drm/xe/xe_vm: Add error injection support to lock and prep
Subsystems (2)
v4 cover drm/xe/xe_vm: Add error injection support to lock and prep
Error injection should use the error injection interface, and should be decoupled from CONFIG_DRM_XE_DEBUG. Remove TEST_VM_OPS_ERROR from the code, and add error injection support to the function vm_bind_ioctl_ops_lock_and_prep. This necessitates marking the function as noinline.
v2: Only noinline vm_bind_ioctl_ops_lock_and_prep when function error injection is enabled (Brost)
v3: Add error_injectable function attribute (Brost, Harrison)
v4: Modify where error_injectable is defined and used (Brost, Wajdeczko)
Jonathan Cavitt (3):
drm/xe: Add error_injectable define
Revert "drm/xe: Add VM bind IOCTL error injection" drm/xe/xe_vm: Add error injection support to lock and prep
drivers/gpu/drm/xe/xe_device.c | 3 ++ drivers/gpu/drm/xe/xe_device_types.h | 12 -------- drivers/gpu/drm/xe/xe_exec_queue.c | 2 ++ drivers/gpu/drm/xe/xe_ggtt.c | 1 + drivers/gpu/drm/xe/xe_guc.c | 1 + drivers/gpu/drm/xe/xe_guc_ads.c | 1 + drivers/gpu/drm/xe/xe_guc_ct.c | 20 ++++--------- drivers/gpu/drm/xe/xe_guc_log.c | 1 + drivers/gpu/drm/xe/xe_guc_relay.c | 1 + drivers/gpu/drm/xe/xe_hw_engine_class_sysfs.c | 2 ++ drivers/gpu/drm/xe/xe_hw_engine_group.c | 1 + drivers/gpu/drm/xe/xe_macros.h | 6 ++++ drivers/gpu/drm/xe/xe_mmio.c | 1 + drivers/gpu/drm/xe/xe_oa.c | 1 + drivers/gpu/drm/xe/xe_pcode.c | 2 ++ drivers/gpu/drm/xe/xe_pm.c | 1 + drivers/gpu/drm/xe/xe_pt.c | 15 ++-------- drivers/gpu/drm/xe/xe_sriov.c | 2 ++ drivers/gpu/drm/xe/xe_sync.c | 1 + drivers/gpu/drm/xe/xe_tile.c | 1 + drivers/gpu/drm/xe/xe_tuning.c | 2 ++ drivers/gpu/drm/xe/xe_uc_fw.c | 1 + drivers/gpu/drm/xe/xe_vm.c | 30 +++++-------------- drivers/gpu/drm/xe/xe_vm_types.h | 14 --------- drivers/gpu/drm/xe/xe_wa.c | 2 ++ drivers/gpu/drm/xe/xe_wopcm.c | 1 + 26 files changed, 50 insertions(+), 75 deletions(-)
Signature · 1 line
2.43.0
PATCH v4 1/3 drm/xe: Add error_injectable define
Add a declaration for the function attribute "error_injectable", which appends noinline to functions tagged with ALLOW_ERROR_INJECTION only if CONFIG_FUNCTION_ERROR_INJECTION is enabled. This function attribute was added to drivers/gpu/drm/xe/xe_macros.h, and has been applied to all Xe functions with ALLOW_ERROR_INJECTION enabled.
v2:
- Move error_injectable from error-injection.h to xe_macros.h (Wajdeczko)
- Reformat function attribute application to minimize diff size (Brost)
--- drivers/gpu/drm/xe/xe_device.c | 3 +++ drivers/gpu/drm/xe/xe_exec_queue.c | 2 ++ drivers/gpu/drm/xe/xe_ggtt.c | 1 + drivers/gpu/drm/xe/xe_guc.c | 1 + drivers/gpu/drm/xe/xe_guc_ads.c | 1 + drivers/gpu/drm/xe/xe_guc_ct.c | 20 +++++-------------- drivers/gpu/drm/xe/xe_guc_log.c | 1 + drivers/gpu/drm/xe/xe_guc_relay.c | 1 + drivers/gpu/drm/xe/xe_hw_engine_class_sysfs.c | 2 ++ drivers/gpu/drm/xe/xe_hw_engine_group.c | 1 + drivers/gpu/drm/xe/xe_macros.h | 6 ++++++ drivers/gpu/drm/xe/xe_mmio.c | 1 + drivers/gpu/drm/xe/xe_oa.c | 1 + drivers/gpu/drm/xe/xe_pcode.c | 2 ++ drivers/gpu/drm/xe/xe_pm.c | 1 + drivers/gpu/drm/xe/xe_pt.c | 3 +++ drivers/gpu/drm/xe/xe_sriov.c | 2 ++ drivers/gpu/drm/xe/xe_sync.c | 1 + drivers/gpu/drm/xe/xe_tile.c | 1 + drivers/gpu/drm/xe/xe_tuning.c | 2 ++ drivers/gpu/drm/xe/xe_uc_fw.c | 1 + drivers/gpu/drm/xe/xe_vm.c | 5 +++++ drivers/gpu/drm/xe/xe_wa.c | 2 ++ drivers/gpu/drm/xe/xe_wopcm.c | 1 + 24 files changed, 47 insertions(+), 15 deletions(-)
drivers/gpu/drm/xe/xe_device.c +3 -0
@@ -417,6 +417,7 @@ static void xe_device_destroy(struct drm_device *dev, void *dummy)ttm_device_fini (&xe->ttm); } +error_injectable struct xe_device *xe_device_create(struct pci_dev *pdev,const struct pci_device_id *ent) {
@@ -634,6 +635,7 @@ static bool verify_lmem_ready(struct xe_device *xe)return !!val; } +error_injectable static int wait_for_lmem_ready(struct xe_device *xe) {unsigned long timeout, start;
@@ -719,6 +721,7 @@ static int xe_device_vram_alloc(struct xe_device *xe)* * Return: 0 on success, error code on failure */ +error_injectable int xe_device_probe_early(struct xe_device *xe) {int err;
drivers/gpu/drm/xe/xe_exec_queue.c +2 -0
@@ -199,6 +199,7 @@ static int __xe_exec_queue_init(struct xe_exec_queue *q)return err; } +error_injectable struct xe_exec_queue *xe_exec_queue_create(struct xe_device *xe, struct xe_vm *vm, u32 logical_mask, u16 width, struct xe_hw_engine *hwe, u32 flags,
@@ -282,6 +283,7 @@ struct xe_exec_queue *xe_exec_queue_create_class(struct xe_device *xe, struct xe* * Returns exec queue on success, ERR_PTR on failure */ +error_injectable struct xe_exec_queue *xe_exec_queue_create_bind(struct xe_device *xe,struct xe_tile *tile,u32 flags,u64 extensions)
drivers/gpu/drm/xe/xe_ggtt.c +1 -0
@@ -256,6 +256,7 @@ static void dev_fini_ggtt(void *arg)* * Return: 0 on success or a negative error code on failure. */ +error_injectable int xe_ggtt_init_early(struct xe_ggtt *ggtt) {struct xe_device *xe =tile_to_xe (ggtt->tile);
drivers/gpu/drm/xe/xe_guc.c +1 -0
@@ -1405,6 +1405,7 @@ int xe_guc_auth_huc(struct xe_guc *guc, u32 rsa_addr)return xe_guc_ct_send_block (&guc->ct, action,ARRAY_SIZE (action)); } +error_injectable int xe_guc_mmio_send_recv(struct xe_guc *guc, const u32 *request,u32 len,u32 *response_buf) {
drivers/gpu/drm/xe/xe_guc_ads.c +1 -0
@@ -386,6 +386,7 @@ static int calculate_waklv_size(struct xe_guc_ads *ads)#define MAX_GOLDEN_LRC_SIZE (SZ_4K * 64) +error_injectable int xe_guc_ads_init(struct xe_guc_ads *ads) {struct xe_device *xe =ads_to_xe (ads);
drivers/gpu/drm/xe/xe_guc_ct.c +5 -15
@@ -213,6 +213,7 @@ static void primelockdep(struct xe_guc_ct *ct)fs_reclaim_release (GFP_KERNEL ); } +error_injectable int xe_guc_ct_init_noalloc(struct xe_guc_ct *ct) {struct xe_device *xe =ct_to_xe (ct);
@@ -252,6 +253,7 @@ int xe_guc_ct_init_noalloc(struct xe_guc_ct *ct) }ALLOW_ERROR_INJECTION (xe_guc_ct_init_noalloc,ERRNO );/* See xe_pci_probe() */ +error_injectable int xe_guc_ct_init(struct xe_guc_ct *ct) {struct xe_device *xe =ct_to_xe (ct);
@@ -1149,6 +1151,7 @@ static int guc_ct_send_recv(struct xe_guc_ct *ct, const u32 *action, u32 len,* DATA0 from `HXG Response`_ if &response_buffer was NULL, or * a negative error code on failure. */ +error_injectable int xe_guc_ct_send_recv(struct xe_guc_ct *ct, const u32 *action, u32 len,u32 *response_buffer) {
@@ -2069,22 +2072,9 @@ void xe_guc_ct_print(struct xe_guc_ct *ct, struct drm_printer *p, bool want_ctb)#if IS_ENABLED (CONFIG_DRM_XE_DEBUG ) -#ifdef CONFIG_FUNCTION_ERROR_INJECTION -/* -* This is a helper function which assists the driver in identifying if a fault -* injection test is currently active, allowing it to reduce unnecessary debug -* output. Typically, the function returns zero, but the fault injection -* framework can alter this to return an error. Since faults are injected -* through this function, it's important to ensure the compiler doesn't optimize -* it into an inline function. To avoid such optimization, the 'noinline' -* attribute is applied. Compiler optimizes the static function defined in the -* header file as an inline function. -*/ -noinline int xe_is_injection_active(void) { return 0; } -ALLOW_ERROR_INJECTION (xe_is_injection_active,ERRNO ); -#else +error_injectable int xe_is_injection_active(void) { return 0; } -#endif +ALLOW_ERROR_INJECTION (xe_is_injection_active,ERRNO );static void ct_dead_capture (struct xe_guc_ct *ct,struct guc_ctb *ctb,u32 reason_code) {
drivers/gpu/drm/xe/xe_guc_log.c +1 -0
@@ -251,6 +251,7 @@ void xe_guc_log_print(struct xe_guc_log *log, struct drm_printer *p)xe_guc_log_snapshot_free (snapshot); } +error_injectable int xe_guc_log_init(struct xe_guc_log *log) {struct xe_device *xe =log_to_xe (log);
drivers/gpu/drm/xe/xe_guc_relay.c +1 -0
@@ -330,6 +330,7 @@ static void __fini_relay(struct drm_device *drm, void *arg)* * Return: 0 on success or a negative error code on failure. */ +error_injectable int xe_guc_relay_init(struct xe_guc_relay *relay) {const int XE_RELAY_MEMPOOL_MIN_NUM =1 ;
drivers/gpu/drm/xe/xe_hw_engine_class_sysfs.c +2 -0
@@ -10,6 +10,7 @@#include "xe_device.h" #include "xe_gt.h" #include "xe_hw_engine_class_sysfs.h" +#include "xe_macros.h" #include "xe_pm.h" #define MAX_ENGINE_CLASS_NAME_LEN 16
@@ -580,6 +581,7 @@ static void hw_engine_class_defaults_fini(void *arg)kobject_put (kobj); } +error_injectable static int xe_add_hw_engine_class_defaults(struct xe_device *xe,struct kobject *parent) {
drivers/gpu/drm/xe/xe_hw_engine_group.c +1 -0
@@ -119,6 +119,7 @@ int xe_hw_engine_setup_groups(struct xe_gt *gt)* Return: 0 on success, * -EINTR if the lock could not be acquired */ +error_injectable int xe_hw_engine_group_add_exec_queue(struct xe_hw_engine_group *group, struct xe_exec_queue *q) {int err;
drivers/gpu/drm/xe/xe_macros.h +6 -0
@@ -19,4 +19,10 @@ cond__; \ }) +#ifdef CONFIG_FUNCTION_ERROR_INJECTION +#define error_injectable noinline +#else +#define error_injectable +#endif +#endif
drivers/gpu/drm/xe/xe_mmio.c +1 -0
@@ -90,6 +90,7 @@ static void mmio_fini(void *arg) root_tile->mmio.regs =NULL ; } +error_injectable int xe_mmio_probe_early(struct xe_device *xe) {struct xe_tile *root_tile =xe_device_get_root_tile (xe);
drivers/gpu/drm/xe/xe_oa.c +1 -0
@@ -2225,6 +2225,7 @@ static bool xe_oa_is_valid_config_reg_addr(struct xe_oa *oa, u32 addr)xe_oa_is_valid_mux_addr (oa, addr); } +error_injectable static struct xe_oa_reg *xe_oa_alloc_regs (struct xe_oa *oa,bool (*is_valid)(struct xe_oa *oa,u32 addr),u32 __user *regs,u32 n_regs)
drivers/gpu/drm/xe/xe_pcode.c +2 -0
@@ -13,6 +13,7 @@#include "xe_assert.h" #include "xe_device.h" +#include "xe_macros.h" #include "xe_mmio.h" #include "xe_pcode_api.h"
@@ -331,6 +332,7 @@ void xe_pcode_init(struct xe_tile *tile)* * Returns 0 on success, error code otherwise */ +error_injectable int xe_pcode_probe_early(struct xe_device *xe) {return xe_pcode_ready (xe, false);
drivers/gpu/drm/xe/xe_pm.c +1 -0
@@ -273,6 +273,7 @@ static void xe_pm_runtime_init(struct xe_device *xe)pm_runtime_put (dev); } +error_injectable int xe_pm_init_early(struct xe_device *xe) {int err;
drivers/gpu/drm/xe/xe_pt.c +3 -0
@@ -98,6 +98,7 @@ static void xe_pt_free(struct xe_pt *pt)* Return: A valid struct xe_pt pointer on success, Pointer error code on * error. */ +error_injectable struct xe_pt *xe_pt_create(struct xe_vm *vm, struct xe_tile *tile,unsigned int level) {
@@ -2132,6 +2133,7 @@ xe_pt_update_ops_init(struct xe_vm_pgtable_update_ops *pt_update_ops)* * Return: 0 on success, negative error code on error. */ +error_injectable int xe_pt_update_ops_prepare(struct xe_tile *tile, struct xe_vma_ops *vops) { struct xe_vm_pgtable_update_ops *pt_update_ops =
@@ -2364,6 +2366,7 @@ static const struct xe_migrate_pt_update_ops svm_migrate_ops;* * Return: fence on success, negative ERR_PTR on error. */ +error_injectable struct dma_fence *xe_pt_update_ops_run (struct xe_tile *tile,struct xe_vma_ops *vops) {
drivers/gpu/drm/xe/xe_sriov.c +2 -0
@@ -11,6 +11,7 @@#include "xe_assert.h" #include "xe_device.h" +#include "xe_macros.h" #include "xe_mmio.h" #include "xe_sriov.h" #include "xe_sriov_pf.h"
@@ -104,6 +105,7 @@ static void fini_sriov(struct drm_device *drm, void *arg)* * Return: 0 on success or a negative error code on failure. */ +error_injectable int xe_sriov_init(struct xe_device *xe) {if (!IS_SRIOV (xe))
drivers/gpu/drm/xe/xe_sync.c +1 -0
@@ -110,6 +110,7 @@ static void user_fence_cb(struct dma_fence *fence, struct dma_fence_cb *cb)kick_ufence (ufence, fence); } +error_injectable int xe_sync_entry_parse(struct xe_device *xe, struct xe_file *xef, struct xe_sync_entry *sync, struct drm_xe_sync __user *sync_user,
drivers/gpu/drm/xe/xe_tile.c +1 -0
@@ -138,6 +138,7 @@ int xe_tile_alloc_vram(struct xe_tile *tile)* * Returns: 0 on success, negative error code on error. */ +error_injectable int xe_tile_init_early(struct xe_tile *tile, struct xe_device *xe, u8 id) {int err;
drivers/gpu/drm/xe/xe_tuning.c +2 -0
@@ -11,6 +11,7 @@#include "regs/xe_gt_regs.h" #include "xe_gt_types.h" +#include "xe_macros.h" #include "xe_platform_types.h" #include "xe_rtp.h"
@@ -148,6 +149,7 @@ static const struct xe_rtp_entry_sr lrc_tunings[] = {* * Returns 0 for success, negative error code otherwise. */ +error_injectable int xe_tuning_init(struct xe_gt *gt) {struct xe_device *xe =gt_to_xe (gt);
drivers/gpu/drm/xe/xe_uc_fw.c +1 -0
@@ -817,6 +817,7 @@ static int uc_fw_copy(struct xe_uc_fw *uc_fw, const void *data, size_t size, u32return err; } +error_injectable int xe_uc_fw_init(struct xe_uc_fw *uc_fw) {const struct firmware *fw =NULL ;
drivers/gpu/drm/xe/xe_vm.c +5 -0
@@ -220,6 +220,7 @@ static void resume_and_reinstall_preempt_fences(struct xe_vm *vm, } } +error_injectable int xe_vm_add_compute_exec_queue(struct xe_vm *vm, struct xe_exec_queue *q) {struct drm_gpuvm_exec vm_exec = {
@@ -781,6 +782,7 @@ int xe_vm_userptr_check_repin(struct xe_vm *vm) list_empty_careful(&vm->userptr.invalidated)) ? 0 : -EAGAIN; } +error_injectable static int xe_vma_ops_alloc(struct xe_vma_ops *vops, bool array_of_binds) {int i;
@@ -1629,6 +1631,7 @@ static void vm_destroy_work_func(struct work_struct *w);* * Return: 0 on success, negative error code on error. */ +error_injectable static int xe_vm_create_scratch(struct xe_device *xe, struct xe_tile *tile,struct xe_vm *vm) {
@@ -2422,6 +2425,7 @@ static void xe_svm_prefetch_gpuva_ops_fini(struct drm_gpuva_ops *ops)* Create operations list from IOCTL arguments, setup operations fields so parse * and commit steps are decoupled from IOCTL arguments. This step can fail. */ +error_injectable static struct drm_gpuva_ops * vm_bind_ioctl_ops_create(struct xe_vm *vm, struct xe_vma_ops *vops, struct xe_bo *bo, u64 bo_offset_or_userptr,
@@ -3432,6 +3436,7 @@ static void vm_bind_ioctl_ops_fini(struct xe_vm *vm, struct xe_vma_ops *vops, } } +error_injectable static struct dma_fence *vm_bind_ioctl_ops_execute(struct xe_vm *vm,struct xe_vma_ops *vops) {
drivers/gpu/drm/xe/xe_wa.c +2 -0
@@ -20,6 +20,7 @@#include "xe_force_wake.h" #include "xe_gt.h" #include "xe_hw_engine_types.h" +#include "xe_macros.h" #include "xe_mmio.h" #include "xe_platform_types.h" #include "xe_rtp.h"
@@ -1011,6 +1012,7 @@ int xe_wa_device_init(struct xe_device *xe)* * Returns 0 for success, negative error code otherwise. */ +error_injectable int xe_wa_gt_init(struct xe_gt *gt) {struct xe_device *xe =gt_to_xe (gt);
drivers/gpu/drm/xe/xe_wopcm.c +1 -0
@@ -196,6 +196,7 @@ u32 xe_wopcm_size(struct xe_device *xe)* size. It will fail the WOPCM init if any of these checks fail, so that the * following WOPCM registers setup and GuC firmware uploading would be aborted. */ +error_injectable int xe_wopcm_init(struct xe_wopcm *wopcm) {struct xe_device *xe =wopcm_to_xe (wopcm);
Signature · 1 line
2.43.0
Re: [PATCH v4 1/3] drm/xe: Add error_injectable define
Quoted 3 lines · Jonathan Cavitt
Add a declaration for the function attribute "
error_injectable", which appends noinline to functions tagged withALLOW_ERROR_INJECTIONonly ifCONFIG_FUNCTION_ERROR_INJECTIONis enabled.
this really doesn't answer the question "why"
Quoted 2 lines
This function attribute was
added todrivers/gpu/drm/xe/xe_macros.h,
this can be clearly seen in diff
Quoted 6 lines
and has been applied to
all Xe functions withALLOW_ERROR_INJECTIONenabled.v2:
- Moveerror_injectablefromerror-injection.htoxe_macros.h(Wajdeczko)
it would be better to just say (Michal)
Quoted 33 lines
- Reformat function attribute application to minimize diff size (Brost)
Suggested-by Matthew Brost <[email protected]>Suggested-by John Harrison <[email protected]>Signed-off-by Jonathan Cavitt <[email protected]>Cc Michal Wajdeczko <[email protected]>--- drivers/gpu/drm/xe/xe_device.c | 3 +++ drivers/gpu/drm/xe/xe_exec_queue.c | 2 ++ drivers/gpu/drm/xe/xe_ggtt.c | 1 + drivers/gpu/drm/xe/xe_guc.c | 1 + drivers/gpu/drm/xe/xe_guc_ads.c | 1 + drivers/gpu/drm/xe/xe_guc_ct.c | 20 +++++-------------- drivers/gpu/drm/xe/xe_guc_log.c | 1 + drivers/gpu/drm/xe/xe_guc_relay.c | 1 + drivers/gpu/drm/xe/xe_hw_engine_class_sysfs.c | 2 ++ drivers/gpu/drm/xe/xe_hw_engine_group.c | 1 + drivers/gpu/drm/xe/xe_macros.h | 6 ++++++ drivers/gpu/drm/xe/xe_mmio.c | 1 + drivers/gpu/drm/xe/xe_oa.c | 1 + drivers/gpu/drm/xe/xe_pcode.c | 2 ++ drivers/gpu/drm/xe/xe_pm.c | 1 + drivers/gpu/drm/xe/xe_pt.c | 3 +++ drivers/gpu/drm/xe/xe_sriov.c | 2 ++ drivers/gpu/drm/xe/xe_sync.c | 1 + drivers/gpu/drm/xe/xe_tile.c | 1 + drivers/gpu/drm/xe/xe_tuning.c | 2 ++ drivers/gpu/drm/xe/xe_uc_fw.c | 1 + drivers/gpu/drm/xe/xe_vm.c | 5 +++++ drivers/gpu/drm/xe/xe_wa.c | 2 ++ drivers/gpu/drm/xe/xe_wopcm.c | 1 + 24 files changed, 47 insertions(+), 15 deletions(-)
...
Quoted 29 lines
drivers/gpu/drm/xe/xe_guc_ct.c +3
-0@@ -213,6 +213,7 @@ static void primelockdep(struct xe_guc_ct *ct)fs_reclaim_release (GFP_KERNEL ); } +error_injectable int xe_guc_ct_init_noalloc(struct xe_guc_ct *ct) {struct xe_device *xe =ct_to_xe (ct);@@ -252,6 +253,7 @@ int xe_guc_ct_init_noalloc(struct xe_guc_ct *ct) }ALLOW_ERROR_INJECTION (xe_guc_ct_init_noalloc,ERRNO );/* See xe_pci_probe() */ +error_injectable int xe_guc_ct_init(struct xe_guc_ct *ct) {struct xe_device *xe =ct_to_xe (ct);@@ -1149,6 +1151,7 @@ static int guc_ct_send_recv(struct xe_guc_ct *ct, const u32 *action, u32 len,* DATA0 from `HXG Response`_ if &response_buffer was NULL, or * a negative error code on failure. */ +error_injectable int xe_guc_ct_send_recv(struct xe_guc_ct *ct, const u32 *action, u32 len,u32 *response_buffer) {
drivers/gpu/drm/xe/xe_guc_ct.c void xe_guc_ct_print(struct xe_guc_ct *ct, struct drm_printer *p, bool want_ctb) · line 2077
Quoted 9 lines
drivers/gpu/drm/xe/xe_guc_ct.c +0
-6@@ -2069,22 +2072,9 @@ void xe_guc_ct_print(struct xe_guc_ct *ct, struct drm_printer *p, bool want_ctb)#if IS_ENABLED (CONFIG_DRM_XE_DEBUG ) -#ifdef CONFIG_FUNCTION_ERROR_INJECTION -/* -* This is a helper function which assists the driver in identifying if a fault -* injection test is currently active, allowing it to reduce unnecessary debug -* output. Typically, the function returns zero, but the fault injection -* framework can alter this to return an error. Since faults are injected
you can use some parts of below explanation in your commit msg
Quoted 3 lines
drivers/gpu/drm/xe/xe_guc_ct.c +0
-3-* through this function, it's important to ensure the compiler doesn't optimize -* it into an inline function. To avoid such optimization, the 'noinline' -* attribute is applied.
....
drivers/gpu/drm/xe/xe_macros.h line 21
Quoted 8 lines
drivers/gpu/drm/xe/xe_macros.h +0
-0@@ -19,4 +19,10 @@ cond__; \ })
and it wouldn't hurt if we also put some description here with how/when to use below macro
Quoted 7 lines
drivers/gpu/drm/xe/xe_macros.h +6
-0+#ifdef CONFIG_FUNCTION_ERROR_INJECTION +#define error_injectable noinline +#else +#define error_injectable +#endif +#endif
PATCH v4 2/3 Revert "drm/xe: Add VM bind IOCTL error injection"
In reply to Jonathan CavittThis reverts commit 04e9c0ce19ac68afd8be7fd54772db3b0356cf75.
Error injection should use the error injection interface, and should be decoupled from CONFIG_DRM_XE_DEBUG.
--- drivers/gpu/drm/xe/xe_device_types.h | 12 ------------ drivers/gpu/drm/xe/xe_pt.c | 12 ------------ drivers/gpu/drm/xe/xe_vm.c | 23 +---------------------- drivers/gpu/drm/xe/xe_vm_types.h | 14 -------------- 4 files changed, 1 insertion(+), 60 deletions(-)
drivers/gpu/drm/xe/xe_device_types.h +0 -12
@@ -27,10 +27,6 @@#include "xe_step_types.h" #include "xe_survivability_mode_types.h" -#if IS_ENABLED (CONFIG_DRM_XE_DEBUG ) -#define TEST_VM_OPS_ERROR -#endif -struct dram_info ;struct intel_display ;struct intel_dg_nvm_dev ;
@@ -565,14 +561,6 @@ struct xe_device {/** @atomic_svm_timeslice_ms: Atomic SVM fault timeslice MS */ u32 atomic_svm_timeslice_ms; -#ifdef TEST_VM_OPS_ERROR -/** -* @vm_inject_error_position: inject errors at different places in VM -* bind IOCTL based on this value -*/ -u8 vm_inject_error_position; -#endif -#if IS_ENABLED (CONFIG_TRACE_GPU_MEM )/** * @global_total_pages: global GPU page usage tracked for gpu_mem
drivers/gpu/drm/xe/xe_pt.c +0 -12
@@ -2162,12 +2162,6 @@ int xe_pt_update_ops_prepare(struct xe_tile *tile, struct xe_vma_ops *vops)xe_tile_assert (tile, pt_update_ops->current_op <= pt_update_ops->num_ops); -#ifdef TEST_VM_OPS_ERROR -if (vops->inject_error && - vops->vm->xe->vm_inject_error_position ==FORCE_OP_ERROR_PREPARE ) -return -ENOSPC ; -#endif -return 0 ; }ALLOW_ERROR_INJECTION (xe_pt_update_ops_prepare,ERRNO );
@@ -2399,12 +2393,6 @@ xe_pt_update_ops_run(struct xe_tile *tile, struct xe_vma_ops *vops)return dma_fence_get_stub (); } -#ifdef TEST_VM_OPS_ERROR -if (vops->inject_error && - vm->xe->vm_inject_error_position ==FORCE_OP_ERROR_RUN ) -return ERR_PTR (-ENOSPC ); -#endif -if (pt_update_ops->needs_invalidation) { ijob = xe_gt_tlb_inval_job_create(pt_update_ops->q, tile->primary_gt,
drivers/gpu/drm/xe/xe_vm.c +1 -22
@@ -3222,12 +3222,6 @@ static int vm_bind_ioctl_ops_lock_and_prep(struct drm_exec *exec,return err; } -#ifdef TEST_VM_OPS_ERROR -if (vops->inject_error && - vm->xe->vm_inject_error_position ==FORCE_OP_ERROR_LOCK ) -return -ENOSPC ; -#endif -return 0 ; }
@@ -3472,7 +3466,7 @@ static struct dma_fence *vm_bind_ioctl_ops_execute(struct xe_vm *vm, }ALLOW_ERROR_INJECTION (vm_bind_ioctl_ops_execute,ERRNO ); -#define SUPPORTED_FLAGS_STUB \ +#define SUPPORTED_FLAGS \ (DRM_XE_VM_BIND_FLAG_READONLY | \ DRM_XE_VM_BIND_FLAG_IMMEDIATE | \ DRM_XE_VM_BIND_FLAG_NULL | \
@@ -3480,12 +3474,6 @@ ALLOW_ERROR_INJECTION(vm_bind_ioctl_ops_execute, ERRNO); DRM_XE_VM_BIND_FLAG_CHECK_PXP | \ DRM_XE_VM_BIND_FLAG_CPU_ADDR_MIRROR) -#ifdef TEST_VM_OPS_ERROR -#define SUPPORTED_FLAGS (SUPPORTED_FLAGS_STUB | FORCE_OP_ERROR) -#else -#define SUPPORTED_FLAGS SUPPORTED_FLAGS_STUB -#endif -#define XE_64K_PAGE_MASK 0xffffull#define ALL_DRM_XE_SYNCS_FLAGS (DRM_XE_SYNCS_FLAG_WAIT_FOR_OP)
@@ -3868,15 +3856,6 @@ int xe_vm_bind_ioctl(struct drm_device *dev, void *data, struct drm_file *file) err =vm_bind_ioctl_ops_parse (vm, ops[i], &vops);if (err) goto unwind_ops; - -#ifdef TEST_VM_OPS_ERROR -if (flags &FORCE_OP_ERROR ) { - vops.inject_error = true; - vm->xe->vm_inject_error_position = - (vm->xe->vm_inject_error_position +1 ) % -FORCE_OP_ERROR_COUNT ; - } -#endif }/* Nothing to do */
drivers/gpu/drm/xe/xe_vm_types.h +0 -14
@@ -25,16 +25,6 @@ struct xe_user_fence;struct xe_vm ;struct xe_vm_pgtable_update_op ; -#if IS_ENABLED (CONFIG_DRM_XE_DEBUG ) -#define TEST_VM_OPS_ERROR -#define FORCE_OP_ERROR BIT(31) - -#define FORCE_OP_ERROR_LOCK 0 -#define FORCE_OP_ERROR_PREPARE 1 -#define FORCE_OP_ERROR_RUN 2 -#define FORCE_OP_ERROR_COUNT 3 -#endif -#define XE_VMA_READ_ONLY DRM_GPUVA_USERBITS#define XE_VMA_DESTROYED (DRM_GPUVA_USERBITS << 1)#define XE_VMA_ATOMIC_PTE_BIT (DRM_GPUVA_USERBITS << 2)
@@ -512,10 +502,6 @@ struct xe_vma_ops {#define XE_VMA_OPS_FLAG_HAS_SVM_PREFETCH BIT(0)#define XE_VMA_OPS_FLAG_MADVISE BIT(1) u32 flags; -#ifdef TEST_VM_OPS_ERROR -/** @inject_error: inject error to test error handling */ -bool inject_error; -#endif };#endif
Signature · 1 line
2.43.0
PATCH v4 3/3 drm/xe/xe_vm: Add error injection support to lock and prep
In reply to Jonathan CavittAdd error injection support to the function vm_bind_ioctl_ops_lock_and_prep. This necessitates marking the function as noinline.
v2: Only noinline vm_bind_ioctl_ops_lock_and_prep when function error injection is enabled (Brost)
v3: Use error_injectable to apply v2 change (Brost, Harrison)
v4: Move error_injectable function attribute (Brost)
--- drivers/gpu/drm/xe/xe_vm.c | 2 ++ 1 file changed, 2 insertions(+)
drivers/gpu/drm/xe/xe_vm.c +2 -0
@@ -3205,6 +3205,7 @@ static int vm_bind_ioctl_ops_prefetch_ranges(struct xe_vm *vm, struct xe_vma_opsreturn 0 ; } +error_injectable static int vm_bind_ioctl_ops_lock_and_prep(struct drm_exec *exec,struct xe_vm *vm,struct xe_vma_ops *vops)
@@ -3224,6 +3225,7 @@ static int vm_bind_ioctl_ops_lock_and_prep(struct drm_exec *exec,return 0 ; } +ALLOW_ERROR_INJECTION (vm_bind_ioctl_ops_lock_and_prep,ERRNO );static void op_trace (struct xe_vma_op *op) {
Signature · 1 line
2.43.0