch') diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c index 9c7d70715862..07c6e81163bf 100644 --- a/arch/s390/kvm/intercept.c +++ b/arch/s390/kvm/intercept.c @@ -22,22 +22,6 @@ #include "trace.h" #include "trace-s390.h" - -static const intercept_handler_t instruction_handlers[256] = { - [0x01] = kvm_s390_handle_01, - [0x82] = kvm_s390_handle_lpsw, - [0x83] = kvm_s390_handle_diag, - [0xaa] = kvm_s390_handle_aa, - [0xae] = kvm_s390_handle_sigp, - [0xb2] = kvm_s390_handle_b2, - [0xb6] = kvm_s390_handle_stctl, - [0xb7] = kvm_s390_handle_lctl, - [0xb9] = kvm_s390_handle_b9, - [0xe3] = kvm_s390_handle_e3, - [0xe5] = kvm_s390_handle_e5, - [0xeb] = kvm_s390_handle_eb, -}; - u8 kvm_s390_get_ilen(struct kvm_vcpu *vcpu) { struct kvm_s390_sie_block *sie_block = vcpu->arch.sie_block; @@ -129,16 +113,39 @@ static int handle_validity(struct kvm_vcpu *vcpu) static int handle_instruction(struct kvm_vcpu *vcpu) { - intercept_handler_t handler; - vcpu->stat.exit_instruction++; trace_kvm_s390_intercept_instruction(vcpu, vcpu->arch.sie_block->ipa, vcpu->arch.sie_block->ipb); - handler = instruction_handlers[vcpu->arch.sie_block->ipa >> 8]; - if (handler) - return handler(vcpu); - return -EOPNOTSUPP; + + switch (vcpu->arch.sie_block->ipa >> 8) { + case 0x01: + return kvm_s390_handle_01(vcpu); + case 0x82: + return kvm_s390_handle_lpsw(vcpu); + case 0x83: + return kvm_s390_handle_diag(vcpu); + case 0xaa: + return kvm_s390_handle_aa(vcpu); + case 0xae: + return kvm_s390_handle_sigp(vcpu); + case 0xb2: + return kvm_s390_handle_b2(vcpu); + case 0xb6: + return kvm_s390_handle_stctl(vcpu); + case 0xb7: + return kvm_s390_handle_lctl(vcpu); + case 0xb9: + return kvm_s390_handle_b9(vcpu); + case 0xe3: + return kvm_s390_handle_e3(vcpu); + case 0xe5: + return kvm_s390_handle_e5(vcpu); + case 0xeb: + return kvm_s390_handle_eb(vcpu); + default: + return -EOPNOTSUPP; + } } static int inject_prog_on_prog_intercept(struct kvm_vcpu *vcpu) diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h index bd31b37b0e6f..3c0a975c2477 100644 --- a/arch/s390/kvm/kvm-s390.h +++ b/arch/s390/kvm/kvm-s390.h @@ -19,8 +19,6 @@ #include #include -typedef int (*intercept_handler_t)(struct kvm_vcpu *vcpu); - /* Transactional Memory Execution related macros */ #define IS_TE_ENABLED(vcpu) ((vcpu->arch.sie_block->ecb & ECB_TE)) #define TDB_FORMAT1 1 -- cgit v1.2.3-55-g7522 From baabee67f4135e3de87bc874929ac50637aacb0d Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Tue, 6 Feb 2018 15:17:43 +0100 Subject: KVM: s390: use switch vs jump table in interrupt.c Just like for the interception handlers, let's also use a switch-case in our interrupt delivery code. Signed-off-by: David Hildenbrand Message-Id: <20180206141743.24497-1-david@redhat.com> Reviewed-by: Cornelia Huck Reviewed-by: Janosch Frank Signed-off-by: Christian Borntraeger --- arch/s390/kvm/interrupt.c | 84 ++++++++++++++++++++++++++++------------------- 1 file changed, 50 insertions(+), 34 deletions(-) (limited to 'arch') diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index e399495001ca..3f2c49b1a393 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -187,12 +187,6 @@ static int cpu_timer_irq_pending(struct kvm_vcpu *vcpu) return kvm_s390_get_cpu_timer(vcpu) >> 63; } -static inline int is_ioirq(unsigned long irq_type) -{ - return ((irq_type >= IRQ_PEND_IO_ISC_7) && - (irq_type <= IRQ_PEND_IO_ISC_0)); -} - static uint64_t isc_to_isc_bits(int isc) { return (0x80 >> isc) << 24; @@ -1016,24 +1010,6 @@ out: return rc; } -typedef int (*deliver_irq_t)(struct kvm_vcpu *vcpu); - -static const deliver_irq_t deliver_irq_funcs[] = { - [IRQ_PEND_MCHK_EX] = __deliver_machine_check, - [IRQ_PEND_MCHK_REP] = __deliver_machine_check, - [IRQ_PEND_PROG] = __deliver_prog, - [IRQ_PEND_EXT_EMERGENCY] = __deliver_emergency_signal, - [IRQ_PEND_EXT_EXTERNAL] = __deliver_external_call, - [IRQ_PEND_EXT_CLOCK_COMP] = __deliver_ckc, - [IRQ_PEND_EXT_CPU_TIMER] = __deliver_cpu_timer, - [IRQ_PEND_RESTART] = __deliver_restart, - [IRQ_PEND_SET_PREFIX] = __deliver_set_prefix, - [IRQ_PEND_PFAULT_INIT] = __deliver_pfault_init, - [IRQ_PEND_EXT_SERVICE] = __deliver_service, - [IRQ_PEND_PFAULT_DONE] = __deliver_pfault_done, - [IRQ_PEND_VIRTIO] = __deliver_virtio, -}; - /* Check whether an external call is pending (deliverable or not) */ int kvm_s390_ext_call_pending(struct kvm_vcpu *vcpu) { @@ -1197,7 +1173,6 @@ void kvm_s390_clear_local_irqs(struct kvm_vcpu *vcpu) int __must_check kvm_s390_deliver_pending_interrupts(struct kvm_vcpu *vcpu) { struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; - deliver_irq_t func; int rc = 0; unsigned long irq_type; unsigned long irqs; @@ -1217,16 +1192,57 @@ int __must_check kvm_s390_deliver_pending_interrupts(struct kvm_vcpu *vcpu) while ((irqs = deliverable_irqs(vcpu)) && !rc) { /* bits are in the reverse order of interrupt priority */ irq_type = find_last_bit(&irqs, IRQ_PEND_COUNT); - if (is_ioirq(irq_type)) { + switch (irq_type) { + case IRQ_PEND_IO_ISC_0: + case IRQ_PEND_IO_ISC_1: + case IRQ_PEND_IO_ISC_2: + case IRQ_PEND_IO_ISC_3: + case IRQ_PEND_IO_ISC_4: + case IRQ_PEND_IO_ISC_5: + case IRQ_PEND_IO_ISC_6: + case IRQ_PEND_IO_ISC_7: rc = __deliver_io(vcpu, irq_type); - } else { - func = deliver_irq_funcs[irq_type]; - if (!func) { - WARN_ON_ONCE(func == NULL); - clear_bit(irq_type, &li->pending_irqs); - continue; - } - rc = func(vcpu); + break; + case IRQ_PEND_MCHK_EX: + case IRQ_PEND_MCHK_REP: + rc = __deliver_machine_check(vcpu); + break; + case IRQ_PEND_PROG: + rc = __deliver_prog(vcpu); + break; + case IRQ_PEND_EXT_EMERGENCY: + rc = __deliver_emergency_signal(vcpu); + break; + case IRQ_PEND_EXT_EXTERNAL: + rc = __deliver_external_call(vcpu); + break; + case IRQ_PEND_EXT_CLOCK_COMP: + rc = __deliver_ckc(vcpu); + break; + case IRQ_PEND_EXT_CPU_TIMER: + rc = __deliver_cpu_timer(vcpu); + break; + case IRQ_PEND_RESTART: + rc = __deliver_restart(vcpu); + break; + case IRQ_PEND_SET_PREFIX: + rc = __deliver_set_prefix(vcpu); + break; + case IRQ_PEND_PFAULT_INIT: + rc = __deliver_pfault_init(vcpu); + break; + case IRQ_PEND_EXT_SERVICE: + rc = __deliver_service(vcpu); + break; + case IRQ_PEND_PFAULT_DONE: + rc = __deliver_pfault_done(vcpu); + break; + case IRQ_PEND_VIRTIO: + rc = __deliver_virtio(vcpu); + break; + default: + WARN_ONCE(1, "Unknown pending irq type %ld", irq_type); + clear_bit(irq_type, &li->pending_irqs); } } -- cgit v1.2.3-55-g7522 From db35340c536f1af0108ec9a0b2126a05d358d14a Mon Sep 17 00:00:00 2001 From: Qi Hou Date: Thu, 11 Jan 2018 12:54:43 +0800 Subject: ARM: OMAP2+: timer: fix a kmemleak caused in omap_get_timer_dt When more than one GP timers are used as kernel system timers and the corresponding nodes in device-tree are marked with the same "disabled" property, then the "attr" field of the property will be initialized more than once as the property being added to sys file system via __of_add_property_sysfs(). In __of_add_property_sysfs(), the "name" field of pp->attr.attr is set directly to the return value of safe_name(), without taking care of whether it's already a valid pointer to a memory block. If it is, its old value will always be overwritten by the new one and the memory block allocated before will a "ghost", then a kmemleak happened. That the same "disabled" property being added to different nodes of device tree would cause that kind of kmemleak overhead, at least once. To fix it, allocate the property dynamically, and delete static one. Signed-off-by: Qi Hou Signed-off-by: Tony Lindgren --- arch/arm/mach-omap2/timer.c | 19 +++++++++++-------- 1 file changed, 11 insertions(+), 8 deletions(-) (limited to 'arch') diff --git a/arch/arm/mach-omap2/timer.c b/arch/arm/mach-omap2/timer.c index ece09c9461f7..d61fbd7a2840 100644 --- a/arch/arm/mach-omap2/timer.c +++ b/arch/arm/mach-omap2/timer.c @@ -156,12 +156,6 @@ static struct clock_event_device clockevent_gpt = { .tick_resume = omap2_gp_timer_shutdown, }; -static struct property device_disabled = { - .name = "status", - .length = sizeof("disabled"), - .value = "disabled", -}; - static const struct of_device_id omap_timer_match[] __initconst = { { .compatible = "ti,omap2420-timer", }, { .compatible = "ti,omap3430-timer", }, @@ -203,8 +197,17 @@ static struct device_node * __init omap_get_timer_dt(const struct of_device_id * of_get_property(np, "ti,timer-secure", NULL))) continue; - if (!of_device_is_compatible(np, "ti,omap-counter32k")) - of_add_property(np, &device_disabled); + if (!of_device_is_compatible(np, "ti,omap-counter32k")) { + struct property *prop; + + prop = kzalloc(sizeof(*prop), GFP_KERNEL); + if (!prop) + return NULL; + prop->name = "status"; + prop->value = "disabled"; + prop->length = strlen(prop->value); + of_add_property(np, prop); + } return np; } -- cgit v1.2.3-55-g7522 From d3be6d2a08bd26580562d9714d3d97ea9ba22c73 Mon Sep 17 00:00:00 2001 From: Tony Lindgren Date: Fri, 9 Feb 2018 08:15:53 -0800 Subject: ARM: OMAP3: Fix prm wake interrupt for resume For platform_suspend_ops, the finish call is too late to re-enable wake irqs and we need re-enable wake irqs on wake call instead. Otherwise noirq resume for devices has already happened. And then dev_pm_disarm_wake_irq() has already disabled the dedicated wake irqs when the interrupt triggers and the wake irq is never handled. For devices that are already in PM runtime suspended state when we enter suspend this means that a possible wake irq will never trigger. And this can lead into a situation where a device has a pending padconf wake irq, and the device will stay unresponsive to any further wake irqs. This issue can be easily reproduced by setting serial console log level to zero, letting the serial console idle, and suspend the system from an ssh terminal. Then try to wake up the system by typing to the serial console. Note that this affects only omap3 PRM interrupt as that's currently the only omap variant that does anything in omap_pm_wake(). In general, for the wake irqs to work, the interrupt must have either IRQF_NO_SUSPEND or IRQF_EARLY_RESUME set for it to trigger before dev_pm_disarm_wake_irq() disables the wake irqs. Reported-by: Grygorii Strashko Cc: Tero Kristo Signed-off-by: Tony Lindgren --- arch/arm/mach-omap2/pm.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch') diff --git a/arch/arm/mach-omap2/pm.c b/arch/arm/mach-omap2/pm.c index 366158a54fcd..6f68576e5695 100644 --- a/arch/arm/mach-omap2/pm.c +++ b/arch/arm/mach-omap2/pm.c @@ -186,7 +186,7 @@ static void omap_pm_end(void) cpu_idle_poll_ctrl(false); } -static void omap_pm_finish(void) +static void omap_pm_wake(void) { if (soc_is_omap34xx()) omap_prcm_irq_complete(); @@ -196,7 +196,7 @@ static const struct platform_suspend_ops omap_pm_ops = { .begin = omap_pm_begin, .end = omap_pm_end, .enter = omap_pm_enter, - .finish = omap_pm_finish, + .wake = omap_pm_wake, .valid = suspend_valid_only_mem, }; -- cgit v1.2.3-55-g7522 From fe27f16794f313f5fc16f6d2f42d8c2b2f4d70cc Mon Sep 17 00:00:00 2001 From: Tony Lindgren Date: Fri, 9 Feb 2018 09:35:56 -0800 Subject: ARM: OMAP2+: Fix sar_base inititalization for HS omaps HS omaps use irq_save_secure_context() instead of irq_save_context() so sar_base will never get initialized and irq_sar_clear() gets called with a wrong address for HS omaps from irq_restore_context(). Starting with commit f4b9f40ae95b ("ARM: OMAP4+: Initialize SAR RAM base early for proper CPU1 reset for kexec") we have it available, and this ideally would been fixed with that commit already. Fixes: f4b9f40ae95b ("ARM: OMAP4+: Initialize SAR RAM base early for proper CPU1 reset for kexec") Cc: Andrew F. Davis Cc: Dave Gerlach Cc: Keerthy Cc: Santosh Shilimkar Cc: Tero Kristo Signed-off-by: Tony Lindgren --- arch/arm/mach-omap2/omap-wakeupgen.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch') diff --git a/arch/arm/mach-omap2/omap-wakeupgen.c b/arch/arm/mach-omap2/omap-wakeupgen.c index 4bb6751864a5..fc5fb776a710 100644 --- a/arch/arm/mach-omap2/omap-wakeupgen.c +++ b/arch/arm/mach-omap2/omap-wakeupgen.c @@ -299,8 +299,6 @@ static void irq_save_context(void) if (soc_is_dra7xx()) return; - if (!sar_base) - sar_base = omap4_get_sar_ram_base(); if (wakeupgen_ops && wakeupgen_ops->save_context) wakeupgen_ops->save_context(); } @@ -598,6 +596,8 @@ static int __init wakeupgen_init(struct device_node *node, irq_hotplug_init(); irq_pm_init(); + sar_base = omap4_get_sar_ram_base(); + return 0; } IRQCHIP_DECLARE(ti_wakeupgen, "ti,omap4-wugen-mpu", wakeupgen_init); -- cgit v1.2.3-55-g7522 From 8cbbf1745dcde7ba7e423dc70619d223de90fd43 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Tue, 2 Jan 2018 16:25:35 +0100 Subject: ARM: OMAP1: clock: Fix debugfs_create_*() usage When exposing data access through debugfs, the correct debugfs_create_*() functions must be used, depending on data type. Remove all casts from data pointers passed to debugfs_create_*() functions, as such casts prevent the compiler from flagging bugs. Correct all wrong usage: - clk.rate is unsigned long, not u32, - clk.flags is u8, not u32, which exposed the successive clk.rate_offset and clk.src_offset fields. Signed-off-by: Geert Uytterhoeven Acked-by: Aaro Koskinen Signed-off-by: Tony Lindgren --- arch/arm/mach-omap1/clock.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'arch') diff --git a/arch/arm/mach-omap1/clock.c b/arch/arm/mach-omap1/clock.c index 43e3e188f521..fa512413a471 100644 --- a/arch/arm/mach-omap1/clock.c +++ b/arch/arm/mach-omap1/clock.c @@ -1011,17 +1011,17 @@ static int clk_debugfs_register_one(struct clk *c) return -ENOMEM; c->dent = d; - d = debugfs_create_u8("usecount", S_IRUGO, c->dent, (u8 *)&c->usecount); + d = debugfs_create_u8("usecount", S_IRUGO, c->dent, &c->usecount); if (!d) { err = -ENOMEM; goto err_out; } - d = debugfs_create_u32("rate", S_IRUGO, c->dent, (u32 *)&c->rate); + d = debugfs_create_ulong("rate", S_IRUGO, c->dent, &c->rate); if (!d) { err = -ENOMEM; goto err_out; } - d = debugfs_create_x32("flags", S_IRUGO, c->dent, (u32 *)&c->flags); + d = debugfs_create_x8("flags", S_IRUGO, c->dent, &c->flags); if (!d) { err = -ENOMEM; goto err_out; -- cgit v1.2.3-55-g7522 From 64116257144bfbe744dd5b41bb0d160ccf65e339 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Tue, 13 Feb 2018 15:15:33 +0100 Subject: ARM: dts: OMAP5: uevm: Fix "debounce-interval" property misspelling "debounce_interval" was never supported. Signed-off-by: Geert Uytterhoeven Cc: Benoît Cousson Signed-off-by: Tony Lindgren --- arch/arm/boot/dts/omap5-uevm.dts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/arm/boot/dts/omap5-uevm.dts b/arch/arm/boot/dts/omap5-uevm.dts index ec2c8baef62a..592e17fd4eeb 100644 --- a/arch/arm/boot/dts/omap5-uevm.dts +++ b/arch/arm/boot/dts/omap5-uevm.dts @@ -47,7 +47,7 @@ gpios = <&gpio3 19 GPIO_ACTIVE_LOW>; /* gpio3_83 */ wakeup-source; autorepeat; - debounce_interval = <50>; + debounce-interval = <50>; }; }; -- cgit v1.2.3-55-g7522 From 74402055a2d3ec998a1ded599e86185a27d9bbf4 Mon Sep 17 00:00:00 2001 From: Adam Ford Date: Thu, 25 Jan 2018 14:10:37 -0600 Subject: ARM: dts: LogicPD Torpedo: Fix I2C1 pinmux The pinmuxing was missing for I2C1 which was causing intermittent issues with the PMIC which is connected to I2C1. The bootloader did not quite configure the I2C1 either, so when running at 2.6MHz, it was generating errors at time. This correctly sets the I2C1 pinmuxing so it can operate at 2.6MHz Fixes: 687c27676151 ("ARM: dts: Add minimal support for LogicPD Torpedo DM3730 devkit") Signed-off-by: Adam Ford Signed-off-by: Tony Lindgren --- arch/arm/boot/dts/logicpd-torpedo-som.dtsi | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'arch') diff --git a/arch/arm/boot/dts/logicpd-torpedo-som.dtsi b/arch/arm/boot/dts/logicpd-torpedo-som.dtsi index b50b796e15c7..47915447a826 100644 --- a/arch/arm/boot/dts/logicpd-torpedo-som.dtsi +++ b/arch/arm/boot/dts/logicpd-torpedo-som.dtsi @@ -66,6 +66,8 @@ }; &i2c1 { + pinctrl-names = "default"; + pinctrl-0 = <&i2c1_pins>; clock-frequency = <2600000>; twl: twl@48 { @@ -136,6 +138,12 @@ OMAP3_CORE1_IOPAD(0x21b8, PIN_INPUT | MUX_MODE0) /* hsusb0_data7.hsusb0_data7 */ >; }; + i2c1_pins: pinmux_i2c1_pins { + pinctrl-single,pins = < + OMAP3_CORE1_IOPAD(0x21ba, PIN_INPUT | MUX_MODE0) /* i2c1_scl.i2c1_scl */ + OMAP3_CORE1_IOPAD(0x21bc, PIN_INPUT | MUX_MODE0) /* i2c1_sda.i2c1_sda */ + >; + }; }; &uart2 { -- cgit v1.2.3-55-g7522 From 84c7efd607e7fb6933920322086db64654f669b2 Mon Sep 17 00:00:00 2001 From: Adam Ford Date: Sat, 27 Jan 2018 15:27:05 -0600 Subject: ARM: dts: LogicPD SOM-LV: Fix I2C1 pinmux The pinmuxing was missing for I2C1 which was causing intermittent issues with the PMIC which is connected to I2C1. The bootloader did not quite configure the I2C1 either, so when running at 2.6MHz, it was generating errors at times. This correctly sets the I2C1 pinmuxing so it can operate at 2.6MHz Fixes: ab8dd3aed011 ("ARM: DTS: Add minimal Support for Logic PD DM3730 SOM-LV") Signed-off-by: Adam Ford Signed-off-by: Tony Lindgren --- arch/arm/boot/dts/logicpd-som-lv.dtsi | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/arm/boot/dts/logicpd-som-lv.dtsi b/arch/arm/boot/dts/logicpd-som-lv.dtsi index c1aa7a4518fb..a30ee9fcb3ae 100644 --- a/arch/arm/boot/dts/logicpd-som-lv.dtsi +++ b/arch/arm/boot/dts/logicpd-som-lv.dtsi @@ -71,6 +71,8 @@ }; &i2c1 { + pinctrl-names = "default"; + pinctrl-0 = <&i2c1_pins>; clock-frequency = <2600000>; twl: twl@48 { @@ -189,7 +191,12 @@ >; }; - + i2c1_pins: pinmux_i2c1_pins { + pinctrl-single,pins = < + OMAP3_CORE1_IOPAD(0x21ba, PIN_INPUT | MUX_MODE0) /* i2c1_scl.i2c1_scl */ + OMAP3_CORE1_IOPAD(0x21bc, PIN_INPUT | MUX_MODE0) /* i2c1_sda.i2c1_sda */ + >; + }; }; &omap3_pmx_wkup { -- cgit v1.2.3-55-g7522 From 2ce77f6d8a9ae9ce6d80397d88bdceb84a2004cd Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Tue, 13 Feb 2018 13:14:09 +0000 Subject: arm64: proc: Set PTE_NG for table entries to avoid traversing them twice When KASAN is enabled, the swapper page table contains many identical mappings of the zero page, which can lead to a stall during boot whilst the G -> nG code continually walks the same page table entries looking for global mappings. This patch sets the nG bit (bit 11, which is IGNORED) in table entries after processing the subtree so we can easily skip them if we see them a second time. Tested-by: Mark Rutland Signed-off-by: Will Deacon Signed-off-by: Catalin Marinas --- arch/arm64/mm/proc.S | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) (limited to 'arch') diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S index 71baed7e592a..c0af47617299 100644 --- a/arch/arm64/mm/proc.S +++ b/arch/arm64/mm/proc.S @@ -205,7 +205,8 @@ ENDPROC(idmap_cpu_replace_ttbr1) dc cvac, cur_\()\type\()p // Ensure any existing dirty dmb sy // lines are written back before ldr \type, [cur_\()\type\()p] // loading the entry - tbz \type, #0, next_\()\type // Skip invalid entries + tbz \type, #0, skip_\()\type // Skip invalid and + tbnz \type, #11, skip_\()\type // non-global entries .endm .macro __idmap_kpti_put_pgtable_ent_ng, type @@ -265,8 +266,9 @@ ENTRY(idmap_kpti_install_ng_mappings) add end_pgdp, cur_pgdp, #(PTRS_PER_PGD * 8) do_pgd: __idmap_kpti_get_pgtable_ent pgd tbnz pgd, #1, walk_puds - __idmap_kpti_put_pgtable_ent_ng pgd next_pgd: + __idmap_kpti_put_pgtable_ent_ng pgd +skip_pgd: add cur_pgdp, cur_pgdp, #8 cmp cur_pgdp, end_pgdp b.ne do_pgd @@ -294,8 +296,9 @@ walk_puds: add end_pudp, cur_pudp, #(PTRS_PER_PUD * 8) do_pud: __idmap_kpti_get_pgtable_ent pud tbnz pud, #1, walk_pmds - __idmap_kpti_put_pgtable_ent_ng pud next_pud: + __idmap_kpti_put_pgtable_ent_ng pud +skip_pud: add cur_pudp, cur_pudp, 8 cmp cur_pudp, end_pudp b.ne do_pud @@ -314,8 +317,9 @@ walk_pmds: add end_pmdp, cur_pmdp, #(PTRS_PER_PMD * 8) do_pmd: __idmap_kpti_get_pgtable_ent pmd tbnz pmd, #1, walk_ptes - __idmap_kpti_put_pgtable_ent_ng pmd next_pmd: + __idmap_kpti_put_pgtable_ent_ng pmd +skip_pmd: add cur_pmdp, cur_pmdp, #8 cmp cur_pmdp, end_pmdp b.ne do_pmd @@ -333,7 +337,7 @@ walk_ptes: add end_ptep, cur_ptep, #(PTRS_PER_PTE * 8) do_pte: __idmap_kpti_get_pgtable_ent pte __idmap_kpti_put_pgtable_ent_ng pte -next_pte: +skip_pte: add cur_ptep, cur_ptep, #8 cmp cur_ptep, end_ptep b.ne do_pte -- cgit v1.2.3-55-g7522 From c134f0d57a47b7f8704dee1cefc246f9471f3e80 Mon Sep 17 00:00:00 2001 From: Cyril Bur Date: Wed, 14 Feb 2018 14:27:06 +1100 Subject: powerpc: Expose TSCR via sysfs only on powernv The TSCR can only be accessed in hypervisor mode. Fixes: 88b5e12eeb11 ("powerpc: Expose TSCR via sysfs") Signed-off-by: Cyril Bur Signed-off-by: Michael Ellerman --- arch/powerpc/kernel/sysfs.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'arch') diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c index 5a8bfee6e187..04d0bbd7a1dd 100644 --- a/arch/powerpc/kernel/sysfs.c +++ b/arch/powerpc/kernel/sysfs.c @@ -788,7 +788,8 @@ static int register_cpu_online(unsigned int cpu) if (cpu_has_feature(CPU_FTR_PPCAS_ARCH_V2)) device_create_file(s, &dev_attr_pir); - if (cpu_has_feature(CPU_FTR_ARCH_206)) + if (cpu_has_feature(CPU_FTR_ARCH_206) && + !firmware_has_feature(FW_FEATURE_LPAR)) device_create_file(s, &dev_attr_tscr); #endif /* CONFIG_PPC64 */ @@ -873,7 +874,8 @@ static int unregister_cpu_online(unsigned int cpu) if (cpu_has_feature(CPU_FTR_PPCAS_ARCH_V2)) device_remove_file(s, &dev_attr_pir); - if (cpu_has_feature(CPU_FTR_ARCH_206)) + if (cpu_has_feature(CPU_FTR_ARCH_206) && + !firmware_has_feature(FW_FEATURE_LPAR)) device_remove_file(s, &dev_attr_tscr); #endif /* CONFIG_PPC64 */ -- cgit v1.2.3-55-g7522 From 8e036c8d30a2cd9d8fc7442fbf6824e0a3e986e7 Mon Sep 17 00:00:00 2001 From: Cédric Le Goater Date: Tue, 13 Feb 2018 09:47:12 +0100 Subject: powerpc/xive: Use hw CPU ids when configuring the CPU queues The CPU event notification queues on sPAPR should be configured using a hardware CPU identifier. The problem did not show up on the Power Hypervisor because pHyp supports 8 threads per core which keeps CPU number contiguous. This is not the case on all sPAPR virtual machines, some use SMT=1. Also improve error logging by adding the CPU number. Fixes: eac1e731b59e ("powerpc/xive: guest exploitation of the XIVE interrupt controller") Cc: stable@vger.kernel.org # v4.14+ Signed-off-by: Cédric Le Goater Signed-off-by: Michael Ellerman --- arch/powerpc/sysdev/xive/spapr.c | 16 ++++++++++------ 1 file changed, 10 insertions(+), 6 deletions(-) (limited to 'arch') diff --git a/arch/powerpc/sysdev/xive/spapr.c b/arch/powerpc/sysdev/xive/spapr.c index d9c4c9366049..091f1d0d0af1 100644 --- a/arch/powerpc/sysdev/xive/spapr.c +++ b/arch/powerpc/sysdev/xive/spapr.c @@ -356,7 +356,8 @@ static int xive_spapr_configure_queue(u32 target, struct xive_q *q, u8 prio, rc = plpar_int_get_queue_info(0, target, prio, &esn_page, &esn_size); if (rc) { - pr_err("Error %lld getting queue info prio %d\n", rc, prio); + pr_err("Error %lld getting queue info CPU %d prio %d\n", rc, + target, prio); rc = -EIO; goto fail; } @@ -370,7 +371,8 @@ static int xive_spapr_configure_queue(u32 target, struct xive_q *q, u8 prio, /* Configure and enable the queue in HW */ rc = plpar_int_set_queue_config(flags, target, prio, qpage_phys, order); if (rc) { - pr_err("Error %lld setting queue for prio %d\n", rc, prio); + pr_err("Error %lld setting queue for CPU %d prio %d\n", rc, + target, prio); rc = -EIO; } else { q->qpage = qpage; @@ -389,8 +391,8 @@ static int xive_spapr_setup_queue(unsigned int cpu, struct xive_cpu *xc, if (IS_ERR(qpage)) return PTR_ERR(qpage); - return xive_spapr_configure_queue(cpu, q, prio, qpage, - xive_queue_shift); + return xive_spapr_configure_queue(get_hard_smp_processor_id(cpu), + q, prio, qpage, xive_queue_shift); } static void xive_spapr_cleanup_queue(unsigned int cpu, struct xive_cpu *xc, @@ -399,10 +401,12 @@ static void xive_spapr_cleanup_queue(unsigned int cpu, struct xive_cpu *xc, struct xive_q *q = &xc->queue[prio]; unsigned int alloc_order; long rc; + int hw_cpu = get_hard_smp_processor_id(cpu); - rc = plpar_int_set_queue_config(0, cpu, prio, 0, 0); + rc = plpar_int_set_queue_config(0, hw_cpu, prio, 0, 0); if (rc) - pr_err("Error %ld setting queue for prio %d\n", rc, prio); + pr_err("Error %ld setting queue for CPU %d prio %d\n", rc, + hw_cpu, prio); alloc_order = xive_alloc_order(xive_queue_shift); free_pages((unsigned long)q->qpage, alloc_order); -- cgit v1.2.3-55-g7522 From e7bde88cdb4f0e432398a7d29ca2a15d2c18952a Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Tue, 13 Feb 2018 17:45:11 +1000 Subject: powerpc/powernv: IMC fix out of bounds memory access at shutdown The OPAL IMC driver's shutdown handler disables nest PMU counters by walking nodes and taking the first CPU out of their cpumask, which is used to index into the paca (get_hard_smp_processor_id()). This does not always do the right thing, and in particular for CPU-less nodes it returns NR_CPUS and that overruns the paca and dereferences random memory. Fix it by being more careful about checking returned CPU, and only using online CPUs. It's not clear this shutdown code makes sense after commit 885dcd709b ("powerpc/perf: Add nest IMC PMU support"), but this should not make things worse Currently the bug causes us to call OPAL with a junk CPU number. A separate patch in development to change the way pacas are allocated escalates this bug into a crash: Unable to handle kernel paging request for data at address 0x2a21af1eeb000076 Faulting instruction address: 0xc0000000000a5468 Oops: Kernel access of bad area, sig: 11 [#1] ... NIP opal_imc_counters_shutdown+0x148/0x1d0 LR opal_imc_counters_shutdown+0x134/0x1d0 Call Trace: opal_imc_counters_shutdown+0x134/0x1d0 (unreliable) platform_drv_shutdown+0x44/0x60 device_shutdown+0x1f8/0x350 kernel_restart_prepare+0x54/0x70 kernel_restart+0x28/0xc0 SyS_reboot+0x1d0/0x2c0 system_call+0x58/0x6c Signed-off-by: Nicholas Piggin Signed-off-by: Michael Ellerman --- arch/powerpc/platforms/powernv/opal-imc.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'arch') diff --git a/arch/powerpc/platforms/powernv/opal-imc.c b/arch/powerpc/platforms/powernv/opal-imc.c index dd4c9b8b8a81..f6f55ab4980e 100644 --- a/arch/powerpc/platforms/powernv/opal-imc.c +++ b/arch/powerpc/platforms/powernv/opal-imc.c @@ -199,9 +199,11 @@ static void disable_nest_pmu_counters(void) const struct cpumask *l_cpumask; get_online_cpus(); - for_each_online_node(nid) { + for_each_node_with_cpus(nid) { l_cpumask = cpumask_of_node(nid); - cpu = cpumask_first(l_cpumask); + cpu = cpumask_first_and(l_cpumask, cpu_online_mask); + if (cpu >= nr_cpu_ids) + continue; opal_imc_counters_stop(OPAL_IMC_COUNTERS_NEST, get_hard_smp_processor_id(cpu)); } -- cgit v1.2.3-55-g7522 From c1e150ceb61e4a585bad156da15c33bfe89f5858 Mon Sep 17 00:00:00 2001 From: Corentin Labbe Date: Wed, 14 Feb 2018 12:17:47 +0000 Subject: powerpc/pseries: Add empty update_numa_cpu_lookup_table() for NUMA=n When CONFIG_NUMA is not set, the build fails with: arch/powerpc/platforms/pseries/hotplug-cpu.c:335:4: error: déclaration implicite de la fonction « update_numa_cpu_lookup_table » So we have to add update_numa_cpu_lookup_table() as an empty function when CONFIG_NUMA is not set. Fixes: 1d9a090783be ("powerpc/numa: Invalidate numa_cpu_lookup_table on cpu remove") Signed-off-by: Corentin Labbe Signed-off-by: Michael Ellerman --- arch/powerpc/include/asm/topology.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'arch') diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h index 593248110902..9f421641a35c 100644 --- a/arch/powerpc/include/asm/topology.h +++ b/arch/powerpc/include/asm/topology.h @@ -81,6 +81,9 @@ static inline int numa_update_cpu_topology(bool cpus_locked) { return 0; } + +static inline void update_numa_cpu_lookup_table(unsigned int cpu, int node) {} + #endif /* CONFIG_NUMA */ #if defined(CONFIG_NUMA) && defined(CONFIG_PPC_SPLPAR) -- cgit v1.2.3-55-g7522 From 2b5db66862b95532cb6cca8165ae6eb73633cf85 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Thu, 8 Feb 2018 17:09:26 -0600 Subject: x86/debug, objtool: Annotate WARN()-related UD2 as reachable By default, objtool assumes that a UD2 is a dead end. This is mainly because GCC 7+ sometimes inserts a UD2 when it detects a divide-by-zero condition. Now that WARN() is moving back to UD2, annotate the code after it as reachable so objtool can follow the code flow. Reported-by: Borislav Petkov Signed-off-by: Josh Poimboeuf Signed-off-by: Peter Zijlstra (Intel) Cc: Andy Lutomirski Cc: Arjan van de Ven Cc: Brian Gerst Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: kbuild test robot Link: http://lkml.kernel.org/r/0e483379275a42626ba8898117f918e1bf661e40.1518130694.git.jpoimboe@redhat.com Signed-off-by: Ingo Molnar --- arch/x86/include/asm/bug.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/x86/include/asm/bug.h b/arch/x86/include/asm/bug.h index 34d99af43994..71e6f4bf9161 100644 --- a/arch/x86/include/asm/bug.h +++ b/arch/x86/include/asm/bug.h @@ -77,7 +77,11 @@ do { \ unreachable(); \ } while (0) -#define __WARN_FLAGS(flags) _BUG_FLAGS(ASM_UD0, BUGFLAG_WARNING|(flags)) +#define __WARN_FLAGS(flags) \ +do { \ + _BUG_FLAGS(ASM_UD0, BUGFLAG_WARNING|(flags)); \ + annotate_reachable(); \ +} while (0) #include -- cgit v1.2.3-55-g7522 From 3b3a371cc9bc980429baabe0a8e5f307f3d1f463 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 9 Feb 2018 13:16:59 +0100 Subject: x86/debug: Use UD2 for WARN() Since the Intel SDM added an ModR/M byte to UD0 and binutils followed that specification, we now cannot disassemble our kernel anymore. This now means Intel and AMD disagree on the encoding of UD0. And instead of playing games with additional bytes that are valid ModR/M and single byte instructions (0xd6 for instance), simply use UD2 for both WARN() and BUG(). Requested-by: Linus Torvalds Signed-off-by: Peter Zijlstra (Intel) Acked-by: Linus Torvalds Cc: Andy Lutomirski Cc: Arjan van de Ven Cc: Borislav Petkov Cc: Brian Gerst Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Josh Poimboeuf Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20180208194406.GD25181@hirez.programming.kicks-ass.net Signed-off-by: Ingo Molnar --- arch/x86/include/asm/bug.h | 15 ++++++--------- arch/x86/kernel/traps.c | 2 +- 2 files changed, 7 insertions(+), 10 deletions(-) (limited to 'arch') diff --git a/arch/x86/include/asm/bug.h b/arch/x86/include/asm/bug.h index 71e6f4bf9161..6804d6642767 100644 --- a/arch/x86/include/asm/bug.h +++ b/arch/x86/include/asm/bug.h @@ -5,23 +5,20 @@ #include /* - * Since some emulators terminate on UD2, we cannot use it for WARN. - * Since various instruction decoders disagree on the length of UD1, - * we cannot use it either. So use UD0 for WARN. + * Despite that some emulators terminate on UD2, we use it for WARN(). * - * (binutils knows about "ud1" but {en,de}codes it as 2 bytes, whereas - * our kernel decoder thinks it takes a ModRM byte, which seems consistent - * with various things like the Intel SDM instruction encoding rules) + * Since various instruction decoders/specs disagree on the encoding of + * UD0/UD1. */ -#define ASM_UD0 ".byte 0x0f, 0xff" +#define ASM_UD0 ".byte 0x0f, 0xff" /* + ModRM (for Intel) */ #define ASM_UD1 ".byte 0x0f, 0xb9" /* + ModRM */ #define ASM_UD2 ".byte 0x0f, 0x0b" #define INSN_UD0 0xff0f #define INSN_UD2 0x0b0f -#define LEN_UD0 2 +#define LEN_UD2 2 #ifdef CONFIG_GENERIC_BUG @@ -79,7 +76,7 @@ do { \ #define __WARN_FLAGS(flags) \ do { \ - _BUG_FLAGS(ASM_UD0, BUGFLAG_WARNING|(flags)); \ + _BUG_FLAGS(ASM_UD2, BUGFLAG_WARNING|(flags)); \ annotate_reachable(); \ } while (0) diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 446c9ef8cfc3..3d9b2308e7fa 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -181,7 +181,7 @@ int fixup_bug(struct pt_regs *regs, int trapnr) break; case BUG_TRAP_TYPE_WARN: - regs->ip += LEN_UD0; + regs->ip += LEN_UD2; return 1; } -- cgit v1.2.3-55-g7522 From be3233fbfcb8f5acb6e3bcd0895c3ef9e100d470 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Tue, 6 Feb 2018 18:22:40 -0800 Subject: x86/speculation: Fix up array_index_nospec_mask() asm constraint Allow the compiler to handle @size as an immediate value or memory directly rather than allocating a register. Reported-by: Linus Torvalds Signed-off-by: Dan Williams Cc: Andy Lutomirski Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/151797010204.1289.1510000292250184993.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Ingo Molnar --- arch/x86/include/asm/barrier.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h index 30d406146016..e1259f043ae9 100644 --- a/arch/x86/include/asm/barrier.h +++ b/arch/x86/include/asm/barrier.h @@ -40,7 +40,7 @@ static inline unsigned long array_index_mask_nospec(unsigned long index, asm ("cmp %1,%2; sbb %0,%0;" :"=r" (mask) - :"r"(size),"r" (index) + :"g"(size),"r" (index) :"cc"); return mask; } -- cgit v1.2.3-55-g7522 From ea00f301285ea2f07393678cd2b6057878320c9d Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 13 Feb 2018 14:28:19 +0100 Subject: x86/speculation: Add dependency Joe Konno reported a compile failure resulting from using an MSR without inclusion of , and while the current code builds fine (by accident) this needs fixing for future patches. Reported-by: Joe Konno Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: arjan@linux.intel.com Cc: bp@alien8.de Cc: dan.j.williams@intel.com Cc: dave.hansen@linux.intel.com Cc: dwmw2@infradead.org Cc: dwmw@amazon.co.uk Cc: gregkh@linuxfoundation.org Cc: hpa@zytor.com Cc: jpoimboe@redhat.com Cc: linux-tip-commits@vger.kernel.org Cc: luto@kernel.org Fixes: 20ffa1caecca ("x86/speculation: Add basic IBPB (Indirect Branch Prediction Barrier) support") Link: http://lkml.kernel.org/r/20180213132819.GJ25201@hirez.programming.kicks-ass.net Signed-off-by: Ingo Molnar --- arch/x86/include/asm/nospec-branch.h | 1 + 1 file changed, 1 insertion(+) (limited to 'arch') diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index 300cc159b4a0..76b058533e47 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -6,6 +6,7 @@ #include #include #include +#include #ifdef __ASSEMBLY__ -- cgit v1.2.3-55-g7522 From 1299ef1d8870d2d9f09a5aadf2f8b2c887c2d033 Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Wed, 31 Jan 2018 08:03:10 -0800 Subject: x86/mm: Rename flush_tlb_single() and flush_tlb_one() to __flush_tlb_one_[user|kernel]() flush_tlb_single() and flush_tlb_one() sound almost identical, but they really mean "flush one user translation" and "flush one kernel translation". Rename them to flush_tlb_one_user() and flush_tlb_one_kernel() to make the semantics more obvious. [ I was looking at some PTI-related code, and the flush-one-address code is unnecessarily hard to understand because the names of the helpers are uninformative. This came up during PTI review, but no one got around to doing it. ] Signed-off-by: Andy Lutomirski Acked-by: Peter Zijlstra (Intel) Cc: Boris Ostrovsky Cc: Borislav Petkov Cc: Brian Gerst Cc: Dave Hansen Cc: Eduardo Valentin Cc: Hugh Dickins Cc: Josh Poimboeuf Cc: Juergen Gross Cc: Kees Cook Cc: Linus Torvalds Cc: Linux-MM Cc: Rik van Riel Cc: Thomas Gleixner Cc: Will Deacon Link: http://lkml.kernel.org/r/3303b02e3c3d049dc5235d5651e0ae6d29a34354.1517414378.git.luto@kernel.org Signed-off-by: Ingo Molnar --- arch/x86/include/asm/paravirt.h | 4 ++-- arch/x86/include/asm/paravirt_types.h | 2 +- arch/x86/include/asm/pgtable_32.h | 2 +- arch/x86/include/asm/tlbflush.h | 27 ++++++++++++++++++++------- arch/x86/kernel/paravirt.c | 6 +++--- arch/x86/mm/init_64.c | 2 +- arch/x86/mm/ioremap.c | 2 +- arch/x86/mm/kmmio.c | 2 +- arch/x86/mm/pgtable_32.c | 2 +- arch/x86/mm/tlb.c | 6 +++--- arch/x86/platform/uv/tlb_uv.c | 2 +- arch/x86/xen/mmu_pv.c | 6 +++--- include/trace/events/xen.h | 2 +- 13 files changed, 39 insertions(+), 26 deletions(-) (limited to 'arch') diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index 892df375b615..554841fab717 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -297,9 +297,9 @@ static inline void __flush_tlb_global(void) { PVOP_VCALL0(pv_mmu_ops.flush_tlb_kernel); } -static inline void __flush_tlb_single(unsigned long addr) +static inline void __flush_tlb_one_user(unsigned long addr) { - PVOP_VCALL1(pv_mmu_ops.flush_tlb_single, addr); + PVOP_VCALL1(pv_mmu_ops.flush_tlb_one_user, addr); } static inline void flush_tlb_others(const struct cpumask *cpumask, diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h index 6ec54d01972d..f624f1f10316 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -217,7 +217,7 @@ struct pv_mmu_ops { /* TLB operations */ void (*flush_tlb_user)(void); void (*flush_tlb_kernel)(void); - void (*flush_tlb_single)(unsigned long addr); + void (*flush_tlb_one_user)(unsigned long addr); void (*flush_tlb_others)(const struct cpumask *cpus, const struct flush_tlb_info *info); diff --git a/arch/x86/include/asm/pgtable_32.h b/arch/x86/include/asm/pgtable_32.h index e67c0620aec2..e55466760ff8 100644 --- a/arch/x86/include/asm/pgtable_32.h +++ b/arch/x86/include/asm/pgtable_32.h @@ -61,7 +61,7 @@ void paging_init(void); #define kpte_clear_flush(ptep, vaddr) \ do { \ pte_clear(&init_mm, (vaddr), (ptep)); \ - __flush_tlb_one((vaddr)); \ + __flush_tlb_one_kernel((vaddr)); \ } while (0) #endif /* !__ASSEMBLY__ */ diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h index 2b8f18ca5874..84137c22fdfa 100644 --- a/arch/x86/include/asm/tlbflush.h +++ b/arch/x86/include/asm/tlbflush.h @@ -140,7 +140,7 @@ static inline unsigned long build_cr3_noflush(pgd_t *pgd, u16 asid) #else #define __flush_tlb() __native_flush_tlb() #define __flush_tlb_global() __native_flush_tlb_global() -#define __flush_tlb_single(addr) __native_flush_tlb_single(addr) +#define __flush_tlb_one_user(addr) __native_flush_tlb_one_user(addr) #endif static inline bool tlb_defer_switch_to_init_mm(void) @@ -400,7 +400,7 @@ static inline void __native_flush_tlb_global(void) /* * flush one page in the user mapping */ -static inline void __native_flush_tlb_single(unsigned long addr) +static inline void __native_flush_tlb_one_user(unsigned long addr) { u32 loaded_mm_asid = this_cpu_read(cpu_tlbstate.loaded_mm_asid); @@ -437,18 +437,31 @@ static inline void __flush_tlb_all(void) /* * flush one page in the kernel mapping */ -static inline void __flush_tlb_one(unsigned long addr) +static inline void __flush_tlb_one_kernel(unsigned long addr) { count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ONE); - __flush_tlb_single(addr); + + /* + * If PTI is off, then __flush_tlb_one_user() is just INVLPG or its + * paravirt equivalent. Even with PCID, this is sufficient: we only + * use PCID if we also use global PTEs for the kernel mapping, and + * INVLPG flushes global translations across all address spaces. + * + * If PTI is on, then the kernel is mapped with non-global PTEs, and + * __flush_tlb_one_user() will flush the given address for the current + * kernel address space and for its usermode counterpart, but it does + * not flush it for other address spaces. + */ + __flush_tlb_one_user(addr); if (!static_cpu_has(X86_FEATURE_PTI)) return; /* - * __flush_tlb_single() will have cleared the TLB entry for this ASID, - * but since kernel space is replicated across all, we must also - * invalidate all others. + * See above. We need to propagate the flush to all other address + * spaces. In principle, we only need to propagate it to kernelmode + * address spaces, but the extra bookkeeping we would need is not + * worth it. */ invalidate_other_asid(); } diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index 041096bdef86..99dc79e76bdc 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -200,9 +200,9 @@ static void native_flush_tlb_global(void) __native_flush_tlb_global(); } -static void native_flush_tlb_single(unsigned long addr) +static void native_flush_tlb_one_user(unsigned long addr) { - __native_flush_tlb_single(addr); + __native_flush_tlb_one_user(addr); } struct static_key paravirt_steal_enabled; @@ -401,7 +401,7 @@ struct pv_mmu_ops pv_mmu_ops __ro_after_init = { .flush_tlb_user = native_flush_tlb, .flush_tlb_kernel = native_flush_tlb_global, - .flush_tlb_single = native_flush_tlb_single, + .flush_tlb_one_user = native_flush_tlb_one_user, .flush_tlb_others = native_flush_tlb_others, .pgd_alloc = __paravirt_pgd_alloc, diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 4a837289f2ad..60ae1fe3609f 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -256,7 +256,7 @@ static void __set_pte_vaddr(pud_t *pud, unsigned long vaddr, pte_t new_pte) * It's enough to flush this one mapping. * (PGE mappings get flushed as well) */ - __flush_tlb_one(vaddr); + __flush_tlb_one_kernel(vaddr); } void set_pte_vaddr_p4d(p4d_t *p4d_page, unsigned long vaddr, pte_t new_pte) diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index c45b6ec5357b..e2db83bebc3b 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -820,5 +820,5 @@ void __init __early_set_fixmap(enum fixed_addresses idx, set_pte(pte, pfn_pte(phys >> PAGE_SHIFT, flags)); else pte_clear(&init_mm, addr, pte); - __flush_tlb_one(addr); + __flush_tlb_one_kernel(addr); } diff --git a/arch/x86/mm/kmmio.c b/arch/x86/mm/kmmio.c index 58477ec3d66d..7c8686709636 100644 --- a/arch/x86/mm/kmmio.c +++ b/arch/x86/mm/kmmio.c @@ -168,7 +168,7 @@ static int clear_page_presence(struct kmmio_fault_page *f, bool clear) return -1; } - __flush_tlb_one(f->addr); + __flush_tlb_one_kernel(f->addr); return 0; } diff --git a/arch/x86/mm/pgtable_32.c b/arch/x86/mm/pgtable_32.c index c3c5274410a9..9bb7f0ab9fe6 100644 --- a/arch/x86/mm/pgtable_32.c +++ b/arch/x86/mm/pgtable_32.c @@ -63,7 +63,7 @@ void set_pte_vaddr(unsigned long vaddr, pte_t pteval) * It's enough to flush this one mapping. * (PGE mappings get flushed as well) */ - __flush_tlb_one(vaddr); + __flush_tlb_one_kernel(vaddr); } unsigned long __FIXADDR_TOP = 0xfffff000; diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 012d02624848..0c936435ea93 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -492,7 +492,7 @@ static void flush_tlb_func_common(const struct flush_tlb_info *f, * flush that changes context.tlb_gen from 2 to 3. If they get * processed on this CPU in reverse order, we'll see * local_tlb_gen == 1, mm_tlb_gen == 3, and end != TLB_FLUSH_ALL. - * If we were to use __flush_tlb_single() and set local_tlb_gen to + * If we were to use __flush_tlb_one_user() and set local_tlb_gen to * 3, we'd be break the invariant: we'd update local_tlb_gen above * 1 without the full flush that's needed for tlb_gen 2. * @@ -513,7 +513,7 @@ static void flush_tlb_func_common(const struct flush_tlb_info *f, addr = f->start; while (addr < f->end) { - __flush_tlb_single(addr); + __flush_tlb_one_user(addr); addr += PAGE_SIZE; } if (local) @@ -660,7 +660,7 @@ static void do_kernel_range_flush(void *info) /* flush range by one by one 'invlpg' */ for (addr = f->start; addr < f->end; addr += PAGE_SIZE) - __flush_tlb_one(addr); + __flush_tlb_one_kernel(addr); } void flush_tlb_kernel_range(unsigned long start, unsigned long end) diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c index 8538a6723171..7d5d53f36a7a 100644 --- a/arch/x86/platform/uv/tlb_uv.c +++ b/arch/x86/platform/uv/tlb_uv.c @@ -299,7 +299,7 @@ static void bau_process_message(struct msg_desc *mdp, struct bau_control *bcp, local_flush_tlb(); stat->d_alltlb++; } else { - __flush_tlb_single(msg->address); + __flush_tlb_one_user(msg->address); stat->d_onetlb++; } stat->d_requestee++; diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c index d85076223a69..aae88fec9941 100644 --- a/arch/x86/xen/mmu_pv.c +++ b/arch/x86/xen/mmu_pv.c @@ -1300,12 +1300,12 @@ static void xen_flush_tlb(void) preempt_enable(); } -static void xen_flush_tlb_single(unsigned long addr) +static void xen_flush_tlb_one_user(unsigned long addr) { struct mmuext_op *op; struct multicall_space mcs; - trace_xen_mmu_flush_tlb_single(addr); + trace_xen_mmu_flush_tlb_one_user(addr); preempt_disable(); @@ -2370,7 +2370,7 @@ static const struct pv_mmu_ops xen_mmu_ops __initconst = { .flush_tlb_user = xen_flush_tlb, .flush_tlb_kernel = xen_flush_tlb, - .flush_tlb_single = xen_flush_tlb_single, + .flush_tlb_one_user = xen_flush_tlb_one_user, .flush_tlb_others = xen_flush_tlb_others, .pgd_alloc = xen_pgd_alloc, diff --git a/include/trace/events/xen.h b/include/trace/events/xen.h index b8adf05c534e..7dd8f34c37df 100644 --- a/include/trace/events/xen.h +++ b/include/trace/events/xen.h @@ -368,7 +368,7 @@ TRACE_EVENT(xen_mmu_flush_tlb, TP_printk("%s", "") ); -TRACE_EVENT(xen_mmu_flush_tlb_single, +TRACE_EVENT(xen_mmu_flush_tlb_one_user, TP_PROTO(unsigned long addr), TP_ARGS(addr), TP_STRUCT__entry( -- cgit v1.2.3-55-g7522 From b399151cb48db30ad1e0e93dd40d68c6d007b637 Mon Sep 17 00:00:00 2001 From: Jia Zhang Date: Mon, 1 Jan 2018 09:52:10 +0800 Subject: x86/cpu: Rename cpu_data.x86_mask to cpu_data.x86_stepping x86_mask is a confusing name which is hard to associate with the processor's stepping. Additionally, correct an indent issue in lib/cpu.c. Signed-off-by: Jia Zhang [ Updated it to more recent kernels. ] Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: bp@alien8.de Cc: tony.luck@intel.com Link: http://lkml.kernel.org/r/1514771530-70829-1-git-send-email-qianyue.zj@alibaba-inc.com Signed-off-by: Ingo Molnar --- arch/x86/events/intel/core.c | 2 +- arch/x86/events/intel/lbr.c | 2 +- arch/x86/events/intel/p6.c | 2 +- arch/x86/include/asm/acpi.h | 2 +- arch/x86/include/asm/processor.h | 2 +- arch/x86/kernel/amd_nb.c | 2 +- arch/x86/kernel/apic/apic.c | 6 +++--- arch/x86/kernel/asm-offsets_32.c | 2 +- arch/x86/kernel/cpu/amd.c | 28 ++++++++++++++-------------- arch/x86/kernel/cpu/centaur.c | 4 ++-- arch/x86/kernel/cpu/common.c | 8 ++++---- arch/x86/kernel/cpu/cyrix.c | 2 +- arch/x86/kernel/cpu/intel.c | 18 +++++++++--------- arch/x86/kernel/cpu/intel_rdt.c | 2 +- arch/x86/kernel/cpu/microcode/intel.c | 4 ++-- arch/x86/kernel/cpu/mtrr/generic.c | 2 +- arch/x86/kernel/cpu/mtrr/main.c | 4 ++-- arch/x86/kernel/cpu/proc.c | 4 ++-- arch/x86/kernel/head_32.S | 4 ++-- arch/x86/kernel/mpparse.c | 2 +- arch/x86/lib/cpu.c | 2 +- drivers/char/hw_random/via-rng.c | 2 +- drivers/cpufreq/acpi-cpufreq.c | 2 +- drivers/cpufreq/longhaul.c | 6 +++--- drivers/cpufreq/p4-clockmod.c | 2 +- drivers/cpufreq/powernow-k7.c | 2 +- drivers/cpufreq/speedstep-centrino.c | 4 ++-- drivers/cpufreq/speedstep-lib.c | 6 +++--- drivers/crypto/padlock-aes.c | 2 +- drivers/edac/amd64_edac.c | 2 +- drivers/hwmon/coretemp.c | 6 +++--- drivers/hwmon/hwmon-vid.c | 2 +- drivers/hwmon/k10temp.c | 2 +- drivers/hwmon/k8temp.c | 2 +- drivers/video/fbdev/geode/video_gx.c | 2 +- 35 files changed, 73 insertions(+), 73 deletions(-) (limited to 'arch') diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 731153a4681e..56457cb73448 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -3559,7 +3559,7 @@ static int intel_snb_pebs_broken(int cpu) break; case INTEL_FAM6_SANDYBRIDGE_X: - switch (cpu_data(cpu).x86_mask) { + switch (cpu_data(cpu).x86_stepping) { case 6: rev = 0x618; break; case 7: rev = 0x70c; break; } diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c index ae64d0b69729..cf372b90557e 100644 --- a/arch/x86/events/intel/lbr.c +++ b/arch/x86/events/intel/lbr.c @@ -1186,7 +1186,7 @@ void __init intel_pmu_lbr_init_atom(void) * on PMU interrupt */ if (boot_cpu_data.x86_model == 28 - && boot_cpu_data.x86_mask < 10) { + && boot_cpu_data.x86_stepping < 10) { pr_cont("LBR disabled due to erratum"); return; } diff --git a/arch/x86/events/intel/p6.c b/arch/x86/events/intel/p6.c index a5604c352930..408879b0c0d4 100644 --- a/arch/x86/events/intel/p6.c +++ b/arch/x86/events/intel/p6.c @@ -234,7 +234,7 @@ static __initconst const struct x86_pmu p6_pmu = { static __init void p6_pmu_rdpmc_quirk(void) { - if (boot_cpu_data.x86_mask < 9) { + if (boot_cpu_data.x86_stepping < 9) { /* * PPro erratum 26; fixed in stepping 9 and above. */ diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h index 8d0ec9df1cbe..f077401869ee 100644 --- a/arch/x86/include/asm/acpi.h +++ b/arch/x86/include/asm/acpi.h @@ -94,7 +94,7 @@ static inline unsigned int acpi_processor_cstate_check(unsigned int max_cstate) if (boot_cpu_data.x86 == 0x0F && boot_cpu_data.x86_vendor == X86_VENDOR_AMD && boot_cpu_data.x86_model <= 0x05 && - boot_cpu_data.x86_mask < 0x0A) + boot_cpu_data.x86_stepping < 0x0A) return 1; else if (boot_cpu_has(X86_BUG_AMD_APIC_C1E)) return 1; diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 99799fbd0f7e..b7c8583328c7 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -91,7 +91,7 @@ struct cpuinfo_x86 { __u8 x86; /* CPU family */ __u8 x86_vendor; /* CPU vendor */ __u8 x86_model; - __u8 x86_mask; + __u8 x86_stepping; #ifdef CONFIG_X86_64 /* Number of 4K pages in DTLB/ITLB combined(in pages): */ int x86_tlbsize; diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c index 6db28f17ff28..c88e0b127810 100644 --- a/arch/x86/kernel/amd_nb.c +++ b/arch/x86/kernel/amd_nb.c @@ -235,7 +235,7 @@ int amd_cache_northbridges(void) if (boot_cpu_data.x86 == 0x10 && boot_cpu_data.x86_model >= 0x8 && (boot_cpu_data.x86_model > 0x9 || - boot_cpu_data.x86_mask >= 0x1)) + boot_cpu_data.x86_stepping >= 0x1)) amd_northbridges.flags |= AMD_NB_L3_INDEX_DISABLE; if (boot_cpu_data.x86 == 0x15) diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 25ddf02598d2..b203af0855b5 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -546,7 +546,7 @@ static DEFINE_PER_CPU(struct clock_event_device, lapic_events); static u32 hsx_deadline_rev(void) { - switch (boot_cpu_data.x86_mask) { + switch (boot_cpu_data.x86_stepping) { case 0x02: return 0x3a; /* EP */ case 0x04: return 0x0f; /* EX */ } @@ -556,7 +556,7 @@ static u32 hsx_deadline_rev(void) static u32 bdx_deadline_rev(void) { - switch (boot_cpu_data.x86_mask) { + switch (boot_cpu_data.x86_stepping) { case 0x02: return 0x00000011; case 0x03: return 0x0700000e; case 0x04: return 0x0f00000c; @@ -568,7 +568,7 @@ static u32 bdx_deadline_rev(void) static u32 skx_deadline_rev(void) { - switch (boot_cpu_data.x86_mask) { + switch (boot_cpu_data.x86_stepping) { case 0x03: return 0x01000136; case 0x04: return 0x02000014; } diff --git a/arch/x86/kernel/asm-offsets_32.c b/arch/x86/kernel/asm-offsets_32.c index fa1261eefa16..f91ba53e06c8 100644 --- a/arch/x86/kernel/asm-offsets_32.c +++ b/arch/x86/kernel/asm-offsets_32.c @@ -18,7 +18,7 @@ void foo(void) OFFSET(CPUINFO_x86, cpuinfo_x86, x86); OFFSET(CPUINFO_x86_vendor, cpuinfo_x86, x86_vendor); OFFSET(CPUINFO_x86_model, cpuinfo_x86, x86_model); - OFFSET(CPUINFO_x86_mask, cpuinfo_x86, x86_mask); + OFFSET(CPUINFO_x86_stepping, cpuinfo_x86, x86_stepping); OFFSET(CPUINFO_cpuid_level, cpuinfo_x86, cpuid_level); OFFSET(CPUINFO_x86_capability, cpuinfo_x86, x86_capability); OFFSET(CPUINFO_x86_vendor_id, cpuinfo_x86, x86_vendor_id); diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index ea831c858195..e7d5a7883632 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -119,7 +119,7 @@ static void init_amd_k6(struct cpuinfo_x86 *c) return; } - if (c->x86_model == 6 && c->x86_mask == 1) { + if (c->x86_model == 6 && c->x86_stepping == 1) { const int K6_BUG_LOOP = 1000000; int n; void (*f_vide)(void); @@ -149,7 +149,7 @@ static void init_amd_k6(struct cpuinfo_x86 *c) /* K6 with old style WHCR */ if (c->x86_model < 8 || - (c->x86_model == 8 && c->x86_mask < 8)) { + (c->x86_model == 8 && c->x86_stepping < 8)) { /* We can only write allocate on the low 508Mb */ if (mbytes > 508) mbytes = 508; @@ -168,7 +168,7 @@ static void init_amd_k6(struct cpuinfo_x86 *c) return; } - if ((c->x86_model == 8 && c->x86_mask > 7) || + if ((c->x86_model == 8 && c->x86_stepping > 7) || c->x86_model == 9 || c->x86_model == 13) { /* The more serious chips .. */ @@ -221,7 +221,7 @@ static void init_amd_k7(struct cpuinfo_x86 *c) * are more robust with CLK_CTL set to 200xxxxx instead of 600xxxxx * As per AMD technical note 27212 0.2 */ - if ((c->x86_model == 8 && c->x86_mask >= 1) || (c->x86_model > 8)) { + if ((c->x86_model == 8 && c->x86_stepping >= 1) || (c->x86_model > 8)) { rdmsr(MSR_K7_CLK_CTL, l, h); if ((l & 0xfff00000) != 0x20000000) { pr_info("CPU: CLK_CTL MSR was %x. Reprogramming to %x\n", @@ -241,12 +241,12 @@ static void init_amd_k7(struct cpuinfo_x86 *c) * but they are not certified as MP capable. */ /* Athlon 660/661 is valid. */ - if ((c->x86_model == 6) && ((c->x86_mask == 0) || - (c->x86_mask == 1))) + if ((c->x86_model == 6) && ((c->x86_stepping == 0) || + (c->x86_stepping == 1))) return; /* Duron 670 is valid */ - if ((c->x86_model == 7) && (c->x86_mask == 0)) + if ((c->x86_model == 7) && (c->x86_stepping == 0)) return; /* @@ -256,8 +256,8 @@ static void init_amd_k7(struct cpuinfo_x86 *c) * See http://www.heise.de/newsticker/data/jow-18.10.01-000 for * more. */ - if (((c->x86_model == 6) && (c->x86_mask >= 2)) || - ((c->x86_model == 7) && (c->x86_mask >= 1)) || + if (((c->x86_model == 6) && (c->x86_stepping >= 2)) || + ((c->x86_model == 7) && (c->x86_stepping >= 1)) || (c->x86_model > 7)) if (cpu_has(c, X86_FEATURE_MP)) return; @@ -583,7 +583,7 @@ static void early_init_amd(struct cpuinfo_x86 *c) /* Set MTRR capability flag if appropriate */ if (c->x86 == 5) if (c->x86_model == 13 || c->x86_model == 9 || - (c->x86_model == 8 && c->x86_mask >= 8)) + (c->x86_model == 8 && c->x86_stepping >= 8)) set_cpu_cap(c, X86_FEATURE_K6_MTRR); #endif #if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_PCI) @@ -769,7 +769,7 @@ static void init_amd_zn(struct cpuinfo_x86 *c) * Fix erratum 1076: CPB feature bit not being set in CPUID. It affects * all up to and including B1. */ - if (c->x86_model <= 1 && c->x86_mask <= 1) + if (c->x86_model <= 1 && c->x86_stepping <= 1) set_cpu_cap(c, X86_FEATURE_CPB); } @@ -880,11 +880,11 @@ static unsigned int amd_size_cache(struct cpuinfo_x86 *c, unsigned int size) /* AMD errata T13 (order #21922) */ if ((c->x86 == 6)) { /* Duron Rev A0 */ - if (c->x86_model == 3 && c->x86_mask == 0) + if (c->x86_model == 3 && c->x86_stepping == 0) size = 64; /* Tbird rev A1/A2 */ if (c->x86_model == 4 && - (c->x86_mask == 0 || c->x86_mask == 1)) + (c->x86_stepping == 0 || c->x86_stepping == 1)) size = 256; } return size; @@ -1021,7 +1021,7 @@ static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum) } /* OSVW unavailable or ID unknown, match family-model-stepping range */ - ms = (cpu->x86_model << 4) | cpu->x86_mask; + ms = (cpu->x86_model << 4) | cpu->x86_stepping; while ((range = *erratum++)) if ((cpu->x86 == AMD_MODEL_RANGE_FAMILY(range)) && (ms >= AMD_MODEL_RANGE_START(range)) && diff --git a/arch/x86/kernel/cpu/centaur.c b/arch/x86/kernel/cpu/centaur.c index 68bc6d9b3132..595be776727d 100644 --- a/arch/x86/kernel/cpu/centaur.c +++ b/arch/x86/kernel/cpu/centaur.c @@ -136,7 +136,7 @@ static void init_centaur(struct cpuinfo_x86 *c) clear_cpu_cap(c, X86_FEATURE_TSC); break; case 8: - switch (c->x86_mask) { + switch (c->x86_stepping) { default: name = "2"; break; @@ -211,7 +211,7 @@ centaur_size_cache(struct cpuinfo_x86 *c, unsigned int size) * - Note, it seems this may only be in engineering samples. */ if ((c->x86 == 6) && (c->x86_model == 9) && - (c->x86_mask == 1) && (size == 65)) + (c->x86_stepping == 1) && (size == 65)) size -= 1; return size; } diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index d63f4b5706e4..a7d8df641a4c 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -731,7 +731,7 @@ void cpu_detect(struct cpuinfo_x86 *c) cpuid(0x00000001, &tfms, &misc, &junk, &cap0); c->x86 = x86_family(tfms); c->x86_model = x86_model(tfms); - c->x86_mask = x86_stepping(tfms); + c->x86_stepping = x86_stepping(tfms); if (cap0 & (1<<19)) { c->x86_clflush_size = ((misc >> 8) & 0xff) * 8; @@ -1186,7 +1186,7 @@ static void identify_cpu(struct cpuinfo_x86 *c) c->loops_per_jiffy = loops_per_jiffy; c->x86_cache_size = -1; c->x86_vendor = X86_VENDOR_UNKNOWN; - c->x86_model = c->x86_mask = 0; /* So far unknown... */ + c->x86_model = c->x86_stepping = 0; /* So far unknown... */ c->x86_vendor_id[0] = '\0'; /* Unset */ c->x86_model_id[0] = '\0'; /* Unset */ c->x86_max_cores = 1; @@ -1378,8 +1378,8 @@ void print_cpu_info(struct cpuinfo_x86 *c) pr_cont(" (family: 0x%x, model: 0x%x", c->x86, c->x86_model); - if (c->x86_mask || c->cpuid_level >= 0) - pr_cont(", stepping: 0x%x)\n", c->x86_mask); + if (c->x86_stepping || c->cpuid_level >= 0) + pr_cont(", stepping: 0x%x)\n", c->x86_stepping); else pr_cont(")\n"); } diff --git a/arch/x86/kernel/cpu/cyrix.c b/arch/x86/kernel/cpu/cyrix.c index 6b4bb335641f..8949b7ae6d92 100644 --- a/arch/x86/kernel/cpu/cyrix.c +++ b/arch/x86/kernel/cpu/cyrix.c @@ -215,7 +215,7 @@ static void init_cyrix(struct cpuinfo_x86 *c) /* common case step number/rev -- exceptions handled below */ c->x86_model = (dir1 >> 4) + 1; - c->x86_mask = dir1 & 0xf; + c->x86_stepping = dir1 & 0xf; /* Now cook; the original recipe is by Channing Corn, from Cyrix. * We do the same thing for each generation: we work out diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index ef796f14f7ae..d19e903214b4 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -146,7 +146,7 @@ static bool bad_spectre_microcode(struct cpuinfo_x86 *c) for (i = 0; i < ARRAY_SIZE(spectre_bad_microcodes); i++) { if (c->x86_model == spectre_bad_microcodes[i].model && - c->x86_mask == spectre_bad_microcodes[i].stepping) + c->x86_stepping == spectre_bad_microcodes[i].stepping) return (c->microcode <= spectre_bad_microcodes[i].microcode); } return false; @@ -193,7 +193,7 @@ static void early_init_intel(struct cpuinfo_x86 *c) * need the microcode to have already been loaded... so if it is * not, recommend a BIOS update and disable large pages. */ - if (c->x86 == 6 && c->x86_model == 0x1c && c->x86_mask <= 2 && + if (c->x86 == 6 && c->x86_model == 0x1c && c->x86_stepping <= 2 && c->microcode < 0x20e) { pr_warn("Atom PSE erratum detected, BIOS microcode update recommended\n"); clear_cpu_cap(c, X86_FEATURE_PSE); @@ -209,7 +209,7 @@ static void early_init_intel(struct cpuinfo_x86 *c) /* CPUID workaround for 0F33/0F34 CPU */ if (c->x86 == 0xF && c->x86_model == 0x3 - && (c->x86_mask == 0x3 || c->x86_mask == 0x4)) + && (c->x86_stepping == 0x3 || c->x86_stepping == 0x4)) c->x86_phys_bits = 36; /* @@ -307,7 +307,7 @@ int ppro_with_ram_bug(void) if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL && boot_cpu_data.x86 == 6 && boot_cpu_data.x86_model == 1 && - boot_cpu_data.x86_mask < 8) { + boot_cpu_data.x86_stepping < 8) { pr_info("Pentium Pro with Errata#50 detected. Taking evasive action.\n"); return 1; } @@ -324,7 +324,7 @@ static void intel_smp_check(struct cpuinfo_x86 *c) * Mask B, Pentium, but not Pentium MMX */ if (c->x86 == 5 && - c->x86_mask >= 1 && c->x86_mask <= 4 && + c->x86_stepping >= 1 && c->x86_stepping <= 4 && c->x86_model <= 3) { /* * Remember we have B step Pentia with bugs @@ -367,7 +367,7 @@ static void intel_workarounds(struct cpuinfo_x86 *c) * SEP CPUID bug: Pentium Pro reports SEP but doesn't have it until * model 3 mask 3 */ - if ((c->x86<<8 | c->x86_model<<4 | c->x86_mask) < 0x633) + if ((c->x86<<8 | c->x86_model<<4 | c->x86_stepping) < 0x633) clear_cpu_cap(c, X86_FEATURE_SEP); /* @@ -385,7 +385,7 @@ static void intel_workarounds(struct cpuinfo_x86 *c) * P4 Xeon erratum 037 workaround. * Hardware prefetcher may cause stale data to be loaded into the cache. */ - if ((c->x86 == 15) && (c->x86_model == 1) && (c->x86_mask == 1)) { + if ((c->x86 == 15) && (c->x86_model == 1) && (c->x86_stepping == 1)) { if (msr_set_bit(MSR_IA32_MISC_ENABLE, MSR_IA32_MISC_ENABLE_PREFETCH_DISABLE_BIT) > 0) { pr_info("CPU: C0 stepping P4 Xeon detected.\n"); @@ -400,7 +400,7 @@ static void intel_workarounds(struct cpuinfo_x86 *c) * Specification Update"). */ if (boot_cpu_has(X86_FEATURE_APIC) && (c->x86<<8 | c->x86_model<<4) == 0x520 && - (c->x86_mask < 0x6 || c->x86_mask == 0xb)) + (c->x86_stepping < 0x6 || c->x86_stepping == 0xb)) set_cpu_bug(c, X86_BUG_11AP); @@ -647,7 +647,7 @@ static void init_intel(struct cpuinfo_x86 *c) case 6: if (l2 == 128) p = "Celeron (Mendocino)"; - else if (c->x86_mask == 0 || c->x86_mask == 5) + else if (c->x86_stepping == 0 || c->x86_stepping == 5) p = "Celeron-A"; break; diff --git a/arch/x86/kernel/cpu/intel_rdt.c b/arch/x86/kernel/cpu/intel_rdt.c index 99442370de40..18dd8f22e353 100644 --- a/arch/x86/kernel/cpu/intel_rdt.c +++ b/arch/x86/kernel/cpu/intel_rdt.c @@ -771,7 +771,7 @@ static __init void rdt_quirks(void) cache_alloc_hsw_probe(); break; case INTEL_FAM6_SKYLAKE_X: - if (boot_cpu_data.x86_mask <= 4) + if (boot_cpu_data.x86_stepping <= 4) set_rdt_options("!cmt,!mbmtotal,!mbmlocal,!l3cat"); } } diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c index f7c55b0e753a..b94279bb5c04 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -921,7 +921,7 @@ static bool is_blacklisted(unsigned int cpu) */ if (c->x86 == 6 && c->x86_model == INTEL_FAM6_BROADWELL_X && - c->x86_mask == 0x01 && + c->x86_stepping == 0x01 && llc_size_per_core > 2621440 && c->microcode < 0x0b000021) { pr_err_once("Erratum BDF90: late loading with revision < 0x0b000021 (0x%x) disabled.\n", c->microcode); @@ -944,7 +944,7 @@ static enum ucode_state request_microcode_fw(int cpu, struct device *device, return UCODE_NFOUND; sprintf(name, "intel-ucode/%02x-%02x-%02x", - c->x86, c->x86_model, c->x86_mask); + c->x86, c->x86_model, c->x86_stepping); if (request_firmware_direct(&firmware, name, device)) { pr_debug("data file %s load failed\n", name); diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c index fdc55215d44d..e12ee86906c6 100644 --- a/arch/x86/kernel/cpu/mtrr/generic.c +++ b/arch/x86/kernel/cpu/mtrr/generic.c @@ -859,7 +859,7 @@ int generic_validate_add_page(unsigned long base, unsigned long size, */ if (is_cpu(INTEL) && boot_cpu_data.x86 == 6 && boot_cpu_data.x86_model == 1 && - boot_cpu_data.x86_mask <= 7) { + boot_cpu_data.x86_stepping <= 7) { if (base & ((1 << (22 - PAGE_SHIFT)) - 1)) { pr_warn("mtrr: base(0x%lx000) is not 4 MiB aligned\n", base); return -EINVAL; diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c index 40d5a8a75212..7468de429087 100644 --- a/arch/x86/kernel/cpu/mtrr/main.c +++ b/arch/x86/kernel/cpu/mtrr/main.c @@ -711,8 +711,8 @@ void __init mtrr_bp_init(void) if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL && boot_cpu_data.x86 == 0xF && boot_cpu_data.x86_model == 0x3 && - (boot_cpu_data.x86_mask == 0x3 || - boot_cpu_data.x86_mask == 0x4)) + (boot_cpu_data.x86_stepping == 0x3 || + boot_cpu_data.x86_stepping == 0x4)) phys_addr = 36; size_or_mask = SIZE_OR_MASK_BITS(phys_addr); diff --git a/arch/x86/kernel/cpu/proc.c b/arch/x86/kernel/cpu/proc.c index e7ecedafa1c8..ee4cc388e8d3 100644 --- a/arch/x86/kernel/cpu/proc.c +++ b/arch/x86/kernel/cpu/proc.c @@ -72,8 +72,8 @@ static int show_cpuinfo(struct seq_file *m, void *v) c->x86_model, c->x86_model_id[0] ? c->x86_model_id : "unknown"); - if (c->x86_mask || c->cpuid_level >= 0) - seq_printf(m, "stepping\t: %d\n", c->x86_mask); + if (c->x86_stepping || c->cpuid_level >= 0) + seq_printf(m, "stepping\t: %d\n", c->x86_stepping); else seq_puts(m, "stepping\t: unknown\n"); if (c->microcode) diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index c29020907886..b59e4fb40fd9 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -37,7 +37,7 @@ #define X86 new_cpu_data+CPUINFO_x86 #define X86_VENDOR new_cpu_data+CPUINFO_x86_vendor #define X86_MODEL new_cpu_data+CPUINFO_x86_model -#define X86_MASK new_cpu_data+CPUINFO_x86_mask +#define X86_STEPPING new_cpu_data+CPUINFO_x86_stepping #define X86_HARD_MATH new_cpu_data+CPUINFO_hard_math #define X86_CPUID new_cpu_data+CPUINFO_cpuid_level #define X86_CAPABILITY new_cpu_data+CPUINFO_x86_capability @@ -332,7 +332,7 @@ ENTRY(startup_32_smp) shrb $4,%al movb %al,X86_MODEL andb $0x0f,%cl # mask mask revision - movb %cl,X86_MASK + movb %cl,X86_STEPPING movl %edx,X86_CAPABILITY .Lis486: diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c index 3a4b12809ab5..bc6bc6689e68 100644 --- a/arch/x86/kernel/mpparse.c +++ b/arch/x86/kernel/mpparse.c @@ -407,7 +407,7 @@ static inline void __init construct_default_ISA_mptable(int mpc_default_type) processor.apicver = mpc_default_type > 4 ? 0x10 : 0x01; processor.cpuflag = CPU_ENABLED; processor.cpufeature = (boot_cpu_data.x86 << 8) | - (boot_cpu_data.x86_model << 4) | boot_cpu_data.x86_mask; + (boot_cpu_data.x86_model << 4) | boot_cpu_data.x86_stepping; processor.featureflag = boot_cpu_data.x86_capability[CPUID_1_EDX]; processor.reserved[0] = 0; processor.reserved[1] = 0; diff --git a/arch/x86/lib/cpu.c b/arch/x86/lib/cpu.c index d6f848d1211d..2dd1fe13a37b 100644 --- a/arch/x86/lib/cpu.c +++ b/arch/x86/lib/cpu.c @@ -18,7 +18,7 @@ unsigned int x86_model(unsigned int sig) { unsigned int fam, model; - fam = x86_family(sig); + fam = x86_family(sig); model = (sig >> 4) & 0xf; diff --git a/drivers/char/hw_random/via-rng.c b/drivers/char/hw_random/via-rng.c index d1f5bb534e0e..6e9df558325b 100644 --- a/drivers/char/hw_random/via-rng.c +++ b/drivers/char/hw_random/via-rng.c @@ -162,7 +162,7 @@ static int via_rng_init(struct hwrng *rng) /* Enable secondary noise source on CPUs where it is present. */ /* Nehemiah stepping 8 and higher */ - if ((c->x86_model == 9) && (c->x86_mask > 7)) + if ((c->x86_model == 9) && (c->x86_stepping > 7)) lo |= VIA_NOISESRC2; /* Esther */ diff --git a/drivers/cpufreq/acpi-cpufreq.c b/drivers/cpufreq/acpi-cpufreq.c index 3a2ca0f79daf..d0c34df0529c 100644 --- a/drivers/cpufreq/acpi-cpufreq.c +++ b/drivers/cpufreq/acpi-cpufreq.c @@ -629,7 +629,7 @@ static int acpi_cpufreq_blacklist(struct cpuinfo_x86 *c) if (c->x86_vendor == X86_VENDOR_INTEL) { if ((c->x86 == 15) && (c->x86_model == 6) && - (c->x86_mask == 8)) { + (c->x86_stepping == 8)) { pr_info("Intel(R) Xeon(R) 7100 Errata AL30, processors may lock up on frequency changes: disabling acpi-cpufreq\n"); return -ENODEV; } diff --git a/drivers/cpufreq/longhaul.c b/drivers/cpufreq/longhaul.c index c46a12df40dd..d5e27bc7585a 100644 --- a/drivers/cpufreq/longhaul.c +++ b/drivers/cpufreq/longhaul.c @@ -775,7 +775,7 @@ static int longhaul_cpu_init(struct cpufreq_policy *policy) break; case 7: - switch (c->x86_mask) { + switch (c->x86_stepping) { case 0: longhaul_version = TYPE_LONGHAUL_V1; cpu_model = CPU_SAMUEL2; @@ -787,7 +787,7 @@ static int longhaul_cpu_init(struct cpufreq_policy *policy) break; case 1 ... 15: longhaul_version = TYPE_LONGHAUL_V2; - if (c->x86_mask < 8) { + if (c->x86_stepping < 8) { cpu_model = CPU_SAMUEL2; cpuname = "C3 'Samuel 2' [C5B]"; } else { @@ -814,7 +814,7 @@ static int longhaul_cpu_init(struct cpufreq_policy *policy) numscales = 32; memcpy(mults, nehemiah_mults, sizeof(nehemiah_mults)); memcpy(eblcr, nehemiah_eblcr, sizeof(nehemiah_eblcr)); - switch (c->x86_mask) { + switch (c->x86_stepping) { case 0 ... 1: cpu_model = CPU_NEHEMIAH; cpuname = "C3 'Nehemiah A' [C5XLOE]"; diff --git a/drivers/cpufreq/p4-clockmod.c b/drivers/cpufreq/p4-clockmod.c index fd77812313f3..a25741b1281b 100644 --- a/drivers/cpufreq/p4-clockmod.c +++ b/drivers/cpufreq/p4-clockmod.c @@ -168,7 +168,7 @@ static int cpufreq_p4_cpu_init(struct cpufreq_policy *policy) #endif /* Errata workaround */ - cpuid = (c->x86 << 8) | (c->x86_model << 4) | c->x86_mask; + cpuid = (c->x86 << 8) | (c->x86_model << 4) | c->x86_stepping; switch (cpuid) { case 0x0f07: case 0x0f0a: diff --git a/drivers/cpufreq/powernow-k7.c b/drivers/cpufreq/powernow-k7.c index 80ac313e6c59..302e9ce793a0 100644 --- a/drivers/cpufreq/powernow-k7.c +++ b/drivers/cpufreq/powernow-k7.c @@ -131,7 +131,7 @@ static int check_powernow(void) return 0; } - if ((c->x86_model == 6) && (c->x86_mask == 0)) { + if ((c->x86_model == 6) && (c->x86_stepping == 0)) { pr_info("K7 660[A0] core detected, enabling errata workarounds\n"); have_a0 = 1; } diff --git a/drivers/cpufreq/speedstep-centrino.c b/drivers/cpufreq/speedstep-centrino.c index 41bc5397f4bb..4fa5adf16c70 100644 --- a/drivers/cpufreq/speedstep-centrino.c +++ b/drivers/cpufreq/speedstep-centrino.c @@ -37,7 +37,7 @@ struct cpu_id { __u8 x86; /* CPU family */ __u8 x86_model; /* model */ - __u8 x86_mask; /* stepping */ + __u8 x86_stepping; /* stepping */ }; enum { @@ -277,7 +277,7 @@ static int centrino_verify_cpu_id(const struct cpuinfo_x86 *c, { if ((c->x86 == x->x86) && (c->x86_model == x->x86_model) && - (c->x86_mask == x->x86_mask)) + (c->x86_stepping == x->x86_stepping)) return 1; return 0; } diff --git a/drivers/cpufreq/speedstep-lib.c b/drivers/cpufreq/speedstep-lib.c index 8085ec9000d1..e3a9962ee410 100644 --- a/drivers/cpufreq/speedstep-lib.c +++ b/drivers/cpufreq/speedstep-lib.c @@ -272,9 +272,9 @@ unsigned int speedstep_detect_processor(void) ebx = cpuid_ebx(0x00000001); ebx &= 0x000000FF; - pr_debug("ebx value is %x, x86_mask is %x\n", ebx, c->x86_mask); + pr_debug("ebx value is %x, x86_stepping is %x\n", ebx, c->x86_stepping); - switch (c->x86_mask) { + switch (c->x86_stepping) { case 4: /* * B-stepping [M-P4-M] @@ -361,7 +361,7 @@ unsigned int speedstep_detect_processor(void) msr_lo, msr_hi); if ((msr_hi & (1<<18)) && (relaxed_check ? 1 : (msr_hi & (3<<24)))) { - if (c->x86_mask == 0x01) { + if (c->x86_stepping == 0x01) { pr_debug("early PIII version\n"); return SPEEDSTEP_CPU_PIII_C_EARLY; } else diff --git a/drivers/crypto/padlock-aes.c b/drivers/crypto/padlock-aes.c index 4b6642a25df5..1c6cbda56afe 100644 --- a/drivers/crypto/padlock-aes.c +++ b/drivers/crypto/padlock-aes.c @@ -512,7 +512,7 @@ static int __init padlock_init(void) printk(KERN_NOTICE PFX "Using VIA PadLock ACE for AES algorithm.\n"); - if (c->x86 == 6 && c->x86_model == 15 && c->x86_mask == 2) { + if (c->x86 == 6 && c->x86_model == 15 && c->x86_stepping == 2) { ecb_fetch_blocks = MAX_ECB_FETCH_BLOCKS; cbc_fetch_blocks = MAX_CBC_FETCH_BLOCKS; printk(KERN_NOTICE PFX "VIA Nano stepping 2 detected: enabling workaround.\n"); diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c index 8b16ec595fa7..329cb96f886f 100644 --- a/drivers/edac/amd64_edac.c +++ b/drivers/edac/amd64_edac.c @@ -3147,7 +3147,7 @@ static struct amd64_family_type *per_family_init(struct amd64_pvt *pvt) struct amd64_family_type *fam_type = NULL; pvt->ext_model = boot_cpu_data.x86_model >> 4; - pvt->stepping = boot_cpu_data.x86_mask; + pvt->stepping = boot_cpu_data.x86_stepping; pvt->model = boot_cpu_data.x86_model; pvt->fam = boot_cpu_data.x86; diff --git a/drivers/hwmon/coretemp.c b/drivers/hwmon/coretemp.c index c13a4fd86b3c..a42744c7665b 100644 --- a/drivers/hwmon/coretemp.c +++ b/drivers/hwmon/coretemp.c @@ -268,13 +268,13 @@ static int adjust_tjmax(struct cpuinfo_x86 *c, u32 id, struct device *dev) for (i = 0; i < ARRAY_SIZE(tjmax_model_table); i++) { const struct tjmax_model *tm = &tjmax_model_table[i]; if (c->x86_model == tm->model && - (tm->mask == ANY || c->x86_mask == tm->mask)) + (tm->mask == ANY || c->x86_stepping == tm->mask)) return tm->tjmax; } /* Early chips have no MSR for TjMax */ - if (c->x86_model == 0xf && c->x86_mask < 4) + if (c->x86_model == 0xf && c->x86_stepping < 4) usemsr_ee = 0; if (c->x86_model > 0xe && usemsr_ee) { @@ -425,7 +425,7 @@ static int chk_ucode_version(unsigned int cpu) * Readings might stop update when processor visited too deep sleep, * fixed for stepping D0 (6EC). */ - if (c->x86_model == 0xe && c->x86_mask < 0xc && c->microcode < 0x39) { + if (c->x86_model == 0xe && c->x86_stepping < 0xc && c->microcode < 0x39) { pr_err("Errata AE18 not fixed, update BIOS or microcode of the CPU!\n"); return -ENODEV; } diff --git a/drivers/hwmon/hwmon-vid.c b/drivers/hwmon/hwmon-vid.c index ef91b8a67549..84e91286fc4f 100644 --- a/drivers/hwmon/hwmon-vid.c +++ b/drivers/hwmon/hwmon-vid.c @@ -293,7 +293,7 @@ u8 vid_which_vrm(void) if (c->x86 < 6) /* Any CPU with family lower than 6 */ return 0; /* doesn't have VID */ - vrm_ret = find_vrm(c->x86, c->x86_model, c->x86_mask, c->x86_vendor); + vrm_ret = find_vrm(c->x86, c->x86_model, c->x86_stepping, c->x86_vendor); if (vrm_ret == 134) vrm_ret = get_via_model_d_vrm(); if (vrm_ret == 0) diff --git a/drivers/hwmon/k10temp.c b/drivers/hwmon/k10temp.c index 0721e175664a..b960015cb073 100644 --- a/drivers/hwmon/k10temp.c +++ b/drivers/hwmon/k10temp.c @@ -226,7 +226,7 @@ static bool has_erratum_319(struct pci_dev *pdev) * and AM3 formats, but that's the best we can do. */ return boot_cpu_data.x86_model < 4 || - (boot_cpu_data.x86_model == 4 && boot_cpu_data.x86_mask <= 2); + (boot_cpu_data.x86_model == 4 && boot_cpu_data.x86_stepping <= 2); } static int k10temp_probe(struct pci_dev *pdev, diff --git a/drivers/hwmon/k8temp.c b/drivers/hwmon/k8temp.c index 5a632bcf869b..e59f9113fb93 100644 --- a/drivers/hwmon/k8temp.c +++ b/drivers/hwmon/k8temp.c @@ -187,7 +187,7 @@ static int k8temp_probe(struct pci_dev *pdev, return -ENOMEM; model = boot_cpu_data.x86_model; - stepping = boot_cpu_data.x86_mask; + stepping = boot_cpu_data.x86_stepping; /* feature available since SH-C0, exclude older revisions */ if ((model == 4 && stepping == 0) || diff --git a/drivers/video/fbdev/geode/video_gx.c b/drivers/video/fbdev/geode/video_gx.c index 6082f653c68a..67773e8bbb95 100644 --- a/drivers/video/fbdev/geode/video_gx.c +++ b/drivers/video/fbdev/geode/video_gx.c @@ -127,7 +127,7 @@ void gx_set_dclk_frequency(struct fb_info *info) int timeout = 1000; /* Rev. 1 Geode GXs use a 14 MHz reference clock instead of 48 MHz. */ - if (cpu_data(0).x86_mask == 1) { + if (cpu_data(0).x86_stepping == 1) { pll_table = gx_pll_table_14MHz; pll_table_len = ARRAY_SIZE(gx_pll_table_14MHz); } else { -- cgit v1.2.3-55-g7522 From 9de29eac8d2189424d81c0d840cd0469aa3d41c8 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Wed, 14 Feb 2018 10:14:17 +0300 Subject: x86/spectre: Fix an error message If i == ARRAY_SIZE(mitigation_options) then we accidentally print garbage from one space beyond the end of the mitigation_options[] array. Signed-off-by: Dan Carpenter Cc: Andy Lutomirski Cc: Borislav Petkov Cc: David Woodhouse Cc: Greg Kroah-Hartman Cc: KarimAllah Ahmed Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: kernel-janitors@vger.kernel.org Fixes: 9005c6834c0f ("x86/spectre: Simplify spectre_v2 command line parsing") Link: http://lkml.kernel.org/r/20180214071416.GA26677@mwanda Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/bugs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 4acf16a76d1e..d71c8b54b696 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -174,7 +174,7 @@ static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void) } if (i >= ARRAY_SIZE(mitigation_options)) { - pr_err("unknown option (%s). Switching to AUTO select\n", mitigation_options[i].option); + pr_err("unknown option (%s). Switching to AUTO select\n", arg); return SPECTRE_V2_CMD_AUTO; } } -- cgit v1.2.3-55-g7522 From 24dbc6000f4b9b0ef5a9daecb161f1907733765a Mon Sep 17 00:00:00 2001 From: Gustavo A. R. Silva Date: Tue, 13 Feb 2018 13:22:08 -0600 Subject: x86/cpu: Change type of x86_cache_size variable to unsigned int Currently, x86_cache_size is of type int, which makes no sense as we will never have a valid cache size equal or less than 0. So instead of initializing this variable to -1, it can perfectly be initialized to 0 and use it as an unsigned variable instead. Suggested-by: Thomas Gleixner Signed-off-by: Gustavo A. R. Silva Cc: Borislav Petkov Cc: Linus Torvalds Cc: Peter Zijlstra Addresses-Coverity-ID: 1464429 Link: http://lkml.kernel.org/r/20180213192208.GA26414@embeddedor.com Signed-off-by: Ingo Molnar --- arch/x86/include/asm/processor.h | 2 +- arch/x86/kernel/cpu/common.c | 2 +- arch/x86/kernel/cpu/microcode/intel.c | 2 +- arch/x86/kernel/cpu/proc.c | 4 ++-- 4 files changed, 5 insertions(+), 5 deletions(-) (limited to 'arch') diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index b7c8583328c7..44c2c4ec6d60 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -109,7 +109,7 @@ struct cpuinfo_x86 { char x86_vendor_id[16]; char x86_model_id[64]; /* in KB - valid for CPUS which support this call: */ - int x86_cache_size; + unsigned int x86_cache_size; int x86_cache_alignment; /* In bytes */ /* Cache QoS architectural values: */ int x86_cache_max_rmid; /* max index */ diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index a7d8df641a4c..824aee0117bb 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1184,7 +1184,7 @@ static void identify_cpu(struct cpuinfo_x86 *c) int i; c->loops_per_jiffy = loops_per_jiffy; - c->x86_cache_size = -1; + c->x86_cache_size = 0; c->x86_vendor = X86_VENDOR_UNKNOWN; c->x86_model = c->x86_stepping = 0; /* So far unknown... */ c->x86_vendor_id[0] = '\0'; /* Unset */ diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c index b94279bb5c04..a15db2b4e0d6 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -982,7 +982,7 @@ static struct microcode_ops microcode_intel_ops = { static int __init calc_llc_size_per_core(struct cpuinfo_x86 *c) { - u64 llc_size = c->x86_cache_size * 1024; + u64 llc_size = c->x86_cache_size * 1024ULL; do_div(llc_size, c->x86_max_cores); diff --git a/arch/x86/kernel/cpu/proc.c b/arch/x86/kernel/cpu/proc.c index ee4cc388e8d3..2c8522a39ed5 100644 --- a/arch/x86/kernel/cpu/proc.c +++ b/arch/x86/kernel/cpu/proc.c @@ -91,8 +91,8 @@ static int show_cpuinfo(struct seq_file *m, void *v) } /* Cache size */ - if (c->x86_cache_size >= 0) - seq_printf(m, "cache size\t: %d KB\n", c->x86_cache_size); + if (c->x86_cache_size) + seq_printf(m, "cache size\t: %u KB\n", c->x86_cache_size); show_cpuinfo_core(m, c, cpu); show_cpuinfo_misc(m, c); -- cgit v1.2.3-55-g7522 From e48657573481a5dff7cfdc3d57005c80aa816500 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Wed, 14 Feb 2018 08:39:11 +0100 Subject: x86/entry/64: Fix CR3 restore in paranoid_exit() Josh Poimboeuf noticed the following bug: "The paranoid exit code only restores the saved CR3 when it switches back to the user GS. However, even in the kernel GS case, it's possible that it needs to restore a user CR3, if for example, the paranoid exception occurred in the syscall exit path between SWITCH_TO_USER_CR3_STACK and SWAPGS." Josh also confirmed via targeted testing that it's possible to hit this bug. Fix the bug by also restoring CR3 in the paranoid_exit_no_swapgs branch. The reason we haven't seen this bug reported by users yet is probably because "paranoid" entry points are limited to the following cases: idtentry double_fault do_double_fault has_error_code=1 paranoid=2 idtentry debug do_debug has_error_code=0 paranoid=1 shift_ist=DEBUG_STACK idtentry int3 do_int3 has_error_code=0 paranoid=1 shift_ist=DEBUG_STACK idtentry machine_check do_mce has_error_code=0 paranoid=1 Amongst those entry points only machine_check is one that will interrupt an IRQS-off critical section asynchronously - and machine check events are rare. The other main asynchronous entries are NMI entries, which can be very high-freq with perf profiling, but they are special: they don't use the 'idtentry' macro but are open coded and restore user CR3 unconditionally so don't have this bug. Reported-and-tested-by: Josh Poimboeuf Reviewed-by: Andy Lutomirski Acked-by: Thomas Gleixner Cc: Arjan van de Ven Cc: Borislav Petkov Cc: Dan Williams Cc: Dave Hansen Cc: David Woodhouse Cc: Greg Kroah-Hartman Cc: Linus Torvalds Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/20180214073910.boevmg65upbk3vqb@gmail.com Signed-off-by: Ingo Molnar --- arch/x86/entry/entry_64.S | 1 + 1 file changed, 1 insertion(+) (limited to 'arch') diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 1c54204207d8..4fd9044e72e7 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -1168,6 +1168,7 @@ ENTRY(paranoid_exit) jmp .Lparanoid_exit_restore .Lparanoid_exit_no_swapgs: TRACE_IRQS_IRETQ_DEBUG + RESTORE_CR3 scratch_reg=%rbx save_reg=%r14 .Lparanoid_exit_restore: jmp restore_regs_and_return_to_kernel END(paranoid_exit) -- cgit v1.2.3-55-g7522 From 5ce0bad4ccd04c8a989e94d3c89e4e796ac22e48 Mon Sep 17 00:00:00 2001 From: Daniel Schultz Date: Tue, 13 Feb 2018 10:44:32 +0100 Subject: ARM: dts: rockchip: Remove 1.8 GHz operation point from phycore som Rockchip recommends to run the CPU cores only with operations points of 1.6 GHz or lower. Removed the cpu0 node with too high operation points and use the default values instead. Fixes: 903d31e34628 ("ARM: dts: rockchip: Add support for phyCORE-RK3288 SoM") Cc: stable@vger.kernel.org Signed-off-by: Daniel Schultz Signed-off-by: Heiko Stuebner --- arch/arm/boot/dts/rk3288-phycore-som.dtsi | 20 -------------------- 1 file changed, 20 deletions(-) (limited to 'arch') diff --git a/arch/arm/boot/dts/rk3288-phycore-som.dtsi b/arch/arm/boot/dts/rk3288-phycore-som.dtsi index 99cfae875e12..5eae4776ffde 100644 --- a/arch/arm/boot/dts/rk3288-phycore-som.dtsi +++ b/arch/arm/boot/dts/rk3288-phycore-som.dtsi @@ -110,26 +110,6 @@ }; }; -&cpu0 { - cpu0-supply = <&vdd_cpu>; - operating-points = < - /* KHz uV */ - 1800000 1400000 - 1608000 1350000 - 1512000 1300000 - 1416000 1200000 - 1200000 1100000 - 1008000 1050000 - 816000 1000000 - 696000 950000 - 600000 900000 - 408000 900000 - 312000 900000 - 216000 900000 - 126000 900000 - >; -}; - &emmc { status = "okay"; bus-width = <8>; -- cgit v1.2.3-55-g7522 From 6ac5a11dc674bc5016ea716e8082fff61f524dc1 Mon Sep 17 00:00:00 2001 From: Max Filippov Date: Tue, 13 Feb 2018 15:31:05 -0800 Subject: xtensa: fix high memory/reserved memory collision Xtensa memory initialization code frees high memory pages without checking whether they are in the reserved memory regions or not. That results in invalid value of totalram_pages and duplicate page usage by CMA and highmem. It produces a bunch of BUGs at startup looking like this: BUG: Bad page state in process swapper pfn:70800 page:be60c000 count:0 mapcount:-127 mapping: (null) index:0x1 flags: 0x80000000() raw: 80000000 00000000 00000001 ffffff80 00000000 be60c014 be60c014 0000000a page dumped because: nonzero mapcount Modules linked in: CPU: 0 PID: 1 Comm: swapper Tainted: G B 4.16.0-rc1-00015-g7928b2cbe55b-dirty #23 Stack: bd839d33 00000000 00000018 ba97b64c a106578c bd839d70 be60c000 00000000 a1378054 bd86a000 00000003 ba97b64c a1066166 bd839da0 be60c000 ffe00000 a1066b58 bd839dc0 be504000 00000000 000002f4 bd838000 00000000 0000001e Call Trace: [] bad_page+0xac/0xd0 [] free_pages_check_bad+0x34/0x4c [] __free_pages_ok+0xae/0x14c [] __free_pages+0x30/0x64 [] init_cma_reserved_pageblock+0x35/0x44 [] cma_init_reserved_areas+0xf4/0x148 [] do_one_initcall+0x80/0xf8 [] kernel_init_freeable+0xda/0x13c [] kernel_init+0x9/0xd0 [] ret_from_kernel_thread+0xc/0x18 Only free high memory pages that are not reserved. Cc: stable@vger.kernel.org Signed-off-by: Max Filippov --- arch/xtensa/mm/init.c | 70 +++++++++++++++++++++++++++++++++++++++++++++------ 1 file changed, 63 insertions(+), 7 deletions(-) (limited to 'arch') diff --git a/arch/xtensa/mm/init.c b/arch/xtensa/mm/init.c index d776ec0d7b22..34aead7dcb48 100644 --- a/arch/xtensa/mm/init.c +++ b/arch/xtensa/mm/init.c @@ -79,19 +79,75 @@ void __init zones_init(void) free_area_init_node(0, zones_size, ARCH_PFN_OFFSET, NULL); } +#ifdef CONFIG_HIGHMEM +static void __init free_area_high(unsigned long pfn, unsigned long end) +{ + for (; pfn < end; pfn++) + free_highmem_page(pfn_to_page(pfn)); +} + +static void __init free_highpages(void) +{ + unsigned long max_low = max_low_pfn; + struct memblock_region *mem, *res; + + reset_all_zones_managed_pages(); + /* set highmem page free */ + for_each_memblock(memory, mem) { + unsigned long start = memblock_region_memory_base_pfn(mem); + unsigned long end = memblock_region_memory_end_pfn(mem); + + /* Ignore complete lowmem entries */ + if (end <= max_low) + continue; + + if (memblock_is_nomap(mem)) + continue; + + /* Truncate partial highmem entries */ + if (start < max_low) + start = max_low; + + /* Find and exclude any reserved regions */ + for_each_memblock(reserved, res) { + unsigned long res_start, res_end; + + res_start = memblock_region_reserved_base_pfn(res); + res_end = memblock_region_reserved_end_pfn(res); + + if (res_end < start) + continue; + if (res_start < start) + res_start = start; + if (res_start > end) + res_start = end; + if (res_end > end) + res_end = end; + if (res_start != start) + free_area_high(start, res_start); + start = res_end; + if (start == end) + break; + } + + /* And now free anything which remains */ + if (start < end) + free_area_high(start, end); + } +} +#else +static void __init free_highpages(void) +{ +} +#endif + /* * Initialize memory pages. */ void __init mem_init(void) { -#ifdef CONFIG_HIGHMEM - unsigned long tmp; - - reset_all_zones_managed_pages(); - for (tmp = max_low_pfn; tmp < max_pfn; tmp++) - free_highmem_page(pfn_to_page(tmp)); -#endif + free_highpages(); max_mapnr = max_pfn - ARCH_PFN_OFFSET; high_memory = (void *)__va(max_low_pfn << PAGE_SHIFT); -- cgit v1.2.3-55-g7522 From 67870eb1204223598ea6d8a4467b482e9f5875b5 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 2 Feb 2018 16:07:34 +0100 Subject: ARM: kvm: fix building with gcc-8 In banked-sr.c, we use a top-level '__asm__(".arch_extension virt")' statement to allow compilation of a multi-CPU kernel for ARMv6 and older ARMv7-A that don't normally support access to the banked registers. This is considered to be a programming error by the gcc developers and will no longer work in gcc-8, where we now get a build error: /tmp/cc4Qy7GR.s:34: Error: Banked registers are not available with this architecture. -- `mrs r3,SP_usr' /tmp/cc4Qy7GR.s:41: Error: Banked registers are not available with this architecture. -- `mrs r3,ELR_hyp' /tmp/cc4Qy7GR.s:55: Error: Banked registers are not available with this architecture. -- `mrs r3,SP_svc' /tmp/cc4Qy7GR.s:62: Error: Banked registers are not available with this architecture. -- `mrs r3,LR_svc' /tmp/cc4Qy7GR.s:69: Error: Banked registers are not available with this architecture. -- `mrs r3,SPSR_svc' /tmp/cc4Qy7GR.s:76: Error: Banked registers are not available with this architecture. -- `mrs r3,SP_abt' Passign the '-march-armv7ve' flag to gcc works, and is ok here, because we know the functions won't ever be called on pre-ARMv7VE machines. Unfortunately, older compiler versions (4.8 and earlier) do not understand that flag, so we still need to keep the asm around. Backporting to stable kernels (4.6+) is needed to allow those to be built with future compilers as well. Link: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=84129 Fixes: 33280b4cd1dc ("ARM: KVM: Add banked registers save/restore") Cc: stable@vger.kernel.org Signed-off-by: Arnd Bergmann Signed-off-by: Christoffer Dall --- arch/arm/kvm/hyp/Makefile | 5 +++++ arch/arm/kvm/hyp/banked-sr.c | 4 ++++ 2 files changed, 9 insertions(+) (limited to 'arch') diff --git a/arch/arm/kvm/hyp/Makefile b/arch/arm/kvm/hyp/Makefile index 5638ce0c9524..63d6b404d88e 100644 --- a/arch/arm/kvm/hyp/Makefile +++ b/arch/arm/kvm/hyp/Makefile @@ -7,6 +7,8 @@ ccflags-y += -fno-stack-protector -DDISABLE_BRANCH_PROFILING KVM=../../../../virt/kvm +CFLAGS_ARMV7VE :=$(call cc-option, -march=armv7ve) + obj-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/hyp/vgic-v2-sr.o obj-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/hyp/vgic-v3-sr.o obj-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/hyp/timer-sr.o @@ -15,7 +17,10 @@ obj-$(CONFIG_KVM_ARM_HOST) += tlb.o obj-$(CONFIG_KVM_ARM_HOST) += cp15-sr.o obj-$(CONFIG_KVM_ARM_HOST) += vfp.o obj-$(CONFIG_KVM_ARM_HOST) += banked-sr.o +CFLAGS_banked-sr.o += $(CFLAGS_ARMV7VE) + obj-$(CONFIG_KVM_ARM_HOST) += entry.o obj-$(CONFIG_KVM_ARM_HOST) += hyp-entry.o obj-$(CONFIG_KVM_ARM_HOST) += switch.o +CFLAGS_switch.o += $(CFLAGS_ARMV7VE) obj-$(CONFIG_KVM_ARM_HOST) += s2-setup.o diff --git a/arch/arm/kvm/hyp/banked-sr.c b/arch/arm/kvm/hyp/banked-sr.c index 111bda8cdebd..be4b8b0a40ad 100644 --- a/arch/arm/kvm/hyp/banked-sr.c +++ b/arch/arm/kvm/hyp/banked-sr.c @@ -20,6 +20,10 @@ #include +/* + * gcc before 4.9 doesn't understand -march=armv7ve, so we have to + * trick the assembler. + */ __asm__(".arch_extension virt"); void __hyp_text __banked_save_state(struct kvm_cpu_context *ctxt) -- cgit v1.2.3-55-g7522 From 5efad9eee33ee5fc4bf3059f74f3932a638534d1 Mon Sep 17 00:00:00 2001 From: James Hogan Date: Wed, 31 Jan 2018 22:24:46 +0000 Subject: sparc,leon: Select USB_UHCI_BIG_ENDIAN_{MMIO,DESC} Now that USB_UHCI_BIG_ENDIAN_MMIO and USB_UHCI_BIG_ENDIAN_DESC are moved outside of the USB_SUPPORT conditional, simply select them from SPARC_LEON rather than by the symbol's defaults in drivers/usb/Kconfig, similar to how it is done for USB_EHCI_BIG_ENDIAN_MMIO and USB_EHCI_BIG_ENDIAN_DESC. Signed-off-by: James Hogan Cc: "David S. Miller" Cc: Greg Kroah-Hartman Cc: Corentin Labbe Cc: sparclinux@vger.kernel.org Cc: linux-usb@vger.kernel.org Acked-by: David S. Miller Patchwork: https://patchwork.linux-mips.org/patch/18560/ --- arch/sparc/Kconfig | 2 ++ drivers/usb/Kconfig | 2 -- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'arch') diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index 6bf594ace663..8767e45f1b2b 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -430,6 +430,8 @@ config SPARC_LEON depends on SPARC32 select USB_EHCI_BIG_ENDIAN_MMIO select USB_EHCI_BIG_ENDIAN_DESC + select USB_UHCI_BIG_ENDIAN_MMIO + select USB_UHCI_BIG_ENDIAN_DESC ---help--- If you say Y here if you are running on a SPARC-LEON processor. The LEON processor is a synthesizable VHDL model of the diff --git a/drivers/usb/Kconfig b/drivers/usb/Kconfig index 65812a2f60b4..148f3ee70286 100644 --- a/drivers/usb/Kconfig +++ b/drivers/usb/Kconfig @@ -21,11 +21,9 @@ config USB_EHCI_BIG_ENDIAN_DESC config USB_UHCI_BIG_ENDIAN_MMIO bool - default y if SPARC_LEON config USB_UHCI_BIG_ENDIAN_DESC bool - default y if SPARC_LEON menuconfig USB_SUPPORT bool "USB support" -- cgit v1.2.3-55-g7522 From ca9eee95a2decc6f60bed65b5b836a26bff825c1 Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Thu, 15 Feb 2018 14:05:53 +0000 Subject: arm64: dts: rockchip: Fix DWMMC clocks Trying to boot an RK3328 box with an HS200-capable eMMC, I see said eMMC fail to initialise as it can't run its tuning procedure, because the sample clock is missing. Upon closer inspection, whilst the clock is present in the DT, its name is subtly incorrect per the binding, so __of_clk_get_by_name() never finds it. By inspection, the drive clock suffers from a similar problem, so has never worked properly either. Fix up all instances of the incorrect clock names across the 64-bit DTs. Fixes: d717f7352ec6 ("arm64: dts: rockchip: add sdmmc/sdio/emmc nodes for RK3328 SoCs") Fixes: b790c2cab5ca ("arm64: dts: add Rockchip rk3368 core dtsi and board dts for the r88 board") Signed-off-by: Robin Murphy Signed-off-by: Heiko Stuebner --- arch/arm64/boot/dts/rockchip/rk3328.dtsi | 6 +++--- arch/arm64/boot/dts/rockchip/rk3368.dtsi | 2 +- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'arch') diff --git a/arch/arm64/boot/dts/rockchip/rk3328.dtsi b/arch/arm64/boot/dts/rockchip/rk3328.dtsi index a037ee56fead..cae341554486 100644 --- a/arch/arm64/boot/dts/rockchip/rk3328.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3328.dtsi @@ -730,7 +730,7 @@ interrupts = ; clocks = <&cru HCLK_SDMMC>, <&cru SCLK_SDMMC>, <&cru SCLK_SDMMC_DRV>, <&cru SCLK_SDMMC_SAMPLE>; - clock-names = "biu", "ciu", "ciu_drv", "ciu_sample"; + clock-names = "biu", "ciu", "ciu-drive", "ciu-sample"; fifo-depth = <0x100>; status = "disabled"; }; @@ -741,7 +741,7 @@ interrupts = ; clocks = <&cru HCLK_SDIO>, <&cru SCLK_SDIO>, <&cru SCLK_SDIO_DRV>, <&cru SCLK_SDIO_SAMPLE>; - clock-names = "biu", "ciu", "ciu_drv", "ciu_sample"; + clock-names = "biu", "ciu", "ciu-drive", "ciu-sample"; fifo-depth = <0x100>; status = "disabled"; }; @@ -752,7 +752,7 @@ interrupts = ; clocks = <&cru HCLK_EMMC>, <&cru SCLK_EMMC>, <&cru SCLK_EMMC_DRV>, <&cru SCLK_EMMC_SAMPLE>; - clock-names = "biu", "ciu", "ciu_drv", "ciu_sample"; + clock-names = "biu", "ciu", "ciu-drive", "ciu-sample"; fifo-depth = <0x100>; status = "disabled"; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3368.dtsi b/arch/arm64/boot/dts/rockchip/rk3368.dtsi index aa4d07046a7b..03458ac44201 100644 --- a/arch/arm64/boot/dts/rockchip/rk3368.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3368.dtsi @@ -257,7 +257,7 @@ max-frequency = <150000000>; clocks = <&cru HCLK_SDIO0>, <&cru SCLK_SDIO0>, <&cru SCLK_SDIO0_DRV>, <&cru SCLK_SDIO0_SAMPLE>; - clock-names = "biu", "ciu", "ciu_drv", "ciu_sample"; + clock-names = "biu", "ciu", "ciu-drive", "ciu-sample"; fifo-depth = <0x100>; interrupts = ; resets = <&cru SRST_SDIO0>; -- cgit v1.2.3-55-g7522 From f960cfd12650fad43c1cde07a1f7642cf2c57f97 Mon Sep 17 00:00:00 2001 From: Matthew Whitehead Date: Thu, 15 Feb 2018 11:54:54 -0500 Subject: x86/Kconfig: Add missing i586-class CPUs to the X86_CMPXCHG64 Kconfig group Several i586-class CPUs supporting this instruction are missing from the X86_CMPXCHG64 config group. Using a configuration with either M586TSC or M586MMX currently sets X86_MINIMUM_CPU_FAMILY=4 instead of the correct value of 5. Booting on an i486 it will fail to generate the "This kernel requires an i586 CPU, but only detected an i486 CPU" message and intentional halt as expected. It will instead just silently hang when it hits i586-specific instructions. The M586 CPU is not in this list because at least the Cyrix 5x86 lacks this instruction, and perhaps others. Signed-off-by: Matthew Whitehead Cc: Andy Lutomirski Cc: Arjan van de Ven Cc: Borislav Petkov Cc: Brian Gerst Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Josh Poimboeuf Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/1518713696-11360-1-git-send-email-tedheadster@gmail.com Signed-off-by: Ingo Molnar --- arch/x86/Kconfig.cpu | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu index 65a9a4716e34..ec64aa728727 100644 --- a/arch/x86/Kconfig.cpu +++ b/arch/x86/Kconfig.cpu @@ -374,7 +374,7 @@ config X86_TSC config X86_CMPXCHG64 def_bool y - depends on X86_PAE || X86_64 || MCORE2 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MATOM + depends on X86_PAE || X86_64 || MCORE2 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || M586TSC || M586MMX || MATOM || MGEODE_LX || MGEODEGX1 || MK6 || MK7 || MK8 # this should be set for all -march=.. options where the compiler # generates cmov. -- cgit v1.2.3-55-g7522 From 69b8d3fcabdc81d9efd82b4a506c8279cbaba692 Mon Sep 17 00:00:00 2001 From: Matthew Whitehead Date: Thu, 15 Feb 2018 11:54:55 -0500 Subject: x86/Kconfig: Exclude i586-class CPUs lacking PAE support from the HIGHMEM64G Kconfig group i586-class machines also lack support for Physical Address Extension (PAE), so add them to the exclusion list. Signed-off-by: Matthew Whitehead Cc: Andy Lutomirski Cc: Arjan van de Ven Cc: Borislav Petkov Cc: Brian Gerst Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Josh Poimboeuf Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/1518713696-11360-2-git-send-email-tedheadster@gmail.com Signed-off-by: Ingo Molnar --- arch/x86/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index a528c14d45a5..c1236b187824 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -1404,7 +1404,7 @@ config HIGHMEM4G config HIGHMEM64G bool "64GB" - depends on !M486 + depends on !M486 && !M586 && !M586TSC && !M586MMX && !MGEODE_LX && !MGEODEGX1 && !MCYRIXIII && !MELAN && !MWINCHIPC6 && !WINCHIP3D && !MK6 select X86_PAE ---help--- Select this if you have a 32-bit processor and more than 4 -- cgit v1.2.3-55-g7522 From 25d76ac888216c369dea91768764728b83769799 Mon Sep 17 00:00:00 2001 From: Matthew Whitehead Date: Thu, 15 Feb 2018 11:54:56 -0500 Subject: x86/Kconfig: Explicitly enumerate i686-class CPUs in Kconfig The X86_P6_NOP config class leaves out many i686-class CPUs. Instead, explicitly enumerate all these CPUs. Using a configuration with M686 currently sets X86_MINIMUM_CPU_FAMILY=5 instead of the correct value of 6. Booting on an i586 it will fail to generate the "This kernel requires an i686 CPU, but only detected an i586 CPU" message and intentional halt as expected. It will instead just silently hang when it hits i686-specific instructions. Signed-off-by: Matthew Whitehead Cc: Andy Lutomirski Cc: Arjan van de Ven Cc: Borislav Petkov Cc: Brian Gerst Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Josh Poimboeuf Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/1518713696-11360-3-git-send-email-tedheadster@gmail.com Signed-off-by: Ingo Molnar --- arch/x86/Kconfig.cpu | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu index ec64aa728727..8b8d2297d486 100644 --- a/arch/x86/Kconfig.cpu +++ b/arch/x86/Kconfig.cpu @@ -385,7 +385,7 @@ config X86_CMOV config X86_MINIMUM_CPU_FAMILY int default "64" if X86_64 - default "6" if X86_32 && X86_P6_NOP + default "6" if X86_32 && (MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MVIAC3_2 || MVIAC7 || MEFFICEON || MATOM || MCRUSOE || MCORE2 || MK7 || MK8) default "5" if X86_32 && X86_CMPXCHG64 default "4" -- cgit v1.2.3-55-g7522 From e78c637127ee7683d606737f2e62b5da6fd7b1c3 Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Thu, 15 Feb 2018 14:05:54 +0000 Subject: ARM: dts: rockchip: Fix DWMMC clocks Trying to boot an RK3328 box with an HS200-capable eMMC, I see said eMMC fail to initialise as it can't run its tuning procedure, because the sample clock is missing. Upon closer inspection, whilst the clock is present in the DT, its name is subtly incorrect per the binding, so __of_clk_get_by_name() never finds it. By inspection, the drive clock suffers from a similar problem, so has never worked properly either. This error has propagated across the 32-bit DTs too, so fix those up. Fixes: 187d7967a5ee ("ARM: dts: rockchip: add the sdio/sdmmc node for rk3036") Fixes: faea098e1808 ("ARM: dts: rockchip: add core rk3036 dtsi") Fixes: 9848ebeb952d ("ARM: dts: rockchip: add core rk3228 dtsi") Signed-off-by: Robin Murphy Signed-off-by: Heiko Stuebner --- arch/arm/boot/dts/rk3036.dtsi | 4 ++-- arch/arm/boot/dts/rk322x.dtsi | 6 +++--- 2 files changed, 5 insertions(+), 5 deletions(-) (limited to 'arch') diff --git a/arch/arm/boot/dts/rk3036.dtsi b/arch/arm/boot/dts/rk3036.dtsi index 3b704cfed69a..a97458112ff6 100644 --- a/arch/arm/boot/dts/rk3036.dtsi +++ b/arch/arm/boot/dts/rk3036.dtsi @@ -280,7 +280,7 @@ max-frequency = <37500000>; clocks = <&cru HCLK_SDIO>, <&cru SCLK_SDIO>, <&cru SCLK_SDIO_DRV>, <&cru SCLK_SDIO_SAMPLE>; - clock-names = "biu", "ciu", "ciu_drv", "ciu_sample"; + clock-names = "biu", "ciu", "ciu-drive", "ciu-sample"; fifo-depth = <0x100>; interrupts = ; resets = <&cru SRST_SDIO>; @@ -298,7 +298,7 @@ max-frequency = <37500000>; clocks = <&cru HCLK_EMMC>, <&cru SCLK_EMMC>, <&cru SCLK_EMMC_DRV>, <&cru SCLK_EMMC_SAMPLE>; - clock-names = "biu", "ciu", "ciu_drv", "ciu_sample"; + clock-names = "biu", "ciu", "ciu-drive", "ciu-sample"; default-sample-phase = <158>; disable-wp; dmas = <&pdma 12>; diff --git a/arch/arm/boot/dts/rk322x.dtsi b/arch/arm/boot/dts/rk322x.dtsi index 780ec3a99b21..341deaf62ff6 100644 --- a/arch/arm/boot/dts/rk322x.dtsi +++ b/arch/arm/boot/dts/rk322x.dtsi @@ -621,7 +621,7 @@ interrupts = ; clocks = <&cru HCLK_SDMMC>, <&cru SCLK_SDMMC>, <&cru SCLK_SDMMC_DRV>, <&cru SCLK_SDMMC_SAMPLE>; - clock-names = "biu", "ciu", "ciu_drv", "ciu_sample"; + clock-names = "biu", "ciu", "ciu-drive", "ciu-sample"; fifo-depth = <0x100>; pinctrl-names = "default"; pinctrl-0 = <&sdmmc_clk &sdmmc_cmd &sdmmc_bus4>; @@ -634,7 +634,7 @@ interrupts = ; clocks = <&cru HCLK_SDIO>, <&cru SCLK_SDIO>, <&cru SCLK_SDIO_DRV>, <&cru SCLK_SDIO_SAMPLE>; - clock-names = "biu", "ciu", "ciu_drv", "ciu_sample"; + clock-names = "biu", "ciu", "ciu-drive", "ciu-sample"; fifo-depth = <0x100>; pinctrl-names = "default"; pinctrl-0 = <&sdio_clk &sdio_cmd &sdio_bus4>; @@ -649,7 +649,7 @@ max-frequency = <37500000>; clocks = <&cru HCLK_EMMC>, <&cru SCLK_EMMC>, <&cru SCLK_EMMC_DRV>, <&cru SCLK_EMMC_SAMPLE>; - clock-names = "biu", "ciu", "ciu_drv", "ciu_sample"; + clock-names = "biu", "ciu", "ciu-drive", "ciu-sample"; bus-width = <8>; default-sample-phase = <158>; fifo-depth = <0x100>; -- cgit v1.2.3-55-g7522 From 2c10636a0b9c689450e85f9945583920f50337c9 Mon Sep 17 00:00:00 2001 From: Nathan Fontenot Date: Thu, 15 Feb 2018 21:27:41 -0600 Subject: powerpc/pseries: Check for zero filled ibm,dynamic-memory property Some versions of QEMU will produce an ibm,dynamic-reconfiguration-memory node with a ibm,dynamic-memory property that is zero-filled. This causes the drmem code to oops trying to parse this property. The fix for this is to validate that the property does contain LMB entries before trying to parse it and bail if the count is zero. Oops: Kernel access of bad area, sig: 11 [#1] DAR: 0000000000000010 NIP read_drconf_v1_cell+0x54/0x9c LR read_drconf_v1_cell+0x48/0x9c Call Trace: __param_initcall_debug+0x0/0x28 (unreliable) drmem_init+0x144/0x2f8 do_one_initcall+0x64/0x1d0 kernel_init_freeable+0x298/0x38c kernel_init+0x24/0x160 ret_from_kernel_thread+0x5c/0xb4 The ibm,dynamic-reconfiguration-memory device tree property generated that causes this: ibm,dynamic-reconfiguration-memory { ibm,lmb-size = <0x0 0x10000000>; ibm,memory-flags-mask = <0xff>; ibm,dynamic-memory = <0x0 0x0 0x0 0x0 0x0 0x0>; linux,phandle = <0x7e57eed8>; ibm,associativity-lookup-arrays = <0x1 0x4 0x0 0x0 0x0 0x0>; ibm,memory-preservation-time = <0x0>; }; Signed-off-by: Nathan Fontenot Reviewed-by: Cyril Bur Tested-by: Daniel Black [mpe: Trim oops report] Signed-off-by: Michael Ellerman --- arch/powerpc/mm/drmem.c | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'arch') diff --git a/arch/powerpc/mm/drmem.c b/arch/powerpc/mm/drmem.c index 1604110c4238..916844f99c64 100644 --- a/arch/powerpc/mm/drmem.c +++ b/arch/powerpc/mm/drmem.c @@ -216,6 +216,8 @@ static void __init __walk_drmem_v1_lmbs(const __be32 *prop, const __be32 *usm, u32 i, n_lmbs; n_lmbs = of_read_number(prop++, 1); + if (n_lmbs == 0) + return; for (i = 0; i < n_lmbs; i++) { read_drconf_v1_cell(&lmb, &prop); @@ -245,6 +247,8 @@ static void __init __walk_drmem_v2_lmbs(const __be32 *prop, const __be32 *usm, u32 i, j, lmb_sets; lmb_sets = of_read_number(prop++, 1); + if (lmb_sets == 0) + return; for (i = 0; i < lmb_sets; i++) { read_drconf_v2_cell(&dr_cell, &prop); @@ -354,6 +358,8 @@ static void __init init_drmem_v1_lmbs(const __be32 *prop) struct drmem_lmb *lmb; drmem_info->n_lmbs = of_read_number(prop++, 1); + if (drmem_info->n_lmbs == 0) + return; drmem_info->lmbs = kcalloc(drmem_info->n_lmbs, sizeof(*lmb), GFP_KERNEL); @@ -373,6 +379,8 @@ static void __init init_drmem_v2_lmbs(const __be32 *prop) int lmb_index; lmb_sets = of_read_number(prop++, 1); + if (lmb_sets == 0) + return; /* first pass, calculate the number of LMBs */ p = prop; -- cgit v1.2.3-55-g7522 From 20a004e7b017cce282a46ac5d02c2b9c6b9bb1fa Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Thu, 15 Feb 2018 11:14:56 +0000 Subject: arm64: mm: Use READ_ONCE/WRITE_ONCE when accessing page tables In many cases, page tables can be accessed concurrently by either another CPU (due to things like fast gup) or by the hardware page table walker itself, which may set access/dirty bits. In such cases, it is important to use READ_ONCE/WRITE_ONCE when accessing page table entries so that entries cannot be torn, merged or subject to apparent loss of coherence due to compiler transformations. Whilst there are some scenarios where this cannot happen (e.g. pinned kernel mappings for the linear region), the overhead of using READ_ONCE /WRITE_ONCE everywhere is minimal and makes the code an awful lot easier to reason about. This patch consistently uses these macros in the arch code, as well as explicitly namespacing pointers to page table entries from the entries themselves by using adopting a 'p' suffix for the former (as is sometimes used elsewhere in the kernel source). Tested-by: Yury Norov Tested-by: Richard Ruigrok Reviewed-by: Marc Zyngier Signed-off-by: Will Deacon Signed-off-by: Catalin Marinas --- arch/arm64/include/asm/hugetlb.h | 2 +- arch/arm64/include/asm/kvm_mmu.h | 26 ++-- arch/arm64/include/asm/mmu_context.h | 4 +- arch/arm64/include/asm/pgalloc.h | 44 +++--- arch/arm64/include/asm/pgtable.h | 23 +-- arch/arm64/kernel/efi.c | 2 +- arch/arm64/kernel/hibernate.c | 148 +++++++++--------- arch/arm64/mm/dump.c | 54 ++++--- arch/arm64/mm/fault.c | 44 +++--- arch/arm64/mm/hugetlbpage.c | 94 ++++++------ arch/arm64/mm/kasan_init.c | 70 ++++----- arch/arm64/mm/mmu.c | 282 ++++++++++++++++++----------------- arch/arm64/mm/pageattr.c | 32 ++-- 13 files changed, 426 insertions(+), 399 deletions(-) (limited to 'arch') diff --git a/arch/arm64/include/asm/hugetlb.h b/arch/arm64/include/asm/hugetlb.h index 1dca41bea16a..e73f68569624 100644 --- a/arch/arm64/include/asm/hugetlb.h +++ b/arch/arm64/include/asm/hugetlb.h @@ -22,7 +22,7 @@ static inline pte_t huge_ptep_get(pte_t *ptep) { - return *ptep; + return READ_ONCE(*ptep); } diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h index 9679067a1574..7faed6e48b46 100644 --- a/arch/arm64/include/asm/kvm_mmu.h +++ b/arch/arm64/include/asm/kvm_mmu.h @@ -185,42 +185,42 @@ static inline pmd_t kvm_s2pmd_mkexec(pmd_t pmd) return pmd; } -static inline void kvm_set_s2pte_readonly(pte_t *pte) +static inline void kvm_set_s2pte_readonly(pte_t *ptep) { pteval_t old_pteval, pteval; - pteval = READ_ONCE(pte_val(*pte)); + pteval = READ_ONCE(pte_val(*ptep)); do { old_pteval = pteval; pteval &= ~PTE_S2_RDWR; pteval |= PTE_S2_RDONLY; - pteval = cmpxchg_relaxed(&pte_val(*pte), old_pteval, pteval); + pteval = cmpxchg_relaxed(&pte_val(*ptep), old_pteval, pteval); } while (pteval != old_pteval); } -static inline bool kvm_s2pte_readonly(pte_t *pte) +static inline bool kvm_s2pte_readonly(pte_t *ptep) { - return (pte_val(*pte) & PTE_S2_RDWR) == PTE_S2_RDONLY; + return (READ_ONCE(pte_val(*ptep)) & PTE_S2_RDWR) == PTE_S2_RDONLY; } -static inline bool kvm_s2pte_exec(pte_t *pte) +static inline bool kvm_s2pte_exec(pte_t *ptep) { - return !(pte_val(*pte) & PTE_S2_XN); + return !(READ_ONCE(pte_val(*ptep)) & PTE_S2_XN); } -static inline void kvm_set_s2pmd_readonly(pmd_t *pmd) +static inline void kvm_set_s2pmd_readonly(pmd_t *pmdp) { - kvm_set_s2pte_readonly((pte_t *)pmd); + kvm_set_s2pte_readonly((pte_t *)pmdp); } -static inline bool kvm_s2pmd_readonly(pmd_t *pmd) +static inline bool kvm_s2pmd_readonly(pmd_t *pmdp) { - return kvm_s2pte_readonly((pte_t *)pmd); + return kvm_s2pte_readonly((pte_t *)pmdp); } -static inline bool kvm_s2pmd_exec(pmd_t *pmd) +static inline bool kvm_s2pmd_exec(pmd_t *pmdp) { - return !(pmd_val(*pmd) & PMD_S2_XN); + return !(READ_ONCE(pmd_val(*pmdp)) & PMD_S2_XN); } static inline bool kvm_page_empty(void *ptr) diff --git a/arch/arm64/include/asm/mmu_context.h b/arch/arm64/include/asm/mmu_context.h index 8d3331985d2e..39ec0b8a689e 100644 --- a/arch/arm64/include/asm/mmu_context.h +++ b/arch/arm64/include/asm/mmu_context.h @@ -141,13 +141,13 @@ static inline void cpu_install_idmap(void) * Atomically replaces the active TTBR1_EL1 PGD with a new VA-compatible PGD, * avoiding the possibility of conflicting TLB entries being allocated. */ -static inline void cpu_replace_ttbr1(pgd_t *pgd) +static inline void cpu_replace_ttbr1(pgd_t *pgdp) { typedef void (ttbr_replace_func)(phys_addr_t); extern ttbr_replace_func idmap_cpu_replace_ttbr1; ttbr_replace_func *replace_phys; - phys_addr_t pgd_phys = virt_to_phys(pgd); + phys_addr_t pgd_phys = virt_to_phys(pgdp); replace_phys = (void *)__pa_symbol(idmap_cpu_replace_ttbr1); diff --git a/arch/arm64/include/asm/pgalloc.h b/arch/arm64/include/asm/pgalloc.h index e9d9f1b006ef..2e05bcd944c8 100644 --- a/arch/arm64/include/asm/pgalloc.h +++ b/arch/arm64/include/asm/pgalloc.h @@ -36,23 +36,23 @@ static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr) return (pmd_t *)__get_free_page(PGALLOC_GFP); } -static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd) +static inline void pmd_free(struct mm_struct *mm, pmd_t *pmdp) { - BUG_ON((unsigned long)pmd & (PAGE_SIZE-1)); - free_page((unsigned long)pmd); + BUG_ON((unsigned long)pmdp & (PAGE_SIZE-1)); + free_page((unsigned long)pmdp); } -static inline void __pud_populate(pud_t *pud, phys_addr_t pmd, pudval_t prot) +static inline void __pud_populate(pud_t *pudp, phys_addr_t pmdp, pudval_t prot) { - set_pud(pud, __pud(__phys_to_pud_val(pmd) | prot)); + set_pud(pudp, __pud(__phys_to_pud_val(pmdp) | prot)); } -static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd) +static inline void pud_populate(struct mm_struct *mm, pud_t *pudp, pmd_t *pmdp) { - __pud_populate(pud, __pa(pmd), PMD_TYPE_TABLE); + __pud_populate(pudp, __pa(pmdp), PMD_TYPE_TABLE); } #else -static inline void __pud_populate(pud_t *pud, phys_addr_t pmd, pudval_t prot) +static inline void __pud_populate(pud_t *pudp, phys_addr_t pmdp, pudval_t prot) { BUILD_BUG(); } @@ -65,30 +65,30 @@ static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr) return (pud_t *)__get_free_page(PGALLOC_GFP); } -static inline void pud_free(struct mm_struct *mm, pud_t *pud) +static inline void pud_free(struct mm_struct *mm, pud_t *pudp) { - BUG_ON((unsigned long)pud & (PAGE_SIZE-1)); - free_page((unsigned long)pud); + BUG_ON((unsigned long)pudp & (PAGE_SIZE-1)); + free_page((unsigned long)pudp); } -static inline void __pgd_populate(pgd_t *pgdp, phys_addr_t pud, pgdval_t prot) +static inline void __pgd_populate(pgd_t *pgdp, phys_addr_t pudp, pgdval_t prot) { - set_pgd(pgdp, __pgd(__phys_to_pgd_val(pud) | prot)); + set_pgd(pgdp, __pgd(__phys_to_pgd_val(pudp) | prot)); } -static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, pud_t *pud) +static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgdp, pud_t *pudp) { - __pgd_populate(pgd, __pa(pud), PUD_TYPE_TABLE); + __pgd_populate(pgdp, __pa(pudp), PUD_TYPE_TABLE); } #else -static inline void __pgd_populate(pgd_t *pgdp, phys_addr_t pud, pgdval_t prot) +static inline void __pgd_populate(pgd_t *pgdp, phys_addr_t pudp, pgdval_t prot) { BUILD_BUG(); } #endif /* CONFIG_PGTABLE_LEVELS > 3 */ extern pgd_t *pgd_alloc(struct mm_struct *mm); -extern void pgd_free(struct mm_struct *mm, pgd_t *pgd); +extern void pgd_free(struct mm_struct *mm, pgd_t *pgdp); static inline pte_t * pte_alloc_one_kernel(struct mm_struct *mm, unsigned long addr) @@ -114,10 +114,10 @@ pte_alloc_one(struct mm_struct *mm, unsigned long addr) /* * Free a PTE table. */ -static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte) +static inline void pte_free_kernel(struct mm_struct *mm, pte_t *ptep) { - if (pte) - free_page((unsigned long)pte); + if (ptep) + free_page((unsigned long)ptep); } static inline void pte_free(struct mm_struct *mm, pgtable_t pte) @@ -126,10 +126,10 @@ static inline void pte_free(struct mm_struct *mm, pgtable_t pte) __free_page(pte); } -static inline void __pmd_populate(pmd_t *pmdp, phys_addr_t pte, +static inline void __pmd_populate(pmd_t *pmdp, phys_addr_t ptep, pmdval_t prot) { - set_pmd(pmdp, __pmd(__phys_to_pmd_val(pte) | prot)); + set_pmd(pmdp, __pmd(__phys_to_pmd_val(ptep) | prot)); } /* diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index 094374c82db0..7e2c27e63cd8 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -218,7 +218,7 @@ static inline pmd_t pmd_mkcont(pmd_t pmd) static inline void set_pte(pte_t *ptep, pte_t pte) { - *ptep = pte; + WRITE_ONCE(*ptep, pte); /* * Only if the new pte is valid and kernel, otherwise TLB maintenance @@ -250,6 +250,8 @@ extern void __sync_icache_dcache(pte_t pteval, unsigned long addr); static inline void set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte) { + pte_t old_pte; + if (pte_present(pte) && pte_user_exec(pte) && !pte_special(pte)) __sync_icache_dcache(pte, addr); @@ -258,14 +260,15 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr, * hardware updates of the pte (ptep_set_access_flags safely changes * valid ptes without going through an invalid entry). */ - if (IS_ENABLED(CONFIG_DEBUG_VM) && pte_valid(*ptep) && pte_valid(pte) && + old_pte = READ_ONCE(*ptep); + if (IS_ENABLED(CONFIG_DEBUG_VM) && pte_valid(old_pte) && pte_valid(pte) && (mm == current->active_mm || atomic_read(&mm->mm_users) > 1)) { VM_WARN_ONCE(!pte_young(pte), "%s: racy access flag clearing: 0x%016llx -> 0x%016llx", - __func__, pte_val(*ptep), pte_val(pte)); - VM_WARN_ONCE(pte_write(*ptep) && !pte_dirty(pte), + __func__, pte_val(old_pte), pte_val(pte)); + VM_WARN_ONCE(pte_write(old_pte) && !pte_dirty(pte), "%s: racy dirty state clearing: 0x%016llx -> 0x%016llx", - __func__, pte_val(*ptep), pte_val(pte)); + __func__, pte_val(old_pte), pte_val(pte)); } set_pte(ptep, pte); @@ -431,7 +434,7 @@ extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, static inline void set_pmd(pmd_t *pmdp, pmd_t pmd) { - *pmdp = pmd; + WRITE_ONCE(*pmdp, pmd); dsb(ishst); isb(); } @@ -482,7 +485,7 @@ static inline phys_addr_t pmd_page_paddr(pmd_t pmd) static inline void set_pud(pud_t *pudp, pud_t pud) { - *pudp = pud; + WRITE_ONCE(*pudp, pud); dsb(ishst); isb(); } @@ -500,7 +503,7 @@ static inline phys_addr_t pud_page_paddr(pud_t pud) /* Find an entry in the second-level page table. */ #define pmd_index(addr) (((addr) >> PMD_SHIFT) & (PTRS_PER_PMD - 1)) -#define pmd_offset_phys(dir, addr) (pud_page_paddr(*(dir)) + pmd_index(addr) * sizeof(pmd_t)) +#define pmd_offset_phys(dir, addr) (pud_page_paddr(READ_ONCE(*(dir))) + pmd_index(addr) * sizeof(pmd_t)) #define pmd_offset(dir, addr) ((pmd_t *)__va(pmd_offset_phys((dir), (addr)))) #define pmd_set_fixmap(addr) ((pmd_t *)set_fixmap_offset(FIX_PMD, addr)) @@ -535,7 +538,7 @@ static inline phys_addr_t pud_page_paddr(pud_t pud) static inline void set_pgd(pgd_t *pgdp, pgd_t pgd) { - *pgdp = pgd; + WRITE_ONCE(*pgdp, pgd); dsb(ishst); } @@ -552,7 +555,7 @@ static inline phys_addr_t pgd_page_paddr(pgd_t pgd) /* Find an entry in the frst-level page table. */ #define pud_index(addr) (((addr) >> PUD_SHIFT) & (PTRS_PER_PUD - 1)) -#define pud_offset_phys(dir, addr) (pgd_page_paddr(*(dir)) + pud_index(addr) * sizeof(pud_t)) +#define pud_offset_phys(dir, addr) (pgd_page_paddr(READ_ONCE(*(dir))) + pud_index(addr) * sizeof(pud_t)) #define pud_offset(dir, addr) ((pud_t *)__va(pud_offset_phys((dir), (addr)))) #define pud_set_fixmap(addr) ((pud_t *)set_fixmap_offset(FIX_PUD, addr)) diff --git a/arch/arm64/kernel/efi.c b/arch/arm64/kernel/efi.c index f85ac58d08a3..a8bf1c892b90 100644 --- a/arch/arm64/kernel/efi.c +++ b/arch/arm64/kernel/efi.c @@ -90,7 +90,7 @@ static int __init set_permissions(pte_t *ptep, pgtable_t token, unsigned long addr, void *data) { efi_memory_desc_t *md = data; - pte_t pte = *ptep; + pte_t pte = READ_ONCE(*ptep); if (md->attribute & EFI_MEMORY_RO) pte = set_pte_bit(pte, __pgprot(PTE_RDONLY)); diff --git a/arch/arm64/kernel/hibernate.c b/arch/arm64/kernel/hibernate.c index f20cf7e99249..1ec5f28c39fc 100644 --- a/arch/arm64/kernel/hibernate.c +++ b/arch/arm64/kernel/hibernate.c @@ -202,10 +202,10 @@ static int create_safe_exec_page(void *src_start, size_t length, gfp_t mask) { int rc = 0; - pgd_t *pgd; - pud_t *pud; - pmd_t *pmd; - pte_t *pte; + pgd_t *pgdp; + pud_t *pudp; + pmd_t *pmdp; + pte_t *ptep; unsigned long dst = (unsigned long)allocator(mask); if (!dst) { @@ -216,38 +216,38 @@ static int create_safe_exec_page(void *src_start, size_t length, memcpy((void *)dst, src_start, length); flush_icache_range(dst, dst + length); - pgd = pgd_offset_raw(allocator(mask), dst_addr); - if (pgd_none(*pgd)) { - pud = allocator(mask); - if (!pud) { + pgdp = pgd_offset_raw(allocator(mask), dst_addr); + if (pgd_none(READ_ONCE(*pgdp))) { + pudp = allocator(mask); + if (!pudp) { rc = -ENOMEM; goto out; } - pgd_populate(&init_mm, pgd, pud); + pgd_populate(&init_mm, pgdp, pudp); } - pud = pud_offset(pgd, dst_addr); - if (pud_none(*pud)) { - pmd = allocator(mask); - if (!pmd) { + pudp = pud_offset(pgdp, dst_addr); + if (pud_none(READ_ONCE(*pudp))) { + pmdp = allocator(mask); + if (!pmdp) { rc = -ENOMEM; goto out; } - pud_populate(&init_mm, pud, pmd); + pud_populate(&init_mm, pudp, pmdp); } - pmd = pmd_offset(pud, dst_addr); - if (pmd_none(*pmd)) { - pte = allocator(mask); - if (!pte) { + pmdp = pmd_offset(pudp, dst_addr); + if (pmd_none(READ_ONCE(*pmdp))) { + ptep = allocator(mask); + if (!ptep) { rc = -ENOMEM; goto out; } - pmd_populate_kernel(&init_mm, pmd, pte); + pmd_populate_kernel(&init_mm, pmdp, ptep); } - pte = pte_offset_kernel(pmd, dst_addr); - set_pte(pte, pfn_pte(virt_to_pfn(dst), PAGE_KERNEL_EXEC)); + ptep = pte_offset_kernel(pmdp, dst_addr); + set_pte(ptep, pfn_pte(virt_to_pfn(dst), PAGE_KERNEL_EXEC)); /* * Load our new page tables. A strict BBM approach requires that we @@ -263,7 +263,7 @@ static int create_safe_exec_page(void *src_start, size_t length, */ cpu_set_reserved_ttbr0(); local_flush_tlb_all(); - write_sysreg(phys_to_ttbr(virt_to_phys(pgd)), ttbr0_el1); + write_sysreg(phys_to_ttbr(virt_to_phys(pgdp)), ttbr0_el1); isb(); *phys_dst_addr = virt_to_phys((void *)dst); @@ -320,9 +320,9 @@ int swsusp_arch_suspend(void) return ret; } -static void _copy_pte(pte_t *dst_pte, pte_t *src_pte, unsigned long addr) +static void _copy_pte(pte_t *dst_ptep, pte_t *src_ptep, unsigned long addr) { - pte_t pte = *src_pte; + pte_t pte = READ_ONCE(*src_ptep); if (pte_valid(pte)) { /* @@ -330,7 +330,7 @@ static void _copy_pte(pte_t *dst_pte, pte_t *src_pte, unsigned long addr) * read only (code, rodata). Clear the RDONLY bit from * the temporary mappings we use during restore. */ - set_pte(dst_pte, pte_mkwrite(pte)); + set_pte(dst_ptep, pte_mkwrite(pte)); } else if (debug_pagealloc_enabled() && !pte_none(pte)) { /* * debug_pagealloc will removed the PTE_VALID bit if @@ -343,112 +343,116 @@ static void _copy_pte(pte_t *dst_pte, pte_t *src_pte, unsigned long addr) */ BUG_ON(!pfn_valid(pte_pfn(pte))); - set_pte(dst_pte, pte_mkpresent(pte_mkwrite(pte))); + set_pte(dst_ptep, pte_mkpresent(pte_mkwrite(pte))); } } -static int copy_pte(pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long start, +static int copy_pte(pmd_t *dst_pmdp, pmd_t *src_pmdp, unsigned long start, unsigned long end) { - pte_t *src_pte; - pte_t *dst_pte; + pte_t *src_ptep; + pte_t *dst_ptep; unsigned long addr = start; - dst_pte = (pte_t *)get_safe_page(GFP_ATOMIC); - if (!dst_pte) + dst_ptep = (pte_t *)get_safe_page(GFP_ATOMIC); + if (!dst_ptep) return -ENOMEM; - pmd_populate_kernel(&init_mm, dst_pmd, dst_pte); - dst_pte = pte_offset_kernel(dst_pmd, start); + pmd_populate_kernel(&init_mm, dst_pmdp, dst_ptep); + dst_ptep = pte_offset_kernel(dst_pmdp, start); - src_pte = pte_offset_kernel(src_pmd, start); + src_ptep = pte_offset_kernel(src_pmdp, start); do { - _copy_pte(dst_pte, src_pte, addr); - } while (dst_pte++, src_pte++, addr += PAGE_SIZE, addr != end); + _copy_pte(dst_ptep, src_ptep, addr); + } while (dst_ptep++, src_ptep++, addr += PAGE_SIZE, addr != end); return 0; } -static int copy_pmd(pud_t *dst_pud, pud_t *src_pud, unsigned long start, +static int copy_pmd(pud_t *dst_pudp, pud_t *src_pudp, unsigned long start, unsigned long end) { - pmd_t *src_pmd; - pmd_t *dst_pmd; + pmd_t *src_pmdp; + pmd_t *dst_pmdp; unsigned long next; unsigned long addr = start; - if (pud_none(*dst_pud)) { - dst_pmd = (pmd_t *)get_safe_page(GFP_ATOMIC); - if (!dst_pmd) + if (pud_none(READ_ONCE(*dst_pudp))) { + dst_pmdp = (pmd_t *)get_safe_page(GFP_ATOMIC); + if (!dst_pmdp) return -ENOMEM; - pud_populate(&init_mm, dst_pud, dst_pmd); + pud_populate(&init_mm, dst_pudp, dst_pmdp); } - dst_pmd = pmd_offset(dst_pud, start); + dst_pmdp = pmd_offset(dst_pudp, start); - src_pmd = pmd_offset(src_pud, start); + src_pmdp = pmd_offset(src_pudp, start); do { + pmd_t pmd = READ_ONCE(*src_pmdp); + next = pmd_addr_end(addr, end); - if (pmd_none(*src_pmd)) + if (pmd_none(pmd)) continue; - if (pmd_table(*src_pmd)) { - if (copy_pte(dst_pmd, src_pmd, addr, next)) + if (pmd_table(pmd)) { + if (copy_pte(dst_pmdp, src_pmdp, addr, next)) return -ENOMEM; } else { - set_pmd(dst_pmd, - __pmd(pmd_val(*src_pmd) & ~PMD_SECT_RDONLY)); + set_pmd(dst_pmdp, + __pmd(pmd_val(pmd) & ~PMD_SECT_RDONLY)); } - } while (dst_pmd++, src_pmd++, addr = next, addr != end); + } while (dst_pmdp++, src_pmdp++, addr = next, addr != end); return 0; } -static int copy_pud(pgd_t *dst_pgd, pgd_t *src_pgd, unsigned long start, +static int copy_pud(pgd_t *dst_pgdp, pgd_t *src_pgdp, unsigned long start, unsigned long end) { - pud_t *dst_pud; - pud_t *src_pud; + pud_t *dst_pudp; + pud_t *src_pudp; unsigned long next; unsigned long addr = start; - if (pgd_none(*dst_pgd)) { - dst_pud = (pud_t *)get_safe_page(GFP_ATOMIC); - if (!dst_pud) + if (pgd_none(READ_ONCE(*dst_pgdp))) { + dst_pudp = (pud_t *)get_safe_page(GFP_ATOMIC); + if (!dst_pudp) return -ENOMEM; - pgd_populate(&init_mm, dst_pgd, dst_pud); + pgd_populate(&init_mm, dst_pgdp, dst_pudp); } - dst_pud = pud_offset(dst_pgd, start); + dst_pudp = pud_offset(dst_pgdp, start); - src_pud = pud_offset(src_pgd, start); + src_pudp = pud_offset(src_pgdp, start); do { + pud_t pud = READ_ONCE(*src_pudp); + next = pud_addr_end(addr, end); - if (pud_none(*src_pud)) + if (pud_none(pud)) continue; - if (pud_table(*(src_pud))) { - if (copy_pmd(dst_pud, src_pud, addr, next)) + if (pud_table(pud)) { + if (copy_pmd(dst_pudp, src_pudp, addr, next)) return -ENOMEM; } else { - set_pud(dst_pud, - __pud(pud_val(*src_pud) & ~PMD_SECT_RDONLY)); + set_pud(dst_pudp, + __pud(pud_val(pud) & ~PMD_SECT_RDONLY)); } - } while (dst_pud++, src_pud++, addr = next, addr != end); + } while (dst_pudp++, src_pudp++, addr = next, addr != end); return 0; } -static int copy_page_tables(pgd_t *dst_pgd, unsigned long start, +static int copy_page_tables(pgd_t *dst_pgdp, unsigned long start, unsigned long end) { unsigned long next; unsigned long addr = start; - pgd_t *src_pgd = pgd_offset_k(start); + pgd_t *src_pgdp = pgd_offset_k(start); - dst_pgd = pgd_offset_raw(dst_pgd, start); + dst_pgdp = pgd_offset_raw(dst_pgdp, start); do { next = pgd_addr_end(addr, end); - if (pgd_none(*src_pgd)) + if (pgd_none(READ_ONCE(*src_pgdp))) continue; - if (copy_pud(dst_pgd, src_pgd, addr, next)) + if (copy_pud(dst_pgdp, src_pgdp, addr, next)) return -ENOMEM; - } while (dst_pgd++, src_pgd++, addr = next, addr != end); + } while (dst_pgdp++, src_pgdp++, addr = next, addr != end); return 0; } diff --git a/arch/arm64/mm/dump.c b/arch/arm64/mm/dump.c index 7b60d62ac593..65dfc8571bf8 100644 --- a/arch/arm64/mm/dump.c +++ b/arch/arm64/mm/dump.c @@ -286,48 +286,52 @@ static void note_page(struct pg_state *st, unsigned long addr, unsigned level, } -static void walk_pte(struct pg_state *st, pmd_t *pmd, unsigned long start) +static void walk_pte(struct pg_state *st, pmd_t *pmdp, unsigned long start) { - pte_t *pte = pte_offset_kernel(pmd, 0UL); + pte_t *ptep = pte_offset_kernel(pmdp, 0UL); unsigned long addr; unsigned i; - for (i = 0; i < PTRS_PER_PTE; i++, pte++) { + for (i = 0; i < PTRS_PER_PTE; i++, ptep++) { addr = start + i * PAGE_SIZE; - note_page(st, addr, 4, pte_val(*pte)); + note_page(st, addr, 4, READ_ONCE(pte_val(*ptep))); } } -static void walk_pmd(struct pg_state *st, pud_t *pud, unsigned long start) +static void walk_pmd(struct pg_state *st, pud_t *pudp, unsigned long start) { - pmd_t *pmd = pmd_offset(pud, 0UL); + pmd_t *pmdp = pmd_offset(pudp, 0UL); unsigned long addr; unsigned i; - for (i = 0; i < PTRS_PER_PMD; i++, pmd++) { + for (i = 0; i < PTRS_PER_PMD; i++, pmdp++) { + pmd_t pmd = READ_ONCE(*pmdp); + addr = start + i * PMD_SIZE; - if (pmd_none(*pmd) || pmd_sect(*pmd)) { - note_page(st, addr, 3, pmd_val(*pmd)); + if (pmd_none(pmd) || pmd_sect(pmd)) { + note_page(st, addr, 3, pmd_val(pmd)); } else { - BUG_ON(pmd_bad(*pmd)); - walk_pte(st, pmd, addr); + BUG_ON(pmd_bad(pmd)); + walk_pte(st, pmdp, addr); } } } -static void walk_pud(struct pg_state *st, pgd_t *pgd, unsigned long start) +static void walk_pud(struct pg_state *st, pgd_t *pgdp, unsigned long start) { - pud_t *pud = pud_offset(pgd, 0UL); + pud_t *pudp = pud_offset(pgdp, 0UL); unsigned long addr; unsigned i; - for (i = 0; i < PTRS_PER_PUD; i++, pud++) { + for (i = 0; i < PTRS_PER_PUD; i++, pudp++) { + pud_t pud = READ_ONCE(*pudp); + addr = start + i * PUD_SIZE; - if (pud_none(*pud) || pud_sect(*pud)) { - note_page(st, addr, 2, pud_val(*pud)); + if (pud_none(pud) || pud_sect(pud)) { + note_page(st, addr, 2, pud_val(pud)); } else { - BUG_ON(pud_bad(*pud)); - walk_pmd(st, pud, addr); + BUG_ON(pud_bad(pud)); + walk_pmd(st, pudp, addr); } } } @@ -335,17 +339,19 @@ static void walk_pud(struct pg_state *st, pgd_t *pgd, unsigned long start) static void walk_pgd(struct pg_state *st, struct mm_struct *mm, unsigned long start) { - pgd_t *pgd = pgd_offset(mm, 0UL); + pgd_t *pgdp = pgd_offset(mm, 0UL); unsigned i; unsigned long addr; - for (i = 0; i < PTRS_PER_PGD; i++, pgd++) { + for (i = 0; i < PTRS_PER_PGD; i++, pgdp++) { + pgd_t pgd = READ_ONCE(*pgdp); + addr = start + i * PGDIR_SIZE; - if (pgd_none(*pgd)) { - note_page(st, addr, 1, pgd_val(*pgd)); + if (pgd_none(pgd)) { + note_page(st, addr, 1, pgd_val(pgd)); } else { - BUG_ON(pgd_bad(*pgd)); - walk_pud(st, pgd, addr); + BUG_ON(pgd_bad(pgd)); + walk_pud(st, pgdp, addr); } } } diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index f76bb2c3c943..bff11553eb05 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -130,7 +130,8 @@ static void mem_abort_decode(unsigned int esr) void show_pte(unsigned long addr) { struct mm_struct *mm; - pgd_t *pgd; + pgd_t *pgdp; + pgd_t pgd; if (addr < TASK_SIZE) { /* TTBR0 */ @@ -149,33 +150,37 @@ void show_pte(unsigned long addr) return; } - pr_alert("%s pgtable: %luk pages, %u-bit VAs, pgd = %p\n", + pr_alert("%s pgtable: %luk pages, %u-bit VAs, pgdp = %p\n", mm == &init_mm ? "swapper" : "user", PAGE_SIZE / SZ_1K, VA_BITS, mm->pgd); - pgd = pgd_offset(mm, addr); - pr_alert("[%016lx] *pgd=%016llx", addr, pgd_val(*pgd)); + pgdp = pgd_offset(mm, addr); + pgd = READ_ONCE(*pgdp); + pr_alert("[%016lx] pgd=%016llx", addr, pgd_val(pgd)); do { - pud_t *pud; - pmd_t *pmd; - pte_t *pte; + pud_t *pudp, pud; + pmd_t *pmdp, pmd; + pte_t *ptep, pte; - if (pgd_none(*pgd) || pgd_bad(*pgd)) + if (pgd_none(pgd) || pgd_bad(pgd)) break; - pud = pud_offset(pgd, addr); - pr_cont(", *pud=%016llx", pud_val(*pud)); - if (pud_none(*pud) || pud_bad(*pud)) + pudp = pud_offset(pgdp, addr); + pud = READ_ONCE(*pudp); + pr_cont(", pud=%016llx", pud_val(pud)); + if (pud_none(pud) || pud_bad(pud)) break; - pmd = pmd_offset(pud, addr); - pr_cont(", *pmd=%016llx", pmd_val(*pmd)); - if (pmd_none(*pmd) || pmd_bad(*pmd)) + pmdp = pmd_offset(pudp, addr); + pmd = READ_ONCE(*pmdp); + pr_cont(", pmd=%016llx", pmd_val(pmd)); + if (pmd_none(pmd) || pmd_bad(pmd)) break; - pte = pte_offset_map(pmd, addr); - pr_cont(", *pte=%016llx", pte_val(*pte)); - pte_unmap(pte); + ptep = pte_offset_map(pmdp, addr); + pte = READ_ONCE(*ptep); + pr_cont(", pte=%016llx", pte_val(pte)); + pte_unmap(ptep); } while(0); pr_cont("\n"); @@ -196,8 +201,9 @@ int ptep_set_access_flags(struct vm_area_struct *vma, pte_t entry, int dirty) { pteval_t old_pteval, pteval; + pte_t pte = READ_ONCE(*ptep); - if (pte_same(*ptep, entry)) + if (pte_same(pte, entry)) return 0; /* only preserve the access flags and write permission */ @@ -210,7 +216,7 @@ int ptep_set_access_flags(struct vm_area_struct *vma, * (calculated as: a & b == ~(~a | ~b)). */ pte_val(entry) ^= PTE_RDONLY; - pteval = READ_ONCE(pte_val(*ptep)); + pteval = pte_val(pte); do { old_pteval = pteval; pteval ^= PTE_RDONLY; diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c index 6cb0fa92a651..ecc6818191df 100644 --- a/arch/arm64/mm/hugetlbpage.c +++ b/arch/arm64/mm/hugetlbpage.c @@ -54,14 +54,14 @@ static inline pgprot_t pte_pgprot(pte_t pte) static int find_num_contig(struct mm_struct *mm, unsigned long addr, pte_t *ptep, size_t *pgsize) { - pgd_t *pgd = pgd_offset(mm, addr); - pud_t *pud; - pmd_t *pmd; + pgd_t *pgdp = pgd_offset(mm, addr); + pud_t *pudp; + pmd_t *pmdp; *pgsize = PAGE_SIZE; - pud = pud_offset(pgd, addr); - pmd = pmd_offset(pud, addr); - if ((pte_t *)pmd == ptep) { + pudp = pud_offset(pgdp, addr); + pmdp = pmd_offset(pudp, addr); + if ((pte_t *)pmdp == ptep) { *pgsize = PMD_SIZE; return CONT_PMDS; } @@ -181,11 +181,8 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, clear_flush(mm, addr, ptep, pgsize, ncontig); - for (i = 0; i < ncontig; i++, ptep++, addr += pgsize, pfn += dpfn) { - pr_debug("%s: set pte %p to 0x%llx\n", __func__, ptep, - pte_val(pfn_pte(pfn, hugeprot))); + for (i = 0; i < ncontig; i++, ptep++, addr += pgsize, pfn += dpfn) set_pte_at(mm, addr, ptep, pfn_pte(pfn, hugeprot)); - } } void set_huge_swap_pte_at(struct mm_struct *mm, unsigned long addr, @@ -203,20 +200,20 @@ void set_huge_swap_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr, unsigned long sz) { - pgd_t *pgd; - pud_t *pud; - pte_t *pte = NULL; - - pr_debug("%s: addr:0x%lx sz:0x%lx\n", __func__, addr, sz); - pgd = pgd_offset(mm, addr); - pud = pud_alloc(mm, pgd, addr); - if (!pud) + pgd_t *pgdp; + pud_t *pudp; + pmd_t *pmdp; + pte_t *ptep = NULL; + + pgdp = pgd_offset(mm, addr); + pudp = pud_alloc(mm, pgdp, addr); + if (!pudp) return NULL; if (sz == PUD_SIZE) { - pte = (pte_t *)pud; + ptep = (pte_t *)pudp; } else if (sz == (PAGE_SIZE * CONT_PTES)) { - pmd_t *pmd = pmd_alloc(mm, pud, addr); + pmdp = pmd_alloc(mm, pudp, addr); WARN_ON(addr & (sz - 1)); /* @@ -226,60 +223,55 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, * will be no pte_unmap() to correspond with this * pte_alloc_map(). */ - pte = pte_alloc_map(mm, pmd, addr); + ptep = pte_alloc_map(mm, pmdp, addr); } else if (sz == PMD_SIZE) { if (IS_ENABLED(CONFIG_ARCH_WANT_HUGE_PMD_SHARE) && - pud_none(*pud)) - pte = huge_pmd_share(mm, addr, pud); + pud_none(READ_ONCE(*pudp))) + ptep = huge_pmd_share(mm, addr, pudp); else - pte = (pte_t *)pmd_alloc(mm, pud, addr); + ptep = (pte_t *)pmd_alloc(mm, pudp, addr); } else if (sz == (PMD_SIZE * CONT_PMDS)) { - pmd_t *pmd; - - pmd = pmd_alloc(mm, pud, addr); + pmdp = pmd_alloc(mm, pudp, addr); WARN_ON(addr & (sz - 1)); - return (pte_t *)pmd; + return (pte_t *)pmdp; } - pr_debug("%s: addr:0x%lx sz:0x%lx ret pte=%p/0x%llx\n", __func__, addr, - sz, pte, pte_val(*pte)); - return pte; + return ptep; } pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr, unsigned long sz) { - pgd_t *pgd; - pud_t *pud; - pmd_t *pmd; + pgd_t *pgdp; + pud_t *pudp, pud; + pmd_t *pmdp, pmd; - pgd = pgd_offset(mm, addr); - pr_debug("%s: addr:0x%lx pgd:%p\n", __func__, addr, pgd); - if (!pgd_present(*pgd)) + pgdp = pgd_offset(mm, addr); + if (!pgd_present(READ_ONCE(*pgdp))) return NULL; - pud = pud_offset(pgd, addr); - if (sz != PUD_SIZE && pud_none(*pud)) + pudp = pud_offset(pgdp, addr); + pud = READ_ONCE(*pudp); + if (sz != PUD_SIZE && pud_none(pud)) return NULL; /* hugepage or swap? */ - if (pud_huge(*pud) || !pud_present(*pud)) - return (pte_t *)pud; + if (pud_huge(pud) || !pud_present(pud)) + return (pte_t *)pudp; /* table; check the next level */ if (sz == CONT_PMD_SIZE) addr &= CONT_PMD_MASK; - pmd = pmd_offset(pud, addr); + pmdp = pmd_offset(pudp, addr); + pmd = READ_ONCE(*pmdp); if (!(sz == PMD_SIZE || sz == CONT_PMD_SIZE) && - pmd_none(*pmd)) + pmd_none(pmd)) return NULL; - if (pmd_huge(*pmd) || !pmd_present(*pmd)) - return (pte_t *)pmd; + if (pmd_huge(pmd) || !pmd_present(pmd)) + return (pte_t *)pmdp; - if (sz == CONT_PTE_SIZE) { - pte_t *pte = pte_offset_kernel(pmd, (addr & CONT_PTE_MASK)); - return pte; - } + if (sz == CONT_PTE_SIZE) + return pte_offset_kernel(pmdp, (addr & CONT_PTE_MASK)); return NULL; } @@ -367,7 +359,7 @@ void huge_ptep_set_wrprotect(struct mm_struct *mm, size_t pgsize; pte_t pte; - if (!pte_cont(*ptep)) { + if (!pte_cont(READ_ONCE(*ptep))) { ptep_set_wrprotect(mm, addr, ptep); return; } @@ -391,7 +383,7 @@ void huge_ptep_clear_flush(struct vm_area_struct *vma, size_t pgsize; int ncontig; - if (!pte_cont(*ptep)) { + if (!pte_cont(READ_ONCE(*ptep))) { ptep_clear_flush(vma, addr, ptep); return; } diff --git a/arch/arm64/mm/kasan_init.c b/arch/arm64/mm/kasan_init.c index 6e02e6fb4c7b..dabfc1ecda3d 100644 --- a/arch/arm64/mm/kasan_init.c +++ b/arch/arm64/mm/kasan_init.c @@ -44,92 +44,92 @@ static phys_addr_t __init kasan_alloc_zeroed_page(int node) return __pa(p); } -static pte_t *__init kasan_pte_offset(pmd_t *pmd, unsigned long addr, int node, +static pte_t *__init kasan_pte_offset(pmd_t *pmdp, unsigned long addr, int node, bool early) { - if (pmd_none(*pmd)) { + if (pmd_none(READ_ONCE(*pmdp))) { phys_addr_t pte_phys = early ? __pa_symbol(kasan_zero_pte) : kasan_alloc_zeroed_page(node); - __pmd_populate(pmd, pte_phys, PMD_TYPE_TABLE); + __pmd_populate(pmdp, pte_phys, PMD_TYPE_TABLE); } - return early ? pte_offset_kimg(pmd, addr) - : pte_offset_kernel(pmd, addr); + return early ? pte_offset_kimg(pmdp, addr) + : pte_offset_kernel(pmdp, addr); } -static pmd_t *__init kasan_pmd_offset(pud_t *pud, unsigned long addr, int node, +static pmd_t *__init kasan_pmd_offset(pud_t *pudp, unsigned long addr, int node, bool early) { - if (pud_none(*pud)) { + if (pud_none(READ_ONCE(*pudp))) { phys_addr_t pmd_phys = early ? __pa_symbol(kasan_zero_pmd) : kasan_alloc_zeroed_page(node); - __pud_populate(pud, pmd_phys, PMD_TYPE_TABLE); + __pud_populate(pudp, pmd_phys, PMD_TYPE_TABLE); } - return early ? pmd_offset_kimg(pud, addr) : pmd_offset(pud, addr); + return early ? pmd_offset_kimg(pudp, addr) : pmd_offset(pudp, addr); } -static pud_t *__init kasan_pud_offset(pgd_t *pgd, unsigned long addr, int node, +static pud_t *__init kasan_pud_offset(pgd_t *pgdp, unsigned long addr, int node, bool early) { - if (pgd_none(*pgd)) { + if (pgd_none(READ_ONCE(*pgdp))) { phys_addr_t pud_phys = early ? __pa_symbol(kasan_zero_pud) : kasan_alloc_zeroed_page(node); - __pgd_populate(pgd, pud_phys, PMD_TYPE_TABLE); + __pgd_populate(pgdp, pud_phys, PMD_TYPE_TABLE); } - return early ? pud_offset_kimg(pgd, addr) : pud_offset(pgd, addr); + return early ? pud_offset_kimg(pgdp, addr) : pud_offset(pgdp, addr); } -static void __init kasan_pte_populate(pmd_t *pmd, unsigned long addr, +static void __init kasan_pte_populate(pmd_t *pmdp, unsigned long addr, unsigned long end, int node, bool early) { unsigned long next; - pte_t *pte = kasan_pte_offset(pmd, addr, node, early); + pte_t *ptep = kasan_pte_offset(pmdp, addr, node, early); do { phys_addr_t page_phys = early ? __pa_symbol(kasan_zero_page) : kasan_alloc_zeroed_page(node); next = addr + PAGE_SIZE; - set_pte(pte, pfn_pte(__phys_to_pfn(page_phys), PAGE_KERNEL)); - } while (pte++, addr = next, addr != end && pte_none(*pte)); + set_pte(ptep, pfn_pte(__phys_to_pfn(page_phys), PAGE_KERNEL)); + } while (ptep++, addr = next, addr != end && pte_none(READ_ONCE(*ptep))); } -static void __init kasan_pmd_populate(pud_t *pud, unsigned long addr, +static void __init kasan_pmd_populate(pud_t *pudp, unsigned long addr, unsigned long end, int node, bool early) { unsigned long next; - pmd_t *pmd = kasan_pmd_offset(pud, addr, node, early); + pmd_t *pmdp = kasan_pmd_offset(pudp, addr, node, early); do { next = pmd_addr_end(addr, end); - kasan_pte_populate(pmd, addr, next, node, early); - } while (pmd++, addr = next, addr != end && pmd_none(*pmd)); + kasan_pte_populate(pmdp, addr, next, node, early); + } while (pmdp++, addr = next, addr != end && pmd_none(READ_ONCE(*pmdp))); } -static void __init kasan_pud_populate(pgd_t *pgd, unsigned long addr, +static void __init kasan_pud_populate(pgd_t *pgdp, unsigned long addr, unsigned long end, int node, bool early) { unsigned long next; - pud_t *pud = kasan_pud_offset(pgd, addr, node, early); + pud_t *pudp = kasan_pud_offset(pgdp, addr, node, early); do { next = pud_addr_end(addr, end); - kasan_pmd_populate(pud, addr, next, node, early); - } while (pud++, addr = next, addr != end && pud_none(*pud)); + kasan_pmd_populate(pudp, addr, next, node, early); + } while (pudp++, addr = next, addr != end && pud_none(READ_ONCE(*pudp))); } static void __init kasan_pgd_populate(unsigned long addr, unsigned long end, int node, bool early) { unsigned long next; - pgd_t *pgd; + pgd_t *pgdp; - pgd = pgd_offset_k(addr); + pgdp = pgd_offset_k(addr); do { next = pgd_addr_end(addr, end); - kasan_pud_populate(pgd, addr, next, node, early); - } while (pgd++, addr = next, addr != end); + kasan_pud_populate(pgdp, addr, next, node, early); + } while (pgdp++, addr = next, addr != end); } /* The early shadow maps everything to a single page of zeroes */ @@ -155,14 +155,14 @@ static void __init kasan_map_populate(unsigned long start, unsigned long end, */ void __init kasan_copy_shadow(pgd_t *pgdir) { - pgd_t *pgd, *pgd_new, *pgd_end; + pgd_t *pgdp, *pgdp_new, *pgdp_end; - pgd = pgd_offset_k(KASAN_SHADOW_START); - pgd_end = pgd_offset_k(KASAN_SHADOW_END); - pgd_new = pgd_offset_raw(pgdir, KASAN_SHADOW_START); + pgdp = pgd_offset_k(KASAN_SHADOW_START); + pgdp_end = pgd_offset_k(KASAN_SHADOW_END); + pgdp_new = pgd_offset_raw(pgdir, KASAN_SHADOW_START); do { - set_pgd(pgd_new, *pgd); - } while (pgd++, pgd_new++, pgd != pgd_end); + set_pgd(pgdp_new, READ_ONCE(*pgdp)); + } while (pgdp++, pgdp_new++, pgdp != pgdp_end); } static void __init clear_pgds(unsigned long start, diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 4694cda823c9..3161b853f29e 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -125,45 +125,48 @@ static bool pgattr_change_is_safe(u64 old, u64 new) return ((old ^ new) & ~mask) == 0; } -static void init_pte(pmd_t *pmd, unsigned long addr, unsigned long end, +static void init_pte(pmd_t *pmdp, unsigned long addr, unsigned long end, phys_addr_t phys, pgprot_t prot) { - pte_t *pte; + pte_t *ptep; - pte = pte_set_fixmap_offset(pmd, addr); + ptep = pte_set_fixmap_offset(pmdp, addr); do { - pte_t old_pte = *pte; + pte_t old_pte = READ_ONCE(*ptep); - set_pte(pte, pfn_pte(__phys_to_pfn(phys), prot)); + set_pte(ptep, pfn_pte(__phys_to_pfn(phys), prot)); /* * After the PTE entry has been populated once, we * only allow updates to the permission attributes. */ - BUG_ON(!pgattr_change_is_safe(pte_val(old_pte), pte_val(*pte))); + BUG_ON(!pgattr_change_is_safe(pte_val(old_pte), + READ_ONCE(pte_val(*ptep)))); phys += PAGE_SIZE; - } while (pte++, addr += PAGE_SIZE, addr != end); + } while (ptep++, addr += PAGE_SIZE, addr != end); pte_clear_fixmap(); } -static void alloc_init_cont_pte(pmd_t *pmd, unsigned long addr, +static void alloc_init_cont_pte(pmd_t *pmdp, unsigned long addr, unsigned long end, phys_addr_t phys, pgprot_t prot, phys_addr_t (*pgtable_alloc)(void), int flags) { unsigned long next; + pmd_t pmd = READ_ONCE(*pmdp); - BUG_ON(pmd_sect(*pmd)); - if (pmd_none(*pmd)) { + BUG_ON(pmd_sect(pmd)); + if (pmd_none(pmd)) { phys_addr_t pte_phys; BUG_ON(!pgtable_alloc); pte_phys = pgtable_alloc(); - __pmd_populate(pmd, pte_phys, PMD_TYPE_TABLE); + __pmd_populate(pmdp, pte_phys, PMD_TYPE_TABLE); + pmd = READ_ONCE(*pmdp); } - BUG_ON(pmd_bad(*pmd)); + BUG_ON(pmd_bad(pmd)); do { pgprot_t __prot = prot; @@ -175,67 +178,69 @@ static void alloc_init_cont_pte(pmd_t *pmd, unsigned long addr, (flags & NO_CONT_MAPPINGS) == 0) __prot = __pgprot(pgprot_val(prot) | PTE_CONT); - init_pte(pmd, addr, next, phys, __prot); + init_pte(pmdp, addr, next, phys, __prot); phys += next - addr; } while (addr = next, addr != end); } -static void init_pmd(pud_t *pud, unsigned long addr, unsigned long end, +static void init_pmd(pud_t *pudp, unsigned long addr, unsigned long end, phys_addr_t phys, pgprot_t prot, phys_addr_t (*pgtable_alloc)(void), int flags) { unsigned long next; - pmd_t *pmd; + pmd_t *pmdp; - pmd = pmd_set_fixmap_offset(pud, addr); + pmdp = pmd_set_fixmap_offset(pudp, addr); do { - pmd_t old_pmd = *pmd; + pmd_t old_pmd = READ_ONCE(*pmdp); next = pmd_addr_end(addr, end); /* try section mapping first */ if (((addr | next | phys) & ~SECTION_MASK) == 0 && (flags & NO_BLOCK_MAPPINGS) == 0) { - pmd_set_huge(pmd, phys, prot); + pmd_set_huge(pmdp, phys, prot); /* * After the PMD entry has been populated once, we * only allow updates to the permission attributes. */ BUG_ON(!pgattr_change_is_safe(pmd_val(old_pmd), - pmd_val(*pmd))); + READ_ONCE(pmd_val(*pmdp)))); } else { - alloc_init_cont_pte(pmd, addr, next, phys, prot, + alloc_init_cont_pte(pmdp, addr, next, phys, prot, pgtable_alloc, flags); BUG_ON(pmd_val(old_pmd) != 0 && - pmd_val(old_pmd) != pmd_val(*pmd)); + pmd_val(old_pmd) != READ_ONCE(pmd_val(*pmdp))); } phys += next - addr; - } while (pmd++, addr = next, addr != end); + } while (pmdp++, addr = next, addr != end); pmd_clear_fixmap(); } -static void alloc_init_cont_pmd(pud_t *pud, unsigned long addr, +static void alloc_init_cont_pmd(pud_t *pudp, unsigned long addr, unsigned long end, phys_addr_t phys, pgprot_t prot, phys_addr_t (*pgtable_alloc)(void), int flags) { unsigned long next; + pud_t pud = READ_ONCE(*pudp); /* * Check for initial section mappings in the pgd/pud. */ - BUG_ON(pud_sect(*pud)); - if (pud_none(*pud)) { + BUG_ON(pud_sect(pud)); + if (pud_none(pud)) { phys_addr_t pmd_phys; BUG_ON(!pgtable_alloc); pmd_phys = pgtable_alloc(); - __pud_populate(pud, pmd_phys, PUD_TYPE_TABLE); + __pud_populate(pudp, pmd_phys, PUD_TYPE_TABLE); + pud = READ_ONCE(*pudp); } - BUG_ON(pud_bad(*pud)); + BUG_ON(pud_bad(pud)); do { pgprot_t __prot = prot; @@ -247,7 +252,7 @@ static void alloc_init_cont_pmd(pud_t *pud, unsigned long addr, (flags & NO_CONT_MAPPINGS) == 0) __prot = __pgprot(pgprot_val(prot) | PTE_CONT); - init_pmd(pud, addr, next, phys, __prot, pgtable_alloc, flags); + init_pmd(pudp, addr, next, phys, __prot, pgtable_alloc, flags); phys += next - addr; } while (addr = next, addr != end); @@ -265,25 +270,27 @@ static inline bool use_1G_block(unsigned long addr, unsigned long next, return true; } -static void alloc_init_pud(pgd_t *pgd, unsigned long addr, unsigned long end, - phys_addr_t phys, pgprot_t prot, - phys_addr_t (*pgtable_alloc)(void), - int flags) +static void alloc_init_pud(pgd_t *pgdp, unsigned long addr, unsigned long end, + phys_addr_t phys, pgprot_t prot, + phys_addr_t (*pgtable_alloc)(void), + int flags) { - pud_t *pud; unsigned long next; + pud_t *pudp; + pgd_t pgd = READ_ONCE(*pgdp); - if (pgd_none(*pgd)) { + if (pgd_none(pgd)) { phys_addr_t pud_phys; BUG_ON(!pgtable_alloc); pud_phys = pgtable_alloc(); - __pgd_populate(pgd, pud_phys, PUD_TYPE_TABLE); + __pgd_populate(pgdp, pud_phys, PUD_TYPE_TABLE); + pgd = READ_ONCE(*pgdp); } - BUG_ON(pgd_bad(*pgd)); + BUG_ON(pgd_bad(pgd)); - pud = pud_set_fixmap_offset(pgd, addr); + pudp = pud_set_fixmap_offset(pgdp, addr); do { - pud_t old_pud = *pud; + pud_t old_pud = READ_ONCE(*pudp); next = pud_addr_end(addr, end); @@ -292,23 +299,23 @@ static void alloc_init_pud(pgd_t *pgd, unsigned long addr, unsigned long end, */ if (use_1G_block(addr, next, phys) && (flags & NO_BLOCK_MAPPINGS) == 0) { - pud_set_huge(pud, phys, prot); + pud_set_huge(pudp, phys, prot); /* * After the PUD entry has been populated once, we * only allow updates to the permission attributes. */ BUG_ON(!pgattr_change_is_safe(pud_val(old_pud), - pud_val(*pud))); + READ_ONCE(pud_val(*pudp)))); } else { - alloc_init_cont_pmd(pud, addr, next, phys, prot, + alloc_init_cont_pmd(pudp, addr, next, phys, prot, pgtable_alloc, flags); BUG_ON(pud_val(old_pud) != 0 && - pud_val(old_pud) != pud_val(*pud)); + pud_val(old_pud) != READ_ONCE(pud_val(*pudp))); } phys += next - addr; - } while (pud++, addr = next, addr != end); + } while (pudp++, addr = next, addr != end); pud_clear_fixmap(); } @@ -320,7 +327,7 @@ static void __create_pgd_mapping(pgd_t *pgdir, phys_addr_t phys, int flags) { unsigned long addr, length, end, next; - pgd_t *pgd = pgd_offset_raw(pgdir, virt); + pgd_t *pgdp = pgd_offset_raw(pgdir, virt); /* * If the virtual and physical address don't have the same offset @@ -336,10 +343,10 @@ static void __create_pgd_mapping(pgd_t *pgdir, phys_addr_t phys, end = addr + length; do { next = pgd_addr_end(addr, end); - alloc_init_pud(pgd, addr, next, phys, prot, pgtable_alloc, + alloc_init_pud(pgdp, addr, next, phys, prot, pgtable_alloc, flags); phys += next - addr; - } while (pgd++, addr = next, addr != end); + } while (pgdp++, addr = next, addr != end); } static phys_addr_t pgd_pgtable_alloc(void) @@ -401,10 +408,10 @@ static void update_mapping_prot(phys_addr_t phys, unsigned long virt, flush_tlb_kernel_range(virt, virt + size); } -static void __init __map_memblock(pgd_t *pgd, phys_addr_t start, +static void __init __map_memblock(pgd_t *pgdp, phys_addr_t start, phys_addr_t end, pgprot_t prot, int flags) { - __create_pgd_mapping(pgd, start, __phys_to_virt(start), end - start, + __create_pgd_mapping(pgdp, start, __phys_to_virt(start), end - start, prot, early_pgtable_alloc, flags); } @@ -418,7 +425,7 @@ void __init mark_linear_text_alias_ro(void) PAGE_KERNEL_RO); } -static void __init map_mem(pgd_t *pgd) +static void __init map_mem(pgd_t *pgdp) { phys_addr_t kernel_start = __pa_symbol(_text); phys_addr_t kernel_end = __pa_symbol(__init_begin); @@ -451,7 +458,7 @@ static void __init map_mem(pgd_t *pgd) if (memblock_is_nomap(reg)) continue; - __map_memblock(pgd, start, end, PAGE_KERNEL, flags); + __map_memblock(pgdp, start, end, PAGE_KERNEL, flags); } /* @@ -464,7 +471,7 @@ static void __init map_mem(pgd_t *pgd) * Note that contiguous mappings cannot be remapped in this way, * so we should avoid them here. */ - __map_memblock(pgd, kernel_start, kernel_end, + __map_memblock(pgdp, kernel_start, kernel_end, PAGE_KERNEL, NO_CONT_MAPPINGS); memblock_clear_nomap(kernel_start, kernel_end - kernel_start); @@ -475,7 +482,7 @@ static void __init map_mem(pgd_t *pgd) * through /sys/kernel/kexec_crash_size interface. */ if (crashk_res.end) { - __map_memblock(pgd, crashk_res.start, crashk_res.end + 1, + __map_memblock(pgdp, crashk_res.start, crashk_res.end + 1, PAGE_KERNEL, NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS); memblock_clear_nomap(crashk_res.start, @@ -499,7 +506,7 @@ void mark_rodata_ro(void) debug_checkwx(); } -static void __init map_kernel_segment(pgd_t *pgd, void *va_start, void *va_end, +static void __init map_kernel_segment(pgd_t *pgdp, void *va_start, void *va_end, pgprot_t prot, struct vm_struct *vma, int flags, unsigned long vm_flags) { @@ -509,7 +516,7 @@ static void __init map_kernel_segment(pgd_t *pgd, void *va_start, void *va_end, BUG_ON(!PAGE_ALIGNED(pa_start)); BUG_ON(!PAGE_ALIGNED(size)); - __create_pgd_mapping(pgd, pa_start, (unsigned long)va_start, size, prot, + __create_pgd_mapping(pgdp, pa_start, (unsigned long)va_start, size, prot, early_pgtable_alloc, flags); if (!(vm_flags & VM_NO_GUARD)) @@ -562,7 +569,7 @@ core_initcall(map_entry_trampoline); /* * Create fine-grained mappings for the kernel. */ -static void __init map_kernel(pgd_t *pgd) +static void __init map_kernel(pgd_t *pgdp) { static struct vm_struct vmlinux_text, vmlinux_rodata, vmlinux_inittext, vmlinux_initdata, vmlinux_data; @@ -578,24 +585,24 @@ static void __init map_kernel(pgd_t *pgd) * Only rodata will be remapped with different permissions later on, * all other segments are allowed to use contiguous mappings. */ - map_kernel_segment(pgd, _text, _etext, text_prot, &vmlinux_text, 0, + map_kernel_segment(pgdp, _text, _etext, text_prot, &vmlinux_text, 0, VM_NO_GUARD); - map_kernel_segment(pgd, __start_rodata, __inittext_begin, PAGE_KERNEL, + map_kernel_segment(pgdp, __start_rodata, __inittext_begin, PAGE_KERNEL, &vmlinux_rodata, NO_CONT_MAPPINGS, VM_NO_GUARD); - map_kernel_segment(pgd, __inittext_begin, __inittext_end, text_prot, + map_kernel_segment(pgdp, __inittext_begin, __inittext_end, text_prot, &vmlinux_inittext, 0, VM_NO_GUARD); - map_kernel_segment(pgd, __initdata_begin, __initdata_end, PAGE_KERNEL, + map_kernel_segment(pgdp, __initdata_begin, __initdata_end, PAGE_KERNEL, &vmlinux_initdata, 0, VM_NO_GUARD); - map_kernel_segment(pgd, _data, _end, PAGE_KERNEL, &vmlinux_data, 0, 0); + map_kernel_segment(pgdp, _data, _end, PAGE_KERNEL, &vmlinux_data, 0, 0); - if (!pgd_val(*pgd_offset_raw(pgd, FIXADDR_START))) { + if (!READ_ONCE(pgd_val(*pgd_offset_raw(pgdp, FIXADDR_START)))) { /* * The fixmap falls in a separate pgd to the kernel, and doesn't * live in the carveout for the swapper_pg_dir. We can simply * re-use the existing dir for the fixmap. */ - set_pgd(pgd_offset_raw(pgd, FIXADDR_START), - *pgd_offset_k(FIXADDR_START)); + set_pgd(pgd_offset_raw(pgdp, FIXADDR_START), + READ_ONCE(*pgd_offset_k(FIXADDR_START))); } else if (CONFIG_PGTABLE_LEVELS > 3) { /* * The fixmap shares its top level pgd entry with the kernel @@ -604,14 +611,15 @@ static void __init map_kernel(pgd_t *pgd) * entry instead. */ BUG_ON(!IS_ENABLED(CONFIG_ARM64_16K_PAGES)); - pud_populate(&init_mm, pud_set_fixmap_offset(pgd, FIXADDR_START), + pud_populate(&init_mm, + pud_set_fixmap_offset(pgdp, FIXADDR_START), lm_alias(bm_pmd)); pud_clear_fixmap(); } else { BUG(); } - kasan_copy_shadow(pgd); + kasan_copy_shadow(pgdp); } /* @@ -621,10 +629,10 @@ static void __init map_kernel(pgd_t *pgd) void __init paging_init(void) { phys_addr_t pgd_phys = early_pgtable_alloc(); - pgd_t *pgd = pgd_set_fixmap(pgd_phys); + pgd_t *pgdp = pgd_set_fixmap(pgd_phys); - map_kernel(pgd); - map_mem(pgd); + map_kernel(pgdp); + map_mem(pgdp); /* * We want to reuse the original swapper_pg_dir so we don't have to @@ -635,7 +643,7 @@ void __init paging_init(void) * To do this we need to go via a temporary pgd. */ cpu_replace_ttbr1(__va(pgd_phys)); - memcpy(swapper_pg_dir, pgd, PGD_SIZE); + memcpy(swapper_pg_dir, pgdp, PGD_SIZE); cpu_replace_ttbr1(lm_alias(swapper_pg_dir)); pgd_clear_fixmap(); @@ -655,37 +663,40 @@ void __init paging_init(void) */ int kern_addr_valid(unsigned long addr) { - pgd_t *pgd; - pud_t *pud; - pmd_t *pmd; - pte_t *pte; + pgd_t *pgdp; + pud_t *pudp, pud; + pmd_t *pmdp, pmd; + pte_t *ptep, pte; if ((((long)addr) >> VA_BITS) != -1UL) return 0; - pgd = pgd_offset_k(addr); - if (pgd_none(*pgd)) + pgdp = pgd_offset_k(addr); + if (pgd_none(READ_ONCE(*pgdp))) return 0; - pud = pud_offset(pgd, addr); - if (pud_none(*pud)) + pudp = pud_offset(pgdp, addr); + pud = READ_ONCE(*pudp); + if (pud_none(pud)) return 0; - if (pud_sect(*pud)) - return pfn_valid(pud_pfn(*pud)); + if (pud_sect(pud)) + return pfn_valid(pud_pfn(pud)); - pmd = pmd_offset(pud, addr); - if (pmd_none(*pmd)) + pmdp = pmd_offset(pudp, addr); + pmd = READ_ONCE(*pmdp); + if (pmd_none(pmd)) return 0; - if (pmd_sect(*pmd)) - return pfn_valid(pmd_pfn(*pmd)); + if (pmd_sect(pmd)) + return pfn_valid(pmd_pfn(pmd)); - pte = pte_offset_kernel(pmd, addr); - if (pte_none(*pte)) + ptep = pte_offset_kernel(pmdp, addr); + pte = READ_ONCE(*ptep); + if (pte_none(pte)) return 0; - return pfn_valid(pte_pfn(*pte)); + return pfn_valid(pte_pfn(pte)); } #ifdef CONFIG_SPARSEMEM_VMEMMAP #if !ARM64_SWAPPER_USES_SECTION_MAPS @@ -700,32 +711,32 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node, { unsigned long addr = start; unsigned long next; - pgd_t *pgd; - pud_t *pud; - pmd_t *pmd; + pgd_t *pgdp; + pud_t *pudp; + pmd_t *pmdp; do { next = pmd_addr_end(addr, end); - pgd = vmemmap_pgd_populate(addr, node); - if (!pgd) + pgdp = vmemmap_pgd_populate(addr, node); + if (!pgdp) return -ENOMEM; - pud = vmemmap_pud_populate(pgd, addr, node); - if (!pud) + pudp = vmemmap_pud_populate(pgdp, addr, node); + if (!pudp) return -ENOMEM; - pmd = pmd_offset(pud, addr); - if (pmd_none(*pmd)) { + pmdp = pmd_offset(pudp, addr); + if (pmd_none(READ_ONCE(*pmdp))) { void *p = NULL; p = vmemmap_alloc_block_buf(PMD_SIZE, node); if (!p) return -ENOMEM; - pmd_set_huge(pmd, __pa(p), __pgprot(PROT_SECT_NORMAL)); + pmd_set_huge(pmdp, __pa(p), __pgprot(PROT_SECT_NORMAL)); } else - vmemmap_verify((pte_t *)pmd, node, addr, next); + vmemmap_verify((pte_t *)pmdp, node, addr, next); } while (addr = next, addr != end); return 0; @@ -739,20 +750,22 @@ void vmemmap_free(unsigned long start, unsigned long end, static inline pud_t * fixmap_pud(unsigned long addr) { - pgd_t *pgd = pgd_offset_k(addr); + pgd_t *pgdp = pgd_offset_k(addr); + pgd_t pgd = READ_ONCE(*pgdp); - BUG_ON(pgd_none(*pgd) || pgd_bad(*pgd)); + BUG_ON(pgd_none(pgd) || pgd_bad(pgd)); - return pud_offset_kimg(pgd, addr); + return pud_offset_kimg(pgdp, addr); } static inline pmd_t * fixmap_pmd(unsigned long addr) { - pud_t *pud = fixmap_pud(addr); + pud_t *pudp = fixmap_pud(addr); + pud_t pud = READ_ONCE(*pudp); - BUG_ON(pud_none(*pud) || pud_bad(*pud)); + BUG_ON(pud_none(pud) || pud_bad(pud)); - return pmd_offset_kimg(pud, addr); + return pmd_offset_kimg(pudp, addr); } static inline pte_t * fixmap_pte(unsigned long addr) @@ -768,30 +781,31 @@ static inline pte_t * fixmap_pte(unsigned long addr) */ void __init early_fixmap_init(void) { - pgd_t *pgd; - pud_t *pud; - pmd_t *pmd; + pgd_t *pgdp, pgd; + pud_t *pudp; + pmd_t *pmdp; unsigned long addr = FIXADDR_START; - pgd = pgd_offset_k(addr); + pgdp = pgd_offset_k(addr); + pgd = READ_ONCE(*pgdp); if (CONFIG_PGTABLE_LEVELS > 3 && - !(pgd_none(*pgd) || pgd_page_paddr(*pgd) == __pa_symbol(bm_pud))) { + !(pgd_none(pgd) || pgd_page_paddr(pgd) == __pa_symbol(bm_pud))) { /* * We only end up here if the kernel mapping and the fixmap * share the top level pgd entry, which should only happen on * 16k/4 levels configurations. */ BUG_ON(!IS_ENABLED(CONFIG_ARM64_16K_PAGES)); - pud = pud_offset_kimg(pgd, addr); + pudp = pud_offset_kimg(pgdp, addr); } else { - if (pgd_none(*pgd)) - __pgd_populate(pgd, __pa_symbol(bm_pud), PUD_TYPE_TABLE); - pud = fixmap_pud(addr); + if (pgd_none(pgd)) + __pgd_populate(pgdp, __pa_symbol(bm_pud), PUD_TYPE_TABLE); + pudp = fixmap_pud(addr); } - if (pud_none(*pud)) - __pud_populate(pud, __pa_symbol(bm_pmd), PMD_TYPE_TABLE); - pmd = fixmap_pmd(addr); - __pmd_populate(pmd, __pa_symbol(bm_pte), PMD_TYPE_TABLE); + if (pud_none(READ_ONCE(*pudp))) + __pud_populate(pudp, __pa_symbol(bm_pmd), PMD_TYPE_TABLE); + pmdp = fixmap_pmd(addr); + __pmd_populate(pmdp, __pa_symbol(bm_pte), PMD_TYPE_TABLE); /* * The boot-ioremap range spans multiple pmds, for which @@ -800,11 +814,11 @@ void __init early_fixmap_init(void) BUILD_BUG_ON((__fix_to_virt(FIX_BTMAP_BEGIN) >> PMD_SHIFT) != (__fix_to_virt(FIX_BTMAP_END) >> PMD_SHIFT)); - if ((pmd != fixmap_pmd(fix_to_virt(FIX_BTMAP_BEGIN))) - || pmd != fixmap_pmd(fix_to_virt(FIX_BTMAP_END))) { + if ((pmdp != fixmap_pmd(fix_to_virt(FIX_BTMAP_BEGIN))) + || pmdp != fixmap_pmd(fix_to_virt(FIX_BTMAP_END))) { WARN_ON(1); - pr_warn("pmd %p != %p, %p\n", - pmd, fixmap_pmd(fix_to_virt(FIX_BTMAP_BEGIN)), + pr_warn("pmdp %p != %p, %p\n", + pmdp, fixmap_pmd(fix_to_virt(FIX_BTMAP_BEGIN)), fixmap_pmd(fix_to_virt(FIX_BTMAP_END))); pr_warn("fix_to_virt(FIX_BTMAP_BEGIN): %08lx\n", fix_to_virt(FIX_BTMAP_BEGIN)); @@ -824,16 +838,16 @@ void __set_fixmap(enum fixed_addresses idx, phys_addr_t phys, pgprot_t flags) { unsigned long addr = __fix_to_virt(idx); - pte_t *pte; + pte_t *ptep; BUG_ON(idx <= FIX_HOLE || idx >= __end_of_fixed_addresses); - pte = fixmap_pte(addr); + ptep = fixmap_pte(addr); if (pgprot_val(flags)) { - set_pte(pte, pfn_pte(phys >> PAGE_SHIFT, flags)); + set_pte(ptep, pfn_pte(phys >> PAGE_SHIFT, flags)); } else { - pte_clear(&init_mm, addr, pte); + pte_clear(&init_mm, addr, ptep); flush_tlb_kernel_range(addr, addr+PAGE_SIZE); } } @@ -915,36 +929,36 @@ int __init arch_ioremap_pmd_supported(void) return 1; } -int pud_set_huge(pud_t *pud, phys_addr_t phys, pgprot_t prot) +int pud_set_huge(pud_t *pudp, phys_addr_t phys, pgprot_t prot) { pgprot_t sect_prot = __pgprot(PUD_TYPE_SECT | pgprot_val(mk_sect_prot(prot))); BUG_ON(phys & ~PUD_MASK); - set_pud(pud, pfn_pud(__phys_to_pfn(phys), sect_prot)); + set_pud(pudp, pfn_pud(__phys_to_pfn(phys), sect_prot)); return 1; } -int pmd_set_huge(pmd_t *pmd, phys_addr_t phys, pgprot_t prot) +int pmd_set_huge(pmd_t *pmdp, phys_addr_t phys, pgprot_t prot) { pgprot_t sect_prot = __pgprot(PMD_TYPE_SECT | pgprot_val(mk_sect_prot(prot))); BUG_ON(phys & ~PMD_MASK); - set_pmd(pmd, pfn_pmd(__phys_to_pfn(phys), sect_prot)); + set_pmd(pmdp, pfn_pmd(__phys_to_pfn(phys), sect_prot)); return 1; } -int pud_clear_huge(pud_t *pud) +int pud_clear_huge(pud_t *pudp) { - if (!pud_sect(*pud)) + if (!pud_sect(READ_ONCE(*pudp))) return 0; - pud_clear(pud); + pud_clear(pudp); return 1; } -int pmd_clear_huge(pmd_t *pmd) +int pmd_clear_huge(pmd_t *pmdp) { - if (!pmd_sect(*pmd)) + if (!pmd_sect(READ_ONCE(*pmdp))) return 0; - pmd_clear(pmd); + pmd_clear(pmdp); return 1; } diff --git a/arch/arm64/mm/pageattr.c b/arch/arm64/mm/pageattr.c index a682a0a2a0fa..a56359373d8b 100644 --- a/arch/arm64/mm/pageattr.c +++ b/arch/arm64/mm/pageattr.c @@ -29,7 +29,7 @@ static int change_page_range(pte_t *ptep, pgtable_t token, unsigned long addr, void *data) { struct page_change_data *cdata = data; - pte_t pte = *ptep; + pte_t pte = READ_ONCE(*ptep); pte = clear_pte_bit(pte, cdata->clear_mask); pte = set_pte_bit(pte, cdata->set_mask); @@ -156,30 +156,32 @@ void __kernel_map_pages(struct page *page, int numpages, int enable) */ bool kernel_page_present(struct page *page) { - pgd_t *pgd; - pud_t *pud; - pmd_t *pmd; - pte_t *pte; + pgd_t *pgdp; + pud_t *pudp, pud; + pmd_t *pmdp, pmd; + pte_t *ptep; unsigned long addr = (unsigned long)page_address(page); - pgd = pgd_offset_k(addr); - if (pgd_none(*pgd)) + pgdp = pgd_offset_k(addr); + if (pgd_none(READ_ONCE(*pgdp))) return false; - pud = pud_offset(pgd, addr); - if (pud_none(*pud)) + pudp = pud_offset(pgdp, addr); + pud = READ_ONCE(*pudp); + if (pud_none(pud)) return false; - if (pud_sect(*pud)) + if (pud_sect(pud)) return true; - pmd = pmd_offset(pud, addr); - if (pmd_none(*pmd)) + pmdp = pmd_offset(pudp, addr); + pmd = READ_ONCE(*pmdp); + if (pmd_none(pmd)) return false; - if (pmd_sect(*pmd)) + if (pmd_sect(pmd)) return true; - pte = pte_offset_kernel(pmd, addr); - return pte_valid(*pte); + ptep = pte_offset_kernel(pmdp, addr); + return pte_valid(READ_ONCE(*ptep)); } #endif /* CONFIG_HIBERNATION */ #endif /* CONFIG_DEBUG_PAGEALLOC */ -- cgit v1.2.3-55-g7522 From 6137e4166004e2ec383ac05d5ca15831f4668806 Mon Sep 17 00:00:00 2001 From: Max Filippov Date: Wed, 14 Feb 2018 16:12:54 -0800 Subject: xtensa: support DMA buffers in high memory If a DMA buffer is allocated in high memory and kernel mapping is required use dma_common_contiguous_remap to map buffer to the vmalloc region and dma_common_free_remap to unmap it. Signed-off-by: Max Filippov --- arch/xtensa/kernel/pci-dma.c | 40 ++++++++++++++++++++++++++++++---------- 1 file changed, 30 insertions(+), 10 deletions(-) (limited to 'arch') diff --git a/arch/xtensa/kernel/pci-dma.c b/arch/xtensa/kernel/pci-dma.c index 623720a11143..732631ce250f 100644 --- a/arch/xtensa/kernel/pci-dma.c +++ b/arch/xtensa/kernel/pci-dma.c @@ -16,6 +16,7 @@ */ #include +#include #include #include #include @@ -123,7 +124,7 @@ static void *xtensa_dma_alloc(struct device *dev, size_t size, unsigned long attrs) { unsigned long ret; - unsigned long uncached = 0; + unsigned long uncached; unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT; struct page *page = NULL; @@ -144,15 +145,27 @@ static void *xtensa_dma_alloc(struct device *dev, size_t size, if (!page) return NULL; - ret = (unsigned long)page_address(page); + *handle = phys_to_dma(dev, page_to_phys(page)); - /* We currently don't support coherent memory outside KSEG */ +#ifdef CONFIG_MMU + if (PageHighMem(page)) { + void *p; + p = dma_common_contiguous_remap(page, size, VM_MAP, + pgprot_noncached(PAGE_KERNEL), + __builtin_return_address(0)); + if (!p) { + if (!dma_release_from_contiguous(dev, page, count)) + __free_pages(page, get_order(size)); + } + return p; + } +#endif + ret = (unsigned long)page_address(page); BUG_ON(ret < XCHAL_KSEG_CACHED_VADDR || ret > XCHAL_KSEG_CACHED_VADDR + XCHAL_KSEG_SIZE - 1); uncached = ret + XCHAL_KSEG_BYPASS_VADDR - XCHAL_KSEG_CACHED_VADDR; - *handle = virt_to_bus((void *)ret); __invalidate_dcache_range(ret, size); return (void *)uncached; @@ -161,13 +174,20 @@ static void *xtensa_dma_alloc(struct device *dev, size_t size, static void xtensa_dma_free(struct device *dev, size_t size, void *vaddr, dma_addr_t dma_handle, unsigned long attrs) { - unsigned long addr = (unsigned long)vaddr + - XCHAL_KSEG_CACHED_VADDR - XCHAL_KSEG_BYPASS_VADDR; - struct page *page = virt_to_page(addr); unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT; - - BUG_ON(addr < XCHAL_KSEG_CACHED_VADDR || - addr > XCHAL_KSEG_CACHED_VADDR + XCHAL_KSEG_SIZE - 1); + unsigned long addr = (unsigned long)vaddr; + struct page *page; + + if (addr >= XCHAL_KSEG_BYPASS_VADDR && + addr - XCHAL_KSEG_BYPASS_VADDR < XCHAL_KSEG_SIZE) { + addr += XCHAL_KSEG_CACHED_VADDR - XCHAL_KSEG_BYPASS_VADDR; + page = virt_to_page(addr); + } else { +#ifdef CONFIG_MMU + dma_common_free_remap(vaddr, size, VM_MAP); +#endif + page = pfn_to_page(PHYS_PFN(dma_to_phys(dev, dma_handle))); + } if (!dma_release_from_contiguous(dev, page, count)) __free_pages(page, get_order(size)); -- cgit v1.2.3-55-g7522 From 3f1f576a195aa266813cbd4ca70291deb61e0129 Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Fri, 16 Feb 2018 12:26:38 +0100 Subject: x86/microcode: Propagate return value from updating functions ... so that callers can know when microcode was updated and act accordingly. Tested-by: Ashok Raj Signed-off-by: Borislav Petkov Reviewed-by: Ashok Raj Cc: Andy Lutomirski Cc: Arjan van de Ven Cc: Borislav Petkov Cc: Dan Williams Cc: Dave Hansen Cc: David Woodhouse Cc: Greg Kroah-Hartman Cc: Josh Poimboeuf Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20180216112640.11554-2-bp@alien8.de Signed-off-by: Ingo Molnar --- arch/x86/include/asm/microcode.h | 9 +++++++-- arch/x86/kernel/cpu/microcode/amd.c | 10 +++++----- arch/x86/kernel/cpu/microcode/core.c | 33 +++++++++++++++++---------------- arch/x86/kernel/cpu/microcode/intel.c | 10 +++++----- 4 files changed, 34 insertions(+), 28 deletions(-) (limited to 'arch') diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h index 55520cec8b27..7fb1047d61c7 100644 --- a/arch/x86/include/asm/microcode.h +++ b/arch/x86/include/asm/microcode.h @@ -37,7 +37,12 @@ struct cpu_signature { struct device; -enum ucode_state { UCODE_ERROR, UCODE_OK, UCODE_NFOUND }; +enum ucode_state { + UCODE_OK = 0, + UCODE_UPDATED, + UCODE_NFOUND, + UCODE_ERROR, +}; struct microcode_ops { enum ucode_state (*request_microcode_user) (int cpu, @@ -54,7 +59,7 @@ struct microcode_ops { * are being called. * See also the "Synchronization" section in microcode_core.c. */ - int (*apply_microcode) (int cpu); + enum ucode_state (*apply_microcode) (int cpu); int (*collect_cpu_info) (int cpu, struct cpu_signature *csig); }; diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c index 330b8462d426..a998e1a7d46f 100644 --- a/arch/x86/kernel/cpu/microcode/amd.c +++ b/arch/x86/kernel/cpu/microcode/amd.c @@ -498,7 +498,7 @@ static unsigned int verify_patch_size(u8 family, u32 patch_size, return patch_size; } -static int apply_microcode_amd(int cpu) +static enum ucode_state apply_microcode_amd(int cpu) { struct cpuinfo_x86 *c = &cpu_data(cpu); struct microcode_amd *mc_amd; @@ -512,7 +512,7 @@ static int apply_microcode_amd(int cpu) p = find_patch(cpu); if (!p) - return 0; + return UCODE_NFOUND; mc_amd = p->data; uci->mc = p->data; @@ -523,13 +523,13 @@ static int apply_microcode_amd(int cpu) if (rev >= mc_amd->hdr.patch_id) { c->microcode = rev; uci->cpu_sig.rev = rev; - return 0; + return UCODE_OK; } if (__apply_microcode_amd(mc_amd)) { pr_err("CPU%d: update failed for patch_level=0x%08x\n", cpu, mc_amd->hdr.patch_id); - return -1; + return UCODE_ERROR; } pr_info("CPU%d: new patch_level=0x%08x\n", cpu, mc_amd->hdr.patch_id); @@ -537,7 +537,7 @@ static int apply_microcode_amd(int cpu) uci->cpu_sig.rev = mc_amd->hdr.patch_id; c->microcode = mc_amd->hdr.patch_id; - return 0; + return UCODE_UPDATED; } static int install_equiv_cpu_table(const u8 *buf) diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index 319dd65f98a2..6fdaf7cf3182 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -374,7 +374,7 @@ static int collect_cpu_info(int cpu) } struct apply_microcode_ctx { - int err; + enum ucode_state err; }; static void apply_microcode_local(void *arg) @@ -489,31 +489,29 @@ static void __exit microcode_dev_exit(void) /* fake device for request_firmware */ static struct platform_device *microcode_pdev; -static int reload_for_cpu(int cpu) +static enum ucode_state reload_for_cpu(int cpu) { struct ucode_cpu_info *uci = ucode_cpu_info + cpu; enum ucode_state ustate; - int err = 0; if (!uci->valid) - return err; + return UCODE_OK; ustate = microcode_ops->request_microcode_fw(cpu, µcode_pdev->dev, true); - if (ustate == UCODE_OK) - apply_microcode_on_target(cpu); - else - if (ustate == UCODE_ERROR) - err = -EINVAL; - return err; + if (ustate != UCODE_OK) + return ustate; + + return apply_microcode_on_target(cpu); } static ssize_t reload_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t size) { + enum ucode_state tmp_ret = UCODE_OK; unsigned long val; + ssize_t ret = 0; int cpu; - ssize_t ret = 0, tmp_ret; ret = kstrtoul(buf, 0, &val); if (ret) @@ -526,15 +524,18 @@ static ssize_t reload_store(struct device *dev, mutex_lock(µcode_mutex); for_each_online_cpu(cpu) { tmp_ret = reload_for_cpu(cpu); - if (tmp_ret != 0) + if (tmp_ret > UCODE_NFOUND) { pr_warn("Error reloading microcode on CPU %d\n", cpu); - /* save retval of the first encountered reload error */ - if (!ret) - ret = tmp_ret; + /* set retval for the first encountered reload error */ + if (!ret) + ret = -EINVAL; + } } - if (!ret) + + if (!ret && tmp_ret == UCODE_UPDATED) perf_check_microcode(); + mutex_unlock(µcode_mutex); put_online_cpus(); diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c index a15db2b4e0d6..923054a6b760 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -772,7 +772,7 @@ static int collect_cpu_info(int cpu_num, struct cpu_signature *csig) return 0; } -static int apply_microcode_intel(int cpu) +static enum ucode_state apply_microcode_intel(int cpu) { struct microcode_intel *mc; struct ucode_cpu_info *uci; @@ -782,7 +782,7 @@ static int apply_microcode_intel(int cpu) /* We should bind the task to the CPU */ if (WARN_ON(raw_smp_processor_id() != cpu)) - return -1; + return UCODE_ERROR; uci = ucode_cpu_info + cpu; mc = uci->mc; @@ -790,7 +790,7 @@ static int apply_microcode_intel(int cpu) /* Look for a newer patch in our cache: */ mc = find_patch(uci); if (!mc) - return 0; + return UCODE_NFOUND; } /* write microcode via MSR 0x79 */ @@ -801,7 +801,7 @@ static int apply_microcode_intel(int cpu) if (rev != mc->hdr.rev) { pr_err("CPU%d update to revision 0x%x failed\n", cpu, mc->hdr.rev); - return -1; + return UCODE_ERROR; } if (rev != prev_rev) { @@ -818,7 +818,7 @@ static int apply_microcode_intel(int cpu) uci->cpu_sig.rev = rev; c->microcode = rev; - return 0; + return UCODE_UPDATED; } static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size, -- cgit v1.2.3-55-g7522 From 1008c52c09dcb23d93f8e0ea83a6246265d2cce0 Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Fri, 16 Feb 2018 12:26:39 +0100 Subject: x86/CPU: Add a microcode loader callback Add a callback function which the microcode loader calls when microcode has been updated to a newer revision. Do the callback only when no error was encountered during loading. Tested-by: Ashok Raj Signed-off-by: Borislav Petkov Reviewed-by: Ashok Raj Cc: Andy Lutomirski Cc: Arjan van de Ven Cc: Borislav Petkov Cc: Dan Williams Cc: Dave Hansen Cc: David Woodhouse Cc: Greg Kroah-Hartman Cc: Josh Poimboeuf Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20180216112640.11554-3-bp@alien8.de Signed-off-by: Ingo Molnar --- arch/x86/include/asm/processor.h | 1 + arch/x86/kernel/cpu/common.c | 10 ++++++++++ arch/x86/kernel/cpu/microcode/core.c | 8 ++++++-- 3 files changed, 17 insertions(+), 2 deletions(-) (limited to 'arch') diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 1bd9ed87606f..b0ccd4847a58 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -977,4 +977,5 @@ bool xen_set_default_idle(void); void stop_this_cpu(void *dummy); void df_debug(struct pt_regs *regs, long error_code); +void microcode_check(void); #endif /* _ASM_X86_PROCESSOR_H */ diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 824aee0117bb..84f1cd88608b 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1749,3 +1749,13 @@ static int __init init_cpu_syscore(void) return 0; } core_initcall(init_cpu_syscore); + +/* + * The microcode loader calls this upon late microcode load to recheck features, + * only when microcode has been updated. Caller holds microcode_mutex and CPU + * hotplug lock. + */ +void microcode_check(void) +{ + perf_check_microcode(); +} diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index 6fdaf7cf3182..aa1b9a422f2b 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -509,6 +509,7 @@ static ssize_t reload_store(struct device *dev, const char *buf, size_t size) { enum ucode_state tmp_ret = UCODE_OK; + bool do_callback = false; unsigned long val; ssize_t ret = 0; int cpu; @@ -531,10 +532,13 @@ static ssize_t reload_store(struct device *dev, if (!ret) ret = -EINVAL; } + + if (tmp_ret == UCODE_UPDATED) + do_callback = true; } - if (!ret && tmp_ret == UCODE_UPDATED) - perf_check_microcode(); + if (!ret && do_callback) + microcode_check(); mutex_unlock(µcode_mutex); put_online_cpus(); -- cgit v1.2.3-55-g7522 From 42ca8082e260dcfd8afa2afa6ec1940b9d41724c Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Fri, 16 Feb 2018 12:26:40 +0100 Subject: x86/CPU: Check CPU feature bits after microcode upgrade With some microcode upgrades, new CPUID features can become visible on the CPU. Check what the kernel has mirrored now and issue a warning hinting at possible things the user/admin can do to make use of the newly visible features. Originally-by: Ashok Raj Tested-by: Ashok Raj Signed-off-by: Borislav Petkov Reviewed-by: Ashok Raj Cc: Andy Lutomirski Cc: Arjan van de Ven Cc: Borislav Petkov Cc: Dan Williams Cc: Dave Hansen Cc: David Woodhouse Cc: Greg Kroah-Hartman Cc: Josh Poimboeuf Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20180216112640.11554-4-bp@alien8.de Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/common.c | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'arch') diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 84f1cd88608b..348cf4821240 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1757,5 +1757,25 @@ core_initcall(init_cpu_syscore); */ void microcode_check(void) { + struct cpuinfo_x86 info; + perf_check_microcode(); + + /* Reload CPUID max function as it might've changed. */ + info.cpuid_level = cpuid_eax(0); + + /* + * Copy all capability leafs to pick up the synthetic ones so that + * memcmp() below doesn't fail on that. The ones coming from CPUID will + * get overwritten in get_cpu_cap(). + */ + memcpy(&info.x86_capability, &boot_cpu_data.x86_capability, sizeof(info.x86_capability)); + + get_cpu_cap(&info); + + if (!memcmp(&info.x86_capability, &boot_cpu_data.x86_capability, sizeof(info.x86_capability))) + return; + + pr_warn("x86/CPU: CPU features have changed after loading microcode, but might not take effect.\n"); + pr_warn("x86/CPU: Please consider either early loading through initrd/built-in or a potential BIOS update.\n"); } -- cgit v1.2.3-55-g7522 From e1a50de37860b3a93a9d643b09638db5aff47650 Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Fri, 16 Feb 2018 17:04:23 +0000 Subject: arm64: cputype: Silence Sparse warnings Sparse makes a fair bit of noise about our MPIDR mask being implicitly long - let's explicitly describe it as such rather than just relying on the value forcing automatic promotion. Signed-off-by: Robin Murphy Signed-off-by: Catalin Marinas --- arch/arm64/include/asm/cputype.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index be7bd19c87ec..eda8c5f629fc 100644 --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -20,7 +20,7 @@ #define MPIDR_UP_BITMASK (0x1 << 30) #define MPIDR_MT_BITMASK (0x1 << 24) -#define MPIDR_HWID_BITMASK 0xff00ffffff +#define MPIDR_HWID_BITMASK 0xff00ffffffUL #define MPIDR_LEVEL_BITS_SHIFT 3 #define MPIDR_LEVEL_BITS (1 << MPIDR_LEVEL_BITS_SHIFT) -- cgit v1.2.3-55-g7522 From 63e708f826bb21470155d37b103a75d8a9e25b18 Mon Sep 17 00:00:00 2001 From: Prarit Bhargava Date: Wed, 7 Feb 2018 18:49:23 -0500 Subject: x86/xen: Calculate __max_logical_packages on PV domains The kernel panics on PV domains because native_smp_cpus_done() is only called for HVM domains. Calculate __max_logical_packages for PV domains. Fixes: b4c0a7326f5d ("x86/smpboot: Fix __max_logical_packages estimate") Signed-off-by: Prarit Bhargava Tested-and-reported-by: Simon Gaiser Cc: Thomas Gleixner Cc: Ingo Molnar Cc: "H. Peter Anvin" Cc: x86@kernel.org Cc: Boris Ostrovsky Cc: Juergen Gross Cc: Dou Liyang Cc: Prarit Bhargava Cc: Kate Stewart Cc: Greg Kroah-Hartman Cc: Andy Lutomirski Cc: Andi Kleen Cc: Vitaly Kuznetsov Cc: xen-devel@lists.xenproject.org Reviewed-by: Boris Ostrovsky Signed-off-by: Juergen Gross --- arch/x86/include/asm/smp.h | 1 + arch/x86/kernel/smpboot.c | 10 ++++++++-- arch/x86/xen/smp.c | 2 ++ 3 files changed, 11 insertions(+), 2 deletions(-) (limited to 'arch') diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h index 461f53d27708..a4189762b266 100644 --- a/arch/x86/include/asm/smp.h +++ b/arch/x86/include/asm/smp.h @@ -129,6 +129,7 @@ static inline void arch_send_call_function_ipi_mask(const struct cpumask *mask) void cpu_disable_common(void); void native_smp_prepare_boot_cpu(void); void native_smp_prepare_cpus(unsigned int max_cpus); +void calculate_max_logical_packages(void); void native_smp_cpus_done(unsigned int max_cpus); void common_cpu_up(unsigned int cpunum, struct task_struct *tidle); int native_cpu_up(unsigned int cpunum, struct task_struct *tidle); diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index cfc61e1d45e2..9eee25d07586 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -1281,11 +1281,10 @@ void __init native_smp_prepare_boot_cpu(void) cpu_set_state_online(me); } -void __init native_smp_cpus_done(unsigned int max_cpus) +void __init calculate_max_logical_packages(void) { int ncpus; - pr_debug("Boot done\n"); /* * Today neither Intel nor AMD support heterogenous systems so * extrapolate the boot cpu's data to all packages. @@ -1293,6 +1292,13 @@ void __init native_smp_cpus_done(unsigned int max_cpus) ncpus = cpu_data(0).booted_cores * topology_max_smt_threads(); __max_logical_packages = DIV_ROUND_UP(nr_cpu_ids, ncpus); pr_info("Max logical packages: %u\n", __max_logical_packages); +} + +void __init native_smp_cpus_done(unsigned int max_cpus) +{ + pr_debug("Boot done\n"); + + calculate_max_logical_packages(); if (x86_has_numa_in_package) set_sched_topology(x86_numa_in_package_topology); diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c index 77c959cf81e7..7a43b2ae19f1 100644 --- a/arch/x86/xen/smp.c +++ b/arch/x86/xen/smp.c @@ -122,6 +122,8 @@ void __init xen_smp_cpus_done(unsigned int max_cpus) if (xen_hvm_domain()) native_smp_cpus_done(max_cpus); + else + calculate_max_logical_packages(); if (xen_have_vcpu_info_placement) return; -- cgit v1.2.3-55-g7522 From 9e809d15d6b692fa061d74be7aaab1c79f6784b8 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Wed, 14 Feb 2018 18:59:23 +0100 Subject: x86/entry: Reduce the code footprint of the 'idtentry' macro Play a little trick in the generic PUSH_AND_CLEAR_REGS macro to insert the GP registers "above" the original return address. This allows us to (re-)insert the macro in error_entry() and paranoid_entry() and to remove it from the idtentry macro. This reduces the static footprint significantly: text data bss dec hex filename 24307 0 0 24307 5ef3 entry_64.o-orig 20987 0 0 20987 51fb entry_64.o Co-developed-by: Linus Torvalds Signed-off-by: Dominik Brodowski Cc: Andy Lutomirski Cc: Arjan van de Ven Cc: Borislav Petkov Cc: Dan Williams Cc: Dave Hansen Cc: David Woodhouse Cc: Greg Kroah-Hartman Cc: Josh Poimboeuf Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20180214175924.23065-2-linux@dominikbrodowski.net [ Small tweaks to comments. ] Signed-off-by: Ingo Molnar --- arch/x86/entry/calling.h | 11 ++++++++++- arch/x86/entry/entry_64.S | 18 ++++++++---------- 2 files changed, 18 insertions(+), 11 deletions(-) (limited to 'arch') diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h index dce7092ab24a..196b6103edf6 100644 --- a/arch/x86/entry/calling.h +++ b/arch/x86/entry/calling.h @@ -97,7 +97,7 @@ For 32-bit we have the following conventions - kernel is built with #define SIZEOF_PTREGS 21*8 -.macro PUSH_AND_CLEAR_REGS rdx=%rdx rax=%rax +.macro PUSH_AND_CLEAR_REGS rdx=%rdx rax=%rax save_ret=0 /* * Push registers and sanitize registers of values that a * speculation attack might otherwise want to exploit. The @@ -105,8 +105,14 @@ For 32-bit we have the following conventions - kernel is built with * could be put to use in a speculative execution gadget. * Interleave XOR with PUSH for better uop scheduling: */ + .if \save_ret + pushq %rsi /* pt_regs->si */ + movq 8(%rsp), %rsi /* temporarily store the return address in %rsi */ + movq %rdi, 8(%rsp) /* pt_regs->di (overwriting original return address) */ + .else pushq %rdi /* pt_regs->di */ pushq %rsi /* pt_regs->si */ + .endif pushq \rdx /* pt_regs->dx */ pushq %rcx /* pt_regs->cx */ pushq \rax /* pt_regs->ax */ @@ -131,6 +137,9 @@ For 32-bit we have the following conventions - kernel is built with pushq %r15 /* pt_regs->r15 */ xorq %r15, %r15 /* nospec r15*/ UNWIND_HINT_REGS + .if \save_ret + pushq %rsi /* return address on top of stack */ + .endif .endm .macro POP_REGS pop_rdi=1 skip_r11rcx=0 diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 8971bd64d515..77edc2390868 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -875,12 +875,8 @@ ENTRY(\sym) pushq $-1 /* ORIG_RAX: no syscall to restart */ .endif - /* Save all registers in pt_regs */ - PUSH_AND_CLEAR_REGS - ENCODE_FRAME_POINTER - .if \paranoid < 2 - testb $3, CS(%rsp) /* If coming from userspace, switch stacks */ + testb $3, CS-ORIG_RAX(%rsp) /* If coming from userspace, switch stacks */ jnz .Lfrom_usermode_switch_stack_\@ .endif @@ -1130,13 +1126,15 @@ idtentry machine_check do_mce has_error_code=0 paranoid=1 #endif /* - * Switch gs if needed. + * Save all registers in pt_regs, and switch gs if needed. * Use slow, but surefire "are we in kernel?" check. * Return: ebx=0: need swapgs on exit, ebx=1: otherwise */ ENTRY(paranoid_entry) UNWIND_HINT_FUNC cld + PUSH_AND_CLEAR_REGS save_ret=1 + ENCODE_FRAME_POINTER 8 movl $1, %ebx movl $MSR_GS_BASE, %ecx rdmsr @@ -1181,12 +1179,14 @@ ENTRY(paranoid_exit) END(paranoid_exit) /* - * Switch gs if needed. + * Save all registers in pt_regs, and switch GS if needed. * Return: EBX=0: came from user mode; EBX=1: otherwise */ ENTRY(error_entry) - UNWIND_HINT_REGS offset=8 + UNWIND_HINT_FUNC cld + PUSH_AND_CLEAR_REGS save_ret=1 + ENCODE_FRAME_POINTER 8 testb $3, CS+8(%rsp) jz .Lerror_kernelspace @@ -1577,8 +1577,6 @@ end_repeat_nmi: * frame to point back to repeat_nmi. */ pushq $-1 /* ORIG_RAX: no syscall to restart */ - PUSH_AND_CLEAR_REGS - ENCODE_FRAME_POINTER /* * Use paranoid_entry to handle SWAPGS, but no need to use paranoid_exit -- cgit v1.2.3-55-g7522 From ced5d0bf603fa0baee8ea889e1d70971fd210894 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Wed, 14 Feb 2018 18:59:24 +0100 Subject: x86/entry/64: Use 'xorl' for faster register clearing On some x86 CPU microarchitectures using 'xorq' to clear general-purpose registers is slower than 'xorl'. As 'xorl' is sufficient to clear all 64 bits of these registers due to zero-extension [*], switch the x86 64-bit entry code to use 'xorl'. No change in functionality and no change in code size. [*] According to Intel 64 and IA-32 Architecture Software Developer's Manual, section 3.4.1.1, the result of 32-bit operands are "zero- extended to a 64-bit result in the destination general-purpose register." The AMD64 Architecture Programmer’s Manual Volume 3, Appendix B.1, describes the same behaviour. Suggested-by: Denys Vlasenko Signed-off-by: Dominik Brodowski Cc: Andy Lutomirski Cc: Arjan van de Ven Cc: Borislav Petkov Cc: Dan Williams Cc: Dave Hansen Cc: David Woodhouse Cc: Greg Kroah-Hartman Cc: Josh Poimboeuf Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20180214175924.23065-3-linux@dominikbrodowski.net [ Improved on the changelog a bit. ] Signed-off-by: Ingo Molnar --- arch/x86/entry/calling.h | 16 ++++++------ arch/x86/entry/entry_64_compat.S | 54 ++++++++++++++++++++-------------------- 2 files changed, 35 insertions(+), 35 deletions(-) (limited to 'arch') diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h index 196b6103edf6..5d10b7a85cad 100644 --- a/arch/x86/entry/calling.h +++ b/arch/x86/entry/calling.h @@ -117,25 +117,25 @@ For 32-bit we have the following conventions - kernel is built with pushq %rcx /* pt_regs->cx */ pushq \rax /* pt_regs->ax */ pushq %r8 /* pt_regs->r8 */ - xorq %r8, %r8 /* nospec r8 */ + xorl %r8d, %r8d /* nospec r8 */ pushq %r9 /* pt_regs->r9 */ - xorq %r9, %r9 /* nospec r9 */ + xorl %r9d, %r9d /* nospec r9 */ pushq %r10 /* pt_regs->r10 */ - xorq %r10, %r10 /* nospec r10 */ + xorl %r10d, %r10d /* nospec r10 */ pushq %r11 /* pt_regs->r11 */ - xorq %r11, %r11 /* nospec r11*/ + xorl %r11d, %r11d /* nospec r11*/ pushq %rbx /* pt_regs->rbx */ xorl %ebx, %ebx /* nospec rbx*/ pushq %rbp /* pt_regs->rbp */ xorl %ebp, %ebp /* nospec rbp*/ pushq %r12 /* pt_regs->r12 */ - xorq %r12, %r12 /* nospec r12*/ + xorl %r12d, %r12d /* nospec r12*/ pushq %r13 /* pt_regs->r13 */ - xorq %r13, %r13 /* nospec r13*/ + xorl %r13d, %r13d /* nospec r13*/ pushq %r14 /* pt_regs->r14 */ - xorq %r14, %r14 /* nospec r14*/ + xorl %r14d, %r14d /* nospec r14*/ pushq %r15 /* pt_regs->r15 */ - xorq %r15, %r15 /* nospec r15*/ + xorl %r15d, %r15d /* nospec r15*/ UNWIND_HINT_REGS .if \save_ret pushq %rsi /* return address on top of stack */ diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S index fd65e016e413..364ea4a207be 100644 --- a/arch/x86/entry/entry_64_compat.S +++ b/arch/x86/entry/entry_64_compat.S @@ -85,25 +85,25 @@ ENTRY(entry_SYSENTER_compat) pushq %rcx /* pt_regs->cx */ pushq $-ENOSYS /* pt_regs->ax */ pushq $0 /* pt_regs->r8 = 0 */ - xorq %r8, %r8 /* nospec r8 */ + xorl %r8d, %r8d /* nospec r8 */ pushq $0 /* pt_regs->r9 = 0 */ - xorq %r9, %r9 /* nospec r9 */ + xorl %r9d, %r9d /* nospec r9 */ pushq $0 /* pt_regs->r10 = 0 */ - xorq %r10, %r10 /* nospec r10 */ + xorl %r10d, %r10d /* nospec r10 */ pushq $0 /* pt_regs->r11 = 0 */ - xorq %r11, %r11 /* nospec r11 */ + xorl %r11d, %r11d /* nospec r11 */ pushq %rbx /* pt_regs->rbx */ xorl %ebx, %ebx /* nospec rbx */ pushq %rbp /* pt_regs->rbp (will be overwritten) */ xorl %ebp, %ebp /* nospec rbp */ pushq $0 /* pt_regs->r12 = 0 */ - xorq %r12, %r12 /* nospec r12 */ + xorl %r12d, %r12d /* nospec r12 */ pushq $0 /* pt_regs->r13 = 0 */ - xorq %r13, %r13 /* nospec r13 */ + xorl %r13d, %r13d /* nospec r13 */ pushq $0 /* pt_regs->r14 = 0 */ - xorq %r14, %r14 /* nospec r14 */ + xorl %r14d, %r14d /* nospec r14 */ pushq $0 /* pt_regs->r15 = 0 */ - xorq %r15, %r15 /* nospec r15 */ + xorl %r15d, %r15d /* nospec r15 */ cld /* @@ -224,25 +224,25 @@ GLOBAL(entry_SYSCALL_compat_after_hwframe) pushq %rbp /* pt_regs->cx (stashed in bp) */ pushq $-ENOSYS /* pt_regs->ax */ pushq $0 /* pt_regs->r8 = 0 */ - xorq %r8, %r8 /* nospec r8 */ + xorl %r8d, %r8d /* nospec r8 */ pushq $0 /* pt_regs->r9 = 0 */ - xorq %r9, %r9 /* nospec r9 */ + xorl %r9d, %r9d /* nospec r9 */ pushq $0 /* pt_regs->r10 = 0 */ - xorq %r10, %r10 /* nospec r10 */ + xorl %r10d, %r10d /* nospec r10 */ pushq $0 /* pt_regs->r11 = 0 */ - xorq %r11, %r11 /* nospec r11 */ + xorl %r11d, %r11d /* nospec r11 */ pushq %rbx /* pt_regs->rbx */ xorl %ebx, %ebx /* nospec rbx */ pushq %rbp /* pt_regs->rbp (will be overwritten) */ xorl %ebp, %ebp /* nospec rbp */ pushq $0 /* pt_regs->r12 = 0 */ - xorq %r12, %r12 /* nospec r12 */ + xorl %r12d, %r12d /* nospec r12 */ pushq $0 /* pt_regs->r13 = 0 */ - xorq %r13, %r13 /* nospec r13 */ + xorl %r13d, %r13d /* nospec r13 */ pushq $0 /* pt_regs->r14 = 0 */ - xorq %r14, %r14 /* nospec r14 */ + xorl %r14d, %r14d /* nospec r14 */ pushq $0 /* pt_regs->r15 = 0 */ - xorq %r15, %r15 /* nospec r15 */ + xorl %r15d, %r15d /* nospec r15 */ /* * User mode is traced as though IRQs are on, and SYSENTER @@ -298,9 +298,9 @@ sysret32_from_system_call: */ SWITCH_TO_USER_CR3_NOSTACK scratch_reg=%r8 scratch_reg2=%r9 - xorq %r8, %r8 - xorq %r9, %r9 - xorq %r10, %r10 + xorl %r8d, %r8d + xorl %r9d, %r9d + xorl %r10d, %r10d swapgs sysretl END(entry_SYSCALL_compat) @@ -358,25 +358,25 @@ ENTRY(entry_INT80_compat) pushq %rcx /* pt_regs->cx */ pushq $-ENOSYS /* pt_regs->ax */ pushq $0 /* pt_regs->r8 = 0 */ - xorq %r8, %r8 /* nospec r8 */ + xorl %r8d, %r8d /* nospec r8 */ pushq $0 /* pt_regs->r9 = 0 */ - xorq %r9, %r9 /* nospec r9 */ + xorl %r9d, %r9d /* nospec r9 */ pushq $0 /* pt_regs->r10 = 0 */ - xorq %r10, %r10 /* nospec r10 */ + xorl %r10d, %r10d /* nospec r10 */ pushq $0 /* pt_regs->r11 = 0 */ - xorq %r11, %r11 /* nospec r11 */ + xorl %r11d, %r11d /* nospec r11 */ pushq %rbx /* pt_regs->rbx */ xorl %ebx, %ebx /* nospec rbx */ pushq %rbp /* pt_regs->rbp */ xorl %ebp, %ebp /* nospec rbp */ pushq %r12 /* pt_regs->r12 */ - xorq %r12, %r12 /* nospec r12 */ + xorl %r12d, %r12d /* nospec r12 */ pushq %r13 /* pt_regs->r13 */ - xorq %r13, %r13 /* nospec r13 */ + xorl %r13d, %r13d /* nospec r13 */ pushq %r14 /* pt_regs->r14 */ - xorq %r14, %r14 /* nospec r14 */ + xorl %r14d, %r14d /* nospec r14 */ pushq %r15 /* pt_regs->r15 */ - xorq %r15, %r15 /* nospec r15 */ + xorl %r15d, %r15d /* nospec r15 */ cld /* -- cgit v1.2.3-55-g7522 From 2cb370d615e9fbed9e95ed222c2c8f337181aa90 Mon Sep 17 00:00:00 2001 From: Eugeniu Rosca Date: Sun, 18 Feb 2018 00:10:29 +0100 Subject: s390: Replace IS_ENABLED(EXPOLINE_*) with IS_ENABLED(CONFIG_EXPOLINE_*) I've accidentally stumbled upon the IS_ENABLED(EXPOLINE_*) lines, which obviously always evaluate to false. Fix this. Fixes: f19fbd5ed642 ("s390: introduce execute-trampolines for branches") Signed-off-by: Eugeniu Rosca Signed-off-by: Martin Schwidefsky --- arch/s390/kernel/nospec-branch.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch') diff --git a/arch/s390/kernel/nospec-branch.c b/arch/s390/kernel/nospec-branch.c index 69d7fcf48158..9aff72d3abda 100644 --- a/arch/s390/kernel/nospec-branch.c +++ b/arch/s390/kernel/nospec-branch.c @@ -2,8 +2,8 @@ #include #include -int nospec_call_disable = IS_ENABLED(EXPOLINE_OFF); -int nospec_return_disable = !IS_ENABLED(EXPOLINE_FULL); +int nospec_call_disable = IS_ENABLED(CONFIG_EXPOLINE_OFF); +int nospec_return_disable = !IS_ENABLED(CONFIG_EXPOLINE_FULL); static int __init nospectre_v2_setup_early(char *str) { -- cgit v1.2.3-55-g7522 From 04c4927359b1f09310bfee92e7187c9022be3e00 Mon Sep 17 00:00:00 2001 From: Bhupesh Sharma Date: Mon, 19 Feb 2018 12:09:54 +0530 Subject: arm64: Fix compilation error while accessing MPIDR_HWID_BITMASK from .S files Since commit e1a50de37860 (arm64: cputype: Silence Sparse warnings), compilation of arm64 architecture is broken with the following error messages: AR arch/arm64/kernel/built-in.o arch/arm64/kernel/head.S: Assembler messages: arch/arm64/kernel/head.S:677: Error: found 'L', expected: ')' arch/arm64/kernel/head.S:677: Error: found 'L', expected: ')' arch/arm64/kernel/head.S:677: Error: found 'L', expected: ')' arch/arm64/kernel/head.S:677: Error: junk at end of line, first unrecognized character is `L' arch/arm64/kernel/head.S:677: Error: unexpected characters following instruction at operand 2 -- `movz x1,:abs_g1_s:0xff00ffffffUL' arch/arm64/kernel/head.S:677: Error: unexpected characters following instruction at operand 2 -- `movk x1,:abs_g0_nc:0xff00ffffffUL' This patch fixes the same by using the UL() macro correctly for assigning the MPIDR_HWID_BITMASK macro value. Fixes: e1a50de37860 ("arm64: cputype: Silence Sparse warnings") Acked-by: Arnd Bergmann Acked-by: Robin Murphy Signed-off-by: Bhupesh Sharma Signed-off-by: Catalin Marinas --- arch/arm64/include/asm/cputype.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index eda8c5f629fc..350c76a1d15b 100644 --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -20,7 +20,7 @@ #define MPIDR_UP_BITMASK (0x1 << 30) #define MPIDR_MT_BITMASK (0x1 << 24) -#define MPIDR_HWID_BITMASK 0xff00ffffffUL +#define MPIDR_HWID_BITMASK UL(0xff00ffffff) #define MPIDR_LEVEL_BITS_SHIFT 3 #define MPIDR_LEVEL_BITS (1 << MPIDR_LEVEL_BITS_SHIFT) -- cgit v1.2.3-55-g7522 From 9085b34d0e8361595a7d19034c550d5d15044556 Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Mon, 19 Feb 2018 13:38:00 +0000 Subject: arm64: uaccess: Formalise types for access_ok() In converting __range_ok() into a static inline, I inadvertently made it more type-safe, but without considering the ordering of the relevant conversions. This leads to quite a lot of Sparse noise about the fact that we use __chk_user_ptr() after addr has already been converted from a user pointer to an unsigned long. Rather than just adding another cast for the sake of shutting Sparse up, it seems reasonable to rework the types to make logical sense (although the resulting codegen for __range_ok() remains identical). The only callers this affects directly are our compat traps where the inferred "user-pointer-ness" of a register value now warrants explicit casting. Signed-off-by: Robin Murphy Signed-off-by: Catalin Marinas --- arch/arm64/include/asm/uaccess.h | 12 ++++++------ arch/arm64/kernel/armv8_deprecated.c | 4 +++- arch/arm64/kernel/sys_compat.c | 2 +- 3 files changed, 10 insertions(+), 8 deletions(-) (limited to 'arch') diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h index 543e11f0f657..e66b0fca99c2 100644 --- a/arch/arm64/include/asm/uaccess.h +++ b/arch/arm64/include/asm/uaccess.h @@ -72,15 +72,15 @@ static inline void set_fs(mm_segment_t fs) * This is equivalent to the following test: * (u65)addr + (u65)size <= (u65)current->addr_limit + 1 */ -static inline unsigned long __range_ok(unsigned long addr, unsigned long size) +static inline unsigned long __range_ok(const void __user *addr, unsigned long size) { - unsigned long limit = current_thread_info()->addr_limit; + unsigned long ret, limit = current_thread_info()->addr_limit; __chk_user_ptr(addr); asm volatile( // A + B <= C + 1 for all A,B,C, in four easy steps: // 1: X = A + B; X' = X % 2^64 - " adds %0, %0, %2\n" + " adds %0, %3, %2\n" // 2: Set C = 0 if X > 2^64, to guarantee X' > C in step 4 " csel %1, xzr, %1, hi\n" // 3: Set X' = ~0 if X >= 2^64. For X == 2^64, this decrements X' @@ -92,9 +92,9 @@ static inline unsigned long __range_ok(unsigned long addr, unsigned long size) // testing X' - C == 0, subject to the previous adjustments. " sbcs xzr, %0, %1\n" " cset %0, ls\n" - : "+r" (addr), "+r" (limit) : "Ir" (size) : "cc"); + : "=&r" (ret), "+r" (limit) : "Ir" (size), "0" (addr) : "cc"); - return addr; + return ret; } /* @@ -104,7 +104,7 @@ static inline unsigned long __range_ok(unsigned long addr, unsigned long size) */ #define untagged_addr(addr) sign_extend64(addr, 55) -#define access_ok(type, addr, size) __range_ok((unsigned long)(addr), size) +#define access_ok(type, addr, size) __range_ok(addr, size) #define user_addr_max get_fs #define _ASM_EXTABLE(from, to) \ diff --git a/arch/arm64/kernel/armv8_deprecated.c b/arch/arm64/kernel/armv8_deprecated.c index c33b5e4010ab..68450e954d47 100644 --- a/arch/arm64/kernel/armv8_deprecated.c +++ b/arch/arm64/kernel/armv8_deprecated.c @@ -370,6 +370,7 @@ static unsigned int __kprobes aarch32_check_condition(u32 opcode, u32 psr) static int swp_handler(struct pt_regs *regs, u32 instr) { u32 destreg, data, type, address = 0; + const void __user *user_ptr; int rn, rt2, res = 0; perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS, 1, regs, regs->pc); @@ -401,7 +402,8 @@ static int swp_handler(struct pt_regs *regs, u32 instr) aarch32_insn_extract_reg_num(instr, A32_RT2_OFFSET), data); /* Check access in reasonable access range for both SWP and SWPB */ - if (!access_ok(VERIFY_WRITE, (address & ~3), 4)) { + user_ptr = (const void __user *)(unsigned long)(address & ~3); + if (!access_ok(VERIFY_WRITE, user_ptr, 4)) { pr_debug("SWP{B} emulation: access to 0x%08x not allowed!\n", address); goto fault; diff --git a/arch/arm64/kernel/sys_compat.c b/arch/arm64/kernel/sys_compat.c index 8b8bbd3eaa52..a382b2a1b84e 100644 --- a/arch/arm64/kernel/sys_compat.c +++ b/arch/arm64/kernel/sys_compat.c @@ -57,7 +57,7 @@ do_compat_cache_op(unsigned long start, unsigned long end, int flags) if (end < start || flags) return -EINVAL; - if (!access_ok(VERIFY_READ, start, end - start)) + if (!access_ok(VERIFY_READ, (const void __user *)start, end - start)) return -EFAULT; return __do_compat_cache_op(start, end); -- cgit v1.2.3-55-g7522 From be68a8aaf925aaf35574260bf820bb09d2f9e07f Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Mon, 19 Feb 2018 14:41:44 +0000 Subject: arm64: cpufeature: Fix CTR_EL0 field definitions Our field definitions for CTR_EL0 suffer from a number of problems: - The IDC and DIC fields are missing, which causes us to enable CTR trapping on CPUs with either of these returning non-zero values. - The ERG is FTR_LOWER_SAFE, whereas it should be treated like CWG as FTR_HIGHER_SAFE so that applications can use it to avoid false sharing. - [nit] A RES1 field is described as "RAO" This patch updates the CTR_EL0 field definitions to fix these issues. Cc: Cc: Shanker Donthineni Signed-off-by: Will Deacon Signed-off-by: Catalin Marinas --- arch/arm64/kernel/cpufeature.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'arch') diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 29b1f873e337..2985a067fc13 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -199,9 +199,11 @@ static const struct arm64_ftr_bits ftr_id_aa64mmfr2[] = { }; static const struct arm64_ftr_bits ftr_ctr[] = { - ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, 31, 1, 1), /* RAO */ + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, 31, 1, 1), /* RES1 */ + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, 29, 1, 1), /* DIC */ + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, 28, 1, 1), /* IDC */ ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_HIGHER_SAFE, 24, 4, 0), /* CWG */ - ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, 20, 4, 0), /* ERG */ + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_HIGHER_SAFE, 20, 4, 0), /* ERG */ ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, 16, 4, 1), /* DminLine */ /* * Linux can handle differing I-cache policies. Userspace JITs will -- cgit v1.2.3-55-g7522 From 5ee39a71fd89ab7240c5339d04161c44a8e03269 Mon Sep 17 00:00:00 2001 From: Michael Weiser Date: Thu, 1 Feb 2018 23:13:38 +0100 Subject: arm64: Disable unhandled signal log messages by default aarch64 unhandled signal kernel messages are very verbose, suggesting them to be more of a debugging aid: sigsegv[33]: unhandled level 2 translation fault (11) at 0x00000000, esr 0x92000046, in sigsegv[400000+71000] CPU: 1 PID: 33 Comm: sigsegv Tainted: G W 4.15.0-rc3+ #3 Hardware name: linux,dummy-virt (DT) pstate: 60000000 (nZCv daif -PAN -UAO) pc : 0x4003f4 lr : 0x4006bc sp : 0000fffffe94a060 x29: 0000fffffe94a070 x28: 0000000000000000 x27: 0000000000000000 x26: 0000000000000000 x25: 0000000000000000 x24: 00000000004001b0 x23: 0000000000486ac8 x22: 00000000004001c8 x21: 0000000000000000 x20: 0000000000400be8 x19: 0000000000400b30 x18: 0000000000484728 x17: 000000000865ffc8 x16: 000000000000270f x15: 00000000000000b0 x14: 0000000000000002 x13: 0000000000000001 x12: 0000000000000000 x11: 0000000000000000 x10: 0008000020008008 x9 : 000000000000000f x8 : ffffffffffffffff x7 : 0004000000000000 x6 : ffffffffffffffff x5 : 0000000000000000 x4 : 0000000000000000 x3 : 00000000004003e4 x2 : 0000fffffe94a1e8 x1 : 000000000000000a x0 : 0000000000000000 Disable them by default, so they can be enabled using /proc/sys/debug/exception-trace. Cc: Signed-off-by: Michael Weiser Signed-off-by: Will Deacon --- arch/arm64/kernel/traps.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c index bbb0fde2780e..c8639f95e59a 100644 --- a/arch/arm64/kernel/traps.c +++ b/arch/arm64/kernel/traps.c @@ -57,7 +57,7 @@ static const char *handler[]= { "Error" }; -int show_unhandled_signals = 1; +int show_unhandled_signals = 0; static void dump_backtrace_entry(unsigned long where) { -- cgit v1.2.3-55-g7522 From 1962682d2b2fbe6cfa995a85c53c069fadda473e Mon Sep 17 00:00:00 2001 From: Michael Weiser Date: Thu, 1 Feb 2018 23:13:36 +0100 Subject: arm64: Remove unimplemented syscall log message Stop printing a (ratelimited) kernel message for each instance of an unimplemented syscall being called. Userland making an unimplemented syscall is not necessarily misbehaviour and to be expected with a current userland running on an older kernel. Also, the current message looks scary to users but does not actually indicate a real problem nor help them narrow down the cause. Just rely on sys_ni_syscall() to return -ENOSYS. Cc: Acked-by: Will Deacon Signed-off-by: Michael Weiser Signed-off-by: Will Deacon --- arch/arm64/kernel/traps.c | 8 -------- 1 file changed, 8 deletions(-) (limited to 'arch') diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c index c8639f95e59a..eb2d15147e8d 100644 --- a/arch/arm64/kernel/traps.c +++ b/arch/arm64/kernel/traps.c @@ -526,14 +526,6 @@ asmlinkage long do_ni_syscall(struct pt_regs *regs) } #endif - if (show_unhandled_signals_ratelimited()) { - pr_info("%s[%d]: syscall %d\n", current->comm, - task_pid_nr(current), regs->syscallno); - dump_instr("", regs); - if (user_mode(regs)) - __show_regs(regs); - } - return sys_ni_syscall(); } -- cgit v1.2.3-55-g7522 From a06f818a70de21b4b3b4186816094208fc7accf9 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Mon, 19 Feb 2018 16:46:57 +0000 Subject: arm64: __show_regs: Only resolve kernel symbols when running at EL1 __show_regs pretty prints PC and LR by attempting to map them to kernel function names to improve the utility of crash reports. Unfortunately, this mapping is applied even when the pt_regs corresponds to user mode, resulting in a KASLR oracle. Avoid this issue by only looking up the function symbols when the register state indicates that we're actually running at EL1. Cc: Reported-by: NCSC Security Signed-off-by: Will Deacon --- arch/arm64/kernel/process.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'arch') diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index ad8aeb098b31..c0da6efe5465 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -220,8 +220,15 @@ void __show_regs(struct pt_regs *regs) show_regs_print_info(KERN_DEFAULT); print_pstate(regs); - printk("pc : %pS\n", (void *)regs->pc); - printk("lr : %pS\n", (void *)lr); + + if (!user_mode(regs)) { + printk("pc : %pS\n", (void *)regs->pc); + printk("lr : %pS\n", (void *)lr); + } else { + printk("pc : %016llx\n", regs->pc); + printk("lr : %016llx\n", lr); + } + printk("sp : %016llx\n", sp); i = top_reg; -- cgit v1.2.3-55-g7522 From 894266466aa74a226e58e23975118ff6231dd2e4 Mon Sep 17 00:00:00 2001 From: KarimAllah Ahmed Date: Tue, 20 Feb 2018 08:39:51 +0100 Subject: x86/headers/UAPI: Use __u64 instead of u64 in ... since u64 has a hidden header dependency that was not there before using it (i.e. it breaks our VMM build). Also, __u64 is the right way to expose data types through UAPI. Signed-off-by: KarimAllah Ahmed Acked-by: Thomas Gleixner Cc: Haiyang Zhang Cc: K. Y. Srinivasan Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Stephen Hemminger Cc: devel@linuxdriverproject.org Fixes: 93286261 ("x86/hyperv: Reenlightenment notifications support") Link: http://lkml.kernel.org/r/1519112391-23773-1-git-send-email-karahmed@amazon.de Signed-off-by: Ingo Molnar --- arch/x86/include/uapi/asm/hyperv.h | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) (limited to 'arch') diff --git a/arch/x86/include/uapi/asm/hyperv.h b/arch/x86/include/uapi/asm/hyperv.h index 197c2e6c7376..099414345865 100644 --- a/arch/x86/include/uapi/asm/hyperv.h +++ b/arch/x86/include/uapi/asm/hyperv.h @@ -241,24 +241,24 @@ #define HV_X64_MSR_REENLIGHTENMENT_CONTROL 0x40000106 struct hv_reenlightenment_control { - u64 vector:8; - u64 reserved1:8; - u64 enabled:1; - u64 reserved2:15; - u64 target_vp:32; + __u64 vector:8; + __u64 reserved1:8; + __u64 enabled:1; + __u64 reserved2:15; + __u64 target_vp:32; }; #define HV_X64_MSR_TSC_EMULATION_CONTROL 0x40000107 #define HV_X64_MSR_TSC_EMULATION_STATUS 0x40000108 struct hv_tsc_emulation_control { - u64 enabled:1; - u64 reserved:63; + __u64 enabled:1; + __u64 reserved:63; }; struct hv_tsc_emulation_status { - u64 inprogress:1; - u64 reserved:63; + __u64 inprogress:1; + __u64 reserved:63; }; #define HV_X64_MSR_HYPERCALL_ENABLE 0x00000001 -- cgit v1.2.3-55-g7522 From 842cef9113c2120f74f645111ded1e020193d84c Mon Sep 17 00:00:00 2001 From: Jan Beulich Date: Mon, 19 Feb 2018 07:48:11 -0700 Subject: x86/mm: Fix {pmd,pud}_{set,clear}_flags() Just like pte_{set,clear}_flags() their PMD and PUD counterparts should not do any address translation. This was outright wrong under Xen (causing a dead boot with no useful output on "suitable" systems), and produced needlessly more complicated code (even if just slightly) when paravirt was enabled. Signed-off-by: Jan Beulich Reviewed-by: Juergen Gross Acked-by: Thomas Gleixner Cc: Andy Lutomirski Cc: Boris Ostrovsky Cc: Borislav Petkov Cc: Brian Gerst Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Josh Poimboeuf Cc: Linus Torvalds Cc: Peter Zijlstra Cc: stable@vger.kernel.org Link: http://lkml.kernel.org/r/5A8AF1BB02000078001A91C3@prv-mh.provo.novell.com Signed-off-by: Ingo Molnar --- arch/x86/include/asm/pgtable.h | 8 ++++---- arch/x86/include/asm/pgtable_types.h | 10 ++++++++++ 2 files changed, 14 insertions(+), 4 deletions(-) (limited to 'arch') diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 63c2552b6b65..b444d83cfc95 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -350,14 +350,14 @@ static inline pmd_t pmd_set_flags(pmd_t pmd, pmdval_t set) { pmdval_t v = native_pmd_val(pmd); - return __pmd(v | set); + return native_make_pmd(v | set); } static inline pmd_t pmd_clear_flags(pmd_t pmd, pmdval_t clear) { pmdval_t v = native_pmd_val(pmd); - return __pmd(v & ~clear); + return native_make_pmd(v & ~clear); } static inline pmd_t pmd_mkold(pmd_t pmd) @@ -409,14 +409,14 @@ static inline pud_t pud_set_flags(pud_t pud, pudval_t set) { pudval_t v = native_pud_val(pud); - return __pud(v | set); + return native_make_pud(v | set); } static inline pud_t pud_clear_flags(pud_t pud, pudval_t clear) { pudval_t v = native_pud_val(pud); - return __pud(v & ~clear); + return native_make_pud(v & ~clear); } static inline pud_t pud_mkold(pud_t pud) diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index 3696398a9475..246f15b4e64c 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -323,6 +323,11 @@ static inline pudval_t native_pud_val(pud_t pud) #else #include +static inline pud_t native_make_pud(pudval_t val) +{ + return (pud_t) { .p4d.pgd = native_make_pgd(val) }; +} + static inline pudval_t native_pud_val(pud_t pud) { return native_pgd_val(pud.p4d.pgd); @@ -344,6 +349,11 @@ static inline pmdval_t native_pmd_val(pmd_t pmd) #else #include +static inline pmd_t native_make_pmd(pmdval_t val) +{ + return (pmd_t) { .pud.p4d.pgd = native_make_pgd(val) }; +} + static inline pmdval_t native_pmd_val(pmd_t pmd) { return native_pgd_val(pmd.pud.p4d.pgd); -- cgit v1.2.3-55-g7522 From 3b3a9268bba62b35a29bafe0931715b1725fdf26 Mon Sep 17 00:00:00 2001 From: Jann Horn Date: Mon, 19 Feb 2018 18:50:39 +0100 Subject: x86/mm: Remove stale comment about KMEMCHECK This comment referred to a conditional call to kmemcheck_hide() that was here until commit 4950276672fc ("kmemcheck: remove annotations"). Now that kmemcheck has been removed, it doesn't make sense anymore. Signed-off-by: Jann Horn Acked-by: Thomas Gleixner Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Josh Poimboeuf Cc: Linus Torvalds Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/20180219175039.253089-1-jannh@google.com Signed-off-by: Ingo Molnar --- arch/x86/mm/fault.c | 4 ---- 1 file changed, 4 deletions(-) (limited to 'arch') diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 800de815519c..c88573d90f3e 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -1248,10 +1248,6 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code, tsk = current; mm = tsk->mm; - /* - * Detect and handle instructions that would cause a page fault for - * both a tracked kernel page and a userspace page. - */ prefetchw(&mm->mmap_sem); if (unlikely(kmmio_fault(regs, address))) -- cgit v1.2.3-55-g7522 From 700b7c5409c3e9da279fbea78cf28a78fbc176cd Mon Sep 17 00:00:00 2001 From: Jan Beulich Date: Mon, 19 Feb 2018 07:49:12 -0700 Subject: x86/asm: Improve how GEN_*_SUFFIXED_RMWcc() specify clobbers Commit: df3405245a ("x86/asm: Add suffix macro for GEN_*_RMWcc()") ... introduced "suffix" RMWcc operations, adding bogus clobber specifiers: For one, on x86 there's no point explicitly clobbering "cc". In fact, with GCC properly fixed, this results in an overlap being detected by the compiler between outputs and clobbers. Furthermore it seems bad practice to me to have clobber specification and use of the clobbered register(s) disconnected - it should rather be at the invocation place of that GEN_{UN,BIN}ARY_SUFFIXED_RMWcc() macros that the clobber is specified which this particular invocation needs. Drop the "cc" clobber altogether and move the "cx" one to refcount.h. Signed-off-by: Jan Beulich Acked-by: Thomas Gleixner Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Josh Poimboeuf Cc: Kees Cook Cc: Linus Torvalds Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/5A8AF1F802000078001A91E1@prv-mh.provo.novell.com Signed-off-by: Ingo Molnar --- arch/x86/include/asm/refcount.h | 4 ++-- arch/x86/include/asm/rmwcc.h | 16 ++++++++-------- 2 files changed, 10 insertions(+), 10 deletions(-) (limited to 'arch') diff --git a/arch/x86/include/asm/refcount.h b/arch/x86/include/asm/refcount.h index 4e44250e7d0d..d65171120e90 100644 --- a/arch/x86/include/asm/refcount.h +++ b/arch/x86/include/asm/refcount.h @@ -67,13 +67,13 @@ static __always_inline __must_check bool refcount_sub_and_test(unsigned int i, refcount_t *r) { GEN_BINARY_SUFFIXED_RMWcc(LOCK_PREFIX "subl", REFCOUNT_CHECK_LT_ZERO, - r->refs.counter, "er", i, "%0", e); + r->refs.counter, "er", i, "%0", e, "cx"); } static __always_inline __must_check bool refcount_dec_and_test(refcount_t *r) { GEN_UNARY_SUFFIXED_RMWcc(LOCK_PREFIX "decl", REFCOUNT_CHECK_LT_ZERO, - r->refs.counter, "%0", e); + r->refs.counter, "%0", e, "cx"); } static __always_inline __must_check diff --git a/arch/x86/include/asm/rmwcc.h b/arch/x86/include/asm/rmwcc.h index f91c365e57c3..4914a3e7c803 100644 --- a/arch/x86/include/asm/rmwcc.h +++ b/arch/x86/include/asm/rmwcc.h @@ -2,8 +2,7 @@ #ifndef _ASM_X86_RMWcc #define _ASM_X86_RMWcc -#define __CLOBBERS_MEM "memory" -#define __CLOBBERS_MEM_CC_CX "memory", "cc", "cx" +#define __CLOBBERS_MEM(clb...) "memory", ## clb #if !defined(__GCC_ASM_FLAG_OUTPUTS__) && defined(CC_HAVE_ASM_GOTO) @@ -40,18 +39,19 @@ do { \ #endif /* defined(__GCC_ASM_FLAG_OUTPUTS__) || !defined(CC_HAVE_ASM_GOTO) */ #define GEN_UNARY_RMWcc(op, var, arg0, cc) \ - __GEN_RMWcc(op " " arg0, var, cc, __CLOBBERS_MEM) + __GEN_RMWcc(op " " arg0, var, cc, __CLOBBERS_MEM()) -#define GEN_UNARY_SUFFIXED_RMWcc(op, suffix, var, arg0, cc) \ +#define GEN_UNARY_SUFFIXED_RMWcc(op, suffix, var, arg0, cc, clobbers...)\ __GEN_RMWcc(op " " arg0 "\n\t" suffix, var, cc, \ - __CLOBBERS_MEM_CC_CX) + __CLOBBERS_MEM(clobbers)) #define GEN_BINARY_RMWcc(op, var, vcon, val, arg0, cc) \ __GEN_RMWcc(op __BINARY_RMWcc_ARG arg0, var, cc, \ - __CLOBBERS_MEM, vcon (val)) + __CLOBBERS_MEM(), vcon (val)) -#define GEN_BINARY_SUFFIXED_RMWcc(op, suffix, var, vcon, val, arg0, cc) \ +#define GEN_BINARY_SUFFIXED_RMWcc(op, suffix, var, vcon, val, arg0, cc, \ + clobbers...) \ __GEN_RMWcc(op __BINARY_RMWcc_ARG arg0 "\n\t" suffix, var, cc, \ - __CLOBBERS_MEM_CC_CX, vcon (val)) + __CLOBBERS_MEM(clobbers), vcon (val)) #endif /* _ASM_X86_RMWcc */ -- cgit v1.2.3-55-g7522 From 6262b6e78ce5ba62be47774ca80f5b0a6f0eb428 Mon Sep 17 00:00:00 2001 From: Jan Beulich Date: Mon, 19 Feb 2018 07:50:23 -0700 Subject: x86/IO-APIC: Avoid warning in 32-bit builds Constants wider than 32 bits should be tagged with ULL. Signed-off-by: Jan Beulich Acked-by: Thomas Gleixner Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Josh Poimboeuf Cc: Linus Torvalds Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/5A8AF23F02000078001A91E5@prv-mh.provo.novell.com Signed-off-by: Ingo Molnar --- arch/x86/kernel/apic/io_apic.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 8ad2e410974f..7c5538769f7e 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -1603,7 +1603,7 @@ static void __init delay_with_tsc(void) do { rep_nop(); now = rdtsc(); - } while ((now - start) < 40000000000UL / HZ && + } while ((now - start) < 40000000000ULL / HZ && time_before_eq(jiffies, end)); } -- cgit v1.2.3-55-g7522 From f2f18b16c779978ece4a04f304a92ff9ac8fbce5 Mon Sep 17 00:00:00 2001 From: Jan Beulich Date: Mon, 19 Feb 2018 07:52:10 -0700 Subject: x86/LDT: Avoid warning in 32-bit builds with older gcc BUG() doesn't always imply "no return", and hence should be followed by a return statement even if that's obviously (to a human) unreachable. Signed-off-by: Jan Beulich Acked-by: Thomas Gleixner Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Josh Poimboeuf Cc: Linus Torvalds Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/5A8AF2AA02000078001A91E9@prv-mh.provo.novell.com Signed-off-by: Ingo Molnar --- arch/x86/include/asm/mmu_context.h | 1 + 1 file changed, 1 insertion(+) (limited to 'arch') diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h index c931b88982a0..1de72ce514cd 100644 --- a/arch/x86/include/asm/mmu_context.h +++ b/arch/x86/include/asm/mmu_context.h @@ -74,6 +74,7 @@ static inline void *ldt_slot_va(int slot) return (void *)(LDT_BASE_ADDR + LDT_SLOT_STRIDE * slot); #else BUG(); + return (void *)fix_to_virt(FIX_HOLE); #endif } -- cgit v1.2.3-55-g7522 From 8554004a0231dedf44d4d62147fb3d6a6db489aa Mon Sep 17 00:00:00 2001 From: Jan Beulich Date: Mon, 19 Feb 2018 08:06:14 -0700 Subject: x86-64/realmode: Add instruction suffix Omitting suffixes from instructions in AT&T mode is bad practice when operand size cannot be determined by the assembler from register operands, and is likely going to be warned about by upstream GAS in the future (mine does already). Add the single missing suffix here. Signed-off-by: Jan Beulich Acked-by: Thomas Gleixner Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Josh Poimboeuf Cc: Linus Torvalds Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/5A8AF5F602000078001A9230@prv-mh.provo.novell.com Signed-off-by: Ingo Molnar --- arch/x86/realmode/rm/trampoline_64.S | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/x86/realmode/rm/trampoline_64.S b/arch/x86/realmode/rm/trampoline_64.S index de53bd15df5a..24bb7598774e 100644 --- a/arch/x86/realmode/rm/trampoline_64.S +++ b/arch/x86/realmode/rm/trampoline_64.S @@ -102,7 +102,7 @@ ENTRY(startup_32) * don't we'll eventually crash trying to execute encrypted * instructions. */ - bt $TH_FLAGS_SME_ACTIVE_BIT, pa_tr_flags + btl $TH_FLAGS_SME_ACTIVE_BIT, pa_tr_flags jnc .Ldone movl $MSR_K8_SYSCFG, %ecx rdmsr -- cgit v1.2.3-55-g7522 From d1c99108af3c5992640aa2afa7d2e88c3775c06e Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Mon, 19 Feb 2018 10:50:56 +0000 Subject: Revert "x86/retpoline: Simplify vmexit_fill_RSB()" This reverts commit 1dde7415e99933bb7293d6b2843752cbdb43ec11. By putting the RSB filling out of line and calling it, we waste one RSB slot for returning from the function itself, which means one fewer actual function call we can make if we're doing the Skylake abomination of call-depth counting. It also changed the number of RSB stuffings we do on vmexit from 32, which was correct, to 16. Let's just stop with the bikeshedding; it didn't actually *fix* anything anyway. Signed-off-by: David Woodhouse Acked-by: Thomas Gleixner Cc: Linus Torvalds Cc: Peter Zijlstra Cc: arjan.van.de.ven@intel.com Cc: bp@alien8.de Cc: dave.hansen@intel.com Cc: jmattson@google.com Cc: karahmed@amazon.de Cc: kvm@vger.kernel.org Cc: pbonzini@redhat.com Cc: rkrcmar@redhat.com Link: http://lkml.kernel.org/r/1519037457-7643-4-git-send-email-dwmw@amazon.co.uk Signed-off-by: Ingo Molnar --- arch/x86/entry/entry_32.S | 3 +- arch/x86/entry/entry_64.S | 3 +- arch/x86/include/asm/asm-prototypes.h | 3 -- arch/x86/include/asm/nospec-branch.h | 70 +++++++++++++++++++++++++++++++---- arch/x86/lib/Makefile | 1 - arch/x86/lib/retpoline.S | 56 ---------------------------- 6 files changed, 65 insertions(+), 71 deletions(-) (limited to 'arch') diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index 16c2c022540d..6ad064c8cf35 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -252,8 +252,7 @@ ENTRY(__switch_to_asm) * exist, overwrite the RSB with entries which capture * speculative execution to prevent attack. */ - /* Clobbers %ebx */ - FILL_RETURN_BUFFER RSB_CLEAR_LOOPS, X86_FEATURE_RSB_CTXSW + FILL_RETURN_BUFFER %ebx, RSB_CLEAR_LOOPS, X86_FEATURE_RSB_CTXSW #endif /* restore callee-saved registers */ diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 77edc2390868..7a53879ec689 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -364,8 +364,7 @@ ENTRY(__switch_to_asm) * exist, overwrite the RSB with entries which capture * speculative execution to prevent attack. */ - /* Clobbers %rbx */ - FILL_RETURN_BUFFER RSB_CLEAR_LOOPS, X86_FEATURE_RSB_CTXSW + FILL_RETURN_BUFFER %r12, RSB_CLEAR_LOOPS, X86_FEATURE_RSB_CTXSW #endif /* restore callee-saved registers */ diff --git a/arch/x86/include/asm/asm-prototypes.h b/arch/x86/include/asm/asm-prototypes.h index 4d111616524b..1908214b9125 100644 --- a/arch/x86/include/asm/asm-prototypes.h +++ b/arch/x86/include/asm/asm-prototypes.h @@ -38,7 +38,4 @@ INDIRECT_THUNK(dx) INDIRECT_THUNK(si) INDIRECT_THUNK(di) INDIRECT_THUNK(bp) -asmlinkage void __fill_rsb(void); -asmlinkage void __clear_rsb(void); - #endif /* CONFIG_RETPOLINE */ diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index 76b058533e47..af34b1e8069a 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -8,6 +8,50 @@ #include #include +/* + * Fill the CPU return stack buffer. + * + * Each entry in the RSB, if used for a speculative 'ret', contains an + * infinite 'pause; lfence; jmp' loop to capture speculative execution. + * + * This is required in various cases for retpoline and IBRS-based + * mitigations for the Spectre variant 2 vulnerability. Sometimes to + * eliminate potentially bogus entries from the RSB, and sometimes + * purely to ensure that it doesn't get empty, which on some CPUs would + * allow predictions from other (unwanted!) sources to be used. + * + * We define a CPP macro such that it can be used from both .S files and + * inline assembly. It's possible to do a .macro and then include that + * from C via asm(".include ") but let's not go there. + */ + +#define RSB_CLEAR_LOOPS 32 /* To forcibly overwrite all entries */ +#define RSB_FILL_LOOPS 16 /* To avoid underflow */ + +/* + * Google experimented with loop-unrolling and this turned out to be + * the optimal version — two calls, each with their own speculation + * trap should their return address end up getting used, in a loop. + */ +#define __FILL_RETURN_BUFFER(reg, nr, sp) \ + mov $(nr/2), reg; \ +771: \ + call 772f; \ +773: /* speculation trap */ \ + pause; \ + lfence; \ + jmp 773b; \ +772: \ + call 774f; \ +775: /* speculation trap */ \ + pause; \ + lfence; \ + jmp 775b; \ +774: \ + dec reg; \ + jnz 771b; \ + add $(BITS_PER_LONG/8) * nr, sp; + #ifdef __ASSEMBLY__ /* @@ -78,10 +122,17 @@ #endif .endm -/* This clobbers the BX register */ -.macro FILL_RETURN_BUFFER nr:req ftr:req + /* + * A simpler FILL_RETURN_BUFFER macro. Don't make people use the CPP + * monstrosity above, manually. + */ +.macro FILL_RETURN_BUFFER reg:req nr:req ftr:req #ifdef CONFIG_RETPOLINE - ALTERNATIVE "", "call __clear_rsb", \ftr + ANNOTATE_NOSPEC_ALTERNATIVE + ALTERNATIVE "jmp .Lskip_rsb_\@", \ + __stringify(__FILL_RETURN_BUFFER(\reg,\nr,%_ASM_SP)) \ + \ftr +.Lskip_rsb_\@: #endif .endm @@ -156,10 +207,15 @@ extern char __indirect_thunk_end[]; static inline void vmexit_fill_RSB(void) { #ifdef CONFIG_RETPOLINE - alternative_input("", - "call __fill_rsb", - X86_FEATURE_RETPOLINE, - ASM_NO_INPUT_CLOBBER(_ASM_BX, "memory")); + unsigned long loops; + + asm volatile (ANNOTATE_NOSPEC_ALTERNATIVE + ALTERNATIVE("jmp 910f", + __stringify(__FILL_RETURN_BUFFER(%0, RSB_CLEAR_LOOPS, %1)), + X86_FEATURE_RETPOLINE) + "910:" + : "=r" (loops), ASM_CALL_CONSTRAINT + : : "memory" ); #endif } diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile index 91e9700cc6dc..25a972c61b0a 100644 --- a/arch/x86/lib/Makefile +++ b/arch/x86/lib/Makefile @@ -28,7 +28,6 @@ lib-$(CONFIG_INSTRUCTION_DECODER) += insn.o inat.o insn-eval.o lib-$(CONFIG_RANDOMIZE_BASE) += kaslr.o lib-$(CONFIG_FUNCTION_ERROR_INJECTION) += error-inject.o lib-$(CONFIG_RETPOLINE) += retpoline.o -OBJECT_FILES_NON_STANDARD_retpoline.o :=y obj-y += msr.o msr-reg.o msr-reg-export.o hweight.o diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S index 480edc3a5e03..c909961e678a 100644 --- a/arch/x86/lib/retpoline.S +++ b/arch/x86/lib/retpoline.S @@ -7,7 +7,6 @@ #include #include #include -#include .macro THUNK reg .section .text.__x86.indirect_thunk @@ -47,58 +46,3 @@ GENERATE_THUNK(r13) GENERATE_THUNK(r14) GENERATE_THUNK(r15) #endif - -/* - * Fill the CPU return stack buffer. - * - * Each entry in the RSB, if used for a speculative 'ret', contains an - * infinite 'pause; lfence; jmp' loop to capture speculative execution. - * - * This is required in various cases for retpoline and IBRS-based - * mitigations for the Spectre variant 2 vulnerability. Sometimes to - * eliminate potentially bogus entries from the RSB, and sometimes - * purely to ensure that it doesn't get empty, which on some CPUs would - * allow predictions from other (unwanted!) sources to be used. - * - * Google experimented with loop-unrolling and this turned out to be - * the optimal version - two calls, each with their own speculation - * trap should their return address end up getting used, in a loop. - */ -.macro STUFF_RSB nr:req sp:req - mov $(\nr / 2), %_ASM_BX - .align 16 -771: - call 772f -773: /* speculation trap */ - pause - lfence - jmp 773b - .align 16 -772: - call 774f -775: /* speculation trap */ - pause - lfence - jmp 775b - .align 16 -774: - dec %_ASM_BX - jnz 771b - add $((BITS_PER_LONG/8) * \nr), \sp -.endm - -#define RSB_FILL_LOOPS 16 /* To avoid underflow */ - -ENTRY(__fill_rsb) - STUFF_RSB RSB_FILL_LOOPS, %_ASM_SP - ret -END(__fill_rsb) -EXPORT_SYMBOL_GPL(__fill_rsb) - -#define RSB_CLEAR_LOOPS 32 /* To forcibly overwrite all entries */ - -ENTRY(__clear_rsb) - STUFF_RSB RSB_CLEAR_LOOPS, %_ASM_SP - ret -END(__clear_rsb) -EXPORT_SYMBOL_GPL(__clear_rsb) -- cgit v1.2.3-55-g7522 From dd84441a797150dcc49298ec95c459a8891d8bb1 Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Mon, 19 Feb 2018 10:50:54 +0000 Subject: x86/speculation: Use IBRS if available before calling into firmware Retpoline means the kernel is safe because it has no indirect branches. But firmware isn't, so use IBRS for firmware calls if it's available. Block preemption while IBRS is set, although in practice the call sites already had to be doing that. Ignore hpwdt.c for now. It's taking spinlocks and calling into firmware code, from an NMI handler. I don't want to touch that with a bargepole. Signed-off-by: David Woodhouse Reviewed-by: Thomas Gleixner Cc: Linus Torvalds Cc: Peter Zijlstra Cc: arjan.van.de.ven@intel.com Cc: bp@alien8.de Cc: dave.hansen@intel.com Cc: jmattson@google.com Cc: karahmed@amazon.de Cc: kvm@vger.kernel.org Cc: pbonzini@redhat.com Cc: rkrcmar@redhat.com Link: http://lkml.kernel.org/r/1519037457-7643-2-git-send-email-dwmw@amazon.co.uk Signed-off-by: Ingo Molnar --- arch/x86/include/asm/apm.h | 6 ++++++ arch/x86/include/asm/cpufeatures.h | 1 + arch/x86/include/asm/efi.h | 17 ++++++++++++++-- arch/x86/include/asm/nospec-branch.h | 39 +++++++++++++++++++++++++++--------- arch/x86/kernel/cpu/bugs.c | 12 ++++++++++- 5 files changed, 63 insertions(+), 12 deletions(-) (limited to 'arch') diff --git a/arch/x86/include/asm/apm.h b/arch/x86/include/asm/apm.h index 4d4015ddcf26..c356098b6fb9 100644 --- a/arch/x86/include/asm/apm.h +++ b/arch/x86/include/asm/apm.h @@ -7,6 +7,8 @@ #ifndef _ASM_X86_MACH_DEFAULT_APM_H #define _ASM_X86_MACH_DEFAULT_APM_H +#include + #ifdef APM_ZERO_SEGS # define APM_DO_ZERO_SEGS \ "pushl %%ds\n\t" \ @@ -32,6 +34,7 @@ static inline void apm_bios_call_asm(u32 func, u32 ebx_in, u32 ecx_in, * N.B. We do NOT need a cld after the BIOS call * because we always save and restore the flags. */ + firmware_restrict_branch_speculation_start(); __asm__ __volatile__(APM_DO_ZERO_SEGS "pushl %%edi\n\t" "pushl %%ebp\n\t" @@ -44,6 +47,7 @@ static inline void apm_bios_call_asm(u32 func, u32 ebx_in, u32 ecx_in, "=S" (*esi) : "a" (func), "b" (ebx_in), "c" (ecx_in) : "memory", "cc"); + firmware_restrict_branch_speculation_end(); } static inline bool apm_bios_call_simple_asm(u32 func, u32 ebx_in, @@ -56,6 +60,7 @@ static inline bool apm_bios_call_simple_asm(u32 func, u32 ebx_in, * N.B. We do NOT need a cld after the BIOS call * because we always save and restore the flags. */ + firmware_restrict_branch_speculation_start(); __asm__ __volatile__(APM_DO_ZERO_SEGS "pushl %%edi\n\t" "pushl %%ebp\n\t" @@ -68,6 +73,7 @@ static inline bool apm_bios_call_simple_asm(u32 func, u32 ebx_in, "=S" (si) : "a" (func), "b" (ebx_in), "c" (ecx_in) : "memory", "cc"); + firmware_restrict_branch_speculation_end(); return error; } diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 0dfe4d3f74e2..f41079da38c5 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -213,6 +213,7 @@ #define X86_FEATURE_SEV ( 7*32+20) /* AMD Secure Encrypted Virtualization */ #define X86_FEATURE_USE_IBPB ( 7*32+21) /* "" Indirect Branch Prediction Barrier enabled */ +#define X86_FEATURE_USE_IBRS_FW ( 7*32+22) /* "" Use IBRS during runtime firmware calls */ /* Virtualization flags: Linux defined, word 8 */ #define X86_FEATURE_TPR_SHADOW ( 8*32+ 0) /* Intel TPR Shadow */ diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index 85f6ccb80b91..a399c1ebf6f0 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -6,6 +6,7 @@ #include #include #include +#include /* * We map the EFI regions needed for runtime services non-contiguously, @@ -36,8 +37,18 @@ extern asmlinkage unsigned long efi_call_phys(void *, ...); -#define arch_efi_call_virt_setup() kernel_fpu_begin() -#define arch_efi_call_virt_teardown() kernel_fpu_end() +#define arch_efi_call_virt_setup() \ +({ \ + kernel_fpu_begin(); \ + firmware_restrict_branch_speculation_start(); \ +}) + +#define arch_efi_call_virt_teardown() \ +({ \ + firmware_restrict_branch_speculation_end(); \ + kernel_fpu_end(); \ +}) + /* * Wrap all the virtual calls in a way that forces the parameters on the stack. @@ -73,6 +84,7 @@ struct efi_scratch { efi_sync_low_kernel_mappings(); \ preempt_disable(); \ __kernel_fpu_begin(); \ + firmware_restrict_branch_speculation_start(); \ \ if (efi_scratch.use_pgd) { \ efi_scratch.prev_cr3 = __read_cr3(); \ @@ -91,6 +103,7 @@ struct efi_scratch { __flush_tlb_all(); \ } \ \ + firmware_restrict_branch_speculation_end(); \ __kernel_fpu_end(); \ preempt_enable(); \ }) diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index af34b1e8069a..ec90c3228991 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -219,17 +219,38 @@ static inline void vmexit_fill_RSB(void) #endif } +#define alternative_msr_write(_msr, _val, _feature) \ + asm volatile(ALTERNATIVE("", \ + "movl %[msr], %%ecx\n\t" \ + "movl %[val], %%eax\n\t" \ + "movl $0, %%edx\n\t" \ + "wrmsr", \ + _feature) \ + : : [msr] "i" (_msr), [val] "i" (_val) \ + : "eax", "ecx", "edx", "memory") + static inline void indirect_branch_prediction_barrier(void) { - asm volatile(ALTERNATIVE("", - "movl %[msr], %%ecx\n\t" - "movl %[val], %%eax\n\t" - "movl $0, %%edx\n\t" - "wrmsr", - X86_FEATURE_USE_IBPB) - : : [msr] "i" (MSR_IA32_PRED_CMD), - [val] "i" (PRED_CMD_IBPB) - : "eax", "ecx", "edx", "memory"); + alternative_msr_write(MSR_IA32_PRED_CMD, PRED_CMD_IBPB, + X86_FEATURE_USE_IBPB); +} + +/* + * With retpoline, we must use IBRS to restrict branch prediction + * before calling into firmware. + */ +static inline void firmware_restrict_branch_speculation_start(void) +{ + preempt_disable(); + alternative_msr_write(MSR_IA32_SPEC_CTRL, SPEC_CTRL_IBRS, + X86_FEATURE_USE_IBRS_FW); +} + +static inline void firmware_restrict_branch_speculation_end(void) +{ + alternative_msr_write(MSR_IA32_SPEC_CTRL, 0, + X86_FEATURE_USE_IBRS_FW); + preempt_enable(); } #endif /* __ASSEMBLY__ */ diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index d71c8b54b696..bfca937bdcc3 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -300,6 +300,15 @@ retpoline_auto: setup_force_cpu_cap(X86_FEATURE_USE_IBPB); pr_info("Spectre v2 mitigation: Enabling Indirect Branch Prediction Barrier\n"); } + + /* + * Retpoline means the kernel is safe because it has no indirect + * branches. But firmware isn't, so use IBRS to protect that. + */ + if (boot_cpu_has(X86_FEATURE_IBRS)) { + setup_force_cpu_cap(X86_FEATURE_USE_IBRS_FW); + pr_info("Enabling Restricted Speculation for firmware calls\n"); + } } #undef pr_fmt @@ -326,8 +335,9 @@ ssize_t cpu_show_spectre_v2(struct device *dev, struct device_attribute *attr, c if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2)) return sprintf(buf, "Not affected\n"); - return sprintf(buf, "%s%s%s\n", spectre_v2_strings[spectre_v2_enabled], + return sprintf(buf, "%s%s%s%s\n", spectre_v2_strings[spectre_v2_enabled], boot_cpu_has(X86_FEATURE_USE_IBPB) ? ", IBPB" : "", + boot_cpu_has(X86_FEATURE_USE_IBRS_FW) ? ", IBRS_FW" : "", spectre_v2_module_string()); } #endif -- cgit v1.2.3-55-g7522 From 87358710c1fb4f1bf96bbe2349975ff9953fc9b2 Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Mon, 19 Feb 2018 10:50:57 +0000 Subject: x86/retpoline: Support retpoline builds with Clang Signed-off-by: David Woodhouse Reviewed-by: Thomas Gleixner Cc: Linus Torvalds Cc: Peter Zijlstra Cc: arjan.van.de.ven@intel.com Cc: bp@alien8.de Cc: dave.hansen@intel.com Cc: jmattson@google.com Cc: karahmed@amazon.de Cc: kvm@vger.kernel.org Cc: pbonzini@redhat.com Cc: rkrcmar@redhat.com Link: http://lkml.kernel.org/r/1519037457-7643-5-git-send-email-dwmw@amazon.co.uk Signed-off-by: Ingo Molnar --- arch/x86/Makefile | 5 ++++- include/linux/compiler-clang.h | 5 +++++ include/linux/compiler-gcc.h | 4 ++++ include/linux/init.h | 8 ++++---- 4 files changed, 17 insertions(+), 5 deletions(-) (limited to 'arch') diff --git a/arch/x86/Makefile b/arch/x86/Makefile index fad55160dcb9..dbc7d0ed2eaa 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -232,7 +232,10 @@ KBUILD_CFLAGS += -fno-asynchronous-unwind-tables # Avoid indirect branches in kernel to deal with Spectre ifdef CONFIG_RETPOLINE - RETPOLINE_CFLAGS += $(call cc-option,-mindirect-branch=thunk-extern -mindirect-branch-register) + RETPOLINE_CFLAGS_GCC := -mindirect-branch=thunk-extern -mindirect-branch-register + RETPOLINE_CFLAGS_CLANG := -mretpoline-external-thunk + + RETPOLINE_CFLAGS += $(call cc-option,$(RETPOLINE_CFLAGS_GCC),$(call cc-option,$(RETPOLINE_CFLAGS_CLANG))) ifneq ($(RETPOLINE_CFLAGS),) KBUILD_CFLAGS += $(RETPOLINE_CFLAGS) -DRETPOLINE endif diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h index d02a4df3f473..d3f264a5b04d 100644 --- a/include/linux/compiler-clang.h +++ b/include/linux/compiler-clang.h @@ -27,3 +27,8 @@ #if __has_feature(address_sanitizer) #define __SANITIZE_ADDRESS__ #endif + +/* Clang doesn't have a way to turn it off per-function, yet. */ +#ifdef __noretpoline +#undef __noretpoline +#endif diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index 73bc63e0a1c4..673fbf904fe5 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -93,6 +93,10 @@ #define __weak __attribute__((weak)) #define __alias(symbol) __attribute__((alias(#symbol))) +#ifdef RETPOLINE +#define __noretpoline __attribute__((indirect_branch("keep"))) +#endif + /* * it doesn't make sense on ARM (currently the only user of __naked) * to trace naked functions because then mcount is called without diff --git a/include/linux/init.h b/include/linux/init.h index 506a98151131..bc27cf03c41e 100644 --- a/include/linux/init.h +++ b/include/linux/init.h @@ -6,10 +6,10 @@ #include /* Built-in __init functions needn't be compiled with retpoline */ -#if defined(RETPOLINE) && !defined(MODULE) -#define __noretpoline __attribute__((indirect_branch("keep"))) +#if defined(__noretpoline) && !defined(MODULE) +#define __noinitretpoline __noretpoline #else -#define __noretpoline +#define __noinitretpoline #endif /* These macros are used to mark some functions or @@ -47,7 +47,7 @@ /* These are for everybody (although not all archs will actually discard it in modules) */ -#define __init __section(.init.text) __cold __latent_entropy __noretpoline +#define __init __section(.init.text) __cold __latent_entropy __noinitretpoline #define __initdata __section(.init.data) #define __initconst __section(.init.rodata) #define __exitdata __section(.exit.data) -- cgit v1.2.3-55-g7522 From 2b05f6ae1ee5a3c625478acd10b0966b66a3a017 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Mon, 5 Feb 2018 16:41:55 +0000 Subject: ARM: ux500: remove PMU IRQ bouncer The ux500 PMU IRQ bouncer is getting in the way of some fundametnal changes to the ARM PMU driver, and it's the only special case that exists today. Let's remove it. Reviewed-by: Linus Walleij Signed-off-by: Mark Rutland Signed-off-by: Will Deacon --- arch/arm/mach-ux500/cpu-db8500.c | 35 ----------------------------------- 1 file changed, 35 deletions(-) (limited to 'arch') diff --git a/arch/arm/mach-ux500/cpu-db8500.c b/arch/arm/mach-ux500/cpu-db8500.c index 57058ac46f49..7e5d7a083707 100644 --- a/arch/arm/mach-ux500/cpu-db8500.c +++ b/arch/arm/mach-ux500/cpu-db8500.c @@ -23,7 +23,6 @@ #include #include #include -#include #include #include @@ -112,37 +111,6 @@ static void ux500_restart(enum reboot_mode mode, const char *cmd) prcmu_system_reset(0); } -/* - * The PMU IRQ lines of two cores are wired together into a single interrupt. - * Bounce the interrupt to the other core if it's not ours. - */ -static irqreturn_t db8500_pmu_handler(int irq, void *dev, irq_handler_t handler) -{ - irqreturn_t ret = handler(irq, dev); - int other = !smp_processor_id(); - - if (ret == IRQ_NONE && cpu_online(other)) - irq_set_affinity(irq, cpumask_of(other)); - - /* - * We should be able to get away with the amount of IRQ_NONEs we give, - * while still having the spurious IRQ detection code kick in if the - * interrupt really starts hitting spuriously. - */ - return ret; -} - -static struct arm_pmu_platdata db8500_pmu_platdata = { - .handle_irq = db8500_pmu_handler, - .irq_flags = IRQF_NOBALANCING | IRQF_NO_THREAD, -}; - -static struct of_dev_auxdata u8500_auxdata_lookup[] __initdata = { - /* Requires call-back bindings. */ - OF_DEV_AUXDATA("arm,cortex-a9-pmu", 0, "arm-pmu", &db8500_pmu_platdata), - {}, -}; - static struct of_dev_auxdata u8540_auxdata_lookup[] __initdata = { OF_DEV_AUXDATA("stericsson,db8500-prcmu", 0x80157000, "db8500-prcmu", NULL), {}, @@ -165,9 +133,6 @@ static void __init u8500_init_machine(void) if (of_machine_is_compatible("st-ericsson,u8540")) of_platform_populate(NULL, u8500_local_bus_nodes, u8540_auxdata_lookup, NULL); - else - of_platform_populate(NULL, u8500_local_bus_nodes, - u8500_auxdata_lookup, NULL); } static const char * stericsson_dt_platform_compat[] = { -- cgit v1.2.3-55-g7522 From 0331365edb1d6ccd6ae68b1038111da85d4c68d1 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Wed, 14 Feb 2018 17:21:57 +0000 Subject: arm64: perf: correct PMUVer probing The ID_AA64DFR0_EL1.PMUVer field doesn't follow the usual ID registers scheme. While value 0xf indicates a non-architected PMU is implemented, values 0x1 to 0xe indicate an increasingly featureful architected PMU, as if the field were unsigned. For more details, see ARM DDI 0487C.a, D10.1.4, "Alternative ID scheme used for the Performance Monitors Extension version". Currently, we treat the field as signed, and erroneously bail out for values 0x8 to 0xe. Let's correct that. Signed-off-by: Mark Rutland Reviewed-by: Robin Murphy Cc: Will Deacon Signed-off-by: Will Deacon --- arch/arm64/kernel/perf_event.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch') diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c index 75b220ba73a3..85a251b6dfa8 100644 --- a/arch/arm64/kernel/perf_event.c +++ b/arch/arm64/kernel/perf_event.c @@ -908,9 +908,9 @@ static void __armv8pmu_probe_pmu(void *info) int pmuver; dfr0 = read_sysreg(id_aa64dfr0_el1); - pmuver = cpuid_feature_extract_signed_field(dfr0, + pmuver = cpuid_feature_extract_unsigned_field(dfr0, ID_AA64DFR0_PMUVER_SHIFT); - if (pmuver < 1) + if (pmuver == 0xf || pmuver == 0) return; probe->present = true; -- cgit v1.2.3-55-g7522 From 6ae1756faddefd7494353380ee546dd38c2f97eb Mon Sep 17 00:00:00 2001 From: James Hogan Date: Tue, 20 Feb 2018 15:44:37 +0000 Subject: MIPS: Drop spurious __unused in struct compat_flock MIPS' struct compat_flock doesn't match the 32-bit struct flock, as it has an extra short __unused before pad[4], which combined with alignment increases the size to 40 bytes compared with struct flock's 36 bytes. Since commit 8c6657cb50cb ("Switch flock copyin/copyout primitives to copy_{from,to}_user()"), put_compat_flock() writes the full compat_flock struct to userland, which results in corruption of the userland word after the struct flock when running 32-bit userlands on 64-bit kernels. This was observed to cause a bus error exception when starting Firefox on Debian 8 (Jessie). Reported-by: Peter Mamonov Signed-off-by: James Hogan Tested-by: Peter Mamonov Cc: Ralf Baechle Cc: Al Viro Cc: linux-mips@linux-mips.org Cc: # 4.13+ Patchwork: https://patchwork.linux-mips.org/patch/18646/ --- arch/mips/include/asm/compat.h | 1 - 1 file changed, 1 deletion(-) (limited to 'arch') diff --git a/arch/mips/include/asm/compat.h b/arch/mips/include/asm/compat.h index 946681db8dc3..9a0fa66b81ac 100644 --- a/arch/mips/include/asm/compat.h +++ b/arch/mips/include/asm/compat.h @@ -86,7 +86,6 @@ struct compat_flock { compat_off_t l_len; s32 l_sysid; compat_pid_t l_pid; - short __unused; s32 pad[4]; }; -- cgit v1.2.3-55-g7522 From ab0dc41b7324329af1c18580b0fc891922a717cf Mon Sep 17 00:00:00 2001 From: Ulf Magnusson Date: Mon, 5 Feb 2018 02:21:19 +0100 Subject: riscv: Remove ARCH_WANT_OPTIONAL_GPIOLIB select The ARCH_WANT_OPTIONAL_GPIOLIB symbol was removed in commit 65053e1a7743 ("gpio: delete ARCH_[WANTS_OPTIONAL|REQUIRE]_GPIOLIB"). GPIOLIB should just be selected explicitly if needed. Remove the ARCH_WANT_OPTIONAL_GPIOLIB select from RISCV. See commit 0145071b3314 ("x86: Do away with ARCH_[WANT_OPTIONAL|REQUIRE]_GPIOLIB") and commit da9a1c6767 ("arm64: do away with ARCH_[WANT_OPTIONAL|REQUIRE]_GPIOLIB") as well. Discovered with the https://github.com/ulfalizer/Kconfiglib/blob/master/examples/list_undefined.py script. Reviewed-by: Linus Walleij Signed-off-by: Ulf Magnusson Signed-off-by: Palmer Dabbelt --- arch/riscv/Kconfig | 1 - 1 file changed, 1 deletion(-) (limited to 'arch') diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index b6722c246d9c..f9fd6ed042b9 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -20,7 +20,6 @@ config RISCV select GENERIC_STRNLEN_USER select GENERIC_SMP_IDLE_THREAD select GENERIC_ATOMIC64 if !64BIT || !RISCV_ISA_A - select ARCH_WANT_OPTIONAL_GPIOLIB select HAVE_MEMBLOCK select HAVE_MEMBLOCK_NODE_MAP select HAVE_DMA_API_DEBUG -- cgit v1.2.3-55-g7522 From 2aaa2dc31bee808703c24ce626e50d1b6d8c7f9c Mon Sep 17 00:00:00 2001 From: Ulf Magnusson Date: Thu, 8 Feb 2018 23:54:46 +0100 Subject: riscv: kconfig: Remove RISCV_IRQ_INTC select The RISCV_IRQ_INTC configuration symbol is undefined, but RISCV selects it. Quoting Palmer Dabbelt: It looks like this slipped through, the symbol has been renamed RISCV_INTC. No RISCV_INTC configuration symbol has been merged either. Just remove the RISCV_IRQ_INTC select for now. Signed-off-by: Ulf Magnusson Signed-off-by: Palmer Dabbelt --- arch/riscv/Kconfig | 1 - 1 file changed, 1 deletion(-) (limited to 'arch') diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index f9fd6ed042b9..97407480982f 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -33,7 +33,6 @@ config RISCV select HAVE_ARCH_TRACEHOOK select MODULES_USE_ELF_RELA if MODULES select THREAD_INFO_IN_TASK - select RISCV_IRQ_INTC select RISCV_TIMER config MMU -- cgit v1.2.3-55-g7522 From 89a4b4441206962d1bbb62f128604a269b60933d Mon Sep 17 00:00:00 2001 From: Ulf Magnusson Date: Mon, 5 Feb 2018 02:21:18 +0100 Subject: riscv: Remove ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE select The ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE symbol was removed in commit 51a021244b9d ("atomic64: no need for CONFIG_ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE"). Remove the ARCH_HAS_ATOMIC64_DEC_IS_POSITIVE select from RISCV. Discovered with the https://github.com/ulfalizer/Kconfiglib/blob/master/examples/list_undefined.py script. Signed-off-by: Ulf Magnusson Reviewed-by: Jonathan Neuschäfer Signed-off-by: Palmer Dabbelt --- arch/riscv/Kconfig | 1 - 1 file changed, 1 deletion(-) (limited to 'arch') diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index 97407480982f..04807c7f64cc 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -8,7 +8,6 @@ config RISCV select OF select OF_EARLY_FLATTREE select OF_IRQ - select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE select ARCH_WANT_FRAME_POINTERS select CLONE_BACKWARDS select COMMON_CLK -- cgit v1.2.3-55-g7522 From bcae803a213172c79ab5d077f169e3428e44d2ba Mon Sep 17 00:00:00 2001 From: zongbox@gmail.com Date: Mon, 29 Jan 2018 23:51:45 -0800 Subject: RISC-V: Enable IRQ during exception handling Interrupt is allowed during exception handling. There are warning messages if the kernel enables the configuration 'CONFIG_DEBUG_ATOMIC_SLEEP=y'. BUG: sleeping function called from invalid context at kernel/locking/rwsem.c:23 in_atomic(): 0, irqs_disabled(): 1, pid: 43, name: ash CPU: 0 PID: 43 Comm: ash Tainted: G W 4.15.0-rc8-00089-g89ffdae-dirty #17 Call Trace: [<000000009abb1587>] walk_stackframe+0x0/0x7a [<00000000d4f3d088>] ___might_sleep+0x102/0x11a [<00000000b1fd792a>] down_read+0x18/0x28 [<000000000289ec01>] do_page_fault+0x86/0x2f6 [<00000000012441f6>] _do_fork+0x1b4/0x1e0 [<00000000f46c3e3b>] ret_from_syscall+0xa/0xe Reviewed-by: Christoph Hellwig Signed-off-by: Zong Li Signed-off-by: Palmer Dabbelt Signed-off-by: Palmer Dabbelt --- arch/riscv/kernel/entry.S | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'arch') diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S index 87fc045be51f..56fa592cfa34 100644 --- a/arch/riscv/kernel/entry.S +++ b/arch/riscv/kernel/entry.S @@ -172,6 +172,9 @@ ENTRY(handle_exception) move a1, sp /* pt_regs */ tail do_IRQ 1: + /* Exceptions run with interrupts enabled */ + csrs sstatus, SR_SIE + /* Handle syscalls */ li t0, EXC_SYSCALL beq s4, t0, handle_syscall @@ -198,8 +201,6 @@ handle_syscall: */ addi s2, s2, 0x4 REG_S s2, PT_SEPC(sp) - /* System calls run with interrupts enabled */ - csrs sstatus, SR_SIE /* Trace syscalls, but only if requested by the user. */ REG_L t0, TASK_TI_FLAGS(tp) andi t0, t0, _TIF_SYSCALL_TRACE -- cgit v1.2.3-55-g7522 From 8b08f50152ff85a4780e5c385d2b65889406e842 Mon Sep 17 00:00:00 2001 From: Michael Clark Date: Fri, 16 Feb 2018 09:30:29 +1300 Subject: Rename sbi_save to parse_dtb to improve code readability The sbi_ prefix would seem to indicate an SBI interface, and save is not very specific. After applying this patch, reading head.S makes more sense. Signed-off-by: Michael Clark Signed-off-by: Palmer Dabbelt --- arch/riscv/kernel/head.S | 2 +- arch/riscv/kernel/setup.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'arch') diff --git a/arch/riscv/kernel/head.S b/arch/riscv/kernel/head.S index 226eeb190f90..6e07ed37bbff 100644 --- a/arch/riscv/kernel/head.S +++ b/arch/riscv/kernel/head.S @@ -64,7 +64,7 @@ ENTRY(_start) /* Start the kernel */ mv a0, s0 mv a1, s1 - call sbi_save + call parse_dtb tail start_kernel relocate: diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c index 09f7064e898c..c11f40c1b2a8 100644 --- a/arch/riscv/kernel/setup.c +++ b/arch/riscv/kernel/setup.c @@ -144,7 +144,7 @@ asmlinkage void __init setup_vm(void) #endif } -void __init sbi_save(unsigned int hartid, void *dtb) +void __init parse_dtb(unsigned int hartid, void *dtb) { early_init_dt_scan(__va(dtb)); } -- cgit v1.2.3-55-g7522 From 5fe01793dd953ab947fababe8abaf5ed5258c8df Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Wed, 7 Feb 2018 12:46:42 +0100 Subject: KVM: s390: take care of clock-comparator sign control Missed when enabling the Multiple-epoch facility. If the facility is installed and the control is set, a sign based comaprison has to be performed. Right now we would inject wrong interrupts and ignore interrupt conditions. Also the sleep time is calculated in a wrong way. Signed-off-by: David Hildenbrand Message-Id: <20180207114647.6220-2-david@redhat.com> Fixes: 8fa1696ea781 ("KVM: s390: Multiple Epoch Facility support") Cc: stable@vger.kernel.org Reviewed-by: Christian Borntraeger Signed-off-by: Christian Borntraeger --- arch/s390/kvm/interrupt.c | 25 +++++++++++++++++++------ 1 file changed, 19 insertions(+), 6 deletions(-) (limited to 'arch') diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index 3f2c49b1a393..b04616b57a94 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -169,8 +169,15 @@ static int ckc_interrupts_enabled(struct kvm_vcpu *vcpu) static int ckc_irq_pending(struct kvm_vcpu *vcpu) { - if (vcpu->arch.sie_block->ckc >= kvm_s390_get_tod_clock_fast(vcpu->kvm)) + const u64 now = kvm_s390_get_tod_clock_fast(vcpu->kvm); + const u64 ckc = vcpu->arch.sie_block->ckc; + + if (vcpu->arch.sie_block->gcr[0] & 0x0020000000000000ul) { + if ((s64)ckc >= (s64)now) + return 0; + } else if (ckc >= now) { return 0; + } return ckc_interrupts_enabled(vcpu); } @@ -1047,13 +1054,19 @@ int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu) static u64 __calculate_sltime(struct kvm_vcpu *vcpu) { - u64 now, cputm, sltime = 0; + const u64 now = kvm_s390_get_tod_clock_fast(vcpu->kvm); + const u64 ckc = vcpu->arch.sie_block->ckc; + u64 cputm, sltime = 0; if (ckc_interrupts_enabled(vcpu)) { - now = kvm_s390_get_tod_clock_fast(vcpu->kvm); - sltime = tod_to_ns(vcpu->arch.sie_block->ckc - now); - /* already expired or overflow? */ - if (!sltime || vcpu->arch.sie_block->ckc <= now) + if (vcpu->arch.sie_block->gcr[0] & 0x0020000000000000ul) { + if ((s64)now < (s64)ckc) + sltime = tod_to_ns((s64)ckc - (s64)now); + } else if (now < ckc) { + sltime = tod_to_ns(ckc - now); + } + /* already expired */ + if (!sltime) return 0; if (cpu_timer_interrupts_enabled(vcpu)) { cputm = kvm_s390_get_cpu_timer(vcpu); -- cgit v1.2.3-55-g7522 From d16b52cb9cdb6f06dea8ab2f0a428e7d7f0b0a81 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Wed, 7 Feb 2018 12:46:44 +0100 Subject: KVM: s390: consider epoch index on hotplugged CPUs We must copy both, the epoch and the epoch_idx. Signed-off-by: David Hildenbrand Message-Id: <20180207114647.6220-4-david@redhat.com> Fixes: 8fa1696ea781 ("KVM: s390: Multiple Epoch Facility support") Reviewed-by: Cornelia Huck Reviewed-by: Christian Borntraeger Fixes: 8fa1696ea781 ("KVM: s390: Multiple Epoch Facility support") Cc: stable@vger.kernel.org Signed-off-by: Christian Borntraeger --- arch/s390/kvm/kvm-s390.c | 1 + 1 file changed, 1 insertion(+) (limited to 'arch') diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index ba4c7092335a..5b7fe80cda56 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -2389,6 +2389,7 @@ void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu) mutex_lock(&vcpu->kvm->lock); preempt_disable(); vcpu->arch.sie_block->epoch = vcpu->kvm->arch.epoch; + vcpu->arch.sie_block->epdx = vcpu->kvm->arch.epdx; preempt_enable(); mutex_unlock(&vcpu->kvm->lock); if (!kvm_is_ucontrol(vcpu->kvm)) { -- cgit v1.2.3-55-g7522 From 1575767ef3cf5326701d2ae3075b7732cbc855e4 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Wed, 7 Feb 2018 12:46:45 +0100 Subject: KVM: s390: consider epoch index on TOD clock syncs For now, we don't take care of over/underflows. Especially underflows are critical: Assume the epoch is currently 0 and we get a sync request for delta=1, meaning the TOD is moved forward by 1 and we have to fix it up by subtracting 1 from the epoch. Right now, this will leave the epoch index untouched, resulting in epoch=-1, epoch_idx=0, which is wrong. We have to take care of over and underflows, also for the VSIE case. So let's factor out calculation into a separate function. Signed-off-by: David Hildenbrand Message-Id: <20180207114647.6220-5-david@redhat.com> Reviewed-by: Christian Borntraeger Fixes: 8fa1696ea781 ("KVM: s390: Multiple Epoch Facility support") Cc: stable@vger.kernel.org Signed-off-by: Christian Borntraeger [use u8 for idx] --- arch/s390/kvm/kvm-s390.c | 32 +++++++++++++++++++++++++++++--- 1 file changed, 29 insertions(+), 3 deletions(-) (limited to 'arch') diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 5b7fe80cda56..b07aa16dcf06 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -179,6 +179,28 @@ int kvm_arch_hardware_enable(void) static void kvm_gmap_notifier(struct gmap *gmap, unsigned long start, unsigned long end); +static void kvm_clock_sync_scb(struct kvm_s390_sie_block *scb, u64 delta) +{ + u8 delta_idx = 0; + + /* + * The TOD jumps by delta, we have to compensate this by adding + * -delta to the epoch. + */ + delta = -delta; + + /* sign-extension - we're adding to signed values below */ + if ((s64)delta < 0) + delta_idx = -1; + + scb->epoch += delta; + if (scb->ecd & ECD_MEF) { + scb->epdx += delta_idx; + if (scb->epoch < delta) + scb->epdx += 1; + } +} + /* * This callback is executed during stop_machine(). All CPUs are therefore * temporarily stopped. In order not to change guest behavior, we have to @@ -194,13 +216,17 @@ static int kvm_clock_sync(struct notifier_block *notifier, unsigned long val, unsigned long long *delta = v; list_for_each_entry(kvm, &vm_list, vm_list) { - kvm->arch.epoch -= *delta; kvm_for_each_vcpu(i, vcpu, kvm) { - vcpu->arch.sie_block->epoch -= *delta; + kvm_clock_sync_scb(vcpu->arch.sie_block, *delta); + if (i == 0) { + kvm->arch.epoch = vcpu->arch.sie_block->epoch; + kvm->arch.epdx = vcpu->arch.sie_block->epdx; + } if (vcpu->arch.cputm_enabled) vcpu->arch.cputm_start += *delta; if (vcpu->arch.vsie_block) - vcpu->arch.vsie_block->epoch -= *delta; + kvm_clock_sync_scb(vcpu->arch.vsie_block, + *delta); } } return NOTIFY_OK; -- cgit v1.2.3-55-g7522 From 0e7def5fb0dc53ddbb9f62a497d15f1e11ccdc36 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Wed, 7 Feb 2018 12:46:43 +0100 Subject: KVM: s390: provide only a single function for setting the tod (fix SCK) Right now, SET CLOCK called in the guest does not properly take care of the epoch index, as the call goes via the old kvm_s390_set_tod_clock() interface. So the epoch index is neither reset to 0, if required, nor properly set to e.g. 0xff on negative values. Fix this by providing a single kvm_s390_set_tod_clock() function. Move Multiple-epoch facility handling into it. Signed-off-by: David Hildenbrand Message-Id: <20180207114647.6220-3-david@redhat.com> Reviewed-by: Christian Borntraeger Fixes: 8fa1696ea781 ("KVM: s390: Multiple Epoch Facility support") Cc: stable@vger.kernel.org Signed-off-by: Christian Borntraeger --- arch/s390/kvm/kvm-s390.c | 46 +++++++++++++++------------------------------- arch/s390/kvm/kvm-s390.h | 5 ++--- arch/s390/kvm/priv.c | 9 +++++---- 3 files changed, 22 insertions(+), 38 deletions(-) (limited to 'arch') diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index b07aa16dcf06..77d7818130db 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -928,12 +928,9 @@ static int kvm_s390_set_tod_ext(struct kvm *kvm, struct kvm_device_attr *attr) if (copy_from_user(>od, (void __user *)attr->addr, sizeof(gtod))) return -EFAULT; - if (test_kvm_facility(kvm, 139)) - kvm_s390_set_tod_clock_ext(kvm, >od); - else if (gtod.epoch_idx == 0) - kvm_s390_set_tod_clock(kvm, gtod.tod); - else + if (!test_kvm_facility(kvm, 139) && gtod.epoch_idx) return -EINVAL; + kvm_s390_set_tod_clock(kvm, >od); VM_EVENT(kvm, 3, "SET: TOD extension: 0x%x, TOD base: 0x%llx", gtod.epoch_idx, gtod.tod); @@ -958,13 +955,14 @@ static int kvm_s390_set_tod_high(struct kvm *kvm, struct kvm_device_attr *attr) static int kvm_s390_set_tod_low(struct kvm *kvm, struct kvm_device_attr *attr) { - u64 gtod; + struct kvm_s390_vm_tod_clock gtod = { 0 }; - if (copy_from_user(>od, (void __user *)attr->addr, sizeof(gtod))) + if (copy_from_user(>od.tod, (void __user *)attr->addr, + sizeof(gtod.tod))) return -EFAULT; - kvm_s390_set_tod_clock(kvm, gtod); - VM_EVENT(kvm, 3, "SET: TOD base: 0x%llx", gtod); + kvm_s390_set_tod_clock(kvm, >od); + VM_EVENT(kvm, 3, "SET: TOD base: 0x%llx", gtod.tod); return 0; } @@ -3048,8 +3046,8 @@ retry: return 0; } -void kvm_s390_set_tod_clock_ext(struct kvm *kvm, - const struct kvm_s390_vm_tod_clock *gtod) +void kvm_s390_set_tod_clock(struct kvm *kvm, + const struct kvm_s390_vm_tod_clock *gtod) { struct kvm_vcpu *vcpu; struct kvm_s390_tod_clock_ext htod; @@ -3061,10 +3059,12 @@ void kvm_s390_set_tod_clock_ext(struct kvm *kvm, get_tod_clock_ext((char *)&htod); kvm->arch.epoch = gtod->tod - htod.tod; - kvm->arch.epdx = gtod->epoch_idx - htod.epoch_idx; - - if (kvm->arch.epoch > gtod->tod) - kvm->arch.epdx -= 1; + kvm->arch.epdx = 0; + if (test_kvm_facility(kvm, 139)) { + kvm->arch.epdx = gtod->epoch_idx - htod.epoch_idx; + if (kvm->arch.epoch > gtod->tod) + kvm->arch.epdx -= 1; + } kvm_s390_vcpu_block_all(kvm); kvm_for_each_vcpu(i, vcpu, kvm) { @@ -3077,22 +3077,6 @@ void kvm_s390_set_tod_clock_ext(struct kvm *kvm, mutex_unlock(&kvm->lock); } -void kvm_s390_set_tod_clock(struct kvm *kvm, u64 tod) -{ - struct kvm_vcpu *vcpu; - int i; - - mutex_lock(&kvm->lock); - preempt_disable(); - kvm->arch.epoch = tod - get_tod_clock(); - kvm_s390_vcpu_block_all(kvm); - kvm_for_each_vcpu(i, vcpu, kvm) - vcpu->arch.sie_block->epoch = kvm->arch.epoch; - kvm_s390_vcpu_unblock_all(kvm); - preempt_enable(); - mutex_unlock(&kvm->lock); -} - /** * kvm_arch_fault_in_page - fault-in guest page if necessary * @vcpu: The corresponding virtual cpu diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h index 3c0a975c2477..f55ac0ef99ea 100644 --- a/arch/s390/kvm/kvm-s390.h +++ b/arch/s390/kvm/kvm-s390.h @@ -281,9 +281,8 @@ int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu); int kvm_s390_handle_sigp_pei(struct kvm_vcpu *vcpu); /* implemented in kvm-s390.c */ -void kvm_s390_set_tod_clock_ext(struct kvm *kvm, - const struct kvm_s390_vm_tod_clock *gtod); -void kvm_s390_set_tod_clock(struct kvm *kvm, u64 tod); +void kvm_s390_set_tod_clock(struct kvm *kvm, + const struct kvm_s390_vm_tod_clock *gtod); long kvm_arch_fault_in_page(struct kvm_vcpu *vcpu, gpa_t gpa, int writable); int kvm_s390_store_status_unloaded(struct kvm_vcpu *vcpu, unsigned long addr); int kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu, unsigned long addr); diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c index a74578cdd3f3..f0b4185158af 100644 --- a/arch/s390/kvm/priv.c +++ b/arch/s390/kvm/priv.c @@ -85,9 +85,10 @@ int kvm_s390_handle_e3(struct kvm_vcpu *vcpu) /* Handle SCK (SET CLOCK) interception */ static int handle_set_clock(struct kvm_vcpu *vcpu) { + struct kvm_s390_vm_tod_clock gtod = { 0 }; int rc; u8 ar; - u64 op2, val; + u64 op2; vcpu->stat.instruction_sck++; @@ -97,12 +98,12 @@ static int handle_set_clock(struct kvm_vcpu *vcpu) op2 = kvm_s390_get_base_disp_s(vcpu, &ar); if (op2 & 7) /* Operand must be on a doubleword boundary */ return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); - rc = read_guest(vcpu, op2, ar, &val, sizeof(val)); + rc = read_guest(vcpu, op2, ar, >od.tod, sizeof(gtod.tod)); if (rc) return kvm_s390_inject_prog_cond(vcpu, rc); - VCPU_EVENT(vcpu, 3, "SCK: setting guest TOD to 0x%llx", val); - kvm_s390_set_tod_clock(vcpu->kvm, val); + VCPU_EVENT(vcpu, 3, "SCK: setting guest TOD to 0x%llx", gtod.tod); + kvm_s390_set_tod_clock(vcpu->kvm, >od); kvm_s390_set_psw_cc(vcpu, 0); return 0; -- cgit v1.2.3-55-g7522 From 521ca5a9859a870e354d1a6b84a6ff4c07bbceb0 Mon Sep 17 00:00:00 2001 From: Juan J. Alvarez Date: Thu, 15 Feb 2018 12:49:51 -0600 Subject: powerpc/eeh: Fix crashes in eeh_report_resume() The notify_resume() callback in eeh_ops is NULL on powernv, leading to crashes: NIP (null) LR eeh_report_resume+0x218/0x220 Call Trace: eeh_report_resume+0x1f0/0x220 (unreliable) eeh_pe_dev_traverse+0x98/0x170 eeh_handle_normal_event+0x3f4/0x650 eeh_handle_event+0x54/0x380 eeh_event_handler+0x14c/0x210 kthread+0x168/0x1b0 ret_from_kernel_thread+0x5c/0xb4 Fix it by adding a check before calling it. Fixes: 856e1eb9bdd4 ("PCI/AER: Add uevents in AER and EEH error/resume") Signed-off-by: Juan J. Alvarez Reviewed-by: Bryant G. Ly Tested-by: Carol L. Soto Reviewed-by: Andrew Donnellan Tested-by: Mauro S. M. Rodrigues Acked-by: Michael Neuling [mpe: Rewrite change log] Signed-off-by: Michael Ellerman --- arch/powerpc/kernel/eeh_driver.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c index beea2182d754..0c0b66fc5bfb 100644 --- a/arch/powerpc/kernel/eeh_driver.c +++ b/arch/powerpc/kernel/eeh_driver.c @@ -384,7 +384,8 @@ static void *eeh_report_resume(void *data, void *userdata) eeh_pcid_put(dev); pci_uevent_ers(dev, PCI_ERS_RESULT_RECOVERED); #ifdef CONFIG_PCI_IOV - eeh_ops->notify_resume(eeh_dev_to_pdn(edev)); + if (eeh_ops->notify_resume && eeh_dev_to_pdn(edev)) + eeh_ops->notify_resume(eeh_dev_to_pdn(edev)); #endif return NULL; } -- cgit v1.2.3-55-g7522 From 9e0e3c5130e949c389caabc8033e9799b129e429 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 17 Jan 2018 22:34:34 +0100 Subject: x86/speculation, objtool: Annotate indirect calls/jumps for objtool Annotate the indirect calls/jumps in the CALL_NOSPEC/JUMP_NOSPEC alternatives. Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: David Woodhouse Acked-by: Thomas Gleixner Acked-by: Josh Poimboeuf Cc: Andy Lutomirski Cc: Arjan van de Ven Cc: Borislav Petkov Cc: Dan Williams Cc: Dave Hansen Cc: David Woodhouse Cc: Greg Kroah-Hartman Cc: Linus Torvalds Cc: Peter Zijlstra Signed-off-by: Ingo Molnar --- arch/x86/include/asm/nospec-branch.h | 27 +++++++++++++++++++++++---- 1 file changed, 23 insertions(+), 4 deletions(-) (limited to 'arch') diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index ec90c3228991..1aad6c79a597 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -67,6 +67,18 @@ .popsection .endm +/* + * This should be used immediately before an indirect jump/call. It tells + * objtool the subsequent indirect jump/call is vouched safe for retpoline + * builds. + */ +.macro ANNOTATE_RETPOLINE_SAFE + .Lannotate_\@: + .pushsection .discard.retpoline_safe + _ASM_PTR .Lannotate_\@ + .popsection +.endm + /* * These are the bare retpoline primitives for indirect jmp and call. * Do not use these directly; they only exist to make the ALTERNATIVE @@ -103,9 +115,9 @@ .macro JMP_NOSPEC reg:req #ifdef CONFIG_RETPOLINE ANNOTATE_NOSPEC_ALTERNATIVE - ALTERNATIVE_2 __stringify(jmp *\reg), \ + ALTERNATIVE_2 __stringify(ANNOTATE_RETPOLINE_SAFE; jmp *\reg), \ __stringify(RETPOLINE_JMP \reg), X86_FEATURE_RETPOLINE, \ - __stringify(lfence; jmp *\reg), X86_FEATURE_RETPOLINE_AMD + __stringify(lfence; ANNOTATE_RETPOLINE_SAFE; jmp *\reg), X86_FEATURE_RETPOLINE_AMD #else jmp *\reg #endif @@ -114,9 +126,9 @@ .macro CALL_NOSPEC reg:req #ifdef CONFIG_RETPOLINE ANNOTATE_NOSPEC_ALTERNATIVE - ALTERNATIVE_2 __stringify(call *\reg), \ + ALTERNATIVE_2 __stringify(ANNOTATE_RETPOLINE_SAFE; call *\reg), \ __stringify(RETPOLINE_CALL \reg), X86_FEATURE_RETPOLINE,\ - __stringify(lfence; call *\reg), X86_FEATURE_RETPOLINE_AMD + __stringify(lfence; ANNOTATE_RETPOLINE_SAFE; call *\reg), X86_FEATURE_RETPOLINE_AMD #else call *\reg #endif @@ -144,6 +156,12 @@ ".long 999b - .\n\t" \ ".popsection\n\t" +#define ANNOTATE_RETPOLINE_SAFE \ + "999:\n\t" \ + ".pushsection .discard.retpoline_safe\n\t" \ + _ASM_PTR " 999b\n\t" \ + ".popsection\n\t" + #if defined(CONFIG_X86_64) && defined(RETPOLINE) /* @@ -153,6 +171,7 @@ # define CALL_NOSPEC \ ANNOTATE_NOSPEC_ALTERNATIVE \ ALTERNATIVE( \ + ANNOTATE_RETPOLINE_SAFE \ "call *%[thunk_target]\n", \ "call __x86_indirect_thunk_%V[thunk_target]\n", \ X86_FEATURE_RETPOLINE) -- cgit v1.2.3-55-g7522 From 3010a0663fd949d122eca0561b06b0a9453f7866 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 17 Jan 2018 16:58:11 +0100 Subject: x86/paravirt, objtool: Annotate indirect calls Paravirt emits indirect calls which get flagged by objtool retpoline checks, annotate it away because all these indirect calls will be patched out before we start userspace. This patching happens through alternative_instructions() -> apply_paravirt() -> pv_init_ops.patch() which will eventually end up in paravirt_patch_default(). This function _will_ write direct alternatives. Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: David Woodhouse Acked-by: Thomas Gleixner Acked-by: Josh Poimboeuf Cc: Andy Lutomirski Cc: Arjan van de Ven Cc: Borislav Petkov Cc: Dan Williams Cc: Dave Hansen Cc: David Woodhouse Cc: Greg Kroah-Hartman Cc: Linus Torvalds Cc: Peter Zijlstra Signed-off-by: Ingo Molnar --- arch/x86/include/asm/paravirt.h | 17 +++++++++++++---- arch/x86/include/asm/paravirt_types.h | 5 ++++- 2 files changed, 17 insertions(+), 5 deletions(-) (limited to 'arch') diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index 554841fab717..c83a2f418cea 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -7,6 +7,7 @@ #ifdef CONFIG_PARAVIRT #include #include +#include #include @@ -879,23 +880,27 @@ extern void default_banner(void); #define INTERRUPT_RETURN \ PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_iret), CLBR_NONE, \ - jmp PARA_INDIRECT(pv_cpu_ops+PV_CPU_iret)) + ANNOTATE_RETPOLINE_SAFE; \ + jmp PARA_INDIRECT(pv_cpu_ops+PV_CPU_iret);) #define DISABLE_INTERRUPTS(clobbers) \ PARA_SITE(PARA_PATCH(pv_irq_ops, PV_IRQ_irq_disable), clobbers, \ PV_SAVE_REGS(clobbers | CLBR_CALLEE_SAVE); \ + ANNOTATE_RETPOLINE_SAFE; \ call PARA_INDIRECT(pv_irq_ops+PV_IRQ_irq_disable); \ PV_RESTORE_REGS(clobbers | CLBR_CALLEE_SAVE);) #define ENABLE_INTERRUPTS(clobbers) \ PARA_SITE(PARA_PATCH(pv_irq_ops, PV_IRQ_irq_enable), clobbers, \ PV_SAVE_REGS(clobbers | CLBR_CALLEE_SAVE); \ + ANNOTATE_RETPOLINE_SAFE; \ call PARA_INDIRECT(pv_irq_ops+PV_IRQ_irq_enable); \ PV_RESTORE_REGS(clobbers | CLBR_CALLEE_SAVE);) #ifdef CONFIG_X86_32 #define GET_CR0_INTO_EAX \ push %ecx; push %edx; \ + ANNOTATE_RETPOLINE_SAFE; \ call PARA_INDIRECT(pv_cpu_ops+PV_CPU_read_cr0); \ pop %edx; pop %ecx #else /* !CONFIG_X86_32 */ @@ -917,21 +922,25 @@ extern void default_banner(void); */ #define SWAPGS \ PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_swapgs), CLBR_NONE, \ - call PARA_INDIRECT(pv_cpu_ops+PV_CPU_swapgs) \ + ANNOTATE_RETPOLINE_SAFE; \ + call PARA_INDIRECT(pv_cpu_ops+PV_CPU_swapgs); \ ) #define GET_CR2_INTO_RAX \ - call PARA_INDIRECT(pv_mmu_ops+PV_MMU_read_cr2) + ANNOTATE_RETPOLINE_SAFE; \ + call PARA_INDIRECT(pv_mmu_ops+PV_MMU_read_cr2); #define USERGS_SYSRET64 \ PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_usergs_sysret64), \ CLBR_NONE, \ - jmp PARA_INDIRECT(pv_cpu_ops+PV_CPU_usergs_sysret64)) + ANNOTATE_RETPOLINE_SAFE; \ + jmp PARA_INDIRECT(pv_cpu_ops+PV_CPU_usergs_sysret64);) #ifdef CONFIG_DEBUG_ENTRY #define SAVE_FLAGS(clobbers) \ PARA_SITE(PARA_PATCH(pv_irq_ops, PV_IRQ_save_fl), clobbers, \ PV_SAVE_REGS(clobbers | CLBR_CALLEE_SAVE); \ + ANNOTATE_RETPOLINE_SAFE; \ call PARA_INDIRECT(pv_irq_ops+PV_IRQ_save_fl); \ PV_RESTORE_REGS(clobbers | CLBR_CALLEE_SAVE);) #endif diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h index f624f1f10316..180bc0bff0fb 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -43,6 +43,7 @@ #include #include #include +#include struct page; struct thread_struct; @@ -392,7 +393,9 @@ int paravirt_disable_iospace(void); * offset into the paravirt_patch_template structure, and can therefore be * freely converted back into a structure offset. */ -#define PARAVIRT_CALL "call *%c[paravirt_opptr];" +#define PARAVIRT_CALL \ + ANNOTATE_RETPOLINE_SAFE \ + "call *%c[paravirt_opptr];" /* * These macros are intended to wrap calls through one of the paravirt -- cgit v1.2.3-55-g7522 From bd89004f6305cbf7352238f61da093207ee518d6 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 16 Jan 2018 10:38:09 +0100 Subject: x86/boot, objtool: Annotate indirect jump in secondary_startup_64() The objtool retpoline validation found this indirect jump. Seeing how it's on CPU bringup before we run userspace it should be safe, annotate it. Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: David Woodhouse Acked-by: Thomas Gleixner Acked-by: Josh Poimboeuf Cc: Andy Lutomirski Cc: Arjan van de Ven Cc: Borislav Petkov Cc: Dan Williams Cc: Dave Hansen Cc: David Woodhouse Cc: Greg Kroah-Hartman Cc: Linus Torvalds Cc: Peter Zijlstra Signed-off-by: Ingo Molnar --- arch/x86/kernel/head_64.S | 2 ++ 1 file changed, 2 insertions(+) (limited to 'arch') diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 04a625f0fcda..0f545b3cf926 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -23,6 +23,7 @@ #include #include "../entry/calling.h" #include +#include #ifdef CONFIG_PARAVIRT #include @@ -134,6 +135,7 @@ ENTRY(secondary_startup_64) /* Ensure I am executing from virtual addresses */ movq $1f, %rax + ANNOTATE_RETPOLINE_SAFE jmp *%rax 1: UNWIND_HINT_EMPTY -- cgit v1.2.3-55-g7522 From 531bb52a869a9c6e08c8d17ba955fcbfc18037ad Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 23 Jan 2018 16:18:50 +0100 Subject: x86/mm/sme, objtool: Annotate indirect call in sme_encrypt_execute() This is boot code and thus Spectre-safe: we run this _way_ before userspace comes along to have a chance to poison our branch predictor. Signed-off-by: Peter Zijlstra (Intel) Acked-by: Thomas Gleixner Acked-by: Josh Poimboeuf Cc: Andy Lutomirski Cc: Arjan van de Ven Cc: Borislav Petkov Cc: Borislav Petkov Cc: Dan Williams Cc: Dave Hansen Cc: David Woodhouse Cc: Greg Kroah-Hartman Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Tom Lendacky Signed-off-by: Ingo Molnar --- arch/x86/mm/mem_encrypt_boot.S | 2 ++ 1 file changed, 2 insertions(+) (limited to 'arch') diff --git a/arch/x86/mm/mem_encrypt_boot.S b/arch/x86/mm/mem_encrypt_boot.S index 01f682cf77a8..40a6085063d6 100644 --- a/arch/x86/mm/mem_encrypt_boot.S +++ b/arch/x86/mm/mem_encrypt_boot.S @@ -15,6 +15,7 @@ #include #include #include +#include .text .code64 @@ -59,6 +60,7 @@ ENTRY(sme_encrypt_execute) movq %rax, %r8 /* Workarea encryption routine */ addq $PAGE_SIZE, %r8 /* Workarea intermediate copy buffer */ + ANNOTATE_RETPOLINE_SAFE call *%rax /* Call the encryption routine */ pop %r12 -- cgit v1.2.3-55-g7522 From 85c615eb52222bc5fab6c7190d146bc59fac289e Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 20 Feb 2018 21:58:21 +0100 Subject: x86/oprofile: Fix bogus GCC-8 warning in nmi_setup() GCC-8 shows a warning for the x86 oprofile code that copies per-CPU data from CPU 0 to all other CPUs, which when building a non-SMP kernel turns into a memcpy() with identical source and destination pointers: arch/x86/oprofile/nmi_int.c: In function 'mux_clone': arch/x86/oprofile/nmi_int.c:285:2: error: 'memcpy' source argument is the same as destination [-Werror=restrict] memcpy(per_cpu(cpu_msrs, cpu).multiplex, ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ per_cpu(cpu_msrs, 0).multiplex, ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ sizeof(struct op_msr) * model->num_virt_counters); ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ arch/x86/oprofile/nmi_int.c: In function 'nmi_setup': arch/x86/oprofile/nmi_int.c:466:3: error: 'memcpy' source argument is the same as destination [-Werror=restrict] arch/x86/oprofile/nmi_int.c:470:3: error: 'memcpy' source argument is the same as destination [-Werror=restrict] I have analyzed a number of such warnings now: some are valid and the GCC warning is welcome. Others turned out to be false-positives, and GCC was changed to not warn about those any more. This is a corner case that is a false-positive but the GCC developers feel it's better to keep warning about it. In this case, it seems best to work around it by telling GCC a little more clearly that this code path is never hit with an IS_ENABLED() configuration check. Cc:stable as we also want old kernels to build cleanly with GCC-8. Signed-off-by: Arnd Bergmann Cc: Jessica Yu Cc: Kees Cook Cc: Linus Torvalds Cc: Martin Sebor Cc: Peter Zijlstra Cc: Robert Richter Cc: Thomas Gleixner Cc: oprofile-list@lists.sf.net Cc: stable@vger.kernel.org Link: http://lkml.kernel.org/r/20180220205826.2008875-1-arnd@arndb.de Link: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=84095 Signed-off-by: Ingo Molnar --- arch/x86/oprofile/nmi_int.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/x86/oprofile/nmi_int.c b/arch/x86/oprofile/nmi_int.c index 174c59774cc9..a7a7677265b6 100644 --- a/arch/x86/oprofile/nmi_int.c +++ b/arch/x86/oprofile/nmi_int.c @@ -460,7 +460,7 @@ static int nmi_setup(void) goto fail; for_each_possible_cpu(cpu) { - if (!cpu) + if (!IS_ENABLED(CONFIG_SMP) || !cpu) continue; memcpy(per_cpu(cpu_msrs, cpu).counters, -- cgit v1.2.3-55-g7522 From cb13b424e986aed68d74cbaec3449ea23c50e167 Mon Sep 17 00:00:00 2001 From: Andrea Parri Date: Tue, 20 Feb 2018 19:45:56 +0100 Subject: locking/xchg/alpha: Add unconditional memory barrier to cmpxchg() Continuing along with the fight against smp_read_barrier_depends() [1] (or rather, against its improper use), add an unconditional barrier to cmpxchg. This guarantees that dependency ordering is preserved when a dependency is headed by an unsuccessful cmpxchg. As it turns out, the change could enable further simplification of LKMM as proposed in [2]. [1] https://marc.info/?l=linux-kernel&m=150884953419377&w=2 https://marc.info/?l=linux-kernel&m=150884946319353&w=2 https://marc.info/?l=linux-kernel&m=151215810824468&w=2 https://marc.info/?l=linux-kernel&m=151215816324484&w=2 [2] https://marc.info/?l=linux-kernel&m=151881978314872&w=2 Signed-off-by: Andrea Parri Acked-by: Peter Zijlstra Acked-by: Paul E. McKenney Cc: Alan Stern Cc: Ivan Kokshaysky Cc: Linus Torvalds Cc: Matt Turner Cc: Richard Henderson Cc: Thomas Gleixner Cc: Will Deacon Cc: linux-alpha@vger.kernel.org Link: http://lkml.kernel.org/r/1519152356-4804-1-git-send-email-parri.andrea@gmail.com Signed-off-by: Ingo Molnar --- arch/alpha/include/asm/xchg.h | 15 +++++++-------- 1 file changed, 7 insertions(+), 8 deletions(-) (limited to 'arch') diff --git a/arch/alpha/include/asm/xchg.h b/arch/alpha/include/asm/xchg.h index 68dfb3cb7145..e2660866ce97 100644 --- a/arch/alpha/include/asm/xchg.h +++ b/arch/alpha/include/asm/xchg.h @@ -128,10 +128,9 @@ ____xchg(, volatile void *ptr, unsigned long x, int size) * store NEW in MEM. Return the initial value in MEM. Success is * indicated by comparing RETURN with OLD. * - * The memory barrier should be placed in SMP only when we actually - * make the change. If we don't change anything (so if the returned - * prev is equal to old) then we aren't acquiring anything new and - * we don't need any memory barrier as far I can tell. + * The memory barrier is placed in SMP unconditionally, in order to + * guarantee that dependency ordering is preserved when a dependency + * is headed by an unsuccessful operation. */ static inline unsigned long @@ -150,8 +149,8 @@ ____cmpxchg(_u8, volatile char *m, unsigned char old, unsigned char new) " or %1,%2,%2\n" " stq_c %2,0(%4)\n" " beq %2,3f\n" - __ASM__MB "2:\n" + __ASM__MB ".subsection 2\n" "3: br 1b\n" ".previous" @@ -177,8 +176,8 @@ ____cmpxchg(_u16, volatile short *m, unsigned short old, unsigned short new) " or %1,%2,%2\n" " stq_c %2,0(%4)\n" " beq %2,3f\n" - __ASM__MB "2:\n" + __ASM__MB ".subsection 2\n" "3: br 1b\n" ".previous" @@ -200,8 +199,8 @@ ____cmpxchg(_u32, volatile int *m, int old, int new) " mov %4,%1\n" " stl_c %1,%2\n" " beq %1,3f\n" - __ASM__MB "2:\n" + __ASM__MB ".subsection 2\n" "3: br 1b\n" ".previous" @@ -223,8 +222,8 @@ ____cmpxchg(_u64, volatile long *m, unsigned long old, unsigned long new) " mov %4,%1\n" " stq_c %1,%2\n" " beq %1,3f\n" - __ASM__MB "2:\n" + __ASM__MB ".subsection 2\n" "3: br 1b\n" ".previous" -- cgit v1.2.3-55-g7522 From d72f4e29e6d84b7ec02ae93088aa459ac70e733b Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Wed, 21 Feb 2018 09:20:37 +0100 Subject: x86/speculation: Move firmware_restrict_branch_speculation_*() from C to CPP firmware_restrict_branch_speculation_*() recently started using preempt_enable()/disable(), but those are relatively high level primitives and cause build failures on some 32-bit builds. Since we want to keep low level, convert them to macros to avoid header hell... Cc: David Woodhouse Cc: Thomas Gleixner Cc: Linus Torvalds Cc: Peter Zijlstra Cc: arjan.van.de.ven@intel.com Cc: bp@alien8.de Cc: dave.hansen@intel.com Cc: jmattson@google.com Cc: karahmed@amazon.de Cc: kvm@vger.kernel.org Cc: pbonzini@redhat.com Cc: rkrcmar@redhat.com Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar --- arch/x86/include/asm/nospec-branch.h | 26 ++++++++++++++------------ 1 file changed, 14 insertions(+), 12 deletions(-) (limited to 'arch') diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index 1aad6c79a597..b7063cfa19f9 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -257,20 +257,22 @@ static inline void indirect_branch_prediction_barrier(void) /* * With retpoline, we must use IBRS to restrict branch prediction * before calling into firmware. + * + * (Implemented as CPP macros due to header hell.) */ -static inline void firmware_restrict_branch_speculation_start(void) -{ - preempt_disable(); - alternative_msr_write(MSR_IA32_SPEC_CTRL, SPEC_CTRL_IBRS, - X86_FEATURE_USE_IBRS_FW); -} +#define firmware_restrict_branch_speculation_start() \ +do { \ + preempt_disable(); \ + alternative_msr_write(MSR_IA32_SPEC_CTRL, SPEC_CTRL_IBRS, \ + X86_FEATURE_USE_IBRS_FW); \ +} while (0) -static inline void firmware_restrict_branch_speculation_end(void) -{ - alternative_msr_write(MSR_IA32_SPEC_CTRL, 0, - X86_FEATURE_USE_IBRS_FW); - preempt_enable(); -} +#define firmware_restrict_branch_speculation_end() \ +do { \ + alternative_msr_write(MSR_IA32_SPEC_CTRL, 0, \ + X86_FEATURE_USE_IBRS_FW); \ + preempt_enable(); \ +} while (0) #endif /* __ASSEMBLY__ */ #endif /* _ASM_X86_NOSPEC_BRANCH_H_ */ -- cgit v1.2.3-55-g7522 From 0e34d226342c27c4f96138b211547d423e4be8a1 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Tue, 20 Feb 2018 22:01:08 +0100 Subject: x86/entry/64: Move PUSH_AND_CLEAR_REGS from interrupt macro to helper function The PUSH_AND_CLEAR_REGS macro is able to insert the GP registers "above" the original return address. This allows us to move a sizeable part of the interrupt entry macro to an interrupt entry helper function: text data bss dec hex filename 21088 0 0 21088 5260 entry_64.o-orig 18006 0 0 18006 4656 entry_64.o Suggested-by: Linus Torvalds Signed-off-by: Dominik Brodowski Acked-by: Thomas Gleixner Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: David Woodhouse Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Josh Poimboeuf Cc: Peter Zijlstra Cc: dan.j.williams@intel.com Link: http://lkml.kernel.org/r/20180220210113.6725-2-linux@dominikbrodowski.net Signed-off-by: Ingo Molnar --- arch/x86/entry/entry_64.S | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'arch') diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 7a53879ec689..b0ae0c3e3815 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -525,6 +525,14 @@ END(irq_entries_start) * * Entry runs with interrupts off. */ +ENTRY(interrupt_entry) + UNWIND_HINT_FUNC + + PUSH_AND_CLEAR_REGS save_ret=1 + ENCODE_FRAME_POINTER 8 + + ret +END(interrupt_entry) /* 0(%rsp): ~(interrupt number) */ .macro interrupt func @@ -536,8 +544,7 @@ END(irq_entries_start) call switch_to_thread_stack 1: - PUSH_AND_CLEAR_REGS - ENCODE_FRAME_POINTER + call interrupt_entry testb $3, CS(%rsp) jz 1f -- cgit v1.2.3-55-g7522 From 2ba6474104a1132c4af9f6dc42c6bfe3ca71f8c7 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Tue, 20 Feb 2018 22:01:09 +0100 Subject: x86/entry/64: Move ENTER_IRQ_STACK from interrupt macro to interrupt_entry Moving the switch to IRQ stack from the interrupt macro to the helper function requires some trickery: All ENTER_IRQ_STACK really cares about is where the "original" stack -- meaning the GP registers etc. -- is stored. Therefore, we need to offset the stored RSP value by 8 whenever ENTER_IRQ_STACK is called from within a function. In such cases, and after switching to the IRQ stack, we need to push the "original" return address (i.e. the return address from the call to the interrupt entry function) to the IRQ stack. This trickery allows us to carve another .85k from the text size (it would be more except for the additional unwind hints): text data bss dec hex filename 18006 0 0 18006 4656 entry_64.o-orig 17158 0 0 17158 4306 entry_64.o Signed-off-by: Dominik Brodowski Acked-by: Thomas Gleixner Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: David Woodhouse Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Josh Poimboeuf Cc: Linus Torvalds Cc: Peter Zijlstra Cc: dan.j.williams@intel.com Link: http://lkml.kernel.org/r/20180220210113.6725-3-linux@dominikbrodowski.net Signed-off-by: Ingo Molnar --- arch/x86/entry/entry_64.S | 56 ++++++++++++++++++++++++++++++++--------------- 1 file changed, 38 insertions(+), 18 deletions(-) (limited to 'arch') diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index b0ae0c3e3815..7a6ae19962ec 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -448,9 +448,19 @@ END(irq_entries_start) * * The invariant is that, if irq_count != -1, then the IRQ stack is in use. */ -.macro ENTER_IRQ_STACK regs=1 old_rsp +.macro ENTER_IRQ_STACK regs=1 old_rsp save_ret=0 DEBUG_ENTRY_ASSERT_IRQS_OFF + + .if \save_ret + /* + * If save_ret is set, the original stack contains one additional + * entry -- the return address. Therefore, move the address one + * entry below %rsp to \old_rsp. + */ + leaq 8(%rsp), \old_rsp + .else movq %rsp, \old_rsp + .endif .if \regs UNWIND_HINT_REGS base=\old_rsp @@ -496,6 +506,15 @@ END(irq_entries_start) .if \regs UNWIND_HINT_REGS indirect=1 .endif + + .if \save_ret + /* + * Push the return address to the stack. This return address can + * be found at the "real" original RSP, which was offset by 8 at + * the beginning of this macro. + */ + pushq -8(\old_rsp) + .endif .endm /* @@ -531,22 +550,7 @@ ENTRY(interrupt_entry) PUSH_AND_CLEAR_REGS save_ret=1 ENCODE_FRAME_POINTER 8 - ret -END(interrupt_entry) - -/* 0(%rsp): ~(interrupt number) */ - .macro interrupt func - cld - - testb $3, CS-ORIG_RAX(%rsp) - jz 1f - SWAPGS - call switch_to_thread_stack -1: - - call interrupt_entry - - testb $3, CS(%rsp) + testb $3, CS+8(%rsp) jz 1f /* @@ -564,10 +568,26 @@ END(interrupt_entry) CALL_enter_from_user_mode 1: - ENTER_IRQ_STACK old_rsp=%rdi + ENTER_IRQ_STACK old_rsp=%rdi save_ret=1 /* We entered an interrupt context - irqs are off: */ TRACE_IRQS_OFF + ret +END(interrupt_entry) + +/* 0(%rsp): ~(interrupt number) */ + .macro interrupt func + cld + + testb $3, CS-ORIG_RAX(%rsp) + jz 1f + SWAPGS + call switch_to_thread_stack +1: + + call interrupt_entry + + UNWIND_HINT_REGS indirect=1 call \func /* rdi points to pt_regs */ .endm -- cgit v1.2.3-55-g7522 From 90a6acc4e7ebafa8672a7a1a5b23fbad3dd04130 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Tue, 20 Feb 2018 22:01:10 +0100 Subject: x86/entry/64: Move the switch_to_thread_stack() call to interrupt_entry() We can also move the CLD, SWAPGS, and the switch_to_thread_stack() call to the interrupt_entry() helper function. As we do not want call depths of two, convert switch_to_thread_stack() to a macro. However, switch_to_thread_stack() has another user in entry_64_compat.S, which currently expects it to be a function. To keep the code changes in this patch minimal, create a wrapper function. The switch to a macro means that there is some binary code duplication if CONFIG_IA32_EMULATION=y is enabled. Therefore, the size reduction differs whether CONFIG_IA32_EMULATION is enabled or not: CONFIG_IA32_EMULATION=y (-0.13k): text data bss dec hex filename 17158 0 0 17158 4306 entry_64.o-orig 17028 0 0 17028 4284 entry_64.o CONFIG_IA32_EMULATION=n (-0.27k): text data bss dec hex filename 17158 0 0 17158 4306 entry_64.o-orig 16882 0 0 16882 41f2 entry_64.o Signed-off-by: Dominik Brodowski Acked-by: Thomas Gleixner Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: David Woodhouse Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Josh Poimboeuf Cc: Linus Torvalds Cc: Peter Zijlstra Cc: dan.j.williams@intel.com Link: http://lkml.kernel.org/r/20180220210113.6725-4-linux@dominikbrodowski.net Signed-off-by: Ingo Molnar --- arch/x86/entry/entry_64.S | 66 ++++++++++++++++++++++++++--------------------- 1 file changed, 37 insertions(+), 29 deletions(-) (limited to 'arch') diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 7a6ae19962ec..b45d76649eff 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -537,6 +537,31 @@ END(irq_entries_start) decl PER_CPU_VAR(irq_count) .endm +/* + * Switch to the thread stack. This is called with the IRET frame and + * orig_ax on the stack. (That is, RDI..R12 are not on the stack and + * space has not been allocated for them.) + */ +.macro DO_SWITCH_TO_THREAD_STACK + pushq %rdi + /* Need to switch before accessing the thread stack. */ + SWITCH_TO_KERNEL_CR3 scratch_reg=%rdi + movq %rsp, %rdi + movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp + UNWIND_HINT sp_offset=16 sp_reg=ORC_REG_DI + + pushq 7*8(%rdi) /* regs->ss */ + pushq 6*8(%rdi) /* regs->rsp */ + pushq 5*8(%rdi) /* regs->eflags */ + pushq 4*8(%rdi) /* regs->cs */ + pushq 3*8(%rdi) /* regs->ip */ + pushq 2*8(%rdi) /* regs->orig_ax */ + pushq 8(%rdi) /* return address */ + UNWIND_HINT_FUNC + + movq (%rdi), %rdi +.endm + /* * Interrupt entry/exit. * @@ -544,8 +569,16 @@ END(irq_entries_start) * * Entry runs with interrupts off. */ +/* 8(%rsp): ~(interrupt number) */ ENTRY(interrupt_entry) UNWIND_HINT_FUNC + cld + + testb $3, CS-ORIG_RAX+8(%rsp) + jz 1f + SWAPGS + DO_SWITCH_TO_THREAD_STACK +1: PUSH_AND_CLEAR_REGS save_ret=1 ENCODE_FRAME_POINTER 8 @@ -577,14 +610,6 @@ END(interrupt_entry) /* 0(%rsp): ~(interrupt number) */ .macro interrupt func - cld - - testb $3, CS-ORIG_RAX(%rsp) - jz 1f - SWAPGS - call switch_to_thread_stack -1: - call interrupt_entry UNWIND_HINT_REGS indirect=1 @@ -858,33 +883,16 @@ apicinterrupt IRQ_WORK_VECTOR irq_work_interrupt smp_irq_work_interrupt */ #define CPU_TSS_IST(x) PER_CPU_VAR(cpu_tss_rw) + (TSS_ist + ((x) - 1) * 8) -/* - * Switch to the thread stack. This is called with the IRET frame and - * orig_ax on the stack. (That is, RDI..R12 are not on the stack and - * space has not been allocated for them.) - */ +#if defined(CONFIG_IA32_EMULATION) +/* entry_64_compat.S::entry_INT80_compat expects this to be an ASM function */ ENTRY(switch_to_thread_stack) UNWIND_HINT_FUNC - pushq %rdi - /* Need to switch before accessing the thread stack. */ - SWITCH_TO_KERNEL_CR3 scratch_reg=%rdi - movq %rsp, %rdi - movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp - UNWIND_HINT sp_offset=16 sp_reg=ORC_REG_DI - - pushq 7*8(%rdi) /* regs->ss */ - pushq 6*8(%rdi) /* regs->rsp */ - pushq 5*8(%rdi) /* regs->eflags */ - pushq 4*8(%rdi) /* regs->cs */ - pushq 3*8(%rdi) /* regs->ip */ - pushq 2*8(%rdi) /* regs->orig_ax */ - pushq 8(%rdi) /* return address */ - UNWIND_HINT_FUNC + DO_SWITCH_TO_THREAD_STACK - movq (%rdi), %rdi ret END(switch_to_thread_stack) +#endif .macro idtentry sym do_sym has_error_code:req paranoid=0 shift_ist=-1 ENTRY(\sym) -- cgit v1.2.3-55-g7522 From 3aa99fc3e708b9cd9b4cfe2df0b7a66cf293e3cf Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Tue, 20 Feb 2018 22:01:11 +0100 Subject: x86/entry/64: Remove 'interrupt' macro It is now trivial to call interrupt_entry() and then the actual worker. Therefore, remove the interrupt macro and open code it all. Suggested-by: Linus Torvalds Signed-off-by: Dominik Brodowski Acked-by: Thomas Gleixner Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: David Woodhouse Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Josh Poimboeuf Cc: Peter Zijlstra Cc: dan.j.williams@intel.com Link: http://lkml.kernel.org/r/20180220210113.6725-5-linux@dominikbrodowski.net Signed-off-by: Ingo Molnar --- arch/x86/entry/entry_64.S | 16 ++++++---------- 1 file changed, 6 insertions(+), 10 deletions(-) (limited to 'arch') diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index b45d76649eff..8ea03cf94a2d 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -608,14 +608,6 @@ ENTRY(interrupt_entry) ret END(interrupt_entry) -/* 0(%rsp): ~(interrupt number) */ - .macro interrupt func - call interrupt_entry - - UNWIND_HINT_REGS indirect=1 - call \func /* rdi points to pt_regs */ - .endm - /* * The interrupt stubs push (~vector+0x80) onto the stack and * then jump to common_interrupt. @@ -624,7 +616,9 @@ END(interrupt_entry) common_interrupt: ASM_CLAC addq $-0x80, (%rsp) /* Adjust vector to [-256, -1] range */ - interrupt do_IRQ + call interrupt_entry + UNWIND_HINT_REGS indirect=1 + call do_IRQ /* rdi points to pt_regs */ /* 0(%rsp): old RSP */ ret_from_intr: DISABLE_INTERRUPTS(CLBR_ANY) @@ -820,7 +814,9 @@ ENTRY(\sym) ASM_CLAC pushq $~(\num) .Lcommon_\sym: - interrupt \do_sym + call interrupt_entry + UNWIND_HINT_REGS indirect=1 + call \do_sym /* rdi points to pt_regs */ jmp ret_from_intr END(\sym) .endm -- cgit v1.2.3-55-g7522 From b2855d8d2de0fa15c1ff30c69ed7756b00c48b22 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Tue, 20 Feb 2018 22:01:12 +0100 Subject: x86/entry/64: Move ASM_CLAC to interrupt_entry() Moving ASM_CLAC to interrupt_entry means two instructions (addq / pushq and call interrupt_entry) are not covered by it. However, it offers a noticeable size reduction (-.2k): text data bss dec hex filename 16882 0 0 16882 41f2 entry_64.o-orig 16623 0 0 16623 40ef entry_64.o Suggested-by: Brian Gerst Signed-off-by: Dominik Brodowski Acked-by: Thomas Gleixner Cc: Andy Lutomirski Cc: Borislav Petkov Cc: David Woodhouse Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Josh Poimboeuf Cc: Linus Torvalds Cc: Peter Zijlstra Cc: dan.j.williams@intel.com Link: http://lkml.kernel.org/r/20180220210113.6725-6-linux@dominikbrodowski.net Signed-off-by: Ingo Molnar --- arch/x86/entry/entry_64.S | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'arch') diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 8ea03cf94a2d..42a4b652469d 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -572,6 +572,7 @@ END(irq_entries_start) /* 8(%rsp): ~(interrupt number) */ ENTRY(interrupt_entry) UNWIND_HINT_FUNC + ASM_CLAC cld testb $3, CS-ORIG_RAX+8(%rsp) @@ -614,7 +615,6 @@ END(interrupt_entry) */ .p2align CONFIG_X86_L1_CACHE_SHIFT common_interrupt: - ASM_CLAC addq $-0x80, (%rsp) /* Adjust vector to [-256, -1] range */ call interrupt_entry UNWIND_HINT_REGS indirect=1 @@ -811,7 +811,6 @@ END(common_interrupt) .macro apicinterrupt3 num sym do_sym ENTRY(\sym) UNWIND_HINT_IRET_REGS - ASM_CLAC pushq $~(\num) .Lcommon_\sym: call interrupt_entry -- cgit v1.2.3-55-g7522 From f3d415ea46968ae1f9cbb9e201601d7207ce74c7 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Tue, 20 Feb 2018 22:01:13 +0100 Subject: x86/entry/64: Open-code switch_to_thread_stack() Open-code the two instances which called switch_to_thread_stack(). This allows us to remove the wrapper around DO_SWITCH_TO_THREAD_STACK. While at it, update the UNWIND hint to reflect where the IRET frame is, and update the commentary to reflect what we are actually doing here. Signed-off-by: Dominik Brodowski Acked-by: Thomas Gleixner Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: David Woodhouse Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Josh Poimboeuf Cc: Linus Torvalds Cc: Peter Zijlstra Cc: dan.j.williams@intel.com Link: http://lkml.kernel.org/r/20180220210113.6725-7-linux@dominikbrodowski.net Signed-off-by: Ingo Molnar --- arch/x86/entry/entry_64.S | 76 +++++++++++++++++++++------------------- arch/x86/entry/entry_64_compat.S | 17 +++++++-- 2 files changed, 55 insertions(+), 38 deletions(-) (limited to 'arch') diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 42a4b652469d..d5c7f18f79ac 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -538,17 +538,48 @@ END(irq_entries_start) .endm /* - * Switch to the thread stack. This is called with the IRET frame and - * orig_ax on the stack. (That is, RDI..R12 are not on the stack and - * space has not been allocated for them.) + * Interrupt entry helper function. + * + * Entry runs with interrupts off. Stack layout at entry: + * +----------------------------------------------------+ + * | regs->ss | + * | regs->rsp | + * | regs->eflags | + * | regs->cs | + * | regs->ip | + * +----------------------------------------------------+ + * | regs->orig_ax = ~(interrupt number) | + * +----------------------------------------------------+ + * | return address | + * +----------------------------------------------------+ */ -.macro DO_SWITCH_TO_THREAD_STACK +ENTRY(interrupt_entry) + UNWIND_HINT_FUNC + ASM_CLAC + cld + + testb $3, CS-ORIG_RAX+8(%rsp) + jz 1f + SWAPGS + + /* + * Switch to the thread stack. The IRET frame and orig_ax are + * on the stack, as well as the return address. RDI..R12 are + * not (yet) on the stack and space has not (yet) been + * allocated for them. + */ pushq %rdi + /* Need to switch before accessing the thread stack. */ SWITCH_TO_KERNEL_CR3 scratch_reg=%rdi movq %rsp, %rdi movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp - UNWIND_HINT sp_offset=16 sp_reg=ORC_REG_DI + + /* + * We have RDI, return address, and orig_ax on the stack on + * top of the IRET frame. That means offset=24 + */ + UNWIND_HINT_IRET_REGS base=%rdi offset=24 pushq 7*8(%rdi) /* regs->ss */ pushq 6*8(%rdi) /* regs->rsp */ @@ -560,25 +591,6 @@ END(irq_entries_start) UNWIND_HINT_FUNC movq (%rdi), %rdi -.endm - -/* - * Interrupt entry/exit. - * - * Interrupt entry points save only callee clobbered registers in fast path. - * - * Entry runs with interrupts off. - */ -/* 8(%rsp): ~(interrupt number) */ -ENTRY(interrupt_entry) - UNWIND_HINT_FUNC - ASM_CLAC - cld - - testb $3, CS-ORIG_RAX+8(%rsp) - jz 1f - SWAPGS - DO_SWITCH_TO_THREAD_STACK 1: PUSH_AND_CLEAR_REGS save_ret=1 @@ -592,7 +604,7 @@ ENTRY(interrupt_entry) * * We need to tell lockdep that IRQs are off. We can't do this until * we fix gsbase, and we should do it before enter_from_user_mode - * (which can take locks). Since TRACE_IRQS_OFF idempotent, + * (which can take locks). Since TRACE_IRQS_OFF is idempotent, * the simplest way to handle it is to just call it twice if * we enter from user mode. There's no reason to optimize this since * TRACE_IRQS_OFF is a no-op if lockdep is off. @@ -609,6 +621,9 @@ ENTRY(interrupt_entry) ret END(interrupt_entry) + +/* Interrupt entry/exit. */ + /* * The interrupt stubs push (~vector+0x80) onto the stack and * then jump to common_interrupt. @@ -878,17 +893,6 @@ apicinterrupt IRQ_WORK_VECTOR irq_work_interrupt smp_irq_work_interrupt */ #define CPU_TSS_IST(x) PER_CPU_VAR(cpu_tss_rw) + (TSS_ist + ((x) - 1) * 8) -#if defined(CONFIG_IA32_EMULATION) -/* entry_64_compat.S::entry_INT80_compat expects this to be an ASM function */ -ENTRY(switch_to_thread_stack) - UNWIND_HINT_FUNC - - DO_SWITCH_TO_THREAD_STACK - - ret -END(switch_to_thread_stack) -#endif - .macro idtentry sym do_sym has_error_code:req paranoid=0 shift_ist=-1 ENTRY(\sym) UNWIND_HINT_IRET_REGS offset=\has_error_code*8 diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S index 364ea4a207be..e811dd9c5e99 100644 --- a/arch/x86/entry/entry_64_compat.S +++ b/arch/x86/entry/entry_64_compat.S @@ -347,10 +347,23 @@ ENTRY(entry_INT80_compat) */ movl %eax, %eax + /* switch to thread stack expects orig_ax and rdi to be pushed */ pushq %rax /* pt_regs->orig_ax */ + pushq %rdi /* pt_regs->di */ + + /* Need to switch before accessing the thread stack. */ + SWITCH_TO_KERNEL_CR3 scratch_reg=%rdi + movq %rsp, %rdi + movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp + + pushq 6*8(%rdi) /* regs->ss */ + pushq 5*8(%rdi) /* regs->rsp */ + pushq 4*8(%rdi) /* regs->eflags */ + pushq 3*8(%rdi) /* regs->cs */ + pushq 2*8(%rdi) /* regs->ip */ + pushq 1*8(%rdi) /* regs->orig_ax */ - /* switch to thread stack expects orig_ax to be pushed */ - call switch_to_thread_stack + movq (%rdi), %rdi /* restore %rdi */ pushq %rdi /* pt_regs->di */ pushq %rsi /* pt_regs->si */ -- cgit v1.2.3-55-g7522 From 9fbcc57aa16424ef84cb54e0d9db3221763de88a Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Tue, 20 Feb 2018 11:37:53 -0600 Subject: extable: Make init_kernel_text() global Convert init_kernel_text() to a global function and use it in a few places instead of manually comparing _sinittext and _einittext. Note that kallsyms.h has a very similar function called is_kernel_inittext(), but its end check is inclusive. I'm not sure whether that's intentional behavior, so I didn't touch it. Suggested-by: Jason Baron Signed-off-by: Josh Poimboeuf Acked-by: Peter Zijlstra Acked-by: Steven Rostedt (VMware) Cc: Borislav Petkov Cc: Linus Torvalds Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/4335d02be8d45ca7d265d2f174251d0b7ee6c5fd.1519051220.git.jpoimboe@redhat.com Signed-off-by: Ingo Molnar --- arch/x86/kernel/unwind_orc.c | 3 +-- include/linux/kernel.h | 1 + kernel/extable.c | 2 +- kernel/jump_label.c | 4 +--- 4 files changed, 4 insertions(+), 6 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c index 1f9188f5357c..feb28fee6cea 100644 --- a/arch/x86/kernel/unwind_orc.c +++ b/arch/x86/kernel/unwind_orc.c @@ -5,7 +5,6 @@ #include #include #include -#include #define orc_warn(fmt, ...) \ printk_deferred_once(KERN_WARNING pr_fmt("WARNING: " fmt), ##__VA_ARGS__) @@ -148,7 +147,7 @@ static struct orc_entry *orc_find(unsigned long ip) } /* vmlinux .init slow lookup: */ - if (ip >= (unsigned long)_sinittext && ip < (unsigned long)_einittext) + if (init_kernel_text(ip)) return __orc_find(__start_orc_unwind_ip, __start_orc_unwind, __stop_orc_unwind_ip - __start_orc_unwind_ip, ip); diff --git a/include/linux/kernel.h b/include/linux/kernel.h index ce51455e2adf..3fd291503576 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -472,6 +472,7 @@ extern bool parse_option_str(const char *str, const char *option); extern char *next_arg(char *args, char **param, char **val); extern int core_kernel_text(unsigned long addr); +extern int init_kernel_text(unsigned long addr); extern int core_kernel_data(unsigned long addr); extern int __kernel_text_address(unsigned long addr); extern int kernel_text_address(unsigned long addr); diff --git a/kernel/extable.c b/kernel/extable.c index a17fdb63dc3e..6a5b61ebc66c 100644 --- a/kernel/extable.c +++ b/kernel/extable.c @@ -64,7 +64,7 @@ const struct exception_table_entry *search_exception_tables(unsigned long addr) return e; } -static inline int init_kernel_text(unsigned long addr) +int init_kernel_text(unsigned long addr) { if (addr >= (unsigned long)_sinittext && addr < (unsigned long)_einittext) diff --git a/kernel/jump_label.c b/kernel/jump_label.c index b2f0b479191b..52a0a7af8640 100644 --- a/kernel/jump_label.c +++ b/kernel/jump_label.c @@ -16,7 +16,6 @@ #include #include #include -#include #ifdef HAVE_JUMP_LABEL @@ -429,8 +428,7 @@ void __init jump_label_invalidate_init(void) struct jump_entry *iter; for (iter = iter_start; iter < iter_stop; iter++) { - if (iter->code >= (unsigned long)_sinittext && - iter->code < (unsigned long)_einittext) + if (init_kernel_text(iter->code)) iter->code = 0; } } -- cgit v1.2.3-55-g7522 From 0ca7d5baa1787e5f2a7abd6bfca3303b1bbb48ac Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Tue, 20 Feb 2018 20:42:14 -0600 Subject: x86/entry/64: Simplify ENCODE_FRAME_POINTER On 64-bit, the stack pointer is always aligned on interrupt, so instead of setting the LSB of the pt_regs address, we can just add 1 to it. Suggested-by: Linus Torvalds Signed-off-by: Josh Poimboeuf Cc: Andrew Lutomirski Cc: Brian Gerst Cc: Dan Williams Cc: Dominik Brodowski Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20180221024214.lhl5jfgw33c4vz3m@treble Signed-off-by: Ingo Molnar --- arch/x86/entry/calling.h | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) (limited to 'arch') diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h index 5d10b7a85cad..be63330c5511 100644 --- a/arch/x86/entry/calling.h +++ b/arch/x86/entry/calling.h @@ -181,12 +181,7 @@ For 32-bit we have the following conventions - kernel is built with */ .macro ENCODE_FRAME_POINTER ptregs_offset=0 #ifdef CONFIG_FRAME_POINTER - .if \ptregs_offset - leaq \ptregs_offset(%rsp), %rbp - .else - mov %rsp, %rbp - .endif - orq $0x1, %rbp + leaq 1+\ptregs_offset(%rsp), %rbp #endif .endm -- cgit v1.2.3-55-g7522 From d5028ba8ee5a18c9d0bb926d883c28b370f89009 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 6 Feb 2018 09:46:13 +0100 Subject: objtool, retpolines: Integrate objtool with retpoline support more closely Disable retpoline validation in objtool if your compiler sucks, and otherwise select the validation stuff for CONFIG_RETPOLINE=y (most builds would already have it set due to ORC). Signed-off-by: Peter Zijlstra (Intel) Acked-by: Thomas Gleixner Cc: Andy Lutomirski Cc: Arjan van de Ven Cc: Borislav Petkov Cc: Dan Williams Cc: Dave Hansen Cc: David Woodhouse Cc: Greg Kroah-Hartman Cc: Josh Poimboeuf Cc: Linus Torvalds Cc: Peter Zijlstra Signed-off-by: Ingo Molnar --- Makefile | 5 +++++ arch/x86/Kconfig | 1 + arch/x86/Makefile | 10 +++------- scripts/Makefile.build | 2 ++ 4 files changed, 11 insertions(+), 7 deletions(-) (limited to 'arch') diff --git a/Makefile b/Makefile index 79ad2bfa24b6..3dfce4d2f25d 100644 --- a/Makefile +++ b/Makefile @@ -489,6 +489,11 @@ KBUILD_CFLAGS += $(CLANG_TARGET) $(CLANG_GCC_TC) KBUILD_AFLAGS += $(CLANG_TARGET) $(CLANG_GCC_TC) endif +RETPOLINE_CFLAGS_GCC := -mindirect-branch=thunk-extern -mindirect-branch-register +RETPOLINE_CFLAGS_CLANG := -mretpoline-external-thunk +RETPOLINE_CFLAGS := $(call cc-option,$(RETPOLINE_CFLAGS_GCC),$(call cc-option,$(RETPOLINE_CFLAGS_CLANG))) +export RETPOLINE_CFLAGS + ifeq ($(config-targets),1) # =========================================================================== # *config targets only - make sure prerequisites are updated, and descend diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 63bf349b2b24..c1aed6c0e413 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -436,6 +436,7 @@ config GOLDFISH config RETPOLINE bool "Avoid speculative indirect branches in kernel" default y + select STACK_VALIDATION if HAVE_STACK_VALIDATION help Compile kernel with the retpoline compiler options to guard against kernel-to-user data leaks by avoiding speculative indirect diff --git a/arch/x86/Makefile b/arch/x86/Makefile index dbc7d0ed2eaa..498c1b812300 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -232,13 +232,9 @@ KBUILD_CFLAGS += -fno-asynchronous-unwind-tables # Avoid indirect branches in kernel to deal with Spectre ifdef CONFIG_RETPOLINE - RETPOLINE_CFLAGS_GCC := -mindirect-branch=thunk-extern -mindirect-branch-register - RETPOLINE_CFLAGS_CLANG := -mretpoline-external-thunk - - RETPOLINE_CFLAGS += $(call cc-option,$(RETPOLINE_CFLAGS_GCC),$(call cc-option,$(RETPOLINE_CFLAGS_CLANG))) - ifneq ($(RETPOLINE_CFLAGS),) - KBUILD_CFLAGS += $(RETPOLINE_CFLAGS) -DRETPOLINE - endif +ifneq ($(RETPOLINE_CFLAGS),) + KBUILD_CFLAGS += $(RETPOLINE_CFLAGS) -DRETPOLINE +endif endif archscripts: scripts_basic diff --git a/scripts/Makefile.build b/scripts/Makefile.build index ce0fc4dd68c6..4f2b25d43ec9 100644 --- a/scripts/Makefile.build +++ b/scripts/Makefile.build @@ -267,8 +267,10 @@ else objtool_args += $(call cc-ifversion, -lt, 0405, --no-unreachable) endif ifdef CONFIG_RETPOLINE +ifneq ($(RETPOLINE_CFLAGS),) objtool_args += --retpoline endif +endif ifdef CONFIG_MODVERSIONS -- cgit v1.2.3-55-g7522 From 173a3efd3edb2ef6ef07471397c5f542a360e9c1 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 21 Feb 2018 14:45:54 -0800 Subject: bug.h: work around GCC PR82365 in BUG() Looking at functions with large stack frames across all architectures led me discovering that BUG() suffers from the same problem as fortify_panic(), which I've added a workaround for already. In short, variables that go out of scope by calling a noreturn function or __builtin_unreachable() keep using stack space in functions afterwards. A workaround that was identified is to insert an empty assembler statement just before calling the function that doesn't return. I'm adding a macro "barrier_before_unreachable()" to document this, and insert calls to that in all instances of BUG() that currently suffer from this problem. The files that saw the largest change from this had these frame sizes before, and much less with my patch: fs/ext4/inode.c:82:1: warning: the frame size of 1672 bytes is larger than 800 bytes [-Wframe-larger-than=] fs/ext4/namei.c:434:1: warning: the frame size of 904 bytes is larger than 800 bytes [-Wframe-larger-than=] fs/ext4/super.c:2279:1: warning: the frame size of 1160 bytes is larger than 800 bytes [-Wframe-larger-than=] fs/ext4/xattr.c:146:1: warning: the frame size of 1168 bytes is larger than 800 bytes [-Wframe-larger-than=] fs/f2fs/inode.c:152:1: warning: the frame size of 1424 bytes is larger than 800 bytes [-Wframe-larger-than=] net/netfilter/ipvs/ip_vs_core.c:1195:1: warning: the frame size of 1068 bytes is larger than 800 bytes [-Wframe-larger-than=] net/netfilter/ipvs/ip_vs_core.c:395:1: warning: the frame size of 1084 bytes is larger than 800 bytes [-Wframe-larger-than=] net/netfilter/ipvs/ip_vs_ftp.c:298:1: warning: the frame size of 928 bytes is larger than 800 bytes [-Wframe-larger-than=] net/netfilter/ipvs/ip_vs_ftp.c:418:1: warning: the frame size of 908 bytes is larger than 800 bytes [-Wframe-larger-than=] net/netfilter/ipvs/ip_vs_lblcr.c:718:1: warning: the frame size of 960 bytes is larger than 800 bytes [-Wframe-larger-than=] drivers/net/xen-netback/netback.c:1500:1: warning: the frame size of 1088 bytes is larger than 800 bytes [-Wframe-larger-than=] In case of ARC and CRIS, it turns out that the BUG() implementation actually does return (or at least the compiler thinks it does), resulting in lots of warnings about uninitialized variable use and leaving noreturn functions, such as: block/cfq-iosched.c: In function 'cfq_async_queue_prio': block/cfq-iosched.c:3804:1: error: control reaches end of non-void function [-Werror=return-type] include/linux/dmaengine.h: In function 'dma_maxpq': include/linux/dmaengine.h:1123:1: error: control reaches end of non-void function [-Werror=return-type] This makes them call __builtin_trap() instead, which should normally dump the stack and kill the current process, like some of the other architectures already do. I tried adding barrier_before_unreachable() to panic() and fortify_panic() as well, but that had very little effect, so I'm not submitting that patch. Vineet said: : For ARC, it is double win. : : 1. Fixes 3 -Wreturn-type warnings : : | ../net/core/ethtool.c:311:1: warning: control reaches end of non-void function : [-Wreturn-type] : | ../kernel/sched/core.c:3246:1: warning: control reaches end of non-void function : [-Wreturn-type] : | ../include/linux/sunrpc/svc_xprt.h:180:1: warning: control reaches end of : non-void function [-Wreturn-type] : : 2. bloat-o-meter reports code size improvements as gcc elides the : generated code for stack return. Link: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=82365 Link: http://lkml.kernel.org/r/20171219114112.939391-1-arnd@arndb.de Signed-off-by: Arnd Bergmann Acked-by: Vineet Gupta [arch/arc] Tested-by: Vineet Gupta [arch/arc] Cc: Mikael Starvik Cc: Jesper Nilsson Cc: Tony Luck Cc: Fenghua Yu Cc: Geert Uytterhoeven Cc: "David S. Miller" Cc: Christopher Li Cc: Thomas Gleixner Cc: Peter Zijlstra Cc: Kees Cook Cc: Ingo Molnar Cc: Josh Poimboeuf Cc: Will Deacon Cc: "Steven Rostedt (VMware)" Cc: Mark Rutland Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/arc/include/asm/bug.h | 3 ++- arch/cris/include/arch-v10/arch/bug.h | 11 +++++++++-- arch/ia64/include/asm/bug.h | 6 +++++- arch/m68k/include/asm/bug.h | 3 +++ arch/sparc/include/asm/bug.h | 6 +++++- include/asm-generic/bug.h | 1 + include/linux/compiler-gcc.h | 15 ++++++++++++++- include/linux/compiler.h | 5 +++++ 8 files changed, 44 insertions(+), 6 deletions(-) (limited to 'arch') diff --git a/arch/arc/include/asm/bug.h b/arch/arc/include/asm/bug.h index ea022d47896c..21ec82466d62 100644 --- a/arch/arc/include/asm/bug.h +++ b/arch/arc/include/asm/bug.h @@ -23,7 +23,8 @@ void die(const char *str, struct pt_regs *regs, unsigned long address); #define BUG() do { \ pr_warn("BUG: failure at %s:%d/%s()!\n", __FILE__, __LINE__, __func__); \ - dump_stack(); \ + barrier_before_unreachable(); \ + __builtin_trap(); \ } while (0) #define HAVE_ARCH_BUG diff --git a/arch/cris/include/arch-v10/arch/bug.h b/arch/cris/include/arch-v10/arch/bug.h index 905afeacfedf..06da9d49152a 100644 --- a/arch/cris/include/arch-v10/arch/bug.h +++ b/arch/cris/include/arch-v10/arch/bug.h @@ -44,18 +44,25 @@ struct bug_frame { * not be used like this with newer versions of gcc. */ #define BUG() \ +do { \ __asm__ __volatile__ ("clear.d [" __stringify(BUG_MAGIC) "]\n\t"\ "movu.w " __stringify(__LINE__) ",$r0\n\t"\ "jump 0f\n\t" \ ".section .rodata\n" \ "0:\t.string \"" __FILE__ "\"\n\t" \ - ".previous") + ".previous"); \ + unreachable(); \ +} while (0) #endif #else /* This just causes an oops. */ -#define BUG() (*(int *)0 = 0) +#define BUG() \ +do { \ + barrier_before_unreachable(); \ + __builtin_trap(); \ +} while (0) #endif diff --git a/arch/ia64/include/asm/bug.h b/arch/ia64/include/asm/bug.h index bd3eeb8d1cfa..66b37a532765 100644 --- a/arch/ia64/include/asm/bug.h +++ b/arch/ia64/include/asm/bug.h @@ -4,7 +4,11 @@ #ifdef CONFIG_BUG #define ia64_abort() __builtin_trap() -#define BUG() do { printk("kernel BUG at %s:%d!\n", __FILE__, __LINE__); ia64_abort(); } while (0) +#define BUG() do { \ + printk("kernel BUG at %s:%d!\n", __FILE__, __LINE__); \ + barrier_before_unreachable(); \ + ia64_abort(); \ +} while (0) /* should this BUG be made generic? */ #define HAVE_ARCH_BUG diff --git a/arch/m68k/include/asm/bug.h b/arch/m68k/include/asm/bug.h index b7e2bf1ba4a6..275dca1435bf 100644 --- a/arch/m68k/include/asm/bug.h +++ b/arch/m68k/include/asm/bug.h @@ -8,16 +8,19 @@ #ifndef CONFIG_SUN3 #define BUG() do { \ pr_crit("kernel BUG at %s:%d!\n", __FILE__, __LINE__); \ + barrier_before_unreachable(); \ __builtin_trap(); \ } while (0) #else #define BUG() do { \ pr_crit("kernel BUG at %s:%d!\n", __FILE__, __LINE__); \ + barrier_before_unreachable(); \ panic("BUG!"); \ } while (0) #endif #else #define BUG() do { \ + barrier_before_unreachable(); \ __builtin_trap(); \ } while (0) #endif diff --git a/arch/sparc/include/asm/bug.h b/arch/sparc/include/asm/bug.h index 6f17528356b2..ea53e418f6c0 100644 --- a/arch/sparc/include/asm/bug.h +++ b/arch/sparc/include/asm/bug.h @@ -9,10 +9,14 @@ void do_BUG(const char *file, int line); #define BUG() do { \ do_BUG(__FILE__, __LINE__); \ + barrier_before_unreachable(); \ __builtin_trap(); \ } while (0) #else -#define BUG() __builtin_trap() +#define BUG() do { \ + barrier_before_unreachable(); \ + __builtin_trap(); \ +} while (0) #endif #define HAVE_ARCH_BUG diff --git a/include/asm-generic/bug.h b/include/asm-generic/bug.h index 963b755d19b0..a7613e1b0c87 100644 --- a/include/asm-generic/bug.h +++ b/include/asm-generic/bug.h @@ -52,6 +52,7 @@ struct bug_entry { #ifndef HAVE_ARCH_BUG #define BUG() do { \ printk("BUG: failure at %s:%d/%s()!\n", __FILE__, __LINE__, __func__); \ + barrier_before_unreachable(); \ panic("BUG!"); \ } while (0) #endif diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index 73bc63e0a1c4..901c1ccb3374 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -207,6 +207,15 @@ #endif #endif +/* + * calling noreturn functions, __builtin_unreachable() and __builtin_trap() + * confuse the stack allocation in gcc, leading to overly large stack + * frames, see https://gcc.gnu.org/bugzilla/show_bug.cgi?id=82365 + * + * Adding an empty inline assembly before it works around the problem + */ +#define barrier_before_unreachable() asm volatile("") + /* * Mark a position in code as unreachable. This can be used to * suppress control flow warnings after asm blocks that transfer @@ -217,7 +226,11 @@ * unreleased. Really, we need to have autoconf for the kernel. */ #define unreachable() \ - do { annotate_unreachable(); __builtin_unreachable(); } while (0) + do { \ + annotate_unreachable(); \ + barrier_before_unreachable(); \ + __builtin_unreachable(); \ + } while (0) /* Mark a function definition as prohibited from being cloned. */ #define __noclone __attribute__((__noclone__, __optimize__("no-tracer"))) diff --git a/include/linux/compiler.h b/include/linux/compiler.h index e835fc0423ec..ab4711c63601 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -86,6 +86,11 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, # define barrier_data(ptr) barrier() #endif +/* workaround for GCC PR82365 if needed */ +#ifndef barrier_before_unreachable +# define barrier_before_unreachable() do { } while (0) +#endif + /* Unreachable code */ #ifdef CONFIG_STACK_VALIDATION /* -- cgit v1.2.3-55-g7522 From 5539d31a04b3b9ac5f55edb766f1d21de683fad1 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Wed, 21 Feb 2018 22:54:37 +1100 Subject: powerpc/pseries: Fix duplicate firmware feature for DRC_INFO We had a mid-air collision between two new firmware features, DRMEM_V2 and DRC_INFO, and they ended up with the same value. No one's actually reported any problems, presumably because the new firmware that supports both properties is not widely available, and the two properties tend to be enabled together. Still if we ever had one enabled but not the other, the bugs that could result are many and varied. So fix it. Fixes: 3f38000eda48 ("powerpc/firmware: Add definitions for new drc-info firmware feature") Signed-off-by: Michael Ellerman Reviewed-by: Tyrel Datwyler --- arch/powerpc/include/asm/firmware.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/powerpc/include/asm/firmware.h b/arch/powerpc/include/asm/firmware.h index 511acfd7ab0d..535add3f7791 100644 --- a/arch/powerpc/include/asm/firmware.h +++ b/arch/powerpc/include/asm/firmware.h @@ -52,7 +52,7 @@ #define FW_FEATURE_TYPE1_AFFINITY ASM_CONST(0x0000000100000000) #define FW_FEATURE_PRRN ASM_CONST(0x0000000200000000) #define FW_FEATURE_DRMEM_V2 ASM_CONST(0x0000000400000000) -#define FW_FEATURE_DRC_INFO ASM_CONST(0x0000000400000000) +#define FW_FEATURE_DRC_INFO ASM_CONST(0x0000000800000000) #ifndef __ASSEMBLY__ -- cgit v1.2.3-55-g7522 From c7a3275e0f9e461bb8942132aa6914aae59e7103 Mon Sep 17 00:00:00 2001 From: Michael Bringmann Date: Tue, 13 Feb 2018 14:02:53 -0600 Subject: powerpc/pseries: Revert support for ibm,drc-info devtree property This reverts commit 02ef6dd8109b581343ebeb1c4c973513682535d6. The earlier patch tried to enable support for a new property "ibm,drc-info" on powerpc systems. Unfortunately, some errors in the associated patch set break things in some of the DLPAR operations. In particular when attempting to hot-add a new CPU or set of CPUs, the original patch failed to properly calculate the available resources, and aborted the operation. In addition, the original set missed several opportunities to compress and reuse common code. As the associated patch set was meant to provide an optimization of storage and performance of a set of device-tree properties for future systems with large amounts of resources, reverting just restores the previous behavior for existing systems. It seems unnecessary to enable this feature and introduce the consequent problems in the field that it will cause at this time, so please revert it for now until testing of the corrections are finished properly. Fixes: 02ef6dd8109b ("powerpc: Enable support for ibm,drc-info devtree property") Signed-off-by: Michael W. Bringmann Signed-off-by: Michael Ellerman --- arch/powerpc/kernel/prom_init.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index adf044daafd7..d22c41c26bb3 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -874,7 +874,7 @@ struct ibm_arch_vec __cacheline_aligned ibm_architecture_vec = { .mmu = 0, .hash_ext = 0, .radix_ext = 0, - .byte22 = OV5_FEAT(OV5_DRC_INFO), + .byte22 = 0, }, /* option vector 6: IBM PAPR hints */ -- cgit v1.2.3-55-g7522 From 083b20907185b076f21c265b30fe5b5f24c03d8c Mon Sep 17 00:00:00 2001 From: Mark Lord Date: Tue, 20 Feb 2018 14:49:20 -0500 Subject: powerpc/bpf/jit: Fix 32-bit JIT for seccomp_data access I am using SECCOMP to filter syscalls on a ppc32 platform, and noticed that the JIT compiler was failing on the BPF even though the interpreter was working fine. The issue was that the compiler was missing one of the instructions used by SECCOMP, so here is a patch to enable JIT for that instruction. Fixes: eb84bab0fb38 ("ppc: Kconfig: Enable BPF JIT on ppc32") Signed-off-by: Mark Lord Acked-by: Naveen N. Rao Signed-off-by: Michael Ellerman --- arch/powerpc/net/bpf_jit_comp.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'arch') diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c index 872d1f6dd11e..a9636d8cba15 100644 --- a/arch/powerpc/net/bpf_jit_comp.c +++ b/arch/powerpc/net/bpf_jit_comp.c @@ -327,6 +327,9 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, len) != 4); PPC_LWZ_OFFS(r_A, r_skb, offsetof(struct sk_buff, len)); break; + case BPF_LDX | BPF_W | BPF_ABS: /* A = *((u32 *)(seccomp_data + K)); */ + PPC_LWZ_OFFS(r_A, r_skb, K); + break; case BPF_LDX | BPF_W | BPF_LEN: /* X = skb->len; */ PPC_LWZ_OFFS(r_X, r_skb, offsetof(struct sk_buff, len)); break; -- cgit v1.2.3-55-g7522 From dc24b7b49a53c7ee5502c877b133558acec0b3f8 Mon Sep 17 00:00:00 2001 From: Hendrik Brueckner Date: Mon, 19 Feb 2018 11:27:09 +0100 Subject: s390/clean-up: use CFI_* macros in entry.S Commit f19fbd5ed642 ("s390: introduce execute-trampolines for branches") introduces .cfi_* assembler directives. Instead of using the directives directly, use the macros from asm/dwarf.h. This also ensures that the dwarf debug information are created in the .debug_frame section. Fixes: f19fbd5ed642 ("s390: introduce execute-trampolines for branches") Signed-off-by: Hendrik Brueckner Signed-off-by: Martin Schwidefsky --- arch/s390/kernel/entry.S | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'arch') diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S index 13a133a6015c..9ec728fa832c 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -14,6 +14,7 @@ #include #include #include +#include #include #include #include @@ -230,7 +231,7 @@ _PIF_WORK = (_PIF_PER_TRAP | _PIF_SYSCALL_RESTART) .hidden \name .type \name,@function \name: - .cfi_startproc + CFI_STARTPROC #ifdef CONFIG_HAVE_MARCH_Z10_FEATURES exrl 0,0f #else @@ -239,7 +240,7 @@ _PIF_WORK = (_PIF_PER_TRAP | _PIF_SYSCALL_RESTART) #endif j . 0: br \reg - .cfi_endproc + CFI_ENDPROC .endm GEN_BR_THUNK __s390x_indirect_jump_r1use_r9,%r9,%r1 -- cgit v1.2.3-55-g7522 From ed7158bae41044ff696e9aafd5ada46d391a5a2e Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Thu, 22 Feb 2018 10:54:55 +0100 Subject: treewide/trivial: Remove ';;$' typo noise On lkml suggestions were made to split up such trivial typo fixes into per subsystem patches: --- a/arch/x86/boot/compressed/eboot.c +++ b/arch/x86/boot/compressed/eboot.c @@ -439,7 +439,7 @@ setup_uga32(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; - u32 *handles = (u32 *)uga_handle;; + u32 *handles = (u32 *)uga_handle; efi_status_t status = EFI_INVALID_PARAMETER; int i; This patch is the result of the following script: $ sed -i 's/;;$/;/g' $(git grep -E ';;$' | grep "\.[ch]:" | grep -vwE 'for|ia64' | cut -d: -f1 | sort | uniq) ... followed by manual review to make sure it's all good. Splitting this up is just crazy talk, let's get over with this and just do it. Reported-by: Pavel Machek Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar --- arch/arc/kernel/setup.c | 2 +- arch/arc/kernel/unwind.c | 2 +- arch/arm/kernel/time.c | 2 +- arch/arm64/kernel/ptrace.c | 2 +- arch/powerpc/kvm/book3s_xive.c | 2 +- arch/powerpc/platforms/powernv/pci-ioda.c | 2 +- arch/x86/boot/compressed/eboot.c | 4 ++-- block/sed-opal.c | 2 +- drivers/clocksource/mips-gic-timer.c | 4 ++-- drivers/clocksource/timer-sun5i.c | 2 +- drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c | 2 +- drivers/gpu/drm/amd/powerplay/amd_powerplay.c | 2 +- drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.c | 2 +- drivers/gpu/drm/scheduler/gpu_scheduler.c | 2 +- drivers/iommu/intel-svm.c | 2 +- drivers/md/raid1.c | 2 +- drivers/soc/imx/gpc.c | 2 +- 17 files changed, 19 insertions(+), 19 deletions(-) (limited to 'arch') diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c index 9d27331fe69a..ec12fe1c2f07 100644 --- a/arch/arc/kernel/setup.c +++ b/arch/arc/kernel/setup.c @@ -373,7 +373,7 @@ static void arc_chk_core_config(void) { struct cpuinfo_arc *cpu = &cpuinfo_arc700[smp_processor_id()]; int saved = 0, present = 0; - char *opt_nm = NULL;; + char *opt_nm = NULL; if (!cpu->extn.timer0) panic("Timer0 is not present!\n"); diff --git a/arch/arc/kernel/unwind.c b/arch/arc/kernel/unwind.c index 333daab7def0..183391d4d33a 100644 --- a/arch/arc/kernel/unwind.c +++ b/arch/arc/kernel/unwind.c @@ -366,7 +366,7 @@ static void init_unwind_hdr(struct unwind_table *table, return; ret_err: - panic("Attention !!! Dwarf FDE parsing errors\n");; + panic("Attention !!! Dwarf FDE parsing errors\n"); } #ifdef CONFIG_MODULES diff --git a/arch/arm/kernel/time.c b/arch/arm/kernel/time.c index 629f8e9981f1..cf2701cb0de8 100644 --- a/arch/arm/kernel/time.c +++ b/arch/arm/kernel/time.c @@ -83,7 +83,7 @@ static void dummy_clock_access(struct timespec64 *ts) } static clock_access_fn __read_persistent_clock = dummy_clock_access; -static clock_access_fn __read_boot_clock = dummy_clock_access;; +static clock_access_fn __read_boot_clock = dummy_clock_access; void read_persistent_clock64(struct timespec64 *ts) { diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index 6618036ae6d4..9ae31f7e2243 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -1419,7 +1419,7 @@ static int compat_ptrace_hbp_get(unsigned int note_type, u64 addr = 0; u32 ctrl = 0; - int err, idx = compat_ptrace_hbp_num_to_idx(num);; + int err, idx = compat_ptrace_hbp_num_to_idx(num); if (num & 1) { err = ptrace_hbp_get_addr(note_type, tsk, idx, &addr); diff --git a/arch/powerpc/kvm/book3s_xive.c b/arch/powerpc/kvm/book3s_xive.c index f0f5cd4d2fe7..f9818d7d3381 100644 --- a/arch/powerpc/kvm/book3s_xive.c +++ b/arch/powerpc/kvm/book3s_xive.c @@ -188,7 +188,7 @@ static int xive_provision_queue(struct kvm_vcpu *vcpu, u8 prio) if (!qpage) { pr_err("Failed to allocate queue %d for VCPU %d\n", prio, xc->server_num); - return -ENOMEM;; + return -ENOMEM; } memset(qpage, 0, 1 << xive->q_order); diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index 496e47696ed0..a6c92c78c9b2 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -1854,7 +1854,7 @@ static int pnv_pci_ioda_dma_set_mask(struct pci_dev *pdev, u64 dma_mask) s64 rc; if (WARN_ON(!pdn || pdn->pe_number == IODA_INVALID_PE)) - return -ENODEV;; + return -ENODEV; pe = &phb->ioda.pe_array[pdn->pe_number]; if (pe->tce_bypass_enabled) { diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c index 353e20c3f114..886a9115af62 100644 --- a/arch/x86/boot/compressed/eboot.c +++ b/arch/x86/boot/compressed/eboot.c @@ -439,7 +439,7 @@ setup_uga32(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; - u32 *handles = (u32 *)uga_handle;; + u32 *handles = (u32 *)uga_handle; efi_status_t status = EFI_INVALID_PARAMETER; int i; @@ -484,7 +484,7 @@ 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;; + u64 *handles = (u64 *)uga_handle; efi_status_t status = EFI_INVALID_PARAMETER; int i; diff --git a/block/sed-opal.c b/block/sed-opal.c index 9ed51d0c6b1d..e4929eec547f 100644 --- a/block/sed-opal.c +++ b/block/sed-opal.c @@ -490,7 +490,7 @@ static int opal_discovery0_end(struct opal_dev *dev) if (!found_com_id) { pr_debug("Could not find OPAL comid for device. Returning early\n"); - return -EOPNOTSUPP;; + return -EOPNOTSUPP; } dev->comid = comid; diff --git a/drivers/clocksource/mips-gic-timer.c b/drivers/clocksource/mips-gic-timer.c index a04808a21d4e..65e18c86d9b9 100644 --- a/drivers/clocksource/mips-gic-timer.c +++ b/drivers/clocksource/mips-gic-timer.c @@ -205,12 +205,12 @@ static int __init gic_clocksource_of_init(struct device_node *node) } else if (of_property_read_u32(node, "clock-frequency", &gic_frequency)) { pr_err("GIC frequency not specified.\n"); - return -EINVAL;; + return -EINVAL; } gic_timer_irq = irq_of_parse_and_map(node, 0); if (!gic_timer_irq) { pr_err("GIC timer IRQ not specified.\n"); - return -EINVAL;; + return -EINVAL; } ret = __gic_clocksource_init(); diff --git a/drivers/clocksource/timer-sun5i.c b/drivers/clocksource/timer-sun5i.c index 2a3fe83ec337..3b56ea3f52af 100644 --- a/drivers/clocksource/timer-sun5i.c +++ b/drivers/clocksource/timer-sun5i.c @@ -334,7 +334,7 @@ static int __init sun5i_timer_init(struct device_node *node) timer_base = of_io_request_and_map(node, 0, of_node_full_name(node)); if (IS_ERR(timer_base)) { pr_err("Can't map registers\n"); - return PTR_ERR(timer_base);; + return PTR_ERR(timer_base); } irq = irq_of_parse_and_map(node, 0); diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c index 61e8c3e02d16..33d91e4474ea 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c @@ -718,7 +718,7 @@ static enum link_training_result perform_channel_equalization_sequence( uint32_t retries_ch_eq; enum dc_lane_count lane_count = lt_settings->link_settings.lane_count; union lane_align_status_updated dpcd_lane_status_updated = {{0}}; - union lane_status dpcd_lane_status[LANE_COUNT_DP_MAX] = {{{0}}};; + union lane_status dpcd_lane_status[LANE_COUNT_DP_MAX] = {{{0}}}; hw_tr_pattern = get_supported_tp(link); diff --git a/drivers/gpu/drm/amd/powerplay/amd_powerplay.c b/drivers/gpu/drm/amd/powerplay/amd_powerplay.c index 4c3223a4d62b..adb6e7b9280c 100644 --- a/drivers/gpu/drm/amd/powerplay/amd_powerplay.c +++ b/drivers/gpu/drm/amd/powerplay/amd_powerplay.c @@ -162,7 +162,7 @@ static int pp_hw_init(void *handle) if(hwmgr->smumgr_funcs->start_smu(pp_handle->hwmgr)) { pr_err("smc start failed\n"); hwmgr->smumgr_funcs->smu_fini(pp_handle->hwmgr); - return -EINVAL;; + return -EINVAL; } if (ret == PP_DPM_DISABLED) goto exit; diff --git a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.c b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.c index 3e9bba4d6624..6d8e3a9a6fc0 100644 --- a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.c +++ b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.c @@ -680,7 +680,7 @@ struct msm_kms *mdp5_kms_init(struct drm_device *dev) } else { dev_info(&pdev->dev, "no iommu, fallback to phys contig buffers for scanout\n"); - aspace = NULL;; + aspace = NULL; } pm_runtime_put_sync(&pdev->dev); diff --git a/drivers/gpu/drm/scheduler/gpu_scheduler.c b/drivers/gpu/drm/scheduler/gpu_scheduler.c index 2c18996d59c5..0d95888ccc3e 100644 --- a/drivers/gpu/drm/scheduler/gpu_scheduler.c +++ b/drivers/gpu/drm/scheduler/gpu_scheduler.c @@ -461,7 +461,7 @@ void drm_sched_hw_job_reset(struct drm_gpu_scheduler *sched, struct drm_sched_jo { struct drm_sched_job *s_job; struct drm_sched_entity *entity, *tmp; - int i;; + int i; spin_lock(&sched->job_list_lock); list_for_each_entry_reverse(s_job, &sched->ring_mirror_list, node) { diff --git a/drivers/iommu/intel-svm.c b/drivers/iommu/intel-svm.c index 35a408d0ae4f..99bc9bd64b9e 100644 --- a/drivers/iommu/intel-svm.c +++ b/drivers/iommu/intel-svm.c @@ -205,7 +205,7 @@ static void intel_flush_svm_range_dev (struct intel_svm *svm, struct intel_svm_d * for example, an "address" value of 0x12345f000 will * flush from 0x123440000 to 0x12347ffff (256KiB). */ unsigned long last = address + ((unsigned long)(pages - 1) << VTD_PAGE_SHIFT); - unsigned long mask = __rounddown_pow_of_two(address ^ last);; + unsigned long mask = __rounddown_pow_of_two(address ^ last); desc.high = QI_DEV_EIOTLB_ADDR((address & ~mask) | (mask - 1)) | QI_DEV_EIOTLB_SIZE; } else { diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index b2eae332e1a2..f978eddc7a21 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -1108,7 +1108,7 @@ static void alloc_behind_master_bio(struct r1bio *r1_bio, bio_copy_data(behind_bio, bio); skip_copy: - r1_bio->behind_master_bio = behind_bio;; + r1_bio->behind_master_bio = behind_bio; set_bit(R1BIO_BehindIO, &r1_bio->state); return; diff --git a/drivers/soc/imx/gpc.c b/drivers/soc/imx/gpc.c index 53f7275d6cbd..cfb42f5eccb2 100644 --- a/drivers/soc/imx/gpc.c +++ b/drivers/soc/imx/gpc.c @@ -348,7 +348,7 @@ static int imx_gpc_old_dt_init(struct device *dev, struct regmap *regmap, if (i == 1) { domain->supply = devm_regulator_get(dev, "pu"); if (IS_ERR(domain->supply)) - return PTR_ERR(domain->supply);; + return PTR_ERR(domain->supply); ret = imx_pgc_get_clocks(dev, domain); if (ret) -- cgit v1.2.3-55-g7522 From 15122ee2c515a253b0c66a3e618bc7ebe35105eb Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Wed, 21 Feb 2018 12:59:27 +0000 Subject: arm64: Enforce BBM for huge IO/VMAP mappings ioremap_page_range doesn't honour break-before-make and attempts to put down huge mappings (using p*d_set_huge) over the top of pre-existing table entries. This leads to us leaking page table memory and also gives rise to TLB conflicts and spurious aborts, which have been seen in practice on Cortex-A75. Until this has been resolved, refuse to put block mappings when the existing entry is found to be present. Fixes: 324420bf91f60 ("arm64: add support for ioremap() block mappings") Reported-by: Hanjun Guo Reported-by: Lei Li Acked-by: Ard Biesheuvel Signed-off-by: Will Deacon Signed-off-by: Catalin Marinas --- arch/arm64/mm/mmu.c | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'arch') diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 3161b853f29e..84a019f55022 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -933,6 +933,11 @@ int pud_set_huge(pud_t *pudp, phys_addr_t phys, pgprot_t prot) { pgprot_t sect_prot = __pgprot(PUD_TYPE_SECT | pgprot_val(mk_sect_prot(prot))); + + /* ioremap_page_range doesn't honour BBM */ + if (pud_present(READ_ONCE(*pudp))) + return 0; + BUG_ON(phys & ~PUD_MASK); set_pud(pudp, pfn_pud(__phys_to_pfn(phys), sect_prot)); return 1; @@ -942,6 +947,11 @@ int pmd_set_huge(pmd_t *pmdp, phys_addr_t phys, pgprot_t prot) { pgprot_t sect_prot = __pgprot(PMD_TYPE_SECT | pgprot_val(mk_sect_prot(prot))); + + /* ioremap_page_range doesn't honour BBM */ + if (pmd_present(READ_ONCE(*pmdp))) + return 0; + BUG_ON(phys & ~PMD_MASK); set_pmd(pmdp, pfn_pmd(__phys_to_pfn(phys), sect_prot)); return 1; -- cgit v1.2.3-55-g7522 From d5feec04fe578c8dbd9e2e1439afc2f0af761ed4 Mon Sep 17 00:00:00 2001 From: Martin Schwidefsky Date: Thu, 22 Feb 2018 13:42:29 +0100 Subject: s390: do not bypass BPENTER for interrupt system calls The system call path can be interrupted before the switch back to the standard branch prediction with BPENTER has been done. The critical section cleanup code skips forward to .Lsysc_do_svc and bypasses the BPENTER. In this case the kernel and all subsequent code will run with the limited branch prediction. Fixes: eacf67eb9b32 ("s390: run user space and KVM guests with modified branch prediction") Signed-off-by: Martin Schwidefsky --- arch/s390/kernel/entry.S | 1 + 1 file changed, 1 insertion(+) (limited to 'arch') diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S index 9ec728fa832c..73492461c454 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -1440,6 +1440,7 @@ cleanup_critical: stg %r15,__LC_SYSTEM_TIMER 0: # update accounting time stamp mvc __LC_LAST_UPDATE_TIMER(8),__LC_SYNC_ENTER_TIMER + BPENTER __TI_flags(%r12),_TIF_ISOLATE_BP # set up saved register r11 lg %r15,__LC_KERNEL_STACK la %r9,STACK_FRAME_OVERHEAD(%r15) -- cgit v1.2.3-55-g7522 From e2c8d283c4e2f468bed1bcfedb80b670b1bc8ab1 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Thu, 1 Feb 2018 15:32:40 -0600 Subject: arm64: dts: cavium: fix PCI bus dtc warnings dtc recently added PCI bus checks. Fix these warnings: arch/arm64/boot/dts/cavium/thunder2-99xx.dtb: Warning (pci_bridge): Node /pci missing bus-range for PCI bridge arch/arm64/boot/dts/cavium/thunder2-99xx.dtb: Warning (unit_address_vs_reg): Node /pci has a reg or ranges property, but no unit name Signed-off-by: Rob Herring Cc: Jayachandran C Signed-off-by: Arnd Bergmann --- arch/arm64/boot/dts/cavium/thunder2-99xx.dtsi | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/arm64/boot/dts/cavium/thunder2-99xx.dtsi b/arch/arm64/boot/dts/cavium/thunder2-99xx.dtsi index 4220fbdcb24a..ff5c4c47b22b 100644 --- a/arch/arm64/boot/dts/cavium/thunder2-99xx.dtsi +++ b/arch/arm64/boot/dts/cavium/thunder2-99xx.dtsi @@ -98,7 +98,7 @@ clock-output-names = "clk125mhz"; }; - pci { + pcie@30000000 { compatible = "pci-host-ecam-generic"; device_type = "pci"; #interrupt-cells = <1>; @@ -118,6 +118,7 @@ ranges = <0x02000000 0 0x40000000 0 0x40000000 0 0x20000000 0x43000000 0x40 0x00000000 0x40 0x00000000 0x20 0x00000000>; + bus-range = <0 0xff>; interrupt-map-mask = <0 0 0 7>; interrupt-map = /* addr pin ic icaddr icintr */ -- cgit v1.2.3-55-g7522 From 9977a8c3497a8f7f7f951994f298a8e4d961234f Mon Sep 17 00:00:00 2001 From: Mathieu Malaterre Date: Thu, 14 Dec 2017 17:53:52 +0100 Subject: arm64: dts: Remove leading 0x and 0s from bindings notation Improve the DTS files by removing all the leading "0x" and zeros to fix the following dtc warnings: Warning (unit_address_format): Node /XXX unit name should not have leading "0x" and Warning (unit_address_format): Node /XXX unit name should not have leading 0s Converted using the following command: find . -type f \( -iname *.dts -o -iname *.dtsi \) -exec sed -E -i -e "s/@0x([0-9a-fA-F\.]+)\s?\{/@\L\1 \{/g" -e "s/@0+([0-9a-fA-F\.]+)\s?\{/@\L\1 \{/g" {} + For simplicity, two sed expressions were used to solve each warnings separately. To make the regex expression more robust a few other issues were resolved, namely setting unit-address to lower case, and adding a whitespace before the the opening curly brace: https://elinux.org/Device_Tree_Linux#Linux_conventions This is a follow up to commit 4c9847b7375a ("dt-bindings: Remove leading 0x from bindings notation") Reported-by: David Daney Suggested-by: Rob Herring Signed-off-by: Mathieu Malaterre Acked-by: Matthias Brugger Acked-by: Andy Gross Signed-off-by: Arnd Bergmann --- arch/arm64/boot/dts/hisilicon/hi6220-hikey.dts | 2 +- arch/arm64/boot/dts/mediatek/mt8173.dtsi | 2 +- arch/arm64/boot/dts/qcom/apq8096-db820c.dtsi | 6 +++--- arch/arm64/boot/dts/qcom/msm8996.dtsi | 6 +++--- 4 files changed, 8 insertions(+), 8 deletions(-) (limited to 'arch') diff --git a/arch/arm64/boot/dts/hisilicon/hi6220-hikey.dts b/arch/arm64/boot/dts/hisilicon/hi6220-hikey.dts index e94fa1a53192..047641fe294c 100644 --- a/arch/arm64/boot/dts/hisilicon/hi6220-hikey.dts +++ b/arch/arm64/boot/dts/hisilicon/hi6220-hikey.dts @@ -51,7 +51,7 @@ #size-cells = <2>; ranges; - ramoops@0x21f00000 { + ramoops@21f00000 { compatible = "ramoops"; reg = <0x0 0x21f00000 0x0 0x00100000>; record-size = <0x00020000>; diff --git a/arch/arm64/boot/dts/mediatek/mt8173.dtsi b/arch/arm64/boot/dts/mediatek/mt8173.dtsi index 9fbe4705ee88..94597e33c806 100644 --- a/arch/arm64/boot/dts/mediatek/mt8173.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt8173.dtsi @@ -341,7 +341,7 @@ reg = <0 0x10005000 0 0x1000>; }; - pio: pinctrl@0x10005000 { + pio: pinctrl@10005000 { compatible = "mediatek,mt8173-pinctrl"; reg = <0 0x1000b000 0 0x1000>; mediatek,pctl-regmap = <&syscfg_pctl_a>; diff --git a/arch/arm64/boot/dts/qcom/apq8096-db820c.dtsi b/arch/arm64/boot/dts/qcom/apq8096-db820c.dtsi index 492a011f14f6..1c8f1b86472d 100644 --- a/arch/arm64/boot/dts/qcom/apq8096-db820c.dtsi +++ b/arch/arm64/boot/dts/qcom/apq8096-db820c.dtsi @@ -140,16 +140,16 @@ }; agnoc@0 { - qcom,pcie@00600000 { + qcom,pcie@600000 { perst-gpio = <&msmgpio 35 GPIO_ACTIVE_LOW>; }; - qcom,pcie@00608000 { + qcom,pcie@608000 { status = "okay"; perst-gpio = <&msmgpio 130 GPIO_ACTIVE_LOW>; }; - qcom,pcie@00610000 { + qcom,pcie@610000 { status = "okay"; perst-gpio = <&msmgpio 114 GPIO_ACTIVE_LOW>; }; diff --git a/arch/arm64/boot/dts/qcom/msm8996.dtsi b/arch/arm64/boot/dts/qcom/msm8996.dtsi index 4b2afcc4fdf4..0a6f7952bbb1 100644 --- a/arch/arm64/boot/dts/qcom/msm8996.dtsi +++ b/arch/arm64/boot/dts/qcom/msm8996.dtsi @@ -840,7 +840,7 @@ #size-cells = <1>; ranges; - pcie0: qcom,pcie@00600000 { + pcie0: qcom,pcie@600000 { compatible = "qcom,pcie-msm8996", "snps,dw-pcie"; status = "disabled"; power-domains = <&gcc PCIE0_GDSC>; @@ -893,7 +893,7 @@ }; - pcie1: qcom,pcie@00608000 { + pcie1: qcom,pcie@608000 { compatible = "qcom,pcie-msm8996", "snps,dw-pcie"; power-domains = <&gcc PCIE1_GDSC>; bus-range = <0x00 0xff>; @@ -946,7 +946,7 @@ "bus_slave"; }; - pcie2: qcom,pcie@00610000 { + pcie2: qcom,pcie@610000 { compatible = "qcom,pcie-msm8996", "snps,dw-pcie"; power-domains = <&gcc PCIE2_GDSC>; bus-range = <0x00 0xff>; -- cgit v1.2.3-55-g7522 From e519eedb6848198cb6fb7f50abb2e416309c0ce5 Mon Sep 17 00:00:00 2001 From: Mathieu Malaterre Date: Fri, 15 Dec 2017 13:46:48 +0100 Subject: arm: zx: dts: Remove leading 0x and 0s from bindings notation Improve the DTS files by removing all the leading "0x" and zeros to fix the following dtc warnings: Warning (unit_address_format): Node /XXX unit name should not have leading "0x" and Warning (unit_address_format): Node /XXX unit name should not have leading 0s Converted using the following command: find . -type f \( -iname *.dts -o -iname *.dtsi \) -exec sed -i -e "s/@\([0-9a-fA-FxX\.;:#]+\)\s*{/@\L\1 {/g" -e "s/@0x\(.*\) {/@\1 {/g" -e "s/@0+\(.*\) {/@\1 {/g" {} +^C For simplicity, two sed expressions were used to solve each warnings separately. To make the regex expression more robust a few other issues were resolved, namely setting unit-address to lower case, and adding a whitespace before the the opening curly brace: https://elinux.org/Device_Tree_Linux#Linux_conventions This will solve as a side effect warning: Warning (simple_bus_reg): Node /XXX@ simple-bus unit address format error, expected "" This is a follow up to commit 4c9847b7375a ("dt-bindings: Remove leading 0x from bindings notation") Reported-by: David Daney Suggested-by: Rob Herring Signed-off-by: Mathieu Malaterre Signed-off-by: Arnd Bergmann --- arch/arm/boot/dts/zx296702.dtsi | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) (limited to 'arch') diff --git a/arch/arm/boot/dts/zx296702.dtsi b/arch/arm/boot/dts/zx296702.dtsi index 8a74efdb6360..240e7a23d81f 100644 --- a/arch/arm/boot/dts/zx296702.dtsi +++ b/arch/arm/boot/dts/zx296702.dtsi @@ -56,7 +56,7 @@ clocks = <&topclk ZX296702_A9_PERIPHCLK>; }; - l2cc: l2-cache-controller@0x00c00000 { + l2cc: l2-cache-controller@c00000 { compatible = "arm,pl310-cache"; reg = <0x00c00000 0x1000>; cache-unified; @@ -67,30 +67,30 @@ arm,double-linefill-incr = <0>; }; - pcu: pcu@0xa0008000 { + pcu: pcu@a0008000 { compatible = "zte,zx296702-pcu"; reg = <0xa0008000 0x1000>; }; - topclk: topclk@0x09800000 { + topclk: topclk@9800000 { compatible = "zte,zx296702-topcrm-clk"; reg = <0x09800000 0x1000>; #clock-cells = <1>; }; - lsp1clk: lsp1clk@0x09400000 { + lsp1clk: lsp1clk@9400000 { compatible = "zte,zx296702-lsp1crpm-clk"; reg = <0x09400000 0x1000>; #clock-cells = <1>; }; - lsp0clk: lsp0clk@0x0b000000 { + lsp0clk: lsp0clk@b000000 { compatible = "zte,zx296702-lsp0crpm-clk"; reg = <0x0b000000 0x1000>; #clock-cells = <1>; }; - uart0: serial@0x09405000 { + uart0: serial@9405000 { compatible = "zte,zx296702-uart"; reg = <0x09405000 0x1000>; interrupts = ; @@ -98,7 +98,7 @@ status = "disabled"; }; - uart1: serial@0x09406000 { + uart1: serial@9406000 { compatible = "zte,zx296702-uart"; reg = <0x09406000 0x1000>; interrupts = ; @@ -106,7 +106,7 @@ status = "disabled"; }; - mmc0: mmc@0x09408000 { + mmc0: mmc@9408000 { compatible = "snps,dw-mshc"; #address-cells = <1>; #size-cells = <0>; @@ -119,7 +119,7 @@ status = "disabled"; }; - mmc1: mmc@0x0b003000 { + mmc1: mmc@b003000 { compatible = "snps,dw-mshc"; #address-cells = <1>; #size-cells = <0>; @@ -132,7 +132,7 @@ status = "disabled"; }; - sysctrl: sysctrl@0xa0007000 { + sysctrl: sysctrl@a0007000 { compatible = "zte,sysctrl", "syscon"; reg = <0xa0007000 0x1000>; }; -- cgit v1.2.3-55-g7522 From 01a6e1267e741a91c6cdb4604cd2f898166e03f0 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 20 Feb 2018 17:24:50 +0100 Subject: ARM: clps711x: mark clps711x_compat as const The array of string pointers is put in __initconst, and the strings themselves are marke 'const' but the the pointers are not, which caused a warning when built with LTO: arch/arm/mach-clps711x/board-dt.c:72:20: error: 'clps711x_compat' causes a section type conflict with 'feroceon_ids' static const char *clps711x_compat[] __initconst = { This marks the array itself const as well, which was certainly the intention originally. Signed-off-by: Arnd Bergmann --- arch/arm/mach-clps711x/board-dt.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/arm/mach-clps711x/board-dt.c b/arch/arm/mach-clps711x/board-dt.c index ee1f83b1a332..4c89a8e9a2e3 100644 --- a/arch/arm/mach-clps711x/board-dt.c +++ b/arch/arm/mach-clps711x/board-dt.c @@ -69,7 +69,7 @@ static void clps711x_restart(enum reboot_mode mode, const char *cmd) soft_restart(0); } -static const char *clps711x_compat[] __initconst = { +static const char *const clps711x_compat[] __initconst = { "cirrus,ep7209", NULL }; -- cgit v1.2.3-55-g7522 From eec51afc9d2612c65523627cfd81456c6995a79a Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 20 Feb 2018 17:24:52 +0100 Subject: ARM: davinci: mark spi_board_info arrays as const Building with LTO revealed that three spi_board_info arrays are marked __initconst, but not const: arch/arm/mach-davinci/board-dm365-evm.c: In function 'dm365_evm_init': arch/arm/mach-davinci/board-dm365-evm.c:729:30: error: 'dm365_evm_spi_info' causes a section type conflict with 'dm646x_edma_device' static struct spi_board_info dm365_evm_spi_info[] __initconst = { ^ arch/arm/mach-davinci/dm646x.c:603:42: note: 'dm646x_edma_device' was declared here static const struct platform_device_info dm646x_edma_device __initconst = { This marks them const as well, as was originally intended. Signed-off-by: Arnd Bergmann --- arch/arm/mach-davinci/board-dm355-evm.c | 2 +- arch/arm/mach-davinci/board-dm355-leopard.c | 2 +- arch/arm/mach-davinci/board-dm365-evm.c | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) (limited to 'arch') diff --git a/arch/arm/mach-davinci/board-dm355-evm.c b/arch/arm/mach-davinci/board-dm355-evm.c index e457f299cd44..d6b11907380c 100644 --- a/arch/arm/mach-davinci/board-dm355-evm.c +++ b/arch/arm/mach-davinci/board-dm355-evm.c @@ -368,7 +368,7 @@ static struct spi_eeprom at25640a = { .flags = EE_ADDR2, }; -static struct spi_board_info dm355_evm_spi_info[] __initconst = { +static const struct spi_board_info dm355_evm_spi_info[] __initconst = { { .modalias = "at25", .platform_data = &at25640a, diff --git a/arch/arm/mach-davinci/board-dm355-leopard.c b/arch/arm/mach-davinci/board-dm355-leopard.c index be997243447b..fad9a5611a5d 100644 --- a/arch/arm/mach-davinci/board-dm355-leopard.c +++ b/arch/arm/mach-davinci/board-dm355-leopard.c @@ -217,7 +217,7 @@ static struct spi_eeprom at25640a = { .flags = EE_ADDR2, }; -static struct spi_board_info dm355_leopard_spi_info[] __initconst = { +static const struct spi_board_info dm355_leopard_spi_info[] __initconst = { { .modalias = "at25", .platform_data = &at25640a, diff --git a/arch/arm/mach-davinci/board-dm365-evm.c b/arch/arm/mach-davinci/board-dm365-evm.c index e75741fb2c1d..e3780986d2a3 100644 --- a/arch/arm/mach-davinci/board-dm365-evm.c +++ b/arch/arm/mach-davinci/board-dm365-evm.c @@ -726,7 +726,7 @@ static struct spi_eeprom at25640 = { .flags = EE_ADDR2, }; -static struct spi_board_info dm365_evm_spi_info[] __initconst = { +static const struct spi_board_info dm365_evm_spi_info[] __initconst = { { .modalias = "at25", .platform_data = &at25640, -- cgit v1.2.3-55-g7522 From 8337d083507b9827dfb36d545538b7789df834fd Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 21 Feb 2018 13:18:49 +0100 Subject: ARM: orion: fix orion_ge00_switch_board_info initialization A section type mismatch warning shows up when building with LTO, since orion_ge00_mvmdio_bus_name was put in __initconst but not marked const itself: include/linux/of.h: In function 'spear_setup_of_timer': arch/arm/mach-spear/time.c:207:34: error: 'timer_of_match' causes a section type conflict with 'orion_ge00_mvmdio_bus_name' static const struct of_device_id timer_of_match[] __initconst = { ^ arch/arm/plat-orion/common.c:475:32: note: 'orion_ge00_mvmdio_bus_name' was declared here static __initconst const char *orion_ge00_mvmdio_bus_name = "orion-mii"; ^ As pointed out by Andrew Lunn, it should in fact be 'const' but not '__initconst' because the string is never copied but may be accessed after the init sections are freed. To fix that, I get rid of the extra symbol and rewrite the initialization in a simpler way that assigns both the bus_id and modalias statically. I spotted another theoretical bug in the same place, where d->netdev[i] may be an out of bounds access, this can be fixed by moving the device assignment into the loop. Cc: stable@vger.kernel.org Reviewed-by: Andrew Lunn Signed-off-by: Arnd Bergmann --- arch/arm/plat-orion/common.c | 23 +++++++++++------------ 1 file changed, 11 insertions(+), 12 deletions(-) (limited to 'arch') diff --git a/arch/arm/plat-orion/common.c b/arch/arm/plat-orion/common.c index aff6994950ba..a2399fd66e97 100644 --- a/arch/arm/plat-orion/common.c +++ b/arch/arm/plat-orion/common.c @@ -472,28 +472,27 @@ void __init orion_ge11_init(struct mv643xx_eth_platform_data *eth_data, /***************************************************************************** * Ethernet switch ****************************************************************************/ -static __initconst const char *orion_ge00_mvmdio_bus_name = "orion-mii"; -static __initdata struct mdio_board_info - orion_ge00_switch_board_info; +static __initdata struct mdio_board_info orion_ge00_switch_board_info = { + .bus_id = "orion-mii", + .modalias = "mv88e6085", +}; void __init orion_ge00_switch_init(struct dsa_chip_data *d) { - struct mdio_board_info *bd; unsigned int i; if (!IS_BUILTIN(CONFIG_PHYLIB)) return; - for (i = 0; i < ARRAY_SIZE(d->port_names); i++) - if (!strcmp(d->port_names[i], "cpu")) + for (i = 0; i < ARRAY_SIZE(d->port_names); i++) { + if (!strcmp(d->port_names[i], "cpu")) { + d->netdev[i] = &orion_ge00.dev; break; + } + } - bd = &orion_ge00_switch_board_info; - bd->bus_id = orion_ge00_mvmdio_bus_name; - bd->mdio_addr = d->sw_addr; - d->netdev[i] = &orion_ge00.dev; - strcpy(bd->modalias, "mv88e6085"); - bd->platform_data = d; + orion_ge00_switch_board_info.mdio_addr = d->sw_addr; + orion_ge00_switch_board_info.platform_data = d; mdiobus_register_board_info(&orion_ge00_switch_board_info, 1); } -- cgit v1.2.3-55-g7522 From b21ebf2fb4cde1618915a97cc773e287ff49173e Mon Sep 17 00:00:00 2001 From: H.J. Lu Date: Wed, 7 Feb 2018 14:20:09 -0800 Subject: x86: Treat R_X86_64_PLT32 as R_X86_64_PC32 On i386, there are 2 types of PLTs, PIC and non-PIC. PIE and shared objects must use PIC PLT. To use PIC PLT, you need to load _GLOBAL_OFFSET_TABLE_ into EBX first. There is no need for that on x86-64 since x86-64 uses PC-relative PLT. On x86-64, for 32-bit PC-relative branches, we can generate PLT32 relocation, instead of PC32 relocation, which can also be used as a marker for 32-bit PC-relative branches. Linker can always reduce PLT32 relocation to PC32 if function is defined locally. Local functions should use PC32 relocation. As far as Linux kernel is concerned, R_X86_64_PLT32 can be treated the same as R_X86_64_PC32 since Linux kernel doesn't use PLT. R_X86_64_PLT32 for 32-bit PC-relative branches has been enabled in binutils master branch which will become binutils 2.31. [ hjl is working on having better documentation on this all, but a few more notes from him: "PLT32 relocation is used as marker for PC-relative branches. Because of EBX, it looks odd to generate PLT32 relocation on i386 when EBX doesn't have GOT. As for symbol resolution, PLT32 and PC32 relocations are almost interchangeable. But when linker sees PLT32 relocation against a protected symbol, it can resolved locally at link-time since it is used on a branch instruction. Linker can't do that for PC32 relocation" but for the kernel use, the two are basically the same, and this commit gets things building and working with the current binutils master - Linus ] Signed-off-by: H.J. Lu Signed-off-by: Linus Torvalds --- arch/x86/kernel/machine_kexec_64.c | 1 + arch/x86/kernel/module.c | 1 + arch/x86/tools/relocs.c | 3 +++ 3 files changed, 5 insertions(+) (limited to 'arch') diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c index 1f790cf9d38f..3b7427aa7d85 100644 --- a/arch/x86/kernel/machine_kexec_64.c +++ b/arch/x86/kernel/machine_kexec_64.c @@ -542,6 +542,7 @@ int arch_kexec_apply_relocations_add(const Elf64_Ehdr *ehdr, goto overflow; break; case R_X86_64_PC32: + case R_X86_64_PLT32: value -= (u64)address; *(u32 *)location = value; break; diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c index da0c160e5589..f58336af095c 100644 --- a/arch/x86/kernel/module.c +++ b/arch/x86/kernel/module.c @@ -191,6 +191,7 @@ int apply_relocate_add(Elf64_Shdr *sechdrs, goto overflow; break; case R_X86_64_PC32: + case R_X86_64_PLT32: if (*(u32 *)loc != 0) goto invalid_relocation; val -= (u64)loc; diff --git a/arch/x86/tools/relocs.c b/arch/x86/tools/relocs.c index 5d73c443e778..220e97841e49 100644 --- a/arch/x86/tools/relocs.c +++ b/arch/x86/tools/relocs.c @@ -770,9 +770,12 @@ static int do_reloc64(struct section *sec, Elf_Rel *rel, ElfW(Sym) *sym, break; case R_X86_64_PC32: + case R_X86_64_PLT32: /* * PC relative relocations don't need to be adjusted unless * referencing a percpu symbol. + * + * NB: R_X86_64_PLT32 can be treated as R_X86_64_PC32. */ if (is_percpu_sym(sym, symname)) add_reloc(&relocs32neg, offset); -- cgit v1.2.3-55-g7522 From 77ee2e1bac3218723a1b252d678827de1fa651ce Mon Sep 17 00:00:00 2001 From: Mathieu Malaterre Date: Fri, 15 Dec 2017 13:46:28 +0100 Subject: ARM: BCM: dts: Remove leading 0x and 0s from bindings notation Improve the DTS files by removing all the leading "0x" and zeros to fix the following dtc warnings: Warning (unit_address_format): Node /XXX unit name should not have leading "0x" and Warning (unit_address_format): Node /XXX unit name should not have leading 0s Converted using the following command: find . -type f \( -iname *.dts -o -iname *.dtsi \) -exec sed -i -e "s/@\([0-9a-fA-FxX\.;:#]+\)\s*{/@\L\1 {/g" -e "s/@0x\(.*\) {/@\1 {/g" -e "s/@0+\(.*\) {/@\1 {/g" {} +^C For simplicity, two sed expressions were used to solve each warnings separately. To make the regex expression more robust a few other issues were resolved, namely setting unit-address to lower case, and adding a whitespace before the the opening curly brace: https://elinux.org/Device_Tree_Linux#Linux_conventions This will solve as a side effect warning: Warning (simple_bus_reg): Node /XXX@ simple-bus unit address format error, expected "" This is a follow up to commit 4c9847b7375a ("dt-bindings: Remove leading 0x from bindings notation") Reported-by: David Daney Suggested-by: Rob Herring Signed-off-by: Mathieu Malaterre Acked-by: Stefan Wahren Signed-off-by: Florian Fainelli --- arch/arm/boot/dts/bcm11351.dtsi | 2 +- arch/arm/boot/dts/bcm21664.dtsi | 2 +- arch/arm/boot/dts/bcm283x.dtsi | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) (limited to 'arch') diff --git a/arch/arm/boot/dts/bcm11351.dtsi b/arch/arm/boot/dts/bcm11351.dtsi index 18045c38bcf1..db7cded1b7ad 100644 --- a/arch/arm/boot/dts/bcm11351.dtsi +++ b/arch/arm/boot/dts/bcm11351.dtsi @@ -55,7 +55,7 @@ <0x3ff00100 0x100>; }; - smc@0x3404c000 { + smc@3404c000 { compatible = "brcm,bcm11351-smc", "brcm,kona-smc"; reg = <0x3404c000 0x400>; /* 1 KiB in SRAM */ }; diff --git a/arch/arm/boot/dts/bcm21664.dtsi b/arch/arm/boot/dts/bcm21664.dtsi index 6dde95f21cef..266f2611dc22 100644 --- a/arch/arm/boot/dts/bcm21664.dtsi +++ b/arch/arm/boot/dts/bcm21664.dtsi @@ -55,7 +55,7 @@ <0x3ff00100 0x100>; }; - smc@0x3404e000 { + smc@3404e000 { compatible = "brcm,bcm21664-smc", "brcm,kona-smc"; reg = <0x3404e000 0x400>; /* 1 KiB in SRAM */ }; diff --git a/arch/arm/boot/dts/bcm283x.dtsi b/arch/arm/boot/dts/bcm283x.dtsi index 18db25a5a66e..9d293decf8d3 100644 --- a/arch/arm/boot/dts/bcm283x.dtsi +++ b/arch/arm/boot/dts/bcm283x.dtsi @@ -465,7 +465,7 @@ status = "disabled"; }; - aux: aux@0x7e215000 { + aux: aux@7e215000 { compatible = "brcm,bcm2835-aux"; #clock-cells = <1>; reg = <0x7e215000 0x8>; -- cgit v1.2.3-55-g7522 From a493a87f38cfa48caaa95c9347be2d914c6fdf29 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Thu, 22 Feb 2018 15:12:53 +0100 Subject: bpf, x64: implement retpoline for tail call Implement a retpoline [0] for the BPF tail call JIT'ing that converts the indirect jump via jmp %rax that is used to make the long jump into another JITed BPF image. Since this is subject to speculative execution, we need to control the transient instruction sequence here as well when CONFIG_RETPOLINE is set, and direct it into a pause + lfence loop. The latter aligns also with what gcc / clang emits (e.g. [1]). JIT dump after patch: # bpftool p d x i 1 0: (18) r2 = map[id:1] 2: (b7) r3 = 0 3: (85) call bpf_tail_call#12 4: (b7) r0 = 2 5: (95) exit With CONFIG_RETPOLINE: # bpftool p d j i 1 [...] 33: cmp %edx,0x24(%rsi) 36: jbe 0x0000000000000072 |* 38: mov 0x24(%rbp),%eax 3e: cmp $0x20,%eax 41: ja 0x0000000000000072 | 43: add $0x1,%eax 46: mov %eax,0x24(%rbp) 4c: mov 0x90(%rsi,%rdx,8),%rax 54: test %rax,%rax 57: je 0x0000000000000072 | 59: mov 0x28(%rax),%rax 5d: add $0x25,%rax 61: callq 0x000000000000006d |+ 66: pause | 68: lfence | 6b: jmp 0x0000000000000066 | 6d: mov %rax,(%rsp) | 71: retq | 72: mov $0x2,%eax [...] * relative fall-through jumps in error case + retpoline for indirect jump Without CONFIG_RETPOLINE: # bpftool p d j i 1 [...] 33: cmp %edx,0x24(%rsi) 36: jbe 0x0000000000000063 |* 38: mov 0x24(%rbp),%eax 3e: cmp $0x20,%eax 41: ja 0x0000000000000063 | 43: add $0x1,%eax 46: mov %eax,0x24(%rbp) 4c: mov 0x90(%rsi,%rdx,8),%rax 54: test %rax,%rax 57: je 0x0000000000000063 | 59: mov 0x28(%rax),%rax 5d: add $0x25,%rax 61: jmpq *%rax |- 63: mov $0x2,%eax [...] * relative fall-through jumps in error case - plain indirect jump as before [0] https://support.google.com/faqs/answer/7625886 [1] https://github.com/gcc-mirror/gcc/commit/a31e654fa107be968b802786d747e962c2fcdb2b Signed-off-by: Daniel Borkmann Signed-off-by: Alexei Starovoitov --- arch/x86/include/asm/nospec-branch.h | 37 ++++++++++++++++++++++++++++++++++++ arch/x86/net/bpf_jit_comp.c | 9 +++++---- 2 files changed, 42 insertions(+), 4 deletions(-) (limited to 'arch') diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index 76b058533e47..81a1be326571 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -177,4 +177,41 @@ static inline void indirect_branch_prediction_barrier(void) } #endif /* __ASSEMBLY__ */ + +/* + * Below is used in the eBPF JIT compiler and emits the byte sequence + * for the following assembly: + * + * With retpolines configured: + * + * callq do_rop + * spec_trap: + * pause + * lfence + * jmp spec_trap + * do_rop: + * mov %rax,(%rsp) + * retq + * + * Without retpolines configured: + * + * jmp *%rax + */ +#ifdef CONFIG_RETPOLINE +# define RETPOLINE_RAX_BPF_JIT_SIZE 17 +# define RETPOLINE_RAX_BPF_JIT() \ + EMIT1_off32(0xE8, 7); /* callq do_rop */ \ + /* spec_trap: */ \ + EMIT2(0xF3, 0x90); /* pause */ \ + EMIT3(0x0F, 0xAE, 0xE8); /* lfence */ \ + EMIT2(0xEB, 0xF9); /* jmp spec_trap */ \ + /* do_rop: */ \ + EMIT4(0x48, 0x89, 0x04, 0x24); /* mov %rax,(%rsp) */ \ + EMIT1(0xC3); /* retq */ +#else +# define RETPOLINE_RAX_BPF_JIT_SIZE 2 +# define RETPOLINE_RAX_BPF_JIT() \ + EMIT2(0xFF, 0xE0); /* jmp *%rax */ +#endif + #endif /* _ASM_X86_NOSPEC_BRANCH_H_ */ diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 4923d92f918d..45e4eb5bcbb2 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -13,6 +13,7 @@ #include #include #include +#include #include /* @@ -290,7 +291,7 @@ static void emit_bpf_tail_call(u8 **pprog) EMIT2(0x89, 0xD2); /* mov edx, edx */ EMIT3(0x39, 0x56, /* cmp dword ptr [rsi + 16], edx */ offsetof(struct bpf_array, map.max_entries)); -#define OFFSET1 43 /* number of bytes to jump */ +#define OFFSET1 (41 + RETPOLINE_RAX_BPF_JIT_SIZE) /* number of bytes to jump */ EMIT2(X86_JBE, OFFSET1); /* jbe out */ label1 = cnt; @@ -299,7 +300,7 @@ static void emit_bpf_tail_call(u8 **pprog) */ EMIT2_off32(0x8B, 0x85, 36); /* mov eax, dword ptr [rbp + 36] */ EMIT3(0x83, 0xF8, MAX_TAIL_CALL_CNT); /* cmp eax, MAX_TAIL_CALL_CNT */ -#define OFFSET2 32 +#define OFFSET2 (30 + RETPOLINE_RAX_BPF_JIT_SIZE) EMIT2(X86_JA, OFFSET2); /* ja out */ label2 = cnt; EMIT3(0x83, 0xC0, 0x01); /* add eax, 1 */ @@ -313,7 +314,7 @@ static void emit_bpf_tail_call(u8 **pprog) * goto out; */ EMIT3(0x48, 0x85, 0xC0); /* test rax,rax */ -#define OFFSET3 10 +#define OFFSET3 (8 + RETPOLINE_RAX_BPF_JIT_SIZE) EMIT2(X86_JE, OFFSET3); /* je out */ label3 = cnt; @@ -326,7 +327,7 @@ static void emit_bpf_tail_call(u8 **pprog) * rdi == ctx (1st arg) * rax == prog->bpf_func + prologue_size */ - EMIT2(0xFF, 0xE0); /* jmp rax */ + RETPOLINE_RAX_BPF_JIT(); /* out: */ BUILD_BUG_ON(cnt - label1 != OFFSET1); -- cgit v1.2.3-55-g7522 From 16338a9b3ac30740d49f5dfed81bac0ffa53b9c7 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Fri, 23 Feb 2018 01:03:43 +0100 Subject: bpf, arm64: fix out of bounds access in tail call I recently noticed a crash on arm64 when feeding a bogus index into BPF tail call helper. The crash would not occur when the interpreter is used, but only in case of JIT. Output looks as follows: [ 347.007486] Unable to handle kernel paging request at virtual address fffb850e96492510 [...] [ 347.043065] [fffb850e96492510] address between user and kernel address ranges [ 347.050205] Internal error: Oops: 96000004 [#1] SMP [...] [ 347.190829] x13: 0000000000000000 x12: 0000000000000000 [ 347.196128] x11: fffc047ebe782800 x10: ffff808fd7d0fd10 [ 347.201427] x9 : 0000000000000000 x8 : 0000000000000000 [ 347.206726] x7 : 0000000000000000 x6 : 001c991738000000 [ 347.212025] x5 : 0000000000000018 x4 : 000000000000ba5a [ 347.217325] x3 : 00000000000329c4 x2 : ffff808fd7cf0500 [ 347.222625] x1 : ffff808fd7d0fc00 x0 : ffff808fd7cf0500 [ 347.227926] Process test_verifier (pid: 4548, stack limit = 0x000000007467fa61) [ 347.235221] Call trace: [ 347.237656] 0xffff000002f3a4fc [ 347.240784] bpf_test_run+0x78/0xf8 [ 347.244260] bpf_prog_test_run_skb+0x148/0x230 [ 347.248694] SyS_bpf+0x77c/0x1110 [ 347.251999] el0_svc_naked+0x30/0x34 [ 347.255564] Code: 9100075a d280220a 8b0a002a d37df04b (f86b694b) [...] In this case the index used in BPF r3 is the same as in r1 at the time of the call, meaning we fed a pointer as index; here, it had the value 0xffff808fd7cf0500 which sits in x2. While I found tail calls to be working in general (also for hitting the error cases), I noticed the following in the code emission: # bpftool p d j i 988 [...] 38: ldr w10, [x1,x10] 3c: cmp w2, w10 40: b.ge 0x000000000000007c <-- signed cmp 44: mov x10, #0x20 // #32 48: cmp x26, x10 4c: b.gt 0x000000000000007c 50: add x26, x26, #0x1 54: mov x10, #0x110 // #272 58: add x10, x1, x10 5c: lsl x11, x2, #3 60: ldr x11, [x10,x11] <-- faulting insn (f86b694b) 64: cbz x11, 0x000000000000007c [...] Meaning, the tests passed because commit ddb55992b04d ("arm64: bpf: implement bpf_tail_call() helper") was using signed compares instead of unsigned which as a result had the test wrongly passing. Change this but also the tail call count test both into unsigned and cap the index as u32. Latter we did as well in 90caccdd8cc0 ("bpf: fix bpf_tail_call() x64 JIT") and is needed in addition here, too. Tested on HiSilicon Hi1616. Result after patch: # bpftool p d j i 268 [...] 38: ldr w10, [x1,x10] 3c: add w2, w2, #0x0 40: cmp w2, w10 44: b.cs 0x0000000000000080 48: mov x10, #0x20 // #32 4c: cmp x26, x10 50: b.hi 0x0000000000000080 54: add x26, x26, #0x1 58: mov x10, #0x110 // #272 5c: add x10, x1, x10 60: lsl x11, x2, #3 64: ldr x11, [x10,x11] 68: cbz x11, 0x0000000000000080 [...] Fixes: ddb55992b04d ("arm64: bpf: implement bpf_tail_call() helper") Signed-off-by: Daniel Borkmann Signed-off-by: Alexei Starovoitov --- arch/arm64/net/bpf_jit_comp.c | 5 +++-- tools/testing/selftests/bpf/test_verifier.c | 26 ++++++++++++++++++++++++++ 2 files changed, 29 insertions(+), 2 deletions(-) (limited to 'arch') diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index 1d4f1da7c58f..a93350451e8e 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -250,8 +250,9 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx) off = offsetof(struct bpf_array, map.max_entries); emit_a64_mov_i64(tmp, off, ctx); emit(A64_LDR32(tmp, r2, tmp), ctx); + emit(A64_MOV(0, r3, r3), ctx); emit(A64_CMP(0, r3, tmp), ctx); - emit(A64_B_(A64_COND_GE, jmp_offset), ctx); + emit(A64_B_(A64_COND_CS, jmp_offset), ctx); /* if (tail_call_cnt > MAX_TAIL_CALL_CNT) * goto out; @@ -259,7 +260,7 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx) */ emit_a64_mov_i64(tmp, MAX_TAIL_CALL_CNT, ctx); emit(A64_CMP(1, tcc, tmp), ctx); - emit(A64_B_(A64_COND_GT, jmp_offset), ctx); + emit(A64_B_(A64_COND_HI, jmp_offset), ctx); emit(A64_ADD_I(1, tcc, tcc, 1), ctx); /* prog = array->ptrs[index]; diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index c0f16e93f9bd..c73592fa3d41 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -2586,6 +2586,32 @@ static struct bpf_test tests[] = { .result_unpriv = REJECT, .result = ACCEPT, }, + { + "runtime/jit: pass negative index to tail_call", + .insns = { + BPF_MOV64_IMM(BPF_REG_3, -1), + BPF_LD_MAP_FD(BPF_REG_2, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_tail_call), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_prog = { 1 }, + .result = ACCEPT, + }, + { + "runtime/jit: pass > 32bit index to tail_call", + .insns = { + BPF_LD_IMM64(BPF_REG_3, 0x100000000ULL), + BPF_LD_MAP_FD(BPF_REG_2, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_tail_call), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_prog = { 2 }, + .result = ACCEPT, + }, { "stack pointer arithmetic", .insns = { -- cgit v1.2.3-55-g7522 From 0f9da844d87796ac31b04e81ee95e155e9043132 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Thu, 22 Feb 2018 16:59:26 -0800 Subject: MIPS: boot: Define __ASSEMBLY__ for its.S build The MIPS %.its.S compiler command did not define __ASSEMBLY__, which meant when compiler_types.h was added to kconfig.h, unexpected things appeared (e.g. struct declarations) which should not have been present. As done in the general %.S compiler command, __ASSEMBLY__ is now included here too. The failure was: Error: arch/mips/boot/vmlinux.gz.its:201.1-2 syntax error FATAL ERROR: Unable to parse input tree /usr/bin/mkimage: Can't read arch/mips/boot/vmlinux.gz.itb.tmp: Invalid argument /usr/bin/mkimage Can't add hashes to FIT blob Reported-by: kbuild test robot Fixes: 28128c61e08e ("kconfig.h: Include compiler types to avoid missed struct attributes") Signed-off-by: Kees Cook Signed-off-by: Linus Torvalds --- arch/mips/boot/Makefile | 1 + 1 file changed, 1 insertion(+) (limited to 'arch') diff --git a/arch/mips/boot/Makefile b/arch/mips/boot/Makefile index 1bd5c4f00d19..c22da16d67b8 100644 --- a/arch/mips/boot/Makefile +++ b/arch/mips/boot/Makefile @@ -126,6 +126,7 @@ $(obj)/vmlinux.its.S: $(addprefix $(srctree)/arch/mips/$(PLATFORM)/,$(ITS_INPUTS quiet_cmd_cpp_its_S = ITS $@ cmd_cpp_its_S = $(CPP) $(cpp_flags) -P -C -o $@ $< \ + -D__ASSEMBLY__ \ -DKERNEL_NAME="\"Linux $(KERNELRELEASE)\"" \ -DVMLINUX_BINARY="\"$(3)\"" \ -DVMLINUX_COMPRESSION="\"$(2)\"" \ -- cgit v1.2.3-55-g7522 From 2f7d03e0511991f124455682cc94094eaa0981ea Mon Sep 17 00:00:00 2001 From: Bharata B Rao Date: Wed, 21 Feb 2018 16:06:26 +0530 Subject: powerpc/mm/drmem: Fix unexpected flag value in ibm,dynamic-memory-v2 Memory addtion and removal by count and indexed-count methods temporarily mark the LMBs that are being added/removed by a special flag value DRMEM_LMB_RESERVED. Accessing flags value directly at a few places without proper accessor method is causing two unexpected side-effects: - DRMEM_LMB_RESERVED bit is becoming part of the flags word of drconf_cell_v2 entries in ibm,dynamic-memory-v2 DT property. - This results in extra drconf_cell entries in ibm,dynamic-memory-v2. For example if 1G memory is added, it leads to one entry for 3 LMBs and 1 separate entry for the last LMB. All the 4 LMBs should be defined by one entry here. Fix this by always accessing the flags by its accessor method drmem_lmb_flags(). Fixes: 2b31e3aec1db ("powerpc/drmem: Add support for ibm, dynamic-memory-v2 property") Signed-off-by: Bharata B Rao Reviewed-by: Nathan Fontenot Signed-off-by: Michael Ellerman --- arch/powerpc/mm/drmem.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'arch') diff --git a/arch/powerpc/mm/drmem.c b/arch/powerpc/mm/drmem.c index 916844f99c64..3f1803672c9b 100644 --- a/arch/powerpc/mm/drmem.c +++ b/arch/powerpc/mm/drmem.c @@ -98,7 +98,7 @@ static void init_drconf_v2_cell(struct of_drconf_cell_v2 *dr_cell, dr_cell->base_addr = cpu_to_be64(lmb->base_addr); dr_cell->drc_index = cpu_to_be32(lmb->drc_index); dr_cell->aa_index = cpu_to_be32(lmb->aa_index); - dr_cell->flags = cpu_to_be32(lmb->flags); + dr_cell->flags = cpu_to_be32(drmem_lmb_flags(lmb)); } static int drmem_update_dt_v2(struct device_node *memory, @@ -121,7 +121,7 @@ static int drmem_update_dt_v2(struct device_node *memory, } if (prev_lmb->aa_index != lmb->aa_index || - prev_lmb->flags != lmb->flags) + drmem_lmb_flags(prev_lmb) != drmem_lmb_flags(lmb)) lmb_sets++; prev_lmb = lmb; @@ -150,7 +150,7 @@ static int drmem_update_dt_v2(struct device_node *memory, } if (prev_lmb->aa_index != lmb->aa_index || - prev_lmb->flags != lmb->flags) { + drmem_lmb_flags(prev_lmb) != drmem_lmb_flags(lmb)) { /* end of one set, start of another */ dr_cell->seq_lmbs = cpu_to_be32(seq_lmbs); dr_cell++; -- cgit v1.2.3-55-g7522 From 582605a429e20ae68fd0b041b2e840af296edd08 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Thu, 22 Feb 2018 23:58:49 +1100 Subject: powerpc/pseries: Support firmware disable of RFI flush Some versions of firmware will have a setting that can be configured to disable the RFI flush, add support for it. Fixes: 8989d56878a7 ("powerpc/pseries: Query hypervisor for RFI flush settings") Signed-off-by: Michael Ellerman --- arch/powerpc/platforms/pseries/setup.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index 372d7ada1a0c..1a527625acf7 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -482,7 +482,8 @@ static void pseries_setup_rfi_flush(void) if (types == L1D_FLUSH_NONE) types = L1D_FLUSH_FALLBACK; - if (!(result.behaviour & H_CPU_BEHAV_L1D_FLUSH_PR)) + if ((!(result.behaviour & H_CPU_BEHAV_L1D_FLUSH_PR)) || + (!(result.behaviour & H_CPU_BEHAV_FAVOUR_SECURITY))) enable = false; } else { /* Default to fallback if case hcall is not available */ -- cgit v1.2.3-55-g7522 From eb0a2d2620ae431c543963c8c7f08f597366fc60 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Fri, 23 Feb 2018 00:00:11 +1100 Subject: powerpc/powernv: Support firmware disable of RFI flush Some versions of firmware will have a setting that can be configured to disable the RFI flush, add support for it. Fixes: 6e032b350cd1 ("powerpc/powernv: Check device-tree for RFI flush settings") Signed-off-by: Michael Ellerman --- arch/powerpc/platforms/powernv/setup.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'arch') diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c index 4fb21e17504a..092715b9674b 100644 --- a/arch/powerpc/platforms/powernv/setup.c +++ b/arch/powerpc/platforms/powernv/setup.c @@ -80,6 +80,10 @@ static void pnv_setup_rfi_flush(void) if (np && of_property_read_bool(np, "disabled")) enable--; + np = of_get_child_by_name(fw_features, "speculation-policy-favor-security"); + if (np && of_property_read_bool(np, "disabled")) + enable = 0; + of_node_put(np); of_node_put(fw_features); } -- cgit v1.2.3-55-g7522 From e84cf6aa501c58bf4bf451f1e425192ec090aed2 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 22 Feb 2018 12:08:06 +0100 Subject: x86/apic/vector: Handle vector release on CPU unplug correctly When a irq vector is replaced, then the previous vector is normally released when the first interrupt happens on the new vector. If the target CPU of the previous vector is already offline when the new vector is installed, then the previous vector is silently discarded, which leads to accounting issues causing suspend failures and other problems. Adjust the logic so that the previous vector is freed in the underlying matrix allocator to ensure that the accounting stays correct. Fixes: 69cde0004a4b ("x86/vector: Use matrix allocator for vector assignment") Reported-by: Yuriy Vostrikov Signed-off-by: Thomas Gleixner Tested-by: Yuriy Vostrikov Cc: Peter Zijlstra Cc: Randy Dunlap Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/20180222112316.930791749@linutronix.de Signed-off-by: Ingo Molnar --- arch/x86/kernel/apic/vector.c | 25 ++++++++++++++++++++++--- 1 file changed, 22 insertions(+), 3 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c index 3cc471beb50b..bb6f7a2148d7 100644 --- a/arch/x86/kernel/apic/vector.c +++ b/arch/x86/kernel/apic/vector.c @@ -134,21 +134,40 @@ static void apic_update_vector(struct irq_data *irqd, unsigned int newvec, { struct apic_chip_data *apicd = apic_chip_data(irqd); struct irq_desc *desc = irq_data_to_desc(irqd); + bool managed = irqd_affinity_is_managed(irqd); lockdep_assert_held(&vector_lock); trace_vector_update(irqd->irq, newvec, newcpu, apicd->vector, apicd->cpu); - /* Setup the vector move, if required */ - if (apicd->vector && cpu_online(apicd->cpu)) { + /* + * If there is no vector associated or if the associated vector is + * the shutdown vector, which is associated to make PCI/MSI + * shutdown mode work, then there is nothing to release. Clear out + * prev_vector for this and the offlined target case. + */ + apicd->prev_vector = 0; + if (!apicd->vector || apicd->vector == MANAGED_IRQ_SHUTDOWN_VECTOR) + goto setnew; + /* + * If the target CPU of the previous vector is online, then mark + * the vector as move in progress and store it for cleanup when the + * first interrupt on the new vector arrives. If the target CPU is + * offline then the regular release mechanism via the cleanup + * vector is not possible and the vector can be immediately freed + * in the underlying matrix allocator. + */ + if (cpu_online(apicd->cpu)) { apicd->move_in_progress = true; apicd->prev_vector = apicd->vector; apicd->prev_cpu = apicd->cpu; } else { - apicd->prev_vector = 0; + irq_matrix_free(vector_matrix, apicd->cpu, apicd->vector, + managed); } +setnew: apicd->vector = newvec; apicd->cpu = newcpu; BUG_ON(!IS_ERR_OR_NULL(per_cpu(vector_irq, newcpu)[newvec])); -- cgit v1.2.3-55-g7522 From 36e74d355297dde6e69a39c838d24710e442babe Mon Sep 17 00:00:00 2001 From: Wang Hui Date: Thu, 22 Feb 2018 19:26:03 -0800 Subject: x86/intel_rdt: Fix incorrect returned value when creating rdgroup sub-directory in resctrl file system If no monitoring feature is detected because all monitoring features are disabled during boot time or there is no monitoring feature in hardware, creating rdtgroup sub-directory by "mkdir" command reports error: mkdir: cannot create directory ‘/sys/fs/resctrl/p1’: No such file or directory But the sub-directory actually is generated and content is correct: cpus cpus_list schemata tasks The error is because rdtgroup_mkdir_ctrl_mon() returns non zero value after the sub-directory is created and the returned value is reported as an error to user. Clear the returned value to report to user that the sub-directory is actually created successfully. Signed-off-by: Wang Hui Signed-off-by: Zhang Yanfei Signed-off-by: Fenghua Yu Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Ravi V Shankar Cc: Thomas Gleixner Cc: Tony Luck Cc: Vikas Cc: Xiaochen Shen Link: http://lkml.kernel.org/r/1519356363-133085-1-git-send-email-fenghua.yu@intel.com Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/intel_rdt_rdtgroup.c | 1 + 1 file changed, 1 insertion(+) (limited to 'arch') diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c index bdab7d2f51af..fca759d272a1 100644 --- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c +++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c @@ -1804,6 +1804,7 @@ static int rdtgroup_mkdir_ctrl_mon(struct kernfs_node *parent_kn, goto out_common_fail; } closid = ret; + ret = 0; rdtgrp->closid = closid; list_add(&rdtgrp->rdtgroup_list, &rdt_all_groups); -- cgit v1.2.3-55-g7522 From ecb586bd29c99fb4de599dec388658e74388daad Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Thu, 22 Feb 2018 16:43:17 +0100 Subject: KVM/x86: Remove indirect MSR op calls from SPEC_CTRL Having a paravirt indirect call in the IBRS restore path is not a good idea, since we are trying to protect from speculative execution of bogus indirect branch targets. It is also slower, so use native_wrmsrl() on the vmentry path too. Signed-off-by: Paolo Bonzini Reviewed-by: Jim Mattson Cc: David Woodhouse Cc: KarimAllah Ahmed Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Radim Krčmář Cc: Thomas Gleixner Cc: kvm@vger.kernel.org Cc: stable@vger.kernel.org Fixes: d28b387fb74da95d69d2615732f50cceb38e9a4d Link: http://lkml.kernel.org/r/20180222154318.20361-2-pbonzini@redhat.com Signed-off-by: Ingo Molnar --- arch/x86/kvm/svm.c | 7 ++++--- arch/x86/kvm/vmx.c | 7 ++++--- 2 files changed, 8 insertions(+), 6 deletions(-) (limited to 'arch') diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index b3e488a74828..1598beeda11c 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -49,6 +49,7 @@ #include #include #include +#include #include #include @@ -5355,7 +5356,7 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) * being speculatively taken. */ if (svm->spec_ctrl) - wrmsrl(MSR_IA32_SPEC_CTRL, svm->spec_ctrl); + native_wrmsrl(MSR_IA32_SPEC_CTRL, svm->spec_ctrl); asm volatile ( "push %%" _ASM_BP "; \n\t" @@ -5465,10 +5466,10 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) * save it. */ if (!msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL)) - rdmsrl(MSR_IA32_SPEC_CTRL, svm->spec_ctrl); + svm->spec_ctrl = native_read_msr(MSR_IA32_SPEC_CTRL); if (svm->spec_ctrl) - wrmsrl(MSR_IA32_SPEC_CTRL, 0); + native_wrmsrl(MSR_IA32_SPEC_CTRL, 0); /* Eliminate branch target predictions from guest mode */ vmexit_fill_RSB(); diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 3dec126aa302..0927be315965 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -51,6 +51,7 @@ #include #include #include +#include #include #include "trace.h" @@ -9452,7 +9453,7 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) * being speculatively taken. */ if (vmx->spec_ctrl) - wrmsrl(MSR_IA32_SPEC_CTRL, vmx->spec_ctrl); + native_wrmsrl(MSR_IA32_SPEC_CTRL, vmx->spec_ctrl); vmx->__launched = vmx->loaded_vmcs->launched; asm( @@ -9588,10 +9589,10 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) * save it. */ if (!msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL)) - rdmsrl(MSR_IA32_SPEC_CTRL, vmx->spec_ctrl); + vmx->spec_ctrl = native_read_msr(MSR_IA32_SPEC_CTRL); if (vmx->spec_ctrl) - wrmsrl(MSR_IA32_SPEC_CTRL, 0); + native_wrmsrl(MSR_IA32_SPEC_CTRL, 0); /* Eliminate branch target predictions from guest mode */ vmexit_fill_RSB(); -- cgit v1.2.3-55-g7522 From 946fbbc13dce68902f64515b610eeb2a6c3d7a64 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Thu, 22 Feb 2018 16:43:18 +0100 Subject: KVM/VMX: Optimize vmx_vcpu_run() and svm_vcpu_run() by marking the RDMSR path as unlikely() vmx_vcpu_run() and svm_vcpu_run() are large functions, and giving branch hints to the compiler can actually make a substantial cycle difference by keeping the fast path contiguous in memory. With this optimization, the retpoline-guest/retpoline-host case is about 50 cycles faster. Signed-off-by: Paolo Bonzini Reviewed-by: Jim Mattson Cc: David Woodhouse Cc: KarimAllah Ahmed Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Radim Krčmář Cc: Thomas Gleixner Cc: kvm@vger.kernel.org Cc: stable@vger.kernel.org Link: http://lkml.kernel.org/r/20180222154318.20361-3-pbonzini@redhat.com Signed-off-by: Ingo Molnar --- arch/x86/kvm/svm.c | 2 +- arch/x86/kvm/vmx.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'arch') diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 1598beeda11c..24c9521ebc24 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -5465,7 +5465,7 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) * If the L02 MSR bitmap does not intercept the MSR, then we need to * save it. */ - if (!msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL)) + if (unlikely(!msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL))) svm->spec_ctrl = native_read_msr(MSR_IA32_SPEC_CTRL); if (svm->spec_ctrl) diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 0927be315965..7f8401d05939 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -9588,7 +9588,7 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) * If the L02 MSR bitmap does not intercept the MSR, then we need to * save it. */ - if (!msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL)) + if (unlikely(!msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL))) vmx->spec_ctrl = native_read_msr(MSR_IA32_SPEC_CTRL); if (vmx->spec_ctrl) -- cgit v1.2.3-55-g7522 From 79d442461df7478cdd0c50d9b8a76f431f150fa3 Mon Sep 17 00:00:00 2001 From: Andrea Parri Date: Thu, 22 Feb 2018 10:24:29 +0100 Subject: locking/xchg/alpha: Clean up barrier usage by using smp_mb() in place of __ASM__MB Replace each occurrence of __ASM__MB with a (trailing) smp_mb() in xchg(), cmpxchg(), and remove the now unused __ASM__MB definitions; this improves readability, with no additional synchronization cost. Suggested-by: Will Deacon Signed-off-by: Andrea Parri Acked-by: Paul E. McKenney Cc: Alan Stern Cc: Andrew Morton Cc: Ivan Kokshaysky Cc: Linus Torvalds Cc: Matt Turner Cc: Peter Zijlstra Cc: Richard Henderson Cc: Thomas Gleixner Cc: linux-alpha@vger.kernel.org Link: http://lkml.kernel.org/r/1519291469-5702-1-git-send-email-parri.andrea@gmail.com Signed-off-by: Ingo Molnar --- arch/alpha/include/asm/cmpxchg.h | 6 ------ arch/alpha/include/asm/xchg.h | 16 ++++++++-------- 2 files changed, 8 insertions(+), 14 deletions(-) (limited to 'arch') diff --git a/arch/alpha/include/asm/cmpxchg.h b/arch/alpha/include/asm/cmpxchg.h index 46ebf14aed4e..8a2b331e43fe 100644 --- a/arch/alpha/include/asm/cmpxchg.h +++ b/arch/alpha/include/asm/cmpxchg.h @@ -6,7 +6,6 @@ * Atomic exchange routines. */ -#define __ASM__MB #define ____xchg(type, args...) __xchg ## type ## _local(args) #define ____cmpxchg(type, args...) __cmpxchg ## type ## _local(args) #include @@ -33,10 +32,6 @@ cmpxchg_local((ptr), (o), (n)); \ }) -#ifdef CONFIG_SMP -#undef __ASM__MB -#define __ASM__MB "\tmb\n" -#endif #undef ____xchg #undef ____cmpxchg #define ____xchg(type, args...) __xchg ##type(args) @@ -64,7 +59,6 @@ cmpxchg((ptr), (o), (n)); \ }) -#undef __ASM__MB #undef ____cmpxchg #endif /* _ALPHA_CMPXCHG_H */ diff --git a/arch/alpha/include/asm/xchg.h b/arch/alpha/include/asm/xchg.h index e2660866ce97..e1facf6fc244 100644 --- a/arch/alpha/include/asm/xchg.h +++ b/arch/alpha/include/asm/xchg.h @@ -28,12 +28,12 @@ ____xchg(_u8, volatile char *m, unsigned long val) " or %1,%2,%2\n" " stq_c %2,0(%3)\n" " beq %2,2f\n" - __ASM__MB ".subsection 2\n" "2: br 1b\n" ".previous" : "=&r" (ret), "=&r" (val), "=&r" (tmp), "=&r" (addr64) : "r" ((long)m), "1" (val) : "memory"); + smp_mb(); return ret; } @@ -52,12 +52,12 @@ ____xchg(_u16, volatile short *m, unsigned long val) " or %1,%2,%2\n" " stq_c %2,0(%3)\n" " beq %2,2f\n" - __ASM__MB ".subsection 2\n" "2: br 1b\n" ".previous" : "=&r" (ret), "=&r" (val), "=&r" (tmp), "=&r" (addr64) : "r" ((long)m), "1" (val) : "memory"); + smp_mb(); return ret; } @@ -72,12 +72,12 @@ ____xchg(_u32, volatile int *m, unsigned long val) " bis $31,%3,%1\n" " stl_c %1,%2\n" " beq %1,2f\n" - __ASM__MB ".subsection 2\n" "2: br 1b\n" ".previous" : "=&r" (val), "=&r" (dummy), "=m" (*m) : "rI" (val), "m" (*m) : "memory"); + smp_mb(); return val; } @@ -92,12 +92,12 @@ ____xchg(_u64, volatile long *m, unsigned long val) " bis $31,%3,%1\n" " stq_c %1,%2\n" " beq %1,2f\n" - __ASM__MB ".subsection 2\n" "2: br 1b\n" ".previous" : "=&r" (val), "=&r" (dummy), "=m" (*m) : "rI" (val), "m" (*m) : "memory"); + smp_mb(); return val; } @@ -150,12 +150,12 @@ ____cmpxchg(_u8, volatile char *m, unsigned char old, unsigned char new) " stq_c %2,0(%4)\n" " beq %2,3f\n" "2:\n" - __ASM__MB ".subsection 2\n" "3: br 1b\n" ".previous" : "=&r" (prev), "=&r" (new), "=&r" (tmp), "=&r" (cmp), "=&r" (addr64) : "r" ((long)m), "Ir" (old), "1" (new) : "memory"); + smp_mb(); return prev; } @@ -177,12 +177,12 @@ ____cmpxchg(_u16, volatile short *m, unsigned short old, unsigned short new) " stq_c %2,0(%4)\n" " beq %2,3f\n" "2:\n" - __ASM__MB ".subsection 2\n" "3: br 1b\n" ".previous" : "=&r" (prev), "=&r" (new), "=&r" (tmp), "=&r" (cmp), "=&r" (addr64) : "r" ((long)m), "Ir" (old), "1" (new) : "memory"); + smp_mb(); return prev; } @@ -200,12 +200,12 @@ ____cmpxchg(_u32, volatile int *m, int old, int new) " stl_c %1,%2\n" " beq %1,3f\n" "2:\n" - __ASM__MB ".subsection 2\n" "3: br 1b\n" ".previous" : "=&r"(prev), "=&r"(cmp), "=m"(*m) : "r"((long) old), "r"(new), "m"(*m) : "memory"); + smp_mb(); return prev; } @@ -223,12 +223,12 @@ ____cmpxchg(_u64, volatile long *m, unsigned long old, unsigned long new) " stq_c %1,%2\n" " beq %1,3f\n" "2:\n" - __ASM__MB ".subsection 2\n" "3: br 1b\n" ".previous" : "=&r"(prev), "=&r"(cmp), "=m"(*m) : "r"((long) old), "r"(new), "m"(*m) : "memory"); + smp_mb(); return prev; } -- cgit v1.2.3-55-g7522 From 472e8c55cf6622d1c112dc2bc777f68bbd4189db Mon Sep 17 00:00:00 2001 From: Andrea Parri Date: Thu, 22 Feb 2018 10:24:48 +0100 Subject: locking/xchg/alpha: Fix xchg() and cmpxchg() memory ordering bugs Successful RMW operations are supposed to be fully ordered, but Alpha's xchg() and cmpxchg() do not meet this requirement. Will Deacon noticed the bug: > So MP using xchg: > > WRITE_ONCE(x, 1) > xchg(y, 1) > > smp_load_acquire(y) == 1 > READ_ONCE(x) == 0 > > would be allowed. ... which thus violates the above requirement. Fix it by adding a leading smp_mb() to the xchg() and cmpxchg() implementations. Reported-by: Will Deacon Signed-off-by: Andrea Parri Acked-by: Paul E. McKenney Cc: Alan Stern Cc: Andrew Morton Cc: Ivan Kokshaysky Cc: Linus Torvalds Cc: Matt Turner Cc: Peter Zijlstra Cc: Richard Henderson Cc: Thomas Gleixner Cc: linux-alpha@vger.kernel.org Link: http://lkml.kernel.org/r/1519291488-5752-1-git-send-email-parri.andrea@gmail.com Signed-off-by: Ingo Molnar --- arch/alpha/include/asm/xchg.h | 21 ++++++++++++++++++--- 1 file changed, 18 insertions(+), 3 deletions(-) (limited to 'arch') diff --git a/arch/alpha/include/asm/xchg.h b/arch/alpha/include/asm/xchg.h index e1facf6fc244..e2b59fac5257 100644 --- a/arch/alpha/include/asm/xchg.h +++ b/arch/alpha/include/asm/xchg.h @@ -12,6 +12,10 @@ * Atomic exchange. * Since it can be used to implement critical sections * it must clobber "memory" (also for interrupts in UP). + * + * The leading and the trailing memory barriers guarantee that these + * operations are fully ordered. + * */ static inline unsigned long @@ -19,6 +23,7 @@ ____xchg(_u8, volatile char *m, unsigned long val) { unsigned long ret, tmp, addr64; + smp_mb(); __asm__ __volatile__( " andnot %4,7,%3\n" " insbl %1,%4,%1\n" @@ -43,6 +48,7 @@ ____xchg(_u16, volatile short *m, unsigned long val) { unsigned long ret, tmp, addr64; + smp_mb(); __asm__ __volatile__( " andnot %4,7,%3\n" " inswl %1,%4,%1\n" @@ -67,6 +73,7 @@ ____xchg(_u32, volatile int *m, unsigned long val) { unsigned long dummy; + smp_mb(); __asm__ __volatile__( "1: ldl_l %0,%4\n" " bis $31,%3,%1\n" @@ -87,6 +94,7 @@ ____xchg(_u64, volatile long *m, unsigned long val) { unsigned long dummy; + smp_mb(); __asm__ __volatile__( "1: ldq_l %0,%4\n" " bis $31,%3,%1\n" @@ -128,9 +136,12 @@ ____xchg(, volatile void *ptr, unsigned long x, int size) * store NEW in MEM. Return the initial value in MEM. Success is * indicated by comparing RETURN with OLD. * - * The memory barrier is placed in SMP unconditionally, in order to - * guarantee that dependency ordering is preserved when a dependency - * is headed by an unsuccessful operation. + * The leading and the trailing memory barriers guarantee that these + * operations are fully ordered. + * + * The trailing memory barrier is placed in SMP unconditionally, in + * order to guarantee that dependency ordering is preserved when a + * dependency is headed by an unsuccessful operation. */ static inline unsigned long @@ -138,6 +149,7 @@ ____cmpxchg(_u8, volatile char *m, unsigned char old, unsigned char new) { unsigned long prev, tmp, cmp, addr64; + smp_mb(); __asm__ __volatile__( " andnot %5,7,%4\n" " insbl %1,%5,%1\n" @@ -165,6 +177,7 @@ ____cmpxchg(_u16, volatile short *m, unsigned short old, unsigned short new) { unsigned long prev, tmp, cmp, addr64; + smp_mb(); __asm__ __volatile__( " andnot %5,7,%4\n" " inswl %1,%5,%1\n" @@ -192,6 +205,7 @@ ____cmpxchg(_u32, volatile int *m, int old, int new) { unsigned long prev, cmp; + smp_mb(); __asm__ __volatile__( "1: ldl_l %0,%5\n" " cmpeq %0,%3,%1\n" @@ -215,6 +229,7 @@ ____cmpxchg(_u64, volatile long *m, unsigned long old, unsigned long new) { unsigned long prev, cmp; + smp_mb(); __asm__ __volatile__( "1: ldq_l %0,%5\n" " cmpeq %0,%3,%1\n" -- cgit v1.2.3-55-g7522 From 4596749339e06dc7a424fc08a15eded850ed78b7 Mon Sep 17 00:00:00 2001 From: Samuel Neves Date: Wed, 21 Feb 2018 20:50:36 +0000 Subject: x86/topology: Update the 'cpu cores' field in /proc/cpuinfo correctly across CPU hotplug operations Without this fix, /proc/cpuinfo will display an incorrect amount of CPU cores, after bringing them offline and online again, as exemplified below: $ cat /proc/cpuinfo | grep cores cpu cores : 4 cpu cores : 8 cpu cores : 8 cpu cores : 20 cpu cores : 4 cpu cores : 3 cpu cores : 2 cpu cores : 2 This patch fixes this by always zeroing the booted_cores variable upon turning off a logical CPU. Tested-by: Dou Liyang Signed-off-by: Samuel Neves Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: jgross@suse.com Cc: luto@kernel.org Cc: prarit@redhat.com Cc: vkuznets@redhat.com Link: http://lkml.kernel.org/r/20180221205036.5244-1-sneves@dei.uc.pt Signed-off-by: Ingo Molnar --- arch/x86/kernel/smpboot.c | 1 + 1 file changed, 1 insertion(+) (limited to 'arch') diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 9eee25d07586..ff99e2b6fc54 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -1437,6 +1437,7 @@ static void remove_siblinginfo(int cpu) cpumask_clear(topology_sibling_cpumask(cpu)); cpumask_clear(topology_core_cpumask(cpu)); c->cpu_core_id = 0; + c->booted_cores = 0; cpumask_clear_cpu(cpu, cpu_sibling_setup_mask); recompute_smt_state(); } -- cgit v1.2.3-55-g7522 From 1b22b4b28fd5fbc51855219e3238b3ab81da8466 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Thu, 22 Feb 2018 17:50:12 +0000 Subject: MIPS: ath25: Check for kzalloc allocation failure Currently there is no null check on a failed allocation of board_data, and hence a null pointer dereference will occurr. Fix this by checking for the out of memory null pointer. Fixes: a7473717483e ("MIPS: ath25: add board configuration detection") Signed-off-by: Colin Ian King Cc: Ralf Baechle Cc: linux-mips@linux-mips.org Cc: # 3.19+ Patchwork: https://patchwork.linux-mips.org/patch/18657/ Signed-off-by: James Hogan --- arch/mips/ath25/board.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'arch') diff --git a/arch/mips/ath25/board.c b/arch/mips/ath25/board.c index 9ab48ff80c1c..6d11ae581ea7 100644 --- a/arch/mips/ath25/board.c +++ b/arch/mips/ath25/board.c @@ -135,6 +135,8 @@ int __init ath25_find_config(phys_addr_t base, unsigned long size) } board_data = kzalloc(BOARD_CONFIG_BUFSZ, GFP_KERNEL); + if (!board_data) + goto error; ath25_board.config = (struct ath25_boarddata *)board_data; memcpy_fromio(board_data, bcfg, 0x100); if (broken_boarddata) { -- cgit v1.2.3-55-g7522 From 902f4d067a50ccf645a58dd5fb1d113b6e0f9b5b Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Thu, 22 Feb 2018 18:08:53 +0000 Subject: MIPS: OCTEON: irq: Check for null return on kzalloc allocation The allocation of host_data is not null checked, leading to a null pointer dereference if the allocation fails. Fix this by adding a null check and return with -ENOMEM. Fixes: 64b139f97c01 ("MIPS: OCTEON: irq: add CIB and other fixes") Signed-off-by: Colin Ian King Acked-by: David Daney Cc: Ralf Baechle Cc: "Steven J. Hill" Cc: linux-mips@linux-mips.org Cc: # 4.0+ Patchwork: https://patchwork.linux-mips.org/patch/18658/ Signed-off-by: James Hogan --- arch/mips/cavium-octeon/octeon-irq.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'arch') diff --git a/arch/mips/cavium-octeon/octeon-irq.c b/arch/mips/cavium-octeon/octeon-irq.c index 5b3a3f6a9ad3..d99f5242169e 100644 --- a/arch/mips/cavium-octeon/octeon-irq.c +++ b/arch/mips/cavium-octeon/octeon-irq.c @@ -2277,6 +2277,8 @@ static int __init octeon_irq_init_cib(struct device_node *ciu_node, } host_data = kzalloc(sizeof(*host_data), GFP_KERNEL); + if (!host_data) + return -ENOMEM; raw_spin_lock_init(&host_data->lock); addr = of_get_address(ciu_node, 0, NULL, NULL); -- cgit v1.2.3-55-g7522 From 9f416319f40cd857d2bb517630e5855a905ef3fb Mon Sep 17 00:00:00 2001 From: Pratyush Anand Date: Mon, 5 Feb 2018 14:28:01 +0100 Subject: arm64: fix unwind_frame() for filtered out fn for function graph tracing do_task_stat() calls get_wchan(), which further does unwind_frame(). unwind_frame() restores frame->pc to original value in case function graph tracer has modified a return address (LR) in a stack frame to hook a function return. However, if function graph tracer has hit a filtered function, then we can't unwind it as ftrace_push_return_trace() has biased the index(frame->graph) with a 'huge negative' offset(-FTRACE_NOTRACE_DEPTH). Moreover, arm64 stack walker defines index(frame->graph) as unsigned int, which can not compare a -ve number. Similar problem we can have with calling of walk_stackframe() from save_stack_trace_tsk() or dump_backtrace(). This patch fixes unwind_frame() to test the index for -ve value and restore index accordingly before we can restore frame->pc. Reproducer: cd /sys/kernel/debug/tracing/ echo schedule > set_graph_notrace echo 1 > options/display-graph echo wakeup > current_tracer ps -ef | grep -i agent Above commands result in: Unable to handle kernel paging request at virtual address ffff801bd3d1e000 pgd = ffff8003cbe97c00 [ffff801bd3d1e000] *pgd=0000000000000000, *pud=0000000000000000 Internal error: Oops: 96000006 [#1] SMP [...] CPU: 5 PID: 11696 Comm: ps Not tainted 4.11.0+ #33 [...] task: ffff8003c21ba000 task.stack: ffff8003cc6c0000 PC is at unwind_frame+0x12c/0x180 LR is at get_wchan+0xd4/0x134 pc : [] lr : [] pstate: 60000145 sp : ffff8003cc6c3ab0 x29: ffff8003cc6c3ab0 x28: 0000000000000001 x27: 0000000000000026 x26: 0000000000000026 x25: 00000000000012d8 x24: 0000000000000000 x23: ffff8003c1c04000 x22: ffff000008c83000 x21: ffff8003c1c00000 x20: 000000000000000f x19: ffff8003c1bc0000 x18: 0000fffffc593690 x17: 0000000000000000 x16: 0000000000000001 x15: 0000b855670e2b60 x14: 0003e97f22cf1d0f x13: 0000000000000001 x12: 0000000000000000 x11: 00000000e8f4883e x10: 0000000154f47ec8 x9 : 0000000070f367c0 x8 : 0000000000000000 x7 : 00008003f7290000 x6 : 0000000000000018 x5 : 0000000000000000 x4 : ffff8003c1c03cb0 x3 : ffff8003c1c03ca0 x2 : 00000017ffe80000 x1 : ffff8003cc6c3af8 x0 : ffff8003d3e9e000 Process ps (pid: 11696, stack limit = 0xffff8003cc6c0000) Stack: (0xffff8003cc6c3ab0 to 0xffff8003cc6c4000) [...] [] unwind_frame+0x12c/0x180 [] do_task_stat+0x864/0x870 [] proc_tgid_stat+0x3c/0x48 [] proc_single_show+0x5c/0xb8 [] seq_read+0x160/0x414 [] __vfs_read+0x58/0x164 [] vfs_read+0x88/0x144 [] SyS_read+0x60/0xc0 [] __sys_trace_return+0x0/0x4 Fixes: 20380bb390a4 (arm64: ftrace: fix a stack tracer's output under function graph tracer) Signed-off-by: Pratyush Anand Signed-off-by: Jerome Marchand [catalin.marinas@arm.com: replace WARN_ON with WARN_ON_ONCE] Signed-off-by: Catalin Marinas --- arch/arm64/include/asm/stacktrace.h | 2 +- arch/arm64/kernel/stacktrace.c | 5 +++++ arch/arm64/kernel/time.c | 2 +- 3 files changed, 7 insertions(+), 2 deletions(-) (limited to 'arch') diff --git a/arch/arm64/include/asm/stacktrace.h b/arch/arm64/include/asm/stacktrace.h index 472ef944e932..902f9edacbea 100644 --- a/arch/arm64/include/asm/stacktrace.h +++ b/arch/arm64/include/asm/stacktrace.h @@ -28,7 +28,7 @@ struct stackframe { unsigned long fp; unsigned long pc; #ifdef CONFIG_FUNCTION_GRAPH_TRACER - unsigned int graph; + int graph; #endif }; diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c index 76809ccd309c..d5718a060672 100644 --- a/arch/arm64/kernel/stacktrace.c +++ b/arch/arm64/kernel/stacktrace.c @@ -59,6 +59,11 @@ int notrace unwind_frame(struct task_struct *tsk, struct stackframe *frame) #ifdef CONFIG_FUNCTION_GRAPH_TRACER if (tsk->ret_stack && (frame->pc == (unsigned long)return_to_handler)) { + if (WARN_ON_ONCE(frame->graph == -1)) + return -EINVAL; + if (frame->graph < -1) + frame->graph += FTRACE_NOTRACE_DEPTH; + /* * This is a case where function graph tracer has * modified a return address (LR) in a stack frame diff --git a/arch/arm64/kernel/time.c b/arch/arm64/kernel/time.c index a4391280fba9..f258636273c9 100644 --- a/arch/arm64/kernel/time.c +++ b/arch/arm64/kernel/time.c @@ -52,7 +52,7 @@ unsigned long profile_pc(struct pt_regs *regs) frame.fp = regs->regs[29]; frame.pc = regs->pc; #ifdef CONFIG_FUNCTION_GRAPH_TRACER - frame.graph = -1; /* no task info */ + frame.graph = current->curr_ret_stack; #endif do { int ret = unwind_frame(NULL, &frame); -- cgit v1.2.3-55-g7522 From 0b2e9904c15963e715d33e5f3f1387f17d19333a Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Fri, 23 Feb 2018 23:29:32 +0100 Subject: KVM: x86: move LAPIC initialization after VMCS creation The initial reset of the local APIC is performed before the VMCS has been created, but it tries to do a vmwrite: vmwrite error: reg 810 value 4a00 (err 18944) CPU: 54 PID: 38652 Comm: qemu-kvm Tainted: G W I 4.16.0-0.rc2.git0.1.fc28.x86_64 #1 Hardware name: Intel Corporation S2600CW/S2600CW, BIOS SE5C610.86B.01.01.0003.090520141303 09/05/2014 Call Trace: vmx_set_rvi [kvm_intel] vmx_hwapic_irr_update [kvm_intel] kvm_lapic_reset [kvm] kvm_create_lapic [kvm] kvm_arch_vcpu_init [kvm] kvm_vcpu_init [kvm] vmx_create_vcpu [kvm_intel] kvm_vm_ioctl [kvm] Move it later, after the VMCS has been created. Fixes: 4191db26b714 ("KVM: x86: Update APICv on APIC reset") Cc: stable@vger.kernel.org Cc: Liran Alon Signed-off-by: Paolo Bonzini --- arch/x86/kvm/lapic.c | 1 - arch/x86/kvm/x86.c | 1 + 2 files changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 924ac8ce9d50..cc5fe7a50dde 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -2165,7 +2165,6 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu) */ vcpu->arch.apic_base = MSR_IA32_APICBASE_ENABLE; static_key_slow_inc(&apic_sw_disabled.key); /* sw disabled at reset */ - kvm_lapic_reset(vcpu, false); kvm_iodevice_init(&apic->dev, &apic_mmio_ops); return 0; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index c8a0b545ac20..ca90d9515137 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -7975,6 +7975,7 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) kvm_vcpu_mtrr_init(vcpu); vcpu_load(vcpu); kvm_vcpu_reset(vcpu, false); + kvm_lapic_reset(vcpu, false); kvm_mmu_setup(vcpu); vcpu_put(vcpu); return 0; -- cgit v1.2.3-55-g7522 From 99158246208b82c0700d09a40d719bb56b32c607 Mon Sep 17 00:00:00 2001 From: Radim Krčmář Date: Wed, 31 Jan 2018 18:12:50 +0100 Subject: KVM: nVMX: preserve SECONDARY_EXEC_DESC without UMIP L1 might want to use SECONDARY_EXEC_DESC, so we must not clear the VMCS bit if UMIP is not being emulated. We must still set the bit when emulating UMIP as the feature can be passed to L2 where L0 will do the emulation and because L2 can change CR4 without a VM exit, we should clear the bit if UMIP is disabled. Fixes: 0367f205a3b7 ("KVM: vmx: add support for emulating UMIP") Reviewed-by: Paolo Bonzini Signed-off-by: Radim Krčmář --- arch/x86/kvm/vmx.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index f427723dc7db..2d2cf8c1f0f4 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -4485,7 +4485,8 @@ static int vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) vmcs_set_bits(SECONDARY_VM_EXEC_CONTROL, SECONDARY_EXEC_DESC); hw_cr4 &= ~X86_CR4_UMIP; - } else + } else if (!is_guest_mode(vcpu) || + !nested_cpu_has2(get_vmcs12(vcpu), SECONDARY_EXEC_DESC)) vmcs_clear_bits(SECONDARY_VM_EXEC_CONTROL, SECONDARY_EXEC_DESC); -- cgit v1.2.3-55-g7522 From 103c763c72dd2df3e8c91f2d7ec88f98ed391111 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Wed, 31 Jan 2018 17:30:21 -0800 Subject: KVM/x86: remove WARN_ON() for when vm_munmap() fails On x86, special KVM memslots such as the TSS region have anonymous memory mappings created on behalf of userspace, and these mappings are removed when the VM is destroyed. It is however possible for removing these mappings via vm_munmap() to fail. This can most easily happen if the thread receives SIGKILL while it's waiting to acquire ->mmap_sem. This triggers the 'WARN_ON(r < 0)' in __x86_set_memory_region(). syzkaller was able to hit this, using 'exit()' to send the SIGKILL. Note that while the vm_munmap() failure results in the mapping not being removed immediately, it is not leaked forever but rather will be freed when the process exits. It's not really possible to handle this failure properly, so almost every other caller of vm_munmap() doesn't check the return value. It's a limitation of having the kernel manage these mappings rather than userspace. So just remove the WARN_ON() so that users can't spam the kernel log with this warning. Fixes: f0d648bdf0a5 ("KVM: x86: map/unmap private slots in __x86_set_memory_region") Reported-by: syzbot Signed-off-by: Eric Biggers Signed-off-by: Radim Krčmář --- arch/x86/kvm/x86.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'arch') diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index ca90d9515137..96edda878dbf 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -8461,10 +8461,8 @@ int __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size) return r; } - if (!size) { - r = vm_munmap(old.userspace_addr, old.npages * PAGE_SIZE); - WARN_ON(r < 0); - } + if (!size) + vm_munmap(old.userspace_addr, old.npages * PAGE_SIZE); return 0; } -- cgit v1.2.3-55-g7522 From 135a06c3a515bbd17729eb04f4f26316d48363d7 Mon Sep 17 00:00:00 2001 From: Chao Gao Date: Sun, 11 Feb 2018 10:06:30 +0800 Subject: KVM: nVMX: Don't halt vcpu when L1 is injecting events to L2 Although L2 is in halt state, it will be in the active state after VM entry if the VM entry is vectoring according to SDM 26.6.2 Activity State. Halting the vcpu here means the event won't be injected to L2 and this decision isn't reported to L1. Thus L0 drops an event that should be injected to L2. Cc: Liran Alon Reviewed-by: Liran Alon Signed-off-by: Chao Gao Signed-off-by: Paolo Bonzini --- arch/x86/kvm/vmx.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 2d2cf8c1f0f4..67b028d8e726 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -11197,7 +11197,12 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) if (ret) return ret; - if (vmcs12->guest_activity_state == GUEST_ACTIVITY_HLT) + /* + * If we're entering a halted L2 vcpu and the L2 vcpu won't be woken + * by event injection, halt vcpu. + */ + if ((vmcs12->guest_activity_state == GUEST_ACTIVITY_HLT) && + !(vmcs12->vm_entry_intr_info_field & INTR_INFO_VALID_MASK)) return kvm_vcpu_halt(vcpu); vmx->nested.nested_run_pending = 1; -- cgit v1.2.3-55-g7522 From 95e057e25892eaa48cad1e2d637b80d0f1a4fac5 Mon Sep 17 00:00:00 2001 From: Wanpeng Li Date: Thu, 8 Feb 2018 15:32:45 +0800 Subject: KVM: X86: Fix SMRAM accessing even if VM is shutdown Reported by syzkaller: WARNING: CPU: 6 PID: 2434 at arch/x86/kvm/vmx.c:6660 handle_ept_misconfig+0x54/0x1e0 [kvm_intel] CPU: 6 PID: 2434 Comm: repro_test Not tainted 4.15.0+ #4 RIP: 0010:handle_ept_misconfig+0x54/0x1e0 [kvm_intel] Call Trace: vmx_handle_exit+0xbd/0xe20 [kvm_intel] kvm_arch_vcpu_ioctl_run+0xdaf/0x1d50 [kvm] kvm_vcpu_ioctl+0x3e9/0x720 [kvm] do_vfs_ioctl+0xa4/0x6a0 SyS_ioctl+0x79/0x90 entry_SYSCALL_64_fastpath+0x25/0x9c The testcase creates a first thread to issue KVM_SMI ioctl, and then creates a second thread to mmap and operate on the same vCPU. This triggers a race condition when running the testcase with multiple threads. Sometimes one thread exits with a triple fault while another thread mmaps and operates on the same vCPU. Because CS=0x3000/IP=0x8000 is not mapped, accessing the SMI handler results in an EPT misconfig. This patch fixes it by returning RET_PF_EMULATE in kvm_handle_bad_page(), which will go on to cause an emulation failure and an exit with KVM_EXIT_INTERNAL_ERROR. Reported-by: syzbot+c1d9517cab094dae65e446c0c5b4de6c40f4dc58@syzkaller.appspotmail.com Cc: Paolo Bonzini Cc: Radim Krčmář Cc: stable@vger.kernel.org Signed-off-by: Wanpeng Li Signed-off-by: Paolo Bonzini --- arch/x86/kvm/mmu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 8eca1d04aeb8..6c5a82c74750 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -3029,7 +3029,7 @@ static int kvm_handle_bad_page(struct kvm_vcpu *vcpu, gfn_t gfn, kvm_pfn_t pfn) return RET_PF_RETRY; } - return -EFAULT; + return RET_PF_EMULATE; } static void transparent_hugepage_adjust(struct kvm_vcpu *vcpu, -- cgit v1.2.3-55-g7522 From f75e4924f0152be747bf04c9d16bb23fd8baf5f9 Mon Sep 17 00:00:00 2001 From: Sebastian Ott Date: Thu, 22 Feb 2018 13:04:39 +0100 Subject: kvm: fix warning for non-x86 builds Fix the following sparse warning by moving the prototype of kvm_arch_mmu_notifier_invalidate_range() to linux/kvm_host.h . CHECK arch/s390/kvm/../../../virt/kvm/kvm_main.c arch/s390/kvm/../../../virt/kvm/kvm_main.c:138:13: warning: symbol 'kvm_arch_mmu_notifier_invalidate_range' was not declared. Should it be static? Signed-off-by: Sebastian Ott Signed-off-by: Paolo Bonzini --- arch/x86/include/asm/kvm_host.h | 3 --- include/linux/kvm_host.h | 3 +++ 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'arch') diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index dd6f57a54a26..0a9e330b34f0 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1464,7 +1464,4 @@ static inline int kvm_cpu_get_apicid(int mps_cpu) #define put_smstate(type, buf, offset, val) \ *(type *)((buf) + (offset) - 0x7e00) = val -void kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm, - unsigned long start, unsigned long end); - #endif /* _ASM_X86_KVM_HOST_H */ diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 84b9c50693f2..6930c63126c7 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1273,4 +1273,7 @@ static inline long kvm_arch_vcpu_async_ioctl(struct file *filp, } #endif /* CONFIG_HAVE_KVM_VCPU_ASYNC_IOCTL */ +void kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm, + unsigned long start, unsigned long end); + #endif -- cgit v1.2.3-55-g7522 From fe2a3027e74e40a3ece3a4c1e4e51403090a907a Mon Sep 17 00:00:00 2001 From: Radim Krčmář Date: Thu, 1 Feb 2018 22:16:21 +0100 Subject: KVM: x86: fix backward migration with async_PF Guests on new hypersiors might set KVM_ASYNC_PF_DELIVERY_AS_PF_VMEXIT bit when enabling async_PF, but this bit is reserved on old hypervisors, which results in a failure upon migration. To avoid breaking different cases, we are checking for CPUID feature bit before enabling the feature and nothing else. Fixes: 52a5c155cf79 ("KVM: async_pf: Let guest support delivery of async_pf from guest mode") Cc: Reviewed-by: Wanpeng Li Reviewed-by: David Hildenbrand Signed-off-by: Radim Krčmář Signed-off-by: Paolo Bonzini --- Documentation/virtual/kvm/cpuid.txt | 4 ++++ Documentation/virtual/kvm/msr.txt | 3 ++- arch/x86/include/uapi/asm/kvm_para.h | 1 + arch/x86/kernel/kvm.c | 8 ++++---- arch/x86/kvm/cpuid.c | 3 ++- 5 files changed, 13 insertions(+), 6 deletions(-) (limited to 'arch') diff --git a/Documentation/virtual/kvm/cpuid.txt b/Documentation/virtual/kvm/cpuid.txt index dcab6dc11e3b..87a7506f31c2 100644 --- a/Documentation/virtual/kvm/cpuid.txt +++ b/Documentation/virtual/kvm/cpuid.txt @@ -58,6 +58,10 @@ KVM_FEATURE_PV_TLB_FLUSH || 9 || guest checks this feature bit || || before enabling paravirtualized || || tlb flush. ------------------------------------------------------------------------------ +KVM_FEATURE_ASYNC_PF_VMEXIT || 10 || paravirtualized async PF VM exit + || || can be enabled by setting bit 2 + || || when writing to msr 0x4b564d02 +------------------------------------------------------------------------------ KVM_FEATURE_CLOCKSOURCE_STABLE_BIT || 24 || host will warn if no guest-side || || per-cpu warps are expected in || || kvmclock. diff --git a/Documentation/virtual/kvm/msr.txt b/Documentation/virtual/kvm/msr.txt index 1ebecc115dc6..f3f0d57ced8e 100644 --- a/Documentation/virtual/kvm/msr.txt +++ b/Documentation/virtual/kvm/msr.txt @@ -170,7 +170,8 @@ MSR_KVM_ASYNC_PF_EN: 0x4b564d02 when asynchronous page faults are enabled on the vcpu 0 when disabled. Bit 1 is 1 if asynchronous page faults can be injected when vcpu is in cpl == 0. Bit 2 is 1 if asynchronous page faults - are delivered to L1 as #PF vmexits. + are delivered to L1 as #PF vmexits. Bit 2 can be set only if + KVM_FEATURE_ASYNC_PF_VMEXIT is present in CPUID. First 4 byte of 64 byte memory location will be written to by the hypervisor at the time of asynchronous page fault (APF) diff --git a/arch/x86/include/uapi/asm/kvm_para.h b/arch/x86/include/uapi/asm/kvm_para.h index 7a2ade4aa235..6cfa9c8cb7d6 100644 --- a/arch/x86/include/uapi/asm/kvm_para.h +++ b/arch/x86/include/uapi/asm/kvm_para.h @@ -26,6 +26,7 @@ #define KVM_FEATURE_PV_EOI 6 #define KVM_FEATURE_PV_UNHALT 7 #define KVM_FEATURE_PV_TLB_FLUSH 9 +#define KVM_FEATURE_ASYNC_PF_VMEXIT 10 /* The last 8 bits are used to indicate how to interpret the flags field * in pvclock structure. If no bits are set, all flags are ignored. diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 4e37d1a851a6..971babe964d2 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -341,10 +341,10 @@ static void kvm_guest_cpu_init(void) #endif pa |= KVM_ASYNC_PF_ENABLED; - /* Async page fault support for L1 hypervisor is optional */ - if (wrmsr_safe(MSR_KVM_ASYNC_PF_EN, - (pa | KVM_ASYNC_PF_DELIVERY_AS_PF_VMEXIT) & 0xffffffff, pa >> 32) < 0) - wrmsrl(MSR_KVM_ASYNC_PF_EN, pa); + if (kvm_para_has_feature(KVM_FEATURE_ASYNC_PF_VMEXIT)) + pa |= KVM_ASYNC_PF_DELIVERY_AS_PF_VMEXIT; + + wrmsrl(MSR_KVM_ASYNC_PF_EN, pa); __this_cpu_write(apf_reason.enabled, 1); printk(KERN_INFO"KVM setup async PF for cpu %d\n", smp_processor_id()); diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index a0c5a69bc7c4..b671fc2d0422 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -607,7 +607,8 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, (1 << KVM_FEATURE_PV_EOI) | (1 << KVM_FEATURE_CLOCKSOURCE_STABLE_BIT) | (1 << KVM_FEATURE_PV_UNHALT) | - (1 << KVM_FEATURE_PV_TLB_FLUSH); + (1 << KVM_FEATURE_PV_TLB_FLUSH) | + (1 << KVM_FEATURE_ASYNC_PF_VMEXIT); if (sched_info_on()) entry->eax |= (1 << KVM_FEATURE_STEAL_TIME); -- cgit v1.2.3-55-g7522 From afdc3f588850a6fbc996205ee2d472eb4426afb3 Mon Sep 17 00:00:00 2001 From: Dou Liyang Date: Wed, 17 Jan 2018 11:46:54 +0800 Subject: x86/kvm: Make parse_no_xxx __init for kvm The early_param() is only called during kernel initialization, So Linux marks the functions of it with __init macro to save memory. But it forgot to mark the parse_no_kvmapf/stealacc/kvmclock_vsyscall, So, Make them __init as well. Cc: Paolo Bonzini Cc: rkrcmar@redhat.com Cc: kvm@vger.kernel.org Cc: Thomas Gleixner Cc: Ingo Molnar Cc: "H. Peter Anvin" Cc: Juergen Gross Cc: x86@kernel.org Signed-off-by: Dou Liyang Signed-off-by: Paolo Bonzini --- arch/x86/kernel/kvm.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 971babe964d2..ee7d5c951864 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -49,7 +49,7 @@ static int kvmapf = 1; -static int parse_no_kvmapf(char *arg) +static int __init parse_no_kvmapf(char *arg) { kvmapf = 0; return 0; @@ -58,7 +58,7 @@ static int parse_no_kvmapf(char *arg) early_param("no-kvmapf", parse_no_kvmapf); static int steal_acc = 1; -static int parse_no_stealacc(char *arg) +static int __init parse_no_stealacc(char *arg) { steal_acc = 0; return 0; @@ -67,7 +67,7 @@ static int parse_no_stealacc(char *arg) early_param("no-steal-acc", parse_no_stealacc); static int kvmclock_vsyscall = 1; -static int parse_no_kvmclock_vsyscall(char *arg) +static int __init parse_no_kvmclock_vsyscall(char *arg) { kvmclock_vsyscall = 0; return 0; -- cgit v1.2.3-55-g7522 From 4f2f61fc507176edd65826fbedc8987dea29b9d5 Mon Sep 17 00:00:00 2001 From: Wanpeng Li Date: Sun, 4 Feb 2018 22:57:58 -0800 Subject: KVM: X86: Avoid traversing all the cpus for pv tlb flush when steal time is disabled Avoid traversing all the cpus for pv tlb flush when steal time is disabled since pv tlb flush depends on the field in steal time for shared data. Cc: Paolo Bonzini Cc: Radim KrÄmář Signed-off-by: Wanpeng Li Signed-off-by: Paolo Bonzini --- arch/x86/kernel/kvm.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index ee7d5c951864..bc1a27280c4b 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -545,7 +545,8 @@ static void __init kvm_guest_init(void) pv_time_ops.steal_clock = kvm_steal_clock; } - if (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH)) + if (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH) && + !kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) pv_mmu_ops.flush_tlb_others = kvm_flush_tlb_others; if (kvm_para_has_feature(KVM_FEATURE_PV_EOI)) @@ -633,7 +634,8 @@ static __init int kvm_setup_pv_tlb_flush(void) { int cpu; - if (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH)) { + if (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH) && + !kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) { for_each_possible_cpu(cpu) { zalloc_cpumask_var_node(per_cpu_ptr(&__pv_tlb_mask, cpu), GFP_KERNEL, cpu_to_node(cpu)); -- cgit v1.2.3-55-g7522 From 3e233385ef4a217a2812115ed84d4be36eb16817 Mon Sep 17 00:00:00 2001 From: Brijesh Singh Date: Fri, 23 Feb 2018 12:36:50 -0600 Subject: KVM: SVM: no need to call access_ok() in LAUNCH_MEASURE command Using the access_ok() to validate the input before issuing the SEV command does not buy us anything in this case. If userland is giving us a garbage pointer then copy_to_user() will catch it when we try to return the measurement. Suggested-by: Al Viro Fixes: 0d0736f76347 (KVM: SVM: Add support for KVM_SEV_LAUNCH_MEASURE ...) Cc: Paolo Bonzini Cc: Radim Krčmář Cc: Borislav Petkov Cc: Tom Lendacky Cc: linux-kernel@vger.kernel.org Cc: Joerg Roedel Signed-off-by: Brijesh Singh Signed-off-by: Paolo Bonzini --- arch/x86/kvm/svm.c | 16 +++++++--------- 1 file changed, 7 insertions(+), 9 deletions(-) (limited to 'arch') diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index b3e488a74828..ca69d53d7e6d 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -6236,16 +6236,18 @@ e_free: static int sev_launch_measure(struct kvm *kvm, struct kvm_sev_cmd *argp) { + void __user *measure = (void __user *)(uintptr_t)argp->data; struct kvm_sev_info *sev = &kvm->arch.sev_info; struct sev_data_launch_measure *data; struct kvm_sev_launch_measure params; + void __user *p = NULL; void *blob = NULL; int ret; if (!sev_guest(kvm)) return -ENOTTY; - if (copy_from_user(¶ms, (void __user *)(uintptr_t)argp->data, sizeof(params))) + if (copy_from_user(¶ms, measure, sizeof(params))) return -EFAULT; data = kzalloc(sizeof(*data), GFP_KERNEL); @@ -6256,17 +6258,13 @@ static int sev_launch_measure(struct kvm *kvm, struct kvm_sev_cmd *argp) if (!params.len) goto cmd; - if (params.uaddr) { + p = (void __user *)(uintptr_t)params.uaddr; + if (p) { if (params.len > SEV_FW_BLOB_MAX_SIZE) { ret = -EINVAL; goto e_free; } - if (!access_ok(VERIFY_WRITE, params.uaddr, params.len)) { - ret = -EFAULT; - goto e_free; - } - ret = -ENOMEM; blob = kmalloc(params.len, GFP_KERNEL); if (!blob) @@ -6290,13 +6288,13 @@ cmd: goto e_free_blob; if (blob) { - if (copy_to_user((void __user *)(uintptr_t)params.uaddr, blob, params.len)) + if (copy_to_user(p, blob, params.len)) ret = -EFAULT; } done: params.len = data->len; - if (copy_to_user((void __user *)(uintptr_t)argp->data, ¶ms, sizeof(params))) + if (copy_to_user(measure, ¶ms, sizeof(params))) ret = -EFAULT; e_free_blob: kfree(blob); -- cgit v1.2.3-55-g7522 From 7607b7174405aec7441ff6c970833c463114040a Mon Sep 17 00:00:00 2001 From: Brijesh Singh Date: Mon, 19 Feb 2018 10:14:44 -0600 Subject: KVM: SVM: install RSM intercept RSM instruction is used by the SMM handler to return from SMM mode. Currently, rsm causes a #UD - which results in instruction fetch, decode, and emulate. By installing the RSM intercept we can avoid the instruction fetch since we know that #VMEXIT was due to rsm. The patch is required for the SEV guest, because in case of SEV guest memory is encrypted with guest-specific key and hypervisor will not able to fetch the instruction bytes from the guest memory. Cc: Paolo Bonzini Cc: Radim Krčmář Cc: Joerg Roedel Cc: Borislav Petkov Cc: Tom Lendacky Signed-off-by: Brijesh Singh Signed-off-by: Paolo Bonzini --- arch/x86/kvm/svm.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index ca69d53d7e6d..4aeb665ffbb0 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -300,6 +300,8 @@ module_param(vgif, int, 0444); static int sev = IS_ENABLED(CONFIG_AMD_MEM_ENCRYPT_ACTIVE_BY_DEFAULT); module_param(sev, int, 0444); +static u8 rsm_ins_bytes[] = "\x0f\xaa"; + static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0); static void svm_flush_tlb(struct kvm_vcpu *vcpu, bool invalidate_gpa); static void svm_complete_interrupts(struct vcpu_svm *svm); @@ -1383,6 +1385,7 @@ static void init_vmcb(struct vcpu_svm *svm) set_intercept(svm, INTERCEPT_SKINIT); set_intercept(svm, INTERCEPT_WBINVD); set_intercept(svm, INTERCEPT_XSETBV); + set_intercept(svm, INTERCEPT_RSM); if (!kvm_mwait_in_guest()) { set_intercept(svm, INTERCEPT_MONITOR); @@ -3699,6 +3702,12 @@ static int emulate_on_interception(struct vcpu_svm *svm) return emulate_instruction(&svm->vcpu, 0) == EMULATE_DONE; } +static int rsm_interception(struct vcpu_svm *svm) +{ + return x86_emulate_instruction(&svm->vcpu, 0, 0, + rsm_ins_bytes, 2) == EMULATE_DONE; +} + static int rdpmc_interception(struct vcpu_svm *svm) { int err; @@ -4541,7 +4550,7 @@ static int (*const svm_exit_handlers[])(struct vcpu_svm *svm) = { [SVM_EXIT_MWAIT] = mwait_interception, [SVM_EXIT_XSETBV] = xsetbv_interception, [SVM_EXIT_NPF] = npf_interception, - [SVM_EXIT_RSM] = emulate_on_interception, + [SVM_EXIT_RSM] = rsm_interception, [SVM_EXIT_AVIC_INCOMPLETE_IPI] = avic_incomplete_ipi_interception, [SVM_EXIT_AVIC_UNACCELERATED_ACCESS] = avic_unaccelerated_access_interception, }; -- cgit v1.2.3-55-g7522 From 9c5e0afaf15788bcbd1c3469da701ac3da826886 Mon Sep 17 00:00:00 2001 From: Brijesh Singh Date: Mon, 19 Feb 2018 10:13:25 -0600 Subject: KVM: SVM: Fix SEV LAUNCH_SECRET command The SEV LAUNCH_SECRET command fails with error code 'invalid param' because we missed filling the guest and header system physical address while issuing the command. Fixes: 9f5b5b950aa9 (KVM: SVM: Add support for SEV LAUNCH_SECRET command) Cc: Paolo Bonzini Cc: Radim Krčmář Cc: Borislav Petkov Cc: Tom Lendacky Cc: linux-kernel@vger.kernel.org Cc: Joerg Roedel Signed-off-by: Brijesh Singh Signed-off-by: Paolo Bonzini --- arch/x86/kvm/svm.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) (limited to 'arch') diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 4aeb665ffbb0..3d8377f75eda 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -6604,7 +6604,7 @@ static int sev_launch_secret(struct kvm *kvm, struct kvm_sev_cmd *argp) struct page **pages; void *blob, *hdr; unsigned long n; - int ret; + int ret, offset; if (!sev_guest(kvm)) return -ENOTTY; @@ -6630,6 +6630,10 @@ static int sev_launch_secret(struct kvm *kvm, struct kvm_sev_cmd *argp) if (!data) goto e_unpin_memory; + offset = params.guest_uaddr & (PAGE_SIZE - 1); + data->guest_address = __sme_page_pa(pages[0]) + offset; + data->guest_len = params.guest_len; + blob = psp_copy_user_blob(params.trans_uaddr, params.trans_len); if (IS_ERR(blob)) { ret = PTR_ERR(blob); @@ -6644,8 +6648,8 @@ static int sev_launch_secret(struct kvm *kvm, struct kvm_sev_cmd *argp) ret = PTR_ERR(hdr); goto e_free_blob; } - data->trans_address = __psp_pa(blob); - data->trans_len = params.trans_len; + data->hdr_address = __psp_pa(hdr); + data->hdr_len = params.hdr_len; data->handle = sev->handle; ret = sev_issue_cmd(kvm, SEV_CMD_LAUNCH_UPDATE_SECRET, data, &argp->error); -- cgit v1.2.3-55-g7522 From c0c6bb2322964bd264b4ddedaa5776f40c709f0c Mon Sep 17 00:00:00 2001 From: Shyam Saini Date: Tue, 20 Feb 2018 18:08:08 +0530 Subject: ARM: dts: imx6dl: Include correct dtsi file for Engicam i.CoreM6 DualLite/Solo RQS This patch fixes the wrongly included dtsi file which was breaking mainline support for Engicam i.CoreM6 DualLite/Solo RQS. As per the board name, the correct file should be imx6dl.dtsi instead of imx6q.dtsi Reported-by: Michael Trimarchi Suggested-by: Jagan Teki Signed-off-by: Shyam Saini Reviewed-by: Fabio Estevam Fixes: 7a9caba55a61 ("ARM: dts: imx6dl: Add Engicam i.CoreM6 DualLite/Solo RQS initial support") Signed-off-by: Shawn Guo --- arch/arm/boot/dts/imx6dl-icore-rqs.dts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/arm/boot/dts/imx6dl-icore-rqs.dts b/arch/arm/boot/dts/imx6dl-icore-rqs.dts index cf42c2f5cdc7..1281bc39b7ab 100644 --- a/arch/arm/boot/dts/imx6dl-icore-rqs.dts +++ b/arch/arm/boot/dts/imx6dl-icore-rqs.dts @@ -42,7 +42,7 @@ /dts-v1/; -#include "imx6q.dtsi" +#include "imx6dl.dtsi" #include "imx6qdl-icore-rqs.dtsi" / { -- cgit v1.2.3-55-g7522 From 753e8abc36b2c966caea075db0c845563c8a19bf Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Fri, 23 Feb 2018 18:04:48 +0000 Subject: arm64: mm: fix thinko in non-global page table attribute check The routine pgattr_change_is_safe() was extended in commit 4e6020565596 ("arm64: mm: Permit transitioning from Global to Non-Global without BBM") to permit changing the nG attribute from not set to set, but did so in a way that inadvertently disallows such changes if other permitted attribute changes take place at the same time. So update the code to take this into account. Fixes: 4e6020565596 ("arm64: mm: Permit transitioning from Global to ...") Cc: # 4.14.x- Acked-by: Mark Rutland Reviewed-by: Marc Zyngier Acked-by: Will Deacon Signed-off-by: Ard Biesheuvel Signed-off-by: Catalin Marinas --- arch/arm64/mm/mmu.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'arch') diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 84a019f55022..8c704f1e53c2 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -108,7 +108,7 @@ static bool pgattr_change_is_safe(u64 old, u64 new) * The following mapping attributes may be updated in live * kernel mappings without the need for break-before-make. */ - static const pteval_t mask = PTE_PXN | PTE_RDONLY | PTE_WRITE; + static const pteval_t mask = PTE_PXN | PTE_RDONLY | PTE_WRITE | PTE_NG; /* creating or taking down mappings is always safe */ if (old == 0 || new == 0) @@ -118,9 +118,9 @@ static bool pgattr_change_is_safe(u64 old, u64 new) if ((old | new) & PTE_CONT) return false; - /* Transitioning from Global to Non-Global is safe */ - if (((old ^ new) == PTE_NG) && (new & PTE_NG)) - return true; + /* Transitioning from Non-Global to Global is unsafe */ + if (old & ~new & PTE_NG) + return false; return ((old ^ new) & ~mask) == 0; } -- cgit v1.2.3-55-g7522 From ab4af60534107c55b00fa462eca0385dcef92384 Mon Sep 17 00:00:00 2001 From: Andrea Parri Date: Tue, 20 Feb 2018 11:17:28 +0100 Subject: riscv/barrier: Define __smp_{mb,rmb,wmb} Introduce __smp_{mb,rmb,wmb}, and rely on the generic definitions for smp_{mb,rmb,wmb}. A first consequence is that smp_{mb,rmb,wmb} map to a compiler barrier on !SMP (while their definition remains unchanged on SMP). As a further consequence, smp_load_acquire and smp_store_release have "fence rw,rw" instead of "fence iorw,iorw". Signed-off-by: Andrea Parri Signed-off-by: Palmer Dabbelt --- arch/riscv/include/asm/barrier.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'arch') diff --git a/arch/riscv/include/asm/barrier.h b/arch/riscv/include/asm/barrier.h index c0319cbf1eec..5510366d169a 100644 --- a/arch/riscv/include/asm/barrier.h +++ b/arch/riscv/include/asm/barrier.h @@ -34,9 +34,9 @@ #define wmb() RISCV_FENCE(ow,ow) /* These barriers do not need to enforce ordering on devices, just memory. */ -#define smp_mb() RISCV_FENCE(rw,rw) -#define smp_rmb() RISCV_FENCE(r,r) -#define smp_wmb() RISCV_FENCE(w,w) +#define __smp_mb() RISCV_FENCE(rw,rw) +#define __smp_rmb() RISCV_FENCE(r,r) +#define __smp_wmb() RISCV_FENCE(w,w) /* * This is a very specific barrier: it's currently only used in two places in -- cgit v1.2.3-55-g7522 From 13a55372b64e00e564a08d785ca87bd9d454ba30 Mon Sep 17 00:00:00 2001 From: David S. Miller Date: Mon, 26 Feb 2018 13:41:47 -0500 Subject: ARM: orion5x: Revert commit 4904dbda41c8. It is not valid for orion5x to use mac_pton(). First of all, the orion5x buffer is not NULL terminated. mac_pton() has no business operating on non-NULL terminated buffers because only the caller can know that this is valid and in what manner it is ok to parse this NULL'less buffer. Second of all, orion5x operates on an __iomem pointer, which cannot be dereferenced using normal C pointer operations. Accesses to such areas much be performed with the proper iomem accessors. Fixes: 4904dbda41c8 ("ARM: orion5x: use mac_pton() helper") Signed-off-by: David S. Miller --- arch/arm/mach-orion5x/Kconfig | 3 -- arch/arm/mach-orion5x/dns323-setup.c | 53 ++++++++++++++++++++++++++++++++++-- arch/arm/mach-orion5x/tsx09-common.c | 49 ++++++++++++++++++++++++++++++--- 3 files changed, 95 insertions(+), 10 deletions(-) (limited to 'arch') diff --git a/arch/arm/mach-orion5x/Kconfig b/arch/arm/mach-orion5x/Kconfig index 2a7bb6ccdcb7..a810f4dd34b1 100644 --- a/arch/arm/mach-orion5x/Kconfig +++ b/arch/arm/mach-orion5x/Kconfig @@ -58,7 +58,6 @@ config MACH_KUROBOX_PRO config MACH_DNS323 bool "D-Link DNS-323" - select GENERIC_NET_UTILS select I2C_BOARDINFO if I2C help Say 'Y' here if you want your kernel to support the @@ -66,7 +65,6 @@ config MACH_DNS323 config MACH_TS209 bool "QNAP TS-109/TS-209" - select GENERIC_NET_UTILS help Say 'Y' here if you want your kernel to support the QNAP TS-109/TS-209 platform. @@ -101,7 +99,6 @@ config MACH_LINKSTATION_LS_HGL config MACH_TS409 bool "QNAP TS-409" - select GENERIC_NET_UTILS help Say 'Y' here if you want your kernel to support the QNAP TS-409 platform. diff --git a/arch/arm/mach-orion5x/dns323-setup.c b/arch/arm/mach-orion5x/dns323-setup.c index cd483bfb5ca8..d13344b2ddcd 100644 --- a/arch/arm/mach-orion5x/dns323-setup.c +++ b/arch/arm/mach-orion5x/dns323-setup.c @@ -173,10 +173,42 @@ static struct mv643xx_eth_platform_data dns323_eth_data = { .phy_addr = MV643XX_ETH_PHY_ADDR(8), }; +/* dns323_parse_hex_*() taken from tsx09-common.c; should a common copy of these + * functions be kept somewhere? + */ +static int __init dns323_parse_hex_nibble(char n) +{ + if (n >= '0' && n <= '9') + return n - '0'; + + if (n >= 'A' && n <= 'F') + return n - 'A' + 10; + + if (n >= 'a' && n <= 'f') + return n - 'a' + 10; + + return -1; +} + +static int __init dns323_parse_hex_byte(const char *b) +{ + int hi; + int lo; + + hi = dns323_parse_hex_nibble(b[0]); + lo = dns323_parse_hex_nibble(b[1]); + + if (hi < 0 || lo < 0) + return -1; + + return (hi << 4) | lo; +} + static int __init dns323_read_mac_addr(void) { u_int8_t addr[6]; - void __iomem *mac_page; + int i; + char *mac_page; /* MAC address is stored as a regular ol' string in /dev/mtdblock4 * (0x007d0000-0x00800000) starting at offset 196480 (0x2ff80). @@ -185,8 +217,23 @@ static int __init dns323_read_mac_addr(void) if (!mac_page) return -ENOMEM; - if (!mac_pton((__force const char *) mac_page, addr)) - goto error_fail; + /* Sanity check the string we're looking at */ + for (i = 0; i < 5; i++) { + if (*(mac_page + (i * 3) + 2) != ':') { + goto error_fail; + } + } + + for (i = 0; i < 6; i++) { + int byte; + + byte = dns323_parse_hex_byte(mac_page + (i * 3)); + if (byte < 0) { + goto error_fail; + } + + addr[i] = byte; + } iounmap(mac_page); printk("DNS-323: Found ethernet MAC address: %pM\n", addr); diff --git a/arch/arm/mach-orion5x/tsx09-common.c b/arch/arm/mach-orion5x/tsx09-common.c index 89774985d380..905d4f2dd0b8 100644 --- a/arch/arm/mach-orion5x/tsx09-common.c +++ b/arch/arm/mach-orion5x/tsx09-common.c @@ -53,12 +53,53 @@ struct mv643xx_eth_platform_data qnap_tsx09_eth_data = { .phy_addr = MV643XX_ETH_PHY_ADDR(8), }; +static int __init qnap_tsx09_parse_hex_nibble(char n) +{ + if (n >= '0' && n <= '9') + return n - '0'; + + if (n >= 'A' && n <= 'F') + return n - 'A' + 10; + + if (n >= 'a' && n <= 'f') + return n - 'a' + 10; + + return -1; +} + +static int __init qnap_tsx09_parse_hex_byte(const char *b) +{ + int hi; + int lo; + + hi = qnap_tsx09_parse_hex_nibble(b[0]); + lo = qnap_tsx09_parse_hex_nibble(b[1]); + + if (hi < 0 || lo < 0) + return -1; + + return (hi << 4) | lo; +} + static int __init qnap_tsx09_check_mac_addr(const char *addr_str) { u_int8_t addr[6]; + int i; - if (!mac_pton(addr_str, addr)) - return -1; + for (i = 0; i < 6; i++) { + int byte; + + /* + * Enforce "xx:xx:xx:xx:xx:xx\n" format. + */ + if (addr_str[(i * 3) + 2] != ((i < 5) ? ':' : '\n')) + return -1; + + byte = qnap_tsx09_parse_hex_byte(addr_str + (i * 3)); + if (byte < 0) + return -1; + addr[i] = byte; + } printk(KERN_INFO "tsx09: found ethernet mac address %pM\n", addr); @@ -77,12 +118,12 @@ void __init qnap_tsx09_find_mac_addr(u32 mem_base, u32 size) unsigned long addr; for (addr = mem_base; addr < (mem_base + size); addr += 1024) { - void __iomem *nor_page; + char *nor_page; int ret = 0; nor_page = ioremap(addr, 1024); if (nor_page != NULL) { - ret = qnap_tsx09_check_mac_addr((__force const char *)nor_page); + ret = qnap_tsx09_check_mac_addr(nor_page); iounmap(nor_page); } -- cgit v1.2.3-55-g7522 From 133390fe497b8c3b63e84383300c03a13b007e08 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 26 Feb 2018 21:38:58 +0100 Subject: ARM: omap2: set CONFIG_LIRC=y in defconfig The CONFIG_LIRC symbol has changed from 'tristate' to 'bool, so we now get a warning for omap2plus_defconfig: arch/arm/configs/omap2plus_defconfig:322:warning: symbol value 'm' invalid for LIRC This changes the file to mark the symbol as built-in to get rid of the warning. Fixes: a60d64b15c20 ("media: lirc: lirc interface should not be a raw decoder") Signed-off-by: Arnd Bergmann --- arch/arm/configs/omap2plus_defconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/arm/configs/omap2plus_defconfig b/arch/arm/configs/omap2plus_defconfig index 2f145c4af93a..92674f247a12 100644 --- a/arch/arm/configs/omap2plus_defconfig +++ b/arch/arm/configs/omap2plus_defconfig @@ -319,7 +319,7 @@ CONFIG_MEDIA_CAMERA_SUPPORT=y CONFIG_RC_CORE=m CONFIG_MEDIA_CONTROLLER=y CONFIG_VIDEO_V4L2_SUBDEV_API=y -CONFIG_LIRC=m +CONFIG_LIRC=y CONFIG_RC_DEVICES=y CONFIG_IR_RX51=m CONFIG_V4L_PLATFORM_DRIVERS=y -- cgit v1.2.3-55-g7522 From 29d1d52b06fbf4b26b592310bff7c4fe3ffaca07 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Sun, 25 Feb 2018 14:08:14 +0100 Subject: ARM: dts: Set D-Link DNS-313 SATA to muxmode 0 This stops the driver from trying to probe the ATA slave interface. The vendor code enables the slave interface but the driver in the vendor tree does not make use of it. Setting it to muxmode 0 disables the slave interface: the hardware only has the master interface connected to the one harddrive slot anyways. Without this change booting takes excessive time, so it is very annoying to end users. Fixes: dd5c0561db75 ("ARM: dts: Add basic devicetree for D-Link DNS-313") Signed-off-by: Linus Walleij Signed-off-by: Arnd Bergmann --- arch/arm/boot/dts/gemini-dlink-dns-313.dts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/arm/boot/dts/gemini-dlink-dns-313.dts b/arch/arm/boot/dts/gemini-dlink-dns-313.dts index 08568ce24d06..da8bb9d60f99 100644 --- a/arch/arm/boot/dts/gemini-dlink-dns-313.dts +++ b/arch/arm/boot/dts/gemini-dlink-dns-313.dts @@ -269,7 +269,7 @@ sata: sata@46000000 { /* The ROM uses this muxmode */ - cortina,gemini-ata-muxmode = <3>; + cortina,gemini-ata-muxmode = <0>; cortina,gemini-enable-sata-bridge; status = "okay"; }; -- cgit v1.2.3-55-g7522 From d269176e766c71c998cb75b4ea8cbc321cc0019d Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Mon, 26 Feb 2018 22:00:47 +0100 Subject: bpf, ppc64: fix out of bounds access in tail call While working on 16338a9b3ac3 ("bpf, arm64: fix out of bounds access in tail call") I noticed that ppc64 JIT is partially affected as well. While the bound checking is correctly performed as unsigned comparison, the register with the index value however, is never truncated into 32 bit space, so e.g. a index value of 0x100000000ULL with a map of 1 element would pass with PPC_CMPLW() whereas we later on continue with the full 64 bit register value. Therefore, as we do in interpreter and other JITs truncate the value to 32 bit initially in order to fix access. Fixes: ce0761419fae ("powerpc/bpf: Implement support for tail calls") Signed-off-by: Daniel Borkmann Reviewed-by: Naveen N. Rao Tested-by: Naveen N. Rao Signed-off-by: Alexei Starovoitov --- arch/powerpc/net/bpf_jit_comp64.c | 1 + 1 file changed, 1 insertion(+) (limited to 'arch') diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c index 0a34b0cec7b7..0ef3d9580e98 100644 --- a/arch/powerpc/net/bpf_jit_comp64.c +++ b/arch/powerpc/net/bpf_jit_comp64.c @@ -240,6 +240,7 @@ static void bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 * goto out; */ PPC_LWZ(b2p[TMP_REG_1], b2p_bpf_array, offsetof(struct bpf_array, map.max_entries)); + PPC_RLWINM(b2p_index, b2p_index, 0, 0, 31); PPC_CMPLW(b2p_index, b2p[TMP_REG_1]); PPC_BCC(COND_GE, out); -- cgit v1.2.3-55-g7522 From 0a5aff64f20d92c5a6e9aeed7b5950b0b817bcd9 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Mon, 26 Feb 2018 17:00:35 -0800 Subject: ARM: dts: NSP: Fix amount of RAM on BCM958625HR Jon attempted to fix the amount of RAM on the BCM958625HR in commit c53beb47f621 ("ARM: dts: NSP: Correct RAM amount for BCM958625HR board") but it seems like we tripped over some poorly documented schematics. The top-level page of the schematics says the board has 2GB, but when you end-up scrolling to page 6, you see two chips of 4GBit (512MB) but what the bootloader really initializes only 512MB, any attempt to use more than that results in data aborts. Fix this again back to 512MB. Fixes: c53beb47f621 ("ARM: dts: NSP: Correct RAM amount for BCM958625HR board") Acked-by: Jon Mason Signed-off-by: Florian Fainelli --- arch/arm/boot/dts/bcm958625hr.dts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/arm/boot/dts/bcm958625hr.dts b/arch/arm/boot/dts/bcm958625hr.dts index 6a44b8021702..f0e2008f7490 100644 --- a/arch/arm/boot/dts/bcm958625hr.dts +++ b/arch/arm/boot/dts/bcm958625hr.dts @@ -49,7 +49,7 @@ memory { device_type = "memory"; - reg = <0x60000000 0x80000000>; + reg = <0x60000000 0x20000000>; }; gpio-restart { -- cgit v1.2.3-55-g7522 From 808b7de86a0c19582a7efce4c80d6b4e1da7f370 Mon Sep 17 00:00:00 2001 From: Stefan Wahren Date: Sat, 24 Feb 2018 15:15:21 +0100 Subject: ARM: dts: bcm283x: Fix unit address of local_intc This patch fixes the following DTC warning (requires W=1): Node /soc/local_intc simple-bus unit address format error, expected "40000000" Signed-off-by: Stefan Wahren Reviewed-by: Eric Anholt Signed-off-by: Florian Fainelli --- arch/arm/boot/dts/bcm2836.dtsi | 2 +- arch/arm/boot/dts/bcm2837.dtsi | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'arch') diff --git a/arch/arm/boot/dts/bcm2836.dtsi b/arch/arm/boot/dts/bcm2836.dtsi index 1dfd76442777..e47f2e9ccbd0 100644 --- a/arch/arm/boot/dts/bcm2836.dtsi +++ b/arch/arm/boot/dts/bcm2836.dtsi @@ -9,7 +9,7 @@ <0x40000000 0x40000000 0x00001000>; dma-ranges = <0xc0000000 0x00000000 0x3f000000>; - local_intc: local_intc { + local_intc: local_intc@40000000 { compatible = "brcm,bcm2836-l1-intc"; reg = <0x40000000 0x100>; interrupt-controller; diff --git a/arch/arm/boot/dts/bcm2837.dtsi b/arch/arm/boot/dts/bcm2837.dtsi index efa7d3387ab2..7704bb029605 100644 --- a/arch/arm/boot/dts/bcm2837.dtsi +++ b/arch/arm/boot/dts/bcm2837.dtsi @@ -8,7 +8,7 @@ <0x40000000 0x40000000 0x00001000>; dma-ranges = <0xc0000000 0x00000000 0x3f000000>; - local_intc: local_intc { + local_intc: local_intc@40000000 { compatible = "brcm,bcm2836-l1-intc"; reg = <0x40000000 0x100>; interrupt-controller; -- cgit v1.2.3-55-g7522 From 2944866ac5b37e24ce1e646d2aaf472148e4a43e Mon Sep 17 00:00:00 2001 From: Stefan Wahren Date: Sat, 24 Feb 2018 15:15:22 +0100 Subject: ARM: dts: bcm283x: Move arm-pmu out of soc node The ARM PMU doesn't have a reg address, so fix the following DTC warning (requires W=1): Node /soc/arm-pmu missing or empty reg/ranges property Signed-off-by: Stefan Wahren Reviewed-by: Eric Anholt Signed-off-by: Florian Fainelli --- arch/arm/boot/dts/bcm2835.dtsi | 6 +++--- arch/arm/boot/dts/bcm2836.dtsi | 10 +++++----- 2 files changed, 8 insertions(+), 8 deletions(-) (limited to 'arch') diff --git a/arch/arm/boot/dts/bcm2835.dtsi b/arch/arm/boot/dts/bcm2835.dtsi index 0e3d2a5ff208..a5c3824c8056 100644 --- a/arch/arm/boot/dts/bcm2835.dtsi +++ b/arch/arm/boot/dts/bcm2835.dtsi @@ -18,10 +18,10 @@ soc { ranges = <0x7e000000 0x20000000 0x02000000>; dma-ranges = <0x40000000 0x00000000 0x20000000>; + }; - arm-pmu { - compatible = "arm,arm1176-pmu"; - }; + arm-pmu { + compatible = "arm,arm1176-pmu"; }; }; diff --git a/arch/arm/boot/dts/bcm2836.dtsi b/arch/arm/boot/dts/bcm2836.dtsi index e47f2e9ccbd0..c933e8413884 100644 --- a/arch/arm/boot/dts/bcm2836.dtsi +++ b/arch/arm/boot/dts/bcm2836.dtsi @@ -16,12 +16,12 @@ #interrupt-cells = <2>; interrupt-parent = <&local_intc>; }; + }; - arm-pmu { - compatible = "arm,cortex-a7-pmu"; - interrupt-parent = <&local_intc>; - interrupts = <9 IRQ_TYPE_LEVEL_HIGH>; - }; + arm-pmu { + compatible = "arm,cortex-a7-pmu"; + interrupt-parent = <&local_intc>; + interrupts = <9 IRQ_TYPE_LEVEL_HIGH>; }; timer { -- cgit v1.2.3-55-g7522 From 64c3f648c25d108f346fdc96c15180c6b7d250e9 Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Fri, 23 Feb 2018 12:55:59 -0800 Subject: powerpc/boot: Fix random libfdt related build errors Once in a while I see build errors similar to the following when building images from a clean tree. Building powerpc:virtex-ml507:44x/virtex5_defconfig ... failed ------------ Error log: arch/powerpc/boot/treeboot-akebono.c:37:20: fatal error: libfdt.h: No such file or directory Building powerpc:bamboo:smpdev:44x/bamboo_defconfig ... failed ------------ Error log: arch/powerpc/boot/treeboot-akebono.c:37:20: fatal error: libfdt.h: No such file or directory arch/powerpc/boot/treeboot-currituck.c:35:20: fatal error: libfdt.h: No such file or directory Rebuilds will succeed. Turns out that several source files in arch/powerpc/boot/ include libfdt.h, but Makefile dependencies are incomplete. Let's fix that. Signed-off-by: Guenter Roeck Signed-off-by: Michael Ellerman --- arch/powerpc/boot/Makefile | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile index ef6549e57157..26d5d2a5b8e9 100644 --- a/arch/powerpc/boot/Makefile +++ b/arch/powerpc/boot/Makefile @@ -101,7 +101,8 @@ $(addprefix $(obj)/,$(zlib-y)): \ libfdt := fdt.c fdt_ro.c fdt_wip.c fdt_sw.c fdt_rw.c fdt_strerror.c libfdtheader := fdt.h libfdt.h libfdt_internal.h -$(addprefix $(obj)/,$(libfdt) libfdt-wrapper.o simpleboot.o epapr.o opal.o): \ +$(addprefix $(obj)/,$(libfdt) libfdt-wrapper.o simpleboot.o epapr.o opal.o \ + treeboot-akebono.o treeboot-currituck.o treeboot-iss4xx.o): \ $(addprefix $(obj)/,$(libfdtheader)) src-wlib-y := string.S crt0.S stdio.c decompress.c main.c \ -- cgit v1.2.3-55-g7522 From cb097be7036aa325adba33d8c41fe77b980b0e77 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Sun, 25 Feb 2018 08:50:56 -0800 Subject: x86/refcounts: Switch to UD2 for exceptions As done in commit 3b3a371cc9bc ("x86/debug: Use UD2 for WARN()"), this switches to UD2 from UD0 to keep disassembly readable. Signed-off-by: Kees Cook Signed-off-by: Thomas Gleixner Cc: Peter Zijlstra Link: https://lkml.kernel.org/r/20180225165056.GA11719@beast --- arch/x86/include/asm/refcount.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/x86/include/asm/refcount.h b/arch/x86/include/asm/refcount.h index d65171120e90..4cf11d88d3b3 100644 --- a/arch/x86/include/asm/refcount.h +++ b/arch/x86/include/asm/refcount.h @@ -17,7 +17,7 @@ #define _REFCOUNT_EXCEPTION \ ".pushsection .text..refcount\n" \ "111:\tlea %[counter], %%" _ASM_CX "\n" \ - "112:\t" ASM_UD0 "\n" \ + "112:\t" ASM_UD2 "\n" \ ASM_UNREACHABLE \ ".popsection\n" \ "113:\n" \ -- cgit v1.2.3-55-g7522 From a368d7fd2a3c6babb852fe974018dd97916bcd3b Mon Sep 17 00:00:00 2001 From: Jan Beulich Date: Mon, 26 Feb 2018 04:11:21 -0700 Subject: x86/entry/64: Add instruction suffix Omitting suffixes from instructions in AT&T mode is bad practice when operand size cannot be determined by the assembler from register operands, and is likely going to be warned about by upstream gas in the future (mine does already). Add the single missing suffix here. Signed-off-by: Jan Beulich Signed-off-by: Thomas Gleixner Link: https://lkml.kernel.org/r/5A93F96902000078001ABAC8@prv-mh.provo.novell.com --- arch/x86/entry/entry_64.S | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index d5c7f18f79ac..805f52703ee3 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -55,7 +55,7 @@ END(native_usergs_sysret64) .macro TRACE_IRQS_FLAGS flags:req #ifdef CONFIG_TRACE_IRQFLAGS - bt $9, \flags /* interrupts off? */ + btl $9, \flags /* interrupts off? */ jnc 1f TRACE_IRQS_ON 1: -- cgit v1.2.3-55-g7522 From 22636f8c9511245cb3c8412039f1dd95afb3aa59 Mon Sep 17 00:00:00 2001 From: Jan Beulich Date: Mon, 26 Feb 2018 04:11:51 -0700 Subject: x86/asm: Add instruction suffixes to bitops Omitting suffixes from instructions in AT&T mode is bad practice when operand size cannot be determined by the assembler from register operands, and is likely going to be warned about by upstream gas in the future (mine does already). Add the missing suffixes here. Note that for 64-bit this means some operations change from being 32-bit to 64-bit. Signed-off-by: Jan Beulich Signed-off-by: Thomas Gleixner Link: https://lkml.kernel.org/r/5A93F98702000078001ABACC@prv-mh.provo.novell.com --- arch/x86/include/asm/bitops.h | 29 ++++++++++++++++------------- arch/x86/include/asm/percpu.h | 2 +- 2 files changed, 17 insertions(+), 14 deletions(-) (limited to 'arch') diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h index 3fa039855b8f..9f645ba57dbb 100644 --- a/arch/x86/include/asm/bitops.h +++ b/arch/x86/include/asm/bitops.h @@ -78,7 +78,7 @@ set_bit(long nr, volatile unsigned long *addr) : "iq" ((u8)CONST_MASK(nr)) : "memory"); } else { - asm volatile(LOCK_PREFIX "bts %1,%0" + asm volatile(LOCK_PREFIX __ASM_SIZE(bts) " %1,%0" : BITOP_ADDR(addr) : "Ir" (nr) : "memory"); } } @@ -94,7 +94,7 @@ set_bit(long nr, volatile unsigned long *addr) */ static __always_inline void __set_bit(long nr, volatile unsigned long *addr) { - asm volatile("bts %1,%0" : ADDR : "Ir" (nr) : "memory"); + asm volatile(__ASM_SIZE(bts) " %1,%0" : ADDR : "Ir" (nr) : "memory"); } /** @@ -115,7 +115,7 @@ clear_bit(long nr, volatile unsigned long *addr) : CONST_MASK_ADDR(nr, addr) : "iq" ((u8)~CONST_MASK(nr))); } else { - asm volatile(LOCK_PREFIX "btr %1,%0" + asm volatile(LOCK_PREFIX __ASM_SIZE(btr) " %1,%0" : BITOP_ADDR(addr) : "Ir" (nr)); } @@ -137,7 +137,7 @@ static __always_inline void clear_bit_unlock(long nr, volatile unsigned long *ad static __always_inline void __clear_bit(long nr, volatile unsigned long *addr) { - asm volatile("btr %1,%0" : ADDR : "Ir" (nr)); + asm volatile(__ASM_SIZE(btr) " %1,%0" : ADDR : "Ir" (nr)); } static __always_inline bool clear_bit_unlock_is_negative_byte(long nr, volatile unsigned long *addr) @@ -182,7 +182,7 @@ static __always_inline void __clear_bit_unlock(long nr, volatile unsigned long * */ static __always_inline void __change_bit(long nr, volatile unsigned long *addr) { - asm volatile("btc %1,%0" : ADDR : "Ir" (nr)); + asm volatile(__ASM_SIZE(btc) " %1,%0" : ADDR : "Ir" (nr)); } /** @@ -201,7 +201,7 @@ static __always_inline void change_bit(long nr, volatile unsigned long *addr) : CONST_MASK_ADDR(nr, addr) : "iq" ((u8)CONST_MASK(nr))); } else { - asm volatile(LOCK_PREFIX "btc %1,%0" + asm volatile(LOCK_PREFIX __ASM_SIZE(btc) " %1,%0" : BITOP_ADDR(addr) : "Ir" (nr)); } @@ -217,7 +217,8 @@ static __always_inline void change_bit(long nr, volatile unsigned long *addr) */ static __always_inline bool test_and_set_bit(long nr, volatile unsigned long *addr) { - GEN_BINARY_RMWcc(LOCK_PREFIX "bts", *addr, "Ir", nr, "%0", c); + GEN_BINARY_RMWcc(LOCK_PREFIX __ASM_SIZE(bts), + *addr, "Ir", nr, "%0", c); } /** @@ -246,7 +247,7 @@ static __always_inline bool __test_and_set_bit(long nr, volatile unsigned long * { bool oldbit; - asm("bts %2,%1" + asm(__ASM_SIZE(bts) " %2,%1" CC_SET(c) : CC_OUT(c) (oldbit), ADDR : "Ir" (nr)); @@ -263,7 +264,8 @@ static __always_inline bool __test_and_set_bit(long nr, volatile unsigned long * */ static __always_inline bool test_and_clear_bit(long nr, volatile unsigned long *addr) { - GEN_BINARY_RMWcc(LOCK_PREFIX "btr", *addr, "Ir", nr, "%0", c); + GEN_BINARY_RMWcc(LOCK_PREFIX __ASM_SIZE(btr), + *addr, "Ir", nr, "%0", c); } /** @@ -286,7 +288,7 @@ static __always_inline bool __test_and_clear_bit(long nr, volatile unsigned long { bool oldbit; - asm volatile("btr %2,%1" + asm volatile(__ASM_SIZE(btr) " %2,%1" CC_SET(c) : CC_OUT(c) (oldbit), ADDR : "Ir" (nr)); @@ -298,7 +300,7 @@ static __always_inline bool __test_and_change_bit(long nr, volatile unsigned lon { bool oldbit; - asm volatile("btc %2,%1" + asm volatile(__ASM_SIZE(btc) " %2,%1" CC_SET(c) : CC_OUT(c) (oldbit), ADDR : "Ir" (nr) : "memory"); @@ -316,7 +318,8 @@ static __always_inline bool __test_and_change_bit(long nr, volatile unsigned lon */ static __always_inline bool test_and_change_bit(long nr, volatile unsigned long *addr) { - GEN_BINARY_RMWcc(LOCK_PREFIX "btc", *addr, "Ir", nr, "%0", c); + GEN_BINARY_RMWcc(LOCK_PREFIX __ASM_SIZE(btc), + *addr, "Ir", nr, "%0", c); } static __always_inline bool constant_test_bit(long nr, const volatile unsigned long *addr) @@ -329,7 +332,7 @@ static __always_inline bool variable_test_bit(long nr, volatile const unsigned l { bool oldbit; - asm volatile("bt %2,%1" + asm volatile(__ASM_SIZE(bt) " %2,%1" CC_SET(c) : CC_OUT(c) (oldbit) : "m" (*(unsigned long *)addr), "Ir" (nr)); diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h index ba3c523aaf16..a06b07399d17 100644 --- a/arch/x86/include/asm/percpu.h +++ b/arch/x86/include/asm/percpu.h @@ -526,7 +526,7 @@ static inline bool x86_this_cpu_variable_test_bit(int nr, { bool oldbit; - asm volatile("bt "__percpu_arg(2)",%1" + asm volatile("btl "__percpu_arg(2)",%1" CC_SET(c) : CC_OUT(c) (oldbit) : "m" (*(unsigned long __percpu *)addr), "Ir" (nr)); -- cgit v1.2.3-55-g7522 From 71c208dd54ab971036d83ff6d9837bae4976e623 Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Mon, 26 Feb 2018 15:08:18 +0100 Subject: x86/xen: Zero MSR_IA32_SPEC_CTRL before suspend Older Xen versions (4.5 and before) might have problems migrating pv guests with MSR_IA32_SPEC_CTRL having a non-zero value. So before suspending zero that MSR and restore it after being resumed. Signed-off-by: Juergen Gross Signed-off-by: Thomas Gleixner Reviewed-by: Jan Beulich Cc: stable@vger.kernel.org Cc: xen-devel@lists.xenproject.org Cc: boris.ostrovsky@oracle.com Link: https://lkml.kernel.org/r/20180226140818.4849-1-jgross@suse.com --- arch/x86/xen/suspend.c | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'arch') diff --git a/arch/x86/xen/suspend.c b/arch/x86/xen/suspend.c index d9f96cc5d743..1d83152c761b 100644 --- a/arch/x86/xen/suspend.c +++ b/arch/x86/xen/suspend.c @@ -1,12 +1,15 @@ // SPDX-License-Identifier: GPL-2.0 #include #include +#include #include #include #include #include +#include +#include #include #include #include @@ -15,6 +18,8 @@ #include "mmu.h" #include "pmu.h" +static DEFINE_PER_CPU(u64, spec_ctrl); + void xen_arch_pre_suspend(void) { xen_save_time_memory_area(); @@ -35,6 +40,9 @@ void xen_arch_post_suspend(int cancelled) static void xen_vcpu_notify_restore(void *data) { + if (xen_pv_domain() && boot_cpu_has(X86_FEATURE_SPEC_CTRL)) + wrmsrl(MSR_IA32_SPEC_CTRL, this_cpu_read(spec_ctrl)); + /* Boot processor notified via generic timekeeping_resume() */ if (smp_processor_id() == 0) return; @@ -44,7 +52,15 @@ static void xen_vcpu_notify_restore(void *data) static void xen_vcpu_notify_suspend(void *data) { + u64 tmp; + tick_suspend_local(); + + if (xen_pv_domain() && boot_cpu_has(X86_FEATURE_SPEC_CTRL)) { + rdmsrl(MSR_IA32_SPEC_CTRL, tmp); + this_cpu_write(spec_ctrl, tmp); + wrmsrl(MSR_IA32_SPEC_CTRL, 0); + } } void xen_arch_resume(void) -- cgit v1.2.3-55-g7522 From 028091f82eefd5e84f81cef81a7673016ecbe78b Mon Sep 17 00:00:00 2001 From: Sebastian Panceac Date: Wed, 28 Feb 2018 11:40:49 +0200 Subject: x86/platform/intel-mid: Handle Intel Edison reboot correctly When the Intel Edison module is powered with 3.3V, the reboot command makes the module stuck. If the module is powered at a greater voltage, like 4.4V (as the Edison Mini Breakout board does), reboot works OK. The official Intel Edison BSP sends the IPCMSG_COLD_RESET message to the SCU by default. The IPCMSG_COLD_BOOT which is used by the upstream kernel is only sent when explicitely selected on the kernel command line. Use IPCMSG_COLD_RESET unconditionally which makes reboot work independent of the power supply voltage. [ tglx: Massaged changelog ] Fixes: bda7b072de99 ("x86/platform/intel-mid: Implement power off sequence") Signed-off-by: Sebastian Panceac Signed-off-by: Thomas Gleixner Acked-by: Andy Shevchenko Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/1519810849-15131-1-git-send-email-sebastian@resin.io --- arch/x86/platform/intel-mid/intel-mid.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/x86/platform/intel-mid/intel-mid.c b/arch/x86/platform/intel-mid/intel-mid.c index 2c67bae6bb53..fb1df9488e98 100644 --- a/arch/x86/platform/intel-mid/intel-mid.c +++ b/arch/x86/platform/intel-mid/intel-mid.c @@ -79,7 +79,7 @@ static void intel_mid_power_off(void) static void intel_mid_reboot(void) { - intel_scu_ipc_simple_command(IPCMSG_COLD_BOOT, 0); + intel_scu_ipc_simple_command(IPCMSG_COLD_RESET, 0); } static unsigned long __init intel_mid_calibrate_tsc(void) -- cgit v1.2.3-55-g7522 From 701eda01cbd212bae2f7d29cf14322bd49b94657 Mon Sep 17 00:00:00 2001 From: Vineet Gupta Date: Wed, 21 Feb 2018 15:10:02 -0800 Subject: ARCv2: boot log: fix HS48 release number Signed-off-by: Vineet Gupta --- arch/arc/kernel/setup.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c index ec12fe1c2f07..b2cae79a25d7 100644 --- a/arch/arc/kernel/setup.c +++ b/arch/arc/kernel/setup.c @@ -51,7 +51,7 @@ static const struct id_to_str arc_cpu_rel[] = { { 0x51, "R2.0" }, { 0x52, "R2.1" }, { 0x53, "R3.0" }, - { 0x54, "R4.0" }, + { 0x54, "R3.10a" }, #endif { 0x00, NULL } }; -- cgit v1.2.3-55-g7522 From 07423d00a2b2a71a97e4287d9262cb83c4c4c89f Mon Sep 17 00:00:00 2001 From: Eugeniy Paltsev Date: Fri, 23 Feb 2018 19:41:52 +0300 Subject: ARC: mcip: halt GFRC counter when ARC cores halt In SMP systems, GFRC is used for clocksource. However by default the counter keeps running even when core is halted (say when debugging via a JTAG debugger). This confuses Linux timekeeping and triggers flase RCU stall splat such as below: | [ARCLinux]# while true; do ./shm_open_23-1.run-test ; done | Running with 1000 processes for 1000 objects | hrtimer: interrupt took 485060 ns | | create_cnt: 1000 | Running with 1000 processes for 1000 objects | [ARCLinux]# INFO: rcu_preempt self-detected stall on CPU | 2-...: (1 GPs behind) idle=a01/1/0 softirq=135770/135773 fqs=0 | INFO: rcu_preempt detected stalls on CPUs/tasks: | 0-...: (1 GPs behind) idle=71e/0/0 softirq=135264/135264 fqs=0 | 2-...: (1 GPs behind) idle=a01/1/0 softirq=135770/135773 fqs=0 | 3-...: (1 GPs behind) idle=4e0/0/0 softirq=134304/134304 fqs=0 | (detected by 1, t=13648 jiffies, g=31493, c=31492, q=1) Starting from ARC HS v3.0 it's possible to tie GFRC to state of up-to 4 ARC cores with help of GFRC's CORE register where we set a mask for cores which state we need to rely on. We update cpu mask every time new cpu came online instead of using hardcoded one or using mask generated from "possible_cpus" as we want it set correctly even if we run kernel on HW which has fewer cores than expected (or we launch kernel via debugger and kick fever cores than HW has) Note that GFRC halts when all cores have halted and thus relies on programming of Inter-Core-dEbug register to halt all cores when one halts. Signed-off-by: Alexey Brodkin Signed-off-by: Eugeniy Paltsev Signed-off-by: Vineet Gupta [vgupta: rewrote changelog] --- arch/arc/kernel/mcip.c | 37 +++++++++++++++++++++++++++++++++++++ include/soc/arc/mcip.h | 3 +++ 2 files changed, 40 insertions(+) (limited to 'arch') diff --git a/arch/arc/kernel/mcip.c b/arch/arc/kernel/mcip.c index f61a52b01625..1119029ae7fc 100644 --- a/arch/arc/kernel/mcip.c +++ b/arch/arc/kernel/mcip.c @@ -22,10 +22,47 @@ static DEFINE_RAW_SPINLOCK(mcip_lock); static char smp_cpuinfo_buf[128]; +/* + * Set mask to halt GFRC if any online core in SMP cluster is halted. + * Only works for ARC HS v3.0+, on earlier versions has no effect. + */ +static void mcip_update_gfrc_halt_mask(int cpu) +{ + struct bcr_generic gfrc; + unsigned long flags; + u32 gfrc_halt_mask; + + READ_BCR(ARC_REG_GFRC_BUILD, gfrc); + + /* + * CMD_GFRC_SET_CORE and CMD_GFRC_READ_CORE commands were added in + * GFRC 0x3 version. + */ + if (gfrc.ver < 0x3) + return; + + raw_spin_lock_irqsave(&mcip_lock, flags); + + __mcip_cmd(CMD_GFRC_READ_CORE, 0); + gfrc_halt_mask = read_aux_reg(ARC_REG_MCIP_READBACK); + gfrc_halt_mask |= BIT(cpu); + __mcip_cmd_data(CMD_GFRC_SET_CORE, 0, gfrc_halt_mask); + + raw_spin_unlock_irqrestore(&mcip_lock, flags); +} + static void mcip_setup_per_cpu(int cpu) { + struct mcip_bcr mp; + + READ_BCR(ARC_REG_MCIP_BCR, mp); + smp_ipi_irq_setup(cpu, IPI_IRQ); smp_ipi_irq_setup(cpu, SOFTIRQ_IRQ); + + /* Update GFRC halt mask as new CPU came online */ + if (mp.gfrc) + mcip_update_gfrc_halt_mask(cpu); } static void mcip_ipi_send(int cpu) diff --git a/include/soc/arc/mcip.h b/include/soc/arc/mcip.h index c2d1b15da136..1138da57baaf 100644 --- a/include/soc/arc/mcip.h +++ b/include/soc/arc/mcip.h @@ -15,6 +15,7 @@ #define ARC_REG_MCIP_BCR 0x0d0 #define ARC_REG_MCIP_IDU_BCR 0x0D5 +#define ARC_REG_GFRC_BUILD 0x0D6 #define ARC_REG_MCIP_CMD 0x600 #define ARC_REG_MCIP_WDATA 0x601 #define ARC_REG_MCIP_READBACK 0x602 @@ -40,6 +41,8 @@ struct mcip_cmd { #define CMD_GFRC_READ_LO 0x42 #define CMD_GFRC_READ_HI 0x43 +#define CMD_GFRC_SET_CORE 0x47 +#define CMD_GFRC_READ_CORE 0x48 #define CMD_IDU_ENABLE 0x71 #define CMD_IDU_DISABLE 0x72 -- cgit v1.2.3-55-g7522 From f3205de98db2fc8083796dd5ad81b191e436fab8 Mon Sep 17 00:00:00 2001 From: Eugeniy Paltsev Date: Fri, 23 Feb 2018 19:41:53 +0300 Subject: ARC: mcip: update MCIP debug mask when the new cpu came online As of today we use hardcoded MCIP debug mask, so if we launch kernel via debugger and kick fever cores than HW has all cpus hang at the momemt of setup MCIP debug mask. So update MCIP debug mask when the new cpu came online, instead of use hardcoded MCIP debug mask. Signed-off-by: Eugeniy Paltsev Signed-off-by: Vineet Gupta --- arch/arc/kernel/mcip.c | 37 ++++++++++++++++++++++++++++++++----- include/soc/arc/mcip.h | 2 ++ 2 files changed, 34 insertions(+), 5 deletions(-) (limited to 'arch') diff --git a/arch/arc/kernel/mcip.c b/arch/arc/kernel/mcip.c index 1119029ae7fc..5fe84e481654 100644 --- a/arch/arc/kernel/mcip.c +++ b/arch/arc/kernel/mcip.c @@ -51,6 +51,34 @@ static void mcip_update_gfrc_halt_mask(int cpu) raw_spin_unlock_irqrestore(&mcip_lock, flags); } +static void mcip_update_debug_halt_mask(int cpu) +{ + u32 mcip_mask = 0; + unsigned long flags; + + raw_spin_lock_irqsave(&mcip_lock, flags); + + /* + * mcip_mask is same for CMD_DEBUG_SET_SELECT and CMD_DEBUG_SET_MASK + * commands. So read it once instead of reading both CMD_DEBUG_READ_MASK + * and CMD_DEBUG_READ_SELECT. + */ + __mcip_cmd(CMD_DEBUG_READ_SELECT, 0); + mcip_mask = read_aux_reg(ARC_REG_MCIP_READBACK); + + mcip_mask |= BIT(cpu); + + __mcip_cmd_data(CMD_DEBUG_SET_SELECT, 0, mcip_mask); + /* + * Parameter specified halt cause: + * STATUS32[H]/actionpoint/breakpoint/self-halt + * We choose all of them (0xF). + */ + __mcip_cmd_data(CMD_DEBUG_SET_MASK, 0xF, mcip_mask); + + raw_spin_unlock_irqrestore(&mcip_lock, flags); +} + static void mcip_setup_per_cpu(int cpu) { struct mcip_bcr mp; @@ -63,6 +91,10 @@ static void mcip_setup_per_cpu(int cpu) /* Update GFRC halt mask as new CPU came online */ if (mp.gfrc) mcip_update_gfrc_halt_mask(cpu); + + /* Update MCIP debug mask as new CPU came online */ + if (mp.dbg) + mcip_update_debug_halt_mask(cpu); } static void mcip_ipi_send(int cpu) @@ -138,11 +170,6 @@ static void mcip_probe_n_setup(void) IS_AVAIL1(mp.gfrc, "GFRC")); cpuinfo_arc700[0].extn.gfrc = mp.gfrc; - - if (mp.dbg) { - __mcip_cmd_data(CMD_DEBUG_SET_SELECT, 0, 0xf); - __mcip_cmd_data(CMD_DEBUG_SET_MASK, 0xf, 0xf); - } } struct plat_smp_ops plat_smp_ops = { diff --git a/include/soc/arc/mcip.h b/include/soc/arc/mcip.h index 1138da57baaf..a91f25151a5b 100644 --- a/include/soc/arc/mcip.h +++ b/include/soc/arc/mcip.h @@ -37,7 +37,9 @@ struct mcip_cmd { #define CMD_SEMA_RELEASE 0x12 #define CMD_DEBUG_SET_MASK 0x34 +#define CMD_DEBUG_READ_MASK 0x35 #define CMD_DEBUG_SET_SELECT 0x36 +#define CMD_DEBUG_READ_SELECT 0x37 #define CMD_GFRC_READ_LO 0x42 #define CMD_GFRC_READ_HI 0x43 -- cgit v1.2.3-55-g7522 From a29a25275452c97fe35815f1eb9564f2a07a1965 Mon Sep 17 00:00:00 2001 From: Eugeniy Paltsev Date: Fri, 23 Feb 2018 19:41:54 +0300 Subject: ARC: setup cpu possible mask according to possible-cpus dts property As we have option in u-boot to set CPU mask for running linux, we want to pass information to kernel about CPU cores should be brought up. So we patch kernel dtb in u-boot to set possible-cpus property. This also allows us to have correctly setuped MCIP debug mask. Signed-off-by: Eugeniy Paltsev Signed-off-by: Vineet Gupta --- arch/arc/kernel/smp.c | 50 ++++++++++++++++++++++++++++++++++++++++---------- 1 file changed, 40 insertions(+), 10 deletions(-) (limited to 'arch') diff --git a/arch/arc/kernel/smp.c b/arch/arc/kernel/smp.c index efe8b4200a67..21d86c36692b 100644 --- a/arch/arc/kernel/smp.c +++ b/arch/arc/kernel/smp.c @@ -24,6 +24,7 @@ #include #include #include +#include #include #include @@ -47,6 +48,42 @@ void __init smp_prepare_boot_cpu(void) { } +static int __init arc_get_cpu_map(const char *name, struct cpumask *cpumask) +{ + unsigned long dt_root = of_get_flat_dt_root(); + const char *buf; + + buf = of_get_flat_dt_prop(dt_root, name, NULL); + if (!buf) + return -EINVAL; + + if (cpulist_parse(buf, cpumask)) + return -EINVAL; + + return 0; +} + +/* + * Read from DeviceTree and setup cpu possible mask. If there is no + * "possible-cpus" property in DeviceTree pretend all [0..NR_CPUS-1] exist. + */ +static void __init arc_init_cpu_possible(void) +{ + struct cpumask cpumask; + + if (arc_get_cpu_map("possible-cpus", &cpumask)) { + pr_warn("Failed to get possible-cpus from dtb, pretending all %u cpus exist\n", + NR_CPUS); + + cpumask_setall(&cpumask); + } + + if (!cpumask_test_cpu(0, &cpumask)) + panic("Master cpu (cpu[0]) is missed in cpu possible mask!"); + + init_cpu_possible(&cpumask); +} + /* * Called from setup_arch() before calling setup_processor() * @@ -58,10 +95,7 @@ void __init smp_prepare_boot_cpu(void) */ void __init smp_init_cpus(void) { - unsigned int i; - - for (i = 0; i < NR_CPUS; i++) - set_cpu_possible(i, true); + arc_init_cpu_possible(); if (plat_smp_ops.init_early_smp) plat_smp_ops.init_early_smp(); @@ -70,16 +104,12 @@ void __init smp_init_cpus(void) /* called from init ( ) => process 1 */ void __init smp_prepare_cpus(unsigned int max_cpus) { - int i; - /* * if platform didn't set the present map already, do it now * boot cpu is set to present already by init/main.c */ - if (num_present_cpus() <= 1) { - for (i = 0; i < max_cpus; i++) - set_cpu_present(i, true); - } + if (num_present_cpus() <= 1) + init_cpu_present(cpu_possible_mask); } void __init smp_cpus_done(unsigned int max_cpus) -- cgit v1.2.3-55-g7522 From 47b02f4c621c5ae9fd27248dfa9a194bc1387ecb Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Tue, 27 Feb 2018 11:19:22 +0100 Subject: x86/xen: add tty0 and hvc0 as preferred consoles for dom0 Today the tty0 and hvc0 consoles are added as a preferred consoles for pv domUs only. As this requires a boot parameter for getting dom0 messages per default, add them for dom0, too. Signed-off-by: Juergen Gross Reviewed-by: Boris Ostrovsky Signed-off-by: Juergen Gross --- arch/x86/xen/enlighten_pv.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'arch') diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c index c047f42552e1..3c2c2530737e 100644 --- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -1376,8 +1376,6 @@ asmlinkage __visible void __init xen_start_kernel(void) if (!xen_initial_domain()) { add_preferred_console("xenboot", 0, NULL); - add_preferred_console("tty", 0, NULL); - add_preferred_console("hvc", 0, NULL); if (pci_xen) x86_init.pci.arch_init = pci_xen_init; } else { @@ -1410,6 +1408,10 @@ asmlinkage __visible void __init xen_start_kernel(void) xen_boot_params_init_edd(); } + + add_preferred_console("tty", 0, NULL); + add_preferred_console("hvc", 0, NULL); + #ifdef CONFIG_PCI /* PCI BIOS service won't work from a PV guest. */ pci_probe &= ~PCI_PROBE_BIOS; -- cgit v1.2.3-55-g7522 From 945fd17ab6bab8a4d05da6c3170519fbcfe62ddb Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 28 Feb 2018 21:14:26 +0100 Subject: x86/cpu_entry_area: Sync cpu_entry_area to initial_page_table The separation of the cpu_entry_area from the fixmap missed the fact that on 32bit non-PAE kernels the cpu_entry_area mapping might not be covered in initial_page_table by the previous synchronizations. This results in suspend/resume failures because 32bit utilizes initial page table for resume. The absence of the cpu_entry_area mapping results in a triple fault, aka. insta reboot. With PAE enabled this works by chance because the PGD entry which covers the fixmap and other parts incindentally provides the cpu_entry_area mapping as well. Synchronize the initial page table after setting up the cpu entry area. Instead of adding yet another copy of the same code, move it to a function and invoke it from the various places. It needs to be investigated if the existing calls in setup_arch() and setup_per_cpu_areas() can be replaced by the later invocation from setup_cpu_entry_areas(), but that's beyond the scope of this fix. Fixes: 92a0f81d8957 ("x86/cpu_entry_area: Move it out of the fixmap") Reported-by: Woody Suwalski Signed-off-by: Thomas Gleixner Tested-by: Woody Suwalski Cc: William Grant Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/alpine.DEB.2.21.1802282137290.1392@nanos.tec.linutronix.de --- arch/x86/include/asm/pgtable_32.h | 1 + arch/x86/include/asm/pgtable_64.h | 1 + arch/x86/kernel/setup.c | 17 +++++------------ arch/x86/kernel/setup_percpu.c | 17 ++++------------- arch/x86/mm/cpu_entry_area.c | 6 ++++++ arch/x86/mm/init_32.c | 15 +++++++++++++++ 6 files changed, 32 insertions(+), 25 deletions(-) (limited to 'arch') diff --git a/arch/x86/include/asm/pgtable_32.h b/arch/x86/include/asm/pgtable_32.h index e55466760ff8..b3ec519e3982 100644 --- a/arch/x86/include/asm/pgtable_32.h +++ b/arch/x86/include/asm/pgtable_32.h @@ -32,6 +32,7 @@ extern pmd_t initial_pg_pmd[]; static inline void pgtable_cache_init(void) { } static inline void check_pgt_cache(void) { } void paging_init(void); +void sync_initial_page_table(void); /* * Define this if things work differently on an i386 and an i486: diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h index 81462e9a34f6..1149d2112b2e 100644 --- a/arch/x86/include/asm/pgtable_64.h +++ b/arch/x86/include/asm/pgtable_64.h @@ -28,6 +28,7 @@ extern pgd_t init_top_pgt[]; #define swapper_pg_dir init_top_pgt extern void paging_init(void); +static inline void sync_initial_page_table(void) { } #define pte_ERROR(e) \ pr_err("%s:%d: bad pte %p(%016lx)\n", \ diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 1ae67e982af7..4c616be28506 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -1204,20 +1204,13 @@ void __init setup_arch(char **cmdline_p) kasan_init(); -#ifdef CONFIG_X86_32 - /* sync back kernel address range */ - clone_pgd_range(initial_page_table + KERNEL_PGD_BOUNDARY, - swapper_pg_dir + KERNEL_PGD_BOUNDARY, - KERNEL_PGD_PTRS); - /* - * sync back low identity map too. It is used for example - * in the 32-bit EFI stub. + * Sync back kernel address range. + * + * FIXME: Can the later sync in setup_cpu_entry_areas() replace + * this call? */ - clone_pgd_range(initial_page_table, - swapper_pg_dir + KERNEL_PGD_BOUNDARY, - min(KERNEL_PGD_PTRS, KERNEL_PGD_BOUNDARY)); -#endif + sync_initial_page_table(); tboot_probe(); diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c index 497aa766fab3..ea554f812ee1 100644 --- a/arch/x86/kernel/setup_percpu.c +++ b/arch/x86/kernel/setup_percpu.c @@ -287,24 +287,15 @@ void __init setup_per_cpu_areas(void) /* Setup cpu initialized, callin, callout masks */ setup_cpu_local_masks(); -#ifdef CONFIG_X86_32 /* * Sync back kernel address range again. We already did this in * setup_arch(), but percpu data also needs to be available in * the smpboot asm. We can't reliably pick up percpu mappings * using vmalloc_fault(), because exception dispatch needs * percpu data. + * + * FIXME: Can the later sync in setup_cpu_entry_areas() replace + * this call? */ - clone_pgd_range(initial_page_table + KERNEL_PGD_BOUNDARY, - swapper_pg_dir + KERNEL_PGD_BOUNDARY, - KERNEL_PGD_PTRS); - - /* - * sync back low identity map too. It is used for example - * in the 32-bit EFI stub. - */ - clone_pgd_range(initial_page_table, - swapper_pg_dir + KERNEL_PGD_BOUNDARY, - min(KERNEL_PGD_PTRS, KERNEL_PGD_BOUNDARY)); -#endif + sync_initial_page_table(); } diff --git a/arch/x86/mm/cpu_entry_area.c b/arch/x86/mm/cpu_entry_area.c index b9283cc27622..476d810639a8 100644 --- a/arch/x86/mm/cpu_entry_area.c +++ b/arch/x86/mm/cpu_entry_area.c @@ -163,4 +163,10 @@ void __init setup_cpu_entry_areas(void) for_each_possible_cpu(cpu) setup_cpu_entry_area(cpu); + + /* + * This is the last essential update to swapper_pgdir which needs + * to be synchronized to initial_page_table on 32bit. + */ + sync_initial_page_table(); } diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index 79cb066f40c0..396e1f0151ac 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -453,6 +453,21 @@ static inline void permanent_kmaps_init(pgd_t *pgd_base) } #endif /* CONFIG_HIGHMEM */ +void __init sync_initial_page_table(void) +{ + clone_pgd_range(initial_page_table + KERNEL_PGD_BOUNDARY, + swapper_pg_dir + KERNEL_PGD_BOUNDARY, + KERNEL_PGD_PTRS); + + /* + * sync back low identity map too. It is used for example + * in the 32-bit EFI stub. + */ + clone_pgd_range(initial_page_table, + swapper_pg_dir + KERNEL_PGD_BOUNDARY, + min(KERNEL_PGD_PTRS, KERNEL_PGD_BOUNDARY)); +} + void __init native_pagetable_init(void) { unsigned long pfn, va; -- cgit v1.2.3-55-g7522 From 09a0fb67536a49af19f2bfc632100e9de91fe526 Mon Sep 17 00:00:00 2001 From: Christian Borntraeger Date: Wed, 28 Feb 2018 18:44:34 +0000 Subject: KVM: s390: provide io interrupt kvm_stat We already count io interrupts, but we forgot to print them. Signed-off-by: Christian Borntraeger Fixes: d8346b7d9b ("KVM: s390: Support for I/O interrupts.") Reviewed-by: Cornelia Huck Reviewed-by: David Hildenbrand Signed-off-by: Christian Borntraeger --- arch/s390/kvm/kvm-s390.c | 1 + 1 file changed, 1 insertion(+) (limited to 'arch') diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 77d7818130db..df19f158347e 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -86,6 +86,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { { "deliver_prefix_signal", VCPU_STAT(deliver_prefix_signal) }, { "deliver_restart_signal", VCPU_STAT(deliver_restart_signal) }, { "deliver_program_interruption", VCPU_STAT(deliver_program_int) }, + { "deliver_io_interrupt", VCPU_STAT(deliver_io_int) }, { "exit_wait_state", VCPU_STAT(exit_wait_state) }, { "instruction_epsw", VCPU_STAT(instruction_epsw) }, { "instruction_gs", VCPU_STAT(instruction_gs) }, -- cgit v1.2.3-55-g7522 From 801e459a6f3a63af9d447e6249088c76ae16efc4 Mon Sep 17 00:00:00 2001 From: Tom Lendacky Date: Wed, 21 Feb 2018 13:39:51 -0600 Subject: KVM: x86: Add a framework for supporting MSR-based features Provide a new KVM capability that allows bits within MSRs to be recognized as features. Two new ioctls are added to the /dev/kvm ioctl routine to retrieve the list of these MSRs and then retrieve their values. A kvm_x86_ops callback is used to determine support for the listed MSR-based features. Signed-off-by: Tom Lendacky Signed-off-by: Paolo Bonzini [Tweaked documentation. - Radim] Signed-off-by: Radim Krčmář --- Documentation/virtual/kvm/api.txt | 40 ++++++++++++++------- arch/x86/include/asm/kvm_host.h | 2 ++ arch/x86/kvm/svm.c | 6 ++++ arch/x86/kvm/vmx.c | 6 ++++ arch/x86/kvm/x86.c | 75 ++++++++++++++++++++++++++++++++++++--- include/uapi/linux/kvm.h | 2 ++ 6 files changed, 114 insertions(+), 17 deletions(-) (limited to 'arch') diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt index 792fa8717d13..d6b3ff51a14f 100644 --- a/Documentation/virtual/kvm/api.txt +++ b/Documentation/virtual/kvm/api.txt @@ -123,14 +123,15 @@ memory layout to fit in user mode), check KVM_CAP_MIPS_VZ and use the flag KVM_VM_MIPS_VZ. -4.3 KVM_GET_MSR_INDEX_LIST +4.3 KVM_GET_MSR_INDEX_LIST, KVM_GET_MSR_FEATURE_INDEX_LIST -Capability: basic +Capability: basic, KVM_CAP_GET_MSR_FEATURES for KVM_GET_MSR_FEATURE_INDEX_LIST Architectures: x86 -Type: system +Type: system ioctl Parameters: struct kvm_msr_list (in/out) Returns: 0 on success; -1 on error Errors: + EFAULT: the msr index list cannot be read from or written to E2BIG: the msr index list is to be to fit in the array specified by the user. @@ -139,16 +140,23 @@ struct kvm_msr_list { __u32 indices[0]; }; -This ioctl returns the guest msrs that are supported. The list varies -by kvm version and host processor, but does not change otherwise. The -user fills in the size of the indices array in nmsrs, and in return -kvm adjusts nmsrs to reflect the actual number of msrs and fills in -the indices array with their numbers. +The user fills in the size of the indices array in nmsrs, and in return +kvm adjusts nmsrs to reflect the actual number of msrs and fills in the +indices array with their numbers. + +KVM_GET_MSR_INDEX_LIST returns the guest msrs that are supported. The list +varies by kvm version and host processor, but does not change otherwise. Note: if kvm indicates supports MCE (KVM_CAP_MCE), then the MCE bank MSRs are not returned in the MSR list, as different vcpus can have a different number of banks, as set via the KVM_X86_SETUP_MCE ioctl. +KVM_GET_MSR_FEATURE_INDEX_LIST returns the list of MSRs that can be passed +to the KVM_GET_MSRS system ioctl. This lets userspace probe host capabilities +and processor features that are exposed via MSRs (e.g., VMX capabilities). +This list also varies by kvm version and host processor, but does not change +otherwise. + 4.4 KVM_CHECK_EXTENSION @@ -475,14 +483,22 @@ Support for this has been removed. Use KVM_SET_GUEST_DEBUG instead. 4.18 KVM_GET_MSRS -Capability: basic +Capability: basic (vcpu), KVM_CAP_GET_MSR_FEATURES (system) Architectures: x86 -Type: vcpu ioctl +Type: system ioctl, vcpu ioctl Parameters: struct kvm_msrs (in/out) -Returns: 0 on success, -1 on error +Returns: number of msrs successfully returned; + -1 on error + +When used as a system ioctl: +Reads the values of MSR-based features that are available for the VM. This +is similar to KVM_GET_SUPPORTED_CPUID, but it returns MSR indices and values. +The list of msr-based features can be obtained using KVM_GET_MSR_FEATURE_INDEX_LIST +in a system ioctl. +When used as a vcpu ioctl: Reads model-specific registers from the vcpu. Supported msr indices can -be obtained using KVM_GET_MSR_INDEX_LIST. +be obtained using KVM_GET_MSR_INDEX_LIST in a system ioctl. struct kvm_msrs { __u32 nmsrs; /* number of msrs in entries */ diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 0a9e330b34f0..bab0694b35c3 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1095,6 +1095,8 @@ struct kvm_x86_ops { int (*mem_enc_op)(struct kvm *kvm, void __user *argp); int (*mem_enc_reg_region)(struct kvm *kvm, struct kvm_enc_region *argp); int (*mem_enc_unreg_region)(struct kvm *kvm, struct kvm_enc_region *argp); + + int (*get_msr_feature)(struct kvm_msr_entry *entry); }; struct kvm_arch_async_pf { diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 3d8377f75eda..d8db947acf70 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -3869,6 +3869,11 @@ static int cr8_write_interception(struct vcpu_svm *svm) return 0; } +static int svm_get_msr_feature(struct kvm_msr_entry *msr) +{ + return 1; +} + static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) { struct vcpu_svm *svm = to_svm(vcpu); @@ -6832,6 +6837,7 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = { .vcpu_unblocking = svm_vcpu_unblocking, .update_bp_intercept = update_bp_intercept, + .get_msr_feature = svm_get_msr_feature, .get_msr = svm_get_msr, .set_msr = svm_set_msr, .get_segment_base = svm_get_segment_base, diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index ec14f2319a87..fafc1f6d8987 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -3226,6 +3226,11 @@ static inline bool vmx_feature_control_msr_valid(struct kvm_vcpu *vcpu, return !(val & ~valid_bits); } +static int vmx_get_msr_feature(struct kvm_msr_entry *msr) +{ + return 1; +} + /* * Reads an msr value (of 'msr_index') into 'pdata'. * Returns 0 on success, non-0 otherwise. @@ -12296,6 +12301,7 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = { .vcpu_put = vmx_vcpu_put, .update_bp_intercept = update_exception_bitmap, + .get_msr_feature = vmx_get_msr_feature, .get_msr = vmx_get_msr, .set_msr = vmx_set_msr, .get_segment_base = vmx_get_segment_base, diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 96edda878dbf..239fc1fd7845 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1049,6 +1049,28 @@ static u32 emulated_msrs[] = { static unsigned num_emulated_msrs; +/* + * List of msr numbers which are used to expose MSR-based features that + * can be used by a hypervisor to validate requested CPU features. + */ +static u32 msr_based_features[] = { +}; + +static unsigned int num_msr_based_features; + +static int do_get_msr_feature(struct kvm_vcpu *vcpu, unsigned index, u64 *data) +{ + struct kvm_msr_entry msr; + + msr.index = index; + if (kvm_x86_ops->get_msr_feature(&msr)) + return 1; + + *data = msr.data; + + return 0; +} + bool kvm_valid_efer(struct kvm_vcpu *vcpu, u64 efer) { if (efer & efer_reserved_bits) @@ -2680,13 +2702,11 @@ static int __msr_io(struct kvm_vcpu *vcpu, struct kvm_msrs *msrs, int (*do_msr)(struct kvm_vcpu *vcpu, unsigned index, u64 *data)) { - int i, idx; + int i; - idx = srcu_read_lock(&vcpu->kvm->srcu); for (i = 0; i < msrs->nmsrs; ++i) if (do_msr(vcpu, entries[i].index, &entries[i].data)) break; - srcu_read_unlock(&vcpu->kvm->srcu, idx); return i; } @@ -2785,6 +2805,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_SET_BOOT_CPU_ID: case KVM_CAP_SPLIT_IRQCHIP: case KVM_CAP_IMMEDIATE_EXIT: + case KVM_CAP_GET_MSR_FEATURES: r = 1; break; case KVM_CAP_ADJUST_CLOCK: @@ -2899,6 +2920,31 @@ long kvm_arch_dev_ioctl(struct file *filp, goto out; r = 0; break; + case KVM_GET_MSR_FEATURE_INDEX_LIST: { + struct kvm_msr_list __user *user_msr_list = argp; + struct kvm_msr_list msr_list; + unsigned int n; + + r = -EFAULT; + if (copy_from_user(&msr_list, user_msr_list, sizeof(msr_list))) + goto out; + n = msr_list.nmsrs; + msr_list.nmsrs = num_msr_based_features; + if (copy_to_user(user_msr_list, &msr_list, sizeof(msr_list))) + goto out; + r = -E2BIG; + if (n < msr_list.nmsrs) + goto out; + r = -EFAULT; + if (copy_to_user(user_msr_list->indices, &msr_based_features, + num_msr_based_features * sizeof(u32))) + goto out; + r = 0; + break; + } + case KVM_GET_MSRS: + r = msr_io(NULL, argp, do_get_msr_feature, 1); + break; } default: r = -EINVAL; @@ -3636,12 +3682,18 @@ long kvm_arch_vcpu_ioctl(struct file *filp, r = 0; break; } - case KVM_GET_MSRS: + case KVM_GET_MSRS: { + int idx = srcu_read_lock(&vcpu->kvm->srcu); r = msr_io(vcpu, argp, do_get_msr, 1); + srcu_read_unlock(&vcpu->kvm->srcu, idx); break; - case KVM_SET_MSRS: + } + case KVM_SET_MSRS: { + int idx = srcu_read_lock(&vcpu->kvm->srcu); r = msr_io(vcpu, argp, do_set_msr, 0); + srcu_read_unlock(&vcpu->kvm->srcu, idx); break; + } case KVM_TPR_ACCESS_REPORTING: { struct kvm_tpr_access_ctl tac; @@ -4464,6 +4516,19 @@ static void kvm_init_msr_list(void) j++; } num_emulated_msrs = j; + + for (i = j = 0; i < ARRAY_SIZE(msr_based_features); i++) { + struct kvm_msr_entry msr; + + msr.index = msr_based_features[i]; + if (kvm_x86_ops->get_msr_feature(&msr)) + continue; + + if (j < i) + msr_based_features[j] = msr_based_features[i]; + j++; + } + num_msr_based_features = j; } static int vcpu_mmio_write(struct kvm_vcpu *vcpu, gpa_t addr, int len, diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 0fb5ef939732..7b26d4b0b052 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -761,6 +761,7 @@ struct kvm_ppc_resize_hpt { #define KVM_TRACE_PAUSE __KVM_DEPRECATED_MAIN_0x07 #define KVM_TRACE_DISABLE __KVM_DEPRECATED_MAIN_0x08 #define KVM_GET_EMULATED_CPUID _IOWR(KVMIO, 0x09, struct kvm_cpuid2) +#define KVM_GET_MSR_FEATURE_INDEX_LIST _IOWR(KVMIO, 0x0a, struct kvm_msr_list) /* * Extension capability list. @@ -934,6 +935,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_S390_AIS_MIGRATION 150 #define KVM_CAP_PPC_GET_CPU_CHAR 151 #define KVM_CAP_S390_BPB 152 +#define KVM_CAP_GET_MSR_FEATURES 153 #ifdef KVM_CAP_IRQ_ROUTING -- cgit v1.2.3-55-g7522 From d1d93fa90f1afa926cb060b7f78ab01a65705b4d Mon Sep 17 00:00:00 2001 From: Tom Lendacky Date: Sat, 24 Feb 2018 00:18:20 +0100 Subject: KVM: SVM: Add MSR-based feature support for serializing LFENCE In order to determine if LFENCE is a serializing instruction on AMD processors, MSR 0xc0011029 (MSR_F10H_DECFG) must be read and the state of bit 1 checked. This patch will add support to allow a guest to properly make this determination. Add the MSR feature callback operation to svm.c and add MSR 0xc0011029 to the list of MSR-based features. If LFENCE is serializing, then the feature is supported, allowing the hypervisor to set the value of the MSR that guest will see. Support is also added to write (hypervisor only) and read the MSR value for the guest. A write by the guest will result in a #GP. A read by the guest will return the value as set by the host. In this way, the support to expose the feature to the guest is controlled by the hypervisor. Reviewed-by: Paolo Bonzini Signed-off-by: Tom Lendacky Signed-off-by: Paolo Bonzini Signed-off-by: Radim Krčmář --- arch/x86/kvm/svm.c | 36 +++++++++++++++++++++++++++++++++++- arch/x86/kvm/x86.c | 1 + 2 files changed, 36 insertions(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index d8db947acf70..f874798f8209 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -178,6 +178,8 @@ struct vcpu_svm { uint64_t sysenter_eip; uint64_t tsc_aux; + u64 msr_decfg; + u64 next_rip; u64 host_user_msrs[NR_HOST_SAVE_USER_MSRS]; @@ -3871,7 +3873,18 @@ static int cr8_write_interception(struct vcpu_svm *svm) static int svm_get_msr_feature(struct kvm_msr_entry *msr) { - return 1; + msr->data = 0; + + switch (msr->index) { + case MSR_F10H_DECFG: + if (boot_cpu_has(X86_FEATURE_LFENCE_RDTSC)) + msr->data |= MSR_F10H_DECFG_LFENCE_SERIALIZE; + break; + default: + return 1; + } + + return 0; } static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) @@ -3969,6 +3982,9 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) msr_info->data = 0x1E; } break; + case MSR_F10H_DECFG: + msr_info->data = svm->msr_decfg; + break; default: return kvm_get_msr_common(vcpu, msr_info); } @@ -4147,6 +4163,24 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) case MSR_VM_IGNNE: vcpu_unimpl(vcpu, "unimplemented wrmsr: 0x%x data 0x%llx\n", ecx, data); break; + case MSR_F10H_DECFG: { + struct kvm_msr_entry msr_entry; + + msr_entry.index = msr->index; + if (svm_get_msr_feature(&msr_entry)) + return 1; + + /* Check the supported bits */ + if (data & ~msr_entry.data) + return 1; + + /* Don't allow the guest to change a bit, #GP */ + if (!msr->host_initiated && (data ^ msr_entry.data)) + return 1; + + svm->msr_decfg = data; + break; + } case MSR_IA32_APICBASE: if (kvm_vcpu_apicv_active(vcpu)) avic_update_vapic_bar(to_svm(vcpu), data); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 239fc1fd7845..54b4ed55945b 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1054,6 +1054,7 @@ static unsigned num_emulated_msrs; * can be used by a hypervisor to validate requested CPU features. */ static u32 msr_based_features[] = { + MSR_F10H_DECFG, }; static unsigned int num_msr_based_features; -- cgit v1.2.3-55-g7522 From 66421c1ec340096b291af763ed5721314cdd9c5c Mon Sep 17 00:00:00 2001 From: Wanpeng Li Date: Wed, 28 Feb 2018 14:03:30 +0800 Subject: KVM: X86: Introduce kvm_get_msr_feature() Introduce kvm_get_msr_feature() to handle the msrs which are supported by different vendors and sharing the same emulation logic. Cc: Paolo Bonzini Cc: Radim Krčmář Cc: Liran Alon Cc: Nadav Amit Cc: Borislav Petkov Cc: Tom Lendacky Signed-off-by: Wanpeng Li Reviewed-by: Paolo Bonzini Signed-off-by: Radim Krčmář --- arch/x86/kvm/x86.c | 18 +++++++++++++++--- 1 file changed, 15 insertions(+), 3 deletions(-) (limited to 'arch') diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 54b4ed55945b..d97620eeb394 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1059,13 +1059,25 @@ static u32 msr_based_features[] = { static unsigned int num_msr_based_features; +static int kvm_get_msr_feature(struct kvm_msr_entry *msr) +{ + switch (msr->index) { + default: + if (kvm_x86_ops->get_msr_feature(msr)) + return 1; + } + return 0; +} + static int do_get_msr_feature(struct kvm_vcpu *vcpu, unsigned index, u64 *data) { struct kvm_msr_entry msr; + int r; msr.index = index; - if (kvm_x86_ops->get_msr_feature(&msr)) - return 1; + r = kvm_get_msr_feature(&msr); + if (r) + return r; *data = msr.data; @@ -4522,7 +4534,7 @@ static void kvm_init_msr_list(void) struct kvm_msr_entry msr; msr.index = msr_based_features[i]; - if (kvm_x86_ops->get_msr_feature(&msr)) + if (kvm_get_msr_feature(&msr)) continue; if (j < i) -- cgit v1.2.3-55-g7522 From 518e7b94817abed94becfe6a44f1ece0d4745afe Mon Sep 17 00:00:00 2001 From: Wanpeng Li Date: Wed, 28 Feb 2018 14:03:31 +0800 Subject: KVM: X86: Allow userspace to define the microcode version Linux (among the others) has checks to make sure that certain features aren't enabled on a certain family/model/stepping if the microcode version isn't greater than or equal to a known good version. By exposing the real microcode version, we're preventing buggy guests that don't check that they are running virtualized (i.e., they should trust the hypervisor) from disabling features that are effectively not buggy. Suggested-by: Filippo Sironi Cc: Paolo Bonzini Cc: Radim Krčmář Cc: Liran Alon Cc: Nadav Amit Cc: Borislav Petkov Cc: Tom Lendacky Signed-off-by: Wanpeng Li Reviewed-by: Paolo Bonzini Signed-off-by: Radim Krčmář --- arch/x86/include/asm/kvm_host.h | 1 + arch/x86/kvm/svm.c | 4 +--- arch/x86/kvm/vmx.c | 1 + arch/x86/kvm/x86.c | 11 +++++++++-- 4 files changed, 12 insertions(+), 5 deletions(-) (limited to 'arch') diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index bab0694b35c3..b605a5b6a30c 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -507,6 +507,7 @@ struct kvm_vcpu_arch { u64 smi_count; bool tpr_access_reporting; u64 ia32_xss; + u64 microcode_version; /* * Paging state of the vcpu diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index f874798f8209..312f33f4ed36 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -1907,6 +1907,7 @@ static void svm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) u32 dummy; u32 eax = 1; + vcpu->arch.microcode_version = 0x01000065; svm->spec_ctrl = 0; if (!init_event) { @@ -3962,9 +3963,6 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) msr_info->data = svm->spec_ctrl; break; - case MSR_IA32_UCODE_REV: - msr_info->data = 0x01000065; - break; case MSR_F15H_IC_CFG: { int family, model; diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index fafc1f6d8987..591214843046 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -5771,6 +5771,7 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) vmx->rmode.vm86_active = 0; vmx->spec_ctrl = 0; + vcpu->arch.microcode_version = 0x100000000ULL; vmx->vcpu.arch.regs[VCPU_REGS_RDX] = get_rdx_init_val(); kvm_set_cr8(vcpu, 0); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index d97620eeb394..11649d290b93 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1055,6 +1055,7 @@ static unsigned num_emulated_msrs; */ static u32 msr_based_features[] = { MSR_F10H_DECFG, + MSR_IA32_UCODE_REV, }; static unsigned int num_msr_based_features; @@ -1062,6 +1063,9 @@ static unsigned int num_msr_based_features; static int kvm_get_msr_feature(struct kvm_msr_entry *msr) { switch (msr->index) { + case MSR_IA32_UCODE_REV: + rdmsrl(msr->index, msr->data); + break; default: if (kvm_x86_ops->get_msr_feature(msr)) return 1; @@ -2257,7 +2261,6 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) switch (msr) { case MSR_AMD64_NB_CFG: - case MSR_IA32_UCODE_REV: case MSR_IA32_UCODE_WRITE: case MSR_VM_HSAVE_PA: case MSR_AMD64_PATCH_LOADER: @@ -2265,6 +2268,10 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_AMD64_DC_CFG: break; + case MSR_IA32_UCODE_REV: + if (msr_info->host_initiated) + vcpu->arch.microcode_version = data; + break; case MSR_EFER: return set_efer(vcpu, data); case MSR_K7_HWCR: @@ -2560,7 +2567,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) msr_info->data = 0; break; case MSR_IA32_UCODE_REV: - msr_info->data = 0x100000000ULL; + msr_info->data = vcpu->arch.microcode_version; break; case MSR_MTRRcap: case 0x200 ... 0x2ff: -- cgit v1.2.3-55-g7522 From b7e31be385584afe7f073130e8e570d53c95f7fe Mon Sep 17 00:00:00 2001 From: Radim Krčmář Date: Thu, 1 Mar 2018 15:24:25 +0100 Subject: KVM: x86: fix vcpu initialization with userspace lapic Moving the code around broke this rare configuration. Use this opportunity to finally call lapic reset from vcpu reset. Reported-by: syzbot+fb7a33a4b6c35007a72b@syzkaller.appspotmail.com Suggested-by: Paolo Bonzini Fixes: 0b2e9904c159 ("KVM: x86: move LAPIC initialization after VMCS creation") Cc: stable@vger.kernel.org Signed-off-by: Radim Krčmář --- arch/x86/kvm/lapic.c | 10 ++++------ arch/x86/kvm/x86.c | 3 ++- 2 files changed, 6 insertions(+), 7 deletions(-) (limited to 'arch') diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index cc5fe7a50dde..391dda8d43b7 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -2002,14 +2002,13 @@ void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value) void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event) { - struct kvm_lapic *apic; + struct kvm_lapic *apic = vcpu->arch.apic; int i; - apic_debug("%s\n", __func__); + if (!apic) + return; - ASSERT(vcpu); - apic = vcpu->arch.apic; - ASSERT(apic != NULL); + apic_debug("%s\n", __func__); /* Stop the timer in case it's a reset to an active apic */ hrtimer_cancel(&apic->lapic_timer.timer); @@ -2568,7 +2567,6 @@ void kvm_apic_accept_events(struct kvm_vcpu *vcpu) pe = xchg(&apic->pending_events, 0); if (test_bit(KVM_APIC_INIT, &pe)) { - kvm_lapic_reset(vcpu, true); kvm_vcpu_reset(vcpu, true); if (kvm_vcpu_is_bsp(apic->vcpu)) vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 11649d290b93..18b5ca7a3197 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -8060,7 +8060,6 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) kvm_vcpu_mtrr_init(vcpu); vcpu_load(vcpu); kvm_vcpu_reset(vcpu, false); - kvm_lapic_reset(vcpu, false); kvm_mmu_setup(vcpu); vcpu_put(vcpu); return 0; @@ -8103,6 +8102,8 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) { + kvm_lapic_reset(vcpu, init_event); + vcpu->arch.hflags = 0; vcpu->arch.smi_pending = 0; -- cgit v1.2.3-55-g7522 From 1b1e4ee86e0064ea2a8b8e5ead13734b1e813a92 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Tue, 20 Feb 2018 02:09:42 +0900 Subject: sh: fix build error for empty CONFIG_BUILTIN_DTB_SOURCE If CONFIG_USE_BUILTIN_DTB is enabled, but CONFIG_BUILTIN_DTB_SOURCE is empty (for example, allmodconfig), it fails to build, like this: make[2]: *** No rule to make target 'arch/sh/boot/dts/.dtb.o', needed by 'arch/sh/boot/dts/built-in.o'. Stop. Surround obj-y with ifneq ... endif. I replaced $(CONFIG_USE_BUILTIN_DTB) with 'y' since this is always the case from the following code from arch/sh/Makefile: core-$(CONFIG_USE_BUILTIN_DTB) += arch/sh/boot/dts/ Signed-off-by: Masahiro Yamada --- arch/sh/boot/dts/Makefile | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/sh/boot/dts/Makefile b/arch/sh/boot/dts/Makefile index 715def00a436..01d0f7fb14cc 100644 --- a/arch/sh/boot/dts/Makefile +++ b/arch/sh/boot/dts/Makefile @@ -1 +1,3 @@ -obj-$(CONFIG_USE_BUILTIN_DTB) += $(patsubst "%",%,$(CONFIG_BUILTIN_DTB_SOURCE)).dtb.o +ifneq ($(CONFIG_BUILTIN_DTB_SOURCE),"") +obj-y += $(patsubst "%",%,$(CONFIG_BUILTIN_DTB_SOURCE)).dtb.o +endif -- cgit v1.2.3-55-g7522 From c3856aeb29402e94ad9b3879030165cc6a4fdc56 Mon Sep 17 00:00:00 2001 From: Paul Mackerras Date: Fri, 23 Feb 2018 21:21:12 +1100 Subject: KVM: PPC: Book3S HV: Fix handling of large pages in radix page fault handler This fixes several bugs in the radix page fault handler relating to the way large pages in the memory backing the guest were handled. First, the check for large pages only checked for explicit huge pages and missed transparent huge pages. Then the check that the addresses (host virtual vs. guest physical) had appropriate alignment was wrong, meaning that the code never put a large page in the partition scoped radix tree; it was always demoted to a small page. Fixing this exposed bugs in kvmppc_create_pte(). We were never invalidating a 2MB PTE, which meant that if a page was initially faulted in without write permission and the guest then attempted to store to it, we would never update the PTE to have write permission. If we find a valid 2MB PTE in the PMD, we need to clear it and do a TLB invalidation before installing either the new 2MB PTE or a pointer to a page table page. This also corrects an assumption that get_user_pages_fast would set the _PAGE_DIRTY bit if we are writing, which is not true. Instead we mark the page dirty explicitly with set_page_dirty_lock(). This also means we don't need the dirty bit set on the host PTE when providing write access on a read fault. Signed-off-by: Paul Mackerras --- arch/powerpc/kvm/book3s_64_mmu_radix.c | 69 +++++++++++++++++++++------------- 1 file changed, 43 insertions(+), 26 deletions(-) (limited to 'arch') diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c index 0c854816e653..5cb4e4687107 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_radix.c +++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c @@ -195,6 +195,12 @@ static void kvmppc_pte_free(pte_t *ptep) kmem_cache_free(kvm_pte_cache, ptep); } +/* Like pmd_huge() and pmd_large(), but works regardless of config options */ +static inline int pmd_is_leaf(pmd_t pmd) +{ + return !!(pmd_val(pmd) & _PAGE_PTE); +} + static int kvmppc_create_pte(struct kvm *kvm, pte_t pte, unsigned long gpa, unsigned int level, unsigned long mmu_seq) { @@ -219,7 +225,7 @@ static int kvmppc_create_pte(struct kvm *kvm, pte_t pte, unsigned long gpa, else new_pmd = pmd_alloc_one(kvm->mm, gpa); - if (level == 0 && !(pmd && pmd_present(*pmd))) + if (level == 0 && !(pmd && pmd_present(*pmd) && !pmd_is_leaf(*pmd))) new_ptep = kvmppc_pte_alloc(); /* Check if we might have been invalidated; let the guest retry if so */ @@ -244,12 +250,30 @@ static int kvmppc_create_pte(struct kvm *kvm, pte_t pte, unsigned long gpa, new_pmd = NULL; } pmd = pmd_offset(pud, gpa); - if (pmd_large(*pmd)) { - /* Someone else has instantiated a large page here; retry */ - ret = -EAGAIN; - goto out_unlock; - } - if (level == 1 && !pmd_none(*pmd)) { + if (pmd_is_leaf(*pmd)) { + unsigned long lgpa = gpa & PMD_MASK; + + /* + * If we raced with another CPU which has just put + * a 2MB pte in after we saw a pte page, try again. + */ + if (level == 0 && !new_ptep) { + ret = -EAGAIN; + goto out_unlock; + } + /* Valid 2MB page here already, remove it */ + old = kvmppc_radix_update_pte(kvm, pmdp_ptep(pmd), + ~0UL, 0, lgpa, PMD_SHIFT); + kvmppc_radix_tlbie_page(kvm, lgpa, PMD_SHIFT); + if (old & _PAGE_DIRTY) { + unsigned long gfn = lgpa >> PAGE_SHIFT; + struct kvm_memory_slot *memslot; + memslot = gfn_to_memslot(kvm, gfn); + if (memslot && memslot->dirty_bitmap) + kvmppc_update_dirty_map(memslot, + gfn, PMD_SIZE); + } + } else if (level == 1 && !pmd_none(*pmd)) { /* * There's a page table page here, but we wanted * to install a large page. Tell the caller and let @@ -412,28 +436,24 @@ int kvmppc_book3s_radix_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu, } else { page = pages[0]; pfn = page_to_pfn(page); - if (PageHuge(page)) { - page = compound_head(page); - pte_size <<= compound_order(page); + if (PageCompound(page)) { + pte_size <<= compound_order(compound_head(page)); /* See if we can insert a 2MB large-page PTE here */ if (pte_size >= PMD_SIZE && - (gpa & PMD_MASK & PAGE_MASK) == - (hva & PMD_MASK & PAGE_MASK)) { + (gpa & (PMD_SIZE - PAGE_SIZE)) == + (hva & (PMD_SIZE - PAGE_SIZE))) { level = 1; pfn &= ~((PMD_SIZE >> PAGE_SHIFT) - 1); } } /* See if we can provide write access */ if (writing) { - /* - * We assume gup_fast has set dirty on the host PTE. - */ pgflags |= _PAGE_WRITE; } else { local_irq_save(flags); ptep = find_current_mm_pte(current->mm->pgd, hva, NULL, NULL); - if (ptep && pte_write(*ptep) && pte_dirty(*ptep)) + if (ptep && pte_write(*ptep)) pgflags |= _PAGE_WRITE; local_irq_restore(flags); } @@ -459,18 +479,15 @@ int kvmppc_book3s_radix_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu, pte = pfn_pte(pfn, __pgprot(pgflags)); ret = kvmppc_create_pte(kvm, pte, gpa, level, mmu_seq); } - if (ret == 0 || ret == -EAGAIN) - ret = RESUME_GUEST; if (page) { - /* - * We drop pages[0] here, not page because page might - * have been set to the head page of a compound, but - * we have to drop the reference on the correct tail - * page to match the get inside gup() - */ - put_page(pages[0]); + if (!ret && (pgflags & _PAGE_WRITE)) + set_page_dirty_lock(page); + put_page(page); } + + if (ret == 0 || ret == -EAGAIN) + ret = RESUME_GUEST; return ret; } @@ -644,7 +661,7 @@ void kvmppc_free_radix(struct kvm *kvm) continue; pmd = pmd_offset(pud, 0); for (im = 0; im < PTRS_PER_PMD; ++im, ++pmd) { - if (pmd_huge(*pmd)) { + if (pmd_is_leaf(*pmd)) { pmd_clear(pmd); continue; } -- cgit v1.2.3-55-g7522 From debd574f4195e205ba505b25e19b2b797f4bcd94 Mon Sep 17 00:00:00 2001 From: Paul Mackerras Date: Fri, 2 Mar 2018 15:38:04 +1100 Subject: KVM: PPC: Book3S HV: Fix VRMA initialization with 2MB or 1GB memory backing The current code for initializing the VRMA (virtual real memory area) for HPT guests requires the page size of the backing memory to be one of 4kB, 64kB or 16MB. With a radix host we have the possibility that the backing memory page size can be 2MB or 1GB. In these cases, if the guest switches to HPT mode, KVM will not initialize the VRMA and the guest will fail to run. In fact it is not necessary that the VRMA page size is the same as the backing memory page size; any VRMA page size less than or equal to the backing memory page size is acceptable. Therefore we now choose the largest page size out of the set {4k, 64k, 16M} which is not larger than the backing memory page size. Signed-off-by: Paul Mackerras --- arch/powerpc/kvm/book3s_hv.c | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) (limited to 'arch') diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index 89707354c2ef..b4a538b29da5 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -3656,15 +3656,17 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu) goto up_out; psize = vma_kernel_pagesize(vma); - porder = __ilog2(psize); up_read(¤t->mm->mmap_sem); /* We can handle 4k, 64k or 16M pages in the VRMA */ - err = -EINVAL; - if (!(psize == 0x1000 || psize == 0x10000 || - psize == 0x1000000)) - goto out_srcu; + if (psize >= 0x1000000) + psize = 0x1000000; + else if (psize >= 0x10000) + psize = 0x10000; + else + psize = 0x1000; + porder = __ilog2(psize); senc = slb_pgsize_encoding(psize); kvm->arch.vrma_slb_v = senc | SLB_VSID_B_1T | -- cgit v1.2.3-55-g7522 From 0adb24e03a124b79130c9499731936b11ce2677d Mon Sep 17 00:00:00 2001 From: John David Anglin Date: Tue, 27 Feb 2018 08:16:07 -0500 Subject: parisc: Fix ordering of cache and TLB flushes The change to flush_kernel_vmap_range() wasn't sufficient to avoid the SMP stalls.  The problem is some drivers call these routines with interrupts disabled.  Interrupts need to be enabled for flush_tlb_all() and flush_cache_all() to work.  This version adds checks to ensure interrupts are not disabled before calling routines that need IPI interrupts.  When interrupts are disabled, we now drop into slower code. The attached change fixes the ordering of cache and TLB flushes in several cases.  When we flush the cache using the existing PTE/TLB entries, we need to flush the TLB after doing the cache flush.  We don't need to do this when we flush the entire instruction and data caches as these flushes don't use the existing TLB entries.  The same is true for tmpalias region flushes. The flush_kernel_vmap_range() and invalidate_kernel_vmap_range() routines have been updated. Secondly, we added a new purge_kernel_dcache_range_asm() routine to pacache.S and use it in invalidate_kernel_vmap_range().  Nominally, purges are faster than flushes as the cache lines don't have to be written back to memory. Hopefully, this is sufficient to resolve the remaining problems due to cache speculation.  So far, testing indicates that this is the case.  I did work up a patch using tmpalias flushes, but there is a performance hit because we need the physical address for each page, and we also need to sequence access to the tmpalias flush code.  This increases the probability of stalls. Signed-off-by: John David Anglin  Cc: stable@vger.kernel.org # 4.9+ Signed-off-by: Helge Deller --- arch/parisc/include/asm/cacheflush.h | 1 + arch/parisc/kernel/cache.c | 57 ++++++++++++++++++++---------------- arch/parisc/kernel/pacache.S | 22 ++++++++++++++ 3 files changed, 54 insertions(+), 26 deletions(-) (limited to 'arch') diff --git a/arch/parisc/include/asm/cacheflush.h b/arch/parisc/include/asm/cacheflush.h index 3742508cc534..bd5ce31936f5 100644 --- a/arch/parisc/include/asm/cacheflush.h +++ b/arch/parisc/include/asm/cacheflush.h @@ -26,6 +26,7 @@ void flush_user_icache_range_asm(unsigned long, unsigned long); void flush_kernel_icache_range_asm(unsigned long, unsigned long); void flush_user_dcache_range_asm(unsigned long, unsigned long); void flush_kernel_dcache_range_asm(unsigned long, unsigned long); +void purge_kernel_dcache_range_asm(unsigned long, unsigned long); void flush_kernel_dcache_page_asm(void *); void flush_kernel_icache_page(void *); diff --git a/arch/parisc/kernel/cache.c b/arch/parisc/kernel/cache.c index 19c0c141bc3f..79089778725b 100644 --- a/arch/parisc/kernel/cache.c +++ b/arch/parisc/kernel/cache.c @@ -465,10 +465,10 @@ EXPORT_SYMBOL(copy_user_page); int __flush_tlb_range(unsigned long sid, unsigned long start, unsigned long end) { - unsigned long flags, size; + unsigned long flags; - size = (end - start); - if (size >= parisc_tlb_flush_threshold) { + if ((!IS_ENABLED(CONFIG_SMP) || !arch_irqs_disabled()) && + end - start >= parisc_tlb_flush_threshold) { flush_tlb_all(); return 1; } @@ -539,13 +539,11 @@ void flush_cache_mm(struct mm_struct *mm) struct vm_area_struct *vma; pgd_t *pgd; - /* Flush the TLB to avoid speculation if coherency is required. */ - if (parisc_requires_coherency()) - flush_tlb_all(); - /* Flushing the whole cache on each cpu takes forever on rp3440, etc. So, avoid it if the mm isn't too big. */ - if (mm_total_size(mm) >= parisc_cache_flush_threshold) { + if ((!IS_ENABLED(CONFIG_SMP) || !arch_irqs_disabled()) && + mm_total_size(mm) >= parisc_cache_flush_threshold) { + flush_tlb_all(); flush_cache_all(); return; } @@ -553,9 +551,9 @@ void flush_cache_mm(struct mm_struct *mm) if (mm->context == mfsp(3)) { for (vma = mm->mmap; vma; vma = vma->vm_next) { flush_user_dcache_range_asm(vma->vm_start, vma->vm_end); - if ((vma->vm_flags & VM_EXEC) == 0) - continue; - flush_user_icache_range_asm(vma->vm_start, vma->vm_end); + if (vma->vm_flags & VM_EXEC) + flush_user_icache_range_asm(vma->vm_start, vma->vm_end); + flush_tlb_range(vma, vma->vm_start, vma->vm_end); } return; } @@ -581,14 +579,9 @@ void flush_cache_mm(struct mm_struct *mm) void flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned long end) { - BUG_ON(!vma->vm_mm->context); - - /* Flush the TLB to avoid speculation if coherency is required. */ - if (parisc_requires_coherency()) + if ((!IS_ENABLED(CONFIG_SMP) || !arch_irqs_disabled()) && + end - start >= parisc_cache_flush_threshold) { flush_tlb_range(vma, start, end); - - if ((end - start) >= parisc_cache_flush_threshold - || vma->vm_mm->context != mfsp(3)) { flush_cache_all(); return; } @@ -596,6 +589,7 @@ void flush_cache_range(struct vm_area_struct *vma, flush_user_dcache_range_asm(start, end); if (vma->vm_flags & VM_EXEC) flush_user_icache_range_asm(start, end); + flush_tlb_range(vma, start, end); } void @@ -604,8 +598,7 @@ flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr, unsigned long BUG_ON(!vma->vm_mm->context); if (pfn_valid(pfn)) { - if (parisc_requires_coherency()) - flush_tlb_page(vma, vmaddr); + flush_tlb_page(vma, vmaddr); __flush_cache_page(vma, vmaddr, PFN_PHYS(pfn)); } } @@ -613,21 +606,33 @@ flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr, unsigned long void flush_kernel_vmap_range(void *vaddr, int size) { unsigned long start = (unsigned long)vaddr; + unsigned long end = start + size; - if ((unsigned long)size > parisc_cache_flush_threshold) + if ((!IS_ENABLED(CONFIG_SMP) || !arch_irqs_disabled()) && + (unsigned long)size >= parisc_cache_flush_threshold) { + flush_tlb_kernel_range(start, end); flush_data_cache(); - else - flush_kernel_dcache_range_asm(start, start + size); + return; + } + + flush_kernel_dcache_range_asm(start, end); + flush_tlb_kernel_range(start, end); } EXPORT_SYMBOL(flush_kernel_vmap_range); void invalidate_kernel_vmap_range(void *vaddr, int size) { unsigned long start = (unsigned long)vaddr; + unsigned long end = start + size; - if ((unsigned long)size > parisc_cache_flush_threshold) + if ((!IS_ENABLED(CONFIG_SMP) || !arch_irqs_disabled()) && + (unsigned long)size >= parisc_cache_flush_threshold) { + flush_tlb_kernel_range(start, end); flush_data_cache(); - else - flush_kernel_dcache_range_asm(start, start + size); + return; + } + + purge_kernel_dcache_range_asm(start, end); + flush_tlb_kernel_range(start, end); } EXPORT_SYMBOL(invalidate_kernel_vmap_range); diff --git a/arch/parisc/kernel/pacache.S b/arch/parisc/kernel/pacache.S index 2d40c4ff3f69..67b0f7532e83 100644 --- a/arch/parisc/kernel/pacache.S +++ b/arch/parisc/kernel/pacache.S @@ -1110,6 +1110,28 @@ ENTRY_CFI(flush_kernel_dcache_range_asm) .procend ENDPROC_CFI(flush_kernel_dcache_range_asm) +ENTRY_CFI(purge_kernel_dcache_range_asm) + .proc + .callinfo NO_CALLS + .entry + + ldil L%dcache_stride, %r1 + ldw R%dcache_stride(%r1), %r23 + ldo -1(%r23), %r21 + ANDCM %r26, %r21, %r26 + +1: cmpb,COND(<<),n %r26, %r25,1b + pdc,m %r23(%r26) + + sync + syncdma + bv %r0(%r2) + nop + .exit + + .procend +ENDPROC_CFI(purge_kernel_dcache_range_asm) + ENTRY_CFI(flush_user_icache_range_asm) .proc .callinfo NO_CALLS -- cgit v1.2.3-55-g7522 From fd8d0ca2563151204f3fe555dc8ca4bcfe8677a3 Mon Sep 17 00:00:00 2001 From: Helge Deller Date: Fri, 12 Jan 2018 22:57:15 +0100 Subject: parisc: Hide virtual kernel memory layout For security reasons do not expose the virtual kernel memory layout to userspace. Signed-off-by: Helge Deller Suggested-by: Kees Cook Cc: stable@vger.kernel.org # 4.15 Reviewed-by: Kees Cook --- arch/parisc/mm/init.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/parisc/mm/init.c b/arch/parisc/mm/init.c index 48f41399fc0b..cab32ee824d2 100644 --- a/arch/parisc/mm/init.c +++ b/arch/parisc/mm/init.c @@ -629,7 +629,12 @@ void __init mem_init(void) #endif mem_init_print_info(NULL); -#ifdef CONFIG_DEBUG_KERNEL /* double-sanity-check paranoia */ + +#if 0 + /* + * Do not expose the virtual kernel memory layout to userspace. + * But keep code for debugging purposes. + */ printk("virtual kernel memory layout:\n" " vmalloc : 0x%px - 0x%px (%4ld MB)\n" " memory : 0x%px - 0x%px (%4ld MB)\n" -- cgit v1.2.3-55-g7522 From 0ed1fe4ad394e54783bbffa84102faf435661a2e Mon Sep 17 00:00:00 2001 From: Helge Deller Date: Fri, 12 Jan 2018 22:51:22 +0100 Subject: parisc: Check if secondary CPUs want own PDC calls The architecture specification says (for 64-bit systems): PDC is a per processor resource, and operating system software must be prepared to manage separate pointers to PDCE_PROC for each processor. The address of PDCE_PROC for the monarch processor is stored in the Page Zero location MEM_PDC. The address of PDCE_PROC for each non-monarch processor is passed in gr26 when PDCE_RESET invokes OS_RENDEZ. Currently we still use one PDC for all CPUs, but in case we face a machine which is following the specification let's warn about it. Signed-off-by: Helge Deller --- arch/parisc/kernel/head.S | 18 ++++++++++++------ arch/parisc/kernel/smp.c | 7 ++++++- 2 files changed, 18 insertions(+), 7 deletions(-) (limited to 'arch') diff --git a/arch/parisc/kernel/head.S b/arch/parisc/kernel/head.S index bbbe360b458f..fbb4e43fda05 100644 --- a/arch/parisc/kernel/head.S +++ b/arch/parisc/kernel/head.S @@ -138,6 +138,16 @@ $pgt_fill_loop: std %dp,0x18(%r10) #endif +#ifdef CONFIG_64BIT + /* Get PDCE_PROC for monarch CPU. */ +#define MEM_PDC_LO 0x388 +#define MEM_PDC_HI 0x35C + ldw MEM_PDC_LO(%r0),%r3 + ldw MEM_PDC_HI(%r0),%r10 + depd %r10, 31, 32, %r3 /* move to upper word */ +#endif + + #ifdef CONFIG_SMP /* Set the smp rendezvous address into page zero. ** It would be safer to do this in init_smp_config() but @@ -196,12 +206,6 @@ common_stext: ** Someday, palo might not do this for the Monarch either. */ 2: -#define MEM_PDC_LO 0x388 -#define MEM_PDC_HI 0x35C - ldw MEM_PDC_LO(%r0),%r3 - ldw MEM_PDC_HI(%r0),%r6 - depd %r6, 31, 32, %r3 /* move to upper word */ - mfctl %cr30,%r6 /* PCX-W2 firmware bug */ ldo PDC_PSW(%r0),%arg0 /* 21 */ @@ -268,6 +272,8 @@ $install_iva: aligned_rfi: pcxt_ssm_bug + copy %r3, %arg0 /* PDCE_PROC for smp_callin() */ + rsm PSW_SM_QUIET,%r0 /* off troublesome PSW bits */ /* Don't need NOPs, have 8 compliant insn before rfi */ diff --git a/arch/parisc/kernel/smp.c b/arch/parisc/kernel/smp.c index 30c28ab14540..4065b5e48c9d 100644 --- a/arch/parisc/kernel/smp.c +++ b/arch/parisc/kernel/smp.c @@ -292,10 +292,15 @@ smp_cpu_init(int cpunum) * Slaves start using C here. Indirectly called from smp_slave_stext. * Do what start_kernel() and main() do for boot strap processor (aka monarch) */ -void __init smp_callin(void) +void __init smp_callin(unsigned long pdce_proc) { int slave_id = cpu_now_booting; +#ifdef CONFIG_64BIT + WARN_ON(((unsigned long)(PAGE0->mem_pdc_hi) << 32 + | PAGE0->mem_pdc) != pdce_proc); +#endif + smp_cpu_init(slave_id); preempt_disable(); -- cgit v1.2.3-55-g7522 From 5ffa8518851f1401817c15d2a7eecc0373c26ff9 Mon Sep 17 00:00:00 2001 From: Helge Deller Date: Fri, 12 Jan 2018 22:44:00 +0100 Subject: parisc: Use cr16 interval timers unconditionally on qemu When running on qemu we know that the (emulated) cr16 cpu-internal clocks are syncronized. So let's use them unconditionally on qemu. Signed-off-by: Helge Deller Cc: stable@vger.kernel.org # 4.14+ --- arch/parisc/include/asm/processor.h | 2 ++ arch/parisc/kernel/time.c | 2 +- 2 files changed, 3 insertions(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/parisc/include/asm/processor.h b/arch/parisc/include/asm/processor.h index 0e6ab6e4a4e9..2dbe5580a1a4 100644 --- a/arch/parisc/include/asm/processor.h +++ b/arch/parisc/include/asm/processor.h @@ -316,6 +316,8 @@ extern int _parisc_requires_coherency; #define parisc_requires_coherency() (0) #endif +extern int running_on_qemu; + #endif /* __ASSEMBLY__ */ #endif /* __ASM_PARISC_PROCESSOR_H */ diff --git a/arch/parisc/kernel/time.c b/arch/parisc/kernel/time.c index 4b8fd6dc22da..68e88e5c0898 100644 --- a/arch/parisc/kernel/time.c +++ b/arch/parisc/kernel/time.c @@ -248,7 +248,7 @@ static int __init init_cr16_clocksource(void) * different sockets, so mark them unstable and lower rating on * multi-socket SMP systems. */ - if (num_online_cpus() > 1) { + if (num_online_cpus() > 1 && !running_on_qemu) { int cpu; unsigned long cpu0_loc; cpu0_loc = per_cpu(cpu_data, 0).cpu_loc; -- cgit v1.2.3-55-g7522 From 636a415bcc7f4fd020ece8fd5fc648c4cef19c34 Mon Sep 17 00:00:00 2001 From: Helge Deller Date: Mon, 12 Feb 2018 21:43:55 +0100 Subject: parisc: Reduce irq overhead when run in qemu When run under QEMU, calling mfctl(16) creates some overhead because the qemu timer has to be scaled and moved into the register. This patch reduces the number of calls to mfctl(16) by moving the calls out of the loops. Additionally, increase the minimal time interval to 8000 cycles instead of 500 to compensate possible QEMU delays when delivering interrupts. Signed-off-by: Helge Deller Cc: stable@vger.kernel.org # 4.14+ --- arch/parisc/kernel/time.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'arch') diff --git a/arch/parisc/kernel/time.c b/arch/parisc/kernel/time.c index 68e88e5c0898..f7e684560186 100644 --- a/arch/parisc/kernel/time.c +++ b/arch/parisc/kernel/time.c @@ -76,10 +76,10 @@ irqreturn_t __irq_entry timer_interrupt(int irq, void *dev_id) next_tick = cpuinfo->it_value; /* Calculate how many ticks have elapsed. */ + now = mfctl(16); do { ++ticks_elapsed; next_tick += cpt; - now = mfctl(16); } while (next_tick - now > cpt); /* Store (in CR16 cycles) up to when we are accounting right now. */ @@ -103,16 +103,17 @@ irqreturn_t __irq_entry timer_interrupt(int irq, void *dev_id) * if one or the other wrapped. If "now" is "bigger" we'll end up * with a very large unsigned number. */ - while (next_tick - mfctl(16) > cpt) + now = mfctl(16); + while (next_tick - now > cpt) next_tick += cpt; /* Program the IT when to deliver the next interrupt. * Only bottom 32-bits of next_tick are writable in CR16! * Timer interrupt will be delivered at least a few hundred cycles - * after the IT fires, so if we are too close (<= 500 cycles) to the + * after the IT fires, so if we are too close (<= 8000 cycles) to the * next cycle, simply skip it. */ - if (next_tick - mfctl(16) <= 500) + if (next_tick - now <= 8000) next_tick += cpt; mtctl(next_tick, 16); -- cgit v1.2.3-55-g7522 From 61e18270f604c744ed9f8f1b740022516f9726f8 Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Thu, 1 Mar 2018 14:40:52 -0800 Subject: s390: Fix runtime warning about negative pgtables_bytes When running s390 images with 'compat' processes, the following BUG is seen repeatedly. BUG: non-zero pgtables_bytes on freeing mm: -16384 Bisect points to commit b4e98d9ac775 ("mm: account pud page tables"). Analysis shows that init_new_context() is called with mm->context.asce_limit set to _REGION3_SIZE. In this situation, pgtables_bytes remains set to 0 and is not increased. The message is displayed when the affected process dies and mm_dec_nr_puds() is called. Cc: Kirill A. Shutemov Cc: Heiko Carstens Fixes: b4e98d9ac775 ("mm: account pud page tables") Signed-off-by: Guenter Roeck Signed-off-by: Martin Schwidefsky --- arch/s390/include/asm/mmu_context.h | 1 + 1 file changed, 1 insertion(+) (limited to 'arch') diff --git a/arch/s390/include/asm/mmu_context.h b/arch/s390/include/asm/mmu_context.h index 65154eaa3714..6c8ce15cde7b 100644 --- a/arch/s390/include/asm/mmu_context.h +++ b/arch/s390/include/asm/mmu_context.h @@ -63,6 +63,7 @@ static inline int init_new_context(struct task_struct *tsk, _ASCE_USER_BITS | _ASCE_TYPE_SEGMENT; /* pgd_alloc() did not account this pmd */ mm_inc_nr_pmds(mm); + mm_inc_nr_puds(mm); } crst_table_init((unsigned long *) mm->pgd, pgd_entry_type(mm)); return 0; -- cgit v1.2.3-55-g7522 From 61bd0f66ff92d5ce765ff9850fd3cbfec773c560 Mon Sep 17 00:00:00 2001 From: Laurent Vivier Date: Fri, 2 Mar 2018 11:51:56 +0100 Subject: KVM: PPC: Book3S HV: Fix guest time accounting with VIRT_CPU_ACCOUNTING_GEN Since commit 8b24e69fc47e ("KVM: PPC: Book3S HV: Close race with testing for signals on guest entry"), if CONFIG_VIRT_CPU_ACCOUNTING_GEN is set, the guest time is not accounted to guest time and user time, but instead to system time. This is because guest_enter()/guest_exit() are called while interrupts are disabled and the tick counter cannot be updated between them. To fix that, move guest_exit() after local_irq_enable(), and as guest_enter() is called with IRQ disabled, call guest_enter_irqoff() instead. Fixes: 8b24e69fc47e ("KVM: PPC: Book3S HV: Close race with testing for signals on guest entry") Signed-off-by: Laurent Vivier Reviewed-by: Paolo Bonzini Signed-off-by: Paul Mackerras --- arch/powerpc/kvm/book3s_hv.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'arch') diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index b4a538b29da5..9cb9448163c4 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -2885,7 +2885,7 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc) */ trace_hardirqs_on(); - guest_enter(); + guest_enter_irqoff(); srcu_idx = srcu_read_lock(&vc->kvm->srcu); @@ -2893,8 +2893,6 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc) srcu_read_unlock(&vc->kvm->srcu, srcu_idx); - guest_exit(); - trace_hardirqs_off(); set_irq_happened(trap); @@ -2937,6 +2935,7 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc) kvmppc_set_host_core(pcpu); local_irq_enable(); + guest_exit(); /* Let secondaries go back to the offline loop */ for (i = 0; i < controlled_threads; ++i) { -- cgit v1.2.3-55-g7522 From 317660940fd9dddd3201c2f92e25c27902c753fa Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Fri, 2 Mar 2018 07:22:30 -0800 Subject: perf/x86/intel/uncore: Fix Skylake UPI event format There is no event extension (bit 21) for SKX UPI, so use 'event' instead of 'event_ext'. Reported-by: Stephane Eranian Signed-off-by: Kan Liang Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Vince Weaver Fixes: cd34cd97b7b4 ("perf/x86/intel/uncore: Add Skylake server uncore support") Link: http://lkml.kernel.org/r/1520004150-4855-1-git-send-email-kan.liang@linux.intel.com Signed-off-by: Ingo Molnar --- arch/x86/events/intel/uncore_snbep.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c index 6d8044ab1060..22ec65bc033a 100644 --- a/arch/x86/events/intel/uncore_snbep.c +++ b/arch/x86/events/intel/uncore_snbep.c @@ -3606,7 +3606,7 @@ static struct intel_uncore_type skx_uncore_imc = { }; static struct attribute *skx_upi_uncore_formats_attr[] = { - &format_attr_event_ext.attr, + &format_attr_event.attr, &format_attr_umask_ext.attr, &format_attr_edge.attr, &format_attr_inv.attr, -- cgit v1.2.3-55-g7522 From 6cfc70c4321bde35cb132831cba4685821e65065 Mon Sep 17 00:00:00 2001 From: Huacai Chen Date: Thu, 1 Mar 2018 10:37:41 +0800 Subject: MIPS: Loongson64: Select ARCH_MIGHT_HAVE_PC_PARPORT Commit a211a0820d3c ("MIPS: Push ARCH_MIGHT_HAVE_PC_PARPORT down to platform level") moves the global MIPS ARCH_MIGHT_HAVE_PC_PARPORT select down to various platforms, but doesn't add it to Loongson64 platforms which need it, so add the selects to these platforms too. Fixes: a211a0820d3c ("MIPS: Push ARCH_MIGHT_HAVE_PC_PARPORT down to platform level") Signed-off-by: Huacai Chen Cc: Ralf Baechle Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/18703/ Signed-off-by: James Hogan --- arch/mips/loongson64/Kconfig | 3 +++ 1 file changed, 3 insertions(+) (limited to 'arch') diff --git a/arch/mips/loongson64/Kconfig b/arch/mips/loongson64/Kconfig index bc2fdbfa8223..12812a8b640c 100644 --- a/arch/mips/loongson64/Kconfig +++ b/arch/mips/loongson64/Kconfig @@ -7,6 +7,7 @@ choice config LEMOTE_FULOONG2E bool "Lemote Fuloong(2e) mini-PC" select ARCH_SPARSEMEM_ENABLE + select ARCH_MIGHT_HAVE_PC_PARPORT select CEVT_R4K select CSRC_R4K select SYS_HAS_CPU_LOONGSON2E @@ -33,6 +34,7 @@ config LEMOTE_FULOONG2E config LEMOTE_MACH2F bool "Lemote Loongson 2F family machines" select ARCH_SPARSEMEM_ENABLE + select ARCH_MIGHT_HAVE_PC_PARPORT select BOARD_SCACHE select BOOT_ELF32 select CEVT_R4K if ! MIPS_EXTERNAL_TIMER @@ -62,6 +64,7 @@ config LEMOTE_MACH2F config LOONGSON_MACH3X bool "Generic Loongson 3 family machines" select ARCH_SPARSEMEM_ENABLE + select ARCH_MIGHT_HAVE_PC_PARPORT select GENERIC_ISA_DMA_SUPPORT_BROKEN select BOOT_ELF32 select BOARD_SCACHE -- cgit v1.2.3-55-g7522 From ee2515d95f9a12e04a3863916ae45831438210ce Mon Sep 17 00:00:00 2001 From: Huacai Chen Date: Thu, 1 Mar 2018 10:37:42 +0800 Subject: MIPS: Loongson64: Select ARCH_MIGHT_HAVE_PC_SERIO Commit 7a407aa5e0d3 ("MIPS: Push ARCH_MIGHT_HAVE_PC_SERIO down to platform level") moves the global MIPS ARCH_MIGHT_HAVE_PC_SERIO select down to various platforms, but doesn't add it to Loongson64 platforms which need it, so add the selects to these platforms too. Fixes: 7a407aa5e0d3 ("MIPS: Push ARCH_MIGHT_HAVE_PC_SERIO down to platform level") Signed-off-by: Huacai Chen Cc: Ralf Baechle Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/18704/ Signed-off-by: James Hogan --- arch/mips/loongson64/Kconfig | 3 +++ 1 file changed, 3 insertions(+) (limited to 'arch') diff --git a/arch/mips/loongson64/Kconfig b/arch/mips/loongson64/Kconfig index 12812a8b640c..72af0c183969 100644 --- a/arch/mips/loongson64/Kconfig +++ b/arch/mips/loongson64/Kconfig @@ -8,6 +8,7 @@ config LEMOTE_FULOONG2E bool "Lemote Fuloong(2e) mini-PC" select ARCH_SPARSEMEM_ENABLE select ARCH_MIGHT_HAVE_PC_PARPORT + select ARCH_MIGHT_HAVE_PC_SERIO select CEVT_R4K select CSRC_R4K select SYS_HAS_CPU_LOONGSON2E @@ -35,6 +36,7 @@ config LEMOTE_MACH2F bool "Lemote Loongson 2F family machines" select ARCH_SPARSEMEM_ENABLE select ARCH_MIGHT_HAVE_PC_PARPORT + select ARCH_MIGHT_HAVE_PC_SERIO select BOARD_SCACHE select BOOT_ELF32 select CEVT_R4K if ! MIPS_EXTERNAL_TIMER @@ -65,6 +67,7 @@ config LOONGSON_MACH3X bool "Generic Loongson 3 family machines" select ARCH_SPARSEMEM_ENABLE select ARCH_MIGHT_HAVE_PC_PARPORT + select ARCH_MIGHT_HAVE_PC_SERIO select GENERIC_ISA_DMA_SUPPORT_BROKEN select BOOT_ELF32 select BOARD_SCACHE -- cgit v1.2.3-55-g7522 From bd5edbe677948d0883f59d9625c444818d5284b1 Mon Sep 17 00:00:00 2001 From: Corentin Labbe Date: Wed, 14 Feb 2018 12:19:06 +0000 Subject: ia64: convert unwcheck.py to python3 Since my system use python3 as default, arch/ia64/scripts/unwcheck.py no longer run. This patch convert it to the python3 syntax. I have ran it with python2/python3 while printing values of start/end/rlen_sum which could be impacted by this change and I see no difference. Fixes: 94a47083522e ("scripts: change scripts to use system python instead of env") Signed-off-by: Corentin Labbe Signed-off-by: Tony Luck --- arch/ia64/scripts/unwcheck.py | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) (limited to 'arch') diff --git a/arch/ia64/scripts/unwcheck.py b/arch/ia64/scripts/unwcheck.py index 89f3a1480a63..c55276e31b6b 100644 --- a/arch/ia64/scripts/unwcheck.py +++ b/arch/ia64/scripts/unwcheck.py @@ -16,7 +16,7 @@ import re import sys if len(sys.argv) != 2: - print "Usage: %s FILE" % sys.argv[0] + print("Usage: %s FILE" % sys.argv[0]) sys.exit(2) readelf = os.getenv("READELF", "readelf") @@ -29,7 +29,7 @@ def check_func (func, slots, rlen_sum): global num_errors num_errors += 1 if not func: func = "[%#x-%#x]" % (start, end) - print "ERROR: %s: %lu slots, total region length = %lu" % (func, slots, rlen_sum) + print("ERROR: %s: %lu slots, total region length = %lu" % (func, slots, rlen_sum)) return num_funcs = 0 @@ -43,23 +43,23 @@ for line in os.popen("%s -u %s" % (readelf, sys.argv[1])): check_func(func, slots, rlen_sum) func = m.group(1) - start = long(m.group(2), 16) - end = long(m.group(3), 16) + start = int(m.group(2), 16) + end = int(m.group(3), 16) slots = 3 * (end - start) / 16 - rlen_sum = 0L + rlen_sum = 0 num_funcs += 1 else: m = rlen_pattern.match(line) if m: - rlen_sum += long(m.group(1)) + rlen_sum += int(m.group(1)) check_func(func, slots, rlen_sum) if num_errors == 0: - print "No errors detected in %u functions." % num_funcs + print("No errors detected in %u functions." % num_funcs) else: if num_errors > 1: err="errors" else: err="error" - print "%u %s detected in %u functions." % (num_errors, err, num_funcs) + print("%u %s detected in %u functions." % (num_errors, err, num_funcs)) sys.exit(1) -- cgit v1.2.3-55-g7522 From 2879b65f9de8b0f159b87ab57fea03096902ce41 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Mon, 19 Feb 2018 09:41:26 -0800 Subject: ia64: Convert remaining atomic operations While we've only seen inlining problems with atomic_sub_return(), the other atomic operations could have the same problem. Convert all remaining operations to use the same solution as atomic_sub_return(). Signed-off-by: Matthew Wilcox Signed-off-by: Tony Luck --- arch/ia64/include/asm/atomic.h | 69 ++++++++++++++---------------------------- 1 file changed, 23 insertions(+), 46 deletions(-) (limited to 'arch') diff --git a/arch/ia64/include/asm/atomic.h b/arch/ia64/include/asm/atomic.h index 762eeb0fcc1d..2524fb60fbc2 100644 --- a/arch/ia64/include/asm/atomic.h +++ b/arch/ia64/include/asm/atomic.h @@ -66,38 +66,35 @@ ATOMIC_OPS(add, +) ATOMIC_OPS(sub, -) #ifdef __OPTIMIZE__ -#define __ia64_atomic_const(i) __builtin_constant_p(i) ? \ +#define __ia64_atomic_const(i) \ + static const int __ia64_atomic_p = __builtin_constant_p(i) ? \ ((i) == 1 || (i) == 4 || (i) == 8 || (i) == 16 || \ - (i) == -1 || (i) == -4 || (i) == -8 || (i) == -16) : 0 + (i) == -1 || (i) == -4 || (i) == -8 || (i) == -16) : 0;\ + __ia64_atomic_p +#else +#define __ia64_atomic_const(i) 0 +#endif -#define atomic_add_return(i, v) \ +#define atomic_add_return(i,v) \ ({ \ - int __i = (i); \ - static const int __ia64_atomic_p = __ia64_atomic_const(i); \ - __ia64_atomic_p ? ia64_fetch_and_add(__i, &(v)->counter) : \ - ia64_atomic_add(__i, v); \ + int __ia64_aar_i = (i); \ + __ia64_atomic_const(i) \ + ? ia64_fetch_and_add(__ia64_aar_i, &(v)->counter) \ + : ia64_atomic_add(__ia64_aar_i, v); \ }) -#define atomic_sub_return(i, v) \ +#define atomic_sub_return(i,v) \ ({ \ - int __i = (i); \ - static const int __ia64_atomic_p = __ia64_atomic_const(i); \ - __ia64_atomic_p ? ia64_fetch_and_add(-__i, &(v)->counter) : \ - ia64_atomic_sub(__i, v); \ + int __ia64_asr_i = (i); \ + __ia64_atomic_const(i) \ + ? ia64_fetch_and_add(-__ia64_asr_i, &(v)->counter) \ + : ia64_atomic_sub(__ia64_asr_i, v); \ }) -#else -#define atomic_add_return(i, v) ia64_atomic_add(i, v) -#define atomic_sub_return(i, v) ia64_atomic_sub(i, v) -#endif #define atomic_fetch_add(i,v) \ ({ \ int __ia64_aar_i = (i); \ - (__builtin_constant_p(i) \ - && ( (__ia64_aar_i == 1) || (__ia64_aar_i == 4) \ - || (__ia64_aar_i == 8) || (__ia64_aar_i == 16) \ - || (__ia64_aar_i == -1) || (__ia64_aar_i == -4) \ - || (__ia64_aar_i == -8) || (__ia64_aar_i == -16))) \ + __ia64_atomic_const(i) \ ? ia64_fetchadd(__ia64_aar_i, &(v)->counter, acq) \ : ia64_atomic_fetch_add(__ia64_aar_i, v); \ }) @@ -105,11 +102,7 @@ ATOMIC_OPS(sub, -) #define atomic_fetch_sub(i,v) \ ({ \ int __ia64_asr_i = (i); \ - (__builtin_constant_p(i) \ - && ( (__ia64_asr_i == 1) || (__ia64_asr_i == 4) \ - || (__ia64_asr_i == 8) || (__ia64_asr_i == 16) \ - || (__ia64_asr_i == -1) || (__ia64_asr_i == -4) \ - || (__ia64_asr_i == -8) || (__ia64_asr_i == -16))) \ + __ia64_atomic_const(i) \ ? ia64_fetchadd(-__ia64_asr_i, &(v)->counter, acq) \ : ia64_atomic_fetch_sub(__ia64_asr_i, v); \ }) @@ -170,11 +163,7 @@ ATOMIC64_OPS(sub, -) #define atomic64_add_return(i,v) \ ({ \ long __ia64_aar_i = (i); \ - (__builtin_constant_p(i) \ - && ( (__ia64_aar_i == 1) || (__ia64_aar_i == 4) \ - || (__ia64_aar_i == 8) || (__ia64_aar_i == 16) \ - || (__ia64_aar_i == -1) || (__ia64_aar_i == -4) \ - || (__ia64_aar_i == -8) || (__ia64_aar_i == -16))) \ + __ia64_atomic_const(i) \ ? ia64_fetch_and_add(__ia64_aar_i, &(v)->counter) \ : ia64_atomic64_add(__ia64_aar_i, v); \ }) @@ -182,11 +171,7 @@ ATOMIC64_OPS(sub, -) #define atomic64_sub_return(i,v) \ ({ \ long __ia64_asr_i = (i); \ - (__builtin_constant_p(i) \ - && ( (__ia64_asr_i == 1) || (__ia64_asr_i == 4) \ - || (__ia64_asr_i == 8) || (__ia64_asr_i == 16) \ - || (__ia64_asr_i == -1) || (__ia64_asr_i == -4) \ - || (__ia64_asr_i == -8) || (__ia64_asr_i == -16))) \ + __ia64_atomic_const(i) \ ? ia64_fetch_and_add(-__ia64_asr_i, &(v)->counter) \ : ia64_atomic64_sub(__ia64_asr_i, v); \ }) @@ -194,11 +179,7 @@ ATOMIC64_OPS(sub, -) #define atomic64_fetch_add(i,v) \ ({ \ long __ia64_aar_i = (i); \ - (__builtin_constant_p(i) \ - && ( (__ia64_aar_i == 1) || (__ia64_aar_i == 4) \ - || (__ia64_aar_i == 8) || (__ia64_aar_i == 16) \ - || (__ia64_aar_i == -1) || (__ia64_aar_i == -4) \ - || (__ia64_aar_i == -8) || (__ia64_aar_i == -16))) \ + __ia64_atomic_const(i) \ ? ia64_fetchadd(__ia64_aar_i, &(v)->counter, acq) \ : ia64_atomic64_fetch_add(__ia64_aar_i, v); \ }) @@ -206,11 +187,7 @@ ATOMIC64_OPS(sub, -) #define atomic64_fetch_sub(i,v) \ ({ \ long __ia64_asr_i = (i); \ - (__builtin_constant_p(i) \ - && ( (__ia64_asr_i == 1) || (__ia64_asr_i == 4) \ - || (__ia64_asr_i == 8) || (__ia64_asr_i == 16) \ - || (__ia64_asr_i == -1) || (__ia64_asr_i == -4) \ - || (__ia64_asr_i == -8) || (__ia64_asr_i == -16))) \ + __ia64_atomic_const(i) \ ? ia64_fetchadd(-__ia64_asr_i, &(v)->counter, acq) \ : ia64_atomic64_fetch_sub(__ia64_asr_i, v); \ }) -- cgit v1.2.3-55-g7522 From 69c907022a7d9325cdc5c9dd064571e445df9a47 Mon Sep 17 00:00:00 2001 From: Davidlohr Bueso Date: Mon, 22 Jan 2018 09:21:37 -0800 Subject: ia64/err-inject: Use get_user_pages_fast() At the point of sysfs callback, the call to gup is done without mmap_sem (or any lock for that matter). This is racy. As such, use the get_user_pages_fast() alternative and safely avoid taking the lock, if possible. Signed-off-by: Davidlohr Bueso Signed-off-by: Tony Luck --- arch/ia64/kernel/err_inject.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/ia64/kernel/err_inject.c b/arch/ia64/kernel/err_inject.c index 85bba43e7d5d..658a8e06a69b 100644 --- a/arch/ia64/kernel/err_inject.c +++ b/arch/ia64/kernel/err_inject.c @@ -142,7 +142,7 @@ store_virtual_to_phys(struct device *dev, struct device_attribute *attr, u64 virt_addr=simple_strtoull(buf, NULL, 16); int ret; - ret = get_user_pages(virt_addr, 1, FOLL_WRITE, NULL, NULL); + ret = get_user_pages_fast(virt_addr, 1, FOLL_WRITE, NULL); if (ret<=0) { #ifdef ERR_INJ_DEBUG printk("Virtual address %lx is not existing.\n",virt_addr); -- cgit v1.2.3-55-g7522 From 48e362dd96f37d819042f848888b2c6407e01e6d Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Fri, 2 Mar 2018 09:10:30 +0000 Subject: ia64/err-inject: fix spelling mistake: "capapbilities" -> "capabilities" Trivial fix to spelling mistake in debug message text. Signed-off-by: Colin Ian King Signed-off-by: Tony Luck --- arch/ia64/kernel/err_inject.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/ia64/kernel/err_inject.c b/arch/ia64/kernel/err_inject.c index 658a8e06a69b..8b5b8e6bc9d9 100644 --- a/arch/ia64/kernel/err_inject.c +++ b/arch/ia64/kernel/err_inject.c @@ -117,7 +117,7 @@ store_call_start(struct device *dev, struct device_attribute *attr, #ifdef ERR_INJ_DEBUG printk(KERN_DEBUG "Returns: status=%d,\n", (int)status[cpu]); - printk(KERN_DEBUG "capapbilities=%lx,\n", capabilities[cpu]); + printk(KERN_DEBUG "capabilities=%lx,\n", capabilities[cpu]); printk(KERN_DEBUG "resources=%lx\n", resources[cpu]); #endif return size; -- cgit v1.2.3-55-g7522 From 06a3f0c9f2725f5d7c63c4203839373c9bd00c28 Mon Sep 17 00:00:00 2001 From: Justin Chen Date: Wed, 27 Sep 2017 17:15:15 -0700 Subject: MIPS: BMIPS: Do not mask IPIs during suspend Commit a3e6c1eff548 ("MIPS: IRQ: Fix disable_irq on CPU IRQs") fixes an issue where disable_irq did not actually disable the irq. The bug caused our IPIs to not be disabled, which actually is the correct behavior. With the addition of commit a3e6c1eff548 ("MIPS: IRQ: Fix disable_irq on CPU IRQs"), the IPIs were getting disabled going into suspend, thus schedule_ipi() was not being called. This caused deadlocks where schedulable task were not being scheduled and other cpus were waiting for them to do something. Add the IRQF_NO_SUSPEND flag so an irq_disable will not be called on the IPIs during suspend. Signed-off-by: Justin Chen Fixes: a3e6c1eff548 ("MIPS: IRQ: Fix disabled_irq on CPU IRQs") Cc: Florian Fainelli Cc: linux-mips@linux-mips.org Cc: stable@vger.kernel.org Patchwork: https://patchwork.linux-mips.org/patch/17385/ [jhogan@kernel.org: checkpatch: wrap long lines and fix commit refs] Signed-off-by: James Hogan --- arch/mips/kernel/smp-bmips.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'arch') diff --git a/arch/mips/kernel/smp-bmips.c b/arch/mips/kernel/smp-bmips.c index 9d41732a9146..159e83add4bb 100644 --- a/arch/mips/kernel/smp-bmips.c +++ b/arch/mips/kernel/smp-bmips.c @@ -168,11 +168,11 @@ static void bmips_prepare_cpus(unsigned int max_cpus) return; } - if (request_irq(IPI0_IRQ, bmips_ipi_interrupt, IRQF_PERCPU, - "smp_ipi0", NULL)) + if (request_irq(IPI0_IRQ, bmips_ipi_interrupt, + IRQF_PERCPU | IRQF_NO_SUSPEND, "smp_ipi0", NULL)) panic("Can't request IPI0 interrupt"); - if (request_irq(IPI1_IRQ, bmips_ipi_interrupt, IRQF_PERCPU, - "smp_ipi1", NULL)) + if (request_irq(IPI1_IRQ, bmips_ipi_interrupt, + IRQF_PERCPU | IRQF_NO_SUSPEND, "smp_ipi1", NULL)) panic("Can't request IPI1 interrupt"); } -- cgit v1.2.3-55-g7522 From f6a015498dcaee72f80283cb7873d88deb07129c Mon Sep 17 00:00:00 2001 From: Eric W. Biederman Date: Tue, 6 Mar 2018 00:29:17 -0600 Subject: signal/x86: Include the field offsets in the build time checks Due to an oversight when refactoring siginfo_t si_pkey has been in the wrong position since 4.16-rc1. Add an explicit check of the offset of every user space field in siginfo_t and compat_siginfo_t to make a mistake like this hard to make in the future. I have run this code on 4.15 and 4.16-rc1 with the position of si_pkey fixed and all of the fields show up in the same location. Signed-off-by: "Eric W. Biederman" --- arch/x86/kernel/signal_compat.c | 65 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 65 insertions(+) (limited to 'arch') diff --git a/arch/x86/kernel/signal_compat.c b/arch/x86/kernel/signal_compat.c index ac057f9b0763..0d930d8987cc 100644 --- a/arch/x86/kernel/signal_compat.c +++ b/arch/x86/kernel/signal_compat.c @@ -43,6 +43,13 @@ static inline void signal_compat_build_tests(void) BUILD_BUG_ON(offsetof(compat_siginfo_t, _sifields) != 3 * sizeof(int)); #define CHECK_CSI_OFFSET(name) BUILD_BUG_ON(_sifields_offset != offsetof(compat_siginfo_t, _sifields.name)) + BUILD_BUG_ON(offsetof(siginfo_t, si_signo) != 0); + BUILD_BUG_ON(offsetof(siginfo_t, si_errno) != 4); + BUILD_BUG_ON(offsetof(siginfo_t, si_code) != 8); + + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_signo) != 0); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_errno) != 4); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_code) != 8); /* * Ensure that the size of each si_field never changes. * If it does, it is a sign that the @@ -63,36 +70,94 @@ static inline void signal_compat_build_tests(void) CHECK_CSI_SIZE (_kill, 2*sizeof(int)); CHECK_SI_SIZE (_kill, 2*sizeof(int)); + BUILD_BUG_ON(offsetof(siginfo_t, si_pid) != 0x10); + BUILD_BUG_ON(offsetof(siginfo_t, si_uid) != 0x14); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_pid) != 0xC); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_uid) != 0x10); + CHECK_CSI_OFFSET(_timer); CHECK_CSI_SIZE (_timer, 3*sizeof(int)); CHECK_SI_SIZE (_timer, 6*sizeof(int)); + BUILD_BUG_ON(offsetof(siginfo_t, si_tid) != 0x10); + BUILD_BUG_ON(offsetof(siginfo_t, si_overrun) != 0x14); + BUILD_BUG_ON(offsetof(siginfo_t, si_value) != 0x18); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_tid) != 0x0C); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_overrun) != 0x10); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_value) != 0x14); + CHECK_CSI_OFFSET(_rt); CHECK_CSI_SIZE (_rt, 3*sizeof(int)); CHECK_SI_SIZE (_rt, 4*sizeof(int)); + BUILD_BUG_ON(offsetof(siginfo_t, si_pid) != 0x10); + BUILD_BUG_ON(offsetof(siginfo_t, si_uid) != 0x14); + BUILD_BUG_ON(offsetof(siginfo_t, si_value) != 0x18); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_pid) != 0x0C); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_uid) != 0x10); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_value) != 0x14); + CHECK_CSI_OFFSET(_sigchld); CHECK_CSI_SIZE (_sigchld, 5*sizeof(int)); CHECK_SI_SIZE (_sigchld, 8*sizeof(int)); + BUILD_BUG_ON(offsetof(siginfo_t, si_pid) != 0x10); + BUILD_BUG_ON(offsetof(siginfo_t, si_uid) != 0x14); + BUILD_BUG_ON(offsetof(siginfo_t, si_status) != 0x18); + BUILD_BUG_ON(offsetof(siginfo_t, si_utime) != 0x20); + BUILD_BUG_ON(offsetof(siginfo_t, si_stime) != 0x28); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_pid) != 0x0C); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_uid) != 0x10); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_status) != 0x14); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_utime) != 0x18); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_stime) != 0x1C); + #ifdef CONFIG_X86_X32_ABI CHECK_CSI_OFFSET(_sigchld_x32); CHECK_CSI_SIZE (_sigchld_x32, 7*sizeof(int)); /* no _sigchld_x32 in the generic siginfo_t */ + BUILD_BUG_ON(offsetof(compat_siginfo_t, _sifields._sigchld_x32._utime) != 0x18); + BUILD_BUG_ON(offsetof(compat_siginfo_t, _sifields._sigchld_x32._stime) != 0x20); #endif CHECK_CSI_OFFSET(_sigfault); CHECK_CSI_SIZE (_sigfault, 4*sizeof(int)); CHECK_SI_SIZE (_sigfault, 8*sizeof(int)); + BUILD_BUG_ON(offsetof(siginfo_t, si_addr) != 0x10); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_addr) != 0x0C); + + BUILD_BUG_ON(offsetof(siginfo_t, si_addr_lsb) != 0x18); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_addr_lsb) != 0x10); + + BUILD_BUG_ON(offsetof(siginfo_t, si_lower) != 0x20); + BUILD_BUG_ON(offsetof(siginfo_t, si_upper) != 0x28); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_lower) != 0x14); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_upper) != 0x18); + + BUILD_BUG_ON(offsetof(siginfo_t, si_pkey) != 0x20); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_pkey) != 0x14); + CHECK_CSI_OFFSET(_sigpoll); CHECK_CSI_SIZE (_sigpoll, 2*sizeof(int)); CHECK_SI_SIZE (_sigpoll, 4*sizeof(int)); + BUILD_BUG_ON(offsetof(siginfo_t, si_band) != 0x10); + BUILD_BUG_ON(offsetof(siginfo_t, si_fd) != 0x18); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_band) != 0x0C); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_fd) != 0x10); + CHECK_CSI_OFFSET(_sigsys); CHECK_CSI_SIZE (_sigsys, 3*sizeof(int)); CHECK_SI_SIZE (_sigsys, 4*sizeof(int)); + BUILD_BUG_ON(offsetof(siginfo_t, si_call_addr) != 0x10); + BUILD_BUG_ON(offsetof(siginfo_t, si_syscall) != 0x18); + BUILD_BUG_ON(offsetof(siginfo_t, si_arch) != 0x1C); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_call_addr) != 0x0C); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_syscall) != 0x10); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_arch) != 0x14); + /* any new si_fields should be added here */ } -- cgit v1.2.3-55-g7522 From d3f468963cd6fd6d2aa5e26aed8b24232096d0e1 Mon Sep 17 00:00:00 2001 From: Christian Borntraeger Date: Mon, 5 Mar 2018 19:18:47 +0000 Subject: s390/entry.S: fix spurious zeroing of r0 when a system call is interrupted we might call the critical section cleanup handler that re-does some of the operations. When we are between .Lsysc_vtime and .Lsysc_do_svc we might also redo the saving of the problem state registers r0-r7: .Lcleanup_system_call: [...] 0: # update accounting time stamp mvc __LC_LAST_UPDATE_TIMER(8),__LC_SYNC_ENTER_TIMER # set up saved register r11 lg %r15,__LC_KERNEL_STACK la %r9,STACK_FRAME_OVERHEAD(%r15) stg %r9,24(%r11) # r11 pt_regs pointer # fill pt_regs mvc __PT_R8(64,%r9),__LC_SAVE_AREA_SYNC ---> stmg %r0,%r7,__PT_R0(%r9) The problem is now, that we might have already zeroed out r0. The fix is to move the zeroing of r0 after sysc_do_svc. Reported-by: Farhan Ali Fixes: 7041d28115e91 ("s390: scrub registers on kernel entry and KVM exit") Signed-off-by: Christian Borntraeger Signed-off-by: Martin Schwidefsky --- arch/s390/kernel/entry.S | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch') diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S index 73492461c454..a5621ea6d123 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -427,13 +427,13 @@ ENTRY(system_call) UPDATE_VTIME %r8,%r9,__LC_SYNC_ENTER_TIMER BPENTER __TI_flags(%r12),_TIF_ISOLATE_BP stmg %r0,%r7,__PT_R0(%r11) - # clear user controlled register to prevent speculative use - xgr %r0,%r0 mvc __PT_R8(64,%r11),__LC_SAVE_AREA_SYNC mvc __PT_PSW(16,%r11),__LC_SVC_OLD_PSW mvc __PT_INT_CODE(4,%r11),__LC_SVC_ILC stg %r14,__PT_FLAGS(%r11) .Lsysc_do_svc: + # clear user controlled register to prevent speculative use + xgr %r0,%r0 # load address of system call table lg %r10,__THREAD_sysc_table(%r13,%r12) llgh %r8,__PT_INT_CODE+2(%r11) -- cgit v1.2.3-55-g7522 From b0c41b8b6e43120d7c35e4709508a3d90a09646e Mon Sep 17 00:00:00 2001 From: Bharata B Rao Date: Tue, 6 Mar 2018 13:44:32 +0530 Subject: powerpc/pseries: Fix vector5 in ibm architecture vector table With ibm,dynamic-memory-v2 and ibm,drc-info coming around the same time, byte22 in vector5 of ibm architecture vector table got set twice separately. The end result is that guest kernel isn't advertising support for ibm,dynamic-memory-v2. Fix this by removing the duplicate assignment of byte22. Fixes: 02ef6dd8109b ("powerpc: Enable support for ibm,drc-info devtree property") Signed-off-by: Bharata B Rao Signed-off-by: Michael Ellerman --- arch/powerpc/kernel/prom_init.c | 1 - 1 file changed, 1 deletion(-) (limited to 'arch') diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index d22c41c26bb3..acf4b2e0530c 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -874,7 +874,6 @@ struct ibm_arch_vec __cacheline_aligned ibm_architecture_vec = { .mmu = 0, .hash_ext = 0, .radix_ext = 0, - .byte22 = 0, }, /* option vector 6: IBM PAPR hints */ -- cgit v1.2.3-55-g7522 From f07afa0462b76a5b9c4f3a43d5ac24fdb86a90c2 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Tue, 6 Mar 2018 14:27:58 +0100 Subject: KVM: s390: fix memory overwrites when not using SCA entries Even if we don't have extended SCA support, we can have more than 64 CPUs if we don't enable any HW features that might use the SCA entries. Now, this works just fine, but we missed a return, which is why we would actually store the SCA entries. If we have more than 64 CPUs, this means writing outside of the basic SCA - bad. Let's fix this. This allows > 64 CPUs when running nested (under vSIE) without random crashes. Fixes: a6940674c384 ("KVM: s390: allow 255 VCPUs when sca entries aren't used") Reported-by: Christian Borntraeger Tested-by: Christian Borntraeger Signed-off-by: David Hildenbrand Message-Id: <20180306132758.21034-1-david@redhat.com> Cc: stable@vger.kernel.org Reviewed-by: Cornelia Huck Signed-off-by: Christian Borntraeger --- arch/s390/kvm/kvm-s390.c | 1 + 1 file changed, 1 insertion(+) (limited to 'arch') diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index df19f158347e..339ac0964590 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -2147,6 +2147,7 @@ static void sca_add_vcpu(struct kvm_vcpu *vcpu) /* we still need the basic sca for the ipte control */ vcpu->arch.sie_block->scaoh = (__u32)(((__u64)sca) >> 32); vcpu->arch.sie_block->scaol = (__u32)(__u64)sca; + return; } read_lock(&vcpu->kvm->arch.sca_lock); if (vcpu->kvm->arch.use_esca) { -- cgit v1.2.3-55-g7522 From b411991e0ca880d8e7f5eb117c05de6f4b47a2c7 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Tue, 6 Mar 2018 22:18:03 +0100 Subject: x86/syscalls/32: Simplify $entry == $compat entries If the compat entry point is equivalent to the native entry point, it does not need to be specified explicitly. Signed-off-by: Dominik Brodowski Acked-by: Linus Torvalds Acked-by: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Josh Poimboeuf Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: luto@amacapital.net Cc: viro@zeniv.linux.org.uk Signed-off-by: Ingo Molnar --- arch/x86/entry/syscalls/syscall_32.tbl | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'arch') diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl index 448ac2161112..ad5e95a369e4 100644 --- a/arch/x86/entry/syscalls/syscall_32.tbl +++ b/arch/x86/entry/syscalls/syscall_32.tbl @@ -8,7 +8,7 @@ # 0 i386 restart_syscall sys_restart_syscall 1 i386 exit sys_exit -2 i386 fork sys_fork sys_fork +2 i386 fork sys_fork 3 i386 read sys_read 4 i386 write sys_write 5 i386 open sys_open compat_sys_open @@ -78,7 +78,7 @@ 69 i386 ssetmask sys_ssetmask 70 i386 setreuid sys_setreuid16 71 i386 setregid sys_setregid16 -72 i386 sigsuspend sys_sigsuspend sys_sigsuspend +72 i386 sigsuspend sys_sigsuspend 73 i386 sigpending sys_sigpending compat_sys_sigpending 74 i386 sethostname sys_sethostname 75 i386 setrlimit sys_setrlimit compat_sys_setrlimit @@ -196,7 +196,7 @@ 187 i386 sendfile sys_sendfile compat_sys_sendfile 188 i386 getpmsg 189 i386 putpmsg -190 i386 vfork sys_vfork sys_vfork +190 i386 vfork sys_vfork 191 i386 ugetrlimit sys_getrlimit compat_sys_getrlimit 192 i386 mmap2 sys_mmap_pgoff 193 i386 truncate64 sys_truncate64 sys32_truncate64 -- cgit v1.2.3-55-g7522 From a41e2ab08ed62fffc81f71a9bc9c642495a52308 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Tue, 6 Mar 2018 22:18:04 +0100 Subject: x86/entry: Remove stale syscall prototype sys32_vm86_warning() is long gone. Signed-off-by: Dominik Brodowski Acked-by: Linus Torvalds Acked-by: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Josh Poimboeuf Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: luto@amacapital.net Cc: viro@zeniv.linux.org.uk Signed-off-by: Ingo Molnar --- arch/x86/include/asm/sys_ia32.h | 1 - 1 file changed, 1 deletion(-) (limited to 'arch') diff --git a/arch/x86/include/asm/sys_ia32.h b/arch/x86/include/asm/sys_ia32.h index 82c34ee25a65..43d59cae9eb1 100644 --- a/arch/x86/include/asm/sys_ia32.h +++ b/arch/x86/include/asm/sys_ia32.h @@ -37,7 +37,6 @@ asmlinkage long sys32_pread(unsigned int, char __user *, u32, u32, u32); asmlinkage long sys32_pwrite(unsigned int, const char __user *, u32, u32, u32); long sys32_fadvise64_64(int, __u32, __u32, __u32, __u32, int); -long sys32_vm86_warning(void); asmlinkage ssize_t sys32_readahead(int, unsigned, unsigned, size_t); asmlinkage long sys32_sync_file_range(int, unsigned, unsigned, -- cgit v1.2.3-55-g7522 From 7c2178c1ff482679fb0ca0b628f720a888814548 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Tue, 6 Mar 2018 22:18:05 +0100 Subject: x86/syscalls: Use proper syscall definition for sys_ioperm() Using SYSCALL_DEFINEx() is recommended, so use it also here. Signed-off-by: Dominik Brodowski Acked-by: Linus Torvalds Acked-by: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Josh Poimboeuf Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: luto@amacapital.net Cc: viro@zeniv.linux.org.uk Signed-off-by: Ingo Molnar --- arch/x86/kernel/ioport.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/x86/kernel/ioport.c b/arch/x86/kernel/ioport.c index 2f723301eb58..38deafebb21b 100644 --- a/arch/x86/kernel/ioport.c +++ b/arch/x86/kernel/ioport.c @@ -23,7 +23,7 @@ /* * this changes the io permissions bitmap in the current task. */ -asmlinkage long sys_ioperm(unsigned long from, unsigned long num, int turn_on) +SYSCALL_DEFINE3(ioperm, unsigned long, from, unsigned long, num, int, turn_on) { struct thread_struct *t = ¤t->thread; struct tss_struct *tss; -- cgit v1.2.3-55-g7522 From 4ddb45db30851b2269101ee8969f079b028dd257 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Tue, 6 Mar 2018 22:18:07 +0100 Subject: x86/syscalls: Use COMPAT_SYSCALL_DEFINEx() macros for x86-only compat syscalls While at it, convert declarations of type "unsigned" to "unsigned int". Signed-off-by: Dominik Brodowski Acked-by: Linus Torvalds Acked-by: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Josh Poimboeuf Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: luto@amacapital.net Cc: viro@zeniv.linux.org.uk Signed-off-by: Ingo Molnar --- arch/x86/entry/syscalls/syscall_32.tbl | 30 ++++++++-------- arch/x86/ia32/sys_ia32.c | 63 ++++++++++++++++++---------------- arch/x86/include/asm/sys_ia32.h | 45 +++++++++++++++--------- 3 files changed, 76 insertions(+), 62 deletions(-) (limited to 'arch') diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl index ad5e95a369e4..e7fd0a76bf99 100644 --- a/arch/x86/entry/syscalls/syscall_32.tbl +++ b/arch/x86/entry/syscalls/syscall_32.tbl @@ -13,7 +13,7 @@ 4 i386 write sys_write 5 i386 open sys_open compat_sys_open 6 i386 close sys_close -7 i386 waitpid sys_waitpid sys32_waitpid +7 i386 waitpid sys_waitpid compat_sys_x86_waitpid 8 i386 creat sys_creat 9 i386 link sys_link 10 i386 unlink sys_unlink @@ -96,7 +96,7 @@ 87 i386 swapon sys_swapon 88 i386 reboot sys_reboot 89 i386 readdir sys_old_readdir compat_sys_old_readdir -90 i386 mmap sys_old_mmap sys32_mmap +90 i386 mmap sys_old_mmap compat_sys_x86_mmap 91 i386 munmap sys_munmap 92 i386 truncate sys_truncate compat_sys_truncate 93 i386 ftruncate sys_ftruncate compat_sys_ftruncate @@ -186,8 +186,8 @@ 177 i386 rt_sigtimedwait sys_rt_sigtimedwait compat_sys_rt_sigtimedwait 178 i386 rt_sigqueueinfo sys_rt_sigqueueinfo compat_sys_rt_sigqueueinfo 179 i386 rt_sigsuspend sys_rt_sigsuspend -180 i386 pread64 sys_pread64 sys32_pread -181 i386 pwrite64 sys_pwrite64 sys32_pwrite +180 i386 pread64 sys_pread64 compat_sys_x86_pread +181 i386 pwrite64 sys_pwrite64 compat_sys_x86_pwrite 182 i386 chown sys_chown16 183 i386 getcwd sys_getcwd 184 i386 capget sys_capget @@ -199,11 +199,11 @@ 190 i386 vfork sys_vfork 191 i386 ugetrlimit sys_getrlimit compat_sys_getrlimit 192 i386 mmap2 sys_mmap_pgoff -193 i386 truncate64 sys_truncate64 sys32_truncate64 -194 i386 ftruncate64 sys_ftruncate64 sys32_ftruncate64 -195 i386 stat64 sys_stat64 sys32_stat64 -196 i386 lstat64 sys_lstat64 sys32_lstat64 -197 i386 fstat64 sys_fstat64 sys32_fstat64 +193 i386 truncate64 sys_truncate64 compat_sys_x86_truncate64 +194 i386 ftruncate64 sys_ftruncate64 compat_sys_x86_ftruncate64 +195 i386 stat64 sys_stat64 compat_sys_x86_stat64 +196 i386 lstat64 sys_lstat64 compat_sys_x86_lstat64 +197 i386 fstat64 sys_fstat64 compat_sys_x86_fstat64 198 i386 lchown32 sys_lchown 199 i386 getuid32 sys_getuid 200 i386 getgid32 sys_getgid @@ -231,7 +231,7 @@ # 222 is unused # 223 is unused 224 i386 gettid sys_gettid -225 i386 readahead sys_readahead sys32_readahead +225 i386 readahead sys_readahead compat_sys_x86_readahead 226 i386 setxattr sys_setxattr 227 i386 lsetxattr sys_lsetxattr 228 i386 fsetxattr sys_fsetxattr @@ -256,7 +256,7 @@ 247 i386 io_getevents sys_io_getevents compat_sys_io_getevents 248 i386 io_submit sys_io_submit compat_sys_io_submit 249 i386 io_cancel sys_io_cancel -250 i386 fadvise64 sys_fadvise64 sys32_fadvise64 +250 i386 fadvise64 sys_fadvise64 compat_sys_x86_fadvise64 # 251 is available for reuse (was briefly sys_set_zone_reclaim) 252 i386 exit_group sys_exit_group 253 i386 lookup_dcookie sys_lookup_dcookie compat_sys_lookup_dcookie @@ -278,7 +278,7 @@ 269 i386 fstatfs64 sys_fstatfs64 compat_sys_fstatfs64 270 i386 tgkill sys_tgkill 271 i386 utimes sys_utimes compat_sys_utimes -272 i386 fadvise64_64 sys_fadvise64_64 sys32_fadvise64_64 +272 i386 fadvise64_64 sys_fadvise64_64 compat_sys_x86_fadvise64_64 273 i386 vserver 274 i386 mbind sys_mbind 275 i386 get_mempolicy sys_get_mempolicy compat_sys_get_mempolicy @@ -306,7 +306,7 @@ 297 i386 mknodat sys_mknodat 298 i386 fchownat sys_fchownat 299 i386 futimesat sys_futimesat compat_sys_futimesat -300 i386 fstatat64 sys_fstatat64 sys32_fstatat +300 i386 fstatat64 sys_fstatat64 compat_sys_x86_fstatat 301 i386 unlinkat sys_unlinkat 302 i386 renameat sys_renameat 303 i386 linkat sys_linkat @@ -320,7 +320,7 @@ 311 i386 set_robust_list sys_set_robust_list compat_sys_set_robust_list 312 i386 get_robust_list sys_get_robust_list compat_sys_get_robust_list 313 i386 splice sys_splice -314 i386 sync_file_range sys_sync_file_range sys32_sync_file_range +314 i386 sync_file_range sys_sync_file_range compat_sys_x86_sync_file_range 315 i386 tee sys_tee 316 i386 vmsplice sys_vmsplice compat_sys_vmsplice 317 i386 move_pages sys_move_pages compat_sys_move_pages @@ -330,7 +330,7 @@ 321 i386 signalfd sys_signalfd compat_sys_signalfd 322 i386 timerfd_create sys_timerfd_create 323 i386 eventfd sys_eventfd -324 i386 fallocate sys_fallocate sys32_fallocate +324 i386 fallocate sys_fallocate compat_sys_x86_fallocate 325 i386 timerfd_settime sys_timerfd_settime compat_sys_timerfd_settime 326 i386 timerfd_gettime sys_timerfd_gettime compat_sys_timerfd_gettime 327 i386 signalfd4 sys_signalfd4 compat_sys_signalfd4 diff --git a/arch/x86/ia32/sys_ia32.c b/arch/x86/ia32/sys_ia32.c index 96cd33bbfc85..3bc03446ec44 100644 --- a/arch/x86/ia32/sys_ia32.c +++ b/arch/x86/ia32/sys_ia32.c @@ -51,15 +51,14 @@ #define AA(__x) ((unsigned long)(__x)) -asmlinkage long sys32_truncate64(const char __user *filename, - unsigned long offset_low, - unsigned long offset_high) +COMPAT_SYSCALL_DEFINE3(x86_truncate64, const char __user *, filename, + unsigned long, offset_low, unsigned long, offset_high) { return sys_truncate(filename, ((loff_t) offset_high << 32) | offset_low); } -asmlinkage long sys32_ftruncate64(unsigned int fd, unsigned long offset_low, - unsigned long offset_high) +COMPAT_SYSCALL_DEFINE3(x86_ftruncate64, unsigned int, fd, + unsigned long, offset_low, unsigned long, offset_high) { return sys_ftruncate(fd, ((loff_t) offset_high << 32) | offset_low); } @@ -96,8 +95,8 @@ static int cp_stat64(struct stat64 __user *ubuf, struct kstat *stat) return 0; } -asmlinkage long sys32_stat64(const char __user *filename, - struct stat64 __user *statbuf) +COMPAT_SYSCALL_DEFINE2(x86_stat64, const char __user *, filename, + struct stat64 __user *, statbuf) { struct kstat stat; int ret = vfs_stat(filename, &stat); @@ -107,8 +106,8 @@ asmlinkage long sys32_stat64(const char __user *filename, return ret; } -asmlinkage long sys32_lstat64(const char __user *filename, - struct stat64 __user *statbuf) +COMPAT_SYSCALL_DEFINE2(x86_lstat64, const char __user *, filename, + struct stat64 __user *, statbuf) { struct kstat stat; int ret = vfs_lstat(filename, &stat); @@ -117,7 +116,8 @@ asmlinkage long sys32_lstat64(const char __user *filename, return ret; } -asmlinkage long sys32_fstat64(unsigned int fd, struct stat64 __user *statbuf) +COMPAT_SYSCALL_DEFINE2(x86_fstat64, unsigned int, fd, + struct stat64 __user *, statbuf) { struct kstat stat; int ret = vfs_fstat(fd, &stat); @@ -126,8 +126,9 @@ asmlinkage long sys32_fstat64(unsigned int fd, struct stat64 __user *statbuf) return ret; } -asmlinkage long sys32_fstatat(unsigned int dfd, const char __user *filename, - struct stat64 __user *statbuf, int flag) +COMPAT_SYSCALL_DEFINE4(x86_fstatat, unsigned int, dfd, + const char __user *, filename, + struct stat64 __user *, statbuf, int, flag) { struct kstat stat; int error; @@ -153,7 +154,7 @@ struct mmap_arg_struct32 { unsigned int offset; }; -asmlinkage long sys32_mmap(struct mmap_arg_struct32 __user *arg) +COMPAT_SYSCALL_DEFINE1(x86_mmap, struct mmap_arg_struct32 __user *, arg) { struct mmap_arg_struct32 a; @@ -167,22 +168,22 @@ asmlinkage long sys32_mmap(struct mmap_arg_struct32 __user *arg) a.offset>>PAGE_SHIFT); } -asmlinkage long sys32_waitpid(compat_pid_t pid, unsigned int __user *stat_addr, - int options) +COMPAT_SYSCALL_DEFINE3(x86_waitpid, compat_pid_t, pid, unsigned int __user *, + stat_addr, int, options) { return compat_sys_wait4(pid, stat_addr, options, NULL); } /* warning: next two assume little endian */ -asmlinkage long sys32_pread(unsigned int fd, char __user *ubuf, u32 count, - u32 poslo, u32 poshi) +COMPAT_SYSCALL_DEFINE5(x86_pread, unsigned int, fd, char __user *, ubuf, + u32, count, u32, poslo, u32, poshi) { return sys_pread64(fd, ubuf, count, ((loff_t)AA(poshi) << 32) | AA(poslo)); } -asmlinkage long sys32_pwrite(unsigned int fd, const char __user *ubuf, - u32 count, u32 poslo, u32 poshi) +COMPAT_SYSCALL_DEFINE5(x86_pwrite, unsigned int, fd, const char __user *, ubuf, + u32, count, u32, poslo, u32, poshi) { return sys_pwrite64(fd, ubuf, count, ((loff_t)AA(poshi) << 32) | AA(poslo)); @@ -193,8 +194,9 @@ asmlinkage long sys32_pwrite(unsigned int fd, const char __user *ubuf, * Some system calls that need sign extended arguments. This could be * done by a generic wrapper. */ -long sys32_fadvise64_64(int fd, __u32 offset_low, __u32 offset_high, - __u32 len_low, __u32 len_high, int advice) +COMPAT_SYSCALL_DEFINE6(x86_fadvise64_64, int, fd, __u32, offset_low, + __u32, offset_high, __u32, len_low, __u32, len_high, + int, advice) { return sys_fadvise64_64(fd, (((u64)offset_high)<<32) | offset_low, @@ -202,30 +204,31 @@ long sys32_fadvise64_64(int fd, __u32 offset_low, __u32 offset_high, advice); } -asmlinkage ssize_t sys32_readahead(int fd, unsigned off_lo, unsigned off_hi, - size_t count) +COMPAT_SYSCALL_DEFINE4(x86_readahead, int, fd, unsigned int, off_lo, + unsigned int, off_hi, size_t, count) { return sys_readahead(fd, ((u64)off_hi << 32) | off_lo, count); } -asmlinkage long sys32_sync_file_range(int fd, unsigned off_low, unsigned off_hi, - unsigned n_low, unsigned n_hi, int flags) +COMPAT_SYSCALL_DEFINE6(x86_sync_file_range, int, fd, unsigned int, off_low, + unsigned int, off_hi, unsigned int, n_low, + unsigned int, n_hi, int, flags) { return sys_sync_file_range(fd, ((u64)off_hi << 32) | off_low, ((u64)n_hi << 32) | n_low, flags); } -asmlinkage long sys32_fadvise64(int fd, unsigned offset_lo, unsigned offset_hi, - size_t len, int advice) +COMPAT_SYSCALL_DEFINE5(x86_fadvise64, int, fd, unsigned int, offset_lo, + unsigned int, offset_hi, size_t, len, int, advice) { return sys_fadvise64_64(fd, ((u64)offset_hi << 32) | offset_lo, len, advice); } -asmlinkage long sys32_fallocate(int fd, int mode, unsigned offset_lo, - unsigned offset_hi, unsigned len_lo, - unsigned len_hi) +COMPAT_SYSCALL_DEFINE6(x86_fallocate, int, fd, int, mode, + unsigned int, offset_lo, unsigned int, offset_hi, + unsigned int, len_lo, unsigned int, len_hi) { return sys_fallocate(fd, mode, ((u64)offset_hi << 32) | offset_lo, ((u64)len_hi << 32) | len_lo); diff --git a/arch/x86/include/asm/sys_ia32.h b/arch/x86/include/asm/sys_ia32.h index 43d59cae9eb1..32831905d97a 100644 --- a/arch/x86/include/asm/sys_ia32.h +++ b/arch/x86/include/asm/sys_ia32.h @@ -20,30 +20,41 @@ #include /* ia32/sys_ia32.c */ -asmlinkage long sys32_truncate64(const char __user *, unsigned long, unsigned long); -asmlinkage long sys32_ftruncate64(unsigned int, unsigned long, unsigned long); +asmlinkage long compat_sys_x86_truncate64(const char __user *, unsigned long, + unsigned long); +asmlinkage long compat_sys_x86_ftruncate64(unsigned int, unsigned long, + unsigned long); -asmlinkage long sys32_stat64(const char __user *, struct stat64 __user *); -asmlinkage long sys32_lstat64(const char __user *, struct stat64 __user *); -asmlinkage long sys32_fstat64(unsigned int, struct stat64 __user *); -asmlinkage long sys32_fstatat(unsigned int, const char __user *, +asmlinkage long compat_sys_x86_stat64(const char __user *, + struct stat64 __user *); +asmlinkage long compat_sys_x86_lstat64(const char __user *, + struct stat64 __user *); +asmlinkage long compat_sys_x86_fstat64(unsigned int, struct stat64 __user *); +asmlinkage long compat_sys_x86_fstatat(unsigned int, const char __user *, struct stat64 __user *, int); struct mmap_arg_struct32; -asmlinkage long sys32_mmap(struct mmap_arg_struct32 __user *); +asmlinkage long compat_sys_x86_mmap(struct mmap_arg_struct32 __user *); -asmlinkage long sys32_waitpid(compat_pid_t, unsigned int __user *, int); +asmlinkage long compat_sys_x86_waitpid(compat_pid_t, unsigned int __user *, + int); -asmlinkage long sys32_pread(unsigned int, char __user *, u32, u32, u32); -asmlinkage long sys32_pwrite(unsigned int, const char __user *, u32, u32, u32); +asmlinkage long compat_sys_x86_pread(unsigned int, char __user *, u32, u32, + u32); +asmlinkage long compat_sys_x86_pwrite(unsigned int, const char __user *, u32, + u32, u32); -long sys32_fadvise64_64(int, __u32, __u32, __u32, __u32, int); +asmlinkage long compat_sys_x86_fadvise64_64(int, __u32, __u32, __u32, __u32, + int); -asmlinkage ssize_t sys32_readahead(int, unsigned, unsigned, size_t); -asmlinkage long sys32_sync_file_range(int, unsigned, unsigned, - unsigned, unsigned, int); -asmlinkage long sys32_fadvise64(int, unsigned, unsigned, size_t, int); -asmlinkage long sys32_fallocate(int, int, unsigned, - unsigned, unsigned, unsigned); +asmlinkage ssize_t compat_sys_x86_readahead(int, unsigned int, unsigned int, + size_t); +asmlinkage long compat_sys_x86_sync_file_range(int, unsigned int, unsigned int, + unsigned int, unsigned int, + int); +asmlinkage long compat_sys_x86_fadvise64(int, unsigned int, unsigned int, + size_t, int); +asmlinkage long compat_sys_x86_fallocate(int, int, unsigned int, unsigned int, + unsigned int, unsigned int); /* ia32/ia32_signal.c */ asmlinkage long sys32_sigreturn(void); -- cgit v1.2.3-55-g7522 From af52201d991624d2d5adce2c123805b3d42a8d4d Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Tue, 6 Mar 2018 22:18:08 +0100 Subject: x86/entry: Do not special-case clone(2) in compat entry With the CPU renaming registers on its own, and all the overhead of the syscall entry/exit, it is doubtful whether the compiled output of mov %r8, %rax mov %rcx, %r8 mov %rax, %rcx jmpq sys_clone is measurably slower than the hand-crafted version of xchg %r8, %rcx So get rid of this special case. Signed-off-by: Dominik Brodowski Acked-by: Linus Torvalds Acked-by: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Josh Poimboeuf Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: luto@amacapital.net Cc: viro@zeniv.linux.org.uk Signed-off-by: Ingo Molnar --- arch/x86/entry/entry_64_compat.S | 12 ------------ arch/x86/entry/syscalls/syscall_32.tbl | 2 +- arch/x86/ia32/sys_ia32.c | 11 +++++++++++ arch/x86/include/asm/sys_ia32.h | 2 ++ 4 files changed, 14 insertions(+), 13 deletions(-) (limited to 'arch') diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S index e811dd9c5e99..ff61b7bb750b 100644 --- a/arch/x86/entry/entry_64_compat.S +++ b/arch/x86/entry/entry_64_compat.S @@ -406,15 +406,3 @@ ENTRY(entry_INT80_compat) TRACE_IRQS_ON jmp swapgs_restore_regs_and_return_to_usermode END(entry_INT80_compat) - -ENTRY(stub32_clone) - /* - * The 32-bit clone ABI is: clone(..., int tls_val, int *child_tidptr). - * The 64-bit clone ABI is: clone(..., int *child_tidptr, int tls_val). - * - * The native 64-bit kernel's sys_clone() implements the latter, - * so we need to swap arguments here before calling it: - */ - xchg %r8, %rcx - jmp sys_clone -ENDPROC(stub32_clone) diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl index e7fd0a76bf99..2a5e99cff859 100644 --- a/arch/x86/entry/syscalls/syscall_32.tbl +++ b/arch/x86/entry/syscalls/syscall_32.tbl @@ -126,7 +126,7 @@ 117 i386 ipc sys_ipc compat_sys_ipc 118 i386 fsync sys_fsync 119 i386 sigreturn sys_sigreturn sys32_sigreturn -120 i386 clone sys_clone stub32_clone +120 i386 clone sys_clone compat_sys_x86_clone 121 i386 setdomainname sys_setdomainname 122 i386 uname sys_newuname 123 i386 modify_ldt sys_modify_ldt diff --git a/arch/x86/ia32/sys_ia32.c b/arch/x86/ia32/sys_ia32.c index 3bc03446ec44..6512498bbef6 100644 --- a/arch/x86/ia32/sys_ia32.c +++ b/arch/x86/ia32/sys_ia32.c @@ -233,3 +233,14 @@ COMPAT_SYSCALL_DEFINE6(x86_fallocate, int, fd, int, mode, return sys_fallocate(fd, mode, ((u64)offset_hi << 32) | offset_lo, ((u64)len_hi << 32) | len_lo); } + +/* + * The 32-bit clone ABI is CONFIG_CLONE_BACKWARDS + */ +COMPAT_SYSCALL_DEFINE5(x86_clone, unsigned long, clone_flags, + unsigned long, newsp, int __user *, parent_tidptr, + unsigned long, tls_val, int __user *, child_tidptr) +{ + return sys_clone(clone_flags, newsp, parent_tidptr, child_tidptr, + tls_val); +} diff --git a/arch/x86/include/asm/sys_ia32.h b/arch/x86/include/asm/sys_ia32.h index 32831905d97a..906794aa034e 100644 --- a/arch/x86/include/asm/sys_ia32.h +++ b/arch/x86/include/asm/sys_ia32.h @@ -55,6 +55,8 @@ asmlinkage long compat_sys_x86_fadvise64(int, unsigned int, unsigned int, size_t, int); asmlinkage long compat_sys_x86_fallocate(int, int, unsigned int, unsigned int, unsigned int, unsigned int); +asmlinkage long compat_sys_x86_clone(unsigned long, unsigned long, int __user *, + unsigned long, int __user *); /* ia32/ia32_signal.c */ asmlinkage long sys32_sigreturn(void); -- cgit v1.2.3-55-g7522 From 91c5f0de64a226e0d9c558b26ef7c2655ef31cca Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Tue, 6 Mar 2018 22:18:09 +0100 Subject: x86/entry/64/compat: Save one instruction in entry_INT80_compat() As %rdi is never user except in the following push, there is no need to restore %rdi to the original value. Signed-off-by: Dominik Brodowski Acked-by: Linus Torvalds Acked-by: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Josh Poimboeuf Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: luto@amacapital.net Cc: viro@zeniv.linux.org.uk Signed-off-by: Ingo Molnar --- arch/x86/entry/entry_64_compat.S | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'arch') diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S index ff61b7bb750b..08425c42f8b7 100644 --- a/arch/x86/entry/entry_64_compat.S +++ b/arch/x86/entry/entry_64_compat.S @@ -363,9 +363,7 @@ ENTRY(entry_INT80_compat) pushq 2*8(%rdi) /* regs->ip */ pushq 1*8(%rdi) /* regs->orig_ax */ - movq (%rdi), %rdi /* restore %rdi */ - - pushq %rdi /* pt_regs->di */ + pushq (%rdi) /* pt_regs->di */ pushq %rsi /* pt_regs->si */ pushq %rdx /* pt_regs->dx */ pushq %rcx /* pt_regs->cx */ -- cgit v1.2.3-55-g7522 From 076ca272a14cea558b1092ec85cea08510283f2a Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Wed, 7 Mar 2018 11:12:27 -0800 Subject: x86/vsyscall/64: Drop "native" vsyscalls Since Linux v3.2, vsyscalls have been deprecated and slow. From v3.2 on, Linux had three vsyscall modes: "native", "emulate", and "none". "emulate" is the default. All known user programs work correctly in emulate mode, but vsyscalls turn into page faults and are emulated. This is very slow. In "native" mode, the vsyscall page is easily usable as an exploit gadget, but vsyscalls are a bit faster -- they turn into normal syscalls. (This is in contrast to vDSO functions, which can be much faster than syscalls.) In "none" mode, there are no vsyscalls. For all practical purposes, "native" was really just a chicken bit in case something went wrong with the emulation. It's been over six years, and nothing has gone wrong. Delete it. Signed-off-by: Andy Lutomirski Acked-by: Kees Cook Acked-by: Linus Torvalds Cc: Borislav Petkov Cc: Dominik Brodowski Cc: Kernel Hardening Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/519fee5268faea09ae550776ce969fa6e88668b0.1520449896.git.luto@kernel.org Signed-off-by: Ingo Molnar --- arch/x86/Kconfig | 11 +---------- arch/x86/entry/vsyscall/vsyscall_64.c | 16 +++------------- arch/x86/include/asm/pgtable_types.h | 2 -- tools/testing/selftests/x86/test_vsyscall.c | 11 ++++++----- 4 files changed, 10 insertions(+), 30 deletions(-) (limited to 'arch') diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index c1aed6c0e413..09c599e0900d 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -2266,7 +2266,7 @@ choice it can be used to assist security vulnerability exploitation. This setting can be changed at boot time via the kernel command - line parameter vsyscall=[native|emulate|none]. + line parameter vsyscall=[emulate|none]. On a system with recent enough glibc (2.14 or newer) and no static binaries, you can say None without a performance penalty @@ -2274,15 +2274,6 @@ choice If unsure, select "Emulate". - config LEGACY_VSYSCALL_NATIVE - bool "Native" - help - Actual executable code is located in the fixed vsyscall - address mapping, implementing time() efficiently. Since - this makes the mapping executable, it can be used during - security vulnerability exploitation (traditionally as - ROP gadgets). This configuration is not recommended. - config LEGACY_VSYSCALL_EMULATE bool "Emulate" help diff --git a/arch/x86/entry/vsyscall/vsyscall_64.c b/arch/x86/entry/vsyscall/vsyscall_64.c index 577fa8adb785..8560ef68a9d6 100644 --- a/arch/x86/entry/vsyscall/vsyscall_64.c +++ b/arch/x86/entry/vsyscall/vsyscall_64.c @@ -42,10 +42,8 @@ #define CREATE_TRACE_POINTS #include "vsyscall_trace.h" -static enum { EMULATE, NATIVE, NONE } vsyscall_mode = -#if defined(CONFIG_LEGACY_VSYSCALL_NATIVE) - NATIVE; -#elif defined(CONFIG_LEGACY_VSYSCALL_NONE) +static enum { EMULATE, NONE } vsyscall_mode = +#ifdef CONFIG_LEGACY_VSYSCALL_NONE NONE; #else EMULATE; @@ -56,8 +54,6 @@ static int __init vsyscall_setup(char *str) if (str) { if (!strcmp("emulate", str)) vsyscall_mode = EMULATE; - else if (!strcmp("native", str)) - vsyscall_mode = NATIVE; else if (!strcmp("none", str)) vsyscall_mode = NONE; else @@ -139,10 +135,6 @@ bool emulate_vsyscall(struct pt_regs *regs, unsigned long address) WARN_ON_ONCE(address != regs->ip); - /* This should be unreachable in NATIVE mode. */ - if (WARN_ON(vsyscall_mode == NATIVE)) - return false; - if (vsyscall_mode == NONE) { warn_bad_vsyscall(KERN_INFO, regs, "vsyscall attempted with vsyscall=none"); @@ -370,9 +362,7 @@ void __init map_vsyscall(void) if (vsyscall_mode != NONE) { __set_fixmap(VSYSCALL_PAGE, physaddr_vsyscall, - vsyscall_mode == NATIVE - ? PAGE_KERNEL_VSYSCALL - : PAGE_KERNEL_VVAR); + PAGE_KERNEL_VVAR); set_vsyscall_pgtable_user_bits(swapper_pg_dir); } diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index 246f15b4e64c..acfe755562a6 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -174,7 +174,6 @@ enum page_cache_mode { #define __PAGE_KERNEL_RO (__PAGE_KERNEL & ~_PAGE_RW) #define __PAGE_KERNEL_RX (__PAGE_KERNEL_EXEC & ~_PAGE_RW) #define __PAGE_KERNEL_NOCACHE (__PAGE_KERNEL | _PAGE_NOCACHE) -#define __PAGE_KERNEL_VSYSCALL (__PAGE_KERNEL_RX | _PAGE_USER) #define __PAGE_KERNEL_VVAR (__PAGE_KERNEL_RO | _PAGE_USER) #define __PAGE_KERNEL_LARGE (__PAGE_KERNEL | _PAGE_PSE) #define __PAGE_KERNEL_LARGE_EXEC (__PAGE_KERNEL_EXEC | _PAGE_PSE) @@ -206,7 +205,6 @@ enum page_cache_mode { #define PAGE_KERNEL_NOCACHE __pgprot(__PAGE_KERNEL_NOCACHE | _PAGE_ENC) #define PAGE_KERNEL_LARGE __pgprot(__PAGE_KERNEL_LARGE | _PAGE_ENC) #define PAGE_KERNEL_LARGE_EXEC __pgprot(__PAGE_KERNEL_LARGE_EXEC | _PAGE_ENC) -#define PAGE_KERNEL_VSYSCALL __pgprot(__PAGE_KERNEL_VSYSCALL | _PAGE_ENC) #define PAGE_KERNEL_VVAR __pgprot(__PAGE_KERNEL_VVAR | _PAGE_ENC) #define PAGE_KERNEL_IO __pgprot(__PAGE_KERNEL_IO) diff --git a/tools/testing/selftests/x86/test_vsyscall.c b/tools/testing/selftests/x86/test_vsyscall.c index be81621446f0..0b4f1cc2291c 100644 --- a/tools/testing/selftests/x86/test_vsyscall.c +++ b/tools/testing/selftests/x86/test_vsyscall.c @@ -450,7 +450,7 @@ static void sigtrap(int sig, siginfo_t *info, void *ctx_void) num_vsyscall_traps++; } -static int test_native_vsyscall(void) +static int test_emulation(void) { time_t tmp; bool is_native; @@ -458,7 +458,7 @@ static int test_native_vsyscall(void) if (!vtime) return 0; - printf("[RUN]\tchecking for native vsyscall\n"); + printf("[RUN]\tchecking that vsyscalls are emulated\n"); sethandler(SIGTRAP, sigtrap, 0); set_eflags(get_eflags() | X86_EFLAGS_TF); vtime(&tmp); @@ -474,11 +474,12 @@ static int test_native_vsyscall(void) */ is_native = (num_vsyscall_traps > 1); - printf("\tvsyscalls are %s (%d instructions in vsyscall page)\n", + printf("[%s]\tvsyscalls are %s (%d instructions in vsyscall page)\n", + (is_native ? "FAIL" : "OK"), (is_native ? "native" : "emulated"), (int)num_vsyscall_traps); - return 0; + return is_native; } #endif @@ -498,7 +499,7 @@ int main(int argc, char **argv) nerrs += test_vsys_r(); #ifdef __x86_64__ - nerrs += test_native_vsyscall(); + nerrs += test_emulation(); #endif return nerrs ? 1 : 0; -- cgit v1.2.3-55-g7522 From 36268223c1e9981d6cfc33aff8520b3bde4b8114 Mon Sep 17 00:00:00 2001 From: Konrad Rzeszutek Wilk Date: Mon, 26 Feb 2018 09:35:01 -0500 Subject: x86/spectre_v2: Don't check microcode versions when running under hypervisors As: 1) It's known that hypervisors lie about the environment anyhow (host mismatch) 2) Even if the hypervisor (Xen, KVM, VMWare, etc) provided a valid "correct" value, it all gets to be very murky when migration happens (do you provide the "new" microcode of the machine?). And in reality the cloud vendors are the ones that should make sure that the microcode that is running is correct and we should just sing lalalala and trust them. Signed-off-by: Konrad Rzeszutek Wilk Signed-off-by: Thomas Gleixner Reviewed-by: Paolo Bonzini Cc: Wanpeng Li Cc: kvm Cc: Krčmář Cc: Borislav Petkov CC: "H. Peter Anvin" CC: stable@vger.kernel.org Link: https://lkml.kernel.org/r/20180226213019.GE9497@char.us.oracle.com --- arch/x86/kernel/cpu/intel.c | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'arch') diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index d19e903214b4..4aa9fd379390 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -144,6 +144,13 @@ static bool bad_spectre_microcode(struct cpuinfo_x86 *c) { int i; + /* + * We know that the hypervisor lie to us on the microcode version so + * we may as well hope that it is running the correct version. + */ + if (cpu_has(c, X86_FEATURE_HYPERVISOR)) + return false; + for (i = 0; i < ARRAY_SIZE(spectre_bad_microcodes); i++) { if (c->x86_model == spectre_bad_microcodes[i].model && c->x86_stepping == spectre_bad_microcodes[i].stepping) -- cgit v1.2.3-55-g7522 From 854857f5944c59a881ff607b37ed9ed41d031a3b Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Wed, 28 Feb 2018 11:28:40 +0100 Subject: x86/microcode: Get rid of struct apply_microcode_ctx It is a useless remnant from earlier times. Use the ucode_state enum directly. No functional change. Signed-off-by: Borislav Petkov Signed-off-by: Thomas Gleixner Tested-by: Tom Lendacky Tested-by: Ashok Raj Cc: Arjan Van De Ven Link: https://lkml.kernel.org/r/20180228102846.13447-2-bp@alien8.de --- arch/x86/kernel/cpu/microcode/core.c | 19 ++++++++----------- 1 file changed, 8 insertions(+), 11 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index aa1b9a422f2b..63370651e376 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -373,26 +373,23 @@ static int collect_cpu_info(int cpu) return ret; } -struct apply_microcode_ctx { - enum ucode_state err; -}; - static void apply_microcode_local(void *arg) { - struct apply_microcode_ctx *ctx = arg; + enum ucode_state *err = arg; - ctx->err = microcode_ops->apply_microcode(smp_processor_id()); + *err = microcode_ops->apply_microcode(smp_processor_id()); } static int apply_microcode_on_target(int cpu) { - struct apply_microcode_ctx ctx = { .err = 0 }; + enum ucode_state err; int ret; - ret = smp_call_function_single(cpu, apply_microcode_local, &ctx, 1); - if (!ret) - ret = ctx.err; - + ret = smp_call_function_single(cpu, apply_microcode_local, &err, 1); + if (!ret) { + if (err == UCODE_ERROR) + ret = 1; + } return ret; } -- cgit v1.2.3-55-g7522 From c182d2b7d0ca48e0d6ff16f7d883161238c447ed Mon Sep 17 00:00:00 2001 From: Ashok Raj Date: Wed, 28 Feb 2018 11:28:41 +0100 Subject: x86/microcode/intel: Check microcode revision before updating sibling threads After updating microcode on one of the threads of a core, the other thread sibling automatically gets the update since the microcode resources on a hyperthreaded core are shared between the two threads. Check the microcode revision on the CPU before performing a microcode update and thus save us the WRMSR 0x79 because it is a particularly expensive operation. [ Borislav: Massage changelog and coding style. ] Signed-off-by: Ashok Raj Signed-off-by: Borislav Petkov Signed-off-by: Thomas Gleixner Tested-by: Tom Lendacky Tested-by: Ashok Raj Cc: Arjan Van De Ven Link: http://lkml.kernel.org/r/1519352533-15992-2-git-send-email-ashok.raj@intel.com Link: https://lkml.kernel.org/r/20180228102846.13447-3-bp@alien8.de --- arch/x86/kernel/cpu/microcode/intel.c | 27 ++++++++++++++++++++++++--- 1 file changed, 24 insertions(+), 3 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c index 923054a6b760..87bd6dc94081 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -589,6 +589,17 @@ static int apply_microcode_early(struct ucode_cpu_info *uci, bool early) if (!mc) return 0; + /* + * Save us the MSR write below - which is a particular expensive + * operation - when the other hyperthread has updated the microcode + * already. + */ + rev = intel_get_microcode_revision(); + if (rev >= mc->hdr.rev) { + uci->cpu_sig.rev = rev; + return UCODE_OK; + } + /* write microcode via MSR 0x79 */ native_wrmsrl(MSR_IA32_UCODE_WRITE, (unsigned long)mc->bits); @@ -776,7 +787,7 @@ static enum ucode_state apply_microcode_intel(int cpu) { struct microcode_intel *mc; struct ucode_cpu_info *uci; - struct cpuinfo_x86 *c; + struct cpuinfo_x86 *c = &cpu_data(cpu); static int prev_rev; u32 rev; @@ -793,6 +804,18 @@ static enum ucode_state apply_microcode_intel(int cpu) return UCODE_NFOUND; } + /* + * Save us the MSR write below - which is a particular expensive + * operation - when the other hyperthread has updated the microcode + * already. + */ + rev = intel_get_microcode_revision(); + if (rev >= mc->hdr.rev) { + uci->cpu_sig.rev = rev; + c->microcode = rev; + return UCODE_OK; + } + /* write microcode via MSR 0x79 */ wrmsrl(MSR_IA32_UCODE_WRITE, (unsigned long)mc->bits); @@ -813,8 +836,6 @@ static enum ucode_state apply_microcode_intel(int cpu) prev_rev = rev; } - c = &cpu_data(cpu); - uci->cpu_sig.rev = rev; c->microcode = rev; -- cgit v1.2.3-55-g7522 From 91df9fdf51492aec9fed6b4cbd33160886740f47 Mon Sep 17 00:00:00 2001 From: Ashok Raj Date: Wed, 28 Feb 2018 11:28:42 +0100 Subject: x86/microcode/intel: Writeback and invalidate caches before updating microcode Updating microcode is less error prone when caches have been flushed and depending on what exactly the microcode is updating. For example, some of the issues around certain Broadwell parts can be addressed by doing a full cache flush. [ Borislav: Massage it and use native_wbinvd() in both cases. ] Signed-off-by: Ashok Raj Signed-off-by: Borislav Petkov Signed-off-by: Thomas Gleixner Tested-by: Tom Lendacky Tested-by: Ashok Raj Cc: Arjan Van De Ven Link: http://lkml.kernel.org/r/1519352533-15992-3-git-send-email-ashok.raj@intel.com Link: https://lkml.kernel.org/r/20180228102846.13447-4-bp@alien8.de --- arch/x86/kernel/cpu/microcode/intel.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'arch') diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c index 87bd6dc94081..e2864bc2d575 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -600,6 +600,12 @@ static int apply_microcode_early(struct ucode_cpu_info *uci, bool early) return UCODE_OK; } + /* + * Writeback and invalidate caches before updating microcode to avoid + * internal issues depending on what the microcode is updating. + */ + native_wbinvd(); + /* write microcode via MSR 0x79 */ native_wrmsrl(MSR_IA32_UCODE_WRITE, (unsigned long)mc->bits); @@ -816,6 +822,12 @@ static enum ucode_state apply_microcode_intel(int cpu) return UCODE_OK; } + /* + * Writeback and invalidate caches before updating microcode to avoid + * internal issues depending on what the microcode is updating. + */ + native_wbinvd(); + /* write microcode via MSR 0x79 */ wrmsrl(MSR_IA32_UCODE_WRITE, (unsigned long)mc->bits); -- cgit v1.2.3-55-g7522 From 30ec26da9967d0d785abc24073129a34c3211777 Mon Sep 17 00:00:00 2001 From: Ashok Raj Date: Wed, 28 Feb 2018 11:28:43 +0100 Subject: x86/microcode: Do not upload microcode if CPUs are offline Avoid loading microcode if any of the CPUs are offline, and issue a warning. Having different microcode revisions on the system at any time is outright dangerous. [ Borislav: Massage changelog. ] Signed-off-by: Ashok Raj Signed-off-by: Borislav Petkov Signed-off-by: Thomas Gleixner Tested-by: Tom Lendacky Tested-by: Ashok Raj Reviewed-by: Tom Lendacky Cc: Arjan Van De Ven Link: http://lkml.kernel.org/r/1519352533-15992-4-git-send-email-ashok.raj@intel.com Link: https://lkml.kernel.org/r/20180228102846.13447-5-bp@alien8.de --- arch/x86/kernel/cpu/microcode/core.c | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'arch') diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index 63370651e376..fa32cb3dcca5 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -486,6 +486,16 @@ static void __exit microcode_dev_exit(void) /* fake device for request_firmware */ static struct platform_device *microcode_pdev; +static int check_online_cpus(void) +{ + if (num_online_cpus() == num_present_cpus()) + return 0; + + pr_err("Not all CPUs online, aborting microcode update.\n"); + + return -EINVAL; +} + static enum ucode_state reload_for_cpu(int cpu) { struct ucode_cpu_info *uci = ucode_cpu_info + cpu; @@ -519,7 +529,13 @@ static ssize_t reload_store(struct device *dev, return size; get_online_cpus(); + + ret = check_online_cpus(); + if (ret) + goto put; + mutex_lock(µcode_mutex); + for_each_online_cpu(cpu) { tmp_ret = reload_for_cpu(cpu); if (tmp_ret > UCODE_NFOUND) { @@ -538,6 +554,8 @@ static ssize_t reload_store(struct device *dev, microcode_check(); mutex_unlock(µcode_mutex); + +put: put_online_cpus(); if (!ret) -- cgit v1.2.3-55-g7522 From d8c3b52c00a05036e0a6b315b4b17921a7b67997 Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Wed, 28 Feb 2018 11:28:44 +0100 Subject: x86/microcode/intel: Look into the patch cache first The cache might contain a newer patch - look in there first. A follow-on change will make sure newest patches are loaded into the cache of microcode patches. Signed-off-by: Borislav Petkov Signed-off-by: Thomas Gleixner Tested-by: Tom Lendacky Tested-by: Ashok Raj Cc: Arjan Van De Ven Link: https://lkml.kernel.org/r/20180228102846.13447-6-bp@alien8.de --- arch/x86/kernel/cpu/microcode/intel.c | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c index e2864bc2d575..2aded9db1d42 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -791,9 +791,9 @@ static int collect_cpu_info(int cpu_num, struct cpu_signature *csig) static enum ucode_state apply_microcode_intel(int cpu) { - struct microcode_intel *mc; - struct ucode_cpu_info *uci; + struct ucode_cpu_info *uci = ucode_cpu_info + cpu; struct cpuinfo_x86 *c = &cpu_data(cpu); + struct microcode_intel *mc; static int prev_rev; u32 rev; @@ -801,11 +801,10 @@ static enum ucode_state apply_microcode_intel(int cpu) if (WARN_ON(raw_smp_processor_id() != cpu)) return UCODE_ERROR; - uci = ucode_cpu_info + cpu; - mc = uci->mc; + /* Look for a newer patch in our cache: */ + mc = find_patch(uci); if (!mc) { - /* Look for a newer patch in our cache: */ - mc = find_patch(uci); + mc = uci->mc; if (!mc) return UCODE_NFOUND; } -- cgit v1.2.3-55-g7522 From cfb52a5a09c8ae3a1dafb44ce549fde5b69e8117 Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Wed, 28 Feb 2018 11:28:45 +0100 Subject: x86/microcode: Request microcode on the BSP ... so that any newer version can land in the cache and can later be fished out by the application functions. Do that before grabbing the hotplug lock. Signed-off-by: Borislav Petkov Signed-off-by: Thomas Gleixner Tested-by: Tom Lendacky Tested-by: Ashok Raj Reviewed-by: Tom Lendacky Cc: Arjan Van De Ven Link: https://lkml.kernel.org/r/20180228102846.13447-7-bp@alien8.de --- arch/x86/kernel/cpu/microcode/core.c | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index fa32cb3dcca5..5dd157d48606 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -499,15 +499,10 @@ static int check_online_cpus(void) static enum ucode_state reload_for_cpu(int cpu) { struct ucode_cpu_info *uci = ucode_cpu_info + cpu; - enum ucode_state ustate; if (!uci->valid) return UCODE_OK; - ustate = microcode_ops->request_microcode_fw(cpu, µcode_pdev->dev, true); - if (ustate != UCODE_OK) - return ustate; - return apply_microcode_on_target(cpu); } @@ -515,11 +510,11 @@ static ssize_t reload_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t size) { + int cpu, bsp = boot_cpu_data.cpu_index; enum ucode_state tmp_ret = UCODE_OK; bool do_callback = false; unsigned long val; ssize_t ret = 0; - int cpu; ret = kstrtoul(buf, 0, &val); if (ret) @@ -528,6 +523,10 @@ static ssize_t reload_store(struct device *dev, if (val != 1) return size; + tmp_ret = microcode_ops->request_microcode_fw(bsp, µcode_pdev->dev, true); + if (tmp_ret != UCODE_OK) + return size; + get_online_cpus(); ret = check_online_cpus(); -- cgit v1.2.3-55-g7522 From a5321aec6412b20b5ad15db2d6b916c05349dbff Mon Sep 17 00:00:00 2001 From: Ashok Raj Date: Wed, 28 Feb 2018 11:28:46 +0100 Subject: x86/microcode: Synchronize late microcode loading Original idea by Ashok, completely rewritten by Borislav. Before you read any further: the early loading method is still the preferred one and you should always do that. The following patch is improving the late loading mechanism for long running jobs and cloud use cases. Gather all cores and serialize the microcode update on them by doing it one-by-one to make the late update process as reliable as possible and avoid potential issues caused by the microcode update. [ Borislav: Rewrite completely. ] Co-developed-by: Borislav Petkov Signed-off-by: Ashok Raj Signed-off-by: Borislav Petkov Signed-off-by: Thomas Gleixner Tested-by: Tom Lendacky Tested-by: Ashok Raj Reviewed-by: Tom Lendacky Cc: Arjan Van De Ven Link: https://lkml.kernel.org/r/20180228102846.13447-8-bp@alien8.de --- arch/x86/kernel/cpu/microcode/core.c | 118 +++++++++++++++++++++++++++-------- 1 file changed, 92 insertions(+), 26 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index 5dd157d48606..70ecbc8099c9 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -22,13 +22,16 @@ #define pr_fmt(fmt) "microcode: " fmt #include +#include #include #include #include #include #include +#include #include #include +#include #include #include @@ -64,6 +67,11 @@ LIST_HEAD(microcode_cache); */ static DEFINE_MUTEX(microcode_mutex); +/* + * Serialize late loading so that CPUs get updated one-by-one. + */ +static DEFINE_SPINLOCK(update_lock); + struct ucode_cpu_info ucode_cpu_info[NR_CPUS]; struct cpu_info_ctx { @@ -486,6 +494,19 @@ static void __exit microcode_dev_exit(void) /* fake device for request_firmware */ static struct platform_device *microcode_pdev; +/* + * Late loading dance. Why the heavy-handed stomp_machine effort? + * + * - HT siblings must be idle and not execute other code while the other sibling + * is loading microcode in order to avoid any negative interactions caused by + * the loading. + * + * - In addition, microcode update on the cores must be serialized until this + * requirement can be relaxed in the future. Right now, this is conservative + * and good. + */ +#define SPINUNIT 100 /* 100 nsec */ + static int check_online_cpus(void) { if (num_online_cpus() == num_present_cpus()) @@ -496,23 +517,85 @@ static int check_online_cpus(void) return -EINVAL; } -static enum ucode_state reload_for_cpu(int cpu) +static atomic_t late_cpus; + +/* + * Returns: + * < 0 - on error + * 0 - no update done + * 1 - microcode was updated + */ +static int __reload_late(void *info) { - struct ucode_cpu_info *uci = ucode_cpu_info + cpu; + unsigned int timeout = NSEC_PER_SEC; + int all_cpus = num_online_cpus(); + int cpu = smp_processor_id(); + enum ucode_state err; + int ret = 0; - if (!uci->valid) - return UCODE_OK; + atomic_dec(&late_cpus); + + /* + * Wait for all CPUs to arrive. A load will not be attempted unless all + * CPUs show up. + * */ + while (atomic_read(&late_cpus)) { + if (timeout < SPINUNIT) { + pr_err("Timeout while waiting for CPUs rendezvous, remaining: %d\n", + atomic_read(&late_cpus)); + return -1; + } + + ndelay(SPINUNIT); + timeout -= SPINUNIT; + + touch_nmi_watchdog(); + } + + spin_lock(&update_lock); + apply_microcode_local(&err); + spin_unlock(&update_lock); + + if (err > UCODE_NFOUND) { + pr_warn("Error reloading microcode on CPU %d\n", cpu); + ret = -1; + } else if (err == UCODE_UPDATED) { + ret = 1; + } - return apply_microcode_on_target(cpu); + atomic_inc(&late_cpus); + + while (atomic_read(&late_cpus) != all_cpus) + cpu_relax(); + + return ret; +} + +/* + * Reload microcode late on all CPUs. Wait for a sec until they + * all gather together. + */ +static int microcode_reload_late(void) +{ + int ret; + + atomic_set(&late_cpus, num_online_cpus()); + + ret = stop_machine_cpuslocked(__reload_late, NULL, cpu_online_mask); + if (ret < 0) + return ret; + else if (ret > 0) + microcode_check(); + + return ret; } static ssize_t reload_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t size) { - int cpu, bsp = boot_cpu_data.cpu_index; enum ucode_state tmp_ret = UCODE_OK; - bool do_callback = false; + int bsp = boot_cpu_data.cpu_index; unsigned long val; ssize_t ret = 0; @@ -534,30 +617,13 @@ static ssize_t reload_store(struct device *dev, goto put; mutex_lock(µcode_mutex); - - for_each_online_cpu(cpu) { - tmp_ret = reload_for_cpu(cpu); - if (tmp_ret > UCODE_NFOUND) { - pr_warn("Error reloading microcode on CPU %d\n", cpu); - - /* set retval for the first encountered reload error */ - if (!ret) - ret = -EINVAL; - } - - if (tmp_ret == UCODE_UPDATED) - do_callback = true; - } - - if (!ret && do_callback) - microcode_check(); - + ret = microcode_reload_late(); mutex_unlock(µcode_mutex); put: put_online_cpus(); - if (!ret) + if (ret >= 0) ret = size; return ret; -- cgit v1.2.3-55-g7522 From c5b679f5c9e3851ee118d95961def374bb3b4ce6 Mon Sep 17 00:00:00 2001 From: Seunghun Han Date: Wed, 7 Mar 2018 13:32:15 +0900 Subject: x86/pti: Fix a comment typo s/visinble/visible/ Signed-off-by: Seunghun Han Signed-off-by: Thomas Gleixner Link: https://lkml.kernel.org/r/1520397135-132809-1-git-send-email-kkamagui@gmail.com --- arch/x86/mm/pti.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/x86/mm/pti.c b/arch/x86/mm/pti.c index ce38f165489b..631507f0c198 100644 --- a/arch/x86/mm/pti.c +++ b/arch/x86/mm/pti.c @@ -332,7 +332,7 @@ static void __init pti_clone_user_shared(void) } /* - * Clone the ESPFIX P4D into the user space visinble page table + * Clone the ESPFIX P4D into the user space visible page table */ static void __init pti_setup_espfix64(void) { -- cgit v1.2.3-55-g7522 From fa94d0c6e0f3431523f5701084d799c77c7d4a4f Mon Sep 17 00:00:00 2001 From: Tony Luck Date: Tue, 6 Mar 2018 15:21:41 +0100 Subject: x86/MCE: Save microcode revision in machine check records Updating microcode used to be relatively rare. Now that it has become more common we should save the microcode version in a machine check record to make sure that those people looking at the error have this important information bundled with the rest of the logged information. [ Borislav: Simplify a bit. ] Signed-off-by: Tony Luck Signed-off-by: Borislav Petkov Signed-off-by: Thomas Gleixner Cc: Yazen Ghannam Cc: linux-edac Cc: stable@vger.kernel.org Link: http://lkml.kernel.org/r/20180301233449.24311-1-tony.luck@intel.com --- arch/x86/include/uapi/asm/mce.h | 1 + arch/x86/kernel/cpu/mcheck/mce.c | 4 +++- 2 files changed, 4 insertions(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/x86/include/uapi/asm/mce.h b/arch/x86/include/uapi/asm/mce.h index 91723461dc1f..435db58a7bad 100644 --- a/arch/x86/include/uapi/asm/mce.h +++ b/arch/x86/include/uapi/asm/mce.h @@ -30,6 +30,7 @@ struct mce { __u64 synd; /* MCA_SYND MSR: only valid on SMCA systems */ __u64 ipid; /* MCA_IPID MSR: only valid on SMCA systems */ __u64 ppin; /* Protected Processor Inventory Number */ + __u32 microcode;/* Microcode revision */ }; #define MCE_GET_RECORD_LEN _IOR('M', 1, int) diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 8ff94d1e2dce..b3323cab9139 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -130,6 +130,8 @@ void mce_setup(struct mce *m) if (this_cpu_has(X86_FEATURE_INTEL_PPIN)) rdmsrl(MSR_PPIN, m->ppin); + + m->microcode = boot_cpu_data.microcode; } DEFINE_PER_CPU(struct mce, injectm); @@ -262,7 +264,7 @@ static void __print_mce(struct mce *m) */ pr_emerg(HW_ERR "PROCESSOR %u:%x TIME %llu SOCKET %u APIC %x microcode %x\n", m->cpuvendor, m->cpuid, m->time, m->socketid, m->apicid, - cpu_data(m->extcpu).microcode); + m->microcode); } static void print_mce(struct mce *m) -- cgit v1.2.3-55-g7522 From b3b7c4795ccab5be71f080774c45bbbcc75c2aaf Mon Sep 17 00:00:00 2001 From: Seunghun Han Date: Tue, 6 Mar 2018 15:21:43 +0100 Subject: x86/MCE: Serialize sysfs changes The check_interval file in /sys/devices/system/machinecheck/machinecheck directory is a global timer value for MCE polling. If it is changed by one CPU, mce_restart() broadcasts the event to other CPUs to delete and restart the MCE polling timer and __mcheck_cpu_init_timer() reinitializes the mce_timer variable. If more than one CPU writes a specific value to the check_interval file concurrently, mce_timer is not protected from such concurrent accesses and all kinds of explosions happen. Since only root can write to those sysfs variables, the issue is not a big deal security-wise. However, concurrent writes to these configuration variables is void of reason so the proper thing to do is to serialize the access with a mutex. Boris: - Make store_int_with_restart() use device_store_ulong() to filter out negative intervals - Limit min interval to 1 second - Correct locking - Massage commit message Signed-off-by: Seunghun Han Signed-off-by: Borislav Petkov Signed-off-by: Thomas Gleixner Cc: Greg Kroah-Hartman Cc: Tony Luck Cc: linux-edac Cc: stable@vger.kernel.org Link: http://lkml.kernel.org/r/20180302202706.9434-1-kkamagui@gmail.com --- arch/x86/kernel/cpu/mcheck/mce.c | 22 +++++++++++++++++++++- 1 file changed, 21 insertions(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index b3323cab9139..466f47301334 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -56,6 +56,9 @@ static DEFINE_MUTEX(mce_log_mutex); +/* sysfs synchronization */ +static DEFINE_MUTEX(mce_sysfs_mutex); + #define CREATE_TRACE_POINTS #include @@ -2088,6 +2091,7 @@ static ssize_t set_ignore_ce(struct device *s, if (kstrtou64(buf, 0, &new) < 0) return -EINVAL; + mutex_lock(&mce_sysfs_mutex); if (mca_cfg.ignore_ce ^ !!new) { if (new) { /* disable ce features */ @@ -2100,6 +2104,8 @@ static ssize_t set_ignore_ce(struct device *s, on_each_cpu(mce_enable_ce, (void *)1, 1); } } + mutex_unlock(&mce_sysfs_mutex); + return size; } @@ -2112,6 +2118,7 @@ static ssize_t set_cmci_disabled(struct device *s, if (kstrtou64(buf, 0, &new) < 0) return -EINVAL; + mutex_lock(&mce_sysfs_mutex); if (mca_cfg.cmci_disabled ^ !!new) { if (new) { /* disable cmci */ @@ -2123,6 +2130,8 @@ static ssize_t set_cmci_disabled(struct device *s, on_each_cpu(mce_enable_ce, NULL, 1); } } + mutex_unlock(&mce_sysfs_mutex); + return size; } @@ -2130,8 +2139,19 @@ static ssize_t store_int_with_restart(struct device *s, struct device_attribute *attr, const char *buf, size_t size) { - ssize_t ret = device_store_int(s, attr, buf, size); + unsigned long old_check_interval = check_interval; + ssize_t ret = device_store_ulong(s, attr, buf, size); + + if (check_interval == old_check_interval) + return ret; + + if (check_interval < 1) + check_interval = 1; + + mutex_lock(&mce_sysfs_mutex); mce_restart(); + mutex_unlock(&mce_sysfs_mutex); + return ret; } -- cgit v1.2.3-55-g7522 From c07a8f8b08ba683ea24f3ac9159f37ae94daf47f Mon Sep 17 00:00:00 2001 From: Francis Deslauriers Date: Thu, 8 Mar 2018 22:18:12 -0500 Subject: x86/kprobes: Fix kernel crash when probing .entry_trampoline code Disable the kprobe probing of the entry trampoline: .entry_trampoline is a code area that is used to ensure page table isolation between userspace and kernelspace. At the beginning of the execution of the trampoline, we load the kernel's CR3 register. This has the effect of enabling the translation of the kernel virtual addresses to physical addresses. Before this happens most kernel addresses can not be translated because the running process' CR3 is still used. If a kprobe is placed on the trampoline code before that change of the CR3 register happens the kernel crashes because int3 handling pages are not accessible. To fix this, add the .entry_trampoline section to the kprobe blacklist to prohibit the probing of code before all the kernel pages are accessible. Signed-off-by: Francis Deslauriers Reviewed-by: Thomas Gleixner Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Josh Poimboeuf Cc: Linus Torvalds Cc: Peter Zijlstra Cc: mathieu.desnoyers@efficios.com Cc: mhiramat@kernel.org Link: http://lkml.kernel.org/r/1520565492-4637-2-git-send-email-francis.deslauriers@efficios.com Signed-off-by: Ingo Molnar --- arch/x86/include/asm/sections.h | 1 + arch/x86/kernel/kprobes/core.c | 10 +++++++++- arch/x86/kernel/vmlinux.lds.S | 2 ++ 3 files changed, 12 insertions(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/x86/include/asm/sections.h b/arch/x86/include/asm/sections.h index d6baf23782bc..5c019d23d06b 100644 --- a/arch/x86/include/asm/sections.h +++ b/arch/x86/include/asm/sections.h @@ -10,6 +10,7 @@ extern struct exception_table_entry __stop___ex_table[]; #if defined(CONFIG_X86_64) extern char __end_rodata_hpage_align[]; +extern char __entry_trampoline_start[], __entry_trampoline_end[]; #endif #endif /* _ASM_X86_SECTIONS_H */ diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index bd36f3c33cd0..0715f827607c 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -1168,10 +1168,18 @@ NOKPROBE_SYMBOL(longjmp_break_handler); bool arch_within_kprobe_blacklist(unsigned long addr) { + bool is_in_entry_trampoline_section = false; + +#ifdef CONFIG_X86_64 + is_in_entry_trampoline_section = + (addr >= (unsigned long)__entry_trampoline_start && + addr < (unsigned long)__entry_trampoline_end); +#endif return (addr >= (unsigned long)__kprobes_text_start && addr < (unsigned long)__kprobes_text_end) || (addr >= (unsigned long)__entry_text_start && - addr < (unsigned long)__entry_text_end); + addr < (unsigned long)__entry_text_end) || + is_in_entry_trampoline_section; } int __init arch_init_kprobes(void) diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index 9b138a06c1a4..b854ebf5851b 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -118,9 +118,11 @@ SECTIONS #ifdef CONFIG_X86_64 . = ALIGN(PAGE_SIZE); + VMLINUX_SYMBOL(__entry_trampoline_start) = .; _entry_trampoline = .; *(.entry_trampoline) . = ALIGN(PAGE_SIZE); + VMLINUX_SYMBOL(__entry_trampoline_end) = .; ASSERT(. - _entry_trampoline == PAGE_SIZE, "entry trampoline is too big"); #endif -- cgit v1.2.3-55-g7522 From e21da1c992007594d391e7b301779cf30f438691 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Fri, 9 Mar 2018 15:40:50 +0000 Subject: arm64: Relax ARM_SMCCC_ARCH_WORKAROUND_1 discovery A recent update to the ARM SMCCC ARCH_WORKAROUND_1 specification allows firmware to return a non zero, positive value to describe that although the mitigation is implemented at the higher exception level, the CPU on which the call is made is not affected. Let's relax the check on the return value from ARCH_WORKAROUND_1 so that we only error out if the returned value is negative. Fixes: b092201e0020 ("arm64: Add ARM_SMCCC_ARCH_WORKAROUND_1 BP hardening support") Signed-off-by: Marc Zyngier Signed-off-by: Catalin Marinas --- arch/arm64/kernel/cpu_errata.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch') diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index 52f15cd896e1..b5a28336c077 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -178,7 +178,7 @@ static int enable_smccc_arch_workaround_1(void *data) case PSCI_CONDUIT_HVC: arm_smccc_1_1_hvc(ARM_SMCCC_ARCH_FEATURES_FUNC_ID, ARM_SMCCC_ARCH_WORKAROUND_1, &res); - if (res.a0) + if ((int)res.a0 < 0) return 0; cb = call_hvc_arch_workaround_1; smccc_start = __smccc_workaround_1_hvc_start; @@ -188,7 +188,7 @@ static int enable_smccc_arch_workaround_1(void *data) case PSCI_CONDUIT_SMC: arm_smccc_1_1_smc(ARM_SMCCC_ARCH_FEATURES_FUNC_ID, ARM_SMCCC_ARCH_WORKAROUND_1, &res); - if (res.a0) + if ((int)res.a0 < 0) return 0; cb = call_smc_arch_workaround_1; smccc_start = __smccc_workaround_1_smc_start; -- cgit v1.2.3-55-g7522