[PATCH v3 i-g-t 1/1] tests/intel/xe_evict: overcommit tests for fault-mode and non-fault-mode VMs

[PATCH v3 i-g-t 1/1] tests/intel/xe_evict: overcommit tests for fault-mode and non-fault-mode VMs

[Sobin Thomas]

The existing tests in xe_evict focus on system-wide memory allocation
across multiple processes. However, enhanced coverage for VRAM
overcommit handling in different VM modes was not there.

This change adds three new tests to verify VM overcommit handling.

 test_evict_oom(): Allocates BOs aggressively in a loop until
 VRAM overcommit occurs testing LR mode error handling.

 test_vm_nonfault_mode_overcommit() verifies that non-fault mode VMs
 properly reject overcommit attempts.

 test_vm_fault_mode_overcommit() validates that fault-mode VMs can
 handle memory pressure gracefully by touching pages to trigger page
 faults.

Sobin Thomas (1):
  tests/intel/xe_evict: overcommit tests for fault-mode and
    non-fault-mode VMs

 tests/intel/xe_evict.c | 310 +++++++++++++++++++++++++++++++++++++++++
 1 file changed, 310 insertions(+)

-- 
2.51.0

[PATCH v3 i-g-t 1/1] tests/intel/xe_evict: overcommit tests for fault-mode and non-fault-mode VMs

[Sobin Thomas]

The existing tests in xe_evict focus on system-wide memory allocation
across multiple processes. However, enhanced coverage for VRAM
overcommit handling in different VM modes was not there.

This change adds three new tests to verify VM overcommit handling.

 test_evict_oom(): Allocates BOs aggressively in a loop until
 VRAM overcommit occurs testing LR mode error handling.

 test_vm_nonfault_mode_overcommit() verifies that non-fault mode VMs
 properly reject overcommit attempts.

 test_vm_fault_mode_overcommit() validates that fault-mode VMs can
 handle memory pressure gracefully by touching pages to trigger page
 faults.

v3:
- Addressed review comments from Nishit on the error handling.
- Replaced igt_info with igt_debug and igt_warn

Signed-off-by: Sobin Thomas <sobin.thomas@intel.com>
---
 tests/intel/xe_evict.c | 310 +++++++++++++++++++++++++++++++++++++++++
 1 file changed, 310 insertions(+)

diff --git a/tests/intel/xe_evict.c b/tests/intel/xe_evict.c
index 2350487c8..136ec4e09 100644
--- a/tests/intel/xe_evict.c
+++ b/tests/intel/xe_evict.c
@@ -1,4 +1,5 @@
 // SPDX-License-Identifier: MIT
+//
 /*
  * Copyright © 2021 Intel Corporation
  */
@@ -29,6 +30,7 @@
 #define COMPUTE_THREAD		(0x1 << 4)
 #define EXTERNAL_OBJ		(0x1 << 5)
 #define BIND_EXEC_QUEUE		(0x1 << 6)
+#define USER_FENCE_VALUE    0xdeadbeefdeadbeefull
 
 static void
 test_evict(int fd, struct drm_xe_engine_class_instance *eci,
@@ -210,6 +212,252 @@ test_evict(int fd, struct drm_xe_engine_class_instance *eci,
 	drm_close_driver(fd);
 }
 
+static int
+test_evict_oom(int fd, struct drm_xe_engine_class_instance *eci,
+	       int n_exec_queues, int n_execs, uint64_t system_size,
+	       size_t bo_size, unsigned long flags)
+{
+	uint32_t vm;
+	uint32_t bind_exec_queues[1] = { 0 };
+	uint64_t addr = 0x100000000;
+	uint64_t total_alloc_size;
+	int bind_err = 0;
+	uint32_t *bo;
+	int i;
+	const size_t min_map_size = 4096;  /* Add constant with proper type */
+
+	struct drm_xe_sync sync[1] = {
+		{ .type = DRM_XE_SYNC_TYPE_USER_FENCE, .flags = DRM_XE_SYNC_FLAG_SIGNAL,
+		  .timeline_value = USER_FENCE_VALUE },
+	};
+
+	/* Calculate total allocation size - now for full n_execs */
+	total_alloc_size = (uint64_t)n_execs * bo_size;
+
+	if (system_size < (total_alloc_size / 4)) {
+		igt_warn("Insufficient memory to run OOM test safely\n");
+		return -ENOMEM;
+	}
+	if (total_alloc_size > system_size) {
+		int safe_n_execs = system_size / bo_size;
+
+		safe_n_execs = ALIGN_DOWN(safe_n_execs, 4);
+		if (safe_n_execs < 4) {
+			igt_warn("Not enough memory to run OOM test\n");
+			return -ENOMEM;
+		}
+		igt_warn("Reducing n_execs from %d to %d to fit in available memory\n",
+			 n_execs, safe_n_execs);
+		n_execs = safe_n_execs;
+		total_alloc_size = (uint64_t)n_execs * bo_size;
+	}
+	igt_debug("OOM test: n_execs=%d, bo_size=%llu MB, total_alloc=%llu MB, available=%llu MB\n",
+		  n_execs, (unsigned long long)(bo_size >> 20),
+		  (unsigned long long)(total_alloc_size >> 20),
+		  (unsigned long long)(system_size >> 20));
+
+	/* Allocate array for n_execs BOs */
+	bo = calloc(n_execs, sizeof(*bo));
+	igt_assert(bo);
+
+	fd = drm_reopen_driver(fd);
+
+	vm = xe_vm_create(fd, DRM_XE_VM_CREATE_FLAG_LR_MODE, 0);
+	bind_exec_queues[0] = xe_bind_exec_queue_create(fd, vm, 0);
+
+	igt_debug("\n n_execs = %d, bo_size = %zu\n", n_execs, bo_size);
+
+	/* Try to allocate and bind more than available memory */
+	for (i = 0; i < n_execs; i++) {
+		uint32_t __bo;
+		struct {
+		uint64_t vm_sync;
+		} *data;
+		int create_ret;
+		size_t map_size;  /* Use size_t for map size */
+
+		/* Use __xe_bo_create to handle allocation failures gracefully */
+		create_ret = __xe_bo_create(fd, 0, bo_size, vram_memory(fd, eci->gt_id),
+					    DRM_XE_GEM_CREATE_FLAG_NEEDS_VISIBLE_VRAM,
+					    NULL, &__bo);
+		if (create_ret) {
+			igt_warn("BO create failed at iteration %d with error %d (%s)\n",
+				 i, create_ret, strerror(-create_ret));
+			break;
+		}
+
+		bo[i] = __bo;
+
+		/* Calculate map size with same types */
+		map_size = sizeof(*data) > min_map_size ? sizeof(*data) : min_map_size;
+		data = xe_bo_map(fd, __bo, map_size);
+		sync[0].addr = to_user_pointer(&data->vm_sync);
+		bind_err = __xe_vm_bind(fd, vm, bind_exec_queues[0], __bo, 0, addr,
+					bo_size, DRM_XE_VM_BIND_OP_MAP, 0, sync,
+					1, 0, 0, 0);
+		/* Attempt bind - should eventually fail with -ENOSPC or -ENOMEM */
+		if (bind_err) {
+			bind_err = -errno;
+			igt_warn("Bind failed at iteration %d with error %d (%s)\n",
+				 i, -bind_err, strerror(-bind_err));
+			munmap(data, map_size);
+			gem_close(fd, __bo);
+			bo[i] = 0;
+			break;
+		}
+
+		xe_wait_ufence(fd, &data->vm_sync, USER_FENCE_VALUE,
+			       bind_exec_queues[0], 20 * NSEC_PER_SEC);
+
+		/* Unmap with the same size we used for mapping */
+		munmap(data, map_size);
+		addr += bo_size;
+	}
+
+	/* Cleanup allocated BOs - iterate through all n_execs */
+	for (int j = 0; j < n_execs; j++) {
+		if (bo[j])
+			gem_close(fd, bo[j]);
+	}
+
+	xe_exec_queue_destroy(fd, bind_exec_queues[0]);
+	xe_vm_destroy(fd, vm);
+	drm_close_driver(fd);
+	free(bo);
+
+	return bind_err;
+}
+
+static unsigned int oom_working_set(uint64_t vram_size, uint64_t system_size,
+				    uint64_t bo_size)
+{
+	uint64_t target_allocation;
+	unsigned int set_size;
+
+	/*
+	 * For VRAM eviction testing, we want to allocate MORE than VRAM size
+	 * to force eviction to system memory. Target 150-200% of VRAM.
+	 * The BOs are created with VRAM placement, so they'll initially go to VRAM
+	 * and then get evicted to system when VRAM fills up.
+	 */
+	target_allocation = (vram_size * 150) / 100;  /* 150% of VRAM */
+
+	/* But ensure we don't exceed available system memory */
+	if (target_allocation > (system_size * 80) / 100) {
+		target_allocation = (system_size * 80) / 100;
+		igt_debug("Limited by system memory: reducing target from %llu MB to %llu MB\n",
+			  (unsigned long long)((vram_size * 150 / 100) >> 20),
+			  (unsigned long long)(target_allocation >> 20));
+	}
+
+	set_size = target_allocation / bo_size;
+
+	igt_debug("VRAM stress calculation: vram_size=%" PRIu64 " MB, system=%" PRIu64
+		  "MB, target_alloc=%" PRIu64 " MB (%.1f%% of VRAM), bo_size=%"
+		  PRIu64 " MB, set_size=%u\n",
+		  (uint64_t)(vram_size >> 20), (uint64_t)(system_size >> 20),
+		  (uint64_t)(target_allocation >> 20),
+		  (double)(target_allocation * 100) / vram_size,
+		  (uint64_t)(bo_size >> 20), set_size);
+
+	return ALIGN_DOWN(set_size, 4);
+}
+
+static void
+test_vm_nonfault_mode_overcommit(int fd, struct drm_xe_engine_class_instance *eci,
+				 uint64_t system_size, uint64_t vram_size,
+				 uint64_t overcommit_multiplier)
+{
+	uint32_t bo;
+	uint64_t overcommit_size;
+	uint32_t vm;
+	int ret, cret;
+
+	overcommit_size = ALIGN(vram_size * overcommit_multiplier, 4096);
+
+	/* Limit overcommit to available memory to avoid OOM killer */
+	if (overcommit_size > system_size) {
+		igt_info("Limiting overcommit size from %llu MB to %llu MB (available)\n",
+			 (unsigned long long)(overcommit_size >> 20),
+			 (unsigned long long)(system_size >> 20));
+		overcommit_size = ALIGN(system_size, 4096);
+	}
+
+	vm = xe_vm_create(fd, 0, 0);
+	cret = __xe_bo_create(fd, vm, overcommit_size,
+			      vram_memory(fd, eci->gt_id) | system_memory(fd),
+			      0, NULL, &bo);
+	if (cret) {
+		igt_assert_f(errno == E2BIG || errno == ENOMEM || errno == ENOSPC,
+			     "xe_bo_create failed with unexpected errno=%d (%s)\n",
+			     errno, strerror(errno));
+		xe_vm_destroy(fd, vm);
+		return;
+	}
+
+	ret = __xe_vm_bind(fd, vm, 0, bo, 0, 0,
+			   overcommit_size, DRM_XE_VM_BIND_OP_MAP, 0,
+			   NULL, 0, 0, 0, 0);
+	igt_assert_f(ret == -ENOMEM || ret == -ENOSPC,
+		     "Expected bind to fail with -ENOMEM/-ENOSPC, got %d\n", ret);
+	gem_close(fd, bo);
+	xe_vm_destroy(fd, vm);
+}
+
+static void test_vm_fault_mode_overcommit(int fd, struct drm_xe_engine_class_instance *eci,
+					  uint64_t available_mem, uint64_t vram_size,
+					  uint64_t overcommit_multiplier)
+{
+	uint64_t overcommit_size;
+	uint32_t vm;
+	uint32_t bo;
+	uint64_t *ptr;
+	int create_ret;
+
+	overcommit_size = ALIGN(vram_size * overcommit_multiplier, 4096);
+
+	/* Limit overcommit to available memory to avoid OOM killer */
+	if (overcommit_size > available_mem) {
+		igt_info("Limiting overcommit size from %llu MB to %llu MB (available)\n",
+			 (unsigned long long)(overcommit_size >> 20),
+			 (unsigned long long)(available_mem >> 20));
+		overcommit_size = ALIGN(available_mem, 4096);
+	}
+
+	igt_debug("Fault mode overcommit test: size=%llu MB, vram=%llu MB\n",
+		  (unsigned long long)(overcommit_size >> 20),
+		  (unsigned long long)(vram_size >> 20));
+	vm = xe_vm_create(fd, DRM_XE_VM_CREATE_FLAG_LR_MODE |
+			  DRM_XE_VM_CREATE_FLAG_FAULT_MODE, 0);
+	igt_assert(vm);
+
+	create_ret = __xe_bo_create(fd, 0, overcommit_size,
+				    vram_memory(fd, eci->gt_id) | system_memory(fd),
+				    DRM_XE_GEM_CREATE_FLAG_NEEDS_VISIBLE_VRAM,
+				    NULL, &bo);
+	if (create_ret) {
+		xe_vm_destroy(fd, vm);
+		igt_assert_f(create_ret != 0, "xe_bo_create failed with unexpected error %d\n",
+			     create_ret);
+		return;
+	}
+
+	ptr = xe_bo_map(fd, bo, overcommit_size);
+	igt_assert(ptr);
+	/* Touch first page */
+	memset(ptr, 0xAA, 4096);
+
+	/* Touch sparse pages to test fault handling - limit to avoid OOM */
+	for (uint64_t off = 0; off < overcommit_size; off += 4096)
+		((char *)ptr)[off] = 0xBB;
+
+	igt_info("Fault mode overcommit test completed successfully\n");
+
+	munmap(ptr, overcommit_size);
+	gem_close(fd, bo);
+	xe_vm_destroy(fd, vm);
+}
+
 static void
 test_evict_cm(int fd, struct drm_xe_engine_class_instance *eci,
 	      int n_exec_queues, int n_execs, size_t bo_size, unsigned long flags,
@@ -665,7 +913,29 @@ static unsigned int working_set(uint64_t vram_size, uint64_t system_size,
  * @beng-threads-large:		bind exec_queue threads large
  *
  */
+/**
+ * SUBTEST: evict-vm-nonfault-overcommit
+ * Description: VM non-fault mode overcommit test - expects bind failure
+ * Test category: functionality test
+ * Feature: VM bind
+ */
 
+/**
+ * SUBTEST: evict-vm-fault-overcommit
+ * Description: VM fault mode overcommit test - touch pages to trigger faults
+ * Test category: functionality test
+ * Feature: VM bind, fault mode
+ */
+/**
+ * SUBTEST: evict-%s
+ * Description: %arg[1] out-of-memory evict test - expects graceful failure
+ * Test category: functionality test
+ *
+ * arg[1]:
+ *
+ * @oom-graceful:       OOM graceful failure with small BOs
+ * @oom-graceful-large: OOM graceful failure with large BOs
+ */
 /*
  * Table driven test that attempts to cover all possible scenarios of eviction
  * (small / large objects, compute mode vs non-compute VMs, external BO or BOs
@@ -730,6 +1000,17 @@ int igt_main()
 			MULTI_VM },
 		{ NULL },
 	};
+	const struct section_oom {
+		const char *name;
+		int n_exec_queues;
+		int mul;
+		int div;
+		unsigned int flags;
+} sections_oom[] = {
+	{ "oom-graceful", 1, 1, 128, BIND_EXEC_QUEUE },
+	{ "oom-graceful-large", 1, 1, 16, BIND_EXEC_QUEUE },
+	{ NULL },
+};
 	const struct section_threads {
 		const char *name;
 		int n_threads;
@@ -836,6 +1117,14 @@ int igt_main()
 		}
 	}
 
+	igt_subtest("evict-vm-nonfault-overcommit") {
+		test_vm_nonfault_mode_overcommit(fd, hwe, system_size, vram_size, 2);
+	}
+
+	igt_subtest("evict-vm-fault-overcommit") {
+		test_vm_fault_mode_overcommit(fd, hwe, system_size, vram_size, 2);
+	}
+
 	for (const struct section_cm *s = sections_cm; s->name; s++) {
 		igt_subtest_f("evict-%s", s->name) {
 			uint64_t bo_size = calc_bo_size(vram_size, s->mul, s->div);
@@ -862,6 +1151,27 @@ int igt_main()
 				min(ws, s->n_execs), bo_size, s->flags);
 		}
 	}
+	for (const struct section_oom *s = sections_oom; s->name; s++) {
+		igt_subtest_f("evict-%s", s->name) {
+			uint64_t bo_size = calc_bo_size(vram_size, s->mul, s->div);
+			int n_execs = oom_working_set(vram_size, system_size, bo_size);
+			int ret;
+
+			igt_debug("OOM test: n_execs %d, bo_size %" PRIu64 " MiB\n",
+				  n_execs, bo_size >> 20);
+
+			ret = test_evict_oom(fd, hwe, s->n_exec_queues, n_execs,
+					     system_size, bo_size, s->flags);
+
+			/* Accept success or graceful OOM errors */
+			igt_assert(ret == 0 || ret == -ENOSPC || ret == -ENOMEM);
+			if (ret != 0)
+				igt_debug("Test passed: Got expected error %d (%s)\n",
+					  ret, strerror(-ret));
+			else
+				igt_debug("Test passed: All allocations and binds succeeded\n");
+	}
+}
 
 	igt_fixture()
 		drm_close_driver(fd);
-- 
2.51.0

Re: [PATCH v3 i-g-t 1/1] tests/intel/xe_evict: overcommit tests for fault-mode and non-fault-mode VMs

[Sharma, Nishit]

On 1/22/2026 6:24 PM, Sobin Thomas wrote:
> The existing tests in xe_evict focus on system-wide memory allocation
> across multiple processes. However, enhanced coverage for VRAM
> overcommit handling in different VM modes was not there.
>
> This change adds three new tests to verify VM overcommit handling.
>
>   test_evict_oom(): Allocates BOs aggressively in a loop until
>   VRAM overcommit occurs testing LR mode error handling.
>
>   test_vm_nonfault_mode_overcommit() verifies that non-fault mode VMs
>   properly reject overcommit attempts.
>
>   test_vm_fault_mode_overcommit() validates that fault-mode VMs can
>   handle memory pressure gracefully by touching pages to trigger page
>   faults.
>
> v3:
> - Addressed review comments from Nishit on the error handling.
> - Replaced igt_info with igt_debug and igt_warn
>
> Signed-off-by: Sobin Thomas <sobin.thomas@intel.com>
> ---
>   tests/intel/xe_evict.c | 310 +++++++++++++++++++++++++++++++++++++++++
>   1 file changed, 310 insertions(+)
>
> diff --git a/tests/intel/xe_evict.c b/tests/intel/xe_evict.c
> index 2350487c8..136ec4e09 100644
> --- a/tests/intel/xe_evict.c
> +++ b/tests/intel/xe_evict.c
> @@ -1,4 +1,5 @@
>   // SPDX-License-Identifier: MIT
> +//
>   /*
>    * Copyright © 2021 Intel Corporation
>    */
> @@ -29,6 +30,7 @@
>   #define COMPUTE_THREAD		(0x1 << 4)
>   #define EXTERNAL_OBJ		(0x1 << 5)
>   #define BIND_EXEC_QUEUE		(0x1 << 6)
> +#define USER_FENCE_VALUE    0xdeadbeefdeadbeefull
>   
>   static void
>   test_evict(int fd, struct drm_xe_engine_class_instance *eci,
> @@ -210,6 +212,252 @@ test_evict(int fd, struct drm_xe_engine_class_instance *eci,
>   	drm_close_driver(fd);
>   }
>   
> +static int
> +test_evict_oom(int fd, struct drm_xe_engine_class_instance *eci,
> +	       int n_exec_queues, int n_execs, uint64_t system_size,
> +	       size_t bo_size, unsigned long flags)
> +{
> +	uint32_t vm;
> +	uint32_t bind_exec_queues[1] = { 0 };
> +	uint64_t addr = 0x100000000;
> +	uint64_t total_alloc_size;
> +	int bind_err = 0;
> +	uint32_t *bo;
> +	int i;
> +	const size_t min_map_size = 4096;  /* Add constant with proper type */
> +
> +	struct drm_xe_sync sync[1] = {
> +		{ .type = DRM_XE_SYNC_TYPE_USER_FENCE, .flags = DRM_XE_SYNC_FLAG_SIGNAL,
> +		  .timeline_value = USER_FENCE_VALUE },
> +	};
> +
> +	/* Calculate total allocation size - now for full n_execs */
> +	total_alloc_size = (uint64_t)n_execs * bo_size;
> +
> +	if (system_size < (total_alloc_size / 4)) {
> +		igt_warn("Insufficient memory to run OOM test safely\n");
> +		return -ENOMEM;
> +	}
> +	if (total_alloc_size > system_size) {
> +		int safe_n_execs = system_size / bo_size;
> +
> +		safe_n_execs = ALIGN_DOWN(safe_n_execs, 4);
> +		if (safe_n_execs < 4) {
> +			igt_warn("Not enough memory to run OOM test\n");
> +			return -ENOMEM;
> +		}
> +		igt_warn("Reducing n_execs from %d to %d to fit in available memory\n",
> +			 n_execs, safe_n_execs);
> +		n_execs = safe_n_execs;
> +		total_alloc_size = (uint64_t)n_execs * bo_size;
> +	}
> +	igt_debug("OOM test: n_execs=%d, bo_size=%llu MB, total_alloc=%llu MB, available=%llu MB\n",
> +		  n_execs, (unsigned long long)(bo_size >> 20),
> +		  (unsigned long long)(total_alloc_size >> 20),
> +		  (unsigned long long)(system_size >> 20));
> +
> +	/* Allocate array for n_execs BOs */
> +	bo = calloc(n_execs, sizeof(*bo));
> +	igt_assert(bo);
> +
> +	fd = drm_reopen_driver(fd);
why drm_reopen_driver()? Already fd is passed from calling function 
which can be used here/
> +
> +	vm = xe_vm_create(fd, DRM_XE_VM_CREATE_FLAG_LR_MODE, 0);
> +	bind_exec_queues[0] = xe_bind_exec_queue_create(fd, vm, 0);
> +
> +	igt_debug("\n n_execs = %d, bo_size = %zu\n", n_execs, bo_size);
> +
> +	/* Try to allocate and bind more than available memory */
> +	for (i = 0; i < n_execs; i++) {
> +		uint32_t __bo;
> +		struct {
> +		uint64_t vm_sync;
> +		} *data;
> +		int create_ret;
> +		size_t map_size;  /* Use size_t for map size */
> +
> +		/* Use __xe_bo_create to handle allocation failures gracefully */
> +		create_ret = __xe_bo_create(fd, 0, bo_size, vram_memory(fd, eci->gt_id),
> +					    DRM_XE_GEM_CREATE_FLAG_NEEDS_VISIBLE_VRAM,
> +					    NULL, &__bo);
> +		if (create_ret) {
> +			igt_warn("BO create failed at iteration %d with error %d (%s)\n",
> +				 i, create_ret, strerror(-create_ret));
> +			break;
> +		}
> +
> +		bo[i] = __bo;
> +
> +		/* Calculate map size with same types */
> +		map_size = sizeof(*data) > min_map_size ? sizeof(*data) : min_map_size;
> +		data = xe_bo_map(fd, __bo, map_size);
> +		sync[0].addr = to_user_pointer(&data->vm_sync);
> +		bind_err = __xe_vm_bind(fd, vm, bind_exec_queues[0], __bo, 0, addr,
> +					bo_size, DRM_XE_VM_BIND_OP_MAP, 0, sync,
> +					1, 0, 0, 0);
> +		/* Attempt bind - should eventually fail with -ENOSPC or -ENOMEM */
> +		if (bind_err) {
> +			bind_err = -errno;
> +			igt_warn("Bind failed at iteration %d with error %d (%s)\n",
> +				 i, -bind_err, strerror(-bind_err));
> +			munmap(data, map_size);
> +			gem_close(fd, __bo);
> +			bo[i] = 0;
> +			break;
> +		}
> +
> +		xe_wait_ufence(fd, &data->vm_sync, USER_FENCE_VALUE,
> +			       bind_exec_queues[0], 20 * NSEC_PER_SEC);
> +
> +		/* Unmap with the same size we used for mapping */
> +		munmap(data, map_size);
> +		addr += bo_size;
> +	}
> +
> +	/* Cleanup allocated BOs - iterate through all n_execs */
> +	for (int j = 0; j < n_execs; j++) {
> +		if (bo[j])
> +			gem_close(fd, bo[j]);
> +	}
> +
> +	xe_exec_queue_destroy(fd, bind_exec_queues[0]);
> +	xe_vm_destroy(fd, vm);
> +	drm_close_driver(fd);
> +	free(bo);
> +
> +	return bind_err;
> +}
> +
> +static unsigned int oom_working_set(uint64_t vram_size, uint64_t system_size,
> +				    uint64_t bo_size)
> +{
> +	uint64_t target_allocation;
> +	unsigned int set_size;
> +
> +	/*
> +	 * For VRAM eviction testing, we want to allocate MORE than VRAM size
> +	 * to force eviction to system memory. Target 150-200% of VRAM.
> +	 * The BOs are created with VRAM placement, so they'll initially go to VRAM
> +	 * and then get evicted to system when VRAM fills up.
> +	 */
> +	target_allocation = (vram_size * 150) / 100;  /* 150% of VRAM */
> +
> +	/* But ensure we don't exceed available system memory */
> +	if (target_allocation > (system_size * 80) / 100) {
> +		target_allocation = (system_size * 80) / 100;
> +		igt_debug("Limited by system memory: reducing target from %llu MB to %llu MB\n",
> +			  (unsigned long long)((vram_size * 150 / 100) >> 20),
> +			  (unsigned long long)(target_allocation >> 20));
> +	}
> +
> +	set_size = target_allocation / bo_size;
> +
> +	igt_debug("VRAM stress calculation: vram_size=%" PRIu64 " MB, system=%" PRIu64
> +		  "MB, target_alloc=%" PRIu64 " MB (%.1f%% of VRAM), bo_size=%"
> +		  PRIu64 " MB, set_size=%u\n",
> +		  (uint64_t)(vram_size >> 20), (uint64_t)(system_size >> 20),
> +		  (uint64_t)(target_allocation >> 20),
> +		  (double)(target_allocation * 100) / vram_size,
> +		  (uint64_t)(bo_size >> 20), set_size);
> +
> +	return ALIGN_DOWN(set_size, 4);
> +}
> +
> +static void
> +test_vm_nonfault_mode_overcommit(int fd, struct drm_xe_engine_class_instance *eci,
> +				 uint64_t system_size, uint64_t vram_size,
> +				 uint64_t overcommit_multiplier)
> +{
> +	uint32_t bo;
> +	uint64_t overcommit_size;
> +	uint32_t vm;
> +	int ret, cret;
> +
> +	overcommit_size = ALIGN(vram_size * overcommit_multiplier, 4096);
> +
> +	/* Limit overcommit to available memory to avoid OOM killer */
> +	if (overcommit_size > system_size) {
> +		igt_info("Limiting overcommit size from %llu MB to %llu MB (available)\n",
> +			 (unsigned long long)(overcommit_size >> 20),
> +			 (unsigned long long)(system_size >> 20));
> +		overcommit_size = ALIGN(system_size, 4096);
> +	}
> +
> +	vm = xe_vm_create(fd, 0, 0);
> +	cret = __xe_bo_create(fd, vm, overcommit_size,
> +			      vram_memory(fd, eci->gt_id) | system_memory(fd),
> +			      0, NULL, &bo);
why both vram and system_memory? I think we are verifying overcommit 
using vram.
> +	if (cret) {
> +		igt_assert_f(errno == E2BIG || errno == ENOMEM || errno == ENOSPC,
> +			     "xe_bo_create failed with unexpected errno=%d (%s)\n",
> +			     errno, strerror(errno));
> +		xe_vm_destroy(fd, vm);
> +		return;
> +	}
> +
> +	ret = __xe_vm_bind(fd, vm, 0, bo, 0, 0,
> +			   overcommit_size, DRM_XE_VM_BIND_OP_MAP, 0,
> +			   NULL, 0, 0, 0, 0);
> +	igt_assert_f(ret == -ENOMEM || ret == -ENOSPC,
> +		     "Expected bind to fail with -ENOMEM/-ENOSPC, got %d\n", ret);
> +	gem_close(fd, bo);
> +	xe_vm_destroy(fd, vm);
> +}
> +
> +static void test_vm_fault_mode_overcommit(int fd, struct drm_xe_engine_class_instance *eci,
> +					  uint64_t available_mem, uint64_t vram_size,
> +					  uint64_t overcommit_multiplier)
better use system_size as available_mem can refer both VRAM or System Mem.
> +{
> +	uint64_t overcommit_size;
> +	uint32_t vm;
> +	uint32_t bo;
> +	uint64_t *ptr;
> +	int create_ret;
> +
> +	overcommit_size = ALIGN(vram_size * overcommit_multiplier, 4096);
> +
> +	/* Limit overcommit to available memory to avoid OOM killer */
> +	if (overcommit_size > available_mem) {
> +		igt_info("Limiting overcommit size from %llu MB to %llu MB (available)\n",
> +			 (unsigned long long)(overcommit_size >> 20),
> +			 (unsigned long long)(available_mem >> 20));
> +		overcommit_size = ALIGN(available_mem, 4096);
> +	}
> +
> +	igt_debug("Fault mode overcommit test: size=%llu MB, vram=%llu MB\n",
> +		  (unsigned long long)(overcommit_size >> 20),
> +		  (unsigned long long)(vram_size >> 20));
> +	vm = xe_vm_create(fd, DRM_XE_VM_CREATE_FLAG_LR_MODE |
> +			  DRM_XE_VM_CREATE_FLAG_FAULT_MODE, 0);
> +	igt_assert(vm);
> +
> +	create_ret = __xe_bo_create(fd, 0, overcommit_size,
> +				    vram_memory(fd, eci->gt_id) | system_memory(fd),
> +				    DRM_XE_GEM_CREATE_FLAG_NEEDS_VISIBLE_VRAM,
> +				    NULL, &bo);
Same comment as above for non_fault_mode()
> +	if (create_ret) {
> +		xe_vm_destroy(fd, vm);
> +		igt_assert_f(create_ret != 0, "xe_bo_create failed with unexpected error %d\n",
> +			     create_ret);
> +		return;
> +	}
> +
> +	ptr = xe_bo_map(fd, bo, overcommit_size);
> +	igt_assert(ptr);
> +	/* Touch first page */
> +	memset(ptr, 0xAA, 4096);
> +
> +	/* Touch sparse pages to test fault handling - limit to avoid OOM */
> +	for (uint64_t off = 0; off < overcommit_size; off += 4096)
> +		((char *)ptr)[off] = 0xBB;
This will do system migration. GPU should be involved for execution. 
Through Batch buffer we can achieve whether overcommit size is 
accessible or not
> +
> +	igt_info("Fault mode overcommit test completed successfully\n");
> +
> +	munmap(ptr, overcommit_size);
> +	gem_close(fd, bo);
> +	xe_vm_destroy(fd, vm);
> +}
> +
>   static void
>   test_evict_cm(int fd, struct drm_xe_engine_class_instance *eci,
>   	      int n_exec_queues, int n_execs, size_t bo_size, unsigned long flags,
> @@ -665,7 +913,29 @@ static unsigned int working_set(uint64_t vram_size, uint64_t system_size,
>    * @beng-threads-large:		bind exec_queue threads large
>    *
>    */
> +/**
> + * SUBTEST: evict-vm-nonfault-overcommit
> + * Description: VM non-fault mode overcommit test - expects bind failure
> + * Test category: functionality test
> + * Feature: VM bind
> + */
>   
> +/**
> + * SUBTEST: evict-vm-fault-overcommit
> + * Description: VM fault mode overcommit test - touch pages to trigger faults
> + * Test category: functionality test
> + * Feature: VM bind, fault mode
> + */
> +/**
> + * SUBTEST: evict-%s
> + * Description: %arg[1] out-of-memory evict test - expects graceful failure
> + * Test category: functionality test
> + *
> + * arg[1]:
> + *
> + * @oom-graceful:       OOM graceful failure with small BOs
> + * @oom-graceful-large: OOM graceful failure with large BOs
> + */
>   /*
>    * Table driven test that attempts to cover all possible scenarios of eviction
>    * (small / large objects, compute mode vs non-compute VMs, external BO or BOs
> @@ -730,6 +1000,17 @@ int igt_main()
>   			MULTI_VM },
>   		{ NULL },
>   	};
> +	const struct section_oom {
> +		const char *name;
> +		int n_exec_queues;
> +		int mul;
> +		int div;
> +		unsigned int flags;
> +} sections_oom[] = {
> +	{ "oom-graceful", 1, 1, 128, BIND_EXEC_QUEUE },
> +	{ "oom-graceful-large", 1, 1, 16, BIND_EXEC_QUEUE },
> +	{ NULL },
> +};
>   	const struct section_threads {
>   		const char *name;
>   		int n_threads;
> @@ -836,6 +1117,14 @@ int igt_main()
>   		}
>   	}
>   
> +	igt_subtest("evict-vm-nonfault-overcommit") {
> +		test_vm_nonfault_mode_overcommit(fd, hwe, system_size, vram_size, 2);
> +	}
> +
> +	igt_subtest("evict-vm-fault-overcommit") {
> +		test_vm_fault_mode_overcommit(fd, hwe, system_size, vram_size, 2);
> +	}
> +
>   	for (const struct section_cm *s = sections_cm; s->name; s++) {
>   		igt_subtest_f("evict-%s", s->name) {
>   			uint64_t bo_size = calc_bo_size(vram_size, s->mul, s->div);
> @@ -862,6 +1151,27 @@ int igt_main()
>   				min(ws, s->n_execs), bo_size, s->flags);
>   		}
>   	}
> +	for (const struct section_oom *s = sections_oom; s->name; s++) {
> +		igt_subtest_f("evict-%s", s->name) {
> +			uint64_t bo_size = calc_bo_size(vram_size, s->mul, s->div);
> +			int n_execs = oom_working_set(vram_size, system_size, bo_size);
> +			int ret;
> +
> +			igt_debug("OOM test: n_execs %d, bo_size %" PRIu64 " MiB\n",
> +				  n_execs, bo_size >> 20);
> +
> +			ret = test_evict_oom(fd, hwe, s->n_exec_queues, n_execs,
> +					     system_size, bo_size, s->flags);
> +
> +			/* Accept success or graceful OOM errors */
> +			igt_assert(ret == 0 || ret == -ENOSPC || ret == -ENOMEM);
> +			if (ret != 0)
> +				igt_debug("Test passed: Got expected error %d (%s)\n",
> +					  ret, strerror(-ret));
ret !=0 means anything other than zero if returned it'll say test 
passed. What if driver returns -ENOENT, -EINVAL, -ENODATA or erros other 
than ENOSPC and ENOMEM? All the time it'll say Test passed
> +			else
> +				igt_debug("Test passed: All allocations and binds succeeded\n");
> +	}
> +}
>   
>   	igt_fixture()
>   		drm_close_driver(fd);
Let's wait for inputs from @Hellstrom, Thomas.

✗ Fi.CI.BUILD: failure for series starting with [v3,i-g-t,1/1] tests/intel/xe_evict: overcommit tests for fault-mode and non-fault-mode VMs

[Patchwork]

== Series Details ==

Series: series starting with [v3,i-g-t,1/1] tests/intel/xe_evict: overcommit tests for fault-mode and non-fault-mode VMs
URL   : https://patchwork.freedesktop.org/series/160491/
State : failure

== Summary ==

Applying: tests/intel/xe_evict: overcommit tests for fault-mode and non-fault-mode VMs
Using index info to reconstruct a base tree...
M	tests/intel/xe_evict.c
Falling back to patching base and 3-way merge...
Auto-merging tests/intel/xe_evict.c
CONFLICT (content): Merge conflict in tests/intel/xe_evict.c
Patch failed at 0001 tests/intel/xe_evict: overcommit tests for fault-mode and non-fault-mode VMs
When you have resolved this problem, run "git am --continue".
If you prefer to skip this patch, run "git am --skip" instead.
To restore the original branch and stop patching, run "git am --abort".