48b PPGTT
Subsystems (3)
cover 48b PPGTT
In order expand the GPU address space, a 4th level translation is added, the Page Map Level 4 (PML4). This PML4 has 256 PML4 Entries (PML4E), PML4[0-255], each pointing to a PDP. All the existing "dynamic alloc ppgtt" functions are used, only adding the 4th level changes. I also updated some remaining variables that were 32b only.
There are 2 hardware workarounds needed to allow correct operation with 48b addresses (Wa32bitGeneralStateOffset & Wa32bitInstructionBaseOffset). I added a flag (EXEC_OBJECT_NEEDS_32BADDRESS) that will indicate if a given object must be allocated inside the first 4 PDPs, and in order to limit the chances of having the first 4GB already full, objects not requiring this workaround start at an offset of this range. Another option would be to send the DRM_MM_CREATE_TOP flag. I'm also including an igt test for this change.
This feature is only available in BDW and Gen9, and requires LRC submission mode (execlists) and setting i915.enable_ppgtt=3.
Also note that this expanded address space is only available for full PPGTT, aliasing PPGTT remains 32b.
Finally, Mika has sent some PPGTT clean up patches, which will conflict with these. I'm open to rebase these patches after Mika's, or update his patches after the 48b ones. Please let me know which option is better.
Michel Thierry (16):
drm/i915: Remove unnecessary gen8_clamp_pd
drm/i915/gen8: Make pdp allocation more dynamic drm/i915/gen8: Abstract PDP usage
drm/i915/gen8: Add dynamic page trace events drm/i915/gen8: implement alloc/free for 4lvl drm/i915/gen8: Add 4 level switching infrastructure and lrc support drm/i915/gen8: Generalize PTE writing for GEN8 PPGTT drm/i915: Plumb sg_iter through va allocation ->maps drm/i915/gen8: Add 4 level support in insert_entries and clear_range drm/i915/gen8: Initialize PDPs
drm/i915: Expand error state's address width to 64b drm/i915/gen8: Add ppgtt info and debug_dump
drm/i915: object size needs to be u64
drm/i915: Check against correct user_size limit in 48b ppgtt mode drm/i915: Wa32bitGeneralStateOffset & Wa32bitInstructionBaseOffset drm/i915/gen8: Flip the 48b switch
drivers/gpu/drm/i915/i915_debugfs.c | 18 +- drivers/gpu/drm/i915/i915_drv.h | 12 +- drivers/gpu/drm/i915/i915_gem.c | 16 +- drivers/gpu/drm/i915/i915_gem_execbuffer.c | 3 + drivers/gpu/drm/i915/i915_gem_gtt.c | 740 ++++++++++++++++++++++++----- drivers/gpu/drm/i915/i915_gem_gtt.h | 70 ++- drivers/gpu/drm/i915/i915_gem_userptr.c | 12 +- drivers/gpu/drm/i915/i915_gpu_error.c | 17 +- drivers/gpu/drm/i915/i915_params.c | 2 +- drivers/gpu/drm/i915/i915_reg.h | 1 + drivers/gpu/drm/i915/i915_trace.h | 16 + drivers/gpu/drm/i915/intel_lrc.c | 50 +- include/uapi/drm/i915_drm.h | 3 +- 13 files changed, 797 insertions(+), 163 deletions(-)
Signature · 6 lines
2.4.0 _______________________________________________ Intel-gfx mailing list [email protected] http://lists.freedesktop.org/mailman/listinfo/intel-gfx
PATCH 1/16 drm/i915: Remove unnecessary gen8_clamp_pd
gen8_clamp_pd clamps to the next page directory boundary, but the macro gen8_for_each_pde already has a check to stop at the page directory boundary.
Furthermore, i915_pte_count also restricts to the next page table boundary.
--- drivers/gpu/drm/i915/i915_gem_gtt.c | 2 +- drivers/gpu/drm/i915/i915_gem_gtt.h | 11 ----------- 2 files changed, 1 insertion(+), 12 deletions(-)
drivers/gpu/drm/i915/i915_gem_gtt.c +1 -1
@@ -878,7 +878,7 @@ static int gen8_alloc_va_range(struct i915_address_space *vm,gen8_for_each_pdpe (pd, &ppgtt->pdp, start, length, temp, pdpe) {gen8_pde_t *const page_directory =kmap_atomic (pd->page);struct i915_page_table *pt; -uint64_t pd_len =gen8_clamp_pd (start, length); +uint64_t pd_len = length;uint64_t pd_start = start;uint32_t pde;
drivers/gpu/drm/i915/i915_gem_gtt.h +0 -11
@@ -431,17 +431,6 @@ static inline uint32_t gen6_pde_index(uint32_t addr) temp = min(temp, length), \ start += temp, length -= temp) -/* Clamp length to the next page_directory boundary */ -static inline uint64_t gen8_clamp_pd (uint64_t start,uint64_t length) -{ -uint64_t next_pd =ALIGN (start +1 ,1 <<GEN8_PDPE_SHIFT ); - -if (next_pd > (start + length)) -return length; - -return next_pd - start; -} -static inline uint32_t gen8_pte_index (uint64_t address) {return i915_pte_index (address,GEN8_PDE_SHIFT );
Signature · 6 lines
2.4.0 _______________________________________________ Intel-gfx mailing list [email protected] http://lists.freedesktop.org/mailman/listinfo/intel-gfx
PATCH 2/16 drm/i915/gen8: Make pdp allocation more dynamic
In reply to Michel ThierryThis transitional patch doesn't do much for the existing code. However, it should make upcoming patches to use the full 48b address space a bit easier. The patch also introduces the PML4, ie. the new top level structure of the page tables.
v2: Renamed pdp_free to be similar to pd/pt (unmap_and_free_pdp).
v3: To facilitate testing, 48b mode will be available on Broadwell and GEN9+, when i915.enable_ppgtt = 3.
v4: Rebase after s/page_tables/page_table/ and added extra information about 4-level page table formats.
--- drivers/gpu/drm/i915/i915_drv.h | 7 ++- drivers/gpu/drm/i915/i915_gem_gtt.c | 107 +++++++++++++++++++++++++++++------- drivers/gpu/drm/i915/i915_gem_gtt.h | 45 ++++++++++++--- 3 files changed, 129 insertions(+), 30 deletions(-)
drivers/gpu/drm/i915/i915_drv.h +6 -1
@@ -2436,7 +2436,12 @@ struct drm_i915_cmd_table {#define HAS_HW_CONTEXTS (dev) (INTEL_INFO(dev)->gen >= 6)#define HAS_LOGICAL_RING_CONTEXTS (dev) (INTEL_INFO(dev)->gen >= 8)#define USES_PPGTT (dev) (i915.enable_ppgtt) -#define USES_FULL_PPGTT (dev) (i915.enable_ppgtt == 2) +#define USES_FULL_PPGTT (dev) (i915.enable_ppgtt >= 2) +#ifdef CONFIG_64BIT +# define USES_FULL_48BIT_PPGTT (dev) (i915.enable_ppgtt == 3) +#else +# define USES_FULL_48BIT_PPGTT (dev) false +#endif #define HAS_OVERLAY (dev) (INTEL_INFO(dev)->has_overlay)#define OVERLAY_NEEDS_PHYSICAL (dev) (INTEL_INFO(dev)->overlay_needs_physical)
drivers/gpu/drm/i915/i915_gem_gtt.c +87 -20
239 lines not on this page · raw message
drivers/gpu/drm/i915/i915_gem_gtt.h +36 -9
82 lines not on this page · raw message
Signature · 6 lines
2.4.0 _______________________________________________ Intel-gfx mailing list [email protected] http://lists.freedesktop.org/mailman/listinfo/intel-gfx
PATCH 3/16 drm/i915/gen8: Abstract PDP usage
In reply to Michel ThierryUp until now, ppgtt->pdp has always been the root of our page tables. Legacy 32b addresses acted like it had 1 PDP with 4 PDPEs.
In preparation for 4 level page tables, we need to stop use ppgtt->pdp directly unless we know it's what we want. The future structure will use ppgtt->pml4 for the top level, and the pdp is just one of the entries being pointed to by a pml4e.
v2: Updated after dynamic page allocation changes.
v3: Rebase after s/page_tables/page_table/.
v4: Rebase after changes in "Dynamic page table allocations" patch.
--- drivers/gpu/drm/i915/i915_gem_gtt.c | 141 +++++++++++++++++++++++------------- 1 file changed, 90 insertions(+), 51 deletions(-)
drivers/gpu/drm/i915/i915_gem_gtt.c +90 -51
@@ -550,6 +550,7 @@ static void gen8_ppgtt_clear_range(struct i915_address_space *vm, {struct i915_hw_ppgtt *ppgtt = container_of(vm, struct i915_hw_ppgtt, base); +struct i915_page_directory_pointer *pdp = &ppgtt->pdp;/* FIXME: 48b */ gen8_pte_t *pt_vaddr, scratch_pte;unsigned pdpe = start >>GEN8_PDPE_SHIFT &GEN8_PDPE_MASK ;unsigned pde = start >>GEN8_PDE_SHIFT &GEN8_PDE_MASK ;
@@ -565,10 +566,10 @@ static void gen8_ppgtt_clear_range(struct i915_address_space *vm,struct i915_page_table *pt;struct page *page_table; -if (WARN_ON (!ppgtt->pdp.page_directory[pdpe])) +if (WARN_ON (!pdp->page_directory[pdpe]))continue ; - pd = ppgtt->pdp.page_directory[pdpe]; + pd = pdp->page_directory[pdpe];if (WARN_ON (!pd->page_table[pde]))continue ;
@@ -610,6 +611,7 @@ static void gen8_ppgtt_insert_entries(struct i915_address_space *vm, {struct i915_hw_ppgtt *ppgtt = container_of(vm, struct i915_hw_ppgtt, base); +struct i915_page_directory_pointer *pdp = &ppgtt->pdp;/* FIXME: 48b */ gen8_pte_t *pt_vaddr;unsigned pdpe = start >>GEN8_PDPE_SHIFT &GEN8_PDPE_MASK ;unsigned pde = start >>GEN8_PDE_SHIFT &GEN8_PDE_MASK ;
@@ -620,7 +622,7 @@ static void gen8_ppgtt_insert_entries(struct i915_address_space *vm,for_each_sg_page (pages->sgl, &sg_iter, pages->nents,0 ) {if (pt_vaddr ==NULL ) { -struct i915_page_directory *pd = ppgtt->pdp.page_directory[pdpe]; +struct i915_page_directory *pd = pdp->page_directory[pdpe];struct i915_page_table *pt = pd->page_table[pde];struct page *page_table = pt->page;
@@ -675,6 +677,28 @@ static void gen8_initialize_pd(struct i915_address_space *vm,if (!HAS_LLC (vm->dev))drm_clflush_virt_range (page_directory,PAGE_SIZE ); + +kunmap_atomic (page_directory); +} + +/* It's likely we'll map more than one pagetable at a time. This function will +* save us unnecessary kmap calls, but do no more functionally than multiple +* calls to map_pt. */ +static void gen8_map_pagetable_range (struct i915_page_directory *pd, +uint64_t start, +uint64_t length, +struct drm_device *dev) +{ +gen8_pde_t *const page_directory =kmap_atomic (pd->page); +struct i915_page_table *pt; +uint64_t temp, pde; + +gen8_for_each_pde (pt, pd, start, length, temp, pde) +__gen8_do_map_pt (page_directory + pde, pt, dev); + +if (!HAS_LLC (dev)) +drm_clflush_virt_range (page_directory,PAGE_SIZE ); +kunmap_atomic (page_directory); }
@@ -700,23 +724,29 @@ static void gen8_ppgtt_cleanup(struct i915_address_space *vm) container_of(vm, struct i915_hw_ppgtt, base);int i; -for_each_set_bit (i, ppgtt->pdp.used_pdpes, -I915_PDPES_PER_PDP (ppgtt->base.dev)) { -if (WARN_ON (!ppgtt->pdp.page_directory[i])) -continue ; +if (!USES_FULL_48BIT_PPGTT (ppgtt->base.dev)) { +for_each_set_bit (i, ppgtt->pdp.used_pdpes, +I915_PDPES_PER_PDP (ppgtt->base.dev)) { +if (WARN_ON (!ppgtt->pdp.page_directory[i])) +continue ; -gen8_free_page_tables (ppgtt->pdp.page_directory[i], ppgtt->base.dev); -unmap_and_free_pd (ppgtt->pdp.page_directory[i], ppgtt->base.dev); +gen8_free_page_tables (ppgtt->pdp.page_directory[i], + ppgtt->base.dev); +unmap_and_free_pd (ppgtt->pdp.page_directory[i], + ppgtt->base.dev); + } +unmap_and_free_pdp (&ppgtt->pdp, ppgtt->base.dev); + }else { +WARN_ON (1 );/* to be implemented later */ } -unmap_and_free_pdp (&ppgtt->pdp, ppgtt->base.dev);unmap_and_free_pd (ppgtt->scratch_pd, ppgtt->base.dev);unmap_and_free_pt (ppgtt->scratch_pt, ppgtt->base.dev); }/** * gen8_ppgtt_alloc_pagetabs() - Allocate page tables for VA range. -* @ppgtt: Master ppgtt structure. +* @vm: Master vm structure. * @pd: Page directory for this address range. * @start: Starting virtual address to begin allocations. * @length Size of the allocations.
@@ -732,13 +762,15 @@ static void gen8_ppgtt_cleanup(struct i915_address_space *vm)* * Return: 0 if success; negative error code otherwise. */ -static int gen8_ppgtt_alloc_pagetabs (struct i915_hw_ppgtt *ppgtt, +static int gen8_ppgtt_alloc_pagetabs (struct i915_address_space *vm,struct i915_page_directory *pd,uint64_t start,uint64_t length,unsigned long *new_pts) { -struct drm_device *dev = ppgtt->base.dev; +struct i915_hw_ppgtt *ppgtt = + container_of(vm, struct i915_hw_ppgtt, base); +struct drm_device *dev = vm->dev;struct i915_page_table *pt;uint64_t temp;uint32_t pde;
@@ -755,7 +787,7 @@ static int gen8_ppgtt_alloc_pagetabs(struct i915_hw_ppgtt *ppgtt,if (IS_ERR (pt)) goto unwind_out; -gen8_initialize_pt (&ppgtt->base, pt); +gen8_initialize_pt (vm, pt); pd->page_table[pde] = pt;set_bit (pde, new_pts); }
@@ -771,7 +803,7 @@ unwind_out:/** * gen8_ppgtt_alloc_page_directories() - Allocate page directories for VA range. -* @ppgtt: Master ppgtt structure. +* @vm: Master vm structure. * @pdp: Page directory pointer for this address range. * @start: Starting virtual address to begin allocations. * @length Size of the allocations.
@@ -792,17 +824,18 @@ unwind_out:* * Return: 0 if success; negative error code otherwise. */ -static int gen8_ppgtt_alloc_page_directories (struct i915_hw_ppgtt *ppgtt, -struct i915_page_directory_pointer *pdp, -uint64_t start, -uint64_t length, -unsigned long *new_pds) +static int +gen8_ppgtt_alloc_page_directories (struct i915_address_space *vm, +struct i915_page_directory_pointer *pdp, +uint64_t start, +uint64_t length, +unsigned long *new_pds) { -struct drm_device *dev = ppgtt->base.dev; +struct drm_device *dev = vm->dev;struct i915_page_directory *pd;uint64_t temp;uint32_t pdpe; -size_t pdpes =I915_PDPES_PER_PDP (ppgtt->base.dev); +size_t pdpes =I915_PDPES_PER_PDP (vm->dev);WARN_ON (!bitmap_empty (new_pds, pdpes));
@@ -817,7 +850,7 @@ static int gen8_ppgtt_alloc_page_directories(struct i915_hw_ppgtt *ppgtt,if (IS_ERR (pd)) goto unwind_out; -gen8_initialize_pd (&ppgtt->base, pd); +gen8_initialize_pd (vm, pd); pdp->page_directory[pdpe] = pd;set_bit (pdpe, new_pds); }
@@ -882,13 +915,13 @@ err_out:return -ENOMEM ; } -static int gen8_alloc_va_range (struct i915_address_space *vm, -uint64_t start, -uint64_t length) +static int gen8_alloc_va_range_3lvl (struct i915_address_space *vm, +struct i915_page_directory_pointer *pdp, +uint64_t start, +uint64_t length) { -struct i915_hw_ppgtt *ppgtt = - container_of(vm, struct i915_hw_ppgtt, base);unsigned long *new_page_dirs, **new_page_tables; +struct drm_device *dev = vm->dev;struct i915_page_directory *pd;const uint64_t orig_start = start;const uint64_t orig_length = length;
@@ -908,16 +941,14 @@ static int gen8_alloc_va_range(struct i915_address_space *vm,return ret;/* Do the allocations first so we can easily bail out */ - ret =gen8_ppgtt_alloc_page_directories (ppgtt, &ppgtt->pdp, start, length, - new_page_dirs); + ret =gen8_ppgtt_alloc_page_directories (vm, pdp, start, length, new_page_dirs);if (ret) {free_gen8_temp_bitmaps (new_page_dirs, new_page_tables, pdpes);return ret; } -/* For every page directory referenced, allocate page tables */ -gen8_for_each_pdpe (pd, &ppgtt->pdp, start, length, temp, pdpe) { - ret =gen8_ppgtt_alloc_pagetabs (ppgtt, pd, start, length, +gen8_for_each_pdpe (pd, pdp, start, length, temp, pdpe) { + ret =gen8_ppgtt_alloc_pagetabs (vm, pd, start, length, new_page_tables[pdpe]);if (ret) goto err_out;
@@ -926,10 +957,7 @@ static int gen8_alloc_va_range(struct i915_address_space *vm, start = orig_start; length = orig_length; -/* Allocations have completed successfully, so set the bitmaps, and do -* the mappings. */ -gen8_for_each_pdpe (pd, &ppgtt->pdp, start, length, temp, pdpe) { -gen8_pde_t *const page_directory =kmap_atomic (pd->page); +gen8_for_each_pdpe (pd, pdp, start, length, temp, pdpe) {struct i915_page_table *pt;uint64_t pd_len = length;uint64_t pd_start = start;
@@ -951,20 +979,10 @@ static int gen8_alloc_va_range(struct i915_address_space *vm,/* Our pde is now pointing to the pagetable, pt */ set_bit (pde, pd->used_pdes); - -/* Map the PDE to the page table */ -__gen8_do_map_pt (page_directory + pde, pt, vm->dev); - -/* NB: We haven't yet mapped ptes to pages. At this -* point we're still relying on insert_entries() */ } -if (!HAS_LLC (vm->dev)) -drm_clflush_virt_range (page_directory,PAGE_SIZE ); - -kunmap_atomic (page_directory); - -set_bit (pdpe, ppgtt->pdp.used_pdpes); +set_bit (pdpe, pdp->used_pdpes); +gen8_map_pagetable_range (pd, start, length, dev); }free_gen8_temp_bitmaps (new_page_dirs, new_page_tables, pdpes);
@@ -973,16 +991,37 @@ static int gen8_alloc_va_range(struct i915_address_space *vm, err_out:while (pdpe--) {for_each_set_bit (temp, new_page_tables[pdpe],I915_PDES ) -unmap_and_free_pt (ppgtt->pdp.page_directory[pdpe]->page_table[temp], vm->dev); +unmap_and_free_pt (pdp->page_directory[pdpe]->page_table[temp], dev); }for_each_set_bit (pdpe, new_page_dirs, pdpes) -unmap_and_free_pd (ppgtt->pdp.page_directory[pdpe], vm->dev); +unmap_and_free_pd (pdp->page_directory[pdpe], dev);free_gen8_temp_bitmaps (new_page_dirs, new_page_tables, pdpes);return ret; } +static int gen8_alloc_va_range_4lvl (struct i915_address_space *vm, +struct i915_pml4 *pml4, +uint64_t start, +uint64_t length) +{ +WARN_ON (1 );/* to be implemented later */ +return 0 ; +} + +static int gen8_alloc_va_range (struct i915_address_space *vm, +uint64_t start,uint64_t length) +{ +struct i915_hw_ppgtt *ppgtt = + container_of(vm, struct i915_hw_ppgtt, base); + +if (!USES_FULL_48BIT_PPGTT (vm->dev)) +return gen8_alloc_va_range_3lvl (vm, &ppgtt->pdp, start, length); +else +return gen8_alloc_va_range_4lvl (vm, &ppgtt->pml4, start, length); +} +/* * GEN8 legacy ppgtt programming is accomplished through a max 4 PDP registers * with a net effect resembling a 2-level page table in normal x86 terms. Each
Signature · 6 lines
2.4.0 _______________________________________________ Intel-gfx mailing list [email protected] http://lists.freedesktop.org/mailman/listinfo/intel-gfx
PATCH 4/16 drm/i915/gen8: Add dynamic page trace events
In reply to Michel ThierryThe dynamic page allocation patch series added it for GEN6, this patch adds them for GEN8.
v2: Consolidate pagetable/page_directory events
v3: Multiple rebases.
v4: Rebase after s/page_tables/page_table/.
--- drivers/gpu/drm/i915/i915_gem_gtt.c | 21 ++++++++++++++------- drivers/gpu/drm/i915/i915_trace.h | 16 ++++++++++++++++ 2 files changed, 30 insertions(+), 7 deletions(-)
drivers/gpu/drm/i915/i915_gem_gtt.c +14 -7
@@ -684,19 +684,24 @@ static void gen8_initialize_pd(struct i915_address_space *vm,/* It's likely we'll map more than one pagetable at a time. This function will * save us unnecessary kmap calls, but do no more functionally than multiple * calls to map_pt. */ -static void gen8_map_pagetable_range (struct i915_page_directory *pd, +static void gen8_map_pagetable_range (struct i915_address_space *vm, +struct i915_page_directory *pd,uint64_t start, -uint64_t length, -struct drm_device *dev) +uint64_t length) {gen8_pde_t *const page_directory =kmap_atomic (pd->page);struct i915_page_table *pt;uint64_t temp, pde; -gen8_for_each_pde (pt, pd, start, length, temp, pde) -__gen8_do_map_pt (page_directory + pde, pt, dev); +gen8_for_each_pde (pt, pd, start, length, temp, pde) { +__gen8_do_map_pt (page_directory + pde, pt, vm->dev); +trace_i915_page_table_entry_map (vm, pde, pt, +gen8_pte_index (start), +gen8_pte_count (start, length), +GEN8_PTES ); + } -if (!HAS_LLC (dev)) +if (!HAS_LLC (vm->dev))drm_clflush_virt_range (page_directory,PAGE_SIZE );kunmap_atomic (page_directory);
@@ -790,6 +795,7 @@ static int gen8_ppgtt_alloc_pagetabs(struct i915_address_space *vm,gen8_initialize_pt (vm, pt); pd->page_table[pde] = pt;set_bit (pde, new_pts); +trace_i915_page_table_entry_alloc (vm, pde, start,GEN8_PDE_SHIFT ); }return 0 ;
@@ -853,6 +859,7 @@ gen8_ppgtt_alloc_page_directories(struct i915_address_space *vm,gen8_initialize_pd (vm, pd); pdp->page_directory[pdpe] = pd;set_bit (pdpe, new_pds); +trace_i915_page_directory_entry_alloc (vm, pdpe, start,GEN8_PDPE_SHIFT ); }return 0 ;
@@ -982,7 +989,7 @@ static int gen8_alloc_va_range_3lvl(struct i915_address_space *vm, }set_bit (pdpe, pdp->used_pdpes); -gen8_map_pagetable_range (pd, start, length, dev); +gen8_map_pagetable_range (vm, pd, start, length); }free_gen8_temp_bitmaps (new_page_dirs, new_page_tables, pdpes);
drivers/gpu/drm/i915/i915_trace.h +16 -0
@@ -213,6 +213,22 @@ DEFINE_EVENT(i915_page_table_entry, i915_page_table_entry_alloc,TP_ARGS (vm, pde, start, pde_shift) ); +DEFINE_EVENT_PRINT (i915_page_table_entry, i915_page_directory_entry_alloc, + TP_PROTO(struct i915_address_space *vm, u32 pdpe, u64 start, u64 pdpe_shift), +TP_ARGS (vm, pdpe, start, pdpe_shift), + +TP_printk ("vm=%p, pdpe=%d (0x%llx-0x%llx)" , + __entry->vm, __entry->pde, __entry->start, __entry->end) +); + +DEFINE_EVENT_PRINT (i915_page_table_entry, i915_page_directory_pointer_entry_alloc, + TP_PROTO(struct i915_address_space *vm, u32 pml4e, u64 start, u64 pml4e_shift), +TP_ARGS (vm, pml4e, start, pml4e_shift), + +TP_printk ("vm=%p, pml4e=%d (0x%llx-0x%llx)" , + __entry->vm, __entry->pde, __entry->start, __entry->end) +); +/* Avoid extra math because we only support two sizes. The format is defined by * bitmap_scnprintf. Each 32 bits is 8 HEX digits followed by comma */ #define TRACE_PT_SIZE (bits) \
Signature · 6 lines
2.4.0 _______________________________________________ Intel-gfx mailing list [email protected] http://lists.freedesktop.org/mailman/listinfo/intel-gfx
PATCH 5/16 drm/i915/gen8: implement alloc/free for 4lvl
In reply to Michel ThierryPML4 has no special attributes, and there will always be a PML4. So simply initialize it at creation, and destroy it at the end.
The code for 4lvl is able to call into the existing 3lvl page table code to handle all of the lower levels.
v2: Return something at the end of gen8_alloc_va_range_4lvl to keep the compiler happy. And define ret only in one place.
Updated gen8_ppgtt_unmap_pages and gen8_ppgtt_free to handle 4lvl.
v3: Use i915_dma_unmap_single instead of pci API. Fix a couple of incorrect checks when unmapping pdp and pd pages (Akash).
v4: Call __pdp_fini also for 32b PPGTT. Clean up alloc_pdp_single param list.
v5: Prevent (harmless) out of range access in gen8_for_each_pml4e.
v6: Simplify alloc_vma_range_4lvl and gen8_ppgtt_init_common error paths. (Akash)
v7: Rebase, s/gen8_ppgtt_free_*/gen8_ppgtt_cleanup_*/.
v8: Change location of pml4_init/fini. It will make next patches cleaner.
--- drivers/gpu/drm/i915/i915_gem_gtt.c | 198 ++++++++++++++++++++++++++++++------ drivers/gpu/drm/i915/i915_gem_gtt.h | 12 ++- 2 files changed, 177 insertions(+), 33 deletions(-)
drivers/gpu/drm/i915/i915_gem_gtt.c +167 -31
@@ -474,8 +474,12 @@ static void unmap_and_free_pdp(struct i915_page_directory_pointer *pdp, struct drm_device *dev) {__pdp_fini (pdp); -if (USES_FULL_48BIT_PPGTT (dev)) + +if (USES_FULL_48BIT_PPGTT (dev)) { +i915_dma_unmap_single (pdp, dev); +__free_page (pdp->page);kfree (pdp); + } } static int __pdp_init(struct i915_page_directory_pointer *pdp,
@@ -501,6 +505,37 @@ static int __pdp_init(struct i915_page_directory_pointer *pdp,return 0 ; } +static struct +i915_page_directory_pointer *alloc_pdp_single (struct i915_hw_ppgtt *ppgtt) +{ +struct drm_device *dev = ppgtt->base.dev; +struct i915_page_directory_pointer *pdp; +int ret; + +WARN_ON (!USES_FULL_48BIT_PPGTT (dev)); + + pdp =kmalloc (sizeof (*pdp),GFP_KERNEL ); +if (!pdp) +return ERR_PTR (-ENOMEM ); + + pdp->page =alloc_page (GFP_KERNEL |GFP_DMA32 | __GFP_ZERO); +if (!pdp->page) { +kfree (pdp); +return ERR_PTR (-ENOMEM ); + } + + ret =__pdp_init (pdp, dev); +if (ret) { +__free_page (pdp->page); +kfree (pdp); +return ERR_PTR (ret); + } + +i915_dma_map_single (pdp, dev); + +return pdp; +} +/* Broadwell Page Directory Pointer Descriptors */ static int gen8_write_pdp(struct intel_engine_cs *ring, unsigned entry,
@@ -681,6 +716,28 @@ static void gen8_initialize_pd(struct i915_address_space *vm,kunmap_atomic (page_directory); } +static void pml4_fini (struct i915_pml4 *pml4) +{ +struct i915_hw_ppgtt *ppgtt = + container_of(pml4, struct i915_hw_ppgtt, pml4); +i915_dma_unmap_single (pml4, ppgtt->base.dev); +__free_page (pml4->page); + pml4->page =NULL ; +} + +static int pml4_init (struct i915_hw_ppgtt *ppgtt) +{ +struct i915_pml4 *pml4 = &ppgtt->pml4; + + pml4->page =alloc_page (GFP_KERNEL | __GFP_ZERO); +if (!pml4->page) +return -ENOMEM ; + +i915_dma_map_single (pml4, ppgtt->base.dev); + +return 0 ; +} +/* It's likely we'll map more than one pagetable at a time. This function will * save us unnecessary kmap calls, but do no more functionally than multiple * calls to map_pt. */
@@ -723,28 +780,46 @@ static void gen8_free_page_tables(struct i915_page_directory *pd, struct drm_dev } } -static void gen8_ppgtt_cleanup (struct i915_address_space *vm) +static void gen8_ppgtt_cleanup_3lvl (struct i915_page_directory_pointer *pdp, +struct drm_device *dev) { -struct i915_hw_ppgtt *ppgtt = - container_of(vm, struct i915_hw_ppgtt, base);int i; -if (!USES_FULL_48BIT_PPGTT (ppgtt->base.dev)) { -for_each_set_bit (i, ppgtt->pdp.used_pdpes, -I915_PDPES_PER_PDP (ppgtt->base.dev)) { -if (WARN_ON (!ppgtt->pdp.page_directory[i])) -continue ; +for_each_set_bit (i, pdp->used_pdpes,I915_PDPES_PER_PDP (dev)) { +if (WARN_ON (!pdp->page_directory[i])) +continue ; -gen8_free_page_tables (ppgtt->pdp.page_directory[i], - ppgtt->base.dev); -unmap_and_free_pd (ppgtt->pdp.page_directory[i], - ppgtt->base.dev); - } -unmap_and_free_pdp (&ppgtt->pdp, ppgtt->base.dev); - }else { -WARN_ON (1 );/* to be implemented later */ +gen8_free_page_tables (pdp->page_directory[i], dev); +unmap_and_free_pd (pdp->page_directory[i], dev); } +unmap_and_free_pdp (pdp, dev); +} + +static void gen8_ppgtt_cleanup_4lvl (struct i915_hw_ppgtt *ppgtt) +{ +int i; + +for_each_set_bit (i, ppgtt->pml4.used_pml4es,GEN8_PML4ES_PER_PML4 ) { +if (WARN_ON (!ppgtt->pml4.pdps[i])) +continue ; + +gen8_ppgtt_cleanup_3lvl (ppgtt->pml4.pdps[i], ppgtt->base.dev); + } + +pml4_fini (&ppgtt->pml4); +} + +static void gen8_ppgtt_cleanup (struct i915_address_space *vm) +{ +struct i915_hw_ppgtt *ppgtt = + container_of(vm, struct i915_hw_ppgtt, base); + +if (!USES_FULL_48BIT_PPGTT (ppgtt->base.dev)) +gen8_ppgtt_cleanup_3lvl (&ppgtt->pdp, ppgtt->base.dev); +else +gen8_ppgtt_cleanup_4lvl (ppgtt); +unmap_and_free_pd (ppgtt->scratch_pd, ppgtt->base.dev);unmap_and_free_pt (ppgtt->scratch_pt, ppgtt->base.dev); }
@@ -1013,8 +1088,62 @@ static int gen8_alloc_va_range_4lvl(struct i915_address_space *vm,uint64_t start, uint64_t length) { -WARN_ON (1 );/* to be implemented later */ +DECLARE_BITMAP (new_pdps ,GEN8_PML4ES_PER_PML4 ); +struct i915_hw_ppgtt *ppgtt = + container_of(vm, struct i915_hw_ppgtt, base); +struct i915_page_directory_pointer *pdp; +const uint64_t orig_start = start; +const uint64_t orig_length = length; +uint64_t temp, pml4e; +int ret =0 ; + +/* Do the pml4 allocations first, so we don't need to track the newly +* allocated tables below the pdp */ +bitmap_zero (new_pdps,GEN8_PML4ES_PER_PML4 ); + +/* The pagedirectory and pagetable allocations are done in the shared 3 +* and 4 level code. Just allocate the pdps. +*/ +gen8_for_each_pml4e (pdp, pml4, start, length, temp, pml4e) { +if (!pdp) { +WARN_ON (test_bit (pml4e, pml4->used_pml4es)); + pdp =alloc_pdp_single (ppgtt); +if (IS_ERR (pdp)) + goto err_out; + + pml4->pdps[pml4e] = pdp; +set_bit (pml4e, new_pdps); +trace_i915_page_directory_pointer_entry_alloc (&ppgtt->base, pml4e, + pml4e <<GEN8_PML4E_SHIFT , +GEN8_PML4E_SHIFT ); + } + } + +WARN (bitmap_weight (new_pdps,GEN8_PML4ES_PER_PML4 ) >2 , +"The allocation has spanned more than 512GB. " +"It is highly likely this is incorrect." ); + + start = orig_start; + length = orig_length; + +gen8_for_each_pml4e (pdp, pml4, start, length, temp, pml4e) { +WARN_ON (!pdp); + + ret =gen8_alloc_va_range_3lvl (vm, pdp, start, length); +if (ret) + goto err_out; + } + +bitmap_or (pml4->used_pml4es, new_pdps, pml4->used_pml4es, +GEN8_PML4ES_PER_PML4 ); +return 0 ; + +err_out: +for_each_set_bit (pml4e, new_pdps,GEN8_PML4ES_PER_PML4 ) +gen8_ppgtt_cleanup_3lvl (pml4->pdps[pml4e], vm->dev); + +return ret; } static int gen8_alloc_va_range(struct i915_address_space *vm,
@@ -1023,10 +1152,10 @@ static int gen8_alloc_va_range(struct i915_address_space *vm,struct i915_hw_ppgtt *ppgtt = container_of(vm, struct i915_hw_ppgtt, base); -if (!USES_FULL_48BIT_PPGTT (vm->dev)) -return gen8_alloc_va_range_3lvl (vm, &ppgtt->pdp, start, length); -else +if (USES_FULL_48BIT_PPGTT (vm->dev))return gen8_alloc_va_range_4lvl (vm, &ppgtt->pml4, start, length); +else +return gen8_alloc_va_range_3lvl (vm, &ppgtt->pdp, start, length); }/*
@@ -1038,6 +1167,8 @@ static int gen8_alloc_va_range(struct i915_address_space *vm,*/ static int gen8_ppgtt_init (struct i915_hw_ppgtt *ppgtt) { +int ret; + ppgtt->scratch_pt =alloc_pt_single (ppgtt->base.dev);if (IS_ERR (ppgtt->scratch_pt))return PTR_ERR (ppgtt->scratch_pt);
@@ -1049,19 +1180,19 @@ static int gen8_ppgtt_init(struct i915_hw_ppgtt *ppgtt)gen8_initialize_pt (&ppgtt->base, ppgtt->scratch_pt);gen8_initialize_pd (&ppgtt->base, ppgtt->scratch_pd); -if (!USES_FULL_48BIT_PPGTT (ppgtt->base.dev)) { -int ret =__pdp_init (&ppgtt->pdp, false); +if (USES_FULL_48BIT_PPGTT (ppgtt->base.dev)) { + ret =pml4_init (ppgtt); +if (ret) + goto err_out; -if (ret) { -unmap_and_free_pd (ppgtt->scratch_pd, ppgtt->base.dev); -unmap_and_free_pt (ppgtt->scratch_pt, ppgtt->base.dev); -return ret; - } + ppgtt->base.total =1ULL <<48 ; + }else { + ret =__pdp_init (&ppgtt->pdp, false); +if (ret) + goto err_out; ppgtt->base.total =1ULL <<32 ; - }else { - ppgtt->base.total =1ULL <<48 ; -return -EPERM ;/* Not yet implemented */ +trace_i915_page_directory_pointer_entry_alloc (&ppgtt->base,0 ,0 ,GEN8_PML4E_SHIFT ); } ppgtt->base.start =0 ;
@@ -1075,6 +1206,11 @@ static int gen8_ppgtt_init(struct i915_hw_ppgtt *ppgtt) ppgtt->switch_mm = gen8_mm_switch;return 0 ; + +err_out: +unmap_and_free_pd (ppgtt->scratch_pd, ppgtt->base.dev); +unmap_and_free_pt (ppgtt->scratch_pt, ppgtt->base.dev); +return ret; }static void gen6_dump_ppgtt (struct i915_hw_ppgtt *ppgtt,struct seq_file *m)
drivers/gpu/drm/i915/i915_gem_gtt.h +10 -2
@@ -95,6 +95,7 @@ typedef uint64_t gen8_pde_t;*/ #define GEN8_PML4ES_PER_PML4 512#define GEN8_PML4E_SHIFT 39 +#define GEN8_PML4E_MASK (GEN8_PML4ES_PER_PML4 - 1)#define GEN8_PDPE_SHIFT 30/* NB: GEN8_PDPE_MASK is untrue for 32b platforms, but it has no impact on 32b page * tables */
@@ -455,6 +456,14 @@ static inline uint32_t gen6_pde_index(uint32_t addr) temp = min(temp, length), \ start += temp, length -= temp) +#define gen8_for_each_pml4e (pdp, pml4, start, length, temp, iter) \ + for (iter = gen8_pml4e_index(start); \ + pdp = (pml4)->pdps[iter], length > 0 && iter < GEN8_PML4ES_PER_PML4; \ + iter++, \ + temp = ALIGN(start+1, 1ULL << GEN8_PML4E_SHIFT) - start, \ + temp = min(temp, length), \ + start += temp, length -= temp) +#define gen8_for_each_pdpe (pd, pdp, start, length, temp, iter) \ gen8_for_each_pdpe_e(pd, pdp, start, length, temp, iter, I915_PDPES_PER_PDP(dev))
@@ -475,8 +484,7 @@ static inline uint32_t gen8_pdpe_index(uint64_t address)static inline uint32_t gen8_pml4e_index (uint64_t address) { -WARN_ON (1 );/* For 64B */ -return 0 ; +return (address >>GEN8_PML4E_SHIFT ) &GEN8_PML4E_MASK ; }static inline size_t gen8_pte_count (uint64_t address,uint64_t length)
Signature · 6 lines
2.4.0 _______________________________________________ Intel-gfx mailing list [email protected] http://lists.freedesktop.org/mailman/listinfo/intel-gfx
PATCH 6/16 drm/i915/gen8: Add 4 level switching infrastructure and lrc support
In reply to Michel ThierryIn 64b (48bit canonical) PPGTT addressing, the PDP0 register contains the base address to PML4, while the other PDP registers are ignored.
In LRC, the addressing mode must be specified in every context descriptor.
v2: PML4 update in legacy context switch is left for historic reasons, the preferred mode of operation is with lrc context based submission.
v3: s/gen8_map_page_directory/gen8_setup_page_directory and s/gen8_map_page_directory_pointer/gen8_setup_page_directory_pointer. Also, clflush will be needed for bxt. (Akash)
v4: Squashed lrc-specific code and use a macro to set PML4 register.
--- drivers/gpu/drm/i915/i915_gem_gtt.c | 62 ++++++++++++++++++++++++++++++++++--- drivers/gpu/drm/i915/i915_gem_gtt.h | 2 ++ drivers/gpu/drm/i915/i915_reg.h | 1 + drivers/gpu/drm/i915/intel_lrc.c | 50 +++++++++++++++++++++++------- 4 files changed, 98 insertions(+), 17 deletions(-)
drivers/gpu/drm/i915/i915_gem_gtt.c +57 -5
@@ -216,6 +216,9 @@ static gen8_pde_t gen8_pde_encode(struct drm_device *dev,return pde; } +#define gen8_pdpe_encode gen8_pde_encode +#define gen8_pml4e_encode gen8_pde_encode +static gen6_pte_t snb_pte_encode (dma_addr_t addr,enum i915_cache_level level,bool valid,u32 unused)
@@ -560,8 +563,8 @@ static int gen8_write_pdp(struct intel_engine_cs *ring,return 0 ; } -static int gen8_mm_switch (struct i915_hw_ppgtt *ppgtt, -struct intel_engine_cs *ring) +static int gen8_legacy_mm_switch (struct i915_hw_ppgtt *ppgtt, +struct intel_engine_cs *ring) {int i, ret;
@@ -578,6 +581,12 @@ static int gen8_mm_switch(struct i915_hw_ppgtt *ppgtt,return 0 ; } +static int gen8_48b_mm_switch (struct i915_hw_ppgtt *ppgtt, +struct intel_engine_cs *ring) +{ +return gen8_write_pdp (ring,0 , ppgtt->pml4.daddr); +} + static void gen8_ppgtt_clear_range(struct i915_address_space *vm, uint64_t start, uint64_t length,
@@ -764,6 +773,45 @@ static void gen8_map_pagetable_range(struct i915_address_space *vm,kunmap_atomic (page_directory); } +static void +gen8_setup_page_directory (struct i915_page_directory_pointer *pdp, +struct i915_page_directory *pd, +int index, +struct drm_device *dev) +{ +gen8_ppgtt_pdpe_t *page_directorypo; +gen8_ppgtt_pdpe_t pdpe; + +if (!USES_FULL_48BIT_PPGTT (dev)) +return ; + + page_directorypo =kmap_atomic (pdp->page); + pdpe =gen8_pdpe_encode (dev, pd->daddr,I915_CACHE_LLC ); + page_directorypo[index] = pdpe; + +if (!HAS_LLC (dev)) +drm_clflush_virt_range (page_directorypo,PAGE_SIZE ); + +kunmap_atomic (page_directorypo); +} + +static void +gen8_setup_page_directory_pointer (struct i915_pml4 *pml4, +struct i915_page_directory_pointer *pdp, +int index, +struct drm_device *dev) +{ +gen8_ppgtt_pml4e_t *pagemap =kmap_atomic (pml4->page); +gen8_ppgtt_pml4e_t pml4e =gen8_pml4e_encode (dev, pdp->daddr,I915_CACHE_LLC ); +WARN_ON (!USES_FULL_48BIT_PPGTT (dev)); + pagemap[index] = pml4e; + +if (!HAS_LLC (dev)) +drm_clflush_virt_range (pagemap,PAGE_SIZE ); + +kunmap_atomic (pagemap); +} +static void gen8_free_page_tables (struct i915_page_directory *pd,struct drm_device *dev) {int i;
@@ -1065,6 +1113,7 @@ static int gen8_alloc_va_range_3lvl(struct i915_address_space *vm,set_bit (pdpe, pdp->used_pdpes);gen8_map_pagetable_range (vm, pd, start, length); +gen8_setup_page_directory (pdp, pd, pdpe, dev); }free_gen8_temp_bitmaps (new_page_dirs, new_page_tables, pdpes);
@@ -1132,6 +1181,8 @@ static int gen8_alloc_va_range_4lvl(struct i915_address_space *vm, ret =gen8_alloc_va_range_3lvl (vm, pdp, start, length);if (ret) goto err_out; + +gen8_setup_page_directory_pointer (pml4, pdp, pml4e, vm->dev); } bitmap_or(pml4->used_pml4es, new_pdps, pml4->used_pml4es,
@@ -1186,12 +1237,14 @@ static int gen8_ppgtt_init(struct i915_hw_ppgtt *ppgtt) goto err_out; ppgtt->base.total =1ULL <<48 ; + ppgtt->switch_mm = gen8_48b_mm_switch; }else { ret =__pdp_init (&ppgtt->pdp, false);if (ret) goto err_out; ppgtt->base.total =1ULL <<32 ; + ppgtt->switch_mm = gen8_legacy_mm_switch;trace_i915_page_directory_pointer_entry_alloc (&ppgtt->base,0 ,0 ,GEN8_PML4E_SHIFT ); }
@@ -1203,8 +1256,6 @@ static int gen8_ppgtt_init(struct i915_hw_ppgtt *ppgtt) ppgtt->base.unbind_vma = ppgtt_unbind_vma; ppgtt->base.bind_vma = ppgtt_bind_vma; - ppgtt->switch_mm = gen8_mm_switch; -return 0 ; err_out:
@@ -1392,8 +1443,9 @@ static void gen8_ppgtt_enable(struct drm_device *dev)int j;for_each_ring (ring, dev_priv, j) { +u32 four_level =USES_FULL_48BIT_PPGTT (dev) ?GEN8_GFX_PPGTT_64B :0 ;I915_WRITE (RING_MODE_GEN7 (ring), -_MASKED_BIT_ENABLE (GFX_PPGTT_ENABLE )); +_MASKED_BIT_ENABLE (GFX_PPGTT_ENABLE | four_level)); } }
drivers/gpu/drm/i915/i915_gem_gtt.h +2 -0
@@ -39,6 +39,8 @@ struct drm_i915_file_private;typedef uint32_t gen6_pte_t ;typedef uint64_t gen8_pte_t ;typedef uint64_t gen8_pde_t ; +typedef uint64_t gen8_ppgtt_pdpe_t ; +typedef uint64_t gen8_ppgtt_pml4e_t ;#define gtt_total_entries (gtt) ((gtt).base.total >> PAGE_SHIFT)
drivers/gpu/drm/i915/i915_reg.h +1 -0
@@ -1642,6 +1642,7 @@ enum skl_disp_power_wells {#define GFX_REPLAY_MODE (1<<11)#define GFX_PSMI_GRANULARITY (1<<10)#define GFX_PPGTT_ENABLE (1<<9) +#define GEN8_GFX_PPGTT_64B (1<<7)#define VLV_DISPLAY_BASE 0x180000#define VLV_MIPI_BASE VLV_DISPLAY_BASE
drivers/gpu/drm/i915/intel_lrc.c +38 -12
78 lines not on this page · raw message
Signature · 6 lines
2.4.0 _______________________________________________ Intel-gfx mailing list [email protected] http://lists.freedesktop.org/mailman/listinfo/intel-gfx
PATCH 7/16 drm/i915/gen8: Generalize PTE writing for GEN8 PPGTT
In reply to Michel ThierryThe insert_entries function was the function used to write PTEs. For the PPGTT it was "hardcoded" to only understand two level page tables, which was the case for GEN7. We can reuse this for 4 level page tables, and remove the concept of insert_entries, which was never viable past 2 level page tables anyway, but it requires a bit of rework to make the function a bit more generic.
This patch begins the generalization work, and it will be heavily used upon when the 48b code is complete. The patch series attempts to make each function which touches a part of code specific to the page table level and here is no exception.
--- drivers/gpu/drm/i915/i915_gem_gtt.c | 56 ++++++++++++++++++++++++++----------- 1 file changed, 39 insertions(+), 17 deletions(-)
drivers/gpu/drm/i915/i915_gem_gtt.c +39 -17
@@ -587,23 +587,19 @@ static int gen8_48b_mm_switch(struct i915_hw_ppgtt *ppgtt,return gen8_write_pdp (ring,0 , ppgtt->pml4.daddr); } -static void gen8_ppgtt_clear_range (struct i915_address_space *vm, -uint64_t start, -uint64_t length, -bool use_scratch) +static void gen8_ppgtt_clear_pte_range (struct i915_page_directory_pointer *pdp, +uint64_t start, +uint64_t length, +gen8_pte_t scratch_pte, +const bool flush) { -struct i915_hw_ppgtt *ppgtt = - container_of(vm, struct i915_hw_ppgtt, base); -struct i915_page_directory_pointer *pdp = &ppgtt->pdp;/* FIXME: 48b */ -gen8_pte_t *pt_vaddr, scratch_pte; +gen8_pte_t *pt_vaddr;unsigned pdpe = start >>GEN8_PDPE_SHIFT &GEN8_PDPE_MASK ;unsigned pde = start >>GEN8_PDE_SHIFT &GEN8_PDE_MASK ;unsigned pte = start >>GEN8_PTE_SHIFT &GEN8_PTE_MASK ;unsigned num_entries = length >>PAGE_SHIFT ;unsigned last_pte, i; - scratch_pte =gen8_pte_encode (ppgtt->base.scratch.addr, -I915_CACHE_LLC , use_scratch);while (num_entries) {struct i915_page_directory *pd;
@@ -636,7 +632,7 @@ static void gen8_ppgtt_clear_range(struct i915_address_space *vm, num_entries--; } -if (!HAS_LLC (ppgtt->base.dev)) +if (flush)drm_clflush_virt_range (pt_vaddr,PAGE_SIZE );kunmap_atomic (pt_vaddr);
@@ -648,14 +644,28 @@ static void gen8_ppgtt_clear_range(struct i915_address_space *vm, } } -static void gen8_ppgtt_insert_entries (struct i915_address_space *vm, -struct sg_table *pages, -uint64_t start, -enum i915_cache_level cache_level,u32 unused) +static void gen8_ppgtt_clear_range (struct i915_address_space *vm, +uint64_t start, +uint64_t length, +bool use_scratch) {struct i915_hw_ppgtt *ppgtt = container_of(vm, struct i915_hw_ppgtt, base);struct i915_page_directory_pointer *pdp = &ppgtt->pdp;/* FIXME: 48b */ + +gen8_pte_t scratch_pte =gen8_pte_encode (ppgtt->base.scratch.addr, +I915_CACHE_LLC , use_scratch); + +gen8_ppgtt_clear_pte_range (pdp, start, length, scratch_pte, !HAS_LLC (vm->dev)); +} + +static void +gen8_ppgtt_insert_pte_entries (struct i915_page_directory_pointer *pdp, +struct sg_table *pages, +uint64_t start, +enum i915_cache_level cache_level, +const bool flush) +{gen8_pte_t *pt_vaddr;unsigned pdpe = start >>GEN8_PDPE_SHIFT &GEN8_PDPE_MASK ;unsigned pde = start >>GEN8_PDE_SHIFT &GEN8_PDE_MASK ;
@@ -677,7 +687,7 @@ static void gen8_ppgtt_insert_entries(struct i915_address_space *vm,gen8_pte_encode (sg_page_iter_dma_address (&sg_iter), cache_level, true);if (++pte ==GEN8_PTES ) { -if (!HAS_LLC (ppgtt->base.dev)) +if (flush)drm_clflush_virt_range (pt_vaddr,PAGE_SIZE );kunmap_atomic (pt_vaddr); pt_vaddr =NULL ;
@@ -689,12 +699,24 @@ static void gen8_ppgtt_insert_entries(struct i915_address_space *vm, } }if (pt_vaddr) { -if (!HAS_LLC (ppgtt->base.dev)) +if (flush)drm_clflush_virt_range (pt_vaddr,PAGE_SIZE );kunmap_atomic (pt_vaddr); } } +static void gen8_ppgtt_insert_entries (struct i915_address_space *vm, +struct sg_table *pages, +uint64_t start, +enum i915_cache_level cache_level, +u32 unused) +{ + struct i915_hw_ppgtt *ppgtt = container_of(vm, struct i915_hw_ppgtt, base); +struct i915_page_directory_pointer *pdp = &ppgtt->pdp;/* FIXME: 48b */ + +gen8_ppgtt_insert_pte_entries (pdp, pages, start, cache_level, !HAS_LLC (vm->dev)); +} +static void __gen8_do_map_pt (gen8_pde_t *const pde,struct i915_page_table *pt,struct drm_device *dev)
Signature · 6 lines
2.4.0 _______________________________________________ Intel-gfx mailing list [email protected] http://lists.freedesktop.org/mailman/listinfo/intel-gfx
PATCH 8/16 drm/i915: Plumb sg_iter through va allocation ->maps
In reply to Michel ThierryAs a step towards implementing 4 levels, while not discarding the existing pte map functions, we need to pass the sg_iter through. The current function understands to the page directory granularity. An object's pages may span the page directory, and so using the iter directly as we write the PTEs allows the iterator to stay coherent through a VMA mapping operation spanning multiple page table levels.
v2: Rebase after s/page_tables/page_table/.
--- drivers/gpu/drm/i915/i915_gem_gtt.c | 46 +++++++++++++++++++++++-------------- 1 file changed, 29 insertions(+), 17 deletions(-)
drivers/gpu/drm/i915/i915_gem_gtt.c +29 -17
@@ -661,7 +661,7 @@ static void gen8_ppgtt_clear_range(struct i915_address_space *vm,static void gen8_ppgtt_insert_pte_entries (struct i915_page_directory_pointer *pdp, -struct sg_table *pages, +struct sg_page_iter *sg_iter,uint64_t start,enum i915_cache_level cache_level,const bool flush)
@@ -670,11 +670,10 @@ gen8_ppgtt_insert_pte_entries(struct i915_page_directory_pointer *pdp,unsigned pdpe = start >>GEN8_PDPE_SHIFT &GEN8_PDPE_MASK ;unsigned pde = start >>GEN8_PDE_SHIFT &GEN8_PDE_MASK ;unsigned pte = start >>GEN8_PTE_SHIFT &GEN8_PTE_MASK ; -struct sg_page_iter sg_iter; pt_vaddr =NULL ; -for_each_sg_page (pages->sgl, &sg_iter, pages->nents,0 ) { +while (__sg_page_iter_next (sg_iter)) {if (pt_vaddr ==NULL ) {struct i915_page_directory *pd = pdp->page_directory[pdpe];struct i915_page_table *pt = pd->page_table[pde];
@@ -684,7 +683,7 @@ gen8_ppgtt_insert_pte_entries(struct i915_page_directory_pointer *pdp, } pt_vaddr[pte] = -gen8_pte_encode (sg_page_iter_dma_address (&sg_iter), +gen8_pte_encode (sg_page_iter_dma_address (sg_iter), cache_level, true);if (++pte ==GEN8_PTES ) {if (flush)
@@ -713,8 +712,10 @@ static void gen8_ppgtt_insert_entries(struct i915_address_space *vm, { struct i915_hw_ppgtt *ppgtt = container_of(vm, struct i915_hw_ppgtt, base);struct i915_page_directory_pointer *pdp = &ppgtt->pdp;/* FIXME: 48b */ +struct sg_page_iter sg_iter; -gen8_ppgtt_insert_pte_entries (pdp, pages, start, cache_level, !HAS_LLC (vm->dev)); +__sg_page_iter_start (&sg_iter, pages->sgl,sg_nents (pages->sgl),0 ); +gen8_ppgtt_insert_pte_entries (pdp, &sg_iter, start, cache_level, !HAS_LLC (vm->dev)); } static void __gen8_do_map_pt(gen8_pde_t * const pde,
@@ -1067,10 +1068,12 @@ err_out:return -ENOMEM ; } -static int gen8_alloc_va_range_3lvl (struct i915_address_space *vm, -struct i915_page_directory_pointer *pdp, -uint64_t start, -uint64_t length) +static int __gen8_alloc_vma_range_3lvl (struct i915_address_space *vm, +struct i915_page_directory_pointer *pdp, +struct sg_page_iter *sg_iter, +uint64_t start, +uint64_t length, +u32 flags) {unsigned long *new_page_dirs, **new_page_tables;struct drm_device *dev = vm->dev;
@@ -1129,7 +1132,11 @@ static int gen8_alloc_va_range_3lvl(struct i915_address_space *vm,gen8_pte_index (pd_start), gen8_pte_count(pd_start, pd_len)); -/* Our pde is now pointing to the pagetable, pt */ +if (sg_iter) { +WARN_ON (!sg_iter->__nents); +gen8_ppgtt_insert_pte_entries (pdp, sg_iter, pd_start, + flags, !HAS_LLC (vm->dev)); + }set_bit (pde, pd->used_pdes); }
@@ -1154,10 +1161,12 @@ err_out:return ret; } -static int gen8_alloc_va_range_4lvl (struct i915_address_space *vm, -struct i915_pml4 *pml4, -uint64_t start, -uint64_t length) +static int __gen8_alloc_vma_range_4lvl (struct i915_address_space *vm, +struct i915_pml4 *pml4, +struct sg_page_iter *sg_iter, +uint64_t start, +uint64_t length, +u32 flags) {DECLARE_BITMAP (new_pdps,GEN8_PML4ES_PER_PML4 ); struct i915_hw_ppgtt *ppgtt =
@@ -1200,7 +1209,8 @@ static int gen8_alloc_va_range_4lvl(struct i915_address_space *vm,gen8_for_each_pml4e (pdp, pml4, start, length, temp, pml4e) {WARN_ON (!pdp); - ret =gen8_alloc_va_range_3lvl (vm, pdp, start, length); + ret =__gen8_alloc_vma_range_3lvl (vm, pdp, sg_iter, + start, length, flags);if (ret) goto err_out;
@@ -1226,9 +1236,11 @@ static int gen8_alloc_va_range(struct i915_address_space *vm, container_of(vm, struct i915_hw_ppgtt, base);if (USES_FULL_48BIT_PPGTT (vm->dev)) -return gen8_alloc_va_range_4lvl (vm, &ppgtt->pml4, start, length); +return __gen8_alloc_vma_range_4lvl (vm, &ppgtt->pml4,NULL , + start, length,0 );else -return gen8_alloc_va_range_3lvl (vm, &ppgtt->pdp, start, length); +return __gen8_alloc_vma_range_3lvl (vm, &ppgtt->pdp,NULL , + start, length,0 ); }/*
Signature · 6 lines
2.4.0 _______________________________________________ Intel-gfx mailing list [email protected] http://lists.freedesktop.org/mailman/listinfo/intel-gfx
PATCH 9/16 drm/i915/gen8: Add 4 level support in insert_entries and clear_range
In reply to Michel ThierryWhen 48b is enabled, gen8_ppgtt_insert_entries needs to read the Page Map Level 4 (PML4), before it selects which Page Directory Pointer (PDP) it will write to.
Similarly, gen8_ppgtt_clear_range needs to get the correct PDP/PD range.
This patch was inspired by Ben's "Depend exclusively on map and unmap_vma".
v2: Rebase after s/page_tables/page_table/.
v3: Remove unnecessary pdpe loop in gen8_ppgtt_clear_range_4lvl and use clamp_pdp in gen8_ppgtt_insert_entries (Akash).
v4: Merge gen8_ppgtt_clear_range_4lvl into gen8_ppgtt_clear_range to maintain symmetry with gen8_ppgtt_insert_entries (Akash).
v5: Do not mix pages and bytes in insert_entries (Akash).
--- drivers/gpu/drm/i915/i915_gem_gtt.c | 51 +++++++++++++++++++++++++++++++------ drivers/gpu/drm/i915/i915_gem_gtt.h | 11 ++++++++ 2 files changed, 54 insertions(+), 8 deletions(-)
drivers/gpu/drm/i915/i915_gem_gtt.c +43 -8
@@ -651,18 +651,33 @@ static void gen8_ppgtt_clear_range(struct i915_address_space *vm, {struct i915_hw_ppgtt *ppgtt = container_of(vm, struct i915_hw_ppgtt, base); -struct i915_page_directory_pointer *pdp = &ppgtt->pdp;/* FIXME: 48b */ -gen8_pte_t scratch_pte =gen8_pte_encode (ppgtt->base.scratch.addr,I915_CACHE_LLC , use_scratch); -gen8_ppgtt_clear_pte_range (pdp, start, length, scratch_pte, !HAS_LLC (vm->dev)); +if (!USES_FULL_48BIT_PPGTT (vm->dev)) { +gen8_ppgtt_clear_pte_range (&ppgtt->pdp, start, length, + scratch_pte, + !HAS_LLC (ppgtt->base.dev)); + }else { +uint64_t templ4, pml4e; +struct i915_page_directory_pointer *pdp; + +gen8_for_each_pml4e (pdp, &ppgtt->pml4, start, length, templ4, pml4e) { +uint64_t pdp_len =gen8_clamp_pdp (start, length); +uint64_t pdp_start = start; + +gen8_ppgtt_clear_pte_range (pdp, pdp_start, pdp_len, + scratch_pte, + !HAS_LLC (ppgtt->base.dev)); + } + } }static void gen8_ppgtt_insert_pte_entries (struct i915_page_directory_pointer *pdp,struct sg_page_iter *sg_iter,uint64_t start, +size_t pages,enum i915_cache_level cache_level,const bool flush) {
@@ -673,7 +688,7 @@ gen8_ppgtt_insert_pte_entries(struct i915_page_directory_pointer *pdp, pt_vaddr =NULL ; -while (__sg_page_iter_next (sg_iter)) { +while (pages-- &&__sg_page_iter_next (sg_iter)) {if (pt_vaddr ==NULL ) {struct i915_page_directory *pd = pdp->page_directory[pdpe];struct i915_page_table *pt = pd->page_table[pde];
@@ -710,12 +725,31 @@ static void gen8_ppgtt_insert_entries(struct i915_address_space *vm, enum i915_cache_level cache_level, u32 unused) { - struct i915_hw_ppgtt *ppgtt = container_of(vm, struct i915_hw_ppgtt, base); -struct i915_page_directory_pointer *pdp = &ppgtt->pdp;/* FIXME: 48b */ +struct i915_hw_ppgtt *ppgtt = + container_of(vm, struct i915_hw_ppgtt, base);struct sg_page_iter sg_iter;__sg_page_iter_start (&sg_iter, pages->sgl,sg_nents (pages->sgl),0 ); -gen8_ppgtt_insert_pte_entries (pdp, &sg_iter, start, cache_level, !HAS_LLC (vm->dev)); + +if (!USES_FULL_48BIT_PPGTT (vm->dev)) { +gen8_ppgtt_insert_pte_entries (&ppgtt->pdp, &sg_iter, start, +sg_nents (pages->sgl), + cache_level, !HAS_LLC (vm->dev)); + }else { +struct i915_page_directory_pointer *pdp; +uint64_t templ4, pml4e; +uint64_t length =sg_nents (pages->sgl) <<PAGE_SHIFT ; + +gen8_for_each_pml4e (pdp, &ppgtt->pml4, start, length, templ4, pml4e) { +uint64_t pdp_len =gen8_clamp_pdp (start, length) >>PAGE_SHIFT ; +uint64_t pdp_start = start; + +gen8_ppgtt_insert_pte_entries (pdp, &sg_iter, + pdp_start, pdp_len, + cache_level, + !HAS_LLC (vm->dev)); + } + } } static void __gen8_do_map_pt(gen8_pde_t * const pde,
@@ -1135,7 +1169,8 @@ static int __gen8_alloc_vma_range_3lvl(struct i915_address_space *vm,if (sg_iter) {WARN_ON (!sg_iter->__nents);gen8_ppgtt_insert_pte_entries (pdp, sg_iter, pd_start, - flags, !HAS_LLC (vm->dev)); +gen8_pte_count (pd_start, pd_len), + flags, !HAS_LLC (vm->dev)); }set_bit (pde, pd->used_pdes); }
drivers/gpu/drm/i915/i915_gem_gtt.h +11 -0
@@ -469,6 +469,17 @@ static inline uint32_t gen6_pde_index(uint32_t addr)#define gen8_for_each_pdpe (pd, pdp, start, length, temp, iter) \ gen8_for_each_pdpe_e(pd, pdp, start, length, temp, iter, I915_PDPES_PER_PDP(dev)) +/* Clamp length to the next page_directory pointer boundary */ +static inline uint64_t gen8_clamp_pdp (uint64_t start,uint64_t length) +{ +uint64_t next_pdp =ALIGN (start +1 ,1ULL <<GEN8_PML4E_SHIFT ); + +if (next_pdp > (start + length)) +return length; + +return next_pdp - start; +} +static inline uint32_t gen8_pte_index (uint64_t address) {return i915_pte_index (address,GEN8_PDE_SHIFT );
Signature · 6 lines
2.4.0 _______________________________________________ Intel-gfx mailing list [email protected] http://lists.freedesktop.org/mailman/listinfo/intel-gfx
Re: [PATCH 09/16] drm/i915/gen8: Add 4 level support in insert_entries and clear_range
Quoted 38 lines · Michel Thierry
When 48b is enabled,
gen8_ppgtt_insert_entriesneeds to read the Page Map Level 4 (PML4), before it selects which Page Directory Pointer (PDP) it will write to.Similarly,
gen8_ppgtt_clear_rangeneeds to get the correct PDP/PD range.This patch was inspired by Ben's "Depend exclusively on map and
unmap_vma".v2: Rebase after s/page_tables/page_table/.
v3: Remove unnecessary pdpe loop ingen8_ppgtt_clear_range_4lvland useclamp_pdpingen8_ppgtt_insert_entries(Akash).
v4: Mergegen8_ppgtt_clear_range_4lvlintogen8_ppgtt_clear_rangeto maintain symmetry withgen8_ppgtt_insert_entries(Akash).
v5: Do not mix pages and bytes ininsert_entries(Akash).Cc Akash Goel <[email protected]>Signed-off-by Michel Thierry <[email protected]>--- drivers/gpu/drm/i915/i915_gem_gtt.c | 51 +++++++++++++++++++++++++++++++------ drivers/gpu/drm/i915/i915_gem_gtt.h | 11 ++++++++ 2 files changed, 54 insertions(+), 8 deletions(-)drivers/gpu/drm/i915/i915_gem_gtt.c +2
-2@@ -710,12 +725,31 @@ static void gen8_ppgtt_insert_entries(struct i915_address_space *vm, enum i915_cache_level cache_level, u32 unused) { - struct i915_hw_ppgtt *ppgtt = container_of(vm, struct i915_hw_ppgtt, base); -struct i915_page_directory_pointer *pdp = &ppgtt->pdp;/* FIXME: 48b */ +struct i915_hw_ppgtt *ppgtt = + container_of(vm, struct i915_hw_ppgtt, base);struct sg_page_iter sg_iter;__sg_page_iter_start (&sg_iter, pages->sgl,sg_nents (pages->sgl),0 );
drivers/gpu/drm/i915/i915_gem_gtt.c static void gen8_ppgtt_insert_entries(struct i915_address_space *vm, · line 741
Quoted 10 lines
drivers/gpu/drm/i915/i915_gem_gtt.c +9
-1-gen8_ppgtt_insert_pte_entries (pdp, &sg_iter, start, cache_level, !HAS_LLC (vm->dev)); + +if (!USES_FULL_48BIT_PPGTT (vm->dev)) { +gen8_ppgtt_insert_pte_entries (&ppgtt->pdp, &sg_iter, start, +sg_nents (pages->sgl), + cache_level, !HAS_LLC (vm->dev)); + }else { +struct i915_page_directory_pointer *pdp; +uint64_t templ4, pml4e; +uint64_t length =sg_nents (pages->sgl) <<PAGE_SHIFT ;
Actually, this should be:
uint64_t length = (uint64_t)sg_nents(pages->sgl) << PAGE_SHIFT;
Otherwise it will overflow if we're inserting 4GB at once.
Quoted 13 lines
drivers/gpu/drm/i915/i915_gem_gtt.c +11
-0+ +gen8_for_each_pml4e (pdp, &ppgtt->pml4, start, length, templ4, pml4e) { +uint64_t pdp_len =gen8_clamp_pdp (start, length) >>PAGE_SHIFT ; +uint64_t pdp_start = start; + +gen8_ppgtt_insert_pte_entries (pdp, &sg_iter, + pdp_start, pdp_len, + cache_level, + !HAS_LLC (vm->dev)); + } + } }
Quoted 5 lines
_______________________________________________
Intel-gfx mailing list
[email protected]
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
_______________________________________________
Intel-gfx mailing list
[email protected]
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
PATCH 10/16 drm/i915/gen8: Initialize PDPs
In reply to Michel ThierrySimilar to PDs, while setting up a page directory pointer, make all entries of the pdp point to the scratch pdp before mapping (and make all its entries point to the scratch page); this is to be safe in case of out of bound access or proactive prefetch.
Systems without LLC require an explicit flush.
This commit also moves gen8_initialize_pt next to the other initialize page functions.
v2: Handle scratch_pdp allocation failure correctly, and keep initialize_px functions together (Akash)
--- drivers/gpu/drm/i915/i915_gem_gtt.c | 108 ++++++++++++++++++++++++++++-------- drivers/gpu/drm/i915/i915_gem_gtt.h | 1 + 2 files changed, 86 insertions(+), 23 deletions(-)
drivers/gpu/drm/i915/i915_gem_gtt.c +85 -23
@@ -365,24 +365,6 @@ static void unmap_and_free_pt(struct i915_page_table *pt,kfree (pt); } -static void gen8_initialize_pt (struct i915_address_space *vm, -struct i915_page_table *pt) -{ -gen8_pte_t *pt_vaddr, scratch_pte; -int i; - - pt_vaddr =kmap_atomic (pt->page); - scratch_pte =gen8_pte_encode (vm->scratch.addr, -I915_CACHE_LLC , true); - -for (i =0 ; i <GEN8_PTES ; i++) - pt_vaddr[i] = scratch_pte; - -if (!HAS_LLC (vm->dev)) -drm_clflush_virt_range (pt_vaddr,PAGE_SIZE ); -kunmap_atomic (pt_vaddr); -} -static struct i915_page_table *alloc_pt_single (struct drm_device *dev) {struct i915_page_table *pt;
@@ -521,7 +503,7 @@ i915_page_directory_pointer *alloc_pdp_single(struct i915_hw_ppgtt *ppgtt)if (!pdp)return ERR_PTR (-ENOMEM ); - pdp->page =alloc_page (GFP_KERNEL |GFP_DMA32 | __GFP_ZERO); + pdp->page =alloc_page (GFP_KERNEL |GFP_DMA32 );if (!pdp->page) {kfree (pdp);return ERR_PTR (-ENOMEM );
@@ -761,6 +743,24 @@ static void __gen8_do_map_pt(gen8_pde_t * const pde, *pde = entry; } +static void gen8_initialize_pt (struct i915_address_space *vm, +struct i915_page_table *pt) +{ +gen8_pte_t *pt_vaddr, scratch_pte; +int i; + + pt_vaddr =kmap_atomic (pt->page); + scratch_pte =gen8_pte_encode (vm->scratch.addr, +I915_CACHE_LLC , true); + +for (i =0 ; i <GEN8_PTES ; i++) + pt_vaddr[i] = scratch_pte; + +if (!HAS_LLC (vm->dev)) +drm_clflush_virt_range (pt_vaddr,PAGE_SIZE ); +kunmap_atomic (pt_vaddr); +} +static void gen8_initialize_pd (struct i915_address_space *vm,struct i915_page_directory *pd) {
@@ -782,6 +782,55 @@ static void gen8_initialize_pd(struct i915_address_space *vm,kunmap_atomic (page_directory); } +static void gen8_initialize_pdp (struct i915_address_space *vm, +struct i915_page_directory_pointer *pdp) +{ +struct i915_hw_ppgtt *ppgtt = + container_of(vm, struct i915_hw_ppgtt, base); +gen8_ppgtt_pdpe_t *page_directorypo; +struct i915_page_directory *pd; +int i; + + page_directorypo =kmap_atomic (pdp->page); + pd = (struct i915_page_directory *)ppgtt->scratch_pd; +for (i =0 ; i <I915_PDPES_PER_PDP (vm->dev); i++) { +/* Map the PDPE to the page directory */ +gen8_ppgtt_pdpe_t entry = +gen8_pdpe_encode (vm->dev, pd->daddr,I915_CACHE_LLC ); + page_directorypo[i] = entry; + } + +if (!HAS_LLC (vm->dev)) +drm_clflush_virt_range (page_directorypo,PAGE_SIZE ); + +kunmap_atomic (page_directorypo); +} + +static void gen8_initialize_pml4 (struct i915_address_space *vm, +struct i915_pml4 *pml4) +{ +struct i915_hw_ppgtt *ppgtt = + container_of(vm, struct i915_hw_ppgtt, base); +gen8_ppgtt_pml4e_t *page_maplevel4; +struct i915_page_directory_pointer *pdp; +int i; + + page_maplevel4 =kmap_atomic (pml4->page); + pdp = (struct i915_page_directory_pointer *)ppgtt->scratch_pdp; +for (i =0 ; i <GEN8_PML4ES_PER_PML4 ; i++) { +/* Map the PML4E to the page directory pointer */ +gen8_ppgtt_pml4e_t entry = +gen8_pml4e_encode (vm->dev, pdp->daddr, +I915_CACHE_LLC ); + page_maplevel4[i] = entry; + } + +if (!HAS_LLC (vm->dev)) +drm_clflush_virt_range (page_maplevel4,PAGE_SIZE ); + +kunmap_atomic (page_maplevel4); +} +static void pml4_fini (struct i915_pml4 *pml4) { struct i915_hw_ppgtt *ppgtt =
@@ -795,10 +844,12 @@ static int pml4_init(struct i915_hw_ppgtt *ppgtt) {struct i915_pml4 *pml4 = &ppgtt->pml4; - pml4->page =alloc_page (GFP_KERNEL | __GFP_ZERO); + pml4->page =alloc_page (GFP_KERNEL |GFP_DMA32 );if (!pml4->page)return -ENOMEM ; +gen8_initialize_pml4 (&ppgtt->base, pml4); +i915_dma_map_single (pml4, ppgtt->base.dev);return 0 ;
@@ -913,6 +964,7 @@ static void gen8_ppgtt_cleanup_4lvl(struct i915_hw_ppgtt *ppgtt) }pml4_fini (&ppgtt->pml4); +unmap_and_free_pdp (ppgtt->scratch_pdp, ppgtt->base.dev); }static void gen8_ppgtt_cleanup (struct i915_address_space *vm)
@@ -1220,12 +1272,12 @@ static int __gen8_alloc_vma_range_4lvl(struct i915_address_space *vm,* and 4 level code. Just allocate the pdps. */ gen8_for_each_pml4e (pdp, pml4, start, length, temp, pml4e) { -if (!pdp) { -WARN_ON (test_bit (pml4e, pml4->used_pml4es)); +if (!test_bit (pml4e, pml4->used_pml4es)) { pdp =alloc_pdp_single (ppgtt);if (IS_ERR (pdp)) goto err_out; +gen8_initialize_pdp (vm, pdp); pml4->pdps[pml4e] = pdp;set_bit (pml4e, new_pdps); trace_i915_page_directory_pointer_entry_alloc(&ppgtt->base, pml4e,
@@ -1301,9 +1353,17 @@ static int gen8_ppgtt_init(struct i915_hw_ppgtt *ppgtt)gen8_initialize_pd (&ppgtt->base, ppgtt->scratch_pd);if (USES_FULL_48BIT_PPGTT (ppgtt->base.dev)) { + ppgtt->scratch_pdp =alloc_pdp_single (ppgtt); +if (IS_ERR (ppgtt->scratch_pdp)) { + ret =PTR_ERR (ppgtt->scratch_pdp); + goto err_out; + } + +gen8_initialize_pdp (&ppgtt->base, ppgtt->scratch_pdp); + ret =pml4_init (ppgtt);if (ret) - goto err_out; + goto err_pdp_out; ppgtt->base.total =1ULL <<48 ; ppgtt->switch_mm = gen8_48b_mm_switch;
@@ -1327,6 +1387,8 @@ static int gen8_ppgtt_init(struct i915_hw_ppgtt *ppgtt)return 0 ; +err_pdp_out: +unmap_and_free_pdp (ppgtt->scratch_pdp, ppgtt->base.dev); err_out:unmap_and_free_pd (ppgtt->scratch_pd, ppgtt->base.dev);unmap_and_free_pt (ppgtt->scratch_pt, ppgtt->base.dev);
drivers/gpu/drm/i915/i915_gem_gtt.h +1 -0
@@ -358,6 +358,7 @@ struct i915_hw_ppgtt {struct i915_page_table *scratch_pt;struct i915_page_directory *scratch_pd; +struct i915_page_directory_pointer *scratch_pdp;struct drm_i915_file_private *file_priv;
Signature · 6 lines
2.4.0 _______________________________________________ Intel-gfx mailing list [email protected] http://lists.freedesktop.org/mailman/listinfo/intel-gfx
PATCH 11/16 drm/i915: Expand error state's address width to 64b
In reply to Michel Thierry--- drivers/gpu/drm/i915/i915_drv.h | 4 ++-- drivers/gpu/drm/i915/i915_gpu_error.c | 17 +++++++++-------- 2 files changed, 11 insertions(+), 10 deletions(-)
drivers/gpu/drm/i915/i915_drv.h +2 -2
@@ -507,7 +507,7 @@ struct drm_i915_error_state {struct drm_i915_error_object {int page_count; -u32 gtt_offset; +u64 gtt_offset;u32 *pages[0 ]; } *ringbuffer, *batchbuffer, *wa_batchbuffer, *ctx, *hws_page;
@@ -533,7 +533,7 @@ struct drm_i915_error_state {u32 size;u32 name;u32 rseqno[I915_NUM_RINGS ], wseqno; -u32 gtt_offset; +u64 gtt_offset;u32 read_domains;u32 write_domain; s32 fence_reg:I915_MAX_NUM_FENCE_BITS;
drivers/gpu/drm/i915/i915_gpu_error.c +9 -8
@@ -197,7 +197,7 @@ static void print_error_buffers(struct drm_i915_error_state_buf *m,err_printf (m," %s [%d]:\n" , name, count);while (count--) { - err_printf(m, " %08x %8u %02x %02x [ ", + err_printf(m, " %016llx %8u %02x %02x [ ", err->gtt_offset, err->size, err->read_domains,
@@ -426,7 +426,7 @@ int i915_error_state_to_str(struct drm_i915_error_state_buf *m,err_printf (m," (submitted by %s [%d])" , error->ring[i].comm, error->ring[i].pid); -err_printf (m," --- gtt_offset = 0x%08x\n" , +err_printf (m," --- gtt_offset = 0x%016llx\n" , obj->gtt_offset);print_error_obj (m, obj); }
@@ -434,7 +434,8 @@ int i915_error_state_to_str(struct drm_i915_error_state_buf *m, obj = error->ring[i].wa_batchbuffer;if (obj) {err_printf (m,"%s (w/a) --- gtt_offset = 0x%08x\n" , - dev_priv->ring[i].name, obj->gtt_offset); + dev_priv->ring[i].name, +lower_32_bits (obj->gtt_offset));print_error_obj (m, obj); }
@@ -453,14 +454,14 @@ int i915_error_state_to_str(struct drm_i915_error_state_buf *m,if ((obj = error->ring[i].ringbuffer)) {err_printf (m,"%s --- ringbuffer = 0x%08x\n" , dev_priv->ring[i].name, - obj->gtt_offset); +lower_32_bits (obj->gtt_offset));print_error_obj (m, obj); }if ((obj = error->ring[i].hws_page)) {err_printf (m,"%s --- HW Status = 0x%08x\n" , dev_priv->ring[i].name, - obj->gtt_offset); +lower_32_bits (obj->gtt_offset)); offset =0 ;for (elt =0 ; elt <PAGE_SIZE /16 ; elt +=4 ) { err_printf(m, "[%04x] %08x %08x %08x %08x\n",
@@ -476,13 +477,13 @@ int i915_error_state_to_str(struct drm_i915_error_state_buf *m,if ((obj = error->ring[i].ctx)) {err_printf (m,"%s --- HW Context = 0x%08x\n" , dev_priv->ring[i].name, - obj->gtt_offset); +lower_32_bits (obj->gtt_offset));print_error_obj (m, obj); } }if ((obj = error->semaphore_obj)) { -err_printf (m,"Semaphore page = 0x%08x\n" , obj->gtt_offset); +err_printf (m,"Semaphore page = 0x%016llx\n" , obj->gtt_offset);for (elt =0 ; elt <PAGE_SIZE /16 ; elt +=4 ) { err_printf(m, "[%04x] %08x %08x %08x %08x\n", elt * 4,
@@ -590,7 +591,7 @@ i915_error_object_create(struct drm_i915_private *dev_priv,int num_pages;bool use_ggtt;int i =0 ; -u32 reloc_offset; +u64 reloc_offset;if (src ==NULL || src->pages ==NULL )return NULL ;
Signature · 6 lines
2.4.0 _______________________________________________ Intel-gfx mailing list [email protected] http://lists.freedesktop.org/mailman/listinfo/intel-gfx
PATCH 12/16 drm/i915/gen8: Add ppgtt info and debug_dump
In reply to Michel Thierryv2: Clean up patch after rebases.
v3: gen8_dump_ppgtt for 32b and 48b PPGTT.
v4: Use used_pml4es/pdpes (Akash).
--- drivers/gpu/drm/i915/i915_debugfs.c | 18 ++++---- drivers/gpu/drm/i915/i915_gem_gtt.c | 88 +++++++++++++++++++++++++++++++++++++ 2 files changed, 98 insertions(+), 8 deletions(-)
drivers/gpu/drm/i915/i915_debugfs.c +10 -8
@@ -2227,7 +2227,6 @@ static void gen6_ppgtt_info(struct seq_file *m, struct drm_device *dev) {struct drm_i915_private *dev_priv = dev->dev_private;struct intel_engine_cs *ring; -struct drm_file *file;int i;if (INTEL_INFO (dev)->gen ==6 )
@@ -2250,13 +2249,6 @@ static void gen6_ppgtt_info(struct seq_file *m, struct drm_device *dev) ppgtt->debug_dump (ppgtt, m); } -list_for_each_entry_reverse (file, &dev->filelist, lhead) { -struct drm_i915_file_private *file_priv = file->driver_priv; - -seq_printf (m,"proc: %s\n" , -get_pid_task (file->pid,PIDTYPE_PID )->comm); -idr_for_each (&file_priv->context_idr, per_file_ctx, m); - }seq_printf (m,"ECOCHK: 0x%08x\n" ,I915_READ (GAM_ECOCHK )); }
@@ -2265,6 +2257,7 @@ static int i915_ppgtt_info(struct seq_file *m, void *data)struct drm_info_node *node = m->private;struct drm_device *dev = node->minor->dev;struct drm_i915_private *dev_priv = dev->dev_private; +struct drm_file *file;int ret =mutex_lock_interruptible (&dev->struct_mutex);if (ret)
@@ -2276,6 +2269,15 @@ static int i915_ppgtt_info(struct seq_file *m, void *data)else if (INTEL_INFO (dev)->gen >=6 )gen6_ppgtt_info (m, dev); +list_for_each_entry_reverse (file, &dev->filelist, lhead) { +struct drm_i915_file_private *file_priv = file->driver_priv; + +seq_printf (m,"\nproc: %s\n" , +get_pid_task (file->pid,PIDTYPE_PID )->comm); +idr_for_each (&file_priv->context_idr, per_file_ctx, + (void *)(unsigned long )m); + } +intel_runtime_pm_put (dev_priv);mutex_unlock (&dev->struct_mutex);
drivers/gpu/drm/i915/i915_gem_gtt.c +88 -0
100 lines not on this page · raw message
Signature · 6 lines
2.4.0 _______________________________________________ Intel-gfx mailing list [email protected] http://lists.freedesktop.org/mailman/listinfo/intel-gfx
PATCH 13/16 drm/i915: object size needs to be u64
In reply to Michel ThierryIn a 48b world, users can try to allocate buffers bigger than 4GB; in these cases it is important that size is a 64b variable.
Also added a warning for illegal bind with size = 0.
--- drivers/gpu/drm/i915/i915_gem.c | 5 +++-- drivers/gpu/drm/i915/i915_gem_gtt.c | 3 +++ 2 files changed, 6 insertions(+), 2 deletions(-)
drivers/gpu/drm/i915/i915_gem.c +3 -2
@@ -3670,7 +3670,8 @@ i915_gem_object_bind_to_vm(struct drm_i915_gem_object *obj, {struct drm_device *dev = obj->base.dev;struct drm_i915_private *dev_priv = dev->dev_private; -u32 size, fence_size, fence_alignment, unfenced_alignment; +u32 fence_alignment, unfenced_alignment; +u64 size, fence_size;unsigned long start = flags &PIN_OFFSET_BIAS ? flags &PIN_OFFSET_MASK :0 ; unsigned long end =
@@ -3729,7 +3730,7 @@ i915_gem_object_bind_to_vm(struct drm_i915_gem_object *obj,* attempt to find space. */ if (size > end) { - DRM_DEBUG("Attempting to bind an object (view type=%u) larger than the aperture: size=%u > %s aperture=%lu\n", + DRM_DEBUG("Attempting to bind an object (view type=%u) larger than the aperture: size=%llu > %s aperture=%lu\n", ggtt_view ? ggtt_view->type : 0, size, flags & PIN_MAPPABLE ? "mappable" : "total",
drivers/gpu/drm/i915/i915_gem_gtt.c +3 -0
@@ -3367,6 +3367,9 @@ int i915_vma_bind(struct i915_vma *vma, enum i915_cache_level cache_level,if (WARN_ON (flags ==0 ))return -EINVAL ; +if (WARN_ON (vma->node.size ==0 )) +return -EINVAL ; + bind_flags =0 ;if (flags &PIN_GLOBAL ) bind_flags |=GLOBAL_BIND ;
Signature · 6 lines
2.4.0 _______________________________________________ Intel-gfx mailing list [email protected] http://lists.freedesktop.org/mailman/listinfo/intel-gfx
PATCH 14/16 drm/i915: Check against correct user_size limit in 48b ppgtt mode
In reply to Michel ThierryGTT is only 32b and its max value is 4GB. In order to allow objects bigger than 4GB in 48b PPGTT, i915_gem_userptr_ioctl needs to check against max 48b range (1ULL << 48).
Whenever possible, read the PPGTT's total instead of the GTT one, this will be accurate in 32 and 48 bit modes.
v2: Use the default ctx to infer the ppgtt max size (Akash).
--- drivers/gpu/drm/i915/i915_gem_userptr.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-)
drivers/gpu/drm/i915/i915_gem_userptr.c +10 -2
@@ -789,8 +789,10 @@ int i915_gem_userptr_ioctl(struct drm_device *dev, void *data, struct drm_file *file) { struct drm_i915_private *dev_priv = dev->dev_private; +struct drm_i915_file_private *file_priv = file->driver_priv;struct drm_i915_gem_userptr *args = data;struct drm_i915_gem_object *obj; +struct intel_context *ctx;int ret;u32 handle;
@@ -801,8 +803,14 @@ i915_gem_userptr_ioctl(struct drm_device *dev, void *data, struct drm_file *fileif (offset_in_page (args->user_ptr | args->user_size))return -EINVAL ; -if (args->user_size > dev_priv->gtt.base.total) -return -E2BIG ; + ctx =i915_gem_context_get (file_priv,DEFAULT_CONTEXT_HANDLE ); +if (ctx->ppgtt) { +if (args->user_size > ctx->ppgtt->base.total) +return -E2BIG ; + }else { +if (args->user_size > dev_priv->gtt.base.total) +return -E2BIG ; + }if (!access_ok (args->flags &I915_USERPTR_READ_ONLY ?VERIFY_READ :VERIFY_WRITE , (char __user *)(unsigned long )args->user_ptr, args->user_size))
Signature · 6 lines
2.4.0 _______________________________________________ Intel-gfx mailing list [email protected] http://lists.freedesktop.org/mailman/listinfo/intel-gfx
PATCH 15/16 drm/i915: Wa32bitGeneralStateOffset & Wa32bitInstructionBaseOffset
In reply to Michel ThierryThere are some allocations that must be only referenced by 32bit offsets. To limit the chances of having the first 4GB already full, objects not requiring this workaround don't use the first 2 PDPs.
User must pass EXEC_OBJECT_NEEDS_32BADDRESS flag to indicate it needs a 32b address.
The flag is ignored in 32b PPGTT.
--- drivers/gpu/drm/i915/i915_drv.h | 1 + drivers/gpu/drm/i915/i915_gem.c | 11 +++++++++++ drivers/gpu/drm/i915/i915_gem_execbuffer.c | 3 +++ include/uapi/drm/i915_drm.h | 3 ++- 4 files changed, 17 insertions(+), 1 deletion(-)
drivers/gpu/drm/i915/i915_drv.h +1 -0
@@ -2714,6 +2714,7 @@ void i915_gem_vma_destroy(struct i915_vma *vma);#define PIN_OFFSET_BIAS (1<<3)#define PIN_USER (1<<4)#define PIN_UPDATE (1<<5) +#define PIN_FULL_RANGE (1<<6)#define PIN_OFFSET_MASK (~4095) int __must_check i915_gem_object_pin(struct drm_i915_gem_object *obj,
drivers/gpu/drm/i915/i915_gem.c +11 -0
@@ -3713,6 +3713,17 @@ i915_gem_object_bind_to_vm(struct drm_i915_gem_object *obj, obj->tiling_mode, false); size = flags &PIN_MAPPABLE ? fence_size : obj->base.size; + +/* Wa32bitGeneralStateOffset & Wa32bitInstructionBaseOffset, +* limit address to 4GB-1 for objects requiring this wa; for +* others, start on the 2nd PDP. +*/ +if (USES_FULL_48BIT_PPGTT (dev)) { +if (flags &PIN_FULL_RANGE ) + start += (2ULL <<GEN8_PDPE_SHIFT ); +else + end = ((4ULL <<GEN8_PDPE_SHIFT ) -1 ); + } }if (alignment ==0 )
drivers/gpu/drm/i915/i915_gem_execbuffer.c +3 -0
@@ -588,6 +588,9 @@ i915_gem_execbuffer_reserve_vma(struct i915_vma *vma,if (entry->flags &EXEC_OBJECT_NEEDS_GTT ) flags |=PIN_GLOBAL ; +if (!(entry->flags &EXEC_OBJECT_NEEDS_32BADDRESS )) + flags |=PIN_FULL_RANGE ; +if (!drm_mm_node_allocated (&vma->node)) {if (entry->flags & __EXEC_OBJECT_NEEDS_MAP) flags |=PIN_GLOBAL |PIN_MAPPABLE ;
include/uapi/drm/i915_drm.h +2 -1
@@ -680,7 +680,8 @@ struct drm_i915_gem_exec_object2 {#define EXEC_OBJECT_NEEDS_FENCE (1<<0)#define EXEC_OBJECT_NEEDS_GTT (1<<1)#define EXEC_OBJECT_WRITE (1<<2) -#define __EXEC_OBJECT_UNKNOWN_FLAGS -(EXEC_OBJECT_WRITE<<1) +#define EXEC_OBJECT_NEEDS_32BADDRESS (1<<3) +#define __EXEC_OBJECT_UNKNOWN_FLAGS -(EXEC_OBJECT_NEEDS_32BADDRESS<<1)__u64 flags;__u64 rsvd1;
Signature · 6 lines
2.4.0 _______________________________________________ Intel-gfx mailing list [email protected] http://lists.freedesktop.org/mailman/listinfo/intel-gfx
Re: [PATCH 15/16] drm/i915: Wa32bitGeneralStateOffset & Wa32bitInstructionBaseOffset
Quoted 70 lines · Michel Thierry
There are some allocations that must be only referenced by 32bit offsets. To limit the chances of having the first 4GB already full, objects not requiring this workaround don't use the first 2 PDPs.
User must pass
EXEC_OBJECT_NEEDS_32BADDRESSflag to indicate it needs a 32b address.The flag is ignored in 32b PPGTT.
Signed-off-by Michel Thierry <[email protected]>--- drivers/gpu/drm/i915/i915_drv.h | 1 + drivers/gpu/drm/i915/i915_gem.c | 11 +++++++++++ drivers/gpu/drm/i915/i915_gem_execbuffer.c | 3 +++ include/uapi/drm/i915_drm.h | 3 ++- 4 files changed, 17 insertions(+), 1 deletion(-)drivers/gpu/drm/i915/i915_drv.h +1
-0@@ -2714,6 +2714,7 @@ void i915_gem_vma_destroy(struct i915_vma *vma);#define PIN_OFFSET_BIAS (1<<3)#define PIN_USER (1<<4)#define PIN_UPDATE (1<<5) +#define PIN_FULL_RANGE (1<<6)#define PIN_OFFSET_MASK (~4095) int __must_check i915_gem_object_pin(struct drm_i915_gem_object *obj,drivers/gpu/drm/i915/i915_gem.c +11
-0@@ -3713,6 +3713,17 @@ i915_gem_object_bind_to_vm(struct drm_i915_gem_object *obj, obj->tiling_mode, false); size = flags &PIN_MAPPABLE ? fence_size : obj->base.size; + +/* Wa32bitGeneralStateOffset & Wa32bitInstructionBaseOffset, +* limit address to 4GB-1 for objects requiring this wa; for +* others, start on the 2nd PDP. +*/ +if (USES_FULL_48BIT_PPGTT (dev)) { +if (flags &PIN_FULL_RANGE ) + start += (2ULL <<GEN8_PDPE_SHIFT ); +else + end = ((4ULL <<GEN8_PDPE_SHIFT ) -1 ); + } }if (alignment ==0 )drivers/gpu/drm/i915/i915_gem_execbuffer.c +3
-0@@ -588,6 +588,9 @@ i915_gem_execbuffer_reserve_vma(struct i915_vma *vma,if (entry->flags &EXEC_OBJECT_NEEDS_GTT ) flags |=PIN_GLOBAL ; +if (!(entry->flags &EXEC_OBJECT_NEEDS_32BADDRESS )) + flags |=PIN_FULL_RANGE ; +if (!drm_mm_node_allocated (&vma->node)) {if (entry->flags & __EXEC_OBJECT_NEEDS_MAP) flags |=PIN_GLOBAL |PIN_MAPPABLE ;include/uapi/drm/i915_drm.h +0
-0
include/uapi/drm/i915_drm.h struct drm_i915_gem_exec_object2 { · line 684
Quoted 6 lines
include/uapi/drm/i915_drm.h +2
-1@@ -680,7 +680,8 @@ struct drm_i915_gem_exec_object2 {#define EXEC_OBJECT_NEEDS_FENCE (1<<0)#define EXEC_OBJECT_NEEDS_GTT (1<<1)#define EXEC_OBJECT_WRITE (1<<2) -#define __EXEC_OBJECT_UNKNOWN_FLAGS -(EXEC_OBJECT_WRITE<<1) +#define EXEC_OBJECT_NEEDS_32BADDRESS (1<<3) +#define __EXEC_OBJECT_UNKNOWN_FLAGS -(EXEC_OBJECT_NEEDS_32BADDRESS<<1)
This is the wrong way round for existing userspace (and remember, bdw is shipping already so we can't opt out of that). Instead the w/a needs to allow 32bit+ addresses only if the new bit is set.
Also this needs the usual pile of userspace enabling (libdrm+mesa). -Daniel
Quoted 10 lines
include/uapi/drm/i915_drm.h +0
-0__u64 flags;__u64 rsvd1;Signature · 6 lines
2.4.0 _______________________________________________ Intel-gfx mailing list [email protected] http://lists.freedesktop.org/mailman/listinfo/intel-gfx
Signature · 7 lines
Daniel Vetter Software Engineer, Intel Corporation http://blog.ffwll.ch _______________________________________________ Intel-gfx mailing list [email protected] http://lists.freedesktop.org/mailman/listinfo/intel-gfx
Re: [PATCH 15/16] drm/i915: Wa32bitGeneralStateOffset & Wa32bitInstructionBaseOffset
Quoted 81 lines · Daniel Vetter
Quoted 70 lines · Michel Thierry
There are some allocations that must be only referenced by 32bit offsets. To limit the chances of having the first 4GB already full, objects not requiring this workaround don't use the first 2 PDPs.
User must pass
EXEC_OBJECT_NEEDS_32BADDRESSflag to indicate it needs a 32b address.The flag is ignored in 32b PPGTT.
Signed-off-by Michel Thierry <[email protected]>--- drivers/gpu/drm/i915/i915_drv.h | 1 + drivers/gpu/drm/i915/i915_gem.c | 11 +++++++++++ drivers/gpu/drm/i915/i915_gem_execbuffer.c | 3 +++ include/uapi/drm/i915_drm.h | 3 ++- 4 files changed, 17 insertions(+), 1 deletion(-)drivers/gpu/drm/i915/i915_drv.h +1
-0@@ -2714,6 +2714,7 @@ void i915_gem_vma_destroy(struct i915_vma *vma);#define PIN_OFFSET_BIAS (1<<3)#define PIN_USER (1<<4)#define PIN_UPDATE (1<<5) +#define PIN_FULL_RANGE (1<<6)#define PIN_OFFSET_MASK (~4095) int __must_check i915_gem_object_pin(struct drm_i915_gem_object *obj,drivers/gpu/drm/i915/i915_gem.c +11
-0@@ -3713,6 +3713,17 @@ i915_gem_object_bind_to_vm(struct drm_i915_gem_object *obj, obj->tiling_mode, false); size = flags &PIN_MAPPABLE ? fence_size : obj->base.size; + +/* Wa32bitGeneralStateOffset & Wa32bitInstructionBaseOffset, +* limit address to 4GB-1 for objects requiring this wa; for +* others, start on the 2nd PDP. +*/ +if (USES_FULL_48BIT_PPGTT (dev)) { +if (flags &PIN_FULL_RANGE ) + start += (2ULL <<GEN8_PDPE_SHIFT ); +else + end = ((4ULL <<GEN8_PDPE_SHIFT ) -1 ); + } }if (alignment ==0 )drivers/gpu/drm/i915/i915_gem_execbuffer.c +3
-0@@ -588,6 +588,9 @@ i915_gem_execbuffer_reserve_vma(struct i915_vma *vma,if (entry->flags &EXEC_OBJECT_NEEDS_GTT ) flags |=PIN_GLOBAL ; +if (!(entry->flags &EXEC_OBJECT_NEEDS_32BADDRESS )) + flags |=PIN_FULL_RANGE ; +if (!drm_mm_node_allocated (&vma->node)) {if (entry->flags & __EXEC_OBJECT_NEEDS_MAP) flags |=PIN_GLOBAL |PIN_MAPPABLE ;include/uapi/drm/i915_drm.h +0
-0include/uapi/drm/i915_drm.h struct drm_i915_gem_exec_object2 { · line 684
Quoted 6 lines
include/uapi/drm/i915_drm.h +2
-1@@ -680,7 +680,8 @@ struct drm_i915_gem_exec_object2 {#define EXEC_OBJECT_NEEDS_FENCE (1<<0)#define EXEC_OBJECT_NEEDS_GTT (1<<1)#define EXEC_OBJECT_WRITE (1<<2) -#define __EXEC_OBJECT_UNKNOWN_FLAGS -(EXEC_OBJECT_WRITE<<1) +#define EXEC_OBJECT_NEEDS_32BADDRESS (1<<3) +#define __EXEC_OBJECT_UNKNOWN_FLAGS -(EXEC_OBJECT_NEEDS_32BADDRESS<<1)This is the wrong way round for existing userspace (and remember, bdw is shipping already so we can't opt out of that). Instead the w/a needs to allow 32bit+ addresses only if the new bit is set.
Quoted 2 lines
Also this needs the usual pile of userspace enabling (libdrm+mesa). -Daniel
Hi,
Ok, I'll change it to something like EXEC_OBJECT_SUPPORTS_48BADDRESS.
--Michel
Quoted 10 lines
Quoted 10 lines
include/uapi/drm/i915_drm.h +0
-0__u64 flags;__u64 rsvd1;Signature · 6 lines
2.4.0 _______________________________________________ Intel-gfx mailing list [email protected] http://lists.freedesktop.org/mailman/listinfo/intel-gfx
_______________________________________________
Intel-gfx mailing list
[email protected]
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
Re: [PATCH 15/16] drm/i915: Wa32bitGeneralStateOffset & Wa32bitInstructionBaseOffset
In reply to Daniel VetterQuoted 6 lines · Daniel Vetter
Quoted 5 lines · Michel Thierry
There are some allocations that must be only referenced by 32bit offsets.
To limit the chances of having the first 4GB already full, objects not requiring this workaround don't use the first 2 PDPs.
This is complete tosh. Please have a later patch that uses SEARCH_BELOW for 48bit objects, and cite eviction rates and improvements.
Quoted 5 lines
This is the wrong way round for existing userspace (and remember, bdw is shipping already so we can't opt out of that). Instead the w/a needs to allow 32bit+ addresses only if the new bit is set.
Also this needs the usual pile of userspace enabling (libdrm+mesa).
Indeed, the code is very much broken as is. So I expect to see a
Testcase: igt/gem_exec_48bit in the next patch.
As a hint, consider reusing the object.
-Chris
Signature · 5 lines
Chris Wilson, Intel Open Source Technology Centre _______________________________________________ Intel-gfx mailing list [email protected] http://lists.freedesktop.org/mailman/listinfo/intel-gfx
Re: [PATCH 15/16] drm/i915: Wa32bitGeneralStateOffset & Wa32bitInstructionBaseOffset
Quoted 10 lines · Chris Wilson
Quoted 6 lines · Daniel Vetter
Quoted 5 lines · Michel Thierry
There are some allocations that must be only referenced by 32bit offsets.
To limit the chances of having the first 4GB already full, objects not requiring this workaround don't use the first 2 PDPs.
This is complete tosh. Please have a later patch that uses
SEARCH_BELOWfor 48bit objects, and cite eviction rates and improvements.
Yeah didn't spot that at first, I agree that trying to segregate objects upfront is premature optimization. There's very few state objects (compard to textures), usually of differen size classes and different lifetimes. And they should all be reused anyway for efficient, so after a few rounds of execbuf things should settle in nicely.
Let's avoid a bit of complexity here when not yet proven to be required. -Daniel
Signature · 7 lines
Daniel Vetter Software Engineer, Intel Corporation http://blog.ffwll.ch _______________________________________________ Intel-gfx mailing list [email protected] http://lists.freedesktop.org/mailman/listinfo/intel-gfx
PATCH 16/16 drm/i915/gen8: Flip the 48b switch
In reply to Michel ThierryUse 48b addresses if hw supports it and i915.enable_ppgtt=3.
Note, aliasing PPGTT remains 32b only.
--- drivers/gpu/drm/i915/i915_gem_gtt.c | 5 +---- drivers/gpu/drm/i915/i915_params.c | 2 +- 2 files changed, 2 insertions(+), 5 deletions(-)
drivers/gpu/drm/i915/i915_gem_gtt.c +1 -4
@@ -111,7 +111,7 @@ static int sanitize_enable_ppgtt(struct drm_device *dev, int enable_ppgtt)#ifdef CONFIG_64BIT has_full_64bit_ppgtt = (IS_BROADWELL (dev) || -INTEL_INFO (dev)->gen >=9 ) && false;/* FIXME: 64b */ +INTEL_INFO (dev)->gen >=9 );#else has_full_64bit_ppgtt = false;#endif
@@ -1164,9 +1164,6 @@ gen8_ppgtt_alloc_page_directories(struct i915_address_space *vm,WARN_ON (!bitmap_empty (new_pds, pdpes)); -/* FIXME: upper bound must not overflow 32 bits */ -WARN_ON ((start + length) > (1ULL <<32 )); -gen8_for_each_pdpe (pd, pdp, start, length, temp, pdpe) {if (pd)continue ;
drivers/gpu/drm/i915/i915_params.c +1 -1
@@ -116,7 +116,7 @@ MODULE_PARM_DESC(enable_hangcheck,module_param_named_unsafe (enable_ppgtt, i915.enable_ppgtt, int,0400 );MODULE_PARM_DESC (enable_ppgtt,"Override PPGTT usage. " -"(-1=auto [default], 0=disabled, 1=aliasing, 2=full)" ); +"(-1=auto [default], 0=disabled, 1=aliasing, 2=full, 3=full_64b)" );module_param_named (enable_execlists, i915.enable_execlists, int,0400 ); MODULE_PARM_DESC(enable_execlists,
Signature · 6 lines
2.4.0 _______________________________________________ Intel-gfx mailing list [email protected] http://lists.freedesktop.org/mailman/listinfo/intel-gfx
PATCH 1/1 tests/gem_ppgtt: Check Wa32bitOffsets workarounds
In reply to Michel ThierryTest EXEC_OBJECT_NEEDS_32BADDRESS flag to use reserved 32b segment. Driver will try to use lower PDPs of each PPGTT for the objects requiring Wa32bitGeneralStateOffset or Wa32bitInstructionBaseOffset.
--- tests/gem_ppgtt.c | 90 +++++++++++++++++++++++++++++++++++++++++++++++++++---- 1 file changed, 85 insertions(+), 5 deletions(-)
tests/gem_ppgtt.c +85 -5
@@ -48,7 +48,15 @@#define HEIGHT 512#define SIZE (HEIGHT*STRIDE) -static bool uses_full_ppgtt (int fd) +#define EXEC_OBJECT_NEEDS_32BADDR (1<<3) + +/* +* 0 - No PPGTT +* 1 - Aliasing PPGTT +* 2 - Full PPGTT (32b) +* 3 - Full PPGTT (48b) +*/ +static bool __uses_full_ppgtt (int fd,int min) {struct drm_i915_getparam gp;int val =0 ;
@@ -61,7 +69,17 @@ static bool uses_full_ppgtt(int fd)return 0 ; errno =0 ; -return val >1 ; +return val >= min; +} + +static bool uses_full_ppgtt (int fd) +{ +return __uses_full_ppgtt (fd,2 ); +} + +static bool uses_48b_full_ppgtt (int fd) +{ +return __uses_full_ppgtt (fd,3 ); } static drm_intel_bo *create_bo(drm_intel_bufmgr *bufmgr,
@@ -216,7 +234,7 @@ static void surfaces_check(dri_bo **bo, int count, uint32_t expected) } } -static uint64_t exec_and_get_offset (int fd,uint32_t batch) +static uint64_t exec_and_get_offset (int fd,uint32_t batch,bool needs_32b_addr) {struct drm_i915_gem_execbuffer2 execbuf;struct drm_i915_gem_exec_object2 exec[1 ];
@@ -226,6 +244,7 @@ static uint64_t exec_and_get_offset(int fd, uint32_t batch)memset (exec,0 ,sizeof (exec)); exec[0 ].handle = batch; + exec[0 ].flags = (needs_32b_addr) ?EXEC_OBJECT_NEEDS_32BADDR :0 ;memset (&execbuf,0 ,sizeof (execbuf)); execbuf.buffers_ptr = (uintptr_t )exec;
@@ -252,7 +271,7 @@ static void flink_and_close(void) fd2 =drm_open_any (); flinked_bo =gem_open (fd2, name); - offset =exec_and_get_offset (fd2, flinked_bo); + offset =exec_and_get_offset (fd2, flinked_bo,0 );gem_sync (fd2, flinked_bo);gem_close (fd2, flinked_bo);
@@ -260,7 +279,7 @@ static void flink_and_close(void)* same size should get the same offset */ new_bo =gem_create (fd2,4096 ); - offset_new =exec_and_get_offset (fd2, new_bo); + offset_new =exec_and_get_offset (fd2, new_bo,0 );gem_close (fd2, new_bo);igt_assert_eq (offset, offset_new);
@@ -270,6 +289,64 @@ static void flink_and_close(void)close (fd2); } +static void createbo_and_compare_offsets (uint32_t fd,uint32_t fd2, +bool needs_32b,bool needs_32b2) +{ +uint32_t bo, bo2; +uint64_t offset, offset2; + + bo =gem_create (fd,4096 ); + offset =exec_and_get_offset (fd, bo, needs_32b); +gem_sync (fd, bo); + + bo2 =gem_create (fd2,4096 ); + offset2 =exec_and_get_offset (fd2, bo2, needs_32b2); +gem_sync (fd2, bo2); + +if (needs_32b == needs_32b2) +igt_assert_eq (offset, offset2); +else +igt_assert_neq (offset, offset2); + + +/* lower PDPs of each PPGTT are reserved for the objects +* requiring this workaround +*/ +if (needs_32b) +igt_assert (offset < (1ULL <<32 )); + +if (needs_32b2) +igt_assert (offset2 < (1ULL <<32 )); + +gem_close (fd, bo); +gem_close (fd2, bo2); +} + + +static void wa_32b_offset_test (void ) +{ +uint32_t fd, fd2; + + fd =drm_open_any (); +igt_require (uses_48b_full_ppgtt (fd)); + + fd2 =drm_open_any (); + +/* allow full addr range */ +createbo_and_compare_offsets (fd, fd2,0 ,0 ); + +/* limit 32b addr range */ +createbo_and_compare_offsets (fd, fd2,1 ,1 ); + +/* mixed */ +createbo_and_compare_offsets (fd, fd2,0 ,1 ); +createbo_and_compare_offsets (fd, fd2,1 ,0 ); + +close (fd); +close (fd2); +} + +#define N_CHILD 8int main (int argc,char **argv) {
@@ -302,5 +379,8 @@ int main(int argc, char **argv) igt_subtest("flink-and-close-vma-leak")flink_and_close (); + igt_subtest("wa-32b-offset-test") +wa_32b_offset_test (); +igt_exit (); }
Signature · 6 lines
2.3.6 _______________________________________________ Intel-gfx mailing list [email protected] http://lists.freedesktop.org/mailman/listinfo/intel-gfx