[Intel-xe] [PATCH v3 10/31] drm/xe: Move VRAM from GT to tile
Gustavo Sousa
gustavo.sousa at intel.com
Wed May 31 19:24:44 UTC 2023
Quoting Matt Roper (2023-05-30 18:15:28-03:00)
>On platforms with VRAM, the VRAM is associated with the tile, not the
>GT.
>
>v2:
> - Unsquash the GGTT handling back into its own patch.
> - Fix kunit test build
>v3:
> - Tweak the "FIXME" comment to clarify that this function will be
> completely gone by the end of the series. (Lucas)
>
>Signed-off-by: Matt Roper <matthew.d.roper at intel.com>
>Reviewed-by: Lucas De Marchi <lucas.demarchi at intel.com>
>---
> drivers/gpu/drm/xe/Makefile | 1 +
> drivers/gpu/drm/xe/tests/xe_bo.c | 6 +-
> drivers/gpu/drm/xe/xe_bo.c | 44 ++++++------
> drivers/gpu/drm/xe/xe_bo.h | 4 +-
> drivers/gpu/drm/xe/xe_device.c | 14 ++--
> drivers/gpu/drm/xe/xe_device_types.h | 30 ++++++++
> drivers/gpu/drm/xe/xe_gt.c | 82 ++--------------------
> drivers/gpu/drm/xe/xe_gt_pagefault.c | 6 +-
> drivers/gpu/drm/xe/xe_gt_types.h | 37 ----------
> drivers/gpu/drm/xe/xe_irq.c | 2 +-
> drivers/gpu/drm/xe/xe_mmio.c | 51 +++++++-------
> drivers/gpu/drm/xe/xe_mmio.h | 2 +-
> drivers/gpu/drm/xe/xe_pci.c | 2 -
> drivers/gpu/drm/xe/xe_query.c | 4 +-
> drivers/gpu/drm/xe/xe_res_cursor.h | 2 +-
> drivers/gpu/drm/xe/xe_tile.c | 33 ++++++++-
> drivers/gpu/drm/xe/xe_ttm_stolen_mgr.c | 18 ++---
> drivers/gpu/drm/xe/xe_ttm_vram_mgr.c | 16 ++---
> drivers/gpu/drm/xe/xe_ttm_vram_mgr.h | 4 +-
> drivers/gpu/drm/xe/xe_ttm_vram_mgr_types.h | 6 +-
> 20 files changed, 161 insertions(+), 203 deletions(-)
>
>diff --git a/drivers/gpu/drm/xe/Makefile b/drivers/gpu/drm/xe/Makefile
>index da1e447c08c7..f34d4bdd510b 100644
>--- a/drivers/gpu/drm/xe/Makefile
>+++ b/drivers/gpu/drm/xe/Makefile
>@@ -97,6 +97,7 @@ xe-y += xe_bb.o \
> xe_sched_job.o \
> xe_step.o \
> xe_sync.o \
>+ xe_tile.o \
This was probably meant to be in the patch with subject "drm/xe: Move GGTT from
GT to tile".
> xe_trace.o \
> xe_ttm_sys_mgr.o \
> xe_ttm_stolen_mgr.o \
>diff --git a/drivers/gpu/drm/xe/tests/xe_bo.c b/drivers/gpu/drm/xe/tests/xe_bo.c
>index 8f3afdc6cca6..6235a6c73a06 100644
>--- a/drivers/gpu/drm/xe/tests/xe_bo.c
>+++ b/drivers/gpu/drm/xe/tests/xe_bo.c
>@@ -115,9 +115,9 @@ static void ccs_test_run_gt(struct xe_device *xe, struct xe_gt *gt,
> int ret;
>
> /* TODO: Sanity check */
>- vram_bit = XE_BO_CREATE_VRAM0_BIT << gt->info.vram_id;
>+ vram_bit = XE_BO_CREATE_VRAM0_BIT << gt_to_tile(gt)->id;
> kunit_info(test, "Testing gt id %u vram id %u\n", gt->info.id,
>- gt->info.vram_id);
>+ gt_to_tile(gt)->id);
>
> bo = xe_bo_create_locked(xe, NULL, NULL, SZ_1M, ttm_bo_type_device,
> vram_bit);
>@@ -179,7 +179,7 @@ static int evict_test_run_gt(struct xe_device *xe, struct xe_gt *gt, struct kuni
> int err, i;
>
> kunit_info(test, "Testing device %s gt id %u vram id %u\n",
>- dev_name(xe->drm.dev), gt->info.id, gt->info.vram_id);
>+ dev_name(xe->drm.dev), gt->info.id, gt_to_tile(gt)->id);
>
> for (i = 0; i < 2; ++i) {
> xe_vm_lock(vm, &ww, 0, false);
>diff --git a/drivers/gpu/drm/xe/xe_bo.c b/drivers/gpu/drm/xe/xe_bo.c
>index 09a9c121a84d..17de7cc5fe36 100644
>--- a/drivers/gpu/drm/xe/xe_bo.c
>+++ b/drivers/gpu/drm/xe/xe_bo.c
>@@ -71,25 +71,25 @@ static bool xe_bo_is_user(struct xe_bo *bo)
> return bo->flags & XE_BO_CREATE_USER_BIT;
> }
>
>-static struct xe_gt *
>-mem_type_to_gt(struct xe_device *xe, u32 mem_type)
>+static struct xe_tile *
>+mem_type_to_tile(struct xe_device *xe, u32 mem_type)
> {
> XE_BUG_ON(mem_type != XE_PL_STOLEN && !mem_type_is_vram(mem_type));
>
>- return xe_device_get_gt(xe, mem_type == XE_PL_STOLEN ? 0 : (mem_type - XE_PL_VRAM0));
>+ return &xe->tiles[mem_type == XE_PL_STOLEN ? 0 : (mem_type - XE_PL_VRAM0)];
> }
>
> /**
>- * xe_bo_to_gt() - Get a GT from a BO's memory location
>+ * xe_bo_to_tile() - Get a tile from a BO's memory location
> * @bo: The buffer object
> *
>- * Get a GT from a BO's memory location, should be called on BOs in VRAM only.
>+ * Get a tile from a BO's memory location, should be called on BOs in VRAM only.
> *
>- * Return: xe_gt object which is closest to the BO
>+ * Return: xe_tile object which is closest to the BO
> */
>-struct xe_gt *xe_bo_to_gt(struct xe_bo *bo)
>+struct xe_tile *xe_bo_to_tile(struct xe_bo *bo)
> {
>- return mem_type_to_gt(xe_bo_device(bo), bo->ttm.resource->mem_type);
>+ return mem_type_to_tile(xe_bo_device(bo), bo->ttm.resource->mem_type);
> }
>
> static void try_add_system(struct xe_bo *bo, struct ttm_place *places,
>@@ -109,9 +109,9 @@ static void try_add_system(struct xe_bo *bo, struct ttm_place *places,
> static void add_vram(struct xe_device *xe, struct xe_bo *bo,
> struct ttm_place *places, u32 bo_flags, u32 mem_type, u32 *c)
> {
>- struct xe_gt *gt = mem_type_to_gt(xe, mem_type);
>+ struct xe_tile *tile = mem_type_to_tile(xe, mem_type);
>
>- XE_BUG_ON(!gt->mem.vram.size);
>+ XE_BUG_ON(!tile->mem.vram.size);
>
> places[*c] = (struct ttm_place) {
> .mem_type = mem_type,
>@@ -362,7 +362,7 @@ static int xe_ttm_io_mem_reserve(struct ttm_device *bdev,
> struct ttm_resource *mem)
> {
> struct xe_device *xe = ttm_to_xe_device(bdev);
>- struct xe_gt *gt;
>+ struct xe_tile *tile;
>
> switch (mem->mem_type) {
> case XE_PL_SYSTEM:
>@@ -370,15 +370,15 @@ static int xe_ttm_io_mem_reserve(struct ttm_device *bdev,
> return 0;
> case XE_PL_VRAM0:
> case XE_PL_VRAM1:
>- gt = mem_type_to_gt(xe, mem->mem_type);
>+ tile = mem_type_to_tile(xe, mem->mem_type);
> mem->bus.offset = mem->start << PAGE_SHIFT;
>
>- if (gt->mem.vram.mapping &&
>+ if (tile->mem.vram.mapping &&
> mem->placement & TTM_PL_FLAG_CONTIGUOUS)
>- mem->bus.addr = (u8 *)gt->mem.vram.mapping +
>+ mem->bus.addr = (u8 *)tile->mem.vram.mapping +
> mem->bus.offset;
>
>- mem->bus.offset += gt->mem.vram.io_start;
>+ mem->bus.offset += tile->mem.vram.io_start;
> mem->bus.is_iomem = true;
>
> #if !defined(CONFIG_X86)
>@@ -638,9 +638,9 @@ static int xe_bo_move(struct ttm_buffer_object *ttm_bo, bool evict,
> if (bo->gt)
> gt = bo->gt;
> else if (resource_is_vram(new_mem))
>- gt = mem_type_to_gt(xe, new_mem->mem_type);
>+ gt = &mem_type_to_tile(xe, new_mem->mem_type)->primary_gt;
> else if (resource_is_vram(old_mem))
>- gt = mem_type_to_gt(xe, old_mem->mem_type);
>+ gt = &mem_type_to_tile(xe, old_mem->mem_type)->primary_gt;
>
> XE_BUG_ON(!gt);
> XE_BUG_ON(!gt->migrate);
>@@ -664,7 +664,7 @@ static int xe_bo_move(struct ttm_buffer_object *ttm_bo, bool evict,
>
> /* Create a new VMAP once kernel BO back in VRAM */
> if (!ret && resource_is_vram(new_mem)) {
>- void *new_addr = gt->mem.vram.mapping +
>+ void *new_addr = gt_to_tile(gt)->mem.vram.mapping +
> (new_mem->start << PAGE_SHIFT);
>
> if (XE_WARN_ON(new_mem->start == XE_BO_INVALID_OFFSET)) {
>@@ -836,14 +836,14 @@ static unsigned long xe_ttm_io_mem_pfn(struct ttm_buffer_object *ttm_bo,
> {
> struct xe_device *xe = ttm_to_xe_device(ttm_bo->bdev);
> struct xe_bo *bo = ttm_to_xe_bo(ttm_bo);
>- struct xe_gt *gt = mem_type_to_gt(xe, ttm_bo->resource->mem_type);
>+ struct xe_tile *tile = mem_type_to_tile(xe, ttm_bo->resource->mem_type);
> struct xe_res_cursor cursor;
>
> if (ttm_bo->resource->mem_type == XE_PL_STOLEN)
> return xe_ttm_stolen_io_offset(bo, page_offset << PAGE_SHIFT) >> PAGE_SHIFT;
>
> xe_res_first(ttm_bo->resource, (u64)page_offset << PAGE_SHIFT, 0, &cursor);
>- return (gt->mem.vram.io_start + cursor.start) >> PAGE_SHIFT;
>+ return (tile->mem.vram.io_start + cursor.start) >> PAGE_SHIFT;
> }
>
> static void __xe_bo_vunmap(struct xe_bo *bo);
>@@ -1344,12 +1344,12 @@ struct xe_bo *xe_bo_create_from_data(struct xe_device *xe, struct xe_gt *gt,
> uint64_t vram_region_gpu_offset(struct ttm_resource *res)
> {
> struct xe_device *xe = ttm_to_xe_device(res->bo->bdev);
>- struct xe_gt *gt = mem_type_to_gt(xe, res->mem_type);
>+ struct xe_tile *tile = mem_type_to_tile(xe, res->mem_type);
>
> if (res->mem_type == XE_PL_STOLEN)
> return xe_ttm_stolen_gpu_offset(xe);
>
>- return xe->mem.vram.base + gt->mem.vram.base;
>+ return xe->mem.vram.base + tile->mem.vram.base;
> }
>
> /**
>diff --git a/drivers/gpu/drm/xe/xe_bo.h b/drivers/gpu/drm/xe/xe_bo.h
>index d945675a259f..2cad82510201 100644
>--- a/drivers/gpu/drm/xe/xe_bo.h
>+++ b/drivers/gpu/drm/xe/xe_bo.h
>@@ -22,7 +22,7 @@
> /* -- */
> #define XE_BO_CREATE_STOLEN_BIT BIT(4)
> #define XE_BO_CREATE_VRAM_IF_DGFX(gt) \
>- (IS_DGFX(gt_to_xe(gt)) ? XE_BO_CREATE_VRAM0_BIT << gt->info.vram_id : \
>+ (IS_DGFX(gt_to_xe(gt)) ? XE_BO_CREATE_VRAM0_BIT << gt_to_tile(gt)->id : \
> XE_BO_CREATE_SYSTEM_BIT)
> #define XE_BO_CREATE_GGTT_BIT BIT(5)
> #define XE_BO_CREATE_IGNORE_MIN_PAGE_SIZE_BIT BIT(6)
>@@ -108,7 +108,7 @@ struct xe_bo *xe_bo_create_from_data(struct xe_device *xe, struct xe_gt *gt,
> int xe_bo_placement_for_flags(struct xe_device *xe, struct xe_bo *bo,
> u32 bo_flags);
>
>-struct xe_gt *xe_bo_to_gt(struct xe_bo *bo);
>+struct xe_tile *xe_bo_to_tile(struct xe_bo *bo);
>
> static inline struct xe_bo *ttm_to_xe_bo(const struct ttm_buffer_object *bo)
> {
>diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c
>index dd4a4a6e0b94..cf28b0f150ed 100644
>--- a/drivers/gpu/drm/xe/xe_device.c
>+++ b/drivers/gpu/drm/xe/xe_device.c
>@@ -28,6 +28,7 @@
> #include "xe_pcode.h"
> #include "xe_pm.h"
> #include "xe_query.h"
>+#include "xe_tile.h"
> #include "xe_ttm_stolen_mgr.h"
> #include "xe_ttm_sys_mgr.h"
> #include "xe_vm.h"
>@@ -244,6 +245,7 @@ static void xe_device_sanitize(struct drm_device *drm, void *arg)
>
> int xe_device_probe(struct xe_device *xe)
> {
>+ struct xe_tile *tile;
> struct xe_gt *gt;
> int err;
> u8 id;
>@@ -253,8 +255,12 @@ int xe_device_probe(struct xe_device *xe)
> if (err)
> return err;
>
>- for_each_gt(gt, xe, id) {
>- err = xe_gt_alloc(xe, gt);
>+ for_each_tile(tile, xe, id) {
>+ err = xe_tile_alloc(tile);
>+ if (err)
>+ return err;
>+
>+ err = xe_gt_alloc(xe, &tile->primary_gt);
This also seems to belong to "drm/xe: Move GGTT from GT to tile".
> if (err)
> return err;
> }
>@@ -289,8 +295,8 @@ int xe_device_probe(struct xe_device *xe)
>
> xe_ttm_sys_mgr_init(xe);
>
>- for_each_gt(gt, xe, id) {
>- err = xe_gt_init_noalloc(gt);
>+ for_each_tile(tile, xe, id) {
>+ err = xe_tile_init_noalloc(tile);
As well as this.
> if (err)
> goto err_irq_shutdown;
> }
>diff --git a/drivers/gpu/drm/xe/xe_device_types.h b/drivers/gpu/drm/xe/xe_device_types.h
>index d7b809253eb9..ab8310525f7b 100644
>--- a/drivers/gpu/drm/xe/xe_device_types.h
>+++ b/drivers/gpu/drm/xe/xe_device_types.h
>@@ -102,6 +102,36 @@ struct xe_tile {
>
> /** @mem: memory management info for tile */
> struct {
>+ /**
>+ * @vram: VRAM info for tile.
>+ *
>+ * Although VRAM is associated with a specific tile, it can
>+ * still be accessed by all tiles' GTs.
>+ */
>+ struct {
>+ /** @io_start: IO start address of this VRAM instance */
>+ resource_size_t io_start;
>+ /**
>+ * @io_size: IO size of this VRAM instance
>+ *
>+ * This represents how much of this VRAM we can access
>+ * via the CPU through the VRAM BAR. This can be smaller
>+ * than @size, in which case only part of VRAM is CPU
>+ * accessible (typically the first 256M). This
>+ * configuration is known as small-bar.
>+ */
>+ resource_size_t io_size;
>+ /** @base: offset of VRAM starting base */
>+ resource_size_t base;
>+ /** @size: size of VRAM. */
>+ resource_size_t size;
>+ /** @mapping: pointer to VRAM mappable space */
>+ void *__iomem mapping;
>+ } vram;
>+
>+ /** @vram_mgr: VRAM TTM manager */
>+ struct xe_ttm_vram_mgr *vram_mgr;
>+
> /** @ggtt: Global graphics translation table */
> struct xe_ggtt *ggtt;
> } mem;
>diff --git a/drivers/gpu/drm/xe/xe_gt.c b/drivers/gpu/drm/xe/xe_gt.c
>index 0f07f810bb1f..419fc471053c 100644
>--- a/drivers/gpu/drm/xe/xe_gt.c
>+++ b/drivers/gpu/drm/xe/xe_gt.c
>@@ -37,7 +37,6 @@
> #include "xe_ring_ops.h"
> #include "xe_sa.h"
> #include "xe_sched_job.h"
>-#include "xe_ttm_vram_mgr.h"
> #include "xe_tuning.h"
> #include "xe_uc.h"
> #include "xe_vm.h"
>@@ -46,58 +45,22 @@
>
> struct xe_gt *xe_find_full_gt(struct xe_gt *gt)
> {
>- struct xe_gt *search;
>- u8 id;
>-
>- XE_BUG_ON(!xe_gt_is_media_type(gt));
>-
>- for_each_gt(search, gt_to_xe(gt), id) {
>- if (search->info.vram_id == gt->info.vram_id)
>- return search;
>- }
>-
>- XE_BUG_ON("NOT POSSIBLE");
>- return NULL;
>+ /*
>+ * FIXME: Once the code is prepared for re-enabling, this function will
>+ * be gone. Just return the only possible gt for now.
>+ */
>+ return gt;
> }
>
> int xe_gt_alloc(struct xe_device *xe, struct xe_gt *gt)
> {
>- struct drm_device *drm = &xe->drm;
>-
> XE_BUG_ON(gt->info.type == XE_GT_TYPE_UNINITIALIZED);
>
>- if (!xe_gt_is_media_type(gt)) {
>- gt->mem.vram_mgr = drmm_kzalloc(drm, sizeof(*gt->mem.vram_mgr),
>- GFP_KERNEL);
>- if (!gt->mem.vram_mgr)
>- return -ENOMEM;
>-
>- } else {
>- struct xe_gt *full_gt = xe_find_full_gt(gt);
>-
>- gt->mem.vram_mgr = full_gt->mem.vram_mgr;
>- }
>-
> gt->ordered_wq = alloc_ordered_workqueue("gt-ordered-wq", 0);
>
> return 0;
> }
>
>-static int gt_ttm_mgr_init(struct xe_gt *gt)
>-{
>- struct xe_device *xe = gt_to_xe(gt);
>- int err;
>-
>- if (gt->mem.vram.size) {
>- err = xe_ttm_vram_mgr_init(gt, gt->mem.vram_mgr);
>- if (err)
>- return err;
>- xe->info.mem_region_mask |= BIT(gt->info.vram_id) << 1;
>- }
>-
>- return 0;
>-}
>-
> void xe_gt_sanitize(struct xe_gt *gt)
> {
> /*
>@@ -321,41 +284,6 @@ int xe_gt_init_early(struct xe_gt *gt)
> return 0;
> }
>
>-/**
>- * xe_gt_init_noalloc - Init GT up to the point where allocations can happen.
>- * @gt: The GT to initialize.
>- *
>- * This function prepares the GT to allow memory allocations to VRAM, but is not
>- * allowed to allocate memory itself. This state is useful for display readout,
>- * because the inherited display framebuffer will otherwise be overwritten as it
>- * is usually put at the start of VRAM.
>- *
>- * Returns: 0 on success, negative error code on error.
>- */
>-int xe_gt_init_noalloc(struct xe_gt *gt)
>-{
>- int err, err2;
>-
>- if (xe_gt_is_media_type(gt))
>- return 0;
>-
>- xe_device_mem_access_get(gt_to_xe(gt));
>- err = xe_force_wake_get(gt_to_fw(gt), XE_FW_GT);
>- if (err)
>- goto err;
>-
>- err = gt_ttm_mgr_init(gt);
>- if (err)
>- goto err_force_wake;
>-
>-err_force_wake:
>- err2 = xe_force_wake_put(gt_to_fw(gt), XE_FW_GT);
>- XE_WARN_ON(err2);
>- xe_device_mem_access_put(gt_to_xe(gt));
>-err:
>- return err;
>-}
>-
> static int gt_fw_domain_init(struct xe_gt *gt)
> {
> int err, i;
>diff --git a/drivers/gpu/drm/xe/xe_gt_pagefault.c b/drivers/gpu/drm/xe/xe_gt_pagefault.c
>index 1677640e1075..f4f3d95ae6b1 100644
>--- a/drivers/gpu/drm/xe/xe_gt_pagefault.c
>+++ b/drivers/gpu/drm/xe/xe_gt_pagefault.c
>@@ -107,6 +107,7 @@ static struct xe_vma *lookup_vma(struct xe_vm *vm, u64 page_addr)
> static int handle_pagefault(struct xe_gt *gt, struct pagefault *pf)
> {
> struct xe_device *xe = gt_to_xe(gt);
>+ struct xe_tile *tile = gt_to_tile(gt);
> struct xe_vm *vm;
> struct xe_vma *vma = NULL;
> struct xe_bo *bo;
>@@ -195,7 +196,7 @@ static int handle_pagefault(struct xe_gt *gt, struct pagefault *pf)
> }
>
> /* Migrate to VRAM, move should invalidate the VMA first */
>- ret = xe_bo_migrate(bo, XE_PL_VRAM0 + gt->info.vram_id);
>+ ret = xe_bo_migrate(bo, XE_PL_VRAM0 + tile->id);
> if (ret)
> goto unlock_dma_resv;
> } else if (bo) {
>@@ -498,6 +499,7 @@ static struct xe_vma *get_acc_vma(struct xe_vm *vm, struct acc *acc)
> static int handle_acc(struct xe_gt *gt, struct acc *acc)
> {
> struct xe_device *xe = gt_to_xe(gt);
>+ struct xe_tile *tile = gt_to_tile(gt);
> struct xe_vm *vm;
> struct xe_vma *vma;
> struct xe_bo *bo;
>@@ -553,7 +555,7 @@ static int handle_acc(struct xe_gt *gt, struct acc *acc)
> goto unlock_vm;
>
> /* Migrate to VRAM, move should invalidate the VMA first */
>- ret = xe_bo_migrate(bo, XE_PL_VRAM0 + gt->info.vram_id);
>+ ret = xe_bo_migrate(bo, XE_PL_VRAM0 + tile->id);
>
> if (only_needs_bo_lock(bo))
> xe_bo_unlock(bo, &ww);
>diff --git a/drivers/gpu/drm/xe/xe_gt_types.h b/drivers/gpu/drm/xe/xe_gt_types.h
>index c06a0b27d6fc..a040ec896e70 100644
>--- a/drivers/gpu/drm/xe/xe_gt_types.h
>+++ b/drivers/gpu/drm/xe/xe_gt_types.h
>@@ -16,8 +16,6 @@
> struct xe_engine_ops;
> struct xe_migrate;
> struct xe_ring_ops;
>-struct xe_ttm_gtt_mgr;
>-struct xe_ttm_vram_mgr;
>
> enum xe_gt_type {
> XE_GT_TYPE_UNINITIALIZED,
>@@ -108,8 +106,6 @@ struct xe_gt {
> enum xe_gt_type type;
> /** @id: id of GT */
> u8 id;
>- /** @vram: id of the VRAM for this GT */
>- u8 vram_id;
> /** @clock_freq: clock frequency */
> u32 clock_freq;
> /** @engine_mask: mask of engines present on GT */
>@@ -144,39 +140,6 @@ struct xe_gt {
> */
> struct xe_reg_sr reg_sr;
>
>- /**
>- * @mem: memory management info for GT, multiple GTs can point to same
>- * objects (virtual split)
>- */
>- struct {
>- /**
>- * @vram: VRAM info for GT, multiple GTs can point to same info
>- * (virtual split), can be subset of global device VRAM
>- */
>- struct {
>- /** @io_start: IO start address of this VRAM instance */
>- resource_size_t io_start;
>- /**
>- * @io_size: IO size of this VRAM instance
>- *
>- * This represents how much of the VRAM the CPU can access
>- * via the VRAM BAR.
>- * This can be smaller than the actual @size, in which
>- * case only part of VRAM is CPU accessible (typically
>- * the first 256M). This configuration is known as small-bar.
>- */
>- resource_size_t io_size;
>- /** @base: offset of VRAM starting base */
>- resource_size_t base;
>- /** @size: size of VRAM. */
>- resource_size_t size;
>- /** @mapping: pointer to VRAM mappable space */
>- void *__iomem mapping;
>- } vram;
>- /** @vram_mgr: VRAM TTM manager */
>- struct xe_ttm_vram_mgr *vram_mgr;
>- } mem;
>-
> /** @reset: state for GT resets */
> struct {
> /**
>diff --git a/drivers/gpu/drm/xe/xe_irq.c b/drivers/gpu/drm/xe/xe_irq.c
>index 5bf359c81cc5..5be31855d789 100644
>--- a/drivers/gpu/drm/xe/xe_irq.c
>+++ b/drivers/gpu/drm/xe/xe_irq.c
>@@ -369,7 +369,7 @@ static irqreturn_t dg1_irq_handler(int irq, void *arg)
> }
>
> for_each_gt(gt, xe, id) {
>- if ((master_tile_ctl & DG1_MSTR_TILE(gt->info.vram_id)) == 0)
>+ if ((master_tile_ctl & DG1_MSTR_TILE(gt_to_tile(gt)->id)) == 0)
> continue;
>
> if (!xe_gt_is_media_type(gt))
>diff --git a/drivers/gpu/drm/xe/xe_mmio.c b/drivers/gpu/drm/xe/xe_mmio.c
>index b27103080ca9..0120b836dd1d 100644
>--- a/drivers/gpu/drm/xe/xe_mmio.c
>+++ b/drivers/gpu/drm/xe/xe_mmio.c
>@@ -206,8 +206,10 @@ static int xe_determine_lmem_bar_size(struct xe_device *xe)
> * NOTE: multi-tile bases will include the tile offset.
> *
> */
>-int xe_mmio_tile_vram_size(struct xe_gt *gt, u64 *vram_size, u64 *tile_size, u64 *tile_offset)
>+int xe_mmio_tile_vram_size(struct xe_tile *tile, u64 *vram_size, u64 *tile_size, u64 *tile_offset)
> {
>+ struct xe_device *xe = tile_to_xe(tile);
>+ struct xe_gt *gt = &tile->primary_gt;
> u64 offset;
> int err;
> u32 reg;
>@@ -217,8 +219,8 @@ int xe_mmio_tile_vram_size(struct xe_gt *gt, u64 *vram_size, u64 *tile_size, u64
> return err;
>
> /* actual size */
>- if (unlikely(gt_to_xe(gt)->info.platform == XE_DG1)) {
>- *tile_size = pci_resource_len(to_pci_dev(gt_to_xe(gt)->drm.dev), GEN12_LMEM_BAR);
>+ if (unlikely(xe->info.platform == XE_DG1)) {
>+ *tile_size = pci_resource_len(to_pci_dev(xe->drm.dev), GEN12_LMEM_BAR);
> *tile_offset = 0;
> } else {
> reg = xe_gt_mcr_unicast_read_any(gt, XEHP_TILE_ADDR_RANGE(gt->info.id));
>@@ -227,7 +229,7 @@ int xe_mmio_tile_vram_size(struct xe_gt *gt, u64 *vram_size, u64 *tile_size, u64
> }
>
> /* minus device usage */
>- if (gt_to_xe(gt)->info.has_flat_ccs) {
>+ if (xe->info.has_flat_ccs) {
> reg = xe_gt_mcr_unicast_read_any(gt, XEHP_FLAT_CCS_BASE_ADDR);
> offset = (u64)REG_FIELD_GET(GENMASK(31, 8), reg) * SZ_64K;
> } else {
>@@ -242,10 +244,10 @@ int xe_mmio_tile_vram_size(struct xe_gt *gt, u64 *vram_size, u64 *tile_size, u64
>
> int xe_mmio_probe_vram(struct xe_device *xe)
> {
>+ struct xe_tile *tile;
> resource_size_t io_size;
> u64 available_size = 0;
> u64 total_size = 0;
>- struct xe_gt *gt;
> u64 tile_offset;
> u64 tile_size;
> u64 vram_size;
>@@ -255,9 +257,9 @@ int xe_mmio_probe_vram(struct xe_device *xe)
> if (!IS_DGFX(xe))
> return 0;
>
>- /* Get the size of the gt0 vram for later accessibility comparison */
>- gt = xe_device_get_gt(xe, 0);
>- err = xe_mmio_tile_vram_size(gt, &vram_size, &tile_size, &tile_offset);
>+ /* Get the size of the root tile's vram for later accessibility comparison */
>+ tile = xe_device_get_root_tile(xe);
>+ err = xe_mmio_tile_vram_size(tile, &vram_size, &tile_size, &tile_offset);
> if (err)
> return err;
>
>@@ -265,7 +267,7 @@ int xe_mmio_probe_vram(struct xe_device *xe)
> if (err)
> return err;
>
>- /* small bar issues will only cover gt0 sizes */
>+ /* small bar issues will only cover root tile sizes */
> if (xe->mem.vram.io_size < vram_size)
> drm_warn(&xe->drm, "Restricting VRAM size to PCI resource size (0x%llx->0x%llx)\n",
> vram_size, (u64)xe->mem.vram.io_size);
>@@ -275,35 +277,32 @@ int xe_mmio_probe_vram(struct xe_device *xe)
>
> io_size = xe->mem.vram.io_size;
>
>- /* gt specific ranges */
>- for_each_gt(gt, xe, id) {
>- if (xe_gt_is_media_type(gt))
>- continue;
>-
>- err = xe_mmio_tile_vram_size(gt, &vram_size, &tile_size, &tile_offset);
>+ /* tile specific ranges */
>+ for_each_tile(tile, xe, id) {
>+ err = xe_mmio_tile_vram_size(tile, &vram_size, &tile_size, &tile_offset);
> if (err)
> return err;
>
>- gt->mem.vram.io_start = xe->mem.vram.io_start + tile_offset;
>- gt->mem.vram.io_size = min_t(u64, vram_size, io_size);
>+ tile->mem.vram.io_start = xe->mem.vram.io_start + tile_offset;
>+ tile->mem.vram.io_size = min_t(u64, vram_size, io_size);
>
>- if (!gt->mem.vram.io_size) {
>+ if (!tile->mem.vram.io_size) {
> drm_err(&xe->drm, "Tile without any CPU visible VRAM. Aborting.\n");
> return -ENODEV;
> }
>
>- gt->mem.vram.base = tile_offset;
>+ tile->mem.vram.base = tile_offset;
>
> /* small bar can limit the visible size. size accordingly */
>- gt->mem.vram.size = min_t(u64, vram_size, io_size);
>- gt->mem.vram.mapping = xe->mem.vram.mapping + tile_offset;
>+ tile->mem.vram.size = min_t(u64, vram_size, io_size);
>+ tile->mem.vram.mapping = xe->mem.vram.mapping + tile_offset;
>
>- drm_info(&xe->drm, "VRAM[%u, %u]: %pa, %pa\n", id, gt->info.vram_id,
>- >->mem.vram.io_start, >->mem.vram.size);
>+ drm_info(&xe->drm, "VRAM[%u, %u]: %pa, %pa\n", id, tile->id,
>+ &tile->mem.vram.io_start, &tile->mem.vram.size);
>
>- if (gt->mem.vram.io_size < gt->mem.vram.size)
>+ if (tile->mem.vram.io_size < tile->mem.vram.size)
> drm_info(&xe->drm, "VRAM[%u, %u]: CPU access limited to %pa\n", id,
>- gt->info.vram_id, >->mem.vram.io_size);
>+ tile->id, &tile->mem.vram.io_size);
>
> /* calculate total size using tile size to get the correct HW sizing */
> total_size += tile_size;
>@@ -329,7 +328,7 @@ int xe_mmio_probe_vram(struct xe_device *xe)
>
> static void xe_mmio_probe_tiles(struct xe_device *xe)
> {
>- struct xe_gt *gt = xe_device_get_gt(xe, 0);
>+ struct xe_gt *gt = &xe_device_get_root_tile(xe)->primary_gt;
> u32 mtcfg;
> u8 adj_tile_count;
> u8 id;
>diff --git a/drivers/gpu/drm/xe/xe_mmio.h b/drivers/gpu/drm/xe/xe_mmio.h
>index 0ba7aa790f0b..3c547d78afba 100644
>--- a/drivers/gpu/drm/xe/xe_mmio.h
>+++ b/drivers/gpu/drm/xe/xe_mmio.h
>@@ -144,6 +144,6 @@ static inline bool xe_mmio_in_range(const struct xe_mmio_range *range,
> }
>
> int xe_mmio_probe_vram(struct xe_device *xe);
>-int xe_mmio_tile_vram_size(struct xe_gt *gt, u64 *vram_size, u64 *tile_size, u64 *tile_base);
>+int xe_mmio_tile_vram_size(struct xe_tile *tile, u64 *vram_size, u64 *tile_size, u64 *tile_base);
>
> #endif
>diff --git a/drivers/gpu/drm/xe/xe_pci.c b/drivers/gpu/drm/xe/xe_pci.c
>index 91d5dc59aa7e..ea3d69607d13 100644
>--- a/drivers/gpu/drm/xe/xe_pci.c
>+++ b/drivers/gpu/drm/xe/xe_pci.c
>@@ -569,7 +569,6 @@ static int xe_info_init(struct xe_device *xe,
>
> if (id == 0) {
> gt->info.type = XE_GT_TYPE_MAIN;
>- gt->info.vram_id = id;
>
> gt->info.__engine_mask = graphics_desc->hw_engine_mask;
> if (MEDIA_VER(xe) < 13 && media_desc)
>@@ -579,7 +578,6 @@ static int xe_info_init(struct xe_device *xe,
> gt->mmio.adj_offset = 0;
> } else {
> gt->info.type = desc->extra_gts[id - 1].type;
>- gt->info.vram_id = desc->extra_gts[id - 1].vram_id;
> gt->info.__engine_mask = (gt->info.type == XE_GT_TYPE_MEDIA) ?
> media_desc->hw_engine_mask :
> graphics_desc->hw_engine_mask;
>diff --git a/drivers/gpu/drm/xe/xe_query.c b/drivers/gpu/drm/xe/xe_query.c
>index b10959fde43b..799bf68800e7 100644
>--- a/drivers/gpu/drm/xe/xe_query.c
>+++ b/drivers/gpu/drm/xe/xe_query.c
>@@ -182,7 +182,7 @@ static int query_config(struct xe_device *xe, struct drm_xe_device_query *query)
> config->num_params = num_params;
> config->info[XE_QUERY_CONFIG_REV_AND_DEVICE_ID] =
> xe->info.devid | (xe->info.revid << 16);
>- if (to_gt(xe)->mem.vram.size)
>+ if (xe_device_get_root_tile(xe)->mem.vram.size)
> config->info[XE_QUERY_CONFIG_FLAGS] =
> XE_QUERY_CONFIG_FLAGS_HAS_VRAM;
> if (xe->info.enable_guc)
>@@ -242,7 +242,7 @@ static int query_gts(struct xe_device *xe, struct drm_xe_device_query *query)
> gts->gts[id].native_mem_regions = 0x1;
> else
> gts->gts[id].native_mem_regions =
>- BIT(gt->info.vram_id) << 1;
>+ BIT(gt_to_tile(gt)->id) << 1;
> gts->gts[id].slow_mem_regions = xe->info.mem_region_mask ^
> gts->gts[id].native_mem_regions;
> }
>diff --git a/drivers/gpu/drm/xe/xe_res_cursor.h b/drivers/gpu/drm/xe/xe_res_cursor.h
>index 4e99fae26b4c..f2ba609712d3 100644
>--- a/drivers/gpu/drm/xe/xe_res_cursor.h
>+++ b/drivers/gpu/drm/xe/xe_res_cursor.h
>@@ -53,7 +53,7 @@ static struct drm_buddy *xe_res_get_buddy(struct ttm_resource *res)
> struct xe_device *xe = ttm_to_xe_device(res->bo->bdev);
>
> if (res->mem_type != XE_PL_STOLEN) {
>- return &xe_device_get_gt(xe, res->mem_type - XE_PL_VRAM0)->mem.vram_mgr->mm;
>+ return &xe->tiles[res->mem_type - XE_PL_VRAM0].mem.vram_mgr->mm;
> } else {
> struct ttm_resource_manager *mgr =
> ttm_manager_type(&xe->ttm, XE_PL_STOLEN);
>diff --git a/drivers/gpu/drm/xe/xe_tile.c b/drivers/gpu/drm/xe/xe_tile.c
>index 7ef594f301ca..5530a6b6ef31 100644
>--- a/drivers/gpu/drm/xe/xe_tile.c
>+++ b/drivers/gpu/drm/xe/xe_tile.c
>@@ -29,6 +29,25 @@ int xe_tile_alloc(struct xe_tile *tile)
> return -ENOMEM;
> tile->mem.ggtt->tile = tile;
>
>+ tile->mem.vram_mgr = drmm_kzalloc(drm, sizeof(*tile->mem.vram_mgr), GFP_KERNEL);
>+ if (!tile->mem.vram_mgr)
>+ return -ENOMEM;
>+
>+ return 0;
>+}
>+
>+static int tile_ttm_mgr_init(struct xe_tile *tile)
>+{
>+ struct xe_device *xe = tile_to_xe(tile);
>+ int err;
>+
>+ if (tile->mem.vram.size) {
>+ err = xe_ttm_vram_mgr_init(tile, tile->mem.vram_mgr);
>+ if (err)
>+ return err;
>+ xe->info.mem_region_mask |= BIT(tile->id) << 1;
>+ }
>+
> return 0;
> }
>
>@@ -48,5 +67,17 @@ int xe_tile_alloc(struct xe_tile *tile)
> */
> int xe_tile_init_noalloc(struct xe_tile *tile)
> {
>- return xe_ggtt_init_noalloc(tile->mem.ggtt);
>+ int err;
>+
>+ xe_device_mem_access_get(tile_to_xe(tile));
>+
>+ err = tile_ttm_mgr_init(tile);
>+ if (err)
>+ goto err_mem_access;
>+
>+ err = xe_ggtt_init_noalloc(tile->mem.ggtt);
>+
>+err_mem_access:
>+ xe_device_mem_access_put(tile_to_xe(tile));
>+ return err;
> }
>diff --git a/drivers/gpu/drm/xe/xe_ttm_stolen_mgr.c b/drivers/gpu/drm/xe/xe_ttm_stolen_mgr.c
>index 49470f0722bd..c68325161c19 100644
>--- a/drivers/gpu/drm/xe/xe_ttm_stolen_mgr.c
>+++ b/drivers/gpu/drm/xe/xe_ttm_stolen_mgr.c
>@@ -51,29 +51,31 @@ bool xe_ttm_stolen_cpu_access_needs_ggtt(struct xe_device *xe)
> return GRAPHICS_VERx100(xe) < 1270 && !IS_DGFX(xe);
> }
>
>-static s64 detect_bar2_dgfx(struct xe_gt *gt, struct xe_ttm_stolen_mgr *mgr)
>+static s64 detect_bar2_dgfx(struct xe_device *xe, struct xe_ttm_stolen_mgr *mgr)
> {
>- struct pci_dev *pdev = to_pci_dev(gt_to_xe(gt)->drm.dev);
>+ struct xe_tile *tile = xe_device_get_root_tile(xe);
>+ struct xe_gt *mmio = &tile->primary_gt;
Was naming this variable "mmio" intentional here?
--
Gustavo Sousa
>+ struct pci_dev *pdev = to_pci_dev(xe->drm.dev);
> u64 stolen_size;
> u64 tile_offset;
> u64 tile_size;
> u64 vram_size;
>
>- if (xe_mmio_tile_vram_size(gt, &vram_size, &tile_size, &tile_offset)) {
>- drm_err(>_to_xe(gt)->drm, "Querying total vram size failed\n");
>+ if (xe_mmio_tile_vram_size(tile, &vram_size, &tile_size, &tile_offset)) {
>+ drm_err(&xe->drm, "Querying total vram size failed\n");
> return 0;
> }
>
> /* Use DSM base address instead for stolen memory */
>- mgr->stolen_base = (xe_mmio_read64(gt, DSMBASE) & BDSM_MASK) - tile_offset;
>- if (drm_WARN_ON(>_to_xe(gt)->drm, tile_size < mgr->stolen_base))
>+ mgr->stolen_base = (xe_mmio_read64(mmio, DSMBASE) & BDSM_MASK) - tile_offset;
>+ if (drm_WARN_ON(&xe->drm, tile_size < mgr->stolen_base))
> return 0;
>
> stolen_size = tile_size - mgr->stolen_base;
>
> /* Verify usage fits in the actual resource available */
> if (mgr->stolen_base + stolen_size <= pci_resource_len(pdev, GEN12_LMEM_BAR))
>- mgr->io_base = gt->mem.vram.io_start + mgr->stolen_base;
>+ mgr->io_base = tile->mem.vram.io_start + mgr->stolen_base;
>
> /*
> * There may be few KB of platform dependent reserved memory at the end
>@@ -141,7 +143,7 @@ void xe_ttm_stolen_mgr_init(struct xe_device *xe)
> int err;
>
> if (IS_DGFX(xe))
>- stolen_size = detect_bar2_dgfx(to_gt(xe), mgr);
>+ stolen_size = detect_bar2_dgfx(xe, mgr);
> else if (GRAPHICS_VERx100(xe) >= 1270)
> stolen_size = detect_bar2_integrated(xe, mgr);
> else
>diff --git a/drivers/gpu/drm/xe/xe_ttm_vram_mgr.c b/drivers/gpu/drm/xe/xe_ttm_vram_mgr.c
>index 73836b9b7fed..1a84abd35fcf 100644
>--- a/drivers/gpu/drm/xe/xe_ttm_vram_mgr.c
>+++ b/drivers/gpu/drm/xe/xe_ttm_vram_mgr.c
>@@ -353,16 +353,14 @@ int __xe_ttm_vram_mgr_init(struct xe_device *xe, struct xe_ttm_vram_mgr *mgr,
> return drmm_add_action_or_reset(&xe->drm, ttm_vram_mgr_fini, mgr);
> }
>
>-int xe_ttm_vram_mgr_init(struct xe_gt *gt, struct xe_ttm_vram_mgr *mgr)
>+int xe_ttm_vram_mgr_init(struct xe_tile *tile, struct xe_ttm_vram_mgr *mgr)
> {
>- struct xe_device *xe = gt_to_xe(gt);
>+ struct xe_device *xe = tile_to_xe(tile);
>
>- XE_BUG_ON(xe_gt_is_media_type(gt));
>+ mgr->tile = tile;
>
>- mgr->gt = gt;
>-
>- return __xe_ttm_vram_mgr_init(xe, mgr, XE_PL_VRAM0 + gt->info.vram_id,
>- gt->mem.vram.size, gt->mem.vram.io_size,
>+ return __xe_ttm_vram_mgr_init(xe, mgr, XE_PL_VRAM0 + tile->id,
>+ tile->mem.vram.size, tile->mem.vram.io_size,
> PAGE_SIZE);
> }
>
>@@ -373,7 +371,7 @@ int xe_ttm_vram_mgr_alloc_sgt(struct xe_device *xe,
> enum dma_data_direction dir,
> struct sg_table **sgt)
> {
>- struct xe_gt *gt = xe_device_get_gt(xe, res->mem_type - XE_PL_VRAM0);
>+ struct xe_tile *tile = &xe->tiles[res->mem_type - XE_PL_VRAM0];
> struct xe_res_cursor cursor;
> struct scatterlist *sg;
> int num_entries = 0;
>@@ -406,7 +404,7 @@ int xe_ttm_vram_mgr_alloc_sgt(struct xe_device *xe,
> */
> xe_res_first(res, offset, length, &cursor);
> for_each_sgtable_sg((*sgt), sg, i) {
>- phys_addr_t phys = cursor.start + gt->mem.vram.io_start;
>+ phys_addr_t phys = cursor.start + tile->mem.vram.io_start;
> size_t size = cursor.size;
> dma_addr_t addr;
>
>diff --git a/drivers/gpu/drm/xe/xe_ttm_vram_mgr.h b/drivers/gpu/drm/xe/xe_ttm_vram_mgr.h
>index 35e5367a79fb..6e1d6033d739 100644
>--- a/drivers/gpu/drm/xe/xe_ttm_vram_mgr.h
>+++ b/drivers/gpu/drm/xe/xe_ttm_vram_mgr.h
>@@ -10,12 +10,12 @@
>
> enum dma_data_direction;
> struct xe_device;
>-struct xe_gt;
>+struct xe_tile;
>
> int __xe_ttm_vram_mgr_init(struct xe_device *xe, struct xe_ttm_vram_mgr *mgr,
> u32 mem_type, u64 size, u64 io_size,
> u64 default_page_size);
>-int xe_ttm_vram_mgr_init(struct xe_gt *gt, struct xe_ttm_vram_mgr *mgr);
>+int xe_ttm_vram_mgr_init(struct xe_tile *tile, struct xe_ttm_vram_mgr *mgr);
> int xe_ttm_vram_mgr_alloc_sgt(struct xe_device *xe,
> struct ttm_resource *res,
> u64 offset, u64 length,
>diff --git a/drivers/gpu/drm/xe/xe_ttm_vram_mgr_types.h b/drivers/gpu/drm/xe/xe_ttm_vram_mgr_types.h
>index 3d9417ff7434..48bb991c14a5 100644
>--- a/drivers/gpu/drm/xe/xe_ttm_vram_mgr_types.h
>+++ b/drivers/gpu/drm/xe/xe_ttm_vram_mgr_types.h
>@@ -9,7 +9,7 @@
> #include <drm/drm_buddy.h>
> #include <drm/ttm/ttm_device.h>
>
>-struct xe_gt;
>+struct xe_tile;
>
> /**
> * struct xe_ttm_vram_mgr - XE TTM VRAM manager
>@@ -17,8 +17,8 @@ struct xe_gt;
> * Manages placement of TTM resource in VRAM.
> */
> struct xe_ttm_vram_mgr {
>- /** @gt: Graphics tile which the VRAM belongs to */
>- struct xe_gt *gt;
>+ /** @tile: Tile which the VRAM belongs to */
>+ struct xe_tile *tile;
> /** @manager: Base TTM resource manager */
> struct ttm_resource_manager manager;
> /** @mm: DRM buddy allocator which manages the VRAM */
>--
>2.40.1
>
More information about the Intel-xe
mailing list