intel-gfx.lists.freedesktop.org archive mirror
 help / color / mirror / Atom feed
From: Matthew Brost <matthew.brost@intel.com>
To: <intel-gfx@lists.freedesktop.org>, <dri-devel@lists.freedesktop.org>
Cc: <daniel.vetter@ffwll.ch>
Subject: [Intel-gfx] [PATCH 16/27] drm/i915: Allocate error capture in nowait context
Date: Wed, 18 Aug 2021 23:16:28 -0700	[thread overview]
Message-ID: <20210819061639.21051-17-matthew.brost@intel.com> (raw)
In-Reply-To: <20210819061639.21051-1-matthew.brost@intel.com>

Error captures can now be done in a work queue processing G2H messages.
These messages need to be completely done being processed in the reset
path, to avoid races in the missing G2H cleanup, which create a
dependency on memory allocations and dma fences (i915_requests).
Requests depend on resets, thus now we have a circular dependency. To
work around this, allocate the error capture in a nowait context.

v2:
 (Daniel Vetter)
  - Use GFP_NOWAIT instead GFP_ATOMIC

Fixes: dc0dad365c5e ("Fix for error capture after full GPU reset with GuC")
Fixes: 573ba126aef3 ("Capture error state on context reset")
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
---
 drivers/gpu/drm/i915/i915_gpu_error.c | 39 +++++++++++++--------------
 1 file changed, 19 insertions(+), 20 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index 0f08bcfbe964..2819b69fbb72 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -49,8 +49,7 @@
 #include "i915_memcpy.h"
 #include "i915_scatterlist.h"
 
-#define ALLOW_FAIL (GFP_KERNEL | __GFP_RETRY_MAYFAIL | __GFP_NOWARN)
-#define ATOMIC_MAYFAIL (GFP_ATOMIC | __GFP_NOWARN)
+#define ATOMIC_MAYFAIL (GFP_NOWAIT | __GFP_NOWARN)
 
 static void __sg_set_buf(struct scatterlist *sg,
 			 void *addr, unsigned int len, loff_t it)
@@ -79,7 +78,7 @@ static bool __i915_error_grow(struct drm_i915_error_state_buf *e, size_t len)
 	if (e->cur == e->end) {
 		struct scatterlist *sgl;
 
-		sgl = (typeof(sgl))__get_free_page(ALLOW_FAIL);
+		sgl = (typeof(sgl))__get_free_page(ATOMIC_MAYFAIL);
 		if (!sgl) {
 			e->err = -ENOMEM;
 			return false;
@@ -99,10 +98,10 @@ static bool __i915_error_grow(struct drm_i915_error_state_buf *e, size_t len)
 	}
 
 	e->size = ALIGN(len + 1, SZ_64K);
-	e->buf = kmalloc(e->size, ALLOW_FAIL);
+	e->buf = kmalloc(e->size, ATOMIC_MAYFAIL);
 	if (!e->buf) {
 		e->size = PAGE_ALIGN(len + 1);
-		e->buf = kmalloc(e->size, GFP_KERNEL);
+		e->buf = kmalloc(e->size, ATOMIC_MAYFAIL);
 	}
 	if (!e->buf) {
 		e->err = -ENOMEM;
@@ -243,12 +242,12 @@ static bool compress_init(struct i915_vma_compress *c)
 {
 	struct z_stream_s *zstream = &c->zstream;
 
-	if (pool_init(&c->pool, ALLOW_FAIL))
+	if (pool_init(&c->pool, ATOMIC_MAYFAIL))
 		return false;
 
 	zstream->workspace =
 		kmalloc(zlib_deflate_workspacesize(MAX_WBITS, MAX_MEM_LEVEL),
-			ALLOW_FAIL);
+			ATOMIC_MAYFAIL);
 	if (!zstream->workspace) {
 		pool_fini(&c->pool);
 		return false;
@@ -256,7 +255,7 @@ static bool compress_init(struct i915_vma_compress *c)
 
 	c->tmp = NULL;
 	if (i915_has_memcpy_from_wc())
-		c->tmp = pool_alloc(&c->pool, ALLOW_FAIL);
+		c->tmp = pool_alloc(&c->pool, ATOMIC_MAYFAIL);
 
 	return true;
 }
@@ -280,7 +279,7 @@ static void *compress_next_page(struct i915_vma_compress *c,
 	if (dst->page_count >= dst->num_pages)
 		return ERR_PTR(-ENOSPC);
 
-	page = pool_alloc(&c->pool, ALLOW_FAIL);
+	page = pool_alloc(&c->pool, ATOMIC_MAYFAIL);
 	if (!page)
 		return ERR_PTR(-ENOMEM);
 
@@ -376,7 +375,7 @@ struct i915_vma_compress {
 
 static bool compress_init(struct i915_vma_compress *c)
 {
-	return pool_init(&c->pool, ALLOW_FAIL) == 0;
+	return pool_init(&c->pool, ATOMIC_MAYFAIL) == 0;
 }
 
 static bool compress_start(struct i915_vma_compress *c)
@@ -391,7 +390,7 @@ static int compress_page(struct i915_vma_compress *c,
 {
 	void *ptr;
 
-	ptr = pool_alloc(&c->pool, ALLOW_FAIL);
+	ptr = pool_alloc(&c->pool, ATOMIC_MAYFAIL);
 	if (!ptr)
 		return -ENOMEM;
 
@@ -997,7 +996,7 @@ i915_vma_coredump_create(const struct intel_gt *gt,
 
 	num_pages = min_t(u64, vma->size, vma->obj->base.size) >> PAGE_SHIFT;
 	num_pages = DIV_ROUND_UP(10 * num_pages, 8); /* worstcase zlib growth */
-	dst = kmalloc(sizeof(*dst) + num_pages * sizeof(u32 *), ALLOW_FAIL);
+	dst = kmalloc(sizeof(*dst) + num_pages * sizeof(u32 *), ATOMIC_MAYFAIL);
 	if (!dst)
 		return NULL;
 
@@ -1433,7 +1432,7 @@ capture_engine(struct intel_engine_cs *engine,
 	struct i915_request *rq = NULL;
 	unsigned long flags;
 
-	ee = intel_engine_coredump_alloc(engine, GFP_KERNEL);
+	ee = intel_engine_coredump_alloc(engine, ATOMIC_MAYFAIL);
 	if (!ee)
 		return NULL;
 
@@ -1481,7 +1480,7 @@ gt_record_engines(struct intel_gt_coredump *gt,
 		struct intel_engine_coredump *ee;
 
 		/* Refill our page pool before entering atomic section */
-		pool_refill(&compress->pool, ALLOW_FAIL);
+		pool_refill(&compress->pool, ATOMIC_MAYFAIL);
 
 		ee = capture_engine(engine, compress);
 		if (!ee)
@@ -1507,7 +1506,7 @@ gt_record_uc(struct intel_gt_coredump *gt,
 	const struct intel_uc *uc = &gt->_gt->uc;
 	struct intel_uc_coredump *error_uc;
 
-	error_uc = kzalloc(sizeof(*error_uc), ALLOW_FAIL);
+	error_uc = kzalloc(sizeof(*error_uc), ATOMIC_MAYFAIL);
 	if (!error_uc)
 		return NULL;
 
@@ -1518,8 +1517,8 @@ gt_record_uc(struct intel_gt_coredump *gt,
 	 * As modparams are generally accesible from the userspace make
 	 * explicit copies of the firmware paths.
 	 */
-	error_uc->guc_fw.path = kstrdup(uc->guc.fw.path, ALLOW_FAIL);
-	error_uc->huc_fw.path = kstrdup(uc->huc.fw.path, ALLOW_FAIL);
+	error_uc->guc_fw.path = kstrdup(uc->guc.fw.path, ATOMIC_MAYFAIL);
+	error_uc->huc_fw.path = kstrdup(uc->huc.fw.path, ATOMIC_MAYFAIL);
 	error_uc->guc_log =
 		i915_vma_coredump_create(gt->_gt,
 					 uc->guc.log.vma, "GuC log buffer",
@@ -1778,7 +1777,7 @@ i915_vma_capture_prepare(struct intel_gt_coredump *gt)
 {
 	struct i915_vma_compress *compress;
 
-	compress = kmalloc(sizeof(*compress), ALLOW_FAIL);
+	compress = kmalloc(sizeof(*compress), ATOMIC_MAYFAIL);
 	if (!compress)
 		return NULL;
 
@@ -1811,11 +1810,11 @@ i915_gpu_coredump(struct intel_gt *gt, intel_engine_mask_t engine_mask)
 	if (IS_ERR(error))
 		return error;
 
-	error = i915_gpu_coredump_alloc(i915, ALLOW_FAIL);
+	error = i915_gpu_coredump_alloc(i915, ATOMIC_MAYFAIL);
 	if (!error)
 		return ERR_PTR(-ENOMEM);
 
-	error->gt = intel_gt_coredump_alloc(gt, ALLOW_FAIL);
+	error->gt = intel_gt_coredump_alloc(gt, ATOMIC_MAYFAIL);
 	if (error->gt) {
 		struct i915_vma_compress *compress;
 
-- 
2.32.0


  parent reply	other threads:[~2021-08-19  6:22 UTC|newest]

Thread overview: 78+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-08-19  6:16 [Intel-gfx] [PATCH 00/27] Clean up GuC CI failures, simplify locking, and kernel DOC Matthew Brost
2021-08-19  6:16 ` [Intel-gfx] [PATCH 01/27] drm/i915/guc: Fix blocked context accounting Matthew Brost
2021-08-24 23:24   ` Daniele Ceraolo Spurio
2021-08-19  6:16 ` [Intel-gfx] [PATCH 02/27] drm/i915/guc: Fix outstanding G2H accounting Matthew Brost
2021-08-19 21:31   ` Daniele Ceraolo Spurio
2021-08-19 21:30     ` Matthew Brost
2021-08-19  6:16 ` [Intel-gfx] [PATCH 03/27] drm/i915/guc: Unwind context requests in reverse order Matthew Brost
2021-08-19 23:54   ` Daniele Ceraolo Spurio
2021-08-19 23:53     ` Matthew Brost
2021-08-20  0:03       ` Daniele Ceraolo Spurio
2021-08-19  6:16 ` [Intel-gfx] [PATCH 04/27] drm/i915/guc: Don't drop ce->guc_active.lock when unwinding context Matthew Brost
2021-08-20  0:01   ` Daniele Ceraolo Spurio
2021-08-19 23:58     ` Matthew Brost
2021-08-19  6:16 ` [Intel-gfx] [PATCH 05/27] drm/i915/guc: Process all G2H message at once in work queue Matthew Brost
2021-08-20  0:06   ` Daniele Ceraolo Spurio
2021-08-19  6:16 ` [Intel-gfx] [PATCH 06/27] drm/i915/guc: Workaround reset G2H is received after schedule done G2H Matthew Brost
2021-08-24 23:31   ` Daniele Ceraolo Spurio
2021-08-25  4:05     ` Matthew Brost
2021-08-19  6:16 ` [Intel-gfx] [PATCH 07/27] Revert "drm/i915/gt: Propagate change in error status to children on unhold" Matthew Brost
2021-08-20 19:47   ` Jason Ekstrand
2021-08-19  6:16 ` [Intel-gfx] [PATCH 08/27] drm/i915/selftests: Add a cancel request selftest that triggers a reset Matthew Brost
2021-08-19  6:16 ` [Intel-gfx] [PATCH 09/27] drm/i915/guc: Kick tasklet after queuing a request Matthew Brost
2021-08-20 18:31   ` Daniele Ceraolo Spurio
2021-08-20 18:36     ` Matthew Brost
2021-08-19  6:16 ` [Intel-gfx] [PATCH 10/27] drm/i915/guc: Don't enable scheduling on a banned context, guc_id invalid, not registered Matthew Brost
2021-08-20 18:42   ` Daniele Ceraolo Spurio
2021-08-20 18:42     ` Matthew Brost
2021-08-19  6:16 ` [Intel-gfx] [PATCH 11/27] drm/i915/selftests: Fix memory corruption in live_lrc_isolation Matthew Brost
2021-08-25  0:07   ` Daniele Ceraolo Spurio
2021-08-25 20:03     ` Matthew Brost
2021-08-19  6:16 ` [Intel-gfx] [PATCH 12/27] drm/i915/selftests: Add initial GuC selftest for scrubbing lost G2H Matthew Brost
2021-08-25  0:58   ` Daniele Ceraolo Spurio
2021-08-19  6:16 ` [Intel-gfx] [PATCH 13/27] drm/i915/guc: Take context ref when cancelling request Matthew Brost
2021-08-21  0:07   ` Daniele Ceraolo Spurio
2021-08-24 15:42     ` Matthew Brost
2021-08-25  1:21       ` Daniele Ceraolo Spurio
2021-08-19  6:16 ` [Intel-gfx] [PATCH 14/27] drm/i915/guc: Don't touch guc_state.sched_state without a lock Matthew Brost
2021-08-25  1:20   ` Daniele Ceraolo Spurio
2021-08-25  1:44     ` Matthew Brost
2021-08-25  1:51       ` Daniele Ceraolo Spurio
2021-08-19  6:16 ` [Intel-gfx] [PATCH 15/27] drm/i915/guc: Reset LRC descriptor if register returns -ENODEV Matthew Brost
2021-08-21  0:14   ` Daniele Ceraolo Spurio
2021-08-19  6:16 ` Matthew Brost [this message]
2021-08-19  6:16 ` [Intel-gfx] [PATCH 17/27] drm/i915/guc: Flush G2H work queue during reset Matthew Brost
2021-08-21  0:25   ` Daniele Ceraolo Spurio
2021-08-24 15:44     ` Matthew Brost
2021-08-25  1:22       ` Daniele Ceraolo Spurio
2021-08-19  6:16 ` [Intel-gfx] [PATCH 18/27] drm/i915/guc: Release submit fence from an irq_work Matthew Brost
2021-08-25  1:44   ` Daniele Ceraolo Spurio
2021-08-19  6:16 ` [Intel-gfx] [PATCH 19/27] drm/i915/guc: Move guc_blocked fence to struct guc_state Matthew Brost
2021-08-21  0:30   ` Daniele Ceraolo Spurio
2021-08-19  6:16 ` [Intel-gfx] [PATCH 20/27] drm/i915/guc: Rework and simplify locking Matthew Brost
2021-08-25 16:52   ` Daniele Ceraolo Spurio
2021-08-25 19:22     ` Matthew Brost
2021-08-19  6:16 ` [Intel-gfx] [PATCH 21/27] drm/i915/guc: Proper xarray usage for contexts_lookup Matthew Brost
2021-08-26  0:44   ` Daniele Ceraolo Spurio
2021-08-26  0:41     ` Matthew Brost
2021-08-26  0:48       ` Daniele Ceraolo Spurio
2021-08-19  6:16 ` [Intel-gfx] [PATCH 22/27] drm/i915/guc: Drop pin count check trick between sched_disable and re-pin Matthew Brost
2021-08-26  0:50   ` Daniele Ceraolo Spurio
2021-08-19  6:16 ` [Intel-gfx] [PATCH 23/27] drm/i915/guc: Move GuC priority fields in context under guc_active Matthew Brost
2021-08-25 21:51   ` Daniele Ceraolo Spurio
2021-08-25 22:53     ` Matthew Brost
2021-08-25 23:04     ` Matthew Brost
2021-08-19  6:16 ` [Intel-gfx] [PATCH 24/27] drm/i915/guc: Move fields protected by guc->contexts_lock into sub structure Matthew Brost
2021-08-25  2:00   ` Daniele Ceraolo Spurio
2021-08-19  6:16 ` [Intel-gfx] [PATCH 25/27] drm/i915/guc: Drop guc_active move everything into guc_state Matthew Brost
2021-08-26  0:54   ` Daniele Ceraolo Spurio
2021-08-19  6:16 ` [Intel-gfx] [PATCH 26/27] drm/i915/guc: Add GuC kernel doc Matthew Brost
2021-08-26  1:03   ` Daniele Ceraolo Spurio
2021-08-19  6:16 ` [Intel-gfx] [PATCH 27/27] drm/i915/guc: Drop static inline functions intel_guc_submission.c Matthew Brost
2021-08-19  7:18 ` [Intel-gfx] ✗ Fi.CI.CHECKPATCH: warning for Clean up GuC CI failures, simplify locking, and kernel DOC (rev3) Patchwork
2021-08-19  7:20 ` [Intel-gfx] ✗ Fi.CI.SPARSE: " Patchwork
2021-08-19  7:51 ` [Intel-gfx] ✓ Fi.CI.BAT: success " Patchwork
2021-08-19  9:08 ` [Intel-gfx] ✗ Fi.CI.IGT: failure " Patchwork
2021-08-26  3:23 [Intel-gfx] [PATCH 00/27] Clean up GuC CI failures, simplify locking, and kernel DOC Matthew Brost
2021-08-26  3:23 ` [Intel-gfx] [PATCH 16/27] drm/i915: Allocate error capture in nowait context Matthew Brost
2021-08-26 16:18   ` Matthew Brost
2021-08-26 16:21   ` Daniel Vetter

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20210819061639.21051-17-matthew.brost@intel.com \
    --to=matthew.brost@intel.com \
    --cc=daniel.vetter@ffwll.ch \
    --cc=dri-devel@lists.freedesktop.org \
    --cc=intel-gfx@lists.freedesktop.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).