From: fei.yang@intel.com
To: intel-gfx@lists.freedesktop.org
Cc: Andi Shyti <andi.shyti@linux.intel.com>,
Lucas De Marchi <lucas.demarchi@intel.com>,
dri-devel@lists.freedesktop.org,
Madhumitha Tolakanahalli Pradeep
<madhumitha.tolakanahalli.pradeep@intel.com>,
Andrzej Hajda <andrzej.hajda@intel.com>,
Matt Roper <matthew.d.roper@intel.com>,
Nirmoy Das <nirmoy.das@intel.com>
Subject: [PATCH 2/8] drm/i915/mtl: Define MOCS and PAT tables for MTL
Date: Wed, 19 Apr 2023 16:00:52 -0700 [thread overview]
Message-ID: <20230419230058.2659455-3-fei.yang@intel.com> (raw)
In-Reply-To: <20230419230058.2659455-1-fei.yang@intel.com>
From: Madhumitha Tolakanahalli Pradeep <madhumitha.tolakanahalli.pradeep@intel.com>
On MTL, GT can no longer allocate on LLC - only the CPU can.
This, along with addition of support for L4 cache calls for
a MOCS/PAT table update.
Also the PAT index registers are multicasted for primary GT,
and there is an address jump from index 7 to 8. This patch
makes sure that these registers are programmed in the proper
way.
BSpec: 44509, 45101, 44235
Cc: Matt Roper <matthew.d.roper@intel.com>
Cc: Lucas De Marchi <lucas.demarchi@intel.com>
Signed-off-by: Madhumitha Tolakanahalli Pradeep <madhumitha.tolakanahalli.pradeep@intel.com>
Signed-off-by: Aravind Iddamsetty <aravind.iddamsetty@intel.com>
Signed-off-by: Nirmoy Das <nirmoy.das@intel.com>
Signed-off-by: Fei Yang <fei.yang@intel.com>
Reviewed-by: Andrzej Hajda <andrzej.hajda@intel.com>
Reviewed-by: Nirmoy Das <nirmoy.das@intel.com>
Reviewed-by: Andi Shyti <andi.shyti@linux.intel.com>
---
drivers/gpu/drm/i915/gt/intel_gt_regs.h | 6 +-
drivers/gpu/drm/i915/gt/intel_gtt.c | 47 ++++++++++++++-
drivers/gpu/drm/i915/gt/intel_gtt.h | 20 ++++++-
drivers/gpu/drm/i915/gt/intel_mocs.c | 76 +++++++++++++++++++++++--
drivers/gpu/drm/i915/gt/selftest_mocs.c | 2 +-
5 files changed, 143 insertions(+), 8 deletions(-)
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_regs.h b/drivers/gpu/drm/i915/gt/intel_gt_regs.h
index fd1f9cd35e9d..e8c3b762a92a 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_regs.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt_regs.h
@@ -356,7 +356,11 @@
#define GEN7_TLB_RD_ADDR _MMIO(0x4700)
#define GEN12_PAT_INDEX(index) _MMIO(0x4800 + (index) * 4)
-#define XEHP_PAT_INDEX(index) MCR_REG(0x4800 + (index) * 4)
+#define _PAT_INDEX(index) _PICK_EVEN_2RANGES(index, 8, \
+ 0x4800, 0x4804, \
+ 0x4848, 0x484c)
+#define XEHP_PAT_INDEX(index) MCR_REG(_PAT_INDEX(index))
+#define XELPMP_PAT_INDEX(index) _MMIO(_PAT_INDEX(index))
#define XEHP_TILE0_ADDR_RANGE MCR_REG(0x4900)
#define XEHP_TILE_LMEM_RANGE_SHIFT 8
diff --git a/drivers/gpu/drm/i915/gt/intel_gtt.c b/drivers/gpu/drm/i915/gt/intel_gtt.c
index 4f436ba7a3c8..2f6a9be0ffe6 100644
--- a/drivers/gpu/drm/i915/gt/intel_gtt.c
+++ b/drivers/gpu/drm/i915/gt/intel_gtt.c
@@ -468,6 +468,44 @@ void gtt_write_workarounds(struct intel_gt *gt)
}
}
+static void xelpmp_setup_private_ppat(struct intel_uncore *uncore)
+{
+ intel_uncore_write(uncore, XELPMP_PAT_INDEX(0),
+ MTL_PPAT_L4_0_WB);
+ intel_uncore_write(uncore, XELPMP_PAT_INDEX(1),
+ MTL_PPAT_L4_1_WT);
+ intel_uncore_write(uncore, XELPMP_PAT_INDEX(2),
+ MTL_PPAT_L4_3_UC);
+ intel_uncore_write(uncore, XELPMP_PAT_INDEX(3),
+ MTL_PPAT_L4_0_WB | MTL_2_COH_1W);
+ intel_uncore_write(uncore, XELPMP_PAT_INDEX(4),
+ MTL_PPAT_L4_0_WB | MTL_3_COH_2W);
+
+ /*
+ * Remaining PAT entries are left at the hardware-default
+ * fully-cached setting
+ */
+}
+
+static void xelpg_setup_private_ppat(struct intel_gt *gt)
+{
+ intel_gt_mcr_multicast_write(gt, XEHP_PAT_INDEX(0),
+ MTL_PPAT_L4_0_WB);
+ intel_gt_mcr_multicast_write(gt, XEHP_PAT_INDEX(1),
+ MTL_PPAT_L4_1_WT);
+ intel_gt_mcr_multicast_write(gt, XEHP_PAT_INDEX(2),
+ MTL_PPAT_L4_3_UC);
+ intel_gt_mcr_multicast_write(gt, XEHP_PAT_INDEX(3),
+ MTL_PPAT_L4_0_WB | MTL_2_COH_1W);
+ intel_gt_mcr_multicast_write(gt, XEHP_PAT_INDEX(4),
+ MTL_PPAT_L4_0_WB | MTL_3_COH_2W);
+
+ /*
+ * Remaining PAT entries are left at the hardware-default
+ * fully-cached setting
+ */
+}
+
static void tgl_setup_private_ppat(struct intel_uncore *uncore)
{
/* TGL doesn't support LLC or AGE settings */
@@ -603,7 +641,14 @@ void setup_private_pat(struct intel_gt *gt)
GEM_BUG_ON(GRAPHICS_VER(i915) < 8);
- if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 50))
+ if (gt->type == GT_MEDIA) {
+ xelpmp_setup_private_ppat(gt->uncore);
+ return;
+ }
+
+ if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 70))
+ xelpg_setup_private_ppat(gt);
+ else if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 50))
xehp_setup_private_ppat(gt);
else if (GRAPHICS_VER(i915) >= 12)
tgl_setup_private_ppat(uncore);
diff --git a/drivers/gpu/drm/i915/gt/intel_gtt.h b/drivers/gpu/drm/i915/gt/intel_gtt.h
index 69ce55f517f5..854ec09fd588 100644
--- a/drivers/gpu/drm/i915/gt/intel_gtt.h
+++ b/drivers/gpu/drm/i915/gt/intel_gtt.h
@@ -88,9 +88,18 @@ typedef u64 gen8_pte_t;
#define BYT_PTE_SNOOPED_BY_CPU_CACHES REG_BIT(2)
#define BYT_PTE_WRITEABLE REG_BIT(1)
+#define MTL_PPGTT_PTE_PAT3 BIT_ULL(62)
#define GEN12_PPGTT_PTE_LM BIT_ULL(11)
+#define GEN12_PPGTT_PTE_PAT2 BIT_ULL(7)
+#define GEN12_PPGTT_PTE_NC BIT_ULL(5)
+#define GEN12_PPGTT_PTE_PAT1 BIT_ULL(4)
+#define GEN12_PPGTT_PTE_PAT0 BIT_ULL(3)
-#define GEN12_GGTT_PTE_LM BIT_ULL(1)
+#define GEN12_GGTT_PTE_LM BIT_ULL(1)
+#define MTL_GGTT_PTE_PAT0 BIT_ULL(52)
+#define MTL_GGTT_PTE_PAT1 BIT_ULL(53)
+#define GEN12_GGTT_PTE_ADDR_MASK GENMASK_ULL(45, 12)
+#define MTL_GGTT_PTE_PAT_MASK GENMASK_ULL(53, 52)
#define GEN12_PDE_64K BIT(6)
#define GEN12_PTE_PS64 BIT(8)
@@ -147,6 +156,15 @@ typedef u64 gen8_pte_t;
#define GEN8_PDE_IPS_64K BIT(11)
#define GEN8_PDE_PS_2M BIT(7)
+#define MTL_PPAT_L4_CACHE_POLICY_MASK REG_GENMASK(3, 2)
+#define MTL_PAT_INDEX_COH_MODE_MASK REG_GENMASK(1, 0)
+#define MTL_PPAT_L4_3_UC REG_FIELD_PREP(MTL_PPAT_L4_CACHE_POLICY_MASK, 3)
+#define MTL_PPAT_L4_1_WT REG_FIELD_PREP(MTL_PPAT_L4_CACHE_POLICY_MASK, 1)
+#define MTL_PPAT_L4_0_WB REG_FIELD_PREP(MTL_PPAT_L4_CACHE_POLICY_MASK, 0)
+#define MTL_3_COH_2W REG_FIELD_PREP(MTL_PAT_INDEX_COH_MODE_MASK, 3)
+#define MTL_2_COH_1W REG_FIELD_PREP(MTL_PAT_INDEX_COH_MODE_MASK, 2)
+#define MTL_0_COH_NON REG_FIELD_PREP(MTL_PAT_INDEX_COH_MODE_MASK, 0)
+
enum i915_cache_level;
struct drm_i915_gem_object;
diff --git a/drivers/gpu/drm/i915/gt/intel_mocs.c b/drivers/gpu/drm/i915/gt/intel_mocs.c
index 69b489e8dfed..89570f137b2c 100644
--- a/drivers/gpu/drm/i915/gt/intel_mocs.c
+++ b/drivers/gpu/drm/i915/gt/intel_mocs.c
@@ -40,6 +40,10 @@ struct drm_i915_mocs_table {
#define LE_COS(value) ((value) << 15)
#define LE_SSE(value) ((value) << 17)
+/* Defines for the tables (GLOB_MOCS_0 - GLOB_MOCS_16) */
+#define _L4_CACHEABILITY(value) ((value) << 2)
+#define IG_PAT(value) ((value) << 8)
+
/* Defines for the tables (LNCFMOCS0 - LNCFMOCS31) - two entries per word */
#define L3_ESC(value) ((value) << 0)
#define L3_SCC(value) ((value) << 1)
@@ -50,6 +54,7 @@ struct drm_i915_mocs_table {
/* Helper defines */
#define GEN9_NUM_MOCS_ENTRIES 64 /* 63-64 are reserved, but configured. */
#define PVC_NUM_MOCS_ENTRIES 3
+#define MTL_NUM_MOCS_ENTRIES 16
/* (e)LLC caching options */
/*
@@ -73,6 +78,12 @@ struct drm_i915_mocs_table {
#define L3_2_RESERVED _L3_CACHEABILITY(2)
#define L3_3_WB _L3_CACHEABILITY(3)
+/* L4 caching options */
+#define L4_0_WB _L4_CACHEABILITY(0)
+#define L4_1_WT _L4_CACHEABILITY(1)
+#define L4_2_RESERVED _L4_CACHEABILITY(2)
+#define L4_3_UC _L4_CACHEABILITY(3)
+
#define MOCS_ENTRY(__idx, __control_value, __l3cc_value) \
[__idx] = { \
.control_value = __control_value, \
@@ -416,6 +427,57 @@ static const struct drm_i915_mocs_entry pvc_mocs_table[] = {
MOCS_ENTRY(2, 0, L3_3_WB),
};
+static const struct drm_i915_mocs_entry mtl_mocs_table[] = {
+ /* Error - Reserved for Non-Use */
+ MOCS_ENTRY(0,
+ IG_PAT(0),
+ L3_LKUP(1) | L3_3_WB),
+ /* Cached - L3 + L4 */
+ MOCS_ENTRY(1,
+ IG_PAT(1),
+ L3_LKUP(1) | L3_3_WB),
+ /* L4 - GO:L3 */
+ MOCS_ENTRY(2,
+ IG_PAT(1),
+ L3_LKUP(1) | L3_1_UC),
+ /* Uncached - GO:L3 */
+ MOCS_ENTRY(3,
+ IG_PAT(1) | L4_3_UC,
+ L3_LKUP(1) | L3_1_UC),
+ /* L4 - GO:Mem */
+ MOCS_ENTRY(4,
+ IG_PAT(1),
+ L3_LKUP(1) | L3_GLBGO(1) | L3_1_UC),
+ /* Uncached - GO:Mem */
+ MOCS_ENTRY(5,
+ IG_PAT(1) | L4_3_UC,
+ L3_LKUP(1) | L3_GLBGO(1) | L3_1_UC),
+ /* L4 - L3:NoLKUP; GO:L3 */
+ MOCS_ENTRY(6,
+ IG_PAT(1),
+ L3_1_UC),
+ /* Uncached - L3:NoLKUP; GO:L3 */
+ MOCS_ENTRY(7,
+ IG_PAT(1) | L4_3_UC,
+ L3_1_UC),
+ /* L4 - L3:NoLKUP; GO:Mem */
+ MOCS_ENTRY(8,
+ IG_PAT(1),
+ L3_GLBGO(1) | L3_1_UC),
+ /* Uncached - L3:NoLKUP; GO:Mem */
+ MOCS_ENTRY(9,
+ IG_PAT(1) | L4_3_UC,
+ L3_GLBGO(1) | L3_1_UC),
+ /* Display - L3; L4:WT */
+ MOCS_ENTRY(14,
+ IG_PAT(1) | L4_1_WT,
+ L3_LKUP(1) | L3_3_WB),
+ /* CCS - Non-Displayable */
+ MOCS_ENTRY(15,
+ IG_PAT(1),
+ L3_GLBGO(1) | L3_1_UC),
+};
+
enum {
HAS_GLOBAL_MOCS = BIT(0),
HAS_ENGINE_MOCS = BIT(1),
@@ -445,7 +507,13 @@ static unsigned int get_mocs_settings(const struct drm_i915_private *i915,
memset(table, 0, sizeof(struct drm_i915_mocs_table));
table->unused_entries_index = I915_MOCS_PTE;
- if (IS_PONTEVECCHIO(i915)) {
+ if (IS_METEORLAKE(i915)) {
+ table->size = ARRAY_SIZE(mtl_mocs_table);
+ table->table = mtl_mocs_table;
+ table->n_entries = MTL_NUM_MOCS_ENTRIES;
+ table->uc_index = 9;
+ table->unused_entries_index = 1;
+ } else if (IS_PONTEVECCHIO(i915)) {
table->size = ARRAY_SIZE(pvc_mocs_table);
table->table = pvc_mocs_table;
table->n_entries = PVC_NUM_MOCS_ENTRIES;
@@ -646,9 +714,9 @@ void intel_mocs_init_engine(struct intel_engine_cs *engine)
init_l3cc_table(engine->gt, &table);
}
-static u32 global_mocs_offset(void)
+static u32 global_mocs_offset(struct intel_gt *gt)
{
- return i915_mmio_reg_offset(GEN12_GLOBAL_MOCS(0));
+ return i915_mmio_reg_offset(GEN12_GLOBAL_MOCS(0)) + gt->uncore->gsi_offset;
}
void intel_set_mocs_index(struct intel_gt *gt)
@@ -671,7 +739,7 @@ void intel_mocs_init(struct intel_gt *gt)
*/
flags = get_mocs_settings(gt->i915, &table);
if (flags & HAS_GLOBAL_MOCS)
- __init_mocs_table(gt->uncore, &table, global_mocs_offset());
+ __init_mocs_table(gt->uncore, &table, global_mocs_offset(gt));
/*
* Initialize the L3CC table as part of mocs initalization to make
diff --git a/drivers/gpu/drm/i915/gt/selftest_mocs.c b/drivers/gpu/drm/i915/gt/selftest_mocs.c
index ca009a6a13bd..730796346514 100644
--- a/drivers/gpu/drm/i915/gt/selftest_mocs.c
+++ b/drivers/gpu/drm/i915/gt/selftest_mocs.c
@@ -137,7 +137,7 @@ static int read_mocs_table(struct i915_request *rq,
return 0;
if (HAS_GLOBAL_MOCS_REGISTERS(rq->engine->i915))
- addr = global_mocs_offset();
+ addr = global_mocs_offset(rq->engine->gt);
else
addr = mocs_offset(rq->engine);
--
2.25.1
WARNING: multiple messages have this Message-ID (diff)
From: fei.yang@intel.com
To: intel-gfx@lists.freedesktop.org
Cc: Lucas De Marchi <lucas.demarchi@intel.com>,
dri-devel@lists.freedesktop.org,
Madhumitha Tolakanahalli Pradeep
<madhumitha.tolakanahalli.pradeep@intel.com>,
Andrzej Hajda <andrzej.hajda@intel.com>,
Matt Roper <matthew.d.roper@intel.com>,
Nirmoy Das <nirmoy.das@intel.com>
Subject: [Intel-gfx] [PATCH 2/8] drm/i915/mtl: Define MOCS and PAT tables for MTL
Date: Wed, 19 Apr 2023 16:00:52 -0700 [thread overview]
Message-ID: <20230419230058.2659455-3-fei.yang@intel.com> (raw)
In-Reply-To: <20230419230058.2659455-1-fei.yang@intel.com>
From: Madhumitha Tolakanahalli Pradeep <madhumitha.tolakanahalli.pradeep@intel.com>
On MTL, GT can no longer allocate on LLC - only the CPU can.
This, along with addition of support for L4 cache calls for
a MOCS/PAT table update.
Also the PAT index registers are multicasted for primary GT,
and there is an address jump from index 7 to 8. This patch
makes sure that these registers are programmed in the proper
way.
BSpec: 44509, 45101, 44235
Cc: Matt Roper <matthew.d.roper@intel.com>
Cc: Lucas De Marchi <lucas.demarchi@intel.com>
Signed-off-by: Madhumitha Tolakanahalli Pradeep <madhumitha.tolakanahalli.pradeep@intel.com>
Signed-off-by: Aravind Iddamsetty <aravind.iddamsetty@intel.com>
Signed-off-by: Nirmoy Das <nirmoy.das@intel.com>
Signed-off-by: Fei Yang <fei.yang@intel.com>
Reviewed-by: Andrzej Hajda <andrzej.hajda@intel.com>
Reviewed-by: Nirmoy Das <nirmoy.das@intel.com>
Reviewed-by: Andi Shyti <andi.shyti@linux.intel.com>
---
drivers/gpu/drm/i915/gt/intel_gt_regs.h | 6 +-
drivers/gpu/drm/i915/gt/intel_gtt.c | 47 ++++++++++++++-
drivers/gpu/drm/i915/gt/intel_gtt.h | 20 ++++++-
drivers/gpu/drm/i915/gt/intel_mocs.c | 76 +++++++++++++++++++++++--
drivers/gpu/drm/i915/gt/selftest_mocs.c | 2 +-
5 files changed, 143 insertions(+), 8 deletions(-)
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_regs.h b/drivers/gpu/drm/i915/gt/intel_gt_regs.h
index fd1f9cd35e9d..e8c3b762a92a 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_regs.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt_regs.h
@@ -356,7 +356,11 @@
#define GEN7_TLB_RD_ADDR _MMIO(0x4700)
#define GEN12_PAT_INDEX(index) _MMIO(0x4800 + (index) * 4)
-#define XEHP_PAT_INDEX(index) MCR_REG(0x4800 + (index) * 4)
+#define _PAT_INDEX(index) _PICK_EVEN_2RANGES(index, 8, \
+ 0x4800, 0x4804, \
+ 0x4848, 0x484c)
+#define XEHP_PAT_INDEX(index) MCR_REG(_PAT_INDEX(index))
+#define XELPMP_PAT_INDEX(index) _MMIO(_PAT_INDEX(index))
#define XEHP_TILE0_ADDR_RANGE MCR_REG(0x4900)
#define XEHP_TILE_LMEM_RANGE_SHIFT 8
diff --git a/drivers/gpu/drm/i915/gt/intel_gtt.c b/drivers/gpu/drm/i915/gt/intel_gtt.c
index 4f436ba7a3c8..2f6a9be0ffe6 100644
--- a/drivers/gpu/drm/i915/gt/intel_gtt.c
+++ b/drivers/gpu/drm/i915/gt/intel_gtt.c
@@ -468,6 +468,44 @@ void gtt_write_workarounds(struct intel_gt *gt)
}
}
+static void xelpmp_setup_private_ppat(struct intel_uncore *uncore)
+{
+ intel_uncore_write(uncore, XELPMP_PAT_INDEX(0),
+ MTL_PPAT_L4_0_WB);
+ intel_uncore_write(uncore, XELPMP_PAT_INDEX(1),
+ MTL_PPAT_L4_1_WT);
+ intel_uncore_write(uncore, XELPMP_PAT_INDEX(2),
+ MTL_PPAT_L4_3_UC);
+ intel_uncore_write(uncore, XELPMP_PAT_INDEX(3),
+ MTL_PPAT_L4_0_WB | MTL_2_COH_1W);
+ intel_uncore_write(uncore, XELPMP_PAT_INDEX(4),
+ MTL_PPAT_L4_0_WB | MTL_3_COH_2W);
+
+ /*
+ * Remaining PAT entries are left at the hardware-default
+ * fully-cached setting
+ */
+}
+
+static void xelpg_setup_private_ppat(struct intel_gt *gt)
+{
+ intel_gt_mcr_multicast_write(gt, XEHP_PAT_INDEX(0),
+ MTL_PPAT_L4_0_WB);
+ intel_gt_mcr_multicast_write(gt, XEHP_PAT_INDEX(1),
+ MTL_PPAT_L4_1_WT);
+ intel_gt_mcr_multicast_write(gt, XEHP_PAT_INDEX(2),
+ MTL_PPAT_L4_3_UC);
+ intel_gt_mcr_multicast_write(gt, XEHP_PAT_INDEX(3),
+ MTL_PPAT_L4_0_WB | MTL_2_COH_1W);
+ intel_gt_mcr_multicast_write(gt, XEHP_PAT_INDEX(4),
+ MTL_PPAT_L4_0_WB | MTL_3_COH_2W);
+
+ /*
+ * Remaining PAT entries are left at the hardware-default
+ * fully-cached setting
+ */
+}
+
static void tgl_setup_private_ppat(struct intel_uncore *uncore)
{
/* TGL doesn't support LLC or AGE settings */
@@ -603,7 +641,14 @@ void setup_private_pat(struct intel_gt *gt)
GEM_BUG_ON(GRAPHICS_VER(i915) < 8);
- if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 50))
+ if (gt->type == GT_MEDIA) {
+ xelpmp_setup_private_ppat(gt->uncore);
+ return;
+ }
+
+ if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 70))
+ xelpg_setup_private_ppat(gt);
+ else if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 50))
xehp_setup_private_ppat(gt);
else if (GRAPHICS_VER(i915) >= 12)
tgl_setup_private_ppat(uncore);
diff --git a/drivers/gpu/drm/i915/gt/intel_gtt.h b/drivers/gpu/drm/i915/gt/intel_gtt.h
index 69ce55f517f5..854ec09fd588 100644
--- a/drivers/gpu/drm/i915/gt/intel_gtt.h
+++ b/drivers/gpu/drm/i915/gt/intel_gtt.h
@@ -88,9 +88,18 @@ typedef u64 gen8_pte_t;
#define BYT_PTE_SNOOPED_BY_CPU_CACHES REG_BIT(2)
#define BYT_PTE_WRITEABLE REG_BIT(1)
+#define MTL_PPGTT_PTE_PAT3 BIT_ULL(62)
#define GEN12_PPGTT_PTE_LM BIT_ULL(11)
+#define GEN12_PPGTT_PTE_PAT2 BIT_ULL(7)
+#define GEN12_PPGTT_PTE_NC BIT_ULL(5)
+#define GEN12_PPGTT_PTE_PAT1 BIT_ULL(4)
+#define GEN12_PPGTT_PTE_PAT0 BIT_ULL(3)
-#define GEN12_GGTT_PTE_LM BIT_ULL(1)
+#define GEN12_GGTT_PTE_LM BIT_ULL(1)
+#define MTL_GGTT_PTE_PAT0 BIT_ULL(52)
+#define MTL_GGTT_PTE_PAT1 BIT_ULL(53)
+#define GEN12_GGTT_PTE_ADDR_MASK GENMASK_ULL(45, 12)
+#define MTL_GGTT_PTE_PAT_MASK GENMASK_ULL(53, 52)
#define GEN12_PDE_64K BIT(6)
#define GEN12_PTE_PS64 BIT(8)
@@ -147,6 +156,15 @@ typedef u64 gen8_pte_t;
#define GEN8_PDE_IPS_64K BIT(11)
#define GEN8_PDE_PS_2M BIT(7)
+#define MTL_PPAT_L4_CACHE_POLICY_MASK REG_GENMASK(3, 2)
+#define MTL_PAT_INDEX_COH_MODE_MASK REG_GENMASK(1, 0)
+#define MTL_PPAT_L4_3_UC REG_FIELD_PREP(MTL_PPAT_L4_CACHE_POLICY_MASK, 3)
+#define MTL_PPAT_L4_1_WT REG_FIELD_PREP(MTL_PPAT_L4_CACHE_POLICY_MASK, 1)
+#define MTL_PPAT_L4_0_WB REG_FIELD_PREP(MTL_PPAT_L4_CACHE_POLICY_MASK, 0)
+#define MTL_3_COH_2W REG_FIELD_PREP(MTL_PAT_INDEX_COH_MODE_MASK, 3)
+#define MTL_2_COH_1W REG_FIELD_PREP(MTL_PAT_INDEX_COH_MODE_MASK, 2)
+#define MTL_0_COH_NON REG_FIELD_PREP(MTL_PAT_INDEX_COH_MODE_MASK, 0)
+
enum i915_cache_level;
struct drm_i915_gem_object;
diff --git a/drivers/gpu/drm/i915/gt/intel_mocs.c b/drivers/gpu/drm/i915/gt/intel_mocs.c
index 69b489e8dfed..89570f137b2c 100644
--- a/drivers/gpu/drm/i915/gt/intel_mocs.c
+++ b/drivers/gpu/drm/i915/gt/intel_mocs.c
@@ -40,6 +40,10 @@ struct drm_i915_mocs_table {
#define LE_COS(value) ((value) << 15)
#define LE_SSE(value) ((value) << 17)
+/* Defines for the tables (GLOB_MOCS_0 - GLOB_MOCS_16) */
+#define _L4_CACHEABILITY(value) ((value) << 2)
+#define IG_PAT(value) ((value) << 8)
+
/* Defines for the tables (LNCFMOCS0 - LNCFMOCS31) - two entries per word */
#define L3_ESC(value) ((value) << 0)
#define L3_SCC(value) ((value) << 1)
@@ -50,6 +54,7 @@ struct drm_i915_mocs_table {
/* Helper defines */
#define GEN9_NUM_MOCS_ENTRIES 64 /* 63-64 are reserved, but configured. */
#define PVC_NUM_MOCS_ENTRIES 3
+#define MTL_NUM_MOCS_ENTRIES 16
/* (e)LLC caching options */
/*
@@ -73,6 +78,12 @@ struct drm_i915_mocs_table {
#define L3_2_RESERVED _L3_CACHEABILITY(2)
#define L3_3_WB _L3_CACHEABILITY(3)
+/* L4 caching options */
+#define L4_0_WB _L4_CACHEABILITY(0)
+#define L4_1_WT _L4_CACHEABILITY(1)
+#define L4_2_RESERVED _L4_CACHEABILITY(2)
+#define L4_3_UC _L4_CACHEABILITY(3)
+
#define MOCS_ENTRY(__idx, __control_value, __l3cc_value) \
[__idx] = { \
.control_value = __control_value, \
@@ -416,6 +427,57 @@ static const struct drm_i915_mocs_entry pvc_mocs_table[] = {
MOCS_ENTRY(2, 0, L3_3_WB),
};
+static const struct drm_i915_mocs_entry mtl_mocs_table[] = {
+ /* Error - Reserved for Non-Use */
+ MOCS_ENTRY(0,
+ IG_PAT(0),
+ L3_LKUP(1) | L3_3_WB),
+ /* Cached - L3 + L4 */
+ MOCS_ENTRY(1,
+ IG_PAT(1),
+ L3_LKUP(1) | L3_3_WB),
+ /* L4 - GO:L3 */
+ MOCS_ENTRY(2,
+ IG_PAT(1),
+ L3_LKUP(1) | L3_1_UC),
+ /* Uncached - GO:L3 */
+ MOCS_ENTRY(3,
+ IG_PAT(1) | L4_3_UC,
+ L3_LKUP(1) | L3_1_UC),
+ /* L4 - GO:Mem */
+ MOCS_ENTRY(4,
+ IG_PAT(1),
+ L3_LKUP(1) | L3_GLBGO(1) | L3_1_UC),
+ /* Uncached - GO:Mem */
+ MOCS_ENTRY(5,
+ IG_PAT(1) | L4_3_UC,
+ L3_LKUP(1) | L3_GLBGO(1) | L3_1_UC),
+ /* L4 - L3:NoLKUP; GO:L3 */
+ MOCS_ENTRY(6,
+ IG_PAT(1),
+ L3_1_UC),
+ /* Uncached - L3:NoLKUP; GO:L3 */
+ MOCS_ENTRY(7,
+ IG_PAT(1) | L4_3_UC,
+ L3_1_UC),
+ /* L4 - L3:NoLKUP; GO:Mem */
+ MOCS_ENTRY(8,
+ IG_PAT(1),
+ L3_GLBGO(1) | L3_1_UC),
+ /* Uncached - L3:NoLKUP; GO:Mem */
+ MOCS_ENTRY(9,
+ IG_PAT(1) | L4_3_UC,
+ L3_GLBGO(1) | L3_1_UC),
+ /* Display - L3; L4:WT */
+ MOCS_ENTRY(14,
+ IG_PAT(1) | L4_1_WT,
+ L3_LKUP(1) | L3_3_WB),
+ /* CCS - Non-Displayable */
+ MOCS_ENTRY(15,
+ IG_PAT(1),
+ L3_GLBGO(1) | L3_1_UC),
+};
+
enum {
HAS_GLOBAL_MOCS = BIT(0),
HAS_ENGINE_MOCS = BIT(1),
@@ -445,7 +507,13 @@ static unsigned int get_mocs_settings(const struct drm_i915_private *i915,
memset(table, 0, sizeof(struct drm_i915_mocs_table));
table->unused_entries_index = I915_MOCS_PTE;
- if (IS_PONTEVECCHIO(i915)) {
+ if (IS_METEORLAKE(i915)) {
+ table->size = ARRAY_SIZE(mtl_mocs_table);
+ table->table = mtl_mocs_table;
+ table->n_entries = MTL_NUM_MOCS_ENTRIES;
+ table->uc_index = 9;
+ table->unused_entries_index = 1;
+ } else if (IS_PONTEVECCHIO(i915)) {
table->size = ARRAY_SIZE(pvc_mocs_table);
table->table = pvc_mocs_table;
table->n_entries = PVC_NUM_MOCS_ENTRIES;
@@ -646,9 +714,9 @@ void intel_mocs_init_engine(struct intel_engine_cs *engine)
init_l3cc_table(engine->gt, &table);
}
-static u32 global_mocs_offset(void)
+static u32 global_mocs_offset(struct intel_gt *gt)
{
- return i915_mmio_reg_offset(GEN12_GLOBAL_MOCS(0));
+ return i915_mmio_reg_offset(GEN12_GLOBAL_MOCS(0)) + gt->uncore->gsi_offset;
}
void intel_set_mocs_index(struct intel_gt *gt)
@@ -671,7 +739,7 @@ void intel_mocs_init(struct intel_gt *gt)
*/
flags = get_mocs_settings(gt->i915, &table);
if (flags & HAS_GLOBAL_MOCS)
- __init_mocs_table(gt->uncore, &table, global_mocs_offset());
+ __init_mocs_table(gt->uncore, &table, global_mocs_offset(gt));
/*
* Initialize the L3CC table as part of mocs initalization to make
diff --git a/drivers/gpu/drm/i915/gt/selftest_mocs.c b/drivers/gpu/drm/i915/gt/selftest_mocs.c
index ca009a6a13bd..730796346514 100644
--- a/drivers/gpu/drm/i915/gt/selftest_mocs.c
+++ b/drivers/gpu/drm/i915/gt/selftest_mocs.c
@@ -137,7 +137,7 @@ static int read_mocs_table(struct i915_request *rq,
return 0;
if (HAS_GLOBAL_MOCS_REGISTERS(rq->engine->i915))
- addr = global_mocs_offset();
+ addr = global_mocs_offset(rq->engine->gt);
else
addr = mocs_offset(rq->engine);
--
2.25.1
next prev parent reply other threads:[~2023-04-19 22:59 UTC|newest]
Thread overview: 79+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-04-19 23:00 [PATCH 0/8] drm/i915/mtl: Define MOCS and PAT tables for MTL fei.yang
2023-04-19 23:00 ` [Intel-gfx] " fei.yang
2023-04-19 23:00 ` [PATCH 1/8] drm/i915/mtl: Set has_llc=0 fei.yang
2023-04-19 23:00 ` [Intel-gfx] " fei.yang
2023-04-20 10:20 ` Das, Nirmoy
2023-04-20 10:20 ` Das, Nirmoy
2023-04-19 23:00 ` fei.yang [this message]
2023-04-19 23:00 ` [Intel-gfx] [PATCH 2/8] drm/i915/mtl: Define MOCS and PAT tables for MTL fei.yang
2023-04-20 20:29 ` Matt Roper
2023-04-19 23:00 ` [PATCH 3/8] drm/i915/mtl: Add PTE encode function fei.yang
2023-04-19 23:00 ` [Intel-gfx] " fei.yang
2023-04-20 20:40 ` Matt Roper
2023-04-21 17:27 ` Yang, Fei
2023-04-21 17:42 ` Matt Roper
2023-04-23 7:37 ` Yang, Fei
2023-04-23 7:37 ` Yang, Fei
2023-04-24 17:20 ` Matt Roper
2023-04-24 18:41 ` Yang, Fei
2023-04-19 23:00 ` [PATCH 4/8] drm/i915/mtl: workaround coherency issue for Media fei.yang
2023-04-19 23:00 ` [Intel-gfx] " fei.yang
2023-04-20 8:26 ` Andrzej Hajda
2023-04-20 11:36 ` Das, Nirmoy
2023-04-20 11:36 ` Das, Nirmoy
2023-04-20 20:52 ` Matt Roper
2023-04-19 23:00 ` [PATCH 5/8] drm/i915/mtl: end support for set caching ioctl fei.yang
2023-04-19 23:00 ` [Intel-gfx] " fei.yang
2023-04-20 21:05 ` Matt Roper
2023-04-19 23:00 ` [PATCH 6/8] drm/i915: preparation for using PAT index fei.yang
2023-04-19 23:00 ` [Intel-gfx] " fei.yang
2023-04-20 8:45 ` Andrzej Hajda
2023-04-20 21:14 ` Matt Roper
2023-04-19 23:00 ` [PATCH 7/8] drm/i915: use pat_index instead of cache_level fei.yang
2023-04-19 23:00 ` [Intel-gfx] " fei.yang
2023-04-20 10:13 ` Andrzej Hajda
2023-04-20 12:39 ` Tvrtko Ursulin
2023-04-20 20:34 ` Yang, Fei
2023-04-21 8:43 ` Tvrtko Ursulin
2023-04-21 10:17 ` Tvrtko Ursulin
2023-04-23 6:12 ` Yang, Fei
2023-04-23 6:12 ` Yang, Fei
2023-04-24 8:41 ` Tvrtko Ursulin
2023-04-21 11:39 ` Tvrtko Ursulin
2023-04-23 6:52 ` Yang, Fei
2023-04-23 6:52 ` Yang, Fei
2023-04-24 9:22 ` Tvrtko Ursulin
2023-04-19 23:00 ` [PATCH 8/8] drm/i915: Allow user to set cache at BO creation fei.yang
2023-04-19 23:00 ` [Intel-gfx] " fei.yang
2023-04-20 11:39 ` Andi Shyti
2023-04-20 11:39 ` [Intel-gfx] " Andi Shyti
2023-04-20 13:06 ` Tvrtko Ursulin
2023-04-20 16:11 ` Yang, Fei
2023-04-20 16:29 ` Andi Shyti
2023-04-20 16:29 ` Andi Shyti
2023-04-21 20:48 ` Jordan Justen
2023-04-21 20:48 ` Jordan Justen
[not found] ` <BYAPR11MB2567F03AD43D7E2DE2628D5D9A669@BYAPR11MB2567.namprd11.prod.outlook.com>
[not found] ` <168232538771.392286.3227368099155268955@jljusten-skl>
2023-04-24 9:08 ` Tvrtko Ursulin
2023-04-24 9:08 ` Tvrtko Ursulin
2023-04-24 17:13 ` Jordan Justen
2023-04-24 17:13 ` Jordan Justen
2023-04-25 13:41 ` IOCTL feature detection (Was: Re: [Intel-gfx] [PATCH 8/8] drm/i915: Allow user to set cache at BO creation) Joonas Lahtinen
2023-04-25 13:41 ` [Intel-gfx] IOCTL feature detection (Was: " Joonas Lahtinen
2023-04-25 17:21 ` IOCTL feature detection (Was: Re: [Intel-gfx] " Teres Alexis, Alan Previn
2023-04-25 17:21 ` [Intel-gfx] IOCTL feature detection (Was: " Teres Alexis, Alan Previn
2023-04-25 18:19 ` IOCTL feature detection (Was: Re: [Intel-gfx] " Jordan Justen
2023-04-25 18:19 ` [Intel-gfx] IOCTL feature detection (Was: " Jordan Justen
2023-04-26 11:52 ` IOCTL feature detection (Was: Re: [Intel-gfx] " Daniel Vetter
2023-04-26 11:52 ` [Intel-gfx] IOCTL feature detection (Was: " Daniel Vetter
2023-04-26 16:48 ` IOCTL feature detection (Was: Re: [Intel-gfx] " Teres Alexis, Alan Previn
2023-04-26 16:48 ` [Intel-gfx] IOCTL feature detection (Was: " Teres Alexis, Alan Previn
2023-04-26 18:10 ` IOCTL feature detection (Was: Re: [Intel-gfx] " Ceraolo Spurio, Daniele
2023-04-26 18:10 ` [Intel-gfx] IOCTL feature detection (Was: " Ceraolo Spurio, Daniele
2023-04-26 20:04 ` IOCTL feature detection (Was: Re: [Intel-gfx] " Jordan Justen
2023-04-26 20:04 ` [Intel-gfx] IOCTL feature detection (Was: " Jordan Justen
2023-04-19 23:29 ` [Intel-gfx] ✗ Fi.CI.SPARSE: warning for drm/i915/mtl: Define MOCS and PAT tables for MTL (rev8) Patchwork
2023-04-19 23:51 ` [Intel-gfx] ✗ Fi.CI.BAT: failure " Patchwork
2023-04-20 11:30 ` [Intel-gfx] [PATCH 0/8] drm/i915/mtl: Define MOCS and PAT tables for MTL Andi Shyti
-- strict thread matches above, loose matches on Subject: below --
2023-04-19 21:12 fei.yang
2023-04-19 21:12 ` [PATCH 2/8] " fei.yang
2023-04-19 18:09 [PATCH 0/8] " fei.yang
2023-04-19 18:09 ` [PATCH 2/8] " fei.yang
2023-04-17 6:24 [PATCH 0/8] " fei.yang
2023-04-17 6:24 ` [PATCH 2/8] " fei.yang
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20230419230058.2659455-3-fei.yang@intel.com \
--to=fei.yang@intel.com \
--cc=andi.shyti@linux.intel.com \
--cc=andrzej.hajda@intel.com \
--cc=dri-devel@lists.freedesktop.org \
--cc=intel-gfx@lists.freedesktop.org \
--cc=lucas.demarchi@intel.com \
--cc=madhumitha.tolakanahalli.pradeep@intel.com \
--cc=matthew.d.roper@intel.com \
--cc=nirmoy.das@intel.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.