summaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/i915
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/gpu/drm/i915')
-rw-r--r--drivers/gpu/drm/i915/display/intel_dp_mst.c1
-rw-r--r--drivers/gpu/drm/i915/gem/i915_gem_region.c2
-rw-r--r--drivers/gpu/drm/i915/gem/i915_gem_ttm.c11
-rw-r--r--drivers/gpu/drm/i915/gem/i915_gem_wait.c34
-rw-r--r--drivers/gpu/drm/i915/gt/intel_context_types.h11
-rw-r--r--drivers/gpu/drm/i915/gt/intel_execlists_submission.c12
-rw-r--r--drivers/gpu/drm/i915/gt/intel_gt.c15
-rw-r--r--drivers/gpu/drm/i915/gt/intel_lrc.h10
-rw-r--r--drivers/gpu/drm/i915/gt/intel_reset.c37
-rw-r--r--drivers/gpu/drm/i915/gt/selftest_lrc.c8
-rw-r--r--drivers/gpu/drm/i915/gt/uc/abi/guc_actions_abi.h3
-rw-r--r--drivers/gpu/drm/i915/gt/uc/intel_guc.h5
-rw-r--r--drivers/gpu/drm/i915/gt/uc/intel_guc_fwif.h45
-rw-r--r--drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c374
-rw-r--r--drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c65
-rw-r--r--drivers/gpu/drm/i915/gt/uc/intel_uc_fw.h7
-rw-r--r--drivers/gpu/drm/i915/gvt/cmd_parser.c6
-rw-r--r--drivers/gpu/drm/i915/i915_scatterlist.c27
-rw-r--r--drivers/gpu/drm/i915/i915_scatterlist.h6
-rw-r--r--drivers/gpu/drm/i915/i915_vma.c12
-rw-r--r--drivers/gpu/drm/i915/intel_region_ttm.c10
-rw-r--r--drivers/gpu/drm/i915/intel_region_ttm.h3
-rw-r--r--drivers/gpu/drm/i915/selftests/i915_gem_gtt.c2
-rw-r--r--drivers/gpu/drm/i915/selftests/intel_memory_region.c21
-rw-r--r--drivers/gpu/drm/i915/selftests/mock_region.c3
25 files changed, 616 insertions, 114 deletions
diff --git a/drivers/gpu/drm/i915/display/intel_dp_mst.c b/drivers/gpu/drm/i915/display/intel_dp_mst.c
index 061b277e5ce7..14d2a64193b2 100644
--- a/drivers/gpu/drm/i915/display/intel_dp_mst.c
+++ b/drivers/gpu/drm/i915/display/intel_dp_mst.c
@@ -839,6 +839,7 @@ static struct drm_connector *intel_dp_add_mst_connector(struct drm_dp_mst_topolo
ret = drm_connector_init(dev, connector, &intel_dp_mst_connector_funcs,
DRM_MODE_CONNECTOR_DisplayPort);
if (ret) {
+ drm_dp_mst_put_port_malloc(port);
intel_connector_free(intel_connector);
return NULL;
}
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_region.c b/drivers/gpu/drm/i915/gem/i915_gem_region.c
index f46ee16a323a..a4fb577eceb4 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_region.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_region.c
@@ -60,6 +60,8 @@ __i915_gem_object_create_region(struct intel_memory_region *mem,
if (page_size)
default_page_size = page_size;
+ /* We should be able to fit a page within an sg entry */
+ GEM_BUG_ON(overflows_type(default_page_size, u32));
GEM_BUG_ON(!is_power_of_2_u64(default_page_size));
GEM_BUG_ON(default_page_size < PAGE_SIZE);
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
index 4c25d9b2f138..8f1bb6a4b7d1 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
@@ -620,10 +620,15 @@ i915_ttm_resource_get_st(struct drm_i915_gem_object *obj,
struct ttm_resource *res)
{
struct ttm_buffer_object *bo = i915_gem_to_ttm(obj);
+ u32 page_alignment;
if (!i915_ttm_gtt_binds_lmem(res))
return i915_ttm_tt_get_st(bo->ttm);
+ page_alignment = bo->page_alignment << PAGE_SHIFT;
+ if (!page_alignment)
+ page_alignment = obj->mm.region->min_page_size;
+
/*
* If CPU mapping differs, we need to add the ttm_tt pages to
* the resulting st. Might make sense for GGTT.
@@ -634,7 +639,8 @@ i915_ttm_resource_get_st(struct drm_i915_gem_object *obj,
struct i915_refct_sgt *rsgt;
rsgt = intel_region_ttm_resource_to_rsgt(obj->mm.region,
- res);
+ res,
+ page_alignment);
if (IS_ERR(rsgt))
return rsgt;
@@ -643,7 +649,8 @@ i915_ttm_resource_get_st(struct drm_i915_gem_object *obj,
return i915_refct_sgt_get(obj->ttm.cached_io_rsgt);
}
- return intel_region_ttm_resource_to_rsgt(obj->mm.region, res);
+ return intel_region_ttm_resource_to_rsgt(obj->mm.region, res,
+ page_alignment);
}
static int i915_ttm_truncate(struct drm_i915_gem_object *obj)
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_wait.c b/drivers/gpu/drm/i915/gem/i915_gem_wait.c
index 319936f91ac5..e6e01c2a74a6 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_wait.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_wait.c
@@ -9,6 +9,7 @@
#include <linux/jiffies.h>
#include "gt/intel_engine.h"
+#include "gt/intel_rps.h"
#include "i915_gem_ioctls.h"
#include "i915_gem_object.h"
@@ -31,6 +32,37 @@ i915_gem_object_wait_fence(struct dma_fence *fence,
timeout);
}
+static void
+i915_gem_object_boost(struct dma_resv *resv, unsigned int flags)
+{
+ struct dma_resv_iter cursor;
+ struct dma_fence *fence;
+
+ /*
+ * Prescan all fences for potential boosting before we begin waiting.
+ *
+ * When we wait, we wait on outstanding fences serially. If the
+ * dma-resv contains a sequence such as 1:1, 1:2 instead of a reduced
+ * form 1:2, then as we look at each wait in turn we see that each
+ * request is currently executing and not worthy of boosting. But if
+ * we only happen to look at the final fence in the sequence (because
+ * of request coalescing or splitting between read/write arrays by
+ * the iterator), then we would boost. As such our decision to boost
+ * or not is delicately balanced on the order we wait on fences.
+ *
+ * So instead of looking for boosts sequentially, look for all boosts
+ * upfront and then wait on the outstanding fences.
+ */
+
+ dma_resv_iter_begin(&cursor, resv,
+ dma_resv_usage_rw(flags & I915_WAIT_ALL));
+ dma_resv_for_each_fence_unlocked(&cursor, fence)
+ if (dma_fence_is_i915(fence) &&
+ !i915_request_started(to_request(fence)))
+ intel_rps_boost(to_request(fence));
+ dma_resv_iter_end(&cursor);
+}
+
static long
i915_gem_object_wait_reservation(struct dma_resv *resv,
unsigned int flags,
@@ -40,6 +72,8 @@ i915_gem_object_wait_reservation(struct dma_resv *resv,
struct dma_fence *fence;
long ret = timeout ?: 1;
+ i915_gem_object_boost(resv, flags);
+
dma_resv_iter_begin(&cursor, resv,
dma_resv_usage_rw(flags & I915_WAIT_ALL));
dma_resv_for_each_fence_unlocked(&cursor, fence) {
diff --git a/drivers/gpu/drm/i915/gt/intel_context_types.h b/drivers/gpu/drm/i915/gt/intel_context_types.h
index 09f82545789f..44e7339e7a4a 100644
--- a/drivers/gpu/drm/i915/gt/intel_context_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_context_types.h
@@ -273,10 +273,17 @@ struct intel_context {
u8 child_index;
/** @guc: GuC specific members for parallel submission */
struct {
- /** @wqi_head: head pointer in work queue */
+ /** @wqi_head: cached head pointer in work queue */
u16 wqi_head;
- /** @wqi_tail: tail pointer in work queue */
+ /** @wqi_tail: cached tail pointer in work queue */
u16 wqi_tail;
+ /** @wq_head: pointer to the actual head in work queue */
+ u32 *wq_head;
+ /** @wq_tail: pointer to the actual head in work queue */
+ u32 *wq_tail;
+ /** @wq_status: pointer to the status in work queue */
+ u32 *wq_status;
+
/**
* @parent_page: page in context state (ce->state) used
* by parent for work queue, process descriptor
diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
index 86f7a9ac1c39..2b0266cab66b 100644
--- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
+++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
@@ -661,6 +661,16 @@ static inline void execlists_schedule_out(struct i915_request *rq)
i915_request_put(rq);
}
+static u32 map_i915_prio_to_lrc_desc_prio(int prio)
+{
+ if (prio > I915_PRIORITY_NORMAL)
+ return GEN12_CTX_PRIORITY_HIGH;
+ else if (prio < I915_PRIORITY_NORMAL)
+ return GEN12_CTX_PRIORITY_LOW;
+ else
+ return GEN12_CTX_PRIORITY_NORMAL;
+}
+
static u64 execlists_update_context(struct i915_request *rq)
{
struct intel_context *ce = rq->context;
@@ -669,7 +679,7 @@ static u64 execlists_update_context(struct i915_request *rq)
desc = ce->lrc.desc;
if (rq->engine->flags & I915_ENGINE_HAS_EU_PRIORITY)
- desc |= lrc_desc_priority(rq_prio(rq));
+ desc |= map_i915_prio_to_lrc_desc_prio(rq_prio(rq));
/*
* WaIdleLiteRestore:bdw,skl
diff --git a/drivers/gpu/drm/i915/gt/intel_gt.c b/drivers/gpu/drm/i915/gt/intel_gt.c
index 51a0fe60c050..531af6ad7007 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt.c
@@ -1209,6 +1209,20 @@ void intel_gt_invalidate_tlbs(struct intel_gt *gt)
mutex_lock(&gt->tlb_invalidate_lock);
intel_uncore_forcewake_get(uncore, FORCEWAKE_ALL);
+ spin_lock_irq(&uncore->lock); /* serialise invalidate with GT reset */
+
+ for_each_engine(engine, gt, id) {
+ struct reg_and_bit rb;
+
+ rb = get_reg_and_bit(engine, regs == gen8_regs, regs, num);
+ if (!i915_mmio_reg_offset(rb.reg))
+ continue;
+
+ intel_uncore_write_fw(uncore, rb.reg, rb.bit);
+ }
+
+ spin_unlock_irq(&uncore->lock);
+
for_each_engine(engine, gt, id) {
/*
* HW architecture suggest typical invalidation time at 40us,
@@ -1223,7 +1237,6 @@ void intel_gt_invalidate_tlbs(struct intel_gt *gt)
if (!i915_mmio_reg_offset(rb.reg))
continue;
- intel_uncore_write_fw(uncore, rb.reg, rb.bit);
if (__intel_wait_for_register_fw(uncore,
rb.reg, rb.bit, 0,
timeout_us, timeout_ms,
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.h b/drivers/gpu/drm/i915/gt/intel_lrc.h
index 31be734010db..a390f0813c8b 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.h
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.h
@@ -111,16 +111,6 @@ enum {
#define XEHP_SW_COUNTER_SHIFT 58
#define XEHP_SW_COUNTER_WIDTH 6
-static inline u32 lrc_desc_priority(int prio)
-{
- if (prio > I915_PRIORITY_NORMAL)
- return GEN12_CTX_PRIORITY_HIGH;
- else if (prio < I915_PRIORITY_NORMAL)
- return GEN12_CTX_PRIORITY_LOW;
- else
- return GEN12_CTX_PRIORITY_NORMAL;
-}
-
static inline void lrc_runtime_start(struct intel_context *ce)
{
struct intel_context_stats *stats = &ce->stats;
diff --git a/drivers/gpu/drm/i915/gt/intel_reset.c b/drivers/gpu/drm/i915/gt/intel_reset.c
index a5338c3fde7a..c68d36fb5bbd 100644
--- a/drivers/gpu/drm/i915/gt/intel_reset.c
+++ b/drivers/gpu/drm/i915/gt/intel_reset.c
@@ -300,9 +300,9 @@ static int gen6_hw_domain_reset(struct intel_gt *gt, u32 hw_domain_mask)
return err;
}
-static int gen6_reset_engines(struct intel_gt *gt,
- intel_engine_mask_t engine_mask,
- unsigned int retry)
+static int __gen6_reset_engines(struct intel_gt *gt,
+ intel_engine_mask_t engine_mask,
+ unsigned int retry)
{
struct intel_engine_cs *engine;
u32 hw_mask;
@@ -321,6 +321,20 @@ static int gen6_reset_engines(struct intel_gt *gt,
return gen6_hw_domain_reset(gt, hw_mask);
}
+static int gen6_reset_engines(struct intel_gt *gt,
+ intel_engine_mask_t engine_mask,
+ unsigned int retry)
+{
+ unsigned long flags;
+ int ret;
+
+ spin_lock_irqsave(&gt->uncore->lock, flags);
+ ret = __gen6_reset_engines(gt, engine_mask, retry);
+ spin_unlock_irqrestore(&gt->uncore->lock, flags);
+
+ return ret;
+}
+
static struct intel_engine_cs *find_sfc_paired_vecs_engine(struct intel_engine_cs *engine)
{
int vecs_id;
@@ -487,9 +501,9 @@ static void gen11_unlock_sfc(struct intel_engine_cs *engine)
rmw_clear_fw(uncore, sfc_lock.lock_reg, sfc_lock.lock_bit);
}
-static int gen11_reset_engines(struct intel_gt *gt,
- intel_engine_mask_t engine_mask,
- unsigned int retry)
+static int __gen11_reset_engines(struct intel_gt *gt,
+ intel_engine_mask_t engine_mask,
+ unsigned int retry)
{
struct intel_engine_cs *engine;
intel_engine_mask_t tmp;
@@ -583,8 +597,11 @@ static int gen8_reset_engines(struct intel_gt *gt,
struct intel_engine_cs *engine;
const bool reset_non_ready = retry >= 1;
intel_engine_mask_t tmp;
+ unsigned long flags;
int ret;
+ spin_lock_irqsave(&gt->uncore->lock, flags);
+
for_each_engine_masked(engine, gt, engine_mask, tmp) {
ret = gen8_engine_reset_prepare(engine);
if (ret && !reset_non_ready)
@@ -612,17 +629,19 @@ static int gen8_reset_engines(struct intel_gt *gt,
* This is best effort, so ignore any error from the initial reset.
*/
if (IS_DG2(gt->i915) && engine_mask == ALL_ENGINES)
- gen11_reset_engines(gt, gt->info.engine_mask, 0);
+ __gen11_reset_engines(gt, gt->info.engine_mask, 0);
if (GRAPHICS_VER(gt->i915) >= 11)
- ret = gen11_reset_engines(gt, engine_mask, retry);
+ ret = __gen11_reset_engines(gt, engine_mask, retry);
else
- ret = gen6_reset_engines(gt, engine_mask, retry);
+ ret = __gen6_reset_engines(gt, engine_mask, retry);
skip_reset:
for_each_engine_masked(engine, gt, engine_mask, tmp)
gen8_engine_reset_cancel(engine);
+ spin_unlock_irqrestore(&gt->uncore->lock, flags);
+
return ret;
}
diff --git a/drivers/gpu/drm/i915/gt/selftest_lrc.c b/drivers/gpu/drm/i915/gt/selftest_lrc.c
index 8b2c11dbe354..1109088fe8f6 100644
--- a/drivers/gpu/drm/i915/gt/selftest_lrc.c
+++ b/drivers/gpu/drm/i915/gt/selftest_lrc.c
@@ -176,8 +176,8 @@ static int live_lrc_layout(void *arg)
continue;
hw = shmem_pin_map(engine->default_state);
- if (IS_ERR(hw)) {
- err = PTR_ERR(hw);
+ if (!hw) {
+ err = -ENOMEM;
break;
}
hw += LRC_STATE_OFFSET / sizeof(*hw);
@@ -365,8 +365,8 @@ static int live_lrc_fixed(void *arg)
continue;
hw = shmem_pin_map(engine->default_state);
- if (IS_ERR(hw)) {
- err = PTR_ERR(hw);
+ if (!hw) {
+ err = -ENOMEM;
break;
}
hw += LRC_STATE_OFFSET / sizeof(*hw);
diff --git a/drivers/gpu/drm/i915/gt/uc/abi/guc_actions_abi.h b/drivers/gpu/drm/i915/gt/uc/abi/guc_actions_abi.h
index 4ef9990ed7f8..29ef8afc8c2e 100644
--- a/drivers/gpu/drm/i915/gt/uc/abi/guc_actions_abi.h
+++ b/drivers/gpu/drm/i915/gt/uc/abi/guc_actions_abi.h
@@ -122,6 +122,9 @@ enum intel_guc_action {
INTEL_GUC_ACTION_SCHED_CONTEXT_MODE_DONE = 0x1002,
INTEL_GUC_ACTION_SCHED_ENGINE_MODE_SET = 0x1003,
INTEL_GUC_ACTION_SCHED_ENGINE_MODE_DONE = 0x1004,
+ INTEL_GUC_ACTION_V69_SET_CONTEXT_PRIORITY = 0x1005,
+ INTEL_GUC_ACTION_V69_SET_CONTEXT_EXECUTION_QUANTUM = 0x1006,
+ INTEL_GUC_ACTION_V69_SET_CONTEXT_PREEMPTION_TIMEOUT = 0x1007,
INTEL_GUC_ACTION_CONTEXT_RESET_NOTIFICATION = 0x1008,
INTEL_GUC_ACTION_ENGINE_FAILURE_NOTIFICATION = 0x1009,
INTEL_GUC_ACTION_HOST2GUC_UPDATE_CONTEXT_POLICIES = 0x100B,
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc.h b/drivers/gpu/drm/i915/gt/uc/intel_guc.h
index 966e69a8b1c1..9feda105f913 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc.h
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc.h
@@ -170,6 +170,11 @@ struct intel_guc {
/** @ads_engine_usage_size: size of engine usage in the ADS */
u32 ads_engine_usage_size;
+ /** @lrc_desc_pool_v69: object allocated to hold the GuC LRC descriptor pool */
+ struct i915_vma *lrc_desc_pool_v69;
+ /** @lrc_desc_pool_vaddr_v69: contents of the GuC LRC descriptor pool */
+ void *lrc_desc_pool_vaddr_v69;
+
/**
* @context_lookup: used to resolve intel_context from guc_id, if a
* context is present in this structure it is registered with the GuC
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_fwif.h b/drivers/gpu/drm/i915/gt/uc/intel_guc_fwif.h
index 42cb7a9a6199..89a7e5ec0614 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_fwif.h
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_fwif.h
@@ -203,6 +203,20 @@ struct guc_wq_item {
u32 fence_id;
} __packed;
+struct guc_process_desc_v69 {
+ u32 stage_id;
+ u64 db_base_addr;
+ u32 head;
+ u32 tail;
+ u32 error_offset;
+ u64 wq_base_addr;
+ u32 wq_size_bytes;
+ u32 wq_status;
+ u32 engine_presence;
+ u32 priority;
+ u32 reserved[36];
+} __packed;
+
struct guc_sched_wq_desc {
u32 head;
u32 tail;
@@ -227,6 +241,37 @@ struct guc_ctxt_registration_info {
};
#define CONTEXT_REGISTRATION_FLAG_KMD BIT(0)
+/* Preempt to idle on quantum expiry */
+#define CONTEXT_POLICY_FLAG_PREEMPT_TO_IDLE_V69 BIT(0)
+
+/*
+ * GuC Context registration descriptor.
+ * FIXME: This is only required to exist during context registration.
+ * The current 1:1 between guc_lrc_desc and LRCs for the lifetime of the LRC
+ * is not required.
+ */
+struct guc_lrc_desc_v69 {
+ u32 hw_context_desc;
+ u32 slpm_perf_mode_hint; /* SPLC v1 only */
+ u32 slpm_freq_hint;
+ u32 engine_submit_mask; /* In logical space */
+ u8 engine_class;
+ u8 reserved0[3];
+ u32 priority;
+ u32 process_desc;
+ u32 wq_addr;
+ u32 wq_size;
+ u32 context_flags; /* CONTEXT_REGISTRATION_* */
+ /* Time for one workload to execute. (in micro seconds) */
+ u32 execution_quantum;
+ /* Time to wait for a preemption request to complete before issuing a
+ * reset. (in micro seconds).
+ */
+ u32 preemption_timeout;
+ u32 policy_flags; /* CONTEXT_POLICY_* */
+ u32 reserved1[19];
+} __packed;
+
/* 32-bit KLV structure as used by policy updates and others */
struct guc_klv_generic_dw_t {
u32 kl;
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
index 1726f0f19901..9ffb343d0f79 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
@@ -414,12 +414,15 @@ struct sync_semaphore {
};
struct parent_scratch {
- struct guc_sched_wq_desc wq_desc;
+ union guc_descs {
+ struct guc_sched_wq_desc wq_desc;
+ struct guc_process_desc_v69 pdesc;
+ } descs;
struct sync_semaphore go;
struct sync_semaphore join[MAX_ENGINE_INSTANCE + 1];
- u8 unused[WQ_OFFSET - sizeof(struct guc_sched_wq_desc) -
+ u8 unused[WQ_OFFSET - sizeof(union guc_descs) -
sizeof(struct sync_semaphore) * (MAX_ENGINE_INSTANCE + 2)];
u32 wq[WQ_SIZE / sizeof(u32)];
@@ -456,17 +459,23 @@ __get_parent_scratch(struct intel_context *ce)
LRC_STATE_OFFSET) / sizeof(u32)));
}
+static struct guc_process_desc_v69 *
+__get_process_desc_v69(struct intel_context *ce)
+{
+ struct parent_scratch *ps = __get_parent_scratch(ce);
+
+ return &ps->descs.pdesc;
+}
+
static struct guc_sched_wq_desc *
-__get_wq_desc(struct intel_context *ce)
+__get_wq_desc_v70(struct intel_context *ce)
{
struct parent_scratch *ps = __get_parent_scratch(ce);
- return &ps->wq_desc;
+ return &ps->descs.wq_desc;
}
-static u32 *get_wq_pointer(struct guc_sched_wq_desc *wq_desc,
- struct intel_context *ce,
- u32 wqi_size)
+static u32 *get_wq_pointer(struct intel_context *ce, u32 wqi_size)
{
/*
* Check for space in work queue. Caching a value of head pointer in
@@ -476,7 +485,7 @@ static u32 *get_wq_pointer(struct guc_sched_wq_desc *wq_desc,
#define AVAILABLE_SPACE \
CIRC_SPACE(ce->parallel.guc.wqi_tail, ce->parallel.guc.wqi_head, WQ_SIZE)
if (wqi_size > AVAILABLE_SPACE) {
- ce->parallel.guc.wqi_head = READ_ONCE(wq_desc->head);
+ ce->parallel.guc.wqi_head = READ_ONCE(*ce->parallel.guc.wq_head);
if (wqi_size > AVAILABLE_SPACE)
return NULL;
@@ -495,11 +504,55 @@ static inline struct intel_context *__get_context(struct intel_guc *guc, u32 id)
return ce;
}
+static struct guc_lrc_desc_v69 *__get_lrc_desc_v69(struct intel_guc *guc, u32 index)
+{
+ struct guc_lrc_desc_v69 *base = guc->lrc_desc_pool_vaddr_v69;
+
+ if (!base)
+ return NULL;
+
+ GEM_BUG_ON(index >= GUC_MAX_CONTEXT_ID);
+
+ return &base[index];
+}
+
+static int guc_lrc_desc_pool_create_v69(struct intel_guc *guc)
+{
+ u32 size;
+ int ret;
+
+ size = PAGE_ALIGN(sizeof(struct guc_lrc_desc_v69) *
+ GUC_MAX_CONTEXT_ID);
+ ret = intel_guc_allocate_and_map_vma(guc, size, &guc->lrc_desc_pool_v69,
+ (void **)&guc->lrc_desc_pool_vaddr_v69);
+ if (ret)
+ return ret;
+
+ return 0;
+}
+
+static void guc_lrc_desc_pool_destroy_v69(struct intel_guc *guc)
+{
+ if (!guc->lrc_desc_pool_vaddr_v69)
+ return;
+
+ guc->lrc_desc_pool_vaddr_v69 = NULL;
+ i915_vma_unpin_and_release(&guc->lrc_desc_pool_v69, I915_VMA_RELEASE_MAP);
+}
+
static inline bool guc_submission_initialized(struct intel_guc *guc)
{
return guc->submission_initialized;
}
+static inline void _reset_lrc_desc_v69(struct intel_guc *guc, u32 id)
+{
+ struct guc_lrc_desc_v69 *desc = __get_lrc_desc_v69(guc, id);
+
+ if (desc)
+ memset(desc, 0, sizeof(*desc));
+}
+
static inline bool ctx_id_mapped(struct intel_guc *guc, u32 id)
{
return __get_context(guc, id);
@@ -526,6 +579,8 @@ static inline void clr_ctx_id_mapping(struct intel_guc *guc, u32 id)
if (unlikely(!guc_submission_initialized(guc)))
return;
+ _reset_lrc_desc_v69(guc, id);
+
/*
* xarray API doesn't have xa_erase_irqsave wrapper, so calling
* the lower level functions directly.
@@ -611,7 +666,7 @@ int intel_guc_wait_for_idle(struct intel_guc *guc, long timeout)
true, timeout);
}
-static int guc_context_policy_init(struct intel_context *ce, bool loop);
+static int guc_context_policy_init_v70(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)
@@ -639,7 +694,7 @@ static int __guc_add_request(struct intel_guc *guc, struct i915_request *rq)
GEM_BUG_ON(context_guc_id_invalid(ce));
if (context_policy_required(ce)) {
- err = guc_context_policy_init(ce, false);
+ err = guc_context_policy_init_v70(ce, false);
if (err)
return err;
}
@@ -737,9 +792,7 @@ static u32 wq_space_until_wrap(struct intel_context *ce)
return (WQ_SIZE - ce->parallel.guc.wqi_tail);
}
-static void write_wqi(struct guc_sched_wq_desc *wq_desc,
- struct intel_context *ce,
- u32 wqi_size)
+static void write_wqi(struct intel_context *ce, u32 wqi_size)
{
BUILD_BUG_ON(!is_power_of_2(WQ_SIZE));
@@ -750,13 +803,12 @@ static void write_wqi(struct guc_sched_wq_desc *wq_desc,
ce->parallel.guc.wqi_tail = (ce->parallel.guc.wqi_tail + wqi_size) &
(WQ_SIZE - 1);
- WRITE_ONCE(wq_desc->tail, ce->parallel.guc.wqi_tail);
+ WRITE_ONCE(*ce->parallel.guc.wq_tail, ce->parallel.guc.wqi_tail);
}
static int guc_wq_noop_append(struct intel_context *ce)
{
- struct guc_sched_wq_desc *wq_desc = __get_wq_desc(ce);
- u32 *wqi = get_wq_pointer(wq_desc, ce, wq_space_until_wrap(ce));
+ u32 *wqi = get_wq_pointer(ce, wq_space_until_wrap(ce));
u32 len_dw = wq_space_until_wrap(ce) / sizeof(u32) - 1;
if (!wqi)
@@ -775,7 +827,6 @@ static int __guc_wq_item_append(struct i915_request *rq)
{
struct intel_context *ce = request_to_scheduling_context(rq);
struct intel_context *child;
- struct guc_sched_wq_desc *wq_desc = __get_wq_desc(ce);
unsigned int wqi_size = (ce->parallel.number_children + 4) *
sizeof(u32);
u32 *wqi;
@@ -795,7 +846,7 @@ static int __guc_wq_item_append(struct i915_request *rq)
return ret;
}
- wqi = get_wq_pointer(wq_desc, ce, wqi_size);
+ wqi = get_wq_pointer(ce, wqi_size);
if (!wqi)
return -EBUSY;
@@ -810,7 +861,7 @@ static int __guc_wq_item_append(struct i915_request *rq)
for_each_child(ce, child)
*wqi++ = child->ring->tail / sizeof(u64);
- write_wqi(wq_desc, ce, wqi_size);
+ write_wqi(ce, wqi_size);
return 0;
}
@@ -1868,20 +1919,34 @@ static void reset_fail_worker_func(struct work_struct *w);
int intel_guc_submission_init(struct intel_guc *guc)
{
struct intel_gt *gt = guc_to_gt(guc);
+ int ret;
if (guc->submission_initialized)
return 0;
+ if (guc->fw.major_ver_found < 70) {
+ ret = guc_lrc_desc_pool_create_v69(guc);
+ if (ret)
+ return ret;
+ }
+
guc->submission_state.guc_ids_bitmap =
bitmap_zalloc(NUMBER_MULTI_LRC_GUC_ID(guc), GFP_KERNEL);
- if (!guc->submission_state.guc_ids_bitmap)
- return -ENOMEM;
+ if (!guc->submission_state.guc_ids_bitmap) {
+ ret = -ENOMEM;
+ goto destroy_pool;
+ }
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;
+
+destroy_pool:
+ guc_lrc_desc_pool_destroy_v69(guc);
+
+ return ret;
}
void intel_guc_submission_fini(struct intel_guc *guc)
@@ -1890,6 +1955,7 @@ void intel_guc_submission_fini(struct intel_guc *guc)
return;
guc_flush_destroyed_contexts(guc);
+ guc_lrc_desc_pool_destroy_v69(guc);
i915_sched_engine_put(guc->sched_engine);
bitmap_free(guc->submission_state.guc_ids_bitmap);
guc->submission_initialized = false;
@@ -2147,10 +2213,34 @@ static void unpin_guc_id(struct intel_guc *guc, struct intel_context *ce)
spin_unlock_irqrestore(&guc->submission_state.lock, flags);
}
-static int __guc_action_register_multi_lrc(struct intel_guc *guc,
- struct intel_context *ce,
- struct guc_ctxt_registration_info *info,
- bool loop)
+static int __guc_action_register_multi_lrc_v69(struct intel_guc *guc,
+ struct intel_context *ce,
+ u32 guc_id,
+ u32 offset,
+ bool loop)
+{
+ struct intel_context *child;
+ u32 action[4 + MAX_ENGINE_INSTANCE];
+ int len = 0;
+
+ GEM_BUG_ON(ce->parallel.number_children > MAX_ENGINE_INSTANCE);
+
+ action[len++] = INTEL_GUC_ACTION_REGISTER_CONTEXT_MULTI_LRC;
+ action[len++] = guc_id;
+ action[len++] = ce->parallel.number_children + 1;
+ action[len++] = offset;
+ for_each_child(ce, child) {
+ offset += sizeof(struct guc_lrc_desc_v69);
+ action[len++] = offset;
+ }
+
+ return guc_submission_send_busy_loop(guc, action, len, 0, loop);
+}
+
+static int __guc_action_register_multi_lrc_v70(struct intel_guc *guc,
+ struct intel_context *ce,
+ struct guc_ctxt_registration_info *info,
+ bool loop)
{
struct intel_context *child;
u32 action[13 + (MAX_ENGINE_INSTANCE * 2)];
@@ -2190,9 +2280,24 @@ static int __guc_action_register_multi_lrc(struct intel_guc *guc,
return guc_submission_send_busy_loop(guc, action, len, 0, loop);
}
-static int __guc_action_register_context(struct intel_guc *guc,
- struct guc_ctxt_registration_info *info,
- bool loop)
+static int __guc_action_register_context_v69(struct intel_guc *guc,
+ u32 guc_id,
+ u32 offset,
+ bool loop)
+{
+ u32 action[] = {
+ INTEL_GUC_ACTION_REGISTER_CONTEXT,
+ guc_id,
+ offset,
+ };
+
+ return guc_submission_send_busy_loop(guc, action, ARRAY_SIZE(action),
+ 0, loop);
+}
+
+static int __guc_action_register_context_v70(struct intel_guc *guc,
+ struct guc_ctxt_registration_info *info,
+ bool loop)
{
u32 action[] = {
INTEL_GUC_ACTION_REGISTER_CONTEXT,
@@ -2213,24 +2318,52 @@ static int __guc_action_register_context(struct intel_guc *guc,
0, loop);
}
-static void prepare_context_registration_info(struct intel_context *ce,
- struct guc_ctxt_registration_info *info);
+static void prepare_context_registration_info_v69(struct intel_context *ce);
+static void prepare_context_registration_info_v70(struct intel_context *ce,
+ struct guc_ctxt_registration_info *info);
-static int register_context(struct intel_context *ce, bool loop)
+static int
+register_context_v69(struct intel_guc *guc, struct intel_context *ce, bool loop)
+{
+ u32 offset = intel_guc_ggtt_offset(guc, guc->lrc_desc_pool_v69) +
+ ce->guc_id.id * sizeof(struct guc_lrc_desc_v69);
+
+ prepare_context_registration_info_v69(ce);
+
+ if (intel_context_is_parent(ce))
+ return __guc_action_register_multi_lrc_v69(guc, ce, ce->guc_id.id,
+ offset, loop);
+ else
+ return __guc_action_register_context_v69(guc, ce->guc_id.id,
+ offset, loop);
+}
+
+static int
+register_context_v70(struct intel_guc *guc, struct intel_context *ce, bool loop)
{
struct guc_ctxt_registration_info info;
+
+ prepare_context_registration_info_v70(ce, &info);
+
+ if (intel_context_is_parent(ce))
+ return __guc_action_register_multi_lrc_v70(guc, ce, &info, loop);
+ else
+ return __guc_action_register_context_v70(guc, &info, loop);
+}
+
+static int register_context(struct intel_context *ce, bool loop)
+{
struct intel_guc *guc = ce_to_guc(ce);
int ret;
GEM_BUG_ON(intel_context_is_child(ce));
trace_intel_context_register(ce);
- prepare_context_registration_info(ce, &info);
-
- if (intel_context_is_parent(ce))
- ret = __guc_action_register_multi_lrc(guc, ce, &info, loop);
+ if (guc->fw.major_ver_found >= 70)
+ ret = register_context_v70(guc, ce, loop);
else
- ret = __guc_action_register_context(guc, &info, loop);
+ ret = register_context_v69(guc, ce, loop);
+
if (likely(!ret)) {
unsigned long flags;
@@ -2238,7 +2371,8 @@ static int register_context(struct intel_context *ce, bool loop)
set_context_registered(ce);
spin_unlock_irqrestore(&ce->guc_state.lock, flags);
- guc_context_policy_init(ce, loop);
+ if (guc->fw.major_ver_found >= 70)
+ guc_context_policy_init_v70(ce, loop);
}
return ret;
@@ -2335,7 +2469,7 @@ static int __guc_context_set_context_policies(struct intel_guc *guc,
0, loop);
}
-static int guc_context_policy_init(struct intel_context *ce, bool loop)
+static int guc_context_policy_init_v70(struct intel_context *ce, bool loop)
{
struct intel_engine_cs *engine = ce->engine;
struct intel_guc *guc = &engine->gt->uc.guc;
@@ -2394,8 +2528,108 @@ static int guc_context_policy_init(struct intel_context *ce, bool loop)
return ret;
}
-static void prepare_context_registration_info(struct intel_context *ce,
- struct guc_ctxt_registration_info *info)
+static void guc_context_policy_init_v69(struct intel_engine_cs *engine,
+ struct guc_lrc_desc_v69 *desc)
+{
+ desc->policy_flags = 0;
+
+ if (engine->flags & I915_ENGINE_WANT_FORCED_PREEMPTION)
+ desc->policy_flags |= CONTEXT_POLICY_FLAG_PREEMPT_TO_IDLE_V69;
+
+ /* NB: For both of these, zero means disabled. */
+ desc->execution_quantum = engine->props.timeslice_duration_ms * 1000;
+ desc->preemption_timeout = engine->props.preempt_timeout_ms * 1000;
+}
+
+static u32 map_guc_prio_to_lrc_desc_prio(u8 prio)
+{
+ /*
+ * this matches the mapping we do in map_i915_prio_to_guc_prio()
+ * (e.g. prio < I915_PRIORITY_NORMAL maps to GUC_CLIENT_PRIORITY_NORMAL)
+ */
+ switch (prio) {
+ default:
+ MISSING_CASE(prio);
+ fallthrough;
+ case GUC_CLIENT_PRIORITY_KMD_NORMAL:
+ return GEN12_CTX_PRIORITY_NORMAL;
+ case GUC_CLIENT_PRIORITY_NORMAL:
+ return GEN12_CTX_PRIORITY_LOW;
+ case GUC_CLIENT_PRIORITY_HIGH:
+ case GUC_CLIENT_PRIORITY_KMD_HIGH:
+ return GEN12_CTX_PRIORITY_HIGH;
+ }
+}
+
+static void prepare_context_registration_info_v69(struct intel_context *ce)
+{
+ struct intel_engine_cs *engine = ce->engine;
+ struct intel_guc *guc = &engine->gt->uc.guc;
+ u32 ctx_id = ce->guc_id.id;
+ struct guc_lrc_desc_v69 *desc;
+ struct intel_context *child;
+
+ GEM_BUG_ON(!engine->mask);
+
+ /*
+ * Ensure LRC + CT vmas are is same region as write barrier is done
+ * based on CT vma region.
+ */
+ GEM_BUG_ON(i915_gem_object_is_lmem(guc->ct.vma->obj) !=
+ i915_gem_object_is_lmem(ce->ring->vma->obj));
+
+ desc = __get_lrc_desc_v69(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;
+ desc->priority = ce->guc_state.prio;
+ desc->context_flags = CONTEXT_REGISTRATION_FLAG_KMD;
+ guc_context_policy_init_v69(engine, desc);
+
+ /*
+ * If context is a parent, we need to register a process descriptor
+ * describing a work queue and register all child contexts.
+ */
+ if (intel_context_is_parent(ce)) {
+ struct guc_process_desc_v69 *pdesc;
+
+ ce->parallel.guc.wqi_tail = 0;
+ ce->parallel.guc.wqi_head = 0;
+
+ desc->process_desc = i915_ggtt_offset(ce->state) +
+ __get_parent_scratch_offset(ce);
+ desc->wq_addr = i915_ggtt_offset(ce->state) +
+ __get_wq_offset(ce);
+ desc->wq_size = WQ_SIZE;
+
+ pdesc = __get_process_desc_v69(ce);
+ memset(pdesc, 0, sizeof(*(pdesc)));
+ pdesc->stage_id = ce->guc_id.id;
+ pdesc->wq_base_addr = desc->wq_addr;
+ pdesc->wq_size_bytes = desc->wq_size;
+ pdesc->wq_status = WQ_STATUS_ACTIVE;
+
+ ce->parallel.guc.wq_head = &pdesc->head;
+ ce->parallel.guc.wq_tail = &pdesc->tail;
+ ce->parallel.guc.wq_status = &pdesc->wq_status;
+
+ for_each_child(ce, child) {
+ desc = __get_lrc_desc_v69(guc, child->guc_id.id);
+
+ desc->engine_class =
+ engine_class_to_guc_class(engine->class);
+ desc->hw_context_desc = child->lrc.lrca;
+ desc->priority = ce->guc_state.prio;
+ desc->context_flags = CONTEXT_REGISTRATION_FLAG_KMD;
+ guc_context_policy_init_v69(engine, desc);
+ }
+
+ clear_children_join_go_memory(ce);
+ }
+}
+
+static void prepare_context_registration_info_v70(struct intel_context *ce,
+ struct guc_ctxt_registration_info *info)
{
struct intel_engine_cs *engine = ce->engine;
struct intel_guc *guc = &engine->gt->uc.guc;
@@ -2420,6 +2654,8 @@ static void prepare_context_registration_info(struct intel_context *ce,
*/
info->hwlrca_lo = lower_32_bits(ce->lrc.lrca);
info->hwlrca_hi = upper_32_bits(ce->lrc.lrca);
+ if (engine->flags & I915_ENGINE_HAS_EU_PRIORITY)
+ info->hwlrca_lo |= map_guc_prio_to_lrc_desc_prio(ce->guc_state.prio);
info->flags = CONTEXT_REGISTRATION_FLAG_KMD;
/*
@@ -2443,10 +2679,14 @@ static void prepare_context_registration_info(struct intel_context *ce,
info->wq_base_hi = upper_32_bits(wq_base_offset);
info->wq_size = WQ_SIZE;
- wq_desc = __get_wq_desc(ce);
+ wq_desc = __get_wq_desc_v70(ce);
memset(wq_desc, 0, sizeof(*wq_desc));
wq_desc->wq_status = WQ_STATUS_ACTIVE;
+ ce->parallel.guc.wq_head = &wq_desc->head;
+ ce->parallel.guc.wq_tail = &wq_desc->tail;
+ ce->parallel.guc.wq_status = &wq_desc->wq_status;
+
clear_children_join_go_memory(ce);
}
}
@@ -2761,11 +3001,21 @@ static void __guc_context_set_preemption_timeout(struct intel_guc *guc,
u16 guc_id,
u32 preemption_timeout)
{
- struct context_policy policy;
+ if (guc->fw.major_ver_found >= 70) {
+ struct context_policy policy;
- __guc_context_policy_start_klv(&policy, guc_id);
- __guc_context_policy_add_preemption_timeout(&policy, preemption_timeout);
- __guc_context_set_context_policies(guc, &policy, true);
+ __guc_context_policy_start_klv(&policy, guc_id);
+ __guc_context_policy_add_preemption_timeout(&policy, preemption_timeout);
+ __guc_context_set_context_policies(guc, &policy, true);
+ } else {
+ u32 action[] = {
+ INTEL_GUC_ACTION_V69_SET_CONTEXT_PREEMPTION_TIMEOUT,
+ guc_id,
+ preemption_timeout
+ };
+
+ intel_guc_send_busy_loop(guc, action, ARRAY_SIZE(action), 0, true);
+ }
}
static void guc_context_ban(struct intel_context *ce, struct i915_request *rq)
@@ -3013,11 +3263,21 @@ static int guc_context_alloc(struct intel_context *ce)
static void __guc_context_set_prio(struct intel_guc *guc,
struct intel_context *ce)
{
- struct context_policy policy;
+ if (guc->fw.major_ver_found >= 70) {
+ struct context_policy policy;
- __guc_context_policy_start_klv(&policy, ce->guc_id.id);
- __guc_context_policy_add_priority(&policy, ce->guc_state.prio);
- __guc_context_set_context_policies(guc, &policy, true);
+ __guc_context_policy_start_klv(&policy, ce->guc_id.id);
+ __guc_context_policy_add_priority(&policy, ce->guc_state.prio);
+ __guc_context_set_context_policies(guc, &policy, true);
+ } else {
+ u32 action[] = {
+ INTEL_GUC_ACTION_V69_SET_CONTEXT_PRIORITY,
+ ce->guc_id.id,
+ ce->guc_state.prio,
+ };
+
+ guc_submission_send_busy_loop(guc, action, ARRAY_SIZE(action), 0, true);
+ }
}
static void guc_context_set_prio(struct intel_guc *guc,
@@ -4527,17 +4787,19 @@ void intel_guc_submission_print_context_info(struct intel_guc *guc,
guc_log_context_priority(p, ce);
if (intel_context_is_parent(ce)) {
- struct guc_sched_wq_desc *wq_desc = __get_wq_desc(ce);
struct intel_context *child;
drm_printf(p, "\t\tNumber children: %u\n",
ce->parallel.number_children);
- drm_printf(p, "\t\tWQI Head: %u\n",
- READ_ONCE(wq_desc->head));
- drm_printf(p, "\t\tWQI Tail: %u\n",
- READ_ONCE(wq_desc->tail));
- drm_printf(p, "\t\tWQI Status: %u\n\n",
- READ_ONCE(wq_desc->wq_status));
+
+ if (ce->parallel.guc.wq_status) {
+ drm_printf(p, "\t\tWQI Head: %u\n",
+ READ_ONCE(*ce->parallel.guc.wq_head));
+ drm_printf(p, "\t\tWQI Tail: %u\n",
+ READ_ONCE(*ce->parallel.guc.wq_tail));
+ drm_printf(p, "\t\tWQI Status: %u\n\n",
+ READ_ONCE(*ce->parallel.guc.wq_status));
+ }
if (ce->engine->emit_bb_start ==
emit_bb_start_parent_no_preempt_mid_batch) {
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c
index f0d7b57b741e..703f42ba5ddd 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c
@@ -70,6 +70,10 @@ void intel_uc_fw_change_status(struct intel_uc_fw *uc_fw,
fw_def(BROXTON, 0, guc_def(bxt, 70, 1, 1)) \
fw_def(SKYLAKE, 0, guc_def(skl, 70, 1, 1))
+#define INTEL_GUC_FIRMWARE_DEFS_FALLBACK(fw_def, guc_def) \
+ fw_def(ALDERLAKE_P, 0, guc_def(adlp, 69, 0, 3)) \
+ fw_def(ALDERLAKE_S, 0, guc_def(tgl, 69, 0, 3))
+
#define INTEL_HUC_FIRMWARE_DEFS(fw_def, huc_def) \
fw_def(ALDERLAKE_P, 0, huc_def(tgl, 7, 9, 3)) \
fw_def(ALDERLAKE_S, 0, huc_def(tgl, 7, 9, 3)) \
@@ -105,6 +109,7 @@ void intel_uc_fw_change_status(struct intel_uc_fw *uc_fw,
MODULE_FIRMWARE(uc_);
INTEL_GUC_FIRMWARE_DEFS(INTEL_UC_MODULE_FW, MAKE_GUC_FW_PATH)
+INTEL_GUC_FIRMWARE_DEFS_FALLBACK(INTEL_UC_MODULE_FW, MAKE_GUC_FW_PATH)
INTEL_HUC_FIRMWARE_DEFS(INTEL_UC_MODULE_FW, MAKE_HUC_FW_PATH)
/* The below structs and macros are used to iterate across the list of blobs */
@@ -149,6 +154,9 @@ __uc_fw_auto_select(struct drm_i915_private *i915, struct intel_uc_fw *uc_fw)
static const struct uc_fw_platform_requirement blobs_guc[] = {
INTEL_GUC_FIRMWARE_DEFS(MAKE_FW_LIST, GUC_FW_BLOB)
};
+ static const struct uc_fw_platform_requirement blobs_guc_fallback[] = {
+ INTEL_GUC_FIRMWARE_DEFS_FALLBACK(MAKE_FW_LIST, GUC_FW_BLOB)
+ };
static const struct uc_fw_platform_requirement blobs_huc[] = {
INTEL_HUC_FIRMWARE_DEFS(MAKE_FW_LIST, HUC_FW_BLOB)
};
@@ -162,6 +170,15 @@ __uc_fw_auto_select(struct drm_i915_private *i915, struct intel_uc_fw *uc_fw)
u8 rev = INTEL_REVID(i915);
int i;
+ /*
+ * The only difference between the ADL GuC FWs is the HWConfig support.
+ * ADL-N does not support HWConfig, so we should use the same binary as
+ * ADL-S, otherwise the GuC might attempt to fetch a config table that
+ * does not exist.
+ */
+ if (IS_ADLP_N(i915))
+ p = INTEL_ALDERLAKE_S;
+
GEM_BUG_ON(uc_fw->type >= ARRAY_SIZE(blobs_all));
fw_blobs = blobs_all[uc_fw->type].blobs;
fw_count = blobs_all[uc_fw->type].count;
@@ -170,12 +187,29 @@ __uc_fw_auto_select(struct drm_i915_private *i915, struct intel_uc_fw *uc_fw)
if (p == fw_blobs[i].p && rev >= fw_blobs[i].rev) {
const struct uc_fw_blob *blob = &fw_blobs[i].blob;
uc_fw->path = blob->path;
+ uc_fw->wanted_path = blob->path;
uc_fw->major_ver_wanted = blob->major;
uc_fw->minor_ver_wanted = blob->minor;
break;
}
}
+ if (uc_fw->type == INTEL_UC_FW_TYPE_GUC) {
+ const struct uc_fw_platform_requirement *blobs = blobs_guc_fallback;
+ u32 count = ARRAY_SIZE(blobs_guc_fallback);
+
+ for (i = 0; i < count && p <= blobs[i].p; i++) {
+ if (p == blobs[i].p && rev >= blobs[i].rev) {
+ const struct uc_fw_blob *blob = &blobs[i].blob;
+
+ uc_fw->fallback.path = blob->path;
+ uc_fw->fallback.major_ver = blob->major;
+ uc_fw->fallback.minor_ver = blob->minor;
+ break;
+ }
+ }
+ }
+
/* make sure the list is ordered as expected */
if (IS_ENABLED(CONFIG_DRM_I915_SELFTEST)) {
for (i = 1; i < fw_count; i++) {
@@ -329,7 +363,24 @@ int intel_uc_fw_fetch(struct intel_uc_fw *uc_fw)
__force_fw_fetch_failures(uc_fw, -EINVAL);
__force_fw_fetch_failures(uc_fw, -ESTALE);
- err = request_firmware(&fw, uc_fw->path, dev);
+ err = firmware_request_nowarn(&fw, uc_fw->path, dev);
+ if (err && !intel_uc_fw_is_overridden(uc_fw) && uc_fw->fallback.path) {
+ err = firmware_request_nowarn(&fw, uc_fw->fallback.path, dev);
+ if (!err) {
+ drm_notice(&i915->drm,
+ "%s firmware %s is recommended, but only %s was found\n",
+ intel_uc_fw_type_repr(uc_fw->type),
+ uc_fw->wanted_path,
+ uc_fw->fallback.path);
+ drm_info(&i915->drm,
+ "Consider updating your linux-firmware pkg or downloading from %s\n",
+ INTEL_UC_FIRMWARE_URL);
+
+ uc_fw->path = uc_fw->fallback.path;
+ uc_fw->major_ver_wanted = uc_fw->fallback.major_ver;
+ uc_fw->minor_ver_wanted = uc_fw->fallback.minor_ver;
+ }
+ }
if (err)
goto fail;
@@ -428,8 +479,8 @@ fail:
INTEL_UC_FIRMWARE_MISSING :
INTEL_UC_FIRMWARE_ERROR);
- drm_notice(&i915->drm, "%s firmware %s: fetch failed with error %d\n",
- intel_uc_fw_type_repr(uc_fw->type), uc_fw->path, err);
+ i915_probe_error(i915, "%s firmware %s: fetch failed with error %d\n",
+ intel_uc_fw_type_repr(uc_fw->type), uc_fw->path, err);
drm_info(&i915->drm, "%s firmware(s) can be downloaded from %s\n",
intel_uc_fw_type_repr(uc_fw->type), INTEL_UC_FIRMWARE_URL);
@@ -787,7 +838,13 @@ size_t intel_uc_fw_copy_rsa(struct intel_uc_fw *uc_fw, void *dst, u32 max_len)
void intel_uc_fw_dump(const struct intel_uc_fw *uc_fw, struct drm_printer *p)
{
drm_printf(p, "%s firmware: %s\n",
- intel_uc_fw_type_repr(uc_fw->type), uc_fw->path);
+ intel_uc_fw_type_repr(uc_fw->type), uc_fw->wanted_path);
+ if (uc_fw->fallback.path) {
+ drm_printf(p, "%s firmware fallback: %s\n",
+ intel_uc_fw_type_repr(uc_fw->type), uc_fw->fallback.path);
+ drm_printf(p, "fallback selected: %s\n",
+ str_yes_no(uc_fw->path == uc_fw->fallback.path));
+ }
drm_printf(p, "\tstatus: %s\n",
intel_uc_fw_status_repr(uc_fw->status));
drm_printf(p, "\tversion: wanted %u.%u, found %u.%u\n",
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.h b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.h
index 3229018877d3..562acdf88adb 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.h
+++ b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.h
@@ -74,6 +74,7 @@ struct intel_uc_fw {
const enum intel_uc_fw_status status;
enum intel_uc_fw_status __status; /* no accidental overwrites */
};
+ const char *wanted_path;
const char *path;
bool user_overridden;
size_t size;
@@ -98,6 +99,12 @@ struct intel_uc_fw {
u16 major_ver_found;
u16 minor_ver_found;
+ struct {
+ const char *path;
+ u16 major_ver;
+ u16 minor_ver;
+ } fallback;
+
u32 rsa_size;
u32 ucode_size;
diff --git a/drivers/gpu/drm/i915/gvt/cmd_parser.c b/drivers/gpu/drm/i915/gvt/cmd_parser.c
index b9eb75a2b400..1c35a41620ae 100644
--- a/drivers/gpu/drm/i915/gvt/cmd_parser.c
+++ b/drivers/gpu/drm/i915/gvt/cmd_parser.c
@@ -3117,9 +3117,9 @@ void intel_gvt_update_reg_whitelist(struct intel_vgpu *vgpu)
continue;
vaddr = shmem_pin_map(engine->default_state);
- if (IS_ERR(vaddr)) {
- gvt_err("failed to map %s->default state, err:%zd\n",
- engine->name, PTR_ERR(vaddr));
+ if (!vaddr) {
+ gvt_err("failed to map %s->default state\n",
+ engine->name);
return;
}
diff --git a/drivers/gpu/drm/i915/i915_scatterlist.c b/drivers/gpu/drm/i915/i915_scatterlist.c
index 159571b9bd24..dcc081874ec8 100644
--- a/drivers/gpu/drm/i915/i915_scatterlist.c
+++ b/drivers/gpu/drm/i915/i915_scatterlist.c
@@ -68,6 +68,7 @@ void i915_refct_sgt_init(struct i915_refct_sgt *rsgt, size_t size)
* drm_mm_node
* @node: The drm_mm_node.
* @region_start: An offset to add to the dma addresses of the sg list.
+ * @page_alignment: Required page alignment for each sg entry. Power of two.
*
* Create a struct sg_table, initializing it from a struct drm_mm_node,
* taking a maximum segment length into account, splitting into segments
@@ -77,22 +78,25 @@ void i915_refct_sgt_init(struct i915_refct_sgt *rsgt, size_t size)
* error code cast to an error pointer on failure.
*/
struct i915_refct_sgt *i915_rsgt_from_mm_node(const struct drm_mm_node *node,
- u64 region_start)
+ u64 region_start,
+ u32 page_alignment)
{
- const u64 max_segment = SZ_1G; /* Do we have a limit on this? */
- u64 segment_pages = max_segment >> PAGE_SHIFT;
+ const u32 max_segment = round_down(UINT_MAX, page_alignment);
+ const u32 segment_pages = max_segment >> PAGE_SHIFT;
u64 block_size, offset, prev_end;
struct i915_refct_sgt *rsgt;
struct sg_table *st;
struct scatterlist *sg;
+ GEM_BUG_ON(!max_segment);
+
rsgt = kmalloc(sizeof(*rsgt), GFP_KERNEL);
if (!rsgt)
return ERR_PTR(-ENOMEM);
i915_refct_sgt_init(rsgt, node->size << PAGE_SHIFT);
st = &rsgt->table;
- if (sg_alloc_table(st, DIV_ROUND_UP(node->size, segment_pages),
+ if (sg_alloc_table(st, DIV_ROUND_UP_ULL(node->size, segment_pages),
GFP_KERNEL)) {
i915_refct_sgt_put(rsgt);
return ERR_PTR(-ENOMEM);
@@ -112,12 +116,14 @@ struct i915_refct_sgt *i915_rsgt_from_mm_node(const struct drm_mm_node *node,
sg = __sg_next(sg);
sg_dma_address(sg) = region_start + offset;
+ GEM_BUG_ON(!IS_ALIGNED(sg_dma_address(sg),
+ page_alignment));
sg_dma_len(sg) = 0;
sg->length = 0;
st->nents++;
}
- len = min(block_size, max_segment - sg->length);
+ len = min_t(u64, block_size, max_segment - sg->length);
sg->length += len;
sg_dma_len(sg) += len;
@@ -138,6 +144,7 @@ struct i915_refct_sgt *i915_rsgt_from_mm_node(const struct drm_mm_node *node,
* i915_buddy_block list
* @res: The struct i915_ttm_buddy_resource.
* @region_start: An offset to add to the dma addresses of the sg list.
+ * @page_alignment: Required page alignment for each sg entry. Power of two.
*
* Create a struct sg_table, initializing it from struct i915_buddy_block list,
* taking a maximum segment length into account, splitting into segments
@@ -147,11 +154,12 @@ struct i915_refct_sgt *i915_rsgt_from_mm_node(const struct drm_mm_node *node,
* error code cast to an error pointer on failure.
*/
struct i915_refct_sgt *i915_rsgt_from_buddy_resource(struct ttm_resource *res,
- u64 region_start)
+ u64 region_start,
+ u32 page_alignment)
{
struct i915_ttm_buddy_resource *bman_res = to_ttm_buddy_resource(res);
const u64 size = res->num_pages << PAGE_SHIFT;
- const u64 max_segment = rounddown(UINT_MAX, PAGE_SIZE);
+ const u32 max_segment = round_down(UINT_MAX, page_alignment);
struct drm_buddy *mm = bman_res->mm;
struct list_head *blocks = &bman_res->blocks;
struct drm_buddy_block *block;
@@ -161,6 +169,7 @@ struct i915_refct_sgt *i915_rsgt_from_buddy_resource(struct ttm_resource *res,
resource_size_t prev_end;
GEM_BUG_ON(list_empty(blocks));
+ GEM_BUG_ON(!max_segment);
rsgt = kmalloc(sizeof(*rsgt), GFP_KERNEL);
if (!rsgt)
@@ -191,12 +200,14 @@ struct i915_refct_sgt *i915_rsgt_from_buddy_resource(struct ttm_resource *res,
sg = __sg_next(sg);
sg_dma_address(sg) = region_start + offset;
+ GEM_BUG_ON(!IS_ALIGNED(sg_dma_address(sg),
+ page_alignment));
sg_dma_len(sg) = 0;
sg->length = 0;
st->nents++;
}
- len = min(block_size, max_segment - sg->length);
+ len = min_t(u64, block_size, max_segment - sg->length);
sg->length += len;
sg_dma_len(sg) += len;
diff --git a/drivers/gpu/drm/i915/i915_scatterlist.h b/drivers/gpu/drm/i915/i915_scatterlist.h
index 12c6a1684081..9ddb3e743a3e 100644
--- a/drivers/gpu/drm/i915/i915_scatterlist.h
+++ b/drivers/gpu/drm/i915/i915_scatterlist.h
@@ -213,9 +213,11 @@ static inline void __i915_refct_sgt_init(struct i915_refct_sgt *rsgt,
void i915_refct_sgt_init(struct i915_refct_sgt *rsgt, size_t size);
struct i915_refct_sgt *i915_rsgt_from_mm_node(const struct drm_mm_node *node,
- u64 region_start);
+ u64 region_start,
+ u32 page_alignment);
struct i915_refct_sgt *i915_rsgt_from_buddy_resource(struct ttm_resource *res,
- u64 region_start);
+ u64 region_start,
+ u32 page_alignment);
#endif
diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c
index 0bffb70b3c5f..04d12f278f57 100644
--- a/drivers/gpu/drm/i915/i915_vma.c
+++ b/drivers/gpu/drm/i915/i915_vma.c
@@ -1637,10 +1637,10 @@ static void force_unbind(struct i915_vma *vma)
GEM_BUG_ON(drm_mm_node_allocated(&vma->node));
}
-static void release_references(struct i915_vma *vma, bool vm_ddestroy)
+static void release_references(struct i915_vma *vma, struct intel_gt *gt,
+ bool vm_ddestroy)
{
struct drm_i915_gem_object *obj = vma->obj;
- struct intel_gt *gt = vma->vm->gt;
GEM_BUG_ON(i915_vma_is_active(vma));
@@ -1695,11 +1695,12 @@ void i915_vma_destroy_locked(struct i915_vma *vma)
force_unbind(vma);
list_del_init(&vma->vm_link);
- release_references(vma, false);
+ release_references(vma, vma->vm->gt, false);
}
void i915_vma_destroy(struct i915_vma *vma)
{
+ struct intel_gt *gt;
bool vm_ddestroy;
mutex_lock(&vma->vm->mutex);
@@ -1707,8 +1708,11 @@ void i915_vma_destroy(struct i915_vma *vma)
list_del_init(&vma->vm_link);
vm_ddestroy = vma->vm_ddestroy;
vma->vm_ddestroy = false;
+
+ /* vma->vm may be freed when releasing vma->vm->mutex. */
+ gt = vma->vm->gt;
mutex_unlock(&vma->vm->mutex);
- release_references(vma, vm_ddestroy);
+ release_references(vma, gt, vm_ddestroy);
}
void i915_vma_parked(struct intel_gt *gt)
diff --git a/drivers/gpu/drm/i915/intel_region_ttm.c b/drivers/gpu/drm/i915/intel_region_ttm.c
index 62ff77445b01..575d67bc6ffe 100644
--- a/drivers/gpu/drm/i915/intel_region_ttm.c
+++ b/drivers/gpu/drm/i915/intel_region_ttm.c
@@ -152,6 +152,7 @@ int intel_region_ttm_fini(struct intel_memory_region *mem)
* Convert an opaque TTM resource manager resource to a refcounted sg_table.
* @mem: The memory region.
* @res: The resource manager resource obtained from the TTM resource manager.
+ * @page_alignment: Required page alignment for each sg entry. Power of two.
*
* The gem backends typically use sg-tables for operations on the underlying
* io_memory. So provide a way for the backends to translate the
@@ -161,16 +162,19 @@ int intel_region_ttm_fini(struct intel_memory_region *mem)
*/
struct i915_refct_sgt *
intel_region_ttm_resource_to_rsgt(struct intel_memory_region *mem,
- struct ttm_resource *res)
+ struct ttm_resource *res,
+ u32 page_alignment)
{
if (mem->is_range_manager) {
struct ttm_range_mgr_node *range_node =
to_ttm_range_mgr_node(res);
return i915_rsgt_from_mm_node(&range_node->mm_nodes[0],
- mem->region.start);
+ mem->region.start,
+ page_alignment);
} else {
- return i915_rsgt_from_buddy_resource(res, mem->region.start);
+ return i915_rsgt_from_buddy_resource(res, mem->region.start,
+ page_alignment);
}
}
diff --git a/drivers/gpu/drm/i915/intel_region_ttm.h b/drivers/gpu/drm/i915/intel_region_ttm.h
index cf9d86dcf409..5bb8d8b582ae 100644
--- a/drivers/gpu/drm/i915/intel_region_ttm.h
+++ b/drivers/gpu/drm/i915/intel_region_ttm.h
@@ -24,7 +24,8 @@ int intel_region_ttm_fini(struct intel_memory_region *mem);
struct i915_refct_sgt *
intel_region_ttm_resource_to_rsgt(struct intel_memory_region *mem,
- struct ttm_resource *res);
+ struct ttm_resource *res,
+ u32 page_alignment);
void intel_region_ttm_resource_free(struct intel_memory_region *mem,
struct ttm_resource *res);
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
index 8633bec18fa7..ab9f17fc85bc 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
@@ -742,7 +742,7 @@ static int pot_hole(struct i915_address_space *vm,
u64 addr;
for (addr = round_up(hole_start + min_alignment, step) - min_alignment;
- addr <= round_down(hole_end - (2 * min_alignment), step) - min_alignment;
+ hole_end > addr && hole_end - addr >= 2 * min_alignment;
addr += step) {
err = i915_vma_pin(vma, 0, 0, addr | flags);
if (err) {
diff --git a/drivers/gpu/drm/i915/selftests/intel_memory_region.c b/drivers/gpu/drm/i915/selftests/intel_memory_region.c
index 73eb53edb8de..3b18e5905c86 100644
--- a/drivers/gpu/drm/i915/selftests/intel_memory_region.c
+++ b/drivers/gpu/drm/i915/selftests/intel_memory_region.c
@@ -451,7 +451,6 @@ out_put:
static int igt_mock_max_segment(void *arg)
{
- const unsigned int max_segment = rounddown(UINT_MAX, PAGE_SIZE);
struct intel_memory_region *mem = arg;
struct drm_i915_private *i915 = mem->i915;
struct i915_ttm_buddy_resource *res;
@@ -460,7 +459,10 @@ static int igt_mock_max_segment(void *arg)
struct drm_buddy *mm;
struct list_head *blocks;
struct scatterlist *sg;
+ I915_RND_STATE(prng);
LIST_HEAD(objects);
+ unsigned int max_segment;
+ unsigned int ps;
u64 size;
int err = 0;
@@ -472,7 +474,13 @@ static int igt_mock_max_segment(void *arg)
*/
size = SZ_8G;
- mem = mock_region_create(i915, 0, size, PAGE_SIZE, 0, 0);
+ ps = PAGE_SIZE;
+ if (i915_prandom_u64_state(&prng) & 1)
+ ps = SZ_64K; /* For something like DG2 */
+
+ max_segment = round_down(UINT_MAX, ps);
+
+ mem = mock_region_create(i915, 0, size, ps, 0, 0);
if (IS_ERR(mem))
return PTR_ERR(mem);
@@ -498,12 +506,21 @@ static int igt_mock_max_segment(void *arg)
}
for (sg = obj->mm.pages->sgl; sg; sg = sg_next(sg)) {
+ dma_addr_t daddr = sg_dma_address(sg);
+
if (sg->length > max_segment) {
pr_err("%s: Created an oversized scatterlist entry, %u > %u\n",
__func__, sg->length, max_segment);
err = -EINVAL;
goto out_close;
}
+
+ if (!IS_ALIGNED(daddr, ps)) {
+ pr_err("%s: Created an unaligned scatterlist entry, addr=%pa, ps=%u\n",
+ __func__, &daddr, ps);
+ err = -EINVAL;
+ goto out_close;
+ }
}
out_close:
diff --git a/drivers/gpu/drm/i915/selftests/mock_region.c b/drivers/gpu/drm/i915/selftests/mock_region.c
index 670557ce1024..bac21fe84ca5 100644
--- a/drivers/gpu/drm/i915/selftests/mock_region.c
+++ b/drivers/gpu/drm/i915/selftests/mock_region.c
@@ -33,7 +33,8 @@ static int mock_region_get_pages(struct drm_i915_gem_object *obj)
return PTR_ERR(obj->mm.res);
obj->mm.rsgt = intel_region_ttm_resource_to_rsgt(obj->mm.region,
- obj->mm.res);
+ obj->mm.res,
+ obj->mm.region->min_page_size);
if (IS_ERR(obj->mm.rsgt)) {
err = PTR_ERR(obj->mm.rsgt);
goto err_free_resource;