diff options
author | Jiri Kosina <jkosina@suse.cz> | 2021-11-05 14:10:27 +0300 |
---|---|---|
committer | Jiri Kosina <jkosina@suse.cz> | 2021-11-05 14:10:27 +0300 |
commit | 820e9906cf64142169134f35b996108303cf22ca (patch) | |
tree | 89f8831fb39c59aba208395d91e25ab4b26f473f /tools/include | |
parent | b9865081a56a5cd01cd7c9735911709ff82bd8df (diff) | |
parent | 2ea5999d07d2a0ab6ad92ccf65524707f2c5e456 (diff) | |
download | linux-820e9906cf64142169134f35b996108303cf22ca.tar.xz |
Merge branch 'for-5.16/asus' into for-linus
Diffstat (limited to 'tools/include')
-rw-r--r-- | tools/include/linux/bitmap.h | 4 | ||||
-rw-r--r-- | tools/include/linux/compiler-gcc.h | 8 | ||||
-rw-r--r-- | tools/include/linux/compiler_types.h | 18 | ||||
-rw-r--r-- | tools/include/linux/overflow.h | 140 | ||||
-rw-r--r-- | tools/include/uapi/asm-generic/unistd.h | 14 | ||||
-rw-r--r-- | tools/include/uapi/drm/drm.h | 14 | ||||
-rw-r--r-- | tools/include/uapi/drm/i915_drm.h | 498 | ||||
-rw-r--r-- | tools/include/uapi/linux/fs.h | 1 | ||||
-rw-r--r-- | tools/include/uapi/linux/in.h | 42 | ||||
-rw-r--r-- | tools/include/uapi/linux/kvm.h | 11 | ||||
-rw-r--r-- | tools/include/uapi/linux/mount.h | 3 | ||||
-rw-r--r-- | tools/include/uapi/linux/prctl.h | 12 | ||||
-rw-r--r-- | tools/include/uapi/sound/asound.h | 1 |
13 files changed, 512 insertions, 254 deletions
diff --git a/tools/include/linux/bitmap.h b/tools/include/linux/bitmap.h index 9d959bc24859..95611df1d26e 100644 --- a/tools/include/linux/bitmap.h +++ b/tools/include/linux/bitmap.h @@ -111,10 +111,10 @@ static inline int test_and_clear_bit(int nr, unsigned long *addr) } /** - * bitmap_alloc - Allocate bitmap + * bitmap_zalloc - Allocate bitmap * @nbits: Number of bits */ -static inline unsigned long *bitmap_alloc(int nbits) +static inline unsigned long *bitmap_zalloc(int nbits) { return calloc(1, BITS_TO_LONGS(nbits) * sizeof(unsigned long)); } diff --git a/tools/include/linux/compiler-gcc.h b/tools/include/linux/compiler-gcc.h index 95c072b70d0e..8816f06fc6c7 100644 --- a/tools/include/linux/compiler-gcc.h +++ b/tools/include/linux/compiler-gcc.h @@ -16,9 +16,9 @@ # define __fallthrough __attribute__ ((fallthrough)) #endif -#if GCC_VERSION >= 40300 +#if __has_attribute(__error__) # define __compiletime_error(message) __attribute__((error(message))) -#endif /* GCC_VERSION >= 40300 */ +#endif /* &a[0] degrades to a pointer: a different type from an array */ #define __must_be_array(a) BUILD_BUG_ON_ZERO(__same_type((a), &(a)[0])) @@ -38,7 +38,3 @@ #endif #define __printf(a, b) __attribute__((format(printf, a, b))) #define __scanf(a, b) __attribute__((format(scanf, a, b))) - -#if GCC_VERSION >= 50100 -#define COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW 1 -#endif diff --git a/tools/include/linux/compiler_types.h b/tools/include/linux/compiler_types.h index feea09029f61..24ae3054f304 100644 --- a/tools/include/linux/compiler_types.h +++ b/tools/include/linux/compiler_types.h @@ -13,6 +13,24 @@ #define __has_builtin(x) (0) #endif +#ifdef __CHECKER__ +/* context/locking */ +# define __must_hold(x) __attribute__((context(x,1,1))) +# define __acquires(x) __attribute__((context(x,0,1))) +# define __releases(x) __attribute__((context(x,1,0))) +# define __acquire(x) __context__(x,1) +# define __release(x) __context__(x,-1) +# define __cond_lock(x,c) ((c) ? ({ __acquire(x); 1; }) : 0) +#else /* __CHECKER__ */ +/* context/locking */ +# define __must_hold(x) +# define __acquires(x) +# define __releases(x) +# define __acquire(x) (void)0 +# define __release(x) (void)0 +# define __cond_lock(x,c) (c) +#endif /* __CHECKER__ */ + /* Compiler specific macros. */ #ifdef __GNUC__ #include <linux/compiler-gcc.h> diff --git a/tools/include/linux/overflow.h b/tools/include/linux/overflow.h index 8712ff70995f..dcb0c1bf6866 100644 --- a/tools/include/linux/overflow.h +++ b/tools/include/linux/overflow.h @@ -5,12 +5,9 @@ #include <linux/compiler.h> /* - * In the fallback code below, we need to compute the minimum and - * maximum values representable in a given type. These macros may also - * be useful elsewhere, so we provide them outside the - * COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW block. - * - * It would seem more obvious to do something like + * We need to compute the minimum and maximum values representable in a given + * type. These macros may also be useful elsewhere. It would seem more obvious + * to do something like: * * #define type_min(T) (T)(is_signed_type(T) ? (T)1 << (8*sizeof(T)-1) : 0) * #define type_max(T) (T)(is_signed_type(T) ? ((T)1 << (8*sizeof(T)-1)) - 1 : ~(T)0) @@ -36,8 +33,6 @@ #define type_max(T) ((T)((__type_half_max(T) - 1) + __type_half_max(T))) #define type_min(T) ((T)((T)-type_max(T)-(T)1)) - -#ifdef COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW /* * For simplicity and code hygiene, the fallback code below insists on * a, b and *d having the same type (similar to the min() and max() @@ -73,135 +68,6 @@ __builtin_mul_overflow(__a, __b, __d); \ }) -#else - - -/* Checking for unsigned overflow is relatively easy without causing UB. */ -#define __unsigned_add_overflow(a, b, d) ({ \ - typeof(a) __a = (a); \ - typeof(b) __b = (b); \ - typeof(d) __d = (d); \ - (void) (&__a == &__b); \ - (void) (&__a == __d); \ - *__d = __a + __b; \ - *__d < __a; \ -}) -#define __unsigned_sub_overflow(a, b, d) ({ \ - typeof(a) __a = (a); \ - typeof(b) __b = (b); \ - typeof(d) __d = (d); \ - (void) (&__a == &__b); \ - (void) (&__a == __d); \ - *__d = __a - __b; \ - __a < __b; \ -}) -/* - * If one of a or b is a compile-time constant, this avoids a division. - */ -#define __unsigned_mul_overflow(a, b, d) ({ \ - typeof(a) __a = (a); \ - typeof(b) __b = (b); \ - typeof(d) __d = (d); \ - (void) (&__a == &__b); \ - (void) (&__a == __d); \ - *__d = __a * __b; \ - __builtin_constant_p(__b) ? \ - __b > 0 && __a > type_max(typeof(__a)) / __b : \ - __a > 0 && __b > type_max(typeof(__b)) / __a; \ -}) - -/* - * For signed types, detecting overflow is much harder, especially if - * we want to avoid UB. But the interface of these macros is such that - * we must provide a result in *d, and in fact we must produce the - * result promised by gcc's builtins, which is simply the possibly - * wrapped-around value. Fortunately, we can just formally do the - * operations in the widest relevant unsigned type (u64) and then - * truncate the result - gcc is smart enough to generate the same code - * with and without the (u64) casts. - */ - -/* - * Adding two signed integers can overflow only if they have the same - * sign, and overflow has happened iff the result has the opposite - * sign. - */ -#define __signed_add_overflow(a, b, d) ({ \ - typeof(a) __a = (a); \ - typeof(b) __b = (b); \ - typeof(d) __d = (d); \ - (void) (&__a == &__b); \ - (void) (&__a == __d); \ - *__d = (u64)__a + (u64)__b; \ - (((~(__a ^ __b)) & (*__d ^ __a)) \ - & type_min(typeof(__a))) != 0; \ -}) - -/* - * Subtraction is similar, except that overflow can now happen only - * when the signs are opposite. In this case, overflow has happened if - * the result has the opposite sign of a. - */ -#define __signed_sub_overflow(a, b, d) ({ \ - typeof(a) __a = (a); \ - typeof(b) __b = (b); \ - typeof(d) __d = (d); \ - (void) (&__a == &__b); \ - (void) (&__a == __d); \ - *__d = (u64)__a - (u64)__b; \ - ((((__a ^ __b)) & (*__d ^ __a)) \ - & type_min(typeof(__a))) != 0; \ -}) - -/* - * Signed multiplication is rather hard. gcc always follows C99, so - * division is truncated towards 0. This means that we can write the - * overflow check like this: - * - * (a > 0 && (b > MAX/a || b < MIN/a)) || - * (a < -1 && (b > MIN/a || b < MAX/a) || - * (a == -1 && b == MIN) - * - * The redundant casts of -1 are to silence an annoying -Wtype-limits - * (included in -Wextra) warning: When the type is u8 or u16, the - * __b_c_e in check_mul_overflow obviously selects - * __unsigned_mul_overflow, but unfortunately gcc still parses this - * code and warns about the limited range of __b. - */ - -#define __signed_mul_overflow(a, b, d) ({ \ - typeof(a) __a = (a); \ - typeof(b) __b = (b); \ - typeof(d) __d = (d); \ - typeof(a) __tmax = type_max(typeof(a)); \ - typeof(a) __tmin = type_min(typeof(a)); \ - (void) (&__a == &__b); \ - (void) (&__a == __d); \ - *__d = (u64)__a * (u64)__b; \ - (__b > 0 && (__a > __tmax/__b || __a < __tmin/__b)) || \ - (__b < (typeof(__b))-1 && (__a > __tmin/__b || __a < __tmax/__b)) || \ - (__b == (typeof(__b))-1 && __a == __tmin); \ -}) - - -#define check_add_overflow(a, b, d) \ - __builtin_choose_expr(is_signed_type(typeof(a)), \ - __signed_add_overflow(a, b, d), \ - __unsigned_add_overflow(a, b, d)) - -#define check_sub_overflow(a, b, d) \ - __builtin_choose_expr(is_signed_type(typeof(a)), \ - __signed_sub_overflow(a, b, d), \ - __unsigned_sub_overflow(a, b, d)) - -#define check_mul_overflow(a, b, d) \ - __builtin_choose_expr(is_signed_type(typeof(a)), \ - __signed_mul_overflow(a, b, d), \ - __unsigned_mul_overflow(a, b, d)) - - -#endif /* COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW */ - /** * array_size() - Calculate size of 2-dimensional array. * diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h index a9d6fcd95f42..1c5fb86d455a 100644 --- a/tools/include/uapi/asm-generic/unistd.h +++ b/tools/include/uapi/asm-generic/unistd.h @@ -673,15 +673,15 @@ __SYSCALL(__NR_madvise, sys_madvise) #define __NR_remap_file_pages 234 __SYSCALL(__NR_remap_file_pages, sys_remap_file_pages) #define __NR_mbind 235 -__SC_COMP(__NR_mbind, sys_mbind, compat_sys_mbind) +__SYSCALL(__NR_mbind, sys_mbind) #define __NR_get_mempolicy 236 -__SC_COMP(__NR_get_mempolicy, sys_get_mempolicy, compat_sys_get_mempolicy) +__SYSCALL(__NR_get_mempolicy, sys_get_mempolicy) #define __NR_set_mempolicy 237 -__SC_COMP(__NR_set_mempolicy, sys_set_mempolicy, compat_sys_set_mempolicy) +__SYSCALL(__NR_set_mempolicy, sys_set_mempolicy) #define __NR_migrate_pages 238 -__SC_COMP(__NR_migrate_pages, sys_migrate_pages, compat_sys_migrate_pages) +__SYSCALL(__NR_migrate_pages, sys_migrate_pages) #define __NR_move_pages 239 -__SC_COMP(__NR_move_pages, sys_move_pages, compat_sys_move_pages) +__SYSCALL(__NR_move_pages, sys_move_pages) #endif #define __NR_rt_tgsigqueueinfo 240 @@ -877,9 +877,11 @@ __SYSCALL(__NR_landlock_restrict_self, sys_landlock_restrict_self) #define __NR_memfd_secret 447 __SYSCALL(__NR_memfd_secret, sys_memfd_secret) #endif +#define __NR_process_mrelease 448 +__SYSCALL(__NR_process_mrelease, sys_process_mrelease) #undef __NR_syscalls -#define __NR_syscalls 448 +#define __NR_syscalls 449 /* * 32 bit systems traditionally used different diff --git a/tools/include/uapi/drm/drm.h b/tools/include/uapi/drm/drm.h index d043752a74cf..3b810b53ba8b 100644 --- a/tools/include/uapi/drm/drm.h +++ b/tools/include/uapi/drm/drm.h @@ -635,8 +635,8 @@ struct drm_gem_open { /** * DRM_CAP_VBLANK_HIGH_CRTC * - * If set to 1, the kernel supports specifying a CRTC index in the high bits of - * &drm_wait_vblank_request.type. + * If set to 1, the kernel supports specifying a :ref:`CRTC index<crtc_index>` + * in the high bits of &drm_wait_vblank_request.type. * * Starting kernel version 2.6.39, this capability is always set to 1. */ @@ -1050,6 +1050,16 @@ extern "C" { #define DRM_IOCTL_MODE_GETPROPBLOB DRM_IOWR(0xAC, struct drm_mode_get_blob) #define DRM_IOCTL_MODE_GETFB DRM_IOWR(0xAD, struct drm_mode_fb_cmd) #define DRM_IOCTL_MODE_ADDFB DRM_IOWR(0xAE, struct drm_mode_fb_cmd) +/** + * DRM_IOCTL_MODE_RMFB - Remove a framebuffer. + * + * This removes a framebuffer previously added via ADDFB/ADDFB2. The IOCTL + * argument is a framebuffer object ID. + * + * Warning: removing a framebuffer currently in-use on an enabled plane will + * disable that plane. The CRTC the plane is linked to may also be disabled + * (depending on driver capabilities). + */ #define DRM_IOCTL_MODE_RMFB DRM_IOWR(0xAF, unsigned int) #define DRM_IOCTL_MODE_PAGE_FLIP DRM_IOWR(0xB0, struct drm_mode_crtc_page_flip) #define DRM_IOCTL_MODE_DIRTYFB DRM_IOWR(0xB1, struct drm_mode_fb_dirty_cmd) diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h index c2c7759b7d2e..bde5860b3686 100644 --- a/tools/include/uapi/drm/i915_drm.h +++ b/tools/include/uapi/drm/i915_drm.h @@ -572,6 +572,15 @@ typedef struct drm_i915_irq_wait { #define I915_SCHEDULER_CAP_PREEMPTION (1ul << 2) #define I915_SCHEDULER_CAP_SEMAPHORES (1ul << 3) #define I915_SCHEDULER_CAP_ENGINE_BUSY_STATS (1ul << 4) +/* + * Indicates the 2k user priority levels are statically mapped into 3 buckets as + * follows: + * + * -1k to -1 Low priority + * 0 Normal priority + * 1 to 1k Highest priority + */ +#define I915_SCHEDULER_CAP_STATIC_PRIORITY_MAP (1ul << 5) #define I915_PARAM_HUC_STATUS 42 @@ -674,6 +683,9 @@ typedef struct drm_i915_irq_wait { */ #define I915_PARAM_HAS_EXEC_TIMELINE_FENCES 55 +/* Query if the kernel supports the I915_USERPTR_PROBE flag. */ +#define I915_PARAM_HAS_USERPTR_PROBE 56 + /* Must be kept compact -- no holes and well documented */ typedef struct drm_i915_getparam { @@ -849,45 +861,113 @@ struct drm_i915_gem_mmap_gtt { __u64 offset; }; +/** + * struct drm_i915_gem_mmap_offset - Retrieve an offset so we can mmap this buffer object. + * + * This struct is passed as argument to the `DRM_IOCTL_I915_GEM_MMAP_OFFSET` ioctl, + * and is used to retrieve the fake offset to mmap an object specified by &handle. + * + * The legacy way of using `DRM_IOCTL_I915_GEM_MMAP` is removed on gen12+. + * `DRM_IOCTL_I915_GEM_MMAP_GTT` is an older supported alias to this struct, but will behave + * as setting the &extensions to 0, and &flags to `I915_MMAP_OFFSET_GTT`. + */ struct drm_i915_gem_mmap_offset { - /** Handle for the object being mapped. */ + /** @handle: Handle for the object being mapped. */ __u32 handle; + /** @pad: Must be zero */ __u32 pad; /** - * Fake offset to use for subsequent mmap call + * @offset: The fake offset to use for subsequent mmap call * * This is a fixed-size type for 32/64 compatibility. */ __u64 offset; /** - * Flags for extended behaviour. + * @flags: Flags for extended behaviour. + * + * It is mandatory that one of the `MMAP_OFFSET` types + * should be included: * - * It is mandatory that one of the MMAP_OFFSET types - * (GTT, WC, WB, UC, etc) should be included. + * - `I915_MMAP_OFFSET_GTT`: Use mmap with the object bound to GTT. (Write-Combined) + * - `I915_MMAP_OFFSET_WC`: Use Write-Combined caching. + * - `I915_MMAP_OFFSET_WB`: Use Write-Back caching. + * - `I915_MMAP_OFFSET_FIXED`: Use object placement to determine caching. + * + * On devices with local memory `I915_MMAP_OFFSET_FIXED` is the only valid + * type. On devices without local memory, this caching mode is invalid. + * + * As caching mode when specifying `I915_MMAP_OFFSET_FIXED`, WC or WB will + * be used, depending on the object placement on creation. WB will be used + * when the object can only exist in system memory, WC otherwise. */ __u64 flags; -#define I915_MMAP_OFFSET_GTT 0 -#define I915_MMAP_OFFSET_WC 1 -#define I915_MMAP_OFFSET_WB 2 -#define I915_MMAP_OFFSET_UC 3 - /* - * Zero-terminated chain of extensions. +#define I915_MMAP_OFFSET_GTT 0 +#define I915_MMAP_OFFSET_WC 1 +#define I915_MMAP_OFFSET_WB 2 +#define I915_MMAP_OFFSET_UC 3 +#define I915_MMAP_OFFSET_FIXED 4 + + /** + * @extensions: Zero-terminated chain of extensions. * * No current extensions defined; mbz. */ __u64 extensions; }; +/** + * struct drm_i915_gem_set_domain - Adjust the objects write or read domain, in + * preparation for accessing the pages via some CPU domain. + * + * Specifying a new write or read domain will flush the object out of the + * previous domain(if required), before then updating the objects domain + * tracking with the new domain. + * + * Note this might involve waiting for the object first if it is still active on + * the GPU. + * + * Supported values for @read_domains and @write_domain: + * + * - I915_GEM_DOMAIN_WC: Uncached write-combined domain + * - I915_GEM_DOMAIN_CPU: CPU cache domain + * - I915_GEM_DOMAIN_GTT: Mappable aperture domain + * + * All other domains are rejected. + * + * Note that for discrete, starting from DG1, this is no longer supported, and + * is instead rejected. On such platforms the CPU domain is effectively static, + * where we also only support a single &drm_i915_gem_mmap_offset cache mode, + * which can't be set explicitly and instead depends on the object placements, + * as per the below. + * + * Implicit caching rules, starting from DG1: + * + * - If any of the object placements (see &drm_i915_gem_create_ext_memory_regions) + * contain I915_MEMORY_CLASS_DEVICE then the object will be allocated and + * mapped as write-combined only. + * + * - Everything else is always allocated and mapped as write-back, with the + * guarantee that everything is also coherent with the GPU. + * + * Note that this is likely to change in the future again, where we might need + * more flexibility on future devices, so making this all explicit as part of a + * new &drm_i915_gem_create_ext extension is probable. + */ struct drm_i915_gem_set_domain { - /** Handle for the object */ + /** @handle: Handle for the object. */ __u32 handle; - /** New read domains */ + /** @read_domains: New read domains. */ __u32 read_domains; - /** New write domain */ + /** + * @write_domain: New write domain. + * + * Note that having something in the write domain implies it's in the + * read domain, and only that read domain. + */ __u32 write_domain; }; @@ -1348,12 +1428,11 @@ struct drm_i915_gem_busy { * reading from the object simultaneously. * * The value of each engine class is the same as specified in the - * I915_CONTEXT_SET_ENGINES parameter and via perf, i.e. + * I915_CONTEXT_PARAM_ENGINES context parameter and via perf, i.e. * I915_ENGINE_CLASS_RENDER, I915_ENGINE_CLASS_COPY, etc. - * reported as active itself. Some hardware may have parallel - * execution engines, e.g. multiple media engines, which are - * mapped to the same class identifier and so are not separately - * reported for busyness. + * Some hardware may have parallel execution engines, e.g. multiple + * media engines, which are mapped to the same class identifier and so + * are not separately reported for busyness. * * Caveat emptor: * Only the boolean result of this query is reliable; that is whether @@ -1364,43 +1443,79 @@ struct drm_i915_gem_busy { }; /** - * I915_CACHING_NONE - * - * GPU access is not coherent with cpu caches. Default for machines without an - * LLC. - */ -#define I915_CACHING_NONE 0 -/** - * I915_CACHING_CACHED - * - * GPU access is coherent with cpu caches and furthermore the data is cached in - * last-level caches shared between cpu cores and the gpu GT. Default on - * machines with HAS_LLC. + * struct drm_i915_gem_caching - Set or get the caching for given object + * handle. + * + * Allow userspace to control the GTT caching bits for a given object when the + * object is later mapped through the ppGTT(or GGTT on older platforms lacking + * ppGTT support, or if the object is used for scanout). Note that this might + * require unbinding the object from the GTT first, if its current caching value + * doesn't match. + * + * Note that this all changes on discrete platforms, starting from DG1, the + * set/get caching is no longer supported, and is now rejected. Instead the CPU + * caching attributes(WB vs WC) will become an immutable creation time property + * for the object, along with the GTT caching level. For now we don't expose any + * new uAPI for this, instead on DG1 this is all implicit, although this largely + * shouldn't matter since DG1 is coherent by default(without any way of + * controlling it). + * + * Implicit caching rules, starting from DG1: + * + * - If any of the object placements (see &drm_i915_gem_create_ext_memory_regions) + * contain I915_MEMORY_CLASS_DEVICE then the object will be allocated and + * mapped as write-combined only. + * + * - Everything else is always allocated and mapped as write-back, with the + * guarantee that everything is also coherent with the GPU. + * + * Note that this is likely to change in the future again, where we might need + * more flexibility on future devices, so making this all explicit as part of a + * new &drm_i915_gem_create_ext extension is probable. + * + * Side note: Part of the reason for this is that changing the at-allocation-time CPU + * caching attributes for the pages might be required(and is expensive) if we + * need to then CPU map the pages later with different caching attributes. This + * inconsistent caching behaviour, while supported on x86, is not universally + * supported on other architectures. So for simplicity we opt for setting + * everything at creation time, whilst also making it immutable, on discrete + * platforms. */ -#define I915_CACHING_CACHED 1 -/** - * I915_CACHING_DISPLAY - * - * Special GPU caching mode which is coherent with the scanout engines. - * Transparently falls back to I915_CACHING_NONE on platforms where no special - * cache mode (like write-through or gfdt flushing) is available. The kernel - * automatically sets this mode when using a buffer as a scanout target. - * Userspace can manually set this mode to avoid a costly stall and clflush in - * the hotpath of drawing the first frame. - */ -#define I915_CACHING_DISPLAY 2 - struct drm_i915_gem_caching { /** - * Handle of the buffer to set/get the caching level of. */ + * @handle: Handle of the buffer to set/get the caching level. + */ __u32 handle; /** - * Cacheing level to apply or return value + * @caching: The GTT caching level to apply or possible return value. + * + * The supported @caching values: * - * bits0-15 are for generic caching control (i.e. the above defined - * values). bits16-31 are reserved for platform-specific variations - * (e.g. l3$ caching on gen7). */ + * I915_CACHING_NONE: + * + * GPU access is not coherent with CPU caches. Default for machines + * without an LLC. This means manual flushing might be needed, if we + * want GPU access to be coherent. + * + * I915_CACHING_CACHED: + * + * GPU access is coherent with CPU caches and furthermore the data is + * cached in last-level caches shared between CPU cores and the GPU GT. + * + * I915_CACHING_DISPLAY: + * + * Special GPU caching mode which is coherent with the scanout engines. + * Transparently falls back to I915_CACHING_NONE on platforms where no + * special cache mode (like write-through or gfdt flushing) is + * available. The kernel automatically sets this mode when using a + * buffer as a scanout target. Userspace can manually set this mode to + * avoid a costly stall and clflush in the hotpath of drawing the first + * frame. + */ +#define I915_CACHING_NONE 0 +#define I915_CACHING_CACHED 1 +#define I915_CACHING_DISPLAY 2 __u32 caching; }; @@ -1639,6 +1754,10 @@ struct drm_i915_gem_context_param { __u32 size; __u64 param; #define I915_CONTEXT_PARAM_BAN_PERIOD 0x1 +/* I915_CONTEXT_PARAM_NO_ZEROMAP has been removed. On the off chance + * someone somewhere has attempted to use it, never re-use this context + * param number. + */ #define I915_CONTEXT_PARAM_NO_ZEROMAP 0x2 #define I915_CONTEXT_PARAM_GTT_SIZE 0x3 #define I915_CONTEXT_PARAM_NO_ERROR_CAPTURE 0x4 @@ -1723,24 +1842,8 @@ struct drm_i915_gem_context_param { */ #define I915_CONTEXT_PARAM_PERSISTENCE 0xb -/* - * I915_CONTEXT_PARAM_RINGSIZE: - * - * Sets the size of the CS ringbuffer to use for logical ring contexts. This - * applies a limit of how many batches can be queued to HW before the caller - * is blocked due to lack of space for more commands. - * - * Only reliably possible to be set prior to first use, i.e. during - * construction. At any later point, the current execution must be flushed as - * the ring can only be changed while the context is idle. Note, the ringsize - * can be specified as a constructor property, see - * I915_CONTEXT_CREATE_EXT_SETPARAM, but can also be set later if required. - * - * Only applies to the current set of engine and lost when those engines - * are replaced by a new mapping (see I915_CONTEXT_PARAM_ENGINES). - * - * Must be between 4 - 512 KiB, in intervals of page size [4 KiB]. - * Default is 16 KiB. +/* This API has been removed. On the off chance someone somewhere has + * attempted to use it, never re-use this context param number. */ #define I915_CONTEXT_PARAM_RINGSIZE 0xc /* Must be kept compact -- no holes and well documented */ @@ -1807,6 +1910,69 @@ struct drm_i915_gem_context_param_sseu { __u32 rsvd; }; +/** + * DOC: Virtual Engine uAPI + * + * Virtual engine is a concept where userspace is able to configure a set of + * physical engines, submit a batch buffer, and let the driver execute it on any + * engine from the set as it sees fit. + * + * This is primarily useful on parts which have multiple instances of a same + * class engine, like for example GT3+ Skylake parts with their two VCS engines. + * + * For instance userspace can enumerate all engines of a certain class using the + * previously described `Engine Discovery uAPI`_. After that userspace can + * create a GEM context with a placeholder slot for the virtual engine (using + * `I915_ENGINE_CLASS_INVALID` and `I915_ENGINE_CLASS_INVALID_NONE` for class + * and instance respectively) and finally using the + * `I915_CONTEXT_ENGINES_EXT_LOAD_BALANCE` extension place a virtual engine in + * the same reserved slot. + * + * Example of creating a virtual engine and submitting a batch buffer to it: + * + * .. code-block:: C + * + * I915_DEFINE_CONTEXT_ENGINES_LOAD_BALANCE(virtual, 2) = { + * .base.name = I915_CONTEXT_ENGINES_EXT_LOAD_BALANCE, + * .engine_index = 0, // Place this virtual engine into engine map slot 0 + * .num_siblings = 2, + * .engines = { { I915_ENGINE_CLASS_VIDEO, 0 }, + * { I915_ENGINE_CLASS_VIDEO, 1 }, }, + * }; + * I915_DEFINE_CONTEXT_PARAM_ENGINES(engines, 1) = { + * .engines = { { I915_ENGINE_CLASS_INVALID, + * I915_ENGINE_CLASS_INVALID_NONE } }, + * .extensions = to_user_pointer(&virtual), // Chains after load_balance extension + * }; + * struct drm_i915_gem_context_create_ext_setparam p_engines = { + * .base = { + * .name = I915_CONTEXT_CREATE_EXT_SETPARAM, + * }, + * .param = { + * .param = I915_CONTEXT_PARAM_ENGINES, + * .value = to_user_pointer(&engines), + * .size = sizeof(engines), + * }, + * }; + * struct drm_i915_gem_context_create_ext create = { + * .flags = I915_CONTEXT_CREATE_FLAGS_USE_EXTENSIONS, + * .extensions = to_user_pointer(&p_engines); + * }; + * + * ctx_id = gem_context_create_ext(drm_fd, &create); + * + * // Now we have created a GEM context with its engine map containing a + * // single virtual engine. Submissions to this slot can go either to + * // vcs0 or vcs1, depending on the load balancing algorithm used inside + * // the driver. The load balancing is dynamic from one batch buffer to + * // another and transparent to userspace. + * + * ... + * execbuf.rsvd1 = ctx_id; + * execbuf.flags = 0; // Submits to index 0 which is the virtual engine + * gem_execbuf(drm_fd, &execbuf); + */ + /* * i915_context_engines_load_balance: * @@ -1883,6 +2049,61 @@ struct i915_context_engines_bond { struct i915_engine_class_instance engines[N__]; \ } __attribute__((packed)) name__ +/** + * DOC: Context Engine Map uAPI + * + * Context engine map is a new way of addressing engines when submitting batch- + * buffers, replacing the existing way of using identifiers like `I915_EXEC_BLT` + * inside the flags field of `struct drm_i915_gem_execbuffer2`. + * + * To use it created GEM contexts need to be configured with a list of engines + * the user is intending to submit to. This is accomplished using the + * `I915_CONTEXT_PARAM_ENGINES` parameter and `struct + * i915_context_param_engines`. + * + * For such contexts the `I915_EXEC_RING_MASK` field becomes an index into the + * configured map. + * + * Example of creating such context and submitting against it: + * + * .. code-block:: C + * + * I915_DEFINE_CONTEXT_PARAM_ENGINES(engines, 2) = { + * .engines = { { I915_ENGINE_CLASS_RENDER, 0 }, + * { I915_ENGINE_CLASS_COPY, 0 } } + * }; + * struct drm_i915_gem_context_create_ext_setparam p_engines = { + * .base = { + * .name = I915_CONTEXT_CREATE_EXT_SETPARAM, + * }, + * .param = { + * .param = I915_CONTEXT_PARAM_ENGINES, + * .value = to_user_pointer(&engines), + * .size = sizeof(engines), + * }, + * }; + * struct drm_i915_gem_context_create_ext create = { + * .flags = I915_CONTEXT_CREATE_FLAGS_USE_EXTENSIONS, + * .extensions = to_user_pointer(&p_engines); + * }; + * + * ctx_id = gem_context_create_ext(drm_fd, &create); + * + * // We have now created a GEM context with two engines in the map: + * // Index 0 points to rcs0 while index 1 points to bcs0. Other engines + * // will not be accessible from this context. + * + * ... + * execbuf.rsvd1 = ctx_id; + * execbuf.flags = 0; // Submits to index 0, which is rcs0 for this context + * gem_execbuf(drm_fd, &execbuf); + * + * ... + * execbuf.rsvd1 = ctx_id; + * execbuf.flags = 1; // Submits to index 0, which is bcs0 for this context + * gem_execbuf(drm_fd, &execbuf); + */ + struct i915_context_param_engines { __u64 extensions; /* linked chain of extension blocks, 0 terminates */ #define I915_CONTEXT_ENGINES_EXT_LOAD_BALANCE 0 /* see i915_context_engines_load_balance */ @@ -1901,20 +2122,10 @@ struct drm_i915_gem_context_create_ext_setparam { struct drm_i915_gem_context_param param; }; -struct drm_i915_gem_context_create_ext_clone { +/* This API has been removed. On the off chance someone somewhere has + * attempted to use it, never re-use this extension number. + */ #define I915_CONTEXT_CREATE_EXT_CLONE 1 - struct i915_user_extension base; - __u32 clone_id; - __u32 flags; -#define I915_CONTEXT_CLONE_ENGINES (1u << 0) -#define I915_CONTEXT_CLONE_FLAGS (1u << 1) -#define I915_CONTEXT_CLONE_SCHEDATTR (1u << 2) -#define I915_CONTEXT_CLONE_SSEU (1u << 3) -#define I915_CONTEXT_CLONE_TIMELINE (1u << 4) -#define I915_CONTEXT_CLONE_VM (1u << 5) -#define I915_CONTEXT_CLONE_UNKNOWN -(I915_CONTEXT_CLONE_VM << 1) - __u64 rsvd; -}; struct drm_i915_gem_context_destroy { __u32 ctx_id; @@ -1986,14 +2197,69 @@ struct drm_i915_reset_stats { __u32 pad; }; +/** + * struct drm_i915_gem_userptr - Create GEM object from user allocated memory. + * + * Userptr objects have several restrictions on what ioctls can be used with the + * object handle. + */ struct drm_i915_gem_userptr { + /** + * @user_ptr: The pointer to the allocated memory. + * + * Needs to be aligned to PAGE_SIZE. + */ __u64 user_ptr; + + /** + * @user_size: + * + * The size in bytes for the allocated memory. This will also become the + * object size. + * + * Needs to be aligned to PAGE_SIZE, and should be at least PAGE_SIZE, + * or larger. + */ __u64 user_size; + + /** + * @flags: + * + * Supported flags: + * + * I915_USERPTR_READ_ONLY: + * + * Mark the object as readonly, this also means GPU access can only be + * readonly. This is only supported on HW which supports readonly access + * through the GTT. If the HW can't support readonly access, an error is + * returned. + * + * I915_USERPTR_PROBE: + * + * Probe the provided @user_ptr range and validate that the @user_ptr is + * indeed pointing to normal memory and that the range is also valid. + * For example if some garbage address is given to the kernel, then this + * should complain. + * + * Returns -EFAULT if the probe failed. + * + * Note that this doesn't populate the backing pages, and also doesn't + * guarantee that the object will remain valid when the object is + * eventually used. + * + * The kernel supports this feature if I915_PARAM_HAS_USERPTR_PROBE + * returns a non-zero value. + * + * I915_USERPTR_UNSYNCHRONIZED: + * + * NOT USED. Setting this flag will result in an error. + */ __u32 flags; #define I915_USERPTR_READ_ONLY 0x1 +#define I915_USERPTR_PROBE 0x2 #define I915_USERPTR_UNSYNCHRONIZED 0x80000000 /** - * Returned handle for the object. + * @handle: Returned handle for the object. * * Object handles are nonzero. */ @@ -2377,6 +2643,76 @@ struct drm_i915_query_topology_info { }; /** + * DOC: Engine Discovery uAPI + * + * Engine discovery uAPI is a way of enumerating physical engines present in a + * GPU associated with an open i915 DRM file descriptor. This supersedes the old + * way of using `DRM_IOCTL_I915_GETPARAM` and engine identifiers like + * `I915_PARAM_HAS_BLT`. + * + * The need for this interface came starting with Icelake and newer GPUs, which + * started to establish a pattern of having multiple engines of a same class, + * where not all instances were always completely functionally equivalent. + * + * Entry point for this uapi is `DRM_IOCTL_I915_QUERY` with the + * `DRM_I915_QUERY_ENGINE_INFO` as the queried item id. + * + * Example for getting the list of engines: + * + * .. code-block:: C + * + * struct drm_i915_query_engine_info *info; + * struct drm_i915_query_item item = { + * .query_id = DRM_I915_QUERY_ENGINE_INFO; + * }; + * struct drm_i915_query query = { + * .num_items = 1, + * .items_ptr = (uintptr_t)&item, + * }; + * int err, i; + * + * // First query the size of the blob we need, this needs to be large + * // enough to hold our array of engines. The kernel will fill out the + * // item.length for us, which is the number of bytes we need. + * // + * // Alternatively a large buffer can be allocated straight away enabling + * // querying in one pass, in which case item.length should contain the + * // length of the provided buffer. + * err = ioctl(fd, DRM_IOCTL_I915_QUERY, &query); + * if (err) ... + * + * info = calloc(1, item.length); + * // Now that we allocated the required number of bytes, we call the ioctl + * // again, this time with the data_ptr pointing to our newly allocated + * // blob, which the kernel can then populate with info on all engines. + * item.data_ptr = (uintptr_t)&info, + * + * err = ioctl(fd, DRM_IOCTL_I915_QUERY, &query); + * if (err) ... + * + * // We can now access each engine in the array + * for (i = 0; i < info->num_engines; i++) { + * struct drm_i915_engine_info einfo = info->engines[i]; + * u16 class = einfo.engine.class; + * u16 instance = einfo.engine.instance; + * .... + * } + * + * free(info); + * + * Each of the enumerated engines, apart from being defined by its class and + * instance (see `struct i915_engine_class_instance`), also can have flags and + * capabilities defined as documented in i915_drm.h. + * + * For instance video engines which support HEVC encoding will have the + * `I915_VIDEO_CLASS_CAPABILITY_HEVC` capability bit set. + * + * Engine discovery only fully comes to its own when combined with the new way + * of addressing engines when submitting batch buffers using contexts with + * engine maps configured. + */ + +/** * struct drm_i915_engine_info * * Describes one engine and it's capabilities as known to the driver. diff --git a/tools/include/uapi/linux/fs.h b/tools/include/uapi/linux/fs.h index 4c32e97dcdf0..bdf7b404b3e7 100644 --- a/tools/include/uapi/linux/fs.h +++ b/tools/include/uapi/linux/fs.h @@ -184,6 +184,7 @@ struct fsxattr { #define BLKSECDISCARD _IO(0x12,125) #define BLKROTATIONAL _IO(0x12,126) #define BLKZEROOUT _IO(0x12,127) +#define BLKGETDISKSEQ _IOR(0x12,128,__u64) /* * A jump here: 130-136 are reserved for zoned block devices * (see uapi/linux/blkzoned.h) diff --git a/tools/include/uapi/linux/in.h b/tools/include/uapi/linux/in.h index d1b327036ae4..14168225cecd 100644 --- a/tools/include/uapi/linux/in.h +++ b/tools/include/uapi/linux/in.h @@ -188,11 +188,22 @@ struct ip_mreq_source { }; struct ip_msfilter { - __be32 imsf_multiaddr; - __be32 imsf_interface; - __u32 imsf_fmode; - __u32 imsf_numsrc; - __be32 imsf_slist[1]; + union { + struct { + __be32 imsf_multiaddr_aux; + __be32 imsf_interface_aux; + __u32 imsf_fmode_aux; + __u32 imsf_numsrc_aux; + __be32 imsf_slist[1]; + }; + struct { + __be32 imsf_multiaddr; + __be32 imsf_interface; + __u32 imsf_fmode; + __u32 imsf_numsrc; + __be32 imsf_slist_flex[]; + }; + }; }; #define IP_MSFILTER_SIZE(numsrc) \ @@ -211,11 +222,22 @@ struct group_source_req { }; struct group_filter { - __u32 gf_interface; /* interface index */ - struct __kernel_sockaddr_storage gf_group; /* multicast address */ - __u32 gf_fmode; /* filter mode */ - __u32 gf_numsrc; /* number of sources */ - struct __kernel_sockaddr_storage gf_slist[1]; /* interface index */ + union { + struct { + __u32 gf_interface_aux; /* interface index */ + struct __kernel_sockaddr_storage gf_group_aux; /* multicast address */ + __u32 gf_fmode_aux; /* filter mode */ + __u32 gf_numsrc_aux; /* number of sources */ + struct __kernel_sockaddr_storage gf_slist[1]; /* interface index */ + }; + struct { + __u32 gf_interface; /* interface index */ + struct __kernel_sockaddr_storage gf_group; /* multicast address */ + __u32 gf_fmode; /* filter mode */ + __u32 gf_numsrc; /* number of sources */ + struct __kernel_sockaddr_storage gf_slist_flex[]; /* interface index */ + }; + }; }; #define GROUP_FILTER_SIZE(numsrc) \ diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index d9e4aabcb31a..a067410ebea5 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -1965,7 +1965,9 @@ struct kvm_stats_header { #define KVM_STATS_TYPE_CUMULATIVE (0x0 << KVM_STATS_TYPE_SHIFT) #define KVM_STATS_TYPE_INSTANT (0x1 << KVM_STATS_TYPE_SHIFT) #define KVM_STATS_TYPE_PEAK (0x2 << KVM_STATS_TYPE_SHIFT) -#define KVM_STATS_TYPE_MAX KVM_STATS_TYPE_PEAK +#define KVM_STATS_TYPE_LINEAR_HIST (0x3 << KVM_STATS_TYPE_SHIFT) +#define KVM_STATS_TYPE_LOG_HIST (0x4 << KVM_STATS_TYPE_SHIFT) +#define KVM_STATS_TYPE_MAX KVM_STATS_TYPE_LOG_HIST #define KVM_STATS_UNIT_SHIFT 4 #define KVM_STATS_UNIT_MASK (0xF << KVM_STATS_UNIT_SHIFT) @@ -1988,8 +1990,9 @@ struct kvm_stats_header { * @size: The number of data items for this stats. * Every data item is of type __u64. * @offset: The offset of the stats to the start of stat structure in - * struture kvm or kvm_vcpu. - * @unused: Unused field for future usage. Always 0 for now. + * structure kvm or kvm_vcpu. + * @bucket_size: A parameter value used for histogram stats. It is only used + * for linear histogram stats, specifying the size of the bucket; * @name: The name string for the stats. Its size is indicated by the * &kvm_stats_header->name_size. */ @@ -1998,7 +2001,7 @@ struct kvm_stats_desc { __s16 exponent; __u16 size; __u32 offset; - __u32 unused; + __u32 bucket_size; char name[]; }; diff --git a/tools/include/uapi/linux/mount.h b/tools/include/uapi/linux/mount.h index dd7a166fdf9c..4d93967f8aea 100644 --- a/tools/include/uapi/linux/mount.h +++ b/tools/include/uapi/linux/mount.h @@ -73,7 +73,8 @@ #define MOVE_MOUNT_T_SYMLINKS 0x00000010 /* Follow symlinks on to path */ #define MOVE_MOUNT_T_AUTOMOUNTS 0x00000020 /* Follow automounts on to path */ #define MOVE_MOUNT_T_EMPTY_PATH 0x00000040 /* Empty to path permitted */ -#define MOVE_MOUNT__MASK 0x00000077 +#define MOVE_MOUNT_SET_GROUP 0x00000100 /* Set sharing group instead */ +#define MOVE_MOUNT__MASK 0x00000177 /* * fsopen() flags. diff --git a/tools/include/uapi/linux/prctl.h b/tools/include/uapi/linux/prctl.h index 967d9c55323d..43bd7f713c39 100644 --- a/tools/include/uapi/linux/prctl.h +++ b/tools/include/uapi/linux/prctl.h @@ -213,6 +213,7 @@ struct prctl_mm_map { /* Speculation control variants */ # define PR_SPEC_STORE_BYPASS 0 # define PR_SPEC_INDIRECT_BRANCH 1 +# define PR_SPEC_L1D_FLUSH 2 /* Return and control values for PR_SET/GET_SPECULATION_CTRL */ # define PR_SPEC_NOT_AFFECTED 0 # define PR_SPEC_PRCTL (1UL << 0) @@ -234,14 +235,15 @@ struct prctl_mm_map { #define PR_GET_TAGGED_ADDR_CTRL 56 # define PR_TAGGED_ADDR_ENABLE (1UL << 0) /* MTE tag check fault modes */ -# define PR_MTE_TCF_SHIFT 1 -# define PR_MTE_TCF_NONE (0UL << PR_MTE_TCF_SHIFT) -# define PR_MTE_TCF_SYNC (1UL << PR_MTE_TCF_SHIFT) -# define PR_MTE_TCF_ASYNC (2UL << PR_MTE_TCF_SHIFT) -# define PR_MTE_TCF_MASK (3UL << PR_MTE_TCF_SHIFT) +# define PR_MTE_TCF_NONE 0 +# define PR_MTE_TCF_SYNC (1UL << 1) +# define PR_MTE_TCF_ASYNC (1UL << 2) +# define PR_MTE_TCF_MASK (PR_MTE_TCF_SYNC | PR_MTE_TCF_ASYNC) /* MTE tag inclusion mask */ # define PR_MTE_TAG_SHIFT 3 # define PR_MTE_TAG_MASK (0xffffUL << PR_MTE_TAG_SHIFT) +/* Unused; kept only for source compatibility */ +# define PR_MTE_TCF_SHIFT 1 /* Control reclaim behavior when allocating memory */ #define PR_SET_IO_FLUSHER 57 diff --git a/tools/include/uapi/sound/asound.h b/tools/include/uapi/sound/asound.h index d17c061950df..1d84ec9db93b 100644 --- a/tools/include/uapi/sound/asound.h +++ b/tools/include/uapi/sound/asound.h @@ -299,6 +299,7 @@ typedef int __bitwise snd_pcm_subformat_t; #define SNDRV_PCM_INFO_HAS_LINK_ABSOLUTE_ATIME 0x02000000 /* report absolute hardware link audio time, not reset on startup */ #define SNDRV_PCM_INFO_HAS_LINK_ESTIMATED_ATIME 0x04000000 /* report estimated link audio time */ #define SNDRV_PCM_INFO_HAS_LINK_SYNCHRONIZED_ATIME 0x08000000 /* report synchronized audio/system time */ +#define SNDRV_PCM_INFO_EXPLICIT_SYNC 0x10000000 /* needs explicit sync of pointers and data */ #define SNDRV_PCM_INFO_DRAIN_TRIGGER 0x40000000 /* internal kernel flag - trigger in drain */ #define SNDRV_PCM_INFO_FIFO_IN_FRAMES 0x80000000 /* internal kernel flag - FIFO size is in frames */ |