diff --git a/Documentation/gpu/i915.rst b/Documentation/gpu/i915.rst
index 54060cd6c419474ef09ae6dc9ab74f7c328dfee1..4e59db1cfb00ef7a07b5d8c6ed9598735a43d0c7 100644
--- a/Documentation/gpu/i915.rst
+++ b/Documentation/gpu/i915.rst
@@ -246,6 +246,18 @@ Display State Buffer
.. kernel-doc:: drivers/gpu/drm/i915/display/intel_dsb.c
:internal:
+GT Programming
+==============
+
+Multicast/Replicated (MCR) Registers
+------------------------------------
+
+.. kernel-doc:: drivers/gpu/drm/i915/gt/intel_gt_mcr.c
+ :doc: GT Multicast/Replicated (MCR) Register Support
+
+.. kernel-doc:: drivers/gpu/drm/i915/gt/intel_gt_mcr.c
+ :internal:
+
Memory Management and Command Submission
========================================
diff --git a/drivers/char/agp/intel-gtt.c b/drivers/char/agp/intel-gtt.c
index 79a1b65527c2c51f3d9b225308c0df8d0a15298a..fe7e2105e7667a530ee20696b111f025729b8f89 100644
--- a/drivers/char/agp/intel-gtt.c
+++ b/drivers/char/agp/intel-gtt.c
@@ -744,7 +744,7 @@ static void i830_write_entry(dma_addr_t addr, unsigned int entry,
writel_relaxed(addr | pte_flags, intel_private.gtt + entry);
}
-bool intel_enable_gtt(void)
+bool intel_gmch_enable_gtt(void)
{
u8 __iomem *reg;
@@ -787,7 +787,7 @@ bool intel_enable_gtt(void)
return true;
}
-EXPORT_SYMBOL(intel_enable_gtt);
+EXPORT_SYMBOL(intel_gmch_enable_gtt);
static int i830_setup(void)
{
@@ -821,8 +821,8 @@ static int intel_fake_agp_free_gatt_table(struct agp_bridge_data *bridge)
static int intel_fake_agp_configure(void)
{
- if (!intel_enable_gtt())
- return -EIO;
+ if (!intel_gmch_enable_gtt())
+ return -EIO;
intel_private.clear_fake_agp = true;
agp_bridge->gart_bus_addr = intel_private.gma_bus_addr;
@@ -844,20 +844,20 @@ static bool i830_check_flags(unsigned int flags)
return false;
}
-void intel_gtt_insert_page(dma_addr_t addr,
- unsigned int pg,
- unsigned int flags)
+void intel_gmch_gtt_insert_page(dma_addr_t addr,
+ unsigned int pg,
+ unsigned int flags)
{
intel_private.driver->write_entry(addr, pg, flags);
readl(intel_private.gtt + pg);
if (intel_private.driver->chipset_flush)
intel_private.driver->chipset_flush();
}
-EXPORT_SYMBOL(intel_gtt_insert_page);
+EXPORT_SYMBOL(intel_gmch_gtt_insert_page);
-void intel_gtt_insert_sg_entries(struct sg_table *st,
- unsigned int pg_start,
- unsigned int flags)
+void intel_gmch_gtt_insert_sg_entries(struct sg_table *st,
+ unsigned int pg_start,
+ unsigned int flags)
{
struct scatterlist *sg;
unsigned int len, m;
@@ -879,13 +879,13 @@ void intel_gtt_insert_sg_entries(struct sg_table *st,
if (intel_private.driver->chipset_flush)
intel_private.driver->chipset_flush();
}
-EXPORT_SYMBOL(intel_gtt_insert_sg_entries);
+EXPORT_SYMBOL(intel_gmch_gtt_insert_sg_entries);
#if IS_ENABLED(CONFIG_AGP_INTEL)
-static void intel_gtt_insert_pages(unsigned int first_entry,
- unsigned int num_entries,
- struct page **pages,
- unsigned int flags)
+static void intel_gmch_gtt_insert_pages(unsigned int first_entry,
+ unsigned int num_entries,
+ struct page **pages,
+ unsigned int flags)
{
int i, j;
@@ -905,7 +905,7 @@ static int intel_fake_agp_insert_entries(struct agp_memory *mem,
if (intel_private.clear_fake_agp) {
int start = intel_private.stolen_size / PAGE_SIZE;
int end = intel_private.gtt_mappable_entries;
- intel_gtt_clear_range(start, end - start);
+ intel_gmch_gtt_clear_range(start, end - start);
intel_private.clear_fake_agp = false;
}
@@ -934,12 +934,12 @@ static int intel_fake_agp_insert_entries(struct agp_memory *mem,
if (ret != 0)
return ret;
- intel_gtt_insert_sg_entries(&st, pg_start, type);
+ intel_gmch_gtt_insert_sg_entries(&st, pg_start, type);
mem->sg_list = st.sgl;
mem->num_sg = st.nents;
} else
- intel_gtt_insert_pages(pg_start, mem->page_count, mem->pages,
- type);
+ intel_gmch_gtt_insert_pages(pg_start, mem->page_count, mem->pages,
+ type);
out:
ret = 0;
@@ -949,7 +949,7 @@ static int intel_fake_agp_insert_entries(struct agp_memory *mem,
}
#endif
-void intel_gtt_clear_range(unsigned int first_entry, unsigned int num_entries)
+void intel_gmch_gtt_clear_range(unsigned int first_entry, unsigned int num_entries)
{
unsigned int i;
@@ -959,7 +959,7 @@ void intel_gtt_clear_range(unsigned int first_entry, unsigned int num_entries)
}
wmb();
}
-EXPORT_SYMBOL(intel_gtt_clear_range);
+EXPORT_SYMBOL(intel_gmch_gtt_clear_range);
#if IS_ENABLED(CONFIG_AGP_INTEL)
static int intel_fake_agp_remove_entries(struct agp_memory *mem,
@@ -968,7 +968,7 @@ static int intel_fake_agp_remove_entries(struct agp_memory *mem,
if (mem->page_count == 0)
return 0;
- intel_gtt_clear_range(pg_start, mem->page_count);
+ intel_gmch_gtt_clear_range(pg_start, mem->page_count);
if (intel_private.needs_dmar) {
intel_gtt_unmap_memory(mem->sg_list, mem->num_sg);
@@ -1431,22 +1431,22 @@ int intel_gmch_probe(struct pci_dev *bridge_pdev, struct pci_dev *gpu_pdev,
}
EXPORT_SYMBOL(intel_gmch_probe);
-void intel_gtt_get(u64 *gtt_total,
- phys_addr_t *mappable_base,
- resource_size_t *mappable_end)
+void intel_gmch_gtt_get(u64 *gtt_total,
+ phys_addr_t *mappable_base,
+ resource_size_t *mappable_end)
{
*gtt_total = intel_private.gtt_total_entries << PAGE_SHIFT;
*mappable_base = intel_private.gma_bus_addr;
*mappable_end = intel_private.gtt_mappable_entries << PAGE_SHIFT;
}
-EXPORT_SYMBOL(intel_gtt_get);
+EXPORT_SYMBOL(intel_gmch_gtt_get);
-void intel_gtt_chipset_flush(void)
+void intel_gmch_gtt_flush(void)
{
if (intel_private.driver->chipset_flush)
intel_private.driver->chipset_flush();
}
-EXPORT_SYMBOL(intel_gtt_chipset_flush);
+EXPORT_SYMBOL(intel_gmch_gtt_flush);
void intel_gmch_remove(void)
{
diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile
index c84a9cd8440d358c9d6e4caf05f7aef413be7c66..522ef9b4aff329625086f8ef5cf9ed9053a2f716 100644
--- a/drivers/gpu/drm/i915/Makefile
+++ b/drivers/gpu/drm/i915/Makefile
@@ -103,6 +103,7 @@ gt-y += \
gt/intel_gt_debugfs.o \
gt/intel_gt_engines_debugfs.o \
gt/intel_gt_irq.o \
+ gt/intel_gt_mcr.o \
gt/intel_gt_pm.o \
gt/intel_gt_pm_debugfs.o \
gt/intel_gt_pm_irq.o \
@@ -129,7 +130,7 @@ gt-y += \
gt/shmem_utils.o \
gt/sysfs_engines.o
# x86 intel-gtt module support
-gt-$(CONFIG_X86) += gt/intel_gt_gmch.o
+gt-$(CONFIG_X86) += gt/intel_ggtt_gmch.o
# autogenerated null render state
gt-y += \
gt/gen6_renderstate.o \
diff --git a/drivers/gpu/drm/i915/display/intel_dpt.c b/drivers/gpu/drm/i915/display/intel_dpt.c
index fb0e7e79e0cdacd9e49d34e4b1e9b784963fa5f1..ac587647e1f5015d393270a8aeeb7b360ef236b3 100644
--- a/drivers/gpu/drm/i915/display/intel_dpt.c
+++ b/drivers/gpu/drm/i915/display/intel_dpt.c
@@ -4,6 +4,7 @@
*/
#include "gem/i915_gem_domain.h"
+#include "gem/i915_gem_internal.h"
#include "gt/gen8_ppgtt.h"
#include "i915_drv.h"
@@ -127,8 +128,12 @@ struct i915_vma *intel_dpt_pin(struct i915_address_space *vm)
struct i915_vma *vma;
void __iomem *iomem;
struct i915_gem_ww_ctx ww;
+ u64 pin_flags = 0;
int err;
+ if (i915_gem_object_is_stolen(dpt->obj))
+ pin_flags |= PIN_MAPPABLE;
+
wakeref = intel_runtime_pm_get(&i915->runtime_pm);
atomic_inc(&i915->gpu_error.pending_fb_pin);
@@ -138,7 +143,7 @@ struct i915_vma *intel_dpt_pin(struct i915_address_space *vm)
continue;
vma = i915_gem_object_ggtt_pin_ww(dpt->obj, &ww, NULL, 0, 4096,
- HAS_LMEM(i915) ? 0 : PIN_MAPPABLE);
+ pin_flags);
if (IS_ERR(vma)) {
err = PTR_ERR(vma);
continue;
@@ -248,10 +253,13 @@ intel_dpt_create(struct intel_framebuffer *fb)
size = round_up(size * sizeof(gen8_pte_t), I915_GTT_PAGE_SIZE);
- if (HAS_LMEM(i915))
- dpt_obj = i915_gem_object_create_lmem(i915, size, I915_BO_ALLOC_CONTIGUOUS);
- else
+ dpt_obj = i915_gem_object_create_lmem(i915, size, I915_BO_ALLOC_CONTIGUOUS);
+ if (IS_ERR(dpt_obj) && i915_ggtt_has_aperture(to_gt(i915)->ggtt))
dpt_obj = i915_gem_object_create_stolen(i915, size);
+ if (IS_ERR(dpt_obj) && !HAS_LMEM(i915)) {
+ drm_dbg_kms(&i915->drm, "Allocating dpt from smem\n");
+ dpt_obj = i915_gem_object_create_internal(i915, size);
+ }
if (IS_ERR(dpt_obj))
return ERR_CAST(dpt_obj);
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c
index ab4c5ab28e4d9fbcd666d341a0d6934c3d2f96dd..dabdfe09f5e51438c7d9b203194316f48b71b1d9 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c
@@ -933,8 +933,9 @@ static int set_proto_ctx_param(struct drm_i915_file_private *fpriv,
case I915_CONTEXT_PARAM_PERSISTENCE:
if (args->size)
ret = -EINVAL;
- ret = proto_context_set_persistence(fpriv->dev_priv, pc,
- args->value);
+ else
+ ret = proto_context_set_persistence(fpriv->dev_priv, pc,
+ args->value);
break;
case I915_CONTEXT_PARAM_PROTECTED_CONTENT:
@@ -1367,7 +1368,8 @@ static struct intel_engine_cs *active_engine(struct intel_context *ce)
return engine;
}
-static void kill_engines(struct i915_gem_engines *engines, bool ban)
+static void
+kill_engines(struct i915_gem_engines *engines, bool exit, bool persistent)
{
struct i915_gem_engines_iter it;
struct intel_context *ce;
@@ -1381,9 +1383,15 @@ static void kill_engines(struct i915_gem_engines *engines, bool ban)
*/
for_each_gem_engine(ce, engines, it) {
struct intel_engine_cs *engine;
+ bool skip = false;
- if (ban && intel_context_ban(ce, NULL))
- continue;
+ if (exit)
+ skip = intel_context_set_exiting(ce);
+ else if (!persistent)
+ skip = intel_context_exit_nonpersistent(ce, NULL);
+
+ if (skip)
+ continue; /* Already marked. */
/*
* Check the current active state of this context; if we
@@ -1395,7 +1403,7 @@ static void kill_engines(struct i915_gem_engines *engines, bool ban)
engine = active_engine(ce);
/* First attempt to gracefully cancel the context */
- if (engine && !__cancel_engine(engine) && ban)
+ if (engine && !__cancel_engine(engine) && (exit || !persistent))
/*
* If we are unable to send a preemptive pulse to bump
* the context from the GPU, we have to resort to a full
@@ -1407,8 +1415,6 @@ static void kill_engines(struct i915_gem_engines *engines, bool ban)
static void kill_context(struct i915_gem_context *ctx)
{
- bool ban = (!i915_gem_context_is_persistent(ctx) ||
- !ctx->i915->params.enable_hangcheck);
struct i915_gem_engines *pos, *next;
spin_lock_irq(&ctx->stale.lock);
@@ -1421,7 +1427,8 @@ static void kill_context(struct i915_gem_context *ctx)
spin_unlock_irq(&ctx->stale.lock);
- kill_engines(pos, ban);
+ kill_engines(pos, !ctx->i915->params.enable_hangcheck,
+ i915_gem_context_is_persistent(ctx));
spin_lock_irq(&ctx->stale.lock);
GEM_BUG_ON(i915_sw_fence_signaled(&pos->fence));
@@ -1467,7 +1474,8 @@ static void engines_idle_release(struct i915_gem_context *ctx,
kill:
if (list_empty(&engines->link)) /* raced, already closed */
- kill_engines(engines, true);
+ kill_engines(engines, true,
+ i915_gem_context_is_persistent(ctx));
i915_sw_fence_commit(&engines->fence);
}
@@ -1875,6 +1883,7 @@ i915_gem_user_to_context_sseu(struct intel_gt *gt,
{
const struct sseu_dev_info *device = >->info.sseu;
struct drm_i915_private *i915 = gt->i915;
+ unsigned int dev_subslice_mask = intel_sseu_get_hsw_subslices(device, 0);
/* No zeros in any field. */
if (!user->slice_mask || !user->subslice_mask ||
@@ -1901,7 +1910,7 @@ i915_gem_user_to_context_sseu(struct intel_gt *gt,
if (user->slice_mask & ~device->slice_mask)
return -EINVAL;
- if (user->subslice_mask & ~device->subslice_mask[0])
+ if (user->subslice_mask & ~dev_subslice_mask)
return -EINVAL;
if (user->max_eus_per_subslice > device->max_eus_per_subslice)
@@ -1915,7 +1924,7 @@ i915_gem_user_to_context_sseu(struct intel_gt *gt,
/* Part specific restrictions. */
if (GRAPHICS_VER(i915) == 11) {
unsigned int hw_s = hweight8(device->slice_mask);
- unsigned int hw_ss_per_s = hweight8(device->subslice_mask[0]);
+ unsigned int hw_ss_per_s = hweight8(dev_subslice_mask);
unsigned int req_s = hweight8(context->slice_mask);
unsigned int req_ss = hweight8(context->subslice_mask);
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_domain.c b/drivers/gpu/drm/i915/gem/i915_gem_domain.c
index 3e5d6057b3ef91cf4a4a8d77cf13f06f1cf60361..1674b0c5802bf0500c6cce1e010f6fb59c8318fe 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_domain.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_domain.c
@@ -35,12 +35,12 @@ bool i915_gem_cpu_write_needs_clflush(struct drm_i915_gem_object *obj)
if (obj->cache_dirty)
return false;
- if (!(obj->cache_coherent & I915_BO_CACHE_COHERENT_FOR_WRITE))
- return true;
-
if (IS_DGFX(i915))
return false;
+ if (!(obj->cache_coherent & I915_BO_CACHE_COHERENT_FOR_WRITE))
+ return true;
+
/* Currently in use by HW (display engine)? Keep flushed. */
return i915_gem_object_is_framebuffer(obj);
}
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
index c326bd2b444fc50cb350a2e6d3ff8184e117d97c..30fe847c6664d3d9c70ce4fd8e8fed675191764f 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
@@ -999,7 +999,8 @@ static int eb_validate_vmas(struct i915_execbuffer *eb)
}
}
- err = dma_resv_reserve_fences(vma->obj->base.resv, 1);
+ /* Reserve enough slots to accommodate composite fences */
+ err = dma_resv_reserve_fences(vma->obj->base.resv, eb->num_batches);
if (err)
return err;
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
index 2e16e91a5a56b03dab1178614c010b062722ce30..4eed3dd90ba8bc75aaa030ae752d2b7403593090 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
@@ -670,17 +670,10 @@ i915_gem_object_create_shmem_from_data(struct drm_i915_private *dev_priv,
static int init_shmem(struct intel_memory_region *mem)
{
- int err;
-
- err = i915_gemfs_init(mem->i915);
- if (err) {
- DRM_NOTE("Unable to create a private tmpfs mount, hugepage support will be disabled(%d).\n",
- err);
- }
-
+ i915_gemfs_init(mem->i915);
intel_memory_region_set_name(mem, "system");
- return 0; /* Don't error, we can simply fallback to the kernel mnt */
+ return 0; /* We have fallback to the kernel mnt if gemfs init failed. */
}
static int release_shmem(struct intel_memory_region *mem)
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c b/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c
index 6a6ff98a87462b388f8af950fcc1b0282e656ade..1030053571a20aa8169faf428bc4ebe0152b2382 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c
@@ -36,7 +36,7 @@ static bool can_release_pages(struct drm_i915_gem_object *obj)
return swap_available() || obj->mm.madv == I915_MADV_DONTNEED;
}
-static int drop_pages(struct drm_i915_gem_object *obj,
+static bool drop_pages(struct drm_i915_gem_object *obj,
unsigned long shrink, bool trylock_vm)
{
unsigned long flags;
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_stolen.c b/drivers/gpu/drm/i915/gem/i915_gem_stolen.c
index 47b5e0e342abd550d575d8eed958e07977e61859..166d0a4b9e8c0c394c386960d731eac182795cdb 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_stolen.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_stolen.c
@@ -13,6 +13,8 @@
#include "gem/i915_gem_lmem.h"
#include "gem/i915_gem_region.h"
#include "gt/intel_gt.h"
+#include "gt/intel_gt_mcr.h"
+#include "gt/intel_gt_regs.h"
#include "gt/intel_region_lmem.h"
#include "i915_drv.h"
#include "i915_gem_stolen.h"
@@ -834,8 +836,8 @@ i915_gem_stolen_lmem_setup(struct drm_i915_private *i915, u16 type,
} else {
resource_size_t lmem_range;
- lmem_range = intel_gt_read_register(&i915->gt0, XEHPSDV_TILE0_ADDR_RANGE) & 0xFFFF;
- lmem_size = lmem_range >> XEHPSDV_TILE_LMEM_RANGE_SHIFT;
+ lmem_range = intel_gt_mcr_read_any(&i915->gt0, XEHP_TILE0_ADDR_RANGE) & 0xFFFF;
+ lmem_size = lmem_range >> XEHP_TILE_LMEM_RANGE_SHIFT;
lmem_size *= SZ_1G;
}
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_tiling.c b/drivers/gpu/drm/i915/gem/i915_gem_tiling.c
index 80ac0db1ae8caca6fffd65525de62d29ed952446..85518b28cd721bd4086c616444f3e5ba32b3397f 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_tiling.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_tiling.c
@@ -114,7 +114,7 @@ u32 i915_gem_fence_alignment(struct drm_i915_private *i915, u32 size,
return i915_gem_fence_size(i915, size, tiling, stride);
}
-/* Check pitch constriants for all chips & tiling formats */
+/* Check pitch constraints for all chips & tiling formats */
static bool
i915_tiling_ok(struct drm_i915_gem_object *obj,
unsigned int tiling, unsigned int stride)
diff --git a/drivers/gpu/drm/i915/gem/i915_gemfs.c b/drivers/gpu/drm/i915/gem/i915_gemfs.c
index ee87874e59dcc2150bd3295590ffd92ce6311cdd..46b9a17d6abc6e64a2e46f2e825746022faa842d 100644
--- a/drivers/gpu/drm/i915/gem/i915_gemfs.c
+++ b/drivers/gpu/drm/i915/gem/i915_gemfs.c
@@ -11,16 +11,11 @@
#include "i915_gemfs.h"
#include "i915_utils.h"
-int i915_gemfs_init(struct drm_i915_private *i915)
+void i915_gemfs_init(struct drm_i915_private *i915)
{
char huge_opt[] = "huge=within_size"; /* r/w */
struct file_system_type *type;
struct vfsmount *gemfs;
- char *opts;
-
- type = get_fs_type("tmpfs");
- if (!type)
- return -ENODEV;
/*
* By creating our own shmemfs mountpoint, we can pass in
@@ -28,30 +23,35 @@ int i915_gemfs_init(struct drm_i915_private *i915)
*
* One example, although it is probably better with a per-file
* control, is selecting huge page allocations ("huge=within_size").
- * However, we only do so to offset the overhead of iommu lookups
- * due to bandwidth issues (slow reads) on Broadwell+.
+ * However, we only do so on platforms which benefit from it, or to
+ * offset the overhead of iommu lookups, where with latter it is a net
+ * win even on platforms which would otherwise see some performance
+ * regressions such a slow reads issue on Broadwell and Skylake.
*/
- opts = NULL;
- if (i915_vtd_active(i915)) {
- if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) {
- opts = huge_opt;
- drm_info(&i915->drm,
- "Transparent Hugepage mode '%s'\n",
- opts);
- } else {
- drm_notice(&i915->drm,
- "Transparent Hugepage support is recommended for optimal performance when IOMMU is enabled!\n");
- }
- }
-
- gemfs = vfs_kern_mount(type, SB_KERNMOUNT, type->name, opts);
+ if (GRAPHICS_VER(i915) < 11 && !i915_vtd_active(i915))
+ return;
+
+ if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE))
+ goto err;
+
+ type = get_fs_type("tmpfs");
+ if (!type)
+ goto err;
+
+ gemfs = vfs_kern_mount(type, SB_KERNMOUNT, type->name, huge_opt);
if (IS_ERR(gemfs))
- return PTR_ERR(gemfs);
+ goto err;
i915->mm.gemfs = gemfs;
-
- return 0;
+ drm_info(&i915->drm, "Using Transparent Hugepages\n");
+ return;
+
+err:
+ drm_notice(&i915->drm,
+ "Transparent Hugepage support is recommended for optimal performance%s\n",
+ GRAPHICS_VER(i915) >= 11 ? " on this platform!" :
+ " when IOMMU is enabled!");
}
void i915_gemfs_fini(struct drm_i915_private *i915)
diff --git a/drivers/gpu/drm/i915/gem/i915_gemfs.h b/drivers/gpu/drm/i915/gem/i915_gemfs.h
index 2a1e59af3e4a1616b26964290e594b20acc8eee6..5d835e44c4f6eba6691557b14dad3f0945445194 100644
--- a/drivers/gpu/drm/i915/gem/i915_gemfs.h
+++ b/drivers/gpu/drm/i915/gem/i915_gemfs.h
@@ -9,8 +9,7 @@
struct drm_i915_private;
-int i915_gemfs_init(struct drm_i915_private *i915);
-
+void i915_gemfs_init(struct drm_i915_private *i915);
void i915_gemfs_fini(struct drm_i915_private *i915);
#endif
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c
index ddd0772fd82864e3af437df60bd183c691266c73..3cfc621ef363d2e097dc863b4941be578ff337e9 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c
@@ -6,6 +6,7 @@
#include "i915_selftest.h"
#include "gt/intel_context.h"
+#include "gt/intel_engine_regs.h"
#include "gt/intel_engine_user.h"
#include "gt/intel_gpu_commands.h"
#include "gt/intel_gt.h"
@@ -18,10 +19,71 @@
#include "huge_gem_object.h"
#include "mock_context.h"
+#define OW_SIZE 16 /* in bytes */
+#define F_SUBTILE_SIZE 64 /* in bytes */
+#define F_TILE_WIDTH 128 /* in bytes */
+#define F_TILE_HEIGHT 32 /* in pixels */
+#define F_SUBTILE_WIDTH OW_SIZE /* in bytes */
+#define F_SUBTILE_HEIGHT 4 /* in pixels */
+
+static int linear_x_y_to_ftiled_pos(int x, int y, u32 stride, int bpp)
+{
+ int tile_base;
+ int tile_x, tile_y;
+ int swizzle, subtile;
+ int pixel_size = bpp / 8;
+ int pos;
+
+ /*
+ * Subtile remapping for F tile. Note that map[a]==b implies map[b]==a
+ * so we can use the same table to tile and until.
+ */
+ static const u8 f_subtile_map[] = {
+ 0, 1, 2, 3, 8, 9, 10, 11,
+ 4, 5, 6, 7, 12, 13, 14, 15,
+ 16, 17, 18, 19, 24, 25, 26, 27,
+ 20, 21, 22, 23, 28, 29, 30, 31,
+ 32, 33, 34, 35, 40, 41, 42, 43,
+ 36, 37, 38, 39, 44, 45, 46, 47,
+ 48, 49, 50, 51, 56, 57, 58, 59,
+ 52, 53, 54, 55, 60, 61, 62, 63
+ };
+
+ x *= pixel_size;
+ /*
+ * Where does the 4k tile start (in bytes)? This is the same for Y and
+ * F so we can use the Y-tile algorithm to get to that point.
+ */
+ tile_base =
+ y / F_TILE_HEIGHT * stride * F_TILE_HEIGHT +
+ x / F_TILE_WIDTH * 4096;
+
+ /* Find pixel within tile */
+ tile_x = x % F_TILE_WIDTH;
+ tile_y = y % F_TILE_HEIGHT;
+
+ /* And figure out the subtile within the 4k tile */
+ subtile = tile_y / F_SUBTILE_HEIGHT * 8 + tile_x / F_SUBTILE_WIDTH;
+
+ /* Swizzle the subtile number according to the bspec diagram */
+ swizzle = f_subtile_map[subtile];
+
+ /* Calculate new position */
+ pos = tile_base +
+ swizzle * F_SUBTILE_SIZE +
+ tile_y % F_SUBTILE_HEIGHT * OW_SIZE +
+ tile_x % F_SUBTILE_WIDTH;
+
+ GEM_BUG_ON(!IS_ALIGNED(pos, pixel_size));
+
+ return pos / pixel_size * 4;
+}
+
enum client_tiling {
CLIENT_TILING_LINEAR,
CLIENT_TILING_X,
CLIENT_TILING_Y,
+ CLIENT_TILING_4,
CLIENT_NUM_TILING_TYPES
};
@@ -45,6 +107,36 @@ struct tiled_blits {
u32 height;
};
+static bool supports_x_tiling(const struct drm_i915_private *i915)
+{
+ int gen = GRAPHICS_VER(i915);
+
+ if (gen < 12)
+ return true;
+
+ if (!HAS_LMEM(i915) || IS_DG1(i915))
+ return false;
+
+ return true;
+}
+
+static bool fast_blit_ok(const struct blit_buffer *buf)
+{
+ int gen = GRAPHICS_VER(buf->vma->vm->i915);
+
+ if (gen < 9)
+ return false;
+
+ if (gen < 12)
+ return true;
+
+ /* filter out platforms with unsupported X-tile support in fastblit */
+ if (buf->tiling == CLIENT_TILING_X && !supports_x_tiling(buf->vma->vm->i915))
+ return false;
+
+ return true;
+}
+
static int prepare_blit(const struct tiled_blits *t,
struct blit_buffer *dst,
struct blit_buffer *src,
@@ -59,51 +151,103 @@ static int prepare_blit(const struct tiled_blits *t,
if (IS_ERR(cs))
return PTR_ERR(cs);
- *cs++ = MI_LOAD_REGISTER_IMM(1);
- *cs++ = i915_mmio_reg_offset(BCS_SWCTRL);
- cmd = (BCS_SRC_Y | BCS_DST_Y) << 16;
- if (src->tiling == CLIENT_TILING_Y)
- cmd |= BCS_SRC_Y;
- if (dst->tiling == CLIENT_TILING_Y)
- cmd |= BCS_DST_Y;
- *cs++ = cmd;
-
- cmd = MI_FLUSH_DW;
- if (ver >= 8)
- cmd++;
- *cs++ = cmd;
- *cs++ = 0;
- *cs++ = 0;
- *cs++ = 0;
-
- cmd = XY_SRC_COPY_BLT_CMD | BLT_WRITE_RGBA | (8 - 2);
- if (ver >= 8)
- cmd += 2;
-
- src_pitch = t->width * 4;
- if (src->tiling) {
- cmd |= XY_SRC_COPY_BLT_SRC_TILED;
- src_pitch /= 4;
- }
+ if (fast_blit_ok(dst) && fast_blit_ok(src)) {
+ struct intel_gt *gt = t->ce->engine->gt;
+ u32 src_tiles = 0, dst_tiles = 0;
+ u32 src_4t = 0, dst_4t = 0;
+
+ /* Need to program BLIT_CCTL if it is not done previously
+ * before using XY_FAST_COPY_BLT
+ */
+ *cs++ = MI_LOAD_REGISTER_IMM(1);
+ *cs++ = i915_mmio_reg_offset(BLIT_CCTL(t->ce->engine->mmio_base));
+ *cs++ = (BLIT_CCTL_SRC_MOCS(gt->mocs.uc_index) |
+ BLIT_CCTL_DST_MOCS(gt->mocs.uc_index));
+
+ src_pitch = t->width; /* in dwords */
+ if (src->tiling == CLIENT_TILING_4) {
+ src_tiles = XY_FAST_COPY_BLT_D0_SRC_TILE_MODE(YMAJOR);
+ src_4t = XY_FAST_COPY_BLT_D1_SRC_TILE4;
+ } else if (src->tiling == CLIENT_TILING_Y) {
+ src_tiles = XY_FAST_COPY_BLT_D0_SRC_TILE_MODE(YMAJOR);
+ } else if (src->tiling == CLIENT_TILING_X) {
+ src_tiles = XY_FAST_COPY_BLT_D0_SRC_TILE_MODE(TILE_X);
+ } else {
+ src_pitch *= 4; /* in bytes */
+ }
- dst_pitch = t->width * 4;
- if (dst->tiling) {
- cmd |= XY_SRC_COPY_BLT_DST_TILED;
- dst_pitch /= 4;
- }
+ dst_pitch = t->width; /* in dwords */
+ if (dst->tiling == CLIENT_TILING_4) {
+ dst_tiles = XY_FAST_COPY_BLT_D0_DST_TILE_MODE(YMAJOR);
+ dst_4t = XY_FAST_COPY_BLT_D1_DST_TILE4;
+ } else if (dst->tiling == CLIENT_TILING_Y) {
+ dst_tiles = XY_FAST_COPY_BLT_D0_DST_TILE_MODE(YMAJOR);
+ } else if (dst->tiling == CLIENT_TILING_X) {
+ dst_tiles = XY_FAST_COPY_BLT_D0_DST_TILE_MODE(TILE_X);
+ } else {
+ dst_pitch *= 4; /* in bytes */
+ }
- *cs++ = cmd;
- *cs++ = BLT_DEPTH_32 | BLT_ROP_SRC_COPY | dst_pitch;
- *cs++ = 0;
- *cs++ = t->height << 16 | t->width;
- *cs++ = lower_32_bits(dst->vma->node.start);
- if (use_64b_reloc)
+ *cs++ = GEN9_XY_FAST_COPY_BLT_CMD | (10 - 2) |
+ src_tiles | dst_tiles;
+ *cs++ = src_4t | dst_4t | BLT_DEPTH_32 | dst_pitch;
+ *cs++ = 0;
+ *cs++ = t->height << 16 | t->width;
+ *cs++ = lower_32_bits(dst->vma->node.start);
*cs++ = upper_32_bits(dst->vma->node.start);
- *cs++ = 0;
- *cs++ = src_pitch;
- *cs++ = lower_32_bits(src->vma->node.start);
- if (use_64b_reloc)
+ *cs++ = 0;
+ *cs++ = src_pitch;
+ *cs++ = lower_32_bits(src->vma->node.start);
*cs++ = upper_32_bits(src->vma->node.start);
+ } else {
+ if (ver >= 6) {
+ *cs++ = MI_LOAD_REGISTER_IMM(1);
+ *cs++ = i915_mmio_reg_offset(BCS_SWCTRL);
+ cmd = (BCS_SRC_Y | BCS_DST_Y) << 16;
+ if (src->tiling == CLIENT_TILING_Y)
+ cmd |= BCS_SRC_Y;
+ if (dst->tiling == CLIENT_TILING_Y)
+ cmd |= BCS_DST_Y;
+ *cs++ = cmd;
+
+ cmd = MI_FLUSH_DW;
+ if (ver >= 8)
+ cmd++;
+ *cs++ = cmd;
+ *cs++ = 0;
+ *cs++ = 0;
+ *cs++ = 0;
+ }
+
+ cmd = XY_SRC_COPY_BLT_CMD | BLT_WRITE_RGBA | (8 - 2);
+ if (ver >= 8)
+ cmd += 2;
+
+ src_pitch = t->width * 4;
+ if (src->tiling) {
+ cmd |= XY_SRC_COPY_BLT_SRC_TILED;
+ src_pitch /= 4;
+ }
+
+ dst_pitch = t->width * 4;
+ if (dst->tiling) {
+ cmd |= XY_SRC_COPY_BLT_DST_TILED;
+ dst_pitch /= 4;
+ }
+
+ *cs++ = cmd;
+ *cs++ = BLT_DEPTH_32 | BLT_ROP_SRC_COPY | dst_pitch;
+ *cs++ = 0;
+ *cs++ = t->height << 16 | t->width;
+ *cs++ = lower_32_bits(dst->vma->node.start);
+ if (use_64b_reloc)
+ *cs++ = upper_32_bits(dst->vma->node.start);
+ *cs++ = 0;
+ *cs++ = src_pitch;
+ *cs++ = lower_32_bits(src->vma->node.start);
+ if (use_64b_reloc)
+ *cs++ = upper_32_bits(src->vma->node.start);
+ }
*cs++ = MI_BATCH_BUFFER_END;
@@ -181,7 +325,13 @@ static int tiled_blits_create_buffers(struct tiled_blits *t,
t->buffers[i].vma = vma;
t->buffers[i].tiling =
- i915_prandom_u32_max_state(CLIENT_TILING_Y + 1, prng);
+ i915_prandom_u32_max_state(CLIENT_NUM_TILING_TYPES, prng);
+
+ /* Platforms support either TileY or Tile4, not both */
+ if (HAS_4TILE(i915) && t->buffers[i].tiling == CLIENT_TILING_Y)
+ t->buffers[i].tiling = CLIENT_TILING_4;
+ else if (!HAS_4TILE(i915) && t->buffers[i].tiling == CLIENT_TILING_4)
+ t->buffers[i].tiling = CLIENT_TILING_Y;
}
return 0;
@@ -206,7 +356,8 @@ static u64 swizzle_bit(unsigned int bit, u64 offset)
static u64 tiled_offset(const struct intel_gt *gt,
u64 v,
unsigned int stride,
- enum client_tiling tiling)
+ enum client_tiling tiling,
+ int x_pos, int y_pos)
{
unsigned int swizzle;
u64 x, y;
@@ -216,7 +367,12 @@ static u64 tiled_offset(const struct intel_gt *gt,
y = div64_u64_rem(v, stride, &x);
- if (tiling == CLIENT_TILING_X) {
+ if (tiling == CLIENT_TILING_4) {
+ v = linear_x_y_to_ftiled_pos(x_pos, y_pos, stride, 32);
+
+ /* no swizzling for f-tiling */
+ swizzle = I915_BIT_6_SWIZZLE_NONE;
+ } else if (tiling == CLIENT_TILING_X) {
v = div64_u64_rem(y, 8, &y) * stride * 8;
v += y * 512;
v += div64_u64_rem(x, 512, &x) << 12;
@@ -259,6 +415,7 @@ static const char *repr_tiling(enum client_tiling tiling)
case CLIENT_TILING_LINEAR: return "linear";
case CLIENT_TILING_X: return "X";
case CLIENT_TILING_Y: return "Y";
+ case CLIENT_TILING_4: return "F";
default: return "unknown";
}
}
@@ -284,7 +441,7 @@ static int verify_buffer(const struct tiled_blits *t,
} else {
u64 v = tiled_offset(buf->vma->vm->gt,
p * 4, t->width * 4,
- buf->tiling);
+ buf->tiling, x, y);
if (vaddr[v / sizeof(*vaddr)] != buf->start_val + p)
ret = -EINVAL;
@@ -504,6 +661,9 @@ static int tiled_blits_bounce(struct tiled_blits *t, struct rnd_state *prng)
if (err)
return err;
+ /* Simulating GTT eviction of the same buffer / layout */
+ t->buffers[2].tiling = t->buffers[0].tiling;
+
/* Reposition so that we overlap the old addresses, and slightly off */
err = tiled_blit(t,
&t->buffers[2], t->hole + t->align,
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c
index 93a67422ca3b133cba32398d75616720d481714b..c6ad67b90e8af2657f6b0c61011fd30bdecaa7d8 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c
@@ -212,7 +212,7 @@ static int __live_parallel_switch1(void *data)
i915_request_add(rq);
}
- if (i915_request_wait(rq, 0, HZ / 5) < 0)
+ if (i915_request_wait(rq, 0, HZ) < 0)
err = -ETIME;
i915_request_put(rq);
if (err)
diff --git a/drivers/gpu/drm/i915/gt/gen8_engine_cs.c b/drivers/gpu/drm/i915/gt/gen8_engine_cs.c
index 3e13960615bdecedc5507a5ac5c29fa8cad0435a..98645797962f59799a6863b2ef3e3307df78809d 100644
--- a/drivers/gpu/drm/i915/gt/gen8_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/gen8_engine_cs.c
@@ -197,8 +197,10 @@ int gen12_emit_flush_rcs(struct i915_request *rq, u32 mode)
flags |= PIPE_CONTROL_CS_STALL;
- if (engine->class == COMPUTE_CLASS)
- flags &= ~PIPE_CONTROL_3D_FLAGS;
+ if (!HAS_3D_PIPELINE(engine->i915))
+ flags &= ~PIPE_CONTROL_3D_ARCH_FLAGS;
+ else if (engine->class == COMPUTE_CLASS)
+ flags &= ~PIPE_CONTROL_3D_ENGINE_FLAGS;
cs = intel_ring_begin(rq, 6);
if (IS_ERR(cs))
@@ -227,8 +229,10 @@ int gen12_emit_flush_rcs(struct i915_request *rq, u32 mode)
flags |= PIPE_CONTROL_CS_STALL;
- if (engine->class == COMPUTE_CLASS)
- flags &= ~PIPE_CONTROL_3D_FLAGS;
+ if (!HAS_3D_PIPELINE(engine->i915))
+ flags &= ~PIPE_CONTROL_3D_ARCH_FLAGS;
+ else if (engine->class == COMPUTE_CLASS)
+ flags &= ~PIPE_CONTROL_3D_ENGINE_FLAGS;
if (!HAS_FLAT_CCS(rq->engine->i915))
count = 8 + 4;
@@ -272,7 +276,8 @@ int gen12_emit_flush_xcs(struct i915_request *rq, u32 mode)
if (!HAS_FLAT_CCS(rq->engine->i915) &&
(rq->engine->class == VIDEO_DECODE_CLASS ||
rq->engine->class == VIDEO_ENHANCEMENT_CLASS)) {
- aux_inv = rq->engine->mask & ~BIT(BCS0);
+ aux_inv = rq->engine->mask &
+ ~GENMASK(_BCS(I915_MAX_BCS - 1), BCS0);
if (aux_inv)
cmd += 4;
}
@@ -716,8 +721,10 @@ u32 *gen12_emit_fini_breadcrumb_rcs(struct i915_request *rq, u32 *cs)
/* Wa_1409600907 */
flags |= PIPE_CONTROL_DEPTH_STALL;
- if (rq->engine->class == COMPUTE_CLASS)
- flags &= ~PIPE_CONTROL_3D_FLAGS;
+ if (!HAS_3D_PIPELINE(rq->engine->i915))
+ flags &= ~PIPE_CONTROL_3D_ARCH_FLAGS;
+ else if (rq->engine->class == COMPUTE_CLASS)
+ flags &= ~PIPE_CONTROL_3D_ENGINE_FLAGS;
cs = gen12_emit_ggtt_write_rcs(cs,
rq->fence.seqno,
diff --git a/drivers/gpu/drm/i915/gt/intel_context.c b/drivers/gpu/drm/i915/gt/intel_context.c
index 4070cb5711d88f672ee3505d98177d74cc0af98c..654a092ed3d69c547704799a877b8d6095343670 100644
--- a/drivers/gpu/drm/i915/gt/intel_context.c
+++ b/drivers/gpu/drm/i915/gt/intel_context.c
@@ -601,6 +601,30 @@ u64 intel_context_get_avg_runtime_ns(struct intel_context *ce)
return avg;
}
+bool intel_context_ban(struct intel_context *ce, struct i915_request *rq)
+{
+ bool ret = intel_context_set_banned(ce);
+
+ trace_intel_context_ban(ce);
+
+ if (ce->ops->revoke)
+ ce->ops->revoke(ce, rq,
+ INTEL_CONTEXT_BANNED_PREEMPT_TIMEOUT_MS);
+
+ return ret;
+}
+
+bool intel_context_exit_nonpersistent(struct intel_context *ce,
+ struct i915_request *rq)
+{
+ bool ret = intel_context_set_exiting(ce);
+
+ if (ce->ops->revoke)
+ ce->ops->revoke(ce, rq, ce->engine->props.preempt_timeout_ms);
+
+ return ret;
+}
+
#if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
#include "selftest_context.c"
#endif
diff --git a/drivers/gpu/drm/i915/gt/intel_context.h b/drivers/gpu/drm/i915/gt/intel_context.h
index b7d3214d2cdd8a4d933308159101797720ecbf35..8e2d70630c49e82c456bf9499b0da5deb952ceda 100644
--- a/drivers/gpu/drm/i915/gt/intel_context.h
+++ b/drivers/gpu/drm/i915/gt/intel_context.h
@@ -25,6 +25,8 @@
##__VA_ARGS__); \
} while (0)
+#define INTEL_CONTEXT_BANNED_PREEMPT_TIMEOUT_MS (1)
+
struct i915_gem_ww_ctx;
void intel_context_init(struct intel_context *ce,
@@ -309,18 +311,27 @@ static inline bool intel_context_set_banned(struct intel_context *ce)
return test_and_set_bit(CONTEXT_BANNED, &ce->flags);
}
-static inline bool intel_context_ban(struct intel_context *ce,
- struct i915_request *rq)
+bool intel_context_ban(struct intel_context *ce, struct i915_request *rq);
+
+static inline bool intel_context_is_schedulable(const struct intel_context *ce)
{
- bool ret = intel_context_set_banned(ce);
+ return !test_bit(CONTEXT_EXITING, &ce->flags) &&
+ !test_bit(CONTEXT_BANNED, &ce->flags);
+}
- trace_intel_context_ban(ce);
- if (ce->ops->ban)
- ce->ops->ban(ce, rq);
+static inline bool intel_context_is_exiting(const struct intel_context *ce)
+{
+ return test_bit(CONTEXT_EXITING, &ce->flags);
+}
- return ret;
+static inline bool intel_context_set_exiting(struct intel_context *ce)
+{
+ return test_and_set_bit(CONTEXT_EXITING, &ce->flags);
}
+bool intel_context_exit_nonpersistent(struct intel_context *ce,
+ struct i915_request *rq);
+
static inline bool
intel_context_force_single_submission(const struct intel_context *ce)
{
diff --git a/drivers/gpu/drm/i915/gt/intel_context_types.h b/drivers/gpu/drm/i915/gt/intel_context_types.h
index 09f82545789f194b305cbadd42305d82d66b22d4..d2d75d9c0c8dd5e832f5e0015da9bdff5360a266 100644
--- a/drivers/gpu/drm/i915/gt/intel_context_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_context_types.h
@@ -40,7 +40,8 @@ struct intel_context_ops {
int (*alloc)(struct intel_context *ce);
- void (*ban)(struct intel_context *ce, struct i915_request *rq);
+ void (*revoke)(struct intel_context *ce, struct i915_request *rq,
+ unsigned int preempt_timeout_ms);
int (*pre_pin)(struct intel_context *ce, struct i915_gem_ww_ctx *ww, void **vaddr);
int (*pin)(struct intel_context *ce, void *vaddr);
@@ -122,6 +123,7 @@ struct intel_context {
#define CONTEXT_GUC_INIT 10
#define CONTEXT_PERMA_PIN 11
#define CONTEXT_IS_PARKING 12
+#define CONTEXT_EXITING 13
struct {
u64 timeout_us;
diff --git a/drivers/gpu/drm/i915/gt/intel_engine.h b/drivers/gpu/drm/i915/gt/intel_engine.h
index 1431f1e9dbee76b475ce4c93f96ae1dc3210fd6c..04e435bce79bdfc731b0f4bf834e3bd06381e2da 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine.h
@@ -201,6 +201,8 @@ int intel_ring_submission_setup(struct intel_engine_cs *engine);
int intel_engine_stop_cs(struct intel_engine_cs *engine);
void intel_engine_cancel_stop_cs(struct intel_engine_cs *engine);
+void intel_engine_wait_for_pending_mi_fw(struct intel_engine_cs *engine);
+
void intel_engine_set_hwsp_writemask(struct intel_engine_cs *engine, u32 mask);
u64 intel_engine_get_active_head(const struct intel_engine_cs *engine);
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
index 14c6ddbbfde8b65586da0030669db5fa266cac01..283870c659911b8b8cbf8f73f9bb5e6789663b45 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
@@ -21,8 +21,9 @@
#include "intel_engine_user.h"
#include "intel_execlists_submission.h"
#include "intel_gt.h"
-#include "intel_gt_requests.h"
+#include "intel_gt_mcr.h"
#include "intel_gt_pm.h"
+#include "intel_gt_requests.h"
#include "intel_lrc.h"
#include "intel_lrc_reg.h"
#include "intel_reset.h"
@@ -71,6 +72,62 @@ static const struct engine_info intel_engines[] = {
{ .graphics_ver = 6, .base = BLT_RING_BASE }
},
},
+ [BCS1] = {
+ .class = COPY_ENGINE_CLASS,
+ .instance = 1,
+ .mmio_bases = {
+ { .graphics_ver = 12, .base = XEHPC_BCS1_RING_BASE }
+ },
+ },
+ [BCS2] = {
+ .class = COPY_ENGINE_CLASS,
+ .instance = 2,
+ .mmio_bases = {
+ { .graphics_ver = 12, .base = XEHPC_BCS2_RING_BASE }
+ },
+ },
+ [BCS3] = {
+ .class = COPY_ENGINE_CLASS,
+ .instance = 3,
+ .mmio_bases = {
+ { .graphics_ver = 12, .base = XEHPC_BCS3_RING_BASE }
+ },
+ },
+ [BCS4] = {
+ .class = COPY_ENGINE_CLASS,
+ .instance = 4,
+ .mmio_bases = {
+ { .graphics_ver = 12, .base = XEHPC_BCS4_RING_BASE }
+ },
+ },
+ [BCS5] = {
+ .class = COPY_ENGINE_CLASS,
+ .instance = 5,
+ .mmio_bases = {
+ { .graphics_ver = 12, .base = XEHPC_BCS5_RING_BASE }
+ },
+ },
+ [BCS6] = {
+ .class = COPY_ENGINE_CLASS,
+ .instance = 6,
+ .mmio_bases = {
+ { .graphics_ver = 12, .base = XEHPC_BCS6_RING_BASE }
+ },
+ },
+ [BCS7] = {
+ .class = COPY_ENGINE_CLASS,
+ .instance = 7,
+ .mmio_bases = {
+ { .graphics_ver = 12, .base = XEHPC_BCS7_RING_BASE }
+ },
+ },
+ [BCS8] = {
+ .class = COPY_ENGINE_CLASS,
+ .instance = 8,
+ .mmio_bases = {
+ { .graphics_ver = 12, .base = XEHPC_BCS8_RING_BASE }
+ },
+ },
[VCS0] = {
.class = VIDEO_DECODE_CLASS,
.instance = 0,
@@ -334,6 +391,14 @@ static u32 get_reset_domain(u8 ver, enum intel_engine_id id)
static const u32 engine_reset_domains[] = {
[RCS0] = GEN11_GRDOM_RENDER,
[BCS0] = GEN11_GRDOM_BLT,
+ [BCS1] = XEHPC_GRDOM_BLT1,
+ [BCS2] = XEHPC_GRDOM_BLT2,
+ [BCS3] = XEHPC_GRDOM_BLT3,
+ [BCS4] = XEHPC_GRDOM_BLT4,
+ [BCS5] = XEHPC_GRDOM_BLT5,
+ [BCS6] = XEHPC_GRDOM_BLT6,
+ [BCS7] = XEHPC_GRDOM_BLT7,
+ [BCS8] = XEHPC_GRDOM_BLT8,
[VCS0] = GEN11_GRDOM_MEDIA,
[VCS1] = GEN11_GRDOM_MEDIA2,
[VCS2] = GEN11_GRDOM_MEDIA3,
@@ -610,8 +675,8 @@ static void engine_mask_apply_compute_fuses(struct intel_gt *gt)
if (GRAPHICS_VER_FULL(i915) < IP_VER(12, 50))
return;
- ccs_mask = intel_slicemask_from_dssmask(intel_sseu_get_compute_subslices(&info->sseu),
- ss_per_ccs);
+ ccs_mask = intel_slicemask_from_xehp_dssmask(info->sseu.compute_subslice_mask,
+ ss_per_ccs);
/*
* If all DSS in a quadrant are fused off, the corresponding CCS
* engine is not available for use.
@@ -622,6 +687,34 @@ static void engine_mask_apply_compute_fuses(struct intel_gt *gt)
}
}
+static void engine_mask_apply_copy_fuses(struct intel_gt *gt)
+{
+ struct drm_i915_private *i915 = gt->i915;
+ struct intel_gt_info *info = >->info;
+ unsigned long meml3_mask;
+ unsigned long quad;
+
+ meml3_mask = intel_uncore_read(gt->uncore, GEN10_MIRROR_FUSE3);
+ meml3_mask = REG_FIELD_GET(GEN12_MEML3_EN_MASK, meml3_mask);
+
+ /*
+ * Link Copy engines may be fused off according to meml3_mask. Each
+ * bit is a quad that houses 2 Link Copy and two Sub Copy engines.
+ */
+ for_each_clear_bit(quad, &meml3_mask, GEN12_MAX_MSLICES) {
+ unsigned int instance = quad * 2 + 1;
+ intel_engine_mask_t mask = GENMASK(_BCS(instance + 1),
+ _BCS(instance));
+
+ if (mask & info->engine_mask) {
+ drm_dbg(&i915->drm, "bcs%u fused off\n", instance);
+ drm_dbg(&i915->drm, "bcs%u fused off\n", instance + 1);
+
+ info->engine_mask &= ~mask;
+ }
+ }
+}
+
/*
* Determine which engines are fused off in our particular hardware.
* Note that we have a catch-22 situation where we need to be able to access
@@ -704,6 +797,7 @@ static intel_engine_mask_t init_engine_mask(struct intel_gt *gt)
GEM_BUG_ON(vebox_mask != VEBOX_MASK(gt));
engine_mask_apply_compute_fuses(gt);
+ engine_mask_apply_copy_fuses(gt);
return info->engine_mask;
}
@@ -1282,10 +1376,10 @@ static int __intel_engine_stop_cs(struct intel_engine_cs *engine,
intel_uncore_write_fw(uncore, mode, _MASKED_BIT_ENABLE(STOP_RING));
/*
- * Wa_22011802037 : gen12, Prior to doing a reset, ensure CS is
+ * Wa_22011802037 : gen11, gen12, Prior to doing a reset, ensure CS is
* stopped, set ring stop bit and prefetch disable bit to halt CS
*/
- if (GRAPHICS_VER(engine->i915) == 12)
+ if (IS_GRAPHICS_VER(engine->i915, 11, 12))
intel_uncore_write_fw(uncore, RING_MODE_GEN7(engine->mmio_base),
_MASKED_BIT_ENABLE(GEN12_GFX_PREFETCH_DISABLE));
@@ -1308,6 +1402,18 @@ int intel_engine_stop_cs(struct intel_engine_cs *engine)
return -ENODEV;
ENGINE_TRACE(engine, "\n");
+ /*
+ * TODO: Find out why occasionally stopping the CS times out. Seen
+ * especially with gem_eio tests.
+ *
+ * Occasionally trying to stop the cs times out, but does not adversely
+ * affect functionality. The timeout is set as a config parameter that
+ * defaults to 100ms. In most cases the follow up operation is to wait
+ * for pending MI_FORCE_WAKES. The assumption is that this timeout is
+ * sufficient for any pending MI_FORCEWAKEs to complete. Once root
+ * caused, the caller must check and handle the return from this
+ * function.
+ */
if (__intel_engine_stop_cs(engine, 1000, stop_timeout(engine))) {
ENGINE_TRACE(engine,
"timed out on STOP_RING -> IDLE; HEAD:%04x, TAIL:%04x\n",
@@ -1334,12 +1440,76 @@ void intel_engine_cancel_stop_cs(struct intel_engine_cs *engine)
ENGINE_WRITE_FW(engine, RING_MI_MODE, _MASKED_BIT_DISABLE(STOP_RING));
}
-static u32
-read_subslice_reg(const struct intel_engine_cs *engine,
- int slice, int subslice, i915_reg_t reg)
+static u32 __cs_pending_mi_force_wakes(struct intel_engine_cs *engine)
+{
+ static const i915_reg_t _reg[I915_NUM_ENGINES] = {
+ [RCS0] = MSG_IDLE_CS,
+ [BCS0] = MSG_IDLE_BCS,
+ [VCS0] = MSG_IDLE_VCS0,
+ [VCS1] = MSG_IDLE_VCS1,
+ [VCS2] = MSG_IDLE_VCS2,
+ [VCS3] = MSG_IDLE_VCS3,
+ [VCS4] = MSG_IDLE_VCS4,
+ [VCS5] = MSG_IDLE_VCS5,
+ [VCS6] = MSG_IDLE_VCS6,
+ [VCS7] = MSG_IDLE_VCS7,
+ [VECS0] = MSG_IDLE_VECS0,
+ [VECS1] = MSG_IDLE_VECS1,
+ [VECS2] = MSG_IDLE_VECS2,
+ [VECS3] = MSG_IDLE_VECS3,
+ [CCS0] = MSG_IDLE_CS,
+ [CCS1] = MSG_IDLE_CS,
+ [CCS2] = MSG_IDLE_CS,
+ [CCS3] = MSG_IDLE_CS,
+ };
+ u32 val;
+
+ if (!_reg[engine->id].reg) {
+ drm_err(&engine->i915->drm,
+ "MSG IDLE undefined for engine id %u\n", engine->id);
+ return 0;
+ }
+
+ val = intel_uncore_read(engine->uncore, _reg[engine->id]);
+
+ /* bits[29:25] & bits[13:9] >> shift */
+ return (val & (val >> 16) & MSG_IDLE_FW_MASK) >> MSG_IDLE_FW_SHIFT;
+}
+
+static void __gpm_wait_for_fw_complete(struct intel_gt *gt, u32 fw_mask)
{
- return intel_uncore_read_with_mcr_steering(engine->uncore, reg,
- slice, subslice);
+ int ret;
+
+ /* Ensure GPM receives fw up/down after CS is stopped */
+ udelay(1);
+
+ /* Wait for forcewake request to complete in GPM */
+ ret = __intel_wait_for_register_fw(gt->uncore,
+ GEN9_PWRGT_DOMAIN_STATUS,
+ fw_mask, fw_mask, 5000, 0, NULL);
+
+ /* Ensure CS receives fw ack from GPM */
+ udelay(1);
+
+ if (ret)
+ GT_TRACE(gt, "Failed to complete pending forcewake %d\n", ret);
+}
+
+/*
+ * Wa_22011802037:gen12: In addition to stopping the cs, we need to wait for any
+ * pending MI_FORCE_WAKEUP requests that the CS has initiated to complete. The
+ * pending status is indicated by bits[13:9] (masked by bits[29:25]) in the
+ * MSG_IDLE register. There's one MSG_IDLE register per reset domain. Since we
+ * are concerned only with the gt reset here, we use a logical OR of pending
+ * forcewakeups from all reset domains and then wait for them to complete by
+ * querying PWRGT_DOMAIN_STATUS.
+ */
+void intel_engine_wait_for_pending_mi_fw(struct intel_engine_cs *engine)
+{
+ u32 fw_pending = __cs_pending_mi_force_wakes(engine);
+
+ if (fw_pending)
+ __gpm_wait_for_fw_complete(engine->gt, fw_pending);
}
/* NB: please notice the memset */
@@ -1375,28 +1545,33 @@ void intel_engine_get_instdone(const struct intel_engine_cs *engine,
if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 50)) {
for_each_instdone_gslice_dss_xehp(i915, sseu, iter, slice, subslice) {
instdone->sampler[slice][subslice] =
- read_subslice_reg(engine, slice, subslice,
- GEN7_SAMPLER_INSTDONE);
+ intel_gt_mcr_read(engine->gt,
+ GEN7_SAMPLER_INSTDONE,
+ slice, subslice);
instdone->row[slice][subslice] =
- read_subslice_reg(engine, slice, subslice,
- GEN7_ROW_INSTDONE);
+ intel_gt_mcr_read(engine->gt,
+ GEN7_ROW_INSTDONE,
+ slice, subslice);
}
} else {
for_each_instdone_slice_subslice(i915, sseu, slice, subslice) {
instdone->sampler[slice][subslice] =
- read_subslice_reg(engine, slice, subslice,
- GEN7_SAMPLER_INSTDONE);
+ intel_gt_mcr_read(engine->gt,
+ GEN7_SAMPLER_INSTDONE,
+ slice, subslice);
instdone->row[slice][subslice] =
- read_subslice_reg(engine, slice, subslice,
- GEN7_ROW_INSTDONE);
+ intel_gt_mcr_read(engine->gt,
+ GEN7_ROW_INSTDONE,
+ slice, subslice);
}
}
if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 55)) {
for_each_instdone_gslice_dss_xehp(i915, sseu, iter, slice, subslice)
instdone->geom_svg[slice][subslice] =
- read_subslice_reg(engine, slice, subslice,
- XEHPG_INSTDONE_GEOM_SVG);
+ intel_gt_mcr_read(engine->gt,
+ XEHPG_INSTDONE_GEOM_SVG,
+ slice, subslice);
}
} else if (GRAPHICS_VER(i915) >= 7) {
instdone->instdone =
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_regs.h b/drivers/gpu/drm/i915/gt/intel_engine_regs.h
index 75a0c55c5aa5dd134bfc237399f1ec267be0235d..889f0df3940b8f5c7c5628c9777faba4c9af94a6 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_regs.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine_regs.h
@@ -8,6 +8,7 @@
#include "i915_reg_defs.h"
+#define RING_EXCC(base) _MMIO((base) + 0x28)
#define RING_TAIL(base) _MMIO((base) + 0x30)
#define TAIL_ADDR 0x001FFFF8
#define RING_HEAD(base) _MMIO((base) + 0x34)
@@ -133,6 +134,8 @@
(REG_FIELD_PREP(BLIT_CCTL_DST_MOCS_MASK, (dst) << 1) | \
REG_FIELD_PREP(BLIT_CCTL_SRC_MOCS_MASK, (src) << 1))
+#define RING_CSCMDOP(base) _MMIO((base) + 0x20c)
+
/*
* CMD_CCTL read/write fields take a MOCS value and _not_ a table index.
* The lsb of each can be considered a separate enabling bit for encryption.
@@ -149,6 +152,7 @@
REG_FIELD_PREP(CMD_CCTL_READ_OVERRIDE_MASK, (read) << 1))
#define RING_PREDICATE_RESULT(base) _MMIO((base) + 0x3b8) /* gen12+ */
+
#define MI_PREDICATE_RESULT_2(base) _MMIO((base) + 0x3bc)
#define LOWER_SLICE_ENABLED (1 << 0)
#define LOWER_SLICE_DISABLED (0 << 0)
@@ -172,6 +176,7 @@
#define CTX_CTRL_ENGINE_CTX_SAVE_INHIBIT REG_BIT(2)
#define CTX_CTRL_INHIBIT_SYN_CTX_SWITCH REG_BIT(3)
#define GEN12_CTX_CTRL_OAR_CONTEXT_ENABLE REG_BIT(8)
+#define RING_CTX_SR_CTL(base) _MMIO((base) + 0x244)
#define RING_SEMA_WAIT_POLL(base) _MMIO((base) + 0x24c)
#define GEN8_RING_PDP_UDW(base, n) _MMIO((base) + 0x270 + (n) * 8 + 4)
#define GEN8_RING_PDP_LDW(base, n) _MMIO((base) + 0x270 + (n) * 8)
@@ -196,6 +201,7 @@
#define RING_CTX_TIMESTAMP(base) _MMIO((base) + 0x3a8) /* gen8+ */
#define RING_PREDICATE_RESULT(base) _MMIO((base) + 0x3b8)
#define RING_FORCE_TO_NONPRIV(base, i) _MMIO(((base) + 0x4D0) + (i) * 4)
+#define RING_FORCE_TO_NONPRIV_DENY REG_BIT(30)
#define RING_FORCE_TO_NONPRIV_ADDRESS_MASK REG_GENMASK(25, 2)
#define RING_FORCE_TO_NONPRIV_ACCESS_RW (0 << 28) /* CFL+ & Gen11+ */
#define RING_FORCE_TO_NONPRIV_ACCESS_RD (1 << 28)
@@ -208,7 +214,9 @@
#define RING_FORCE_TO_NONPRIV_RANGE_64 (3 << 0)
#define RING_FORCE_TO_NONPRIV_RANGE_MASK (3 << 0)
#define RING_FORCE_TO_NONPRIV_MASK_VALID \
- (RING_FORCE_TO_NONPRIV_RANGE_MASK | RING_FORCE_TO_NONPRIV_ACCESS_MASK)
+ (RING_FORCE_TO_NONPRIV_RANGE_MASK | \
+ RING_FORCE_TO_NONPRIV_ACCESS_MASK | \
+ RING_FORCE_TO_NONPRIV_DENY)
#define RING_MAX_NONPRIV_SLOTS 12
#define RING_EXECLIST_SQ_CONTENTS(base) _MMIO((base) + 0x510)
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_types.h b/drivers/gpu/drm/i915/gt/intel_engine_types.h
index 298f2cc7a879f402fb6bf732179e1aab905ad5b6..2286f96f5f8772aff10d3d8c78e46f6fdd2f2a33 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine_types.h
@@ -35,7 +35,7 @@
#define OTHER_CLASS 4
#define COMPUTE_CLASS 5
#define MAX_ENGINE_CLASS 5
-#define MAX_ENGINE_INSTANCE 7
+#define MAX_ENGINE_INSTANCE 8
#define I915_MAX_SLICES 3
#define I915_MAX_SUBSLICES 8
@@ -99,6 +99,7 @@ struct i915_ctx_workarounds {
#define I915_MAX_SFC (I915_MAX_VCS / 2)
#define I915_MAX_CCS 4
#define I915_MAX_RCS 1
+#define I915_MAX_BCS 9
/*
* Engine IDs definitions.
@@ -107,6 +108,15 @@ struct i915_ctx_workarounds {
enum intel_engine_id {
RCS0 = 0,
BCS0,
+ BCS1,
+ BCS2,
+ BCS3,
+ BCS4,
+ BCS5,
+ BCS6,
+ BCS7,
+ BCS8,
+#define _BCS(n) (BCS0 + (n))
VCS0,
VCS1,
VCS2,
diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
index aa0d2bbbbcc41e3011a8baabf1098f00b912a136..4b909cb88cdfb7b7422bd5cc1629f536f9422032 100644
--- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
+++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
@@ -480,9 +480,9 @@ __execlists_schedule_in(struct i915_request *rq)
if (unlikely(intel_context_is_closed(ce) &&
!intel_engine_has_heartbeat(engine)))
- intel_context_set_banned(ce);
+ intel_context_set_exiting(ce);
- if (unlikely(intel_context_is_banned(ce) || bad_request(rq)))
+ if (unlikely(!intel_context_is_schedulable(ce) || bad_request(rq)))
reset_active(rq, engine);
if (IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM))
@@ -661,6 +661,16 @@ static inline void execlists_schedule_out(struct i915_request *rq)
i915_request_put(rq);
}
+static u32 map_i915_prio_to_lrc_desc_prio(int prio)
+{
+ if (prio > I915_PRIORITY_NORMAL)
+ return GEN12_CTX_PRIORITY_HIGH;
+ else if (prio < I915_PRIORITY_NORMAL)
+ return GEN12_CTX_PRIORITY_LOW;
+ else
+ return GEN12_CTX_PRIORITY_NORMAL;
+}
+
static u64 execlists_update_context(struct i915_request *rq)
{
struct intel_context *ce = rq->context;
@@ -669,7 +679,7 @@ static u64 execlists_update_context(struct i915_request *rq)
desc = ce->lrc.desc;
if (rq->engine->flags & I915_ENGINE_HAS_EU_PRIORITY)
- desc |= lrc_desc_priority(rq_prio(rq));
+ desc |= map_i915_prio_to_lrc_desc_prio(rq_prio(rq));
/*
* WaIdleLiteRestore:bdw,skl
@@ -1233,7 +1243,7 @@ static unsigned long active_preempt_timeout(struct intel_engine_cs *engine,
/* Force a fast reset for terminated contexts (ignoring sysfs!) */
if (unlikely(intel_context_is_banned(rq->context) || bad_request(rq)))
- return 1;
+ return INTEL_CONTEXT_BANNED_PREEMPT_TIMEOUT_MS;
return READ_ONCE(engine->props.preempt_timeout_ms);
}
@@ -2958,6 +2968,13 @@ static void execlists_reset_prepare(struct intel_engine_cs *engine)
ring_set_paused(engine, 1);
intel_engine_stop_cs(engine);
+ /*
+ * Wa_22011802037:gen11/gen12: In addition to stopping the cs, we need
+ * to wait for any pending mi force wakeups
+ */
+ if (IS_GRAPHICS_VER(engine->i915, 11, 12))
+ intel_engine_wait_for_pending_mi_fw(engine);
+
engine->execlists.reset_ccid = active_ccid(engine);
}
diff --git a/drivers/gpu/drm/i915/gt/intel_ggtt.c b/drivers/gpu/drm/i915/gt/intel_ggtt.c
index e6b2eb122ad7ed60c5b6a0bb92dbaa7d9a86453c..15a915bb4088e9e7e5601688791c8c0043e84049 100644
--- a/drivers/gpu/drm/i915/gt/intel_ggtt.c
+++ b/drivers/gpu/drm/i915/gt/intel_ggtt.c
@@ -3,16 +3,18 @@
* Copyright © 2020 Intel Corporation
*/
-#include <linux/types.h>
#include <asm/set_memory.h>
#include <asm/smp.h>
+#include <linux/types.h>
+#include <linux/stop_machine.h>
#include <drm/i915_drm.h>
+#include <drm/intel-gtt.h>
#include "gem/i915_gem_lmem.h"
+#include "intel_ggtt_gmch.h"
#include "intel_gt.h"
-#include "intel_gt_gmch.h"
#include "intel_gt_regs.h"
#include "i915_drv.h"
#include "i915_scatterlist.h"
@@ -22,6 +24,13 @@
#include "intel_gtt.h"
#include "gen8_ppgtt.h"
+static inline bool suspend_retains_ptes(struct i915_address_space *vm)
+{
+ return GRAPHICS_VER(vm->i915) >= 8 &&
+ !HAS_LMEM(vm->i915) &&
+ vm->is_ggtt;
+}
+
static void i915_ggtt_color_adjust(const struct drm_mm_node *node,
unsigned long color,
u64 *start,
@@ -93,6 +102,23 @@ int i915_ggtt_init_hw(struct drm_i915_private *i915)
return 0;
}
+/*
+ * Return the value of the last GGTT pte cast to an u64, if
+ * the system is supposed to retain ptes across resume. 0 otherwise.
+ */
+static u64 read_last_pte(struct i915_address_space *vm)
+{
+ struct i915_ggtt *ggtt = i915_vm_to_ggtt(vm);
+ gen8_pte_t __iomem *ptep;
+
+ if (!suspend_retains_ptes(vm))
+ return 0;
+
+ GEM_BUG_ON(GRAPHICS_VER(vm->i915) < 8);
+ ptep = (typeof(ptep))ggtt->gsm + (ggtt_total_entries(ggtt) - 1);
+ return readq(ptep);
+}
+
/**
* i915_ggtt_suspend_vm - Suspend the memory mappings for a GGTT or DPT VM
* @vm: The VM to suspend the mappings for
@@ -156,7 +182,10 @@ void i915_ggtt_suspend_vm(struct i915_address_space *vm)
i915_gem_object_unlock(obj);
}
- vm->clear_range(vm, 0, vm->total);
+ if (!suspend_retains_ptes(vm))
+ vm->clear_range(vm, 0, vm->total);
+ else
+ i915_vm_to_ggtt(vm)->probed_pte = read_last_pte(vm);
vm->skip_pte_rewrite = save_skip_rewrite;
@@ -181,7 +210,7 @@ void gen6_ggtt_invalidate(struct i915_ggtt *ggtt)
spin_unlock_irq(&uncore->lock);
}
-void gen8_ggtt_invalidate(struct i915_ggtt *ggtt)
+static void gen8_ggtt_invalidate(struct i915_ggtt *ggtt)
{
struct intel_uncore *uncore = ggtt->vm.gt->uncore;
@@ -218,11 +247,232 @@ u64 gen8_ggtt_pte_encode(dma_addr_t addr,
return pte;
}
+static void gen8_set_pte(void __iomem *addr, gen8_pte_t pte)
+{
+ writeq(pte, addr);
+}
+
+static void gen8_ggtt_insert_page(struct i915_address_space *vm,
+ dma_addr_t addr,
+ u64 offset,
+ enum i915_cache_level level,
+ u32 flags)
+{
+ struct i915_ggtt *ggtt = i915_vm_to_ggtt(vm);
+ gen8_pte_t __iomem *pte =
+ (gen8_pte_t __iomem *)ggtt->gsm + offset / I915_GTT_PAGE_SIZE;
+
+ gen8_set_pte(pte, gen8_ggtt_pte_encode(addr, level, flags));
+
+ ggtt->invalidate(ggtt);
+}
+
+static void gen8_ggtt_insert_entries(struct i915_address_space *vm,
+ struct i915_vma_resource *vma_res,
+ enum i915_cache_level level,
+ u32 flags)
+{
+ const gen8_pte_t pte_encode = gen8_ggtt_pte_encode(0, level, flags);
+ struct i915_ggtt *ggtt = i915_vm_to_ggtt(vm);
+ gen8_pte_t __iomem *gte;
+ gen8_pte_t __iomem *end;
+ struct sgt_iter iter;
+ dma_addr_t addr;
+
+ /*
+ * Note that we ignore PTE_READ_ONLY here. The caller must be careful
+ * not to allow the user to override access to a read only page.
+ */
+
+ gte = (gen8_pte_t __iomem *)ggtt->gsm;
+ gte += vma_res->start / I915_GTT_PAGE_SIZE;
+ end = gte + vma_res->node_size / I915_GTT_PAGE_SIZE;
+
+ for_each_sgt_daddr(addr, iter, vma_res->bi.pages)
+ gen8_set_pte(gte++, pte_encode | addr);
+ GEM_BUG_ON(gte > end);
+
+ /* Fill the allocated but "unused" space beyond the end of the buffer */
+ while (gte < end)
+ gen8_set_pte(gte++, vm->scratch[0]->encode);
+
+ /*
+ * We want to flush the TLBs only after we're certain all the PTE
+ * updates have finished.
+ */
+ ggtt->invalidate(ggtt);
+}
+
+static void gen6_ggtt_insert_page(struct i915_address_space *vm,
+ dma_addr_t addr,
+ u64 offset,
+ enum i915_cache_level level,
+ u32 flags)
+{
+ struct i915_ggtt *ggtt = i915_vm_to_ggtt(vm);
+ gen6_pte_t __iomem *pte =
+ (gen6_pte_t __iomem *)ggtt->gsm + offset / I915_GTT_PAGE_SIZE;
+
+ iowrite32(vm->pte_encode(addr, level, flags), pte);
+
+ ggtt->invalidate(ggtt);
+}
+
+/*
+ * Binds an object into the global gtt with the specified cache level.
+ * The object will be accessible to the GPU via commands whose operands
+ * reference offsets within the global GTT as well as accessible by the GPU
+ * through the GMADR mapped BAR (i915->mm.gtt->gtt).
+ */
+static void gen6_ggtt_insert_entries(struct i915_address_space *vm,
+ struct i915_vma_resource *vma_res,
+ enum i915_cache_level level,
+ u32 flags)
+{
+ struct i915_ggtt *ggtt = i915_vm_to_ggtt(vm);
+ gen6_pte_t __iomem *gte;
+ gen6_pte_t __iomem *end;
+ struct sgt_iter iter;
+ dma_addr_t addr;
+
+ gte = (gen6_pte_t __iomem *)ggtt->gsm;
+ gte += vma_res->start / I915_GTT_PAGE_SIZE;
+ end = gte + vma_res->node_size / I915_GTT_PAGE_SIZE;
+
+ for_each_sgt_daddr(addr, iter, vma_res->bi.pages)
+ iowrite32(vm->pte_encode(addr, level, flags), gte++);
+ GEM_BUG_ON(gte > end);
+
+ /* Fill the allocated but "unused" space beyond the end of the buffer */
+ while (gte < end)
+ iowrite32(vm->scratch[0]->encode, gte++);
+
+ /*
+ * We want to flush the TLBs only after we're certain all the PTE
+ * updates have finished.
+ */
+ ggtt->invalidate(ggtt);
+}
+
+static void nop_clear_range(struct i915_address_space *vm,
+ u64 start, u64 length)
+{
+}
+
+static void gen8_ggtt_clear_range(struct i915_address_space *vm,
+ u64 start, u64 length)
+{
+ struct i915_ggtt *ggtt = i915_vm_to_ggtt(vm);
+ unsigned int first_entry = start / I915_GTT_PAGE_SIZE;
+ unsigned int num_entries = length / I915_GTT_PAGE_SIZE;
+ const gen8_pte_t scratch_pte = vm->scratch[0]->encode;
+ gen8_pte_t __iomem *gtt_base =
+ (gen8_pte_t __iomem *)ggtt->gsm + first_entry;
+ const int max_entries = ggtt_total_entries(ggtt) - first_entry;
+ int i;
+
+ if (WARN(num_entries > max_entries,
+ "First entry = %d; Num entries = %d (max=%d)\n",
+ first_entry, num_entries, max_entries))
+ num_entries = max_entries;
+
+ for (i = 0; i < num_entries; i++)
+ gen8_set_pte(>t_base[i], scratch_pte);
+}
+
+static void bxt_vtd_ggtt_wa(struct i915_address_space *vm)
+{
+ /*
+ * Make sure the internal GAM fifo has been cleared of all GTT
+ * writes before exiting stop_machine(). This guarantees that
+ * any aperture accesses waiting to start in another process
+ * cannot back up behind the GTT writes causing a hang.
+ * The register can be any arbitrary GAM register.
+ */
+ intel_uncore_posting_read_fw(vm->gt->uncore, GFX_FLSH_CNTL_GEN6);
+}
+
+struct insert_page {
+ struct i915_address_space *vm;
+ dma_addr_t addr;
+ u64 offset;
+ enum i915_cache_level level;
+};
+
+static int bxt_vtd_ggtt_insert_page__cb(void *_arg)
+{
+ struct insert_page *arg = _arg;
+
+ gen8_ggtt_insert_page(arg->vm, arg->addr, arg->offset, arg->level, 0);
+ bxt_vtd_ggtt_wa(arg->vm);
+
+ return 0;
+}
+
+static void bxt_vtd_ggtt_insert_page__BKL(struct i915_address_space *vm,
+ dma_addr_t addr,
+ u64 offset,
+ enum i915_cache_level level,
+ u32 unused)
+{
+ struct insert_page arg = { vm, addr, offset, level };
+
+ stop_machine(bxt_vtd_ggtt_insert_page__cb, &arg, NULL);
+}
+
+struct insert_entries {
+ struct i915_address_space *vm;
+ struct i915_vma_resource *vma_res;
+ enum i915_cache_level level;
+ u32 flags;
+};
+
+static int bxt_vtd_ggtt_insert_entries__cb(void *_arg)
+{
+ struct insert_entries *arg = _arg;
+
+ gen8_ggtt_insert_entries(arg->vm, arg->vma_res, arg->level, arg->flags);
+ bxt_vtd_ggtt_wa(arg->vm);
+
+ return 0;
+}
+
+static void bxt_vtd_ggtt_insert_entries__BKL(struct i915_address_space *vm,
+ struct i915_vma_resource *vma_res,
+ enum i915_cache_level level,
+ u32 flags)
+{
+ struct insert_entries arg = { vm, vma_res, level, flags };
+
+ stop_machine(bxt_vtd_ggtt_insert_entries__cb, &arg, NULL);
+}
+
+static void gen6_ggtt_clear_range(struct i915_address_space *vm,
+ u64 start, u64 length)
+{
+ struct i915_ggtt *ggtt = i915_vm_to_ggtt(vm);
+ unsigned int first_entry = start / I915_GTT_PAGE_SIZE;
+ unsigned int num_entries = length / I915_GTT_PAGE_SIZE;
+ gen6_pte_t scratch_pte, __iomem *gtt_base =
+ (gen6_pte_t __iomem *)ggtt->gsm + first_entry;
+ const int max_entries = ggtt_total_entries(ggtt) - first_entry;
+ int i;
+
+ if (WARN(num_entries > max_entries,
+ "First entry = %d; Num entries = %d (max=%d)\n",
+ first_entry, num_entries, max_entries))
+ num_entries = max_entries;
+
+ scratch_pte = vm->scratch[0]->encode;
+ for (i = 0; i < num_entries; i++)
+ iowrite32(scratch_pte, >t_base[i]);
+}
+
void intel_ggtt_bind_vma(struct i915_address_space *vm,
- struct i915_vm_pt_stash *stash,
- struct i915_vma_resource *vma_res,
- enum i915_cache_level cache_level,
- u32 flags)
+ struct i915_vm_pt_stash *stash,
+ struct i915_vma_resource *vma_res,
+ enum i915_cache_level cache_level,
+ u32 flags)
{
u32 pte_flags;
@@ -243,7 +493,7 @@ void intel_ggtt_bind_vma(struct i915_address_space *vm,
}
void intel_ggtt_unbind_vma(struct i915_address_space *vm,
- struct i915_vma_resource *vma_res)
+ struct i915_vma_resource *vma_res)
{
vm->clear_range(vm, vma_res->start, vma_res->vma_size);
}
@@ -299,6 +549,8 @@ static int init_ggtt(struct i915_ggtt *ggtt)
struct drm_mm_node *entry;
int ret;
+ ggtt->pte_lost = true;
+
/*
* GuC requires all resources that we're sharing with it to be placed in
* non-WOPCM memory. If GuC is not present or not in use we still need a
@@ -560,12 +812,326 @@ void i915_ggtt_driver_late_release(struct drm_i915_private *i915)
dma_resv_fini(&ggtt->vm._resv);
}
-struct resource intel_pci_resource(struct pci_dev *pdev, int bar)
+static unsigned int gen6_get_total_gtt_size(u16 snb_gmch_ctl)
+{
+ snb_gmch_ctl >>= SNB_GMCH_GGMS_SHIFT;
+ snb_gmch_ctl &= SNB_GMCH_GGMS_MASK;
+ return snb_gmch_ctl << 20;
+}
+
+static unsigned int gen8_get_total_gtt_size(u16 bdw_gmch_ctl)
+{
+ bdw_gmch_ctl >>= BDW_GMCH_GGMS_SHIFT;
+ bdw_gmch_ctl &= BDW_GMCH_GGMS_MASK;
+ if (bdw_gmch_ctl)
+ bdw_gmch_ctl = 1 << bdw_gmch_ctl;
+
+#ifdef CONFIG_X86_32
+ /* Limit 32b platforms to a 2GB GGTT: 4 << 20 / pte size * I915_GTT_PAGE_SIZE */
+ if (bdw_gmch_ctl > 4)
+ bdw_gmch_ctl = 4;
+#endif
+
+ return bdw_gmch_ctl << 20;
+}
+
+static unsigned int chv_get_total_gtt_size(u16 gmch_ctrl)
+{
+ gmch_ctrl >>= SNB_GMCH_GGMS_SHIFT;
+ gmch_ctrl &= SNB_GMCH_GGMS_MASK;
+
+ if (gmch_ctrl)
+ return 1 << (20 + gmch_ctrl);
+
+ return 0;
+}
+
+static unsigned int gen6_gttmmadr_size(struct drm_i915_private *i915)
+{
+ /*
+ * GEN6: GTTMMADR size is 4MB and GTTADR starts at 2MB offset
+ * GEN8: GTTMMADR size is 16MB and GTTADR starts at 8MB offset
+ */
+ GEM_BUG_ON(GRAPHICS_VER(i915) < 6);
+ return (GRAPHICS_VER(i915) < 8) ? SZ_4M : SZ_16M;
+}
+
+static unsigned int gen6_gttadr_offset(struct drm_i915_private *i915)
+{
+ return gen6_gttmmadr_size(i915) / 2;
+}
+
+static int ggtt_probe_common(struct i915_ggtt *ggtt, u64 size)
+{
+ struct drm_i915_private *i915 = ggtt->vm.i915;
+ struct pci_dev *pdev = to_pci_dev(i915->drm.dev);
+ phys_addr_t phys_addr;
+ u32 pte_flags;
+ int ret;
+
+ GEM_WARN_ON(pci_resource_len(pdev, 0) != gen6_gttmmadr_size(i915));
+ phys_addr = pci_resource_start(pdev, 0) + gen6_gttadr_offset(i915);
+
+ /*
+ * On BXT+/ICL+ writes larger than 64 bit to the GTT pagetable range
+ * will be dropped. For WC mappings in general we have 64 byte burst
+ * writes when the WC buffer is flushed, so we can't use it, but have to
+ * resort to an uncached mapping. The WC issue is easily caught by the
+ * readback check when writing GTT PTE entries.
+ */
+ if (IS_GEN9_LP(i915) || GRAPHICS_VER(i915) >= 11)
+ ggtt->gsm = ioremap(phys_addr, size);
+ else
+ ggtt->gsm = ioremap_wc(phys_addr, size);
+ if (!ggtt->gsm) {
+ drm_err(&i915->drm, "Failed to map the ggtt page table\n");
+ return -ENOMEM;
+ }
+
+ kref_init(&ggtt->vm.resv_ref);
+ ret = setup_scratch_page(&ggtt->vm);
+ if (ret) {
+ drm_err(&i915->drm, "Scratch setup failed\n");
+ /* iounmap will also get called at remove, but meh */
+ iounmap(ggtt->gsm);
+ return ret;
+ }
+
+ pte_flags = 0;
+ if (i915_gem_object_is_lmem(ggtt->vm.scratch[0]))
+ pte_flags |= PTE_LM;
+
+ ggtt->vm.scratch[0]->encode =
+ ggtt->vm.pte_encode(px_dma(ggtt->vm.scratch[0]),
+ I915_CACHE_NONE, pte_flags);
+
+ return 0;
+}
+
+static void gen6_gmch_remove(struct i915_address_space *vm)
+{
+ struct i915_ggtt *ggtt = i915_vm_to_ggtt(vm);
+
+ iounmap(ggtt->gsm);
+ free_scratch(vm);
+}
+
+static struct resource pci_resource(struct pci_dev *pdev, int bar)
{
return (struct resource)DEFINE_RES_MEM(pci_resource_start(pdev, bar),
pci_resource_len(pdev, bar));
}
+static int gen8_gmch_probe(struct i915_ggtt *ggtt)
+{
+ struct drm_i915_private *i915 = ggtt->vm.i915;
+ struct pci_dev *pdev = to_pci_dev(i915->drm.dev);
+ unsigned int size;
+ u16 snb_gmch_ctl;
+
+ if (!HAS_LMEM(i915)) {
+ ggtt->gmadr = pci_resource(pdev, 2);
+ ggtt->mappable_end = resource_size(&ggtt->gmadr);
+ }
+
+ pci_read_config_word(pdev, SNB_GMCH_CTRL, &snb_gmch_ctl);
+ if (IS_CHERRYVIEW(i915))
+ size = chv_get_total_gtt_size(snb_gmch_ctl);
+ else
+ size = gen8_get_total_gtt_size(snb_gmch_ctl);
+
+ ggtt->vm.alloc_pt_dma = alloc_pt_dma;
+ ggtt->vm.alloc_scratch_dma = alloc_pt_dma;
+ ggtt->vm.lmem_pt_obj_flags = I915_BO_ALLOC_PM_EARLY;
+
+ ggtt->vm.total = (size / sizeof(gen8_pte_t)) * I915_GTT_PAGE_SIZE;
+ ggtt->vm.cleanup = gen6_gmch_remove;
+ ggtt->vm.insert_page = gen8_ggtt_insert_page;
+ ggtt->vm.clear_range = nop_clear_range;
+ if (intel_scanout_needs_vtd_wa(i915))
+ ggtt->vm.clear_range = gen8_ggtt_clear_range;
+
+ ggtt->vm.insert_entries = gen8_ggtt_insert_entries;
+
+ /*
+ * Serialize GTT updates with aperture access on BXT if VT-d is on,
+ * and always on CHV.
+ */
+ if (intel_vm_no_concurrent_access_wa(i915)) {
+ ggtt->vm.insert_entries = bxt_vtd_ggtt_insert_entries__BKL;
+ ggtt->vm.insert_page = bxt_vtd_ggtt_insert_page__BKL;
+
+ /*
+ * Calling stop_machine() version of GGTT update function
+ * at error capture/reset path will raise lockdep warning.
+ * Allow calling gen8_ggtt_insert_* directly at reset path
+ * which is safe from parallel GGTT updates.
+ */
+ ggtt->vm.raw_insert_page = gen8_ggtt_insert_page;
+ ggtt->vm.raw_insert_entries = gen8_ggtt_insert_entries;
+
+ ggtt->vm.bind_async_flags =
+ I915_VMA_GLOBAL_BIND | I915_VMA_LOCAL_BIND;
+ }
+
+ ggtt->invalidate = gen8_ggtt_invalidate;
+
+ ggtt->vm.vma_ops.bind_vma = intel_ggtt_bind_vma;
+ ggtt->vm.vma_ops.unbind_vma = intel_ggtt_unbind_vma;
+
+ ggtt->vm.pte_encode = gen8_ggtt_pte_encode;
+
+ setup_private_pat(ggtt->vm.gt->uncore);
+
+ return ggtt_probe_common(ggtt, size);
+}
+
+static u64 snb_pte_encode(dma_addr_t addr,
+ enum i915_cache_level level,
+ u32 flags)
+{
+ gen6_pte_t pte = GEN6_PTE_ADDR_ENCODE(addr) | GEN6_PTE_VALID;
+
+ switch (level) {
+ case I915_CACHE_L3_LLC:
+ case I915_CACHE_LLC:
+ pte |= GEN6_PTE_CACHE_LLC;
+ break;
+ case I915_CACHE_NONE:
+ pte |= GEN6_PTE_UNCACHED;
+ break;
+ default:
+ MISSING_CASE(level);
+ }
+
+ return pte;
+}
+
+static u64 ivb_pte_encode(dma_addr_t addr,
+ enum i915_cache_level level,
+ u32 flags)
+{
+ gen6_pte_t pte = GEN6_PTE_ADDR_ENCODE(addr) | GEN6_PTE_VALID;
+
+ switch (level) {
+ case I915_CACHE_L3_LLC:
+ pte |= GEN7_PTE_CACHE_L3_LLC;
+ break;
+ case I915_CACHE_LLC:
+ pte |= GEN6_PTE_CACHE_LLC;
+ break;
+ case I915_CACHE_NONE:
+ pte |= GEN6_PTE_UNCACHED;
+ break;
+ default:
+ MISSING_CASE(level);
+ }
+
+ return pte;
+}
+
+static u64 byt_pte_encode(dma_addr_t addr,
+ enum i915_cache_level level,
+ u32 flags)
+{
+ gen6_pte_t pte = GEN6_PTE_ADDR_ENCODE(addr) | GEN6_PTE_VALID;
+
+ if (!(flags & PTE_READ_ONLY))
+ pte |= BYT_PTE_WRITEABLE;
+
+ if (level != I915_CACHE_NONE)
+ pte |= BYT_PTE_SNOOPED_BY_CPU_CACHES;
+
+ return pte;
+}
+
+static u64 hsw_pte_encode(dma_addr_t addr,
+ enum i915_cache_level level,
+ u32 flags)
+{
+ gen6_pte_t pte = HSW_PTE_ADDR_ENCODE(addr) | GEN6_PTE_VALID;
+
+ if (level != I915_CACHE_NONE)
+ pte |= HSW_WB_LLC_AGE3;
+
+ return pte;
+}
+
+static u64 iris_pte_encode(dma_addr_t addr,
+ enum i915_cache_level level,
+ u32 flags)
+{
+ gen6_pte_t pte = HSW_PTE_ADDR_ENCODE(addr) | GEN6_PTE_VALID;
+
+ switch (level) {
+ case I915_CACHE_NONE:
+ break;
+ case I915_CACHE_WT:
+ pte |= HSW_WT_ELLC_LLC_AGE3;
+ break;
+ default:
+ pte |= HSW_WB_ELLC_LLC_AGE3;
+ break;
+ }
+
+ return pte;
+}
+
+static int gen6_gmch_probe(struct i915_ggtt *ggtt)
+{
+ struct drm_i915_private *i915 = ggtt->vm.i915;
+ struct pci_dev *pdev = to_pci_dev(i915->drm.dev);
+ unsigned int size;
+ u16 snb_gmch_ctl;
+
+ ggtt->gmadr = pci_resource(pdev, 2);
+ ggtt->mappable_end = resource_size(&ggtt->gmadr);
+
+ /*
+ * 64/512MB is the current min/max we actually know of, but this is
+ * just a coarse sanity check.
+ */
+ if (ggtt->mappable_end < (64 << 20) ||
+ ggtt->mappable_end > (512 << 20)) {
+ drm_err(&i915->drm, "Unknown GMADR size (%pa)\n",
+ &ggtt->mappable_end);
+ return -ENXIO;
+ }
+
+ pci_read_config_word(pdev, SNB_GMCH_CTRL, &snb_gmch_ctl);
+
+ size = gen6_get_total_gtt_size(snb_gmch_ctl);
+ ggtt->vm.total = (size / sizeof(gen6_pte_t)) * I915_GTT_PAGE_SIZE;
+
+ ggtt->vm.alloc_pt_dma = alloc_pt_dma;
+ ggtt->vm.alloc_scratch_dma = alloc_pt_dma;
+
+ ggtt->vm.clear_range = nop_clear_range;
+ if (!HAS_FULL_PPGTT(i915) || intel_scanout_needs_vtd_wa(i915))
+ ggtt->vm.clear_range = gen6_ggtt_clear_range;
+ ggtt->vm.insert_page = gen6_ggtt_insert_page;
+ ggtt->vm.insert_entries = gen6_ggtt_insert_entries;
+ ggtt->vm.cleanup = gen6_gmch_remove;
+
+ ggtt->invalidate = gen6_ggtt_invalidate;
+
+ if (HAS_EDRAM(i915))
+ ggtt->vm.pte_encode = iris_pte_encode;
+ else if (IS_HASWELL(i915))
+ ggtt->vm.pte_encode = hsw_pte_encode;
+ else if (IS_VALLEYVIEW(i915))
+ ggtt->vm.pte_encode = byt_pte_encode;
+ else if (GRAPHICS_VER(i915) >= 7)
+ ggtt->vm.pte_encode = ivb_pte_encode;
+ else
+ ggtt->vm.pte_encode = snb_pte_encode;
+
+ ggtt->vm.vma_ops.bind_vma = intel_ggtt_bind_vma;
+ ggtt->vm.vma_ops.unbind_vma = intel_ggtt_unbind_vma;
+
+ return ggtt_probe_common(ggtt, size);
+}
+
static int ggtt_probe_hw(struct i915_ggtt *ggtt, struct intel_gt *gt)
{
struct drm_i915_private *i915 = gt->i915;
@@ -576,12 +1142,13 @@ static int ggtt_probe_hw(struct i915_ggtt *ggtt, struct intel_gt *gt)
ggtt->vm.dma = i915->drm.dev;
dma_resv_init(&ggtt->vm._resv);
- if (GRAPHICS_VER(i915) <= 5)
- ret = intel_gt_gmch_gen5_probe(ggtt);
- else if (GRAPHICS_VER(i915) < 8)
- ret = intel_gt_gmch_gen6_probe(ggtt);
+ if (GRAPHICS_VER(i915) >= 8)
+ ret = gen8_gmch_probe(ggtt);
+ else if (GRAPHICS_VER(i915) >= 6)
+ ret = gen6_gmch_probe(ggtt);
else
- ret = intel_gt_gmch_gen8_probe(ggtt);
+ ret = intel_ggtt_gmch_probe(ggtt);
+
if (ret) {
dma_resv_fini(&ggtt->vm._resv);
return ret;
@@ -635,7 +1202,10 @@ int i915_ggtt_probe_hw(struct drm_i915_private *i915)
int i915_ggtt_enable_hw(struct drm_i915_private *i915)
{
- return intel_gt_gmch_gen5_enable_hw(i915);
+ if (GRAPHICS_VER(i915) < 6)
+ return intel_ggtt_gmch_enable_hw(i915);
+
+ return 0;
}
void i915_ggtt_enable_guc(struct i915_ggtt *ggtt)
@@ -675,11 +1245,20 @@ bool i915_ggtt_resume_vm(struct i915_address_space *vm)
{
struct i915_vma *vma;
bool write_domain_objs = false;
+ bool retained_ptes;
drm_WARN_ON(&vm->i915->drm, !vm->is_ggtt && !vm->is_dpt);
- /* First fill our portion of the GTT with scratch pages */
- vm->clear_range(vm, 0, vm->total);
+ /*
+ * First fill our portion of the GTT with scratch pages if
+ * they were not retained across suspend.
+ */
+ retained_ptes = suspend_retains_ptes(vm) &&
+ !i915_vm_to_ggtt(vm)->pte_lost &&
+ !GEM_WARN_ON(i915_vm_to_ggtt(vm)->probed_pte != read_last_pte(vm));
+
+ if (!retained_ptes)
+ vm->clear_range(vm, 0, vm->total);
/* clflush objects bound into the GGTT and rebind them. */
list_for_each_entry(vma, &vm->bound_list, vm_link) {
@@ -688,9 +1267,10 @@ bool i915_ggtt_resume_vm(struct i915_address_space *vm)
atomic_read(&vma->flags) & I915_VMA_BIND_MASK;
GEM_BUG_ON(!was_bound);
- vma->ops->bind_vma(vm, NULL, vma->resource,
- obj ? obj->cache_level : 0,
- was_bound);
+ if (!retained_ptes)
+ vma->ops->bind_vma(vm, NULL, vma->resource,
+ obj ? obj->cache_level : 0,
+ was_bound);
if (obj) { /* only used during resume => exclusive access */
write_domain_objs |= fetch_and_zero(&obj->write_domain);
obj->read_domains |= I915_GEM_DOMAIN_GTT;
@@ -718,3 +1298,8 @@ void i915_ggtt_resume(struct i915_ggtt *ggtt)
intel_ggtt_restore_fences(ggtt);
}
+
+void i915_ggtt_mark_pte_lost(struct drm_i915_private *i915, bool val)
+{
+ to_gt(i915)->ggtt->pte_lost = val;
+}
diff --git a/drivers/gpu/drm/i915/gt/intel_ggtt_gmch.c b/drivers/gpu/drm/i915/gt/intel_ggtt_gmch.c
new file mode 100644
index 0000000000000000000000000000000000000000..4e2163a1aa469fc3228ed5abb5ccb989b7f19f51
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/intel_ggtt_gmch.c
@@ -0,0 +1,132 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2022 Intel Corporation
+ */
+
+#include "intel_ggtt_gmch.h"
+
+#include <drm/intel-gtt.h>
+#include <drm/i915_drm.h>
+
+#include <linux/agp_backend.h>
+
+#include "i915_drv.h"
+#include "i915_utils.h"
+#include "intel_gtt.h"
+#include "intel_gt_regs.h"
+#include "intel_gt.h"
+
+static void gmch_ggtt_insert_page(struct i915_address_space *vm,
+ dma_addr_t addr,
+ u64 offset,
+ enum i915_cache_level cache_level,
+ u32 unused)
+{
+ unsigned int flags = (cache_level == I915_CACHE_NONE) ?
+ AGP_USER_MEMORY : AGP_USER_CACHED_MEMORY;
+
+ intel_gmch_gtt_insert_page(addr, offset >> PAGE_SHIFT, flags);
+}
+
+static void gmch_ggtt_insert_entries(struct i915_address_space *vm,
+ struct i915_vma_resource *vma_res,
+ enum i915_cache_level cache_level,
+ u32 unused)
+{
+ unsigned int flags = (cache_level == I915_CACHE_NONE) ?
+ AGP_USER_MEMORY : AGP_USER_CACHED_MEMORY;
+
+ intel_gmch_gtt_insert_sg_entries(vma_res->bi.pages, vma_res->start >> PAGE_SHIFT,
+ flags);
+}
+
+static void gmch_ggtt_invalidate(struct i915_ggtt *ggtt)
+{
+ intel_gmch_gtt_flush();
+}
+
+static void gmch_ggtt_clear_range(struct i915_address_space *vm,
+ u64 start, u64 length)
+{
+ intel_gmch_gtt_clear_range(start >> PAGE_SHIFT, length >> PAGE_SHIFT);
+}
+
+static void gmch_ggtt_remove(struct i915_address_space *vm)
+{
+ intel_gmch_remove();
+}
+
+/*
+ * Certain Gen5 chipsets require idling the GPU before unmapping anything from
+ * the GTT when VT-d is enabled.
+ */
+static bool needs_idle_maps(struct drm_i915_private *i915)
+{
+ /*
+ * Query intel_iommu to see if we need the workaround. Presumably that
+ * was loaded first.
+ */
+ if (!i915_vtd_active(i915))
+ return false;
+
+ if (GRAPHICS_VER(i915) == 5 && IS_MOBILE(i915))
+ return true;
+
+ return false;
+}
+
+int intel_ggtt_gmch_probe(struct i915_ggtt *ggtt)
+{
+ struct drm_i915_private *i915 = ggtt->vm.i915;
+ phys_addr_t gmadr_base;
+ int ret;
+
+ ret = intel_gmch_probe(i915->bridge_dev, to_pci_dev(i915->drm.dev), NULL);
+ if (!ret) {
+ drm_err(&i915->drm, "failed to set up gmch\n");
+ return -EIO;
+ }
+
+ intel_gmch_gtt_get(&ggtt->vm.total, &gmadr_base, &ggtt->mappable_end);
+
+ ggtt->gmadr =
+ (struct resource)DEFINE_RES_MEM(gmadr_base, ggtt->mappable_end);
+
+ ggtt->vm.alloc_pt_dma = alloc_pt_dma;
+ ggtt->vm.alloc_scratch_dma = alloc_pt_dma;
+
+ if (needs_idle_maps(i915)) {
+ drm_notice(&i915->drm,
+ "Flushing DMA requests before IOMMU unmaps; performance may be degraded\n");
+ ggtt->do_idle_maps = true;
+ }
+
+ ggtt->vm.insert_page = gmch_ggtt_insert_page;
+ ggtt->vm.insert_entries = gmch_ggtt_insert_entries;
+ ggtt->vm.clear_range = gmch_ggtt_clear_range;
+ ggtt->vm.cleanup = gmch_ggtt_remove;
+
+ ggtt->invalidate = gmch_ggtt_invalidate;
+
+ ggtt->vm.vma_ops.bind_vma = intel_ggtt_bind_vma;
+ ggtt->vm.vma_ops.unbind_vma = intel_ggtt_unbind_vma;
+
+ if (unlikely(ggtt->do_idle_maps))
+ drm_notice(&i915->drm,
+ "Applying Ironlake quirks for intel_iommu\n");
+
+ return 0;
+}
+
+int intel_ggtt_gmch_enable_hw(struct drm_i915_private *i915)
+{
+ if (!intel_gmch_enable_gtt())
+ return -EIO;
+
+ return 0;
+}
+
+void intel_ggtt_gmch_flush(void)
+{
+ intel_gmch_gtt_flush();
+}
diff --git a/drivers/gpu/drm/i915/gt/intel_ggtt_gmch.h b/drivers/gpu/drm/i915/gt/intel_ggtt_gmch.h
new file mode 100644
index 0000000000000000000000000000000000000000..370bf321b4e26e66e06067b95193e00598f56865
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/intel_ggtt_gmch.h
@@ -0,0 +1,27 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2022 Intel Corporation
+ */
+
+#ifndef __INTEL_GGTT_GMCH_H__
+#define __INTEL_GGTT_GMCH_H__
+
+#include "intel_gtt.h"
+
+/* For x86 platforms */
+#if IS_ENABLED(CONFIG_X86)
+
+void intel_ggtt_gmch_flush(void);
+int intel_ggtt_gmch_enable_hw(struct drm_i915_private *i915);
+int intel_ggtt_gmch_probe(struct i915_ggtt *ggtt);
+
+/* Stubs for non-x86 platforms */
+#else
+
+static inline void intel_ggtt_gmch_flush(void) { }
+static inline int intel_ggtt_gmch_enable_hw(struct drm_i915_private *i915) { return -ENODEV; }
+static inline int intel_ggtt_gmch_probe(struct i915_ggtt *ggtt) { return -ENODEV; }
+
+#endif
+
+#endif /* __INTEL_GGTT_GMCH_H__ */
diff --git a/drivers/gpu/drm/i915/gt/intel_gpu_commands.h b/drivers/gpu/drm/i915/gt/intel_gpu_commands.h
index 556bca3be80403ee4d35deb86aa04f07ba02d5c7..d4e9702d3c8e7f06c007bc8cfb031672aa81c9bb 100644
--- a/drivers/gpu/drm/i915/gt/intel_gpu_commands.h
+++ b/drivers/gpu/drm/i915/gt/intel_gpu_commands.h
@@ -236,6 +236,28 @@
#define XY_FAST_COLOR_BLT_DW 16
#define XY_FAST_COLOR_BLT_MOCS_MASK GENMASK(27, 21)
#define XY_FAST_COLOR_BLT_MEM_TYPE_SHIFT 31
+
+#define XY_FAST_COPY_BLT_D0_SRC_TILING_MASK REG_GENMASK(21, 20)
+#define XY_FAST_COPY_BLT_D0_DST_TILING_MASK REG_GENMASK(14, 13)
+#define XY_FAST_COPY_BLT_D0_SRC_TILE_MODE(mode) \
+ REG_FIELD_PREP(XY_FAST_COPY_BLT_D0_SRC_TILING_MASK, mode)
+#define XY_FAST_COPY_BLT_D0_DST_TILE_MODE(mode) \
+ REG_FIELD_PREP(XY_FAST_COPY_BLT_D0_DST_TILING_MASK, mode)
+#define LINEAR 0
+#define TILE_X 0x1
+#define XMAJOR 0x1
+#define YMAJOR 0x2
+#define TILE_64 0x3
+#define XY_FAST_COPY_BLT_D1_SRC_TILE4 REG_BIT(31)
+#define XY_FAST_COPY_BLT_D1_DST_TILE4 REG_BIT(30)
+#define BLIT_CCTL_SRC_MOCS_MASK REG_GENMASK(6, 0)
+#define BLIT_CCTL_DST_MOCS_MASK REG_GENMASK(14, 8)
+/* Note: MOCS value = (index << 1) */
+#define BLIT_CCTL_SRC_MOCS(idx) \
+ REG_FIELD_PREP(BLIT_CCTL_SRC_MOCS_MASK, (idx) << 1)
+#define BLIT_CCTL_DST_MOCS(idx) \
+ REG_FIELD_PREP(BLIT_CCTL_DST_MOCS_MASK, (idx) << 1)
+
#define SRC_COPY_BLT_CMD (2 << 29 | 0x43 << 22)
#define GEN9_XY_FAST_COPY_BLT_CMD (2 << 29 | 0x42 << 22)
#define XY_SRC_COPY_BLT_CMD (2 << 29 | 0x53 << 22)
@@ -288,8 +310,11 @@
#define PIPE_CONTROL_DEPTH_CACHE_FLUSH (1<<0)
#define PIPE_CONTROL_GLOBAL_GTT (1<<2) /* in addr dword */
-/* 3D-related flags can't be set on compute engine */
-#define PIPE_CONTROL_3D_FLAGS (\
+/*
+ * 3D-related flags that can't be set on _engines_ that lack access to the 3D
+ * pipeline (i.e., CCS engines).
+ */
+#define PIPE_CONTROL_3D_ENGINE_FLAGS (\
PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH | \
PIPE_CONTROL_DEPTH_CACHE_FLUSH | \
PIPE_CONTROL_TILE_CACHE_FLUSH | \
@@ -300,6 +325,14 @@
PIPE_CONTROL_VF_CACHE_INVALIDATE | \
PIPE_CONTROL_GLOBAL_SNAPSHOT_RESET)
+/* 3D-related flags that can't be set on _platforms_ that lack a 3D pipeline */
+#define PIPE_CONTROL_3D_ARCH_FLAGS ( \
+ PIPE_CONTROL_3D_ENGINE_FLAGS | \
+ PIPE_CONTROL_INDIRECT_STATE_DISABLE | \
+ PIPE_CONTROL_FLUSH_ENABLE | \
+ PIPE_CONTROL_TEXTURE_CACHE_INVALIDATE | \
+ PIPE_CONTROL_DC_FLUSH_ENABLE)
+
#define MI_MATH(x) MI_INSTR(0x1a, (x) - 1)
#define MI_MATH_INSTR(opcode, op1, op2) ((opcode) << 20 | (op1) << 10 | (op2))
/* Opcodes for MI_MATH_INSTR */
diff --git a/drivers/gpu/drm/i915/gt/intel_gt.c b/drivers/gpu/drm/i915/gt/intel_gt.c
index 53307ca0eed0c873286a768bdf3ad94d32750349..8da3314bb6bf605267d493bb2093ecb02f14a883 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt.c
@@ -4,6 +4,7 @@
*/
#include <drm/drm_managed.h>
+#include <drm/intel-gtt.h>
#include "gem/i915_gem_internal.h"
#include "gem/i915_gem_lmem.h"
@@ -12,11 +13,12 @@
#include "i915_drv.h"
#include "intel_context.h"
#include "intel_engine_regs.h"
+#include "intel_ggtt_gmch.h"
#include "intel_gt.h"
#include "intel_gt_buffer_pool.h"
#include "intel_gt_clock_utils.h"
#include "intel_gt_debugfs.h"
-#include "intel_gt_gmch.h"
+#include "intel_gt_mcr.h"
#include "intel_gt_pm.h"
#include "intel_gt_regs.h"
#include "intel_gt_requests.h"
@@ -102,78 +104,13 @@ int intel_gt_assign_ggtt(struct intel_gt *gt)
return gt->ggtt ? 0 : -ENOMEM;
}
-static const char * const intel_steering_types[] = {
- "L3BANK",
- "MSLICE",
- "LNCF",
-};
-
-static const struct intel_mmio_range icl_l3bank_steering_table[] = {
- { 0x00B100, 0x00B3FF },
- {},
-};
-
-static const struct intel_mmio_range xehpsdv_mslice_steering_table[] = {
- { 0x004000, 0x004AFF },
- { 0x00C800, 0x00CFFF },
- { 0x00DD00, 0x00DDFF },
- { 0x00E900, 0x00FFFF }, /* 0xEA00 - OxEFFF is unused */
- {},
-};
-
-static const struct intel_mmio_range xehpsdv_lncf_steering_table[] = {
- { 0x00B000, 0x00B0FF },
- { 0x00D800, 0x00D8FF },
- {},
-};
-
-static const struct intel_mmio_range dg2_lncf_steering_table[] = {
- { 0x00B000, 0x00B0FF },
- { 0x00D880, 0x00D8FF },
- {},
-};
-
-static u16 slicemask(struct intel_gt *gt, int count)
-{
- u64 dss_mask = intel_sseu_get_subslices(>->info.sseu, 0);
-
- return intel_slicemask_from_dssmask(dss_mask, count);
-}
-
int intel_gt_init_mmio(struct intel_gt *gt)
{
- struct drm_i915_private *i915 = gt->i915;
-
intel_gt_init_clock_frequency(gt);
intel_uc_init_mmio(>->uc);
intel_sseu_info_init(gt);
-
- /*
- * An mslice is unavailable only if both the meml3 for the slice is
- * disabled *and* all of the DSS in the slice (quadrant) are disabled.
- */
- if (HAS_MSLICES(i915))
- gt->info.mslice_mask =
- slicemask(gt, GEN_DSS_PER_MSLICE) |
- (intel_uncore_read(gt->uncore, GEN10_MIRROR_FUSE3) &
- GEN12_MEML3_EN_MASK);
-
- if (IS_DG2(i915)) {
- gt->steering_table[MSLICE] = xehpsdv_mslice_steering_table;
- gt->steering_table[LNCF] = dg2_lncf_steering_table;
- } else if (IS_XEHPSDV(i915)) {
- gt->steering_table[MSLICE] = xehpsdv_mslice_steering_table;
- gt->steering_table[LNCF] = xehpsdv_lncf_steering_table;
- } else if (GRAPHICS_VER(i915) >= 11 &&
- GRAPHICS_VER_FULL(i915) < IP_VER(12, 50)) {
- gt->steering_table[L3BANK] = icl_l3bank_steering_table;
- gt->info.l3bank_mask =
- ~intel_uncore_read(gt->uncore, GEN10_MIRROR_FUSE3) &
- GEN10_L3BANK_MASK;
- } else if (HAS_MSLICES(i915)) {
- MISSING_CASE(INTEL_INFO(i915)->platform);
- }
+ intel_gt_mcr_init(gt);
return intel_engines_init_mmio(gt);
}
@@ -451,7 +388,7 @@ void intel_gt_chipset_flush(struct intel_gt *gt)
{
wmb();
if (GRAPHICS_VER(gt->i915) < 6)
- intel_gt_gmch_gen5_chipset_flush(gt);
+ intel_ggtt_gmch_flush();
}
void intel_gt_driver_register(struct intel_gt *gt)
@@ -785,6 +722,7 @@ void intel_gt_driver_unregister(struct intel_gt *gt)
{
intel_wakeref_t wakeref;
+ intel_gt_sysfs_unregister(gt);
intel_rps_driver_unregister(>->rps);
intel_gsc_fini(>->gsc);
@@ -834,200 +772,6 @@ void intel_gt_driver_late_release_all(struct drm_i915_private *i915)
}
}
-/**
- * intel_gt_reg_needs_read_steering - determine whether a register read
- * requires explicit steering
- * @gt: GT structure
- * @reg: the register to check steering requirements for
- * @type: type of multicast steering to check
- *
- * Determines whether @reg needs explicit steering of a specific type for
- * reads.
- *
- * Returns false if @reg does not belong to a register range of the given
- * steering type, or if the default (subslice-based) steering IDs are suitable
- * for @type steering too.
- */
-static bool intel_gt_reg_needs_read_steering(struct intel_gt *gt,
- i915_reg_t reg,
- enum intel_steering_type type)
-{
- const u32 offset = i915_mmio_reg_offset(reg);
- const struct intel_mmio_range *entry;
-
- if (likely(!intel_gt_needs_read_steering(gt, type)))
- return false;
-
- for (entry = gt->steering_table[type]; entry->end; entry++) {
- if (offset >= entry->start && offset <= entry->end)
- return true;
- }
-
- return false;
-}
-
-/**
- * intel_gt_get_valid_steering - determines valid IDs for a class of MCR steering
- * @gt: GT structure
- * @type: multicast register type
- * @sliceid: Slice ID returned
- * @subsliceid: Subslice ID returned
- *
- * Determines sliceid and subsliceid values that will steer reads
- * of a specific multicast register class to a valid value.
- */
-static void intel_gt_get_valid_steering(struct intel_gt *gt,
- enum intel_steering_type type,
- u8 *sliceid, u8 *subsliceid)
-{
- switch (type) {
- case L3BANK:
- GEM_DEBUG_WARN_ON(!gt->info.l3bank_mask); /* should be impossible! */
-
- *sliceid = 0; /* unused */
- *subsliceid = __ffs(gt->info.l3bank_mask);
- break;
- case MSLICE:
- GEM_DEBUG_WARN_ON(!gt->info.mslice_mask); /* should be impossible! */
-
- *sliceid = __ffs(gt->info.mslice_mask);
- *subsliceid = 0; /* unused */
- break;
- case LNCF:
- GEM_DEBUG_WARN_ON(!gt->info.mslice_mask); /* should be impossible! */
-
- /*
- * An LNCF is always present if its mslice is present, so we
- * can safely just steer to LNCF 0 in all cases.
- */
- *sliceid = __ffs(gt->info.mslice_mask) << 1;
- *subsliceid = 0; /* unused */
- break;
- default:
- MISSING_CASE(type);
- *sliceid = 0;
- *subsliceid = 0;
- }
-}
-
-/**
- * intel_gt_read_register_fw - reads a GT register with support for multicast
- * @gt: GT structure
- * @reg: register to read
- *
- * This function will read a GT register. If the register is a multicast
- * register, the read will be steered to a valid instance (i.e., one that
- * isn't fused off or powered down by power gating).
- *
- * Returns the value from a valid instance of @reg.
- */
-u32 intel_gt_read_register_fw(struct intel_gt *gt, i915_reg_t reg)
-{
- int type;
- u8 sliceid, subsliceid;
-
- for (type = 0; type < NUM_STEERING_TYPES; type++) {
- if (intel_gt_reg_needs_read_steering(gt, reg, type)) {
- intel_gt_get_valid_steering(gt, type, &sliceid,
- &subsliceid);
- return intel_uncore_read_with_mcr_steering_fw(gt->uncore,
- reg,
- sliceid,
- subsliceid);
- }
- }
-
- return intel_uncore_read_fw(gt->uncore, reg);
-}
-
-/**
- * intel_gt_get_valid_steering_for_reg - get a valid steering for a register
- * @gt: GT structure
- * @reg: register for which the steering is required
- * @sliceid: return variable for slice steering
- * @subsliceid: return variable for subslice steering
- *
- * This function returns a slice/subslice pair that is guaranteed to work for
- * read steering of the given register. Note that a value will be returned even
- * if the register is not replicated and therefore does not actually require
- * steering.
- */
-void intel_gt_get_valid_steering_for_reg(struct intel_gt *gt, i915_reg_t reg,
- u8 *sliceid, u8 *subsliceid)
-{
- int type;
-
- for (type = 0; type < NUM_STEERING_TYPES; type++) {
- if (intel_gt_reg_needs_read_steering(gt, reg, type)) {
- intel_gt_get_valid_steering(gt, type, sliceid,
- subsliceid);
- return;
- }
- }
-
- *sliceid = gt->default_steering.groupid;
- *subsliceid = gt->default_steering.instanceid;
-}
-
-u32 intel_gt_read_register(struct intel_gt *gt, i915_reg_t reg)
-{
- int type;
- u8 sliceid, subsliceid;
-
- for (type = 0; type < NUM_STEERING_TYPES; type++) {
- if (intel_gt_reg_needs_read_steering(gt, reg, type)) {
- intel_gt_get_valid_steering(gt, type, &sliceid,
- &subsliceid);
- return intel_uncore_read_with_mcr_steering(gt->uncore,
- reg,
- sliceid,
- subsliceid);
- }
- }
-
- return intel_uncore_read(gt->uncore, reg);
-}
-
-static void report_steering_type(struct drm_printer *p,
- struct intel_gt *gt,
- enum intel_steering_type type,
- bool dump_table)
-{
- const struct intel_mmio_range *entry;
- u8 slice, subslice;
-
- BUILD_BUG_ON(ARRAY_SIZE(intel_steering_types) != NUM_STEERING_TYPES);
-
- if (!gt->steering_table[type]) {
- drm_printf(p, "%s steering: uses default steering\n",
- intel_steering_types[type]);
- return;
- }
-
- intel_gt_get_valid_steering(gt, type, &slice, &subslice);
- drm_printf(p, "%s steering: sliceid=0x%x, subsliceid=0x%x\n",
- intel_steering_types[type], slice, subslice);
-
- if (!dump_table)
- return;
-
- for (entry = gt->steering_table[type]; entry->end; entry++)
- drm_printf(p, "\t0x%06x - 0x%06x\n", entry->start, entry->end);
-}
-
-void intel_gt_report_steering(struct drm_printer *p, struct intel_gt *gt,
- bool dump_table)
-{
- drm_printf(p, "Default steering: sliceid=0x%x, subsliceid=0x%x\n",
- gt->default_steering.groupid,
- gt->default_steering.instanceid);
-
- if (HAS_MSLICES(gt->i915)) {
- report_steering_type(p, gt, MSLICE, dump_table);
- report_steering_type(p, gt, LNCF, dump_table);
- }
-}
-
static int intel_gt_tile_setup(struct intel_gt *gt, phys_addr_t phys_addr)
{
int ret;
diff --git a/drivers/gpu/drm/i915/gt/intel_gt.h b/drivers/gpu/drm/i915/gt/intel_gt.h
index 44c6cb63ccbc8592f5f7a61260e15a9d1a6754da..82d6f248d876256f1831369951665ec526a826aa 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt.h
@@ -13,13 +13,6 @@
struct drm_i915_private;
struct drm_printer;
-struct insert_entries {
- struct i915_address_space *vm;
- struct i915_vma_resource *vma_res;
- enum i915_cache_level level;
- u32 flags;
-};
-
#define GT_TRACE(gt, fmt, ...) do { \
const struct intel_gt *gt__ __maybe_unused = (gt); \
GEM_TRACE("%s " fmt, dev_name(gt__->i915->drm.dev), \
@@ -93,21 +86,6 @@ static inline bool intel_gt_is_wedged(const struct intel_gt *gt)
return unlikely(test_bit(I915_WEDGED, >->reset.flags));
}
-static inline bool intel_gt_needs_read_steering(struct intel_gt *gt,
- enum intel_steering_type type)
-{
- return gt->steering_table[type];
-}
-
-void intel_gt_get_valid_steering_for_reg(struct intel_gt *gt, i915_reg_t reg,
- u8 *sliceid, u8 *subsliceid);
-
-u32 intel_gt_read_register_fw(struct intel_gt *gt, i915_reg_t reg);
-u32 intel_gt_read_register(struct intel_gt *gt, i915_reg_t reg);
-
-void intel_gt_report_steering(struct drm_printer *p, struct intel_gt *gt,
- bool dump_table);
-
int intel_gt_probe_all(struct drm_i915_private *i915);
int intel_gt_tiles_init(struct drm_i915_private *i915);
void intel_gt_release_all(struct drm_i915_private *i915);
@@ -125,6 +103,4 @@ void intel_gt_watchdog_work(struct work_struct *work);
void intel_gt_invalidate_tlbs(struct intel_gt *gt);
-struct resource intel_pci_resource(struct pci_dev *pdev, int bar);
-
#endif /* __INTEL_GT_H__ */
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_debugfs.c b/drivers/gpu/drm/i915/gt/intel_gt_debugfs.c
index d886fdc2c694bd3359252528bc048dae8f764985..dd53641f36372d77ee38da71ec1ffae7f2bdc945 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_debugfs.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt_debugfs.c
@@ -9,6 +9,7 @@
#include "intel_gt.h"
#include "intel_gt_debugfs.h"
#include "intel_gt_engines_debugfs.h"
+#include "intel_gt_mcr.h"
#include "intel_gt_pm_debugfs.h"
#include "intel_sseu_debugfs.h"
#include "pxp/intel_pxp_debugfs.h"
@@ -64,7 +65,7 @@ static int steering_show(struct seq_file *m, void *data)
struct drm_printer p = drm_seq_file_printer(m);
struct intel_gt *gt = m->private;
- intel_gt_report_steering(&p, gt, true);
+ intel_gt_mcr_report_steering(&p, gt, true);
return 0;
}
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_gmch.c b/drivers/gpu/drm/i915/gt/intel_gt_gmch.c
deleted file mode 100644
index 18e488672d1b3e6c3cb887384cc4e8f615ded3d1..0000000000000000000000000000000000000000
--- a/drivers/gpu/drm/i915/gt/intel_gt_gmch.c
+++ /dev/null
@@ -1,654 +0,0 @@
-// SPDX-License-Identifier: MIT
-/*
- * Copyright © 2022 Intel Corporation
- */
-
-#include <drm/intel-gtt.h>
-#include <drm/i915_drm.h>
-
-#include <linux/agp_backend.h>
-#include <linux/stop_machine.h>
-
-#include "i915_drv.h"
-#include "intel_gt_gmch.h"
-#include "intel_gt_regs.h"
-#include "intel_gt.h"
-#include "i915_utils.h"
-
-#include "gen8_ppgtt.h"
-
-struct insert_page {
- struct i915_address_space *vm;
- dma_addr_t addr;
- u64 offset;
- enum i915_cache_level level;
-};
-
-static void gen8_set_pte(void __iomem *addr, gen8_pte_t pte)
-{
- writeq(pte, addr);
-}
-
-static void nop_clear_range(struct i915_address_space *vm,
- u64 start, u64 length)
-{
-}
-
-static u64 snb_pte_encode(dma_addr_t addr,
- enum i915_cache_level level,
- u32 flags)
-{
- gen6_pte_t pte = GEN6_PTE_ADDR_ENCODE(addr) | GEN6_PTE_VALID;
-
- switch (level) {
- case I915_CACHE_L3_LLC:
- case I915_CACHE_LLC:
- pte |= GEN6_PTE_CACHE_LLC;
- break;
- case I915_CACHE_NONE:
- pte |= GEN6_PTE_UNCACHED;
- break;
- default:
- MISSING_CASE(level);
- }
-
- return pte;
-}
-
-static u64 ivb_pte_encode(dma_addr_t addr,
- enum i915_cache_level level,
- u32 flags)
-{
- gen6_pte_t pte = GEN6_PTE_ADDR_ENCODE(addr) | GEN6_PTE_VALID;
-
- switch (level) {
- case I915_CACHE_L3_LLC:
- pte |= GEN7_PTE_CACHE_L3_LLC;
- break;
- case I915_CACHE_LLC:
- pte |= GEN6_PTE_CACHE_LLC;
- break;
- case I915_CACHE_NONE:
- pte |= GEN6_PTE_UNCACHED;
- break;
- default:
- MISSING_CASE(level);
- }
-
- return pte;
-}
-
-static u64 byt_pte_encode(dma_addr_t addr,
- enum i915_cache_level level,
- u32 flags)
-{
- gen6_pte_t pte = GEN6_PTE_ADDR_ENCODE(addr) | GEN6_PTE_VALID;
-
- if (!(flags & PTE_READ_ONLY))
- pte |= BYT_PTE_WRITEABLE;
-
- if (level != I915_CACHE_NONE)
- pte |= BYT_PTE_SNOOPED_BY_CPU_CACHES;
-
- return pte;
-}
-
-static u64 hsw_pte_encode(dma_addr_t addr,
- enum i915_cache_level level,
- u32 flags)
-{
- gen6_pte_t pte = HSW_PTE_ADDR_ENCODE(addr) | GEN6_PTE_VALID;
-
- if (level != I915_CACHE_NONE)
- pte |= HSW_WB_LLC_AGE3;
-
- return pte;
-}
-
-static u64 iris_pte_encode(dma_addr_t addr,
- enum i915_cache_level level,
- u32 flags)
-{
- gen6_pte_t pte = HSW_PTE_ADDR_ENCODE(addr) | GEN6_PTE_VALID;
-
- switch (level) {
- case I915_CACHE_NONE:
- break;
- case I915_CACHE_WT:
- pte |= HSW_WT_ELLC_LLC_AGE3;
- break;
- default:
- pte |= HSW_WB_ELLC_LLC_AGE3;
- break;
- }
-
- return pte;
-}
-
-static void gen5_ggtt_insert_page(struct i915_address_space *vm,
- dma_addr_t addr,
- u64 offset,
- enum i915_cache_level cache_level,
- u32 unused)
-{
- unsigned int flags = (cache_level == I915_CACHE_NONE) ?
- AGP_USER_MEMORY : AGP_USER_CACHED_MEMORY;
-
- intel_gtt_insert_page(addr, offset >> PAGE_SHIFT, flags);
-}
-
-static void gen6_ggtt_insert_page(struct i915_address_space *vm,
- dma_addr_t addr,
- u64 offset,
- enum i915_cache_level level,
- u32 flags)
-{
- struct i915_ggtt *ggtt = i915_vm_to_ggtt(vm);
- gen6_pte_t __iomem *pte =
- (gen6_pte_t __iomem *)ggtt->gsm + offset / I915_GTT_PAGE_SIZE;
-
- iowrite32(vm->pte_encode(addr, level, flags), pte);
-
- ggtt->invalidate(ggtt);
-}
-
-static void gen8_ggtt_insert_page(struct i915_address_space *vm,
- dma_addr_t addr,
- u64 offset,
- enum i915_cache_level level,
- u32 flags)
-{
- struct i915_ggtt *ggtt = i915_vm_to_ggtt(vm);
- gen8_pte_t __iomem *pte =
- (gen8_pte_t __iomem *)ggtt->gsm + offset / I915_GTT_PAGE_SIZE;
-
- gen8_set_pte(pte, gen8_ggtt_pte_encode(addr, level, flags));
-
- ggtt->invalidate(ggtt);
-}
-
-static void gen5_ggtt_insert_entries(struct i915_address_space *vm,
- struct i915_vma_resource *vma_res,
- enum i915_cache_level cache_level,
- u32 unused)
-{
- unsigned int flags = (cache_level == I915_CACHE_NONE) ?
- AGP_USER_MEMORY : AGP_USER_CACHED_MEMORY;
-
- intel_gtt_insert_sg_entries(vma_res->bi.pages, vma_res->start >> PAGE_SHIFT,
- flags);
-}
-
-/*
- * Binds an object into the global gtt with the specified cache level.
- * The object will be accessible to the GPU via commands whose operands
- * reference offsets within the global GTT as well as accessible by the GPU
- * through the GMADR mapped BAR (i915->mm.gtt->gtt).
- */
-static void gen6_ggtt_insert_entries(struct i915_address_space *vm,
- struct i915_vma_resource *vma_res,
- enum i915_cache_level level,
- u32 flags)
-{
- struct i915_ggtt *ggtt = i915_vm_to_ggtt(vm);
- gen6_pte_t __iomem *gte;
- gen6_pte_t __iomem *end;
- struct sgt_iter iter;
- dma_addr_t addr;
-
- gte = (gen6_pte_t __iomem *)ggtt->gsm;
- gte += vma_res->start / I915_GTT_PAGE_SIZE;
- end = gte + vma_res->node_size / I915_GTT_PAGE_SIZE;
-
- for_each_sgt_daddr(addr, iter, vma_res->bi.pages)
- iowrite32(vm->pte_encode(addr, level, flags), gte++);
- GEM_BUG_ON(gte > end);
-
- /* Fill the allocated but "unused" space beyond the end of the buffer */
- while (gte < end)
- iowrite32(vm->scratch[0]->encode, gte++);
-
- /*
- * We want to flush the TLBs only after we're certain all the PTE
- * updates have finished.
- */
- ggtt->invalidate(ggtt);
-}
-
-static void gen8_ggtt_insert_entries(struct i915_address_space *vm,
- struct i915_vma_resource *vma_res,
- enum i915_cache_level level,
- u32 flags)
-{
- const gen8_pte_t pte_encode = gen8_ggtt_pte_encode(0, level, flags);
- struct i915_ggtt *ggtt = i915_vm_to_ggtt(vm);
- gen8_pte_t __iomem *gte;
- gen8_pte_t __iomem *end;
- struct sgt_iter iter;
- dma_addr_t addr;
-
- /*
- * Note that we ignore PTE_READ_ONLY here. The caller must be careful
- * not to allow the user to override access to a read only page.
- */
-
- gte = (gen8_pte_t __iomem *)ggtt->gsm;
- gte += vma_res->start / I915_GTT_PAGE_SIZE;
- end = gte + vma_res->node_size / I915_GTT_PAGE_SIZE;
-
- for_each_sgt_daddr(addr, iter, vma_res->bi.pages)
- gen8_set_pte(gte++, pte_encode | addr);
- GEM_BUG_ON(gte > end);
-
- /* Fill the allocated but "unused" space beyond the end of the buffer */
- while (gte < end)
- gen8_set_pte(gte++, vm->scratch[0]->encode);
-
- /*
- * We want to flush the TLBs only after we're certain all the PTE
- * updates have finished.
- */
- ggtt->invalidate(ggtt);
-}
-
-static void bxt_vtd_ggtt_wa(struct i915_address_space *vm)
-{
- /*
- * Make sure the internal GAM fifo has been cleared of all GTT
- * writes before exiting stop_machine(). This guarantees that
- * any aperture accesses waiting to start in another process
- * cannot back up behind the GTT writes causing a hang.
- * The register can be any arbitrary GAM register.
- */
- intel_uncore_posting_read_fw(vm->gt->uncore, GFX_FLSH_CNTL_GEN6);
-}
-
-static int bxt_vtd_ggtt_insert_page__cb(void *_arg)
-{
- struct insert_page *arg = _arg;
-
- gen8_ggtt_insert_page(arg->vm, arg->addr, arg->offset, arg->level, 0);
- bxt_vtd_ggtt_wa(arg->vm);
-
- return 0;
-}
-
-static void bxt_vtd_ggtt_insert_page__BKL(struct i915_address_space *vm,
- dma_addr_t addr,
- u64 offset,
- enum i915_cache_level level,
- u32 unused)
-{
- struct insert_page arg = { vm, addr, offset, level };
-
- stop_machine(bxt_vtd_ggtt_insert_page__cb, &arg, NULL);
-}
-
-static int bxt_vtd_ggtt_insert_entries__cb(void *_arg)
-{
- struct insert_entries *arg = _arg;
-
- gen8_ggtt_insert_entries(arg->vm, arg->vma_res, arg->level, arg->flags);
- bxt_vtd_ggtt_wa(arg->vm);
-
- return 0;
-}
-
-static void bxt_vtd_ggtt_insert_entries__BKL(struct i915_address_space *vm,
- struct i915_vma_resource *vma_res,
- enum i915_cache_level level,
- u32 flags)
-{
- struct insert_entries arg = { vm, vma_res, level, flags };
-
- stop_machine(bxt_vtd_ggtt_insert_entries__cb, &arg, NULL);
-}
-
-void intel_gt_gmch_gen5_chipset_flush(struct intel_gt *gt)
-{
- intel_gtt_chipset_flush();
-}
-
-static void gmch_ggtt_invalidate(struct i915_ggtt *ggtt)
-{
- intel_gtt_chipset_flush();
-}
-
-static void gen5_ggtt_clear_range(struct i915_address_space *vm,
- u64 start, u64 length)
-{
- intel_gtt_clear_range(start >> PAGE_SHIFT, length >> PAGE_SHIFT);
-}
-
-static void gen6_ggtt_clear_range(struct i915_address_space *vm,
- u64 start, u64 length)
-{
- struct i915_ggtt *ggtt = i915_vm_to_ggtt(vm);
- unsigned int first_entry = start / I915_GTT_PAGE_SIZE;
- unsigned int num_entries = length / I915_GTT_PAGE_SIZE;
- gen6_pte_t scratch_pte, __iomem *gtt_base =
- (gen6_pte_t __iomem *)ggtt->gsm + first_entry;
- const int max_entries = ggtt_total_entries(ggtt) - first_entry;
- int i;
-
- if (WARN(num_entries > max_entries,
- "First entry = %d; Num entries = %d (max=%d)\n",
- first_entry, num_entries, max_entries))
- num_entries = max_entries;
-
- scratch_pte = vm->scratch[0]->encode;
- for (i = 0; i < num_entries; i++)
- iowrite32(scratch_pte, >t_base[i]);
-}
-
-static void gen8_ggtt_clear_range(struct i915_address_space *vm,
- u64 start, u64 length)
-{
- struct i915_ggtt *ggtt = i915_vm_to_ggtt(vm);
- unsigned int first_entry = start / I915_GTT_PAGE_SIZE;
- unsigned int num_entries = length / I915_GTT_PAGE_SIZE;
- const gen8_pte_t scratch_pte = vm->scratch[0]->encode;
- gen8_pte_t __iomem *gtt_base =
- (gen8_pte_t __iomem *)ggtt->gsm + first_entry;
- const int max_entries = ggtt_total_entries(ggtt) - first_entry;
- int i;
-
- if (WARN(num_entries > max_entries,
- "First entry = %d; Num entries = %d (max=%d)\n",
- first_entry, num_entries, max_entries))
- num_entries = max_entries;
-
- for (i = 0; i < num_entries; i++)
- gen8_set_pte(>t_base[i], scratch_pte);
-}
-
-static void gen5_gmch_remove(struct i915_address_space *vm)
-{
- intel_gmch_remove();
-}
-
-static void gen6_gmch_remove(struct i915_address_space *vm)
-{
- struct i915_ggtt *ggtt = i915_vm_to_ggtt(vm);
-
- iounmap(ggtt->gsm);
- free_scratch(vm);
-}
-
-/*
- * Certain Gen5 chipsets require idling the GPU before
- * unmapping anything from the GTT when VT-d is enabled.
- */
-static bool needs_idle_maps(struct drm_i915_private *i915)
-{
- /*
- * Query intel_iommu to see if we need the workaround. Presumably that
- * was loaded first.
- */
- if (!i915_vtd_active(i915))
- return false;
-
- if (GRAPHICS_VER(i915) == 5 && IS_MOBILE(i915))
- return true;
-
- if (GRAPHICS_VER(i915) == 12)
- return true; /* XXX DMAR fault reason 7 */
-
- return false;
-}
-
-static unsigned int gen6_gttmmadr_size(struct drm_i915_private *i915)
-{
- /*
- * GEN6: GTTMMADR size is 4MB and GTTADR starts at 2MB offset
- * GEN8: GTTMMADR size is 16MB and GTTADR starts at 8MB offset
- */
- GEM_BUG_ON(GRAPHICS_VER(i915) < 6);
- return (GRAPHICS_VER(i915) < 8) ? SZ_4M : SZ_16M;
-}
-
-static unsigned int gen6_get_total_gtt_size(u16 snb_gmch_ctl)
-{
- snb_gmch_ctl >>= SNB_GMCH_GGMS_SHIFT;
- snb_gmch_ctl &= SNB_GMCH_GGMS_MASK;
- return snb_gmch_ctl << 20;
-}
-
-static unsigned int gen8_get_total_gtt_size(u16 bdw_gmch_ctl)
-{
- bdw_gmch_ctl >>= BDW_GMCH_GGMS_SHIFT;
- bdw_gmch_ctl &= BDW_GMCH_GGMS_MASK;
- if (bdw_gmch_ctl)
- bdw_gmch_ctl = 1 << bdw_gmch_ctl;
-
-#ifdef CONFIG_X86_32
- /* Limit 32b platforms to a 2GB GGTT: 4 << 20 / pte size * I915_GTT_PAGE_SIZE */
- if (bdw_gmch_ctl > 4)
- bdw_gmch_ctl = 4;
-#endif
-
- return bdw_gmch_ctl << 20;
-}
-
-static unsigned int gen6_gttadr_offset(struct drm_i915_private *i915)
-{
- return gen6_gttmmadr_size(i915) / 2;
-}
-
-static int ggtt_probe_common(struct i915_ggtt *ggtt, u64 size)
-{
- struct drm_i915_private *i915 = ggtt->vm.i915;
- struct pci_dev *pdev = to_pci_dev(i915->drm.dev);
- phys_addr_t phys_addr;
- u32 pte_flags;
- int ret;
-
- GEM_WARN_ON(pci_resource_len(pdev, 0) != gen6_gttmmadr_size(i915));
- phys_addr = pci_resource_start(pdev, 0) + gen6_gttadr_offset(i915);
-
- /*
- * On BXT+/ICL+ writes larger than 64 bit to the GTT pagetable range
- * will be dropped. For WC mappings in general we have 64 byte burst
- * writes when the WC buffer is flushed, so we can't use it, but have to
- * resort to an uncached mapping. The WC issue is easily caught by the
- * readback check when writing GTT PTE entries.
- */
- if (IS_GEN9_LP(i915) || GRAPHICS_VER(i915) >= 11)
- ggtt->gsm = ioremap(phys_addr, size);
- else
- ggtt->gsm = ioremap_wc(phys_addr, size);
- if (!ggtt->gsm) {
- drm_err(&i915->drm, "Failed to map the ggtt page table\n");
- return -ENOMEM;
- }
-
- kref_init(&ggtt->vm.resv_ref);
- ret = setup_scratch_page(&ggtt->vm);
- if (ret) {
- drm_err(&i915->drm, "Scratch setup failed\n");
- /* iounmap will also get called at remove, but meh */
- iounmap(ggtt->gsm);
- return ret;
- }
-
- pte_flags = 0;
- if (i915_gem_object_is_lmem(ggtt->vm.scratch[0]))
- pte_flags |= PTE_LM;
-
- ggtt->vm.scratch[0]->encode =
- ggtt->vm.pte_encode(px_dma(ggtt->vm.scratch[0]),
- I915_CACHE_NONE, pte_flags);
-
- return 0;
-}
-
-int intel_gt_gmch_gen5_probe(struct i915_ggtt *ggtt)
-{
- struct drm_i915_private *i915 = ggtt->vm.i915;
- phys_addr_t gmadr_base;
- int ret;
-
- ret = intel_gmch_probe(i915->bridge_dev, to_pci_dev(i915->drm.dev), NULL);
- if (!ret) {
- drm_err(&i915->drm, "failed to set up gmch\n");
- return -EIO;
- }
-
- intel_gtt_get(&ggtt->vm.total, &gmadr_base, &ggtt->mappable_end);
-
- ggtt->gmadr =
- (struct resource)DEFINE_RES_MEM(gmadr_base, ggtt->mappable_end);
-
- ggtt->vm.alloc_pt_dma = alloc_pt_dma;
- ggtt->vm.alloc_scratch_dma = alloc_pt_dma;
-
- if (needs_idle_maps(i915)) {
- drm_notice(&i915->drm,
- "Flushing DMA requests before IOMMU unmaps; performance may be degraded\n");
- ggtt->do_idle_maps = true;
- }
-
- ggtt->vm.insert_page = gen5_ggtt_insert_page;
- ggtt->vm.insert_entries = gen5_ggtt_insert_entries;
- ggtt->vm.clear_range = gen5_ggtt_clear_range;
- ggtt->vm.cleanup = gen5_gmch_remove;
-
- ggtt->invalidate = gmch_ggtt_invalidate;
-
- ggtt->vm.vma_ops.bind_vma = intel_ggtt_bind_vma;
- ggtt->vm.vma_ops.unbind_vma = intel_ggtt_unbind_vma;
-
- if (unlikely(ggtt->do_idle_maps))
- drm_notice(&i915->drm,
- "Applying Ironlake quirks for intel_iommu\n");
-
- return 0;
-}
-
-int intel_gt_gmch_gen6_probe(struct i915_ggtt *ggtt)
-{
- struct drm_i915_private *i915 = ggtt->vm.i915;
- struct pci_dev *pdev = to_pci_dev(i915->drm.dev);
- unsigned int size;
- u16 snb_gmch_ctl;
-
- ggtt->gmadr = intel_pci_resource(pdev, 2);
- ggtt->mappable_end = resource_size(&ggtt->gmadr);
-
- /*
- * 64/512MB is the current min/max we actually know of, but this is
- * just a coarse sanity check.
- */
- if (ggtt->mappable_end < (64<<20) || ggtt->mappable_end > (512<<20)) {
- drm_err(&i915->drm, "Unknown GMADR size (%pa)\n",
- &ggtt->mappable_end);
- return -ENXIO;
- }
-
- pci_read_config_word(pdev, SNB_GMCH_CTRL, &snb_gmch_ctl);
-
- size = gen6_get_total_gtt_size(snb_gmch_ctl);
- ggtt->vm.total = (size / sizeof(gen6_pte_t)) * I915_GTT_PAGE_SIZE;
-
- ggtt->vm.alloc_pt_dma = alloc_pt_dma;
- ggtt->vm.alloc_scratch_dma = alloc_pt_dma;
-
- ggtt->vm.clear_range = nop_clear_range;
- if (!HAS_FULL_PPGTT(i915) || intel_scanout_needs_vtd_wa(i915))
- ggtt->vm.clear_range = gen6_ggtt_clear_range;
- ggtt->vm.insert_page = gen6_ggtt_insert_page;
- ggtt->vm.insert_entries = gen6_ggtt_insert_entries;
- ggtt->vm.cleanup = gen6_gmch_remove;
-
- ggtt->invalidate = gen6_ggtt_invalidate;
-
- if (HAS_EDRAM(i915))
- ggtt->vm.pte_encode = iris_pte_encode;
- else if (IS_HASWELL(i915))
- ggtt->vm.pte_encode = hsw_pte_encode;
- else if (IS_VALLEYVIEW(i915))
- ggtt->vm.pte_encode = byt_pte_encode;
- else if (GRAPHICS_VER(i915) >= 7)
- ggtt->vm.pte_encode = ivb_pte_encode;
- else
- ggtt->vm.pte_encode = snb_pte_encode;
-
- ggtt->vm.vma_ops.bind_vma = intel_ggtt_bind_vma;
- ggtt->vm.vma_ops.unbind_vma = intel_ggtt_unbind_vma;
-
- return ggtt_probe_common(ggtt, size);
-}
-
-static unsigned int chv_get_total_gtt_size(u16 gmch_ctrl)
-{
- gmch_ctrl >>= SNB_GMCH_GGMS_SHIFT;
- gmch_ctrl &= SNB_GMCH_GGMS_MASK;
-
- if (gmch_ctrl)
- return 1 << (20 + gmch_ctrl);
-
- return 0;
-}
-
-int intel_gt_gmch_gen8_probe(struct i915_ggtt *ggtt)
-{
- struct drm_i915_private *i915 = ggtt->vm.i915;
- struct pci_dev *pdev = to_pci_dev(i915->drm.dev);
- unsigned int size;
- u16 snb_gmch_ctl;
-
- /* TODO: We're not aware of mappable constraints on gen8 yet */
- if (!HAS_LMEM(i915)) {
- ggtt->gmadr = intel_pci_resource(pdev, 2);
- ggtt->mappable_end = resource_size(&ggtt->gmadr);
- }
-
- pci_read_config_word(pdev, SNB_GMCH_CTRL, &snb_gmch_ctl);
- if (IS_CHERRYVIEW(i915))
- size = chv_get_total_gtt_size(snb_gmch_ctl);
- else
- size = gen8_get_total_gtt_size(snb_gmch_ctl);
-
- ggtt->vm.alloc_pt_dma = alloc_pt_dma;
- ggtt->vm.alloc_scratch_dma = alloc_pt_dma;
- ggtt->vm.lmem_pt_obj_flags = I915_BO_ALLOC_PM_EARLY;
-
- ggtt->vm.total = (size / sizeof(gen8_pte_t)) * I915_GTT_PAGE_SIZE;
- ggtt->vm.cleanup = gen6_gmch_remove;
- ggtt->vm.insert_page = gen8_ggtt_insert_page;
- ggtt->vm.clear_range = nop_clear_range;
- if (intel_scanout_needs_vtd_wa(i915))
- ggtt->vm.clear_range = gen8_ggtt_clear_range;
-
- ggtt->vm.insert_entries = gen8_ggtt_insert_entries;
-
- /*
- * Serialize GTT updates with aperture access on BXT if VT-d is on,
- * and always on CHV.
- */
- if (intel_vm_no_concurrent_access_wa(i915)) {
- ggtt->vm.insert_entries = bxt_vtd_ggtt_insert_entries__BKL;
- ggtt->vm.insert_page = bxt_vtd_ggtt_insert_page__BKL;
- ggtt->vm.bind_async_flags =
- I915_VMA_GLOBAL_BIND | I915_VMA_LOCAL_BIND;
- }
-
- ggtt->invalidate = gen8_ggtt_invalidate;
-
- ggtt->vm.vma_ops.bind_vma = intel_ggtt_bind_vma;
- ggtt->vm.vma_ops.unbind_vma = intel_ggtt_unbind_vma;
-
- ggtt->vm.pte_encode = gen8_ggtt_pte_encode;
-
- setup_private_pat(ggtt->vm.gt->uncore);
-
- return ggtt_probe_common(ggtt, size);
-}
-
-int intel_gt_gmch_gen5_enable_hw(struct drm_i915_private *i915)
-{
- if (GRAPHICS_VER(i915) < 6 && !intel_enable_gtt())
- return -EIO;
-
- return 0;
-}
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_gmch.h b/drivers/gpu/drm/i915/gt/intel_gt_gmch.h
deleted file mode 100644
index 75ed55c1f30aa330906e08877526e49e2132a975..0000000000000000000000000000000000000000
--- a/drivers/gpu/drm/i915/gt/intel_gt_gmch.h
+++ /dev/null
@@ -1,46 +0,0 @@
-/* SPDX-License-Identifier: MIT */
-/*
- * Copyright © 2022 Intel Corporation
- */
-
-#ifndef __INTEL_GT_GMCH_H__
-#define __INTEL_GT_GMCH_H__
-
-#include "intel_gtt.h"
-
-/* For x86 platforms */
-#if IS_ENABLED(CONFIG_X86)
-void intel_gt_gmch_gen5_chipset_flush(struct intel_gt *gt);
-int intel_gt_gmch_gen6_probe(struct i915_ggtt *ggtt);
-int intel_gt_gmch_gen8_probe(struct i915_ggtt *ggtt);
-int intel_gt_gmch_gen5_probe(struct i915_ggtt *ggtt);
-int intel_gt_gmch_gen5_enable_hw(struct drm_i915_private *i915);
-
-/* Stubs for non-x86 platforms */
-#else
-static inline void intel_gt_gmch_gen5_chipset_flush(struct intel_gt *gt)
-{
-}
-static inline int intel_gt_gmch_gen5_probe(struct i915_ggtt *ggtt)
-{
- /* No HW should be probed for this case yet, return fail */
- return -ENODEV;
-}
-static inline int intel_gt_gmch_gen6_probe(struct i915_ggtt *ggtt)
-{
- /* No HW should be probed for this case yet, return fail */
- return -ENODEV;
-}
-static inline int intel_gt_gmch_gen8_probe(struct i915_ggtt *ggtt)
-{
- /* No HW should be probed for this case yet, return fail */
- return -ENODEV;
-}
-static inline int intel_gt_gmch_gen5_enable_hw(struct drm_i915_private *i915)
-{
- /* No HW should be enabled for this case yet, return fail */
- return -ENODEV;
-}
-#endif
-
-#endif /* __INTEL_GT_GMCH_H__ */
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_irq.c b/drivers/gpu/drm/i915/gt/intel_gt_irq.c
index 88b4becfcb175b11d2813f1685ffbf83cbf18c58..3a72d4fd0214e41fa60924b45697265b8143b1bd 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_irq.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt_irq.c
@@ -193,6 +193,14 @@ void gen11_gt_irq_reset(struct intel_gt *gt)
/* Restore masks irqs on RCS, BCS, VCS and VECS engines. */
intel_uncore_write(uncore, GEN11_RCS0_RSVD_INTR_MASK, ~0);
intel_uncore_write(uncore, GEN11_BCS_RSVD_INTR_MASK, ~0);
+ if (HAS_ENGINE(gt, BCS1) || HAS_ENGINE(gt, BCS2))
+ intel_uncore_write(uncore, XEHPC_BCS1_BCS2_INTR_MASK, ~0);
+ if (HAS_ENGINE(gt, BCS3) || HAS_ENGINE(gt, BCS4))
+ intel_uncore_write(uncore, XEHPC_BCS3_BCS4_INTR_MASK, ~0);
+ if (HAS_ENGINE(gt, BCS5) || HAS_ENGINE(gt, BCS6))
+ intel_uncore_write(uncore, XEHPC_BCS5_BCS6_INTR_MASK, ~0);
+ if (HAS_ENGINE(gt, BCS7) || HAS_ENGINE(gt, BCS8))
+ intel_uncore_write(uncore, XEHPC_BCS7_BCS8_INTR_MASK, ~0);
intel_uncore_write(uncore, GEN11_VCS0_VCS1_INTR_MASK, ~0);
intel_uncore_write(uncore, GEN11_VCS2_VCS3_INTR_MASK, ~0);
if (HAS_ENGINE(gt, VCS4) || HAS_ENGINE(gt, VCS5))
@@ -248,6 +256,14 @@ void gen11_gt_irq_postinstall(struct intel_gt *gt)
/* Unmask irqs on RCS, BCS, VCS and VECS engines. */
intel_uncore_write(uncore, GEN11_RCS0_RSVD_INTR_MASK, ~smask);
intel_uncore_write(uncore, GEN11_BCS_RSVD_INTR_MASK, ~smask);
+ if (HAS_ENGINE(gt, BCS1) || HAS_ENGINE(gt, BCS2))
+ intel_uncore_write(uncore, XEHPC_BCS1_BCS2_INTR_MASK, ~dmask);
+ if (HAS_ENGINE(gt, BCS3) || HAS_ENGINE(gt, BCS4))
+ intel_uncore_write(uncore, XEHPC_BCS3_BCS4_INTR_MASK, ~dmask);
+ if (HAS_ENGINE(gt, BCS5) || HAS_ENGINE(gt, BCS6))
+ intel_uncore_write(uncore, XEHPC_BCS5_BCS6_INTR_MASK, ~dmask);
+ if (HAS_ENGINE(gt, BCS7) || HAS_ENGINE(gt, BCS8))
+ intel_uncore_write(uncore, XEHPC_BCS7_BCS8_INTR_MASK, ~dmask);
intel_uncore_write(uncore, GEN11_VCS0_VCS1_INTR_MASK, ~dmask);
intel_uncore_write(uncore, GEN11_VCS2_VCS3_INTR_MASK, ~dmask);
if (HAS_ENGINE(gt, VCS4) || HAS_ENGINE(gt, VCS5))
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_mcr.c b/drivers/gpu/drm/i915/gt/intel_gt_mcr.c
new file mode 100644
index 0000000000000000000000000000000000000000..777025d5bd66506bcfbd62d74dd94b5aa6bd1a9d
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/intel_gt_mcr.c
@@ -0,0 +1,497 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2022 Intel Corporation
+ */
+
+#include "i915_drv.h"
+
+#include "intel_gt_mcr.h"
+#include "intel_gt_regs.h"
+
+/**
+ * DOC: GT Multicast/Replicated (MCR) Register Support
+ *
+ * Some GT registers are designed as "multicast" or "replicated" registers:
+ * multiple instances of the same register share a single MMIO offset. MCR
+ * registers are generally used when the hardware needs to potentially track
+ * independent values of a register per hardware unit (e.g., per-subslice,
+ * per-L3bank, etc.). The specific types of replication that exist vary
+ * per-platform.
+ *
+ * MMIO accesses to MCR registers are controlled according to the settings
+ * programmed in the platform's MCR_SELECTOR register(s). MMIO writes to MCR
+ * registers can be done in either a (i.e., a single write updates all
+ * instances of the register to the same value) or unicast (a write updates only
+ * one specific instance). Reads of MCR registers always operate in a unicast
+ * manner regardless of how the multicast/unicast bit is set in MCR_SELECTOR.
+ * Selection of a specific MCR instance for unicast operations is referred to
+ * as "steering."
+ *
+ * If MCR register operations are steered toward a hardware unit that is
+ * fused off or currently powered down due to power gating, the MMIO operation
+ * is "terminated" by the hardware. Terminated read operations will return a
+ * value of zero and terminated unicast write operations will be silently
+ * ignored.
+ */
+
+#define HAS_MSLICE_STEERING(dev_priv) (INTEL_INFO(dev_priv)->has_mslice_steering)
+
+static const char * const intel_steering_types[] = {
+ "L3BANK",
+ "MSLICE",
+ "LNCF",
+ "INSTANCE 0",
+};
+
+static const struct intel_mmio_range icl_l3bank_steering_table[] = {
+ { 0x00B100, 0x00B3FF },
+ {},
+};
+
+static const struct intel_mmio_range xehpsdv_mslice_steering_table[] = {
+ { 0x004000, 0x004AFF },
+ { 0x00C800, 0x00CFFF },
+ { 0x00DD00, 0x00DDFF },
+ { 0x00E900, 0x00FFFF }, /* 0xEA00 - OxEFFF is unused */
+ {},
+};
+
+static const struct intel_mmio_range xehpsdv_lncf_steering_table[] = {
+ { 0x00B000, 0x00B0FF },
+ { 0x00D800, 0x00D8FF },
+ {},
+};
+
+static const struct intel_mmio_range dg2_lncf_steering_table[] = {
+ { 0x00B000, 0x00B0FF },
+ { 0x00D880, 0x00D8FF },
+ {},
+};
+
+/*
+ * We have several types of MCR registers on PVC where steering to (0,0)
+ * will always provide us with a non-terminated value. We'll stick them
+ * all in the same table for simplicity.
+ */
+static const struct intel_mmio_range pvc_instance0_steering_table[] = {
+ { 0x004000, 0x004AFF }, /* HALF-BSLICE */
+ { 0x008800, 0x00887F }, /* CC */
+ { 0x008A80, 0x008AFF }, /* TILEPSMI */
+ { 0x00B000, 0x00B0FF }, /* HALF-BSLICE */
+ { 0x00B100, 0x00B3FF }, /* L3BANK */
+ { 0x00C800, 0x00CFFF }, /* HALF-BSLICE */
+ { 0x00D800, 0x00D8FF }, /* HALF-BSLICE */
+ { 0x00DD00, 0x00DDFF }, /* BSLICE */
+ { 0x00E900, 0x00E9FF }, /* HALF-BSLICE */
+ { 0x00EC00, 0x00EEFF }, /* HALF-BSLICE */
+ { 0x00F000, 0x00FFFF }, /* HALF-BSLICE */
+ { 0x024180, 0x0241FF }, /* HALF-BSLICE */
+ {},
+};
+
+void intel_gt_mcr_init(struct intel_gt *gt)
+{
+ struct drm_i915_private *i915 = gt->i915;
+
+ /*
+ * An mslice is unavailable only if both the meml3 for the slice is
+ * disabled *and* all of the DSS in the slice (quadrant) are disabled.
+ */
+ if (HAS_MSLICE_STEERING(i915)) {
+ gt->info.mslice_mask =
+ intel_slicemask_from_xehp_dssmask(gt->info.sseu.subslice_mask,
+ GEN_DSS_PER_MSLICE);
+ gt->info.mslice_mask |=
+ (intel_uncore_read(gt->uncore, GEN10_MIRROR_FUSE3) &
+ GEN12_MEML3_EN_MASK);
+
+ if (!gt->info.mslice_mask) /* should be impossible! */
+ drm_warn(&i915->drm, "mslice mask all zero!\n");
+ }
+
+ if (IS_PONTEVECCHIO(i915)) {
+ gt->steering_table[INSTANCE0] = pvc_instance0_steering_table;
+ } else if (IS_DG2(i915)) {
+ gt->steering_table[MSLICE] = xehpsdv_mslice_steering_table;
+ gt->steering_table[LNCF] = dg2_lncf_steering_table;
+ } else if (IS_XEHPSDV(i915)) {
+ gt->steering_table[MSLICE] = xehpsdv_mslice_steering_table;
+ gt->steering_table[LNCF] = xehpsdv_lncf_steering_table;
+ } else if (GRAPHICS_VER(i915) >= 11 &&
+ GRAPHICS_VER_FULL(i915) < IP_VER(12, 50)) {
+ gt->steering_table[L3BANK] = icl_l3bank_steering_table;
+ gt->info.l3bank_mask =
+ ~intel_uncore_read(gt->uncore, GEN10_MIRROR_FUSE3) &
+ GEN10_L3BANK_MASK;
+ if (!gt->info.l3bank_mask) /* should be impossible! */
+ drm_warn(&i915->drm, "L3 bank mask is all zero!\n");
+ } else if (GRAPHICS_VER(i915) >= 11) {
+ /*
+ * We expect all modern platforms to have at least some
+ * type of steering that needs to be initialized.
+ */
+ MISSING_CASE(INTEL_INFO(i915)->platform);
+ }
+}
+
+/*
+ * rw_with_mcr_steering_fw - Access a register with specific MCR steering
+ * @uncore: pointer to struct intel_uncore
+ * @reg: register being accessed
+ * @rw_flag: FW_REG_READ for read access or FW_REG_WRITE for write access
+ * @group: group number (documented as "sliceid" on older platforms)
+ * @instance: instance number (documented as "subsliceid" on older platforms)
+ * @value: register value to be written (ignored for read)
+ *
+ * Return: 0 for write access. register value for read access.
+ *
+ * Caller needs to make sure the relevant forcewake wells are up.
+ */
+static u32 rw_with_mcr_steering_fw(struct intel_uncore *uncore,
+ i915_reg_t reg, u8 rw_flag,
+ int group, int instance, u32 value)
+{
+ u32 mcr_mask, mcr_ss, mcr, old_mcr, val = 0;
+
+ lockdep_assert_held(&uncore->lock);
+
+ if (GRAPHICS_VER(uncore->i915) >= 11) {
+ mcr_mask = GEN11_MCR_SLICE_MASK | GEN11_MCR_SUBSLICE_MASK;
+ mcr_ss = GEN11_MCR_SLICE(group) | GEN11_MCR_SUBSLICE(instance);
+
+ /*
+ * Wa_22013088509
+ *
+ * The setting of the multicast/unicast bit usually wouldn't
+ * matter for read operations (which always return the value
+ * from a single register instance regardless of how that bit
+ * is set), but some platforms have a workaround requiring us
+ * to remain in multicast mode for reads. There's no real
+ * downside to this, so we'll just go ahead and do so on all
+ * platforms; we'll only clear the multicast bit from the mask
+ * when exlicitly doing a write operation.
+ */
+ if (rw_flag == FW_REG_WRITE)
+ mcr_mask |= GEN11_MCR_MULTICAST;
+ } else {
+ mcr_mask = GEN8_MCR_SLICE_MASK | GEN8_MCR_SUBSLICE_MASK;
+ mcr_ss = GEN8_MCR_SLICE(group) | GEN8_MCR_SUBSLICE(instance);
+ }
+
+ old_mcr = mcr = intel_uncore_read_fw(uncore, GEN8_MCR_SELECTOR);
+
+ mcr &= ~mcr_mask;
+ mcr |= mcr_ss;
+ intel_uncore_write_fw(uncore, GEN8_MCR_SELECTOR, mcr);
+
+ if (rw_flag == FW_REG_READ)
+ val = intel_uncore_read_fw(uncore, reg);
+ else
+ intel_uncore_write_fw(uncore, reg, value);
+
+ mcr &= ~mcr_mask;
+ mcr |= old_mcr & mcr_mask;
+
+ intel_uncore_write_fw(uncore, GEN8_MCR_SELECTOR, mcr);
+
+ return val;
+}
+
+static u32 rw_with_mcr_steering(struct intel_uncore *uncore,
+ i915_reg_t reg, u8 rw_flag,
+ int group, int instance,
+ u32 value)
+{
+ enum forcewake_domains fw_domains;
+ u32 val;
+
+ fw_domains = intel_uncore_forcewake_for_reg(uncore, reg,
+ rw_flag);
+ fw_domains |= intel_uncore_forcewake_for_reg(uncore,
+ GEN8_MCR_SELECTOR,
+ FW_REG_READ | FW_REG_WRITE);
+
+ spin_lock_irq(&uncore->lock);
+ intel_uncore_forcewake_get__locked(uncore, fw_domains);
+
+ val = rw_with_mcr_steering_fw(uncore, reg, rw_flag, group, instance, value);
+
+ intel_uncore_forcewake_put__locked(uncore, fw_domains);
+ spin_unlock_irq(&uncore->lock);
+
+ return val;
+}
+
+/**
+ * intel_gt_mcr_read - read a specific instance of an MCR register
+ * @gt: GT structure
+ * @reg: the MCR register to read
+ * @group: the MCR group
+ * @instance: the MCR instance
+ *
+ * Returns the value read from an MCR register after steering toward a specific
+ * group/instance.
+ */
+u32 intel_gt_mcr_read(struct intel_gt *gt,
+ i915_reg_t reg,
+ int group, int instance)
+{
+ return rw_with_mcr_steering(gt->uncore, reg, FW_REG_READ, group, instance, 0);
+}
+
+/**
+ * intel_gt_mcr_unicast_write - write a specific instance of an MCR register
+ * @gt: GT structure
+ * @reg: the MCR register to write
+ * @value: value to write
+ * @group: the MCR group
+ * @instance: the MCR instance
+ *
+ * Write an MCR register in unicast mode after steering toward a specific
+ * group/instance.
+ */
+void intel_gt_mcr_unicast_write(struct intel_gt *gt, i915_reg_t reg, u32 value,
+ int group, int instance)
+{
+ rw_with_mcr_steering(gt->uncore, reg, FW_REG_WRITE, group, instance, value);
+}
+
+/**
+ * intel_gt_mcr_multicast_write - write a value to all instances of an MCR register
+ * @gt: GT structure
+ * @reg: the MCR register to write
+ * @value: value to write
+ *
+ * Write an MCR register in multicast mode to update all instances.
+ */
+void intel_gt_mcr_multicast_write(struct intel_gt *gt,
+ i915_reg_t reg, u32 value)
+{
+ intel_uncore_write(gt->uncore, reg, value);
+}
+
+/**
+ * intel_gt_mcr_multicast_write_fw - write a value to all instances of an MCR register
+ * @gt: GT structure
+ * @reg: the MCR register to write
+ * @value: value to write
+ *
+ * Write an MCR register in multicast mode to update all instances. This
+ * function assumes the caller is already holding any necessary forcewake
+ * domains; use intel_gt_mcr_multicast_write() in cases where forcewake should
+ * be obtained automatically.
+ */
+void intel_gt_mcr_multicast_write_fw(struct intel_gt *gt, i915_reg_t reg, u32 value)
+{
+ intel_uncore_write_fw(gt->uncore, reg, value);
+}
+
+/*
+ * reg_needs_read_steering - determine whether a register read requires
+ * explicit steering
+ * @gt: GT structure
+ * @reg: the register to check steering requirements for
+ * @type: type of multicast steering to check
+ *
+ * Determines whether @reg needs explicit steering of a specific type for
+ * reads.
+ *
+ * Returns false if @reg does not belong to a register range of the given
+ * steering type, or if the default (subslice-based) steering IDs are suitable
+ * for @type steering too.
+ */
+static bool reg_needs_read_steering(struct intel_gt *gt,
+ i915_reg_t reg,
+ enum intel_steering_type type)
+{
+ const u32 offset = i915_mmio_reg_offset(reg);
+ const struct intel_mmio_range *entry;
+
+ if (likely(!gt->steering_table[type]))
+ return false;
+
+ for (entry = gt->steering_table[type]; entry->end; entry++) {
+ if (offset >= entry->start && offset <= entry->end)
+ return true;
+ }
+
+ return false;
+}
+
+/*
+ * get_nonterminated_steering - determines valid IDs for a class of MCR steering
+ * @gt: GT structure
+ * @type: multicast register type
+ * @group: Group ID returned
+ * @instance: Instance ID returned
+ *
+ * Determines group and instance values that will steer reads of the specified
+ * MCR class to a non-terminated instance.
+ */
+static void get_nonterminated_steering(struct intel_gt *gt,
+ enum intel_steering_type type,
+ u8 *group, u8 *instance)
+{
+ switch (type) {
+ case L3BANK:
+ *group = 0; /* unused */
+ *instance = __ffs(gt->info.l3bank_mask);
+ break;
+ case MSLICE:
+ GEM_WARN_ON(!HAS_MSLICE_STEERING(gt->i915));
+ *group = __ffs(gt->info.mslice_mask);
+ *instance = 0; /* unused */
+ break;
+ case LNCF:
+ /*
+ * An LNCF is always present if its mslice is present, so we
+ * can safely just steer to LNCF 0 in all cases.
+ */
+ GEM_WARN_ON(!HAS_MSLICE_STEERING(gt->i915));
+ *group = __ffs(gt->info.mslice_mask) << 1;
+ *instance = 0; /* unused */
+ break;
+ case INSTANCE0:
+ /*
+ * There are a lot of MCR types for which instance (0, 0)
+ * will always provide a non-terminated value.
+ */
+ *group = 0;
+ *instance = 0;
+ break;
+ default:
+ MISSING_CASE(type);
+ *group = 0;
+ *instance = 0;
+ }
+}
+
+/**
+ * intel_gt_mcr_get_nonterminated_steering - find group/instance values that
+ * will steer a register to a non-terminated instance
+ * @gt: GT structure
+ * @reg: register for which the steering is required
+ * @group: return variable for group steering
+ * @instance: return variable for instance steering
+ *
+ * This function returns a group/instance pair that is guaranteed to work for
+ * read steering of the given register. Note that a value will be returned even
+ * if the register is not replicated and therefore does not actually require
+ * steering.
+ */
+void intel_gt_mcr_get_nonterminated_steering(struct intel_gt *gt,
+ i915_reg_t reg,
+ u8 *group, u8 *instance)
+{
+ int type;
+
+ for (type = 0; type < NUM_STEERING_TYPES; type++) {
+ if (reg_needs_read_steering(gt, reg, type)) {
+ get_nonterminated_steering(gt, type, group, instance);
+ return;
+ }
+ }
+
+ *group = gt->default_steering.groupid;
+ *instance = gt->default_steering.instanceid;
+}
+
+/**
+ * intel_gt_mcr_read_any_fw - reads one instance of an MCR register
+ * @gt: GT structure
+ * @reg: register to read
+ *
+ * Reads a GT MCR register. The read will be steered to a non-terminated
+ * instance (i.e., one that isn't fused off or powered down by power gating).
+ * This function assumes the caller is already holding any necessary forcewake
+ * domains; use intel_gt_mcr_read_any() in cases where forcewake should be
+ * obtained automatically.
+ *
+ * Returns the value from a non-terminated instance of @reg.
+ */
+u32 intel_gt_mcr_read_any_fw(struct intel_gt *gt, i915_reg_t reg)
+{
+ int type;
+ u8 group, instance;
+
+ for (type = 0; type < NUM_STEERING_TYPES; type++) {
+ if (reg_needs_read_steering(gt, reg, type)) {
+ get_nonterminated_steering(gt, type, &group, &instance);
+ return rw_with_mcr_steering_fw(gt->uncore, reg,
+ FW_REG_READ,
+ group, instance, 0);
+ }
+ }
+
+ return intel_uncore_read_fw(gt->uncore, reg);
+}
+
+/**
+ * intel_gt_mcr_read_any - reads one instance of an MCR register
+ * @gt: GT structure
+ * @reg: register to read
+ *
+ * Reads a GT MCR register. The read will be steered to a non-terminated
+ * instance (i.e., one that isn't fused off or powered down by power gating).
+ *
+ * Returns the value from a non-terminated instance of @reg.
+ */
+u32 intel_gt_mcr_read_any(struct intel_gt *gt, i915_reg_t reg)
+{
+ int type;
+ u8 group, instance;
+
+ for (type = 0; type < NUM_STEERING_TYPES; type++) {
+ if (reg_needs_read_steering(gt, reg, type)) {
+ get_nonterminated_steering(gt, type, &group, &instance);
+ return rw_with_mcr_steering(gt->uncore, reg,
+ FW_REG_READ,
+ group, instance, 0);
+ }
+ }
+
+ return intel_uncore_read(gt->uncore, reg);
+}
+
+static void report_steering_type(struct drm_printer *p,
+ struct intel_gt *gt,
+ enum intel_steering_type type,
+ bool dump_table)
+{
+ const struct intel_mmio_range *entry;
+ u8 group, instance;
+
+ BUILD_BUG_ON(ARRAY_SIZE(intel_steering_types) != NUM_STEERING_TYPES);
+
+ if (!gt->steering_table[type]) {
+ drm_printf(p, "%s steering: uses default steering\n",
+ intel_steering_types[type]);
+ return;
+ }
+
+ get_nonterminated_steering(gt, type, &group, &instance);
+ drm_printf(p, "%s steering: group=0x%x, instance=0x%x\n",
+ intel_steering_types[type], group, instance);
+
+ if (!dump_table)
+ return;
+
+ for (entry = gt->steering_table[type]; entry->end; entry++)
+ drm_printf(p, "\t0x%06x - 0x%06x\n", entry->start, entry->end);
+}
+
+void intel_gt_mcr_report_steering(struct drm_printer *p, struct intel_gt *gt,
+ bool dump_table)
+{
+ drm_printf(p, "Default steering: group=0x%x, instance=0x%x\n",
+ gt->default_steering.groupid,
+ gt->default_steering.instanceid);
+
+ if (IS_PONTEVECCHIO(gt->i915)) {
+ report_steering_type(p, gt, INSTANCE0, dump_table);
+ } else if (HAS_MSLICE_STEERING(gt->i915)) {
+ report_steering_type(p, gt, MSLICE, dump_table);
+ report_steering_type(p, gt, LNCF, dump_table);
+ }
+}
+
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_mcr.h b/drivers/gpu/drm/i915/gt/intel_gt_mcr.h
new file mode 100644
index 0000000000000000000000000000000000000000..506b0cbc8db351f75d3df086915ba01d889827d2
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/intel_gt_mcr.h
@@ -0,0 +1,34 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2022 Intel Corporation
+ */
+
+#ifndef __INTEL_GT_MCR__
+#define __INTEL_GT_MCR__
+
+#include "intel_gt_types.h"
+
+void intel_gt_mcr_init(struct intel_gt *gt);
+
+u32 intel_gt_mcr_read(struct intel_gt *gt,
+ i915_reg_t reg,
+ int group, int instance);
+u32 intel_gt_mcr_read_any_fw(struct intel_gt *gt, i915_reg_t reg);
+u32 intel_gt_mcr_read_any(struct intel_gt *gt, i915_reg_t reg);
+
+void intel_gt_mcr_unicast_write(struct intel_gt *gt,
+ i915_reg_t reg, u32 value,
+ int group, int instance);
+void intel_gt_mcr_multicast_write(struct intel_gt *gt,
+ i915_reg_t reg, u32 value);
+void intel_gt_mcr_multicast_write_fw(struct intel_gt *gt,
+ i915_reg_t reg, u32 value);
+
+void intel_gt_mcr_get_nonterminated_steering(struct intel_gt *gt,
+ i915_reg_t reg,
+ u8 *group, u8 *instance);
+
+void intel_gt_mcr_report_steering(struct drm_printer *p, struct intel_gt *gt,
+ bool dump_table);
+
+#endif /* __INTEL_GT_MCR__ */
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_pm_debugfs.c b/drivers/gpu/drm/i915/gt/intel_gt_pm_debugfs.c
index 90a4408650378ab7e7601852821475f278cc4af3..40bdd4cb629feadcd70506d0de871582b688c7b4 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_pm_debugfs.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt_pm_debugfs.c
@@ -100,14 +100,16 @@ static int vlv_drpc(struct seq_file *m)
{
struct intel_gt *gt = m->private;
struct intel_uncore *uncore = gt->uncore;
- u32 rcctl1, pw_status;
+ u32 rcctl1, pw_status, mt_fwake_req;
+ mt_fwake_req = intel_uncore_read_fw(uncore, FORCEWAKE_MT);
pw_status = intel_uncore_read(uncore, VLV_GTLC_PW_STATUS);
rcctl1 = intel_uncore_read(uncore, GEN6_RC_CONTROL);
seq_printf(m, "RC6 Enabled: %s\n",
str_yes_no(rcctl1 & (GEN7_RC_CTL_TO_MODE |
GEN6_RC_CTL_EI_MODE(1))));
+ seq_printf(m, "Multi-threaded Forcewake Request: 0x%x\n", mt_fwake_req);
seq_printf(m, "Render Power Well: %s\n",
(pw_status & VLV_GTLC_PW_RENDER_STATUS_MASK) ? "Up" : "Down");
seq_printf(m, "Media Power Well: %s\n",
@@ -124,9 +126,10 @@ static int gen6_drpc(struct seq_file *m)
struct intel_gt *gt = m->private;
struct drm_i915_private *i915 = gt->i915;
struct intel_uncore *uncore = gt->uncore;
- u32 gt_core_status, rcctl1, rc6vids = 0;
+ u32 gt_core_status, mt_fwake_req, rcctl1, rc6vids = 0;
u32 gen9_powergate_enable = 0, gen9_powergate_status = 0;
+ mt_fwake_req = intel_uncore_read_fw(uncore, FORCEWAKE_MT);
gt_core_status = intel_uncore_read_fw(uncore, GEN6_GT_CORE_STATUS);
rcctl1 = intel_uncore_read(uncore, GEN6_RC_CONTROL);
@@ -178,6 +181,7 @@ static int gen6_drpc(struct seq_file *m)
seq_printf(m, "Core Power Down: %s\n",
str_yes_no(gt_core_status & GEN6_CORE_CPD_STATE_MASK));
+ seq_printf(m, "Multi-threaded Forcewake Request: 0x%x\n", mt_fwake_req);
if (GRAPHICS_VER(i915) >= 9) {
seq_printf(m, "Render Power Well: %s\n",
(gen9_powergate_status &
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_regs.h b/drivers/gpu/drm/i915/gt/intel_gt_regs.h
index a0a49c16babd36b3f577dfb5e33229e7a2807e6e..37c1095d8603b42bb5dadc145a2d59bfa74601ea 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_regs.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt_regs.h
@@ -140,6 +140,7 @@
#define FF_SLICE_CS_CHICKEN2 _MMIO(0x20e4)
#define GEN9_TSG_BARRIER_ACK_DISABLE (1 << 8)
#define GEN9_POOLED_EU_LOAD_BALANCING_FIX_DISABLE (1 << 10)
+#define GEN12_PERF_FIX_BALANCING_CFE_DISABLE REG_BIT(15)
#define GEN9_CS_DEBUG_MODE1 _MMIO(0x20ec)
#define FF_DOP_CLOCK_GATE_DISABLE REG_BIT(1)
@@ -323,8 +324,11 @@
#define GEN12_PAT_INDEX(index) _MMIO(0x4800 + (index) * 4)
-#define XEHPSDV_FLAT_CCS_BASE_ADDR _MMIO(0x4910)
-#define XEHPSDV_CCS_BASE_SHIFT 8
+#define XEHP_TILE0_ADDR_RANGE _MMIO(0x4900)
+#define XEHP_TILE_LMEM_RANGE_SHIFT 8
+
+#define XEHP_FLAT_CCS_BASE_ADDR _MMIO(0x4910)
+#define XEHP_CCS_BASE_SHIFT 8
#define GAMTARBMODE _MMIO(0x4a08)
#define ARB_MODE_BWGTLB_DISABLE (1 << 9)
@@ -561,6 +565,7 @@
#define GEN11_GT_VEBOX_DISABLE_MASK (0x0f << GEN11_GT_VEBOX_DISABLE_SHIFT)
#define GEN12_GT_COMPUTE_DSS_ENABLE _MMIO(0x9144)
+#define XEHPC_GT_COMPUTE_DSS_ENABLE_EXT _MMIO(0x9148)
#define GEN6_UCGCTL1 _MMIO(0x9400)
#define GEN6_GAMUNIT_CLOCK_GATE_DISABLE (1 << 22)
@@ -597,24 +602,32 @@
/* GEN11 changed all bit defs except for FULL & RENDER */
#define GEN11_GRDOM_FULL GEN6_GRDOM_FULL
#define GEN11_GRDOM_RENDER GEN6_GRDOM_RENDER
-#define GEN11_GRDOM_BLT (1 << 2)
-#define GEN11_GRDOM_GUC (1 << 3)
-#define GEN11_GRDOM_MEDIA (1 << 5)
-#define GEN11_GRDOM_MEDIA2 (1 << 6)
-#define GEN11_GRDOM_MEDIA3 (1 << 7)
-#define GEN11_GRDOM_MEDIA4 (1 << 8)
-#define GEN11_GRDOM_MEDIA5 (1 << 9)
-#define GEN11_GRDOM_MEDIA6 (1 << 10)
-#define GEN11_GRDOM_MEDIA7 (1 << 11)
-#define GEN11_GRDOM_MEDIA8 (1 << 12)
-#define GEN11_GRDOM_VECS (1 << 13)
-#define GEN11_GRDOM_VECS2 (1 << 14)
-#define GEN11_GRDOM_VECS3 (1 << 15)
-#define GEN11_GRDOM_VECS4 (1 << 16)
-#define GEN11_GRDOM_SFC0 (1 << 17)
-#define GEN11_GRDOM_SFC1 (1 << 18)
-#define GEN11_GRDOM_SFC2 (1 << 19)
-#define GEN11_GRDOM_SFC3 (1 << 20)
+#define XEHPC_GRDOM_BLT8 REG_BIT(31)
+#define XEHPC_GRDOM_BLT7 REG_BIT(30)
+#define XEHPC_GRDOM_BLT6 REG_BIT(29)
+#define XEHPC_GRDOM_BLT5 REG_BIT(28)
+#define XEHPC_GRDOM_BLT4 REG_BIT(27)
+#define XEHPC_GRDOM_BLT3 REG_BIT(26)
+#define XEHPC_GRDOM_BLT2 REG_BIT(25)
+#define XEHPC_GRDOM_BLT1 REG_BIT(24)
+#define GEN11_GRDOM_SFC3 REG_BIT(20)
+#define GEN11_GRDOM_SFC2 REG_BIT(19)
+#define GEN11_GRDOM_SFC1 REG_BIT(18)
+#define GEN11_GRDOM_SFC0 REG_BIT(17)
+#define GEN11_GRDOM_VECS4 REG_BIT(16)
+#define GEN11_GRDOM_VECS3 REG_BIT(15)
+#define GEN11_GRDOM_VECS2 REG_BIT(14)
+#define GEN11_GRDOM_VECS REG_BIT(13)
+#define GEN11_GRDOM_MEDIA8 REG_BIT(12)
+#define GEN11_GRDOM_MEDIA7 REG_BIT(11)
+#define GEN11_GRDOM_MEDIA6 REG_BIT(10)
+#define GEN11_GRDOM_MEDIA5 REG_BIT(9)
+#define GEN11_GRDOM_MEDIA4 REG_BIT(8)
+#define GEN11_GRDOM_MEDIA3 REG_BIT(7)
+#define GEN11_GRDOM_MEDIA2 REG_BIT(6)
+#define GEN11_GRDOM_MEDIA REG_BIT(5)
+#define GEN11_GRDOM_GUC REG_BIT(3)
+#define GEN11_GRDOM_BLT REG_BIT(2)
#define GEN11_VCS_SFC_RESET_BIT(instance) (GEN11_GRDOM_SFC0 << ((instance) >> 1))
#define GEN11_VECS_SFC_RESET_BIT(instance) (GEN11_GRDOM_SFC0 << (instance))
@@ -622,6 +635,7 @@
#define GEN7_MISCCPCTL _MMIO(0x9424)
#define GEN7_DOP_CLOCK_GATE_ENABLE (1 << 0)
+#define GEN12_DOP_CLOCK_GATE_RENDER_ENABLE REG_BIT(1)
#define GEN8_DOP_CLOCK_GATE_CFCLK_ENABLE (1 << 2)
#define GEN8_DOP_CLOCK_GATE_GUC_ENABLE (1 << 4)
#define GEN8_DOP_CLOCK_GATE_MEDIA_ENABLE (1 << 6)
@@ -732,6 +746,7 @@
#define GEN6_AGGRESSIVE_TURBO (0 << 15)
#define GEN9_SW_REQ_UNSLICE_RATIO_SHIFT 23
#define GEN9_IGNORE_SLICE_RATIO (0 << 0)
+#define GEN12_MEDIA_FREQ_RATIO REG_BIT(13)
#define GEN6_RC_VIDEO_FREQ _MMIO(0xa00c)
#define GEN6_RC_CTL_RC6pp_ENABLE (1 << 16)
@@ -969,6 +984,11 @@
#define XEHP_L3SCQREG7 _MMIO(0xb188)
#define BLEND_FILL_CACHING_OPT_DIS REG_BIT(3)
+#define XEHPC_L3SCRUB _MMIO(0xb18c)
+#define SCRUB_CL_DWNGRADE_SHARED REG_BIT(12)
+#define SCRUB_RATE_PER_BANK_MASK REG_GENMASK(2, 0)
+#define SCRUB_RATE_4B_PER_CLK REG_FIELD_PREP(SCRUB_RATE_PER_BANK_MASK, 0x6)
+
#define L3SQCREG1_CCS0 _MMIO(0xb200)
#define FLUSHALLNONCOH REG_BIT(5)
@@ -1060,8 +1080,10 @@
#define GEN9_ENABLE_GPGPU_PREEMPTION REG_BIT(2)
#define GEN10_CACHE_MODE_SS _MMIO(0xe420)
-#define ENABLE_PREFETCH_INTO_IC REG_BIT(3)
+#define ENABLE_EU_COUNT_FOR_TDL_FLUSH REG_BIT(10)
+#define DISABLE_ECC REG_BIT(5)
#define FLOAT_BLEND_OPTIMIZATION_ENABLE REG_BIT(4)
+#define ENABLE_PREFETCH_INTO_IC REG_BIT(3)
#define EU_PERF_CNTL0 _MMIO(0xe458)
#define EU_PERF_CNTL4 _MMIO(0xe45c)
@@ -1476,6 +1498,14 @@
#define GEN11_KCR (19)
#define GEN11_GTPM (16)
#define GEN11_BCS (15)
+#define XEHPC_BCS1 (14)
+#define XEHPC_BCS2 (13)
+#define XEHPC_BCS3 (12)
+#define XEHPC_BCS4 (11)
+#define XEHPC_BCS5 (10)
+#define XEHPC_BCS6 (9)
+#define XEHPC_BCS7 (8)
+#define XEHPC_BCS8 (23)
#define GEN12_CCS3 (7)
#define GEN12_CCS2 (6)
#define GEN12_CCS1 (5)
@@ -1521,6 +1551,10 @@
#define GEN11_GUNIT_CSME_INTR_MASK _MMIO(0x1900f4)
#define GEN12_CCS0_CCS1_INTR_MASK _MMIO(0x190100)
#define GEN12_CCS2_CCS3_INTR_MASK _MMIO(0x190104)
+#define XEHPC_BCS1_BCS2_INTR_MASK _MMIO(0x190110)
+#define XEHPC_BCS3_BCS4_INTR_MASK _MMIO(0x190114)
+#define XEHPC_BCS5_BCS6_INTR_MASK _MMIO(0x190118)
+#define XEHPC_BCS7_BCS8_INTR_MASK _MMIO(0x19011c)
#define GEN12_SFC_DONE(n) _MMIO(0x1cc000 + (n) * 0x1000)
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_sysfs.c b/drivers/gpu/drm/i915/gt/intel_gt_sysfs.c
index 8ec8bc660c8c2bbf88c551bcfac3294753b0123b..9e4ebf53379bcaf8a17afd24ec921b492b136267 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_sysfs.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt_sysfs.c
@@ -24,7 +24,7 @@ bool is_object_gt(struct kobject *kobj)
static struct intel_gt *kobj_to_gt(struct kobject *kobj)
{
- return container_of(kobj, struct kobj_gt, base)->gt;
+ return container_of(kobj, struct intel_gt, sysfs_gt);
}
struct intel_gt *intel_gt_sysfs_get_drvdata(struct device *dev,
@@ -72,9 +72,9 @@ static struct attribute *id_attrs[] = {
};
ATTRIBUTE_GROUPS(id);
+/* A kobject needs a release() method even if it does nothing */
static void kobj_gt_release(struct kobject *kobj)
{
- kfree(kobj);
}
static struct kobj_type kobj_gt_type = {
@@ -85,8 +85,6 @@ static struct kobj_type kobj_gt_type = {
void intel_gt_sysfs_register(struct intel_gt *gt)
{
- struct kobj_gt *kg;
-
/*
* We need to make things right with the
* ABI compatibility. The files were originally
@@ -98,25 +96,22 @@ void intel_gt_sysfs_register(struct intel_gt *gt)
if (gt_is_root(gt))
intel_gt_sysfs_pm_init(gt, gt_get_parent_obj(gt));
- kg = kzalloc(sizeof(*kg), GFP_KERNEL);
- if (!kg)
+ /* init and xfer ownership to sysfs tree */
+ if (kobject_init_and_add(>->sysfs_gt, &kobj_gt_type,
+ gt->i915->sysfs_gt, "gt%d", gt->info.id))
goto exit_fail;
- kobject_init(&kg->base, &kobj_gt_type);
- kg->gt = gt;
-
- /* xfer ownership to sysfs tree */
- if (kobject_add(&kg->base, gt->i915->sysfs_gt, "gt%d", gt->info.id))
- goto exit_kobj_put;
-
- intel_gt_sysfs_pm_init(gt, &kg->base);
+ intel_gt_sysfs_pm_init(gt, >->sysfs_gt);
return;
-exit_kobj_put:
- kobject_put(&kg->base);
-
exit_fail:
+ kobject_put(>->sysfs_gt);
drm_warn(>->i915->drm,
"failed to initialize gt%d sysfs root\n", gt->info.id);
}
+
+void intel_gt_sysfs_unregister(struct intel_gt *gt)
+{
+ kobject_put(>->sysfs_gt);
+}
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_sysfs.h b/drivers/gpu/drm/i915/gt/intel_gt_sysfs.h
index 9471b26752cfcfeccffc5c159d551925a3778fb6..a99aa7e8b01a631f85080f7e9da13421362887c4 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_sysfs.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt_sysfs.h
@@ -13,11 +13,6 @@
struct intel_gt;
-struct kobj_gt {
- struct kobject base;
- struct intel_gt *gt;
-};
-
bool is_object_gt(struct kobject *kobj);
struct drm_i915_private *kobj_to_i915(struct kobject *kobj);
@@ -28,6 +23,7 @@ intel_gt_create_kobj(struct intel_gt *gt,
const char *name);
void intel_gt_sysfs_register(struct intel_gt *gt);
+void intel_gt_sysfs_unregister(struct intel_gt *gt);
struct intel_gt *intel_gt_sysfs_get_drvdata(struct device *dev,
const char *name);
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_sysfs_pm.c b/drivers/gpu/drm/i915/gt/intel_gt_sysfs_pm.c
index f76b6cf8040ec86ace1285356b1639836118b014..73a8b46e0234430ec08515c93fdad7c4547a38e2 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_sysfs_pm.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt_sysfs_pm.c
@@ -14,6 +14,7 @@
#include "intel_gt_regs.h"
#include "intel_gt_sysfs.h"
#include "intel_gt_sysfs_pm.h"
+#include "intel_pcode.h"
#include "intel_rc6.h"
#include "intel_rps.h"
@@ -558,6 +559,174 @@ static const struct attribute *freq_attrs[] = {
NULL
};
+/*
+ * Scaling for multipliers (aka frequency factors).
+ * The format of the value in the register is u8.8.
+ *
+ * The presentation to userspace is inspired by the perf event framework.
+ * See:
+ * Documentation/ABI/testing/sysfs-bus-event_source-devices-events
+ * for description of:
+ * /sys/bus/event_source/devices/<pmu>/events/<event>.scale
+ *
+ * Summary: Expose two sysfs files for each multiplier.
+ *
+ * 1. File <attr> contains a raw hardware value.
+ * 2. File <attr>.scale contains the multiplicative scale factor to be
+ * used by userspace to compute the actual value.
+ *
+ * So userspace knows that to get the frequency_factor it multiplies the
+ * provided value by the specified scale factor and vice-versa.
+ *
+ * That way there is no precision loss in the kernel interface and API
+ * is future proof should one day the hardware register change to u16.u16,
+ * on some platform. (Or any other fixed point representation.)
+ *
+ * Example:
+ * File <attr> contains the value 2.5, represented as u8.8 0x0280, which
+ * is comprised of:
+ * - an integer part of 2
+ * - a fractional part of 0x80 (representing 0x80 / 2^8 == 0x80 / 256).
+ * File <attr>.scale contains a string representation of floating point
+ * value 0.00390625 (which is (1 / 256)).
+ * Userspace computes the actual value:
+ * 0x0280 * 0.00390625 -> 2.5
+ * or converts an actual value to the value to be written into <attr>:
+ * 2.5 / 0.00390625 -> 0x0280
+ */
+
+#define U8_8_VAL_MASK 0xffff
+#define U8_8_SCALE_TO_VALUE "0.00390625"
+
+static ssize_t freq_factor_scale_show(struct device *dev,
+ struct device_attribute *attr,
+ char *buff)
+{
+ return sysfs_emit(buff, "%s\n", U8_8_SCALE_TO_VALUE);
+}
+
+static u32 media_ratio_mode_to_factor(u32 mode)
+{
+ /* 0 -> 0, 1 -> 256, 2 -> 128 */
+ return !mode ? mode : 256 / mode;
+}
+
+static ssize_t media_freq_factor_show(struct device *dev,
+ struct device_attribute *attr,
+ char *buff)
+{
+ struct intel_gt *gt = intel_gt_sysfs_get_drvdata(dev, attr->attr.name);
+ struct intel_guc_slpc *slpc = >->uc.guc.slpc;
+ intel_wakeref_t wakeref;
+ u32 mode;
+
+ /*
+ * Retrieve media_ratio_mode from GEN6_RPNSWREQ bit 13 set by
+ * GuC. GEN6_RPNSWREQ:13 value 0 represents 1:2 and 1 represents 1:1
+ */
+ if (IS_XEHPSDV(gt->i915) &&
+ slpc->media_ratio_mode == SLPC_MEDIA_RATIO_MODE_DYNAMIC_CONTROL) {
+ /*
+ * For XEHPSDV dynamic mode GEN6_RPNSWREQ:13 does not contain
+ * the media_ratio_mode, just return the cached media ratio
+ */
+ mode = slpc->media_ratio_mode;
+ } else {
+ with_intel_runtime_pm(gt->uncore->rpm, wakeref)
+ mode = intel_uncore_read(gt->uncore, GEN6_RPNSWREQ);
+ mode = REG_FIELD_GET(GEN12_MEDIA_FREQ_RATIO, mode) ?
+ SLPC_MEDIA_RATIO_MODE_FIXED_ONE_TO_ONE :
+ SLPC_MEDIA_RATIO_MODE_FIXED_ONE_TO_TWO;
+ }
+
+ return sysfs_emit(buff, "%u\n", media_ratio_mode_to_factor(mode));
+}
+
+static ssize_t media_freq_factor_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buff, size_t count)
+{
+ struct intel_gt *gt = intel_gt_sysfs_get_drvdata(dev, attr->attr.name);
+ struct intel_guc_slpc *slpc = >->uc.guc.slpc;
+ u32 factor, mode;
+ int err;
+
+ err = kstrtou32(buff, 0, &factor);
+ if (err)
+ return err;
+
+ for (mode = SLPC_MEDIA_RATIO_MODE_DYNAMIC_CONTROL;
+ mode <= SLPC_MEDIA_RATIO_MODE_FIXED_ONE_TO_TWO; mode++)
+ if (factor == media_ratio_mode_to_factor(mode))
+ break;
+
+ if (mode > SLPC_MEDIA_RATIO_MODE_FIXED_ONE_TO_TWO)
+ return -EINVAL;
+
+ err = intel_guc_slpc_set_media_ratio_mode(slpc, mode);
+ if (!err) {
+ slpc->media_ratio_mode = mode;
+ DRM_DEBUG("Set slpc->media_ratio_mode to %d", mode);
+ }
+ return err ?: count;
+}
+
+static ssize_t media_RP0_freq_mhz_show(struct device *dev,
+ struct device_attribute *attr,
+ char *buff)
+{
+ struct intel_gt *gt = intel_gt_sysfs_get_drvdata(dev, attr->attr.name);
+ u32 val;
+ int err;
+
+ err = snb_pcode_read_p(gt->uncore, XEHP_PCODE_FREQUENCY_CONFIG,
+ PCODE_MBOX_FC_SC_READ_FUSED_P0,
+ PCODE_MBOX_DOMAIN_MEDIAFF, &val);
+
+ if (err)
+ return err;
+
+ /* Fused media RP0 read from pcode is in units of 50 MHz */
+ val *= GT_FREQUENCY_MULTIPLIER;
+
+ return sysfs_emit(buff, "%u\n", val);
+}
+
+static ssize_t media_RPn_freq_mhz_show(struct device *dev,
+ struct device_attribute *attr,
+ char *buff)
+{
+ struct intel_gt *gt = intel_gt_sysfs_get_drvdata(dev, attr->attr.name);
+ u32 val;
+ int err;
+
+ err = snb_pcode_read_p(gt->uncore, XEHP_PCODE_FREQUENCY_CONFIG,
+ PCODE_MBOX_FC_SC_READ_FUSED_PN,
+ PCODE_MBOX_DOMAIN_MEDIAFF, &val);
+
+ if (err)
+ return err;
+
+ /* Fused media RPn read from pcode is in units of 50 MHz */
+ val *= GT_FREQUENCY_MULTIPLIER;
+
+ return sysfs_emit(buff, "%u\n", val);
+}
+
+static DEVICE_ATTR_RW(media_freq_factor);
+static struct device_attribute dev_attr_media_freq_factor_scale =
+ __ATTR(media_freq_factor.scale, 0444, freq_factor_scale_show, NULL);
+static DEVICE_ATTR_RO(media_RP0_freq_mhz);
+static DEVICE_ATTR_RO(media_RPn_freq_mhz);
+
+static const struct attribute *media_perf_power_attrs[] = {
+ &dev_attr_media_freq_factor.attr,
+ &dev_attr_media_freq_factor_scale.attr,
+ &dev_attr_media_RP0_freq_mhz.attr,
+ &dev_attr_media_RPn_freq_mhz.attr,
+ NULL
+};
+
static int intel_sysfs_rps_init(struct intel_gt *gt, struct kobject *kobj,
const struct attribute * const *attrs)
{
@@ -599,4 +768,12 @@ void intel_gt_sysfs_pm_init(struct intel_gt *gt, struct kobject *kobj)
drm_warn(>->i915->drm,
"failed to create gt%u throttle sysfs files (%pe)",
gt->info.id, ERR_PTR(ret));
+
+ if (HAS_MEDIA_RATIO_MODE(gt->i915) && intel_uc_uses_guc_slpc(>->uc)) {
+ ret = sysfs_create_files(kobj, media_perf_power_attrs);
+ if (ret)
+ drm_warn(>->i915->drm,
+ "failed to create gt%u media_perf_power_attrs sysfs (%pe)\n",
+ gt->info.id, ERR_PTR(ret));
+ }
}
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_types.h b/drivers/gpu/drm/i915/gt/intel_gt_types.h
index b06611c1d4ada19860d07be87ec5a4411bfde81e..df708802889dfc00e17863295b11bba5bf7d2e90 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt_types.h
@@ -59,6 +59,13 @@ enum intel_steering_type {
MSLICE,
LNCF,
+ /*
+ * On some platforms there are multiple types of MCR registers that
+ * will always return a non-terminated value at instance (0, 0). We'll
+ * lump those all into a single category to keep things simple.
+ */
+ INSTANCE0,
+
NUM_STEERING_TYPES
};
@@ -221,9 +228,13 @@ struct intel_gt {
struct {
u8 uc_index;
+ u8 wb_index; /* Only used on HAS_L3_CCS_READ() platforms */
} mocs;
struct intel_pxp pxp;
+
+ /* gt/gtN sysfs */
+ struct kobject sysfs_gt;
};
enum intel_gt_scratch_field {
diff --git a/drivers/gpu/drm/i915/gt/intel_gtt.h b/drivers/gpu/drm/i915/gt/intel_gtt.h
index a40d928b38884d2e12ef9e717ddc3da059e50448..e639434e97fdb40dcfa2af0b0bb84d2de9ff5617 100644
--- a/drivers/gpu/drm/i915/gt/intel_gtt.h
+++ b/drivers/gpu/drm/i915/gt/intel_gtt.h
@@ -306,6 +306,15 @@ struct i915_address_space {
struct i915_vma_resource *vma_res,
enum i915_cache_level cache_level,
u32 flags);
+ void (*raw_insert_page)(struct i915_address_space *vm,
+ dma_addr_t addr,
+ u64 offset,
+ enum i915_cache_level cache_level,
+ u32 flags);
+ void (*raw_insert_entries)(struct i915_address_space *vm,
+ struct i915_vma_resource *vma_res,
+ enum i915_cache_level cache_level,
+ u32 flags);
void (*cleanup)(struct i915_address_space *vm);
void (*foreach)(struct i915_address_space *vm,
@@ -345,6 +354,19 @@ struct i915_ggtt {
bool do_idle_maps;
+ /**
+ * @pte_lost: Are ptes lost on resume?
+ *
+ * Whether the system was recently restored from hibernate and
+ * thus may have lost pte content.
+ */
+ bool pte_lost;
+
+ /**
+ * @probed_pte: Probed pte value on suspend. Re-checked on resume.
+ */
+ u64 probed_pte;
+
int mtrr;
/** Bit 6 swizzling required for X tiling */
@@ -548,14 +570,13 @@ i915_page_dir_dma_addr(const struct i915_ppgtt *ppgtt, const unsigned int n)
void ppgtt_init(struct i915_ppgtt *ppgtt, struct intel_gt *gt,
unsigned long lmem_pt_obj_flags);
-
void intel_ggtt_bind_vma(struct i915_address_space *vm,
- struct i915_vm_pt_stash *stash,
- struct i915_vma_resource *vma_res,
- enum i915_cache_level cache_level,
- u32 flags);
+ struct i915_vm_pt_stash *stash,
+ struct i915_vma_resource *vma_res,
+ enum i915_cache_level cache_level,
+ u32 flags);
void intel_ggtt_unbind_vma(struct i915_address_space *vm,
- struct i915_vma_resource *vma_res);
+ struct i915_vma_resource *vma_res);
int i915_ggtt_probe_hw(struct drm_i915_private *i915);
int i915_ggtt_init_hw(struct drm_i915_private *i915);
@@ -581,6 +602,17 @@ bool i915_ggtt_resume_vm(struct i915_address_space *vm);
void i915_ggtt_suspend(struct i915_ggtt *gtt);
void i915_ggtt_resume(struct i915_ggtt *ggtt);
+/**
+ * i915_ggtt_mark_pte_lost - Mark ggtt ptes as lost or clear such a marking
+ * @i915 The device private.
+ * @val whether the ptes should be marked as lost.
+ *
+ * In some cases pte content is retained across suspend, but typically lost
+ * across hibernate. Typically they should be marked as lost on
+ * hibernation restore and such marking cleared on suspend.
+ */
+void i915_ggtt_mark_pte_lost(struct drm_i915_private *i915, bool val);
+
void
fill_page_dma(struct drm_i915_gem_object *p, const u64 val, unsigned int count);
@@ -627,7 +659,6 @@ release_pd_entry(struct i915_page_directory * const pd,
struct i915_page_table * const pt,
const struct drm_i915_gem_object * const scratch);
void gen6_ggtt_invalidate(struct i915_ggtt *ggtt);
-void gen8_ggtt_invalidate(struct i915_ggtt *ggtt);
void ppgtt_bind_vma(struct i915_address_space *vm,
struct i915_vm_pt_stash *stash,
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.h b/drivers/gpu/drm/i915/gt/intel_lrc.h
index 31be734010db3bc5cd7234caff95a42268e035a3..a390f0813c8b64e5b0ee08a48a9ca7e875ad9e94 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.h
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.h
@@ -111,16 +111,6 @@ enum {
#define XEHP_SW_COUNTER_SHIFT 58
#define XEHP_SW_COUNTER_WIDTH 6
-static inline u32 lrc_desc_priority(int prio)
-{
- if (prio > I915_PRIORITY_NORMAL)
- return GEN12_CTX_PRIORITY_HIGH;
- else if (prio < I915_PRIORITY_NORMAL)
- return GEN12_CTX_PRIORITY_LOW;
- else
- return GEN12_CTX_PRIORITY_NORMAL;
-}
-
static inline void lrc_runtime_start(struct intel_context *ce)
{
struct intel_context_stats *stats = &ce->stats;
diff --git a/drivers/gpu/drm/i915/gt/intel_mocs.c b/drivers/gpu/drm/i915/gt/intel_mocs.c
index c4c37585ae8cc7ce9a8a2bd915b544631b33d6ec..c6ebe2781076465260a51e944d0e424c06843e9c 100644
--- a/drivers/gpu/drm/i915/gt/intel_mocs.c
+++ b/drivers/gpu/drm/i915/gt/intel_mocs.c
@@ -23,6 +23,7 @@ struct drm_i915_mocs_table {
unsigned int n_entries;
const struct drm_i915_mocs_entry *table;
u8 uc_index;
+ u8 wb_index; /* Only used on HAS_L3_CCS_READ() platforms */
u8 unused_entries_index;
};
@@ -47,6 +48,7 @@ struct drm_i915_mocs_table {
/* Helper defines */
#define GEN9_NUM_MOCS_ENTRIES 64 /* 63-64 are reserved, but configured. */
+#define PVC_NUM_MOCS_ENTRIES 3
/* (e)LLC caching options */
/*
@@ -394,6 +396,17 @@ static const struct drm_i915_mocs_entry dg2_mocs_table_g10_ax[] = {
MOCS_ENTRY(3, 0, L3_3_WB | L3_LKUP(1)),
};
+static const struct drm_i915_mocs_entry pvc_mocs_table[] = {
+ /* Error */
+ MOCS_ENTRY(0, 0, L3_3_WB),
+
+ /* UC */
+ MOCS_ENTRY(1, 0, L3_1_UC),
+
+ /* WB */
+ MOCS_ENTRY(2, 0, L3_3_WB),
+};
+
enum {
HAS_GLOBAL_MOCS = BIT(0),
HAS_ENGINE_MOCS = BIT(1),
@@ -423,7 +436,14 @@ static unsigned int get_mocs_settings(const struct drm_i915_private *i915,
memset(table, 0, sizeof(struct drm_i915_mocs_table));
table->unused_entries_index = I915_MOCS_PTE;
- if (IS_DG2(i915)) {
+ if (IS_PONTEVECCHIO(i915)) {
+ table->size = ARRAY_SIZE(pvc_mocs_table);
+ table->table = pvc_mocs_table;
+ table->n_entries = PVC_NUM_MOCS_ENTRIES;
+ table->uc_index = 1;
+ table->wb_index = 2;
+ table->unused_entries_index = 2;
+ } else if (IS_DG2(i915)) {
if (IS_DG2_GRAPHICS_STEP(i915, G10, STEP_A0, STEP_B0)) {
table->size = ARRAY_SIZE(dg2_mocs_table_g10_ax);
table->table = dg2_mocs_table_g10_ax;
@@ -622,6 +642,8 @@ void intel_set_mocs_index(struct intel_gt *gt)
get_mocs_settings(gt->i915, &table);
gt->mocs.uc_index = table.uc_index;
+ if (HAS_L3_CCS_READ(gt->i915))
+ gt->mocs.wb_index = table.wb_index;
}
void intel_mocs_init(struct intel_gt *gt)
diff --git a/drivers/gpu/drm/i915/gt/intel_region_lmem.c b/drivers/gpu/drm/i915/gt/intel_region_lmem.c
index f5111c0a006058c2c67dec1c8ee95fa74adb9e51..d09b996a975944c0cbf78e9d96654c644bbdf12e 100644
--- a/drivers/gpu/drm/i915/gt/intel_region_lmem.c
+++ b/drivers/gpu/drm/i915/gt/intel_region_lmem.c
@@ -12,6 +12,7 @@
#include "gem/i915_gem_region.h"
#include "gem/i915_gem_ttm.h"
#include "gt/intel_gt.h"
+#include "gt/intel_gt_mcr.h"
#include "gt/intel_gt_regs.h"
static int
@@ -101,14 +102,24 @@ static struct intel_memory_region *setup_lmem(struct intel_gt *gt)
return ERR_PTR(-ENODEV);
if (HAS_FLAT_CCS(i915)) {
+ resource_size_t lmem_range;
u64 tile_stolen, flat_ccs_base;
- lmem_size = pci_resource_len(pdev, 2);
- flat_ccs_base = intel_gt_read_register(gt, XEHPSDV_FLAT_CCS_BASE_ADDR);
- flat_ccs_base = (flat_ccs_base >> XEHPSDV_CCS_BASE_SHIFT) * SZ_64K;
+ lmem_range = intel_gt_mcr_read_any(&i915->gt0, XEHP_TILE0_ADDR_RANGE) & 0xFFFF;
+ lmem_size = lmem_range >> XEHP_TILE_LMEM_RANGE_SHIFT;
+ lmem_size *= SZ_1G;
+
+ flat_ccs_base = intel_gt_mcr_read_any(gt, XEHP_FLAT_CCS_BASE_ADDR);
+ flat_ccs_base = (flat_ccs_base >> XEHP_CCS_BASE_SHIFT) * SZ_64K;
+
+ /* FIXME: Remove this when we have small-bar enabled */
+ if (pci_resource_len(pdev, 2) < lmem_size) {
+ drm_err(&i915->drm, "System requires small-BAR support, which is currently unsupported on this kernel\n");
+ return ERR_PTR(-EINVAL);
+ }
if (GEM_WARN_ON(lmem_size < flat_ccs_base))
- return ERR_PTR(-ENODEV);
+ return ERR_PTR(-EIO);
tile_stolen = lmem_size - flat_ccs_base;
@@ -131,7 +142,7 @@ static struct intel_memory_region *setup_lmem(struct intel_gt *gt)
io_start = pci_resource_start(pdev, 2);
io_size = min(pci_resource_len(pdev, 2), lmem_size);
if (!io_size)
- return ERR_PTR(-ENODEV);
+ return ERR_PTR(-EIO);
min_page_size = HAS_64K_PAGES(i915) ? I915_GTT_PAGE_SIZE_64K :
I915_GTT_PAGE_SIZE_4K;
diff --git a/drivers/gpu/drm/i915/gt/intel_ring_submission.c b/drivers/gpu/drm/i915/gt/intel_ring_submission.c
index 5423bfd301adf8f8c7f9fc474cb2981f6e07bf81..d5d6f1fadcae397ff1d060f47ce4a178f484aa73 100644
--- a/drivers/gpu/drm/i915/gt/intel_ring_submission.c
+++ b/drivers/gpu/drm/i915/gt/intel_ring_submission.c
@@ -117,7 +117,9 @@ static void flush_cs_tlb(struct intel_engine_cs *engine)
return;
/* ring should be idle before issuing a sync flush*/
- GEM_DEBUG_WARN_ON((ENGINE_READ(engine, RING_MI_MODE) & MODE_IDLE) == 0);
+ if ((ENGINE_READ(engine, RING_MI_MODE) & MODE_IDLE) == 0)
+ drm_warn(&engine->i915->drm, "%s not idle before sync flush!\n",
+ engine->name);
ENGINE_WRITE_FW(engine, RING_INSTPM,
_MASKED_BIT_ENABLE(INSTPM_TLB_INVALIDATE |
@@ -596,8 +598,9 @@ static void ring_context_reset(struct intel_context *ce)
clear_bit(CONTEXT_VALID_BIT, &ce->flags);
}
-static void ring_context_ban(struct intel_context *ce,
- struct i915_request *rq)
+static void ring_context_revoke(struct intel_context *ce,
+ struct i915_request *rq,
+ unsigned int preempt_timeout_ms)
{
struct intel_engine_cs *engine;
@@ -632,7 +635,7 @@ static const struct intel_context_ops ring_context_ops = {
.cancel_request = ring_context_cancel_request,
- .ban = ring_context_ban,
+ .revoke = ring_context_revoke,
.pre_pin = ring_context_pre_pin,
.pin = ring_context_pin,
diff --git a/drivers/gpu/drm/i915/gt/intel_rps.c b/drivers/gpu/drm/i915/gt/intel_rps.c
index 9b991df2cfbb417c648b91c82c1886f9df5a21fa..fb3f57ee450bc935d1ead4ec97ce0079a13d76f7 100644
--- a/drivers/gpu/drm/i915/gt/intel_rps.c
+++ b/drivers/gpu/drm/i915/gt/intel_rps.c
@@ -1075,7 +1075,9 @@ static u32 intel_rps_read_state_cap(struct intel_rps *rps)
struct drm_i915_private *i915 = rps_to_i915(rps);
struct intel_uncore *uncore = rps_to_uncore(rps);
- if (IS_XEHPSDV(i915))
+ if (IS_PONTEVECCHIO(i915))
+ return intel_uncore_read(uncore, PVC_RP_STATE_CAP);
+ else if (IS_XEHPSDV(i915))
return intel_uncore_read(uncore, XEHPSDV_RP_STATE_CAP);
else if (IS_GEN9_LP(i915))
return intel_uncore_read(uncore, BXT_RP_STATE_CAP);
diff --git a/drivers/gpu/drm/i915/gt/intel_sseu.c b/drivers/gpu/drm/i915/gt/intel_sseu.c
index fdd25691beda0207389c5f49759080025a4fd531..c6d3050604c89d4f71a770175379e72b245a31aa 100644
--- a/drivers/gpu/drm/i915/gt/intel_sseu.c
+++ b/drivers/gpu/drm/i915/gt/intel_sseu.c
@@ -16,11 +16,6 @@ void intel_sseu_set_info(struct sseu_dev_info *sseu, u8 max_slices,
sseu->max_slices = max_slices;
sseu->max_subslices = max_subslices;
sseu->max_eus_per_subslice = max_eus_per_subslice;
-
- sseu->ss_stride = GEN_SSEU_STRIDE(sseu->max_subslices);
- GEM_BUG_ON(sseu->ss_stride > GEN_MAX_SUBSLICE_STRIDE);
- sseu->eu_stride = GEN_SSEU_STRIDE(sseu->max_eus_per_subslice);
- GEM_BUG_ON(sseu->eu_stride > GEN_MAX_EU_STRIDE);
}
unsigned int
@@ -28,152 +23,240 @@ intel_sseu_subslice_total(const struct sseu_dev_info *sseu)
{
unsigned int i, total = 0;
- for (i = 0; i < ARRAY_SIZE(sseu->subslice_mask); i++)
- total += hweight8(sseu->subslice_mask[i]);
+ if (sseu->has_xehp_dss)
+ return bitmap_weight(sseu->subslice_mask.xehp,
+ XEHP_BITMAP_BITS(sseu->subslice_mask));
+
+ for (i = 0; i < ARRAY_SIZE(sseu->subslice_mask.hsw); i++)
+ total += hweight8(sseu->subslice_mask.hsw[i]);
return total;
}
-static u32
-sseu_get_subslices(const struct sseu_dev_info *sseu,
- const u8 *subslice_mask, u8 slice)
+unsigned int
+intel_sseu_get_hsw_subslices(const struct sseu_dev_info *sseu, u8 slice)
{
- int i, offset = slice * sseu->ss_stride;
- u32 mask = 0;
-
- GEM_BUG_ON(slice >= sseu->max_slices);
-
- for (i = 0; i < sseu->ss_stride; i++)
- mask |= (u32)subslice_mask[offset + i] << i * BITS_PER_BYTE;
+ WARN_ON(sseu->has_xehp_dss);
+ if (WARN_ON(slice >= sseu->max_slices))
+ return 0;
- return mask;
+ return sseu->subslice_mask.hsw[slice];
}
-u32 intel_sseu_get_subslices(const struct sseu_dev_info *sseu, u8 slice)
+static u16 sseu_get_eus(const struct sseu_dev_info *sseu, int slice,
+ int subslice)
{
- return sseu_get_subslices(sseu, sseu->subslice_mask, slice);
+ if (sseu->has_xehp_dss) {
+ WARN_ON(slice > 0);
+ return sseu->eu_mask.xehp[subslice];
+ } else {
+ return sseu->eu_mask.hsw[slice][subslice];
+ }
}
-static u32 sseu_get_geometry_subslices(const struct sseu_dev_info *sseu)
+static void sseu_set_eus(struct sseu_dev_info *sseu, int slice, int subslice,
+ u16 eu_mask)
{
- return sseu_get_subslices(sseu, sseu->geometry_subslice_mask, 0);
+ GEM_WARN_ON(eu_mask && __fls(eu_mask) >= sseu->max_eus_per_subslice);
+ if (sseu->has_xehp_dss) {
+ GEM_WARN_ON(slice > 0);
+ sseu->eu_mask.xehp[subslice] = eu_mask;
+ } else {
+ sseu->eu_mask.hsw[slice][subslice] = eu_mask;
+ }
}
-u32 intel_sseu_get_compute_subslices(const struct sseu_dev_info *sseu)
+static u16 compute_eu_total(const struct sseu_dev_info *sseu)
{
- return sseu_get_subslices(sseu, sseu->compute_subslice_mask, 0);
-}
+ int s, ss, total = 0;
-void intel_sseu_set_subslices(struct sseu_dev_info *sseu, int slice,
- u8 *subslice_mask, u32 ss_mask)
-{
- int offset = slice * sseu->ss_stride;
+ for (s = 0; s < sseu->max_slices; s++)
+ for (ss = 0; ss < sseu->max_subslices; ss++)
+ if (sseu->has_xehp_dss)
+ total += hweight16(sseu->eu_mask.xehp[ss]);
+ else
+ total += hweight16(sseu->eu_mask.hsw[s][ss]);
- memcpy(&subslice_mask[offset], &ss_mask, sseu->ss_stride);
+ return total;
}
-unsigned int
-intel_sseu_subslices_per_slice(const struct sseu_dev_info *sseu, u8 slice)
+/**
+ * intel_sseu_copy_eumask_to_user - Copy EU mask into a userspace buffer
+ * @to: Pointer to userspace buffer to copy to
+ * @sseu: SSEU structure containing EU mask to copy
+ *
+ * Copies the EU mask to a userspace buffer in the format expected by
+ * the query ioctl's topology queries.
+ *
+ * Returns the result of the copy_to_user() operation.
+ */
+int intel_sseu_copy_eumask_to_user(void __user *to,
+ const struct sseu_dev_info *sseu)
{
- return hweight32(intel_sseu_get_subslices(sseu, slice));
-}
+ u8 eu_mask[GEN_SS_MASK_SIZE * GEN_MAX_EU_STRIDE] = {};
+ int eu_stride = GEN_SSEU_STRIDE(sseu->max_eus_per_subslice);
+ int len = sseu->max_slices * sseu->max_subslices * eu_stride;
+ int s, ss, i;
-static int sseu_eu_idx(const struct sseu_dev_info *sseu, int slice,
- int subslice)
-{
- int slice_stride = sseu->max_subslices * sseu->eu_stride;
+ for (s = 0; s < sseu->max_slices; s++) {
+ for (ss = 0; ss < sseu->max_subslices; ss++) {
+ int uapi_offset =
+ s * sseu->max_subslices * eu_stride +
+ ss * eu_stride;
+ u16 mask = sseu_get_eus(sseu, s, ss);
+
+ for (i = 0; i < eu_stride; i++)
+ eu_mask[uapi_offset + i] =
+ (mask >> (BITS_PER_BYTE * i)) & 0xff;
+ }
+ }
- return slice * slice_stride + subslice * sseu->eu_stride;
+ return copy_to_user(to, eu_mask, len);
}
-static u16 sseu_get_eus(const struct sseu_dev_info *sseu, int slice,
- int subslice)
+/**
+ * intel_sseu_copy_ssmask_to_user - Copy subslice mask into a userspace buffer
+ * @to: Pointer to userspace buffer to copy to
+ * @sseu: SSEU structure containing subslice mask to copy
+ *
+ * Copies the subslice mask to a userspace buffer in the format expected by
+ * the query ioctl's topology queries.
+ *
+ * Returns the result of the copy_to_user() operation.
+ */
+int intel_sseu_copy_ssmask_to_user(void __user *to,
+ const struct sseu_dev_info *sseu)
{
- int i, offset = sseu_eu_idx(sseu, slice, subslice);
- u16 eu_mask = 0;
+ u8 ss_mask[GEN_SS_MASK_SIZE] = {};
+ int ss_stride = GEN_SSEU_STRIDE(sseu->max_subslices);
+ int len = sseu->max_slices * ss_stride;
+ int s, ss, i;
- for (i = 0; i < sseu->eu_stride; i++)
- eu_mask |=
- ((u16)sseu->eu_mask[offset + i]) << (i * BITS_PER_BYTE);
+ for (s = 0; s < sseu->max_slices; s++) {
+ for (ss = 0; ss < sseu->max_subslices; ss++) {
+ i = s * ss_stride * BITS_PER_BYTE + ss;
- return eu_mask;
-}
+ if (!intel_sseu_has_subslice(sseu, s, ss))
+ continue;
-static void sseu_set_eus(struct sseu_dev_info *sseu, int slice, int subslice,
- u16 eu_mask)
-{
- int i, offset = sseu_eu_idx(sseu, slice, subslice);
+ ss_mask[i / BITS_PER_BYTE] |= BIT(i % BITS_PER_BYTE);
+ }
+ }
- for (i = 0; i < sseu->eu_stride; i++)
- sseu->eu_mask[offset + i] =
- (eu_mask >> (BITS_PER_BYTE * i)) & 0xff;
+ return copy_to_user(to, ss_mask, len);
}
-static u16 compute_eu_total(const struct sseu_dev_info *sseu)
+static void gen11_compute_sseu_info(struct sseu_dev_info *sseu,
+ u32 ss_en, u16 eu_en)
{
- u16 i, total = 0;
+ u32 valid_ss_mask = GENMASK(sseu->max_subslices - 1, 0);
+ int ss;
- for (i = 0; i < ARRAY_SIZE(sseu->eu_mask); i++)
- total += hweight8(sseu->eu_mask[i]);
+ sseu->slice_mask |= BIT(0);
+ sseu->subslice_mask.hsw[0] = ss_en & valid_ss_mask;
- return total;
+ for (ss = 0; ss < sseu->max_subslices; ss++)
+ if (intel_sseu_has_subslice(sseu, 0, ss))
+ sseu_set_eus(sseu, 0, ss, eu_en);
+
+ sseu->eu_per_subslice = hweight16(eu_en);
+ sseu->eu_total = compute_eu_total(sseu);
}
-static u32 get_ss_stride_mask(struct sseu_dev_info *sseu, u8 s, u32 ss_en)
+static void xehp_compute_sseu_info(struct sseu_dev_info *sseu,
+ u16 eu_en)
{
- u32 ss_mask;
+ int ss;
- ss_mask = ss_en >> (s * sseu->max_subslices);
- ss_mask &= GENMASK(sseu->max_subslices - 1, 0);
+ sseu->slice_mask |= BIT(0);
- return ss_mask;
+ bitmap_or(sseu->subslice_mask.xehp,
+ sseu->compute_subslice_mask.xehp,
+ sseu->geometry_subslice_mask.xehp,
+ XEHP_BITMAP_BITS(sseu->subslice_mask));
+
+ for (ss = 0; ss < sseu->max_subslices; ss++)
+ if (intel_sseu_has_subslice(sseu, 0, ss))
+ sseu_set_eus(sseu, 0, ss, eu_en);
+
+ sseu->eu_per_subslice = hweight16(eu_en);
+ sseu->eu_total = compute_eu_total(sseu);
}
-static void gen11_compute_sseu_info(struct sseu_dev_info *sseu, u8 s_en,
- u32 g_ss_en, u32 c_ss_en, u16 eu_en)
+static void
+xehp_load_dss_mask(struct intel_uncore *uncore,
+ intel_sseu_ss_mask_t *ssmask,
+ int numregs,
+ ...)
{
- int s, ss;
+ va_list argp;
+ u32 fuse_val[I915_MAX_SS_FUSE_REGS] = {};
+ int i;
- /* g_ss_en/c_ss_en represent entire subslice mask across all slices */
- GEM_BUG_ON(sseu->max_slices * sseu->max_subslices >
- sizeof(g_ss_en) * BITS_PER_BYTE);
+ if (WARN_ON(numregs > I915_MAX_SS_FUSE_REGS))
+ numregs = I915_MAX_SS_FUSE_REGS;
- for (s = 0; s < sseu->max_slices; s++) {
- if ((s_en & BIT(s)) == 0)
- continue;
+ va_start(argp, numregs);
+ for (i = 0; i < numregs; i++)
+ fuse_val[i] = intel_uncore_read(uncore, va_arg(argp, i915_reg_t));
+ va_end(argp);
- sseu->slice_mask |= BIT(s);
-
- /*
- * XeHP introduces the concept of compute vs geometry DSS. To
- * reduce variation between GENs around subslice usage, store a
- * mask for both the geometry and compute enabled masks since
- * userspace will need to be able to query these masks
- * independently. Also compute a total enabled subslice count
- * for the purposes of selecting subslices to use in a
- * particular GEM context.
- */
- intel_sseu_set_subslices(sseu, s, sseu->compute_subslice_mask,
- get_ss_stride_mask(sseu, s, c_ss_en));
- intel_sseu_set_subslices(sseu, s, sseu->geometry_subslice_mask,
- get_ss_stride_mask(sseu, s, g_ss_en));
- intel_sseu_set_subslices(sseu, s, sseu->subslice_mask,
- get_ss_stride_mask(sseu, s,
- g_ss_en | c_ss_en));
+ bitmap_from_arr32(ssmask->xehp, fuse_val, numregs * 32);
+}
- for (ss = 0; ss < sseu->max_subslices; ss++)
- if (intel_sseu_has_subslice(sseu, s, ss))
- sseu_set_eus(sseu, s, ss, eu_en);
+static void xehp_sseu_info_init(struct intel_gt *gt)
+{
+ struct sseu_dev_info *sseu = >->info.sseu;
+ struct intel_uncore *uncore = gt->uncore;
+ u16 eu_en = 0;
+ u8 eu_en_fuse;
+ int num_compute_regs, num_geometry_regs;
+ int eu;
+
+ if (IS_PONTEVECCHIO(gt->i915)) {
+ num_geometry_regs = 0;
+ num_compute_regs = 2;
+ } else {
+ num_geometry_regs = 1;
+ num_compute_regs = 1;
}
- sseu->eu_per_subslice = hweight16(eu_en);
- sseu->eu_total = compute_eu_total(sseu);
+
+ /*
+ * The concept of slice has been removed in Xe_HP. To be compatible
+ * with prior generations, assume a single slice across the entire
+ * device. Then calculate out the DSS for each workload type within
+ * that software slice.
+ */
+ intel_sseu_set_info(sseu, 1,
+ 32 * max(num_geometry_regs, num_compute_regs),
+ HAS_ONE_EU_PER_FUSE_BIT(gt->i915) ? 8 : 16);
+ sseu->has_xehp_dss = 1;
+
+ xehp_load_dss_mask(uncore, &sseu->geometry_subslice_mask,
+ num_geometry_regs,
+ GEN12_GT_GEOMETRY_DSS_ENABLE);
+ xehp_load_dss_mask(uncore, &sseu->compute_subslice_mask,
+ num_compute_regs,
+ GEN12_GT_COMPUTE_DSS_ENABLE,
+ XEHPC_GT_COMPUTE_DSS_ENABLE_EXT);
+
+ eu_en_fuse = intel_uncore_read(uncore, XEHP_EU_ENABLE) & XEHP_EU_ENA_MASK;
+
+ if (HAS_ONE_EU_PER_FUSE_BIT(gt->i915))
+ eu_en = eu_en_fuse;
+ else
+ for (eu = 0; eu < sseu->max_eus_per_subslice / 2; eu++)
+ if (eu_en_fuse & BIT(eu))
+ eu_en |= BIT(eu * 2) | BIT(eu * 2 + 1);
+
+ xehp_compute_sseu_info(sseu, eu_en);
}
static void gen12_sseu_info_init(struct intel_gt *gt)
{
struct sseu_dev_info *sseu = >->info.sseu;
struct intel_uncore *uncore = gt->uncore;
- u32 g_dss_en, c_dss_en = 0;
+ u32 g_dss_en;
u16 eu_en = 0;
u8 eu_en_fuse;
u8 s_en;
@@ -183,43 +266,28 @@ static void gen12_sseu_info_init(struct intel_gt *gt)
* Gen12 has Dual-Subslices, which behave similarly to 2 gen11 SS.
* Instead of splitting these, provide userspace with an array
* of DSS to more closely represent the hardware resource.
- *
- * In addition, the concept of slice has been removed in Xe_HP.
- * To be compatible with prior generations, assume a single slice
- * across the entire device. Then calculate out the DSS for each
- * workload type within that software slice.
*/
- if (IS_DG2(gt->i915) || IS_XEHPSDV(gt->i915))
- intel_sseu_set_info(sseu, 1, 32, 16);
- else
- intel_sseu_set_info(sseu, 1, 6, 16);
+ intel_sseu_set_info(sseu, 1, 6, 16);
/*
- * As mentioned above, Xe_HP does not have the concept of a slice.
- * Enable one for software backwards compatibility.
+ * Although gen12 architecture supported multiple slices, TGL, RKL,
+ * DG1, and ADL only had a single slice.
*/
- if (GRAPHICS_VER_FULL(gt->i915) >= IP_VER(12, 50))
- s_en = 0x1;
- else
- s_en = intel_uncore_read(uncore, GEN11_GT_SLICE_ENABLE) &
- GEN11_GT_S_ENA_MASK;
+ s_en = intel_uncore_read(uncore, GEN11_GT_SLICE_ENABLE) &
+ GEN11_GT_S_ENA_MASK;
+ drm_WARN_ON(>->i915->drm, s_en != 0x1);
g_dss_en = intel_uncore_read(uncore, GEN12_GT_GEOMETRY_DSS_ENABLE);
- if (GRAPHICS_VER_FULL(gt->i915) >= IP_VER(12, 50))
- c_dss_en = intel_uncore_read(uncore, GEN12_GT_COMPUTE_DSS_ENABLE);
/* one bit per pair of EUs */
- if (GRAPHICS_VER_FULL(gt->i915) >= IP_VER(12, 50))
- eu_en_fuse = intel_uncore_read(uncore, XEHP_EU_ENABLE) & XEHP_EU_ENA_MASK;
- else
- eu_en_fuse = ~(intel_uncore_read(uncore, GEN11_EU_DISABLE) &
- GEN11_EU_DIS_MASK);
+ eu_en_fuse = ~(intel_uncore_read(uncore, GEN11_EU_DISABLE) &
+ GEN11_EU_DIS_MASK);
for (eu = 0; eu < sseu->max_eus_per_subslice / 2; eu++)
if (eu_en_fuse & BIT(eu))
eu_en |= BIT(eu * 2) | BIT(eu * 2 + 1);
- gen11_compute_sseu_info(sseu, s_en, g_dss_en, c_dss_en, eu_en);
+ gen11_compute_sseu_info(sseu, g_dss_en, eu_en);
/* TGL only supports slice-level power gating */
sseu->has_slice_pg = 1;
@@ -238,14 +306,20 @@ static void gen11_sseu_info_init(struct intel_gt *gt)
else
intel_sseu_set_info(sseu, 1, 8, 8);
+ /*
+ * Although gen11 architecture supported multiple slices, ICL and
+ * EHL/JSL only had a single slice in practice.
+ */
s_en = intel_uncore_read(uncore, GEN11_GT_SLICE_ENABLE) &
GEN11_GT_S_ENA_MASK;
+ drm_WARN_ON(>->i915->drm, s_en != 0x1);
+
ss_en = ~intel_uncore_read(uncore, GEN11_GT_SUBSLICE_DISABLE);
eu_en = ~(intel_uncore_read(uncore, GEN11_EU_DISABLE) &
GEN11_EU_DIS_MASK);
- gen11_compute_sseu_info(sseu, s_en, ss_en, 0, eu_en);
+ gen11_compute_sseu_info(sseu, ss_en, eu_en);
/* ICL has no power gating restrictions. */
sseu->has_slice_pg = 1;
@@ -257,7 +331,6 @@ static void cherryview_sseu_info_init(struct intel_gt *gt)
{
struct sseu_dev_info *sseu = >->info.sseu;
u32 fuse;
- u8 subslice_mask = 0;
fuse = intel_uncore_read(gt->uncore, CHV_FUSE_GT);
@@ -271,8 +344,8 @@ static void cherryview_sseu_info_init(struct intel_gt *gt)
(((fuse & CHV_FGT_EU_DIS_SS0_R1_MASK) >>
CHV_FGT_EU_DIS_SS0_R1_SHIFT) << 4);
- subslice_mask |= BIT(0);
- sseu_set_eus(sseu, 0, 0, ~disabled_mask);
+ sseu->subslice_mask.hsw[0] |= BIT(0);
+ sseu_set_eus(sseu, 0, 0, ~disabled_mask & 0xFF);
}
if (!(fuse & CHV_FGT_DISABLE_SS1)) {
@@ -282,12 +355,10 @@ static void cherryview_sseu_info_init(struct intel_gt *gt)
(((fuse & CHV_FGT_EU_DIS_SS1_R1_MASK) >>
CHV_FGT_EU_DIS_SS1_R1_SHIFT) << 4);
- subslice_mask |= BIT(1);
- sseu_set_eus(sseu, 0, 1, ~disabled_mask);
+ sseu->subslice_mask.hsw[0] |= BIT(1);
+ sseu_set_eus(sseu, 0, 1, ~disabled_mask & 0xFF);
}
- intel_sseu_set_subslices(sseu, 0, sseu->subslice_mask, subslice_mask);
-
sseu->eu_total = compute_eu_total(sseu);
/*
@@ -342,8 +413,7 @@ static void gen9_sseu_info_init(struct intel_gt *gt)
/* skip disabled slice */
continue;
- intel_sseu_set_subslices(sseu, s, sseu->subslice_mask,
- subslice_mask);
+ sseu->subslice_mask.hsw[s] = subslice_mask;
eu_disable = intel_uncore_read(uncore, GEN9_EU_DISABLE(s));
for (ss = 0; ss < sseu->max_subslices; ss++) {
@@ -356,7 +426,7 @@ static void gen9_sseu_info_init(struct intel_gt *gt)
eu_disabled_mask = (eu_disable >> (ss * 8)) & eu_mask;
- sseu_set_eus(sseu, s, ss, ~eu_disabled_mask);
+ sseu_set_eus(sseu, s, ss, ~eu_disabled_mask & eu_mask);
eu_per_ss = sseu->max_eus_per_subslice -
hweight8(eu_disabled_mask);
@@ -400,8 +470,8 @@ static void gen9_sseu_info_init(struct intel_gt *gt)
sseu->has_eu_pg = sseu->eu_per_subslice > 2;
if (IS_GEN9_LP(i915)) {
-#define IS_SS_DISABLED(ss) (!(sseu->subslice_mask[0] & BIT(ss)))
- info->has_pooled_eu = hweight8(sseu->subslice_mask[0]) == 3;
+#define IS_SS_DISABLED(ss) (!(sseu->subslice_mask.hsw[0] & BIT(ss)))
+ info->has_pooled_eu = hweight8(sseu->subslice_mask.hsw[0]) == 3;
sseu->min_eu_in_pool = 0;
if (info->has_pooled_eu) {
@@ -455,8 +525,7 @@ static void bdw_sseu_info_init(struct intel_gt *gt)
/* skip disabled slice */
continue;
- intel_sseu_set_subslices(sseu, s, sseu->subslice_mask,
- subslice_mask);
+ sseu->subslice_mask.hsw[s] = subslice_mask;
for (ss = 0; ss < sseu->max_subslices; ss++) {
u8 eu_disabled_mask;
@@ -469,7 +538,7 @@ static void bdw_sseu_info_init(struct intel_gt *gt)
eu_disabled_mask =
eu_disable[s] >> (ss * sseu->max_eus_per_subslice);
- sseu_set_eus(sseu, s, ss, ~eu_disabled_mask);
+ sseu_set_eus(sseu, s, ss, ~eu_disabled_mask & 0xFF);
n_disabled = hweight8(eu_disabled_mask);
@@ -553,8 +622,7 @@ static void hsw_sseu_info_init(struct intel_gt *gt)
sseu->eu_per_subslice);
for (s = 0; s < sseu->max_slices; s++) {
- intel_sseu_set_subslices(sseu, s, sseu->subslice_mask,
- subslice_mask);
+ sseu->subslice_mask.hsw[s] = subslice_mask;
for (ss = 0; ss < sseu->max_subslices; ss++) {
sseu_set_eus(sseu, s, ss,
@@ -574,18 +642,20 @@ void intel_sseu_info_init(struct intel_gt *gt)
{
struct drm_i915_private *i915 = gt->i915;
- if (IS_HASWELL(i915))
- hsw_sseu_info_init(gt);
- else if (IS_CHERRYVIEW(i915))
- cherryview_sseu_info_init(gt);
- else if (IS_BROADWELL(i915))
- bdw_sseu_info_init(gt);
- else if (GRAPHICS_VER(i915) == 9)
- gen9_sseu_info_init(gt);
- else if (GRAPHICS_VER(i915) == 11)
- gen11_sseu_info_init(gt);
+ if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 50))
+ xehp_sseu_info_init(gt);
else if (GRAPHICS_VER(i915) >= 12)
gen12_sseu_info_init(gt);
+ else if (GRAPHICS_VER(i915) >= 11)
+ gen11_sseu_info_init(gt);
+ else if (GRAPHICS_VER(i915) >= 9)
+ gen9_sseu_info_init(gt);
+ else if (IS_BROADWELL(i915))
+ bdw_sseu_info_init(gt);
+ else if (IS_CHERRYVIEW(i915))
+ cherryview_sseu_info_init(gt);
+ else if (IS_HASWELL(i915))
+ hsw_sseu_info_init(gt);
}
u32 intel_sseu_make_rpcs(struct intel_gt *gt,
@@ -641,7 +711,7 @@ u32 intel_sseu_make_rpcs(struct intel_gt *gt,
*/
if (GRAPHICS_VER(i915) == 11 &&
slices == 1 &&
- subslices > min_t(u8, 4, hweight8(sseu->subslice_mask[0]) / 2)) {
+ subslices > min_t(u8, 4, hweight8(sseu->subslice_mask.hsw[0]) / 2)) {
GEM_BUG_ON(subslices & 1);
subslice_pg = false;
@@ -707,14 +777,29 @@ void intel_sseu_dump(const struct sseu_dev_info *sseu, struct drm_printer *p)
{
int s;
- drm_printf(p, "slice total: %u, mask=%04x\n",
- hweight8(sseu->slice_mask), sseu->slice_mask);
- drm_printf(p, "subslice total: %u\n", intel_sseu_subslice_total(sseu));
- for (s = 0; s < sseu->max_slices; s++) {
- drm_printf(p, "slice%d: %u subslices, mask=%08x\n",
- s, intel_sseu_subslices_per_slice(sseu, s),
- intel_sseu_get_subslices(sseu, s));
+ if (sseu->has_xehp_dss) {
+ drm_printf(p, "subslice total: %u\n",
+ intel_sseu_subslice_total(sseu));
+ drm_printf(p, "geometry dss mask=%*pb\n",
+ XEHP_BITMAP_BITS(sseu->geometry_subslice_mask),
+ sseu->geometry_subslice_mask.xehp);
+ drm_printf(p, "compute dss mask=%*pb\n",
+ XEHP_BITMAP_BITS(sseu->compute_subslice_mask),
+ sseu->compute_subslice_mask.xehp);
+ } else {
+ drm_printf(p, "slice total: %u, mask=%04x\n",
+ hweight8(sseu->slice_mask), sseu->slice_mask);
+ drm_printf(p, "subslice total: %u\n",
+ intel_sseu_subslice_total(sseu));
+
+ for (s = 0; s < sseu->max_slices; s++) {
+ u8 ss_mask = sseu->subslice_mask.hsw[s];
+
+ drm_printf(p, "slice%d: %u subslices, mask=%08x\n",
+ s, hweight8(ss_mask), ss_mask);
+ }
}
+
drm_printf(p, "EU total: %u\n", sseu->eu_total);
drm_printf(p, "EU per subslice: %u\n", sseu->eu_per_subslice);
drm_printf(p, "has slice power gating: %s\n",
@@ -731,9 +816,10 @@ static void sseu_print_hsw_topology(const struct sseu_dev_info *sseu,
int s, ss;
for (s = 0; s < sseu->max_slices; s++) {
+ u8 ss_mask = sseu->subslice_mask.hsw[s];
+
drm_printf(p, "slice%d: %u subslice(s) (0x%08x):\n",
- s, intel_sseu_subslices_per_slice(sseu, s),
- intel_sseu_get_subslices(sseu, s));
+ s, hweight8(ss_mask), ss_mask);
for (ss = 0; ss < sseu->max_subslices; ss++) {
u16 enabled_eus = sseu_get_eus(sseu, s, ss);
@@ -747,16 +833,14 @@ static void sseu_print_hsw_topology(const struct sseu_dev_info *sseu,
static void sseu_print_xehp_topology(const struct sseu_dev_info *sseu,
struct drm_printer *p)
{
- u32 g_dss_mask = sseu_get_geometry_subslices(sseu);
- u32 c_dss_mask = intel_sseu_get_compute_subslices(sseu);
int dss;
for (dss = 0; dss < sseu->max_subslices; dss++) {
u16 enabled_eus = sseu_get_eus(sseu, 0, dss);
drm_printf(p, "DSS_%02d: G:%3s C:%3s, %2u EUs (0x%04hx)\n", dss,
- str_yes_no(g_dss_mask & BIT(dss)),
- str_yes_no(c_dss_mask & BIT(dss)),
+ str_yes_no(test_bit(dss, sseu->geometry_subslice_mask.xehp)),
+ str_yes_no(test_bit(dss, sseu->compute_subslice_mask.xehp)),
hweight16(enabled_eus), enabled_eus);
}
}
@@ -774,20 +858,44 @@ void intel_sseu_print_topology(struct drm_i915_private *i915,
}
}
-u16 intel_slicemask_from_dssmask(u64 dss_mask, int dss_per_slice)
+void intel_sseu_print_ss_info(const char *type,
+ const struct sseu_dev_info *sseu,
+ struct seq_file *m)
{
- u16 slice_mask = 0;
+ int s;
+
+ if (sseu->has_xehp_dss) {
+ seq_printf(m, " %s Geometry DSS: %u\n", type,
+ bitmap_weight(sseu->geometry_subslice_mask.xehp,
+ XEHP_BITMAP_BITS(sseu->geometry_subslice_mask)));
+ seq_printf(m, " %s Compute DSS: %u\n", type,
+ bitmap_weight(sseu->compute_subslice_mask.xehp,
+ XEHP_BITMAP_BITS(sseu->compute_subslice_mask)));
+ } else {
+ for (s = 0; s < fls(sseu->slice_mask); s++)
+ seq_printf(m, " %s Slice%i subslices: %u\n", type,
+ s, hweight8(sseu->subslice_mask.hsw[s]));
+ }
+}
+
+u16 intel_slicemask_from_xehp_dssmask(intel_sseu_ss_mask_t dss_mask,
+ int dss_per_slice)
+{
+ intel_sseu_ss_mask_t per_slice_mask = {};
+ unsigned long slice_mask = 0;
int i;
- WARN_ON(sizeof(dss_mask) * 8 / dss_per_slice > 8 * sizeof(slice_mask));
+ WARN_ON(DIV_ROUND_UP(XEHP_BITMAP_BITS(dss_mask), dss_per_slice) >
+ 8 * sizeof(slice_mask));
- for (i = 0; dss_mask; i++) {
- if (dss_mask & GENMASK(dss_per_slice - 1, 0))
+ bitmap_fill(per_slice_mask.xehp, dss_per_slice);
+ for (i = 0; !bitmap_empty(dss_mask.xehp, XEHP_BITMAP_BITS(dss_mask)); i++) {
+ if (bitmap_intersects(dss_mask.xehp, per_slice_mask.xehp, dss_per_slice))
slice_mask |= BIT(i);
- dss_mask >>= dss_per_slice;
+ bitmap_shift_right(dss_mask.xehp, dss_mask.xehp, dss_per_slice,
+ XEHP_BITMAP_BITS(dss_mask));
}
return slice_mask;
}
-
diff --git a/drivers/gpu/drm/i915/gt/intel_sseu.h b/drivers/gpu/drm/i915/gt/intel_sseu.h
index 5c078df4729cbac3219291a5bb40ea8ec75c4ce6..aa87d3832d60d92539413d6cc5f840873c65696a 100644
--- a/drivers/gpu/drm/i915/gt/intel_sseu.h
+++ b/drivers/gpu/drm/i915/gt/intel_sseu.h
@@ -25,12 +25,16 @@ struct drm_printer;
/*
* Maximum number of subslices that can exist within a HSW-style slice. This
* is only relevant to pre-Xe_HP platforms (Xe_HP and beyond use the
- * GEN_MAX_DSS value below).
+ * I915_MAX_SS_FUSE_BITS value below).
*/
#define GEN_MAX_SS_PER_HSW_SLICE 6
-/* Maximum number of DSS on newer platforms (Xe_HP and beyond). */
-#define GEN_MAX_DSS 32
+/*
+ * Maximum number of 32-bit registers used by hardware to express the
+ * enabled/disabled subslices.
+ */
+#define I915_MAX_SS_FUSE_REGS 2
+#define I915_MAX_SS_FUSE_BITS (I915_MAX_SS_FUSE_REGS * 32)
/* Maximum number of EUs that can exist within a subslice or DSS. */
#define GEN_MAX_EUS_PER_SS 16
@@ -38,7 +42,7 @@ struct drm_printer;
#define SSEU_MAX(a, b) ((a) > (b) ? (a) : (b))
/* The maximum number of bits needed to express each subslice/DSS independently */
-#define GEN_SS_MASK_SIZE SSEU_MAX(GEN_MAX_DSS, \
+#define GEN_SS_MASK_SIZE SSEU_MAX(I915_MAX_SS_FUSE_BITS, \
GEN_MAX_HSW_SLICES * GEN_MAX_SS_PER_HSW_SLICE)
#define GEN_SSEU_STRIDE(max_entries) DIV_ROUND_UP(max_entries, BITS_PER_BYTE)
@@ -49,15 +53,28 @@ struct drm_printer;
#define GEN_DSS_PER_CSLICE 8
#define GEN_DSS_PER_MSLICE 8
-#define GEN_MAX_GSLICES (GEN_MAX_DSS / GEN_DSS_PER_GSLICE)
-#define GEN_MAX_CSLICES (GEN_MAX_DSS / GEN_DSS_PER_CSLICE)
+#define GEN_MAX_GSLICES (I915_MAX_SS_FUSE_BITS / GEN_DSS_PER_GSLICE)
+#define GEN_MAX_CSLICES (I915_MAX_SS_FUSE_BITS / GEN_DSS_PER_CSLICE)
+
+typedef union {
+ u8 hsw[GEN_MAX_HSW_SLICES];
+
+ /* Bitmap compatible with linux/bitmap.h; may exceed size of u64 */
+ unsigned long xehp[BITS_TO_LONGS(I915_MAX_SS_FUSE_BITS)];
+} intel_sseu_ss_mask_t;
+
+#define XEHP_BITMAP_BITS(mask) ((int)BITS_PER_TYPE(typeof(mask.xehp)))
struct sseu_dev_info {
u8 slice_mask;
- u8 subslice_mask[GEN_SS_MASK_SIZE];
- u8 geometry_subslice_mask[GEN_SS_MASK_SIZE];
- u8 compute_subslice_mask[GEN_SS_MASK_SIZE];
- u8 eu_mask[GEN_SS_MASK_SIZE * GEN_MAX_EU_STRIDE];
+ intel_sseu_ss_mask_t subslice_mask;
+ intel_sseu_ss_mask_t geometry_subslice_mask;
+ intel_sseu_ss_mask_t compute_subslice_mask;
+ union {
+ u16 hsw[GEN_MAX_HSW_SLICES][GEN_MAX_SS_PER_HSW_SLICE];
+ u16 xehp[I915_MAX_SS_FUSE_BITS];
+ } eu_mask;
+
u16 eu_total;
u8 eu_per_subslice;
u8 min_eu_in_pool;
@@ -66,14 +83,16 @@ struct sseu_dev_info {
u8 has_slice_pg:1;
u8 has_subslice_pg:1;
u8 has_eu_pg:1;
+ /*
+ * For Xe_HP and beyond, the hardware no longer has traditional slices
+ * so we just report the entire DSS pool under a fake "slice 0."
+ */
+ u8 has_xehp_dss:1;
/* Topology fields */
u8 max_slices;
u8 max_subslices;
u8 max_eus_per_subslice;
-
- u8 ss_stride;
- u8 eu_stride;
};
/*
@@ -91,7 +110,7 @@ intel_sseu_from_device_info(const struct sseu_dev_info *sseu)
{
struct intel_sseu value = {
.slice_mask = sseu->slice_mask,
- .subslice_mask = sseu->subslice_mask[0],
+ .subslice_mask = sseu->subslice_mask.hsw[0],
.min_eus_per_subslice = sseu->max_eus_per_subslice,
.max_eus_per_subslice = sseu->max_eus_per_subslice,
};
@@ -103,18 +122,28 @@ static inline bool
intel_sseu_has_subslice(const struct sseu_dev_info *sseu, int slice,
int subslice)
{
- u8 mask;
- int ss_idx = subslice / BITS_PER_BYTE;
-
if (slice >= sseu->max_slices ||
subslice >= sseu->max_subslices)
return false;
- GEM_BUG_ON(ss_idx >= sseu->ss_stride);
-
- mask = sseu->subslice_mask[slice * sseu->ss_stride + ss_idx];
+ if (sseu->has_xehp_dss)
+ return test_bit(subslice, sseu->subslice_mask.xehp);
+ else
+ return sseu->subslice_mask.hsw[slice] & BIT(subslice);
+}
- return mask & BIT(subslice % BITS_PER_BYTE);
+/*
+ * Used to obtain the index of the first DSS. Can start searching from the
+ * beginning of a specific dss group (e.g., gslice, cslice, etc.) if
+ * groupsize and groupnum are non-zero.
+ */
+static inline unsigned int
+intel_sseu_find_first_xehp_dss(const struct sseu_dev_info *sseu, int groupsize,
+ int groupnum)
+{
+ return find_next_bit(sseu->subslice_mask.xehp,
+ XEHP_BITMAP_BITS(sseu->subslice_mask),
+ groupnum * groupsize);
}
void intel_sseu_set_info(struct sseu_dev_info *sseu, u8 max_slices,
@@ -124,14 +153,10 @@ unsigned int
intel_sseu_subslice_total(const struct sseu_dev_info *sseu);
unsigned int
-intel_sseu_subslices_per_slice(const struct sseu_dev_info *sseu, u8 slice);
+intel_sseu_get_hsw_subslices(const struct sseu_dev_info *sseu, u8 slice);
-u32 intel_sseu_get_subslices(const struct sseu_dev_info *sseu, u8 slice);
-
-u32 intel_sseu_get_compute_subslices(const struct sseu_dev_info *sseu);
-
-void intel_sseu_set_subslices(struct sseu_dev_info *sseu, int slice,
- u8 *subslice_mask, u32 ss_mask);
+intel_sseu_ss_mask_t
+intel_sseu_get_compute_subslices(const struct sseu_dev_info *sseu);
void intel_sseu_info_init(struct intel_gt *gt);
@@ -143,6 +168,15 @@ void intel_sseu_print_topology(struct drm_i915_private *i915,
const struct sseu_dev_info *sseu,
struct drm_printer *p);
-u16 intel_slicemask_from_dssmask(u64 dss_mask, int dss_per_slice);
+u16 intel_slicemask_from_xehp_dssmask(intel_sseu_ss_mask_t dss_mask, int dss_per_slice);
+
+int intel_sseu_copy_eumask_to_user(void __user *to,
+ const struct sseu_dev_info *sseu);
+int intel_sseu_copy_ssmask_to_user(void __user *to,
+ const struct sseu_dev_info *sseu);
+
+void intel_sseu_print_ss_info(const char *type,
+ const struct sseu_dev_info *sseu,
+ struct seq_file *m);
#endif /* __INTEL_SSEU_H__ */
diff --git a/drivers/gpu/drm/i915/gt/intel_sseu_debugfs.c b/drivers/gpu/drm/i915/gt/intel_sseu_debugfs.c
index 2d5d011e01db273cd86987aaee9aa45f0eb837c9..c2ee5e1826b5dcbd8b99b5acb71e7270f26591dc 100644
--- a/drivers/gpu/drm/i915/gt/intel_sseu_debugfs.c
+++ b/drivers/gpu/drm/i915/gt/intel_sseu_debugfs.c
@@ -4,6 +4,7 @@
* Copyright © 2020 Intel Corporation
*/
+#include <linux/bitmap.h>
#include <linux/string_helpers.h>
#include "i915_drv.h"
@@ -11,14 +12,6 @@
#include "intel_gt_regs.h"
#include "intel_sseu_debugfs.h"
-static void sseu_copy_subslices(const struct sseu_dev_info *sseu,
- int slice, u8 *to_mask)
-{
- int offset = slice * sseu->ss_stride;
-
- memcpy(&to_mask[offset], &sseu->subslice_mask[offset], sseu->ss_stride);
-}
-
static void cherryview_sseu_device_status(struct intel_gt *gt,
struct sseu_dev_info *sseu)
{
@@ -41,7 +34,7 @@ static void cherryview_sseu_device_status(struct intel_gt *gt,
continue;
sseu->slice_mask = BIT(0);
- sseu->subslice_mask[0] |= BIT(ss);
+ sseu->subslice_mask.hsw[0] |= BIT(ss);
eu_cnt = ((sig1[ss] & CHV_EU08_PG_ENABLE) ? 0 : 2) +
((sig1[ss] & CHV_EU19_PG_ENABLE) ? 0 : 2) +
((sig1[ss] & CHV_EU210_PG_ENABLE) ? 0 : 2) +
@@ -92,7 +85,7 @@ static void gen11_sseu_device_status(struct intel_gt *gt,
continue;
sseu->slice_mask |= BIT(s);
- sseu_copy_subslices(&info->sseu, s, sseu->subslice_mask);
+ sseu->subslice_mask.hsw[s] = info->sseu.subslice_mask.hsw[s];
for (ss = 0; ss < info->sseu.max_subslices; ss++) {
unsigned int eu_cnt;
@@ -147,21 +140,17 @@ static void gen9_sseu_device_status(struct intel_gt *gt,
sseu->slice_mask |= BIT(s);
if (IS_GEN9_BC(gt->i915))
- sseu_copy_subslices(&info->sseu, s,
- sseu->subslice_mask);
+ sseu->subslice_mask.hsw[s] = info->sseu.subslice_mask.hsw[s];
for (ss = 0; ss < info->sseu.max_subslices; ss++) {
unsigned int eu_cnt;
- u8 ss_idx = s * info->sseu.ss_stride +
- ss / BITS_PER_BYTE;
if (IS_GEN9_LP(gt->i915)) {
if (!(s_reg[s] & (GEN9_PGCTL_SS_ACK(ss))))
/* skip disabled subslice */
continue;
- sseu->subslice_mask[ss_idx] |=
- BIT(ss % BITS_PER_BYTE);
+ sseu->subslice_mask.hsw[s] |= BIT(ss);
}
eu_cnt = eu_reg[2 * s + ss / 2] & eu_mask[ss % 2];
@@ -188,8 +177,7 @@ static void bdw_sseu_device_status(struct intel_gt *gt,
if (sseu->slice_mask) {
sseu->eu_per_subslice = info->sseu.eu_per_subslice;
for (s = 0; s < fls(sseu->slice_mask); s++)
- sseu_copy_subslices(&info->sseu, s,
- sseu->subslice_mask);
+ sseu->subslice_mask.hsw[s] = info->sseu.subslice_mask.hsw[s];
sseu->eu_total = sseu->eu_per_subslice *
intel_sseu_subslice_total(sseu);
@@ -208,7 +196,6 @@ static void i915_print_sseu_info(struct seq_file *m,
const struct sseu_dev_info *sseu)
{
const char *type = is_available_info ? "Available" : "Enabled";
- int s;
seq_printf(m, " %s Slice Mask: %04x\n", type,
sseu->slice_mask);
@@ -216,10 +203,7 @@ static void i915_print_sseu_info(struct seq_file *m,
hweight8(sseu->slice_mask));
seq_printf(m, " %s Subslice Total: %u\n", type,
intel_sseu_subslice_total(sseu));
- for (s = 0; s < fls(sseu->slice_mask); s++) {
- seq_printf(m, " %s Slice%i subslices: %u\n", type,
- s, intel_sseu_subslices_per_slice(sseu, s));
- }
+ intel_sseu_print_ss_info(type, sseu, m);
seq_printf(m, " %s EU Total: %u\n", type,
sseu->eu_total);
seq_printf(m, " %s EU Per Subslice: %u\n", type,
diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c
index a05c4b99b3fbc059f9efcc1e1b0dfd0346df18b3..3213c593a55f45a057c70a2a0b756cdc9b8fad9a 100644
--- a/drivers/gpu/drm/i915/gt/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c
@@ -9,6 +9,7 @@
#include "intel_engine_regs.h"
#include "intel_gpu_commands.h"
#include "intel_gt.h"
+#include "intel_gt_mcr.h"
#include "intel_gt_regs.h"
#include "intel_ring.h"
#include "intel_workarounds.h"
@@ -776,7 +777,9 @@ __intel_engine_init_ctx_wa(struct intel_engine_cs *engine,
if (engine->class != RENDER_CLASS)
goto done;
- if (IS_DG2(i915))
+ if (IS_PONTEVECCHIO(i915))
+ ; /* noop; none at this time */
+ else if (IS_DG2(i915))
dg2_ctx_workarounds_init(engine, wal);
else if (IS_XEHPSDV(i915))
; /* noop; none at this time */
@@ -948,8 +951,8 @@ gen9_wa_init_mcr(struct drm_i915_private *i915, struct i915_wa_list *wal)
* on s/ss combo, the read should be done with read_subslice_reg.
*/
slice = ffs(sseu->slice_mask) - 1;
- GEM_BUG_ON(slice >= ARRAY_SIZE(sseu->subslice_mask));
- subslice = ffs(intel_sseu_get_subslices(sseu, slice));
+ GEM_BUG_ON(slice >= ARRAY_SIZE(sseu->subslice_mask.hsw));
+ subslice = ffs(intel_sseu_get_hsw_subslices(sseu, slice));
GEM_BUG_ON(!subslice);
subslice--;
@@ -1080,18 +1083,17 @@ static void __add_mcr_wa(struct intel_gt *gt, struct i915_wa_list *wal,
gt->default_steering.instanceid = subslice;
if (drm_debug_enabled(DRM_UT_DRIVER))
- intel_gt_report_steering(&p, gt, false);
+ intel_gt_mcr_report_steering(&p, gt, false);
}
static void
icl_wa_init_mcr(struct intel_gt *gt, struct i915_wa_list *wal)
{
const struct sseu_dev_info *sseu = >->info.sseu;
- unsigned int slice, subslice;
+ unsigned int subslice;
GEM_BUG_ON(GRAPHICS_VER(gt->i915) < 11);
GEM_BUG_ON(hweight8(sseu->slice_mask) > 1);
- slice = 0;
/*
* Although a platform may have subslices, we need to always steer
@@ -1102,7 +1104,7 @@ icl_wa_init_mcr(struct intel_gt *gt, struct i915_wa_list *wal)
* one of the higher subslices, we run the risk of reading back 0's or
* random garbage.
*/
- subslice = __ffs(intel_sseu_get_subslices(sseu, slice));
+ subslice = __ffs(intel_sseu_get_hsw_subslices(sseu, 0));
/*
* If the subslice we picked above also steers us to a valid L3 bank,
@@ -1112,7 +1114,7 @@ icl_wa_init_mcr(struct intel_gt *gt, struct i915_wa_list *wal)
if (gt->info.l3bank_mask & BIT(subslice))
gt->steering_table[L3BANK] = NULL;
- __add_mcr_wa(gt, wal, slice, subslice);
+ __add_mcr_wa(gt, wal, 0, subslice);
}
static void
@@ -1120,7 +1122,6 @@ xehp_init_mcr(struct intel_gt *gt, struct i915_wa_list *wal)
{
const struct sseu_dev_info *sseu = >->info.sseu;
unsigned long slice, subslice = 0, slice_mask = 0;
- u64 dss_mask = 0;
u32 lncf_mask = 0;
int i;
@@ -1151,8 +1152,8 @@ xehp_init_mcr(struct intel_gt *gt, struct i915_wa_list *wal)
*/
/* Find the potential gslice candidates */
- dss_mask = intel_sseu_get_subslices(sseu, 0);
- slice_mask = intel_slicemask_from_dssmask(dss_mask, GEN_DSS_PER_GSLICE);
+ slice_mask = intel_slicemask_from_xehp_dssmask(sseu->subslice_mask,
+ GEN_DSS_PER_GSLICE);
/*
* Find the potential LNCF candidates. Either LNCF within a valid
@@ -1177,9 +1178,8 @@ xehp_init_mcr(struct intel_gt *gt, struct i915_wa_list *wal)
}
slice = __ffs(slice_mask);
- subslice = __ffs(dss_mask >> (slice * GEN_DSS_PER_GSLICE));
- WARN_ON(subslice > GEN_DSS_PER_GSLICE);
- WARN_ON(dss_mask >> (slice * GEN_DSS_PER_GSLICE) == 0);
+ subslice = intel_sseu_find_first_xehp_dss(sseu, GEN_DSS_PER_GSLICE, slice) %
+ GEN_DSS_PER_GSLICE;
__add_mcr_wa(gt, wal, slice, subslice);
@@ -1196,6 +1196,20 @@ xehp_init_mcr(struct intel_gt *gt, struct i915_wa_list *wal)
__set_mcr_steering(wal, SF_MCR_SELECTOR, 0, 2);
}
+static void
+pvc_init_mcr(struct intel_gt *gt, struct i915_wa_list *wal)
+{
+ unsigned int dss;
+
+ /*
+ * Setup implicit steering for COMPUTE and DSS ranges to the first
+ * non-fused-off DSS. All other types of MCR registers will be
+ * explicitly steered.
+ */
+ dss = intel_sseu_find_first_xehp_dss(>->info.sseu, 0, 0);
+ __add_mcr_wa(gt, wal, dss / GEN_DSS_PER_CSLICE, dss % GEN_DSS_PER_CSLICE);
+}
+
static void
icl_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal)
{
@@ -1487,6 +1501,18 @@ dg2_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal)
* performance guide section.
*/
wa_write_or(wal, GEN12_SQCM, EN_32B_ACCESS);
+
+ /* Wa_14015795083 */
+ wa_write_clr(wal, GEN7_MISCCPCTL, GEN12_DOP_CLOCK_GATE_RENDER_ENABLE);
+}
+
+static void
+pvc_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal)
+{
+ pvc_init_mcr(gt, wal);
+
+ /* Wa_14015795083 */
+ wa_write_clr(wal, GEN7_MISCCPCTL, GEN12_DOP_CLOCK_GATE_RENDER_ENABLE);
}
static void
@@ -1494,7 +1520,9 @@ gt_init_workarounds(struct intel_gt *gt, struct i915_wa_list *wal)
{
struct drm_i915_private *i915 = gt->i915;
- if (IS_DG2(i915))
+ if (IS_PONTEVECCHIO(i915))
+ pvc_gt_workarounds_init(gt, wal);
+ else if (IS_DG2(i915))
dg2_gt_workarounds_init(gt, wal);
else if (IS_XEHPSDV(i915))
xehpsdv_gt_workarounds_init(gt, wal);
@@ -1596,13 +1624,13 @@ wa_list_apply(struct intel_gt *gt, const struct i915_wa_list *wal)
u32 val, old = 0;
/* open-coded rmw due to steering */
- old = wa->clr ? intel_gt_read_register_fw(gt, wa->reg) : 0;
+ old = wa->clr ? intel_gt_mcr_read_any_fw(gt, wa->reg) : 0;
val = (old & ~wa->clr) | wa->set;
if (val != old || !wa->clr)
intel_uncore_write_fw(uncore, wa->reg, val);
if (IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM))
- wa_verify(wa, intel_gt_read_register_fw(gt, wa->reg),
+ wa_verify(wa, intel_gt_mcr_read_any_fw(gt, wa->reg),
wal->name, "application");
}
@@ -1633,7 +1661,7 @@ static bool wa_list_verify(struct intel_gt *gt,
for (i = 0, wa = wal->list; i < wal->count; i++, wa++)
ok &= wa_verify(wa,
- intel_gt_read_register_fw(gt, wa->reg),
+ intel_gt_mcr_read_any_fw(gt, wa->reg),
wal->name, from);
intel_uncore_forcewake_put__locked(uncore, fw);
@@ -1924,6 +1952,32 @@ static void dg2_whitelist_build(struct intel_engine_cs *engine)
}
}
+static void blacklist_trtt(struct intel_engine_cs *engine)
+{
+ struct i915_wa_list *w = &engine->whitelist;
+
+ /*
+ * Prevent read/write access to [0x4400, 0x4600) which covers
+ * the TRTT range across all engines. Note that normally userspace
+ * cannot access the other engines' trtt control, but for simplicity
+ * we cover the entire range on each engine.
+ */
+ whitelist_reg_ext(w, _MMIO(0x4400),
+ RING_FORCE_TO_NONPRIV_DENY |
+ RING_FORCE_TO_NONPRIV_RANGE_64);
+ whitelist_reg_ext(w, _MMIO(0x4500),
+ RING_FORCE_TO_NONPRIV_DENY |
+ RING_FORCE_TO_NONPRIV_RANGE_64);
+}
+
+static void pvc_whitelist_build(struct intel_engine_cs *engine)
+{
+ allow_read_ctx_timestamp(engine);
+
+ /* Wa_16014440446:pvc */
+ blacklist_trtt(engine);
+}
+
void intel_engine_init_whitelist(struct intel_engine_cs *engine)
{
struct drm_i915_private *i915 = engine->i915;
@@ -1931,7 +1985,9 @@ void intel_engine_init_whitelist(struct intel_engine_cs *engine)
wa_init_start(w, "whitelist", engine->name);
- if (IS_DG2(i915))
+ if (IS_PONTEVECCHIO(i915))
+ pvc_whitelist_build(engine);
+ else if (IS_DG2(i915))
dg2_whitelist_build(engine);
else if (IS_XEHPSDV(i915))
xehpsdv_whitelist_build(engine);
@@ -1994,27 +2050,44 @@ void intel_engine_apply_whitelist(struct intel_engine_cs *engine)
static void
engine_fake_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal)
{
- u8 mocs;
+ u8 mocs_w, mocs_r;
/*
- * RING_CMD_CCTL are need to be programed to un-cached
- * for memory writes and reads outputted by Command
- * Streamers on Gen12 onward platforms.
+ * RING_CMD_CCTL specifies the default MOCS entry that will be used
+ * by the command streamer when executing commands that don't have
+ * a way to explicitly specify a MOCS setting. The default should
+ * usually reference whichever MOCS entry corresponds to uncached
+ * behavior, although use of a WB cached entry is recommended by the
+ * spec in certain circumstances on specific platforms.
*/
if (GRAPHICS_VER(engine->i915) >= 12) {
- mocs = engine->gt->mocs.uc_index;
+ mocs_r = engine->gt->mocs.uc_index;
+ mocs_w = engine->gt->mocs.uc_index;
+
+ if (HAS_L3_CCS_READ(engine->i915) &&
+ engine->class == COMPUTE_CLASS) {
+ mocs_r = engine->gt->mocs.wb_index;
+
+ /*
+ * Even on the few platforms where MOCS 0 is a
+ * legitimate table entry, it's never the correct
+ * setting to use here; we can assume the MOCS init
+ * just forgot to initialize wb_index.
+ */
+ drm_WARN_ON(&engine->i915->drm, mocs_r == 0);
+ }
+
wa_masked_field_set(wal,
RING_CMD_CCTL(engine->mmio_base),
CMD_CCTL_MOCS_MASK,
- CMD_CCTL_MOCS_OVERRIDE(mocs, mocs));
+ CMD_CCTL_MOCS_OVERRIDE(mocs_w, mocs_r));
}
}
static bool needs_wa_1308578152(struct intel_engine_cs *engine)
{
- u64 dss_mask = intel_sseu_get_subslices(&engine->gt->info.sseu, 0);
-
- return (dss_mask & GENMASK(GEN_DSS_PER_GSLICE - 1, 0)) == 0;
+ return intel_sseu_find_first_xehp_dss(&engine->gt->info.sseu, 0, 0) >=
+ GEN_DSS_PER_GSLICE;
}
static void
@@ -2023,9 +2096,6 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal)
struct drm_i915_private *i915 = engine->i915;
if (IS_DG2(i915)) {
- /* Wa_14015227452:dg2 */
- wa_masked_en(wal, GEN9_ROW_CHICKEN4, XEHP_DIS_BBL_SYSPIPE);
-
/* Wa_1509235366:dg2 */
wa_write_or(wal, GEN12_GAMCNTRL_CTRL, INVALIDATION_BROADCAST_MODE_DIS |
GLOBAL_INVALIDATION_MODE);
@@ -2036,12 +2106,6 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal)
* performance guide section.
*/
wa_write_or(wal, XEHP_L3SCQREG7, BLEND_FILL_CACHING_OPT_DIS);
-
- /* Wa_18018781329:dg2 */
- wa_write_or(wal, RENDER_MOD_CTRL, FORCE_MISS_FTLB);
- wa_write_or(wal, COMP_MOD_CTRL, FORCE_MISS_FTLB);
- wa_write_or(wal, VDBX_MOD_CTRL, FORCE_MISS_FTLB);
- wa_write_or(wal, VEBX_MOD_CTRL, FORCE_MISS_FTLB);
}
if (IS_DG2_GRAPHICS_STEP(i915, G11, STEP_A0, STEP_B0)) {
@@ -2160,6 +2224,16 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal)
wa_write_or(wal, GEN12_MERT_MOD_CTRL, FORCE_MISS_FTLB);
}
+ if (IS_DG2_GRAPHICS_STEP(i915, G11, STEP_B0, STEP_FOREVER) ||
+ IS_DG2_G10(i915)) {
+ /* Wa_22014600077:dg2 */
+ wa_add(wal, GEN10_CACHE_MODE_SS, 0,
+ _MASKED_BIT_ENABLE(ENABLE_EU_COUNT_FOR_TDL_FLUSH),
+ 0 /* Wa_14012342262 :write-only reg, so skip
+ verification */,
+ true);
+ }
+
if (IS_DG1_GRAPHICS_STEP(i915, STEP_A0, STEP_B0) ||
IS_TGL_UY_GRAPHICS_STEP(i915, STEP_A0, STEP_B0)) {
/*
@@ -2583,6 +2657,15 @@ xcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal)
}
}
+static void
+ccs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal)
+{
+ if (IS_PVC_CT_STEP(engine->i915, STEP_A0, STEP_C0)) {
+ /* Wa_14014999345:pvc */
+ wa_masked_en(wal, GEN10_CACHE_MODE_SS, DISABLE_ECC);
+ }
+}
+
/*
* The workarounds in this function apply to shared registers in
* the general render reset domain that aren't tied to a
@@ -2597,6 +2680,15 @@ general_render_compute_wa_init(struct intel_engine_cs *engine, struct i915_wa_li
{
struct drm_i915_private *i915 = engine->i915;
+ if (IS_PONTEVECCHIO(i915)) {
+ /*
+ * The following is not actually a "workaround" but rather
+ * a recommended tuning setting documented in the bspec's
+ * performance guide section.
+ */
+ wa_write(wal, XEHPC_L3SCRUB, SCRUB_CL_DWNGRADE_SHARED | SCRUB_RATE_4B_PER_CLK);
+ }
+
if (IS_XEHPSDV(i915)) {
/* Wa_1409954639 */
wa_masked_en(wal,
@@ -2629,9 +2721,21 @@ general_render_compute_wa_init(struct intel_engine_cs *engine, struct i915_wa_li
GLOBAL_INVALIDATION_MODE);
}
- if (IS_DG2(i915)) {
- /* Wa_22014226127:dg2 */
+ if (IS_DG2(i915) || IS_PONTEVECCHIO(i915)) {
+ /* Wa_14015227452:dg2,pvc */
+ wa_masked_en(wal, GEN9_ROW_CHICKEN4, XEHP_DIS_BBL_SYSPIPE);
+
+ /* Wa_22014226127:dg2,pvc */
wa_write_or(wal, LSC_CHICKEN_BIT_0, DISABLE_D8_D16_COASLESCE);
+
+ /* Wa_16015675438:dg2,pvc */
+ wa_masked_en(wal, FF_SLICE_CS_CHICKEN2, GEN12_PERF_FIX_BALANCING_CFE_DISABLE);
+
+ /* Wa_18018781329:dg2,pvc */
+ wa_write_or(wal, RENDER_MOD_CTRL, FORCE_MISS_FTLB);
+ wa_write_or(wal, COMP_MOD_CTRL, FORCE_MISS_FTLB);
+ wa_write_or(wal, VDBX_MOD_CTRL, FORCE_MISS_FTLB);
+ wa_write_or(wal, VEBX_MOD_CTRL, FORCE_MISS_FTLB);
}
}
@@ -2651,7 +2755,9 @@ engine_init_workarounds(struct intel_engine_cs *engine, struct i915_wa_list *wal
if (engine->flags & I915_ENGINE_FIRST_RENDER_COMPUTE)
general_render_compute_wa_init(engine, wal);
- if (engine->class == RENDER_CLASS)
+ if (engine->class == COMPUTE_CLASS)
+ ccs_engine_wa_init(engine, wal);
+ else if (engine->class == RENDER_CLASS)
rcs_engine_wa_init(engine, wal);
else
xcs_engine_wa_init(engine, wal);
diff --git a/drivers/gpu/drm/i915/gt/selftest_hangcheck.c b/drivers/gpu/drm/i915/gt/selftest_hangcheck.c
index 83ff4c2e57c5039928ad6eec6a208c9407285b7f..6493265d5f6426a514a7eed2fc308b5aceac2c55 100644
--- a/drivers/gpu/drm/i915/gt/selftest_hangcheck.c
+++ b/drivers/gpu/drm/i915/gt/selftest_hangcheck.c
@@ -976,6 +976,7 @@ static int __igt_reset_engines(struct intel_gt *gt,
{
struct i915_gpu_error *global = >->i915->gpu_error;
struct intel_engine_cs *engine, *other;
+ struct active_engine *threads;
enum intel_engine_id id, tmp;
struct hang h;
int err = 0;
@@ -996,8 +997,11 @@ static int __igt_reset_engines(struct intel_gt *gt,
h.ctx->sched.priority = 1024;
}
+ threads = kmalloc_array(I915_NUM_ENGINES, sizeof(*threads), GFP_KERNEL);
+ if (!threads)
+ return -ENOMEM;
+
for_each_engine(engine, gt, id) {
- struct active_engine threads[I915_NUM_ENGINES] = {};
unsigned long device = i915_reset_count(global);
unsigned long count = 0, reported;
bool using_guc = intel_engine_uses_guc(engine);
@@ -1016,7 +1020,7 @@ static int __igt_reset_engines(struct intel_gt *gt,
break;
}
- memset(threads, 0, sizeof(threads));
+ memset(threads, 0, sizeof(*threads) * I915_NUM_ENGINES);
for_each_engine(other, gt, tmp) {
struct task_struct *tsk;
@@ -1236,6 +1240,7 @@ static int __igt_reset_engines(struct intel_gt *gt,
break;
}
}
+ kfree(threads);
if (intel_gt_is_wedged(gt))
err = -EIO;
diff --git a/drivers/gpu/drm/i915/gt/uc/abi/guc_actions_slpc_abi.h b/drivers/gpu/drm/i915/gt/uc/abi/guc_actions_slpc_abi.h
index 62cb4254a77af37b327f42cfbb48de286af8dddd..4c840a2639dc58663501aa22e5a0795693604cf3 100644
--- a/drivers/gpu/drm/i915/gt/uc/abi/guc_actions_slpc_abi.h
+++ b/drivers/gpu/drm/i915/gt/uc/abi/guc_actions_slpc_abi.h
@@ -122,6 +122,12 @@ enum slpc_param_id {
SLPC_MAX_PARAM = 32,
};
+enum slpc_media_ratio_mode {
+ SLPC_MEDIA_RATIO_MODE_DYNAMIC_CONTROL = 0,
+ SLPC_MEDIA_RATIO_MODE_FIXED_ONE_TO_ONE = 1,
+ SLPC_MEDIA_RATIO_MODE_FIXED_ONE_TO_TWO = 2,
+};
+
enum slpc_event_id {
SLPC_EVENT_RESET = 0,
SLPC_EVENT_SHUTDOWN = 1,
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc.c b/drivers/gpu/drm/i915/gt/uc/intel_guc.c
index 2c4ad4a65089936b393dc9852baff81b0e405698..2706a8c650900e661a4a178f999e9e464443d885 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc.c
@@ -310,8 +310,8 @@ static u32 guc_ctl_wa_flags(struct intel_guc *guc)
if (IS_DG2(gt->i915))
flags |= GUC_WA_DUAL_QUEUE;
- /* Wa_22011802037: graphics version 12 */
- if (GRAPHICS_VER(gt->i915) == 12)
+ /* Wa_22011802037: graphics version 11/12 */
+ if (IS_GRAPHICS_VER(gt->i915, 11, 12))
flags |= GUC_WA_PRE_PARSER;
/* Wa_16011777198:dg2 */
@@ -327,6 +327,10 @@ static u32 guc_ctl_wa_flags(struct intel_guc *guc)
IS_DG2_GRAPHICS_STEP(gt->i915, G11, STEP_A0, STEP_FOREVER))
flags |= GUC_WA_CONTEXT_ISOLATION;
+ /* Wa_16015675438 */
+ if (!RCS_MASK(gt))
+ flags |= GUC_WA_RCS_REGS_IN_CCS_REGS_LIST;
+
return flags;
}
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc.h b/drivers/gpu/drm/i915/gt/uc/intel_guc.h
index 966e69a8b1c124d3b9ab107b9f65f774589c2b10..d0d99f178f2d4eab4ebd39f08100f14145858ef5 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc.h
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc.h
@@ -230,6 +230,14 @@ struct intel_guc {
* @shift: Right shift value for the gpm timestamp
*/
u32 shift;
+
+ /**
+ * @last_stat_jiffies: jiffies at last actual stats collection time
+ * We use this timestamp to ensure we don't oversample the
+ * stats because runtime power management events can trigger
+ * stats collection at much higher rates than required.
+ */
+ unsigned long last_stat_jiffies;
} timestamp;
#ifdef CONFIG_DRM_I915_SELFTEST
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_ads.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_ads.c
index 3eabf4cf8eec3ee9b484d6b014a3741fc4746dd8..ba7541f3ca6104e0156bb2e3bd3e649e6d9fb09a 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_ads.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_ads.c
@@ -7,6 +7,7 @@
#include "gt/intel_engine_regs.h"
#include "gt/intel_gt.h"
+#include "gt/intel_gt_mcr.h"
#include "gt/intel_gt_regs.h"
#include "gt/intel_lrc.h"
#include "gt/shmem_utils.h"
@@ -313,7 +314,7 @@ static long __must_check guc_mmio_reg_add(struct intel_gt *gt,
* tracking, it is easier to just program the default steering for all
* regs that don't need a non-default one.
*/
- intel_gt_get_valid_steering_for_reg(gt, reg, &group, &inst);
+ intel_gt_mcr_get_nonterminated_steering(gt, reg, &group, &inst);
entry.flags |= GUC_REGSET_STEERING(group, inst);
slot = __mmio_reg_add(regset, &entry);
@@ -457,7 +458,7 @@ static void fill_engine_enable_masks(struct intel_gt *gt,
{
info_map_write(info_map, engine_enabled_masks[GUC_RENDER_CLASS], RCS_MASK(gt));
info_map_write(info_map, engine_enabled_masks[GUC_COMPUTE_CLASS], CCS_MASK(gt));
- info_map_write(info_map, engine_enabled_masks[GUC_BLITTER_CLASS], 1);
+ info_map_write(info_map, engine_enabled_masks[GUC_BLITTER_CLASS], BCS_MASK(gt));
info_map_write(info_map, engine_enabled_masks[GUC_VIDEO_CLASS], VDBOX_MASK(gt));
info_map_write(info_map, engine_enabled_masks[GUC_VIDEOENHANCE_CLASS], VEBOX_MASK(gt));
}
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_capture.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_capture.c
index c4e25966d3e9f6fc7870a3fa6dcf96bcab21439c..97a32e610c303a3e64b0218221a3d6c92783f3e5 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_capture.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_capture.c
@@ -420,72 +420,6 @@ guc_capture_get_device_reglist(struct intel_guc *guc)
return default_lists;
}
-static const char *
-__stringify_owner(u32 owner)
-{
- switch (owner) {
- case GUC_CAPTURE_LIST_INDEX_PF:
- return "PF";
- case GUC_CAPTURE_LIST_INDEX_VF:
- return "VF";
- default:
- return "unknown";
- }
-
- return "";
-}
-
-static const char *
-__stringify_type(u32 type)
-{
- switch (type) {
- case GUC_CAPTURE_LIST_TYPE_GLOBAL:
- return "Global";
- case GUC_CAPTURE_LIST_TYPE_ENGINE_CLASS:
- return "Class";
- case GUC_CAPTURE_LIST_TYPE_ENGINE_INSTANCE:
- return "Instance";
- default:
- return "unknown";
- }
-
- return "";
-}
-
-static const char *
-__stringify_engclass(u32 class)
-{
- switch (class) {
- case GUC_RENDER_CLASS:
- return "Render";
- case GUC_VIDEO_CLASS:
- return "Video";
- case GUC_VIDEOENHANCE_CLASS:
- return "VideoEnhance";
- case GUC_BLITTER_CLASS:
- return "Blitter";
- case GUC_COMPUTE_CLASS:
- return "Compute";
- default:
- return "unknown";
- }
-
- return "";
-}
-
-static void
-guc_capture_warn_with_list_info(struct drm_i915_private *i915, char *msg,
- u32 owner, u32 type, u32 classid)
-{
- if (type == GUC_CAPTURE_LIST_TYPE_GLOBAL)
- drm_dbg(&i915->drm, "GuC-capture: %s for %s %s-Registers.\n", msg,
- __stringify_owner(owner), __stringify_type(type));
- else
- drm_dbg(&i915->drm, "GuC-capture: %s for %s %s-Registers on %s-Engine\n", msg,
- __stringify_owner(owner), __stringify_type(type),
- __stringify_engclass(classid));
-}
-
static int
guc_capture_list_init(struct intel_guc *guc, u32 owner, u32 type, u32 classid,
struct guc_mmio_reg *ptr, u16 num_entries)
@@ -501,11 +435,8 @@ guc_capture_list_init(struct intel_guc *guc, u32 owner, u32 type, u32 classid,
return -ENODEV;
match = guc_capture_get_one_list(reglists, owner, type, classid);
- if (!match) {
- guc_capture_warn_with_list_info(i915, "Missing register list init", owner, type,
- classid);
+ if (!match)
return -ENODATA;
- }
for (i = 0; i < num_entries && i < match->num_regs; ++i) {
ptr[i].offset = match->list[i].reg.reg;
@@ -556,7 +487,6 @@ int
intel_guc_capture_getlistsize(struct intel_guc *guc, u32 owner, u32 type, u32 classid,
size_t *size)
{
- struct drm_i915_private *i915 = guc_to_gt(guc)->i915;
struct intel_guc_state_capture *gc = guc->capture;
struct __guc_capture_ads_cache *cache = &gc->ads_cache[owner][type][classid];
int num_regs;
@@ -570,11 +500,8 @@ intel_guc_capture_getlistsize(struct intel_guc *guc, u32 owner, u32 type, u32 cl
}
num_regs = guc_cap_list_num_regs(gc, owner, type, classid);
- if (!num_regs) {
- guc_capture_warn_with_list_info(i915, "Missing register list size",
- owner, type, classid);
+ if (!num_regs)
return -ENODATA;
- }
*size = PAGE_ALIGN((sizeof(struct guc_debug_capture_list)) +
(num_regs * sizeof(struct guc_mmio_reg)));
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_fwif.h b/drivers/gpu/drm/i915/gt/uc/intel_guc_fwif.h
index 42cb7a9a6199c79f8350efd259bbeb0fd46b57c3..b3c9a9327f7648ee84d5aa1df71dfae16a8a8d25 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_fwif.h
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_fwif.h
@@ -105,6 +105,7 @@
#define GUC_WA_PRE_PARSER BIT(14)
#define GUC_WA_HOLD_CCS_SWITCHOUT BIT(17)
#define GUC_WA_POLLCS BIT(18)
+#define GUC_WA_RCS_REGS_IN_CCS_REGS_LIST BIT(21)
#define GUC_CTL_FEATURE 2
#define GUC_CTL_ENABLE_SLPC BIT(2)
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_hwconfig.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_hwconfig.c
index 79c66b6b51a3f77fe7eebf9660e3685c32e3fc1d..4781fccc2687d6d407643bb99e4abb6e624aa113 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_hwconfig.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_hwconfig.c
@@ -94,9 +94,9 @@ static int guc_hwconfig_fill_buffer(struct intel_guc *guc, struct intel_hwconfig
static bool has_table(struct drm_i915_private *i915)
{
- if (IS_ALDERLAKE_P(i915))
+ if (IS_ALDERLAKE_P(i915) && !IS_ADLP_N(i915))
return true;
- if (IS_DG2(i915))
+ if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 55))
return true;
return false;
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_rc.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_rc.c
index e00661fb0853169b7e5c4b3d4de4089f255f9b17..8f8dd05835c5aaf766e0f70ccbba6a3c85904dda 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_rc.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_rc.c
@@ -49,7 +49,6 @@ static int guc_action_control_gucrc(struct intel_guc *guc, bool enable)
static int __guc_rc_control(struct intel_guc *guc, bool enable)
{
struct intel_gt *gt = guc_to_gt(guc);
- struct drm_device *drm = &guc_to_gt(guc)->i915->drm;
int ret;
if (!intel_uc_uses_guc_rc(>->uc))
@@ -60,8 +59,8 @@ static int __guc_rc_control(struct intel_guc *guc, bool enable)
ret = guc_action_control_gucrc(guc, enable);
if (ret) {
- drm_err(drm, "Failed to %s GuC RC (%pe)\n",
- str_enable_disable(enable), ERR_PTR(ret));
+ i915_probe_error(guc_to_gt(guc)->i915, "Failed to %s GuC RC (%pe)\n",
+ str_enable_disable(enable), ERR_PTR(ret));
return ret;
}
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_reg.h b/drivers/gpu/drm/i915/gt/uc/intel_guc_reg.h
index ad570fa002a6b9e7429c6ae19a5140daa04a43a0..8dc063f087eb15add9f2a3155eea46f0832f9d85 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_reg.h
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_reg.h
@@ -96,6 +96,7 @@
#define GUC_SHIM_CONTROL2 _MMIO(0xc068)
#define GUC_IS_PRIVILEGED (1<<29)
+#define GSC_LOADS_HUC (1<<30)
#define GUC_SEND_INTERRUPT _MMIO(0xc4c8)
#define GUC_SEND_TRIGGER (1<<0)
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.c
index 1db833da42df31c1ee5bcfe1fea76161c31d84cd..ec9c4ca0f615bc909eb41fd559d670d6e159019a 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.c
@@ -98,6 +98,30 @@ static u32 slpc_get_state(struct intel_guc_slpc *slpc)
return data->header.global_state;
}
+static int guc_action_slpc_set_param_nb(struct intel_guc *guc, u8 id, u32 value)
+{
+ u32 request[] = {
+ GUC_ACTION_HOST2GUC_PC_SLPC_REQUEST,
+ SLPC_EVENT(SLPC_EVENT_PARAMETER_SET, 2),
+ id,
+ value,
+ };
+ int ret;
+
+ ret = intel_guc_send_nb(guc, request, ARRAY_SIZE(request), 0);
+
+ return ret > 0 ? -EPROTO : ret;
+}
+
+static int slpc_set_param_nb(struct intel_guc_slpc *slpc, u8 id, u32 value)
+{
+ struct intel_guc *guc = slpc_to_guc(slpc);
+
+ GEM_BUG_ON(id >= SLPC_MAX_PARAM);
+
+ return guc_action_slpc_set_param_nb(guc, id, value);
+}
+
static int guc_action_slpc_set_param(struct intel_guc *guc, u8 id, u32 value)
{
u32 request[] = {
@@ -208,12 +232,14 @@ static int slpc_force_min_freq(struct intel_guc_slpc *slpc, u32 freq)
*/
with_intel_runtime_pm(&i915->runtime_pm, wakeref) {
- ret = slpc_set_param(slpc,
- SLPC_PARAM_GLOBAL_MIN_GT_UNSLICE_FREQ_MHZ,
- freq);
+ /* Non-blocking request will avoid stalls */
+ ret = slpc_set_param_nb(slpc,
+ SLPC_PARAM_GLOBAL_MIN_GT_UNSLICE_FREQ_MHZ,
+ freq);
if (ret)
- i915_probe_error(i915, "Unable to force min freq to %u: %d",
- freq, ret);
+ drm_notice(&i915->drm,
+ "Failed to send set_param for min freq(%d): (%d)\n",
+ freq, ret);
}
return ret;
@@ -222,6 +248,7 @@ static int slpc_force_min_freq(struct intel_guc_slpc *slpc, u32 freq)
static void slpc_boost_work(struct work_struct *work)
{
struct intel_guc_slpc *slpc = container_of(work, typeof(*slpc), boost_work);
+ int err;
/*
* Raise min freq to boost. It's possible that
@@ -231,8 +258,9 @@ static void slpc_boost_work(struct work_struct *work)
*/
mutex_lock(&slpc->lock);
if (atomic_read(&slpc->num_waiters)) {
- slpc_force_min_freq(slpc, slpc->boost_freq);
- slpc->num_boosts++;
+ err = slpc_force_min_freq(slpc, slpc->boost_freq);
+ if (!err)
+ slpc->num_boosts++;
}
mutex_unlock(&slpc->lock);
}
@@ -260,6 +288,7 @@ int intel_guc_slpc_init(struct intel_guc_slpc *slpc)
slpc->boost_freq = 0;
atomic_set(&slpc->num_waiters, 0);
slpc->num_boosts = 0;
+ slpc->media_ratio_mode = SLPC_MEDIA_RATIO_MODE_DYNAMIC_CONTROL;
mutex_init(&slpc->lock);
INIT_WORK(&slpc->boost_work, slpc_boost_work);
@@ -506,6 +535,22 @@ int intel_guc_slpc_get_min_freq(struct intel_guc_slpc *slpc, u32 *val)
return ret;
}
+int intel_guc_slpc_set_media_ratio_mode(struct intel_guc_slpc *slpc, u32 val)
+{
+ struct drm_i915_private *i915 = slpc_to_i915(slpc);
+ intel_wakeref_t wakeref;
+ int ret = 0;
+
+ if (!HAS_MEDIA_RATIO_MODE(i915))
+ return -ENODEV;
+
+ with_intel_runtime_pm(&i915->runtime_pm, wakeref)
+ ret = slpc_set_param(slpc,
+ SLPC_PARAM_MEDIA_FF_RATIO_MODE,
+ val);
+ return ret;
+}
+
void intel_guc_pm_intrmsk_enable(struct intel_gt *gt)
{
u32 pm_intrmsk_mbz = 0;
@@ -654,6 +699,9 @@ int intel_guc_slpc_enable(struct intel_guc_slpc *slpc)
return ret;
}
+ /* Set cached media freq ratio mode */
+ intel_guc_slpc_set_media_ratio_mode(slpc, slpc->media_ratio_mode);
+
return 0;
}
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.h b/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.h
index 0caa8fee3c040ec7cdccc68ab8292cda6f4a85f2..82a98f78f96c3f71accd8dba6e3d424315f79680 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.h
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.h
@@ -38,6 +38,7 @@ int intel_guc_slpc_set_boost_freq(struct intel_guc_slpc *slpc, u32 val);
int intel_guc_slpc_get_max_freq(struct intel_guc_slpc *slpc, u32 *val);
int intel_guc_slpc_get_min_freq(struct intel_guc_slpc *slpc, u32 *val);
int intel_guc_slpc_print_info(struct intel_guc_slpc *slpc, struct drm_printer *p);
+int intel_guc_slpc_set_media_ratio_mode(struct intel_guc_slpc *slpc, u32 val);
void intel_guc_pm_intrmsk_enable(struct intel_gt *gt);
void intel_guc_slpc_boost(struct intel_guc_slpc *slpc);
void intel_guc_slpc_dec_waiters(struct intel_guc_slpc *slpc);
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc_types.h b/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc_types.h
index bf5b9a563c09e0a9a7549787cfcd6268c36e4c4b..73d208123528ff740a8b25d1defa75148b04b3dc 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc_types.h
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc_types.h
@@ -29,6 +29,9 @@ struct intel_guc_slpc {
u32 min_freq_softlimit;
u32 max_freq_softlimit;
+ /* cached media ratio mode */
+ u32 media_ratio_mode;
+
/* Protects set/reset of boost freq
* and value of num_waiters
*/
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
index 1726f0f19901097551de288ec80bdf37a4744a52..40f726c61e95183be1d11a07641b72c728821a3d 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
@@ -1314,6 +1314,8 @@ static void __update_guc_busyness_stats(struct intel_guc *guc)
unsigned long flags;
ktime_t unused;
+ guc->timestamp.last_stat_jiffies = jiffies;
+
spin_lock_irqsave(&guc->timestamp.lock, flags);
guc_update_pm_timestamp(guc, &unused);
@@ -1386,6 +1388,17 @@ void intel_guc_busyness_park(struct intel_gt *gt)
return;
cancel_delayed_work(&guc->timestamp.work);
+
+ /*
+ * Before parking, we should sample engine busyness stats if we need to.
+ * We can skip it if we are less than half a ping from the last time we
+ * sampled the busyness stats.
+ */
+ if (guc->timestamp.last_stat_jiffies &&
+ !time_after(jiffies, guc->timestamp.last_stat_jiffies +
+ (guc->timestamp.ping_delay / 2)))
+ return;
+
__update_guc_busyness_stats(guc);
}
@@ -1527,87 +1540,18 @@ static void guc_reset_state(struct intel_context *ce, u32 head, bool scrub)
lrc_update_regs(ce, engine, head);
}
-static u32 __cs_pending_mi_force_wakes(struct intel_engine_cs *engine)
-{
- static const i915_reg_t _reg[I915_NUM_ENGINES] = {
- [RCS0] = MSG_IDLE_CS,
- [BCS0] = MSG_IDLE_BCS,
- [VCS0] = MSG_IDLE_VCS0,
- [VCS1] = MSG_IDLE_VCS1,
- [VCS2] = MSG_IDLE_VCS2,
- [VCS3] = MSG_IDLE_VCS3,
- [VCS4] = MSG_IDLE_VCS4,
- [VCS5] = MSG_IDLE_VCS5,
- [VCS6] = MSG_IDLE_VCS6,
- [VCS7] = MSG_IDLE_VCS7,
- [VECS0] = MSG_IDLE_VECS0,
- [VECS1] = MSG_IDLE_VECS1,
- [VECS2] = MSG_IDLE_VECS2,
- [VECS3] = MSG_IDLE_VECS3,
- [CCS0] = MSG_IDLE_CS,
- [CCS1] = MSG_IDLE_CS,
- [CCS2] = MSG_IDLE_CS,
- [CCS3] = MSG_IDLE_CS,
- };
- u32 val;
-
- if (!_reg[engine->id].reg)
- return 0;
-
- val = intel_uncore_read(engine->uncore, _reg[engine->id]);
-
- /* bits[29:25] & bits[13:9] >> shift */
- return (val & (val >> 16) & MSG_IDLE_FW_MASK) >> MSG_IDLE_FW_SHIFT;
-}
-
-static void __gpm_wait_for_fw_complete(struct intel_gt *gt, u32 fw_mask)
-{
- int ret;
-
- /* Ensure GPM receives fw up/down after CS is stopped */
- udelay(1);
-
- /* Wait for forcewake request to complete in GPM */
- ret = __intel_wait_for_register_fw(gt->uncore,
- GEN9_PWRGT_DOMAIN_STATUS,
- fw_mask, fw_mask, 5000, 0, NULL);
-
- /* Ensure CS receives fw ack from GPM */
- udelay(1);
-
- if (ret)
- GT_TRACE(gt, "Failed to complete pending forcewake %d\n", ret);
-}
-
-/*
- * Wa_22011802037:gen12: In addition to stopping the cs, we need to wait for any
- * pending MI_FORCE_WAKEUP requests that the CS has initiated to complete. The
- * pending status is indicated by bits[13:9] (masked by bits[ 29:25]) in the
- * MSG_IDLE register. There's one MSG_IDLE register per reset domain. Since we
- * are concerned only with the gt reset here, we use a logical OR of pending
- * forcewakeups from all reset domains and then wait for them to complete by
- * querying PWRGT_DOMAIN_STATUS.
- */
static void guc_engine_reset_prepare(struct intel_engine_cs *engine)
{
- u32 fw_pending;
-
- if (GRAPHICS_VER(engine->i915) != 12)
+ if (!IS_GRAPHICS_VER(engine->i915, 11, 12))
return;
- /*
- * Wa_22011802037
- * TODO: Occasionally trying to stop the cs times out, but does not
- * adversely affect functionality. The timeout is set as a config
- * parameter that defaults to 100ms. Assuming that this timeout is
- * sufficient for any pending MI_FORCEWAKEs to complete, ignore the
- * timeout returned here until it is root caused.
- */
intel_engine_stop_cs(engine);
- fw_pending = __cs_pending_mi_force_wakes(engine);
- if (fw_pending)
- __gpm_wait_for_fw_complete(engine->gt, fw_pending);
+ /*
+ * Wa_22011802037:gen11/gen12: In addition to stopping the cs, we need
+ * to wait for any pending mi force wakeups
+ */
+ intel_engine_wait_for_pending_mi_fw(engine);
}
static void guc_reset_nop(struct intel_engine_cs *engine)
@@ -2394,6 +2338,26 @@ static int guc_context_policy_init(struct intel_context *ce, bool loop)
return ret;
}
+static u32 map_guc_prio_to_lrc_desc_prio(u8 prio)
+{
+ /*
+ * this matches the mapping we do in map_i915_prio_to_guc_prio()
+ * (e.g. prio < I915_PRIORITY_NORMAL maps to GUC_CLIENT_PRIORITY_NORMAL)
+ */
+ switch (prio) {
+ default:
+ MISSING_CASE(prio);
+ fallthrough;
+ case GUC_CLIENT_PRIORITY_KMD_NORMAL:
+ return GEN12_CTX_PRIORITY_NORMAL;
+ case GUC_CLIENT_PRIORITY_NORMAL:
+ return GEN12_CTX_PRIORITY_LOW;
+ case GUC_CLIENT_PRIORITY_HIGH:
+ case GUC_CLIENT_PRIORITY_KMD_HIGH:
+ return GEN12_CTX_PRIORITY_HIGH;
+ }
+}
+
static void prepare_context_registration_info(struct intel_context *ce,
struct guc_ctxt_registration_info *info)
{
@@ -2420,6 +2384,8 @@ static void prepare_context_registration_info(struct intel_context *ce,
*/
info->hwlrca_lo = lower_32_bits(ce->lrc.lrca);
info->hwlrca_hi = upper_32_bits(ce->lrc.lrca);
+ if (engine->flags & I915_ENGINE_HAS_EU_PRIORITY)
+ info->hwlrca_lo |= map_guc_prio_to_lrc_desc_prio(ce->guc_state.prio);
info->flags = CONTEXT_REGISTRATION_FLAG_KMD;
/*
@@ -2768,7 +2734,9 @@ static void __guc_context_set_preemption_timeout(struct intel_guc *guc,
__guc_context_set_context_policies(guc, &policy, true);
}
-static void guc_context_ban(struct intel_context *ce, struct i915_request *rq)
+static void
+guc_context_revoke(struct intel_context *ce, struct i915_request *rq,
+ unsigned int preempt_timeout_ms)
{
struct intel_guc *guc = ce_to_guc(ce);
struct intel_runtime_pm *runtime_pm =
@@ -2807,7 +2775,8 @@ static void guc_context_ban(struct intel_context *ce, struct i915_request *rq)
* gets kicked off the HW ASAP.
*/
with_intel_runtime_pm(runtime_pm, wakeref) {
- __guc_context_set_preemption_timeout(guc, guc_id, 1);
+ __guc_context_set_preemption_timeout(guc, guc_id,
+ preempt_timeout_ms);
__guc_context_sched_disable(guc, ce, guc_id);
}
} else {
@@ -2815,7 +2784,7 @@ static void guc_context_ban(struct intel_context *ce, struct i915_request *rq)
with_intel_runtime_pm(runtime_pm, wakeref)
__guc_context_set_preemption_timeout(guc,
ce->guc_id.id,
- 1);
+ preempt_timeout_ms);
spin_unlock_irqrestore(&ce->guc_state.lock, flags);
}
}
@@ -3168,7 +3137,7 @@ static const struct intel_context_ops guc_context_ops = {
.unpin = guc_context_unpin,
.post_unpin = guc_context_post_unpin,
- .ban = guc_context_ban,
+ .revoke = guc_context_revoke,
.cancel_request = guc_context_cancel_request,
@@ -3417,7 +3386,7 @@ static const struct intel_context_ops virtual_guc_context_ops = {
.unpin = guc_virtual_context_unpin,
.post_unpin = guc_context_post_unpin,
- .ban = guc_context_ban,
+ .revoke = guc_context_revoke,
.cancel_request = guc_context_cancel_request,
@@ -3506,7 +3475,7 @@ static const struct intel_context_ops virtual_parent_context_ops = {
.unpin = guc_parent_context_unpin,
.post_unpin = guc_context_post_unpin,
- .ban = guc_context_ban,
+ .revoke = guc_context_revoke,
.cancel_request = guc_context_cancel_request,
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_huc.c b/drivers/gpu/drm/i915/gt/uc/intel_huc.c
index 556829de9c17287dc8f2ee598627fed91caf123d..3bb8838e325a4121ce478c526eb7348d4b4f62d3 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_huc.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_huc.c
@@ -6,6 +6,7 @@
#include <linux/types.h>
#include "gt/intel_gt.h"
+#include "intel_guc_reg.h"
#include "intel_huc.h"
#include "i915_drv.h"
@@ -17,11 +18,15 @@
* capabilities by adding HuC specific commands to batch buffers.
*
* The kernel driver is only responsible for loading the HuC firmware and
- * triggering its security authentication, which is performed by the GuC. For
- * The GuC to correctly perform the authentication, the HuC binary must be
- * loaded before the GuC one. Loading the HuC is optional; however, not using
- * the HuC might negatively impact power usage and/or performance of media
- * workloads, depending on the use-cases.
+ * triggering its security authentication, which is performed by the GuC on
+ * older platforms and by the GSC on newer ones. For the GuC to correctly
+ * perform the authentication, the HuC binary must be loaded before the GuC one.
+ * Loading the HuC is optional; however, not using the HuC might negatively
+ * impact power usage and/or performance of media workloads, depending on the
+ * use-cases.
+ * HuC must be reloaded on events that cause the WOPCM to lose its contents
+ * (S3/S4, FLR); GuC-authenticated HuC must also be reloaded on GuC/GT reset,
+ * while GSC-managed HuC will survive that.
*
* See https://github.com/intel/media-driver for the latest details on HuC
* functionality.
@@ -54,11 +59,51 @@ void intel_huc_init_early(struct intel_huc *huc)
}
}
+#define HUC_LOAD_MODE_STRING(x) (x ? "GSC" : "legacy")
+static int check_huc_loading_mode(struct intel_huc *huc)
+{
+ struct intel_gt *gt = huc_to_gt(huc);
+ bool fw_needs_gsc = intel_huc_is_loaded_by_gsc(huc);
+ bool hw_uses_gsc = false;
+
+ /*
+ * The fuse for HuC load via GSC is only valid on platforms that have
+ * GuC deprivilege.
+ */
+ if (HAS_GUC_DEPRIVILEGE(gt->i915))
+ hw_uses_gsc = intel_uncore_read(gt->uncore, GUC_SHIM_CONTROL2) &
+ GSC_LOADS_HUC;
+
+ if (fw_needs_gsc != hw_uses_gsc) {
+ drm_err(>->i915->drm,
+ "mismatch between HuC FW (%s) and HW (%s) load modes\n",
+ HUC_LOAD_MODE_STRING(fw_needs_gsc),
+ HUC_LOAD_MODE_STRING(hw_uses_gsc));
+ return -ENOEXEC;
+ }
+
+ /* make sure we can access the GSC via the mei driver if we need it */
+ if (!(IS_ENABLED(CONFIG_INTEL_MEI_PXP) && IS_ENABLED(CONFIG_INTEL_MEI_GSC)) &&
+ fw_needs_gsc) {
+ drm_info(>->i915->drm,
+ "Can't load HuC due to missing MEI modules\n");
+ return -EIO;
+ }
+
+ drm_dbg(>->i915->drm, "GSC loads huc=%s\n", str_yes_no(fw_needs_gsc));
+
+ return 0;
+}
+
int intel_huc_init(struct intel_huc *huc)
{
struct drm_i915_private *i915 = huc_to_gt(huc)->i915;
int err;
+ err = check_huc_loading_mode(huc);
+ if (err)
+ goto out;
+
err = intel_uc_fw_init(&huc->fw);
if (err)
goto out;
@@ -68,7 +113,7 @@ int intel_huc_init(struct intel_huc *huc)
return 0;
out:
- i915_probe_error(i915, "failed with %d\n", err);
+ drm_info(&i915->drm, "HuC init failed with %d\n", err);
return err;
}
@@ -96,17 +141,20 @@ int intel_huc_auth(struct intel_huc *huc)
struct intel_guc *guc = >->uc.guc;
int ret;
- GEM_BUG_ON(intel_huc_is_authenticated(huc));
-
if (!intel_uc_fw_is_loaded(&huc->fw))
return -ENOEXEC;
+ /* GSC will do the auth */
+ if (intel_huc_is_loaded_by_gsc(huc))
+ return -ENODEV;
+
ret = i915_inject_probe_error(gt->i915, -ENXIO);
if (ret)
goto fail;
- ret = intel_guc_auth_huc(guc,
- intel_guc_ggtt_offset(guc, huc->fw.rsa_data));
+ GEM_BUG_ON(intel_uc_fw_is_running(&huc->fw));
+
+ ret = intel_guc_auth_huc(guc, intel_guc_ggtt_offset(guc, huc->fw.rsa_data));
if (ret) {
DRM_ERROR("HuC: GuC did not ack Auth request %d\n", ret);
goto fail;
@@ -133,6 +181,18 @@ int intel_huc_auth(struct intel_huc *huc)
return ret;
}
+static bool huc_is_authenticated(struct intel_huc *huc)
+{
+ struct intel_gt *gt = huc_to_gt(huc);
+ intel_wakeref_t wakeref;
+ u32 status = 0;
+
+ with_intel_runtime_pm(gt->uncore->rpm, wakeref)
+ status = intel_uncore_read(gt->uncore, huc->status.reg);
+
+ return (status & huc->status.mask) == huc->status.value;
+}
+
/**
* intel_huc_check_status() - check HuC status
* @huc: intel_huc structure
@@ -150,10 +210,6 @@ int intel_huc_auth(struct intel_huc *huc)
*/
int intel_huc_check_status(struct intel_huc *huc)
{
- struct intel_gt *gt = huc_to_gt(huc);
- intel_wakeref_t wakeref;
- u32 status = 0;
-
switch (__intel_uc_fw_status(&huc->fw)) {
case INTEL_UC_FIRMWARE_NOT_SUPPORTED:
return -ENODEV;
@@ -167,10 +223,17 @@ int intel_huc_check_status(struct intel_huc *huc)
break;
}
- with_intel_runtime_pm(gt->uncore->rpm, wakeref)
- status = intel_uncore_read(gt->uncore, huc->status.reg);
+ return huc_is_authenticated(huc);
+}
- return (status & huc->status.mask) == huc->status.value;
+void intel_huc_update_auth_status(struct intel_huc *huc)
+{
+ if (!intel_uc_fw_is_loadable(&huc->fw))
+ return;
+
+ if (huc_is_authenticated(huc))
+ intel_uc_fw_change_status(&huc->fw,
+ INTEL_UC_FIRMWARE_RUNNING);
}
/**
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_huc.h b/drivers/gpu/drm/i915/gt/uc/intel_huc.h
index 73ec670800f2b55f6266370f5173dae17f546e93..d7e25b6e879eb7e8249d6fad7898256566d55b31 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_huc.h
+++ b/drivers/gpu/drm/i915/gt/uc/intel_huc.h
@@ -27,6 +27,7 @@ int intel_huc_init(struct intel_huc *huc);
void intel_huc_fini(struct intel_huc *huc);
int intel_huc_auth(struct intel_huc *huc);
int intel_huc_check_status(struct intel_huc *huc);
+void intel_huc_update_auth_status(struct intel_huc *huc);
static inline int intel_huc_sanitize(struct intel_huc *huc)
{
@@ -50,9 +51,9 @@ static inline bool intel_huc_is_used(struct intel_huc *huc)
return intel_uc_fw_is_available(&huc->fw);
}
-static inline bool intel_huc_is_authenticated(struct intel_huc *huc)
+static inline bool intel_huc_is_loaded_by_gsc(const struct intel_huc *huc)
{
- return intel_uc_fw_is_running(&huc->fw);
+ return huc->fw.loaded_via_gsc;
}
void intel_huc_load_status(struct intel_huc *huc, struct drm_printer *p);
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_huc_fw.c b/drivers/gpu/drm/i915/gt/uc/intel_huc_fw.c
index e5ef509c70e8944712a67431c1a21b0f084ae099..9d6ab1e016395f2feeb91f98787b2f1258d0711c 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_huc_fw.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_huc_fw.c
@@ -8,7 +8,7 @@
#include "i915_drv.h"
/**
- * intel_huc_fw_upload() - load HuC uCode to device
+ * intel_huc_fw_upload() - load HuC uCode to device via DMA transfer
* @huc: intel_huc structure
*
* Called from intel_uc_init_hw() during driver load, resume from sleep and
@@ -21,6 +21,9 @@
*/
int intel_huc_fw_upload(struct intel_huc *huc)
{
+ if (intel_huc_is_loaded_by_gsc(huc))
+ return -ENODEV;
+
/* HW doesn't look at destination address for HuC, so set it to 0 */
return intel_uc_fw_upload(&huc->fw, 0, HUC_UKERNEL);
}
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc.c b/drivers/gpu/drm/i915/gt/uc/intel_uc.c
index e8f099360e010ff1ebd40492de6674a3f57966a1..f2e7c82985efd00213c096169b47714df19abdf6 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_uc.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_uc.c
@@ -45,6 +45,10 @@ static void uc_expand_default_options(struct intel_uc *uc)
/* Default: enable HuC authentication and GuC submission */
i915->params.enable_guc = ENABLE_GUC_LOAD_HUC | ENABLE_GUC_SUBMISSION;
+
+ /* XEHPSDV and PVC do not use HuC */
+ if (IS_XEHPSDV(i915) || IS_PONTEVECCHIO(i915))
+ i915->params.enable_guc &= ~ENABLE_GUC_LOAD_HUC;
}
/* Reset GuC providing us with fresh state for both GuC and HuC.
@@ -323,17 +327,10 @@ static int __uc_init(struct intel_uc *uc)
if (ret)
return ret;
- if (intel_uc_uses_huc(uc)) {
- ret = intel_huc_init(huc);
- if (ret)
- goto out_guc;
- }
+ if (intel_uc_uses_huc(uc))
+ intel_huc_init(huc);
return 0;
-
-out_guc:
- intel_guc_fini(guc);
- return ret;
}
static void __uc_fini(struct intel_uc *uc)
@@ -509,7 +506,16 @@ static int __uc_init_hw(struct intel_uc *uc)
if (ret)
goto err_log_capture;
- intel_huc_auth(huc);
+ /*
+ * GSC-loaded HuC is authenticated by the GSC, so we don't need to
+ * trigger the auth here. However, given that the HuC loaded this way
+ * survive GT reset, we still need to update our SW bookkeeping to make
+ * sure it reflects the correct HW status.
+ */
+ if (intel_huc_is_loaded_by_gsc(huc))
+ intel_huc_update_auth_status(huc);
+ else
+ intel_huc_auth(huc);
if (intel_uc_uses_guc_submission(uc))
intel_guc_submission_enable(guc);
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c
index d078f884b5e3263258836d718843ca452255ecc9..c06e83872c34d07d79b1d643a5ea7dc91777c251 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c
@@ -156,7 +156,7 @@ __uc_fw_auto_select(struct drm_i915_private *i915, struct intel_uc_fw *uc_fw)
[INTEL_UC_FW_TYPE_GUC] = { blobs_guc, ARRAY_SIZE(blobs_guc) },
[INTEL_UC_FW_TYPE_HUC] = { blobs_huc, ARRAY_SIZE(blobs_huc) },
};
- static const struct uc_fw_platform_requirement *fw_blobs;
+ const struct uc_fw_platform_requirement *fw_blobs;
enum intel_platform p = INTEL_INFO(i915)->platform;
u32 fw_count;
u8 rev = INTEL_REVID(i915);
@@ -301,45 +301,31 @@ static void __force_fw_fetch_failures(struct intel_uc_fw *uc_fw, int e)
}
}
-/**
- * intel_uc_fw_fetch - fetch uC firmware
- * @uc_fw: uC firmware
- *
- * Fetch uC firmware into GEM obj.
- *
- * Return: 0 on success, a negative errno code on failure.
- */
-int intel_uc_fw_fetch(struct intel_uc_fw *uc_fw)
+static int check_gsc_manifest(const struct firmware *fw,
+ struct intel_uc_fw *uc_fw)
{
- struct drm_i915_private *i915 = __uc_fw_to_gt(uc_fw)->i915;
- struct device *dev = i915->drm.dev;
- struct drm_i915_gem_object *obj;
- const struct firmware *fw = NULL;
- struct uc_css_header *css;
- size_t size;
- int err;
+ u32 *dw = (u32 *)fw->data;
+ u32 version = dw[HUC_GSC_VERSION_DW];
- GEM_BUG_ON(!i915->wopcm.size);
- GEM_BUG_ON(!intel_uc_fw_is_enabled(uc_fw));
-
- err = i915_inject_probe_error(i915, -ENXIO);
- if (err)
- goto fail;
+ uc_fw->major_ver_found = FIELD_GET(HUC_GSC_MAJOR_VER_MASK, version);
+ uc_fw->minor_ver_found = FIELD_GET(HUC_GSC_MINOR_VER_MASK, version);
- __force_fw_fetch_failures(uc_fw, -EINVAL);
- __force_fw_fetch_failures(uc_fw, -ESTALE);
+ return 0;
+}
- err = request_firmware(&fw, uc_fw->path, dev);
- if (err)
- goto fail;
+static int check_ccs_header(struct drm_i915_private *i915,
+ const struct firmware *fw,
+ struct intel_uc_fw *uc_fw)
+{
+ struct uc_css_header *css;
+ size_t size;
/* Check the size of the blob before examining buffer contents */
if (unlikely(fw->size < sizeof(struct uc_css_header))) {
drm_warn(&i915->drm, "%s firmware %s: invalid size: %zu < %zu\n",
intel_uc_fw_type_repr(uc_fw->type), uc_fw->path,
fw->size, sizeof(struct uc_css_header));
- err = -ENODATA;
- goto fail;
+ return -ENODATA;
}
css = (struct uc_css_header *)fw->data;
@@ -352,8 +338,7 @@ int intel_uc_fw_fetch(struct intel_uc_fw *uc_fw)
"%s firmware %s: unexpected header size: %zu != %zu\n",
intel_uc_fw_type_repr(uc_fw->type), uc_fw->path,
fw->size, sizeof(struct uc_css_header));
- err = -EPROTO;
- goto fail;
+ return -EPROTO;
}
/* uCode size must calculated from other sizes */
@@ -368,8 +353,7 @@ int intel_uc_fw_fetch(struct intel_uc_fw *uc_fw)
drm_warn(&i915->drm, "%s firmware %s: invalid size: %zu < %zu\n",
intel_uc_fw_type_repr(uc_fw->type), uc_fw->path,
fw->size, size);
- err = -ENOEXEC;
- goto fail;
+ return -ENOEXEC;
}
/* Sanity check whether this fw is not larger than whole WOPCM memory */
@@ -378,8 +362,7 @@ int intel_uc_fw_fetch(struct intel_uc_fw *uc_fw)
drm_warn(&i915->drm, "%s firmware %s: invalid size: %zu > %zu\n",
intel_uc_fw_type_repr(uc_fw->type), uc_fw->path,
size, (size_t)i915->wopcm.size);
- err = -E2BIG;
- goto fail;
+ return -E2BIG;
}
/* Get version numbers from the CSS header */
@@ -388,6 +371,49 @@ int intel_uc_fw_fetch(struct intel_uc_fw *uc_fw)
uc_fw->minor_ver_found = FIELD_GET(CSS_SW_VERSION_UC_MINOR,
css->sw_version);
+ if (uc_fw->type == INTEL_UC_FW_TYPE_GUC)
+ uc_fw->private_data_size = css->private_data_size;
+
+ return 0;
+}
+
+/**
+ * intel_uc_fw_fetch - fetch uC firmware
+ * @uc_fw: uC firmware
+ *
+ * Fetch uC firmware into GEM obj.
+ *
+ * Return: 0 on success, a negative errno code on failure.
+ */
+int intel_uc_fw_fetch(struct intel_uc_fw *uc_fw)
+{
+ struct drm_i915_private *i915 = __uc_fw_to_gt(uc_fw)->i915;
+ struct device *dev = i915->drm.dev;
+ struct drm_i915_gem_object *obj;
+ const struct firmware *fw = NULL;
+ int err;
+
+ GEM_BUG_ON(!i915->wopcm.size);
+ GEM_BUG_ON(!intel_uc_fw_is_enabled(uc_fw));
+
+ err = i915_inject_probe_error(i915, -ENXIO);
+ if (err)
+ goto fail;
+
+ __force_fw_fetch_failures(uc_fw, -EINVAL);
+ __force_fw_fetch_failures(uc_fw, -ESTALE);
+
+ err = request_firmware(&fw, uc_fw->path, dev);
+ if (err)
+ goto fail;
+
+ if (uc_fw->loaded_via_gsc)
+ err = check_gsc_manifest(fw, uc_fw);
+ else
+ err = check_ccs_header(i915, fw, uc_fw);
+ if (err)
+ goto fail;
+
if (uc_fw->major_ver_found != uc_fw->major_ver_wanted ||
uc_fw->minor_ver_found < uc_fw->minor_ver_wanted) {
drm_notice(&i915->drm, "%s firmware %s: unexpected version: %u.%u != %u.%u\n",
@@ -400,9 +426,6 @@ int intel_uc_fw_fetch(struct intel_uc_fw *uc_fw)
}
}
- if (uc_fw->type == INTEL_UC_FW_TYPE_GUC)
- uc_fw->private_data_size = css->private_data_size;
-
if (HAS_LMEM(i915)) {
obj = i915_gem_object_create_lmem_from_data(i915, fw->data, fw->size);
if (!IS_ERR(obj))
@@ -470,7 +493,10 @@ static void uc_fw_bind_ggtt(struct intel_uc_fw *uc_fw)
if (i915_gem_object_is_lmem(obj))
pte_flags |= PTE_LM;
- ggtt->vm.insert_entries(&ggtt->vm, dummy, I915_CACHE_NONE, pte_flags);
+ if (ggtt->vm.raw_insert_entries)
+ ggtt->vm.raw_insert_entries(&ggtt->vm, dummy, I915_CACHE_NONE, pte_flags);
+ else
+ ggtt->vm.insert_entries(&ggtt->vm, dummy, I915_CACHE_NONE, pte_flags);
}
static void uc_fw_unbind_ggtt(struct intel_uc_fw *uc_fw)
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.h b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.h
index 3229018877d3dbc63fa52e395ca647a606dd2a78..4f169035f5041b64b46cc076d2a1dabc930d8019 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.h
+++ b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.h
@@ -102,6 +102,8 @@ struct intel_uc_fw {
u32 ucode_size;
u32 private_data_size;
+
+ bool loaded_via_gsc;
};
#ifdef CONFIG_DRM_I915_DEBUG_GUC
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw_abi.h b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw_abi.h
index e41ffc7a7fbcb0aceedd079819a3f27405748733..b05e0e35b734c434e4960e52c75f21c4fc3f5a62 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw_abi.h
+++ b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw_abi.h
@@ -39,6 +39,11 @@
* 3. Length info of each component can be found in header, in dwords.
* 4. Modulus and exponent key are not required by driver. They may not appear
* in fw. So driver will load a truncated firmware in this case.
+ *
+ * Starting from DG2, the HuC is loaded by the GSC instead of i915. The GSC
+ * firmware performs all the required integrity checks, we just need to check
+ * the version. Note that the header for GSC-managed blobs is different from the
+ * CSS used for dma-loaded firmwares.
*/
struct uc_css_header {
@@ -78,4 +83,8 @@ struct uc_css_header {
} __packed;
static_assert(sizeof(struct uc_css_header) == 128);
+#define HUC_GSC_VERSION_DW 44
+#define HUC_GSC_MAJOR_VER_MASK (0xFF << 0)
+#define HUC_GSC_MINOR_VER_MASK (0xFF << 16)
+
#endif /* _INTEL_UC_FW_ABI_H */
diff --git a/drivers/gpu/drm/i915/gvt/cmd_parser.c b/drivers/gpu/drm/i915/gvt/cmd_parser.c
index b9eb75a2b4002a4463e3d6584a2f8fe2797d8635..0ba2a3455d99327f7a551b800e4c84e19dfe880b 100644
--- a/drivers/gpu/drm/i915/gvt/cmd_parser.c
+++ b/drivers/gpu/drm/i915/gvt/cmd_parser.c
@@ -428,7 +428,7 @@ struct cmd_info {
#define R_VECS BIT(VECS0)
#define R_ALL (R_RCS | R_VCS | R_BCS | R_VECS)
/* rings that support this cmd: BLT/RCS/VCS/VECS */
- u16 rings;
+ intel_engine_mask_t rings;
/* devices that support this cmd: SNB/IVB/HSW/... */
u16 devices;
diff --git a/drivers/gpu/drm/i915/i915_driver.c b/drivers/gpu/drm/i915/i915_driver.c
index b47746152d97fc2cbec410beaebfe9e69fdf5dcf..0e224761d0ed8cfa261cf64f6dd5af13999533b0 100644
--- a/drivers/gpu/drm/i915/i915_driver.c
+++ b/drivers/gpu/drm/i915/i915_driver.c
@@ -100,6 +100,9 @@
#include "intel_region_ttm.h"
#include "vlv_suspend.h"
+/* Intel Rapid Start Technology ACPI device name */
+static const char irst_name[] = "INT3392";
+
static const struct drm_driver i915_drm_driver;
static int i915_get_bridge_dev(struct drm_i915_private *dev_priv)
@@ -520,6 +523,22 @@ static int i915_set_dma_info(struct drm_i915_private *i915)
return ret;
}
+static int i915_pcode_init(struct drm_i915_private *i915)
+{
+ struct intel_gt *gt;
+ int id, ret;
+
+ for_each_gt(gt, i915, id) {
+ ret = intel_pcode_init(gt->uncore);
+ if (ret) {
+ drm_err(>->i915->drm, "gt%d: intel_pcode_init failed %d\n", id, ret);
+ return ret;
+ }
+ }
+
+ return 0;
+}
+
/**
* i915_driver_hw_probe - setup state requiring device access
* @dev_priv: device private
@@ -629,7 +648,7 @@ static int i915_driver_hw_probe(struct drm_i915_private *dev_priv)
intel_opregion_setup(dev_priv);
- ret = intel_pcode_init(&dev_priv->uncore);
+ ret = i915_pcode_init(dev_priv);
if (ret)
goto err_msi;
@@ -1251,7 +1270,7 @@ static int i915_drm_resume(struct drm_device *dev)
disable_rpm_wakeref_asserts(&dev_priv->runtime_pm);
- ret = intel_pcode_init(&dev_priv->uncore);
+ ret = i915_pcode_init(dev_priv);
if (ret)
return ret;
@@ -1425,6 +1444,8 @@ static int i915_pm_suspend(struct device *kdev)
return -ENODEV;
}
+ i915_ggtt_mark_pte_lost(i915, false);
+
if (i915->drm.switch_power_state == DRM_SWITCH_POWER_OFF)
return 0;
@@ -1477,6 +1498,14 @@ static int i915_pm_resume(struct device *kdev)
if (i915->drm.switch_power_state == DRM_SWITCH_POWER_OFF)
return 0;
+ /*
+ * If IRST is enabled, or if we can't detect whether it's enabled,
+ * then we must assume we lost the GGTT page table entries, since
+ * they are not retained if IRST decided to enter S4.
+ */
+ if (!IS_ENABLED(CONFIG_ACPI) || acpi_dev_present(irst_name, NULL, -1))
+ i915_ggtt_mark_pte_lost(i915, true);
+
return i915_drm_resume(&i915->drm);
}
@@ -1536,6 +1565,9 @@ static int i915_pm_restore_early(struct device *kdev)
static int i915_pm_restore(struct device *kdev)
{
+ struct drm_i915_private *i915 = kdev_to_i915(kdev);
+
+ i915_ggtt_mark_pte_lost(i915, true);
return i915_pm_resume(kdev);
}
diff --git a/drivers/gpu/drm/i915/i915_drm_client.c b/drivers/gpu/drm/i915/i915_drm_client.c
index 18d38cb59923d01b760cd5ae53064bf82b93c6d2..b09d1d3865740378006cc497da2dd3b3bddf60ff 100644
--- a/drivers/gpu/drm/i915/i915_drm_client.c
+++ b/drivers/gpu/drm/i915/i915_drm_client.c
@@ -116,8 +116,9 @@ show_client_class(struct seq_file *m,
total += busy_add(ctx, class);
rcu_read_unlock();
- seq_printf(m, "drm-engine-%s:\t%llu ns\n",
- uabi_class_names[class], total);
+ if (capacity)
+ seq_printf(m, "drm-engine-%s:\t%llu ns\n",
+ uabi_class_names[class], total);
if (capacity > 1)
seq_printf(m, "drm-engine-capacity-%s:\t%u\n",
diff --git a/drivers/gpu/drm/i915/i915_drm_client.h b/drivers/gpu/drm/i915/i915_drm_client.h
index f796c5e8e06066889cf71a5d101f8f8bb220cc86..69496af996d9e94ac1903bd834563d4ef80a2151 100644
--- a/drivers/gpu/drm/i915/i915_drm_client.h
+++ b/drivers/gpu/drm/i915/i915_drm_client.h
@@ -11,7 +11,7 @@
#include <linux/spinlock.h>
#include <linux/xarray.h>
-#include "gt/intel_engine_types.h"
+#include <uapi/drm/i915_drm.h>
#define I915_LAST_UABI_ENGINE_CLASS I915_ENGINE_CLASS_COMPUTE
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 4d57609d619a516b82f6d3eb19da9e6b5800fd20..c22f29c3faa0e2e665ad6131be7504e8447ec7f4 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -879,6 +879,7 @@ static inline struct intel_gt *to_gt(struct drm_i915_private *i915)
#define INTEL_DISPLAY_STEP(__i915) (RUNTIME_INFO(__i915)->step.display_step)
#define INTEL_GRAPHICS_STEP(__i915) (RUNTIME_INFO(__i915)->step.graphics_step)
#define INTEL_MEDIA_STEP(__i915) (RUNTIME_INFO(__i915)->step.media_step)
+#define INTEL_BASEDIE_STEP(__i915) (RUNTIME_INFO(__i915)->step.basedie_step)
#define IS_DISPLAY_STEP(__i915, since, until) \
(drm_WARN_ON(&(__i915)->drm, INTEL_DISPLAY_STEP(__i915) == STEP_NONE), \
@@ -892,6 +893,10 @@ static inline struct intel_gt *to_gt(struct drm_i915_private *i915)
(drm_WARN_ON(&(__i915)->drm, INTEL_MEDIA_STEP(__i915) == STEP_NONE), \
INTEL_MEDIA_STEP(__i915) >= (since) && INTEL_MEDIA_STEP(__i915) < (until))
+#define IS_BASEDIE_STEP(__i915, since, until) \
+ (drm_WARN_ON(&(__i915)->drm, INTEL_BASEDIE_STEP(__i915) == STEP_NONE), \
+ INTEL_BASEDIE_STEP(__i915) >= (since) && INTEL_BASEDIE_STEP(__i915) < (until))
+
static __always_inline unsigned int
__platform_mask_index(const struct intel_runtime_info *info,
enum intel_platform p)
@@ -1144,6 +1149,14 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915,
(IS_DG2(__i915) && \
IS_DISPLAY_STEP(__i915, since, until))
+#define IS_PVC_BD_STEP(__i915, since, until) \
+ (IS_PONTEVECCHIO(__i915) && \
+ IS_BASEDIE_STEP(__i915, since, until))
+
+#define IS_PVC_CT_STEP(__i915, since, until) \
+ (IS_PONTEVECCHIO(__i915) && \
+ IS_GRAPHICS_STEP(__i915, since, until))
+
#define IS_LP(dev_priv) (INTEL_INFO(dev_priv)->is_lp)
#define IS_GEN9_LP(dev_priv) (GRAPHICS_VER(dev_priv) == 9 && IS_LP(dev_priv))
#define IS_GEN9_BC(dev_priv) (GRAPHICS_VER(dev_priv) == 9 && !IS_LP(dev_priv))
@@ -1159,6 +1172,8 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915,
})
#define RCS_MASK(gt) \
ENGINE_INSTANCES_MASK(gt, RCS0, I915_MAX_RCS)
+#define BCS_MASK(gt) \
+ ENGINE_INSTANCES_MASK(gt, BCS0, I915_MAX_BCS)
#define VDBOX_MASK(gt) \
ENGINE_INSTANCES_MASK(gt, VCS0, I915_MAX_VCS)
#define VEBOX_MASK(gt) \
@@ -1267,9 +1282,6 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915,
#define HAS_RUNTIME_PM(dev_priv) (INTEL_INFO(dev_priv)->has_runtime_pm)
#define HAS_64BIT_RELOC(dev_priv) (INTEL_INFO(dev_priv)->has_64bit_reloc)
-#define HAS_MSLICES(dev_priv) \
- (INTEL_INFO(dev_priv)->has_mslices)
-
/*
* Set this flag, when platform requires 64K GTT page sizes or larger for
* device local memory access.
@@ -1308,6 +1320,8 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915,
#define HAS_LSPCON(dev_priv) (IS_DISPLAY_VER(dev_priv, 9, 10))
+#define HAS_L3_CCS_READ(i915) (INTEL_INFO(i915)->has_l3_ccs_read)
+
/* DPF == dynamic parity feature */
#define HAS_L3_DPF(dev_priv) (INTEL_INFO(dev_priv)->has_l3_dpf)
#define NUM_L3_SLICES(dev_priv) (IS_HSW_GT3(dev_priv) ? \
@@ -1341,6 +1355,10 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915,
#define HAS_MBUS_JOINING(i915) (IS_ALDERLAKE_P(i915))
+#define HAS_3D_PIPELINE(i915) (INTEL_INFO(i915)->has_3d_pipeline)
+
+#define HAS_ONE_EU_PER_FUSE_BIT(i915) (INTEL_INFO(i915)->has_one_eu_per_fuse_bit)
+
/* i915_gem.c */
void i915_gem_init_early(struct drm_i915_private *dev_priv);
void i915_gem_cleanup_early(struct drm_i915_private *dev_priv);
diff --git a/drivers/gpu/drm/i915/i915_getparam.c b/drivers/gpu/drm/i915/i915_getparam.c
index c12a0adefda539498151f3f1573b6508fae9618b..6fd15b39570c108a5c354f3f95e903852e525ab9 100644
--- a/drivers/gpu/drm/i915/i915_getparam.c
+++ b/drivers/gpu/drm/i915/i915_getparam.c
@@ -148,14 +148,21 @@ int i915_getparam_ioctl(struct drm_device *dev, void *data,
value = intel_engines_has_context_isolation(i915);
break;
case I915_PARAM_SLICE_MASK:
+ /* Not supported from Xe_HP onward; use topology queries */
+ if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 50))
+ return -EINVAL;
+
value = sseu->slice_mask;
if (!value)
return -ENODEV;
break;
case I915_PARAM_SUBSLICE_MASK:
+ /* Not supported from Xe_HP onward; use topology queries */
+ if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 50))
+ return -EINVAL;
+
/* Only copy bits from the first slice */
- memcpy(&value, sseu->subslice_mask,
- min(sseu->ss_stride, (u8)sizeof(value)));
+ value = intel_sseu_get_hsw_subslices(sseu, 0);
if (!value)
return -ENODEV;
break;
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index 0512c66fa4f3f1fd48dcd4e60c454deb51fa6ea2..f9b1969ed7ed28727912cfa283297584a5f332f0 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -581,6 +581,15 @@ static void error_print_engine(struct drm_i915_error_state_buf *m,
err_printf(m, " RC PSMI: 0x%08x\n", ee->rc_psmi);
err_printf(m, " FAULT_REG: 0x%08x\n", ee->fault_reg);
}
+ if (GRAPHICS_VER(m->i915) >= 11) {
+ err_printf(m, " NOPID: 0x%08x\n", ee->nopid);
+ err_printf(m, " EXCC: 0x%08x\n", ee->excc);
+ err_printf(m, " CMD_CCTL: 0x%08x\n", ee->cmd_cctl);
+ err_printf(m, " CSCMDOP: 0x%08x\n", ee->cscmdop);
+ err_printf(m, " CTX_SR_CTL: 0x%08x\n", ee->ctx_sr_ctl);
+ err_printf(m, " DMA_FADDR_HI: 0x%08x\n", ee->dma_faddr_hi);
+ err_printf(m, " DMA_FADDR_LO: 0x%08x\n", ee->dma_faddr_lo);
+ }
if (HAS_PPGTT(m->i915)) {
err_printf(m, " GFX_MODE: 0x%08x\n", ee->vm_info.gfx_mode);
@@ -1095,8 +1104,12 @@ i915_vma_coredump_create(const struct intel_gt *gt,
for_each_sgt_daddr(dma, iter, vma_res->bi.pages) {
mutex_lock(&ggtt->error_mutex);
- ggtt->vm.insert_page(&ggtt->vm, dma, slot,
- I915_CACHE_NONE, 0);
+ if (ggtt->vm.raw_insert_page)
+ ggtt->vm.raw_insert_page(&ggtt->vm, dma, slot,
+ I915_CACHE_NONE, 0);
+ else
+ ggtt->vm.insert_page(&ggtt->vm, dma, slot,
+ I915_CACHE_NONE, 0);
mb();
s = io_mapping_map_wc(&ggtt->iomap, slot, PAGE_SIZE);
@@ -1224,6 +1237,16 @@ static void engine_record_registers(struct intel_engine_coredump *ee)
ee->ipehr = ENGINE_READ(engine, IPEHR);
}
+ if (GRAPHICS_VER(i915) >= 11) {
+ ee->cmd_cctl = ENGINE_READ(engine, RING_CMD_CCTL);
+ ee->cscmdop = ENGINE_READ(engine, RING_CSCMDOP);
+ ee->ctx_sr_ctl = ENGINE_READ(engine, RING_CTX_SR_CTL);
+ ee->dma_faddr_hi = ENGINE_READ(engine, RING_DMA_FADD_UDW);
+ ee->dma_faddr_lo = ENGINE_READ(engine, RING_DMA_FADD);
+ ee->nopid = ENGINE_READ(engine, RING_NOPID);
+ ee->excc = ENGINE_READ(engine, RING_EXCC);
+ }
+
intel_engine_get_instdone(engine, &ee->instdone);
ee->instpm = ENGINE_READ(engine, RING_INSTPM);
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.h b/drivers/gpu/drm/i915/i915_gpu_error.h
index a611abacd9c2c089e3d1278e6d4eac24a6a148f9..55a143b92d10ec0fe58cf596bed5c17695aba4bf 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.h
+++ b/drivers/gpu/drm/i915/i915_gpu_error.h
@@ -84,6 +84,13 @@ struct intel_engine_coredump {
u32 fault_reg;
u64 faddr;
u32 rc_psmi; /* sleep state */
+ u32 nopid;
+ u32 excc;
+ u32 cmd_cctl;
+ u32 cscmdop;
+ u32 ctx_sr_ctl;
+ u32 dma_faddr_hi;
+ u32 dma_faddr_lo;
struct intel_instdone instdone;
/* GuC matched capture-lists info */
diff --git a/drivers/gpu/drm/i915/i915_pci.c b/drivers/gpu/drm/i915/i915_pci.c
index 47b2a2631c5bd80756aad26a3ffdf33c4848b753..d6d875b2d3799dec9183e35a8759496cb02a9b94 100644
--- a/drivers/gpu/drm/i915/i915_pci.c
+++ b/drivers/gpu/drm/i915/i915_pci.c
@@ -171,6 +171,7 @@
.display.overlay_needs_physical = 1, \
.display.has_gmch = 1, \
.gpu_reset_clobbers_display = true, \
+ .has_3d_pipeline = 1, \
.hws_needs_physical = 1, \
.unfenced_needs_alignment = 1, \
.platform_engine_mask = BIT(RCS0), \
@@ -190,6 +191,7 @@
.display.has_overlay = 1, \
.display.overlay_needs_physical = 1, \
.display.has_gmch = 1, \
+ .has_3d_pipeline = 1, \
.gpu_reset_clobbers_display = true, \
.hws_needs_physical = 1, \
.unfenced_needs_alignment = 1, \
@@ -232,6 +234,7 @@ static const struct intel_device_info i865g_info = {
.display.has_gmch = 1, \
.gpu_reset_clobbers_display = true, \
.platform_engine_mask = BIT(RCS0), \
+ .has_3d_pipeline = 1, \
.has_snoop = true, \
.has_coherent_ggtt = true, \
.dma_mask_size = 32, \
@@ -323,6 +326,7 @@ static const struct intel_device_info pnv_m_info = {
.display.has_gmch = 1, \
.gpu_reset_clobbers_display = true, \
.platform_engine_mask = BIT(RCS0), \
+ .has_3d_pipeline = 1, \
.has_snoop = true, \
.has_coherent_ggtt = true, \
.dma_mask_size = 36, \
@@ -374,6 +378,7 @@ static const struct intel_device_info gm45_info = {
.display.cpu_transcoder_mask = BIT(TRANSCODER_A) | BIT(TRANSCODER_B), \
.display.has_hotplug = 1, \
.platform_engine_mask = BIT(RCS0) | BIT(VCS0), \
+ .has_3d_pipeline = 1, \
.has_snoop = true, \
.has_coherent_ggtt = true, \
/* ilk does support rc6, but we do not implement [power] contexts */ \
@@ -405,6 +410,7 @@ static const struct intel_device_info ilk_m_info = {
.display.has_hotplug = 1, \
.display.fbc_mask = BIT(INTEL_FBC_A), \
.platform_engine_mask = BIT(RCS0) | BIT(VCS0) | BIT(BCS0), \
+ .has_3d_pipeline = 1, \
.has_coherent_ggtt = true, \
.has_llc = 1, \
.has_rc6 = 1, \
@@ -456,6 +462,7 @@ static const struct intel_device_info snb_m_gt2_info = {
.display.has_hotplug = 1, \
.display.fbc_mask = BIT(INTEL_FBC_A), \
.platform_engine_mask = BIT(RCS0) | BIT(VCS0) | BIT(BCS0), \
+ .has_3d_pipeline = 1, \
.has_coherent_ggtt = true, \
.has_llc = 1, \
.has_rc6 = 1, \
@@ -692,6 +699,7 @@ static const struct intel_device_info skl_gt4_info = {
.display.cpu_transcoder_mask = BIT(TRANSCODER_A) | BIT(TRANSCODER_B) | \
BIT(TRANSCODER_C) | BIT(TRANSCODER_EDP) | \
BIT(TRANSCODER_DSI_A) | BIT(TRANSCODER_DSI_C), \
+ .has_3d_pipeline = 1, \
.has_64bit_reloc = 1, \
.display.has_ddi = 1, \
.display.has_fpga_dbg = 1, \
@@ -1005,6 +1013,7 @@ static const struct intel_device_info adl_p_info = {
.graphics.rel = 50, \
XE_HP_PAGE_SIZES, \
.dma_mask_size = 46, \
+ .has_3d_pipeline = 1, \
.has_64bit_reloc = 1, \
.has_flat_ccs = 1, \
.has_global_mocs = 1, \
@@ -1012,7 +1021,7 @@ static const struct intel_device_info adl_p_info = {
.has_llc = 1, \
.has_logical_ring_contexts = 1, \
.has_logical_ring_elsq = 1, \
- .has_mslices = 1, \
+ .has_mslice_steering = 1, \
.has_rc6 = 1, \
.has_reset_engine = 1, \
.has_rps = 1, \
@@ -1079,7 +1088,12 @@ static const struct intel_device_info ats_m_info = {
#define XE_HPC_FEATURES \
XE_HP_FEATURES, \
- .dma_mask_size = 52
+ .dma_mask_size = 52, \
+ .has_3d_pipeline = 0, \
+ .has_guc_deprivilege = 1, \
+ .has_l3_ccs_read = 1, \
+ .has_mslice_steering = 0, \
+ .has_one_eu_per_fuse_bit = 1
__maybe_unused
static const struct intel_device_info pvc_info = {
diff --git a/drivers/gpu/drm/i915/i915_query.c b/drivers/gpu/drm/i915/i915_query.c
index 7584cec53d5da18ae3e8111368fb4fce8419f011..0094f67c63f2bfc3c32990f9dd9cd0ba1af8ea51 100644
--- a/drivers/gpu/drm/i915/i915_query.c
+++ b/drivers/gpu/drm/i915/i915_query.c
@@ -31,10 +31,12 @@ static int copy_query_item(void *query_hdr, size_t query_sz,
static int fill_topology_info(const struct sseu_dev_info *sseu,
struct drm_i915_query_item *query_item,
- const u8 *subslice_mask)
+ intel_sseu_ss_mask_t subslice_mask)
{
struct drm_i915_query_topology_info topo;
u32 slice_length, subslice_length, eu_length, total_length;
+ int ss_stride = GEN_SSEU_STRIDE(sseu->max_subslices);
+ int eu_stride = GEN_SSEU_STRIDE(sseu->max_eus_per_subslice);
int ret;
BUILD_BUG_ON(sizeof(u8) != sizeof(sseu->slice_mask));
@@ -43,8 +45,8 @@ static int fill_topology_info(const struct sseu_dev_info *sseu,
return -ENODEV;
slice_length = sizeof(sseu->slice_mask);
- subslice_length = sseu->max_slices * sseu->ss_stride;
- eu_length = sseu->max_slices * sseu->max_subslices * sseu->eu_stride;
+ subslice_length = sseu->max_slices * ss_stride;
+ eu_length = sseu->max_slices * sseu->max_subslices * eu_stride;
total_length = sizeof(topo) + slice_length + subslice_length +
eu_length;
@@ -59,9 +61,9 @@ static int fill_topology_info(const struct sseu_dev_info *sseu,
topo.max_eus_per_subslice = sseu->max_eus_per_subslice;
topo.subslice_offset = slice_length;
- topo.subslice_stride = sseu->ss_stride;
+ topo.subslice_stride = ss_stride;
topo.eu_offset = slice_length + subslice_length;
- topo.eu_stride = sseu->eu_stride;
+ topo.eu_stride = eu_stride;
if (copy_to_user(u64_to_user_ptr(query_item->data_ptr),
&topo, sizeof(topo)))
@@ -71,15 +73,15 @@ static int fill_topology_info(const struct sseu_dev_info *sseu,
&sseu->slice_mask, slice_length))
return -EFAULT;
- if (copy_to_user(u64_to_user_ptr(query_item->data_ptr +
- sizeof(topo) + slice_length),
- subslice_mask, subslice_length))
+ if (intel_sseu_copy_ssmask_to_user(u64_to_user_ptr(query_item->data_ptr +
+ sizeof(topo) + slice_length),
+ sseu))
return -EFAULT;
- if (copy_to_user(u64_to_user_ptr(query_item->data_ptr +
- sizeof(topo) +
- slice_length + subslice_length),
- sseu->eu_mask, eu_length))
+ if (intel_sseu_copy_eumask_to_user(u64_to_user_ptr(query_item->data_ptr +
+ sizeof(topo) +
+ slice_length + subslice_length),
+ sseu))
return -EFAULT;
return total_length;
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 616164fa2e320ed1e5f36ca8b09182225dd79c1f..643d7f020a4a4cd9feb2eb5ab2dd9ea34c44b852 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -976,6 +976,14 @@
#define GEN12_COMPUTE2_RING_BASE 0x1e000
#define GEN12_COMPUTE3_RING_BASE 0x26000
#define BLT_RING_BASE 0x22000
+#define XEHPC_BCS1_RING_BASE 0x3e0000
+#define XEHPC_BCS2_RING_BASE 0x3e2000
+#define XEHPC_BCS3_RING_BASE 0x3e4000
+#define XEHPC_BCS4_RING_BASE 0x3e6000
+#define XEHPC_BCS5_RING_BASE 0x3e8000
+#define XEHPC_BCS6_RING_BASE 0x3ea000
+#define XEHPC_BCS7_RING_BASE 0x3ec000
+#define XEHPC_BCS8_RING_BASE 0x3ee000
#define DG1_GSC_HECI1_BASE 0x00258000
#define DG1_GSC_HECI2_BASE 0x00259000
#define DG2_GSC_HECI1_BASE 0x00373000
@@ -1846,6 +1854,7 @@
#define BXT_RP_STATE_CAP _MMIO(0x138170)
#define GEN9_RP_STATE_LIMITS _MMIO(0x138148)
#define XEHPSDV_RP_STATE_CAP _MMIO(0x250014)
+#define PVC_RP_STATE_CAP _MMIO(0x281014)
#define GT0_PERF_LIMIT_REASONS _MMIO(0x1381a8)
#define GT0_PERF_LIMIT_REASONS_MASK 0xde3
@@ -6758,6 +6767,14 @@
#define DG1_UNCORE_GET_INIT_STATUS 0x0
#define DG1_UNCORE_INIT_STATUS_COMPLETE 0x1
#define GEN12_PCODE_READ_SAGV_BLOCK_TIME_US 0x23
+#define XEHP_PCODE_FREQUENCY_CONFIG 0x6e /* xehpsdv, pvc */
+/* XEHP_PCODE_FREQUENCY_CONFIG sub-commands (param1) */
+#define PCODE_MBOX_FC_SC_READ_FUSED_P0 0x0
+#define PCODE_MBOX_FC_SC_READ_FUSED_PN 0x1
+/* PCODE_MBOX_DOMAIN_* - mailbox domain IDs */
+/* XEHP_PCODE_FREQUENCY_CONFIG param2 */
+#define PCODE_MBOX_DOMAIN_NONE 0x0
+#define PCODE_MBOX_DOMAIN_MEDIAFF 0x3
#define GEN6_PCODE_DATA _MMIO(0x138128)
#define GEN6_PCODE_FREQ_IA_RATIO_SHIFT 8
#define GEN6_PCODE_FREQ_RING_RATIO_SHIFT 16
@@ -8328,23 +8345,6 @@ enum skl_power_gate {
#define SGGI_DIS REG_BIT(15)
#define SGR_DIS REG_BIT(13)
-#define XEHPSDV_TILE0_ADDR_RANGE _MMIO(0x4900)
-#define XEHPSDV_TILE_LMEM_RANGE_SHIFT 8
-
-#define XEHPSDV_FLAT_CCS_BASE_ADDR _MMIO(0x4910)
-#define XEHPSDV_CCS_BASE_SHIFT 8
-
-/* gamt regs */
-#define GEN8_L3_LRA_1_GPGPU _MMIO(0x4dd4)
-#define GEN8_L3_LRA_1_GPGPU_DEFAULT_VALUE_BDW 0x67F1427F /* max/min for LRA1/2 */
-#define GEN8_L3_LRA_1_GPGPU_DEFAULT_VALUE_CHV 0x5FF101FF /* max/min for LRA1/2 */
-#define GEN9_L3_LRA_1_GPGPU_DEFAULT_VALUE_SKL 0x67F1427F /* " " */
-#define GEN9_L3_LRA_1_GPGPU_DEFAULT_VALUE_BXT 0x5FF101FF /* " " */
-
-#define MMCD_MISC_CTRL _MMIO(0x4ddc) /* skl+ */
-#define MMCD_PCLA (1 << 31)
-#define MMCD_HOTSPOT_EN (1 << 27)
-
#define _ICL_PHY_MISC_A 0x64C00
#define _ICL_PHY_MISC_B 0x64C04
#define _DG2_PHY_MISC_TC1 0x64C14 /* TC1="PHY E" but offset as if "PHY F" */
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index 73d5195146b0b82665f9f5ca7d23e3380d1f4e6b..62fad16a55e84f15ba3784a298e1155349f64297 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -60,7 +60,7 @@ static struct kmem_cache *slab_execute_cbs;
static const char *i915_fence_get_driver_name(struct dma_fence *fence)
{
- return dev_name(to_request(fence)->engine->i915->drm.dev);
+ return dev_name(to_request(fence)->i915->drm.dev);
}
static const char *i915_fence_get_timeline_name(struct dma_fence *fence)
@@ -134,17 +134,42 @@ static void i915_fence_release(struct dma_fence *fence)
i915_sw_fence_fini(&rq->semaphore);
/*
- * Keep one request on each engine for reserved use under mempressure,
+ * Keep one request on each engine for reserved use under mempressure
* do not use with virtual engines as this really is only needed for
* kernel contexts.
+ *
+ * We do not hold a reference to the engine here and so have to be
+ * very careful in what rq->engine we poke. The virtual engine is
+ * referenced via the rq->context and we released that ref during
+ * i915_request_retire(), ergo we must not dereference a virtual
+ * engine here. Not that we would want to, as the only consumer of
+ * the reserved engine->request_pool is the power management parking,
+ * which must-not-fail, and that is only run on the physical engines.
+ *
+ * Since the request must have been executed to be have completed,
+ * we know that it will have been processed by the HW and will
+ * not be unsubmitted again, so rq->engine and rq->execution_mask
+ * at this point is stable. rq->execution_mask will be a single
+ * bit if the last and _only_ engine it could execution on was a
+ * physical engine, if it's multiple bits then it started on and
+ * could still be on a virtual engine. Thus if the mask is not a
+ * power-of-two we assume that rq->engine may still be a virtual
+ * engine and so a dangling invalid pointer that we cannot dereference
+ *
+ * For example, consider the flow of a bonded request through a virtual
+ * engine. The request is created with a wide engine mask (all engines
+ * that we might execute on). On processing the bond, the request mask
+ * is reduced to one or more engines. If the request is subsequently
+ * bound to a single engine, it will then be constrained to only
+ * execute on that engine and never returned to the virtual engine
+ * after timeslicing away, see __unwind_incomplete_requests(). Thus we
+ * know that if the rq->execution_mask is a single bit, rq->engine
+ * can be a physical engine with the exact corresponding mask.
*/
if (!intel_engine_is_virtual(rq->engine) &&
- !cmpxchg(&rq->engine->request_pool, NULL, rq)) {
- intel_context_put(rq->context);
+ is_power_of_2(rq->execution_mask) &&
+ !cmpxchg(&rq->engine->request_pool, NULL, rq))
return;
- }
-
- intel_context_put(rq->context);
kmem_cache_free(slab_requests, rq);
}
@@ -611,7 +636,7 @@ bool __i915_request_submit(struct i915_request *request)
goto active;
}
- if (unlikely(intel_context_is_banned(request->context)))
+ if (unlikely(!intel_context_is_schedulable(request->context)))
i915_request_set_error_once(request, -EIO);
if (unlikely(fatal_error(request->fence.error)))
@@ -921,22 +946,11 @@ __i915_request_create(struct intel_context *ce, gfp_t gfp)
}
}
- /*
- * Hold a reference to the intel_context over life of an i915_request.
- * Without this an i915_request can exist after the context has been
- * destroyed (e.g. request retired, context closed, but user space holds
- * a reference to the request from an out fence). In the case of GuC
- * submission + virtual engine, the engine that the request references
- * is also destroyed which can trigger bad pointer dref in fence ops
- * (e.g. i915_fence_get_driver_name). We could likely change these
- * functions to avoid touching the engine but let's just be safe and
- * hold the intel_context reference. In execlist mode the request always
- * eventually points to a physical engine so this isn't an issue.
- */
- rq->context = intel_context_get(ce);
+ rq->context = ce;
rq->engine = ce->engine;
rq->ring = ce->ring;
rq->execution_mask = ce->engine->mask;
+ rq->i915 = ce->engine->i915;
ret = intel_timeline_get_seqno(tl, rq, &seqno);
if (ret)
@@ -1008,7 +1022,6 @@ __i915_request_create(struct intel_context *ce, gfp_t gfp)
GEM_BUG_ON(!list_empty(&rq->sched.waiters_list));
err_free:
- intel_context_put(ce);
kmem_cache_free(slab_requests, rq);
err_unreserve:
intel_context_unpin(ce);
diff --git a/drivers/gpu/drm/i915/i915_request.h b/drivers/gpu/drm/i915/i915_request.h
index 28b1f9db54875944d59d3a59b1e85c6ff16d4aa6..47041ec68df8982eb9be0d0269cb77b8ac44dfd7 100644
--- a/drivers/gpu/drm/i915/i915_request.h
+++ b/drivers/gpu/drm/i915/i915_request.h
@@ -196,6 +196,8 @@ struct i915_request {
struct dma_fence fence;
spinlock_t lock;
+ struct drm_i915_private *i915;
+
/**
* Context and ring buffer related to this request
* Contexts are refcounted, so when this request is associated with a
diff --git a/drivers/gpu/drm/i915/i915_sysfs.c b/drivers/gpu/drm/i915/i915_sysfs.c
index 8521daba212a79f740ec1e1966cdfc47e10bea13..1e2750210831308d1edd4c1c4bde4dfa3ebd77cc 100644
--- a/drivers/gpu/drm/i915/i915_sysfs.c
+++ b/drivers/gpu/drm/i915/i915_sysfs.c
@@ -166,7 +166,14 @@ static ssize_t error_state_read(struct file *filp, struct kobject *kobj,
struct device *kdev = kobj_to_dev(kobj);
struct drm_i915_private *i915 = kdev_minor_to_i915(kdev);
struct i915_gpu_coredump *gpu;
- ssize_t ret;
+ ssize_t ret = 0;
+
+ /*
+ * FIXME: Concurrent clients triggering resets and reading + clearing
+ * dumps can cause inconsistent sysfs reads when a user calls in with a
+ * non-zero offset to complete a prior partial read but the
+ * gpu_coredump has been cleared or replaced.
+ */
gpu = i915_first_error_state(i915);
if (IS_ERR(gpu)) {
@@ -178,8 +185,10 @@ static ssize_t error_state_read(struct file *filp, struct kobject *kobj,
const char *str = "No error state collected\n";
size_t len = strlen(str);
- ret = min_t(size_t, count, len - off);
- memcpy(buf, str + off, ret);
+ if (off < len) {
+ ret = min_t(size_t, count, len - off);
+ memcpy(buf, str + off, ret);
+ }
}
return ret;
@@ -259,4 +268,6 @@ void i915_teardown_sysfs(struct drm_i915_private *dev_priv)
device_remove_bin_file(kdev, &dpf_attrs_1);
device_remove_bin_file(kdev, &dpf_attrs);
+
+ kobject_put(dev_priv->sysfs_gt);
}
diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c
index 4f6db539571aa64d3327e577cb6cc4e026ff2f49..5d5828b9a24268e69659f0eaa8184d82d3df7863 100644
--- a/drivers/gpu/drm/i915/i915_vma.c
+++ b/drivers/gpu/drm/i915/i915_vma.c
@@ -23,6 +23,7 @@
*/
#include <linux/sched/mm.h>
+#include <linux/dma-fence-array.h>
#include <drm/drm_gem.h>
#include "display/intel_frontbuffer.h"
@@ -550,13 +551,6 @@ void __iomem *i915_vma_pin_iomap(struct i915_vma *vma)
if (WARN_ON_ONCE(vma->obj->flags & I915_BO_ALLOC_GPU_ONLY))
return IOMEM_ERR_PTR(-EINVAL);
- if (!i915_gem_object_is_lmem(vma->obj)) {
- if (GEM_WARN_ON(!i915_vma_is_map_and_fenceable(vma))) {
- err = -ENODEV;
- goto err;
- }
- }
-
GEM_BUG_ON(!i915_vma_is_ggtt(vma));
GEM_BUG_ON(!i915_vma_is_bound(vma, I915_VMA_GLOBAL_BIND));
GEM_BUG_ON(i915_vma_verify_bind_complete(vma));
@@ -569,20 +563,33 @@ void __iomem *i915_vma_pin_iomap(struct i915_vma *vma)
* of pages, that way we can also drop the
* I915_BO_ALLOC_CONTIGUOUS when allocating the object.
*/
- if (i915_gem_object_is_lmem(vma->obj))
+ if (i915_gem_object_is_lmem(vma->obj)) {
ptr = i915_gem_object_lmem_io_map(vma->obj, 0,
vma->obj->base.size);
- else
+ } else if (i915_vma_is_map_and_fenceable(vma)) {
ptr = io_mapping_map_wc(&i915_vm_to_ggtt(vma->vm)->iomap,
vma->node.start,
vma->node.size);
+ } else {
+ ptr = (void __iomem *)
+ i915_gem_object_pin_map(vma->obj, I915_MAP_WC);
+ if (IS_ERR(ptr)) {
+ err = PTR_ERR(ptr);
+ goto err;
+ }
+ ptr = page_pack_bits(ptr, 1);
+ }
+
if (ptr == NULL) {
err = -ENOMEM;
goto err;
}
if (unlikely(cmpxchg(&vma->iomap, NULL, ptr))) {
- io_mapping_unmap(ptr);
+ if (page_unmask_bits(ptr))
+ __i915_gem_object_release_map(vma->obj);
+ else
+ io_mapping_unmap(ptr);
ptr = vma->iomap;
}
}
@@ -596,7 +603,7 @@ void __iomem *i915_vma_pin_iomap(struct i915_vma *vma)
i915_vma_set_ggtt_write(vma);
/* NB Access through the GTT requires the device to be awake. */
- return ptr;
+ return page_mask_bits(ptr);
err_unpin:
__i915_vma_unpin(vma);
@@ -614,6 +621,8 @@ void i915_vma_unpin_iomap(struct i915_vma *vma)
{
GEM_BUG_ON(vma->iomap == NULL);
+ /* XXX We keep the mapping until __i915_vma_unbind()/evict() */
+
i915_vma_flush_writes(vma);
i915_vma_unpin_fence(vma);
@@ -1762,7 +1771,10 @@ static void __i915_vma_iounmap(struct i915_vma *vma)
if (vma->iomap == NULL)
return;
- io_mapping_unmap(vma->iomap);
+ if (page_unmask_bits(vma->iomap))
+ __i915_gem_object_release_map(vma->obj);
+ else
+ io_mapping_unmap(vma->iomap);
vma->iomap = NULL;
}
@@ -1823,6 +1835,21 @@ int _i915_vma_move_to_active(struct i915_vma *vma,
if (unlikely(err))
return err;
+ /*
+ * Reserve fences slot early to prevent an allocation after preparing
+ * the workload and associating fences with dma_resv.
+ */
+ if (fence && !(flags & __EXEC_OBJECT_NO_RESERVE)) {
+ struct dma_fence *curr;
+ int idx;
+
+ dma_fence_array_for_each(curr, idx, fence)
+ ;
+ err = dma_resv_reserve_fences(vma->obj->base.resv, idx);
+ if (unlikely(err))
+ return err;
+ }
+
if (flags & EXEC_OBJECT_WRITE) {
struct intel_frontbuffer *front;
@@ -1832,31 +1859,23 @@ int _i915_vma_move_to_active(struct i915_vma *vma,
i915_active_add_request(&front->write, rq);
intel_frontbuffer_put(front);
}
+ }
- if (!(flags & __EXEC_OBJECT_NO_RESERVE)) {
- err = dma_resv_reserve_fences(vma->obj->base.resv, 1);
- if (unlikely(err))
- return err;
- }
+ if (fence) {
+ struct dma_fence *curr;
+ enum dma_resv_usage usage;
+ int idx;
- if (fence) {
- dma_resv_add_fence(vma->obj->base.resv, fence,
- DMA_RESV_USAGE_WRITE);
+ obj->read_domains = 0;
+ if (flags & EXEC_OBJECT_WRITE) {
+ usage = DMA_RESV_USAGE_WRITE;
obj->write_domain = I915_GEM_DOMAIN_RENDER;
- obj->read_domains = 0;
- }
- } else {
- if (!(flags & __EXEC_OBJECT_NO_RESERVE)) {
- err = dma_resv_reserve_fences(vma->obj->base.resv, 1);
- if (unlikely(err))
- return err;
+ } else {
+ usage = DMA_RESV_USAGE_READ;
}
- if (fence) {
- dma_resv_add_fence(vma->obj->base.resv, fence,
- DMA_RESV_USAGE_READ);
- obj->write_domain = 0;
- }
+ dma_fence_array_for_each(curr, idx, fence)
+ dma_resv_add_fence(vma->obj->base.resv, curr, usage);
}
if (flags & EXEC_OBJECT_NEEDS_FENCE && vma->fence)
@@ -1899,9 +1918,11 @@ struct dma_fence *__i915_vma_evict(struct i915_vma *vma, bool async)
/* release the fence reg _after_ flushing */
i915_vma_revoke_fence(vma);
- __i915_vma_iounmap(vma);
clear_bit(I915_VMA_CAN_FENCE_BIT, __i915_vma_flags(vma));
}
+
+ __i915_vma_iounmap(vma);
+
GEM_BUG_ON(vma->fence);
GEM_BUG_ON(i915_vma_has_userfault(vma));
diff --git a/drivers/gpu/drm/i915/intel_device_info.h b/drivers/gpu/drm/i915/intel_device_info.h
index f414144eadf8d72602e9b2b9bb9bd9041ad2d88f..08341174ee0a544e2f87affcbd4c59905c8afaf2 100644
--- a/drivers/gpu/drm/i915/intel_device_info.h
+++ b/drivers/gpu/drm/i915/intel_device_info.h
@@ -143,6 +143,7 @@ enum intel_ppgtt_type {
func(needs_compact_pt); \
func(gpu_reset_clobbers_display); \
func(has_reset_engine); \
+ func(has_3d_pipeline); \
func(has_4tile); \
func(has_flat_ccs); \
func(has_global_mocs); \
@@ -150,12 +151,14 @@ enum intel_ppgtt_type {
func(has_heci_pxp); \
func(has_heci_gscfi); \
func(has_guc_deprivilege); \
+ func(has_l3_ccs_read); \
func(has_l3_dpf); \
func(has_llc); \
func(has_logical_ring_contexts); \
func(has_logical_ring_elsq); \
func(has_media_ratio_mode); \
- func(has_mslices); \
+ func(has_mslice_steering); \
+ func(has_one_eu_per_fuse_bit); \
func(has_pooled_eu); \
func(has_pxp); \
func(has_rc6); \
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 3355486a0b2036151f62a8f2b9b94ac4b6907741..9b7e93ca1ff9edfd22843395b9bac301b877ec1f 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -7634,10 +7634,9 @@ static void xehpsdv_init_clock_gating(struct drm_i915_private *dev_priv)
static void dg2_init_clock_gating(struct drm_i915_private *i915)
{
- /* Wa_22010954014:dg2_g10 */
- if (IS_DG2_G10(i915))
- intel_uncore_rmw(&i915->uncore, XEHP_CLOCK_GATE_DIS, 0,
- SGSI_SIDECLK_DIS);
+ /* Wa_22010954014:dg2 */
+ intel_uncore_rmw(&i915->uncore, XEHP_CLOCK_GATE_DIS, 0,
+ SGSI_SIDECLK_DIS);
/*
* Wa_14010733611:dg2_g10
@@ -7648,6 +7647,17 @@ static void dg2_init_clock_gating(struct drm_i915_private *i915)
SGR_DIS | SGGI_DIS);
}
+static void pvc_init_clock_gating(struct drm_i915_private *dev_priv)
+{
+ /* Wa_14012385139:pvc */
+ if (IS_PVC_BD_STEP(dev_priv, STEP_A0, STEP_B0))
+ intel_uncore_rmw(&dev_priv->uncore, XEHP_CLOCK_GATE_DIS, 0, SGR_DIS);
+
+ /* Wa_22010954014:pvc */
+ if (IS_PVC_BD_STEP(dev_priv, STEP_A0, STEP_B0))
+ intel_uncore_rmw(&dev_priv->uncore, XEHP_CLOCK_GATE_DIS, 0, SGSI_SIDECLK_DIS);
+}
+
static void cnp_init_clock_gating(struct drm_i915_private *dev_priv)
{
if (!HAS_PCH_CNP(dev_priv))
@@ -8064,6 +8074,7 @@ static const struct drm_i915_clock_gating_funcs platform##_clock_gating_funcs =
.init_clock_gating = platform##_init_clock_gating, \
}
+CG_FUNCS(pvc);
CG_FUNCS(dg2);
CG_FUNCS(xehpsdv);
CG_FUNCS(adlp);
@@ -8102,7 +8113,9 @@ CG_FUNCS(nop);
*/
void intel_init_clock_gating_hooks(struct drm_i915_private *dev_priv)
{
- if (IS_DG2(dev_priv))
+ if (IS_PONTEVECCHIO(dev_priv))
+ dev_priv->clock_gating_funcs = &pvc_clock_gating_funcs;
+ else if (IS_DG2(dev_priv))
dev_priv->clock_gating_funcs = &dg2_clock_gating_funcs;
else if (IS_XEHPSDV(dev_priv))
dev_priv->clock_gating_funcs = &xehpsdv_clock_gating_funcs;
diff --git a/drivers/gpu/drm/i915/intel_step.c b/drivers/gpu/drm/i915/intel_step.c
index 74e8e4680028a2ccfb04761408aba2e80e5edb10..42b3133d8387aba0330e3e246b6aef8647261df8 100644
--- a/drivers/gpu/drm/i915/intel_step.c
+++ b/drivers/gpu/drm/i915/intel_step.c
@@ -135,6 +135,8 @@ static const struct intel_step_info adlp_n_revids[] = {
[0x0] = { COMMON_GT_MEDIA_STEP(A0), .display_step = STEP_D0 },
};
+static void pvc_step_init(struct drm_i915_private *i915, int pci_revid);
+
void intel_step_init(struct drm_i915_private *i915)
{
const struct intel_step_info *revids = NULL;
@@ -142,7 +144,10 @@ void intel_step_init(struct drm_i915_private *i915)
int revid = INTEL_REVID(i915);
struct intel_step_info step = {};
- if (IS_DG2_G10(i915)) {
+ if (IS_PONTEVECCHIO(i915)) {
+ pvc_step_init(i915, revid);
+ return;
+ } else if (IS_DG2_G10(i915)) {
revids = dg2_g10_revid_step_tbl;
size = ARRAY_SIZE(dg2_g10_revid_step_tbl);
} else if (IS_DG2_G11(i915)) {
@@ -235,6 +240,69 @@ void intel_step_init(struct drm_i915_private *i915)
RUNTIME_INFO(i915)->step = step;
}
+#define PVC_BD_REVID GENMASK(5, 3)
+#define PVC_CT_REVID GENMASK(2, 0)
+
+static const int pvc_bd_subids[] = {
+ [0x0] = STEP_A0,
+ [0x3] = STEP_B0,
+ [0x4] = STEP_B1,
+ [0x5] = STEP_B3,
+};
+
+static const int pvc_ct_subids[] = {
+ [0x3] = STEP_A0,
+ [0x5] = STEP_B0,
+ [0x6] = STEP_B1,
+ [0x7] = STEP_C0,
+};
+
+static int
+pvc_step_lookup(struct drm_i915_private *i915, const char *type,
+ const int *table, int size, int subid)
+{
+ if (subid < size && table[subid] != STEP_NONE)
+ return table[subid];
+
+ drm_warn(&i915->drm, "Unknown %s id 0x%02x\n", type, subid);
+
+ /*
+ * As on other platforms, try to use the next higher ID if we land on a
+ * gap in the table.
+ */
+ while (subid < size && table[subid] == STEP_NONE)
+ subid++;
+
+ if (subid < size) {
+ drm_dbg(&i915->drm, "Using steppings for %s id 0x%02x\n",
+ type, subid);
+ return table[subid];
+ }
+
+ drm_dbg(&i915->drm, "Using future steppings\n");
+ return STEP_FUTURE;
+}
+
+/*
+ * PVC needs special handling since we don't lookup the
+ * revid in a table, but rather specific bitfields within
+ * the revid for various components.
+ */
+static void pvc_step_init(struct drm_i915_private *i915, int pci_revid)
+{
+ int ct_subid, bd_subid;
+
+ bd_subid = FIELD_GET(PVC_BD_REVID, pci_revid);
+ ct_subid = FIELD_GET(PVC_CT_REVID, pci_revid);
+
+ RUNTIME_INFO(i915)->step.basedie_step =
+ pvc_step_lookup(i915, "Base Die", pvc_bd_subids,
+ ARRAY_SIZE(pvc_bd_subids), bd_subid);
+ RUNTIME_INFO(i915)->step.graphics_step =
+ pvc_step_lookup(i915, "Compute Tile", pvc_ct_subids,
+ ARRAY_SIZE(pvc_ct_subids), ct_subid);
+}
+
#define STEP_NAME_CASE(name) \
case STEP_##name: \
return #name;
diff --git a/drivers/gpu/drm/i915/intel_step.h b/drivers/gpu/drm/i915/intel_step.h
index d71a99bd51793d2c3f2b4f11a9f46fe81f77cf5c..a6b12bfa9744a27a0d4c939f453fd9070598dc5f 100644
--- a/drivers/gpu/drm/i915/intel_step.h
+++ b/drivers/gpu/drm/i915/intel_step.h
@@ -11,9 +11,10 @@
struct drm_i915_private;
struct intel_step_info {
- u8 graphics_step;
+ u8 graphics_step; /* Represents the compute tile on Xe_HPC */
u8 display_step;
u8 media_step;
+ u8 basedie_step;
};
#define STEP_ENUM_VAL(name) STEP_##name,
@@ -25,6 +26,7 @@ struct intel_step_info {
func(B0) \
func(B1) \
func(B2) \
+ func(B3) \
func(C0) \
func(C1) \
func(D0) \
diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c
index 83517a703eb6e8421658b7c3248f40e4246b2f75..a852c471d1b38576f2f0740edb7105db79f66949 100644
--- a/drivers/gpu/drm/i915/intel_uncore.c
+++ b/drivers/gpu/drm/i915/intel_uncore.c
@@ -938,36 +938,32 @@ find_fw_domain(struct intel_uncore *uncore, u32 offset)
return entry->domains;
}
-#define GEN_FW_RANGE(s, e, d) \
- { .start = (s), .end = (e), .domains = (d) }
-
-/* *Must* be sorted by offset ranges! See intel_fw_table_check(). */
-static const struct intel_forcewake_range __vlv_fw_ranges[] = {
- GEN_FW_RANGE(0x2000, 0x3fff, FORCEWAKE_RENDER),
- GEN_FW_RANGE(0x5000, 0x7fff, FORCEWAKE_RENDER),
- GEN_FW_RANGE(0xb000, 0x11fff, FORCEWAKE_RENDER),
- GEN_FW_RANGE(0x12000, 0x13fff, FORCEWAKE_MEDIA),
- GEN_FW_RANGE(0x22000, 0x23fff, FORCEWAKE_MEDIA),
- GEN_FW_RANGE(0x2e000, 0x2ffff, FORCEWAKE_RENDER),
- GEN_FW_RANGE(0x30000, 0x3ffff, FORCEWAKE_MEDIA),
-};
-
-#define __fwtable_reg_read_fw_domains(uncore, offset) \
-({ \
- enum forcewake_domains __fwd = 0; \
- if (NEEDS_FORCE_WAKE((offset))) \
- __fwd = find_fw_domain(uncore, offset); \
- __fwd; \
-})
+/*
+ * Shadowed register tables describe special register ranges that i915 is
+ * allowed to write to without acquiring forcewake. If these registers' power
+ * wells are down, the hardware will save values written by i915 to a shadow
+ * copy and automatically transfer them into the real register the next time
+ * the power well is woken up. Shadowing only applies to writes; forcewake
+ * must still be acquired when reading from registers in these ranges.
+ *
+ * The documentation for shadowed registers is somewhat spotty on older
+ * platforms. However missing registers from these lists is non-fatal; it just
+ * means we'll wake up the hardware for some register accesses where we didn't
+ * really need to.
+ *
+ * The ranges listed in these tables must be sorted by offset.
+ *
+ * When adding new tables here, please also add them to
+ * intel_shadow_table_check() in selftests/intel_uncore.c so that they will be
+ * scanned for obvious mistakes or typos by the selftests.
+ */
-/* *Must* be sorted by offset! See intel_shadow_table_check(). */
static const struct i915_range gen8_shadowed_regs[] = {
{ .start = 0x2030, .end = 0x2030 },
{ .start = 0xA008, .end = 0xA00C },
{ .start = 0x12030, .end = 0x12030 },
{ .start = 0x1a030, .end = 0x1a030 },
{ .start = 0x22030, .end = 0x22030 },
- /* TODO: Other registers are not yet used */
};
static const struct i915_range gen11_shadowed_regs[] = {
@@ -1080,6 +1076,45 @@ static const struct i915_range dg2_shadowed_regs[] = {
{ .start = 0x1F8510, .end = 0x1F8550 },
};
+static const struct i915_range pvc_shadowed_regs[] = {
+ { .start = 0x2030, .end = 0x2030 },
+ { .start = 0x2510, .end = 0x2550 },
+ { .start = 0xA008, .end = 0xA00C },
+ { .start = 0xA188, .end = 0xA188 },
+ { .start = 0xA278, .end = 0xA278 },
+ { .start = 0xA540, .end = 0xA56C },
+ { .start = 0xC4C8, .end = 0xC4C8 },
+ { .start = 0xC4E0, .end = 0xC4E0 },
+ { .start = 0xC600, .end = 0xC600 },
+ { .start = 0xC658, .end = 0xC658 },
+ { .start = 0x22030, .end = 0x22030 },
+ { .start = 0x22510, .end = 0x22550 },
+ { .start = 0x1C0030, .end = 0x1C0030 },
+ { .start = 0x1C0510, .end = 0x1C0550 },
+ { .start = 0x1C4030, .end = 0x1C4030 },
+ { .start = 0x1C4510, .end = 0x1C4550 },
+ { .start = 0x1C8030, .end = 0x1C8030 },
+ { .start = 0x1C8510, .end = 0x1C8550 },
+ { .start = 0x1D0030, .end = 0x1D0030 },
+ { .start = 0x1D0510, .end = 0x1D0550 },
+ { .start = 0x1D4030, .end = 0x1D4030 },
+ { .start = 0x1D4510, .end = 0x1D4550 },
+ { .start = 0x1D8030, .end = 0x1D8030 },
+ { .start = 0x1D8510, .end = 0x1D8550 },
+ { .start = 0x1E0030, .end = 0x1E0030 },
+ { .start = 0x1E0510, .end = 0x1E0550 },
+ { .start = 0x1E4030, .end = 0x1E4030 },
+ { .start = 0x1E4510, .end = 0x1E4550 },
+ { .start = 0x1E8030, .end = 0x1E8030 },
+ { .start = 0x1E8510, .end = 0x1E8550 },
+ { .start = 0x1F0030, .end = 0x1F0030 },
+ { .start = 0x1F0510, .end = 0x1F0550 },
+ { .start = 0x1F4030, .end = 0x1F4030 },
+ { .start = 0x1F4510, .end = 0x1F4550 },
+ { .start = 0x1F8030, .end = 0x1F8030 },
+ { .start = 0x1F8510, .end = 0x1F8550 },
+};
+
static int mmio_range_cmp(u32 key, const struct i915_range *range)
{
if (key < range->start)
@@ -1107,11 +1142,70 @@ gen6_reg_write_fw_domains(struct intel_uncore *uncore, i915_reg_t reg)
return FORCEWAKE_RENDER;
}
+#define __fwtable_reg_read_fw_domains(uncore, offset) \
+({ \
+ enum forcewake_domains __fwd = 0; \
+ if (NEEDS_FORCE_WAKE((offset))) \
+ __fwd = find_fw_domain(uncore, offset); \
+ __fwd; \
+})
+
+#define __fwtable_reg_write_fw_domains(uncore, offset) \
+({ \
+ enum forcewake_domains __fwd = 0; \
+ const u32 __offset = (offset); \
+ if (NEEDS_FORCE_WAKE((__offset)) && !is_shadowed(uncore, __offset)) \
+ __fwd = find_fw_domain(uncore, __offset); \
+ __fwd; \
+})
+
+#define GEN_FW_RANGE(s, e, d) \
+ { .start = (s), .end = (e), .domains = (d) }
+
+/*
+ * All platforms' forcewake tables below must be sorted by offset ranges.
+ * Furthermore, new forcewake tables added should be "watertight" and have
+ * no gaps between ranges.
+ *
+ * When there are multiple consecutive ranges listed in the bspec with
+ * the same forcewake domain, it is customary to combine them into a single
+ * row in the tables below to keep the tables small and lookups fast.
+ * Likewise, reserved/unused ranges may be combined with the preceding and/or
+ * following ranges since the driver will never be making MMIO accesses in
+ * those ranges.
+ *
+ * For example, if the bspec were to list:
+ *
+ * ...
+ * 0x1000 - 0x1fff: GT
+ * 0x2000 - 0x2cff: GT
+ * 0x2d00 - 0x2fff: unused/reserved
+ * 0x3000 - 0xffff: GT
+ * ...
+ *
+ * these could all be represented by a single line in the code:
+ *
+ * GEN_FW_RANGE(0x1000, 0xffff, FORCEWAKE_GT)
+ *
+ * When adding new forcewake tables here, please also add them to
+ * intel_uncore_mock_selftests in selftests/intel_uncore.c so that they will be
+ * scanned for obvious mistakes or typos by the selftests.
+ */
+
static const struct intel_forcewake_range __gen6_fw_ranges[] = {
GEN_FW_RANGE(0x0, 0x3ffff, FORCEWAKE_RENDER),
};
-/* *Must* be sorted by offset ranges! See intel_fw_table_check(). */
+static const struct intel_forcewake_range __vlv_fw_ranges[] = {
+ GEN_FW_RANGE(0x2000, 0x3fff, FORCEWAKE_RENDER),
+ GEN_FW_RANGE(0x5000, 0x7fff, FORCEWAKE_RENDER),
+ GEN_FW_RANGE(0xb000, 0x11fff, FORCEWAKE_RENDER),
+ GEN_FW_RANGE(0x12000, 0x13fff, FORCEWAKE_MEDIA),
+ GEN_FW_RANGE(0x22000, 0x23fff, FORCEWAKE_MEDIA),
+ GEN_FW_RANGE(0x2e000, 0x2ffff, FORCEWAKE_RENDER),
+ GEN_FW_RANGE(0x30000, 0x3ffff, FORCEWAKE_MEDIA),
+};
+
static const struct intel_forcewake_range __chv_fw_ranges[] = {
GEN_FW_RANGE(0x2000, 0x3fff, FORCEWAKE_RENDER),
GEN_FW_RANGE(0x4000, 0x4fff, FORCEWAKE_RENDER | FORCEWAKE_MEDIA),
@@ -1131,16 +1225,6 @@ static const struct intel_forcewake_range __chv_fw_ranges[] = {
GEN_FW_RANGE(0x30000, 0x37fff, FORCEWAKE_MEDIA),
};
-#define __fwtable_reg_write_fw_domains(uncore, offset) \
-({ \
- enum forcewake_domains __fwd = 0; \
- const u32 __offset = (offset); \
- if (NEEDS_FORCE_WAKE((__offset)) && !is_shadowed(uncore, __offset)) \
- __fwd = find_fw_domain(uncore, __offset); \
- __fwd; \
-})
-
-/* *Must* be sorted by offset ranges! See intel_fw_table_check(). */
static const struct intel_forcewake_range __gen9_fw_ranges[] = {
GEN_FW_RANGE(0x0, 0xaff, FORCEWAKE_GT),
GEN_FW_RANGE(0xb00, 0x1fff, 0), /* uncore range */
@@ -1176,7 +1260,6 @@ static const struct intel_forcewake_range __gen9_fw_ranges[] = {
GEN_FW_RANGE(0x30000, 0x3ffff, FORCEWAKE_MEDIA),
};
-/* *Must* be sorted by offset ranges! See intel_fw_table_check(). */
static const struct intel_forcewake_range __gen11_fw_ranges[] = {
GEN_FW_RANGE(0x0, 0x1fff, 0), /* uncore range */
GEN_FW_RANGE(0x2000, 0x26ff, FORCEWAKE_RENDER),
@@ -1215,14 +1298,6 @@ static const struct intel_forcewake_range __gen11_fw_ranges[] = {
GEN_FW_RANGE(0x1d4000, 0x1dbfff, 0)
};
-/*
- * *Must* be sorted by offset ranges! See intel_fw_table_check().
- *
- * Note that the spec lists several reserved/unused ranges that don't
- * actually contain any registers. In the table below we'll combine those
- * reserved ranges with either the preceding or following range to keep the
- * table small and lookups fast.
- */
static const struct intel_forcewake_range __gen12_fw_ranges[] = {
GEN_FW_RANGE(0x0, 0x1fff, 0), /*
0x0 - 0xaff: reserved
@@ -1327,8 +1402,6 @@ static const struct intel_forcewake_range __gen12_fw_ranges[] = {
/*
* Graphics IP version 12.55 brings a slight change to the 0xd800 range,
* switching it from the GT domain to the render domain.
- *
- * *Must* be sorted by offset ranges! See intel_fw_table_check().
*/
#define XEHP_FWRANGES(FW_RANGE_D800) \
GEN_FW_RANGE(0x0, 0x1fff, 0), /* \
@@ -1490,6 +1563,103 @@ static const struct intel_forcewake_range __dg2_fw_ranges[] = {
XEHP_FWRANGES(FORCEWAKE_RENDER)
};
+static const struct intel_forcewake_range __pvc_fw_ranges[] = {
+ GEN_FW_RANGE(0x0, 0xaff, 0),
+ GEN_FW_RANGE(0xb00, 0xbff, FORCEWAKE_GT),
+ GEN_FW_RANGE(0xc00, 0xfff, 0),
+ GEN_FW_RANGE(0x1000, 0x1fff, FORCEWAKE_GT),
+ GEN_FW_RANGE(0x2000, 0x26ff, FORCEWAKE_RENDER),
+ GEN_FW_RANGE(0x2700, 0x2fff, FORCEWAKE_GT),
+ GEN_FW_RANGE(0x3000, 0x3fff, FORCEWAKE_RENDER),
+ GEN_FW_RANGE(0x4000, 0x813f, FORCEWAKE_GT), /*
+ 0x4000 - 0x4aff: gt
+ 0x4b00 - 0x4fff: reserved
+ 0x5000 - 0x51ff: gt
+ 0x5200 - 0x52ff: reserved
+ 0x5300 - 0x53ff: gt
+ 0x5400 - 0x7fff: reserved
+ 0x8000 - 0x813f: gt */
+ GEN_FW_RANGE(0x8140, 0x817f, FORCEWAKE_RENDER),
+ GEN_FW_RANGE(0x8180, 0x81ff, 0),
+ GEN_FW_RANGE(0x8200, 0x94cf, FORCEWAKE_GT), /*
+ 0x8200 - 0x82ff: gt
+ 0x8300 - 0x84ff: reserved
+ 0x8500 - 0x887f: gt
+ 0x8880 - 0x8a7f: reserved
+ 0x8a80 - 0x8aff: gt
+ 0x8b00 - 0x8fff: reserved
+ 0x9000 - 0x947f: gt
+ 0x9480 - 0x94cf: reserved */
+ GEN_FW_RANGE(0x94d0, 0x955f, FORCEWAKE_RENDER),
+ GEN_FW_RANGE(0x9560, 0x967f, 0), /*
+ 0x9560 - 0x95ff: always on
+ 0x9600 - 0x967f: reserved */
+ GEN_FW_RANGE(0x9680, 0x97ff, FORCEWAKE_RENDER), /*
+ 0x9680 - 0x96ff: render
+ 0x9700 - 0x97ff: reserved */
+ GEN_FW_RANGE(0x9800, 0xcfff, FORCEWAKE_GT), /*
+ 0x9800 - 0xb4ff: gt
+ 0xb500 - 0xbfff: reserved
+ 0xc000 - 0xcfff: gt */
+ GEN_FW_RANGE(0xd000, 0xd3ff, 0),
+ GEN_FW_RANGE(0xd400, 0xdbff, FORCEWAKE_GT),
+ GEN_FW_RANGE(0xdc00, 0xdcff, FORCEWAKE_RENDER),
+ GEN_FW_RANGE(0xdd00, 0xde7f, FORCEWAKE_GT), /*
+ 0xdd00 - 0xddff: gt
+ 0xde00 - 0xde7f: reserved */
+ GEN_FW_RANGE(0xde80, 0xe8ff, FORCEWAKE_RENDER), /*
+ 0xde80 - 0xdeff: render
+ 0xdf00 - 0xe1ff: reserved
+ 0xe200 - 0xe7ff: render
+ 0xe800 - 0xe8ff: reserved */
+ GEN_FW_RANGE(0xe900, 0x11fff, FORCEWAKE_GT), /*
+ 0xe900 - 0xe9ff: gt
+ 0xea00 - 0xebff: reserved
+ 0xec00 - 0xffff: gt
+ 0x10000 - 0x11fff: reserved */
+ GEN_FW_RANGE(0x12000, 0x12fff, 0), /*
+ 0x12000 - 0x127ff: always on
+ 0x12800 - 0x12fff: reserved */
+ GEN_FW_RANGE(0x13000, 0x23fff, FORCEWAKE_GT), /*
+ 0x13000 - 0x135ff: gt
+ 0x13600 - 0x147ff: reserved
+ 0x14800 - 0x153ff: gt
+ 0x15400 - 0x19fff: reserved
+ 0x1a000 - 0x1ffff: gt
+ 0x20000 - 0x21fff: reserved
+ 0x22000 - 0x23fff: gt */
+ GEN_FW_RANGE(0x24000, 0x2417f, 0), /*
+ 24000 - 0x2407f: always on
+ 24080 - 0x2417f: reserved */
+ GEN_FW_RANGE(0x24180, 0x3ffff, FORCEWAKE_GT), /*
+ 0x24180 - 0x241ff: gt
+ 0x24200 - 0x251ff: reserved
+ 0x25200 - 0x252ff: gt
+ 0x25300 - 0x25fff: reserved
+ 0x26000 - 0x27fff: gt
+ 0x28000 - 0x2ffff: reserved
+ 0x30000 - 0x3ffff: gt */
+ GEN_FW_RANGE(0x40000, 0x1bffff, 0),
+ GEN_FW_RANGE(0x1c0000, 0x1c3fff, FORCEWAKE_MEDIA_VDBOX0), /*
+ 0x1c0000 - 0x1c2bff: VD0
+ 0x1c2c00 - 0x1c2cff: reserved
+ 0x1c2d00 - 0x1c2dff: VD0
+ 0x1c2e00 - 0x1c3eff: reserved
+ 0x1c3f00 - 0x1c3fff: VD0 */
+ GEN_FW_RANGE(0x1c4000, 0x1cffff, FORCEWAKE_MEDIA_VDBOX1), /*
+ 0x1c4000 - 0x1c6aff: VD1
+ 0x1c6b00 - 0x1c7eff: reserved
+ 0x1c7f00 - 0x1c7fff: VD1
+ 0x1c8000 - 0x1cffff: reserved */
+ GEN_FW_RANGE(0x1d0000, 0x23ffff, FORCEWAKE_MEDIA_VDBOX2), /*
+ 0x1d0000 - 0x1d2aff: VD2
+ 0x1d2b00 - 0x1d3eff: reserved
+ 0x1d3f00 - 0x1d3fff: VD2
+ 0x1d4000 - 0x23ffff: reserved */
+ GEN_FW_RANGE(0x240000, 0x3dffff, 0),
+ GEN_FW_RANGE(0x3e0000, 0x3effff, FORCEWAKE_GT),
+};
+
static void
ilk_dummy_write(struct intel_uncore *uncore)
{
@@ -2125,7 +2295,11 @@ static int uncore_forcewake_init(struct intel_uncore *uncore)
ASSIGN_READ_MMIO_VFUNCS(uncore, fwtable);
- if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 55)) {
+ if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 60)) {
+ ASSIGN_FW_DOMAINS_TABLE(uncore, __pvc_fw_ranges);
+ ASSIGN_SHADOW_TABLE(uncore, pvc_shadowed_regs);
+ ASSIGN_WRITE_MMIO_VFUNCS(uncore, fwtable);
+ } else if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 55)) {
ASSIGN_FW_DOMAINS_TABLE(uncore, __dg2_fw_ranges);
ASSIGN_SHADOW_TABLE(uncore, dg2_shadowed_regs);
ASSIGN_WRITE_MMIO_VFUNCS(uncore, fwtable);
@@ -2470,118 +2644,6 @@ intel_uncore_forcewake_for_reg(struct intel_uncore *uncore,
return fw_domains;
}
-/**
- * uncore_rw_with_mcr_steering_fw - Access a register after programming
- * the MCR selector register.
- * @uncore: pointer to struct intel_uncore
- * @reg: register being accessed
- * @rw_flag: FW_REG_READ for read access or FW_REG_WRITE for write access
- * @slice: slice number (ignored for multi-cast write)
- * @subslice: sub-slice number (ignored for multi-cast write)
- * @value: register value to be written (ignored for read)
- *
- * Return: 0 for write access. register value for read access.
- *
- * Caller needs to make sure the relevant forcewake wells are up.
- */
-static u32 uncore_rw_with_mcr_steering_fw(struct intel_uncore *uncore,
- i915_reg_t reg, u8 rw_flag,
- int slice, int subslice, u32 value)
-{
- u32 mcr_mask, mcr_ss, mcr, old_mcr, val = 0;
-
- lockdep_assert_held(&uncore->lock);
-
- if (GRAPHICS_VER(uncore->i915) >= 11) {
- mcr_mask = GEN11_MCR_SLICE_MASK | GEN11_MCR_SUBSLICE_MASK;
- mcr_ss = GEN11_MCR_SLICE(slice) | GEN11_MCR_SUBSLICE(subslice);
-
- /*
- * Wa_22013088509
- *
- * The setting of the multicast/unicast bit usually wouldn't
- * matter for read operations (which always return the value
- * from a single register instance regardless of how that bit
- * is set), but some platforms have a workaround requiring us
- * to remain in multicast mode for reads. There's no real
- * downside to this, so we'll just go ahead and do so on all
- * platforms; we'll only clear the multicast bit from the mask
- * when exlicitly doing a write operation.
- */
- if (rw_flag == FW_REG_WRITE)
- mcr_mask |= GEN11_MCR_MULTICAST;
- } else {
- mcr_mask = GEN8_MCR_SLICE_MASK | GEN8_MCR_SUBSLICE_MASK;
- mcr_ss = GEN8_MCR_SLICE(slice) | GEN8_MCR_SUBSLICE(subslice);
- }
-
- old_mcr = mcr = intel_uncore_read_fw(uncore, GEN8_MCR_SELECTOR);
-
- mcr &= ~mcr_mask;
- mcr |= mcr_ss;
- intel_uncore_write_fw(uncore, GEN8_MCR_SELECTOR, mcr);
-
- if (rw_flag == FW_REG_READ)
- val = intel_uncore_read_fw(uncore, reg);
- else
- intel_uncore_write_fw(uncore, reg, value);
-
- mcr &= ~mcr_mask;
- mcr |= old_mcr & mcr_mask;
-
- intel_uncore_write_fw(uncore, GEN8_MCR_SELECTOR, mcr);
-
- return val;
-}
-
-static u32 uncore_rw_with_mcr_steering(struct intel_uncore *uncore,
- i915_reg_t reg, u8 rw_flag,
- int slice, int subslice,
- u32 value)
-{
- enum forcewake_domains fw_domains;
- u32 val;
-
- fw_domains = intel_uncore_forcewake_for_reg(uncore, reg,
- rw_flag);
- fw_domains |= intel_uncore_forcewake_for_reg(uncore,
- GEN8_MCR_SELECTOR,
- FW_REG_READ | FW_REG_WRITE);
-
- spin_lock_irq(&uncore->lock);
- intel_uncore_forcewake_get__locked(uncore, fw_domains);
-
- val = uncore_rw_with_mcr_steering_fw(uncore, reg, rw_flag,
- slice, subslice, value);
-
- intel_uncore_forcewake_put__locked(uncore, fw_domains);
- spin_unlock_irq(&uncore->lock);
-
- return val;
-}
-
-u32 intel_uncore_read_with_mcr_steering_fw(struct intel_uncore *uncore,
- i915_reg_t reg, int slice, int subslice)
-{
- return uncore_rw_with_mcr_steering_fw(uncore, reg, FW_REG_READ,
- slice, subslice, 0);
-}
-
-u32 intel_uncore_read_with_mcr_steering(struct intel_uncore *uncore,
- i915_reg_t reg, int slice, int subslice)
-{
- return uncore_rw_with_mcr_steering(uncore, reg, FW_REG_READ,
- slice, subslice, 0);
-}
-
-void intel_uncore_write_with_mcr_steering(struct intel_uncore *uncore,
- i915_reg_t reg, u32 value,
- int slice, int subslice)
-{
- uncore_rw_with_mcr_steering(uncore, reg, FW_REG_WRITE,
- slice, subslice, value);
-}
-
#if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
#include "selftests/mock_uncore.c"
#include "selftests/intel_uncore.c"
diff --git a/drivers/gpu/drm/i915/intel_uncore.h b/drivers/gpu/drm/i915/intel_uncore.h
index 52fe3d89dd2b8ac7b8ef6a343d52c9c3bc190b49..b1fa912a65e75db0eaad8e0206b576893adfc409 100644
--- a/drivers/gpu/drm/i915/intel_uncore.h
+++ b/drivers/gpu/drm/i915/intel_uncore.h
@@ -210,14 +210,6 @@ intel_uncore_has_fifo(const struct intel_uncore *uncore)
return uncore->flags & UNCORE_HAS_FIFO;
}
-u32 intel_uncore_read_with_mcr_steering_fw(struct intel_uncore *uncore,
- i915_reg_t reg,
- int slice, int subslice);
-u32 intel_uncore_read_with_mcr_steering(struct intel_uncore *uncore,
- i915_reg_t reg, int slice, int subslice);
-void intel_uncore_write_with_mcr_steering(struct intel_uncore *uncore,
- i915_reg_t reg, u32 value,
- int slice, int subslice);
void
intel_uncore_mmio_debug_init_early(struct intel_uncore_mmio_debug *mmio_debug);
void intel_uncore_init_early(struct intel_uncore *uncore,
diff --git a/drivers/gpu/drm/i915/selftests/intel_uncore.c b/drivers/gpu/drm/i915/selftests/intel_uncore.c
index cdd196783535af05263c437f793bafe03bff0df1..fda9bb79c049d5a97c8dbdcb7d592331b28deac0 100644
--- a/drivers/gpu/drm/i915/selftests/intel_uncore.c
+++ b/drivers/gpu/drm/i915/selftests/intel_uncore.c
@@ -69,6 +69,7 @@ static int intel_shadow_table_check(void)
{ gen11_shadowed_regs, ARRAY_SIZE(gen11_shadowed_regs) },
{ gen12_shadowed_regs, ARRAY_SIZE(gen12_shadowed_regs) },
{ dg2_shadowed_regs, ARRAY_SIZE(dg2_shadowed_regs) },
+ { pvc_shadowed_regs, ARRAY_SIZE(pvc_shadowed_regs) },
};
const struct i915_range *range;
unsigned int i, j;
@@ -115,6 +116,7 @@ int intel_uncore_mock_selftests(void)
{ __gen11_fw_ranges, ARRAY_SIZE(__gen11_fw_ranges), true },
{ __gen12_fw_ranges, ARRAY_SIZE(__gen12_fw_ranges), true },
{ __xehp_fw_ranges, ARRAY_SIZE(__xehp_fw_ranges), true },
+ { __pvc_fw_ranges, ARRAY_SIZE(__pvc_fw_ranges), true },
};
int err, i;
diff --git a/include/drm/intel-gtt.h b/include/drm/intel-gtt.h
index 67530bfef129c87a1dbd0b461ee42314cfe1df3a..cb0d5b7200c7fe51b5d28e2bb9cd003b47878f20 100644
--- a/include/drm/intel-gtt.h
+++ b/include/drm/intel-gtt.h
@@ -10,24 +10,24 @@ struct agp_bridge_data;
struct pci_dev;
struct sg_table;
-void intel_gtt_get(u64 *gtt_total,
- phys_addr_t *mappable_base,
- resource_size_t *mappable_end);
+void intel_gmch_gtt_get(u64 *gtt_total,
+ phys_addr_t *mappable_base,
+ resource_size_t *mappable_end);
int intel_gmch_probe(struct pci_dev *bridge_pdev, struct pci_dev *gpu_pdev,
struct agp_bridge_data *bridge);
void intel_gmch_remove(void);
-bool intel_enable_gtt(void);
+bool intel_gmch_enable_gtt(void);
-void intel_gtt_chipset_flush(void);
-void intel_gtt_insert_page(dma_addr_t addr,
- unsigned int pg,
- unsigned int flags);
-void intel_gtt_insert_sg_entries(struct sg_table *st,
- unsigned int pg_start,
- unsigned int flags);
-void intel_gtt_clear_range(unsigned int first_entry, unsigned int num_entries);
+void intel_gmch_gtt_flush(void);
+void intel_gmch_gtt_insert_page(dma_addr_t addr,
+ unsigned int pg,
+ unsigned int flags);
+void intel_gmch_gtt_insert_sg_entries(struct sg_table *st,
+ unsigned int pg_start,
+ unsigned int flags);
+void intel_gmch_gtt_clear_range(unsigned int first_entry, unsigned int num_entries);
/* Special gtt memory types */
#define AGP_DCACHE_MEMORY 1
diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h
index a2def7b270097836327d738e9eb3240fdf248ab4..de49b68b4fc87d47ae5f05a6d72c19c0ac56ac48 100644
--- a/include/uapi/drm/i915_drm.h
+++ b/include/uapi/drm/i915_drm.h
@@ -3443,6 +3443,22 @@ struct drm_i915_gem_create_ext {
* At which point we get the object handle in &drm_i915_gem_create_ext.handle,
* along with the final object size in &drm_i915_gem_create_ext.size, which
* should account for any rounding up, if required.
+ *
+ * Note that userspace has no means of knowing the current backing region
+ * for objects where @num_regions is larger than one. The kernel will only
+ * ensure that the priority order of the @regions array is honoured, either
+ * when initially placing the object, or when moving memory around due to
+ * memory pressure
+ *
+ * On Flat-CCS capable HW, compression is supported for the objects residing
+ * in I915_MEMORY_CLASS_DEVICE. When such objects (compressed) have other
+ * memory class in @regions and migrated (by i915, due to memory
+ * constraints) to the non I915_MEMORY_CLASS_DEVICE region, then i915 needs to
+ * decompress the content. But i915 doesn't have the required information to
+ * decompress the userspace compressed objects.
+ *
+ * So i915 supports Flat-CCS, on the objects which can reside only on
+ * I915_MEMORY_CLASS_DEVICE regions.
*/
struct drm_i915_gem_create_ext_memory_regions {
/** @base: Extension link. See struct i915_user_extension. */