summaryrefslogtreecommitdiffstats
path: root/drivers/gpu/drm/i915/intel_engine_cs.c
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/gpu/drm/i915/intel_engine_cs.c')
-rw-r--r--drivers/gpu/drm/i915/intel_engine_cs.c1323
1 files changed, 438 insertions, 885 deletions
diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c
index f7c25828d3bb..76b5f94ea6cb 100644
--- a/drivers/gpu/drm/i915/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/intel_engine_cs.c
@@ -25,7 +25,6 @@
#include <drm/drm_print.h>
#include "i915_drv.h"
-#include "i915_vgpu.h"
#include "intel_ringbuffer.h"
#include "intel_lrc.h"
@@ -81,13 +80,17 @@ static const struct engine_class_info intel_engine_classes[] = {
},
};
+#define MAX_MMIO_BASES 3
struct engine_info {
unsigned int hw_id;
unsigned int uabi_id;
u8 class;
u8 instance;
- u32 mmio_base;
- unsigned irq_shift;
+ /* mmio bases table *must* be sorted in reverse gen order */
+ struct engine_mmio_base {
+ u32 gen : 8;
+ u32 base : 24;
+ } mmio_bases[MAX_MMIO_BASES];
};
static const struct engine_info intel_engines[] = {
@@ -96,64 +99,76 @@ static const struct engine_info intel_engines[] = {
.uabi_id = I915_EXEC_RENDER,
.class = RENDER_CLASS,
.instance = 0,
- .mmio_base = RENDER_RING_BASE,
- .irq_shift = GEN8_RCS_IRQ_SHIFT,
+ .mmio_bases = {
+ { .gen = 1, .base = RENDER_RING_BASE }
+ },
},
[BCS] = {
.hw_id = BCS_HW,
.uabi_id = I915_EXEC_BLT,
.class = COPY_ENGINE_CLASS,
.instance = 0,
- .mmio_base = BLT_RING_BASE,
- .irq_shift = GEN8_BCS_IRQ_SHIFT,
+ .mmio_bases = {
+ { .gen = 6, .base = BLT_RING_BASE }
+ },
},
[VCS] = {
.hw_id = VCS_HW,
.uabi_id = I915_EXEC_BSD,
.class = VIDEO_DECODE_CLASS,
.instance = 0,
- .mmio_base = GEN6_BSD_RING_BASE,
- .irq_shift = GEN8_VCS1_IRQ_SHIFT,
+ .mmio_bases = {
+ { .gen = 11, .base = GEN11_BSD_RING_BASE },
+ { .gen = 6, .base = GEN6_BSD_RING_BASE },
+ { .gen = 4, .base = BSD_RING_BASE }
+ },
},
[VCS2] = {
.hw_id = VCS2_HW,
.uabi_id = I915_EXEC_BSD,
.class = VIDEO_DECODE_CLASS,
.instance = 1,
- .mmio_base = GEN8_BSD2_RING_BASE,
- .irq_shift = GEN8_VCS2_IRQ_SHIFT,
+ .mmio_bases = {
+ { .gen = 11, .base = GEN11_BSD2_RING_BASE },
+ { .gen = 8, .base = GEN8_BSD2_RING_BASE }
+ },
},
[VCS3] = {
.hw_id = VCS3_HW,
.uabi_id = I915_EXEC_BSD,
.class = VIDEO_DECODE_CLASS,
.instance = 2,
- .mmio_base = GEN11_BSD3_RING_BASE,
- .irq_shift = 0, /* not used */
+ .mmio_bases = {
+ { .gen = 11, .base = GEN11_BSD3_RING_BASE }
+ },
},
[VCS4] = {
.hw_id = VCS4_HW,
.uabi_id = I915_EXEC_BSD,
.class = VIDEO_DECODE_CLASS,
.instance = 3,
- .mmio_base = GEN11_BSD4_RING_BASE,
- .irq_shift = 0, /* not used */
+ .mmio_bases = {
+ { .gen = 11, .base = GEN11_BSD4_RING_BASE }
+ },
},
[VECS] = {
.hw_id = VECS_HW,
.uabi_id = I915_EXEC_VEBOX,
.class = VIDEO_ENHANCEMENT_CLASS,
.instance = 0,
- .mmio_base = VEBOX_RING_BASE,
- .irq_shift = GEN8_VECS_IRQ_SHIFT,
+ .mmio_bases = {
+ { .gen = 11, .base = GEN11_VEBOX_RING_BASE },
+ { .gen = 7, .base = VEBOX_RING_BASE }
+ },
},
[VECS2] = {
.hw_id = VECS2_HW,
.uabi_id = I915_EXEC_VEBOX,
.class = VIDEO_ENHANCEMENT_CLASS,
.instance = 1,
- .mmio_base = GEN11_VEBOX2_RING_BASE,
- .irq_shift = 0, /* not used */
+ .mmio_bases = {
+ { .gen = 11, .base = GEN11_VEBOX2_RING_BASE }
+ },
},
};
@@ -214,6 +229,7 @@ __intel_engine_context_size(struct drm_i915_private *dev_priv, u8 class)
break;
default:
MISSING_CASE(class);
+ /* fall through */
case VIDEO_DECODE_CLASS:
case VIDEO_ENHANCEMENT_CLASS:
case COPY_ENGINE_CLASS:
@@ -223,16 +239,36 @@ __intel_engine_context_size(struct drm_i915_private *dev_priv, u8 class)
}
}
+static u32 __engine_mmio_base(struct drm_i915_private *i915,
+ const struct engine_mmio_base *bases)
+{
+ int i;
+
+ for (i = 0; i < MAX_MMIO_BASES; i++)
+ if (INTEL_GEN(i915) >= bases[i].gen)
+ break;
+
+ GEM_BUG_ON(i == MAX_MMIO_BASES);
+ GEM_BUG_ON(!bases[i].base);
+
+ return bases[i].base;
+}
+
+static void __sprint_engine_name(char *name, const struct engine_info *info)
+{
+ WARN_ON(snprintf(name, INTEL_ENGINE_CS_MAX_NAME, "%s%u",
+ intel_engine_classes[info->class].name,
+ info->instance) >= INTEL_ENGINE_CS_MAX_NAME);
+}
+
static int
intel_engine_setup(struct drm_i915_private *dev_priv,
enum intel_engine_id id)
{
const struct engine_info *info = &intel_engines[id];
- const struct engine_class_info *class_info;
struct intel_engine_cs *engine;
GEM_BUG_ON(info->class >= ARRAY_SIZE(intel_engine_classes));
- class_info = &intel_engine_classes[info->class];
BUILD_BUG_ON(MAX_ENGINE_CLASS >= BIT(GEN11_ENGINE_CLASS_WIDTH));
BUILD_BUG_ON(MAX_ENGINE_INSTANCE >= BIT(GEN11_ENGINE_INSTANCE_WIDTH));
@@ -253,45 +289,26 @@ intel_engine_setup(struct drm_i915_private *dev_priv,
engine->id = id;
engine->i915 = dev_priv;
- WARN_ON(snprintf(engine->name, sizeof(engine->name), "%s%u",
- class_info->name, info->instance) >=
- sizeof(engine->name));
+ __sprint_engine_name(engine->name, info);
engine->hw_id = engine->guc_id = info->hw_id;
- if (INTEL_GEN(dev_priv) >= 11) {
- switch (engine->id) {
- case VCS:
- engine->mmio_base = GEN11_BSD_RING_BASE;
- break;
- case VCS2:
- engine->mmio_base = GEN11_BSD2_RING_BASE;
- break;
- case VECS:
- engine->mmio_base = GEN11_VEBOX_RING_BASE;
- break;
- default:
- /* take the original value for all other engines */
- engine->mmio_base = info->mmio_base;
- break;
- }
- } else {
- engine->mmio_base = info->mmio_base;
- }
- engine->irq_shift = info->irq_shift;
+ engine->mmio_base = __engine_mmio_base(dev_priv, info->mmio_bases);
engine->class = info->class;
engine->instance = info->instance;
engine->uabi_id = info->uabi_id;
- engine->uabi_class = class_info->uabi_class;
+ engine->uabi_class = intel_engine_classes[info->class].uabi_class;
engine->context_size = __intel_engine_context_size(dev_priv,
engine->class);
if (WARN_ON(engine->context_size > BIT(20)))
engine->context_size = 0;
+ if (engine->context_size)
+ DRIVER_CAPS(dev_priv)->has_logical_contexts = true;
/* Nothing to do here, execute in order of dependencies */
engine->schedule = NULL;
- spin_lock_init(&engine->stats.lock);
+ seqlock_init(&engine->stats.lock);
ATOMIC_INIT_NOTIFIER_HEAD(&engine->context_status_notifier);
@@ -436,41 +453,21 @@ void intel_engine_init_global_seqno(struct intel_engine_cs *engine, u32 seqno)
GEM_BUG_ON(intel_engine_get_seqno(engine) != seqno);
}
-static void intel_engine_init_timeline(struct intel_engine_cs *engine)
+static void intel_engine_init_batch_pool(struct intel_engine_cs *engine)
{
- engine->timeline = &engine->i915->gt.global_timeline.engine[engine->id];
-}
-
-static bool csb_force_mmio(struct drm_i915_private *i915)
-{
- /*
- * IOMMU adds unpredictable latency causing the CSB write (from the
- * GPU into the HWSP) to only be visible some time after the interrupt
- * (missed breadcrumb syndrome).
- */
- if (intel_vtd_active())
- return true;
-
- /* Older GVT emulation depends upon intercepting CSB mmio */
- if (intel_vgpu_active(i915) && !intel_vgpu_has_hwsp_emulation(i915))
- return true;
-
- return false;
+ i915_gem_batch_pool_init(&engine->batch_pool, engine);
}
static void intel_engine_init_execlist(struct intel_engine_cs *engine)
{
struct intel_engine_execlists * const execlists = &engine->execlists;
- execlists->csb_use_mmio = csb_force_mmio(engine->i915);
-
execlists->port_mask = 1;
BUILD_BUG_ON_NOT_POWER_OF_2(execlists_num_ports(execlists));
GEM_BUG_ON(execlists_num_ports(execlists) > EXECLIST_MAX_PORTS);
execlists->queue_priority = INT_MIN;
- execlists->queue = RB_ROOT;
- execlists->first = NULL;
+ execlists->queue = RB_ROOT_CACHED;
}
/**
@@ -484,83 +481,25 @@ static void intel_engine_init_execlist(struct intel_engine_cs *engine)
*/
void intel_engine_setup_common(struct intel_engine_cs *engine)
{
- intel_engine_init_execlist(engine);
+ i915_timeline_init(engine->i915, &engine->timeline, engine->name);
+ lockdep_set_subclass(&engine->timeline.lock, TIMELINE_ENGINE);
- intel_engine_init_timeline(engine);
+ intel_engine_init_execlist(engine);
intel_engine_init_hangcheck(engine);
- i915_gem_batch_pool_init(engine, &engine->batch_pool);
-
+ intel_engine_init_batch_pool(engine);
intel_engine_init_cmd_parser(engine);
}
-int intel_engine_create_scratch(struct intel_engine_cs *engine, int size)
-{
- struct drm_i915_gem_object *obj;
- struct i915_vma *vma;
- int ret;
-
- WARN_ON(engine->scratch);
-
- obj = i915_gem_object_create_stolen(engine->i915, size);
- if (!obj)
- obj = i915_gem_object_create_internal(engine->i915, size);
- if (IS_ERR(obj)) {
- DRM_ERROR("Failed to allocate scratch page\n");
- return PTR_ERR(obj);
- }
-
- vma = i915_vma_instance(obj, &engine->i915->ggtt.base, NULL);
- if (IS_ERR(vma)) {
- ret = PTR_ERR(vma);
- goto err_unref;
- }
-
- ret = i915_vma_pin(vma, 0, 4096, PIN_GLOBAL | PIN_HIGH);
- if (ret)
- goto err_unref;
-
- engine->scratch = vma;
- DRM_DEBUG_DRIVER("%s pipe control offset: 0x%08x\n",
- engine->name, i915_ggtt_offset(vma));
- return 0;
-
-err_unref:
- i915_gem_object_put(obj);
- return ret;
-}
-
-static void intel_engine_cleanup_scratch(struct intel_engine_cs *engine)
-{
- i915_vma_unpin_and_release(&engine->scratch);
-}
-
-static void cleanup_phys_status_page(struct intel_engine_cs *engine)
-{
- struct drm_i915_private *dev_priv = engine->i915;
-
- if (!dev_priv->status_page_dmah)
- return;
-
- drm_pci_free(&dev_priv->drm, dev_priv->status_page_dmah);
- engine->status_page.page_addr = NULL;
-}
-
static void cleanup_status_page(struct intel_engine_cs *engine)
{
- struct i915_vma *vma;
- struct drm_i915_gem_object *obj;
-
- vma = fetch_and_zero(&engine->status_page.vma);
- if (!vma)
- return;
+ if (HWS_NEEDS_PHYSICAL(engine->i915)) {
+ void *addr = fetch_and_zero(&engine->status_page.page_addr);
- obj = vma->obj;
-
- i915_vma_unpin(vma);
- i915_vma_close(vma);
+ __free_page(virt_to_page(addr));
+ }
- i915_gem_object_unpin_map(obj);
- __i915_gem_object_release_unless_active(obj);
+ i915_vma_unpin_and_release(&engine->status_page.vma,
+ I915_VMA_RELEASE_MAP);
}
static int init_status_page(struct intel_engine_cs *engine)
@@ -581,7 +520,7 @@ static int init_status_page(struct intel_engine_cs *engine)
if (ret)
goto err;
- vma = i915_vma_instance(obj, &engine->i915->ggtt.base, NULL);
+ vma = i915_vma_instance(obj, &engine->i915->ggtt.vm, NULL);
if (IS_ERR(vma)) {
ret = PTR_ERR(vma);
goto err;
@@ -602,7 +541,7 @@ static int init_status_page(struct intel_engine_cs *engine)
flags |= PIN_MAPPABLE;
else
flags |= PIN_HIGH;
- ret = i915_vma_pin(vma, 0, 4096, flags);
+ ret = i915_vma_pin(vma, 0, 0, flags);
if (ret)
goto err;
@@ -615,9 +554,6 @@ static int init_status_page(struct intel_engine_cs *engine)
engine->status_page.vma = vma;
engine->status_page.ggtt_offset = i915_ggtt_offset(vma);
engine->status_page.page_addr = memset(vaddr, 0, PAGE_SIZE);
-
- DRM_DEBUG_DRIVER("%s hws offset: 0x%08x\n",
- engine->name, i915_ggtt_offset(vma));
return 0;
err_unpin:
@@ -629,21 +565,28 @@ err:
static int init_phys_status_page(struct intel_engine_cs *engine)
{
- struct drm_i915_private *dev_priv = engine->i915;
-
- GEM_BUG_ON(engine->id != RCS);
+ struct page *page;
- dev_priv->status_page_dmah =
- drm_pci_alloc(&dev_priv->drm, PAGE_SIZE, PAGE_SIZE);
- if (!dev_priv->status_page_dmah)
+ /*
+ * Though the HWS register does support 36bit addresses, historically
+ * we have had hangs and corruption reported due to wild writes if
+ * the HWS is placed above 4G.
+ */
+ page = alloc_page(GFP_KERNEL | __GFP_DMA32 | __GFP_ZERO);
+ if (!page)
return -ENOMEM;
- engine->status_page.page_addr = dev_priv->status_page_dmah->vaddr;
- memset(engine->status_page.page_addr, 0, PAGE_SIZE);
+ engine->status_page.page_addr = page_address(page);
return 0;
}
+static void __intel_context_unpin(struct i915_gem_context *ctx,
+ struct intel_engine_cs *engine)
+{
+ intel_context_unpin(to_intel_context(ctx, engine));
+}
+
/**
* intel_engines_init_common - initialize cengine state which might require hw access
* @engine: Engine to initialize.
@@ -657,7 +600,8 @@ static int init_phys_status_page(struct intel_engine_cs *engine)
*/
int intel_engine_init_common(struct intel_engine_cs *engine)
{
- struct intel_ring *ring;
+ struct drm_i915_private *i915 = engine->i915;
+ struct intel_context *ce;
int ret;
engine->set_default_submission(engine);
@@ -669,19 +613,18 @@ int intel_engine_init_common(struct intel_engine_cs *engine)
* be available. To avoid this we always pin the default
* context.
*/
- ring = engine->context_pin(engine, engine->i915->kernel_context);
- if (IS_ERR(ring))
- return PTR_ERR(ring);
+ ce = intel_context_pin(i915->kernel_context, engine);
+ if (IS_ERR(ce))
+ return PTR_ERR(ce);
/*
* Similarly the preempt context must always be available so that
* we can interrupt the engine at any time.
*/
- if (engine->i915->preempt_context) {
- ring = engine->context_pin(engine,
- engine->i915->preempt_context);
- if (IS_ERR(ring)) {
- ret = PTR_ERR(ring);
+ if (i915->preempt_context) {
+ ce = intel_context_pin(i915->preempt_context, engine);
+ if (IS_ERR(ce)) {
+ ret = PTR_ERR(ce);
goto err_unpin_kernel;
}
}
@@ -690,7 +633,7 @@ int intel_engine_init_common(struct intel_engine_cs *engine)
if (ret)
goto err_unpin_preempt;
- if (HWS_NEEDS_PHYSICAL(engine->i915))
+ if (HWS_NEEDS_PHYSICAL(i915))
ret = init_phys_status_page(engine);
else
ret = init_status_page(engine);
@@ -702,10 +645,11 @@ int intel_engine_init_common(struct intel_engine_cs *engine)
err_breadcrumbs:
intel_engine_fini_breadcrumbs(engine);
err_unpin_preempt:
- if (engine->i915->preempt_context)
- engine->context_unpin(engine, engine->i915->preempt_context);
+ if (i915->preempt_context)
+ __intel_context_unpin(i915->preempt_context, engine);
+
err_unpin_kernel:
- engine->context_unpin(engine, engine->i915->kernel_context);
+ __intel_context_unpin(i915->kernel_context, engine);
return ret;
}
@@ -718,12 +662,9 @@ err_unpin_kernel:
*/
void intel_engine_cleanup_common(struct intel_engine_cs *engine)
{
- intel_engine_cleanup_scratch(engine);
+ struct drm_i915_private *i915 = engine->i915;
- if (HWS_NEEDS_PHYSICAL(engine->i915))
- cleanup_phys_status_page(engine);
- else
- cleanup_status_page(engine);
+ cleanup_status_page(engine);
intel_engine_fini_breadcrumbs(engine);
intel_engine_cleanup_cmd_parser(engine);
@@ -732,9 +673,13 @@ void intel_engine_cleanup_common(struct intel_engine_cs *engine)
if (engine->default_state)
i915_gem_object_put(engine->default_state);
- if (engine->i915->preempt_context)
- engine->context_unpin(engine, engine->i915->preempt_context);
- engine->context_unpin(engine, engine->i915->kernel_context);
+ if (i915->preempt_context)
+ __intel_context_unpin(i915->preempt_context, engine);
+ __intel_context_unpin(i915->kernel_context, engine);
+
+ i915_timeline_fini(&engine->timeline);
+
+ intel_wa_list_free(&engine->wa_list);
}
u64 intel_engine_get_active_head(const struct intel_engine_cs *engine)
@@ -767,6 +712,45 @@ u64 intel_engine_get_last_batch_head(const struct intel_engine_cs *engine)
return bbaddr;
}
+int intel_engine_stop_cs(struct intel_engine_cs *engine)
+{
+ struct drm_i915_private *dev_priv = engine->i915;
+ const u32 base = engine->mmio_base;
+ const i915_reg_t mode = RING_MI_MODE(base);
+ int err;
+
+ if (INTEL_GEN(dev_priv) < 3)
+ return -ENODEV;
+
+ GEM_TRACE("%s\n", engine->name);
+
+ I915_WRITE_FW(mode, _MASKED_BIT_ENABLE(STOP_RING));
+
+ err = 0;
+ if (__intel_wait_for_register_fw(dev_priv,
+ mode, MODE_IDLE, MODE_IDLE,
+ 1000, 0,
+ NULL)) {
+ GEM_TRACE("%s: timed out on STOP_RING -> IDLE\n", engine->name);
+ err = -ETIMEDOUT;
+ }
+
+ /* A final mmio read to let GPU writes be hopefully flushed to memory */
+ POSTING_READ_FW(mode);
+
+ return err;
+}
+
+void intel_engine_cancel_stop_cs(struct intel_engine_cs *engine)
+{
+ struct drm_i915_private *dev_priv = engine->i915;
+
+ GEM_TRACE("%s\n", engine->name);
+
+ I915_WRITE_FW(RING_MI_MODE(engine->mmio_base),
+ _MASKED_BIT_DISABLE(STOP_RING));
+}
+
const char *i915_cache_level_str(struct drm_i915_private *i915, int type)
{
switch (type) {
@@ -778,14 +762,50 @@ const char *i915_cache_level_str(struct drm_i915_private *i915, int type)
}
}
+u32 intel_calculate_mcr_s_ss_select(struct drm_i915_private *dev_priv)
+{
+ const struct sseu_dev_info *sseu = &(INTEL_INFO(dev_priv)->sseu);
+ u32 mcr_s_ss_select;
+ u32 slice = fls(sseu->slice_mask);
+ u32 subslice = fls(sseu->subslice_mask[slice]);
+
+ if (INTEL_GEN(dev_priv) == 10)
+ mcr_s_ss_select = GEN8_MCR_SLICE(slice) |
+ GEN8_MCR_SUBSLICE(subslice);
+ else if (INTEL_GEN(dev_priv) >= 11)
+ mcr_s_ss_select = GEN11_MCR_SLICE(slice) |
+ GEN11_MCR_SUBSLICE(subslice);
+ else
+ mcr_s_ss_select = 0;
+
+ return mcr_s_ss_select;
+}
+
static inline uint32_t
read_subslice_reg(struct drm_i915_private *dev_priv, int slice,
int subslice, i915_reg_t reg)
{
+ uint32_t mcr_slice_subslice_mask;
+ uint32_t mcr_slice_subslice_select;
+ uint32_t default_mcr_s_ss_select;
uint32_t mcr;
uint32_t ret;
enum forcewake_domains fw_domains;
+ if (INTEL_GEN(dev_priv) >= 11) {
+ mcr_slice_subslice_mask = GEN11_MCR_SLICE_MASK |
+ GEN11_MCR_SUBSLICE_MASK;
+ mcr_slice_subslice_select = GEN11_MCR_SLICE(slice) |
+ GEN11_MCR_SUBSLICE(subslice);
+ } else {
+ mcr_slice_subslice_mask = GEN8_MCR_SLICE_MASK |
+ GEN8_MCR_SUBSLICE_MASK;
+ mcr_slice_subslice_select = GEN8_MCR_SLICE(slice) |
+ GEN8_MCR_SUBSLICE(subslice);
+ }
+
+ default_mcr_s_ss_select = intel_calculate_mcr_s_ss_select(dev_priv);
+
fw_domains = intel_uncore_forcewake_for_reg(dev_priv, reg,
FW_REG_READ);
fw_domains |= intel_uncore_forcewake_for_reg(dev_priv,
@@ -796,18 +816,19 @@ read_subslice_reg(struct drm_i915_private *dev_priv, int slice,
intel_uncore_forcewake_get__locked(dev_priv, fw_domains);
mcr = I915_READ_FW(GEN8_MCR_SELECTOR);
- /*
- * The HW expects the slice and sublice selectors to be reset to 0
- * after reading out the registers.
- */
- WARN_ON_ONCE(mcr & (GEN8_MCR_SLICE_MASK | GEN8_MCR_SUBSLICE_MASK));
- mcr &= ~(GEN8_MCR_SLICE_MASK | GEN8_MCR_SUBSLICE_MASK);
- mcr |= GEN8_MCR_SLICE(slice) | GEN8_MCR_SUBSLICE(subslice);
+
+ WARN_ON_ONCE((mcr & mcr_slice_subslice_mask) !=
+ default_mcr_s_ss_select);
+
+ mcr &= ~mcr_slice_subslice_mask;
+ mcr |= mcr_slice_subslice_select;
I915_WRITE_FW(GEN8_MCR_SELECTOR, mcr);
ret = I915_READ_FW(reg);
- mcr &= ~(GEN8_MCR_SLICE_MASK | GEN8_MCR_SUBSLICE_MASK);
+ mcr &= ~mcr_slice_subslice_mask;
+ mcr |= default_mcr_s_ss_select;
+
I915_WRITE_FW(GEN8_MCR_SELECTOR, mcr);
intel_uncore_forcewake_put__locked(dev_priv, fw_domains);
@@ -871,644 +892,6 @@ void intel_engine_get_instdone(struct intel_engine_cs *engine,
}
}
-static int wa_add(struct drm_i915_private *dev_priv,
- i915_reg_t addr,
- const u32 mask, const u32 val)
-{
- const u32 idx = dev_priv->workarounds.count;
-
- if (WARN_ON(idx >= I915_MAX_WA_REGS))
- return -ENOSPC;
-
- dev_priv->workarounds.reg[idx].addr = addr;
- dev_priv->workarounds.reg[idx].value = val;
- dev_priv->workarounds.reg[idx].mask = mask;
-
- dev_priv->workarounds.count++;
-
- return 0;
-}
-
-#define WA_REG(addr, mask, val) do { \
- const int r = wa_add(dev_priv, (addr), (mask), (val)); \
- if (r) \
- return r; \
- } while (0)
-
-#define WA_SET_BIT_MASKED(addr, mask) \
- WA_REG(addr, (mask), _MASKED_BIT_ENABLE(mask))
-
-#define WA_CLR_BIT_MASKED(addr, mask) \
- WA_REG(addr, (mask), _MASKED_BIT_DISABLE(mask))
-
-#define WA_SET_FIELD_MASKED(addr, mask, value) \
- WA_REG(addr, mask, _MASKED_FIELD(mask, value))
-
-static int wa_ring_whitelist_reg(struct intel_engine_cs *engine,
- i915_reg_t reg)
-{
- struct drm_i915_private *dev_priv = engine->i915;
- struct i915_workarounds *wa = &dev_priv->workarounds;
- const uint32_t index = wa->hw_whitelist_count[engine->id];
-
- if (WARN_ON(index >= RING_MAX_NONPRIV_SLOTS))
- return -EINVAL;
-
- I915_WRITE(RING_FORCE_TO_NONPRIV(engine->mmio_base, index),
- i915_mmio_reg_offset(reg));
- wa->hw_whitelist_count[engine->id]++;
-
- return 0;
-}
-
-static int gen8_init_workarounds(struct intel_engine_cs *engine)
-{
- struct drm_i915_private *dev_priv = engine->i915;
-
- WA_SET_BIT_MASKED(INSTPM, INSTPM_FORCE_ORDERING);
-
- /* WaDisableAsyncFlipPerfMode:bdw,chv */
- WA_SET_BIT_MASKED(MI_MODE, ASYNC_FLIP_PERF_DISABLE);
-
- /* WaDisablePartialInstShootdown:bdw,chv */
- WA_SET_BIT_MASKED(GEN8_ROW_CHICKEN,
- PARTIAL_INSTRUCTION_SHOOTDOWN_DISABLE);
-
- /* Use Force Non-Coherent whenever executing a 3D context. This is a
- * workaround for for a possible hang in the unlikely event a TLB
- * invalidation occurs during a PSD flush.
- */
- /* WaForceEnableNonCoherent:bdw,chv */
- /* WaHdcDisableFetchWhenMasked:bdw,chv */
- WA_SET_BIT_MASKED(HDC_CHICKEN0,
- HDC_DONOT_FETCH_MEM_WHEN_MASKED |
- HDC_FORCE_NON_COHERENT);
-
- /* From the Haswell PRM, Command Reference: Registers, CACHE_MODE_0:
- * "The Hierarchical Z RAW Stall Optimization allows non-overlapping
- * polygons in the same 8x4 pixel/sample area to be processed without
- * stalling waiting for the earlier ones to write to Hierarchical Z
- * buffer."
- *
- * This optimization is off by default for BDW and CHV; turn it on.
- */
- WA_CLR_BIT_MASKED(CACHE_MODE_0_GEN7, HIZ_RAW_STALL_OPT_DISABLE);
-
- /* Wa4x4STCOptimizationDisable:bdw,chv */
- WA_SET_BIT_MASKED(CACHE_MODE_1, GEN8_4x4_STC_OPTIMIZATION_DISABLE);
-
- /*
- * BSpec recommends 8x4 when MSAA is used,
- * however in practice 16x4 seems fastest.
- *
- * Note that PS/WM thread counts depend on the WIZ hashing
- * disable bit, which we don't touch here, but it's good
- * to keep in mind (see 3DSTATE_PS and 3DSTATE_WM).
- */
- WA_SET_FIELD_MASKED(GEN7_GT_MODE,
- GEN6_WIZ_HASHING_MASK,
- GEN6_WIZ_HASHING_16x4);
-
- return 0;
-}
-
-static int bdw_init_workarounds(struct intel_engine_cs *engine)
-{
- struct drm_i915_private *dev_priv = engine->i915;
- int ret;
-
- ret = gen8_init_workarounds(engine);
- if (ret)
- return ret;
-
- /* WaDisableThreadStallDopClockGating:bdw (pre-production) */
- WA_SET_BIT_MASKED(GEN8_ROW_CHICKEN, STALL_DOP_GATING_DISABLE);
-
- /* WaDisableDopClockGating:bdw
- *
- * Also see the related UCGTCL1 write in broadwell_init_clock_gating()
- * to disable EUTC clock gating.
- */
- WA_SET_BIT_MASKED(GEN7_ROW_CHICKEN2,
- DOP_CLOCK_GATING_DISABLE);
-
- WA_SET_BIT_MASKED(HALF_SLICE_CHICKEN3,
- GEN8_SAMPLER_POWER_BYPASS_DIS);
-
- WA_SET_BIT_MASKED(HDC_CHICKEN0,
- /* WaForceContextSaveRestoreNonCoherent:bdw */
- HDC_FORCE_CONTEXT_SAVE_RESTORE_NON_COHERENT |
- /* WaDisableFenceDestinationToSLM:bdw (pre-prod) */
- (IS_BDW_GT3(dev_priv) ? HDC_FENCE_DEST_SLM_DISABLE : 0));
-
- return 0;
-}
-
-static int chv_init_workarounds(struct intel_engine_cs *engine)
-{
- struct drm_i915_private *dev_priv = engine->i915;
- int ret;
-
- ret = gen8_init_workarounds(engine);
- if (ret)
- return ret;
-
- /* WaDisableThreadStallDopClockGating:chv */
- WA_SET_BIT_MASKED(GEN8_ROW_CHICKEN, STALL_DOP_GATING_DISABLE);
-
- /* Improve HiZ throughput on CHV. */
- WA_SET_BIT_MASKED(HIZ_CHICKEN, CHV_HZ_8X8_MODE_IN_1X);
-
- return 0;
-}
-
-static int gen9_init_workarounds(struct intel_engine_cs *engine)
-{
- struct drm_i915_private *dev_priv = engine->i915;
- int ret;
-
- /* WaConextSwitchWithConcurrentTLBInvalidate:skl,bxt,kbl,glk,cfl */
- I915_WRITE(GEN9_CSFE_CHICKEN1_RCS, _MASKED_BIT_ENABLE(GEN9_PREEMPT_GPGPU_SYNC_SWITCH_DISABLE));
-
- /* WaEnableLbsSlaRetryTimerDecrement:skl,bxt,kbl,glk,cfl */
- I915_WRITE(BDW_SCRATCH1, I915_READ(BDW_SCRATCH1) |
- GEN9_LBS_SLA_RETRY_TIMER_DECREMENT_ENABLE);
-
- /* WaDisableKillLogic:bxt,skl,kbl */
- if (!IS_COFFEELAKE(dev_priv))
- I915_WRITE(GAM_ECOCHK, I915_READ(GAM_ECOCHK) |
- ECOCHK_DIS_TLB);
-
- if (HAS_LLC(dev_priv)) {
- /* WaCompressedResourceSamplerPbeMediaNewHashMode:skl,kbl
- *
- * Must match Display Engine. See
- * WaCompressedResourceDisplayNewHashMode.
- */
- WA_SET_BIT_MASKED(COMMON_SLICE_CHICKEN2,
- GEN9_PBE_COMPRESSED_HASH_SELECTION);
- WA_SET_BIT_MASKED(GEN9_HALF_SLICE_CHICKEN7,
- GEN9_SAMPLER_HASH_COMPRESSED_READ_ADDR);
-
- I915_WRITE(MMCD_MISC_CTRL,
- I915_READ(MMCD_MISC_CTRL) |
- MMCD_PCLA |
- MMCD_HOTSPOT_EN);
- }
-
- /* WaClearFlowControlGpgpuContextSave:skl,bxt,kbl,glk,cfl */
- /* WaDisablePartialInstShootdown:skl,bxt,kbl,glk,cfl */
- WA_SET_BIT_MASKED(GEN8_ROW_CHICKEN,
- FLOW_CONTROL_ENABLE |
- PARTIAL_INSTRUCTION_SHOOTDOWN_DISABLE);
-
- /* Syncing dependencies between camera and graphics:skl,bxt,kbl */
- if (!IS_COFFEELAKE(dev_priv))
- WA_SET_BIT_MASKED(HALF_SLICE_CHICKEN3,
- GEN9_DISABLE_OCL_OOB_SUPPRESS_LOGIC);
-
- /* WaEnableYV12BugFixInHalfSliceChicken7:skl,bxt,kbl,glk,cfl */
- /* WaEnableSamplerGPGPUPreemptionSupport:skl,bxt,kbl,cfl */
- WA_SET_BIT_MASKED(GEN9_HALF_SLICE_CHICKEN7,
- GEN9_ENABLE_YV12_BUGFIX |
- GEN9_ENABLE_GPGPU_PREEMPTION);
-
- /* Wa4x4STCOptimizationDisable:skl,bxt,kbl,glk,cfl */
- /* WaDisablePartialResolveInVc:skl,bxt,kbl,cfl */
- WA_SET_BIT_MASKED(CACHE_MODE_1, (GEN8_4x4_STC_OPTIMIZATION_DISABLE |
- GEN9_PARTIAL_RESOLVE_IN_VC_DISABLE));
-
- /* WaCcsTlbPrefetchDisable:skl,bxt,kbl,glk,cfl */
- WA_CLR_BIT_MASKED(GEN9_HALF_SLICE_CHICKEN5,
- GEN9_CCS_TLB_PREFETCH_ENABLE);
-
- /* WaForceContextSaveRestoreNonCoherent:skl,bxt,kbl,cfl */
- WA_SET_BIT_MASKED(HDC_CHICKEN0,
- HDC_FORCE_CONTEXT_SAVE_RESTORE_NON_COHERENT |
- HDC_FORCE_CSR_NON_COHERENT_OVR_DISABLE);
-
- /* WaForceEnableNonCoherent and WaDisableHDCInvalidation are
- * both tied to WaForceContextSaveRestoreNonCoherent
- * in some hsds for skl. We keep the tie for all gen9. The
- * documentation is a bit hazy and so we want to get common behaviour,
- * even though there is no clear evidence we would need both on kbl/bxt.
- * This area has been source of system hangs so we play it safe
- * and mimic the skl regardless of what bspec says.
- *
- * Use Force Non-Coherent whenever executing a 3D context. This
- * is a workaround for a possible hang in the unlikely event
- * a TLB invalidation occurs during a PSD flush.
- */
-
- /* WaForceEnableNonCoherent:skl,bxt,kbl,cfl */
- WA_SET_BIT_MASKED(HDC_CHICKEN0,
- HDC_FORCE_NON_COHERENT);
-
- /* WaDisableHDCInvalidation:skl,bxt,kbl,cfl */
- I915_WRITE(GAM_ECOCHK, I915_READ(GAM_ECOCHK) |
- BDW_DISABLE_HDC_INVALIDATION);
-
- /* WaDisableSamplerPowerBypassForSOPingPong:skl,bxt,kbl,cfl */
- if (IS_SKYLAKE(dev_priv) ||
- IS_KABYLAKE(dev_priv) ||
- IS_COFFEELAKE(dev_priv))
- WA_SET_BIT_MASKED(HALF_SLICE_CHICKEN3,
- GEN8_SAMPLER_POWER_BYPASS_DIS);
-
- /* WaDisableSTUnitPowerOptimization:skl,bxt,kbl,glk,cfl */
- WA_SET_BIT_MASKED(HALF_SLICE_CHICKEN2, GEN8_ST_PO_DISABLE);
-
- /* WaProgramL3SqcReg1DefaultForPerf:bxt,glk */
- if (IS_GEN9_LP(dev_priv)) {
- u32 val = I915_READ(GEN8_L3SQCREG1);
-
- val &= ~L3_PRIO_CREDITS_MASK;
- val |= L3_GENERAL_PRIO_CREDITS(62) | L3_HIGH_PRIO_CREDITS(2);
- I915_WRITE(GEN8_L3SQCREG1, val);
- }
-
- /* WaOCLCoherentLineFlush:skl,bxt,kbl,cfl */
- I915_WRITE(GEN8_L3SQCREG4, (I915_READ(GEN8_L3SQCREG4) |
- GEN8_LQSC_FLUSH_COHERENT_LINES));
-
- /*
- * Supporting preemption with fine-granularity requires changes in the
- * batch buffer programming. Since we can't break old userspace, we
- * need to set our default preemption level to safe value. Userspace is
- * still able to use more fine-grained preemption levels, since in
- * WaEnablePreemptionGranularityControlByUMD we're whitelisting the
- * per-ctx register. As such, WaDisable{3D,GPGPU}MidCmdPreemption are
- * not real HW workarounds, but merely a way to start using preemption
- * while maintaining old contract with userspace.
- */
-
- /* WaDisable3DMidCmdPreemption:skl,bxt,glk,cfl,[cnl] */
- WA_CLR_BIT_MASKED(GEN8_CS_CHICKEN1, GEN9_PREEMPT_3D_OBJECT_LEVEL);
-
- /* WaDisableGPGPUMidCmdPreemption:skl,bxt,blk,cfl,[cnl] */
- WA_SET_FIELD_MASKED(GEN8_CS_CHICKEN1, GEN9_PREEMPT_GPGPU_LEVEL_MASK,
- GEN9_PREEMPT_GPGPU_COMMAND_LEVEL);
-
- /* WaClearHIZ_WM_CHICKEN3:bxt,glk */
- if (IS_GEN9_LP(dev_priv))
- WA_SET_BIT_MASKED(GEN9_WM_CHICKEN3, GEN9_FACTOR_IN_CLR_VAL_HIZ);
-
- /* WaVFEStateAfterPipeControlwithMediaStateClear:skl,bxt,glk,cfl */
- ret = wa_ring_whitelist_reg(engine, GEN9_CTX_PREEMPT_REG);
- if (ret)
- return ret;
-
- /* WaEnablePreemptionGranularityControlByUMD:skl,bxt,kbl,cfl,[cnl] */
- I915_WRITE(GEN7_FF_SLICE_CS_CHICKEN1,
- _MASKED_BIT_ENABLE(GEN9_FFSC_PERCTX_PREEMPT_CTRL));
- ret = wa_ring_whitelist_reg(engine, GEN8_CS_CHICKEN1);
- if (ret)
- return ret;
-
- /* WaAllowUMDToModifyHDCChicken1:skl,bxt,kbl,glk,cfl */
- ret = wa_ring_whitelist_reg(engine, GEN8_HDC_CHICKEN1);
- if (ret)
- return ret;
-
- return 0;
-}
-
-static int skl_tune_iz_hashing(struct intel_engine_cs *engine)
-{
- struct drm_i915_private *dev_priv = engine->i915;
- u8 vals[3] = { 0, 0, 0 };
- unsigned int i;
-
- for (i = 0; i < 3; i++) {
- u8 ss;
-
- /*
- * Only consider slices where one, and only one, subslice has 7
- * EUs
- */
- if (!is_power_of_2(INTEL_INFO(dev_priv)->sseu.subslice_7eu[i]))
- continue;
-
- /*
- * subslice_7eu[i] != 0 (because of the check above) and
- * ss_max == 4 (maximum number of subslices possible per slice)
- *
- * -> 0 <= ss <= 3;
- */
- ss = ffs(INTEL_INFO(dev_priv)->sseu.subslice_7eu[i]) - 1;
- vals[i] = 3 - ss;
- }
-
- if (vals[0] == 0 && vals[1] == 0 && vals[2] == 0)
- return 0;
-
- /* Tune IZ hashing. See intel_device_info_runtime_init() */
- WA_SET_FIELD_MASKED(GEN7_GT_MODE,
- GEN9_IZ_HASHING_MASK(2) |
- GEN9_IZ_HASHING_MASK(1) |
- GEN9_IZ_HASHING_MASK(0),
- GEN9_IZ_HASHING(2, vals[2]) |
- GEN9_IZ_HASHING(1, vals[1]) |
- GEN9_IZ_HASHING(0, vals[0]));
-
- return 0;
-}
-
-static int skl_init_workarounds(struct intel_engine_cs *engine)
-{
- struct drm_i915_private *dev_priv = engine->i915;
- int ret;
-
- ret = gen9_init_workarounds(engine);
- if (ret)
- return ret;
-
- /* WaEnableGapsTsvCreditFix:skl */
- I915_WRITE(GEN8_GARBCNTL, (I915_READ(GEN8_GARBCNTL) |
- GEN9_GAPS_TSV_CREDIT_DISABLE));
-
- /* WaDisableGafsUnitClkGating:skl */
- I915_WRITE(GEN7_UCGCTL4, (I915_READ(GEN7_UCGCTL4) |
- GEN8_EU_GAUNIT_CLOCK_GATE_DISABLE));
-
- /* WaInPlaceDecompressionHang:skl */
- if (IS_SKL_REVID(dev_priv, SKL_REVID_H0, REVID_FOREVER))
- I915_WRITE(GEN9_GAMT_ECO_REG_RW_IA,
- (I915_READ(GEN9_GAMT_ECO_REG_RW_IA) |
- GAMT_ECO_ENABLE_IN_PLACE_DECOMPRESS));
-
- /* WaDisableLSQCROPERFforOCL:skl */
- ret = wa_ring_whitelist_reg(engine, GEN8_L3SQCREG4);
- if (ret)
- return ret;
-
- return skl_tune_iz_hashing(engine);
-}
-
-static int bxt_init_workarounds(struct intel_engine_cs *engine)
-{
- struct drm_i915_private *dev_priv = engine->i915;
- int ret;
-
- ret = gen9_init_workarounds(engine);
- if (ret)
- return ret;
-
- /* WaDisableThreadStallDopClockGating:bxt */
- WA_SET_BIT_MASKED(GEN8_ROW_CHICKEN,
- STALL_DOP_GATING_DISABLE);
-
- /* WaDisablePooledEuLoadBalancingFix:bxt */
- I915_WRITE(FF_SLICE_CS_CHICKEN2,
- _MASKED_BIT_ENABLE(GEN9_POOLED_EU_LOAD_BALANCING_FIX_DISABLE));
-
- /* WaToEnableHwFixForPushConstHWBug:bxt */
- WA_SET_BIT_MASKED(COMMON_SLICE_CHICKEN2,
- GEN8_SBE_DISABLE_REPLAY_BUF_OPTIMIZATION);
-
- /* WaInPlaceDecompressionHang:bxt */
- I915_WRITE(GEN9_GAMT_ECO_REG_RW_IA,
- (I915_READ(GEN9_GAMT_ECO_REG_RW_IA) |
- GAMT_ECO_ENABLE_IN_PLACE_DECOMPRESS));
-
- return 0;
-}
-
-static int cnl_init_workarounds(struct intel_engine_cs *engine)
-{
- struct drm_i915_private *dev_priv = engine->i915;
- int ret;
-
- /* WaDisableI2mCycleOnWRPort:cnl (pre-prod) */
- if (IS_CNL_REVID(dev_priv, CNL_REVID_B0, CNL_REVID_B0))
- I915_WRITE(GAMT_CHKN_BIT_REG,
- (I915_READ(GAMT_CHKN_BIT_REG) |
- GAMT_CHKN_DISABLE_I2M_CYCLE_ON_WR_PORT));
-
- /* WaForceContextSaveRestoreNonCoherent:cnl */
- WA_SET_BIT_MASKED(CNL_HDC_CHICKEN0,
- HDC_FORCE_CONTEXT_SAVE_RESTORE_NON_COHERENT);
-
- /* WaThrottleEUPerfToAvoidTDBackPressure:cnl(pre-prod) */
- if (IS_CNL_REVID(dev_priv, CNL_REVID_B0, CNL_REVID_B0))
- WA_SET_BIT_MASKED(GEN8_ROW_CHICKEN, THROTTLE_12_5);
-
- /* WaDisableReplayBufferBankArbitrationOptimization:cnl */
- WA_SET_BIT_MASKED(COMMON_SLICE_CHICKEN2,
- GEN8_SBE_DISABLE_REPLAY_BUF_OPTIMIZATION);
-
- /* WaDisableEnhancedSBEVertexCaching:cnl (pre-prod) */
- if (IS_CNL_REVID(dev_priv, 0, CNL_REVID_B0))
- WA_SET_BIT_MASKED(COMMON_SLICE_CHICKEN2,
- GEN8_CSC2_SBE_VUE_CACHE_CONSERVATIVE);
-
- /* WaInPlaceDecompressionHang:cnl */
- I915_WRITE(GEN9_GAMT_ECO_REG_RW_IA,
- (I915_READ(GEN9_GAMT_ECO_REG_RW_IA) |
- GAMT_ECO_ENABLE_IN_PLACE_DECOMPRESS));
-
- /* WaPushConstantDereferenceHoldDisable:cnl */
- WA_SET_BIT_MASKED(GEN7_ROW_CHICKEN2, PUSH_CONSTANT_DEREF_DISABLE);
-
- /* FtrEnableFastAnisoL1BankingFix: cnl */
- WA_SET_BIT_MASKED(HALF_SLICE_CHICKEN3, CNL_FAST_ANISO_L1_BANKING_FIX);
-
- /* WaDisable3DMidCmdPreemption:cnl */
- WA_CLR_BIT_MASKED(GEN8_CS_CHICKEN1, GEN9_PREEMPT_3D_OBJECT_LEVEL);
-
- /* WaDisableGPGPUMidCmdPreemption:cnl */
- WA_SET_FIELD_MASKED(GEN8_CS_CHICKEN1, GEN9_PREEMPT_GPGPU_LEVEL_MASK,
- GEN9_PREEMPT_GPGPU_COMMAND_LEVEL);
-
- /* WaEnablePreemptionGranularityControlByUMD:cnl */
- I915_WRITE(GEN7_FF_SLICE_CS_CHICKEN1,
- _MASKED_BIT_ENABLE(GEN9_FFSC_PERCTX_PREEMPT_CTRL));
- ret= wa_ring_whitelist_reg(engine, GEN8_CS_CHICKEN1);
- if (ret)
- return ret;
-
- /* WaDisableEarlyEOT:cnl */
- WA_SET_BIT_MASKED(GEN8_ROW_CHICKEN, DISABLE_EARLY_EOT);
-
- return 0;
-}
-
-static int kbl_init_workarounds(struct intel_engine_cs *engine)
-{
- struct drm_i915_private *dev_priv = engine->i915;
- int ret;
-
- ret = gen9_init_workarounds(engine);
- if (ret)
- return ret;
-
- /* WaEnableGapsTsvCreditFix:kbl */
- I915_WRITE(GEN8_GARBCNTL, (I915_READ(GEN8_GARBCNTL) |
- GEN9_GAPS_TSV_CREDIT_DISABLE));
-
- /* WaDisableDynamicCreditSharing:kbl */
- if (IS_KBL_REVID(dev_priv, 0, KBL_REVID_B0))
- I915_WRITE(GAMT_CHKN_BIT_REG,
- (I915_READ(GAMT_CHKN_BIT_REG) |
- GAMT_CHKN_DISABLE_DYNAMIC_CREDIT_SHARING));
-
- /* WaDisableFenceDestinationToSLM:kbl (pre-prod) */
- if (IS_KBL_REVID(dev_priv, KBL_REVID_A0, KBL_REVID_A0))
- WA_SET_BIT_MASKED(HDC_CHICKEN0,
- HDC_FENCE_DEST_SLM_DISABLE);
-
- /* WaToEnableHwFixForPushConstHWBug:kbl */
- if (IS_KBL_REVID(dev_priv, KBL_REVID_C0, REVID_FOREVER))
- WA_SET_BIT_MASKED(COMMON_SLICE_CHICKEN2,
- GEN8_SBE_DISABLE_REPLAY_BUF_OPTIMIZATION);
-
- /* WaDisableGafsUnitClkGating:kbl */
- I915_WRITE(GEN7_UCGCTL4, (I915_READ(GEN7_UCGCTL4) |
- GEN8_EU_GAUNIT_CLOCK_GATE_DISABLE));
-
- /* WaDisableSbeCacheDispatchPortSharing:kbl */
- WA_SET_BIT_MASKED(
- GEN7_HALF_SLICE_CHICKEN1,
- GEN7_SBE_SS_CACHE_DISPATCH_PORT_SHARING_DISABLE);
-
- /* WaInPlaceDecompressionHang:kbl */
- I915_WRITE(GEN9_GAMT_ECO_REG_RW_IA,
- (I915_READ(GEN9_GAMT_ECO_REG_RW_IA) |
- GAMT_ECO_ENABLE_IN_PLACE_DECOMPRESS));
-
- /* WaDisableLSQCROPERFforOCL:kbl */
- ret = wa_ring_whitelist_reg(engine, GEN8_L3SQCREG4);
- if (ret)
- return ret;
-
- return 0;
-}
-
-static int glk_init_workarounds(struct intel_engine_cs *engine)
-{
- struct drm_i915_private *dev_priv = engine->i915;
- int ret;
-
- ret = gen9_init_workarounds(engine);
- if (ret)
- return ret;
-
- /* WA #0862: Userspace has to set "Barrier Mode" to avoid hangs. */
- ret = wa_ring_whitelist_reg(engine, GEN9_SLICE_COMMON_ECO_CHICKEN1);
- if (ret)
- return ret;
-
- /* WaToEnableHwFixForPushConstHWBug:glk */
- WA_SET_BIT_MASKED(COMMON_SLICE_CHICKEN2,
- GEN8_SBE_DISABLE_REPLAY_BUF_OPTIMIZATION);
-
- return 0;
-}
-
-static int cfl_init_workarounds(struct intel_engine_cs *engine)
-{
- struct drm_i915_private *dev_priv = engine->i915;
- int ret;
-
- ret = gen9_init_workarounds(engine);
- if (ret)
- return ret;
-
- /* WaEnableGapsTsvCreditFix:cfl */
- I915_WRITE(GEN8_GARBCNTL, (I915_READ(GEN8_GARBCNTL) |
- GEN9_GAPS_TSV_CREDIT_DISABLE));
-
- /* WaToEnableHwFixForPushConstHWBug:cfl */
- WA_SET_BIT_MASKED(COMMON_SLICE_CHICKEN2,
- GEN8_SBE_DISABLE_REPLAY_BUF_OPTIMIZATION);
-
- /* WaDisableGafsUnitClkGating:cfl */
- I915_WRITE(GEN7_UCGCTL4, (I915_READ(GEN7_UCGCTL4) |
- GEN8_EU_GAUNIT_CLOCK_GATE_DISABLE));
-
- /* WaDisableSbeCacheDispatchPortSharing:cfl */
- WA_SET_BIT_MASKED(
- GEN7_HALF_SLICE_CHICKEN1,
- GEN7_SBE_SS_CACHE_DISPATCH_PORT_SHARING_DISABLE);
-
- /* WaInPlaceDecompressionHang:cfl */
- I915_WRITE(GEN9_GAMT_ECO_REG_RW_IA,
- (I915_READ(GEN9_GAMT_ECO_REG_RW_IA) |
- GAMT_ECO_ENABLE_IN_PLACE_DECOMPRESS));
-
- return 0;
-}
-
-int init_workarounds_ring(struct intel_engine_cs *engine)
-{
- struct drm_i915_private *dev_priv = engine->i915;
- int err;
-
- if (GEM_WARN_ON(engine->id != RCS))
- return -EINVAL;
-
- dev_priv->workarounds.count = 0;
- dev_priv->workarounds.hw_whitelist_count[engine->id] = 0;
-
- if (IS_BROADWELL(dev_priv))
- err = bdw_init_workarounds(engine);
- else if (IS_CHERRYVIEW(dev_priv))
- err = chv_init_workarounds(engine);
- else if (IS_SKYLAKE(dev_priv))
- err = skl_init_workarounds(engine);
- else if (IS_BROXTON(dev_priv))
- err = bxt_init_workarounds(engine);
- else if (IS_KABYLAKE(dev_priv))
- err = kbl_init_workarounds(engine);
- else if (IS_GEMINILAKE(dev_priv))
- err = glk_init_workarounds(engine);
- else if (IS_COFFEELAKE(dev_priv))
- err = cfl_init_workarounds(engine);
- else if (IS_CANNONLAKE(dev_priv))
- err = cnl_init_workarounds(engine);
- else
- err = 0;
- if (err)
- return err;
-
- DRM_DEBUG_DRIVER("%s: Number of context specific w/a: %d\n",
- engine->name, dev_priv->workarounds.count);
- return 0;
-}
-
-int intel_ring_workarounds_emit(struct i915_request *rq)
-{
- struct i915_workarounds *w = &rq->i915->workarounds;
- u32 *cs;
- int ret, i;
-
- if (w->count == 0)
- return 0;
-
- ret = rq->engine->emit_flush(rq, EMIT_BARRIER);
- if (ret)
- return ret;
-
- cs = intel_ring_begin(rq, w->count * 2 + 2);
- if (IS_ERR(cs))
- return PTR_ERR(cs);
-
- *cs++ = MI_LOAD_REGISTER_IMM(w->count);
- for (i = 0; i < w->count; i++) {
- *cs++ = i915_mmio_reg_offset(w->reg[i].addr);
- *cs++ = w->reg[i].value;
- }
- *cs++ = MI_NOOP;
-
- intel_ring_advance(rq, cs);
-
- ret = rq->engine->emit_flush(rq, EMIT_BARRIER);
- if (ret)
- return ret;
-
- return 0;
-}
-
static bool ring_is_idle(struct intel_engine_cs *engine)
{
struct drm_i915_private *dev_priv = engine->i915;
@@ -1548,19 +931,34 @@ bool intel_engine_is_idle(struct intel_engine_cs *engine)
return true;
/* Any inflight/incomplete requests? */
- if (!i915_seqno_passed(intel_engine_get_seqno(engine),
- intel_engine_last_submit(engine)))
+ if (!intel_engine_signaled(engine, intel_engine_last_submit(engine)))
return false;
if (I915_SELFTEST_ONLY(engine->breadcrumbs.mock))
return true;
/* Waiting to drain ELSP? */
- if (READ_ONCE(engine->execlists.active))
- return false;
+ if (READ_ONCE(engine->execlists.active)) {
+ struct tasklet_struct *t = &engine->execlists.tasklet;
+
+ local_bh_disable();
+ if (tasklet_trylock(t)) {
+ /* Must wait for any GPU reset in progress. */
+ if (__tasklet_is_enabled(t))
+ t->func(t->data);
+ tasklet_unlock(t);
+ }
+ local_bh_enable();
- /* ELSP is empty, but there are ready requests? */
- if (READ_ONCE(engine->execlists.first))
+ /* Otherwise flush the tasklet if it was on another cpu */
+ tasklet_unlock_wait(t);
+
+ if (READ_ONCE(engine->execlists.active))
+ return false;
+ }
+
+ /* ELSP is empty, but there are ready requests? E.g. after reset */
+ if (!RB_EMPTY_ROOT(&engine->execlists.queue.rb_root))
return false;
/* Ring stopped? */
@@ -1600,8 +998,8 @@ bool intel_engines_are_idle(struct drm_i915_private *dev_priv)
*/
bool intel_engine_has_kernel_context(const struct intel_engine_cs *engine)
{
- const struct i915_gem_context * const kernel_context =
- engine->i915->kernel_context;
+ const struct intel_context *kernel_context =
+ to_intel_context(engine->i915->kernel_context, engine);
struct i915_request *rq;
lockdep_assert_held(&engine->i915->drm.struct_mutex);
@@ -1611,9 +1009,9 @@ bool intel_engine_has_kernel_context(const struct intel_engine_cs *engine)
* the last request that remains in the timeline. When idle, it is
* the last executed context as tracked by retirement.
*/
- rq = __i915_gem_active_peek(&engine->timeline->last_request);
+ rq = __i915_gem_active_peek(&engine->timeline.last_request);
if (rq)
- return rq->ctx == kernel_context;
+ return rq->hw_context == kernel_context;
else
return engine->last_retired_context == kernel_context;
}
@@ -1628,6 +1026,28 @@ void intel_engines_reset_default_submission(struct drm_i915_private *i915)
}
/**
+ * intel_engines_sanitize: called after the GPU has lost power
+ * @i915: the i915 device
+ *
+ * Anytime we reset the GPU, either with an explicit GPU reset or through a
+ * PCI power cycle, the GPU loses state and we must reset our state tracking
+ * to match. Note that calling intel_engines_sanitize() if the GPU has not
+ * been reset results in much confusion!
+ */
+void intel_engines_sanitize(struct drm_i915_private *i915)
+{
+ struct intel_engine_cs *engine;
+ enum intel_engine_id id;
+
+ GEM_TRACE("\n");
+
+ for_each_engine(engine, i915, id) {
+ if (engine->reset.reset)
+ engine->reset.reset(engine, NULL);
+ }
+}
+
+/**
* intel_engines_park: called when the GT is transitioning from busy->idle
* @i915: the i915 device
*
@@ -1659,9 +1079,17 @@ void intel_engines_park(struct drm_i915_private *i915)
intel_engine_dump(engine, &p, NULL);
}
+ /* Must be reset upon idling, or we may miss the busy wakeup. */
+ GEM_BUG_ON(engine->execlists.queue_priority != INT_MIN);
+
if (engine->park)
engine->park(engine);
+ if (engine->pinned_default_state) {
+ i915_gem_object_unpin_map(engine->default_state);
+ engine->pinned_default_state = NULL;
+ }
+
i915_gem_batch_pool_fini(&engine->batch_pool);
engine->execlists.no_priolist = false;
}
@@ -1679,11 +1107,43 @@ void intel_engines_unpark(struct drm_i915_private *i915)
enum intel_engine_id id;
for_each_engine(engine, i915, id) {
+ void *map;
+
+ /* Pin the default state for fast resets from atomic context. */
+ map = NULL;
+ if (engine->default_state)
+ map = i915_gem_object_pin_map(engine->default_state,
+ I915_MAP_WB);
+ if (!IS_ERR_OR_NULL(map))
+ engine->pinned_default_state = map;
+
if (engine->unpark)
engine->unpark(engine);
+
+ intel_engine_init_hangcheck(engine);
}
}
+/**
+ * intel_engine_lost_context: called when the GPU is reset into unknown state
+ * @engine: the engine
+ *
+ * We have either reset the GPU or otherwise about to lose state tracking of
+ * the current GPU logical state (e.g. suspend). On next use, it is therefore
+ * imperative that we make no presumptions about the current state and load
+ * from scratch.
+ */
+void intel_engine_lost_context(struct intel_engine_cs *engine)
+{
+ struct intel_context *ce;
+
+ lockdep_assert_held(&engine->i915->drm.struct_mutex);
+
+ ce = fetch_and_zero(&engine->last_retired_context);
+ if (ce)
+ intel_context_unpin(ce);
+}
+
bool intel_engine_can_store_dword(struct intel_engine_cs *engine)
{
switch (INTEL_GEN(engine->i915)) {
@@ -1713,17 +1173,37 @@ unsigned int intel_engines_has_context_isolation(struct drm_i915_private *i915)
return which;
}
+static int print_sched_attr(struct drm_i915_private *i915,
+ const struct i915_sched_attr *attr,
+ char *buf, int x, int len)
+{
+ if (attr->priority == I915_PRIORITY_INVALID)
+ return x;
+
+ x += snprintf(buf + x, len - x,
+ " prio=%d", attr->priority);
+
+ return x;
+}
+
static void print_request(struct drm_printer *m,
struct i915_request *rq,
const char *prefix)
{
- drm_printf(m, "%s%x%s [%llx:%x] prio=%d @ %dms: %s\n", prefix,
+ const char *name = rq->fence.ops->get_timeline_name(&rq->fence);
+ char buf[80] = "";
+ int x = 0;
+
+ x = print_sched_attr(rq->i915, &rq->sched.attr, buf, x, sizeof(buf));
+
+ drm_printf(m, "%s%x%s [%llx:%x]%s @ %dms: %s\n",
+ prefix,
rq->global_seqno,
i915_request_completed(rq) ? "!" : "",
rq->fence.context, rq->fence.seqno,
- rq->priotree.priority,
+ buf,
jiffies_to_msecs(jiffies - rq->emitted_jiffies),
- rq->timeline->common->name);
+ name);
}
static void hexdump(struct drm_printer *m, const void *buf, size_t len)
@@ -1748,7 +1228,7 @@ static void hexdump(struct drm_printer *m, const void *buf, size_t len)
rowsize, sizeof(u32),
line, sizeof(line),
false) >= sizeof(line));
- drm_printf(m, "%08zx %s\n", pos, line);
+ drm_printf(m, "[%04zx] %s\n", pos, line);
prev = buf + pos;
skip = false;
@@ -1763,6 +1243,8 @@ static void intel_engine_print_registers(const struct intel_engine_cs *engine,
&engine->execlists;
u64 addr;
+ if (engine->id == RCS && IS_GEN(dev_priv, 4, 7))
+ drm_printf(m, "\tCCID: 0x%08x\n", I915_READ(CCID));
drm_printf(m, "\tRING_START: 0x%08x\n",
I915_READ(RING_START(engine->mmio_base)));
drm_printf(m, "\tRING_HEAD: 0x%08x\n",
@@ -1819,22 +1301,22 @@ static void intel_engine_print_registers(const struct intel_engine_cs *engine,
if (HAS_EXECLISTS(dev_priv)) {
const u32 *hws = &engine->status_page.page_addr[I915_HWS_CSB_BUF0_INDEX];
- u32 ptr, read, write;
unsigned int idx;
+ u8 read, write;
drm_printf(m, "\tExeclist status: 0x%08x %08x\n",
I915_READ(RING_EXECLIST_STATUS_LO(engine)),
I915_READ(RING_EXECLIST_STATUS_HI(engine)));
- ptr = I915_READ(RING_CONTEXT_STATUS_PTR(engine));
- read = GEN8_CSB_READ_PTR(ptr);
- write = GEN8_CSB_WRITE_PTR(ptr);
- drm_printf(m, "\tExeclist CSB read %d [%d cached], write %d [%d from hws], interrupt posted? %s\n",
- read, execlists->csb_head,
- write,
- intel_read_status_page(engine, intel_hws_csb_write_index(engine->i915)),
- yesno(test_bit(ENGINE_IRQ_EXECLIST,
- &engine->irq_posted)));
+ read = execlists->csb_head;
+ write = READ_ONCE(*execlists->csb_write);
+
+ drm_printf(m, "\tExeclist CSB read %d, write %d [mmio:%d], tasklet queued? %s (%s)\n",
+ read, write,
+ GEN8_CSB_WRITE_PTR(I915_READ(RING_CONTEXT_STATUS_PTR(engine))),
+ yesno(test_bit(TASKLET_STATE_SCHED,
+ &engine->execlists.tasklet.state)),
+ enableddisabled(!atomic_read(&engine->execlists.tasklet.count)));
if (read >= GEN8_CSB_ENTRIES)
read = 0;
if (write >= GEN8_CSB_ENTRIES)
@@ -1843,12 +1325,12 @@ static void intel_engine_print_registers(const struct intel_engine_cs *engine,
write += GEN8_CSB_ENTRIES;
while (read < write) {
idx = ++read % GEN8_CSB_ENTRIES;
- drm_printf(m, "\tExeclist CSB[%d]: 0x%08x [0x%08x in hwsp], context: %d [%d in hwsp]\n",
+ drm_printf(m, "\tExeclist CSB[%d]: 0x%08x [mmio:0x%08x], context: %d [mmio:%d]\n",
idx,
- I915_READ(RING_CONTEXT_STATUS_BUF_LO(engine, idx)),
hws[idx * 2],
- I915_READ(RING_CONTEXT_STATUS_BUF_HI(engine, idx)),
- hws[idx * 2 + 1]);
+ I915_READ(RING_CONTEXT_STATUS_BUF_LO(engine, idx)),
+ hws[idx * 2 + 1],
+ I915_READ(RING_CONTEXT_STATUS_BUF_HI(engine, idx)));
}
rcu_read_lock();
@@ -1861,8 +1343,9 @@ static void intel_engine_print_registers(const struct intel_engine_cs *engine,
char hdr[80];
snprintf(hdr, sizeof(hdr),
- "\t\tELSP[%d] count=%d, rq: ",
- idx, count);
+ "\t\tELSP[%d] count=%d, ring->start=%08x, rq: ",
+ idx, count,
+ i915_ggtt_offset(rq->ring->vma));
print_request(m, rq, hdr);
} else {
drm_printf(m, "\t\tELSP[%d] idle\n", idx);
@@ -1880,15 +1363,51 @@ static void intel_engine_print_registers(const struct intel_engine_cs *engine,
}
}
+static void print_request_ring(struct drm_printer *m, struct i915_request *rq)
+{
+ void *ring;
+ int size;
+
+ drm_printf(m,
+ "[head %04x, postfix %04x, tail %04x, batch 0x%08x_%08x]:\n",
+ rq->head, rq->postfix, rq->tail,
+ rq->batch ? upper_32_bits(rq->batch->node.start) : ~0u,
+ rq->batch ? lower_32_bits(rq->batch->node.start) : ~0u);
+
+ size = rq->tail - rq->head;
+ if (rq->tail < rq->head)
+ size += rq->ring->size;
+
+ ring = kmalloc(size, GFP_ATOMIC);
+ if (ring) {
+ const void *vaddr = rq->ring->vaddr;
+ unsigned int head = rq->head;
+ unsigned int len = 0;
+
+ if (rq->tail < head) {
+ len = rq->ring->size - head;
+ memcpy(ring, vaddr + head, len);
+ head = 0;
+ }
+ memcpy(ring + len, vaddr + head, size - len);
+
+ hexdump(m, ring, size);
+ kfree(ring);
+ }
+}
+
void intel_engine_dump(struct intel_engine_cs *engine,
struct drm_printer *m,
const char *header, ...)
{
+ const int MAX_REQUESTS_TO_SHOW = 8;
struct intel_breadcrumbs * const b = &engine->breadcrumbs;
const struct intel_engine_execlists * const execlists = &engine->execlists;
struct i915_gpu_error * const error = &engine->i915->gpu_error;
- struct i915_request *rq;
+ struct i915_request *rq, *last;
+ unsigned long flags;
struct rb_node *rb;
+ int count;
if (header) {
va_list ap;
@@ -1901,12 +1420,11 @@ void intel_engine_dump(struct intel_engine_cs *engine,
if (i915_terminally_wedged(&engine->i915->gpu_error))
drm_printf(m, "*** WEDGED ***\n");
- drm_printf(m, "\tcurrent seqno %x, last %x, hangcheck %x [%d ms], inflight %d\n",
+ drm_printf(m, "\tcurrent seqno %x, last %x, hangcheck %x [%d ms]\n",
intel_engine_get_seqno(engine),
intel_engine_last_submit(engine),
engine->hangcheck.seqno,
- jiffies_to_msecs(jiffies - engine->hangcheck.action_timestamp),
- engine->timeline->inflight_seqnos);
+ jiffies_to_msecs(jiffies - engine->hangcheck.action_timestamp));
drm_printf(m, "\tReset count: %d (global %d)\n",
i915_reset_engine_count(error, engine),
i915_reset_count(error));
@@ -1915,30 +1433,32 @@ void intel_engine_dump(struct intel_engine_cs *engine,
drm_printf(m, "\tRequests:\n");
- rq = list_first_entry(&engine->timeline->requests,
+ rq = list_first_entry(&engine->timeline.requests,
struct i915_request, link);
- if (&rq->link != &engine->timeline->requests)
+ if (&rq->link != &engine->timeline.requests)
print_request(m, rq, "\t\tfirst ");
- rq = list_last_entry(&engine->timeline->requests,
+ rq = list_last_entry(&engine->timeline.requests,
struct i915_request, link);
- if (&rq->link != &engine->timeline->requests)
+ if (&rq->link != &engine->timeline.requests)
print_request(m, rq, "\t\tlast ");
rq = i915_gem_find_active_request(engine);
if (rq) {
print_request(m, rq, "\t\tactive ");
- drm_printf(m,
- "\t\t[head %04x, postfix %04x, tail %04x, batch 0x%08x_%08x]\n",
- rq->head, rq->postfix, rq->tail,
- rq->batch ? upper_32_bits(rq->batch->node.start) : ~0u,
- rq->batch ? lower_32_bits(rq->batch->node.start) : ~0u);
- drm_printf(m, "\t\tring->start: 0x%08x\n",
+
+ drm_printf(m, "\t\tring->start: 0x%08x\n",
i915_ggtt_offset(rq->ring->vma));
- drm_printf(m, "\t\tring->head: 0x%08x\n",
+ drm_printf(m, "\t\tring->head: 0x%08x\n",
rq->ring->head);
- drm_printf(m, "\t\tring->tail: 0x%08x\n",
+ drm_printf(m, "\t\tring->tail: 0x%08x\n",
rq->ring->tail);
+ drm_printf(m, "\t\tring->emit: 0x%08x\n",
+ rq->ring->emit);
+ drm_printf(m, "\t\tring->space: 0x%08x\n",
+ rq->ring->space);
+
+ print_request_ring(m, rq);
}
rcu_read_unlock();
@@ -1950,33 +1470,64 @@ void intel_engine_dump(struct intel_engine_cs *engine,
drm_printf(m, "\tDevice is asleep; skipping register dump\n");
}
- spin_lock_irq(&engine->timeline->lock);
- list_for_each_entry(rq, &engine->timeline->requests, link)
- print_request(m, rq, "\t\tE ");
+ local_irq_save(flags);
+ spin_lock(&engine->timeline.lock);
+
+ last = NULL;
+ count = 0;
+ list_for_each_entry(rq, &engine->timeline.requests, link) {
+ if (count++ < MAX_REQUESTS_TO_SHOW - 1)
+ print_request(m, rq, "\t\tE ");
+ else
+ last = rq;
+ }
+ if (last) {
+ if (count > MAX_REQUESTS_TO_SHOW) {
+ drm_printf(m,
+ "\t\t...skipping %d executing requests...\n",
+ count - MAX_REQUESTS_TO_SHOW);
+ }
+ print_request(m, last, "\t\tE ");
+ }
+
+ last = NULL;
+ count = 0;
drm_printf(m, "\t\tQueue priority: %d\n", execlists->queue_priority);
- for (rb = execlists->first; rb; rb = rb_next(rb)) {
+ for (rb = rb_first_cached(&execlists->queue); rb; rb = rb_next(rb)) {
struct i915_priolist *p =
rb_entry(rb, typeof(*p), node);
- list_for_each_entry(rq, &p->requests, priotree.link)
- print_request(m, rq, "\t\tQ ");
+ list_for_each_entry(rq, &p->requests, sched.link) {
+ if (count++ < MAX_REQUESTS_TO_SHOW - 1)
+ print_request(m, rq, "\t\tQ ");
+ else
+ last = rq;
+ }
+ }
+ if (last) {
+ if (count > MAX_REQUESTS_TO_SHOW) {
+ drm_printf(m,
+ "\t\t...skipping %d queued requests...\n",
+ count - MAX_REQUESTS_TO_SHOW);
+ }
+ print_request(m, last, "\t\tQ ");
}
- spin_unlock_irq(&engine->timeline->lock);
- spin_lock_irq(&b->rb_lock);
+ spin_unlock(&engine->timeline.lock);
+
+ spin_lock(&b->rb_lock);
for (rb = rb_first(&b->waiters); rb; rb = rb_next(rb)) {
struct intel_wait *w = rb_entry(rb, typeof(*w), node);
drm_printf(m, "\t%s [%d] waiting for %x\n",
w->tsk->comm, w->tsk->pid, w->seqno);
}
- spin_unlock_irq(&b->rb_lock);
+ spin_unlock(&b->rb_lock);
+ local_irq_restore(flags);
- drm_printf(m, "IRQ? 0x%lx (breadcrumbs? %s) (execlists? %s)\n",
+ drm_printf(m, "IRQ? 0x%lx (breadcrumbs? %s)\n",
engine->irq_posted,
yesno(test_bit(ENGINE_IRQ_BREADCRUMB,
- &engine->irq_posted)),
- yesno(test_bit(ENGINE_IRQ_EXECLIST,
&engine->irq_posted)));
drm_printf(m, "HWSP:\n");
@@ -2025,8 +1576,8 @@ int intel_enable_engine_stats(struct intel_engine_cs *engine)
if (!intel_engine_supports_stats(engine))
return -ENODEV;
- tasklet_disable(&execlists->tasklet);
- spin_lock_irqsave(&engine->stats.lock, flags);
+ spin_lock_irqsave(&engine->timeline.lock, flags);
+ write_seqlock(&engine->stats.lock);
if (unlikely(engine->stats.enabled == ~0)) {
err = -EBUSY;
@@ -2050,8 +1601,8 @@ int intel_enable_engine_stats(struct intel_engine_cs *engine)
}
unlock:
- spin_unlock_irqrestore(&engine->stats.lock, flags);
- tasklet_enable(&execlists->tasklet);
+ write_sequnlock(&engine->stats.lock);
+ spin_unlock_irqrestore(&engine->timeline.lock, flags);
return err;
}
@@ -2079,12 +1630,13 @@ static ktime_t __intel_engine_get_busy_time(struct intel_engine_cs *engine)
*/
ktime_t intel_engine_get_busy_time(struct intel_engine_cs *engine)
{
+ unsigned int seq;
ktime_t total;
- unsigned long flags;
- spin_lock_irqsave(&engine->stats.lock, flags);
- total = __intel_engine_get_busy_time(engine);
- spin_unlock_irqrestore(&engine->stats.lock, flags);
+ do {
+ seq = read_seqbegin(&engine->stats.lock);
+ total = __intel_engine_get_busy_time(engine);
+ } while (read_seqretry(&engine->stats.lock, seq));
return total;
}
@@ -2102,15 +1654,16 @@ void intel_disable_engine_stats(struct intel_engine_cs *engine)
if (!intel_engine_supports_stats(engine))
return;
- spin_lock_irqsave(&engine->stats.lock, flags);
+ write_seqlock_irqsave(&engine->stats.lock, flags);
WARN_ON_ONCE(engine->stats.enabled == 0);
if (--engine->stats.enabled == 0) {
engine->stats.total = __intel_engine_get_busy_time(engine);
engine->stats.active = 0;
}
- spin_unlock_irqrestore(&engine->stats.lock, flags);
+ write_sequnlock_irqrestore(&engine->stats.lock, flags);
}
#if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
#include "selftests/mock_engine.c"
+#include "selftests/intel_engine_cs.c"
#endif
OpenPOWER on IntegriCloud