summaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/i915/gt/intel_gt.c
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/gpu/drm/i915/gt/intel_gt.c')
-rw-r--r--drivers/gpu/drm/i915/gt/intel_gt.c159
1 files changed, 125 insertions, 34 deletions
diff --git a/drivers/gpu/drm/i915/gt/intel_gt.c b/drivers/gpu/drm/i915/gt/intel_gt.c
index 7caa3412a244..767e329e1cc5 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt.c
@@ -12,6 +12,7 @@
#include "i915_drv.h"
#include "i915_perf_oa_regs.h"
+#include "i915_reg.h"
#include "intel_context.h"
#include "intel_engine_pm.h"
#include "intel_engine_regs.h"
@@ -40,8 +41,6 @@ void intel_gt_common_init_early(struct intel_gt *gt)
{
spin_lock_init(gt->irq_lock);
- INIT_LIST_HEAD(&gt->lmem_userfault_list);
- mutex_init(&gt->lmem_userfault_lock);
INIT_LIST_HEAD(&gt->closed_vma);
spin_lock_init(&gt->closed_lock);
@@ -56,6 +55,7 @@ void intel_gt_common_init_early(struct intel_gt *gt)
seqcount_mutex_init(&gt->tlb.seqno, &gt->tlb.invalidate_lock);
intel_gt_pm_init_early(gt);
+ intel_wopcm_init_early(&gt->wopcm);
intel_uc_init_early(&gt->uc);
intel_rps_init_early(&gt->rps);
}
@@ -192,7 +192,7 @@ int intel_gt_init_hw(struct intel_gt *gt)
ret = i915_ppgtt_init_hw(gt);
if (ret) {
- DRM_ERROR("Enabling PPGTT failed (%d)\n", ret);
+ drm_err(&i915->drm, "Enabling PPGTT failed (%d)\n", ret);
goto out;
}
@@ -231,6 +231,16 @@ static void gen6_clear_engine_error_register(struct intel_engine_cs *engine)
GEN6_RING_FAULT_REG_POSTING_READ(engine);
}
+i915_reg_t intel_gt_perf_limit_reasons_reg(struct intel_gt *gt)
+{
+ /* GT0_PERF_LIMIT_REASONS is available only for Gen11+ */
+ if (GRAPHICS_VER(gt->i915) < 11)
+ return INVALID_MMIO_REG;
+
+ return gt->type == GT_MEDIA ?
+ MTL_MEDIA_PERF_LIMIT_REASONS : GT0_PERF_LIMIT_REASONS;
+}
+
void
intel_gt_clear_error_registers(struct intel_gt *gt,
intel_engine_mask_t engine_mask)
@@ -254,13 +264,17 @@ intel_gt_clear_error_registers(struct intel_gt *gt,
* some errors might have become stuck,
* mask them.
*/
- DRM_DEBUG_DRIVER("EIR stuck: 0x%08x, masking\n", eir);
+ drm_dbg(&gt->i915->drm, "EIR stuck: 0x%08x, masking\n", eir);
rmw_set(uncore, EMR, eir);
intel_uncore_write(uncore, GEN2_IIR,
I915_MASTER_ERROR_INTERRUPT);
}
- if (GRAPHICS_VER(i915) >= 12) {
+ if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 50)) {
+ intel_gt_mcr_multicast_rmw(gt, XEHP_RING_FAULT_REG,
+ RING_FAULT_VALID, 0);
+ intel_gt_mcr_read_any(gt, XEHP_RING_FAULT_REG);
+ } else if (GRAPHICS_VER(i915) >= 12) {
rmw_clear(uncore, GEN12_RING_FAULT_REG, RING_FAULT_VALID);
intel_uncore_posting_read(uncore, GEN12_RING_FAULT_REG);
} else if (GRAPHICS_VER(i915) >= 8) {
@@ -298,6 +312,42 @@ static void gen6_check_faults(struct intel_gt *gt)
}
}
+static void xehp_check_faults(struct intel_gt *gt)
+{
+ u32 fault;
+
+ /*
+ * Although the fault register now lives in an MCR register range,
+ * the GAM registers are special and we only truly need to read
+ * the "primary" GAM instance rather than handling each instance
+ * individually. intel_gt_mcr_read_any() will automatically steer
+ * toward the primary instance.
+ */
+ fault = intel_gt_mcr_read_any(gt, XEHP_RING_FAULT_REG);
+ if (fault & RING_FAULT_VALID) {
+ u32 fault_data0, fault_data1;
+ u64 fault_addr;
+
+ fault_data0 = intel_gt_mcr_read_any(gt, XEHP_FAULT_TLB_DATA0);
+ fault_data1 = intel_gt_mcr_read_any(gt, XEHP_FAULT_TLB_DATA1);
+
+ fault_addr = ((u64)(fault_data1 & FAULT_VA_HIGH_BITS) << 44) |
+ ((u64)fault_data0 << 12);
+
+ drm_dbg(&gt->i915->drm, "Unexpected fault\n"
+ "\tAddr: 0x%08x_%08x\n"
+ "\tAddress space: %s\n"
+ "\tEngine ID: %d\n"
+ "\tSource ID: %d\n"
+ "\tType: %d\n",
+ upper_32_bits(fault_addr), lower_32_bits(fault_addr),
+ fault_data1 & FAULT_GTT_SEL ? "GGTT" : "PPGTT",
+ GEN8_RING_FAULT_ENGINE_ID(fault),
+ RING_FAULT_SRCID(fault),
+ RING_FAULT_FAULT_TYPE(fault));
+ }
+}
+
static void gen8_check_faults(struct intel_gt *gt)
{
struct intel_uncore *uncore = gt->uncore;
@@ -344,7 +394,9 @@ void intel_gt_check_and_clear_faults(struct intel_gt *gt)
struct drm_i915_private *i915 = gt->i915;
/* From GEN8 onwards we only have one 'All Engine Fault Register' */
- if (GRAPHICS_VER(i915) >= 8)
+ if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 50))
+ xehp_check_faults(gt);
+ else if (GRAPHICS_VER(i915) >= 8)
gen8_check_faults(gt);
else if (GRAPHICS_VER(i915) >= 6)
gen6_check_faults(gt);
@@ -812,7 +864,6 @@ static int intel_gt_tile_setup(struct intel_gt *gt, phys_addr_t phys_addr)
}
intel_uncore_init_early(gt->uncore, gt);
- intel_wakeref_auto_init(&gt->userfault_wakeref, gt->uncore->rpm);
ret = intel_uncore_setup_mmio(gt->uncore, phys_addr);
if (ret)
@@ -833,7 +884,7 @@ int intel_gt_probe_all(struct drm_i915_private *i915)
unsigned int i;
int ret;
- mmio_bar = GRAPHICS_VER(i915) == 2 ? GEN2_GTTMMADR_BAR : GTTMMADR_BAR;
+ mmio_bar = intel_mmio_bar(GRAPHICS_VER(i915));
phys_addr = pci_resource_start(pdev, mmio_bar);
/*
@@ -944,7 +995,10 @@ void intel_gt_info_print(const struct intel_gt_info *info,
}
struct reg_and_bit {
- i915_reg_t reg;
+ union {
+ i915_reg_t reg;
+ i915_mcr_reg_t mcr_reg;
+ };
u32 bit;
};
@@ -970,6 +1024,32 @@ get_reg_and_bit(const struct intel_engine_cs *engine, const bool gen8,
return rb;
}
+/*
+ * HW architecture suggest typical invalidation time at 40us,
+ * with pessimistic cases up to 100us and a recommendation to
+ * cap at 1ms. We go a bit higher just in case.
+ */
+#define TLB_INVAL_TIMEOUT_US 100
+#define TLB_INVAL_TIMEOUT_MS 4
+
+/*
+ * On Xe_HP the TLB invalidation registers are located at the same MMIO offsets
+ * but are now considered MCR registers. Since they exist within a GAM range,
+ * the primary instance of the register rolls up the status from each unit.
+ */
+static int wait_for_invalidate(struct intel_gt *gt, struct reg_and_bit rb)
+{
+ if (GRAPHICS_VER_FULL(gt->i915) >= IP_VER(12, 50))
+ return intel_gt_mcr_wait_for_reg(gt, rb.mcr_reg, rb.bit, 0,
+ TLB_INVAL_TIMEOUT_US,
+ TLB_INVAL_TIMEOUT_MS);
+ else
+ return __intel_wait_for_register_fw(gt->uncore, rb.reg, rb.bit, 0,
+ TLB_INVAL_TIMEOUT_US,
+ TLB_INVAL_TIMEOUT_MS,
+ NULL);
+}
+
static void mmio_invalidate_full(struct intel_gt *gt)
{
static const i915_reg_t gen8_regs[] = {
@@ -985,6 +1065,13 @@ static void mmio_invalidate_full(struct intel_gt *gt)
[COPY_ENGINE_CLASS] = GEN12_BLT_TLB_INV_CR,
[COMPUTE_CLASS] = GEN12_COMPCTX_TLB_INV_CR,
};
+ static const i915_mcr_reg_t xehp_regs[] = {
+ [RENDER_CLASS] = XEHP_GFX_TLB_INV_CR,
+ [VIDEO_DECODE_CLASS] = XEHP_VD_TLB_INV_CR,
+ [VIDEO_ENHANCEMENT_CLASS] = XEHP_VE_TLB_INV_CR,
+ [COPY_ENGINE_CLASS] = XEHP_BLT_TLB_INV_CR,
+ [COMPUTE_CLASS] = XEHP_COMPCTX_TLB_INV_CR,
+ };
struct drm_i915_private *i915 = gt->i915;
struct intel_uncore *uncore = gt->uncore;
struct intel_engine_cs *engine;
@@ -993,7 +1080,10 @@ static void mmio_invalidate_full(struct intel_gt *gt)
const i915_reg_t *regs;
unsigned int num = 0;
- if (GRAPHICS_VER(i915) == 12) {
+ if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 50)) {
+ regs = NULL;
+ num = ARRAY_SIZE(xehp_regs);
+ } else if (GRAPHICS_VER(i915) == 12) {
regs = gen12_regs;
num = ARRAY_SIZE(gen12_regs);
} else if (GRAPHICS_VER(i915) >= 8 && GRAPHICS_VER(i915) <= 11) {
@@ -1018,16 +1108,22 @@ static void mmio_invalidate_full(struct intel_gt *gt)
if (!intel_engine_pm_is_awake(engine))
continue;
- rb = get_reg_and_bit(engine, regs == gen8_regs, regs, num);
- if (!i915_mmio_reg_offset(rb.reg))
- continue;
-
- if (GRAPHICS_VER(i915) == 12 && (engine->class == VIDEO_DECODE_CLASS ||
- engine->class == VIDEO_ENHANCEMENT_CLASS ||
- engine->class == COMPUTE_CLASS))
- rb.bit = _MASKED_BIT_ENABLE(rb.bit);
-
- intel_uncore_write_fw(uncore, rb.reg, rb.bit);
+ if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 50)) {
+ intel_gt_mcr_multicast_write_fw(gt,
+ xehp_regs[engine->class],
+ BIT(engine->instance));
+ } else {
+ rb = get_reg_and_bit(engine, regs == gen8_regs, regs, num);
+ if (!i915_mmio_reg_offset(rb.reg))
+ continue;
+
+ if (GRAPHICS_VER(i915) == 12 && (engine->class == VIDEO_DECODE_CLASS ||
+ engine->class == VIDEO_ENHANCEMENT_CLASS ||
+ engine->class == COMPUTE_CLASS))
+ rb.bit = _MASKED_BIT_ENABLE(rb.bit);
+
+ intel_uncore_write_fw(uncore, rb.reg, rb.bit);
+ }
awake |= engine->mask;
}
@@ -1047,22 +1143,17 @@ static void mmio_invalidate_full(struct intel_gt *gt)
for_each_engine_masked(engine, gt, awake, tmp) {
struct reg_and_bit rb;
- /*
- * HW architecture suggest typical invalidation time at 40us,
- * with pessimistic cases up to 100us and a recommendation to
- * cap at 1ms. We go a bit higher just in case.
- */
- const unsigned int timeout_us = 100;
- const unsigned int timeout_ms = 4;
-
- rb = get_reg_and_bit(engine, regs == gen8_regs, regs, num);
- if (__intel_wait_for_register_fw(uncore,
- rb.reg, rb.bit, 0,
- timeout_us, timeout_ms,
- NULL))
+ if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 50)) {
+ rb.mcr_reg = xehp_regs[engine->class];
+ rb.bit = BIT(engine->instance);
+ } else {
+ rb = get_reg_and_bit(engine, regs == gen8_regs, regs, num);
+ }
+
+ if (wait_for_invalidate(gt, rb))
drm_err_ratelimited(&gt->i915->drm,
"%s TLB invalidation did not complete in %ums!\n",
- engine->name, timeout_ms);
+ engine->name, TLB_INVAL_TIMEOUT_MS);
}
/*
generated by cgit (git 2.34.1) at 2024-05-28 03:55:51 +0000