diff options
Diffstat (limited to 'drivers/gpu/drm/xe')
40 files changed, 370 insertions, 433 deletions
diff --git a/drivers/gpu/drm/xe/Makefile b/drivers/gpu/drm/xe/Makefile index cb6c625bdef0..da80c29aa363 100644 --- a/drivers/gpu/drm/xe/Makefile +++ b/drivers/gpu/drm/xe/Makefile @@ -150,7 +150,6 @@ subdir-ccflags-$(CONFIG_DRM_XE_DISPLAY) += \ -I$(src)/display/ext \ -I$(src)/compat-i915-headers \ -I$(srctree)/drivers/gpu/drm/i915/display/ \ - -Ddrm_i915_gem_object=xe_bo \ -Ddrm_i915_private=xe_device # Rule to build SOC code shared with i915 @@ -167,6 +166,7 @@ $(obj)/i915-display/%.o: $(srctree)/drivers/gpu/drm/i915/display/%.c FORCE xe-$(CONFIG_DRM_XE_DISPLAY) += \ display/ext/i915_irq.o \ display/ext/i915_utils.o \ + display/intel_bo.o \ display/intel_fb_bo.o \ display/intel_fbdev_fb.o \ display/xe_display.o \ @@ -182,7 +182,8 @@ xe-$(CONFIG_DRM_XE_DISPLAY) += \ # SOC code shared with i915 xe-$(CONFIG_DRM_XE_DISPLAY) += \ i915-soc/intel_dram.o \ - i915-soc/intel_pch.o + i915-soc/intel_pch.o \ + i915-soc/intel_rom.o # Display code shared with i915 xe-$(CONFIG_DRM_XE_DISPLAY) += \ @@ -222,6 +223,7 @@ xe-$(CONFIG_DRM_XE_DISPLAY) += \ i915-display/intel_dp_hdcp.o \ i915-display/intel_dp_link_training.o \ i915-display/intel_dp_mst.o \ + i915-display/intel_dp_test.o \ i915-display/intel_dpll.o \ i915-display/intel_dpll_mgr.o \ i915-display/intel_dpt_common.o \ diff --git a/drivers/gpu/drm/xe/compat-i915-headers/gem/i915_gem_lmem.h b/drivers/gpu/drm/xe/compat-i915-headers/gem/i915_gem_lmem.h deleted file mode 100644 index 710cecca972d..000000000000 --- a/drivers/gpu/drm/xe/compat-i915-headers/gem/i915_gem_lmem.h +++ /dev/null @@ -1 +0,0 @@ -/* Empty */ diff --git a/drivers/gpu/drm/xe/compat-i915-headers/gem/i915_gem_mman.h b/drivers/gpu/drm/xe/compat-i915-headers/gem/i915_gem_mman.h deleted file mode 100644 index 650ea2803a97..000000000000 --- a/drivers/gpu/drm/xe/compat-i915-headers/gem/i915_gem_mman.h +++ /dev/null @@ -1,17 +0,0 @@ -/* SPDX-License-Identifier: MIT */ -/* - * Copyright © 2023 Intel Corporation - */ - -#ifndef _I915_GEM_MMAN_H_ -#define _I915_GEM_MMAN_H_ - -#include "xe_bo_types.h" -#include <drm/drm_prime.h> - -static inline int i915_gem_fb_mmap(struct xe_bo *bo, struct vm_area_struct *vma) -{ - return drm_gem_prime_mmap(&bo->ttm.base, vma); -} - -#endif diff --git a/drivers/gpu/drm/xe/compat-i915-headers/gem/i915_gem_object.h b/drivers/gpu/drm/xe/compat-i915-headers/gem/i915_gem_object.h deleted file mode 100644 index 777c20ceabab..000000000000 --- a/drivers/gpu/drm/xe/compat-i915-headers/gem/i915_gem_object.h +++ /dev/null @@ -1,64 +0,0 @@ -/* SPDX-License-Identifier: MIT */ -/* - * Copyright © 2022 Intel Corporation - */ - -#ifndef _I915_GEM_OBJECT_H_ -#define _I915_GEM_OBJECT_H_ - -#include <linux/types.h> - -#include "xe_bo.h" - -#define i915_gem_object_is_shmem(obj) (0) /* We don't use shmem */ - -static inline dma_addr_t i915_gem_object_get_dma_address(const struct xe_bo *bo, pgoff_t n) -{ - /* Should never be called */ - WARN_ON(1); - return n; -} - -static inline bool i915_gem_object_is_tiled(const struct xe_bo *bo) -{ - /* legacy tiling is unused */ - return false; -} - -static inline bool i915_gem_object_is_userptr(const struct xe_bo *bo) -{ - /* legacy tiling is unused */ - return false; -} - -static inline int i915_gem_object_read_from_page(struct xe_bo *bo, - u32 ofs, u64 *ptr, u32 size) -{ - struct ttm_bo_kmap_obj map; - void *src; - bool is_iomem; - int ret; - - ret = xe_bo_lock(bo, true); - if (ret) - return ret; - - ret = ttm_bo_kmap(&bo->ttm, ofs >> PAGE_SHIFT, 1, &map); - if (ret) - goto out_unlock; - - ofs &= ~PAGE_MASK; - src = ttm_kmap_obj_virtual(&map, &is_iomem); - src += ofs; - if (is_iomem) - memcpy_fromio(ptr, (void __iomem *)src, size); - else - memcpy(ptr, src, size); - - ttm_bo_kunmap(&map); -out_unlock: - xe_bo_unlock(bo); - return ret; -} - -#endif diff --git a/drivers/gpu/drm/xe/compat-i915-headers/gem/i915_gem_object_frontbuffer.h b/drivers/gpu/drm/xe/compat-i915-headers/gem/i915_gem_object_frontbuffer.h deleted file mode 100644 index 2a3f12d2978c..000000000000 --- a/drivers/gpu/drm/xe/compat-i915-headers/gem/i915_gem_object_frontbuffer.h +++ /dev/null @@ -1,12 +0,0 @@ -/* SPDX-License-Identifier: MIT */ -/* - * Copyright © 2022 Intel Corporation - */ - -#ifndef _I915_GEM_OBJECT_FRONTBUFFER_H_ -#define _I915_GEM_OBJECT_FRONTBUFFER_H_ - -#define i915_gem_object_get_frontbuffer(obj) NULL -#define i915_gem_object_set_frontbuffer(obj, front) (front) - -#endif diff --git a/drivers/gpu/drm/xe/compat-i915-headers/gem/i915_gem_object_types.h b/drivers/gpu/drm/xe/compat-i915-headers/gem/i915_gem_object_types.h deleted file mode 100644 index 7d6bb1abab73..000000000000 --- a/drivers/gpu/drm/xe/compat-i915-headers/gem/i915_gem_object_types.h +++ /dev/null @@ -1,11 +0,0 @@ -/* SPDX-License-Identifier: MIT */ -/* Copyright © 2024 Intel Corporation */ - -#ifndef __I915_GEM_OBJECT_TYPES_H__ -#define __I915_GEM_OBJECT_TYPES_H__ - -#include "xe_bo.h" - -#define to_intel_bo(x) gem_to_xe_bo((x)) - -#endif diff --git a/drivers/gpu/drm/xe/compat-i915-headers/gem/i915_gem_stolen.h b/drivers/gpu/drm/xe/compat-i915-headers/gem/i915_gem_stolen.h index cb6c7598824b..9c4cf050059a 100644 --- a/drivers/gpu/drm/xe/compat-i915-headers/gem/i915_gem_stolen.h +++ b/drivers/gpu/drm/xe/compat-i915-headers/gem/i915_gem_stolen.h @@ -29,7 +29,7 @@ static inline int i915_gem_stolen_insert_node_in_range(struct xe_device *xe, bo = xe_bo_create_locked_range(xe, xe_device_get_root_tile(xe), NULL, size, start, end, - ttm_bo_type_kernel, flags); + ttm_bo_type_kernel, flags, 0); if (IS_ERR(bo)) { err = PTR_ERR(bo); bo = NULL; diff --git a/drivers/gpu/drm/xe/compat-i915-headers/i915_debugfs.h b/drivers/gpu/drm/xe/compat-i915-headers/i915_debugfs.h deleted file mode 100644 index b4c47617b64b..000000000000 --- a/drivers/gpu/drm/xe/compat-i915-headers/i915_debugfs.h +++ /dev/null @@ -1,14 +0,0 @@ -/* SPDX-License-Identifier: MIT */ -/* - * Copyright © 2023 Intel Corporation - */ - -#ifndef __I915_DEBUGFS_H__ -#define __I915_DEBUGFS_H__ - -struct drm_i915_gem_object; -struct seq_file; - -static inline void i915_debugfs_describe_obj(struct seq_file *m, struct drm_i915_gem_object *obj) {} - -#endif /* __I915_DEBUGFS_H__ */ diff --git a/drivers/gpu/drm/xe/compat-i915-headers/i915_drv.h b/drivers/gpu/drm/xe/compat-i915-headers/i915_drv.h index f27a2c75b56d..b7041b578e5e 100644 --- a/drivers/gpu/drm/xe/compat-i915-headers/i915_drv.h +++ b/drivers/gpu/drm/xe/compat-i915-headers/i915_drv.h @@ -14,6 +14,7 @@ #include "i915_utils.h" #include "intel_runtime_pm.h" +#include "xe_device.h" /* for xe_device_has_flat_ccs() */ #include "xe_device_types.h" static inline struct drm_i915_private *to_i915(const struct drm_device *dev) @@ -75,10 +76,6 @@ static inline struct drm_i915_private *to_i915(const struct drm_device *dev) #define IS_MOBILE(xe) (xe && 0) -#define IS_LP(xe) ((xe) && 0) -#define IS_GEN9_LP(xe) ((xe) && 0) -#define IS_GEN9_BC(xe) ((xe) && 0) - #define IS_TIGERLAKE_UY(xe) (xe && 0) #define IS_COMETLAKE_ULX(xe) (xe && 0) #define IS_COFFEELAKE_ULX(xe) (xe && 0) diff --git a/drivers/gpu/drm/xe/compat-i915-headers/intel_runtime_pm.h b/drivers/gpu/drm/xe/compat-i915-headers/intel_runtime_pm.h index 8c7b315aa8ac..cba587ceba1b 100644 --- a/drivers/gpu/drm/xe/compat-i915-headers/intel_runtime_pm.h +++ b/drivers/gpu/drm/xe/compat-i915-headers/intel_runtime_pm.h @@ -24,14 +24,14 @@ static inline intel_wakeref_t intel_runtime_pm_get(struct xe_runtime_pm *pm) { struct xe_device *xe = container_of(pm, struct xe_device, runtime_pm); - return xe_pm_runtime_resume_and_get(xe); + return xe_pm_runtime_resume_and_get(xe) ? INTEL_WAKEREF_DEF : NULL; } static inline intel_wakeref_t intel_runtime_pm_get_if_in_use(struct xe_runtime_pm *pm) { struct xe_device *xe = container_of(pm, struct xe_device, runtime_pm); - return xe_pm_runtime_get_if_in_use(xe); + return xe_pm_runtime_get_if_in_use(xe) ? INTEL_WAKEREF_DEF : NULL; } static inline intel_wakeref_t intel_runtime_pm_get_noresume(struct xe_runtime_pm *pm) @@ -39,7 +39,8 @@ static inline intel_wakeref_t intel_runtime_pm_get_noresume(struct xe_runtime_pm struct xe_device *xe = container_of(pm, struct xe_device, runtime_pm); xe_pm_runtime_get_noresume(xe); - return true; + + return INTEL_WAKEREF_DEF; } static inline void intel_runtime_pm_put_unchecked(struct xe_runtime_pm *pm) @@ -62,6 +63,6 @@ static inline void intel_runtime_pm_put(struct xe_runtime_pm *pm, intel_wakeref_ #define with_intel_runtime_pm(rpm, wf) \ for ((wf) = intel_runtime_pm_get(rpm); (wf); \ - intel_runtime_pm_put((rpm), (wf)), (wf) = 0) + intel_runtime_pm_put((rpm), (wf)), (wf) = NULL) #endif diff --git a/drivers/gpu/drm/xe/compat-i915-headers/intel_uncore.h b/drivers/gpu/drm/xe/compat-i915-headers/intel_uncore.h index ee3469d4ae73..0382beb4035b 100644 --- a/drivers/gpu/drm/xe/compat-i915-headers/intel_uncore.h +++ b/drivers/gpu/drm/xe/compat-i915-headers/intel_uncore.h @@ -155,30 +155,6 @@ static inline void intel_uncore_write_notrace(struct intel_uncore *uncore, xe_mmio_write32(__compat_uncore_to_mmio(uncore), reg, val); } -static inline void __iomem *intel_uncore_regs(struct intel_uncore *uncore) -{ - struct xe_device *xe = container_of(uncore, struct xe_device, uncore); - - return xe_device_get_root_tile(xe)->mmio.regs; -} - -/* - * The raw_reg_{read,write} macros are intended as a micro-optimization for - * interrupt handlers so that the pointer indirection on uncore->regs can - * be computed once (and presumably cached in a register) instead of generating - * extra load instructions for each MMIO access. - * - * Given that these macros are only intended for non-GSI interrupt registers - * (and the goal is to avoid extra instructions generated by the compiler), - * these macros do not account for uncore->gsi_offset. Any caller that needs - * to use these macros on a GSI register is responsible for adding the - * appropriate GSI offset to the 'base' parameter. - */ -#define raw_reg_read(base, reg) \ - readl(base + i915_mmio_reg_offset(reg)) -#define raw_reg_write(base, reg, value) \ - writel(value, base + i915_mmio_reg_offset(reg)) - #define intel_uncore_forcewake_get(x, y) do { } while (0) #define intel_uncore_forcewake_put(x, y) do { } while (0) diff --git a/drivers/gpu/drm/xe/compat-i915-headers/intel_wakeref.h b/drivers/gpu/drm/xe/compat-i915-headers/intel_wakeref.h index ecb1c0707706..2a32faea9db5 100644 --- a/drivers/gpu/drm/xe/compat-i915-headers/intel_wakeref.h +++ b/drivers/gpu/drm/xe/compat-i915-headers/intel_wakeref.h @@ -5,4 +5,6 @@ #include <linux/types.h> -typedef unsigned long intel_wakeref_t; +typedef struct ref_tracker *intel_wakeref_t; + +#define INTEL_WAKEREF_DEF ERR_PTR(-ENOENT) diff --git a/drivers/gpu/drm/xe/compat-i915-headers/pxp/intel_pxp.h b/drivers/gpu/drm/xe/compat-i915-headers/pxp/intel_pxp.h index c2c30ece8f77..5dfc587c8237 100644 --- a/drivers/gpu/drm/xe/compat-i915-headers/pxp/intel_pxp.h +++ b/drivers/gpu/drm/xe/compat-i915-headers/pxp/intel_pxp.h @@ -9,20 +9,14 @@ #include <linux/errno.h> #include <linux/types.h> -struct drm_i915_gem_object; +struct drm_gem_object; struct intel_pxp; static inline int intel_pxp_key_check(struct intel_pxp *pxp, - struct drm_i915_gem_object *obj, + struct drm_gem_object *obj, bool assign) { return -ENODEV; } -static inline bool -i915_gem_object_is_protected(const struct drm_i915_gem_object *obj) -{ - return false; -} - #endif diff --git a/drivers/gpu/drm/xe/compat-i915-headers/soc/intel_rom.h b/drivers/gpu/drm/xe/compat-i915-headers/soc/intel_rom.h new file mode 100644 index 000000000000..05cbfb697b2b --- /dev/null +++ b/drivers/gpu/drm/xe/compat-i915-headers/soc/intel_rom.h @@ -0,0 +1,6 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright © 2024 Intel Corporation + */ + +#include "../../../i915/soc/intel_rom.h" diff --git a/drivers/gpu/drm/xe/display/ext/i915_irq.c b/drivers/gpu/drm/xe/display/ext/i915_irq.c index eb40f1cb44f6..977ef47ea1f9 100644 --- a/drivers/gpu/drm/xe/display/ext/i915_irq.c +++ b/drivers/gpu/drm/xe/display/ext/i915_irq.c @@ -7,19 +7,18 @@ #include "i915_reg.h" #include "intel_uncore.h" -void gen3_irq_reset(struct intel_uncore *uncore, i915_reg_t imr, - i915_reg_t iir, i915_reg_t ier) +void gen3_irq_reset(struct intel_uncore *uncore, struct i915_irq_regs regs) { - intel_uncore_write(uncore, imr, 0xffffffff); - intel_uncore_posting_read(uncore, imr); + intel_uncore_write(uncore, regs.imr, 0xffffffff); + intel_uncore_posting_read(uncore, regs.imr); - intel_uncore_write(uncore, ier, 0); + intel_uncore_write(uncore, regs.ier, 0); /* IIR can theoretically queue up two events. Be paranoid. */ - intel_uncore_write(uncore, iir, 0xffffffff); - intel_uncore_posting_read(uncore, iir); - intel_uncore_write(uncore, iir, 0xffffffff); - intel_uncore_posting_read(uncore, iir); + intel_uncore_write(uncore, regs.iir, 0xffffffff); + intel_uncore_posting_read(uncore, regs.iir); + intel_uncore_write(uncore, regs.iir, 0xffffffff); + intel_uncore_posting_read(uncore, regs.iir); } /* @@ -42,16 +41,14 @@ void gen3_assert_iir_is_zero(struct intel_uncore *uncore, i915_reg_t reg) intel_uncore_posting_read(uncore, reg); } -void gen3_irq_init(struct intel_uncore *uncore, - i915_reg_t imr, u32 imr_val, - i915_reg_t ier, u32 ier_val, - i915_reg_t iir) +void gen3_irq_init(struct intel_uncore *uncore, struct i915_irq_regs regs, + u32 imr_val, u32 ier_val) { - gen3_assert_iir_is_zero(uncore, iir); + gen3_assert_iir_is_zero(uncore, regs.iir); - intel_uncore_write(uncore, ier, ier_val); - intel_uncore_write(uncore, imr, imr_val); - intel_uncore_posting_read(uncore, imr); + intel_uncore_write(uncore, regs.ier, ier_val); + intel_uncore_write(uncore, regs.imr, imr_val); + intel_uncore_posting_read(uncore, regs.imr); } bool intel_irqs_enabled(struct xe_device *xe) diff --git a/drivers/gpu/drm/xe/display/intel_bo.c b/drivers/gpu/drm/xe/display/intel_bo.c new file mode 100644 index 000000000000..9f54fad0f1c0 --- /dev/null +++ b/drivers/gpu/drm/xe/display/intel_bo.c @@ -0,0 +1,84 @@ +// SPDX-License-Identifier: MIT +/* Copyright © 2024 Intel Corporation */ + +#include <drm/drm_gem.h> + +#include "xe_bo.h" +#include "intel_bo.h" + +bool intel_bo_is_tiled(struct drm_gem_object *obj) +{ + /* legacy tiling is unused */ + return false; +} + +bool intel_bo_is_userptr(struct drm_gem_object *obj) +{ + /* xe does not have userptr bos */ + return false; +} + +bool intel_bo_is_shmem(struct drm_gem_object *obj) +{ + return false; +} + +bool intel_bo_is_protected(struct drm_gem_object *obj) +{ + return false; +} + +void intel_bo_flush_if_display(struct drm_gem_object *obj) +{ +} + +int intel_bo_fb_mmap(struct drm_gem_object *obj, struct vm_area_struct *vma) +{ + return drm_gem_prime_mmap(obj, vma); +} + +int intel_bo_read_from_page(struct drm_gem_object *obj, u64 offset, void *dst, int size) +{ + struct xe_bo *bo = gem_to_xe_bo(obj); + struct ttm_bo_kmap_obj map; + void *src; + bool is_iomem; + int ret; + + ret = xe_bo_lock(bo, true); + if (ret) + return ret; + + ret = ttm_bo_kmap(&bo->ttm, offset >> PAGE_SHIFT, 1, &map); + if (ret) + goto out_unlock; + + offset &= ~PAGE_MASK; + src = ttm_kmap_obj_virtual(&map, &is_iomem); + src += offset; + if (is_iomem) + memcpy_fromio(dst, (void __iomem *)src, size); + else + memcpy(dst, src, size); + + ttm_bo_kunmap(&map); +out_unlock: + xe_bo_unlock(bo); + return ret; +} + +struct intel_frontbuffer *intel_bo_get_frontbuffer(struct drm_gem_object *obj) +{ + return NULL; +} + +struct intel_frontbuffer *intel_bo_set_frontbuffer(struct drm_gem_object *obj, + struct intel_frontbuffer *front) +{ + return front; +} + +void intel_bo_describe(struct seq_file *m, struct drm_gem_object *obj) +{ + /* FIXME */ +} diff --git a/drivers/gpu/drm/xe/display/intel_fb_bo.c b/drivers/gpu/drm/xe/display/intel_fb_bo.c index 63ce97cc4cfe..4d209ebc26c2 100644 --- a/drivers/gpu/drm/xe/display/intel_fb_bo.c +++ b/drivers/gpu/drm/xe/display/intel_fb_bo.c @@ -11,8 +11,10 @@ #include "intel_fb_bo.h" #include "xe_bo.h" -void intel_fb_bo_framebuffer_fini(struct xe_bo *bo) +void intel_fb_bo_framebuffer_fini(struct drm_gem_object *obj) { + struct xe_bo *bo = gem_to_xe_bo(obj); + if (bo->flags & XE_BO_FLAG_PINNED) { /* Unpin our kernel fb first */ xe_bo_lock(bo, false); @@ -23,9 +25,10 @@ void intel_fb_bo_framebuffer_fini(struct xe_bo *bo) } int intel_fb_bo_framebuffer_init(struct intel_framebuffer *intel_fb, - struct xe_bo *bo, + struct drm_gem_object *obj, struct drm_mode_fb_cmd2 *mode_cmd) { + struct xe_bo *bo = gem_to_xe_bo(obj); struct xe_device *xe = to_xe_device(bo->ttm.base.dev); int ret; @@ -65,11 +68,11 @@ err: return ret; } -struct xe_bo *intel_fb_bo_lookup_valid_bo(struct drm_i915_private *i915, - struct drm_file *filp, - const struct drm_mode_fb_cmd2 *mode_cmd) +struct drm_gem_object *intel_fb_bo_lookup_valid_bo(struct drm_i915_private *i915, + struct drm_file *filp, + const struct drm_mode_fb_cmd2 *mode_cmd) { - struct drm_i915_gem_object *bo; + struct xe_bo *bo; struct drm_gem_object *gem = drm_gem_object_lookup(filp, mode_cmd->handles[0]); if (!gem) @@ -78,11 +81,11 @@ struct xe_bo *intel_fb_bo_lookup_valid_bo(struct drm_i915_private *i915, bo = gem_to_xe_bo(gem); /* Require vram placement or dma-buf import */ if (IS_DGFX(i915) && - !xe_bo_can_migrate(gem_to_xe_bo(gem), XE_PL_VRAM0) && + !xe_bo_can_migrate(bo, XE_PL_VRAM0) && bo->ttm.type != ttm_bo_type_sg) { drm_gem_object_put(gem); return ERR_PTR(-EREMOTE); } - return bo; + return gem; } diff --git a/drivers/gpu/drm/xe/display/intel_fb_bo.h b/drivers/gpu/drm/xe/display/intel_fb_bo.h deleted file mode 100644 index 5d365b925b7a..000000000000 --- a/drivers/gpu/drm/xe/display/intel_fb_bo.h +++ /dev/null @@ -1,24 +0,0 @@ -/* SPDX-License-Identifier: MIT */ -/* - * Copyright © 2021 Intel Corporation - */ - -#ifndef __INTEL_FB_BO_H__ -#define __INTEL_FB_BO_H__ - -struct drm_file; -struct drm_mode_fb_cmd2; -struct drm_i915_private; -struct intel_framebuffer; -struct xe_bo; - -void intel_fb_bo_framebuffer_fini(struct xe_bo *bo); -int intel_fb_bo_framebuffer_init(struct intel_framebuffer *intel_fb, - struct xe_bo *bo, - struct drm_mode_fb_cmd2 *mode_cmd); - -struct xe_bo *intel_fb_bo_lookup_valid_bo(struct drm_i915_private *i915, - struct drm_file *filp, - const struct drm_mode_fb_cmd2 *mode_cmd); - -#endif diff --git a/drivers/gpu/drm/xe/display/intel_fbdev_fb.c b/drivers/gpu/drm/xe/display/intel_fbdev_fb.c index 99499d6c0256..ca95fcd098ec 100644 --- a/drivers/gpu/drm/xe/display/intel_fbdev_fb.c +++ b/drivers/gpu/drm/xe/display/intel_fbdev_fb.c @@ -6,6 +6,7 @@ #include <drm/drm_fb_helper.h> #include "intel_display_types.h" +#include "intel_fb.h" #include "intel_fbdev_fb.h" #include "xe_bo.h" #include "xe_ttm_stolen_mgr.h" @@ -20,7 +21,7 @@ struct intel_framebuffer *intel_fbdev_fb_alloc(struct drm_fb_helper *helper, struct drm_device *dev = helper->dev; struct xe_device *xe = to_xe_device(dev); struct drm_mode_fb_cmd2 mode_cmd = {}; - struct drm_i915_gem_object *obj; + struct xe_bo *obj; int size; /* we don't do packed 24bpp */ @@ -64,13 +65,13 @@ struct intel_framebuffer *intel_fbdev_fb_alloc(struct drm_fb_helper *helper, goto err; } - fb = intel_framebuffer_create(obj, &mode_cmd); + fb = intel_framebuffer_create(&obj->ttm.base, &mode_cmd); if (IS_ERR(fb)) { xe_bo_unpin_map_no_vm(obj); goto err; } - drm_gem_object_put(intel_bo_to_drm_bo(obj)); + drm_gem_object_put(&obj->ttm.base); return to_intel_framebuffer(fb); @@ -79,8 +80,9 @@ err: } int intel_fbdev_fb_fill_info(struct drm_i915_private *i915, struct fb_info *info, - struct drm_i915_gem_object *obj, struct i915_vma *vma) + struct drm_gem_object *_obj, struct i915_vma *vma) { + struct xe_bo *obj = gem_to_xe_bo(_obj); struct pci_dev *pdev = to_pci_dev(i915->drm.dev); if (!(obj->flags & XE_BO_FLAG_SYSTEM)) { @@ -100,7 +102,7 @@ int intel_fbdev_fb_fill_info(struct drm_i915_private *i915, struct fb_info *info XE_WARN_ON(iosys_map_is_null(&obj->vmap)); info->screen_base = obj->vmap.vaddr_iomem; - info->screen_size = intel_bo_to_drm_bo(obj)->size; + info->screen_size = obj->ttm.base.size; return 0; } diff --git a/drivers/gpu/drm/xe/display/xe_display.c b/drivers/gpu/drm/xe/display/xe_display.c index 26b2cae11d46..695c27ac6b0f 100644 --- a/drivers/gpu/drm/xe/display/xe_display.c +++ b/drivers/gpu/drm/xe/display/xe_display.c @@ -10,6 +10,7 @@ #include <drm/drm_drv.h> #include <drm/drm_managed.h> +#include <drm/drm_probe_helper.h> #include <uapi/drm/xe_drm.h> #include "soc/intel_dram.h" @@ -320,7 +321,9 @@ static void __xe_display_pm_suspend(struct xe_device *xe, bool runtime) * properly. */ intel_power_domains_disable(xe); - intel_fbdev_set_suspend(&xe->drm, FBINFO_STATE_SUSPENDED, true); + if (!runtime) + intel_fbdev_set_suspend(&xe->drm, FBINFO_STATE_SUSPENDED, true); + if (!runtime && has_display(xe)) { drm_kms_helper_poll_disable(&xe->drm); intel_display_driver_disable_user_access(xe); @@ -329,7 +332,8 @@ static void __xe_display_pm_suspend(struct xe_device *xe, bool runtime) xe_display_flush_cleanup_work(xe); - intel_dp_mst_suspend(xe); + if (!runtime) + intel_dp_mst_suspend(xe); intel_hpd_cancel_work(xe); @@ -340,7 +344,10 @@ static void __xe_display_pm_suspend(struct xe_device *xe, bool runtime) intel_opregion_suspend(display, s2idle ? PCI_D1 : PCI_D3cold); - intel_dmc_suspend(xe); + intel_dmc_suspend(display); + + if (runtime && has_display(xe)) + intel_hpd_poll_enable(xe); } void xe_display_pm_suspend(struct xe_device *xe) @@ -375,7 +382,7 @@ void xe_display_pm_shutdown(struct xe_device *xe) intel_opregion_suspend(display, PCI_D3cold); - intel_dmc_suspend(xe); + intel_dmc_suspend(display); } void xe_display_pm_runtime_suspend(struct xe_device *xe) @@ -383,8 +390,10 @@ void xe_display_pm_runtime_suspend(struct xe_device *xe) if (!xe->info.probe_display) return; - if (xe->d3cold.allowed) + if (xe->d3cold.allowed) { __xe_display_pm_suspend(xe, true); + return; + } intel_hpd_poll_enable(xe); } @@ -430,7 +439,7 @@ static void __xe_display_pm_resume(struct xe_device *xe, bool runtime) if (!xe->info.probe_display) return; - intel_dmc_resume(xe); + intel_dmc_resume(display); if (has_display(xe)) drm_mode_config_reset(&xe->drm); @@ -442,17 +451,22 @@ static void __xe_display_pm_resume(struct xe_device *xe, bool runtime) intel_display_driver_resume_access(xe); /* MST sideband requires HPD interrupts enabled */ - intel_dp_mst_resume(xe); + if (!runtime) + intel_dp_mst_resume(xe); + if (!runtime && has_display(xe)) { intel_display_driver_resume(xe); drm_kms_helper_poll_enable(&xe->drm); intel_display_driver_enable_user_access(xe); - intel_hpd_poll_disable(xe); } + if (has_display(xe)) + intel_hpd_poll_disable(xe); + intel_opregion_resume(display); - intel_fbdev_set_suspend(&xe->drm, FBINFO_STATE_RUNNING, false); + if (!runtime) + intel_fbdev_set_suspend(&xe->drm, FBINFO_STATE_RUNNING, false); intel_power_domains_enable(xe); } @@ -467,10 +481,13 @@ void xe_display_pm_runtime_resume(struct xe_device *xe) if (!xe->info.probe_display) return; - intel_hpd_poll_disable(xe); - - if (xe->d3cold.allowed) + if (xe->d3cold.allowed) { __xe_display_pm_resume(xe, true); + return; + } + + intel_hpd_init(xe); + intel_hpd_poll_disable(xe); } diff --git a/drivers/gpu/drm/xe/display/xe_fb_pin.c b/drivers/gpu/drm/xe/display/xe_fb_pin.c index b58fc4ba2aac..761510ae0690 100644 --- a/drivers/gpu/drm/xe/display/xe_fb_pin.c +++ b/drivers/gpu/drm/xe/display/xe_fb_pin.c @@ -79,12 +79,14 @@ write_dpt_remapped(struct xe_bo *bo, struct iosys_map *map, u32 *dpt_ofs, static int __xe_pin_fb_vma_dpt(const struct intel_framebuffer *fb, const struct i915_gtt_view *view, - struct i915_vma *vma) + struct i915_vma *vma, + u64 physical_alignment) { struct xe_device *xe = to_xe_device(fb->base.dev); struct xe_tile *tile0 = xe_device_get_root_tile(xe); struct xe_ggtt *ggtt = tile0->mem.ggtt; - struct xe_bo *bo = intel_fb_obj(&fb->base), *dpt; + struct drm_gem_object *obj = intel_fb_bo(&fb->base); + struct xe_bo *bo = gem_to_xe_bo(obj), *dpt; u32 dpt_size, size = bo->ttm.base.size; if (view->type == I915_GTT_VIEW_NORMAL) @@ -98,23 +100,29 @@ static int __xe_pin_fb_vma_dpt(const struct intel_framebuffer *fb, XE_PAGE_SIZE); if (IS_DGFX(xe)) - dpt = xe_bo_create_pin_map(xe, tile0, NULL, dpt_size, - ttm_bo_type_kernel, - XE_BO_FLAG_VRAM0 | - XE_BO_FLAG_GGTT | - XE_BO_FLAG_PAGETABLE); + dpt = xe_bo_create_pin_map_at_aligned(xe, tile0, NULL, + dpt_size, ~0ull, + ttm_bo_type_kernel, + XE_BO_FLAG_VRAM0 | + XE_BO_FLAG_GGTT | + XE_BO_FLAG_PAGETABLE, + physical_alignment); else - dpt = xe_bo_create_pin_map(xe, tile0, NULL, dpt_size, - ttm_bo_type_kernel, - XE_BO_FLAG_STOLEN | - XE_BO_FLAG_GGTT | - XE_BO_FLAG_PAGETABLE); + dpt = xe_bo_create_pin_map_at_aligned(xe, tile0, NULL, + dpt_size, ~0ull, + ttm_bo_type_kernel, + XE_BO_FLAG_STOLEN | + XE_BO_FLAG_GGTT | + XE_BO_FLAG_PAGETABLE, + physical_alignment); if (IS_ERR(dpt)) - dpt = xe_bo_create_pin_map(xe, tile0, NULL, dpt_size, - ttm_bo_type_kernel, - XE_BO_FLAG_SYSTEM | - XE_BO_FLAG_GGTT | - XE_BO_FLAG_PAGETABLE); + dpt = xe_bo_create_pin_map_at_aligned(xe, tile0, NULL, + dpt_size, ~0ull, + ttm_bo_type_kernel, + XE_BO_FLAG_SYSTEM | + XE_BO_FLAG_GGTT | + XE_BO_FLAG_PAGETABLE, + physical_alignment); if (IS_ERR(dpt)) return PTR_ERR(dpt); @@ -183,9 +191,11 @@ write_ggtt_rotated(struct xe_bo *bo, struct xe_ggtt *ggtt, u32 *ggtt_ofs, u32 bo static int __xe_pin_fb_vma_ggtt(const struct intel_framebuffer *fb, const struct i915_gtt_view *view, - struct i915_vma *vma) + struct i915_vma *vma, + u64 physical_alignment) { - struct xe_bo *bo = intel_fb_obj(&fb->base); + struct drm_gem_object *obj = intel_fb_bo(&fb->base); + struct xe_bo *bo = gem_to_xe_bo(obj); struct xe_device *xe = to_xe_device(fb->base.dev); struct xe_ggtt *ggtt = xe_device_get_root_tile(xe)->mem.ggtt; u32 align; @@ -264,12 +274,14 @@ out: } static struct i915_vma *__xe_pin_fb_vma(const struct intel_framebuffer *fb, - const struct i915_gtt_view *view) + const struct i915_gtt_view *view, + u64 physical_alignment) { struct drm_device *dev = fb->base.dev; struct xe_device *xe = to_xe_device(dev); struct i915_vma *vma = kzalloc(sizeof(*vma), GFP_KERNEL); - struct xe_bo *bo = intel_fb_obj(&fb->base); + struct drm_gem_object *obj = intel_fb_bo(&fb->base); + struct xe_bo *bo = gem_to_xe_bo(obj); int ret; if (!vma) @@ -312,9 +324,9 @@ static struct i915_vma *__xe_pin_fb_vma(const struct intel_framebuffer *fb, vma->bo = bo; if (intel_fb_uses_dpt(&fb->base)) - ret = __xe_pin_fb_vma_dpt(fb, view, vma); + ret = __xe_pin_fb_vma_dpt(fb, view, vma, physical_alignment); else - ret = __xe_pin_fb_vma_ggtt(fb, view, vma); + ret = __xe_pin_fb_vma_ggtt(fb, view, vma, physical_alignment); if (ret) goto err_unpin; @@ -355,7 +367,7 @@ intel_fb_pin_to_ggtt(const struct drm_framebuffer *fb, { *out_flags = 0; - return __xe_pin_fb_vma(to_intel_framebuffer(fb), view); + return __xe_pin_fb_vma(to_intel_framebuffer(fb), view, phys_alignment); } void intel_fb_unpin_vma(struct i915_vma *vma, unsigned long flags) @@ -366,13 +378,18 @@ void intel_fb_unpin_vma(struct i915_vma *vma, unsigned long flags) int intel_plane_pin_fb(struct intel_plane_state *plane_state) { struct drm_framebuffer *fb = plane_state->hw.fb; - struct xe_bo *bo = intel_fb_obj(fb); + struct drm_gem_object *obj = intel_fb_bo(fb); + struct xe_bo *bo = gem_to_xe_bo(obj); struct i915_vma *vma; + struct intel_framebuffer *intel_fb = to_intel_framebuffer(fb); + struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane); + u64 phys_alignment = plane->min_alignment(plane, fb, 0); /* We reject creating !SCANOUT fb's, so this is weird.. */ drm_WARN_ON(bo->ttm.base.dev, !(bo->flags & XE_BO_FLAG_SCANOUT)); - vma = __xe_pin_fb_vma(to_intel_framebuffer(fb), &plane_state->view.gtt); + vma = __xe_pin_fb_vma(intel_fb, &plane_state->view.gtt, phys_alignment); + if (IS_ERR(vma)) return PTR_ERR(vma); diff --git a/drivers/gpu/drm/xe/display/xe_hdcp_gsc.c b/drivers/gpu/drm/xe/display/xe_hdcp_gsc.c index 6619a40aed15..231677129a35 100644 --- a/drivers/gpu/drm/xe/display/xe_hdcp_gsc.c +++ b/drivers/gpu/drm/xe/display/xe_hdcp_gsc.c @@ -30,13 +30,14 @@ struct intel_hdcp_gsc_message { #define HDCP_GSC_HEADER_SIZE sizeof(struct intel_gsc_mtl_header) -bool intel_hdcp_gsc_cs_required(struct xe_device *xe) +bool intel_hdcp_gsc_cs_required(struct intel_display *display) { - return DISPLAY_VER(xe) >= 14; + return DISPLAY_VER(display) >= 14; } -bool intel_hdcp_gsc_check_status(struct xe_device *xe) +bool intel_hdcp_gsc_check_status(struct intel_display *display) { + struct xe_device *xe = to_xe_device(display->drm); struct xe_tile *tile = xe_device_get_root_tile(xe); struct xe_gt *gt = tile->media_gt; struct xe_gsc *gsc = >->uc.gsc; @@ -66,9 +67,10 @@ out: } /*This function helps allocate memory for the command that we will send to gsc cs */ -static int intel_hdcp_gsc_initialize_message(struct xe_device *xe, +static int intel_hdcp_gsc_initialize_message(struct intel_display *display, struct intel_hdcp_gsc_message *hdcp_message) { + struct xe_device *xe = to_xe_device(display->drm); struct xe_bo *bo = NULL; u64 cmd_in, cmd_out; int ret = 0; @@ -80,7 +82,7 @@ static int intel_hdcp_gsc_initialize_message(struct xe_device *xe, XE_BO_FLAG_GGTT); if (IS_ERR(bo)) { - drm_err(&xe->drm, "Failed to allocate bo for HDCP streaming command!\n"); + drm_err(display->drm, "Failed to allocate bo for HDCP streaming command!\n"); ret = PTR_ERR(bo); goto out; } @@ -96,7 +98,7 @@ out: return ret; } -static int intel_hdcp_gsc_hdcp2_init(struct xe_device *xe) +static int intel_hdcp_gsc_hdcp2_init(struct intel_display *display) { struct intel_hdcp_gsc_message *hdcp_message; int ret; @@ -110,14 +112,14 @@ static int intel_hdcp_gsc_hdcp2_init(struct xe_device *xe) * NOTE: No need to lock the comp mutex here as it is already * going to be taken before this function called */ - ret = intel_hdcp_gsc_initialize_message(xe, hdcp_message); + ret = intel_hdcp_gsc_initialize_message(display, hdcp_message); if (ret) { - drm_err(&xe->drm, "Could not initialize hdcp_message\n"); + drm_err(display->drm, "Could not initialize hdcp_message\n"); kfree(hdcp_message); return ret; } - xe->display.hdcp.hdcp_message = hdcp_message; + display->hdcp.hdcp_message = hdcp_message; return ret; } @@ -137,7 +139,7 @@ static const struct i915_hdcp_ops gsc_hdcp_ops = { .close_hdcp_session = intel_hdcp_gsc_close_session, }; -int intel_hdcp_gsc_init(struct xe_device *xe) +int intel_hdcp_gsc_init(struct intel_display *display) { struct i915_hdcp_arbiter *data; int ret; @@ -146,33 +148,33 @@ int intel_hdcp_gsc_init(struct xe_device *xe) if (!data) return -ENOMEM; - mutex_lock(&xe->display.hdcp.hdcp_mutex); - xe->display.hdcp.arbiter = data; - xe->display.hdcp.arbiter->hdcp_dev = xe->drm.dev; - xe->display.hdcp.arbiter->ops = &gsc_hdcp_ops; - ret = intel_hdcp_gsc_hdcp2_init(xe); + mutex_lock(&display->hdcp.hdcp_mutex); + display->hdcp.arbiter = data; + display->hdcp.arbiter->hdcp_dev = display->drm->dev; + display->hdcp.arbiter->ops = &gsc_hdcp_ops; + ret = intel_hdcp_gsc_hdcp2_init(display); if (ret) kfree(data); - mutex_unlock(&xe->display.hdcp.hdcp_mutex); + mutex_unlock(&display->hdcp.hdcp_mutex); return ret; } -void intel_hdcp_gsc_fini(struct xe_device *xe) +void intel_hdcp_gsc_fini(struct intel_display *display) { struct intel_hdcp_gsc_message *hdcp_message = - xe->display.hdcp.hdcp_message; - struct i915_hdcp_arbiter *arb = xe->display.hdcp.arbiter; + display->hdcp.hdcp_message; + struct i915_hdcp_arbiter *arb = display->hdcp.arbiter; if (hdcp_message) { xe_bo_unpin_map_no_vm(hdcp_message->hdcp_bo); kfree(hdcp_message); - xe->display.hdcp.hdcp_message = NULL; + display->hdcp.hdcp_message = NULL; } kfree(arb); - xe->display.hdcp.arbiter = NULL; + display->hdcp.arbiter = NULL; } static int xe_gsc_send_sync(struct xe_device *xe, diff --git a/drivers/gpu/drm/xe/display/xe_plane_initial.c b/drivers/gpu/drm/xe/display/xe_plane_initial.c index a50ab9eae40a..8c113463a3d5 100644 --- a/drivers/gpu/drm/xe/display/xe_plane_initial.c +++ b/drivers/gpu/drm/xe/display/xe_plane_initial.c @@ -170,7 +170,7 @@ intel_alloc_initial_plane_obj(struct intel_crtc *crtc, return false; if (intel_framebuffer_init(to_intel_framebuffer(fb), - bo, &mode_cmd)) { + &bo->ttm.base, &mode_cmd)) { drm_dbg_kms(&xe->drm, "intel fb init failed\n"); goto err_bo; } @@ -248,7 +248,7 @@ intel_find_initial_plane_obj(struct intel_crtc *crtc, * the lookup of sysmem scratch pages. */ plane->check_plane(crtc_state, plane_state); - plane->async_flip(plane, crtc_state, plane_state, true); + plane->async_flip(NULL, plane, crtc_state, plane_state, true); return; nofb: diff --git a/drivers/gpu/drm/xe/regs/xe_gt_regs.h b/drivers/gpu/drm/xe/regs/xe_gt_regs.h index d428d04164d9..42dc55cb23f4 100644 --- a/drivers/gpu/drm/xe/regs/xe_gt_regs.h +++ b/drivers/gpu/drm/xe/regs/xe_gt_regs.h @@ -410,12 +410,6 @@ #define XE2LPM_SCRATCH3_LBCF XE_REG_MCR(0xb654) -#define XE2LPM_L3SQCREG2 XE_REG_MCR(0xb604) - -#define XE2LPM_L3SQCREG3 XE_REG_MCR(0xb608) - -#define XE2LPM_SCRATCH3_LBCF XE_REG_MCR(0xb654) - #define XE2LPM_L3SQCREG5 XE_REG_MCR(0xb658) #define XE2_TDF_CTRL XE_REG(0xb418) diff --git a/drivers/gpu/drm/xe/xe_bo.c b/drivers/gpu/drm/xe/xe_bo.c index c74c121ea7bb..5b232f2951b1 100644 --- a/drivers/gpu/drm/xe/xe_bo.c +++ b/drivers/gpu/drm/xe/xe_bo.c @@ -1454,7 +1454,8 @@ static struct xe_bo * __xe_bo_create_locked(struct xe_device *xe, struct xe_tile *tile, struct xe_vm *vm, size_t size, u64 start, u64 end, - u16 cpu_caching, enum ttm_bo_type type, u32 flags) + u16 cpu_caching, enum ttm_bo_type type, u32 flags, + u64 alignment) { struct xe_bo *bo = NULL; int err; @@ -1483,6 +1484,8 @@ __xe_bo_create_locked(struct xe_device *xe, if (IS_ERR(bo)) return bo; + bo->min_align = alignment; + /* * Note that instead of taking a reference no the drm_gpuvm_resv_bo(), * to ensure the shared resv doesn't disappear under the bo, the bo @@ -1523,16 +1526,18 @@ struct xe_bo * xe_bo_create_locked_range(struct xe_device *xe, struct xe_tile *tile, struct xe_vm *vm, size_t size, u64 start, u64 end, - enum ttm_bo_type type, u32 flags) + enum ttm_bo_type type, u32 flags, u64 alignment) { - return __xe_bo_create_locked(xe, tile, vm, size, start, end, 0, type, flags); + return __xe_bo_create_locked(xe, tile, vm, size, start, end, 0, type, + flags, alignment); } struct xe_bo *xe_bo_create_locked(struct xe_device *xe, struct xe_tile *tile, struct xe_vm *vm, size_t size, enum ttm_bo_type type, u32 flags) { - return __xe_bo_create_locked(xe, tile, vm, size, 0, ~0ULL, 0, type, flags); + return __xe_bo_create_locked(xe, tile, vm, size, 0, ~0ULL, 0, type, + flags, 0); } struct xe_bo *xe_bo_create_user(struct xe_device *xe, struct xe_tile *tile, @@ -1542,7 +1547,7 @@ struct xe_bo *xe_bo_create_user(struct xe_device *xe, struct xe_tile *tile, { struct xe_bo *bo = __xe_bo_create_locked(xe, tile, vm, size, 0, ~0ULL, cpu_caching, ttm_bo_type_device, - flags | XE_BO_FLAG_USER); + flags | XE_BO_FLAG_USER, 0); if (!IS_ERR(bo)) xe_bo_unlock_vm_held(bo); @@ -1566,6 +1571,17 @@ struct xe_bo *xe_bo_create_pin_map_at(struct xe_device *xe, struct xe_tile *tile size_t size, u64 offset, enum ttm_bo_type type, u32 flags) { + return xe_bo_create_pin_map_at_aligned(xe, tile, vm, size, offset, + type, flags, 0); +} + +struct xe_bo *xe_bo_create_pin_map_at_aligned(struct xe_device *xe, + struct xe_tile *tile, + struct xe_vm *vm, + size_t size, u64 offset, + enum ttm_bo_type type, u32 flags, + u64 alignment) +{ struct xe_bo *bo; int err; u64 start = offset == ~0ull ? 0 : offset; @@ -1576,7 +1592,8 @@ struct xe_bo *xe_bo_create_pin_map_at(struct xe_device *xe, struct xe_tile *tile flags |= XE_BO_FLAG_GGTT; bo = xe_bo_create_locked_range(xe, tile, vm, size, start, end, type, - flags | XE_BO_FLAG_NEEDS_CPU_ACCESS); + flags | XE_BO_FLAG_NEEDS_CPU_ACCESS, + alignment); if (IS_ERR(bo)) return bo; diff --git a/drivers/gpu/drm/xe/xe_bo.h b/drivers/gpu/drm/xe/xe_bo.h index 6e4be52306df..7fa44a0138b0 100644 --- a/drivers/gpu/drm/xe/xe_bo.h +++ b/drivers/gpu/drm/xe/xe_bo.h @@ -77,7 +77,7 @@ struct xe_bo * xe_bo_create_locked_range(struct xe_device *xe, struct xe_tile *tile, struct xe_vm *vm, size_t size, u64 start, u64 end, - enum ttm_bo_type type, u32 flags); + enum ttm_bo_type type, u32 flags, u64 alignment); struct xe_bo *xe_bo_create_locked(struct xe_device *xe, struct xe_tile *tile, struct xe_vm *vm, size_t size, enum ttm_bo_type type, u32 flags); @@ -94,6 +94,12 @@ struct xe_bo *xe_bo_create_pin_map(struct xe_device *xe, struct xe_tile *tile, struct xe_bo *xe_bo_create_pin_map_at(struct xe_device *xe, struct xe_tile *tile, struct xe_vm *vm, size_t size, u64 offset, enum ttm_bo_type type, u32 flags); +struct xe_bo *xe_bo_create_pin_map_at_aligned(struct xe_device *xe, + struct xe_tile *tile, + struct xe_vm *vm, + size_t size, u64 offset, + enum ttm_bo_type type, u32 flags, + u64 alignment); struct xe_bo *xe_bo_create_from_data(struct xe_device *xe, struct xe_tile *tile, const void *data, size_t size, enum ttm_bo_type type, u32 flags); @@ -312,8 +318,6 @@ static inline unsigned int xe_sg_segment_size(struct device *dev) return round_down(max / 2, PAGE_SIZE); } -#define i915_gem_object_flush_if_display(obj) ((void)(obj)) - #if IS_ENABLED(CONFIG_DRM_XE_KUNIT_TEST) /** * xe_bo_is_mem_type - Whether the bo currently resides in the given diff --git a/drivers/gpu/drm/xe/xe_bo_types.h b/drivers/gpu/drm/xe/xe_bo_types.h index 2ed558ac2264..13c6d8a69e91 100644 --- a/drivers/gpu/drm/xe/xe_bo_types.h +++ b/drivers/gpu/drm/xe/xe_bo_types.h @@ -76,9 +76,11 @@ struct xe_bo { /** @vram_userfault_link: Link into @mem_access.vram_userfault.list */ struct list_head vram_userfault_link; -}; -#define intel_bo_to_drm_bo(bo) (&(bo)->ttm.base) -#define intel_bo_to_i915(bo) to_i915(intel_bo_to_drm_bo(bo)->dev) + /** @min_align: minimum alignment needed for this BO if different + * from default + */ + u64 min_align; +}; #endif diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c index 088369897aa7..f6c87d14f78c 100644 --- a/drivers/gpu/drm/xe/xe_device.c +++ b/drivers/gpu/drm/xe/xe_device.c @@ -925,7 +925,7 @@ void xe_device_l2_flush(struct xe_device *xe) spin_lock(>->global_invl_lock); xe_mmio_write32(>->mmio, XE2_GLOBAL_INVAL, 0x1); - if (xe_mmio_wait32(>->mmio, XE2_GLOBAL_INVAL, 0x1, 0x0, 150, NULL, true)) + if (xe_mmio_wait32(>->mmio, XE2_GLOBAL_INVAL, 0x1, 0x0, 500, NULL, true)) xe_gt_err_once(gt, "Global invalidation timeout\n"); spin_unlock(>->global_invl_lock); diff --git a/drivers/gpu/drm/xe/xe_exec.c b/drivers/gpu/drm/xe/xe_exec.c index 7b38485817dc..f23ac1e2ed88 100644 --- a/drivers/gpu/drm/xe/xe_exec.c +++ b/drivers/gpu/drm/xe/xe_exec.c @@ -41,11 +41,6 @@ * user knows an exec writes to a BO and reads from the BO in the next exec, it * is the user's responsibility to pass in / out fence between the two execs). * - * Implicit dependencies for external BOs are handled by using the dma-buf - * implicit dependency uAPI (TODO: add link). To make this works each exec must - * install the job's fence into the DMA_RESV_USAGE_WRITE slot of every external - * BO mapped in the VM. - * * We do not allow a user to trigger a bind at exec time rather we have a VM * bind IOCTL which uses the same in / out fence interface as exec. In that * sense, a VM bind is basically the same operation as an exec from the user @@ -59,8 +54,8 @@ * behind any pending kernel operations on any external BOs in VM or any BOs * private to the VM. This is accomplished by the rebinds waiting on BOs * DMA_RESV_USAGE_KERNEL slot (kernel ops) and kernel ops waiting on all BOs - * slots (inflight execs are in the DMA_RESV_USAGE_BOOKING for private BOs and - * in DMA_RESV_USAGE_WRITE for external BOs). + * slots (inflight execs are in the DMA_RESV_USAGE_BOOKKEEP for private BOs and + * for external BOs). * * Rebinds / dma-resv usage applies to non-compute mode VMs only as for compute * mode VMs we use preempt fences and a rebind worker (TODO: add link). @@ -304,7 +299,8 @@ retry: xe_sched_job_arm(job); if (!xe_vm_in_lr_mode(vm)) drm_gpuvm_resv_add_fence(&vm->gpuvm, exec, &job->drm.s_fence->finished, - DMA_RESV_USAGE_BOOKKEEP, DMA_RESV_USAGE_WRITE); + DMA_RESV_USAGE_BOOKKEEP, + DMA_RESV_USAGE_BOOKKEEP); for (i = 0; i < num_syncs; i++) { xe_sync_entry_signal(&syncs[i], &job->drm.s_fence->finished); diff --git a/drivers/gpu/drm/xe/xe_force_wake.c b/drivers/gpu/drm/xe/xe_force_wake.c index a64c14757c84..08621717b14b 100644 --- a/drivers/gpu/drm/xe/xe_force_wake.c +++ b/drivers/gpu/drm/xe/xe_force_wake.c @@ -115,9 +115,15 @@ static int __domain_wait(struct xe_gt *gt, struct xe_force_wake_domain *domain, XE_FORCE_WAKE_ACK_TIMEOUT_MS * USEC_PER_MSEC, &value, true); if (ret) - xe_gt_notice(gt, "Force wake domain %d failed to ack %s (%pe) reg[%#x] = %#x\n", - domain->id, str_wake_sleep(wake), ERR_PTR(ret), - domain->reg_ack.addr, value); + xe_gt_err(gt, "Force wake domain %d failed to ack %s (%pe) reg[%#x] = %#x\n", + domain->id, str_wake_sleep(wake), ERR_PTR(ret), + domain->reg_ack.addr, value); + if (value == ~0) { + xe_gt_err(gt, + "Force wake domain %d: %s. MMIO unreliable (forcewake register returns 0xFFFFFFFF)!\n", + domain->id, str_wake_sleep(wake)); + ret = -EIO; + } return ret; } diff --git a/drivers/gpu/drm/xe/xe_ggtt.c b/drivers/gpu/drm/xe/xe_ggtt.c index 47bfd9d2635d..65bc41d2c867 100644 --- a/drivers/gpu/drm/xe/xe_ggtt.c +++ b/drivers/gpu/drm/xe/xe_ggtt.c @@ -401,6 +401,16 @@ static void ggtt_invalidate_gt_tlb(struct xe_gt *gt) static void xe_ggtt_invalidate(struct xe_ggtt *ggtt) { + struct xe_device *xe = tile_to_xe(ggtt->tile); + + /* + * XXX: Barrier for GGTT pages. Unsure exactly why this required but + * without this LNL is having issues with the GuC reading scratch page + * vs. correct GGTT page. Not particularly a hot code path so blindly + * do a mmio read here which results in GuC reading correct GGTT page. + */ + xe_mmio_read32(&xe_root_mmio_gt(xe)->mmio, VF_CAP_REG); + /* Each GT in a tile has its own TLB to cache GGTT lookups */ ggtt_invalidate_gt_tlb(ggtt->tile->primary_gt); ggtt_invalidate_gt_tlb(ggtt->tile->media_gt); @@ -603,7 +613,7 @@ static int __xe_ggtt_insert_bo_at(struct xe_ggtt *ggtt, struct xe_bo *bo, u64 start, u64 end) { int err; - u64 alignment = XE_PAGE_SIZE; + u64 alignment = bo->min_align > 0 ? bo->min_align : XE_PAGE_SIZE; if (xe_bo_is_vram(bo) && ggtt->flags & XE_GGTT_FLAGS_64K) alignment = SZ_64K; diff --git a/drivers/gpu/drm/xe/xe_gpu_scheduler.h b/drivers/gpu/drm/xe/xe_gpu_scheduler.h index 5ad5629a6c60..64b2ae6839db 100644 --- a/drivers/gpu/drm/xe/xe_gpu_scheduler.h +++ b/drivers/gpu/drm/xe/xe_gpu_scheduler.h @@ -63,7 +63,9 @@ xe_sched_invalidate_job(struct xe_sched_job *job, int threshold) static inline void xe_sched_add_pending_job(struct xe_gpu_scheduler *sched, struct xe_sched_job *job) { + spin_lock(&sched->base.job_list_lock); list_add(&job->drm.list, &sched->base.pending_list); + spin_unlock(&sched->base.job_list_lock); } static inline diff --git a/drivers/gpu/drm/xe/xe_guc_ct.c b/drivers/gpu/drm/xe/xe_guc_ct.c index c7673f56d413..c260d8840990 100644 --- a/drivers/gpu/drm/xe/xe_guc_ct.c +++ b/drivers/gpu/drm/xe/xe_guc_ct.c @@ -1019,6 +1019,24 @@ retry_same_fence: ret = wait_event_timeout(ct->g2h_fence_wq, g2h_fence.done, HZ); /* + * Occasionally it is seen that the G2H worker starts running after a delay of more than + * a second even after being queued and activated by the Linux workqueue subsystem. This + * leads to G2H timeout error. The root cause of issue lies with scheduling latency of + * Lunarlake Hybrid CPU. Issue dissappears if we disable Lunarlake atom cores from BIOS + * and this is beyond xe kmd. + * + * TODO: Drop this change once workqueue scheduling delay issue is fixed on LNL Hybrid CPU. + */ + if (!ret) { + flush_work(&ct->g2h_worker); + if (g2h_fence.done) { + xe_gt_warn(gt, "G2H fence %u, action %04x, done\n", + g2h_fence.seqno, action[0]); + ret = 1; + } + } + + /* * Ensure we serialize with completion side to prevent UAF with fence going out of scope on * the stack, since we have no clue if it will fire after the timeout before we can erase * from the xa. Also we have some dependent loads and stores below for which we need the diff --git a/drivers/gpu/drm/xe/xe_guc_log.c b/drivers/gpu/drm/xe/xe_guc_log.c index 93921f04153f..cc70f448d879 100644 --- a/drivers/gpu/drm/xe/xe_guc_log.c +++ b/drivers/gpu/drm/xe/xe_guc_log.c @@ -122,7 +122,7 @@ void xe_guc_log_snapshot_free(struct xe_guc_log_snapshot *snapshot) if (!snapshot) return; - if (!snapshot->copy) { + if (snapshot->copy) { for (i = 0; i < snapshot->num_chunks; i++) kfree(snapshot->copy[i]); kfree(snapshot->copy); diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c index c1ebc693a617..5f8c7a45b028 100644 --- a/drivers/gpu/drm/xe/xe_guc_submit.c +++ b/drivers/gpu/drm/xe/xe_guc_submit.c @@ -225,80 +225,11 @@ static bool exec_queue_killed_or_banned_or_wedged(struct xe_exec_queue *q) EXEC_QUEUE_STATE_BANNED)); } -#ifdef CONFIG_PROVE_LOCKING -static int alloc_submit_wq(struct xe_guc *guc) -{ - int i; - - for (i = 0; i < NUM_SUBMIT_WQ; ++i) { - guc->submission_state.submit_wq_pool[i] = - alloc_ordered_workqueue("submit_wq", 0); - if (!guc->submission_state.submit_wq_pool[i]) - goto err_free; - } - - return 0; - -err_free: - while (i) - destroy_workqueue(guc->submission_state.submit_wq_pool[--i]); - - return -ENOMEM; -} - -static void free_submit_wq(struct xe_guc *guc) -{ - int i; - - for (i = 0; i < NUM_SUBMIT_WQ; ++i) - destroy_workqueue(guc->submission_state.submit_wq_pool[i]); -} - -static struct workqueue_struct *get_submit_wq(struct xe_guc *guc) -{ - int idx = guc->submission_state.submit_wq_idx++ % NUM_SUBMIT_WQ; - - return guc->submission_state.submit_wq_pool[idx]; -} -#else -static int alloc_submit_wq(struct xe_guc *guc) -{ - return 0; -} - -static void free_submit_wq(struct xe_guc *guc) -{ - -} - -static struct workqueue_struct *get_submit_wq(struct xe_guc *guc) -{ - return NULL; -} -#endif - -static void xe_guc_submit_fini(struct xe_guc *guc) -{ - struct xe_device *xe = guc_to_xe(guc); - struct xe_gt *gt = guc_to_gt(guc); - int ret; - - ret = wait_event_timeout(guc->submission_state.fini_wq, - xa_empty(&guc->submission_state.exec_queue_lookup), - HZ * 5); - - drain_workqueue(xe->destroy_wq); - - xe_gt_assert(gt, ret); -} - static void guc_submit_fini(struct drm_device *drm, void *arg) { struct xe_guc *guc = arg; - xe_guc_submit_fini(guc); xa_destroy(&guc->submission_state.exec_queue_lookup); - free_submit_wq(guc); } static void guc_submit_wedged_fini(void *arg) @@ -360,10 +291,6 @@ int xe_guc_submit_init(struct xe_guc *guc, unsigned int num_ids) if (err) return err; - err = alloc_submit_wq(guc); - if (err) - return err; - gt->exec_queue_ops = &guc_exec_queue_ops; xa_init(&guc->submission_state.exec_queue_lookup); @@ -990,12 +917,22 @@ static void xe_guc_exec_queue_lr_cleanup(struct work_struct *w) static bool check_timeout(struct xe_exec_queue *q, struct xe_sched_job *job) { struct xe_gt *gt = guc_to_gt(exec_queue_to_guc(q)); - u32 ctx_timestamp = xe_lrc_ctx_timestamp(q->lrc[0]); - u32 ctx_job_timestamp = xe_lrc_ctx_job_timestamp(q->lrc[0]); + u32 ctx_timestamp, ctx_job_timestamp; u32 timeout_ms = q->sched_props.job_timeout_ms; u32 diff; u64 running_time_ms; + if (!xe_sched_job_started(job)) { + xe_gt_warn(gt, "Check job timeout: seqno=%u, lrc_seqno=%u, guc_id=%d, not started", + xe_sched_job_seqno(job), xe_sched_job_lrc_seqno(job), + q->guc->id); + + return xe_sched_invalidate_job(job, 2); + } + + ctx_timestamp = xe_lrc_ctx_timestamp(q->lrc[0]); + ctx_job_timestamp = xe_lrc_ctx_job_timestamp(q->lrc[0]); + /* * Counter wraps at ~223s at the usual 19.2MHz, be paranoid catch * possible overflows with a high timeout. @@ -1105,10 +1042,13 @@ guc_exec_queue_timedout_job(struct drm_sched_job *drm_job) /* * TDR has fired before free job worker. Common if exec queue - * immediately closed after last fence signaled. + * immediately closed after last fence signaled. Add back to pending + * list so job can be freed and kick scheduler ensuring free job is not + * lost. */ if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &job->fence->flags)) { - guc_exec_queue_free_job(drm_job); + xe_sched_add_pending_job(sched, job); + xe_sched_submission_start(sched); return DRM_GPU_SCHED_STAT_NOMINAL; } @@ -1121,10 +1061,6 @@ guc_exec_queue_timedout_job(struct drm_sched_job *drm_job) exec_queue_killed_or_banned_or_wedged(q) || exec_queue_destroyed(q); - /* Job hasn't started, can't be timed out */ - if (!skip_timeout_check && !xe_sched_job_started(job)) - goto rearm; - /* * If devcoredump not captured and GuC capture for the job is not ready * do manual capture first and decide later if we need to use it @@ -1496,8 +1432,7 @@ static int guc_exec_queue_init(struct xe_exec_queue *q) timeout = (q->vm && xe_vm_in_lr_mode(q->vm)) ? MAX_SCHEDULE_TIMEOUT : msecs_to_jiffies(q->sched_props.job_timeout_ms); err = xe_sched_init(&ge->sched, &drm_sched_ops, &xe_sched_ops, - get_submit_wq(guc), - q->lrc[0]->ring.size / MAX_JOB_SIZE_BYTES, 64, + NULL, q->lrc[0]->ring.size / MAX_JOB_SIZE_BYTES, 64, timeout, guc_to_gt(guc)->ordered_wq, NULL, q->name, gt_to_xe(q->gt)->drm.dev); if (err) @@ -1814,8 +1749,13 @@ void xe_guc_submit_stop(struct xe_guc *guc) mutex_lock(&guc->submission_state.lock); - xa_for_each(&guc->submission_state.exec_queue_lookup, index, q) + xa_for_each(&guc->submission_state.exec_queue_lookup, index, q) { + /* Prevent redundant attempts to stop parallel queues */ + if (q->guc->id != index) + continue; + guc_exec_queue_stop(guc, q); + } mutex_unlock(&guc->submission_state.lock); @@ -1853,8 +1793,13 @@ int xe_guc_submit_start(struct xe_guc *guc) mutex_lock(&guc->submission_state.lock); atomic_dec(&guc->submission_state.stopped); - xa_for_each(&guc->submission_state.exec_queue_lookup, index, q) + xa_for_each(&guc->submission_state.exec_queue_lookup, index, q) { + /* Prevent redundant attempts to start parallel queues */ + if (q->guc->id != index) + continue; + guc_exec_queue_start(q); + } mutex_unlock(&guc->submission_state.lock); wake_up_all(&guc->ct.wq); diff --git a/drivers/gpu/drm/xe/xe_guc_types.h b/drivers/gpu/drm/xe/xe_guc_types.h index ebc5a2237648..fa75f57bf5da 100644 --- a/drivers/gpu/drm/xe/xe_guc_types.h +++ b/drivers/gpu/drm/xe/xe_guc_types.h @@ -74,13 +74,6 @@ struct xe_guc { atomic_t stopped; /** @submission_state.lock: protects submission state */ struct mutex lock; -#ifdef CONFIG_PROVE_LOCKING -#define NUM_SUBMIT_WQ 256 - /** @submission_state.submit_wq_pool: submission ordered workqueues pool */ - struct workqueue_struct *submit_wq_pool[NUM_SUBMIT_WQ]; - /** @submission_state.submit_wq_idx: submission ordered workqueue index */ - int submit_wq_idx; -#endif /** @submission_state.enabled: submission is enabled */ bool enabled; /** @submission_state.fini_wq: submit fini wait queue */ diff --git a/drivers/gpu/drm/xe/xe_query.c b/drivers/gpu/drm/xe/xe_query.c index 158629971eab..5093a243e9fe 100644 --- a/drivers/gpu/drm/xe/xe_query.c +++ b/drivers/gpu/drm/xe/xe_query.c @@ -85,16 +85,13 @@ static __ktime_func_t __clock_id_to_func(clockid_t clk_id) } static void -__read_timestamps(struct xe_gt *gt, - struct xe_reg lower_reg, - struct xe_reg upper_reg, - u64 *engine_ts, - u64 *cpu_ts, - u64 *cpu_delta, - __ktime_func_t cpu_clock) +hwe_read_timestamp(struct xe_hw_engine *hwe, u64 *engine_ts, u64 *cpu_ts, + u64 *cpu_delta, __ktime_func_t cpu_clock) { - struct xe_mmio *mmio = >->mmio; + struct xe_mmio *mmio = &hwe->gt->mmio; u32 upper, lower, old_upper, loop = 0; + struct xe_reg upper_reg = RING_TIMESTAMP_UDW(hwe->mmio_base), + lower_reg = RING_TIMESTAMP(hwe->mmio_base); upper = xe_mmio_read32(mmio, upper_reg); do { @@ -155,28 +152,21 @@ query_engine_cycles(struct xe_device *xe, if (xe_force_wake_get(gt_to_fw(gt), XE_FORCEWAKE_ALL)) return -EIO; - __read_timestamps(gt, - RING_TIMESTAMP(hwe->mmio_base), - RING_TIMESTAMP_UDW(hwe->mmio_base), - &resp.engine_cycles, - &resp.cpu_timestamp, - &resp.cpu_delta, - cpu_clock); + hwe_read_timestamp(hwe, &resp.engine_cycles, &resp.cpu_timestamp, + &resp.cpu_delta, cpu_clock); xe_force_wake_put(gt_to_fw(gt), XE_FORCEWAKE_ALL); - resp.width = 36; - /* Only write to the output fields of user query */ - if (put_user(resp.cpu_timestamp, &query_ptr->cpu_timestamp)) - return -EFAULT; - - if (put_user(resp.cpu_delta, &query_ptr->cpu_delta)) - return -EFAULT; - - if (put_user(resp.engine_cycles, &query_ptr->engine_cycles)) - return -EFAULT; + if (GRAPHICS_VER(xe) >= 20) + resp.width = 64; + else + resp.width = 36; - if (put_user(resp.width, &query_ptr->width)) + /* Only write to the output fields of user query */ + if (put_user(resp.cpu_timestamp, &query_ptr->cpu_timestamp) || + put_user(resp.cpu_delta, &query_ptr->cpu_delta) || + put_user(resp.engine_cycles, &query_ptr->engine_cycles) || + put_user(resp.width, &query_ptr->width)) return -EFAULT; return 0; diff --git a/drivers/gpu/drm/xe/xe_sync.c b/drivers/gpu/drm/xe/xe_sync.c index bb3c2a830362..2e72c06fd40d 100644 --- a/drivers/gpu/drm/xe/xe_sync.c +++ b/drivers/gpu/drm/xe/xe_sync.c @@ -54,11 +54,12 @@ static struct xe_user_fence *user_fence_create(struct xe_device *xe, u64 addr, { struct xe_user_fence *ufence; u64 __user *ptr = u64_to_user_ptr(addr); + u64 __maybe_unused prefetch_val; - if (!access_ok(ptr, sizeof(*ptr))) + if (get_user(prefetch_val, ptr)) return ERR_PTR(-EFAULT); - ufence = kmalloc(sizeof(*ufence), GFP_KERNEL); + ufence = kzalloc(sizeof(*ufence), GFP_KERNEL); if (!ufence) return ERR_PTR(-ENOMEM); diff --git a/drivers/gpu/drm/xe/xe_wa.c b/drivers/gpu/drm/xe/xe_wa.c index 0c90438e8e72..02cf647f86d8 100644 --- a/drivers/gpu/drm/xe/xe_wa.c +++ b/drivers/gpu/drm/xe/xe_wa.c @@ -602,6 +602,11 @@ static const struct xe_rtp_entry_sr engine_was[] = { XE_RTP_RULES(GRAPHICS_VERSION_RANGE(3000, 3001), FUNC(xe_rtp_match_first_render_or_compute)), XE_RTP_ACTIONS(SET(HALF_SLICE_CHICKEN7, CLEAR_OPTIMIZATION_DISABLE)) }, + { XE_RTP_NAME("18034896535"), + XE_RTP_RULES(GRAPHICS_VERSION(3000), GRAPHICS_STEP(A0, B0), + FUNC(xe_rtp_match_first_render_or_compute)), + XE_RTP_ACTIONS(SET(ROW_CHICKEN4, DISABLE_TDL_PUSH)) + }, {} }; diff --git a/drivers/gpu/drm/xe/xe_wait_user_fence.c b/drivers/gpu/drm/xe/xe_wait_user_fence.c index d46fa8374980..f5deb81eba01 100644 --- a/drivers/gpu/drm/xe/xe_wait_user_fence.c +++ b/drivers/gpu/drm/xe/xe_wait_user_fence.c @@ -169,9 +169,6 @@ int xe_wait_user_fence_ioctl(struct drm_device *dev, void *data, args->timeout = 0; } - if (!timeout && !(err < 0)) - err = -ETIME; - if (q) xe_exec_queue_put(q); |