All of lore.kernel.org
 help / color / mirror / Atom feed
From: Chris Wilson <chris@chris-wilson.co.uk>
To: linux-kernel@vger.kernel.org, intel-gfx@lists.freedesktop.org
Cc: linux-mm@kvack.org, Chris Wilson <chris@chris-wilson.co.uk>,
	Pavel Machek <pavel@ucw.cz>,
	Joonas Lahtinen <joonas.lahtinen@linux.intel.com>,
	stable@vger.kernel.org
Subject: [PATCH 4/4] drm/i915/gem: Replace reloc chain with terminator on error unwind
Date: Fri, 21 Aug 2020 09:50:11 +0100	[thread overview]
Message-ID: <20200821085011.28878-4-chris@chris-wilson.co.uk> (raw)
In-Reply-To: <20200821085011.28878-1-chris@chris-wilson.co.uk>

If we hit an error during construction of the reloc chain, we need to
replace the chain into the next batch with the terminator so that upon
flushing the relocations so far, we do not execute a hanging batch.

Reported-by: Pavel Machek <pavel@ucw.cz>
Fixes: 964a9b0f611e ("drm/i915/gem: Use chained reloc batches")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Pavel Machek <pavel@ucw.cz>
Cc: <stable@vger.kernel.org> # v5.8+
---
 .../gpu/drm/i915/gem/i915_gem_execbuffer.c    | 31 ++++++++++---------
 1 file changed, 16 insertions(+), 15 deletions(-)

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
index 24a1486d2dc5..a09f04eee417 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
@@ -972,21 +972,6 @@ static int reloc_gpu_chain(struct reloc_cache *cache)
 	if (err)
 		goto out_pool;
 
-	GEM_BUG_ON(cache->rq_size + RELOC_TAIL > PAGE_SIZE  / sizeof(u32));
-	cmd = cache->rq_cmd + cache->rq_size;
-	*cmd++ = MI_ARB_CHECK;
-	if (cache->gen >= 8)
-		*cmd++ = MI_BATCH_BUFFER_START_GEN8;
-	else if (cache->gen >= 6)
-		*cmd++ = MI_BATCH_BUFFER_START;
-	else
-		*cmd++ = MI_BATCH_BUFFER_START | MI_BATCH_GTT;
-	*cmd++ = lower_32_bits(batch->node.start);
-	*cmd++ = upper_32_bits(batch->node.start); /* Always 0 for gen<8 */
-	i915_gem_object_flush_map(cache->rq_vma->obj);
-	i915_gem_object_unpin_map(cache->rq_vma->obj);
-	cache->rq_vma = NULL;
-
 	err = intel_gt_buffer_pool_mark_active(pool, rq);
 	if (err == 0) {
 		i915_vma_lock(batch);
@@ -999,15 +984,31 @@ static int reloc_gpu_chain(struct reloc_cache *cache)
 	if (err)
 		goto out_pool;
 
+	GEM_BUG_ON(cache->rq_size + RELOC_TAIL > PAGE_SIZE  / sizeof(u32));
+	cmd = cache->rq_cmd + cache->rq_size;
+	*cmd++ = MI_ARB_CHECK;
+	if (cache->gen >= 8)
+		*cmd++ = MI_BATCH_BUFFER_START_GEN8;
+	else if (cache->gen >= 6)
+		*cmd++ = MI_BATCH_BUFFER_START;
+	else
+		*cmd++ = MI_BATCH_BUFFER_START | MI_BATCH_GTT;
+	*cmd++ = lower_32_bits(batch->node.start);
+	*cmd++ = upper_32_bits(batch->node.start); /* Always 0 for gen<8 */
+
 	cmd = i915_gem_object_pin_map(batch->obj,
 				      cache->has_llc ?
 				      I915_MAP_FORCE_WB :
 				      I915_MAP_FORCE_WC);
 	if (IS_ERR(cmd)) {
+		/* We will replace the BBS with BBE upon flushing the rq */
 		err = PTR_ERR(cmd);
 		goto out_pool;
 	}
 
+	i915_gem_object_flush_map(cache->rq_vma->obj);
+	i915_gem_object_unpin_map(cache->rq_vma->obj);
+
 	/* Return with batch mapping (cmd) still pinned */
 	cache->rq_cmd = cmd;
 	cache->rq_size = 0;
-- 
2.20.1


WARNING: multiple messages have this Message-ID (diff)
From: Chris Wilson <chris@chris-wilson.co.uk>
To: linux-kernel@vger.kernel.org, intel-gfx@lists.freedesktop.org
Cc: linux-mm@kvack.org, stable@vger.kernel.org,
	Pavel Machek <pavel@ucw.cz>,
	Chris Wilson <chris@chris-wilson.co.uk>
Subject: [Intel-gfx] [PATCH 4/4] drm/i915/gem: Replace reloc chain with terminator on error unwind
Date: Fri, 21 Aug 2020 09:50:11 +0100	[thread overview]
Message-ID: <20200821085011.28878-4-chris@chris-wilson.co.uk> (raw)
In-Reply-To: <20200821085011.28878-1-chris@chris-wilson.co.uk>

If we hit an error during construction of the reloc chain, we need to
replace the chain into the next batch with the terminator so that upon
flushing the relocations so far, we do not execute a hanging batch.

Reported-by: Pavel Machek <pavel@ucw.cz>
Fixes: 964a9b0f611e ("drm/i915/gem: Use chained reloc batches")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Pavel Machek <pavel@ucw.cz>
Cc: <stable@vger.kernel.org> # v5.8+
---
 .../gpu/drm/i915/gem/i915_gem_execbuffer.c    | 31 ++++++++++---------
 1 file changed, 16 insertions(+), 15 deletions(-)

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
index 24a1486d2dc5..a09f04eee417 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
@@ -972,21 +972,6 @@ static int reloc_gpu_chain(struct reloc_cache *cache)
 	if (err)
 		goto out_pool;
 
-	GEM_BUG_ON(cache->rq_size + RELOC_TAIL > PAGE_SIZE  / sizeof(u32));
-	cmd = cache->rq_cmd + cache->rq_size;
-	*cmd++ = MI_ARB_CHECK;
-	if (cache->gen >= 8)
-		*cmd++ = MI_BATCH_BUFFER_START_GEN8;
-	else if (cache->gen >= 6)
-		*cmd++ = MI_BATCH_BUFFER_START;
-	else
-		*cmd++ = MI_BATCH_BUFFER_START | MI_BATCH_GTT;
-	*cmd++ = lower_32_bits(batch->node.start);
-	*cmd++ = upper_32_bits(batch->node.start); /* Always 0 for gen<8 */
-	i915_gem_object_flush_map(cache->rq_vma->obj);
-	i915_gem_object_unpin_map(cache->rq_vma->obj);
-	cache->rq_vma = NULL;
-
 	err = intel_gt_buffer_pool_mark_active(pool, rq);
 	if (err == 0) {
 		i915_vma_lock(batch);
@@ -999,15 +984,31 @@ static int reloc_gpu_chain(struct reloc_cache *cache)
 	if (err)
 		goto out_pool;
 
+	GEM_BUG_ON(cache->rq_size + RELOC_TAIL > PAGE_SIZE  / sizeof(u32));
+	cmd = cache->rq_cmd + cache->rq_size;
+	*cmd++ = MI_ARB_CHECK;
+	if (cache->gen >= 8)
+		*cmd++ = MI_BATCH_BUFFER_START_GEN8;
+	else if (cache->gen >= 6)
+		*cmd++ = MI_BATCH_BUFFER_START;
+	else
+		*cmd++ = MI_BATCH_BUFFER_START | MI_BATCH_GTT;
+	*cmd++ = lower_32_bits(batch->node.start);
+	*cmd++ = upper_32_bits(batch->node.start); /* Always 0 for gen<8 */
+
 	cmd = i915_gem_object_pin_map(batch->obj,
 				      cache->has_llc ?
 				      I915_MAP_FORCE_WB :
 				      I915_MAP_FORCE_WC);
 	if (IS_ERR(cmd)) {
+		/* We will replace the BBS with BBE upon flushing the rq */
 		err = PTR_ERR(cmd);
 		goto out_pool;
 	}
 
+	i915_gem_object_flush_map(cache->rq_vma->obj);
+	i915_gem_object_unpin_map(cache->rq_vma->obj);
+
 	/* Return with batch mapping (cmd) still pinned */
 	cache->rq_cmd = cmd;
 	cache->rq_size = 0;
-- 
2.20.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

  parent reply	other threads:[~2020-08-21  8:50 UTC|newest]

Thread overview: 40+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-08-21  8:50 [PATCH 1/4] mm: Export flush_vm_area() to sync the PTEs upon construction Chris Wilson
2020-08-21  8:50 ` [Intel-gfx] " Chris Wilson
2020-08-21  8:50 ` [PATCH 2/4] drm/i915/gem: Sync the vmap " Chris Wilson
2020-08-21  8:50   ` [Intel-gfx] " Chris Wilson
2020-08-21 12:41   ` Linus Torvalds
2020-08-21 12:41     ` [Intel-gfx] " Linus Torvalds
2020-08-21 12:41     ` Linus Torvalds
2020-08-21 13:01     ` Chris Wilson
2020-08-21 13:01       ` [Intel-gfx] " Chris Wilson
2020-08-21  8:50 ` [PATCH 3/4] drm/i915/gem: Use set_pte_at() for assigning the vmapped PTE Chris Wilson
2020-08-21  8:50   ` [Intel-gfx] " Chris Wilson
2020-08-21  8:50 ` Chris Wilson [this message]
2020-08-21  8:50   ` [Intel-gfx] [PATCH 4/4] drm/i915/gem: Replace reloc chain with terminator on error unwind Chris Wilson
2020-08-21  9:14 ` [Intel-gfx] ✗ Fi.CI.CHECKPATCH: warning for series starting with [1/4] mm: Export flush_vm_area() to sync the PTEs upon construction Patchwork
2020-08-21  9:16 ` [Intel-gfx] ✗ Fi.CI.SPARSE: " Patchwork
2020-08-21  9:29 ` [Intel-gfx] ✓ Fi.CI.BAT: success " Patchwork
2020-08-21  9:51 ` [PATCH 1/4] " Joerg Roedel
2020-08-21  9:51   ` [Intel-gfx] " Joerg Roedel
2020-08-21  9:54   ` Chris Wilson
2020-08-21  9:54     ` [Intel-gfx] " Chris Wilson
2020-08-21 10:22     ` Joerg Roedel
2020-08-21 10:22       ` [Intel-gfx] " Joerg Roedel
2020-08-21 10:36       ` Chris Wilson
2020-08-21 10:36         ` [Intel-gfx] " Chris Wilson
2020-08-21 10:09 ` [PATCH] mm: Track page table modifications in __apply_to_page_range() construction Joerg Roedel
2020-08-21 10:09   ` [Intel-gfx] " Joerg Roedel
2020-08-21 10:13   ` Chris Wilson
2020-08-21 10:13     ` [Intel-gfx] " Chris Wilson
2020-08-21 10:23     ` Joerg Roedel
2020-08-21 10:23       ` [Intel-gfx] " Joerg Roedel
2020-08-21 10:39       ` Chris Wilson
2020-08-21 10:39         ` [Intel-gfx] " Chris Wilson
2020-08-21 11:38         ` Chris Wilson
2020-08-21 11:38           ` [Intel-gfx] " Chris Wilson
2020-08-21 12:18           ` Joerg Roedel
2020-08-21 12:18             ` [Intel-gfx] " Joerg Roedel
2020-08-21 10:53   ` Greg KH
2020-08-21 10:53     ` [Intel-gfx] " Greg KH
2020-08-21 10:27 ` [Intel-gfx] ✗ Fi.CI.BUILD: failure for series starting with mm: Track page table modifications in __apply_to_page_range() construction (rev2) Patchwork
2020-08-21 11:33 ` [Intel-gfx] ✓ Fi.CI.IGT: success for series starting with [1/4] mm: Export flush_vm_area() to sync the PTEs upon construction 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=20200821085011.28878-4-chris@chris-wilson.co.uk \
    --to=chris@chris-wilson.co.uk \
    --cc=intel-gfx@lists.freedesktop.org \
    --cc=joonas.lahtinen@linux.intel.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=pavel@ucw.cz \
    --cc=stable@vger.kernel.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.