diff options
Diffstat (limited to 'include')
100 files changed, 1466 insertions, 537 deletions
diff --git a/include/asm-generic/bitops/__ffs.h b/include/asm-generic/bitops/__ffs.h index 2d08c750c8a7..3a899c626fdc 100644 --- a/include/asm-generic/bitops/__ffs.h +++ b/include/asm-generic/bitops/__ffs.h @@ -10,7 +10,7 @@ * * Undefined if no bit exists, so code should check against 0 first. */ -static __always_inline unsigned int generic___ffs(unsigned long word) +static __always_inline __attribute_const__ unsigned int generic___ffs(unsigned long word) { unsigned int num = 0; diff --git a/include/asm-generic/bitops/__fls.h b/include/asm-generic/bitops/__fls.h index e974ec932ec1..35f33780ca6c 100644 --- a/include/asm-generic/bitops/__fls.h +++ b/include/asm-generic/bitops/__fls.h @@ -10,7 +10,7 @@ * * Undefined if no set bit exists, so code should check against 0 first. */ -static __always_inline unsigned int generic___fls(unsigned long word) +static __always_inline __attribute_const__ unsigned int generic___fls(unsigned long word) { unsigned int num = BITS_PER_LONG - 1; diff --git a/include/asm-generic/bitops/builtin-__ffs.h b/include/asm-generic/bitops/builtin-__ffs.h index cf4b3d33bf96..d3c3f567045d 100644 --- a/include/asm-generic/bitops/builtin-__ffs.h +++ b/include/asm-generic/bitops/builtin-__ffs.h @@ -8,7 +8,7 @@ * * Undefined if no bit exists, so code should check against 0 first. */ -static __always_inline unsigned int __ffs(unsigned long word) +static __always_inline __attribute_const__ unsigned int __ffs(unsigned long word) { return __builtin_ctzl(word); } diff --git a/include/asm-generic/bitops/builtin-__fls.h b/include/asm-generic/bitops/builtin-__fls.h index 6d72fc8a5259..7770c4f1bfcd 100644 --- a/include/asm-generic/bitops/builtin-__fls.h +++ b/include/asm-generic/bitops/builtin-__fls.h @@ -8,7 +8,7 @@ * * Undefined if no set bit exists, so code should check against 0 first. */ -static __always_inline unsigned int __fls(unsigned long word) +static __always_inline __attribute_const__ unsigned int __fls(unsigned long word) { return (sizeof(word) * 8) - 1 - __builtin_clzl(word); } diff --git a/include/asm-generic/bitops/builtin-fls.h b/include/asm-generic/bitops/builtin-fls.h index c8455cc28841..be707da8c7cd 100644 --- a/include/asm-generic/bitops/builtin-fls.h +++ b/include/asm-generic/bitops/builtin-fls.h @@ -9,7 +9,7 @@ * This is defined the same way as ffs. * Note fls(0) = 0, fls(1) = 1, fls(0x80000000) = 32. */ -static __always_inline int fls(unsigned int x) +static __always_inline __attribute_const__ int fls(unsigned int x) { return x ? sizeof(x) * 8 - __builtin_clz(x) : 0; } diff --git a/include/asm-generic/bitops/ffs.h b/include/asm-generic/bitops/ffs.h index 4c43f242daeb..5ff2b7fbda6d 100644 --- a/include/asm-generic/bitops/ffs.h +++ b/include/asm-generic/bitops/ffs.h @@ -10,7 +10,7 @@ * the libc and compiler builtin ffs routines, therefore * differs in spirit from ffz (man ffs). */ -static inline int generic_ffs(int x) +static inline __attribute_const__ int generic_ffs(int x) { int r = 1; diff --git a/include/asm-generic/bitops/fls.h b/include/asm-generic/bitops/fls.h index 26f3ce1dd6e4..8eed3437edb9 100644 --- a/include/asm-generic/bitops/fls.h +++ b/include/asm-generic/bitops/fls.h @@ -10,7 +10,7 @@ * Note fls(0) = 0, fls(1) = 1, fls(0x80000000) = 32. */ -static __always_inline int generic_fls(unsigned int x) +static __always_inline __attribute_const__ int generic_fls(unsigned int x) { int r = 32; diff --git a/include/asm-generic/bitops/fls64.h b/include/asm-generic/bitops/fls64.h index 866f2b2304ff..b5f58dd261a3 100644 --- a/include/asm-generic/bitops/fls64.h +++ b/include/asm-generic/bitops/fls64.h @@ -16,7 +16,7 @@ * at position 64. */ #if BITS_PER_LONG == 32 -static __always_inline int fls64(__u64 x) +static __always_inline __attribute_const__ int fls64(__u64 x) { __u32 h = x >> 32; if (h) @@ -24,7 +24,7 @@ static __always_inline int fls64(__u64 x) return fls(x); } #elif BITS_PER_LONG == 64 -static __always_inline int fls64(__u64 x) +static __always_inline __attribute_const__ int fls64(__u64 x) { if (x == 0) return 0; diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index ae2d2359b79e..a65a87366c48 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -157,7 +157,7 @@ defined(CONFIG_AUTOFDO_CLANG) || defined(CONFIG_PROPELLER_CLANG) #define PATCHABLE_DISCARDS *(__patchable_function_entries) #endif -#ifndef CONFIG_ARCH_SUPPORTS_CFI_CLANG +#ifndef CONFIG_ARCH_SUPPORTS_CFI /* * Simply points to ftrace_stub, but with the proper protocol. * Defined by the linker script in linux/vmlinux.lds.h diff --git a/include/crypto/chacha.h b/include/crypto/chacha.h index 91f6b4cf561c..38e26dff27b0 100644 --- a/include/crypto/chacha.h +++ b/include/crypto/chacha.h @@ -45,19 +45,11 @@ static inline void chacha20_block(struct chacha_state *state, chacha_block_generic(state, out, 20); } -void hchacha_block_arch(const struct chacha_state *state, - u32 out[HCHACHA_OUT_WORDS], int nrounds); void hchacha_block_generic(const struct chacha_state *state, u32 out[HCHACHA_OUT_WORDS], int nrounds); -static inline void hchacha_block(const struct chacha_state *state, - u32 out[HCHACHA_OUT_WORDS], int nrounds) -{ - if (IS_ENABLED(CONFIG_CRYPTO_ARCH_HAVE_LIB_CHACHA)) - hchacha_block_arch(state, out, nrounds); - else - hchacha_block_generic(state, out, nrounds); -} +void hchacha_block(const struct chacha_state *state, + u32 out[HCHACHA_OUT_WORDS], int nrounds); enum chacha_constants { /* expand 32-byte k */ CHACHA_CONSTANT_EXPA = 0x61707865U, @@ -93,20 +85,8 @@ static inline void chacha_init(struct chacha_state *state, state->x[15] = get_unaligned_le32(iv + 12); } -void chacha_crypt_arch(struct chacha_state *state, u8 *dst, const u8 *src, - unsigned int bytes, int nrounds); -void chacha_crypt_generic(struct chacha_state *state, u8 *dst, const u8 *src, - unsigned int bytes, int nrounds); - -static inline void chacha_crypt(struct chacha_state *state, - u8 *dst, const u8 *src, - unsigned int bytes, int nrounds) -{ - if (IS_ENABLED(CONFIG_CRYPTO_ARCH_HAVE_LIB_CHACHA)) - chacha_crypt_arch(state, dst, src, bytes, nrounds); - else - chacha_crypt_generic(state, dst, src, bytes, nrounds); -} +void chacha_crypt(struct chacha_state *state, u8 *dst, const u8 *src, + unsigned int bytes, int nrounds); static inline void chacha20_crypt(struct chacha_state *state, u8 *dst, const u8 *src, unsigned int bytes) @@ -119,13 +99,4 @@ static inline void chacha_zeroize_state(struct chacha_state *state) memzero_explicit(state, sizeof(*state)); } -#if IS_ENABLED(CONFIG_CRYPTO_ARCH_HAVE_LIB_CHACHA) -bool chacha_is_arch_optimized(void); -#else -static inline bool chacha_is_arch_optimized(void) -{ - return false; -} -#endif - #endif /* _CRYPTO_CHACHA_H */ diff --git a/include/crypto/curve25519.h b/include/crypto/curve25519.h index ece6a9b5fafc..db63a5577c00 100644 --- a/include/crypto/curve25519.h +++ b/include/crypto/curve25519.h @@ -6,7 +6,6 @@ #ifndef CURVE25519_H #define CURVE25519_H -#include <crypto/algapi.h> // For crypto_memneq. #include <linux/types.h> #include <linux/random.h> @@ -14,49 +13,16 @@ enum curve25519_lengths { CURVE25519_KEY_SIZE = 32 }; -extern const u8 curve25519_null_point[]; -extern const u8 curve25519_base_point[]; - void curve25519_generic(u8 out[CURVE25519_KEY_SIZE], const u8 scalar[CURVE25519_KEY_SIZE], const u8 point[CURVE25519_KEY_SIZE]); -void curve25519_arch(u8 out[CURVE25519_KEY_SIZE], - const u8 scalar[CURVE25519_KEY_SIZE], - const u8 point[CURVE25519_KEY_SIZE]); - -void curve25519_base_arch(u8 pub[CURVE25519_KEY_SIZE], - const u8 secret[CURVE25519_KEY_SIZE]); - -bool curve25519_selftest(void); - -static inline bool __must_check curve25519(u8 mypublic[CURVE25519_KEY_SIZE], const u8 secret[CURVE25519_KEY_SIZE], - const u8 basepoint[CURVE25519_KEY_SIZE]) -{ - if (IS_ENABLED(CONFIG_CRYPTO_ARCH_HAVE_LIB_CURVE25519)) - curve25519_arch(mypublic, secret, basepoint); - else - curve25519_generic(mypublic, secret, basepoint); - return crypto_memneq(mypublic, curve25519_null_point, - CURVE25519_KEY_SIZE); -} - -static inline bool -__must_check curve25519_generate_public(u8 pub[CURVE25519_KEY_SIZE], - const u8 secret[CURVE25519_KEY_SIZE]) -{ - if (unlikely(!crypto_memneq(secret, curve25519_null_point, - CURVE25519_KEY_SIZE))) - return false; + const u8 basepoint[CURVE25519_KEY_SIZE]); - if (IS_ENABLED(CONFIG_CRYPTO_ARCH_HAVE_LIB_CURVE25519)) - curve25519_base_arch(pub, secret); - else - curve25519_generic(pub, secret, curve25519_base_point); - return crypto_memneq(pub, curve25519_null_point, CURVE25519_KEY_SIZE); -} +bool __must_check curve25519_generate_public(u8 pub[CURVE25519_KEY_SIZE], + const u8 secret[CURVE25519_KEY_SIZE]); static inline void curve25519_clamp_secret(u8 secret[CURVE25519_KEY_SIZE]) { diff --git a/include/crypto/if_alg.h b/include/crypto/if_alg.h index f7b3b93f3a49..107b797c33ec 100644 --- a/include/crypto/if_alg.h +++ b/include/crypto/if_alg.h @@ -135,6 +135,7 @@ struct af_alg_async_req { * SG? * @enc: Cryptographic operation to be performed when * recvmsg is invoked. + * @write: True if we are in the middle of a write. * @init: True if metadata has been sent. * @len: Length of memory allocated for this data structure. * @inflight: Non-zero when AIO requests are in flight. @@ -151,10 +152,11 @@ struct af_alg_ctx { size_t used; atomic_t rcvused; - bool more; - bool merge; - bool enc; - bool init; + bool more:1, + merge:1, + enc:1, + write:1, + init:1; unsigned int len; diff --git a/include/crypto/internal/blake2s.h b/include/crypto/internal/blake2s.h deleted file mode 100644 index 506d56530ca9..000000000000 --- a/include/crypto/internal/blake2s.h +++ /dev/null @@ -1,21 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 OR MIT */ -/* - * Helper functions for BLAKE2s implementations. - * Keep this in sync with the corresponding BLAKE2b header. - */ - -#ifndef _CRYPTO_INTERNAL_BLAKE2S_H -#define _CRYPTO_INTERNAL_BLAKE2S_H - -#include <crypto/blake2s.h> -#include <linux/string.h> - -void blake2s_compress_generic(struct blake2s_state *state, const u8 *block, - size_t nblocks, const u32 inc); - -void blake2s_compress(struct blake2s_state *state, const u8 *block, - size_t nblocks, const u32 inc); - -bool blake2s_selftest(void); - -#endif /* _CRYPTO_INTERNAL_BLAKE2S_H */ diff --git a/include/crypto/internal/poly1305.h b/include/crypto/internal/poly1305.h index c60315f47562..a72fff409ab8 100644 --- a/include/crypto/internal/poly1305.h +++ b/include/crypto/internal/poly1305.h @@ -30,12 +30,13 @@ void poly1305_core_blocks(struct poly1305_state *state, void poly1305_core_emit(const struct poly1305_state *state, const u32 nonce[4], void *dst); -void poly1305_block_init_arch(struct poly1305_block_state *state, - const u8 raw_key[POLY1305_BLOCK_SIZE]); -void poly1305_block_init_generic(struct poly1305_block_state *state, - const u8 raw_key[POLY1305_BLOCK_SIZE]); -void poly1305_blocks_arch(struct poly1305_block_state *state, const u8 *src, - unsigned int len, u32 padbit); +static inline void +poly1305_block_init_generic(struct poly1305_block_state *desc, + const u8 raw_key[POLY1305_BLOCK_SIZE]) +{ + poly1305_core_init(&desc->h); + poly1305_core_setkey(&desc->core_r, raw_key); +} static inline void poly1305_blocks_generic(struct poly1305_block_state *state, const u8 *src, unsigned int len, @@ -45,9 +46,6 @@ static inline void poly1305_blocks_generic(struct poly1305_block_state *state, len / POLY1305_BLOCK_SIZE, padbit); } -void poly1305_emit_arch(const struct poly1305_state *state, - u8 digest[POLY1305_DIGEST_SIZE], const u32 nonce[4]); - static inline void poly1305_emit_generic(const struct poly1305_state *state, u8 digest[POLY1305_DIGEST_SIZE], const u32 nonce[4]) diff --git a/include/crypto/md5.h b/include/crypto/md5.h index 28ee533a0507..c9aa5c3abc53 100644 --- a/include/crypto/md5.h +++ b/include/crypto/md5.h @@ -7,6 +7,7 @@ #define MD5_DIGEST_SIZE 16 #define MD5_HMAC_BLOCK_SIZE 64 +#define MD5_BLOCK_SIZE 64 #define MD5_BLOCK_WORDS 16 #define MD5_HASH_WORDS 4 #define MD5_STATE_SIZE 24 @@ -27,4 +28,182 @@ struct md5_state { u32 block[MD5_BLOCK_WORDS]; }; -#endif +/* State for the MD5 compression function */ +struct md5_block_state { + u32 h[MD5_HASH_WORDS]; +}; + +/** + * struct md5_ctx - Context for hashing a message with MD5 + * @state: the compression function state + * @bytecount: number of bytes processed so far + * @buf: partial block buffer; bytecount % MD5_BLOCK_SIZE bytes are valid + */ +struct md5_ctx { + struct md5_block_state state; + u64 bytecount; + u8 buf[MD5_BLOCK_SIZE] __aligned(__alignof__(__le64)); +}; + +/** + * md5_init() - Initialize an MD5 context for a new message + * @ctx: the context to initialize + * + * If you don't need incremental computation, consider md5() instead. + * + * Context: Any context. + */ +void md5_init(struct md5_ctx *ctx); + +/** + * md5_update() - Update an MD5 context with message data + * @ctx: the context to update; must have been initialized + * @data: the message data + * @len: the data length in bytes + * + * This can be called any number of times. + * + * Context: Any context. + */ +void md5_update(struct md5_ctx *ctx, const u8 *data, size_t len); + +/** + * md5_final() - Finish computing an MD5 message digest + * @ctx: the context to finalize; must have been initialized + * @out: (output) the resulting MD5 message digest + * + * After finishing, this zeroizes @ctx. So the caller does not need to do it. + * + * Context: Any context. + */ +void md5_final(struct md5_ctx *ctx, u8 out[MD5_DIGEST_SIZE]); + +/** + * md5() - Compute MD5 message digest in one shot + * @data: the message data + * @len: the data length in bytes + * @out: (output) the resulting MD5 message digest + * + * Context: Any context. + */ +void md5(const u8 *data, size_t len, u8 out[MD5_DIGEST_SIZE]); + +/** + * struct hmac_md5_key - Prepared key for HMAC-MD5 + * @istate: private + * @ostate: private + */ +struct hmac_md5_key { + struct md5_block_state istate; + struct md5_block_state ostate; +}; + +/** + * struct hmac_md5_ctx - Context for computing HMAC-MD5 of a message + * @hash_ctx: private + * @ostate: private + */ +struct hmac_md5_ctx { + struct md5_ctx hash_ctx; + struct md5_block_state ostate; +}; + +/** + * hmac_md5_preparekey() - Prepare a key for HMAC-MD5 + * @key: (output) the key structure to initialize + * @raw_key: the raw HMAC-MD5 key + * @raw_key_len: the key length in bytes. All key lengths are supported. + * + * Note: the caller is responsible for zeroizing both the struct hmac_md5_key + * and the raw key once they are no longer needed. + * + * Context: Any context. + */ +void hmac_md5_preparekey(struct hmac_md5_key *key, + const u8 *raw_key, size_t raw_key_len); + +/** + * hmac_md5_init() - Initialize an HMAC-MD5 context for a new message + * @ctx: (output) the HMAC context to initialize + * @key: the prepared HMAC key + * + * If you don't need incremental computation, consider hmac_md5() instead. + * + * Context: Any context. + */ +void hmac_md5_init(struct hmac_md5_ctx *ctx, const struct hmac_md5_key *key); + +/** + * hmac_md5_init_usingrawkey() - Initialize an HMAC-MD5 context for a new + * message, using a raw key + * @ctx: (output) the HMAC context to initialize + * @raw_key: the raw HMAC-MD5 key + * @raw_key_len: the key length in bytes. All key lengths are supported. + * + * If you don't need incremental computation, consider hmac_md5_usingrawkey() + * instead. + * + * Context: Any context. + */ +void hmac_md5_init_usingrawkey(struct hmac_md5_ctx *ctx, + const u8 *raw_key, size_t raw_key_len); + +/** + * hmac_md5_update() - Update an HMAC-MD5 context with message data + * @ctx: the HMAC context to update; must have been initialized + * @data: the message data + * @data_len: the data length in bytes + * + * This can be called any number of times. + * + * Context: Any context. + */ +static inline void hmac_md5_update(struct hmac_md5_ctx *ctx, + const u8 *data, size_t data_len) +{ + md5_update(&ctx->hash_ctx, data, data_len); +} + +/** + * hmac_md5_final() - Finish computing an HMAC-MD5 value + * @ctx: the HMAC context to finalize; must have been initialized + * @out: (output) the resulting HMAC-MD5 value + * + * After finishing, this zeroizes @ctx. So the caller does not need to do it. + * + * Context: Any context. + */ +void hmac_md5_final(struct hmac_md5_ctx *ctx, u8 out[MD5_DIGEST_SIZE]); + +/** + * hmac_md5() - Compute HMAC-MD5 in one shot, using a prepared key + * @key: the prepared HMAC key + * @data: the message data + * @data_len: the data length in bytes + * @out: (output) the resulting HMAC-MD5 value + * + * If you're using the key only once, consider using hmac_md5_usingrawkey(). + * + * Context: Any context. + */ +void hmac_md5(const struct hmac_md5_key *key, + const u8 *data, size_t data_len, u8 out[MD5_DIGEST_SIZE]); + +/** + * hmac_md5_usingrawkey() - Compute HMAC-MD5 in one shot, using a raw key + * @raw_key: the raw HMAC-MD5 key + * @raw_key_len: the key length in bytes. All key lengths are supported. + * @data: the message data + * @data_len: the data length in bytes + * @out: (output) the resulting HMAC-MD5 value + * + * If you're using the key multiple times, prefer to use hmac_md5_preparekey() + * followed by multiple calls to hmac_md5() instead. + * + * Context: Any context. + */ +void hmac_md5_usingrawkey(const u8 *raw_key, size_t raw_key_len, + const u8 *data, size_t data_len, + u8 out[MD5_DIGEST_SIZE]); + +#endif /* _CRYPTO_MD5_H */ diff --git a/include/crypto/poly1305.h b/include/crypto/poly1305.h index e54abda8cfe9..d4daeec8da19 100644 --- a/include/crypto/poly1305.h +++ b/include/crypto/poly1305.h @@ -64,13 +64,4 @@ void poly1305_update(struct poly1305_desc_ctx *desc, const u8 *src, unsigned int nbytes); void poly1305_final(struct poly1305_desc_ctx *desc, u8 *digest); -#if IS_ENABLED(CONFIG_CRYPTO_ARCH_HAVE_LIB_POLY1305) -bool poly1305_is_arch_optimized(void); -#else -static inline bool poly1305_is_arch_optimized(void) -{ - return false; -} -#endif - #endif diff --git a/include/crypto/sha2.h b/include/crypto/sha2.h index 15e461e568cc..e5dafb935cc8 100644 --- a/include/crypto/sha2.h +++ b/include/crypto/sha2.h @@ -376,6 +376,34 @@ void sha256_final(struct sha256_ctx *ctx, u8 out[SHA256_DIGEST_SIZE]); void sha256(const u8 *data, size_t len, u8 out[SHA256_DIGEST_SIZE]); /** + * sha256_finup_2x() - Compute two SHA-256 digests from a common initial + * context. On some CPUs, this is faster than sequentially + * computing each digest. + * @ctx: an optional initial context, which may have already processed data. If + * NULL, a default initial context is used (equivalent to sha256_init()). + * @data1: data for the first message + * @data2: data for the second message + * @len: the length of each of @data1 and @data2, in bytes + * @out1: (output) the first SHA-256 message digest + * @out2: (output) the second SHA-256 message digest + * + * Context: Any context. + */ +void sha256_finup_2x(const struct sha256_ctx *ctx, const u8 *data1, + const u8 *data2, size_t len, u8 out1[SHA256_DIGEST_SIZE], + u8 out2[SHA256_DIGEST_SIZE]); + +/** + * sha256_finup_2x_is_optimized() - Check if sha256_finup_2x() is using a real + * interleaved implementation, as opposed to a + * sequential fallback + * @return: true if optimized + * + * Context: Any context. + */ +bool sha256_finup_2x_is_optimized(void); + +/** * struct hmac_sha256_key - Prepared key for HMAC-SHA256 * @key: private */ diff --git a/include/kunit/run-in-irq-context.h b/include/kunit/run-in-irq-context.h new file mode 100644 index 000000000000..108e96433ea4 --- /dev/null +++ b/include/kunit/run-in-irq-context.h @@ -0,0 +1,129 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Helper function for testing code in interrupt contexts + * + * Copyright 2025 Google LLC + */ +#ifndef _KUNIT_RUN_IN_IRQ_CONTEXT_H +#define _KUNIT_RUN_IN_IRQ_CONTEXT_H + +#include <kunit/test.h> +#include <linux/timekeeping.h> +#include <linux/hrtimer.h> +#include <linux/workqueue.h> + +#define KUNIT_IRQ_TEST_HRTIMER_INTERVAL us_to_ktime(5) + +struct kunit_irq_test_state { + bool (*func)(void *test_specific_state); + void *test_specific_state; + bool task_func_reported_failure; + bool hardirq_func_reported_failure; + bool softirq_func_reported_failure; + unsigned long hardirq_func_calls; + unsigned long softirq_func_calls; + struct hrtimer timer; + struct work_struct bh_work; +}; + +static enum hrtimer_restart kunit_irq_test_timer_func(struct hrtimer *timer) +{ + struct kunit_irq_test_state *state = + container_of(timer, typeof(*state), timer); + + WARN_ON_ONCE(!in_hardirq()); + state->hardirq_func_calls++; + + if (!state->func(state->test_specific_state)) + state->hardirq_func_reported_failure = true; + + hrtimer_forward_now(&state->timer, KUNIT_IRQ_TEST_HRTIMER_INTERVAL); + queue_work(system_bh_wq, &state->bh_work); + return HRTIMER_RESTART; +} + +static void kunit_irq_test_bh_work_func(struct work_struct *work) +{ + struct kunit_irq_test_state *state = + container_of(work, typeof(*state), bh_work); + + WARN_ON_ONCE(!in_serving_softirq()); + state->softirq_func_calls++; + + if (!state->func(state->test_specific_state)) + state->softirq_func_reported_failure = true; +} + +/* + * Helper function which repeatedly runs the given @func in task, softirq, and + * hardirq context concurrently, and reports a failure to KUnit if any + * invocation of @func in any context returns false. @func is passed + * @test_specific_state as its argument. At most 3 invocations of @func will + * run concurrently: one in each of task, softirq, and hardirq context. + * + * The main purpose of this interrupt context testing is to validate fallback + * code paths that run in contexts where the normal code path cannot be used, + * typically due to the FPU or vector registers already being in-use in kernel + * mode. These code paths aren't covered when the test code is executed only by + * the KUnit test runner thread in task context. The reason for the concurrency + * is because merely using hardirq context is not sufficient to reach a fallback + * code path on some architectures; the hardirq actually has to occur while the + * FPU or vector unit was already in-use in kernel mode. + * + * Another purpose of this testing is to detect issues with the architecture's + * irq_fpu_usable() and kernel_fpu_begin/end() or equivalent functions, + * especially in softirq context when the softirq may have interrupted a task + * already using kernel-mode FPU or vector (if the arch didn't prevent that). + * Crypto functions are often executed in softirqs, so this is important. + */ +static inline void kunit_run_irq_test(struct kunit *test, bool (*func)(void *), + int max_iterations, + void *test_specific_state) +{ + struct kunit_irq_test_state state = { + .func = func, + .test_specific_state = test_specific_state, + }; + unsigned long end_jiffies; + + /* + * Set up a hrtimer (the way we access hardirq context) and a work + * struct for the BH workqueue (the way we access softirq context). + */ + hrtimer_setup_on_stack(&state.timer, kunit_irq_test_timer_func, + CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD); + INIT_WORK_ONSTACK(&state.bh_work, kunit_irq_test_bh_work_func); + + /* Run for up to max_iterations or 1 second, whichever comes first. */ + end_jiffies = jiffies + HZ; + hrtimer_start(&state.timer, KUNIT_IRQ_TEST_HRTIMER_INTERVAL, + HRTIMER_MODE_REL_HARD); + for (int i = 0; i < max_iterations && !time_after(jiffies, end_jiffies); + i++) { + if (!func(test_specific_state)) + state.task_func_reported_failure = true; + } + + /* Cancel the timer and work. */ + hrtimer_cancel(&state.timer); + flush_work(&state.bh_work); + + /* Sanity check: the timer and BH functions should have been run. */ + KUNIT_EXPECT_GT_MSG(test, state.hardirq_func_calls, 0, + "Timer function was not called"); + KUNIT_EXPECT_GT_MSG(test, state.softirq_func_calls, 0, + "BH work function was not called"); + + /* Check for incorrect hash values reported from any context. */ + KUNIT_EXPECT_FALSE_MSG( + test, state.task_func_reported_failure, + "Incorrect hash values reported from task context"); + KUNIT_EXPECT_FALSE_MSG( + test, state.hardirq_func_reported_failure, + "Incorrect hash values reported from hardirq context"); + KUNIT_EXPECT_FALSE_MSG( + test, state.softirq_func_reported_failure, + "Incorrect hash values reported from softirq context"); +} + +#endif /* _KUNIT_RUN_IN_IRQ_CONTEXT_H */ diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h index 404883c7af6e..4000ff16f295 100644 --- a/include/kvm/arm_vgic.h +++ b/include/kvm/arm_vgic.h @@ -8,8 +8,8 @@ #include <linux/bits.h> #include <linux/kvm.h> #include <linux/irqreturn.h> -#include <linux/kref.h> #include <linux/mutex.h> +#include <linux/refcount.h> #include <linux/spinlock.h> #include <linux/static_key.h> #include <linux/types.h> @@ -139,10 +139,13 @@ struct vgic_irq { bool pending_latch; /* The pending latch state used to calculate * the pending state for both level * and edge triggered IRQs. */ - bool active; /* not used for LPIs */ + bool active; + bool pending_release; /* Used for LPIs only, unreferenced IRQ + * pending a release */ + bool enabled; bool hw; /* Tied to HW IRQ */ - struct kref refcount; /* Used for LPIs */ + refcount_t refcount; /* Used for LPIs */ u32 hwintid; /* HW INTID number */ unsigned int host_irq; /* linux irq corresponding to hwintid */ union { diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h index 2ad261082bba..c5c9d89c73ed 100644 --- a/include/linux/backing-dev-defs.h +++ b/include/linux/backing-dev-defs.h @@ -152,6 +152,10 @@ struct bdi_writeback { struct list_head blkcg_node; /* anchored at blkcg->cgwb_list */ struct list_head b_attached; /* attached inodes, protected by list_lock */ struct list_head offline_node; /* anchored at offline_cgwbs */ + struct work_struct switch_work; /* work used to perform inode switching + * to this wb */ + struct llist_head switch_wbs_ctxs; /* queued contexts for + * writeback switching */ union { struct work_struct release_work; diff --git a/include/linux/bitops.h b/include/linux/bitops.h index 9be2d50da09a..ea7898cc5903 100644 --- a/include/linux/bitops.h +++ b/include/linux/bitops.h @@ -267,7 +267,7 @@ static inline int parity8(u8 val) * The result is not defined if no bits are set, so check that @word * is non-zero before calling this. */ -static inline unsigned int __ffs64(u64 word) +static inline __attribute_const__ unsigned int __ffs64(u64 word) { #if BITS_PER_LONG == 32 if (((u32)word) == 0UL) diff --git a/include/linux/cfi.h b/include/linux/cfi.h index 52a98886a455..1fd22ea6eba4 100644 --- a/include/linux/cfi.h +++ b/include/linux/cfi.h @@ -11,7 +11,7 @@ #include <linux/module.h> #include <asm/cfi.h> -#ifdef CONFIG_CFI_CLANG +#ifdef CONFIG_CFI extern bool cfi_warn; enum bug_trap_type report_cfi_failure(struct pt_regs *regs, unsigned long addr, @@ -52,7 +52,7 @@ static inline u32 cfi_get_func_hash(void *func) extern u32 cfi_bpf_hash; extern u32 cfi_bpf_subprog_hash; -#else /* CONFIG_CFI_CLANG */ +#else /* CONFIG_CFI */ static inline int cfi_get_offset(void) { return 0; } static inline u32 cfi_get_func_hash(void *func) { return 0; } @@ -60,7 +60,7 @@ static inline u32 cfi_get_func_hash(void *func) { return 0; } #define cfi_bpf_hash 0U #define cfi_bpf_subprog_hash 0U -#endif /* CONFIG_CFI_CLANG */ +#endif /* CONFIG_CFI */ #ifdef CONFIG_ARCH_USES_CFI_TRAPS bool is_cfi_trap(unsigned long addr); diff --git a/include/linux/cfi_types.h b/include/linux/cfi_types.h index 685f7181780f..a86af9bc8bdc 100644 --- a/include/linux/cfi_types.h +++ b/include/linux/cfi_types.h @@ -8,7 +8,7 @@ #ifdef __ASSEMBLY__ #include <linux/linkage.h> -#ifdef CONFIG_CFI_CLANG +#ifdef CONFIG_CFI /* * Use the __kcfi_typeid_<function> type identifier symbol to * annotate indirectly called assembly functions. The compiler emits @@ -29,12 +29,12 @@ #define SYM_TYPED_START(name, linkage, align...) \ SYM_TYPED_ENTRY(name, linkage, align) -#else /* CONFIG_CFI_CLANG */ +#else /* CONFIG_CFI */ #define SYM_TYPED_START(name, linkage, align...) \ SYM_START(name, linkage, align) -#endif /* CONFIG_CFI_CLANG */ +#endif /* CONFIG_CFI */ #ifndef SYM_TYPED_FUNC_START #define SYM_TYPED_FUNC_START(name) \ @@ -43,7 +43,7 @@ #else /* __ASSEMBLY__ */ -#ifdef CONFIG_CFI_CLANG +#ifdef CONFIG_CFI #define DEFINE_CFI_TYPE(name, func) \ /* \ * Force a reference to the function so the compiler generates \ diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index b18fb5fcb38e..bab98357960d 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -27,6 +27,7 @@ #include <linux/kernel_stat.h> #include <linux/cgroup-defs.h> +#include <linux/cgroup_namespace.h> struct kernel_clone_args; @@ -783,52 +784,6 @@ static inline void cgroup_sk_free(struct sock_cgroup_data *skcd) {} #endif /* CONFIG_CGROUP_DATA */ -struct cgroup_namespace { - struct ns_common ns; - struct user_namespace *user_ns; - struct ucounts *ucounts; - struct css_set *root_cset; -}; - -extern struct cgroup_namespace init_cgroup_ns; - -#ifdef CONFIG_CGROUPS - -void free_cgroup_ns(struct cgroup_namespace *ns); - -struct cgroup_namespace *copy_cgroup_ns(unsigned long flags, - struct user_namespace *user_ns, - struct cgroup_namespace *old_ns); - -int cgroup_path_ns(struct cgroup *cgrp, char *buf, size_t buflen, - struct cgroup_namespace *ns); - -static inline void get_cgroup_ns(struct cgroup_namespace *ns) -{ - refcount_inc(&ns->ns.count); -} - -static inline void put_cgroup_ns(struct cgroup_namespace *ns) -{ - if (refcount_dec_and_test(&ns->ns.count)) - free_cgroup_ns(ns); -} - -#else /* !CONFIG_CGROUPS */ - -static inline void free_cgroup_ns(struct cgroup_namespace *ns) { } -static inline struct cgroup_namespace * -copy_cgroup_ns(unsigned long flags, struct user_namespace *user_ns, - struct cgroup_namespace *old_ns) -{ - return old_ns; -} - -static inline void get_cgroup_ns(struct cgroup_namespace *ns) { } -static inline void put_cgroup_ns(struct cgroup_namespace *ns) { } - -#endif /* !CONFIG_CGROUPS */ - #ifdef CONFIG_CGROUPS void cgroup_enter_frozen(void); diff --git a/include/linux/cgroup_namespace.h b/include/linux/cgroup_namespace.h new file mode 100644 index 000000000000..78a8418558a4 --- /dev/null +++ b/include/linux/cgroup_namespace.h @@ -0,0 +1,58 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_CGROUP_NAMESPACE_H +#define _LINUX_CGROUP_NAMESPACE_H + +#include <linux/ns_common.h> + +struct cgroup_namespace { + struct ns_common ns; + struct user_namespace *user_ns; + struct ucounts *ucounts; + struct css_set *root_cset; +}; + +extern struct cgroup_namespace init_cgroup_ns; + +#ifdef CONFIG_CGROUPS + +static inline struct cgroup_namespace *to_cg_ns(struct ns_common *ns) +{ + return container_of(ns, struct cgroup_namespace, ns); +} + +void free_cgroup_ns(struct cgroup_namespace *ns); + +struct cgroup_namespace *copy_cgroup_ns(u64 flags, + struct user_namespace *user_ns, + struct cgroup_namespace *old_ns); + +int cgroup_path_ns(struct cgroup *cgrp, char *buf, size_t buflen, + struct cgroup_namespace *ns); + +static inline void get_cgroup_ns(struct cgroup_namespace *ns) +{ + ns_ref_inc(ns); +} + +static inline void put_cgroup_ns(struct cgroup_namespace *ns) +{ + if (ns_ref_put(ns)) + free_cgroup_ns(ns); +} + +#else /* !CONFIG_CGROUPS */ + +static inline void free_cgroup_ns(struct cgroup_namespace *ns) { } +static inline struct cgroup_namespace * +copy_cgroup_ns(u64 flags, struct user_namespace *user_ns, + struct cgroup_namespace *old_ns) +{ + return old_ns; +} + +static inline void get_cgroup_ns(struct cgroup_namespace *ns) { } +static inline void put_cgroup_ns(struct cgroup_namespace *ns) { } + +#endif /* !CONFIG_CGROUPS */ + +#endif /* _LINUX_CGROUP_NAMESPACE_H */ diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h index fa4ffe037bc7..8720a0705900 100644 --- a/include/linux/compiler-clang.h +++ b/include/linux/compiler-clang.h @@ -18,23 +18,42 @@ #define KASAN_ABI_VERSION 5 /* + * Clang 22 added preprocessor macros to match GCC, in hopes of eventually + * dropping __has_feature support for sanitizers: + * https://github.com/llvm/llvm-project/commit/568c23bbd3303518c5056d7f03444dae4fdc8a9c + * Create these macros for older versions of clang so that it is easy to clean + * up once the minimum supported version of LLVM for building the kernel always + * creates these macros. + * * Note: Checking __has_feature(*_sanitizer) is only true if the feature is * enabled. Therefore it is not required to additionally check defined(CONFIG_*) * to avoid adding redundant attributes in other configurations. */ +#if __has_feature(address_sanitizer) && !defined(__SANITIZE_ADDRESS__) +#define __SANITIZE_ADDRESS__ +#endif +#if __has_feature(hwaddress_sanitizer) && !defined(__SANITIZE_HWADDRESS__) +#define __SANITIZE_HWADDRESS__ +#endif +#if __has_feature(thread_sanitizer) && !defined(__SANITIZE_THREAD__) +#define __SANITIZE_THREAD__ +#endif -#if __has_feature(address_sanitizer) || __has_feature(hwaddress_sanitizer) -/* Emulate GCC's __SANITIZE_ADDRESS__ flag */ +/* + * Treat __SANITIZE_HWADDRESS__ the same as __SANITIZE_ADDRESS__ in the kernel. + */ +#ifdef __SANITIZE_HWADDRESS__ #define __SANITIZE_ADDRESS__ +#endif + +#ifdef __SANITIZE_ADDRESS__ #define __no_sanitize_address \ __attribute__((no_sanitize("address", "hwaddress"))) #else #define __no_sanitize_address #endif -#if __has_feature(thread_sanitizer) -/* emulate gcc's __SANITIZE_THREAD__ flag */ -#define __SANITIZE_THREAD__ +#ifdef __SANITIZE_THREAD__ #define __no_sanitize_thread \ __attribute__((no_sanitize("thread"))) #else diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 64ff73c533e5..5b45ea7dff3e 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -248,7 +248,7 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, #endif /* __KERNEL__ */ -#if defined(CONFIG_CFI_CLANG) && !defined(__DISABLE_EXPORTS) && !defined(BUILD_VDSO) +#if defined(CONFIG_CFI) && !defined(__DISABLE_EXPORTS) && !defined(BUILD_VDSO) /* * Force a reference to the external symbol so the compiler generates * __kcfi_typid. diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index 16755431fc11..2f3e80bf9f35 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -330,6 +330,29 @@ struct ftrace_likely_data { #endif /* + * The assume attribute is used to indicate that a certain condition is + * assumed to be true. If this condition is violated at runtime, the behavior + * is undefined. Compilers may or may not use this indication to generate + * optimized code. + * + * Note that the clang documentation states that optimizers may react + * differently to this attribute, and this may even have a negative + * performance impact. Therefore this attribute should be used with care. + * + * Optional: only supported since gcc >= 13 + * Optional: only supported since clang >= 19 + * + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Statement-Attributes.html#index-assume-statement-attribute + * clang: https://clang.llvm.org/docs/AttributeReference.html#id13 + * + */ +#ifdef CONFIG_CC_HAS_ASSUME +# define __assume(expr) __attribute__((__assume__(expr))) +#else +# define __assume(expr) +#endif + +/* * Optional: only supported since gcc >= 15 * Optional: only supported since clang >= 18 * diff --git a/include/linux/cpu.h b/include/linux/cpu.h index b91b993f58ee..487b3bf2e1ea 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -83,6 +83,7 @@ extern ssize_t cpu_show_old_microcode(struct device *dev, extern ssize_t cpu_show_indirect_target_selection(struct device *dev, struct device_attribute *attr, char *buf); extern ssize_t cpu_show_tsa(struct device *dev, struct device_attribute *attr, char *buf); +extern ssize_t cpu_show_vmscape(struct device *dev, struct device_attribute *attr, char *buf); extern __printf(4, 5) struct device *cpu_device_create(struct device *parent, void *drvdata, diff --git a/include/linux/cred.h b/include/linux/cred.h index a102a10f833f..89ae50ad2ace 100644 --- a/include/linux/cred.h +++ b/include/linux/cred.h @@ -148,7 +148,7 @@ struct cred { extern void __put_cred(struct cred *); extern void exit_creds(struct task_struct *); -extern int copy_creds(struct task_struct *, unsigned long); +extern int copy_creds(struct task_struct *, u64); extern const struct cred *get_task_cred(struct task_struct *); extern struct cred *cred_alloc_blank(void); extern struct cred *prepare_creds(void); diff --git a/include/linux/damon.h b/include/linux/damon.h index f13664c62ddd..9e62b2a85538 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -636,6 +636,7 @@ struct damon_operations { * @data: Data that will be passed to @fn. * @repeat: Repeat invocations. * @return_code: Return code from @fn invocation. + * @dealloc_on_cancel: De-allocate when canceled. * * Control damon_call(), which requests specific kdamond to invoke a given * function. Refer to damon_call() for more details. @@ -645,6 +646,7 @@ struct damon_call_control { void *data; bool repeat; int return_code; + bool dealloc_on_cancel; /* private: internal use only */ /* informs if the kdamond finished handling of the request */ struct completion completion; diff --git a/include/linux/dlm.h b/include/linux/dlm.h index bacda9898f2b..7e7b45b0d097 100644 --- a/include/linux/dlm.h +++ b/include/linux/dlm.h @@ -88,12 +88,43 @@ int dlm_new_lockspace(const char *name, const char *cluster, int *ops_result, dlm_lockspace_t **lockspace); /* + * dlm_release_lockspace() release_option values: + * + * DLM_RELEASE_NO_LOCKS returns -EBUSY if any locks (lkb's) + * exist in the local lockspace. + * + * DLM_RELEASE_UNUSED previous value that is no longer used. + * + * DLM_RELEASE_NORMAL releases the lockspace regardless of any + * locks managed in the local lockspace. + * + * DLM_RELEASE_NO_EVENT release the lockspace regardless of any + * locks managed in the local lockspace, and does not submit + * a leave event to the cluster manager, so other nodes will + * not be notified that the node should be removed from the + * list of lockspace members. + * + * DLM_RELEASE_RECOVER like DLM_RELEASE_NORMAL, but the remaining + * nodes will handle the removal of the node as if the node + * had failed, e.g. the recover_slot() callback would be used. + */ +#define DLM_RELEASE_NO_LOCKS 0 +#define DLM_RELEASE_UNUSED 1 +#define DLM_RELEASE_NORMAL 2 +#define DLM_RELEASE_NO_EVENT 3 +#define DLM_RELEASE_RECOVER 4 +#define __DLM_RELEASE_MAX DLM_RELEASE_RECOVER + +/* * dlm_release_lockspace * * Stop a lockspace. + * + * release_option: see DLM_RELEASE values above. */ -int dlm_release_lockspace(dlm_lockspace_t *lockspace, int force); +int dlm_release_lockspace(dlm_lockspace_t *lockspace, + unsigned int release_option); /* * dlm_lock diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h index 7fa1eb3cc823..61d50571ad88 100644 --- a/include/linux/energy_model.h +++ b/include/linux/energy_model.h @@ -171,6 +171,9 @@ int em_dev_update_perf_domain(struct device *dev, int em_dev_register_perf_domain(struct device *dev, unsigned int nr_states, const struct em_data_callback *cb, const cpumask_t *cpus, bool microwatts); +int em_dev_register_pd_no_update(struct device *dev, unsigned int nr_states, + const struct em_data_callback *cb, + const cpumask_t *cpus, bool microwatts); void em_dev_unregister_perf_domain(struct device *dev); struct em_perf_table *em_table_alloc(struct em_perf_domain *pd); void em_table_free(struct em_perf_table *table); @@ -350,6 +353,13 @@ int em_dev_register_perf_domain(struct device *dev, unsigned int nr_states, { return -EINVAL; } +static inline +int em_dev_register_pd_no_update(struct device *dev, unsigned int nr_states, + const struct em_data_callback *cb, + const cpumask_t *cpus, bool microwatts) +{ + return -EINVAL; +} static inline void em_dev_unregister_perf_domain(struct device *dev) { } diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index de5bd76a400c..d7d757e72554 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -856,8 +856,8 @@ struct kernel_ethtool_ts_info { enum hwtstamp_provider_qualifier phc_qualifier; enum hwtstamp_source phc_source; int phc_phyindex; - enum hwtstamp_tx_types tx_types; - enum hwtstamp_rx_filters rx_filters; + u32 tx_types; + u32 rx_filters; }; /** diff --git a/include/linux/exportfs.h b/include/linux/exportfs.h index cfb0dd1ea49c..3aac58a520c7 100644 --- a/include/linux/exportfs.h +++ b/include/linux/exportfs.h @@ -123,6 +123,12 @@ enum fid_type { FILEID_BCACHEFS_WITH_PARENT = 0xb2, /* + * + * 64 bit namespace identifier, 32 bit namespace type, 32 bit inode number. + */ + FILEID_NSFS = 0xf1, + + /* * 64 bit unique kernfs id */ FILEID_KERNFS = 0xfe, diff --git a/include/linux/firmware/imx/sm.h b/include/linux/firmware/imx/sm.h index d4212bc42b2c..a33b45027356 100644 --- a/include/linux/firmware/imx/sm.h +++ b/include/linux/firmware/imx/sm.h @@ -26,13 +26,43 @@ #define SCMI_IMX94_CTRL_SAI3_MCLK 5U /*!< WAKE SAI3 MCLK */ #define SCMI_IMX94_CTRL_SAI4_MCLK 6U /*!< WAKE SAI4 MCLK */ +#if IS_ENABLED(CONFIG_IMX_SCMI_MISC_DRV) int scmi_imx_misc_ctrl_get(u32 id, u32 *num, u32 *val); int scmi_imx_misc_ctrl_set(u32 id, u32 val); +#else +static inline int scmi_imx_misc_ctrl_get(u32 id, u32 *num, u32 *val) +{ + return -EOPNOTSUPP; +} +static inline int scmi_imx_misc_ctrl_set(u32 id, u32 val) +{ + return -EOPNOTSUPP; +} +#endif + +#if IS_ENABLED(CONFIG_IMX_SCMI_CPU_DRV) int scmi_imx_cpu_start(u32 cpuid, bool start); int scmi_imx_cpu_started(u32 cpuid, bool *started); int scmi_imx_cpu_reset_vector_set(u32 cpuid, u64 vector, bool start, bool boot, bool resume); +#else +static inline int scmi_imx_cpu_start(u32 cpuid, bool start) +{ + return -EOPNOTSUPP; +} + +static inline int scmi_imx_cpu_started(u32 cpuid, bool *started) +{ + return -EOPNOTSUPP; +} + +static inline int scmi_imx_cpu_reset_vector_set(u32 cpuid, u64 vector, bool start, + bool boot, bool resume) +{ + return -EOPNOTSUPP; +} +#endif enum scmi_imx_lmm_op { SCMI_IMX_LMM_BOOT, @@ -44,7 +74,24 @@ enum scmi_imx_lmm_op { #define SCMI_IMX_LMM_OP_FORCEFUL 0 #define SCMI_IMX_LMM_OP_GRACEFUL BIT(0) +#if IS_ENABLED(CONFIG_IMX_SCMI_LMM_DRV) int scmi_imx_lmm_operation(u32 lmid, enum scmi_imx_lmm_op op, u32 flags); int scmi_imx_lmm_info(u32 lmid, struct scmi_imx_lmm_info *info); int scmi_imx_lmm_reset_vector_set(u32 lmid, u32 cpuid, u32 flags, u64 vector); +#else +static inline int scmi_imx_lmm_operation(u32 lmid, enum scmi_imx_lmm_op op, u32 flags) +{ + return -EOPNOTSUPP; +} + +static inline int scmi_imx_lmm_info(u32 lmid, struct scmi_imx_lmm_info *info) +{ + return -EOPNOTSUPP; +} + +static inline int scmi_imx_lmm_reset_vector_set(u32 lmid, u32 cpuid, u32 flags, u64 vector) +{ + return -EOPNOTSUPP; +} +#endif #endif diff --git a/include/linux/fs.h b/include/linux/fs.h index d7ab4f96d705..9e9d7c757efe 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -72,9 +72,7 @@ struct swap_info_struct; struct seq_file; struct workqueue_struct; struct iov_iter; -struct fscrypt_inode_info; struct fscrypt_operations; -struct fsverity_info; struct fsverity_operations; struct fsnotify_mark_connector; struct fsnotify_sb_info; @@ -149,7 +147,8 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, /* Expect random access pattern */ #define FMODE_RANDOM ((__force fmode_t)(1 << 12)) -/* FMODE_* bit 13 */ +/* Supports IOCB_HAS_METADATA */ +#define FMODE_HAS_METADATA ((__force fmode_t)(1 << 13)) /* File is opened with O_PATH; almost nothing can be done with it */ #define FMODE_PATH ((__force fmode_t)(1 << 14)) @@ -356,6 +355,7 @@ struct readahead_control; #define IOCB_APPEND (__force int) RWF_APPEND #define IOCB_ATOMIC (__force int) RWF_ATOMIC #define IOCB_DONTCACHE (__force int) RWF_DONTCACHE +#define IOCB_NOSIGNAL (__force int) RWF_NOSIGNAL /* non-RWF related bits - start at 16 */ #define IOCB_EVENTFD (1 << 16) @@ -667,6 +667,124 @@ is_uncached_acl(struct posix_acl *acl) #define IOP_CACHED_LINK 0x0040 /* + * Inode state bits. Protected by inode->i_lock + * + * Four bits determine the dirty state of the inode: I_DIRTY_SYNC, + * I_DIRTY_DATASYNC, I_DIRTY_PAGES, and I_DIRTY_TIME. + * + * Four bits define the lifetime of an inode. Initially, inodes are I_NEW, + * until that flag is cleared. I_WILL_FREE, I_FREEING and I_CLEAR are set at + * various stages of removing an inode. + * + * Two bits are used for locking and completion notification, I_NEW and I_SYNC. + * + * I_DIRTY_SYNC Inode is dirty, but doesn't have to be written on + * fdatasync() (unless I_DIRTY_DATASYNC is also set). + * Timestamp updates are the usual cause. + * I_DIRTY_DATASYNC Data-related inode changes pending. We keep track of + * these changes separately from I_DIRTY_SYNC so that we + * don't have to write inode on fdatasync() when only + * e.g. the timestamps have changed. + * I_DIRTY_PAGES Inode has dirty pages. Inode itself may be clean. + * I_DIRTY_TIME The inode itself has dirty timestamps, and the + * lazytime mount option is enabled. We keep track of this + * separately from I_DIRTY_SYNC in order to implement + * lazytime. This gets cleared if I_DIRTY_INODE + * (I_DIRTY_SYNC and/or I_DIRTY_DATASYNC) gets set. But + * I_DIRTY_TIME can still be set if I_DIRTY_SYNC is already + * in place because writeback might already be in progress + * and we don't want to lose the time update + * I_NEW Serves as both a mutex and completion notification. + * New inodes set I_NEW. If two processes both create + * the same inode, one of them will release its inode and + * wait for I_NEW to be released before returning. + * Inodes in I_WILL_FREE, I_FREEING or I_CLEAR state can + * also cause waiting on I_NEW, without I_NEW actually + * being set. find_inode() uses this to prevent returning + * nearly-dead inodes. + * I_WILL_FREE Must be set when calling write_inode_now() if i_count + * is zero. I_FREEING must be set when I_WILL_FREE is + * cleared. + * I_FREEING Set when inode is about to be freed but still has dirty + * pages or buffers attached or the inode itself is still + * dirty. + * I_CLEAR Added by clear_inode(). In this state the inode is + * clean and can be destroyed. Inode keeps I_FREEING. + * + * Inodes that are I_WILL_FREE, I_FREEING or I_CLEAR are + * prohibited for many purposes. iget() must wait for + * the inode to be completely released, then create it + * anew. Other functions will just ignore such inodes, + * if appropriate. I_NEW is used for waiting. + * + * I_SYNC Writeback of inode is running. The bit is set during + * data writeback, and cleared with a wakeup on the bit + * address once it is done. The bit is also used to pin + * the inode in memory for flusher thread. + * + * I_REFERENCED Marks the inode as recently references on the LRU list. + * + * I_WB_SWITCH Cgroup bdi_writeback switching in progress. Used to + * synchronize competing switching instances and to tell + * wb stat updates to grab the i_pages lock. See + * inode_switch_wbs_work_fn() for details. + * + * I_OVL_INUSE Used by overlayfs to get exclusive ownership on upper + * and work dirs among overlayfs mounts. + * + * I_CREATING New object's inode in the middle of setting up. + * + * I_DONTCACHE Evict inode as soon as it is not used anymore. + * + * I_SYNC_QUEUED Inode is queued in b_io or b_more_io writeback lists. + * Used to detect that mark_inode_dirty() should not move + * inode between dirty lists. + * + * I_PINNING_FSCACHE_WB Inode is pinning an fscache object for writeback. + * + * I_LRU_ISOLATING Inode is pinned being isolated from LRU without holding + * i_count. + * + * Q: What is the difference between I_WILL_FREE and I_FREEING? + * + * __I_{SYNC,NEW,LRU_ISOLATING} are used to derive unique addresses to wait + * upon. There's one free address left. + */ + +enum inode_state_bits { + __I_NEW = 0U, + __I_SYNC = 1U, + __I_LRU_ISOLATING = 2U + /* reserved wait address bit 3 */ +}; + +enum inode_state_flags_t { + I_NEW = (1U << __I_NEW), + I_SYNC = (1U << __I_SYNC), + I_LRU_ISOLATING = (1U << __I_LRU_ISOLATING), + /* reserved flag bit 3 */ + I_DIRTY_SYNC = (1U << 4), + I_DIRTY_DATASYNC = (1U << 5), + I_DIRTY_PAGES = (1U << 6), + I_WILL_FREE = (1U << 7), + I_FREEING = (1U << 8), + I_CLEAR = (1U << 9), + I_REFERENCED = (1U << 10), + I_LINKABLE = (1U << 11), + I_DIRTY_TIME = (1U << 12), + I_WB_SWITCH = (1U << 13), + I_OVL_INUSE = (1U << 14), + I_CREATING = (1U << 15), + I_DONTCACHE = (1U << 16), + I_SYNC_QUEUED = (1U << 17), + I_PINNING_NETFS_WB = (1U << 18) +}; + +#define I_DIRTY_INODE (I_DIRTY_SYNC | I_DIRTY_DATASYNC) +#define I_DIRTY (I_DIRTY_INODE | I_DIRTY_PAGES) +#define I_DIRTY_ALL (I_DIRTY | I_DIRTY_TIME) + +/* * Keep mostly read-only and often accessed (especially for * the RCU path lookup and 'stat' data) fields at the beginning * of the 'struct inode' @@ -724,7 +842,7 @@ struct inode { #endif /* Misc */ - u32 i_state; + enum inode_state_flags_t i_state; /* 32-bit hole */ struct rw_semaphore i_rwsem; @@ -780,14 +898,6 @@ struct inode { struct fsnotify_mark_connector __rcu *i_fsnotify_marks; #endif -#ifdef CONFIG_FS_ENCRYPTION - struct fscrypt_inode_info *i_crypt_info; -#endif - -#ifdef CONFIG_FS_VERITY - struct fsverity_info *i_verity_info; -#endif - void *i_private; /* fs or device private pointer */ } __randomize_layout; @@ -2008,20 +2118,18 @@ int vfs_unlink(struct mnt_idmap *, struct inode *, struct dentry *, /** * struct renamedata - contains all information required for renaming - * @old_mnt_idmap: idmap of the old mount the inode was found from + * @mnt_idmap: idmap of the mount in which the rename is happening. * @old_parent: parent of source * @old_dentry: source - * @new_mnt_idmap: idmap of the new mount the inode was found from * @new_parent: parent of destination * @new_dentry: destination * @delegated_inode: returns an inode needing a delegation break * @flags: rename flags */ struct renamedata { - struct mnt_idmap *old_mnt_idmap; + struct mnt_idmap *mnt_idmap; struct dentry *old_parent; struct dentry *old_dentry; - struct mnt_idmap *new_mnt_idmap; struct dentry *new_parent; struct dentry *new_dentry; struct inode **delegated_inode; @@ -2052,8 +2160,6 @@ int vfs_fchown(struct file *file, uid_t user, gid_t group); int vfs_fchmod(struct file *file, umode_t mode); int vfs_utimes(const struct path *path, struct timespec64 *times); -int vfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg); - #ifdef CONFIG_COMPAT extern long compat_ptr_ioctl(struct file *file, unsigned int cmd, unsigned long arg); @@ -2492,117 +2598,6 @@ static inline void kiocb_clone(struct kiocb *kiocb, struct kiocb *kiocb_src, }; } -/* - * Inode state bits. Protected by inode->i_lock - * - * Four bits determine the dirty state of the inode: I_DIRTY_SYNC, - * I_DIRTY_DATASYNC, I_DIRTY_PAGES, and I_DIRTY_TIME. - * - * Four bits define the lifetime of an inode. Initially, inodes are I_NEW, - * until that flag is cleared. I_WILL_FREE, I_FREEING and I_CLEAR are set at - * various stages of removing an inode. - * - * Two bits are used for locking and completion notification, I_NEW and I_SYNC. - * - * I_DIRTY_SYNC Inode is dirty, but doesn't have to be written on - * fdatasync() (unless I_DIRTY_DATASYNC is also set). - * Timestamp updates are the usual cause. - * I_DIRTY_DATASYNC Data-related inode changes pending. We keep track of - * these changes separately from I_DIRTY_SYNC so that we - * don't have to write inode on fdatasync() when only - * e.g. the timestamps have changed. - * I_DIRTY_PAGES Inode has dirty pages. Inode itself may be clean. - * I_DIRTY_TIME The inode itself has dirty timestamps, and the - * lazytime mount option is enabled. We keep track of this - * separately from I_DIRTY_SYNC in order to implement - * lazytime. This gets cleared if I_DIRTY_INODE - * (I_DIRTY_SYNC and/or I_DIRTY_DATASYNC) gets set. But - * I_DIRTY_TIME can still be set if I_DIRTY_SYNC is already - * in place because writeback might already be in progress - * and we don't want to lose the time update - * I_NEW Serves as both a mutex and completion notification. - * New inodes set I_NEW. If two processes both create - * the same inode, one of them will release its inode and - * wait for I_NEW to be released before returning. - * Inodes in I_WILL_FREE, I_FREEING or I_CLEAR state can - * also cause waiting on I_NEW, without I_NEW actually - * being set. find_inode() uses this to prevent returning - * nearly-dead inodes. - * I_WILL_FREE Must be set when calling write_inode_now() if i_count - * is zero. I_FREEING must be set when I_WILL_FREE is - * cleared. - * I_FREEING Set when inode is about to be freed but still has dirty - * pages or buffers attached or the inode itself is still - * dirty. - * I_CLEAR Added by clear_inode(). In this state the inode is - * clean and can be destroyed. Inode keeps I_FREEING. - * - * Inodes that are I_WILL_FREE, I_FREEING or I_CLEAR are - * prohibited for many purposes. iget() must wait for - * the inode to be completely released, then create it - * anew. Other functions will just ignore such inodes, - * if appropriate. I_NEW is used for waiting. - * - * I_SYNC Writeback of inode is running. The bit is set during - * data writeback, and cleared with a wakeup on the bit - * address once it is done. The bit is also used to pin - * the inode in memory for flusher thread. - * - * I_REFERENCED Marks the inode as recently references on the LRU list. - * - * I_WB_SWITCH Cgroup bdi_writeback switching in progress. Used to - * synchronize competing switching instances and to tell - * wb stat updates to grab the i_pages lock. See - * inode_switch_wbs_work_fn() for details. - * - * I_OVL_INUSE Used by overlayfs to get exclusive ownership on upper - * and work dirs among overlayfs mounts. - * - * I_CREATING New object's inode in the middle of setting up. - * - * I_DONTCACHE Evict inode as soon as it is not used anymore. - * - * I_SYNC_QUEUED Inode is queued in b_io or b_more_io writeback lists. - * Used to detect that mark_inode_dirty() should not move - * inode between dirty lists. - * - * I_PINNING_FSCACHE_WB Inode is pinning an fscache object for writeback. - * - * I_LRU_ISOLATING Inode is pinned being isolated from LRU without holding - * i_count. - * - * Q: What is the difference between I_WILL_FREE and I_FREEING? - * - * __I_{SYNC,NEW,LRU_ISOLATING} are used to derive unique addresses to wait - * upon. There's one free address left. - */ -#define __I_NEW 0 -#define I_NEW (1 << __I_NEW) -#define __I_SYNC 1 -#define I_SYNC (1 << __I_SYNC) -#define __I_LRU_ISOLATING 2 -#define I_LRU_ISOLATING (1 << __I_LRU_ISOLATING) - -#define I_DIRTY_SYNC (1 << 3) -#define I_DIRTY_DATASYNC (1 << 4) -#define I_DIRTY_PAGES (1 << 5) -#define I_WILL_FREE (1 << 6) -#define I_FREEING (1 << 7) -#define I_CLEAR (1 << 8) -#define I_REFERENCED (1 << 9) -#define I_LINKABLE (1 << 10) -#define I_DIRTY_TIME (1 << 11) -#define I_WB_SWITCH (1 << 12) -#define I_OVL_INUSE (1 << 13) -#define I_CREATING (1 << 14) -#define I_DONTCACHE (1 << 15) -#define I_SYNC_QUEUED (1 << 16) -#define I_PINNING_NETFS_WB (1 << 17) - -#define I_DIRTY_INODE (I_DIRTY_SYNC | I_DIRTY_DATASYNC) -#define I_DIRTY (I_DIRTY_INODE | I_DIRTY_PAGES) -#define I_DIRTY_ALL (I_DIRTY | I_DIRTY_TIME) - extern void __mark_inode_dirty(struct inode *, int); static inline void mark_inode_dirty(struct inode *inode) { @@ -2614,6 +2609,11 @@ static inline void mark_inode_dirty_sync(struct inode *inode) __mark_inode_dirty(inode, I_DIRTY_SYNC); } +static inline int icount_read(const struct inode *inode) +{ + return atomic_read(&inode->i_count); +} + /* * Returns true if the given inode itself only has dirty timestamps (its pages * may still be dirty) and isn't currently being allocated or freed. @@ -2713,12 +2713,6 @@ static inline bool is_mgtime(const struct inode *inode) return inode->i_opflags & IOP_MGTIME; } -extern struct dentry *mount_bdev(struct file_system_type *fs_type, - int flags, const char *dev_name, void *data, - int (*fill_super)(struct super_block *, void *, int)); -extern struct dentry *mount_nodev(struct file_system_type *fs_type, - int flags, void *data, - int (*fill_super)(struct super_block *, void *, int)); extern struct dentry *mount_subtree(struct vfsmount *mnt, const char *path); void retire_super(struct super_block *sb); void generic_shutdown_super(struct super_block *sb); @@ -3281,7 +3275,7 @@ static inline bool is_dot_dotdot(const char *name, size_t len) /** * name_contains_dotdot - check if a file name contains ".." path components - * + * @name: File path string to check * Search for ".." surrounded by either '/' or start/end of string. */ static inline bool name_contains_dotdot(const char *name) @@ -3313,8 +3307,8 @@ extern void address_space_init_once(struct address_space *mapping); extern struct inode * igrab(struct inode *); extern ino_t iunique(struct super_block *, ino_t); extern int inode_needs_sync(struct inode *inode); -extern int generic_delete_inode(struct inode *inode); -static inline int generic_drop_inode(struct inode *inode) +extern int inode_just_drop(struct inode *inode); +static inline int inode_generic_drop(struct inode *inode) { return !inode->i_nlink || inode_unhashed(inode); } @@ -3393,7 +3387,6 @@ static inline struct inode *new_inode_pseudo(struct super_block *sb) extern struct inode *new_inode(struct super_block *sb); extern void free_inode_nonrcu(struct inode *inode); extern int setattr_should_drop_suidgid(struct mnt_idmap *, struct inode *); -extern int file_remove_privs_flags(struct file *file, unsigned int flags); extern int file_remove_privs(struct file *); int setattr_should_drop_sgid(struct mnt_idmap *idmap, const struct inode *inode); @@ -4023,4 +4016,18 @@ static inline bool vfs_empty_path(int dfd, const char __user *path) int generic_atomic_write_valid(struct kiocb *iocb, struct iov_iter *iter); +static inline bool extensible_ioctl_valid(unsigned int cmd_a, + unsigned int cmd_b, size_t min_size) +{ + if (_IOC_DIR(cmd_a) != _IOC_DIR(cmd_b)) + return false; + if (_IOC_TYPE(cmd_a) != _IOC_TYPE(cmd_b)) + return false; + if (_IOC_NR(cmd_a) != _IOC_NR(cmd_b)) + return false; + if (_IOC_SIZE(cmd_a) < min_size) + return false; + return true; +} + #endif /* _LINUX_FS_H */ diff --git a/include/linux/fs_context.h b/include/linux/fs_context.h index 7773eb870039..671f031be173 100644 --- a/include/linux/fs_context.h +++ b/include/linux/fs_context.h @@ -186,10 +186,12 @@ struct fc_log { extern __attribute__((format(printf, 4, 5))) void logfc(struct fc_log *log, const char *prefix, char level, const char *fmt, ...); -#define __logfc(fc, l, fmt, ...) logfc((fc)->log.log, NULL, \ - l, fmt, ## __VA_ARGS__) -#define __plog(p, l, fmt, ...) logfc((p)->log, (p)->prefix, \ - l, fmt, ## __VA_ARGS__) +#define __logfc(fc, l, fmt, ...) \ + logfc((fc)->log.log, NULL, (l), (fmt), ## __VA_ARGS__) +#define __plogp(p, prefix, l, fmt, ...) \ + logfc((p)->log, (prefix), (l), (fmt), ## __VA_ARGS__) +#define __plog(p, l, fmt, ...) __plogp(p, (p)->prefix, l, fmt, ## __VA_ARGS__) + /** * infof - Store supplementary informational message * @fc: The context in which to log the informational message @@ -201,6 +203,8 @@ void logfc(struct fc_log *log, const char *prefix, char level, const char *fmt, #define infof(fc, fmt, ...) __logfc(fc, 'i', fmt, ## __VA_ARGS__) #define info_plog(p, fmt, ...) __plog(p, 'i', fmt, ## __VA_ARGS__) #define infofc(fc, fmt, ...) __plog((&(fc)->log), 'i', fmt, ## __VA_ARGS__) +#define infofcp(fc, prefix, fmt, ...) \ + __plogp((&(fc)->log), prefix, 'i', fmt, ## __VA_ARGS__) /** * warnf - Store supplementary warning message @@ -213,6 +217,8 @@ void logfc(struct fc_log *log, const char *prefix, char level, const char *fmt, #define warnf(fc, fmt, ...) __logfc(fc, 'w', fmt, ## __VA_ARGS__) #define warn_plog(p, fmt, ...) __plog(p, 'w', fmt, ## __VA_ARGS__) #define warnfc(fc, fmt, ...) __plog((&(fc)->log), 'w', fmt, ## __VA_ARGS__) +#define warnfcp(fc, prefix, fmt, ...) \ + __plogp((&(fc)->log), prefix, 'w', fmt, ## __VA_ARGS__) /** * errorf - Store supplementary error message @@ -225,6 +231,8 @@ void logfc(struct fc_log *log, const char *prefix, char level, const char *fmt, #define errorf(fc, fmt, ...) __logfc(fc, 'e', fmt, ## __VA_ARGS__) #define error_plog(p, fmt, ...) __plog(p, 'e', fmt, ## __VA_ARGS__) #define errorfc(fc, fmt, ...) __plog((&(fc)->log), 'e', fmt, ## __VA_ARGS__) +#define errorfcp(fc, prefix, fmt, ...) \ + __plogp((&(fc)->log), prefix, 'e', fmt, ## __VA_ARGS__) /** * invalf - Store supplementary invalid argument error message @@ -237,5 +245,7 @@ void logfc(struct fc_log *log, const char *prefix, char level, const char *fmt, #define invalf(fc, fmt, ...) (errorf(fc, fmt, ## __VA_ARGS__), -EINVAL) #define inval_plog(p, fmt, ...) (error_plog(p, fmt, ## __VA_ARGS__), -EINVAL) #define invalfc(fc, fmt, ...) (errorfc(fc, fmt, ## __VA_ARGS__), -EINVAL) +#define invalfcp(fc, prefix, fmt, ...) \ + (errorfcp(fc, prefix, fmt, ## __VA_ARGS__), -EINVAL) #endif /* _LINUX_FS_CONTEXT_H */ diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h index 10dd161690a2..516aba5b858b 100644 --- a/include/linux/fscrypt.h +++ b/include/linux/fscrypt.h @@ -61,6 +61,12 @@ struct fscrypt_name { /* Crypto operations for filesystems */ struct fscrypt_operations { + /* + * The offset of the pointer to struct fscrypt_inode_info in the + * filesystem-specific part of the inode, relative to the beginning of + * the common part of the inode (the 'struct inode'). + */ + ptrdiff_t inode_info_offs; /* * If set, then fs/crypto/ will allocate a global bounce page pool the @@ -195,16 +201,44 @@ struct fscrypt_operations { int fscrypt_d_revalidate(struct inode *dir, const struct qstr *name, struct dentry *dentry, unsigned int flags); +/* + * Returns the address of the fscrypt info pointer within the + * filesystem-specific part of the inode. (To save memory on filesystems that + * don't support fscrypt, a field in 'struct inode' itself is no longer used.) + */ +static inline struct fscrypt_inode_info ** +fscrypt_inode_info_addr(const struct inode *inode) +{ + VFS_WARN_ON_ONCE(inode->i_sb->s_cop->inode_info_offs == 0); + return (void *)inode + inode->i_sb->s_cop->inode_info_offs; +} + +/* + * Load the inode's fscrypt info pointer, using a raw dereference. Since this + * uses a raw dereference with no memory barrier, it is appropriate to use only + * when the caller knows the inode's key setup already happened, resulting in + * non-NULL fscrypt info. E.g., the file contents en/decryption functions use + * this, since fscrypt_file_open() set up the key. + */ +static inline struct fscrypt_inode_info * +fscrypt_get_inode_info_raw(const struct inode *inode) +{ + struct fscrypt_inode_info *ci = *fscrypt_inode_info_addr(inode); + + VFS_WARN_ON_ONCE(ci == NULL); + return ci; +} + static inline struct fscrypt_inode_info * fscrypt_get_inode_info(const struct inode *inode) { /* * Pairs with the cmpxchg_release() in fscrypt_setup_encryption_info(). - * I.e., another task may publish ->i_crypt_info concurrently, executing - * a RELEASE barrier. We need to use smp_load_acquire() here to safely + * I.e., another task may publish the fscrypt info concurrently, + * executing a RELEASE barrier. Use smp_load_acquire() here to safely * ACQUIRE the memory the other task published. */ - return smp_load_acquire(&inode->i_crypt_info); + return smp_load_acquire(fscrypt_inode_info_addr(inode)); } /** diff --git a/include/linux/fsverity.h b/include/linux/fsverity.h index 1eb7eae580be..5bc7280425a7 100644 --- a/include/linux/fsverity.h +++ b/include/linux/fsverity.h @@ -26,8 +26,16 @@ /* Arbitrary limit to bound the kmalloc() size. Can be changed. */ #define FS_VERITY_MAX_DESCRIPTOR_SIZE 16384 +struct fsverity_info; + /* Verity operations for filesystems */ struct fsverity_operations { + /** + * The offset of the pointer to struct fsverity_info in the + * filesystem-specific part of the inode, relative to the beginning of + * the common part of the inode (the 'struct inode'). + */ + ptrdiff_t inode_info_offs; /** * Begin enabling verity on the given file. @@ -124,15 +132,37 @@ struct fsverity_operations { #ifdef CONFIG_FS_VERITY +/* + * Returns the address of the verity info pointer within the filesystem-specific + * part of the inode. (To save memory on filesystems that don't support + * fsverity, a field in 'struct inode' itself is no longer used.) + */ +static inline struct fsverity_info ** +fsverity_info_addr(const struct inode *inode) +{ + VFS_WARN_ON_ONCE(inode->i_sb->s_vop->inode_info_offs == 0); + return (void *)inode + inode->i_sb->s_vop->inode_info_offs; +} + static inline struct fsverity_info *fsverity_get_info(const struct inode *inode) { /* - * Pairs with the cmpxchg_release() in fsverity_set_info(). - * I.e., another task may publish ->i_verity_info concurrently, - * executing a RELEASE barrier. We need to use smp_load_acquire() here - * to safely ACQUIRE the memory the other task published. + * Since this function can be called on inodes belonging to filesystems + * that don't support fsverity at all, and fsverity_info_addr() doesn't + * work on such filesystems, we have to start with an IS_VERITY() check. + * Checking IS_VERITY() here is also useful to minimize the overhead of + * fsverity_active() on non-verity files. + */ + if (!IS_VERITY(inode)) + return NULL; + + /* + * Pairs with the cmpxchg_release() in fsverity_set_info(). I.e., + * another task may publish the inode's verity info concurrently, + * executing a RELEASE barrier. Use smp_load_acquire() here to safely + * ACQUIRE the memory the other task published. */ - return smp_load_acquire(&inode->i_verity_info); + return smp_load_acquire(fsverity_info_addr(inode)); } /* enable.c */ @@ -156,12 +186,19 @@ void __fsverity_cleanup_inode(struct inode *inode); * fsverity_cleanup_inode() - free the inode's verity info, if present * @inode: an inode being evicted * - * Filesystems must call this on inode eviction to free ->i_verity_info. + * Filesystems must call this on inode eviction to free the inode's verity info. */ static inline void fsverity_cleanup_inode(struct inode *inode) { - if (inode->i_verity_info) + /* + * Only IS_VERITY() inodes can have verity info, so start by checking + * for IS_VERITY() (which is faster than retrieving the pointer to the + * verity info). This minimizes overhead for non-verity inodes. + */ + if (IS_VERITY(inode)) __fsverity_cleanup_inode(inode); + else + VFS_WARN_ON_ONCE(*fsverity_info_addr(inode) != NULL); } /* read_metadata.c */ @@ -267,12 +304,12 @@ static inline bool fsverity_verify_page(struct page *page) * fsverity_active() - do reads from the inode need to go through fs-verity? * @inode: inode to check * - * This checks whether ->i_verity_info has been set. + * This checks whether the inode's verity info has been set. * * Filesystems call this from ->readahead() to check whether the pages need to * be verified or not. Don't use IS_VERITY() for this purpose; it's subject to * a race condition where the file is being read concurrently with - * FS_IOC_ENABLE_VERITY completing. (S_VERITY is set before ->i_verity_info.) + * FS_IOC_ENABLE_VERITY completing. (S_VERITY is set before the verity info.) * * Return: true if reads need to go through fs-verity, otherwise false */ @@ -287,7 +324,7 @@ static inline bool fsverity_active(const struct inode *inode) * @filp: the struct file being set up * * When opening a verity file, deny the open if it is for writing. Otherwise, - * set up the inode's ->i_verity_info if not already done. + * set up the inode's verity info if not already done. * * When combined with fscrypt, this must be called after fscrypt_file_open(). * Otherwise, we won't have the key set up to decrypt the verity metadata. diff --git a/include/linux/hfs_common.h b/include/linux/hfs_common.h new file mode 100644 index 000000000000..8838ca2f3d08 --- /dev/null +++ b/include/linux/hfs_common.h @@ -0,0 +1,20 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * HFS/HFS+ common definitions, inline functions, + * and shared functionality. + */ + +#ifndef _HFS_COMMON_H_ +#define _HFS_COMMON_H_ + +#ifdef pr_fmt +#undef pr_fmt +#endif + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#define hfs_dbg(fmt, ...) \ + pr_debug("pid %d:%s:%d %s(): " fmt, \ + current->pid, __FILE__, __LINE__, __func__, ##__VA_ARGS__) \ + +#endif /* _HFS_COMMON_H_ */ diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h index 80a178f3d896..12f5ee43850e 100644 --- a/include/linux/io_uring_types.h +++ b/include/linux/io_uring_types.h @@ -420,9 +420,6 @@ struct io_ring_ctx { struct list_head defer_list; unsigned nr_drained; - struct io_alloc_cache msg_cache; - spinlock_t msg_lock; - #ifdef CONFIG_NET_RX_BUSY_POLL struct list_head napi_list; /* track busy poll napi_id */ spinlock_t napi_lock; /* napi_list lock */ diff --git a/include/linux/iocontext.h b/include/linux/iocontext.h index 14f7eaf1b443..079d8773790c 100644 --- a/include/linux/iocontext.h +++ b/include/linux/iocontext.h @@ -118,8 +118,8 @@ struct task_struct; #ifdef CONFIG_BLOCK void put_io_context(struct io_context *ioc); void exit_io_context(struct task_struct *task); -int __copy_io(unsigned long clone_flags, struct task_struct *tsk); -static inline int copy_io(unsigned long clone_flags, struct task_struct *tsk) +int __copy_io(u64 clone_flags, struct task_struct *tsk); +static inline int copy_io(u64 clone_flags, struct task_struct *tsk) { if (!current->io_context) return 0; @@ -129,7 +129,7 @@ static inline int copy_io(unsigned long clone_flags, struct task_struct *tsk) struct io_context; static inline void put_io_context(struct io_context *ioc) { } static inline void exit_io_context(struct task_struct *task) { } -static inline int copy_io(unsigned long clone_flags, struct task_struct *tsk) +static inline int copy_io(u64 clone_flags, struct task_struct *tsk) { return 0; } diff --git a/include/linux/ipc_namespace.h b/include/linux/ipc_namespace.h index e8240cf2611a..12faca29bbb9 100644 --- a/include/linux/ipc_namespace.h +++ b/include/linux/ipc_namespace.h @@ -129,20 +129,25 @@ static inline int mq_init_ns(struct ipc_namespace *ns) { return 0; } #endif #if defined(CONFIG_IPC_NS) -extern struct ipc_namespace *copy_ipcs(unsigned long flags, +static inline struct ipc_namespace *to_ipc_ns(struct ns_common *ns) +{ + return container_of(ns, struct ipc_namespace, ns); +} + +extern struct ipc_namespace *copy_ipcs(u64 flags, struct user_namespace *user_ns, struct ipc_namespace *ns); static inline struct ipc_namespace *get_ipc_ns(struct ipc_namespace *ns) { if (ns) - refcount_inc(&ns->ns.count); + ns_ref_inc(ns); return ns; } static inline struct ipc_namespace *get_ipc_ns_not_zero(struct ipc_namespace *ns) { if (ns) { - if (refcount_inc_not_zero(&ns->ns.count)) + if (ns_ref_get(ns)) return ns; } @@ -151,7 +156,7 @@ static inline struct ipc_namespace *get_ipc_ns_not_zero(struct ipc_namespace *ns extern void put_ipc_ns(struct ipc_namespace *ns); #else -static inline struct ipc_namespace *copy_ipcs(unsigned long flags, +static inline struct ipc_namespace *copy_ipcs(u64 flags, struct user_namespace *user_ns, struct ipc_namespace *ns) { if (flags & CLONE_NEWIPC) diff --git a/include/linux/kasan.h b/include/linux/kasan.h index 890011071f2b..fe5ce9215821 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -562,7 +562,7 @@ static inline void kasan_init_hw_tags(void) { } #if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS) void kasan_populate_early_vm_area_shadow(void *start, unsigned long size); -int kasan_populate_vmalloc(unsigned long addr, unsigned long size); +int kasan_populate_vmalloc(unsigned long addr, unsigned long size, gfp_t gfp_mask); void kasan_release_vmalloc(unsigned long start, unsigned long end, unsigned long free_region_start, unsigned long free_region_end, @@ -574,7 +574,7 @@ static inline void kasan_populate_early_vm_area_shadow(void *start, unsigned long size) { } static inline int kasan_populate_vmalloc(unsigned long start, - unsigned long size) + unsigned long size, gfp_t gfp_mask) { return 0; } @@ -610,7 +610,7 @@ static __always_inline void kasan_poison_vmalloc(const void *start, static inline void kasan_populate_early_vm_area_shadow(void *start, unsigned long size) { } static inline int kasan_populate_vmalloc(unsigned long start, - unsigned long size) + unsigned long size, gfp_t gfp_mask) { return 0; } diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index fd11fffdd3c3..adbe234a6f6c 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -211,7 +211,7 @@ LSM_HOOK(int, 0, file_open, struct file *file) LSM_HOOK(int, 0, file_post_open, struct file *file, int mask) LSM_HOOK(int, 0, file_truncate, struct file *file) LSM_HOOK(int, 0, task_alloc, struct task_struct *task, - unsigned long clone_flags) + u64 clone_flags) LSM_HOOK(void, LSM_RET_VOID, task_free, struct task_struct *task) LSM_HOOK(int, 0, cred_alloc_blank, struct cred *cred, gfp_t gfp) LSM_HOOK(void, LSM_RET_VOID, cred_free, struct cred *cred) diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 8c5fbfb85749..10fe492e1fed 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -663,6 +663,7 @@ struct mlx5e_resources { bool tisn_valid; } hw_objs; struct net_device *uplink_netdev; + netdevice_tracker tracker; struct mutex uplink_netdev_lock; struct mlx5_crypto_dek_priv *dek_priv; }; diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index 86055d55836d..6ac76a0c3827 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -308,6 +308,8 @@ struct mlx5_fc *mlx5_fc_create(struct mlx5_core_dev *dev, bool aging); void mlx5_fc_destroy(struct mlx5_core_dev *dev, struct mlx5_fc *counter); struct mlx5_fc *mlx5_fc_local_create(u32 counter_id, u32 offset, u32 bulk_size); void mlx5_fc_local_destroy(struct mlx5_fc *counter); +void mlx5_fc_local_get(struct mlx5_fc *counter); +void mlx5_fc_local_put(struct mlx5_fc *counter); u64 mlx5_fc_query_lastuse(struct mlx5_fc *counter); void mlx5_fc_query_cached(struct mlx5_fc *counter, u64 *bytes, u64 *packets, u64 *lastuse); diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 08bc2442db93..7f625c35128b 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -631,6 +631,11 @@ static inline int ptdesc_pmd_pts_count(struct ptdesc *ptdesc) { return atomic_read(&ptdesc->pt_share_count); } + +static inline bool ptdesc_pmd_is_shared(struct ptdesc *ptdesc) +{ + return !!ptdesc_pmd_pts_count(ptdesc); +} #else static inline void ptdesc_pmd_pts_init(struct ptdesc *ptdesc) { @@ -1102,6 +1107,11 @@ struct mm_struct { unsigned long saved_auxv[AT_VECTOR_SIZE]; /* for /proc/PID/auxv */ +#ifdef CONFIG_ARCH_HAS_ELF_CORE_EFLAGS + /* the ABI-related flags from the ELF header. Used for core dump */ + unsigned long saved_e_flags; +#endif + struct percpu_counter rss_stat[NR_MM_COUNTERS]; struct linux_binfmt *binfmt; diff --git a/include/linux/mnt_namespace.h b/include/linux/mnt_namespace.h index 70b366b64816..0acd1089d149 100644 --- a/include/linux/mnt_namespace.h +++ b/include/linux/mnt_namespace.h @@ -11,7 +11,9 @@ struct fs_struct; struct user_namespace; struct ns_common; -extern struct mnt_namespace *copy_mnt_ns(unsigned long, struct mnt_namespace *, +extern struct mnt_namespace init_mnt_ns; + +extern struct mnt_namespace *copy_mnt_ns(u64, struct mnt_namespace *, struct user_namespace *, struct fs_struct *); extern void put_mnt_ns(struct mnt_namespace *ns); DEFINE_FREE(put_mnt_ns, struct mnt_namespace *, if (!IS_ERR_OR_NULL(_T)) put_mnt_ns(_T)) diff --git a/include/linux/msi.h b/include/linux/msi.h index e5e86a8529fb..faac634ac230 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -431,8 +431,6 @@ struct msi_domain_info; * function. * @domain_free_irqs: Optional function to override the default free * function. - * @msi_post_free: Optional function which is invoked after freeing - * all interrupts. * @msi_translate: Optional translate callback to support the odd wire to * MSI bridges, e.g. MBIGEN * @@ -473,8 +471,6 @@ struct msi_domain_ops { struct device *dev, int nvec); void (*domain_free_irqs)(struct irq_domain *domain, struct device *dev); - void (*msi_post_free)(struct irq_domain *domain, - struct device *dev); int (*msi_translate)(struct irq_domain *domain, struct irq_fwspec *fwspec, irq_hw_number_t *hwirq, unsigned int *type); }; diff --git a/include/linux/namei.h b/include/linux/namei.h index 5d085428e471..a7800ef04e76 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -57,13 +57,17 @@ struct dentry *lookup_one_qstr_excl(const struct qstr *name, struct dentry *base, unsigned int flags); extern int kern_path(const char *, unsigned, struct path *); - -extern struct dentry *kern_path_create(int, const char *, struct path *, unsigned int); -extern struct dentry *user_path_create(int, const char __user *, struct path *, unsigned int); -extern void done_path_create(struct path *, struct dentry *); -extern struct dentry *kern_path_locked(const char *, struct path *); -extern struct dentry *kern_path_locked_negative(const char *, struct path *); -extern struct dentry *user_path_locked_at(int , const char __user *, struct path *); +struct dentry *kern_path_parent(const char *name, struct path *parent); + +extern struct dentry *start_creating_path(int, const char *, struct path *, unsigned int); +extern struct dentry *start_creating_user_path(int, const char __user *, struct path *, unsigned int); +extern void end_creating_path(struct path *, struct dentry *); +extern struct dentry *start_removing_path(const char *, struct path *); +extern struct dentry *start_removing_user_path_at(int , const char __user *, struct path *); +static inline void end_removing_path(struct path *path , struct dentry *dentry) +{ + end_creating_path(path, dentry); +} int vfs_path_parent_lookup(struct filename *filename, unsigned int flags, struct path *parent, struct qstr *last, int *type, const struct path *root); @@ -80,6 +84,9 @@ struct dentry *lookup_one_unlocked(struct mnt_idmap *idmap, struct dentry *lookup_one_positive_unlocked(struct mnt_idmap *idmap, struct qstr *name, struct dentry *base); +struct dentry *lookup_one_positive_killable(struct mnt_idmap *idmap, + struct qstr *name, + struct dentry *base); extern int follow_down_one(struct path *); extern int follow_down(struct path *path, unsigned int flags); diff --git a/include/linux/ns_common.h b/include/linux/ns_common.h index 7d22ea50b098..f5b68b8abb54 100644 --- a/include/linux/ns_common.h +++ b/include/linux/ns_common.h @@ -3,14 +3,151 @@ #define _LINUX_NS_COMMON_H #include <linux/refcount.h> +#include <linux/rbtree.h> +#include <uapi/linux/sched.h> struct proc_ns_operations; +struct cgroup_namespace; +struct ipc_namespace; +struct mnt_namespace; +struct net; +struct pid_namespace; +struct time_namespace; +struct user_namespace; +struct uts_namespace; + +extern struct cgroup_namespace init_cgroup_ns; +extern struct ipc_namespace init_ipc_ns; +extern struct mnt_namespace init_mnt_ns; +extern struct net init_net; +extern struct pid_namespace init_pid_ns; +extern struct time_namespace init_time_ns; +extern struct user_namespace init_user_ns; +extern struct uts_namespace init_uts_ns; + +extern const struct proc_ns_operations netns_operations; +extern const struct proc_ns_operations utsns_operations; +extern const struct proc_ns_operations ipcns_operations; +extern const struct proc_ns_operations pidns_operations; +extern const struct proc_ns_operations pidns_for_children_operations; +extern const struct proc_ns_operations userns_operations; +extern const struct proc_ns_operations mntns_operations; +extern const struct proc_ns_operations cgroupns_operations; +extern const struct proc_ns_operations timens_operations; +extern const struct proc_ns_operations timens_for_children_operations; + struct ns_common { + u32 ns_type; struct dentry *stashed; const struct proc_ns_operations *ops; unsigned int inum; - refcount_t count; + refcount_t __ns_ref; /* do not use directly */ + union { + struct { + u64 ns_id; + struct rb_node ns_tree_node; + struct list_head ns_list_node; + }; + struct rcu_head ns_rcu; + }; }; +int __ns_common_init(struct ns_common *ns, u32 ns_type, const struct proc_ns_operations *ops, int inum); +void __ns_common_free(struct ns_common *ns); + +#define to_ns_common(__ns) \ + _Generic((__ns), \ + struct cgroup_namespace *: &(__ns)->ns, \ + const struct cgroup_namespace *: &(__ns)->ns, \ + struct ipc_namespace *: &(__ns)->ns, \ + const struct ipc_namespace *: &(__ns)->ns, \ + struct mnt_namespace *: &(__ns)->ns, \ + const struct mnt_namespace *: &(__ns)->ns, \ + struct net *: &(__ns)->ns, \ + const struct net *: &(__ns)->ns, \ + struct pid_namespace *: &(__ns)->ns, \ + const struct pid_namespace *: &(__ns)->ns, \ + struct time_namespace *: &(__ns)->ns, \ + const struct time_namespace *: &(__ns)->ns, \ + struct user_namespace *: &(__ns)->ns, \ + const struct user_namespace *: &(__ns)->ns, \ + struct uts_namespace *: &(__ns)->ns, \ + const struct uts_namespace *: &(__ns)->ns) + +#define ns_init_inum(__ns) \ + _Generic((__ns), \ + struct cgroup_namespace *: CGROUP_NS_INIT_INO, \ + struct ipc_namespace *: IPC_NS_INIT_INO, \ + struct mnt_namespace *: MNT_NS_INIT_INO, \ + struct net *: NET_NS_INIT_INO, \ + struct pid_namespace *: PID_NS_INIT_INO, \ + struct time_namespace *: TIME_NS_INIT_INO, \ + struct user_namespace *: USER_NS_INIT_INO, \ + struct uts_namespace *: UTS_NS_INIT_INO) + +#define ns_init_ns(__ns) \ + _Generic((__ns), \ + struct cgroup_namespace *: &init_cgroup_ns, \ + struct ipc_namespace *: &init_ipc_ns, \ + struct mnt_namespace *: &init_mnt_ns, \ + struct net *: &init_net, \ + struct pid_namespace *: &init_pid_ns, \ + struct time_namespace *: &init_time_ns, \ + struct user_namespace *: &init_user_ns, \ + struct uts_namespace *: &init_uts_ns) + +#define to_ns_operations(__ns) \ + _Generic((__ns), \ + struct cgroup_namespace *: (IS_ENABLED(CONFIG_CGROUPS) ? &cgroupns_operations : NULL), \ + struct ipc_namespace *: (IS_ENABLED(CONFIG_IPC_NS) ? &ipcns_operations : NULL), \ + struct mnt_namespace *: &mntns_operations, \ + struct net *: (IS_ENABLED(CONFIG_NET_NS) ? &netns_operations : NULL), \ + struct pid_namespace *: (IS_ENABLED(CONFIG_PID_NS) ? &pidns_operations : NULL), \ + struct time_namespace *: (IS_ENABLED(CONFIG_TIME_NS) ? &timens_operations : NULL), \ + struct user_namespace *: (IS_ENABLED(CONFIG_USER_NS) ? &userns_operations : NULL), \ + struct uts_namespace *: (IS_ENABLED(CONFIG_UTS_NS) ? &utsns_operations : NULL)) + +#define ns_common_type(__ns) \ + _Generic((__ns), \ + struct cgroup_namespace *: CLONE_NEWCGROUP, \ + struct ipc_namespace *: CLONE_NEWIPC, \ + struct mnt_namespace *: CLONE_NEWNS, \ + struct net *: CLONE_NEWNET, \ + struct pid_namespace *: CLONE_NEWPID, \ + struct time_namespace *: CLONE_NEWTIME, \ + struct user_namespace *: CLONE_NEWUSER, \ + struct uts_namespace *: CLONE_NEWUTS) + +#define ns_common_init(__ns) \ + __ns_common_init(to_ns_common(__ns), \ + ns_common_type(__ns), \ + to_ns_operations(__ns), \ + (((__ns) == ns_init_ns(__ns)) ? ns_init_inum(__ns) : 0)) + +#define ns_common_init_inum(__ns, __inum) \ + __ns_common_init(to_ns_common(__ns), \ + ns_common_type(__ns), \ + to_ns_operations(__ns), \ + __inum) + +#define ns_common_free(__ns) __ns_common_free(to_ns_common((__ns))) + +static __always_inline __must_check bool __ns_ref_put(struct ns_common *ns) +{ + return refcount_dec_and_test(&ns->__ns_ref); +} + +static __always_inline __must_check bool __ns_ref_get(struct ns_common *ns) +{ + return refcount_inc_not_zero(&ns->__ns_ref); +} + +#define ns_ref_read(__ns) refcount_read(&to_ns_common((__ns))->__ns_ref) +#define ns_ref_inc(__ns) refcount_inc(&to_ns_common((__ns))->__ns_ref) +#define ns_ref_get(__ns) __ns_ref_get(to_ns_common((__ns))) +#define ns_ref_put(__ns) __ns_ref_put(to_ns_common((__ns))) +#define ns_ref_put_and_lock(__ns, __lock) \ + refcount_dec_and_lock(&to_ns_common((__ns))->__ns_ref, (__lock)) + #endif diff --git a/include/linux/nsfs.h b/include/linux/nsfs.h new file mode 100644 index 000000000000..e5a5fa83d36b --- /dev/null +++ b/include/linux/nsfs.h @@ -0,0 +1,40 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2025 Christian Brauner <brauner@kernel.org> */ + +#ifndef _LINUX_NSFS_H +#define _LINUX_NSFS_H + +#include <linux/ns_common.h> +#include <linux/cred.h> +#include <linux/pid_namespace.h> + +struct path; +struct task_struct; +struct proc_ns_operations; + +int ns_get_path(struct path *path, struct task_struct *task, + const struct proc_ns_operations *ns_ops); +typedef struct ns_common *ns_get_path_helper_t(void *); +int ns_get_path_cb(struct path *path, ns_get_path_helper_t ns_get_cb, + void *private_data); + +bool ns_match(const struct ns_common *ns, dev_t dev, ino_t ino); + +int ns_get_name(char *buf, size_t size, struct task_struct *task, + const struct proc_ns_operations *ns_ops); +void nsfs_init(void); + +#define __current_namespace_from_type(__ns) \ + _Generic((__ns), \ + struct cgroup_namespace *: current->nsproxy->cgroup_ns, \ + struct ipc_namespace *: current->nsproxy->ipc_ns, \ + struct net *: current->nsproxy->net_ns, \ + struct pid_namespace *: task_active_pid_ns(current), \ + struct mnt_namespace *: current->nsproxy->mnt_ns, \ + struct time_namespace *: current->nsproxy->time_ns, \ + struct user_namespace *: current_user_ns(), \ + struct uts_namespace *: current->nsproxy->uts_ns) + +#define current_in_namespace(__ns) (__current_namespace_from_type(__ns) == __ns) + +#endif /* _LINUX_NSFS_H */ diff --git a/include/linux/nsproxy.h b/include/linux/nsproxy.h index dab6a1734a22..bd118a187dec 100644 --- a/include/linux/nsproxy.h +++ b/include/linux/nsproxy.h @@ -42,17 +42,6 @@ struct nsproxy { }; extern struct nsproxy init_nsproxy; -#define to_ns_common(__ns) \ - _Generic((__ns), \ - struct cgroup_namespace *: &(__ns->ns), \ - struct ipc_namespace *: &(__ns->ns), \ - struct net *: &(__ns->ns), \ - struct pid_namespace *: &(__ns->ns), \ - struct mnt_namespace *: &(__ns->ns), \ - struct time_namespace *: &(__ns->ns), \ - struct user_namespace *: &(__ns->ns), \ - struct uts_namespace *: &(__ns->ns)) - /* * A structure to encompass all bits needed to install * a partial or complete new set of namespaces. @@ -103,7 +92,7 @@ static inline struct cred *nsset_cred(struct nsset *set) * */ -int copy_namespaces(unsigned long flags, struct task_struct *tsk); +int copy_namespaces(u64 flags, struct task_struct *tsk); void exit_task_namespaces(struct task_struct *tsk); void switch_task_namespaces(struct task_struct *tsk, struct nsproxy *new); int exec_task_namespaces(void); diff --git a/include/linux/nstree.h b/include/linux/nstree.h new file mode 100644 index 000000000000..8b8636690473 --- /dev/null +++ b/include/linux/nstree.h @@ -0,0 +1,78 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_NSTREE_H +#define _LINUX_NSTREE_H + +#include <linux/ns_common.h> +#include <linux/nsproxy.h> +#include <linux/rbtree.h> +#include <linux/seqlock.h> +#include <linux/rculist.h> +#include <linux/cookie.h> + +extern struct ns_tree cgroup_ns_tree; +extern struct ns_tree ipc_ns_tree; +extern struct ns_tree mnt_ns_tree; +extern struct ns_tree net_ns_tree; +extern struct ns_tree pid_ns_tree; +extern struct ns_tree time_ns_tree; +extern struct ns_tree user_ns_tree; +extern struct ns_tree uts_ns_tree; + +#define to_ns_tree(__ns) \ + _Generic((__ns), \ + struct cgroup_namespace *: &(cgroup_ns_tree), \ + struct ipc_namespace *: &(ipc_ns_tree), \ + struct net *: &(net_ns_tree), \ + struct pid_namespace *: &(pid_ns_tree), \ + struct mnt_namespace *: &(mnt_ns_tree), \ + struct time_namespace *: &(time_ns_tree), \ + struct user_namespace *: &(user_ns_tree), \ + struct uts_namespace *: &(uts_ns_tree)) + +u64 ns_tree_gen_id(struct ns_common *ns); +void __ns_tree_add_raw(struct ns_common *ns, struct ns_tree *ns_tree); +void __ns_tree_remove(struct ns_common *ns, struct ns_tree *ns_tree); +struct ns_common *ns_tree_lookup_rcu(u64 ns_id, int ns_type); +struct ns_common *__ns_tree_adjoined_rcu(struct ns_common *ns, + struct ns_tree *ns_tree, + bool previous); + +static inline void __ns_tree_add(struct ns_common *ns, struct ns_tree *ns_tree) +{ + ns_tree_gen_id(ns); + __ns_tree_add_raw(ns, ns_tree); +} + +/** + * ns_tree_add_raw - Add a namespace to a namespace + * @ns: Namespace to add + * + * This function adds a namespace to the appropriate namespace tree + * without assigning a id. + */ +#define ns_tree_add_raw(__ns) __ns_tree_add_raw(to_ns_common(__ns), to_ns_tree(__ns)) + +/** + * ns_tree_add - Add a namespace to a namespace tree + * @ns: Namespace to add + * + * This function assigns a new id to the namespace and adds it to the + * appropriate namespace tree and list. + */ +#define ns_tree_add(__ns) __ns_tree_add(to_ns_common(__ns), to_ns_tree(__ns)) + +/** + * ns_tree_remove - Remove a namespace from a namespace tree + * @ns: Namespace to remove + * + * This function removes a namespace from the appropriate namespace + * tree and list. + */ +#define ns_tree_remove(__ns) __ns_tree_remove(to_ns_common(__ns), to_ns_tree(__ns)) + +#define ns_tree_adjoined_rcu(__ns, __previous) \ + __ns_tree_adjoined_rcu(to_ns_common(__ns), to_ns_tree(__ns), __previous) + +#define ns_tree_active(__ns) (!RB_EMPTY_NODE(&to_ns_common(__ns)->ns_tree_node)) + +#endif /* _LINUX_NSTREE_H */ diff --git a/include/linux/pagewalk.h b/include/linux/pagewalk.h index 682472c15495..88e18615dd72 100644 --- a/include/linux/pagewalk.h +++ b/include/linux/pagewalk.h @@ -134,6 +134,9 @@ int walk_page_range(struct mm_struct *mm, unsigned long start, int walk_kernel_page_table_range(unsigned long start, unsigned long end, const struct mm_walk_ops *ops, pgd_t *pgd, void *private); +int walk_kernel_page_table_range_lockless(unsigned long start, + unsigned long end, const struct mm_walk_ops *ops, + pgd_t *pgd, void *private); int walk_page_range_vma(struct vm_area_struct *vma, unsigned long start, unsigned long end, const struct mm_walk_ops *ops, void *private); diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index 2b80fd456c8b..25a7257052ff 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -232,9 +232,9 @@ static inline int pmd_dirty(pmd_t pmd) * and the mode cannot be used in interrupt context. */ #ifndef __HAVE_ARCH_ENTER_LAZY_MMU_MODE -#define arch_enter_lazy_mmu_mode() do {} while (0) -#define arch_leave_lazy_mmu_mode() do {} while (0) -#define arch_flush_lazy_mmu_mode() do {} while (0) +static inline void arch_enter_lazy_mmu_mode(void) {} +static inline void arch_leave_lazy_mmu_mode(void) {} +static inline void arch_flush_lazy_mmu_mode(void) {} #endif #ifndef pte_batch_hint diff --git a/include/linux/pid_namespace.h b/include/linux/pid_namespace.h index 7c67a5811199..445517a72ad0 100644 --- a/include/linux/pid_namespace.h +++ b/include/linux/pid_namespace.h @@ -54,10 +54,15 @@ extern struct pid_namespace init_pid_ns; #define PIDNS_ADDING (1U << 31) #ifdef CONFIG_PID_NS +static inline struct pid_namespace *to_pid_ns(struct ns_common *ns) +{ + return container_of(ns, struct pid_namespace, ns); +} + static inline struct pid_namespace *get_pid_ns(struct pid_namespace *ns) { if (ns != &init_pid_ns) - refcount_inc(&ns->ns.count); + ns_ref_inc(ns); return ns; } @@ -78,12 +83,15 @@ static inline int pidns_memfd_noexec_scope(struct pid_namespace *ns) } #endif -extern struct pid_namespace *copy_pid_ns(unsigned long flags, +extern struct pid_namespace *copy_pid_ns(u64 flags, struct user_namespace *user_ns, struct pid_namespace *ns); extern void zap_pid_ns_processes(struct pid_namespace *pid_ns); extern int reboot_pid_ns(struct pid_namespace *pid_ns, int cmd); extern void put_pid_ns(struct pid_namespace *ns); +extern bool pidns_is_ancestor(struct pid_namespace *child, + struct pid_namespace *ancestor); + #else /* !CONFIG_PID_NS */ #include <linux/err.h> @@ -97,7 +105,7 @@ static inline int pidns_memfd_noexec_scope(struct pid_namespace *ns) return 0; } -static inline struct pid_namespace *copy_pid_ns(unsigned long flags, +static inline struct pid_namespace *copy_pid_ns(u64 flags, struct user_namespace *user_ns, struct pid_namespace *ns) { if (flags & CLONE_NEWPID) @@ -118,6 +126,12 @@ static inline int reboot_pid_ns(struct pid_namespace *pid_ns, int cmd) { return 0; } + +static inline bool pidns_is_ancestor(struct pid_namespace *child, + struct pid_namespace *ancestor) +{ + return false; +} #endif /* CONFIG_PID_NS */ extern struct pid_namespace *task_active_pid_ns(struct task_struct *tsk); diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index c84edf217819..f67a2cb7d781 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -115,6 +115,12 @@ struct dev_pm_domain_list { * genpd provider specific way, likely through a * parent device node. This flag makes genpd to * skip its internal support for this. + * + * GENPD_FLAG_NO_STAY_ON: For genpd OF providers a powered-on PM domain at + * initialization is prevented from being + * powered-off until the ->sync_state() callback is + * invoked. This flag informs genpd to allow a + * power-off without waiting for ->sync_state(). */ #define GENPD_FLAG_PM_CLK (1U << 0) #define GENPD_FLAG_IRQ_SAFE (1U << 1) @@ -126,6 +132,7 @@ struct dev_pm_domain_list { #define GENPD_FLAG_OPP_TABLE_FW (1U << 7) #define GENPD_FLAG_DEV_NAME_FW (1U << 8) #define GENPD_FLAG_NO_SYNC_STATE (1U << 9) +#define GENPD_FLAG_NO_STAY_ON (1U << 10) enum gpd_status { GENPD_STATE_ON = 0, /* PM domain is on */ diff --git a/include/linux/proc_ns.h b/include/linux/proc_ns.h index 4b20375f3783..e81b8e596e4f 100644 --- a/include/linux/proc_ns.h +++ b/include/linux/proc_ns.h @@ -5,7 +5,7 @@ #ifndef _LINUX_PROC_NS_H #define _LINUX_PROC_NS_H -#include <linux/ns_common.h> +#include <linux/nsfs.h> #include <uapi/linux/nsfs.h> struct pid_namespace; @@ -17,7 +17,6 @@ struct inode; struct proc_ns_operations { const char *name; const char *real_ns_name; - int type; struct ns_common *(*get)(struct task_struct *task); void (*put)(struct ns_common *ns); int (*install)(struct nsset *nsset, struct ns_common *ns); @@ -66,25 +65,6 @@ static inline void proc_free_inum(unsigned int inum) {} #endif /* CONFIG_PROC_FS */ -static inline int ns_alloc_inum(struct ns_common *ns) -{ - WRITE_ONCE(ns->stashed, NULL); - return proc_alloc_inum(&ns->inum); -} - -#define ns_free_inum(ns) proc_free_inum((ns)->inum) - #define get_proc_ns(inode) ((struct ns_common *)(inode)->i_private) -extern int ns_get_path(struct path *path, struct task_struct *task, - const struct proc_ns_operations *ns_ops); -typedef struct ns_common *ns_get_path_helper_t(void *); -extern int ns_get_path_cb(struct path *path, ns_get_path_helper_t ns_get_cb, - void *private_data); - -extern bool ns_match(const struct ns_common *ns, dev_t dev, ino_t ino); - -extern int ns_get_name(char *buf, size_t size, struct task_struct *task, - const struct proc_ns_operations *ns_ops); -extern void nsfs_init(void); #endif /* _LINUX_PROC_NS_H */ diff --git a/include/linux/rseq.h b/include/linux/rseq.h index bc8af3eb5598..a96fd345aa38 100644 --- a/include/linux/rseq.h +++ b/include/linux/rseq.h @@ -65,7 +65,7 @@ static inline void rseq_migrate(struct task_struct *t) * If parent process has a registered restartable sequences area, the * child inherits. Unregister rseq for a clone with CLONE_VM set. */ -static inline void rseq_fork(struct task_struct *t, unsigned long clone_flags) +static inline void rseq_fork(struct task_struct *t, u64 clone_flags) { if (clone_flags & CLONE_VM) { t->rseq = NULL; @@ -107,7 +107,7 @@ static inline void rseq_preempt(struct task_struct *t) static inline void rseq_migrate(struct task_struct *t) { } -static inline void rseq_fork(struct task_struct *t, unsigned long clone_flags) +static inline void rseq_fork(struct task_struct *t, u64 clone_flags) { } static inline void rseq_execve(struct task_struct *t) diff --git a/include/linux/rv.h b/include/linux/rv.h index 14410a42faef..9520aab34bcb 100644 --- a/include/linux/rv.h +++ b/include/linux/rv.h @@ -7,16 +7,14 @@ #ifndef _LINUX_RV_H #define _LINUX_RV_H -#include <linux/types.h> -#include <linux/list.h> - #define MAX_DA_NAME_LEN 32 #define MAX_DA_RETRY_RACING_EVENTS 3 #ifdef CONFIG_RV +#include <linux/array_size.h> #include <linux/bitops.h> +#include <linux/list.h> #include <linux/types.h> -#include <linux/array_size.h> /* * Deterministic automaton per-object variables. diff --git a/include/linux/rw_hint.h b/include/linux/rw_hint.h index 309ca72f2dfb..adcc43042c90 100644 --- a/include/linux/rw_hint.h +++ b/include/linux/rw_hint.h @@ -14,6 +14,7 @@ enum rw_hint { WRITE_LIFE_MEDIUM = RWH_WRITE_LIFE_MEDIUM, WRITE_LIFE_LONG = RWH_WRITE_LIFE_LONG, WRITE_LIFE_EXTREME = RWH_WRITE_LIFE_EXTREME, + WRITE_LIFE_HINT_NR, } __packed; /* Sparse ignores __packed annotations on enums, hence the #ifndef below. */ diff --git a/include/linux/sched.h b/include/linux/sched.h index f8188b833350..e4ce0a76831e 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -706,7 +706,6 @@ struct sched_dl_entity { unsigned int dl_defer : 1; unsigned int dl_defer_armed : 1; unsigned int dl_defer_running : 1; - unsigned int dl_server_idle : 1; /* * Bandwidth enforcement timer. Each -deadline task has its @@ -733,7 +732,6 @@ struct sched_dl_entity { * runnable task. */ struct rq *rq; - dl_server_has_tasks_f server_has_tasks; dl_server_pick_f server_pick_task; #ifdef CONFIG_RT_MUTEXES diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h index ea41795a352b..34d6a0e108c3 100644 --- a/include/linux/sched/task.h +++ b/include/linux/sched/task.h @@ -63,7 +63,7 @@ extern int lockdep_tasklist_lock_is_held(void); extern asmlinkage void schedule_tail(struct task_struct *prev); extern void init_idle(struct task_struct *idle, int cpu); -extern int sched_fork(unsigned long clone_flags, struct task_struct *p); +extern int sched_fork(u64 clone_flags, struct task_struct *p); extern int sched_cgroup_fork(struct task_struct *p, struct kernel_clone_args *kargs); extern void sched_cancel_fork(struct task_struct *p); extern void sched_post_fork(struct task_struct *p); diff --git a/include/linux/security.h b/include/linux/security.h index 521bcb5b9717..9a1d4a6c8673 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -489,7 +489,7 @@ int security_file_receive(struct file *file); int security_file_open(struct file *file); int security_file_post_open(struct file *file, int mask); int security_file_truncate(struct file *file); -int security_task_alloc(struct task_struct *task, unsigned long clone_flags); +int security_task_alloc(struct task_struct *task, u64 clone_flags); void security_task_free(struct task_struct *task); int security_cred_alloc_blank(struct cred *cred, gfp_t gfp); void security_cred_free(struct cred *cred); @@ -1215,7 +1215,7 @@ static inline int security_file_truncate(struct file *file) } static inline int security_task_alloc(struct task_struct *task, - unsigned long clone_flags) + u64 clone_flags) { return 0; } diff --git a/include/linux/sem.h b/include/linux/sem.h index c4deefe42aeb..275269ce2ec8 100644 --- a/include/linux/sem.h +++ b/include/linux/sem.h @@ -9,12 +9,12 @@ struct task_struct; #ifdef CONFIG_SYSVIPC -extern int copy_semundo(unsigned long clone_flags, struct task_struct *tsk); +extern int copy_semundo(u64 clone_flags, struct task_struct *tsk); extern void exit_sem(struct task_struct *tsk); #else -static inline int copy_semundo(unsigned long clone_flags, struct task_struct *tsk) +static inline int copy_semundo(u64 clone_flags, struct task_struct *tsk) { return 0; } diff --git a/include/linux/stddef.h b/include/linux/stddef.h index dab49e2ec8c0..80b6bfb944f0 100644 --- a/include/linux/stddef.h +++ b/include/linux/stddef.h @@ -94,7 +94,8 @@ enum { __DECLARE_FLEX_ARRAY(TYPE, NAME) /** - * TRAILING_OVERLAP() - Overlap a flexible-array member with trailing members. + * __TRAILING_OVERLAP() - Overlap a flexible-array member with trailing + * members. * * Creates a union between a flexible-array member (FAM) in a struct and a set * of additional members that would otherwise follow it. @@ -102,15 +103,30 @@ enum { * @TYPE: Flexible structure type name, including "struct" keyword. * @NAME: Name for a variable to define. * @FAM: The flexible-array member within @TYPE + * @ATTRS: Any struct attributes (usually empty) * @MEMBERS: Trailing overlapping members. */ -#define TRAILING_OVERLAP(TYPE, NAME, FAM, MEMBERS) \ +#define __TRAILING_OVERLAP(TYPE, NAME, FAM, ATTRS, MEMBERS) \ union { \ TYPE NAME; \ struct { \ - unsigned char __offset_to_##FAM[offsetof(TYPE, FAM)]; \ + unsigned char __offset_to_FAM[offsetof(TYPE, FAM)]; \ MEMBERS \ - }; \ + } ATTRS; \ } +/** + * TRAILING_OVERLAP() - Overlap a flexible-array member with trailing members. + * + * Creates a union between a flexible-array member (FAM) in a struct and a set + * of additional members that would otherwise follow it. + * + * @TYPE: Flexible structure type name, including "struct" keyword. + * @NAME: Name for a variable to define. + * @FAM: The flexible-array member within @TYPE + * @MEMBERS: Trailing overlapping members. + */ +#define TRAILING_OVERLAP(TYPE, NAME, FAM, MEMBERS) \ + __TRAILING_OVERLAP(TYPE, NAME, FAM, /* no attrs */, MEMBERS) + #endif diff --git a/include/linux/string_choices.h b/include/linux/string_choices.h index f3ba4f52ff26..6c4077be7742 100644 --- a/include/linux/string_choices.h +++ b/include/linux/string_choices.h @@ -17,6 +17,12 @@ #include <linux/types.h> +static inline const char *str_assert_deassert(bool v) +{ + return v ? "assert" : "deassert"; +} +#define str_deassert_assert(v) str_assert_deassert(!(v)) + static inline const char *str_enable_disable(bool v) { return v ? "enable" : "disable"; diff --git a/include/linux/swap.h b/include/linux/swap.h index 2fe6ed2cc3fd..7012a0f758d8 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -385,6 +385,16 @@ void folio_add_lru_vma(struct folio *, struct vm_area_struct *); void mark_page_accessed(struct page *); void folio_mark_accessed(struct folio *); +static inline bool folio_may_be_lru_cached(struct folio *folio) +{ + /* + * Holding PMD-sized folios in per-CPU LRU cache unbalances accounting. + * Holding small numbers of low-order mTHP folios in per-CPU LRU cache + * will be sensible, but nobody has implemented and tested that yet. + */ + return !folio_test_large(folio); +} + extern atomic_t lru_disable_count; static inline bool lru_cache_disabled(void) diff --git a/include/linux/time_namespace.h b/include/linux/time_namespace.h index bb2c52f4fc94..c514d0e5a45c 100644 --- a/include/linux/time_namespace.h +++ b/include/linux/time_namespace.h @@ -33,17 +33,22 @@ struct time_namespace { extern struct time_namespace init_time_ns; #ifdef CONFIG_TIME_NS +static inline struct time_namespace *to_time_ns(struct ns_common *ns) +{ + return container_of(ns, struct time_namespace, ns); +} +void __init time_ns_init(void); extern int vdso_join_timens(struct task_struct *task, struct time_namespace *ns); extern void timens_commit(struct task_struct *tsk, struct time_namespace *ns); static inline struct time_namespace *get_time_ns(struct time_namespace *ns) { - refcount_inc(&ns->ns.count); + ns_ref_inc(ns); return ns; } -struct time_namespace *copy_time_ns(unsigned long flags, +struct time_namespace *copy_time_ns(u64 flags, struct user_namespace *user_ns, struct time_namespace *old_ns); void free_time_ns(struct time_namespace *ns); @@ -52,7 +57,7 @@ struct page *find_timens_vvar_page(struct vm_area_struct *vma); static inline void put_time_ns(struct time_namespace *ns) { - if (refcount_dec_and_test(&ns->ns.count)) + if (ns_ref_put(ns)) free_time_ns(ns); } @@ -108,6 +113,10 @@ static inline ktime_t timens_ktime_to_host(clockid_t clockid, ktime_t tim) } #else +static inline void __init time_ns_init(void) +{ +} + static inline int vdso_join_timens(struct task_struct *task, struct time_namespace *ns) { @@ -129,7 +138,7 @@ static inline void put_time_ns(struct time_namespace *ns) } static inline -struct time_namespace *copy_time_ns(unsigned long flags, +struct time_namespace *copy_time_ns(u64 flags, struct user_namespace *user_ns, struct time_namespace *old_ns) { diff --git a/include/linux/uprobes.h b/include/linux/uprobes.h index 516217c39094..915303a82d84 100644 --- a/include/linux/uprobes.h +++ b/include/linux/uprobes.h @@ -205,7 +205,7 @@ extern void uprobe_start_dup_mmap(void); extern void uprobe_end_dup_mmap(void); extern void uprobe_dup_mmap(struct mm_struct *oldmm, struct mm_struct *newmm); extern void uprobe_free_utask(struct task_struct *t); -extern void uprobe_copy_process(struct task_struct *t, unsigned long flags); +extern void uprobe_copy_process(struct task_struct *t, u64 flags); extern int uprobe_post_sstep_notifier(struct pt_regs *regs); extern int uprobe_pre_sstep_notifier(struct pt_regs *regs); extern void uprobe_notify_resume(struct pt_regs *regs); @@ -281,7 +281,7 @@ static inline bool uprobe_deny_signal(void) static inline void uprobe_free_utask(struct task_struct *t) { } -static inline void uprobe_copy_process(struct task_struct *t, unsigned long flags) +static inline void uprobe_copy_process(struct task_struct *t, u64 flags) { } static inline void uprobe_clear_state(struct mm_struct *mm) diff --git a/include/linux/user_events.h b/include/linux/user_events.h index 8afa8c3a0973..57d1ff006090 100644 --- a/include/linux/user_events.h +++ b/include/linux/user_events.h @@ -33,7 +33,7 @@ extern void user_event_mm_dup(struct task_struct *t, extern void user_event_mm_remove(struct task_struct *t); static inline void user_events_fork(struct task_struct *t, - unsigned long clone_flags) + u64 clone_flags) { struct user_event_mm *old_mm; @@ -68,7 +68,7 @@ static inline void user_events_exit(struct task_struct *t) } #else static inline void user_events_fork(struct task_struct *t, - unsigned long clone_flags) + u64 clone_flags) { } diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h index a0bb6d012137..9a9aebbf96b9 100644 --- a/include/linux/user_namespace.h +++ b/include/linux/user_namespace.h @@ -168,10 +168,15 @@ static inline void set_userns_rlimit_max(struct user_namespace *ns, #ifdef CONFIG_USER_NS +static inline struct user_namespace *to_user_ns(struct ns_common *ns) +{ + return container_of(ns, struct user_namespace, ns); +} + static inline struct user_namespace *get_user_ns(struct user_namespace *ns) { if (ns) - refcount_inc(&ns->ns.count); + ns_ref_inc(ns); return ns; } @@ -181,7 +186,7 @@ extern void __put_user_ns(struct user_namespace *ns); static inline void put_user_ns(struct user_namespace *ns) { - if (ns && refcount_dec_and_test(&ns->ns.count)) + if (ns && ns_ref_put(ns)) __put_user_ns(ns); } diff --git a/include/linux/uts_namespace.h b/include/linux/uts_namespace.h new file mode 100644 index 000000000000..60f37fec0f4b --- /dev/null +++ b/include/linux/uts_namespace.h @@ -0,0 +1,65 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_UTS_NAMESPACE_H +#define _LINUX_UTS_NAMESPACE_H + +#include <linux/ns_common.h> +#include <uapi/linux/utsname.h> + +struct user_namespace; +extern struct user_namespace init_user_ns; + +struct uts_namespace { + struct new_utsname name; + struct user_namespace *user_ns; + struct ucounts *ucounts; + struct ns_common ns; +} __randomize_layout; + +extern struct uts_namespace init_uts_ns; + +#ifdef CONFIG_UTS_NS +static inline struct uts_namespace *to_uts_ns(struct ns_common *ns) +{ + return container_of(ns, struct uts_namespace, ns); +} + +static inline void get_uts_ns(struct uts_namespace *ns) +{ + ns_ref_inc(ns); +} + +extern struct uts_namespace *copy_utsname(u64 flags, + struct user_namespace *user_ns, struct uts_namespace *old_ns); +extern void free_uts_ns(struct uts_namespace *ns); + +static inline void put_uts_ns(struct uts_namespace *ns) +{ + if (ns_ref_put(ns)) + free_uts_ns(ns); +} + +void uts_ns_init(void); +#else +static inline void get_uts_ns(struct uts_namespace *ns) +{ +} + +static inline void put_uts_ns(struct uts_namespace *ns) +{ +} + +static inline struct uts_namespace *copy_utsname(u64 flags, + struct user_namespace *user_ns, struct uts_namespace *old_ns) +{ + if (flags & CLONE_NEWUTS) + return ERR_PTR(-EINVAL); + + return old_ns; +} + +static inline void uts_ns_init(void) +{ +} +#endif + +#endif /* _LINUX_UTS_NAMESPACE_H */ diff --git a/include/linux/utsname.h b/include/linux/utsname.h index bf7613ba412b..547bd4439706 100644 --- a/include/linux/utsname.h +++ b/include/linux/utsname.h @@ -7,7 +7,7 @@ #include <linux/nsproxy.h> #include <linux/ns_common.h> #include <linux/err.h> -#include <uapi/linux/utsname.h> +#include <linux/uts_namespace.h> enum uts_proc { UTS_PROC_ARCH, @@ -18,57 +18,6 @@ enum uts_proc { UTS_PROC_DOMAINNAME, }; -struct user_namespace; -extern struct user_namespace init_user_ns; - -struct uts_namespace { - struct new_utsname name; - struct user_namespace *user_ns; - struct ucounts *ucounts; - struct ns_common ns; -} __randomize_layout; -extern struct uts_namespace init_uts_ns; - -#ifdef CONFIG_UTS_NS -static inline void get_uts_ns(struct uts_namespace *ns) -{ - refcount_inc(&ns->ns.count); -} - -extern struct uts_namespace *copy_utsname(unsigned long flags, - struct user_namespace *user_ns, struct uts_namespace *old_ns); -extern void free_uts_ns(struct uts_namespace *ns); - -static inline void put_uts_ns(struct uts_namespace *ns) -{ - if (refcount_dec_and_test(&ns->ns.count)) - free_uts_ns(ns); -} - -void uts_ns_init(void); -#else -static inline void get_uts_ns(struct uts_namespace *ns) -{ -} - -static inline void put_uts_ns(struct uts_namespace *ns) -{ -} - -static inline struct uts_namespace *copy_utsname(unsigned long flags, - struct user_namespace *user_ns, struct uts_namespace *old_ns) -{ - if (flags & CLONE_NEWUTS) - return ERR_PTR(-EINVAL); - - return old_ns; -} - -static inline void uts_ns_init(void) -{ -} -#endif - #ifdef CONFIG_PROC_SYSCTL extern void uts_proc_notify(enum uts_proc proc); #else diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h index 8bf156dde554..7427b79d6f3d 100644 --- a/include/linux/virtio_config.h +++ b/include/linux/virtio_config.h @@ -193,14 +193,15 @@ static inline bool virtio_has_feature(const struct virtio_device *vdev, } static inline void virtio_get_features(struct virtio_device *vdev, - u64 *features) + u64 *features_out) { if (vdev->config->get_extended_features) { - vdev->config->get_extended_features(vdev, features); + vdev->config->get_extended_features(vdev, features_out); return; } - virtio_features_from_u64(features, vdev->config->get_features(vdev)); + virtio_features_from_u64(features_out, + vdev->config->get_features(vdev)); } /** @@ -326,11 +327,11 @@ int virtqueue_set_affinity(struct virtqueue *vq, const struct cpumask *cpu_mask) static inline bool virtio_get_shm_region(struct virtio_device *vdev, - struct virtio_shm_region *region, u8 id) + struct virtio_shm_region *region_out, u8 id) { if (!vdev->config->get_shm_region) return false; - return vdev->config->get_shm_region(vdev, region, id); + return vdev->config->get_shm_region(vdev, region_out, id); } static inline bool virtio_is_little_endian(struct virtio_device *vdev) diff --git a/include/linux/writeback.h b/include/linux/writeback.h index a2848d731a46..15a4bc4ab819 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -265,6 +265,8 @@ static inline void wbc_init_bio(struct writeback_control *wbc, struct bio *bio) bio_associate_blkg_from_css(bio, wbc->wb->blkcg_css); } +void inode_switch_wbs_work_fn(struct work_struct *work); + #else /* CONFIG_CGROUP_WRITEBACK */ static inline void inode_attach_wb(struct inode *inode, struct folio *folio) diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 6906af7a8f24..6560b32f3125 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -1245,6 +1245,27 @@ static inline struct hci_conn *hci_conn_hash_lookup_ba(struct hci_dev *hdev, return NULL; } +static inline struct hci_conn *hci_conn_hash_lookup_role(struct hci_dev *hdev, + __u8 type, __u8 role, + bdaddr_t *ba) +{ + struct hci_conn_hash *h = &hdev->conn_hash; + struct hci_conn *c; + + rcu_read_lock(); + + list_for_each_entry_rcu(c, &h->list, list) { + if (c->type == type && c->role == role && !bacmp(&c->dst, ba)) { + rcu_read_unlock(); + return c; + } + } + + rcu_read_unlock(); + + return NULL; +} + static inline struct hci_conn *hci_conn_hash_lookup_le(struct hci_dev *hdev, bdaddr_t *ba, __u8 ba_type) diff --git a/include/net/dst_metadata.h b/include/net/dst_metadata.h index 4160731dcb6e..1fc2fb03ce3f 100644 --- a/include/net/dst_metadata.h +++ b/include/net/dst_metadata.h @@ -3,6 +3,7 @@ #define __NET_DST_METADATA_H 1 #include <linux/skbuff.h> +#include <net/ip.h> #include <net/ip_tunnels.h> #include <net/macsec.h> #include <net/dst.h> @@ -220,9 +221,15 @@ static inline struct metadata_dst *ip_tun_rx_dst(struct sk_buff *skb, int md_size) { const struct iphdr *iph = ip_hdr(skb); + struct metadata_dst *tun_dst; + + tun_dst = __ip_tun_set_dst(iph->saddr, iph->daddr, iph->tos, iph->ttl, + 0, flags, tunnel_id, md_size); - return __ip_tun_set_dst(iph->saddr, iph->daddr, iph->tos, iph->ttl, - 0, flags, tunnel_id, md_size); + if (tun_dst && (iph->frag_off & htons(IP_DF))) + __set_bit(IP_TUNNEL_DONT_FRAGMENT_BIT, + tun_dst->u.tun_info.key.tun_flags); + return tun_dst; } static inline struct metadata_dst *__ipv6_tun_set_dst(const struct in6_addr *saddr, diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index 025a7574b275..cb664f6e3558 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -204,7 +204,7 @@ struct net { extern struct net init_net; #ifdef CONFIG_NET_NS -struct net *copy_net_ns(unsigned long flags, struct user_namespace *user_ns, +struct net *copy_net_ns(u64 flags, struct user_namespace *user_ns, struct net *old_net); void net_ns_get_ownership(const struct net *net, kuid_t *uid, kgid_t *gid); @@ -218,7 +218,7 @@ extern struct task_struct *cleanup_net_task; #else /* CONFIG_NET_NS */ #include <linux/sched.h> #include <linux/nsproxy.h> -static inline struct net *copy_net_ns(unsigned long flags, +static inline struct net *copy_net_ns(u64 flags, struct user_namespace *user_ns, struct net *old_net) { if (flags & CLONE_NEWNET) @@ -262,10 +262,15 @@ void ipx_unregister_sysctl(void); #ifdef CONFIG_NET_NS void __put_net(struct net *net); +static inline struct net *to_net_ns(struct ns_common *ns) +{ + return container_of(ns, struct net, ns); +} + /* Try using get_net_track() instead */ static inline struct net *get_net(struct net *net) { - refcount_inc(&net->ns.count); + ns_ref_inc(net); return net; } @@ -276,7 +281,7 @@ static inline struct net *maybe_get_net(struct net *net) * exists. If the reference count is zero this * function fails and returns NULL. */ - if (!refcount_inc_not_zero(&net->ns.count)) + if (!ns_ref_get(net)) net = NULL; return net; } @@ -284,7 +289,7 @@ static inline struct net *maybe_get_net(struct net *net) /* Try using put_net_track() instead */ static inline void put_net(struct net *net) { - if (refcount_dec_and_test(&net->ns.count)) + if (ns_ref_put(net)) __put_net(net); } @@ -296,7 +301,7 @@ int net_eq(const struct net *net1, const struct net *net2) static inline int check_net(const struct net *net) { - return refcount_read(&net->ns.count) != 0; + return ns_ref_read(net) != 0; } void net_drop_ns(void *); diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 891e43a01bdc..3faa80f5d801 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -1912,7 +1912,6 @@ struct nftables_pernet { struct mutex commit_mutex; u64 table_handle; u64 tstamp; - unsigned int base_seq; unsigned int gc_seq; u8 validate_state; struct work_struct destroy_work; diff --git a/include/net/netfilter/nf_tables_core.h b/include/net/netfilter/nf_tables_core.h index 6c2f483d9828..656e784714f3 100644 --- a/include/net/netfilter/nf_tables_core.h +++ b/include/net/netfilter/nf_tables_core.h @@ -109,17 +109,11 @@ nft_hash_lookup_fast(const struct net *net, const struct nft_set *set, const struct nft_set_ext * nft_hash_lookup(const struct net *net, const struct nft_set *set, const u32 *key); +#endif + const struct nft_set_ext * nft_set_do_lookup(const struct net *net, const struct nft_set *set, const u32 *key); -#else -static inline const struct nft_set_ext * -nft_set_do_lookup(const struct net *net, const struct nft_set *set, - const u32 *key) -{ - return set->ops->lookup(net, set, key); -} -#endif /* called from nft_pipapo_avx2.c */ const struct nft_set_ext * diff --git a/include/net/netns/nftables.h b/include/net/netns/nftables.h index cc8060c017d5..99dd166c5d07 100644 --- a/include/net/netns/nftables.h +++ b/include/net/netns/nftables.h @@ -3,6 +3,7 @@ #define _NETNS_NFTABLES_H_ struct netns_nftables { + unsigned int base_seq; u8 gencursor; }; diff --git a/include/net/sock.h b/include/net/sock.h index fb13322a11fc..2e14283c5be1 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -2061,6 +2061,9 @@ static inline void sk_set_socket(struct sock *sk, struct socket *sock) if (sock) { WRITE_ONCE(sk->sk_uid, SOCK_INODE(sock)->i_uid); WRITE_ONCE(sk->sk_ino, SOCK_INODE(sock)->i_ino); + } else { + /* Note: sk_uid is unchanged. */ + WRITE_ONCE(sk->sk_ino, 0); } } @@ -2082,8 +2085,6 @@ static inline void sock_orphan(struct sock *sk) sock_set_flag(sk, SOCK_DEAD); sk_set_socket(sk, NULL); sk->sk_wq = NULL; - /* Note: sk_uid is unchanged. */ - WRITE_ONCE(sk->sk_ino, 0); write_unlock_bh(&sk->sk_callback_lock); } diff --git a/include/rv/ltl_monitor.h b/include/rv/ltl_monitor.h index 67031a774e3d..5368cf5fd623 100644 --- a/include/rv/ltl_monitor.h +++ b/include/rv/ltl_monitor.h @@ -56,7 +56,7 @@ static void ltl_task_init(struct task_struct *task, bool task_creation) ltl_atoms_fetch(task, mon); } -static void handle_task_newtask(void *data, struct task_struct *task, unsigned long flags) +static void handle_task_newtask(void *data, struct task_struct *task, u64 flags) { ltl_task_init(task, true); } diff --git a/include/sound/sdca.h b/include/sound/sdca.h index 5a5d6de78d72..9c6a351c9d47 100644 --- a/include/sound/sdca.h +++ b/include/sound/sdca.h @@ -46,6 +46,7 @@ struct sdca_device_data { enum sdca_quirk { SDCA_QUIRKS_RT712_VB, + SDCA_QUIRKS_SKIP_FUNC_TYPE_PATCHING, }; #if IS_ENABLED(CONFIG_ACPI) && IS_ENABLED(CONFIG_SND_SOC_SDCA) diff --git a/include/sound/sdca_function.h b/include/sound/sdca_function.h index 06ec126cdcc3..ea68856e4c8c 100644 --- a/include/sound/sdca_function.h +++ b/include/sound/sdca_function.h @@ -1063,27 +1063,30 @@ struct sdca_entity_ge { /** * struct sdca_entity_hide - information specific to HIDE Entities * @hid: HID device structure - * @hidtx_ids: HIDTx Report ID * @num_hidtx_ids: number of HIDTx Report ID - * @hidrx_ids: HIDRx Report ID * @num_hidrx_ids: number of HIDRx Report ID - * @hide_reside_function_num: indicating which Audio Function Numbers within this Device - * @max_delay: the maximum time in microseconds allowed for the Device to change the ownership from Device to Host - * @af_number_list: which Audio Function Numbers within this Device are sending/receiving the messages in this HIDE - * @hid_desc: HID descriptor for the HIDE Entity + * @hidtx_ids: HIDTx Report ID + * @hidrx_ids: HIDRx Report ID + * @af_number_list: which Audio Function Numbers within this Device are + * sending/receiving the messages in this HIDE + * @hide_reside_function_num: indicating which Audio Function Numbers + * within this Device + * @max_delay: the maximum time in microseconds allowed for the Device + * to change the ownership from Device to Host * @hid_report_desc: HID Report Descriptor for the HIDE Entity + * @hid_desc: HID descriptor for the HIDE Entity */ struct sdca_entity_hide { struct hid_device *hid; unsigned int *hidtx_ids; - int num_hidtx_ids; unsigned int *hidrx_ids; + int num_hidtx_ids; int num_hidrx_ids; + unsigned int af_number_list[SDCA_MAX_FUNCTION_COUNT]; unsigned int hide_reside_function_num; unsigned int max_delay; - unsigned int af_number_list[SDCA_MAX_FUNCTION_COUNT]; - struct hid_descriptor hid_desc; unsigned char *hid_report_desc; + struct hid_descriptor hid_desc; }; /** diff --git a/include/trace/events/afs.h b/include/trace/events/afs.h index 7f83d242c8e9..1b3c48b5591d 100644 --- a/include/trace/events/afs.h +++ b/include/trace/events/afs.h @@ -69,6 +69,9 @@ enum afs_fs_operation { yfs_FS_RemoveACL = 64171, yfs_FS_RemoveFile2 = 64173, yfs_FS_StoreOpaqueACL2 = 64174, + yfs_FS_Rename_Replace = 64176, + yfs_FS_Rename_NoReplace = 64177, + yfs_FS_Rename_Exchange = 64187, yfs_FS_InlineBulkStatus = 64536, /* YFS Fetch multiple file statuses with errors */ yfs_FS_FetchData64 = 64537, /* YFS Fetch file data */ yfs_FS_StoreData64 = 64538, /* YFS Store file data */ @@ -300,6 +303,9 @@ enum yfs_cm_operation { EM(yfs_FS_RemoveACL, "YFS.RemoveACL") \ EM(yfs_FS_RemoveFile2, "YFS.RemoveFile2") \ EM(yfs_FS_StoreOpaqueACL2, "YFS.StoreOpaqueACL2") \ + EM(yfs_FS_Rename_Replace, "YFS.Rename_Replace") \ + EM(yfs_FS_Rename_NoReplace, "YFS.Rename_NoReplace") \ + EM(yfs_FS_Rename_Exchange, "YFS.Rename_Exchange") \ EM(yfs_FS_InlineBulkStatus, "YFS.InlineBulkStatus") \ EM(yfs_FS_FetchData64, "YFS.FetchData64") \ EM(yfs_FS_StoreData64, "YFS.StoreData64") \ diff --git a/include/trace/events/filelock.h b/include/trace/events/filelock.h index b8d1e00a7982..370016c38a5b 100644 --- a/include/trace/events/filelock.h +++ b/include/trace/events/filelock.h @@ -27,7 +27,8 @@ { FL_SLEEP, "FL_SLEEP" }, \ { FL_DOWNGRADE_PENDING, "FL_DOWNGRADE_PENDING" }, \ { FL_UNLOCK_PENDING, "FL_UNLOCK_PENDING" }, \ - { FL_OFDLCK, "FL_OFDLCK" }) + { FL_OFDLCK, "FL_OFDLCK" }, \ + { FL_RECLAIM, "FL_RECLAIM"}) #define show_fl_type(val) \ __print_symbolic(val, \ @@ -189,7 +190,7 @@ TRACE_EVENT(generic_add_lease, __entry->i_ino = inode->i_ino; __entry->wcount = atomic_read(&inode->i_writecount); __entry->rcount = atomic_read(&inode->i_readcount); - __entry->icount = atomic_read(&inode->i_count); + __entry->icount = icount_read(inode); __entry->owner = fl->c.flc_owner; __entry->flags = fl->c.flc_flags; __entry->type = fl->c.flc_type; diff --git a/include/trace/events/task.h b/include/trace/events/task.h index af535b053033..4f0759634306 100644 --- a/include/trace/events/task.h +++ b/include/trace/events/task.h @@ -8,14 +8,14 @@ TRACE_EVENT(task_newtask, - TP_PROTO(struct task_struct *task, unsigned long clone_flags), + TP_PROTO(struct task_struct *task, u64 clone_flags), TP_ARGS(task, clone_flags), TP_STRUCT__entry( __field( pid_t, pid) __array( char, comm, TASK_COMM_LEN) - __field( unsigned long, clone_flags) + __field( u64, clone_flags) __field( short, oom_score_adj) ), @@ -26,7 +26,7 @@ TRACE_EVENT(task_newtask, __entry->oom_score_adj = task->signal->oom_score_adj; ), - TP_printk("pid=%d comm=%s clone_flags=%lx oom_score_adj=%hd", + TP_printk("pid=%d comm=%s clone_flags=%llx oom_score_adj=%hd", __entry->pid, __entry->comm, __entry->clone_flags, __entry->oom_score_adj) ); diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h index 1e23919c0da9..c08aff044e80 100644 --- a/include/trace/events/writeback.h +++ b/include/trace/events/writeback.h @@ -213,6 +213,35 @@ TRACE_EVENT(inode_foreign_history, ) ); +TRACE_EVENT(inode_switch_wbs_queue, + + TP_PROTO(struct bdi_writeback *old_wb, struct bdi_writeback *new_wb, + unsigned int count), + + TP_ARGS(old_wb, new_wb, count), + + TP_STRUCT__entry( + __array(char, name, 32) + __field(ino_t, old_cgroup_ino) + __field(ino_t, new_cgroup_ino) + __field(unsigned int, count) + ), + + TP_fast_assign( + strscpy_pad(__entry->name, bdi_dev_name(old_wb->bdi), 32); + __entry->old_cgroup_ino = __trace_wb_assign_cgroup(old_wb); + __entry->new_cgroup_ino = __trace_wb_assign_cgroup(new_wb); + __entry->count = count; + ), + + TP_printk("bdi %s: old_cgroup_ino=%lu new_cgroup_ino=%lu count=%u", + __entry->name, + (unsigned long)__entry->old_cgroup_ino, + (unsigned long)__entry->new_cgroup_ino, + __entry->count + ) +); + TRACE_EVENT(inode_switch_wbs, TP_PROTO(struct inode *inode, struct bdi_writeback *old_wb, diff --git a/include/uapi/linux/fcntl.h b/include/uapi/linux/fcntl.h index f291ab4f94eb..3741ea1b73d8 100644 --- a/include/uapi/linux/fcntl.h +++ b/include/uapi/linux/fcntl.h @@ -111,6 +111,7 @@ #define PIDFD_SELF_THREAD_GROUP -10001 /* Current thread group leader. */ #define FD_PIDFS_ROOT -10002 /* Root of the pidfs filesystem */ +#define FD_NSFS_ROOT -10003 /* Root of the nsfs filesystem */ #define FD_INVALID -10009 /* Invalid file descriptor: -10000 - EBADF = -10009 */ /* Generic flags for the *at(2) family of syscalls. */ diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h index 0bd678a4a10e..beb4c2d1e41c 100644 --- a/include/uapi/linux/fs.h +++ b/include/uapi/linux/fs.h @@ -430,10 +430,13 @@ typedef int __bitwise __kernel_rwf_t; /* buffered IO that drops the cache after reading or writing data */ #define RWF_DONTCACHE ((__force __kernel_rwf_t)0x00000080) +/* prevent pipe and socket writes from raising SIGPIPE */ +#define RWF_NOSIGNAL ((__force __kernel_rwf_t)0x00000100) + /* mask of flags supported by the kernel */ #define RWF_SUPPORTED (RWF_HIPRI | RWF_DSYNC | RWF_SYNC | RWF_NOWAIT |\ RWF_APPEND | RWF_NOAPPEND | RWF_ATOMIC |\ - RWF_DONTCACHE) + RWF_DONTCACHE | RWF_NOSIGNAL) #define PROCFS_IOCTL_MAGIC 'f' diff --git a/include/uapi/linux/mptcp.h b/include/uapi/linux/mptcp.h index 67d015df8893..5fd5b4cf75ca 100644 --- a/include/uapi/linux/mptcp.h +++ b/include/uapi/linux/mptcp.h @@ -31,6 +31,8 @@ #define MPTCP_INFO_FLAG_FALLBACK _BITUL(0) #define MPTCP_INFO_FLAG_REMOTE_KEY_RECEIVED _BITUL(1) +#define MPTCP_PM_EV_FLAG_DENY_JOIN_ID0 _BITUL(0) + #define MPTCP_PM_ADDR_FLAG_SIGNAL (1 << 0) #define MPTCP_PM_ADDR_FLAG_SUBFLOW (1 << 1) #define MPTCP_PM_ADDR_FLAG_BACKUP (1 << 2) diff --git a/include/uapi/linux/mptcp_pm.h b/include/uapi/linux/mptcp_pm.h index 6ac84b2f636c..7359d34da446 100644 --- a/include/uapi/linux/mptcp_pm.h +++ b/include/uapi/linux/mptcp_pm.h @@ -16,10 +16,10 @@ * good time to allocate memory and send ADD_ADDR if needed. Depending on the * traffic-patterns it can take a long time until the MPTCP_EVENT_ESTABLISHED * is sent. Attributes: token, family, saddr4 | saddr6, daddr4 | daddr6, - * sport, dport, server-side. + * sport, dport, server-side, [flags]. * @MPTCP_EVENT_ESTABLISHED: A MPTCP connection is established (can start new * subflows). Attributes: token, family, saddr4 | saddr6, daddr4 | daddr6, - * sport, dport, server-side. + * sport, dport, server-side, [flags]. * @MPTCP_EVENT_CLOSED: A MPTCP connection has stopped. Attribute: token. * @MPTCP_EVENT_ANNOUNCED: A new address has been announced by the peer. * Attributes: token, rem_id, family, daddr4 | daddr6 [, dport]. diff --git a/include/uapi/linux/nsfs.h b/include/uapi/linux/nsfs.h index 97d8d80d139f..e098759ec917 100644 --- a/include/uapi/linux/nsfs.h +++ b/include/uapi/linux/nsfs.h @@ -16,8 +16,6 @@ #define NS_GET_NSTYPE _IO(NSIO, 0x3) /* Get owner UID (in the caller's user namespace) for a user namespace */ #define NS_GET_OWNER_UID _IO(NSIO, 0x4) -/* Get the id for a mount namespace */ -#define NS_GET_MNTNS_ID _IOR(NSIO, 0x5, __u64) /* Translate pid from target pid namespace into the caller's pid namespace. */ #define NS_GET_PID_FROM_PIDNS _IOR(NSIO, 0x6, int) /* Return thread-group leader id of pid in the callers pid namespace. */ @@ -42,6 +40,10 @@ struct mnt_ns_info { /* Get previous namespace. */ #define NS_MNT_GET_PREV _IOR(NSIO, 12, struct mnt_ns_info) +/* Retrieve namespace identifiers. */ +#define NS_GET_MNTNS_ID _IOR(NSIO, 5, __u64) +#define NS_GET_ID _IOR(NSIO, 13, __u64) + enum init_ns_ino { IPC_NS_INIT_INO = 0xEFFFFFFFU, UTS_NS_INIT_INO = 0xEFFFFFFEU, @@ -51,6 +53,18 @@ enum init_ns_ino { TIME_NS_INIT_INO = 0xEFFFFFFAU, NET_NS_INIT_INO = 0xEFFFFFF9U, MNT_NS_INIT_INO = 0xEFFFFFF8U, +#ifdef __KERNEL__ + MNT_NS_ANON_INO = 0xEFFFFFF7U, +#endif +}; + +struct nsfs_file_handle { + __u64 ns_id; + __u32 ns_type; + __u32 ns_inum; }; +#define NSFS_FILE_HANDLE_SIZE_VER0 16 /* sizeof first published struct */ +#define NSFS_FILE_HANDLE_SIZE_LATEST sizeof(struct nsfs_file_handle) /* sizeof latest published struct */ + #endif /* __LINUX_NSFS_H */ diff --git a/include/uapi/linux/ptp_clock.h b/include/uapi/linux/ptp_clock.h index 18eefa6d93d6..2c3346e91dbe 100644 --- a/include/uapi/linux/ptp_clock.h +++ b/include/uapi/linux/ptp_clock.h @@ -37,6 +37,9 @@ /* * flag fields valid for the new PTP_EXTTS_REQUEST2 ioctl. + * + * Note: PTP_STRICT_FLAGS is always enabled by the kernel for + * PTP_EXTTS_REQUEST2 regardless of whether it is set by userspace. */ #define PTP_EXTTS_VALID_FLAGS (PTP_ENABLE_FEATURE | \ PTP_RISING_EDGE | \ diff --git a/include/uapi/linux/vduse.h b/include/uapi/linux/vduse.h index 68a627d04afa..10ad71aa00d6 100644 --- a/include/uapi/linux/vduse.h +++ b/include/uapi/linux/vduse.h @@ -237,7 +237,7 @@ struct vduse_iova_umem { * struct vduse_iova_info - information of one IOVA region * @start: start of the IOVA region * @last: last of the IOVA region - * @capability: capability of the IOVA regsion + * @capability: capability of the IOVA region * @reserved: for future use, needs to be initialized to zero * * Structure used by VDUSE_IOTLB_GET_INFO ioctl to get information of |