mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-28 11:18:45 +07:00
15c344f4d0
lockdep doesn't like us taking the mm->mmap_sem inside the get_pages
callback for a couple of reasons. The straightforward deadlock:
[13755.434059] =============================================
[13755.434061] [ INFO: possible recursive locking detected ]
[13755.434064] 4.11.0-rc1-CI-CI_DRM_297+ #1 Tainted: G U
[13755.434066] ---------------------------------------------
[13755.434068] gem_userptr_bli/8398 is trying to acquire lock:
[13755.434070] (&mm->mmap_sem){++++++}, at: [<ffffffffa00c988a>] i915_gem_userptr_get_pages+0x5a/0x2e0 [i915]
[13755.434096]
but task is already holding lock:
[13755.434098] (&mm->mmap_sem){++++++}, at: [<ffffffff8104d485>] __do_page_fault+0x105/0x560
[13755.434105]
other info that might help us debug this:
[13755.434108] Possible unsafe locking scenario:
[13755.434110] CPU0
[13755.434111] ----
[13755.434112] lock(&mm->mmap_sem);
[13755.434115] lock(&mm->mmap_sem);
[13755.434117]
*** DEADLOCK ***
[13755.434121] May be due to missing lock nesting notation
[13755.434126] 2 locks held by gem_userptr_bli/8398:
[13755.434128] #0: (&mm->mmap_sem){++++++}, at: [<ffffffff8104d485>] __do_page_fault+0x105/0x560
[13755.434135] #1: (&obj->mm.lock){+.+.+.}, at: [<ffffffffa00b887d>] __i915_gem_object_get_pages+0x1d/0x70 [i915]
[13755.434156]
stack backtrace:
[13755.434161] CPU: 3 PID: 8398 Comm: gem_userptr_bli Tainted: G U 4.11.0-rc1-CI-CI_DRM_297+ #1
[13755.434165] Hardware name: GIGABYTE GB-BKi7(H)A-7500/MFLP7AP-00, BIOS F4 02/20/2017
[13755.434169] Call Trace:
[13755.434174] dump_stack+0x67/0x92
[13755.434178] __lock_acquire+0x133a/0x1b50
[13755.434182] lock_acquire+0xc9/0x220
[13755.434200] ? i915_gem_userptr_get_pages+0x5a/0x2e0 [i915]
[13755.434204] down_read+0x42/0x70
[13755.434221] ? i915_gem_userptr_get_pages+0x5a/0x2e0 [i915]
[13755.434238] i915_gem_userptr_get_pages+0x5a/0x2e0 [i915]
[13755.434255] ____i915_gem_object_get_pages+0x25/0x60 [i915]
[13755.434272] __i915_gem_object_get_pages+0x59/0x70 [i915]
[13755.434288] i915_gem_fault+0x397/0x6a0 [i915]
[13755.434304] ? i915_gem_fault+0x1a1/0x6a0 [i915]
[13755.434308] ? __lock_acquire+0x449/0x1b50
[13755.434311] ? __lock_acquire+0x449/0x1b50
[13755.434315] ? vm_mmap_pgoff+0xa9/0xd0
[13755.434318] __do_fault+0x19/0x70
[13755.434321] __handle_mm_fault+0x863/0xe50
[13755.434325] handle_mm_fault+0x17f/0x370
[13755.434329] ? handle_mm_fault+0x40/0x370
[13755.434332] __do_page_fault+0x279/0x560
[13755.434336] do_page_fault+0xc/0x10
[13755.434339] page_fault+0x22/0x30
[13755.434342] RIP: 0033:0x7f5ab91b5880
[13755.434345] RSP: 002b:00007fff62922218 EFLAGS: 00010216
[13755.434348] RAX: 0000000000b74500 RBX: 00007f5ab7f81000 RCX: 0000000000000000
[13755.434352] RDX: 0000000000100000 RSI: 00007f5ab7f81000 RDI: 00007f5aba61c000
[13755.434355] RBP: 00007f5aba61c000 R08: 0000000000000007 R09: 0000000100000000
[13755.434359] R10: 000000000000037d R11: 00007f5ab91b5840 R12: 0000000000000001
[13755.434362] R13: 0000000000000005 R14: 0000000000000001 R15: 0000000000000000
and cyclic deadlocks:
[ 2566.458979] ======================================================
[ 2566.459054] [ INFO: possible circular locking dependency detected ]
[ 2566.459127] 4.11.0-rc1+ #26 Not tainted
[ 2566.459194] -------------------------------------------------------
[ 2566.459266] gem_streaming_w/759 is trying to acquire lock:
[ 2566.459334] (&obj->mm.lock){+.+.+.}, at: [<ffffffffa034bc80>] i915_gem_object_pin_pages+0x0/0xc0 [i915]
[ 2566.459605]
[ 2566.459605] but task is already holding lock:
[ 2566.459699] (&mm->mmap_sem){++++++}, at: [<ffffffff8106fd11>] __do_page_fault+0x121/0x500
[ 2566.459814]
[ 2566.459814] which lock already depends on the new lock.
[ 2566.459814]
[ 2566.459934]
[ 2566.459934] the existing dependency chain (in reverse order) is:
[ 2566.460030]
[ 2566.460030] -> #1 (&mm->mmap_sem){++++++}:
[ 2566.460139] lock_acquire+0xfe/0x220
[ 2566.460214] down_read+0x4e/0x90
[ 2566.460444] i915_gem_userptr_get_pages+0x6e/0x340 [i915]
[ 2566.460669] ____i915_gem_object_get_pages+0x8b/0xd0 [i915]
[ 2566.460900] __i915_gem_object_get_pages+0x6a/0x80 [i915]
[ 2566.461132] __i915_vma_do_pin+0x7fa/0x930 [i915]
[ 2566.461352] eb_add_vma+0x67b/0x830 [i915]
[ 2566.461572] eb_lookup_vmas+0xafe/0x1010 [i915]
[ 2566.461792] i915_gem_do_execbuffer+0x715/0x2870 [i915]
[ 2566.462012] i915_gem_execbuffer2+0x106/0x2b0 [i915]
[ 2566.462152] drm_ioctl+0x36c/0x670 [drm]
[ 2566.462236] do_vfs_ioctl+0x12c/0xa60
[ 2566.462317] SyS_ioctl+0x41/0x70
[ 2566.462399] entry_SYSCALL_64_fastpath+0x1c/0xb1
[ 2566.462477]
[ 2566.462477] -> #0 (&obj->mm.lock){+.+.+.}:
[ 2566.462587] __lock_acquire+0x1602/0x1790
[ 2566.462661] lock_acquire+0xfe/0x220
[ 2566.462893] i915_gem_object_pin_pages+0x4c/0xc0 [i915]
[ 2566.463116] i915_gem_fault+0x2c2/0x8c0 [i915]
[ 2566.463197] __do_fault+0x42/0x130
[ 2566.463276] __handle_mm_fault+0x92c/0x1280
[ 2566.463356] handle_mm_fault+0x1e2/0x440
[ 2566.463443] __do_page_fault+0x1c4/0x500
[ 2566.463529] do_page_fault+0xc/0x10
[ 2566.463613] page_fault+0x1f/0x30
[ 2566.463693]
[ 2566.463693] other info that might help us debug this:
[ 2566.463693]
[ 2566.463820] Possible unsafe locking scenario:
[ 2566.463820]
[ 2566.463918] CPU0 CPU1
[ 2566.463988] ---- ----
[ 2566.464068] lock(&mm->mmap_sem);
[ 2566.464143] lock(&obj->mm.lock);
[ 2566.464226] lock(&mm->mmap_sem);
[ 2566.464304] lock(&obj->mm.lock);
[ 2566.464378]
[ 2566.464378] *** DEADLOCK ***
[ 2566.464378]
[ 2566.464504] 1 lock held by gem_streaming_w/759:
[ 2566.464576] #0: (&mm->mmap_sem){++++++}, at: [<ffffffff8106fd11>] __do_page_fault+0x121/0x500
[ 2566.464699]
[ 2566.464699] stack backtrace:
[ 2566.464801] CPU: 0 PID: 759 Comm: gem_streaming_w Not tainted 4.11.0-rc1+ #26
[ 2566.464881] Hardware name: GIGABYTE GB-BXBT-1900/MZBAYAB-00, BIOS F8 03/02/2016
[ 2566.464983] Call Trace:
[ 2566.465061] dump_stack+0x68/0x9f
[ 2566.465144] print_circular_bug+0x20b/0x260
[ 2566.465234] __lock_acquire+0x1602/0x1790
[ 2566.465323] ? debug_check_no_locks_freed+0x1a0/0x1a0
[ 2566.465564] ? i915_gem_object_wait+0x238/0x650 [i915]
[ 2566.465657] ? debug_lockdep_rcu_enabled.part.4+0x1a/0x30
[ 2566.465749] lock_acquire+0xfe/0x220
[ 2566.465985] ? i915_sg_trim+0x1b0/0x1b0 [i915]
[ 2566.466223] i915_gem_object_pin_pages+0x4c/0xc0 [i915]
[ 2566.466461] ? i915_sg_trim+0x1b0/0x1b0 [i915]
[ 2566.466699] i915_gem_fault+0x2c2/0x8c0 [i915]
[ 2566.466939] ? i915_gem_pwrite_ioctl+0xce0/0xce0 [i915]
[ 2566.467030] ? __lock_acquire+0x642/0x1790
[ 2566.467122] ? __lock_acquire+0x642/0x1790
[ 2566.467209] ? debug_lockdep_rcu_enabled+0x35/0x40
[ 2566.467299] ? get_unmapped_area+0x1b4/0x1d0
[ 2566.467387] __do_fault+0x42/0x130
[ 2566.467474] __handle_mm_fault+0x92c/0x1280
[ 2566.467564] ? __pmd_alloc+0x1e0/0x1e0
[ 2566.467651] ? vm_mmap_pgoff+0x160/0x190
[ 2566.467740] ? handle_mm_fault+0x111/0x440
[ 2566.467827] handle_mm_fault+0x1e2/0x440
[ 2566.467914] ? handle_mm_fault+0x5d/0x440
[ 2566.468002] __do_page_fault+0x1c4/0x500
[ 2566.468090] do_page_fault+0xc/0x10
[ 2566.468180] page_fault+0x1f/0x30
[ 2566.468263] RIP: 0033:0x557895ced32a
[ 2566.468337] RSP: 002b:00007fffd6dd8a10 EFLAGS: 00010202
[ 2566.468419] RAX: 00007f659a4db000 RBX: 0000000000000003 RCX: 00007f659ad032da
[ 2566.468501] RDX: 0000000000000000 RSI: 0000000000100000 RDI: 0000000000000000
[ 2566.468586] RBP: 0000000000000007 R08: 0000000000000003 R09: 0000000100000000
[ 2566.468667] R10: 0000000000000001 R11: 0000000000000246 R12: 0000557895ceda60
[ 2566.468749] R13: 0000000000000001 R14: 00007fffd6dd8ac0 R15: 00007f659a4db000
By checking the status of the gup worker (serialized by the
obj->mm.lock) we can determine whether it is still active, has failed or
has succeeded. If the worker is still active (or failed), we know that
it cannot be bound and so we can skip taking struct_mutex (risking
potential recursion). As we check the worker status, we mark it to
discard any partial results, forcing us to restart on the next
get_pages.
Reported-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Fixes:
|
||
|---|---|---|
| .. | ||
| gvt | ||
| selftests | ||
| dvo_ch7xxx.c | ||
| dvo_ch7017.c | ||
| dvo_ivch.c | ||
| dvo_ns2501.c | ||
| dvo_sil164.c | ||
| dvo_tfp410.c | ||
| dvo.h | ||
| i915_cmd_parser.c | ||
| i915_debugfs.c | ||
| i915_drv.c | ||
| i915_drv.h | ||
| i915_gem_batch_pool.c | ||
| i915_gem_batch_pool.h | ||
| i915_gem_clflush.c | ||
| i915_gem_clflush.h | ||
| i915_gem_context.c | ||
| i915_gem_context.h | ||
| i915_gem_dmabuf.c | ||
| i915_gem_evict.c | ||
| i915_gem_execbuffer.c | ||
| i915_gem_fence_reg.c | ||
| i915_gem_fence_reg.h | ||
| i915_gem_gtt.c | ||
| i915_gem_gtt.h | ||
| i915_gem_internal.c | ||
| i915_gem_object.h | ||
| i915_gem_render_state.c | ||
| i915_gem_render_state.h | ||
| i915_gem_request.c | ||
| i915_gem_request.h | ||
| i915_gem_shrinker.c | ||
| i915_gem_stolen.c | ||
| i915_gem_tiling.c | ||
| i915_gem_timeline.c | ||
| i915_gem_timeline.h | ||
| i915_gem_userptr.c | ||
| i915_gem.c | ||
| i915_gem.h | ||
| i915_gpu_error.c | ||
| i915_guc_reg.h | ||
| i915_guc_submission.c | ||
| i915_ioc32.c | ||
| i915_irq.c | ||
| i915_memcpy.c | ||
| i915_mm.c | ||
| i915_oa_hsw.c | ||
| i915_oa_hsw.h | ||
| i915_params.c | ||
| i915_params.h | ||
| i915_pci.c | ||
| i915_perf.c | ||
| i915_pvinfo.h | ||
| i915_reg.h | ||
| i915_selftest.h | ||
| i915_suspend.c | ||
| i915_sw_fence.c | ||
| i915_sw_fence.h | ||
| i915_sysfs.c | ||
| i915_trace_points.c | ||
| i915_trace.h | ||
| i915_utils.h | ||
| i915_vgpu.c | ||
| i915_vgpu.h | ||
| i915_vma.c | ||
| i915_vma.h | ||
| intel_acpi.c | ||
| intel_atomic_plane.c | ||
| intel_atomic.c | ||
| intel_audio.c | ||
| intel_bios.c | ||
| intel_bios.h | ||
| intel_breadcrumbs.c | ||
| intel_cdclk.c | ||
| intel_color.c | ||
| intel_crt.c | ||
| intel_csr.c | ||
| intel_ddi.c | ||
| intel_device_info.c | ||
| intel_display.c | ||
| intel_dp_aux_backlight.c | ||
| intel_dp_link_training.c | ||
| intel_dp_mst.c | ||
| intel_dp.c | ||
| intel_dpio_phy.c | ||
| intel_dpll_mgr.c | ||
| intel_dpll_mgr.h | ||
| intel_drv.h | ||
| intel_dsi_dcs_backlight.c | ||
| intel_dsi_pll.c | ||
| intel_dsi_vbt.c | ||
| intel_dsi.c | ||
| intel_dsi.h | ||
| intel_dvo.c | ||
| intel_engine_cs.c | ||
| intel_fbc.c | ||
| intel_fbdev.c | ||
| intel_fifo_underrun.c | ||
| intel_frontbuffer.c | ||
| intel_frontbuffer.h | ||
| intel_guc_fwif.h | ||
| intel_guc_loader.c | ||
| intel_guc_log.c | ||
| intel_gvt.c | ||
| intel_gvt.h | ||
| intel_hangcheck.c | ||
| intel_hdmi.c | ||
| intel_hotplug.c | ||
| intel_huc.c | ||
| intel_i2c.c | ||
| intel_lpe_audio.c | ||
| intel_lrc.c | ||
| intel_lrc.h | ||
| intel_lspcon.c | ||
| intel_lvds.c | ||
| intel_mocs.c | ||
| intel_mocs.h | ||
| intel_modes.c | ||
| intel_opregion.c | ||
| intel_overlay.c | ||
| intel_panel.c | ||
| intel_pipe_crc.c | ||
| intel_pm.c | ||
| intel_psr.c | ||
| intel_renderstate_gen6.c | ||
| intel_renderstate_gen7.c | ||
| intel_renderstate_gen8.c | ||
| intel_renderstate_gen9.c | ||
| intel_renderstate.h | ||
| intel_ringbuffer.c | ||
| intel_ringbuffer.h | ||
| intel_runtime_pm.c | ||
| intel_sdvo_regs.h | ||
| intel_sdvo.c | ||
| intel_sideband.c | ||
| intel_sprite.c | ||
| intel_tv.c | ||
| intel_uc.c | ||
| intel_uc.h | ||
| intel_uncore.c | ||
| intel_vbt_defs.h | ||
| Kconfig | ||
| Kconfig.debug | ||
| Makefile | ||