Skip to content

Commit 17f6f6f

Browse files
Thomas Hellströmlucasdemarchi
Thomas Hellström
authored and
lucasdemarchi
committed
drm/xe/bo: Fix an idle assertion for local bos
Before calling ttm_bo_populate() in the CPU fault path of a bo, we assert that the bo is not being migrated. However, for local bos we share the reservation object with other local bos that might be in the process of being migrated. Also some VM operations may attach USAGE_KERNEL fences to the common reservation object and trigger false positives from the assert. So remove the assert and instead wait for bo idle. This may unnecessarily wait for idle in some cases but since we're doing this wait later in the fault path anyway we might as well do it here as well. This fixes warnings like: Sep 25 14:56:23 desky kernel: ------------[ cut here ]------------ Sep 25 14:56:23 desky kernel: xe 0000:03:00.0: [drm] Assertion `dma_resv_test_signaled(tbo->base.resv, DMA_RESV_USAGE_KERNEL) || (tbo->ttm && ttm_tt_is_populated(tbo->ttm))` failed! platform: BATTLEMAGE subplatform: 1 graphics: Xe2_HPG 20.01 step A0 media: Xe2_HPM 13.01 step A1 Sep 25 14:56:23 desky kernel: WARNING: CPU: 6 PID: 24767 at drivers/gpu/drm/xe/xe_bo.c:1748 xe_bo_fault_migrate+0x1bb/0x300 [xe] Sep 25 14:56:23 desky kernel: Modules linked in: cpuid dm_crypt xt_conntrack nft_chain_nat xt_MASQUERADE nf_nat nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 bridge stp llc xfrm_user xfr> Sep 25 14:56:23 desky kernel: snd_soc_sdca snd_seq_midi prime_numbers coretemp snd_seq_midi_event drm_ttm_helper snd_hda_codec drm_buddy drm_exec snd_rawmidi snd_soc_core snd_hda_cor> Sep 25 14:56:23 desky kernel: CPU: 6 UID: 1000 PID: 24767 Comm: steamwebhelper Tainted: G U W 6.17.0-rc7+ torvalds#32 PREEMPT(voluntary) Sep 25 14:56:23 desky kernel: Tainted: [U]=USER, [W]=WARN Sep 25 14:56:23 desky kernel: Hardware name: Micro-Star International Co., Ltd. MS-7D36/PRO Z690-P DDR4 (MS-7D36), BIOS A.A1 10/18/2022 Sep 25 14:56:23 desky kernel: RIP: 0010:xe_bo_fault_migrate+0x1bb/0x300 [xe] Sep 25 14:56:23 desky kernel: Code: fa 64 29 f9 48 c7 c7 40 e0 d3 c1 51 48 c7 c1 c0 e3 d3 c1 52 4c 8b 45 c0 41 50 44 8b 4d c8 4d 89 e0 48 8b 55 a8 e8 25 27 95 ef <0f> 0b 48 83 c4 40 4> Sep 25 14:56:23 desky kernel: RSP: 0000:ffffae1ca88c7b10 EFLAGS: 00010286 Sep 25 14:56:23 desky kernel: RAX: 0000000000000000 RBX: ffff8d7cfd7e6800 RCX: 0000000000000027 Sep 25 14:56:23 desky kernel: RDX: ffff8d845019cec8 RSI: 0000000000000001 RDI: ffff8d845019cec0 Sep 25 14:56:23 desky kernel: RBP: ffffae1ca88c7bc8 R08: 0000000000000000 R09: 0000000000000000 Sep 25 14:56:23 desky kernel: R10: 0000000000000000 R11: 0000000000000004 R12: ffffffffc1db1faa Sep 25 14:56:23 desky kernel: R13: ffffffffc1db2ab4 R14: 0000000000000001 R15: ffffae1ca88c7bd8 Sep 25 14:56:23 desky kernel: FS: 00007fb1baf31940(0000) GS:ffff8d849c870000(0000) knlGS:0000000000000000 Sep 25 14:56:23 desky kernel: CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 Sep 25 14:56:23 desky kernel: CR2: 00007fb1b2860020 CR3: 00000001705a9004 CR4: 0000000000772ef0 Sep 25 14:56:23 desky kernel: PKRU: 55555558 Sep 25 14:56:23 desky kernel: Call Trace: Sep 25 14:56:23 desky kernel: <TASK> Sep 25 14:56:23 desky kernel: xe_bo_cpu_fault_fastpath+0x11e/0x220 [xe] Sep 25 14:56:23 desky kernel: xe_bo_cpu_fault+0x84/0x410 [xe] Sep 25 14:56:23 desky kernel: ? __x64_sys_mmap+0x33/0x50 Sep 25 14:56:23 desky kernel: ? x64_sys_call+0x1b2e/0x20d0 Sep 25 14:56:23 desky kernel: ? do_syscall_64+0x9d/0x1f0 Sep 25 14:56:23 desky kernel: ? __check_object_size+0x4a/0x2e0 Sep 25 14:56:23 desky kernel: __do_fault+0x36/0x190 Sep 25 14:56:23 desky kernel: do_fault+0xcf/0x570 Sep 25 14:56:23 desky kernel: __handle_mm_fault+0x92b/0xfe0 Sep 25 14:56:23 desky kernel: ? ktime_get_mono_fast_ns+0x39/0xd0 Sep 25 14:56:23 desky kernel: handle_mm_fault+0x164/0x2c0 Sep 25 14:56:23 desky kernel: do_user_addr_fault+0x2cb/0x840 Sep 25 14:56:23 desky kernel: exc_page_fault+0x75/0x180 Sep 25 14:56:23 desky kernel: asm_exc_page_fault+0x27/0x30 Sep 25 14:56:23 desky kernel: RIP: 0033:0x7fb1bc388bb7 Sep 25 14:56:23 desky kernel: Code: 48 ff c7 48 01 fe 48 8d 54 11 80 0f 1f 84 00 00 00 00 00 c5 fe 6f 0e c5 fe 6f 56 20 c5 fe 6f 5e 40 c5 fe 6f 66 60 48 83 ee 80 <c5> fd 7f 0f c5 fd 7> Sep 25 14:56:23 desky kernel: RSP: 002b:00007ffd7814fad8 EFLAGS: 00010207 Sep 25 14:56:23 desky kernel: RAX: 00007fb1b2860000 RBX: 0000000000000690 RCX: 00007fb1b2860000 Sep 25 14:56:23 desky kernel: RDX: 00007fb1b2860610 RSI: 0000556eda79f4c0 RDI: 00007fb1b2860020 Sep 25 14:56:23 desky kernel: RBP: 00007ffd7814fb60 R08: 0000000000000000 R09: 000000012be0e000 Sep 25 14:56:23 desky kernel: R10: 00007fb1b2860000 R11: 0000000000000246 R12: 0000556edd39a240 Sep 25 14:56:23 desky kernel: R13: 00007fb1b2dcb010 R14: 0000556eda79f420 R15: 0000000000000000 Sep 25 14:56:23 desky kernel: </TASK> Link: https://gitlab.freedesktop.org/drm/xe/kernel/-/issues/5250 Fixes: c2ae94c ("drm/xe: Convert the CPU fault handler for exhaustive eviction") Cc: Matthew Brost <matthew.brost@intel.com> Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com> Reviewed-by: Matthew Brost <matthew.brost@intel.com> Link: https://lore.kernel.org/r/20250929112649.6131-1-thomas.hellstrom@linux.intel.com (cherry picked from commit 8f1756a) Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
1 parent 3734c81 commit 17f6f6f

File tree

1 file changed

+23
-11
lines changed

1 file changed

+23
-11
lines changed

‎drivers/gpu/drm/xe/xe_bo.c‎

Lines changed: 23 additions & 11 deletions
Original file line numberDiff line numberDiff line change
@@ -1737,6 +1737,24 @@ static bool should_migrate_to_smem(struct xe_bo *bo)
17371737
bo->attr.atomic_access == DRM_XE_ATOMIC_CPU;
17381738
}
17391739

1740+
static int xe_bo_wait_usage_kernel(struct xe_bo *bo, struct ttm_operation_ctx *ctx)
1741+
{
1742+
long lerr;
1743+
1744+
if (ctx->no_wait_gpu)
1745+
return dma_resv_test_signaled(bo->ttm.base.resv, DMA_RESV_USAGE_KERNEL) ?
1746+
0 : -EBUSY;
1747+
1748+
lerr = dma_resv_wait_timeout(bo->ttm.base.resv, DMA_RESV_USAGE_KERNEL,
1749+
ctx->interruptible, MAX_SCHEDULE_TIMEOUT);
1750+
if (lerr < 0)
1751+
return lerr;
1752+
if (lerr == 0)
1753+
return -EBUSY;
1754+
1755+
return 0;
1756+
}
1757+
17401758
/* Populate the bo if swapped out, or migrate if the access mode requires that. */
17411759
static int xe_bo_fault_migrate(struct xe_bo *bo, struct ttm_operation_ctx *ctx,
17421760
struct drm_exec *exec)
@@ -1745,10 +1763,9 @@ static int xe_bo_fault_migrate(struct xe_bo *bo, struct ttm_operation_ctx *ctx,
17451763
int err = 0;
17461764

17471765
if (ttm_manager_type(tbo->bdev, tbo->resource->mem_type)->use_tt) {
1748-
xe_assert(xe_bo_device(bo),
1749-
dma_resv_test_signaled(tbo->base.resv, DMA_RESV_USAGE_KERNEL) ||
1750-
(tbo->ttm && ttm_tt_is_populated(tbo->ttm)));
1751-
err = ttm_bo_populate(&bo->ttm, ctx);
1766+
err = xe_bo_wait_usage_kernel(bo, ctx);
1767+
if (!err)
1768+
err = ttm_bo_populate(&bo->ttm, ctx);
17521769
} else if (should_migrate_to_smem(bo)) {
17531770
xe_assert(xe_bo_device(bo), bo->flags & XE_BO_FLAG_SYSTEM);
17541771
err = xe_bo_migrate(bo, XE_PL_TT, ctx, exec);
@@ -1922,7 +1939,6 @@ static vm_fault_t xe_bo_cpu_fault(struct vm_fault *vmf)
19221939
.no_wait_gpu = false,
19231940
.gfp_retry_mayfail = retry_after_wait,
19241941
};
1925-
long lerr;
19261942

19271943
err = drm_exec_lock_obj(&exec, &tbo->base);
19281944
drm_exec_retry_on_contention(&exec);
@@ -1942,13 +1958,9 @@ static vm_fault_t xe_bo_cpu_fault(struct vm_fault *vmf)
19421958
break;
19431959
}
19441960

1945-
lerr = dma_resv_wait_timeout(tbo->base.resv,
1946-
DMA_RESV_USAGE_KERNEL, true,
1947-
MAX_SCHEDULE_TIMEOUT);
1948-
if (lerr < 0) {
1949-
err = lerr;
1961+
err = xe_bo_wait_usage_kernel(bo, &tctx);
1962+
if (err)
19501963
break;
1951-
}
19521964

19531965
if (!retry_after_wait)
19541966
ret = __xe_bo_cpu_fault(vmf, xe, bo);

0 commit comments

Comments
 (0)