summaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/xe
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/gpu/drm/xe')
-rw-r--r--drivers/gpu/drm/xe/Makefile2
-rw-r--r--drivers/gpu/drm/xe/display/xe_display.c28
-rw-r--r--drivers/gpu/drm/xe/display/xe_dsb_buffer.c8
-rw-r--r--drivers/gpu/drm/xe/display/xe_fb_pin.c3
-rw-r--r--drivers/gpu/drm/xe/regs/xe_gt_regs.h9
-rw-r--r--drivers/gpu/drm/xe/xe_bo.c6
-rw-r--r--drivers/gpu/drm/xe/xe_device.c91
-rw-r--r--drivers/gpu/drm/xe/xe_device.h4
-rw-r--r--drivers/gpu/drm/xe/xe_device_types.h3
-rw-r--r--drivers/gpu/drm/xe/xe_drm_client.c5
-rw-r--r--drivers/gpu/drm/xe/xe_exec_queue.c34
-rw-r--r--drivers/gpu/drm/xe/xe_exec_queue_types.h9
-rw-r--r--drivers/gpu/drm/xe/xe_gsc.c8
-rw-r--r--drivers/gpu/drm/xe/xe_gt.c55
-rw-r--r--drivers/gpu/drm/xe/xe_gt_pagefault.c18
-rw-r--r--drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c11
-rw-r--r--drivers/gpu/drm/xe/xe_gt_sriov_vf.c2
-rw-r--r--drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c201
-rw-r--r--drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h12
-rw-r--r--drivers/gpu/drm/xe/xe_gt_tlb_invalidation_types.h4
-rw-r--r--drivers/gpu/drm/xe/xe_gt_types.h6
-rw-r--r--drivers/gpu/drm/xe/xe_guc_ct.c10
-rw-r--r--drivers/gpu/drm/xe/xe_guc_submit.c8
-rw-r--r--drivers/gpu/drm/xe/xe_hw_fence.c9
-rw-r--r--drivers/gpu/drm/xe/xe_hw_fence_types.h7
-rw-r--r--drivers/gpu/drm/xe/xe_hwmon.c5
-rw-r--r--drivers/gpu/drm/xe/xe_lrc.c15
-rw-r--r--drivers/gpu/drm/xe/xe_mmio.c28
-rw-r--r--drivers/gpu/drm/xe/xe_observation.c1
-rw-r--r--drivers/gpu/drm/xe/xe_pat.c11
-rw-r--r--drivers/gpu/drm/xe/xe_pm.c11
-rw-r--r--drivers/gpu/drm/xe/xe_preempt_fence.c3
-rw-r--r--drivers/gpu/drm/xe/xe_preempt_fence_types.h2
-rw-r--r--drivers/gpu/drm/xe/xe_pt.c26
-rw-r--r--drivers/gpu/drm/xe/xe_rtp.c2
-rw-r--r--drivers/gpu/drm/xe/xe_sched_job.c3
-rw-r--r--drivers/gpu/drm/xe/xe_sync.c14
-rw-r--r--drivers/gpu/drm/xe/xe_trace.h2
-rw-r--r--drivers/gpu/drm/xe/xe_ttm_vram_mgr.c2
-rw-r--r--drivers/gpu/drm/xe/xe_vm.c59
-rw-r--r--drivers/gpu/drm/xe/xe_wa.c18
-rw-r--r--drivers/gpu/drm/xe/xe_wa_oob.rules1
42 files changed, 544 insertions, 212 deletions
diff --git a/drivers/gpu/drm/xe/Makefile b/drivers/gpu/drm/xe/Makefile
index 628c245c4822..e97c9da451b3 100644
--- a/drivers/gpu/drm/xe/Makefile
+++ b/drivers/gpu/drm/xe/Makefile
@@ -25,12 +25,14 @@ $(obj)/generated/%_wa_oob.c $(obj)/generated/%_wa_oob.h: $(obj)/xe_gen_wa_oob \
uses_generated_oob := \
$(obj)/xe_ggtt.o \
+ $(obj)/xe_device.o \
$(obj)/xe_gsc.o \
$(obj)/xe_gt.o \
$(obj)/xe_guc.o \
$(obj)/xe_guc_ads.o \
$(obj)/xe_guc_pc.o \
$(obj)/xe_migrate.o \
+ $(obj)/xe_pat.o \
$(obj)/xe_ring_ops.o \
$(obj)/xe_vm.o \
$(obj)/xe_wa.o \
diff --git a/drivers/gpu/drm/xe/display/xe_display.c b/drivers/gpu/drm/xe/display/xe_display.c
index 8b83dcff72e1..49de4e4f8a75 100644
--- a/drivers/gpu/drm/xe/display/xe_display.c
+++ b/drivers/gpu/drm/xe/display/xe_display.c
@@ -132,6 +132,7 @@ static void xe_display_fini_noirq(void *arg)
return;
intel_display_driver_remove_noirq(xe);
+ intel_opregion_cleanup(xe);
}
int xe_display_init_noirq(struct xe_device *xe)
@@ -157,8 +158,10 @@ int xe_display_init_noirq(struct xe_device *xe)
intel_display_device_info_runtime_init(xe);
err = intel_display_driver_probe_noirq(xe);
- if (err)
+ if (err) {
+ intel_opregion_cleanup(xe);
return err;
+ }
return devm_add_action_or_reset(xe->drm.dev, xe_display_fini_noirq, xe);
}
@@ -280,6 +283,27 @@ static bool suspend_to_idle(void)
return false;
}
+static void xe_display_flush_cleanup_work(struct xe_device *xe)
+{
+ struct intel_crtc *crtc;
+
+ for_each_intel_crtc(&xe->drm, crtc) {
+ struct drm_crtc_commit *commit;
+
+ spin_lock(&crtc->base.commit_lock);
+ commit = list_first_entry_or_null(&crtc->base.commit_list,
+ struct drm_crtc_commit, commit_entry);
+ if (commit)
+ drm_crtc_commit_get(commit);
+ spin_unlock(&crtc->base.commit_lock);
+
+ if (commit) {
+ wait_for_completion(&commit->cleanup_done);
+ drm_crtc_commit_put(commit);
+ }
+ }
+}
+
void xe_display_pm_suspend(struct xe_device *xe, bool runtime)
{
bool s2idle = suspend_to_idle();
@@ -297,6 +321,8 @@ void xe_display_pm_suspend(struct xe_device *xe, bool runtime)
if (!runtime)
intel_display_driver_suspend(xe);
+ xe_display_flush_cleanup_work(xe);
+
intel_dp_mst_suspend(xe);
intel_hpd_cancel_work(xe);
diff --git a/drivers/gpu/drm/xe/display/xe_dsb_buffer.c b/drivers/gpu/drm/xe/display/xe_dsb_buffer.c
index 9e860c61f4b3..ccd0d87d438a 100644
--- a/drivers/gpu/drm/xe/display/xe_dsb_buffer.c
+++ b/drivers/gpu/drm/xe/display/xe_dsb_buffer.c
@@ -7,6 +7,8 @@
#include "intel_display_types.h"
#include "intel_dsb_buffer.h"
#include "xe_bo.h"
+#include "xe_device.h"
+#include "xe_device_types.h"
#include "xe_gt.h"
u32 intel_dsb_buffer_ggtt_offset(struct intel_dsb_buffer *dsb_buf)
@@ -16,7 +18,10 @@ u32 intel_dsb_buffer_ggtt_offset(struct intel_dsb_buffer *dsb_buf)
void intel_dsb_buffer_write(struct intel_dsb_buffer *dsb_buf, u32 idx, u32 val)
{
+ struct xe_device *xe = dsb_buf->vma->bo->tile->xe;
+
iosys_map_wr(&dsb_buf->vma->bo->vmap, idx * 4, u32, val);
+ xe_device_l2_flush(xe);
}
u32 intel_dsb_buffer_read(struct intel_dsb_buffer *dsb_buf, u32 idx)
@@ -26,9 +31,12 @@ u32 intel_dsb_buffer_read(struct intel_dsb_buffer *dsb_buf, u32 idx)
void intel_dsb_buffer_memset(struct intel_dsb_buffer *dsb_buf, u32 idx, u32 val, size_t size)
{
+ struct xe_device *xe = dsb_buf->vma->bo->tile->xe;
+
WARN_ON(idx > (dsb_buf->buf_size - size) / sizeof(*dsb_buf->cmd_buf));
iosys_map_memset(&dsb_buf->vma->bo->vmap, idx * 4, val, size);
+ xe_device_l2_flush(xe);
}
bool intel_dsb_buffer_create(struct intel_crtc *crtc, struct intel_dsb_buffer *dsb_buf, size_t size)
diff --git a/drivers/gpu/drm/xe/display/xe_fb_pin.c b/drivers/gpu/drm/xe/display/xe_fb_pin.c
index 423f367c7065..d7db44e79eaf 100644
--- a/drivers/gpu/drm/xe/display/xe_fb_pin.c
+++ b/drivers/gpu/drm/xe/display/xe_fb_pin.c
@@ -10,6 +10,7 @@
#include "intel_fb.h"
#include "intel_fb_pin.h"
#include "xe_bo.h"
+#include "xe_device.h"
#include "xe_ggtt.h"
#include "xe_gt.h"
#include "xe_pm.h"
@@ -304,6 +305,8 @@ static struct i915_vma *__xe_pin_fb_vma(const struct intel_framebuffer *fb,
if (ret)
goto err_unpin;
+ /* Ensure DPT writes are flushed */
+ xe_device_l2_flush(xe);
return vma;
err_unpin:
diff --git a/drivers/gpu/drm/xe/regs/xe_gt_regs.h b/drivers/gpu/drm/xe/regs/xe_gt_regs.h
index d44564bad009..3c2865040058 100644
--- a/drivers/gpu/drm/xe/regs/xe_gt_regs.h
+++ b/drivers/gpu/drm/xe/regs/xe_gt_regs.h
@@ -80,6 +80,9 @@
#define LE_CACHEABILITY_MASK REG_GENMASK(1, 0)
#define LE_CACHEABILITY(value) REG_FIELD_PREP(LE_CACHEABILITY_MASK, value)
+#define XE2_GAMREQSTRM_CTRL XE_REG(0x4194)
+#define CG_DIS_CNTLBUS REG_BIT(6)
+
#define CCS_AUX_INV XE_REG(0x4208)
#define VD0_AUX_INV XE_REG(0x4218)
@@ -372,6 +375,11 @@
#define XEHPC_L3CLOS_MASK(i) XE_REG_MCR(0xb194 + (i) * 8)
+#define XE2_GLOBAL_INVAL XE_REG(0xb404)
+
+#define SCRATCH1LPFC XE_REG(0xb474)
+#define EN_L3_RW_CCS_CACHE_FLUSH REG_BIT(0)
+
#define XE2LPM_L3SQCREG5 XE_REG_MCR(0xb658)
#define XE2_TDF_CTRL XE_REG(0xb418)
@@ -429,6 +437,7 @@
#define DIS_FIX_EOT1_FLUSH REG_BIT(9)
#define TDL_TSL_CHICKEN XE_REG_MCR(0xe4c4, XE_REG_OPTION_MASKED)
+#define STK_ID_RESTRICT REG_BIT(12)
#define SLM_WMTP_RESTORE REG_BIT(11)
#define ROW_CHICKEN XE_REG_MCR(0xe4f0, XE_REG_OPTION_MASKED)
diff --git a/drivers/gpu/drm/xe/xe_bo.c b/drivers/gpu/drm/xe/xe_bo.c
index 31192d983d9e..261d3d6c8a93 100644
--- a/drivers/gpu/drm/xe/xe_bo.c
+++ b/drivers/gpu/drm/xe/xe_bo.c
@@ -1575,7 +1575,7 @@ struct xe_bo *xe_bo_create_from_data(struct xe_device *xe, struct xe_tile *tile,
return bo;
}
-static void __xe_bo_unpin_map_no_vm(struct drm_device *drm, void *arg)
+static void __xe_bo_unpin_map_no_vm(void *arg)
{
xe_bo_unpin_map_no_vm(arg);
}
@@ -1590,7 +1590,7 @@ struct xe_bo *xe_managed_bo_create_pin_map(struct xe_device *xe, struct xe_tile
if (IS_ERR(bo))
return bo;
- ret = drmm_add_action_or_reset(&xe->drm, __xe_bo_unpin_map_no_vm, bo);
+ ret = devm_add_action_or_reset(xe->drm.dev, __xe_bo_unpin_map_no_vm, bo);
if (ret)
return ERR_PTR(ret);
@@ -1638,7 +1638,7 @@ int xe_managed_bo_reinit_in_vram(struct xe_device *xe, struct xe_tile *tile, str
if (IS_ERR(bo))
return PTR_ERR(bo);
- drmm_release_action(&xe->drm, __xe_bo_unpin_map_no_vm, *src);
+ devm_release_action(xe->drm.dev, __xe_bo_unpin_map_no_vm, *src);
*src = bo;
return 0;
diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c
index 76109415eba6..c89deffffb6d 100644
--- a/drivers/gpu/drm/xe/xe_device.c
+++ b/drivers/gpu/drm/xe/xe_device.c
@@ -54,6 +54,9 @@
#include "xe_vm.h"
#include "xe_vram.h"
#include "xe_wait_user_fence.h"
+#include "xe_wa.h"
+
+#include <generated/xe_wa_oob.h>
static int xe_file_open(struct drm_device *dev, struct drm_file *file)
{
@@ -87,9 +90,55 @@ static int xe_file_open(struct drm_device *dev, struct drm_file *file)
spin_unlock(&xe->clients.lock);
file->driver_priv = xef;
+ kref_init(&xef->refcount);
+
return 0;
}
+static void xe_file_destroy(struct kref *ref)
+{
+ struct xe_file *xef = container_of(ref, struct xe_file, refcount);
+ struct xe_device *xe = xef->xe;
+
+ xa_destroy(&xef->exec_queue.xa);
+ mutex_destroy(&xef->exec_queue.lock);
+ xa_destroy(&xef->vm.xa);
+ mutex_destroy(&xef->vm.lock);
+
+ spin_lock(&xe->clients.lock);
+ xe->clients.count--;
+ spin_unlock(&xe->clients.lock);
+
+ xe_drm_client_put(xef->client);
+ kfree(xef);
+}
+
+/**
+ * xe_file_get() - Take a reference to the xe file object
+ * @xef: Pointer to the xe file
+ *
+ * Anyone with a pointer to xef must take a reference to the xe file
+ * object using this call.
+ *
+ * Return: xe file pointer
+ */
+struct xe_file *xe_file_get(struct xe_file *xef)
+{
+ kref_get(&xef->refcount);
+ return xef;
+}
+
+/**
+ * xe_file_put() - Drop a reference to the xe file object
+ * @xef: Pointer to the xe file
+ *
+ * Used to drop reference to the xef object
+ */
+void xe_file_put(struct xe_file *xef)
+{
+ kref_put(&xef->refcount, xe_file_destroy);
+}
+
static void xe_file_close(struct drm_device *dev, struct drm_file *file)
{
struct xe_device *xe = to_xe_device(dev);
@@ -98,6 +147,8 @@ static void xe_file_close(struct drm_device *dev, struct drm_file *file)
struct xe_exec_queue *q;
unsigned long idx;
+ xe_pm_runtime_get(xe);
+
/*
* No need for exec_queue.lock here as there is no contention for it
* when FD is closing as IOCTLs presumably can't be modifying the
@@ -108,21 +159,14 @@ static void xe_file_close(struct drm_device *dev, struct drm_file *file)
xe_exec_queue_kill(q);
xe_exec_queue_put(q);
}
- xa_destroy(&xef->exec_queue.xa);
- mutex_destroy(&xef->exec_queue.lock);
mutex_lock(&xef->vm.lock);
xa_for_each(&xef->vm.xa, idx, vm)
xe_vm_close_and_put(vm);
mutex_unlock(&xef->vm.lock);
- xa_destroy(&xef->vm.xa);
- mutex_destroy(&xef->vm.lock);
- spin_lock(&xe->clients.lock);
- xe->clients.count--;
- spin_unlock(&xe->clients.lock);
+ xe_file_put(xef);
- xe_drm_client_put(xef->client);
- kfree(xef);
+ xe_pm_runtime_put(xe);
}
static const struct drm_ioctl_desc xe_ioctls[] = {
@@ -779,6 +823,11 @@ void xe_device_td_flush(struct xe_device *xe)
if (!IS_DGFX(xe) || GRAPHICS_VER(xe) < 20)
return;
+ if (XE_WA(xe_root_mmio_gt(xe), 16023588340)) {
+ xe_device_l2_flush(xe);
+ return;
+ }
+
for_each_gt(gt, xe, id) {
if (xe_gt_is_media_type(gt))
continue;
@@ -802,6 +851,30 @@ void xe_device_td_flush(struct xe_device *xe)
}
}
+void xe_device_l2_flush(struct xe_device *xe)
+{
+ struct xe_gt *gt;
+ int err;
+
+ gt = xe_root_mmio_gt(xe);
+
+ if (!XE_WA(gt, 16023588340))
+ return;
+
+ err = xe_force_wake_get(gt_to_fw(gt), XE_FW_GT);
+ if (err)
+ return;
+
+ spin_lock(&gt->global_invl_lock);
+ xe_mmio_write32(gt, XE2_GLOBAL_INVAL, 0x1);
+
+ if (xe_mmio_wait32(gt, XE2_GLOBAL_INVAL, 0x1, 0x0, 150, NULL, true))
+ xe_gt_err_once(gt, "Global invalidation timeout\n");
+ spin_unlock(&gt->global_invl_lock);
+
+ xe_force_wake_put(gt_to_fw(gt), XE_FW_GT);
+}
+
u32 xe_device_ccs_bytes(struct xe_device *xe, u64 size)
{
return xe_device_has_flat_ccs(xe) ?
diff --git a/drivers/gpu/drm/xe/xe_device.h b/drivers/gpu/drm/xe/xe_device.h
index bb07f5669dbb..533ccfb2567a 100644
--- a/drivers/gpu/drm/xe/xe_device.h
+++ b/drivers/gpu/drm/xe/xe_device.h
@@ -162,6 +162,7 @@ u64 xe_device_canonicalize_addr(struct xe_device *xe, u64 address);
u64 xe_device_uncanonicalize_addr(struct xe_device *xe, u64 address);
void xe_device_td_flush(struct xe_device *xe);
+void xe_device_l2_flush(struct xe_device *xe);
static inline bool xe_device_wedged(struct xe_device *xe)
{
@@ -170,4 +171,7 @@ static inline bool xe_device_wedged(struct xe_device *xe)
void xe_device_declare_wedged(struct xe_device *xe);
+struct xe_file *xe_file_get(struct xe_file *xef);
+void xe_file_put(struct xe_file *xef);
+
#endif
diff --git a/drivers/gpu/drm/xe/xe_device_types.h b/drivers/gpu/drm/xe/xe_device_types.h
index 3bca6d344744..cbc582bcc90a 100644
--- a/drivers/gpu/drm/xe/xe_device_types.h
+++ b/drivers/gpu/drm/xe/xe_device_types.h
@@ -566,6 +566,9 @@ struct xe_file {
/** @client: drm client */
struct xe_drm_client *client;
+
+ /** @refcount: ref count of this xe file */
+ struct kref refcount;
};
#endif
diff --git a/drivers/gpu/drm/xe/xe_drm_client.c b/drivers/gpu/drm/xe/xe_drm_client.c
index 6a26923fa10e..7ddd59908334 100644
--- a/drivers/gpu/drm/xe/xe_drm_client.c
+++ b/drivers/gpu/drm/xe/xe_drm_client.c
@@ -251,11 +251,8 @@ static void show_run_ticks(struct drm_printer *p, struct drm_file *file)
/* Accumulate all the exec queues from this client */
mutex_lock(&xef->exec_queue.lock);
- xa_for_each(&xef->exec_queue.xa, i, q) {
+ xa_for_each(&xef->exec_queue.xa, i, q)
xe_exec_queue_update_run_ticks(q);
- xef->run_ticks[q->class] += q->run_ticks - q->old_run_ticks;
- q->old_run_ticks = q->run_ticks;
- }
mutex_unlock(&xef->exec_queue.lock);
/* Get the total GPU cycles */
diff --git a/drivers/gpu/drm/xe/xe_exec_queue.c b/drivers/gpu/drm/xe/xe_exec_queue.c
index 0ba37835849b..9731dcd0b1bd 100644
--- a/drivers/gpu/drm/xe/xe_exec_queue.c
+++ b/drivers/gpu/drm/xe/xe_exec_queue.c
@@ -37,6 +37,10 @@ static void __xe_exec_queue_free(struct xe_exec_queue *q)
{
if (q->vm)
xe_vm_put(q->vm);
+
+ if (q->xef)
+ xe_file_put(q->xef);
+
kfree(q);
}
@@ -101,22 +105,35 @@ static struct xe_exec_queue *__xe_exec_queue_alloc(struct xe_device *xe,
static int __xe_exec_queue_init(struct xe_exec_queue *q)
{
+ struct xe_vm *vm = q->vm;
int i, err;
+ if (vm) {
+ err = xe_vm_lock(vm, true);
+ if (err)
+ return err;
+ }
+
for (i = 0; i < q->width; ++i) {
q->lrc[i] = xe_lrc_create(q->hwe, q->vm, SZ_16K);
if (IS_ERR(q->lrc[i])) {
err = PTR_ERR(q->lrc[i]);
- goto err_lrc;
+ goto err_unlock;
}
}
+ if (vm)
+ xe_vm_unlock(vm);
+
err = q->ops->init(q);
if (err)
goto err_lrc;
return 0;
+err_unlock:
+ if (vm)
+ xe_vm_unlock(vm);
err_lrc:
for (i = i - 1; i >= 0; --i)
xe_lrc_put(q->lrc[i]);
@@ -136,15 +153,7 @@ struct xe_exec_queue *xe_exec_queue_create(struct xe_device *xe, struct xe_vm *v
if (IS_ERR(q))
return q;
- if (vm) {
- err = xe_vm_lock(vm, true);
- if (err)
- goto err_post_alloc;
- }
-
err = __xe_exec_queue_init(q);
- if (vm)
- xe_vm_unlock(vm);
if (err)
goto err_post_alloc;
@@ -634,7 +643,6 @@ int xe_exec_queue_create_ioctl(struct drm_device *dev, void *data,
if (xe_vm_in_preempt_fence_mode(vm)) {
q->lr.context = dma_fence_context_alloc(1);
- spin_lock_init(&q->lr.lock);
err = xe_vm_add_compute_exec_queue(vm, q);
if (XE_IOCTL_DBG(xe, err))
@@ -649,6 +657,7 @@ int xe_exec_queue_create_ioctl(struct drm_device *dev, void *data,
goto kill_exec_queue;
args->exec_queue_id = id;
+ q->xef = xe_file_get(xef);
return 0;
@@ -762,6 +771,7 @@ bool xe_exec_queue_is_idle(struct xe_exec_queue *q)
*/
void xe_exec_queue_update_run_ticks(struct xe_exec_queue *q)
{
+ struct xe_file *xef;
struct xe_lrc *lrc;
u32 old_ts, new_ts;
@@ -773,6 +783,8 @@ void xe_exec_queue_update_run_ticks(struct xe_exec_queue *q)
if (!q->vm || !q->vm->xef)
return;
+ xef = q->vm->xef;
+
/*
* Only sample the first LRC. For parallel submission, all of them are
* scheduled together and we compensate that below by multiplying by
@@ -783,7 +795,7 @@ void xe_exec_queue_update_run_ticks(struct xe_exec_queue *q)
*/
lrc = q->lrc[0];
new_ts = xe_lrc_update_timestamp(lrc, &old_ts);
- q->run_ticks += (new_ts - old_ts) * q->width;
+ xef->run_ticks[q->class] += (new_ts - old_ts) * q->width;
}
void xe_exec_queue_kill(struct xe_exec_queue *q)
diff --git a/drivers/gpu/drm/xe/xe_exec_queue_types.h b/drivers/gpu/drm/xe/xe_exec_queue_types.h
index 201588ec33c3..f6ee0ae80fd6 100644
--- a/drivers/gpu/drm/xe/xe_exec_queue_types.h
+++ b/drivers/gpu/drm/xe/xe_exec_queue_types.h
@@ -38,6 +38,9 @@ enum xe_exec_queue_priority {
* a kernel object.
*/
struct xe_exec_queue {
+ /** @xef: Back pointer to xe file if this is user created exec queue */
+ struct xe_file *xef;
+
/** @gt: graphics tile this exec queue can submit to */
struct xe_gt *gt;
/**
@@ -123,8 +126,6 @@ struct xe_exec_queue {
u32 seqno;
/** @lr.link: link into VM's list of exec queues */
struct list_head link;
- /** @lr.lock: preemption fences lock */
- spinlock_t lock;
} lr;
/** @ops: submission backend exec queue operations */
@@ -139,10 +140,6 @@ struct xe_exec_queue {
* Protected by @vm's resv. Unused if @vm == NULL.
*/
u64 tlb_flush_seqno;
- /** @old_run_ticks: prior hw engine class run time in ticks for this exec queue */
- u64 old_run_ticks;
- /** @run_ticks: hw engine class run time in ticks for this exec queue */
- u64 run_ticks;
/** @lrc: logical ring context for this exec queue */
struct xe_lrc *lrc[];
};
diff --git a/drivers/gpu/drm/xe/xe_gsc.c b/drivers/gpu/drm/xe/xe_gsc.c
index f8239a13fa2b..2a612652bb13 100644
--- a/drivers/gpu/drm/xe/xe_gsc.c
+++ b/drivers/gpu/drm/xe/xe_gsc.c
@@ -260,7 +260,7 @@ static int gsc_upload_and_init(struct xe_gsc *gsc)
struct xe_tile *tile = gt_to_tile(gt);
int ret;
- if (XE_WA(gt, 14018094691)) {
+ if (XE_WA(tile->primary_gt, 14018094691)) {
ret = xe_force_wake_get(gt_to_fw(tile->primary_gt), XE_FORCEWAKE_ALL);
/*
@@ -278,7 +278,7 @@ static int gsc_upload_and_init(struct xe_gsc *gsc)
ret = gsc_upload(gsc);
- if (XE_WA(gt, 14018094691))
+ if (XE_WA(tile->primary_gt, 14018094691))
xe_force_wake_put(gt_to_fw(tile->primary_gt), XE_FORCEWAKE_ALL);
if (ret)
@@ -437,7 +437,7 @@ out:
return ret;
}
-static void free_resources(struct drm_device *drm, void *arg)
+static void free_resources(void *arg)
{
struct xe_gsc *gsc = arg;
@@ -501,7 +501,7 @@ int xe_gsc_init_post_hwconfig(struct xe_gsc *gsc)
gsc->q = q;
gsc->wq = wq;
- err = drmm_add_action_or_reset(&xe->drm, free_resources, gsc);
+ err = devm_add_action_or_reset(xe->drm.dev, free_resources, gsc);
if (err)
return err;
diff --git a/drivers/gpu/drm/xe/xe_gt.c b/drivers/gpu/drm/xe/xe_gt.c
index 31b2e64c70c6..b9bcbbe27705 100644
--- a/drivers/gpu/drm/xe/xe_gt.c
+++ b/drivers/gpu/drm/xe/xe_gt.c
@@ -11,6 +11,8 @@
#include <drm/xe_drm.h>
#include <generated/xe_wa_oob.h>
+#include <generated/xe_wa_oob.h>
+
#include "instructions/xe_gfxpipe_commands.h"
#include "instructions/xe_mi_commands.h"
#include "regs/xe_gt_regs.h"
@@ -95,6 +97,51 @@ void xe_gt_sanitize(struct xe_gt *gt)
gt->uc.guc.submission_state.enabled = false;
}
+static void xe_gt_enable_host_l2_vram(struct xe_gt *gt)
+{
+ u32 reg;
+ int err;
+
+ if (!XE_WA(gt, 16023588340))
+ return;
+
+ err = xe_force_wake_get(gt_to_fw(gt), XE_FW_GT);
+ if (WARN_ON(err))
+ return;
+
+ if (!xe_gt_is_media_type(gt)) {
+ xe_mmio_write32(gt, SCRATCH1LPFC, EN_L3_RW_CCS_CACHE_FLUSH);
+ reg = xe_mmio_read32(gt, XE2_GAMREQSTRM_CTRL);
+ reg |= CG_DIS_CNTLBUS;
+ xe_mmio_write32(gt, XE2_GAMREQSTRM_CTRL, reg);
+ }
+
+ xe_gt_mcr_multicast_write(gt, XEHPC_L3CLOS_MASK(3), 0x3);
+ xe_force_wake_put(gt_to_fw(gt), XE_FW_GT);
+}
+
+static void xe_gt_disable_host_l2_vram(struct xe_gt *gt)
+{
+ u32 reg;
+ int err;
+
+ if (!XE_WA(gt, 16023588340))
+ return;
+
+ if (xe_gt_is_media_type(gt))
+ return;
+
+ err = xe_force_wake_get(gt_to_fw(gt), XE_FW_GT);
+ if (WARN_ON(err))
+ return;
+
+ reg = xe_mmio_read32(gt, XE2_GAMREQSTRM_CTRL);
+ reg &= ~CG_DIS_CNTLBUS;
+ xe_mmio_write32(gt, XE2_GAMREQSTRM_CTRL, reg);
+
+ xe_force_wake_put(gt_to_fw(gt), XE_FW_GT);
+}
+
/**
* xe_gt_remove() - Clean up the GT structures before driver removal
* @gt: the GT object
@@ -111,6 +158,8 @@ void xe_gt_remove(struct xe_gt *gt)
for (i = 0; i < XE_ENGINE_CLASS_MAX; ++i)
xe_hw_fence_irq_finish(&gt->fence_irq[i]);
+
+ xe_gt_disable_host_l2_vram(gt);
}
static void gt_reset_worker(struct work_struct *w);
@@ -339,6 +388,7 @@ int xe_gt_init_early(struct xe_gt *gt)
xe_force_wake_init_gt(gt, gt_to_fw(gt));
xe_pcode_init(gt);
+ spin_lock_init(&gt->global_invl_lock);
return 0;
}
@@ -508,6 +558,7 @@ int xe_gt_init_hwconfig(struct xe_gt *gt)
xe_gt_mcr_init_early(gt);
xe_pat_init(gt);
+ xe_gt_enable_host_l2_vram(gt);
err = xe_uc_init(&gt->uc);
if (err)
@@ -643,6 +694,8 @@ static int do_gt_restart(struct xe_gt *gt)
xe_pat_init(gt);
+ xe_gt_enable_host_l2_vram(gt);
+
xe_gt_mcr_set_implicit_defaults(gt);
xe_reg_sr_apply_mmio(&gt->reg_sr, gt);
@@ -796,6 +849,8 @@ int xe_gt_suspend(struct xe_gt *gt)
xe_gt_idle_disable_pg(gt);
+ xe_gt_disable_host_l2_vram(gt);
+
XE_WARN_ON(xe_force_wake_put(gt_to_fw(gt), XE_FORCEWAKE_ALL));
xe_gt_dbg(gt, "suspended\n");
diff --git a/drivers/gpu/drm/xe/xe_gt_pagefault.c b/drivers/gpu/drm/xe/xe_gt_pagefault.c
index 9292d5468868..b2a7fa55bd18 100644
--- a/drivers/gpu/drm/xe/xe_gt_pagefault.c
+++ b/drivers/gpu/drm/xe/xe_gt_pagefault.c
@@ -382,6 +382,18 @@ static void pf_queue_work_func(struct work_struct *w)
static void acc_queue_work_func(struct work_struct *w);
+static void pagefault_fini(void *arg)
+{
+ struct xe_gt *gt = arg;
+ struct xe_device *xe = gt_to_xe(gt);
+
+ if (!xe->info.has_usm)
+ return;
+
+ destroy_workqueue(gt->usm.acc_wq);
+ destroy_workqueue(gt->usm.pf_wq);
+}
+
int xe_gt_pagefault_init(struct xe_gt *gt)
{
struct xe_device *xe = gt_to_xe(gt);
@@ -409,10 +421,12 @@ int xe_gt_pagefault_init(struct xe_gt *gt)
gt->usm.acc_wq = alloc_workqueue("xe_gt_access_counter_work_queue",
WQ_UNBOUND | WQ_HIGHPRI,
NUM_ACC_QUEUE);
- if (!gt->usm.acc_wq)
+ if (!gt->usm.acc_wq) {
+ destroy_workqueue(gt->usm.pf_wq);
return -ENOMEM;
+ }
- return 0;
+ return devm_add_action_or_reset(xe->drm.dev, pagefault_fini, gt);
}
void xe_gt_pagefault_reset(struct xe_gt *gt)
diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c b/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c
index 4699b7836001..b6f0a7299c03 100644
--- a/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c
+++ b/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c
@@ -1927,6 +1927,7 @@ static int pf_validate_vf_config(struct xe_gt *gt, unsigned int vfid)
{
struct xe_gt *primary_gt = gt_to_tile(gt)->primary_gt;
struct xe_device *xe = gt_to_xe(gt);
+ bool is_primary = !xe_gt_is_media_type(gt);
bool valid_ggtt, valid_ctxs, valid_dbs;
bool valid_any, valid_all;
@@ -1935,13 +1936,17 @@ static int pf_validate_vf_config(struct xe_gt *gt, unsigned int vfid)
valid_dbs = pf_get_vf_config_dbs(gt, vfid);
/* note that GuC doorbells are optional */
- valid_any = valid_ggtt || valid_ctxs || valid_dbs;
- valid_all = valid_ggtt && valid_ctxs;
+ valid_any = valid_ctxs || valid_dbs;
+ valid_all = valid_ctxs;
+
+ /* and GGTT/LMEM is configured on primary GT only */
+ valid_all = valid_all && valid_ggtt;
+ valid_any = valid_any || (valid_ggtt && is_primary);
if (IS_DGFX(xe)) {
bool valid_lmem = pf_get_vf_config_ggtt(primary_gt, vfid);
- valid_any = valid_any || valid_lmem;
+ valid_any = valid_any || (valid_lmem && is_primary);
valid_all = valid_all && valid_lmem;
}
diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_vf.c b/drivers/gpu/drm/xe/xe_gt_sriov_vf.c
index 41e46a00c01e..8892d6c2291e 100644
--- a/drivers/gpu/drm/xe/xe_gt_sriov_vf.c
+++ b/drivers/gpu/drm/xe/xe_gt_sriov_vf.c
@@ -850,7 +850,7 @@ static struct vf_runtime_reg *vf_lookup_reg(struct xe_gt *gt, u32 addr)
xe_gt_assert(gt, IS_SRIOV_VF(gt_to_xe(gt)));
- return bsearch(&key, runtime->regs, runtime->regs_size, sizeof(key),
+ return bsearch(&key, runtime->regs, runtime->num_regs, sizeof(key),
vf_runtime_reg_cmp);
}
diff --git a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c
index d9359976ab8b..481d83d07367 100644
--- a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c
+++ b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c
@@ -13,10 +13,13 @@
#include "xe_guc.h"
#include "xe_guc_ct.h"
#include "xe_mmio.h"
+#include "xe_pm.h"
#include "xe_sriov.h"
#include "xe_trace.h"
#include "regs/xe_guc_regs.h"
+#define FENCE_STACK_BIT DMA_FENCE_FLAG_USER_BITS
+
/*
* TLB inval depends on pending commands in the CT queue and then the real
* invalidation time. Double up the time to process full CT queue
@@ -33,6 +36,24 @@ static long tlb_timeout_jiffies(struct xe_gt *gt)
return hw_tlb_timeout + 2 * delay;
}
+static void
+__invalidation_fence_signal(struct xe_device *xe, struct xe_gt_tlb_invalidation_fence *fence)
+{
+ bool stack = test_bit(FENCE_STACK_BIT, &fence->base.flags);
+
+ trace_xe_gt_tlb_invalidation_fence_signal(xe, fence);
+ xe_gt_tlb_invalidation_fence_fini(fence);
+ dma_fence_signal(&fence->base);
+ if (!stack)
+ dma_fence_put(&fence->base);
+}
+
+static void
+invalidation_fence_signal(struct xe_device *xe, struct xe_gt_tlb_invalidation_fence *fence)
+{
+ list_del(&fence->link);
+ __invalidation_fence_signal(xe, fence);
+}
static void xe_gt_tlb_fence_timeout(struct work_struct *work)
{
@@ -54,10 +75,8 @@ static void xe_gt_tlb_fence_timeout(struct work_struct *work)
xe_gt_err(gt, "TLB invalidation fence timeout, seqno=%d recv=%d",
fence->seqno, gt->tlb_invalidation.seqno_recv);
- list_del(&fence->link);
fence->base.error = -ETIME;
- dma_fence_signal(&fence->base);
- dma_fence_put(&fence->base);
+ invalidation_fence_signal(xe, fence);
}
if (!list_empty(&gt->tlb_invalidation.pending_fences))
queue_delayed_work(system_wq,
@@ -87,21 +106,6 @@ int xe_gt_tlb_invalidation_init(struct xe_gt *gt)
return 0;
}
-static void
-__invalidation_fence_signal(struct xe_device *xe, struct xe_gt_tlb_invalidation_fence *fence)
-{
- trace_xe_gt_tlb_invalidation_fence_signal(xe, fence);
- dma_fence_signal(&fence->base);
- dma_fence_put(&fence->base);
-}
-
-static void
-invalidation_fence_signal(struct xe_device *xe, struct xe_gt_tlb_invalidation_fence *fence)
-{
- list_del(&fence->link);
- __invalidation_fence_signal(xe, fence);
-}
-
/**
* xe_gt_tlb_invalidation_reset - Initialize GT TLB invalidation reset
* @gt: graphics tile
@@ -111,7 +115,6 @@ invalidation_fence_signal(struct xe_device *xe, struct xe_gt_tlb_invalidation_fe
void xe_gt_tlb_invalidation_reset(struct xe_gt *gt)
{
struct xe_gt_tlb_invalidation_fence *fence, *next;
- struct xe_guc *guc = &gt->uc.guc;
int pending_seqno;
/*
@@ -134,7 +137,6 @@ void xe_gt_tlb_invalidation_reset(struct xe_gt *gt)
else
pending_seqno = gt->tlb_invalidation.seqno - 1;
WRITE_ONCE(gt->tlb_invalidation.seqno_recv, pending_seqno);
- wake_up_all(&guc->ct.wq);
list_for_each_entry_safe(fence, next,
&gt->tlb_invalidation.pending_fences, link)
@@ -165,6 +167,8 @@ static int send_tlb_invalidation(struct xe_guc *guc,
int seqno;
int ret;
+ xe_gt_assert(gt, fence);
+
/*
* XXX: The seqno algorithm relies on TLB invalidation being processed
* in order which they currently are, if that changes the algorithm will
@@ -173,10 +177,8 @@ static int send_tlb_invalidation(struct xe_guc *guc,
mutex_lock(&guc->ct.lock);
seqno = gt->tlb_invalidation.seqno;
- if (fence) {
- fence->seqno = seqno;
- trace_xe_gt_tlb_invalidation_fence_send(xe, fence);
- }
+ fence->seqno = seqno;
+ trace_xe_gt_tlb_invalidation_fence_send(xe, fence);
action[1] = seqno;
ret = xe_guc_ct_send_locked(&guc->ct, action, len,
G2H_LEN_DW_TLB_INVALIDATE, 1);
@@ -209,7 +211,6 @@ static int send_tlb_invalidation(struct xe_guc *guc,
TLB_INVALIDATION_SEQNO_MAX;
if (!gt->tlb_invalidation.seqno)
gt->tlb_invalidation.seqno = 1;
- ret = seqno;
}
mutex_unlock(&guc->ct.lock);
@@ -223,14 +224,16 @@ static int send_tlb_invalidation(struct xe_guc *guc,
/**
* xe_gt_tlb_invalidation_guc - Issue a TLB invalidation on this GT for the GuC
* @gt: graphics tile
+ * @fence: invalidation fence which will be signal on TLB invalidation
+ * completion
*
* Issue a TLB invalidation for the GuC. Completion of TLB is asynchronous and
- * caller can use seqno + xe_gt_tlb_invalidation_wait to wait for completion.
+ * caller can use the invalidation fence to wait for completion.
*
- * Return: Seqno which can be passed to xe_gt_tlb_invalidation_wait on success,
- * negative error code on error.
+ * Return: 0 on success, negative error code on error
*/
-static int xe_gt_tlb_invalidation_guc(struct xe_gt *gt)
+static int xe_gt_tlb_invalidation_guc(struct xe_gt *gt,
+ struct xe_gt_tlb_invalidation_fence *fence)
{
u32 action[] = {
XE_GUC_ACTION_TLB_INVALIDATION,
@@ -238,7 +241,7 @@ static int xe_gt_tlb_invalidation_guc(struct xe_gt *gt)
MAKE_INVAL_OP(XE_GUC_TLB_INVAL_GUC),
};
- return send_tlb_invalidation(&gt->uc.guc, NULL, action,
+ return send_tlb_invalidation(&gt->uc.guc, fence, action,
ARRAY_SIZE(action));
}
@@ -257,13 +260,17 @@ int xe_gt_tlb_invalidation_ggtt(struct xe_gt *gt)
if (xe_guc_ct_enabled(&gt->uc.guc.ct) &&
gt->uc.guc.submission_state.enabled) {
- int seqno;
-
- seqno = xe_gt_tlb_invalidation_guc(gt);
- if (seqno <= 0)
- return seqno;
+ struct xe_gt_tlb_invalidation_fence fence;
+ int ret;
+
+ xe_gt_tlb_invalidation_fence_init(gt, &fence, true);
+ ret = xe_gt_tlb_invalidation_guc(gt, &fence);
+ if (ret < 0) {
+ xe_gt_tlb_invalidation_fence_fini(&fence);
+ return ret;
+ }
- xe_gt_tlb_invalidation_wait(gt, seqno);
+ xe_gt_tlb_invalidation_fence_wait(&fence);
} else if (xe_device_uc_enabled(xe) && !xe_device_wedged(xe)) {
if (IS_SRIOV_VF(xe))
return 0;
@@ -290,18 +297,16 @@ int xe_gt_tlb_invalidation_ggtt(struct xe_gt *gt)
*
* @gt: graphics tile
* @fence: invalidation fence which will be signal on TLB invalidation
- * completion, can be NULL
+ * completion
* @start: start address
* @end: end address
* @asid: address space id
*
* Issue a range based TLB invalidation if supported, if not fallback to a full
- * TLB invalidation. Completion of TLB is asynchronous and caller can either use
- * the invalidation fence or seqno + xe_gt_tlb_invalidation_wait to wait for
- * completion.
+ * TLB invalidation. Completion of TLB is asynchronous and caller can use
+ * the invalidation fence to wait for completion.
*
- * Return: Seqno which can be passed to xe_gt_tlb_invalidation_wait on success,
- * negative error code on error.
+ * Return: Negative error code on error, 0 on success
*/
int xe_gt_tlb_invalidation_range(struct xe_gt *gt,
struct xe_gt_tlb_invalidation_fence *fence,
@@ -312,11 +317,11 @@ int xe_gt_tlb_invalidation_range(struct xe_gt *gt,
u32 action[MAX_TLB_INVALIDATION_LEN];
int len = 0;
+ xe_gt_assert(gt, fence);
+
/* Execlists not supported */
if (gt_to_xe(gt)->info.force_execlist) {
- if (fence)
- __invalidation_fence_signal(xe, fence);
-
+ __invalidation_fence_signal(xe, fence);
return 0;
}
@@ -382,12 +387,10 @@ int xe_gt_tlb_invalidation_range(struct xe_gt *gt,
* @vma: VMA to invalidate
*
* Issue a range based TLB invalidation if supported, if not fallback to a full
- * TLB invalidation. Completion of TLB is asynchronous and caller can either use
- * the invalidation fence or seqno + xe_gt_tlb_invalidation_wait to wait for
- * completion.
+ * TLB invalidation. Completion of TLB is asynchronous and caller can use
+ * the invalidation fence to wait for completion.
*
- * Return: Seqno which can be passed to xe_gt_tlb_invalidation_wait on success,
- * negative error code on error.
+ * Return: Negative error code on error, 0 on success
*/
int xe_gt_tlb_invalidation_vma(struct xe_gt *gt,
struct xe_gt_tlb_invalidation_fence *fence,
@@ -401,43 +404,6 @@ int xe_gt_tlb_invalidation_vma(struct xe_gt *gt,
}
/**
- * xe_gt_tlb_invalidation_wait - Wait for TLB to complete
- * @gt: graphics tile
- * @seqno: seqno to wait which was returned from xe_gt_tlb_invalidation
- *
- * Wait for tlb_timeout_jiffies() for a TLB invalidation to complete.
- *
- * Return: 0 on success, -ETIME on TLB invalidation timeout
- */
-int xe_gt_tlb_invalidation_wait(struct xe_gt *gt, int seqno)
-{
- struct xe_guc *guc = &gt->uc.guc;
- int ret;
-
- /* Execlists not supported */
- if (gt_to_xe(gt)->info.force_execlist)
- return 0;
-
- /*
- * XXX: See above, this algorithm only works if seqno are always in
- * order
- */
- ret = wait_event_timeout(guc->ct.wq,
- tlb_invalidation_seqno_past(gt, seqno),
- tlb_timeout_jiffies(gt));
- if (!ret) {
- struct drm_printer p = xe_gt_err_printer(gt);
-
- xe_gt_err(gt, "TLB invalidation time'd out, seqno=%d, recv=%d\n",
- seqno, gt->tlb_invalidation.seqno_recv);
- xe_guc_ct_print(&guc->ct, &p, true);
- return -ETIME;
- }
-
- return 0;
-}
-
-/**
* xe_guc_tlb_invalidation_done_handler - TLB invalidation done handler
* @guc: guc
* @msg: message indicating TLB invalidation done
@@ -480,12 +446,7 @@ int xe_guc_tlb_invalidation_done_handler(struct xe_guc *guc, u32 *msg, u32 len)
return 0;
}
- /*
- * wake_up_all() and wait_event_timeout() already have the correct
- * barriers.
- */
WRITE_ONCE(gt->tlb_invalidation.seqno_recv, msg[0]);
- wake_up_all(&guc->ct.wq);
list_for_each_entry_safe(fence, next,
&gt->tlb_invalidation.pending_fences, link) {
@@ -508,3 +469,59 @@ int xe_guc_tlb_invalidation_done_handler(struct xe_guc *guc, u32 *msg, u32 len)
return 0;
}
+
+static const char *
+invalidation_fence_get_driver_name(struct dma_fence *dma_fence)
+{
+ return "xe";
+}
+
+static const char *
+invalidation_fence_get_timeline_name(struct dma_fence *dma_fence)
+{
+ return "invalidation_fence";
+}
+
+static const struct dma_fence_ops invalidation_fence_ops = {
+ .get_driver_name = invalidation_fence_get_driver_name,
+ .get_timeline_name = invalidation_fence_get_timeline_name,
+};
+
+/**
+ * xe_gt_tlb_invalidation_fence_init - Initialize TLB invalidation fence
+ * @gt: GT
+ * @fence: TLB invalidation fence to initialize
+ * @stack: fence is stack variable
+ *
+ * Initialize TLB invalidation fence for use. xe_gt_tlb_invalidation_fence_fini
+ * must be called if fence is not signaled.
+ */
+void xe_gt_tlb_invalidation_fence_init(struct xe_gt *gt,
+ struct xe_gt_tlb_invalidation_fence *fence,
+ bool stack)
+{
+ xe_pm_runtime_get_noresume(gt_to_xe(gt));
+
+ spin_lock_irq(&gt->tlb_invalidation.lock);
+ dma_fence_init(&fence->base, &invalidation_fence_ops,
+ &gt->tlb_invalidation.lock,
+ dma_fence_context_alloc(1), 1);
+ spin_unlock_irq(&gt->tlb_invalidation.lock);
+ INIT_LIST_HEAD(&fence->link);
+ if (stack)
+ set_bit(FENCE_STACK_BIT, &fence->base.flags);
+ else
+ dma_fence_get(&fence->base);
+ fence->gt = gt;
+}
+
+/**
+ * xe_gt_tlb_invalidation_fence_fini - Finalize TLB invalidation fence
+ * @fence: TLB invalidation fence to finalize
+ *
+ * Drop PM ref which fence took durinig init.
+ */
+void xe_gt_tlb_invalidation_fence_fini(struct xe_gt_tlb_invalidation_fence *fence)
+{
+ xe_pm_runtime_put(gt_to_xe(fence->gt));
+}
diff --git a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h
index bf3bebd9f985..a84065fa324c 100644
--- a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h
+++ b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h
@@ -23,7 +23,17 @@ int xe_gt_tlb_invalidation_vma(struct xe_gt *gt,
int xe_gt_tlb_invalidation_range(struct xe_gt *gt,
struct xe_gt_tlb_invalidation_fence *fence,
u64 start, u64 end, u32 asid);
-int xe_gt_tlb_invalidation_wait(struct xe_gt *gt, int seqno);
int xe_guc_tlb_invalidation_done_handler(struct xe_guc *guc, u32 *msg, u32 len);
+void xe_gt_tlb_invalidation_fence_init(struct xe_gt *gt,
+ struct xe_gt_tlb_invalidation_fence *fence,
+ bool stack);
+void xe_gt_tlb_invalidation_fence_fini(struct xe_gt_tlb_invalidation_fence *fence);
+
+static inline void
+xe_gt_tlb_invalidation_fence_wait(struct xe_gt_tlb_invalidation_fence *fence)
+{
+ dma_fence_wait(&fence->base, false);
+}
+
#endif /* _XE_GT_TLB_INVALIDATION_ */
diff --git a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation_types.h b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation_types.h
index 934c828efe31..de6e825e0851 100644
--- a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation_types.h
+++ b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation_types.h
@@ -8,6 +8,8 @@
#include <linux/dma-fence.h>
+struct xe_gt;
+
/**
* struct xe_gt_tlb_invalidation_fence - XE GT TLB invalidation fence
*
@@ -17,6 +19,8 @@
struct xe_gt_tlb_invalidation_fence {
/** @base: dma fence base */
struct dma_fence base;
+ /** @gt: GT which fence belong to */
+ struct xe_gt *gt;
/** @link: link into list of pending tlb fences */
struct list_head link;
/** @seqno: seqno of TLB invalidation to signal fence one */
diff --git a/drivers/gpu/drm/xe/xe_gt_types.h b/drivers/gpu/drm/xe/xe_gt_types.h
index 6b5e0b45efb0..38a0d0e178c8 100644
--- a/drivers/gpu/drm/xe/xe_gt_types.h
+++ b/drivers/gpu/drm/xe/xe_gt_types.h
@@ -362,6 +362,12 @@ struct xe_gt {
*/
spinlock_t mcr_lock;
+ /**
+ * @global_invl_lock: protects the register for the duration
+ * of a global invalidation of l2 cache
+ */
+ spinlock_t global_invl_lock;
+
/** @wa_active: keep track of active workarounds */
struct {
/** @wa_active.gt: bitmap with active GT workarounds */
diff --git a/drivers/gpu/drm/xe/xe_guc_ct.c b/drivers/gpu/drm/xe/xe_guc_ct.c
index 7d2e937da1d8..64afc90ad2c5 100644
--- a/drivers/gpu/drm/xe/xe_guc_ct.c
+++ b/drivers/gpu/drm/xe/xe_guc_ct.c
@@ -327,6 +327,8 @@ static void xe_guc_ct_set_state(struct xe_guc_ct *ct,
xe_gt_assert(ct_to_gt(ct), ct->g2h_outstanding == 0 ||
state == XE_GUC_CT_STATE_STOPPED);
+ if (ct->g2h_outstanding)
+ xe_pm_runtime_put(ct_to_xe(ct));
ct->g2h_outstanding = 0;
ct->state = state;
@@ -495,10 +497,15 @@ static void h2g_reserve_space(struct xe_guc_ct *ct, u32 cmd_len)
static void __g2h_reserve_space(struct xe_guc_ct *ct, u32 g2h_len, u32 num_g2h)
{
xe_gt_assert(ct_to_gt(ct), g2h_len <= ct->ctbs.g2h.info.space);
+ xe_gt_assert(ct_to_gt(ct), (!g2h_len && !num_g2h) ||
+ (g2h_len && num_g2h));
if (g2h_len) {
lockdep_assert_held(&ct->fast_lock);
+ if (!ct->g2h_outstanding)
+ xe_pm_runtime_get_noresume(ct_to_xe(ct));
+
ct->ctbs.g2h.info.space -= g2h_len;
ct->g2h_outstanding += num_g2h;
}
@@ -511,7 +518,8 @@ static void __g2h_release_space(struct xe_guc_ct *ct, u32 g2h_len)
ct->ctbs.g2h.info.size - ct->ctbs.g2h.info.resv_space);
ct->ctbs.g2h.info.space += g2h_len;
- --ct->g2h_outstanding;
+ if (!--ct->g2h_outstanding)
+ xe_pm_runtime_put(ct_to_xe(ct));
}
static void g2h_release_space(struct xe_guc_ct *ct, u32 g2h_len)
diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c
index 8d7e7f4bbff7..77b0f0d8f729 100644
--- a/drivers/gpu/drm/xe/xe_guc_submit.c
+++ b/drivers/gpu/drm/xe/xe_guc_submit.c
@@ -284,7 +284,7 @@ static void guc_submit_fini(struct drm_device *drm, void *arg)
free_submit_wq(guc);
}
-static void guc_submit_wedged_fini(struct drm_device *drm, void *arg)
+static void guc_submit_wedged_fini(void *arg)
{
struct xe_guc *guc = arg;
struct xe_exec_queue *q;
@@ -877,7 +877,7 @@ void xe_guc_submit_wedge(struct xe_guc *guc)
xe_gt_assert(guc_to_gt(guc), guc_to_xe(guc)->wedged.mode);
- err = drmm_add_action_or_reset(&guc_to_xe(guc)->drm,
+ err = devm_add_action_or_reset(guc_to_xe(guc)->drm.dev,
guc_submit_wedged_fini, guc);
if (err) {
drm_err(&xe->drm, "Failed to register xe_guc_submit clean-up on wedged.mode=2. Although device is wedged.\n");
@@ -1393,6 +1393,8 @@ static void guc_exec_queue_process_msg(struct xe_sched_msg *msg)
default:
XE_WARN_ON("Unknown message type");
}
+
+ xe_pm_runtime_put(guc_to_xe(exec_queue_to_guc(msg->private_data)));
}
static const struct drm_sched_backend_ops drm_sched_ops = {
@@ -1482,6 +1484,8 @@ static void guc_exec_queue_kill(struct xe_exec_queue *q)
static void guc_exec_queue_add_msg(struct xe_exec_queue *q, struct xe_sched_msg *msg,
u32 opcode)
{
+ xe_pm_runtime_get_noresume(guc_to_xe(exec_queue_to_guc(q)));
+
INIT_LIST_HEAD(&msg->link);
msg->opcode = opcode;
msg->private_data = q;
diff --git a/drivers/gpu/drm/xe/xe_hw_fence.c b/drivers/gpu/drm/xe/xe_hw_fence.c
index 45a9789cf501..0b4f12be3692 100644
--- a/drivers/gpu/drm/xe/xe_hw_fence.c
+++ b/drivers/gpu/drm/xe/xe_hw_fence.c
@@ -148,20 +148,20 @@ static const char *xe_hw_fence_get_driver_name(struct dma_fence *dma_fence)
{
struct xe_hw_fence *fence = to_xe_hw_fence(dma_fence);
- return dev_name(gt_to_xe(fence->ctx->gt)->drm.dev);
+ return dev_name(fence->xe->drm.dev);
}
static const char *xe_hw_fence_get_timeline_name(struct dma_fence *dma_fence)
{
struct xe_hw_fence *fence = to_xe_hw_fence(dma_fence);
- return fence->ctx->name;
+ return fence->name;
}
static bool xe_hw_fence_signaled(struct dma_fence *dma_fence)
{
struct xe_hw_fence *fence = to_xe_hw_fence(dma_fence);
- struct xe_device *xe = gt_to_xe(fence->ctx->gt);
+ struct xe_device *xe = fence->xe;
u32 seqno = xe_map_rd(xe, &fence->seqno_map, 0, u32);
return dma_fence->error ||
@@ -253,7 +253,8 @@ void xe_hw_fence_init(struct dma_fence *fence, struct xe_hw_fence_ctx *ctx,
struct xe_hw_fence *hw_fence =
container_of(fence, typeof(*hw_fence), dma);
- hw_fence->ctx = ctx;
+ hw_fence->xe = gt_to_xe(ctx->gt);
+ snprintf(hw_fence->name, sizeof(hw_fence->name), "%s", ctx->name);
hw_fence->seqno_map = seqno_map;
INIT_LIST_HEAD(&hw_fence->irq_link);
diff --git a/drivers/gpu/drm/xe/xe_hw_fence_types.h b/drivers/gpu/drm/xe/xe_hw_fence_types.h
index b33c4956e8ea..364a61f4bfda 100644
--- a/drivers/gpu/drm/xe/xe_hw_fence_types.h
+++ b/drivers/gpu/drm/xe/xe_hw_fence_types.h
@@ -12,6 +12,7 @@
#include <linux/list.h>
#include <linux/spinlock.h>
+struct xe_device;
struct xe_gt;
/**
@@ -61,8 +62,10 @@ struct xe_hw_fence_ctx {
struct xe_hw_fence {
/** @dma: base dma fence for hardware fence context */
struct dma_fence dma;
- /** @ctx: hardware fence context */
- struct xe_hw_fence_ctx *ctx;
+ /** @xe: Xe device for hw fence driver name */
+ struct xe_device *xe;
+ /** @name: name of hardware fence context */
+ char name[MAX_FENCE_NAME_LEN];
/** @seqno_map: I/O map for seqno */
struct iosys_map seqno_map;
/** @irq_link: Link in struct xe_hw_fence_irq.pending */
diff --git a/drivers/gpu/drm/xe/xe_hwmon.c b/drivers/gpu/drm/xe/xe_hwmon.c
index 0c8ce09e5025..1faeca70900e 100644
--- a/drivers/gpu/drm/xe/xe_hwmon.c
+++ b/drivers/gpu/drm/xe/xe_hwmon.c
@@ -203,9 +203,10 @@ static int xe_hwmon_power_max_write(struct xe_hwmon *hwmon, int channel, long va
reg_val = xe_mmio_rmw32(hwmon->gt, rapl_limit, PKG_PWR_LIM_1_EN, 0);
reg_val = xe_mmio_read32(hwmon->gt, rapl_limit);
if (reg_val & PKG_PWR_LIM_1_EN) {
+ drm_warn(&gt_to_xe(hwmon->gt)->drm, "PL1 disable is not supported!\n");
ret = -EOPNOTSUPP;
- goto unlock;
}
+ goto unlock;
}
/* Computation in 64-bits to avoid overflow. Round to nearest. */
@@ -449,7 +450,7 @@ static int xe_hwmon_pcode_write_i1(struct xe_gt *gt, u32 uval)
{
return xe_pcode_write(gt, PCODE_MBOX(PCODE_POWER_SETUP,
POWER_SETUP_SUBCOMMAND_WRITE_I1, 0),
- uval);
+ (uval & POWER_SETUP_I1_DATA_MASK));
}
static int xe_hwmon_power_curr_crit_read(struct xe_hwmon *hwmon, int channel,
diff --git a/drivers/gpu/drm/xe/xe_lrc.c b/drivers/gpu/drm/xe/xe_lrc.c
index 94ff62e1d95e..58121821f081 100644
--- a/drivers/gpu/drm/xe/xe_lrc.c
+++ b/drivers/gpu/drm/xe/xe_lrc.c
@@ -1634,6 +1634,9 @@ struct xe_lrc_snapshot *xe_lrc_snapshot_capture(struct xe_lrc *lrc)
if (!snapshot)
return NULL;
+ if (lrc->bo && lrc->bo->vm)
+ xe_vm_get(lrc->bo->vm);
+
snapshot->context_desc = xe_lrc_ggtt_addr(lrc);
snapshot->indirect_context_desc = xe_lrc_indirect_ring_ggtt_addr(lrc);
snapshot->head = xe_lrc_ring_head(lrc);
@@ -1653,12 +1656,14 @@ struct xe_lrc_snapshot *xe_lrc_snapshot_capture(struct xe_lrc *lrc)
void xe_lrc_snapshot_capture_delayed(struct xe_lrc_snapshot *snapshot)
{
struct xe_bo *bo;
+ struct xe_vm *vm;
struct iosys_map src;
if (!snapshot)
return;
bo = snapshot->lrc_bo;
+ vm = bo->vm;
snapshot->lrc_bo = NULL;
snapshot->lrc_snapshot = kvmalloc(snapshot->lrc_size, GFP_KERNEL);
@@ -1678,6 +1683,8 @@ void xe_lrc_snapshot_capture_delayed(struct xe_lrc_snapshot *snapshot)
xe_bo_unlock(bo);
put_bo:
xe_bo_put(bo);
+ if (vm)
+ xe_vm_put(vm);
}
void xe_lrc_snapshot_print(struct xe_lrc_snapshot *snapshot, struct drm_printer *p)
@@ -1727,8 +1734,14 @@ void xe_lrc_snapshot_free(struct xe_lrc_snapshot *snapshot)
return;
kvfree(snapshot->lrc_snapshot);
- if (snapshot->lrc_bo)
+ if (snapshot->lrc_bo) {
+ struct xe_vm *vm;
+
+ vm = snapshot->lrc_bo->vm;
xe_bo_put(snapshot->lrc_bo);
+ if (vm)
+ xe_vm_put(vm);
+ }
kfree(snapshot);
}
diff --git a/drivers/gpu/drm/xe/xe_mmio.c b/drivers/gpu/drm/xe/xe_mmio.c
index f92faad4b96d..aa68cac9fdf8 100644
--- a/drivers/gpu/drm/xe/xe_mmio.c
+++ b/drivers/gpu/drm/xe/xe_mmio.c
@@ -30,7 +30,8 @@ static void tiles_fini(void *arg)
int id;
for_each_tile(tile, xe, id)
- tile->mmio.regs = NULL;
+ if (tile != xe_device_get_root_tile(xe))
+ tile->mmio.regs = NULL;
}
int xe_mmio_probe_tiles(struct xe_device *xe)
@@ -91,9 +92,11 @@ add_mmio_ext:
static void mmio_fini(void *arg)
{
struct xe_device *xe = arg;
+ struct xe_tile *root_tile = xe_device_get_root_tile(xe);
pci_iounmap(to_pci_dev(xe->drm.dev), xe->mmio.regs);
xe->mmio.regs = NULL;
+ root_tile->mmio.regs = NULL;
}
int xe_mmio_init(struct xe_device *xe)
@@ -121,12 +124,29 @@ int xe_mmio_init(struct xe_device *xe)
return devm_add_action_or_reset(xe->drm.dev, mmio_fini, xe);
}
+static void mmio_flush_pending_writes(struct xe_gt *gt)
+{
+#define DUMMY_REG_OFFSET 0x130030
+ struct xe_tile *tile = gt_to_tile(gt);
+ int i;
+
+ if (tile->xe->info.platform != XE_LUNARLAKE)
+ return;
+
+ /* 4 dummy writes */
+ for (i = 0; i < 4; i++)
+ writel(0, tile->mmio.regs + DUMMY_REG_OFFSET);
+}
+
u8 xe_mmio_read8(struct xe_gt *gt, struct xe_reg reg)
{
struct xe_tile *tile = gt_to_tile(gt);
u32 addr = xe_mmio_adjusted_addr(gt, reg.addr);
u8 val;
+ /* Wa_15015404425 */
+ mmio_flush_pending_writes(gt);
+
val = readb((reg.ext ? tile->mmio_ext.regs : tile->mmio.regs) + addr);
trace_xe_reg_rw(gt, false, addr, val, sizeof(val));
@@ -139,6 +159,9 @@ u16 xe_mmio_read16(struct xe_gt *gt, struct xe_reg reg)
u32 addr = xe_mmio_adjusted_addr(gt, reg.addr);
u16 val;
+ /* Wa_15015404425 */
+ mmio_flush_pending_writes(gt);
+
val = readw((reg.ext ? tile->mmio_ext.regs : tile->mmio.regs) + addr);
trace_xe_reg_rw(gt, false, addr, val, sizeof(val));
@@ -160,6 +183,9 @@ u32 xe_mmio_read32(struct xe_gt *gt, struct xe_reg reg)
u32 addr = xe_mmio_adjusted_addr(gt, reg.addr);
u32 val;
+ /* Wa_15015404425 */
+ mmio_flush_pending_writes(gt);
+
if (!reg.vf && IS_SRIOV_VF(gt_to_xe(gt)))
val = xe_gt_sriov_vf_read32(gt, reg);
else
diff --git a/drivers/gpu/drm/xe/xe_observation.c b/drivers/gpu/drm/xe/xe_observation.c
index fcb584b42a7d..a78c92a44ec2 100644
--- a/drivers/gpu/drm/xe/xe_observation.c
+++ b/drivers/gpu/drm/xe/xe_observation.c
@@ -66,7 +66,6 @@ static struct ctl_table observation_ctl_table[] = {
.extra1 = SYSCTL_ZERO,
.extra2 = SYSCTL_ONE,
},
- {}
};
/**
diff --git a/drivers/gpu/drm/xe/xe_pat.c b/drivers/gpu/drm/xe/xe_pat.c
index 4ee32ee1cc88..722278cc23fc 100644
--- a/drivers/gpu/drm/xe/xe_pat.c
+++ b/drivers/gpu/drm/xe/xe_pat.c
@@ -7,6 +7,8 @@
#include <drm/xe_drm.h>
+#include <generated/xe_wa_oob.h>
+
#include "regs/xe_reg_defs.h"
#include "xe_assert.h"
#include "xe_device.h"
@@ -15,6 +17,7 @@
#include "xe_gt_mcr.h"
#include "xe_mmio.h"
#include "xe_sriov.h"
+#include "xe_wa.h"
#define _PAT_ATS 0x47fc
#define _PAT_INDEX(index) _PICK_EVEN_2RANGES(index, 8, \
@@ -382,7 +385,13 @@ void xe_pat_init_early(struct xe_device *xe)
if (GRAPHICS_VER(xe) == 20) {
xe->pat.ops = &xe2_pat_ops;
xe->pat.table = xe2_pat_table;
- xe->pat.n_entries = ARRAY_SIZE(xe2_pat_table);
+
+ /* Wa_16023588340. XXX: Should use XE_WA */
+ if (GRAPHICS_VERx100(xe) == 2001)
+ xe->pat.n_entries = 28; /* Disable CLOS3 */
+ else
+ xe->pat.n_entries = ARRAY_SIZE(xe2_pat_table);
+
xe->pat.idx[XE_CACHE_NONE] = 3;
xe->pat.idx[XE_CACHE_WT] = 15;
xe->pat.idx[XE_CACHE_WB] = 2;
diff --git a/drivers/gpu/drm/xe/xe_pm.c b/drivers/gpu/drm/xe/xe_pm.c
index de3b5df65e48..9a3f618d22dc 100644
--- a/drivers/gpu/drm/xe/xe_pm.c
+++ b/drivers/gpu/drm/xe/xe_pm.c
@@ -91,13 +91,13 @@ int xe_pm_suspend(struct xe_device *xe)
for_each_gt(gt, xe, id)
xe_gt_suspend_prepare(gt);
+ xe_display_pm_suspend(xe, false);
+
/* FIXME: Super racey... */
err = xe_bo_evict_all(xe);
if (err)
goto err;
- xe_display_pm_suspend(xe, false);
-
for_each_gt(gt, xe, id) {
err = xe_gt_suspend(gt);
if (err) {
@@ -151,11 +151,11 @@ int xe_pm_resume(struct xe_device *xe)
xe_irq_resume(xe);
- xe_display_pm_resume(xe, false);
-
for_each_gt(gt, xe, id)
xe_gt_resume(gt);
+ xe_display_pm_resume(xe, false);
+
err = xe_bo_restore_user(xe);
if (err)
goto err;
@@ -363,10 +363,11 @@ int xe_pm_runtime_suspend(struct xe_device *xe)
mutex_unlock(&xe->mem_access.vram_userfault.lock);
if (xe->d3cold.allowed) {
+ xe_display_pm_suspend(xe, true);
+
err = xe_bo_evict_all(xe);
if (err)
goto out;
- xe_display_pm_suspend(xe, true);
}
for_each_gt(gt, xe, id) {
diff --git a/drivers/gpu/drm/xe/xe_preempt_fence.c b/drivers/gpu/drm/xe/xe_preempt_fence.c
index e8b8ae5c6485..c453f45328b1 100644
--- a/drivers/gpu/drm/xe/xe_preempt_fence.c
+++ b/drivers/gpu/drm/xe/xe_preempt_fence.c
@@ -128,8 +128,9 @@ xe_preempt_fence_arm(struct xe_preempt_fence *pfence, struct xe_exec_queue *q,
{
list_del_init(&pfence->link);
pfence->q = xe_exec_queue_get(q);
+ spin_lock_init(&pfence->lock);
dma_fence_init(&pfence->base, &preempt_fence_ops,
- &q->lr.lock, context, seqno);
+ &pfence->lock, context, seqno);
return &pfence->base;
}
diff --git a/drivers/gpu/drm/xe/xe_preempt_fence_types.h b/drivers/gpu/drm/xe/xe_preempt_fence_types.h
index b54b5c29b533..312c3372a49f 100644
--- a/drivers/gpu/drm/xe/xe_preempt_fence_types.h
+++ b/drivers/gpu/drm/xe/xe_preempt_fence_types.h
@@ -25,6 +25,8 @@ struct xe_preempt_fence {
struct xe_exec_queue *q;
/** @preempt_work: work struct which issues preemption */
struct work_struct preempt_work;
+ /** @lock: dma-fence fence lock */
+ spinlock_t lock;
/** @error: preempt fence is in error state */
int error;
};
diff --git a/drivers/gpu/drm/xe/xe_pt.c b/drivers/gpu/drm/xe/xe_pt.c
index ade9e7a3a0ad..31a751a5de3f 100644
--- a/drivers/gpu/drm/xe/xe_pt.c
+++ b/drivers/gpu/drm/xe/xe_pt.c
@@ -1115,23 +1115,6 @@ struct invalidation_fence {
u32 asid;
};
-static const char *
-invalidation_fence_get_driver_name(struct dma_fence *dma_fence)
-{
- return "xe";
-}
-
-static const char *
-invalidation_fence_get_timeline_name(struct dma_fence *dma_fence)
-{
- return "invalidation_fence";
-}
-
-static const struct dma_fence_ops invalidation_fence_ops = {
- .get_driver_name = invalidation_fence_get_driver_name,
- .get_timeline_name = invalidation_fence_get_timeline_name,
-};
-
static void invalidation_fence_cb(struct dma_fence *fence,
struct dma_fence_cb *cb)
{
@@ -1170,15 +1153,8 @@ static int invalidation_fence_init(struct xe_gt *gt,
trace_xe_gt_tlb_invalidation_fence_create(gt_to_xe(gt), &ifence->base);
- spin_lock_irq(&gt->tlb_invalidation.lock);
- dma_fence_init(&ifence->base.base, &invalidation_fence_ops,
- &gt->tlb_invalidation.lock,
- dma_fence_context_alloc(1), 1);
- spin_unlock_irq(&gt->tlb_invalidation.lock);
-
- INIT_LIST_HEAD(&ifence->base.link);
+ xe_gt_tlb_invalidation_fence_init(gt, &ifence->base, false);
- dma_fence_get(&ifence->base.base); /* Ref for caller */
ifence->fence = fence;
ifence->gt = gt;
ifence->start = start;
diff --git a/drivers/gpu/drm/xe/xe_rtp.c b/drivers/gpu/drm/xe/xe_rtp.c
index 02e28274282f..5efe83cc82ab 100644
--- a/drivers/gpu/drm/xe/xe_rtp.c
+++ b/drivers/gpu/drm/xe/xe_rtp.c
@@ -231,7 +231,7 @@ static void rtp_mark_active(struct xe_device *xe,
if (first == last)
bitmap_set(ctx->active_entries, first, 1);
else
- bitmap_set(ctx->active_entries, first, last - first + 2);
+ bitmap_set(ctx->active_entries, first, last - first + 1);
}
/**
diff --git a/drivers/gpu/drm/xe/xe_sched_job.c b/drivers/gpu/drm/xe/xe_sched_job.c
index 44d534e362cd..9628f9deb3c0 100644
--- a/drivers/gpu/drm/xe/xe_sched_job.c
+++ b/drivers/gpu/drm/xe/xe_sched_job.c
@@ -171,12 +171,13 @@ void xe_sched_job_destroy(struct kref *ref)
struct xe_sched_job *job =
container_of(ref, struct xe_sched_job, refcount);
struct xe_device *xe = job_to_xe(job);
+ struct xe_exec_queue *q = job->q;
xe_sched_job_free_fences(job);
- xe_exec_queue_put(job->q);
dma_fence_put(job->fence);
drm_sched_job_cleanup(&job->drm);
job_free(job);
+ xe_exec_queue_put(q);
xe_pm_runtime_put(xe);
}
diff --git a/drivers/gpu/drm/xe/xe_sync.c b/drivers/gpu/drm/xe/xe_sync.c
index 2883d9aca404..e8d31e010860 100644
--- a/drivers/gpu/drm/xe/xe_sync.c
+++ b/drivers/gpu/drm/xe/xe_sync.c
@@ -53,14 +53,18 @@ static struct xe_user_fence *user_fence_create(struct xe_device *xe, u64 addr,
u64 value)
{
struct xe_user_fence *ufence;
+ u64 __user *ptr = u64_to_user_ptr(addr);
+
+ if (!access_ok(ptr, sizeof(ptr)))
+ return ERR_PTR(-EFAULT);
ufence = kmalloc(sizeof(*ufence), GFP_KERNEL);
if (!ufence)
- return NULL;
+ return ERR_PTR(-ENOMEM);
ufence->xe = xe;
kref_init(&ufence->refcount);
- ufence->addr = u64_to_user_ptr(addr);
+ ufence->addr = ptr;
ufence->value = value;
ufence->mm = current->mm;
mmgrab(ufence->mm);
@@ -183,8 +187,8 @@ int xe_sync_entry_parse(struct xe_device *xe, struct xe_file *xef,
} else {
sync->ufence = user_fence_create(xe, sync_in.addr,
sync_in.timeline_value);
- if (XE_IOCTL_DBG(xe, !sync->ufence))
- return -ENOMEM;
+ if (XE_IOCTL_DBG(xe, IS_ERR(sync->ufence)))
+ return PTR_ERR(sync->ufence);
}
break;
@@ -263,7 +267,7 @@ void xe_sync_entry_cleanup(struct xe_sync_entry *sync)
if (sync->fence)
dma_fence_put(sync->fence);
if (sync->chain_fence)
- dma_fence_put(&sync->chain_fence->base);
+ dma_fence_chain_free(sync->chain_fence);
if (sync->ufence)
user_fence_put(sync->ufence);
}
diff --git a/drivers/gpu/drm/xe/xe_trace.h b/drivers/gpu/drm/xe/xe_trace.h
index baba14fb1e32..01837f6f609f 100644
--- a/drivers/gpu/drm/xe/xe_trace.h
+++ b/drivers/gpu/drm/xe/xe_trace.h
@@ -309,7 +309,7 @@ DECLARE_EVENT_CLASS(xe_hw_fence,
TP_ARGS(fence),
TP_STRUCT__entry(
- __string(dev, __dev_name_gt(fence->ctx->gt))
+ __string(dev, __dev_name_xe(fence->xe))
__field(u64, ctx)
__field(u32, seqno)
__field(struct xe_hw_fence *, fence)
diff --git a/drivers/gpu/drm/xe/xe_ttm_vram_mgr.c b/drivers/gpu/drm/xe/xe_ttm_vram_mgr.c
index fe3779fdba2c..423b261ea743 100644
--- a/drivers/gpu/drm/xe/xe_ttm_vram_mgr.c
+++ b/drivers/gpu/drm/xe/xe_ttm_vram_mgr.c
@@ -150,7 +150,7 @@ static int xe_ttm_vram_mgr_new(struct ttm_resource_manager *man,
} while (remaining_size);
if (place->flags & TTM_PL_FLAG_CONTIGUOUS) {
- if (!drm_buddy_block_trim(mm, vres->base.size, &vres->blocks))
+ if (!drm_buddy_block_trim(mm, NULL, vres->base.size, &vres->blocks))
size = vres->base.size;
}
diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index 5b166fa03684..50e8fc49ba6c 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -1601,6 +1601,10 @@ static void vm_destroy_work_func(struct work_struct *w)
XE_WARN_ON(vm->pt_root[id]);
trace_xe_vm_free(vm);
+
+ if (vm->xef)
+ xe_file_put(vm->xef);
+
kfree(vm);
}
@@ -1916,7 +1920,7 @@ int xe_vm_create_ioctl(struct drm_device *dev, void *data,
}
args->vm_id = id;
- vm->xef = xef;
+ vm->xef = xe_file_get(xef);
/* Record BO memory for VM pagetable created against client */
for_each_tile(tile, xe, id)
@@ -3337,10 +3341,11 @@ int xe_vm_invalidate_vma(struct xe_vma *vma)
{
struct xe_device *xe = xe_vma_vm(vma)->xe;
struct xe_tile *tile;
- u32 tile_needs_invalidate = 0;
- int seqno[XE_MAX_TILES_PER_DEVICE];
+ struct xe_gt_tlb_invalidation_fence
+ fence[XE_MAX_TILES_PER_DEVICE * XE_MAX_GT_PER_TILE];
u8 id;
- int ret;
+ u32 fence_id = 0;
+ int ret = 0;
xe_assert(xe, !xe_vma_is_null(vma));
trace_xe_vma_invalidate(vma);
@@ -3365,29 +3370,43 @@ int xe_vm_invalidate_vma(struct xe_vma *vma)
for_each_tile(tile, xe, id) {
if (xe_pt_zap_ptes(tile, vma)) {
- tile_needs_invalidate |= BIT(id);
xe_device_wmb(xe);
- /*
- * FIXME: We potentially need to invalidate multiple
- * GTs within the tile
- */
- seqno[id] = xe_gt_tlb_invalidation_vma(tile->primary_gt, NULL, vma);
- if (seqno[id] < 0)
- return seqno[id];
- }
- }
+ xe_gt_tlb_invalidation_fence_init(tile->primary_gt,
+ &fence[fence_id],
+ true);
+
+ ret = xe_gt_tlb_invalidation_vma(tile->primary_gt,
+ &fence[fence_id], vma);
+ if (ret < 0) {
+ xe_gt_tlb_invalidation_fence_fini(&fence[fence_id]);
+ goto wait;
+ }
+ ++fence_id;
- for_each_tile(tile, xe, id) {
- if (tile_needs_invalidate & BIT(id)) {
- ret = xe_gt_tlb_invalidation_wait(tile->primary_gt, seqno[id]);
- if (ret < 0)
- return ret;
+ if (!tile->media_gt)
+ continue;
+
+ xe_gt_tlb_invalidation_fence_init(tile->media_gt,
+ &fence[fence_id],
+ true);
+
+ ret = xe_gt_tlb_invalidation_vma(tile->media_gt,
+ &fence[fence_id], vma);
+ if (ret < 0) {
+ xe_gt_tlb_invalidation_fence_fini(&fence[fence_id]);
+ goto wait;
+ }
+ ++fence_id;
}
}
+wait:
+ for (id = 0; id < fence_id; ++id)
+ xe_gt_tlb_invalidation_fence_wait(&fence[id]);
+
vma->tile_invalidated = vma->tile_mask;
- return 0;
+ return ret;
}
struct xe_vm_snapshot {
diff --git a/drivers/gpu/drm/xe/xe_wa.c b/drivers/gpu/drm/xe/xe_wa.c
index c7bf0862b231..e648265d081b 100644
--- a/drivers/gpu/drm/xe/xe_wa.c
+++ b/drivers/gpu/drm/xe/xe_wa.c
@@ -486,6 +486,10 @@ static const struct xe_rtp_entry_sr engine_was[] = {
XE_RTP_RULES(GRAPHICS_VERSION(2004), FUNC(xe_rtp_match_first_render_or_compute)),
XE_RTP_ACTIONS(SET(TDL_TSL_CHICKEN, SLM_WMTP_RESTORE))
},
+ { XE_RTP_NAME("14021402888"),
+ XE_RTP_RULES(GRAPHICS_VERSION(2004), ENGINE_CLASS(RENDER)),
+ XE_RTP_ACTIONS(SET(HALF_SLICE_CHICKEN7, CLEAR_OPTIMIZATION_DISABLE))
+ },
/* Xe2_HPG */
@@ -538,6 +542,20 @@ static const struct xe_rtp_entry_sr engine_was[] = {
XE_RTP_RULES(GRAPHICS_VERSION(2001), ENGINE_CLASS(RENDER)),
XE_RTP_ACTIONS(SET(HALF_SLICE_CHICKEN7, CLEAR_OPTIMIZATION_DISABLE))
},
+ { XE_RTP_NAME("14021821874"),
+ XE_RTP_RULES(GRAPHICS_VERSION(2001), FUNC(xe_rtp_match_first_render_or_compute)),
+ XE_RTP_ACTIONS(SET(TDL_TSL_CHICKEN, STK_ID_RESTRICT))
+ },
+
+ /* Xe2_LPM */
+
+ { XE_RTP_NAME("16021639441"),
+ XE_RTP_RULES(MEDIA_VERSION(2000)),
+ XE_RTP_ACTIONS(SET(CSFE_CHICKEN1(0),
+ GHWSP_CSB_REPORT_DIS |
+ PPHWSP_CSB_AND_TIMESTAMP_REPORT_DIS,
+ XE_RTP_ACTION_FLAG(ENGINE_BASE)))
+ },
/* Xe2_HPM */
diff --git a/drivers/gpu/drm/xe/xe_wa_oob.rules b/drivers/gpu/drm/xe/xe_wa_oob.rules
index 26066beb4f6f..08f7336881e3 100644
--- a/drivers/gpu/drm/xe/xe_wa_oob.rules
+++ b/drivers/gpu/drm/xe/xe_wa_oob.rules
@@ -29,3 +29,4 @@
13011645652 GRAPHICS_VERSION(2004)
22019338487 MEDIA_VERSION(2000)
GRAPHICS_VERSION(2001)
+16023588340 GRAPHICS_VERSION(2001)