On 29-11-2022 01:22, Yang, Fei wrote:
>> From: Iddamsetty, Aravind <aravind.iddamsetty@xxxxxxxxx>
>> Sent: Monday, November 28, 2022 2:14 AM
>> To: intel-gfx@xxxxxxxxxxxxxxxxxxxxx
>> Cc: De Marchi, Lucas <lucas.demarchi@xxxxxxxxx>; Roper, Matthew D <matthew.d.roper@xxxxxxxxx>; Yang, Fei <fei.yang@xxxxxxxxx>
>> Subject: [PATCH 2/3] drm/i915/mtl: Define new PTE encode for MTL
>>
>> Add a separate PTE encode function for MTL. The number of PAT
>> registers have increased to 16 on MTL. All 16 PAT registers are
>> available for PPGTT mapped pages, but only the lower 4 are
>> available for GGTT mapped pages.
>>
>> BSPEC: 63884
>>
>> Cc: Lucas De Marchi <lucas.demarchi@xxxxxxxxx>
>> Cc: Matt Roper <matthew.d.roper@xxxxxxxxx>
>> Co-developed-by: Fei Yang <fei.yang@xxxxxxxxx>
>> Signed-off-by: Fei Yang <fei.yang@xxxxxxxxx>
>> Signed-off-by: Aravind Iddamsetty <aravind.iddamsetty@xxxxxxxxx>
>> ---
>> drivers/gpu/drm/i915/display/intel_dpt.c | 2 +-
>> drivers/gpu/drm/i915/gt/gen8_ppgtt.c | 43 ++++++++++++++++++++----
>> drivers/gpu/drm/i915/gt/gen8_ppgtt.h | 4 +++
>> drivers/gpu/drm/i915/gt/intel_ggtt.c | 36 ++++++++++++++++++--
>> drivers/gpu/drm/i915/gt/intel_gtt.h | 13 +++++--
>> 5 files changed, 86 insertions(+), 12 deletions(-)
>>
>> diff --git a/drivers/gpu/drm/i915/display/intel_dpt.c b/drivers/gpu/drm/i915/display/intel_dpt.c
>> index ad1a37b515fb..cb8ed9bfb240 100644
>> --- a/drivers/gpu/drm/i915/display/intel_dpt.c
>> +++ b/drivers/gpu/drm/i915/display/intel_dpt.c
>> @@ -298,7 +298,7 @@ intel_dpt_create(struct intel_framebuffer *fb)
>> vm->vma_ops.bind_vma = dpt_bind_vma;
>> vm->vma_ops.unbind_vma = dpt_unbind_vma;
>>
>> - vm->pte_encode = gen8_ggtt_pte_encode;
>> + vm->pte_encode = vm->gt->ggtt->vm.pte_encode;
>>
>> dpt->obj = dpt_obj;
>>
>> diff --git a/drivers/gpu/drm/i915/gt/gen8_ppgtt.c b/drivers/gpu/drm/i915/gt/gen8_ppgtt.c
>> index 4daaa6f55668..4197b43150cc 100644
>> --- a/drivers/gpu/drm/i915/gt/gen8_ppgtt.c
>> +++ b/drivers/gpu/drm/i915/gt/gen8_ppgtt.c
>> @@ -55,6 +55,34 @@ static u64 gen8_pte_encode(dma_addr_t addr,
>> return pte;
>> }
>>
>> +static u64 mtl_pte_encode(dma_addr_t addr,
>> + enum i915_cache_level level,
>> + u32 flags)
>> +{
>> + gen8_pte_t pte = addr | GEN8_PAGE_PRESENT | GEN8_PAGE_RW;
>> +
>> + if (unlikely(flags & PTE_READ_ONLY))
>> + pte &= ~GEN8_PAGE_RW;
>> +
>> + if (flags & PTE_LM)
>> + pte |= GEN12_PPGTT_PTE_LM | GEN12_PPGTT_PTE_NC;
>> +
>> + switch (level) {
>> + case I915_CACHE_NONE:
>> + pte |= GEN12_PPGTT_PTE_PAT1;
>> + break;
>> + case I915_CACHE_LLC:
>> + case I915_CACHE_L3_LLC:
>> + pte |= GEN12_PPGTT_PTE_PAT0 | GEN12_PPGTT_PTE_PAT1;
>> + break;
>> + case I915_CACHE_WT:
>> + pte |= GEN12_PPGTT_PTE_PAT0;
>> + break;
>> + }
>
> How are the PAT indices greater then 3 being handled for ppgtt?
The default cachelevels we have will use upto 3 indices only, and also
presently we do not have way to select PAT index, when in future we
support setting PAT Index via VM_BIND we shall extend this as well.
>
>> +
>> + return pte;
>> +}
>> +
>> static void gen8_ppgtt_notify_vgt(struct i915_ppgtt *ppgtt, bool create) {
>> struct drm_i915_private *i915 = ppgtt->vm.i915; @@ -427,7 +455,7 @@ gen8_ppgtt_insert_pte(struct i915_ppgtt *ppgtt,
>> u32 flags)
>> {
>> struct i915_page_directory *pd;
>> - const gen8_pte_t pte_encode = gen8_pte_encode(0, cache_level, flags);
>> + const gen8_pte_t pte_encode = ppgtt->vm.pte_encode(0, cache_level,
>> +flags);
>> gen8_pte_t *vaddr;
>>
>> pd = i915_pd_entry(pdp, gen8_pd_index(idx, 2)); @@ -580,7 +608,7 @@ static void gen8_ppgtt_insert_huge(struct i915_address_space *vm,
>> enum i915_cache_level cache_level,
>> u32 flags)
>> {
>> - const gen8_pte_t pte_encode = gen8_pte_encode(0, cache_level, flags);
>> + const gen8_pte_t pte_encode = vm->pte_encode(0, cache_level, flags);
>> unsigned int rem = sg_dma_len(iter->sg);
>> u64 start = vma_res->start;
>>
>> @@ -743,7 +771,7 @@ static void gen8_ppgtt_insert_entry(struct i915_address_space *vm,
>> GEM_BUG_ON(pt->is_compact);
>>
>> vaddr = px_vaddr(pt);
>> - vaddr[gen8_pd_index(idx, 0)] = gen8_pte_encode(addr, level, flags);
>> + vaddr[gen8_pd_index(idx, 0)] = vm->pte_encode(addr, level, flags);
>> drm_clflush_virt_range(&vaddr[gen8_pd_index(idx, 0)], sizeof(*vaddr)); }
>>
>> @@ -773,7 +801,7 @@ static void __xehpsdv_ppgtt_insert_entry_lm(struct i915_address_space *vm,
>> }
>>
>> vaddr = px_vaddr(pt);
>> - vaddr[gen8_pd_index(idx, 0) / 16] = gen8_pte_encode(addr, level, flags);
>> + vaddr[gen8_pd_index(idx, 0) / 16] = vm->pte_encode(addr, level,
>> +flags);
>> }
>>
>> static void xehpsdv_ppgtt_insert_entry(struct i915_address_space *vm, @@ -820,7 +848,7 @@ static int gen8_init_scratch(struct i915_address_space *vm)
>> pte_flags |= PTE_LM;
>>
>> vm->scratch[0]->encode =
>> - gen8_pte_encode(px_dma(vm->scratch[0]),
>> + vm->pte_encode(px_dma(vm->scratch[0]),
>> I915_CACHE_NONE, pte_flags);
>>
>> for (i = 1; i <= vm->top; i++) {
>> @@ -963,7 +991,10 @@ struct i915_ppgtt *gen8_ppgtt_create(struct intel_gt *gt,
>> */
>> ppgtt->vm.alloc_scratch_dma = alloc_pt_dma;
>>
>> - ppgtt->vm.pte_encode = gen8_pte_encode;
>> + if (GRAPHICS_VER_FULL(gt->i915) >= IP_VER(12, 70))
>> + ppgtt->vm.pte_encode = mtl_pte_encode;
>> + else
>> + ppgtt->vm.pte_encode = gen8_pte_encode;
>>
>> ppgtt->vm.bind_async_flags = I915_VMA_LOCAL_BIND;
>> ppgtt->vm.insert_entries = gen8_ppgtt_insert; diff --git a/drivers/gpu/drm/i915/gt/gen8_ppgtt.h b/drivers/gpu/drm/i915/gt/gen8_ppgtt.h
>> index f541d19264b4..c48f1fc32909 100644
>> --- a/drivers/gpu/drm/i915/gt/gen8_ppgtt.h
>> +++ b/drivers/gpu/drm/i915/gt/gen8_ppgtt.h
>> @@ -19,4 +19,8 @@ u64 gen8_ggtt_pte_encode(dma_addr_t addr,
>> enum i915_cache_level level,
>> u32 flags);
>>
>> +u64 mtl_ggtt_pte_encode(dma_addr_t addr,
>> + enum i915_cache_level level,
>> + u32 flags);
>> +
>> #endif
>> diff --git a/drivers/gpu/drm/i915/gt/intel_ggtt.c b/drivers/gpu/drm/i915/gt/intel_ggtt.c
>> index 8145851ad23d..ffe910694ca0 100644
>> --- a/drivers/gpu/drm/i915/gt/intel_ggtt.c
>> +++ b/drivers/gpu/drm/i915/gt/intel_ggtt.c
>> @@ -237,6 +237,33 @@ static void guc_ggtt_invalidate(struct i915_ggtt *ggtt)
>> intel_uncore_write_fw(uncore, GEN8_GTCR, GEN8_GTCR_INVALIDATE); }
>>
>> +u64 mtl_ggtt_pte_encode(dma_addr_t addr,
>> + enum i915_cache_level level,
>> + u32 flags)
>> +{
>> + gen8_pte_t pte = addr | GEN8_PAGE_PRESENT;
>> +
>> + GEM_BUG_ON(addr & ~GEN12_GGTT_PTE_ADDR_MASK);
>> +
>> + if (flags & PTE_LM)
>> + pte |= GEN12_GGTT_PTE_LM;
>> +
>> + switch (level) {
>> + case I915_CACHE_NONE:
>> + pte |= MTL_GGTT_PTE_PAT1;
>> + break;
>> + case I915_CACHE_LLC:
>> + case I915_CACHE_L3_LLC:
>> + pte |= MTL_GGTT_PTE_PAT0 | MTL_GGTT_PTE_PAT1;
>> + break;
>> + case I915_CACHE_WT:
>> + pte |= MTL_GGTT_PTE_PAT0;
>> + break;
>> + }
>
> PAT index 4 is valid for GGTT, right? which means we need to define
> MTL_GGTT_PTE_PAT2.
No, GGTT at max can use 4 PAT indexes i.e 0 - 3.
Thanks,
Aravind.
>
> -Fei
>
>> +
>> + return pte;
>> +}
>> +
>> u64 gen8_ggtt_pte_encode(dma_addr_t addr,
>> enum i915_cache_level level,
>> u32 flags)
>> @@ -264,7 +291,7 @@ static void gen8_ggtt_insert_page(struct i915_address_space *vm,
>> gen8_pte_t __iomem *pte =
>> (gen8_pte_t __iomem *)ggtt->gsm + offset / I915_GTT_PAGE_SIZE;
>>
>> - gen8_set_pte(pte, gen8_ggtt_pte_encode(addr, level, flags));
>> + gen8_set_pte(pte, ggtt->vm.pte_encode(addr, level, flags));
>>
>> ggtt->invalidate(ggtt);
>> }
>> @@ -274,8 +301,8 @@ static void gen8_ggtt_insert_entries(struct i915_address_space *vm,
>> enum i915_cache_level level,
>> u32 flags)
>> {
>> - const gen8_pte_t pte_encode = gen8_ggtt_pte_encode(0, level, flags);
>> struct i915_ggtt *ggtt = i915_vm_to_ggtt(vm);
>> + const gen8_pte_t pte_encode = ggtt->vm.pte_encode(0, level, flags);
>> gen8_pte_t __iomem *gte;
>> gen8_pte_t __iomem *end;
>> struct sgt_iter iter;
>> @@ -984,7 +1011,10 @@ static int gen8_gmch_probe(struct i915_ggtt *ggtt)
>> ggtt->vm.vma_ops.bind_vma = intel_ggtt_bind_vma;
>> ggtt->vm.vma_ops.unbind_vma = intel_ggtt_unbind_vma;
>>
>> - ggtt->vm.pte_encode = gen8_ggtt_pte_encode;
>> + if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 70))
>> + ggtt->vm.pte_encode = mtl_ggtt_pte_encode;
>> + else
>> + ggtt->vm.pte_encode = gen8_ggtt_pte_encode;
>>
>> setup_private_pat(ggtt->vm.gt);
>>
>> diff --git a/drivers/gpu/drm/i915/gt/intel_gtt.h b/drivers/gpu/drm/i915/gt/intel_gtt.h
>> index 43bf9188ffef..450ed0541d0f 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 GEN12_PPGTT_PTE_PAT3 BIT_ULL(62)
>> #define GEN12_PPGTT_PTE_LM BIT_ULL(11)
>> -
>> -#define GEN12_GGTT_PTE_LM BIT_ULL(1)
>> +#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 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)
>> --
>> 2.25.1
