From b7f21899276a3e06ea3c98d0b3771f09eefc6e3d Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Mon, 26 Nov 2018 12:28:21 +0000 Subject: drm/i915/ringbuffer: 2-step restart We may be simply restarting too fast for the culmudgeonly gen3/gen4 as we still see missing interrupts following a reset. So let's try restarting a little slower, first wake up the ring empty and then tell it about the work it has to perform. References: https://bugs.freedesktop.org/show_bug.cgi?id=108735 Signed-off-by: Chris Wilson Reviewed-by: Joonas Lahtinen Link: https://patchwork.freedesktop.org/patch/msgid/20181126122821.4537-1-chris@chris-wilson.co.uk --- drivers/gpu/drm/i915/intel_ringbuffer.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'drivers/gpu/drm/i915/intel_ringbuffer.c') diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c index 87eebc13c0d8..e18a64d41843 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.c +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c @@ -546,10 +546,11 @@ static int init_ring_common(struct intel_engine_cs *engine) /* Check that the ring offsets point within the ring! */ GEM_BUG_ON(!intel_ring_offset_valid(ring, ring->head)); GEM_BUG_ON(!intel_ring_offset_valid(ring, ring->tail)); - intel_ring_update_space(ring); + + /* First wake the ring up to an empty/idle ring */ I915_WRITE_HEAD(engine, ring->head); - I915_WRITE_TAIL(engine, ring->tail); + I915_WRITE_TAIL(engine, ring->head); (void)I915_READ_TAIL(engine); I915_WRITE_CTL(engine, RING_CTL_SIZE(ring->size) | RING_VALID); @@ -574,6 +575,12 @@ static int init_ring_common(struct intel_engine_cs *engine) if (INTEL_GEN(dev_priv) > 2) I915_WRITE_MODE(engine, _MASKED_BIT_DISABLE(STOP_RING)); + /* Now awake, let it get started */ + if (ring->tail != ring->head) { + I915_WRITE_TAIL(engine, ring->tail); + (void)I915_READ_TAIL(engine); + } + /* Papering over lost _interrupts_ immediately following the restart */ intel_engine_wakeup(engine); out: -- cgit v1.2.3 From a2538cbc989cfab007149dddd1b63a0ba509370a Mon Sep 17 00:00:00 2001 From: Tvrtko Ursulin Date: Thu, 29 Nov 2018 13:41:28 +0000 Subject: drm/i915: Remove whitelist application from ringbuffer backend There is no white-listing before Gen8 and after the removal ringbuffer support for these platforms we can remove the call to this no-op. Signed-off-by: Tvrtko Ursulin Reviewed-by: Chris Wilson Link: https://patchwork.freedesktop.org/patch/msgid/20181129134128.7994-1-tvrtko.ursulin@linux.intel.com --- drivers/gpu/drm/i915/intel_ringbuffer.c | 2 -- 1 file changed, 2 deletions(-) (limited to 'drivers/gpu/drm/i915/intel_ringbuffer.c') diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c index e18a64d41843..28ae1e436ea6 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.c +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c @@ -667,8 +667,6 @@ static int init_render_ring(struct intel_engine_cs *engine) if (ret) return ret; - intel_whitelist_workarounds_apply(engine); - /* WaTimedSingleVertexDispatch:cl,bw,ctg,elk,ilk,snb */ if (IS_GEN(dev_priv, 4, 6)) I915_WRITE(MI_MODE, _MASKED_BIT_ENABLE(VS_TIMER_DISPATCH)); -- cgit v1.2.3 From f36c071f6344e0a335ed4b4e0b3a38c0dd54648b Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Mon, 3 Dec 2018 11:36:56 +0000 Subject: drm/i915/ringbuffer: Clear semaphore sync registers on ring init Ensure that the sync registers are cleared every time we restart the ring to avoid stale values from creeping in from random neutrinos. Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=108888 Signed-off-by: Chris Wilson Reviewed-by: Mika Kuoppala Link: https://patchwork.freedesktop.org/patch/msgid/20181203113701.12106-3-chris@chris-wilson.co.uk --- drivers/gpu/drm/i915/intel_ringbuffer.c | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'drivers/gpu/drm/i915/intel_ringbuffer.c') diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c index 28ae1e436ea6..d81eaf5f6b3e 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.c +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c @@ -529,6 +529,13 @@ static int init_ring_common(struct intel_engine_cs *engine) intel_engine_reset_breadcrumbs(engine); + if (HAS_LEGACY_SEMAPHORES(engine->i915)) { + I915_WRITE(RING_SYNC_0(engine->mmio_base), 0); + I915_WRITE(RING_SYNC_1(engine->mmio_base), 0); + if (HAS_VEBOX(dev_priv)) + I915_WRITE(RING_SYNC_2(engine->mmio_base), 0); + } + /* Enforce ordering by reading HEAD register back */ I915_READ_HEAD(engine); -- cgit v1.2.3 From 3800960afe158fa3d4c622774eaf59a9b3960a82 Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Mon, 3 Dec 2018 11:36:55 +0000 Subject: drm/i915: Complete the fences as they are cancelled due to wedging We inspect the requests under the assumption that they will be marked as completed when they are removed from the queue. Currently however, in the process of wedging the requests will be removed from the queue before they are completed, so rearrange the code to complete the fences before the locks are dropped. <1>[ 354.473346] BUG: unable to handle kernel NULL pointer dereference at 0000000000000250 <6>[ 354.473363] PGD 0 P4D 0 <4>[ 354.473370] Oops: 0000 [#1] PREEMPT SMP PTI <4>[ 354.473380] CPU: 0 PID: 4470 Comm: gem_eio Tainted: G U 4.20.0-rc4-CI-CI_DRM_5216+ #1 <4>[ 354.473393] Hardware name: Intel Corporation NUC7CJYH/NUC7JYB, BIOS JYGLKCPX.86A.0027.2018.0125.1347 01/25/2018 <4>[ 354.473480] RIP: 0010:__i915_schedule+0x311/0x5e0 [i915] <4>[ 354.473490] Code: 49 89 44 24 20 4d 89 4c 24 28 4d 89 29 44 39 b3 a0 04 00 00 7d 3a 41 8b 44 24 78 85 c0 74 13 48 8b 93 78 04 00 00 48 83 e2 fc <39> 82 50 02 00 00 79 1e 44 89 b3 a0 04 00 00 48 8d bb d0 03 00 00 <4>[ 354.473515] RSP: 0018:ffffc900001bba90 EFLAGS: 00010046 <4>[ 354.473524] RAX: 0000000000000003 RBX: ffff8882624c8008 RCX: f34a737800000000 <4>[ 354.473535] RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffff8882624c8048 <4>[ 354.473545] RBP: ffffc900001bbab0 R08: 000000005963f1f1 R09: 0000000000000000 <4>[ 354.473556] R10: ffffc900001bba10 R11: ffff8882624c8060 R12: ffff88824fdd7b98 <4>[ 354.473567] R13: ffff88824fdd7bb8 R14: 0000000000000001 R15: ffff88824fdd7750 <4>[ 354.473578] FS: 00007f44b4b5b980(0000) GS:ffff888277e00000(0000) knlGS:0000000000000000 <4>[ 354.473590] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 <4>[ 354.473599] CR2: 0000000000000250 CR3: 000000026976e000 CR4: 0000000000340ef0 <4>[ 354.473611] Call Trace: <4>[ 354.473622] ? lock_acquire+0xa6/0x1c0 <4>[ 354.473677] ? i915_schedule_bump_priority+0x57/0xd0 [i915] <4>[ 354.473736] i915_schedule_bump_priority+0x72/0xd0 [i915] <4>[ 354.473792] i915_request_wait+0x4db/0x840 [i915] <4>[ 354.473804] ? get_pwq.isra.4+0x2c/0x50 <4>[ 354.473813] ? ___preempt_schedule+0x16/0x18 <4>[ 354.473824] ? wake_up_q+0x70/0x70 <4>[ 354.473831] ? wake_up_q+0x70/0x70 <4>[ 354.473882] ? gen6_rps_boost+0x118/0x120 [i915] <4>[ 354.473936] i915_gem_object_wait_fence+0x8a/0x110 [i915] <4>[ 354.473991] i915_gem_object_wait+0x113/0x500 [i915] <4>[ 354.474047] i915_gem_wait_ioctl+0x11c/0x2f0 [i915] <4>[ 354.474101] ? i915_gem_unset_wedged+0x210/0x210 [i915] <4>[ 354.474113] drm_ioctl_kernel+0x81/0xf0 <4>[ 354.474123] drm_ioctl+0x2de/0x390 <4>[ 354.474175] ? i915_gem_unset_wedged+0x210/0x210 [i915] <4>[ 354.474187] ? finish_task_switch+0x95/0x260 <4>[ 354.474197] ? lock_acquire+0xa6/0x1c0 <4>[ 354.474207] do_vfs_ioctl+0xa0/0x6e0 <4>[ 354.474217] ? __fget+0xfc/0x1e0 <4>[ 354.474225] ksys_ioctl+0x35/0x60 <4>[ 354.474233] __x64_sys_ioctl+0x11/0x20 <4>[ 354.474241] do_syscall_64+0x55/0x190 <4>[ 354.474251] entry_SYSCALL_64_after_hwframe+0x49/0xbe <4>[ 354.474260] RIP: 0033:0x7f44b3de65d7 <4>[ 354.474267] Code: b3 66 90 48 8b 05 b1 48 2d 00 64 c7 00 26 00 00 00 48 c7 c0 ff ff ff ff c3 66 2e 0f 1f 84 00 00 00 00 00 b8 10 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d 81 48 2d 00 f7 d8 64 89 01 48 <4>[ 354.474293] RSP: 002b:00007fff974948e8 EFLAGS: 00000246 ORIG_RAX: 0000000000000010 <4>[ 354.474305] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f44b3de65d7 <4>[ 354.474316] RDX: 00007fff97494940 RSI: 00000000c010646c RDI: 0000000000000007 <4>[ 354.474327] RBP: 00007fff97494940 R08: 0000000000000000 R09: 00007f44b40bbc40 <4>[ 354.474337] R10: 0000000000000000 R11: 0000000000000246 R12: 00000000c010646c <4>[ 354.474348] R13: 0000000000000007 R14: 0000000000000000 R15: 0000000000000000 v2: Avoid floating requests. v3: Can't call dma_fence_signal() under the timeline lock! v4: Can't call dma_fence_signal() from inside another fence either. Signed-off-by: Chris Wilson Reviewed-by: Tvrtko Ursulin Link: https://patchwork.freedesktop.org/patch/msgid/20181203113701.12106-2-chris@chris-wilson.co.uk --- drivers/gpu/drm/i915/intel_ringbuffer.c | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) (limited to 'drivers/gpu/drm/i915/intel_ringbuffer.c') diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c index d81eaf5f6b3e..81b10d85b738 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.c +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c @@ -755,9 +755,18 @@ static void cancel_requests(struct intel_engine_cs *engine) /* Mark all submitted requests as skipped. */ list_for_each_entry(request, &engine->timeline.requests, link) { GEM_BUG_ON(!request->global_seqno); - if (!i915_request_completed(request)) - dma_fence_set_error(&request->fence, -EIO); + + if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, + &request->fence.flags)) + continue; + + dma_fence_set_error(&request->fence, -EIO); } + + intel_write_status_page(engine, + I915_GEM_HWS_INDEX, + intel_engine_last_submit(engine)); + /* Remaining _unready_ requests will be nop'ed when submitted */ spin_unlock_irqrestore(&engine->timeline.lock, flags); -- cgit v1.2.3 From 452420d22d5b41256a0bb82402a797295e525da9 Mon Sep 17 00:00:00 2001 From: Tvrtko Ursulin Date: Mon, 3 Dec 2018 13:33:57 +0000 Subject: drm/i915: Fuse per-context workaround handling with the common framework Convert the per context workaround handling code to run against the newly introduced common workaround framework and fuse the two to use the existing smarter list add helper, the one which does the sorted insert and merges registers where possible. This completes migration of all four classes of workarounds onto the common framework. Existing macros are kept untouched for smaller code churn. v2: * Rename to list name ctx_wa_list and move from dev_priv to engine. v3: * API rename and parameters tweaking. (Chris Wilson) Signed-off-by: Tvrtko Ursulin Reviewed-by: Chris Wilson Link: https://patchwork.freedesktop.org/patch/msgid/20181203133357.10341-1-tvrtko.ursulin@linux.intel.com --- drivers/gpu/drm/i915/intel_ringbuffer.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/gpu/drm/i915/intel_ringbuffer.c') diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c index 81b10d85b738..7f88df5bff09 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.c +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c @@ -656,7 +656,7 @@ static int intel_rcs_ctx_init(struct i915_request *rq) { int ret; - ret = intel_ctx_workarounds_emit(rq); + ret = intel_engine_emit_ctx_wa(rq); if (ret != 0) return ret; -- cgit v1.2.3 From 5179749925933575a67f9d8f16d0cc204f98a29f Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Tue, 4 Dec 2018 14:15:16 +0000 Subject: drm/i915: Allocate a common scratch page Currently we allocate a scratch page for each engine, but since we only ever write into it for post-sync operations, it is not exposed to userspace nor do we care for coherency. As we then do not care about its contents, we can use one page for all, reducing our allocations and avoid complications by not assuming per-engine isolation. For later use, it simplifies engine initialisation (by removing the allocation that required struct_mutex!) and means that we can always rely on there being a scratch page. v2: Check that we allocated a large enough scratch for I830 w/a Fixes: 06e562e7f515 ("drm/i915/ringbuffer: Delay after EMIT_INVALIDATE for gen4/gen5") # v4.18.20 Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=108850 Signed-off-by: Chris Wilson Cc: Tvrtko Ursulin Cc: Mika Kuoppala Reviewed-by: Mika Kuoppala Link: https://patchwork.freedesktop.org/patch/msgid/20181204141522.13640-1-chris@chris-wilson.co.uk Cc: Joonas Lahtinen Cc: # v4.18.20+ --- drivers/gpu/drm/i915/intel_ringbuffer.c | 37 +++++++++++---------------------- 1 file changed, 12 insertions(+), 25 deletions(-) (limited to 'drivers/gpu/drm/i915/intel_ringbuffer.c') diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c index 7f88df5bff09..c5eb26a7ee79 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.c +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c @@ -150,8 +150,7 @@ gen4_render_ring_flush(struct i915_request *rq, u32 mode) */ if (mode & EMIT_INVALIDATE) { *cs++ = GFX_OP_PIPE_CONTROL(4) | PIPE_CONTROL_QW_WRITE; - *cs++ = i915_ggtt_offset(rq->engine->scratch) | - PIPE_CONTROL_GLOBAL_GTT; + *cs++ = i915_scratch_offset(rq->i915) | PIPE_CONTROL_GLOBAL_GTT; *cs++ = 0; *cs++ = 0; @@ -159,8 +158,7 @@ gen4_render_ring_flush(struct i915_request *rq, u32 mode) *cs++ = MI_FLUSH; *cs++ = GFX_OP_PIPE_CONTROL(4) | PIPE_CONTROL_QW_WRITE; - *cs++ = i915_ggtt_offset(rq->engine->scratch) | - PIPE_CONTROL_GLOBAL_GTT; + *cs++ = i915_scratch_offset(rq->i915) | PIPE_CONTROL_GLOBAL_GTT; *cs++ = 0; *cs++ = 0; } @@ -212,8 +210,7 @@ gen4_render_ring_flush(struct i915_request *rq, u32 mode) static int intel_emit_post_sync_nonzero_flush(struct i915_request *rq) { - u32 scratch_addr = - i915_ggtt_offset(rq->engine->scratch) + 2 * CACHELINE_BYTES; + u32 scratch_addr = i915_scratch_offset(rq->i915) + 2 * CACHELINE_BYTES; u32 *cs; cs = intel_ring_begin(rq, 6); @@ -246,8 +243,7 @@ intel_emit_post_sync_nonzero_flush(struct i915_request *rq) static int gen6_render_ring_flush(struct i915_request *rq, u32 mode) { - u32 scratch_addr = - i915_ggtt_offset(rq->engine->scratch) + 2 * CACHELINE_BYTES; + u32 scratch_addr = i915_scratch_offset(rq->i915) + 2 * CACHELINE_BYTES; u32 *cs, flags = 0; int ret; @@ -316,8 +312,7 @@ gen7_render_ring_cs_stall_wa(struct i915_request *rq) static int gen7_render_ring_flush(struct i915_request *rq, u32 mode) { - u32 scratch_addr = - i915_ggtt_offset(rq->engine->scratch) + 2 * CACHELINE_BYTES; + u32 scratch_addr = i915_scratch_offset(rq->i915) + 2 * CACHELINE_BYTES; u32 *cs, flags = 0; /* @@ -994,7 +989,7 @@ i965_emit_bb_start(struct i915_request *rq, } /* Just userspace ABI convention to limit the wa batch bo to a resonable size */ -#define I830_BATCH_LIMIT (256*1024) +#define I830_BATCH_LIMIT SZ_256K #define I830_TLB_ENTRIES (2) #define I830_WA_SIZE max(I830_TLB_ENTRIES*4096, I830_BATCH_LIMIT) static int @@ -1002,7 +997,9 @@ i830_emit_bb_start(struct i915_request *rq, u64 offset, u32 len, unsigned int dispatch_flags) { - u32 *cs, cs_offset = i915_ggtt_offset(rq->engine->scratch); + u32 *cs, cs_offset = i915_scratch_offset(rq->i915); + + GEM_BUG_ON(rq->i915->gt.scratch->size < I830_WA_SIZE); cs = intel_ring_begin(rq, 6); if (IS_ERR(cs)) @@ -1459,7 +1456,6 @@ static int intel_init_ring_buffer(struct intel_engine_cs *engine) { struct i915_timeline *timeline; struct intel_ring *ring; - unsigned int size; int err; intel_engine_setup_common(engine); @@ -1484,21 +1480,12 @@ static int intel_init_ring_buffer(struct intel_engine_cs *engine) GEM_BUG_ON(engine->buffer); engine->buffer = ring; - size = PAGE_SIZE; - if (HAS_BROKEN_CS_TLB(engine->i915)) - size = I830_WA_SIZE; - err = intel_engine_create_scratch(engine, size); - if (err) - goto err_unpin; - err = intel_engine_init_common(engine); if (err) - goto err_scratch; + goto err_unpin; return 0; -err_scratch: - intel_engine_cleanup_scratch(engine); err_unpin: intel_ring_unpin(ring); err_ring: @@ -1572,7 +1559,7 @@ static int flush_pd_dir(struct i915_request *rq) /* Stall until the page table load is complete */ *cs++ = MI_STORE_REGISTER_MEM | MI_SRM_LRM_GLOBAL_GTT; *cs++ = i915_mmio_reg_offset(RING_PP_DIR_BASE(engine)); - *cs++ = i915_ggtt_offset(engine->scratch); + *cs++ = i915_scratch_offset(rq->i915); *cs++ = MI_NOOP; intel_ring_advance(rq, cs); @@ -1681,7 +1668,7 @@ static inline int mi_set_context(struct i915_request *rq, u32 flags) /* Insert a delay before the next switch! */ *cs++ = MI_STORE_REGISTER_MEM | MI_SRM_LRM_GLOBAL_GTT; *cs++ = i915_mmio_reg_offset(last_reg); - *cs++ = i915_ggtt_offset(engine->scratch); + *cs++ = i915_scratch_offset(rq->i915); *cs++ = MI_NOOP; } *cs++ = MI_ARB_ON_OFF | MI_ARB_ENABLE; -- cgit v1.2.3