Skip to contentSkip to conversation

tests/xe: Add purgeable memory madvise tests for system allocator

PATCH Superseded Arvind Yadav 4 participants 14 messages Jan 20 – Feb 9

v1 of 10 Superseded Latest is v10 →

lore
Share & tools
lore
#0 lore raw

cover tests/xe: Add purgeable memory madvise tests for system allocator

This series adds IGT tests for the purgeable memory madvise functionality in the XE driver's system allocator path.

Purgeable memory allows userspace to mark buffer objects as DONTNEED, making them eligible for kernel reclamation under memory pressure. This is critical for mobile and memory-constrained platforms to prevent OOM conditions while managing temporary or regeneratable GPU data.

The test suite validates:
- Basic purgeable lifecycle (WILLNEED -> DONTNEED -> PURGED)
- "Once purged, always purged" semantics (i915 compatibility)
- Per-VMA purgeable state tracking for shared buffers
- CPU fault handling on purged BOs (SIGBUS/SIGSEGV)
- GPU execution with purged memory and scratch page protection
- Proper state transitions across multiple VMs

Purgeable Memory States:-
- **WILLNEED (0)**: Memory is actively needed, kernel should not reclaim it.
- **DONTNEED (1)**: Application doesn't need this memory right now, kernel can reclaim it if needed

Retained Value
When querying purgeable state, the kernel returns:
- retained = 1: Memory is still present (not purged)
- retained = 0: Memory was purged/reclaimed

Kernel dependency: https://patchwork.freedesktop.org/series/156651/

Test Cases :
1. madvise-purgeable-dontneed-before-mmap
Purpose: Validate that mmap fails on already-purged BO

2. madvise-purgeable-dontneed-after-mmap
Purpose: Validate that accessing an existing mapping of purged memory triggers SIGBUS/SIGSEGV

3. madvise-purgeable-dontneed-before-exec
Purpose: Validate GPU execution on purgeable BO (before it's used)

4. madvise-purgeable-dontneed-after-exec
Purpose: Validate that previously-used BO can be purged and becomes inaccessible

5. madvise-purgeable-per-vma-tracking
Purpose: Validate per-VMA purgeable state tracking

6. madvise-purgeable-per-vma-protection
Purpose: Validate that WILLNEED VMA protects BO from purging during GPU operations

Arvind Yadav (2):
lib/xe: Add purgeable memory ioctl support tests/intel/xe_exec_system_allocator: Add purgeable memory madvise
tests

Himal Prasad Ghimiray (1):
drm-uapi/xe_drm: Add UAPI support for purgeable buffer objects

 include/drm-uapi/xe_drm.h              |  37 ++
 lib/xe/xe_ioctl.c                      |  33 ++
 lib/xe/xe_ioctl.h                      |   2 +
 tests/intel/xe_exec_system_allocator.c | 638 +++++++++++++++++++++++++
 4 files changed, 710 insertions(+)
Signature · 1 line
2.43.0
#1 lore raw

PATCH 1/3 drm-uapi/xe_drm: Add UAPI support for purgeable buffer objects

From: Himal Prasad Ghimiray <[email protected]>

Extend the DRM_XE_MADVISE ioctl to support purgeable buffer object management by adding DRM_XE_VMA_ATTR_PURGEABLE_STATE attribute type.

This allows userspace applications to provide memory usage hints to the kernel for better memory management under pressure:

This allows userspace applications to provide memory usage hints to the kernel for better memory management under pressure:

- WILLNEED: Buffer is needed and should not be purged. If the BO was previously purged, retained field returns 0 indicating backing store was lost (once purged, always purged semantics matching i915).

- DONTNEED: Buffer is not currently needed and may be purged by the kernel under memory pressure to free resources. Only applies to non-shared BOs.

The implementation includes a 'retained' output field (matching i915's drm_i915_gem_madvise.retained) that indicates whether the BO's backing store still exists (1) or has been purged (0).

---
 include/drm-uapi/xe_drm.h | 37 +++++++++++++++++++++++++++++++++++++
 1 file changed, 37 insertions(+)
include/drm-uapi/xe_drm.h +37 -0
index 077e66a68..7b3901e4b 100644
@@ -2099,6 +2099,7 @@ struct drm_xe_madvise {
 #define DRM_XE_MEM_RANGE_ATTR_PREFERRED_LOC	0
 #define DRM_XE_MEM_RANGE_ATTR_ATOMIC		1
 #define DRM_XE_MEM_RANGE_ATTR_PAT		2
+#define DRM_XE_VMA_ATTR_PURGEABLE_STATE		3
 	/** @type: type of attribute */
 	__u32 type;
 
@@ -2189,6 +2190,42 @@ struct drm_xe_madvise {
 			/** @pat_index.reserved: Reserved */
 			__u64 reserved;
 		} pat_index;
+
+		/**
+		 * @purge_state_val: Purgeable state configuration
+		 *
+		 * Used when @type == DRM_XE_VMA_ATTR_PURGEABLE_STATE.
+		 *
+		 * Configures the purgeable state of buffer objects in the specified
+		 * virtual address range. This allows applications to hint to the kernel
+		 * about bo's usage patterns for better memory management.
+		 *
+		 * Supported values for @purge_state_val.val:
+		 *  - DRM_XE_VMA_PURGEABLE_STATE_WILLNEED (0): Marks BO as needed.
+		 *    If BO was purged, returns retained=0 (backing store lost).
+		 *
+		 *  - DRM_XE_VMA_PURGEABLE_STATE_DONTNEED (1): Hints that BO is not
+		 *    currently needed. Kernel may purge it under memory pressure.
+		 *    Only applies to non-shared BOs. Returns retained=1 if not purged.
+		 */
+		struct {
+#define DRM_XE_VMA_PURGEABLE_STATE_WILLNEED	0
+#define DRM_XE_VMA_PURGEABLE_STATE_DONTNEED	1
+			/** @purge_state_val.val: value for DRM_XE_VMA_ATTR_PURGEABLE_STATE */
+			__u32 val;
+
+			/* @purge_state_val.pad */
+			__u32 pad;
+			/**
+			 * @purge_state_val.retained: Pointer to output field for backing
+			 * store status.
+			 *
+			 * Userspace provides a pointer to u32. Kernel writes to it:
+			 * 1 if backing store exists, 0 if purged.
+			 * Similar to i915's drm_i915_gem_madvise.retained field.
+			 */
+			__u64 retained;
+		} purge_state_val;
 	};
 
 	/** @reserved: Reserved */
Signature · 1 line
2.43.0
#2 lore raw

PATCH 2/3 lib/xe: Add purgeable memory ioctl support

In reply to Arvind Yadav

Add xe_vm_madvise_purgeable() helper function to support purgeable memory management through the XE madvise ioctl. This allows applications to hint to the kernel about buffer object usage patterns for better memory management under pressure.

The function provides a clean interface to:
- Mark buffer objects as DONTNEED (purgeable)
- Mark buffer objects as WILLNEED (not purgeable)

Returns the retained value directly (1 if backing store exists, 0 if purged).

Also update __xe_vm_madvise() to reject purgeable state operations and direct users to the dedicated helper.

Cc Matthew Brost <[email protected]>
Cc Thomas Hellström <[email protected]>
Cc Himal Prasad Ghimiray <[email protected]>
---
 lib/xe/xe_ioctl.c | 33 +++++++++++++++++++++++++++++++++
 lib/xe/xe_ioctl.h |  2 ++
 2 files changed, 35 insertions(+)
lib/xe/xe_ioctl.c +33 -0
index 16aae05c9..3f25a0a44 100644
@@ -739,6 +739,9 @@ int __xe_vm_madvise(int fd, uint32_t vm, uint64_t addr, uint64_t range,
 	case DRM_XE_MEM_RANGE_ATTR_PAT:
 		madvise.pat_index.val = op_val;
 		break;
+	case DRM_XE_VMA_ATTR_PURGEABLE_STATE:
+		/* Purgeable state handled by xe_vm_madvise_purgeable */
+		return -EINVAL;
 	default:
 		igt_warn("Unknown attribute\n");
 		return -EINVAL;
@@ -775,6 +778,36 @@ void xe_vm_madvise(int fd, uint32_t vm, uint64_t addr, uint64_t range,
 				      instance), 0);
 }
 
+/**
+ * xe_vm_madvise_purgeable:
+ * @fd: xe device fd
+ * @vm_id: vm_id of the virtual range
+ * @start: start of the virtual address range
+ * @range: size of the virtual address range
+ * @state: purgeable state (DRM_XE_VMA_PURGEABLE_STATE_WILLNEED or DONTNEED)
+ *
+ * Sets the purgeable state for a virtual memory range. This allows applications
+ * to hint to the kernel about buffer object usage patterns for better memory management.
+ *
+ * Returns: retained value (1 if backing store exists, 0 if purged)
+ */
+uint32_t xe_vm_madvise_purgeable(int fd, uint32_t vm_id, uint64_t start,
+				 uint64_t range, uint32_t state)
+{
+	uint32_t retained_val;
+	struct drm_xe_madvise madvise = {
+		.vm_id = vm_id,
+		.start = start,
+		.range = range,
+		.type = DRM_XE_VMA_ATTR_PURGEABLE_STATE,
+		.purge_state_val.val = state,
+		.purge_state_val.retained = (uint64_t)(uintptr_t)&retained_val,
+	};
+
+	igt_assert_eq(igt_ioctl(fd, DRM_IOCTL_XE_MADVISE, &madvise), 0);
+	return retained_val;
+}
+
 #define	BIND_SYNC_VAL	0x686868
 void xe_vm_bind_lr_sync(int fd, uint32_t vm, uint32_t bo, uint64_t offset,
 			uint64_t addr, uint64_t size, uint32_t flags)
lib/xe/xe_ioctl.h +2 -0
index 3ea651063..8eb506915 100644
@@ -107,6 +107,8 @@ int __xe_vm_madvise(int fd, uint32_t vm, uint64_t addr, uint64_t range, uint64_t
 		    uint32_t type, uint32_t op_val, uint16_t policy, uint16_t instance);
 void xe_vm_madvise(int fd, uint32_t vm, uint64_t addr, uint64_t range, uint64_t ext,
 		   uint32_t type, uint32_t op_val, uint16_t policy, uint16_t instance);
+uint32_t xe_vm_madvise_purgeable(int fd, uint32_t vm_id, uint64_t start,
+				 uint64_t range, uint32_t state);
 int xe_vm_number_vmas_in_range(int fd, struct drm_xe_vm_query_mem_range_attr *vmas_attr);
 int xe_vm_vma_attrs(int fd, struct drm_xe_vm_query_mem_range_attr *vmas_attr,
 		    struct drm_xe_mem_range_attr *mem_attr);
Signature · 1 line
2.43.0
#3 lore raw

PATCH 3/3 tests/intel/xe_exec_system_allocator: Add purgeable memory madvise tests

In reply to Arvind Yadav

Add six purgeable memory test cases for system allocator using madvise:

- madvise-purgeable-dontneed-before-mmap: Mark BO as DONTNEED before mmap, verify mmap fails on purged memory

- madvise-purgeable-dontneed-after-mmap: Mark BO as DONTNEED after mmap, verify SIGBUS/SIGSEGV on accessing purged mapping

- madvise-purgeable-dontneed-before-exec: Mark BO as DONTNEED before GPU execution, verify GPU behavior on purged memory with SCRATCH_PAGE VMs

- madvise-purgeable-dontneed-after-exec: Mark BO as DONTNEED after GPU execution, verify previously-used memory becomes inaccessible

- madvise-purgeable-per-vma-tracking: One BO mapped in two VMs becomes purgeable only when BOTH VMAs are marked DONTNEED

- madvise-purgeable-per-vma-protection: One VMA marked DONTNEED allows GPU execution on other VMA; both DONTNEED makes BO purgeable

Tests use xe_vm_madvise_purgeable() for WILLNEED/DONTNEED state management and trigger_memory_pressure() to simulate OOM conditions forcing kernel to reclaim purgeable memory.

Cc Matthew Brost <[email protected]>
Cc Thomas Hellström <[email protected]>
Cc Himal Prasad Ghimiray <[email protected]>
---
 tests/intel/xe_exec_system_allocator.c | 638 +++++++++++++++++++++++++
 1 file changed, 638 insertions(+)
tests/intel/xe_exec_system_allocator.c +638 -0
index 8af66d76e..338037a48 100644
@@ -32,6 +32,15 @@
 #define QUARTER_SEC		(NSEC_PER_SEC / 4)
 #define FIVE_SEC		(5LL * NSEC_PER_SEC)
 
+/* Purgeable test constants */
+#define PURGEABLE_ADDR		0x1a0000
+#define PURGEABLE_ADDR2		0x2b0000
+#define PURGEABLE_BATCH_ADDR	0x3c0000
+#define PURGEABLE_BO_SIZE	4096
+#define PURGEABLE_FENCE_VAL	0xbeef
+#define PURGEABLE_TEST_PATTERN	0xc0ffee
+#define PURGEABLE_DEAD_PATTERN	0xdead
+
 struct test_exec_data {
 	uint32_t batch[32];
 	uint64_t pad;
@@ -2245,6 +2254,599 @@ test_compute(int fd, size_t size, unsigned int flags)
 	xe_vm_destroy(fd, vm);
 }
 
+/**
+ * trigger_memory_pressure - Trigger memory pressure for purgeable tests
+ * @fd: DRM file descriptor
+ * @vm: VM handle
+ *
+ * Creates temporary BOs exceeding VRAM size (VRAM + 64MB) to trigger memory
+ * pressure, forcing kernel to reclaim purgeable BOs in system allocator.
+ */
+static void trigger_memory_pressure(int fd, uint32_t vm)
+{
+	uint64_t vram_size;
+	const uint64_t chunk = 8ull << 20; /* 8 MiB */
+	int max_objs, n = 0;
+	uint32_t *handles;
+	uint64_t total;
+	void *p;
+	uint32_t bo2;
+
+	vram_size = xe_visible_vram_size(fd, 0);
+	max_objs = vram_size / chunk + 64;
+	handles = calloc(max_objs, sizeof(*handles));
+	igt_assert(handles);
+
+	total = 0;
+	while (total < vram_size + (64 << 20) && n < max_objs) {
+		bo2 = xe_bo_create(fd, vm, chunk, vram_if_possible(fd, 0),
+				   DRM_XE_GEM_CREATE_FLAG_NEEDS_VISIBLE_VRAM);
+		handles[n++] = bo2;
+		total += chunk;
+		p = xe_bo_map(fd, bo2, chunk);
+		memset(p, 0xCD, 4096);
+		munmap(p, chunk);
+	}
+
+	for (int i = 0; i < n; i++)
+		gem_close(fd, handles[i]);
+
+	free(handles);
+}
+
+static jmp_buf jmp;
+
+__noreturn static void sigtrap(int sig)
+{
+	siglongjmp(jmp, sig);
+}
+
+/**
+ * purgeable_mark_and_verify_purged - Mark BO as DONTNEED and verify purge
+ * @fd: DRM file descriptor
+ * @vm: VM handle
+ * @addr: Virtual address of the BO
+ * @size: Size of the BO
+ *
+ * Marks BO as DONTNEED, triggers memory pressure, and verifies purge.
+ * Returns: true if BO was successfully purged, false otherwise
+ */
+static bool purgeable_mark_and_verify_purged(int fd, uint32_t vm, uint64_t addr, size_t size)
+{
+	uint32_t retained;
+
+	/* Mark as DONTNEED */
+	retained = xe_vm_madvise_purgeable(fd, vm, addr, size,
+					   DRM_XE_VMA_PURGEABLE_STATE_DONTNEED);
+	if (retained != 1)
+		return false;
+
+	/* Trigger memory pressure */
+	trigger_memory_pressure(fd, vm);
+
+	/* Verify purged */
+	retained = xe_vm_madvise_purgeable(fd, vm, addr, size,
+					   DRM_XE_VMA_PURGEABLE_STATE_WILLNEED);
+	return retained == 0;
+}
+
+/**
+ * purgeable_setup_simple_bo - Setup VM and bind a single BO
+ * @fd: DRM file descriptor
+ * @vm: Output VM handle
+ * @bo: Output BO handle
+ * @addr: Virtual address to bind at
+ * @size: Size of the BO
+ * @use_scratch: Whether to use scratch page flag
+ *
+ * Helper to create VM, BO, and bind it at the specified address.
+ */
+static void purgeable_setup_simple_bo(int fd, uint32_t *vm, uint32_t *bo,
+				      uint64_t addr, size_t size, bool use_scratch)
+{
+	struct drm_xe_sync sync = {
+		.type = DRM_XE_SYNC_TYPE_USER_FENCE,
+		.flags = DRM_XE_SYNC_FLAG_SIGNAL,
+		.timeline_value = 1,
+	};
+	uint64_t sync_val = 0;
+
+	*vm = xe_vm_create(fd, use_scratch ? DRM_XE_VM_CREATE_FLAG_SCRATCH_PAGE : 0, 0);
+	*bo = xe_bo_create(fd, *vm, size, vram_if_possible(fd, 0), 0);
+
+	sync.addr = to_user_pointer(&sync_val);
+	xe_vm_bind_async(fd, *vm, 0, *bo, 0, addr, size, &sync, 1);
+	xe_wait_ufence(fd, &sync_val, 1, 0, NSEC_PER_SEC);
+}
+
+/**
+ * purgeable_setup_batch_and_data - Setup VM with batch and data BOs for GPU exec
+ * @fd: DRM file descriptor
+ * @vm: Output VM handle
+ * @bind_engine: Output bind engine handle
+ * @batch_bo: Output batch BO handle
+ * @data_bo: Output data BO handle
+ * @batch: Output batch buffer pointer
+ * @data: Output data buffer pointer
+ * @batch_addr: Batch virtual address
+ * @data_addr: Data virtual address
+ * @batch_size: Batch buffer size
+ * @data_size: Data buffer size
+ *
+ * Helper to create VM, bind engine, batch and data BOs, and bind them.
+ */
+static void purgeable_setup_batch_and_data(int fd, uint32_t *vm, uint32_t *bind_engine,
+					    uint32_t *batch_bo, uint32_t *data_bo,
+					    uint32_t **batch, uint32_t **data,
+					    uint64_t batch_addr, uint64_t data_addr,
+					    size_t batch_size, size_t data_size)
+{
+	struct drm_xe_sync sync = {
+		.type = DRM_XE_SYNC_TYPE_USER_FENCE,
+		.flags = DRM_XE_SYNC_FLAG_SIGNAL,
+		.timeline_value = PURGEABLE_FENCE_VAL,
+	};
+	uint64_t vm_sync = 0;
+
+	*vm = xe_vm_create(fd, DRM_XE_VM_CREATE_FLAG_SCRATCH_PAGE, 0);
+	*bind_engine = xe_bind_exec_queue_create(fd, *vm, 0);
+
+	/* Create and bind batch BO */
+	*batch_bo = xe_bo_create(fd, *vm, batch_size, vram_if_possible(fd, 0),
+				 DRM_XE_GEM_CREATE_FLAG_NEEDS_VISIBLE_VRAM);
+	*batch = xe_bo_map(fd, *batch_bo, batch_size);
+
+	sync.addr = to_user_pointer(&vm_sync);
+	xe_vm_bind_async(fd, *vm, *bind_engine, *batch_bo, 0, batch_addr, batch_size, &sync, 1);
+	xe_wait_ufence(fd, &vm_sync, PURGEABLE_FENCE_VAL, 0, NSEC_PER_SEC);
+
+	/* Create and bind data BO */
+	*data_bo = xe_bo_create(fd, *vm, data_size, vram_if_possible(fd, 0),
+				DRM_XE_GEM_CREATE_FLAG_NEEDS_VISIBLE_VRAM);
+	*data = xe_bo_map(fd, *data_bo, data_size);
+
+	vm_sync = 0;
+	xe_vm_bind_async(fd, *vm, *bind_engine, *data_bo, 0, data_addr, data_size, &sync, 1);
+	xe_wait_ufence(fd, &vm_sync, PURGEABLE_FENCE_VAL, 0, NSEC_PER_SEC);
+}
+
+/**
+ * purgeable_setup_two_vms_shared_bo - Setup two VMs with one shared BO
+ * @fd: DRM file descriptor
+ * @vm1: Output first VM handle
+ * @vm2: Output second VM handle
+ * @bo: Output shared BO handle
+ * @addr1: Virtual address in VM1
+ * @addr2: Virtual address in VM2
+ * @size: Size of the BO
+ * @use_scratch: Whether to use scratch page flag for VMs
+ *
+ * Helper to create two VMs and bind one shared BO in both VMs.
+ * Returns mapped pointer to the BO.
+ */
+static void *purgeable_setup_two_vms_shared_bo(int fd, uint32_t *vm1, uint32_t *vm2,
+						uint32_t *bo, uint64_t addr1, uint64_t addr2,
+						size_t size, bool use_scratch)
+{
+	struct drm_xe_sync sync = {
+		.type = DRM_XE_SYNC_TYPE_USER_FENCE,
+		.flags = DRM_XE_SYNC_FLAG_SIGNAL,
+		.timeline_value = 1,
+	};
+	uint64_t sync_val = 0;
+	void *map;
+
+	/* Create two VMs */
+	*vm1 = xe_vm_create(fd, use_scratch ? DRM_XE_VM_CREATE_FLAG_SCRATCH_PAGE : 0, 0);
+	*vm2 = xe_vm_create(fd, use_scratch ? DRM_XE_VM_CREATE_FLAG_SCRATCH_PAGE : 0, 0);
+
+	/* Create shared BO */
+	*bo = xe_bo_create(fd, 0, size, vram_if_possible(fd, 0),
+			   DRM_XE_GEM_CREATE_FLAG_NEEDS_VISIBLE_VRAM);
+
+	map = xe_bo_map(fd, *bo, size);
+	memset(map, 0xAB, size);
+
+	/* Bind BO in VM1 */
+	sync.addr = to_user_pointer(&sync_val);
+	sync_val = 0;
+	xe_vm_bind_async(fd, *vm1, 0, *bo, 0, addr1, size, &sync, 1);
+	xe_wait_ufence(fd, &sync_val, 1, 0, NSEC_PER_SEC);
+
+	/* Bind BO in VM2 */
+	sync_val = 0;
+	xe_vm_bind_async(fd, *vm2, 0, *bo, 0, addr2, size, &sync, 1);
+	xe_wait_ufence(fd, &sync_val, 1, 0, NSEC_PER_SEC);
+
+	return map;
+}
+
+/**
+ * SUBTEST: madvise-purgeable-dontneed-before-mmap
+ * Description: Test marking memory as DONTNEED before mmap access in system allocator
+ * Test category: functionality test
+ */
+static void test_dontneed_before_mmap_madvise(int fd, struct drm_xe_engine_class_instance *hwe)
+{
+	uint32_t bo, vm;
+	uint64_t addr = PURGEABLE_ADDR;
+	size_t bo_size = PURGEABLE_BO_SIZE;
+	void *map;
+
+	purgeable_setup_simple_bo(fd, &vm, &bo, addr, bo_size, false);
+	if (!purgeable_mark_and_verify_purged(fd, vm, addr, bo_size))
+		igt_skip("Unable to induce purge on this platform/config");
+
+	/* Try to mmap - should fail on purged BO */
+	map = __gem_mmap__device_coherent(fd, bo, 0, bo_size, PROT_READ | PROT_WRITE);
+	igt_assert_f(map == NULL, "mmap should fail on purged BO");
+	igt_assert_f(errno == EINVAL || errno == EFAULT,
+		     "Expected EINVAL or EFAULT, got errno=%d\n", errno);
+
+	gem_close(fd, bo);
+	xe_vm_destroy(fd, vm);
+}
+
+/**
+ * SUBTEST: madvise-purgeable-dontneed-after-mmap
+ * Description: Test marking memory as DONTNEED after mmap in system allocator
+ * Test category: functionality test
+ */
+static void test_dontneed_after_mmap_madvise(int fd, struct drm_xe_engine_class_instance *hwe)
+{
+	uint32_t bo, vm;
+	uint64_t addr = PURGEABLE_ADDR;
+	size_t bo_size = PURGEABLE_BO_SIZE;
+	void *map;
+
+	purgeable_setup_simple_bo(fd, &vm, &bo, addr, bo_size, true);
+
+	map = xe_bo_map(fd, bo, bo_size);
+	memset(map, 0xAB, bo_size);
+
+	if (!purgeable_mark_and_verify_purged(fd, vm, addr, bo_size))
+		igt_skip("Unable to induce purge on this platform/config");
+
+	/* Access purged mapping - should trigger SIGBUS/SIGSEGV */
+	{
+		sighandler_t old_sigsegv, old_sigbus;
+		char *ptr = (char *)map;
+		int sig;
+
+		old_sigsegv = signal(SIGSEGV, (__sighandler_t)sigtrap);
+		old_sigbus = signal(SIGBUS, (__sighandler_t)sigtrap);
+
+		sig = sigsetjmp(jmp, SIGBUS | SIGSEGV);
+		if (sig == SIGBUS || sig == SIGSEGV) {
+			/* Expected - purged mapping access failed */
+		} else if (sig == 0) {
+			*ptr = 0;
+			igt_assert_f(false, "Access to purged mapping should trigger signal\n");
+		} else {
+			igt_assert_f(false, "unexpected signal %d\n", sig);
+		}
+
+		signal(SIGBUS, old_sigbus);
+		signal(SIGSEGV, old_sigsegv);
+	}
+
+	munmap(map, bo_size);
+	gem_close(fd, bo);
+	xe_vm_destroy(fd, vm);
+}
+
+/**
+ * SUBTEST: madvise-purgeable-dontneed-before-exec
+ * Description: Test marking memory as DONTNEED before GPU exec in system allocator
+ * Test category: functionality test
+ */
+static void test_dontneed_before_exec_madvise(int fd, struct drm_xe_engine_class_instance *hwe)
+{
+	uint32_t vm, exec_queue, bo, batch_bo, bind_engine;
+	uint64_t data_addr = 0x1a0000;
+	uint64_t batch_addr = 0x2a0000;
+	size_t data_size = 4096;
+	size_t batch_size = 4096;
+	struct drm_xe_sync sync[1] = {
+		{ .type = DRM_XE_SYNC_TYPE_USER_FENCE,
+		  .flags = DRM_XE_SYNC_FLAG_SIGNAL,
+		  .timeline_value = 0xbeef },
+	};
+	struct drm_xe_exec exec = {
+		.num_batch_buffer = 1,
+		.num_syncs = 1,
+		.syncs = to_user_pointer(sync),
+	};
+	uint32_t *data, *batch;
+	uint64_t vm_sync = 0;
+	int b, ret;
+
+	purgeable_setup_batch_and_data(fd, &vm, &bind_engine, &batch_bo, &bo,
+					&batch, &data, batch_addr, data_addr,
+					batch_size, data_size);
+
+	/* Prepare batch */
+	b = 0;
+	batch[b++] = MI_STORE_DWORD_IMM_GEN4;
+	batch[b++] = data_addr;
+	batch[b++] = data_addr >> 32;
+	batch[b++] = PURGEABLE_DEAD_PATTERN;
+	batch[b++] = MI_BATCH_BUFFER_END;
+
+	igt_assert(purgeable_mark_and_verify_purged(fd, vm, data_addr, data_size));
+
+	/* Try to execute - should fail or cause GPU fault */
+	exec_queue = xe_exec_queue_create(fd, vm, hwe, 0);
+	exec.exec_queue_id = exec_queue;
+	exec.address = batch_addr;
+
+	vm_sync = 0;
+	sync[0].addr = to_user_pointer(&vm_sync);
+
+	ret = __xe_exec(fd, &exec);
+	if (ret == 0) {
+		int64_t timeout = NSEC_PER_SEC;
+
+		__xe_wait_ufence(fd, &vm_sync, 0xbeef, exec_queue, &timeout);
+		/* Wait may succeed (NULL rebind) or fail (purged) - both acceptable */
+	}
+
+	munmap(data, data_size);
+	munmap(batch, batch_size);
+	gem_close(fd, bo);
+	gem_close(fd, batch_bo);
+	xe_exec_queue_destroy(fd, bind_engine);
+	xe_exec_queue_destroy(fd, exec_queue);
+	xe_vm_destroy(fd, vm);
+}
+
+/**
+ * SUBTEST: madvise-purgeable-dontneed-after-exec
+ * Description: Test marking memory as DONTNEED after successful GPU exec
+ * Test category: functionality test
+ */
+static void test_dontneed_after_exec_madvise(int fd, struct drm_xe_engine_class_instance *hwe)
+{
+	uint32_t vm, exec_queue, bo, batch_bo, bind_engine;
+	uint64_t data_addr = 0x1a0000;
+	uint64_t batch_addr = 0x2a0000;
+	size_t data_size = 4096;
+	size_t batch_size = 4096;
+	struct drm_xe_sync sync[2] = {
+		{ .type = DRM_XE_SYNC_TYPE_USER_FENCE,
+		  .flags = DRM_XE_SYNC_FLAG_SIGNAL,
+		  .timeline_value = 0xbeef },
+		{ .type = DRM_XE_SYNC_TYPE_SYNCOBJ,
+		  .flags = DRM_XE_SYNC_FLAG_SIGNAL },
+	};
+	struct drm_xe_exec exec = {
+		.num_batch_buffer = 1,
+		.num_syncs = 2,
+		.syncs = to_user_pointer(sync),
+	};
+	uint32_t *data, *batch;
+	uint32_t syncobj;
+	int b, ret;
+
+	purgeable_setup_batch_and_data(fd, &vm, &bind_engine, &batch_bo, &bo,
+					&batch, &data, batch_addr, data_addr,
+					batch_size, data_size);
+	memset(data, 0, data_size);
+
+	syncobj = syncobj_create(fd, 0);
+
+	/* Prepare batch to write to data BO */
+	b = 0;
+	batch[b++] = MI_STORE_DWORD_IMM_GEN4;
+	batch[b++] = data_addr;
+	batch[b++] = data_addr >> 32;
+	batch[b++] = 0xfeed0001;
+	batch[b++] = MI_BATCH_BUFFER_END;
+
+	exec_queue = xe_exec_queue_create(fd, vm, hwe, 0);
+	exec.exec_queue_id = exec_queue;
+	exec.address = batch_addr;
+
+	/* Use only syncobj for exec (not USER_FENCE) */
+	sync[1].handle = syncobj;
+	exec.num_syncs = 1;
+	exec.syncs = to_user_pointer(&sync[1]);
+
+	ret = __xe_exec(fd, &exec);
+	igt_assert_eq(ret, 0);
+
+	igt_assert(syncobj_wait(fd, &syncobj, 1, INT64_MAX, 0, NULL));
+	munmap(data, data_size);
+	data = xe_bo_map(fd, bo, data_size);
+	igt_assert_eq(data[0], 0xfeed0001);
+
+	igt_assert(purgeable_mark_and_verify_purged(fd, vm, data_addr, data_size));
+
+	/* Prepare second batch (different value) */
+	b = 0;
+	batch[b++] = MI_STORE_DWORD_IMM_GEN4;
+	batch[b++] = data_addr;
+	batch[b++] = data_addr >> 32;
+	batch[b++] = 0xfeed0002;
+	batch[b++] = MI_BATCH_BUFFER_END;
+
+	ret = __xe_exec(fd, &exec);
+	if (ret == 0) {
+		/* Exec succeeded, but wait may fail on purged BO (both behaviors valid) */
+		syncobj_wait(fd, &syncobj, 1, INT64_MAX, 0, NULL);
+	}
+
+	munmap(data, data_size);
+	munmap(batch, batch_size);
+	gem_close(fd, bo);
+	gem_close(fd, batch_bo);
+	syncobj_destroy(fd, syncobj);
+	xe_exec_queue_destroy(fd, bind_engine);
+	xe_exec_queue_destroy(fd, exec_queue);
+	xe_vm_destroy(fd, vm);
+}
+
+/**
+ * SUBTEST: madvise-purgeable-per-vma-tracking
+ * Description: Test per-VMA purgeable state tracking with multiple VMs
+ * Test category: functionality test
+ */
+static void test_per_vma_tracking_madvise(int fd, struct drm_xe_engine_class_instance *hwe)
+{
+	uint32_t bo, vm1, vm2;
+	uint64_t addr1 = PURGEABLE_ADDR;
+	uint64_t addr2 = PURGEABLE_ADDR2;
+	size_t bo_size = PURGEABLE_BO_SIZE;
+	uint32_t retained;
+	void *map;
+
+	map = purgeable_setup_two_vms_shared_bo(fd, &vm1, &vm2, &bo,
+							addr1, addr2, bo_size, false);
+
+	/* Mark VMA1 as DONTNEED */
+	retained = xe_vm_madvise_purgeable(fd, vm1, addr1, bo_size,
+					   DRM_XE_VMA_PURGEABLE_STATE_DONTNEED);
+	igt_assert_eq(retained, 1);
+
+	/* Verify BO NOT purgeable (VMA2 still WILLNEED) */
+	retained = xe_vm_madvise_purgeable(fd, vm1, addr1, bo_size,
+					   DRM_XE_VMA_PURGEABLE_STATE_WILLNEED);
+	igt_assert_eq(retained, 1);
+
+	/* Mark both VMAs as DONTNEED */
+	retained = xe_vm_madvise_purgeable(fd, vm1, addr1, bo_size,
+					   DRM_XE_VMA_PURGEABLE_STATE_DONTNEED);
+	igt_assert_eq(retained, 1);
+
+	retained = xe_vm_madvise_purgeable(fd, vm2, addr2, bo_size,
+					   DRM_XE_VMA_PURGEABLE_STATE_DONTNEED);
+	igt_assert_eq(retained, 1);
+
+	/* Trigger pressure and verify BO was purged */
+	trigger_memory_pressure(fd, vm1);
+
+	retained = xe_vm_madvise_purgeable(fd, vm1, addr1, bo_size,
+					   DRM_XE_VMA_PURGEABLE_STATE_WILLNEED);
+	igt_assert_eq(retained, 0);
+
+	munmap(map, bo_size);
+	gem_close(fd, bo);
+	xe_vm_destroy(fd, vm1);
+	xe_vm_destroy(fd, vm2);
+}
+
+/**
+ * SUBTEST: madvise-purgeable-per-vma-protection
+ * Description: Test per-VMA protection from purging with GPU workload
+ * Test category: functionality test
+ */
+static void test_per_vma_protection_madvise(int fd, struct drm_xe_engine_class_instance *hwe)
+{
+	uint32_t vm1, vm2, exec_queue, bo, batch_bo, bind_engine;
+	uint64_t data_addr1 = PURGEABLE_ADDR;
+	uint64_t data_addr2 = PURGEABLE_ADDR2;
+	uint64_t batch_addr = PURGEABLE_BATCH_ADDR;
+	size_t data_size = PURGEABLE_BO_SIZE;
+	size_t batch_size = PURGEABLE_BO_SIZE;
+	struct drm_xe_sync sync[2] = {
+		{ .type = DRM_XE_SYNC_TYPE_USER_FENCE,
+		  .flags = DRM_XE_SYNC_FLAG_SIGNAL,
+		  .timeline_value = PURGEABLE_FENCE_VAL },
+		{ .type = DRM_XE_SYNC_TYPE_SYNCOBJ,
+		  .flags = DRM_XE_SYNC_FLAG_SIGNAL },
+	};
+	struct drm_xe_exec exec = {
+		.num_batch_buffer = 1,
+		.num_syncs = 1,
+		.syncs = to_user_pointer(&sync[1]),
+	};
+	uint32_t *data, *batch;
+	uint64_t vm_sync = 0;
+	uint32_t retained, syncobj;
+	int b, ret;
+
+	/* Create two VMs and bind shared data BO */
+	data = purgeable_setup_two_vms_shared_bo(fd, &vm1, &vm2, &bo,
+							 data_addr1, data_addr2, data_size, true);
+	memset(data, 0, data_size);
+	bind_engine = xe_bind_exec_queue_create(fd, vm2, 0);
+
+	/* Create and bind batch BO in VM2 */
+	batch_bo = xe_bo_create(fd, vm2, batch_size, vram_if_possible(fd, 0),
+				DRM_XE_GEM_CREATE_FLAG_NEEDS_VISIBLE_VRAM);
+	batch = xe_bo_map(fd, batch_bo, batch_size);
+
+	sync[0].addr = to_user_pointer(&vm_sync);
+	vm_sync = 0;
+	xe_vm_bind_async(fd, vm2, bind_engine, batch_bo, 0, batch_addr, batch_size, sync, 1);
+	xe_wait_ufence(fd, &vm_sync, PURGEABLE_FENCE_VAL, 0, NSEC_PER_SEC);
+
+	/* Mark VMA1 as DONTNEED, VMA2 stays WILLNEED */
+	retained = xe_vm_madvise_purgeable(fd, vm1, data_addr1, data_size,
+					   DRM_XE_VMA_PURGEABLE_STATE_DONTNEED);
+	igt_assert_eq(retained, 1);
+
+	/* Trigger pressure - BO should survive (VMA2 protects) */
+	trigger_memory_pressure(fd, vm1);
+
+	retained = xe_vm_madvise_purgeable(fd, vm2, data_addr2, data_size,
+					   DRM_XE_VMA_PURGEABLE_STATE_WILLNEED);
+	igt_assert_eq(retained, 1);
+
+	/* GPU workload - should succeed */
+	b = 0;
+	batch[b++] = MI_STORE_DWORD_IMM_GEN4;
+	batch[b++] = data_addr2;
+	batch[b++] = data_addr2 >> 32;
+	batch[b++] = PURGEABLE_TEST_PATTERN;
+	batch[b++] = MI_BATCH_BUFFER_END;
+
+	syncobj = syncobj_create(fd, 0);
+	sync[1].handle = syncobj;
+	exec_queue = xe_exec_queue_create(fd, vm2, hwe, 0);
+	exec.exec_queue_id = exec_queue;
+	exec.address = batch_addr;
+
+	ret = __xe_exec(fd, &exec);
+	igt_assert_eq(ret, 0);
+	igt_assert(syncobj_wait(fd, &syncobj, 1, INT64_MAX, 0, NULL));
+
+	munmap(data, data_size);
+	data = xe_bo_map(fd, bo, data_size);
+	igt_assert_eq(data[0], PURGEABLE_TEST_PATTERN);
+
+	/* Mark both VMAs DONTNEED */
+	retained = xe_vm_madvise_purgeable(fd, vm2, data_addr2, data_size,
+					   DRM_XE_VMA_PURGEABLE_STATE_DONTNEED);
+	igt_assert_eq(retained, 1);
+
+	/* Trigger pressure - BO should be purged */
+	trigger_memory_pressure(fd, vm1);
+
+	retained = xe_vm_madvise_purgeable(fd, vm2, data_addr2, data_size,
+					   DRM_XE_VMA_PURGEABLE_STATE_WILLNEED);
+	igt_assert_eq(retained, 0);
+
+	/* GPU workload - should fail or succeed with NULL rebind */
+	batch[3] = PURGEABLE_DEAD_PATTERN;
+
+	ret = __xe_exec(fd, &exec);
+	/* With SCRATCH_PAGE, kernel may allow exec with NULL rebind.
+	 * Without it, exec should fail with -EIO/-EFAULT or wait should timeout.
+	 * Both behaviors are valid depending on kernel support.
+	 */
+
+	munmap(data, data_size);
+	munmap(batch, batch_size);
+	gem_close(fd, bo);
+	gem_close(fd, batch_bo);
+	syncobj_destroy(fd, syncobj);
+	xe_exec_queue_destroy(fd, bind_engine);
+	xe_exec_queue_destroy(fd, exec_queue);
+	xe_vm_destroy(fd, vm1);
+	xe_vm_destroy(fd, vm2);
+}
+
 struct section {
 	const char *name;
 	unsigned long long flags;
@@ -2649,6 +3251,42 @@ int igt_main()
 			test_compute(fd, SZ_2M, s->flags);
 	}
 
+	igt_subtest("madvise-purgeable-dontneed-before-mmap")
+		xe_for_each_engine(fd, hwe) {
+			test_dontneed_before_mmap_madvise(fd, hwe);
+			break;
+		}
+
+	igt_subtest("madvise-purgeable-dontneed-after-mmap")
+		xe_for_each_engine(fd, hwe) {
+			test_dontneed_after_mmap_madvise(fd, hwe);
+			break;
+		}
+
+	igt_subtest("madvise-purgeable-dontneed-before-exec")
+		xe_for_each_engine(fd, hwe) {
+			test_dontneed_before_exec_madvise(fd, hwe);
+			break;
+		}
+
+	igt_subtest("madvise-purgeable-dontneed-after-exec")
+		xe_for_each_engine(fd, hwe) {
+			test_dontneed_after_exec_madvise(fd, hwe);
+			break;
+		}
+
+	igt_subtest("madvise-purgeable-per-vma-tracking")
+		xe_for_each_engine(fd, hwe) {
+			test_per_vma_tracking_madvise(fd, hwe);
+			break;
+		}
+
+	igt_subtest("madvise-purgeable-per-vma-protection")
+		xe_for_each_engine(fd, hwe) {
+			test_per_vma_protection_madvise(fd, hwe);
+			break;
+		}
+
 	igt_fixture() {
 		xe_device_put(fd);
 		drm_close_driver(fd);
Signature · 1 line
2.43.0
#4 lore raw

Re: [PATCH i-g-t 3/3] tests/intel/xe_exec_system_allocator: Add purgeable memory madvise tests

Hi, Arvind,

Quoted 2 lines · Arvind Yadav

Add six purgeable memory test cases for system allocator using madvise:

I wonder is xe_exec_system_allocator really the igt we should use for this? Sure, it's possible to bind bos to a SVM VM, but I think that's not really the typical use-case, but rather ordinary VMs used by graphics UMDs.

xe_exec_system_allocator is already a huge test, primarily intended to test the system allocator functionality rather than bo functionality. Can't we craft a separate igt test app for this that tests the purgeability functionality for various VM types?

Thanks,
Thomas

Quoted 803 lines

- madvise-purgeable-dontneed-before-mmap: Mark BO as DONTNEED before mmap,
  verify mmap fails on purged memory

- madvise-purgeable-dontneed-after-mmap: Mark BO as DONTNEED after mmap,
  verify SIGBUS/SIGSEGV on accessing purged mapping

- madvise-purgeable-dontneed-before-exec: Mark BO as DONTNEED before GPU
  execution, verify GPU behavior on purged memory with SCRATCH_PAGE VMs

- madvise-purgeable-dontneed-after-exec: Mark BO as DONTNEED after GPU
  execution, verify previously-used memory becomes inaccessible

- madvise-purgeable-per-vma-tracking: One BO mapped in two VMs becomes
  purgeable only when BOTH VMAs are marked DONTNEED

- madvise-purgeable-per-vma-protection: One VMA marked DONTNEED allows
  GPU execution on other VMA; both DONTNEED makes BO purgeable

Tests use xe_vm_madvise_purgeable() for WILLNEED/DONTNEED state management
and trigger_memory_pressure() to simulate OOM conditions forcing kernel to
reclaim purgeable memory.

Cc Matthew Brost <[email protected]>
Cc Thomas Hellström <[email protected]>
Cc Himal Prasad Ghimiray <[email protected]>

---
 tests/intel/xe_exec_system_allocator.c | 638
+++++++++++++++++++++++++

 1 file changed, 638 insertions(+)
tests/intel/xe_exec_system_allocator.c +0 -0
index 8af66d76e..338037a48 100644
@@ -32,6 +32,15 @@
  #define QUARTER_SEC		(NSEC_PER_SEC / 4)
  #define FIVE_SEC		(5LL * NSEC_PER_SEC)

tests/intel/xe_exec_system_allocator.c +9 -0
+/* Purgeable test constants */
+#define PURGEABLE_ADDR		0x1a0000
+#define PURGEABLE_ADDR2		0x2b0000
+#define PURGEABLE_BATCH_ADDR	0x3c0000
+#define PURGEABLE_BO_SIZE	4096
+#define PURGEABLE_FENCE_VAL	0xbeef
+#define PURGEABLE_TEST_PATTERN	0xc0ffee
+#define PURGEABLE_DEAD_PATTERN	0xdead
+

 struct test_exec_data {
  uint32_t batch[32];
  uint64_t pad;

tests/intel/xe_exec_system_allocator.c +0 -0
@@ -2245,6 +2254,599 @@ test_compute(int fd, size_t size, unsigned
 int flags)
  	xe_vm_destroy(fd, vm);
  }


+/**
+ * trigger_memory_pressure - Trigger memory pressure for purgeable tests
+ * @fd: DRM file descriptor
+ * @vm: VM handle
+ *
+ * Creates temporary BOs exceeding VRAM size (VRAM + 64MB) to trigger memory
+ * pressure, forcing kernel to reclaim purgeable BOs in system allocator.
+ */

tests/intel/xe_exec_system_allocator.c +18 -0
+static void trigger_memory_pressure(int fd, uint32_t vm)
+{
+	uint64_t vram_size;
+	const uint64_t chunk = 8ull << 20; /* 8 MiB */
+	int max_objs, n = 0;
+	uint32_t *handles;
+	uint64_t total;
+	void *p;
+	uint32_t bo2;
+
+	vram_size = xe_visible_vram_size(fd, 0);
+	max_objs = vram_size / chunk + 64;
+	handles = calloc(max_objs, sizeof(*handles));
+	igt_assert(handles);
+
+	total = 0;
+	while (total < vram_size + (64 << 20) && n < max_objs) {
+		bo2 = xe_bo_create(fd, vm, chunk,

vram_if_possible(fd, 0),

tests/intel/xe_exec_system_allocator.c +1 -0
+				  

DRM_XE_GEM_CREATE_FLAG_NEEDS_VISIBLE_VRAM);

tests/intel/xe_exec_system_allocator.c +22 -0
+		handles[n++] = bo2;
+		total += chunk;
+		p = xe_bo_map(fd, bo2, chunk);
+		memset(p, 0xCD, 4096);
+		munmap(p, chunk);
+	}
+
+	for (int i = 0; i < n; i++)
+		gem_close(fd, handles[i]);
+
+	free(handles);
+}
+
+static jmp_buf jmp;
+
+__noreturn static void sigtrap(int sig)
+{
+	siglongjmp(jmp, sig);
+}
+
+/**
+ * purgeable_mark_and_verify_purged - Mark BO as DONTNEED and verify

purge
+ * @fd: DRM file descriptor
+ * @vm: VM handle
+ * @addr: Virtual address of the BO
+ * @size: Size of the BO
+ *
+ * Marks BO as DONTNEED, triggers memory pressure, and verifies purge.
+ * Returns: true if BO was successfully purged, false otherwise
+ */
+static bool purgeable_mark_and_verify_purged(int fd, uint32_t vm, uint64_t addr, size_t size)

tests/intel/xe_exec_system_allocator.c +6 -0
+{
+	uint32_t retained;
+
+	/* Mark as DONTNEED */
+	retained = xe_vm_madvise_purgeable(fd, vm, addr, size,
+					  

DRM_XE_VMA_PURGEABLE_STATE_DONTNEED);

tests/intel/xe_exec_system_allocator.c +9 -0
+	if (retained != 1)
+		return false;
+
+	/* Trigger memory pressure */
+	trigger_memory_pressure(fd, vm);
+
+	/* Verify purged */
+	retained = xe_vm_madvise_purgeable(fd, vm, addr, size,
+					  

DRM_XE_VMA_PURGEABLE_STATE_WILLNEED);

tests/intel/xe_exec_system_allocator.c +15 -0
+	return retained == 0;
+}
+
+/**
+ * purgeable_setup_simple_bo - Setup VM and bind a single BO
+ * @fd: DRM file descriptor
+ * @vm: Output VM handle
+ * @bo: Output BO handle
+ * @addr: Virtual address to bind at
+ * @size: Size of the BO
+ * @use_scratch: Whether to use scratch page flag
+ *
+ * Helper to create VM, BO, and bind it at the specified address.
+ */
+static void purgeable_setup_simple_bo(int fd, uint32_t *vm, uint32_t

*bo,

tests/intel/xe_exec_system_allocator.c +1 -0
+				      uint64_t addr, size_t size,

bool use_scratch)

tests/intel/xe_exec_system_allocator.c +9 -0
+{
+	struct drm_xe_sync sync = {
+		.type = DRM_XE_SYNC_TYPE_USER_FENCE,
+		.flags = DRM_XE_SYNC_FLAG_SIGNAL,
+		.timeline_value = 1,
+	};
+	uint64_t sync_val = 0;
+
+	*vm = xe_vm_create(fd, use_scratch ?

DRM_XE_VM_CREATE_FLAG_SCRATCH_PAGE : 0, 0);

tests/intel/xe_exec_system_allocator.c +1 -0
+	*bo = xe_bo_create(fd, *vm, size, vram_if_possible(fd, 0),

0);

tests/intel/xe_exec_system_allocator.c +8 -0
+
+	sync.addr = to_user_pointer(&sync_val);
+	xe_vm_bind_async(fd, *vm, 0, *bo, 0, addr, size, &sync, 1);
+	xe_wait_ufence(fd, &sync_val, 1, 0, NSEC_PER_SEC);
+}
+
+/**
+ * purgeable_setup_batch_and_data - Setup VM with batch and data BOs

for GPU exec
+ * @fd: DRM file descriptor
+ * @vm: Output VM handle
+ * @bind_engine: Output bind engine handle
+ * @batch_bo: Output batch BO handle
+ * @data_bo: Output data BO handle
+ * @batch: Output batch buffer pointer
+ * @data: Output data buffer pointer
+ * @batch_addr: Batch virtual address
+ * @data_addr: Data virtual address
+ * @batch_size: Batch buffer size
+ * @data_size: Data buffer size
+ *
+ * Helper to create VM, bind engine, batch and data BOs, and bind them.
+ */
+static void purgeable_setup_batch_and_data(int fd, uint32_t *vm, uint32_t *bind_engine,

tests/intel/xe_exec_system_allocator.c +1 -0
+					    uint32_t *batch_bo,

uint32_t *data_bo,

tests/intel/xe_exec_system_allocator.c +1 -0
+					    uint32_t **batch,

uint32_t **data,

tests/intel/xe_exec_system_allocator.c +1 -0
+					    uint64_t batch_addr,

uint64_t data_addr,

tests/intel/xe_exec_system_allocator.c +1 -0
+					    size_t batch_size,

size_t data_size)

tests/intel/xe_exec_system_allocator.c +9 -0
+{
+	struct drm_xe_sync sync = {
+		.type = DRM_XE_SYNC_TYPE_USER_FENCE,
+		.flags = DRM_XE_SYNC_FLAG_SIGNAL,
+		.timeline_value = PURGEABLE_FENCE_VAL,
+	};
+	uint64_t vm_sync = 0;
+
+	*vm = xe_vm_create(fd, DRM_XE_VM_CREATE_FLAG_SCRATCH_PAGE,

0);

tests/intel/xe_exec_system_allocator.c +4 -0
+	*bind_engine = xe_bind_exec_queue_create(fd, *vm, 0);
+
+	/* Create and bind batch BO */
+	*batch_bo = xe_bo_create(fd, *vm, batch_size,

vram_if_possible(fd, 0),

tests/intel/xe_exec_system_allocator.c +1 -0
+				

DRM_XE_GEM_CREATE_FLAG_NEEDS_VISIBLE_VRAM);

tests/intel/xe_exec_system_allocator.c +4 -0
+	*batch = xe_bo_map(fd, *batch_bo, batch_size);
+
+	sync.addr = to_user_pointer(&vm_sync);
+	xe_vm_bind_async(fd, *vm, *bind_engine, *batch_bo, 0,

batch_addr, batch_size, &sync, 1);

tests/intel/xe_exec_system_allocator.c +1 -0
+	xe_wait_ufence(fd, &vm_sync, PURGEABLE_FENCE_VAL, 0,

NSEC_PER_SEC);

tests/intel/xe_exec_system_allocator.c +3 -0
+
+	/* Create and bind data BO */
+	*data_bo = xe_bo_create(fd, *vm, data_size,

vram_if_possible(fd, 0),

tests/intel/xe_exec_system_allocator.c +1 -0
+				DRM_XE_GEM_CREATE_FLAG_NEEDS_VISIBLE

_VRAM);

tests/intel/xe_exec_system_allocator.c +4 -0
+	*data = xe_bo_map(fd, *data_bo, data_size);
+
+	vm_sync = 0;
+	xe_vm_bind_async(fd, *vm, *bind_engine, *data_bo, 0,

data_addr, data_size, &sync, 1);

tests/intel/xe_exec_system_allocator.c +1 -0
+	xe_wait_ufence(fd, &vm_sync, PURGEABLE_FENCE_VAL, 0,

NSEC_PER_SEC);

tests/intel/xe_exec_system_allocator.c +4 -0
+}
+
+/**
+ * purgeable_setup_two_vms_shared_bo - Setup two VMs with one shared

BO
+ * @fd: DRM file descriptor
+ * @vm1: Output first VM handle
+ * @vm2: Output second VM handle
+ * @bo: Output shared BO handle
+ * @addr1: Virtual address in VM1
+ * @addr2: Virtual address in VM2
+ * @size: Size of the BO
+ * @use_scratch: Whether to use scratch page flag for VMs
+ *
+ * Helper to create two VMs and bind one shared BO in both VMs.
+ * Returns mapped pointer to the BO.
+ */
+static void *purgeable_setup_two_vms_shared_bo(int fd, uint32_t *vm1, uint32_t *vm2,

tests/intel/xe_exec_system_allocator.c +1 -0
+						uint32_t *bo,

uint64_t addr1, uint64_t addr2,

tests/intel/xe_exec_system_allocator.c +1 -0
+						size_t size, bool

use_scratch)

tests/intel/xe_exec_system_allocator.c +11 -0
+{
+	struct drm_xe_sync sync = {
+		.type = DRM_XE_SYNC_TYPE_USER_FENCE,
+		.flags = DRM_XE_SYNC_FLAG_SIGNAL,
+		.timeline_value = 1,
+	};
+	uint64_t sync_val = 0;
+	void *map;
+
+	/* Create two VMs */
+	*vm1 = xe_vm_create(fd, use_scratch ?

DRM_XE_VM_CREATE_FLAG_SCRATCH_PAGE : 0, 0);

tests/intel/xe_exec_system_allocator.c +1 -0
+	*vm2 = xe_vm_create(fd, use_scratch ?

DRM_XE_VM_CREATE_FLAG_SCRATCH_PAGE : 0, 0);

tests/intel/xe_exec_system_allocator.c +4 -0
+
+	/* Create shared BO */
+	*bo = xe_bo_create(fd, 0, size, vram_if_possible(fd, 0),
+			  

DRM_XE_GEM_CREATE_FLAG_NEEDS_VISIBLE_VRAM);

tests/intel/xe_exec_system_allocator.c +8 -0
+
+	map = xe_bo_map(fd, *bo, size);
+	memset(map, 0xAB, size);
+
+	/* Bind BO in VM1 */
+	sync.addr = to_user_pointer(&sync_val);
+	sync_val = 0;
+	xe_vm_bind_async(fd, *vm1, 0, *bo, 0, addr1, size, &sync,

1);

tests/intel/xe_exec_system_allocator.c +5 -0
+	xe_wait_ufence(fd, &sync_val, 1, 0, NSEC_PER_SEC);
+
+	/* Bind BO in VM2 */
+	sync_val = 0;
+	xe_vm_bind_async(fd, *vm2, 0, *bo, 0, addr2, size, &sync,

1);

tests/intel/xe_exec_system_allocator.c +8 -0
+	xe_wait_ufence(fd, &sync_val, 1, 0, NSEC_PER_SEC);
+
+	return map;
+}
+
+/**
+ * SUBTEST: madvise-purgeable-dontneed-before-mmap
+ * Description: Test marking memory as DONTNEED before mmap access

in system allocator
+ * Test category: functionality test
+ */
+static void test_dontneed_before_mmap_madvise(int fd, struct drm_xe_engine_class_instance *hwe)

tests/intel/xe_exec_system_allocator.c +7 -0
+{
+	uint32_t bo, vm;
+	uint64_t addr = PURGEABLE_ADDR;
+	size_t bo_size = PURGEABLE_BO_SIZE;
+	void *map;
+
+	purgeable_setup_simple_bo(fd, &vm, &bo, addr, bo_size,

false);

tests/intel/xe_exec_system_allocator.c +1 -0
+	if (!purgeable_mark_and_verify_purged(fd, vm, addr,

bo_size))

tests/intel/xe_exec_system_allocator.c +1 -0
+		igt_skip("Unable to induce purge on this

platform/config");

tests/intel/xe_exec_system_allocator.c +3 -0
+
+	/* Try to mmap - should fail on purged BO */
+	map = __gem_mmap__device_coherent(fd, bo, 0, bo_size,

PROT_READ | PROT_WRITE);

tests/intel/xe_exec_system_allocator.c +3 -0
+	igt_assert_f(map == NULL, "mmap should fail on purged BO");
+	igt_assert_f(errno == EINVAL || errno == EFAULT,
+		     "Expected EINVAL or EFAULT, got errno=%d\n",

errno);

tests/intel/xe_exec_system_allocator.c +8 -0
+
+	gem_close(fd, bo);
+	xe_vm_destroy(fd, vm);
+}
+
+/**
+ * SUBTEST: madvise-purgeable-dontneed-after-mmap
+ * Description: Test marking memory as DONTNEED after mmap in system

allocator
+ * Test category: functionality test
+ */
+static void test_dontneed_after_mmap_madvise(int fd, struct drm_xe_engine_class_instance *hwe)

tests/intel/xe_exec_system_allocator.c +7 -0
+{
+	uint32_t bo, vm;
+	uint64_t addr = PURGEABLE_ADDR;
+	size_t bo_size = PURGEABLE_BO_SIZE;
+	void *map;
+
+	purgeable_setup_simple_bo(fd, &vm, &bo, addr, bo_size,

true);

tests/intel/xe_exec_system_allocator.c +5 -0
+
+	map = xe_bo_map(fd, bo, bo_size);
+	memset(map, 0xAB, bo_size);
+
+	if (!purgeable_mark_and_verify_purged(fd, vm, addr,

bo_size))

tests/intel/xe_exec_system_allocator.c +1 -0
+		igt_skip("Unable to induce purge on this

platform/config");

tests/intel/xe_exec_system_allocator.c +8 -0
+
+	/* Access purged mapping - should trigger SIGBUS/SIGSEGV */
+	{
+		sighandler_t old_sigsegv, old_sigbus;
+		char *ptr = (char *)map;
+		int sig;
+
+		old_sigsegv = signal(SIGSEGV,

(__sighandler_t)sigtrap);

tests/intel/xe_exec_system_allocator.c +1 -0
+		old_sigbus = signal(SIGBUS,

(__sighandler_t)sigtrap);

tests/intel/xe_exec_system_allocator.c +4 -0
+
+		sig = sigsetjmp(jmp, SIGBUS | SIGSEGV);
+		if (sig == SIGBUS || sig == SIGSEGV) {
+			/* Expected - purged mapping access failed

*/

tests/intel/xe_exec_system_allocator.c +3 -0
+		} else if (sig == 0) {
+			*ptr = 0;
+			igt_assert_f(false, "Access to purged

mapping should trigger signal\n");

tests/intel/xe_exec_system_allocator.c +2 -0
+		} else {
+			igt_assert_f(false, "unexpected signal

%d\n", sig);

tests/intel/xe_exec_system_allocator.c +14 -0
+		}
+
+		signal(SIGBUS, old_sigbus);
+		signal(SIGSEGV, old_sigsegv);
+	}
+
+	munmap(map, bo_size);
+	gem_close(fd, bo);
+	xe_vm_destroy(fd, vm);
+}
+
+/**
+ * SUBTEST: madvise-purgeable-dontneed-before-exec
+ * Description: Test marking memory as DONTNEED before GPU exec in

system allocator
+ * Test category: functionality test
+ */
+static void test_dontneed_before_exec_madvise(int fd, struct drm_xe_engine_class_instance *hwe)

tests/intel/xe_exec_system_allocator.c +21 -0
+{
+	uint32_t vm, exec_queue, bo, batch_bo, bind_engine;
+	uint64_t data_addr = 0x1a0000;
+	uint64_t batch_addr = 0x2a0000;
+	size_t data_size = 4096;
+	size_t batch_size = 4096;
+	struct drm_xe_sync sync[1] = {
+		{ .type = DRM_XE_SYNC_TYPE_USER_FENCE,
+		  .flags = DRM_XE_SYNC_FLAG_SIGNAL,
+		  .timeline_value = 0xbeef },
+	};
+	struct drm_xe_exec exec = {
+		.num_batch_buffer = 1,
+		.num_syncs = 1,
+		.syncs = to_user_pointer(sync),
+	};
+	uint32_t *data, *batch;
+	uint64_t vm_sync = 0;
+	int b, ret;
+
+	purgeable_setup_batch_and_data(fd, &vm, &bind_engine,

&batch_bo, &bo,

tests/intel/xe_exec_system_allocator.c +1 -0
+					&batch, &data, batch_addr,

data_addr,

tests/intel/xe_exec_system_allocator.c +11 -0
+					batch_size, data_size);
+
+	/* Prepare batch */
+	b = 0;
+	batch[b++] = MI_STORE_DWORD_IMM_GEN4;
+	batch[b++] = data_addr;
+	batch[b++] = data_addr >> 32;
+	batch[b++] = PURGEABLE_DEAD_PATTERN;
+	batch[b++] = MI_BATCH_BUFFER_END;
+
+	igt_assert(purgeable_mark_and_verify_purged(fd, vm,

data_addr, data_size));

tests/intel/xe_exec_system_allocator.c +14 -0
+
+	/* Try to execute - should fail or cause GPU fault */
+	exec_queue = xe_exec_queue_create(fd, vm, hwe, 0);
+	exec.exec_queue_id = exec_queue;
+	exec.address = batch_addr;
+
+	vm_sync = 0;
+	sync[0].addr = to_user_pointer(&vm_sync);
+
+	ret = __xe_exec(fd, &exec);
+	if (ret == 0) {
+		int64_t timeout = NSEC_PER_SEC;
+
+		__xe_wait_ufence(fd, &vm_sync, 0xbeef, exec_queue,

&timeout);

tests/intel/xe_exec_system_allocator.c +1 -0
+		/* Wait may succeed (NULL rebind) or fail (purged) -

both acceptable */

tests/intel/xe_exec_system_allocator.c +14 -0
+	}
+
+	munmap(data, data_size);
+	munmap(batch, batch_size);
+	gem_close(fd, bo);
+	gem_close(fd, batch_bo);
+	xe_exec_queue_destroy(fd, bind_engine);
+	xe_exec_queue_destroy(fd, exec_queue);
+	xe_vm_destroy(fd, vm);
+}
+
+/**
+ * SUBTEST: madvise-purgeable-dontneed-after-exec
+ * Description: Test marking memory as DONTNEED after successful GPU

exec
+ * Test category: functionality test
+ */
+static void test_dontneed_after_exec_madvise(int fd, struct drm_xe_engine_class_instance *hwe)

tests/intel/xe_exec_system_allocator.c +23 -0
+{
+	uint32_t vm, exec_queue, bo, batch_bo, bind_engine;
+	uint64_t data_addr = 0x1a0000;
+	uint64_t batch_addr = 0x2a0000;
+	size_t data_size = 4096;
+	size_t batch_size = 4096;
+	struct drm_xe_sync sync[2] = {
+		{ .type = DRM_XE_SYNC_TYPE_USER_FENCE,
+		  .flags = DRM_XE_SYNC_FLAG_SIGNAL,
+		  .timeline_value = 0xbeef },
+		{ .type = DRM_XE_SYNC_TYPE_SYNCOBJ,
+		  .flags = DRM_XE_SYNC_FLAG_SIGNAL },
+	};
+	struct drm_xe_exec exec = {
+		.num_batch_buffer = 1,
+		.num_syncs = 2,
+		.syncs = to_user_pointer(sync),
+	};
+	uint32_t *data, *batch;
+	uint32_t syncobj;
+	int b, ret;
+
+	purgeable_setup_batch_and_data(fd, &vm, &bind_engine,

&batch_bo, &bo,

tests/intel/xe_exec_system_allocator.c +1 -0
+					&batch, &data, batch_addr,

data_addr,

tests/intel/xe_exec_system_allocator.c +26 -0
+					batch_size, data_size);
+	memset(data, 0, data_size);
+
+	syncobj = syncobj_create(fd, 0);
+
+	/* Prepare batch to write to data BO */
+	b = 0;
+	batch[b++] = MI_STORE_DWORD_IMM_GEN4;
+	batch[b++] = data_addr;
+	batch[b++] = data_addr >> 32;
+	batch[b++] = 0xfeed0001;
+	batch[b++] = MI_BATCH_BUFFER_END;
+
+	exec_queue = xe_exec_queue_create(fd, vm, hwe, 0);
+	exec.exec_queue_id = exec_queue;
+	exec.address = batch_addr;
+
+	/* Use only syncobj for exec (not USER_FENCE) */
+	sync[1].handle = syncobj;
+	exec.num_syncs = 1;
+	exec.syncs = to_user_pointer(&sync[1]);
+
+	ret = __xe_exec(fd, &exec);
+	igt_assert_eq(ret, 0);
+
+	igt_assert(syncobj_wait(fd, &syncobj, 1, INT64_MAX, 0,

NULL));

tests/intel/xe_exec_system_allocator.c +5 -0
+	munmap(data, data_size);
+	data = xe_bo_map(fd, bo, data_size);
+	igt_assert_eq(data[0], 0xfeed0001);
+
+	igt_assert(purgeable_mark_and_verify_purged(fd, vm,

data_addr, data_size));

tests/intel/xe_exec_system_allocator.c +12 -0
+
+	/* Prepare second batch (different value) */
+	b = 0;
+	batch[b++] = MI_STORE_DWORD_IMM_GEN4;
+	batch[b++] = data_addr;
+	batch[b++] = data_addr >> 32;
+	batch[b++] = 0xfeed0002;
+	batch[b++] = MI_BATCH_BUFFER_END;
+
+	ret = __xe_exec(fd, &exec);
+	if (ret == 0) {
+		/* Exec succeeded, but wait may fail on purged BO

(both behaviors valid) */

tests/intel/xe_exec_system_allocator.c +16 -0
+		syncobj_wait(fd, &syncobj, 1, INT64_MAX, 0, NULL);
+	}
+
+	munmap(data, data_size);
+	munmap(batch, batch_size);
+	gem_close(fd, bo);
+	gem_close(fd, batch_bo);
+	syncobj_destroy(fd, syncobj);
+	xe_exec_queue_destroy(fd, bind_engine);
+	xe_exec_queue_destroy(fd, exec_queue);
+	xe_vm_destroy(fd, vm);
+}
+
+/**
+ * SUBTEST: madvise-purgeable-per-vma-tracking
+ * Description: Test per-VMA purgeable state tracking with multiple

VMs
+ * Test category: functionality test
+ */
+static void test_per_vma_tracking_madvise(int fd, struct drm_xe_engine_class_instance *hwe)

tests/intel/xe_exec_system_allocator.c +10 -0
+{
+	uint32_t bo, vm1, vm2;
+	uint64_t addr1 = PURGEABLE_ADDR;
+	uint64_t addr2 = PURGEABLE_ADDR2;
+	size_t bo_size = PURGEABLE_BO_SIZE;
+	uint32_t retained;
+	void *map;
+
+	map = purgeable_setup_two_vms_shared_bo(fd, &vm1, &vm2, &bo,
+							addr1,

addr2, bo_size, false);

tests/intel/xe_exec_system_allocator.c +4 -0
+
+	/* Mark VMA1 as DONTNEED */
+	retained = xe_vm_madvise_purgeable(fd, vm1, addr1, bo_size,
+					  

DRM_XE_VMA_PURGEABLE_STATE_DONTNEED);

tests/intel/xe_exec_system_allocator.c +5 -0
+	igt_assert_eq(retained, 1);
+
+	/* Verify BO NOT purgeable (VMA2 still WILLNEED) */
+	retained = xe_vm_madvise_purgeable(fd, vm1, addr1, bo_size,
+					  

DRM_XE_VMA_PURGEABLE_STATE_WILLNEED);

tests/intel/xe_exec_system_allocator.c +5 -0
+	igt_assert_eq(retained, 1);
+
+	/* Mark both VMAs as DONTNEED */
+	retained = xe_vm_madvise_purgeable(fd, vm1, addr1, bo_size,
+					  

DRM_XE_VMA_PURGEABLE_STATE_DONTNEED);

tests/intel/xe_exec_system_allocator.c +4 -0
+	igt_assert_eq(retained, 1);
+
+	retained = xe_vm_madvise_purgeable(fd, vm2, addr2, bo_size,
+					  

DRM_XE_VMA_PURGEABLE_STATE_DONTNEED);

tests/intel/xe_exec_system_allocator.c +7 -0
+	igt_assert_eq(retained, 1);
+
+	/* Trigger pressure and verify BO was purged */
+	trigger_memory_pressure(fd, vm1);
+
+	retained = xe_vm_madvise_purgeable(fd, vm1, addr1, bo_size,
+					  

DRM_XE_VMA_PURGEABLE_STATE_WILLNEED);

tests/intel/xe_exec_system_allocator.c +11 -0
+	igt_assert_eq(retained, 0);
+
+	munmap(map, bo_size);
+	gem_close(fd, bo);
+	xe_vm_destroy(fd, vm1);
+	xe_vm_destroy(fd, vm2);
+}
+
+/**
+ * SUBTEST: madvise-purgeable-per-vma-protection
+ * Description: Test per-VMA protection from purging with GPU

workload
+ * Test category: functionality test
+ */
+static void test_per_vma_protection_madvise(int fd, struct drm_xe_engine_class_instance *hwe)

tests/intel/xe_exec_system_allocator.c +26 -0
+{
+	uint32_t vm1, vm2, exec_queue, bo, batch_bo, bind_engine;
+	uint64_t data_addr1 = PURGEABLE_ADDR;
+	uint64_t data_addr2 = PURGEABLE_ADDR2;
+	uint64_t batch_addr = PURGEABLE_BATCH_ADDR;
+	size_t data_size = PURGEABLE_BO_SIZE;
+	size_t batch_size = PURGEABLE_BO_SIZE;
+	struct drm_xe_sync sync[2] = {
+		{ .type = DRM_XE_SYNC_TYPE_USER_FENCE,
+		  .flags = DRM_XE_SYNC_FLAG_SIGNAL,
+		  .timeline_value = PURGEABLE_FENCE_VAL },
+		{ .type = DRM_XE_SYNC_TYPE_SYNCOBJ,
+		  .flags = DRM_XE_SYNC_FLAG_SIGNAL },
+	};
+	struct drm_xe_exec exec = {
+		.num_batch_buffer = 1,
+		.num_syncs = 1,
+		.syncs = to_user_pointer(&sync[1]),
+	};
+	uint32_t *data, *batch;
+	uint64_t vm_sync = 0;
+	uint32_t retained, syncobj;
+	int b, ret;
+
+	/* Create two VMs and bind shared data BO */
+	data = purgeable_setup_two_vms_shared_bo(fd, &vm1, &vm2,

&bo,

tests/intel/xe_exec_system_allocator.c +1 -0
+							 data_addr1,

data_addr2, data_size, true);

tests/intel/xe_exec_system_allocator.c +5 -0
+	memset(data, 0, data_size);
+	bind_engine = xe_bind_exec_queue_create(fd, vm2, 0);
+
+	/* Create and bind batch BO in VM2 */
+	batch_bo = xe_bo_create(fd, vm2, batch_size,

vram_if_possible(fd, 0),

tests/intel/xe_exec_system_allocator.c +1 -0
+				DRM_XE_GEM_CREATE_FLAG_NEEDS_VISIBLE

_VRAM);

tests/intel/xe_exec_system_allocator.c +5 -0
+	batch = xe_bo_map(fd, batch_bo, batch_size);
+
+	sync[0].addr = to_user_pointer(&vm_sync);
+	vm_sync = 0;
+	xe_vm_bind_async(fd, vm2, bind_engine, batch_bo, 0,

batch_addr, batch_size, sync, 1);

tests/intel/xe_exec_system_allocator.c +1 -0
+	xe_wait_ufence(fd, &vm_sync, PURGEABLE_FENCE_VAL, 0,

NSEC_PER_SEC);

tests/intel/xe_exec_system_allocator.c +3 -0
+
+	/* Mark VMA1 as DONTNEED, VMA2 stays WILLNEED */
+	retained = xe_vm_madvise_purgeable(fd, vm1, data_addr1,

data_size,

tests/intel/xe_exec_system_allocator.c +1 -0
+					  

DRM_XE_VMA_PURGEABLE_STATE_DONTNEED);

tests/intel/xe_exec_system_allocator.c +6 -0
+	igt_assert_eq(retained, 1);
+
+	/* Trigger pressure - BO should survive (VMA2 protects) */
+	trigger_memory_pressure(fd, vm1);
+
+	retained = xe_vm_madvise_purgeable(fd, vm2, data_addr2,

data_size,

tests/intel/xe_exec_system_allocator.c +1 -0
+					  

DRM_XE_VMA_PURGEABLE_STATE_WILLNEED);

tests/intel/xe_exec_system_allocator.c +19 -0
+	igt_assert_eq(retained, 1);
+
+	/* GPU workload - should succeed */
+	b = 0;
+	batch[b++] = MI_STORE_DWORD_IMM_GEN4;
+	batch[b++] = data_addr2;
+	batch[b++] = data_addr2 >> 32;
+	batch[b++] = PURGEABLE_TEST_PATTERN;
+	batch[b++] = MI_BATCH_BUFFER_END;
+
+	syncobj = syncobj_create(fd, 0);
+	sync[1].handle = syncobj;
+	exec_queue = xe_exec_queue_create(fd, vm2, hwe, 0);
+	exec.exec_queue_id = exec_queue;
+	exec.address = batch_addr;
+
+	ret = __xe_exec(fd, &exec);
+	igt_assert_eq(ret, 0);
+	igt_assert(syncobj_wait(fd, &syncobj, 1, INT64_MAX, 0,

NULL));

tests/intel/xe_exec_system_allocator.c +7 -0
+
+	munmap(data, data_size);
+	data = xe_bo_map(fd, bo, data_size);
+	igt_assert_eq(data[0], PURGEABLE_TEST_PATTERN);
+
+	/* Mark both VMAs DONTNEED */
+	retained = xe_vm_madvise_purgeable(fd, vm2, data_addr2,

data_size,

tests/intel/xe_exec_system_allocator.c +1 -0
+					  

DRM_XE_VMA_PURGEABLE_STATE_DONTNEED);

tests/intel/xe_exec_system_allocator.c +6 -0
+	igt_assert_eq(retained, 1);
+
+	/* Trigger pressure - BO should be purged */
+	trigger_memory_pressure(fd, vm1);
+
+	retained = xe_vm_madvise_purgeable(fd, vm2, data_addr2,

data_size,

tests/intel/xe_exec_system_allocator.c +1 -0
+					  

DRM_XE_VMA_PURGEABLE_STATE_WILLNEED);

tests/intel/xe_exec_system_allocator.c +7 -0
+	igt_assert_eq(retained, 0);
+
+	/* GPU workload - should fail or succeed with NULL rebind */
+	batch[3] = PURGEABLE_DEAD_PATTERN;
+
+	ret = __xe_exec(fd, &exec);
+	/* With SCRATCH_PAGE, kernel may allow exec with NULL

rebind.

tests/intel/xe_exec_system_allocator.c +1 -0
+	 * Without it, exec should fail with -EIO/-EFAULT or wait

should timeout.

tests/intel/xe_exec_system_allocator.c +14 -0
+	 * Both behaviors are valid depending on kernel support.
+	 */
+
+	munmap(data, data_size);
+	munmap(batch, batch_size);
+	gem_close(fd, bo);
+	gem_close(fd, batch_bo);
+	syncobj_destroy(fd, syncobj);
+	xe_exec_queue_destroy(fd, bind_engine);
+	xe_exec_queue_destroy(fd, exec_queue);
+	xe_vm_destroy(fd, vm1);
+	xe_vm_destroy(fd, vm2);
+}
+

 struct section {
  const char *name;
  unsigned long long flags;

tests/intel/xe_exec_system_allocator.c +0 -0
@@ -2649,6 +3251,42 @@ int igt_main()
  			test_compute(fd, SZ_2M, s->flags);
  	}

tests/intel/xe_exec_system_allocator.c +36 -0
+	igt_subtest("madvise-purgeable-dontneed-before-mmap")
+		xe_for_each_engine(fd, hwe) {
+			test_dontneed_before_mmap_madvise(fd, hwe);
+			break;
+		}
+
+	igt_subtest("madvise-purgeable-dontneed-after-mmap")
+		xe_for_each_engine(fd, hwe) {
+			test_dontneed_after_mmap_madvise(fd, hwe);
+			break;
+		}
+
+	igt_subtest("madvise-purgeable-dontneed-before-exec")
+		xe_for_each_engine(fd, hwe) {
+			test_dontneed_before_exec_madvise(fd, hwe);
+			break;
+		}
+
+	igt_subtest("madvise-purgeable-dontneed-after-exec")
+		xe_for_each_engine(fd, hwe) {
+			test_dontneed_after_exec_madvise(fd, hwe);
+			break;
+		}
+
+	igt_subtest("madvise-purgeable-per-vma-tracking")
+		xe_for_each_engine(fd, hwe) {
+			test_per_vma_tracking_madvise(fd, hwe);
+			break;
+		}
+
+	igt_subtest("madvise-purgeable-per-vma-protection")
+		xe_for_each_engine(fd, hwe) {
+			test_per_vma_protection_madvise(fd, hwe);
+			break;
+		}
+

  igt_fixture() {
  xe_device_put(fd);
  drm_close_driver(fd);

#5 lore raw

Re: [PATCH i-g-t 3/3] tests/intel/xe_exec_system_allocator: Add purgeable memory madvise tests

Quoted 10 lines · Thomas Hellström

Hi, Arvind,

Quoted 2 lines · Arvind Yadav

Add six purgeable memory test cases for system allocator using madvise:

I wonder is xe_exec_system_allocator really the igt we should use for this? Sure, it's possible to bind bos to a SVM VM, but I think that's not really the typical use-case, but rather ordinary VMs used by graphics UMDs.

Quoted 4 lines

xe_exec_system_allocator is already a huge test, primarily intended to test the system allocator functionality rather than bo functionality. Can't we craft a separate igt test app for this that tests the purgeability functionality for various VM types?

Agreed. I'll move these to a new test file tests/intel/xe_madvise.c (following i915's gem_madvise.c pattern which has similar tests) to keep purgeable BO tests separate and focused. This makes more sense than cluttering xe_exec_system_allocator. I Will send v2 with the new structure.

Thanks,
Arvind

Quoted 807 lines

Thanks,
Thomas

Quoted 802 lines

- madvise-purgeable-dontneed-before-mmap: Mark BO as DONTNEED before mmap,
  verify mmap fails on purged memory

- madvise-purgeable-dontneed-after-mmap: Mark BO as DONTNEED after mmap,
  verify SIGBUS/SIGSEGV on accessing purged mapping

- madvise-purgeable-dontneed-before-exec: Mark BO as DONTNEED before GPU
  execution, verify GPU behavior on purged memory with SCRATCH_PAGE
VMs

- madvise-purgeable-dontneed-after-exec: Mark BO as DONTNEED after GPU
  execution, verify previously-used memory becomes inaccessible

- madvise-purgeable-per-vma-tracking: One BO mapped in two VMs becomes
  purgeable only when BOTH VMAs are marked DONTNEED

- madvise-purgeable-per-vma-protection: One VMA marked DONTNEED allows
  GPU execution on other VMA; both DONTNEED makes BO purgeable

Tests use xe_vm_madvise_purgeable() for WILLNEED/DONTNEED state management
and trigger_memory_pressure() to simulate OOM conditions forcing kernel to
reclaim purgeable memory.

Cc Matthew Brost <[email protected]>
Cc Thomas Hellström <[email protected]>
Cc Himal Prasad Ghimiray <[email protected]>
---
  tests/intel/xe_exec_system_allocator.c | 638
+++++++++++++++++++++++++
  1 file changed, 638 insertions(+)
tests/intel/xe_exec_system_allocator.c +11 -0
index 8af66d76e..338037a48 100644
@@ -32,6 +32,15 @@
  #define QUARTER_SEC		(NSEC_PER_SEC / 4)
  #define FIVE_SEC		(5LL * NSEC_PER_SEC)
 
+/* Purgeable test constants */
+#define PURGEABLE_ADDR		0x1a0000
+#define PURGEABLE_ADDR2		0x2b0000
+#define PURGEABLE_BATCH_ADDR	0x3c0000
+#define PURGEABLE_BO_SIZE	4096
+#define PURGEABLE_FENCE_VAL	0xbeef
+#define PURGEABLE_TEST_PATTERN	0xc0ffee
+#define PURGEABLE_DEAD_PATTERN	0xdead
+
  struct test_exec_data {
  	uint32_t batch[32];
  	uint64_t pad;
@@ -2245,6 +2254,599 @@ test_compute(int fd, size_t size, unsigned
 int flags)
  	xe_vm_destroy(fd, vm);
  }
 
+/**
+ * trigger_memory_pressure - Trigger memory pressure for purgeable

tests
+ * @fd: DRM file descriptor
+ * @vm: VM handle
+ *
+ * Creates temporary BOs exceeding VRAM size (VRAM + 64MB) to trigger memory
+ * pressure, forcing kernel to reclaim purgeable BOs in system allocator.
+ */

tests/intel/xe_exec_system_allocator.c +18 -0
+static void trigger_memory_pressure(int fd, uint32_t vm)
+{
+	uint64_t vram_size;
+	const uint64_t chunk = 8ull << 20; /* 8 MiB */
+	int max_objs, n = 0;
+	uint32_t *handles;
+	uint64_t total;
+	void *p;
+	uint32_t bo2;
+
+	vram_size = xe_visible_vram_size(fd, 0);
+	max_objs = vram_size / chunk + 64;
+	handles = calloc(max_objs, sizeof(*handles));
+	igt_assert(handles);
+
+	total = 0;
+	while (total < vram_size + (64 << 20) && n < max_objs) {
+		bo2 = xe_bo_create(fd, vm, chunk,

vram_if_possible(fd, 0),

tests/intel/xe_exec_system_allocator.c +1 -0
+				

DRM_XE_GEM_CREATE_FLAG_NEEDS_VISIBLE_VRAM);

tests/intel/xe_exec_system_allocator.c +22 -0
+		handles[n++] = bo2;
+		total += chunk;
+		p = xe_bo_map(fd, bo2, chunk);
+		memset(p, 0xCD, 4096);
+		munmap(p, chunk);
+	}
+
+	for (int i = 0; i < n; i++)
+		gem_close(fd, handles[i]);
+
+	free(handles);
+}
+
+static jmp_buf jmp;
+
+__noreturn static void sigtrap(int sig)
+{
+	siglongjmp(jmp, sig);
+}
+
+/**
+ * purgeable_mark_and_verify_purged - Mark BO as DONTNEED and verify

purge
+ * @fd: DRM file descriptor
+ * @vm: VM handle
+ * @addr: Virtual address of the BO
+ * @size: Size of the BO
+ *
+ * Marks BO as DONTNEED, triggers memory pressure, and verifies purge.
+ * Returns: true if BO was successfully purged, false otherwise
+ */
+static bool purgeable_mark_and_verify_purged(int fd, uint32_t vm, uint64_t addr, size_t size)

tests/intel/xe_exec_system_allocator.c +6 -0
+{
+	uint32_t retained;
+
+	/* Mark as DONTNEED */
+	retained = xe_vm_madvise_purgeable(fd, vm, addr, size,
+					

DRM_XE_VMA_PURGEABLE_STATE_DONTNEED);

tests/intel/xe_exec_system_allocator.c +9 -0
+	if (retained != 1)
+		return false;
+
+	/* Trigger memory pressure */
+	trigger_memory_pressure(fd, vm);
+
+	/* Verify purged */
+	retained = xe_vm_madvise_purgeable(fd, vm, addr, size,
+					

DRM_XE_VMA_PURGEABLE_STATE_WILLNEED);

tests/intel/xe_exec_system_allocator.c +15 -0
+	return retained == 0;
+}
+
+/**
+ * purgeable_setup_simple_bo - Setup VM and bind a single BO
+ * @fd: DRM file descriptor
+ * @vm: Output VM handle
+ * @bo: Output BO handle
+ * @addr: Virtual address to bind at
+ * @size: Size of the BO
+ * @use_scratch: Whether to use scratch page flag
+ *
+ * Helper to create VM, BO, and bind it at the specified address.
+ */
+static void purgeable_setup_simple_bo(int fd, uint32_t *vm, uint32_t

*bo,

tests/intel/xe_exec_system_allocator.c +1 -0
+				      uint64_t addr, size_t size,

bool use_scratch)

tests/intel/xe_exec_system_allocator.c +9 -0
+{
+	struct drm_xe_sync sync = {
+		.type = DRM_XE_SYNC_TYPE_USER_FENCE,
+		.flags = DRM_XE_SYNC_FLAG_SIGNAL,
+		.timeline_value = 1,
+	};
+	uint64_t sync_val = 0;
+
+	*vm = xe_vm_create(fd, use_scratch ?

DRM_XE_VM_CREATE_FLAG_SCRATCH_PAGE : 0, 0);

tests/intel/xe_exec_system_allocator.c +1 -0
+	*bo = xe_bo_create(fd, *vm, size, vram_if_possible(fd, 0),

0);

tests/intel/xe_exec_system_allocator.c +8 -0
+
+	sync.addr = to_user_pointer(&sync_val);
+	xe_vm_bind_async(fd, *vm, 0, *bo, 0, addr, size, &sync, 1);
+	xe_wait_ufence(fd, &sync_val, 1, 0, NSEC_PER_SEC);
+}
+
+/**
+ * purgeable_setup_batch_and_data - Setup VM with batch and data BOs

for GPU exec
+ * @fd: DRM file descriptor
+ * @vm: Output VM handle
+ * @bind_engine: Output bind engine handle
+ * @batch_bo: Output batch BO handle
+ * @data_bo: Output data BO handle
+ * @batch: Output batch buffer pointer
+ * @data: Output data buffer pointer
+ * @batch_addr: Batch virtual address
+ * @data_addr: Data virtual address
+ * @batch_size: Batch buffer size
+ * @data_size: Data buffer size
+ *
+ * Helper to create VM, bind engine, batch and data BOs, and bind them.
+ */
+static void purgeable_setup_batch_and_data(int fd, uint32_t *vm, uint32_t *bind_engine,

tests/intel/xe_exec_system_allocator.c +1 -0
+					    uint32_t *batch_bo,

uint32_t *data_bo,

tests/intel/xe_exec_system_allocator.c +1 -0
+					    uint32_t **batch,

uint32_t **data,

tests/intel/xe_exec_system_allocator.c +1 -0
+					    uint64_t batch_addr,

uint64_t data_addr,

tests/intel/xe_exec_system_allocator.c +1 -0
+					    size_t batch_size,

size_t data_size)

tests/intel/xe_exec_system_allocator.c +9 -0
+{
+	struct drm_xe_sync sync = {
+		.type = DRM_XE_SYNC_TYPE_USER_FENCE,
+		.flags = DRM_XE_SYNC_FLAG_SIGNAL,
+		.timeline_value = PURGEABLE_FENCE_VAL,
+	};
+	uint64_t vm_sync = 0;
+
+	*vm = xe_vm_create(fd, DRM_XE_VM_CREATE_FLAG_SCRATCH_PAGE,

0);

tests/intel/xe_exec_system_allocator.c +4 -0
+	*bind_engine = xe_bind_exec_queue_create(fd, *vm, 0);
+
+	/* Create and bind batch BO */
+	*batch_bo = xe_bo_create(fd, *vm, batch_size,

vram_if_possible(fd, 0),

tests/intel/xe_exec_system_allocator.c +1 -0
+				

DRM_XE_GEM_CREATE_FLAG_NEEDS_VISIBLE_VRAM);

tests/intel/xe_exec_system_allocator.c +4 -0
+	*batch = xe_bo_map(fd, *batch_bo, batch_size);
+
+	sync.addr = to_user_pointer(&vm_sync);
+	xe_vm_bind_async(fd, *vm, *bind_engine, *batch_bo, 0,

batch_addr, batch_size, &sync, 1);

tests/intel/xe_exec_system_allocator.c +1 -0
+	xe_wait_ufence(fd, &vm_sync, PURGEABLE_FENCE_VAL, 0,

NSEC_PER_SEC);

tests/intel/xe_exec_system_allocator.c +3 -0
+
+	/* Create and bind data BO */
+	*data_bo = xe_bo_create(fd, *vm, data_size,

vram_if_possible(fd, 0),

tests/intel/xe_exec_system_allocator.c +1 -0
+				DRM_XE_GEM_CREATE_FLAG_NEEDS_VISIBLE

_VRAM);

tests/intel/xe_exec_system_allocator.c +4 -0
+	*data = xe_bo_map(fd, *data_bo, data_size);
+
+	vm_sync = 0;
+	xe_vm_bind_async(fd, *vm, *bind_engine, *data_bo, 0,

data_addr, data_size, &sync, 1);

tests/intel/xe_exec_system_allocator.c +1 -0
+	xe_wait_ufence(fd, &vm_sync, PURGEABLE_FENCE_VAL, 0,

NSEC_PER_SEC);

tests/intel/xe_exec_system_allocator.c +4 -0
+}
+
+/**
+ * purgeable_setup_two_vms_shared_bo - Setup two VMs with one shared

BO
+ * @fd: DRM file descriptor
+ * @vm1: Output first VM handle
+ * @vm2: Output second VM handle
+ * @bo: Output shared BO handle
+ * @addr1: Virtual address in VM1
+ * @addr2: Virtual address in VM2
+ * @size: Size of the BO
+ * @use_scratch: Whether to use scratch page flag for VMs
+ *
+ * Helper to create two VMs and bind one shared BO in both VMs.
+ * Returns mapped pointer to the BO.
+ */
+static void *purgeable_setup_two_vms_shared_bo(int fd, uint32_t *vm1, uint32_t *vm2,

tests/intel/xe_exec_system_allocator.c +1 -0
+						uint32_t *bo,

uint64_t addr1, uint64_t addr2,

tests/intel/xe_exec_system_allocator.c +1 -0
+						size_t size, bool

use_scratch)

tests/intel/xe_exec_system_allocator.c +11 -0
+{
+	struct drm_xe_sync sync = {
+		.type = DRM_XE_SYNC_TYPE_USER_FENCE,
+		.flags = DRM_XE_SYNC_FLAG_SIGNAL,
+		.timeline_value = 1,
+	};
+	uint64_t sync_val = 0;
+	void *map;
+
+	/* Create two VMs */
+	*vm1 = xe_vm_create(fd, use_scratch ?

DRM_XE_VM_CREATE_FLAG_SCRATCH_PAGE : 0, 0);

tests/intel/xe_exec_system_allocator.c +1 -0
+	*vm2 = xe_vm_create(fd, use_scratch ?

DRM_XE_VM_CREATE_FLAG_SCRATCH_PAGE : 0, 0);

tests/intel/xe_exec_system_allocator.c +4 -0
+
+	/* Create shared BO */
+	*bo = xe_bo_create(fd, 0, size, vram_if_possible(fd, 0),
+			

DRM_XE_GEM_CREATE_FLAG_NEEDS_VISIBLE_VRAM);

tests/intel/xe_exec_system_allocator.c +8 -0
+
+	map = xe_bo_map(fd, *bo, size);
+	memset(map, 0xAB, size);
+
+	/* Bind BO in VM1 */
+	sync.addr = to_user_pointer(&sync_val);
+	sync_val = 0;
+	xe_vm_bind_async(fd, *vm1, 0, *bo, 0, addr1, size, &sync,

1);

tests/intel/xe_exec_system_allocator.c +5 -0
+	xe_wait_ufence(fd, &sync_val, 1, 0, NSEC_PER_SEC);
+
+	/* Bind BO in VM2 */
+	sync_val = 0;
+	xe_vm_bind_async(fd, *vm2, 0, *bo, 0, addr2, size, &sync,

1);

tests/intel/xe_exec_system_allocator.c +8 -0
+	xe_wait_ufence(fd, &sync_val, 1, 0, NSEC_PER_SEC);
+
+	return map;
+}
+
+/**
+ * SUBTEST: madvise-purgeable-dontneed-before-mmap
+ * Description: Test marking memory as DONTNEED before mmap access

in system allocator
+ * Test category: functionality test
+ */
+static void test_dontneed_before_mmap_madvise(int fd, struct drm_xe_engine_class_instance *hwe)

tests/intel/xe_exec_system_allocator.c +7 -0
+{
+	uint32_t bo, vm;
+	uint64_t addr = PURGEABLE_ADDR;
+	size_t bo_size = PURGEABLE_BO_SIZE;
+	void *map;
+
+	purgeable_setup_simple_bo(fd, &vm, &bo, addr, bo_size,

false);

tests/intel/xe_exec_system_allocator.c +1 -0
+	if (!purgeable_mark_and_verify_purged(fd, vm, addr,

bo_size))

tests/intel/xe_exec_system_allocator.c +1 -0
+		igt_skip("Unable to induce purge on this

platform/config");

tests/intel/xe_exec_system_allocator.c +3 -0
+
+	/* Try to mmap - should fail on purged BO */
+	map = __gem_mmap__device_coherent(fd, bo, 0, bo_size,

PROT_READ | PROT_WRITE);

tests/intel/xe_exec_system_allocator.c +3 -0
+	igt_assert_f(map == NULL, "mmap should fail on purged BO");
+	igt_assert_f(errno == EINVAL || errno == EFAULT,
+		     "Expected EINVAL or EFAULT, got errno=%d\n",

errno);

tests/intel/xe_exec_system_allocator.c +8 -0
+
+	gem_close(fd, bo);
+	xe_vm_destroy(fd, vm);
+}
+
+/**
+ * SUBTEST: madvise-purgeable-dontneed-after-mmap
+ * Description: Test marking memory as DONTNEED after mmap in system

allocator
+ * Test category: functionality test
+ */
+static void test_dontneed_after_mmap_madvise(int fd, struct drm_xe_engine_class_instance *hwe)

tests/intel/xe_exec_system_allocator.c +7 -0
+{
+	uint32_t bo, vm;
+	uint64_t addr = PURGEABLE_ADDR;
+	size_t bo_size = PURGEABLE_BO_SIZE;
+	void *map;
+
+	purgeable_setup_simple_bo(fd, &vm, &bo, addr, bo_size,

true);

tests/intel/xe_exec_system_allocator.c +5 -0
+
+	map = xe_bo_map(fd, bo, bo_size);
+	memset(map, 0xAB, bo_size);
+
+	if (!purgeable_mark_and_verify_purged(fd, vm, addr,

bo_size))

tests/intel/xe_exec_system_allocator.c +1 -0
+		igt_skip("Unable to induce purge on this

platform/config");

tests/intel/xe_exec_system_allocator.c +8 -0
+
+	/* Access purged mapping - should trigger SIGBUS/SIGSEGV */
+	{
+		sighandler_t old_sigsegv, old_sigbus;
+		char *ptr = (char *)map;
+		int sig;
+
+		old_sigsegv = signal(SIGSEGV,

(__sighandler_t)sigtrap);

tests/intel/xe_exec_system_allocator.c +1 -0
+		old_sigbus = signal(SIGBUS,

(__sighandler_t)sigtrap);

tests/intel/xe_exec_system_allocator.c +4 -0
+
+		sig = sigsetjmp(jmp, SIGBUS | SIGSEGV);
+		if (sig == SIGBUS || sig == SIGSEGV) {
+			/* Expected - purged mapping access failed

*/

tests/intel/xe_exec_system_allocator.c +3 -0
+		} else if (sig == 0) {
+			*ptr = 0;
+			igt_assert_f(false, "Access to purged

mapping should trigger signal\n");

tests/intel/xe_exec_system_allocator.c +2 -0
+		} else {
+			igt_assert_f(false, "unexpected signal

%d\n", sig);

tests/intel/xe_exec_system_allocator.c +14 -0
+		}
+
+		signal(SIGBUS, old_sigbus);
+		signal(SIGSEGV, old_sigsegv);
+	}
+
+	munmap(map, bo_size);
+	gem_close(fd, bo);
+	xe_vm_destroy(fd, vm);
+}
+
+/**
+ * SUBTEST: madvise-purgeable-dontneed-before-exec
+ * Description: Test marking memory as DONTNEED before GPU exec in

system allocator
+ * Test category: functionality test
+ */
+static void test_dontneed_before_exec_madvise(int fd, struct drm_xe_engine_class_instance *hwe)

tests/intel/xe_exec_system_allocator.c +21 -0
+{
+	uint32_t vm, exec_queue, bo, batch_bo, bind_engine;
+	uint64_t data_addr = 0x1a0000;
+	uint64_t batch_addr = 0x2a0000;
+	size_t data_size = 4096;
+	size_t batch_size = 4096;
+	struct drm_xe_sync sync[1] = {
+		{ .type = DRM_XE_SYNC_TYPE_USER_FENCE,
+		  .flags = DRM_XE_SYNC_FLAG_SIGNAL,
+		  .timeline_value = 0xbeef },
+	};
+	struct drm_xe_exec exec = {
+		.num_batch_buffer = 1,
+		.num_syncs = 1,
+		.syncs = to_user_pointer(sync),
+	};
+	uint32_t *data, *batch;
+	uint64_t vm_sync = 0;
+	int b, ret;
+
+	purgeable_setup_batch_and_data(fd, &vm, &bind_engine,

&batch_bo, &bo,

tests/intel/xe_exec_system_allocator.c +1 -0
+					&batch, &data, batch_addr,

data_addr,

tests/intel/xe_exec_system_allocator.c +11 -0
+					batch_size, data_size);
+
+	/* Prepare batch */
+	b = 0;
+	batch[b++] = MI_STORE_DWORD_IMM_GEN4;
+	batch[b++] = data_addr;
+	batch[b++] = data_addr >> 32;
+	batch[b++] = PURGEABLE_DEAD_PATTERN;
+	batch[b++] = MI_BATCH_BUFFER_END;
+
+	igt_assert(purgeable_mark_and_verify_purged(fd, vm,

data_addr, data_size));

tests/intel/xe_exec_system_allocator.c +14 -0
+
+	/* Try to execute - should fail or cause GPU fault */
+	exec_queue = xe_exec_queue_create(fd, vm, hwe, 0);
+	exec.exec_queue_id = exec_queue;
+	exec.address = batch_addr;
+
+	vm_sync = 0;
+	sync[0].addr = to_user_pointer(&vm_sync);
+
+	ret = __xe_exec(fd, &exec);
+	if (ret == 0) {
+		int64_t timeout = NSEC_PER_SEC;
+
+		__xe_wait_ufence(fd, &vm_sync, 0xbeef, exec_queue,

&timeout);

tests/intel/xe_exec_system_allocator.c +1 -0
+		/* Wait may succeed (NULL rebind) or fail (purged) -

both acceptable */

tests/intel/xe_exec_system_allocator.c +14 -0
+	}
+
+	munmap(data, data_size);
+	munmap(batch, batch_size);
+	gem_close(fd, bo);
+	gem_close(fd, batch_bo);
+	xe_exec_queue_destroy(fd, bind_engine);
+	xe_exec_queue_destroy(fd, exec_queue);
+	xe_vm_destroy(fd, vm);
+}
+
+/**
+ * SUBTEST: madvise-purgeable-dontneed-after-exec
+ * Description: Test marking memory as DONTNEED after successful GPU

exec
+ * Test category: functionality test
+ */
+static void test_dontneed_after_exec_madvise(int fd, struct drm_xe_engine_class_instance *hwe)

tests/intel/xe_exec_system_allocator.c +23 -0
+{
+	uint32_t vm, exec_queue, bo, batch_bo, bind_engine;
+	uint64_t data_addr = 0x1a0000;
+	uint64_t batch_addr = 0x2a0000;
+	size_t data_size = 4096;
+	size_t batch_size = 4096;
+	struct drm_xe_sync sync[2] = {
+		{ .type = DRM_XE_SYNC_TYPE_USER_FENCE,
+		  .flags = DRM_XE_SYNC_FLAG_SIGNAL,
+		  .timeline_value = 0xbeef },
+		{ .type = DRM_XE_SYNC_TYPE_SYNCOBJ,
+		  .flags = DRM_XE_SYNC_FLAG_SIGNAL },
+	};
+	struct drm_xe_exec exec = {
+		.num_batch_buffer = 1,
+		.num_syncs = 2,
+		.syncs = to_user_pointer(sync),
+	};
+	uint32_t *data, *batch;
+	uint32_t syncobj;
+	int b, ret;
+
+	purgeable_setup_batch_and_data(fd, &vm, &bind_engine,

&batch_bo, &bo,

tests/intel/xe_exec_system_allocator.c +1 -0
+					&batch, &data, batch_addr,

data_addr,

tests/intel/xe_exec_system_allocator.c +26 -0
+					batch_size, data_size);
+	memset(data, 0, data_size);
+
+	syncobj = syncobj_create(fd, 0);
+
+	/* Prepare batch to write to data BO */
+	b = 0;
+	batch[b++] = MI_STORE_DWORD_IMM_GEN4;
+	batch[b++] = data_addr;
+	batch[b++] = data_addr >> 32;
+	batch[b++] = 0xfeed0001;
+	batch[b++] = MI_BATCH_BUFFER_END;
+
+	exec_queue = xe_exec_queue_create(fd, vm, hwe, 0);
+	exec.exec_queue_id = exec_queue;
+	exec.address = batch_addr;
+
+	/* Use only syncobj for exec (not USER_FENCE) */
+	sync[1].handle = syncobj;
+	exec.num_syncs = 1;
+	exec.syncs = to_user_pointer(&sync[1]);
+
+	ret = __xe_exec(fd, &exec);
+	igt_assert_eq(ret, 0);
+
+	igt_assert(syncobj_wait(fd, &syncobj, 1, INT64_MAX, 0,

NULL));

tests/intel/xe_exec_system_allocator.c +5 -0
+	munmap(data, data_size);
+	data = xe_bo_map(fd, bo, data_size);
+	igt_assert_eq(data[0], 0xfeed0001);
+
+	igt_assert(purgeable_mark_and_verify_purged(fd, vm,

data_addr, data_size));

tests/intel/xe_exec_system_allocator.c +12 -0
+
+	/* Prepare second batch (different value) */
+	b = 0;
+	batch[b++] = MI_STORE_DWORD_IMM_GEN4;
+	batch[b++] = data_addr;
+	batch[b++] = data_addr >> 32;
+	batch[b++] = 0xfeed0002;
+	batch[b++] = MI_BATCH_BUFFER_END;
+
+	ret = __xe_exec(fd, &exec);
+	if (ret == 0) {
+		/* Exec succeeded, but wait may fail on purged BO

(both behaviors valid) */

tests/intel/xe_exec_system_allocator.c +16 -0
+		syncobj_wait(fd, &syncobj, 1, INT64_MAX, 0, NULL);
+	}
+
+	munmap(data, data_size);
+	munmap(batch, batch_size);
+	gem_close(fd, bo);
+	gem_close(fd, batch_bo);
+	syncobj_destroy(fd, syncobj);
+	xe_exec_queue_destroy(fd, bind_engine);
+	xe_exec_queue_destroy(fd, exec_queue);
+	xe_vm_destroy(fd, vm);
+}
+
+/**
+ * SUBTEST: madvise-purgeable-per-vma-tracking
+ * Description: Test per-VMA purgeable state tracking with multiple

VMs
+ * Test category: functionality test
+ */
+static void test_per_vma_tracking_madvise(int fd, struct drm_xe_engine_class_instance *hwe)

tests/intel/xe_exec_system_allocator.c +10 -0
+{
+	uint32_t bo, vm1, vm2;
+	uint64_t addr1 = PURGEABLE_ADDR;
+	uint64_t addr2 = PURGEABLE_ADDR2;
+	size_t bo_size = PURGEABLE_BO_SIZE;
+	uint32_t retained;
+	void *map;
+
+	map = purgeable_setup_two_vms_shared_bo(fd, &vm1, &vm2, &bo,
+							addr1,

addr2, bo_size, false);

tests/intel/xe_exec_system_allocator.c +4 -0
+
+	/* Mark VMA1 as DONTNEED */
+	retained = xe_vm_madvise_purgeable(fd, vm1, addr1, bo_size,
+					

DRM_XE_VMA_PURGEABLE_STATE_DONTNEED);

tests/intel/xe_exec_system_allocator.c +5 -0
+	igt_assert_eq(retained, 1);
+
+	/* Verify BO NOT purgeable (VMA2 still WILLNEED) */
+	retained = xe_vm_madvise_purgeable(fd, vm1, addr1, bo_size,
+					

DRM_XE_VMA_PURGEABLE_STATE_WILLNEED);

tests/intel/xe_exec_system_allocator.c +5 -0
+	igt_assert_eq(retained, 1);
+
+	/* Mark both VMAs as DONTNEED */
+	retained = xe_vm_madvise_purgeable(fd, vm1, addr1, bo_size,
+					

DRM_XE_VMA_PURGEABLE_STATE_DONTNEED);

tests/intel/xe_exec_system_allocator.c +4 -0
+	igt_assert_eq(retained, 1);
+
+	retained = xe_vm_madvise_purgeable(fd, vm2, addr2, bo_size,
+					

DRM_XE_VMA_PURGEABLE_STATE_DONTNEED);

tests/intel/xe_exec_system_allocator.c +7 -0
+	igt_assert_eq(retained, 1);
+
+	/* Trigger pressure and verify BO was purged */
+	trigger_memory_pressure(fd, vm1);
+
+	retained = xe_vm_madvise_purgeable(fd, vm1, addr1, bo_size,
+					

DRM_XE_VMA_PURGEABLE_STATE_WILLNEED);

tests/intel/xe_exec_system_allocator.c +11 -0
+	igt_assert_eq(retained, 0);
+
+	munmap(map, bo_size);
+	gem_close(fd, bo);
+	xe_vm_destroy(fd, vm1);
+	xe_vm_destroy(fd, vm2);
+}
+
+/**
+ * SUBTEST: madvise-purgeable-per-vma-protection
+ * Description: Test per-VMA protection from purging with GPU

workload
+ * Test category: functionality test
+ */
+static void test_per_vma_protection_madvise(int fd, struct drm_xe_engine_class_instance *hwe)

tests/intel/xe_exec_system_allocator.c +26 -0
+{
+	uint32_t vm1, vm2, exec_queue, bo, batch_bo, bind_engine;
+	uint64_t data_addr1 = PURGEABLE_ADDR;
+	uint64_t data_addr2 = PURGEABLE_ADDR2;
+	uint64_t batch_addr = PURGEABLE_BATCH_ADDR;
+	size_t data_size = PURGEABLE_BO_SIZE;
+	size_t batch_size = PURGEABLE_BO_SIZE;
+	struct drm_xe_sync sync[2] = {
+		{ .type = DRM_XE_SYNC_TYPE_USER_FENCE,
+		  .flags = DRM_XE_SYNC_FLAG_SIGNAL,
+		  .timeline_value = PURGEABLE_FENCE_VAL },
+		{ .type = DRM_XE_SYNC_TYPE_SYNCOBJ,
+		  .flags = DRM_XE_SYNC_FLAG_SIGNAL },
+	};
+	struct drm_xe_exec exec = {
+		.num_batch_buffer = 1,
+		.num_syncs = 1,
+		.syncs = to_user_pointer(&sync[1]),
+	};
+	uint32_t *data, *batch;
+	uint64_t vm_sync = 0;
+	uint32_t retained, syncobj;
+	int b, ret;
+
+	/* Create two VMs and bind shared data BO */
+	data = purgeable_setup_two_vms_shared_bo(fd, &vm1, &vm2,

&bo,

tests/intel/xe_exec_system_allocator.c +1 -0
+							 data_addr1,

data_addr2, data_size, true);

tests/intel/xe_exec_system_allocator.c +5 -0
+	memset(data, 0, data_size);
+	bind_engine = xe_bind_exec_queue_create(fd, vm2, 0);
+
+	/* Create and bind batch BO in VM2 */
+	batch_bo = xe_bo_create(fd, vm2, batch_size,

vram_if_possible(fd, 0),

tests/intel/xe_exec_system_allocator.c +1 -0
+				DRM_XE_GEM_CREATE_FLAG_NEEDS_VISIBLE

_VRAM);

tests/intel/xe_exec_system_allocator.c +5 -0
+	batch = xe_bo_map(fd, batch_bo, batch_size);
+
+	sync[0].addr = to_user_pointer(&vm_sync);
+	vm_sync = 0;
+	xe_vm_bind_async(fd, vm2, bind_engine, batch_bo, 0,

batch_addr, batch_size, sync, 1);

tests/intel/xe_exec_system_allocator.c +1 -0
+	xe_wait_ufence(fd, &vm_sync, PURGEABLE_FENCE_VAL, 0,

NSEC_PER_SEC);

tests/intel/xe_exec_system_allocator.c +3 -0
+
+	/* Mark VMA1 as DONTNEED, VMA2 stays WILLNEED */
+	retained = xe_vm_madvise_purgeable(fd, vm1, data_addr1,

data_size,

tests/intel/xe_exec_system_allocator.c +1 -0
+					

DRM_XE_VMA_PURGEABLE_STATE_DONTNEED);

tests/intel/xe_exec_system_allocator.c +6 -0
+	igt_assert_eq(retained, 1);
+
+	/* Trigger pressure - BO should survive (VMA2 protects) */
+	trigger_memory_pressure(fd, vm1);
+
+	retained = xe_vm_madvise_purgeable(fd, vm2, data_addr2,

data_size,

tests/intel/xe_exec_system_allocator.c +1 -0
+					

DRM_XE_VMA_PURGEABLE_STATE_WILLNEED);

tests/intel/xe_exec_system_allocator.c +19 -0
+	igt_assert_eq(retained, 1);
+
+	/* GPU workload - should succeed */
+	b = 0;
+	batch[b++] = MI_STORE_DWORD_IMM_GEN4;
+	batch[b++] = data_addr2;
+	batch[b++] = data_addr2 >> 32;
+	batch[b++] = PURGEABLE_TEST_PATTERN;
+	batch[b++] = MI_BATCH_BUFFER_END;
+
+	syncobj = syncobj_create(fd, 0);
+	sync[1].handle = syncobj;
+	exec_queue = xe_exec_queue_create(fd, vm2, hwe, 0);
+	exec.exec_queue_id = exec_queue;
+	exec.address = batch_addr;
+
+	ret = __xe_exec(fd, &exec);
+	igt_assert_eq(ret, 0);
+	igt_assert(syncobj_wait(fd, &syncobj, 1, INT64_MAX, 0,

NULL));

tests/intel/xe_exec_system_allocator.c +7 -0
+
+	munmap(data, data_size);
+	data = xe_bo_map(fd, bo, data_size);
+	igt_assert_eq(data[0], PURGEABLE_TEST_PATTERN);
+
+	/* Mark both VMAs DONTNEED */
+	retained = xe_vm_madvise_purgeable(fd, vm2, data_addr2,

data_size,

tests/intel/xe_exec_system_allocator.c +1 -0
+					

DRM_XE_VMA_PURGEABLE_STATE_DONTNEED);

tests/intel/xe_exec_system_allocator.c +6 -0
+	igt_assert_eq(retained, 1);
+
+	/* Trigger pressure - BO should be purged */
+	trigger_memory_pressure(fd, vm1);
+
+	retained = xe_vm_madvise_purgeable(fd, vm2, data_addr2,

data_size,

tests/intel/xe_exec_system_allocator.c +1 -0
+					

DRM_XE_VMA_PURGEABLE_STATE_WILLNEED);

tests/intel/xe_exec_system_allocator.c +7 -0
+	igt_assert_eq(retained, 0);
+
+	/* GPU workload - should fail or succeed with NULL rebind */
+	batch[3] = PURGEABLE_DEAD_PATTERN;
+
+	ret = __xe_exec(fd, &exec);
+	/* With SCRATCH_PAGE, kernel may allow exec with NULL

rebind.

tests/intel/xe_exec_system_allocator.c +1 -0
+	 * Without it, exec should fail with -EIO/-EFAULT or wait

should timeout.

tests/intel/xe_exec_system_allocator.c +50 -0
+	 * Both behaviors are valid depending on kernel support.
+	 */
+
+	munmap(data, data_size);
+	munmap(batch, batch_size);
+	gem_close(fd, bo);
+	gem_close(fd, batch_bo);
+	syncobj_destroy(fd, syncobj);
+	xe_exec_queue_destroy(fd, bind_engine);
+	xe_exec_queue_destroy(fd, exec_queue);
+	xe_vm_destroy(fd, vm1);
+	xe_vm_destroy(fd, vm2);
+}
+
  struct section {
  	const char *name;
  	unsigned long long flags;
@@ -2649,6 +3251,42 @@ int igt_main()
  			test_compute(fd, SZ_2M, s->flags);
  	}
 
+	igt_subtest("madvise-purgeable-dontneed-before-mmap")
+		xe_for_each_engine(fd, hwe) {
+			test_dontneed_before_mmap_madvise(fd, hwe);
+			break;
+		}
+
+	igt_subtest("madvise-purgeable-dontneed-after-mmap")
+		xe_for_each_engine(fd, hwe) {
+			test_dontneed_after_mmap_madvise(fd, hwe);
+			break;
+		}
+
+	igt_subtest("madvise-purgeable-dontneed-before-exec")
+		xe_for_each_engine(fd, hwe) {
+			test_dontneed_before_exec_madvise(fd, hwe);
+			break;
+		}
+
+	igt_subtest("madvise-purgeable-dontneed-after-exec")
+		xe_for_each_engine(fd, hwe) {
+			test_dontneed_after_exec_madvise(fd, hwe);
+			break;
+		}
+
+	igt_subtest("madvise-purgeable-per-vma-tracking")
+		xe_for_each_engine(fd, hwe) {
+			test_per_vma_tracking_madvise(fd, hwe);
+			break;
+		}
+
+	igt_subtest("madvise-purgeable-per-vma-protection")
+		xe_for_each_engine(fd, hwe) {
+			test_per_vma_protection_madvise(fd, hwe);
+			break;
+		}
+
  	igt_fixture() {
  		xe_device_put(fd);
  		drm_close_driver(fd);
#6 lore raw

RE: [PATCH i-g-t 3/3] tests/intel/xe_exec_system_allocator: Add purgeable memory madvise tests

In reply to Arvind Yadav
Quoted 84 lines

-----Original Message-----
From: Yadav, Arvind <[email protected]>
Sent: Tuesday, 20 January, 2026 11:42 AM
To: [email protected]
Cc: Brost, Matthew <[email protected]>; Ghimiray, Himal Prasad <[email protected]>; [email protected]; Sharma, Nishit <[email protected]>; Gurram, Pravalika <[email protected]>
Subject: [PATCH i-g-t 3/3] tests/intel/xe_exec_system_allocator: Add purgeable memory madvise tests

Add six purgeable memory test cases for system allocator using madvise:

- madvise-purgeable-dontneed-before-mmap: Mark BO as DONTNEED before mmap,
verify mmap fails on purged memory

- madvise-purgeable-dontneed-after-mmap: Mark BO as DONTNEED after mmap,
verify SIGBUS/SIGSEGV on accessing purged mapping

- madvise-purgeable-dontneed-before-exec: Mark BO as DONTNEED before GPU
execution, verify GPU behavior on purged memory with SCRATCH_PAGE VMs

- madvise-purgeable-dontneed-after-exec: Mark BO as DONTNEED after GPU execution, verify previously-used memory becomes inaccessible

- madvise-purgeable-per-vma-tracking: One BO mapped in two VMs becomes purgeable only when BOTH VMAs are marked DONTNEED

- madvise-purgeable-per-vma-protection: One VMA marked DONTNEED allows
GPU execution on other VMA; both DONTNEED makes BO purgeable

Tests use xe_vm_madvise_purgeable() for WILLNEED/DONTNEED state management and trigger_memory_pressure() to simulate OOM conditions forcing kernel to reclaim purgeable memory.

Cc Matthew Brost <[email protected]>
Cc Thomas Hellström <[email protected]>
Cc Himal Prasad Ghimiray <[email protected]>
---
 tests/intel/xe_exec_system_allocator.c | 638
+++++++++++++++++++++++++
 1 file changed, 638 insertions(+)
tests/intel/xe_exec_system_allocator.c +17 -0
index 8af66d76e..338037a48 100644
@@ -32,6 +32,15 @@
 #define QUARTER_SEC		(NSEC_PER_SEC / 4)
 #define FIVE_SEC		(5LL * NSEC_PER_SEC)
 
+/* Purgeable test constants */
+#define PURGEABLE_ADDR		0x1a0000
+#define PURGEABLE_ADDR2		0x2b0000
+#define PURGEABLE_BATCH_ADDR	0x3c0000
+#define PURGEABLE_BO_SIZE	4096
+#define PURGEABLE_FENCE_VAL	0xbeef
+#define PURGEABLE_TEST_PATTERN	0xc0ffee
+#define PURGEABLE_DEAD_PATTERN	0xdead
+
 struct test_exec_data {
 	uint32_t batch[32];
 	uint64_t pad;
@@ -2245,6 +2254,599 @@ test_compute(int fd, size_t size, unsigned int
 flags)
 	xe_vm_destroy(fd, vm);
 }
 
+/**
+ * trigger_memory_pressure - Trigger memory pressure for purgeable
+tests
+ * @fd: DRM file descriptor
+ * @vm: VM handle
+ *
+ * Creates temporary BOs exceeding VRAM size (VRAM + 64MB) to trigger
+memory

tests/intel/xe_exec_system_allocator.c test_compute(int fd, size_t size, unsigned int · line 2275

Quoted 10 lines
tests/intel/xe_exec_system_allocator.c +10 -0
+ * pressure, forcing kernel to reclaim purgeable BOs in system allocator.
+ */
+static void trigger_memory_pressure(int fd, uint32_t vm) {
+	uint64_t vram_size;
+	const uint64_t chunk = 8ull << 20; /* 8 MiB */
+	int max_objs, n = 0;
+	uint32_t *handles;
+	uint64_t total;
+	void *p;
+	uint32_t bo2;

bo2 suggests there's a bo1, but there isn't. Use bo or handle for clarity

tests/intel/xe_exec_system_allocator.c test_compute(int fd, size_t size, unsigned int flags) · line 2281

Quoted 8 lines
tests/intel/xe_exec_system_allocator.c +8 -0
+
+	vram_size = xe_visible_vram_size(fd, 0);
+	max_objs = vram_size / chunk + 64;
+	handles = calloc(max_objs, sizeof(*handles));
+	igt_assert(handles);
+
+	total = 0;
+	while (total < vram_size + (64 << 20) && n < max_objs) {

The hardcoded 64MB overpressure does not scale with VRAM size, causing the test to behave inconsistently across different hardware configurations. Use percentage-based overpressure that adapts to system VRAM. Like Allocate 25% over VRAM size.

tests/intel/xe_exec_system_allocator.c test_compute(int fd, size_t size, unsigned int flags) · line 2286

Quoted 6 lines
tests/intel/xe_exec_system_allocator.c +5 -0
+		bo2 = xe_bo_create(fd, vm, chunk, vram_if_possible(fd, 0),
+
 DRM_XE_GEM_CREATE_FLAG_NEEDS_VISIBLE_VRAM);
+		handles[n++] = bo2;
+		total += chunk;
+		p = xe_bo_map(fd, bo2, chunk);

No MAP_FAILED check

tests/intel/xe_exec_system_allocator.c test_compute(int fd, size_t size, unsigned int flags) · line 2287

Quoted 1 line
tests/intel/xe_exec_system_allocator.c +1 -0
+		memset(p, 0xCD, 4096);

Why Only touching the first 4KB page of an 8MB allocation Touch multiple pages throughout each allocation.

tests/intel/xe_exec_system_allocator.c test_compute(int fd, size_t size, unsigned int flags) · line 2290

Quoted 3 lines
tests/intel/xe_exec_system_allocator.c +3 -0
+		munmap(p, chunk);
+	}
+

Immediately frees BOs after allocation without giving the kernel shrinker time to run. suggest to add 100ms. Allow shrinker time to process pressure

Quoted 639 lines
tests/intel/xe_exec_system_allocator.c +38 -0
+	for (int i = 0; i < n; i++)
+		gem_close(fd, handles[i]);
+
+	free(handles);
+}
+
+static jmp_buf jmp;
+
+__noreturn static void sigtrap(int sig) {
+	siglongjmp(jmp, sig);
+}
+
+/**
+ * purgeable_mark_and_verify_purged - Mark BO as DONTNEED and verify
+purge
+ * @fd: DRM file descriptor
+ * @vm: VM handle
+ * @addr: Virtual address of the BO
+ * @size: Size of the BO
+ *
+ * Marks BO as DONTNEED, triggers memory pressure, and verifies purge.
+ * Returns: true if BO was successfully purged, false otherwise  */
+static bool purgeable_mark_and_verify_purged(int fd, uint32_t vm,
+uint64_t addr, size_t size) {
+	uint32_t retained;
+
+	/* Mark as DONTNEED */
+	retained = xe_vm_madvise_purgeable(fd, vm, addr, size,
+
 DRM_XE_VMA_PURGEABLE_STATE_DONTNEED);
+	if (retained != 1)
+		return false;
+
+	/* Trigger memory pressure */
+	trigger_memory_pressure(fd, vm);
+
+	/* Verify purged */
+	retained = xe_vm_madvise_purgeable(fd, vm, addr, size,
+

DRM_XE_VMA_PURGEABLE_STATE_WILLNEED);

tests/intel/xe_exec_system_allocator.c +16 -0
+	return retained == 0;
+}
+
+/**
+ * purgeable_setup_simple_bo - Setup VM and bind a single BO
+ * @fd: DRM file descriptor
+ * @vm: Output VM handle
+ * @bo: Output BO handle
+ * @addr: Virtual address to bind at
+ * @size: Size of the BO
+ * @use_scratch: Whether to use scratch page flag
+ *
+ * Helper to create VM, BO, and bind it at the specified address.
+ */
+static void purgeable_setup_simple_bo(int fd, uint32_t *vm, uint32_t *bo,
+				      uint64_t addr, size_t size, bool

use_scratch) {

tests/intel/xe_exec_system_allocator.c +8 -0
+	struct drm_xe_sync sync = {
+		.type = DRM_XE_SYNC_TYPE_USER_FENCE,
+		.flags = DRM_XE_SYNC_FLAG_SIGNAL,
+		.timeline_value = 1,
+	};
+	uint64_t sync_val = 0;
+
+	*vm = xe_vm_create(fd, use_scratch ?

DRM_XE_VM_CREATE_FLAG_SCRATCH_PAGE : 0, 0);

tests/intel/xe_exec_system_allocator.c +24 -0
+	*bo = xe_bo_create(fd, *vm, size, vram_if_possible(fd, 0), 0);
+
+	sync.addr = to_user_pointer(&sync_val);
+	xe_vm_bind_async(fd, *vm, 0, *bo, 0, addr, size, &sync, 1);
+	xe_wait_ufence(fd, &sync_val, 1, 0, NSEC_PER_SEC); }
+
+/**
+ * purgeable_setup_batch_and_data - Setup VM with batch and data BOs
+for GPU exec
+ * @fd: DRM file descriptor
+ * @vm: Output VM handle
+ * @bind_engine: Output bind engine handle
+ * @batch_bo: Output batch BO handle
+ * @data_bo: Output data BO handle
+ * @batch: Output batch buffer pointer
+ * @data: Output data buffer pointer
+ * @batch_addr: Batch virtual address
+ * @data_addr: Data virtual address
+ * @batch_size: Batch buffer size
+ * @data_size: Data buffer size
+ *
+ * Helper to create VM, bind engine, batch and data BOs, and bind them.
+ */
+static void purgeable_setup_batch_and_data(int fd, uint32_t *vm, uint32_t

*bind_engine,

tests/intel/xe_exec_system_allocator.c +1 -0
+					    uint32_t *batch_bo, uint32_t

*data_bo,

tests/intel/xe_exec_system_allocator.c +2 -0
+					    uint32_t **batch, uint32_t **data,
+					    uint64_t batch_addr, uint64_t

data_addr,

tests/intel/xe_exec_system_allocator.c +9 -0
+					    size_t batch_size, size_t data_size) {
+	struct drm_xe_sync sync = {
+		.type = DRM_XE_SYNC_TYPE_USER_FENCE,
+		.flags = DRM_XE_SYNC_FLAG_SIGNAL,
+		.timeline_value = PURGEABLE_FENCE_VAL,
+	};
+	uint64_t vm_sync = 0;
+
+	*vm = xe_vm_create(fd, DRM_XE_VM_CREATE_FLAG_SCRATCH_PAGE,

0);

tests/intel/xe_exec_system_allocator.c +4 -0
+	*bind_engine = xe_bind_exec_queue_create(fd, *vm, 0);
+
+	/* Create and bind batch BO */
+	*batch_bo = xe_bo_create(fd, *vm, batch_size, vram_if_possible(fd,

0),
+
DRM_XE_GEM_CREATE_FLAG_NEEDS_VISIBLE_VRAM);

tests/intel/xe_exec_system_allocator.c +4 -0
+	*batch = xe_bo_map(fd, *batch_bo, batch_size);
+
+	sync.addr = to_user_pointer(&vm_sync);
+	xe_vm_bind_async(fd, *vm, *bind_engine, *batch_bo, 0, batch_addr,

batch_size, &sync, 1);

tests/intel/xe_exec_system_allocator.c +1 -0
+	xe_wait_ufence(fd, &vm_sync, PURGEABLE_FENCE_VAL, 0,

NSEC_PER_SEC);

tests/intel/xe_exec_system_allocator.c +4 -0
+
+	/* Create and bind data BO */
+	*data_bo = xe_bo_create(fd, *vm, data_size, vram_if_possible(fd, 0),
+
	DRM_XE_GEM_CREATE_FLAG_NEEDS_VISIBLE_VRAM);
tests/intel/xe_exec_system_allocator.c +4 -0
+	*data = xe_bo_map(fd, *data_bo, data_size);
+
+	vm_sync = 0;
+	xe_vm_bind_async(fd, *vm, *bind_engine, *data_bo, 0, data_addr,

data_size, &sync, 1);

tests/intel/xe_exec_system_allocator.c +1 -0
+	xe_wait_ufence(fd, &vm_sync, PURGEABLE_FENCE_VAL, 0,

NSEC_PER_SEC); }

tests/intel/xe_exec_system_allocator.c +3 -0
+
+/**
+ * purgeable_setup_two_vms_shared_bo - Setup two VMs with one shared

BO
+ * @fd: DRM file descriptor
+ * @vm1: Output first VM handle
+ * @vm2: Output second VM handle
+ * @bo: Output shared BO handle
+ * @addr1: Virtual address in VM1
+ * @addr2: Virtual address in VM2
+ * @size: Size of the BO
+ * @use_scratch: Whether to use scratch page flag for VMs
+ *
+ * Helper to create two VMs and bind one shared BO in both VMs.
+ * Returns mapped pointer to the BO.
+ */
+static void *purgeable_setup_two_vms_shared_bo(int fd, uint32_t *vm1, uint32_t *vm2,

tests/intel/xe_exec_system_allocator.c +1 -0
+						uint32_t *bo, uint64_t addr1,

uint64_t addr2,

tests/intel/xe_exec_system_allocator.c +12 -0
+						size_t size, bool use_scratch)
+{
+	struct drm_xe_sync sync = {
+		.type = DRM_XE_SYNC_TYPE_USER_FENCE,
+		.flags = DRM_XE_SYNC_FLAG_SIGNAL,
+		.timeline_value = 1,
+	};
+	uint64_t sync_val = 0;
+	void *map;
+
+	/* Create two VMs */
+	*vm1 = xe_vm_create(fd, use_scratch ?

DRM_XE_VM_CREATE_FLAG_SCRATCH_PAGE : 0, 0);

tests/intel/xe_exec_system_allocator.c +6 -0
+	*vm2 = xe_vm_create(fd, use_scratch ?
+DRM_XE_VM_CREATE_FLAG_SCRATCH_PAGE : 0, 0);
+
+	/* Create shared BO */
+	*bo = xe_bo_create(fd, 0, size, vram_if_possible(fd, 0),
+

DRM_XE_GEM_CREATE_FLAG_NEEDS_VISIBLE_VRAM);

tests/intel/xe_exec_system_allocator.c +37 -0
+
+	map = xe_bo_map(fd, *bo, size);
+	memset(map, 0xAB, size);
+
+	/* Bind BO in VM1 */
+	sync.addr = to_user_pointer(&sync_val);
+	sync_val = 0;
+	xe_vm_bind_async(fd, *vm1, 0, *bo, 0, addr1, size, &sync, 1);
+	xe_wait_ufence(fd, &sync_val, 1, 0, NSEC_PER_SEC);
+
+	/* Bind BO in VM2 */
+	sync_val = 0;
+	xe_vm_bind_async(fd, *vm2, 0, *bo, 0, addr2, size, &sync, 1);
+	xe_wait_ufence(fd, &sync_val, 1, 0, NSEC_PER_SEC);
+
+	return map;
+}
+
+/**
+ * SUBTEST: madvise-purgeable-dontneed-before-mmap
+ * Description: Test marking memory as DONTNEED before mmap access in
+system allocator
+ * Test category: functionality test
+ */
+static void test_dontneed_before_mmap_madvise(int fd, struct
+drm_xe_engine_class_instance *hwe) {
+	uint32_t bo, vm;
+	uint64_t addr = PURGEABLE_ADDR;
+	size_t bo_size = PURGEABLE_BO_SIZE;
+	void *map;
+
+	purgeable_setup_simple_bo(fd, &vm, &bo, addr, bo_size, false);
+	if (!purgeable_mark_and_verify_purged(fd, vm, addr, bo_size))
+		igt_skip("Unable to induce purge on this platform/config");
+
+	/* Try to mmap - should fail on purged BO */
+	map = __gem_mmap__device_coherent(fd, bo, 0, bo_size,

PROT_READ | PROT_WRITE);

tests/intel/xe_exec_system_allocator.c +44 -0
+	igt_assert_f(map == NULL, "mmap should fail on purged BO");
+	igt_assert_f(errno == EINVAL || errno == EFAULT,
+		     "Expected EINVAL or EFAULT, got errno=%d\n", errno);
+
+	gem_close(fd, bo);
+	xe_vm_destroy(fd, vm);
+}
+
+/**
+ * SUBTEST: madvise-purgeable-dontneed-after-mmap
+ * Description: Test marking memory as DONTNEED after mmap in system
+allocator
+ * Test category: functionality test
+ */
+static void test_dontneed_after_mmap_madvise(int fd, struct
+drm_xe_engine_class_instance *hwe) {
+	uint32_t bo, vm;
+	uint64_t addr = PURGEABLE_ADDR;
+	size_t bo_size = PURGEABLE_BO_SIZE;
+	void *map;
+
+	purgeable_setup_simple_bo(fd, &vm, &bo, addr, bo_size, true);
+
+	map = xe_bo_map(fd, bo, bo_size);
+	memset(map, 0xAB, bo_size);
+
+	if (!purgeable_mark_and_verify_purged(fd, vm, addr, bo_size))
+		igt_skip("Unable to induce purge on this platform/config");
+
+	/* Access purged mapping - should trigger SIGBUS/SIGSEGV */
+	{
+		sighandler_t old_sigsegv, old_sigbus;
+		char *ptr = (char *)map;
+		int sig;
+
+		old_sigsegv = signal(SIGSEGV, (__sighandler_t)sigtrap);
+		old_sigbus = signal(SIGBUS, (__sighandler_t)sigtrap);
+
+		sig = sigsetjmp(jmp, SIGBUS | SIGSEGV);
+		if (sig == SIGBUS || sig == SIGSEGV) {
+			/* Expected - purged mapping access failed */
+		} else if (sig == 0) {
+			*ptr = 0;
+			igt_assert_f(false, "Access to purged mapping should

trigger signal\n");

tests/intel/xe_exec_system_allocator.c +41 -0
+		} else {
+			igt_assert_f(false, "unexpected signal %d\n", sig);
+		}
+
+		signal(SIGBUS, old_sigbus);
+		signal(SIGSEGV, old_sigsegv);
+	}
+
+	munmap(map, bo_size);
+	gem_close(fd, bo);
+	xe_vm_destroy(fd, vm);
+}
+
+/**
+ * SUBTEST: madvise-purgeable-dontneed-before-exec
+ * Description: Test marking memory as DONTNEED before GPU exec in
+system allocator
+ * Test category: functionality test
+ */
+static void test_dontneed_before_exec_madvise(int fd, struct
+drm_xe_engine_class_instance *hwe) {
+	uint32_t vm, exec_queue, bo, batch_bo, bind_engine;
+	uint64_t data_addr = 0x1a0000;
+	uint64_t batch_addr = 0x2a0000;
+	size_t data_size = 4096;
+	size_t batch_size = 4096;
+	struct drm_xe_sync sync[1] = {
+		{ .type = DRM_XE_SYNC_TYPE_USER_FENCE,
+		  .flags = DRM_XE_SYNC_FLAG_SIGNAL,
+		  .timeline_value = 0xbeef },
+	};
+	struct drm_xe_exec exec = {
+		.num_batch_buffer = 1,
+		.num_syncs = 1,
+		.syncs = to_user_pointer(sync),
+	};
+	uint32_t *data, *batch;
+	uint64_t vm_sync = 0;
+	int b, ret;
+
+	purgeable_setup_batch_and_data(fd, &vm, &bind_engine,

&batch_bo, &bo,

tests/intel/xe_exec_system_allocator.c +1 -0
+					&batch, &data, batch_addr,

data_addr,

tests/intel/xe_exec_system_allocator.c +26 -0
+					batch_size, data_size);
+
+	/* Prepare batch */
+	b = 0;
+	batch[b++] = MI_STORE_DWORD_IMM_GEN4;
+	batch[b++] = data_addr;
+	batch[b++] = data_addr >> 32;
+	batch[b++] = PURGEABLE_DEAD_PATTERN;
+	batch[b++] = MI_BATCH_BUFFER_END;
+
+	igt_assert(purgeable_mark_and_verify_purged(fd, vm, data_addr,
+data_size));
+
+	/* Try to execute - should fail or cause GPU fault */
+	exec_queue = xe_exec_queue_create(fd, vm, hwe, 0);
+	exec.exec_queue_id = exec_queue;
+	exec.address = batch_addr;
+
+	vm_sync = 0;
+	sync[0].addr = to_user_pointer(&vm_sync);
+
+	ret = __xe_exec(fd, &exec);
+	if (ret == 0) {
+		int64_t timeout = NSEC_PER_SEC;
+
+		__xe_wait_ufence(fd, &vm_sync, 0xbeef, exec_queue,

&timeout);

tests/intel/xe_exec_system_allocator.c +1 -0
+		/* Wait may succeed (NULL rebind) or fail (purged) - both

acceptable */

tests/intel/xe_exec_system_allocator.c +41 -0
+	}
+
+	munmap(data, data_size);
+	munmap(batch, batch_size);
+	gem_close(fd, bo);
+	gem_close(fd, batch_bo);
+	xe_exec_queue_destroy(fd, bind_engine);
+	xe_exec_queue_destroy(fd, exec_queue);
+	xe_vm_destroy(fd, vm);
+}
+
+/**
+ * SUBTEST: madvise-purgeable-dontneed-after-exec
+ * Description: Test marking memory as DONTNEED after successful GPU
+exec
+ * Test category: functionality test
+ */
+static void test_dontneed_after_exec_madvise(int fd, struct
+drm_xe_engine_class_instance *hwe) {
+	uint32_t vm, exec_queue, bo, batch_bo, bind_engine;
+	uint64_t data_addr = 0x1a0000;
+	uint64_t batch_addr = 0x2a0000;
+	size_t data_size = 4096;
+	size_t batch_size = 4096;
+	struct drm_xe_sync sync[2] = {
+		{ .type = DRM_XE_SYNC_TYPE_USER_FENCE,
+		  .flags = DRM_XE_SYNC_FLAG_SIGNAL,
+		  .timeline_value = 0xbeef },
+		{ .type = DRM_XE_SYNC_TYPE_SYNCOBJ,
+		  .flags = DRM_XE_SYNC_FLAG_SIGNAL },
+	};
+	struct drm_xe_exec exec = {
+		.num_batch_buffer = 1,
+		.num_syncs = 2,
+		.syncs = to_user_pointer(sync),
+	};
+	uint32_t *data, *batch;
+	uint32_t syncobj;
+	int b, ret;
+
+	purgeable_setup_batch_and_data(fd, &vm, &bind_engine,

&batch_bo, &bo,

tests/intel/xe_exec_system_allocator.c +1 -0
+					&batch, &data, batch_addr,

data_addr,

tests/intel/xe_exec_system_allocator.c +44 -0
+					batch_size, data_size);
+	memset(data, 0, data_size);
+
+	syncobj = syncobj_create(fd, 0);
+
+	/* Prepare batch to write to data BO */
+	b = 0;
+	batch[b++] = MI_STORE_DWORD_IMM_GEN4;
+	batch[b++] = data_addr;
+	batch[b++] = data_addr >> 32;
+	batch[b++] = 0xfeed0001;
+	batch[b++] = MI_BATCH_BUFFER_END;
+
+	exec_queue = xe_exec_queue_create(fd, vm, hwe, 0);
+	exec.exec_queue_id = exec_queue;
+	exec.address = batch_addr;
+
+	/* Use only syncobj for exec (not USER_FENCE) */
+	sync[1].handle = syncobj;
+	exec.num_syncs = 1;
+	exec.syncs = to_user_pointer(&sync[1]);
+
+	ret = __xe_exec(fd, &exec);
+	igt_assert_eq(ret, 0);
+
+	igt_assert(syncobj_wait(fd, &syncobj, 1, INT64_MAX, 0, NULL));
+	munmap(data, data_size);
+	data = xe_bo_map(fd, bo, data_size);
+	igt_assert_eq(data[0], 0xfeed0001);
+
+	igt_assert(purgeable_mark_and_verify_purged(fd, vm, data_addr,
+data_size));
+
+	/* Prepare second batch (different value) */
+	b = 0;
+	batch[b++] = MI_STORE_DWORD_IMM_GEN4;
+	batch[b++] = data_addr;
+	batch[b++] = data_addr >> 32;
+	batch[b++] = 0xfeed0002;
+	batch[b++] = MI_BATCH_BUFFER_END;
+
+	ret = __xe_exec(fd, &exec);
+	if (ret == 0) {
+		/* Exec succeeded, but wait may fail on purged BO (both

behaviors valid) */

tests/intel/xe_exec_system_allocator.c +29 -0
+		syncobj_wait(fd, &syncobj, 1, INT64_MAX, 0, NULL);
+	}
+
+	munmap(data, data_size);
+	munmap(batch, batch_size);
+	gem_close(fd, bo);
+	gem_close(fd, batch_bo);
+	syncobj_destroy(fd, syncobj);
+	xe_exec_queue_destroy(fd, bind_engine);
+	xe_exec_queue_destroy(fd, exec_queue);
+	xe_vm_destroy(fd, vm);
+}
+
+/**
+ * SUBTEST: madvise-purgeable-per-vma-tracking
+ * Description: Test per-VMA purgeable state tracking with multiple VMs
+ * Test category: functionality test
+ */
+static void test_per_vma_tracking_madvise(int fd, struct
+drm_xe_engine_class_instance *hwe) {
+	uint32_t bo, vm1, vm2;
+	uint64_t addr1 = PURGEABLE_ADDR;
+	uint64_t addr2 = PURGEABLE_ADDR2;
+	size_t bo_size = PURGEABLE_BO_SIZE;
+	uint32_t retained;
+	void *map;
+
+	map = purgeable_setup_two_vms_shared_bo(fd, &vm1, &vm2, &bo,
+							addr1, addr2,

bo_size, false);

tests/intel/xe_exec_system_allocator.c +4 -0
+
+	/* Mark VMA1 as DONTNEED */
+	retained = xe_vm_madvise_purgeable(fd, vm1, addr1, bo_size,
+

DRM_XE_VMA_PURGEABLE_STATE_DONTNEED);

tests/intel/xe_exec_system_allocator.c +5 -0
+	igt_assert_eq(retained, 1);
+
+	/* Verify BO NOT purgeable (VMA2 still WILLNEED) */
+	retained = xe_vm_madvise_purgeable(fd, vm1, addr1, bo_size,
+

DRM_XE_VMA_PURGEABLE_STATE_WILLNEED);

tests/intel/xe_exec_system_allocator.c +5 -0
+	igt_assert_eq(retained, 1);
+
+	/* Mark both VMAs as DONTNEED */
+	retained = xe_vm_madvise_purgeable(fd, vm1, addr1, bo_size,
+

DRM_XE_VMA_PURGEABLE_STATE_DONTNEED);

tests/intel/xe_exec_system_allocator.c +4 -0
+	igt_assert_eq(retained, 1);
+
+	retained = xe_vm_madvise_purgeable(fd, vm2, addr2, bo_size,
+

DRM_XE_VMA_PURGEABLE_STATE_DONTNEED);

tests/intel/xe_exec_system_allocator.c +7 -0
+	igt_assert_eq(retained, 1);
+
+	/* Trigger pressure and verify BO was purged */
+	trigger_memory_pressure(fd, vm1);
+
+	retained = xe_vm_madvise_purgeable(fd, vm1, addr1, bo_size,
+

DRM_XE_VMA_PURGEABLE_STATE_WILLNEED);

tests/intel/xe_exec_system_allocator.c +41 -0
+	igt_assert_eq(retained, 0);
+
+	munmap(map, bo_size);
+	gem_close(fd, bo);
+	xe_vm_destroy(fd, vm1);
+	xe_vm_destroy(fd, vm2);
+}
+
+/**
+ * SUBTEST: madvise-purgeable-per-vma-protection
+ * Description: Test per-VMA protection from purging with GPU workload
+ * Test category: functionality test
+ */
+static void test_per_vma_protection_madvise(int fd, struct
+drm_xe_engine_class_instance *hwe) {
+	uint32_t vm1, vm2, exec_queue, bo, batch_bo, bind_engine;
+	uint64_t data_addr1 = PURGEABLE_ADDR;
+	uint64_t data_addr2 = PURGEABLE_ADDR2;
+	uint64_t batch_addr = PURGEABLE_BATCH_ADDR;
+	size_t data_size = PURGEABLE_BO_SIZE;
+	size_t batch_size = PURGEABLE_BO_SIZE;
+	struct drm_xe_sync sync[2] = {
+		{ .type = DRM_XE_SYNC_TYPE_USER_FENCE,
+		  .flags = DRM_XE_SYNC_FLAG_SIGNAL,
+		  .timeline_value = PURGEABLE_FENCE_VAL },
+		{ .type = DRM_XE_SYNC_TYPE_SYNCOBJ,
+		  .flags = DRM_XE_SYNC_FLAG_SIGNAL },
+	};
+	struct drm_xe_exec exec = {
+		.num_batch_buffer = 1,
+		.num_syncs = 1,
+		.syncs = to_user_pointer(&sync[1]),
+	};
+	uint32_t *data, *batch;
+	uint64_t vm_sync = 0;
+	uint32_t retained, syncobj;
+	int b, ret;
+
+	/* Create two VMs and bind shared data BO */
+	data = purgeable_setup_two_vms_shared_bo(fd, &vm1, &vm2, &bo,
+							 data_addr1,

data_addr2, data_size, true);

tests/intel/xe_exec_system_allocator.c +6 -0
+	memset(data, 0, data_size);
+	bind_engine = xe_bind_exec_queue_create(fd, vm2, 0);
+
+	/* Create and bind batch BO in VM2 */
+	batch_bo = xe_bo_create(fd, vm2, batch_size, vram_if_possible(fd, 0),
+
	DRM_XE_GEM_CREATE_FLAG_NEEDS_VISIBLE_VRAM);
tests/intel/xe_exec_system_allocator.c +5 -0
+	batch = xe_bo_map(fd, batch_bo, batch_size);
+
+	sync[0].addr = to_user_pointer(&vm_sync);
+	vm_sync = 0;
+	xe_vm_bind_async(fd, vm2, bind_engine, batch_bo, 0, batch_addr,

batch_size, sync, 1);

tests/intel/xe_exec_system_allocator.c +1 -0
+	xe_wait_ufence(fd, &vm_sync, PURGEABLE_FENCE_VAL, 0,

NSEC_PER_SEC);

tests/intel/xe_exec_system_allocator.c +4 -0
+
+	/* Mark VMA1 as DONTNEED, VMA2 stays WILLNEED */
+	retained = xe_vm_madvise_purgeable(fd, vm1, data_addr1, data_size,
+

DRM_XE_VMA_PURGEABLE_STATE_DONTNEED);

tests/intel/xe_exec_system_allocator.c +7 -0
+	igt_assert_eq(retained, 1);
+
+	/* Trigger pressure - BO should survive (VMA2 protects) */
+	trigger_memory_pressure(fd, vm1);
+
+	retained = xe_vm_madvise_purgeable(fd, vm2, data_addr2, data_size,
+

DRM_XE_VMA_PURGEABLE_STATE_WILLNEED);

tests/intel/xe_exec_system_allocator.c +27 -0
+	igt_assert_eq(retained, 1);
+
+	/* GPU workload - should succeed */
+	b = 0;
+	batch[b++] = MI_STORE_DWORD_IMM_GEN4;
+	batch[b++] = data_addr2;
+	batch[b++] = data_addr2 >> 32;
+	batch[b++] = PURGEABLE_TEST_PATTERN;
+	batch[b++] = MI_BATCH_BUFFER_END;
+
+	syncobj = syncobj_create(fd, 0);
+	sync[1].handle = syncobj;
+	exec_queue = xe_exec_queue_create(fd, vm2, hwe, 0);
+	exec.exec_queue_id = exec_queue;
+	exec.address = batch_addr;
+
+	ret = __xe_exec(fd, &exec);
+	igt_assert_eq(ret, 0);
+	igt_assert(syncobj_wait(fd, &syncobj, 1, INT64_MAX, 0, NULL));
+
+	munmap(data, data_size);
+	data = xe_bo_map(fd, bo, data_size);
+	igt_assert_eq(data[0], PURGEABLE_TEST_PATTERN);
+
+	/* Mark both VMAs DONTNEED */
+	retained = xe_vm_madvise_purgeable(fd, vm2, data_addr2, data_size,
+

DRM_XE_VMA_PURGEABLE_STATE_DONTNEED);

tests/intel/xe_exec_system_allocator.c +7 -0
+	igt_assert_eq(retained, 1);
+
+	/* Trigger pressure - BO should be purged */
+	trigger_memory_pressure(fd, vm1);
+
+	retained = xe_vm_madvise_purgeable(fd, vm2, data_addr2, data_size,
+

DRM_XE_VMA_PURGEABLE_STATE_WILLNEED);

tests/intel/xe_exec_system_allocator.c +8 -0
+	igt_assert_eq(retained, 0);
+
+	/* GPU workload - should fail or succeed with NULL rebind */
+	batch[3] = PURGEABLE_DEAD_PATTERN;
+
+	ret = __xe_exec(fd, &exec);
+	/* With SCRATCH_PAGE, kernel may allow exec with NULL rebind.
+	 * Without it, exec should fail with -EIO/-EFAULT or wait should

timeout.

tests/intel/xe_exec_system_allocator.c +40 -0
+	 * Both behaviors are valid depending on kernel support.
+	 */
+
+	munmap(data, data_size);
+	munmap(batch, batch_size);
+	gem_close(fd, bo);
+	gem_close(fd, batch_bo);
+	syncobj_destroy(fd, syncobj);
+	xe_exec_queue_destroy(fd, bind_engine);
+	xe_exec_queue_destroy(fd, exec_queue);
+	xe_vm_destroy(fd, vm1);
+	xe_vm_destroy(fd, vm2);
+}
+
 struct section {
 	const char *name;
 	unsigned long long flags;
@@ -2649,6 +3251,42 @@ int igt_main()
 			test_compute(fd, SZ_2M, s->flags);
 	}
 
+	igt_subtest("madvise-purgeable-dontneed-before-mmap")
+		xe_for_each_engine(fd, hwe) {
+			test_dontneed_before_mmap_madvise(fd, hwe);
+			break;
+		}
+
+	igt_subtest("madvise-purgeable-dontneed-after-mmap")
+		xe_for_each_engine(fd, hwe) {
+			test_dontneed_after_mmap_madvise(fd, hwe);
+			break;
+		}
+
+	igt_subtest("madvise-purgeable-dontneed-before-exec")
+		xe_for_each_engine(fd, hwe) {
+			test_dontneed_before_exec_madvise(fd, hwe);
+			break;
+		}
+
+	igt_subtest("madvise-purgeable-dontneed-after-exec")
+		xe_for_each_engine(fd, hwe) {
+			test_dontneed_after_exec_madvise(fd, hwe);
+			break;
+		}
+
+	igt_subtest("madvise-purgeable-per-vma-tracking")
+		xe_for_each_engine(fd, hwe) {

tests/intel/xe_exec_system_allocator.c int igt_main() · line 3289

Quoted 10 lines
tests/intel/xe_exec_system_allocator.c +10 -0
+			test_per_vma_tracking_madvise(fd, hwe);
+			break;
+		}
+
+	igt_subtest("madvise-purgeable-per-vma-protection")
+		xe_for_each_engine(fd, hwe) {
+			test_per_vma_protection_madvise(fd, hwe);
+			break;
+		}
+

can you please sperate all the test cases into the individual commits.

-Pravalika

Quoted 5 lines
tests/intel/xe_exec_system_allocator.c +0 -1
 	igt_fixture() {
 		xe_device_put(fd);
 		drm_close_driver(fd);
--

2.43.0

#7 lore raw

Re: [PATCH i-g-t 3/3] tests/intel/xe_exec_system_allocator: Add purgeable memory madvise tests

Quoted 86 lines · Pravalika
Quoted 86 lines

-----Original Message-----
From: Yadav, Arvind <[email protected]>
Sent: Tuesday, 20 January, 2026 11:42 AM
To: [email protected]
Cc: Brost, Matthew <[email protected]>; Ghimiray, Himal Prasad <[email protected]>; [email protected]; Sharma, Nishit <[email protected]>; Gurram, Pravalika <[email protected]>
Subject: [PATCH i-g-t 3/3] tests/intel/xe_exec_system_allocator: Add purgeable memory madvise tests

Add six purgeable memory test cases for system allocator using madvise:

- madvise-purgeable-dontneed-before-mmap: Mark BO as DONTNEED before mmap,
verify mmap fails on purged memory

- madvise-purgeable-dontneed-after-mmap: Mark BO as DONTNEED after mmap,
verify SIGBUS/SIGSEGV on accessing purged mapping

- madvise-purgeable-dontneed-before-exec: Mark BO as DONTNEED before GPU
execution, verify GPU behavior on purged memory with SCRATCH_PAGE VMs

- madvise-purgeable-dontneed-after-exec: Mark BO as DONTNEED after GPU execution, verify previously-used memory becomes inaccessible

- madvise-purgeable-per-vma-tracking: One BO mapped in two VMs becomes purgeable only when BOTH VMAs are marked DONTNEED

- madvise-purgeable-per-vma-protection: One VMA marked DONTNEED allows
GPU execution on other VMA; both DONTNEED makes BO purgeable

Tests use xe_vm_madvise_purgeable() for WILLNEED/DONTNEED state management and trigger_memory_pressure() to simulate OOM conditions forcing kernel to reclaim purgeable memory.

Cc Matthew Brost <[email protected]>
Cc Thomas Hellström <[email protected]>
Cc Himal Prasad Ghimiray <[email protected]>
---
  tests/intel/xe_exec_system_allocator.c | 638
+++++++++++++++++++++++++
  1 file changed, 638 insertions(+)
tests/intel/xe_exec_system_allocator.c +20 -0
index 8af66d76e..338037a48 100644
@@ -32,6 +32,15 @@
  #define QUARTER_SEC		(NSEC_PER_SEC / 4)
  #define FIVE_SEC		(5LL * NSEC_PER_SEC)
 
+/* Purgeable test constants */
+#define PURGEABLE_ADDR		0x1a0000
+#define PURGEABLE_ADDR2		0x2b0000
+#define PURGEABLE_BATCH_ADDR	0x3c0000
+#define PURGEABLE_BO_SIZE	4096
+#define PURGEABLE_FENCE_VAL	0xbeef
+#define PURGEABLE_TEST_PATTERN	0xc0ffee
+#define PURGEABLE_DEAD_PATTERN	0xdead
+
  struct test_exec_data {
  	uint32_t batch[32];
  	uint64_t pad;
@@ -2245,6 +2254,599 @@ test_compute(int fd, size_t size, unsigned int
 flags)
  	xe_vm_destroy(fd, vm);
  }
 
+/**
+ * trigger_memory_pressure - Trigger memory pressure for purgeable
+tests
+ * @fd: DRM file descriptor
+ * @vm: VM handle
+ *
+ * Creates temporary BOs exceeding VRAM size (VRAM + 64MB) to trigger
+memory
+ * pressure, forcing kernel to reclaim purgeable BOs in system allocator.
+ */
+static void trigger_memory_pressure(int fd, uint32_t vm) {
Quoted 8 lines

tests/intel/xe_exec_system_allocator.c test_compute(int fd, size_t size, unsigned int flags) · line 2273

Quoted 7 lines
tests/intel/xe_exec_system_allocator.c +7 -0
+	uint64_t vram_size;
+	const uint64_t chunk = 8ull << 20; /* 8 MiB */
+	int max_objs, n = 0;
+	uint32_t *handles;
+	uint64_t total;
+	void *p;
+	uint32_t bo2;

bo2 suggests there's a bo1, but there isn't. Use bo or handle for clarity

Noted,

Quoted 10 lines

tests/intel/xe_exec_system_allocator.c test_compute(int fd, size_t size, unsigned int flags) · line 2281

Quoted 8 lines
tests/intel/xe_exec_system_allocator.c +8 -0
+
+	vram_size = xe_visible_vram_size(fd, 0);
+	max_objs = vram_size / chunk + 64;
+	handles = calloc(max_objs, sizeof(*handles));
+	igt_assert(handles);
+
+	total = 0;
+	while (total < vram_size + (64 << 20) && n < max_objs) {

The hardcoded 64MB overpressure does not scale with VRAM size, causing the test to behave inconsistently across different hardware configurations. Use percentage-based overpressure that adapts to system VRAM. Like Allocate 25% over VRAM size.

Noted.

Quoted 7 lines

tests/intel/xe_exec_system_allocator.c test_compute(int fd, size_t size, unsigned int flags) · line 2286

Quoted 6 lines
tests/intel/xe_exec_system_allocator.c +5 -0
+		bo2 = xe_bo_create(fd, vm, chunk, vram_if_possible(fd, 0),
+
 DRM_XE_GEM_CREATE_FLAG_NEEDS_VISIBLE_VRAM);
+		handles[n++] = bo2;
+		total += chunk;
+		p = xe_bo_map(fd, bo2, chunk);

No MAP_FAILED check

Noted

Quoted 3 lines

tests/intel/xe_exec_system_allocator.c test_compute(int fd, size_t size, unsigned int flags) · line 2287

Quoted 1 line
tests/intel/xe_exec_system_allocator.c +1 -0
+		memset(p, 0xCD, 4096);

Why Only touching the first 4KB page of an 8MB allocation Touch multiple pages throughout each allocation.

Noted

Quoted 5 lines

tests/intel/xe_exec_system_allocator.c test_compute(int fd, size_t size, unsigned int flags) · line 2290

Quoted 3 lines
tests/intel/xe_exec_system_allocator.c +3 -0
+		munmap(p, chunk);
+	}
+

Immediately frees BOs after allocation without giving the kernel shrinker time to run. suggest to add 100ms. Allow shrinker time to process pressure

I will add delay.

Thanks,
Arvind

Quoted 658 lines
Quoted 640 lines
tests/intel/xe_exec_system_allocator.c +38 -0
+	for (int i = 0; i < n; i++)
+		gem_close(fd, handles[i]);
+
+	free(handles);
+}
+
+static jmp_buf jmp;
+
+__noreturn static void sigtrap(int sig) {
+	siglongjmp(jmp, sig);
+}
+
+/**
+ * purgeable_mark_and_verify_purged - Mark BO as DONTNEED and verify
+purge
+ * @fd: DRM file descriptor
+ * @vm: VM handle
+ * @addr: Virtual address of the BO
+ * @size: Size of the BO
+ *
+ * Marks BO as DONTNEED, triggers memory pressure, and verifies purge.
+ * Returns: true if BO was successfully purged, false otherwise  */
+static bool purgeable_mark_and_verify_purged(int fd, uint32_t vm,
+uint64_t addr, size_t size) {
+	uint32_t retained;
+
+	/* Mark as DONTNEED */
+	retained = xe_vm_madvise_purgeable(fd, vm, addr, size,
+
 DRM_XE_VMA_PURGEABLE_STATE_DONTNEED);
+	if (retained != 1)
+		return false;
+
+	/* Trigger memory pressure */
+	trigger_memory_pressure(fd, vm);
+
+	/* Verify purged */
+	retained = xe_vm_madvise_purgeable(fd, vm, addr, size,
+

DRM_XE_VMA_PURGEABLE_STATE_WILLNEED);

tests/intel/xe_exec_system_allocator.c +16 -0
+	return retained == 0;
+}
+
+/**
+ * purgeable_setup_simple_bo - Setup VM and bind a single BO
+ * @fd: DRM file descriptor
+ * @vm: Output VM handle
+ * @bo: Output BO handle
+ * @addr: Virtual address to bind at
+ * @size: Size of the BO
+ * @use_scratch: Whether to use scratch page flag
+ *
+ * Helper to create VM, BO, and bind it at the specified address.
+ */
+static void purgeable_setup_simple_bo(int fd, uint32_t *vm, uint32_t *bo,
+				      uint64_t addr, size_t size, bool

use_scratch) {

tests/intel/xe_exec_system_allocator.c +8 -0
+	struct drm_xe_sync sync = {
+		.type = DRM_XE_SYNC_TYPE_USER_FENCE,
+		.flags = DRM_XE_SYNC_FLAG_SIGNAL,
+		.timeline_value = 1,
+	};
+	uint64_t sync_val = 0;
+
+	*vm = xe_vm_create(fd, use_scratch ?

DRM_XE_VM_CREATE_FLAG_SCRATCH_PAGE : 0, 0);

tests/intel/xe_exec_system_allocator.c +24 -0
+	*bo = xe_bo_create(fd, *vm, size, vram_if_possible(fd, 0), 0);
+
+	sync.addr = to_user_pointer(&sync_val);
+	xe_vm_bind_async(fd, *vm, 0, *bo, 0, addr, size, &sync, 1);
+	xe_wait_ufence(fd, &sync_val, 1, 0, NSEC_PER_SEC); }
+
+/**
+ * purgeable_setup_batch_and_data - Setup VM with batch and data BOs
+for GPU exec
+ * @fd: DRM file descriptor
+ * @vm: Output VM handle
+ * @bind_engine: Output bind engine handle
+ * @batch_bo: Output batch BO handle
+ * @data_bo: Output data BO handle
+ * @batch: Output batch buffer pointer
+ * @data: Output data buffer pointer
+ * @batch_addr: Batch virtual address
+ * @data_addr: Data virtual address
+ * @batch_size: Batch buffer size
+ * @data_size: Data buffer size
+ *
+ * Helper to create VM, bind engine, batch and data BOs, and bind them.
+ */
+static void purgeable_setup_batch_and_data(int fd, uint32_t *vm, uint32_t

*bind_engine,

tests/intel/xe_exec_system_allocator.c +1 -0
+					    uint32_t *batch_bo, uint32_t

*data_bo,

tests/intel/xe_exec_system_allocator.c +2 -0
+					    uint32_t **batch, uint32_t **data,
+					    uint64_t batch_addr, uint64_t

data_addr,

tests/intel/xe_exec_system_allocator.c +9 -0
+					    size_t batch_size, size_t data_size) {
+	struct drm_xe_sync sync = {
+		.type = DRM_XE_SYNC_TYPE_USER_FENCE,
+		.flags = DRM_XE_SYNC_FLAG_SIGNAL,
+		.timeline_value = PURGEABLE_FENCE_VAL,
+	};
+	uint64_t vm_sync = 0;
+
+	*vm = xe_vm_create(fd, DRM_XE_VM_CREATE_FLAG_SCRATCH_PAGE,

0);

tests/intel/xe_exec_system_allocator.c +4 -0
+	*bind_engine = xe_bind_exec_queue_create(fd, *vm, 0);
+
+	/* Create and bind batch BO */
+	*batch_bo = xe_bo_create(fd, *vm, batch_size, vram_if_possible(fd,

0),
+
DRM_XE_GEM_CREATE_FLAG_NEEDS_VISIBLE_VRAM);

tests/intel/xe_exec_system_allocator.c +4 -0
+	*batch = xe_bo_map(fd, *batch_bo, batch_size);
+
+	sync.addr = to_user_pointer(&vm_sync);
+	xe_vm_bind_async(fd, *vm, *bind_engine, *batch_bo, 0, batch_addr,

batch_size, &sync, 1);

tests/intel/xe_exec_system_allocator.c +1 -0
+	xe_wait_ufence(fd, &vm_sync, PURGEABLE_FENCE_VAL, 0,

NSEC_PER_SEC);

tests/intel/xe_exec_system_allocator.c +4 -0
+
+	/* Create and bind data BO */
+	*data_bo = xe_bo_create(fd, *vm, data_size, vram_if_possible(fd, 0),
+
	DRM_XE_GEM_CREATE_FLAG_NEEDS_VISIBLE_VRAM);
tests/intel/xe_exec_system_allocator.c +4 -0
+	*data = xe_bo_map(fd, *data_bo, data_size);
+
+	vm_sync = 0;
+	xe_vm_bind_async(fd, *vm, *bind_engine, *data_bo, 0, data_addr,

data_size, &sync, 1);

tests/intel/xe_exec_system_allocator.c +1 -0
+	xe_wait_ufence(fd, &vm_sync, PURGEABLE_FENCE_VAL, 0,

NSEC_PER_SEC); }

tests/intel/xe_exec_system_allocator.c +3 -0
+
+/**
+ * purgeable_setup_two_vms_shared_bo - Setup two VMs with one shared

BO
+ * @fd: DRM file descriptor
+ * @vm1: Output first VM handle
+ * @vm2: Output second VM handle
+ * @bo: Output shared BO handle
+ * @addr1: Virtual address in VM1
+ * @addr2: Virtual address in VM2
+ * @size: Size of the BO
+ * @use_scratch: Whether to use scratch page flag for VMs
+ *
+ * Helper to create two VMs and bind one shared BO in both VMs.
+ * Returns mapped pointer to the BO.
+ */
+static void *purgeable_setup_two_vms_shared_bo(int fd, uint32_t *vm1, uint32_t *vm2,

tests/intel/xe_exec_system_allocator.c +1 -0
+						uint32_t *bo, uint64_t addr1,

uint64_t addr2,

tests/intel/xe_exec_system_allocator.c +12 -0
+						size_t size, bool use_scratch)
+{
+	struct drm_xe_sync sync = {
+		.type = DRM_XE_SYNC_TYPE_USER_FENCE,
+		.flags = DRM_XE_SYNC_FLAG_SIGNAL,
+		.timeline_value = 1,
+	};
+	uint64_t sync_val = 0;
+	void *map;
+
+	/* Create two VMs */
+	*vm1 = xe_vm_create(fd, use_scratch ?

DRM_XE_VM_CREATE_FLAG_SCRATCH_PAGE : 0, 0);

tests/intel/xe_exec_system_allocator.c +6 -0
+	*vm2 = xe_vm_create(fd, use_scratch ?
+DRM_XE_VM_CREATE_FLAG_SCRATCH_PAGE : 0, 0);
+
+	/* Create shared BO */
+	*bo = xe_bo_create(fd, 0, size, vram_if_possible(fd, 0),
+

DRM_XE_GEM_CREATE_FLAG_NEEDS_VISIBLE_VRAM);

tests/intel/xe_exec_system_allocator.c +37 -0
+
+	map = xe_bo_map(fd, *bo, size);
+	memset(map, 0xAB, size);
+
+	/* Bind BO in VM1 */
+	sync.addr = to_user_pointer(&sync_val);
+	sync_val = 0;
+	xe_vm_bind_async(fd, *vm1, 0, *bo, 0, addr1, size, &sync, 1);
+	xe_wait_ufence(fd, &sync_val, 1, 0, NSEC_PER_SEC);
+
+	/* Bind BO in VM2 */
+	sync_val = 0;
+	xe_vm_bind_async(fd, *vm2, 0, *bo, 0, addr2, size, &sync, 1);
+	xe_wait_ufence(fd, &sync_val, 1, 0, NSEC_PER_SEC);
+
+	return map;
+}
+
+/**
+ * SUBTEST: madvise-purgeable-dontneed-before-mmap
+ * Description: Test marking memory as DONTNEED before mmap access in
+system allocator
+ * Test category: functionality test
+ */
+static void test_dontneed_before_mmap_madvise(int fd, struct
+drm_xe_engine_class_instance *hwe) {
+	uint32_t bo, vm;
+	uint64_t addr = PURGEABLE_ADDR;
+	size_t bo_size = PURGEABLE_BO_SIZE;
+	void *map;
+
+	purgeable_setup_simple_bo(fd, &vm, &bo, addr, bo_size, false);
+	if (!purgeable_mark_and_verify_purged(fd, vm, addr, bo_size))
+		igt_skip("Unable to induce purge on this platform/config");
+
+	/* Try to mmap - should fail on purged BO */
+	map = __gem_mmap__device_coherent(fd, bo, 0, bo_size,

PROT_READ | PROT_WRITE);

tests/intel/xe_exec_system_allocator.c +44 -0
+	igt_assert_f(map == NULL, "mmap should fail on purged BO");
+	igt_assert_f(errno == EINVAL || errno == EFAULT,
+		     "Expected EINVAL or EFAULT, got errno=%d\n", errno);
+
+	gem_close(fd, bo);
+	xe_vm_destroy(fd, vm);
+}
+
+/**
+ * SUBTEST: madvise-purgeable-dontneed-after-mmap
+ * Description: Test marking memory as DONTNEED after mmap in system
+allocator
+ * Test category: functionality test
+ */
+static void test_dontneed_after_mmap_madvise(int fd, struct
+drm_xe_engine_class_instance *hwe) {
+	uint32_t bo, vm;
+	uint64_t addr = PURGEABLE_ADDR;
+	size_t bo_size = PURGEABLE_BO_SIZE;
+	void *map;
+
+	purgeable_setup_simple_bo(fd, &vm, &bo, addr, bo_size, true);
+
+	map = xe_bo_map(fd, bo, bo_size);
+	memset(map, 0xAB, bo_size);
+
+	if (!purgeable_mark_and_verify_purged(fd, vm, addr, bo_size))
+		igt_skip("Unable to induce purge on this platform/config");
+
+	/* Access purged mapping - should trigger SIGBUS/SIGSEGV */
+	{
+		sighandler_t old_sigsegv, old_sigbus;
+		char *ptr = (char *)map;
+		int sig;
+
+		old_sigsegv = signal(SIGSEGV, (__sighandler_t)sigtrap);
+		old_sigbus = signal(SIGBUS, (__sighandler_t)sigtrap);
+
+		sig = sigsetjmp(jmp, SIGBUS | SIGSEGV);
+		if (sig == SIGBUS || sig == SIGSEGV) {
+			/* Expected - purged mapping access failed */
+		} else if (sig == 0) {
+			*ptr = 0;
+			igt_assert_f(false, "Access to purged mapping should

trigger signal\n");

tests/intel/xe_exec_system_allocator.c +41 -0
+		} else {
+			igt_assert_f(false, "unexpected signal %d\n", sig);
+		}
+
+		signal(SIGBUS, old_sigbus);
+		signal(SIGSEGV, old_sigsegv);
+	}
+
+	munmap(map, bo_size);
+	gem_close(fd, bo);
+	xe_vm_destroy(fd, vm);
+}
+
+/**
+ * SUBTEST: madvise-purgeable-dontneed-before-exec
+ * Description: Test marking memory as DONTNEED before GPU exec in
+system allocator
+ * Test category: functionality test
+ */
+static void test_dontneed_before_exec_madvise(int fd, struct
+drm_xe_engine_class_instance *hwe) {
+	uint32_t vm, exec_queue, bo, batch_bo, bind_engine;
+	uint64_t data_addr = 0x1a0000;
+	uint64_t batch_addr = 0x2a0000;
+	size_t data_size = 4096;
+	size_t batch_size = 4096;
+	struct drm_xe_sync sync[1] = {
+		{ .type = DRM_XE_SYNC_TYPE_USER_FENCE,
+		  .flags = DRM_XE_SYNC_FLAG_SIGNAL,
+		  .timeline_value = 0xbeef },
+	};
+	struct drm_xe_exec exec = {
+		.num_batch_buffer = 1,
+		.num_syncs = 1,
+		.syncs = to_user_pointer(sync),
+	};
+	uint32_t *data, *batch;
+	uint64_t vm_sync = 0;
+	int b, ret;
+
+	purgeable_setup_batch_and_data(fd, &vm, &bind_engine,

&batch_bo, &bo,

tests/intel/xe_exec_system_allocator.c +1 -0
+					&batch, &data, batch_addr,

data_addr,

tests/intel/xe_exec_system_allocator.c +26 -0
+					batch_size, data_size);
+
+	/* Prepare batch */
+	b = 0;
+	batch[b++] = MI_STORE_DWORD_IMM_GEN4;
+	batch[b++] = data_addr;
+	batch[b++] = data_addr >> 32;
+	batch[b++] = PURGEABLE_DEAD_PATTERN;
+	batch[b++] = MI_BATCH_BUFFER_END;
+
+	igt_assert(purgeable_mark_and_verify_purged(fd, vm, data_addr,
+data_size));
+
+	/* Try to execute - should fail or cause GPU fault */
+	exec_queue = xe_exec_queue_create(fd, vm, hwe, 0);
+	exec.exec_queue_id = exec_queue;
+	exec.address = batch_addr;
+
+	vm_sync = 0;
+	sync[0].addr = to_user_pointer(&vm_sync);
+
+	ret = __xe_exec(fd, &exec);
+	if (ret == 0) {
+		int64_t timeout = NSEC_PER_SEC;
+
+		__xe_wait_ufence(fd, &vm_sync, 0xbeef, exec_queue,

&timeout);

tests/intel/xe_exec_system_allocator.c +1 -0
+		/* Wait may succeed (NULL rebind) or fail (purged) - both

acceptable */

tests/intel/xe_exec_system_allocator.c +41 -0
+	}
+
+	munmap(data, data_size);
+	munmap(batch, batch_size);
+	gem_close(fd, bo);
+	gem_close(fd, batch_bo);
+	xe_exec_queue_destroy(fd, bind_engine);
+	xe_exec_queue_destroy(fd, exec_queue);
+	xe_vm_destroy(fd, vm);
+}
+
+/**
+ * SUBTEST: madvise-purgeable-dontneed-after-exec
+ * Description: Test marking memory as DONTNEED after successful GPU
+exec
+ * Test category: functionality test
+ */
+static void test_dontneed_after_exec_madvise(int fd, struct
+drm_xe_engine_class_instance *hwe) {
+	uint32_t vm, exec_queue, bo, batch_bo, bind_engine;
+	uint64_t data_addr = 0x1a0000;
+	uint64_t batch_addr = 0x2a0000;
+	size_t data_size = 4096;
+	size_t batch_size = 4096;
+	struct drm_xe_sync sync[2] = {
+		{ .type = DRM_XE_SYNC_TYPE_USER_FENCE,
+		  .flags = DRM_XE_SYNC_FLAG_SIGNAL,
+		  .timeline_value = 0xbeef },
+		{ .type = DRM_XE_SYNC_TYPE_SYNCOBJ,
+		  .flags = DRM_XE_SYNC_FLAG_SIGNAL },
+	};
+	struct drm_xe_exec exec = {
+		.num_batch_buffer = 1,
+		.num_syncs = 2,
+		.syncs = to_user_pointer(sync),
+	};
+	uint32_t *data, *batch;
+	uint32_t syncobj;
+	int b, ret;
+
+	purgeable_setup_batch_and_data(fd, &vm, &bind_engine,

&batch_bo, &bo,

tests/intel/xe_exec_system_allocator.c +1 -0
+					&batch, &data, batch_addr,

data_addr,

tests/intel/xe_exec_system_allocator.c +44 -0
+					batch_size, data_size);
+	memset(data, 0, data_size);
+
+	syncobj = syncobj_create(fd, 0);
+
+	/* Prepare batch to write to data BO */
+	b = 0;
+	batch[b++] = MI_STORE_DWORD_IMM_GEN4;
+	batch[b++] = data_addr;
+	batch[b++] = data_addr >> 32;
+	batch[b++] = 0xfeed0001;
+	batch[b++] = MI_BATCH_BUFFER_END;
+
+	exec_queue = xe_exec_queue_create(fd, vm, hwe, 0);
+	exec.exec_queue_id = exec_queue;
+	exec.address = batch_addr;
+
+	/* Use only syncobj for exec (not USER_FENCE) */
+	sync[1].handle = syncobj;
+	exec.num_syncs = 1;
+	exec.syncs = to_user_pointer(&sync[1]);
+
+	ret = __xe_exec(fd, &exec);
+	igt_assert_eq(ret, 0);
+
+	igt_assert(syncobj_wait(fd, &syncobj, 1, INT64_MAX, 0, NULL));
+	munmap(data, data_size);
+	data = xe_bo_map(fd, bo, data_size);
+	igt_assert_eq(data[0], 0xfeed0001);
+
+	igt_assert(purgeable_mark_and_verify_purged(fd, vm, data_addr,
+data_size));
+
+	/* Prepare second batch (different value) */
+	b = 0;
+	batch[b++] = MI_STORE_DWORD_IMM_GEN4;
+	batch[b++] = data_addr;
+	batch[b++] = data_addr >> 32;
+	batch[b++] = 0xfeed0002;
+	batch[b++] = MI_BATCH_BUFFER_END;
+
+	ret = __xe_exec(fd, &exec);
+	if (ret == 0) {
+		/* Exec succeeded, but wait may fail on purged BO (both

behaviors valid) */

tests/intel/xe_exec_system_allocator.c +29 -0
+		syncobj_wait(fd, &syncobj, 1, INT64_MAX, 0, NULL);
+	}
+
+	munmap(data, data_size);
+	munmap(batch, batch_size);
+	gem_close(fd, bo);
+	gem_close(fd, batch_bo);
+	syncobj_destroy(fd, syncobj);
+	xe_exec_queue_destroy(fd, bind_engine);
+	xe_exec_queue_destroy(fd, exec_queue);
+	xe_vm_destroy(fd, vm);
+}
+
+/**
+ * SUBTEST: madvise-purgeable-per-vma-tracking
+ * Description: Test per-VMA purgeable state tracking with multiple VMs
+ * Test category: functionality test
+ */
+static void test_per_vma_tracking_madvise(int fd, struct
+drm_xe_engine_class_instance *hwe) {
+	uint32_t bo, vm1, vm2;
+	uint64_t addr1 = PURGEABLE_ADDR;
+	uint64_t addr2 = PURGEABLE_ADDR2;
+	size_t bo_size = PURGEABLE_BO_SIZE;
+	uint32_t retained;
+	void *map;
+
+	map = purgeable_setup_two_vms_shared_bo(fd, &vm1, &vm2, &bo,
+							addr1, addr2,

bo_size, false);

tests/intel/xe_exec_system_allocator.c +4 -0
+
+	/* Mark VMA1 as DONTNEED */
+	retained = xe_vm_madvise_purgeable(fd, vm1, addr1, bo_size,
+

DRM_XE_VMA_PURGEABLE_STATE_DONTNEED);

tests/intel/xe_exec_system_allocator.c +5 -0
+	igt_assert_eq(retained, 1);
+
+	/* Verify BO NOT purgeable (VMA2 still WILLNEED) */
+	retained = xe_vm_madvise_purgeable(fd, vm1, addr1, bo_size,
+

DRM_XE_VMA_PURGEABLE_STATE_WILLNEED);

tests/intel/xe_exec_system_allocator.c +5 -0
+	igt_assert_eq(retained, 1);
+
+	/* Mark both VMAs as DONTNEED */
+	retained = xe_vm_madvise_purgeable(fd, vm1, addr1, bo_size,
+

DRM_XE_VMA_PURGEABLE_STATE_DONTNEED);

tests/intel/xe_exec_system_allocator.c +4 -0
+	igt_assert_eq(retained, 1);
+
+	retained = xe_vm_madvise_purgeable(fd, vm2, addr2, bo_size,
+

DRM_XE_VMA_PURGEABLE_STATE_DONTNEED);

tests/intel/xe_exec_system_allocator.c +7 -0
+	igt_assert_eq(retained, 1);
+
+	/* Trigger pressure and verify BO was purged */
+	trigger_memory_pressure(fd, vm1);
+
+	retained = xe_vm_madvise_purgeable(fd, vm1, addr1, bo_size,
+

DRM_XE_VMA_PURGEABLE_STATE_WILLNEED);

tests/intel/xe_exec_system_allocator.c +41 -0
+	igt_assert_eq(retained, 0);
+
+	munmap(map, bo_size);
+	gem_close(fd, bo);
+	xe_vm_destroy(fd, vm1);
+	xe_vm_destroy(fd, vm2);
+}
+
+/**
+ * SUBTEST: madvise-purgeable-per-vma-protection
+ * Description: Test per-VMA protection from purging with GPU workload
+ * Test category: functionality test
+ */
+static void test_per_vma_protection_madvise(int fd, struct
+drm_xe_engine_class_instance *hwe) {
+	uint32_t vm1, vm2, exec_queue, bo, batch_bo, bind_engine;
+	uint64_t data_addr1 = PURGEABLE_ADDR;
+	uint64_t data_addr2 = PURGEABLE_ADDR2;
+	uint64_t batch_addr = PURGEABLE_BATCH_ADDR;
+	size_t data_size = PURGEABLE_BO_SIZE;
+	size_t batch_size = PURGEABLE_BO_SIZE;
+	struct drm_xe_sync sync[2] = {
+		{ .type = DRM_XE_SYNC_TYPE_USER_FENCE,
+		  .flags = DRM_XE_SYNC_FLAG_SIGNAL,
+		  .timeline_value = PURGEABLE_FENCE_VAL },
+		{ .type = DRM_XE_SYNC_TYPE_SYNCOBJ,
+		  .flags = DRM_XE_SYNC_FLAG_SIGNAL },
+	};
+	struct drm_xe_exec exec = {
+		.num_batch_buffer = 1,
+		.num_syncs = 1,
+		.syncs = to_user_pointer(&sync[1]),
+	};
+	uint32_t *data, *batch;
+	uint64_t vm_sync = 0;
+	uint32_t retained, syncobj;
+	int b, ret;
+
+	/* Create two VMs and bind shared data BO */
+	data = purgeable_setup_two_vms_shared_bo(fd, &vm1, &vm2, &bo,
+							 data_addr1,

data_addr2, data_size, true);

tests/intel/xe_exec_system_allocator.c +6 -0
+	memset(data, 0, data_size);
+	bind_engine = xe_bind_exec_queue_create(fd, vm2, 0);
+
+	/* Create and bind batch BO in VM2 */
+	batch_bo = xe_bo_create(fd, vm2, batch_size, vram_if_possible(fd, 0),
+
	DRM_XE_GEM_CREATE_FLAG_NEEDS_VISIBLE_VRAM);
tests/intel/xe_exec_system_allocator.c +5 -0
+	batch = xe_bo_map(fd, batch_bo, batch_size);
+
+	sync[0].addr = to_user_pointer(&vm_sync);
+	vm_sync = 0;
+	xe_vm_bind_async(fd, vm2, bind_engine, batch_bo, 0, batch_addr,

batch_size, sync, 1);

tests/intel/xe_exec_system_allocator.c +1 -0
+	xe_wait_ufence(fd, &vm_sync, PURGEABLE_FENCE_VAL, 0,

NSEC_PER_SEC);

tests/intel/xe_exec_system_allocator.c +4 -0
+
+	/* Mark VMA1 as DONTNEED, VMA2 stays WILLNEED */
+	retained = xe_vm_madvise_purgeable(fd, vm1, data_addr1, data_size,
+

DRM_XE_VMA_PURGEABLE_STATE_DONTNEED);

tests/intel/xe_exec_system_allocator.c +7 -0
+	igt_assert_eq(retained, 1);
+
+	/* Trigger pressure - BO should survive (VMA2 protects) */
+	trigger_memory_pressure(fd, vm1);
+
+	retained = xe_vm_madvise_purgeable(fd, vm2, data_addr2, data_size,
+

DRM_XE_VMA_PURGEABLE_STATE_WILLNEED);

tests/intel/xe_exec_system_allocator.c +27 -0
+	igt_assert_eq(retained, 1);
+
+	/* GPU workload - should succeed */
+	b = 0;
+	batch[b++] = MI_STORE_DWORD_IMM_GEN4;
+	batch[b++] = data_addr2;
+	batch[b++] = data_addr2 >> 32;
+	batch[b++] = PURGEABLE_TEST_PATTERN;
+	batch[b++] = MI_BATCH_BUFFER_END;
+
+	syncobj = syncobj_create(fd, 0);
+	sync[1].handle = syncobj;
+	exec_queue = xe_exec_queue_create(fd, vm2, hwe, 0);
+	exec.exec_queue_id = exec_queue;
+	exec.address = batch_addr;
+
+	ret = __xe_exec(fd, &exec);
+	igt_assert_eq(ret, 0);
+	igt_assert(syncobj_wait(fd, &syncobj, 1, INT64_MAX, 0, NULL));
+
+	munmap(data, data_size);
+	data = xe_bo_map(fd, bo, data_size);
+	igt_assert_eq(data[0], PURGEABLE_TEST_PATTERN);
+
+	/* Mark both VMAs DONTNEED */
+	retained = xe_vm_madvise_purgeable(fd, vm2, data_addr2, data_size,
+

DRM_XE_VMA_PURGEABLE_STATE_DONTNEED);

tests/intel/xe_exec_system_allocator.c +7 -0
+	igt_assert_eq(retained, 1);
+
+	/* Trigger pressure - BO should be purged */
+	trigger_memory_pressure(fd, vm1);
+
+	retained = xe_vm_madvise_purgeable(fd, vm2, data_addr2, data_size,
+

DRM_XE_VMA_PURGEABLE_STATE_WILLNEED);

tests/intel/xe_exec_system_allocator.c +8 -0
+	igt_assert_eq(retained, 0);
+
+	/* GPU workload - should fail or succeed with NULL rebind */
+	batch[3] = PURGEABLE_DEAD_PATTERN;
+
+	ret = __xe_exec(fd, &exec);
+	/* With SCRATCH_PAGE, kernel may allow exec with NULL rebind.
+	 * Without it, exec should fail with -EIO/-EFAULT or wait should

timeout.

tests/intel/xe_exec_system_allocator.c +40 -0
+	 * Both behaviors are valid depending on kernel support.
+	 */
+
+	munmap(data, data_size);
+	munmap(batch, batch_size);
+	gem_close(fd, bo);
+	gem_close(fd, batch_bo);
+	syncobj_destroy(fd, syncobj);
+	xe_exec_queue_destroy(fd, bind_engine);
+	xe_exec_queue_destroy(fd, exec_queue);
+	xe_vm_destroy(fd, vm1);
+	xe_vm_destroy(fd, vm2);
+}
+
  struct section {
  	const char *name;
  	unsigned long long flags;
@@ -2649,6 +3251,42 @@ int igt_main()
  			test_compute(fd, SZ_2M, s->flags);
  	}
 
+	igt_subtest("madvise-purgeable-dontneed-before-mmap")
+		xe_for_each_engine(fd, hwe) {
+			test_dontneed_before_mmap_madvise(fd, hwe);
+			break;
+		}
+
+	igt_subtest("madvise-purgeable-dontneed-after-mmap")
+		xe_for_each_engine(fd, hwe) {
+			test_dontneed_after_mmap_madvise(fd, hwe);
+			break;
+		}
+
+	igt_subtest("madvise-purgeable-dontneed-before-exec")
+		xe_for_each_engine(fd, hwe) {
+			test_dontneed_before_exec_madvise(fd, hwe);
+			break;
+		}
+
+	igt_subtest("madvise-purgeable-dontneed-after-exec")
+		xe_for_each_engine(fd, hwe) {
+			test_dontneed_after_exec_madvise(fd, hwe);
+			break;
+		}
+
+	igt_subtest("madvise-purgeable-per-vma-tracking")
+		xe_for_each_engine(fd, hwe) {

tests/intel/xe_exec_system_allocator.c int igt_main() · line 3289

Quoted 10 lines
tests/intel/xe_exec_system_allocator.c +10 -0
+			test_per_vma_tracking_madvise(fd, hwe);
+			break;
+		}
+
+	igt_subtest("madvise-purgeable-per-vma-protection")
+		xe_for_each_engine(fd, hwe) {
+			test_per_vma_protection_madvise(fd, hwe);
+			break;
+		}
+

can you please sperate all the test cases into the individual commits.

-Pravalika

Quoted 5 lines
tests/intel/xe_exec_system_allocator.c +0 -1
  	igt_fixture() {
  		xe_device_put(fd);
  		drm_close_driver(fd);
--

2.43.0

#8 lore raw

RE: [PATCH i-g-t 3/3] tests/intel/xe_exec_system_allocator: Add purgeable memory madvise tests

In reply to Arvind Yadav
Quoted 322 lines

-----Original Message-----
From: Yadav, Arvind <[email protected]>
Sent: Tuesday, 20 January, 2026 11:42 AM
To: [email protected]
Cc: Brost, Matthew <[email protected]>; Ghimiray, Himal Prasad <[email protected]>; [email protected]; Sharma, Nishit <[email protected]>; Gurram, Pravalika <[email protected]>
Subject: [PATCH i-g-t 3/3] tests/intel/xe_exec_system_allocator: Add purgeable memory madvise tests

Add six purgeable memory test cases for system allocator using madvise:

- madvise-purgeable-dontneed-before-mmap: Mark BO as DONTNEED before mmap,
verify mmap fails on purged memory

- madvise-purgeable-dontneed-after-mmap: Mark BO as DONTNEED after mmap,
verify SIGBUS/SIGSEGV on accessing purged mapping

- madvise-purgeable-dontneed-before-exec: Mark BO as DONTNEED before GPU
execution, verify GPU behavior on purged memory with SCRATCH_PAGE VMs

- madvise-purgeable-dontneed-after-exec: Mark BO as DONTNEED after GPU execution, verify previously-used memory becomes inaccessible

- madvise-purgeable-per-vma-tracking: One BO mapped in two VMs becomes purgeable only when BOTH VMAs are marked DONTNEED

- madvise-purgeable-per-vma-protection: One VMA marked DONTNEED allows
GPU execution on other VMA; both DONTNEED makes BO purgeable

Tests use xe_vm_madvise_purgeable() for WILLNEED/DONTNEED state management and trigger_memory_pressure() to simulate OOM conditions forcing kernel to reclaim purgeable memory.

Cc Matthew Brost <[email protected]>
Cc Thomas Hellström <[email protected]>
Cc Himal Prasad Ghimiray <[email protected]>
---
 tests/intel/xe_exec_system_allocator.c | 638
+++++++++++++++++++++++++
 1 file changed, 638 insertions(+)
tests/intel/xe_exec_system_allocator.c +82 -0
index 8af66d76e..338037a48 100644
@@ -32,6 +32,15 @@
 #define QUARTER_SEC		(NSEC_PER_SEC / 4)
 #define FIVE_SEC		(5LL * NSEC_PER_SEC)
 
+/* Purgeable test constants */
+#define PURGEABLE_ADDR		0x1a0000
+#define PURGEABLE_ADDR2		0x2b0000
+#define PURGEABLE_BATCH_ADDR	0x3c0000
+#define PURGEABLE_BO_SIZE	4096
+#define PURGEABLE_FENCE_VAL	0xbeef
+#define PURGEABLE_TEST_PATTERN	0xc0ffee
+#define PURGEABLE_DEAD_PATTERN	0xdead
+
 struct test_exec_data {
 	uint32_t batch[32];
 	uint64_t pad;
@@ -2245,6 +2254,599 @@ test_compute(int fd, size_t size, unsigned int
 flags)
 	xe_vm_destroy(fd, vm);
 }
 
+/**
+ * trigger_memory_pressure - Trigger memory pressure for purgeable
+tests
+ * @fd: DRM file descriptor
+ * @vm: VM handle
+ *
+ * Creates temporary BOs exceeding VRAM size (VRAM + 64MB) to trigger
+memory
+ * pressure, forcing kernel to reclaim purgeable BOs in system allocator.
+ */
+static void trigger_memory_pressure(int fd, uint32_t vm) {
+	uint64_t vram_size;
+	const uint64_t chunk = 8ull << 20; /* 8 MiB */
+	int max_objs, n = 0;
+	uint32_t *handles;
+	uint64_t total;
+	void *p;
+	uint32_t bo2;
+
+	vram_size = xe_visible_vram_size(fd, 0);
+	max_objs = vram_size / chunk + 64;
+	handles = calloc(max_objs, sizeof(*handles));
+	igt_assert(handles);
+
+	total = 0;
+	while (total < vram_size + (64 << 20) && n < max_objs) {
+		bo2 = xe_bo_create(fd, vm, chunk, vram_if_possible(fd, 0),
+
 DRM_XE_GEM_CREATE_FLAG_NEEDS_VISIBLE_VRAM);
+		handles[n++] = bo2;
+		total += chunk;
+		p = xe_bo_map(fd, bo2, chunk);
+		memset(p, 0xCD, 4096);
+		munmap(p, chunk);
+	}
+
+	for (int i = 0; i < n; i++)
+		gem_close(fd, handles[i]);
+
+	free(handles);
+}
+
+static jmp_buf jmp;
+
+__noreturn static void sigtrap(int sig) {
+	siglongjmp(jmp, sig);
+}
+
+/**
+ * purgeable_mark_and_verify_purged - Mark BO as DONTNEED and verify
+purge
+ * @fd: DRM file descriptor
+ * @vm: VM handle
+ * @addr: Virtual address of the BO
+ * @size: Size of the BO
+ *
+ * Marks BO as DONTNEED, triggers memory pressure, and verifies purge.
+ * Returns: true if BO was successfully purged, false otherwise  */
+static bool purgeable_mark_and_verify_purged(int fd, uint32_t vm,
+uint64_t addr, size_t size) {
+	uint32_t retained;
+
+	/* Mark as DONTNEED */
+	retained = xe_vm_madvise_purgeable(fd, vm, addr, size,
+
 DRM_XE_VMA_PURGEABLE_STATE_DONTNEED);
+	if (retained != 1)
+		return false;
+
+	/* Trigger memory pressure */
+	trigger_memory_pressure(fd, vm);
+
+	/* Verify purged */
+	retained = xe_vm_madvise_purgeable(fd, vm, addr, size,
+

DRM_XE_VMA_PURGEABLE_STATE_WILLNEED);

tests/intel/xe_exec_system_allocator.c +16 -0
+	return retained == 0;
+}
+
+/**
+ * purgeable_setup_simple_bo - Setup VM and bind a single BO
+ * @fd: DRM file descriptor
+ * @vm: Output VM handle
+ * @bo: Output BO handle
+ * @addr: Virtual address to bind at
+ * @size: Size of the BO
+ * @use_scratch: Whether to use scratch page flag
+ *
+ * Helper to create VM, BO, and bind it at the specified address.
+ */
+static void purgeable_setup_simple_bo(int fd, uint32_t *vm, uint32_t *bo,
+				      uint64_t addr, size_t size, bool

use_scratch) {

tests/intel/xe_exec_system_allocator.c +8 -0
+	struct drm_xe_sync sync = {
+		.type = DRM_XE_SYNC_TYPE_USER_FENCE,
+		.flags = DRM_XE_SYNC_FLAG_SIGNAL,
+		.timeline_value = 1,
+	};
+	uint64_t sync_val = 0;
+
+	*vm = xe_vm_create(fd, use_scratch ?

DRM_XE_VM_CREATE_FLAG_SCRATCH_PAGE : 0, 0);

tests/intel/xe_exec_system_allocator.c +24 -0
+	*bo = xe_bo_create(fd, *vm, size, vram_if_possible(fd, 0), 0);
+
+	sync.addr = to_user_pointer(&sync_val);
+	xe_vm_bind_async(fd, *vm, 0, *bo, 0, addr, size, &sync, 1);
+	xe_wait_ufence(fd, &sync_val, 1, 0, NSEC_PER_SEC); }
+
+/**
+ * purgeable_setup_batch_and_data - Setup VM with batch and data BOs
+for GPU exec
+ * @fd: DRM file descriptor
+ * @vm: Output VM handle
+ * @bind_engine: Output bind engine handle
+ * @batch_bo: Output batch BO handle
+ * @data_bo: Output data BO handle
+ * @batch: Output batch buffer pointer
+ * @data: Output data buffer pointer
+ * @batch_addr: Batch virtual address
+ * @data_addr: Data virtual address
+ * @batch_size: Batch buffer size
+ * @data_size: Data buffer size
+ *
+ * Helper to create VM, bind engine, batch and data BOs, and bind them.
+ */
+static void purgeable_setup_batch_and_data(int fd, uint32_t *vm, uint32_t

*bind_engine,

tests/intel/xe_exec_system_allocator.c +1 -0
+					    uint32_t *batch_bo, uint32_t

*data_bo,

tests/intel/xe_exec_system_allocator.c +2 -0
+					    uint32_t **batch, uint32_t **data,
+					    uint64_t batch_addr, uint64_t

data_addr,

tests/intel/xe_exec_system_allocator.c +9 -0
+					    size_t batch_size, size_t data_size) {
+	struct drm_xe_sync sync = {
+		.type = DRM_XE_SYNC_TYPE_USER_FENCE,
+		.flags = DRM_XE_SYNC_FLAG_SIGNAL,
+		.timeline_value = PURGEABLE_FENCE_VAL,
+	};
+	uint64_t vm_sync = 0;
+
+	*vm = xe_vm_create(fd, DRM_XE_VM_CREATE_FLAG_SCRATCH_PAGE,

0);

tests/intel/xe_exec_system_allocator.c +4 -0
+	*bind_engine = xe_bind_exec_queue_create(fd, *vm, 0);
+
+	/* Create and bind batch BO */
+	*batch_bo = xe_bo_create(fd, *vm, batch_size, vram_if_possible(fd,

0),
+
DRM_XE_GEM_CREATE_FLAG_NEEDS_VISIBLE_VRAM);

tests/intel/xe_exec_system_allocator.c +4 -0
+	*batch = xe_bo_map(fd, *batch_bo, batch_size);
+
+	sync.addr = to_user_pointer(&vm_sync);
+	xe_vm_bind_async(fd, *vm, *bind_engine, *batch_bo, 0, batch_addr,

batch_size, &sync, 1);

tests/intel/xe_exec_system_allocator.c +1 -0
+	xe_wait_ufence(fd, &vm_sync, PURGEABLE_FENCE_VAL, 0,

NSEC_PER_SEC);

tests/intel/xe_exec_system_allocator.c +4 -0
+
+	/* Create and bind data BO */
+	*data_bo = xe_bo_create(fd, *vm, data_size, vram_if_possible(fd, 0),
+
	DRM_XE_GEM_CREATE_FLAG_NEEDS_VISIBLE_VRAM);
tests/intel/xe_exec_system_allocator.c +4 -0
+	*data = xe_bo_map(fd, *data_bo, data_size);
+
+	vm_sync = 0;
+	xe_vm_bind_async(fd, *vm, *bind_engine, *data_bo, 0, data_addr,

data_size, &sync, 1);

tests/intel/xe_exec_system_allocator.c +1 -0
+	xe_wait_ufence(fd, &vm_sync, PURGEABLE_FENCE_VAL, 0,

NSEC_PER_SEC); }

tests/intel/xe_exec_system_allocator.c +3 -0
+
+/**
+ * purgeable_setup_two_vms_shared_bo - Setup two VMs with one shared

BO
+ * @fd: DRM file descriptor
+ * @vm1: Output first VM handle
+ * @vm2: Output second VM handle
+ * @bo: Output shared BO handle
+ * @addr1: Virtual address in VM1
+ * @addr2: Virtual address in VM2
+ * @size: Size of the BO
+ * @use_scratch: Whether to use scratch page flag for VMs
+ *
+ * Helper to create two VMs and bind one shared BO in both VMs.
+ * Returns mapped pointer to the BO.
+ */
+static void *purgeable_setup_two_vms_shared_bo(int fd, uint32_t *vm1, uint32_t *vm2,

tests/intel/xe_exec_system_allocator.c +1 -0
+						uint32_t *bo, uint64_t addr1,

uint64_t addr2,

tests/intel/xe_exec_system_allocator.c +12 -0
+						size_t size, bool use_scratch)
+{
+	struct drm_xe_sync sync = {
+		.type = DRM_XE_SYNC_TYPE_USER_FENCE,
+		.flags = DRM_XE_SYNC_FLAG_SIGNAL,
+		.timeline_value = 1,
+	};
+	uint64_t sync_val = 0;
+	void *map;
+
+	/* Create two VMs */
+	*vm1 = xe_vm_create(fd, use_scratch ?

DRM_XE_VM_CREATE_FLAG_SCRATCH_PAGE : 0, 0);

tests/intel/xe_exec_system_allocator.c +6 -0
+	*vm2 = xe_vm_create(fd, use_scratch ?
+DRM_XE_VM_CREATE_FLAG_SCRATCH_PAGE : 0, 0);
+
+	/* Create shared BO */
+	*bo = xe_bo_create(fd, 0, size, vram_if_possible(fd, 0),
+

DRM_XE_GEM_CREATE_FLAG_NEEDS_VISIBLE_VRAM);

tests/intel/xe_exec_system_allocator.c +37 -0
+
+	map = xe_bo_map(fd, *bo, size);
+	memset(map, 0xAB, size);
+
+	/* Bind BO in VM1 */
+	sync.addr = to_user_pointer(&sync_val);
+	sync_val = 0;
+	xe_vm_bind_async(fd, *vm1, 0, *bo, 0, addr1, size, &sync, 1);
+	xe_wait_ufence(fd, &sync_val, 1, 0, NSEC_PER_SEC);
+
+	/* Bind BO in VM2 */
+	sync_val = 0;
+	xe_vm_bind_async(fd, *vm2, 0, *bo, 0, addr2, size, &sync, 1);
+	xe_wait_ufence(fd, &sync_val, 1, 0, NSEC_PER_SEC);
+
+	return map;
+}
+
+/**
+ * SUBTEST: madvise-purgeable-dontneed-before-mmap
+ * Description: Test marking memory as DONTNEED before mmap access in
+system allocator
+ * Test category: functionality test
+ */
+static void test_dontneed_before_mmap_madvise(int fd, struct
+drm_xe_engine_class_instance *hwe) {
+	uint32_t bo, vm;
+	uint64_t addr = PURGEABLE_ADDR;
+	size_t bo_size = PURGEABLE_BO_SIZE;
+	void *map;
+
+	purgeable_setup_simple_bo(fd, &vm, &bo, addr, bo_size, false);
+	if (!purgeable_mark_and_verify_purged(fd, vm, addr, bo_size))
+		igt_skip("Unable to induce purge on this platform/config");
+
+	/* Try to mmap - should fail on purged BO */
+	map = __gem_mmap__device_coherent(fd, bo, 0, bo_size,

PROT_READ | PROT_WRITE);

tests/intel/xe_exec_system_allocator.c test_compute(int fd, size_t size, unsigned int flags) · line 2485

Quoted 4 lines
tests/intel/xe_exec_system_allocator.c +4 -0
+	igt_assert_f(map == NULL, "mmap should fail on purged BO");
+	igt_assert_f(errno == EINVAL || errno == EFAULT,
+		     "Expected EINVAL or EFAULT, got errno=%d\n", errno);
+

It will be good if SIGBUS will be handled if mmap is not NULL, please refer gem_madvise.

Quoted 57 lines
tests/intel/xe_exec_system_allocator.c +40 -0
+	gem_close(fd, bo);
+	xe_vm_destroy(fd, vm);
+}
+
+/**
+ * SUBTEST: madvise-purgeable-dontneed-after-mmap
+ * Description: Test marking memory as DONTNEED after mmap in system
+allocator
+ * Test category: functionality test
+ */
+static void test_dontneed_after_mmap_madvise(int fd, struct
+drm_xe_engine_class_instance *hwe) {
+	uint32_t bo, vm;
+	uint64_t addr = PURGEABLE_ADDR;
+	size_t bo_size = PURGEABLE_BO_SIZE;
+	void *map;
+
+	purgeable_setup_simple_bo(fd, &vm, &bo, addr, bo_size, true);
+
+	map = xe_bo_map(fd, bo, bo_size);
+	memset(map, 0xAB, bo_size);
+
+	if (!purgeable_mark_and_verify_purged(fd, vm, addr, bo_size))
+		igt_skip("Unable to induce purge on this platform/config");
+
+	/* Access purged mapping - should trigger SIGBUS/SIGSEGV */
+	{
+		sighandler_t old_sigsegv, old_sigbus;
+		char *ptr = (char *)map;
+		int sig;
+
+		old_sigsegv = signal(SIGSEGV, (__sighandler_t)sigtrap);
+		old_sigbus = signal(SIGBUS, (__sighandler_t)sigtrap);
+
+		sig = sigsetjmp(jmp, SIGBUS | SIGSEGV);
+		if (sig == SIGBUS || sig == SIGSEGV) {
+			/* Expected - purged mapping access failed */
+		} else if (sig == 0) {
+			*ptr = 0;
+			igt_assert_f(false, "Access to purged mapping should

trigger signal\n");

tests/intel/xe_exec_system_allocator.c +16 -0
+		} else {
+			igt_assert_f(false, "unexpected signal %d\n", sig);
+		}
+
+		signal(SIGBUS, old_sigbus);
+		signal(SIGSEGV, old_sigsegv);
+	}
+
+	munmap(map, bo_size);
+	gem_close(fd, bo);
+	xe_vm_destroy(fd, vm);
+}
+
+/**
+ * SUBTEST: madvise-purgeable-dontneed-before-exec
+ * Description: Test marking memory as DONTNEED before GPU exec in

tests/intel/xe_exec_system_allocator.c test_compute(int fd, size_t size, unsigned int flags) · line 2549

Quoted 10 lines
tests/intel/xe_exec_system_allocator.c +10 -0
+system allocator
+ * Test category: functionality test
+ */
+static void test_dontneed_before_exec_madvise(int fd, struct
+drm_xe_engine_class_instance *hwe) {
+	uint32_t vm, exec_queue, bo, batch_bo, bind_engine;
+	uint64_t data_addr = 0x1a0000;
+	uint64_t batch_addr = 0x2a0000;
+	size_t data_size = 4096;
+	size_t batch_size = 4096;

Uses hardcoded values instead of defined constants.

Quoted 21 lines
tests/intel/xe_exec_system_allocator.c +15 -0
+	struct drm_xe_sync sync[1] = {
+		{ .type = DRM_XE_SYNC_TYPE_USER_FENCE,
+		  .flags = DRM_XE_SYNC_FLAG_SIGNAL,
+		  .timeline_value = 0xbeef },
+	};
+	struct drm_xe_exec exec = {
+		.num_batch_buffer = 1,
+		.num_syncs = 1,
+		.syncs = to_user_pointer(sync),
+	};
+	uint32_t *data, *batch;
+	uint64_t vm_sync = 0;
+	int b, ret;
+
+	purgeable_setup_batch_and_data(fd, &vm, &bind_engine,

&batch_bo, &bo,

tests/intel/xe_exec_system_allocator.c +1 -0
+					&batch, &data, batch_addr,

data_addr,

tests/intel/xe_exec_system_allocator.c +3 -0
+					batch_size, data_size);
+
+	/* Prepare batch */

tests/intel/xe_exec_system_allocator.c test_compute(int fd, size_t size, unsigned int flags) · line 2577

Quoted 10 lines
tests/intel/xe_exec_system_allocator.c +10 -0
+	b = 0;
+	batch[b++] = MI_STORE_DWORD_IMM_GEN4;
+	batch[b++] = data_addr;
+	batch[b++] = data_addr >> 32;
+	batch[b++] = PURGEABLE_DEAD_PATTERN;
+	batch[b++] = MI_BATCH_BUFFER_END;
+
+	igt_assert(purgeable_mark_and_verify_purged(fd, vm, data_addr,
+data_size));
+

Only the data BO is purged, not the batch BO can you cover the batch bo purge test also?

tests/intel/xe_exec_system_allocator.c test_compute(int fd, size_t size, unsigned int flags) · line 2586

Quoted 10 lines
tests/intel/xe_exec_system_allocator.c +9 -0
+	/* Try to execute - should fail or cause GPU fault */
+	exec_queue = xe_exec_queue_create(fd, vm, hwe, 0);
+	exec.exec_queue_id = exec_queue;
+	exec.address = batch_addr;
+
 
+	vm_sync = 0;
+	sync[0].addr = to_user_pointer(&vm_sync);
+
+	ret = __xe_exec(fd, &exec);

Exec on purged BO should fail. But here its returning 0 mean its success correct ?

Quoted 8 lines
tests/intel/xe_exec_system_allocator.c +4 -0
+	if (ret == 0) {
+		int64_t timeout = NSEC_PER_SEC;
+
+		__xe_wait_ufence(fd, &vm_sync, 0xbeef, exec_queue,

&timeout);

tests/intel/xe_exec_system_allocator.c +1 -0
+		/* Wait may succeed (NULL rebind) or fail (purged) - both

acceptable */

tests/intel/xe_exec_system_allocator.c +1 -0
+	}

tests/intel/xe_exec_system_allocator.c test_compute(int fd, size_t size, unsigned int flags) · line 2602

Quoted 10 lines
tests/intel/xe_exec_system_allocator.c +10 -0
+
+	munmap(data, data_size);
+	munmap(batch, batch_size);
+	gem_close(fd, bo);
+	gem_close(fd, batch_bo);
+	xe_exec_queue_destroy(fd, bind_engine);
+	xe_exec_queue_destroy(fd, exec_queue);
+	xe_vm_destroy(fd, vm);
+}
+

can you also cover these cases.
suggest to add dma-bufs use case also does dma-bufs can be purgeable or not?
that once Bo purged, BO cannot transition back to WILLNEED
--Pravalika

Quoted 315 lines
tests/intel/xe_exec_system_allocator.c +30 -0
+/**
+ * SUBTEST: madvise-purgeable-dontneed-after-exec
+ * Description: Test marking memory as DONTNEED after successful GPU
+exec
+ * Test category: functionality test
+ */
+static void test_dontneed_after_exec_madvise(int fd, struct
+drm_xe_engine_class_instance *hwe) {
+	uint32_t vm, exec_queue, bo, batch_bo, bind_engine;
+	uint64_t data_addr = 0x1a0000;
+	uint64_t batch_addr = 0x2a0000;
+	size_t data_size = 4096;
+	size_t batch_size = 4096;
+	struct drm_xe_sync sync[2] = {
+		{ .type = DRM_XE_SYNC_TYPE_USER_FENCE,
+		  .flags = DRM_XE_SYNC_FLAG_SIGNAL,
+		  .timeline_value = 0xbeef },
+		{ .type = DRM_XE_SYNC_TYPE_SYNCOBJ,
+		  .flags = DRM_XE_SYNC_FLAG_SIGNAL },
+	};
+	struct drm_xe_exec exec = {
+		.num_batch_buffer = 1,
+		.num_syncs = 2,
+		.syncs = to_user_pointer(sync),
+	};
+	uint32_t *data, *batch;
+	uint32_t syncobj;
+	int b, ret;
+
+	purgeable_setup_batch_and_data(fd, &vm, &bind_engine,

&batch_bo, &bo,

tests/intel/xe_exec_system_allocator.c +1 -0
+					&batch, &data, batch_addr,

data_addr,

tests/intel/xe_exec_system_allocator.c +44 -0
+					batch_size, data_size);
+	memset(data, 0, data_size);
+
+	syncobj = syncobj_create(fd, 0);
+
+	/* Prepare batch to write to data BO */
+	b = 0;
+	batch[b++] = MI_STORE_DWORD_IMM_GEN4;
+	batch[b++] = data_addr;
+	batch[b++] = data_addr >> 32;
+	batch[b++] = 0xfeed0001;
+	batch[b++] = MI_BATCH_BUFFER_END;
+
+	exec_queue = xe_exec_queue_create(fd, vm, hwe, 0);
+	exec.exec_queue_id = exec_queue;
+	exec.address = batch_addr;
+
+	/* Use only syncobj for exec (not USER_FENCE) */
+	sync[1].handle = syncobj;
+	exec.num_syncs = 1;
+	exec.syncs = to_user_pointer(&sync[1]);
+
+	ret = __xe_exec(fd, &exec);
+	igt_assert_eq(ret, 0);
+
+	igt_assert(syncobj_wait(fd, &syncobj, 1, INT64_MAX, 0, NULL));
+	munmap(data, data_size);
+	data = xe_bo_map(fd, bo, data_size);
+	igt_assert_eq(data[0], 0xfeed0001);
+
+	igt_assert(purgeable_mark_and_verify_purged(fd, vm, data_addr,
+data_size));
+
+	/* Prepare second batch (different value) */
+	b = 0;
+	batch[b++] = MI_STORE_DWORD_IMM_GEN4;
+	batch[b++] = data_addr;
+	batch[b++] = data_addr >> 32;
+	batch[b++] = 0xfeed0002;
+	batch[b++] = MI_BATCH_BUFFER_END;
+
+	ret = __xe_exec(fd, &exec);
+	if (ret == 0) {
+		/* Exec succeeded, but wait may fail on purged BO (both

behaviors valid) */

tests/intel/xe_exec_system_allocator.c +29 -0
+		syncobj_wait(fd, &syncobj, 1, INT64_MAX, 0, NULL);
+	}
+
+	munmap(data, data_size);
+	munmap(batch, batch_size);
+	gem_close(fd, bo);
+	gem_close(fd, batch_bo);
+	syncobj_destroy(fd, syncobj);
+	xe_exec_queue_destroy(fd, bind_engine);
+	xe_exec_queue_destroy(fd, exec_queue);
+	xe_vm_destroy(fd, vm);
+}
+
+/**
+ * SUBTEST: madvise-purgeable-per-vma-tracking
+ * Description: Test per-VMA purgeable state tracking with multiple VMs
+ * Test category: functionality test
+ */
+static void test_per_vma_tracking_madvise(int fd, struct
+drm_xe_engine_class_instance *hwe) {
+	uint32_t bo, vm1, vm2;
+	uint64_t addr1 = PURGEABLE_ADDR;
+	uint64_t addr2 = PURGEABLE_ADDR2;
+	size_t bo_size = PURGEABLE_BO_SIZE;
+	uint32_t retained;
+	void *map;
+
+	map = purgeable_setup_two_vms_shared_bo(fd, &vm1, &vm2, &bo,
+							addr1, addr2,

bo_size, false);

tests/intel/xe_exec_system_allocator.c +4 -0
+
+	/* Mark VMA1 as DONTNEED */
+	retained = xe_vm_madvise_purgeable(fd, vm1, addr1, bo_size,
+

DRM_XE_VMA_PURGEABLE_STATE_DONTNEED);

tests/intel/xe_exec_system_allocator.c +5 -0
+	igt_assert_eq(retained, 1);
+
+	/* Verify BO NOT purgeable (VMA2 still WILLNEED) */
+	retained = xe_vm_madvise_purgeable(fd, vm1, addr1, bo_size,
+

DRM_XE_VMA_PURGEABLE_STATE_WILLNEED);

tests/intel/xe_exec_system_allocator.c +5 -0
+	igt_assert_eq(retained, 1);
+
+	/* Mark both VMAs as DONTNEED */
+	retained = xe_vm_madvise_purgeable(fd, vm1, addr1, bo_size,
+

DRM_XE_VMA_PURGEABLE_STATE_DONTNEED);

tests/intel/xe_exec_system_allocator.c +4 -0
+	igt_assert_eq(retained, 1);
+
+	retained = xe_vm_madvise_purgeable(fd, vm2, addr2, bo_size,
+

DRM_XE_VMA_PURGEABLE_STATE_DONTNEED);

tests/intel/xe_exec_system_allocator.c +7 -0
+	igt_assert_eq(retained, 1);
+
+	/* Trigger pressure and verify BO was purged */
+	trigger_memory_pressure(fd, vm1);
+
+	retained = xe_vm_madvise_purgeable(fd, vm1, addr1, bo_size,
+

DRM_XE_VMA_PURGEABLE_STATE_WILLNEED);

tests/intel/xe_exec_system_allocator.c +41 -0
+	igt_assert_eq(retained, 0);
+
+	munmap(map, bo_size);
+	gem_close(fd, bo);
+	xe_vm_destroy(fd, vm1);
+	xe_vm_destroy(fd, vm2);
+}
+
+/**
+ * SUBTEST: madvise-purgeable-per-vma-protection
+ * Description: Test per-VMA protection from purging with GPU workload
+ * Test category: functionality test
+ */
+static void test_per_vma_protection_madvise(int fd, struct
+drm_xe_engine_class_instance *hwe) {
+	uint32_t vm1, vm2, exec_queue, bo, batch_bo, bind_engine;
+	uint64_t data_addr1 = PURGEABLE_ADDR;
+	uint64_t data_addr2 = PURGEABLE_ADDR2;
+	uint64_t batch_addr = PURGEABLE_BATCH_ADDR;
+	size_t data_size = PURGEABLE_BO_SIZE;
+	size_t batch_size = PURGEABLE_BO_SIZE;
+	struct drm_xe_sync sync[2] = {
+		{ .type = DRM_XE_SYNC_TYPE_USER_FENCE,
+		  .flags = DRM_XE_SYNC_FLAG_SIGNAL,
+		  .timeline_value = PURGEABLE_FENCE_VAL },
+		{ .type = DRM_XE_SYNC_TYPE_SYNCOBJ,
+		  .flags = DRM_XE_SYNC_FLAG_SIGNAL },
+	};
+	struct drm_xe_exec exec = {
+		.num_batch_buffer = 1,
+		.num_syncs = 1,
+		.syncs = to_user_pointer(&sync[1]),
+	};
+	uint32_t *data, *batch;
+	uint64_t vm_sync = 0;
+	uint32_t retained, syncobj;
+	int b, ret;
+
+	/* Create two VMs and bind shared data BO */
+	data = purgeable_setup_two_vms_shared_bo(fd, &vm1, &vm2, &bo,
+							 data_addr1,

data_addr2, data_size, true);

tests/intel/xe_exec_system_allocator.c +6 -0
+	memset(data, 0, data_size);
+	bind_engine = xe_bind_exec_queue_create(fd, vm2, 0);
+
+	/* Create and bind batch BO in VM2 */
+	batch_bo = xe_bo_create(fd, vm2, batch_size, vram_if_possible(fd, 0),
+
	DRM_XE_GEM_CREATE_FLAG_NEEDS_VISIBLE_VRAM);
tests/intel/xe_exec_system_allocator.c +5 -0
+	batch = xe_bo_map(fd, batch_bo, batch_size);
+
+	sync[0].addr = to_user_pointer(&vm_sync);
+	vm_sync = 0;
+	xe_vm_bind_async(fd, vm2, bind_engine, batch_bo, 0, batch_addr,

batch_size, sync, 1);

tests/intel/xe_exec_system_allocator.c +1 -0
+	xe_wait_ufence(fd, &vm_sync, PURGEABLE_FENCE_VAL, 0,

NSEC_PER_SEC);

tests/intel/xe_exec_system_allocator.c +4 -0
+
+	/* Mark VMA1 as DONTNEED, VMA2 stays WILLNEED */
+	retained = xe_vm_madvise_purgeable(fd, vm1, data_addr1, data_size,
+

DRM_XE_VMA_PURGEABLE_STATE_DONTNEED);

tests/intel/xe_exec_system_allocator.c +7 -0
+	igt_assert_eq(retained, 1);
+
+	/* Trigger pressure - BO should survive (VMA2 protects) */
+	trigger_memory_pressure(fd, vm1);
+
+	retained = xe_vm_madvise_purgeable(fd, vm2, data_addr2, data_size,
+

DRM_XE_VMA_PURGEABLE_STATE_WILLNEED);

tests/intel/xe_exec_system_allocator.c +27 -0
+	igt_assert_eq(retained, 1);
+
+	/* GPU workload - should succeed */
+	b = 0;
+	batch[b++] = MI_STORE_DWORD_IMM_GEN4;
+	batch[b++] = data_addr2;
+	batch[b++] = data_addr2 >> 32;
+	batch[b++] = PURGEABLE_TEST_PATTERN;
+	batch[b++] = MI_BATCH_BUFFER_END;
+
+	syncobj = syncobj_create(fd, 0);
+	sync[1].handle = syncobj;
+	exec_queue = xe_exec_queue_create(fd, vm2, hwe, 0);
+	exec.exec_queue_id = exec_queue;
+	exec.address = batch_addr;
+
+	ret = __xe_exec(fd, &exec);
+	igt_assert_eq(ret, 0);
+	igt_assert(syncobj_wait(fd, &syncobj, 1, INT64_MAX, 0, NULL));
+
+	munmap(data, data_size);
+	data = xe_bo_map(fd, bo, data_size);
+	igt_assert_eq(data[0], PURGEABLE_TEST_PATTERN);
+
+	/* Mark both VMAs DONTNEED */
+	retained = xe_vm_madvise_purgeable(fd, vm2, data_addr2, data_size,
+

DRM_XE_VMA_PURGEABLE_STATE_DONTNEED);

tests/intel/xe_exec_system_allocator.c +7 -0
+	igt_assert_eq(retained, 1);
+
+	/* Trigger pressure - BO should be purged */
+	trigger_memory_pressure(fd, vm1);
+
+	retained = xe_vm_madvise_purgeable(fd, vm2, data_addr2, data_size,
+

DRM_XE_VMA_PURGEABLE_STATE_WILLNEED);

tests/intel/xe_exec_system_allocator.c +8 -0
+	igt_assert_eq(retained, 0);
+
+	/* GPU workload - should fail or succeed with NULL rebind */
+	batch[3] = PURGEABLE_DEAD_PATTERN;
+
+	ret = __xe_exec(fd, &exec);
+	/* With SCRATCH_PAGE, kernel may allow exec with NULL rebind.
+	 * Without it, exec should fail with -EIO/-EFAULT or wait should

timeout.

tests/intel/xe_exec_system_allocator.c +50 -1
+	 * Both behaviors are valid depending on kernel support.
+	 */
+
+	munmap(data, data_size);
+	munmap(batch, batch_size);
+	gem_close(fd, bo);
+	gem_close(fd, batch_bo);
+	syncobj_destroy(fd, syncobj);
+	xe_exec_queue_destroy(fd, bind_engine);
+	xe_exec_queue_destroy(fd, exec_queue);
+	xe_vm_destroy(fd, vm1);
+	xe_vm_destroy(fd, vm2);
+}
+
 struct section {
 	const char *name;
 	unsigned long long flags;
@@ -2649,6 +3251,42 @@ int igt_main()
 			test_compute(fd, SZ_2M, s->flags);
 	}
 
+	igt_subtest("madvise-purgeable-dontneed-before-mmap")
+		xe_for_each_engine(fd, hwe) {
+			test_dontneed_before_mmap_madvise(fd, hwe);
+			break;
+		}
+
+	igt_subtest("madvise-purgeable-dontneed-after-mmap")
+		xe_for_each_engine(fd, hwe) {
+			test_dontneed_after_mmap_madvise(fd, hwe);
+			break;
+		}
+
+	igt_subtest("madvise-purgeable-dontneed-before-exec")
+		xe_for_each_engine(fd, hwe) {
+			test_dontneed_before_exec_madvise(fd, hwe);
+			break;
+		}
+
+	igt_subtest("madvise-purgeable-dontneed-after-exec")
+		xe_for_each_engine(fd, hwe) {
+			test_dontneed_after_exec_madvise(fd, hwe);
+			break;
+		}
+
+	igt_subtest("madvise-purgeable-per-vma-tracking")
+		xe_for_each_engine(fd, hwe) {
+			test_per_vma_tracking_madvise(fd, hwe);
+			break;
+		}
+
+	igt_subtest("madvise-purgeable-per-vma-protection")
+		xe_for_each_engine(fd, hwe) {
+			test_per_vma_protection_madvise(fd, hwe);
+			break;
+		}
+
 	igt_fixture() {
 		xe_device_put(fd);
 		drm_close_driver(fd);
--

2.43.0

#9 lore raw

Re: [PATCH i-g-t 3/3] tests/intel/xe_exec_system_allocator: Add purgeable memory madvise tests

Quoted 318 lines · Pravalika
Quoted 318 lines

-----Original Message-----
From: Yadav, Arvind <[email protected]>
Sent: Tuesday, 20 January, 2026 11:42 AM
To: [email protected]
Cc: Brost, Matthew <[email protected]>; Ghimiray, Himal Prasad <[email protected]>; [email protected]; Sharma, Nishit <[email protected]>; Gurram, Pravalika <[email protected]>
Subject: [PATCH i-g-t 3/3] tests/intel/xe_exec_system_allocator: Add purgeable memory madvise tests

Add six purgeable memory test cases for system allocator using madvise:

- madvise-purgeable-dontneed-before-mmap: Mark BO as DONTNEED before mmap,
verify mmap fails on purged memory

- madvise-purgeable-dontneed-after-mmap: Mark BO as DONTNEED after mmap,
verify SIGBUS/SIGSEGV on accessing purged mapping

- madvise-purgeable-dontneed-before-exec: Mark BO as DONTNEED before GPU
execution, verify GPU behavior on purged memory with SCRATCH_PAGE VMs

- madvise-purgeable-dontneed-after-exec: Mark BO as DONTNEED after GPU execution, verify previously-used memory becomes inaccessible

- madvise-purgeable-per-vma-tracking: One BO mapped in two VMs becomes purgeable only when BOTH VMAs are marked DONTNEED

- madvise-purgeable-per-vma-protection: One VMA marked DONTNEED allows
GPU execution on other VMA; both DONTNEED makes BO purgeable

Tests use xe_vm_madvise_purgeable() for WILLNEED/DONTNEED state management and trigger_memory_pressure() to simulate OOM conditions forcing kernel to reclaim purgeable memory.

Cc Matthew Brost <[email protected]>
Cc Thomas Hellström <[email protected]>
Cc Himal Prasad Ghimiray <[email protected]>
---
  tests/intel/xe_exec_system_allocator.c | 638
+++++++++++++++++++++++++
  1 file changed, 638 insertions(+)
tests/intel/xe_exec_system_allocator.c +82 -0
index 8af66d76e..338037a48 100644
@@ -32,6 +32,15 @@
  #define QUARTER_SEC		(NSEC_PER_SEC / 4)
  #define FIVE_SEC		(5LL * NSEC_PER_SEC)
 
+/* Purgeable test constants */
+#define PURGEABLE_ADDR		0x1a0000
+#define PURGEABLE_ADDR2		0x2b0000
+#define PURGEABLE_BATCH_ADDR	0x3c0000
+#define PURGEABLE_BO_SIZE	4096
+#define PURGEABLE_FENCE_VAL	0xbeef
+#define PURGEABLE_TEST_PATTERN	0xc0ffee
+#define PURGEABLE_DEAD_PATTERN	0xdead
+
  struct test_exec_data {
  	uint32_t batch[32];
  	uint64_t pad;
@@ -2245,6 +2254,599 @@ test_compute(int fd, size_t size, unsigned int
 flags)
  	xe_vm_destroy(fd, vm);
  }
 
+/**
+ * trigger_memory_pressure - Trigger memory pressure for purgeable
+tests
+ * @fd: DRM file descriptor
+ * @vm: VM handle
+ *
+ * Creates temporary BOs exceeding VRAM size (VRAM + 64MB) to trigger
+memory
+ * pressure, forcing kernel to reclaim purgeable BOs in system allocator.
+ */
+static void trigger_memory_pressure(int fd, uint32_t vm) {
+	uint64_t vram_size;
+	const uint64_t chunk = 8ull << 20; /* 8 MiB */
+	int max_objs, n = 0;
+	uint32_t *handles;
+	uint64_t total;
+	void *p;
+	uint32_t bo2;
+
+	vram_size = xe_visible_vram_size(fd, 0);
+	max_objs = vram_size / chunk + 64;
+	handles = calloc(max_objs, sizeof(*handles));
+	igt_assert(handles);
+
+	total = 0;
+	while (total < vram_size + (64 << 20) && n < max_objs) {
+		bo2 = xe_bo_create(fd, vm, chunk, vram_if_possible(fd, 0),
+
 DRM_XE_GEM_CREATE_FLAG_NEEDS_VISIBLE_VRAM);
+		handles[n++] = bo2;
+		total += chunk;
+		p = xe_bo_map(fd, bo2, chunk);
+		memset(p, 0xCD, 4096);
+		munmap(p, chunk);
+	}
+
+	for (int i = 0; i < n; i++)
+		gem_close(fd, handles[i]);
+
+	free(handles);
+}
+
+static jmp_buf jmp;
+
+__noreturn static void sigtrap(int sig) {
+	siglongjmp(jmp, sig);
+}
+
+/**
+ * purgeable_mark_and_verify_purged - Mark BO as DONTNEED and verify
+purge
+ * @fd: DRM file descriptor
+ * @vm: VM handle
+ * @addr: Virtual address of the BO
+ * @size: Size of the BO
+ *
+ * Marks BO as DONTNEED, triggers memory pressure, and verifies purge.
+ * Returns: true if BO was successfully purged, false otherwise  */
+static bool purgeable_mark_and_verify_purged(int fd, uint32_t vm,
+uint64_t addr, size_t size) {
+	uint32_t retained;
+
+	/* Mark as DONTNEED */
+	retained = xe_vm_madvise_purgeable(fd, vm, addr, size,
+
 DRM_XE_VMA_PURGEABLE_STATE_DONTNEED);
+	if (retained != 1)
+		return false;
+
+	/* Trigger memory pressure */
+	trigger_memory_pressure(fd, vm);
+
+	/* Verify purged */
+	retained = xe_vm_madvise_purgeable(fd, vm, addr, size,
+

DRM_XE_VMA_PURGEABLE_STATE_WILLNEED);

tests/intel/xe_exec_system_allocator.c +16 -0
+	return retained == 0;
+}
+
+/**
+ * purgeable_setup_simple_bo - Setup VM and bind a single BO
+ * @fd: DRM file descriptor
+ * @vm: Output VM handle
+ * @bo: Output BO handle
+ * @addr: Virtual address to bind at
+ * @size: Size of the BO
+ * @use_scratch: Whether to use scratch page flag
+ *
+ * Helper to create VM, BO, and bind it at the specified address.
+ */
+static void purgeable_setup_simple_bo(int fd, uint32_t *vm, uint32_t *bo,
+				      uint64_t addr, size_t size, bool

use_scratch) {

tests/intel/xe_exec_system_allocator.c +8 -0
+	struct drm_xe_sync sync = {
+		.type = DRM_XE_SYNC_TYPE_USER_FENCE,
+		.flags = DRM_XE_SYNC_FLAG_SIGNAL,
+		.timeline_value = 1,
+	};
+	uint64_t sync_val = 0;
+
+	*vm = xe_vm_create(fd, use_scratch ?

DRM_XE_VM_CREATE_FLAG_SCRATCH_PAGE : 0, 0);

tests/intel/xe_exec_system_allocator.c +24 -0
+	*bo = xe_bo_create(fd, *vm, size, vram_if_possible(fd, 0), 0);
+
+	sync.addr = to_user_pointer(&sync_val);
+	xe_vm_bind_async(fd, *vm, 0, *bo, 0, addr, size, &sync, 1);
+	xe_wait_ufence(fd, &sync_val, 1, 0, NSEC_PER_SEC); }
+
+/**
+ * purgeable_setup_batch_and_data - Setup VM with batch and data BOs
+for GPU exec
+ * @fd: DRM file descriptor
+ * @vm: Output VM handle
+ * @bind_engine: Output bind engine handle
+ * @batch_bo: Output batch BO handle
+ * @data_bo: Output data BO handle
+ * @batch: Output batch buffer pointer
+ * @data: Output data buffer pointer
+ * @batch_addr: Batch virtual address
+ * @data_addr: Data virtual address
+ * @batch_size: Batch buffer size
+ * @data_size: Data buffer size
+ *
+ * Helper to create VM, bind engine, batch and data BOs, and bind them.
+ */
+static void purgeable_setup_batch_and_data(int fd, uint32_t *vm, uint32_t

*bind_engine,

tests/intel/xe_exec_system_allocator.c +1 -0
+					    uint32_t *batch_bo, uint32_t

*data_bo,

tests/intel/xe_exec_system_allocator.c +2 -0
+					    uint32_t **batch, uint32_t **data,
+					    uint64_t batch_addr, uint64_t

data_addr,

tests/intel/xe_exec_system_allocator.c +9 -0
+					    size_t batch_size, size_t data_size) {
+	struct drm_xe_sync sync = {
+		.type = DRM_XE_SYNC_TYPE_USER_FENCE,
+		.flags = DRM_XE_SYNC_FLAG_SIGNAL,
+		.timeline_value = PURGEABLE_FENCE_VAL,
+	};
+	uint64_t vm_sync = 0;
+
+	*vm = xe_vm_create(fd, DRM_XE_VM_CREATE_FLAG_SCRATCH_PAGE,

0);

tests/intel/xe_exec_system_allocator.c +4 -0
+	*bind_engine = xe_bind_exec_queue_create(fd, *vm, 0);
+
+	/* Create and bind batch BO */
+	*batch_bo = xe_bo_create(fd, *vm, batch_size, vram_if_possible(fd,

0),
+
DRM_XE_GEM_CREATE_FLAG_NEEDS_VISIBLE_VRAM);

tests/intel/xe_exec_system_allocator.c +4 -0
+	*batch = xe_bo_map(fd, *batch_bo, batch_size);
+
+	sync.addr = to_user_pointer(&vm_sync);
+	xe_vm_bind_async(fd, *vm, *bind_engine, *batch_bo, 0, batch_addr,

batch_size, &sync, 1);

tests/intel/xe_exec_system_allocator.c +1 -0
+	xe_wait_ufence(fd, &vm_sync, PURGEABLE_FENCE_VAL, 0,

NSEC_PER_SEC);

tests/intel/xe_exec_system_allocator.c +4 -0
+
+	/* Create and bind data BO */
+	*data_bo = xe_bo_create(fd, *vm, data_size, vram_if_possible(fd, 0),
+
	DRM_XE_GEM_CREATE_FLAG_NEEDS_VISIBLE_VRAM);
tests/intel/xe_exec_system_allocator.c +4 -0
+	*data = xe_bo_map(fd, *data_bo, data_size);
+
+	vm_sync = 0;
+	xe_vm_bind_async(fd, *vm, *bind_engine, *data_bo, 0, data_addr,

data_size, &sync, 1);

tests/intel/xe_exec_system_allocator.c +1 -0
+	xe_wait_ufence(fd, &vm_sync, PURGEABLE_FENCE_VAL, 0,

NSEC_PER_SEC); }

tests/intel/xe_exec_system_allocator.c +3 -0
+
+/**
+ * purgeable_setup_two_vms_shared_bo - Setup two VMs with one shared

BO
+ * @fd: DRM file descriptor
+ * @vm1: Output first VM handle
+ * @vm2: Output second VM handle
+ * @bo: Output shared BO handle
+ * @addr1: Virtual address in VM1
+ * @addr2: Virtual address in VM2
+ * @size: Size of the BO
+ * @use_scratch: Whether to use scratch page flag for VMs
+ *
+ * Helper to create two VMs and bind one shared BO in both VMs.
+ * Returns mapped pointer to the BO.
+ */
+static void *purgeable_setup_two_vms_shared_bo(int fd, uint32_t *vm1, uint32_t *vm2,

tests/intel/xe_exec_system_allocator.c +1 -0
+						uint32_t *bo, uint64_t addr1,

uint64_t addr2,

tests/intel/xe_exec_system_allocator.c +12 -0
+						size_t size, bool use_scratch)
+{
+	struct drm_xe_sync sync = {
+		.type = DRM_XE_SYNC_TYPE_USER_FENCE,
+		.flags = DRM_XE_SYNC_FLAG_SIGNAL,
+		.timeline_value = 1,
+	};
+	uint64_t sync_val = 0;
+	void *map;
+
+	/* Create two VMs */
+	*vm1 = xe_vm_create(fd, use_scratch ?

DRM_XE_VM_CREATE_FLAG_SCRATCH_PAGE : 0, 0);

tests/intel/xe_exec_system_allocator.c +6 -0
+	*vm2 = xe_vm_create(fd, use_scratch ?
+DRM_XE_VM_CREATE_FLAG_SCRATCH_PAGE : 0, 0);
+
+	/* Create shared BO */
+	*bo = xe_bo_create(fd, 0, size, vram_if_possible(fd, 0),
+

DRM_XE_GEM_CREATE_FLAG_NEEDS_VISIBLE_VRAM);

tests/intel/xe_exec_system_allocator.c +35 -0
+
+	map = xe_bo_map(fd, *bo, size);
+	memset(map, 0xAB, size);
+
+	/* Bind BO in VM1 */
+	sync.addr = to_user_pointer(&sync_val);
+	sync_val = 0;
+	xe_vm_bind_async(fd, *vm1, 0, *bo, 0, addr1, size, &sync, 1);
+	xe_wait_ufence(fd, &sync_val, 1, 0, NSEC_PER_SEC);
+
+	/* Bind BO in VM2 */
+	sync_val = 0;
+	xe_vm_bind_async(fd, *vm2, 0, *bo, 0, addr2, size, &sync, 1);
+	xe_wait_ufence(fd, &sync_val, 1, 0, NSEC_PER_SEC);
+
+	return map;
+}
+
+/**
+ * SUBTEST: madvise-purgeable-dontneed-before-mmap
+ * Description: Test marking memory as DONTNEED before mmap access in
+system allocator
+ * Test category: functionality test
+ */
+static void test_dontneed_before_mmap_madvise(int fd, struct
+drm_xe_engine_class_instance *hwe) {
+	uint32_t bo, vm;
+	uint64_t addr = PURGEABLE_ADDR;
+	size_t bo_size = PURGEABLE_BO_SIZE;
+	void *map;
+
+	purgeable_setup_simple_bo(fd, &vm, &bo, addr, bo_size, false);
+	if (!purgeable_mark_and_verify_purged(fd, vm, addr, bo_size))
+		igt_skip("Unable to induce purge on this platform/config");
+
Quoted 8 lines

tests/intel/xe_exec_system_allocator.c test_compute(int fd, size_t size, unsigned int flags) · line 2485

Quoted 7 lines
tests/intel/xe_exec_system_allocator.c +2 -0
+	/* Try to mmap - should fail on purged BO */
+	map = __gem_mmap__device_coherent(fd, bo, 0, bo_size,

PROT_READ | PROT_WRITE);

tests/intel/xe_exec_system_allocator.c +4 -0
+	igt_assert_f(map == NULL, "mmap should fail on purged BO");
+	igt_assert_f(errno == EINVAL || errno == EFAULT,
+		     "Expected EINVAL or EFAULT, got errno=%d\n", errno);
+

It will be good if SIGBUS will be handled if mmap is not NULL, please refer gem_madvise.

Noted,

Quoted 60 lines
Quoted 60 lines
tests/intel/xe_exec_system_allocator.c +40 -0
+	gem_close(fd, bo);
+	xe_vm_destroy(fd, vm);
+}
+
+/**
+ * SUBTEST: madvise-purgeable-dontneed-after-mmap
+ * Description: Test marking memory as DONTNEED after mmap in system
+allocator
+ * Test category: functionality test
+ */
+static void test_dontneed_after_mmap_madvise(int fd, struct
+drm_xe_engine_class_instance *hwe) {
+	uint32_t bo, vm;
+	uint64_t addr = PURGEABLE_ADDR;
+	size_t bo_size = PURGEABLE_BO_SIZE;
+	void *map;
+
+	purgeable_setup_simple_bo(fd, &vm, &bo, addr, bo_size, true);
+
+	map = xe_bo_map(fd, bo, bo_size);
+	memset(map, 0xAB, bo_size);
+
+	if (!purgeable_mark_and_verify_purged(fd, vm, addr, bo_size))
+		igt_skip("Unable to induce purge on this platform/config");
+
+	/* Access purged mapping - should trigger SIGBUS/SIGSEGV */
+	{
+		sighandler_t old_sigsegv, old_sigbus;
+		char *ptr = (char *)map;
+		int sig;
+
+		old_sigsegv = signal(SIGSEGV, (__sighandler_t)sigtrap);
+		old_sigbus = signal(SIGBUS, (__sighandler_t)sigtrap);
+
+		sig = sigsetjmp(jmp, SIGBUS | SIGSEGV);
+		if (sig == SIGBUS || sig == SIGSEGV) {
+			/* Expected - purged mapping access failed */
+		} else if (sig == 0) {
+			*ptr = 0;
+			igt_assert_f(false, "Access to purged mapping should

trigger signal\n");

tests/intel/xe_exec_system_allocator.c +19 -0
+		} else {
+			igt_assert_f(false, "unexpected signal %d\n", sig);
+		}
+
+		signal(SIGBUS, old_sigbus);
+		signal(SIGSEGV, old_sigsegv);
+	}
+
+	munmap(map, bo_size);
+	gem_close(fd, bo);
+	xe_vm_destroy(fd, vm);
+}
+
+/**
+ * SUBTEST: madvise-purgeable-dontneed-before-exec
+ * Description: Test marking memory as DONTNEED before GPU exec in
+system allocator
+ * Test category: functionality test
+ */
Quoted 8 lines

tests/intel/xe_exec_system_allocator.c test_compute(int fd, size_t size, unsigned int flags) · line 2549

Quoted 7 lines
tests/intel/xe_exec_system_allocator.c +7 -0
+static void test_dontneed_before_exec_madvise(int fd, struct
+drm_xe_engine_class_instance *hwe) {
+	uint32_t vm, exec_queue, bo, batch_bo, bind_engine;
+	uint64_t data_addr = 0x1a0000;
+	uint64_t batch_addr = 0x2a0000;
+	size_t data_size = 4096;
+	size_t batch_size = 4096;

Uses hardcoded values instead of defined constants.

Noted,

Quoted 24 lines
Quoted 24 lines
tests/intel/xe_exec_system_allocator.c +15 -0
+	struct drm_xe_sync sync[1] = {
+		{ .type = DRM_XE_SYNC_TYPE_USER_FENCE,
+		  .flags = DRM_XE_SYNC_FLAG_SIGNAL,
+		  .timeline_value = 0xbeef },
+	};
+	struct drm_xe_exec exec = {
+		.num_batch_buffer = 1,
+		.num_syncs = 1,
+		.syncs = to_user_pointer(sync),
+	};
+	uint32_t *data, *batch;
+	uint64_t vm_sync = 0;
+	int b, ret;
+
+	purgeable_setup_batch_and_data(fd, &vm, &bind_engine,

&batch_bo, &bo,

tests/intel/xe_exec_system_allocator.c +1 -0
+					&batch, &data, batch_addr,

data_addr,

tests/intel/xe_exec_system_allocator.c +6 -0
+					batch_size, data_size);
+
+	/* Prepare batch */
+	b = 0;
+	batch[b++] = MI_STORE_DWORD_IMM_GEN4;
+	batch[b++] = data_addr;
Quoted 8 lines

tests/intel/xe_exec_system_allocator.c test_compute(int fd, size_t size, unsigned int flags) · line 2577

Quoted 7 lines
tests/intel/xe_exec_system_allocator.c +7 -0
+	batch[b++] = data_addr >> 32;
+	batch[b++] = PURGEABLE_DEAD_PATTERN;
+	batch[b++] = MI_BATCH_BUFFER_END;
+
+	igt_assert(purgeable_mark_and_verify_purged(fd, vm, data_addr,
+data_size));
+

Only the data BO is purged, not the batch BO can you cover the batch bo purge test also?

This is a negative test case; batch BO purge coverage can be added later.

Quoted 12 lines

tests/intel/xe_exec_system_allocator.c test_compute(int fd, size_t size, unsigned int flags) · line 2586

Quoted 10 lines
tests/intel/xe_exec_system_allocator.c +9 -0
+	/* Try to execute - should fail or cause GPU fault */
+	exec_queue = xe_exec_queue_create(fd, vm, hwe, 0);
+	exec.exec_queue_id = exec_queue;
+	exec.address = batch_addr;
+
+	vm_sync = 0;
+	sync[0].addr = to_user_pointer(&vm_sync);
+
+	ret = __xe_exec(fd, &exec);

Exec on purged BO should fail. But here its returning 0 mean its success correct ?

yes, The exec returning 0 is expected here. The batch BO (containing the MI_STORE_DWORD instructions) is still valid and not purged — only the data BO (the target of the GPU write) is purged.

Quoted 13 lines
Quoted 13 lines
tests/intel/xe_exec_system_allocator.c +4 -0
+	if (ret == 0) {
+		int64_t timeout = NSEC_PER_SEC;
+
+		__xe_wait_ufence(fd, &vm_sync, 0xbeef, exec_queue,

&timeout);

tests/intel/xe_exec_system_allocator.c +1 -0
+		/* Wait may succeed (NULL rebind) or fail (purged) - both

acceptable */

tests/intel/xe_exec_system_allocator.c +6 -0
+	}
+
+	munmap(data, data_size);
+	munmap(batch, batch_size);
+	gem_close(fd, bo);
+	gem_close(fd, batch_bo);
Quoted 8 lines

tests/intel/xe_exec_system_allocator.c test_compute(int fd, size_t size, unsigned int flags) · line 2602

Quoted 5 lines
tests/intel/xe_exec_system_allocator.c +5 -0
+	xe_exec_queue_destroy(fd, bind_engine);
+	xe_exec_queue_destroy(fd, exec_queue);
+	xe_vm_destroy(fd, vm);
+}
+

can you also cover these cases.
suggest to add dma-bufs use case also does dma-bufs can be purgeable or not?
that once Bo purged, BO cannot transition back to WILLNEED

These all  a negative test cases can be added later.

Thanks,
Arvind

Quoted 316 lines

--Pravalika

Quoted 315 lines
tests/intel/xe_exec_system_allocator.c +30 -0
+/**
+ * SUBTEST: madvise-purgeable-dontneed-after-exec
+ * Description: Test marking memory as DONTNEED after successful GPU
+exec
+ * Test category: functionality test
+ */
+static void test_dontneed_after_exec_madvise(int fd, struct
+drm_xe_engine_class_instance *hwe) {
+	uint32_t vm, exec_queue, bo, batch_bo, bind_engine;
+	uint64_t data_addr = 0x1a0000;
+	uint64_t batch_addr = 0x2a0000;
+	size_t data_size = 4096;
+	size_t batch_size = 4096;
+	struct drm_xe_sync sync[2] = {
+		{ .type = DRM_XE_SYNC_TYPE_USER_FENCE,
+		  .flags = DRM_XE_SYNC_FLAG_SIGNAL,
+		  .timeline_value = 0xbeef },
+		{ .type = DRM_XE_SYNC_TYPE_SYNCOBJ,
+		  .flags = DRM_XE_SYNC_FLAG_SIGNAL },
+	};
+	struct drm_xe_exec exec = {
+		.num_batch_buffer = 1,
+		.num_syncs = 2,
+		.syncs = to_user_pointer(sync),
+	};
+	uint32_t *data, *batch;
+	uint32_t syncobj;
+	int b, ret;
+
+	purgeable_setup_batch_and_data(fd, &vm, &bind_engine,

&batch_bo, &bo,

tests/intel/xe_exec_system_allocator.c +1 -0
+					&batch, &data, batch_addr,

data_addr,

tests/intel/xe_exec_system_allocator.c +44 -0
+					batch_size, data_size);
+	memset(data, 0, data_size);
+
+	syncobj = syncobj_create(fd, 0);
+
+	/* Prepare batch to write to data BO */
+	b = 0;
+	batch[b++] = MI_STORE_DWORD_IMM_GEN4;
+	batch[b++] = data_addr;
+	batch[b++] = data_addr >> 32;
+	batch[b++] = 0xfeed0001;
+	batch[b++] = MI_BATCH_BUFFER_END;
+
+	exec_queue = xe_exec_queue_create(fd, vm, hwe, 0);
+	exec.exec_queue_id = exec_queue;
+	exec.address = batch_addr;
+
+	/* Use only syncobj for exec (not USER_FENCE) */
+	sync[1].handle = syncobj;
+	exec.num_syncs = 1;
+	exec.syncs = to_user_pointer(&sync[1]);
+
+	ret = __xe_exec(fd, &exec);
+	igt_assert_eq(ret, 0);
+
+	igt_assert(syncobj_wait(fd, &syncobj, 1, INT64_MAX, 0, NULL));
+	munmap(data, data_size);
+	data = xe_bo_map(fd, bo, data_size);
+	igt_assert_eq(data[0], 0xfeed0001);
+
+	igt_assert(purgeable_mark_and_verify_purged(fd, vm, data_addr,
+data_size));
+
+	/* Prepare second batch (different value) */
+	b = 0;
+	batch[b++] = MI_STORE_DWORD_IMM_GEN4;
+	batch[b++] = data_addr;
+	batch[b++] = data_addr >> 32;
+	batch[b++] = 0xfeed0002;
+	batch[b++] = MI_BATCH_BUFFER_END;
+
+	ret = __xe_exec(fd, &exec);
+	if (ret == 0) {
+		/* Exec succeeded, but wait may fail on purged BO (both

behaviors valid) */

tests/intel/xe_exec_system_allocator.c +29 -0
+		syncobj_wait(fd, &syncobj, 1, INT64_MAX, 0, NULL);
+	}
+
+	munmap(data, data_size);
+	munmap(batch, batch_size);
+	gem_close(fd, bo);
+	gem_close(fd, batch_bo);
+	syncobj_destroy(fd, syncobj);
+	xe_exec_queue_destroy(fd, bind_engine);
+	xe_exec_queue_destroy(fd, exec_queue);
+	xe_vm_destroy(fd, vm);
+}
+
+/**
+ * SUBTEST: madvise-purgeable-per-vma-tracking
+ * Description: Test per-VMA purgeable state tracking with multiple VMs
+ * Test category: functionality test
+ */
+static void test_per_vma_tracking_madvise(int fd, struct
+drm_xe_engine_class_instance *hwe) {
+	uint32_t bo, vm1, vm2;
+	uint64_t addr1 = PURGEABLE_ADDR;
+	uint64_t addr2 = PURGEABLE_ADDR2;
+	size_t bo_size = PURGEABLE_BO_SIZE;
+	uint32_t retained;
+	void *map;
+
+	map = purgeable_setup_two_vms_shared_bo(fd, &vm1, &vm2, &bo,
+							addr1, addr2,

bo_size, false);

tests/intel/xe_exec_system_allocator.c +4 -0
+
+	/* Mark VMA1 as DONTNEED */
+	retained = xe_vm_madvise_purgeable(fd, vm1, addr1, bo_size,
+

DRM_XE_VMA_PURGEABLE_STATE_DONTNEED);

tests/intel/xe_exec_system_allocator.c +5 -0
+	igt_assert_eq(retained, 1);
+
+	/* Verify BO NOT purgeable (VMA2 still WILLNEED) */
+	retained = xe_vm_madvise_purgeable(fd, vm1, addr1, bo_size,
+

DRM_XE_VMA_PURGEABLE_STATE_WILLNEED);

tests/intel/xe_exec_system_allocator.c +5 -0
+	igt_assert_eq(retained, 1);
+
+	/* Mark both VMAs as DONTNEED */
+	retained = xe_vm_madvise_purgeable(fd, vm1, addr1, bo_size,
+

DRM_XE_VMA_PURGEABLE_STATE_DONTNEED);

tests/intel/xe_exec_system_allocator.c +4 -0
+	igt_assert_eq(retained, 1);
+
+	retained = xe_vm_madvise_purgeable(fd, vm2, addr2, bo_size,
+

DRM_XE_VMA_PURGEABLE_STATE_DONTNEED);

tests/intel/xe_exec_system_allocator.c +7 -0
+	igt_assert_eq(retained, 1);
+
+	/* Trigger pressure and verify BO was purged */
+	trigger_memory_pressure(fd, vm1);
+
+	retained = xe_vm_madvise_purgeable(fd, vm1, addr1, bo_size,
+

DRM_XE_VMA_PURGEABLE_STATE_WILLNEED);

tests/intel/xe_exec_system_allocator.c +41 -0
+	igt_assert_eq(retained, 0);
+
+	munmap(map, bo_size);
+	gem_close(fd, bo);
+	xe_vm_destroy(fd, vm1);
+	xe_vm_destroy(fd, vm2);
+}
+
+/**
+ * SUBTEST: madvise-purgeable-per-vma-protection
+ * Description: Test per-VMA protection from purging with GPU workload
+ * Test category: functionality test
+ */
+static void test_per_vma_protection_madvise(int fd, struct
+drm_xe_engine_class_instance *hwe) {
+	uint32_t vm1, vm2, exec_queue, bo, batch_bo, bind_engine;
+	uint64_t data_addr1 = PURGEABLE_ADDR;
+	uint64_t data_addr2 = PURGEABLE_ADDR2;
+	uint64_t batch_addr = PURGEABLE_BATCH_ADDR;
+	size_t data_size = PURGEABLE_BO_SIZE;
+	size_t batch_size = PURGEABLE_BO_SIZE;
+	struct drm_xe_sync sync[2] = {
+		{ .type = DRM_XE_SYNC_TYPE_USER_FENCE,
+		  .flags = DRM_XE_SYNC_FLAG_SIGNAL,
+		  .timeline_value = PURGEABLE_FENCE_VAL },
+		{ .type = DRM_XE_SYNC_TYPE_SYNCOBJ,
+		  .flags = DRM_XE_SYNC_FLAG_SIGNAL },
+	};
+	struct drm_xe_exec exec = {
+		.num_batch_buffer = 1,
+		.num_syncs = 1,
+		.syncs = to_user_pointer(&sync[1]),
+	};
+	uint32_t *data, *batch;
+	uint64_t vm_sync = 0;
+	uint32_t retained, syncobj;
+	int b, ret;
+
+	/* Create two VMs and bind shared data BO */
+	data = purgeable_setup_two_vms_shared_bo(fd, &vm1, &vm2, &bo,
+							 data_addr1,

data_addr2, data_size, true);

tests/intel/xe_exec_system_allocator.c +6 -0
+	memset(data, 0, data_size);
+	bind_engine = xe_bind_exec_queue_create(fd, vm2, 0);
+
+	/* Create and bind batch BO in VM2 */
+	batch_bo = xe_bo_create(fd, vm2, batch_size, vram_if_possible(fd, 0),
+
	DRM_XE_GEM_CREATE_FLAG_NEEDS_VISIBLE_VRAM);
tests/intel/xe_exec_system_allocator.c +5 -0
+	batch = xe_bo_map(fd, batch_bo, batch_size);
+
+	sync[0].addr = to_user_pointer(&vm_sync);
+	vm_sync = 0;
+	xe_vm_bind_async(fd, vm2, bind_engine, batch_bo, 0, batch_addr,

batch_size, sync, 1);

tests/intel/xe_exec_system_allocator.c +1 -0
+	xe_wait_ufence(fd, &vm_sync, PURGEABLE_FENCE_VAL, 0,

NSEC_PER_SEC);

tests/intel/xe_exec_system_allocator.c +4 -0
+
+	/* Mark VMA1 as DONTNEED, VMA2 stays WILLNEED */
+	retained = xe_vm_madvise_purgeable(fd, vm1, data_addr1, data_size,
+

DRM_XE_VMA_PURGEABLE_STATE_DONTNEED);

tests/intel/xe_exec_system_allocator.c +7 -0
+	igt_assert_eq(retained, 1);
+
+	/* Trigger pressure - BO should survive (VMA2 protects) */
+	trigger_memory_pressure(fd, vm1);
+
+	retained = xe_vm_madvise_purgeable(fd, vm2, data_addr2, data_size,
+

DRM_XE_VMA_PURGEABLE_STATE_WILLNEED);

tests/intel/xe_exec_system_allocator.c +27 -0
+	igt_assert_eq(retained, 1);
+
+	/* GPU workload - should succeed */
+	b = 0;
+	batch[b++] = MI_STORE_DWORD_IMM_GEN4;
+	batch[b++] = data_addr2;
+	batch[b++] = data_addr2 >> 32;
+	batch[b++] = PURGEABLE_TEST_PATTERN;
+	batch[b++] = MI_BATCH_BUFFER_END;
+
+	syncobj = syncobj_create(fd, 0);
+	sync[1].handle = syncobj;
+	exec_queue = xe_exec_queue_create(fd, vm2, hwe, 0);
+	exec.exec_queue_id = exec_queue;
+	exec.address = batch_addr;
+
+	ret = __xe_exec(fd, &exec);
+	igt_assert_eq(ret, 0);
+	igt_assert(syncobj_wait(fd, &syncobj, 1, INT64_MAX, 0, NULL));
+
+	munmap(data, data_size);
+	data = xe_bo_map(fd, bo, data_size);
+	igt_assert_eq(data[0], PURGEABLE_TEST_PATTERN);
+
+	/* Mark both VMAs DONTNEED */
+	retained = xe_vm_madvise_purgeable(fd, vm2, data_addr2, data_size,
+

DRM_XE_VMA_PURGEABLE_STATE_DONTNEED);

tests/intel/xe_exec_system_allocator.c +7 -0
+	igt_assert_eq(retained, 1);
+
+	/* Trigger pressure - BO should be purged */
+	trigger_memory_pressure(fd, vm1);
+
+	retained = xe_vm_madvise_purgeable(fd, vm2, data_addr2, data_size,
+

DRM_XE_VMA_PURGEABLE_STATE_WILLNEED);

tests/intel/xe_exec_system_allocator.c +8 -0
+	igt_assert_eq(retained, 0);
+
+	/* GPU workload - should fail or succeed with NULL rebind */
+	batch[3] = PURGEABLE_DEAD_PATTERN;
+
+	ret = __xe_exec(fd, &exec);
+	/* With SCRATCH_PAGE, kernel may allow exec with NULL rebind.
+	 * Without it, exec should fail with -EIO/-EFAULT or wait should

timeout.

tests/intel/xe_exec_system_allocator.c +50 -1
+	 * Both behaviors are valid depending on kernel support.
+	 */
+
+	munmap(data, data_size);
+	munmap(batch, batch_size);
+	gem_close(fd, bo);
+	gem_close(fd, batch_bo);
+	syncobj_destroy(fd, syncobj);
+	xe_exec_queue_destroy(fd, bind_engine);
+	xe_exec_queue_destroy(fd, exec_queue);
+	xe_vm_destroy(fd, vm1);
+	xe_vm_destroy(fd, vm2);
+}
+
  struct section {
  	const char *name;
  	unsigned long long flags;
@@ -2649,6 +3251,42 @@ int igt_main()
  			test_compute(fd, SZ_2M, s->flags);
  	}
 
+	igt_subtest("madvise-purgeable-dontneed-before-mmap")
+		xe_for_each_engine(fd, hwe) {
+			test_dontneed_before_mmap_madvise(fd, hwe);
+			break;
+		}
+
+	igt_subtest("madvise-purgeable-dontneed-after-mmap")
+		xe_for_each_engine(fd, hwe) {
+			test_dontneed_after_mmap_madvise(fd, hwe);
+			break;
+		}
+
+	igt_subtest("madvise-purgeable-dontneed-before-exec")
+		xe_for_each_engine(fd, hwe) {
+			test_dontneed_before_exec_madvise(fd, hwe);
+			break;
+		}
+
+	igt_subtest("madvise-purgeable-dontneed-after-exec")
+		xe_for_each_engine(fd, hwe) {
+			test_dontneed_after_exec_madvise(fd, hwe);
+			break;
+		}
+
+	igt_subtest("madvise-purgeable-per-vma-tracking")
+		xe_for_each_engine(fd, hwe) {
+			test_per_vma_tracking_madvise(fd, hwe);
+			break;
+		}
+
+	igt_subtest("madvise-purgeable-per-vma-protection")
+		xe_for_each_engine(fd, hwe) {
+			test_per_vma_protection_madvise(fd, hwe);
+			break;
+		}
+
  	igt_fixture() {
  		xe_device_put(fd);
  		drm_close_driver(fd);
--

2.43.0

#10 lore raw

✓ Xe.CI.BAT: success for tests/xe: Add purgeable memory madvise tests for system allocator

In reply to Arvind Yadav
== Series Details ==

== Series Details ==

Series: tests/xe: Add purgeable memory madvise tests for system allocator
URL : https://patchwork.freedesktop.org/series/160333/
State : success

== Summary ==

CI Bug Log - changes from XEIGT_8707_BAT -> XEIGTPW_14377_BAT
====================================================

Summary
-------

**SUCCESS**

No regressions found.

Participating hosts (12 -> 12)
------------------------------

No changes in participating hosts

Changes
-------

No changes found

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

* IGT: IGT_8707 -> IGTPW_14377

IGTPW_14377: c017ff2cf772ed6dda1ec5e0bc3716886b3ba71a @ https://gitlab.freedesktop.org/drm/igt-gpu-tools.git
IGT_8707: 8707
xe-4410-d5c98420766570dc019dc42dfbbe5a1061c03085: d5c98420766570dc019dc42dfbbe5a1061c03085

== Logs ==

For more details see: https://intel-gfx-ci.01.org/tree/intel-xe/IGTPW_14377/index.html

#11 lore raw

✓ i915.CI.BAT: success for tests/xe: Add purgeable memory madvise tests for system allocator

In reply to Arvind Yadav
== Series Details ==

== Series Details ==

Series: tests/xe: Add purgeable memory madvise tests for system allocator
URL : https://patchwork.freedesktop.org/series/160333/
State : success

== Summary ==

CI Bug Log - changes from IGT_8707 -> IGTPW_14377
====================================================

Summary
-------

**SUCCESS**

No regressions found.

External URL: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/index.html

Participating hosts (42 -> 40)
------------------------------

Missing (2): bat-dg2-13 fi-snb-2520m

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

Here are the changes found in IGTPW_14377 that come from known issues:

### IGT changes ###

#### Issues hit ####

* igt@i915_selftest@live@workarounds:
- bat-dg2-9: [PASS][1] -> [DMESG-FAIL][2] ([i915#12061]) +1 other test dmesg-fail
[1]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/bat-dg2-9/igt@i915_selftest@[email protected]
[2]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/bat-dg2-9/igt@i915_selftest@[email protected]
- bat-mtlp-9: [PASS][3] -> [DMESG-FAIL][4] ([i915#12061]) +1 other test dmesg-fail
[3]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/bat-mtlp-9/igt@i915_selftest@[email protected]
[4]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/bat-mtlp-9/igt@i915_selftest@[email protected]

* igt@kms_pm_rpm@basic-rte:
- bat-rpls-4: [PASS][5] -> [DMESG-WARN][6] ([i915#13400])
[5]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/bat-rpls-4/igt@[email protected]
[6]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/bat-rpls-4/igt@[email protected]

#### Possible fixes ####

* igt@i915_selftest@live:
- bat-jsl-1: [DMESG-FAIL][7] ([i915#15394]) -> [PASS][8] +1 other test pass
[7]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/bat-jsl-1/igt@[email protected]
[8]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/bat-jsl-1/igt@[email protected]

* igt@i915_selftest@live@workarounds:
- bat-arls-5: [DMESG-FAIL][9] ([i915#12061]) -> [PASS][10] +1 other test pass
[9]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/bat-arls-5/igt@i915_selftest@[email protected]
[10]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/bat-arls-5/igt@i915_selftest@[email protected]

[i915#12061]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/12061
[i915#13400]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/13400
[i915#15394]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/15394

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

* CI: CI-20190529 -> None
* IGT: IGT_8707 -> IGTPW_14377

CI-20190529: 20190529
CI_DRM_17845: d5c98420766570dc019dc42dfbbe5a1061c03085 @ git://anongit.freedesktop.org/gfx-ci/linux
IGTPW_14377: c017ff2cf772ed6dda1ec5e0bc3716886b3ba71a @ https://gitlab.freedesktop.org/drm/igt-gpu-tools.git
IGT_8707: 8707

== Logs ==

For more details see: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/index.html

#12 lore raw

✗ Xe.CI.Full: failure for tests/xe: Add purgeable memory madvise tests for system allocator

In reply to Arvind Yadav
== Series Details ==

== Series Details ==

Series: tests/xe: Add purgeable memory madvise tests for system allocator
URL : https://patchwork.freedesktop.org/series/160333/
State : failure

== Summary ==

CI Bug Log - changes from XEIGT_8707_FULL -> XEIGTPW_14377_FULL
====================================================

Summary
-------

**FAILURE**

Serious unknown changes coming with XEIGTPW_14377_FULL absolutely need to be verified manually.

If you think the reported changes have nothing to do with the changes
introduced in XEIGTPW_14377_FULL, please notify your bug team ([email protected]) to allow them to document this new failure mode, which will reduce false positives in CI.

Participating hosts (2 -> 2)
------------------------------

No changes in participating hosts

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

Here are the unknown changes that may have been introduced in XEIGTPW_14377_FULL:

### IGT changes ###

#### Possible regressions ####

* igt@kms_atomic_transition@plane-all-transition-fencing@pipe-b-hdmi-a-3:
- shard-bmg: [PASS][1] -> [INCOMPLETE][2] +1 other test incomplete
[1]: https://intel-gfx-ci.01.org/tree/intel-xe/IGT_8707/shard-bmg-9/igt@kms_atomic_transition@[email protected]
[2]: https://intel-gfx-ci.01.org/tree/intel-xe/IGTPW_14377/shard-bmg-3/igt@kms_atomic_transition@[email protected]

* igt@xe_configfs@survivability-mode:
- shard-bmg: NOTRUN -> [ABORT][3]
[3]: https://intel-gfx-ci.01.org/tree/intel-xe/IGTPW_14377/shard-bmg-7/igt@[email protected]

* {igt@xe_exec_system_allocator@madvise-purgeable-per-vma-protection} (NEW):
- shard-lnl: NOTRUN -> [FAIL][4] +4 other tests fail
[4]: https://intel-gfx-ci.01.org/tree/intel-xe/IGTPW_14377/shard-lnl-4/igt@xe_exec_system_allocator@madvise-purgeable-per-vma-protection.html

* {igt@xe_exec_system_allocator@madvise-purgeable-per-vma-tracking} (NEW):
- shard-bmg: NOTRUN -> [FAIL][5] +5 other tests fail
[5]: https://intel-gfx-ci.01.org/tree/intel-xe/IGTPW_14377/shard-bmg-3/igt@[email protected]

* igt@xe_pm@d3hot-basic-exec:
- shard-lnl: [PASS][6] -> [TIMEOUT][7]
[6]: https://intel-gfx-ci.01.org/tree/intel-xe/IGT_8707/shard-lnl-8/igt@[email protected]
[7]: https://intel-gfx-ci.01.org/tree/intel-xe/IGTPW_14377/shard-lnl-2/igt@[email protected]

#### Warnings ####

* igt@kms_pm_rpm@dpms-mode-unset-non-lpsp:
- shard-lnl: [SKIP][8] ([Intel XE#1439] / [Intel XE#836]) -> [SKIP][9]
[8]: https://intel-gfx-ci.01.org/tree/intel-xe/IGT_8707/shard-lnl-1/igt@[email protected]
[9]: https://intel-gfx-ci.01.org/tree/intel-xe/IGTPW_14377/shard-lnl-2/igt@[email protected]

New tests
---------

New tests have been introduced between XEIGT_8707_FULL and XEIGTPW_14377_FULL:

### New IGT tests (6) ###

* igt@xe_exec_system_allocator@madvise-purgeable-dontneed-after-exec:
- Statuses : 1 fail(s)
- Exec time: [0.02] s

* igt@xe_exec_system_allocator@madvise-purgeable-dontneed-after-mmap:
- Statuses : 2 fail(s)
- Exec time: [0.01] s

* igt@xe_exec_system_allocator@madvise-purgeable-dontneed-before-exec:
- Statuses : 2 fail(s)
- Exec time: [0.01] s

* igt@xe_exec_system_allocator@madvise-purgeable-dontneed-before-mmap:
- Statuses : 2 fail(s)
- Exec time: [0.01, 0.02] s

* igt@xe_exec_system_allocator@madvise-purgeable-per-vma-protection:
- Statuses : 2 fail(s)
- Exec time: [0.01] s

* igt@xe_exec_system_allocator@madvise-purgeable-per-vma-tracking:
- Statuses : 2 fail(s)
- Exec time: [0.01] s

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

Here are the changes found in XEIGTPW_14377_FULL that come from known issues:

### IGT changes ###

#### Issues hit ####

* igt@kms_big_fb@linear-32bpp-rotate-270:
- shard-bmg: NOTRUN -> [SKIP][10] ([Intel XE#2327]) +1 other test skip
[10]: https://intel-gfx-ci.01.org/tree/intel-xe/IGTPW_14377/shard-bmg-7/igt@[email protected]

* igt@kms_big_fb@yf-tiled-8bpp-rotate-90:
- shard-bmg: NOTRUN -> [SKIP][11] ([Intel XE#1124]) +6 other tests skip
[11]: https://intel-gfx-ci.01.org/tree/intel-xe/IGTPW_14377/shard-bmg-3/igt@[email protected]
- shard-lnl: NOTRUN -> [SKIP][12] ([Intel XE#1124])
[12]: https://intel-gfx-ci.01.org/tree/intel-xe/IGTPW_14377/shard-lnl-8/igt@[email protected]

* igt@kms_big_fb@yf-tiled-addfb-size-offset-overflow:
- shard-bmg: NOTRUN -> [SKIP][13] ([Intel XE#607])
[13]: https://intel-gfx-ci.01.org/tree/intel-xe/IGTPW_14377/shard-bmg-9/igt@[email protected]

* igt@kms_bw@linear-tiling-1-displays-1920x1080p:
- shard-bmg: NOTRUN -> [SKIP][14] ([Intel XE#367])
[14]: https://intel-gfx-ci.01.org/tree/intel-xe/IGTPW_14377/shard-bmg-1/igt@[email protected]

* igt@kms_ccs@bad-pixel-format-y-tiled-gen12-rc-ccs-cc:
- shard-bmg: NOTRUN -> [SKIP][15] ([Intel XE#2887]) +6 other tests skip
[15]: https://intel-gfx-ci.01.org/tree/intel-xe/IGTPW_14377/shard-bmg-4/igt@[email protected]

* igt@kms_ccs@ccs-on-another-bo-4-tiled-mtl-mc-ccs:
- shard-lnl: NOTRUN -> [SKIP][16] ([Intel XE#2887])
[16]: https://intel-gfx-ci.01.org/tree/intel-xe/IGTPW_14377/shard-lnl-5/igt@[email protected]

* igt@kms_ccs@crc-primary-basic-4-tiled-lnl-ccs:
- shard-bmg: NOTRUN -> [SKIP][17] ([Intel XE#2652] / [Intel XE#787]) +8 other tests skip
[17]: https://intel-gfx-ci.01.org/tree/intel-xe/IGTPW_14377/shard-bmg-1/igt@[email protected]

* igt@kms_ccs@crc-primary-suspend-4-tiled-dg2-mc-ccs:
- shard-bmg: NOTRUN -> [SKIP][18] ([Intel XE#3432]) +1 other test skip
[18]: https://intel-gfx-ci.01.org/tree/intel-xe/IGTPW_14377/shard-bmg-4/igt@[email protected]

* igt@kms_chamelium_color@ctm-green-to-red:
- shard-lnl: NOTRUN -> [SKIP][19] ([Intel XE#306])
[19]: https://intel-gfx-ci.01.org/tree/intel-xe/IGTPW_14377/shard-lnl-2/igt@[email protected]
- shard-bmg: NOTRUN -> [SKIP][20] ([Intel XE#2325])
[20]: https://intel-gfx-ci.01.org/tree/intel-xe/IGTPW_14377/shard-bmg-3/igt@[email protected]

* igt@kms_chamelium_frames@hdmi-cmp-planes-random:
- shard-lnl: NOTRUN -> [SKIP][21] ([Intel XE#373])
[21]: https://intel-gfx-ci.01.org/tree/intel-xe/IGTPW_14377/shard-lnl-4/igt@[email protected]
- shard-bmg: NOTRUN -> [SKIP][22] ([Intel XE#2252]) +1 other test skip
[22]: https://intel-gfx-ci.01.org/tree/intel-xe/IGTPW_14377/shard-bmg-10/igt@[email protected]

* igt@kms_content_protection@dp-mst-type-0:
- shard-bmg: NOTRUN -> [SKIP][23] ([Intel XE#2390] / [Intel XE#6974])
[23]: https://intel-gfx-ci.01.org/tree/intel-xe/IGTPW_14377/shard-bmg-10/igt@[email protected]

* igt@kms_content_protection@legacy:
- shard-bmg: NOTRUN -> [FAIL][24] ([Intel XE#1178] / [Intel XE#3304]) +3 other tests fail
[24]: https://intel-gfx-ci.01.org/tree/intel-xe/IGTPW_14377/shard-bmg-1/igt@[email protected]

* igt@kms_content_protection@uevent-hdcp14:
- shard-lnl: NOTRUN -> [SKIP][25] ([Intel XE#6973])
[25]: https://intel-gfx-ci.01.org/tree/intel-xe/IGTPW_14377/shard-lnl-4/igt@[email protected]

* igt@kms_cursor_crc@cursor-offscreen-32x10:
- shard-bmg: NOTRUN -> [SKIP][26] ([Intel XE#2320]) +1 other test skip
[26]: https://intel-gfx-ci.01.org/tree/intel-xe/IGTPW_14377/shard-bmg-1/igt@[email protected]

* igt@kms_cursor_crc@cursor-onscreen-512x170:
- shard-bmg: NOTRUN -> [SKIP][27] ([Intel XE#2321]) +1 other test skip
[27]: https://intel-gfx-ci.01.org/tree/intel-xe/IGTPW_14377/shard-bmg-3/igt@[email protected]

* igt@kms_cursor_legacy@flip-vs-cursor-atomic:
- shard-bmg: [PASS][28] -> [FAIL][29] ([Intel XE#6715])
[28]: https://intel-gfx-ci.01.org/tree/intel-xe/IGT_8707/shard-bmg-8/igt@[email protected]
[29]: https://intel-gfx-ci.01.org/tree/intel-xe/IGTPW_14377/shard-bmg-3/igt@[email protected]

* igt@kms_cursor_legacy@short-busy-flip-before-cursor-atomic-transitions-varying-size:
- shard-bmg: NOTRUN -> [SKIP][30] ([Intel XE#2286])
[30]: https://intel-gfx-ci.01.org/tree/intel-xe/IGTPW_14377/shard-bmg-10/igt@kms_cursor_legacy@short-busy-flip-before-cursor-atomic-transitions-varying-size.html

* igt@kms_dp_link_training@non-uhbr-mst:
- shard-bmg: NOTRUN -> [SKIP][31] ([Intel XE#4354])
[31]: https://intel-gfx-ci.01.org/tree/intel-xe/IGTPW_14377/shard-bmg-7/igt@[email protected]

* igt@kms_dsc@dsc-basic:
- shard-bmg: NOTRUN -> [SKIP][32] ([Intel XE#2244])
[32]: https://intel-gfx-ci.01.org/tree/intel-xe/IGTPW_14377/shard-bmg-4/igt@[email protected]

* igt@kms_flip@2x-flip-vs-suspend:
- shard-lnl: NOTRUN -> [SKIP][33] ([Intel XE#1421])
[33]: https://intel-gfx-ci.01.org/tree/intel-xe/IGTPW_14377/shard-lnl-1/igt@[email protected]

* igt@kms_flip_scaled_crc@flip-32bpp-yftile-to-64bpp-yftile-upscaling@pipe-a-default-mode:
- shard-lnl: NOTRUN -> [SKIP][34] ([Intel XE#1401]) +1 other test skip
[34]: https://intel-gfx-ci.01.org/tree/intel-xe/IGTPW_14377/shard-lnl-7/igt@kms_flip_scaled_crc@flip-32bpp-yftile-to-64bpp-yftile-upscaling@pipe-a-default-mode.html

* igt@kms_flip_scaled_crc@flip-64bpp-yftile-to-32bpp-yftile-upscaling:
- shard-lnl: NOTRUN -> [SKIP][35] ([Intel XE#1401] / [Intel XE#1745]) +1 other test skip
[35]: https://intel-gfx-ci.01.org/tree/intel-xe/IGTPW_14377/shard-lnl-7/igt@kms_flip_scaled_crc@flip-64bpp-yftile-to-32bpp-yftile-upscaling.html
- shard-bmg: NOTRUN -> [SKIP][36] ([Intel XE#2293] / [Intel XE#2380]) +2 other tests skip
[36]: https://intel-gfx-ci.01.org/tree/intel-xe/IGTPW_14377/shard-bmg-8/igt@kms_flip_scaled_crc@flip-64bpp-yftile-to-32bpp-yftile-upscaling.html

* igt@kms_flip_scaled_crc@flip-64bpp-yftile-to-32bpp-yftile-upscaling@pipe-a-valid-mode:
- shard-bmg: NOTRUN -> [SKIP][37] ([Intel XE#2293]) +2 other tests skip
[37]: https://intel-gfx-ci.01.org/tree/intel-xe/IGTPW_14377/shard-bmg-8/igt@kms_flip_scaled_crc@flip-64bpp-yftile-to-32bpp-yftile-upscaling@pipe-a-valid-mode.html

* igt@kms_frontbuffer_tracking@drrs-2p-scndscrn-spr-indfb-draw-render:
- shard-lnl: NOTRUN -> [SKIP][38] ([Intel XE#656]) +3 other tests skip
[38]: https://intel-gfx-ci.01.org/tree/intel-xe/IGTPW_14377/shard-lnl-8/igt@kms_frontbuffer_tracking@drrs-2p-scndscrn-spr-indfb-draw-render.html

* igt@kms_frontbuffer_tracking@drrs-abgr161616f-draw-mmap-wc:
- shard-bmg: NOTRUN -> [SKIP][39] ([Intel XE#7061]) +2 other tests skip
[39]: https://intel-gfx-ci.01.org/tree/intel-xe/IGTPW_14377/shard-bmg-1/igt@[email protected]

* igt@kms_frontbuffer_tracking@drrs-modesetfrombusy:
- shard-lnl: NOTRUN -> [SKIP][40] ([Intel XE#651])
[40]: https://intel-gfx-ci.01.org/tree/intel-xe/IGTPW_14377/shard-lnl-5/igt@[email protected]

* igt@kms_frontbuffer_tracking@fbc-2p-scndscrn-shrfb-pgflip-blt:
- shard-bmg: NOTRUN -> [SKIP][41] ([Intel XE#4141]) +5 other tests skip
[41]: https://intel-gfx-ci.01.org/tree/intel-xe/IGTPW_14377/shard-bmg-4/igt@[email protected]

* igt@kms_frontbuffer_tracking@fbcdrrs-2p-primscrn-shrfb-plflip-blt:
- shard-bmg: NOTRUN -> [SKIP][42] ([Intel XE#2311]) +22 other tests skip
[42]: https://intel-gfx-ci.01.org/tree/intel-xe/IGTPW_14377/shard-bmg-7/igt@kms_frontbuffer_tracking@fbcdrrs-2p-primscrn-shrfb-plflip-blt.html

* igt@kms_frontbuffer_tracking@psr-1p-offscreen-pri-shrfb-draw-mmap-wc:
- shard-bmg: NOTRUN -> [SKIP][43] ([Intel XE#2313]) +15 other tests skip
[43]: https://intel-gfx-ci.01.org/tree/intel-xe/IGTPW_14377/shard-bmg-3/igt@kms_frontbuffer_tracking@psr-1p-offscreen-pri-shrfb-draw-mmap-wc.html

* igt@kms_pm_dc@dc5-dpms:
- shard-lnl: [PASS][44] -> [FAIL][45] ([Intel XE#718])
[44]: https://intel-gfx-ci.01.org/tree/intel-xe/IGT_8707/shard-lnl-2/igt@[email protected]
[45]: https://intel-gfx-ci.01.org/tree/intel-xe/IGTPW_14377/shard-lnl-4/igt@[email protected]

* igt@kms_pm_rpm@dpms-lpsp:
- shard-bmg: NOTRUN -> [SKIP][46] ([Intel XE#1439] / [Intel XE#3141] / [Intel XE#836])
[46]: https://intel-gfx-ci.01.org/tree/intel-xe/IGTPW_14377/shard-bmg-3/igt@[email protected]

* igt@kms_psr2_sf@pr-overlay-plane-update-continuous-sf:
- shard-lnl: NOTRUN -> [SKIP][47] ([Intel XE#1406] / [Intel XE#2893])
[47]: https://intel-gfx-ci.01.org/tree/intel-xe/IGTPW_14377/shard-lnl-8/igt@[email protected]

* igt@kms_psr2_sf@psr2-primary-plane-update-sf-dmg-area-big-fb:
- shard-bmg: NOTRUN -> [SKIP][48] ([Intel XE#1406] / [Intel XE#1489]) +3 other tests skip
[48]: https://intel-gfx-ci.01.org/tree/intel-xe/IGTPW_14377/shard-bmg-9/igt@[email protected]

* igt@kms_psr2_su@page_flip-nv12:
- shard-lnl: NOTRUN -> [SKIP][49] ([Intel XE#1128] / [Intel XE#1406])
[49]: https://intel-gfx-ci.01.org/tree/intel-xe/IGTPW_14377/shard-lnl-7/igt@kms_psr2_su@page_flip-nv12.html
- shard-bmg: NOTRUN -> [SKIP][50] ([Intel XE#1406] / [Intel XE#2387])
[50]: https://intel-gfx-ci.01.org/tree/intel-xe/IGTPW_14377/shard-bmg-8/igt@kms_psr2_su@page_flip-nv12.html

* igt@kms_psr@psr-basic:
- shard-bmg: NOTRUN -> [SKIP][51] ([Intel XE#1406] / [Intel XE#2234] / [Intel XE#2850]) +6 other tests skip
[51]: https://intel-gfx-ci.01.org/tree/intel-xe/IGTPW_14377/shard-bmg-7/igt@[email protected]

* igt@kms_rotation_crc@primary-rotation-90:
- shard-bmg: NOTRUN -> [SKIP][52] ([Intel XE#3414] / [Intel XE#3904]) +1 other test skip
[52]: https://intel-gfx-ci.01.org/tree/intel-xe/IGTPW_14377/shard-bmg-4/igt@[email protected]

* igt@kms_sharpness_filter@filter-dpms:
- shard-bmg: NOTRUN -> [SKIP][53] ([Intel XE#6503])
[53]: https://intel-gfx-ci.01.org/tree/intel-xe/IGTPW_14377/shard-bmg-10/igt@[email protected]

* igt@kms_vrr@cmrr:
- shard-bmg: NOTRUN -> [SKIP][54] ([Intel XE#2168])
[54]: https://intel-gfx-ci.01.org/tree/intel-xe/IGTPW_14377/shard-bmg-8/igt@[email protected]

* igt@kms_vrr@flip-suspend:
- shard-bmg: NOTRUN -> [SKIP][55] ([Intel XE#1499]) +1 other test skip
[55]: https://intel-gfx-ci.01.org/tree/intel-xe/IGTPW_14377/shard-bmg-4/igt@[email protected]

* igt@kms_vrr@seamless-rr-switch-virtual@pipe-a-edp-1:
- shard-lnl: [PASS][56] -> [FAIL][57] ([Intel XE#2142]) +1 other test fail
[56]: https://intel-gfx-ci.01.org/tree/intel-xe/IGT_8707/shard-lnl-8/igt@kms_vrr@[email protected]
[57]: https://intel-gfx-ci.01.org/tree/intel-xe/IGTPW_14377/shard-lnl-5/igt@kms_vrr@[email protected]

* igt@xe_eudebug@basic-client:
- shard-lnl: NOTRUN -> [SKIP][58] ([Intel XE#4837])
[58]: https://intel-gfx-ci.01.org/tree/intel-xe/IGTPW_14377/shard-lnl-1/igt@[email protected]

* igt@xe_eudebug_online@interrupt-other:
- shard-bmg: NOTRUN -> [SKIP][59] ([Intel XE#4837] / [Intel XE#6665]) +3 other tests skip
[59]: https://intel-gfx-ci.01.org/tree/intel-xe/IGTPW_14377/shard-bmg-4/igt@[email protected]

* igt@xe_eudebug_sriov@deny-eudebug:
- shard-lnl: NOTRUN -> [SKIP][60] ([Intel XE#4518])
[60]: https://intel-gfx-ci.01.org/tree/intel-xe/IGTPW_14377/shard-lnl-2/igt@[email protected]
- shard-bmg: NOTRUN -> [SKIP][61] ([Intel XE#5793])
[61]: https://intel-gfx-ci.01.org/tree/intel-xe/IGTPW_14377/shard-bmg-7/igt@[email protected]

* igt@xe_evict@evict-beng-mixed-many-threads-small:
- shard-bmg: [PASS][62] -> [INCOMPLETE][63] ([Intel XE#6321])
[62]: https://intel-gfx-ci.01.org/tree/intel-xe/IGT_8707/shard-bmg-9/igt@[email protected]
[63]: https://intel-gfx-ci.01.org/tree/intel-xe/IGTPW_14377/shard-bmg-3/igt@[email protected]

* igt@xe_evict@evict-mixed-threads-small:
- shard-lnl: NOTRUN -> [SKIP][64] ([Intel XE#688])
[64]: https://intel-gfx-ci.01.org/tree/intel-xe/IGTPW_14377/shard-lnl-3/igt@[email protected]

* igt@xe_exec_basic@multigpu-once-null-defer-mmap:
- shard-bmg: NOTRUN -> [SKIP][65] ([Intel XE#2322]) +4 other tests skip
[65]: https://intel-gfx-ci.01.org/tree/intel-xe/IGTPW_14377/shard-bmg-7/igt@[email protected]
- shard-lnl: NOTRUN -> [SKIP][66] ([Intel XE#1392]) +1 other test skip
[66]: https://intel-gfx-ci.01.org/tree/intel-xe/IGTPW_14377/shard-lnl-3/igt@[email protected]

* igt@xe_exec_compute_mode@once-rebind:
- shard-lnl: [PASS][67] -> [DMESG-WARN][68] ([Intel XE#4537] / [Intel XE#7063])
[67]: https://intel-gfx-ci.01.org/tree/intel-xe/IGT_8707/shard-lnl-5/igt@[email protected]
[68]: https://intel-gfx-ci.01.org/tree/intel-xe/IGTPW_14377/shard-lnl-5/igt@[email protected]

* igt@xe_exec_multi_queue@few-execs-preempt-mode-priority-smem:
- shard-lnl: NOTRUN -> [SKIP][69] ([Intel XE#6874]) +2 other tests skip
[69]: https://intel-gfx-ci.01.org/tree/intel-xe/IGTPW_14377/shard-lnl-8/igt@[email protected]

* igt@xe_exec_multi_queue@two-queues-preempt-mode-basic-smem:
- shard-bmg: NOTRUN -> [SKIP][70] ([Intel XE#6874]) +16 other tests skip
[70]: https://intel-gfx-ci.01.org/tree/intel-xe/IGTPW_14377/shard-bmg-4/igt@[email protected]

* igt@xe_exec_sip_eudebug@breakpoint-writesip-nodebug:
- shard-bmg: NOTRUN -> [SKIP][71] ([Intel XE#4837]) +1 other test skip
[71]: https://intel-gfx-ci.01.org/tree/intel-xe/IGTPW_14377/shard-bmg-10/igt@[email protected]

* igt@xe_exec_system_allocator@many-64k-mmap-free-huge-nomemset:
- shard-bmg: NOTRUN -> [SKIP][72] ([Intel XE#5007])
[72]: https://intel-gfx-ci.01.org/tree/intel-xe/IGTPW_14377/shard-bmg-2/igt@[email protected]

* igt@xe_exec_system_allocator@many-execqueues-mmap-free-huge:
- shard-bmg: NOTRUN -> [SKIP][73] ([Intel XE#4943]) +14 other tests skip
[73]: https://intel-gfx-ci.01.org/tree/intel-xe/IGTPW_14377/shard-bmg-7/igt@[email protected]

* igt@xe_exec_system_allocator@pat-index-madvise-pat-idx-uc-multi-vma:
- shard-lnl: [PASS][74] -> [FAIL][75] ([Intel XE#5625])
[74]: https://intel-gfx-ci.01.org/tree/intel-xe/IGT_8707/shard-lnl-1/igt@xe_exec_system_allocator@pat-index-madvise-pat-idx-uc-multi-vma.html
[75]: https://intel-gfx-ci.01.org/tree/intel-xe/IGTPW_14377/shard-lnl-7/igt@xe_exec_system_allocator@pat-index-madvise-pat-idx-uc-multi-vma.html

* igt@xe_exec_system_allocator@process-many-stride-mmap-huge:
- shard-lnl: NOTRUN -> [SKIP][76] ([Intel XE#4943])
[76]: https://intel-gfx-ci.01.org/tree/intel-xe/IGTPW_14377/shard-lnl-2/igt@[email protected]

* igt@xe_multigpu_svm@mgpu-coherency-fail-prefetch:
- shard-bmg: NOTRUN -> [SKIP][77] ([Intel XE#6964]) +1 other test skip
[77]: https://intel-gfx-ci.01.org/tree/intel-xe/IGTPW_14377/shard-bmg-7/igt@[email protected]

* igt@xe_pm@d3cold-mmap-system:
- shard-bmg: NOTRUN -> [SKIP][78] ([Intel XE#2284]) +1 other test skip
[78]: https://intel-gfx-ci.01.org/tree/intel-xe/IGTPW_14377/shard-bmg-7/igt@[email protected]

* igt@xe_pxp@pxp-stale-bo-exec-post-termination-irq:
- shard-bmg: NOTRUN -> [SKIP][79] ([Intel XE#4733]) +4 other tests skip
[79]: https://intel-gfx-ci.01.org/tree/intel-xe/IGTPW_14377/shard-bmg-4/igt@[email protected]

* igt@xe_query@multigpu-query-invalid-size:
- shard-lnl: NOTRUN -> [SKIP][80] ([Intel XE#944])
[80]: https://intel-gfx-ci.01.org/tree/intel-xe/IGTPW_14377/shard-lnl-8/igt@[email protected]
- shard-bmg: NOTRUN -> [SKIP][81] ([Intel XE#944])
[81]: https://intel-gfx-ci.01.org/tree/intel-xe/IGTPW_14377/shard-bmg-9/igt@[email protected]

* igt@xe_sriov_flr@flr-vfs-parallel:
- shard-bmg: [PASS][82] -> [FAIL][83] ([Intel XE#6569]) +1 other test fail
[82]: https://intel-gfx-ci.01.org/tree/intel-xe/IGT_8707/shard-bmg-9/igt@[email protected]
[83]: https://intel-gfx-ci.01.org/tree/intel-xe/IGTPW_14377/shard-bmg-7/igt@[email protected]

* igt@xe_vm@bind-array-enobufs:
- shard-lnl: [PASS][84] -> [DMESG-WARN][85] ([Intel XE#7063]) +9 other tests dmesg-warn
[84]: https://intel-gfx-ci.01.org/tree/intel-xe/IGT_8707/shard-lnl-8/igt@[email protected]
[85]: https://intel-gfx-ci.01.org/tree/intel-xe/IGTPW_14377/shard-lnl-8/igt@[email protected]

#### Possible fixes ####

* igt@kms_cursor_legacy@flip-vs-cursor-legacy:
- shard-bmg: [FAIL][86] ([Intel XE#4633]) -> [PASS][87]
[86]: https://intel-gfx-ci.01.org/tree/intel-xe/IGT_8707/shard-bmg-10/igt@[email protected]
[87]: https://intel-gfx-ci.01.org/tree/intel-xe/IGTPW_14377/shard-bmg-4/igt@[email protected]

* igt@kms_pm_dc@dc5-psr:
- shard-lnl: [FAIL][88] ([Intel XE#718]) -> [PASS][89] +1 other test pass
[88]: https://intel-gfx-ci.01.org/tree/intel-xe/IGT_8707/shard-lnl-4/igt@[email protected]
[89]: https://intel-gfx-ci.01.org/tree/intel-xe/IGTPW_14377/shard-lnl-3/igt@[email protected]

* igt@kms_pm_rpm@i2c:
- shard-bmg: [FAIL][90] ([Intel XE#5099]) -> [PASS][91]
[90]: https://intel-gfx-ci.01.org/tree/intel-xe/IGT_8707/shard-bmg-10/igt@[email protected]
[91]: https://intel-gfx-ci.01.org/tree/intel-xe/IGTPW_14377/shard-bmg-8/igt@[email protected]

* igt@kms_setmode@basic@pipe-b-edp-1:
- shard-lnl: [FAIL][92] ([Intel XE#6361]) -> [PASS][93] +1 other test pass
[92]: https://intel-gfx-ci.01.org/tree/intel-xe/IGT_8707/shard-lnl-3/igt@kms_setmode@[email protected]
[93]: https://intel-gfx-ci.01.org/tree/intel-xe/IGTPW_14377/shard-lnl-2/igt@kms_setmode@[email protected]

* igt@xe_exec_system_allocator@threads-many-stride-mmap-prefetch-shared:
- shard-lnl: [DMESG-WARN][94] ([Intel XE#7063]) -> [PASS][95] +5 other tests pass
[94]: https://intel-gfx-ci.01.org/tree/intel-xe/IGT_8707/shard-lnl-5/igt@xe_exec_system_allocator@threads-many-stride-mmap-prefetch-shared.html
[95]: https://intel-gfx-ci.01.org/tree/intel-xe/IGTPW_14377/shard-lnl-4/igt@xe_exec_system_allocator@threads-many-stride-mmap-prefetch-shared.html

#### Warnings ####

* igt@kms_tiled_display@basic-test-pattern-with-chamelium:
- shard-bmg: [SKIP][96] ([Intel XE#2509]) -> [SKIP][97] ([Intel XE#2426])
[96]: https://intel-gfx-ci.01.org/tree/intel-xe/IGT_8707/shard-bmg-10/igt@[email protected]
[97]: https://intel-gfx-ci.01.org/tree/intel-xe/IGTPW_14377/shard-bmg-8/igt@[email protected]

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

[Intel XE#1124]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/1124
[Intel XE#1128]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/1128
[Intel XE#1178]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/1178
[Intel XE#1392]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/1392
[Intel XE#1401]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/1401
[Intel XE#1406]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/1406
[Intel XE#1421]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/1421
[Intel XE#1439]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/1439
[Intel XE#1489]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/1489
[Intel XE#1499]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/1499
[Intel XE#1745]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/1745
[Intel XE#2142]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/2142
[Intel XE#2168]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/2168
[Intel XE#2234]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/2234
[Intel XE#2244]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/2244
[Intel XE#2252]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/2252
[Intel XE#2284]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/2284
[Intel XE#2286]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/2286
[Intel XE#2293]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/2293
[Intel XE#2311]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/2311
[Intel XE#2313]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/2313
[Intel XE#2320]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/2320
[Intel XE#2321]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/2321
[Intel XE#2322]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/2322
[Intel XE#2325]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/2325
[Intel XE#2327]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/2327
[Intel XE#2380]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/2380
[Intel XE#2387]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/2387
[Intel XE#2390]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/2390
[Intel XE#2426]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/2426
[Intel XE#2509]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/2509
[Intel XE#2652]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/2652
[Intel XE#2850]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/2850
[Intel XE#2887]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/2887
[Intel XE#2893]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/2893
[Intel XE#306]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/306
[Intel XE#3141]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/3141
[Intel XE#3304]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/3304
[Intel XE#3414]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/3414
[Intel XE#3432]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/3432
[Intel XE#367]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/367
[Intel XE#373]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/373
[Intel XE#3904]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/3904
[Intel XE#4141]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/4141
[Intel XE#4354]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/4354
[Intel XE#4518]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/4518
[Intel XE#4537]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/4537
[Intel XE#4633]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/4633
[Intel XE#4733]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/4733
[Intel XE#4837]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/4837
[Intel XE#4943]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/4943
[Intel XE#5007]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/5007
[Intel XE#5099]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/5099
[Intel XE#5625]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/5625
[Intel XE#5793]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/5793
[Intel XE#607]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/607
[Intel XE#6321]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/6321
[Intel XE#6361]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/6361
[Intel XE#6503]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/6503
[Intel XE#651]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/651
[Intel XE#656]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/656
[Intel XE#6569]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/6569
[Intel XE#6665]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/6665
[Intel XE#6715]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/6715
[Intel XE#6874]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/6874
[Intel XE#688]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/688
[Intel XE#6964]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/6964
[Intel XE#6973]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/6973
[Intel XE#6974]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/6974
[Intel XE#7061]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/7061
[Intel XE#7063]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/7063
[Intel XE#718]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/718
[Intel XE#787]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/787
[Intel XE#836]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/836
[Intel XE#944]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/944

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

* IGT: IGT_8707 -> IGTPW_14377

IGTPW_14377: c017ff2cf772ed6dda1ec5e0bc3716886b3ba71a @ https://gitlab.freedesktop.org/drm/igt-gpu-tools.git
IGT_8707: 8707
xe-4410-d5c98420766570dc019dc42dfbbe5a1061c03085: d5c98420766570dc019dc42dfbbe5a1061c03085

== Logs ==

For more details see: https://intel-gfx-ci.01.org/tree/intel-xe/IGTPW_14377/index.html

#13 lore raw

✗ i915.CI.Full: failure for tests/xe: Add purgeable memory madvise tests for system allocator

In reply to Arvind Yadav
== Series Details ==

== Series Details ==

Series: tests/xe: Add purgeable memory madvise tests for system allocator
URL : https://patchwork.freedesktop.org/series/160333/
State : failure

== Summary ==

CI Bug Log - changes from IGT_8707_full -> IGTPW_14377_full
====================================================

Summary
-------

**FAILURE**

Serious unknown changes coming with IGTPW_14377_full absolutely need to be verified manually.

If you think the reported changes have nothing to do with the changes
introduced in IGTPW_14377_full, please notify your bug team ([email protected]) to allow them to document this new failure mode, which will reduce false positives in CI.

External URL: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/index.html

Participating hosts (9 -> 9)
------------------------------

No changes in participating hosts

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

Here are the unknown changes that may have been introduced in IGTPW_14377_full:

### IGT changes ###

#### Possible regressions ####

* igt@gem_exec_balancer@bonded-chain:
- shard-rkl: NOTRUN -> [ABORT][1] +8 other tests abort
[1]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-6/igt@[email protected]
- shard-tglu-1: NOTRUN -> [ABORT][2] +1 other test abort
[2]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-tglu-1/igt@[email protected]

* igt@gem_exec_balancer@bonded-true-hang:
- shard-dg2: NOTRUN -> [ABORT][3] +9 other tests abort
[3]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg2-7/igt@[email protected]

* igt@gem_exec_balancer@individual:
- shard-glk10: NOTRUN -> [ABORT][4]
[4]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-glk10/igt@[email protected]

* igt@gem_pxp@hw-rejects-pxp-buffer:
- shard-rkl: NOTRUN -> [FAIL][5]
[5]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-2/igt@[email protected]

* igt@kms_async_flips@basic-modeset-with-all-modifiers-formats@pipe-a-edp-1-4-yuyv:
- shard-mtlp: NOTRUN -> [FAIL][6] +39 other tests fail
[6]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-mtlp-2/igt@kms_async_flips@basic-modeset-with-all-modifiers-formats@pipe-a-edp-1-4-yuyv.html

* igt@perf@non-system-wide-paranoid:
- shard-mtlp: NOTRUN -> [ABORT][7] +8 other tests abort
[7]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-mtlp-5/igt@[email protected]

* igt@perf@oa-formats:
- shard-dg1: NOTRUN -> [ABORT][8] +9 other tests abort
[8]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg1-12/igt@[email protected]

* igt@perf_pmu@busy-double-start:
- shard-tglu: NOTRUN -> [ABORT][9] +13 other tests abort
[9]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-tglu-2/igt@[email protected]

* igt@perf_pmu@busy-idle-no-semaphores@rcs0:
- shard-glk: NOTRUN -> [ABORT][10] +14 other tests abort
[10]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-glk2/igt@perf_pmu@[email protected]

* igt@perf_pmu@faulting-read:
- shard-snb: NOTRUN -> [ABORT][11] +1 other test abort
[11]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-snb4/igt@[email protected]

#### Warnings ####

* igt@gem_exec_balancer@noheartbeat:
- shard-dg2: [SKIP][12] ([i915#2575]) -> [ABORT][13]
[12]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/shard-dg2-4/igt@[email protected]
[13]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg2-5/igt@[email protected]
- shard-rkl: [SKIP][14] -> [ABORT][15]
[14]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/shard-rkl-2/igt@[email protected]
[15]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-6/igt@[email protected]
- shard-dg1: [SKIP][16] ([i915#2575]) -> [ABORT][17]
[16]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/shard-dg1-19/igt@[email protected]
[17]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg1-16/igt@[email protected]
- shard-tglu: [SKIP][18] ([i915#2575]) -> [ABORT][19]
[18]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/shard-tglu-10/igt@[email protected]
[19]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-tglu-7/igt@[email protected]
- shard-mtlp: [SKIP][20] ([i915#2575]) -> [ABORT][21]
[20]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/shard-mtlp-8/igt@[email protected]
[21]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-mtlp-6/igt@[email protected]

* igt@i915_pm_rc6_residency@rc6-idle:
- shard-dg1: [ABORT][22] ([i915#15602]) -> [ABORT][23] +2 other tests abort
[22]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/shard-dg1-17/igt@[email protected]
[23]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg1-18/igt@[email protected]

* igt@perf@gen12-group-exclusive-stream-sample-oa:
- shard-dg2: [ABORT][24] ([i915#15602]) -> [ABORT][25] +1 other test abort
[24]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/shard-dg2-6/igt@[email protected]
[25]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg2-7/igt@[email protected]

* igt@perf_pmu@multi-client@rcs0:
- shard-snb: [ABORT][26] ([i915#15602]) -> [ABORT][27] +4 other tests abort
[26]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/shard-snb1/igt@perf_pmu@[email protected]
[27]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-snb7/igt@perf_pmu@[email protected]

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

Here are the changes found in IGTPW_14377_full that come from known issues:

### IGT changes ###

#### Issues hit ####

* igt@gem_ccs@block-multicopy-inplace:
- shard-rkl: NOTRUN -> [SKIP][28] ([i915#3555] / [i915#9323])
[28]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-8/igt@[email protected]
- shard-dg1: NOTRUN -> [SKIP][29] ([i915#3555] / [i915#9323])
[29]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg1-14/igt@[email protected]
- shard-tglu: NOTRUN -> [SKIP][30] ([i915#3555] / [i915#9323])
[30]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-tglu-10/igt@[email protected]
- shard-mtlp: NOTRUN -> [SKIP][31] ([i915#3555] / [i915#9323])
[31]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-mtlp-4/igt@[email protected]

* igt@gem_ccs@ctrl-surf-copy-new-ctx:
- shard-mtlp: NOTRUN -> [SKIP][32] ([i915#9323]) +1 other test skip
[32]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-mtlp-6/igt@[email protected]

* igt@gem_ccs@suspend-resume:
- shard-rkl: NOTRUN -> [SKIP][33] ([i915#9323]) +1 other test skip
[33]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-8/igt@[email protected]
- shard-dg1: NOTRUN -> [SKIP][34] ([i915#9323]) +1 other test skip
[34]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg1-16/igt@[email protected]
- shard-tglu: NOTRUN -> [SKIP][35] ([i915#9323]) +1 other test skip
[35]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-tglu-9/igt@[email protected]

* igt@gem_close_race@multigpu-basic-threads:
- shard-dg2: NOTRUN -> [SKIP][36] ([i915#7697])
[36]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg2-3/igt@[email protected]
- shard-dg1: NOTRUN -> [SKIP][37] ([i915#7697])
[37]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg1-16/igt@[email protected]
- shard-tglu: NOTRUN -> [SKIP][38] ([i915#7697])
[38]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-tglu-4/igt@[email protected]
- shard-mtlp: NOTRUN -> [SKIP][39] ([i915#7697])
[39]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-mtlp-8/igt@[email protected]

* igt@gem_create@create-ext-cpu-access-sanity-check:
- shard-tglu: NOTRUN -> [SKIP][40] ([i915#6335])
[40]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-tglu-3/igt@[email protected]
- shard-mtlp: NOTRUN -> [SKIP][41] ([i915#6335])
[41]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-mtlp-3/igt@[email protected]
- shard-rkl: NOTRUN -> [SKIP][42] ([i915#6335])
[42]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-4/igt@[email protected]

* igt@gem_ctx_freq@sysfs@gt0:
- shard-tglu: NOTRUN -> [ABORT][43] ([i915#15602]) +9 other tests abort
[43]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-tglu-8/igt@gem_ctx_freq@[email protected]

* igt@gem_ctx_persistence@engines-hostile-preempt:
- shard-snb: NOTRUN -> [SKIP][44] ([i915#1099]) +3 other tests skip
[44]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-snb5/igt@[email protected]

* igt@gem_ctx_persistence@heartbeat-hang:
- shard-dg2: NOTRUN -> [SKIP][45] ([i915#8555]) +1 other test skip
[45]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg2-11/igt@[email protected]

* igt@gem_ctx_persistence@heartbeat-stop:
- shard-dg1: NOTRUN -> [SKIP][46] ([i915#8555]) +1 other test skip
[46]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg1-13/igt@[email protected]
- shard-mtlp: NOTRUN -> [SKIP][47] ([i915#8555]) +1 other test skip
[47]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-mtlp-2/igt@[email protected]

* igt@gem_ctx_persistence@saturated-hostile-nopreempt:
- shard-dg2: NOTRUN -> [SKIP][48] ([i915#5882]) +7 other tests skip
[48]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg2-5/igt@[email protected]

* igt@gem_ctx_persistence@saturated-hostile-nopreempt@vcs0:
- shard-mtlp: NOTRUN -> [SKIP][49] ([i915#5882]) +6 other tests skip
[49]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-mtlp-6/igt@gem_ctx_persistence@[email protected]

* igt@gem_ctx_sseu@engines:
- shard-rkl: NOTRUN -> [SKIP][50] ([i915#280])
[50]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-5/igt@[email protected]
- shard-tglu: NOTRUN -> [SKIP][51] ([i915#280])
[51]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-tglu-3/igt@[email protected]

* igt@gem_exec_balancer@invalid-balancer:
- shard-mtlp: NOTRUN -> [ABORT][52] ([i915#15602]) +12 other tests abort
[52]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-mtlp-5/igt@[email protected]

* igt@gem_exec_balancer@parallel:
- shard-tglu: NOTRUN -> [SKIP][53] ([i915#4525]) +2 other tests skip
[53]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-tglu-10/igt@[email protected]

* igt@gem_exec_balancer@parallel-balancer:
- shard-rkl: NOTRUN -> [SKIP][54] ([i915#4525]) +2 other tests skip
[54]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-8/igt@[email protected]

* igt@gem_exec_capture@capture-recoverable:
- shard-rkl: NOTRUN -> [SKIP][55] ([i915#6344])
[55]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-8/igt@[email protected]
- shard-tglu: NOTRUN -> [SKIP][56] ([i915#6344])
[56]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-tglu-10/igt@[email protected]

* igt@gem_exec_flush@basic-wb-ro-default:
- shard-dg2: NOTRUN -> [SKIP][57] ([i915#3539] / [i915#4852])
[57]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg2-5/igt@[email protected]

* igt@gem_exec_reloc@basic-concurrent0:
- shard-dg1: NOTRUN -> [SKIP][58] ([i915#3281]) +9 other tests skip
[58]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg1-14/igt@[email protected]

* igt@gem_exec_reloc@basic-gtt:
- shard-dg2: NOTRUN -> [SKIP][59] ([i915#3281]) +10 other tests skip
[59]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg2-11/igt@[email protected]

* igt@gem_exec_reloc@basic-wc-gtt:
- shard-mtlp: NOTRUN -> [SKIP][60] ([i915#3281]) +9 other tests skip
[60]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-mtlp-3/igt@[email protected]

* igt@gem_exec_reloc@basic-wc-read-noreloc:
- shard-rkl: NOTRUN -> [SKIP][61] ([i915#3281]) +9 other tests skip
[61]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-4/igt@[email protected]

* igt@gem_exec_schedule@preempt-queue-chain:
- shard-mtlp: NOTRUN -> [SKIP][62] ([i915#4537] / [i915#4812]) +1 other test skip
[62]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-mtlp-6/igt@[email protected]
- shard-dg2: NOTRUN -> [SKIP][63] ([i915#4537] / [i915#4812]) +1 other test skip
[63]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg2-4/igt@[email protected]
- shard-dg1: NOTRUN -> [SKIP][64] ([i915#4812]) +1 other test skip
[64]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg1-19/igt@[email protected]

* igt@gem_fence_thrash@bo-write-verify-y:
- shard-dg2: NOTRUN -> [SKIP][65] ([i915#4860]) +2 other tests skip
[65]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg2-5/igt@[email protected]

* igt@gem_fenced_exec_thrash@no-spare-fences:
- shard-dg1: NOTRUN -> [SKIP][66] ([i915#4860]) +2 other tests skip
[66]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg1-19/igt@[email protected]

* igt@gem_fenced_exec_thrash@too-many-fences:
- shard-mtlp: NOTRUN -> [SKIP][67] ([i915#4860]) +2 other tests skip
[67]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-mtlp-6/igt@[email protected]

* igt@gem_lmem_swapping@parallel-multi:
- shard-rkl: NOTRUN -> [SKIP][68] ([i915#4613]) +1 other test skip
[68]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-4/igt@[email protected]
- shard-tglu: NOTRUN -> [SKIP][69] ([i915#4613]) +1 other test skip
[69]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-tglu-3/igt@[email protected]
- shard-mtlp: NOTRUN -> [SKIP][70] ([i915#4613]) +1 other test skip
[70]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-mtlp-3/igt@[email protected]

* igt@gem_lmem_swapping@parallel-random:
- shard-glk: NOTRUN -> [SKIP][71] ([i915#4613])
[71]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-glk9/igt@[email protected]

* igt@gem_mmap@basic-small-bo:
- shard-mtlp: NOTRUN -> [SKIP][72] ([i915#4083]) +3 other tests skip
[72]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-mtlp-3/igt@[email protected]

* igt@gem_mmap_gtt@basic-read:
- shard-dg2: NOTRUN -> [SKIP][73] ([i915#4077]) +11 other tests skip
[73]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg2-7/igt@[email protected]

* igt@gem_mmap_gtt@fault-concurrent-y:
- shard-mtlp: NOTRUN -> [SKIP][74] ([i915#4077]) +11 other tests skip
[74]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-mtlp-8/igt@[email protected]

* igt@gem_mmap_wc@invalid-flags:
- shard-dg2: NOTRUN -> [SKIP][75] ([i915#4083]) +3 other tests skip
[75]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg2-11/igt@[email protected]
- shard-dg1: NOTRUN -> [SKIP][76] ([i915#4083]) +3 other tests skip
[76]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg1-15/igt@[email protected]

* igt@gem_partial_pwrite_pread@write-uncached:
- shard-dg2: NOTRUN -> [SKIP][77] ([i915#3282]) +5 other tests skip
[77]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg2-5/igt@[email protected]

* igt@gem_pwrite@basic-self:
- shard-rkl: NOTRUN -> [SKIP][78] ([i915#3282]) +8 other tests skip
[78]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-4/igt@[email protected]
- shard-dg1: NOTRUN -> [SKIP][79] ([i915#3282]) +5 other tests skip
[79]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg1-17/igt@[email protected]

* igt@gem_pxp@display-protected-crc:
- shard-dg2: NOTRUN -> [SKIP][80] ([i915#4270]) +2 other tests skip
[80]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg2-5/igt@[email protected]
- shard-dg1: NOTRUN -> [SKIP][81] ([i915#4270]) +2 other tests skip
[81]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg1-14/igt@[email protected]

* igt@gem_pxp@hw-rejects-pxp-buffer:
- shard-tglu: NOTRUN -> [SKIP][82] ([i915#13398])
[82]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-tglu-5/igt@[email protected]

* igt@gem_pxp@verify-pxp-execution-after-suspend-resume:
- shard-rkl: NOTRUN -> [SKIP][83] ([i915#4270])
[83]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-8/igt@[email protected]

* igt@gem_readwrite@read-bad-handle:
- shard-mtlp: NOTRUN -> [SKIP][84] ([i915#3282]) +5 other tests skip
[84]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-mtlp-7/igt@[email protected]

* igt@gem_render_copy@y-tiled-ccs-to-y-tiled-mc-ccs:
- shard-glk: NOTRUN -> [SKIP][85] +168 other tests skip
[85]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-glk9/igt@[email protected]
- shard-mtlp: NOTRUN -> [SKIP][86] ([i915#8428]) +5 other tests skip
[86]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-mtlp-2/igt@[email protected]

* igt@gem_render_copy@yf-tiled-ccs-to-y-tiled:
- shard-dg2: NOTRUN -> [SKIP][87] ([i915#5190] / [i915#8428]) +5 other tests skip
[87]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg2-8/igt@[email protected]

* igt@gem_set_tiling_vs_pwrite:
- shard-dg1: NOTRUN -> [SKIP][88] ([i915#4079])
[88]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg1-12/igt@gem_set_tiling_vs_pwrite.html
- shard-mtlp: NOTRUN -> [SKIP][89] ([i915#4079])
[89]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-mtlp-2/igt@gem_set_tiling_vs_pwrite.html
- shard-dg2: NOTRUN -> [SKIP][90] ([i915#4079])
[90]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg2-8/igt@gem_set_tiling_vs_pwrite.html

* igt@gem_tiled_partial_pwrite_pread@writes-after-reads:
- shard-dg1: NOTRUN -> [SKIP][91] ([i915#4077]) +11 other tests skip
[91]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg1-15/igt@[email protected]

* igt@gem_userptr_blits@coherency-unsync:
- shard-rkl: NOTRUN -> [SKIP][92] ([i915#3297]) +1 other test skip
[92]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-8/igt@[email protected]

* igt@gem_userptr_blits@invalid-mmap-offset-unsync:
- shard-tglu: NOTRUN -> [SKIP][93] ([i915#3297]) +1 other test skip
[93]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-tglu-6/igt@[email protected]
- shard-mtlp: NOTRUN -> [SKIP][94] ([i915#3297])
[94]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-mtlp-4/igt@[email protected]
- shard-dg2: NOTRUN -> [SKIP][95] ([i915#3297])
[95]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg2-5/igt@[email protected]
- shard-dg1: NOTRUN -> [SKIP][96] ([i915#3297])
[96]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg1-14/igt@[email protected]

* igt@gem_vm_create@invalid-create:
- shard-snb: NOTRUN -> [SKIP][97] +505 other tests skip
[97]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-snb1/igt@[email protected]

* igt@gen9_exec_parse@bb-start-out:
- shard-rkl: NOTRUN -> [SKIP][98] ([i915#2527]) +4 other tests skip
[98]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-4/igt@[email protected]
- shard-dg1: NOTRUN -> [SKIP][99] ([i915#2527]) +5 other tests skip
[99]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg1-15/igt@[email protected]

* igt@gen9_exec_parse@bb-start-param:
- shard-dg2: NOTRUN -> [SKIP][100] ([i915#2856]) +5 other tests skip
[100]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg2-3/igt@[email protected]

* igt@gen9_exec_parse@unaligned-jump:
- shard-tglu: NOTRUN -> [SKIP][101] ([i915#2527] / [i915#2856]) +5 other tests skip
[101]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-tglu-8/igt@[email protected]
- shard-mtlp: NOTRUN -> [SKIP][102] ([i915#2856]) +5 other tests skip
[102]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-mtlp-5/igt@[email protected]

* igt@i915_drm_fdinfo@all-busy-idle-check-all:
- shard-dg2: NOTRUN -> [SKIP][103] ([i915#14123])
[103]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg2-11/igt@[email protected]
- shard-dg1: NOTRUN -> [SKIP][104] ([i915#14123])
[104]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg1-15/igt@[email protected]
- shard-mtlp: NOTRUN -> [SKIP][105] ([i915#14123])
[105]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-mtlp-5/igt@[email protected]

* igt@i915_drm_fdinfo@busy-idle@bcs0:
- shard-dg1: NOTRUN -> [SKIP][106] ([i915#14073]) +17 other tests skip
[106]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg1-19/igt@i915_drm_fdinfo@[email protected]

* igt@i915_drm_fdinfo@busy@vecs1:
- shard-dg2: NOTRUN -> [SKIP][107] ([i915#14073]) +23 other tests skip
[107]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg2-11/igt@i915_drm_fdinfo@[email protected]

* igt@i915_drm_fdinfo@most-busy-idle-check-all:
- shard-mtlp: NOTRUN -> [SKIP][108] ([i915#14073]) +20 other tests skip
[108]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-mtlp-6/igt@[email protected]

* igt@i915_drm_fdinfo@virtual-busy-all:
- shard-mtlp: NOTRUN -> [SKIP][109] ([i915#14118]) +1 other test skip
[109]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-mtlp-4/igt@[email protected]
- shard-dg2: NOTRUN -> [SKIP][110] ([i915#14118]) +1 other test skip
[110]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg2-5/igt@[email protected]
- shard-dg1: NOTRUN -> [SKIP][111] ([i915#14118]) +1 other test skip
[111]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg1-14/igt@[email protected]

* igt@i915_module_load@reload-no-display:
- shard-snb: NOTRUN -> [DMESG-WARN][112] ([i915#14545])
[112]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-snb5/igt@[email protected]

* igt@i915_module_load@resize-bar:
- shard-dg2: NOTRUN -> [DMESG-WARN][113] ([i915#14545])
[113]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg2-7/igt@[email protected]
- shard-rkl: NOTRUN -> [SKIP][114] ([i915#6412])
[114]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-7/igt@[email protected]
- shard-dg1: NOTRUN -> [SKIP][115] ([i915#7178])
[115]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg1-19/igt@[email protected]
- shard-tglu: NOTRUN -> [SKIP][116] ([i915#6412])
[116]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-tglu-7/igt@[email protected]
- shard-mtlp: NOTRUN -> [SKIP][117] ([i915#6412])
[117]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-mtlp-6/igt@[email protected]

* igt@i915_pm_freq_api@freq-basic-api:
- shard-tglu: NOTRUN -> [SKIP][118] ([i915#8399]) +1 other test skip
[118]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-tglu-10/igt@[email protected]
- shard-rkl: NOTRUN -> [SKIP][119] ([i915#8399]) +1 other test skip
[119]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-8/igt@[email protected]

* igt@i915_pm_freq_mult@media-freq@gt0:
- shard-rkl: NOTRUN -> [SKIP][120] ([i915#6590]) +1 other test skip
[120]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-8/igt@i915_pm_freq_mult@[email protected]
- shard-tglu: NOTRUN -> [SKIP][121] ([i915#6590]) +1 other test skip
[121]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-tglu-9/igt@i915_pm_freq_mult@[email protected]

* igt@i915_pm_rpm@system-suspend:
- shard-glk10: NOTRUN -> [INCOMPLETE][122] ([i915#13356])
[122]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-glk10/igt@[email protected]

* igt@i915_pm_rps@thresholds:
- shard-mtlp: NOTRUN -> [SKIP][123] ([i915#11681])
[123]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-mtlp-5/igt@[email protected]
- shard-dg2: NOTRUN -> [SKIP][124] ([i915#11681])
[124]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg2-11/igt@[email protected]
- shard-dg1: NOTRUN -> [SKIP][125] ([i915#11681])
[125]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg1-15/igt@[email protected]

* igt@i915_pm_sseu@full-enable:
- shard-dg2: NOTRUN -> [SKIP][126] ([i915#4387])
[126]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg2-3/igt@[email protected]
- shard-rkl: NOTRUN -> [SKIP][127] ([i915#4387])
[127]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-1/igt@[email protected]
- shard-dg1: NOTRUN -> [SKIP][128] ([i915#4387])
[128]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg1-16/igt@[email protected]
- shard-tglu: NOTRUN -> [SKIP][129] ([i915#4387])
[129]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-tglu-4/igt@[email protected]
- shard-mtlp: NOTRUN -> [SKIP][130] ([i915#8437])
[130]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-mtlp-8/igt@[email protected]

* igt@i915_suspend@fence-restore-untiled:
- shard-glk: [PASS][131] -> [INCOMPLETE][132] ([i915#4817])
[131]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/shard-glk6/igt@[email protected]
[132]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-glk3/igt@[email protected]

* igt@i915_suspend@forcewake:
- shard-glk: NOTRUN -> [INCOMPLETE][133] ([i915#4817])
[133]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-glk6/igt@[email protected]

* igt@kms_addfb_basic@clobberred-modifier:
- shard-dg2: NOTRUN -> [SKIP][134] ([i915#4212]) +1 other test skip
[134]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg2-7/igt@[email protected]

* igt@kms_addfb_basic@tile-pitch-mismatch:
- shard-dg1: NOTRUN -> [SKIP][135] ([i915#4212]) +1 other test skip
[135]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg1-13/igt@[email protected]
- shard-mtlp: NOTRUN -> [SKIP][136] ([i915#4212]) +1 other test skip
[136]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-mtlp-5/igt@[email protected]

* igt@kms_atomic_transition@plane-all-modeset-transition-fencing-internal-panels:
- shard-snb: NOTRUN -> [SKIP][137] ([i915#1769]) +1 other test skip
[137]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-snb1/igt@kms_atomic_transition@plane-all-modeset-transition-fencing-internal-panels.html
- shard-tglu: NOTRUN -> [SKIP][138] ([i915#1769] / [i915#3555]) +1 other test skip
[138]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-tglu-2/igt@kms_atomic_transition@plane-all-modeset-transition-fencing-internal-panels.html

* igt@kms_atomic_transition@plane-all-modeset-transition-internal-panels:
- shard-glk10: NOTRUN -> [SKIP][139] ([i915#1769])
[139]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-glk10/igt@kms_atomic_transition@plane-all-modeset-transition-internal-panels.html
- shard-dg2: NOTRUN -> [SKIP][140] ([i915#1769] / [i915#3555]) +1 other test skip
[140]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg2-6/igt@kms_atomic_transition@plane-all-modeset-transition-internal-panels.html
- shard-rkl: NOTRUN -> [SKIP][141] ([i915#1769] / [i915#3555]) +1 other test skip
[141]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-4/igt@kms_atomic_transition@plane-all-modeset-transition-internal-panels.html
- shard-dg1: NOTRUN -> [SKIP][142] ([i915#1769] / [i915#3555]) +1 other test skip
[142]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg1-17/igt@kms_atomic_transition@plane-all-modeset-transition-internal-panels.html

* igt@kms_big_fb@4-tiled-max-hw-stride-32bpp-rotate-0:
- shard-rkl: NOTRUN -> [SKIP][143] ([i915#5286]) +3 other tests skip
[143]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-7/igt@[email protected]
- shard-dg1: NOTRUN -> [SKIP][144] ([i915#4538] / [i915#5286]) +1 other test skip
[144]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg1-13/igt@[email protected]

* igt@kms_big_fb@4-tiled-max-hw-stride-64bpp-rotate-0:
- shard-tglu: NOTRUN -> [SKIP][145] ([i915#5286]) +3 other tests skip
[145]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-tglu-5/igt@[email protected]

* igt@kms_big_fb@linear-32bpp-rotate-90:
- shard-dg1: NOTRUN -> [SKIP][146] ([i915#3638]) +3 other tests skip
[146]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg1-13/igt@[email protected]

* igt@kms_big_fb@linear-64bpp-rotate-270:
- shard-mtlp: NOTRUN -> [SKIP][147] +20 other tests skip
[147]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-mtlp-3/igt@[email protected]
- shard-rkl: NOTRUN -> [SKIP][148] ([i915#3638]) +2 other tests skip
[148]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-4/igt@[email protected]

* igt@kms_big_fb@linear-max-hw-stride-32bpp-rotate-0:
- shard-snb: [PASS][149] -> [SKIP][150] +14 other tests skip
[149]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/shard-snb7/igt@[email protected]
[150]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-snb6/igt@[email protected]

* igt@kms_big_fb@linear-max-hw-stride-32bpp-rotate-0-hflip:
- shard-dg1: NOTRUN -> [SKIP][151] ([i915#3828])
[151]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg1-14/igt@[email protected]
- shard-mtlp: NOTRUN -> [SKIP][152] ([i915#3828])
[152]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-mtlp-8/igt@[email protected]
- shard-dg2: NOTRUN -> [SKIP][153] ([i915#3828])
[153]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg2-5/igt@[email protected]
- shard-rkl: NOTRUN -> [SKIP][154] ([i915#14544] / [i915#3828])
[154]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-6/igt@[email protected]
- shard-tglu-1: NOTRUN -> [SKIP][155] ([i915#3828])
[155]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-tglu-1/igt@[email protected]

* igt@kms_big_fb@linear-max-hw-stride-64bpp-rotate-0-hflip:
- shard-rkl: NOTRUN -> [SKIP][156] ([i915#3828])
[156]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-5/igt@[email protected]

* igt@kms_big_fb@y-tiled-max-hw-stride-64bpp-rotate-0-async-flip:
- shard-dg2: NOTRUN -> [SKIP][157] ([i915#4538] / [i915#5190]) +9 other tests skip
[157]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg2-4/igt@[email protected]

* igt@kms_big_fb@yf-tiled-16bpp-rotate-90:
- shard-glk10: NOTRUN -> [SKIP][158] +23 other tests skip
[158]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-glk10/igt@[email protected]

* igt@kms_big_fb@yf-tiled-max-hw-stride-64bpp-rotate-180:
- shard-dg1: NOTRUN -> [SKIP][159] ([i915#4538]) +8 other tests skip
[159]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg1-13/igt@[email protected]

* igt@kms_ccs@bad-pixel-format-4-tiled-mtl-mc-ccs:
- shard-dg2: NOTRUN -> [SKIP][160] ([i915#10307] / [i915#6095]) +74 other tests skip
[160]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg2-11/igt@[email protected]

* igt@kms_ccs@bad-pixel-format-y-tiled-ccs:
- shard-rkl: NOTRUN -> [SKIP][161] ([i915#14098] / [i915#14544] / [i915#6095]) +3 other tests skip
[161]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-6/igt@[email protected]

* igt@kms_ccs@ccs-on-another-bo-y-tiled-gen12-mc-ccs@pipe-b-edp-1:
- shard-mtlp: NOTRUN -> [SKIP][162] ([i915#6095]) +64 other tests skip
[162]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-mtlp-8/igt@kms_ccs@[email protected]

* igt@kms_ccs@ccs-on-another-bo-y-tiled-gen12-mc-ccs@pipe-b-hdmi-a-1:
- shard-tglu: NOTRUN -> [SKIP][163] ([i915#6095]) +78 other tests skip
[163]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-tglu-4/igt@kms_ccs@[email protected]

* igt@kms_ccs@crc-primary-basic-4-tiled-bmg-ccs:
- shard-dg2: NOTRUN -> [SKIP][164] ([i915#12313])
[164]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg2-7/igt@[email protected]
- shard-rkl: NOTRUN -> [SKIP][165] ([i915#12313]) +1 other test skip
[165]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-7/igt@[email protected]
- shard-dg1: NOTRUN -> [SKIP][166] ([i915#12313])
[166]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg1-19/igt@[email protected]
- shard-mtlp: NOTRUN -> [SKIP][167] ([i915#12313])
[167]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-mtlp-6/igt@[email protected]

* igt@kms_ccs@crc-primary-suspend-4-tiled-bmg-ccs:
- shard-dg1: NOTRUN -> [SKIP][168] ([i915#12805]) +1 other test skip
[168]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg1-12/igt@[email protected]
- shard-tglu: NOTRUN -> [SKIP][169] ([i915#12805]) +1 other test skip
[169]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-tglu-8/igt@[email protected]
- shard-mtlp: NOTRUN -> [SKIP][170] ([i915#12805]) +1 other test skip
[170]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-mtlp-7/igt@[email protected]

* igt@kms_ccs@crc-primary-suspend-4-tiled-lnl-ccs:
- shard-dg2: NOTRUN -> [SKIP][171] ([i915#12805]) +1 other test skip
[171]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg2-7/igt@[email protected]
- shard-rkl: NOTRUN -> [SKIP][172] ([i915#12805]) +1 other test skip
[172]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-3/igt@[email protected]

* igt@kms_ccs@crc-primary-suspend-y-tiled-gen12-rc-ccs-cc:
- shard-rkl: NOTRUN -> [ABORT][173] ([i915#15132]) +1 other test abort
[173]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-1/igt@[email protected]

* igt@kms_ccs@crc-primary-suspend-y-tiled-gen12-rc-ccs-cc@pipe-b-hdmi-a-3:
- shard-dg2: NOTRUN -> [SKIP][174] ([i915#6095]) +14 other tests skip
[174]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg2-3/igt@kms_ccs@[email protected]

* igt@kms_ccs@crc-primary-suspend-yf-tiled-ccs:
- shard-rkl: NOTRUN -> [SKIP][175] ([i915#14098] / [i915#6095]) +33 other tests skip
[175]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-8/igt@[email protected]

* igt@kms_ccs@crc-primary-suspend-yf-tiled-ccs@pipe-a-hdmi-a-1:
- shard-dg1: NOTRUN -> [SKIP][176] ([i915#6095]) +77 other tests skip
[176]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg1-14/igt@kms_ccs@[email protected]

* igt@kms_ccs@crc-sprite-planes-basic-4-tiled-mtl-mc-ccs:
- shard-tglu-1: NOTRUN -> [SKIP][177] ([i915#6095]) +9 other tests skip
[177]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-tglu-1/igt@[email protected]

* igt@kms_ccs@crc-sprite-planes-basic-4-tiled-mtl-rc-ccs@pipe-a-hdmi-a-2:
- shard-rkl: NOTRUN -> [SKIP][178] ([i915#14544] / [i915#6095]) +3 other tests skip
[178]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-6/igt@kms_ccs@[email protected]

* igt@kms_ccs@random-ccs-data-4-tiled-lnl-ccs:
- shard-tglu: NOTRUN -> [SKIP][179] ([i915#12313]) +1 other test skip
[179]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-tglu-5/igt@[email protected]

* igt@kms_ccs@random-ccs-data-4-tiled-mtl-rc-ccs@pipe-b-hdmi-a-2:
- shard-rkl: NOTRUN -> [SKIP][180] ([i915#6095]) +37 other tests skip
[180]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-4/igt@kms_ccs@[email protected]

* igt@kms_cdclk@mode-transition:
- shard-mtlp: NOTRUN -> [SKIP][181] ([i915#13781]) +4 other tests skip
[181]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-mtlp-3/igt@[email protected]
- shard-rkl: NOTRUN -> [SKIP][182] ([i915#3742])
[182]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-4/igt@[email protected]
- shard-dg1: NOTRUN -> [SKIP][183] ([i915#3742])
[183]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg1-17/igt@[email protected]
- shard-tglu: NOTRUN -> [SKIP][184] ([i915#3742])
[184]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-tglu-3/igt@[email protected]

* igt@kms_cdclk@mode-transition@pipe-d-hdmi-a-3:
- shard-dg2: NOTRUN -> [SKIP][185] ([i915#13781]) +4 other tests skip
[185]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg2-7/igt@kms_cdclk@[email protected]

* igt@kms_chamelium_color@ctm-max:
- shard-dg2: NOTRUN -> [SKIP][186] +10 other tests skip
[186]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg2-10/igt@[email protected]

* igt@kms_chamelium_edid@dp-mode-timings:
- shard-mtlp: NOTRUN -> [SKIP][187] ([i915#11151] / [i915#7828]) +8 other tests skip
[187]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-mtlp-2/igt@[email protected]
- shard-rkl: NOTRUN -> [SKIP][188] ([i915#11151] / [i915#14544] / [i915#7828]) +1 other test skip
[188]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-6/igt@[email protected]

* igt@kms_chamelium_frames@hdmi-crc-multiple:
- shard-dg2: NOTRUN -> [SKIP][189] ([i915#11151] / [i915#7828]) +9 other tests skip
[189]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg2-8/igt@[email protected]

* igt@kms_chamelium_hpd@dp-hpd:
- shard-rkl: NOTRUN -> [SKIP][190] ([i915#11151] / [i915#7828]) +6 other tests skip
[190]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-8/igt@[email protected]

* igt@kms_chamelium_hpd@hdmi-hpd-storm-disable:
- shard-dg1: NOTRUN -> [SKIP][191] ([i915#11151] / [i915#7828]) +8 other tests skip
[191]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg1-17/igt@[email protected]
- shard-tglu: NOTRUN -> [SKIP][192] ([i915#11151] / [i915#7828]) +9 other tests skip
[192]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-tglu-10/igt@[email protected]

* igt@kms_color@deep-color:
- shard-dg2: NOTRUN -> [SKIP][193] ([i915#12655] / [i915#3555])
[193]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg2-5/igt@[email protected]
- shard-rkl: NOTRUN -> [SKIP][194] ([i915#12655] / [i915#3555])
[194]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-8/igt@[email protected]
- shard-dg1: NOTRUN -> [SKIP][195] ([i915#12655] / [i915#3555])
[195]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg1-14/igt@[email protected]
- shard-tglu: NOTRUN -> [SKIP][196] ([i915#3555] / [i915#9979])
[196]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-tglu-6/igt@[email protected]

* igt@kms_color_pipeline@plane-lut1d-lut1d@pipe-b-edp-1:
- shard-mtlp: NOTRUN -> [FAIL][197] ([i915#15522]) +9 other tests fail
[197]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-mtlp-8/igt@kms_color_pipeline@[email protected]

* igt@kms_content_protection@atomic-dpms:
- shard-tglu: NOTRUN -> [SKIP][198] ([i915#6944] / [i915#7116] / [i915#7118] / [i915#9424])
[198]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-tglu-7/igt@[email protected]
- shard-mtlp: NOTRUN -> [SKIP][199] ([i915#6944] / [i915#9424])
[199]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-mtlp-6/igt@[email protected]
- shard-dg2: NOTRUN -> [SKIP][200] ([i915#6944] / [i915#7118] / [i915#9424])
[200]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg2-5/igt@[email protected]
- shard-rkl: NOTRUN -> [SKIP][201] ([i915#14544] / [i915#6944] / [i915#7118] / [i915#9424])
[201]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-6/igt@[email protected]
- shard-dg1: NOTRUN -> [SKIP][202] ([i915#6944] / [i915#7116] / [i915#9424])
[202]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg1-16/igt@[email protected]

* igt@kms_content_protection@atomic-hdcp14:
- shard-dg1: NOTRUN -> [SKIP][203] ([i915#6944])
[203]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg1-14/igt@[email protected]
- shard-mtlp: NOTRUN -> [SKIP][204] ([i915#6944])
[204]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-mtlp-4/igt@[email protected]
- shard-dg2: NOTRUN -> [SKIP][205] ([i915#6944])
[205]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg2-3/igt@[email protected]

* igt@kms_content_protection@dp-mst-lic-type-0:
- shard-tglu: NOTRUN -> [SKIP][206] ([i915#15330] / [i915#3116] / [i915#3299]) +1 other test skip
[206]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-tglu-6/igt@[email protected]
- shard-mtlp: NOTRUN -> [SKIP][207] ([i915#15330] / [i915#3299]) +1 other test skip
[207]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-mtlp-2/igt@[email protected]
- shard-dg2: NOTRUN -> [SKIP][208] ([i915#15330] / [i915#3299]) +1 other test skip
[208]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg2-10/igt@[email protected]

* igt@kms_content_protection@dp-mst-type-0:
- shard-rkl: NOTRUN -> [SKIP][209] ([i915#15330] / [i915#3116]) +1 other test skip
[209]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-4/igt@[email protected]
- shard-dg1: NOTRUN -> [SKIP][210] ([i915#15330] / [i915#3299]) +1 other test skip
[210]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg1-17/igt@[email protected]

* igt@kms_content_protection@dp-mst-type-0-hdcp14:
- shard-dg2: NOTRUN -> [SKIP][211] ([i915#15330]) +1 other test skip
[211]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg2-8/igt@[email protected]
- shard-rkl: NOTRUN -> [SKIP][212] ([i915#15330])
[212]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-8/igt@[email protected]
- shard-dg1: NOTRUN -> [SKIP][213] ([i915#15330]) +1 other test skip
[213]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg1-16/igt@[email protected]
- shard-tglu: NOTRUN -> [SKIP][214] ([i915#15330])
[214]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-tglu-9/igt@[email protected]

* igt@kms_content_protection@dp-mst-type-0-suspend-resume:
- shard-mtlp: NOTRUN -> [SKIP][215] ([i915#15330]) +1 other test skip
[215]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-mtlp-6/igt@[email protected]
- shard-tglu-1: NOTRUN -> [SKIP][216] ([i915#15330])
[216]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-tglu-1/igt@[email protected]

* igt@kms_content_protection@uevent-hdcp14:
- shard-tglu: NOTRUN -> [SKIP][217] ([i915#6944]) +1 other test skip
[217]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-tglu-5/igt@[email protected]
- shard-rkl: NOTRUN -> [SKIP][218] ([i915#6944]) +1 other test skip
[218]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-2/igt@[email protected]

* igt@kms_cursor_crc@cursor-offscreen-32x10:
- shard-tglu-1: NOTRUN -> [SKIP][219] ([i915#3555])
[219]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-tglu-1/igt@[email protected]

* igt@kms_cursor_crc@cursor-offscreen-512x170:
- shard-tglu: NOTRUN -> [SKIP][220] ([i915#13049]) +1 other test skip
[220]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-tglu-7/igt@[email protected]
- shard-mtlp: NOTRUN -> [SKIP][221] ([i915#13049]) +1 other test skip
[221]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-mtlp-6/igt@[email protected]
- shard-dg2: NOTRUN -> [SKIP][222] ([i915#13049]) +1 other test skip
[222]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg2-7/igt@[email protected]
- shard-rkl: NOTRUN -> [SKIP][223] ([i915#13049]) +1 other test skip
[223]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-7/igt@[email protected]
- shard-dg1: NOTRUN -> [SKIP][224] ([i915#13049]) +1 other test skip
[224]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg1-19/igt@[email protected]

* igt@kms_cursor_crc@cursor-onscreen-128x42:
- shard-mtlp: NOTRUN -> [SKIP][225] ([i915#8814])
[225]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-mtlp-8/igt@[email protected]

* igt@kms_cursor_crc@cursor-onscreen-32x10:
- shard-mtlp: NOTRUN -> [SKIP][226] ([i915#3555] / [i915#8814]) +2 other tests skip
[226]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-mtlp-2/igt@[email protected]

* igt@kms_cursor_crc@cursor-random-128x42@pipe-a-hdmi-a-1:
- shard-rkl: NOTRUN -> [FAIL][227] ([i915#13566])
[227]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-8/igt@kms_cursor_crc@[email protected]

* igt@kms_cursor_crc@cursor-rapid-movement-32x10:
- shard-rkl: NOTRUN -> [SKIP][228] ([i915#3555]) +3 other tests skip
[228]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-2/igt@[email protected]
- shard-dg1: NOTRUN -> [SKIP][229] ([i915#3555]) +4 other tests skip
[229]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg1-15/igt@[email protected]
- shard-tglu: NOTRUN -> [SKIP][230] ([i915#3555]) +4 other tests skip
[230]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-tglu-9/igt@[email protected]

* igt@kms_cursor_legacy@2x-nonblocking-modeset-vs-cursor-atomic:
- shard-mtlp: NOTRUN -> [SKIP][231] ([i915#9809]) +6 other tests skip
[231]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-mtlp-8/igt@[email protected]

* igt@kms_cursor_legacy@cursora-vs-flipb-atomic-transitions-varying-size:
- shard-rkl: NOTRUN -> [SKIP][232] +21 other tests skip
[232]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-8/igt@kms_cursor_legacy@cursora-vs-flipb-atomic-transitions-varying-size.html

* igt@kms_cursor_legacy@cursora-vs-flipb-toggle:
- shard-dg2: NOTRUN -> [SKIP][233] ([i915#13046] / [i915#5354]) +6 other tests skip
[233]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg2-1/igt@[email protected]

* igt@kms_cursor_legacy@cursora-vs-flipb-varying-size:
- shard-rkl: NOTRUN -> [SKIP][234] ([i915#14544]) +3 other tests skip
[234]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-6/igt@[email protected]

* igt@kms_cursor_legacy@short-busy-flip-before-cursor-atomic-transitions-varying-size:
- shard-rkl: NOTRUN -> [SKIP][235] ([i915#4103])
[235]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-8/igt@kms_cursor_legacy@short-busy-flip-before-cursor-atomic-transitions-varying-size.html
- shard-tglu: NOTRUN -> [SKIP][236] ([i915#4103])
[236]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-tglu-9/igt@kms_cursor_legacy@short-busy-flip-before-cursor-atomic-transitions-varying-size.html

* igt@kms_dp_link_training@non-uhbr-sst:
- shard-mtlp: NOTRUN -> [SKIP][237] ([i915#13749])
[237]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-mtlp-2/igt@[email protected]
- shard-dg2: NOTRUN -> [SKIP][238] ([i915#13749])
[238]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg2-8/igt@[email protected]
- shard-rkl: NOTRUN -> [SKIP][239] ([i915#13749])
[239]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-5/igt@[email protected]
- shard-dg1: NOTRUN -> [SKIP][240] ([i915#13749])
[240]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg1-12/igt@[email protected]
- shard-tglu: NOTRUN -> [SKIP][241] ([i915#13749])
[241]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-tglu-2/igt@[email protected]

* igt@kms_dsc@dsc-basic:
- shard-dg2: NOTRUN -> [SKIP][242] ([i915#3555] / [i915#3840]) +1 other test skip
[242]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg2-7/igt@[email protected]
- shard-rkl: NOTRUN -> [SKIP][243] ([i915#3555] / [i915#3840]) +1 other test skip
[243]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-3/igt@[email protected]
- shard-dg1: NOTRUN -> [SKIP][244] ([i915#3555] / [i915#3840]) +1 other test skip
[244]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg1-18/igt@[email protected]
- shard-tglu: NOTRUN -> [SKIP][245] ([i915#3555] / [i915#3840]) +1 other test skip
[245]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-tglu-7/igt@[email protected]
- shard-mtlp: NOTRUN -> [SKIP][246] ([i915#3555] / [i915#3840] / [i915#9159])
[246]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-mtlp-7/igt@[email protected]

* igt@kms_dsc@dsc-with-bpc-formats:
- shard-mtlp: NOTRUN -> [SKIP][247] ([i915#3555] / [i915#3840])
[247]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-mtlp-4/igt@[email protected]

* igt@kms_fbcon_fbt@psr-suspend:
- shard-rkl: NOTRUN -> [SKIP][248] ([i915#14544] / [i915#3955])
[248]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-6/igt@[email protected]
- shard-tglu-1: NOTRUN -> [SKIP][249] ([i915#3469])
[249]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-tglu-1/igt@[email protected]
- shard-dg1: NOTRUN -> [SKIP][250] ([i915#3469])
[250]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg1-14/igt@[email protected]
- shard-dg2: NOTRUN -> [SKIP][251] ([i915#3469])
[251]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg2-5/igt@[email protected]

* igt@kms_flip@2x-blocking-absolute-wf_vblank:
- shard-tglu: NOTRUN -> [SKIP][252] ([i915#3637] / [i915#9934]) +13 other tests skip
[252]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-tglu-10/igt@kms_flip@2x-blocking-absolute-wf_vblank.html

* igt@kms_flip@2x-flip-vs-dpms:
- shard-rkl: NOTRUN -> [SKIP][253] ([i915#14544] / [i915#9934]) +2 other tests skip
[253]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-6/igt@[email protected]

* igt@kms_flip@2x-flip-vs-dpms-on-nop-interruptible:
- shard-tglu: NOTRUN -> [SKIP][254] ([i915#9934])
[254]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-tglu-6/igt@[email protected]
- shard-mtlp: NOTRUN -> [SKIP][255] ([i915#9934])
[255]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-mtlp-2/igt@[email protected]

* igt@kms_flip@2x-flip-vs-expired-vblank-interruptible:
- shard-mtlp: NOTRUN -> [SKIP][256] ([i915#3637] / [i915#9934]) +11 other tests skip
[256]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-mtlp-5/igt@[email protected]

* igt@kms_flip@2x-flip-vs-suspend@ab-vga1-hdmi-a1:
- shard-snb: NOTRUN -> [TIMEOUT][257] ([i915#14033]) +1 other test timeout
[257]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-snb4/igt@kms_flip@[email protected]

* igt@kms_flip@2x-plain-flip-fb-recreate-interruptible:
- shard-dg1: NOTRUN -> [SKIP][258] ([i915#9934]) +12 other tests skip
[258]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg1-19/igt@[email protected]

* igt@kms_flip@2x-plain-flip-interruptible:
- shard-rkl: NOTRUN -> [SKIP][259] ([i915#9934]) +10 other tests skip
[259]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-5/igt@[email protected]

* igt@kms_flip@2x-single-buffer-flip-vs-dpms-off-vs-modeset:
- shard-dg2: NOTRUN -> [SKIP][260] ([i915#9934]) +12 other tests skip
[260]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg2-3/igt@[email protected]

* igt@kms_flip@flip-vs-fences:
- shard-mtlp: NOTRUN -> [SKIP][261] ([i915#8381])
[261]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-mtlp-2/igt@[email protected]
- shard-dg2: NOTRUN -> [SKIP][262] ([i915#8381])
[262]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg2-10/igt@[email protected]
- shard-dg1: NOTRUN -> [SKIP][263] ([i915#8381])
[263]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg1-13/igt@[email protected]

* igt@kms_flip_scaled_crc@flip-32bpp-4tile-to-32bpp-4tiledg2rcccs-downscaling:
- shard-tglu: NOTRUN -> [SKIP][264] ([i915#2672] / [i915#3555]) +2 other tests skip
[264]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-tglu-5/igt@kms_flip_scaled_crc@flip-32bpp-4tile-to-32bpp-4tiledg2rcccs-downscaling.html

* igt@kms_flip_scaled_crc@flip-32bpp-4tile-to-32bpp-4tiledg2rcccs-upscaling:
- shard-rkl: NOTRUN -> [SKIP][265] ([i915#2672] / [i915#3555]) +1 other test skip
[265]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-4/igt@kms_flip_scaled_crc@flip-32bpp-4tile-to-32bpp-4tiledg2rcccs-upscaling.html

* igt@kms_flip_scaled_crc@flip-32bpp-4tile-to-32bpp-4tiledg2rcccs-upscaling@pipe-a-default-mode:
- shard-mtlp: NOTRUN -> [SKIP][266] ([i915#2672] / [i915#8813]) +3 other tests skip
[266]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-mtlp-3/igt@kms_flip_scaled_crc@flip-32bpp-4tile-to-32bpp-4tiledg2rcccs-upscaling@pipe-a-default-mode.html

* igt@kms_flip_scaled_crc@flip-32bpp-4tile-to-32bpp-4tiledg2rcccs-upscaling@pipe-a-valid-mode:
- shard-rkl: NOTRUN -> [SKIP][267] ([i915#2672]) +2 other tests skip
[267]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-4/igt@kms_flip_scaled_crc@flip-32bpp-4tile-to-32bpp-4tiledg2rcccs-upscaling@pipe-a-valid-mode.html

* igt@kms_flip_scaled_crc@flip-32bpp-linear-to-32bpp-linear-reflect-x:
- shard-tglu: NOTRUN -> [SKIP][268] ([i915#15573]) +3 other tests skip
[268]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-tglu-4/igt@kms_flip_scaled_crc@flip-32bpp-linear-to-32bpp-linear-reflect-x.html
- shard-mtlp: NOTRUN -> [SKIP][269] ([i915#8813]) +3 other tests skip
[269]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-mtlp-8/igt@kms_flip_scaled_crc@flip-32bpp-linear-to-32bpp-linear-reflect-x.html

* igt@kms_flip_scaled_crc@flip-32bpp-xtile-to-64bpp-xtile-downscaling:
- shard-mtlp: NOTRUN -> [SKIP][270] ([i915#3555] / [i915#8810] / [i915#8813]) +1 other test skip
[270]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-mtlp-4/igt@kms_flip_scaled_crc@flip-32bpp-xtile-to-64bpp-xtile-downscaling.html

* igt@kms_flip_scaled_crc@flip-32bpp-yftile-to-32bpp-yftileccs-upscaling:
- shard-mtlp: NOTRUN -> [SKIP][271] ([i915#2672] / [i915#3555] / [i915#8813]) +4 other tests skip
[271]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-mtlp-7/igt@kms_flip_scaled_crc@flip-32bpp-yftile-to-32bpp-yftileccs-upscaling.html

* igt@kms_flip_scaled_crc@flip-32bpp-yftile-to-32bpp-yftileccs-upscaling@pipe-a-valid-mode:
- shard-dg1: NOTRUN -> [SKIP][272] ([i915#2587] / [i915#2672]) +3 other tests skip
[272]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg1-17/igt@kms_flip_scaled_crc@flip-32bpp-yftile-to-32bpp-yftileccs-upscaling@pipe-a-valid-mode.html

* igt@kms_flip_scaled_crc@flip-32bpp-yftileccs-to-64bpp-yftile-downscaling:
- shard-dg2: NOTRUN -> [SKIP][273] ([i915#2672] / [i915#3555]) +2 other tests skip
[273]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg2-6/igt@kms_flip_scaled_crc@flip-32bpp-yftileccs-to-64bpp-yftile-downscaling.html

* igt@kms_flip_scaled_crc@flip-32bpp-yftileccs-to-64bpp-yftile-downscaling@pipe-a-valid-mode:
- shard-dg2: NOTRUN -> [SKIP][274] ([i915#2672]) +4 other tests skip
[274]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg2-6/igt@kms_flip_scaled_crc@flip-32bpp-yftileccs-to-64bpp-yftile-downscaling@pipe-a-valid-mode.html

* igt@kms_flip_scaled_crc@flip-32bpp-ytileccs-to-64bpp-ytile-downscaling@pipe-a-valid-mode:
- shard-tglu: NOTRUN -> [SKIP][275] ([i915#2587] / [i915#2672]) +3 other tests skip
[275]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-tglu-2/igt@kms_flip_scaled_crc@flip-32bpp-ytileccs-to-64bpp-ytile-downscaling@pipe-a-valid-mode.html

* igt@kms_flip_scaled_crc@flip-32bpp-yuv-linear-to-32bpp-yuv-linear-reflect-x:
- shard-rkl: NOTRUN -> [SKIP][276] ([i915#15573]) +1 other test skip
[276]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-4/igt@kms_flip_scaled_crc@flip-32bpp-yuv-linear-to-32bpp-yuv-linear-reflect-x.html
- shard-dg1: NOTRUN -> [SKIP][277] ([i915#15573]) +3 other tests skip
[277]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg1-15/igt@kms_flip_scaled_crc@flip-32bpp-yuv-linear-to-32bpp-yuv-linear-reflect-x.html

* igt@kms_flip_scaled_crc@flip-32bpp-yuv-linear-to-32bpp-yuv-linear-reflect-x@pipe-a-valid-mode:
- shard-dg2: NOTRUN -> [SKIP][278] ([i915#15573]) +3 other tests skip
[278]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg2-11/igt@kms_flip_scaled_crc@flip-32bpp-yuv-linear-to-32bpp-yuv-linear-reflect-x@pipe-a-valid-mode.html

* igt@kms_flip_scaled_crc@flip-64bpp-yftile-to-32bpp-yftile-downscaling:
- shard-dg1: NOTRUN -> [SKIP][279] ([i915#2672] / [i915#3555]) +2 other tests skip
[279]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg1-14/igt@kms_flip_scaled_crc@flip-64bpp-yftile-to-32bpp-yftile-downscaling.html

* igt@kms_flip_scaled_crc@flip-64bpp-ytile-to-16bpp-ytile-upscaling:
- shard-dg2: NOTRUN -> [SKIP][280] ([i915#2672] / [i915#3555] / [i915#5190])
[280]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg2-5/igt@kms_flip_scaled_crc@flip-64bpp-ytile-to-16bpp-ytile-upscaling.html

* igt@kms_frontbuffer_tracking@fbc-1p-offscreen-pri-shrfb-draw-mmap-wc:
- shard-dg1: NOTRUN -> [SKIP][281] ([i915#15104])
[281]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg1-17/igt@kms_frontbuffer_tracking@fbc-1p-offscreen-pri-shrfb-draw-mmap-wc.html
- shard-dg2: NOTRUN -> [SKIP][282] ([i915#15104])
[282]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg2-6/igt@kms_frontbuffer_tracking@fbc-1p-offscreen-pri-shrfb-draw-mmap-wc.html

* igt@kms_frontbuffer_tracking@fbc-2p-primscrn-spr-indfb-onoff:
- shard-mtlp: NOTRUN -> [SKIP][283] ([i915#1825]) +26 other tests skip
[283]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-mtlp-5/igt@[email protected]

* igt@kms_frontbuffer_tracking@fbc-2p-rte:
- shard-dg2: NOTRUN -> [SKIP][284] ([i915#5354]) +22 other tests skip
[284]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg2-4/igt@[email protected]

* igt@kms_frontbuffer_tracking@fbc-2p-scndscrn-cur-indfb-draw-render:
- shard-dg1: NOTRUN -> [SKIP][285] +35 other tests skip
[285]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg1-12/igt@kms_frontbuffer_tracking@fbc-2p-scndscrn-cur-indfb-draw-render.html

* igt@kms_frontbuffer_tracking@fbc-2p-scndscrn-pri-shrfb-draw-mmap-gtt:
- shard-rkl: NOTRUN -> [SKIP][286] ([i915#1825]) +27 other tests skip
[286]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-4/igt@kms_frontbuffer_tracking@fbc-2p-scndscrn-pri-shrfb-draw-mmap-gtt.html

* igt@kms_frontbuffer_tracking@fbc-abgr161616f-draw-mmap-wc:
- shard-mtlp: NOTRUN -> [SKIP][287] ([i915#15574]) +4 other tests skip
[287]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-mtlp-5/igt@[email protected]

* igt@kms_frontbuffer_tracking@fbc-argb161616f-draw-pwrite:
- shard-tglu: NOTRUN -> [SKIP][288] ([i915#15574]) +4 other tests skip
[288]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-tglu-10/igt@[email protected]

* igt@kms_frontbuffer_tracking@fbc-suspend:
- shard-glk: NOTRUN -> [INCOMPLETE][289] ([i915#10056])
[289]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-glk5/igt@[email protected]

* igt@kms_frontbuffer_tracking@fbcpsr-1p-offscreen-pri-indfb-draw-render:
- shard-rkl: NOTRUN -> [SKIP][290] ([i915#15102]) +2 other tests skip
[290]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-8/igt@kms_frontbuffer_tracking@fbcpsr-1p-offscreen-pri-indfb-draw-render.html
- shard-dg1: NOTRUN -> [SKIP][291] ([i915#15102]) +1 other test skip
[291]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg1-16/igt@kms_frontbuffer_tracking@fbcpsr-1p-offscreen-pri-indfb-draw-render.html

* igt@kms_frontbuffer_tracking@fbcpsr-2p-primscrn-cur-indfb-draw-render:
- shard-rkl: NOTRUN -> [SKIP][292] ([i915#14544] / [i915#1825]) +4 other tests skip
[292]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-6/igt@kms_frontbuffer_tracking@fbcpsr-2p-primscrn-cur-indfb-draw-render.html

* igt@kms_frontbuffer_tracking@fbcpsr-argb161616f-draw-mmap-wc:
- shard-dg2: NOTRUN -> [SKIP][293] ([i915#15574]) +4 other tests skip
[293]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg2-5/igt@[email protected]
- shard-rkl: NOTRUN -> [SKIP][294] ([i915#14544] / [i915#15574]) +1 other test skip
[294]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-6/igt@[email protected]
- shard-tglu-1: NOTRUN -> [SKIP][295] ([i915#15574])
[295]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-tglu-1/igt@[email protected]

* igt@kms_frontbuffer_tracking@psr-1p-offscreen-pri-shrfb-draw-mmap-cpu:
- shard-dg2: NOTRUN -> [SKIP][296] ([i915#15102]) +1 other test skip
[296]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg2-5/igt@kms_frontbuffer_tracking@psr-1p-offscreen-pri-shrfb-draw-mmap-cpu.html

* igt@kms_frontbuffer_tracking@psr-1p-primscrn-cur-indfb-draw-mmap-wc:
- shard-dg1: NOTRUN -> [SKIP][297] ([i915#8708]) +15 other tests skip
[297]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg1-17/igt@kms_frontbuffer_tracking@psr-1p-primscrn-cur-indfb-draw-mmap-wc.html

* igt@kms_frontbuffer_tracking@psr-1p-primscrn-pri-indfb-draw-mmap-gtt:
- shard-mtlp: NOTRUN -> [SKIP][298] ([i915#8708]) +7 other tests skip
[298]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-mtlp-8/igt@kms_frontbuffer_tracking@psr-1p-primscrn-pri-indfb-draw-mmap-gtt.html

* igt@kms_frontbuffer_tracking@psr-1p-primscrn-pri-indfb-draw-render:
- shard-rkl: NOTRUN -> [SKIP][299] ([i915#15102] / [i915#3023]) +24 other tests skip
[299]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-3/igt@kms_frontbuffer_tracking@psr-1p-primscrn-pri-indfb-draw-render.html

* igt@kms_frontbuffer_tracking@psr-1p-primscrn-spr-indfb-draw-mmap-wc:
- shard-dg2: NOTRUN -> [SKIP][300] ([i915#8708]) +15 other tests skip
[300]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg2-8/igt@kms_frontbuffer_tracking@psr-1p-primscrn-spr-indfb-draw-mmap-wc.html

* igt@kms_frontbuffer_tracking@psr-2p-primscrn-cur-indfb-onoff:
- shard-tglu-1: NOTRUN -> [SKIP][301] +7 other tests skip
[301]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-tglu-1/igt@[email protected]

* igt@kms_frontbuffer_tracking@psr-2p-scndscrn-pri-shrfb-draw-mmap-wc:
- shard-tglu: NOTRUN -> [SKIP][302] +61 other tests skip
[302]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-tglu-2/igt@kms_frontbuffer_tracking@psr-2p-scndscrn-pri-shrfb-draw-mmap-wc.html

* igt@kms_frontbuffer_tracking@psr-abgr161616f-draw-render:
- shard-rkl: NOTRUN -> [SKIP][303] ([i915#15574]) +1 other test skip
[303]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-8/igt@[email protected]

* igt@kms_frontbuffer_tracking@psr-argb161616f-draw-mmap-wc:
- shard-dg1: NOTRUN -> [SKIP][304] ([i915#15574]) +4 other tests skip
[304]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg1-17/igt@[email protected]

* igt@kms_frontbuffer_tracking@psr-indfb-scaledprimary:
- shard-dg2: NOTRUN -> [SKIP][305] ([i915#15102] / [i915#3458]) +14 other tests skip
[305]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg2-7/igt@[email protected]

* igt@kms_frontbuffer_tracking@psr-rgb101010-draw-pwrite:
- shard-tglu-1: NOTRUN -> [SKIP][306] ([i915#15102])
[306]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-tglu-1/igt@[email protected]

* igt@kms_frontbuffer_tracking@psr-rgb565-draw-mmap-gtt:
- shard-rkl: NOTRUN -> [SKIP][307] ([i915#14544] / [i915#15102] / [i915#3023])
[307]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-6/igt@[email protected]

* igt@kms_frontbuffer_tracking@psr-rgb565-draw-pwrite:
- shard-dg1: NOTRUN -> [SKIP][308] ([i915#15102] / [i915#3458]) +14 other tests skip
[308]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg1-14/igt@[email protected]

* igt@kms_frontbuffer_tracking@psr-shrfb-scaledprimary:
- shard-tglu: NOTRUN -> [SKIP][309] ([i915#15102]) +28 other tests skip
[309]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-tglu-10/igt@[email protected]

* igt@kms_hdr@static-swap:
- shard-dg1: NOTRUN -> [SKIP][310] ([i915#3555] / [i915#8228])
[310]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg1-12/igt@[email protected]
- shard-tglu: NOTRUN -> [SKIP][311] ([i915#3555] / [i915#8228]) +1 other test skip
[311]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-tglu-4/igt@[email protected]
- shard-mtlp: NOTRUN -> [SKIP][312] ([i915#12713] / [i915#3555] / [i915#8228])
[312]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-mtlp-4/igt@[email protected]
- shard-dg2: NOTRUN -> [SKIP][313] ([i915#3555] / [i915#8228])
[313]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg2-3/igt@[email protected]

* igt@kms_hdr@static-toggle-dpms:
- shard-rkl: NOTRUN -> [SKIP][314] ([i915#3555] / [i915#8228]) +1 other test skip
[314]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-8/igt@[email protected]

* igt@kms_joiner@basic-big-joiner:
- shard-rkl: NOTRUN -> [SKIP][315] ([i915#15460])
[315]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-4/igt@[email protected]
- shard-dg1: NOTRUN -> [SKIP][316] ([i915#15460])
[316]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg1-17/igt@[email protected]
- shard-tglu: NOTRUN -> [SKIP][317] ([i915#15460])
[317]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-tglu-2/igt@[email protected]
- shard-mtlp: NOTRUN -> [SKIP][318] ([i915#15460])
[318]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-mtlp-3/igt@[email protected]
- shard-dg2: NOTRUN -> [SKIP][319] ([i915#15460])
[319]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg2-6/igt@[email protected]

* igt@kms_joiner@basic-max-non-joiner:
- shard-tglu: NOTRUN -> [SKIP][320] ([i915#13688])
[320]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-tglu-9/igt@[email protected]
- shard-mtlp: NOTRUN -> [SKIP][321] ([i915#13688])
[321]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-mtlp-5/igt@[email protected]
- shard-dg2: NOTRUN -> [SKIP][322] ([i915#13688])
[322]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg2-8/igt@[email protected]
- shard-rkl: NOTRUN -> [SKIP][323] ([i915#13688])
[323]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-8/igt@[email protected]
- shard-dg1: NOTRUN -> [SKIP][324] ([i915#13688])
[324]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg1-16/igt@[email protected]

* igt@kms_joiner@switch-modeset-ultra-joiner-big-joiner:
- shard-tglu-1: NOTRUN -> [SKIP][325] ([i915#13522])
[325]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-tglu-1/igt@[email protected]
- shard-dg1: NOTRUN -> [SKIP][326] ([i915#13522])
[326]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg1-14/igt@[email protected]
- shard-mtlp: NOTRUN -> [SKIP][327] ([i915#13522])
[327]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-mtlp-8/igt@[email protected]
- shard-dg2: NOTRUN -> [SKIP][328] ([i915#13522])
[328]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg2-5/igt@[email protected]
- shard-rkl: NOTRUN -> [SKIP][329] ([i915#13522] / [i915#14544])
[329]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-6/igt@[email protected]

* igt@kms_multipipe_modeset@basic-max-pipe-crc-check:
- shard-mtlp: NOTRUN -> [SKIP][330] ([i915#4816])
[330]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-mtlp-3/igt@[email protected]
- shard-dg2: NOTRUN -> [SKIP][331] ([i915#4816])
[331]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg2-6/igt@[email protected]
- shard-rkl: NOTRUN -> [SKIP][332] ([i915#1839] / [i915#4816])
[332]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-4/igt@[email protected]
- shard-dg1: NOTRUN -> [SKIP][333] ([i915#1839])
[333]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg1-17/igt@[email protected]
- shard-tglu: NOTRUN -> [SKIP][334] ([i915#1839])
[334]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-tglu-2/igt@[email protected]

* igt@kms_plane_alpha_blend@alpha-basic:
- shard-glk: NOTRUN -> [FAIL][335] ([i915#12178])
[335]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-glk6/igt@[email protected]

* igt@kms_plane_alpha_blend@alpha-basic@pipe-c-hdmi-a-1:
- shard-glk: NOTRUN -> [FAIL][336] ([i915#7862]) +1 other test fail
[336]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-glk6/igt@kms_plane_alpha_blend@[email protected]

* igt@kms_plane_multiple@2x-tiling-x:
- shard-dg2: NOTRUN -> [SKIP][337] ([i915#13958])
[337]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg2-3/igt@[email protected]
- shard-dg1: NOTRUN -> [SKIP][338] ([i915#13958])
[338]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg1-16/igt@[email protected]
- shard-mtlp: NOTRUN -> [SKIP][339] ([i915#13958])
[339]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-mtlp-8/igt@[email protected]

* igt@kms_plane_multiple@2x-tiling-y:
- shard-rkl: NOTRUN -> [SKIP][340] ([i915#13958]) +1 other test skip
[340]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-2/igt@[email protected]
- shard-tglu: NOTRUN -> [SKIP][341] ([i915#13958]) +1 other test skip
[341]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-tglu-5/igt@[email protected]

* igt@kms_plane_scaling@planes-downscale-factor-0-75:
- shard-mtlp: NOTRUN -> [SKIP][342] ([i915#15329] / [i915#3555] / [i915#6953])
[342]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-mtlp-8/igt@[email protected]

* igt@kms_plane_scaling@planes-downscale-factor-0-75@pipe-b:
- shard-mtlp: NOTRUN -> [SKIP][343] ([i915#15329]) +8 other tests skip
[343]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-mtlp-8/igt@kms_plane_scaling@[email protected]

* igt@kms_pm_dc@dc5-psr:
- shard-rkl: NOTRUN -> [SKIP][344] ([i915#9685]) +1 other test skip
[344]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-2/igt@[email protected]
- shard-dg1: NOTRUN -> [SKIP][345] ([i915#9685])
[345]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg1-15/igt@[email protected]
- shard-dg2: NOTRUN -> [SKIP][346] ([i915#9685])
[346]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg2-11/igt@[email protected]

* igt@kms_pm_rpm@i2c:
- shard-dg1: NOTRUN -> [DMESG-WARN][347] ([i915#4423])
[347]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg1-16/igt@[email protected]

* igt@kms_pm_rpm@modeset-non-lpsp:
- shard-tglu: NOTRUN -> [SKIP][348] ([i915#15073]) +1 other test skip
[348]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-tglu-9/igt@[email protected]
- shard-mtlp: NOTRUN -> [SKIP][349] ([i915#15073]) +1 other test skip
[349]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-mtlp-5/igt@[email protected]

* igt@kms_pm_rpm@modeset-non-lpsp-stress:
- shard-rkl: NOTRUN -> [SKIP][350] ([i915#15073]) +1 other test skip
[350]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-8/igt@[email protected]
- shard-dg1: NOTRUN -> [SKIP][351] ([i915#15073])
[351]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg1-14/igt@[email protected]

* igt@kms_pm_rpm@package-g7:
- shard-tglu: NOTRUN -> [SKIP][352] ([i915#15403])
[352]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-tglu-8/igt@[email protected]
- shard-mtlp: NOTRUN -> [SKIP][353] ([i915#15403])
[353]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-mtlp-5/igt@[email protected]
- shard-dg2: NOTRUN -> [SKIP][354] ([i915#15403])
[354]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg2-1/igt@[email protected]
- shard-rkl: NOTRUN -> [SKIP][355] ([i915#15403])
[355]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-7/igt@[email protected]
- shard-dg1: NOTRUN -> [SKIP][356] ([i915#15403])
[356]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg1-13/igt@[email protected]

* igt@kms_pm_rpm@system-suspend-idle:
- shard-rkl: NOTRUN -> [INCOMPLETE][357] ([i915#14419])
[357]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-6/igt@[email protected]

* igt@kms_prime@basic-modeset-hybrid:
- shard-rkl: NOTRUN -> [SKIP][358] ([i915#6524])
[358]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-7/igt@[email protected]
- shard-dg1: NOTRUN -> [SKIP][359] ([i915#6524])
[359]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg1-13/igt@[email protected]
- shard-tglu: NOTRUN -> [SKIP][360] ([i915#6524])
[360]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-tglu-8/igt@[email protected]
- shard-mtlp: NOTRUN -> [SKIP][361] ([i915#6524])
[361]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-mtlp-5/igt@[email protected]
- shard-dg2: NOTRUN -> [SKIP][362] ([i915#6524] / [i915#6805])
[362]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg2-1/igt@[email protected]

* igt@kms_psr2_sf@fbc-pr-cursor-plane-update-sf:
- shard-glk: NOTRUN -> [SKIP][363] ([i915#11520]) +4 other tests skip
[363]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-glk5/igt@[email protected]
- shard-tglu-1: NOTRUN -> [SKIP][364] ([i915#11520])
[364]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-tglu-1/igt@[email protected]

* igt@kms_psr2_sf@fbc-psr2-cursor-plane-move-continuous-sf:
- shard-dg1: NOTRUN -> [SKIP][365] ([i915#11520]) +7 other tests skip
[365]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg1-16/igt@[email protected]

* igt@kms_psr2_sf@fbc-psr2-cursor-plane-move-continuous-sf@pipe-a-edp-1:
- shard-mtlp: NOTRUN -> [SKIP][366] ([i915#9808]) +1 other test skip
[366]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-mtlp-6/igt@kms_psr2_sf@[email protected]

* igt@kms_psr2_sf@fbc-psr2-overlay-plane-update-continuous-sf:
- shard-mtlp: NOTRUN -> [SKIP][367] ([i915#12316]) +7 other tests skip
[367]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-mtlp-4/igt@[email protected]

* igt@kms_psr2_sf@pr-overlay-plane-update-sf-dmg-area:
- shard-rkl: NOTRUN -> [SKIP][368] ([i915#11520]) +7 other tests skip
[368]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-5/igt@[email protected]

* igt@kms_psr2_sf@pr-overlay-primary-update-sf-dmg-area:
- shard-tglu: NOTRUN -> [SKIP][369] ([i915#11520]) +9 other tests skip
[369]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-tglu-5/igt@[email protected]

* igt@kms_psr2_sf@psr2-overlay-plane-update-sf-dmg-area:
- shard-dg2: NOTRUN -> [SKIP][370] ([i915#11520]) +7 other tests skip
[370]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg2-6/igt@[email protected]

* igt@kms_psr2_sf@psr2-primary-plane-update-sf-dmg-area:
- shard-rkl: NOTRUN -> [SKIP][371] ([i915#11520] / [i915#14544]) +1 other test skip
[371]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-6/igt@[email protected]

* igt@kms_psr2_sf@psr2-primary-plane-update-sf-dmg-area-big-fb:
- shard-snb: NOTRUN -> [SKIP][372] ([i915#11520]) +9 other tests skip
[372]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-snb7/igt@[email protected]

* igt@kms_psr2_su@frontbuffer-xrgb8888:
- shard-mtlp: NOTRUN -> [SKIP][373] ([i915#4348])
[373]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-mtlp-5/igt@[email protected]
- shard-dg2: NOTRUN -> [SKIP][374] ([i915#9683])
[374]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg2-1/igt@[email protected]
- shard-rkl: NOTRUN -> [SKIP][375] ([i915#9683])
[375]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-7/igt@[email protected]
- shard-dg1: NOTRUN -> [SKIP][376] ([i915#9683])
[376]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg1-13/igt@[email protected]
- shard-tglu: NOTRUN -> [SKIP][377] ([i915#9683])
[377]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-tglu-8/igt@[email protected]

* igt@kms_psr@fbc-pr-basic:
- shard-mtlp: NOTRUN -> [SKIP][378] ([i915#9688]) +19 other tests skip
[378]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-mtlp-5/igt@[email protected]

* igt@kms_psr@fbc-pr-no-drrs:
- shard-rkl: NOTRUN -> [SKIP][379] ([i915#1072] / [i915#9732]) +15 other tests skip
[379]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-2/igt@[email protected]

* igt@kms_psr@fbc-psr2-cursor-plane-move:
- shard-tglu: NOTRUN -> [SKIP][380] ([i915#9732]) +17 other tests skip
[380]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-tglu-10/igt@[email protected]

* igt@kms_psr@psr2-primary-mmap-cpu:
- shard-tglu-1: NOTRUN -> [SKIP][381] ([i915#9732]) +1 other test skip
[381]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-tglu-1/igt@[email protected]
- shard-dg1: NOTRUN -> [SKIP][382] ([i915#1072] / [i915#9732]) +17 other tests skip
[382]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg1-14/igt@[email protected]

* igt@kms_psr@psr2-primary-mmap-gtt:
- shard-dg2: NOTRUN -> [SKIP][383] ([i915#1072] / [i915#9732]) +17 other tests skip
[383]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg2-7/igt@[email protected]

* igt@kms_psr@psr2-primary-mmap-gtt@edp-1:
- shard-mtlp: NOTRUN -> [SKIP][384] ([i915#4077] / [i915#9688]) +1 other test skip
[384]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-mtlp-7/igt@kms_psr@[email protected]

* igt@kms_psr@psr2-sprite-plane-move:
- shard-rkl: NOTRUN -> [SKIP][385] ([i915#1072] / [i915#14544] / [i915#9732]) +3 other tests skip
[385]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-6/igt@[email protected]

* igt@kms_psr_stress_test@invalidate-primary-flip-overlay:
- shard-tglu: NOTRUN -> [SKIP][386] ([i915#9685]) +1 other test skip
[386]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-tglu-9/igt@[email protected]

* igt@kms_rotation_crc@primary-rotation-270:
- shard-dg2: NOTRUN -> [SKIP][387] ([i915#12755]) +1 other test skip
[387]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg2-4/igt@[email protected]

* igt@kms_rotation_crc@primary-rotation-90:
- shard-mtlp: NOTRUN -> [SKIP][388] ([i915#12755]) +2 other tests skip
[388]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-mtlp-6/igt@[email protected]

* igt@kms_rotation_crc@primary-y-tiled-reflect-x-270:
- shard-dg2: NOTRUN -> [SKIP][389] ([i915#12755] / [i915#5190])
[389]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg2-3/igt@[email protected]

* igt@kms_scaling_modes@scaling-mode-none:
- shard-dg2: NOTRUN -> [SKIP][390] ([i915#3555]) +4 other tests skip
[390]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg2-6/igt@[email protected]
- shard-mtlp: NOTRUN -> [SKIP][391] ([i915#3555] / [i915#5030] / [i915#9041])
[391]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-mtlp-3/igt@[email protected]

* igt@kms_scaling_modes@scaling-mode-none@pipe-a-edp-1:
- shard-mtlp: NOTRUN -> [SKIP][392] ([i915#5030]) +2 other tests skip
[392]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-mtlp-3/igt@kms_scaling_modes@[email protected]

* igt@kms_scaling_modes@scaling-mode-none@pipe-d-edp-1:
- shard-mtlp: NOTRUN -> [SKIP][393] ([i915#5030] / [i915#9041])
[393]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-mtlp-3/igt@kms_scaling_modes@[email protected]

* igt@kms_setmode@basic:
- shard-snb: NOTRUN -> [FAIL][394] ([i915#15106]) +2 other tests fail
[394]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-snb5/igt@[email protected]
- shard-tglu: NOTRUN -> [FAIL][395] ([i915#15106]) +2 other tests fail
[395]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-tglu-3/igt@[email protected]

* igt@kms_setmode@invalid-clone-single-crtc-stealing:
- shard-rkl: NOTRUN -> [SKIP][396] ([i915#14544] / [i915#3555]) +1 other test skip
[396]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-6/igt@[email protected]
- shard-mtlp: NOTRUN -> [SKIP][397] ([i915#3555] / [i915#8809])
[397]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-mtlp-6/igt@[email protected]

* igt@kms_vrr@flipline:
- shard-rkl: NOTRUN -> [SKIP][398] ([i915#15243] / [i915#3555])
[398]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-8/igt@[email protected]

* igt@kms_vrr@lobf:
- shard-rkl: NOTRUN -> [SKIP][399] ([i915#11920])
[399]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-2/igt@[email protected]
- shard-tglu: NOTRUN -> [SKIP][400] ([i915#11920])
[400]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-tglu-5/igt@[email protected]

* igt@kms_vrr@seamless-rr-switch-virtual:
- shard-dg2: NOTRUN -> [SKIP][401] ([i915#9906])
[401]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg2-3/igt@[email protected]
- shard-rkl: NOTRUN -> [SKIP][402] ([i915#9906])
[402]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-8/igt@[email protected]
- shard-dg1: NOTRUN -> [SKIP][403] ([i915#9906])
[403]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg1-14/igt@[email protected]
- shard-tglu: NOTRUN -> [SKIP][404] ([i915#9906])
[404]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-tglu-10/igt@[email protected]
- shard-mtlp: NOTRUN -> [SKIP][405] ([i915#8808] / [i915#9906])
[405]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-mtlp-4/igt@[email protected]

* igt@perf_pmu@busy-double-start@ccs0:
- shard-mtlp: NOTRUN -> [FAIL][406] ([i915#4349])
[406]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-mtlp-3/igt@perf_pmu@[email protected]

* igt@perf_pmu@idle@rcs0:
- shard-snb: NOTRUN -> [ABORT][407] ([i915#15602]) +9 other tests abort
[407]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-snb4/igt@perf_pmu@[email protected]

* igt@perf_pmu@multi-client@rcs0:
- shard-dg1: NOTRUN -> [ABORT][408] ([i915#15602]) +11 other tests abort
[408]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg1-13/igt@perf_pmu@[email protected]

* igt@perf_pmu@rc6:
- shard-rkl: NOTRUN -> [ABORT][409] ([i915#15602]) +11 other tests abort
[409]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-5/igt@[email protected]
- shard-glk: NOTRUN -> [ABORT][410] ([i915#15602]) +1 other test abort
[410]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-glk9/igt@[email protected]

* igt@perf_pmu@rc6@gt0:
- shard-dg2: NOTRUN -> [ABORT][411] ([i915#15602]) +11 other tests abort
[411]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg2-10/igt@perf_pmu@[email protected]

* igt@perf_pmu@rc6@other-idle-gt0:
- shard-dg2: NOTRUN -> [SKIP][412] ([i915#8516])
[412]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg2-10/igt@perf_pmu@[email protected]
- shard-rkl: NOTRUN -> [SKIP][413] ([i915#8516])
[413]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-5/igt@perf_pmu@[email protected]
- shard-dg1: NOTRUN -> [SKIP][414] ([i915#8516])
[414]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg1-13/igt@perf_pmu@[email protected]
- shard-tglu: NOTRUN -> [SKIP][415] ([i915#8516])
[415]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-tglu-6/igt@perf_pmu@[email protected]

#### Possible fixes ####

* igt@api_intel_bb@misplaced-blitter:
- shard-snb: [SKIP][416] -> [PASS][417] +35 other tests pass
[416]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/shard-snb7/igt@[email protected]
[417]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-snb5/igt@[email protected]

* igt@core_getversion@basic:
- shard-dg2: [FAIL][418] -> [PASS][419]
[418]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/shard-dg2-4/igt@[email protected]
[419]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg2-11/igt@[email protected]
- shard-rkl: [FAIL][420] -> [PASS][421]
[420]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/shard-rkl-2/igt@[email protected]
[421]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-6/igt@[email protected]
- shard-dg1: [FAIL][422] -> [PASS][423]
[422]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/shard-dg1-19/igt@[email protected]
[423]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg1-15/igt@[email protected]
- shard-snb: [FAIL][424] -> [PASS][425]
[424]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/shard-snb7/igt@[email protected]
[425]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-snb6/igt@[email protected]
- shard-tglu: [FAIL][426] -> [PASS][427]
[426]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/shard-tglu-10/igt@[email protected]
[427]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-tglu-10/igt@[email protected]
- shard-mtlp: [FAIL][428] -> [PASS][429]
[428]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/shard-mtlp-8/igt@[email protected]
[429]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-mtlp-2/igt@[email protected]

* igt@gem_create@busy-create:
- shard-rkl: [SKIP][430] -> [PASS][431] +15 other tests pass
[430]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/shard-rkl-2/igt@[email protected]
[431]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-4/igt@[email protected]

* igt@gem_ctx_persistence@legacy-engines-hostile-preempt:
- shard-dg1: [SKIP][432] ([i915#2575]) -> [PASS][433] +7 other tests pass
[432]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/shard-dg1-19/igt@[email protected]
[433]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg1-12/igt@[email protected]

* igt@gem_exec_endless@dispatch:
- shard-glk: [SKIP][434] -> [PASS][435] +5 other tests pass
[434]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/shard-glk3/igt@[email protected]
[435]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-glk9/igt@[email protected]
- shard-mtlp: [SKIP][436] ([i915#2575]) -> [PASS][437] +8 other tests pass
[436]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/shard-mtlp-8/igt@[email protected]
[437]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-mtlp-2/igt@[email protected]

* igt@gem_exec_whisper@basic-forked-all:
- shard-dg2: [SKIP][438] ([i915#2575]) -> [PASS][439] +7 other tests pass
[438]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/shard-dg2-4/igt@[email protected]
[439]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg2-6/igt@[email protected]

* igt@gem_flink_basic@bad-flink:
- shard-tglu: [SKIP][440] ([i915#2575]) -> [PASS][441] +16 other tests pass
[440]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/shard-tglu-10/igt@[email protected]
[441]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-tglu-10/igt@[email protected]

* igt@i915_pm_rpm@system-suspend:
- shard-dg1: [SKIP][442] -> [PASS][443] +6 other tests pass
[442]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/shard-dg1-19/igt@[email protected]
[443]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg1-17/igt@[email protected]
- shard-tglu: [SKIP][444] -> [PASS][445] +1 other test pass
[444]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/shard-tglu-10/igt@[email protected]
[445]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-tglu-2/igt@[email protected]

* igt@kms_cursor_edge_walk@256x256-right-edge:
- shard-mtlp: [SKIP][446] -> [PASS][447] +5 other tests pass
[446]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/shard-mtlp-8/igt@[email protected]
[447]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-mtlp-6/igt@[email protected]

* igt@kms_flip@absolute-wf_vblank-interruptible:
- shard-dg2: [SKIP][448] -> [PASS][449] +6 other tests pass
[448]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/shard-dg2-4/igt@kms_flip@absolute-wf_vblank-interruptible.html
[449]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg2-4/igt@kms_flip@absolute-wf_vblank-interruptible.html

* igt@kms_pipe_crc_basic@suspend-read-crc:
- shard-rkl: [INCOMPLETE][450] ([i915#12756] / [i915#13476]) -> [PASS][451]
[450]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/shard-rkl-6/igt@[email protected]
[451]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-2/igt@[email protected]

#### Warnings ####

* igt@gem_bad_reloc@negative-reloc:
- shard-rkl: [SKIP][452] ([i915#3281]) -> [SKIP][453] ([i915#14544] / [i915#3281])
[452]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/shard-rkl-4/igt@[email protected]
[453]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-6/igt@[email protected]

* igt@gem_ctx_persistence@legacy-engines-hostile-preempt:
- shard-snb: [SKIP][454] -> [SKIP][455] ([i915#1099])
[454]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/shard-snb7/igt@[email protected]
[455]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-snb1/igt@[email protected]

* igt@gem_exec_balancer@busy:
- shard-tglu: [ABORT][456] -> [ABORT][457] ([i915#15602])
[456]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/shard-tglu-6/igt@[email protected]
[457]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-tglu-7/igt@[email protected]
- shard-dg2: [ABORT][458] -> [ABORT][459] ([i915#15602])
[458]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/shard-dg2-7/igt@[email protected]
[459]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg2-7/igt@[email protected]

* igt@gem_lmem_evict@dontneed-evict-race:
- shard-rkl: [SKIP][460] -> [SKIP][461] ([i915#4613] / [i915#7582])
[460]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/shard-rkl-2/igt@[email protected]
[461]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-4/igt@[email protected]
- shard-tglu: [SKIP][462] -> [SKIP][463] ([i915#4613] / [i915#7582])
[462]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/shard-tglu-10/igt@[email protected]
[463]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-tglu-2/igt@[email protected]
- shard-mtlp: [SKIP][464] -> [SKIP][465] ([i915#4613])
[464]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/shard-mtlp-8/igt@[email protected]
[465]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-mtlp-3/igt@[email protected]

* igt@gem_partial_pwrite_pread@write-snoop:
- shard-mtlp: [SKIP][466] ([i915#2575]) -> [SKIP][467] ([i915#3282]) +1 other test skip
[466]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/shard-mtlp-8/igt@[email protected]
[467]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-mtlp-2/igt@[email protected]
- shard-rkl: [SKIP][468] -> [SKIP][469] ([i915#14544] / [i915#3282])
[468]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/shard-rkl-2/igt@[email protected]
[469]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-6/igt@[email protected]

* igt@gem_pread@self:
- shard-dg2: [SKIP][470] ([i915#2575]) -> [SKIP][471] ([i915#3282]) +1 other test skip
[470]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/shard-dg2-4/igt@[email protected]
[471]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg2-6/igt@[email protected]
- shard-dg1: [SKIP][472] ([i915#2575]) -> [SKIP][473] ([i915#3282]) +1 other test skip
[472]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/shard-dg1-19/igt@[email protected]
[473]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg1-17/igt@[email protected]

* igt@gem_readwrite@beyond-eob:
- shard-rkl: [SKIP][474] -> [SKIP][475] ([i915#3282]) +1 other test skip
[474]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/shard-rkl-2/igt@[email protected]
[475]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-8/igt@[email protected]

* igt@kms_big_fb@4-tiled-8bpp-rotate-270:
- shard-mtlp: [SKIP][476] ([i915#2575]) -> [SKIP][477] +1 other test skip
[476]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/shard-mtlp-8/igt@[email protected]
[477]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-mtlp-2/igt@[email protected]
- shard-rkl: [SKIP][478] -> [SKIP][479] ([i915#14544] / [i915#5286])
[478]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/shard-rkl-2/igt@[email protected]
[479]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-6/igt@[email protected]
- shard-dg1: [SKIP][480] -> [SKIP][481] ([i915#4538] / [i915#5286])
[480]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/shard-dg1-19/igt@[email protected]
[481]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg1-15/igt@[email protected]
- shard-tglu: [SKIP][482] ([i915#2575]) -> [SKIP][483] ([i915#5286])
[482]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/shard-tglu-10/igt@[email protected]
[483]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-tglu-10/igt@[email protected]

* igt@kms_big_fb@yf-tiled-16bpp-rotate-180:
- shard-rkl: [SKIP][484] -> [SKIP][485] ([i915#14544])
[484]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/shard-rkl-4/igt@[email protected]
[485]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-6/igt@[email protected]

* igt@kms_ccs@crc-primary-rotation-180-4-tiled-bmg-ccs:
- shard-dg1: [SKIP][486] -> [SKIP][487] ([i915#12313])
[486]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/shard-dg1-19/igt@[email protected]
[487]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg1-16/igt@[email protected]
- shard-tglu: [SKIP][488] ([i915#2575]) -> [SKIP][489] ([i915#12313])
[488]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/shard-tglu-10/igt@[email protected]
[489]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-tglu-7/igt@[email protected]
- shard-mtlp: [SKIP][490] -> [SKIP][491] ([i915#12313])
[490]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/shard-mtlp-8/igt@[email protected]
[491]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-mtlp-6/igt@[email protected]
- shard-dg2: [SKIP][492] -> [SKIP][493] ([i915#12313])
[492]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/shard-dg2-4/igt@[email protected]
[493]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg2-5/igt@[email protected]
- shard-rkl: [SKIP][494] -> [SKIP][495] ([i915#12313] / [i915#14544])
[494]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/shard-rkl-2/igt@[email protected]
[495]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-6/igt@[email protected]

* igt@kms_ccs@crc-primary-suspend-4-tiled-dg2-rc-ccs:
- shard-rkl: [SKIP][496] ([i915#14098] / [i915#14544] / [i915#6095]) -> [SKIP][497] ([i915#14098] / [i915#6095])
[496]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/shard-rkl-6/igt@[email protected]
[497]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-2/igt@[email protected]

* igt@kms_ccs@crc-sprite-planes-basic-4-tiled-mtl-rc-ccs-cc:
- shard-rkl: [SKIP][498] -> [SKIP][499] ([i915#14098] / [i915#6095])
[498]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/shard-rkl-2/igt@[email protected]
[499]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-2/igt@[email protected]
- shard-tglu: [SKIP][500] ([i915#2575]) -> [SKIP][501] ([i915#6095])
[500]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/shard-tglu-10/igt@[email protected]
[501]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-tglu-5/igt@[email protected]

* igt@kms_chamelium_hpd@hdmi-hpd-with-enabled-mode:
- shard-mtlp: [SKIP][502] -> [SKIP][503] ([i915#11151] / [i915#7828])
[502]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/shard-mtlp-8/igt@[email protected]
[503]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-mtlp-3/igt@[email protected]
- shard-dg2: [SKIP][504] -> [SKIP][505] ([i915#11151] / [i915#7828])
[504]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/shard-dg2-4/igt@[email protected]
[505]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg2-7/igt@[email protected]
- shard-rkl: [SKIP][506] -> [SKIP][507] ([i915#11151] / [i915#7828])
[506]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/shard-rkl-2/igt@[email protected]
[507]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-4/igt@[email protected]
- shard-dg1: [SKIP][508] -> [SKIP][509] ([i915#11151] / [i915#7828])
[508]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/shard-dg1-19/igt@[email protected]
[509]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg1-17/igt@[email protected]
- shard-tglu: [SKIP][510] ([i915#2575]) -> [SKIP][511] ([i915#11151] / [i915#7828])
[510]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/shard-tglu-10/igt@[email protected]
[511]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-tglu-3/igt@[email protected]

* igt@kms_flip_scaled_crc@flip-32bpp-ytileccs-to-64bpp-ytile-downscaling:
- shard-mtlp: [SKIP][512] ([i915#2575]) -> [SKIP][513] ([i915#2672] / [i915#3555] / [i915#8813])
[512]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/shard-mtlp-8/igt@kms_flip_scaled_crc@flip-32bpp-ytileccs-to-64bpp-ytile-downscaling.html
[513]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-mtlp-2/igt@kms_flip_scaled_crc@flip-32bpp-ytileccs-to-64bpp-ytile-downscaling.html
- shard-dg2: [SKIP][514] ([i915#5190]) -> [SKIP][515] ([i915#2672] / [i915#3555] / [i915#5190])
[514]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/shard-dg2-4/igt@kms_flip_scaled_crc@flip-32bpp-ytileccs-to-64bpp-ytile-downscaling.html
[515]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg2-8/igt@kms_flip_scaled_crc@flip-32bpp-ytileccs-to-64bpp-ytile-downscaling.html
- shard-rkl: [SKIP][516] -> [SKIP][517] ([i915#2672] / [i915#3555])
[516]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/shard-rkl-2/igt@kms_flip_scaled_crc@flip-32bpp-ytileccs-to-64bpp-ytile-downscaling.html
[517]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-5/igt@kms_flip_scaled_crc@flip-32bpp-ytileccs-to-64bpp-ytile-downscaling.html
- shard-dg1: [SKIP][518] -> [SKIP][519] ([i915#2587] / [i915#2672] / [i915#3555])
[518]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/shard-dg1-19/igt@kms_flip_scaled_crc@flip-32bpp-ytileccs-to-64bpp-ytile-downscaling.html
[519]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg1-12/igt@kms_flip_scaled_crc@flip-32bpp-ytileccs-to-64bpp-ytile-downscaling.html
- shard-tglu: [SKIP][520] ([i915#2575]) -> [SKIP][521] ([i915#2587] / [i915#2672] / [i915#3555])
[520]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/shard-tglu-10/igt@kms_flip_scaled_crc@flip-32bpp-ytileccs-to-64bpp-ytile-downscaling.html
[521]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-tglu-2/igt@kms_flip_scaled_crc@flip-32bpp-ytileccs-to-64bpp-ytile-downscaling.html

* igt@kms_frontbuffer_tracking@fbc-2p-primscrn-pri-indfb-draw-blt:
- shard-rkl: [SKIP][522] ([i915#1825]) -> [SKIP][523] ([i915#14544] / [i915#1825])
[522]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/shard-rkl-5/igt@[email protected]
[523]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-6/igt@[email protected]

* igt@kms_frontbuffer_tracking@fbcpsr-1p-offscreen-pri-indfb-draw-mmap-gtt:
- shard-rkl: [SKIP][524] -> [SKIP][525] ([i915#15102])
[524]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/shard-rkl-2/igt@kms_frontbuffer_tracking@fbcpsr-1p-offscreen-pri-indfb-draw-mmap-gtt.html
[525]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-5/igt@kms_frontbuffer_tracking@fbcpsr-1p-offscreen-pri-indfb-draw-mmap-gtt.html
- shard-dg1: [SKIP][526] -> [SKIP][527] ([i915#15104])
[526]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/shard-dg1-19/igt@kms_frontbuffer_tracking@fbcpsr-1p-offscreen-pri-indfb-draw-mmap-gtt.html
[527]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg1-12/igt@kms_frontbuffer_tracking@fbcpsr-1p-offscreen-pri-indfb-draw-mmap-gtt.html
- shard-mtlp: [SKIP][528] -> [SKIP][529] ([i915#15104])
[528]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/shard-mtlp-8/igt@kms_frontbuffer_tracking@fbcpsr-1p-offscreen-pri-indfb-draw-mmap-gtt.html
[529]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-mtlp-2/igt@kms_frontbuffer_tracking@fbcpsr-1p-offscreen-pri-indfb-draw-mmap-gtt.html
- shard-dg2: [SKIP][530] -> [SKIP][531] ([i915#15104])
[530]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/shard-dg2-4/igt@kms_frontbuffer_tracking@fbcpsr-1p-offscreen-pri-indfb-draw-mmap-gtt.html
[531]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg2-8/igt@kms_frontbuffer_tracking@fbcpsr-1p-offscreen-pri-indfb-draw-mmap-gtt.html

* igt@kms_frontbuffer_tracking@fbcpsr-2p-primscrn-spr-indfb-onoff:
- shard-tglu: [SKIP][532] ([i915#2575]) -> [SKIP][533] +1 other test skip
[532]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/shard-tglu-10/igt@[email protected]
[533]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-tglu-6/igt@[email protected]
- shard-mtlp: [SKIP][534] ([i915#2575]) -> [SKIP][535] ([i915#1825])
[534]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/shard-mtlp-8/igt@[email protected]
[535]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-mtlp-2/igt@[email protected]
- shard-dg2: [SKIP][536] -> [SKIP][537] ([i915#5354])
[536]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/shard-dg2-4/igt@[email protected]
[537]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg2-10/igt@[email protected]
- shard-rkl: [SKIP][538] -> [SKIP][539] ([i915#1825])
[538]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/shard-rkl-2/igt@[email protected]
[539]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-5/igt@[email protected]

* igt@kms_frontbuffer_tracking@fbcpsr-argb161616f-draw-blt:
- shard-tglu: [SKIP][540] ([i915#2575]) -> [SKIP][541] ([i915#15574])
[540]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/shard-tglu-10/igt@[email protected]
[541]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-tglu-9/igt@[email protected]
- shard-rkl: [SKIP][542] -> [SKIP][543] ([i915#15574])
[542]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/shard-rkl-2/igt@[email protected]
[543]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-8/igt@[email protected]

* igt@kms_frontbuffer_tracking@psr-1p-primscrn-cur-indfb-onoff:
- shard-rkl: [SKIP][544] ([i915#14544] / [i915#15102] / [i915#3023]) -> [SKIP][545] ([i915#15102] / [i915#3023])
[544]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/shard-rkl-6/igt@[email protected]
[545]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-3/igt@[email protected]

* igt@kms_frontbuffer_tracking@psr-1p-primscrn-indfb-pgflip-blt:
- shard-rkl: [SKIP][546] ([i915#15102] / [i915#3023]) -> [SKIP][547] ([i915#14544] / [i915#15102] / [i915#3023])
[546]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/shard-rkl-2/igt@[email protected]
[547]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-6/igt@[email protected]

* igt@kms_frontbuffer_tracking@psr-1p-primscrn-pri-shrfb-draw-render:
- shard-tglu: [SKIP][548] ([i915#2575]) -> [SKIP][549] ([i915#15102]) +1 other test skip
[548]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/shard-tglu-10/igt@kms_frontbuffer_tracking@psr-1p-primscrn-pri-shrfb-draw-render.html
[549]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-tglu-6/igt@kms_frontbuffer_tracking@psr-1p-primscrn-pri-shrfb-draw-render.html
- shard-dg2: [SKIP][550] -> [SKIP][551] ([i915#15102] / [i915#3458])
[550]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/shard-dg2-4/igt@kms_frontbuffer_tracking@psr-1p-primscrn-pri-shrfb-draw-render.html
[551]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg2-5/igt@kms_frontbuffer_tracking@psr-1p-primscrn-pri-shrfb-draw-render.html
- shard-rkl: [SKIP][552] -> [SKIP][553] ([i915#15102] / [i915#3023])
[552]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/shard-rkl-2/igt@kms_frontbuffer_tracking@psr-1p-primscrn-pri-shrfb-draw-render.html
[553]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-8/igt@kms_frontbuffer_tracking@psr-1p-primscrn-pri-shrfb-draw-render.html
- shard-dg1: [SKIP][554] -> [SKIP][555] ([i915#15102] / [i915#3458])
[554]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/shard-dg1-19/igt@kms_frontbuffer_tracking@psr-1p-primscrn-pri-shrfb-draw-render.html
[555]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg1-14/igt@kms_frontbuffer_tracking@psr-1p-primscrn-pri-shrfb-draw-render.html

* igt@kms_frontbuffer_tracking@psr-2p-scndscrn-spr-indfb-draw-blt:
- shard-rkl: [SKIP][556] ([i915#14544] / [i915#1825]) -> [SKIP][557] ([i915#1825])
[556]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/shard-rkl-6/igt@[email protected]
[557]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-2/igt@[email protected]

* igt@kms_pipe_b_c_ivb@disable-pipe-b-enable-pipe-c:
- shard-dg2: [SKIP][558] ([i915#2575]) -> [SKIP][559]
[558]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/shard-dg2-4/igt@[email protected]
[559]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg2-7/igt@[email protected]
- shard-dg1: [SKIP][560] ([i915#2575]) -> [SKIP][561]
[560]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/shard-dg1-19/igt@[email protected]
[561]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg1-18/igt@[email protected]

* igt@kms_pm_rpm@pm-tiling:
- shard-dg2: [SKIP][562] -> [SKIP][563] ([i915#4077])
[562]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/shard-dg2-4/igt@[email protected]
[563]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg2-5/igt@[email protected]
- shard-dg1: [SKIP][564] -> [SKIP][565] ([i915#4077])
[564]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/shard-dg1-19/igt@[email protected]
[565]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg1-16/igt@[email protected]
- shard-mtlp: [SKIP][566] -> [SKIP][567] ([i915#4077])
[566]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/shard-mtlp-8/igt@[email protected]
[567]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-mtlp-6/igt@[email protected]

* igt@kms_psr2_sf@fbc-pr-cursor-plane-update-sf:
- shard-rkl: [SKIP][568] ([i915#11520]) -> [SKIP][569] ([i915#11520] / [i915#14544])
[568]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/shard-rkl-7/igt@[email protected]
[569]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-6/igt@[email protected]

* igt@kms_psr2_sf@psr2-cursor-plane-move-continuous-exceed-sf:
- shard-snb: [SKIP][570] -> [SKIP][571] ([i915#11520]) +1 other test skip
[570]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/shard-snb7/igt@[email protected]
[571]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-snb1/igt@[email protected]

* igt@kms_psr@fbc-psr-sprite-plane-move:
- shard-tglu: [SKIP][572] ([i915#2575]) -> [SKIP][573] ([i915#9732])
[572]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/shard-tglu-10/igt@[email protected]
[573]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-tglu-8/igt@[email protected]
- shard-mtlp: [SKIP][574] -> [SKIP][575] ([i915#9688])
[574]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/shard-mtlp-8/igt@[email protected]
[575]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-mtlp-5/igt@[email protected]
- shard-dg2: [SKIP][576] -> [SKIP][577] ([i915#1072] / [i915#9732])
[576]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/shard-dg2-4/igt@[email protected]
[577]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg2-1/igt@[email protected]
- shard-rkl: [SKIP][578] -> [SKIP][579] ([i915#1072] / [i915#9732])
[578]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/shard-rkl-2/igt@[email protected]
[579]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-7/igt@[email protected]
- shard-dg1: [SKIP][580] -> [SKIP][581] ([i915#1072] / [i915#9732])
[580]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/shard-dg1-19/igt@[email protected]
[581]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg1-13/igt@[email protected]

* igt@perf@gen12-group-exclusive-stream-sample-oa:
- shard-dg1: [ABORT][582] -> [ABORT][583] ([i915#15602]) +3 other tests abort
[582]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/shard-dg1-13/igt@[email protected]
[583]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-dg1-17/igt@[email protected]

* igt@perf_pmu@frequency@gt0:
- shard-rkl: [ABORT][584] -> [ABORT][585] ([i915#15602]) +1 other test abort
[584]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/shard-rkl-7/igt@perf_pmu@[email protected]
[585]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-rkl-8/igt@perf_pmu@[email protected]

* igt@perf_pmu@most-busy-idle-check-all@rcs0:
- shard-snb: [ABORT][586] -> [ABORT][587] ([i915#15602]) +3 other tests abort
[586]: https://intel-gfx-ci.01.org/tree/drm-tip/IGT_8707/shard-snb4/igt@perf_pmu@[email protected]
[587]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/shard-snb5/igt@perf_pmu@[email protected]

[i915#10056]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/10056
[i915#10307]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/10307
[i915#1072]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/1072
[i915#1099]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/1099
[i915#11151]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/11151
[i915#11520]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/11520
[i915#11681]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/11681
[i915#11920]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/11920
[i915#12178]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/12178
[i915#12313]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/12313
[i915#12316]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/12316
[i915#12655]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/12655
[i915#12713]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/12713
[i915#12755]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/12755
[i915#12756]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/12756
[i915#12805]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/12805
[i915#13046]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/13046
[i915#13049]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/13049
[i915#13356]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/13356
[i915#13398]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/13398
[i915#13476]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/13476
[i915#13522]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/13522
[i915#13566]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/13566
[i915#13688]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/13688
[i915#13749]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/13749
[i915#13781]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/13781
[i915#13958]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/13958
[i915#14033]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/14033
[i915#14073]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/14073
[i915#14098]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/14098
[i915#14118]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/14118
[i915#14123]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/14123
[i915#14419]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/14419
[i915#14544]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/14544
[i915#14545]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/14545
[i915#15073]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/15073
[i915#15102]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/15102
[i915#15104]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/15104
[i915#15106]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/15106
[i915#15132]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/15132
[i915#15243]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/15243
[i915#15329]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/15329
[i915#15330]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/15330
[i915#15403]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/15403
[i915#15460]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/15460
[i915#15522]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/15522
[i915#15573]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/15573
[i915#15574]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/15574
[i915#15602]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/15602
[i915#1769]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/1769
[i915#1825]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/1825
[i915#1839]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/1839
[i915#2527]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/2527
[i915#2575]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/2575
[i915#2587]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/2587
[i915#2672]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/2672
[i915#280]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/280
[i915#2856]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/2856
[i915#3023]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/3023
[i915#3116]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/3116
[i915#3281]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/3281
[i915#3282]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/3282
[i915#3297]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/3297
[i915#3299]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/3299
[i915#3458]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/3458
[i915#3469]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/3469
[i915#3539]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/3539
[i915#3555]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/3555
[i915#3637]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/3637
[i915#3638]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/3638
[i915#3742]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/3742
[i915#3828]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/3828
[i915#3840]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/3840
[i915#3955]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/3955
[i915#4077]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/4077
[i915#4079]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/4079
[i915#4083]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/4083
[i915#4103]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/4103
[i915#4212]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/4212
[i915#4270]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/4270
[i915#4348]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/4348
[i915#4349]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/4349
[i915#4387]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/4387
[i915#4423]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/4423
[i915#4525]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/4525
[i915#4537]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/4537
[i915#4538]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/4538
[i915#4613]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/4613
[i915#4812]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/4812
[i915#4816]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/4816
[i915#4817]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/4817
[i915#4852]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/4852
[i915#4860]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/4860
[i915#5030]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/5030
[i915#5190]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/5190
[i915#5286]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/5286
[i915#5354]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/5354
[i915#5882]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/5882
[i915#6095]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/6095
[i915#6335]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/6335
[i915#6344]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/6344
[i915#6412]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/6412
[i915#6524]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/6524
[i915#6590]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/6590
[i915#6805]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/6805
[i915#6944]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/6944
[i915#6953]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/6953
[i915#7116]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/7116
[i915#7118]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/7118
[i915#7178]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/7178
[i915#7582]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/7582
[i915#7697]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/7697
[i915#7828]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/7828
[i915#7862]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/7862
[i915#8228]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/8228
[i915#8381]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/8381
[i915#8399]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/8399
[i915#8428]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/8428
[i915#8437]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/8437
[i915#8516]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/8516
[i915#8555]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/8555
[i915#8708]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/8708
[i915#8808]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/8808
[i915#8809]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/8809
[i915#8810]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/8810
[i915#8813]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/8813
[i915#8814]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/8814
[i915#9041]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/9041
[i915#9159]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/9159
[i915#9323]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/9323
[i915#9424]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/9424
[i915#9683]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/9683
[i915#9685]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/9685
[i915#9688]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/9688
[i915#9732]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/9732
[i915#9808]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/9808
[i915#9809]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/9809
[i915#9906]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/9906
[i915#9934]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/9934
[i915#9979]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/9979

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

* CI: CI-20190529 -> None
* IGT: IGT_8707 -> IGTPW_14377

CI-20190529: 20190529
CI_DRM_17845: d5c98420766570dc019dc42dfbbe5a1061c03085 @ git://anongit.freedesktop.org/gfx-ci/linux
IGTPW_14377: c017ff2cf772ed6dda1ec5e0bc3716886b3ba71a @ https://gitlab.freedesktop.org/drm/igt-gpu-tools.git
IGT_8707: 8707

== Logs ==

For more details see: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_14377/index.html