diff options
Diffstat (limited to 'include')
84 files changed, 1418 insertions, 457 deletions
diff --git a/include/asm-generic/atomic64.h b/include/asm-generic/atomic64.h index d7a15096fb3b..370f01d4450f 100644 --- a/include/asm-generic/atomic64.h +++ b/include/asm-generic/atomic64.h @@ -10,24 +10,24 @@ #include <linux/types.h> typedef struct { - long long counter; + s64 counter; } atomic64_t; #define ATOMIC64_INIT(i) { (i) } -extern long long atomic64_read(const atomic64_t *v); -extern void atomic64_set(atomic64_t *v, long long i); +extern s64 atomic64_read(const atomic64_t *v); +extern void atomic64_set(atomic64_t *v, s64 i); #define atomic64_set_release(v, i) atomic64_set((v), (i)) #define ATOMIC64_OP(op) \ -extern void atomic64_##op(long long a, atomic64_t *v); +extern void atomic64_##op(s64 a, atomic64_t *v); #define ATOMIC64_OP_RETURN(op) \ -extern long long atomic64_##op##_return(long long a, atomic64_t *v); +extern s64 atomic64_##op##_return(s64 a, atomic64_t *v); #define ATOMIC64_FETCH_OP(op) \ -extern long long atomic64_fetch_##op(long long a, atomic64_t *v); +extern s64 atomic64_fetch_##op(s64 a, atomic64_t *v); #define ATOMIC64_OPS(op) ATOMIC64_OP(op) ATOMIC64_OP_RETURN(op) ATOMIC64_FETCH_OP(op) @@ -46,11 +46,11 @@ ATOMIC64_OPS(xor) #undef ATOMIC64_OP_RETURN #undef ATOMIC64_OP -extern long long atomic64_dec_if_positive(atomic64_t *v); +extern s64 atomic64_dec_if_positive(atomic64_t *v); #define atomic64_dec_if_positive atomic64_dec_if_positive -extern long long atomic64_cmpxchg(atomic64_t *v, long long o, long long n); -extern long long atomic64_xchg(atomic64_t *v, long long new); -extern long long atomic64_fetch_add_unless(atomic64_t *v, long long a, long long u); +extern s64 atomic64_cmpxchg(atomic64_t *v, s64 o, s64 n); +extern s64 atomic64_xchg(atomic64_t *v, s64 new); +extern s64 atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u); #define atomic64_fetch_add_unless atomic64_fetch_add_unless #endif /* _ASM_GENERIC_ATOMIC64_H */ diff --git a/include/asm-generic/vdso/vsyscall.h b/include/asm-generic/vdso/vsyscall.h new file mode 100644 index 000000000000..e94b19782c92 --- /dev/null +++ b/include/asm-generic/vdso/vsyscall.h @@ -0,0 +1,50 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __ASM_GENERIC_VSYSCALL_H +#define __ASM_GENERIC_VSYSCALL_H + +#ifndef __ASSEMBLY__ + +#ifndef __arch_get_k_vdso_data +static __always_inline struct vdso_data *__arch_get_k_vdso_data(void) +{ + return NULL; +} +#endif /* __arch_get_k_vdso_data */ + +#ifndef __arch_update_vdso_data +static __always_inline int __arch_update_vdso_data(void) +{ + return 0; +} +#endif /* __arch_update_vdso_data */ + +#ifndef __arch_get_clock_mode +static __always_inline int __arch_get_clock_mode(struct timekeeper *tk) +{ + return 0; +} +#endif /* __arch_get_clock_mode */ + +#ifndef __arch_use_vsyscall +static __always_inline int __arch_use_vsyscall(struct vdso_data *vdata) +{ + return 1; +} +#endif /* __arch_use_vsyscall */ + +#ifndef __arch_update_vsyscall +static __always_inline void __arch_update_vsyscall(struct vdso_data *vdata, + struct timekeeper *tk) +{ +} +#endif /* __arch_update_vsyscall */ + +#ifndef __arch_sync_vdso_data +static __always_inline void __arch_sync_vdso_data(struct vdso_data *vdata) +{ +} +#endif /* __arch_sync_vdso_data */ + +#endif /* !__ASSEMBLY__ */ + +#endif /* __ASM_GENERIC_VSYSCALL_H */ diff --git a/include/clocksource/hyperv_timer.h b/include/clocksource/hyperv_timer.h new file mode 100644 index 000000000000..a821deb8ecb2 --- /dev/null +++ b/include/clocksource/hyperv_timer.h @@ -0,0 +1,107 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +/* + * Definitions for the clocksource provided by the Hyper-V + * hypervisor to guest VMs, as described in the Hyper-V Top + * Level Functional Spec (TLFS). + * + * Copyright (C) 2019, Microsoft, Inc. + * + * Author: Michael Kelley <mikelley@microsoft.com> + */ + +#ifndef __CLKSOURCE_HYPERV_TIMER_H +#define __CLKSOURCE_HYPERV_TIMER_H + +#include <linux/clocksource.h> +#include <linux/math64.h> +#include <asm/mshyperv.h> + +#define HV_MAX_MAX_DELTA_TICKS 0xffffffff +#define HV_MIN_DELTA_TICKS 1 + +/* Routines called by the VMbus driver */ +extern int hv_stimer_alloc(int sint); +extern void hv_stimer_free(void); +extern void hv_stimer_init(unsigned int cpu); +extern void hv_stimer_cleanup(unsigned int cpu); +extern void hv_stimer_global_cleanup(void); +extern void hv_stimer0_isr(void); + +#if IS_ENABLED(CONFIG_HYPERV) +extern struct clocksource *hyperv_cs; +extern void hv_init_clocksource(void); +#endif /* CONFIG_HYPERV */ + +#ifdef CONFIG_HYPERV_TSCPAGE +extern struct ms_hyperv_tsc_page *hv_get_tsc_page(void); + +static inline notrace u64 +hv_read_tsc_page_tsc(const struct ms_hyperv_tsc_page *tsc_pg, u64 *cur_tsc) +{ + u64 scale, offset; + u32 sequence; + + /* + * The protocol for reading Hyper-V TSC page is specified in Hypervisor + * Top-Level Functional Specification ver. 3.0 and above. To get the + * reference time we must do the following: + * - READ ReferenceTscSequence + * A special '0' value indicates the time source is unreliable and we + * need to use something else. The currently published specification + * versions (up to 4.0b) contain a mistake and wrongly claim '-1' + * instead of '0' as the special value, see commit c35b82ef0294. + * - ReferenceTime = + * ((RDTSC() * ReferenceTscScale) >> 64) + ReferenceTscOffset + * - READ ReferenceTscSequence again. In case its value has changed + * since our first reading we need to discard ReferenceTime and repeat + * the whole sequence as the hypervisor was updating the page in + * between. + */ + do { + sequence = READ_ONCE(tsc_pg->tsc_sequence); + if (!sequence) + return U64_MAX; + /* + * Make sure we read sequence before we read other values from + * TSC page. + */ + smp_rmb(); + + scale = READ_ONCE(tsc_pg->tsc_scale); + offset = READ_ONCE(tsc_pg->tsc_offset); + *cur_tsc = hv_get_raw_timer(); + + /* + * Make sure we read sequence after we read all other values + * from TSC page. + */ + smp_rmb(); + + } while (READ_ONCE(tsc_pg->tsc_sequence) != sequence); + + return mul_u64_u64_shr(*cur_tsc, scale, 64) + offset; +} + +static inline notrace u64 +hv_read_tsc_page(const struct ms_hyperv_tsc_page *tsc_pg) +{ + u64 cur_tsc; + + return hv_read_tsc_page_tsc(tsc_pg, &cur_tsc); +} + +#else /* CONFIG_HYPERV_TSC_PAGE */ +static inline struct ms_hyperv_tsc_page *hv_get_tsc_page(void) +{ + return NULL; +} + +static inline u64 hv_read_tsc_page_tsc(const struct ms_hyperv_tsc_page *tsc_pg, + u64 *cur_tsc) +{ + return U64_MAX; +} +#endif /* CONFIG_HYPERV_TSCPAGE */ + +#endif diff --git a/include/clocksource/timer-davinci.h b/include/clocksource/timer-davinci.h new file mode 100644 index 000000000000..1dcc1333fbc8 --- /dev/null +++ b/include/clocksource/timer-davinci.h @@ -0,0 +1,44 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * TI DaVinci clocksource driver + * + * Copyright (C) 2019 Texas Instruments + * Author: Bartosz Golaszewski <bgolaszewski@baylibre.com> + */ + +#ifndef __TIMER_DAVINCI_H__ +#define __TIMER_DAVINCI_H__ + +#include <linux/clk.h> +#include <linux/ioport.h> + +enum { + DAVINCI_TIMER_CLOCKEVENT_IRQ, + DAVINCI_TIMER_CLOCKSOURCE_IRQ, + DAVINCI_TIMER_NUM_IRQS, +}; + +/** + * struct davinci_timer_cfg - davinci clocksource driver configuration struct + * @reg: register range resource + * @irq: clockevent and clocksource interrupt resources + * @cmp_off: if set - it specifies the compare register used for clockevent + * + * Note: if the compare register is specified, the driver will use the bottom + * clock half for both clocksource and clockevent and the compare register + * to generate event irqs. The user must supply the correct compare register + * interrupt number. + * + * This is only used by da830 the DSP of which uses the top half. The timer + * driver still configures the top half to run in free-run mode. + */ +struct davinci_timer_cfg { + struct resource reg; + struct resource irq[DAVINCI_TIMER_NUM_IRQS]; + unsigned int cmp_off; +}; + +int __init davinci_timer_register(struct clk *clk, + const struct davinci_timer_cfg *data); + +#endif /* __TIMER_DAVINCI_H__ */ diff --git a/include/crypto/aead.h b/include/crypto/aead.h index 61bb10490492..3c245b1859e7 100644 --- a/include/crypto/aead.h +++ b/include/crypto/aead.h @@ -317,21 +317,7 @@ static inline struct crypto_aead *crypto_aead_reqtfm(struct aead_request *req) * * Return: 0 if the cipher operation was successful; < 0 if an error occurred */ -static inline int crypto_aead_encrypt(struct aead_request *req) -{ - struct crypto_aead *aead = crypto_aead_reqtfm(req); - struct crypto_alg *alg = aead->base.__crt_alg; - unsigned int cryptlen = req->cryptlen; - int ret; - - crypto_stats_get(alg); - if (crypto_aead_get_flags(aead) & CRYPTO_TFM_NEED_KEY) - ret = -ENOKEY; - else - ret = crypto_aead_alg(aead)->encrypt(req); - crypto_stats_aead_encrypt(cryptlen, alg, ret); - return ret; -} +int crypto_aead_encrypt(struct aead_request *req); /** * crypto_aead_decrypt() - decrypt ciphertext @@ -355,23 +341,7 @@ static inline int crypto_aead_encrypt(struct aead_request *req) * integrity of the ciphertext or the associated data was violated); * < 0 if an error occurred. */ -static inline int crypto_aead_decrypt(struct aead_request *req) -{ - struct crypto_aead *aead = crypto_aead_reqtfm(req); - struct crypto_alg *alg = aead->base.__crt_alg; - unsigned int cryptlen = req->cryptlen; - int ret; - - crypto_stats_get(alg); - if (crypto_aead_get_flags(aead) & CRYPTO_TFM_NEED_KEY) - ret = -ENOKEY; - else if (req->cryptlen < crypto_aead_authsize(aead)) - ret = -EINVAL; - else - ret = crypto_aead_alg(aead)->decrypt(req); - crypto_stats_aead_decrypt(cryptlen, alg, ret); - return ret; -} +int crypto_aead_decrypt(struct aead_request *req); /** * DOC: Asynchronous AEAD Request Handle diff --git a/include/crypto/algapi.h b/include/crypto/algapi.h index 743d626479ef..dc1106af95c3 100644 --- a/include/crypto/algapi.h +++ b/include/crypto/algapi.h @@ -189,7 +189,6 @@ void crypto_init_queue(struct crypto_queue *queue, unsigned int max_qlen); int crypto_enqueue_request(struct crypto_queue *queue, struct crypto_async_request *request); struct crypto_async_request *crypto_dequeue_request(struct crypto_queue *queue); -int crypto_tfm_in_queue(struct crypto_queue *queue, struct crypto_tfm *tfm); static inline unsigned int crypto_queue_len(struct crypto_queue *queue) { return queue->qlen; @@ -371,12 +370,6 @@ static inline void *ablkcipher_request_ctx(struct ablkcipher_request *req) return req->__ctx; } -static inline int ablkcipher_tfm_in_queue(struct crypto_queue *queue, - struct crypto_ablkcipher *tfm) -{ - return crypto_tfm_in_queue(queue, crypto_ablkcipher_tfm(tfm)); -} - static inline struct crypto_alg *crypto_get_attr_alg(struct rtattr **tb, u32 type, u32 mask) { diff --git a/include/crypto/arc4.h b/include/crypto/arc4.h index 5b2c24ab0139..f3c22fe01704 100644 --- a/include/crypto/arc4.h +++ b/include/crypto/arc4.h @@ -6,8 +6,18 @@ #ifndef _CRYPTO_ARC4_H #define _CRYPTO_ARC4_H +#include <linux/types.h> + #define ARC4_MIN_KEY_SIZE 1 #define ARC4_MAX_KEY_SIZE 256 #define ARC4_BLOCK_SIZE 1 +struct arc4_ctx { + u32 S[256]; + u32 x, y; +}; + +int arc4_setkey(struct arc4_ctx *ctx, const u8 *in_key, unsigned int key_len); +void arc4_crypt(struct arc4_ctx *ctx, u8 *out, const u8 *in, unsigned int len); + #endif /* _CRYPTO_ARC4_H */ diff --git a/include/crypto/chacha.h b/include/crypto/chacha.h index 1fc70a69d550..d1e723c6a37d 100644 --- a/include/crypto/chacha.h +++ b/include/crypto/chacha.h @@ -41,7 +41,7 @@ static inline void chacha20_block(u32 *state, u8 *stream) } void hchacha_block(const u32 *in, u32 *out, int nrounds); -void crypto_chacha_init(u32 *state, struct chacha_ctx *ctx, u8 *iv); +void crypto_chacha_init(u32 *state, const struct chacha_ctx *ctx, const u8 *iv); int crypto_chacha20_setkey(struct crypto_skcipher *tfm, const u8 *key, unsigned int keysize); diff --git a/include/crypto/crypto_wq.h b/include/crypto/crypto_wq.h deleted file mode 100644 index 23114746ac08..000000000000 --- a/include/crypto/crypto_wq.h +++ /dev/null @@ -1,8 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef CRYPTO_WQ_H -#define CRYPTO_WQ_H - -#include <linux/workqueue.h> - -extern struct workqueue_struct *kcrypto_wq; -#endif diff --git a/include/crypto/drbg.h b/include/crypto/drbg.h index 3fb581bf3b87..8c9af21efce1 100644 --- a/include/crypto/drbg.h +++ b/include/crypto/drbg.h @@ -129,6 +129,8 @@ struct drbg_state { bool seeded; /* DRBG fully seeded? */ bool pr; /* Prediction resistance enabled? */ + bool fips_primed; /* Continuous test primed? */ + unsigned char *prev; /* FIPS 140-2 continuous test value */ struct work_struct seed_work; /* asynchronous seeding support */ struct crypto_rng *jent; const struct drbg_state_ops *d_ops; diff --git a/include/crypto/internal/hash.h b/include/crypto/internal/hash.h index 31e0662fa429..bfc9db7b100d 100644 --- a/include/crypto/internal/hash.h +++ b/include/crypto/internal/hash.h @@ -196,12 +196,6 @@ static inline struct ahash_request *ahash_dequeue_request( return ahash_request_cast(crypto_dequeue_request(queue)); } -static inline int ahash_tfm_in_queue(struct crypto_queue *queue, - struct crypto_ahash *tfm) -{ - return crypto_tfm_in_queue(queue, crypto_ahash_tfm(tfm)); -} - static inline void *crypto_shash_ctx(struct crypto_shash *tfm) { return crypto_tfm_ctx(&tfm->base); diff --git a/include/crypto/internal/skcipher.h b/include/crypto/internal/skcipher.h index fe0376d5a471..d68faa5759ad 100644 --- a/include/crypto/internal/skcipher.h +++ b/include/crypto/internal/skcipher.h @@ -200,6 +200,66 @@ static inline unsigned int crypto_skcipher_alg_max_keysize( return alg->max_keysize; } +static inline unsigned int crypto_skcipher_alg_chunksize( + struct skcipher_alg *alg) +{ + if ((alg->base.cra_flags & CRYPTO_ALG_TYPE_MASK) == + CRYPTO_ALG_TYPE_BLKCIPHER) + return alg->base.cra_blocksize; + + if (alg->base.cra_ablkcipher.encrypt) + return alg->base.cra_blocksize; + + return alg->chunksize; +} + +static inline unsigned int crypto_skcipher_alg_walksize( + struct skcipher_alg *alg) +{ + if ((alg->base.cra_flags & CRYPTO_ALG_TYPE_MASK) == + CRYPTO_ALG_TYPE_BLKCIPHER) + return alg->base.cra_blocksize; + + if (alg->base.cra_ablkcipher.encrypt) + return alg->base.cra_blocksize; + + return alg->walksize; +} + +/** + * crypto_skcipher_chunksize() - obtain chunk size + * @tfm: cipher handle + * + * The block size is set to one for ciphers such as CTR. However, + * you still need to provide incremental updates in multiples of + * the underlying block size as the IV does not have sub-block + * granularity. This is known in this API as the chunk size. + * + * Return: chunk size in bytes + */ +static inline unsigned int crypto_skcipher_chunksize( + struct crypto_skcipher *tfm) +{ + return crypto_skcipher_alg_chunksize(crypto_skcipher_alg(tfm)); +} + +/** + * crypto_skcipher_walksize() - obtain walk size + * @tfm: cipher handle + * + * In some cases, algorithms can only perform optimally when operating on + * multiple blocks in parallel. This is reflected by the walksize, which + * must be a multiple of the chunksize (or equal if the concern does not + * apply) + * + * Return: walk size in bytes + */ +static inline unsigned int crypto_skcipher_walksize( + struct crypto_skcipher *tfm) +{ + return crypto_skcipher_alg_walksize(crypto_skcipher_alg(tfm)); +} + /* Helpers for simple block cipher modes of operation */ struct skcipher_ctx_simple { struct crypto_cipher *cipher; /* underlying block cipher */ diff --git a/include/crypto/skcipher.h b/include/crypto/skcipher.h index ce7fa0973580..37c164234d97 100644 --- a/include/crypto/skcipher.h +++ b/include/crypto/skcipher.h @@ -288,66 +288,6 @@ static inline unsigned int crypto_sync_skcipher_ivsize( return crypto_skcipher_ivsize(&tfm->base); } -static inline unsigned int crypto_skcipher_alg_chunksize( - struct skcipher_alg *alg) -{ - if ((alg->base.cra_flags & CRYPTO_ALG_TYPE_MASK) == - CRYPTO_ALG_TYPE_BLKCIPHER) - return alg->base.cra_blocksize; - - if (alg->base.cra_ablkcipher.encrypt) - return alg->base.cra_blocksize; - - return alg->chunksize; -} - -static inline unsigned int crypto_skcipher_alg_walksize( - struct skcipher_alg *alg) -{ - if ((alg->base.cra_flags & CRYPTO_ALG_TYPE_MASK) == - CRYPTO_ALG_TYPE_BLKCIPHER) - return alg->base.cra_blocksize; - - if (alg->base.cra_ablkcipher.encrypt) - return alg->base.cra_blocksize; - - return alg->walksize; -} - -/** - * crypto_skcipher_chunksize() - obtain chunk size - * @tfm: cipher handle - * - * The block size is set to one for ciphers such as CTR. However, - * you still need to provide incremental updates in multiples of - * the underlying block size as the IV does not have sub-block - * granularity. This is known in this API as the chunk size. - * - * Return: chunk size in bytes - */ -static inline unsigned int crypto_skcipher_chunksize( - struct crypto_skcipher *tfm) -{ - return crypto_skcipher_alg_chunksize(crypto_skcipher_alg(tfm)); -} - -/** - * crypto_skcipher_walksize() - obtain walk size - * @tfm: cipher handle - * - * In some cases, algorithms can only perform optimally when operating on - * multiple blocks in parallel. This is reflected by the walksize, which - * must be a multiple of the chunksize (or equal if the concern does not - * apply) - * - * Return: walk size in bytes - */ -static inline unsigned int crypto_skcipher_walksize( - struct crypto_skcipher *tfm) -{ - return crypto_skcipher_alg_walksize(crypto_skcipher_alg(tfm)); -} - /** * crypto_skcipher_blocksize() - obtain block size of cipher * @tfm: cipher handle @@ -479,21 +419,7 @@ static inline struct crypto_sync_skcipher *crypto_sync_skcipher_reqtfm( * * Return: 0 if the cipher operation was successful; < 0 if an error occurred */ -static inline int crypto_skcipher_encrypt(struct skcipher_request *req) -{ - struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); - struct crypto_alg *alg = tfm->base.__crt_alg; - unsigned int cryptlen = req->cryptlen; - int ret; - - crypto_stats_get(alg); - if (crypto_skcipher_get_flags(tfm) & CRYPTO_TFM_NEED_KEY) - ret = -ENOKEY; - else - ret = tfm->encrypt(req); - crypto_stats_skcipher_encrypt(cryptlen, ret, alg); - return ret; -} +int crypto_skcipher_encrypt(struct skcipher_request *req); /** * crypto_skcipher_decrypt() - decrypt ciphertext @@ -506,21 +432,7 @@ static inline int crypto_skcipher_encrypt(struct skcipher_request *req) * * Return: 0 if the cipher operation was successful; < 0 if an error occurred */ -static inline int crypto_skcipher_decrypt(struct skcipher_request *req) -{ - struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); - struct crypto_alg *alg = tfm->base.__crt_alg; - unsigned int cryptlen = req->cryptlen; - int ret; - - crypto_stats_get(alg); - if (crypto_skcipher_get_flags(tfm) & CRYPTO_TFM_NEED_KEY) - ret = -ENOKEY; - else - ret = tfm->decrypt(req); - crypto_stats_skcipher_decrypt(cryptlen, ret, alg); - return ret; -} +int crypto_skcipher_decrypt(struct skcipher_request *req); /** * DOC: Symmetric Key Cipher Request Handle diff --git a/include/dt-bindings/clock/g12a-clkc.h b/include/dt-bindings/clock/g12a-clkc.h index 82c9e0c020b2..e10470ed7c4f 100644 --- a/include/dt-bindings/clock/g12a-clkc.h +++ b/include/dt-bindings/clock/g12a-clkc.h @@ -130,7 +130,7 @@ #define CLKID_MALI_1_SEL 172 #define CLKID_MALI_1 174 #define CLKID_MALI 175 -#define CLKID_MPLL_5OM 177 +#define CLKID_MPLL_50M 177 #define CLKID_CPU_CLK 187 #define CLKID_PCIE_PLL 201 #define CLKID_VDEC_1 204 diff --git a/include/dt-bindings/clock/sifive-fu540-prci.h b/include/dt-bindings/clock/sifive-fu540-prci.h index 6a0b70a37d78..3b21d0522c91 100644 --- a/include/dt-bindings/clock/sifive-fu540-prci.h +++ b/include/dt-bindings/clock/sifive-fu540-prci.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: (GPL-2.0 OR MIT) */ /* * Copyright (C) 2018-2019 SiFive, Inc. * Wesley Terpstra diff --git a/include/keys/request_key_auth-type.h b/include/keys/request_key_auth-type.h index 20485ca481f4..36b89a933310 100644 --- a/include/keys/request_key_auth-type.h +++ b/include/keys/request_key_auth-type.h @@ -14,6 +14,7 @@ * Authorisation record for request_key(). */ struct request_key_auth { + struct rcu_head rcu; struct key *target_key; struct key *dest_keyring; const struct cred *cred; diff --git a/include/linux/acpi.h b/include/linux/acpi.h index d315d86844e4..469be6844703 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -10,6 +10,7 @@ #include <linux/errno.h> #include <linux/ioport.h> /* for struct resource */ +#include <linux/irqdomain.h> #include <linux/resource_ext.h> #include <linux/device.h> #include <linux/property.h> @@ -314,6 +315,12 @@ int acpi_isa_irq_to_gsi (unsigned isa_irq, u32 *gsi); void acpi_set_irq_model(enum acpi_irq_model_id model, struct fwnode_handle *fwnode); +struct irq_domain *acpi_irq_create_hierarchy(unsigned int flags, + unsigned int size, + struct fwnode_handle *fwnode, + const struct irq_domain_ops *ops, + void *host_data); + #ifdef CONFIG_X86_IO_APIC extern int acpi_get_override_irq(u32 gsi, int *trigger, int *polarity); #else @@ -1303,6 +1310,7 @@ static inline int lpit_read_residency_count_address(u64 *address) #ifdef CONFIG_ACPI_PPTT int find_acpi_cpu_topology(unsigned int cpu, int level); int find_acpi_cpu_topology_package(unsigned int cpu); +int find_acpi_cpu_topology_hetero_id(unsigned int cpu); int find_acpi_cpu_cache_topology(unsigned int cpu, int level); #else static inline int find_acpi_cpu_topology(unsigned int cpu, int level) @@ -1313,6 +1321,10 @@ static inline int find_acpi_cpu_topology_package(unsigned int cpu) { return -EINVAL; } +static inline int find_acpi_cpu_topology_hetero_id(unsigned int cpu) +{ + return -EINVAL; +} static inline int find_acpi_cpu_cache_topology(unsigned int cpu, int level) { return -EINVAL; diff --git a/include/linux/arch_topology.h b/include/linux/arch_topology.h index d9bdc1a7f4e7..1cfe05ea1d89 100644 --- a/include/linux/arch_topology.h +++ b/include/linux/arch_topology.h @@ -18,7 +18,7 @@ DECLARE_PER_CPU(unsigned long, cpu_scale); struct sched_domain; static inline -unsigned long topology_get_cpu_scale(struct sched_domain *sd, int cpu) +unsigned long topology_get_cpu_scale(int cpu) { return per_cpu(cpu_scale, cpu); } diff --git a/include/linux/audit.h b/include/linux/audit.h index 3a4f2415bb7c..97d0925454df 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -182,6 +182,9 @@ static inline unsigned int audit_get_sessionid(struct task_struct *tsk) } extern u32 audit_enabled; + +extern int audit_signal_info(int sig, struct task_struct *t); + #else /* CONFIG_AUDIT */ static inline __printf(4, 5) void audit_log(struct audit_context *ctx, gfp_t gfp_mask, int type, @@ -235,6 +238,12 @@ static inline unsigned int audit_get_sessionid(struct task_struct *tsk) } #define audit_enabled AUDIT_OFF + +static inline int audit_signal_info(int sig, struct task_struct *t) +{ + return 0; +} + #endif /* CONFIG_AUDIT */ #ifdef CONFIG_AUDIT_COMPAT_GENERIC diff --git a/include/linux/cacheinfo.h b/include/linux/cacheinfo.h index 70e19bc6cc9f..46b92cd61d0c 100644 --- a/include/linux/cacheinfo.h +++ b/include/linux/cacheinfo.h @@ -17,6 +17,8 @@ enum cache_type { CACHE_TYPE_UNIFIED = BIT(2), }; +extern unsigned int coherency_max_size; + /** * struct cacheinfo - represent a cache leaf node * @id: This cache's id. It is unique among caches with the same (type, level). diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 5c6062206760..87c211adf49e 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -116,10 +116,10 @@ enum cpuhp_state { CPUHP_AP_PERF_ARM_ACPI_STARTING, CPUHP_AP_PERF_ARM_STARTING, CPUHP_AP_ARM_L2X0_STARTING, + CPUHP_AP_EXYNOS4_MCT_TIMER_STARTING, CPUHP_AP_ARM_ARCH_TIMER_STARTING, CPUHP_AP_ARM_GLOBAL_TIMER_STARTING, CPUHP_AP_JCORE_TIMER_STARTING, - CPUHP_AP_EXYNOS4_MCT_TIMER_STARTING, CPUHP_AP_ARM_TWD_STARTING, CPUHP_AP_QCOM_TIMER_STARTING, CPUHP_AP_TEGRA_TIMER_STARTING, diff --git a/include/linux/crypto.h b/include/linux/crypto.h index 9cf8f3ce0e50..19ea3a371d7b 100644 --- a/include/linux/crypto.h +++ b/include/linux/crypto.h @@ -49,7 +49,6 @@ #define CRYPTO_ALG_TYPE_SCOMPRESS 0x0000000b #define CRYPTO_ALG_TYPE_RNG 0x0000000c #define CRYPTO_ALG_TYPE_AKCIPHER 0x0000000d -#define CRYPTO_ALG_TYPE_DIGEST 0x0000000e #define CRYPTO_ALG_TYPE_HASH 0x0000000e #define CRYPTO_ALG_TYPE_SHASH 0x0000000e #define CRYPTO_ALG_TYPE_AHASH 0x0000000f @@ -323,6 +322,17 @@ struct cipher_alg { void (*cia_decrypt)(struct crypto_tfm *tfm, u8 *dst, const u8 *src); }; +/** + * struct compress_alg - compression/decompression algorithm + * @coa_compress: Compress a buffer of specified length, storing the resulting + * data in the specified buffer. Return the length of the + * compressed data in dlen. + * @coa_decompress: Decompress the source buffer, storing the uncompressed + * data in the specified buffer. The length of the data is + * returned in dlen. + * + * All fields are mandatory. + */ struct compress_alg { int (*coa_compress)(struct crypto_tfm *tfm, const u8 *src, unsigned int slen, u8 *dst, unsigned int *dlen); diff --git a/include/linux/device.h b/include/linux/device.h index 848fc71c6ba6..4a295e324ac5 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -704,7 +704,8 @@ extern unsigned long devm_get_free_pages(struct device *dev, gfp_t gfp_mask, unsigned int order); extern void devm_free_pages(struct device *dev, unsigned long addr); -void __iomem *devm_ioremap_resource(struct device *dev, struct resource *res); +void __iomem *devm_ioremap_resource(struct device *dev, + const struct resource *res); void __iomem *devm_of_iomap(struct device *dev, struct device_node *node, int index, diff --git a/include/linux/dns_resolver.h b/include/linux/dns_resolver.h index f2b3ae22e6b7..976cbbdb2832 100644 --- a/include/linux/dns_resolver.h +++ b/include/linux/dns_resolver.h @@ -26,7 +26,8 @@ #include <uapi/linux/dns_resolver.h> -extern int dns_query(const char *type, const char *name, size_t namelen, +struct net; +extern int dns_query(struct net *net, const char *type, const char *name, size_t namelen, const char *options, char **_result, time64_t *_expiry, bool invalidate); diff --git a/include/linux/efi.h b/include/linux/efi.h index 6ebc2098cfe1..f87fabea4a85 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -689,6 +689,7 @@ void efi_native_runtime_setup(void); #define LINUX_EFI_LOADER_ENTRY_GUID EFI_GUID(0x4a67b082, 0x0a4c, 0x41cf, 0xb6, 0xc7, 0x44, 0x0b, 0x29, 0xbb, 0x8c, 0x4f) #define LINUX_EFI_RANDOM_SEED_TABLE_GUID EFI_GUID(0x1ce1e5bc, 0x7ceb, 0x42f2, 0x81, 0xe5, 0x8a, 0xad, 0xf1, 0x80, 0xf5, 0x7b) #define LINUX_EFI_TPM_EVENT_LOG_GUID EFI_GUID(0xb7799cb0, 0xeca2, 0x4943, 0x96, 0x67, 0x1f, 0xae, 0x07, 0xb7, 0x47, 0xfa) +#define LINUX_EFI_TPM_FINAL_LOG_GUID EFI_GUID(0x1e2ed096, 0x30e2, 0x4254, 0xbd, 0x89, 0x86, 0x3b, 0xbe, 0xf8, 0x23, 0x25) #define LINUX_EFI_MEMRESERVE_TABLE_GUID EFI_GUID(0x888eb0c6, 0x8ede, 0x4ff5, 0xa8, 0xf0, 0x9a, 0xee, 0x5c, 0xb9, 0x77, 0xc2) typedef struct { @@ -996,6 +997,7 @@ extern struct efi { unsigned long mem_attr_table; /* memory attributes table */ unsigned long rng_seed; /* UEFI firmware random seed */ unsigned long tpm_log; /* TPM2 Event Log table */ + unsigned long tpm_final_log; /* TPM2 Final Events Log table */ unsigned long mem_reserve; /* Linux EFI memreserve table */ efi_get_time_t *get_time; efi_set_time_t *set_time; @@ -1706,12 +1708,20 @@ struct linux_efi_random_seed { struct linux_efi_tpm_eventlog { u32 size; + u32 final_events_preboot_size; u8 version; u8 log[]; }; extern int efi_tpm_eventlog_init(void); +struct efi_tcg2_final_events_table { + u64 version; + u64 nr_events; + u8 events[]; +}; +extern int efi_tpm_final_log_size; + /* * efi_runtime_service() function identifiers. * "NONE" is used by efi_recover_from_page_fault() to check if the page diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h index aa027f7bcb3e..73f8c3cb9588 100644 --- a/include/linux/energy_model.h +++ b/include/linux/energy_model.h @@ -89,7 +89,7 @@ static inline unsigned long em_pd_energy(struct em_perf_domain *pd, * like schedutil. */ cpu = cpumask_first(to_cpumask(pd->cpus)); - scale_cpu = arch_scale_cpu_capacity(NULL, cpu); + scale_cpu = arch_scale_cpu_capacity(cpu); cs = &pd->table[pd->nr_cap_states - 1]; freq = map_util_freq(max_util, cs->frequency, scale_cpu); diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index 2e8957eac4d4..4971100a8cab 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -12,8 +12,8 @@ #ifndef _LINUX_HRTIMER_H #define _LINUX_HRTIMER_H +#include <linux/hrtimer_defs.h> #include <linux/rbtree.h> -#include <linux/ktime.h> #include <linux/init.h> #include <linux/list.h> #include <linux/percpu.h> @@ -298,26 +298,12 @@ struct clock_event_device; extern void hrtimer_interrupt(struct clock_event_device *dev); -/* - * The resolution of the clocks. The resolution value is returned in - * the clock_getres() system call to give application programmers an - * idea of the (in)accuracy of timers. Timer values are rounded up to - * this resolution values. - */ -# define HIGH_RES_NSEC 1 -# define KTIME_HIGH_RES (HIGH_RES_NSEC) -# define MONOTONIC_RES_NSEC HIGH_RES_NSEC -# define KTIME_MONOTONIC_RES KTIME_HIGH_RES - extern void clock_was_set_delayed(void); extern unsigned int hrtimer_resolution; #else -# define MONOTONIC_RES_NSEC LOW_RES_NSEC -# define KTIME_MONOTONIC_RES KTIME_LOW_RES - #define hrtimer_resolution (unsigned int)LOW_RES_NSEC static inline void clock_was_set_delayed(void) { } diff --git a/include/linux/hrtimer_defs.h b/include/linux/hrtimer_defs.h new file mode 100644 index 000000000000..2d3e3c5fb946 --- /dev/null +++ b/include/linux/hrtimer_defs.h @@ -0,0 +1,27 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_HRTIMER_DEFS_H +#define _LINUX_HRTIMER_DEFS_H + +#include <linux/ktime.h> + +#ifdef CONFIG_HIGH_RES_TIMERS + +/* + * The resolution of the clocks. The resolution value is returned in + * the clock_getres() system call to give application programmers an + * idea of the (in)accuracy of timers. Timer values are rounded up to + * this resolution values. + */ +# define HIGH_RES_NSEC 1 +# define KTIME_HIGH_RES (HIGH_RES_NSEC) +# define MONOTONIC_RES_NSEC HIGH_RES_NSEC +# define KTIME_MONOTONIC_RES KTIME_HIGH_RES + +#else + +# define MONOTONIC_RES_NSEC LOW_RES_NSEC +# define KTIME_MONOTONIC_RES KTIME_LOW_RES + +#endif + +#endif diff --git a/include/linux/ima.h b/include/linux/ima.h index 00036d2f57c3..a20ad398d260 100644 --- a/include/linux/ima.h +++ b/include/linux/ima.h @@ -23,6 +23,7 @@ extern int ima_read_file(struct file *file, enum kernel_read_file_id id); extern int ima_post_read_file(struct file *file, void *buf, loff_t size, enum kernel_read_file_id id); extern void ima_post_path_mknod(struct dentry *dentry); +extern void ima_kexec_cmdline(const void *buf, int size); #ifdef CONFIG_IMA_KEXEC extern void ima_add_kexec_buffer(struct kimage *image); @@ -89,6 +90,7 @@ static inline void ima_post_path_mknod(struct dentry *dentry) return; } +static inline void ima_kexec_cmdline(const void *buf, int size) {} #endif /* CONFIG_IMA */ #ifndef CONFIG_IMA_KEXEC diff --git a/include/linux/intel-ish-client-if.h b/include/linux/intel-ish-client-if.h index 16255c2ca2f4..0d6b4bc191c5 100644 --- a/include/linux/intel-ish-client-if.h +++ b/include/linux/intel-ish-client-if.h @@ -103,6 +103,7 @@ void ishtp_put_device(struct ishtp_cl_device *cl_dev); void ishtp_get_device(struct ishtp_cl_device *cl_dev); void ishtp_set_drvdata(struct ishtp_cl_device *cl_device, void *data); void *ishtp_get_drvdata(struct ishtp_cl_device *cl_device); +struct ishtp_cl_device *ishtp_dev_to_cl_device(struct device *dev); int ishtp_register_event_cb(struct ishtp_cl_device *device, void (*read_cb)(struct ishtp_cl_device *)); struct ishtp_fw_client *ishtp_fw_cl_get_client(struct ishtp_device *dev, diff --git a/include/linux/irqchip/arm-gic-common.h b/include/linux/irqchip/arm-gic-common.h index 626283858563..b9850f5f1906 100644 --- a/include/linux/irqchip/arm-gic-common.h +++ b/include/linux/irqchip/arm-gic-common.h @@ -36,4 +36,9 @@ struct gic_kvm_info { const struct gic_kvm_info *gic_get_kvm_info(void); +struct irq_domain; +struct fwnode_handle; +int gicv2m_init(struct fwnode_handle *parent_handle, + struct irq_domain *parent); + #endif /* __LINUX_IRQCHIP_ARM_GIC_COMMON_H */ diff --git a/include/linux/irqchip/arm-gic.h b/include/linux/irqchip/arm-gic.h index 316087da1d09..5686711b0f40 100644 --- a/include/linux/irqchip/arm-gic.h +++ b/include/linux/irqchip/arm-gic.h @@ -157,9 +157,6 @@ int gic_of_init_child(struct device *dev, struct gic_chip_data **gic, int irq); */ void gic_init(void __iomem *dist , void __iomem *cpu); -int gicv2m_init(struct fwnode_handle *parent_handle, - struct irq_domain *parent); - void gic_send_sgi(unsigned int cpu_id, unsigned int irq); int gic_get_cpu_id(unsigned int cpu); void gic_migrate_target(unsigned int new_cpu_id); diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h index 3e113a1fa0f1..3526c0aee954 100644 --- a/include/linux/jump_label.h +++ b/include/linux/jump_label.h @@ -215,6 +215,9 @@ extern void arch_jump_label_transform(struct jump_entry *entry, enum jump_label_type type); extern void arch_jump_label_transform_static(struct jump_entry *entry, enum jump_label_type type); +extern bool arch_jump_label_transform_queue(struct jump_entry *entry, + enum jump_label_type type); +extern void arch_jump_label_transform_apply(void); extern int jump_label_text_reserved(void *start, void *end); extern void static_key_slow_inc(struct static_key *key); extern void static_key_slow_dec(struct static_key *key); diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 74b1ee9027f5..0c9bc231107f 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -93,7 +93,8 @@ #define DIV_ROUND_DOWN_ULL(ll, d) \ ({ unsigned long long _tmp = (ll); do_div(_tmp, d); _tmp; }) -#define DIV_ROUND_UP_ULL(ll, d) DIV_ROUND_DOWN_ULL((ll) + (d) - 1, (d)) +#define DIV_ROUND_UP_ULL(ll, d) \ + DIV_ROUND_DOWN_ULL((unsigned long long)(ll) + (d) - 1, (d)) #if BITS_PER_LONG == 32 # define DIV_ROUND_UP_SECTOR_T(ll,d) DIV_ROUND_UP_ULL(ll, d) diff --git a/include/linux/key-type.h b/include/linux/key-type.h index 331cab70db09..4ded94bcf274 100644 --- a/include/linux/key-type.h +++ b/include/linux/key-type.h @@ -70,6 +70,9 @@ struct key_type { */ size_t def_datalen; + unsigned int flags; +#define KEY_TYPE_NET_DOMAIN 0x00000001 /* Keys of this type have a net namespace domain */ + /* vet a description */ int (*vet_description)(const char *description); diff --git a/include/linux/key.h b/include/linux/key.h index 1c8b88b455ef..6fef6684501f 100644 --- a/include/linux/key.h +++ b/include/linux/key.h @@ -27,48 +27,14 @@ /* key handle serial number */ typedef int32_t key_serial_t; -/* key handle permissions mask */ -typedef uint32_t key_perm_t; - struct key; +struct net; #ifdef CONFIG_KEYS -#undef KEY_DEBUGGING +#include <linux/keyctl.h> -#define KEY_POS_VIEW 0x01000000 /* possessor can view a key's attributes */ -#define KEY_POS_READ 0x02000000 /* possessor can read key payload / view keyring */ -#define KEY_POS_WRITE 0x04000000 /* possessor can update key payload / add link to keyring */ -#define KEY_POS_SEARCH 0x08000000 /* possessor can find a key in search / search a keyring */ -#define KEY_POS_LINK 0x10000000 /* possessor can create a link to a key/keyring */ -#define KEY_POS_SETATTR 0x20000000 /* possessor can set key attributes */ -#define KEY_POS_ALL 0x3f000000 - -#define KEY_USR_VIEW 0x00010000 /* user permissions... */ -#define KEY_USR_READ 0x00020000 -#define KEY_USR_WRITE 0x00040000 -#define KEY_USR_SEARCH 0x00080000 -#define KEY_USR_LINK 0x00100000 -#define KEY_USR_SETATTR 0x00200000 -#define KEY_USR_ALL 0x003f0000 - -#define KEY_GRP_VIEW 0x00000100 /* group permissions... */ -#define KEY_GRP_READ 0x00000200 -#define KEY_GRP_WRITE 0x00000400 -#define KEY_GRP_SEARCH 0x00000800 -#define KEY_GRP_LINK 0x00001000 -#define KEY_GRP_SETATTR 0x00002000 -#define KEY_GRP_ALL 0x00003f00 - -#define KEY_OTH_VIEW 0x00000001 /* third party permissions... */ -#define KEY_OTH_READ 0x00000002 -#define KEY_OTH_WRITE 0x00000004 -#define KEY_OTH_SEARCH 0x00000008 -#define KEY_OTH_LINK 0x00000010 -#define KEY_OTH_SETATTR 0x00000020 -#define KEY_OTH_ALL 0x0000003f - -#define KEY_PERM_UNDEF 0xffffffff +#undef KEY_DEBUGGING struct seq_file; struct user_struct; @@ -77,13 +43,34 @@ struct cred; struct key_type; struct key_owner; +struct key_tag; struct keyring_list; struct keyring_name; +struct key_tag { + struct rcu_head rcu; + refcount_t usage; + bool removed; /* T when subject removed */ +}; + struct keyring_index_key { + /* [!] If this structure is altered, the union in struct key must change too! */ + unsigned long hash; /* Hash value */ + union { + struct { +#ifdef __LITTLE_ENDIAN /* Put desc_len at the LSB of x */ + u8 desc_len; + char desc[sizeof(long) - 1]; /* First few chars of description */ +#else + char desc[sizeof(long) - 1]; /* First few chars of description */ + u8 desc_len; +#endif + }; + unsigned long x; + }; struct key_type *type; + struct key_tag *domain_tag; /* Domain of operation */ const char *description; - size_t desc_len; }; union key_payload { @@ -91,6 +78,36 @@ union key_payload { void *data[4]; }; +struct key_ace { + unsigned int type; + unsigned int perm; + union { + kuid_t uid; + kgid_t gid; + unsigned int subject_id; + }; +}; + +struct key_acl { + refcount_t usage; + unsigned short nr_ace; + bool possessor_viewable; + struct rcu_head rcu; + struct key_ace aces[]; +}; + +#define KEY_POSSESSOR_ACE(perms) { \ + .type = KEY_ACE_SUBJ_STANDARD, \ + .perm = perms, \ + .subject_id = KEY_ACE_POSSESSOR \ + } + +#define KEY_OWNER_ACE(perms) { \ + .type = KEY_ACE_SUBJ_STANDARD, \ + .perm = perms, \ + .subject_id = KEY_ACE_OWNER \ + } + /*****************************************************************************/ /* * key reference with possession attribute handling @@ -157,6 +174,7 @@ struct key { struct rw_semaphore sem; /* change vs change sem */ struct key_user *user; /* owner of this key */ void *security; /* security data for this key */ + struct key_acl __rcu *acl; union { time64_t expiry; /* time at which key expires (or 0) */ time64_t revoked_at; /* time at which key was revoked */ @@ -164,7 +182,6 @@ struct key { time64_t last_used_at; /* last time used for LRU keyring discard */ kuid_t uid; kgid_t gid; - key_perm_t perm; /* access permissions */ unsigned short quotalen; /* length added to quota */ unsigned short datalen; /* payload data length * - may not match RCU dereferenced payload @@ -188,6 +205,7 @@ struct key { #define KEY_FLAG_ROOT_CAN_INVAL 7 /* set if key can be invalidated by root without permission */ #define KEY_FLAG_KEEP 8 /* set if key should not be removed */ #define KEY_FLAG_UID_KEYRING 9 /* set if key is a user or user session keyring */ +#define KEY_FLAG_HAS_ACL 10 /* Set if KEYCTL_SETACL called on key */ /* the key type and key description string * - the desc is used to match a key against search criteria @@ -197,7 +215,10 @@ struct key { union { struct keyring_index_key index_key; struct { + unsigned long hash; + unsigned long len_desc; struct key_type *type; /* type of key */ + struct key_tag *domain_tag; /* Domain of operation */ char *description; }; }; @@ -233,7 +254,7 @@ extern struct key *key_alloc(struct key_type *type, const char *desc, kuid_t uid, kgid_t gid, const struct cred *cred, - key_perm_t perm, + struct key_acl *acl, unsigned long flags, struct key_restriction *restrict_link); @@ -248,6 +269,8 @@ extern struct key *key_alloc(struct key_type *type, extern void key_revoke(struct key *key); extern void key_invalidate(struct key *key); extern void key_put(struct key *key); +extern bool key_put_tag(struct key_tag *tag); +extern void key_remove_domain(struct key_tag *domain_tag); static inline struct key *__key_get(struct key *key) { @@ -265,26 +288,61 @@ static inline void key_ref_put(key_ref_t key_ref) key_put(key_ref_to_ptr(key_ref)); } -extern struct key *request_key(struct key_type *type, - const char *description, - const char *callout_info); +extern struct key *request_key_tag(struct key_type *type, + const char *description, + struct key_tag *domain_tag, + const char *callout_info, + struct key_acl *acl); + +extern struct key *request_key_rcu(struct key_type *type, + const char *description, + struct key_tag *domain_tag); extern struct key *request_key_with_auxdata(struct key_type *type, const char *description, + struct key_tag *domain_tag, const void *callout_info, size_t callout_len, - void *aux); + void *aux, + struct key_acl *acl); -extern struct key *request_key_async(struct key_type *type, - const char *description, - const void *callout_info, - size_t callout_len); +/** + * request_key - Request a key and wait for construction + * @type: Type of key. + * @description: The searchable description of the key. + * @callout_info: The data to pass to the instantiation upcall (or NULL). + * @acl: The ACL to attach to a new key (or NULL). + * + * As for request_key_tag(), but with the default global domain tag. + */ +static inline struct key *request_key(struct key_type *type, + const char *description, + const char *callout_info, + struct key_acl *acl) +{ + return request_key_tag(type, description, NULL, callout_info, acl); +} -extern struct key *request_key_async_with_auxdata(struct key_type *type, - const char *description, - const void *callout_info, - size_t callout_len, - void *aux); +#ifdef CONFIG_NET +/* + * request_key_net - Request a key for a net namespace and wait for construction + * @type: Type of key. + * @description: The searchable description of the key. + * @net: The network namespace that is the key's domain of operation. + * @callout_info: The data to pass to the instantiation upcall (or NULL). + * @acl: The ACL to attach to a new key (or NULL). + * + * As for request_key() except that it does not add the returned key to a + * keyring if found, new keys are always allocated in the user's quota, the + * callout_info must be a NUL-terminated string and no auxiliary data can be + * passed. Only keys that operate the specified network namespace are used. + * + * Furthermore, it then works as wait_for_key_construction() to wait for the + * completion of keys undergoing construction with a non-interruptible wait. + */ +#define request_key_net(type, description, net, callout_info, acl) \ + request_key_tag(type, description, net->key_domain, callout_info, acl); +#endif /* CONFIG_NET */ extern int wait_for_key_construction(struct key *key, bool intr); @@ -295,7 +353,7 @@ extern key_ref_t key_create_or_update(key_ref_t keyring, const char *description, const void *payload, size_t plen, - key_perm_t perm, + struct key_acl *acl, unsigned long flags); extern int key_update(key_ref_t key, @@ -305,12 +363,17 @@ extern int key_update(key_ref_t key, extern int key_link(struct key *keyring, struct key *key); +extern int key_move(struct key *key, + struct key *from_keyring, + struct key *to_keyring, + unsigned int flags); + extern int key_unlink(struct key *keyring, struct key *key); extern struct key *keyring_alloc(const char *description, kuid_t uid, kgid_t gid, const struct cred *cred, - key_perm_t perm, + struct key_acl *acl, unsigned long flags, struct key_restriction *restrict_link, struct key *dest); @@ -324,7 +387,8 @@ extern int keyring_clear(struct key *keyring); extern key_ref_t keyring_search(key_ref_t keyring, struct key_type *type, - const char *description); + const char *description, + bool recurse); extern int keyring_add_key(struct key *keyring, struct key *key); @@ -342,18 +406,29 @@ static inline key_serial_t key_serial(const struct key *key) extern void key_set_timeout(struct key *, unsigned); extern key_ref_t lookup_user_key(key_serial_t id, unsigned long flags, - key_perm_t perm); + u32 desired_perm); +extern void key_free_user_ns(struct user_namespace *); /* * The permissions required on a key that we're looking up. */ -#define KEY_NEED_VIEW 0x01 /* Require permission to view attributes */ -#define KEY_NEED_READ 0x02 /* Require permission to read content */ -#define KEY_NEED_WRITE 0x04 /* Require permission to update / modify */ -#define KEY_NEED_SEARCH 0x08 /* Require permission to search (keyring) or find (key) */ -#define KEY_NEED_LINK 0x10 /* Require permission to link */ -#define KEY_NEED_SETATTR 0x20 /* Require permission to change attributes */ -#define KEY_NEED_ALL 0x3f /* All the above permissions */ +#define KEY_NEED_VIEW 0x001 /* Require permission to view attributes */ +#define KEY_NEED_READ 0x002 /* Require permission to read content */ +#define KEY_NEED_WRITE 0x004 /* Require permission to update / modify */ +#define KEY_NEED_SEARCH 0x008 /* Require permission to search (keyring) or find (key) */ +#define KEY_NEED_LINK 0x010 /* Require permission to link */ +#define KEY_NEED_SETSEC 0x020 /* Require permission to set owner, group, ACL */ +#define KEY_NEED_INVAL 0x040 /* Require permission to invalidate key */ +#define KEY_NEED_REVOKE 0x080 /* Require permission to revoke key */ +#define KEY_NEED_JOIN 0x100 /* Require permission to join keyring as session */ +#define KEY_NEED_CLEAR 0x200 /* Require permission to clear a keyring */ +#define KEY_NEED_ALL 0x3ff + +#define OLD_KEY_NEED_SETATTR 0x20 /* Used to be Require permission to change attributes */ + +extern struct key_acl internal_key_acl; +extern struct key_acl internal_keyring_acl; +extern struct key_acl internal_writable_keyring_acl; static inline short key_read_state(const struct key *key) { @@ -397,8 +472,8 @@ extern struct ctl_table key_sysctls[]; * the userspace interface */ extern int install_thread_keyring_to_cred(struct cred *cred); -extern void key_fsuid_changed(struct task_struct *tsk); -extern void key_fsgid_changed(struct task_struct *tsk); +extern void key_fsuid_changed(struct cred *new_cred); +extern void key_fsgid_changed(struct cred *new_cred); extern void key_init(void); #else /* CONFIG_KEYS */ @@ -413,9 +488,11 @@ extern void key_init(void); #define make_key_ref(k, p) NULL #define key_ref_to_ptr(k) NULL #define is_key_possessed(k) 0 -#define key_fsuid_changed(t) do { } while(0) -#define key_fsgid_changed(t) do { } while(0) +#define key_fsuid_changed(c) do { } while(0) +#define key_fsgid_changed(c) do { } while(0) #define key_init() do { } while(0) +#define key_free_user_ns(ns) do { } while(0) +#define key_remove_domain(d) do { } while(0) #endif /* CONFIG_KEYS */ #endif /* __KERNEL__ */ diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index 6e2377e6c1d6..57baa27f238c 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -203,11 +203,17 @@ struct lock_list { struct lock_list *parent; }; -/* - * We record lock dependency chains, so that we can cache them: +/** + * struct lock_chain - lock dependency chain record + * + * @irq_context: the same as irq_context in held_lock below + * @depth: the number of held locks in this chain + * @base: the index in chain_hlocks for this chain + * @entry: the collided lock chains in lock_chain hash list + * @chain_key: the hash key of this lock_chain */ struct lock_chain { - /* see BUILD_BUG_ON()s in lookup_chain_cache() */ + /* see BUILD_BUG_ON()s in add_chain_cache() */ unsigned int irq_context : 2, depth : 6, base : 24; @@ -217,12 +223,8 @@ struct lock_chain { }; #define MAX_LOCKDEP_KEYS_BITS 13 -/* - * Subtract one because we offset hlock->class_idx by 1 in order - * to make 0 mean no class. This avoids overflowing the class_idx - * bitfield and hitting the BUG in hlock_class(). - */ -#define MAX_LOCKDEP_KEYS ((1UL << MAX_LOCKDEP_KEYS_BITS) - 1) +#define MAX_LOCKDEP_KEYS (1UL << MAX_LOCKDEP_KEYS_BITS) +#define INITIAL_CHAIN_KEY -1 struct held_lock { /* @@ -247,6 +249,11 @@ struct held_lock { u64 waittime_stamp; u64 holdtime_stamp; #endif + /* + * class_idx is zero-indexed; it points to the element in + * lock_classes this held lock instance belongs to. class_idx is in + * the range from 0 to (MAX_LOCKDEP_KEYS-1) inclusive. + */ unsigned int class_idx:MAX_LOCKDEP_KEYS_BITS; /* * The lock-stack is unified in that the lock chains of interrupt @@ -281,6 +288,8 @@ extern void lockdep_free_key_range(void *start, unsigned long size); extern asmlinkage void lockdep_sys_exit(void); extern void lockdep_set_selftest_task(struct task_struct *task); +extern void lockdep_init_task(struct task_struct *task); + extern void lockdep_off(void); extern void lockdep_on(void); @@ -385,7 +394,7 @@ extern void lock_unpin_lock(struct lockdep_map *lock, struct pin_cookie); WARN_ON(debug_locks && !lockdep_is_held(l)); \ } while (0) -#define lockdep_assert_held_exclusive(l) do { \ +#define lockdep_assert_held_write(l) do { \ WARN_ON(debug_locks && !lockdep_is_held_type(l, 0)); \ } while (0) @@ -405,6 +414,10 @@ extern void lock_unpin_lock(struct lockdep_map *lock, struct pin_cookie); #else /* !CONFIG_LOCKDEP */ +static inline void lockdep_init_task(struct task_struct *task) +{ +} + static inline void lockdep_off(void) { } @@ -466,7 +479,7 @@ struct lockdep_map { }; #define lockdep_is_held_type(l, r) (1) #define lockdep_assert_held(l) do { (void)(l); } while (0) -#define lockdep_assert_held_exclusive(l) do { (void)(l); } while (0) +#define lockdep_assert_held_write(l) do { (void)(l); } while (0) #define lockdep_assert_held_read(l) do { (void)(l); } while (0) #define lockdep_assert_held_once(l) do { (void)(l); } while (0) @@ -497,7 +510,6 @@ enum xhlock_context_t { { .name = (_name), .key = (void *)(_key), } static inline void lockdep_invariant_state(bool force) {} -static inline void lockdep_init_task(struct task_struct *task) {} static inline void lockdep_free_task(struct task_struct *task) {} #ifdef CONFIG_LOCK_STAT @@ -632,11 +644,18 @@ do { \ "IRQs not disabled as expected\n"); \ } while (0) +#define lockdep_assert_in_irq() do { \ + WARN_ONCE(debug_locks && !current->lockdep_recursion && \ + !current->hardirq_context, \ + "Not in hardirq as expected\n"); \ + } while (0) + #else # define might_lock(lock) do { } while (0) # define might_lock_read(lock) do { } while (0) # define lockdep_assert_irqs_enabled() do { } while (0) # define lockdep_assert_irqs_disabled() do { } while (0) +# define lockdep_assert_in_irq() do { } while (0) #endif #ifdef CONFIG_LOCKDEP diff --git a/include/linux/log2.h b/include/linux/log2.h index 1aec01365ed4..83a4a3ca3e8a 100644 --- a/include/linux/log2.h +++ b/include/linux/log2.h @@ -220,4 +220,38 @@ int __order_base_2(unsigned long n) ilog2((n) - 1) + 1) : \ __order_base_2(n) \ ) + +static inline __attribute__((const)) +int __bits_per(unsigned long n) +{ + if (n < 2) + return 1; + if (is_power_of_2(n)) + return order_base_2(n) + 1; + return order_base_2(n); +} + +/** + * bits_per - calculate the number of bits required for the argument + * @n: parameter + * + * This is constant-capable and can be used for compile time + * initializations, e.g bitfields. + * + * The first few values calculated by this routine: + * bf(0) = 1 + * bf(1) = 1 + * bf(2) = 2 + * bf(3) = 2 + * bf(4) = 3 + * ... and so on. + */ +#define bits_per(n) \ +( \ + __builtin_constant_p(n) ? ( \ + ((n) == 0 || (n) == 1) \ + ? 1 : ilog2(n) + 1 \ + ) : \ + __bits_per(n) \ +) #endif /* _LINUX_LOG2_H */ diff --git a/include/linux/module.h b/include/linux/module.h index 188998d3dca9..1455812dd325 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -21,6 +21,7 @@ #include <linux/rbtree_latch.h> #include <linux/error-injection.h> #include <linux/tracepoint-defs.h> +#include <linux/srcu.h> #include <linux/percpu.h> #include <asm/module.h> @@ -450,6 +451,10 @@ struct module { unsigned int num_tracepoints; tracepoint_ptr_t *tracepoints_ptrs; #endif +#ifdef CONFIG_TREE_SRCU + unsigned int num_srcu_structs; + struct srcu_struct **srcu_struct_ptrs; +#endif #ifdef CONFIG_BPF_EVENTS unsigned int num_bpf_raw_events; struct bpf_raw_event_map *bpf_raw_events; diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 9ec3544baee2..fe0b29bf2df7 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -333,19 +333,6 @@ static inline struct page *grab_cache_page_nowait(struct address_space *mapping, mapping_gfp_mask(mapping)); } -static inline struct page *find_subpage(struct page *page, pgoff_t offset) -{ - unsigned long mask; - - if (PageHuge(page)) - return page; - - VM_BUG_ON_PAGE(PageTail(page), page); - - mask = (1UL << compound_order(page)) - 1; - return page + (offset & mask); -} - struct page *find_get_entry(struct address_space *mapping, pgoff_t offset); struct page *find_lock_entry(struct address_space *mapping, pgoff_t offset); unsigned find_get_entries(struct address_space *mapping, pgoff_t start, diff --git a/include/linux/percpu-rwsem.h b/include/linux/percpu-rwsem.h index 03cb4b6f842e..3998cdf9cd14 100644 --- a/include/linux/percpu-rwsem.h +++ b/include/linux/percpu-rwsem.h @@ -17,14 +17,18 @@ struct percpu_rw_semaphore { int readers_block; }; -#define DEFINE_STATIC_PERCPU_RWSEM(name) \ +#define __DEFINE_PERCPU_RWSEM(name, is_static) \ static DEFINE_PER_CPU(unsigned int, __percpu_rwsem_rc_##name); \ -static struct percpu_rw_semaphore name = { \ - .rss = __RCU_SYNC_INITIALIZER(name.rss, RCU_SCHED_SYNC), \ +is_static struct percpu_rw_semaphore name = { \ + .rss = __RCU_SYNC_INITIALIZER(name.rss), \ .read_count = &__percpu_rwsem_rc_##name, \ .rw_sem = __RWSEM_INITIALIZER(name.rw_sem), \ .writer = __RCUWAIT_INITIALIZER(name.writer), \ } +#define DEFINE_PERCPU_RWSEM(name) \ + __DEFINE_PERCPU_RWSEM(name, /* not static */) +#define DEFINE_STATIC_PERCPU_RWSEM(name) \ + __DEFINE_PERCPU_RWSEM(name, static) extern int __percpu_down_read(struct percpu_rw_semaphore *, int); extern void __percpu_up_read(struct percpu_rw_semaphore *); @@ -117,7 +121,7 @@ static inline void percpu_rwsem_release(struct percpu_rw_semaphore *sem, lock_release(&sem->rw_sem.dep_map, 1, ip); #ifdef CONFIG_RWSEM_SPIN_ON_OWNER if (!read) - sem->rw_sem.owner = RWSEM_OWNER_UNKNOWN; + atomic_long_set(&sem->rw_sem.owner, RWSEM_OWNER_UNKNOWN); #endif } @@ -127,7 +131,7 @@ static inline void percpu_rwsem_acquire(struct percpu_rw_semaphore *sem, lock_acquire(&sem->rw_sem.dep_map, 0, 1, read, 1, NULL, ip); #ifdef CONFIG_RWSEM_SPIN_ON_OWNER if (!read) - sem->rw_sem.owner = current; + atomic_long_set(&sem->rw_sem.owner, (long)current); #endif } diff --git a/include/linux/perf/arm_pmu.h b/include/linux/perf/arm_pmu.h index a9b0ee408fbd..71f525a35ac2 100644 --- a/include/linux/perf/arm_pmu.h +++ b/include/linux/perf/arm_pmu.h @@ -171,4 +171,6 @@ void armpmu_free_irq(int irq, int cpu); #endif /* CONFIG_ARM_PMU */ +#define ARMV8_SPE_PDEV_NAME "arm,spe-v1" + #endif /* __ARM_PMU_H__ */ diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 0ab99c7b652d..2bca72f3028b 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -241,6 +241,7 @@ struct perf_event; #define PERF_PMU_CAP_NO_INTERRUPT 0x01 #define PERF_PMU_CAP_NO_NMI 0x02 #define PERF_PMU_CAP_AUX_NO_SG 0x04 +#define PERF_PMU_CAP_EXTENDED_REGS 0x08 #define PERF_PMU_CAP_EXCLUSIVE 0x10 #define PERF_PMU_CAP_ITRACE 0x20 #define PERF_PMU_CAP_HETEROGENEOUS_CPUS 0x40 diff --git a/include/linux/perf_regs.h b/include/linux/perf_regs.h index 476747456bca..2d12e97d5e7b 100644 --- a/include/linux/perf_regs.h +++ b/include/linux/perf_regs.h @@ -11,6 +11,11 @@ struct perf_regs { #ifdef CONFIG_HAVE_PERF_REGS #include <asm/perf_regs.h> + +#ifndef PERF_REG_EXTENDED_MASK +#define PERF_REG_EXTENDED_MASK 0 +#endif + u64 perf_reg_value(struct pt_regs *regs, int idx); int perf_reg_validate(u64 mask); u64 perf_reg_abi(struct task_struct *task); @@ -18,6 +23,9 @@ void perf_get_regs_user(struct perf_regs *regs_user, struct pt_regs *regs, struct pt_regs *regs_user_copy); #else + +#define PERF_REG_EXTENDED_MASK 0 + static inline u64 perf_reg_value(struct pt_regs *regs, int idx) { return 0; diff --git a/include/linux/pfn_t.h b/include/linux/pfn_t.h index 7bb77850c65a..3c202a11a79e 100644 --- a/include/linux/pfn_t.h +++ b/include/linux/pfn_t.h @@ -68,7 +68,7 @@ static inline phys_addr_t pfn_t_to_phys(pfn_t pfn) static inline void *pfn_t_to_virt(pfn_t pfn) { - if (pfn_t_has_page(pfn)) + if (pfn_t_has_page(pfn) && !is_device_private_page(pfn_t_to_page(pfn))) return __va(pfn_t_to_phys(pfn)); return NULL; } diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index 52a283ba0465..a705aa2d03f9 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -75,6 +75,15 @@ struct proc_dir_entry *proc_create_net_single_write(const char *name, umode_t mo void *data); extern struct pid *tgid_pidfd_to_pid(const struct file *file); +#ifdef CONFIG_PROC_PID_ARCH_STATUS +/* + * The architecture which selects CONFIG_PROC_PID_ARCH_STATUS must + * provide proc_pid_arch_status() definition. + */ +int proc_pid_arch_status(struct seq_file *m, struct pid_namespace *ns, + struct pid *pid, struct task_struct *task); +#endif /* CONFIG_PROC_PID_ARCH_STATUS */ + #else /* CONFIG_PROC_FS */ static inline void proc_root_init(void) diff --git a/include/linux/processor.h b/include/linux/processor.h index dbc952eec869..dc78bdc7079a 100644 --- a/include/linux/processor.h +++ b/include/linux/processor.h @@ -32,15 +32,6 @@ #define spin_cpu_relax() cpu_relax() #endif -/* - * spin_cpu_yield may be called to yield (undirected) to the hypervisor if - * necessary. This should be used if the wait is expected to take longer - * than context switch overhead, but we can't sleep or do a directed yield. - */ -#ifndef spin_cpu_yield -#define spin_cpu_yield() cpu_relax_yield() -#endif - #ifndef spin_end #define spin_end() #endif diff --git a/include/linux/rcu_sync.h b/include/linux/rcu_sync.h index 6fc53a1345b3..9b83865d24f9 100644 --- a/include/linux/rcu_sync.h +++ b/include/linux/rcu_sync.h @@ -13,62 +13,44 @@ #include <linux/wait.h> #include <linux/rcupdate.h> -enum rcu_sync_type { RCU_SYNC, RCU_SCHED_SYNC, RCU_BH_SYNC }; - /* Structure to mediate between updaters and fastpath-using readers. */ struct rcu_sync { int gp_state; int gp_count; wait_queue_head_t gp_wait; - int cb_state; struct rcu_head cb_head; - - enum rcu_sync_type gp_type; }; -extern void rcu_sync_lockdep_assert(struct rcu_sync *); - /** * rcu_sync_is_idle() - Are readers permitted to use their fastpaths? * @rsp: Pointer to rcu_sync structure to use for synchronization * - * Returns true if readers are permitted to use their fastpaths. - * Must be invoked within an RCU read-side critical section whose - * flavor matches that of the rcu_sync struture. + * Returns true if readers are permitted to use their fastpaths. Must be + * invoked within some flavor of RCU read-side critical section. */ static inline bool rcu_sync_is_idle(struct rcu_sync *rsp) { -#ifdef CONFIG_PROVE_RCU - rcu_sync_lockdep_assert(rsp); -#endif - return !rsp->gp_state; /* GP_IDLE */ + RCU_LOCKDEP_WARN(!rcu_read_lock_held() && + !rcu_read_lock_bh_held() && + !rcu_read_lock_sched_held(), + "suspicious rcu_sync_is_idle() usage"); + return !READ_ONCE(rsp->gp_state); /* GP_IDLE */ } -extern void rcu_sync_init(struct rcu_sync *, enum rcu_sync_type); +extern void rcu_sync_init(struct rcu_sync *); extern void rcu_sync_enter_start(struct rcu_sync *); extern void rcu_sync_enter(struct rcu_sync *); extern void rcu_sync_exit(struct rcu_sync *); extern void rcu_sync_dtor(struct rcu_sync *); -#define __RCU_SYNC_INITIALIZER(name, type) { \ +#define __RCU_SYNC_INITIALIZER(name) { \ .gp_state = 0, \ .gp_count = 0, \ .gp_wait = __WAIT_QUEUE_HEAD_INITIALIZER(name.gp_wait), \ - .cb_state = 0, \ - .gp_type = type, \ } -#define __DEFINE_RCU_SYNC(name, type) \ - struct rcu_sync_struct name = __RCU_SYNC_INITIALIZER(name, type) - -#define DEFINE_RCU_SYNC(name) \ - __DEFINE_RCU_SYNC(name, RCU_SYNC) - -#define DEFINE_RCU_SCHED_SYNC(name) \ - __DEFINE_RCU_SYNC(name, RCU_SCHED_SYNC) - -#define DEFINE_RCU_BH_SYNC(name) \ - __DEFINE_RCU_SYNC(name, RCU_BH_SYNC) +#define DEFINE_RCU_SYNC(name) \ + struct rcu_sync name = __RCU_SYNC_INITIALIZER(name) #endif /* _LINUX_RCU_SYNC_H_ */ diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index b25d20822e75..8f7167478c1d 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -365,16 +365,15 @@ static inline void rcu_preempt_sleep_check(void) { } * other macros that it invokes. */ #define rcu_assign_pointer(p, v) \ -({ \ +do { \ uintptr_t _r_a_p__v = (uintptr_t)(v); \ - rcu_check_sparse(p, __rcu); \ + rcu_check_sparse(p, __rcu); \ \ if (__builtin_constant_p(v) && (_r_a_p__v) == (uintptr_t)NULL) \ WRITE_ONCE((p), (typeof(p))(_r_a_p__v)); \ else \ smp_store_release(&p, RCU_INITIALIZER((typeof(p))_r_a_p__v)); \ - _r_a_p__v; \ -}) +} while (0) /** * rcu_swap_protected() - swap an RCU and a regular pointer @@ -586,7 +585,7 @@ static inline void rcu_preempt_sleep_check(void) { } * read-side critical sections may be preempted and they may also block, but * only when acquiring spinlocks that are subject to priority inheritance. */ -static inline void rcu_read_lock(void) +static __always_inline void rcu_read_lock(void) { __rcu_read_lock(); __acquire(RCU); @@ -803,7 +802,7 @@ static inline notrace void rcu_read_unlock_sched_notrace(void) /** * kfree_rcu() - kfree an object after a grace period. * @ptr: pointer to kfree - * @rcu_head: the name of the struct rcu_head within the type of @ptr. + * @rhf: the name of the struct rcu_head within the type of @ptr. * * Many rcu callbacks functions just call kfree() on the base structure. * These functions are trivial, but their size adds up, and furthermore @@ -826,9 +825,13 @@ static inline notrace void rcu_read_unlock_sched_notrace(void) * The BUILD_BUG_ON check must not involve any function calls, hence the * checks are done in macros here. */ -#define kfree_rcu(ptr, rcu_head) \ - __kfree_rcu(&((ptr)->rcu_head), offsetof(typeof(*(ptr)), rcu_head)) - +#define kfree_rcu(ptr, rhf) \ +do { \ + typeof (ptr) ___p = (ptr); \ + \ + if (___p) \ + __kfree_rcu(&((___p)->rhf), offsetof(typeof(*(ptr)), rhf)); \ +} while (0) /* * Place this after a lock-acquisition primitive to guarantee that diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h index 2ea18a3def04..e401358c4e7e 100644 --- a/include/linux/rwsem.h +++ b/include/linux/rwsem.h @@ -34,12 +34,13 @@ */ struct rw_semaphore { atomic_long_t count; -#ifdef CONFIG_RWSEM_SPIN_ON_OWNER /* - * Write owner. Used as a speculative check to see - * if the owner is running on the cpu. + * Write owner or one of the read owners as well flags regarding + * the current state of the rwsem. Can be used as a speculative + * check to see if the write owner is running on the cpu. */ - struct task_struct *owner; + atomic_long_t owner; +#ifdef CONFIG_RWSEM_SPIN_ON_OWNER struct optimistic_spin_queue osq; /* spinner MCS lock */ #endif raw_spinlock_t wait_lock; @@ -50,10 +51,10 @@ struct rw_semaphore { }; /* - * Setting bit 1 of the owner field but not bit 0 will indicate + * Setting all bits of the owner field except bit 0 will indicate * that the rwsem is writer-owned with an unknown owner. */ -#define RWSEM_OWNER_UNKNOWN ((struct task_struct *)-2L) +#define RWSEM_OWNER_UNKNOWN (-2L) /* In all implementations count != 0 means locked */ static inline int rwsem_is_locked(struct rw_semaphore *sem) @@ -73,13 +74,14 @@ static inline int rwsem_is_locked(struct rw_semaphore *sem) #endif #ifdef CONFIG_RWSEM_SPIN_ON_OWNER -#define __RWSEM_OPT_INIT(lockname) , .osq = OSQ_LOCK_UNLOCKED, .owner = NULL +#define __RWSEM_OPT_INIT(lockname) , .osq = OSQ_LOCK_UNLOCKED #else #define __RWSEM_OPT_INIT(lockname) #endif #define __RWSEM_INITIALIZER(name) \ { __RWSEM_INIT_COUNT(name), \ + .owner = ATOMIC_LONG_INIT(0), \ .wait_list = LIST_HEAD_INIT((name).wait_list), \ .wait_lock = __RAW_SPIN_LOCK_UNLOCKED(name.wait_lock) \ __RWSEM_OPT_INIT(name) \ diff --git a/include/linux/sched.h b/include/linux/sched.h index 11837410690f..8dc1811487f5 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -35,6 +35,7 @@ struct audit_context; struct backing_dev_info; struct bio_list; struct blk_plug; +struct capture_control; struct cfs_rq; struct fs_struct; struct futex_pi_state; @@ -47,8 +48,9 @@ struct pid_namespace; struct pipe_inode_info; struct rcu_node; struct reclaim_state; -struct capture_control; struct robust_list_head; +struct root_domain; +struct rq; struct sched_attr; struct sched_param; struct seq_file; @@ -281,6 +283,18 @@ struct vtime { u64 gtime; }; +/* + * Utilization clamp constraints. + * @UCLAMP_MIN: Minimum utilization + * @UCLAMP_MAX: Maximum utilization + * @UCLAMP_CNT: Utilization clamp constraints count + */ +enum uclamp_id { + UCLAMP_MIN = 0, + UCLAMP_MAX, + UCLAMP_CNT +}; + struct sched_info { #ifdef CONFIG_SCHED_INFO /* Cumulative counters: */ @@ -312,6 +326,10 @@ struct sched_info { # define SCHED_FIXEDPOINT_SHIFT 10 # define SCHED_FIXEDPOINT_SCALE (1L << SCHED_FIXEDPOINT_SHIFT) +/* Increase resolution of cpu_capacity calculations */ +# define SCHED_CAPACITY_SHIFT SCHED_FIXEDPOINT_SHIFT +# define SCHED_CAPACITY_SCALE (1L << SCHED_CAPACITY_SHIFT) + struct load_weight { unsigned long weight; u32 inv_weight; @@ -560,12 +578,47 @@ struct sched_dl_entity { struct hrtimer inactive_timer; }; +#ifdef CONFIG_UCLAMP_TASK +/* Number of utilization clamp buckets (shorter alias) */ +#define UCLAMP_BUCKETS CONFIG_UCLAMP_BUCKETS_COUNT + +/* + * Utilization clamp for a scheduling entity + * @value: clamp value "assigned" to a se + * @bucket_id: bucket index corresponding to the "assigned" value + * @active: the se is currently refcounted in a rq's bucket + * @user_defined: the requested clamp value comes from user-space + * + * The bucket_id is the index of the clamp bucket matching the clamp value + * which is pre-computed and stored to avoid expensive integer divisions from + * the fast path. + * + * The active bit is set whenever a task has got an "effective" value assigned, + * which can be different from the clamp value "requested" from user-space. + * This allows to know a task is refcounted in the rq's bucket corresponding + * to the "effective" bucket_id. + * + * The user_defined bit is set whenever a task has got a task-specific clamp + * value requested from userspace, i.e. the system defaults apply to this task + * just as a restriction. This allows to relax default clamps when a less + * restrictive task-specific value has been requested, thus allowing to + * implement a "nice" semantic. For example, a task running with a 20% + * default boost can still drop its own boosting to 0%. + */ +struct uclamp_se { + unsigned int value : bits_per(SCHED_CAPACITY_SCALE); + unsigned int bucket_id : bits_per(UCLAMP_BUCKETS); + unsigned int active : 1; + unsigned int user_defined : 1; +}; +#endif /* CONFIG_UCLAMP_TASK */ + union rcu_special { struct { u8 blocked; u8 need_qs; u8 exp_hint; /* Hint for performance. */ - u8 pad; /* No garbage from compiler! */ + u8 deferred_qs; } b; /* Bits. */ u32 s; /* Set of bits. */ }; @@ -640,6 +693,13 @@ struct task_struct { #endif struct sched_dl_entity dl; +#ifdef CONFIG_UCLAMP_TASK + /* Clamp values requested for a scheduling entity */ + struct uclamp_se uclamp_req[UCLAMP_CNT]; + /* Effective clamp values used for a scheduling entity */ + struct uclamp_se uclamp[UCLAMP_CNT]; +#endif + #ifdef CONFIG_PREEMPT_NOTIFIERS /* List of struct preempt_notifier: */ struct hlist_head preempt_notifiers; @@ -651,7 +711,8 @@ struct task_struct { unsigned int policy; int nr_cpus_allowed; - cpumask_t cpus_allowed; + const cpumask_t *cpus_ptr; + cpumask_t cpus_mask; #ifdef CONFIG_PREEMPT_RCU int rcu_read_lock_nesting; @@ -831,6 +892,11 @@ struct task_struct { /* Effective (overridable) subjective task credentials (COW): */ const struct cred __rcu *cred; +#ifdef CONFIG_KEYS + /* Cached requested key. */ + struct key *cached_requested_key; +#endif + /* * executable name, excluding path. * @@ -1399,7 +1465,7 @@ extern struct pid *cad_pid; #define PF_SWAPWRITE 0x00800000 /* Allowed to write to swap */ #define PF_MEMSTALL 0x01000000 /* Stalled due to lack of memory */ #define PF_UMH 0x02000000 /* I'm an Usermodehelper process */ -#define PF_NO_SETAFFINITY 0x04000000 /* Userland is not allowed to meddle with cpus_allowed */ +#define PF_NO_SETAFFINITY 0x04000000 /* Userland is not allowed to meddle with cpus_mask */ #define PF_MCE_EARLY 0x08000000 /* Early kill for mce process policy */ #define PF_MEMALLOC_NOCMA 0x10000000 /* All allocation request will have _GFP_MOVABLE cleared */ #define PF_FREEZER_SKIP 0x40000000 /* Freezer should not count it as freezable */ @@ -1518,10 +1584,6 @@ static inline int set_cpus_allowed_ptr(struct task_struct *p, const struct cpuma } #endif -#ifndef cpu_relax_yield -#define cpu_relax_yield() cpu_relax() -#endif - extern int yield_to(struct task_struct *p, bool preempt); extern void set_user_nice(struct task_struct *p, long nice); extern int task_prio(const struct task_struct *p); @@ -1919,4 +1981,16 @@ static inline void rseq_syscall(struct pt_regs *regs) #endif +const struct sched_avg *sched_trace_cfs_rq_avg(struct cfs_rq *cfs_rq); +char *sched_trace_cfs_rq_path(struct cfs_rq *cfs_rq, char *str, int len); +int sched_trace_cfs_rq_cpu(struct cfs_rq *cfs_rq); + +const struct sched_avg *sched_trace_rq_avg_rt(struct rq *rq); +const struct sched_avg *sched_trace_rq_avg_dl(struct rq *rq); +const struct sched_avg *sched_trace_rq_avg_irq(struct rq *rq); + +int sched_trace_rq_cpu(struct rq *rq); + +const struct cpumask *sched_trace_rd_span(struct root_domain *rd); + #endif diff --git a/include/linux/sched/nohz.h b/include/linux/sched/nohz.h index b36f4cf38111..1abe91ff6e4a 100644 --- a/include/linux/sched/nohz.h +++ b/include/linux/sched/nohz.h @@ -7,14 +7,6 @@ */ #if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON) -extern void cpu_load_update_nohz_start(void); -extern void cpu_load_update_nohz_stop(void); -#else -static inline void cpu_load_update_nohz_start(void) { } -static inline void cpu_load_update_nohz_stop(void) { } -#endif - -#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON) extern void nohz_balance_enter_idle(int cpu); extern int get_nohz_timer_target(void); #else diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h index 99ce6d728df7..d4f6215ee03f 100644 --- a/include/linux/sched/sysctl.h +++ b/include/linux/sched/sysctl.h @@ -56,6 +56,11 @@ int sched_proc_update_handler(struct ctl_table *table, int write, extern unsigned int sysctl_sched_rt_period; extern int sysctl_sched_rt_runtime; +#ifdef CONFIG_UCLAMP_TASK +extern unsigned int sysctl_sched_uclamp_util_min; +extern unsigned int sysctl_sched_uclamp_util_max; +#endif + #ifdef CONFIG_CFS_BANDWIDTH extern unsigned int sysctl_sched_cfs_bandwidth_slice; #endif @@ -75,6 +80,12 @@ extern int sched_rt_handler(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos); +#ifdef CONFIG_UCLAMP_TASK +extern int sysctl_sched_uclamp_handler(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, + loff_t *ppos); +#endif + extern int sysctl_numa_balancing(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos); diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h index cfc0a89a7159..7863bb62d2ab 100644 --- a/include/linux/sched/topology.h +++ b/include/linux/sched/topology.h @@ -7,12 +7,6 @@ #include <linux/sched/idle.h> /* - * Increase resolution of cpu_capacity calculations - */ -#define SCHED_CAPACITY_SHIFT SCHED_FIXEDPOINT_SHIFT -#define SCHED_CAPACITY_SCALE (1L << SCHED_CAPACITY_SHIFT) - -/* * sched-domains (multiprocessor balancing) declarations: */ #ifdef CONFIG_SMP @@ -84,11 +78,6 @@ struct sched_domain { unsigned int busy_factor; /* less balancing by factor if busy */ unsigned int imbalance_pct; /* No balance until over watermark */ unsigned int cache_nice_tries; /* Leave cache hot tasks for # tries */ - unsigned int busy_idx; - unsigned int idle_idx; - unsigned int newidle_idx; - unsigned int wake_idx; - unsigned int forkexec_idx; int nohz_idle; /* NOHZ IDLE status */ int flags; /* See SD_* */ @@ -201,14 +190,6 @@ extern void set_sched_topology(struct sched_domain_topology_level *tl); # define SD_INIT_NAME(type) #endif -#ifndef arch_scale_cpu_capacity -static __always_inline -unsigned long arch_scale_cpu_capacity(struct sched_domain *sd, int cpu) -{ - return SCHED_CAPACITY_SCALE; -} -#endif - #else /* CONFIG_SMP */ struct sched_domain_attr; @@ -224,16 +205,16 @@ static inline bool cpus_share_cache(int this_cpu, int that_cpu) return true; } +#endif /* !CONFIG_SMP */ + #ifndef arch_scale_cpu_capacity static __always_inline -unsigned long arch_scale_cpu_capacity(void __always_unused *sd, int cpu) +unsigned long arch_scale_cpu_capacity(int cpu) { return SCHED_CAPACITY_SCALE; } #endif -#endif /* !CONFIG_SMP */ - static inline int task_node(const struct task_struct *p) { return cpu_to_node(task_cpu(p)); diff --git a/include/linux/sched/user.h b/include/linux/sched/user.h index 468d2565a9fe..917d88edb7b9 100644 --- a/include/linux/sched/user.h +++ b/include/linux/sched/user.h @@ -7,8 +7,6 @@ #include <linux/refcount.h> #include <linux/ratelimit.h> -struct key; - /* * Some day this will be a full-fledged user tracking system.. */ @@ -30,18 +28,6 @@ struct user_struct { unsigned long unix_inflight; /* How many files in flight in unix sockets */ atomic_long_t pipe_bufs; /* how many pages are allocated in pipe buffers */ -#ifdef CONFIG_KEYS - /* - * These pointers can only change from NULL to a non-NULL value once. - * Writes are protected by key_user_keyring_mutex. - * Unlocked readers should use READ_ONCE() unless they know that - * install_user_keyrings() has been called successfully (which sets - * these members to non-NULL values, preventing further modifications). - */ - struct key *uid_keyring; /* UID specific keyring */ - struct key *session_keyring; /* UID's default session keyring */ -#endif - /* Hash table maintenance information */ struct hlist_node uidhash_node; kuid_t uid; diff --git a/include/linux/sched/wake_q.h b/include/linux/sched/wake_q.h index ad826d2a4557..26a2013ac39c 100644 --- a/include/linux/sched/wake_q.h +++ b/include/linux/sched/wake_q.h @@ -51,6 +51,11 @@ static inline void wake_q_init(struct wake_q_head *head) head->lastp = &head->first; } +static inline bool wake_q_empty(struct wake_q_head *head) +{ + return head->first == WAKE_Q_TAIL; +} + extern void wake_q_add(struct wake_q_head *head, struct task_struct *task); extern void wake_q_add_safe(struct wake_q_head *head, struct task_struct *task); extern void wake_up_q(struct wake_q_head *head); diff --git a/include/linux/security.h b/include/linux/security.h index 659071c2e57c..5f7441abbf42 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -189,9 +189,9 @@ static inline const char *kernel_load_data_id_str(enum kernel_load_data_id id) #ifdef CONFIG_SECURITY -int call_lsm_notifier(enum lsm_event event, void *data); -int register_lsm_notifier(struct notifier_block *nb); -int unregister_lsm_notifier(struct notifier_block *nb); +int call_blocking_lsm_notifier(enum lsm_event event, void *data); +int register_blocking_lsm_notifier(struct notifier_block *nb); +int unregister_blocking_lsm_notifier(struct notifier_block *nb); /* prototypes */ extern int security_init(void); @@ -394,17 +394,17 @@ int security_inode_setsecctx(struct dentry *dentry, void *ctx, u32 ctxlen); int security_inode_getsecctx(struct inode *inode, void **ctx, u32 *ctxlen); #else /* CONFIG_SECURITY */ -static inline int call_lsm_notifier(enum lsm_event event, void *data) +static inline int call_blocking_lsm_notifier(enum lsm_event event, void *data) { return 0; } -static inline int register_lsm_notifier(struct notifier_block *nb) +static inline int register_blocking_lsm_notifier(struct notifier_block *nb) { return 0; } -static inline int unregister_lsm_notifier(struct notifier_block *nb) +static inline int unregister_blocking_lsm_notifier(struct notifier_block *nb) { return 0; } diff --git a/include/linux/signal.h b/include/linux/signal.h index 9702016734b1..78c2bb376954 100644 --- a/include/linux/signal.h +++ b/include/linux/signal.h @@ -276,7 +276,7 @@ extern int sigprocmask(int, sigset_t *, sigset_t *); extern int set_user_sigmask(const sigset_t __user *usigmask, sigset_t *set, sigset_t *oldset, size_t sigsetsize); extern void restore_user_sigmask(const void __user *usigmask, - sigset_t *sigsaved); + sigset_t *sigsaved, bool interrupted); extern void set_current_blocked(sigset_t *); extern void __set_current_blocked(const sigset_t *); extern int show_unhandled_signals; diff --git a/include/linux/smp.h b/include/linux/smp.h index a56f08ff3097..6fc856c9eda5 100644 --- a/include/linux/smp.h +++ b/include/linux/smp.h @@ -35,7 +35,7 @@ int smp_call_function_single(int cpuid, smp_call_func_t func, void *info, /* * Call a function on all processors */ -int on_each_cpu(smp_call_func_t func, void *info, int wait); +void on_each_cpu(smp_call_func_t func, void *info, int wait); /* * Call a function on processors specified by mask, which might include @@ -101,7 +101,7 @@ extern void smp_cpus_done(unsigned int max_cpus); /* * Call a function on all other processors */ -int smp_call_function(smp_call_func_t func, void *info, int wait); +void smp_call_function(smp_call_func_t func, void *info, int wait); void smp_call_function_many(const struct cpumask *mask, smp_call_func_t func, void *info, bool wait); @@ -144,9 +144,8 @@ static inline void smp_send_stop(void) { } * These macros fold the SMP functionality into a single CPU system */ #define raw_smp_processor_id() 0 -static inline int up_smp_call_function(smp_call_func_t func, void *info) +static inline void up_smp_call_function(smp_call_func_t func, void *info) { - return 0; } #define smp_call_function(func, info, wait) \ (up_smp_call_function(func, info)) @@ -181,29 +180,46 @@ static inline int get_boot_cpu_id(void) #endif /* !SMP */ -/* - * smp_processor_id(): get the current CPU ID. +/** + * raw_processor_id() - get the current (unstable) CPU id + * + * For then you know what you are doing and need an unstable + * CPU id. + */ + +/** + * smp_processor_id() - get the current (stable) CPU id + * + * This is the normal accessor to the CPU id and should be used + * whenever possible. * - * if DEBUG_PREEMPT is enabled then we check whether it is - * used in a preemption-safe way. (smp_processor_id() is safe - * if it's used in a preemption-off critical section, or in - * a thread that is bound to the current CPU.) + * The CPU id is stable when: * - * NOTE: raw_smp_processor_id() is for internal use only - * (smp_processor_id() is the preferred variant), but in rare - * instances it might also be used to turn off false positives - * (i.e. smp_processor_id() use that the debugging code reports but - * which use for some reason is legal). Don't use this to hack around - * the warning message, as your code might not work under PREEMPT. + * - IRQs are disabled; + * - preemption is disabled; + * - the task is CPU affine. + * + * When CONFIG_DEBUG_PREEMPT; we verify these assumption and WARN + * when smp_processor_id() is used when the CPU id is not stable. + */ + +/* + * Allow the architecture to differentiate between a stable and unstable read. + * For example, x86 uses an IRQ-safe asm-volatile read for the unstable but a + * regular asm read for the stable. */ +#ifndef __smp_processor_id +#define __smp_processor_id(x) raw_smp_processor_id(x) +#endif + #ifdef CONFIG_DEBUG_PREEMPT extern unsigned int debug_smp_processor_id(void); # define smp_processor_id() debug_smp_processor_id() #else -# define smp_processor_id() raw_smp_processor_id() +# define smp_processor_id() __smp_processor_id() #endif -#define get_cpu() ({ preempt_disable(); smp_processor_id(); }) +#define get_cpu() ({ preempt_disable(); __smp_processor_id(); }) #define put_cpu() preempt_enable() /* diff --git a/include/linux/srcutree.h b/include/linux/srcutree.h index 7f7c8c050f63..9cfcc8a756ae 100644 --- a/include/linux/srcutree.h +++ b/include/linux/srcutree.h @@ -120,9 +120,17 @@ struct srcu_struct { * * See include/linux/percpu-defs.h for the rules on per-CPU variables. */ -#define __DEFINE_SRCU(name, is_static) \ - static DEFINE_PER_CPU(struct srcu_data, name##_srcu_data);\ - is_static struct srcu_struct name = __SRCU_STRUCT_INIT(name, name##_srcu_data) +#ifdef MODULE +# define __DEFINE_SRCU(name, is_static) \ + is_static struct srcu_struct name; \ + struct srcu_struct * const __srcu_struct_##name \ + __section("___srcu_struct_ptrs") = &name +#else +# define __DEFINE_SRCU(name, is_static) \ + static DEFINE_PER_CPU(struct srcu_data, name##_srcu_data); \ + is_static struct srcu_struct name = \ + __SRCU_STRUCT_INIT(name, name##_srcu_data) +#endif #define DEFINE_SRCU(name) __DEFINE_SRCU(name, /* not static */) #define DEFINE_STATIC_SRCU(name) __DEFINE_SRCU(name, static) diff --git a/include/linux/stop_machine.h b/include/linux/stop_machine.h index 6d3635c86dbe..f9a0c6189852 100644 --- a/include/linux/stop_machine.h +++ b/include/linux/stop_machine.h @@ -36,6 +36,7 @@ int stop_cpus(const struct cpumask *cpumask, cpu_stop_fn_t fn, void *arg); int try_stop_cpus(const struct cpumask *cpumask, cpu_stop_fn_t fn, void *arg); void stop_machine_park(int cpu); void stop_machine_unpark(int cpu); +void stop_machine_yield(const struct cpumask *cpumask); #else /* CONFIG_SMP */ diff --git a/include/linux/suspend.h b/include/linux/suspend.h index 8594001e8be8..f0d262ad7b78 100644 --- a/include/linux/suspend.h +++ b/include/linux/suspend.h @@ -209,8 +209,9 @@ extern int suspend_valid_only_mem(suspend_state_t state); extern unsigned int pm_suspend_global_flags; -#define PM_SUSPEND_FLAG_FW_SUSPEND (1 << 0) -#define PM_SUSPEND_FLAG_FW_RESUME (1 << 1) +#define PM_SUSPEND_FLAG_FW_SUSPEND BIT(0) +#define PM_SUSPEND_FLAG_FW_RESUME BIT(1) +#define PM_SUSPEND_FLAG_NO_PLATFORM BIT(2) static inline void pm_suspend_clear_flags(void) { @@ -227,6 +228,11 @@ static inline void pm_set_resume_via_firmware(void) pm_suspend_global_flags |= PM_SUSPEND_FLAG_FW_RESUME; } +static inline void pm_set_suspend_no_platform(void) +{ + pm_suspend_global_flags |= PM_SUSPEND_FLAG_NO_PLATFORM; +} + /** * pm_suspend_via_firmware - Check if platform firmware will suspend the system. * @@ -268,6 +274,22 @@ static inline bool pm_resume_via_firmware(void) return !!(pm_suspend_global_flags & PM_SUSPEND_FLAG_FW_RESUME); } +/** + * pm_suspend_no_platform - Check if platform may change device power states. + * + * To be called during system-wide power management transitions to sleep states + * or during the subsequent system-wide transitions back to the working state. + * + * Return 'true' if the power states of devices remain under full control of the + * kernel throughout the system-wide suspend and resume cycle in progress (that + * is, if a device is put into a certain power state during suspend, it can be + * expected to remain in that state during resume). + */ +static inline bool pm_suspend_no_platform(void) +{ + return !!(pm_suspend_global_flags & PM_SUSPEND_FLAG_NO_PLATFORM); +} + /* Suspend-to-idle state machnine. */ enum s2idle_states { S2IDLE_STATE_NONE, /* Not suspended/suspending. */ diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h index a8ab0f143ac4..b27e2ffa96c1 100644 --- a/include/linux/timekeeping.h +++ b/include/linux/timekeeping.h @@ -113,6 +113,34 @@ static inline ktime_t ktime_get_coarse_clocktai(void) return ktime_get_coarse_with_offset(TK_OFFS_TAI); } +static inline ktime_t ktime_get_coarse(void) +{ + struct timespec64 ts; + + ktime_get_coarse_ts64(&ts); + return timespec64_to_ktime(ts); +} + +static inline u64 ktime_get_coarse_ns(void) +{ + return ktime_to_ns(ktime_get_coarse()); +} + +static inline u64 ktime_get_coarse_real_ns(void) +{ + return ktime_to_ns(ktime_get_coarse_real()); +} + +static inline u64 ktime_get_coarse_boottime_ns(void) +{ + return ktime_to_ns(ktime_get_coarse_boottime()); +} + +static inline u64 ktime_get_coarse_clocktai_ns(void) +{ + return ktime_to_ns(ktime_get_coarse_clocktai()); +} + /** * ktime_mono_to_real - Convert monotonic time to clock realtime */ @@ -131,12 +159,12 @@ static inline u64 ktime_get_real_ns(void) return ktime_to_ns(ktime_get_real()); } -static inline u64 ktime_get_boot_ns(void) +static inline u64 ktime_get_boottime_ns(void) { return ktime_to_ns(ktime_get_boottime()); } -static inline u64 ktime_get_tai_ns(void) +static inline u64 ktime_get_clocktai_ns(void) { return ktime_to_ns(ktime_get_clocktai()); } diff --git a/include/linux/timer.h b/include/linux/timer.h index 7b066fd38248..282e4f2a532a 100644 --- a/include/linux/timer.h +++ b/include/linux/timer.h @@ -36,19 +36,30 @@ struct timer_list { #define __TIMER_LOCKDEP_MAP_INITIALIZER(_kn) #endif -/* - * A deferrable timer will work normally when the system is busy, but - * will not cause a CPU to come out of idle just to service it; instead, - * the timer will be serviced when the CPU eventually wakes up with a - * subsequent non-deferrable timer. +/** + * @TIMER_DEFERRABLE: A deferrable timer will work normally when the + * system is busy, but will not cause a CPU to come out of idle just + * to service it; instead, the timer will be serviced when the CPU + * eventually wakes up with a subsequent non-deferrable timer. * - * An irqsafe timer is executed with IRQ disabled and it's safe to wait for - * the completion of the running instance from IRQ handlers, for example, - * by calling del_timer_sync(). + * @TIMER_IRQSAFE: An irqsafe timer is executed with IRQ disabled and + * it's safe to wait for the completion of the running instance from + * IRQ handlers, for example, by calling del_timer_sync(). * * Note: The irq disabled callback execution is a special case for * workqueue locking issues. It's not meant for executing random crap * with interrupts disabled. Abuse is monitored! + * + * @TIMER_PINNED: A pinned timer will not be affected by any timer + * placement heuristics (like, NOHZ) and will always expire on the CPU + * on which the timer was enqueued. + * + * Note: Because enqueuing of timers can migrate the timer from one + * CPU to another, pinned timers are not guaranteed to stay on the + * initialy selected CPU. They move to the CPU on which the enqueue + * function is invoked via mod_timer() or add_timer(). If the timer + * should be placed on a particular CPU, then add_timer_on() has to be + * used. */ #define TIMER_CPUMASK 0x0003FFFF #define TIMER_MIGRATING 0x00040000 diff --git a/include/linux/topology.h b/include/linux/topology.h index cb0775e1ee4b..47a3e3c08036 100644 --- a/include/linux/topology.h +++ b/include/linux/topology.h @@ -184,6 +184,9 @@ static inline int cpu_to_mem(int cpu) #ifndef topology_physical_package_id #define topology_physical_package_id(cpu) ((void)(cpu), -1) #endif +#ifndef topology_die_id +#define topology_die_id(cpu) ((void)(cpu), -1) +#endif #ifndef topology_core_id #define topology_core_id(cpu) ((void)(cpu), 0) #endif @@ -193,6 +196,9 @@ static inline int cpu_to_mem(int cpu) #ifndef topology_core_cpumask #define topology_core_cpumask(cpu) cpumask_of(cpu) #endif +#ifndef topology_die_cpumask +#define topology_die_cpumask(cpu) cpumask_of(cpu) +#endif #ifdef CONFIG_SCHED_SMT static inline const struct cpumask *cpu_smt_mask(int cpu) diff --git a/include/linux/torture.h b/include/linux/torture.h index 23d80db426d7..a620118385bb 100644 --- a/include/linux/torture.h +++ b/include/linux/torture.h @@ -66,7 +66,7 @@ int torture_shutdown_init(int ssecs, void (*cleanup)(void)); /* Task stuttering, which forces load/no-load transitions. */ bool stutter_wait(const char *title); -int torture_stutter_init(int s); +int torture_stutter_init(int s, int sgap); /* Initialization and cleanup. */ bool torture_init_begin(char *ttype, int v); diff --git a/include/linux/tpm_eventlog.h b/include/linux/tpm_eventlog.h index 81519f163211..63238c84dc0b 100644 --- a/include/linux/tpm_eventlog.h +++ b/include/linux/tpm_eventlog.h @@ -112,4 +112,156 @@ struct tcg_pcr_event2_head { struct tpm_digest digests[]; } __packed; +struct tcg_algorithm_size { + u16 algorithm_id; + u16 algorithm_size; +}; + +struct tcg_algorithm_info { + u8 signature[16]; + u32 platform_class; + u8 spec_version_minor; + u8 spec_version_major; + u8 spec_errata; + u8 uintn_size; + u32 number_of_algorithms; + struct tcg_algorithm_size digest_sizes[]; +}; + +#ifndef TPM_MEMREMAP +#define TPM_MEMREMAP(start, size) NULL +#endif + +#ifndef TPM_MEMUNMAP +#define TPM_MEMUNMAP(start, size) do{} while(0) +#endif + +/** + * __calc_tpm2_event_size - calculate the size of a TPM2 event log entry + * @event: Pointer to the event whose size should be calculated + * @event_header: Pointer to the initial event containing the digest lengths + * @do_mapping: Whether or not the event needs to be mapped + * + * The TPM2 event log format can contain multiple digests corresponding to + * separate PCR banks, and also contains a variable length of the data that + * was measured. This requires knowledge of how long each digest type is, + * and this information is contained within the first event in the log. + * + * We calculate the length by examining the number of events, and then looking + * at each event in turn to determine how much space is used for events in + * total. Once we've done this we know the offset of the data length field, + * and can calculate the total size of the event. + * + * Return: size of the event on success, <0 on failure + */ + +static inline int __calc_tpm2_event_size(struct tcg_pcr_event2_head *event, + struct tcg_pcr_event *event_header, + bool do_mapping) +{ + struct tcg_efi_specid_event_head *efispecid; + struct tcg_event_field *event_field; + void *mapping = NULL; + int mapping_size; + void *marker; + void *marker_start; + u32 halg_size; + size_t size; + u16 halg; + int i; + int j; + + marker = event; + marker_start = marker; + marker = marker + sizeof(event->pcr_idx) + sizeof(event->event_type) + + sizeof(event->count); + + /* Map the event header */ + if (do_mapping) { + mapping_size = marker - marker_start; + mapping = TPM_MEMREMAP((unsigned long)marker_start, + mapping_size); + if (!mapping) { + size = 0; + goto out; + } + } else { + mapping = marker_start; + } + + event = (struct tcg_pcr_event2_head *)mapping; + + efispecid = (struct tcg_efi_specid_event_head *)event_header->event; + + /* Check if event is malformed. */ + if (event->count > efispecid->num_algs) { + size = 0; + goto out; + } + + for (i = 0; i < event->count; i++) { + halg_size = sizeof(event->digests[i].alg_id); + + /* Map the digest's algorithm identifier */ + if (do_mapping) { + TPM_MEMUNMAP(mapping, mapping_size); + mapping_size = halg_size; + mapping = TPM_MEMREMAP((unsigned long)marker, + mapping_size); + if (!mapping) { + size = 0; + goto out; + } + } else { + mapping = marker; + } + + memcpy(&halg, mapping, halg_size); + marker = marker + halg_size; + + for (j = 0; j < efispecid->num_algs; j++) { + if (halg == efispecid->digest_sizes[j].alg_id) { + marker += + efispecid->digest_sizes[j].digest_size; + break; + } + } + /* Algorithm without known length. Such event is unparseable. */ + if (j == efispecid->num_algs) { + size = 0; + goto out; + } + } + + /* + * Map the event size - we don't read from the event itself, so + * we don't need to map it + */ + if (do_mapping) { + TPM_MEMUNMAP(mapping, mapping_size); + mapping_size += sizeof(event_field->event_size); + mapping = TPM_MEMREMAP((unsigned long)marker, + mapping_size); + if (!mapping) { + size = 0; + goto out; + } + } else { + mapping = marker; + } + + event_field = (struct tcg_event_field *)mapping; + + marker = marker + sizeof(event_field->event_size) + + event_field->event_size; + size = marker - marker_start; + + if ((event->event_type == 0) && (event_field->event_size == 0)) + size = 0; +out: + if (do_mapping) + TPM_MEMUNMAP(mapping, mapping_size); + return size; +} + #endif diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h index 09d678433fc0..8446573cc682 100644 --- a/include/linux/tracehook.h +++ b/include/linux/tracehook.h @@ -184,6 +184,13 @@ static inline void tracehook_notify_resume(struct pt_regs *regs) if (unlikely(current->task_works)) task_work_run(); +#ifdef CONFIG_KEYS_REQUEST_CACHE + if (unlikely(current->cached_requested_key)) { + key_put(current->cached_requested_key); + current->cached_requested_key = NULL; + } +#endif + mem_cgroup_handle_over_high(); blkcg_maybe_throttle_current(); } diff --git a/include/linux/types.h b/include/linux/types.h index 231114ae38f4..05030f608be3 100644 --- a/include/linux/types.h +++ b/include/linux/types.h @@ -174,7 +174,7 @@ typedef struct { #ifdef CONFIG_64BIT typedef struct { - long counter; + s64 counter; } atomic64_t; #endif diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h index d6b74b91096b..fb9f4f799554 100644 --- a/include/linux/user_namespace.h +++ b/include/linux/user_namespace.h @@ -64,10 +64,20 @@ struct user_namespace { struct ns_common ns; unsigned long flags; +#ifdef CONFIG_KEYS + /* List of joinable keyrings in this namespace. Modification access of + * these pointers is controlled by keyring_sem. Once + * user_keyring_register is set, it won't be changed, so it can be + * accessed directly with READ_ONCE(). + */ + struct list_head keyring_name_list; + struct key *user_keyring_register; + struct rw_semaphore keyring_sem; +#endif + /* Register of per-UID persistent keyrings for this namespace */ #ifdef CONFIG_PERSISTENT_KEYRINGS struct key *persistent_keyring_register; - struct rw_semaphore persistent_keyring_register_sem; #endif struct work_struct work; #ifdef CONFIG_SYSCTL diff --git a/include/linux/xarray.h b/include/linux/xarray.h index 0e01e6129145..5921599b6dc4 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -265,6 +265,7 @@ enum xa_lock_type { #define XA_FLAGS_TRACK_FREE ((__force gfp_t)4U) #define XA_FLAGS_ZERO_BUSY ((__force gfp_t)8U) #define XA_FLAGS_ALLOC_WRAPPED ((__force gfp_t)16U) +#define XA_FLAGS_ACCOUNT ((__force gfp_t)32U) #define XA_FLAGS_MARK(mark) ((__force gfp_t)((1U << __GFP_BITS_SHIFT) << \ (__force unsigned)(mark))) diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 8fb5be3ca0ca..1fce25b1d87f 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -2007,7 +2007,7 @@ enum cfg80211_signal_type { * received by the device (not just by the host, in case it was * buffered on the device) and be accurate to about 10ms. * If the frame isn't buffered, just passing the return value of - * ktime_get_boot_ns() is likely appropriate. + * ktime_get_boottime_ns() is likely appropriate. * @parent_tsf: the time at the start of reception of the first octet of the * timestamp field of the frame. The time is the TSF of the BSS specified * by %parent_bssid. diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index 4790beaa86e0..ee7405e759ba 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -262,8 +262,8 @@ static inline bool ip6_sk_ignore_df(const struct sock *sk) inet6_sk(sk)->pmtudisc == IPV6_PMTUDISC_OMIT; } -static inline struct in6_addr *rt6_nexthop(struct rt6_info *rt, - struct in6_addr *daddr) +static inline const struct in6_addr *rt6_nexthop(const struct rt6_info *rt, + const struct in6_addr *daddr) { if (rt->rt6i_flags & RTF_GATEWAY) return &rt->rt6i_gateway; diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index 12689ddfc24c..a56bf7fc7c2b 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -71,6 +71,9 @@ struct net { */ struct llist_node cleanup_list; /* namespaces on death row */ +#ifdef CONFIG_KEYS + struct key_tag *key_domain; /* Key domain of operation tag */ +#endif struct user_namespace *user_ns; /* Owning user namespace */ struct ucounts *ucounts; spinlock_t nsid_lock; diff --git a/include/net/route.h b/include/net/route.h index 065b47754f05..55ff71ffb796 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -221,6 +221,7 @@ void ip_rt_get_source(u8 *src, struct sk_buff *skb, struct rtable *rt); struct rtable *rt_dst_alloc(struct net_device *dev, unsigned int flags, u16 type, bool nopolicy, bool noxfrm, bool will_cache); +struct rtable *rt_dst_clone(struct net_device *dev, struct rtable *rt); struct in_ifaddr; void fib_add_ifaddr(struct in_ifaddr *); diff --git a/include/net/tls.h b/include/net/tls.h index 4a55ce6a303f..53d96bca220d 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -373,21 +373,6 @@ static inline bool tls_is_partially_sent_record(struct tls_context *ctx) return !!ctx->partially_sent_record; } -static inline int tls_complete_pending_work(struct sock *sk, - struct tls_context *ctx, - int flags, long *timeo) -{ - int rc = 0; - - if (unlikely(sk->sk_write_pending)) - rc = wait_on_pending_writer(sk, timeo); - - if (!rc && tls_is_partially_sent_record(ctx)) - rc = tls_push_partial_record(sk, ctx, flags); - - return rc; -} - static inline bool tls_is_pending_open_record(struct tls_context *tls_ctx) { return tls_ctx->pending_open_record_frags; diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h index c8c7c7efb487..420e80e56e55 100644 --- a/include/trace/events/sched.h +++ b/include/trace/events/sched.h @@ -594,6 +594,37 @@ TRACE_EVENT(sched_wake_idle_without_ipi, TP_printk("cpu=%d", __entry->cpu) ); + +/* + * Following tracepoints are not exported in tracefs and provide hooking + * mechanisms only for testing and debugging purposes. + * + * Postfixed with _tp to make them easily identifiable in the code. + */ +DECLARE_TRACE(pelt_cfs_tp, + TP_PROTO(struct cfs_rq *cfs_rq), + TP_ARGS(cfs_rq)); + +DECLARE_TRACE(pelt_rt_tp, + TP_PROTO(struct rq *rq), + TP_ARGS(rq)); + +DECLARE_TRACE(pelt_dl_tp, + TP_PROTO(struct rq *rq), + TP_ARGS(rq)); + +DECLARE_TRACE(pelt_irq_tp, + TP_PROTO(struct rq *rq), + TP_ARGS(rq)); + +DECLARE_TRACE(pelt_se_tp, + TP_PROTO(struct sched_entity *se), + TP_ARGS(se)); + +DECLARE_TRACE(sched_overutilized_tp, + TP_PROTO(struct root_domain *rd, bool overutilized), + TP_ARGS(rd, overutilized)); + #endif /* _TRACE_SCHED_H */ /* This part must be outside protection */ diff --git a/include/uapi/linux/audit.h b/include/uapi/linux/audit.h index a1280af20336..c89c6495983d 100644 --- a/include/uapi/linux/audit.h +++ b/include/uapi/linux/audit.h @@ -281,6 +281,7 @@ #define AUDIT_OBJ_GID 110 #define AUDIT_FIELD_COMPARE 111 #define AUDIT_EXE 112 +#define AUDIT_SADDR_FAM 113 #define AUDIT_ARG0 200 #define AUDIT_ARG1 (AUDIT_ARG0+1) diff --git a/include/uapi/linux/keyctl.h b/include/uapi/linux/keyctl.h index f45ee0f69c0c..1f7a4e737214 100644 --- a/include/uapi/linux/keyctl.h +++ b/include/uapi/linux/keyctl.h @@ -15,6 +15,69 @@ #include <linux/types.h> +/* + * Keyring permission grant definitions + */ +enum key_ace_subject_type { + KEY_ACE_SUBJ_STANDARD = 0, /* subject is one of key_ace_standard_subject */ + nr__key_ace_subject_type +}; + +enum key_ace_standard_subject { + KEY_ACE_EVERYONE = 0, /* Everyone, including owner and group */ + KEY_ACE_GROUP = 1, /* The key's group */ + KEY_ACE_OWNER = 2, /* The owner of the key */ + KEY_ACE_POSSESSOR = 3, /* Any process that possesses of the key */ + nr__key_ace_standard_subject +}; + +#define KEY_ACE_VIEW 0x00000001 /* Can describe the key */ +#define KEY_ACE_READ 0x00000002 /* Can read the key content */ +#define KEY_ACE_WRITE 0x00000004 /* Can update/modify the key content */ +#define KEY_ACE_SEARCH 0x00000008 /* Can find the key by search */ +#define KEY_ACE_LINK 0x00000010 /* Can make a link to the key */ +#define KEY_ACE_SET_SECURITY 0x00000020 /* Can set owner, group, ACL */ +#define KEY_ACE_INVAL 0x00000040 /* Can invalidate the key */ +#define KEY_ACE_REVOKE 0x00000080 /* Can revoke the key */ +#define KEY_ACE_JOIN 0x00000100 /* Can join keyring */ +#define KEY_ACE_CLEAR 0x00000200 /* Can clear keyring */ +#define KEY_ACE__PERMS 0xffffffff + +/* + * Old-style permissions mask, deprecated in favour of ACL. + */ +#define KEY_POS_VIEW 0x01000000 /* possessor can view a key's attributes */ +#define KEY_POS_READ 0x02000000 /* possessor can read key payload / view keyring */ +#define KEY_POS_WRITE 0x04000000 /* possessor can update key payload / add link to keyring */ +#define KEY_POS_SEARCH 0x08000000 /* possessor can find a key in search / search a keyring */ +#define KEY_POS_LINK 0x10000000 /* possessor can create a link to a key/keyring */ +#define KEY_POS_SETATTR 0x20000000 /* possessor can set key attributes */ +#define KEY_POS_ALL 0x3f000000 + +#define KEY_USR_VIEW 0x00010000 /* user permissions... */ +#define KEY_USR_READ 0x00020000 +#define KEY_USR_WRITE 0x00040000 +#define KEY_USR_SEARCH 0x00080000 +#define KEY_USR_LINK 0x00100000 +#define KEY_USR_SETATTR 0x00200000 +#define KEY_USR_ALL 0x003f0000 + +#define KEY_GRP_VIEW 0x00000100 /* group permissions... */ +#define KEY_GRP_READ 0x00000200 +#define KEY_GRP_WRITE 0x00000400 +#define KEY_GRP_SEARCH 0x00000800 +#define KEY_GRP_LINK 0x00001000 +#define KEY_GRP_SETATTR 0x00002000 +#define KEY_GRP_ALL 0x00003f00 + +#define KEY_OTH_VIEW 0x00000001 /* third party permissions... */ +#define KEY_OTH_READ 0x00000002 +#define KEY_OTH_WRITE 0x00000004 +#define KEY_OTH_SEARCH 0x00000008 +#define KEY_OTH_LINK 0x00000010 +#define KEY_OTH_SETATTR 0x00000020 +#define KEY_OTH_ALL 0x0000003f + /* special process keyring shortcut IDs */ #define KEY_SPEC_THREAD_KEYRING -1 /* - key ID for thread-specific keyring */ #define KEY_SPEC_PROCESS_KEYRING -2 /* - key ID for process-specific keyring */ @@ -67,6 +130,9 @@ #define KEYCTL_PKEY_SIGN 27 /* Create a public key signature */ #define KEYCTL_PKEY_VERIFY 28 /* Verify a public key signature */ #define KEYCTL_RESTRICT_KEYRING 29 /* Restrict keys allowed to link to a keyring */ +#define KEYCTL_MOVE 30 /* Move keys between keyrings */ +#define KEYCTL_CAPABILITIES 31 /* Find capabilities of keyrings subsystem */ +#define KEYCTL_GRANT_PERMISSION 32 /* Grant a permit to a key */ /* keyctl structures */ struct keyctl_dh_params { @@ -112,4 +178,22 @@ struct keyctl_pkey_params { __u32 __spare[7]; }; +#define KEYCTL_MOVE_EXCL 0x00000001 /* Do not displace from the to-keyring */ + +/* + * Capabilities flags. The capabilities list is an array of 8-bit integers; + * each integer can carry up to 8 flags. + */ +#define KEYCTL_CAPS0_CAPABILITIES 0x01 /* KEYCTL_CAPABILITIES supported */ +#define KEYCTL_CAPS0_PERSISTENT_KEYRINGS 0x02 /* Persistent keyrings enabled */ +#define KEYCTL_CAPS0_DIFFIE_HELLMAN 0x04 /* Diffie-Hellman computation enabled */ +#define KEYCTL_CAPS0_PUBLIC_KEY 0x08 /* Public key ops enabled */ +#define KEYCTL_CAPS0_BIG_KEY 0x10 /* big_key-type enabled */ +#define KEYCTL_CAPS0_INVALIDATE 0x20 /* KEYCTL_INVALIDATE supported */ +#define KEYCTL_CAPS0_RESTRICT_KEYRING 0x40 /* KEYCTL_RESTRICT_KEYRING supported */ +#define KEYCTL_CAPS0_MOVE 0x80 /* KEYCTL_MOVE supported */ +#define KEYCTL_CAPS1_NS_KEYRING_NAME 0x01 /* Keyring names are per-user_namespace */ +#define KEYCTL_CAPS1_NS_KEY_TAG 0x02 /* Key indexing can include a namespace tag */ +#define KEYCTL_CAPS1_ACL_ALTERABLE 0x04 /* Keys have internal ACL that can be altered */ + #endif /* _LINUX_KEYCTL_H */ diff --git a/include/uapi/linux/sched.h b/include/uapi/linux/sched.h index ed4ee170bee2..617bb59aa8ba 100644 --- a/include/uapi/linux/sched.h +++ b/include/uapi/linux/sched.h @@ -51,9 +51,21 @@ #define SCHED_FLAG_RESET_ON_FORK 0x01 #define SCHED_FLAG_RECLAIM 0x02 #define SCHED_FLAG_DL_OVERRUN 0x04 +#define SCHED_FLAG_KEEP_POLICY 0x08 +#define SCHED_FLAG_KEEP_PARAMS 0x10 +#define SCHED_FLAG_UTIL_CLAMP_MIN 0x20 +#define SCHED_FLAG_UTIL_CLAMP_MAX 0x40 + +#define SCHED_FLAG_KEEP_ALL (SCHED_FLAG_KEEP_POLICY | \ + SCHED_FLAG_KEEP_PARAMS) + +#define SCHED_FLAG_UTIL_CLAMP (SCHED_FLAG_UTIL_CLAMP_MIN | \ + SCHED_FLAG_UTIL_CLAMP_MAX) #define SCHED_FLAG_ALL (SCHED_FLAG_RESET_ON_FORK | \ SCHED_FLAG_RECLAIM | \ - SCHED_FLAG_DL_OVERRUN) + SCHED_FLAG_DL_OVERRUN | \ + SCHED_FLAG_KEEP_ALL | \ + SCHED_FLAG_UTIL_CLAMP) #endif /* _UAPI_LINUX_SCHED_H */ diff --git a/include/uapi/linux/sched/types.h b/include/uapi/linux/sched/types.h index 10fbb8031930..c852153ddb0d 100644 --- a/include/uapi/linux/sched/types.h +++ b/include/uapi/linux/sched/types.h @@ -9,6 +9,7 @@ struct sched_param { }; #define SCHED_ATTR_SIZE_VER0 48 /* sizeof first published struct */ +#define SCHED_ATTR_SIZE_VER1 56 /* add: util_{min,max} */ /* * Extended scheduling parameters data structure. @@ -21,8 +22,33 @@ struct sched_param { * the tasks may be useful for a wide variety of application fields, e.g., * multimedia, streaming, automation and control, and many others. * - * This variant (sched_attr) is meant at describing a so-called - * sporadic time-constrained task. In such model a task is specified by: + * This variant (sched_attr) allows to define additional attributes to + * improve the scheduler knowledge about task requirements. + * + * Scheduling Class Attributes + * =========================== + * + * A subset of sched_attr attributes specifies the + * scheduling policy and relative POSIX attributes: + * + * @size size of the structure, for fwd/bwd compat. + * + * @sched_policy task's scheduling policy + * @sched_nice task's nice value (SCHED_NORMAL/BATCH) + * @sched_priority task's static priority (SCHED_FIFO/RR) + * + * Certain more advanced scheduling features can be controlled by a + * predefined set of flags via the attribute: + * + * @sched_flags for customizing the scheduler behaviour + * + * Sporadic Time-Constrained Task Attributes + * ========================================= + * + * A subset of sched_attr attributes allows to describe a so-called + * sporadic time-constrained task. + * + * In such a model a task is specified by: * - the activation period or minimum instance inter-arrival time; * - the maximum (or average, depending on the actual scheduling * discipline) computation time of all instances, a.k.a. runtime; @@ -34,14 +60,8 @@ struct sched_param { * than the runtime and must be completed by time instant t equal to * the instance activation time + the deadline. * - * This is reflected by the actual fields of the sched_attr structure: + * This is reflected by the following fields of the sched_attr structure: * - * @size size of the structure, for fwd/bwd compat. - * - * @sched_policy task's scheduling policy - * @sched_flags for customizing the scheduler behaviour - * @sched_nice task's nice value (SCHED_NORMAL/BATCH) - * @sched_priority task's static priority (SCHED_FIFO/RR) * @sched_deadline representative of the task's deadline * @sched_runtime representative of the task's runtime * @sched_period representative of the task's period @@ -53,6 +73,29 @@ struct sched_param { * As of now, the SCHED_DEADLINE policy (sched_dl scheduling class) is the * only user of this new interface. More information about the algorithm * available in the scheduling class file or in Documentation/. + * + * Task Utilization Attributes + * =========================== + * + * A subset of sched_attr attributes allows to specify the utilization + * expected for a task. These attributes allow to inform the scheduler about + * the utilization boundaries within which it should schedule the task. These + * boundaries are valuable hints to support scheduler decisions on both task + * placement and frequency selection. + * + * @sched_util_min represents the minimum utilization + * @sched_util_max represents the maximum utilization + * + * Utilization is a value in the range [0..SCHED_CAPACITY_SCALE]. It + * represents the percentage of CPU time used by a task when running at the + * maximum frequency on the highest capacity CPU of the system. For example, a + * 20% utilization task is a task running for 2ms every 10ms at maximum + * frequency. + * + * A task with a min utilization value bigger than 0 is more likely scheduled + * on a CPU with a capacity big enough to fit the specified value. + * A task with a max utilization value smaller than 1024 is more likely + * scheduled on a CPU with no more capacity than the specified value. */ struct sched_attr { __u32 size; @@ -70,6 +113,11 @@ struct sched_attr { __u64 sched_runtime; __u64 sched_deadline; __u64 sched_period; + + /* Utilization hints */ + __u32 sched_util_min; + __u32 sched_util_max; + }; #endif /* _UAPI_LINUX_SCHED_TYPES_H */ diff --git a/include/vdso/datapage.h b/include/vdso/datapage.h new file mode 100644 index 000000000000..2e302c0f41f7 --- /dev/null +++ b/include/vdso/datapage.h @@ -0,0 +1,89 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __VDSO_DATAPAGE_H +#define __VDSO_DATAPAGE_H + +#ifndef __ASSEMBLY__ + +#include <linux/bits.h> +#include <linux/time.h> +#include <linux/types.h> + +#define VDSO_BASES (CLOCK_TAI + 1) +#define VDSO_HRES (BIT(CLOCK_REALTIME) | \ + BIT(CLOCK_MONOTONIC) | \ + BIT(CLOCK_BOOTTIME) | \ + BIT(CLOCK_TAI)) +#define VDSO_COARSE (BIT(CLOCK_REALTIME_COARSE) | \ + BIT(CLOCK_MONOTONIC_COARSE)) +#define VDSO_RAW (BIT(CLOCK_MONOTONIC_RAW)) + +#define CS_HRES_COARSE 0 +#define CS_RAW 1 +#define CS_BASES (CS_RAW + 1) + +/** + * struct vdso_timestamp - basetime per clock_id + * @sec: seconds + * @nsec: nanoseconds + * + * There is one vdso_timestamp object in vvar for each vDSO-accelerated + * clock_id. For high-resolution clocks, this encodes the time + * corresponding to vdso_data.cycle_last. For coarse clocks this encodes + * the actual time. + * + * To be noticed that for highres clocks nsec is left-shifted by + * vdso_data.cs[x].shift. + */ +struct vdso_timestamp { + u64 sec; + u64 nsec; +}; + +/** + * struct vdso_data - vdso datapage representation + * @seq: timebase sequence counter + * @clock_mode: clock mode + * @cycle_last: timebase at clocksource init + * @mask: clocksource mask + * @mult: clocksource multiplier + * @shift: clocksource shift + * @basetime[clock_id]: basetime per clock_id + * @tz_minuteswest: minutes west of Greenwich + * @tz_dsttime: type of DST correction + * @hrtimer_res: hrtimer resolution + * @__unused: unused + * + * vdso_data will be accessed by 64 bit and compat code at the same time + * so we should be careful before modifying this structure. + */ +struct vdso_data { + u32 seq; + + s32 clock_mode; + u64 cycle_last; + u64 mask; + u32 mult; + u32 shift; + + struct vdso_timestamp basetime[VDSO_BASES]; + + s32 tz_minuteswest; + s32 tz_dsttime; + u32 hrtimer_res; + u32 __unused; +}; + +/* + * We use the hidden visibility to prevent the compiler from generating a GOT + * relocation. Not only is going through a GOT useless (the entry couldn't and + * must not be overridden by another library), it does not even work: the linker + * cannot generate an absolute address to the data page. + * + * With the hidden visibility, the compiler simply generates a PC-relative + * relocation, and this is what we need. + */ +extern struct vdso_data _vdso_data[CS_BASES] __attribute__((visibility("hidden"))); + +#endif /* !__ASSEMBLY__ */ + +#endif /* __VDSO_DATAPAGE_H */ diff --git a/include/vdso/helpers.h b/include/vdso/helpers.h new file mode 100644 index 000000000000..01641dbb68ef --- /dev/null +++ b/include/vdso/helpers.h @@ -0,0 +1,56 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __VDSO_HELPERS_H +#define __VDSO_HELPERS_H + +#ifndef __ASSEMBLY__ + +#include <vdso/datapage.h> + +static __always_inline u32 vdso_read_begin(const struct vdso_data *vd) +{ + u32 seq; + + while ((seq = READ_ONCE(vd->seq)) & 1) + cpu_relax(); + + smp_rmb(); + return seq; +} + +static __always_inline u32 vdso_read_retry(const struct vdso_data *vd, + u32 start) +{ + u32 seq; + + smp_rmb(); + seq = READ_ONCE(vd->seq); + return seq != start; +} + +static __always_inline void vdso_write_begin(struct vdso_data *vd) +{ + /* + * WRITE_ONCE it is required otherwise the compiler can validly tear + * updates to vd[x].seq and it is possible that the value seen by the + * reader it is inconsistent. + */ + WRITE_ONCE(vd[CS_HRES_COARSE].seq, vd[CS_HRES_COARSE].seq + 1); + WRITE_ONCE(vd[CS_RAW].seq, vd[CS_RAW].seq + 1); + smp_wmb(); +} + +static __always_inline void vdso_write_end(struct vdso_data *vd) +{ + smp_wmb(); + /* + * WRITE_ONCE it is required otherwise the compiler can validly tear + * updates to vd[x].seq and it is possible that the value seen by the + * reader it is inconsistent. + */ + WRITE_ONCE(vd[CS_HRES_COARSE].seq, vd[CS_HRES_COARSE].seq + 1); + WRITE_ONCE(vd[CS_RAW].seq, vd[CS_RAW].seq + 1); +} + +#endif /* !__ASSEMBLY__ */ + +#endif /* __VDSO_HELPERS_H */ diff --git a/include/vdso/vsyscall.h b/include/vdso/vsyscall.h new file mode 100644 index 000000000000..2c6134e0c23d --- /dev/null +++ b/include/vdso/vsyscall.h @@ -0,0 +1,11 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __VDSO_VSYSCALL_H +#define __VDSO_VSYSCALL_H + +#ifndef __ASSEMBLY__ + +#include <asm/vdso/vsyscall.h> + +#endif /* !__ASSEMBLY__ */ + +#endif /* __VDSO_VSYSCALL_H */ |
