Pull in TTM changes needed for DG2 CCS enabling from Ram.
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
--- /dev/null
+.. _drm-client-usage-stats:
+
+======================
+DRM client usage stats
+======================
+
+DRM drivers can choose to export partly standardised text output via the
+`fops->show_fdinfo()` as part of the driver specific file operations registered
+in the `struct drm_driver` object registered with the DRM core.
+
+One purpose of this output is to enable writing as generic as practicaly
+feasible `top(1)` like userspace monitoring tools.
+
+Given the differences between various DRM drivers the specification of the
+output is split between common and driver specific parts. Having said that,
+wherever possible effort should still be made to standardise as much as
+possible.
+
+File format specification
+=========================
+
+- File shall contain one key value pair per one line of text.
+- Colon character (`:`) must be used to delimit keys and values.
+- All keys shall be prefixed with `drm-`.
+- Whitespace between the delimiter and first non-whitespace character shall be
+ ignored when parsing.
+- Neither keys or values are allowed to contain whitespace characters.
+- Numerical key value pairs can end with optional unit string.
+- Data type of the value is fixed as defined in the specification.
+
+Key types
+---------
+
+1. Mandatory, fully standardised.
+2. Optional, fully standardised.
+3. Driver specific.
+
+Data types
+----------
+
+- <uint> - Unsigned integer without defining the maximum value.
+- <str> - String excluding any above defined reserved characters or whitespace.
+
+Mandatory fully standardised keys
+---------------------------------
+
+- drm-driver: <str>
+
+String shall contain the name this driver registered as via the respective
+`struct drm_driver` data structure.
+
+Optional fully standardised keys
+--------------------------------
+
+- drm-pdev: <aaaa:bb.cc.d>
+
+For PCI devices this should contain the PCI slot address of the device in
+question.
+
+- drm-client-id: <uint>
+
+Unique value relating to the open DRM file descriptor used to distinguish
+duplicated and shared file descriptors. Conceptually the value should map 1:1
+to the in kernel representation of `struct drm_file` instances.
+
+Uniqueness of the value shall be either globally unique, or unique within the
+scope of each device, in which case `drm-pdev` shall be present as well.
+
+Userspace should make sure to not double account any usage statistics by using
+the above described criteria in order to associate data to individual clients.
+
+- drm-engine-<str>: <uint> ns
+
+GPUs usually contain multiple execution engines. Each shall be given a stable
+and unique name (str), with possible values documented in the driver specific
+documentation.
+
+Value shall be in specified time units which the respective GPU engine spent
+busy executing workloads belonging to this client.
+
+Values are not required to be constantly monotonic if it makes the driver
+implementation easier, but are required to catch up with the previously reported
+larger value within a reasonable period. Upon observing a value lower than what
+was previously read, userspace is expected to stay with that larger previous
+value until a monotonic update is seen.
+
+- drm-engine-capacity-<str>: <uint>
+
+Engine identifier string must be the same as the one specified in the
+drm-engine-<str> tag and shall contain a greater than zero number in case the
+exported engine corresponds to a group of identical hardware engines.
+
+In the absence of this tag parser shall assume capacity of one. Zero capacity
+is not allowed.
+
+- drm-memory-<str>: <uint> [KiB|MiB]
+
+Each possible memory type which can be used to store buffer objects by the
+GPU in question shall be given a stable and unique name to be returned as the
+string here.
+
+Value shall reflect the amount of storage currently consumed by the buffer
+object belong to this client, in the respective memory region.
+
+Default unit shall be bytes with optional unit specifiers of 'KiB' or 'MiB'
+indicating kibi- or mebi-bytes.
+
+===============================
+Driver specific implementations
+===============================
+
+:ref:`i915-usage-stats`
.. kernel-doc:: drivers/gpu/drm/i915/i915_reg.h
:doc: The i915 register macro definition style guide
+
+.. _i915-usage-stats:
+
+i915 DRM client usage stats implementation
+==========================================
+
+The drm/i915 driver implements the DRM client usage stats specification as
+documented in :ref:`drm-client-usage-stats`.
+
+Example of the output showing the implemented key value pairs and entirety of
+the currently possible format options:
+
+::
+
+ pos: 0
+ flags: 0100002
+ mnt_id: 21
+ drm-driver: i915
+ drm-pdev: 0000:00:02.0
+ drm-client-id: 7
+ drm-engine-render: 9288864723 ns
+ drm-engine-copy: 2035071108 ns
+ drm-engine-video: 0 ns
+ drm-engine-capacity-video: 2
+ drm-engine-video-enhance: 0 ns
+
+Possible `drm-engine-` key names are: `render`, `copy`, `video` and
+`video-enhance`.
drm-kms
drm-kms-helpers
drm-uapi
+ drm-usage-stats
driver-uapi
drm-client
drivers
depends on DRM
depends on X86 && PCI
depends on !PREEMPT_RT
- select INTEL_GTT
+ select INTEL_GTT if X86
select INTERVAL_TREE
# we need shmfs for the swappable backing store, and in particular
# the shmem_readpage() which depends upon tmpfs
# core driver code
i915-y += i915_driver.o \
+ i915_drm_client.o \
i915_config.o \
i915_getparam.o \
i915_ioctl.o \
gt/intel_gt_pm_debugfs.o \
gt/intel_gt_pm_irq.o \
gt/intel_gt_requests.o \
+ gt/intel_gt_sysfs.o \
+ gt/intel_gt_sysfs_pm.o \
gt/intel_gtt.o \
gt/intel_llc.o \
gt/intel_lrc.o \
gt/intel_workarounds.o \
gt/shmem_utils.o \
gt/sysfs_engines.o
+# x86 intel-gtt module support
+gt-$(CONFIG_X86) += gt/intel_gt_gmch.o
# autogenerated null render state
gt-y += \
gt/gen6_renderstate.o \
gt/uc/intel_uc_fw.o \
gt/uc/intel_guc.o \
gt/uc/intel_guc_ads.o \
+ gt/uc/intel_guc_capture.o \
gt/uc/intel_guc_ct.o \
gt/uc/intel_guc_debugfs.o \
gt/uc/intel_guc_fw.o \
+ gt/uc/intel_guc_hwconfig.o \
gt/uc/intel_guc_log.o \
gt/uc/intel_guc_log_debugfs.o \
gt/uc/intel_guc_rc.o \
{
struct i915_dpt *dpt = i915_vm_to_dpt(vm);
- i915_vm_close(&dpt->vm);
+ i915_vm_put(&dpt->vm);
}
/* object is backed with LMEM for discrete */
i915 = to_i915(obj->base.dev);
- if (HAS_LMEM(i915) && !i915_gem_object_can_migrate(obj, INTEL_REGION_LMEM)) {
+ if (HAS_LMEM(i915) && !i915_gem_object_can_migrate(obj, INTEL_REGION_LMEM_0)) {
/* object is "remote", not in local memory */
i915_gem_object_put(obj);
return ERR_PTR(-EREMOTE);
if (!ret && phys_cursor)
ret = i915_gem_object_attach_phys(obj, alignment);
else if (!ret && HAS_LMEM(dev_priv))
- ret = i915_gem_object_migrate(obj, &ww, INTEL_REGION_LMEM);
+ ret = i915_gem_object_migrate(obj, &ww, INTEL_REGION_LMEM_0);
/* TODO: Do we need to sync when migration becomes async? */
if (!ret)
ret = i915_gem_object_pin_pages(obj);
/* Our framebuffer is the entirety of fbdev's system memory */
info->fix.smem_start =
(unsigned long)(ggtt->gmadr.start + vma->node.start);
- info->fix.smem_len = vma->node.size;
+ info->fix.smem_len = vma->size;
}
vaddr = i915_vma_pin_iomap(vma);
goto out_unpin;
}
info->screen_base = vaddr;
- info->screen_size = vma->node.size;
+ info->screen_size = vma->size;
drm_fb_helper_fill_info(info, &ifbdev->helper, sizes);
* Copyright © 2021 Intel Corporation
*/
+#include "gem/i915_gem_region.h"
#include "i915_drv.h"
#include "intel_atomic_plane.h"
#include "intel_display.h"
initial_plane_vma(struct drm_i915_private *i915,
struct intel_initial_plane_config *plane_config)
{
- struct intel_memory_region *mem = i915->mm.stolen_region;
+ struct intel_memory_region *mem;
struct drm_i915_gem_object *obj;
struct i915_vma *vma;
+ resource_size_t phys_base;
u32 base, size;
+ u64 pinctl;
- if (!mem || plane_config->size == 0)
+ if (plane_config->size == 0)
+ return NULL;
+
+ base = round_down(plane_config->base, I915_GTT_MIN_ALIGNMENT);
+ if (IS_DGFX(i915)) {
+ gen8_pte_t __iomem *gte = to_gt(i915)->ggtt->gsm;
+ gen8_pte_t pte;
+
+ gte += base / I915_GTT_PAGE_SIZE;
+
+ pte = ioread64(gte);
+ if (!(pte & GEN12_GGTT_PTE_LM)) {
+ drm_err(&i915->drm,
+ "Initial plane programming missing PTE_LM bit\n");
+ return NULL;
+ }
+
+ phys_base = pte & I915_GTT_PAGE_MASK;
+ mem = i915->mm.regions[INTEL_REGION_LMEM_0];
+
+ /*
+ * We don't currently expect this to ever be placed in the
+ * stolen portion.
+ */
+ if (phys_base >= resource_size(&mem->region)) {
+ drm_err(&i915->drm,
+ "Initial plane programming using invalid range, phys_base=%pa\n",
+ &phys_base);
+ return NULL;
+ }
+
+ drm_dbg(&i915->drm,
+ "Using phys_base=%pa, based on initial plane programming\n",
+ &phys_base);
+ } else {
+ phys_base = base;
+ mem = i915->mm.stolen_region;
+ }
+
+ if (!mem)
return NULL;
- base = round_down(plane_config->base,
- I915_GTT_MIN_ALIGNMENT);
size = round_up(plane_config->base + plane_config->size,
mem->min_page_size);
size -= base;
* features.
*/
if (IS_ENABLED(CONFIG_FRAMEBUFFER_CONSOLE) &&
+ mem == i915->mm.stolen_region &&
size * 2 > i915->stolen_usable_size)
return NULL;
- obj = i915_gem_object_create_stolen_for_preallocated(i915, base, size);
+ obj = i915_gem_object_create_region_at(mem, phys_base, size, 0);
if (IS_ERR(obj))
return NULL;
if (IS_ERR(vma))
goto err_obj;
- if (i915_ggtt_pin(vma, NULL, 0, PIN_MAPPABLE | PIN_OFFSET_FIXED | base))
+ pinctl = PIN_GLOBAL | PIN_OFFSET_FIXED | base;
+ if (HAS_GMCH(i915))
+ pinctl |= PIN_MAPPABLE;
+ if (i915_vma_pin(vma, 0, 0, pinctl))
goto err_obj;
if (i915_gem_object_is_tiled(obj) &&
free_engines(engines);
}
+static void accumulate_runtime(struct i915_drm_client *client,
+ struct i915_gem_engines *engines)
+{
+ struct i915_gem_engines_iter it;
+ struct intel_context *ce;
+
+ if (!client)
+ return;
+
+ /* Transfer accumulated runtime to the parent GEM context. */
+ for_each_gem_engine(ce, engines, it) {
+ unsigned int class = ce->engine->uabi_class;
+
+ GEM_BUG_ON(class >= ARRAY_SIZE(client->past_runtime));
+ atomic64_add(intel_context_get_total_runtime_ns(ce),
+ &client->past_runtime[class]);
+ }
+}
+
static int
engines_notify(struct i915_sw_fence *fence, enum i915_sw_fence_notify state)
{
struct i915_gem_engines *engines =
container_of(fence, typeof(*engines), fence);
+ struct i915_gem_context *ctx = engines->ctx;
switch (state) {
case FENCE_COMPLETE:
if (!list_empty(&engines->link)) {
- struct i915_gem_context *ctx = engines->ctx;
unsigned long flags;
spin_lock_irqsave(&ctx->stale.lock, flags);
list_del(&engines->link);
spin_unlock_irqrestore(&ctx->stale.lock, flags);
}
- i915_gem_context_put(engines->ctx);
+ accumulate_runtime(ctx->client, engines);
+ i915_gem_context_put(ctx);
+
break;
case FENCE_FREE:
if (ctx->pxp_wakeref)
intel_runtime_pm_put(&ctx->i915->runtime_pm, ctx->pxp_wakeref);
+ if (ctx->client)
+ i915_drm_client_put(ctx->client);
+
mutex_destroy(&ctx->engines_mutex);
mutex_destroy(&ctx->lut_mutex);
static void context_close(struct i915_gem_context *ctx)
{
- struct i915_address_space *vm;
+ struct i915_drm_client *client;
/* Flush any concurrent set_engines() */
mutex_lock(&ctx->engines_mutex);
set_closed_name(ctx);
- vm = ctx->vm;
- if (vm) {
- /* i915_vm_close drops the final reference, which is a bit too
- * early and could result in surprises with concurrent
- * operations racing with thist ctx close. Keep a full reference
- * until the end.
- */
- i915_vm_get(vm);
- i915_vm_close(vm);
- }
-
- ctx->file_priv = ERR_PTR(-EBADF);
-
/*
* The LUT uses the VMA as a backpointer to unref the object,
* so we need to clear the LUT before we close all the VMA (inside
*/
lut_close(ctx);
+ ctx->file_priv = ERR_PTR(-EBADF);
+
spin_lock(&ctx->i915->gem.contexts.lock);
list_del(&ctx->link);
spin_unlock(&ctx->i915->gem.contexts.lock);
+ client = ctx->client;
+ if (client) {
+ spin_lock(&client->ctx_lock);
+ list_del_rcu(&ctx->client_link);
+ spin_unlock(&client->ctx_lock);
+ }
+
mutex_unlock(&ctx->mutex);
/*
}
vm = &ppgtt->vm;
}
- if (vm) {
- ctx->vm = i915_vm_open(vm);
-
- /* i915_vm_open() takes a reference */
- i915_vm_put(vm);
- }
+ if (vm)
+ ctx->vm = vm;
mutex_init(&ctx->engines_mutex);
if (pc->num_user_engines >= 0) {
free_engines(e);
err_vm:
if (ctx->vm)
- i915_vm_close(ctx->vm);
+ i915_vm_put(ctx->vm);
err_ctx:
kfree(ctx);
return ERR_PTR(err);
ctx->file_priv = fpriv;
ctx->pid = get_task_pid(current, PIDTYPE_PID);
+ ctx->client = i915_drm_client_get(fpriv->client);
+
snprintf(ctx->name, sizeof(ctx->name), "%s[%d]",
current->comm, pid_nr(ctx->pid));
old = xa_store(&fpriv->context_xa, id, ctx, GFP_KERNEL);
WARN_ON(old);
+ spin_lock(&ctx->client->ctx_lock);
+ list_add_tail_rcu(&ctx->client_link, &ctx->client->ctx_list);
+ spin_unlock(&ctx->client->ctx_lock);
+
spin_lock(&i915->gem.contexts.lock);
list_add_tail(&ctx->link, &i915->gem.contexts.list);
spin_unlock(&i915->gem.contexts.lock);
if (err)
return err;
- i915_vm_open(vm);
+ i915_vm_get(vm);
GEM_BUG_ON(id == 0); /* reserved for invalid/unassigned ppgtt */
args->value = id;
/** @link: place with &drm_i915_private.context_list */
struct list_head link;
+ /** @client: struct i915_drm_client */
+ struct i915_drm_client *client;
+
+ /** @client_link: for linking onto &i915_drm_client.ctx_list */
+ struct list_head client_link;
+
/**
* @ref: reference count
*
*/
flags = I915_BO_ALLOC_USER;
- ret = mr->ops->init_object(mr, obj, size, 0, flags);
+ ret = mr->ops->init_object(mr, obj, I915_BO_INVALID_OFFSET, size, 0, flags);
if (ret)
goto object_free;
return ERR_PTR(ret);
}
-static void i915_gem_unmap_dma_buf(struct dma_buf_attachment *attachment,
- struct sg_table *sg,
- enum dma_data_direction dir)
-{
- dma_unmap_sgtable(attachment->dev, sg, dir, DMA_ATTR_SKIP_CPU_SYNC);
- sg_free_table(sg);
- kfree(sg);
-}
-
static int i915_gem_dmabuf_vmap(struct dma_buf *dma_buf,
struct iosys_map *map)
{
static int i915_gem_dmabuf_mmap(struct dma_buf *dma_buf, struct vm_area_struct *vma)
{
struct drm_i915_gem_object *obj = dma_buf_to_obj(dma_buf);
+ struct drm_i915_private *i915 = to_i915(obj->base.dev);
int ret;
if (obj->base.size < vma->vm_end - vma->vm_start)
return -EINVAL;
+ if (HAS_LMEM(i915))
+ return drm_gem_prime_mmap(&obj->base, vma);
+
if (!obj->base.filp)
return -ENODEV;
.attach = i915_gem_dmabuf_attach,
.detach = i915_gem_dmabuf_detach,
.map_dma_buf = i915_gem_map_dma_buf,
- .unmap_dma_buf = i915_gem_unmap_dma_buf,
+ .unmap_dma_buf = drm_gem_unmap_dma_buf,
.release = drm_gem_dmabuf_release,
.mmap = i915_gem_dmabuf_mmap,
.vmap = i915_gem_dmabuf_vmap,
static void clflush_write32(u32 *addr, u32 value, unsigned int flushes)
{
if (unlikely(flushes & (CLFLUSH_BEFORE | CLFLUSH_AFTER))) {
- if (flushes & CLFLUSH_BEFORE) {
- clflushopt(addr);
- mb();
- }
+ if (flushes & CLFLUSH_BEFORE)
+ drm_clflush_virt_range(addr, sizeof(*addr));
*addr = value;
* to ensure ordering of clflush wrt to the system.
*/
if (flushes & CLFLUSH_AFTER)
- clflushopt(addr);
+ drm_clflush_virt_range(addr, sizeof(*addr));
} else
*addr = value;
}
if (err)
goto err;
+ if (!i915_vm_tryget(ce->vm)) {
+ err = -ENOENT;
+ goto err;
+ }
+
eb->context = ce;
eb->gt = ce->engine->gt;
{
struct intel_context *child;
+ i915_vm_put(eb->context->vm);
intel_gt_pm_put(eb->gt);
for_each_child(eb->context, child)
intel_context_put(child);
resource_size_t page_size,
unsigned int flags)
{
- return i915_gem_object_create_region(i915->mm.regions[INTEL_REGION_LMEM],
+ return i915_gem_object_create_region(i915->mm.regions[INTEL_REGION_LMEM_0],
size, page_size, flags);
}
resource_size_t size,
unsigned int flags)
{
- return i915_gem_object_create_region(i915->mm.regions[INTEL_REGION_LMEM],
+ return i915_gem_object_create_region(i915->mm.regions[INTEL_REGION_LMEM_0],
size, 0, flags);
}
* mmap ioctl is disallowed for all discrete platforms,
* and for all platforms with GRAPHICS_VER > 12.
*/
- if (IS_DGFX(i915) || GRAPHICS_VER(i915) > 12)
+ if (IS_DGFX(i915) || GRAPHICS_VER_FULL(i915) > IP_VER(12, 0))
return -EOPNOTSUPP;
if (args->flags & ~(I915_MMAP_WC))
struct drm_mm_node *stolen;
+ resource_size_t bo_offset;
+
unsigned long scratch;
u64 encode;
mutex_unlock(&mem->objects.lock);
}
-struct drm_i915_gem_object *
-i915_gem_object_create_region(struct intel_memory_region *mem,
- resource_size_t size,
- resource_size_t page_size,
- unsigned int flags)
+static struct drm_i915_gem_object *
+__i915_gem_object_create_region(struct intel_memory_region *mem,
+ resource_size_t offset,
+ resource_size_t size,
+ resource_size_t page_size,
+ unsigned int flags)
{
struct drm_i915_gem_object *obj;
resource_size_t default_page_size;
size = round_up(size, default_page_size);
+ if (default_page_size == size)
+ flags |= I915_BO_ALLOC_CONTIGUOUS;
+
GEM_BUG_ON(!size);
GEM_BUG_ON(!IS_ALIGNED(size, I915_GTT_MIN_ALIGNMENT));
if (default_page_size < mem->min_page_size)
flags |= I915_BO_ALLOC_PM_EARLY;
- err = mem->ops->init_object(mem, obj, size, page_size, flags);
+ err = mem->ops->init_object(mem, obj, offset, size, page_size, flags);
if (err)
goto err_object_free;
return ERR_PTR(err);
}
+struct drm_i915_gem_object *
+i915_gem_object_create_region(struct intel_memory_region *mem,
+ resource_size_t size,
+ resource_size_t page_size,
+ unsigned int flags)
+{
+ return __i915_gem_object_create_region(mem, I915_BO_INVALID_OFFSET,
+ size, page_size, flags);
+}
+
+struct drm_i915_gem_object *
+i915_gem_object_create_region_at(struct intel_memory_region *mem,
+ resource_size_t offset,
+ resource_size_t size,
+ unsigned int flags)
+{
+ GEM_BUG_ON(offset == I915_BO_INVALID_OFFSET);
+
+ if (GEM_WARN_ON(!IS_ALIGNED(size, mem->min_page_size)) ||
+ GEM_WARN_ON(!IS_ALIGNED(offset, mem->min_page_size)))
+ return ERR_PTR(-EINVAL);
+
+ if (range_overflows(offset, size, resource_size(&mem->region)))
+ return ERR_PTR(-EINVAL);
+
+ if (!(flags & I915_BO_ALLOC_GPU_ONLY) &&
+ offset + size > mem->io_size &&
+ !i915_ggtt_has_aperture(to_gt(mem->i915)->ggtt))
+ return ERR_PTR(-ENOSPC);
+
+ return __i915_gem_object_create_region(mem, offset, size, 0,
+ flags | I915_BO_ALLOC_CONTIGUOUS);
+}
+
/**
* i915_gem_process_region - Iterate over all objects of a region using ops
* to process and optionally skip objects
struct i915_gem_apply_to_region;
+#define I915_BO_INVALID_OFFSET ((resource_size_t)-1)
+
/**
* struct i915_gem_apply_to_region_ops - ops to use when iterating over all
* region objects.
resource_size_t size,
resource_size_t page_size,
unsigned int flags);
+struct drm_i915_gem_object *
+i915_gem_object_create_region_at(struct intel_memory_region *mem,
+ resource_size_t offset,
+ resource_size_t size,
+ unsigned int flags);
int i915_gem_process_region(struct intel_memory_region *mr,
struct i915_gem_apply_to_region *apply);
static int shmem_object_init(struct intel_memory_region *mem,
struct drm_i915_gem_object *obj,
+ resource_size_t offset,
resource_size_t size,
resource_size_t page_size,
unsigned int flags)
#include "gem/i915_gem_lmem.h"
#include "gem/i915_gem_region.h"
+#include "gt/intel_gt.h"
+#include "gt/intel_region_lmem.h"
#include "i915_drv.h"
#include "i915_gem_stolen.h"
#include "i915_reg.h"
/* Exclude the reserved region from driver use */
mem->region.end = reserved_base - 1;
- mem->io_size = resource_size(&mem->region);
+ mem->io_size = min(mem->io_size, resource_size(&mem->region));
/* It is possible for the reserved area to end before the end of stolen
* memory, so just consider the start. */
static int _i915_gem_object_stolen_init(struct intel_memory_region *mem,
struct drm_i915_gem_object *obj,
+ resource_size_t offset,
resource_size_t size,
resource_size_t page_size,
unsigned int flags)
if (size == 0)
return -EINVAL;
+ /*
+ * With discrete devices, where we lack a mappable aperture there is no
+ * possible way to ever access this memory on the CPU side.
+ */
+ if (mem->type == INTEL_MEMORY_STOLEN_LOCAL && !mem->io_size &&
+ !(flags & I915_BO_ALLOC_GPU_ONLY))
+ return -ENOSPC;
+
stolen = kzalloc(sizeof(*stolen), GFP_KERNEL);
if (!stolen)
return -ENOMEM;
- ret = i915_gem_stolen_insert_node(i915, stolen, size,
- mem->min_page_size);
+ if (offset != I915_BO_INVALID_OFFSET) {
+ drm_dbg(&i915->drm,
+ "creating preallocated stolen object: stolen_offset=%pa, size=%pa\n",
+ &offset, &size);
+
+ stolen->start = offset;
+ stolen->size = size;
+ mutex_lock(&i915->mm.stolen_lock);
+ ret = drm_mm_reserve_node(&i915->mm.stolen, stolen);
+ mutex_unlock(&i915->mm.stolen_lock);
+ } else {
+ ret = i915_gem_stolen_insert_node(i915, stolen, size,
+ mem->min_page_size);
+ }
if (ret)
goto err_free;
if (GEM_WARN_ON(resource_size(&mem->region) == 0))
return -ENODEV;
- if (!io_mapping_init_wc(&mem->iomap,
- mem->io_start,
- mem->io_size))
- return -EIO;
-
/*
* TODO: For stolen lmem we mostly just care about populating the dsm
* related bits and setting up the drm_mm allocator for the range.
*/
err = i915_gem_init_stolen(mem);
if (err)
- goto err_fini;
+ return err;
+
+ if (mem->io_size && !io_mapping_init_wc(&mem->iomap,
+ mem->io_start,
+ mem->io_size)) {
+ err = -EIO;
+ goto err_cleanup;
+ }
return 0;
-err_fini:
- io_mapping_fini(&mem->iomap);
+err_cleanup:
+ i915_gem_cleanup_stolen(mem->i915);
return err;
}
static int release_stolen_lmem(struct intel_memory_region *mem)
{
- io_mapping_fini(&mem->iomap);
+ if (mem->io_size)
+ io_mapping_fini(&mem->iomap);
i915_gem_cleanup_stolen(mem->i915);
return 0;
}
{
struct intel_uncore *uncore = &i915->uncore;
struct pci_dev *pdev = to_pci_dev(i915->drm.dev);
+ resource_size_t dsm_size, dsm_base, lmem_size;
struct intel_memory_region *mem;
+ resource_size_t io_start, io_size;
resource_size_t min_page_size;
- resource_size_t io_start;
- resource_size_t lmem_size;
- u64 lmem_base;
- lmem_base = intel_uncore_read64(uncore, GEN12_DSMBASE);
- if (GEM_WARN_ON(lmem_base >= pci_resource_len(pdev, 2)))
+ if (WARN_ON_ONCE(instance))
return ERR_PTR(-ENODEV);
- lmem_size = pci_resource_len(pdev, 2) - lmem_base;
- io_start = pci_resource_start(pdev, 2) + lmem_base;
+ /* Use DSM base address instead for stolen memory */
+ dsm_base = intel_uncore_read64(uncore, GEN12_DSMBASE);
+ if (IS_DG1(uncore->i915)) {
+ lmem_size = pci_resource_len(pdev, 2);
+ if (WARN_ON(lmem_size < dsm_base))
+ return ERR_PTR(-ENODEV);
+ } 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_size *= SZ_1G;
+ }
+
+ dsm_size = lmem_size - dsm_base;
+ if (pci_resource_len(pdev, 2) < lmem_size) {
+ io_start = 0;
+ io_size = 0;
+ } else {
+ io_start = pci_resource_start(pdev, 2) + dsm_base;
+ io_size = dsm_size;
+ }
min_page_size = HAS_64K_PAGES(i915) ? I915_GTT_PAGE_SIZE_64K :
I915_GTT_PAGE_SIZE_4K;
- mem = intel_memory_region_create(i915, lmem_base, lmem_size,
+ mem = intel_memory_region_create(i915, dsm_base, dsm_size,
min_page_size,
- io_start, lmem_size,
+ io_start, io_size,
type, instance,
&i915_region_stolen_lmem_ops);
if (IS_ERR(mem))
drm_dbg(&i915->drm, "Stolen Local memory IO start: %pa\n",
&mem->io_start);
+ drm_dbg(&i915->drm, "Stolen Local DSM base: %pa\n", &dsm_base);
intel_memory_region_set_name(mem, "stolen-local");
return mem;
}
-struct drm_i915_gem_object *
-i915_gem_object_create_stolen_for_preallocated(struct drm_i915_private *i915,
- resource_size_t stolen_offset,
- resource_size_t size)
-{
- struct intel_memory_region *mem = i915->mm.stolen_region;
- struct drm_i915_gem_object *obj;
- struct drm_mm_node *stolen;
- int ret;
-
- if (!drm_mm_initialized(&i915->mm.stolen))
- return ERR_PTR(-ENODEV);
-
- drm_dbg(&i915->drm,
- "creating preallocated stolen object: stolen_offset=%pa, size=%pa\n",
- &stolen_offset, &size);
-
- /* KISS and expect everything to be page-aligned */
- if (GEM_WARN_ON(size == 0) ||
- GEM_WARN_ON(!IS_ALIGNED(size, mem->min_page_size)) ||
- GEM_WARN_ON(!IS_ALIGNED(stolen_offset, mem->min_page_size)))
- return ERR_PTR(-EINVAL);
-
- stolen = kzalloc(sizeof(*stolen), GFP_KERNEL);
- if (!stolen)
- return ERR_PTR(-ENOMEM);
-
- stolen->start = stolen_offset;
- stolen->size = size;
- mutex_lock(&i915->mm.stolen_lock);
- ret = drm_mm_reserve_node(&i915->mm.stolen, stolen);
- mutex_unlock(&i915->mm.stolen_lock);
- if (ret)
- goto err_free;
-
- obj = i915_gem_object_alloc();
- if (!obj) {
- ret = -ENOMEM;
- goto err_stolen;
- }
-
- ret = __i915_gem_object_create_stolen(mem, obj, stolen);
- if (ret)
- goto err_object_free;
-
- i915_gem_object_set_cache_coherency(obj, I915_CACHE_NONE);
- return obj;
-
-err_object_free:
- i915_gem_object_free(obj);
-err_stolen:
- i915_gem_stolen_remove_node(i915, stolen);
-err_free:
- kfree(stolen);
- return ERR_PTR(ret);
-}
-
bool i915_gem_object_is_stolen(const struct drm_i915_gem_object *obj)
{
return obj->ops == &i915_gem_object_stolen_ops;
struct drm_i915_gem_object *
i915_gem_object_create_stolen(struct drm_i915_private *dev_priv,
resource_size_t size);
-struct drm_i915_gem_object *
-i915_gem_object_create_stolen_for_preallocated(struct drm_i915_private *dev_priv,
- resource_size_t stolen_offset,
- resource_size_t size);
bool i915_gem_object_is_stolen(const struct drm_i915_gem_object *obj);
static void
i915_ttm_place_from_region(const struct intel_memory_region *mr,
struct ttm_place *place,
+ resource_size_t offset,
+ resource_size_t size,
unsigned int flags)
{
memset(place, 0, sizeof(*place));
place->mem_type = intel_region_to_ttm_type(mr);
+ if (mr->type == INTEL_MEMORY_SYSTEM)
+ return;
+
if (flags & I915_BO_ALLOC_CONTIGUOUS)
place->flags |= TTM_PL_FLAG_CONTIGUOUS;
- if (mr->io_size && mr->io_size < mr->total) {
+ if (offset != I915_BO_INVALID_OFFSET) {
+ place->fpfn = offset >> PAGE_SHIFT;
+ place->lpfn = place->fpfn + (size >> PAGE_SHIFT);
+ } else if (mr->io_size && mr->io_size < mr->total) {
if (flags & I915_BO_ALLOC_GPU_ONLY) {
place->flags |= TTM_PL_FLAG_TOPDOWN;
} else {
placement->num_placement = 1;
i915_ttm_place_from_region(num_allowed ? obj->mm.placements[0] :
- obj->mm.region, requested, flags);
+ obj->mm.region, requested, obj->bo_offset,
+ obj->base.size, flags);
/* Cache this on object? */
placement->num_busy_placement = num_allowed;
for (i = 0; i < placement->num_busy_placement; ++i)
- i915_ttm_place_from_region(obj->mm.placements[i], busy + i, flags);
+ i915_ttm_place_from_region(obj->mm.placements[i], busy + i,
+ obj->bo_offset, obj->base.size, flags);
if (num_allowed == 0) {
*busy = *requested;
struct ttm_placement placement;
int ret;
- i915_ttm_place_from_region(mr, &requested, flags);
+ i915_ttm_place_from_region(mr, &requested, obj->bo_offset,
+ obj->base.size, flags);
placement.num_placement = 1;
placement.num_busy_placement = 1;
placement.placement = &requested;
*/
int __i915_gem_ttm_object_init(struct intel_memory_region *mem,
struct drm_i915_gem_object *obj,
+ resource_size_t offset,
resource_size_t size,
resource_size_t page_size,
unsigned int flags)
drm_gem_private_object_init(&i915->drm, &obj->base, size);
i915_gem_object_init(obj, &i915_gem_ttm_obj_ops, &lock_class, flags);
+ obj->bo_offset = offset;
+
/* Don't put on a region list until we're either locked or fully initialized. */
obj->mm.region = mem;
INIT_LIST_HEAD(&obj->mm.region_link);
int __i915_gem_ttm_object_init(struct intel_memory_region *mem,
struct drm_i915_gem_object *obj,
+ resource_size_t offset,
resource_size_t size,
resource_size_t page_size,
unsigned int flags);
static int igt_dmabuf_import_same_driver_lmem(void *arg)
{
struct drm_i915_private *i915 = arg;
- struct intel_memory_region *lmem = i915->mm.regions[INTEL_REGION_LMEM];
+ struct intel_memory_region *lmem = i915->mm.regions[INTEL_REGION_LMEM_0];
struct drm_i915_gem_object *obj;
struct drm_gem_object *import;
struct dma_buf *dmabuf;
struct drm_i915_private *i915 = arg;
struct intel_memory_region *regions[2];
- if (!i915->mm.regions[INTEL_REGION_LMEM])
+ if (!i915->mm.regions[INTEL_REGION_LMEM_0])
return 0;
- regions[0] = i915->mm.regions[INTEL_REGION_LMEM];
+ regions[0] = i915->mm.regions[INTEL_REGION_LMEM_0];
regions[1] = i915->mm.regions[INTEL_REGION_SMEM];
return igt_dmabuf_import_same_driver(i915, regions, 2);
}
static int igt_smem_create_migrate(void *arg)
{
- return igt_create_migrate(arg, INTEL_REGION_LMEM, INTEL_REGION_SMEM);
+ return igt_create_migrate(arg, INTEL_REGION_LMEM_0, INTEL_REGION_SMEM);
}
static int igt_lmem_create_migrate(void *arg)
{
- return igt_create_migrate(arg, INTEL_REGION_SMEM, INTEL_REGION_LMEM);
+ return igt_create_migrate(arg, INTEL_REGION_SMEM, INTEL_REGION_LMEM_0);
}
static int igt_same_create_migrate(void *arg)
{
- return igt_create_migrate(arg, INTEL_REGION_LMEM, INTEL_REGION_LMEM);
+ return igt_create_migrate(arg, INTEL_REGION_LMEM_0, INTEL_REGION_LMEM_0);
}
static int lmem_pages_migrate_one(struct i915_gem_ww_ctx *ww,
}
} else {
- err = i915_gem_object_migrate(obj, ww, INTEL_REGION_LMEM);
+ err = i915_gem_object_migrate(obj, ww, INTEL_REGION_LMEM_0);
if (err) {
pr_err("Object failed migration to lmem\n");
if (err)
if (!ppgtt)
goto err_free;
- ctx->vm = i915_vm_open(&ppgtt->vm);
- i915_vm_put(&ppgtt->vm);
+ ctx->vm = &ppgtt->vm;
}
mutex_init(&ctx->engines_mutex);
err_vm:
if (ctx->vm)
- i915_vm_close(ctx->vm);
+ i915_vm_put(ctx->vm);
err_free:
kfree(ctx);
return NULL;
struct gen6_ppgtt *ppgtt = to_gen6_ppgtt(base);
int err;
- GEM_BUG_ON(!atomic_read(&ppgtt->base.vm.open));
+ GEM_BUG_ON(!kref_read(&ppgtt->base.vm.ref));
/*
* Workaround the limited maximum vma->pin_count and the aliasing_ppgtt
#include "gen8_engine_cs.h"
#include "i915_drv.h"
#include "intel_gpu_commands.h"
-#include "intel_gt_regs.h"
#include "intel_lrc.h"
#include "intel_ring.h"
return MI_ARB_CHECK | 1 << 8 | state;
}
-static i915_reg_t aux_inv_reg(const struct intel_engine_cs *engine)
+u32 *gen12_emit_aux_table_inv(u32 *cs, const i915_reg_t inv_reg)
{
- static const i915_reg_t vd[] = {
- GEN12_VD0_AUX_NV,
- GEN12_VD1_AUX_NV,
- GEN12_VD2_AUX_NV,
- GEN12_VD3_AUX_NV,
- };
-
- static const i915_reg_t ve[] = {
- GEN12_VE0_AUX_NV,
- GEN12_VE1_AUX_NV,
- };
-
- if (engine->class == VIDEO_DECODE_CLASS)
- return vd[engine->instance];
-
- if (engine->class == VIDEO_ENHANCEMENT_CLASS)
- return ve[engine->instance];
-
- GEM_BUG_ON("unknown aux_inv reg\n");
- return INVALID_MMIO_REG;
-}
-
-static u32 *gen12_emit_aux_table_inv(const i915_reg_t inv_reg, u32 *cs)
-{
- *cs++ = MI_LOAD_REGISTER_IMM(1);
+ *cs++ = MI_LOAD_REGISTER_IMM(1) | MI_LRI_MMIO_REMAP_EN;
*cs++ = i915_mmio_reg_offset(inv_reg);
*cs++ = AUX_INV;
*cs++ = MI_NOOP;
if (mode & EMIT_INVALIDATE) {
u32 flags = 0;
- u32 *cs;
+ u32 *cs, count;
flags |= PIPE_CONTROL_COMMAND_CACHE_INVALIDATE;
flags |= PIPE_CONTROL_TLB_INVALIDATE;
if (engine->class == COMPUTE_CLASS)
flags &= ~PIPE_CONTROL_3D_FLAGS;
- cs = intel_ring_begin(rq, 8 + 4);
+ if (!HAS_FLAT_CCS(rq->engine->i915))
+ count = 8 + 4;
+ else
+ count = 8;
+
+ cs = intel_ring_begin(rq, count);
if (IS_ERR(cs))
return PTR_ERR(cs);
cs = gen8_emit_pipe_control(cs, flags, LRC_PPHWSP_SCRATCH_ADDR);
- /* hsdes: 1809175790 */
- cs = gen12_emit_aux_table_inv(GEN12_GFX_CCS_AUX_NV, cs);
+ if (!HAS_FLAT_CCS(rq->engine->i915)) {
+ /* hsdes: 1809175790 */
+ cs = gen12_emit_aux_table_inv(cs, GEN12_GFX_CCS_AUX_NV);
+ }
*cs++ = preparser_disable(false);
intel_ring_advance(rq, cs);
u32 cmd, *cs;
cmd = 4;
- if (mode & EMIT_INVALIDATE)
+ if (mode & EMIT_INVALIDATE) {
cmd += 2;
- if (mode & EMIT_INVALIDATE)
- aux_inv = rq->engine->mask & ~BIT(BCS0);
- if (aux_inv)
- cmd += 2 * hweight32(aux_inv) + 2;
+
+ 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);
+ if (aux_inv)
+ cmd += 4;
+ }
+ }
cs = intel_ring_begin(rq, cmd);
if (IS_ERR(cs))
*cs++ = 0; /* value */
if (aux_inv) { /* hsdes: 1809175790 */
- struct intel_engine_cs *engine;
- unsigned int tmp;
-
- *cs++ = MI_LOAD_REGISTER_IMM(hweight32(aux_inv));
- for_each_engine_masked(engine, rq->engine->gt, aux_inv, tmp) {
- *cs++ = i915_mmio_reg_offset(aux_inv_reg(engine));
- *cs++ = AUX_INV;
- }
- *cs++ = MI_NOOP;
+ if (rq->engine->class == VIDEO_DECODE_CLASS)
+ cs = gen12_emit_aux_table_inv(cs, GEN12_VD0_AUX_NV);
+ else
+ cs = gen12_emit_aux_table_inv(cs, GEN12_VE0_AUX_NV);
}
if (mode & EMIT_INVALIDATE)
#include <linux/types.h>
#include "i915_gem.h" /* GEM_BUG_ON */
-
+#include "intel_gt_regs.h"
#include "intel_gpu_commands.h"
struct i915_request;
u32 *gen11_emit_fini_breadcrumb_rcs(struct i915_request *rq, u32 *cs);
u32 *gen12_emit_fini_breadcrumb_rcs(struct i915_request *rq, u32 *cs);
+u32 *gen12_emit_aux_table_inv(u32 *cs, const i915_reg_t inv_reg);
+
static inline u32 *
__gen8_emit_pipe_control(u32 *batch, u32 flags0, u32 flags1, u32 offset)
{
pd = pdp->entry[gen8_pd_index(idx, 2)];
}
- clflush_cache_range(vaddr, PAGE_SIZE);
+ drm_clflush_virt_range(vaddr, PAGE_SIZE);
vaddr = px_vaddr(i915_pt_entry(pd, gen8_pd_index(idx, 1)));
}
} while (1);
- clflush_cache_range(vaddr, PAGE_SIZE);
+ drm_clflush_virt_range(vaddr, PAGE_SIZE);
return idx;
}
}
} while (rem >= page_size && index < I915_PDES);
- clflush_cache_range(vaddr, PAGE_SIZE);
+ drm_clflush_virt_range(vaddr, PAGE_SIZE);
/*
* Is it safe to mark the 2M block as 64K? -- Either we have
I915_GTT_PAGE_SIZE_2M)))) {
vaddr = px_vaddr(pd);
vaddr[maybe_64K] |= GEN8_PDE_IPS_64K;
- clflush_cache_range(vaddr, PAGE_SIZE);
+ drm_clflush_virt_range(vaddr, PAGE_SIZE);
page_size = I915_GTT_PAGE_SIZE_64K;
/*
for (i = 1; i < index; i += 16)
memset64(vaddr + i, encode, 15);
- clflush_cache_range(vaddr, PAGE_SIZE);
+ drm_clflush_virt_range(vaddr, PAGE_SIZE);
}
}
vaddr = px_vaddr(pt);
vaddr[gen8_pd_index(idx, 0)] = gen8_pte_encode(addr, level, flags);
- clflush_cache_range(&vaddr[gen8_pd_index(idx, 0)], sizeof(*vaddr));
+ drm_clflush_virt_range(&vaddr[gen8_pd_index(idx, 0)], sizeof(*vaddr));
}
static void __xehpsdv_ppgtt_insert_entry_lm(struct i915_address_space *vm,
ce->ring = NULL;
ce->ring_size = SZ_4K;
- ewma_runtime_init(&ce->runtime.avg);
+ ewma_runtime_init(&ce->stats.runtime.avg);
ce->vm = i915_vm_get(engine->gt->vm);
INIT_LIST_HEAD(&ce->guc_state.fences);
INIT_LIST_HEAD(&ce->guc_state.requests);
- ce->guc_id.id = GUC_INVALID_LRC_ID;
+ ce->guc_id.id = GUC_INVALID_CONTEXT_ID;
INIT_LIST_HEAD(&ce->guc_id.link);
INIT_LIST_HEAD(&ce->destroyed_link);
child->parallel.parent = parent;
}
+u64 intel_context_get_total_runtime_ns(const struct intel_context *ce)
+{
+ u64 total, active;
+
+ total = ce->stats.runtime.total;
+ if (ce->ops->flags & COPS_RUNTIME_CYCLES)
+ total *= ce->engine->gt->clock_period_ns;
+
+ active = READ_ONCE(ce->stats.active);
+ if (active)
+ active = intel_context_clock() - active;
+
+ return total + active;
+}
+
+u64 intel_context_get_avg_runtime_ns(struct intel_context *ce)
+{
+ u64 avg = ewma_runtime_read(&ce->stats.runtime.avg);
+
+ if (ce->ops->flags & COPS_RUNTIME_CYCLES)
+ avg *= ce->engine->gt->clock_period_ns;
+
+ return avg;
+}
+
#if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
#include "selftest_context.c"
#endif
clear_bit(CONTEXT_NOPREEMPT, &ce->flags);
}
-static inline u64 intel_context_get_total_runtime_ns(struct intel_context *ce)
-{
- const u32 period = ce->engine->gt->clock_period_ns;
-
- return READ_ONCE(ce->runtime.total) * period;
-}
+u64 intel_context_get_total_runtime_ns(const struct intel_context *ce);
+u64 intel_context_get_avg_runtime_ns(struct intel_context *ce);
-static inline u64 intel_context_get_avg_runtime_ns(struct intel_context *ce)
+static inline u64 intel_context_clock(void)
{
- const u32 period = ce->engine->gt->clock_period_ns;
-
- return mul_u32_u32(ewma_runtime_read(&ce->runtime.avg), period);
+ /* As we mix CS cycles with CPU clocks, use the raw monotonic clock. */
+ return ktime_get_raw_fast_ns();
}
#endif /* __INTEL_CONTEXT_H__ */
#define COPS_HAS_INFLIGHT_BIT 0
#define COPS_HAS_INFLIGHT BIT(COPS_HAS_INFLIGHT_BIT)
+#define COPS_RUNTIME_CYCLES_BIT 1
+#define COPS_RUNTIME_CYCLES BIT(COPS_RUNTIME_CYCLES_BIT)
+
int (*alloc)(struct intel_context *ce);
void (*ban)(struct intel_context *ce, struct i915_request *rq);
} lrc;
u32 tag; /* cookie passed to HW to track this context on submission */
- /* Time on GPU as tracked by the hw. */
- struct {
- struct ewma_runtime avg;
- u64 total;
- u32 last;
- I915_SELFTEST_DECLARE(u32 num_underflow);
- I915_SELFTEST_DECLARE(u32 max_underflow);
- } runtime;
+ /** stats: Context GPU engine busyness tracking. */
+ struct intel_context_stats {
+ u64 active;
+
+ /* Time on GPU as tracked by the hw. */
+ struct {
+ struct ewma_runtime avg;
+ u64 total;
+ u32 last;
+ I915_SELFTEST_DECLARE(u32 num_underflow);
+ I915_SELFTEST_DECLARE(u32 max_underflow);
+ } runtime;
+ } stats;
unsigned int active_count; /* protected by timeline->mutex */
#include <asm/cacheflush.h>
#include <drm/drm_util.h>
+#include <drm/drm_cache.h>
#include <linux/hashtable.h>
#include <linux/irq_work.h>
* of extra paranoia to try and ensure that the HWS takes the value
* we give and that it doesn't end up trapped inside the CPU!
*/
- if (static_cpu_has(X86_FEATURE_CLFLUSH)) {
- mb();
- clflush(&engine->status_page.addr[reg]);
- engine->status_page.addr[reg] = value;
- clflush(&engine->status_page.addr[reg]);
- mb();
- } else {
- WRITE_ONCE(engine->status_page.addr[reg], value);
- }
+ drm_clflush_virt_range(&engine->status_page.addr[reg], sizeof(value));
+ WRITE_ONCE(engine->status_page.addr[reg], value);
+ drm_clflush_virt_range(&engine->status_page.addr[reg], sizeof(value));
}
/*
if (GRAPHICS_VER(i915) == 12 && engine->class == RENDER_CLASS)
engine->props.preempt_timeout_ms = 0;
+ if ((engine->class == COMPUTE_CLASS && !RCS_MASK(engine->gt) &&
+ __ffs(CCS_MASK(engine->gt)) == engine->instance) ||
+ engine->class == RENDER_CLASS)
+ engine->flags |= I915_ENGINE_FIRST_RENDER_COMPUTE;
+
/* features common between engines sharing EUs */
if (engine->class == RENDER_CLASS || engine->class == COMPUTE_CLASS) {
engine->flags |= I915_ENGINE_HAS_RCS_REG_STATE;
static void setup_logical_ids(struct intel_gt *gt, u8 *logical_ids, u8 class)
{
- int i;
- u8 map[MAX_ENGINE_INSTANCE + 1];
+ /*
+ * Logical to physical mapping is needed for proper support
+ * to split-frame feature.
+ */
+ if (MEDIA_VER(gt->i915) >= 11 && class == VIDEO_DECODE_CLASS) {
+ const u8 map[] = { 0, 2, 4, 6, 1, 3, 5, 7 };
- for (i = 0; i < MAX_ENGINE_INSTANCE + 1; ++i)
- map[i] = i;
- populate_logical_ids(gt, logical_ids, class, map, ARRAY_SIZE(map));
+ populate_logical_ids(gt, logical_ids, class,
+ map, ARRAY_SIZE(map));
+ } else {
+ int i;
+ u8 map[MAX_ENGINE_INSTANCE + 1];
+
+ for (i = 0; i < MAX_ENGINE_INSTANCE + 1; ++i)
+ map[i] = i;
+ populate_logical_ids(gt, logical_ids, class,
+ map, ARRAY_SIZE(map));
+ }
}
/**
drm_printf(m, "\tIPEHR: 0x%08x\n", ENGINE_READ(engine, IPEHR));
}
- if (intel_engine_uses_guc(engine)) {
- /* nothing to print yet */
- } else if (HAS_EXECLISTS(dev_priv)) {
+ if (HAS_EXECLISTS(dev_priv) && !intel_engine_uses_guc(engine)) {
struct i915_request * const *port, *rq;
const u32 *hws =
&engine->status_page.addr[I915_HWS_CSB_BUF0_INDEX];
#define I915_MAX_VCS 8
#define I915_MAX_VECS 4
+#define I915_MAX_SFC (I915_MAX_VCS / 2)
#define I915_MAX_CCS 4
+#define I915_MAX_RCS 1
/*
* Engine IDs definitions.
#define I915_ENGINE_WANT_FORCED_PREEMPTION BIT(8)
#define I915_ENGINE_HAS_RCS_REG_STATE BIT(9)
#define I915_ENGINE_HAS_EU_PRIORITY BIT(10)
+#define I915_ENGINE_FIRST_RENDER_COMPUTE BIT(11)
unsigned int flags;
/*
#define for_each_instdone_gslice_dss_xehp(dev_priv_, sseu_, iter_, gslice_, dss_) \
for ((iter_) = 0, (gslice_) = 0, (dss_) = 0; \
- (iter_) < GEN_MAX_SUBSLICES; \
+ (iter_) < GEN_SS_MASK_SIZE; \
(iter_)++, (gslice_) = (iter_) / GEN_DSS_PER_GSLICE, \
(dss_) = (iter_) % GEN_DSS_PER_GSLICE) \
for_each_if(intel_sseu_has_subslice((sseu_), 0, (iter_)))
void intel_engines_driver_register(struct drm_i915_private *i915)
{
struct legacy_ring ring = {};
- u8 uabi_instances[5] = {};
struct list_head *it, *next;
struct rb_node **p, *prev;
LIST_HEAD(engines);
GEM_BUG_ON(engine->class >= ARRAY_SIZE(uabi_classes));
engine->uabi_class = uabi_classes[engine->class];
- GEM_BUG_ON(engine->uabi_class >= ARRAY_SIZE(uabi_instances));
- engine->uabi_instance = uabi_instances[engine->uabi_class]++;
+ GEM_BUG_ON(engine->uabi_class >=
+ ARRAY_SIZE(i915->engine_uabi_class_count));
+ engine->uabi_instance =
+ i915->engine_uabi_class_count[engine->uabi_class]++;
/* Replace the internal name with the final user facing name */
memcpy(old, engine->name, sizeof(engine->name));
int class, inst;
int errors = 0;
- for (class = 0; class < ARRAY_SIZE(uabi_instances); class++) {
- for (inst = 0; inst < uabi_instances[class]; inst++) {
+ for (class = 0; class < ARRAY_SIZE(i915->engine_uabi_class_count); class++) {
+ for (inst = 0; inst < i915->engine_uabi_class_count[class]; inst++) {
engine = intel_engine_lookup_user(i915,
class, inst);
if (!engine) {
GEM_BUG_ON(test_bit(ccid - 1, &engine->context_tag));
__set_bit(ccid - 1, &engine->context_tag);
}
-
- lrc_update_runtime(ce);
intel_engine_context_out(engine);
execlists_context_status_change(rq, INTEL_CONTEXT_SCHEDULE_OUT);
if (engine->fw_domain && !--engine->fw_active)
return inactive;
}
-static void invalidate_csb_entries(const u64 *first, const u64 *last)
-{
- clflush((void *)first);
- clflush((void *)last);
-}
-
/*
* Starting with Gen12, the status has a new format:
*
* the wash as hardware, working or not, will need to do the
* invalidation before.
*/
- invalidate_csb_entries(&buf[0], &buf[num_entries - 1]);
+ drm_clflush_virt_range(&buf[0], num_entries * sizeof(buf[0]));
/*
* We assume that any event reflects a change in context flow
* and merits a fresh timeslice. We reinstall the timer after
* inspecting the queue to see if we need to resumbit.
*/
- if (*prev != *execlists->active) /* elide lite-restores */
+ if (*prev != *execlists->active) { /* elide lite-restores */
+ /*
+ * Note the inherent discrepancy between the HW runtime,
+ * recorded as part of the context switch, and the CPU
+ * adjustment for active contexts. We have to hope that
+ * the delay in processing the CS event is very small
+ * and consistent. It works to our advantage to have
+ * the CPU adjustment _undershoot_ (i.e. start later than)
+ * the CS timestamp so we never overreport the runtime
+ * and correct overselves later when updating from HW.
+ */
+ if (*prev)
+ lrc_runtime_stop((*prev)->context);
+ if (*execlists->active)
+ lrc_runtime_start((*execlists->active)->context);
new_timeslice(execlists);
+ }
return inactive;
}
if (!cap->error)
goto err_cap;
- cap->error->gt = intel_gt_coredump_alloc(engine->gt, gfp);
+ cap->error->gt = intel_gt_coredump_alloc(engine->gt, gfp, CORE_DUMP_FLAG_NONE);
if (!cap->error->gt)
goto err_gpu;
- cap->error->gt->engine = intel_engine_coredump_alloc(engine, gfp);
+ cap->error->gt->engine = intel_engine_coredump_alloc(engine, gfp, CORE_DUMP_FLAG_NONE);
if (!cap->error->gt->engine)
goto err_gt;
}
static const struct intel_context_ops execlists_context_ops = {
- .flags = COPS_HAS_INFLIGHT,
+ .flags = COPS_HAS_INFLIGHT | COPS_RUNTIME_CYCLES,
.alloc = execlists_context_alloc,
/* Check that the GPU does indeed update the CSB entries! */
memset(execlists->csb_status, -1, (reset_value + 1) * sizeof(u64));
- invalidate_csb_entries(&execlists->csb_status[0],
- &execlists->csb_status[reset_value]);
+ drm_clflush_virt_range(execlists->csb_status,
+ execlists->csb_size *
+ sizeof(execlists->csb_status));
/* Once more for luck and our trusty paranoia */
ENGINE_WRITE(engine, RING_CONTEXT_STATUS_PTR,
sanitize_hwsp(engine);
/* And scrub the dirty cachelines for the HWSP */
- clflush_cache_range(engine->status_page.addr, PAGE_SIZE);
+ drm_clflush_virt_range(engine->status_page.addr, PAGE_SIZE);
intel_engine_reset_pinned_contexts(engine);
}
enable_execlists(engine);
- if (engine->class == RENDER_CLASS)
+ if (engine->flags & I915_ENGINE_FIRST_RENDER_COMPUTE)
xehp_enable_ccs_engines(engine);
return 0;
{
struct intel_engine_execlists * const execlists = &engine->execlists;
- mb(); /* paranoia: read the CSB pointers from after the reset */
- clflush(execlists->csb_write);
- mb();
+ drm_clflush_virt_range(execlists->csb_write,
+ sizeof(execlists->csb_write[0]));
inactive = process_csb(engine, inactive); /* drain preemption events */
}
static const struct intel_context_ops virtual_context_ops = {
- .flags = COPS_HAS_INFLIGHT,
+ .flags = COPS_HAS_INFLIGHT | COPS_RUNTIME_CYCLES,
.alloc = virtual_context_alloc,
* Copyright © 2020 Intel Corporation
*/
-#include <linux/agp_backend.h>
-#include <linux/stop_machine.h>
-
+#include <linux/types.h>
#include <asm/set_memory.h>
#include <asm/smp.h>
#include <drm/i915_drm.h>
-#include <drm/intel-gtt.h>
#include "gem/i915_gem_lmem.h"
#include "intel_gt.h"
+#include "intel_gt_gmch.h"
#include "intel_gt_regs.h"
#include "i915_drv.h"
#include "i915_scatterlist.h"
return 0;
}
-/*
- * 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 (!intel_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;
-}
-
/**
* i915_ggtt_suspend_vm - Suspend the memory mappings for a GGTT or DPT VM
* @vm: The VM to suspend the mappings for
void i915_ggtt_suspend_vm(struct i915_address_space *vm)
{
struct i915_vma *vma, *vn;
- int open;
+ int save_skip_rewrite;
drm_WARN_ON(&vm->i915->drm, !vm->is_ggtt && !vm->is_dpt);
mutex_lock(&vm->mutex);
- /* Skip rewriting PTE on VMA unbind. */
- open = atomic_xchg(&vm->open, 0);
+ /*
+ * Skip rewriting PTE on VMA unbind.
+ * FIXME: Use an argument to i915_vma_unbind() instead?
+ */
+ save_skip_rewrite = vm->skip_pte_rewrite;
+ vm->skip_pte_rewrite = true;
list_for_each_entry_safe(vma, vn, &vm->bound_list, vm_link) {
struct drm_i915_gem_object *obj = vma->obj;
*/
i915_gem_object_get(obj);
- atomic_set(&vm->open, open);
mutex_unlock(&vm->mutex);
i915_gem_object_lock(obj, NULL);
- open = i915_vma_unbind(vma);
+ GEM_WARN_ON(i915_vma_unbind(vma));
i915_gem_object_unlock(obj);
-
- GEM_WARN_ON(open);
-
i915_gem_object_put(obj);
+
+ vm->skip_pte_rewrite = save_skip_rewrite;
goto retry;
}
vm->clear_range(vm, 0, vm->total);
- atomic_set(&vm->open, open);
+ vm->skip_pte_rewrite = save_skip_rewrite;
mutex_unlock(&vm->mutex);
}
spin_unlock_irq(&uncore->lock);
}
-static void gen8_ggtt_invalidate(struct i915_ggtt *ggtt)
+void gen8_ggtt_invalidate(struct i915_ggtt *ggtt)
{
struct intel_uncore *uncore = ggtt->vm.gt->uncore;
intel_uncore_write_fw(uncore, GEN8_GTCR, GEN8_GTCR_INVALIDATE);
}
-static void gmch_ggtt_invalidate(struct i915_ggtt *ggtt)
-{
- intel_gtt_chipset_flush();
-}
-
u64 gen8_ggtt_pte_encode(dma_addr_t addr,
enum i915_cache_level level,
u32 flags)
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]);
-}
-
-static void i915_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 i915_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);
-}
-
-static void i915_ggtt_clear_range(struct i915_address_space *vm,
- u64 start, u64 length)
-{
- intel_gtt_clear_range(start >> PAGE_SHIFT, length >> PAGE_SHIFT);
-}
-
-static void ggtt_bind_vma(struct i915_address_space *vm,
+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,
vma_res->page_sizes_gtt = I915_GTT_PAGE_SIZE;
}
-static void ggtt_unbind_vma(struct i915_address_space *vm,
+void intel_ggtt_unbind_vma(struct i915_address_space *vm,
struct i915_vma_resource *vma_res)
{
vm->clear_range(vm, vma_res->start, vma_res->vma_size);
ggtt->alias = ppgtt;
ggtt->vm.bind_async_flags |= ppgtt->vm.bind_async_flags;
- GEM_BUG_ON(ggtt->vm.vma_ops.bind_vma != ggtt_bind_vma);
+ GEM_BUG_ON(ggtt->vm.vma_ops.bind_vma != intel_ggtt_bind_vma);
ggtt->vm.vma_ops.bind_vma = aliasing_gtt_bind_vma;
- GEM_BUG_ON(ggtt->vm.vma_ops.unbind_vma != ggtt_unbind_vma);
+ GEM_BUG_ON(ggtt->vm.vma_ops.unbind_vma != intel_ggtt_unbind_vma);
ggtt->vm.vma_ops.unbind_vma = aliasing_gtt_unbind_vma;
i915_vm_free_pt_stash(&ppgtt->vm, &stash);
i915_vm_put(&ppgtt->vm);
- ggtt->vm.vma_ops.bind_vma = ggtt_bind_vma;
- ggtt->vm.vma_ops.unbind_vma = ggtt_unbind_vma;
+ ggtt->vm.vma_ops.bind_vma = intel_ggtt_bind_vma;
+ ggtt->vm.vma_ops.unbind_vma = intel_ggtt_unbind_vma;
}
int i915_init_ggtt(struct drm_i915_private *i915)
{
struct i915_vma *vma, *vn;
- atomic_set(&ggtt->vm.open, 0);
-
flush_workqueue(ggtt->vm.i915->wq);
i915_gem_drain_freed_objects(ggtt->vm.i915);
mutex_lock(&ggtt->vm.mutex);
+ ggtt->vm.skip_pte_rewrite = true;
+
list_for_each_entry_safe(vma, vn, &ggtt->vm.bound_list, vm_link) {
struct drm_i915_gem_object *obj = vma->obj;
bool trylock;
dma_resv_fini(&ggtt->vm._resv);
}
-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)
+struct resource intel_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;
-
- /* TODO: We're not aware of mappable constraints on gen8 yet */
- 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;
- ggtt->vm.bind_async_flags =
- I915_VMA_GLOBAL_BIND | I915_VMA_LOCAL_BIND;
- }
-
- ggtt->invalidate = gen8_ggtt_invalidate;
-
- ggtt->vm.vma_ops.bind_vma = ggtt_bind_vma;
- ggtt->vm.vma_ops.unbind_vma = 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 = ggtt_bind_vma;
- ggtt->vm.vma_ops.unbind_vma = ggtt_unbind_vma;
-
- return ggtt_probe_common(ggtt, size);
-}
-
-static void i915_gmch_remove(struct i915_address_space *vm)
-{
- intel_gmch_remove();
-}
-
-static int i915_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_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 = i915_ggtt_insert_page;
- ggtt->vm.insert_entries = i915_ggtt_insert_entries;
- ggtt->vm.clear_range = i915_ggtt_clear_range;
- ggtt->vm.cleanup = i915_gmch_remove;
-
- ggtt->invalidate = gmch_ggtt_invalidate;
-
- ggtt->vm.vma_ops.bind_vma = ggtt_bind_vma;
- ggtt->vm.vma_ops.unbind_vma = ggtt_unbind_vma;
-
- if (unlikely(ggtt->do_idle_maps))
- drm_notice(&i915->drm,
- "Applying Ironlake quirks for intel_iommu\n");
-
- return 0;
-}
-
static int ggtt_probe_hw(struct i915_ggtt *ggtt, struct intel_gt *gt)
{
struct drm_i915_private *i915 = gt->i915;
dma_resv_init(&ggtt->vm._resv);
if (GRAPHICS_VER(i915) <= 5)
- ret = i915_gmch_probe(ggtt);
+ ret = intel_gt_gmch_gen5_probe(ggtt);
else if (GRAPHICS_VER(i915) < 8)
- ret = gen6_gmch_probe(ggtt);
+ ret = intel_gt_gmch_gen6_probe(ggtt);
else
- ret = gen8_gmch_probe(ggtt);
+ ret = intel_gt_gmch_gen8_probe(ggtt);
if (ret) {
dma_resv_fini(&ggtt->vm._resv);
return ret;
int i915_ggtt_enable_hw(struct drm_i915_private *i915)
{
- if (GRAPHICS_VER(i915) < 6 && !intel_enable_gtt())
- return -EIO;
-
- return 0;
+ return intel_gt_gmch_gen5_enable_hw(i915);
}
void i915_ggtt_enable_guc(struct i915_ggtt *ggtt)
{
struct i915_vma *vma;
bool write_domain_objs = false;
- int open;
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);
- /* Skip rewriting PTE on VMA unbind. */
- open = atomic_xchg(&vm->open, 0);
-
/* clflush objects bound into the GGTT and rebind them. */
list_for_each_entry(vma, &vm->bound_list, vm_link) {
struct drm_i915_gem_object *obj = vma->obj;
}
}
- atomic_set(&vm->open, open);
-
return write_domain_objs;
}
#define MI_LOAD_REGISTER_IMM(x) MI_INSTR(0x22, 2*(x)-1)
/* Gen11+. addr = base + (ctx_restore ? offset & GENMASK(12,2) : offset) */
#define MI_LRI_LRM_CS_MMIO REG_BIT(19)
+#define MI_LRI_MMIO_REMAP_EN REG_BIT(17)
#define MI_LRI_FORCE_POSTED (1<<12)
#define MI_LOAD_REGISTER_IMM_MAX_REGS (126)
#define MI_STORE_REGISTER_MEM MI_INSTR(0x24, 1)
*/
#include <drm/drm_managed.h>
-#include <drm/intel-gtt.h>
#include "gem/i915_gem_internal.h"
#include "gem/i915_gem_lmem.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_pm.h"
#include "intel_gt_regs.h"
#include "intel_gt_requests.h"
#include "intel_rc6.h"
#include "intel_renderstate.h"
#include "intel_rps.h"
+#include "intel_gt_sysfs.h"
#include "intel_uncore.h"
#include "shmem_utils.h"
-void __intel_gt_init_early(struct intel_gt *gt, struct drm_i915_private *i915)
+static void __intel_gt_init_early(struct intel_gt *gt)
{
spin_lock_init(>->irq_lock);
intel_rps_init_early(>->rps);
}
-void intel_gt_init_early(struct intel_gt *gt, struct drm_i915_private *i915)
+/* Preliminary initialization of Tile 0 */
+void intel_root_gt_init_early(struct drm_i915_private *i915)
{
+ struct intel_gt *gt = to_gt(i915);
+
gt->i915 = i915;
gt->uncore = &i915->uncore;
+
+ __intel_gt_init_early(gt);
}
-int intel_gt_probe_lmem(struct intel_gt *gt)
+static int intel_gt_probe_lmem(struct intel_gt *gt)
{
struct drm_i915_private *i915 = gt->i915;
+ unsigned int instance = gt->info.id;
+ int id = INTEL_REGION_LMEM_0 + instance;
struct intel_memory_region *mem;
- int id;
int err;
mem = intel_gt_setup_lmem(gt);
return err;
}
- id = INTEL_REGION_LMEM;
-
mem->id = id;
+ mem->instance = instance;
intel_memory_region_set_name(mem, "local%u", mem->instance);
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 },
{},
{
wmb();
if (GRAPHICS_VER(gt->i915) < 6)
- intel_gtt_chipset_flush();
+ intel_gt_gmch_gen5_chipset_flush(gt);
}
void intel_gt_driver_register(struct intel_gt *gt)
intel_rps_driver_register(>->rps);
intel_gt_debugfs_register(gt);
+ intel_gt_sysfs_register(gt);
}
static int intel_gt_init_scratch(struct intel_gt *gt, unsigned int size)
if (err)
goto err_uc_init;
+ err = intel_gt_init_hwconfig(gt);
+ if (err)
+ drm_err(>->i915->drm, "Failed to retrieve hwconfig table: %pe\n",
+ ERR_PTR(err));
+
err = __engines_record_defaults(gt);
if (err)
goto err_gt;
intel_gt_pm_fini(gt);
intel_gt_fini_scratch(gt);
intel_gt_fini_buffer_pool(gt);
+ intel_gt_fini_hwconfig(gt);
}
-void intel_gt_driver_late_release(struct intel_gt *gt)
+void intel_gt_driver_late_release_all(struct drm_i915_private *i915)
{
+ struct intel_gt *gt;
+ unsigned int id;
+
/* We need to wait for inflight RCU frees to release their grip */
rcu_barrier();
- intel_uc_driver_late_release(>->uc);
- intel_gt_fini_requests(gt);
- intel_gt_fini_reset(gt);
- intel_gt_fini_timelines(gt);
- intel_engines_free(gt);
+ for_each_gt(gt, i915, id) {
+ intel_uc_driver_late_release(>->uc);
+ intel_gt_fini_requests(gt);
+ intel_gt_fini_reset(gt);
+ intel_gt_fini_timelines(gt);
+ intel_engines_free(gt);
+ }
}
/**
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;
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;
+
+ if (!gt_is_root(gt)) {
+ struct intel_uncore_mmio_debug *mmio_debug;
+ struct intel_uncore *uncore;
+
+ uncore = kzalloc(sizeof(*uncore), GFP_KERNEL);
+ if (!uncore)
+ return -ENOMEM;
+
+ mmio_debug = kzalloc(sizeof(*mmio_debug), GFP_KERNEL);
+ if (!mmio_debug) {
+ kfree(uncore);
+ return -ENOMEM;
+ }
+
+ gt->uncore = uncore;
+ gt->uncore->debug = mmio_debug;
+
+ __intel_gt_init_early(gt);
+ }
+
+ intel_uncore_init_early(gt->uncore, gt);
+
+ ret = intel_uncore_setup_mmio(gt->uncore, phys_addr);
+ if (ret)
+ return ret;
+
+ gt->phys_addr = phys_addr;
+
+ return 0;
+}
+
+static void
+intel_gt_tile_cleanup(struct intel_gt *gt)
+{
+ intel_uncore_cleanup_mmio(gt->uncore);
+
+ if (!gt_is_root(gt)) {
+ kfree(gt->uncore->debug);
+ kfree(gt->uncore);
+ kfree(gt);
+ }
+}
+
+int intel_gt_probe_all(struct drm_i915_private *i915)
+{
+ struct pci_dev *pdev = to_pci_dev(i915->drm.dev);
+ struct intel_gt *gt = &i915->gt0;
+ phys_addr_t phys_addr;
+ unsigned int mmio_bar;
+ int ret;
+
+ mmio_bar = GRAPHICS_VER(i915) == 2 ? 1 : 0;
+ phys_addr = pci_resource_start(pdev, mmio_bar);
+
+ /*
+ * We always have at least one primary GT on any device
+ * and it has been already initialized early during probe
+ * in i915_driver_probe()
+ */
+ ret = intel_gt_tile_setup(gt, phys_addr);
+ if (ret)
+ return ret;
+
+ i915->gt[0] = gt;
+
+ /* TODO: add more tiles */
+ return 0;
+}
+
+int intel_gt_tiles_init(struct drm_i915_private *i915)
+{
+ struct intel_gt *gt;
+ unsigned int id;
+ int ret;
+
+ for_each_gt(gt, i915, id) {
+ ret = intel_gt_probe_lmem(gt);
+ if (ret)
+ return ret;
+ }
+
+ return 0;
+}
+
+void intel_gt_release_all(struct drm_i915_private *i915)
+{
+ struct intel_gt *gt;
+ unsigned int id;
+
+ for_each_gt(gt, i915, id) {
+ intel_gt_tile_cleanup(gt);
+ i915->gt[id] = NULL;
+ }
+}
+
void intel_gt_info_print(const struct intel_gt_info *info,
struct drm_printer *p)
{
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), \
##__VA_ARGS__); \
} while (0)
+static inline bool gt_is_root(struct intel_gt *gt)
+{
+ return !gt->info.id;
+}
+
static inline struct intel_gt *uc_to_gt(struct intel_uc *uc)
{
return container_of(uc, struct intel_gt, uc);
return container_of(huc, struct intel_gt, uc.huc);
}
-void intel_gt_init_early(struct intel_gt *gt, struct drm_i915_private *i915);
-void __intel_gt_init_early(struct intel_gt *gt, struct drm_i915_private *i915);
+void intel_root_gt_init_early(struct drm_i915_private *i915);
int intel_gt_assign_ggtt(struct intel_gt *gt);
-int intel_gt_probe_lmem(struct intel_gt *gt);
int intel_gt_init_mmio(struct intel_gt *gt);
int __must_check intel_gt_init_hw(struct intel_gt *gt);
int intel_gt_init(struct intel_gt *gt);
void intel_gt_driver_remove(struct intel_gt *gt);
void intel_gt_driver_release(struct intel_gt *gt);
-void intel_gt_driver_late_release(struct intel_gt *gt);
+void intel_gt_driver_late_release_all(struct drm_i915_private *i915);
int intel_gt_wait_for_idle(struct intel_gt *gt, long timeout);
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);
+
+#define for_each_gt(gt__, i915__, id__) \
+ for ((id__) = 0; \
+ (id__) < I915_MAX_GT; \
+ (id__)++) \
+ for_each_if(((gt__) = (i915__)->gt[(id__)]))
+
void intel_gt_info_print(const struct intel_gt_info *info,
struct drm_printer *p);
void intel_gt_invalidate_tlbs(struct intel_gt *gt);
+struct resource intel_pci_resource(struct pci_dev *pdev, int bar);
+
#endif /* __INTEL_GT_H__ */
if (gt->clock_frequency)
gt->clock_period_ns = intel_gt_clock_interval_to_ns(gt, 1);
+ /* Icelake appears to use another fixed frequency for CTX_TIMESTAMP */
+ if (GRAPHICS_VER(gt->i915) == 11)
+ gt->clock_period_ns = NSEC_PER_SEC / 13750000;
+
GT_TRACE(gt,
"Using clock frequency: %dkHz, period: %dns, wrap: %lldms\n",
gt->clock_frequency / 1000,
#include <linux/debugfs.h>
#include "i915_drv.h"
+#include "intel_gt.h"
#include "intel_gt_debugfs.h"
#include "intel_gt_engines_debugfs.h"
#include "intel_gt_pm_debugfs.h"
}
}
-int intel_gt_debugfs_reset_store(struct intel_gt *gt, u64 val)
+void intel_gt_debugfs_reset_store(struct intel_gt *gt, u64 val)
{
/* Flush any previous reset before applying for a new one */
wait_event(gt->reset.queue,
intel_gt_handle_error(gt, val, I915_ERROR_CAPTURE,
"Manually reset engine mask to %llx", val);
- return 0;
}
/*
static int __intel_gt_debugfs_reset_store(void *data, u64 val)
{
- return intel_gt_debugfs_reset_store(data, val);
+ intel_gt_debugfs_reset_store(data, val);
+
+ return 0;
}
DEFINE_SIMPLE_ATTRIBUTE(reset_fops, __intel_gt_debugfs_reset_show,
__intel_gt_debugfs_reset_store, "%llu\n");
+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);
+
+ return 0;
+}
+DEFINE_INTEL_GT_DEBUGFS_ATTRIBUTE(steering);
+
static void gt_debugfs_register(struct intel_gt *gt, struct dentry *root)
{
static const struct intel_gt_debugfs_file files[] = {
{ "reset", &reset_fops, NULL },
+ { "steering", &steering_fops },
};
intel_gt_debugfs_register_files(root, files, ARRAY_SIZE(files), gt);
/* functions that need to be accessed by the upper level non-gt interfaces */
int intel_gt_debugfs_reset_show(struct intel_gt *gt, u64 *val);
-int intel_gt_debugfs_reset_store(struct intel_gt *gt, u64 val);
+void intel_gt_debugfs_reset_store(struct intel_gt *gt, u64 val);
#endif /* INTEL_GT_DEBUGFS_H */
--- /dev/null
+// 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 (!intel_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;
+}
--- /dev/null
+/* 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__ */
void intel_gt_pm_init_early(struct intel_gt *gt)
{
- intel_wakeref_init(>->wakeref, gt->uncore->rpm, &wf_ops);
+ /*
+ * We access the runtime_pm structure via gt->i915 here rather than
+ * gt->uncore as we do elsewhere in the file because gt->uncore is not
+ * yet initialized for all tiles at this point in the driver startup.
+ * runtime_pm is per-device rather than per-tile, so this is still the
+ * correct structure.
+ */
+ intel_wakeref_init(>->wakeref, >->i915->runtime_pm, &wf_ops);
seqcount_mutex_init(>->stats.lock, >->wakeref.mutex);
}
#include "intel_uncore.h"
#include "vlv_sideband.h"
-int intel_gt_pm_debugfs_forcewake_user_open(struct intel_gt *gt)
+void intel_gt_pm_debugfs_forcewake_user_open(struct intel_gt *gt)
{
atomic_inc(>->user_wakeref);
intel_gt_pm_get(gt);
if (GRAPHICS_VER(gt->i915) >= 6)
intel_uncore_forcewake_user_get(gt->uncore);
-
- return 0;
}
-int intel_gt_pm_debugfs_forcewake_user_release(struct intel_gt *gt)
+void intel_gt_pm_debugfs_forcewake_user_release(struct intel_gt *gt)
{
if (GRAPHICS_VER(gt->i915) >= 6)
intel_uncore_forcewake_user_put(gt->uncore);
intel_gt_pm_put(gt);
atomic_dec(>->user_wakeref);
-
- return 0;
}
static int forcewake_user_open(struct inode *inode, struct file *file)
{
struct intel_gt *gt = inode->i_private;
- return intel_gt_pm_debugfs_forcewake_user_open(gt);
+ intel_gt_pm_debugfs_forcewake_user_open(gt);
+
+ return 0;
}
static int forcewake_user_release(struct inode *inode, struct file *file)
{
struct intel_gt *gt = inode->i_private;
- return intel_gt_pm_debugfs_forcewake_user_release(gt);
+ intel_gt_pm_debugfs_forcewake_user_release(gt);
+
+ return 0;
}
static const struct file_operations forcewake_user_fops = {
} else if (GRAPHICS_VER(i915) >= 6) {
u32 rp_state_limits;
u32 gt_perf_status;
- u32 rp_state_cap;
+ struct intel_rps_freq_caps caps;
u32 rpmodectl, rpinclimit, rpdeclimit;
u32 rpstat, cagf, reqf;
u32 rpcurupei, rpcurup, rpprevup;
u32 rpcurdownei, rpcurdown, rpprevdown;
u32 rpupei, rpupt, rpdownei, rpdownt;
u32 pm_ier, pm_imr, pm_isr, pm_iir, pm_mask;
- int max_freq;
rp_state_limits = intel_uncore_read(uncore, GEN6_RP_STATE_LIMITS);
- rp_state_cap = intel_rps_read_state_cap(rps);
+ gen6_rps_get_freq_caps(rps, &caps);
if (IS_GEN9_LP(i915))
gt_perf_status = intel_uncore_read(uncore, BXT_GT_PERF_STATUS);
else
drm_printf(p, "RP DOWN THRESHOLD: %d (%lldns)\n",
rpdownt, intel_gt_pm_interval_to_ns(gt, rpdownt));
- max_freq = (IS_GEN9_LP(i915) ? rp_state_cap >> 0 :
- rp_state_cap >> 16) & 0xff;
- max_freq *= (IS_GEN9_BC(i915) ||
- GRAPHICS_VER(i915) >= 11 ? GEN9_FREQ_SCALER : 1);
drm_printf(p, "Lowest (RPN) frequency: %dMHz\n",
- intel_gpu_freq(rps, max_freq));
-
- max_freq = (rp_state_cap & 0xff00) >> 8;
- max_freq *= (IS_GEN9_BC(i915) ||
- GRAPHICS_VER(i915) >= 11 ? GEN9_FREQ_SCALER : 1);
+ intel_gpu_freq(rps, caps.min_freq));
drm_printf(p, "Nominal (RP1) frequency: %dMHz\n",
- intel_gpu_freq(rps, max_freq));
-
- max_freq = (IS_GEN9_LP(i915) ? rp_state_cap >> 16 :
- rp_state_cap >> 0) & 0xff;
- max_freq *= (IS_GEN9_BC(i915) ||
- GRAPHICS_VER(i915) >= 11 ? GEN9_FREQ_SCALER : 1);
+ intel_gpu_freq(rps, caps.rp1_freq));
drm_printf(p, "Max non-overclocked (RP0) frequency: %dMHz\n",
- intel_gpu_freq(rps, max_freq));
+ intel_gpu_freq(rps, caps.rp0_freq));
drm_printf(p, "Max overclocked frequency: %dMHz\n",
intel_gpu_freq(rps, rps->max_freq));
void intel_gt_pm_frequency_dump(struct intel_gt *gt, struct drm_printer *m);
/* functions that need to be accessed by the upper level non-gt interfaces */
-int intel_gt_pm_debugfs_forcewake_user_open(struct intel_gt *gt);
-int intel_gt_pm_debugfs_forcewake_user_release(struct intel_gt *gt);
+void intel_gt_pm_debugfs_forcewake_user_open(struct intel_gt *gt);
+void intel_gt_pm_debugfs_forcewake_user_release(struct intel_gt *gt);
#endif /* INTEL_GT_PM_DEBUGFS_H */
#define GEN8_MCR_SLICE_MASK GEN8_MCR_SLICE(3)
#define GEN8_MCR_SUBSLICE(subslice) (((subslice) & 3) << 24)
#define GEN8_MCR_SUBSLICE_MASK GEN8_MCR_SUBSLICE(3)
+#define GEN11_MCR_MULTICAST REG_BIT(31)
#define GEN11_MCR_SLICE(slice) (((slice) & 0xf) << 27)
#define GEN11_MCR_SLICE_MASK GEN11_MCR_SLICE(0xf)
#define GEN11_MCR_SUBSLICE(subslice) (((subslice) & 0x7) << 24)
#define EU_PERF_CNTL3 _MMIO(0xe758)
#define LSC_CHICKEN_BIT_0 _MMIO(0xe7c8)
+#define DISABLE_D8_D16_COASLESCE REG_BIT(30)
#define FORCE_1_SUB_MESSAGE_PER_FRAGMENT REG_BIT(15)
#define LSC_CHICKEN_BIT_0_UDW _MMIO(0xe7c8 + 4)
#define DIS_CHAIN_2XSIMD8 REG_BIT(55 - 32)
--- /dev/null
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2022 Intel Corporation
+ */
+
+#include <drm/drm_device.h>
+#include <linux/device.h>
+#include <linux/kobject.h>
+#include <linux/printk.h>
+#include <linux/sysfs.h>
+
+#include "i915_drv.h"
+#include "i915_sysfs.h"
+#include "intel_gt.h"
+#include "intel_gt_sysfs.h"
+#include "intel_gt_sysfs_pm.h"
+#include "intel_gt_types.h"
+#include "intel_rc6.h"
+
+bool is_object_gt(struct kobject *kobj)
+{
+ return !strncmp(kobj->name, "gt", 2);
+}
+
+static struct intel_gt *kobj_to_gt(struct kobject *kobj)
+{
+ return container_of(kobj, struct kobj_gt, base)->gt;
+}
+
+struct intel_gt *intel_gt_sysfs_get_drvdata(struct device *dev,
+ const char *name)
+{
+ struct kobject *kobj = &dev->kobj;
+
+ /*
+ * We are interested at knowing from where the interface
+ * has been called, whether it's called from gt/ or from
+ * the parent directory.
+ * From the interface position it depends also the value of
+ * the private data.
+ * If the interface is called from gt/ then private data is
+ * of the "struct intel_gt *" type, otherwise it's * a
+ * "struct drm_i915_private *" type.
+ */
+ if (!is_object_gt(kobj)) {
+ struct drm_i915_private *i915 = kdev_minor_to_i915(dev);
+
+ return to_gt(i915);
+ }
+
+ return kobj_to_gt(kobj);
+}
+
+static struct kobject *gt_get_parent_obj(struct intel_gt *gt)
+{
+ return >->i915->drm.primary->kdev->kobj;
+}
+
+static ssize_t id_show(struct device *dev,
+ struct device_attribute *attr,
+ char *buf)
+{
+ struct intel_gt *gt = intel_gt_sysfs_get_drvdata(dev, attr->attr.name);
+
+ return sysfs_emit(buf, "%u\n", gt->info.id);
+}
+static DEVICE_ATTR_RO(id);
+
+static struct attribute *id_attrs[] = {
+ &dev_attr_id.attr,
+ NULL,
+};
+ATTRIBUTE_GROUPS(id);
+
+static void kobj_gt_release(struct kobject *kobj)
+{
+ kfree(kobj);
+}
+
+static struct kobj_type kobj_gt_type = {
+ .release = kobj_gt_release,
+ .sysfs_ops = &kobj_sysfs_ops,
+ .default_groups = id_groups,
+};
+
+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
+ * generated under the parent directory.
+ *
+ * We generate the files only for gt 0
+ * to avoid duplicates.
+ */
+ if (gt_is_root(gt))
+ intel_gt_sysfs_pm_init(gt, gt_get_parent_obj(gt));
+
+ kg = kzalloc(sizeof(*kg), GFP_KERNEL);
+ if (!kg)
+ 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);
+
+ return;
+
+exit_kobj_put:
+ kobject_put(&kg->base);
+
+exit_fail:
+ drm_warn(>->i915->drm,
+ "failed to initialize gt%d sysfs root\n", gt->info.id);
+}
--- /dev/null
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2022 Intel Corporation
+ */
+
+#ifndef __SYSFS_GT_H__
+#define __SYSFS_GT_H__
+
+#include <linux/ctype.h>
+#include <linux/kobject.h>
+
+#include "i915_gem.h" /* GEM_BUG_ON() */
+
+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);
+
+struct kobject *
+intel_gt_create_kobj(struct intel_gt *gt,
+ struct kobject *dir,
+ const char *name);
+
+void intel_gt_sysfs_register(struct intel_gt *gt);
+struct intel_gt *intel_gt_sysfs_get_drvdata(struct device *dev,
+ const char *name);
+
+#endif /* SYSFS_GT_H */
--- /dev/null
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2022 Intel Corporation
+ */
+
+#include <drm/drm_device.h>
+#include <linux/sysfs.h>
+#include <linux/printk.h>
+
+#include "i915_drv.h"
+#include "i915_reg.h"
+#include "i915_sysfs.h"
+#include "intel_gt.h"
+#include "intel_gt_regs.h"
+#include "intel_gt_sysfs.h"
+#include "intel_gt_sysfs_pm.h"
+#include "intel_rc6.h"
+#include "intel_rps.h"
+
+#ifdef CONFIG_PM
+enum intel_gt_sysfs_op {
+ INTEL_GT_SYSFS_MIN = 0,
+ INTEL_GT_SYSFS_MAX,
+};
+
+static int
+sysfs_gt_attribute_w_func(struct device *dev, struct device_attribute *attr,
+ int (func)(struct intel_gt *gt, u32 val), u32 val)
+{
+ struct intel_gt *gt;
+ int ret;
+
+ if (!is_object_gt(&dev->kobj)) {
+ int i;
+ struct drm_i915_private *i915 = kdev_minor_to_i915(dev);
+
+ for_each_gt(gt, i915, i) {
+ ret = func(gt, val);
+ if (ret)
+ break;
+ }
+ } else {
+ gt = intel_gt_sysfs_get_drvdata(dev, attr->attr.name);
+ ret = func(gt, val);
+ }
+
+ return ret;
+}
+
+static u32
+sysfs_gt_attribute_r_func(struct device *dev, struct device_attribute *attr,
+ u32 (func)(struct intel_gt *gt),
+ enum intel_gt_sysfs_op op)
+{
+ struct intel_gt *gt;
+ u32 ret;
+
+ ret = (op == INTEL_GT_SYSFS_MAX) ? 0 : (u32) -1;
+
+ if (!is_object_gt(&dev->kobj)) {
+ int i;
+ struct drm_i915_private *i915 = kdev_minor_to_i915(dev);
+
+ for_each_gt(gt, i915, i) {
+ u32 val = func(gt);
+
+ switch (op) {
+ case INTEL_GT_SYSFS_MIN:
+ if (val < ret)
+ ret = val;
+ break;
+
+ case INTEL_GT_SYSFS_MAX:
+ if (val > ret)
+ ret = val;
+ break;
+ }
+ }
+ } else {
+ gt = intel_gt_sysfs_get_drvdata(dev, attr->attr.name);
+ ret = func(gt);
+ }
+
+ return ret;
+}
+
+/* RC6 interfaces will show the minimum RC6 residency value */
+#define sysfs_gt_attribute_r_min_func(d, a, f) \
+ sysfs_gt_attribute_r_func(d, a, f, INTEL_GT_SYSFS_MIN)
+
+/* Frequency interfaces will show the maximum frequency value */
+#define sysfs_gt_attribute_r_max_func(d, a, f) \
+ sysfs_gt_attribute_r_func(d, a, f, INTEL_GT_SYSFS_MAX)
+
+static u32 get_residency(struct intel_gt *gt, i915_reg_t reg)
+{
+ intel_wakeref_t wakeref;
+ u64 res = 0;
+
+ with_intel_runtime_pm(gt->uncore->rpm, wakeref)
+ res = intel_rc6_residency_us(>->rc6, reg);
+
+ return DIV_ROUND_CLOSEST_ULL(res, 1000);
+}
+
+static ssize_t rc6_enable_show(struct device *dev,
+ struct device_attribute *attr,
+ char *buff)
+{
+ struct intel_gt *gt = intel_gt_sysfs_get_drvdata(dev, attr->attr.name);
+ u8 mask = 0;
+
+ if (HAS_RC6(gt->i915))
+ mask |= BIT(0);
+ if (HAS_RC6p(gt->i915))
+ mask |= BIT(1);
+ if (HAS_RC6pp(gt->i915))
+ mask |= BIT(2);
+
+ return sysfs_emit(buff, "%x\n", mask);
+}
+
+static u32 __rc6_residency_ms_show(struct intel_gt *gt)
+{
+ return get_residency(gt, GEN6_GT_GFX_RC6);
+}
+
+static ssize_t rc6_residency_ms_show(struct device *dev,
+ struct device_attribute *attr,
+ char *buff)
+{
+ u32 rc6_residency = sysfs_gt_attribute_r_min_func(dev, attr,
+ __rc6_residency_ms_show);
+
+ return sysfs_emit(buff, "%u\n", rc6_residency);
+}
+
+static u32 __rc6p_residency_ms_show(struct intel_gt *gt)
+{
+ return get_residency(gt, GEN6_GT_GFX_RC6p);
+}
+
+static ssize_t rc6p_residency_ms_show(struct device *dev,
+ struct device_attribute *attr,
+ char *buff)
+{
+ u32 rc6p_residency = sysfs_gt_attribute_r_min_func(dev, attr,
+ __rc6p_residency_ms_show);
+
+ return sysfs_emit(buff, "%u\n", rc6p_residency);
+}
+
+static u32 __rc6pp_residency_ms_show(struct intel_gt *gt)
+{
+ return get_residency(gt, GEN6_GT_GFX_RC6pp);
+}
+
+static ssize_t rc6pp_residency_ms_show(struct device *dev,
+ struct device_attribute *attr,
+ char *buff)
+{
+ u32 rc6pp_residency = sysfs_gt_attribute_r_min_func(dev, attr,
+ __rc6pp_residency_ms_show);
+
+ return sysfs_emit(buff, "%u\n", rc6pp_residency);
+}
+
+static u32 __media_rc6_residency_ms_show(struct intel_gt *gt)
+{
+ return get_residency(gt, VLV_GT_MEDIA_RC6);
+}
+
+static ssize_t media_rc6_residency_ms_show(struct device *dev,
+ struct device_attribute *attr,
+ char *buff)
+{
+ u32 rc6_residency = sysfs_gt_attribute_r_min_func(dev, attr,
+ __media_rc6_residency_ms_show);
+
+ return sysfs_emit(buff, "%u\n", rc6_residency);
+}
+
+static DEVICE_ATTR_RO(rc6_enable);
+static DEVICE_ATTR_RO(rc6_residency_ms);
+static DEVICE_ATTR_RO(rc6p_residency_ms);
+static DEVICE_ATTR_RO(rc6pp_residency_ms);
+static DEVICE_ATTR_RO(media_rc6_residency_ms);
+
+static struct attribute *rc6_attrs[] = {
+ &dev_attr_rc6_enable.attr,
+ &dev_attr_rc6_residency_ms.attr,
+ NULL
+};
+
+static struct attribute *rc6p_attrs[] = {
+ &dev_attr_rc6p_residency_ms.attr,
+ &dev_attr_rc6pp_residency_ms.attr,
+ NULL
+};
+
+static struct attribute *media_rc6_attrs[] = {
+ &dev_attr_media_rc6_residency_ms.attr,
+ NULL
+};
+
+static const struct attribute_group rc6_attr_group[] = {
+ { .attrs = rc6_attrs, },
+ { .name = power_group_name, .attrs = rc6_attrs, },
+};
+
+static const struct attribute_group rc6p_attr_group[] = {
+ { .attrs = rc6p_attrs, },
+ { .name = power_group_name, .attrs = rc6p_attrs, },
+};
+
+static const struct attribute_group media_rc6_attr_group[] = {
+ { .attrs = media_rc6_attrs, },
+ { .name = power_group_name, .attrs = media_rc6_attrs, },
+};
+
+static int __intel_gt_sysfs_create_group(struct kobject *kobj,
+ const struct attribute_group *grp)
+{
+ return is_object_gt(kobj) ?
+ sysfs_create_group(kobj, &grp[0]) :
+ sysfs_merge_group(kobj, &grp[1]);
+}
+
+static void intel_sysfs_rc6_init(struct intel_gt *gt, struct kobject *kobj)
+{
+ int ret;
+
+ if (!HAS_RC6(gt->i915))
+ return;
+
+ ret = __intel_gt_sysfs_create_group(kobj, rc6_attr_group);
+ if (ret)
+ drm_warn(>->i915->drm,
+ "failed to create gt%u RC6 sysfs files (%pe)\n",
+ gt->info.id, ERR_PTR(ret));
+
+ /*
+ * cannot use the is_visible() attribute because
+ * the upper object inherits from the parent group.
+ */
+ if (HAS_RC6p(gt->i915)) {
+ ret = __intel_gt_sysfs_create_group(kobj, rc6p_attr_group);
+ if (ret)
+ drm_warn(>->i915->drm,
+ "failed to create gt%u RC6p sysfs files (%pe)\n",
+ gt->info.id, ERR_PTR(ret));
+ }
+
+ if (IS_VALLEYVIEW(gt->i915) || IS_CHERRYVIEW(gt->i915)) {
+ ret = __intel_gt_sysfs_create_group(kobj, media_rc6_attr_group);
+ if (ret)
+ drm_warn(>->i915->drm,
+ "failed to create media %u RC6 sysfs files (%pe)\n",
+ gt->info.id, ERR_PTR(ret));
+ }
+}
+#else
+static void intel_sysfs_rc6_init(struct intel_gt *gt, struct kobject *kobj)
+{
+}
+#endif /* CONFIG_PM */
+
+static u32 __act_freq_mhz_show(struct intel_gt *gt)
+{
+ return intel_rps_read_actual_frequency(>->rps);
+}
+
+static ssize_t act_freq_mhz_show(struct device *dev,
+ struct device_attribute *attr, char *buff)
+{
+ u32 actual_freq = sysfs_gt_attribute_r_max_func(dev, attr,
+ __act_freq_mhz_show);
+
+ return sysfs_emit(buff, "%u\n", actual_freq);
+}
+
+static u32 __cur_freq_mhz_show(struct intel_gt *gt)
+{
+ return intel_rps_get_requested_frequency(>->rps);
+}
+
+static ssize_t cur_freq_mhz_show(struct device *dev,
+ struct device_attribute *attr, char *buff)
+{
+ u32 cur_freq = sysfs_gt_attribute_r_max_func(dev, attr,
+ __cur_freq_mhz_show);
+
+ return sysfs_emit(buff, "%u\n", cur_freq);
+}
+
+static u32 __boost_freq_mhz_show(struct intel_gt *gt)
+{
+ return intel_rps_get_boost_frequency(>->rps);
+}
+
+static ssize_t boost_freq_mhz_show(struct device *dev,
+ struct device_attribute *attr,
+ char *buff)
+{
+ u32 boost_freq = sysfs_gt_attribute_r_max_func(dev, attr,
+ __boost_freq_mhz_show);
+
+ return sysfs_emit(buff, "%u\n", boost_freq);
+}
+
+static int __boost_freq_mhz_store(struct intel_gt *gt, u32 val)
+{
+ return intel_rps_set_boost_frequency(>->rps, val);
+}
+
+static ssize_t boost_freq_mhz_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buff, size_t count)
+{
+ ssize_t ret;
+ u32 val;
+
+ ret = kstrtou32(buff, 0, &val);
+ if (ret)
+ return ret;
+
+ return sysfs_gt_attribute_w_func(dev, attr,
+ __boost_freq_mhz_store, val) ?: count;
+}
+
+static u32 __rp0_freq_mhz_show(struct intel_gt *gt)
+{
+ return intel_rps_get_rp0_frequency(>->rps);
+}
+
+static ssize_t RP0_freq_mhz_show(struct device *dev,
+ struct device_attribute *attr, char *buff)
+{
+ u32 rp0_freq = sysfs_gt_attribute_r_max_func(dev, attr,
+ __rp0_freq_mhz_show);
+
+ return sysfs_emit(buff, "%u\n", rp0_freq);
+}
+
+static u32 __rp1_freq_mhz_show(struct intel_gt *gt)
+{
+ return intel_rps_get_rp1_frequency(>->rps);
+}
+
+static ssize_t RP1_freq_mhz_show(struct device *dev,
+ struct device_attribute *attr, char *buff)
+{
+ u32 rp1_freq = sysfs_gt_attribute_r_max_func(dev, attr,
+ __rp1_freq_mhz_show);
+
+ return sysfs_emit(buff, "%u\n", rp1_freq);
+}
+
+static u32 __rpn_freq_mhz_show(struct intel_gt *gt)
+{
+ return intel_rps_get_rpn_frequency(>->rps);
+}
+
+static ssize_t RPn_freq_mhz_show(struct device *dev,
+ struct device_attribute *attr, char *buff)
+{
+ u32 rpn_freq = sysfs_gt_attribute_r_max_func(dev, attr,
+ __rpn_freq_mhz_show);
+
+ return sysfs_emit(buff, "%u\n", rpn_freq);
+}
+
+static u32 __max_freq_mhz_show(struct intel_gt *gt)
+{
+ return intel_rps_get_max_frequency(>->rps);
+}
+
+static ssize_t max_freq_mhz_show(struct device *dev,
+ struct device_attribute *attr, char *buff)
+{
+ u32 max_freq = sysfs_gt_attribute_r_max_func(dev, attr,
+ __max_freq_mhz_show);
+
+ return sysfs_emit(buff, "%u\n", max_freq);
+}
+
+static int __set_max_freq(struct intel_gt *gt, u32 val)
+{
+ return intel_rps_set_max_frequency(>->rps, val);
+}
+
+static ssize_t max_freq_mhz_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buff, size_t count)
+{
+ int ret;
+ u32 val;
+
+ ret = kstrtou32(buff, 0, &val);
+ if (ret)
+ return ret;
+
+ ret = sysfs_gt_attribute_w_func(dev, attr, __set_max_freq, val);
+
+ return ret ?: count;
+}
+
+static u32 __min_freq_mhz_show(struct intel_gt *gt)
+{
+ return intel_rps_get_min_frequency(>->rps);
+}
+
+static ssize_t min_freq_mhz_show(struct device *dev,
+ struct device_attribute *attr, char *buff)
+{
+ u32 min_freq = sysfs_gt_attribute_r_min_func(dev, attr,
+ __min_freq_mhz_show);
+
+ return sysfs_emit(buff, "%u\n", min_freq);
+}
+
+static int __set_min_freq(struct intel_gt *gt, u32 val)
+{
+ return intel_rps_set_min_frequency(>->rps, val);
+}
+
+static ssize_t min_freq_mhz_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buff, size_t count)
+{
+ int ret;
+ u32 val;
+
+ ret = kstrtou32(buff, 0, &val);
+ if (ret)
+ return ret;
+
+ ret = sysfs_gt_attribute_w_func(dev, attr, __set_min_freq, val);
+
+ return ret ?: count;
+}
+
+static u32 __vlv_rpe_freq_mhz_show(struct intel_gt *gt)
+{
+ struct intel_rps *rps = >->rps;
+
+ return intel_gpu_freq(rps, rps->efficient_freq);
+}
+
+static ssize_t vlv_rpe_freq_mhz_show(struct device *dev,
+ struct device_attribute *attr, char *buff)
+{
+ u32 rpe_freq = sysfs_gt_attribute_r_max_func(dev, attr,
+ __vlv_rpe_freq_mhz_show);
+
+ return sysfs_emit(buff, "%u\n", rpe_freq);
+}
+
+#define INTEL_GT_RPS_SYSFS_ATTR(_name, _mode, _show, _store) \
+ struct device_attribute dev_attr_gt_##_name = __ATTR(gt_##_name, _mode, _show, _store); \
+ struct device_attribute dev_attr_rps_##_name = __ATTR(rps_##_name, _mode, _show, _store)
+
+#define INTEL_GT_RPS_SYSFS_ATTR_RO(_name) \
+ INTEL_GT_RPS_SYSFS_ATTR(_name, 0444, _name##_show, NULL)
+#define INTEL_GT_RPS_SYSFS_ATTR_RW(_name) \
+ INTEL_GT_RPS_SYSFS_ATTR(_name, 0644, _name##_show, _name##_store)
+
+static INTEL_GT_RPS_SYSFS_ATTR_RO(act_freq_mhz);
+static INTEL_GT_RPS_SYSFS_ATTR_RO(cur_freq_mhz);
+static INTEL_GT_RPS_SYSFS_ATTR_RW(boost_freq_mhz);
+static INTEL_GT_RPS_SYSFS_ATTR_RO(RP0_freq_mhz);
+static INTEL_GT_RPS_SYSFS_ATTR_RO(RP1_freq_mhz);
+static INTEL_GT_RPS_SYSFS_ATTR_RO(RPn_freq_mhz);
+static INTEL_GT_RPS_SYSFS_ATTR_RW(max_freq_mhz);
+static INTEL_GT_RPS_SYSFS_ATTR_RW(min_freq_mhz);
+
+static DEVICE_ATTR_RO(vlv_rpe_freq_mhz);
+
+#define GEN6_ATTR(s) { \
+ &dev_attr_##s##_act_freq_mhz.attr, \
+ &dev_attr_##s##_cur_freq_mhz.attr, \
+ &dev_attr_##s##_boost_freq_mhz.attr, \
+ &dev_attr_##s##_max_freq_mhz.attr, \
+ &dev_attr_##s##_min_freq_mhz.attr, \
+ &dev_attr_##s##_RP0_freq_mhz.attr, \
+ &dev_attr_##s##_RP1_freq_mhz.attr, \
+ &dev_attr_##s##_RPn_freq_mhz.attr, \
+ NULL, \
+ }
+
+#define GEN6_RPS_ATTR GEN6_ATTR(rps)
+#define GEN6_GT_ATTR GEN6_ATTR(gt)
+
+static const struct attribute * const gen6_rps_attrs[] = GEN6_RPS_ATTR;
+static const struct attribute * const gen6_gt_attrs[] = GEN6_GT_ATTR;
+
+static ssize_t punit_req_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 preq = intel_rps_read_punit_req_frequency(>->rps);
+
+ return sysfs_emit(buff, "%u\n", preq);
+}
+
+struct intel_gt_bool_throttle_attr {
+ struct attribute attr;
+ ssize_t (*show)(struct device *dev, struct device_attribute *attr,
+ char *buf);
+ i915_reg_t reg32;
+ u32 mask;
+};
+
+static ssize_t throttle_reason_bool_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_gt_bool_throttle_attr *t_attr =
+ (struct intel_gt_bool_throttle_attr *) attr;
+ bool val = rps_read_mask_mmio(>->rps, t_attr->reg32, t_attr->mask);
+
+ return sysfs_emit(buff, "%u\n", val);
+}
+
+#define INTEL_GT_RPS_BOOL_ATTR_RO(sysfs_func__, mask__) \
+struct intel_gt_bool_throttle_attr attr_##sysfs_func__ = { \
+ .attr = { .name = __stringify(sysfs_func__), .mode = 0444 }, \
+ .show = throttle_reason_bool_show, \
+ .reg32 = GT0_PERF_LIMIT_REASONS, \
+ .mask = mask__, \
+}
+
+static DEVICE_ATTR_RO(punit_req_freq_mhz);
+static INTEL_GT_RPS_BOOL_ATTR_RO(throttle_reason_status, GT0_PERF_LIMIT_REASONS_MASK);
+static INTEL_GT_RPS_BOOL_ATTR_RO(throttle_reason_pl1, POWER_LIMIT_1_MASK);
+static INTEL_GT_RPS_BOOL_ATTR_RO(throttle_reason_pl2, POWER_LIMIT_2_MASK);
+static INTEL_GT_RPS_BOOL_ATTR_RO(throttle_reason_pl4, POWER_LIMIT_4_MASK);
+static INTEL_GT_RPS_BOOL_ATTR_RO(throttle_reason_thermal, THERMAL_LIMIT_MASK);
+static INTEL_GT_RPS_BOOL_ATTR_RO(throttle_reason_prochot, PROCHOT_MASK);
+static INTEL_GT_RPS_BOOL_ATTR_RO(throttle_reason_ratl, RATL_MASK);
+static INTEL_GT_RPS_BOOL_ATTR_RO(throttle_reason_vr_thermalert, VR_THERMALERT_MASK);
+static INTEL_GT_RPS_BOOL_ATTR_RO(throttle_reason_vr_tdc, VR_TDC_MASK);
+
+static const struct attribute *freq_attrs[] = {
+ &dev_attr_punit_req_freq_mhz.attr,
+ &attr_throttle_reason_status.attr,
+ &attr_throttle_reason_pl1.attr,
+ &attr_throttle_reason_pl2.attr,
+ &attr_throttle_reason_pl4.attr,
+ &attr_throttle_reason_thermal.attr,
+ &attr_throttle_reason_prochot.attr,
+ &attr_throttle_reason_ratl.attr,
+ &attr_throttle_reason_vr_thermalert.attr,
+ &attr_throttle_reason_vr_tdc.attr,
+ NULL
+};
+
+static int intel_sysfs_rps_init(struct intel_gt *gt, struct kobject *kobj,
+ const struct attribute * const *attrs)
+{
+ int ret;
+
+ if (GRAPHICS_VER(gt->i915) < 6)
+ return 0;
+
+ ret = sysfs_create_files(kobj, attrs);
+ if (ret)
+ return ret;
+
+ if (IS_VALLEYVIEW(gt->i915) || IS_CHERRYVIEW(gt->i915))
+ ret = sysfs_create_file(kobj, &dev_attr_vlv_rpe_freq_mhz.attr);
+
+ return ret;
+}
+
+void intel_gt_sysfs_pm_init(struct intel_gt *gt, struct kobject *kobj)
+{
+ int ret;
+
+ intel_sysfs_rc6_init(gt, kobj);
+
+ ret = is_object_gt(kobj) ?
+ intel_sysfs_rps_init(gt, kobj, gen6_rps_attrs) :
+ intel_sysfs_rps_init(gt, kobj, gen6_gt_attrs);
+ if (ret)
+ drm_warn(>->i915->drm,
+ "failed to create gt%u RPS sysfs files (%pe)",
+ gt->info.id, ERR_PTR(ret));
+
+ /* end of the legacy interfaces */
+ if (!is_object_gt(kobj))
+ return;
+
+ ret = sysfs_create_files(kobj, freq_attrs);
+ if (ret)
+ drm_warn(>->i915->drm,
+ "failed to create gt%u throttle sysfs files (%pe)",
+ gt->info.id, ERR_PTR(ret));
+}
--- /dev/null
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2022 Intel Corporation
+ */
+
+#ifndef __SYSFS_GT_PM_H__
+#define __SYSFS_GT_PM_H__
+
+#include <linux/kobject.h>
+
+#include "intel_gt_types.h"
+
+void intel_gt_sysfs_pm_init(struct intel_gt *gt, struct kobject *kobj);
+
+#endif /* SYSFS_RC6_H */
#include "i915_vma.h"
#include "intel_engine_types.h"
#include "intel_gt_buffer_pool_types.h"
+#include "intel_hwconfig.h"
#include "intel_llc_types.h"
#include "intel_reset_types.h"
#include "intel_rc6_types.h"
const struct intel_mmio_range *steering_table[NUM_STEERING_TYPES];
+ struct {
+ u8 groupid;
+ u8 instanceid;
+ } default_steering;
+
+ /*
+ * Base of per-tile GTTMMADR where we can derive the MMIO and the GGTT.
+ */
+ phys_addr_t phys_addr;
+
struct intel_gt_info {
+ unsigned int id;
+
intel_engine_mask_t engine_mask;
u32 l3bank_mask;
struct sseu_dev_info sseu;
unsigned long mslice_mask;
+
+ /** @hwconfig: hardware configuration data */
+ struct intel_hwconfig hwconfig;
} info;
struct {
return 0;
}
-void __i915_vm_close(struct i915_address_space *vm)
+static void clear_vm_list(struct list_head *list)
{
struct i915_vma *vma, *vn;
- if (!atomic_dec_and_mutex_lock(&vm->open, &vm->mutex))
- return;
-
- list_for_each_entry_safe(vma, vn, &vm->bound_list, vm_link) {
+ list_for_each_entry_safe(vma, vn, list, vm_link) {
struct drm_i915_gem_object *obj = vma->obj;
- if (!kref_get_unless_zero(&obj->base.refcount)) {
+ if (!i915_gem_object_get_rcu(obj)) {
/*
- * Unbind the dying vma to ensure the bound_list
+ * Object is dying, but has not yet cleared its
+ * vma list.
+ * Unbind the dying vma to ensure our list
* is completely drained. We leave the destruction to
- * the object destructor.
+ * the object destructor to avoid the vma
+ * disappearing under it.
*/
atomic_and(~I915_VMA_PIN_MASK, &vma->flags);
WARN_ON(__i915_vma_unbind(vma));
- continue;
+
+ /* Remove from the unbound list */
+ list_del_init(&vma->vm_link);
+
+ /*
+ * Delay the vm and vm mutex freeing until the
+ * object is done with destruction.
+ */
+ i915_vm_resv_get(vma->vm);
+ vma->vm_ddestroy = true;
+ } else {
+ i915_vma_destroy_locked(vma);
+ i915_gem_object_put(obj);
}
- /* Keep the obj (and hence the vma) alive as _we_ destroy it */
- i915_vma_destroy_locked(vma);
- i915_gem_object_put(obj);
}
+}
+
+static void __i915_vm_close(struct i915_address_space *vm)
+{
+ mutex_lock(&vm->mutex);
+
+ clear_vm_list(&vm->bound_list);
+ clear_vm_list(&vm->unbound_list);
+
+ /* Check for must-fix unanticipated side-effects */
GEM_BUG_ON(!list_empty(&vm->bound_list));
+ GEM_BUG_ON(!list_empty(&vm->unbound_list));
mutex_unlock(&vm->mutex);
}
void i915_address_space_fini(struct i915_address_space *vm)
{
drm_mm_takedown(&vm->mm);
- mutex_destroy(&vm->mutex);
}
/**
* @kref: Pointer to the &i915_address_space.resv_ref member.
*
* This function is called when the last lock sharer no longer shares the
- * &i915_address_space._resv lock.
+ * &i915_address_space._resv lock, and also if we raced when
+ * destroying a vma by the vma destruction
*/
void i915_vm_resv_release(struct kref *kref)
{
container_of(kref, typeof(*vm), resv_ref);
dma_resv_fini(&vm->_resv);
+ mutex_destroy(&vm->mutex);
+
kfree(vm);
}
struct i915_address_space *vm =
container_of(work, struct i915_address_space, release_work);
+ __i915_vm_close(vm);
+
/* Synchronize async unbinds. */
i915_vma_resource_bind_dep_sync_all(vm);
vm->pending_unbind = RB_ROOT_CACHED;
INIT_WORK(&vm->release_work, __i915_vm_release);
- atomic_set(&vm->open, 1);
/*
* The vm->mutex must be reclaim safe (for use in the shrinker).
vm->mm.head_node.color = I915_COLOR_UNEVICTABLE;
INIT_LIST_HEAD(&vm->bound_list);
+ INIT_LIST_HEAD(&vm->unbound_list);
}
void *__px_vaddr(struct drm_i915_gem_object *p)
void *vaddr = __px_vaddr(p);
memset64(vaddr, val, count);
- clflush_cache_range(vaddr, PAGE_SIZE);
+ drm_clflush_virt_range(vaddr, PAGE_SIZE);
}
static void poison_scratch_page(struct drm_i915_gem_object *scratch)
unsigned int bind_async_flags;
- /*
- * Each active user context has its own address space (in full-ppgtt).
- * Since the vm may be shared between multiple contexts, we count how
- * many contexts keep us "open". Once open hits zero, we are closed
- * and do not allow any new attachments, and proceed to shutdown our
- * vma and page directories.
- */
- atomic_t open;
-
struct mutex mutex; /* protects vma and our lists */
struct kref resv_ref; /* kref to keep the reservation lock alive. */
*/
struct list_head bound_list;
+ /**
+ * List of vmas not yet bound or evicted.
+ */
+ struct list_head unbound_list;
+
/* Global GTT */
bool is_ggtt:1;
/* Some systems support read-only mappings for GGTT and/or PPGTT */
bool has_read_only:1;
+ /* Skip pte rewrite on unbind for suspend. Protected by @mutex */
+ bool skip_pte_rewrite:1;
+
u8 top;
u8 pd_shift;
u8 scratch_order;
return vm;
}
+static inline struct i915_address_space *
+i915_vm_tryget(struct i915_address_space *vm)
+{
+ return kref_get_unless_zero(&vm->ref) ? vm : NULL;
+}
+
+static inline void assert_vm_alive(struct i915_address_space *vm)
+{
+ GEM_BUG_ON(!kref_read(&vm->ref));
+}
+
/**
* i915_vm_resv_get - Obtain a reference on the vm's reservation lock
* @vm: The vm whose reservation lock we want to share.
kref_put(&vm->resv_ref, i915_vm_resv_release);
}
-static inline struct i915_address_space *
-i915_vm_open(struct i915_address_space *vm)
-{
- GEM_BUG_ON(!atomic_read(&vm->open));
- atomic_inc(&vm->open);
- return i915_vm_get(vm);
-}
-
-static inline bool
-i915_vm_tryopen(struct i915_address_space *vm)
-{
- if (atomic_add_unless(&vm->open, 1, 0))
- return i915_vm_get(vm);
-
- return false;
-}
-
-void __i915_vm_close(struct i915_address_space *vm);
-
-static inline void
-i915_vm_close(struct i915_address_space *vm)
-{
- GEM_BUG_ON(!atomic_read(&vm->open));
- __i915_vm_close(vm);
-
- i915_vm_put(vm);
-}
-
void i915_address_space_init(struct i915_address_space *vm, int subclass);
void i915_address_space_fini(struct i915_address_space *vm);
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);
+void intel_ggtt_unbind_vma(struct i915_address_space *vm,
+ 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);
int i915_ggtt_enable_hw(struct drm_i915_private *i915);
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,
--- /dev/null
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2022 Intel Corporation
+ */
+
+#ifndef _INTEL_HWCONFIG_H_
+#define _INTEL_HWCONFIG_H_
+
+#include <linux/types.h>
+
+struct intel_gt;
+
+struct intel_hwconfig {
+ u32 size;
+ void *ptr;
+};
+
+int intel_gt_init_hwconfig(struct intel_gt *gt);
+void intel_gt_fini_hwconfig(struct intel_gt *gt);
+
+#endif /* _INTEL_HWCONFIG_H_ */
CTX_CTRL_RS_CTX_ENABLE);
regs[CTX_CONTEXT_CONTROL] = ctl;
- regs[CTX_TIMESTAMP] = ce->runtime.last;
+ regs[CTX_TIMESTAMP] = ce->stats.runtime.last;
}
static void init_wa_bb_regs(u32 * const regs,
IS_DG2_G11(ce->engine->i915))
cs = gen8_emit_pipe_control(cs, PIPE_CONTROL_INSTRUCTION_CACHE_INVALIDATE, 0);
+ /* hsdes: 1809175790 */
+ if (!HAS_FLAT_CCS(ce->engine->i915))
+ cs = gen12_emit_aux_table_inv(cs, GEN12_GFX_CCS_AUX_NV);
+
return cs;
}
PIPE_CONTROL_INSTRUCTION_CACHE_INVALIDATE,
0);
+ /* hsdes: 1809175790 */
+ if (!HAS_FLAT_CCS(ce->engine->i915)) {
+ if (ce->engine->class == VIDEO_DECODE_CLASS)
+ cs = gen12_emit_aux_table_inv(cs, GEN12_VD0_AUX_NV);
+ else if (ce->engine->class == VIDEO_ENHANCEMENT_CLASS)
+ cs = gen12_emit_aux_table_inv(cs, GEN12_VE0_AUX_NV);
+ }
+
return cs;
}
}
}
-static void st_update_runtime_underflow(struct intel_context *ce, s32 dt)
+static void st_runtime_underflow(struct intel_context_stats *stats, s32 dt)
{
#if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
- ce->runtime.num_underflow++;
- ce->runtime.max_underflow = max_t(u32, ce->runtime.max_underflow, -dt);
+ stats->runtime.num_underflow++;
+ stats->runtime.max_underflow =
+ max_t(u32, stats->runtime.max_underflow, -dt);
#endif
}
void lrc_update_runtime(struct intel_context *ce)
{
+ struct intel_context_stats *stats = &ce->stats;
u32 old;
s32 dt;
- if (intel_context_is_barrier(ce))
+ old = stats->runtime.last;
+ stats->runtime.last = lrc_get_runtime(ce);
+ dt = stats->runtime.last - old;
+ if (!dt)
return;
- old = ce->runtime.last;
- ce->runtime.last = lrc_get_runtime(ce);
- dt = ce->runtime.last - old;
-
if (unlikely(dt < 0)) {
CE_TRACE(ce, "runtime underflow: last=%u, new=%u, delta=%d\n",
- old, ce->runtime.last, dt);
- st_update_runtime_underflow(ce, dt);
+ old, stats->runtime.last, dt);
+ st_runtime_underflow(stats, dt);
return;
}
- ewma_runtime_add(&ce->runtime.avg, dt);
- ce->runtime.total += dt;
+ ewma_runtime_add(&stats->runtime.avg, dt);
+ stats->runtime.total += dt;
}
#if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
#include <linux/bitfield.h>
#include <linux/types.h>
+#include "intel_context.h"
+
struct drm_i915_gem_object;
struct i915_gem_ww_ctx;
-struct intel_context;
struct intel_engine_cs;
struct intel_ring;
struct kref;
return GEN12_CTX_PRIORITY_NORMAL;
}
+static inline void lrc_runtime_start(struct intel_context *ce)
+{
+ struct intel_context_stats *stats = &ce->stats;
+
+ if (intel_context_is_barrier(ce))
+ return;
+
+ if (stats->active)
+ return;
+
+ WRITE_ONCE(stats->active, intel_context_clock());
+}
+
+static inline void lrc_runtime_stop(struct intel_context *ce)
+{
+ struct intel_context_stats *stats = &ce->stats;
+
+ if (!stats->active)
+ return;
+
+ lrc_update_runtime(ce);
+ WRITE_ONCE(stats->active, 0);
+}
+
#endif /* __INTEL_LRC_H__ */
int err;
GEM_BUG_ON(ce->vm != ce->engine->gt->migrate.context->vm);
+ GEM_BUG_ON(IS_DGFX(ce->engine->i915) && (!src_is_lmem && !dst_is_lmem));
*out = NULL;
GEM_BUG_ON(ce->ring->size < SZ_64K);
src_offset = 0;
dst_offset = CHUNK_SZ;
if (HAS_64K_PAGES(ce->engine->i915)) {
- GEM_BUG_ON(!src_is_lmem && !dst_is_lmem);
-
src_offset = 0;
dst_offset = 0;
if (src_is_lmem)
u64 * const vaddr = __px_vaddr(pdma);
vaddr[idx] = encoded_entry;
- clflush_cache_range(&vaddr[idx], sizeof(u64));
+ drm_clflush_virt_range(&vaddr[idx], sizeof(u64));
}
void
#include <linux/pm_runtime.h>
+#include "gem/i915_gem_region.h"
#include "i915_drv.h"
#include "i915_reg.h"
#include "i915_vgpu.h"
resource_size_t pcbr_offset;
pcbr_offset = (pcbr & ~4095) - i915->dsm.start;
- pctx = i915_gem_object_create_stolen_for_preallocated(i915,
- pcbr_offset,
- pctx_size);
+ pctx = i915_gem_object_create_region_at(i915->mm.stolen_region,
+ pcbr_offset,
+ pctx_size,
+ 0);
if (IS_ERR(pctx))
return PTR_ERR(pctx);
struct intel_memory_region *mem;
resource_size_t min_page_size;
resource_size_t io_start;
+ resource_size_t io_size;
resource_size_t lmem_size;
int err;
lmem_size = intel_uncore_read64(&i915->uncore, GEN12_GSMBASE);
}
+ if (i915->params.lmem_size > 0) {
+ lmem_size = min_t(resource_size_t, lmem_size,
+ mul_u32_u32(i915->params.lmem_size, SZ_1M));
+ }
io_start = pci_resource_start(pdev, 2);
- if (GEM_WARN_ON(lmem_size > pci_resource_len(pdev, 2)))
+ io_size = min(pci_resource_len(pdev, 2), lmem_size);
+ if (!io_size)
return ERR_PTR(-ENODEV);
min_page_size = HAS_64K_PAGES(i915) ? I915_GTT_PAGE_SIZE_64K :
lmem_size,
min_page_size,
io_start,
- lmem_size,
+ io_size,
INTEL_MEMORY_LOCAL,
0,
&intel_region_lmem_ops);
engine_mask &= gt->info.engine_mask;
if (flags & I915_ERROR_CAPTURE) {
- i915_capture_error_state(gt, engine_mask);
+ i915_capture_error_state(gt, engine_mask, CORE_DUMP_FLAG_NONE);
intel_gt_clear_error_registers(gt, engine_mask);
}
if (GRAPHICS_VER(i915) == 7) {
if (num_engines) {
struct intel_engine_cs *signaller;
- i915_reg_t last_reg = {}; /* keep gcc quiet */
+ i915_reg_t last_reg = INVALID_MMIO_REG; /* keep gcc quiet */
*cs++ = MI_LOAD_REGISTER_IMM(num_engines);
for_each_engine(signaller, engine->gt, id) {
return 0;
}
-static void gen6_rps_init(struct intel_rps *rps)
+static u32 intel_rps_read_state_cap(struct intel_rps *rps)
{
struct drm_i915_private *i915 = rps_to_i915(rps);
- u32 rp_state_cap = intel_rps_read_state_cap(rps);
+ struct intel_uncore *uncore = rps_to_uncore(rps);
- /* All of these values are in units of 50MHz */
+ 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);
+ else
+ return intel_uncore_read(uncore, GEN6_RP_STATE_CAP);
+}
+
+/**
+ * gen6_rps_get_freq_caps - Get freq caps exposed by HW
+ * @rps: the intel_rps structure
+ * @caps: returned freq caps
+ *
+ * Returned "caps" frequencies should be converted to MHz using
+ * intel_gpu_freq()
+ */
+void gen6_rps_get_freq_caps(struct intel_rps *rps, struct intel_rps_freq_caps *caps)
+{
+ struct drm_i915_private *i915 = rps_to_i915(rps);
+ u32 rp_state_cap;
+
+ rp_state_cap = intel_rps_read_state_cap(rps);
/* static values from HW: RP0 > RP1 > RPn (min_freq) */
if (IS_GEN9_LP(i915)) {
- rps->rp0_freq = (rp_state_cap >> 16) & 0xff;
- rps->rp1_freq = (rp_state_cap >> 8) & 0xff;
- rps->min_freq = (rp_state_cap >> 0) & 0xff;
+ caps->rp0_freq = (rp_state_cap >> 16) & 0xff;
+ caps->rp1_freq = (rp_state_cap >> 8) & 0xff;
+ caps->min_freq = (rp_state_cap >> 0) & 0xff;
} else {
- rps->rp0_freq = (rp_state_cap >> 0) & 0xff;
- rps->rp1_freq = (rp_state_cap >> 8) & 0xff;
- rps->min_freq = (rp_state_cap >> 16) & 0xff;
+ caps->rp0_freq = (rp_state_cap >> 0) & 0xff;
+ caps->rp1_freq = (rp_state_cap >> 8) & 0xff;
+ caps->min_freq = (rp_state_cap >> 16) & 0xff;
}
+ if (IS_GEN9_BC(i915) || GRAPHICS_VER(i915) >= 11) {
+ /*
+ * In this case rp_state_cap register reports frequencies in
+ * units of 50 MHz. Convert these to the actual "hw unit", i.e.
+ * units of 16.67 MHz
+ */
+ caps->rp0_freq *= GEN9_FREQ_SCALER;
+ caps->rp1_freq *= GEN9_FREQ_SCALER;
+ caps->min_freq *= GEN9_FREQ_SCALER;
+ }
+}
+
+static void gen6_rps_init(struct intel_rps *rps)
+{
+ struct drm_i915_private *i915 = rps_to_i915(rps);
+ struct intel_rps_freq_caps caps;
+
+ gen6_rps_get_freq_caps(rps, &caps);
+ rps->rp0_freq = caps.rp0_freq;
+ rps->rp1_freq = caps.rp1_freq;
+ rps->min_freq = caps.min_freq;
+
/* hw_max = RP0 until we check for overclocking */
rps->max_freq = rps->rp0_freq;
if (IS_HASWELL(i915) || IS_BROADWELL(i915) ||
IS_GEN9_BC(i915) || GRAPHICS_VER(i915) >= 11) {
u32 ddcc_status = 0;
+ u32 mult = 1;
+ if (IS_GEN9_BC(i915) || GRAPHICS_VER(i915) >= 11)
+ mult = GEN9_FREQ_SCALER;
if (snb_pcode_read(i915, HSW_PCODE_DYNAMIC_DUTY_CYCLE_CONTROL,
&ddcc_status, NULL) == 0)
rps->efficient_freq =
- clamp_t(u8,
- (ddcc_status >> 8) & 0xff,
+ clamp_t(u32,
+ ((ddcc_status >> 8) & 0xff) * mult,
rps->min_freq,
rps->max_freq);
}
-
- if (IS_GEN9_BC(i915) || GRAPHICS_VER(i915) >= 11) {
- /* Store the frequency values in 16.66 MHZ units, which is
- * the natural hardware unit for SKL
- */
- rps->rp0_freq *= GEN9_FREQ_SCALER;
- rps->rp1_freq *= GEN9_FREQ_SCALER;
- rps->min_freq *= GEN9_FREQ_SCALER;
- rps->max_freq *= GEN9_FREQ_SCALER;
- rps->efficient_freq *= GEN9_FREQ_SCALER;
- }
}
static bool rps_reset(struct intel_rps *rps)
return set_min_freq(rps, val);
}
-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))
- return intel_uncore_read(uncore, XEHPSDV_RP_STATE_CAP);
- else if (IS_GEN9_LP(i915))
- return intel_uncore_read(uncore, BXT_RP_STATE_CAP);
- else
- return intel_uncore_read(uncore, GEN6_RP_STATE_CAP);
-}
-
static void intel_rps_set_manual(struct intel_rps *rps, bool enable)
{
struct intel_uncore *uncore = rps_to_uncore(rps);
void intel_rps_raise_unslice(struct intel_rps *rps)
{
struct intel_uncore *uncore = rps_to_uncore(rps);
- u32 rp0_unslice_req;
mutex_lock(&rps->lock);
if (rps_uses_slpc(rps)) {
/* RP limits have not been initialized yet for SLPC path */
- rp0_unslice_req = ((intel_rps_read_state_cap(rps) >> 0)
- & 0xff) * GEN9_FREQ_SCALER;
+ struct intel_rps_freq_caps caps;
+
+ gen6_rps_get_freq_caps(rps, &caps);
intel_rps_set_manual(rps, true);
intel_uncore_write(uncore, GEN6_RPNSWREQ,
- ((rp0_unslice_req <<
+ ((caps.rp0_freq <<
GEN9_SW_REQ_UNSLICE_RATIO_SHIFT) |
GEN9_IGNORE_SLICE_RATIO));
intel_rps_set_manual(rps, false);
void intel_rps_lower_unslice(struct intel_rps *rps)
{
struct intel_uncore *uncore = rps_to_uncore(rps);
- u32 rpn_unslice_req;
mutex_lock(&rps->lock);
if (rps_uses_slpc(rps)) {
/* RP limits have not been initialized yet for SLPC path */
- rpn_unslice_req = ((intel_rps_read_state_cap(rps) >> 16)
- & 0xff) * GEN9_FREQ_SCALER;
+ struct intel_rps_freq_caps caps;
+
+ gen6_rps_get_freq_caps(rps, &caps);
intel_rps_set_manual(rps, true);
intel_uncore_write(uncore, GEN6_RPNSWREQ,
- ((rpn_unslice_req <<
+ ((caps.min_freq <<
GEN9_SW_REQ_UNSLICE_RATIO_SHIFT) |
GEN9_IGNORE_SLICE_RATIO));
intel_rps_set_manual(rps, false);
mutex_unlock(&rps->lock);
}
+static u32 rps_read_mmio(struct intel_rps *rps, i915_reg_t reg32)
+{
+ struct intel_gt *gt = rps_to_gt(rps);
+ intel_wakeref_t wakeref;
+ u32 val;
+
+ with_intel_runtime_pm(gt->uncore->rpm, wakeref)
+ val = intel_uncore_read(gt->uncore, reg32);
+
+ return val;
+}
+
+bool rps_read_mask_mmio(struct intel_rps *rps,
+ i915_reg_t reg32, u32 mask)
+{
+ return rps_read_mmio(rps, reg32) & mask;
+}
+
/* External interface for intel_ips.ko */
static struct drm_i915_private __rcu *ips_mchdev;
#define INTEL_RPS_H
#include "intel_rps_types.h"
+#include "i915_reg_defs.h"
struct i915_request;
u32 intel_rps_get_rpn_frequency(struct intel_rps *rps);
u32 intel_rps_read_punit_req(struct intel_rps *rps);
u32 intel_rps_read_punit_req_frequency(struct intel_rps *rps);
-u32 intel_rps_read_state_cap(struct intel_rps *rps);
+void gen6_rps_get_freq_caps(struct intel_rps *rps, struct intel_rps_freq_caps *caps);
void intel_rps_raise_unslice(struct intel_rps *rps);
void intel_rps_lower_unslice(struct intel_rps *rps);
+u32 intel_rps_read_throttle_reason(struct intel_rps *rps);
+bool rps_read_mask_mmio(struct intel_rps *rps, i915_reg_t reg32, u32 mask);
+
void gen5_rps_irq_handler(struct intel_rps *rps);
void gen6_rps_irq_handler(struct intel_rps *rps, u32 pm_iir);
void gen11_rps_irq_handler(struct intel_rps *rps, u32 pm_iir);
INTEL_RPS_TIMER,
};
+/**
+ * struct intel_rps_freq_caps - rps freq capabilities
+ * @rp0_freq: non-overclocked max frequency
+ * @rp1_freq: "less than" RP0 power/freqency
+ * @min_freq: aka RPn, minimum frequency
+ *
+ * Freq caps exposed by HW, values are in "hw units" and intel_gpu_freq()
+ * should be used to convert to MHz
+ */
+struct intel_rps_freq_caps {
+ u8 rp0_freq;
+ u8 rp1_freq;
+ u8 min_freq;
+};
+
struct intel_rps {
struct mutex lock; /* protects enabling and the worker */
#include "intel_gt_regs.h"
#include "intel_sseu.h"
+#include "linux/string_helpers.h"
+
void intel_sseu_set_info(struct sseu_dev_info *sseu, u8 max_slices,
u8 max_subslices, u8 max_eus_per_subslice)
{
}
static u32
-_intel_sseu_get_subslices(const struct sseu_dev_info *sseu,
- const u8 *subslice_mask, u8 slice)
+sseu_get_subslices(const struct sseu_dev_info *sseu,
+ const u8 *subslice_mask, u8 slice)
{
int i, offset = slice * sseu->ss_stride;
u32 mask = 0;
u32 intel_sseu_get_subslices(const struct sseu_dev_info *sseu, u8 slice)
{
- return _intel_sseu_get_subslices(sseu, sseu->subslice_mask, slice);
+ return sseu_get_subslices(sseu, sseu->subslice_mask, slice);
+}
+
+static u32 sseu_get_geometry_subslices(const struct sseu_dev_info *sseu)
+{
+ return sseu_get_subslices(sseu, sseu->geometry_subslice_mask, 0);
}
u32 intel_sseu_get_compute_subslices(const struct sseu_dev_info *sseu)
{
- return _intel_sseu_get_subslices(sseu, sseu->compute_subslice_mask, 0);
+ return sseu_get_subslices(sseu, sseu->compute_subslice_mask, 0);
}
void intel_sseu_set_subslices(struct sseu_dev_info *sseu, int slice,
drm_printf(p, "has EU power gating: %s\n", yesno(sseu->has_eu_pg));
}
-void intel_sseu_print_topology(const struct sseu_dev_info *sseu,
- struct drm_printer *p)
+static void sseu_print_hsw_topology(const struct sseu_dev_info *sseu,
+ struct drm_printer *p)
{
int s, ss;
- if (sseu->max_slices == 0) {
- drm_printf(p, "Unavailable\n");
- return;
- }
-
for (s = 0; s < sseu->max_slices; s++) {
drm_printf(p, "slice%d: %u subslice(s) (0x%08x):\n",
s, intel_sseu_subslices_per_slice(sseu, s),
}
}
+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)),
+ hweight16(enabled_eus), enabled_eus);
+ }
+}
+
+void intel_sseu_print_topology(struct drm_i915_private *i915,
+ const struct sseu_dev_info *sseu,
+ struct drm_printer *p)
+{
+ if (sseu->max_slices == 0) {
+ drm_printf(p, "Unavailable\n");
+ } else if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 50)) {
+ sseu_print_xehp_topology(sseu, p);
+ } else {
+ sseu_print_hsw_topology(sseu, p);
+ }
+}
+
u16 intel_slicemask_from_dssmask(u64 dss_mask, int dss_per_slice)
{
u16 slice_mask = 0;
struct intel_gt;
struct drm_printer;
-#define GEN_MAX_SLICES (3) /* SKL upper bound */
-#define GEN_MAX_SUBSLICES (32) /* XEHPSDV upper bound */
-#define GEN_SSEU_STRIDE(max_entries) DIV_ROUND_UP(max_entries, BITS_PER_BYTE)
-#define GEN_MAX_SUBSLICE_STRIDE GEN_SSEU_STRIDE(GEN_MAX_SUBSLICES)
-#define GEN_MAX_EUS (16) /* TGL upper bound */
-#define GEN_MAX_EU_STRIDE GEN_SSEU_STRIDE(GEN_MAX_EUS)
+/*
+ * Maximum number of slices on older platforms. Slices no longer exist
+ * starting on Xe_HP ("gslices," "cslices," etc. are a different concept and
+ * are not expressed through fusing).
+ */
+#define GEN_MAX_HSW_SLICES 3
+
+/*
+ * 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).
+ */
+#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 EUs that can exist within a subslice or DSS. */
+#define GEN_MAX_EUS_PER_SS 16
+
+#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, \
+ GEN_MAX_HSW_SLICES * GEN_MAX_SS_PER_HSW_SLICE)
+
+#define GEN_SSEU_STRIDE(max_entries) DIV_ROUND_UP(max_entries, BITS_PER_BYTE)
+#define GEN_MAX_SUBSLICE_STRIDE GEN_SSEU_STRIDE(GEN_SS_MASK_SIZE)
+#define GEN_MAX_EU_STRIDE GEN_SSEU_STRIDE(GEN_MAX_EUS_PER_SS)
#define GEN_DSS_PER_GSLICE 4
#define GEN_DSS_PER_CSLICE 8
#define GEN_DSS_PER_MSLICE 8
-#define GEN_MAX_GSLICES (GEN_MAX_SUBSLICES / GEN_DSS_PER_GSLICE)
-#define GEN_MAX_CSLICES (GEN_MAX_SUBSLICES / GEN_DSS_PER_CSLICE)
+#define GEN_MAX_GSLICES (GEN_MAX_DSS / GEN_DSS_PER_GSLICE)
+#define GEN_MAX_CSLICES (GEN_MAX_DSS / GEN_DSS_PER_CSLICE)
struct sseu_dev_info {
u8 slice_mask;
- u8 subslice_mask[GEN_MAX_SLICES * GEN_MAX_SUBSLICE_STRIDE];
- u8 geometry_subslice_mask[GEN_MAX_SLICES * GEN_MAX_SUBSLICE_STRIDE];
- u8 compute_subslice_mask[GEN_MAX_SLICES * GEN_MAX_SUBSLICE_STRIDE];
- u8 eu_mask[GEN_MAX_SLICES * GEN_MAX_SUBSLICES * GEN_MAX_EU_STRIDE];
+ 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];
u16 eu_total;
u8 eu_per_subslice;
u8 min_eu_in_pool;
const struct intel_sseu *req_sseu);
void intel_sseu_dump(const struct sseu_dev_info *sseu, struct drm_printer *p);
-void intel_sseu_print_topology(const struct sseu_dev_info *sseu,
+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);
{
struct drm_i915_private *i915 = gt->i915;
const struct intel_gt_info *info = >->info;
- struct sseu_dev_info sseu;
+ struct sseu_dev_info *sseu;
intel_wakeref_t wakeref;
if (GRAPHICS_VER(i915) < 8)
i915_print_sseu_info(m, true, HAS_POOLED_EU(i915), &info->sseu);
seq_puts(m, "SSEU Device Status\n");
- memset(&sseu, 0, sizeof(sseu));
- intel_sseu_set_info(&sseu, info->sseu.max_slices,
+
+ sseu = kzalloc(sizeof(*sseu), GFP_KERNEL);
+ if (!sseu)
+ return -ENOMEM;
+
+ intel_sseu_set_info(sseu, info->sseu.max_slices,
info->sseu.max_subslices,
info->sseu.max_eus_per_subslice);
with_intel_runtime_pm(&i915->runtime_pm, wakeref) {
if (IS_CHERRYVIEW(i915))
- cherryview_sseu_device_status(gt, &sseu);
+ cherryview_sseu_device_status(gt, sseu);
else if (IS_BROADWELL(i915))
- bdw_sseu_device_status(gt, &sseu);
+ bdw_sseu_device_status(gt, sseu);
else if (GRAPHICS_VER(i915) == 9)
- gen9_sseu_device_status(gt, &sseu);
+ gen9_sseu_device_status(gt, sseu);
else if (GRAPHICS_VER(i915) >= 11)
- gen11_sseu_device_status(gt, &sseu);
+ gen11_sseu_device_status(gt, sseu);
}
- i915_print_sseu_info(m, false, HAS_POOLED_EU(i915), &sseu);
+ i915_print_sseu_info(m, false, HAS_POOLED_EU(i915), sseu);
+
+ kfree(sseu);
return 0;
}
}
DEFINE_INTEL_GT_DEBUGFS_ATTRIBUTE(sseu_status);
-static int rcs_topology_show(struct seq_file *m, void *unused)
+static int sseu_topology_show(struct seq_file *m, void *unused)
{
struct intel_gt *gt = m->private;
struct drm_printer p = drm_seq_file_printer(m);
- intel_sseu_print_topology(>->info.sseu, &p);
+ intel_sseu_print_topology(gt->i915, >->info.sseu, &p);
return 0;
}
-DEFINE_INTEL_GT_DEBUGFS_ATTRIBUTE(rcs_topology);
+DEFINE_INTEL_GT_DEBUGFS_ATTRIBUTE(sseu_topology);
void intel_sseu_debugfs_register(struct intel_gt *gt, struct dentry *root)
{
static const struct intel_gt_debugfs_file files[] = {
{ "sseu_status", &sseu_status_fops, NULL },
- { "rcs_topology", &rcs_topology_fops, NULL },
+ { "sseu_topology", &sseu_topology_fops, NULL },
};
intel_gt_debugfs_register_files(root, files, ARRAY_SIZE(files), gt);
static void __add_mcr_wa(struct intel_gt *gt, struct i915_wa_list *wal,
unsigned int slice, unsigned int subslice)
{
- drm_dbg(>->i915->drm, "MCR slice=0x%x, subslice=0x%x\n", slice, subslice);
+ struct drm_printer p = drm_debug_printer("MCR Steering:");
__set_mcr_steering(wal, GEN8_MCR_SELECTOR, slice, subslice);
+
+ gt->default_steering.groupid = slice;
+ gt->default_steering.instanceid = subslice;
+
+ if (drm_debug_enabled(DRM_UT_DRIVER))
+ intel_gt_report_steering(&p, gt, false);
}
static void
FF_DOP_CLOCK_GATE_DISABLE);
}
- if (IS_GRAPHICS_VER(i915, 9, 12)) {
+ if (HAS_PERCTX_PREEMPT_CTRL(i915)) {
/* FtrPerCtxtPreemptionGranularityControl:skl,bxt,kbl,cfl,cnl,icl,tgl */
wa_masked_en(wal,
GEN7_FF_SLICE_CS_CHICKEN1,
wa_write_or(wal, GEN12_GAMCNTRL_CTRL, INVALIDATION_BROADCAST_MODE_DIS |
GLOBAL_INVALIDATION_MODE);
}
+
+ if (IS_DG2(i915)) {
+ /* Wa_22014226127:dg2 */
+ wa_write_or(wal, LSC_CHICKEN_BIT_0, DISABLE_D8_D16_COASLESCE);
+ }
}
static void
* to a single RCS/CCS engine's workaround list since
* they're reset as part of the general render domain reset.
*/
- if (engine->class == RENDER_CLASS)
+ if (engine->flags & I915_ENGINE_FIRST_RENDER_COMPUTE)
general_render_compute_wa_init(engine, wal);
if (engine->class == RENDER_CLASS)
enum intel_engine_id id;
int err = -ENOMEM;
- if (igt_spinner_init(&spin_hi, gt))
- return -ENOMEM;
-
- if (igt_spinner_init(&spin_lo, gt))
- goto err_spin_hi;
-
ctx_hi = kernel_context(gt->i915, NULL);
if (!ctx_hi)
- goto err_spin_lo;
+ return -ENOMEM;
ctx_hi->sched.priority = I915_CONTEXT_MAX_USER_PRIORITY;
ctx_lo = kernel_context(gt->i915, NULL);
goto err_ctx_hi;
ctx_lo->sched.priority = I915_CONTEXT_MIN_USER_PRIORITY;
+ if (igt_spinner_init(&spin_hi, gt))
+ goto err_ctx_lo;
+
+ if (igt_spinner_init(&spin_lo, gt))
+ goto err_spin_hi;
+
for_each_engine(engine, gt, id) {
struct igt_live_test t;
struct i915_request *rq;
if (igt_live_test_begin(&t, gt->i915, __func__, engine->name)) {
err = -EIO;
- goto err_ctx_lo;
+ goto err_spin_lo;
}
rq = spinner_create_request(&spin_lo, ctx_lo, engine,
MI_ARB_CHECK);
if (IS_ERR(rq)) {
err = PTR_ERR(rq);
- goto err_ctx_lo;
+ goto err_spin_lo;
}
i915_request_add(rq);
GEM_TRACE_DUMP();
intel_gt_set_wedged(gt);
err = -EIO;
- goto err_ctx_lo;
+ goto err_spin_lo;
}
rq = spinner_create_request(&spin_hi, ctx_hi, engine,
if (IS_ERR(rq)) {
igt_spinner_end(&spin_lo);
err = PTR_ERR(rq);
- goto err_ctx_lo;
+ goto err_spin_lo;
}
i915_request_add(rq);
GEM_TRACE_DUMP();
intel_gt_set_wedged(gt);
err = -EIO;
- goto err_ctx_lo;
+ goto err_spin_lo;
}
igt_spinner_end(&spin_hi);
if (igt_live_test_end(&t)) {
err = -EIO;
- goto err_ctx_lo;
+ goto err_spin_lo;
}
}
err = 0;
-err_ctx_lo:
- kernel_context_close(ctx_lo);
-err_ctx_hi:
- kernel_context_close(ctx_hi);
err_spin_lo:
igt_spinner_fini(&spin_lo);
err_spin_hi:
igt_spinner_fini(&spin_hi);
+err_ctx_lo:
+ kernel_context_close(ctx_lo);
+err_ctx_hi:
+ kernel_context_close(ctx_hi);
return err;
}
enum intel_engine_id id;
int err = -ENOMEM;
- if (igt_spinner_init(&spin_hi, gt))
- return -ENOMEM;
-
- if (igt_spinner_init(&spin_lo, gt))
- goto err_spin_hi;
-
ctx_hi = kernel_context(gt->i915, NULL);
if (!ctx_hi)
- goto err_spin_lo;
+ return -ENOMEM;
ctx_lo = kernel_context(gt->i915, NULL);
if (!ctx_lo)
goto err_ctx_hi;
+ if (igt_spinner_init(&spin_hi, gt))
+ goto err_ctx_lo;
+
+ if (igt_spinner_init(&spin_lo, gt))
+ goto err_spin_hi;
+
/* Make sure ctx_lo stays before ctx_hi until we trigger preemption. */
ctx_lo->sched.priority = 1;
if (igt_live_test_begin(&t, gt->i915, __func__, engine->name)) {
err = -EIO;
- goto err_ctx_lo;
+ goto err_spin_lo;
}
rq = spinner_create_request(&spin_lo, ctx_lo, engine,
MI_ARB_CHECK);
if (IS_ERR(rq)) {
err = PTR_ERR(rq);
- goto err_ctx_lo;
+ goto err_spin_lo;
}
i915_request_add(rq);
if (IS_ERR(rq)) {
igt_spinner_end(&spin_lo);
err = PTR_ERR(rq);
- goto err_ctx_lo;
+ goto err_spin_lo;
}
i915_request_add(rq);
if (igt_live_test_end(&t)) {
err = -EIO;
- goto err_ctx_lo;
+ goto err_spin_lo;
}
}
err = 0;
-err_ctx_lo:
- kernel_context_close(ctx_lo);
-err_ctx_hi:
- kernel_context_close(ctx_hi);
err_spin_lo:
igt_spinner_fini(&spin_lo);
err_spin_hi:
igt_spinner_fini(&spin_hi);
+err_ctx_lo:
+ kernel_context_close(ctx_lo);
+err_ctx_hi:
+ kernel_context_close(ctx_hi);
return err;
err_wedged:
igt_spinner_end(&spin_lo);
intel_gt_set_wedged(gt);
err = -EIO;
- goto err_ctx_lo;
+ goto err_spin_lo;
}
struct preempt_client {
if (!intel_has_reset_engine(gt))
return 0;
- if (igt_spinner_init(&spin_lo, gt))
- return -ENOMEM;
-
ctx_hi = kernel_context(gt->i915, NULL);
if (!ctx_hi)
- goto err_spin_lo;
+ return -ENOMEM;
ctx_hi->sched.priority = I915_CONTEXT_MAX_USER_PRIORITY;
ctx_lo = kernel_context(gt->i915, NULL);
goto err_ctx_hi;
ctx_lo->sched.priority = I915_CONTEXT_MIN_USER_PRIORITY;
+ if (igt_spinner_init(&spin_lo, gt))
+ goto err_ctx_lo;
+
for_each_engine(engine, gt, id) {
unsigned long saved_timeout;
struct i915_request *rq;
MI_NOOP); /* preemption disabled */
if (IS_ERR(rq)) {
err = PTR_ERR(rq);
- goto err_ctx_lo;
+ goto err_spin_lo;
}
i915_request_add(rq);
if (!igt_wait_for_spinner(&spin_lo, rq)) {
intel_gt_set_wedged(gt);
err = -EIO;
- goto err_ctx_lo;
+ goto err_spin_lo;
}
rq = igt_request_alloc(ctx_hi, engine);
if (IS_ERR(rq)) {
igt_spinner_end(&spin_lo);
err = PTR_ERR(rq);
- goto err_ctx_lo;
+ goto err_spin_lo;
}
/* Flush the previous CS ack before changing timeouts */
intel_gt_set_wedged(gt);
i915_request_put(rq);
err = -ETIME;
- goto err_ctx_lo;
+ goto err_spin_lo;
}
igt_spinner_end(&spin_lo);
}
err = 0;
+err_spin_lo:
+ igt_spinner_fini(&spin_lo);
err_ctx_lo:
kernel_context_close(ctx_lo);
err_ctx_hi:
kernel_context_close(ctx_hi);
-err_spin_lo:
- igt_spinner_fini(&spin_lo);
return err;
}
if (IS_ERR(ce))
return PTR_ERR(ce);
- ce->runtime.num_underflow = 0;
- ce->runtime.max_underflow = 0;
+ ce->stats.runtime.num_underflow = 0;
+ ce->stats.runtime.max_underflow = 0;
do {
unsigned int loop = 1024;
intel_context_get_avg_runtime_ns(ce));
err = 0;
- if (ce->runtime.num_underflow) {
+ if (ce->stats.runtime.num_underflow) {
pr_err("%s: pphwsp underflow %u time(s), max %u cycles!\n",
engine->name,
- ce->runtime.num_underflow,
- ce->runtime.max_underflow);
+ ce->stats.runtime.num_underflow,
+ ce->stats.runtime.max_underflow);
GEM_TRACE_DUMP();
err = -EOVERFLOW;
}
for (i = 0; i < ARRAY_SIZE(sizes); i++) {
struct drm_i915_gem_object *src, *dst;
+ size_t sz;
int err;
src = create_init_lmem_internal(gt, sizes[i], true);
if (IS_ERR(src))
return PTR_ERR(src);
- dst = create_init_lmem_internal(gt, sizes[i], false);
+ sz = src->base.size;
+ dst = create_init_lmem_internal(gt, sz, false);
if (IS_ERR(dst)) {
err = PTR_ERR(dst);
goto err_src;
dst->mm.pages->sgl,
I915_CACHE_NONE,
i915_gem_object_is_lmem(dst),
- sizes[i]);
+ sz);
i915_gem_object_unlock(dst);
i915_gem_object_put(dst);
INTEL_GUC_ACTION_ENGINE_FAILURE_NOTIFICATION = 0x1009,
INTEL_GUC_ACTION_SETUP_PC_GUCRC = 0x3004,
INTEL_GUC_ACTION_AUTHENTICATE_HUC = 0x4000,
+ INTEL_GUC_ACTION_GET_HWCONFIG = 0x4100,
INTEL_GUC_ACTION_REGISTER_CONTEXT = 0x4502,
INTEL_GUC_ACTION_DEREGISTER_CONTEXT = 0x4503,
- INTEL_GUC_ACTION_REGISTER_COMMAND_TRANSPORT_BUFFER = 0x4505,
- INTEL_GUC_ACTION_DEREGISTER_COMMAND_TRANSPORT_BUFFER = 0x4506,
INTEL_GUC_ACTION_DEREGISTER_CONTEXT_DONE = 0x4600,
INTEL_GUC_ACTION_REGISTER_CONTEXT_MULTI_LRC = 0x4601,
INTEL_GUC_ACTION_CLIENT_SOFT_RESET = 0x5507,
#define GUC_LOG_CONTROL_VERBOSITY_MASK (0xF << GUC_LOG_CONTROL_VERBOSITY_SHIFT)
#define GUC_LOG_CONTROL_DEFAULT_LOGGING (1 << 8)
+enum intel_guc_state_capture_event_status {
+ INTEL_GUC_STATE_CAPTURE_EVENT_STATUS_SUCCESS = 0x0,
+ INTEL_GUC_STATE_CAPTURE_EVENT_STATUS_NOSPACE = 0x1,
+};
+
+#define INTEL_GUC_STATE_CAPTURE_EVENT_STATUS_MASK 0x000000FF
+
#endif /* _ABI_GUC_ACTIONS_ABI_H */
enum intel_guc_response_status {
INTEL_GUC_RESPONSE_STATUS_SUCCESS = 0x0,
+ INTEL_GUC_RESPONSE_NOT_SUPPORTED = 0x20,
+ INTEL_GUC_RESPONSE_NO_ATTRIBUTE_TABLE = 0x201,
+ INTEL_GUC_RESPONSE_NO_DECRYPTION_KEY = 0x202,
+ INTEL_GUC_RESPONSE_DECRYPTION_FAILED = 0x204,
INTEL_GUC_RESPONSE_STATUS_GENERIC_FAIL = 0xF000,
};
--- /dev/null
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2021-2022 Intel Corporation
+ */
+
+#ifndef _INTEL_GUC_CAPTURE_FWIF_H
+#define _INTEL_GUC_CAPTURE_FWIF_H
+
+#include <linux/types.h>
+#include "intel_guc_fwif.h"
+
+struct intel_guc;
+struct file;
+
+/**
+ * struct __guc_capture_bufstate
+ *
+ * Book-keeping structure used to track read and write pointers
+ * as we extract error capture data from the GuC-log-buffer's
+ * error-capture region as a stream of dwords.
+ */
+struct __guc_capture_bufstate {
+ u32 size;
+ void *data;
+ u32 rd;
+ u32 wr;
+};
+
+/**
+ * struct __guc_capture_parsed_output - extracted error capture node
+ *
+ * A single unit of extracted error-capture output data grouped together
+ * at an engine-instance level. We keep these nodes in a linked list.
+ * See cachelist and outlist below.
+ */
+struct __guc_capture_parsed_output {
+ /*
+ * A single set of 3 capture lists: a global-list
+ * an engine-class-list and an engine-instance list.
+ * outlist in __guc_capture_parsed_output will keep
+ * a linked list of these nodes that will eventually
+ * be detached from outlist and attached into to
+ * i915_gpu_codedump in response to a context reset
+ */
+ struct list_head link;
+ bool is_partial;
+ u32 eng_class;
+ u32 eng_inst;
+ u32 guc_id;
+ u32 lrca;
+ struct gcap_reg_list_info {
+ u32 vfid;
+ u32 num_regs;
+ struct guc_mmio_reg *regs;
+ } reginfo[GUC_CAPTURE_LIST_TYPE_MAX];
+#define GCAP_PARSED_REGLIST_INDEX_GLOBAL BIT(GUC_CAPTURE_LIST_TYPE_GLOBAL)
+#define GCAP_PARSED_REGLIST_INDEX_ENGCLASS BIT(GUC_CAPTURE_LIST_TYPE_ENGINE_CLASS)
+#define GCAP_PARSED_REGLIST_INDEX_ENGINST BIT(GUC_CAPTURE_LIST_TYPE_ENGINE_INSTANCE)
+};
+
+/**
+ * struct guc_debug_capture_list_header / struct guc_debug_capture_list
+ *
+ * As part of ADS registration, these header structures (followed by
+ * an array of 'struct guc_mmio_reg' entries) are used to register with
+ * GuC microkernel the list of registers we want it to dump out prior
+ * to a engine reset.
+ */
+struct guc_debug_capture_list_header {
+ u32 info;
+#define GUC_CAPTURELISTHDR_NUMDESCR GENMASK(15, 0)
+} __packed;
+
+struct guc_debug_capture_list {
+ struct guc_debug_capture_list_header header;
+ struct guc_mmio_reg regs[0];
+} __packed;
+
+/**
+ * struct __guc_mmio_reg_descr / struct __guc_mmio_reg_descr_group
+ *
+ * intel_guc_capture module uses these structures to maintain static
+ * tables (per unique platform) that consists of lists of registers
+ * (offsets, names, flags,...) that are used at the ADS regisration
+ * time as well as during runtime processing and reporting of error-
+ * capture states generated by GuC just prior to engine reset events.
+ */
+struct __guc_mmio_reg_descr {
+ i915_reg_t reg;
+ u32 flags;
+ u32 mask;
+ const char *regname;
+};
+
+struct __guc_mmio_reg_descr_group {
+ const struct __guc_mmio_reg_descr *list;
+ u32 num_regs;
+ u32 owner; /* see enum guc_capture_owner */
+ u32 type; /* see enum guc_capture_type */
+ u32 engine; /* as per MAX_ENGINE_CLASS */
+ struct __guc_mmio_reg_descr *extlist; /* only used for steered registers */
+};
+
+/**
+ * struct guc_state_capture_header_t / struct guc_state_capture_t /
+ * guc_state_capture_group_header_t / guc_state_capture_group_t
+ *
+ * Prior to resetting engines that have hung or faulted, GuC microkernel
+ * reports the engine error-state (register values that was read) by
+ * logging them into the shared GuC log buffer using these hierarchy
+ * of structures.
+ */
+struct guc_state_capture_header_t {
+ u32 owner;
+#define CAP_HDR_CAPTURE_VFID GENMASK(7, 0)
+ u32 info;
+#define CAP_HDR_CAPTURE_TYPE GENMASK(3, 0) /* see enum guc_capture_type */
+#define CAP_HDR_ENGINE_CLASS GENMASK(7, 4) /* see GUC_MAX_ENGINE_CLASSES */
+#define CAP_HDR_ENGINE_INSTANCE GENMASK(11, 8)
+ u32 lrca; /* if type-instance, LRCA (address) that hung, else set to ~0 */
+ u32 guc_id; /* if type-instance, context index of hung context, else set to ~0 */
+ u32 num_mmios;
+#define CAP_HDR_NUM_MMIOS GENMASK(9, 0)
+} __packed;
+
+struct guc_state_capture_t {
+ struct guc_state_capture_header_t header;
+ struct guc_mmio_reg mmio_entries[0];
+} __packed;
+
+enum guc_capture_group_types {
+ GUC_STATE_CAPTURE_GROUP_TYPE_FULL,
+ GUC_STATE_CAPTURE_GROUP_TYPE_PARTIAL,
+ GUC_STATE_CAPTURE_GROUP_TYPE_MAX,
+};
+
+struct guc_state_capture_group_header_t {
+ u32 owner;
+#define CAP_GRP_HDR_CAPTURE_VFID GENMASK(7, 0)
+ u32 info;
+#define CAP_GRP_HDR_NUM_CAPTURES GENMASK(7, 0)
+#define CAP_GRP_HDR_CAPTURE_TYPE GENMASK(15, 8) /* guc_capture_group_types */
+} __packed;
+
+/* this is the top level structure where an error-capture dump starts */
+struct guc_state_capture_group_t {
+ struct guc_state_capture_group_header_t grp_header;
+ struct guc_state_capture_t capture_entries[0];
+} __packed;
+
+/**
+ * struct __guc_capture_ads_cache
+ *
+ * A structure to cache register lists that were populated and registered
+ * with GuC at startup during ADS registration. This allows much quicker
+ * GuC resets without re-parsing all the tables for the given gt.
+ */
+struct __guc_capture_ads_cache {
+ bool is_valid;
+ void *ptr;
+ size_t size;
+ int status;
+};
+
+/**
+ * struct intel_guc_state_capture
+ *
+ * Internal context of the intel_guc_capture module.
+ */
+struct intel_guc_state_capture {
+ /**
+ * @reglists: static table of register lists used for error-capture state.
+ */
+ const struct __guc_mmio_reg_descr_group *reglists;
+
+ /**
+ * @extlists: allocated table of steered register lists used for error-capture state.
+ *
+ * NOTE: steered registers have multiple instances depending on the HW configuration
+ * (slices or dual-sub-slices) and thus depends on HW fuses discovered at startup
+ */
+ struct __guc_mmio_reg_descr_group *extlists;
+
+ /**
+ * @ads_cache: cached register lists that is ADS format ready
+ */
+ struct __guc_capture_ads_cache ads_cache[GUC_CAPTURE_LIST_INDEX_MAX]
+ [GUC_CAPTURE_LIST_TYPE_MAX]
+ [GUC_MAX_ENGINE_CLASSES];
+ void *ads_null_cache;
+
+ /**
+ * @cachelist: Pool of pre-allocated nodes for error capture output
+ *
+ * We need this pool of pre-allocated nodes because we cannot
+ * dynamically allocate new nodes when receiving the G2H notification
+ * because the event handlers for all G2H event-processing is called
+ * by the ct processing worker queue and when that queue is being
+ * processed, there is no absoluate guarantee that we are not in the
+ * midst of a GT reset operation (which doesn't allow allocations).
+ */
+ struct list_head cachelist;
+#define PREALLOC_NODES_MAX_COUNT (3 * GUC_MAX_ENGINE_CLASSES * GUC_MAX_INSTANCES_PER_CLASS)
+#define PREALLOC_NODES_DEFAULT_NUMREGS 64
+ int max_mmio_per_node;
+
+ /**
+ * @outlist: Pool of pre-allocated nodes for error capture output
+ *
+ * A linked list of parsed GuC error-capture output data before
+ * reporting with formatting via i915_gpu_coredump. Each node in this linked list shall
+ * contain a single engine-capture including global, engine-class and
+ * engine-instance register dumps as per guc_capture_parsed_output_node
+ */
+ struct list_head outlist;
+};
+
+#endif /* _INTEL_GUC_CAPTURE_FWIF_H */
#include "gt/intel_gt_pm_irq.h"
#include "gt/intel_gt_regs.h"
#include "intel_guc.h"
-#include "intel_guc_slpc.h"
#include "intel_guc_ads.h"
+#include "intel_guc_capture.h"
+#include "intel_guc_slpc.h"
#include "intel_guc_submission.h"
#include "i915_drv.h"
#include "i915_irq.h"
if (ret)
goto err_fw;
- ret = intel_guc_ads_create(guc);
+ ret = intel_guc_capture_init(guc);
if (ret)
goto err_log;
+
+ ret = intel_guc_ads_create(guc);
+ if (ret)
+ goto err_capture;
+
GEM_BUG_ON(!guc->ads_vma);
ret = intel_guc_ct_init(&guc->ct);
intel_guc_ct_fini(&guc->ct);
err_ads:
intel_guc_ads_destroy(guc);
+err_capture:
+ intel_guc_capture_destroy(guc);
err_log:
intel_guc_log_destroy(&guc->log);
err_fw:
intel_guc_ct_fini(&guc->ct);
intel_guc_ads_destroy(guc);
+ intel_guc_capture_destroy(guc);
intel_guc_log_destroy(&guc->log);
intel_uc_fw_fini(&guc->fw);
}
#include <linux/iosys-map.h>
#include <linux/xarray.h>
-#include "intel_uncore.h"
+#include "intel_guc_ct.h"
#include "intel_guc_fw.h"
#include "intel_guc_fwif.h"
-#include "intel_guc_ct.h"
#include "intel_guc_log.h"
#include "intel_guc_reg.h"
#include "intel_guc_slpc_types.h"
#include "intel_uc_fw.h"
+#include "intel_uncore.h"
#include "i915_utils.h"
#include "i915_vma.h"
struct __guc_ads_blob;
+struct intel_guc_state_capture;
/**
* struct intel_guc - Top level structure of GuC.
struct intel_guc_ct ct;
/** @slpc: sub-structure containing SLPC related data and objects */
struct intel_guc_slpc slpc;
+ /** @capture: the error-state-capture module's data and objects */
+ struct intel_guc_state_capture *capture;
/** @sched_engine: Global engine used to submit requests to GuC */
struct i915_sched_engine *sched_engine;
bool submission_supported;
/** @submission_selected: tracks whether the user enabled GuC submission */
bool submission_selected;
+ /** @submission_initialized: tracks whether GuC submission has been initialised */
+ bool submission_initialized;
/**
* @rc_supported: tracks whether we support GuC rc on the current platform
*/
struct guc_mmio_reg *ads_regset;
/** @ads_golden_ctxt_size: size of the golden contexts in the ADS */
u32 ads_golden_ctxt_size;
+ /** @ads_capture_size: size of register lists in the ADS used for error capture */
+ u32 ads_capture_size;
/** @ads_engine_usage_size: size of engine usage in the ADS */
u32 ads_engine_usage_size;
int intel_guc_error_capture_process_msg(struct intel_guc *guc,
const u32 *msg, u32 len);
+struct intel_engine_cs *
+intel_guc_lookup_engine(struct intel_guc *guc, u8 guc_class, u8 instance);
+
void intel_guc_find_hung_context(struct intel_engine_cs *engine);
int intel_guc_global_policies_update(struct intel_guc *guc);
#include "gt/intel_lrc.h"
#include "gt/shmem_utils.h"
#include "intel_guc_ads.h"
+#include "intel_guc_capture.h"
#include "intel_guc_fwif.h"
#include "intel_uc.h"
#include "i915_drv.h"
static u32 guc_ads_capture_size(struct intel_guc *guc)
{
- /* FIXME: Allocate a proper capture list */
- return PAGE_ALIGN(PAGE_SIZE);
+ return PAGE_ALIGN(guc->ads_capture_size);
}
static u32 guc_ads_private_data_size(struct intel_guc *guc)
return slot;
}
-static long __must_check guc_mmio_reg_add(struct temp_regset *regset,
- u32 offset, u32 flags)
+#define GUC_REGSET_STEERING(group, instance) ( \
+ FIELD_PREP(GUC_REGSET_STEERING_GROUP, (group)) | \
+ FIELD_PREP(GUC_REGSET_STEERING_INSTANCE, (instance)) | \
+ GUC_REGSET_NEEDS_STEERING \
+)
+
+static long __must_check guc_mmio_reg_add(struct intel_gt *gt,
+ struct temp_regset *regset,
+ i915_reg_t reg, u32 flags)
{
u32 count = regset->storage_used - (regset->registers - regset->storage);
- struct guc_mmio_reg reg = {
+ u32 offset = i915_mmio_reg_offset(reg);
+ struct guc_mmio_reg entry = {
.offset = offset,
.flags = flags,
};
struct guc_mmio_reg *slot;
+ u8 group, inst;
/*
* The mmio list is built using separate lists within the driver.
* register more than once. Do not consider this an error; silently
* move on if the register is already in the list.
*/
- if (bsearch(®, regset->registers, count,
- sizeof(reg), guc_mmio_reg_cmp))
+ if (bsearch(&entry, regset->registers, count,
+ sizeof(entry), guc_mmio_reg_cmp))
return 0;
- slot = __mmio_reg_add(regset, ®);
+ /*
+ * The GuC doesn't have a default steering, so we need to explicitly
+ * steer all registers that need steering. However, we do not keep track
+ * of all the steering ranges, only of those that have a chance of using
+ * a non-default steering from the i915 pov. Instead of adding such
+ * 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);
+ entry.flags |= GUC_REGSET_STEERING(group, inst);
+
+ slot = __mmio_reg_add(regset, &entry);
if (IS_ERR(slot))
return PTR_ERR(slot);
return 0;
}
-#define GUC_MMIO_REG_ADD(regset, reg, masked) \
- guc_mmio_reg_add(regset, \
- i915_mmio_reg_offset((reg)), \
+#define GUC_MMIO_REG_ADD(gt, regset, reg, masked) \
+ guc_mmio_reg_add(gt, \
+ regset, \
+ (reg), \
(masked) ? GUC_REGSET_MASKED : 0)
static int guc_mmio_regset_init(struct temp_regset *regset,
struct intel_engine_cs *engine)
{
+ struct intel_gt *gt = engine->gt;
const u32 base = engine->mmio_base;
struct i915_wa_list *wal = &engine->wa_list;
struct i915_wa *wa;
*/
regset->registers = regset->storage + regset->storage_used;
- ret |= GUC_MMIO_REG_ADD(regset, RING_MODE_GEN7(base), true);
- ret |= GUC_MMIO_REG_ADD(regset, RING_HWS_PGA(base), false);
- ret |= GUC_MMIO_REG_ADD(regset, RING_IMR(base), false);
+ ret |= GUC_MMIO_REG_ADD(gt, regset, RING_MODE_GEN7(base), true);
+ ret |= GUC_MMIO_REG_ADD(gt, regset, RING_HWS_PGA(base), false);
+ ret |= GUC_MMIO_REG_ADD(gt, regset, RING_IMR(base), false);
- if (engine->class == RENDER_CLASS &&
+ if ((engine->flags & I915_ENGINE_FIRST_RENDER_COMPUTE) &&
CCS_MASK(engine->gt))
- ret |= GUC_MMIO_REG_ADD(regset, GEN12_RCU_MODE, true);
+ ret |= GUC_MMIO_REG_ADD(gt, regset, GEN12_RCU_MODE, true);
for (i = 0, wa = wal->list; i < wal->count; i++, wa++)
- ret |= GUC_MMIO_REG_ADD(regset, wa->reg, wa->masked_reg);
+ ret |= GUC_MMIO_REG_ADD(gt, regset, wa->reg, wa->masked_reg);
/* Be extra paranoid and include all whitelist registers. */
for (i = 0; i < RING_MAX_NONPRIV_SLOTS; i++)
- ret |= GUC_MMIO_REG_ADD(regset,
+ ret |= GUC_MMIO_REG_ADD(gt, regset,
RING_FORCE_TO_NONPRIV(base, i),
false);
/* add in local MOCS registers */
for (i = 0; i < GEN9_LNCFCMOCS_REG_COUNT; i++)
- ret |= GUC_MMIO_REG_ADD(regset, GEN9_LNCFCMOCS(i), false);
+ ret |= GUC_MMIO_REG_ADD(gt, regset, GEN9_LNCFCMOCS(i), false);
return ret ? -1 : 0;
}
static void fill_engine_enable_masks(struct intel_gt *gt,
struct iosys_map *info_map)
{
- info_map_write(info_map, engine_enabled_masks[GUC_RENDER_CLASS], 1);
+ 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_VIDEO_CLASS], VDBOX_MASK(gt));
GEM_BUG_ON(guc->ads_golden_ctxt_size != total_size);
}
-static void guc_capture_list_init(struct intel_guc *guc)
+static int
+guc_capture_prep_lists(struct intel_guc *guc)
{
+ struct intel_gt *gt = guc_to_gt(guc);
+ struct drm_i915_private *i915 = guc_to_gt(guc)->i915;
+ u32 ads_ggtt, capture_offset, null_ggtt, total_size = 0;
+ struct guc_gt_system_info local_info;
+ struct iosys_map info_map;
+ bool ads_is_mapped;
+ size_t size = 0;
+ void *ptr;
int i, j;
- u32 addr_ggtt, offset;
- offset = guc_ads_capture_offset(guc);
- addr_ggtt = intel_guc_ggtt_offset(guc, guc->ads_vma) + offset;
+ ads_is_mapped = !iosys_map_is_null(&guc->ads_map);
+ if (ads_is_mapped) {
+ capture_offset = guc_ads_capture_offset(guc);
+ ads_ggtt = intel_guc_ggtt_offset(guc, guc->ads_vma);
+ info_map = IOSYS_MAP_INIT_OFFSET(&guc->ads_map,
+ offsetof(struct __guc_ads_blob, system_info));
+ } else {
+ memset(&local_info, 0, sizeof(local_info));
+ iosys_map_set_vaddr(&info_map, &local_info);
+ fill_engine_enable_masks(gt, &info_map);
+ }
- /* FIXME: Populate a proper capture list */
+ /* first, set aside the first page for a capture_list with zero descriptors */
+ total_size = PAGE_SIZE;
+ if (ads_is_mapped) {
+ if (!intel_guc_capture_getnullheader(guc, &ptr, &size))
+ iosys_map_memcpy_to(&guc->ads_map, capture_offset, ptr, size);
+ null_ggtt = ads_ggtt + capture_offset;
+ capture_offset += PAGE_SIZE;
+ }
for (i = 0; i < GUC_CAPTURE_LIST_INDEX_MAX; i++) {
for (j = 0; j < GUC_MAX_ENGINE_CLASSES; j++) {
- ads_blob_write(guc, ads.capture_instance[i][j], addr_ggtt);
- ads_blob_write(guc, ads.capture_class[i][j], addr_ggtt);
- }
- ads_blob_write(guc, ads.capture_global[i], addr_ggtt);
+ /* null list if we dont have said engine or list */
+ if (!info_map_read(&info_map, engine_enabled_masks[j])) {
+ if (ads_is_mapped) {
+ ads_blob_write(guc, ads.capture_class[i][j], null_ggtt);
+ ads_blob_write(guc, ads.capture_instance[i][j], null_ggtt);
+ }
+ continue;
+ }
+ if (intel_guc_capture_getlistsize(guc, i,
+ GUC_CAPTURE_LIST_TYPE_ENGINE_CLASS,
+ j, &size)) {
+ if (ads_is_mapped)
+ ads_blob_write(guc, ads.capture_class[i][j], null_ggtt);
+ goto engine_instance_list;
+ }
+ total_size += size;
+ if (ads_is_mapped) {
+ if (total_size > guc->ads_capture_size ||
+ intel_guc_capture_getlist(guc, i,
+ GUC_CAPTURE_LIST_TYPE_ENGINE_CLASS,
+ j, &ptr)) {
+ ads_blob_write(guc, ads.capture_class[i][j], null_ggtt);
+ continue;
+ }
+ ads_blob_write(guc, ads.capture_class[i][j], ads_ggtt +
+ capture_offset);
+ iosys_map_memcpy_to(&guc->ads_map, capture_offset, ptr, size);
+ capture_offset += size;
+ }
+engine_instance_list:
+ if (intel_guc_capture_getlistsize(guc, i,
+ GUC_CAPTURE_LIST_TYPE_ENGINE_INSTANCE,
+ j, &size)) {
+ if (ads_is_mapped)
+ ads_blob_write(guc, ads.capture_instance[i][j], null_ggtt);
+ continue;
+ }
+ total_size += size;
+ if (ads_is_mapped) {
+ if (total_size > guc->ads_capture_size ||
+ intel_guc_capture_getlist(guc, i,
+ GUC_CAPTURE_LIST_TYPE_ENGINE_INSTANCE,
+ j, &ptr)) {
+ ads_blob_write(guc, ads.capture_instance[i][j], null_ggtt);
+ continue;
+ }
+ ads_blob_write(guc, ads.capture_instance[i][j], ads_ggtt +
+ capture_offset);
+ iosys_map_memcpy_to(&guc->ads_map, capture_offset, ptr, size);
+ capture_offset += size;
+ }
+ }
+ if (intel_guc_capture_getlistsize(guc, i, GUC_CAPTURE_LIST_TYPE_GLOBAL, 0, &size)) {
+ if (ads_is_mapped)
+ ads_blob_write(guc, ads.capture_global[i], null_ggtt);
+ continue;
+ }
+ total_size += size;
+ if (ads_is_mapped) {
+ if (total_size > guc->ads_capture_size ||
+ intel_guc_capture_getlist(guc, i, GUC_CAPTURE_LIST_TYPE_GLOBAL, 0,
+ &ptr)) {
+ ads_blob_write(guc, ads.capture_global[i], null_ggtt);
+ continue;
+ }
+ ads_blob_write(guc, ads.capture_global[i], ads_ggtt + capture_offset);
+ iosys_map_memcpy_to(&guc->ads_map, capture_offset, ptr, size);
+ capture_offset += size;
+ }
}
+
+ if (guc->ads_capture_size && guc->ads_capture_size != PAGE_ALIGN(total_size))
+ drm_warn(&i915->drm, "GuC->ADS->Capture alloc size changed from %d to %d\n",
+ guc->ads_capture_size, PAGE_ALIGN(total_size));
+
+ return PAGE_ALIGN(total_size);
}
static void __guc_ads_init(struct intel_guc *guc)
base = intel_guc_ggtt_offset(guc, guc->ads_vma);
- /* Capture list for hang debug */
- guc_capture_list_init(guc);
+ /* Lists for error capture debug */
+ guc_capture_prep_lists(guc);
/* ADS */
ads_blob_write(guc, ads.scheduler_policies, base +
return ret;
guc->ads_golden_ctxt_size = ret;
+ /* Likewise the capture lists: */
+ ret = guc_capture_prep_lists(guc);
+ if (ret < 0)
+ return ret;
+ guc->ads_capture_size = ret;
+
/* Now the total size can be determined: */
size = guc_ads_blob_size(guc);
--- /dev/null
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2021-2022 Intel Corporation
+ */
+
+#include <linux/types.h>
+
+#include <drm/drm_print.h>
+
+#include "gt/intel_engine_regs.h"
+#include "gt/intel_gt.h"
+#include "gt/intel_gt_regs.h"
+#include "gt/intel_lrc.h"
+#include "guc_capture_fwif.h"
+#include "intel_guc_capture.h"
+#include "intel_guc_fwif.h"
+#include "i915_drv.h"
+#include "i915_gpu_error.h"
+#include "i915_irq.h"
+#include "i915_memcpy.h"
+#include "i915_reg.h"
+
+/*
+ * Define all device tables of GuC error capture register lists
+ * NOTE: For engine-registers, GuC only needs the register offsets
+ * from the engine-mmio-base
+ */
+#define COMMON_BASE_GLOBAL \
+ { FORCEWAKE_MT, 0, 0, "FORCEWAKE" }
+
+#define COMMON_GEN9BASE_GLOBAL \
+ { GEN8_FAULT_TLB_DATA0, 0, 0, "GEN8_FAULT_TLB_DATA0" }, \
+ { GEN8_FAULT_TLB_DATA1, 0, 0, "GEN8_FAULT_TLB_DATA1" }, \
+ { ERROR_GEN6, 0, 0, "ERROR_GEN6" }, \
+ { DONE_REG, 0, 0, "DONE_REG" }, \
+ { HSW_GTT_CACHE_EN, 0, 0, "HSW_GTT_CACHE_EN" }
+
+#define COMMON_GEN12BASE_GLOBAL \
+ { GEN12_FAULT_TLB_DATA0, 0, 0, "GEN12_FAULT_TLB_DATA0" }, \
+ { GEN12_FAULT_TLB_DATA1, 0, 0, "GEN12_FAULT_TLB_DATA1" }, \
+ { GEN12_AUX_ERR_DBG, 0, 0, "AUX_ERR_DBG" }, \
+ { GEN12_GAM_DONE, 0, 0, "GAM_DONE" }, \
+ { GEN12_RING_FAULT_REG, 0, 0, "FAULT_REG" }
+
+#define COMMON_BASE_ENGINE_INSTANCE \
+ { RING_PSMI_CTL(0), 0, 0, "RC PSMI" }, \
+ { RING_ESR(0), 0, 0, "ESR" }, \
+ { RING_DMA_FADD(0), 0, 0, "RING_DMA_FADD_LDW" }, \
+ { RING_DMA_FADD_UDW(0), 0, 0, "RING_DMA_FADD_UDW" }, \
+ { RING_IPEIR(0), 0, 0, "IPEIR" }, \
+ { RING_IPEHR(0), 0, 0, "IPEHR" }, \
+ { RING_INSTPS(0), 0, 0, "INSTPS" }, \
+ { RING_BBADDR(0), 0, 0, "RING_BBADDR_LOW32" }, \
+ { RING_BBADDR_UDW(0), 0, 0, "RING_BBADDR_UP32" }, \
+ { RING_BBSTATE(0), 0, 0, "BB_STATE" }, \
+ { CCID(0), 0, 0, "CCID" }, \
+ { RING_ACTHD(0), 0, 0, "ACTHD_LDW" }, \
+ { RING_ACTHD_UDW(0), 0, 0, "ACTHD_UDW" }, \
+ { RING_INSTPM(0), 0, 0, "INSTPM" }, \
+ { RING_INSTDONE(0), 0, 0, "INSTDONE" }, \
+ { RING_NOPID(0), 0, 0, "RING_NOPID" }, \
+ { RING_START(0), 0, 0, "START" }, \
+ { RING_HEAD(0), 0, 0, "HEAD" }, \
+ { RING_TAIL(0), 0, 0, "TAIL" }, \
+ { RING_CTL(0), 0, 0, "CTL" }, \
+ { RING_MI_MODE(0), 0, 0, "MODE" }, \
+ { RING_CONTEXT_CONTROL(0), 0, 0, "RING_CONTEXT_CONTROL" }, \
+ { RING_HWS_PGA(0), 0, 0, "HWS" }, \
+ { RING_MODE_GEN7(0), 0, 0, "GFX_MODE" }, \
+ { GEN8_RING_PDP_LDW(0, 0), 0, 0, "PDP0_LDW" }, \
+ { GEN8_RING_PDP_UDW(0, 0), 0, 0, "PDP0_UDW" }, \
+ { GEN8_RING_PDP_LDW(0, 1), 0, 0, "PDP1_LDW" }, \
+ { GEN8_RING_PDP_UDW(0, 1), 0, 0, "PDP1_UDW" }, \
+ { GEN8_RING_PDP_LDW(0, 2), 0, 0, "PDP2_LDW" }, \
+ { GEN8_RING_PDP_UDW(0, 2), 0, 0, "PDP2_UDW" }, \
+ { GEN8_RING_PDP_LDW(0, 3), 0, 0, "PDP3_LDW" }, \
+ { GEN8_RING_PDP_UDW(0, 3), 0, 0, "PDP3_UDW" }
+
+#define COMMON_BASE_HAS_EU \
+ { EIR, 0, 0, "EIR" }
+
+#define COMMON_BASE_RENDER \
+ { GEN7_SC_INSTDONE, 0, 0, "GEN7_SC_INSTDONE" }
+
+#define COMMON_GEN12BASE_RENDER \
+ { GEN12_SC_INSTDONE_EXTRA, 0, 0, "GEN12_SC_INSTDONE_EXTRA" }, \
+ { GEN12_SC_INSTDONE_EXTRA2, 0, 0, "GEN12_SC_INSTDONE_EXTRA2" }
+
+#define COMMON_GEN12BASE_VEC \
+ { GEN12_SFC_DONE(0), 0, 0, "SFC_DONE[0]" }, \
+ { GEN12_SFC_DONE(1), 0, 0, "SFC_DONE[1]" }, \
+ { GEN12_SFC_DONE(2), 0, 0, "SFC_DONE[2]" }, \
+ { GEN12_SFC_DONE(3), 0, 0, "SFC_DONE[3]" }
+
+/* XE_LPD - Global */
+static const struct __guc_mmio_reg_descr xe_lpd_global_regs[] = {
+ COMMON_BASE_GLOBAL,
+ COMMON_GEN9BASE_GLOBAL,
+ COMMON_GEN12BASE_GLOBAL,
+};
+
+/* XE_LPD - Render / Compute Per-Class */
+static const struct __guc_mmio_reg_descr xe_lpd_rc_class_regs[] = {
+ COMMON_BASE_HAS_EU,
+ COMMON_BASE_RENDER,
+ COMMON_GEN12BASE_RENDER,
+};
+
+/* GEN9/XE_LPD - Render / Compute Per-Engine-Instance */
+static const struct __guc_mmio_reg_descr xe_lpd_rc_inst_regs[] = {
+ COMMON_BASE_ENGINE_INSTANCE,
+};
+
+/* GEN9/XE_LPD - Media Decode/Encode Per-Engine-Instance */
+static const struct __guc_mmio_reg_descr xe_lpd_vd_inst_regs[] = {
+ COMMON_BASE_ENGINE_INSTANCE,
+};
+
+/* XE_LPD - Video Enhancement Per-Class */
+static const struct __guc_mmio_reg_descr xe_lpd_vec_class_regs[] = {
+ COMMON_GEN12BASE_VEC,
+};
+
+/* GEN9/XE_LPD - Video Enhancement Per-Engine-Instance */
+static const struct __guc_mmio_reg_descr xe_lpd_vec_inst_regs[] = {
+ COMMON_BASE_ENGINE_INSTANCE,
+};
+
+/* GEN9/XE_LPD - Blitter Per-Engine-Instance */
+static const struct __guc_mmio_reg_descr xe_lpd_blt_inst_regs[] = {
+ COMMON_BASE_ENGINE_INSTANCE,
+};
+
+/* GEN9 - Global */
+static const struct __guc_mmio_reg_descr default_global_regs[] = {
+ COMMON_BASE_GLOBAL,
+ COMMON_GEN9BASE_GLOBAL,
+};
+
+static const struct __guc_mmio_reg_descr default_rc_class_regs[] = {
+ COMMON_BASE_HAS_EU,
+ COMMON_BASE_RENDER,
+};
+
+/*
+ * Empty lists:
+ * GEN9/XE_LPD - Blitter Per-Class
+ * GEN9/XE_LPD - Media Decode/Encode Per-Class
+ * GEN9 - VEC Class
+ */
+static const struct __guc_mmio_reg_descr empty_regs_list[] = {
+};
+
+#define TO_GCAP_DEF_OWNER(x) (GUC_CAPTURE_LIST_INDEX_##x)
+#define TO_GCAP_DEF_TYPE(x) (GUC_CAPTURE_LIST_TYPE_##x)
+#define MAKE_REGLIST(regslist, regsowner, regstype, class) \
+ { \
+ regslist, \
+ ARRAY_SIZE(regslist), \
+ TO_GCAP_DEF_OWNER(regsowner), \
+ TO_GCAP_DEF_TYPE(regstype), \
+ class, \
+ NULL, \
+ }
+
+/* List of lists */
+static struct __guc_mmio_reg_descr_group default_lists[] = {
+ MAKE_REGLIST(default_global_regs, PF, GLOBAL, 0),
+ MAKE_REGLIST(default_rc_class_regs, PF, ENGINE_CLASS, GUC_RENDER_CLASS),
+ MAKE_REGLIST(xe_lpd_rc_inst_regs, PF, ENGINE_INSTANCE, GUC_RENDER_CLASS),
+ MAKE_REGLIST(empty_regs_list, PF, ENGINE_CLASS, GUC_VIDEO_CLASS),
+ MAKE_REGLIST(xe_lpd_vd_inst_regs, PF, ENGINE_INSTANCE, GUC_VIDEO_CLASS),
+ MAKE_REGLIST(empty_regs_list, PF, ENGINE_CLASS, GUC_VIDEOENHANCE_CLASS),
+ MAKE_REGLIST(xe_lpd_vec_inst_regs, PF, ENGINE_INSTANCE, GUC_VIDEOENHANCE_CLASS),
+ MAKE_REGLIST(empty_regs_list, PF, ENGINE_CLASS, GUC_BLITTER_CLASS),
+ MAKE_REGLIST(xe_lpd_blt_inst_regs, PF, ENGINE_INSTANCE, GUC_BLITTER_CLASS),
+ {}
+};
+
+static const struct __guc_mmio_reg_descr_group xe_lpd_lists[] = {
+ MAKE_REGLIST(xe_lpd_global_regs, PF, GLOBAL, 0),
+ MAKE_REGLIST(xe_lpd_rc_class_regs, PF, ENGINE_CLASS, GUC_RENDER_CLASS),
+ MAKE_REGLIST(xe_lpd_rc_inst_regs, PF, ENGINE_INSTANCE, GUC_RENDER_CLASS),
+ MAKE_REGLIST(empty_regs_list, PF, ENGINE_CLASS, GUC_VIDEO_CLASS),
+ MAKE_REGLIST(xe_lpd_vd_inst_regs, PF, ENGINE_INSTANCE, GUC_VIDEO_CLASS),
+ MAKE_REGLIST(xe_lpd_vec_class_regs, PF, ENGINE_CLASS, GUC_VIDEOENHANCE_CLASS),
+ MAKE_REGLIST(xe_lpd_vec_inst_regs, PF, ENGINE_INSTANCE, GUC_VIDEOENHANCE_CLASS),
+ MAKE_REGLIST(empty_regs_list, PF, ENGINE_CLASS, GUC_BLITTER_CLASS),
+ MAKE_REGLIST(xe_lpd_blt_inst_regs, PF, ENGINE_INSTANCE, GUC_BLITTER_CLASS),
+ {}
+};
+
+static const struct __guc_mmio_reg_descr_group *
+guc_capture_get_one_list(const struct __guc_mmio_reg_descr_group *reglists,
+ u32 owner, u32 type, u32 id)
+{
+ int i;
+
+ if (!reglists)
+ return NULL;
+
+ for (i = 0; reglists[i].list; ++i) {
+ if (reglists[i].owner == owner && reglists[i].type == type &&
+ (reglists[i].engine == id || reglists[i].type == GUC_CAPTURE_LIST_TYPE_GLOBAL))
+ return ®lists[i];
+ }
+
+ return NULL;
+}
+
+static struct __guc_mmio_reg_descr_group *
+guc_capture_get_one_ext_list(struct __guc_mmio_reg_descr_group *reglists,
+ u32 owner, u32 type, u32 id)
+{
+ int i;
+
+ if (!reglists)
+ return NULL;
+
+ for (i = 0; reglists[i].extlist; ++i) {
+ if (reglists[i].owner == owner && reglists[i].type == type &&
+ (reglists[i].engine == id || reglists[i].type == GUC_CAPTURE_LIST_TYPE_GLOBAL))
+ return ®lists[i];
+ }
+
+ return NULL;
+}
+
+static void guc_capture_free_extlists(struct __guc_mmio_reg_descr_group *reglists)
+{
+ int i = 0;
+
+ if (!reglists)
+ return;
+
+ while (reglists[i].extlist)
+ kfree(reglists[i++].extlist);
+}
+
+struct __ext_steer_reg {
+ const char *name;
+ i915_reg_t reg;
+};
+
+static const struct __ext_steer_reg xe_extregs[] = {
+ {"GEN7_SAMPLER_INSTDONE", GEN7_SAMPLER_INSTDONE},
+ {"GEN7_ROW_INSTDONE", GEN7_ROW_INSTDONE}
+};
+
+static void __fill_ext_reg(struct __guc_mmio_reg_descr *ext,
+ const struct __ext_steer_reg *extlist,
+ int slice_id, int subslice_id)
+{
+ ext->reg = extlist->reg;
+ ext->flags = FIELD_PREP(GUC_REGSET_STEERING_GROUP, slice_id);
+ ext->flags |= FIELD_PREP(GUC_REGSET_STEERING_INSTANCE, subslice_id);
+ ext->regname = extlist->name;
+}
+
+static int
+__alloc_ext_regs(struct __guc_mmio_reg_descr_group *newlist,
+ const struct __guc_mmio_reg_descr_group *rootlist, int num_regs)
+{
+ struct __guc_mmio_reg_descr *list;
+
+ list = kcalloc(num_regs, sizeof(struct __guc_mmio_reg_descr), GFP_KERNEL);
+ if (!list)
+ return -ENOMEM;
+
+ newlist->extlist = list;
+ newlist->num_regs = num_regs;
+ newlist->owner = rootlist->owner;
+ newlist->engine = rootlist->engine;
+ newlist->type = rootlist->type;
+
+ return 0;
+}
+
+static void
+guc_capture_alloc_steered_lists_xe_lpd(struct intel_guc *guc,
+ const struct __guc_mmio_reg_descr_group *lists)
+{
+ struct intel_gt *gt = guc_to_gt(guc);
+ struct drm_i915_private *i915 = guc_to_gt(guc)->i915;
+ int slice, subslice, i, num_steer_regs, num_tot_regs = 0;
+ const struct __guc_mmio_reg_descr_group *list;
+ struct __guc_mmio_reg_descr_group *extlists;
+ struct __guc_mmio_reg_descr *extarray;
+ struct sseu_dev_info *sseu;
+
+ /* In XE_LPD we only have steered registers for the render-class */
+ list = guc_capture_get_one_list(lists, GUC_CAPTURE_LIST_INDEX_PF,
+ GUC_CAPTURE_LIST_TYPE_ENGINE_CLASS, GUC_RENDER_CLASS);
+ /* skip if extlists was previously allocated */
+ if (!list || guc->capture->extlists)
+ return;
+
+ num_steer_regs = ARRAY_SIZE(xe_extregs);
+
+ sseu = >->info.sseu;
+ for_each_instdone_slice_subslice(i915, sseu, slice, subslice)
+ num_tot_regs += num_steer_regs;
+
+ if (!num_tot_regs)
+ return;
+
+ /* allocate an extra for an end marker */
+ extlists = kcalloc(2, sizeof(struct __guc_mmio_reg_descr_group), GFP_KERNEL);
+ if (!extlists)
+ return;
+
+ if (__alloc_ext_regs(&extlists[0], list, num_tot_regs)) {
+ kfree(extlists);
+ return;
+ }
+
+ extarray = extlists[0].extlist;
+ for_each_instdone_slice_subslice(i915, sseu, slice, subslice) {
+ for (i = 0; i < num_steer_regs; ++i) {
+ __fill_ext_reg(extarray, &xe_extregs[i], slice, subslice);
+ ++extarray;
+ }
+ }
+
+ guc->capture->extlists = extlists;
+}
+
+static const struct __ext_steer_reg xehpg_extregs[] = {
+ {"XEHPG_INSTDONE_GEOM_SVG", XEHPG_INSTDONE_GEOM_SVG}
+};
+
+static bool __has_xehpg_extregs(u32 ipver)
+{
+ return (ipver >= IP_VER(12, 55));
+}
+
+static void
+guc_capture_alloc_steered_lists_xe_hpg(struct intel_guc *guc,
+ const struct __guc_mmio_reg_descr_group *lists,
+ u32 ipver)
+{
+ struct intel_gt *gt = guc_to_gt(guc);
+ struct drm_i915_private *i915 = guc_to_gt(guc)->i915;
+ struct sseu_dev_info *sseu;
+ int slice, subslice, i, iter, num_steer_regs, num_tot_regs = 0;
+ const struct __guc_mmio_reg_descr_group *list;
+ struct __guc_mmio_reg_descr_group *extlists;
+ struct __guc_mmio_reg_descr *extarray;
+
+ /* In XE_LP / HPG we only have render-class steering registers during error-capture */
+ list = guc_capture_get_one_list(lists, GUC_CAPTURE_LIST_INDEX_PF,
+ GUC_CAPTURE_LIST_TYPE_ENGINE_CLASS, GUC_RENDER_CLASS);
+ /* skip if extlists was previously allocated */
+ if (!list || guc->capture->extlists)
+ return;
+
+ num_steer_regs = ARRAY_SIZE(xe_extregs);
+ if (__has_xehpg_extregs(ipver))
+ num_steer_regs += ARRAY_SIZE(xehpg_extregs);
+
+ sseu = >->info.sseu;
+ for_each_instdone_gslice_dss_xehp(i915, sseu, iter, slice, subslice) {
+ num_tot_regs += num_steer_regs;
+ }
+
+ if (!num_tot_regs)
+ return;
+
+ /* allocate an extra for an end marker */
+ extlists = kcalloc(2, sizeof(struct __guc_mmio_reg_descr_group), GFP_KERNEL);
+ if (!extlists)
+ return;
+
+ if (__alloc_ext_regs(&extlists[0], list, num_tot_regs)) {
+ kfree(extlists);
+ return;
+ }
+
+ extarray = extlists[0].extlist;
+ for_each_instdone_gslice_dss_xehp(i915, sseu, iter, slice, subslice) {
+ for (i = 0; i < ARRAY_SIZE(xe_extregs); ++i) {
+ __fill_ext_reg(extarray, &xe_extregs[i], slice, subslice);
+ ++extarray;
+ }
+ if (__has_xehpg_extregs(ipver)) {
+ for (i = 0; i < ARRAY_SIZE(xehpg_extregs); ++i) {
+ __fill_ext_reg(extarray, &xehpg_extregs[i], slice, subslice);
+ ++extarray;
+ }
+ }
+ }
+
+ drm_dbg(&i915->drm, "GuC-capture found %d-ext-regs.\n", num_tot_regs);
+ guc->capture->extlists = extlists;
+}
+
+static const struct __guc_mmio_reg_descr_group *
+guc_capture_get_device_reglist(struct intel_guc *guc)
+{
+ struct drm_i915_private *i915 = guc_to_gt(guc)->i915;
+
+ if (GRAPHICS_VER(i915) > 11) {
+ /*
+ * For certain engine classes, there are slice and subslice
+ * level registers requiring steering. We allocate and populate
+ * these at init time based on hw config add it as an extension
+ * list at the end of the pre-populated render list.
+ */
+ if (IS_DG2(i915))
+ guc_capture_alloc_steered_lists_xe_hpg(guc, xe_lpd_lists, IP_VER(12, 55));
+ else if (IS_XEHPSDV(i915))
+ guc_capture_alloc_steered_lists_xe_hpg(guc, xe_lpd_lists, IP_VER(12, 50));
+ else
+ guc_capture_alloc_steered_lists_xe_lpd(guc, xe_lpd_lists);
+
+ return xe_lpd_lists;
+ }
+
+ /* if GuC submission is enabled on a non-POR platform, just use a common baseline */
+ 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)
+{
+ u32 i = 0, j = 0;
+ struct drm_i915_private *i915 = guc_to_gt(guc)->i915;
+ const struct __guc_mmio_reg_descr_group *reglists = guc->capture->reglists;
+ struct __guc_mmio_reg_descr_group *extlists = guc->capture->extlists;
+ const struct __guc_mmio_reg_descr_group *match;
+ struct __guc_mmio_reg_descr_group *matchext;
+
+ if (!reglists)
+ 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);
+ return -ENODATA;
+ }
+
+ for (i = 0; i < num_entries && i < match->num_regs; ++i) {
+ ptr[i].offset = match->list[i].reg.reg;
+ ptr[i].value = 0xDEADF00D;
+ ptr[i].flags = match->list[i].flags;
+ ptr[i].mask = match->list[i].mask;
+ }
+
+ matchext = guc_capture_get_one_ext_list(extlists, owner, type, classid);
+ if (matchext) {
+ for (i = match->num_regs, j = 0; i < num_entries &&
+ i < (match->num_regs + matchext->num_regs) &&
+ j < matchext->num_regs; ++i, ++j) {
+ ptr[i].offset = matchext->extlist[j].reg.reg;
+ ptr[i].value = 0xDEADF00D;
+ ptr[i].flags = matchext->extlist[j].flags;
+ ptr[i].mask = matchext->extlist[j].mask;
+ }
+ }
+ if (i < num_entries)
+ drm_dbg(&i915->drm, "GuC-capture: Init reglist short %d out %d.\n",
+ (int)i, (int)num_entries);
+
+ return 0;
+}
+
+static int
+guc_cap_list_num_regs(struct intel_guc_state_capture *gc, u32 owner, u32 type, u32 classid)
+{
+ const struct __guc_mmio_reg_descr_group *match;
+ struct __guc_mmio_reg_descr_group *matchext;
+ int num_regs;
+
+ match = guc_capture_get_one_list(gc->reglists, owner, type, classid);
+ if (!match)
+ return 0;
+
+ num_regs = match->num_regs;
+
+ matchext = guc_capture_get_one_ext_list(gc->extlists, owner, type, classid);
+ if (matchext)
+ num_regs += matchext->num_regs;
+
+ return num_regs;
+}
+
+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;
+
+ if (!gc->reglists)
+ return -ENODEV;
+
+ if (cache->is_valid) {
+ *size = cache->size;
+ return cache->status;
+ }
+
+ 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);
+ return -ENODATA;
+ }
+
+ *size = PAGE_ALIGN((sizeof(struct guc_debug_capture_list)) +
+ (num_regs * sizeof(struct guc_mmio_reg)));
+
+ return 0;
+}
+
+static void guc_capture_create_prealloc_nodes(struct intel_guc *guc);
+
+int
+intel_guc_capture_getlist(struct intel_guc *guc, u32 owner, u32 type, u32 classid,
+ void **outptr)
+{
+ struct intel_guc_state_capture *gc = guc->capture;
+ struct __guc_capture_ads_cache *cache = &gc->ads_cache[owner][type][classid];
+ struct drm_i915_private *i915 = guc_to_gt(guc)->i915;
+ struct guc_debug_capture_list *listnode;
+ int ret, num_regs;
+ u8 *caplist, *tmp;
+ size_t size = 0;
+
+ if (!gc->reglists)
+ return -ENODEV;
+
+ if (cache->is_valid) {
+ *outptr = cache->ptr;
+ return cache->status;
+ }
+
+ /*
+ * ADS population of input registers is a good
+ * time to pre-allocate cachelist output nodes
+ */
+ guc_capture_create_prealloc_nodes(guc);
+
+ ret = intel_guc_capture_getlistsize(guc, owner, type, classid, &size);
+ if (ret) {
+ cache->is_valid = true;
+ cache->ptr = NULL;
+ cache->size = 0;
+ cache->status = ret;
+ return ret;
+ }
+
+ caplist = kzalloc(size, GFP_KERNEL);
+ if (!caplist) {
+ drm_dbg(&i915->drm, "GuC-capture: failed to alloc cached caplist");
+ return -ENOMEM;
+ }
+
+ /* populate capture list header */
+ tmp = caplist;
+ num_regs = guc_cap_list_num_regs(guc->capture, owner, type, classid);
+ listnode = (struct guc_debug_capture_list *)tmp;
+ listnode->header.info = FIELD_PREP(GUC_CAPTURELISTHDR_NUMDESCR, (u32)num_regs);
+
+ /* populate list of register descriptor */
+ tmp += sizeof(struct guc_debug_capture_list);
+ guc_capture_list_init(guc, owner, type, classid, (struct guc_mmio_reg *)tmp, num_regs);
+
+ /* cache this list */
+ cache->is_valid = true;
+ cache->ptr = caplist;
+ cache->size = size;
+ cache->status = 0;
+
+ *outptr = caplist;
+
+ return 0;
+}
+
+int
+intel_guc_capture_getnullheader(struct intel_guc *guc,
+ void **outptr, size_t *size)
+{
+ struct intel_guc_state_capture *gc = guc->capture;
+ struct drm_i915_private *i915 = guc_to_gt(guc)->i915;
+ int tmp = sizeof(u32) * 4;
+ void *null_header;
+
+ if (gc->ads_null_cache) {
+ *outptr = gc->ads_null_cache;
+ *size = tmp;
+ return 0;
+ }
+
+ null_header = kzalloc(tmp, GFP_KERNEL);
+ if (!null_header) {
+ drm_dbg(&i915->drm, "GuC-capture: failed to alloc cached nulllist");
+ return -ENOMEM;
+ }
+
+ gc->ads_null_cache = null_header;
+ *outptr = null_header;
+ *size = tmp;
+
+ return 0;
+}
+
+#define GUC_CAPTURE_OVERBUFFER_MULTIPLIER 3
+
+int
+intel_guc_capture_output_min_size_est(struct intel_guc *guc)
+{
+ struct intel_gt *gt = guc_to_gt(guc);
+ struct intel_engine_cs *engine;
+ enum intel_engine_id id;
+ int worst_min_size = 0, num_regs = 0;
+ size_t tmp = 0;
+
+ if (!guc->capture)
+ return -ENODEV;
+
+ /*
+ * If every single engine-instance suffered a failure in quick succession but
+ * were all unrelated, then a burst of multiple error-capture events would dump
+ * registers for every one engine instance, one at a time. In this case, GuC
+ * would even dump the global-registers repeatedly.
+ *
+ * For each engine instance, there would be 1 x guc_state_capture_group_t output
+ * followed by 3 x guc_state_capture_t lists. The latter is how the register
+ * dumps are split across different register types (where the '3' are global vs class
+ * vs instance). Finally, let's multiply the whole thing by 3x (just so we are
+ * not limited to just 1 round of data in a worst case full register dump log)
+ *
+ * NOTE: intel_guc_log that allocates the log buffer would round this size up to
+ * a power of two.
+ */
+
+ for_each_engine(engine, gt, id) {
+ worst_min_size += sizeof(struct guc_state_capture_group_header_t) +
+ (3 * sizeof(struct guc_state_capture_header_t));
+
+ if (!intel_guc_capture_getlistsize(guc, 0, GUC_CAPTURE_LIST_TYPE_GLOBAL, 0, &tmp))
+ num_regs += tmp;
+
+ if (!intel_guc_capture_getlistsize(guc, 0, GUC_CAPTURE_LIST_TYPE_ENGINE_CLASS,
+ engine->class, &tmp)) {
+ num_regs += tmp;
+ }
+ if (!intel_guc_capture_getlistsize(guc, 0, GUC_CAPTURE_LIST_TYPE_ENGINE_INSTANCE,
+ engine->class, &tmp)) {
+ num_regs += tmp;
+ }
+ }
+
+ worst_min_size += (num_regs * sizeof(struct guc_mmio_reg));
+
+ return (worst_min_size * GUC_CAPTURE_OVERBUFFER_MULTIPLIER);
+}
+
+/*
+ * KMD Init time flows:
+ * --------------------
+ * --> alloc A: GuC input capture regs lists (registered to GuC via ADS).
+ * intel_guc_ads acquires the register lists by calling
+ * intel_guc_capture_list_size and intel_guc_capture_list_get 'n' times,
+ * where n = 1 for global-reg-list +
+ * num_engine_classes for class-reg-list +
+ * num_engine_classes for instance-reg-list
+ * (since all instances of the same engine-class type
+ * have an identical engine-instance register-list).
+ * ADS module also calls separately for PF vs VF.
+ *
+ * --> alloc B: GuC output capture buf (registered via guc_init_params(log_param))
+ * Size = #define CAPTURE_BUFFER_SIZE (warns if on too-small)
+ * Note2: 'x 3' to hold multiple capture groups
+ *
+ * GUC Runtime notify capture:
+ * --------------------------
+ * --> G2H STATE_CAPTURE_NOTIFICATION
+ * L--> intel_guc_capture_process
+ * L--> Loop through B (head..tail) and for each engine instance's
+ * err-state-captured register-list we find, we alloc 'C':
+ * --> alloc C: A capture-output-node structure that includes misc capture info along
+ * with 3 register list dumps (global, engine-class and engine-instance)
+ * This node is created from a pre-allocated list of blank nodes in
+ * guc->capture->cachelist and populated with the error-capture
+ * data from GuC and then it's added into guc->capture->outlist linked
+ * list. This list is used for matchup and printout by i915_gpu_coredump
+ * and err_print_gt, (when user invokes the error capture sysfs).
+ *
+ * GUC --> notify context reset:
+ * -----------------------------
+ * --> G2H CONTEXT RESET
+ * L--> guc_handle_context_reset --> i915_capture_error_state
+ * L--> i915_gpu_coredump(..IS_GUC_CAPTURE) --> gt_record_engines
+ * --> capture_engine(..IS_GUC_CAPTURE)
+ * L--> intel_guc_capture_get_matching_node is where
+ * detach C from internal linked list and add it into
+ * intel_engine_coredump struct (if the context and
+ * engine of the event notification matches a node
+ * in the link list).
+ *
+ * User Sysfs / Debugfs
+ * --------------------
+ * --> i915_gpu_coredump_copy_to_buffer->
+ * L--> err_print_to_sgl --> err_print_gt
+ * L--> error_print_guc_captures
+ * L--> intel_guc_capture_print_node prints the
+ * register lists values of the attached node
+ * on the error-engine-dump being reported.
+ * L--> i915_reset_error_state ... -->__i915_gpu_coredump_free
+ * L--> ... cleanup_gt -->
+ * L--> intel_guc_capture_free_node returns the
+ * capture-output-node back to the internal
+ * cachelist for reuse.
+ *
+ */
+
+static int guc_capture_buf_cnt(struct __guc_capture_bufstate *buf)
+{
+ if (buf->wr >= buf->rd)
+ return (buf->wr - buf->rd);
+ return (buf->size - buf->rd) + buf->wr;
+}
+
+static int guc_capture_buf_cnt_to_end(struct __guc_capture_bufstate *buf)
+{
+ if (buf->rd > buf->wr)
+ return (buf->size - buf->rd);
+ return (buf->wr - buf->rd);
+}
+
+/*
+ * GuC's error-capture output is a ring buffer populated in a byte-stream fashion:
+ *
+ * The GuC Log buffer region for error-capture is managed like a ring buffer.
+ * The GuC firmware dumps error capture logs into this ring in a byte-stream flow.
+ * Additionally, as per the current and foreseeable future, all packed error-
+ * capture output structures are dword aligned.
+ *
+ * That said, if the GuC firmware is in the midst of writing a structure that is larger
+ * than one dword but the tail end of the err-capture buffer-region has lesser space left,
+ * we would need to extract that structure one dword at a time straddled across the end,
+ * onto the start of the ring.
+ *
+ * Below function, guc_capture_log_remove_dw is a helper for that. All callers of this
+ * function would typically do a straight-up memcpy from the ring contents and will only
+ * call this helper if their structure-extraction is straddling across the end of the
+ * ring. GuC firmware does not add any padding. The reason for the no-padding is to ease
+ * scalability for future expansion of output data types without requiring a redesign
+ * of the flow controls.
+ */
+static int
+guc_capture_log_remove_dw(struct intel_guc *guc, struct __guc_capture_bufstate *buf,
+ u32 *dw)
+{
+ struct drm_i915_private *i915 = guc_to_gt(guc)->i915;
+ int tries = 2;
+ int avail = 0;
+ u32 *src_data;
+
+ if (!guc_capture_buf_cnt(buf))
+ return 0;
+
+ while (tries--) {
+ avail = guc_capture_buf_cnt_to_end(buf);
+ if (avail >= sizeof(u32)) {
+ src_data = (u32 *)(buf->data + buf->rd);
+ *dw = *src_data;
+ buf->rd += 4;
+ return 4;
+ }
+ if (avail)
+ drm_dbg(&i915->drm, "GuC-Cap-Logs not dword aligned, skipping.\n");
+ buf->rd = 0;
+ }
+
+ return 0;
+}
+
+static bool
+guc_capture_data_extracted(struct __guc_capture_bufstate *b,
+ int size, void *dest)
+{
+ if (guc_capture_buf_cnt_to_end(b) >= size) {
+ memcpy(dest, (b->data + b->rd), size);
+ b->rd += size;
+ return true;
+ }
+ return false;
+}
+
+static int
+guc_capture_log_get_group_hdr(struct intel_guc *guc, struct __guc_capture_bufstate *buf,
+ struct guc_state_capture_group_header_t *ghdr)
+{
+ int read = 0;
+ int fullsize = sizeof(struct guc_state_capture_group_header_t);
+
+ if (fullsize > guc_capture_buf_cnt(buf))
+ return -1;
+
+ if (guc_capture_data_extracted(buf, fullsize, (void *)ghdr))
+ return 0;
+
+ read += guc_capture_log_remove_dw(guc, buf, &ghdr->owner);
+ read += guc_capture_log_remove_dw(guc, buf, &ghdr->info);
+ if (read != fullsize)
+ return -1;
+
+ return 0;
+}
+
+static int
+guc_capture_log_get_data_hdr(struct intel_guc *guc, struct __guc_capture_bufstate *buf,
+ struct guc_state_capture_header_t *hdr)
+{
+ int read = 0;
+ int fullsize = sizeof(struct guc_state_capture_header_t);
+
+ if (fullsize > guc_capture_buf_cnt(buf))
+ return -1;
+
+ if (guc_capture_data_extracted(buf, fullsize, (void *)hdr))
+ return 0;
+
+ read += guc_capture_log_remove_dw(guc, buf, &hdr->owner);
+ read += guc_capture_log_remove_dw(guc, buf, &hdr->info);
+ read += guc_capture_log_remove_dw(guc, buf, &hdr->lrca);
+ read += guc_capture_log_remove_dw(guc, buf, &hdr->guc_id);
+ read += guc_capture_log_remove_dw(guc, buf, &hdr->num_mmios);
+ if (read != fullsize)
+ return -1;
+
+ return 0;
+}
+
+static int
+guc_capture_log_get_register(struct intel_guc *guc, struct __guc_capture_bufstate *buf,
+ struct guc_mmio_reg *reg)
+{
+ int read = 0;
+ int fullsize = sizeof(struct guc_mmio_reg);
+
+ if (fullsize > guc_capture_buf_cnt(buf))
+ return -1;
+
+ if (guc_capture_data_extracted(buf, fullsize, (void *)reg))
+ return 0;
+
+ read += guc_capture_log_remove_dw(guc, buf, ®->offset);
+ read += guc_capture_log_remove_dw(guc, buf, ®->value);
+ read += guc_capture_log_remove_dw(guc, buf, ®->flags);
+ read += guc_capture_log_remove_dw(guc, buf, ®->mask);
+ if (read != fullsize)
+ return -1;
+
+ return 0;
+}
+
+static void
+guc_capture_delete_one_node(struct intel_guc *guc, struct __guc_capture_parsed_output *node)
+{
+ int i;
+
+ for (i = 0; i < GUC_CAPTURE_LIST_TYPE_MAX; ++i)
+ kfree(node->reginfo[i].regs);
+ list_del(&node->link);
+ kfree(node);
+}
+
+static void
+guc_capture_delete_prealloc_nodes(struct intel_guc *guc)
+{
+ struct __guc_capture_parsed_output *n, *ntmp;
+
+ /*
+ * NOTE: At the end of driver operation, we must assume that we
+ * have prealloc nodes in both the cachelist as well as outlist
+ * if unclaimed error capture events occurred prior to shutdown.
+ */
+ list_for_each_entry_safe(n, ntmp, &guc->capture->outlist, link)
+ guc_capture_delete_one_node(guc, n);
+
+ list_for_each_entry_safe(n, ntmp, &guc->capture->cachelist, link)
+ guc_capture_delete_one_node(guc, n);
+}
+
+static void
+guc_capture_add_node_to_list(struct __guc_capture_parsed_output *node,
+ struct list_head *list)
+{
+ list_add_tail(&node->link, list);
+}
+
+static void
+guc_capture_add_node_to_outlist(struct intel_guc_state_capture *gc,
+ struct __guc_capture_parsed_output *node)
+{
+ guc_capture_add_node_to_list(node, &gc->outlist);
+}
+
+static void
+guc_capture_add_node_to_cachelist(struct intel_guc_state_capture *gc,
+ struct __guc_capture_parsed_output *node)
+{
+ guc_capture_add_node_to_list(node, &gc->cachelist);
+}
+
+static void
+guc_capture_init_node(struct intel_guc *guc, struct __guc_capture_parsed_output *node)
+{
+ struct guc_mmio_reg *tmp[GUC_CAPTURE_LIST_TYPE_MAX];
+ int i;
+
+ for (i = 0; i < GUC_CAPTURE_LIST_TYPE_MAX; ++i) {
+ tmp[i] = node->reginfo[i].regs;
+ memset(tmp[i], 0, sizeof(struct guc_mmio_reg) *
+ guc->capture->max_mmio_per_node);
+ }
+ memset(node, 0, sizeof(*node));
+ for (i = 0; i < GUC_CAPTURE_LIST_TYPE_MAX; ++i)
+ node->reginfo[i].regs = tmp[i];
+
+ INIT_LIST_HEAD(&node->link);
+}
+
+static struct __guc_capture_parsed_output *
+guc_capture_get_prealloc_node(struct intel_guc *guc)
+{
+ struct __guc_capture_parsed_output *found = NULL;
+
+ if (!list_empty(&guc->capture->cachelist)) {
+ struct __guc_capture_parsed_output *n, *ntmp;
+
+ /* get first avail node from the cache list */
+ list_for_each_entry_safe(n, ntmp, &guc->capture->cachelist, link) {
+ found = n;
+ list_del(&n->link);
+ break;
+ }
+ } else {
+ struct __guc_capture_parsed_output *n, *ntmp;
+
+ /* traverse down and steal back the oldest node already allocated */
+ list_for_each_entry_safe(n, ntmp, &guc->capture->outlist, link) {
+ found = n;
+ }
+ if (found)
+ list_del(&found->link);
+ }
+ if (found)
+ guc_capture_init_node(guc, found);
+
+ return found;
+}
+
+static struct __guc_capture_parsed_output *
+guc_capture_alloc_one_node(struct intel_guc *guc)
+{
+ struct __guc_capture_parsed_output *new;
+ int i;
+
+ new = kzalloc(sizeof(*new), GFP_KERNEL);
+ if (!new)
+ return NULL;
+
+ for (i = 0; i < GUC_CAPTURE_LIST_TYPE_MAX; ++i) {
+ new->reginfo[i].regs = kcalloc(guc->capture->max_mmio_per_node,
+ sizeof(struct guc_mmio_reg), GFP_KERNEL);
+ if (!new->reginfo[i].regs) {
+ while (i)
+ kfree(new->reginfo[--i].regs);
+ kfree(new);
+ return NULL;
+ }
+ }
+ guc_capture_init_node(guc, new);
+
+ return new;
+}
+
+static struct __guc_capture_parsed_output *
+guc_capture_clone_node(struct intel_guc *guc, struct __guc_capture_parsed_output *original,
+ u32 keep_reglist_mask)
+{
+ struct __guc_capture_parsed_output *new;
+ int i;
+
+ new = guc_capture_get_prealloc_node(guc);
+ if (!new)
+ return NULL;
+ if (!original)
+ return new;
+
+ new->is_partial = original->is_partial;
+
+ /* copy reg-lists that we want to clone */
+ for (i = 0; i < GUC_CAPTURE_LIST_TYPE_MAX; ++i) {
+ if (keep_reglist_mask & BIT(i)) {
+ GEM_BUG_ON(original->reginfo[i].num_regs >
+ guc->capture->max_mmio_per_node);
+
+ memcpy(new->reginfo[i].regs, original->reginfo[i].regs,
+ original->reginfo[i].num_regs * sizeof(struct guc_mmio_reg));
+
+ new->reginfo[i].num_regs = original->reginfo[i].num_regs;
+ new->reginfo[i].vfid = original->reginfo[i].vfid;
+
+ if (i == GUC_CAPTURE_LIST_TYPE_ENGINE_CLASS) {
+ new->eng_class = original->eng_class;
+ } else if (i == GUC_CAPTURE_LIST_TYPE_ENGINE_INSTANCE) {
+ new->eng_inst = original->eng_inst;
+ new->guc_id = original->guc_id;
+ new->lrca = original->lrca;
+ }
+ }
+ }
+
+ return new;
+}
+
+static void
+__guc_capture_create_prealloc_nodes(struct intel_guc *guc)
+{
+ struct __guc_capture_parsed_output *node = NULL;
+ struct drm_i915_private *i915 = guc_to_gt(guc)->i915;
+ int i;
+
+ for (i = 0; i < PREALLOC_NODES_MAX_COUNT; ++i) {
+ node = guc_capture_alloc_one_node(guc);
+ if (!node) {
+ drm_warn(&i915->drm, "GuC Capture pre-alloc-cache failure\n");
+ /* dont free the priors, use what we got and cleanup at shutdown */
+ return;
+ }
+ guc_capture_add_node_to_cachelist(guc->capture, node);
+ }
+}
+
+static int
+guc_get_max_reglist_count(struct intel_guc *guc)
+{
+ int i, j, k, tmp, maxregcount = 0;
+
+ for (i = 0; i < GUC_CAPTURE_LIST_INDEX_MAX; ++i) {
+ for (j = 0; j < GUC_CAPTURE_LIST_TYPE_MAX; ++j) {
+ for (k = 0; k < GUC_MAX_ENGINE_CLASSES; ++k) {
+ if (j == GUC_CAPTURE_LIST_TYPE_GLOBAL && k > 0)
+ continue;
+
+ tmp = guc_cap_list_num_regs(guc->capture, i, j, k);
+ if (tmp > maxregcount)
+ maxregcount = tmp;
+ }
+ }
+ }
+ if (!maxregcount)
+ maxregcount = PREALLOC_NODES_DEFAULT_NUMREGS;
+
+ return maxregcount;
+}
+
+static void
+guc_capture_create_prealloc_nodes(struct intel_guc *guc)
+{
+ /* skip if we've already done the pre-alloc */
+ if (guc->capture->max_mmio_per_node)
+ return;
+
+ guc->capture->max_mmio_per_node = guc_get_max_reglist_count(guc);
+ __guc_capture_create_prealloc_nodes(guc);
+}
+
+static int
+guc_capture_extract_reglists(struct intel_guc *guc, struct __guc_capture_bufstate *buf)
+{
+ struct drm_i915_private *i915 = guc_to_gt(guc)->i915;
+ struct guc_state_capture_group_header_t ghdr = {0};
+ struct guc_state_capture_header_t hdr = {0};
+ struct __guc_capture_parsed_output *node = NULL;
+ struct guc_mmio_reg *regs = NULL;
+ int i, numlists, numregs, ret = 0;
+ enum guc_capture_type datatype;
+ struct guc_mmio_reg tmp;
+ bool is_partial = false;
+
+ i = guc_capture_buf_cnt(buf);
+ if (!i)
+ return -ENODATA;
+ if (i % sizeof(u32)) {
+ drm_warn(&i915->drm, "GuC Capture new entries unaligned\n");
+ ret = -EIO;
+ goto bailout;
+ }
+
+ /* first get the capture group header */
+ if (guc_capture_log_get_group_hdr(guc, buf, &ghdr)) {
+ ret = -EIO;
+ goto bailout;
+ }
+ /*
+ * we would typically expect a layout as below where n would be expected to be
+ * anywhere between 3 to n where n > 3 if we are seeing multiple dependent engine
+ * instances being reset together.
+ * ____________________________________________
+ * | Capture Group |
+ * | ________________________________________ |
+ * | | Capture Group Header: | |
+ * | | - num_captures = 5 | |
+ * | |______________________________________| |
+ * | ________________________________________ |
+ * | | Capture1: | |
+ * | | Hdr: GLOBAL, numregs=a | |
+ * | | ____________________________________ | |
+ * | | | Reglist | | |
+ * | | | - reg1, reg2, ... rega | | |
+ * | | |__________________________________| | |
+ * | |______________________________________| |
+ * | ________________________________________ |
+ * | | Capture2: | |
+ * | | Hdr: CLASS=RENDER/COMPUTE, numregs=b| |
+ * | | ____________________________________ | |
+ * | | | Reglist | | |
+ * | | | - reg1, reg2, ... regb | | |
+ * | | |__________________________________| | |
+ * | |______________________________________| |
+ * | ________________________________________ |
+ * | | Capture3: | |
+ * | | Hdr: INSTANCE=RCS, numregs=c | |
+ * | | ____________________________________ | |
+ * | | | Reglist | | |
+ * | | | - reg1, reg2, ... regc | | |
+ * | | |__________________________________| | |
+ * | |______________________________________| |
+ * | ________________________________________ |
+ * | | Capture4: | |
+ * | | Hdr: CLASS=RENDER/COMPUTE, numregs=d| |
+ * | | ____________________________________ | |
+ * | | | Reglist | | |
+ * | | | - reg1, reg2, ... regd | | |
+ * | | |__________________________________| | |
+ * | |______________________________________| |
+ * | ________________________________________ |
+ * | | Capture5: | |
+ * | | Hdr: INSTANCE=CCS0, numregs=e | |
+ * | | ____________________________________ | |
+ * | | | Reglist | | |
+ * | | | - reg1, reg2, ... rege | | |
+ * | | |__________________________________| | |
+ * | |______________________________________| |
+ * |__________________________________________|
+ */
+ is_partial = FIELD_GET(CAP_GRP_HDR_CAPTURE_TYPE, ghdr.info);
+ numlists = FIELD_GET(CAP_GRP_HDR_NUM_CAPTURES, ghdr.info);
+
+ while (numlists--) {
+ if (guc_capture_log_get_data_hdr(guc, buf, &hdr)) {
+ ret = -EIO;
+ break;
+ }
+
+ datatype = FIELD_GET(CAP_HDR_CAPTURE_TYPE, hdr.info);
+ if (datatype > GUC_CAPTURE_LIST_TYPE_ENGINE_INSTANCE) {
+ /* unknown capture type - skip over to next capture set */
+ numregs = FIELD_GET(CAP_HDR_NUM_MMIOS, hdr.num_mmios);
+ while (numregs--) {
+ if (guc_capture_log_get_register(guc, buf, &tmp)) {
+ ret = -EIO;
+ break;
+ }
+ }
+ continue;
+ } else if (node) {
+ /*
+ * Based on the current capture type and what we have so far,
+ * decide if we should add the current node into the internal
+ * linked list for match-up when i915_gpu_coredump calls later
+ * (and alloc a blank node for the next set of reglists)
+ * or continue with the same node or clone the current node
+ * but only retain the global or class registers (such as the
+ * case of dependent engine resets).
+ */
+ if (datatype == GUC_CAPTURE_LIST_TYPE_GLOBAL) {
+ guc_capture_add_node_to_outlist(guc->capture, node);
+ node = NULL;
+ } else if (datatype == GUC_CAPTURE_LIST_TYPE_ENGINE_CLASS &&
+ node->reginfo[GUC_CAPTURE_LIST_TYPE_ENGINE_CLASS].num_regs) {
+ /* Add to list, clone node and duplicate global list */
+ guc_capture_add_node_to_outlist(guc->capture, node);
+ node = guc_capture_clone_node(guc, node,
+ GCAP_PARSED_REGLIST_INDEX_GLOBAL);
+ } else if (datatype == GUC_CAPTURE_LIST_TYPE_ENGINE_INSTANCE &&
+ node->reginfo[GUC_CAPTURE_LIST_TYPE_ENGINE_INSTANCE].num_regs) {
+ /* Add to list, clone node and duplicate global + class lists */
+ guc_capture_add_node_to_outlist(guc->capture, node);
+ node = guc_capture_clone_node(guc, node,
+ (GCAP_PARSED_REGLIST_INDEX_GLOBAL |
+ GCAP_PARSED_REGLIST_INDEX_ENGCLASS));
+ }
+ }
+
+ if (!node) {
+ node = guc_capture_get_prealloc_node(guc);
+ if (!node) {
+ ret = -ENOMEM;
+ break;
+ }
+ if (datatype != GUC_CAPTURE_LIST_TYPE_GLOBAL)
+ drm_dbg(&i915->drm, "GuC Capture missing global dump: %08x!\n",
+ datatype);
+ }
+ node->is_partial = is_partial;
+ node->reginfo[datatype].vfid = FIELD_GET(CAP_HDR_CAPTURE_VFID, hdr.owner);
+ switch (datatype) {
+ case GUC_CAPTURE_LIST_TYPE_ENGINE_INSTANCE:
+ node->eng_class = FIELD_GET(CAP_HDR_ENGINE_CLASS, hdr.info);
+ node->eng_inst = FIELD_GET(CAP_HDR_ENGINE_INSTANCE, hdr.info);
+ node->lrca = hdr.lrca;
+ node->guc_id = hdr.guc_id;
+ break;
+ case GUC_CAPTURE_LIST_TYPE_ENGINE_CLASS:
+ node->eng_class = FIELD_GET(CAP_HDR_ENGINE_CLASS, hdr.info);
+ break;
+ default:
+ break;
+ }
+
+ numregs = FIELD_GET(CAP_HDR_NUM_MMIOS, hdr.num_mmios);
+ if (numregs > guc->capture->max_mmio_per_node) {
+ drm_dbg(&i915->drm, "GuC Capture list extraction clipped by prealloc!\n");
+ numregs = guc->capture->max_mmio_per_node;
+ }
+ node->reginfo[datatype].num_regs = numregs;
+ regs = node->reginfo[datatype].regs;
+ i = 0;
+ while (numregs--) {
+ if (guc_capture_log_get_register(guc, buf, ®s[i++])) {
+ ret = -EIO;
+ break;
+ }
+ }
+ }
+
+bailout:
+ if (node) {
+ /* If we have data, add to linked list for match-up when i915_gpu_coredump calls */
+ for (i = GUC_CAPTURE_LIST_TYPE_GLOBAL; i < GUC_CAPTURE_LIST_TYPE_MAX; ++i) {
+ if (node->reginfo[i].regs) {
+ guc_capture_add_node_to_outlist(guc->capture, node);
+ node = NULL;
+ break;
+ }
+ }
+ if (node) /* else return it back to cache list */
+ guc_capture_add_node_to_cachelist(guc->capture, node);
+ }
+ return ret;
+}
+
+static int __guc_capture_flushlog_complete(struct intel_guc *guc)
+{
+ u32 action[] = {
+ INTEL_GUC_ACTION_LOG_BUFFER_FILE_FLUSH_COMPLETE,
+ GUC_CAPTURE_LOG_BUFFER
+ };
+
+ return intel_guc_send(guc, action, ARRAY_SIZE(action));
+}
+
+static void __guc_capture_process_output(struct intel_guc *guc)
+{
+ unsigned int buffer_size, read_offset, write_offset, full_count;
+ struct intel_uc *uc = container_of(guc, typeof(*uc), guc);
+ struct drm_i915_private *i915 = guc_to_gt(guc)->i915;
+ struct guc_log_buffer_state log_buf_state_local;
+ struct guc_log_buffer_state *log_buf_state;
+ struct __guc_capture_bufstate buf;
+ void *src_data = NULL;
+ bool new_overflow;
+ int ret;
+
+ log_buf_state = guc->log.buf_addr +
+ (sizeof(struct guc_log_buffer_state) * GUC_CAPTURE_LOG_BUFFER);
+ src_data = guc->log.buf_addr + intel_guc_get_log_buffer_offset(GUC_CAPTURE_LOG_BUFFER);
+
+ /*
+ * Make a copy of the state structure, inside GuC log buffer
+ * (which is uncached mapped), on the stack to avoid reading
+ * from it multiple times.
+ */
+ memcpy(&log_buf_state_local, log_buf_state, sizeof(struct guc_log_buffer_state));
+ buffer_size = intel_guc_get_log_buffer_size(GUC_CAPTURE_LOG_BUFFER);
+ read_offset = log_buf_state_local.read_ptr;
+ write_offset = log_buf_state_local.sampled_write_ptr;
+ full_count = log_buf_state_local.buffer_full_cnt;
+
+ /* Bookkeeping stuff */
+ guc->log.stats[GUC_CAPTURE_LOG_BUFFER].flush += log_buf_state_local.flush_to_file;
+ new_overflow = intel_guc_check_log_buf_overflow(&guc->log, GUC_CAPTURE_LOG_BUFFER,
+ full_count);
+
+ /* Now copy the actual logs. */
+ if (unlikely(new_overflow)) {
+ /* copy the whole buffer in case of overflow */
+ read_offset = 0;
+ write_offset = buffer_size;
+ } else if (unlikely((read_offset > buffer_size) ||
+ (write_offset > buffer_size))) {
+ drm_err(&i915->drm, "invalid GuC log capture buffer state!\n");
+ /* copy whole buffer as offsets are unreliable */
+ read_offset = 0;
+ write_offset = buffer_size;
+ }
+
+ buf.size = buffer_size;
+ buf.rd = read_offset;
+ buf.wr = write_offset;
+ buf.data = src_data;
+
+ if (!uc->reset_in_progress) {
+ do {
+ ret = guc_capture_extract_reglists(guc, &buf);
+ } while (ret >= 0);
+ }
+
+ /* Update the state of log buffer err-cap state */
+ log_buf_state->read_ptr = write_offset;
+ log_buf_state->flush_to_file = 0;
+ __guc_capture_flushlog_complete(guc);
+}
+
+#if IS_ENABLED(CONFIG_DRM_I915_CAPTURE_ERROR)
+
+static const char *
+guc_capture_reg_to_str(const struct intel_guc *guc, u32 owner, u32 type,
+ u32 class, u32 id, u32 offset, u32 *is_ext)
+{
+ const struct __guc_mmio_reg_descr_group *reglists = guc->capture->reglists;
+ struct __guc_mmio_reg_descr_group *extlists = guc->capture->extlists;
+ const struct __guc_mmio_reg_descr_group *match;
+ struct __guc_mmio_reg_descr_group *matchext;
+ int j;
+
+ *is_ext = 0;
+ if (!reglists)
+ return NULL;
+
+ match = guc_capture_get_one_list(reglists, owner, type, id);
+ if (!match)
+ return NULL;
+
+ for (j = 0; j < match->num_regs; ++j) {
+ if (offset == match->list[j].reg.reg)
+ return match->list[j].regname;
+ }
+ if (extlists) {
+ matchext = guc_capture_get_one_ext_list(extlists, owner, type, id);
+ if (!matchext)
+ return NULL;
+ for (j = 0; j < matchext->num_regs; ++j) {
+ if (offset == matchext->extlist[j].reg.reg) {
+ *is_ext = 1;
+ return matchext->extlist[j].regname;
+ }
+ }
+ }
+
+ return NULL;
+}
+
+#ifdef CONFIG_DRM_I915_DEBUG_GUC
+#define __out(a, ...) \
+ do { \
+ drm_warn((&(a)->i915->drm), __VA_ARGS__); \
+ i915_error_printf((a), __VA_ARGS__); \
+ } while (0)
+#else
+#define __out(a, ...) \
+ i915_error_printf(a, __VA_ARGS__)
+#endif
+
+#define GCAP_PRINT_INTEL_ENG_INFO(ebuf, eng) \
+ do { \
+ __out(ebuf, " i915-Eng-Name: %s command stream\n", \
+ (eng)->name); \
+ __out(ebuf, " i915-Eng-Inst-Class: 0x%02x\n", (eng)->class); \
+ __out(ebuf, " i915-Eng-Inst-Id: 0x%02x\n", (eng)->instance); \
+ __out(ebuf, " i915-Eng-LogicalMask: 0x%08x\n", \
+ (eng)->logical_mask); \
+ } while (0)
+
+#define GCAP_PRINT_GUC_INST_INFO(ebuf, node) \
+ do { \
+ __out(ebuf, " GuC-Engine-Inst-Id: 0x%08x\n", \
+ (node)->eng_inst); \
+ __out(ebuf, " GuC-Context-Id: 0x%08x\n", (node)->guc_id); \
+ __out(ebuf, " LRCA: 0x%08x\n", (node)->lrca); \
+ } while (0)
+
+int intel_guc_capture_print_engine_node(struct drm_i915_error_state_buf *ebuf,
+ const struct intel_engine_coredump *ee)
+{
+ const char *grptype[GUC_STATE_CAPTURE_GROUP_TYPE_MAX] = {
+ "full-capture",
+ "partial-capture"
+ };
+ const char *datatype[GUC_CAPTURE_LIST_TYPE_MAX] = {
+ "Global",
+ "Engine-Class",
+ "Engine-Instance"
+ };
+ struct intel_guc_state_capture *cap;
+ struct __guc_capture_parsed_output *node;
+ struct intel_engine_cs *eng;
+ struct guc_mmio_reg *regs;
+ struct intel_guc *guc;
+ const char *str;
+ int numregs, i, j;
+ u32 is_ext;
+
+ if (!ebuf || !ee)
+ return -EINVAL;
+ cap = ee->capture;
+ if (!cap || !ee->engine)
+ return -ENODEV;
+
+ guc = &ee->engine->gt->uc.guc;
+
+ __out(ebuf, "global --- GuC Error Capture on %s command stream:\n",
+ ee->engine->name);
+
+ node = ee->guc_capture_node;
+ if (!node) {
+ __out(ebuf, " No matching ee-node\n");
+ return 0;
+ }
+
+ __out(ebuf, "Coverage: %s\n", grptype[node->is_partial]);
+
+ for (i = GUC_CAPTURE_LIST_TYPE_GLOBAL; i < GUC_CAPTURE_LIST_TYPE_MAX; ++i) {
+ __out(ebuf, " RegListType: %s\n",
+ datatype[i % GUC_CAPTURE_LIST_TYPE_MAX]);
+ __out(ebuf, " Owner-Id: %d\n", node->reginfo[i].vfid);
+
+ switch (i) {
+ case GUC_CAPTURE_LIST_TYPE_GLOBAL:
+ default:
+ break;
+ case GUC_CAPTURE_LIST_TYPE_ENGINE_CLASS:
+ __out(ebuf, " GuC-Eng-Class: %d\n", node->eng_class);
+ __out(ebuf, " i915-Eng-Class: %d\n",
+ guc_class_to_engine_class(node->eng_class));
+ break;
+ case GUC_CAPTURE_LIST_TYPE_ENGINE_INSTANCE:
+ eng = intel_guc_lookup_engine(guc, node->eng_class, node->eng_inst);
+ if (eng)
+ GCAP_PRINT_INTEL_ENG_INFO(ebuf, eng);
+ else
+ __out(ebuf, " i915-Eng-Lookup Fail!\n");
+ GCAP_PRINT_GUC_INST_INFO(ebuf, node);
+ break;
+ }
+
+ numregs = node->reginfo[i].num_regs;
+ __out(ebuf, " NumRegs: %d\n", numregs);
+ j = 0;
+ while (numregs--) {
+ regs = node->reginfo[i].regs;
+ str = guc_capture_reg_to_str(guc, GUC_CAPTURE_LIST_INDEX_PF, i,
+ node->eng_class, 0, regs[j].offset, &is_ext);
+ if (!str)
+ __out(ebuf, " REG-0x%08x", regs[j].offset);
+ else
+ __out(ebuf, " %s", str);
+ if (is_ext)
+ __out(ebuf, "[%ld][%ld]",
+ FIELD_GET(GUC_REGSET_STEERING_GROUP, regs[j].flags),
+ FIELD_GET(GUC_REGSET_STEERING_INSTANCE, regs[j].flags));
+ __out(ebuf, ": 0x%08x\n", regs[j].value);
+ ++j;
+ }
+ }
+ return 0;
+}
+
+#endif //CONFIG_DRM_I915_CAPTURE_ERROR
+
+void intel_guc_capture_free_node(struct intel_engine_coredump *ee)
+{
+ if (!ee || !ee->guc_capture_node)
+ return;
+
+ guc_capture_add_node_to_cachelist(ee->capture, ee->guc_capture_node);
+ ee->capture = NULL;
+ ee->guc_capture_node = NULL;
+}
+
+void intel_guc_capture_get_matching_node(struct intel_gt *gt,
+ struct intel_engine_coredump *ee,
+ struct intel_context *ce)
+{
+ struct __guc_capture_parsed_output *n, *ntmp;
+ struct drm_i915_private *i915;
+ struct intel_guc *guc;
+
+ if (!gt || !ee || !ce)
+ return;
+
+ i915 = gt->i915;
+ guc = >->uc.guc;
+ if (!guc->capture)
+ return;
+
+ GEM_BUG_ON(ee->guc_capture_node);
+ /*
+ * Look for a matching GuC reported error capture node from
+ * the internal output link-list based on lrca, guc-id and engine
+ * identification.
+ */
+ list_for_each_entry_safe(n, ntmp, &guc->capture->outlist, link) {
+ if (n->eng_inst == GUC_ID_TO_ENGINE_INSTANCE(ee->engine->guc_id) &&
+ n->eng_class == GUC_ID_TO_ENGINE_CLASS(ee->engine->guc_id) &&
+ n->guc_id && n->guc_id == ce->guc_id.id &&
+ (n->lrca & CTX_GTT_ADDRESS_MASK) && (n->lrca & CTX_GTT_ADDRESS_MASK) ==
+ (ce->lrc.lrca & CTX_GTT_ADDRESS_MASK)) {
+ list_del(&n->link);
+ ee->guc_capture_node = n;
+ ee->capture = guc->capture;
+ return;
+ }
+ }
+ drm_dbg(&i915->drm, "GuC capture can't match ee to node\n");
+}
+
+void intel_guc_capture_process(struct intel_guc *guc)
+{
+ if (guc->capture)
+ __guc_capture_process_output(guc);
+}
+
+static void
+guc_capture_free_ads_cache(struct intel_guc_state_capture *gc)
+{
+ int i, j, k;
+ struct __guc_capture_ads_cache *cache;
+
+ for (i = 0; i < GUC_CAPTURE_LIST_INDEX_MAX; ++i) {
+ for (j = 0; j < GUC_CAPTURE_LIST_TYPE_MAX; ++j) {
+ for (k = 0; k < GUC_MAX_ENGINE_CLASSES; ++k) {
+ cache = &gc->ads_cache[i][j][k];
+ if (cache->is_valid)
+ kfree(cache->ptr);
+ }
+ }
+ }
+ kfree(gc->ads_null_cache);
+}
+
+void intel_guc_capture_destroy(struct intel_guc *guc)
+{
+ if (!guc->capture)
+ return;
+
+ guc_capture_free_ads_cache(guc->capture);
+
+ guc_capture_delete_prealloc_nodes(guc);
+
+ guc_capture_free_extlists(guc->capture->extlists);
+ kfree(guc->capture->extlists);
+
+ kfree(guc->capture);
+ guc->capture = NULL;
+}
+
+int intel_guc_capture_init(struct intel_guc *guc)
+{
+ guc->capture = kzalloc(sizeof(*guc->capture), GFP_KERNEL);
+ if (!guc->capture)
+ return -ENOMEM;
+
+ guc->capture->reglists = guc_capture_get_device_reglist(guc);
+
+ INIT_LIST_HEAD(&guc->capture->outlist);
+ INIT_LIST_HEAD(&guc->capture->cachelist);
+
+ return 0;
+}
--- /dev/null
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2021-2021 Intel Corporation
+ */
+
+#ifndef _INTEL_GUC_CAPTURE_H
+#define _INTEL_GUC_CAPTURE_H
+
+#include <linux/types.h>
+
+struct drm_i915_error_state_buf;
+struct guc_gt_system_info;
+struct intel_engine_coredump;
+struct intel_context;
+struct intel_gt;
+struct intel_guc;
+
+void intel_guc_capture_free_node(struct intel_engine_coredump *ee);
+int intel_guc_capture_print_engine_node(struct drm_i915_error_state_buf *m,
+ const struct intel_engine_coredump *ee);
+void intel_guc_capture_get_matching_node(struct intel_gt *gt, struct intel_engine_coredump *ee,
+ struct intel_context *ce);
+void intel_guc_capture_process(struct intel_guc *guc);
+int intel_guc_capture_output_min_size_est(struct intel_guc *guc);
+int intel_guc_capture_getlist(struct intel_guc *guc, u32 owner, u32 type, u32 classid,
+ void **outptr);
+int intel_guc_capture_getlistsize(struct intel_guc *guc, u32 owner, u32 type, u32 classid,
+ size_t *size);
+int intel_guc_capture_getnullheader(struct intel_guc *guc, void **outptr, size_t *size);
+void intel_guc_capture_destroy(struct intel_guc *guc);
+int intel_guc_capture_init(struct intel_guc *guc);
+
+#endif /* _INTEL_GUC_CAPTURE_H */
#define GUC_CLIENT_PRIORITY_NORMAL 3
#define GUC_CLIENT_PRIORITY_NUM 4
-#define GUC_MAX_LRC_DESCRIPTORS 65535
-#define GUC_INVALID_LRC_ID GUC_MAX_LRC_DESCRIPTORS
+#define GUC_MAX_CONTEXT_ID 65535
+#define GUC_INVALID_CONTEXT_ID GUC_MAX_CONTEXT_ID
#define GUC_RENDER_ENGINE 0
#define GUC_VIDEO_ENGINE 1
u32 offset;
u32 value;
u32 flags;
- u32 mask;
#define GUC_REGSET_MASKED BIT(0)
+#define GUC_REGSET_NEEDS_STEERING BIT(1)
#define GUC_REGSET_MASKED_WITH_VALUE BIT(2)
#define GUC_REGSET_RESTORE_ONLY BIT(3)
+#define GUC_REGSET_STEERING_GROUP GENMASK(15, 12)
+#define GUC_REGSET_STEERING_INSTANCE GENMASK(23, 20)
+ u32 mask;
} __packed;
/* GuC register sets */
GUC_CAPTURE_LIST_INDEX_MAX = 2,
};
+/*Register-types of GuC capture register lists */
+enum guc_capture_type {
+ GUC_CAPTURE_LIST_TYPE_GLOBAL = 0,
+ GUC_CAPTURE_LIST_TYPE_ENGINE_CLASS,
+ GUC_CAPTURE_LIST_TYPE_ENGINE_INSTANCE,
+ GUC_CAPTURE_LIST_TYPE_MAX,
+};
+
/* GuC Additional Data Struct */
struct guc_ads {
struct guc_mmio_reg_set reg_state_list[GUC_MAX_ENGINE_CLASSES][GUC_MAX_INSTANCES_PER_CLASS];
--- /dev/null
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2022 Intel Corporation
+ */
+
+#include "gt/intel_gt.h"
+#include "gt/intel_hwconfig.h"
+#include "i915_drv.h"
+#include "i915_memcpy.h"
+
+/*
+ * GuC has a blob containing hardware configuration information (HWConfig).
+ * This is formatted as a simple and flexible KLV (Key/Length/Value) table.
+ *
+ * For example, a minimal version could be:
+ * enum device_attr {
+ * ATTR_SOME_VALUE = 0,
+ * ATTR_SOME_MASK = 1,
+ * };
+ *
+ * static const u32 hwconfig[] = {
+ * ATTR_SOME_VALUE,
+ * 1, // Value Length in DWords
+ * 8, // Value
+ *
+ * ATTR_SOME_MASK,
+ * 3,
+ * 0x00FFFFFFFF, 0xFFFFFFFF, 0xFF000000,
+ * };
+ *
+ * The attribute ids are defined in a hardware spec.
+ */
+
+static int __guc_action_get_hwconfig(struct intel_guc *guc,
+ u32 ggtt_offset, u32 ggtt_size)
+{
+ u32 action[] = {
+ INTEL_GUC_ACTION_GET_HWCONFIG,
+ lower_32_bits(ggtt_offset),
+ upper_32_bits(ggtt_offset),
+ ggtt_size,
+ };
+ int ret;
+
+ ret = intel_guc_send_mmio(guc, action, ARRAY_SIZE(action), NULL, 0);
+ if (ret == -ENXIO)
+ return -ENOENT;
+
+ return ret;
+}
+
+static int guc_hwconfig_discover_size(struct intel_guc *guc, struct intel_hwconfig *hwconfig)
+{
+ int ret;
+
+ /*
+ * Sending a query with zero offset and size will return the
+ * size of the blob.
+ */
+ ret = __guc_action_get_hwconfig(guc, 0, 0);
+ if (ret < 0)
+ return ret;
+
+ if (ret == 0)
+ return -EINVAL;
+
+ hwconfig->size = ret;
+ return 0;
+}
+
+static int guc_hwconfig_fill_buffer(struct intel_guc *guc, struct intel_hwconfig *hwconfig)
+{
+ struct i915_vma *vma;
+ u32 ggtt_offset;
+ void *vaddr;
+ int ret;
+
+ GEM_BUG_ON(!hwconfig->size);
+
+ ret = intel_guc_allocate_and_map_vma(guc, hwconfig->size, &vma, &vaddr);
+ if (ret)
+ return ret;
+
+ ggtt_offset = intel_guc_ggtt_offset(guc, vma);
+
+ ret = __guc_action_get_hwconfig(guc, ggtt_offset, hwconfig->size);
+ if (ret >= 0)
+ memcpy(hwconfig->ptr, vaddr, hwconfig->size);
+
+ i915_vma_unpin_and_release(&vma, I915_VMA_RELEASE_MAP);
+
+ return ret;
+}
+
+static bool has_table(struct drm_i915_private *i915)
+{
+ if (IS_ALDERLAKE_P(i915))
+ return true;
+
+ return false;
+}
+
+/**
+ * intel_guc_hwconfig_init - Initialize the HWConfig
+ *
+ * Retrieve the HWConfig table from the GuC and save it locally.
+ * It can then be queried on demand by other users later on.
+ */
+static int guc_hwconfig_init(struct intel_gt *gt)
+{
+ struct intel_hwconfig *hwconfig = >->info.hwconfig;
+ struct intel_guc *guc = >->uc.guc;
+ int ret;
+
+ if (!has_table(gt->i915))
+ return 0;
+
+ ret = guc_hwconfig_discover_size(guc, hwconfig);
+ if (ret)
+ return ret;
+
+ hwconfig->ptr = kmalloc(hwconfig->size, GFP_KERNEL);
+ if (!hwconfig->ptr) {
+ hwconfig->size = 0;
+ return -ENOMEM;
+ }
+
+ ret = guc_hwconfig_fill_buffer(guc, hwconfig);
+ if (ret < 0) {
+ intel_gt_fini_hwconfig(gt);
+ return ret;
+ }
+
+ return 0;
+}
+
+/**
+ * intel_gt_init_hwconfig - Initialize the HWConfig if available
+ *
+ * Retrieve the HWConfig table if available on the current platform.
+ */
+int intel_gt_init_hwconfig(struct intel_gt *gt)
+{
+ if (!intel_uc_uses_guc(>->uc))
+ return 0;
+
+ return guc_hwconfig_init(gt);
+}
+
+/**
+ * intel_gt_fini_hwconfig - Finalize the HWConfig
+ *
+ * Free up the memory allocation holding the table.
+ */
+void intel_gt_fini_hwconfig(struct intel_gt *gt)
+{
+ struct intel_hwconfig *hwconfig = >->info.hwconfig;
+
+ kfree(hwconfig->ptr);
+ hwconfig->size = 0;
+ hwconfig->ptr = NULL;
+}
#include "i915_drv.h"
#include "i915_irq.h"
#include "i915_memcpy.h"
+#include "intel_guc_capture.h"
#include "intel_guc_log.h"
-static void guc_log_capture_logs(struct intel_guc_log *log);
+static void guc_log_copy_debuglogs_for_relay(struct intel_guc_log *log);
/**
* DOC: GuC firmware log
static int guc_action_flush_log_complete(struct intel_guc *guc)
{
u32 action[] = {
- INTEL_GUC_ACTION_LOG_BUFFER_FILE_FLUSH_COMPLETE
+ INTEL_GUC_ACTION_LOG_BUFFER_FILE_FLUSH_COMPLETE,
+ GUC_DEBUG_LOG_BUFFER
};
return intel_guc_send(guc, action, ARRAY_SIZE(action));
smp_wmb();
/* All data has been written, so now move the offset of sub buffer. */
- relay_reserve(log->relay.channel, log->vma->obj->base.size);
+ relay_reserve(log->relay.channel, log->vma->obj->base.size - CAPTURE_BUFFER_SIZE);
/* Switch to the next sub buffer */
relay_flush(log->relay.channel);
return relay_reserve(log->relay.channel, 0);
}
-static bool guc_check_log_buf_overflow(struct intel_guc_log *log,
- enum guc_log_buffer_type type,
- unsigned int full_cnt)
+bool intel_guc_check_log_buf_overflow(struct intel_guc_log *log,
+ enum guc_log_buffer_type type,
+ unsigned int full_cnt)
{
unsigned int prev_full_cnt = log->stats[type].sampled_overflow;
bool overflow = false;
return overflow;
}
-static unsigned int guc_get_log_buffer_size(enum guc_log_buffer_type type)
+unsigned int intel_guc_get_log_buffer_size(enum guc_log_buffer_type type)
{
switch (type) {
case GUC_DEBUG_LOG_BUFFER:
return 0;
}
-static void guc_read_update_log_buffer(struct intel_guc_log *log)
+size_t intel_guc_get_log_buffer_offset(enum guc_log_buffer_type type)
+{
+ enum guc_log_buffer_type i;
+ size_t offset = PAGE_SIZE;/* for the log_buffer_states */
+
+ for (i = GUC_DEBUG_LOG_BUFFER; i < GUC_MAX_LOG_BUFFER; ++i) {
+ if (i == type)
+ break;
+ offset += intel_guc_get_log_buffer_size(i);
+ }
+
+ return offset;
+}
+
+static void _guc_log_copy_debuglogs_for_relay(struct intel_guc_log *log)
{
unsigned int buffer_size, read_offset, write_offset, bytes_to_copy, full_cnt;
struct guc_log_buffer_state *log_buf_state, *log_buf_snapshot_state;
goto out_unlock;
/* Get the pointer to shared GuC log buffer */
- log_buf_state = src_data = log->relay.buf_addr;
+ src_data = log->buf_addr;
+ log_buf_state = src_data;
/* Get the pointer to local buffer to store the logs */
log_buf_snapshot_state = dst_data = guc_get_write_buffer(log);
* Used rate limited to avoid deluge of messages, logs might be
* getting consumed by User at a slow rate.
*/
- DRM_ERROR_RATELIMITED("no sub-buffer to capture logs\n");
+ DRM_ERROR_RATELIMITED("no sub-buffer to copy general logs\n");
log->relay.full_count++;
goto out_unlock;
src_data += PAGE_SIZE;
dst_data += PAGE_SIZE;
- for (type = GUC_DEBUG_LOG_BUFFER; type < GUC_MAX_LOG_BUFFER; type++) {
+ /* For relay logging, we exclude error state capture */
+ for (type = GUC_DEBUG_LOG_BUFFER; type <= GUC_CRASH_DUMP_LOG_BUFFER; type++) {
/*
* Make a copy of the state structure, inside GuC log buffer
* (which is uncached mapped), on the stack to avoid reading
*/
memcpy(&log_buf_state_local, log_buf_state,
sizeof(struct guc_log_buffer_state));
- buffer_size = guc_get_log_buffer_size(type);
+ buffer_size = intel_guc_get_log_buffer_size(type);
read_offset = log_buf_state_local.read_ptr;
write_offset = log_buf_state_local.sampled_write_ptr;
full_cnt = log_buf_state_local.buffer_full_cnt;
/* Bookkeeping stuff */
log->stats[type].flush += log_buf_state_local.flush_to_file;
- new_overflow = guc_check_log_buf_overflow(log, type, full_cnt);
+ new_overflow = intel_guc_check_log_buf_overflow(log, type, full_cnt);
/* Update the state of shared log buffer */
log_buf_state->read_ptr = write_offset;
mutex_unlock(&log->relay.lock);
}
-static void capture_logs_work(struct work_struct *work)
+static void copy_debug_logs_work(struct work_struct *work)
{
struct intel_guc_log *log =
container_of(work, struct intel_guc_log, relay.flush_work);
- guc_log_capture_logs(log);
+ guc_log_copy_debuglogs_for_relay(log);
}
-static int guc_log_map(struct intel_guc_log *log)
+static int guc_log_relay_map(struct intel_guc_log *log)
{
- void *vaddr;
-
lockdep_assert_held(&log->relay.lock);
- if (!log->vma)
+ if (!log->vma || !log->buf_addr)
return -ENODEV;
/*
- * Create a WC (Uncached for read) vmalloc mapping of log
- * buffer pages, so that we can directly get the data
- * (up-to-date) from memory.
+ * WC vmalloc mapping of log buffer pages was done at
+ * GuC Log Init time, but lets keep a ref for book-keeping
*/
- vaddr = i915_gem_object_pin_map_unlocked(log->vma->obj, I915_MAP_WC);
- if (IS_ERR(vaddr))
- return PTR_ERR(vaddr);
-
- log->relay.buf_addr = vaddr;
+ i915_gem_object_get(log->vma->obj);
+ log->relay.buf_in_use = true;
return 0;
}
-static void guc_log_unmap(struct intel_guc_log *log)
+static void guc_log_relay_unmap(struct intel_guc_log *log)
{
lockdep_assert_held(&log->relay.lock);
- i915_gem_object_unpin_map(log->vma->obj);
- log->relay.buf_addr = NULL;
+ i915_gem_object_put(log->vma->obj);
+ log->relay.buf_in_use = false;
}
void intel_guc_log_init_early(struct intel_guc_log *log)
{
mutex_init(&log->relay.lock);
- INIT_WORK(&log->relay.flush_work, capture_logs_work);
+ INIT_WORK(&log->relay.flush_work, copy_debug_logs_work);
log->relay.started = false;
}
lockdep_assert_held(&log->relay.lock);
GEM_BUG_ON(!log->vma);
- /* Keep the size of sub buffers same as shared log buffer */
- subbuf_size = log->vma->size;
+ /*
+ * Keep the size of sub buffers same as shared log buffer
+ * but GuC log-events excludes the error-state-capture logs
+ */
+ subbuf_size = log->vma->size - CAPTURE_BUFFER_SIZE;
/*
* Store up to 8 snapshots, which is large enough to buffer sufficient
log->relay.channel = NULL;
}
-static void guc_log_capture_logs(struct intel_guc_log *log)
+static void guc_log_copy_debuglogs_for_relay(struct intel_guc_log *log)
{
struct intel_guc *guc = log_to_guc(log);
struct drm_i915_private *dev_priv = guc_to_gt(guc)->i915;
intel_wakeref_t wakeref;
- guc_read_update_log_buffer(log);
+ _guc_log_copy_debuglogs_for_relay(log);
/*
* Generally device is expected to be active only at this
{
struct intel_guc *guc = log_to_guc(log);
struct i915_vma *vma;
+ void *vaddr;
u32 guc_log_size;
int ret;
/*
* GuC Log buffer Layout
+ * (this ordering must follow "enum guc_log_buffer_type" definition)
*
* +===============================+ 00B
- * | Crash dump state header |
- * +-------------------------------+ 32B
* | Debug state header |
+ * +-------------------------------+ 32B
+ * | Crash dump state header |
* +-------------------------------+ 64B
* | Capture state header |
* +-------------------------------+ 96B
* | |
* +===============================+ PAGE_SIZE (4KB)
- * | Crash Dump logs |
- * +===============================+ + CRASH_SIZE
* | Debug logs |
* +===============================+ + DEBUG_SIZE
+ * | Crash Dump logs |
+ * +===============================+ + CRASH_SIZE
* | Capture logs |
* +===============================+ + CAPTURE_SIZE
*/
+ if (intel_guc_capture_output_min_size_est(guc) > CAPTURE_BUFFER_SIZE)
+ DRM_WARN("GuC log buffer for state_capture maybe too small. %d < %d\n",
+ CAPTURE_BUFFER_SIZE, intel_guc_capture_output_min_size_est(guc));
+
guc_log_size = PAGE_SIZE + CRASH_BUFFER_SIZE + DEBUG_BUFFER_SIZE +
CAPTURE_BUFFER_SIZE;
}
log->vma = vma;
+ /*
+ * Create a WC (Uncached for read) vmalloc mapping up front immediate access to
+ * data from memory during critical events such as error capture
+ */
+ vaddr = i915_gem_object_pin_map_unlocked(log->vma->obj, I915_MAP_WC);
+ if (IS_ERR(vaddr)) {
+ ret = PTR_ERR(vaddr);
+ i915_vma_unpin_and_release(&log->vma, 0);
+ goto err;
+ }
+ log->buf_addr = vaddr;
log->level = __get_default_log_level(log);
DRM_DEBUG_DRIVER("guc_log_level=%d (%s, verbose:%s, verbosity:%d)\n",
return 0;
err:
- DRM_ERROR("Failed to allocate GuC log buffer. %d\n", ret);
+ DRM_ERROR("Failed to allocate or map GuC log buffer. %d\n", ret);
return ret;
}
void intel_guc_log_destroy(struct intel_guc_log *log)
{
- i915_vma_unpin_and_release(&log->vma, 0);
+ log->buf_addr = NULL;
+ i915_vma_unpin_and_release(&log->vma, I915_VMA_RELEASE_MAP);
}
int intel_guc_log_set_level(struct intel_guc_log *log, u32 level)
bool intel_guc_log_relay_created(const struct intel_guc_log *log)
{
- return log->relay.buf_addr;
+ return log->buf_addr;
}
int intel_guc_log_relay_open(struct intel_guc_log *log)
if (ret)
goto out_unlock;
- ret = guc_log_map(log);
+ ret = guc_log_relay_map(log);
if (ret)
goto out_relay;
with_intel_runtime_pm(guc_to_gt(guc)->uncore->rpm, wakeref)
guc_action_flush_log(guc);
- /* GuC would have updated log buffer by now, so capture it */
- guc_log_capture_logs(log);
+ /* GuC would have updated log buffer by now, so copy it */
+ guc_log_copy_debuglogs_for_relay(log);
}
/*
mutex_lock(&log->relay.lock);
GEM_BUG_ON(!intel_guc_log_relay_created(log));
- guc_log_unmap(log);
+ guc_log_relay_unmap(log);
guc_log_relay_destroy(log);
mutex_unlock(&log->relay.lock);
}
struct intel_guc_log {
u32 level;
struct i915_vma *vma;
+ void *buf_addr;
struct {
- void *buf_addr;
+ bool buf_in_use;
bool started;
struct work_struct flush_work;
struct rchan *channel;
};
void intel_guc_log_init_early(struct intel_guc_log *log);
+bool intel_guc_check_log_buf_overflow(struct intel_guc_log *log, enum guc_log_buffer_type type,
+ unsigned int full_cnt);
+unsigned int intel_guc_get_log_buffer_size(enum guc_log_buffer_type type);
+size_t intel_guc_get_log_buffer_offset(enum guc_log_buffer_type type);
int intel_guc_log_create(struct intel_guc_log *log);
void intel_guc_log_destroy(struct intel_guc_log *log);
static void slpc_get_rp_values(struct intel_guc_slpc *slpc)
{
struct intel_rps *rps = &slpc_to_gt(slpc)->rps;
- u32 rp_state_cap;
+ struct intel_rps_freq_caps caps;
- rp_state_cap = intel_rps_read_state_cap(rps);
-
- slpc->rp0_freq = REG_FIELD_GET(RP0_CAP_MASK, rp_state_cap) *
- GT_FREQUENCY_MULTIPLIER;
- slpc->rp1_freq = REG_FIELD_GET(RP1_CAP_MASK, rp_state_cap) *
- GT_FREQUENCY_MULTIPLIER;
- slpc->min_freq = REG_FIELD_GET(RPN_CAP_MASK, rp_state_cap) *
- GT_FREQUENCY_MULTIPLIER;
+ gen6_rps_get_freq_caps(rps, &caps);
+ slpc->rp0_freq = intel_gpu_freq(rps, caps.rp0_freq);
+ slpc->rp1_freq = intel_gpu_freq(rps, caps.rp1_freq);
+ slpc->min_freq = intel_gpu_freq(rps, caps.min_freq);
if (!slpc->boost_freq)
slpc->boost_freq = slpc->rp0_freq;
#include "gt/intel_ring.h"
#include "intel_guc_ads.h"
+#include "intel_guc_capture.h"
#include "intel_guc_submission.h"
#include "i915_drv.h"
static inline bool context_guc_id_invalid(struct intel_context *ce)
{
- return ce->guc_id.id == GUC_INVALID_LRC_ID;
+ return ce->guc_id.id == GUC_INVALID_CONTEXT_ID;
}
static inline void set_context_guc_id_invalid(struct intel_context *ce)
{
- ce->guc_id.id = GUC_INVALID_LRC_ID;
+ ce->guc_id.id = GUC_INVALID_CONTEXT_ID;
}
static inline struct intel_guc *ce_to_guc(struct intel_context *ce)
{
struct guc_lrc_desc *base = guc->lrc_desc_pool_vaddr;
- GEM_BUG_ON(index >= GUC_MAX_LRC_DESCRIPTORS);
+ GEM_BUG_ON(index >= GUC_MAX_CONTEXT_ID);
return &base[index];
}
{
struct intel_context *ce = xa_load(&guc->context_lookup, id);
- GEM_BUG_ON(id >= GUC_MAX_LRC_DESCRIPTORS);
+ GEM_BUG_ON(id >= GUC_MAX_CONTEXT_ID);
return ce;
}
int ret;
size = PAGE_ALIGN(sizeof(struct guc_lrc_desc) *
- GUC_MAX_LRC_DESCRIPTORS);
+ GUC_MAX_CONTEXT_ID);
ret = intel_guc_allocate_and_map_vma(guc, size, &guc->lrc_desc_pool,
(void **)&guc->lrc_desc_pool_vaddr);
if (ret)
static inline bool guc_submission_initialized(struct intel_guc *guc)
{
- return !!guc->lrc_desc_pool_vaddr;
+ return guc->submission_initialized;
}
-static inline void reset_lrc_desc(struct intel_guc *guc, u32 id)
+static inline void _reset_lrc_desc(struct intel_guc *guc, u32 id)
{
- if (likely(guc_submission_initialized(guc))) {
- struct guc_lrc_desc *desc = __get_lrc_desc(guc, id);
- unsigned long flags;
-
- memset(desc, 0, sizeof(*desc));
+ struct guc_lrc_desc *desc = __get_lrc_desc(guc, id);
- /*
- * xarray API doesn't have xa_erase_irqsave wrapper, so calling
- * the lower level functions directly.
- */
- xa_lock_irqsave(&guc->context_lookup, flags);
- __xa_erase(&guc->context_lookup, id);
- xa_unlock_irqrestore(&guc->context_lookup, flags);
- }
+ memset(desc, 0, sizeof(*desc));
}
-static inline bool lrc_desc_registered(struct intel_guc *guc, u32 id)
+static inline bool ctx_id_mapped(struct intel_guc *guc, u32 id)
{
return __get_context(guc, id);
}
-static inline void set_lrc_desc_registered(struct intel_guc *guc, u32 id,
- struct intel_context *ce)
+static inline void set_ctx_id_mapping(struct intel_guc *guc, u32 id,
+ struct intel_context *ce)
{
unsigned long flags;
xa_unlock_irqrestore(&guc->context_lookup, flags);
}
+static inline void clr_ctx_id_mapping(struct intel_guc *guc, u32 id)
+{
+ unsigned long flags;
+
+ if (unlikely(!guc_submission_initialized(guc)))
+ return;
+
+ _reset_lrc_desc(guc, id);
+
+ /*
+ * xarray API doesn't have xa_erase_irqsave wrapper, so calling
+ * the lower level functions directly.
+ */
+ xa_lock_irqsave(&guc->context_lookup, flags);
+ __xa_erase(&guc->context_lookup, id);
+ xa_unlock_irqrestore(&guc->context_lookup, flags);
+}
+
static void decr_outstanding_submission_g2h(struct intel_guc *guc)
{
if (atomic_dec_and_test(&guc->outstanding_submission_g2h))
true, timeout);
}
-static int guc_lrc_desc_pin(struct intel_context *ce, bool loop);
+static int try_context_registration(struct intel_context *ce, bool loop);
static int __guc_add_request(struct intel_guc *guc, struct i915_request *rq)
{
GEM_BUG_ON(!atomic_read(&ce->guc_id.ref));
GEM_BUG_ON(context_guc_id_invalid(ce));
GEM_BUG_ON(context_wait_for_deregister_to_register(ce));
- GEM_BUG_ON(!lrc_desc_registered(ce_to_guc(ce), ce->guc_id.id));
+ GEM_BUG_ON(!ctx_id_mapped(ce_to_guc(ce), ce->guc_id.id));
/* Insert NOOP if this work queue item will wrap the tail pointer. */
if (wqi_size > wq_space_until_wrap(ce)) {
if (submit) {
struct intel_context *ce = request_to_scheduling_context(last);
- if (unlikely(!lrc_desc_registered(guc, ce->guc_id.id) &&
+ if (unlikely(!ctx_id_mapped(guc, ce->guc_id.id) &&
!intel_context_is_banned(ce))) {
- ret = guc_lrc_desc_pin(ce, false);
+ ret = try_context_registration(ce, false);
if (unlikely(ret == -EPIPE)) {
goto deadlk;
} else if (ret == -EBUSY) {
struct intel_gt *gt = guc_to_gt(guc);
int ret;
- if (guc->lrc_desc_pool)
+ if (guc->submission_initialized)
return 0;
ret = guc_lrc_desc_pool_create(guc);
guc->timestamp.ping_delay = (POLL_TIME_CLKS / gt->clock_frequency + 1) * HZ;
guc->timestamp.shift = gpm_timestamp_shift(gt);
+ guc->submission_initialized = true;
return 0;
}
void intel_guc_submission_fini(struct intel_guc *guc)
{
- if (!guc->lrc_desc_pool)
+ if (!guc->submission_initialized)
return;
guc_flush_destroyed_contexts(guc);
guc_lrc_desc_pool_destroy(guc);
i915_sched_engine_put(guc->sched_engine);
bitmap_free(guc->submission_state.guc_ids_bitmap);
+ guc->submission_initialized = false;
}
static inline void queue_request(struct i915_sched_engine *sched_engine,
return submission_disabled(guc) || guc->stalled_request ||
!i915_sched_engine_is_empty(sched_engine) ||
- !lrc_desc_registered(guc, ce->guc_id.id);
+ !ctx_id_mapped(guc, ce->guc_id.id);
}
static void guc_submit_request(struct i915_request *rq)
else
ida_simple_remove(&guc->submission_state.guc_ids,
ce->guc_id.id);
- reset_lrc_desc(guc, ce->guc_id.id);
+ clr_ctx_id_mapping(guc, ce->guc_id.id);
set_context_guc_id_invalid(ce);
}
if (!list_empty(&ce->guc_id.link))
0, loop);
}
+static void prepare_context_registration_info(struct intel_context *ce);
+
static int register_context(struct intel_context *ce, bool loop)
{
struct intel_guc *guc = ce_to_guc(ce);
GEM_BUG_ON(intel_context_is_child(ce));
trace_intel_context_register(ce);
+ prepare_context_registration_info(ce);
+
if (intel_context_is_parent(ce))
ret = __guc_action_register_multi_lrc(guc, ce, ce->guc_id.id,
offset, loop);
desc->preemption_timeout = engine->props.preempt_timeout_ms * 1000;
}
-static int guc_lrc_desc_pin(struct intel_context *ce, bool loop)
+static void prepare_context_registration_info(struct intel_context *ce)
{
struct intel_engine_cs *engine = ce->engine;
- struct intel_runtime_pm *runtime_pm = engine->uncore->rpm;
struct intel_guc *guc = &engine->gt->uc.guc;
- u32 desc_idx = ce->guc_id.id;
+ u32 ctx_id = ce->guc_id.id;
struct guc_lrc_desc *desc;
- bool context_registered;
- intel_wakeref_t wakeref;
struct intel_context *child;
- int ret = 0;
GEM_BUG_ON(!engine->mask);
- GEM_BUG_ON(!sched_state_is_init(ce));
/*
* Ensure LRC + CT vmas are is same region as write barrier is done
GEM_BUG_ON(i915_gem_object_is_lmem(guc->ct.vma->obj) !=
i915_gem_object_is_lmem(ce->ring->vma->obj));
- context_registered = lrc_desc_registered(guc, desc_idx);
-
- reset_lrc_desc(guc, desc_idx);
- set_lrc_desc_registered(guc, desc_idx, ce);
-
- desc = __get_lrc_desc(guc, desc_idx);
+ desc = __get_lrc_desc(guc, ctx_id);
desc->engine_class = engine_class_to_guc_class(engine->class);
desc->engine_submit_mask = engine->logical_mask;
desc->hw_context_desc = ce->lrc.lrca;
clear_children_join_go_memory(ce);
}
+}
+
+static int try_context_registration(struct intel_context *ce, bool loop)
+{
+ struct intel_engine_cs *engine = ce->engine;
+ struct intel_runtime_pm *runtime_pm = engine->uncore->rpm;
+ struct intel_guc *guc = &engine->gt->uc.guc;
+ intel_wakeref_t wakeref;
+ u32 ctx_id = ce->guc_id.id;
+ bool context_registered;
+ int ret = 0;
+
+ GEM_BUG_ON(!sched_state_is_init(ce));
+
+ context_registered = ctx_id_mapped(guc, ctx_id);
+
+ clr_ctx_id_mapping(guc, ctx_id);
+ set_ctx_id_mapping(guc, ctx_id, ce);
/*
* The context_lookup xarray is used to determine if the hardware
}
spin_unlock_irqrestore(&ce->guc_state.lock, flags);
if (unlikely(disabled)) {
- reset_lrc_desc(guc, desc_idx);
+ clr_ctx_id_mapping(guc, ctx_id);
return 0; /* Will get registered later */
}
with_intel_runtime_pm(runtime_pm, wakeref)
ret = register_context(ce, loop);
if (unlikely(ret == -EBUSY)) {
- reset_lrc_desc(guc, desc_idx);
+ clr_ctx_id_mapping(guc, ctx_id);
} else if (unlikely(ret == -ENODEV)) {
- reset_lrc_desc(guc, desc_idx);
+ clr_ctx_id_mapping(guc, ctx_id);
ret = 0; /* Will get registered later */
}
}
GUC_CONTEXT_DISABLE
};
- GEM_BUG_ON(guc_id == GUC_INVALID_LRC_ID);
+ GEM_BUG_ON(guc_id == GUC_INVALID_CONTEXT_ID);
GEM_BUG_ON(intel_context_is_child(ce));
trace_intel_context_sched_disable(ce);
return (ce->guc_state.sched_state & SCHED_STATE_NO_UNBLOCK) ||
context_guc_id_invalid(ce) ||
- !lrc_desc_registered(ce_to_guc(ce), ce->guc_id.id) ||
+ !ctx_id_mapped(ce_to_guc(ce), ce->guc_id.id) ||
!intel_context_is_pinned(ce);
}
bool disabled;
GEM_BUG_ON(!intel_gt_pm_is_awake(gt));
- GEM_BUG_ON(!lrc_desc_registered(guc, ce->guc_id.id));
+ GEM_BUG_ON(!ctx_id_mapped(guc, ce->guc_id.id));
GEM_BUG_ON(ce != __get_context(guc, ce->guc_id.id));
GEM_BUG_ON(context_enabled(ce));
*/
spin_lock_irqsave(&guc->submission_state.lock, flags);
destroy = submission_disabled(guc) || context_guc_id_invalid(ce) ||
- !lrc_desc_registered(guc, ce->guc_id.id);
+ !ctx_id_mapped(guc, ce->guc_id.id);
if (likely(!destroy)) {
if (!list_empty(&ce->guc_id.link))
list_del_init(&ce->guc_id.link);
static bool context_needs_register(struct intel_context *ce, bool new_guc_id)
{
return (new_guc_id || test_bit(CONTEXT_LRCA_DIRTY, &ce->flags) ||
- !lrc_desc_registered(ce_to_guc(ce), ce->guc_id.id)) &&
+ !ctx_id_mapped(ce_to_guc(ce), ce->guc_id.id)) &&
!submission_disabled(ce_to_guc(ce));
}
if (unlikely(ret < 0))
return ret;
if (context_needs_register(ce, !!ret)) {
- ret = guc_lrc_desc_pin(ce, true);
+ ret = try_context_registration(ce, true);
if (unlikely(ret)) { /* unwind */
if (ret == -EPIPE) {
disable_submission(guc);
sanitize_hwsp(engine);
/* And scrub the dirty cachelines for the HWSP */
- clflush_cache_range(engine->status_page.addr, PAGE_SIZE);
+ drm_clflush_virt_range(engine->status_page.addr, PAGE_SIZE);
intel_engine_reset_pinned_contexts(engine);
}
setup_hwsp(engine);
start_engine(engine);
- if (engine->class == RENDER_CLASS)
+ if (engine->flags & I915_ENGINE_FIRST_RENDER_COMPUTE)
xehp_enable_ccs_engines(engine);
return 0;
static inline void guc_kernel_context_pin(struct intel_guc *guc,
struct intel_context *ce)
{
+ /*
+ * Note: we purposefully do not check the returns below because
+ * the registration can only fail if a reset is just starting.
+ * This is called at the end of reset so presumably another reset
+ * isn't happening and even it did this code would be run again.
+ */
+
if (context_guc_id_invalid(ce))
pin_guc_id(guc, ce);
- guc_lrc_desc_pin(ce, true);
+
+ try_context_registration(ce, true);
}
static inline void guc_init_lrc_mapping(struct intel_guc *guc)
* Also, after a reset the of the GuC we want to make sure that the
* information shared with GuC is properly reset. The kernel LRCs are
* not attached to the gem_context, so they need to be added separately.
- *
- * Note: we purposefully do not check the return of guc_lrc_desc_pin,
- * because that function can only fail if a reset is just starting. This
- * is at the end of reset so presumably another reset isn't happening
- * and even it did this code would be run again.
*/
-
for_each_engine(engine, gt, id) {
struct intel_context *ce;
spin_lock_init(&guc->timestamp.lock);
INIT_DELAYED_WORK(&guc->timestamp.work, guc_timestamp_ping);
- guc->submission_state.num_guc_ids = GUC_MAX_LRC_DESCRIPTORS;
+ guc->submission_state.num_guc_ids = GUC_MAX_CONTEXT_ID;
guc->submission_supported = __guc_submission_supported(guc);
guc->submission_selected = __guc_submission_selected(guc);
}
static inline struct intel_context *
-g2h_context_lookup(struct intel_guc *guc, u32 desc_idx)
+g2h_context_lookup(struct intel_guc *guc, u32 ctx_id)
{
struct intel_context *ce;
- if (unlikely(desc_idx >= GUC_MAX_LRC_DESCRIPTORS)) {
+ if (unlikely(ctx_id >= GUC_MAX_CONTEXT_ID)) {
drm_err(&guc_to_gt(guc)->i915->drm,
- "Invalid desc_idx %u", desc_idx);
+ "Invalid ctx_id %u\n", ctx_id);
return NULL;
}
- ce = __get_context(guc, desc_idx);
+ ce = __get_context(guc, ctx_id);
if (unlikely(!ce)) {
drm_err(&guc_to_gt(guc)->i915->drm,
- "Context is NULL, desc_idx %u", desc_idx);
+ "Context is NULL, ctx_id %u\n", ctx_id);
return NULL;
}
if (unlikely(intel_context_is_child(ce))) {
drm_err(&guc_to_gt(guc)->i915->drm,
- "Context is child, desc_idx %u", desc_idx);
+ "Context is child, ctx_id %u\n", ctx_id);
return NULL;
}
u32 len)
{
struct intel_context *ce;
- u32 desc_idx = msg[0];
+ u32 ctx_id;
if (unlikely(len < 1)) {
- drm_err(&guc_to_gt(guc)->i915->drm, "Invalid length %u", len);
+ drm_err(&guc_to_gt(guc)->i915->drm, "Invalid length %u\n", len);
return -EPROTO;
}
+ ctx_id = msg[0];
- ce = g2h_context_lookup(guc, desc_idx);
+ ce = g2h_context_lookup(guc, ctx_id);
if (unlikely(!ce))
return -EPROTO;
{
struct intel_context *ce;
unsigned long flags;
- u32 desc_idx = msg[0];
+ u32 ctx_id;
if (unlikely(len < 2)) {
- drm_err(&guc_to_gt(guc)->i915->drm, "Invalid length %u", len);
+ drm_err(&guc_to_gt(guc)->i915->drm, "Invalid length %u\n", len);
return -EPROTO;
}
+ ctx_id = msg[0];
- ce = g2h_context_lookup(guc, desc_idx);
+ ce = g2h_context_lookup(guc, ctx_id);
if (unlikely(!ce))
return -EPROTO;
(!context_pending_enable(ce) &&
!context_pending_disable(ce)))) {
drm_err(&guc_to_gt(guc)->i915->drm,
- "Bad context sched_state 0x%x, desc_idx %u",
- ce->guc_state.sched_state, desc_idx);
+ "Bad context sched_state 0x%x, ctx_id %u\n",
+ ce->guc_state.sched_state, ctx_id);
return -EPROTO;
}
intel_engine_set_hung_context(engine, ce);
with_intel_runtime_pm(&i915->runtime_pm, wakeref)
- i915_capture_error_state(gt, engine->mask);
+ i915_capture_error_state(gt, engine->mask, CORE_DUMP_FLAG_IS_GUC_CAPTURE);
atomic_inc(&i915->gpu_error.reset_engine_count[engine->uabi_class]);
}
{
struct intel_context *ce;
unsigned long flags;
- int desc_idx;
+ int ctx_id;
if (unlikely(len != 1)) {
drm_err(&guc_to_gt(guc)->i915->drm, "Invalid length %u", len);
return -EPROTO;
}
- desc_idx = msg[0];
+ ctx_id = msg[0];
/*
* The context lookup uses the xarray but lookups only require an RCU lock
* asynchronously until the reset is done.
*/
xa_lock_irqsave(&guc->context_lookup, flags);
- ce = g2h_context_lookup(guc, desc_idx);
+ ce = g2h_context_lookup(guc, ctx_id);
if (ce)
intel_context_get(ce);
xa_unlock_irqrestore(&guc->context_lookup, flags);
int intel_guc_error_capture_process_msg(struct intel_guc *guc,
const u32 *msg, u32 len)
{
- int status;
+ u32 status;
if (unlikely(len != 1)) {
drm_dbg(&guc_to_gt(guc)->i915->drm, "Invalid length %u", len);
return -EPROTO;
}
- status = msg[0];
- drm_info(&guc_to_gt(guc)->i915->drm, "Got error capture: status = %d", status);
+ status = msg[0] & INTEL_GUC_STATE_CAPTURE_EVENT_STATUS_MASK;
+ if (status == INTEL_GUC_STATE_CAPTURE_EVENT_STATUS_NOSPACE)
+ drm_warn(&guc_to_gt(guc)->i915->drm, "G2H-Error capture no space");
- /* FIXME: Do something with the capture */
+ intel_guc_capture_process(guc);
return 0;
}
-static struct intel_engine_cs *
-guc_lookup_engine(struct intel_guc *guc, u8 guc_class, u8 instance)
+struct intel_engine_cs *
+intel_guc_lookup_engine(struct intel_guc *guc, u8 guc_class, u8 instance)
{
struct intel_gt *gt = guc_to_gt(guc);
u8 engine_class = guc_class_to_engine_class(guc_class);
instance = msg[1];
reason = msg[2];
- engine = guc_lookup_engine(guc, guc_class, instance);
+ engine = intel_guc_lookup_engine(guc, guc_class, instance);
if (unlikely(!engine)) {
drm_err(>->i915->drm,
"Invalid engine %d:%d", guc_class, instance);
struct i915_request *spin_rq = NULL, *rq, *last = NULL;
int number_guc_id_stolen = guc->number_guc_id_stolen;
- ce = kzalloc(sizeof(*ce) * GUC_MAX_LRC_DESCRIPTORS, GFP_KERNEL);
+ ce = kcalloc(GUC_MAX_CONTEXT_ID, sizeof(*ce), GFP_KERNEL);
if (!ce) {
pr_err("Context array allocation failed\n");
return -ENOMEM;
gpu = NULL;
with_intel_runtime_pm(&i915->runtime_pm, wakeref)
- gpu = i915_gpu_coredump(to_gt(i915), ALL_ENGINES);
+ gpu = i915_gpu_coredump(to_gt(i915), ALL_ENGINES, CORE_DUMP_FLAG_NONE);
+
if (IS_ERR(gpu))
return PTR_ERR(gpu);
static int i915_wedged_set(void *data, u64 val)
{
struct drm_i915_private *i915 = data;
+ intel_gt_debugfs_reset_store(to_gt(i915), val);
- return intel_gt_debugfs_reset_store(to_gt(i915), val);
+ return 0;
}
DEFINE_SIMPLE_ATTRIBUTE(i915_wedged_fops,
static int i915_forcewake_open(struct inode *inode, struct file *file)
{
struct drm_i915_private *i915 = inode->i_private;
+ intel_gt_pm_debugfs_forcewake_user_open(to_gt(i915));
- return intel_gt_pm_debugfs_forcewake_user_open(to_gt(i915));
+ return 0;
}
static int i915_forcewake_release(struct inode *inode, struct file *file)
{
struct drm_i915_private *i915 = inode->i_private;
+ intel_gt_pm_debugfs_forcewake_user_release(to_gt(i915));
- return intel_gt_pm_debugfs_forcewake_user_release(to_gt(i915));
+ return 0;
}
static const struct file_operations i915_forcewake_fops = {
#include "i915_file_private.h"
#include "i915_debugfs.h"
#include "i915_driver.h"
+#include "i915_drm_client.h"
#include "i915_drv.h"
#include "i915_getparam.h"
#include "i915_ioc32.h"
intel_device_info_subplatform_init(dev_priv);
intel_step_init(dev_priv);
- intel_gt_init_early(to_gt(dev_priv), dev_priv);
intel_uncore_mmio_debug_init_early(&dev_priv->mmio_debug);
- intel_uncore_init_early(&dev_priv->uncore, to_gt(dev_priv));
spin_lock_init(&dev_priv->irq_lock);
spin_lock_init(&dev_priv->gpu_error.lock);
intel_wopcm_init_early(&dev_priv->wopcm);
- __intel_gt_init_early(to_gt(dev_priv), dev_priv);
+ intel_root_gt_init_early(dev_priv);
+
+ i915_drm_clients_init(&dev_priv->clients, dev_priv);
i915_gem_init_early(dev_priv);
err_gem:
i915_gem_cleanup_early(dev_priv);
- intel_gt_driver_late_release(to_gt(dev_priv));
+ intel_gt_driver_late_release_all(dev_priv);
+ i915_drm_clients_fini(&dev_priv->clients);
intel_region_ttm_device_fini(dev_priv);
err_ttm:
vlv_suspend_cleanup(dev_priv);
intel_irq_fini(dev_priv);
intel_power_domains_cleanup(dev_priv);
i915_gem_cleanup_early(dev_priv);
- intel_gt_driver_late_release(to_gt(dev_priv));
+ intel_gt_driver_late_release_all(dev_priv);
+ i915_drm_clients_fini(&dev_priv->clients);
intel_region_ttm_device_fini(dev_priv);
vlv_suspend_cleanup(dev_priv);
i915_workqueues_cleanup(dev_priv);
if (ret < 0)
return ret;
- ret = intel_uncore_setup_mmio(&dev_priv->uncore);
- if (ret < 0)
- goto err_bridge;
-
ret = intel_uncore_init_mmio(&dev_priv->uncore);
if (ret)
- goto err_mmio;
+ return ret;
/* Try to make sure MCHBAR is enabled before poking at it */
intel_setup_mchbar(dev_priv);
err_uncore:
intel_teardown_mchbar(dev_priv);
intel_uncore_fini_mmio(&dev_priv->uncore);
-err_mmio:
- intel_uncore_cleanup_mmio(&dev_priv->uncore);
-err_bridge:
pci_dev_put(dev_priv->bridge_dev);
return ret;
{
intel_teardown_mchbar(dev_priv);
intel_uncore_fini_mmio(&dev_priv->uncore);
- intel_uncore_cleanup_mmio(&dev_priv->uncore);
pci_dev_put(dev_priv->bridge_dev);
}
if (ret)
goto err_ggtt;
- ret = intel_gt_probe_lmem(to_gt(dev_priv));
+ ret = intel_gt_tiles_init(dev_priv);
if (ret)
goto err_mem_regions;
intel_vgpu_detect(i915);
- ret = i915_driver_mmio_probe(i915);
+ ret = intel_gt_probe_all(i915);
if (ret < 0)
goto out_runtime_pm_put;
+ ret = i915_driver_mmio_probe(i915);
+ if (ret < 0)
+ goto out_tiles_cleanup;
+
ret = i915_driver_hw_probe(i915);
if (ret < 0)
goto out_cleanup_mmio;
i915_ggtt_driver_late_release(i915);
out_cleanup_mmio:
i915_driver_mmio_release(i915);
+out_tiles_cleanup:
+ intel_gt_release_all(i915);
out_runtime_pm_put:
enable_rpm_wakeref_asserts(&i915->runtime_pm);
i915_driver_late_release(i915);
struct drm_i915_file_private *file_priv = file->driver_priv;
i915_gem_context_close(file);
+ i915_drm_client_put(file_priv->client);
kfree_rcu(file_priv, rcu);
.read = drm_read,
.compat_ioctl = i915_ioc32_compat_ioctl,
.llseek = noop_llseek,
+#ifdef CONFIG_PROC_FS
+ .show_fdinfo = i915_drm_client_fdinfo,
+#endif
};
static int
--- /dev/null
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2020 Intel Corporation
+ */
+
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+
+#include <uapi/drm/i915_drm.h>
+
+#include <drm/drm_print.h>
+
+#include "gem/i915_gem_context.h"
+#include "i915_drm_client.h"
+#include "i915_file_private.h"
+#include "i915_gem.h"
+#include "i915_utils.h"
+
+void i915_drm_clients_init(struct i915_drm_clients *clients,
+ struct drm_i915_private *i915)
+{
+ clients->i915 = i915;
+ clients->next_id = 0;
+
+ xa_init_flags(&clients->xarray, XA_FLAGS_ALLOC | XA_FLAGS_LOCK_IRQ);
+}
+
+struct i915_drm_client *i915_drm_client_add(struct i915_drm_clients *clients)
+{
+ struct i915_drm_client *client;
+ struct xarray *xa = &clients->xarray;
+ int ret;
+
+ client = kzalloc(sizeof(*client), GFP_KERNEL);
+ if (!client)
+ return ERR_PTR(-ENOMEM);
+
+ xa_lock_irq(xa);
+ ret = __xa_alloc_cyclic(xa, &client->id, client, xa_limit_32b,
+ &clients->next_id, GFP_KERNEL);
+ xa_unlock_irq(xa);
+ if (ret < 0)
+ goto err;
+
+ kref_init(&client->kref);
+ spin_lock_init(&client->ctx_lock);
+ INIT_LIST_HEAD(&client->ctx_list);
+ client->clients = clients;
+
+ return client;
+
+err:
+ kfree(client);
+
+ return ERR_PTR(ret);
+}
+
+void __i915_drm_client_free(struct kref *kref)
+{
+ struct i915_drm_client *client =
+ container_of(kref, typeof(*client), kref);
+ struct xarray *xa = &client->clients->xarray;
+ unsigned long flags;
+
+ xa_lock_irqsave(xa, flags);
+ __xa_erase(xa, client->id);
+ xa_unlock_irqrestore(xa, flags);
+ kfree(client);
+}
+
+void i915_drm_clients_fini(struct i915_drm_clients *clients)
+{
+ GEM_BUG_ON(!xa_empty(&clients->xarray));
+ xa_destroy(&clients->xarray);
+}
+
+#ifdef CONFIG_PROC_FS
+static const char * const uabi_class_names[] = {
+ [I915_ENGINE_CLASS_RENDER] = "render",
+ [I915_ENGINE_CLASS_COPY] = "copy",
+ [I915_ENGINE_CLASS_VIDEO] = "video",
+ [I915_ENGINE_CLASS_VIDEO_ENHANCE] = "video-enhance",
+};
+
+static u64 busy_add(struct i915_gem_context *ctx, unsigned int class)
+{
+ struct i915_gem_engines_iter it;
+ struct intel_context *ce;
+ u64 total = 0;
+
+ for_each_gem_engine(ce, rcu_dereference(ctx->engines), it) {
+ if (ce->engine->uabi_class != class)
+ continue;
+
+ total += intel_context_get_total_runtime_ns(ce);
+ }
+
+ return total;
+}
+
+static void
+show_client_class(struct seq_file *m,
+ struct i915_drm_client *client,
+ unsigned int class)
+{
+ const struct list_head *list = &client->ctx_list;
+ u64 total = atomic64_read(&client->past_runtime[class]);
+ const unsigned int capacity =
+ client->clients->i915->engine_uabi_class_count[class];
+ struct i915_gem_context *ctx;
+
+ rcu_read_lock();
+ list_for_each_entry_rcu(ctx, list, client_link)
+ 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 > 1)
+ seq_printf(m, "drm-engine-capacity-%s:\t%u\n",
+ uabi_class_names[class],
+ capacity);
+}
+
+void i915_drm_client_fdinfo(struct seq_file *m, struct file *f)
+{
+ struct drm_file *file = f->private_data;
+ struct drm_i915_file_private *file_priv = file->driver_priv;
+ struct drm_i915_private *i915 = file_priv->dev_priv;
+ struct i915_drm_client *client = file_priv->client;
+ struct pci_dev *pdev = to_pci_dev(i915->drm.dev);
+ unsigned int i;
+
+ /*
+ * ******************************************************************
+ * For text output format description please see drm-usage-stats.rst!
+ * ******************************************************************
+ */
+
+ seq_printf(m, "drm-driver:\t%s\n", i915->drm.driver->name);
+ seq_printf(m, "drm-pdev:\t%04x:%02x:%02x.%d\n",
+ pci_domain_nr(pdev->bus), pdev->bus->number,
+ PCI_SLOT(pdev->devfn), PCI_FUNC(pdev->devfn));
+ seq_printf(m, "drm-client-id:\t%u\n", client->id);
+
+ if (GRAPHICS_VER(i915) < 8)
+ return;
+
+ for (i = 0; i < ARRAY_SIZE(uabi_class_names); i++)
+ show_client_class(m, client, i);
+}
+#endif
--- /dev/null
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2020 Intel Corporation
+ */
+
+#ifndef __I915_DRM_CLIENT_H__
+#define __I915_DRM_CLIENT_H__
+
+#include <linux/kref.h>
+#include <linux/list.h>
+#include <linux/spinlock.h>
+#include <linux/xarray.h>
+
+#include "gt/intel_engine_types.h"
+
+#define I915_LAST_UABI_ENGINE_CLASS I915_ENGINE_CLASS_VIDEO_ENHANCE
+
+struct drm_i915_private;
+
+struct i915_drm_clients {
+ struct drm_i915_private *i915;
+
+ struct xarray xarray;
+ u32 next_id;
+};
+
+struct i915_drm_client {
+ struct kref kref;
+
+ unsigned int id;
+
+ spinlock_t ctx_lock; /* For add/remove from ctx_list. */
+ struct list_head ctx_list; /* List of contexts belonging to client. */
+
+ struct i915_drm_clients *clients;
+
+ /**
+ * @past_runtime: Accumulation of pphwsp runtimes from closed contexts.
+ */
+ atomic64_t past_runtime[I915_LAST_UABI_ENGINE_CLASS + 1];
+};
+
+void i915_drm_clients_init(struct i915_drm_clients *clients,
+ struct drm_i915_private *i915);
+
+static inline struct i915_drm_client *
+i915_drm_client_get(struct i915_drm_client *client)
+{
+ kref_get(&client->kref);
+ return client;
+}
+
+void __i915_drm_client_free(struct kref *kref);
+
+static inline void i915_drm_client_put(struct i915_drm_client *client)
+{
+ kref_put(&client->kref, __i915_drm_client_free);
+}
+
+struct i915_drm_client *i915_drm_client_add(struct i915_drm_clients *clients);
+
+#ifdef CONFIG_PROC_FS
+void i915_drm_client_fdinfo(struct seq_file *m, struct file *f);
+#endif
+
+void i915_drm_clients_fini(struct i915_drm_clients *clients);
+
+#endif /* !__I915_DRM_CLIENT_H__ */
#include "gt/intel_workarounds.h"
#include "gt/uc/intel_uc.h"
+#include "i915_drm_client.h"
#include "i915_gem.h"
#include "i915_gpu_error.h"
#include "i915_params.h"
struct pci_dev *bridge_dev;
struct rb_root uabi_engines;
+ unsigned int engine_uabi_class_count[I915_LAST_UABI_ENGINE_CLASS + 1];
struct resource mch_res;
/* Abstract the submission mechanism (legacy ringbuffer or execlists) away */
struct intel_gt gt0;
+ /*
+ * i915->gt[0] == &i915->gt0
+ */
+#define I915_MAX_GT 4
+ struct intel_gt *gt[I915_MAX_GT];
+
+ struct kobject *sysfs_gt;
+
struct {
struct i915_gem_contexts {
spinlock_t lock; /* locks list */
struct i915_pmu pmu;
+ struct i915_drm_clients clients;
+
struct i915_hdcp_comp_master *hdcp_master;
bool hdcp_comp_added;
((gt)->info.engine_mask & \
GENMASK(first__ + count__ - 1, first__)) >> first__; \
})
+#define RCS_MASK(gt) \
+ ENGINE_INSTANCES_MASK(gt, RCS0, I915_MAX_RCS)
#define VDBOX_MASK(gt) \
ENGINE_INSTANCES_MASK(gt, VCS0, I915_MAX_VCS)
#define VEBOX_MASK(gt) \
#define HAS_GUC_DEPRIVILEGE(dev_priv) \
(INTEL_INFO(dev_priv)->has_guc_deprivilege)
+#define HAS_PERCTX_PREEMPT_CTRL(i915) \
+ ((GRAPHICS_VER(i915) >= 9) && GRAPHICS_VER_FULL(i915) < IP_VER(12, 55))
+
static inline bool run_as_guest(void)
{
return !hypervisor_is_type(X86_HYPER_NATIVE);
struct drm_i915_private;
struct drm_file;
+struct i915_drm_client;
struct drm_i915_file_private {
struct drm_i915_private *dev_priv;
/** ban_score: Accumulated score of all ctx bans and fast hangs. */
atomic_t ban_score;
unsigned long hang_timestamp;
+
+ struct i915_drm_client *client;
};
#endif /* __I915_FILE_PRIVATE_H__ */
unsigned long flags)
{
struct intel_runtime_pm *rpm = &to_i915(obj->base.dev)->runtime_pm;
+ bool vm_trylock = !!(flags & I915_GEM_OBJECT_UNBIND_VM_TRYLOCK);
LIST_HEAD(still_in_list);
intel_wakeref_t wakeref;
struct i915_vma *vma;
while (!ret && (vma = list_first_entry_or_null(&obj->vma.list,
struct i915_vma,
obj_link))) {
- struct i915_address_space *vm = vma->vm;
-
list_move_tail(&vma->obj_link, &still_in_list);
if (!i915_vma_is_bound(vma, I915_VMA_BIND_MASK))
continue;
break;
}
+ /*
+ * Requiring the vm destructor to take the object lock
+ * before destroying a vma would help us eliminate the
+ * i915_vm_tryget() here, AND thus also the barrier stuff
+ * at the end. That's an easy fix, but sleeping locks in
+ * a kthread should generally be avoided.
+ */
ret = -EAGAIN;
- if (!i915_vm_tryopen(vm))
+ if (!i915_vm_tryget(vma->vm))
break;
- /* Prevent vma being freed by i915_vma_parked as we unbind */
- vma = __i915_vma_get(vma);
spin_unlock(&obj->vma.lock);
- if (vma) {
- bool vm_trylock = !!(flags & I915_GEM_OBJECT_UNBIND_VM_TRYLOCK);
- ret = -EBUSY;
- if (flags & I915_GEM_OBJECT_UNBIND_ASYNC) {
- assert_object_held(vma->obj);
- ret = i915_vma_unbind_async(vma, vm_trylock);
- }
+ /*
+ * Since i915_vma_parked() takes the object lock
+ * before vma destruction, it won't race us here,
+ * and destroy the vma from under us.
+ */
- if (ret == -EBUSY && (flags & I915_GEM_OBJECT_UNBIND_ACTIVE ||
- !i915_vma_is_active(vma))) {
- if (vm_trylock) {
- if (mutex_trylock(&vma->vm->mutex)) {
- ret = __i915_vma_unbind(vma);
- mutex_unlock(&vma->vm->mutex);
- } else {
- ret = -EBUSY;
- }
- } else {
- ret = i915_vma_unbind(vma);
+ ret = -EBUSY;
+ if (flags & I915_GEM_OBJECT_UNBIND_ASYNC) {
+ assert_object_held(vma->obj);
+ ret = i915_vma_unbind_async(vma, vm_trylock);
+ }
+
+ if (ret == -EBUSY && (flags & I915_GEM_OBJECT_UNBIND_ACTIVE ||
+ !i915_vma_is_active(vma))) {
+ if (vm_trylock) {
+ if (mutex_trylock(&vma->vm->mutex)) {
+ ret = __i915_vma_unbind(vma);
+ mutex_unlock(&vma->vm->mutex);
}
+ } else {
+ ret = i915_vma_unbind(vma);
}
-
- __i915_vma_put(vma);
}
- i915_vm_close(vm);
+ i915_vm_put(vma->vm);
spin_lock(&obj->vma.lock);
}
list_splice_init(&still_in_list, &obj->vma.list);
if (i915_vma_is_pinned(vma) || i915_vma_is_active(vma))
return ERR_PTR(-ENOSPC);
+ /*
+ * If this misplaced vma is too big (i.e, at-least
+ * half the size of aperture) or hasn't been pinned
+ * mappable before, we ignore the misplacement when
+ * PIN_NONBLOCK is set in order to avoid the ping-pong
+ * issue described above. In other words, we try to
+ * avoid the costly operation of unbinding this vma
+ * from the GGTT and rebinding it back because there
+ * may not be enough space for this vma in the aperture.
+ */
if (flags & PIN_MAPPABLE &&
- vma->fence_size > ggtt->mappable_end / 2)
+ (vma->fence_size > ggtt->mappable_end / 2 ||
+ !i915_vma_is_map_and_fenceable(vma)))
return ERR_PTR(-ENOSPC);
}
int i915_gem_open(struct drm_i915_private *i915, struct drm_file *file)
{
struct drm_i915_file_private *file_priv;
- int ret;
+ struct i915_drm_client *client;
+ int ret = -ENOMEM;
DRM_DEBUG("\n");
file_priv = kzalloc(sizeof(*file_priv), GFP_KERNEL);
if (!file_priv)
- return -ENOMEM;
+ goto err_alloc;
+
+ client = i915_drm_client_add(&i915->clients);
+ if (IS_ERR(client)) {
+ ret = PTR_ERR(client);
+ goto err_client;
+ }
file->driver_priv = file_priv;
file_priv->dev_priv = i915;
file_priv->file = file;
+ file_priv->client = client;
file_priv->bsd_engine = -1;
file_priv->hang_timestamp = jiffies;
ret = i915_gem_context_open(i915, file);
if (ret)
- kfree(file_priv);
+ goto err_context;
+
+ return 0;
+err_context:
+ i915_drm_client_put(client);
+err_client:
+ kfree(file_priv);
+err_alloc:
return ret;
}
#include "gt/intel_gt.h"
#include "gt/intel_gt_pm.h"
#include "gt/intel_gt_regs.h"
+#include "gt/uc/intel_guc_capture.h"
#include "i915_driver.h"
#include "i915_drv.h"
const char *header,
const struct i915_gem_context_coredump *ctx)
{
- const u32 period = to_gt(m->i915)->clock_period_ns;
-
err_printf(m, "%s%s[%d] prio %d, guilty %d active %d, runtime total %lluns, avg %lluns\n",
header, ctx->comm, ctx->pid, ctx->sched_attr.priority,
ctx->guilty, ctx->active,
- ctx->total_runtime * period,
- mul_u32_u32(ctx->avg_runtime, period));
+ ctx->total_runtime, ctx->avg_runtime);
}
static struct i915_vma_coredump *
return NULL;
}
-static struct i915_vma_coredump *
-find_batch(const struct intel_engine_coredump *ee)
+struct i915_vma_coredump *
+intel_gpu_error_find_batch(const struct intel_engine_coredump *ee)
{
return __find_vma(ee->vma, "batch");
}
error_print_instdone(m, ee);
- batch = find_batch(ee);
+ batch = intel_gpu_error_find_batch(ee);
if (batch) {
u64 start = batch->gtt_offset;
u64 end = start + batch->gtt_size;
ee->vm_info.pp_dir_base);
}
}
- err_printf(m, " hung: %u\n", ee->hung);
- err_printf(m, " engine reset count: %u\n", ee->reset_count);
for (n = 0; n < ee->num_ports; n++) {
err_printf(m, " ELSP[%d]:", n);
error_print_request(m, " ", &ee->execlist[n]);
}
-
- error_print_context(m, " Active context: ", &ee->context);
}
void i915_error_printf(struct drm_i915_error_state_buf *e, const char *f, ...)
va_end(args);
}
-static void print_error_vma(struct drm_i915_error_state_buf *m,
- const struct intel_engine_cs *engine,
- const struct i915_vma_coredump *vma)
+void intel_gpu_error_print_vma(struct drm_i915_error_state_buf *m,
+ const struct intel_engine_cs *engine,
+ const struct i915_vma_coredump *vma)
{
char out[ASCII85_BUFSZ];
struct page *page;
intel_uc_fw_dump(&error_uc->guc_fw, &p);
intel_uc_fw_dump(&error_uc->huc_fw, &p);
- print_error_vma(m, NULL, error_uc->guc_log);
+ intel_gpu_error_print_vma(m, NULL, error_uc->guc_log);
}
static void err_free_sgl(struct scatterlist *sgl)
struct drm_printer p = i915_error_printer(m);
intel_gt_info_print(>->info, &p);
- intel_sseu_print_topology(>->info.sseu, &p);
+ intel_sseu_print_topology(gt->_gt->i915, >->info.sseu, &p);
}
-static void err_print_gt(struct drm_i915_error_state_buf *m,
- struct intel_gt_coredump *gt)
+static void err_print_gt_display(struct drm_i915_error_state_buf *m,
+ struct intel_gt_coredump *gt)
+{
+ err_printf(m, "IER: 0x%08x\n", gt->ier);
+ err_printf(m, "DERRMR: 0x%08x\n", gt->derrmr);
+}
+
+static void err_print_gt_global_nonguc(struct drm_i915_error_state_buf *m,
+ struct intel_gt_coredump *gt)
{
- const struct intel_engine_coredump *ee;
int i;
err_printf(m, "GT awake: %s\n", yesno(gt->awake));
err_printf(m, "EIR: 0x%08x\n", gt->eir);
- err_printf(m, "IER: 0x%08x\n", gt->ier);
+ err_printf(m, "PGTBL_ER: 0x%08x\n", gt->pgtbl_er);
+
for (i = 0; i < gt->ngtier; i++)
err_printf(m, "GTIER[%d]: 0x%08x\n", i, gt->gtier[i]);
- err_printf(m, "PGTBL_ER: 0x%08x\n", gt->pgtbl_er);
- err_printf(m, "FORCEWAKE: 0x%08x\n", gt->forcewake);
- err_printf(m, "DERRMR: 0x%08x\n", gt->derrmr);
+}
- for (i = 0; i < gt->nfence; i++)
- err_printf(m, " fence[%d] = %08llx\n", i, gt->fence[i]);
+static void err_print_gt_global(struct drm_i915_error_state_buf *m,
+ struct intel_gt_coredump *gt)
+{
+ err_printf(m, "FORCEWAKE: 0x%08x\n", gt->forcewake);
if (IS_GRAPHICS_VER(m->i915, 6, 11)) {
err_printf(m, "ERROR: 0x%08x\n", gt->error);
if (GRAPHICS_VER(m->i915) >= 12) {
int i;
- for (i = 0; i < GEN12_SFC_DONE_MAX; i++) {
+ for (i = 0; i < I915_MAX_SFC; i++) {
/*
* SFC_DONE resides in the VD forcewake domain, so it
* only exists if the corresponding VCS engine is
err_printf(m, " GAM_DONE: 0x%08x\n", gt->gam_done);
}
+}
+
+static void err_print_gt_fences(struct drm_i915_error_state_buf *m,
+ struct intel_gt_coredump *gt)
+{
+ int i;
+
+ for (i = 0; i < gt->nfence; i++)
+ err_printf(m, " fence[%d] = %08llx\n", i, gt->fence[i]);
+}
+
+static void err_print_gt_engines(struct drm_i915_error_state_buf *m,
+ struct intel_gt_coredump *gt)
+{
+ const struct intel_engine_coredump *ee;
for (ee = gt->engine; ee; ee = ee->next) {
const struct i915_vma_coredump *vma;
- error_print_engine(m, ee);
+ if (ee->guc_capture_node)
+ intel_guc_capture_print_engine_node(m, ee);
+ else
+ error_print_engine(m, ee);
+
+ err_printf(m, " hung: %u\n", ee->hung);
+ err_printf(m, " engine reset count: %u\n", ee->reset_count);
+ error_print_context(m, " Active context: ", &ee->context);
+
for (vma = ee->vma; vma; vma = vma->next)
- print_error_vma(m, ee->engine, vma);
+ intel_gpu_error_print_vma(m, ee->engine, vma);
}
- if (gt->uc)
- err_print_uc(m, gt->uc);
-
- err_print_gt_info(m, gt);
}
static void __err_print_to_sgl(struct drm_i915_error_state_buf *m,
err_printf(m, "RPM wakelock: %s\n", yesno(error->wakelock));
err_printf(m, "PM suspended: %s\n", yesno(error->suspended));
- if (error->gt)
- err_print_gt(m, error->gt);
+ if (error->gt) {
+ bool print_guc_capture = false;
+
+ if (error->gt->uc && error->gt->uc->is_guc_capture)
+ print_guc_capture = true;
+
+ err_print_gt_display(m, error->gt);
+ err_print_gt_global_nonguc(m, error->gt);
+ err_print_gt_fences(m, error->gt);
+
+ /*
+ * GuC dumped global, eng-class and eng-instance registers together
+ * as part of engine state dump so we print in err_print_gt_engines
+ */
+ if (!print_guc_capture)
+ err_print_gt_global(m, error->gt);
+
+ err_print_gt_engines(m, error->gt);
+
+ if (error->gt->uc)
+ err_print_uc(m, error->gt->uc);
+
+ err_print_gt_info(m, error->gt);
+ }
if (error->overlay)
intel_overlay_print_error_state(m, error->overlay);
gt->engine = ee->next;
i915_vma_coredump_free(ee->vma);
+ intel_guc_capture_free_node(ee);
kfree(ee);
}
e->guilty = atomic_read(&ctx->guilty_count);
e->active = atomic_read(&ctx->active_count);
- e->total_runtime = rq->context->runtime.total;
- e->avg_runtime = ewma_runtime_read(&rq->context->runtime.avg);
+ e->total_runtime = intel_context_get_total_runtime_ns(rq->context);
+ e->avg_runtime = intel_context_get_avg_runtime_ns(rq->context);
simulated = i915_gem_context_no_error_capture(ctx);
}
struct intel_engine_coredump *
-intel_engine_coredump_alloc(struct intel_engine_cs *engine, gfp_t gfp)
+intel_engine_coredump_alloc(struct intel_engine_cs *engine, gfp_t gfp, u32 dump_flags)
{
struct intel_engine_coredump *ee;
ee->engine = engine;
- engine_record_registers(ee);
- engine_record_execlists(ee);
+ if (!(dump_flags & CORE_DUMP_FLAG_IS_GUC_CAPTURE)) {
+ engine_record_registers(ee);
+ engine_record_execlists(ee);
+ }
return ee;
}
static struct intel_engine_coredump *
capture_engine(struct intel_engine_cs *engine,
- struct i915_vma_compress *compress)
+ struct i915_vma_compress *compress,
+ u32 dump_flags)
{
struct intel_engine_capture_vma *capture = NULL;
struct intel_engine_coredump *ee;
struct i915_request *rq = NULL;
unsigned long flags;
- ee = intel_engine_coredump_alloc(engine, ALLOW_FAIL);
+ ee = intel_engine_coredump_alloc(engine, ALLOW_FAIL, dump_flags);
if (!ee)
return NULL;
i915_request_put(rq);
goto no_request_capture;
}
+ if (dump_flags & CORE_DUMP_FLAG_IS_GUC_CAPTURE)
+ intel_guc_capture_get_matching_node(engine->gt, ee, ce);
intel_engine_coredump_add_vma(ee, capture, compress);
i915_request_put(rq);
static void
gt_record_engines(struct intel_gt_coredump *gt,
intel_engine_mask_t engine_mask,
- struct i915_vma_compress *compress)
+ struct i915_vma_compress *compress,
+ u32 dump_flags)
{
struct intel_engine_cs *engine;
enum intel_engine_id id;
/* Refill our page pool before entering atomic section */
pool_refill(&compress->pool, ALLOW_FAIL);
- ee = capture_engine(engine, compress);
+ ee = capture_engine(engine, compress, dump_flags);
if (!ee)
continue;
gt->simulated |= ee->simulated;
if (ee->simulated) {
+ if (dump_flags & CORE_DUMP_FLAG_IS_GUC_CAPTURE)
+ intel_guc_capture_free_node(ee);
kfree(ee);
continue;
}
return error_uc;
}
-/* Capture all registers which don't fit into another category. */
-static void gt_record_regs(struct intel_gt_coredump *gt)
+/* Capture display registers. */
+static void gt_record_display_regs(struct intel_gt_coredump *gt)
+{
+ struct intel_uncore *uncore = gt->_gt->uncore;
+ struct drm_i915_private *i915 = uncore->i915;
+
+ if (GRAPHICS_VER(i915) >= 6)
+ gt->derrmr = intel_uncore_read(uncore, DERRMR);
+
+ if (GRAPHICS_VER(i915) >= 8)
+ gt->ier = intel_uncore_read(uncore, GEN8_DE_MISC_IER);
+ else if (IS_VALLEYVIEW(i915))
+ gt->ier = intel_uncore_read(uncore, VLV_IER);
+ else if (HAS_PCH_SPLIT(i915))
+ gt->ier = intel_uncore_read(uncore, DEIER);
+ else if (GRAPHICS_VER(i915) == 2)
+ gt->ier = intel_uncore_read16(uncore, GEN2_IER);
+ else
+ gt->ier = intel_uncore_read(uncore, GEN2_IER);
+}
+
+/* Capture all other registers that GuC doesn't capture. */
+static void gt_record_global_nonguc_regs(struct intel_gt_coredump *gt)
+{
+ struct intel_uncore *uncore = gt->_gt->uncore;
+ struct drm_i915_private *i915 = uncore->i915;
+ int i;
+
+ if (IS_VALLEYVIEW(i915)) {
+ gt->gtier[0] = intel_uncore_read(uncore, GTIER);
+ gt->ngtier = 1;
+ } else if (GRAPHICS_VER(i915) >= 11) {
+ gt->gtier[0] =
+ intel_uncore_read(uncore,
+ GEN11_RENDER_COPY_INTR_ENABLE);
+ gt->gtier[1] =
+ intel_uncore_read(uncore, GEN11_VCS_VECS_INTR_ENABLE);
+ gt->gtier[2] =
+ intel_uncore_read(uncore, GEN11_GUC_SG_INTR_ENABLE);
+ gt->gtier[3] =
+ intel_uncore_read(uncore,
+ GEN11_GPM_WGBOXPERF_INTR_ENABLE);
+ gt->gtier[4] =
+ intel_uncore_read(uncore,
+ GEN11_CRYPTO_RSVD_INTR_ENABLE);
+ gt->gtier[5] =
+ intel_uncore_read(uncore,
+ GEN11_GUNIT_CSME_INTR_ENABLE);
+ gt->ngtier = 6;
+ } else if (GRAPHICS_VER(i915) >= 8) {
+ for (i = 0; i < 4; i++)
+ gt->gtier[i] =
+ intel_uncore_read(uncore, GEN8_GT_IER(i));
+ gt->ngtier = 4;
+ } else if (HAS_PCH_SPLIT(i915)) {
+ gt->gtier[0] = intel_uncore_read(uncore, GTIER);
+ gt->ngtier = 1;
+ }
+
+ gt->eir = intel_uncore_read(uncore, EIR);
+ gt->pgtbl_er = intel_uncore_read(uncore, PGTBL_ER);
+}
+
+/*
+ * Capture all registers that relate to workload submission.
+ * NOTE: In GuC submission, when GuC resets an engine, it can dump these for us
+ */
+static void gt_record_global_regs(struct intel_gt_coredump *gt)
{
struct intel_uncore *uncore = gt->_gt->uncore;
struct drm_i915_private *i915 = uncore->i915;
*/
/* 1: Registers specific to a single generation */
- if (IS_VALLEYVIEW(i915)) {
- gt->gtier[0] = intel_uncore_read(uncore, GTIER);
- gt->ier = intel_uncore_read(uncore, VLV_IER);
+ if (IS_VALLEYVIEW(i915))
gt->forcewake = intel_uncore_read_fw(uncore, FORCEWAKE_VLV);
- }
if (GRAPHICS_VER(i915) == 7)
gt->err_int = intel_uncore_read(uncore, GEN7_ERR_INT);
gt->forcewake = intel_uncore_read_fw(uncore, FORCEWAKE_MT);
if (GRAPHICS_VER(i915) >= 6) {
- gt->derrmr = intel_uncore_read(uncore, DERRMR);
if (GRAPHICS_VER(i915) < 12) {
gt->error = intel_uncore_read(uncore, ERROR_GEN6);
gt->done_reg = intel_uncore_read(uncore, DONE_REG);
gt->aux_err = intel_uncore_read(uncore, GEN12_AUX_ERR_DBG);
if (GRAPHICS_VER(i915) >= 12) {
- for (i = 0; i < GEN12_SFC_DONE_MAX; i++) {
+ for (i = 0; i < I915_MAX_SFC; i++) {
/*
* SFC_DONE resides in the VD forcewake domain, so it
* only exists if the corresponding VCS engine is
gt->gam_done = intel_uncore_read(uncore, GEN12_GAM_DONE);
}
-
- /* 4: Everything else */
- if (GRAPHICS_VER(i915) >= 11) {
- gt->ier = intel_uncore_read(uncore, GEN8_DE_MISC_IER);
- gt->gtier[0] =
- intel_uncore_read(uncore,
- GEN11_RENDER_COPY_INTR_ENABLE);
- gt->gtier[1] =
- intel_uncore_read(uncore, GEN11_VCS_VECS_INTR_ENABLE);
- gt->gtier[2] =
- intel_uncore_read(uncore, GEN11_GUC_SG_INTR_ENABLE);
- gt->gtier[3] =
- intel_uncore_read(uncore,
- GEN11_GPM_WGBOXPERF_INTR_ENABLE);
- gt->gtier[4] =
- intel_uncore_read(uncore,
- GEN11_CRYPTO_RSVD_INTR_ENABLE);
- gt->gtier[5] =
- intel_uncore_read(uncore,
- GEN11_GUNIT_CSME_INTR_ENABLE);
- gt->ngtier = 6;
- } else if (GRAPHICS_VER(i915) >= 8) {
- gt->ier = intel_uncore_read(uncore, GEN8_DE_MISC_IER);
- for (i = 0; i < 4; i++)
- gt->gtier[i] =
- intel_uncore_read(uncore, GEN8_GT_IER(i));
- gt->ngtier = 4;
- } else if (HAS_PCH_SPLIT(i915)) {
- gt->ier = intel_uncore_read(uncore, DEIER);
- gt->gtier[0] = intel_uncore_read(uncore, GTIER);
- gt->ngtier = 1;
- } else if (GRAPHICS_VER(i915) == 2) {
- gt->ier = intel_uncore_read16(uncore, GEN2_IER);
- } else if (!IS_VALLEYVIEW(i915)) {
- gt->ier = intel_uncore_read(uncore, GEN2_IER);
- }
- gt->eir = intel_uncore_read(uncore, EIR);
- gt->pgtbl_er = intel_uncore_read(uncore, PGTBL_ER);
}
static void gt_record_info(struct intel_gt_coredump *gt)
#define DAY_AS_SECONDS(x) (24 * 60 * 60 * (x))
struct intel_gt_coredump *
-intel_gt_coredump_alloc(struct intel_gt *gt, gfp_t gfp)
+intel_gt_coredump_alloc(struct intel_gt *gt, gfp_t gfp, u32 dump_flags)
{
struct intel_gt_coredump *gc;
gc->_gt = gt;
gc->awake = intel_gt_pm_is_awake(gt);
- gt_record_regs(gc);
+ gt_record_display_regs(gc);
+ gt_record_global_nonguc_regs(gc);
+
+ /*
+ * GuC dumps global, eng-class and eng-instance registers
+ * (that can change as part of engine state during execution)
+ * before an engine is reset due to a hung context.
+ * GuC captures and reports all three groups of registers
+ * together as a single set before the engine is reset.
+ * Thus, if GuC triggered the context reset we retrieve
+ * the register values as part of gt_record_engines.
+ */
+ if (!(dump_flags & CORE_DUMP_FLAG_IS_GUC_CAPTURE))
+ gt_record_global_regs(gc);
+
gt_record_fences(gc);
return gc;
}
static struct i915_gpu_coredump *
-__i915_gpu_coredump(struct intel_gt *gt, intel_engine_mask_t engine_mask)
+__i915_gpu_coredump(struct intel_gt *gt, intel_engine_mask_t engine_mask, u32 dump_flags)
{
struct drm_i915_private *i915 = gt->i915;
struct i915_gpu_coredump *error;
if (!error)
return ERR_PTR(-ENOMEM);
- error->gt = intel_gt_coredump_alloc(gt, ALLOW_FAIL);
+ error->gt = intel_gt_coredump_alloc(gt, ALLOW_FAIL, dump_flags);
if (error->gt) {
struct i915_vma_compress *compress;
return ERR_PTR(-ENOMEM);
}
+ if (INTEL_INFO(i915)->has_gt_uc) {
+ error->gt->uc = gt_record_uc(error->gt, compress);
+ if (error->gt->uc) {
+ if (dump_flags & CORE_DUMP_FLAG_IS_GUC_CAPTURE)
+ error->gt->uc->is_guc_capture = true;
+ else
+ GEM_BUG_ON(error->gt->uc->is_guc_capture);
+ }
+ }
+
gt_record_info(error->gt);
- gt_record_engines(error->gt, engine_mask, compress);
+ gt_record_engines(error->gt, engine_mask, compress, dump_flags);
- if (INTEL_INFO(i915)->has_gt_uc)
- error->gt->uc = gt_record_uc(error->gt, compress);
i915_vma_capture_finish(error->gt, compress);
}
struct i915_gpu_coredump *
-i915_gpu_coredump(struct intel_gt *gt, intel_engine_mask_t engine_mask)
+i915_gpu_coredump(struct intel_gt *gt, intel_engine_mask_t engine_mask, u32 dump_flags)
{
static DEFINE_MUTEX(capture_mutex);
int ret = mutex_lock_interruptible(&capture_mutex);
if (ret)
return ERR_PTR(ret);
- dump = __i915_gpu_coredump(gt, engine_mask);
+ dump = __i915_gpu_coredump(gt, engine_mask, dump_flags);
mutex_unlock(&capture_mutex);
return dump;
* to pick up.
*/
void i915_capture_error_state(struct intel_gt *gt,
- intel_engine_mask_t engine_mask)
+ intel_engine_mask_t engine_mask, u32 dump_flags)
{
struct i915_gpu_coredump *error;
- error = i915_gpu_coredump(gt, engine_mask);
+ error = i915_gpu_coredump(gt, engine_mask, dump_flags);
if (IS_ERR(error)) {
cmpxchg(>->i915->gpu_error.first_error, NULL, error);
return;
struct i915_sched_attr sched_attr;
};
+struct __guc_capture_parsed_output;
+
struct intel_engine_coredump {
const struct intel_engine_cs *engine;
u32 rc_psmi; /* sleep state */
struct intel_instdone instdone;
+ /* GuC matched capture-lists info */
+ struct intel_guc_state_capture *capture;
+ struct __guc_capture_parsed_output *guc_capture_node;
+
struct i915_gem_context_coredump {
char comm[TASK_COMM_LEN];
u64 total_runtime;
- u32 avg_runtime;
+ u64 avg_runtime;
pid_t pid;
int active;
u32 pgtbl_er;
u32 ier;
u32 gtier[6], ngtier;
- u32 derrmr;
u32 forcewake;
u32 error; /* gen6+ */
u32 err_int; /* gen7 */
u32 gfx_mode;
u32 gtt_cache;
u32 aux_err; /* gen12 */
- u32 sfc_done[GEN12_SFC_DONE_MAX]; /* gen12 */
u32 gam_done; /* gen12 */
+ /* Display related */
+ u32 derrmr;
+ u32 sfc_done[I915_MAX_SFC]; /* gen12 */
+
u32 nfence;
u64 fence[I915_MAX_NUM_FENCES];
struct intel_uc_fw guc_fw;
struct intel_uc_fw huc_fw;
struct i915_vma_coredump *guc_log;
+ bool is_guc_capture;
} *uc;
struct intel_gt_coredump *next;
return atomic_read(&error->reset_engine_count[engine->uabi_class]);
}
+#define CORE_DUMP_FLAG_NONE 0x0
+#define CORE_DUMP_FLAG_IS_GUC_CAPTURE BIT(0)
+
#if IS_ENABLED(CONFIG_DRM_I915_CAPTURE_ERROR)
__printf(2, 3)
void i915_error_printf(struct drm_i915_error_state_buf *e, const char *f, ...);
+void intel_gpu_error_print_vma(struct drm_i915_error_state_buf *m,
+ const struct intel_engine_cs *engine,
+ const struct i915_vma_coredump *vma);
+struct i915_vma_coredump *
+intel_gpu_error_find_batch(const struct intel_engine_coredump *ee);
struct i915_gpu_coredump *i915_gpu_coredump(struct intel_gt *gt,
- intel_engine_mask_t engine_mask);
+ intel_engine_mask_t engine_mask, u32 dump_flags);
void i915_capture_error_state(struct intel_gt *gt,
- intel_engine_mask_t engine_mask);
+ intel_engine_mask_t engine_mask, u32 dump_flags);
struct i915_gpu_coredump *
i915_gpu_coredump_alloc(struct drm_i915_private *i915, gfp_t gfp);
struct intel_gt_coredump *
-intel_gt_coredump_alloc(struct intel_gt *gt, gfp_t gfp);
+intel_gt_coredump_alloc(struct intel_gt *gt, gfp_t gfp, u32 dump_flags);
struct intel_engine_coredump *
-intel_engine_coredump_alloc(struct intel_engine_cs *engine, gfp_t gfp);
+intel_engine_coredump_alloc(struct intel_engine_cs *engine, gfp_t gfp, u32 dump_flags);
struct intel_engine_capture_vma *
intel_engine_coredump_add_request(struct intel_engine_coredump *ee,
#else
static inline void
-i915_capture_error_state(struct intel_gt *gt, intel_engine_mask_t engine_mask)
+i915_capture_error_state(struct intel_gt *gt, intel_engine_mask_t engine_mask, u32 dump_flags)
{
}
}
static inline struct intel_gt_coredump *
-intel_gt_coredump_alloc(struct intel_gt *gt, gfp_t gfp)
+intel_gt_coredump_alloc(struct intel_gt *gt, gfp_t gfp, u32 dump_flags)
{
return NULL;
}
static inline struct intel_engine_coredump *
-intel_engine_coredump_alloc(struct intel_engine_cs *engine, gfp_t gfp)
+intel_engine_coredump_alloc(struct intel_engine_cs *engine, gfp_t gfp, u32 dump_flags)
{
return NULL;
}
"Default request/fence/batch buffer expiration timeout.");
#endif
+i915_param_named_unsafe(lmem_size, uint, 0400,
+ "Set the lmem size(in MiB) for each region. (default: 0, all memory)");
+
static __always_inline void _print_param(struct drm_printer *p,
const char *name,
const char *type,
param(int, enable_dpcd_backlight, -1, 0600) \
param(char *, force_probe, CONFIG_DRM_I915_FORCE_PROBE, 0400) \
param(unsigned int, request_timeout_ms, CONFIG_DRM_I915_REQUEST_TIMEOUT, CONFIG_DRM_I915_REQUEST_TIMEOUT ? 0600 : 0) \
+ param(unsigned int, lmem_size, 0, 0400) \
/* leave bools at the end to not create holes */ \
param(bool, enable_hangcheck, true, 0600) \
param(bool, load_detect_test, false, 0600) \
return total_length;
}
+static int query_hwconfig_blob(struct drm_i915_private *i915,
+ struct drm_i915_query_item *query_item)
+{
+ struct intel_gt *gt = to_gt(i915);
+ struct intel_hwconfig *hwconfig = >->info.hwconfig;
+
+ if (!hwconfig->size || !hwconfig->ptr)
+ return -ENODEV;
+
+ if (query_item->length == 0)
+ return hwconfig->size;
+
+ if (query_item->length < hwconfig->size)
+ return -EINVAL;
+
+ if (copy_to_user(u64_to_user_ptr(query_item->data_ptr),
+ hwconfig->ptr, hwconfig->size))
+ return -EFAULT;
+
+ return hwconfig->size;
+}
+
static int (* const i915_query_funcs[])(struct drm_i915_private *dev_priv,
struct drm_i915_query_item *query_item) = {
query_topology_info,
query_engine_info,
query_perf_config,
query_memregion_info,
+ query_hwconfig_blob,
};
int i915_query_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
#define GEN9_RP_STATE_LIMITS _MMIO(0x138148)
#define XEHPSDV_RP_STATE_CAP _MMIO(0x250014)
+#define GT0_PERF_LIMIT_REASONS _MMIO(0x1381a8)
+#define GT0_PERF_LIMIT_REASONS_MASK 0xde3
+#define PROCHOT_MASK REG_BIT(1)
+#define THERMAL_LIMIT_MASK REG_BIT(2)
+#define RATL_MASK REG_BIT(6)
+#define VR_THERMALERT_MASK REG_BIT(7)
+#define VR_TDC_MASK REG_BIT(8)
+#define POWER_LIMIT_4_MASK REG_BIT(9)
+#define POWER_LIMIT_1_MASK REG_BIT(11)
+#define POWER_LIMIT_2_MASK REG_BIT(12)
+
#define CHV_CLK_CTL1 _MMIO(0x101100)
#define VLV_CLK_CTL2 _MMIO(0x101104)
#define CLK_CTL2_CZCOUNT_30NS_SHIFT 28
#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
#define VLV_DISPLAY_BASE 0x180000
-#define GEN12_SFC_DONE_MAX 4
-
#endif /* __I915_REG_DEFS__ */
#include "i915_sysfs.h"
#include "intel_pm.h"
-static inline struct drm_i915_private *kdev_minor_to_i915(struct device *kdev)
+struct drm_i915_private *kdev_minor_to_i915(struct device *kdev)
{
struct drm_minor *minor = dev_get_drvdata(kdev);
return to_i915(minor->dev);
}
-#ifdef CONFIG_PM
-static u32 calc_residency(struct drm_i915_private *dev_priv,
- i915_reg_t reg)
-{
- intel_wakeref_t wakeref;
- u64 res = 0;
-
- with_intel_runtime_pm(&dev_priv->runtime_pm, wakeref)
- res = intel_rc6_residency_us(&to_gt(dev_priv)->rc6, reg);
-
- return DIV_ROUND_CLOSEST_ULL(res, 1000);
-}
-
-static ssize_t rc6_enable_show(struct device *kdev,
- struct device_attribute *attr, char *buf)
-{
- struct drm_i915_private *dev_priv = kdev_minor_to_i915(kdev);
- unsigned int mask;
-
- mask = 0;
- if (HAS_RC6(dev_priv))
- mask |= BIT(0);
- if (HAS_RC6p(dev_priv))
- mask |= BIT(1);
- if (HAS_RC6pp(dev_priv))
- mask |= BIT(2);
-
- return sysfs_emit(buf, "%x\n", mask);
-}
-
-static ssize_t rc6_residency_ms_show(struct device *kdev,
- struct device_attribute *attr, char *buf)
-{
- struct drm_i915_private *dev_priv = kdev_minor_to_i915(kdev);
- u32 rc6_residency = calc_residency(dev_priv, GEN6_GT_GFX_RC6);
- return sysfs_emit(buf, "%u\n", rc6_residency);
-}
-
-static ssize_t rc6p_residency_ms_show(struct device *kdev,
- struct device_attribute *attr, char *buf)
-{
- struct drm_i915_private *dev_priv = kdev_minor_to_i915(kdev);
- u32 rc6p_residency = calc_residency(dev_priv, GEN6_GT_GFX_RC6p);
- return sysfs_emit(buf, "%u\n", rc6p_residency);
-}
-
-static ssize_t rc6pp_residency_ms_show(struct device *kdev,
- struct device_attribute *attr, char *buf)
-{
- struct drm_i915_private *dev_priv = kdev_minor_to_i915(kdev);
- u32 rc6pp_residency = calc_residency(dev_priv, GEN6_GT_GFX_RC6pp);
- return sysfs_emit(buf, "%u\n", rc6pp_residency);
-}
-
-static ssize_t media_rc6_residency_ms_show(struct device *kdev,
- struct device_attribute *attr, char *buf)
-{
- struct drm_i915_private *dev_priv = kdev_minor_to_i915(kdev);
- u32 rc6_residency = calc_residency(dev_priv, VLV_GT_MEDIA_RC6);
- return sysfs_emit(buf, "%u\n", rc6_residency);
-}
-
-static DEVICE_ATTR_RO(rc6_enable);
-static DEVICE_ATTR_RO(rc6_residency_ms);
-static DEVICE_ATTR_RO(rc6p_residency_ms);
-static DEVICE_ATTR_RO(rc6pp_residency_ms);
-static DEVICE_ATTR_RO(media_rc6_residency_ms);
-
-static struct attribute *rc6_attrs[] = {
- &dev_attr_rc6_enable.attr,
- &dev_attr_rc6_residency_ms.attr,
- NULL
-};
-
-static const struct attribute_group rc6_attr_group = {
- .name = power_group_name,
- .attrs = rc6_attrs
-};
-
-static struct attribute *rc6p_attrs[] = {
- &dev_attr_rc6p_residency_ms.attr,
- &dev_attr_rc6pp_residency_ms.attr,
- NULL
-};
-
-static const struct attribute_group rc6p_attr_group = {
- .name = power_group_name,
- .attrs = rc6p_attrs
-};
-
-static struct attribute *media_rc6_attrs[] = {
- &dev_attr_media_rc6_residency_ms.attr,
- NULL
-};
-
-static const struct attribute_group media_rc6_attr_group = {
- .name = power_group_name,
- .attrs = media_rc6_attrs
-};
-#endif
-
static int l3_access_valid(struct drm_i915_private *i915, loff_t offset)
{
if (!HAS_L3_DPF(i915))
.private = (void *)1
};
-static ssize_t gt_act_freq_mhz_show(struct device *kdev,
- struct device_attribute *attr, char *buf)
-{
- struct drm_i915_private *i915 = kdev_minor_to_i915(kdev);
- struct intel_rps *rps = &to_gt(i915)->rps;
-
- return sysfs_emit(buf, "%d\n", intel_rps_read_actual_frequency(rps));
-}
-
-static ssize_t gt_cur_freq_mhz_show(struct device *kdev,
- struct device_attribute *attr, char *buf)
-{
- struct drm_i915_private *i915 = kdev_minor_to_i915(kdev);
- struct intel_rps *rps = &to_gt(i915)->rps;
-
- return sysfs_emit(buf, "%d\n", intel_rps_get_requested_frequency(rps));
-}
-
-static ssize_t gt_boost_freq_mhz_show(struct device *kdev, struct device_attribute *attr, char *buf)
-{
- struct drm_i915_private *i915 = kdev_minor_to_i915(kdev);
- struct intel_rps *rps = &to_gt(i915)->rps;
-
- return sysfs_emit(buf, "%d\n", intel_rps_get_boost_frequency(rps));
-}
-
-static ssize_t gt_boost_freq_mhz_store(struct device *kdev,
- struct device_attribute *attr,
- const char *buf, size_t count)
-{
- struct drm_i915_private *dev_priv = kdev_minor_to_i915(kdev);
- struct intel_rps *rps = &to_gt(dev_priv)->rps;
- ssize_t ret;
- u32 val;
-
- ret = kstrtou32(buf, 0, &val);
- if (ret)
- return ret;
-
- ret = intel_rps_set_boost_frequency(rps, val);
-
- return ret ?: count;
-}
-
-static ssize_t vlv_rpe_freq_mhz_show(struct device *kdev,
- struct device_attribute *attr, char *buf)
-{
- struct drm_i915_private *dev_priv = kdev_minor_to_i915(kdev);
- struct intel_rps *rps = &to_gt(dev_priv)->rps;
-
- return sysfs_emit(buf, "%d\n", intel_gpu_freq(rps, rps->efficient_freq));
-}
-
-static ssize_t gt_max_freq_mhz_show(struct device *kdev, struct device_attribute *attr, char *buf)
-{
- struct drm_i915_private *dev_priv = kdev_minor_to_i915(kdev);
- struct intel_gt *gt = to_gt(dev_priv);
- struct intel_rps *rps = >->rps;
-
- return sysfs_emit(buf, "%d\n", intel_rps_get_max_frequency(rps));
-}
-
-static ssize_t gt_max_freq_mhz_store(struct device *kdev,
- struct device_attribute *attr,
- const char *buf, size_t count)
-{
- struct drm_i915_private *dev_priv = kdev_minor_to_i915(kdev);
- struct intel_gt *gt = to_gt(dev_priv);
- struct intel_rps *rps = >->rps;
- ssize_t ret;
- u32 val;
-
- ret = kstrtou32(buf, 0, &val);
- if (ret)
- return ret;
-
- ret = intel_rps_set_max_frequency(rps, val);
-
- return ret ?: count;
-}
-
-static ssize_t gt_min_freq_mhz_show(struct device *kdev, struct device_attribute *attr, char *buf)
-{
- struct drm_i915_private *i915 = kdev_minor_to_i915(kdev);
- struct intel_gt *gt = to_gt(i915);
- struct intel_rps *rps = >->rps;
-
- return sysfs_emit(buf, "%d\n", intel_rps_get_min_frequency(rps));
-}
-
-static ssize_t gt_min_freq_mhz_store(struct device *kdev,
- struct device_attribute *attr,
- const char *buf, size_t count)
-{
- struct drm_i915_private *i915 = kdev_minor_to_i915(kdev);
- struct intel_rps *rps = &to_gt(i915)->rps;
- ssize_t ret;
- u32 val;
-
- ret = kstrtou32(buf, 0, &val);
- if (ret)
- return ret;
-
- ret = intel_rps_set_min_frequency(rps, val);
-
- return ret ?: count;
-}
-
-static DEVICE_ATTR_RO(gt_act_freq_mhz);
-static DEVICE_ATTR_RO(gt_cur_freq_mhz);
-static DEVICE_ATTR_RW(gt_boost_freq_mhz);
-static DEVICE_ATTR_RW(gt_max_freq_mhz);
-static DEVICE_ATTR_RW(gt_min_freq_mhz);
-
-static DEVICE_ATTR_RO(vlv_rpe_freq_mhz);
-
-static ssize_t gt_rp_mhz_show(struct device *kdev, struct device_attribute *attr, char *buf);
-static DEVICE_ATTR(gt_RP0_freq_mhz, S_IRUGO, gt_rp_mhz_show, NULL);
-static DEVICE_ATTR(gt_RP1_freq_mhz, S_IRUGO, gt_rp_mhz_show, NULL);
-static DEVICE_ATTR(gt_RPn_freq_mhz, S_IRUGO, gt_rp_mhz_show, NULL);
-
-/* For now we have a static number of RP states */
-static ssize_t gt_rp_mhz_show(struct device *kdev, struct device_attribute *attr, char *buf)
-{
- struct drm_i915_private *dev_priv = kdev_minor_to_i915(kdev);
- struct intel_rps *rps = &to_gt(dev_priv)->rps;
- u32 val;
-
- if (attr == &dev_attr_gt_RP0_freq_mhz)
- val = intel_rps_get_rp0_frequency(rps);
- else if (attr == &dev_attr_gt_RP1_freq_mhz)
- val = intel_rps_get_rp1_frequency(rps);
- else if (attr == &dev_attr_gt_RPn_freq_mhz)
- val = intel_rps_get_rpn_frequency(rps);
- else
- BUG();
-
- return sysfs_emit(buf, "%d\n", val);
-}
-
-static const struct attribute * const gen6_attrs[] = {
- &dev_attr_gt_act_freq_mhz.attr,
- &dev_attr_gt_cur_freq_mhz.attr,
- &dev_attr_gt_boost_freq_mhz.attr,
- &dev_attr_gt_max_freq_mhz.attr,
- &dev_attr_gt_min_freq_mhz.attr,
- &dev_attr_gt_RP0_freq_mhz.attr,
- &dev_attr_gt_RP1_freq_mhz.attr,
- &dev_attr_gt_RPn_freq_mhz.attr,
- NULL,
-};
-
-static const struct attribute * const vlv_attrs[] = {
- &dev_attr_gt_act_freq_mhz.attr,
- &dev_attr_gt_cur_freq_mhz.attr,
- &dev_attr_gt_boost_freq_mhz.attr,
- &dev_attr_gt_max_freq_mhz.attr,
- &dev_attr_gt_min_freq_mhz.attr,
- &dev_attr_gt_RP0_freq_mhz.attr,
- &dev_attr_gt_RP1_freq_mhz.attr,
- &dev_attr_gt_RPn_freq_mhz.attr,
- &dev_attr_vlv_rpe_freq_mhz.attr,
- NULL,
-};
-
#if IS_ENABLED(CONFIG_DRM_I915_CAPTURE_ERROR)
static ssize_t error_state_read(struct file *filp, struct kobject *kobj,
struct device *kdev = dev_priv->drm.primary->kdev;
int ret;
-#ifdef CONFIG_PM
- if (HAS_RC6(dev_priv)) {
- ret = sysfs_merge_group(&kdev->kobj,
- &rc6_attr_group);
- if (ret)
- drm_err(&dev_priv->drm,
- "RC6 residency sysfs setup failed\n");
- }
- if (HAS_RC6p(dev_priv)) {
- ret = sysfs_merge_group(&kdev->kobj,
- &rc6p_attr_group);
- if (ret)
- drm_err(&dev_priv->drm,
- "RC6p residency sysfs setup failed\n");
- }
- if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) {
- ret = sysfs_merge_group(&kdev->kobj,
- &media_rc6_attr_group);
- if (ret)
- drm_err(&dev_priv->drm,
- "Media RC6 residency sysfs setup failed\n");
- }
-#endif
if (HAS_L3_DPF(dev_priv)) {
ret = device_create_bin_file(kdev, &dpf_attrs);
if (ret)
}
}
- ret = 0;
- if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv))
- ret = sysfs_create_files(&kdev->kobj, vlv_attrs);
- else if (GRAPHICS_VER(dev_priv) >= 6)
- ret = sysfs_create_files(&kdev->kobj, gen6_attrs);
- if (ret)
- drm_err(&dev_priv->drm, "RPS sysfs setup failed\n");
+ dev_priv->sysfs_gt = kobject_create_and_add("gt", &kdev->kobj);
+ if (!dev_priv->sysfs_gt)
+ drm_warn(&dev_priv->drm,
+ "failed to register GT sysfs directory\n");
i915_setup_error_capture(kdev);
i915_teardown_error_capture(kdev);
- if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv))
- sysfs_remove_files(&kdev->kobj, vlv_attrs);
- else
- sysfs_remove_files(&kdev->kobj, gen6_attrs);
device_remove_bin_file(kdev, &dpf_attrs_1);
device_remove_bin_file(kdev, &dpf_attrs);
-#ifdef CONFIG_PM
- sysfs_unmerge_group(&kdev->kobj, &rc6_attr_group);
- sysfs_unmerge_group(&kdev->kobj, &rc6p_attr_group);
-#endif
}
#ifndef __I915_SYSFS_H__
#define __I915_SYSFS_H__
+struct device;
struct drm_i915_private;
+struct drm_i915_private *kdev_minor_to_i915(struct device *kdev);
+
void i915_setup_sysfs(struct drm_i915_private *i915);
void i915_teardown_sysfs(struct drm_i915_private *i915);
GEM_BUG_ON(min_page_size < mm->chunk_size);
- if (place->flags & TTM_PL_FLAG_CONTIGUOUS) {
+ if (place->fpfn + bman_res->base.num_pages != place->lpfn &&
+ place->flags & TTM_PL_FLAG_CONTIGUOUS) {
unsigned long pages;
size = roundup_pow_of_two(size);
* This is the only exception to the requirement of the object lock
* being held.
*/
- if (atomic_read(&vma->vm->open))
+ if (kref_read(&vma->vm->ref))
assert_object_held_shared(vma->obj);
}
struct i915_vma *pos = ERR_PTR(-E2BIG);
struct i915_vma *vma;
struct rb_node *rb, **p;
+ int err;
/* The aliasing_ppgtt should never be used directly! */
GEM_BUG_ON(vm == &vm->gt->ggtt->alias->vm);
if (vma == NULL)
return ERR_PTR(-ENOMEM);
- kref_init(&vma->ref);
- vma->vm = i915_vm_get(vm);
vma->ops = &vm->vma_ops;
vma->obj = obj;
vma->size = obj->base.size;
}
INIT_LIST_HEAD(&vma->closed_link);
+ INIT_LIST_HEAD(&vma->obj_link);
+ RB_CLEAR_NODE(&vma->obj_node);
if (view && view->type != I915_GGTT_VIEW_NORMAL) {
vma->ggtt_view = *view;
GEM_BUG_ON(!IS_ALIGNED(vma->size, I915_GTT_PAGE_SIZE));
- spin_lock(&obj->vma.lock);
+ err = mutex_lock_interruptible(&vm->mutex);
+ if (err) {
+ pos = ERR_PTR(err);
+ goto err_vma;
+ }
+ vma->vm = vm;
+ list_add_tail(&vma->vm_link, &vm->unbound_list);
+
+ spin_lock(&obj->vma.lock);
if (i915_is_ggtt(vm)) {
if (unlikely(overflows_type(vma->size, u32)))
goto err_unlock;
list_add_tail(&vma->obj_link, &obj->vma.list);
spin_unlock(&obj->vma.lock);
+ mutex_unlock(&vm->mutex);
return vma;
err_unlock:
spin_unlock(&obj->vma.lock);
+ list_del_init(&vma->vm_link);
+ mutex_unlock(&vm->mutex);
err_vma:
- i915_vm_put(vm);
i915_vma_free(vma);
return pos;
}
struct i915_vma *vma;
GEM_BUG_ON(view && !i915_is_ggtt_or_dpt(vm));
- GEM_BUG_ON(!atomic_read(&vm->open));
+ GEM_BUG_ON(!kref_read(&vm->ref));
spin_lock(&obj->vma.lock);
vma = i915_vma_lookup(obj, vm, view);
i915_gem_object_put(vw->pinned);
i915_vm_free_pt_stash(vw->vm, &vw->stash);
- i915_vm_put(vw->vm);
if (vw->vma_res)
i915_vma_resource_put(vw->vma_res);
}
if (!work->vma_res->bi.pages_rsgt)
work->pinned = i915_gem_object_get(vma->obj);
} else {
- if (vma->obj) {
- ret = i915_gem_object_wait_moving_fence(vma->obj, true);
- if (ret) {
- i915_vma_resource_free(vma->resource);
- vma->resource = NULL;
+ ret = i915_gem_object_wait_moving_fence(vma->obj, true);
+ if (ret) {
+ i915_vma_resource_free(vma->resource);
+ vma->resource = NULL;
- return ret;
- }
+ return ret;
}
vma->ops->bind_vma(vma->vm, NULL, vma->resource, cache_level,
bind_flags);
}
- if (vma->obj)
- set_bit(I915_BO_WAS_BOUND_BIT, &vma->obj->flags);
+ set_bit(I915_BO_WAS_BOUND_BIT, &vma->obj->flags);
atomic_or(bind_flags, &vma->flags);
return 0;
GEM_BUG_ON(!drm_mm_node_allocated(&vma->node));
GEM_BUG_ON(!i915_gem_valid_gtt_space(vma, color));
- list_add_tail(&vma->vm_link, &vma->vm->bound_list);
+ list_move_tail(&vma->vm_link, &vma->vm->bound_list);
return 0;
}
* vma, we can drop its hold on the backing storage and allow
* it to be reaped by the shrinker.
*/
- list_del(&vma->vm_link);
+ list_move_tail(&vma->vm_link, &vma->vm->unbound_list);
}
static bool try_qad_pin(struct i915_vma *vma, unsigned int flags)
if (flags & PIN_GLOBAL)
wakeref = intel_runtime_pm_get(&vma->vm->i915->runtime_pm);
- moving = vma->obj ? i915_gem_object_get_moving_fence(vma->obj) : NULL;
- if (flags & vma->vm->bind_async_flags || moving) {
+ if (flags & vma->vm->bind_async_flags) {
/* lock VM */
err = i915_vm_lock_objects(vma->vm, ww);
if (err)
goto err_rpm;
}
- work->vm = i915_vm_get(vma->vm);
+ work->vm = vma->vm;
+ moving = i915_gem_object_get_moving_fence(vma->obj);
dma_fence_work_chain(&work->base, moving);
/* Allocate enough page directories to used PTE */
__i915_vma_remove_closed(vma);
}
-void i915_vma_release(struct kref *ref)
-{
- struct i915_vma *vma = container_of(ref, typeof(*vma), ref);
-
- i915_vm_put(vma->vm);
- i915_active_fini(&vma->active);
- GEM_WARN_ON(vma->resource);
- i915_vma_free(vma);
-}
-
static void force_unbind(struct i915_vma *vma)
{
if (!drm_mm_node_allocated(&vma->node))
GEM_BUG_ON(drm_mm_node_allocated(&vma->node));
}
-static void release_references(struct i915_vma *vma)
+static void release_references(struct i915_vma *vma, bool vm_ddestroy)
{
struct drm_i915_gem_object *obj = vma->obj;
list_del(&vma->obj_link);
if (!RB_EMPTY_NODE(&vma->obj_node))
rb_erase(&vma->obj_node, &obj->vma.tree);
+
spin_unlock(&obj->vma.lock);
__i915_vma_remove_closed(vma);
- __i915_vma_put(vma);
+ if (vm_ddestroy)
+ i915_vm_resv_put(vma->vm);
+
+ i915_active_fini(&vma->active);
+ GEM_WARN_ON(vma->resource);
+ i915_vma_free(vma);
}
/**
* - __i915_gem_object_pages_fini()
* - __i915_vm_close() - Blocks the above function by taking a reference on
* the object.
- * - __i915_vma_parked() - Blocks the above functions by taking an open-count on
- * the vm and a reference on the object.
+ * - __i915_vma_parked() - Blocks the above functions by taking a reference
+ * on the vm and a reference on the object. Also takes the object lock so
+ * destruction from __i915_vma_parked() can be blocked by holding the
+ * object lock. Since the object lock is only allowed from within i915 with
+ * an object refcount, holding the object lock also implicitly blocks the
+ * vma freeing from __i915_gem_object_pages_fini().
*
* Because of locks taken during destruction, a vma is also guaranteed to
* stay alive while the following locks are held if it was looked up while
* - vm->mutex
* - obj->vma.lock
* - gt->closed_lock
- *
- * A vma user can also temporarily keep the vma alive while holding a vma
- * reference.
*/
void i915_vma_destroy_locked(struct i915_vma *vma)
{
lockdep_assert_held(&vma->vm->mutex);
force_unbind(vma);
- release_references(vma);
+ list_del_init(&vma->vm_link);
+ release_references(vma, false);
}
void i915_vma_destroy(struct i915_vma *vma)
{
+ bool vm_ddestroy;
+
mutex_lock(&vma->vm->mutex);
force_unbind(vma);
+ list_del_init(&vma->vm_link);
+ vm_ddestroy = vma->vm_ddestroy;
+ vma->vm_ddestroy = false;
mutex_unlock(&vma->vm->mutex);
- release_references(vma);
+ release_references(vma, vm_ddestroy);
}
void i915_vma_parked(struct intel_gt *gt)
if (!kref_get_unless_zero(&obj->base.refcount))
continue;
- if (!i915_vm_tryopen(vm)) {
+ if (!i915_vm_tryget(vm)) {
i915_gem_object_put(obj);
continue;
}
}
i915_gem_object_put(obj);
- i915_vm_close(vm);
+ i915_vm_put(vm);
}
}
/* If vm is not open, unbind is a nop. */
vma_res->needs_wakeref = i915_vma_is_bound(vma, I915_VMA_GLOBAL_BIND) &&
- atomic_read(&vma->vm->open);
+ kref_read(&vma->vm->ref);
+ vma_res->skip_pte_rewrite = !kref_read(&vma->vm->ref) ||
+ vma->vm->skip_pte_rewrite;
trace_i915_vma_unbind(vma);
unbind_fence = i915_vma_resource_unbind(vma_res);
void i915_vma_close(struct i915_vma *vma);
void i915_vma_reopen(struct i915_vma *vma);
-static inline struct i915_vma *__i915_vma_get(struct i915_vma *vma)
-{
- if (kref_get_unless_zero(&vma->ref))
- return vma;
-
- return NULL;
-}
-
-void i915_vma_release(struct kref *ref);
-static inline void __i915_vma_put(struct i915_vma *vma)
-{
- kref_put(&vma->ref, i915_vma_release);
-}
-
void i915_vma_destroy_locked(struct i915_vma *vma);
void i915_vma_destroy(struct i915_vma *vma);
bool lockdep_cookie;
lockdep_cookie = dma_fence_begin_signalling();
- if (likely(atomic_read(&vm->open)))
+ if (likely(!vma_res->skip_pte_rewrite))
vma_res->ops->unbind_vma(vm, vma_res);
dma_fence_end_signalling(lockdep_cookie);
* deferred to a work item awaiting unsignaled fences. This is a hack.
* (dma_fence_work uses a fence flag for this, but this seems slightly
* cleaner).
+ * @needs_wakeref: Whether a wakeref is needed during unbind. Since we can't
+ * take a wakeref in the dma-fence signalling critical path, it needs to be
+ * taken when the unbind is scheduled.
+ * @skip_pte_rewrite: During ggtt suspend and vm takedown pte rewriting
+ * needs to be skipped for unbind.
*
* The lifetime of a struct i915_vma_resource is from a binding request to
* the actual possible asynchronous unbind has completed.
bool allocated:1;
bool immediate_unbind:1;
bool needs_wakeref:1;
+ bool skip_pte_rewrite:1;
};
bool i915_vma_resource_hold(struct i915_vma_resource *vma_res,
* handles (but same file) for execbuf, i.e. the number of aliases
* that exist in the ctx->handle_vmas LUT for this vma.
*/
- struct kref ref;
atomic_t open_count;
atomic_t flags;
/**
atomic_t pages_count; /* number of active binds to the pages */
/**
+ * Whether we hold a reference on the vm dma_resv lock to temporarily
+ * block vm freeing until the vma is destroyed.
+ * Protected by the vm mutex.
+ */
+ bool vm_ddestroy;
+
+ /**
* Support different GGTT views into the same object.
* This means there can be multiple VMA mappings per object and per VM.
* i915_ggtt_view_type is used to distinguish between those entries.
.class = INTEL_MEMORY_SYSTEM,
.instance = 0,
},
- [INTEL_REGION_LMEM] = {
+ [INTEL_REGION_LMEM_0] = {
.class = INTEL_MEMORY_LOCAL,
.instance = 0,
},
enum intel_region_id {
INTEL_REGION_SMEM = 0,
- INTEL_REGION_LMEM,
+ INTEL_REGION_LMEM_0,
+ INTEL_REGION_LMEM_1,
+ INTEL_REGION_LMEM_2,
+ INTEL_REGION_LMEM_3,
INTEL_REGION_STOLEN_SMEM,
INTEL_REGION_STOLEN_LMEM,
INTEL_REGION_UNKNOWN, /* Should be last */
};
#define REGION_SMEM BIT(INTEL_REGION_SMEM)
-#define REGION_LMEM BIT(INTEL_REGION_LMEM)
+#define REGION_LMEM BIT(INTEL_REGION_LMEM_0)
#define REGION_STOLEN_SMEM BIT(INTEL_REGION_STOLEN_SMEM)
#define REGION_STOLEN_LMEM BIT(INTEL_REGION_STOLEN_LMEM)
int (*init_object)(struct intel_memory_region *mem,
struct drm_i915_gem_object *obj,
+ resource_size_t offset,
resource_size_t size,
resource_size_t page_size,
unsigned int flags);
#include "intel_region_ttm.h"
+#include "gem/i915_gem_region.h"
#include "gem/i915_gem_ttm.h" /* For the funcs/ops export only */
/**
* DOC: TTM support structure
*/
struct ttm_resource *
intel_region_ttm_resource_alloc(struct intel_memory_region *mem,
+ resource_size_t offset,
resource_size_t size,
unsigned int flags)
{
if (flags & I915_BO_ALLOC_CONTIGUOUS)
place.flags |= TTM_PL_FLAG_CONTIGUOUS;
- if (mem->io_size && mem->io_size < mem->total) {
+ if (offset != I915_BO_INVALID_OFFSET) {
+ place.fpfn = offset >> PAGE_SHIFT;
+ place.lpfn = place.fpfn + (size >> PAGE_SHIFT);
+ } else if (mem->io_size && mem->io_size < mem->total) {
if (flags & I915_BO_ALLOC_GPU_ONLY) {
place.flags |= TTM_PL_FLAG_TOPDOWN;
} else {
#ifdef CONFIG_DRM_I915_SELFTEST
struct ttm_resource *
intel_region_ttm_resource_alloc(struct intel_memory_region *mem,
+ resource_size_t offset,
resource_size_t size,
unsigned int flags);
#endif
return NOTIFY_OK;
}
-int intel_uncore_setup_mmio(struct intel_uncore *uncore)
+int intel_uncore_setup_mmio(struct intel_uncore *uncore, phys_addr_t phys_addr)
{
struct drm_i915_private *i915 = uncore->i915;
- struct pci_dev *pdev = to_pci_dev(i915->drm.dev);
- int mmio_bar;
int mmio_size;
- mmio_bar = GRAPHICS_VER(i915) == 2 ? 1 : 0;
/*
* Before gen4, the registers and the GTT are behind different BARs.
* However, from gen4 onwards, the registers and the GTT are shared
else
mmio_size = 2 * 1024 * 1024;
- uncore->regs = pci_iomap(pdev, mmio_bar, mmio_size);
+ uncore->regs = ioremap(phys_addr, mmio_size);
if (uncore->regs == NULL) {
drm_err(&i915->drm, "failed to map registers\n");
return -EIO;
void intel_uncore_cleanup_mmio(struct intel_uncore *uncore)
{
- struct pci_dev *pdev = to_pci_dev(uncore->i915->drm.dev);
-
- pci_iounmap(pdev, uncore->regs);
+ iounmap(uncore->regs);
}
void intel_uncore_init_early(struct intel_uncore *uncore,
return fw_domains;
}
-u32 intel_uncore_read_with_mcr_steering_fw(struct intel_uncore *uncore,
- i915_reg_t reg,
- int slice, int subslice)
+/**
+ * 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;
+ 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);
mcr |= mcr_ss;
intel_uncore_write_fw(uncore, GEN8_MCR_SELECTOR, mcr);
- val = intel_uncore_read_fw(uncore, reg);
+ 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;
return val;
}
-u32 intel_uncore_read_with_mcr_steering(struct intel_uncore *uncore,
- i915_reg_t reg, int slice, int subslice)
+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,
- FW_REG_READ);
+ 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 = intel_uncore_read_with_mcr_steering_fw(uncore, reg, slice, subslice);
+ 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"
#include <linux/notifier.h>
#include <linux/hrtimer.h>
#include <linux/io-64-nonatomic-lo-hi.h>
+#include <linux/types.h>
#include "i915_reg_defs.h"
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,
struct intel_gt *gt);
-int intel_uncore_setup_mmio(struct intel_uncore *uncore);
+int intel_uncore_setup_mmio(struct intel_uncore *uncore, phys_addr_t phys_addr);
int intel_uncore_init_mmio(struct intel_uncore *uncore);
void intel_uncore_prune_engine_fw_domains(struct intel_uncore *uncore,
struct intel_gt *gt);
goto out_free;
}
GEM_BUG_ON(offset_in_page(ppgtt->vm.total));
- GEM_BUG_ON(!atomic_read(&ppgtt->vm.open));
+ assert_vm_alive(&ppgtt->vm);
err = func(&ppgtt->vm, 0, ppgtt->vm.total, end_time);
vma->resource->bi.pages = vma->pages;
mutex_lock(&vma->vm->mutex);
- list_add_tail(&vma->vm_link, &vma->vm->bound_list);
+ list_move_tail(&vma->vm_link, &vma->vm->bound_list);
mutex_unlock(&vma->vm->mutex);
}
destroy_workqueue(i915->wq);
intel_region_ttm_device_fini(i915);
- intel_gt_driver_late_release(to_gt(i915));
+ intel_gt_driver_late_release_all(i915);
intel_memory_regions_driver_release(i915);
drm_mode_config_cleanup(&i915->drm);
},
};
+static void mock_gt_probe(struct drm_i915_private *i915)
+{
+ i915->gt[0] = &i915->gt0;
+}
+
struct drm_i915_private *mock_gem_device(void)
{
#if IS_ENABLED(CONFIG_IOMMU_API) && defined(CONFIG_INTEL_IOMMU)
spin_lock_init(&i915->gpu_error.lock);
i915_gem_init__mm(i915);
- intel_gt_init_early(to_gt(i915), i915);
- __intel_gt_init_early(to_gt(i915), i915);
+ intel_root_gt_init_early(i915);
mock_uncore_init(&i915->uncore, i915);
atomic_inc(&to_gt(i915)->wakeref.count); /* disable; no hw support */
to_gt(i915)->awake = -ENODEV;
+ mock_gt_probe(i915);
ret = intel_region_ttm_device_init(i915);
if (ret)
err_drv:
intel_region_ttm_device_fini(i915);
err_ttm:
- intel_gt_driver_late_release(to_gt(i915));
+ intel_gt_driver_late_release_all(i915);
intel_memory_regions_driver_release(i915);
drm_mode_config_cleanup(&i915->drm);
mock_destroy_device(i915);
int err;
obj->mm.res = intel_region_ttm_resource_alloc(obj->mm.region,
+ obj->bo_offset,
obj->base.size,
obj->flags);
if (IS_ERR(obj->mm.res))
static int mock_object_init(struct intel_memory_region *mem,
struct drm_i915_gem_object *obj,
+ resource_size_t offset,
resource_size_t size,
resource_size_t page_size,
unsigned int flags)
drm_gem_private_object_init(&i915->drm, &obj->base, size);
i915_gem_object_init(obj, &mock_region_obj_ops, &lock_class, flags);
+ obj->bo_offset = offset;
+
obj->read_domains = I915_GEM_DOMAIN_CPU | I915_GEM_DOMAIN_GTT;
i915_gem_object_set_cache_coherency(obj, I915_CACHE_NONE);
*
* The behaviour is determined by the @query_id. Note that exactly what
* @data_ptr is also depends on the specific @query_id.
+ *
+ * For specific queries see:
+ * * `GuC HWCONFIG blob uAPI`_
*/
struct drm_i915_query_item {
/** @query_id: The id for this query */
#define DRM_I915_QUERY_ENGINE_INFO 2
#define DRM_I915_QUERY_PERF_CONFIG 3
#define DRM_I915_QUERY_MEMORY_REGIONS 4
+#define DRM_I915_QUERY_HWCONFIG_BLOB 5
/* Must be kept compact -- no holes and well documented */
/**
};
/**
+ * DOC: GuC HWCONFIG blob uAPI
+ *
+ * The GuC produces a blob with information about the current device.
+ * i915 reads this blob from GuC and makes it available via this uAPI.
+ *
+ * The format and meaning of the blob content are documented in the
+ * Programmer's Reference Manual.
+ */
+
+/**
* struct drm_i915_gem_create_ext - Existing gem_create behaviour, with added
* extension support using struct i915_user_extension.
*