Re: [PATCH v4] drm/i915: add guard page to ggtt->error_capture

Andrzej Hajda <andrzej.hajda@xxxxxxxxx> · Thu, 2 Mar 2023 12:00:54 +0100

On 02.03.2023 11:43, Tvrtko Ursulin wrote:

On 08/02/2023 10:51, Andrzej Hajda wrote:
Write-combining memory allows speculative reads by CPU.
ggtt->error_capture is WC mapped to CPU, so CPU/MMU can try
to prefetch memory beyond the error_capture, ie it tries
to read memory pointed by next PTE in GGTT.
If this PTE points to invalid address DMAR errors will occur.
This behaviour was observed on ADL, RPL, DG2 platforms.
To avoid it, guard scratch page should be added after error_capture.
The patch fixes the most annoying issue with error capture but
since WC reads are used also in other places there is a risk similar
problem can affect them as well.

Signed-off-by: Andrzej Hajda <andrzej.hajda@xxxxxxxxx>
Reviewed-by: Andi Shyti <andi.shyti@xxxxxxxxxxxxxxx>

Research tells the explanation is plausible so:

Acked-by: Tvrtko Ursulin <tvrtko.ursulin@xxxxxxxxx>


Thanks for looking at it.

On patch details below.

What about "simiar risk in other places" - are there any plans to 
asses the potential impact elsewhere?

Yes, merging this patch is the 1st step, as error_capture is responsible 
for most (maybe even all) regular
DMAR read errors. After removing this noise it will be much easier to 
spot other DMAR read errors.
There are also multiple regular DMAR write errors (less frequent, but 
still), which I hope to debug if time permits.

Regards
Andrzej


---
This patch tries to diminish plague of DMAR read errors present
in CI for ADL*, RPL*, DG2 platforms, see for example [1] (grep DMAR).
CI is usually tolerant for these errors, so the scale of the problem
is not really visible.
To show it I have counted lines containing DMAR read errors in dmesgs
produced by CI for all three versions of the patch, but in contrast 
to v2
I have grepped only for lines containing "PTE Read access".
Below stats for kernel w/o patch vs patched one.
v1: 210 vs 0
v2: 201 vs 0
v3: 214 vs 0
Apparently the patch fixes all common PTE read errors.

In previous version there were different numbers due to less exact 
grepping,
"grep DMAR" catched write errors and "DMAR: DRHD: handling fault 
status reg"
lines, anyway the actual number of errors is much bigger - DMAR errors
are rate-limited.

[1]: 
http://gfx-ci.igk.intel.com/tree/drm-tip/CI_DRM_12678/bat-adln-1/dmesg0.txt

Changelog:
v2:
     - modified commit message (I hope the diagnosis is correct),
     - added bug checks to ensure scratch is initialized on gen3 
platforms.
       CI produces strange stacktrace for it suggesting scratch[0] is 
NULL,
       to be removed after resolving the issue with gen3 platforms.
v3:
     - removed bug checks, replaced with gen check.
v4:
     - change code for scratch page insertion to support all platforms,
     - add info in commit message there could be more similar issues

Regards
Andrzej
---
  drivers/gpu/drm/i915/gt/intel_ggtt.c | 31 ++++++++++++++++++++++++----
  1 file changed, 27 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_ggtt.c 
b/drivers/gpu/drm/i915/gt/intel_ggtt.c
index 842e69c7b21e49..6566d2066f1f8b 100644
--- a/drivers/gpu/drm/i915/gt/intel_ggtt.c
+++ b/drivers/gpu/drm/i915/gt/intel_ggtt.c
@@ -503,6 +503,21 @@ static void cleanup_init_ggtt(struct i915_ggtt 
*ggtt)
      mutex_destroy(&ggtt->error_mutex);
  }
  +static void
+ggtt_insert_scratch_pages(struct i915_ggtt *ggtt, u64 offset, u64 
length)
+{
+    struct i915_address_space *vm = &ggtt->vm;
+
+    if (GRAPHICS_VER(ggtt->vm.i915) < 8)
+        return vm->clear_range(vm, offset, length);
+    /* clear_range since gen8 is nop */

It would also work to simply drop the <gen8 case and just do the loop 
below, right? If so would that be clearer?

+    while (length > 0) {

Maybe add a GEM_BUG_ON if length is not aligned? Granted it may be a 
huge stretch of imagination..

Regards,

Tvrtko

+        vm->insert_page(vm, px_dma(vm->scratch[0]), offset, 
I915_CACHE_NONE, 0);
+        offset += I915_GTT_PAGE_SIZE;
+        length -= I915_GTT_PAGE_SIZE;
+    }
+}
+
  static int init_ggtt(struct i915_ggtt *ggtt)
  {
      /*
@@ -551,8 +566,12 @@ static int init_ggtt(struct i915_ggtt *ggtt)
           * paths, and we trust that 0 will remain reserved. However,
           * the only likely reason for failure to insert is a driver
           * bug, which we expect to cause other failures...
+         *
+         * Since CPU can perform speculative reads on error capture
+         * (write-combining allows it) add scratch page after error
+         * capture to avoid DMAR errors.
           */
-        ggtt->error_capture.size = I915_GTT_PAGE_SIZE;
+        ggtt->error_capture.size = 2 * I915_GTT_PAGE_SIZE;
          ggtt->error_capture.color = I915_COLOR_UNEVICTABLE;
          if (drm_mm_reserve_node(&ggtt->vm.mm, &ggtt->error_capture))
              drm_mm_insert_node_in_range(&ggtt->vm.mm,
@@ -562,11 +581,15 @@ static int init_ggtt(struct i915_ggtt *ggtt)
                              0, ggtt->mappable_end,
                              DRM_MM_INSERT_LOW);
      }
-    if (drm_mm_node_allocated(&ggtt->error_capture))
+    if (drm_mm_node_allocated(&ggtt->error_capture)) {
+        u64 start = ggtt->error_capture.start;
+        u64 size = ggtt->error_capture.size;
+
+        ggtt_insert_scratch_pages(ggtt, start, size);
          drm_dbg(&ggtt->vm.i915->drm,
              "Reserved GGTT:[%llx, %llx] for use by error capture\n",
-            ggtt->error_capture.start,
-            ggtt->error_capture.start + ggtt->error_capture.size);
+            start, start + size);
+    }
        /*
       * The upper portion of the GuC address space has a sizeable hole







