2015-08-12 08:43:39 -06:00
|
|
|
/*
|
|
|
|
* Copyright © 2014 Intel Corporation
|
|
|
|
*
|
|
|
|
* Permission is hereby granted, free of charge, to any person obtaining a
|
|
|
|
* copy of this software and associated documentation files (the "Software"),
|
|
|
|
* to deal in the Software without restriction, including without limitation
|
|
|
|
* the rights to use, copy, modify, merge, publish, distribute, sublicense,
|
|
|
|
* and/or sell copies of the Software, and to permit persons to whom the
|
|
|
|
* Software is furnished to do so, subject to the following conditions:
|
|
|
|
*
|
|
|
|
* The above copyright notice and this permission notice (including the next
|
|
|
|
* paragraph) shall be included in all copies or substantial portions of the
|
|
|
|
* Software.
|
|
|
|
*
|
|
|
|
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
|
|
|
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
|
|
|
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
|
|
|
|
* THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
|
|
|
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
|
|
|
|
* FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
|
|
|
|
* IN THE SOFTWARE.
|
|
|
|
*
|
|
|
|
*/
|
|
|
|
#include <linux/firmware.h>
|
|
|
|
#include <linux/circ_buf.h>
|
|
|
|
#include "i915_drv.h"
|
|
|
|
#include "intel_guc.h"
|
|
|
|
|
2015-08-12 08:43:41 -06:00
|
|
|
/**
|
2015-10-19 17:10:54 -06:00
|
|
|
* DOC: GuC-based command submission
|
2015-08-12 08:43:41 -06:00
|
|
|
*
|
|
|
|
* i915_guc_client:
|
|
|
|
* We use the term client to avoid confusion with contexts. A i915_guc_client is
|
|
|
|
* equivalent to GuC object guc_context_desc. This context descriptor is
|
|
|
|
* allocated from a pool of 1024 entries. Kernel driver will allocate doorbell
|
|
|
|
* and workqueue for it. Also the process descriptor (guc_process_desc), which
|
|
|
|
* is mapped to client space. So the client can write Work Item then ring the
|
|
|
|
* doorbell.
|
|
|
|
*
|
|
|
|
* To simplify the implementation, we allocate one gem object that contains all
|
|
|
|
* pages for doorbell, process descriptor and workqueue.
|
|
|
|
*
|
|
|
|
* The Scratch registers:
|
|
|
|
* There are 16 MMIO-based registers start from 0xC180. The kernel driver writes
|
|
|
|
* a value to the action register (SOFT_SCRATCH_0) along with any data. It then
|
|
|
|
* triggers an interrupt on the GuC via another register write (0xC4C8).
|
|
|
|
* Firmware writes a success/fail code back to the action register after
|
|
|
|
* processes the request. The kernel driver polls waiting for this update and
|
|
|
|
* then proceeds.
|
|
|
|
* See host2guc_action()
|
|
|
|
*
|
|
|
|
* Doorbells:
|
|
|
|
* Doorbells are interrupts to uKernel. A doorbell is a single cache line (QW)
|
|
|
|
* mapped into process space.
|
|
|
|
*
|
|
|
|
* Work Items:
|
|
|
|
* There are several types of work items that the host may place into a
|
|
|
|
* workqueue, each with its own requirements and limitations. Currently only
|
|
|
|
* WQ_TYPE_INORDER is needed to support legacy submission via GuC, which
|
|
|
|
* represents in-order queue. The kernel driver packs ring tail pointer and an
|
|
|
|
* ELSP context descriptor dword into Work Item.
|
|
|
|
* See guc_add_workqueue_item()
|
|
|
|
*
|
|
|
|
*/
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Read GuC command/status register (SOFT_SCRATCH_0)
|
|
|
|
* Return true if it contains a response rather than a command
|
|
|
|
*/
|
|
|
|
static inline bool host2guc_action_response(struct drm_i915_private *dev_priv,
|
|
|
|
u32 *status)
|
|
|
|
{
|
|
|
|
u32 val = I915_READ(SOFT_SCRATCH(0));
|
|
|
|
*status = val;
|
|
|
|
return GUC2HOST_IS_RESPONSE(val);
|
|
|
|
}
|
|
|
|
|
|
|
|
static int host2guc_action(struct intel_guc *guc, u32 *data, u32 len)
|
|
|
|
{
|
|
|
|
struct drm_i915_private *dev_priv = guc_to_i915(guc);
|
|
|
|
u32 status;
|
|
|
|
int i;
|
|
|
|
int ret;
|
|
|
|
|
|
|
|
if (WARN_ON(len < 1 || len > 15))
|
|
|
|
return -EINVAL;
|
|
|
|
|
|
|
|
intel_uncore_forcewake_get(dev_priv, FORCEWAKE_ALL);
|
|
|
|
|
|
|
|
dev_priv->guc.action_count += 1;
|
|
|
|
dev_priv->guc.action_cmd = data[0];
|
|
|
|
|
|
|
|
for (i = 0; i < len; i++)
|
|
|
|
I915_WRITE(SOFT_SCRATCH(i), data[i]);
|
|
|
|
|
|
|
|
POSTING_READ(SOFT_SCRATCH(i - 1));
|
|
|
|
|
|
|
|
I915_WRITE(HOST2GUC_INTERRUPT, HOST2GUC_TRIGGER);
|
|
|
|
|
|
|
|
/* No HOST2GUC command should take longer than 10ms */
|
|
|
|
ret = wait_for_atomic(host2guc_action_response(dev_priv, &status), 10);
|
|
|
|
if (status != GUC2HOST_STATUS_SUCCESS) {
|
|
|
|
/*
|
|
|
|
* Either the GuC explicitly returned an error (which
|
|
|
|
* we convert to -EIO here) or no response at all was
|
|
|
|
* received within the timeout limit (-ETIMEDOUT)
|
|
|
|
*/
|
|
|
|
if (ret != -ETIMEDOUT)
|
|
|
|
ret = -EIO;
|
|
|
|
|
|
|
|
DRM_ERROR("GUC: host2guc action 0x%X failed. ret=%d "
|
|
|
|
"status=0x%08X response=0x%08X\n",
|
|
|
|
data[0], ret, status,
|
|
|
|
I915_READ(SOFT_SCRATCH(15)));
|
|
|
|
|
|
|
|
dev_priv->guc.action_fail += 1;
|
|
|
|
dev_priv->guc.action_err = ret;
|
|
|
|
}
|
|
|
|
dev_priv->guc.action_status = status;
|
|
|
|
|
|
|
|
intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL);
|
|
|
|
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Tell the GuC to allocate or deallocate a specific doorbell
|
|
|
|
*/
|
|
|
|
|
|
|
|
static int host2guc_allocate_doorbell(struct intel_guc *guc,
|
|
|
|
struct i915_guc_client *client)
|
|
|
|
{
|
|
|
|
u32 data[2];
|
|
|
|
|
|
|
|
data[0] = HOST2GUC_ACTION_ALLOCATE_DOORBELL;
|
|
|
|
data[1] = client->ctx_index;
|
|
|
|
|
|
|
|
return host2guc_action(guc, data, 2);
|
|
|
|
}
|
|
|
|
|
|
|
|
static int host2guc_release_doorbell(struct intel_guc *guc,
|
|
|
|
struct i915_guc_client *client)
|
|
|
|
{
|
|
|
|
u32 data[2];
|
|
|
|
|
|
|
|
data[0] = HOST2GUC_ACTION_DEALLOCATE_DOORBELL;
|
|
|
|
data[1] = client->ctx_index;
|
|
|
|
|
|
|
|
return host2guc_action(guc, data, 2);
|
|
|
|
}
|
|
|
|
|
2015-08-18 15:34:47 -06:00
|
|
|
static int host2guc_sample_forcewake(struct intel_guc *guc,
|
|
|
|
struct i915_guc_client *client)
|
|
|
|
{
|
|
|
|
struct drm_i915_private *dev_priv = guc_to_i915(guc);
|
2015-09-25 12:46:56 -06:00
|
|
|
struct drm_device *dev = dev_priv->dev;
|
2015-08-18 15:34:47 -06:00
|
|
|
u32 data[2];
|
|
|
|
|
|
|
|
data[0] = HOST2GUC_ACTION_SAMPLE_FORCEWAKE;
|
2015-09-25 12:46:56 -06:00
|
|
|
/* WaRsDisableCoarsePowerGating:skl,bxt */
|
2015-12-16 10:18:37 -07:00
|
|
|
if (!intel_enable_rc6(dev) ||
|
|
|
|
NEEDS_WaRsDisableCoarsePowerGating(dev))
|
2015-09-25 12:46:56 -06:00
|
|
|
data[1] = 0;
|
|
|
|
else
|
|
|
|
/* bit 0 and 1 are for Render and Media domain separately */
|
|
|
|
data[1] = GUC_FORCEWAKE_RENDER | GUC_FORCEWAKE_MEDIA;
|
|
|
|
|
|
|
|
return host2guc_action(guc, data, ARRAY_SIZE(data));
|
2015-08-18 15:34:47 -06:00
|
|
|
}
|
|
|
|
|
2015-08-12 08:43:41 -06:00
|
|
|
/*
|
|
|
|
* Initialise, update, or clear doorbell data shared with the GuC
|
|
|
|
*
|
|
|
|
* These functions modify shared data and so need access to the mapped
|
|
|
|
* client object which contains the page being used for the doorbell
|
|
|
|
*/
|
|
|
|
|
|
|
|
static void guc_init_doorbell(struct intel_guc *guc,
|
|
|
|
struct i915_guc_client *client)
|
|
|
|
{
|
|
|
|
struct guc_doorbell_info *doorbell;
|
|
|
|
void *base;
|
|
|
|
|
|
|
|
base = kmap_atomic(i915_gem_object_get_page(client->client_obj, 0));
|
|
|
|
doorbell = base + client->doorbell_offset;
|
|
|
|
|
|
|
|
doorbell->db_status = 1;
|
|
|
|
doorbell->cookie = 0;
|
|
|
|
|
|
|
|
kunmap_atomic(base);
|
|
|
|
}
|
|
|
|
|
|
|
|
static int guc_ring_doorbell(struct i915_guc_client *gc)
|
|
|
|
{
|
|
|
|
struct guc_process_desc *desc;
|
|
|
|
union guc_doorbell_qw db_cmp, db_exc, db_ret;
|
|
|
|
union guc_doorbell_qw *db;
|
|
|
|
void *base;
|
|
|
|
int attempt = 2, ret = -EAGAIN;
|
|
|
|
|
|
|
|
base = kmap_atomic(i915_gem_object_get_page(gc->client_obj, 0));
|
|
|
|
desc = base + gc->proc_desc_offset;
|
|
|
|
|
|
|
|
/* Update the tail so it is visible to GuC */
|
|
|
|
desc->tail = gc->wq_tail;
|
|
|
|
|
|
|
|
/* current cookie */
|
|
|
|
db_cmp.db_status = GUC_DOORBELL_ENABLED;
|
|
|
|
db_cmp.cookie = gc->cookie;
|
|
|
|
|
|
|
|
/* cookie to be updated */
|
|
|
|
db_exc.db_status = GUC_DOORBELL_ENABLED;
|
|
|
|
db_exc.cookie = gc->cookie + 1;
|
|
|
|
if (db_exc.cookie == 0)
|
|
|
|
db_exc.cookie = 1;
|
|
|
|
|
|
|
|
/* pointer of current doorbell cacheline */
|
|
|
|
db = base + gc->doorbell_offset;
|
|
|
|
|
|
|
|
while (attempt--) {
|
|
|
|
/* lets ring the doorbell */
|
|
|
|
db_ret.value_qw = atomic64_cmpxchg((atomic64_t *)db,
|
|
|
|
db_cmp.value_qw, db_exc.value_qw);
|
|
|
|
|
|
|
|
/* if the exchange was successfully executed */
|
|
|
|
if (db_ret.value_qw == db_cmp.value_qw) {
|
|
|
|
/* db was successfully rung */
|
|
|
|
gc->cookie = db_exc.cookie;
|
|
|
|
ret = 0;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* XXX: doorbell was lost and need to acquire it again */
|
|
|
|
if (db_ret.db_status == GUC_DOORBELL_DISABLED)
|
|
|
|
break;
|
|
|
|
|
|
|
|
DRM_ERROR("Cookie mismatch. Expected %d, returned %d\n",
|
|
|
|
db_cmp.cookie, db_ret.cookie);
|
|
|
|
|
|
|
|
/* update the cookie to newly read cookie from GuC */
|
|
|
|
db_cmp.cookie = db_ret.cookie;
|
|
|
|
db_exc.cookie = db_ret.cookie + 1;
|
|
|
|
if (db_exc.cookie == 0)
|
|
|
|
db_exc.cookie = 1;
|
|
|
|
}
|
|
|
|
|
2015-12-16 12:45:55 -07:00
|
|
|
/* Finally, update the cached copy of the GuC's WQ head */
|
|
|
|
gc->wq_head = desc->head;
|
|
|
|
|
2015-08-12 08:43:41 -06:00
|
|
|
kunmap_atomic(base);
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void guc_disable_doorbell(struct intel_guc *guc,
|
|
|
|
struct i915_guc_client *client)
|
|
|
|
{
|
|
|
|
struct drm_i915_private *dev_priv = guc_to_i915(guc);
|
|
|
|
struct guc_doorbell_info *doorbell;
|
|
|
|
void *base;
|
drm/i915: Type safe register read/write
Make I915_READ and I915_WRITE more type safe by wrapping the register
offset in a struct. This should eliminate most of the fumbles we've had
with misplaced parens.
This only takes care of normal mmio registers. We could extend the idea
to other register types and define each with its own struct. That way
you wouldn't be able to accidentally pass the wrong thing to a specific
register access function.
The gpio_reg setup is probably the ugliest thing left. But I figure I'd
just leave it for now, and wait for some divine inspiration to strike
before making it nice.
As for the generated code, it's actually a bit better sometimes. Eg.
looking at i915_irq_handler(), we can see the following change:
lea 0x70024(%rdx,%rax,1),%r9d
mov $0x1,%edx
- movslq %r9d,%r9
- mov %r9,%rsi
- mov %r9,-0x58(%rbp)
- callq *0xd8(%rbx)
+ mov %r9d,%esi
+ mov %r9d,-0x48(%rbp)
callq *0xd8(%rbx)
So previously gcc thought the register offset might be signed and
decided to sign extend it, just in case. The rest appears to be
mostly just minor shuffling of instructions.
v2: i915_mmio_reg_{offset,equal,valid}() helpers added
s/_REG/_MMIO/ in the register defines
mo more switch statements left to worry about
ring_emit stuff got sorted in a prep patch
cmd parser, lrc context and w/a batch buildup also in prep patch
vgpu stuff cleaned up and moved to a prep patch
all other unrelated changes split out
v3: Rebased due to BXT DSI/BLC, MOCS, etc.
v4: Rebased due to churn, s/i915_mmio_reg_t/i915_reg_t/
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: http://patchwork.freedesktop.org/patch/msgid/1447853606-2751-1-git-send-email-ville.syrjala@linux.intel.com
2015-11-18 06:33:26 -07:00
|
|
|
i915_reg_t drbreg = GEN8_DRBREGL(client->doorbell_id);
|
2015-08-12 08:43:41 -06:00
|
|
|
int value;
|
|
|
|
|
|
|
|
base = kmap_atomic(i915_gem_object_get_page(client->client_obj, 0));
|
|
|
|
doorbell = base + client->doorbell_offset;
|
|
|
|
|
|
|
|
doorbell->db_status = 0;
|
|
|
|
|
|
|
|
kunmap_atomic(base);
|
|
|
|
|
|
|
|
I915_WRITE(drbreg, I915_READ(drbreg) & ~GEN8_DRB_VALID);
|
|
|
|
|
|
|
|
value = I915_READ(drbreg);
|
|
|
|
WARN_ON((value & GEN8_DRB_VALID) != 0);
|
|
|
|
|
|
|
|
I915_WRITE(GEN8_DRBREGU(client->doorbell_id), 0);
|
|
|
|
I915_WRITE(drbreg, 0);
|
|
|
|
|
|
|
|
/* XXX: wait for any interrupts */
|
|
|
|
/* XXX: wait for workqueue to drain */
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Select, assign and relase doorbell cachelines
|
|
|
|
*
|
|
|
|
* These functions track which doorbell cachelines are in use.
|
|
|
|
* The data they manipulate is protected by the host2guc lock.
|
|
|
|
*/
|
|
|
|
|
|
|
|
static uint32_t select_doorbell_cacheline(struct intel_guc *guc)
|
|
|
|
{
|
|
|
|
const uint32_t cacheline_size = cache_line_size();
|
|
|
|
uint32_t offset;
|
|
|
|
|
|
|
|
/* Doorbell uses a single cache line within a page */
|
|
|
|
offset = offset_in_page(guc->db_cacheline);
|
|
|
|
|
|
|
|
/* Moving to next cache line to reduce contention */
|
|
|
|
guc->db_cacheline += cacheline_size;
|
|
|
|
|
|
|
|
DRM_DEBUG_DRIVER("selected doorbell cacheline 0x%x, next 0x%x, linesize %u\n",
|
|
|
|
offset, guc->db_cacheline, cacheline_size);
|
|
|
|
|
|
|
|
return offset;
|
|
|
|
}
|
|
|
|
|
|
|
|
static uint16_t assign_doorbell(struct intel_guc *guc, uint32_t priority)
|
|
|
|
{
|
|
|
|
/*
|
|
|
|
* The bitmap is split into two halves; the first half is used for
|
|
|
|
* normal priority contexts, the second half for high-priority ones.
|
|
|
|
* Note that logically higher priorities are numerically less than
|
|
|
|
* normal ones, so the test below means "is it high-priority?"
|
|
|
|
*/
|
|
|
|
const bool hi_pri = (priority <= GUC_CTX_PRIORITY_HIGH);
|
|
|
|
const uint16_t half = GUC_MAX_DOORBELLS / 2;
|
|
|
|
const uint16_t start = hi_pri ? half : 0;
|
|
|
|
const uint16_t end = start + half;
|
|
|
|
uint16_t id;
|
|
|
|
|
|
|
|
id = find_next_zero_bit(guc->doorbell_bitmap, end, start);
|
|
|
|
if (id == end)
|
|
|
|
id = GUC_INVALID_DOORBELL_ID;
|
|
|
|
else
|
|
|
|
bitmap_set(guc->doorbell_bitmap, id, 1);
|
|
|
|
|
|
|
|
DRM_DEBUG_DRIVER("assigned %s priority doorbell id 0x%x\n",
|
|
|
|
hi_pri ? "high" : "normal", id);
|
|
|
|
|
|
|
|
return id;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void release_doorbell(struct intel_guc *guc, uint16_t id)
|
|
|
|
{
|
|
|
|
bitmap_clear(guc->doorbell_bitmap, id, 1);
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Initialise the process descriptor shared with the GuC firmware.
|
|
|
|
*/
|
|
|
|
static void guc_init_proc_desc(struct intel_guc *guc,
|
|
|
|
struct i915_guc_client *client)
|
|
|
|
{
|
|
|
|
struct guc_process_desc *desc;
|
|
|
|
void *base;
|
|
|
|
|
|
|
|
base = kmap_atomic(i915_gem_object_get_page(client->client_obj, 0));
|
|
|
|
desc = base + client->proc_desc_offset;
|
|
|
|
|
|
|
|
memset(desc, 0, sizeof(*desc));
|
|
|
|
|
|
|
|
/*
|
|
|
|
* XXX: pDoorbell and WQVBaseAddress are pointers in process address
|
|
|
|
* space for ring3 clients (set them as in mmap_ioctl) or kernel
|
|
|
|
* space for kernel clients (map on demand instead? May make debug
|
|
|
|
* easier to have it mapped).
|
|
|
|
*/
|
|
|
|
desc->wq_base_addr = 0;
|
|
|
|
desc->db_base_addr = 0;
|
|
|
|
|
|
|
|
desc->context_id = client->ctx_index;
|
|
|
|
desc->wq_size_bytes = client->wq_size;
|
|
|
|
desc->wq_status = WQ_STATUS_ACTIVE;
|
|
|
|
desc->priority = client->priority;
|
|
|
|
|
|
|
|
kunmap_atomic(base);
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Initialise/clear the context descriptor shared with the GuC firmware.
|
|
|
|
*
|
|
|
|
* This descriptor tells the GuC where (in GGTT space) to find the important
|
|
|
|
* data structures relating to this client (doorbell, process descriptor,
|
|
|
|
* write queue, etc).
|
|
|
|
*/
|
|
|
|
|
|
|
|
static void guc_init_ctx_desc(struct intel_guc *guc,
|
|
|
|
struct i915_guc_client *client)
|
|
|
|
{
|
2016-01-23 12:58:14 -07:00
|
|
|
struct drm_i915_private *dev_priv = guc_to_i915(guc);
|
|
|
|
struct intel_engine_cs *ring;
|
drm/i915: Integrate GuC-based command submission
GuC-based submission is mostly the same as execlist mode, up to
intel_logical_ring_advance_and_submit(), where the context being
dispatched would be added to the execlist queue; at this point
we submit the context to the GuC backend instead.
There are, however, a few other changes also required, notably:
1. Contexts must be pinned at GGTT addresses accessible by the GuC
i.e. NOT in the range [0..WOPCM_SIZE), so we have to add the
PIN_OFFSET_BIAS flag to the relevant GGTT-pinning calls.
2. The GuC's TLB must be invalidated after a context is pinned at
a new GGTT address.
3. GuC firmware uses the one page before Ring Context as shared data.
Therefore, whenever driver wants to get base address of LRC, we
will offset one page for it. LRC_PPHWSP_PN is defined as the page
number of LRCA.
4. In the work queue used to pass requests to the GuC, the GuC
firmware requires the ring-tail-offset to be represented as an
11-bit value, expressed in QWords. Therefore, the ringbuffer
size must be reduced to the representable range (4 pages).
v2:
Defer adding #defines until needed [Chris Wilson]
Rationalise type declarations [Chris Wilson]
v4:
Squashed kerneldoc patch into here [Daniel Vetter]
v5:
Update request->tail in code common to both GuC and execlist modes.
Add a private version of lr_context_update(), as sharing the
execlist version leads to race conditions when the CPU and
the GuC both update TAIL in the context image.
Conversion of error-captured HWS page to string must account
for offset from start of object to actual HWS (LRC_PPHWSP_PN).
Issue: VIZ-4884
Signed-off-by: Alex Dai <yu.dai@intel.com>
Signed-off-by: Dave Gordon <david.s.gordon@intel.com>
Reviewed-by: Tom O'Rourke <Tom.O'Rourke@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2015-08-12 08:43:43 -06:00
|
|
|
struct intel_context *ctx = client->owner;
|
2015-08-12 08:43:41 -06:00
|
|
|
struct guc_context_desc desc;
|
|
|
|
struct sg_table *sg;
|
drm/i915: Integrate GuC-based command submission
GuC-based submission is mostly the same as execlist mode, up to
intel_logical_ring_advance_and_submit(), where the context being
dispatched would be added to the execlist queue; at this point
we submit the context to the GuC backend instead.
There are, however, a few other changes also required, notably:
1. Contexts must be pinned at GGTT addresses accessible by the GuC
i.e. NOT in the range [0..WOPCM_SIZE), so we have to add the
PIN_OFFSET_BIAS flag to the relevant GGTT-pinning calls.
2. The GuC's TLB must be invalidated after a context is pinned at
a new GGTT address.
3. GuC firmware uses the one page before Ring Context as shared data.
Therefore, whenever driver wants to get base address of LRC, we
will offset one page for it. LRC_PPHWSP_PN is defined as the page
number of LRCA.
4. In the work queue used to pass requests to the GuC, the GuC
firmware requires the ring-tail-offset to be represented as an
11-bit value, expressed in QWords. Therefore, the ringbuffer
size must be reduced to the representable range (4 pages).
v2:
Defer adding #defines until needed [Chris Wilson]
Rationalise type declarations [Chris Wilson]
v4:
Squashed kerneldoc patch into here [Daniel Vetter]
v5:
Update request->tail in code common to both GuC and execlist modes.
Add a private version of lr_context_update(), as sharing the
execlist version leads to race conditions when the CPU and
the GuC both update TAIL in the context image.
Conversion of error-captured HWS page to string must account
for offset from start of object to actual HWS (LRC_PPHWSP_PN).
Issue: VIZ-4884
Signed-off-by: Alex Dai <yu.dai@intel.com>
Signed-off-by: Dave Gordon <david.s.gordon@intel.com>
Reviewed-by: Tom O'Rourke <Tom.O'Rourke@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2015-08-12 08:43:43 -06:00
|
|
|
int i;
|
2015-08-12 08:43:41 -06:00
|
|
|
|
|
|
|
memset(&desc, 0, sizeof(desc));
|
|
|
|
|
|
|
|
desc.attribute = GUC_CTX_DESC_ATTR_ACTIVE | GUC_CTX_DESC_ATTR_KERNEL;
|
|
|
|
desc.context_id = client->ctx_index;
|
|
|
|
desc.priority = client->priority;
|
|
|
|
desc.db_id = client->doorbell_id;
|
|
|
|
|
2016-01-23 12:58:14 -07:00
|
|
|
for_each_ring(ring, dev_priv, i) {
|
|
|
|
struct guc_execlist_context *lrc = &desc.lrc[ring->guc_id];
|
drm/i915: Integrate GuC-based command submission
GuC-based submission is mostly the same as execlist mode, up to
intel_logical_ring_advance_and_submit(), where the context being
dispatched would be added to the execlist queue; at this point
we submit the context to the GuC backend instead.
There are, however, a few other changes also required, notably:
1. Contexts must be pinned at GGTT addresses accessible by the GuC
i.e. NOT in the range [0..WOPCM_SIZE), so we have to add the
PIN_OFFSET_BIAS flag to the relevant GGTT-pinning calls.
2. The GuC's TLB must be invalidated after a context is pinned at
a new GGTT address.
3. GuC firmware uses the one page before Ring Context as shared data.
Therefore, whenever driver wants to get base address of LRC, we
will offset one page for it. LRC_PPHWSP_PN is defined as the page
number of LRCA.
4. In the work queue used to pass requests to the GuC, the GuC
firmware requires the ring-tail-offset to be represented as an
11-bit value, expressed in QWords. Therefore, the ringbuffer
size must be reduced to the representable range (4 pages).
v2:
Defer adding #defines until needed [Chris Wilson]
Rationalise type declarations [Chris Wilson]
v4:
Squashed kerneldoc patch into here [Daniel Vetter]
v5:
Update request->tail in code common to both GuC and execlist modes.
Add a private version of lr_context_update(), as sharing the
execlist version leads to race conditions when the CPU and
the GuC both update TAIL in the context image.
Conversion of error-captured HWS page to string must account
for offset from start of object to actual HWS (LRC_PPHWSP_PN).
Issue: VIZ-4884
Signed-off-by: Alex Dai <yu.dai@intel.com>
Signed-off-by: Dave Gordon <david.s.gordon@intel.com>
Reviewed-by: Tom O'Rourke <Tom.O'Rourke@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2015-08-12 08:43:43 -06:00
|
|
|
struct drm_i915_gem_object *obj;
|
|
|
|
uint64_t ctx_desc;
|
|
|
|
|
|
|
|
/* TODO: We have a design issue to be solved here. Only when we
|
|
|
|
* receive the first batch, we know which engine is used by the
|
|
|
|
* user. But here GuC expects the lrc and ring to be pinned. It
|
|
|
|
* is not an issue for default context, which is the only one
|
|
|
|
* for now who owns a GuC client. But for future owner of GuC
|
|
|
|
* client, need to make sure lrc is pinned prior to enter here.
|
|
|
|
*/
|
|
|
|
obj = ctx->engine[i].state;
|
|
|
|
if (!obj)
|
|
|
|
break; /* XXX: continue? */
|
|
|
|
|
|
|
|
ctx_desc = intel_lr_context_descriptor(ctx, ring);
|
|
|
|
lrc->context_desc = (u32)ctx_desc;
|
|
|
|
|
|
|
|
/* The state page is after PPHWSP */
|
|
|
|
lrc->ring_lcra = i915_gem_obj_ggtt_offset(obj) +
|
|
|
|
LRC_STATE_PN * PAGE_SIZE;
|
|
|
|
lrc->context_id = (client->ctx_index << GUC_ELC_CTXID_OFFSET) |
|
2016-01-23 12:58:14 -07:00
|
|
|
(ring->guc_id << GUC_ELC_ENGINE_OFFSET);
|
drm/i915: Integrate GuC-based command submission
GuC-based submission is mostly the same as execlist mode, up to
intel_logical_ring_advance_and_submit(), where the context being
dispatched would be added to the execlist queue; at this point
we submit the context to the GuC backend instead.
There are, however, a few other changes also required, notably:
1. Contexts must be pinned at GGTT addresses accessible by the GuC
i.e. NOT in the range [0..WOPCM_SIZE), so we have to add the
PIN_OFFSET_BIAS flag to the relevant GGTT-pinning calls.
2. The GuC's TLB must be invalidated after a context is pinned at
a new GGTT address.
3. GuC firmware uses the one page before Ring Context as shared data.
Therefore, whenever driver wants to get base address of LRC, we
will offset one page for it. LRC_PPHWSP_PN is defined as the page
number of LRCA.
4. In the work queue used to pass requests to the GuC, the GuC
firmware requires the ring-tail-offset to be represented as an
11-bit value, expressed in QWords. Therefore, the ringbuffer
size must be reduced to the representable range (4 pages).
v2:
Defer adding #defines until needed [Chris Wilson]
Rationalise type declarations [Chris Wilson]
v4:
Squashed kerneldoc patch into here [Daniel Vetter]
v5:
Update request->tail in code common to both GuC and execlist modes.
Add a private version of lr_context_update(), as sharing the
execlist version leads to race conditions when the CPU and
the GuC both update TAIL in the context image.
Conversion of error-captured HWS page to string must account
for offset from start of object to actual HWS (LRC_PPHWSP_PN).
Issue: VIZ-4884
Signed-off-by: Alex Dai <yu.dai@intel.com>
Signed-off-by: Dave Gordon <david.s.gordon@intel.com>
Reviewed-by: Tom O'Rourke <Tom.O'Rourke@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2015-08-12 08:43:43 -06:00
|
|
|
|
2016-01-23 12:58:14 -07:00
|
|
|
obj = ctx->engine[i].ringbuf->obj;
|
drm/i915: Integrate GuC-based command submission
GuC-based submission is mostly the same as execlist mode, up to
intel_logical_ring_advance_and_submit(), where the context being
dispatched would be added to the execlist queue; at this point
we submit the context to the GuC backend instead.
There are, however, a few other changes also required, notably:
1. Contexts must be pinned at GGTT addresses accessible by the GuC
i.e. NOT in the range [0..WOPCM_SIZE), so we have to add the
PIN_OFFSET_BIAS flag to the relevant GGTT-pinning calls.
2. The GuC's TLB must be invalidated after a context is pinned at
a new GGTT address.
3. GuC firmware uses the one page before Ring Context as shared data.
Therefore, whenever driver wants to get base address of LRC, we
will offset one page for it. LRC_PPHWSP_PN is defined as the page
number of LRCA.
4. In the work queue used to pass requests to the GuC, the GuC
firmware requires the ring-tail-offset to be represented as an
11-bit value, expressed in QWords. Therefore, the ringbuffer
size must be reduced to the representable range (4 pages).
v2:
Defer adding #defines until needed [Chris Wilson]
Rationalise type declarations [Chris Wilson]
v4:
Squashed kerneldoc patch into here [Daniel Vetter]
v5:
Update request->tail in code common to both GuC and execlist modes.
Add a private version of lr_context_update(), as sharing the
execlist version leads to race conditions when the CPU and
the GuC both update TAIL in the context image.
Conversion of error-captured HWS page to string must account
for offset from start of object to actual HWS (LRC_PPHWSP_PN).
Issue: VIZ-4884
Signed-off-by: Alex Dai <yu.dai@intel.com>
Signed-off-by: Dave Gordon <david.s.gordon@intel.com>
Reviewed-by: Tom O'Rourke <Tom.O'Rourke@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2015-08-12 08:43:43 -06:00
|
|
|
|
|
|
|
lrc->ring_begin = i915_gem_obj_ggtt_offset(obj);
|
|
|
|
lrc->ring_end = lrc->ring_begin + obj->base.size - 1;
|
|
|
|
lrc->ring_next_free_location = lrc->ring_begin;
|
|
|
|
lrc->ring_current_tail_pointer_value = 0;
|
|
|
|
|
2016-01-23 12:58:14 -07:00
|
|
|
desc.engines_used |= (1 << ring->guc_id);
|
drm/i915: Integrate GuC-based command submission
GuC-based submission is mostly the same as execlist mode, up to
intel_logical_ring_advance_and_submit(), where the context being
dispatched would be added to the execlist queue; at this point
we submit the context to the GuC backend instead.
There are, however, a few other changes also required, notably:
1. Contexts must be pinned at GGTT addresses accessible by the GuC
i.e. NOT in the range [0..WOPCM_SIZE), so we have to add the
PIN_OFFSET_BIAS flag to the relevant GGTT-pinning calls.
2. The GuC's TLB must be invalidated after a context is pinned at
a new GGTT address.
3. GuC firmware uses the one page before Ring Context as shared data.
Therefore, whenever driver wants to get base address of LRC, we
will offset one page for it. LRC_PPHWSP_PN is defined as the page
number of LRCA.
4. In the work queue used to pass requests to the GuC, the GuC
firmware requires the ring-tail-offset to be represented as an
11-bit value, expressed in QWords. Therefore, the ringbuffer
size must be reduced to the representable range (4 pages).
v2:
Defer adding #defines until needed [Chris Wilson]
Rationalise type declarations [Chris Wilson]
v4:
Squashed kerneldoc patch into here [Daniel Vetter]
v5:
Update request->tail in code common to both GuC and execlist modes.
Add a private version of lr_context_update(), as sharing the
execlist version leads to race conditions when the CPU and
the GuC both update TAIL in the context image.
Conversion of error-captured HWS page to string must account
for offset from start of object to actual HWS (LRC_PPHWSP_PN).
Issue: VIZ-4884
Signed-off-by: Alex Dai <yu.dai@intel.com>
Signed-off-by: Dave Gordon <david.s.gordon@intel.com>
Reviewed-by: Tom O'Rourke <Tom.O'Rourke@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2015-08-12 08:43:43 -06:00
|
|
|
}
|
|
|
|
|
|
|
|
WARN_ON(desc.engines_used == 0);
|
|
|
|
|
2015-08-12 08:43:41 -06:00
|
|
|
/*
|
|
|
|
* The CPU address is only needed at certain points, so kmap_atomic on
|
|
|
|
* demand instead of storing it in the ctx descriptor.
|
|
|
|
* XXX: May make debug easier to have it mapped
|
|
|
|
*/
|
|
|
|
desc.db_trigger_cpu = 0;
|
|
|
|
desc.db_trigger_uk = client->doorbell_offset +
|
|
|
|
i915_gem_obj_ggtt_offset(client->client_obj);
|
|
|
|
desc.db_trigger_phy = client->doorbell_offset +
|
|
|
|
sg_dma_address(client->client_obj->pages->sgl);
|
|
|
|
|
|
|
|
desc.process_desc = client->proc_desc_offset +
|
|
|
|
i915_gem_obj_ggtt_offset(client->client_obj);
|
|
|
|
|
|
|
|
desc.wq_addr = client->wq_offset +
|
|
|
|
i915_gem_obj_ggtt_offset(client->client_obj);
|
|
|
|
|
|
|
|
desc.wq_size = client->wq_size;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* XXX: Take LRCs from an existing intel_context if this is not an
|
|
|
|
* IsKMDCreatedContext client
|
|
|
|
*/
|
|
|
|
desc.desc_private = (uintptr_t)client;
|
|
|
|
|
|
|
|
/* Pool context is pinned already */
|
|
|
|
sg = guc->ctx_pool_obj->pages;
|
|
|
|
sg_pcopy_from_buffer(sg->sgl, sg->nents, &desc, sizeof(desc),
|
|
|
|
sizeof(desc) * client->ctx_index);
|
|
|
|
}
|
|
|
|
|
|
|
|
static void guc_fini_ctx_desc(struct intel_guc *guc,
|
|
|
|
struct i915_guc_client *client)
|
|
|
|
{
|
|
|
|
struct guc_context_desc desc;
|
|
|
|
struct sg_table *sg;
|
|
|
|
|
|
|
|
memset(&desc, 0, sizeof(desc));
|
|
|
|
|
|
|
|
sg = guc->ctx_pool_obj->pages;
|
|
|
|
sg_pcopy_from_buffer(sg->sgl, sg->nents, &desc, sizeof(desc),
|
|
|
|
sizeof(desc) * client->ctx_index);
|
|
|
|
}
|
|
|
|
|
2015-12-16 12:45:55 -07:00
|
|
|
int i915_guc_wq_check_space(struct i915_guc_client *gc)
|
2015-08-12 08:43:41 -06:00
|
|
|
{
|
|
|
|
struct guc_process_desc *desc;
|
|
|
|
void *base;
|
|
|
|
u32 size = sizeof(struct guc_wq_item);
|
2015-12-02 17:56:29 -07:00
|
|
|
int ret = -ETIMEDOUT, timeout_counter = 200;
|
2015-08-12 08:43:41 -06:00
|
|
|
|
2015-12-16 12:45:55 -07:00
|
|
|
if (!gc)
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
/* Quickly return if wq space is available since last time we cache the
|
|
|
|
* head position. */
|
|
|
|
if (CIRC_SPACE(gc->wq_tail, gc->wq_head, gc->wq_size) >= size)
|
|
|
|
return 0;
|
|
|
|
|
2015-08-12 08:43:41 -06:00
|
|
|
base = kmap_atomic(i915_gem_object_get_page(gc->client_obj, 0));
|
|
|
|
desc = base + gc->proc_desc_offset;
|
|
|
|
|
|
|
|
while (timeout_counter-- > 0) {
|
2015-12-16 12:45:55 -07:00
|
|
|
gc->wq_head = desc->head;
|
2015-08-12 08:43:41 -06:00
|
|
|
|
2015-12-16 12:45:55 -07:00
|
|
|
if (CIRC_SPACE(gc->wq_tail, gc->wq_head, gc->wq_size) >= size) {
|
2015-12-02 17:56:29 -07:00
|
|
|
ret = 0;
|
2015-12-16 12:45:55 -07:00
|
|
|
break;
|
2015-08-12 08:43:41 -06:00
|
|
|
}
|
2015-12-02 17:56:29 -07:00
|
|
|
|
|
|
|
if (timeout_counter)
|
|
|
|
usleep_range(1000, 2000);
|
2015-08-12 08:43:41 -06:00
|
|
|
};
|
|
|
|
|
|
|
|
kunmap_atomic(base);
|
|
|
|
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int guc_add_workqueue_item(struct i915_guc_client *gc,
|
|
|
|
struct drm_i915_gem_request *rq)
|
|
|
|
{
|
|
|
|
struct guc_wq_item *wqi;
|
|
|
|
void *base;
|
2015-12-16 12:45:55 -07:00
|
|
|
u32 tail, wq_len, wq_off, space;
|
|
|
|
|
|
|
|
space = CIRC_SPACE(gc->wq_tail, gc->wq_head, gc->wq_size);
|
|
|
|
if (WARN_ON(space < sizeof(struct guc_wq_item)))
|
|
|
|
return -ENOSPC; /* shouldn't happen */
|
2015-08-12 08:43:41 -06:00
|
|
|
|
2015-12-16 12:45:55 -07:00
|
|
|
/* postincrement WQ tail for next time */
|
|
|
|
wq_off = gc->wq_tail;
|
|
|
|
gc->wq_tail += sizeof(struct guc_wq_item);
|
|
|
|
gc->wq_tail &= gc->wq_size - 1;
|
2015-08-12 08:43:41 -06:00
|
|
|
|
|
|
|
/* For now workqueue item is 4 DWs; workqueue buffer is 2 pages. So we
|
|
|
|
* should not have the case where structure wqi is across page, neither
|
|
|
|
* wrapped to the beginning. This simplifies the implementation below.
|
|
|
|
*
|
|
|
|
* XXX: if not the case, we need save data to a temp wqi and copy it to
|
|
|
|
* workqueue buffer dw by dw.
|
|
|
|
*/
|
|
|
|
WARN_ON(sizeof(struct guc_wq_item) != 16);
|
|
|
|
WARN_ON(wq_off & 3);
|
|
|
|
|
|
|
|
/* wq starts from the page after doorbell / process_desc */
|
|
|
|
base = kmap_atomic(i915_gem_object_get_page(gc->client_obj,
|
|
|
|
(wq_off + GUC_DB_SIZE) >> PAGE_SHIFT));
|
|
|
|
wq_off &= PAGE_SIZE - 1;
|
|
|
|
wqi = (struct guc_wq_item *)((char *)base + wq_off);
|
|
|
|
|
|
|
|
/* len does not include the header */
|
|
|
|
wq_len = sizeof(struct guc_wq_item) / sizeof(u32) - 1;
|
|
|
|
wqi->header = WQ_TYPE_INORDER |
|
|
|
|
(wq_len << WQ_LEN_SHIFT) |
|
2016-01-23 12:58:14 -07:00
|
|
|
(rq->ring->guc_id << WQ_TARGET_SHIFT) |
|
2015-08-12 08:43:41 -06:00
|
|
|
WQ_NO_WCFLUSH_WAIT;
|
|
|
|
|
|
|
|
/* The GuC wants only the low-order word of the context descriptor */
|
|
|
|
wqi->context_desc = (u32)intel_lr_context_descriptor(rq->ctx, rq->ring);
|
|
|
|
|
|
|
|
/* The GuC firmware wants the tail index in QWords, not bytes */
|
|
|
|
tail = rq->ringbuf->tail >> 3;
|
|
|
|
wqi->ring_tail = tail << WQ_RING_TAIL_SHIFT;
|
|
|
|
wqi->fence_id = 0; /*XXX: what fence to be here */
|
|
|
|
|
|
|
|
kunmap_atomic(base);
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
|
|
|
* i915_guc_submit() - Submit commands through GuC
|
|
|
|
* @client: the guc client where commands will go through
|
2015-10-19 17:10:54 -06:00
|
|
|
* @rq: request associated with the commands
|
2015-08-12 08:43:41 -06:00
|
|
|
*
|
|
|
|
* Return: 0 if succeed
|
|
|
|
*/
|
|
|
|
int i915_guc_submit(struct i915_guc_client *client,
|
|
|
|
struct drm_i915_gem_request *rq)
|
|
|
|
{
|
|
|
|
struct intel_guc *guc = client->guc;
|
2016-01-23 12:58:14 -07:00
|
|
|
unsigned int engine_id = rq->ring->guc_id;
|
2015-08-12 08:43:41 -06:00
|
|
|
int q_ret, b_ret;
|
|
|
|
|
|
|
|
q_ret = guc_add_workqueue_item(client, rq);
|
|
|
|
if (q_ret == 0)
|
|
|
|
b_ret = guc_ring_doorbell(client);
|
|
|
|
|
2016-01-23 12:58:14 -07:00
|
|
|
client->submissions[engine_id] += 1;
|
2015-08-12 08:43:41 -06:00
|
|
|
if (q_ret) {
|
|
|
|
client->q_fail += 1;
|
|
|
|
client->retcode = q_ret;
|
|
|
|
} else if (b_ret) {
|
|
|
|
client->b_fail += 1;
|
|
|
|
client->retcode = q_ret = b_ret;
|
|
|
|
} else {
|
|
|
|
client->retcode = 0;
|
|
|
|
}
|
2016-01-23 12:58:14 -07:00
|
|
|
guc->submissions[engine_id] += 1;
|
|
|
|
guc->last_seqno[engine_id] = rq->seqno;
|
2015-08-12 08:43:41 -06:00
|
|
|
|
|
|
|
return q_ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Everything below here is concerned with setup & teardown, and is
|
|
|
|
* therefore not part of the somewhat time-critical batch-submission
|
|
|
|
* path of i915_guc_submit() above.
|
|
|
|
*/
|
|
|
|
|
2015-08-12 08:43:39 -06:00
|
|
|
/**
|
|
|
|
* gem_allocate_guc_obj() - Allocate gem object for GuC usage
|
|
|
|
* @dev: drm device
|
|
|
|
* @size: size of object
|
|
|
|
*
|
|
|
|
* This is a wrapper to create a gem obj. In order to use it inside GuC, the
|
|
|
|
* object needs to be pinned lifetime. Also we must pin it to gtt space other
|
|
|
|
* than [0, GUC_WOPCM_TOP) because this range is reserved inside GuC.
|
|
|
|
*
|
|
|
|
* Return: A drm_i915_gem_object if successful, otherwise NULL.
|
|
|
|
*/
|
|
|
|
static struct drm_i915_gem_object *gem_allocate_guc_obj(struct drm_device *dev,
|
|
|
|
u32 size)
|
|
|
|
{
|
|
|
|
struct drm_i915_private *dev_priv = dev->dev_private;
|
|
|
|
struct drm_i915_gem_object *obj;
|
|
|
|
|
|
|
|
obj = i915_gem_alloc_object(dev, size);
|
|
|
|
if (!obj)
|
|
|
|
return NULL;
|
|
|
|
|
|
|
|
if (i915_gem_object_get_pages(obj)) {
|
|
|
|
drm_gem_object_unreference(&obj->base);
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (i915_gem_obj_ggtt_pin(obj, PAGE_SIZE,
|
|
|
|
PIN_OFFSET_BIAS | GUC_WOPCM_TOP)) {
|
|
|
|
drm_gem_object_unreference(&obj->base);
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Invalidate GuC TLB to let GuC take the latest updates to GTT. */
|
|
|
|
I915_WRITE(GEN8_GTCR, GEN8_GTCR_INVALIDATE);
|
|
|
|
|
|
|
|
return obj;
|
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
|
|
|
* gem_release_guc_obj() - Release gem object allocated for GuC usage
|
|
|
|
* @obj: gem obj to be released
|
2015-11-25 07:21:30 -07:00
|
|
|
*/
|
2015-08-12 08:43:39 -06:00
|
|
|
static void gem_release_guc_obj(struct drm_i915_gem_object *obj)
|
|
|
|
{
|
|
|
|
if (!obj)
|
|
|
|
return;
|
|
|
|
|
|
|
|
if (i915_gem_obj_is_pinned(obj))
|
|
|
|
i915_gem_object_ggtt_unpin(obj);
|
|
|
|
|
|
|
|
drm_gem_object_unreference(&obj->base);
|
|
|
|
}
|
|
|
|
|
2015-08-12 08:43:41 -06:00
|
|
|
static void guc_client_free(struct drm_device *dev,
|
|
|
|
struct i915_guc_client *client)
|
|
|
|
{
|
|
|
|
struct drm_i915_private *dev_priv = dev->dev_private;
|
|
|
|
struct intel_guc *guc = &dev_priv->guc;
|
|
|
|
|
|
|
|
if (!client)
|
|
|
|
return;
|
|
|
|
|
|
|
|
if (client->doorbell_id != GUC_INVALID_DOORBELL_ID) {
|
|
|
|
/*
|
|
|
|
* First disable the doorbell, then tell the GuC we've
|
|
|
|
* finished with it, finally deallocate it in our bitmap
|
|
|
|
*/
|
|
|
|
guc_disable_doorbell(guc, client);
|
|
|
|
host2guc_release_doorbell(guc, client);
|
|
|
|
release_doorbell(guc, client->doorbell_id);
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* XXX: wait for any outstanding submissions before freeing memory.
|
|
|
|
* Be sure to drop any locks
|
|
|
|
*/
|
|
|
|
|
|
|
|
gem_release_guc_obj(client->client_obj);
|
|
|
|
|
|
|
|
if (client->ctx_index != GUC_INVALID_CTX_ID) {
|
|
|
|
guc_fini_ctx_desc(guc, client);
|
|
|
|
ida_simple_remove(&guc->ctx_ids, client->ctx_index);
|
|
|
|
}
|
|
|
|
|
|
|
|
kfree(client);
|
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
|
|
|
* guc_client_alloc() - Allocate an i915_guc_client
|
|
|
|
* @dev: drm device
|
|
|
|
* @priority: four levels priority _CRITICAL, _HIGH, _NORMAL and _LOW
|
|
|
|
* The kernel client to replace ExecList submission is created with
|
|
|
|
* NORMAL priority. Priority of a client for scheduler can be HIGH,
|
|
|
|
* while a preemption context can use CRITICAL.
|
2015-10-19 17:10:54 -06:00
|
|
|
* @ctx: the context that owns the client (we use the default render
|
|
|
|
* context)
|
2015-08-12 08:43:41 -06:00
|
|
|
*
|
|
|
|
* Return: An i915_guc_client object if success.
|
|
|
|
*/
|
|
|
|
static struct i915_guc_client *guc_client_alloc(struct drm_device *dev,
|
drm/i915: Integrate GuC-based command submission
GuC-based submission is mostly the same as execlist mode, up to
intel_logical_ring_advance_and_submit(), where the context being
dispatched would be added to the execlist queue; at this point
we submit the context to the GuC backend instead.
There are, however, a few other changes also required, notably:
1. Contexts must be pinned at GGTT addresses accessible by the GuC
i.e. NOT in the range [0..WOPCM_SIZE), so we have to add the
PIN_OFFSET_BIAS flag to the relevant GGTT-pinning calls.
2. The GuC's TLB must be invalidated after a context is pinned at
a new GGTT address.
3. GuC firmware uses the one page before Ring Context as shared data.
Therefore, whenever driver wants to get base address of LRC, we
will offset one page for it. LRC_PPHWSP_PN is defined as the page
number of LRCA.
4. In the work queue used to pass requests to the GuC, the GuC
firmware requires the ring-tail-offset to be represented as an
11-bit value, expressed in QWords. Therefore, the ringbuffer
size must be reduced to the representable range (4 pages).
v2:
Defer adding #defines until needed [Chris Wilson]
Rationalise type declarations [Chris Wilson]
v4:
Squashed kerneldoc patch into here [Daniel Vetter]
v5:
Update request->tail in code common to both GuC and execlist modes.
Add a private version of lr_context_update(), as sharing the
execlist version leads to race conditions when the CPU and
the GuC both update TAIL in the context image.
Conversion of error-captured HWS page to string must account
for offset from start of object to actual HWS (LRC_PPHWSP_PN).
Issue: VIZ-4884
Signed-off-by: Alex Dai <yu.dai@intel.com>
Signed-off-by: Dave Gordon <david.s.gordon@intel.com>
Reviewed-by: Tom O'Rourke <Tom.O'Rourke@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2015-08-12 08:43:43 -06:00
|
|
|
uint32_t priority,
|
|
|
|
struct intel_context *ctx)
|
2015-08-12 08:43:41 -06:00
|
|
|
{
|
|
|
|
struct i915_guc_client *client;
|
|
|
|
struct drm_i915_private *dev_priv = dev->dev_private;
|
|
|
|
struct intel_guc *guc = &dev_priv->guc;
|
|
|
|
struct drm_i915_gem_object *obj;
|
|
|
|
|
|
|
|
client = kzalloc(sizeof(*client), GFP_KERNEL);
|
|
|
|
if (!client)
|
|
|
|
return NULL;
|
|
|
|
|
|
|
|
client->doorbell_id = GUC_INVALID_DOORBELL_ID;
|
|
|
|
client->priority = priority;
|
drm/i915: Integrate GuC-based command submission
GuC-based submission is mostly the same as execlist mode, up to
intel_logical_ring_advance_and_submit(), where the context being
dispatched would be added to the execlist queue; at this point
we submit the context to the GuC backend instead.
There are, however, a few other changes also required, notably:
1. Contexts must be pinned at GGTT addresses accessible by the GuC
i.e. NOT in the range [0..WOPCM_SIZE), so we have to add the
PIN_OFFSET_BIAS flag to the relevant GGTT-pinning calls.
2. The GuC's TLB must be invalidated after a context is pinned at
a new GGTT address.
3. GuC firmware uses the one page before Ring Context as shared data.
Therefore, whenever driver wants to get base address of LRC, we
will offset one page for it. LRC_PPHWSP_PN is defined as the page
number of LRCA.
4. In the work queue used to pass requests to the GuC, the GuC
firmware requires the ring-tail-offset to be represented as an
11-bit value, expressed in QWords. Therefore, the ringbuffer
size must be reduced to the representable range (4 pages).
v2:
Defer adding #defines until needed [Chris Wilson]
Rationalise type declarations [Chris Wilson]
v4:
Squashed kerneldoc patch into here [Daniel Vetter]
v5:
Update request->tail in code common to both GuC and execlist modes.
Add a private version of lr_context_update(), as sharing the
execlist version leads to race conditions when the CPU and
the GuC both update TAIL in the context image.
Conversion of error-captured HWS page to string must account
for offset from start of object to actual HWS (LRC_PPHWSP_PN).
Issue: VIZ-4884
Signed-off-by: Alex Dai <yu.dai@intel.com>
Signed-off-by: Dave Gordon <david.s.gordon@intel.com>
Reviewed-by: Tom O'Rourke <Tom.O'Rourke@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2015-08-12 08:43:43 -06:00
|
|
|
client->owner = ctx;
|
2015-08-12 08:43:41 -06:00
|
|
|
client->guc = guc;
|
|
|
|
|
|
|
|
client->ctx_index = (uint32_t)ida_simple_get(&guc->ctx_ids, 0,
|
|
|
|
GUC_MAX_GPU_CONTEXTS, GFP_KERNEL);
|
|
|
|
if (client->ctx_index >= GUC_MAX_GPU_CONTEXTS) {
|
|
|
|
client->ctx_index = GUC_INVALID_CTX_ID;
|
|
|
|
goto err;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* The first page is doorbell/proc_desc. Two followed pages are wq. */
|
|
|
|
obj = gem_allocate_guc_obj(dev, GUC_DB_SIZE + GUC_WQ_SIZE);
|
|
|
|
if (!obj)
|
|
|
|
goto err;
|
|
|
|
|
|
|
|
client->client_obj = obj;
|
|
|
|
client->wq_offset = GUC_DB_SIZE;
|
|
|
|
client->wq_size = GUC_WQ_SIZE;
|
|
|
|
|
|
|
|
client->doorbell_offset = select_doorbell_cacheline(guc);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Since the doorbell only requires a single cacheline, we can save
|
|
|
|
* space by putting the application process descriptor in the same
|
|
|
|
* page. Use the half of the page that doesn't include the doorbell.
|
|
|
|
*/
|
|
|
|
if (client->doorbell_offset >= (GUC_DB_SIZE / 2))
|
|
|
|
client->proc_desc_offset = 0;
|
|
|
|
else
|
|
|
|
client->proc_desc_offset = (GUC_DB_SIZE / 2);
|
|
|
|
|
|
|
|
client->doorbell_id = assign_doorbell(guc, client->priority);
|
|
|
|
if (client->doorbell_id == GUC_INVALID_DOORBELL_ID)
|
|
|
|
/* XXX: evict a doorbell instead */
|
|
|
|
goto err;
|
|
|
|
|
|
|
|
guc_init_proc_desc(guc, client);
|
|
|
|
guc_init_ctx_desc(guc, client);
|
|
|
|
guc_init_doorbell(guc, client);
|
|
|
|
|
|
|
|
/* XXX: Any cache flushes needed? General domain mgmt calls? */
|
|
|
|
|
|
|
|
if (host2guc_allocate_doorbell(guc, client))
|
|
|
|
goto err;
|
|
|
|
|
|
|
|
DRM_DEBUG_DRIVER("new priority %u client %p: ctx_index %u db_id %u\n",
|
|
|
|
priority, client, client->ctx_index, client->doorbell_id);
|
|
|
|
|
|
|
|
return client;
|
|
|
|
|
|
|
|
err:
|
|
|
|
DRM_ERROR("FAILED to create priority %u GuC client!\n", priority);
|
|
|
|
|
|
|
|
guc_client_free(dev, client);
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
|
2015-08-12 08:43:40 -06:00
|
|
|
static void guc_create_log(struct intel_guc *guc)
|
|
|
|
{
|
|
|
|
struct drm_i915_private *dev_priv = guc_to_i915(guc);
|
|
|
|
struct drm_i915_gem_object *obj;
|
|
|
|
unsigned long offset;
|
|
|
|
uint32_t size, flags;
|
|
|
|
|
|
|
|
if (i915.guc_log_level < GUC_LOG_VERBOSITY_MIN)
|
|
|
|
return;
|
|
|
|
|
|
|
|
if (i915.guc_log_level > GUC_LOG_VERBOSITY_MAX)
|
|
|
|
i915.guc_log_level = GUC_LOG_VERBOSITY_MAX;
|
|
|
|
|
|
|
|
/* The first page is to save log buffer state. Allocate one
|
|
|
|
* extra page for others in case for overlap */
|
|
|
|
size = (1 + GUC_LOG_DPC_PAGES + 1 +
|
|
|
|
GUC_LOG_ISR_PAGES + 1 +
|
|
|
|
GUC_LOG_CRASH_PAGES + 1) << PAGE_SHIFT;
|
|
|
|
|
|
|
|
obj = guc->log_obj;
|
|
|
|
if (!obj) {
|
|
|
|
obj = gem_allocate_guc_obj(dev_priv->dev, size);
|
|
|
|
if (!obj) {
|
|
|
|
/* logging will be off */
|
|
|
|
i915.guc_log_level = -1;
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
|
|
|
guc->log_obj = obj;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* each allocated unit is a page */
|
|
|
|
flags = GUC_LOG_VALID | GUC_LOG_NOTIFY_ON_HALF_FULL |
|
|
|
|
(GUC_LOG_DPC_PAGES << GUC_LOG_DPC_SHIFT) |
|
|
|
|
(GUC_LOG_ISR_PAGES << GUC_LOG_ISR_SHIFT) |
|
|
|
|
(GUC_LOG_CRASH_PAGES << GUC_LOG_CRASH_SHIFT);
|
|
|
|
|
|
|
|
offset = i915_gem_obj_ggtt_offset(obj) >> PAGE_SHIFT; /* in pages */
|
|
|
|
guc->log_flags = (offset << GUC_LOG_BUF_ADDR_SHIFT) | flags;
|
|
|
|
}
|
|
|
|
|
2015-12-18 13:00:10 -07:00
|
|
|
static void init_guc_policies(struct guc_policies *policies)
|
|
|
|
{
|
|
|
|
struct guc_policy *policy;
|
|
|
|
u32 p, i;
|
|
|
|
|
|
|
|
policies->dpc_promote_time = 500000;
|
|
|
|
policies->max_num_work_items = POLICY_MAX_NUM_WI;
|
|
|
|
|
|
|
|
for (p = 0; p < GUC_CTX_PRIORITY_NUM; p++) {
|
2016-01-23 12:58:14 -07:00
|
|
|
for (i = GUC_RENDER_ENGINE; i < GUC_MAX_ENGINES_NUM; i++) {
|
2015-12-18 13:00:10 -07:00
|
|
|
policy = &policies->policy[p][i];
|
|
|
|
|
|
|
|
policy->execution_quantum = 1000000;
|
|
|
|
policy->preemption_time = 500000;
|
|
|
|
policy->fault_time = 250000;
|
|
|
|
policy->policy_flags = 0;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
policies->is_valid = 1;
|
|
|
|
}
|
|
|
|
|
2015-12-18 13:00:09 -07:00
|
|
|
static void guc_create_ads(struct intel_guc *guc)
|
|
|
|
{
|
|
|
|
struct drm_i915_private *dev_priv = guc_to_i915(guc);
|
|
|
|
struct drm_i915_gem_object *obj;
|
|
|
|
struct guc_ads *ads;
|
2015-12-18 13:00:10 -07:00
|
|
|
struct guc_policies *policies;
|
2015-12-18 13:00:11 -07:00
|
|
|
struct guc_mmio_reg_state *reg_state;
|
2015-12-18 13:00:09 -07:00
|
|
|
struct intel_engine_cs *ring;
|
|
|
|
struct page *page;
|
|
|
|
u32 size, i;
|
|
|
|
|
|
|
|
/* The ads obj includes the struct itself and buffers passed to GuC */
|
2015-12-18 13:00:11 -07:00
|
|
|
size = sizeof(struct guc_ads) + sizeof(struct guc_policies) +
|
|
|
|
sizeof(struct guc_mmio_reg_state) +
|
|
|
|
GUC_S3_SAVE_SPACE_PAGES * PAGE_SIZE;
|
2015-12-18 13:00:09 -07:00
|
|
|
|
|
|
|
obj = guc->ads_obj;
|
|
|
|
if (!obj) {
|
|
|
|
obj = gem_allocate_guc_obj(dev_priv->dev, PAGE_ALIGN(size));
|
|
|
|
if (!obj)
|
|
|
|
return;
|
|
|
|
|
|
|
|
guc->ads_obj = obj;
|
|
|
|
}
|
|
|
|
|
|
|
|
page = i915_gem_object_get_page(obj, 0);
|
|
|
|
ads = kmap(page);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* The GuC requires a "Golden Context" when it reinitialises
|
|
|
|
* engines after a reset. Here we use the Render ring default
|
|
|
|
* context, which must already exist and be pinned in the GGTT,
|
|
|
|
* so its address won't change after we've told the GuC where
|
|
|
|
* to find it.
|
|
|
|
*/
|
|
|
|
ring = &dev_priv->ring[RCS];
|
|
|
|
ads->golden_context_lrca = ring->status_page.gfx_addr;
|
|
|
|
|
|
|
|
for_each_ring(ring, dev_priv, i)
|
2016-01-23 12:58:14 -07:00
|
|
|
ads->eng_state_size[ring->guc_id] = intel_lr_context_size(ring);
|
2015-12-18 13:00:09 -07:00
|
|
|
|
2015-12-18 13:00:10 -07:00
|
|
|
/* GuC scheduling policies */
|
|
|
|
policies = (void *)ads + sizeof(struct guc_ads);
|
|
|
|
init_guc_policies(policies);
|
|
|
|
|
|
|
|
ads->scheduler_policies = i915_gem_obj_ggtt_offset(obj) +
|
|
|
|
sizeof(struct guc_ads);
|
|
|
|
|
2015-12-18 13:00:11 -07:00
|
|
|
/* MMIO reg state */
|
|
|
|
reg_state = (void *)policies + sizeof(struct guc_policies);
|
|
|
|
|
2016-01-23 12:58:14 -07:00
|
|
|
for_each_ring(ring, dev_priv, i) {
|
|
|
|
reg_state->mmio_white_list[ring->guc_id].mmio_start =
|
|
|
|
ring->mmio_base + GUC_MMIO_WHITE_LIST_START;
|
2015-12-18 13:00:11 -07:00
|
|
|
|
|
|
|
/* Nothing to be saved or restored for now. */
|
2016-01-23 12:58:14 -07:00
|
|
|
reg_state->mmio_white_list[ring->guc_id].count = 0;
|
2015-12-18 13:00:11 -07:00
|
|
|
}
|
|
|
|
|
|
|
|
ads->reg_state_addr = ads->scheduler_policies +
|
|
|
|
sizeof(struct guc_policies);
|
|
|
|
|
|
|
|
ads->reg_state_buffer = ads->reg_state_addr +
|
|
|
|
sizeof(struct guc_mmio_reg_state);
|
|
|
|
|
2015-12-18 13:00:09 -07:00
|
|
|
kunmap(page);
|
|
|
|
}
|
|
|
|
|
2015-08-12 08:43:39 -06:00
|
|
|
/*
|
|
|
|
* Set up the memory resources to be shared with the GuC. At this point,
|
|
|
|
* we require just one object that can be mapped through the GGTT.
|
|
|
|
*/
|
|
|
|
int i915_guc_submission_init(struct drm_device *dev)
|
|
|
|
{
|
|
|
|
struct drm_i915_private *dev_priv = dev->dev_private;
|
|
|
|
const size_t ctxsize = sizeof(struct guc_context_desc);
|
|
|
|
const size_t poolsize = GUC_MAX_GPU_CONTEXTS * ctxsize;
|
|
|
|
const size_t gemsize = round_up(poolsize, PAGE_SIZE);
|
|
|
|
struct intel_guc *guc = &dev_priv->guc;
|
|
|
|
|
|
|
|
if (!i915.enable_guc_submission)
|
|
|
|
return 0; /* not enabled */
|
|
|
|
|
|
|
|
if (guc->ctx_pool_obj)
|
|
|
|
return 0; /* already allocated */
|
|
|
|
|
|
|
|
guc->ctx_pool_obj = gem_allocate_guc_obj(dev_priv->dev, gemsize);
|
|
|
|
if (!guc->ctx_pool_obj)
|
|
|
|
return -ENOMEM;
|
|
|
|
|
|
|
|
ida_init(&guc->ctx_ids);
|
|
|
|
|
2015-08-12 08:43:40 -06:00
|
|
|
guc_create_log(guc);
|
|
|
|
|
2015-12-18 13:00:09 -07:00
|
|
|
guc_create_ads(guc);
|
|
|
|
|
2015-08-12 08:43:39 -06:00
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2015-08-12 08:43:41 -06:00
|
|
|
int i915_guc_submission_enable(struct drm_device *dev)
|
|
|
|
{
|
|
|
|
struct drm_i915_private *dev_priv = dev->dev_private;
|
|
|
|
struct intel_guc *guc = &dev_priv->guc;
|
2016-01-19 12:02:54 -07:00
|
|
|
struct intel_context *ctx = dev_priv->kernel_context;
|
2015-08-12 08:43:41 -06:00
|
|
|
struct i915_guc_client *client;
|
|
|
|
|
|
|
|
/* client for execbuf submission */
|
drm/i915: Integrate GuC-based command submission
GuC-based submission is mostly the same as execlist mode, up to
intel_logical_ring_advance_and_submit(), where the context being
dispatched would be added to the execlist queue; at this point
we submit the context to the GuC backend instead.
There are, however, a few other changes also required, notably:
1. Contexts must be pinned at GGTT addresses accessible by the GuC
i.e. NOT in the range [0..WOPCM_SIZE), so we have to add the
PIN_OFFSET_BIAS flag to the relevant GGTT-pinning calls.
2. The GuC's TLB must be invalidated after a context is pinned at
a new GGTT address.
3. GuC firmware uses the one page before Ring Context as shared data.
Therefore, whenever driver wants to get base address of LRC, we
will offset one page for it. LRC_PPHWSP_PN is defined as the page
number of LRCA.
4. In the work queue used to pass requests to the GuC, the GuC
firmware requires the ring-tail-offset to be represented as an
11-bit value, expressed in QWords. Therefore, the ringbuffer
size must be reduced to the representable range (4 pages).
v2:
Defer adding #defines until needed [Chris Wilson]
Rationalise type declarations [Chris Wilson]
v4:
Squashed kerneldoc patch into here [Daniel Vetter]
v5:
Update request->tail in code common to both GuC and execlist modes.
Add a private version of lr_context_update(), as sharing the
execlist version leads to race conditions when the CPU and
the GuC both update TAIL in the context image.
Conversion of error-captured HWS page to string must account
for offset from start of object to actual HWS (LRC_PPHWSP_PN).
Issue: VIZ-4884
Signed-off-by: Alex Dai <yu.dai@intel.com>
Signed-off-by: Dave Gordon <david.s.gordon@intel.com>
Reviewed-by: Tom O'Rourke <Tom.O'Rourke@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2015-08-12 08:43:43 -06:00
|
|
|
client = guc_client_alloc(dev, GUC_CTX_PRIORITY_KMD_NORMAL, ctx);
|
2015-08-12 08:43:41 -06:00
|
|
|
if (!client) {
|
|
|
|
DRM_ERROR("Failed to create execbuf guc_client\n");
|
|
|
|
return -ENOMEM;
|
|
|
|
}
|
|
|
|
|
|
|
|
guc->execbuf_client = client;
|
2015-08-18 15:34:47 -06:00
|
|
|
|
|
|
|
host2guc_sample_forcewake(guc, client);
|
|
|
|
|
2015-08-12 08:43:41 -06:00
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
void i915_guc_submission_disable(struct drm_device *dev)
|
|
|
|
{
|
|
|
|
struct drm_i915_private *dev_priv = dev->dev_private;
|
|
|
|
struct intel_guc *guc = &dev_priv->guc;
|
|
|
|
|
|
|
|
guc_client_free(dev, guc->execbuf_client);
|
|
|
|
guc->execbuf_client = NULL;
|
|
|
|
}
|
|
|
|
|
2015-08-12 08:43:39 -06:00
|
|
|
void i915_guc_submission_fini(struct drm_device *dev)
|
|
|
|
{
|
|
|
|
struct drm_i915_private *dev_priv = dev->dev_private;
|
|
|
|
struct intel_guc *guc = &dev_priv->guc;
|
|
|
|
|
2015-12-18 13:00:09 -07:00
|
|
|
gem_release_guc_obj(dev_priv->guc.ads_obj);
|
|
|
|
guc->ads_obj = NULL;
|
|
|
|
|
2015-08-12 08:43:40 -06:00
|
|
|
gem_release_guc_obj(dev_priv->guc.log_obj);
|
|
|
|
guc->log_obj = NULL;
|
|
|
|
|
2015-08-12 08:43:39 -06:00
|
|
|
if (guc->ctx_pool_obj)
|
|
|
|
ida_destroy(&guc->ctx_ids);
|
|
|
|
gem_release_guc_obj(guc->ctx_pool_obj);
|
|
|
|
guc->ctx_pool_obj = NULL;
|
|
|
|
}
|
2015-09-30 10:46:37 -06:00
|
|
|
|
|
|
|
/**
|
|
|
|
* intel_guc_suspend() - notify GuC entering suspend state
|
|
|
|
* @dev: drm device
|
|
|
|
*/
|
|
|
|
int intel_guc_suspend(struct drm_device *dev)
|
|
|
|
{
|
|
|
|
struct drm_i915_private *dev_priv = dev->dev_private;
|
|
|
|
struct intel_guc *guc = &dev_priv->guc;
|
|
|
|
struct intel_context *ctx;
|
|
|
|
u32 data[3];
|
|
|
|
|
|
|
|
if (!i915.enable_guc_submission)
|
|
|
|
return 0;
|
|
|
|
|
2016-01-19 12:02:54 -07:00
|
|
|
ctx = dev_priv->kernel_context;
|
2015-09-30 10:46:37 -06:00
|
|
|
|
|
|
|
data[0] = HOST2GUC_ACTION_ENTER_S_STATE;
|
|
|
|
/* any value greater than GUC_POWER_D0 */
|
|
|
|
data[1] = GUC_POWER_D1;
|
|
|
|
/* first page is shared data with GuC */
|
|
|
|
data[2] = i915_gem_obj_ggtt_offset(ctx->engine[RCS].state);
|
|
|
|
|
|
|
|
return host2guc_action(guc, data, ARRAY_SIZE(data));
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
/**
|
|
|
|
* intel_guc_resume() - notify GuC resuming from suspend state
|
|
|
|
* @dev: drm device
|
|
|
|
*/
|
|
|
|
int intel_guc_resume(struct drm_device *dev)
|
|
|
|
{
|
|
|
|
struct drm_i915_private *dev_priv = dev->dev_private;
|
|
|
|
struct intel_guc *guc = &dev_priv->guc;
|
|
|
|
struct intel_context *ctx;
|
|
|
|
u32 data[3];
|
|
|
|
|
|
|
|
if (!i915.enable_guc_submission)
|
|
|
|
return 0;
|
|
|
|
|
2016-01-19 12:02:54 -07:00
|
|
|
ctx = dev_priv->kernel_context;
|
2015-09-30 10:46:37 -06:00
|
|
|
|
|
|
|
data[0] = HOST2GUC_ACTION_EXIT_S_STATE;
|
|
|
|
data[1] = GUC_POWER_D0;
|
|
|
|
/* first page is shared data with GuC */
|
|
|
|
data[2] = i915_gem_obj_ggtt_offset(ctx->engine[RCS].state);
|
|
|
|
|
|
|
|
return host2guc_action(guc, data, ARRAY_SIZE(data));
|
|
|
|
}
|