diff options
| author | Thomas Zimmermann <tzimmermann@suse.de> | 2026-03-31 11:05:42 +0200 |
|---|---|---|
| committer | Thomas Zimmermann <tzimmermann@suse.de> | 2026-03-31 11:05:42 +0200 |
| commit | 86a28e154c3a754cf661c91b57eb96816e8485df (patch) | |
| tree | ef725a2feb9010fd123903f84b73ce9639133e36 /include | |
| parent | fb7b1a0ab25a6077d26cb3829e31743972d4f31d (diff) | |
| parent | f6225b546dfccfc322b18c0d757b7b9c767a1e27 (diff) | |
Merge drm/drm-next into drm-misc-next
Backmerging to get fixes and updates from v7.0-rc6.
Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de>
Diffstat (limited to 'include')
76 files changed, 1517 insertions, 226 deletions
diff --git a/include/drm/drm_fb_helper.h b/include/drm/drm_fb_helper.h index 15274b8a1d97..bf391903443d 100644 --- a/include/drm/drm_fb_helper.h +++ b/include/drm/drm_fb_helper.h @@ -271,6 +271,8 @@ int drm_fb_helper_ioctl(struct fb_info *info, unsigned int cmd, int drm_fb_helper_hotplug_event(struct drm_fb_helper *fb_helper); int drm_fb_helper_initial_config(struct drm_fb_helper *fb_helper); +bool drm_fb_helper_gem_is_fb(const struct drm_fb_helper *fb_helper, + const struct drm_gem_object *obj); #endif #endif diff --git a/include/drm/drm_pagemap.h b/include/drm/drm_pagemap.h index c848f578e3da..75e6ca58922d 100644 --- a/include/drm/drm_pagemap.h +++ b/include/drm/drm_pagemap.h @@ -4,6 +4,7 @@ #include <linux/dma-direction.h> #include <linux/hmm.h> +#include <linux/memremap.h> #include <linux/types.h> #define NR_PAGES(order) (1U << (order)) @@ -367,6 +368,26 @@ void drm_pagemap_destroy(struct drm_pagemap *dpagemap, bool is_atomic_or_reclaim int drm_pagemap_reinit(struct drm_pagemap *dpagemap); +/** + * drm_pagemap_page_zone_device_data() - Page to zone_device_data + * @page: Pointer to the page + * + * Return: Page's zone_device_data + */ +static inline struct drm_pagemap_zdd *drm_pagemap_page_zone_device_data(struct page *page) +{ + struct folio *folio = page_folio(page); + + return folio_zone_device_data(folio); +} + +#else + +static inline struct drm_pagemap_zdd *drm_pagemap_page_zone_device_data(struct page *page) +{ + return NULL; +} + #endif /* IS_ENABLED(CONFIG_ZONE_DEVICE) */ #endif diff --git a/include/drm/drm_ras.h b/include/drm/drm_ras.h new file mode 100644 index 000000000000..5d50209e51db --- /dev/null +++ b/include/drm/drm_ras.h @@ -0,0 +1,75 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright © 2026 Intel Corporation + */ + +#ifndef __DRM_RAS_H__ +#define __DRM_RAS_H__ + +#include <uapi/drm/drm_ras.h> + +/** + * struct drm_ras_node - A DRM RAS Node + */ +struct drm_ras_node { + /** @id: Unique identifier for the node. Dynamically assigned. */ + u32 id; + /** + * @device_name: Human-readable name of the device. Given by the driver. + */ + const char *device_name; + /** @node_name: Human-readable name of the node. Given by the driver. */ + const char *node_name; + /** @type: Type of the node (enum drm_ras_node_type). */ + enum drm_ras_node_type type; + + /* Error-Counter Related Callback and Variables */ + + /** @error_counter_range: Range of valid Error IDs for this node. */ + struct { + /** @first: First valid Error ID. */ + u32 first; + /** @last: Last valid Error ID. Mandatory entry. */ + u32 last; + } error_counter_range; + + /** + * @query_error_counter: + * + * This callback is used by drm-ras to query a specific error counter. + * Used for input check and to iterate all error counters in a node. + * + * Driver should expect query_error_counter() to be called with + * error_id from `error_counter_range.first` to + * `error_counter_range.last`. + * + * The @query_error_counter is a mandatory callback for + * error_counter_node. + * + * Returns: 0 on success, + * -ENOENT when error_id is not supported as an indication that + * drm_ras should silently skip this entry. Used for + * supporting non-contiguous error ranges. + * Driver is responsible for maintaining the list of + * supported error IDs in the range of first to last. + * Other negative values on errors that should terminate the + * netlink query. + */ + int (*query_error_counter)(struct drm_ras_node *node, u32 error_id, + const char **name, u32 *val); + + /** @priv: Driver private data */ + void *priv; +}; + +struct drm_device; + +#if IS_ENABLED(CONFIG_DRM_RAS) +int drm_ras_node_register(struct drm_ras_node *node); +void drm_ras_node_unregister(struct drm_ras_node *node); +#else +static inline int drm_ras_node_register(struct drm_ras_node *node) { return 0; } +static inline void drm_ras_node_unregister(struct drm_ras_node *node) { } +#endif + +#endif diff --git a/include/drm/drm_ras_genl_family.h b/include/drm/drm_ras_genl_family.h new file mode 100644 index 000000000000..910fb3943a75 --- /dev/null +++ b/include/drm/drm_ras_genl_family.h @@ -0,0 +1,17 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright © 2026 Intel Corporation + */ + +#ifndef __DRM_RAS_GENL_FAMILY_H__ +#define __DRM_RAS_GENL_FAMILY_H__ + +#if IS_ENABLED(CONFIG_DRM_RAS) +int drm_ras_genl_family_register(void); +void drm_ras_genl_family_unregister(void); +#else +static inline int drm_ras_genl_family_register(void) { return 0; } +static inline void drm_ras_genl_family_unregister(void) { } +#endif + +#endif diff --git a/include/drm/intel/display_parent_interface.h b/include/drm/intel/display_parent_interface.h index ce946859a3a9..97ec94a2e749 100644 --- a/include/drm/intel/display_parent_interface.h +++ b/include/drm/intel/display_parent_interface.h @@ -9,19 +9,66 @@ struct dma_fence; struct drm_crtc; struct drm_device; +struct drm_file; struct drm_framebuffer; struct drm_gem_object; +struct drm_mode_fb_cmd2; struct drm_plane_state; struct drm_scanout_buffer; struct i915_vma; +struct intel_dpt; +struct intel_dsb_buffer; +struct intel_frontbuffer; struct intel_hdcp_gsc_context; struct intel_initial_plane_config; struct intel_panic; struct intel_stolen_node; struct ref_tracker; +struct seq_file; +struct vm_area_struct; /* Keep struct definitions sorted */ +struct intel_display_bo_interface { + bool (*is_tiled)(struct drm_gem_object *obj); /* Optional */ + bool (*is_userptr)(struct drm_gem_object *obj); /* Optional */ + bool (*is_shmem)(struct drm_gem_object *obj); /* Optional */ + bool (*is_protected)(struct drm_gem_object *obj); + int (*key_check)(struct drm_gem_object *obj); + int (*fb_mmap)(struct drm_gem_object *obj, struct vm_area_struct *vma); + int (*read_from_page)(struct drm_gem_object *obj, u64 offset, void *dst, int size); + void (*describe)(struct seq_file *m, struct drm_gem_object *obj); /* Optional */ + int (*framebuffer_init)(struct drm_gem_object *obj, struct drm_mode_fb_cmd2 *mode_cmd); + void (*framebuffer_fini)(struct drm_gem_object *obj); + struct drm_gem_object *(*framebuffer_lookup)(struct drm_device *drm, + struct drm_file *filp, + const struct drm_mode_fb_cmd2 *user_mode_cmd); +}; + +struct intel_display_dpt_interface { + struct intel_dpt *(*create)(struct drm_gem_object *obj, size_t size); + void (*destroy)(struct intel_dpt *dpt); + void (*suspend)(struct intel_dpt *dpt); + void (*resume)(struct intel_dpt *dpt); +}; + +struct intel_display_dsb_interface { + u32 (*ggtt_offset)(struct intel_dsb_buffer *dsb_buf); + void (*write)(struct intel_dsb_buffer *dsb_buf, u32 idx, u32 val); + u32 (*read)(struct intel_dsb_buffer *dsb_buf, u32 idx); + void (*fill)(struct intel_dsb_buffer *dsb_buf, u32 idx, u32 val, size_t size); + struct intel_dsb_buffer *(*create)(struct drm_device *drm, size_t size); + void (*cleanup)(struct intel_dsb_buffer *dsb_buf); + void (*flush_map)(struct intel_dsb_buffer *dsb_buf); +}; + +struct intel_display_frontbuffer_interface { + struct intel_frontbuffer *(*get)(struct drm_gem_object *obj); + void (*ref)(struct intel_frontbuffer *front); + void (*put)(struct intel_frontbuffer *front); + void (*flush_for_display)(struct intel_frontbuffer *front); +}; + struct intel_display_hdcp_interface { ssize_t (*gsc_msg_send)(struct intel_hdcp_gsc_context *gsc_context, void *msg_in, size_t msg_in_len, @@ -44,6 +91,35 @@ struct intel_display_irq_interface { void (*synchronize)(struct drm_device *drm); }; +struct intel_display_overlay_interface { + bool (*is_active)(struct drm_device *drm); + + int (*overlay_on)(struct drm_device *drm, + u32 frontbuffer_bits); + int (*overlay_continue)(struct drm_device *drm, + struct i915_vma *vma, + bool load_polyphase_filter); + int (*overlay_off)(struct drm_device *drm); + int (*recover_from_interrupt)(struct drm_device *drm); + int (*release_old_vid)(struct drm_device *drm); + + void (*reset)(struct drm_device *drm); + + struct i915_vma *(*pin_fb)(struct drm_device *drm, + struct drm_gem_object *obj, + u32 *offset); + void (*unpin_fb)(struct drm_device *drm, + struct i915_vma *vma); + + struct drm_gem_object *(*obj_lookup)(struct drm_device *drm, + struct drm_file *filp, + u32 handle); + + void __iomem *(*setup)(struct drm_device *drm, + bool needs_physical); + void (*cleanup)(struct drm_device *drm); +}; + struct intel_display_panic_interface { struct intel_panic *(*alloc)(void); int (*setup)(struct intel_panic *panic, struct drm_scanout_buffer *sb); @@ -55,6 +131,13 @@ struct intel_display_pc8_interface { void (*unblock)(struct drm_device *drm); }; +struct intel_display_pcode_interface { + int (*read)(struct drm_device *drm, u32 mbox, u32 *val, u32 *val1); + int (*write)(struct drm_device *drm, u32 mbox, u32 val, int timeout_ms); + int (*request)(struct drm_device *drm, u32 mbox, u32 request, + u32 reply_mask, u32 reply, int timeout_base_ms); +}; + struct intel_display_rpm_interface { struct ref_tracker *(*get)(const struct drm_device *drm); struct ref_tracker *(*get_raw)(const struct drm_device *drm); @@ -93,6 +176,10 @@ struct intel_display_stolen_interface { void (*node_free)(const struct intel_stolen_node *node); }; +struct intel_display_vma_interface { + int (*fence_id)(const struct i915_vma *vma); +}; + /** * struct intel_display_parent_interface - services parent driver provides to display * @@ -106,6 +193,18 @@ struct intel_display_stolen_interface { * check the optional pointers. */ struct intel_display_parent_interface { + /** @bo: BO interface */ + const struct intel_display_bo_interface *bo; + + /** @dpt: DPT interface. Optional. */ + const struct intel_display_dpt_interface *dpt; + + /** @dsb: DSB buffer interface */ + const struct intel_display_dsb_interface *dsb; + + /** @frontbuffer: Frontbuffer interface */ + const struct intel_display_frontbuffer_interface *frontbuffer; + /** @hdcp: HDCP GSC interface */ const struct intel_display_hdcp_interface *hdcp; @@ -118,9 +217,15 @@ struct intel_display_parent_interface { /** @panic: Panic interface */ const struct intel_display_panic_interface *panic; + /** @overlay: Overlay. Optional. */ + const struct intel_display_overlay_interface *overlay; + /** @pc8: PC8 interface. Optional. */ const struct intel_display_pc8_interface *pc8; + /** @pcode: Pcode interface */ + const struct intel_display_pcode_interface *pcode; + /** @rpm: Runtime PM functions */ const struct intel_display_rpm_interface *rpm; @@ -130,6 +235,9 @@ struct intel_display_parent_interface { /** @stolen: Stolen memory. */ const struct intel_display_stolen_interface *stolen; + /** @vma: VMA interface. Optional. */ + const struct intel_display_vma_interface *vma; + /* Generic independent functions */ struct { /** @fence_priority_display: Set display priority. Optional. */ diff --git a/include/drm/intel/i915_drm.h b/include/drm/intel/i915_drm.h index adff68538484..1fdaabed1470 100644 --- a/include/drm/intel/i915_drm.h +++ b/include/drm/intel/i915_drm.h @@ -39,46 +39,46 @@ bool i915_gpu_turbo_disable(void); extern struct resource intel_graphics_stolen_res; /* - * The Bridge device's PCI config space has information about the - * fb aperture size and the amount of pre-reserved memory. - * This is all handled in the intel-gtt.ko module. i915.ko only - * cares about the vga bit for the vga arbiter. + * The bridge device's (device 0) PCI config space has information + * about the fb aperture size and the amount of pre-reserved memory. */ -#define INTEL_GMCH_CTRL 0x52 -#define INTEL_GMCH_VGA_DISABLE (1 << 1) + +/* device 2 has a read-only mirror */ #define SNB_GMCH_CTRL 0x50 -#define SNB_GMCH_GGMS_SHIFT 8 /* GTT Graphics Memory Size */ -#define SNB_GMCH_GGMS_MASK 0x3 -#define SNB_GMCH_GMS_SHIFT 3 /* Graphics Mode Select */ -#define SNB_GMCH_GMS_MASK 0x1f -#define BDW_GMCH_GGMS_SHIFT 6 -#define BDW_GMCH_GGMS_MASK 0x3 -#define BDW_GMCH_GMS_SHIFT 8 -#define BDW_GMCH_GMS_MASK 0xff +#define SNB_GMCH_GGMS_SHIFT 8 /* GTT Graphics Memory Size */ +#define SNB_GMCH_GGMS_MASK 0x3 +#define SNB_GMCH_GMS_SHIFT 3 /* Graphics Mode Select */ +#define SNB_GMCH_GMS_MASK 0x1f +#define BDW_GMCH_GGMS_SHIFT 6 +#define BDW_GMCH_GGMS_MASK 0x3 +#define BDW_GMCH_GMS_SHIFT 8 +#define BDW_GMCH_GMS_MASK 0xff +/* device 2 has a read-only mirror from i85x/i865 onwards */ #define I830_GMCH_CTRL 0x52 +#define I830_GMCH_GMS_MASK (0x7 << 4) +#define I830_GMCH_GMS_LOCAL (0x1 << 4) +#define I830_GMCH_GMS_STOLEN_512 (0x2 << 4) +#define I830_GMCH_GMS_STOLEN_1024 (0x3 << 4) +#define I830_GMCH_GMS_STOLEN_8192 (0x4 << 4) +#define I855_GMCH_GMS_MASK (0xF << 4) +#define I855_GMCH_GMS_STOLEN_0M (0x0 << 4) +#define I855_GMCH_GMS_STOLEN_1M (0x1 << 4) +#define I855_GMCH_GMS_STOLEN_4M (0x2 << 4) +#define I855_GMCH_GMS_STOLEN_8M (0x3 << 4) +#define I855_GMCH_GMS_STOLEN_16M (0x4 << 4) +#define I855_GMCH_GMS_STOLEN_32M (0x5 << 4) +#define I915_GMCH_GMS_STOLEN_48M (0x6 << 4) +#define I915_GMCH_GMS_STOLEN_64M (0x7 << 4) +#define G33_GMCH_GMS_STOLEN_128M (0x8 << 4) +#define G33_GMCH_GMS_STOLEN_256M (0x9 << 4) +#define INTEL_GMCH_GMS_STOLEN_96M (0xa << 4) +#define INTEL_GMCH_GMS_STOLEN_160M (0xb << 4) +#define INTEL_GMCH_GMS_STOLEN_224M (0xc << 4) +#define INTEL_GMCH_GMS_STOLEN_352M (0xd << 4) -#define I830_GMCH_GMS_MASK 0x70 -#define I830_GMCH_GMS_LOCAL 0x10 -#define I830_GMCH_GMS_STOLEN_512 0x20 -#define I830_GMCH_GMS_STOLEN_1024 0x30 -#define I830_GMCH_GMS_STOLEN_8192 0x40 - -#define I855_GMCH_GMS_MASK 0xF0 -#define I855_GMCH_GMS_STOLEN_0M 0x0 -#define I855_GMCH_GMS_STOLEN_1M (0x1 << 4) -#define I855_GMCH_GMS_STOLEN_4M (0x2 << 4) -#define I855_GMCH_GMS_STOLEN_8M (0x3 << 4) -#define I855_GMCH_GMS_STOLEN_16M (0x4 << 4) -#define I855_GMCH_GMS_STOLEN_32M (0x5 << 4) -#define I915_GMCH_GMS_STOLEN_48M (0x6 << 4) -#define I915_GMCH_GMS_STOLEN_64M (0x7 << 4) -#define G33_GMCH_GMS_STOLEN_128M (0x8 << 4) -#define G33_GMCH_GMS_STOLEN_256M (0x9 << 4) -#define INTEL_GMCH_GMS_STOLEN_96M (0xa << 4) -#define INTEL_GMCH_GMS_STOLEN_160M (0xb << 4) -#define INTEL_GMCH_GMS_STOLEN_224M (0xc << 4) -#define INTEL_GMCH_GMS_STOLEN_352M (0xd << 4) +/* valid for both I830_GMCH_CTRL and SNB_GMCH_CTRL */ +#define INTEL_GMCH_VGA_DISABLE (1 << 1) #define I830_DRB3 0x63 #define I85X_DRB3 0x43 @@ -87,12 +87,12 @@ extern struct resource intel_graphics_stolen_res; #define I830_ESMRAMC 0x91 #define I845_ESMRAMC 0x9e #define I85X_ESMRAMC 0x61 -#define TSEG_ENABLE (1 << 0) -#define I830_TSEG_SIZE_512K (0 << 1) -#define I830_TSEG_SIZE_1M (1 << 1) -#define I845_TSEG_SIZE_MASK (3 << 1) -#define I845_TSEG_SIZE_512K (2 << 1) -#define I845_TSEG_SIZE_1M (3 << 1) +#define TSEG_ENABLE (1 << 0) +#define I830_TSEG_SIZE_512K (0 << 1) +#define I830_TSEG_SIZE_1M (1 << 1) +#define I845_TSEG_SIZE_MASK (3 << 1) +#define I845_TSEG_SIZE_512K (2 << 1) +#define I845_TSEG_SIZE_1M (3 << 1) #define INTEL_BSM 0x5c #define INTEL_GEN11_BSM_DW0 0xc0 diff --git a/include/drm/intel/intel_gmd_interrupt_regs.h b/include/drm/intel/intel_gmd_interrupt_regs.h new file mode 100644 index 000000000000..ce66c4151e76 --- /dev/null +++ b/include/drm/intel/intel_gmd_interrupt_regs.h @@ -0,0 +1,92 @@ +/* SPDX-License-Identifier: MIT */ +/* Copyright © 2026 Intel Corporation */ + +#ifndef _INTEL_GMD_INTERRUPT_REGS_H_ +#define _INTEL_GMD_INTERRUPT_REGS_H_ + +#define I915_PM_INTERRUPT (1 << 31) +#define I915_ISP_INTERRUPT (1 << 22) +#define I915_LPE_PIPE_B_INTERRUPT (1 << 21) +#define I915_LPE_PIPE_A_INTERRUPT (1 << 20) +#define I915_MIPIC_INTERRUPT (1 << 19) +#define I915_MIPIA_INTERRUPT (1 << 18) +#define I915_PIPE_CONTROL_NOTIFY_INTERRUPT (1 << 18) +#define I915_DISPLAY_PORT_INTERRUPT (1 << 17) +#define I915_DISPLAY_PIPE_C_HBLANK_INTERRUPT (1 << 16) +#define I915_MASTER_ERROR_INTERRUPT (1 << 15) +#define I915_DISPLAY_PIPE_B_HBLANK_INTERRUPT (1 << 14) +#define I915_GMCH_THERMAL_SENSOR_EVENT_INTERRUPT (1 << 14) /* p-state */ +#define I915_DISPLAY_PIPE_A_HBLANK_INTERRUPT (1 << 13) +#define I915_HWB_OOM_INTERRUPT (1 << 13) +#define I915_LPE_PIPE_C_INTERRUPT (1 << 12) +#define I915_SYNC_STATUS_INTERRUPT (1 << 12) +#define I915_MISC_INTERRUPT (1 << 11) +#define I915_DISPLAY_PLANE_A_FLIP_PENDING_INTERRUPT (1 << 11) +#define I915_DISPLAY_PIPE_C_VBLANK_INTERRUPT (1 << 10) +#define I915_DISPLAY_PLANE_B_FLIP_PENDING_INTERRUPT (1 << 10) +#define I915_DISPLAY_PIPE_C_EVENT_INTERRUPT (1 << 9) +#define I915_OVERLAY_PLANE_FLIP_PENDING_INTERRUPT (1 << 9) +#define I915_DISPLAY_PIPE_C_DPBM_INTERRUPT (1 << 8) +#define I915_DISPLAY_PLANE_C_FLIP_PENDING_INTERRUPT (1 << 8) +#define I915_DISPLAY_PIPE_A_VBLANK_INTERRUPT (1 << 7) +#define I915_DISPLAY_PIPE_A_EVENT_INTERRUPT (1 << 6) +#define I915_DISPLAY_PIPE_B_VBLANK_INTERRUPT (1 << 5) +#define I915_DISPLAY_PIPE_B_EVENT_INTERRUPT (1 << 4) +#define I915_DISPLAY_PIPE_A_DPBM_INTERRUPT (1 << 3) +#define I915_DISPLAY_PIPE_B_DPBM_INTERRUPT (1 << 2) +#define I915_DEBUG_INTERRUPT (1 << 2) +#define I915_WINVALID_INTERRUPT (1 << 1) +#define I915_USER_INTERRUPT (1 << 1) +#define I915_ASLE_INTERRUPT (1 << 0) +#define I915_BSD_USER_INTERRUPT (1 << 25) + +#define GEN8_MASTER_IRQ _MMIO(0x44200) +#define GEN8_MASTER_IRQ_CONTROL (1 << 31) +#define GEN8_PCU_IRQ (1 << 30) +#define GEN8_DE_PCH_IRQ (1 << 23) +#define GEN8_DE_MISC_IRQ (1 << 22) +#define GEN8_DE_PORT_IRQ (1 << 20) +#define GEN8_DE_PIPE_C_IRQ (1 << 18) +#define GEN8_DE_PIPE_B_IRQ (1 << 17) +#define GEN8_DE_PIPE_A_IRQ (1 << 16) +#define GEN8_DE_PIPE_IRQ(pipe) (1 << (16 + (pipe))) +#define GEN8_GT_VECS_IRQ (1 << 6) +#define GEN8_GT_GUC_IRQ (1 << 5) +#define GEN8_GT_PM_IRQ (1 << 4) +#define GEN8_GT_VCS1_IRQ (1 << 3) /* NB: VCS2 in bspec! */ +#define GEN8_GT_VCS0_IRQ (1 << 2) /* NB: VCS1 in bpsec! */ +#define GEN8_GT_BCS_IRQ (1 << 1) +#define GEN8_GT_RCS_IRQ (1 << 0) + +#define GEN11_GU_MISC_ISR _MMIO(0x444f0) +#define GEN11_GU_MISC_IMR _MMIO(0x444f4) +#define GEN11_GU_MISC_IIR _MMIO(0x444f8) +#define GEN11_GU_MISC_IER _MMIO(0x444fc) +#define GEN11_GU_MISC_GSE (1 << 27) + +#define GEN11_GU_MISC_IRQ_REGS I915_IRQ_REGS(GEN11_GU_MISC_IMR, \ + GEN11_GU_MISC_IER, \ + GEN11_GU_MISC_IIR) + +#define GEN11_GFX_MSTR_IRQ _MMIO(0x190010) +#define GEN11_MASTER_IRQ (1 << 31) +#define GEN11_PCU_IRQ (1 << 30) +#define GEN11_GU_MISC_IRQ (1 << 29) +#define GEN11_DISPLAY_IRQ (1 << 16) +#define GEN11_GT_DW_IRQ(x) (1 << (x)) +#define GEN11_GT_DW1_IRQ (1 << 1) +#define GEN11_GT_DW0_IRQ (1 << 0) + +#define SCPD0 _MMIO(0x209c) /* 915+ only */ +#define SCPD_FBC_IGNORE_3D (1 << 6) +#define CSTATE_RENDER_CLOCK_GATE_DISABLE (1 << 5) + +#define VLV_IIR_RW _MMIO(VLV_DISPLAY_BASE + 0x2084) +#define VLV_IER _MMIO(VLV_DISPLAY_BASE + 0x20a0) +#define VLV_IIR _MMIO(VLV_DISPLAY_BASE + 0x20a4) +#define VLV_IMR _MMIO(VLV_DISPLAY_BASE + 0x20a8) +#define VLV_ISR _MMIO(VLV_DISPLAY_BASE + 0x20ac) +#define VLV_PCBR _MMIO(VLV_DISPLAY_BASE + 0x2120) +#define VLV_PCBR_ADDR_SHIFT 12 + +#endif diff --git a/include/drm/intel/intel_gmd_misc_regs.h b/include/drm/intel/intel_gmd_misc_regs.h new file mode 100644 index 000000000000..763d7711f21c --- /dev/null +++ b/include/drm/intel/intel_gmd_misc_regs.h @@ -0,0 +1,21 @@ +/* SPDX-License-Identifier: MIT */ +/* Copyright © 2026 Intel Corporation */ + +#ifndef _INTEL_GMD_MISC_REGS_H_ +#define _INTEL_GMD_MISC_REGS_H_ + +#define DISP_ARB_CTL _MMIO(0x45000) +#define DISP_FBC_MEMORY_WAKE REG_BIT(31) +#define DISP_TILE_SURFACE_SWIZZLING REG_BIT(13) +#define DISP_FBC_WM_DIS REG_BIT(15) + +#define INSTPM _MMIO(0x20c0) +#define INSTPM_SELF_EN (1 << 12) /* 915GM only */ +#define INSTPM_AGPBUSY_INT_EN (1 << 11) /* gen3: when disabled, pending interrupts + will not assert AGPBUSY# and will only + be delivered when out of C3. */ +#define INSTPM_FORCE_ORDERING (1 << 7) /* GEN6+ */ +#define INSTPM_TLB_INVALIDATE (1 << 9) +#define INSTPM_SYNC_FLUSH (1 << 5) + +#endif diff --git a/include/drm/intel/intel_pcode_regs.h b/include/drm/intel/intel_pcode_regs.h new file mode 100644 index 000000000000..db989ee7c488 --- /dev/null +++ b/include/drm/intel/intel_pcode_regs.h @@ -0,0 +1,108 @@ +/* SPDX-License-Identifier: MIT */ +/* Copyright © 2026 Intel Corporation */ + +#ifndef _INTEL_PCODE_REGS_H_ +#define _INTEL_PCODE_REGS_H_ + +#define GEN6_PCODE_MAILBOX _MMIO(0x138124) +#define GEN6_PCODE_READY (1 << 31) +#define GEN6_PCODE_MB_PARAM2 REG_GENMASK(23, 16) +#define GEN6_PCODE_MB_PARAM1 REG_GENMASK(15, 8) +#define GEN6_PCODE_MB_COMMAND REG_GENMASK(7, 0) +#define GEN6_PCODE_ERROR_MASK 0xFF +#define GEN6_PCODE_SUCCESS 0x0 +#define GEN6_PCODE_ILLEGAL_CMD 0x1 +#define GEN6_PCODE_MIN_FREQ_TABLE_GT_RATIO_OUT_OF_RANGE 0x2 +#define GEN6_PCODE_TIMEOUT 0x3 +#define GEN6_PCODE_UNIMPLEMENTED_CMD 0xFF +#define GEN7_PCODE_TIMEOUT 0x2 +#define GEN7_PCODE_ILLEGAL_DATA 0x3 +#define GEN11_PCODE_ILLEGAL_SUBCOMMAND 0x4 +#define GEN11_PCODE_LOCKED 0x6 +#define GEN11_PCODE_REJECTED 0x11 +#define GEN7_PCODE_MIN_FREQ_TABLE_GT_RATIO_OUT_OF_RANGE 0x10 +#define GEN6_PCODE_WRITE_RC6VIDS 0x4 +#define GEN6_PCODE_READ_RC6VIDS 0x5 +#define GEN6_ENCODE_RC6_VID(mv) (((mv) - 245) / 5) +#define GEN6_DECODE_RC6_VID(vids) (((vids) * 5) + 245) +#define BDW_PCODE_DISPLAY_FREQ_CHANGE_REQ 0x18 +#define GEN9_PCODE_READ_MEM_LATENCY 0x6 +#define GEN9_MEM_LATENCY_LEVEL_3_7_MASK REG_GENMASK(31, 24) +#define GEN9_MEM_LATENCY_LEVEL_2_6_MASK REG_GENMASK(23, 16) +#define GEN9_MEM_LATENCY_LEVEL_1_5_MASK REG_GENMASK(15, 8) +#define GEN9_MEM_LATENCY_LEVEL_0_4_MASK REG_GENMASK(7, 0) +#define SKL_PCODE_LOAD_HDCP_KEYS 0x5 +#define SKL_PCODE_CDCLK_CONTROL 0x7 +#define SKL_CDCLK_PREPARE_FOR_CHANGE 0x3 +#define SKL_CDCLK_READY_FOR_CHANGE 0x1 +#define GEN6_PCODE_WRITE_MIN_FREQ_TABLE 0x8 +#define GEN6_PCODE_READ_MIN_FREQ_TABLE 0x9 +#define GEN6_READ_OC_PARAMS 0xc +#define ICL_PCODE_MEM_SUBSYSYSTEM_INFO 0xd +#define ICL_PCODE_MEM_SS_READ_GLOBAL_INFO (0x0 << 8) +#define ICL_PCODE_MEM_SS_READ_QGV_POINT_INFO(point) (((point) << 16) | (0x1 << 8)) +#define ADL_PCODE_MEM_SS_READ_PSF_GV_INFO ((0) | (0x2 << 8)) +#define DISPLAY_TO_PCODE_CDCLK_MAX 0x28D +#define DISPLAY_TO_PCODE_VOLTAGE_MASK REG_GENMASK(1, 0) +#define DISPLAY_TO_PCODE_VOLTAGE_MAX DISPLAY_TO_PCODE_VOLTAGE_MASK +#define DISPLAY_TO_PCODE_CDCLK_VALID REG_BIT(27) +#define DISPLAY_TO_PCODE_PIPE_COUNT_VALID REG_BIT(31) +#define DISPLAY_TO_PCODE_CDCLK_MASK REG_GENMASK(25, 16) +#define DISPLAY_TO_PCODE_PIPE_COUNT_MASK REG_GENMASK(30, 28) +#define DISPLAY_TO_PCODE_CDCLK(x) REG_FIELD_PREP(DISPLAY_TO_PCODE_CDCLK_MASK, (x)) +#define DISPLAY_TO_PCODE_PIPE_COUNT(x) REG_FIELD_PREP(DISPLAY_TO_PCODE_PIPE_COUNT_MASK, (x)) +#define DISPLAY_TO_PCODE_VOLTAGE(x) REG_FIELD_PREP(DISPLAY_TO_PCODE_VOLTAGE_MASK, (x)) +#define DISPLAY_TO_PCODE_UPDATE_MASK(cdclk, num_pipes, voltage_level) \ + ((DISPLAY_TO_PCODE_CDCLK(cdclk)) | \ + (DISPLAY_TO_PCODE_PIPE_COUNT(num_pipes)) | \ + (DISPLAY_TO_PCODE_VOLTAGE(voltage_level))) +#define ICL_PCODE_SAGV_DE_MEM_SS_CONFIG 0xe +#define ICL_PCODE_REP_QGV_MASK REG_GENMASK(1, 0) +#define ICL_PCODE_REP_QGV_SAFE REG_FIELD_PREP(ICL_PCODE_REP_QGV_MASK, 0) +#define ICL_PCODE_REP_QGV_POLL REG_FIELD_PREP(ICL_PCODE_REP_QGV_MASK, 1) +#define ICL_PCODE_REP_QGV_REJECTED REG_FIELD_PREP(ICL_PCODE_REP_QGV_MASK, 2) +#define ADLS_PCODE_REP_PSF_MASK REG_GENMASK(3, 2) +#define ADLS_PCODE_REP_PSF_SAFE REG_FIELD_PREP(ADLS_PCODE_REP_PSF_MASK, 0) +#define ADLS_PCODE_REP_PSF_POLL REG_FIELD_PREP(ADLS_PCODE_REP_PSF_MASK, 1) +#define ADLS_PCODE_REP_PSF_REJECTED REG_FIELD_PREP(ADLS_PCODE_REP_PSF_MASK, 2) +#define ICL_PCODE_REQ_QGV_PT_MASK REG_GENMASK(7, 0) +#define ICL_PCODE_REQ_QGV_PT(x) REG_FIELD_PREP(ICL_PCODE_REQ_QGV_PT_MASK, (x)) +#define ADLS_PCODE_REQ_PSF_PT_MASK REG_GENMASK(10, 8) +#define ADLS_PCODE_REQ_PSF_PT(x) REG_FIELD_PREP(ADLS_PCODE_REQ_PSF_PT_MASK, (x)) +#define GEN6_PCODE_READ_D_COMP 0x10 +#define GEN6_PCODE_WRITE_D_COMP 0x11 +#define ICL_PCODE_EXIT_TCCOLD 0x12 +#define HSW_PCODE_DE_WRITE_FREQ_REQ 0x17 +#define DISPLAY_IPS_CONTROL 0x19 +#define TGL_PCODE_TCCOLD 0x26 +#define TGL_PCODE_EXIT_TCCOLD_DATA_L_EXIT_FAILED REG_BIT(0) +#define TGL_PCODE_EXIT_TCCOLD_DATA_L_BLOCK_REQ 0 +#define TGL_PCODE_EXIT_TCCOLD_DATA_L_UNBLOCK_REQ REG_BIT(0) +/* See also IPS_CTL */ +#define IPS_PCODE_CONTROL (1 << 30) +#define HSW_PCODE_DYNAMIC_DUTY_CYCLE_CONTROL 0x1A +#define GEN9_PCODE_SAGV_CONTROL 0x21 +#define GEN9_SAGV_DISABLE 0x0 +#define GEN9_SAGV_IS_DISABLED 0x1 +#define GEN9_SAGV_ENABLE 0x3 +#define DG1_PCODE_STATUS 0x7E +#define DG1_UNCORE_GET_INIT_STATUS 0x0 +#define DG1_UNCORE_INIT_STATUS_COMPLETE 0x1 +#define PCODE_POWER_SETUP 0x7C +#define POWER_SETUP_SUBCOMMAND_READ_I1 0x4 +#define POWER_SETUP_SUBCOMMAND_WRITE_I1 0x5 +#define POWER_SETUP_I1_WATTS REG_BIT(31) +#define POWER_SETUP_I1_SHIFT 6 /* 10.6 fixed point format */ +#define POWER_SETUP_I1_DATA_MASK REG_GENMASK(15, 0) +#define POWER_SETUP_SUBCOMMAND_G8_ENABLE 0x6 +#define GEN12_PCODE_READ_SAGV_BLOCK_TIME_US 0x23 +#define XEHP_PCODE_FREQUENCY_CONFIG 0x6e /* pvc */ +/* XEHP_PCODE_FREQUENCY_CONFIG sub-commands (param1) */ +#define PCODE_MBOX_FC_SC_READ_FUSED_P0 0x0 +#define PCODE_MBOX_FC_SC_READ_FUSED_PN 0x1 +/* PCODE_MBOX_DOMAIN_* - mailbox domain IDs */ +/* XEHP_PCODE_FREQUENCY_CONFIG param2 */ +#define PCODE_MBOX_DOMAIN_NONE 0x0 +#define PCODE_MBOX_DOMAIN_MEDIAFF 0x3 + +#endif diff --git a/include/drm/intel/pick.h b/include/drm/intel/pick.h new file mode 100644 index 000000000000..d976fab8f270 --- /dev/null +++ b/include/drm/intel/pick.h @@ -0,0 +1,51 @@ +/* SPDX-License-Identifier: MIT */ +/* Copyright © 2026 Intel Corporation */ + +#ifndef _PICK_H_ +#define _PICK_H_ + +/* + * Given the first two numbers __a and __b of arbitrarily many evenly spaced + * numbers, pick the 0-based __index'th value. + * + * Always prefer this over _PICK() if the numbers are evenly spaced. + */ +#define _PICK_EVEN(__index, __a, __b) ((__a) + (__index) * ((__b) - (__a))) + +/* + * Like _PICK_EVEN(), but supports 2 ranges of evenly spaced address offsets. + * @__c_index corresponds to the index in which the second range starts to be + * used. Using math interval notation, the first range is used for indexes [ 0, + * @__c_index), while the second range is used for [ @__c_index, ... ). Example: + * + * #define _FOO_A 0xf000 + * #define _FOO_B 0xf004 + * #define _FOO_C 0xf008 + * #define _SUPER_FOO_A 0xa000 + * #define _SUPER_FOO_B 0xa100 + * #define FOO(x) _MMIO(_PICK_EVEN_2RANGES(x, 3, \ + * _FOO_A, _FOO_B, \ + * _SUPER_FOO_A, _SUPER_FOO_B)) + * + * This expands to: + * 0: 0xf000, + * 1: 0xf004, + * 2: 0xf008, + * 3: 0xa000, + * 4: 0xa100, + * 5: 0xa200, + * ... + */ +#define _PICK_EVEN_2RANGES(__index, __c_index, __a, __b, __c, __d) \ + (BUILD_BUG_ON_ZERO(!__is_constexpr(__c_index)) + \ + ((__index) < (__c_index) ? _PICK_EVEN(__index, __a, __b) : \ + _PICK_EVEN((__index) - (__c_index), __c, __d))) + +/* + * Given the arbitrary numbers in varargs, pick the 0-based __index'th number. + * + * Always prefer _PICK_EVEN() over this if the numbers are evenly spaced. + */ +#define _PICK(__index, ...) (((const u32 []){ __VA_ARGS__ })[__index]) + +#endif diff --git a/include/drm/intel/reg_bits.h b/include/drm/intel/reg_bits.h new file mode 100644 index 000000000000..2a9066e1d808 --- /dev/null +++ b/include/drm/intel/reg_bits.h @@ -0,0 +1,139 @@ +/* SPDX-License-Identifier: MIT */ +/* Copyright © 2026 Intel Corporation */ + +#ifndef _REG_BITS_H_ +#define _REG_BITS_H_ + +#include <linux/bitfield.h> +#include <linux/bits.h> + +/* + * Wrappers over the generic fixed width BIT_U*() and GENMASK_U*() + * implementations, for compatibility reasons with previous implementation. + */ +#define REG_GENMASK(high, low) GENMASK_U32(high, low) +#define REG_GENMASK64(high, low) GENMASK_U64(high, low) +#define REG_GENMASK16(high, low) GENMASK_U16(high, low) +#define REG_GENMASK8(high, low) GENMASK_U8(high, low) + +#define REG_BIT(n) BIT_U32(n) +#define REG_BIT64(n) BIT_U64(n) +#define REG_BIT16(n) BIT_U16(n) +#define REG_BIT8(n) BIT_U8(n) + +/* + * Local integer constant expression version of is_power_of_2(). + */ +#define IS_POWER_OF_2(__x) ((__x) && (((__x) & ((__x) - 1)) == 0)) + +/** + * REG_FIELD_PREP8() - Prepare a u8 bitfield value + * @__mask: shifted mask defining the field's length and position + * @__val: value to put in the field + * + * Local copy of FIELD_PREP() to generate an integer constant expression, force + * u8 and for consistency with REG_FIELD_GET8(), REG_BIT8() and REG_GENMASK8(). + * + * @return: @__val masked and shifted into the field defined by @__mask. + */ +#define REG_FIELD_PREP8(__mask, __val) \ + ((u8)((((typeof(__mask))(__val) << __bf_shf(__mask)) & (__mask)) + \ + BUILD_BUG_ON_ZERO(!__is_constexpr(__mask)) + \ + BUILD_BUG_ON_ZERO((__mask) == 0 || (__mask) > U8_MAX) + \ + BUILD_BUG_ON_ZERO(!IS_POWER_OF_2((__mask) + (1ULL << __bf_shf(__mask)))) + \ + BUILD_BUG_ON_ZERO(__builtin_choose_expr(__is_constexpr(__val), (~((__mask) >> __bf_shf(__mask)) & (__val)), 0)))) + +/** + * REG_FIELD_PREP16() - Prepare a u16 bitfield value + * @__mask: shifted mask defining the field's length and position + * @__val: value to put in the field + * + * Local copy of FIELD_PREP16() to generate an integer constant + * expression, force u8 and for consistency with + * REG_FIELD_GET16(), REG_BIT16() and REG_GENMASK16(). + * + * @return: @__val masked and shifted into the field defined by @__mask. + */ +#define REG_FIELD_PREP16(__mask, __val) \ + ((u16)((((typeof(__mask))(__val) << __bf_shf(__mask)) & (__mask)) + \ + BUILD_BUG_ON_ZERO(!__is_constexpr(__mask)) + \ + BUILD_BUG_ON_ZERO((__mask) == 0 || (__mask) > U16_MAX) + \ + BUILD_BUG_ON_ZERO(!IS_POWER_OF_2((__mask) + (1ULL << __bf_shf(__mask)))) + \ + BUILD_BUG_ON_ZERO(__builtin_choose_expr(__is_constexpr(__val), (~((__mask) >> __bf_shf(__mask)) & (__val)), 0)))) + +/** + * REG_FIELD_PREP() - Prepare a u32 bitfield value + * @__mask: shifted mask defining the field's length and position + * @__val: value to put in the field + * + * Local copy of FIELD_PREP() to generate an integer constant expression, force + * u32 and for consistency with REG_FIELD_GET(), REG_BIT() and REG_GENMASK(). + * + * @return: @__val masked and shifted into the field defined by @__mask. + */ +#define REG_FIELD_PREP(__mask, __val) \ + ((u32)((((typeof(__mask))(__val) << __bf_shf(__mask)) & (__mask)) + \ + BUILD_BUG_ON_ZERO(!__is_constexpr(__mask)) + \ + BUILD_BUG_ON_ZERO((__mask) == 0 || (__mask) > U32_MAX) + \ + BUILD_BUG_ON_ZERO(!IS_POWER_OF_2((__mask) + (1ULL << __bf_shf(__mask)))) + \ + BUILD_BUG_ON_ZERO(__builtin_choose_expr(__is_constexpr(__val), (~((__mask) >> __bf_shf(__mask)) & (__val)), 0)))) + +/** + * REG_FIELD_GET8() - Extract a u8 bitfield value + * @__mask: shifted mask defining the field's length and position + * @__val: value to extract the bitfield value from + * + * Local wrapper for FIELD_GET() to force u8 and for consistency with + * REG_FIELD_PREP(), REG_BIT() and REG_GENMASK(). + * + * @return: Masked and shifted value of the field defined by @__mask in @__val. + */ +#define REG_FIELD_GET8(__mask, __val) ((u8)FIELD_GET(__mask, __val)) + +/** + * REG_FIELD_GET() - Extract a u32 bitfield value + * @__mask: shifted mask defining the field's length and position + * @__val: value to extract the bitfield value from + * + * Local wrapper for FIELD_GET() to force u32 and for consistency with + * REG_FIELD_PREP(), REG_BIT() and REG_GENMASK(). + * + * @return: Masked and shifted value of the field defined by @__mask in @__val. + */ +#define REG_FIELD_GET(__mask, __val) ((u32)FIELD_GET(__mask, __val)) + +/** + * REG_FIELD_GET64() - Extract a u64 bitfield value + * @__mask: shifted mask defining the field's length and position + * @__val: value to extract the bitfield value from + * + * Local wrapper for FIELD_GET() to force u64 and for consistency with + * REG_GENMASK64(). + * + * @return: Masked and shifted value of the field defined by @__mask in @__val. + */ +#define REG_FIELD_GET64(__mask, __val) ((u64)FIELD_GET(__mask, __val)) + +/** + * REG_FIELD_MAX() - produce the maximum value representable by a field + * @__mask: shifted mask defining the field's length and position + * + * Local wrapper for FIELD_MAX() to return the maximum bit value that can + * be held in the field specified by @_mask, cast to u32 for consistency + * with other macros. + */ +#define REG_FIELD_MAX(__mask) ((u32)FIELD_MAX(__mask)) + +#define REG_MASKED_FIELD(mask, value) \ + (BUILD_BUG_ON_ZERO(__builtin_choose_expr(__builtin_constant_p(mask), (mask) & 0xffff0000, 0)) + \ + BUILD_BUG_ON_ZERO(__builtin_choose_expr(__builtin_constant_p(value), (value) & 0xffff0000, 0)) + \ + BUILD_BUG_ON_ZERO(__builtin_choose_expr(__builtin_constant_p(mask) && __builtin_constant_p(value), (value) & ~(mask), 0)) + \ + ((mask) << 16 | (value))) + +#define REG_MASKED_FIELD_ENABLE(a) \ + (__builtin_choose_expr(__builtin_constant_p(a), REG_MASKED_FIELD((a), (a)), ({ typeof(a) _a = (a); REG_MASKED_FIELD(_a, _a); }))) + +#define REG_MASKED_FIELD_DISABLE(a) \ + (REG_MASKED_FIELD((a), 0)) + +#endif diff --git a/include/drm/intel/xe_sriov_vfio.h b/include/drm/intel/xe_sriov_vfio.h index e9814e8149fd..27c224a70e6f 100644 --- a/include/drm/intel/xe_sriov_vfio.h +++ b/include/drm/intel/xe_sriov_vfio.h @@ -28,6 +28,17 @@ struct xe_device *xe_sriov_vfio_get_pf(struct pci_dev *pdev); bool xe_sriov_vfio_migration_supported(struct xe_device *xe); /** + * xe_sriov_vfio_flr_prepare() - Notify PF that VF FLR prepare has started. + * @xe: the PF &xe_device obtained by calling xe_sriov_vfio_get_pf() + * @vfid: the VF identifier (can't be 0) + * + * This function marks VF FLR as pending before PF receives GuC FLR event. + * + * Return: 0 on success or a negative error code on failure. + */ +int xe_sriov_vfio_flr_prepare(struct xe_device *xe, unsigned int vfid); + +/** * xe_sriov_vfio_wait_flr_done() - Wait for VF FLR completion. * @xe: the PF &xe_device obtained by calling xe_sriov_vfio_get_pf() * @vfid: the VF identifier (can't be 0) diff --git a/include/hyperv/hvgdk_mini.h b/include/hyperv/hvgdk_mini.h index 056ef7b6b360..1823a290a7b7 100644 --- a/include/hyperv/hvgdk_mini.h +++ b/include/hyperv/hvgdk_mini.h @@ -477,7 +477,6 @@ union hv_vp_assist_msr_contents { /* HV_REGISTER_VP_ASSIST_PAGE */ #define HVCALL_NOTIFY_PARTITION_EVENT 0x0087 #define HVCALL_ENTER_SLEEP_STATE 0x0084 #define HVCALL_NOTIFY_PORT_RING_EMPTY 0x008b -#define HVCALL_SCRUB_PARTITION 0x008d #define HVCALL_REGISTER_INTERCEPT_RESULT 0x0091 #define HVCALL_ASSERT_VIRTUAL_INTERRUPT 0x0094 #define HVCALL_CREATE_PORT 0x0095 @@ -1121,6 +1120,8 @@ enum hv_register_name { HV_X64_REGISTER_MSR_MTRR_FIX4KF8000 = 0x0008007A, HV_X64_REGISTER_REG_PAGE = 0x0009001C, +#elif defined(CONFIG_ARM64) + HV_ARM64_REGISTER_SINT_RESERVED_INTERRUPT_ID = 0x00070001, #endif }; diff --git a/include/linux/auxvec.h b/include/linux/auxvec.h index 407f7005e6d6..8bcb9b726262 100644 --- a/include/linux/auxvec.h +++ b/include/linux/auxvec.h @@ -4,6 +4,6 @@ #include <uapi/linux/auxvec.h> -#define AT_VECTOR_SIZE_BASE 22 /* NEW_AUX_ENT entries in auxiliary table */ +#define AT_VECTOR_SIZE_BASE 24 /* NEW_AUX_ENT entries in auxiliary table */ /* number of "#define AT_.*" above, minus {AT_NULL, AT_IGNORE, AT_NOTELF} */ #endif /* _LINUX_AUXVEC_H */ diff --git a/include/linux/build_bug.h b/include/linux/build_bug.h index 2cfbb4c65c78..d3dc5dc5f916 100644 --- a/include/linux/build_bug.h +++ b/include/linux/build_bug.h @@ -32,7 +32,8 @@ /** * BUILD_BUG_ON_MSG - break compile if a condition is true & emit supplied * error message. - * @condition: the condition which the compiler should know is false. + * @cond: the condition which the compiler should know is false. + * @msg: build-time error message * * See BUILD_BUG_ON for description. */ @@ -60,6 +61,7 @@ /** * static_assert - check integer constant expression at build time + * @expr: expression to be checked * * static_assert() is a wrapper for the C11 _Static_assert, with a * little macro magic to make the message optional (defaulting to the diff --git a/include/linux/console_struct.h b/include/linux/console_struct.h index 13b35637bd5a..d5ca855116df 100644 --- a/include/linux/console_struct.h +++ b/include/linux/console_struct.h @@ -160,6 +160,7 @@ struct vc_data { struct uni_pagedict **uni_pagedict_loc; /* [!] Location of uni_pagedict variable for this console */ u32 **vc_uni_lines; /* unicode screen content */ u16 *vc_saved_screen; + u32 **vc_saved_uni_lines; unsigned int vc_saved_cols; unsigned int vc_saved_rows; /* additional information is in vt_kern.h */ diff --git a/include/linux/damon.h b/include/linux/damon.h index a4fea23da857..be3d198043ff 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -810,6 +810,12 @@ struct damon_ctx { struct damos_walk_control *walk_control; struct mutex walk_control_lock; + /* + * indicate if this may be corrupted. Currentonly this is set only for + * damon_commit_ctx() failure. + */ + bool maybe_corrupted; + /* Working thread of the given DAMON context */ struct task_struct *kdamond; /* Protects @kdamond field access */ diff --git a/include/linux/device.h b/include/linux/device.h index 0be95294b6e6..e65d564f01cd 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -483,6 +483,8 @@ struct device_physical_location { * on. This shrinks the "Board Support Packages" (BSPs) and * minimizes board-specific #ifdefs in drivers. * @driver_data: Private pointer for driver specific info. + * @driver_override: Driver name to force a match. Do not touch directly; use + * device_set_driver_override() instead. * @links: Links to suppliers and consumers of this device. * @power: For device power management. * See Documentation/driver-api/pm/devices.rst for details. @@ -576,6 +578,10 @@ struct device { core doesn't touch it */ void *driver_data; /* Driver data, set and get with dev_set_drvdata/dev_get_drvdata */ + struct { + const char *name; + spinlock_t lock; + } driver_override; struct mutex mutex; /* mutex to synchronize calls to * its driver. */ @@ -701,6 +707,54 @@ struct device_link { #define kobj_to_dev(__kobj) container_of_const(__kobj, struct device, kobj) +int __device_set_driver_override(struct device *dev, const char *s, size_t len); + +/** + * device_set_driver_override() - Helper to set or clear driver override. + * @dev: Device to change + * @s: NUL-terminated string, new driver name to force a match, pass empty + * string to clear it ("" or "\n", where the latter is only for sysfs + * interface). + * + * Helper to set or clear driver override of a device. + * + * Returns: 0 on success or a negative error code on failure. + */ +static inline int device_set_driver_override(struct device *dev, const char *s) +{ + return __device_set_driver_override(dev, s, s ? strlen(s) : 0); +} + +/** + * device_has_driver_override() - Check if a driver override has been set. + * @dev: device to check + * + * Returns true if a driver override has been set for this device. + */ +static inline bool device_has_driver_override(struct device *dev) +{ + guard(spinlock)(&dev->driver_override.lock); + return !!dev->driver_override.name; +} + +/** + * device_match_driver_override() - Match a driver against the device's driver_override. + * @dev: device to check + * @drv: driver to match against + * + * Returns > 0 if a driver override is set and matches the given driver, 0 if a + * driver override is set but does not match, or < 0 if a driver override is not + * set at all. + */ +static inline int device_match_driver_override(struct device *dev, + const struct device_driver *drv) +{ + guard(spinlock)(&dev->driver_override.lock); + if (dev->driver_override.name) + return !strcmp(dev->driver_override.name, drv->name); + return -1; +} + /** * device_iommu_mapped - Returns true when the device DMA is translated * by an IOMMU diff --git a/include/linux/device/bus.h b/include/linux/device/bus.h index 63de5f053c33..c1b463cd6464 100644 --- a/include/linux/device/bus.h +++ b/include/linux/device/bus.h @@ -65,6 +65,9 @@ struct fwnode_handle; * this bus. * @pm: Power management operations of this bus, callback the specific * device driver's pm-ops. + * @driver_override: Set to true if this bus supports the driver_override + * mechanism, which allows userspace to force a specific + * driver to bind to a device via a sysfs attribute. * @need_parent_lock: When probing or removing a device on this bus, the * device core should lock the device's parent. * @@ -106,6 +109,7 @@ struct bus_type { const struct dev_pm_ops *pm; + bool driver_override; bool need_parent_lock; }; diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 29973baa0581..99ef042ecdb4 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -80,11 +80,18 @@ #define DMA_ATTR_MMIO (1UL << 10) /* - * DMA_ATTR_CPU_CACHE_CLEAN: Indicates the CPU will not dirty any cacheline - * overlapping this buffer while it is mapped for DMA. All mappings sharing - * a cacheline must have this attribute for this to be considered safe. + * DMA_ATTR_DEBUGGING_IGNORE_CACHELINES: Indicates the CPU cache line can be + * overlapped. All mappings sharing a cacheline must have this attribute for + * this to be considered safe. */ -#define DMA_ATTR_CPU_CACHE_CLEAN (1UL << 11) +#define DMA_ATTR_DEBUGGING_IGNORE_CACHELINES (1UL << 11) + +/* + * DMA_ATTR_REQUIRE_COHERENT: Indicates that DMA coherency is required. + * All mappings that carry this attribute can't work with SWIOTLB and cache + * flushing. + */ +#define DMA_ATTR_REQUIRE_COHERENT (1UL << 12) /* * A dma_addr_t can hold any valid DMA or bus address for the platform. It can @@ -248,8 +255,8 @@ static inline void *dma_alloc_attrs(struct device *dev, size_t size, { return NULL; } -static void dma_free_attrs(struct device *dev, size_t size, void *cpu_addr, - dma_addr_t dma_handle, unsigned long attrs) +static inline void dma_free_attrs(struct device *dev, size_t size, + void *cpu_addr, dma_addr_t dma_handle, unsigned long attrs) { } static inline void *dmam_alloc_attrs(struct device *dev, size_t size, diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h index 9a1eacf35d37..df8f88f63a70 100644 --- a/include/linux/etherdevice.h +++ b/include/linux/etherdevice.h @@ -42,7 +42,8 @@ extern const struct header_ops eth_header_ops; int eth_header(struct sk_buff *skb, struct net_device *dev, unsigned short type, const void *daddr, const void *saddr, unsigned len); -int eth_header_parse(const struct sk_buff *skb, unsigned char *haddr); +int eth_header_parse(const struct sk_buff *skb, const struct net_device *dev, + unsigned char *haddr); int eth_header_cache(const struct neighbour *neigh, struct hh_cache *hh, __be16 type); void eth_header_cache_update(struct hh_cache *hh, const struct net_device *dev, diff --git a/include/linux/firmware/intel/stratix10-svc-client.h b/include/linux/firmware/intel/stratix10-svc-client.h index d290060f4c73..91013161e9db 100644 --- a/include/linux/firmware/intel/stratix10-svc-client.h +++ b/include/linux/firmware/intel/stratix10-svc-client.h @@ -68,12 +68,12 @@ * timeout value used in Stratix10 FPGA manager driver. * timeout value used in RSU driver */ -#define SVC_RECONFIG_REQUEST_TIMEOUT_MS 300 -#define SVC_RECONFIG_BUFFER_TIMEOUT_MS 720 -#define SVC_RSU_REQUEST_TIMEOUT_MS 300 +#define SVC_RECONFIG_REQUEST_TIMEOUT_MS 5000 +#define SVC_RECONFIG_BUFFER_TIMEOUT_MS 5000 +#define SVC_RSU_REQUEST_TIMEOUT_MS 2000 #define SVC_FCS_REQUEST_TIMEOUT_MS 2000 #define SVC_COMPLETED_TIMEOUT_MS 30000 -#define SVC_HWMON_REQUEST_TIMEOUT_MS 300 +#define SVC_HWMON_REQUEST_TIMEOUT_MS 2000 struct stratix10_svc_chan; diff --git a/include/linux/fs/super_types.h b/include/linux/fs/super_types.h index fa7638b81246..383050e7fdf5 100644 --- a/include/linux/fs/super_types.h +++ b/include/linux/fs/super_types.h @@ -338,5 +338,6 @@ struct super_block { #define SB_I_NOUMASK 0x00001000 /* VFS does not apply umask */ #define SB_I_NOIDMAP 0x00002000 /* No idmapped mounts on this superblock */ #define SB_I_ALLOW_HSM 0x00004000 /* Allow HSM events on this superblock */ +#define SB_I_NO_DATA_INTEGRITY 0x00008000 /* fs cannot guarantee data persistence on sync */ #endif /* _LINUX_FS_SUPER_TYPES_H */ diff --git a/include/linux/hid.h b/include/linux/hid.h index 2990b9f94cb5..31324609af4d 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -682,6 +682,7 @@ struct hid_device { __s32 battery_charge_status; enum hid_battery_status battery_status; bool battery_avoid_query; + bool battery_present; ktime_t battery_ratelimit_time; #endif diff --git a/include/linux/if_ether.h b/include/linux/if_ether.h index 61b7335aa037..ca9afa824aa4 100644 --- a/include/linux/if_ether.h +++ b/include/linux/if_ether.h @@ -40,7 +40,8 @@ static inline struct ethhdr *inner_eth_hdr(const struct sk_buff *skb) return (struct ethhdr *)skb_inner_mac_header(skb); } -int eth_header_parse(const struct sk_buff *skb, unsigned char *haddr); +int eth_header_parse(const struct sk_buff *skb, const struct net_device *dev, + unsigned char *haddr); extern ssize_t sysfs_format_mac(char *buf, const unsigned char *addr, int len); diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h index 7a1516011ccf..e19872e37e06 100644 --- a/include/linux/io-pgtable.h +++ b/include/linux/io-pgtable.h @@ -53,7 +53,7 @@ struct iommu_flush_ops { * tables. * @ias: Input address (iova) size, in bits. * @oas: Output address (paddr) size, in bits. - * @coherent_walk A flag to indicate whether or not page table walks made + * @coherent_walk: A flag to indicate whether or not page table walks made * by the IOMMU are coherent with the CPU caches. * @tlb: TLB management callbacks for this set of tables. * @iommu_dev: The device representing the DMA configuration for the @@ -136,6 +136,7 @@ struct io_pgtable_cfg { void (*free)(void *cookie, void *pages, size_t size); /* Low-level data specific to the table format */ + /* private: */ union { struct { u64 ttbr; @@ -203,6 +204,9 @@ struct arm_lpae_io_pgtable_walk_data { * @unmap_pages: Unmap a range of virtually contiguous pages of the same size. * @iova_to_phys: Translate iova to physical address. * @pgtable_walk: (optional) Perform a page table walk for a given iova. + * @read_and_clear_dirty: Record dirty info per IOVA. If an IOVA is dirty, + * clear its dirty state from the PTE unless the + * IOMMU_DIRTY_NO_CLEAR flag is passed in. * * These functions map directly onto the iommu_ops member functions with * the same names. @@ -231,7 +235,9 @@ struct io_pgtable_ops { * the configuration actually provided by the allocator (e.g. the * pgsize_bitmap may be restricted). * @cookie: An opaque token provided by the IOMMU driver and passed back to - * the callback routines in cfg->tlb. + * the callback routines. + * + * Returns: Pointer to the &struct io_pgtable_ops for this set of page tables. */ struct io_pgtable_ops *alloc_io_pgtable_ops(enum io_pgtable_fmt fmt, struct io_pgtable_cfg *cfg, diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h index 3e4a82a6f817..214fdbd49052 100644 --- a/include/linux/io_uring_types.h +++ b/include/linux/io_uring_types.h @@ -388,6 +388,7 @@ struct io_ring_ctx { * regularly bounce b/w CPUs. */ struct { + struct io_rings __rcu *rings_rcu; struct llist_head work_llist; struct llist_head retry_llist; unsigned long check_cq; @@ -540,6 +541,7 @@ enum { REQ_F_BL_NO_RECYCLE_BIT, REQ_F_BUFFERS_COMMIT_BIT, REQ_F_BUF_NODE_BIT, + REQ_F_BUF_MORE_BIT, REQ_F_HAS_METADATA_BIT, REQ_F_IMPORT_BUFFER_BIT, REQ_F_SQE_COPIED_BIT, @@ -625,6 +627,8 @@ enum { REQ_F_BUFFERS_COMMIT = IO_REQ_FLAG(REQ_F_BUFFERS_COMMIT_BIT), /* buf node is valid */ REQ_F_BUF_NODE = IO_REQ_FLAG(REQ_F_BUF_NODE_BIT), + /* incremental buffer consumption, more space available */ + REQ_F_BUF_MORE = IO_REQ_FLAG(REQ_F_BUF_MORE_BIT), /* request has read/write metadata assigned */ REQ_F_HAS_METADATA = IO_REQ_FLAG(REQ_F_HAS_METADATA_BIT), /* diff --git a/include/linux/iopoll.h b/include/linux/iopoll.h index bdd2e0652bc3..53edd69acb9b 100644 --- a/include/linux/iopoll.h +++ b/include/linux/iopoll.h @@ -159,7 +159,7 @@ * * This macro does not rely on timekeeping. Hence it is safe to call even when * timekeeping is suspended, at the expense of an underestimation of wall clock - * time, which is rather minimal with a non-zero delay_us. + * time, which is rather minimal with a non-zero @delay_us. * * When available, you'll probably want to use one of the specialized * macros defined below rather than this macro directly. @@ -167,9 +167,9 @@ * Returns: 0 on success and -ETIMEDOUT upon a timeout. In either * case, the last read value at @args is stored in @val. */ -#define read_poll_timeout_atomic(op, val, cond, sleep_us, timeout_us, \ - sleep_before_read, args...) \ - poll_timeout_us_atomic((val) = op(args), cond, sleep_us, timeout_us, sleep_before_read) +#define read_poll_timeout_atomic(op, val, cond, delay_us, timeout_us, \ + delay_before_read, args...) \ + poll_timeout_us_atomic((val) = op(args), cond, delay_us, timeout_us, delay_before_read) /** * readx_poll_timeout - Periodically poll an address until a condition is met or a timeout occurs diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 443053a76dcf..a7421382a916 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -333,7 +333,12 @@ struct tcp6_timewait_sock { }; #if IS_ENABLED(CONFIG_IPV6) -bool ipv6_mod_enabled(void); +extern int disable_ipv6_mod; + +static inline bool ipv6_mod_enabled(void) +{ + return disable_ipv6_mod == 0; +} static inline struct ipv6_pinfo *inet6_sk(const struct sock *__sk) { diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 34759a262b28..6b76e7a6f4c2 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1940,56 +1940,43 @@ enum kvm_stat_kind { struct kvm_stat_data { struct kvm *kvm; - const struct _kvm_stats_desc *desc; + const struct kvm_stats_desc *desc; enum kvm_stat_kind kind; }; -struct _kvm_stats_desc { - struct kvm_stats_desc desc; - char name[KVM_STATS_NAME_SIZE]; -}; - -#define STATS_DESC_COMMON(type, unit, base, exp, sz, bsz) \ - .flags = type | unit | base | \ - BUILD_BUG_ON_ZERO(type & ~KVM_STATS_TYPE_MASK) | \ - BUILD_BUG_ON_ZERO(unit & ~KVM_STATS_UNIT_MASK) | \ - BUILD_BUG_ON_ZERO(base & ~KVM_STATS_BASE_MASK), \ - .exponent = exp, \ - .size = sz, \ +#define STATS_DESC_COMMON(type, unit, base, exp, sz, bsz) \ + .flags = type | unit | base | \ + BUILD_BUG_ON_ZERO(type & ~KVM_STATS_TYPE_MASK) | \ + BUILD_BUG_ON_ZERO(unit & ~KVM_STATS_UNIT_MASK) | \ + BUILD_BUG_ON_ZERO(base & ~KVM_STATS_BASE_MASK), \ + .exponent = exp, \ + .size = sz, \ .bucket_size = bsz -#define VM_GENERIC_STATS_DESC(stat, type, unit, base, exp, sz, bsz) \ - { \ - { \ - STATS_DESC_COMMON(type, unit, base, exp, sz, bsz), \ - .offset = offsetof(struct kvm_vm_stat, generic.stat) \ - }, \ - .name = #stat, \ - } -#define VCPU_GENERIC_STATS_DESC(stat, type, unit, base, exp, sz, bsz) \ - { \ - { \ - STATS_DESC_COMMON(type, unit, base, exp, sz, bsz), \ - .offset = offsetof(struct kvm_vcpu_stat, generic.stat) \ - }, \ - .name = #stat, \ - } -#define VM_STATS_DESC(stat, type, unit, base, exp, sz, bsz) \ - { \ - { \ - STATS_DESC_COMMON(type, unit, base, exp, sz, bsz), \ - .offset = offsetof(struct kvm_vm_stat, stat) \ - }, \ - .name = #stat, \ - } -#define VCPU_STATS_DESC(stat, type, unit, base, exp, sz, bsz) \ - { \ - { \ - STATS_DESC_COMMON(type, unit, base, exp, sz, bsz), \ - .offset = offsetof(struct kvm_vcpu_stat, stat) \ - }, \ - .name = #stat, \ - } +#define VM_GENERIC_STATS_DESC(stat, type, unit, base, exp, sz, bsz) \ +{ \ + STATS_DESC_COMMON(type, unit, base, exp, sz, bsz), \ + .offset = offsetof(struct kvm_vm_stat, generic.stat), \ + .name = #stat, \ +} +#define VCPU_GENERIC_STATS_DESC(stat, type, unit, base, exp, sz, bsz) \ +{ \ + STATS_DESC_COMMON(type, unit, base, exp, sz, bsz), \ + .offset = offsetof(struct kvm_vcpu_stat, generic.stat), \ + .name = #stat, \ +} +#define VM_STATS_DESC(stat, type, unit, base, exp, sz, bsz) \ +{ \ + STATS_DESC_COMMON(type, unit, base, exp, sz, bsz), \ + .offset = offsetof(struct kvm_vm_stat, stat), \ + .name = #stat, \ +} +#define VCPU_STATS_DESC(stat, type, unit, base, exp, sz, bsz) \ +{ \ + STATS_DESC_COMMON(type, unit, base, exp, sz, bsz), \ + .offset = offsetof(struct kvm_vcpu_stat, stat), \ + .name = #stat, \ +} /* SCOPE: VM, VM_GENERIC, VCPU, VCPU_GENERIC */ #define STATS_DESC(SCOPE, stat, type, unit, base, exp, sz, bsz) \ SCOPE##_STATS_DESC(stat, type, unit, base, exp, sz, bsz) @@ -2066,7 +2053,7 @@ struct _kvm_stats_desc { STATS_DESC_IBOOLEAN(VCPU_GENERIC, blocking) ssize_t kvm_stats_read(char *id, const struct kvm_stats_header *header, - const struct _kvm_stats_desc *desc, + const struct kvm_stats_desc *desc, void *stats, size_t size_stats, char __user *user_buffer, size_t size, loff_t *offset); @@ -2111,9 +2098,9 @@ static inline void kvm_stats_log_hist_update(u64 *data, size_t size, u64 value) extern const struct kvm_stats_header kvm_vm_stats_header; -extern const struct _kvm_stats_desc kvm_vm_stats_desc[]; +extern const struct kvm_stats_desc kvm_vm_stats_desc[]; extern const struct kvm_stats_header kvm_vcpu_stats_header; -extern const struct _kvm_stats_desc kvm_vcpu_stats_desc[]; +extern const struct kvm_stats_desc kvm_vcpu_stats_desc[]; static inline int mmu_invalidate_retry(struct kvm *kvm, unsigned long mmu_seq) { diff --git a/include/linux/leafops.h b/include/linux/leafops.h index a9ff94b744f2..05673d3529e7 100644 --- a/include/linux/leafops.h +++ b/include/linux/leafops.h @@ -363,6 +363,23 @@ static inline unsigned long softleaf_to_pfn(softleaf_t entry) return swp_offset(entry) & SWP_PFN_MASK; } +static inline void softleaf_migration_sync(softleaf_t entry, + struct folio *folio) +{ + /* + * Ensure we do not race with split, which might alter tail pages into new + * folios and thus result in observing an unlocked folio. + * This matches the write barrier in __split_folio_to_order(). + */ + smp_rmb(); + + /* + * Any use of migration entries may only occur while the + * corresponding page is locked + */ + VM_WARN_ON_ONCE(!folio_test_locked(folio)); +} + /** * softleaf_to_page() - Obtains struct page for PFN encoded within leaf entry. * @entry: Leaf entry, softleaf_has_pfn(@entry) must return true. @@ -374,11 +391,8 @@ static inline struct page *softleaf_to_page(softleaf_t entry) struct page *page = pfn_to_page(softleaf_to_pfn(entry)); VM_WARN_ON_ONCE(!softleaf_has_pfn(entry)); - /* - * Any use of migration entries may only occur while the - * corresponding page is locked - */ - VM_WARN_ON_ONCE(softleaf_is_migration(entry) && !PageLocked(page)); + if (softleaf_is_migration(entry)) + softleaf_migration_sync(entry, page_folio(page)); return page; } @@ -394,12 +408,8 @@ static inline struct folio *softleaf_to_folio(softleaf_t entry) struct folio *folio = pfn_folio(softleaf_to_pfn(entry)); VM_WARN_ON_ONCE(!softleaf_has_pfn(entry)); - /* - * Any use of migration entries may only occur while the - * corresponding folio is locked. - */ - VM_WARN_ON_ONCE(softleaf_is_migration(entry) && - !folio_test_locked(folio)); + if (softleaf_is_migration(entry)) + softleaf_migration_sync(entry, folio); return folio; } diff --git a/include/linux/local_lock_internal.h b/include/linux/local_lock_internal.h index eff711bf973f..234be7f12c15 100644 --- a/include/linux/local_lock_internal.h +++ b/include/linux/local_lock_internal.h @@ -315,7 +315,7 @@ do { \ #endif /* CONFIG_PREEMPT_RT */ -#if defined(WARN_CONTEXT_ANALYSIS) +#if defined(WARN_CONTEXT_ANALYSIS) && !defined(__CHECKER__) /* * Because the compiler only knows about the base per-CPU variable, use this * helper function to make the compiler think we lock/unlock the @base variable, diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h index 0fe96f3ab3ef..65c732d440d2 100644 --- a/include/linux/mempolicy.h +++ b/include/linux/mempolicy.h @@ -55,6 +55,7 @@ struct mempolicy { nodemask_t cpuset_mems_allowed; /* relative to these nodes */ nodemask_t user_nodemask; /* nodemask passed by user */ } w; + struct rcu_head rcu; }; /* diff --git a/include/linux/mm.h b/include/linux/mm.h index 5be3d8a8f806..abb4963c1f06 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3514,26 +3514,21 @@ static inline bool ptlock_init(struct ptdesc *ptdesc) { return true; } static inline void ptlock_free(struct ptdesc *ptdesc) {} #endif /* defined(CONFIG_SPLIT_PTE_PTLOCKS) */ -static inline unsigned long ptdesc_nr_pages(const struct ptdesc *ptdesc) -{ - return compound_nr(ptdesc_page(ptdesc)); -} - static inline void __pagetable_ctor(struct ptdesc *ptdesc) { - pg_data_t *pgdat = NODE_DATA(memdesc_nid(ptdesc->pt_flags)); + struct folio *folio = ptdesc_folio(ptdesc); - __SetPageTable(ptdesc_page(ptdesc)); - mod_node_page_state(pgdat, NR_PAGETABLE, ptdesc_nr_pages(ptdesc)); + __folio_set_pgtable(folio); + lruvec_stat_add_folio(folio, NR_PAGETABLE); } static inline void pagetable_dtor(struct ptdesc *ptdesc) { - pg_data_t *pgdat = NODE_DATA(memdesc_nid(ptdesc->pt_flags)); + struct folio *folio = ptdesc_folio(ptdesc); ptlock_free(ptdesc); - __ClearPageTable(ptdesc_page(ptdesc)); - mod_node_page_state(pgdat, NR_PAGETABLE, -ptdesc_nr_pages(ptdesc)); + __folio_clear_pgtable(folio); + lruvec_stat_sub_folio(folio, NR_PAGETABLE); } static inline void pagetable_dtor_free(struct ptdesc *ptdesc) diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h index 07a2bbaf86e9..0da15adb4aac 100644 --- a/include/linux/mmu_notifier.h +++ b/include/linux/mmu_notifier.h @@ -234,15 +234,57 @@ struct mmu_notifier { }; /** - * struct mmu_interval_notifier_ops + * struct mmu_interval_notifier_finish - mmu_interval_notifier two-pass abstraction + * @link: Lockless list link for the notifiers pending pass list + * @notifier: The mmu_interval_notifier for which the finish pass is called. + * + * Allocate, typically using GFP_NOWAIT in the interval notifier's start pass. + * Note that with a large number of notifiers implementing two passes, + * allocation with GFP_NOWAIT will become increasingly likely to fail, so consider + * implementing a small pool instead of using kmalloc() allocations. + * + * If the implementation needs to pass data between the start and the finish passes, + * the recommended way is to embed struct mmu_interval_notifier_finish into a larger + * structure that also contains the data needed to be shared. Keep in mind that + * a notifier callback can be invoked in parallel, and each invocation needs its + * own struct mmu_interval_notifier_finish. + * + * If allocation fails, then the &mmu_interval_notifier_ops->invalidate_start op + * needs to implements the full notifier functionality. Please refer to its + * documentation. + */ +struct mmu_interval_notifier_finish { + struct llist_node link; + struct mmu_interval_notifier *notifier; +}; + +/** + * struct mmu_interval_notifier_ops - callback for range notification * @invalidate: Upon return the caller must stop using any SPTEs within this * range. This function can sleep. Return false only if sleeping * was required but mmu_notifier_range_blockable(range) is false. + * @invalidate_start: Similar to @invalidate, but intended for two-pass notifier + * callbacks where the call to @invalidate_start is the first + * pass and any struct mmu_interval_notifier_finish pointer + * returned in the @finish parameter describes the finish pass. + * If *@finish is %NULL on return, then no final pass will be + * called, and @invalidate_start needs to implement the full + * notifier, behaving like @invalidate. The value of *@finish + * is guaranteed to be %NULL at function entry. + * @invalidate_finish: Called as the second pass for any notifier that returned + * a non-NULL *@finish from @invalidate_start. The @finish + * pointer passed here is the same one returned by + * @invalidate_start. */ struct mmu_interval_notifier_ops { bool (*invalidate)(struct mmu_interval_notifier *interval_sub, const struct mmu_notifier_range *range, unsigned long cur_seq); + bool (*invalidate_start)(struct mmu_interval_notifier *interval_sub, + const struct mmu_notifier_range *range, + unsigned long cur_seq, + struct mmu_interval_notifier_finish **finish); + void (*invalidate_finish)(struct mmu_interval_notifier_finish *finish); }; struct mmu_interval_notifier { @@ -309,8 +351,8 @@ void mmu_interval_notifier_remove(struct mmu_interval_notifier *interval_sub); /** * mmu_interval_set_seq - Save the invalidation sequence - * @interval_sub - The subscription passed to invalidate - * @cur_seq - The cur_seq passed to the invalidate() callback + * @interval_sub: The subscription passed to invalidate + * @cur_seq: The cur_seq passed to the invalidate() callback * * This must be called unconditionally from the invalidate callback of a * struct mmu_interval_notifier_ops under the same lock that is used to call @@ -329,8 +371,8 @@ mmu_interval_set_seq(struct mmu_interval_notifier *interval_sub, /** * mmu_interval_read_retry - End a read side critical section against a VA range - * interval_sub: The subscription - * seq: The return of the paired mmu_interval_read_begin() + * @interval_sub: The subscription + * @seq: The return of the paired mmu_interval_read_begin() * * This MUST be called under a user provided lock that is also held * unconditionally by op->invalidate() when it calls mmu_interval_set_seq(). @@ -338,7 +380,7 @@ mmu_interval_set_seq(struct mmu_interval_notifier *interval_sub, * Each call should be paired with a single mmu_interval_read_begin() and * should be used to conclude the read side. * - * Returns true if an invalidation collided with this critical section, and + * Returns: true if an invalidation collided with this critical section, and * the caller should retry. */ static inline bool @@ -350,20 +392,21 @@ mmu_interval_read_retry(struct mmu_interval_notifier *interval_sub, /** * mmu_interval_check_retry - Test if a collision has occurred - * interval_sub: The subscription - * seq: The return of the matching mmu_interval_read_begin() + * @interval_sub: The subscription + * @seq: The return of the matching mmu_interval_read_begin() * * This can be used in the critical section between mmu_interval_read_begin() - * and mmu_interval_read_retry(). A return of true indicates an invalidation - * has collided with this critical region and a future - * mmu_interval_read_retry() will return true. - * - * False is not reliable and only suggests a collision may not have - * occurred. It can be called many times and does not have to hold the user - * provided lock. + * and mmu_interval_read_retry(). * * This call can be used as part of loops and other expensive operations to * expedite a retry. + * It can be called many times and does not have to hold the user + * provided lock. + * + * Returns: true indicates an invalidation has collided with this critical + * region and a future mmu_interval_read_retry() will return true. + * False is not reliable and only suggests a collision may not have + * occurred. */ static inline bool mmu_interval_check_retry(struct mmu_interval_notifier *interval_sub, diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 67e25f6d15a4..7ca01eb3f7d2 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -311,7 +311,9 @@ struct header_ops { int (*create) (struct sk_buff *skb, struct net_device *dev, unsigned short type, const void *daddr, const void *saddr, unsigned int len); - int (*parse)(const struct sk_buff *skb, unsigned char *haddr); + int (*parse)(const struct sk_buff *skb, + const struct net_device *dev, + unsigned char *haddr); int (*cache)(const struct neighbour *neigh, struct hh_cache *hh, __be16 type); void (*cache_update)(struct hh_cache *hh, const struct net_device *dev, @@ -2155,6 +2157,7 @@ struct net_device { unsigned long state; unsigned int flags; unsigned short hard_header_len; + enum netdev_stat_type pcpu_stat_type:8; netdev_features_t features; struct inet6_dev __rcu *ip6_ptr; __cacheline_group_end(net_device_read_txrx); @@ -2404,8 +2407,6 @@ struct net_device { void *ml_priv; enum netdev_ml_priv_type ml_priv_type; - enum netdev_stat_type pcpu_stat_type:8; - #if IS_ENABLED(CONFIG_GARP) struct garp_port __rcu *garp_port; #endif @@ -3446,7 +3447,7 @@ static inline int dev_parse_header(const struct sk_buff *skb, if (!dev->header_ops || !dev->header_ops->parse) return 0; - return dev->header_ops->parse(skb, haddr); + return dev->header_ops->parse(skb, dev, haddr); } static inline __be16 dev_parse_header_protocol(const struct sk_buff *skb) @@ -3576,17 +3577,49 @@ struct page_pool_bh { }; DECLARE_PER_CPU(struct page_pool_bh, system_page_pool); +#define XMIT_RECURSION_LIMIT 8 + #ifndef CONFIG_PREEMPT_RT static inline int dev_recursion_level(void) { return this_cpu_read(softnet_data.xmit.recursion); } + +static inline bool dev_xmit_recursion(void) +{ + return unlikely(__this_cpu_read(softnet_data.xmit.recursion) > + XMIT_RECURSION_LIMIT); +} + +static inline void dev_xmit_recursion_inc(void) +{ + __this_cpu_inc(softnet_data.xmit.recursion); +} + +static inline void dev_xmit_recursion_dec(void) +{ + __this_cpu_dec(softnet_data.xmit.recursion); +} #else static inline int dev_recursion_level(void) { return current->net_xmit.recursion; } +static inline bool dev_xmit_recursion(void) +{ + return unlikely(current->net_xmit.recursion > XMIT_RECURSION_LIMIT); +} + +static inline void dev_xmit_recursion_inc(void) +{ + current->net_xmit.recursion++; +} + +static inline void dev_xmit_recursion_dec(void) +{ + current->net_xmit.recursion--; +} #endif void __netif_schedule(struct Qdisc *q); diff --git a/include/linux/netfs.h b/include/linux/netfs.h index 72ee7d210a74..ba17ac5bf356 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -140,7 +140,6 @@ struct netfs_io_stream { void (*issue_write)(struct netfs_io_subrequest *subreq); /* Collection tracking */ struct list_head subrequests; /* Contributory I/O operations */ - struct netfs_io_subrequest *front; /* Op being collected */ unsigned long long collected_to; /* Position we've collected results to */ size_t transferred; /* The amount transferred from this stream */ unsigned short error; /* Aggregate error for the stream */ diff --git a/include/linux/nvme-auth.h b/include/linux/nvme-auth.h index 60e069a6757f..e75c29c51464 100644 --- a/include/linux/nvme-auth.h +++ b/include/linux/nvme-auth.h @@ -11,7 +11,7 @@ struct nvme_dhchap_key { size_t len; u8 hash; - u8 key[]; + u8 key[] __counted_by(len); }; u32 nvme_auth_get_seqnum(void); diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index ec442af3f886..31a848485ad9 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -210,7 +210,6 @@ enum mapping_flags { AS_WRITEBACK_MAY_DEADLOCK_ON_RECLAIM = 9, AS_KERNEL_FILE = 10, /* mapping for a fake kernel file that shouldn't account usage to user cgroups */ - AS_NO_DATA_INTEGRITY = 11, /* no data integrity guarantees */ /* Bits 16-25 are used for FOLIO_ORDER */ AS_FOLIO_ORDER_BITS = 5, AS_FOLIO_ORDER_MIN = 16, @@ -346,16 +345,6 @@ static inline bool mapping_writeback_may_deadlock_on_reclaim(const struct addres return test_bit(AS_WRITEBACK_MAY_DEADLOCK_ON_RECLAIM, &mapping->flags); } -static inline void mapping_set_no_data_integrity(struct address_space *mapping) -{ - set_bit(AS_NO_DATA_INTEGRITY, &mapping->flags); -} - -static inline bool mapping_no_data_integrity(const struct address_space *mapping) -{ - return test_bit(AS_NO_DATA_INTEGRITY, &mapping->flags); -} - static inline gfp_t mapping_gfp_mask(const struct address_space *mapping) { return mapping->gfp_mask; diff --git a/include/linux/platform_device.h b/include/linux/platform_device.h index 813da101b5bf..ed1d50d1c3c1 100644 --- a/include/linux/platform_device.h +++ b/include/linux/platform_device.h @@ -31,11 +31,6 @@ struct platform_device { struct resource *resource; const struct platform_device_id *id_entry; - /* - * Driver name to force a match. Do not set directly, because core - * frees it. Use driver_set_override() to set or clear it. - */ - const char *driver_override; /* MFD cell pointer */ struct mfd_cell *mfd_cell; diff --git a/include/linux/rseq_types.h b/include/linux/rseq_types.h index da5fa6f40294..0b42045988db 100644 --- a/include/linux/rseq_types.h +++ b/include/linux/rseq_types.h @@ -133,10 +133,12 @@ struct rseq_data { }; * @active: MM CID is active for the task * @cid: The CID associated to the task either permanently or * borrowed from the CPU + * @node: Queued in the per MM MMCID list */ struct sched_mm_cid { unsigned int active; unsigned int cid; + struct hlist_node node; }; /** @@ -157,6 +159,7 @@ struct mm_cid_pcpu { * @work: Regular work to handle the affinity mode change case * @lock: Spinlock to protect against affinity setting which can't take @mutex * @mutex: Mutex to serialize forks and exits related to this mm + * @user_list: List of the MM CID users of a MM * @nr_cpus_allowed: The number of CPUs in the per MM allowed CPUs map. The map * is growth only. * @users: The number of tasks sharing this MM. Separate from mm::mm_users @@ -177,13 +180,14 @@ struct mm_mm_cid { raw_spinlock_t lock; struct mutex mutex; + struct hlist_head user_list; /* Low frequency modified */ unsigned int nr_cpus_allowed; unsigned int users; unsigned int pcpu_thrs; unsigned int update_deferred; -}____cacheline_aligned_in_smp; +} ____cacheline_aligned; #else /* CONFIG_SCHED_MM_CID */ struct mm_mm_cid { }; struct sched_mm_cid { }; diff --git a/include/linux/sched.h b/include/linux/sched.h index a7b4a980eb2f..5a5d3dbc9cdf 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2354,7 +2354,6 @@ static __always_inline void alloc_tag_restore(struct alloc_tag *tag, struct allo #ifdef CONFIG_SCHED_MM_CID void sched_mm_cid_before_execve(struct task_struct *t); void sched_mm_cid_after_execve(struct task_struct *t); -void sched_mm_cid_fork(struct task_struct *t); void sched_mm_cid_exit(struct task_struct *t); static __always_inline int task_mm_cid(struct task_struct *t) { @@ -2363,7 +2362,6 @@ static __always_inline int task_mm_cid(struct task_struct *t) #else static inline void sched_mm_cid_before_execve(struct task_struct *t) { } static inline void sched_mm_cid_after_execve(struct task_struct *t) { } -static inline void sched_mm_cid_fork(struct task_struct *t) { } static inline void sched_mm_cid_exit(struct task_struct *t) { } static __always_inline int task_mm_cid(struct task_struct *t) { diff --git a/include/linux/security.h b/include/linux/security.h index 83a646d72f6f..ee88dd2d2d1f 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -145,6 +145,7 @@ enum lockdown_reason { LOCKDOWN_BPF_WRITE_USER, LOCKDOWN_DBG_WRITE_KERNEL, LOCKDOWN_RTAS_ERROR_INJECTION, + LOCKDOWN_XEN_USER_ACTIONS, LOCKDOWN_INTEGRITY_MAX, LOCKDOWN_KCORE, LOCKDOWN_KPROBES, diff --git a/include/linux/serial_8250.h b/include/linux/serial_8250.h index 01efdce0fda0..a95b2d143d24 100644 --- a/include/linux/serial_8250.h +++ b/include/linux/serial_8250.h @@ -195,6 +195,7 @@ void serial8250_do_set_mctrl(struct uart_port *port, unsigned int mctrl); void serial8250_do_set_divisor(struct uart_port *port, unsigned int baud, unsigned int quot); int fsl8250_handle_irq(struct uart_port *port); +void serial8250_handle_irq_locked(struct uart_port *port, unsigned int iir); int serial8250_handle_irq(struct uart_port *port, unsigned int iir); u16 serial8250_rx_chars(struct uart_8250_port *up, u16 lsr); void serial8250_read_char(struct uart_8250_port *up, u16 lsr); diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index af7cfee7b8f6..0dc671c07d3a 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -159,10 +159,6 @@ extern void spi_transfer_cs_change_delay_exec(struct spi_message *msg, * @modalias: Name of the driver to use with this device, or an alias * for that name. This appears in the sysfs "modalias" attribute * for driver coldplugging, and in uevents used for hotplugging - * @driver_override: If the name of a driver is written to this attribute, then - * the device will bind to the named driver and only the named driver. - * Do not set directly, because core frees it; use driver_set_override() to - * set or clear it. * @pcpu_statistics: statistics for the spi_device * @word_delay: delay to be inserted between consecutive * words of a transfer @@ -224,7 +220,6 @@ struct spi_device { void *controller_state; void *controller_data; char modalias[SPI_NAME_SIZE]; - const char *driver_override; /* The statistics */ struct spi_statistics __percpu *pcpu_statistics; diff --git a/include/linux/srcutiny.h b/include/linux/srcutiny.h index dec7cbe015aa..905b629e8fa3 100644 --- a/include/linux/srcutiny.h +++ b/include/linux/srcutiny.h @@ -11,6 +11,7 @@ #ifndef _LINUX_SRCU_TINY_H #define _LINUX_SRCU_TINY_H +#include <linux/irq_work_types.h> #include <linux/swait.h> struct srcu_struct { @@ -24,18 +25,21 @@ struct srcu_struct { struct rcu_head *srcu_cb_head; /* Pending callbacks: Head. */ struct rcu_head **srcu_cb_tail; /* Pending callbacks: Tail. */ struct work_struct srcu_work; /* For driving grace periods. */ + struct irq_work srcu_irq_work; /* Defer schedule_work() to irq work. */ #ifdef CONFIG_DEBUG_LOCK_ALLOC struct lockdep_map dep_map; #endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ }; void srcu_drive_gp(struct work_struct *wp); +void srcu_tiny_irq_work(struct irq_work *irq_work); #define __SRCU_STRUCT_INIT(name, __ignored, ___ignored, ____ignored) \ { \ .srcu_wq = __SWAIT_QUEUE_HEAD_INITIALIZER(name.srcu_wq), \ .srcu_cb_tail = &name.srcu_cb_head, \ .srcu_work = __WORK_INITIALIZER(name.srcu_work, srcu_drive_gp), \ + .srcu_irq_work = { .func = srcu_tiny_irq_work }, \ __SRCU_DEP_MAP_INIT(name) \ } diff --git a/include/linux/srcutree.h b/include/linux/srcutree.h index 958cb7ef41cb..be76fa4fc170 100644 --- a/include/linux/srcutree.h +++ b/include/linux/srcutree.h @@ -34,7 +34,7 @@ struct srcu_data { /* Values: SRCU_READ_FLAVOR_.* */ /* Update-side state. */ - spinlock_t __private lock ____cacheline_internodealigned_in_smp; + raw_spinlock_t __private lock ____cacheline_internodealigned_in_smp; struct rcu_segcblist srcu_cblist; /* List of callbacks.*/ unsigned long srcu_gp_seq_needed; /* Furthest future GP needed. */ unsigned long srcu_gp_seq_needed_exp; /* Furthest future exp GP. */ @@ -55,7 +55,7 @@ struct srcu_data { * Node in SRCU combining tree, similar in function to rcu_data. */ struct srcu_node { - spinlock_t __private lock; + raw_spinlock_t __private lock; unsigned long srcu_have_cbs[4]; /* GP seq for children having CBs, but only */ /* if greater than ->srcu_gp_seq. */ unsigned long srcu_data_have_cbs[4]; /* Which srcu_data structs have CBs for given GP? */ @@ -74,7 +74,7 @@ struct srcu_usage { /* First node at each level. */ int srcu_size_state; /* Small-to-big transition state. */ struct mutex srcu_cb_mutex; /* Serialize CB preparation. */ - spinlock_t __private lock; /* Protect counters and size state. */ + raw_spinlock_t __private lock; /* Protect counters and size state. */ struct mutex srcu_gp_mutex; /* Serialize GP work. */ unsigned long srcu_gp_seq; /* Grace-period seq #. */ unsigned long srcu_gp_seq_needed; /* Latest gp_seq needed. */ @@ -95,6 +95,7 @@ struct srcu_usage { unsigned long reschedule_jiffies; unsigned long reschedule_count; struct delayed_work work; + struct irq_work irq_work; struct srcu_struct *srcu_ssp; }; @@ -156,7 +157,7 @@ struct srcu_struct { #define __SRCU_USAGE_INIT(name) \ { \ - .lock = __SPIN_LOCK_UNLOCKED(name.lock), \ + .lock = __RAW_SPIN_LOCK_UNLOCKED(name.lock), \ .srcu_gp_seq = SRCU_GP_SEQ_INITIAL_VAL, \ .srcu_gp_seq_needed = SRCU_GP_SEQ_INITIAL_VAL_WITH_STATE, \ .srcu_gp_seq_needed_exp = SRCU_GP_SEQ_INITIAL_VAL, \ diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index 809e4f7dfdbd..4fe63169d5a2 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -792,7 +792,7 @@ for (bool done = false; !done; done = true) \ /** * scoped_user_rw_access_size - Start a scoped user read/write access with given size - * @uptr Pointer to the user space address to read from and write to + * @uptr: Pointer to the user space address to read from and write to * @size: Size of the access starting from @uptr * @elbl: Error label to goto when the access region is rejected * @@ -803,7 +803,7 @@ for (bool done = false; !done; done = true) \ /** * scoped_user_rw_access - Start a scoped user read/write access - * @uptr Pointer to the user space address to read from and write to + * @uptr: Pointer to the user space address to read from and write to * @elbl: Error label to goto when the access region is rejected * * The size of the access starting from @uptr is determined via sizeof(*@uptr)). diff --git a/include/linux/usb.h b/include/linux/usb.h index fbfcc70b07fb..04277af4bb9d 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -1862,14 +1862,18 @@ void usb_free_noncoherent(struct usb_device *dev, size_t size, * SYNCHRONOUS CALL SUPPORT * *-------------------------------------------------------------------*/ +/* Maximum value allowed for timeout in synchronous routines below */ +#define USB_MAX_SYNCHRONOUS_TIMEOUT 60000 /* ms */ + extern int usb_control_msg(struct usb_device *dev, unsigned int pipe, __u8 request, __u8 requesttype, __u16 value, __u16 index, void *data, __u16 size, int timeout); extern int usb_interrupt_msg(struct usb_device *usb_dev, unsigned int pipe, void *data, int len, int *actual_length, int timeout); extern int usb_bulk_msg(struct usb_device *usb_dev, unsigned int pipe, - void *data, int len, int *actual_length, - int timeout); + void *data, int len, int *actual_length, int timeout); +extern int usb_bulk_msg_killable(struct usb_device *usb_dev, unsigned int pipe, + void *data, int len, int *actual_length, int timeout); /* wrappers around usb_control_msg() for the most common standard requests */ int usb_control_msg_send(struct usb_device *dev, __u8 endpoint, __u8 request, diff --git a/include/linux/usb/quirks.h b/include/linux/usb/quirks.h index 2f7bd2fdc616..b3cc7beab4a3 100644 --- a/include/linux/usb/quirks.h +++ b/include/linux/usb/quirks.h @@ -78,4 +78,7 @@ /* skip BOS descriptor request */ #define USB_QUIRK_NO_BOS BIT(17) +/* Device claims zero configurations, forcing to 1 */ +#define USB_QUIRK_FORCE_ONE_CONFIG BIT(18) + #endif /* __LINUX_USB_QUIRKS_H */ diff --git a/include/linux/usb/usbnet.h b/include/linux/usb/usbnet.h index b0e84896e6ac..bbf799ccf3b3 100644 --- a/include/linux/usb/usbnet.h +++ b/include/linux/usb/usbnet.h @@ -132,6 +132,7 @@ struct driver_info { #define FLAG_MULTI_PACKET 0x2000 #define FLAG_RX_ASSEMBLE 0x4000 /* rx packets may span >1 frames */ #define FLAG_NOARP 0x8000 /* device can't do ARP */ +#define FLAG_NOMAXMTU 0x10000 /* allow max_mtu above hard_mtu */ /* init device ... can sleep, or cause probe() failure */ int (*bind)(struct usbnet *, struct usb_interface *); diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h index 75dabb763c65..f36d21b5bc19 100644 --- a/include/linux/virtio_net.h +++ b/include/linux/virtio_net.h @@ -207,6 +207,39 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb, return __virtio_net_hdr_to_skb(skb, hdr, little_endian, hdr->gso_type); } +/* This function must be called after virtio_net_hdr_from_skb(). */ +static inline void __virtio_net_set_hdrlen(const struct sk_buff *skb, + struct virtio_net_hdr *hdr, + bool little_endian) +{ + u16 hdr_len; + + hdr_len = skb_transport_offset(skb); + + if (hdr->gso_type == VIRTIO_NET_HDR_GSO_UDP_L4) + hdr_len += sizeof(struct udphdr); + else + hdr_len += tcp_hdrlen(skb); + + hdr->hdr_len = __cpu_to_virtio16(little_endian, hdr_len); +} + +/* This function must be called after virtio_net_hdr_from_skb(). */ +static inline void __virtio_net_set_tnl_hdrlen(const struct sk_buff *skb, + struct virtio_net_hdr *hdr) +{ + u16 hdr_len; + + hdr_len = skb_inner_transport_offset(skb); + + if (hdr->gso_type == VIRTIO_NET_HDR_GSO_UDP_L4) + hdr_len += sizeof(struct udphdr); + else + hdr_len += inner_tcp_hdrlen(skb); + + hdr->hdr_len = __cpu_to_virtio16(true, hdr_len); +} + static inline int virtio_net_hdr_from_skb(const struct sk_buff *skb, struct virtio_net_hdr *hdr, bool little_endian, @@ -385,7 +418,8 @@ virtio_net_hdr_tnl_from_skb(const struct sk_buff *skb, bool tnl_hdr_negotiated, bool little_endian, int vlan_hlen, - bool has_data_valid) + bool has_data_valid, + bool feature_hdrlen) { struct virtio_net_hdr *hdr = (struct virtio_net_hdr *)vhdr; unsigned int inner_nh, outer_th; @@ -394,9 +428,17 @@ virtio_net_hdr_tnl_from_skb(const struct sk_buff *skb, tnl_gso_type = skb_shinfo(skb)->gso_type & (SKB_GSO_UDP_TUNNEL | SKB_GSO_UDP_TUNNEL_CSUM); - if (!tnl_gso_type) - return virtio_net_hdr_from_skb(skb, hdr, little_endian, - has_data_valid, vlan_hlen); + if (!tnl_gso_type) { + ret = virtio_net_hdr_from_skb(skb, hdr, little_endian, + has_data_valid, vlan_hlen); + if (ret) + return ret; + + if (feature_hdrlen && hdr->hdr_len) + __virtio_net_set_hdrlen(skb, hdr, little_endian); + + return ret; + } /* Tunnel support not negotiated but skb ask for it. */ if (!tnl_hdr_negotiated) @@ -414,6 +456,9 @@ virtio_net_hdr_tnl_from_skb(const struct sk_buff *skb, if (ret) return ret; + if (feature_hdrlen && hdr->hdr_len) + __virtio_net_set_tnl_hdrlen(skb, hdr); + if (skb->protocol == htons(ETH_P_IPV6)) hdr->gso_type |= VIRTIO_NET_HDR_GSO_UDP_TUNNEL_IPV6; else diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h index 010f1a8fd15f..5172afee5494 100644 --- a/include/net/bluetooth/l2cap.h +++ b/include/net/bluetooth/l2cap.h @@ -658,6 +658,7 @@ struct l2cap_conn { struct sk_buff *rx_skb; __u32 rx_len; struct ida tx_ida; + __u8 tx_ident; struct sk_buff_head pending_rx; struct work_struct pending_rx_work; diff --git a/include/net/codel_impl.h b/include/net/codel_impl.h index 78a27ac73070..b2c359c6dd1b 100644 --- a/include/net/codel_impl.h +++ b/include/net/codel_impl.h @@ -158,6 +158,7 @@ static struct sk_buff *codel_dequeue(void *ctx, bool drop; if (!skb) { + vars->first_above_time = 0; vars->dropping = false; return skb; } diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index 5a979dcab538..6d936e9f2fd3 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -264,6 +264,20 @@ inet_bhashfn_portaddr(const struct inet_hashinfo *hinfo, const struct sock *sk, return &hinfo->bhash2[hash & (hinfo->bhash_size - 1)]; } +static inline bool inet_use_hash2_on_bind(const struct sock *sk) +{ +#if IS_ENABLED(CONFIG_IPV6) + if (sk->sk_family == AF_INET6) { + if (ipv6_addr_any(&sk->sk_v6_rcv_saddr)) + return false; + + if (!ipv6_addr_v4mapped(&sk->sk_v6_rcv_saddr)) + return true; + } +#endif + return sk->sk_rcv_saddr != htonl(INADDR_ANY); +} + struct inet_bind_hashbucket * inet_bhash2_addr_any_hashbucket(const struct sock *sk, const struct net *net, int port); diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index 88b0dd4d8e09..9f8b6814a96a 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -507,12 +507,14 @@ void fib6_rt_update(struct net *net, struct fib6_info *rt, void inet6_rt_notify(int event, struct fib6_info *rt, struct nl_info *info, unsigned int flags); +void fib6_age_exceptions(struct fib6_info *rt, struct fib6_gc_args *gc_args, + unsigned long now); void fib6_run_gc(unsigned long expires, struct net *net, bool force); - void fib6_gc_cleanup(void); int fib6_init(void); +#if IS_ENABLED(CONFIG_IPV6) /* Add the route to the gc list if it is not already there * * The callers should hold f6i->fib6_table->tb6_lock. @@ -545,6 +547,23 @@ static inline void fib6_remove_gc_list(struct fib6_info *f6i) hlist_del_init(&f6i->gc_link); } +static inline void fib6_may_remove_gc_list(struct net *net, + struct fib6_info *f6i) +{ + struct fib6_gc_args gc_args; + + if (hlist_unhashed(&f6i->gc_link)) + return; + + gc_args.timeout = READ_ONCE(net->ipv6.sysctl.ip6_rt_gc_interval); + gc_args.more = 0; + + rcu_read_lock(); + fib6_age_exceptions(f6i, &gc_args, jiffies); + rcu_read_unlock(); +} +#endif + struct ipv6_route_iter { struct seq_net_private p; struct fib6_walker w; diff --git a/include/net/ip6_tunnel.h b/include/net/ip6_tunnel.h index 120db2865811..359b595f1df9 100644 --- a/include/net/ip6_tunnel.h +++ b/include/net/ip6_tunnel.h @@ -156,6 +156,18 @@ static inline void ip6tunnel_xmit(struct sock *sk, struct sk_buff *skb, { int pkt_len, err; + if (unlikely(dev_recursion_level() > IP_TUNNEL_RECURSION_LIMIT)) { + if (dev) { + net_crit_ratelimited("Dead loop on virtual device %s, fix it urgently!\n", + dev->name); + DEV_STATS_INC(dev, tx_errors); + } + kfree_skb(skb); + return; + } + + dev_xmit_recursion_inc(); + memset(skb->cb, 0, sizeof(struct inet6_skb_parm)); IP6CB(skb)->flags = ip6cb_flags; pkt_len = skb->len - skb_inner_network_offset(skb); @@ -166,6 +178,8 @@ static inline void ip6tunnel_xmit(struct sock *sk, struct sk_buff *skb, pkt_len = -1; iptunnel_xmit_stats(dev, pkt_len); } + + dev_xmit_recursion_dec(); } #endif #endif diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index 4021e6a73e32..1f577a4f8ce9 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -27,6 +27,13 @@ #include <net/ip6_route.h> #endif +/* Recursion limit for tunnel xmit to detect routing loops. + * Unlike XMIT_RECURSION_LIMIT (8) used in the no-qdisc path, tunnel + * recursion involves route lookups and full IP output, consuming much + * more stack per level, so a lower limit is needed. + */ +#define IP_TUNNEL_RECURSION_LIMIT 4 + /* Keep error state on tunnel for 30 sec */ #define IPTUNNEL_ERR_TIMEO (30*HZ) @@ -658,13 +665,29 @@ static inline int iptunnel_pull_offloads(struct sk_buff *skb) static inline void iptunnel_xmit_stats(struct net_device *dev, int pkt_len) { if (pkt_len > 0) { - struct pcpu_sw_netstats *tstats = get_cpu_ptr(dev->tstats); - - u64_stats_update_begin(&tstats->syncp); - u64_stats_add(&tstats->tx_bytes, pkt_len); - u64_stats_inc(&tstats->tx_packets); - u64_stats_update_end(&tstats->syncp); - put_cpu_ptr(tstats); + if (dev->pcpu_stat_type == NETDEV_PCPU_STAT_DSTATS) { + struct pcpu_dstats *dstats = get_cpu_ptr(dev->dstats); + + u64_stats_update_begin(&dstats->syncp); + u64_stats_add(&dstats->tx_bytes, pkt_len); + u64_stats_inc(&dstats->tx_packets); + u64_stats_update_end(&dstats->syncp); + put_cpu_ptr(dstats); + return; + } + if (dev->pcpu_stat_type == NETDEV_PCPU_STAT_TSTATS) { + struct pcpu_sw_netstats *tstats = get_cpu_ptr(dev->tstats); + + u64_stats_update_begin(&tstats->syncp); + u64_stats_add(&tstats->tx_bytes, pkt_len); + u64_stats_inc(&tstats->tx_packets); + u64_stats_update_end(&tstats->syncp); + put_cpu_ptr(tstats); + return; + } + pr_err_once("iptunnel_xmit_stats pcpu_stat_type=%d\n", + dev->pcpu_stat_type); + WARN_ON_ONCE(1); return; } diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 7f9d96939a4e..adce2144a678 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -7407,7 +7407,9 @@ void ieee80211_report_wowlan_wakeup(struct ieee80211_vif *vif, * @band: the band to transmit on * @sta: optional pointer to get the station to send the frame to * - * Return: %true if the skb was prepared, %false otherwise + * Return: %true if the skb was prepared, %false otherwise. + * On failure, the skb is freed by this function; callers must not + * free it again. * * Note: must be called under RCU lock */ diff --git a/include/net/netfilter/nf_conntrack_core.h b/include/net/netfilter/nf_conntrack_core.h index 3384859a8921..8883575adcc1 100644 --- a/include/net/netfilter/nf_conntrack_core.h +++ b/include/net/netfilter/nf_conntrack_core.h @@ -83,6 +83,11 @@ void nf_conntrack_lock(spinlock_t *lock); extern spinlock_t nf_conntrack_expect_lock; +static inline void lockdep_nfct_expect_lock_held(void) +{ + lockdep_assert_held(&nf_conntrack_expect_lock); +} + /* ctnetlink code shared by both ctnetlink and nf_conntrack_bpf */ static inline void __nf_ct_set_timeout(struct nf_conn *ct, u64 timeout) diff --git a/include/net/netfilter/nf_conntrack_expect.h b/include/net/netfilter/nf_conntrack_expect.h index 165e7a03b8e9..e9a8350e7ccf 100644 --- a/include/net/netfilter/nf_conntrack_expect.h +++ b/include/net/netfilter/nf_conntrack_expect.h @@ -22,10 +22,16 @@ struct nf_conntrack_expect { /* Hash member */ struct hlist_node hnode; + /* Network namespace */ + possible_net_t net; + /* We expect this tuple, with the following mask */ struct nf_conntrack_tuple tuple; struct nf_conntrack_tuple_mask mask; +#ifdef CONFIG_NF_CONNTRACK_ZONES + struct nf_conntrack_zone zone; +#endif /* Usage count. */ refcount_t use; @@ -40,7 +46,7 @@ struct nf_conntrack_expect { struct nf_conntrack_expect *this); /* Helper to assign to new connection */ - struct nf_conntrack_helper *helper; + struct nf_conntrack_helper __rcu *helper; /* The conntrack of the master connection */ struct nf_conn *master; @@ -62,7 +68,17 @@ struct nf_conntrack_expect { static inline struct net *nf_ct_exp_net(struct nf_conntrack_expect *exp) { - return nf_ct_net(exp->master); + return read_pnet(&exp->net); +} + +static inline bool nf_ct_exp_zone_equal_any(const struct nf_conntrack_expect *a, + const struct nf_conntrack_zone *b) +{ +#ifdef CONFIG_NF_CONNTRACK_ZONES + return a->zone.id == b->id; +#else + return true; +#endif } #define NF_CT_EXP_POLICY_NAME_LEN 16 diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index e2d2bfc1f989..ec8a8ec9c0aa 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -277,8 +277,6 @@ struct nft_userdata { unsigned char data[]; }; -#define NFT_SET_ELEM_INTERNAL_LAST 0x1 - /* placeholder structure for opaque set element backend representation. */ struct nft_elem_priv { }; @@ -288,7 +286,6 @@ struct nft_elem_priv { }; * @key: element key * @key_end: closing element key * @data: element data - * @flags: flags * @priv: element private data and extensions */ struct nft_set_elem { @@ -304,7 +301,6 @@ struct nft_set_elem { u32 buf[NFT_DATA_VALUE_MAXLEN / sizeof(u32)]; struct nft_data val; } data; - u32 flags; struct nft_elem_priv *priv; }; @@ -878,6 +874,8 @@ struct nft_elem_priv *nft_set_elem_init(const struct nft_set *set, u64 timeout, u64 expiration, gfp_t gfp); int nft_set_elem_expr_clone(const struct nft_ctx *ctx, struct nft_set *set, struct nft_expr *expr_array[]); +void nft_set_elem_expr_destroy(const struct nft_ctx *ctx, + struct nft_set_elem_expr *elem_expr); void nft_set_elem_destroy(const struct nft_set *set, const struct nft_elem_priv *elem_priv, bool destroy_expr); diff --git a/include/net/netns/xfrm.h b/include/net/netns/xfrm.h index 23dd647fe024..b73983a17e08 100644 --- a/include/net/netns/xfrm.h +++ b/include/net/netns/xfrm.h @@ -59,7 +59,7 @@ struct netns_xfrm { struct list_head inexact_bins; - struct sock *nlsk; + struct sock __rcu *nlsk; struct sock *nlsk_stash; u32 sysctl_aevent_etime; diff --git a/include/net/page_pool/types.h b/include/net/page_pool/types.h index 0d453484a585..cdd95477af7a 100644 --- a/include/net/page_pool/types.h +++ b/include/net/page_pool/types.h @@ -247,7 +247,7 @@ struct page_pool { /* User-facing fields, protected by page_pools_lock */ struct { struct hlist_node list; - u64 detach_time; + ktime_t detach_time; u32 id; } user; }; diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index d5d55cb21686..c3d657359a3d 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -716,6 +716,34 @@ void qdisc_destroy(struct Qdisc *qdisc); void qdisc_put(struct Qdisc *qdisc); void qdisc_put_unlocked(struct Qdisc *qdisc); void qdisc_tree_reduce_backlog(struct Qdisc *qdisc, int n, int len); + +static inline void dev_reset_queue(struct net_device *dev, + struct netdev_queue *dev_queue, + void *_unused) +{ + struct Qdisc *qdisc; + bool nolock; + + qdisc = rtnl_dereference(dev_queue->qdisc_sleeping); + if (!qdisc) + return; + + nolock = qdisc->flags & TCQ_F_NOLOCK; + + if (nolock) + spin_lock_bh(&qdisc->seqlock); + spin_lock_bh(qdisc_lock(qdisc)); + + qdisc_reset(qdisc); + + spin_unlock_bh(qdisc_lock(qdisc)); + if (nolock) { + clear_bit(__QDISC_STATE_MISSED, &qdisc->state); + clear_bit(__QDISC_STATE_DRAINING, &qdisc->state); + spin_unlock_bh(&qdisc->seqlock); + } +} + #ifdef CONFIG_NET_SCHED int qdisc_offload_dump_helper(struct Qdisc *q, enum tc_setup_type type, void *type_data); @@ -1429,6 +1457,11 @@ void mini_qdisc_pair_init(struct mini_Qdisc_pair *miniqp, struct Qdisc *qdisc, void mini_qdisc_pair_block_init(struct mini_Qdisc_pair *miniqp, struct tcf_block *block); +static inline bool mini_qdisc_pair_inited(struct mini_Qdisc_pair *miniqp) +{ + return !!miniqp->p_miniq; +} + void mq_change_real_num_tx(struct Qdisc *sch, unsigned int new_real_tx); int sch_frag_xmit_hook(struct sk_buff *skb, int (*xmit)(struct sk_buff *skb)); diff --git a/include/net/udp_tunnel.h b/include/net/udp_tunnel.h index d9c6d04bb3b5..fc1fc43345b5 100644 --- a/include/net/udp_tunnel.h +++ b/include/net/udp_tunnel.h @@ -52,7 +52,7 @@ int udp_sock_create6(struct net *net, struct udp_port_cfg *cfg, static inline int udp_sock_create6(struct net *net, struct udp_port_cfg *cfg, struct socket **sockp) { - return 0; + return -EPFNOSUPPORT; } #endif diff --git a/include/sound/sdca_function.h b/include/sound/sdca_function.h index 79bd5a7a0f88..0e871c786513 100644 --- a/include/sound/sdca_function.h +++ b/include/sound/sdca_function.h @@ -27,11 +27,6 @@ struct sdca_function_desc; #define SDCA_MAX_ENTITY_COUNT 128 /* - * Sanity check on number of initialization writes, can be expanded if needed. - */ -#define SDCA_MAX_INIT_COUNT 2048 - -/* * The Cluster IDs are 16-bit, so a maximum of 65535 Clusters per * function can be represented, however limit this to a slightly * more reasonable value. Can be expanded if needed. diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h index 125bdc166bfe..0864700f76e0 100644 --- a/include/trace/events/btrfs.h +++ b/include/trace/events/btrfs.h @@ -769,12 +769,15 @@ TRACE_EVENT(btrfs_sync_file, ), TP_fast_assign( - const struct dentry *dentry = file->f_path.dentry; - const struct inode *inode = d_inode(dentry); + struct dentry *dentry = file_dentry(file); + struct inode *inode = file_inode(file); + struct dentry *parent = dget_parent(dentry); + struct inode *parent_inode = d_inode(parent); - TP_fast_assign_fsid(btrfs_sb(file->f_path.dentry->d_sb)); + dput(parent); + TP_fast_assign_fsid(btrfs_sb(inode->i_sb)); __entry->ino = btrfs_ino(BTRFS_I(inode)); - __entry->parent = btrfs_ino(BTRFS_I(d_inode(dentry->d_parent))); + __entry->parent = btrfs_ino(BTRFS_I(parent_inode)); __entry->datasync = datasync; __entry->root_objectid = btrfs_root_id(BTRFS_I(inode)->root); ), diff --git a/include/trace/events/dma.h b/include/trace/events/dma.h index 33e99e792f1a..63597b004424 100644 --- a/include/trace/events/dma.h +++ b/include/trace/events/dma.h @@ -32,7 +32,9 @@ TRACE_DEFINE_ENUM(DMA_NONE); { DMA_ATTR_ALLOC_SINGLE_PAGES, "ALLOC_SINGLE_PAGES" }, \ { DMA_ATTR_NO_WARN, "NO_WARN" }, \ { DMA_ATTR_PRIVILEGED, "PRIVILEGED" }, \ - { DMA_ATTR_MMIO, "MMIO" }) + { DMA_ATTR_MMIO, "MMIO" }, \ + { DMA_ATTR_DEBUGGING_IGNORE_CACHELINES, "CACHELINES_OVERLAP" }, \ + { DMA_ATTR_REQUIRE_COHERENT, "REQUIRE_COHERENT" }) DECLARE_EVENT_CLASS(dma_map, TP_PROTO(struct device *dev, phys_addr_t phys_addr, dma_addr_t dma_addr, diff --git a/include/trace/events/netfs.h b/include/trace/events/netfs.h index 2d366be46a1c..cbe28211106c 100644 --- a/include/trace/events/netfs.h +++ b/include/trace/events/netfs.h @@ -740,19 +740,19 @@ TRACE_EVENT(netfs_collect_stream, __field(unsigned int, wreq) __field(unsigned char, stream) __field(unsigned long long, collected_to) - __field(unsigned long long, front) + __field(unsigned long long, issued_to) ), TP_fast_assign( __entry->wreq = wreq->debug_id; __entry->stream = stream->stream_nr; __entry->collected_to = stream->collected_to; - __entry->front = stream->front ? stream->front->start : UINT_MAX; + __entry->issued_to = atomic64_read(&wreq->issued_to); ), - TP_printk("R=%08x[%x:] cto=%llx frn=%llx", + TP_printk("R=%08x[%x:] cto=%llx ito=%llx", __entry->wreq, __entry->stream, - __entry->collected_to, __entry->front) + __entry->collected_to, __entry->issued_to) ); TRACE_EVENT(netfs_folioq, diff --git a/include/trace/events/task.h b/include/trace/events/task.h index 4f0759634306..b9a129eb54d9 100644 --- a/include/trace/events/task.h +++ b/include/trace/events/task.h @@ -38,19 +38,22 @@ TRACE_EVENT(task_rename, TP_ARGS(task, comm), TP_STRUCT__entry( + __field( pid_t, pid) __array( char, oldcomm, TASK_COMM_LEN) __array( char, newcomm, TASK_COMM_LEN) __field( short, oom_score_adj) ), TP_fast_assign( + __entry->pid = task->pid; memcpy(entry->oldcomm, task->comm, TASK_COMM_LEN); strscpy(entry->newcomm, comm, TASK_COMM_LEN); __entry->oom_score_adj = task->signal->oom_score_adj; ), - TP_printk("oldcomm=%s newcomm=%s oom_score_adj=%hd", - __entry->oldcomm, __entry->newcomm, __entry->oom_score_adj) + TP_printk("pid=%d oldcomm=%s newcomm=%s oom_score_adj=%hd", + __entry->pid, __entry->oldcomm, + __entry->newcomm, __entry->oom_score_adj) ); /** diff --git a/include/uapi/drm/drm_ras.h b/include/uapi/drm/drm_ras.h new file mode 100644 index 000000000000..5f40fa5b869d --- /dev/null +++ b/include/uapi/drm/drm_ras.h @@ -0,0 +1,49 @@ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ +/* Do not edit directly, auto-generated from: */ +/* Documentation/netlink/specs/drm_ras.yaml */ +/* YNL-GEN uapi header */ +/* To regenerate run: tools/net/ynl/ynl-regen.sh */ + +#ifndef _UAPI_LINUX_DRM_RAS_H +#define _UAPI_LINUX_DRM_RAS_H + +#define DRM_RAS_FAMILY_NAME "drm-ras" +#define DRM_RAS_FAMILY_VERSION 1 + +/* + * Type of the node. Currently, only error-counter nodes are supported, which + * expose reliability counters for a hardware/software component. + */ +enum drm_ras_node_type { + DRM_RAS_NODE_TYPE_ERROR_COUNTER = 1, +}; + +enum { + DRM_RAS_A_NODE_ATTRS_NODE_ID = 1, + DRM_RAS_A_NODE_ATTRS_DEVICE_NAME, + DRM_RAS_A_NODE_ATTRS_NODE_NAME, + DRM_RAS_A_NODE_ATTRS_NODE_TYPE, + + __DRM_RAS_A_NODE_ATTRS_MAX, + DRM_RAS_A_NODE_ATTRS_MAX = (__DRM_RAS_A_NODE_ATTRS_MAX - 1) +}; + +enum { + DRM_RAS_A_ERROR_COUNTER_ATTRS_NODE_ID = 1, + DRM_RAS_A_ERROR_COUNTER_ATTRS_ERROR_ID, + DRM_RAS_A_ERROR_COUNTER_ATTRS_ERROR_NAME, + DRM_RAS_A_ERROR_COUNTER_ATTRS_ERROR_VALUE, + + __DRM_RAS_A_ERROR_COUNTER_ATTRS_MAX, + DRM_RAS_A_ERROR_COUNTER_ATTRS_MAX = (__DRM_RAS_A_ERROR_COUNTER_ATTRS_MAX - 1) +}; + +enum { + DRM_RAS_CMD_LIST_NODES = 1, + DRM_RAS_CMD_GET_ERROR_COUNTER, + + __DRM_RAS_CMD_MAX, + DRM_RAS_CMD_MAX = (__DRM_RAS_CMD_MAX - 1) +}; + +#endif /* _UAPI_LINUX_DRM_RAS_H */ diff --git a/include/uapi/drm/xe_drm.h b/include/uapi/drm/xe_drm.h index ef2565048bdf..ae2fda23ce7c 100644 --- a/include/uapi/drm/xe_drm.h +++ b/include/uapi/drm/xe_drm.h @@ -83,6 +83,7 @@ extern "C" { * - &DRM_IOCTL_XE_OBSERVATION * - &DRM_IOCTL_XE_MADVISE * - &DRM_IOCTL_XE_VM_QUERY_MEM_RANGE_ATTRS + * - &DRM_IOCTL_XE_VM_GET_PROPERTY */ /* @@ -107,6 +108,7 @@ extern "C" { #define DRM_XE_MADVISE 0x0c #define DRM_XE_VM_QUERY_MEM_RANGE_ATTRS 0x0d #define DRM_XE_EXEC_QUEUE_SET_PROPERTY 0x0e +#define DRM_XE_VM_GET_PROPERTY 0x0f /* Must be kept compact -- no holes */ @@ -125,6 +127,7 @@ extern "C" { #define DRM_IOCTL_XE_MADVISE DRM_IOW(DRM_COMMAND_BASE + DRM_XE_MADVISE, struct drm_xe_madvise) #define DRM_IOCTL_XE_VM_QUERY_MEM_RANGE_ATTRS DRM_IOWR(DRM_COMMAND_BASE + DRM_XE_VM_QUERY_MEM_RANGE_ATTRS, struct drm_xe_vm_query_mem_range_attr) #define DRM_IOCTL_XE_EXEC_QUEUE_SET_PROPERTY DRM_IOW(DRM_COMMAND_BASE + DRM_XE_EXEC_QUEUE_SET_PROPERTY, struct drm_xe_exec_queue_set_property) +#define DRM_IOCTL_XE_VM_GET_PROPERTY DRM_IOWR(DRM_COMMAND_BASE + DRM_XE_VM_GET_PROPERTY, struct drm_xe_vm_get_property) /** * DOC: Xe IOCTL Extensions @@ -406,6 +409,9 @@ struct drm_xe_query_mem_regions { * - %DRM_XE_QUERY_CONFIG_FLAG_HAS_NO_COMPRESSION_HINT - Flag is set if the * device supports the userspace hint %DRM_XE_GEM_CREATE_FLAG_NO_COMPRESSION. * This is exposed only on Xe2+. + * - %DRM_XE_QUERY_CONFIG_FLAG_HAS_DISABLE_STATE_CACHE_PERF_FIX - Flag is set + * if a queue can be creaed with + * %DRM_XE_EXEC_QUEUE_SET_DISABLE_STATE_CACHE_PERF_FIX * - %DRM_XE_QUERY_CONFIG_MIN_ALIGNMENT - Minimal memory alignment * required by this device, typically SZ_4K or SZ_64K * - %DRM_XE_QUERY_CONFIG_VA_BITS - Maximum bits of a virtual address @@ -425,6 +431,8 @@ struct drm_xe_query_config { #define DRM_XE_QUERY_CONFIG_FLAG_HAS_LOW_LATENCY (1 << 1) #define DRM_XE_QUERY_CONFIG_FLAG_HAS_CPU_ADDR_MIRROR (1 << 2) #define DRM_XE_QUERY_CONFIG_FLAG_HAS_NO_COMPRESSION_HINT (1 << 3) + #define DRM_XE_QUERY_CONFIG_FLAG_HAS_DISABLE_STATE_CACHE_PERF_FIX (1 << 4) + #define DRM_XE_QUERY_CONFIG_FLAG_HAS_PURGING_SUPPORT (1 << 5) #define DRM_XE_QUERY_CONFIG_MIN_ALIGNMENT 2 #define DRM_XE_QUERY_CONFIG_VA_BITS 3 #define DRM_XE_QUERY_CONFIG_MAX_EXEC_QUEUE_PRIORITY 4 @@ -1053,6 +1061,13 @@ struct drm_xe_vm_destroy { * not invoke autoreset. Neither will stack variables going out of scope. * Therefore it's recommended to always explicitly reset the madvises when * freeing the memory backing a region used in a &DRM_IOCTL_XE_MADVISE call. + * - %DRM_XE_VM_BIND_FLAG_DECOMPRESS - Request on-device decompression for a MAP. + * When set on a MAP bind operation, request the driver schedule an on-device + * in-place decompression (via the migrate/resolve path) for the GPU mapping + * created by this bind. Only valid for DRM_XE_VM_BIND_OP_MAP; usage on + * other ops is rejected. The bind's pat_index must select the device's + * "no-compression" PAT. Only meaningful for VRAM-backed BOs on devices that + * support Flat CCS and the required HW generation XE2+. * * The @prefetch_mem_region_instance for %DRM_XE_VM_BIND_OP_PREFETCH can also be: * - %DRM_XE_CONSULT_MEM_ADVISE_PREF_LOC, which ensures prefetching occurs in @@ -1103,7 +1118,9 @@ struct drm_xe_vm_bind_op { * incoherent GT access is possible. * * Note: For userptr and externally imported dma-buf the kernel expects - * either 1WAY or 2WAY for the @pat_index. + * either 1WAY or 2WAY for the @pat_index. Starting from NVL-P, for + * userptr, svm, madvise and externally imported dma-buf the kernel expects + * either 2WAY or 1WAY and XA @pat_index. * * For DRM_XE_VM_BIND_FLAG_NULL bindings there are no KMD restrictions * on the @pat_index. For such mappings there is no actual memory being @@ -1160,6 +1177,7 @@ struct drm_xe_vm_bind_op { #define DRM_XE_VM_BIND_FLAG_CHECK_PXP (1 << 4) #define DRM_XE_VM_BIND_FLAG_CPU_ADDR_MIRROR (1 << 5) #define DRM_XE_VM_BIND_FLAG_MADVISE_AUTORESET (1 << 6) +#define DRM_XE_VM_BIND_FLAG_DECOMPRESS (1 << 7) /** @flags: Bind flags */ __u32 flags; @@ -1249,6 +1267,89 @@ struct drm_xe_vm_bind { __u64 reserved[2]; }; +/** struct xe_vm_fault - Describes faults for %DRM_XE_VM_GET_PROPERTY_FAULTS */ +struct xe_vm_fault { + /** @address: Canonical address of the fault */ + __u64 address; + /** @address_precision: Precision of faulted address */ + __u32 address_precision; + /** @access_type: Type of address access that resulted in fault */ +#define FAULT_ACCESS_TYPE_READ 0 +#define FAULT_ACCESS_TYPE_WRITE 1 +#define FAULT_ACCESS_TYPE_ATOMIC 2 + __u8 access_type; + /** @fault_type: Type of fault reported */ +#define FAULT_TYPE_NOT_PRESENT 0 +#define FAULT_TYPE_WRITE_ACCESS 1 +#define FAULT_TYPE_ATOMIC_ACCESS 2 + __u8 fault_type; + /** @fault_level: fault level of the fault */ +#define FAULT_LEVEL_PTE 0 +#define FAULT_LEVEL_PDE 1 +#define FAULT_LEVEL_PDP 2 +#define FAULT_LEVEL_PML4 3 +#define FAULT_LEVEL_PML5 4 + __u8 fault_level; + /** @pad: MBZ */ + __u8 pad; + /** @reserved: MBZ */ + __u64 reserved[4]; +}; + +/** + * struct drm_xe_vm_get_property - Input of &DRM_IOCTL_XE_VM_GET_PROPERTY + * + * The user provides a VM and a property to query among DRM_XE_VM_GET_PROPERTY_*, + * and sets the values in the vm_id and property members, respectively. This + * determines both the VM to get the property of, as well as the property to + * report. + * + * If size is set to 0, the driver fills it with the required size for the + * requested property. The user is expected here to allocate memory for the + * property structure and to provide a pointer to the allocated memory using the + * data member. For some properties, this may be zero, in which case, the + * value of the property will be saved to the value member and size will remain + * zero on return. + * + * If size is not zero, then the IOCTL will attempt to copy the requested + * property into the data member. + * + * The IOCTL will return -ENOENT if the VM could not be identified from the + * provided VM ID, or -EINVAL if the IOCTL fails for any other reason, such as + * providing an invalid size for the given property or if the property data + * could not be copied to the memory allocated to the data member. + * + * The property member can be: + * - %DRM_XE_VM_GET_PROPERTY_FAULTS + */ +struct drm_xe_vm_get_property { + /** @extensions: Pointer to the first extension struct, if any */ + __u64 extensions; + + /** @vm_id: The ID of the VM to query the properties of */ + __u32 vm_id; + +#define DRM_XE_VM_GET_PROPERTY_FAULTS 0 + /** @property: property to get */ + __u32 property; + + /** @size: Size to allocate for @data */ + __u32 size; + + /** @pad: MBZ */ + __u32 pad; + + union { + /** @data: Pointer to user-defined array of flexible size and type */ + __u64 data; + /** @value: Return value for scalar queries */ + __u64 value; + }; + + /** @reserved: MBZ */ + __u64 reserved[3]; +}; + /** * struct drm_xe_exec_queue_create - Input of &DRM_IOCTL_XE_EXEC_QUEUE_CREATE * @@ -1285,6 +1386,9 @@ struct drm_xe_vm_bind { * - %DRM_XE_EXEC_QUEUE_SET_PROPERTY_MULTI_QUEUE_PRIORITY - Set the queue * priority within the multi-queue group. Current valid priority values are 0–2 * (default is 1), with higher values indicating higher priority. + * - %DRM_XE_EXEC_QUEUE_SET_DISABLE_STATE_CACHE_PERF_FIX - Set the queue to + * enable render color cache keying on BTP+BTI instead of just BTI + * (only valid for render queues). * * The example below shows how to use @drm_xe_exec_queue_create to create * a simple exec_queue (no parallel submission) of class @@ -1329,6 +1433,7 @@ struct drm_xe_exec_queue_create { #define DRM_XE_EXEC_QUEUE_SET_PROPERTY_MULTI_GROUP 4 #define DRM_XE_MULTI_GROUP_CREATE (1ull << 63) #define DRM_XE_EXEC_QUEUE_SET_PROPERTY_MULTI_QUEUE_PRIORITY 5 +#define DRM_XE_EXEC_QUEUE_SET_DISABLE_STATE_CACHE_PERF_FIX 6 /** @extensions: Pointer to the first extension struct, if any */ __u64 extensions; @@ -2067,6 +2172,7 @@ struct drm_xe_query_eu_stall { * - DRM_XE_MEM_RANGE_ATTR_PREFERRED_LOC: Set preferred memory location. * - DRM_XE_MEM_RANGE_ATTR_ATOMIC: Set atomic access policy. * - DRM_XE_MEM_RANGE_ATTR_PAT: Set page attribute table index. + * - DRM_XE_VMA_ATTR_PURGEABLE_STATE: Set purgeable state for BOs. * * Example: * @@ -2099,6 +2205,7 @@ struct drm_xe_madvise { #define DRM_XE_MEM_RANGE_ATTR_PREFERRED_LOC 0 #define DRM_XE_MEM_RANGE_ATTR_ATOMIC 1 #define DRM_XE_MEM_RANGE_ATTR_PAT 2 +#define DRM_XE_VMA_ATTR_PURGEABLE_STATE 3 /** @type: type of attribute */ __u32 type; @@ -2189,6 +2296,72 @@ struct drm_xe_madvise { /** @pat_index.reserved: Reserved */ __u64 reserved; } pat_index; + + /** + * @purge_state_val: Purgeable state configuration + * + * Used when @type == DRM_XE_VMA_ATTR_PURGEABLE_STATE. + * + * Configures the purgeable state of buffer objects in the specified + * virtual address range. This allows applications to hint to the kernel + * about bo's usage patterns for better memory management. + * + * By default all VMAs are in WILLNEED state. + * + * Supported values for @purge_state_val.val: + * - DRM_XE_VMA_PURGEABLE_STATE_WILLNEED (0): Marks BO as needed. + * If the BO was previously purged, the kernel sets the __u32 at + * @retained_ptr to 0 (backing store lost) so the application knows + * it must recreate the BO. + * + * - DRM_XE_VMA_PURGEABLE_STATE_DONTNEED (1): Marks BO as not currently + * needed. Kernel may purge it under memory pressure to reclaim memory. + * Only applies to non-shared BOs. The kernel sets the __u32 at + * @retained_ptr to 1 if the backing store still exists (not yet purged), + * or 0 if it was already purged. + * + * Important: Once marked as DONTNEED, touching the BO's memory + * is undefined behavior. It may succeed temporarily (before the + * kernel purges the backing store) but will suddenly fail once + * the BO transitions to PURGED state. + * + * To transition back: use WILLNEED and check @retained_ptr — + * if 0, backing store was lost and the BO must be recreated. + * + * The following operations are blocked in DONTNEED state to + * prevent the BO from being re-mapped after madvise: + * - New mmap() calls: Fail with -EBUSY + * - VM_BIND operations: Fail with -EBUSY + * - New dma-buf exports: Fail with -EBUSY + * - CPU page faults (existing mmap): Fail with SIGBUS + * - GPU page faults (fault-mode VMs): Fail with -EACCES + */ + struct { +#define DRM_XE_VMA_PURGEABLE_STATE_WILLNEED 0 +#define DRM_XE_VMA_PURGEABLE_STATE_DONTNEED 1 + /** @purge_state_val.val: value for DRM_XE_VMA_ATTR_PURGEABLE_STATE */ + __u32 val; + + /** @purge_state_val.pad: MBZ */ + __u32 pad; + /** + * @purge_state_val.retained_ptr: Pointer to a __u32 output + * field for backing store status. + * + * Userspace must initialize the __u32 value at this address + * to 0 before the ioctl. Kernel writes a __u32 after the + * operation: + * - 1 if backing store exists (not purged) + * - 0 if backing store was purged + * + * If userspace fails to initialize to 0, ioctl returns -EINVAL. + * This ensures a safe default (0 = assume purged) if kernel + * cannot write the result. + * + * Similar to i915's drm_i915_gem_madvise.retained field. + */ + __u64 retained_ptr; + } purge_state_val; }; /** @reserved: Reserved */ @@ -2357,6 +2530,85 @@ struct drm_xe_exec_queue_set_property { __u64 reserved[2]; }; +/** + * DOC: Xe DRM RAS + * + * The enums and strings defined below map to the attributes of the DRM RAS Netlink Interface. + * Refer to Documentation/netlink/specs/drm_ras.yaml for complete interface specification. + * + * Node Registration + * ================= + * + * The driver registers DRM RAS nodes for each error severity level. + * enum drm_xe_ras_error_severity defines the node-id, while DRM_XE_RAS_ERROR_SEVERITY_NAMES maps + * node-id to node-name. + * + * Error Classification + * ==================== + * + * Each node contains a list of error counters. Each error is identified by a error-id and + * an error-name. enum drm_xe_ras_error_component defines the error-id, while + * DRM_XE_RAS_ERROR_COMPONENT_NAMES maps error-id to error-name. + * + * User Interface + * ============== + * + * To retrieve error values of a error counter, userspace applications should + * follow the below steps: + * + * 1. Use command LIST_NODES to enumerate all available nodes + * 2. Select node by node-id or node-name + * 3. Use command GET_ERROR_COUNTERS to list errors of specific node + * 4. Query specific error values using either error-id or error-name + * + * .. code-block:: C + * + * // Lookup tables for ID-to-name resolution + * static const char *nodes[] = DRM_XE_RAS_ERROR_SEVERITY_NAMES; + * static const char *errors[] = DRM_XE_RAS_ERROR_COMPONENT_NAMES; + * + */ + +/** + * enum drm_xe_ras_error_severity - DRM RAS error severity. + */ +enum drm_xe_ras_error_severity { + /** @DRM_XE_RAS_ERR_SEV_CORRECTABLE: Correctable Error */ + DRM_XE_RAS_ERR_SEV_CORRECTABLE = 0, + /** @DRM_XE_RAS_ERR_SEV_UNCORRECTABLE: Uncorrectable Error */ + DRM_XE_RAS_ERR_SEV_UNCORRECTABLE, + /** @DRM_XE_RAS_ERR_SEV_MAX: Max severity */ + DRM_XE_RAS_ERR_SEV_MAX /* non-ABI */ +}; + +/** + * enum drm_xe_ras_error_component - DRM RAS error component. + */ +enum drm_xe_ras_error_component { + /** @DRM_XE_RAS_ERR_COMP_CORE_COMPUTE: Core Compute Error */ + DRM_XE_RAS_ERR_COMP_CORE_COMPUTE = 1, + /** @DRM_XE_RAS_ERR_COMP_SOC_INTERNAL: SoC Internal Error */ + DRM_XE_RAS_ERR_COMP_SOC_INTERNAL, + /** @DRM_XE_RAS_ERR_COMP_MAX: Max Error */ + DRM_XE_RAS_ERR_COMP_MAX /* non-ABI */ +}; + +/* + * Error severity to name mapping. + */ +#define DRM_XE_RAS_ERROR_SEVERITY_NAMES { \ + [DRM_XE_RAS_ERR_SEV_CORRECTABLE] = "correctable-errors", \ + [DRM_XE_RAS_ERR_SEV_UNCORRECTABLE] = "uncorrectable-errors", \ +} + +/* + * Error component to name mapping. + */ +#define DRM_XE_RAS_ERROR_COMPONENT_NAMES { \ + [DRM_XE_RAS_ERR_COMP_CORE_COMPUTE] = "core-compute", \ + [DRM_XE_RAS_ERR_COMP_SOC_INTERNAL] = "soc-internal" \ +} + #if defined(__cplusplus) } #endif diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 65500f5db379..80364d4dbebb 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -14,6 +14,10 @@ #include <linux/ioctl.h> #include <asm/kvm.h> +#ifdef __KERNEL__ +#include <linux/kvm_types.h> +#endif + #define KVM_API_VERSION 12 /* @@ -1601,7 +1605,11 @@ struct kvm_stats_desc { __u16 size; __u32 offset; __u32 bucket_size; +#ifdef __KERNEL__ + char name[KVM_STATS_NAME_SIZE]; +#else char name[]; +#endif }; #define KVM_GET_STATS_FD _IO(KVMIO, 0xce) diff --git a/include/uapi/linux/netfilter/nf_conntrack_common.h b/include/uapi/linux/netfilter/nf_conntrack_common.h index 26071021e986..56b6b60a814f 100644 --- a/include/uapi/linux/netfilter/nf_conntrack_common.h +++ b/include/uapi/linux/netfilter/nf_conntrack_common.h @@ -159,5 +159,9 @@ enum ip_conntrack_expect_events { #define NF_CT_EXPECT_INACTIVE 0x2 #define NF_CT_EXPECT_USERSPACE 0x4 +#ifdef __KERNEL__ +#define NF_CT_EXPECT_MASK (NF_CT_EXPECT_PERMANENT | NF_CT_EXPECT_INACTIVE | \ + NF_CT_EXPECT_USERSPACE) +#endif #endif /* _UAPI_NF_CONNTRACK_COMMON_H */ diff --git a/include/video/vga.h b/include/video/vga.h index 468764d6727a..2f13c371800b 100644 --- a/include/video/vga.h +++ b/include/video/vga.h @@ -46,6 +46,7 @@ #define VGA_MIS_R 0x3CC /* Misc Output Read Register */ #define VGA_MIS_W 0x3C2 /* Misc Output Write Register */ #define VGA_FTC_R 0x3CA /* Feature Control Read Register */ +#define VGA_IS0_R 0x3C2 /* Input Status Register 0 */ #define VGA_IS1_RC 0x3DA /* Input Status Register 1 - color emulation */ #define VGA_IS1_RM 0x3BA /* Input Status Register 1 - mono emulation */ #define VGA_PEL_D 0x3C9 /* PEL Data Register */ |