Skip to contentSkip to conversation

Add support for dumping error captures via kernel logging

PATCH In review [email protected] 4 participants 13 messages Apr 18, 2023 – May 16, 2023

Subsystems (2)
lore
Share & tools
lore
#0 lore raw

v2 cover Add support for dumping error captures via kernel logging

From: John Harrison <[email protected]>

Sometimes, the only effective way to debug an issue is to dump all the interesting information at the point of failure. So add support for doing that.

v2: Extra CONFIG wrapping (review feedback from Rodrigo)

John Harrison (2):
drm/i915: Dump error capture to kernel log drm/i915/guc: Dump error capture to dmesg on CTB error

 drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c |  53 +++++++++
 drivers/gpu/drm/i915/gt/uc/intel_guc_ct.h |   6 +
 drivers/gpu/drm/i915/i915_gpu_error.c     | 132 ++++++++++++++++++++++
 drivers/gpu/drm/i915/i915_gpu_error.h     |  10 ++
 4 files changed, 201 insertions(+)
Signature · 1 line
2.39.1
#1 lore raw

PATCH v2 1/2 drm/i915: Dump error capture to kernel log

From: John Harrison <[email protected]>

This is useful for getting debug information out in certain situations, such as failing kernel selftests and CI runs that don't log error captures. It is especially useful for things like retrieving GuC logs as GuC operation can't be tracked by adding printk or ftrace entries.

v2: Add CONFIG_DRM_I915_DEBUG_GEM wrapper (review feedback by Rodrigo).

---
 drivers/gpu/drm/i915/i915_gpu_error.c | 132 ++++++++++++++++++++++++++
 drivers/gpu/drm/i915/i915_gpu_error.h |  10 ++
 2 files changed, 142 insertions(+)
drivers/gpu/drm/i915/i915_gpu_error.c +132 -0
index f020c0086fbcd..03d62c250c465 100644
@@ -2219,3 +2219,135 @@ void i915_disable_error_state(struct drm_i915_private *i915, int err)
 		i915->gpu_error.first_error = ERR_PTR(err);
 	spin_unlock_irq(&i915->gpu_error.lock);
 }
+
+#if IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM)
+void intel_klog_error_capture(struct intel_gt *gt,
+			      intel_engine_mask_t engine_mask)
+{
+	static int g_count;
+	struct drm_i915_private *i915 = gt->i915;
+	struct i915_gpu_coredump *error;
+	intel_wakeref_t wakeref;
+	size_t buf_size = PAGE_SIZE * 128;
+	size_t pos_err;
+	char *buf, *ptr, *next;
+	int l_count = g_count++;
+	int line = 0;
+
+	/* Can't allocate memory during a reset */
+	if (test_bit(I915_RESET_BACKOFF, &gt->reset.flags)) {
+		drm_err(&gt->i915->drm, "[Capture/%d.%d] Inside GT reset, skipping error capture :(\n",
+			l_count, line++);
+		return;
+	}
+
+	error = READ_ONCE(i915->gpu_error.first_error);
+	if (error) {
+		drm_err(&i915->drm, "[Capture/%d.%d] Clearing existing error capture first...\n",
+			l_count, line++);
+		i915_reset_error_state(i915);
+	}
+
+	with_intel_runtime_pm(&i915->runtime_pm, wakeref)
+		error = i915_gpu_coredump(gt, engine_mask, CORE_DUMP_FLAG_NONE);
+
+	if (IS_ERR(error)) {
+		drm_err(&i915->drm, "[Capture/%d.%d] Failed to capture error capture: %ld!\n",
+			l_count, line++, PTR_ERR(error));
+		return;
+	}
+
+	buf = kvmalloc(buf_size, GFP_KERNEL);
+	if (!buf) {
+		drm_err(&i915->drm, "[Capture/%d.%d] Failed to allocate buffer for error capture!\n",
+			l_count, line++);
+		i915_gpu_coredump_put(error);
+		return;
+	}
+
+	drm_info(&i915->drm, "[Capture/%d.%d] Dumping i915 error capture for %ps...\n",
+		 l_count, line++, __builtin_return_address(0));
+
+	/* Largest string length safe to print via dmesg */
+#	define MAX_CHUNK	800
+
+	pos_err = 0;
+	while (1) {
+		ssize_t got = i915_gpu_coredump_copy_to_buffer(error, buf, pos_err, buf_size - 1);
+
+		if (got <= 0)
+			break;
+
+		buf[got] = 0;
+		pos_err += got;
+
+		ptr = buf;
+		while (got > 0) {
+			size_t count;
+			char tag[2];
+
+			next = strnchr(ptr, got, '\n');
+			if (next) {
+				count = next - ptr;
+				*next = 0;
+				tag[0] = '>';
+				tag[1] = '<';
+			} else {
+				count = got;
+				tag[0] = '}';
+				tag[1] = '{';
+			}
+
+			if (count > MAX_CHUNK) {
+				size_t pos;
+				char *ptr2 = ptr;
+
+				for (pos = MAX_CHUNK; pos < count; pos += MAX_CHUNK) {
+					char chr = ptr[pos];
+
+					ptr[pos] = 0;
+					drm_info(&i915->drm, "[Capture/%d.%d] }%s{\n",
+						 l_count, line++, ptr2);
+					ptr[pos] = chr;
+					ptr2 = ptr + pos;
+
+					/*
+					 * If spewing large amounts of data via a serial console,
+					 * this can be a very slow process. So be friendly and try
+					 * not to cause 'softlockup on CPU' problems.
+					 */
+					cond_resched();
+				}
+
+				if (ptr2 < (ptr + count))
+					drm_info(&i915->drm, "[Capture/%d.%d] %c%s%c\n",
+						 l_count, line++, tag[0], ptr2, tag[1]);
+				else if (tag[0] == '>')
+					drm_info(&i915->drm, "[Capture/%d.%d] ><\n",
+						 l_count, line++);
+			} else {
+				drm_info(&i915->drm, "[Capture/%d.%d] %c%s%c\n",
+					 l_count, line++, tag[0], ptr, tag[1]);
+			}
+
+			ptr = next;
+			got -= count;
+			if (next) {
+				ptr++;
+				got--;
+			}
+
+			/* As above. */
+			cond_resched();
+		}
+
+		if (got)
+			drm_info(&i915->drm, "[Capture/%d.%d] Got %zd bytes remaining!\n",
+				 l_count, line++, got);
+	}
+
+	kvfree(buf);
+
+	drm_info(&i915->drm, "[Capture/%d.%d] Dumped %zd bytes\n", l_count, line++, pos_err);
+}
+#endif
drivers/gpu/drm/i915/i915_gpu_error.h +10 -0
index a91932cc65317..a78c061ce26fb 100644
@@ -258,6 +258,16 @@ static inline u32 i915_reset_engine_count(struct i915_gpu_error *error,
 #define CORE_DUMP_FLAG_NONE           0x0
 #define CORE_DUMP_FLAG_IS_GUC_CAPTURE BIT(0)
 
+#if IS_ENABLED(CONFIG_DRM_I915_CAPTURE_ERROR) && IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM)
+void intel_klog_error_capture(struct intel_gt *gt,
+			      intel_engine_mask_t engine_mask);
+#else
+static inline void intel_klog_error_capture(struct intel_gt *gt,
+					    intel_engine_mask_t engine_mask)
+{
+}
+#endif
+
 #if IS_ENABLED(CONFIG_DRM_I915_CAPTURE_ERROR)
 
 __printf(2, 3)
Signature · 1 line
2.39.1
Reviewed-by on v2 1/2
#2 lore raw

Re: [Intel-gfx] [PATCH v2 1/2] drm/i915: Dump error capture to kernel log

Quoted 9 lines · On 4/18/2023 11:17 AM, [email protected] wrote:

From: John Harrison <[email protected]>

This is useful for getting debug information out in certain situations, such as failing kernel selftests and CI runs that don't log error captures. It is especially useful for things like retrieving GuC logs as GuC operation can't be tracked by adding printk or ftrace entries.

v2: Add CONFIG_DRM_I915_DEBUG_GEM wrapper (review feedback by Rodrigo).

Do the CI sparse warnings hold water? With that looked at,

LGTM,

Quoted 168 lines
---
  drivers/gpu/drm/i915/i915_gpu_error.c | 132 ++++++++++++++++++++++++++
  drivers/gpu/drm/i915/i915_gpu_error.h |  10 ++
  2 files changed, 142 insertions(+)
drivers/gpu/drm/i915/i915_gpu_error.c +132 -0
index f020c0086fbcd..03d62c250c465 100644
@@ -2219,3 +2219,135 @@ void i915_disable_error_state(struct drm_i915_private *i915, int err)
  		i915->gpu_error.first_error = ERR_PTR(err);
  	spin_unlock_irq(&i915->gpu_error.lock);
  }
+
+#if IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM)
+void intel_klog_error_capture(struct intel_gt *gt,
+			      intel_engine_mask_t engine_mask)
+{
+	static int g_count;
+	struct drm_i915_private *i915 = gt->i915;
+	struct i915_gpu_coredump *error;
+	intel_wakeref_t wakeref;
+	size_t buf_size = PAGE_SIZE * 128;
+	size_t pos_err;
+	char *buf, *ptr, *next;
+	int l_count = g_count++;
+	int line = 0;
+
+	/* Can't allocate memory during a reset */
+	if (test_bit(I915_RESET_BACKOFF, &gt->reset.flags)) {
+		drm_err(&gt->i915->drm, "[Capture/%d.%d] Inside GT reset, skipping error capture :(\n",
+			l_count, line++);
+		return;
+	}
+
+	error = READ_ONCE(i915->gpu_error.first_error);
+	if (error) {
+		drm_err(&i915->drm, "[Capture/%d.%d] Clearing existing error capture first...\n",
+			l_count, line++);
+		i915_reset_error_state(i915);
+	}
+
+	with_intel_runtime_pm(&i915->runtime_pm, wakeref)
+		error = i915_gpu_coredump(gt, engine_mask, CORE_DUMP_FLAG_NONE);
+
+	if (IS_ERR(error)) {
+		drm_err(&i915->drm, "[Capture/%d.%d] Failed to capture error capture: %ld!\n",
+			l_count, line++, PTR_ERR(error));
+		return;
+	}
+
+	buf = kvmalloc(buf_size, GFP_KERNEL);
+	if (!buf) {
+		drm_err(&i915->drm, "[Capture/%d.%d] Failed to allocate buffer for error capture!\n",
+			l_count, line++);
+		i915_gpu_coredump_put(error);
+		return;
+	}
+
+	drm_info(&i915->drm, "[Capture/%d.%d] Dumping i915 error capture for %ps...\n",
+		 l_count, line++, __builtin_return_address(0));
+
+	/* Largest string length safe to print via dmesg */
+#	define MAX_CHUNK	800
+
+	pos_err = 0;
+	while (1) {
+		ssize_t got = i915_gpu_coredump_copy_to_buffer(error, buf, pos_err, buf_size - 1);
+
+		if (got <= 0)
+			break;
+
+		buf[got] = 0;
+		pos_err += got;
+
+		ptr = buf;
+		while (got > 0) {
+			size_t count;
+			char tag[2];
+
+			next = strnchr(ptr, got, '\n');
+			if (next) {
+				count = next - ptr;
+				*next = 0;
+				tag[0] = '>';
+				tag[1] = '<';
+			} else {
+				count = got;
+				tag[0] = '}';
+				tag[1] = '{';
+			}
+
+			if (count > MAX_CHUNK) {
+				size_t pos;
+				char *ptr2 = ptr;
+
+				for (pos = MAX_CHUNK; pos < count; pos += MAX_CHUNK) {
+					char chr = ptr[pos];
+
+					ptr[pos] = 0;
+					drm_info(&i915->drm, "[Capture/%d.%d] }%s{\n",
+						 l_count, line++, ptr2);
+					ptr[pos] = chr;
+					ptr2 = ptr + pos;
+
+					/*
+					 * If spewing large amounts of data via a serial console,
+					 * this can be a very slow process. So be friendly and try
+					 * not to cause 'softlockup on CPU' problems.
+					 */
+					cond_resched();
+				}
+
+				if (ptr2 < (ptr + count))
+					drm_info(&i915->drm, "[Capture/%d.%d] %c%s%c\n",
+						 l_count, line++, tag[0], ptr2, tag[1]);
+				else if (tag[0] == '>')
+					drm_info(&i915->drm, "[Capture/%d.%d] ><\n",
+						 l_count, line++);
+			} else {
+				drm_info(&i915->drm, "[Capture/%d.%d] %c%s%c\n",
+					 l_count, line++, tag[0], ptr, tag[1]);
+			}
+
+			ptr = next;
+			got -= count;
+			if (next) {
+				ptr++;
+				got--;
+			}
+
+			/* As above. */
+			cond_resched();
+		}
+
+		if (got)
+			drm_info(&i915->drm, "[Capture/%d.%d] Got %zd bytes remaining!\n",
+				 l_count, line++, got);
+	}
+
+	kvfree(buf);
+
+	drm_info(&i915->drm, "[Capture/%d.%d] Dumped %zd bytes\n", l_count, line++, pos_err);
+}
+#endif
drivers/gpu/drm/i915/i915_gpu_error.h +10 -0
index a91932cc65317..a78c061ce26fb 100644
@@ -258,6 +258,16 @@ static inline u32 i915_reset_engine_count(struct i915_gpu_error *error,
  #define CORE_DUMP_FLAG_NONE           0x0
  #define CORE_DUMP_FLAG_IS_GUC_CAPTURE BIT(0)
 
+#if IS_ENABLED(CONFIG_DRM_I915_CAPTURE_ERROR) && IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM)
+void intel_klog_error_capture(struct intel_gt *gt,
+			      intel_engine_mask_t engine_mask);
+#else
+static inline void intel_klog_error_capture(struct intel_gt *gt,
+					    intel_engine_mask_t engine_mask)
+{
+}
+#endif
+
  #if IS_ENABLED(CONFIG_DRM_I915_CAPTURE_ERROR)
 
  __printf(2, 3)
#3 lore raw

Re: [Intel-gfx] [PATCH v2 1/2] drm/i915: Dump error capture to kernel log

Quoted 9 lines · Vinay
Quoted 8 lines · On 4/18/2023 11:17 AM, [email protected] wrote:

From: John Harrison <[email protected]>

This is useful for getting debug information out in certain situations, such as failing kernel selftests and CI runs that don't log error captures. It is especially useful for things like retrieving GuC logs as GuC operation can't be tracked by adding printk or ftrace entries.

Quoted 3 lines
Quoted 1 line

v2: Add CONFIG_DRM_I915_DEBUG_GEM wrapper (review feedback by Rodrigo).

Do the CI sparse warnings hold water? With that looked at,

You mean this one totally fatal and absolutely must be fixed error?

Fast mode used, each commit won't be checked separately.

Does anyone even know what that means or why it (apparently totally randomly) hits some patch sets and not others?

If you mean the checkpatch warnings. One is about not reporting out of memory errors (because you are supposed to return -ENOMEM and let the user handle it instead), but that doesn't apply for an internal kernel only thing which is already just a debug print. The other is about macro argument re-use, which is not an issue in this case and not worth re-writing the code to avoid.

John.

Quoted 184 lines

LGTM,

Quoted 179 lines

---
  drivers/gpu/drm/i915/i915_gpu_error.c | 132 ++++++++++++++++++++++++++ drivers/gpu/drm/i915/i915_gpu_error.h |  10 ++

  2 files changed, 142 insertions(+)
drivers/gpu/drm/i915/i915_gpu_error.c +0 -0
index f020c0086fbcd..03d62c250c465 100644
@@ -2219,3 +2219,135 @@ void i915_disable_error_state(struct 
 drm_i915_private *i915, int err)
           i915->gpu_error.first_error = ERR_PTR(err);
       spin_unlock_irq(&i915->gpu_error.lock);

  }

drivers/gpu/drm/i915/i915_gpu_error.c +18 -0
+
+#if IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM)
+void intel_klog_error_capture(struct intel_gt *gt,
+                  intel_engine_mask_t engine_mask)
+{
+    static int g_count;
+    struct drm_i915_private *i915 = gt->i915;
+    struct i915_gpu_coredump *error;
+    intel_wakeref_t wakeref;
+    size_t buf_size = PAGE_SIZE * 128;
+    size_t pos_err;
+    char *buf, *ptr, *next;
+    int l_count = g_count++;
+    int line = 0;
+
+    /* Can't allocate memory during a reset */
+    if (test_bit(I915_RESET_BACKOFF, &gt->reset.flags)) {
+        drm_err(&gt->i915->drm, "[Capture/%d.%d] Inside GT reset, 

skipping error capture :(\n",
+            l_count, line++);
+        return;
+    }
+
+    error = READ_ONCE(i915->gpu_error.first_error);
+    if (error) {
+        drm_err(&i915->drm, "[Capture/%d.%d] Clearing existing error capture first...\n",
+            l_count, line++);
+        i915_reset_error_state(i915);
+    }
+
+    with_intel_runtime_pm(&i915->runtime_pm, wakeref)
+        error = i915_gpu_coredump(gt, engine_mask, CORE_DUMP_FLAG_NONE);
+
+    if (IS_ERR(error)) {
+        drm_err(&i915->drm, "[Capture/%d.%d] Failed to capture error
capture: %ld!\n",
+            l_count, line++, PTR_ERR(error));
+        return;
+    }
+
+    buf = kvmalloc(buf_size, GFP_KERNEL);
+    if (!buf) {
+        drm_err(&i915->drm, "[Capture/%d.%d] Failed to allocate buffer for error capture!\n",
+            l_count, line++);
+        i915_gpu_coredump_put(error);
+        return;
+    }
+
+    drm_info(&i915->drm, "[Capture/%d.%d] Dumping i915 error capture for %ps...\n",
+         l_count, line++, __builtin_return_address(0));

drivers/gpu/drm/i915/i915_gpu_error.c +7 -0
+
+    /* Largest string length safe to print via dmesg */
+#    define MAX_CHUNK    800
+
+    pos_err = 0;
+    while (1) {
+        ssize_t got = i915_gpu_coredump_copy_to_buffer(error, buf, 

pos_err, buf_size - 1);

drivers/gpu/drm/i915/i915_gpu_error.c +39 -0
+
+        if (got <= 0)
+            break;
+
+        buf[got] = 0;
+        pos_err += got;
+
+        ptr = buf;
+        while (got > 0) {
+            size_t count;
+            char tag[2];
+
+            next = strnchr(ptr, got, '\n');
+            if (next) {
+                count = next - ptr;
+                *next = 0;
+                tag[0] = '>';
+                tag[1] = '<';
+            } else {
+                count = got;
+                tag[0] = '}';
+                tag[1] = '{';
+            }
+
+            if (count > MAX_CHUNK) {
+                size_t pos;
+                char *ptr2 = ptr;
+
+                for (pos = MAX_CHUNK; pos < count; pos += MAX_CHUNK) {
+                    char chr = ptr[pos];
+
+                    ptr[pos] = 0;
+                    drm_info(&i915->drm, "[Capture/%d.%d] }%s{\n",
+                         l_count, line++, ptr2);
+                    ptr[pos] = chr;
+                    ptr2 = ptr + pos;
+
+                    /*
+                     * If spewing large amounts of data via a serial 

console,
+                     * this can be a very slow process. So be friendly and try
+                     * not to cause 'softlockup on CPU' problems. +                     */
+                    cond_resched();
+                }

drivers/gpu/drm/i915/i915_gpu_error.c +25 -0
+
+                if (ptr2 < (ptr + count))
+                    drm_info(&i915->drm, "[Capture/%d.%d] %c%s%c\n",
+                         l_count, line++, tag[0], ptr2, tag[1]);
+                else if (tag[0] == '>')
+                    drm_info(&i915->drm, "[Capture/%d.%d] ><\n",
+                         l_count, line++);
+            } else {
+                drm_info(&i915->drm, "[Capture/%d.%d] %c%s%c\n",
+                     l_count, line++, tag[0], ptr, tag[1]);
+            }
+
+            ptr = next;
+            got -= count;
+            if (next) {
+                ptr++;
+                got--;
+            }
+
+            /* As above. */
+            cond_resched();
+        }
+
+        if (got)
+            drm_info(&i915->drm, "[Capture/%d.%d] Got %zd bytes 

remaining!\n",
+                 l_count, line++, got);
+    }

drivers/gpu/drm/i915/i915_gpu_error.c +4 -0
+
+    kvfree(buf);
+
+    drm_info(&i915->drm, "[Capture/%d.%d] Dumped %zd bytes\n", 

l_count, line++, pos_err);

drivers/gpu/drm/i915/i915_gpu_error.c +2 -0
+}
+#endif
drivers/gpu/drm/i915/i915_gpu_error.h +9 -0
index a91932cc65317..a78c061ce26fb 100644
@@ -258,6 +258,16 @@ static inline u32 i915_reset_engine_count(struct 
 i915_gpu_error *error,
   #define CORE_DUMP_FLAG_NONE           0x0
   #define CORE_DUMP_FLAG_IS_GUC_CAPTURE BIT(0)
   +#if IS_ENABLED(CONFIG_DRM_I915_CAPTURE_ERROR) && IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM)
+void intel_klog_error_capture(struct intel_gt *gt,
+                  intel_engine_mask_t engine_mask);
+#else
+static inline void intel_klog_error_capture(struct intel_gt *gt,
+                        intel_engine_mask_t engine_mask)
+{
+}
+#endif
+
   #if IS_ENABLED(CONFIG_DRM_I915_CAPTURE_ERROR)
     __printf(2, 3)
#4 lore raw

Re: [Intel-gfx] [PATCH v2 1/2] drm/i915: Dump error capture to kernel log

Quoted 6 lines · John Harrison
Quoted 3 lines · Vinay
Quoted 1 line · On 4/18/2023 11:17 AM, [1][email protected] wrote:

From: John Harrison [2]<[email protected]>

Quoted 7 lines
Quoted 7 lines
Quoted 7 lines

This is useful for getting debug information out in certain situations, such as failing kernel selftests and CI runs that don't log error captures. It is especially useful for things like retrieving GuC logs as GuC operation can't be tracked by adding printk or ftrace entries.

v2: Add CONFIG_DRM_I915_DEBUG_GEM wrapper (review feedback by Rodrigo).

Thanks

Quoted 6 lines
Quoted 2 lines

Do the CI sparse warnings hold water? With that looked at,

You mean this one totally fatal and absolutely must be fixed error?

Fast mode used, each commit won't be checked separately.

You should never rely on this assumption. There are bisects and autobisects out there. Also every patch needs to be independently available for backport.

So, if there's any issue it needs to be fix before we merge.

Quoted 207 lines
                                                                                
   Does anyone even know what that means or why it (apparently totally          
   randomly) hits some patch sets and not others?                               
                                                                                
   If you mean the checkpatch warnings. One is about not reporting out of       
   memory errors (because you are supposed to return -ENOMEM and let the user   
   handle it instead), but that doesn't apply for an internal kernel only       
   thing which is already just a debug print. The other is about macro          
   argument re-use, which is not an issue in this case and not worth            
   re-writing the code to avoid.                                                
                                                                                
   John.                                                                        
                                                                                
   > LGTM,                                                                      
                                                                                
   > Reviewed-by: Vinay Belgaumkar [3]<[email protected]>              
                                                                                
   >> Signed-off-by: John Harrison [4]<[email protected]>               
   >> ---                                                                       
   >>   drivers/gpu/drm/i915/i915_gpu_error.c | 132                             
   >> ++++++++++++++++++++++++++                                                
   >>   drivers/gpu/drm/i915/i915_gpu_error.h |  10 ++                          
   >>   2 files changed, 142 insertions(+)                                      
                                                                                
   >> diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c                        
   >> b/drivers/gpu/drm/i915/i915_gpu_error.c                                   
   >> index f020c0086fbcd..03d62c250c465 100644                                 
   >> --- a/drivers/gpu/drm/i915/i915_gpu_error.c                               
   >> +++ b/drivers/gpu/drm/i915/i915_gpu_error.c                               
   >> @@ -2219,3 +2219,135 @@ void i915_disable_error_state(struct              
   >> drm_i915_private *i915, int err)                                          
   >>           i915->gpu_error.first_error = ERR_PTR(err);                     
   >>       spin_unlock_irq(&i915->gpu_error.lock);                             
   >>   }                                                                       
   >> +                                                                         
   >> +#if IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM)                                
   >> +void intel_klog_error_capture(struct intel_gt *gt,                       
   >> +                  intel_engine_mask_t engine_mask)                       
   >> +{                                                                        
   >> +    static int g_count;                                                  
   >> +    struct drm_i915_private *i915 = gt->i915;                            
   >> +    struct i915_gpu_coredump *error;                                     
   >> +    intel_wakeref_t wakeref;                                             
   >> +    size_t buf_size = PAGE_SIZE * 128;                                   
   >> +    size_t pos_err;                                                      
   >> +    char *buf, *ptr, *next;                                              
   >> +    int l_count = g_count++;                                             
   >> +    int line = 0;                                                        
   >> +                                                                         
   >> +    /* Can't allocate memory during a reset */                           
   >> +    if (test_bit(I915_RESET_BACKOFF, &gt->reset.flags)) {                
   >> +        drm_err(&gt->i915->drm, "[Capture/%d.%d] Inside GT reset,        
   >> skipping error capture :(\n",                                             
   >> +            l_count, line++);                                            
   >> +        return;                                                          
   >> +    }                                                                    
   >> +                                                                         
   >> +    error = READ_ONCE(i915->gpu_error.first_error);                      
   >> +    if (error) {                                                         
   >> +        drm_err(&i915->drm, "[Capture/%d.%d] Clearing existing error     
   >> capture first...\n",                                                      
   >> +            l_count, line++);                                            
   >> +        i915_reset_error_state(i915);                                    
   >> +    }                                                                    
   >> +                                                                         
   >> +    with_intel_runtime_pm(&i915->runtime_pm, wakeref)                    
   >> +        error = i915_gpu_coredump(gt, engine_mask,                       
   >> CORE_DUMP_FLAG_NONE);                                                     
   >> +                                                                         
   >> +    if (IS_ERR(error)) {                                                 
   >> +        drm_err(&i915->drm, "[Capture/%d.%d] Failed to capture error     
   >> capture: %ld!\n",                                                         
   >> +            l_count, line++, PTR_ERR(error));                            
   >> +        return;                                                          
   >> +    }                                                                    
   >> +                                                                         
   >> +    buf = kvmalloc(buf_size, GFP_KERNEL);                                
   >> +    if (!buf) {                                                          
   >> +        drm_err(&i915->drm, "[Capture/%d.%d] Failed to allocate buffer   
   >> for error capture!\n",                                                    
   >> +            l_count, line++);                                            
   >> +        i915_gpu_coredump_put(error);                                    
   >> +        return;                                                          
   >> +    }                                                                    
   >> +                                                                         
   >> +    drm_info(&i915->drm, "[Capture/%d.%d] Dumping i915 error capture     
   >> for %ps...\n",                                                            
   >> +         l_count, line++, __builtin_return_address(0));                  
   >> +                                                                         
   >> +    /* Largest string length safe to print via dmesg */                  
   >> +#    define MAX_CHUNK    800                                             
   >> +                                                                         
   >> +    pos_err = 0;                                                         
   >> +    while (1) {                                                          
   >> +        ssize_t got = i915_gpu_coredump_copy_to_buffer(error, buf,       
   >> pos_err, buf_size - 1);                                                   
   >> +                                                                         
   >> +        if (got <= 0)                                                    
   >> +            break;                                                       
   >> +                                                                         
   >> +        buf[got] = 0;                                                    
   >> +        pos_err += got;                                                  
   >> +                                                                         
   >> +        ptr = buf;                                                       
   >> +        while (got > 0) {                                                
   >> +            size_t count;                                                
   >> +            char tag[2];                                                 
   >> +                                                                         
   >> +            next = strnchr(ptr, got, '\n');                              
   >> +            if (next) {                                                  
   >> +                count = next - ptr;                                      
   >> +                *next = 0;                                               
   >> +                tag[0] = '>';                                            
   >> +                tag[1] = '<';                                            
   >> +            } else {                                                     
   >> +                count = got;                                             
   >> +                tag[0] = '}';                                            
   >> +                tag[1] = '{';                                            
   >> +            }                                                            
   >> +                                                                         
   >> +            if (count > MAX_CHUNK) {                                     
   >> +                size_t pos;                                              
   >> +                char *ptr2 = ptr;                                        
   >> +                                                                         
   >> +                for (pos = MAX_CHUNK; pos < count; pos += MAX_CHUNK) {   
   >> +                    char chr = ptr[pos];                                 
   >> +                                                                         
   >> +                    ptr[pos] = 0;                                        
   >> +                    drm_info(&i915->drm, "[Capture/%d.%d] }%s{\n",       
   >> +                         l_count, line++, ptr2);                         
   >> +                    ptr[pos] = chr;                                      
   >> +                    ptr2 = ptr + pos;                                    
   >> +                                                                         
   >> +                    /*                                                   
   >> +                     * If spewing large amounts of data via a serial     
   >> console,                                                                  
   >> +                     * this can be a very slow process. So be friendly   
   >> and try                                                                   
   >> +                     * not to cause 'softlockup on CPU' problems.        
   >> +                     */                                                  
   >> +                    cond_resched();                                      
   >> +                }                                                        
   >> +                                                                         
   >> +                if (ptr2 < (ptr + count))                                
   >> +                    drm_info(&i915->drm, "[Capture/%d.%d] %c%s%c\n",     
   >> +                         l_count, line++, tag[0], ptr2, tag[1]);         
   >> +                else if (tag[0] == '>')                                  
   >> +                    drm_info(&i915->drm, "[Capture/%d.%d] ><\n",         
   >> +                         l_count, line++);                               
   >> +            } else {                                                     
   >> +                drm_info(&i915->drm, "[Capture/%d.%d] %c%s%c\n",         
   >> +                     l_count, line++, tag[0], ptr, tag[1]);              
   >> +            }                                                            
   >> +                                                                         
   >> +            ptr = next;                                                  
   >> +            got -= count;                                                
   >> +            if (next) {                                                  
   >> +                ptr++;                                                   
   >> +                got--;                                                   
   >> +            }                                                            
   >> +                                                                         
   >> +            /* As above. */                                              
   >> +            cond_resched();                                              
   >> +        }                                                                
   >> +                                                                         
   >> +        if (got)                                                         
   >> +            drm_info(&i915->drm, "[Capture/%d.%d] Got %zd bytes          
   >> remaining!\n",                                                            
   >> +                 l_count, line++, got);                                  
   >> +    }                                                                    
   >> +                                                                         
   >> +    kvfree(buf);                                                         
   >> +                                                                         
   >> +    drm_info(&i915->drm, "[Capture/%d.%d] Dumped %zd bytes\n",           
   >> l_count, line++, pos_err);                                                
   >> +}                                                                        
   >> +#endif                                                                   
   >> diff --git a/drivers/gpu/drm/i915/i915_gpu_error.h                        
   >> b/drivers/gpu/drm/i915/i915_gpu_error.h                                   
   >> index a91932cc65317..a78c061ce26fb 100644                                 
   >> --- a/drivers/gpu/drm/i915/i915_gpu_error.h                               
   >> +++ b/drivers/gpu/drm/i915/i915_gpu_error.h                               
   >> @@ -258,6 +258,16 @@ static inline u32 i915_reset_engine_count(struct     
   >> i915_gpu_error *error,                                                    
   >>   #define CORE_DUMP_FLAG_NONE           0x0                               
   >>   #define CORE_DUMP_FLAG_IS_GUC_CAPTURE BIT(0)                            
   >>   +#if IS_ENABLED(CONFIG_DRM_I915_CAPTURE_ERROR) &&                       
   >> IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM)                                     
   >> +void intel_klog_error_capture(struct intel_gt *gt,                       
   >> +                  intel_engine_mask_t engine_mask);                      
   >> +#else                                                                    
   >> +static inline void intel_klog_error_capture(struct intel_gt *gt,         
   >> +                        intel_engine_mask_t engine_mask)                 
   >> +{                                                                        
   >> +}                                                                        
   >> +#endif                                                                   
   >> +                                                                         
   >>   #if IS_ENABLED(CONFIG_DRM_I915_CAPTURE_ERROR)                           
   >>     __printf(2, 3)                                                        

References

Visible links
1. mailto:[email protected]
2. mailto:[email protected]
3. mailto:[email protected]
4. mailto:[email protected]

#5 lore raw

Re: [Intel-gfx] [PATCH v2 1/2] drm/i915: Dump error capture to kernel log

Quoted 19 lines · Rodrigo Vivi
Quoted 6 lines · John Harrison

On 5/16/2023 12:17, Belgaumkar, Vinay wrote:

> On 4/18/2023 11:17 AM, [1][email protected] wrote:

>> From: John Harrison [2]<[email protected]>

Quoted 7 lines

>> This is useful for getting debug information out in certain >> situations, such as failing kernel selftests and CI runs that don't >> log error captures. It is especially useful for things like retrieving >> GuC logs as GuC operation can't be tracked by adding printk or ftrace >> entries.

>> v2: Add CONFIG_DRM_I915_DEBUG_GEM wrapper (review feedback by Rodrigo).

Thanks

Quoted 3 lines
Quoted 2 lines

Do the CI sparse warnings hold water? With that looked at,

Quoted 7 lines
Quoted 3 lines

You mean this one totally fatal and absolutely must be fixed error?

Fast mode used, each commit won't be checked separately.

You should never rely on this assumption. There are bisects and autobisects out there. Also every patch needs to be independently available for backport.

So, if there's any issue it needs to be fix before we merge.

What assumption? That sparse claims failure even when there are no errors at all, just a notice about 'fast mode used'?  If there are errors, please point out where I can find them. AFAICT, the sparse email is actually saying the patch set is clean despite the fact it has a big red cross on it.

John.

Quoted 208 lines
Quoted 208 lines
                                                                                 
    Does anyone even know what that means or why it (apparently totally
    randomly) hits some patch sets and not others?
                                                                                 
    If you mean the checkpatch warnings. One is about not reporting out of
    memory errors (because you are supposed to return -ENOMEM and let the user
    handle it instead), but that doesn't apply for an internal kernel only
    thing which is already just a debug print. The other is about macro
    argument re-use, which is not an issue in this case and not worth
    re-writing the code to avoid.
                                                                                 
    John.
                                                                                 
    > LGTM,
                                                                                 
    > Reviewed-by: Vinay Belgaumkar [3]<[email protected]>
                                                                                 
    >> Signed-off-by: John Harrison [4]<[email protected]>
    >> ---
    >>   drivers/gpu/drm/i915/i915_gpu_error.c | 132
    >> ++++++++++++++++++++++++++
    >>   drivers/gpu/drm/i915/i915_gpu_error.h |  10 ++
    >>   2 files changed, 142 insertions(+)
                                                                                 
    >> diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c
    >> b/drivers/gpu/drm/i915/i915_gpu_error.c
    >> index f020c0086fbcd..03d62c250c465 100644
    >> --- a/drivers/gpu/drm/i915/i915_gpu_error.c
    >> +++ b/drivers/gpu/drm/i915/i915_gpu_error.c
    >> @@ -2219,3 +2219,135 @@ void i915_disable_error_state(struct
    >> drm_i915_private *i915, int err)
    >>           i915->gpu_error.first_error = ERR_PTR(err);
    >>       spin_unlock_irq(&i915->gpu_error.lock);
    >>   }
    >> +
    >> +#if IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM)
    >> +void intel_klog_error_capture(struct intel_gt *gt,
    >> +                  intel_engine_mask_t engine_mask)
    >> +{
    >> +    static int g_count;
    >> +    struct drm_i915_private *i915 = gt->i915;
    >> +    struct i915_gpu_coredump *error;
    >> +    intel_wakeref_t wakeref;
    >> +    size_t buf_size = PAGE_SIZE * 128;
    >> +    size_t pos_err;
    >> +    char *buf, *ptr, *next;
    >> +    int l_count = g_count++;
    >> +    int line = 0;
    >> +
    >> +    /* Can't allocate memory during a reset */
    >> +    if (test_bit(I915_RESET_BACKOFF, &gt->reset.flags)) {
    >> +        drm_err(&gt->i915->drm, "[Capture/%d.%d] Inside GT reset,
    >> skipping error capture :(\n",
    >> +            l_count, line++);
    >> +        return;
    >> +    }
    >> +
    >> +    error = READ_ONCE(i915->gpu_error.first_error);
    >> +    if (error) {
    >> +        drm_err(&i915->drm, "[Capture/%d.%d] Clearing existing error
    >> capture first...\n",
    >> +            l_count, line++);
    >> +        i915_reset_error_state(i915);
    >> +    }
    >> +
    >> +    with_intel_runtime_pm(&i915->runtime_pm, wakeref)
    >> +        error = i915_gpu_coredump(gt, engine_mask,
    >> CORE_DUMP_FLAG_NONE);
    >> +
    >> +    if (IS_ERR(error)) {
    >> +        drm_err(&i915->drm, "[Capture/%d.%d] Failed to capture error
    >> capture: %ld!\n",
    >> +            l_count, line++, PTR_ERR(error));
    >> +        return;
    >> +    }
    >> +
    >> +    buf = kvmalloc(buf_size, GFP_KERNEL);
    >> +    if (!buf) {
    >> +        drm_err(&i915->drm, "[Capture/%d.%d] Failed to allocate buffer
    >> for error capture!\n",
    >> +            l_count, line++);
    >> +        i915_gpu_coredump_put(error);
    >> +        return;
    >> +    }
    >> +
    >> +    drm_info(&i915->drm, "[Capture/%d.%d] Dumping i915 error capture
    >> for %ps...\n",
    >> +         l_count, line++, __builtin_return_address(0));
    >> +
    >> +    /* Largest string length safe to print via dmesg */
    >> +#    define MAX_CHUNK    800
    >> +
    >> +    pos_err = 0;
    >> +    while (1) {
    >> +        ssize_t got = i915_gpu_coredump_copy_to_buffer(error, buf,
    >> pos_err, buf_size - 1);
    >> +
    >> +        if (got <= 0)
    >> +            break;
    >> +
    >> +        buf[got] = 0;
    >> +        pos_err += got;
    >> +
    >> +        ptr = buf;
    >> +        while (got > 0) {
    >> +            size_t count;
    >> +            char tag[2];
    >> +
    >> +            next = strnchr(ptr, got, '\n');
    >> +            if (next) {
    >> +                count = next - ptr;
    >> +                *next = 0;
    >> +                tag[0] = '>';
    >> +                tag[1] = '<';
    >> +            } else {
    >> +                count = got;
    >> +                tag[0] = '}';
    >> +                tag[1] = '{';
    >> +            }
    >> +
    >> +            if (count > MAX_CHUNK) {
    >> +                size_t pos;
    >> +                char *ptr2 = ptr;
    >> +
    >> +                for (pos = MAX_CHUNK; pos < count; pos += MAX_CHUNK) {
    >> +                    char chr = ptr[pos];
    >> +
    >> +                    ptr[pos] = 0;
    >> +                    drm_info(&i915->drm, "[Capture/%d.%d] }%s{\n",
    >> +                         l_count, line++, ptr2);
    >> +                    ptr[pos] = chr;
    >> +                    ptr2 = ptr + pos;
    >> +
    >> +                    /*
    >> +                     * If spewing large amounts of data via a serial
    >> console,
    >> +                     * this can be a very slow process. So be friendly
    >> and try
    >> +                     * not to cause 'softlockup on CPU' problems.
    >> +                     */
    >> +                    cond_resched();
    >> +                }
    >> +
    >> +                if (ptr2 < (ptr + count))
    >> +                    drm_info(&i915->drm, "[Capture/%d.%d] %c%s%c\n",
    >> +                         l_count, line++, tag[0], ptr2, tag[1]);
    >> +                else if (tag[0] == '>')
    >> +                    drm_info(&i915->drm, "[Capture/%d.%d] ><\n",
    >> +                         l_count, line++);
    >> +            } else {
    >> +                drm_info(&i915->drm, "[Capture/%d.%d] %c%s%c\n",
    >> +                     l_count, line++, tag[0], ptr, tag[1]);
    >> +            }
    >> +
    >> +            ptr = next;
    >> +            got -= count;
    >> +            if (next) {
    >> +                ptr++;
    >> +                got--;
    >> +            }
    >> +
    >> +            /* As above. */
    >> +            cond_resched();
    >> +        }
    >> +
    >> +        if (got)
    >> +            drm_info(&i915->drm, "[Capture/%d.%d] Got %zd bytes
    >> remaining!\n",
    >> +                 l_count, line++, got);
    >> +    }
    >> +
    >> +    kvfree(buf);
    >> +
    >> +    drm_info(&i915->drm, "[Capture/%d.%d] Dumped %zd bytes\n",
    >> l_count, line++, pos_err);
    >> +}
    >> +#endif
    >> diff --git a/drivers/gpu/drm/i915/i915_gpu_error.h
    >> b/drivers/gpu/drm/i915/i915_gpu_error.h
    >> index a91932cc65317..a78c061ce26fb 100644
    >> --- a/drivers/gpu/drm/i915/i915_gpu_error.h
    >> +++ b/drivers/gpu/drm/i915/i915_gpu_error.h
    >> @@ -258,6 +258,16 @@ static inline u32 i915_reset_engine_count(struct
    >> i915_gpu_error *error,
    >>   #define CORE_DUMP_FLAG_NONE           0x0
    >>   #define CORE_DUMP_FLAG_IS_GUC_CAPTURE BIT(0)
    >>   +#if IS_ENABLED(CONFIG_DRM_I915_CAPTURE_ERROR) &&
    >> IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM)
    >> +void intel_klog_error_capture(struct intel_gt *gt,
    >> +                  intel_engine_mask_t engine_mask);
    >> +#else
    >> +static inline void intel_klog_error_capture(struct intel_gt *gt,
    >> +                        intel_engine_mask_t engine_mask)
    >> +{
    >> +}
    >> +#endif
    >> +
    >>   #if IS_ENABLED(CONFIG_DRM_I915_CAPTURE_ERROR)
    >>     __printf(2, 3)

References

Visible links
1. mailto:[email protected]
2. mailto:[email protected]
3. mailto:[email protected]
4. mailto:[email protected]

#6 lore raw

PATCH v2 2/2 drm/i915/guc: Dump error capture to dmesg on CTB error

In reply to [email protected]

From: John Harrison <[email protected]>

In the past, There have been sporadic CTB failures which proved hard to reproduce manually. The most effective solution was to dump the GuC log at the point of failure and let the CI system do the repro. It is preferable not to dump the GuC log via dmesg for all issues as it is not always necessary and is not helpful for end users. But rather than trying to re-invent the code to do this each time it is wanted, commit the code but for DEBUG_GUC builds only.

v2: Use IS_ENABLED for testing config options.

---
 drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c | 53 +++++++++++++++++++++++
 drivers/gpu/drm/i915/gt/uc/intel_guc_ct.h |  6 +++
 2 files changed, 59 insertions(+)
drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c +53 -0
index 1803a633ed648..dc5cd712f1ff5 100644
@@ -13,6 +13,30 @@
 #include "intel_guc_ct.h"
 #include "intel_guc_print.h"
 
+#if IS_ENABLED(CONFIG_DRM_I915_DEBUG_GUC)
+enum {
+	CT_DEAD_ALIVE = 0,
+	CT_DEAD_SETUP,
+	CT_DEAD_WRITE,
+	CT_DEAD_DEADLOCK,
+	CT_DEAD_H2G_HAS_ROOM,
+	CT_DEAD_READ,
+	CT_DEAD_PROCESS_FAILED,
+};
+
+static void ct_dead_ct_worker_func(struct work_struct *w);
+
+#define CT_DEAD(ct, reason)	\
+	do { \
+		if (!(ct)->dead_ct_reported) { \
+			(ct)->dead_ct_reason |= 1 << CT_DEAD_##reason; \
+			queue_work(system_unbound_wq, &(ct)->dead_ct_worker); \
+		} \
+	} while (0)
+#else
+#define CT_DEAD(ct, reason)	do { } while (0)
+#endif
+
 static inline struct intel_guc *ct_to_guc(struct intel_guc_ct *ct)
 {
 	return container_of(ct, struct intel_guc, ct);
@@ -93,6 +117,9 @@ void intel_guc_ct_init_early(struct intel_guc_ct *ct)
 	spin_lock_init(&ct->requests.lock);
 	INIT_LIST_HEAD(&ct->requests.pending);
 	INIT_LIST_HEAD(&ct->requests.incoming);
+#if IS_ENABLED(CONFIG_DRM_I915_DEBUG_GUC)
+	INIT_WORK(&ct->dead_ct_worker, ct_dead_ct_worker_func);
+#endif
 	INIT_WORK(&ct->requests.worker, ct_incoming_request_worker_func);
 	tasklet_setup(&ct->receive_tasklet, ct_receive_tasklet_func);
 	init_waitqueue_head(&ct->wq);
@@ -319,11 +346,16 @@ int intel_guc_ct_enable(struct intel_guc_ct *ct)
 
 	ct->enabled = true;
 	ct->stall_time = KTIME_MAX;
+#if IS_ENABLED(CONFIG_DRM_I915_DEBUG_GUC)
+	ct->dead_ct_reported = false;
+	ct->dead_ct_reason = CT_DEAD_ALIVE;
+#endif
 
 	return 0;
 
 err_out:
 	CT_PROBE_ERROR(ct, "Failed to enable CTB (%pe)\n", ERR_PTR(err));
+	CT_DEAD(ct, SETUP);
 	return err;
 }
 
@@ -434,6 +466,7 @@ static int ct_write(struct intel_guc_ct *ct,
 corrupted:
 	CT_ERROR(ct, "Corrupted descriptor head=%u tail=%u status=%#x\n",
 		 desc->head, desc->tail, desc->status);
+	CT_DEAD(ct, WRITE);
 	ctb->broken = true;
 	return -EPIPE;
 }
@@ -504,6 +537,7 @@ static inline bool ct_deadlocked(struct intel_guc_ct *ct)
 		CT_ERROR(ct, "Head: %u\n (Dwords)", ct->ctbs.recv.desc->head);
 		CT_ERROR(ct, "Tail: %u\n (Dwords)", ct->ctbs.recv.desc->tail);
 
+		CT_DEAD(ct, DEADLOCK);
 		ct->ctbs.send.broken = true;
 	}
 
@@ -552,6 +586,7 @@ static inline bool h2g_has_room(struct intel_guc_ct *ct, u32 len_dw)
 			 head, ctb->size);
 		desc->status |= GUC_CTB_STATUS_OVERFLOW;
 		ctb->broken = true;
+		CT_DEAD(ct, H2G_HAS_ROOM);
 		return false;
 	}
 
@@ -908,6 +943,7 @@ static int ct_read(struct intel_guc_ct *ct, struct ct_incoming_msg **msg)
 	CT_ERROR(ct, "Corrupted descriptor head=%u tail=%u status=%#x\n",
 		 desc->head, desc->tail, desc->status);
 	ctb->broken = true;
+	CT_DEAD(ct, READ);
 	return -EPIPE;
 }
 
@@ -1057,6 +1093,7 @@ static bool ct_process_incoming_requests(struct intel_guc_ct *ct)
 	if (unlikely(err)) {
 		CT_ERROR(ct, "Failed to process CT message (%pe) %*ph\n",
 			 ERR_PTR(err), 4 * request->size, request->msg);
+		CT_DEAD(ct, PROCESS_FAILED);
 		ct_free_msg(request);
 	}
 
@@ -1233,3 +1270,19 @@ void intel_guc_ct_print_info(struct intel_guc_ct *ct,
 	drm_printf(p, "Tail: %u\n",
 		   ct->ctbs.recv.desc->tail);
 }
+
+#if IS_ENABLED(CONFIG_DRM_I915_DEBUG_GUC)
+static void ct_dead_ct_worker_func(struct work_struct *w)
+{
+	struct intel_guc_ct *ct = container_of(w, struct intel_guc_ct, dead_ct_worker);
+	struct intel_guc *guc = ct_to_guc(ct);
+
+	if (ct->dead_ct_reported)
+		return;
+
+	ct->dead_ct_reported = true;
+
+	guc_info(guc, "CTB is dead - reason=0x%X\n", ct->dead_ct_reason);
+	intel_klog_error_capture(guc_to_gt(guc), (intel_engine_mask_t)~0U);
+}
+#endif
drivers/gpu/drm/i915/gt/uc/intel_guc_ct.h +6 -0
index f709a19c7e214..818415b64f4d1 100644
@@ -85,6 +85,12 @@ struct intel_guc_ct {
 
 	/** @stall_time: time of first time a CTB submission is stalled */
 	ktime_t stall_time;
+
+#if IS_ENABLED(CONFIG_DRM_I915_DEBUG_GUC)
+	int dead_ct_reason;
+	bool dead_ct_reported;
+	struct work_struct dead_ct_worker;
+#endif
 };
 
 void intel_guc_ct_init_early(struct intel_guc_ct *ct);
Signature · 1 line
2.39.1
Reviewed-by on v2 2/2
#7 lore raw

Re: [Intel-gfx] [PATCH v2 2/2] drm/i915/guc: Dump error capture to dmesg on CTB error

Quoted 11 lines · On 4/18/2023 11:17 AM, [email protected] wrote:

From: John Harrison <[email protected]>

In the past, There have been sporadic CTB failures which proved hard to reproduce manually. The most effective solution was to dump the GuC log at the point of failure and let the CI system do the repro. It is preferable not to dump the GuC log via dmesg for all issues as it is not always necessary and is not helpful for end users. But rather than trying to re-invent the code to do this each time it is wanted, commit the code but for DEBUG_GUC builds only.

v2: Use IS_ENABLED for testing config options.

LGTM,

Quoted 146 lines
---
  drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c | 53 +++++++++++++++++++++++
  drivers/gpu/drm/i915/gt/uc/intel_guc_ct.h |  6 +++
  2 files changed, 59 insertions(+)
drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c +53 -0
index 1803a633ed648..dc5cd712f1ff5 100644
@@ -13,6 +13,30 @@
  #include "intel_guc_ct.h"
  #include "intel_guc_print.h"
 
+#if IS_ENABLED(CONFIG_DRM_I915_DEBUG_GUC)
+enum {
+	CT_DEAD_ALIVE = 0,
+	CT_DEAD_SETUP,
+	CT_DEAD_WRITE,
+	CT_DEAD_DEADLOCK,
+	CT_DEAD_H2G_HAS_ROOM,
+	CT_DEAD_READ,
+	CT_DEAD_PROCESS_FAILED,
+};
+
+static void ct_dead_ct_worker_func(struct work_struct *w);
+
+#define CT_DEAD(ct, reason)	\
+	do { \
+		if (!(ct)->dead_ct_reported) { \
+			(ct)->dead_ct_reason |= 1 << CT_DEAD_##reason; \
+			queue_work(system_unbound_wq, &(ct)->dead_ct_worker); \
+		} \
+	} while (0)
+#else
+#define CT_DEAD(ct, reason)	do { } while (0)
+#endif
+
  static inline struct intel_guc *ct_to_guc(struct intel_guc_ct *ct)
  {
  	return container_of(ct, struct intel_guc, ct);
@@ -93,6 +117,9 @@ void intel_guc_ct_init_early(struct intel_guc_ct *ct)
  	spin_lock_init(&ct->requests.lock);
  	INIT_LIST_HEAD(&ct->requests.pending);
  	INIT_LIST_HEAD(&ct->requests.incoming);
+#if IS_ENABLED(CONFIG_DRM_I915_DEBUG_GUC)
+	INIT_WORK(&ct->dead_ct_worker, ct_dead_ct_worker_func);
+#endif
  	INIT_WORK(&ct->requests.worker, ct_incoming_request_worker_func);
  	tasklet_setup(&ct->receive_tasklet, ct_receive_tasklet_func);
  	init_waitqueue_head(&ct->wq);
@@ -319,11 +346,16 @@ int intel_guc_ct_enable(struct intel_guc_ct *ct)
 
  	ct->enabled = true;
  	ct->stall_time = KTIME_MAX;
+#if IS_ENABLED(CONFIG_DRM_I915_DEBUG_GUC)
+	ct->dead_ct_reported = false;
+	ct->dead_ct_reason = CT_DEAD_ALIVE;
+#endif
 
  	return 0;
 
  err_out:
  	CT_PROBE_ERROR(ct, "Failed to enable CTB (%pe)\n", ERR_PTR(err));
+	CT_DEAD(ct, SETUP);
  	return err;
  }
 
@@ -434,6 +466,7 @@ static int ct_write(struct intel_guc_ct *ct,
  corrupted:
  	CT_ERROR(ct, "Corrupted descriptor head=%u tail=%u status=%#x\n",
  		 desc->head, desc->tail, desc->status);
+	CT_DEAD(ct, WRITE);
  	ctb->broken = true;
  	return -EPIPE;
  }
@@ -504,6 +537,7 @@ static inline bool ct_deadlocked(struct intel_guc_ct *ct)
  		CT_ERROR(ct, "Head: %u\n (Dwords)", ct->ctbs.recv.desc->head);
  		CT_ERROR(ct, "Tail: %u\n (Dwords)", ct->ctbs.recv.desc->tail);
 
+		CT_DEAD(ct, DEADLOCK);
  		ct->ctbs.send.broken = true;
  	}
 
@@ -552,6 +586,7 @@ static inline bool h2g_has_room(struct intel_guc_ct *ct, u32 len_dw)
  			 head, ctb->size);
  		desc->status |= GUC_CTB_STATUS_OVERFLOW;
  		ctb->broken = true;
+		CT_DEAD(ct, H2G_HAS_ROOM);
  		return false;
  	}
 
@@ -908,6 +943,7 @@ static int ct_read(struct intel_guc_ct *ct, struct ct_incoming_msg **msg)
  	CT_ERROR(ct, "Corrupted descriptor head=%u tail=%u status=%#x\n",
  		 desc->head, desc->tail, desc->status);
  	ctb->broken = true;
+	CT_DEAD(ct, READ);
  	return -EPIPE;
  }
 
@@ -1057,6 +1093,7 @@ static bool ct_process_incoming_requests(struct intel_guc_ct *ct)
  	if (unlikely(err)) {
  		CT_ERROR(ct, "Failed to process CT message (%pe) %*ph\n",
  			 ERR_PTR(err), 4 * request->size, request->msg);
+		CT_DEAD(ct, PROCESS_FAILED);
  		ct_free_msg(request);
  	}
 
@@ -1233,3 +1270,19 @@ void intel_guc_ct_print_info(struct intel_guc_ct *ct,
  	drm_printf(p, "Tail: %u\n",
  		   ct->ctbs.recv.desc->tail);
  }
+
+#if IS_ENABLED(CONFIG_DRM_I915_DEBUG_GUC)
+static void ct_dead_ct_worker_func(struct work_struct *w)
+{
+	struct intel_guc_ct *ct = container_of(w, struct intel_guc_ct, dead_ct_worker);
+	struct intel_guc *guc = ct_to_guc(ct);
+
+	if (ct->dead_ct_reported)
+		return;
+
+	ct->dead_ct_reported = true;
+
+	guc_info(guc, "CTB is dead - reason=0x%X\n", ct->dead_ct_reason);
+	intel_klog_error_capture(guc_to_gt(guc), (intel_engine_mask_t)~0U);
+}
+#endif
drivers/gpu/drm/i915/gt/uc/intel_guc_ct.h +6 -0
index f709a19c7e214..818415b64f4d1 100644
@@ -85,6 +85,12 @@ struct intel_guc_ct {
 
  	/** @stall_time: time of first time a CTB submission is stalled */
  	ktime_t stall_time;
+
+#if IS_ENABLED(CONFIG_DRM_I915_DEBUG_GUC)
+	int dead_ct_reason;
+	bool dead_ct_reported;
+	struct work_struct dead_ct_worker;
+#endif
  };
 
  void intel_guc_ct_init_early(struct intel_guc_ct *ct);
#8 lore raw

[Intel-gfx] ✗ Fi.CI.CHECKPATCH: warning for Add support for dumping error captures via kernel logging (rev2)

In reply to [email protected]
== Series Details ==

== Series Details ==

Series: Add support for dumping error captures via kernel logging (rev2)
URL : https://patchwork.freedesktop.org/series/116280/
State : warning

== Summary ==

Error: dim checkpatch failed
0fdd3a06a2b6 drm/i915: Dump error capture to kernel log -:64: WARNING:OOM_MESSAGE: Possible unnecessary 'out of memory' message #64: FILE: drivers/gpu/drm/i915/i915_gpu_error.c:2262:
+ if (!buf) {
+ drm_err(&i915->drm, "[Capture/%d.%d] Failed to allocate buffer for error capture!\n",

total: 0 errors, 1 warnings, 0 checks, 151 lines checked adfdeee9f311 drm/i915/guc: Dump error capture to dmesg on CTB error -:39: CHECK:MACRO_ARG_REUSE: Macro argument reuse 'ct' - possible side-effects? #39: FILE: drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c:29:
+#define CT_DEAD(ct, reason) \
+ do { \
+ if (!(ct)->dead_ct_reported) { \
+ (ct)->dead_ct_reason |= 1 << CT_DEAD_##reason; \
+ queue_work(system_unbound_wq, &(ct)->dead_ct_worker); \
+ } \
+ } while (0)

total: 0 errors, 0 warnings, 1 checks, 121 lines checked

#9 lore raw

[Intel-gfx] ✗ Fi.CI.SPARSE: warning for Add support for dumping error captures via kernel logging (rev2)

In reply to [email protected]
== Series Details ==

== Series Details ==

Series: Add support for dumping error captures via kernel logging (rev2)
URL : https://patchwork.freedesktop.org/series/116280/
State : warning

== Summary ==

Error: dim sparse failed
Sparse version: v0.6.2
Fast mode used, each commit won't be checked separately.

#10 lore raw

[Intel-gfx] ✓ Fi.CI.BAT: success for Add support for dumping error captures via kernel logging (rev2)

In reply to [email protected]
== Series Details ==

== Series Details ==

Series: Add support for dumping error captures via kernel logging (rev2)
URL : https://patchwork.freedesktop.org/series/116280/
State : success

== Summary ==

CI Bug Log - changes from CI_DRM_13026 -> Patchwork_116280v2
====================================================

Summary
-------

**SUCCESS**

No regressions found.

External URL: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_116280v2/index.html

Participating hosts (38 -> 36)
------------------------------

Missing (2): bat-rpls-2 fi-snb-2520m

Known issues
------------

Here are the changes found in Patchwork_116280v2 that come from known issues:

### IGT changes ###

#### Issues hit ####

* igt@i915_selftest@live@reset:
- bat-rpls-1: [PASS][1] -> [ABORT][2] ([i915#4983] / [i915#7981])
[1]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_13026/bat-rpls-1/igt@i915_selftest@[email protected]
[2]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_116280v2/bat-rpls-1/igt@i915_selftest@[email protected]

* igt@i915_selftest@live@workarounds:
- bat-adlp-6: [PASS][3] -> [INCOMPLETE][4] ([i915#4983] / [i915#7677] / [i915#7913])
[3]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_13026/bat-adlp-6/igt@i915_selftest@[email protected]
[4]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_116280v2/bat-adlp-6/igt@i915_selftest@[email protected]

* igt@kms_pipe_crc_basic@nonblocking-crc@pipe-c-dp-1:
- bat-dg2-8: [PASS][5] -> [FAIL][6] ([i915#7932])
[5]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_13026/bat-dg2-8/igt@kms_pipe_crc_basic@[email protected]
[6]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_116280v2/bat-dg2-8/igt@kms_pipe_crc_basic@[email protected]

#### Possible fixes ####

* igt@i915_selftest@live@migrate:
- bat-dg2-11: [DMESG-WARN][7] ([i915#7699]) -> [PASS][8]
[7]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_13026/bat-dg2-11/igt@i915_selftest@[email protected]
[8]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_116280v2/bat-dg2-11/igt@i915_selftest@[email protected]

{name}: This element is suppressed. This means it is ignored when computing
the status of the difference (SUCCESS, WARNING, or FAILURE).

[i915#3708]: https://gitlab.freedesktop.org/drm/intel/issues/3708
[i915#4077]: https://gitlab.freedesktop.org/drm/intel/issues/4077
[i915#4983]: https://gitlab.freedesktop.org/drm/intel/issues/4983
[i915#7677]: https://gitlab.freedesktop.org/drm/intel/issues/7677
[i915#7699]: https://gitlab.freedesktop.org/drm/intel/issues/7699
[i915#7913]: https://gitlab.freedesktop.org/drm/intel/issues/7913
[i915#7932]: https://gitlab.freedesktop.org/drm/intel/issues/7932
[i915#7981]: https://gitlab.freedesktop.org/drm/intel/issues/7981

Build changes
-------------

* Linux: CI_DRM_13026 -> Patchwork_116280v2

CI-20190529: 20190529
CI_DRM_13026: 45bed7de41ad8bd909a82382a8fc4cb65e04ad56 @ git://anongit.freedesktop.org/gfx-ci/linux
IGT_7259: 3d3a7f1c041d3f8d84d7457abf96adef0ea071cb @ https://gitlab.freedesktop.org/drm/igt-gpu-tools.git
Patchwork_116280v2: 45bed7de41ad8bd909a82382a8fc4cb65e04ad56 @ git://anongit.freedesktop.org/gfx-ci/linux

### Linux commits

fd841c544085 drm/i915/guc: Dump error capture to dmesg on CTB error 725a11e64b63 drm/i915: Dump error capture to kernel log

== Logs ==

For more details see: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_116280v2/index.html

#11 lore raw

[Intel-gfx] ✓ Fi.CI.IGT: success for Add support for dumping error captures via kernel logging (rev2)

In reply to [email protected]
== Series Details ==

== Series Details ==

Series: Add support for dumping error captures via kernel logging (rev2)
URL : https://patchwork.freedesktop.org/series/116280/
State : success

== Summary ==

CI Bug Log - changes from CI_DRM_13026_full -> Patchwork_116280v2_full
====================================================

Summary
-------

**SUCCESS**

No regressions found.

Participating hosts (7 -> 7)
------------------------------

No changes in participating hosts

Possible new issues
-------------------

Here are the unknown changes that may have been introduced in Patchwork_116280v2_full:

### IGT changes ###

#### Suppressed ####

The following results come from untrusted machines, tests, or statuses. They do not affect the overall result.

* igt@kms_vblank@pipe-g-query-idle:
- {shard-dg1}: NOTRUN -> [SKIP][1] +43 similar issues
[1]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_116280v2/shard-dg1-14/igt@[email protected]

* igt@kms_vblank@pipe-h-wait-idle:
- {shard-tglu}: NOTRUN -> [SKIP][2]
[2]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_116280v2/shard-tglu-8/igt@[email protected]

Known issues
------------

Here are the changes found in Patchwork_116280v2_full that come from known issues:

### IGT changes ###

#### Issues hit ####

* igt@gem_exec_fair@basic-pace-share@rcs0:
- shard-glk: [PASS][3] -> [FAIL][4] ([i915#2842])
[3]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_13026/shard-glk8/igt@gem_exec_fair@[email protected]
[4]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_116280v2/shard-glk3/igt@gem_exec_fair@[email protected]

* igt@kms_flip@flip-vs-suspend-interruptible@c-dp1:
- shard-apl: [PASS][5] -> [ABORT][6] ([i915#180])
[5]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_13026/shard-apl7/igt@kms_flip@[email protected]
[6]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_116280v2/shard-apl3/igt@kms_flip@[email protected]

* igt@kms_plane_scaling@planes-downscale-factor-0-5-unity-scaling@pipe-b-vga-1:
- shard-snb: NOTRUN -> [SKIP][7] ([fdo#109271]) +37 similar issues
[7]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_116280v2/shard-snb2/igt@kms_plane_scaling@[email protected]

* igt@kms_setmode@basic@pipe-a-hdmi-a-1:
- shard-snb: NOTRUN -> [FAIL][8] ([i915#5465]) +1 similar issue
[8]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_116280v2/shard-snb1/igt@kms_setmode@[email protected]

#### Possible fixes ####

* igt@gem_barrier_race@remote-request@rcs0:
- {shard-tglu}: [ABORT][9] ([i915#8211]) -> [PASS][10]
[9]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_13026/shard-tglu-9/igt@gem_barrier_race@[email protected]
[10]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_116280v2/shard-tglu-8/igt@gem_barrier_race@[email protected]

* igt@gem_exec_fair@basic-none-solo@rcs0:
- shard-apl: [FAIL][11] ([i915#2842]) -> [PASS][12]
[11]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_13026/shard-apl1/igt@gem_exec_fair@[email protected]
[12]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_116280v2/shard-apl7/igt@gem_exec_fair@[email protected]

* igt@gem_exec_fair@basic-pace@vecs0:
- {shard-rkl}: [FAIL][13] ([i915#2842]) -> [PASS][14]
[13]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_13026/shard-rkl-7/igt@gem_exec_fair@[email protected]
[14]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_116280v2/shard-rkl-1/igt@gem_exec_fair@[email protected]

* igt@gem_exec_suspend@basic-s4-devices@lmem0:
- {shard-dg1}: [ABORT][15] ([i915#7975]) -> [PASS][16]
[15]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_13026/shard-dg1-14/igt@gem_exec_suspend@[email protected]
[16]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_116280v2/shard-dg1-17/igt@gem_exec_suspend@[email protected]

* igt@i915_pm_dc@dc6-dpms:
- {shard-tglu}: [FAIL][17] ([i915#3989] / [i915#454]) -> [PASS][18]
[17]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_13026/shard-tglu-7/igt@[email protected]
[18]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_116280v2/shard-tglu-10/igt@[email protected]

* igt@i915_pm_rpm@dpms-non-lpsp:
- {shard-rkl}: [SKIP][19] ([i915#1397]) -> [PASS][20] +1 similar issue
[19]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_13026/shard-rkl-7/igt@[email protected]
[20]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_116280v2/shard-rkl-1/igt@[email protected]

* igt@i915_pm_rpm@modeset-non-lpsp:
- {shard-dg1}: [SKIP][21] ([i915#1397]) -> [PASS][22]
[21]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_13026/shard-dg1-14/igt@[email protected]
[22]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_116280v2/shard-dg1-17/igt@[email protected]

* igt@kms_cursor_legacy@flip-vs-cursor-atomic-transitions:
- shard-glk: [FAIL][23] ([i915#2346]) -> [PASS][24]
[23]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_13026/shard-glk1/igt@[email protected]
[24]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_116280v2/shard-glk6/igt@[email protected]

* igt@kms_cursor_legacy@single-bo@pipe-b:
- {shard-rkl}: [INCOMPLETE][25] ([i915#8011]) -> [PASS][26] +1 similar issue
[25]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_13026/shard-rkl-7/igt@kms_cursor_legacy@[email protected]
[26]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_116280v2/shard-rkl-2/igt@kms_cursor_legacy@[email protected]

* igt@kms_flip@flip-vs-expired-vblank-interruptible@c-hdmi-a2:
- shard-glk: [FAIL][27] ([i915#79]) -> [PASS][28]
[27]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_13026/shard-glk2/igt@kms_flip@[email protected]
[28]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_116280v2/shard-glk5/igt@kms_flip@[email protected]

* igt@kms_plane_scaling@i915-max-src-size@pipe-a-hdmi-a-2:
- {shard-rkl}: [FAIL][29] ([i915#8292]) -> [PASS][30]
[29]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_13026/shard-rkl-2/igt@kms_plane_scaling@[email protected]
[30]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_116280v2/shard-rkl-4/igt@kms_plane_scaling@[email protected]

{name}: This element is suppressed. This means it is ignored when computing
the status of the difference (SUCCESS, WARNING, or FAILURE).

[fdo#109271]: https://bugs.freedesktop.org/show_bug.cgi?id=109271
[fdo#109274]: https://bugs.freedesktop.org/show_bug.cgi?id=109274
[fdo#109280]: https://bugs.freedesktop.org/show_bug.cgi?id=109280
[fdo#109283]: https://bugs.freedesktop.org/show_bug.cgi?id=109283
[fdo#109285]: https://bugs.freedesktop.org/show_bug.cgi?id=109285
[fdo#109289]: https://bugs.freedesktop.org/show_bug.cgi?id=109289
[fdo#109314]: https://bugs.freedesktop.org/show_bug.cgi?id=109314
[fdo#109315]: https://bugs.freedesktop.org/show_bug.cgi?id=109315
[fdo#110189]: https://bugs.freedesktop.org/show_bug.cgi?id=110189
[fdo#111068]: https://bugs.freedesktop.org/show_bug.cgi?id=111068
[fdo#111615]: https://bugs.freedesktop.org/show_bug.cgi?id=111615
[fdo#111825]: https://bugs.freedesktop.org/show_bug.cgi?id=111825
[fdo#111827]: https://bugs.freedesktop.org/show_bug.cgi?id=111827
[fdo#112054]: https://bugs.freedesktop.org/show_bug.cgi?id=112054
[fdo#112283]: https://bugs.freedesktop.org/show_bug.cgi?id=112283
[i915#1072]: https://gitlab.freedesktop.org/drm/intel/issues/1072
[i915#1397]: https://gitlab.freedesktop.org/drm/intel/issues/1397
[i915#180]: https://gitlab.freedesktop.org/drm/intel/issues/180
[i915#2346]: https://gitlab.freedesktop.org/drm/intel/issues/2346
[i915#2437]: https://gitlab.freedesktop.org/drm/intel/issues/2437
[i915#2527]: https://gitlab.freedesktop.org/drm/intel/issues/2527
[i915#2575]: https://gitlab.freedesktop.org/drm/intel/issues/2575
[i915#2587]: https://gitlab.freedesktop.org/drm/intel/issues/2587
[i915#2672]: https://gitlab.freedesktop.org/drm/intel/issues/2672
[i915#2681]: https://gitlab.freedesktop.org/drm/intel/issues/2681
[i915#2705]: https://gitlab.freedesktop.org/drm/intel/issues/2705
[i915#2842]: https://gitlab.freedesktop.org/drm/intel/issues/2842
[i915#3281]: https://gitlab.freedesktop.org/drm/intel/issues/3281
[i915#3282]: https://gitlab.freedesktop.org/drm/intel/issues/3282
[i915#3297]: https://gitlab.freedesktop.org/drm/intel/issues/3297
[i915#3299]: https://gitlab.freedesktop.org/drm/intel/issues/3299
[i915#3359]: https://gitlab.freedesktop.org/drm/intel/issues/3359
[i915#3458]: https://gitlab.freedesktop.org/drm/intel/issues/3458
[i915#3539]: https://gitlab.freedesktop.org/drm/intel/issues/3539
[i915#3555]: https://gitlab.freedesktop.org/drm/intel/issues/3555
[i915#3591]: https://gitlab.freedesktop.org/drm/intel/issues/3591
[i915#3637]: https://gitlab.freedesktop.org/drm/intel/issues/3637
[i915#3638]: https://gitlab.freedesktop.org/drm/intel/issues/3638
[i915#3689]: https://gitlab.freedesktop.org/drm/intel/issues/3689
[i915#3742]: https://gitlab.freedesktop.org/drm/intel/issues/3742
[i915#3743]: https://gitlab.freedesktop.org/drm/intel/issues/3743
[i915#3840]: https://gitlab.freedesktop.org/drm/intel/issues/3840
[i915#3886]: https://gitlab.freedesktop.org/drm/intel/issues/3886
[i915#3989]: https://gitlab.freedesktop.org/drm/intel/issues/3989
[i915#4036]: https://gitlab.freedesktop.org/drm/intel/issues/4036
[i915#4070]: https://gitlab.freedesktop.org/drm/intel/issues/4070
[i915#4077]: https://gitlab.freedesktop.org/drm/intel/issues/4077
[i915#4083]: https://gitlab.freedesktop.org/drm/intel/issues/4083
[i915#4098]: https://gitlab.freedesktop.org/drm/intel/issues/4098
[i915#4103]: https://gitlab.freedesktop.org/drm/intel/issues/4103
[i915#4212]: https://gitlab.freedesktop.org/drm/intel/issues/4212
[i915#4213]: https://gitlab.freedesktop.org/drm/intel/issues/4213
[i915#4270]: https://gitlab.freedesktop.org/drm/intel/issues/4270
[i915#4349]: https://gitlab.freedesktop.org/drm/intel/issues/4349
[i915#4538]: https://gitlab.freedesktop.org/drm/intel/issues/4538
[i915#454]: https://gitlab.freedesktop.org/drm/intel/issues/454
[i915#4565]: https://gitlab.freedesktop.org/drm/intel/issues/4565
[i915#4579]: https://gitlab.freedesktop.org/drm/intel/issues/4579
[i915#4771]: https://gitlab.freedesktop.org/drm/intel/issues/4771
[i915#4812]: https://gitlab.freedesktop.org/drm/intel/issues/4812
[i915#4816]: https://gitlab.freedesktop.org/drm/intel/issues/4816
[i915#4833]: https://gitlab.freedesktop.org/drm/intel/issues/4833
[i915#4852]: https://gitlab.freedesktop.org/drm/intel/issues/4852
[i915#4860]: https://gitlab.freedesktop.org/drm/intel/issues/4860
[i915#4881]: https://gitlab.freedesktop.org/drm/intel/issues/4881
[i915#4884]: https://gitlab.freedesktop.org/drm/intel/issues/4884
[i915#4983]: https://gitlab.freedesktop.org/drm/intel/issues/4983
[i915#5176]: https://gitlab.freedesktop.org/drm/intel/issues/5176
[i915#5235]: https://gitlab.freedesktop.org/drm/intel/issues/5235
[i915#5286]: https://gitlab.freedesktop.org/drm/intel/issues/5286
[i915#5288]: https://gitlab.freedesktop.org/drm/intel/issues/5288
[i915#5289]: https://gitlab.freedesktop.org/drm/intel/issues/5289
[i915#5325]: https://gitlab.freedesktop.org/drm/intel/issues/5325
[i915#5461]: https://gitlab.freedesktop.org/drm/intel/issues/5461
[i915#5465]: https://gitlab.freedesktop.org/drm/intel/issues/5465
[i915#5563]: https://gitlab.freedesktop.org/drm/intel/issues/5563
[i915#5723]: https://gitlab.freedesktop.org/drm/intel/issues/5723
[i915#6095]: https://gitlab.freedesktop.org/drm/intel/issues/6095
[i915#6433]: https://gitlab.freedesktop.org/drm/intel/issues/6433
[i915#6524]: https://gitlab.freedesktop.org/drm/intel/issues/6524
[i915#658]: https://gitlab.freedesktop.org/drm/intel/issues/658
[i915#7116]: https://gitlab.freedesktop.org/drm/intel/issues/7116
[i915#7561]: https://gitlab.freedesktop.org/drm/intel/issues/7561
[i915#7697]: https://gitlab.freedesktop.org/drm/intel/issues/7697
[i915#7711]: https://gitlab.freedesktop.org/drm/intel/issues/7711
[i915#7828]: https://gitlab.freedesktop.org/drm/intel/issues/7828
[i915#79]: https://gitlab.freedesktop.org/drm/intel/issues/79
[i915#7975]: https://gitlab.freedesktop.org/drm/intel/issues/7975
[i915#8011]: https://gitlab.freedesktop.org/drm/intel/issues/8011
[i915#8211]: https://gitlab.freedesktop.org/drm/intel/issues/8211
[i915#8292]: https://gitlab.freedesktop.org/drm/intel/issues/8292

Build changes
-------------

* Linux: CI_DRM_13026 -> Patchwork_116280v2

CI-20190529: 20190529
CI_DRM_13026: 45bed7de41ad8bd909a82382a8fc4cb65e04ad56 @ git://anongit.freedesktop.org/gfx-ci/linux
IGT_7259: 3d3a7f1c041d3f8d84d7457abf96adef0ea071cb @ https://gitlab.freedesktop.org/drm/igt-gpu-tools.git
Patchwork_116280v2: 45bed7de41ad8bd909a82382a8fc4cb65e04ad56 @ git://anongit.freedesktop.org/gfx-ci/linux
piglit_4509: fdc5a4ca11124ab8413c7988896eec4c97336694 @ git://anongit.freedesktop.org/piglit

== Logs ==

For more details see: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_116280v2/index.html

Reviewed-by on the v2 series
#12 lore raw
In reply to [email protected]
Quoted 9 lines · On 4/18/2023 11:17 AM, [email protected] wrote:

From: John Harrison <[email protected]>

Sometimes, the only effective way to debug an issue is to dump all the interesting information at the point of failure. So add support for doing that.

v2: Extra CONFIG wrapping (review feedback from Rodrigo)

series LGTM,

Quoted 12 lines

John Harrison (2):
drm/i915: Dump error capture to kernel log drm/i915/guc: Dump error capture to dmesg on CTB error

  drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c |  53 +++++++++
  drivers/gpu/drm/i915/gt/uc/intel_guc_ct.h |   6 +
  drivers/gpu/drm/i915/i915_gpu_error.c     | 132 ++++++++++++++++++++++
  drivers/gpu/drm/i915/i915_gpu_error.h     |  10 ++
  4 files changed, 201 insertions(+)