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 14/22] drm/i915: Allocate error capture in atomic context
Date: Mon, 16 Aug 2021 06:51:31 -0700 [thread overview]
Message-ID: <20210816135139.10060-15-matthew.brost@intel.com> (raw)
In-Reply-To: <20210816135139.10060-1-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 an atomic context.
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 | 37 +++++++++++++--------------
1 file changed, 18 insertions(+), 19 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index 0f08bcfbe964..453376aa6d9f 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -49,7 +49,6 @@
#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)
static void __sg_set_buf(struct scatterlist *sg,
@@ -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->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
next prev parent reply other threads:[~2021-08-16 13:57 UTC|newest]
Thread overview: 56+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-08-16 13:51 [Intel-gfx] [PATCH 00/22] Clean up GuC CI failures, simplify locking, and kernel DOC Matthew Brost
2021-08-16 13:51 ` [Intel-gfx] [PATCH 01/22] drm/i915/guc: Fix blocked context accounting Matthew Brost
2021-08-16 13:51 ` [Intel-gfx] [PATCH 02/22] drm/i915/guc: Fix outstanding G2H accounting Matthew Brost
2021-08-17 9:39 ` Daniel Vetter
2021-08-17 18:17 ` Matthew Brost
2021-08-16 13:51 ` [Intel-gfx] [PATCH 03/22] drm/i915/guc: Unwind context requests in reverse order Matthew Brost
2021-08-16 13:51 ` [Intel-gfx] [PATCH 04/22] drm/i915/guc: Don't drop ce->guc_active.lock when unwinding context Matthew Brost
2021-08-16 13:51 ` [Intel-gfx] [PATCH 05/22] drm/i915/guc: Workaround reset G2H is received after schedule done G2H Matthew Brost
2021-08-17 9:32 ` Daniel Vetter
2021-08-17 15:03 ` Matthew Brost
2021-08-16 13:51 ` [Intel-gfx] [PATCH 06/22] drm/i915/execlists: Do not propagate errors to dependent fences Matthew Brost
2021-08-17 9:21 ` Daniel Vetter
2021-08-17 15:08 ` Matthew Brost
2021-08-17 15:49 ` Daniel Vetter
2021-08-16 13:51 ` [Intel-gfx] [PATCH 07/22] drm/i915/selftests: Add a cancel request selftest that triggers a reset Matthew Brost
2021-08-16 13:51 ` [Intel-gfx] [PATCH 08/22] drm/i915/guc: Don't enable scheduling on a banned context, guc_id invalid, not registered Matthew Brost
2021-08-17 9:47 ` Daniel Vetter
2021-08-17 9:57 ` Daniel Vetter
2021-08-17 16:44 ` Matthew Brost
2021-08-16 13:51 ` [Intel-gfx] [PATCH 09/22] drm/i915/selftests: Fix memory corruption in live_lrc_isolation Matthew Brost
2021-08-16 13:51 ` [Intel-gfx] [PATCH 10/22] drm/i915/selftests: Add initial GuC selftest for scrubbing lost G2H Matthew Brost
2021-08-16 13:51 ` [Intel-gfx] [PATCH 11/22] drm/i915/guc: Take context ref when cancelling request Matthew Brost
2021-08-16 13:51 ` [Intel-gfx] [PATCH 12/22] drm/i915/guc: Don't touch guc_state.sched_state without a lock Matthew Brost
2021-08-17 7:21 ` kernel test robot
2021-08-16 13:51 ` [Intel-gfx] [PATCH 13/22] drm/i915/guc: Reset LRC descriptor if register returns -ENODEV Matthew Brost
2021-08-16 13:51 ` Matthew Brost [this message]
2021-08-17 10:06 ` [Intel-gfx] [PATCH 14/22] drm/i915: Allocate error capture in atomic context Daniel Vetter
2021-08-17 16:12 ` Matthew Brost
2021-08-16 13:51 ` [Intel-gfx] [PATCH 15/22] drm/i915/guc: Flush G2H work queue during reset Matthew Brost
2021-08-17 10:06 ` Daniel Vetter
2021-08-16 13:51 ` [Intel-gfx] [PATCH 16/22] drm/i915/guc: Release submit fence from an IRQ Matthew Brost
2021-08-17 10:08 ` Daniel Vetter
2021-08-16 13:51 ` [Intel-gfx] [PATCH 17/22] drm/i915/guc: Move guc_blocked fence to struct guc_state Matthew Brost
2021-08-17 10:10 ` Daniel Vetter
2021-08-16 13:51 ` [Intel-gfx] [PATCH 18/22] drm/i915/guc: Rework and simplify locking Matthew Brost
2021-08-17 10:15 ` Daniel Vetter
2021-08-17 15:30 ` Matthew Brost
2021-08-16 13:51 ` [Intel-gfx] [PATCH 19/22] drm/i915/guc: Proper xarray usage for contexts_lookup Matthew Brost
2021-08-17 10:27 ` Daniel Vetter
2021-08-17 15:26 ` Matthew Brost
2021-08-17 17:13 ` Daniel Vetter
2021-08-17 17:13 ` Matthew Brost
2021-08-16 13:51 ` [Intel-gfx] [PATCH 20/22] drm/i915/guc: Drop pin count check trick between sched_disable and re-pin Matthew Brost
2021-08-16 13:51 ` [Intel-gfx] [PATCH 21/22] drm/i915/guc: Move GuC priority fields in context under guc_active Matthew Brost
2021-08-16 13:51 ` [Intel-gfx] [PATCH 22/22] drm/i915/guc: Add GuC kernel doc Matthew Brost
2021-08-17 11:11 ` Daniel Vetter
2021-08-17 16:36 ` Matthew Brost
2021-08-17 17:20 ` Daniel Vetter
2021-08-17 17:27 ` Michal Wajdeczko
2021-08-17 17:34 ` Daniel Vetter
2021-08-17 20:41 ` Michal Wajdeczko
2021-08-17 21:49 ` Daniel Vetter
2021-08-17 12:49 ` [Intel-gfx] ✗ Fi.CI.CHECKPATCH: warning for Clean up GuC CI failures, simplify locking, and kernel DOC (rev2) Patchwork
2021-08-17 12:51 ` [Intel-gfx] ✗ Fi.CI.SPARSE: " Patchwork
2021-08-17 13:22 ` [Intel-gfx] ✓ Fi.CI.BAT: success " Patchwork
2021-08-17 14:39 ` [Intel-gfx] ✗ Fi.CI.IGT: failure " Patchwork
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=20210816135139.10060-15-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).