summaryrefslogtreecommitdiffstats
Commit message (Collapse)AuthorAgeFilesLines
* powerpc/mm: Speed up computation of base and actual page size for a HPTEPaul Mackerras2016-09-095-120/+102Star
| | | | | | | | | | | | | | | | | | | | | | | | | This replaces a 2-D search through an array with a simple 8-bit table lookup for determining the actual and/or base page size for a HPT entry. The encoding in the second doubleword of the HPTE is designed to encode the actual and base page sizes without using any more bits than would be needed for a 4k page number, by using between 1 and 8 low-order bits of the RPN (real page number) field to encode the page sizes. A single "large page" bit in the first doubleword indicates that these low-order bits are to be interpreted like this. We can determine the page sizes by using the low-order 8 bits of the RPN to look up a 256-entry table. For actual page sizes less than 1MB, some of the upper bits of these 8 bits are going to be real address bits, but we can cope with that by replicating the entries for those smaller page sizes. While we're at it, let's move the hpte_page_size() and hpte_base_page_size() functions from a KVM-specific header to a header for 64-bit HPT systems, since this computation doesn't have anything specifically to do with KVM. Reviewed-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
* Linux 4.8-rc2Linus Torvalds2016-08-151-1/+1
|
* Merge branch 'next' of ↵Linus Torvalds2016-08-159-8/+84
|\ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | git://git.kernel.org/pub/scm/linux/kernel/git/rzhang/linux Pull thermal updates from Zhang Rui: - Fix a race condition when updating cooling device, which may lead to a situation where a thermal governor never updates the cooling device. From Michele Di Giorgio. - Fix a zero division error when disabling the forced idle injection from the intel powerclamp. From Petr Mladek. - Add suspend/resume callback for intel_pch_thermal thermal driver. From Srinivas Pandruvada. - Another two fixes for clocking cooling driver and hwmon sysfs I/F. From Michele Di Giorgio and Kuninori Morimoto. [ Hmm. That suspend/resume callback for intel_pch_thermal doesn't look like a fix, but I'm letting it slide.. - Linus ] * 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/rzhang/linux: thermal: clock_cooling: Fix missing mutex_init() thermal: hwmon: EXPORT_SYMBOL_GPL for thermal hwmon sysfs thermal: fix race condition when updating cooling device thermal/powerclamp: Prevent division by zero when counting interval thermal: intel_pch_thermal: Add suspend/resume callback
| * Merge branches 'thermal-intel' and 'thermal-core' into nextZhang Rui2016-08-087-3/+18
| |\
| | * thermal: clock_cooling: Fix missing mutex_init()Wei Yongjun2016-08-081-0/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The driver allocates the mutex but not initialize it. Use mutex_init() on it to initialize it correctly. This is detected by Coccinelle semantic patch. Signed-off-by: Wei Yongjun <weiyj.lk@gmail.com> Signed-off-by: Zhang Rui <rui.zhang@intel.com>
| | * thermal: hwmon: EXPORT_SYMBOL_GPL for thermal hwmon sysfsKuninori Morimoto2016-08-081-0/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | thermal_add_hwmon_sysfs()/thermal_remove_hwmon_sysfs() need EXPORT_SYMBOL_GPL(). Otherwise we will have ERROR >> ERROR: "thermal_remove_hwmon_sysfs" [drivers/thermal/rcar_thermal.ko] undefined! >> ERROR: "thermal_add_hwmon_sysfs" [drivers/thermal/rcar_thermal.ko] undefined! Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com> Signed-off-by: Zhang Rui <rui.zhang@intel.com>
| | * thermal: fix race condition when updating cooling deviceMichele Di Giorgio2016-08-085-3/+15
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | When multiple thermal zones are bound to the same cooling device, multiple kernel threads may want to update the cooling device state by calling thermal_cdev_update(). Having cdev not protected by a mutex can lead to a race condition. Consider the following situation with two kernel threads k1 and k2: Thread k1 Thread k2 || || call thermal_cdev_update() || ... || set_cur_state(cdev, target); call power_actor_set_power() || ... || instance->target = state; || cdev->updated = false; || || cdev->updated = true; || // completes execution call thermal_cdev_update() || // cdev->updated == true || return; || \/ time k2 has already looped through the thermal instances looking for the deepest cooling device state and is preempted right before setting cdev->updated to true. Now, k1 runs, modifies the thermal instance state and sets cdev->updated to false. Then, k1 is preempted and k2 continues the execution by setting cdev->updated to true, therefore preventing k1 from performing the update. Notice that this is not an issue if k2 looks at the instance->target modified by k1 "after" it is assigned by k1. In fact, in this case the update will happen anyway and k1 can safely return immediately from thermal_cdev_update(). This may lead to a situation where a thermal governor never updates the cooling device. For example, this is the case for the step_wise governor: when calling the function thermal_zone_trip_update(), the governor may always get a new state equal to the old one (which, however, wasn't notified to the cooling device) and will therefore skip the update. CC: Zhang Rui <rui.zhang@intel.com> CC: Eduardo Valentin <edubezval@gmail.com> CC: Peter Feuerer <peter@piie.net> Reported-by: Toby Huang <toby.huang@arm.com> Signed-off-by: Michele Di Giorgio <michele.digiorgio@arm.com> Reviewed-by: Javi Merino <javi.merino@arm.com> Signed-off-by: Zhang Rui <rui.zhang@intel.com>
| * | thermal/powerclamp: Prevent division by zero when counting intervalPetr Mladek2016-08-081-4/+7
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | I have got a zero division error when disabling the forced idle injection from the intel powerclamp. I did echo 0 >/sys/class/thermal/cooling_device48/cur_state and got [ 986.072632] divide error: 0000 [#1] PREEMPT SMP [ 986.078989] Modules linked in: [ 986.083618] CPU: 17 PID: 24967 Comm: kidle_inject/17 Not tainted 4.7.0-1-default+ #3055 [ 986.093781] Hardware name: Intel Corporation S2600CP/S2600CP, BIOS RMLSDP.86I.R3.27.D685.1305151734 05/15/2013 [ 986.106227] task: ffff880430e1c080 task.stack: ffff880427ef0000 [ 986.114122] RIP: 0010:[<ffffffff81794859>] [<ffffffff81794859>] clamp_thread+0x1d9/0x600 [ 986.124609] RSP: 0018:ffff880427ef3e20 EFLAGS: 00010246 [ 986.131860] RAX: 0000000000000258 RBX: 0000000000000006 RCX: 0000000000000001 [ 986.141179] RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000018 [ 986.150478] RBP: ffff880427ef3ec8 R08: ffff880427ef0000 R09: 0000000000000002 [ 986.159779] R10: 0000000000003df2 R11: 0000000000000018 R12: 0000000000000002 [ 986.169089] R13: 0000000000000000 R14: ffff880427ef0000 R15: ffff880427ef0000 [ 986.178388] FS: 0000000000000000(0000) GS:ffff880435940000(0000) knlGS:0000000000000000 [ 986.188785] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 986.196559] CR2: 00007f1d0caf0000 CR3: 0000000002006000 CR4: 00000000001406e0 [ 986.205909] Stack: [ 986.209524] ffff8802be897b00 ffff880430e1c080 0000000000000011 0000006a35959780 [ 986.219236] 0000000000000011 ffff880427ef0008 0000000000000000 ffff8804359503d0 [ 986.228966] 0000000100029d93 ffffffff81794140 0000000000000000 ffffffff05000011 [ 986.238686] Call Trace: [ 986.242825] [<ffffffff81794140>] ? pkg_state_counter+0x80/0x80 [ 986.250866] [<ffffffff81794680>] ? powerclamp_set_cur_state+0x180/0x180 [ 986.259797] [<ffffffff8111d1a9>] kthread+0xc9/0xe0 [ 986.266682] [<ffffffff8193d69f>] ret_from_fork+0x1f/0x40 [ 986.274142] [<ffffffff8111d0e0>] ? kthread_create_on_node+0x180/0x180 [ 986.282869] Code: d1 ea 48 89 d6 80 3d 6a d0 d4 00 00 ba 64 00 00 00 89 d8 41 0f 45 f5 0f af c2 42 8d 14 2e be 31 00 00 00 83 fa 31 0f 42 f2 31 d2 <f7> f6 48 8b 15 9e 07 87 00 48 8b 3d 97 07 87 00 48 63 f0 83 e8 [ 986.307806] RIP [<ffffffff81794859>] clamp_thread+0x1d9/0x600 [ 986.315871] RSP <ffff880427ef3e20> RIP points to the following lines: compensation = get_compensation(target_ratio); interval = duration_jiffies*100/(target_ratio+compensation); A solution would be to switch the following two commands in powerclamp_set_cur_state(): set_target_ratio = 0; end_power_clamp(); But I think that the zero division might happen also when target_ratio is non-zero because the compensation might be negative. Therefore we also check the sum of target_ratio and compensation explicitly. Also the compensated_ratio variable is always set. Therefore there is no need to initialize it. Signed-off-by: Petr Mladek <pmladek@suse.com> Acked-by: Jacob Pan <jacob.jun.pan@linux.intel.com> Signed-off-by: Zhang Rui <rui.zhang@intel.com>
| * | thermal: intel_pch_thermal: Add suspend/resume callbackSrinivas Pandruvada2016-08-081-1/+59
| |/ | | | | | | | | | | | | | | | | Added suspend/resume callback to disable/enable PCH thermal sensor respectively. If the sensor is enabled by the BIOS, then the sensor status will not be changed during suspend/resume. Signed-off-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com> Signed-off-by: Zhang Rui <rui.zhang@intel.com>
* | Merge branch 'for-linus' of ↵Linus Torvalds2016-08-151-1/+0Star
|\ \ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | git://git.kernel.org/pub/scm/linux/kernel/git/gerg/m68knommu Pull m68knommu fix from Greg Ungerer: "This contains only a single fix for a register corruption problem on certain types of m68k flat format binaries" * 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/gerg/m68knommu: m68knommu: fix user a5 register being overwritten
| * | m68knommu: fix user a5 register being overwrittenGreg Ungerer2016-08-081-1/+0Star
| |/ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | On no-MMU systems the application a5 register can be overwitten with the address of the process data segment when processing application signals. For flat format applications compiled with full absolute relocation this effectively corrupts the a5 register on signal processing - and this very quickly leads to process crash and often takes out the whole system with a panic as well. This has no effect on flat format applications compiled with the more common PIC methods (such as -msep-data). These format applications reserve a5 for the pointer to the data segment anyway - so it doesn't change it. A long time ago the a5 register was used in the code packed into the user stack to enable signal return processing. And so it had to be restored on end of signal cleanup processing back to the original a5 user value. This was historically done by saving away a5 in the sigcontext structure. At some point (a long time back it seems) the a5 restore process was changed and it was hard coded to put the user data segment address directly into a5. Which is ok for the common PIC compiled application case, but breaks the full relocation application code. We no longer use this type of signal handling mechanism and so we don't need to do anything special to save and restore a5 at all now. So remove the code that hard codes a5 to the address of the user data segment. Signed-off-by: Greg Ungerer <gerg@linux-m68k.org>
* | Merge tag 'fixes-for-linus-4.8' of ↵Linus Torvalds2016-08-142-1/+3
|\ \ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | git://git.kernel.org/pub/scm/linux/kernel/git/groeck/linux-staging Pull h8300 and unicore32 architecture fixes from Guenter Roeck: "Two patches to fix h8300 and unicore32 builds. unicore32 builds have been broken since v4.6. The fix has been available in -next since March of this year. h8300 builds have been broken since the last commit window. The fix has been available in -next since June of this year" * tag 'fixes-for-linus-4.8' of git://git.kernel.org/pub/scm/linux/kernel/git/groeck/linux-staging: h8300: Add missing include file to asm/io.h unicore32: mm: Add missing parameter to arch_vma_access_permitted
| * | h8300: Add missing include file to asm/io.hGuenter Roeck2016-08-131-0/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | h8300 builds fail with arch/h8300/include/asm/io.h:9:15: error: unknown type name ‘u8’ arch/h8300/include/asm/io.h:15:15: error: unknown type name ‘u16’ arch/h8300/include/asm/io.h:21:15: error: unknown type name ‘u32’ and many related errors. Fixes: 23c82d41bdf4 ("kexec-allow-architectures-to-override-boot-mapping-fix") Cc: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Guenter Roeck <linux@roeck-us.net>
| * | unicore32: mm: Add missing parameter to arch_vma_access_permittedGuenter Roeck2016-08-131-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | unicore32 fails to compile with the following errors. mm/memory.c: In function ‘__handle_mm_fault’: mm/memory.c:3381: error: too many arguments to function ‘arch_vma_access_permitted’ mm/gup.c: In function ‘check_vma_flags’: mm/gup.c:456: error: too many arguments to function ‘arch_vma_access_permitted’ mm/gup.c: In function ‘vma_permits_fault’: mm/gup.c:640: error: too many arguments to function ‘arch_vma_access_permitted’ Fixes: d61172b4b695b ("mm/core, x86/mm/pkeys: Differentiate instruction fetches") Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@kernel.org> Signed-off-by: Guenter Roeck <linux@roeck-us.net> Acked-by: Guan Xuetao <gxt@mprc.pku.edu.cn>
* | | Merge tag 'arm64-fixes' of ↵Linus Torvalds2016-08-148-86/+136
|\ \ \ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux Pull arm64 fixes from Catalin Marinas: - support for nr_cpus= command line argument (maxcpus was previously changed to allow secondary CPUs to be hot-plugged) - ARM PMU interrupt handling fix - fix potential TLB conflict in the hibernate code - improved handling of EL1 instruction aborts (better error reporting) - removal of useless jprobes code for stack saving/restoring - defconfig updates * tag 'arm64-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: arm64: defconfig: enable CONFIG_LOCALVERSION_AUTO arm64: defconfig: add options for virtualization and containers arm64: hibernate: handle allocation failures arm64: hibernate: avoid potential TLB conflict arm64: Handle el1 synchronous instruction aborts cleanly arm64: Remove stack duplicating code from jprobes drivers/perf: arm-pmu: Fix handling of SPI lacking "interrupt-affinity" property drivers/perf: arm-pmu: convert arm_pmu_mutex to spinlock arm64: Support hard limit of cpu count by nr_cpus
| * | | arm64: defconfig: enable CONFIG_LOCALVERSION_AUTOMasahiro Yamada2016-08-121-1/+0Star
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | When CONFIG_LOCALVERSION_AUTO is disabled, the version string is just a tag name (or with a '+' appended if HEAD is not a tagged commit). During the development (and especially when git-bisecting), longer version string would be helpful to identify the commit we are running. This is a default y option, so drop the unset to enable it. Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com> Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
| * | | arm64: defconfig: add options for virtualization and containersRiku Voipio2016-08-121-6/+46
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Enable options commonly needed by popular virtualization and container applications. Use modules when possible to avoid too much overhead for users not interested. - add namespace and cgroup options needed - add seccomp - optional, but enhances Qemu etc - bridge, nat, veth, macvtap and multicast for routing guests and containers - btfrs and overlayfs modules for container COW backends - while near it, make fuse a module instead of built-in. Generated with make saveconfig and dropping unrelated spurious change hunks while commiting. bloat-o-meter old-vmlinux vmlinux: add/remove: 905/390 grow/shrink: 767/229 up/down: 183513/-94861 (88652) .... Total: Before=10515408, After=10604060, chg +0.84% Signed-off-by: Riku Voipio <riku.voipio@linaro.org> Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
| * | | arm64: hibernate: handle allocation failuresMark Rutland2016-08-121-27/+32
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | In create_safe_exec_page(), we create a copy of the hibernate exit text, along with some page tables to map this via TTBR0. We then install the new tables in TTBR0. In swsusp_arch_resume() we call create_safe_exec_page() before trying a number of operations which may fail (e.g. copying the linear map page tables). If these fail, we bail out of swsusp_arch_resume() and return an error code, but leave TTBR0 as-is. Subsequently, the core hibernate code will call free_basic_memory_bitmaps(), which will free all of the memory allocations we made, including the page tables installed in TTBR0. Thus, we may have TTBR0 pointing at dangling freed memory for some period of time. If the hibernate attempt was triggered by a user requesting a hibernate test via the reboot syscall, we may return to userspace with the clobbered TTBR0 value. Avoid these issues by reorganising swsusp_arch_resume() such that we have no failure paths after create_safe_exec_page(). We also add a check that the zero page allocation succeeded, matching what we have for other allocations. Fixes: 82869ac57b5d ("arm64: kernel: Add support for hibernate/suspend-to-disk") Signed-off-by: Mark Rutland <mark.rutland@arm.com> Acked-by: James Morse <james.morse@arm.com> Cc: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com> Cc: Will Deacon <will.deacon@arm.com> Cc: <stable@vger.kernel.org> # 4.7+ Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
| * | | arm64: hibernate: avoid potential TLB conflictMark Rutland2016-08-121-6/+17
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | In create_safe_exec_page we install a set of global mappings in TTBR0, then subsequently invalidate TLBs. While TTBR0 points at the zero page, and the TLBs should be free of stale global entries, we may have stale ASID-tagged entries (e.g. from the EFI runtime services mappings) for the same VAs. Per the ARM ARM these ASID-tagged entries may conflict with newly-allocated global entries, and we must follow a Break-Before-Make approach to avoid issues resulting from this. This patch reworks create_safe_exec_page to invalidate TLBs while the zero page is still in place, ensuring that there are no potential conflicts when the new TTBR0 value is installed. As a single CPU is online while this code executes, we do not need to perform broadcast TLB maintenance, and can call local_flush_tlb_all(), which also subsumes some barriers. The remaining assembly is converted to use write_sysreg() and isb(). Other than this, we safely manipulate TTBRs in the hibernate dance. The code we install as part of the new TTBR0 mapping (the hibernated kernel's swsusp_arch_suspend_exit) installs a zero page into TTBR1, invalidates TLBs, then installs its preferred value. Upon being restored to the middle of swsusp_arch_suspend, the new image will call __cpu_suspend_exit, which will call cpu_uninstall_idmap, installing the zero page in TTBR0 and invalidating all TLB entries. Fixes: 82869ac57b5d ("arm64: kernel: Add support for hibernate/suspend-to-disk") Signed-off-by: Mark Rutland <mark.rutland@arm.com> Acked-by: James Morse <james.morse@arm.com> Tested-by: James Morse <james.morse@arm.com> Cc: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com> Cc: Will Deacon <will.deacon@arm.com> Cc: <stable@vger.kernel.org> # 4.7+ Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
| * | | arm64: Handle el1 synchronous instruction aborts cleanlyLaura Abbott2016-08-122-2/+19
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Executing from a non-executable area gives an ugly message: lkdtm: Performing direct entry EXEC_RODATA lkdtm: attempting ok execution at ffff0000084c0e08 lkdtm: attempting bad execution at ffff000008880700 Bad mode in Synchronous Abort handler detected on CPU2, code 0x8400000e -- IABT (current EL) CPU: 2 PID: 998 Comm: sh Not tainted 4.7.0-rc2+ #13 Hardware name: linux,dummy-virt (DT) task: ffff800077e35780 ti: ffff800077970000 task.ti: ffff800077970000 PC is at lkdtm_rodata_do_nothing+0x0/0x8 LR is at execute_location+0x74/0x88 The 'IABT (current EL)' indicates the error but it's a bit cryptic without knowledge of the ARM ARM. There is also no indication of the specific address which triggered the fault. The increase in kernel page permissions makes hitting this case more likely as well. Handling the case in the vectors gives a much more familiar looking error message: lkdtm: Performing direct entry EXEC_RODATA lkdtm: attempting ok execution at ffff0000084c0840 lkdtm: attempting bad execution at ffff000008880680 Unable to handle kernel paging request at virtual address ffff000008880680 pgd = ffff8000089b2000 [ffff000008880680] *pgd=00000000489b4003, *pud=0000000048904003, *pmd=0000000000000000 Internal error: Oops: 8400000e [#1] PREEMPT SMP Modules linked in: CPU: 1 PID: 997 Comm: sh Not tainted 4.7.0-rc1+ #24 Hardware name: linux,dummy-virt (DT) task: ffff800077f9f080 ti: ffff800008a1c000 task.ti: ffff800008a1c000 PC is at lkdtm_rodata_do_nothing+0x0/0x8 LR is at execute_location+0x74/0x88 Acked-by: Mark Rutland <mark.rutland@arm.com> Signed-off-by: Laura Abbott <labbott@redhat.com> Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
| * | | arm64: Remove stack duplicating code from jprobesDavid A. Long2016-08-112-28/+5Star
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Because the arm64 calling standard allows stacked function arguments to be anywhere in the stack frame, do not attempt to duplicate the stack frame for jprobes handler functions. Documentation changes to describe this issue have been broken out into a separate patch in order to simultaneously address them in other architecture(s). Signed-off-by: David A. Long <dave.long@linaro.org> Acked-by: Masami Hiramatsu <mhiramat@kernel.org> Acked-by: Marc Zyngier <marc.zyngier@arm.com> Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
| * | | drivers/perf: arm-pmu: Fix handling of SPI lacking "interrupt-affinity" propertyMarc Zyngier2016-08-091-3/+4
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Patch 19a469a58720 ("drivers/perf: arm-pmu: Handle per-interrupt affinity mask") added support for partitionned PPI setups, but inadvertently broke setups using SPIs without the "interrupt-affinity" property (which is the case for UP platforms). This patch restore the broken functionnality by testing whether the interrupt is percpu or not instead of relying on the using_spi flag that really means "SPI *and* interrupt-affinity property". Acked-by: Mark Rutland <mark.rutland@arm.com> Reported-by: Geert Uytterhoeven <geert@linux-m68k.org> Tested-by: Geert Uytterhoeven <geert@linux-m68k.org> Fixes: 19a469a58720 ("drivers/perf: arm-pmu: Handle per-interrupt affinity mask") Signed-off-by: Marc Zyngier <marc.zyngier@arm.com> Signed-off-by: Will Deacon <will.deacon@arm.com>
| * | | drivers/perf: arm-pmu: convert arm_pmu_mutex to spinlockSudeep Holla2016-08-091-9/+9
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | arm_pmu_mutex is never held long and we don't want to sleep while the lock is being held as it's executed in the context of hotplug notifiers. So it can be converted to a simple spinlock instead. Without this patch we get the following warning: BUG: sleeping function called from invalid context at kernel/locking/mutex.c:620 in_atomic(): 1, irqs_disabled(): 128, pid: 0, name: swapper/2 no locks held by swapper/2/0. irq event stamp: 381314 hardirqs last enabled at (381313): _raw_spin_unlock_irqrestore+0x7c/0x88 hardirqs last disabled at (381314): cpu_die+0x28/0x48 softirqs last enabled at (381294): _local_bh_enable+0x28/0x50 softirqs last disabled at (381293): irq_enter+0x58/0x78 CPU: 2 PID: 0 Comm: swapper/2 Not tainted 4.7.0 #12 Call trace: dump_backtrace+0x0/0x220 show_stack+0x24/0x30 dump_stack+0xb4/0xf0 ___might_sleep+0x1d8/0x1f0 __might_sleep+0x5c/0x98 mutex_lock_nested+0x54/0x400 arm_perf_starting_cpu+0x34/0xb0 cpuhp_invoke_callback+0x88/0x3d8 notify_cpu_starting+0x78/0x98 secondary_start_kernel+0x108/0x1a8 This patch converts the mutex to spinlock to eliminate the above warnings. This constraints pmu->reset to be non-blocking call which is the case with all the ARM PMU backends. Cc: Stephen Boyd <sboyd@codeaurora.org> Fixes: 37b502f121ad ("arm/perf: Fix hotplug state machine conversion") Acked-by: Mark Rutland <mark.rutland@arm.com> Signed-off-by: Sudeep Holla <sudeep.holla@arm.com> Signed-off-by: Will Deacon <will.deacon@arm.com>
| * | | arm64: Support hard limit of cpu count by nr_cpusKefeng Wang2016-08-091-4/+4
| | |/ | |/| | | | | | | | | | | | | | | | | | | | | | | | | | | | Enable the hard limit of cpu count by set boot options nr_cpus=x on arm64, and make a minor change about message when total number of cpu exceeds the limit. Reviewed-by: Suzuki K Poulose <suzuki.poulose@arm.com> Reported-by: Shiyuan Hu <hushiyuan@huawei.com> Signed-off-by: Kefeng Wang <wangkefeng.wang@huawei.com> Signed-off-by: Will Deacon <will.deacon@arm.com>
* | | Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvmLinus Torvalds2016-08-138-53/+118
|\ \ \ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Pull KVM fixes from Radim Krčmář: "KVM: - lock kvm_device list to prevent corruption on device creation. PPC: - split debugfs initialization from creation of the xics device to unlock the newly taken kvm lock earlier. s390: - prevent userspace from triggering two WARN_ON_ONCE. MIPS: - fix several issues in the management of TLB faults (Cc: stable)" * tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: MIPS: KVM: Propagate kseg0/mapped tlb fault errors MIPS: KVM: Fix gfn range check in kseg0 tlb faults MIPS: KVM: Add missing gfn range check MIPS: KVM: Fix mapped fault broken commpage handling KVM: Protect device ops->create and list_add with kvm->lock KVM: PPC: Move xics_debugfs_init out of create KVM: s390: reset KVM_REQ_MMU_RELOAD if mapping the prefix failed KVM: s390: set the prefix initially properly
| * \ \ Merge tag 'kvm-s390-master-4.8-1' of ↵Radim Krčmář2016-08-121-1/+4
| |\ \ \ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | git://git.kernel.org/pub/scm/linux/kernel/git/kvms390/linux KVM: s390: Fixes for 4.8 (via kvm/master) Here are two fixes found by fuzzing of the ioctl interface. Both cases can trigger a WARN_ON_ONCE from user space.
| | * | | KVM: s390: reset KVM_REQ_MMU_RELOAD if mapping the prefix failedJulius Niedworok2016-08-121-1/+3
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | When triggering KVM_RUN without a user memory region being mapped (KVM_SET_USER_MEMORY_REGION) a validity intercept occurs. This could happen, if the user memory region was not mapped initially or if it was unmapped after the vcpu is initialized. The function kvm_s390_handle_requests checks for the KVM_REQ_MMU_RELOAD bit. The check function always clears this bit. If gmap_mprotect_notify returns an error code, the mapping failed, but the KVM_REQ_MMU_RELOAD was not set anymore. So the next time kvm_s390_handle_requests is called, the execution would fall trough the check for KVM_REQ_MMU_RELOAD. The bit needs to be resetted, if gmap_mprotect_notify returns an error code. Resetting the bit with kvm_make_request(KVM_REQ_MMU_RELOAD, vcpu) fixes the bug. Reviewed-by: David Hildenbrand <dahi@linux.vnet.ibm.com> Signed-off-by: Julius Niedworok <jniedwor@linux.vnet.ibm.com> Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
| | * | | KVM: s390: set the prefix initially properlyJulius Niedworok2016-08-121-0/+1
| | |/ / | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | When KVM_RUN is triggered on a VCPU without an initial reset, a validity intercept occurs. Setting the prefix will set the KVM_REQ_MMU_RELOAD bit initially, thus preventing the bug. Reviewed-by: David Hildenbrand <dahi@linux.vnet.ibm.com> Acked-by: Cornelia Huck <cornelia.huck@de.ibm.com> Signed-off-by: Julius Niedworok <jniedwor@linux.vnet.ibm.com> Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
| * | | MIPS: KVM: Propagate kseg0/mapped tlb fault errorsJames Hogan2016-08-122-12/+35
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Propagate errors from kvm_mips_handle_kseg0_tlb_fault() and kvm_mips_handle_mapped_seg_tlb_fault(), usually triggering an internal error since they normally indicate the guest accessed bad physical memory or the commpage in an unexpected way. Fixes: 858dd5d45733 ("KVM/MIPS32: MMU/TLB operations for the Guest.") Fixes: e685c689f3a8 ("KVM/MIPS32: Privileged instruction/target branch emulation.") Signed-off-by: James Hogan <james.hogan@imgtec.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: "Radim Krčmář" <rkrcmar@redhat.com> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: linux-mips@linux-mips.org Cc: kvm@vger.kernel.org Cc: <stable@vger.kernel.org> # 3.10.x- Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
| * | | MIPS: KVM: Fix gfn range check in kseg0 tlb faultsJames Hogan2016-08-121-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Two consecutive gfns are loaded into host TLB, so ensure the range check isn't off by one if guest_pmap_npages is odd. Fixes: 858dd5d45733 ("KVM/MIPS32: MMU/TLB operations for the Guest.") Signed-off-by: James Hogan <james.hogan@imgtec.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: "Radim Krčmář" <rkrcmar@redhat.com> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: linux-mips@linux-mips.org Cc: kvm@vger.kernel.org Cc: <stable@vger.kernel.org> # 3.10.x- Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
| * | | MIPS: KVM: Add missing gfn range checkJames Hogan2016-08-121-8/+15
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | kvm_mips_handle_mapped_seg_tlb_fault() calculates the guest frame number based on the guest TLB EntryLo values, however it is not range checked to ensure it lies within the guest_pmap. If the physical memory the guest refers to is out of range then dump the guest TLB and emit an internal error. Fixes: 858dd5d45733 ("KVM/MIPS32: MMU/TLB operations for the Guest.") Signed-off-by: James Hogan <james.hogan@imgtec.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: "Radim Krčmář" <rkrcmar@redhat.com> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: linux-mips@linux-mips.org Cc: kvm@vger.kernel.org Cc: <stable@vger.kernel.org> # 3.10.x- Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
| * | | MIPS: KVM: Fix mapped fault broken commpage handlingJames Hogan2016-08-121-21/+28
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | kvm_mips_handle_mapped_seg_tlb_fault() appears to map the guest page at virtual address 0 to PFN 0 if the guest has created its own mapping there. The intention is unclear, but it may have been an attempt to protect the zero page from being mapped to anything but the comm page in code paths you wouldn't expect from genuine commpage accesses (guest kernel mode cache instructions on that address, hitting trapping instructions when executing from that address with a coincidental TLB eviction during the KVM handling, and guest user mode accesses to that address). Fix this to check for mappings exactly at KVM_GUEST_COMMPAGE_ADDR (it may not be at address 0 since commit 42aa12e74e91 ("MIPS: KVM: Move commpage so 0x0 is unmapped")), and set the corresponding EntryLo to be interpreted as 0 (invalid). Fixes: 858dd5d45733 ("KVM/MIPS32: MMU/TLB operations for the Guest.") Signed-off-by: James Hogan <james.hogan@imgtec.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: "Radim Krčmář" <rkrcmar@redhat.com> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: linux-mips@linux-mips.org Cc: kvm@vger.kernel.org Cc: <stable@vger.kernel.org> # 3.10.x- Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
| * | | KVM: Protect device ops->create and list_add with kvm->lockChristoffer Dall2016-08-125-17/+27
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | KVM devices were manipulating list data structures without any form of synchronization, and some implementations of the create operations also suffered from a lack of synchronization. Now when we've split the xics create operation into create and init, we can hold the kvm->lock mutex while calling the create operation and when manipulating the devices list. The error path in the generic code gets slightly ugly because we have to take the mutex again and delete the device from the list, but holding the mutex during anon_inode_getfd or releasing/locking the mutex in the common non-error path seemed wrong. Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org> Reviewed-by: Paolo Bonzini <pbonzini@redhat.com> Acked-by: Christian Borntraeger <borntraeger@de.ibm.com> Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
| * | | KVM: PPC: Move xics_debugfs_init out of createChristoffer Dall2016-08-123-2/+17
| |/ / | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | As we are about to hold the kvm->lock during the create operation on KVM devices, we should move the call to xics_debugfs_init into its own function, since holding a mutex over extended amounts of time might not be a good idea. Introduce an init operation on the kvm_device_ops struct which cannot fail and call this, if configured, after the device has been created. Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org> Reviewed-by: Paolo Bonzini <pbonzini@redhat.com> Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
* | | Merge branch 'for-linus' of git://git.kernel.dk/linux-blockLinus Torvalds2016-08-1310-85/+160
|\ \ \ | |_|/ |/| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Pull block fixes from Jens Axboe: - an NVMe fix from Gabriel, fixing a suspend/resume issue on some setups - addition of a few missing entries in the block queue sysfs documentation, from Joe - a fix for a sparse shadow warning for the bvec iterator, from Johannes - a writeback deadlock involving raid issuing barriers, and not flushing the plug when we wakeup the flusher threads. From Konstantin - a set of patches for the NVMe target/loop/rdma code, from Roland and Sagi * 'for-linus' of git://git.kernel.dk/linux-block: bvec: avoid variable shadowing warning doc: update block/queue-sysfs.txt entries nvme: Suspend all queues before deletion mm, writeback: flush plugged IO in wakeup_flusher_threads() nvme-rdma: Remove unused includes nvme-rdma: start async event handler after reconnecting to a controller nvmet: Fix controller serial number inconsistency nvmet-rdma: Don't use the inline buffer in order to avoid allocation for small reads nvmet-rdma: Correctly handle RDMA device hot removal nvme-rdma: Make sure to shutdown the controller if we can nvme-loop: Remove duplicate call to nvme_remove_namespaces nvme-rdma: Free the I/O tags when we delete the controller nvme-rdma: Remove duplicate call to nvme_remove_namespaces nvme-rdma: Fix device removal handling nvme-rdma: Queue ns scanning after a sucessful reconnection nvme-rdma: Don't leak uninitialized memory in connect request private data
| * | bvec: avoid variable shadowing warningJohannes Berg2016-08-111-1/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Due to the (indirect) nesting of min(..., min(...)), sparse will show a variable shadowing warning whenever bvec.h is included. Avoid that by assigning the inner min() to a temporary variable first. Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: Jens Axboe <axboe@fb.com>
| * | doc: update block/queue-sysfs.txt entriesJoe Lawrence2016-08-111-0/+18
| | | | | | | | | | | | | | | | | | | | | Add descriptions for dax, io_poll, and write_same_max_bytes files. Signed-off-by: Joe Lawrence <joe.lawrence@redhat.com> Signed-off-by: Jens Axboe <axboe@fb.com>
| * | nvme: Suspend all queues before deletionGabriel Krisman Bertazi2016-08-111-12/+8Star
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | When nvme_delete_queue fails in the first pass of the nvme_disable_io_queues() loop, we return early, failing to suspend all of the IO queues. Later, on the nvme_pci_disable path, this causes us to disable MSI without actually having freed all the IRQs, which triggers the BUG_ON in free_msi_irqs(), as show below. This patch refactors nvme_disable_io_queues to suspend all queues before start submitting delete queue commands. This way, we ensure that we have at least returned every IRQ before continuing with the removal path. [ 487.529200] kernel BUG at ../drivers/pci/msi.c:368! cpu 0x46: Vector: 700 (Program Check) at [c0000078c5b83650] pc: c000000000627a50: free_msi_irqs+0x90/0x200 lr: c000000000627a40: free_msi_irqs+0x80/0x200 sp: c0000078c5b838d0 msr: 9000000100029033 current = 0xc0000078c5b40000 paca = 0xc000000002bd7600 softe: 0 irq_happened: 0x01 pid = 1376, comm = kworker/70:1H kernel BUG at ../drivers/pci/msi.c:368! Linux version 4.7.0.mainline+ (root@iod76) (gcc version 5.3.1 20160413 (Ubuntu/IBM 5.3.1-14ubuntu2.1) ) #104 SMP Fri Jul 29 09:20:17 CDT 2016 enter ? for help [c0000078c5b83920] d0000000363b0cd8 nvme_dev_disable+0x208/0x4f0 [nvme] [c0000078c5b83a10] d0000000363b12a4 nvme_timeout+0xe4/0x250 [nvme] [c0000078c5b83ad0] c0000000005690e4 blk_mq_rq_timed_out+0x64/0x110 [c0000078c5b83b40] c00000000056c930 bt_for_each+0x160/0x170 [c0000078c5b83bb0] c00000000056d928 blk_mq_queue_tag_busy_iter+0x78/0x110 [c0000078c5b83c00] c0000000005675d8 blk_mq_timeout_work+0xd8/0x1b0 [c0000078c5b83c50] c0000000000e8cf0 process_one_work+0x1e0/0x590 [c0000078c5b83ce0] c0000000000e9148 worker_thread+0xa8/0x660 [c0000078c5b83d80] c0000000000f2090 kthread+0x110/0x130 [c0000078c5b83e30] c0000000000095f0 ret_from_kernel_thread+0x5c/0x6c Signed-off-by: Gabriel Krisman Bertazi <krisman@linux.vnet.ibm.com> Cc: Brian King <brking@linux.vnet.ibm.com> Cc: Keith Busch <keith.busch@intel.com> Cc: linux-nvme@lists.infradead.org Signed-off-by: Jens Axboe <axboe@fb.com>
| * | mm, writeback: flush plugged IO in wakeup_flusher_threads()Konstantin Khlebnikov2016-08-101-0/+6
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | I've found funny live-lock between raid10 barriers during resync and memory controller hard limits. Inside mpage_readpages() task holds on to its plug bio which blocks the barrier in raid10. Its memory cgroup have no free memory thus the task goes into reclaimer but all reclaimable pages are dirty and cannot be written because raid10 is rebuilding and stuck on the barrier. Common flush of such IO in schedule() never happens, because the caller doesn't go to sleep. Lock is 'live' because changing memory limit or killing tasks which holds that stuck bio unblock whole progress. That was what happened in 3.18.x but I see no difference in upstream logic. Theoretically this might happen even without memory cgroup. Signed-off-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru> Signed-off-by: Jens Axboe <axboe@fb.com>
| * | Merge branch 'nvmf-4.8-rc' of git://git.infradead.org/nvme-fabrics into ↵Jens Axboe2016-08-086-72/+126
| |\ \ | | |/ | |/| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | for-linus Sagi writes: Mostly stability fixes for nvmet, rdma: - fix uninitialized rdma_cm private data from Roland. - rdma device removal handling (host and target). - fix controller disconnect during active mounts. - fix namespaces lost after fabric reconnects. - remove redundant calls to namespace removal (rdma, loop). - actually send controller shutdown when disconnecting. - reconnect fixes (ns rescan and aen requeue) - nvmet controller serial number inconsistency fix.
| | * nvme-rdma: Remove unused includesSagi Grimberg2016-08-041-3/+0Star
| | | | | | | | | | | | | | | Signed-off-by: Sagi Grimberg <sagi@grimberg.me> Reviewed-by: Steve Wise <swise@opengridcomputing.com>
| | * nvme-rdma: start async event handler after reconnecting to a controllerSagi Grimberg2016-08-041-0/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | When we reset or reconnect to a controller, we are cancelling the async event handler so we can safely re-establish resources, but we need to remember to start it again when we successfully reconnect. Signed-off-by: Sagi Grimberg <sagi@grimberg.me> Reviewed-by: Christoph Hellwig <hch@lst.de>
| | * nvmet: Fix controller serial number inconsistencySagi Grimberg2016-08-043-5/+6
| | | | | | | | | | | | | | | | | | | | | | | | | | | The host is allowed to issue identify as many times as it wants, we need to stay consistent when reporting the serial number for a given controller. Signed-off-by: Sagi Grimberg <sagi@grimberg.me> Reviewed-by: Christoph Hellwig <hch@lst.de>
| | * nvmet-rdma: Don't use the inline buffer in order to avoid allocation for ↵Sagi Grimberg2016-08-041-9/+4Star
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | small reads Under extreme conditions this might cause data corruptions. By doing that we we repost the buffer and then post this buffer for the device to send. If we happen to use shared receive queues the device might write to the buffer before it sends it (there is no ordering between send and recv queues). Without SRQs we probably won't get that if the host doesn't mis-behave and send more than we allowed it, but relying on that is not really a good idea. Signed-off-by: Sagi Grimberg <sagi@grimberg.me> Reviewed-by: Christoph Hellwig <hch@lst.de>
| | * nvmet-rdma: Correctly handle RDMA device hot removalSagi Grimberg2016-08-041-17/+70
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | When configuring a device attached listener, we may see device removal events. In this case we return a non-zero return code from the cm event handler which implicitly destroys the cm_id. It is possible that in the future the user will remove this listener and by that trigger a second call to rdma_destroy_id on an already destroyed cm_id -> BUG. In addition, when a queue bound (active session) cm_id generates a DEVICE_REMOVAL event we must guarantee all resources are cleaned up by the time we return from the event handler. Introduce nvmet_rdma_device_removal which addresses (or at least attempts to) both scenarios. Signed-off-by: Sagi Grimberg <sagi@grimberg.me> Reviewed-by: Christoph Hellwig <hch@lst.de>
| | * nvme-rdma: Make sure to shutdown the controller if we canSagi Grimberg2016-08-031-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Relying on ctrl state in nvme_rdma_shutdown_ctrl is wrong because it will never be NVME_CTRL_LIVE (delete_ctrl or reset_ctrl invoked it). Instead, check that the admin queue is connected. Note that it is safe because we can never see a copmeting thread trying to destroy the admin queue (reset or delete controller). Signed-off-by: Sagi Grimberg <sagi@grimberg.me> Reviewed-by: Christoph Hellwig <hch@lst.de>
| | * nvme-loop: Remove duplicate call to nvme_remove_namespacesSagi Grimberg2016-08-031-3/+1Star
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | nvme_uninit_ctrl already does that for us. Note that we reordered nvme_loop_shutdown_ctrl with nvme_uninit_ctrl but its safe because we want controller uninit to happen before we shutdown the transport resources. Signed-off-by: Sagi Grimberg <sagi@grimberg.me> Reviewed-by: Christoph Hellwig <hch@lst.de>
| | * nvme-rdma: Free the I/O tags when we delete the controllerSagi Grimberg2016-08-031-5/+7
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | If we wait until we free the controller (free_ctrl) we might lose our rdma device without any notification while we still have open resources (tags mrs and dma mappings). Instead, destroy the tags with their rdma resources once we delete the device and not when freeing it. Note that we don't do that in nvme_rdma_shutdown_ctrl because controller reset uses it as well and we want to give active I/O a chance to complete successfully. Signed-off-by: Sagi Grimberg <sagi@grimberg.me> Reviewed-by: Christoph Hellwig <hch@lst.de>
| | * nvme-rdma: Remove duplicate call to nvme_remove_namespacesSagi Grimberg2016-08-031-7/+10
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | nvme_uninit_ctrl already does that for us. Note that we reordered nvme_rdma_shutdown_ctrl and nvme_uninit_ctrl, this is perfectly fine because we actually want ctrl uninit (aen, scan cancellation and namespaces removal) to happen before we shutdown the rdma resources. Also, centralize the deletion work and the dead controller removal work code duplication into __nvme_rdma_shutdown_ctrl that accepts a shutdown boolean. Signed-off-by: Sagi Grimberg <sagi@grimberg.me> Reviewed-by: Christoph Hellwig <hch@lst.de>
| | * nvme-rdma: Fix device removal handlingSagi Grimberg2016-08-031-20/+21
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Device removal sequence may have crashed because the controller (and admin queue space) was freed before we destroyed the admin queue resources. Thus we want to destroy the admin queue and only then queue controller deletion and wait for it to complete. More specifically we: 1. own the controller deletion (make sure we are not competing with another deletion). 2. get rid of inflight reconnects if exists (which also destroy and create queues). 3. destroy the queue. 4. safely queue controller deletion (and wait for it to complete). Reported-by: Steve Wise <swise@opengridcomputing.com> Signed-off-by: Sagi Grimberg <sagi@grimberg.me> Reviewed-by: Christoph Hellwig <hch@lst.de>
generated by cgit v1.2.3-55-g7522 (git 2.39.0) at 2024-09-17 10:49:51 +0200