diff options
Diffstat (limited to 'include/linux')
176 files changed, 3385 insertions, 892 deletions
diff --git a/include/linux/acpi.h b/include/linux/acpi.h index a73246c3c35e..db3a33e19c97 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -787,6 +787,11 @@ static inline bool acpi_dev_present(const char *hid, const char *uid, s64 hrv) struct acpi_device; +static inline bool acpi_dev_uid_match(struct acpi_device *adev, const char *uid2) +{ + return false; +} + static inline bool acpi_dev_hid_uid_match(struct acpi_device *adev, const char *hid2, const char *uid2) { @@ -1480,6 +1485,15 @@ static inline int lpit_read_residency_count_address(u64 *address) } #endif +#ifdef CONFIG_ACPI_PROCESSOR_IDLE +#ifndef arch_get_idle_state_flags +static inline unsigned int arch_get_idle_state_flags(u32 arch_flags) +{ + return 0; +} +#endif +#endif /* CONFIG_ACPI_PROCESSOR_IDLE */ + #ifdef CONFIG_ACPI_PPTT int acpi_pptt_cpu_is_thread(unsigned int cpu); int find_acpi_cpu_topology(unsigned int cpu, int level); diff --git a/include/linux/aer.h b/include/linux/aer.h index 2dd175f5debd..29cc10220952 100644 --- a/include/linux/aer.h +++ b/include/linux/aer.h @@ -42,11 +42,13 @@ struct aer_capability_regs { #if defined(CONFIG_PCIEAER) int pci_aer_clear_nonfatal_status(struct pci_dev *dev); +int pcie_aer_is_native(struct pci_dev *dev); #else static inline int pci_aer_clear_nonfatal_status(struct pci_dev *dev) { return -EINVAL; } +static inline int pcie_aer_is_native(struct pci_dev *dev) { return 0; } #endif void cper_print_aer(struct pci_dev *dev, int aer_severity, diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h index 7c67c17321d4..083f85653716 100644 --- a/include/linux/arm-smccc.h +++ b/include/linux/arm-smccc.h @@ -67,6 +67,8 @@ #define ARM_SMCCC_VERSION_1_3 0x10003 #define ARM_SMCCC_1_3_SVE_HINT 0x10000 +#define ARM_SMCCC_CALL_HINTS ARM_SMCCC_1_3_SVE_HINT + #define ARM_SMCCC_VERSION_FUNC_ID \ ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ diff --git a/include/linux/atomic/atomic-arch-fallback.h b/include/linux/atomic/atomic-arch-fallback.h index 18f5744dfb5d..5e95faa959c4 100644 --- a/include/linux/atomic/atomic-arch-fallback.h +++ b/include/linux/atomic/atomic-arch-fallback.h @@ -428,6 +428,19 @@ extern void raw_cmpxchg128_relaxed_not_implemented(void); #define raw_sync_cmpxchg arch_sync_cmpxchg +#ifdef arch_sync_try_cmpxchg +#define raw_sync_try_cmpxchg arch_sync_try_cmpxchg +#else +#define raw_sync_try_cmpxchg(_ptr, _oldp, _new) \ +({ \ + typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \ + ___r = raw_sync_cmpxchg((_ptr), ___o, (_new)); \ + if (unlikely(___r != ___o)) \ + *___op = ___r; \ + likely(___r == ___o); \ +}) +#endif + /** * raw_atomic_read() - atomic load with relaxed ordering * @v: pointer to atomic_t @@ -459,8 +472,6 @@ raw_atomic_read_acquire(const atomic_t *v) { #if defined(arch_atomic_read_acquire) return arch_atomic_read_acquire(v); -#elif defined(arch_atomic_read) - return arch_atomic_read(v); #else int ret; @@ -508,8 +519,6 @@ raw_atomic_set_release(atomic_t *v, int i) { #if defined(arch_atomic_set_release) arch_atomic_set_release(v, i); -#elif defined(arch_atomic_set) - arch_atomic_set(v, i); #else if (__native_word(atomic_t)) { smp_store_release(&(v)->counter, i); @@ -2575,8 +2584,6 @@ raw_atomic64_read_acquire(const atomic64_t *v) { #if defined(arch_atomic64_read_acquire) return arch_atomic64_read_acquire(v); -#elif defined(arch_atomic64_read) - return arch_atomic64_read(v); #else s64 ret; @@ -2624,8 +2631,6 @@ raw_atomic64_set_release(atomic64_t *v, s64 i) { #if defined(arch_atomic64_set_release) arch_atomic64_set_release(v, i); -#elif defined(arch_atomic64_set) - arch_atomic64_set(v, i); #else if (__native_word(atomic64_t)) { smp_store_release(&(v)->counter, i); @@ -4657,4 +4662,4 @@ raw_atomic64_dec_if_positive(atomic64_t *v) } #endif /* _LINUX_ATOMIC_FALLBACK_H */ -// 202b45c7db600ce36198eb1f1fc2c2d5268ace2d +// eec048affea735b8464f58e6d96992101f8f85f1 diff --git a/include/linux/atomic/atomic-instrumented.h b/include/linux/atomic/atomic-instrumented.h index d401b406ef7c..54d7bbe0aeaa 100644 --- a/include/linux/atomic/atomic-instrumented.h +++ b/include/linux/atomic/atomic-instrumented.h @@ -4998,6 +4998,14 @@ atomic_long_dec_if_positive(atomic_long_t *v) raw_try_cmpxchg128_local(__ai_ptr, __ai_oldp, __VA_ARGS__); \ }) +#define sync_try_cmpxchg(ptr, ...) \ +({ \ + typeof(ptr) __ai_ptr = (ptr); \ + kcsan_mb(); \ + instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ + raw_sync_try_cmpxchg(__ai_ptr, __VA_ARGS__); \ +}) + #endif /* _LINUX_ATOMIC_INSTRUMENTED_H */ -// 1568f875fef72097413caab8339120c065a39aa4 +// 2cc4bc990fef44d3836ec108f11b610f3f438184 diff --git a/include/linux/avf/virtchnl.h b/include/linux/avf/virtchnl.h index d0807ad43f93..6b3acf15be5c 100644 --- a/include/linux/avf/virtchnl.h +++ b/include/linux/avf/virtchnl.h @@ -4,6 +4,10 @@ #ifndef _VIRTCHNL_H_ #define _VIRTCHNL_H_ +#include <linux/bitops.h> +#include <linux/overflow.h> +#include <uapi/linux/if_ether.h> + /* Description: * This header file describes the Virtual Function (VF) - Physical Function * (PF) communication protocol used by the drivers for all devices starting @@ -240,6 +244,7 @@ VIRTCHNL_CHECK_STRUCT_LEN(16, virtchnl_vsi_resource); #define VIRTCHNL_VF_OFFLOAD_REQ_QUEUES BIT(6) /* used to negotiate communicating link speeds in Mbps */ #define VIRTCHNL_VF_CAP_ADV_LINK_SPEED BIT(7) +#define VIRTCHNL_VF_OFFLOAD_CRC BIT(10) #define VIRTCHNL_VF_OFFLOAD_VLAN_V2 BIT(15) #define VIRTCHNL_VF_OFFLOAD_VLAN BIT(16) #define VIRTCHNL_VF_OFFLOAD_RX_POLLING BIT(17) @@ -295,7 +300,13 @@ VIRTCHNL_CHECK_STRUCT_LEN(24, virtchnl_txq_info); /* VIRTCHNL_OP_CONFIG_RX_QUEUE * VF sends this message to set up parameters for one RX queue. * External data buffer contains one instance of virtchnl_rxq_info. - * PF configures requested queue and returns a status code. + * PF configures requested queue and returns a status code. The + * crc_disable flag disables CRC stripping on the VF. Setting + * the crc_disable flag to 1 will disable CRC stripping for each + * queue in the VF where the flag is set. The VIRTCHNL_VF_OFFLOAD_CRC + * offload must have been set prior to sending this info or the PF + * will ignore the request. This flag should be set the same for + * all of the queues for a VF. */ /* Rx queue config info */ @@ -307,7 +318,7 @@ struct virtchnl_rxq_info { u16 splithdr_enabled; /* deprecated with AVF 1.0 */ u32 databuffer_size; u32 max_pkt_size; - u8 pad0; + u8 crc_disable; u8 rxdid; u8 pad1[2]; u64 dma_ring_addr; diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h index 8d51f69f9f5e..70f97f685bff 100644 --- a/include/linux/binfmts.h +++ b/include/linux/binfmts.h @@ -90,6 +90,16 @@ struct linux_binfmt { #endif } __randomize_layout; +#if IS_ENABLED(CONFIG_BINFMT_MISC) +struct binfmt_misc { + struct list_head entries; + rwlock_t entries_lock; + bool enabled; +} __randomize_layout; + +extern struct binfmt_misc init_binfmt_misc; +#endif + extern void __register_binfmt(struct linux_binfmt *fmt, int insert); /* Registration of default binfmt handlers */ diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index eef450f25982..51fa7ffdee83 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1479,14 +1479,25 @@ extern const struct blk_holder_ops fs_holder_ops; #define sb_open_mode(flags) \ (BLK_OPEN_READ | (((flags) & SB_RDONLY) ? 0 : BLK_OPEN_WRITE)) +struct bdev_handle { + struct block_device *bdev; + void *holder; + blk_mode_t mode; +}; + struct block_device *blkdev_get_by_dev(dev_t dev, blk_mode_t mode, void *holder, const struct blk_holder_ops *hops); struct block_device *blkdev_get_by_path(const char *path, blk_mode_t mode, void *holder, const struct blk_holder_ops *hops); +struct bdev_handle *bdev_open_by_dev(dev_t dev, blk_mode_t mode, void *holder, + const struct blk_holder_ops *hops); +struct bdev_handle *bdev_open_by_path(const char *path, blk_mode_t mode, + void *holder, const struct blk_holder_ops *hops); int bd_prepare_to_claim(struct block_device *bdev, void *holder, const struct blk_holder_ops *hops); void bd_abort_claiming(struct block_device *bdev, void *holder); void blkdev_put(struct block_device *bdev, void *holder); +void bdev_release(struct bdev_handle *handle); /* just for blk-cgroup, don't use elsewhere */ struct block_device *blkdev_get_no_open(dev_t dev); diff --git a/include/linux/bpf-cgroup-defs.h b/include/linux/bpf-cgroup-defs.h index 7b121bd780eb..0985221d5478 100644 --- a/include/linux/bpf-cgroup-defs.h +++ b/include/linux/bpf-cgroup-defs.h @@ -28,19 +28,24 @@ enum cgroup_bpf_attach_type { CGROUP_INET6_BIND, CGROUP_INET4_CONNECT, CGROUP_INET6_CONNECT, + CGROUP_UNIX_CONNECT, CGROUP_INET4_POST_BIND, CGROUP_INET6_POST_BIND, CGROUP_UDP4_SENDMSG, CGROUP_UDP6_SENDMSG, + CGROUP_UNIX_SENDMSG, CGROUP_SYSCTL, CGROUP_UDP4_RECVMSG, CGROUP_UDP6_RECVMSG, + CGROUP_UNIX_RECVMSG, CGROUP_GETSOCKOPT, CGROUP_SETSOCKOPT, CGROUP_INET4_GETPEERNAME, CGROUP_INET6_GETPEERNAME, + CGROUP_UNIX_GETPEERNAME, CGROUP_INET4_GETSOCKNAME, CGROUP_INET6_GETSOCKNAME, + CGROUP_UNIX_GETSOCKNAME, CGROUP_INET_SOCK_RELEASE, CGROUP_LSM_START, CGROUP_LSM_END = CGROUP_LSM_START + CGROUP_LSM_NUM - 1, diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index 8506690dbb9c..98b8cea904fe 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -48,19 +48,24 @@ to_cgroup_bpf_attach_type(enum bpf_attach_type attach_type) CGROUP_ATYPE(CGROUP_INET6_BIND); CGROUP_ATYPE(CGROUP_INET4_CONNECT); CGROUP_ATYPE(CGROUP_INET6_CONNECT); + CGROUP_ATYPE(CGROUP_UNIX_CONNECT); CGROUP_ATYPE(CGROUP_INET4_POST_BIND); CGROUP_ATYPE(CGROUP_INET6_POST_BIND); CGROUP_ATYPE(CGROUP_UDP4_SENDMSG); CGROUP_ATYPE(CGROUP_UDP6_SENDMSG); + CGROUP_ATYPE(CGROUP_UNIX_SENDMSG); CGROUP_ATYPE(CGROUP_SYSCTL); CGROUP_ATYPE(CGROUP_UDP4_RECVMSG); CGROUP_ATYPE(CGROUP_UDP6_RECVMSG); + CGROUP_ATYPE(CGROUP_UNIX_RECVMSG); CGROUP_ATYPE(CGROUP_GETSOCKOPT); CGROUP_ATYPE(CGROUP_SETSOCKOPT); CGROUP_ATYPE(CGROUP_INET4_GETPEERNAME); CGROUP_ATYPE(CGROUP_INET6_GETPEERNAME); + CGROUP_ATYPE(CGROUP_UNIX_GETPEERNAME); CGROUP_ATYPE(CGROUP_INET4_GETSOCKNAME); CGROUP_ATYPE(CGROUP_INET6_GETSOCKNAME); + CGROUP_ATYPE(CGROUP_UNIX_GETSOCKNAME); CGROUP_ATYPE(CGROUP_INET_SOCK_RELEASE); default: return CGROUP_BPF_ATTACH_TYPE_INVALID; @@ -120,6 +125,7 @@ int __cgroup_bpf_run_filter_sk(struct sock *sk, int __cgroup_bpf_run_filter_sock_addr(struct sock *sk, struct sockaddr *uaddr, + int *uaddrlen, enum cgroup_bpf_attach_type atype, void *t_ctx, u32 *flags); @@ -230,22 +236,22 @@ static inline bool cgroup_bpf_sock_enabled(struct sock *sk, #define BPF_CGROUP_RUN_PROG_INET6_POST_BIND(sk) \ BPF_CGROUP_RUN_SK_PROG(sk, CGROUP_INET6_POST_BIND) -#define BPF_CGROUP_RUN_SA_PROG(sk, uaddr, atype) \ +#define BPF_CGROUP_RUN_SA_PROG(sk, uaddr, uaddrlen, atype) \ ({ \ int __ret = 0; \ if (cgroup_bpf_enabled(atype)) \ - __ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, atype, \ - NULL, NULL); \ + __ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, uaddrlen, \ + atype, NULL, NULL); \ __ret; \ }) -#define BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, atype, t_ctx) \ +#define BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, atype, t_ctx) \ ({ \ int __ret = 0; \ if (cgroup_bpf_enabled(atype)) { \ lock_sock(sk); \ - __ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, atype, \ - t_ctx, NULL); \ + __ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, uaddrlen, \ + atype, t_ctx, NULL); \ release_sock(sk); \ } \ __ret; \ @@ -256,14 +262,14 @@ static inline bool cgroup_bpf_sock_enabled(struct sock *sk, * (at bit position 0) is to indicate CAP_NET_BIND_SERVICE capability check * should be bypassed (BPF_RET_BIND_NO_CAP_NET_BIND_SERVICE). */ -#define BPF_CGROUP_RUN_PROG_INET_BIND_LOCK(sk, uaddr, atype, bind_flags) \ +#define BPF_CGROUP_RUN_PROG_INET_BIND_LOCK(sk, uaddr, uaddrlen, atype, bind_flags) \ ({ \ u32 __flags = 0; \ int __ret = 0; \ if (cgroup_bpf_enabled(atype)) { \ lock_sock(sk); \ - __ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, atype, \ - NULL, &__flags); \ + __ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, uaddrlen, \ + atype, NULL, &__flags); \ release_sock(sk); \ if (__flags & BPF_RET_BIND_NO_CAP_NET_BIND_SERVICE) \ *bind_flags |= BIND_NO_CAP_NET_BIND_SERVICE; \ @@ -276,29 +282,38 @@ static inline bool cgroup_bpf_sock_enabled(struct sock *sk, cgroup_bpf_enabled(CGROUP_INET6_CONNECT)) && \ (sk)->sk_prot->pre_connect) -#define BPF_CGROUP_RUN_PROG_INET4_CONNECT(sk, uaddr) \ - BPF_CGROUP_RUN_SA_PROG(sk, uaddr, CGROUP_INET4_CONNECT) +#define BPF_CGROUP_RUN_PROG_INET4_CONNECT(sk, uaddr, uaddrlen) \ + BPF_CGROUP_RUN_SA_PROG(sk, uaddr, uaddrlen, CGROUP_INET4_CONNECT) -#define BPF_CGROUP_RUN_PROG_INET6_CONNECT(sk, uaddr) \ - BPF_CGROUP_RUN_SA_PROG(sk, uaddr, CGROUP_INET6_CONNECT) +#define BPF_CGROUP_RUN_PROG_INET6_CONNECT(sk, uaddr, uaddrlen) \ + BPF_CGROUP_RUN_SA_PROG(sk, uaddr, uaddrlen, CGROUP_INET6_CONNECT) -#define BPF_CGROUP_RUN_PROG_INET4_CONNECT_LOCK(sk, uaddr) \ - BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, CGROUP_INET4_CONNECT, NULL) +#define BPF_CGROUP_RUN_PROG_INET4_CONNECT_LOCK(sk, uaddr, uaddrlen) \ + BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_INET4_CONNECT, NULL) -#define BPF_CGROUP_RUN_PROG_INET6_CONNECT_LOCK(sk, uaddr) \ - BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, CGROUP_INET6_CONNECT, NULL) +#define BPF_CGROUP_RUN_PROG_INET6_CONNECT_LOCK(sk, uaddr, uaddrlen) \ + BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_INET6_CONNECT, NULL) -#define BPF_CGROUP_RUN_PROG_UDP4_SENDMSG_LOCK(sk, uaddr, t_ctx) \ - BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, CGROUP_UDP4_SENDMSG, t_ctx) +#define BPF_CGROUP_RUN_PROG_UNIX_CONNECT_LOCK(sk, uaddr, uaddrlen) \ + BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_UNIX_CONNECT, NULL) -#define BPF_CGROUP_RUN_PROG_UDP6_SENDMSG_LOCK(sk, uaddr, t_ctx) \ - BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, CGROUP_UDP6_SENDMSG, t_ctx) +#define BPF_CGROUP_RUN_PROG_UDP4_SENDMSG_LOCK(sk, uaddr, uaddrlen, t_ctx) \ + BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_UDP4_SENDMSG, t_ctx) -#define BPF_CGROUP_RUN_PROG_UDP4_RECVMSG_LOCK(sk, uaddr) \ - BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, CGROUP_UDP4_RECVMSG, NULL) +#define BPF_CGROUP_RUN_PROG_UDP6_SENDMSG_LOCK(sk, uaddr, uaddrlen, t_ctx) \ + BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_UDP6_SENDMSG, t_ctx) -#define BPF_CGROUP_RUN_PROG_UDP6_RECVMSG_LOCK(sk, uaddr) \ - BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, CGROUP_UDP6_RECVMSG, NULL) +#define BPF_CGROUP_RUN_PROG_UNIX_SENDMSG_LOCK(sk, uaddr, uaddrlen, t_ctx) \ + BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_UNIX_SENDMSG, t_ctx) + +#define BPF_CGROUP_RUN_PROG_UDP4_RECVMSG_LOCK(sk, uaddr, uaddrlen) \ + BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_UDP4_RECVMSG, NULL) + +#define BPF_CGROUP_RUN_PROG_UDP6_RECVMSG_LOCK(sk, uaddr, uaddrlen) \ + BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_UDP6_RECVMSG, NULL) + +#define BPF_CGROUP_RUN_PROG_UNIX_RECVMSG_LOCK(sk, uaddr, uaddrlen) \ + BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_UNIX_RECVMSG, NULL) /* The SOCK_OPS"_SK" macro should be used when sock_ops->sk is not a * fullsock and its parent fullsock cannot be traced by @@ -477,24 +492,27 @@ static inline int bpf_percpu_cgroup_storage_update(struct bpf_map *map, } #define cgroup_bpf_enabled(atype) (0) -#define BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, atype, t_ctx) ({ 0; }) -#define BPF_CGROUP_RUN_SA_PROG(sk, uaddr, atype) ({ 0; }) +#define BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, atype, t_ctx) ({ 0; }) +#define BPF_CGROUP_RUN_SA_PROG(sk, uaddr, uaddrlen, atype) ({ 0; }) #define BPF_CGROUP_PRE_CONNECT_ENABLED(sk) (0) #define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk,skb) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET_EGRESS(sk,skb) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET_SOCK(sk) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET_SOCK_RELEASE(sk) ({ 0; }) -#define BPF_CGROUP_RUN_PROG_INET_BIND_LOCK(sk, uaddr, atype, flags) ({ 0; }) +#define BPF_CGROUP_RUN_PROG_INET_BIND_LOCK(sk, uaddr, uaddrlen, atype, flags) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET4_POST_BIND(sk) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET6_POST_BIND(sk) ({ 0; }) -#define BPF_CGROUP_RUN_PROG_INET4_CONNECT(sk, uaddr) ({ 0; }) -#define BPF_CGROUP_RUN_PROG_INET4_CONNECT_LOCK(sk, uaddr) ({ 0; }) -#define BPF_CGROUP_RUN_PROG_INET6_CONNECT(sk, uaddr) ({ 0; }) -#define BPF_CGROUP_RUN_PROG_INET6_CONNECT_LOCK(sk, uaddr) ({ 0; }) -#define BPF_CGROUP_RUN_PROG_UDP4_SENDMSG_LOCK(sk, uaddr, t_ctx) ({ 0; }) -#define BPF_CGROUP_RUN_PROG_UDP6_SENDMSG_LOCK(sk, uaddr, t_ctx) ({ 0; }) -#define BPF_CGROUP_RUN_PROG_UDP4_RECVMSG_LOCK(sk, uaddr) ({ 0; }) -#define BPF_CGROUP_RUN_PROG_UDP6_RECVMSG_LOCK(sk, uaddr) ({ 0; }) +#define BPF_CGROUP_RUN_PROG_INET4_CONNECT(sk, uaddr, uaddrlen) ({ 0; }) +#define BPF_CGROUP_RUN_PROG_INET4_CONNECT_LOCK(sk, uaddr, uaddrlen) ({ 0; }) +#define BPF_CGROUP_RUN_PROG_INET6_CONNECT(sk, uaddr, uaddrlen) ({ 0; }) +#define BPF_CGROUP_RUN_PROG_INET6_CONNECT_LOCK(sk, uaddr, uaddrlen) ({ 0; }) +#define BPF_CGROUP_RUN_PROG_UNIX_CONNECT_LOCK(sk, uaddr, uaddrlen) ({ 0; }) +#define BPF_CGROUP_RUN_PROG_UDP4_SENDMSG_LOCK(sk, uaddr, uaddrlen, t_ctx) ({ 0; }) +#define BPF_CGROUP_RUN_PROG_UDP6_SENDMSG_LOCK(sk, uaddr, uaddrlen, t_ctx) ({ 0; }) +#define BPF_CGROUP_RUN_PROG_UNIX_SENDMSG_LOCK(sk, uaddr, uaddrlen, t_ctx) ({ 0; }) +#define BPF_CGROUP_RUN_PROG_UDP4_RECVMSG_LOCK(sk, uaddr, uaddrlen) ({ 0; }) +#define BPF_CGROUP_RUN_PROG_UDP6_RECVMSG_LOCK(sk, uaddr, uaddrlen) ({ 0; }) +#define BPF_CGROUP_RUN_PROG_UNIX_RECVMSG_LOCK(sk, uaddr, uaddrlen) ({ 0; }) #define BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops) ({ 0; }) #define BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(atype, major, minor, access) ({ 0; }) #define BPF_CGROUP_RUN_PROG_SYSCTL(head,table,write,buf,count,pos) ({ 0; }) diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 024e8b28c34b..b4825d3cdb29 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -55,8 +55,8 @@ struct cgroup; extern struct idr btf_idr; extern spinlock_t btf_idr_lock; extern struct kobject *btf_kobj; -extern struct bpf_mem_alloc bpf_global_ma; -extern bool bpf_global_ma_set; +extern struct bpf_mem_alloc bpf_global_ma, bpf_global_percpu_ma; +extern bool bpf_global_ma_set, bpf_global_percpu_ma_set; typedef u64 (*bpf_callback_t)(u64, u64, u64, u64, u64); typedef int (*bpf_iter_init_seq_priv_t)(void *private_data, @@ -180,14 +180,15 @@ enum btf_field_type { BPF_TIMER = (1 << 1), BPF_KPTR_UNREF = (1 << 2), BPF_KPTR_REF = (1 << 3), - BPF_KPTR = BPF_KPTR_UNREF | BPF_KPTR_REF, - BPF_LIST_HEAD = (1 << 4), - BPF_LIST_NODE = (1 << 5), - BPF_RB_ROOT = (1 << 6), - BPF_RB_NODE = (1 << 7), + BPF_KPTR_PERCPU = (1 << 4), + BPF_KPTR = BPF_KPTR_UNREF | BPF_KPTR_REF | BPF_KPTR_PERCPU, + BPF_LIST_HEAD = (1 << 5), + BPF_LIST_NODE = (1 << 6), + BPF_RB_ROOT = (1 << 7), + BPF_RB_NODE = (1 << 8), BPF_GRAPH_NODE_OR_ROOT = BPF_LIST_NODE | BPF_LIST_HEAD | BPF_RB_NODE | BPF_RB_ROOT, - BPF_REFCOUNT = (1 << 8), + BPF_REFCOUNT = (1 << 9), }; typedef void (*btf_dtor_kfunc_t)(void *); @@ -300,6 +301,8 @@ static inline const char *btf_field_type_name(enum btf_field_type type) case BPF_KPTR_UNREF: case BPF_KPTR_REF: return "kptr"; + case BPF_KPTR_PERCPU: + return "percpu_kptr"; case BPF_LIST_HEAD: return "bpf_list_head"; case BPF_LIST_NODE: @@ -325,6 +328,7 @@ static inline u32 btf_field_type_size(enum btf_field_type type) return sizeof(struct bpf_timer); case BPF_KPTR_UNREF: case BPF_KPTR_REF: + case BPF_KPTR_PERCPU: return sizeof(u64); case BPF_LIST_HEAD: return sizeof(struct bpf_list_head); @@ -351,6 +355,7 @@ static inline u32 btf_field_type_align(enum btf_field_type type) return __alignof__(struct bpf_timer); case BPF_KPTR_UNREF: case BPF_KPTR_REF: + case BPF_KPTR_PERCPU: return __alignof__(u64); case BPF_LIST_HEAD: return __alignof__(struct bpf_list_head); @@ -389,6 +394,7 @@ static inline void bpf_obj_init_field(const struct btf_field *field, void *addr) case BPF_TIMER: case BPF_KPTR_UNREF: case BPF_KPTR_REF: + case BPF_KPTR_PERCPU: break; default: WARN_ON_ONCE(1); @@ -1029,6 +1035,11 @@ struct btf_func_model { */ #define BPF_TRAMP_F_SHARE_IPMODIFY BIT(6) +/* Indicate that current trampoline is in a tail call context. Then, it has to + * cache and restore tail_call_cnt to avoid infinite tail call loop. + */ +#define BPF_TRAMP_F_TAIL_CALL_CTX BIT(7) + /* Each call __bpf_prog_enter + call bpf_func + call __bpf_prog_exit is ~50 * bytes on x86. */ @@ -1307,7 +1318,7 @@ static inline int bpf_trampoline_unlink_prog(struct bpf_tramp_link *link, static inline struct bpf_trampoline *bpf_trampoline_get(u64 key, struct bpf_attach_target_info *tgt_info) { - return ERR_PTR(-EOPNOTSUPP); + return NULL; } static inline void bpf_trampoline_put(struct bpf_trampoline *tr) {} #define DEFINE_BPF_DISPATCHER(name) @@ -1378,6 +1389,7 @@ struct bpf_prog_aux { u32 stack_depth; u32 id; u32 func_cnt; /* used by non-func prog as the number of func progs */ + u32 real_func_cnt; /* includes hidden progs, only used for JIT and freeing progs */ u32 func_idx; /* 0 for non-func prog, the index in func array for func prog */ u32 attach_btf_id; /* in-kernel BTF type id to attach to */ u32 ctx_arg_info_size; @@ -1398,6 +1410,8 @@ struct bpf_prog_aux { bool sleepable; bool tail_call_reachable; bool xdp_has_frags; + bool exception_cb; + bool exception_boundary; /* BTF_KIND_FUNC_PROTO for valid attach_btf_id */ const struct btf_type *attach_func_proto; /* function name for valid attach_btf_id */ @@ -1420,6 +1434,7 @@ struct bpf_prog_aux { int cgroup_atype; /* enum cgroup_bpf_attach_type */ struct bpf_map *cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE]; char name[BPF_OBJ_NAME_LEN]; + unsigned int (*bpf_exception_cb)(u64 cookie, u64 sp, u64 bp); #ifdef CONFIG_SECURITY void *security; #endif @@ -2043,6 +2058,7 @@ struct btf_record *btf_record_dup(const struct btf_record *rec); bool btf_record_equal(const struct btf_record *rec_a, const struct btf_record *rec_b); void bpf_obj_free_timer(const struct btf_record *rec, void *obj); void bpf_obj_free_fields(const struct btf_record *rec, void *obj); +void __bpf_obj_drop_impl(void *p, const struct btf_record *rec, bool percpu); struct bpf_map *bpf_map_get(u32 ufd); struct bpf_map *bpf_map_get_with_uref(u32 ufd); @@ -2149,12 +2165,12 @@ static inline bool bpf_allow_uninit_stack(void) static inline bool bpf_bypass_spec_v1(void) { - return perfmon_capable(); + return cpu_mitigations_off() || perfmon_capable(); } static inline bool bpf_bypass_spec_v4(void) { - return perfmon_capable(); + return cpu_mitigations_off() || perfmon_capable(); } int bpf_map_new_fd(struct bpf_map *map, int flags); @@ -2407,9 +2423,11 @@ int btf_check_subprog_arg_match(struct bpf_verifier_env *env, int subprog, int btf_check_subprog_call(struct bpf_verifier_env *env, int subprog, struct bpf_reg_state *regs); int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog, - struct bpf_reg_state *reg); + struct bpf_reg_state *reg, bool is_ex_cb); int btf_check_type_match(struct bpf_verifier_log *log, const struct bpf_prog *prog, struct btf *btf, const struct btf_type *t); +const char *btf_find_decl_tag_value(const struct btf *btf, const struct btf_type *pt, + int comp_idx, const char *tag_key); struct bpf_prog *bpf_prog_by_id(u32 id); struct bpf_link *bpf_link_by_id(u32 id); @@ -2461,6 +2479,9 @@ void bpf_dynptr_init(struct bpf_dynptr_kern *ptr, void *data, enum bpf_dynptr_type type, u32 offset, u32 size); void bpf_dynptr_set_null(struct bpf_dynptr_kern *ptr); void bpf_dynptr_set_rdonly(struct bpf_dynptr_kern *ptr); + +bool dev_check_flush(void); +bool cpu_map_check_flush(void); #else /* !CONFIG_BPF_SYSCALL */ static inline struct bpf_prog *bpf_prog_get(u32 ufd) { @@ -2905,6 +2926,22 @@ static inline int sock_map_bpf_prog_query(const union bpf_attr *attr, #endif /* CONFIG_BPF_SYSCALL */ #endif /* CONFIG_NET && CONFIG_BPF_SYSCALL */ +static __always_inline void +bpf_prog_inc_misses_counters(const struct bpf_prog_array *array) +{ + const struct bpf_prog_array_item *item; + struct bpf_prog *prog; + + if (unlikely(!array)) + return; + + item = &array->items[0]; + while ((prog = READ_ONCE(item->prog))) { + bpf_prog_inc_misses_counter(prog); + item++; + } +} + #if defined(CONFIG_INET) && defined(CONFIG_BPF_SYSCALL) void bpf_sk_reuseport_detach(struct sock *sk); int bpf_fd_reuseport_array_lookup_elem(struct bpf_map *map, void *key, @@ -3183,4 +3220,9 @@ static inline gfp_t bpf_memcg_flags(gfp_t flags) return flags; } +static inline bool bpf_is_subprog(const struct bpf_prog *prog) +{ + return prog->aux->func_idx != 0; +} + #endif /* _LINUX_BPF_H */ diff --git a/include/linux/bpf_mem_alloc.h b/include/linux/bpf_mem_alloc.h index d644bbb298af..bb1223b21308 100644 --- a/include/linux/bpf_mem_alloc.h +++ b/include/linux/bpf_mem_alloc.h @@ -11,6 +11,7 @@ struct bpf_mem_caches; struct bpf_mem_alloc { struct bpf_mem_caches __percpu *caches; struct bpf_mem_cache __percpu *cache; + bool percpu; struct work_struct work; }; diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index b6e58dab8e27..24213a99cc79 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -300,6 +300,7 @@ struct bpf_func_state { bool in_callback_fn; struct tnum callback_ret_range; bool in_async_callback_fn; + bool in_exception_callback_fn; /* The following fields should be last. See copy_func_state() */ int acquired_refs; @@ -372,10 +373,25 @@ struct bpf_verifier_state { struct bpf_active_lock active_lock; bool speculative; bool active_rcu_lock; + /* If this state was ever pointed-to by other state's loop_entry field + * this flag would be set to true. Used to avoid freeing such states + * while they are still in use. + */ + bool used_as_loop_entry; /* first and last insn idx of this verifier state */ u32 first_insn_idx; u32 last_insn_idx; + /* If this state is a part of states loop this field points to some + * parent of this state such that: + * - it is also a member of the same states loop; + * - DFS states traversal starting from initial state visits loop_entry + * state before this state. + * Used to compute topmost loop entry for state loops. + * State loops might appear because of open coded iterators logic. + * See get_loop_entry() for more information. + */ + struct bpf_verifier_state *loop_entry; /* jmp history recorded from first to last. * backtracking is using it to go from last to first. * For most states jmp_history_cnt is [0-3]. @@ -383,21 +399,21 @@ struct bpf_verifier_state { */ struct bpf_idx_pair *jmp_history; u32 jmp_history_cnt; + u32 dfs_depth; }; -#define bpf_get_spilled_reg(slot, frame) \ +#define bpf_get_spilled_reg(slot, frame, mask) \ (((slot < frame->allocated_stack / BPF_REG_SIZE) && \ - (frame->stack[slot].slot_type[0] == STACK_SPILL)) \ + ((1 << frame->stack[slot].slot_type[0]) & (mask))) \ ? &frame->stack[slot].spilled_ptr : NULL) /* Iterate over 'frame', setting 'reg' to either NULL or a spilled register. */ -#define bpf_for_each_spilled_reg(iter, frame, reg) \ - for (iter = 0, reg = bpf_get_spilled_reg(iter, frame); \ +#define bpf_for_each_spilled_reg(iter, frame, reg, mask) \ + for (iter = 0, reg = bpf_get_spilled_reg(iter, frame, mask); \ iter < frame->allocated_stack / BPF_REG_SIZE; \ - iter++, reg = bpf_get_spilled_reg(iter, frame)) + iter++, reg = bpf_get_spilled_reg(iter, frame, mask)) -/* Invoke __expr over regsiters in __vst, setting __state and __reg */ -#define bpf_for_each_reg_in_vstate(__vst, __state, __reg, __expr) \ +#define bpf_for_each_reg_in_vstate_mask(__vst, __state, __reg, __mask, __expr) \ ({ \ struct bpf_verifier_state *___vstate = __vst; \ int ___i, ___j; \ @@ -409,7 +425,7 @@ struct bpf_verifier_state { __reg = &___regs[___j]; \ (void)(__expr); \ } \ - bpf_for_each_spilled_reg(___j, __state, __reg) { \ + bpf_for_each_spilled_reg(___j, __state, __reg, __mask) { \ if (!__reg) \ continue; \ (void)(__expr); \ @@ -417,6 +433,10 @@ struct bpf_verifier_state { } \ }) +/* Invoke __expr over regsiters in __vst, setting __state and __reg */ +#define bpf_for_each_reg_in_vstate(__vst, __state, __reg, __expr) \ + bpf_for_each_reg_in_vstate_mask(__vst, __state, __reg, 1 << STACK_SPILL, __expr) + /* linked list of verifier states used to prune search */ struct bpf_verifier_state_list { struct bpf_verifier_state state; @@ -480,6 +500,7 @@ struct bpf_insn_aux_data { bool zext_dst; /* this insn zero extends dst reg */ bool storage_get_func_atomic; /* bpf_*_storage_get() with atomic memory alloc */ bool is_iter_next; /* bpf_iter_<type>_next() kfunc call */ + bool call_with_percpu_alloc_ptr; /* {this,per}_cpu_ptr() with prog percpu alloc */ u8 alu_state; /* used in combination with alu_limit */ /* below fields are initialized once */ @@ -540,7 +561,9 @@ struct bpf_subprog_info { bool has_tail_call; bool tail_call_reachable; bool has_ld_abs; + bool is_cb; bool is_async_cb; + bool is_exception_cb; }; struct bpf_verifier_env; @@ -587,6 +610,8 @@ struct bpf_verifier_env { u32 used_map_cnt; /* number of used maps */ u32 used_btf_cnt; /* number of used BTF objects */ u32 id_gen; /* used to generate unique reg IDs */ + u32 hidden_subprog_cnt; /* number of hidden subprogs */ + int exception_callback_subprog; bool explore_alu_limits; bool allow_ptr_leaks; bool allow_uninit_stack; @@ -594,10 +619,11 @@ struct bpf_verifier_env { bool bypass_spec_v1; bool bypass_spec_v4; bool seen_direct_write; + bool seen_exception; struct bpf_insn_aux_data *insn_aux_data; /* array of per-insn state */ const struct bpf_line_info *prev_linfo; struct bpf_verifier_log log; - struct bpf_subprog_info subprog_info[BPF_MAX_SUBPROGS + 1]; + struct bpf_subprog_info subprog_info[BPF_MAX_SUBPROGS + 2]; /* max + 2 for the fake and exception subprogs */ union { struct bpf_idmap idmap_scratch; struct bpf_idset idset_scratch; diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h index c55810a43541..1394ba302367 100644 --- a/include/linux/brcmphy.h +++ b/include/linux/brcmphy.h @@ -11,6 +11,7 @@ #define PHY_ID_BCM50610 0x0143bd60 #define PHY_ID_BCM50610M 0x0143bd70 +#define PHY_ID_BCM5221 0x004061e0 #define PHY_ID_BCM5241 0x0143bc30 #define PHY_ID_BCMAC131 0x0143bc70 #define PHY_ID_BCM5481 0x0143bca0 @@ -331,6 +332,15 @@ #define BCM54XX_WOL_INT_STATUS (MII_BCM54XX_EXP_SEL_WOL + 0x94) +/* BCM5221 Registers */ +#define BCM5221_AEGSR 0x1C +#define BCM5221_AEGSR_MDIX_STATUS BIT(13) +#define BCM5221_AEGSR_MDIX_MAN_SWAP BIT(12) +#define BCM5221_AEGSR_MDIX_DIS BIT(11) + +#define BCM5221_SHDW_AM4_EN_CLK_LPM BIT(2) +#define BCM5221_SHDW_AM4_FORCE_LPM BIT(1) + /*****************************************************************************/ /* Fast Ethernet Transceiver definitions. */ /*****************************************************************************/ diff --git a/include/linux/btf.h b/include/linux/btf.h index 928113a80a95..c2231c64d60b 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -74,6 +74,7 @@ #define KF_ITER_NEW (1 << 8) /* kfunc implements BPF iter constructor */ #define KF_ITER_NEXT (1 << 9) /* kfunc implements BPF iter next method */ #define KF_ITER_DESTROY (1 << 10) /* kfunc implements BPF iter destructor */ +#define KF_RCU_PROTECTED (1 << 11) /* kfunc should be protected by rcu cs when they are invoked */ /* * Tag marking a kernel function as a kfunc. This is meant to minimize the diff --git a/include/linux/btf_ids.h b/include/linux/btf_ids.h index a3462a9b8e18..a9cb10b0e2e9 100644 --- a/include/linux/btf_ids.h +++ b/include/linux/btf_ids.h @@ -49,7 +49,7 @@ word \ ____BTF_ID(symbol, word) #define __ID(prefix) \ - __PASTE(prefix, __COUNTER__) + __PASTE(__PASTE(prefix, __COUNTER__), __LINE__) /* * The BTF_ID defines unique symbol for each ID pointing diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 4ede47649a81..44e9de51eedf 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -171,7 +171,10 @@ static __always_inline int buffer_uptodate(const struct buffer_head *bh) return test_bit_acquire(BH_Uptodate, &bh->b_state); } -#define bh_offset(bh) ((unsigned long)(bh)->b_data & ~PAGE_MASK) +static inline unsigned long bh_offset(const struct buffer_head *bh) +{ + return (unsigned long)(bh)->b_data & (page_size(bh->b_page) - 1); +} /* If we *know* page->private refers to buffer_heads */ #define page_buffers(page) \ diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h index 982ba245eb41..1b92aed49363 100644 --- a/include/linux/can/dev.h +++ b/include/linux/can/dev.h @@ -195,6 +195,10 @@ int can_restart_now(struct net_device *dev); void can_bus_off(struct net_device *dev); const char *can_get_state_str(const enum can_state state); +void can_state_get_by_berr_counter(const struct net_device *dev, + const struct can_berr_counter *bec, + enum can_state *tx_state, + enum can_state *rx_state); void can_change_state(struct net_device *dev, struct can_frame *cf, enum can_state tx_state, enum can_state rx_state); diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h index 5f2301ee88bc..f3b3593254b9 100644 --- a/include/linux/ceph/ceph_fs.h +++ b/include/linux/ceph/ceph_fs.h @@ -467,19 +467,17 @@ union ceph_mds_request_args { } __attribute__ ((packed)); union ceph_mds_request_args_ext { - union { - union ceph_mds_request_args old; - struct { - __le32 mode; - __le32 uid; - __le32 gid; - struct ceph_timespec mtime; - struct ceph_timespec atime; - __le64 size, old_size; /* old_size needed by truncate */ - __le32 mask; /* CEPH_SETATTR_* */ - struct ceph_timespec btime; - } __attribute__ ((packed)) setattr_ext; - }; + union ceph_mds_request_args old; + struct { + __le32 mode; + __le32 uid; + __le32 gid; + struct ceph_timespec mtime; + struct ceph_timespec atime; + __le64 size, old_size; /* old_size needed by truncate */ + __le32 mask; /* CEPH_SETATTR_* */ + struct ceph_timespec btime; + } __attribute__ ((packed)) setattr_ext; }; #define CEPH_MDS_FLAG_REPLAY 1 /* this is a replayed op */ diff --git a/include/linux/ceph/mon_client.h b/include/linux/ceph/mon_client.h index b658961156a0..7a9a40163c0f 100644 --- a/include/linux/ceph/mon_client.h +++ b/include/linux/ceph/mon_client.h @@ -19,7 +19,7 @@ struct ceph_monmap { struct ceph_fsid fsid; u32 epoch; u32 num_mon; - struct ceph_entity_inst mon_inst[]; + struct ceph_entity_inst mon_inst[] __counted_by(num_mon); }; struct ceph_mon_client; diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index bf9823956758..b8610e9d2471 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -278,7 +278,7 @@ struct ceph_osd_request { int r_attempts; u32 r_map_dne_bound; - struct ceph_osd_req_op r_ops[]; + struct ceph_osd_req_op r_ops[] __counted_by(r_num_ops); }; struct ceph_request_redirect { diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index f1b3151ac30b..265da00a1a8b 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -238,7 +238,7 @@ struct css_set { * Lists running through all tasks using this cgroup group. * mg_tasks lists tasks which belong to this cset but are in the * process of being migrated out or in. Protected by - * css_set_rwsem, but, during migration, once tasks are moved to + * css_set_lock, but, during migration, once tasks are moved to * mg_tasks, it can be read safely while holding cgroup_mutex. */ struct list_head tasks; diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index b307013b9c6c..0ef0af66080e 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -40,13 +40,11 @@ struct kernel_clone_args; #define CGROUP_WEIGHT_DFL 100 #define CGROUP_WEIGHT_MAX 10000 -/* walk only threadgroup leaders */ -#define CSS_TASK_ITER_PROCS (1U << 0) -/* walk all threaded css_sets in the domain */ -#define CSS_TASK_ITER_THREADED (1U << 1) - -/* internal flags */ -#define CSS_TASK_ITER_SKIPPED (1U << 16) +enum { + CSS_TASK_ITER_PROCS = (1U << 0), /* walk only threadgroup leaders */ + CSS_TASK_ITER_THREADED = (1U << 1), /* walk all threaded css_sets in the domain */ + CSS_TASK_ITER_SKIPPED = (1U << 16), /* internal flags */ +}; /* a css_task_iter should be treated as an opaque object */ struct css_task_iter { diff --git a/include/linux/cleanup.h b/include/linux/cleanup.h index 53f1a7a932b0..9f1a9c455b68 100644 --- a/include/linux/cleanup.h +++ b/include/linux/cleanup.h @@ -7,8 +7,9 @@ /* * DEFINE_FREE(name, type, free): * simple helper macro that defines the required wrapper for a __free() - * based cleanup function. @free is an expression using '_T' to access - * the variable. + * based cleanup function. @free is an expression using '_T' to access the + * variable. @free should typically include a NULL test before calling a + * function, see the example below. * * __free(name): * variable attribute to add a scoped based cleanup to the variable. @@ -17,6 +18,9 @@ * like a non-atomic xchg(var, NULL), such that the cleanup function will * be inhibited -- provided it sanely deals with a NULL value. * + * NOTE: this has __must_check semantics so that it is harder to accidentally + * leak the resource. + * * return_ptr(p): * returns p while inhibiting the __free(). * @@ -24,6 +28,8 @@ * * DEFINE_FREE(kfree, void *, if (_T) kfree(_T)) * + * void *alloc_obj(...) + * { * struct obj *p __free(kfree) = kmalloc(...); * if (!p) * return NULL; @@ -32,6 +38,24 @@ * return NULL; * * return_ptr(p); + * } + * + * NOTE: the DEFINE_FREE()'s @free expression includes a NULL test even though + * kfree() is fine to be called with a NULL value. This is on purpose. This way + * the compiler sees the end of our alloc_obj() function as: + * + * tmp = p; + * p = NULL; + * if (p) + * kfree(p); + * return tmp; + * + * And through the magic of value-propagation and dead-code-elimination, it + * eliminates the actual cleanup call and compiles into: + * + * return p; + * + * Without the NULL test it turns into a mess and the compiler can't help us. */ #define DEFINE_FREE(_name, _type, _free) \ @@ -39,8 +63,17 @@ #define __free(_name) __cleanup(__free_##_name) +#define __get_and_null_ptr(p) \ + ({ __auto_type __ptr = &(p); \ + __auto_type __val = *__ptr; \ + *__ptr = NULL; __val; }) + +static inline __must_check +const volatile void * __must_check_fn(const volatile void *val) +{ return val; } + #define no_free_ptr(p) \ - ({ __auto_type __ptr = (p); (p) = NULL; __ptr; }) + ((typeof(p)) __must_check_fn(__get_and_null_ptr(p))) #define return_ptr(p) return no_free_ptr(p) diff --git a/include/linux/closure.h b/include/linux/closure.h new file mode 100644 index 000000000000..722a586bb224 --- /dev/null +++ b/include/linux/closure.h @@ -0,0 +1,404 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_CLOSURE_H +#define _LINUX_CLOSURE_H + +#include <linux/llist.h> +#include <linux/sched.h> +#include <linux/sched/task_stack.h> +#include <linux/workqueue.h> + +/* + * Closure is perhaps the most overused and abused term in computer science, but + * since I've been unable to come up with anything better you're stuck with it + * again. + * + * What are closures? + * + * They embed a refcount. The basic idea is they count "things that are in + * progress" - in flight bios, some other thread that's doing something else - + * anything you might want to wait on. + * + * The refcount may be manipulated with closure_get() and closure_put(). + * closure_put() is where many of the interesting things happen, when it causes + * the refcount to go to 0. + * + * Closures can be used to wait on things both synchronously and asynchronously, + * and synchronous and asynchronous use can be mixed without restriction. To + * wait synchronously, use closure_sync() - you will sleep until your closure's + * refcount hits 1. + * + * To wait asynchronously, use + * continue_at(cl, next_function, workqueue); + * + * passing it, as you might expect, the function to run when nothing is pending + * and the workqueue to run that function out of. + * + * continue_at() also, critically, requires a 'return' immediately following the + * location where this macro is referenced, to return to the calling function. + * There's good reason for this. + * + * To use safely closures asynchronously, they must always have a refcount while + * they are running owned by the thread that is running them. Otherwise, suppose + * you submit some bios and wish to have a function run when they all complete: + * + * foo_endio(struct bio *bio) + * { + * closure_put(cl); + * } + * + * closure_init(cl); + * + * do_stuff(); + * closure_get(cl); + * bio1->bi_endio = foo_endio; + * bio_submit(bio1); + * + * do_more_stuff(); + * closure_get(cl); + * bio2->bi_endio = foo_endio; + * bio_submit(bio2); + * + * continue_at(cl, complete_some_read, system_wq); + * + * If closure's refcount started at 0, complete_some_read() could run before the + * second bio was submitted - which is almost always not what you want! More + * importantly, it wouldn't be possible to say whether the original thread or + * complete_some_read()'s thread owned the closure - and whatever state it was + * associated with! + * + * So, closure_init() initializes a closure's refcount to 1 - and when a + * closure_fn is run, the refcount will be reset to 1 first. + * + * Then, the rule is - if you got the refcount with closure_get(), release it + * with closure_put() (i.e, in a bio->bi_endio function). If you have a refcount + * on a closure because you called closure_init() or you were run out of a + * closure - _always_ use continue_at(). Doing so consistently will help + * eliminate an entire class of particularly pernicious races. + * + * Lastly, you might have a wait list dedicated to a specific event, and have no + * need for specifying the condition - you just want to wait until someone runs + * closure_wake_up() on the appropriate wait list. In that case, just use + * closure_wait(). It will return either true or false, depending on whether the + * closure was already on a wait list or not - a closure can only be on one wait + * list at a time. + * + * Parents: + * + * closure_init() takes two arguments - it takes the closure to initialize, and + * a (possibly null) parent. + * + * If parent is non null, the new closure will have a refcount for its lifetime; + * a closure is considered to be "finished" when its refcount hits 0 and the + * function to run is null. Hence + * + * continue_at(cl, NULL, NULL); + * + * returns up the (spaghetti) stack of closures, precisely like normal return + * returns up the C stack. continue_at() with non null fn is better thought of + * as doing a tail call. + * + * All this implies that a closure should typically be embedded in a particular + * struct (which its refcount will normally control the lifetime of), and that + * struct can very much be thought of as a stack frame. + */ + +struct closure; +struct closure_syncer; +typedef void (closure_fn) (struct closure *); +extern struct dentry *bcache_debug; + +struct closure_waitlist { + struct llist_head list; +}; + +enum closure_state { + /* + * CLOSURE_WAITING: Set iff the closure is on a waitlist. Must be set by + * the thread that owns the closure, and cleared by the thread that's + * waking up the closure. + * + * The rest are for debugging and don't affect behaviour: + * + * CLOSURE_RUNNING: Set when a closure is running (i.e. by + * closure_init() and when closure_put() runs then next function), and + * must be cleared before remaining hits 0. Primarily to help guard + * against incorrect usage and accidentally transferring references. + * continue_at() and closure_return() clear it for you, if you're doing + * something unusual you can use closure_set_dead() which also helps + * annotate where references are being transferred. + */ + + CLOSURE_BITS_START = (1U << 26), + CLOSURE_DESTRUCTOR = (1U << 26), + CLOSURE_WAITING = (1U << 28), + CLOSURE_RUNNING = (1U << 30), +}; + +#define CLOSURE_GUARD_MASK \ + ((CLOSURE_DESTRUCTOR|CLOSURE_WAITING|CLOSURE_RUNNING) << 1) + +#define CLOSURE_REMAINING_MASK (CLOSURE_BITS_START - 1) +#define CLOSURE_REMAINING_INITIALIZER (1|CLOSURE_RUNNING) + +struct closure { + union { + struct { + struct workqueue_struct *wq; + struct closure_syncer *s; + struct llist_node list; + closure_fn *fn; + }; + struct work_struct work; + }; + + struct closure *parent; + + atomic_t remaining; + +#ifdef CONFIG_DEBUG_CLOSURES +#define CLOSURE_MAGIC_DEAD 0xc054dead +#define CLOSURE_MAGIC_ALIVE 0xc054a11e + + unsigned int magic; + struct list_head all; + unsigned long ip; + unsigned long waiting_on; +#endif +}; + +void closure_sub(struct closure *cl, int v); +void closure_put(struct closure *cl); +void __closure_wake_up(struct closure_waitlist *list); +bool closure_wait(struct closure_waitlist *list, struct closure *cl); +void __closure_sync(struct closure *cl); + +static inline unsigned closure_nr_remaining(struct closure *cl) +{ + return atomic_read(&cl->remaining) & CLOSURE_REMAINING_MASK; +} + +/** + * closure_sync - sleep until a closure a closure has nothing left to wait on + * + * Sleeps until the refcount hits 1 - the thread that's running the closure owns + * the last refcount. + */ +static inline void closure_sync(struct closure *cl) +{ + if (closure_nr_remaining(cl) != 1) + __closure_sync(cl); +} + +#ifdef CONFIG_DEBUG_CLOSURES + +void closure_debug_create(struct closure *cl); +void closure_debug_destroy(struct closure *cl); + +#else + +static inline void closure_debug_create(struct closure *cl) {} +static inline void closure_debug_destroy(struct closure *cl) {} + +#endif + +static inline void closure_set_ip(struct closure *cl) +{ +#ifdef CONFIG_DEBUG_CLOSURES + cl->ip = _THIS_IP_; +#endif +} + +static inline void closure_set_ret_ip(struct closure *cl) +{ +#ifdef CONFIG_DEBUG_CLOSURES + cl->ip = _RET_IP_; +#endif +} + +static inline void closure_set_waiting(struct closure *cl, unsigned long f) +{ +#ifdef CONFIG_DEBUG_CLOSURES + cl->waiting_on = f; +#endif +} + +static inline void closure_set_stopped(struct closure *cl) +{ + atomic_sub(CLOSURE_RUNNING, &cl->remaining); +} + +static inline void set_closure_fn(struct closure *cl, closure_fn *fn, + struct workqueue_struct *wq) +{ + closure_set_ip(cl); + cl->fn = fn; + cl->wq = wq; + /* between atomic_dec() in closure_put() */ + smp_mb__before_atomic(); +} + +static inline void closure_queue(struct closure *cl) +{ + struct workqueue_struct *wq = cl->wq; + /** + * Changes made to closure, work_struct, or a couple of other structs + * may cause work.func not pointing to the right location. + */ + BUILD_BUG_ON(offsetof(struct closure, fn) + != offsetof(struct work_struct, func)); + + if (wq) { + INIT_WORK(&cl->work, cl->work.func); + BUG_ON(!queue_work(wq, &cl->work)); + } else + cl->fn(cl); +} + +/** + * closure_get - increment a closure's refcount + */ +static inline void closure_get(struct closure *cl) +{ +#ifdef CONFIG_DEBUG_CLOSURES + BUG_ON((atomic_inc_return(&cl->remaining) & + CLOSURE_REMAINING_MASK) <= 1); +#else + atomic_inc(&cl->remaining); +#endif +} + +/** + * closure_init - Initialize a closure, setting the refcount to 1 + * @cl: closure to initialize + * @parent: parent of the new closure. cl will take a refcount on it for its + * lifetime; may be NULL. + */ +static inline void closure_init(struct closure *cl, struct closure *parent) +{ + cl->fn = NULL; + cl->parent = parent; + if (parent) + closure_get(parent); + + atomic_set(&cl->remaining, CLOSURE_REMAINING_INITIALIZER); + + closure_debug_create(cl); + closure_set_ip(cl); +} + +static inline void closure_init_stack(struct closure *cl) +{ + memset(cl, 0, sizeof(struct closure)); + atomic_set(&cl->remaining, CLOSURE_REMAINING_INITIALIZER); +} + +/** + * closure_wake_up - wake up all closures on a wait list, + * with memory barrier + */ +static inline void closure_wake_up(struct closure_waitlist *list) +{ + /* Memory barrier for the wait list */ + smp_mb(); + __closure_wake_up(list); +} + +/** + * continue_at - jump to another function with barrier + * + * After @cl is no longer waiting on anything (i.e. all outstanding refs have + * been dropped with closure_put()), it will resume execution at @fn running out + * of @wq (or, if @wq is NULL, @fn will be called by closure_put() directly). + * + * This is because after calling continue_at() you no longer have a ref on @cl, + * and whatever @cl owns may be freed out from under you - a running closure fn + * has a ref on its own closure which continue_at() drops. + * + * Note you are expected to immediately return after using this macro. + */ +#define continue_at(_cl, _fn, _wq) \ +do { \ + set_closure_fn(_cl, _fn, _wq); \ + closure_sub(_cl, CLOSURE_RUNNING + 1); \ +} while (0) + +/** + * closure_return - finish execution of a closure + * + * This is used to indicate that @cl is finished: when all outstanding refs on + * @cl have been dropped @cl's ref on its parent closure (as passed to + * closure_init()) will be dropped, if one was specified - thus this can be + * thought of as returning to the parent closure. + */ +#define closure_return(_cl) continue_at((_cl), NULL, NULL) + +/** + * continue_at_nobarrier - jump to another function without barrier + * + * Causes @fn to be executed out of @cl, in @wq context (or called directly if + * @wq is NULL). + * + * The ref the caller of continue_at_nobarrier() had on @cl is now owned by @fn, + * thus it's not safe to touch anything protected by @cl after a + * continue_at_nobarrier(). + */ +#define continue_at_nobarrier(_cl, _fn, _wq) \ +do { \ + set_closure_fn(_cl, _fn, _wq); \ + closure_queue(_cl); \ +} while (0) + +/** + * closure_return_with_destructor - finish execution of a closure, + * with destructor + * + * Works like closure_return(), except @destructor will be called when all + * outstanding refs on @cl have been dropped; @destructor may be used to safely + * free the memory occupied by @cl, and it is called with the ref on the parent + * closure still held - so @destructor could safely return an item to a + * freelist protected by @cl's parent. + */ +#define closure_return_with_destructor(_cl, _destructor) \ +do { \ + set_closure_fn(_cl, _destructor, NULL); \ + closure_sub(_cl, CLOSURE_RUNNING - CLOSURE_DESTRUCTOR + 1); \ +} while (0) + +/** + * closure_call - execute @fn out of a new, uninitialized closure + * + * Typically used when running out of one closure, and we want to run @fn + * asynchronously out of a new closure - @parent will then wait for @cl to + * finish. + */ +static inline void closure_call(struct closure *cl, closure_fn fn, + struct workqueue_struct *wq, + struct closure *parent) +{ + closure_init(cl, parent); + continue_at_nobarrier(cl, fn, wq); +} + +#define __closure_wait_event(waitlist, _cond) \ +do { \ + struct closure cl; \ + \ + closure_init_stack(&cl); \ + \ + while (1) { \ + closure_wait(waitlist, &cl); \ + if (_cond) \ + break; \ + closure_sync(&cl); \ + } \ + closure_wake_up(waitlist); \ + closure_sync(&cl); \ +} while (0) + +#define closure_wait_event(waitlist, _cond) \ +do { \ + if (!(_cond)) \ + __closure_wait_event(waitlist, _cond); \ +} while (0) + +#endif /* _LINUX_CLOSURE_H */ diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index c523c6683789..6f1ca49306d2 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -2,6 +2,15 @@ #ifndef __LINUX_COMPILER_TYPES_H #define __LINUX_COMPILER_TYPES_H +/* + * __has_builtin is supported on gcc >= 10, clang >= 3 and icc >= 21. + * In the meantime, to support gcc < 10, we implement __has_builtin + * by hand. + */ +#ifndef __has_builtin +#define __has_builtin(x) (0) +#endif + #ifndef __ASSEMBLY__ /* @@ -134,17 +143,6 @@ static inline void __chk_io_ptr(const volatile void __iomem *ptr) { } # define __preserve_most #endif -/* Builtins */ - -/* - * __has_builtin is supported on gcc >= 10, clang >= 3 and icc >= 21. - * In the meantime, to support gcc < 10, we implement __has_builtin - * by hand. - */ -#ifndef __has_builtin -#define __has_builtin(x) (0) -#endif - /* Compiler specific macros. */ #ifdef __clang__ #include <linux/compiler-clang.h> @@ -352,6 +350,18 @@ struct ftrace_likely_data { # define __realloc_size(x, ...) #endif +/* + * When the size of an allocated object is needed, use the best available + * mechanism to find it. (For cases where sizeof() cannot be used.) + */ +#if __has_builtin(__builtin_dynamic_object_size) +#define __struct_size(p) __builtin_dynamic_object_size(p, 0) +#define __member_size(p) __builtin_dynamic_object_size(p, 1) +#else +#define __struct_size(p) __builtin_object_size(p, 0) +#define __member_size(p) __builtin_object_size(p, 1) +#endif + #ifndef asm_volatile_goto #define asm_volatile_goto(x...) asm goto(x) #endif diff --git a/include/linux/cpu.h b/include/linux/cpu.h index 0abd60a7987b..fc8094419084 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -80,6 +80,8 @@ extern __printf(4, 5) struct device *cpu_device_create(struct device *parent, void *drvdata, const struct attribute_group **groups, const char *fmt, ...); +extern int arch_register_cpu(int cpu); +extern void arch_unregister_cpu(int cpu); #ifdef CONFIG_HOTPLUG_CPU extern void unregister_cpu(struct cpu *cpu); extern ssize_t arch_cpu_probe(const char *, size_t); @@ -153,6 +155,8 @@ static inline int remove_cpu(unsigned int cpu) { return -EPERM; } static inline void smp_shutdown_nonboot_cpus(unsigned int primary_cpu) { } #endif /* !CONFIG_HOTPLUG_CPU */ +DEFINE_LOCK_GUARD_0(cpus_read_lock, cpus_read_lock(), cpus_read_unlock()) + #ifdef CONFIG_PM_SLEEP_SMP extern int freeze_secondary_cpus(int primary); extern void thaw_secondary_cpus(void); diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 71d186d6933a..1c5ca92a0555 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -1193,14 +1193,6 @@ static inline int of_perf_domain_get_sharing_cpumask(int pcpu, const char *list_ } #endif -#if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL) -void sched_cpufreq_governor_change(struct cpufreq_policy *policy, - struct cpufreq_governor *old_gov); -#else -static inline void sched_cpufreq_governor_change(struct cpufreq_policy *policy, - struct cpufreq_governor *old_gov) { } -#endif - extern unsigned int arch_freq_get_on_cpu(int cpu); #ifndef arch_set_freq_scale diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 06dda85f0424..d246d325918a 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -90,7 +90,6 @@ enum cpuhp_state { CPUHP_FS_BUFF_DEAD, CPUHP_PRINTK_DEAD, CPUHP_MM_MEMCQ_DEAD, - CPUHP_XFS_DEAD, CPUHP_PERCPU_CNT_DEAD, CPUHP_RADIX_DEAD, CPUHP_PAGE_ALLOC, @@ -205,7 +204,6 @@ enum cpuhp_state { CPUHP_AP_KVM_ONLINE, CPUHP_AP_SCHED_WAIT_EMPTY, CPUHP_AP_SMPBOOT_THREADS, - CPUHP_AP_X86_VDSO_VMA_ONLINE, CPUHP_AP_IRQ_AFFINITY_ONLINE, CPUHP_AP_BLK_MQ_ONLINE, CPUHP_AP_ARM_MVEBU_SYNC_CLOCKS, diff --git a/include/linux/crash_core.h b/include/linux/crash_core.h index 0c06561bf5ff..08704c29fdb4 100644 --- a/include/linux/crash_core.h +++ b/include/linux/crash_core.h @@ -92,7 +92,7 @@ int parse_crashkernel_low(char *cmdline, unsigned long long system_ram, struct crash_mem { unsigned int max_nr_ranges; unsigned int nr_ranges; - struct range ranges[]; + struct range ranges[] __counted_by(max_nr_ranges); }; extern int crash_exclude_mem_range(struct crash_mem *mem, diff --git a/include/linux/cred.h b/include/linux/cred.h index f923528d5cc4..af8d353a4b86 100644 --- a/include/linux/cred.h +++ b/include/linux/cred.h @@ -12,6 +12,7 @@ #include <linux/init.h> #include <linux/key.h> #include <linux/atomic.h> +#include <linux/refcount.h> #include <linux/uidgid.h> #include <linux/sched.h> #include <linux/sched/user.h> @@ -23,7 +24,7 @@ struct inode; * COW Supplementary groups list */ struct group_info { - atomic_t usage; + refcount_t usage; int ngroups; kgid_t gid[]; } __randomize_layout; @@ -39,7 +40,7 @@ struct group_info { */ static inline struct group_info *get_group_info(struct group_info *gi) { - atomic_inc(&gi->usage); + refcount_inc(&gi->usage); return gi; } @@ -49,7 +50,7 @@ static inline struct group_info *get_group_info(struct group_info *gi) */ #define put_group_info(group_info) \ do { \ - if (atomic_dec_and_test(&(group_info)->usage)) \ + if (refcount_dec_and_test(&(group_info)->usage)) \ groups_free(group_info); \ } while (0) @@ -219,6 +220,20 @@ static inline bool cap_ambient_invariant_ok(const struct cred *cred) } /** + * get_new_cred_many - Get references on a new set of credentials + * @cred: The new credentials to reference + * @nr: Number of references to acquire + * + * Get references on the specified set of new credentials. The caller must + * release all acquired references. + */ +static inline struct cred *get_new_cred_many(struct cred *cred, int nr) +{ + atomic_add(nr, &cred->usage); + return cred; +} + +/** * get_new_cred - Get a reference on a new set of credentials * @cred: The new credentials to reference * @@ -227,16 +242,16 @@ static inline bool cap_ambient_invariant_ok(const struct cred *cred) */ static inline struct cred *get_new_cred(struct cred *cred) { - atomic_inc(&cred->usage); - return cred; + return get_new_cred_many(cred, 1); } /** - * get_cred - Get a reference on a set of credentials + * get_cred_many - Get references on a set of credentials * @cred: The credentials to reference + * @nr: Number of references to acquire * - * Get a reference on the specified set of credentials. The caller must - * release the reference. If %NULL is passed, it is returned with no action. + * Get references on the specified set of credentials. The caller must release + * all acquired reference. If %NULL is passed, it is returned with no action. * * This is used to deal with a committed set of credentials. Although the * pointer is const, this will temporarily discard the const and increment the @@ -244,14 +259,28 @@ static inline struct cred *get_new_cred(struct cred *cred) * accidental alteration of a set of credentials that should be considered * immutable. */ -static inline const struct cred *get_cred(const struct cred *cred) +static inline const struct cred *get_cred_many(const struct cred *cred, int nr) { struct cred *nonconst_cred = (struct cred *) cred; if (!cred) return cred; validate_creds(cred); nonconst_cred->non_rcu = 0; - return get_new_cred(nonconst_cred); + return get_new_cred_many(nonconst_cred, nr); +} + +/* + * get_cred - Get a reference on a set of credentials + * @cred: The credentials to reference + * + * Get a reference on the specified set of credentials. The caller must + * release the reference. If %NULL is passed, it is returned with no action. + * + * This is used to deal with a committed set of credentials. + */ +static inline const struct cred *get_cred(const struct cred *cred) +{ + return get_cred_many(cred, 1); } static inline const struct cred *get_cred_rcu(const struct cred *cred) @@ -269,6 +298,7 @@ static inline const struct cred *get_cred_rcu(const struct cred *cred) /** * put_cred - Release a reference to a set of credentials * @cred: The credentials to release + * @nr: Number of references to release * * Release a reference to a set of credentials, deleting them when the last ref * is released. If %NULL is passed, nothing is done. @@ -277,17 +307,29 @@ static inline const struct cred *get_cred_rcu(const struct cred *cred) * on task_struct are attached by const pointers to prevent accidental * alteration of otherwise immutable credential sets. */ -static inline void put_cred(const struct cred *_cred) +static inline void put_cred_many(const struct cred *_cred, int nr) { struct cred *cred = (struct cred *) _cred; if (cred) { validate_creds(cred); - if (atomic_dec_and_test(&(cred)->usage)) + if (atomic_sub_and_test(nr, &cred->usage)) __put_cred(cred); } } +/* + * put_cred - Release a reference to a set of credentials + * @cred: The credentials to release + * + * Release a reference to a set of credentials, deleting them when the last ref + * is released. If %NULL is passed, nothing is done. + */ +static inline void put_cred(const struct cred *cred) +{ + put_cred_many(cred, 1); +} + /** * current_cred - Access the current task's subjective credentials * diff --git a/include/linux/dcache.h b/include/linux/dcache.h index 6b351e009f59..3da2f0545d5d 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -251,6 +251,7 @@ extern struct dentry * d_make_root(struct inode *); /* <clickety>-<click> the ramfs-type tree */ extern void d_genocide(struct dentry *); +extern void d_mark_tmpfile(struct file *, struct inode *); extern void d_tmpfile(struct file *, struct inode *); extern struct dentry *d_find_alias(struct inode *); diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index 69d0435c7ebb..772ab4d74d94 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -165,6 +165,7 @@ void dm_error(const char *message); struct dm_dev { struct block_device *bdev; + struct bdev_handle *bdev_handle; struct dax_device *dax_dev; blk_mode_t mode; char name[16]; diff --git a/include/linux/dma-fence.h b/include/linux/dma-fence.h index 0d678e9a7b24..ebe78bd3d121 100644 --- a/include/linux/dma-fence.h +++ b/include/linux/dma-fence.h @@ -568,6 +568,25 @@ static inline void dma_fence_set_error(struct dma_fence *fence, fence->error = error; } +/** + * dma_fence_timestamp - helper to get the completion timestamp of a fence + * @fence: fence to get the timestamp from. + * + * After a fence is signaled the timestamp is updated with the signaling time, + * but setting the timestamp can race with tasks waiting for the signaling. This + * helper busy waits for the correct timestamp to appear. + */ +static inline ktime_t dma_fence_timestamp(struct dma_fence *fence) +{ + if (WARN_ON(!test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags))) + return ktime_get(); + + while (!test_bit(DMA_FENCE_FLAG_TIMESTAMP_BIT, &fence->flags)) + cpu_relax(); + + return fence->timestamp; +} + signed long dma_fence_wait_timeout(struct dma_fence *, bool intr, signed long timeout); signed long dma_fence_wait_any_timeout(struct dma_fence **fences, diff --git a/include/linux/dpll.h b/include/linux/dpll.h new file mode 100644 index 000000000000..578fc5fa3750 --- /dev/null +++ b/include/linux/dpll.h @@ -0,0 +1,170 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2023 Meta Platforms, Inc. and affiliates + * Copyright (c) 2023 Intel and affiliates + */ + +#ifndef __DPLL_H__ +#define __DPLL_H__ + +#include <uapi/linux/dpll.h> +#include <linux/device.h> +#include <linux/netlink.h> + +struct dpll_device; +struct dpll_pin; + +struct dpll_device_ops { + int (*mode_get)(const struct dpll_device *dpll, void *dpll_priv, + enum dpll_mode *mode, struct netlink_ext_ack *extack); + bool (*mode_supported)(const struct dpll_device *dpll, void *dpll_priv, + const enum dpll_mode mode, + struct netlink_ext_ack *extack); + int (*lock_status_get)(const struct dpll_device *dpll, void *dpll_priv, + enum dpll_lock_status *status, + struct netlink_ext_ack *extack); + int (*temp_get)(const struct dpll_device *dpll, void *dpll_priv, + s32 *temp, struct netlink_ext_ack *extack); +}; + +struct dpll_pin_ops { + int (*frequency_set)(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_device *dpll, void *dpll_priv, + const u64 frequency, + struct netlink_ext_ack *extack); + int (*frequency_get)(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_device *dpll, void *dpll_priv, + u64 *frequency, struct netlink_ext_ack *extack); + int (*direction_set)(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_device *dpll, void *dpll_priv, + const enum dpll_pin_direction direction, + struct netlink_ext_ack *extack); + int (*direction_get)(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_device *dpll, void *dpll_priv, + enum dpll_pin_direction *direction, + struct netlink_ext_ack *extack); + int (*state_on_pin_get)(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_pin *parent_pin, + void *parent_pin_priv, + enum dpll_pin_state *state, + struct netlink_ext_ack *extack); + int (*state_on_dpll_get)(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_device *dpll, + void *dpll_priv, enum dpll_pin_state *state, + struct netlink_ext_ack *extack); + int (*state_on_pin_set)(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_pin *parent_pin, + void *parent_pin_priv, + const enum dpll_pin_state state, + struct netlink_ext_ack *extack); + int (*state_on_dpll_set)(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_device *dpll, + void *dpll_priv, + const enum dpll_pin_state state, + struct netlink_ext_ack *extack); + int (*prio_get)(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_device *dpll, void *dpll_priv, + u32 *prio, struct netlink_ext_ack *extack); + int (*prio_set)(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_device *dpll, void *dpll_priv, + const u32 prio, struct netlink_ext_ack *extack); + int (*phase_offset_get)(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_device *dpll, void *dpll_priv, + s64 *phase_offset, + struct netlink_ext_ack *extack); + int (*phase_adjust_get)(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_device *dpll, void *dpll_priv, + s32 *phase_adjust, + struct netlink_ext_ack *extack); + int (*phase_adjust_set)(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_device *dpll, void *dpll_priv, + const s32 phase_adjust, + struct netlink_ext_ack *extack); +}; + +struct dpll_pin_frequency { + u64 min; + u64 max; +}; + +#define DPLL_PIN_FREQUENCY_RANGE(_min, _max) \ + { \ + .min = _min, \ + .max = _max, \ + } + +#define DPLL_PIN_FREQUENCY(_val) DPLL_PIN_FREQUENCY_RANGE(_val, _val) +#define DPLL_PIN_FREQUENCY_1PPS \ + DPLL_PIN_FREQUENCY(DPLL_PIN_FREQUENCY_1_HZ) +#define DPLL_PIN_FREQUENCY_10MHZ \ + DPLL_PIN_FREQUENCY(DPLL_PIN_FREQUENCY_10_MHZ) +#define DPLL_PIN_FREQUENCY_IRIG_B \ + DPLL_PIN_FREQUENCY(DPLL_PIN_FREQUENCY_10_KHZ) +#define DPLL_PIN_FREQUENCY_DCF77 \ + DPLL_PIN_FREQUENCY(DPLL_PIN_FREQUENCY_77_5_KHZ) + +struct dpll_pin_phase_adjust_range { + s32 min; + s32 max; +}; + +struct dpll_pin_properties { + const char *board_label; + const char *panel_label; + const char *package_label; + enum dpll_pin_type type; + unsigned long capabilities; + u32 freq_supported_num; + struct dpll_pin_frequency *freq_supported; + struct dpll_pin_phase_adjust_range phase_range; +}; + +#if IS_ENABLED(CONFIG_DPLL) +size_t dpll_msg_pin_handle_size(struct dpll_pin *pin); +int dpll_msg_add_pin_handle(struct sk_buff *msg, struct dpll_pin *pin); +#else +static inline size_t dpll_msg_pin_handle_size(struct dpll_pin *pin) +{ + return 0; +} + +static inline int dpll_msg_add_pin_handle(struct sk_buff *msg, struct dpll_pin *pin) +{ + return 0; +} +#endif + +struct dpll_device * +dpll_device_get(u64 clock_id, u32 dev_driver_id, struct module *module); + +void dpll_device_put(struct dpll_device *dpll); + +int dpll_device_register(struct dpll_device *dpll, enum dpll_type type, + const struct dpll_device_ops *ops, void *priv); + +void dpll_device_unregister(struct dpll_device *dpll, + const struct dpll_device_ops *ops, void *priv); + +struct dpll_pin * +dpll_pin_get(u64 clock_id, u32 dev_driver_id, struct module *module, + const struct dpll_pin_properties *prop); + +int dpll_pin_register(struct dpll_device *dpll, struct dpll_pin *pin, + const struct dpll_pin_ops *ops, void *priv); + +void dpll_pin_unregister(struct dpll_device *dpll, struct dpll_pin *pin, + const struct dpll_pin_ops *ops, void *priv); + +void dpll_pin_put(struct dpll_pin *pin); + +int dpll_pin_on_pin_register(struct dpll_pin *parent, struct dpll_pin *pin, + const struct dpll_pin_ops *ops, void *priv); + +void dpll_pin_on_pin_unregister(struct dpll_pin *parent, struct dpll_pin *pin, + const struct dpll_pin_ops *ops, void *priv); + +int dpll_device_change_ntf(struct dpll_device *dpll); + +int dpll_pin_change_ntf(struct dpll_pin *pin); + +#endif diff --git a/include/linux/dsa/sja1105.h b/include/linux/dsa/sja1105.h index c177322f793d..b9dd35d4b8f5 100644 --- a/include/linux/dsa/sja1105.h +++ b/include/linux/dsa/sja1105.h @@ -28,7 +28,7 @@ /* Source and Destination MAC of follow-up meta frames. * Whereas the choice of SMAC only affects the unique identification of the * switch as sender of meta frames, the DMAC must be an address that is present - * in the DSA master port's multicast MAC filter. + * in the DSA conduit port's multicast MAC filter. * 01-80-C2-00-00-0E is a good choice for this, as all profiles of IEEE 1588 * over L2 use this address for some purpose already. */ diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 62b61527bcc4..226a36ed5aa1 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -1052,4 +1052,23 @@ static inline int ethtool_mm_frag_size_min_to_add(u32 val_min, u32 *val_add, * next string. */ extern __printf(2, 3) void ethtool_sprintf(u8 **data, const char *fmt, ...); + +/* Link mode to forced speed capabilities maps */ +struct ethtool_forced_speed_map { + u32 speed; + __ETHTOOL_DECLARE_LINK_MODE_MASK(caps); + + const u32 *cap_arr; + u32 arr_size; +}; + +#define ETHTOOL_FORCED_SPEED_MAP(prefix, value) \ +{ \ + .speed = SPEED_##value, \ + .cap_arr = prefix##_##value, \ + .arr_size = ARRAY_SIZE(prefix##_##value), \ +} + +void +ethtool_forced_speed_maps_init(struct ethtool_forced_speed_map *maps, u32 size); #endif /* _LINUX_ETHTOOL_H */ diff --git a/include/linux/export-internal.h b/include/linux/export-internal.h index 1c849db953a5..45fca09b2319 100644 --- a/include/linux/export-internal.h +++ b/include/linux/export-internal.h @@ -52,6 +52,8 @@ #ifdef CONFIG_IA64 #define KSYM_FUNC(name) @fptr(name) +#elif defined(CONFIG_PARISC) && defined(CONFIG_64BIT) +#define KSYM_FUNC(name) P%name #else #define KSYM_FUNC(name) name #endif diff --git a/include/linux/exportfs.h b/include/linux/exportfs.h index 11fbd0ee1370..0388e8c20f52 100644 --- a/include/linux/exportfs.h +++ b/include/linux/exportfs.h @@ -105,6 +105,12 @@ enum fid_type { FILEID_LUSTRE = 0x97, /* + * 64 bit inode number, 32 bit subvolume, 32 bit generation number: + */ + FILEID_BCACHEFS_WITHOUT_PARENT = 0xb1, + FILEID_BCACHEFS_WITH_PARENT = 0xb2, + + /* * 64 bit unique kernfs id */ FILEID_KERNFS = 0xfe, @@ -224,9 +230,23 @@ struct export_operations { atomic attribute updates */ #define EXPORT_OP_FLUSH_ON_CLOSE (0x20) /* fs flushes file data on close */ +#define EXPORT_OP_ASYNC_LOCK (0x40) /* fs can do async lock request */ unsigned long flags; }; +/** + * exportfs_lock_op_is_async() - export op supports async lock operation + * @export_ops: the nfs export operations to check + * + * Returns true if the nfs export_operations structure has + * EXPORT_OP_ASYNC_LOCK in their flags set + */ +static inline bool +exportfs_lock_op_is_async(const struct export_operations *export_ops) +{ + return export_ops->flags & EXPORT_OP_ASYNC_LOCK; +} + extern int exportfs_encode_inode_fh(struct inode *inode, struct fid *fid, int *max_len, struct inode *parent, int flags); diff --git a/include/linux/fdtable.h b/include/linux/fdtable.h index e066816f3519..bc4c3287a65e 100644 --- a/include/linux/fdtable.h +++ b/include/linux/fdtable.h @@ -98,20 +98,9 @@ static inline struct file *files_lookup_fd_locked(struct files_struct *files, un return files_lookup_fd_raw(files, fd); } -static inline struct file *files_lookup_fd_rcu(struct files_struct *files, unsigned int fd) -{ - RCU_LOCKDEP_WARN(!rcu_read_lock_held(), - "suspicious rcu_dereference_check() usage"); - return files_lookup_fd_raw(files, fd); -} - -static inline struct file *lookup_fd_rcu(unsigned int fd) -{ - return files_lookup_fd_rcu(current->files, fd); -} - -struct file *task_lookup_fd_rcu(struct task_struct *task, unsigned int fd); -struct file *task_lookup_next_fd_rcu(struct task_struct *task, unsigned int *fd); +struct file *lookup_fdget_rcu(unsigned int fd); +struct file *task_lookup_fdget_rcu(struct task_struct *task, unsigned int fd); +struct file *task_lookup_next_fdget_rcu(struct task_struct *task, unsigned int *fd); struct task_struct; diff --git a/include/linux/filter.h b/include/linux/filter.h index 761af6b3cf2b..a4953fafc8cb 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -117,21 +117,25 @@ struct ctl_table_header; /* ALU ops on immediates, bpf_add|sub|...: dst_reg += imm32 */ -#define BPF_ALU64_IMM(OP, DST, IMM) \ +#define BPF_ALU64_IMM_OFF(OP, DST, IMM, OFF) \ ((struct bpf_insn) { \ .code = BPF_ALU64 | BPF_OP(OP) | BPF_K, \ .dst_reg = DST, \ .src_reg = 0, \ - .off = 0, \ + .off = OFF, \ .imm = IMM }) +#define BPF_ALU64_IMM(OP, DST, IMM) \ + BPF_ALU64_IMM_OFF(OP, DST, IMM, 0) -#define BPF_ALU32_IMM(OP, DST, IMM) \ +#define BPF_ALU32_IMM_OFF(OP, DST, IMM, OFF) \ ((struct bpf_insn) { \ .code = BPF_ALU | BPF_OP(OP) | BPF_K, \ .dst_reg = DST, \ .src_reg = 0, \ - .off = 0, \ + .off = OFF, \ .imm = IMM }) +#define BPF_ALU32_IMM(OP, DST, IMM) \ + BPF_ALU32_IMM_OFF(OP, DST, IMM, 0) /* Endianess conversion, cpu_to_{l,b}e(), {l,b}e_to_cpu() */ @@ -143,6 +147,16 @@ struct ctl_table_header; .off = 0, \ .imm = LEN }) +/* Byte Swap, bswap16/32/64 */ + +#define BPF_BSWAP(DST, LEN) \ + ((struct bpf_insn) { \ + .code = BPF_ALU64 | BPF_END | BPF_SRC(BPF_TO_LE), \ + .dst_reg = DST, \ + .src_reg = 0, \ + .off = 0, \ + .imm = LEN }) + /* Short form of mov, dst_reg = src_reg */ #define BPF_MOV64_REG(DST, SRC) \ @@ -179,6 +193,24 @@ struct ctl_table_header; .off = 0, \ .imm = IMM }) +/* Short form of movsx, dst_reg = (s8,s16,s32)src_reg */ + +#define BPF_MOVSX64_REG(DST, SRC, OFF) \ + ((struct bpf_insn) { \ + .code = BPF_ALU64 | BPF_MOV | BPF_X, \ + .dst_reg = DST, \ + .src_reg = SRC, \ + .off = OFF, \ + .imm = 0 }) + +#define BPF_MOVSX32_REG(DST, SRC, OFF) \ + ((struct bpf_insn) { \ + .code = BPF_ALU | BPF_MOV | BPF_X, \ + .dst_reg = DST, \ + .src_reg = SRC, \ + .off = OFF, \ + .imm = 0 }) + /* Special form of mov32, used for doing explicit zero extension on dst. */ #define BPF_ZEXT_REG(DST) \ ((struct bpf_insn) { \ @@ -263,6 +295,16 @@ static inline bool insn_is_zext(const struct bpf_insn *insn) .off = OFF, \ .imm = 0 }) +/* Memory load, dst_reg = *(signed size *) (src_reg + off16) */ + +#define BPF_LDX_MEMSX(SIZE, DST, SRC, OFF) \ + ((struct bpf_insn) { \ + .code = BPF_LDX | BPF_SIZE(SIZE) | BPF_MEMSX, \ + .dst_reg = DST, \ + .src_reg = SRC, \ + .off = OFF, \ + .imm = 0 }) + /* Memory store, *(uint *) (dst_reg + off16) = src_reg */ #define BPF_STX_MEM(SIZE, DST, SRC, OFF) \ @@ -694,7 +736,7 @@ static inline void bpf_compute_and_save_data_end( cb->data_end = skb->data + skb_headlen(skb); } -/* Restore data saved by bpf_compute_data_pointers(). */ +/* Restore data saved by bpf_compute_and_save_data_end(). */ static inline void bpf_restore_data_end( struct sk_buff *skb, void *saved_data_end) { @@ -912,6 +954,8 @@ bool bpf_jit_needs_zext(void); bool bpf_jit_supports_subprog_tailcalls(void); bool bpf_jit_supports_kfunc_call(void); bool bpf_jit_supports_far_kfunc_call(void); +bool bpf_jit_supports_exceptions(void); +void arch_bpf_stack_walk(bool (*consume_fn)(void *cookie, u64 ip, u64 sp, u64 bp), void *cookie); bool bpf_helper_changes_pkt_data(void *func); static inline bool bpf_dump_raw_ok(const struct cred *cred) @@ -981,12 +1025,6 @@ int xdp_do_redirect_frame(struct net_device *dev, struct bpf_prog *prog); void xdp_do_flush(void); -/* The xdp_do_flush_map() helper has been renamed to drop the _map suffix, as - * it is no longer only flushing maps. Keep this define for compatibility - * until all drivers are updated - do not use xdp_do_flush_map() in new code! - */ -#define xdp_do_flush_map xdp_do_flush - void bpf_warn_invalid_xdp_action(struct net_device *dev, struct bpf_prog *prog, u32 act); #ifdef CONFIG_INET @@ -1127,6 +1165,7 @@ const char *__bpf_address_lookup(unsigned long addr, unsigned long *size, bool is_bpf_text_address(unsigned long addr); int bpf_get_kallsym(unsigned int symnum, unsigned long *value, char *type, char *sym); +struct bpf_prog *bpf_prog_ksym_find(unsigned long addr); static inline const char * bpf_address_lookup(unsigned long addr, unsigned long *size, @@ -1194,6 +1233,11 @@ static inline int bpf_get_kallsym(unsigned int symnum, unsigned long *value, return -ERANGE; } +static inline struct bpf_prog *bpf_prog_ksym_find(unsigned long addr) +{ + return NULL; +} + static inline const char * bpf_address_lookup(unsigned long addr, unsigned long *size, unsigned long *off, char **modname, char *sym) @@ -1285,6 +1329,7 @@ struct bpf_sock_addr_kern { */ u64 tmp_reg; void *t_ctx; /* Attach type specific context. */ + u32 uaddrlen; }; struct bpf_sock_ops_kern { diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index e8b12ec8b060..d1ea3898564c 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -100,6 +100,18 @@ #define SD_ITAPDLY 0xFF180314 #define SD_OTAPDLYSEL 0xFF180318 +/** + * XPM_EVENT_ERROR_MASK_DDRMC_CR: Error event mask for DDRMC MC Correctable ECC Error. + */ +#define XPM_EVENT_ERROR_MASK_DDRMC_CR BIT(18) + +/** + * XPM_EVENT_ERROR_MASK_DDRMC_NCR: Error event mask for DDRMC MC Non-Correctable ECC Error. + */ +#define XPM_EVENT_ERROR_MASK_DDRMC_NCR BIT(19) +#define XPM_EVENT_ERROR_MASK_NOC_NCR BIT(13) +#define XPM_EVENT_ERROR_MASK_NOC_CR BIT(12) + enum pm_api_cb_id { PM_INIT_SUSPEND_CB = 30, PM_ACKNOWLEDGE_CB = 31, diff --git a/include/linux/fortify-string.h b/include/linux/fortify-string.h index da51a83b2829..1e7711185ec6 100644 --- a/include/linux/fortify-string.h +++ b/include/linux/fortify-string.h @@ -93,13 +93,9 @@ extern char *__underlying_strncpy(char *p, const char *q, __kernel_size_t size) #if __has_builtin(__builtin_dynamic_object_size) #define POS __pass_dynamic_object_size(1) #define POS0 __pass_dynamic_object_size(0) -#define __struct_size(p) __builtin_dynamic_object_size(p, 0) -#define __member_size(p) __builtin_dynamic_object_size(p, 1) #else #define POS __pass_object_size(1) #define POS0 __pass_object_size(0) -#define __struct_size(p) __builtin_object_size(p, 0) -#define __member_size(p) __builtin_object_size(p, 1) #endif #define __compiletime_lessthan(bounds, length) ( \ diff --git a/include/linux/fs.h b/include/linux/fs.h index 4aeb3fa11927..c27c324ba58a 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -67,7 +67,7 @@ struct swap_info_struct; struct seq_file; struct workqueue_struct; struct iov_iter; -struct fscrypt_info; +struct fscrypt_inode_info; struct fscrypt_operations; struct fsverity_info; struct fsverity_operations; @@ -671,8 +671,8 @@ struct inode { }; dev_t i_rdev; loff_t i_size; - struct timespec64 i_atime; - struct timespec64 i_mtime; + struct timespec64 __i_atime; + struct timespec64 __i_mtime; struct timespec64 __i_ctime; /* use inode_*_ctime accessors! */ spinlock_t i_lock; /* i_blocks, i_bytes, maybe i_size */ unsigned short i_bytes; @@ -738,7 +738,7 @@ struct inode { #endif #ifdef CONFIG_FS_ENCRYPTION - struct fscrypt_info *i_crypt_info; + struct fscrypt_inode_info *i_crypt_info; #endif #ifdef CONFIG_FS_VERITY @@ -1042,7 +1042,10 @@ static inline struct file *get_file(struct file *f) atomic_long_inc(&f->f_count); return f; } -#define get_file_rcu(x) atomic_long_inc_not_zero(&(x)->f_count) + +struct file *get_file_rcu(struct file __rcu **f); +struct file *get_file_active(struct file **f); + #define file_count(x) atomic_long_read(&(x)->f_count) #define MAX_NON_LFS ((1UL<<31) - 1) @@ -1119,7 +1122,7 @@ extern int send_sigurg(struct fown_struct *fown); #define SB_NOATIME BIT(10) /* Do not update access times. */ #define SB_NODIRATIME BIT(11) /* Do not update directory access times */ #define SB_SILENT BIT(15) -#define SB_POSIXACL BIT(16) /* VFS does not apply the umask */ +#define SB_POSIXACL BIT(16) /* Supports POSIX ACLs */ #define SB_INLINECRYPT BIT(17) /* Use blk-crypto for encrypted files */ #define SB_KERNMOUNT BIT(22) /* this is a kern_mount call */ #define SB_I_VERSION BIT(23) /* Update inode I_version field */ @@ -1166,6 +1169,7 @@ extern int send_sigurg(struct fown_struct *fown); #define SB_I_PERSB_BDI 0x00000200 /* has a per-sb bdi */ #define SB_I_TS_EXPIRY_WARNED 0x00000400 /* warned about timestamp range expiry */ #define SB_I_RETIRED 0x00000800 /* superblock shouldn't be reused */ +#define SB_I_NOUMASK 0x00001000 /* VFS does not apply umask */ /* Possible states of 'frozen' field */ enum { @@ -1206,7 +1210,7 @@ struct super_block { #ifdef CONFIG_SECURITY void *s_security; #endif - const struct xattr_handler **s_xattr; + const struct xattr_handler * const *s_xattr; #ifdef CONFIG_FS_ENCRYPTION const struct fscrypt_operations *s_cop; struct fscrypt_keyring *s_master_keys; /* master crypto keys in use */ @@ -1221,6 +1225,7 @@ struct super_block { struct hlist_bl_head s_roots; /* alternate root dentries for NFS */ struct list_head s_mounts; /* list of mounts; _not_ for fs use */ struct block_device *s_bdev; + struct bdev_handle *s_bdev_handle; struct backing_dev_info *s_bdi; struct mtd_info *s_mtd; struct hlist_node s_instances; @@ -1508,56 +1513,84 @@ static inline bool fsuidgid_has_mapping(struct super_block *sb, kgid_has_mapping(fs_userns, kgid); } -struct timespec64 current_mgtime(struct inode *inode); struct timespec64 current_time(struct inode *inode); struct timespec64 inode_set_ctime_current(struct inode *inode); -/* - * Multigrain timestamps - * - * Conditionally use fine-grained ctime and mtime timestamps when there - * are users actively observing them via getattr. The primary use-case - * for this is NFS clients that use the ctime to distinguish between - * different states of the file, and that are often fooled by multiple - * operations that occur in the same coarse-grained timer tick. - * - * The kernel always keeps normalized struct timespec64 values in the ctime, - * which means that only the first 30 bits of the value are used. Use the - * 31st bit of the ctime's tv_nsec field as a flag to indicate that the value - * has been queried since it was last updated. - */ -#define I_CTIME_QUERIED (1L<<30) +static inline time64_t inode_get_atime_sec(const struct inode *inode) +{ + return inode->__i_atime.tv_sec; +} -/** - * inode_get_ctime - fetch the current ctime from the inode - * @inode: inode from which to fetch ctime - * - * Grab the current ctime tv_nsec field from the inode, mask off the - * I_CTIME_QUERIED flag and return it. This is mostly intended for use by - * internal consumers of the ctime that aren't concerned with ensuring a - * fine-grained update on the next change (e.g. when preparing to store - * the value in the backing store for later retrieval). - * - * This is safe to call regardless of whether the underlying filesystem - * is using multigrain timestamps. - */ -static inline struct timespec64 inode_get_ctime(const struct inode *inode) +static inline long inode_get_atime_nsec(const struct inode *inode) +{ + return inode->__i_atime.tv_nsec; +} + +static inline struct timespec64 inode_get_atime(const struct inode *inode) +{ + return inode->__i_atime; +} + +static inline struct timespec64 inode_set_atime_to_ts(struct inode *inode, + struct timespec64 ts) { - struct timespec64 ctime; + inode->__i_atime = ts; + return ts; +} + +static inline struct timespec64 inode_set_atime(struct inode *inode, + time64_t sec, long nsec) +{ + struct timespec64 ts = { .tv_sec = sec, + .tv_nsec = nsec }; + return inode_set_atime_to_ts(inode, ts); +} - ctime.tv_sec = inode->__i_ctime.tv_sec; - ctime.tv_nsec = inode->__i_ctime.tv_nsec & ~I_CTIME_QUERIED; +static inline time64_t inode_get_mtime_sec(const struct inode *inode) +{ + return inode->__i_mtime.tv_sec; +} - return ctime; +static inline long inode_get_mtime_nsec(const struct inode *inode) +{ + return inode->__i_mtime.tv_nsec; +} + +static inline struct timespec64 inode_get_mtime(const struct inode *inode) +{ + return inode->__i_mtime; +} + +static inline struct timespec64 inode_set_mtime_to_ts(struct inode *inode, + struct timespec64 ts) +{ + inode->__i_mtime = ts; + return ts; +} + +static inline struct timespec64 inode_set_mtime(struct inode *inode, + time64_t sec, long nsec) +{ + struct timespec64 ts = { .tv_sec = sec, + .tv_nsec = nsec }; + return inode_set_mtime_to_ts(inode, ts); +} + +static inline time64_t inode_get_ctime_sec(const struct inode *inode) +{ + return inode->__i_ctime.tv_sec; +} + +static inline long inode_get_ctime_nsec(const struct inode *inode) +{ + return inode->__i_ctime.tv_nsec; +} + +static inline struct timespec64 inode_get_ctime(const struct inode *inode) +{ + return inode->__i_ctime; } -/** - * inode_set_ctime_to_ts - set the ctime in the inode - * @inode: inode in which to set the ctime - * @ts: value to set in the ctime field - * - * Set the ctime in @inode to @ts - */ static inline struct timespec64 inode_set_ctime_to_ts(struct inode *inode, struct timespec64 ts) { @@ -1582,6 +1615,8 @@ static inline struct timespec64 inode_set_ctime(struct inode *inode, return inode_set_ctime_to_ts(inode, ts); } +struct timespec64 simple_inode_init_ts(struct inode *inode); + /* * Snapshotting support. */ @@ -2110,7 +2145,12 @@ static inline bool sb_rdonly(const struct super_block *sb) { return sb->s_flags #define IS_NOQUOTA(inode) ((inode)->i_flags & S_NOQUOTA) #define IS_APPEND(inode) ((inode)->i_flags & S_APPEND) #define IS_IMMUTABLE(inode) ((inode)->i_flags & S_IMMUTABLE) + +#ifdef CONFIG_FS_POSIX_ACL #define IS_POSIXACL(inode) __IS_FLG(inode, SB_POSIXACL) +#else +#define IS_POSIXACL(inode) 0 +#endif #define IS_DEADDIR(inode) ((inode)->i_flags & S_DEAD) #define IS_NOCMTIME(inode) ((inode)->i_flags & S_NOCMTIME) @@ -2334,7 +2374,6 @@ struct file_system_type { #define FS_USERNS_MOUNT 8 /* Can be mounted by userns root */ #define FS_DISALLOW_NOTIFY_PERM 16 /* Disable fanotify permission events */ #define FS_ALLOW_IDMAP 32 /* FS has been updated to handle vfs idmappings. */ -#define FS_MGTIME 64 /* FS uses multigrain timestamps */ #define FS_RENAME_DOES_D_MOVE 32768 /* FS will handle d_move() during rename() internally. */ int (*init_fs_context)(struct fs_context *); const struct fs_parameter_spec *parameters; @@ -2358,17 +2397,6 @@ struct file_system_type { #define MODULE_ALIAS_FS(NAME) MODULE_ALIAS("fs-" NAME) -/** - * is_mgtime: is this inode using multigrain timestamps - * @inode: inode to test for multigrain timestamps - * - * Return true if the inode uses multigrain timestamps, false otherwise. - */ -static inline bool is_mgtime(const struct inode *inode) -{ - return inode->i_sb->s_type->fs_flags & FS_MGTIME; -} - extern struct dentry *mount_bdev(struct file_system_type *fs_type, int flags, const char *dev_name, void *data, int (*fill_super)(struct super_block *, void *, int)); @@ -2444,13 +2472,13 @@ struct audit_names; struct filename { const char *name; /* pointer to actual string */ const __user char *uptr; /* original userland pointer */ - int refcnt; + atomic_t refcnt; struct audit_names *aname; const char iname[]; }; static_assert(offsetof(struct filename, iname) % sizeof(long) == 0); -static inline struct mnt_idmap *file_mnt_idmap(struct file *file) +static inline struct mnt_idmap *file_mnt_idmap(const struct file *file) { return mnt_idmap(file->f_path.mnt); } @@ -2489,24 +2517,24 @@ struct file *dentry_open(const struct path *path, int flags, const struct cred *creds); struct file *dentry_create(const struct path *path, int flags, umode_t mode, const struct cred *cred); -struct file *backing_file_open(const struct path *path, int flags, +struct file *backing_file_open(const struct path *user_path, int flags, const struct path *real_path, const struct cred *cred); -struct path *backing_file_real_path(struct file *f); +struct path *backing_file_user_path(struct file *f); /* - * file_real_path - get the path corresponding to f_inode + * file_user_path - get the path to display for memory mapped file * - * When opening a backing file for a stackable filesystem (e.g., - * overlayfs) f_path may be on the stackable filesystem and f_inode on - * the underlying filesystem. When the path associated with f_inode is - * needed, this helper should be used instead of accessing f_path - * directly. -*/ -static inline const struct path *file_real_path(struct file *f) + * When mmapping a file on a stackable filesystem (e.g., overlayfs), the file + * stored in ->vm_file is a backing file whose f_inode is on the underlying + * filesystem. When the mapped file path is displayed to user (e.g. via + * /proc/<pid>/maps), this helper should be used to get the path to display + * to the user, which is the path of the fd that user has requested to map. + */ +static inline const struct path *file_user_path(struct file *f) { if (unlikely(f->f_mode & FMODE_BACKING)) - return backing_file_real_path(f); + return backing_file_user_path(f); return &f->f_path; } @@ -3054,7 +3082,6 @@ extern void page_put_link(void *); extern int page_symlink(struct inode *inode, const char *symname, int len); extern const struct inode_operations page_symlink_inode_operations; extern void kfree_link(void *); -void fill_mg_cmtime(struct kstat *stat, u32 request_mask, struct inode *inode); void generic_fillattr(struct mnt_idmap *, u32, struct inode *, struct kstat *); void generic_fill_statx_attr(struct inode *inode, struct kstat *stat); extern int vfs_getattr_nosec(const struct path *, struct kstat *, u32, unsigned int); diff --git a/include/linux/fs_context.h b/include/linux/fs_context.h index 96332db693d5..c13e99cbbf81 100644 --- a/include/linux/fs_context.h +++ b/include/linux/fs_context.h @@ -136,6 +136,8 @@ extern struct fs_context *vfs_dup_fs_context(struct fs_context *fc); extern int vfs_parse_fs_param(struct fs_context *fc, struct fs_parameter *param); extern int vfs_parse_fs_string(struct fs_context *fc, const char *key, const char *value, size_t v_size); +int vfs_parse_monolithic_sep(struct fs_context *fc, void *data, + char *(*sep)(char **)); extern int generic_parse_monolithic(struct fs_context *fc, void *data); extern int vfs_get_tree(struct fs_context *fc); extern void put_fs_context(struct fs_context *fc); diff --git a/include/linux/fs_stack.h b/include/linux/fs_stack.h index 010d39d0dc1c..2b1f74b24070 100644 --- a/include/linux/fs_stack.h +++ b/include/linux/fs_stack.h @@ -16,14 +16,14 @@ extern void fsstack_copy_inode_size(struct inode *dst, struct inode *src); static inline void fsstack_copy_attr_atime(struct inode *dest, const struct inode *src) { - dest->i_atime = src->i_atime; + inode_set_atime_to_ts(dest, inode_get_atime(src)); } static inline void fsstack_copy_attr_times(struct inode *dest, const struct inode *src) { - dest->i_atime = src->i_atime; - dest->i_mtime = src->i_mtime; + inode_set_atime_to_ts(dest, inode_get_atime(src)); + inode_set_mtime_to_ts(dest, inode_get_mtime(src)); inode_set_ctime_to_ts(dest, inode_get_ctime(src)); } diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h index c895b12737a1..12f9e455d569 100644 --- a/include/linux/fscrypt.h +++ b/include/linux/fscrypt.h @@ -31,7 +31,7 @@ #define FSCRYPT_CONTENTS_ALIGNMENT 16 union fscrypt_policy; -struct fscrypt_info; +struct fscrypt_inode_info; struct fs_parameter; struct seq_file; @@ -59,26 +59,55 @@ struct fscrypt_name { #ifdef CONFIG_FS_ENCRYPTION -/* - * If set, the fscrypt bounce page pool won't be allocated (unless another - * filesystem needs it). Set this if the filesystem always uses its own bounce - * pages for writes and therefore won't need the fscrypt bounce page pool. - */ -#define FS_CFLG_OWN_PAGES (1U << 1) - /* Crypto operations for filesystems */ struct fscrypt_operations { - /* Set of optional flags; see above for allowed flags */ - unsigned int flags; + /* + * If set, then fs/crypto/ will allocate a global bounce page pool the + * first time an encryption key is set up for a file. The bounce page + * pool is required by the following functions: + * + * - fscrypt_encrypt_pagecache_blocks() + * - fscrypt_zeroout_range() for files not using inline crypto + * + * If the filesystem doesn't use those, it doesn't need to set this. + */ + unsigned int needs_bounce_pages : 1; /* - * If set, this is a filesystem-specific key description prefix that - * will be accepted for "logon" keys for v1 fscrypt policies, in - * addition to the generic prefix "fscrypt:". This functionality is - * deprecated, so new filesystems shouldn't set this field. + * If set, then fs/crypto/ will allow the use of encryption settings + * that assume inode numbers fit in 32 bits (i.e. + * FSCRYPT_POLICY_FLAG_IV_INO_LBLK_{32,64}), provided that the other + * prerequisites for these settings are also met. This is only useful + * if the filesystem wants to support inline encryption hardware that is + * limited to 32-bit or 64-bit data unit numbers and where programming + * keyslots is very slow. */ - const char *key_prefix; + unsigned int has_32bit_inodes : 1; + + /* + * If set, then fs/crypto/ will allow users to select a crypto data unit + * size that is less than the filesystem block size. This is done via + * the log2_data_unit_size field of the fscrypt policy. This flag is + * not compatible with filesystems that encrypt variable-length blocks + * (i.e. blocks that aren't all equal to filesystem's block size), for + * example as a result of compression. It's also not compatible with + * the fscrypt_encrypt_block_inplace() and + * fscrypt_decrypt_block_inplace() functions. + */ + unsigned int supports_subblock_data_units : 1; + + /* + * This field exists only for backwards compatibility reasons and should + * only be set by the filesystems that are setting it already. It + * contains the filesystem-specific key description prefix that is + * accepted for "logon" keys for v1 fscrypt policies. This + * functionality is deprecated in favor of the generic prefix + * "fscrypt:", which itself is deprecated in favor of the filesystem + * keyring ioctls such as FS_IOC_ADD_ENCRYPTION_KEY. Filesystems that + * are newly adding fscrypt support should not set this field. + */ + const char *legacy_key_prefix; /* * Get the fscrypt context of the given inode. @@ -146,21 +175,6 @@ struct fscrypt_operations { bool (*has_stable_inodes)(struct super_block *sb); /* - * Get the number of bits that the filesystem uses to represent inode - * numbers and file logical block numbers. - * - * By default, both of these are assumed to be 64-bit. This function - * can be implemented to declare that either or both of these numbers is - * shorter, which may allow the use of the - * FSCRYPT_POLICY_FLAG_IV_INO_LBLK_{32,64} flags and/or the use of - * inline crypto hardware whose maximum DUN length is less than 64 bits - * (e.g., eMMC v5.2 spec compliant hardware). This function only needs - * to be implemented if support for one of these features is needed. - */ - void (*get_ino_and_lblk_bits)(struct super_block *sb, - int *ino_bits_ret, int *lblk_bits_ret); - - /* * Return an array of pointers to the block devices to which the * filesystem may write encrypted file contents, NULL if the filesystem * only has a single such block device, or an ERR_PTR() on error. @@ -178,7 +192,8 @@ struct fscrypt_operations { unsigned int *num_devs); }; -static inline struct fscrypt_info *fscrypt_get_info(const struct inode *inode) +static inline struct fscrypt_inode_info * +fscrypt_get_inode_info(const struct inode *inode) { /* * Pairs with the cmpxchg_release() in fscrypt_setup_encryption_info(). @@ -390,7 +405,8 @@ static inline void fscrypt_set_ops(struct super_block *sb, } #else /* !CONFIG_FS_ENCRYPTION */ -static inline struct fscrypt_info *fscrypt_get_info(const struct inode *inode) +static inline struct fscrypt_inode_info * +fscrypt_get_inode_info(const struct inode *inode) { return NULL; } @@ -868,7 +884,7 @@ static inline bool fscrypt_inode_uses_fs_layer_crypto(const struct inode *inode) */ static inline bool fscrypt_has_encryption_key(const struct inode *inode) { - return fscrypt_get_info(inode) != NULL; + return fscrypt_get_inode_info(inode) != NULL; } /** diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h index ed48e4f1e755..bcb6609b54b3 100644 --- a/include/linux/fsnotify.h +++ b/include/linux/fsnotify.h @@ -96,8 +96,7 @@ static inline int fsnotify_file(struct file *file, __u32 mask) if (file->f_mode & FMODE_NONOTIFY) return 0; - /* Overlayfs internal files have fake f_path */ - path = file_real_path(file); + path = &file->f_path; return fsnotify_parent(path->dentry, mask, path, FSNOTIFY_EVENT_PATH); } diff --git a/include/linux/generic-radix-tree.h b/include/linux/generic-radix-tree.h index 107613f7d792..847413164738 100644 --- a/include/linux/generic-radix-tree.h +++ b/include/linux/generic-radix-tree.h @@ -38,6 +38,7 @@ #include <asm/page.h> #include <linux/bug.h> +#include <linux/limits.h> #include <linux/log2.h> #include <linux/math.h> #include <linux/types.h> @@ -116,6 +117,11 @@ static inline size_t __idx_to_offset(size_t idx, size_t obj_size) #define __genradix_cast(_radix) (typeof((_radix)->type[0]) *) #define __genradix_obj_size(_radix) sizeof((_radix)->type[0]) +#define __genradix_objs_per_page(_radix) \ + (PAGE_SIZE / sizeof((_radix)->type[0])) +#define __genradix_page_remainder(_radix) \ + (PAGE_SIZE % sizeof((_radix)->type[0])) + #define __genradix_idx_to_offset(_radix, _idx) \ __idx_to_offset(_idx, __genradix_obj_size(_radix)) @@ -179,11 +185,35 @@ void *__genradix_iter_peek(struct genradix_iter *, struct __genradix *, size_t); #define genradix_iter_peek(_iter, _radix) \ (__genradix_cast(_radix) \ __genradix_iter_peek(_iter, &(_radix)->tree, \ - PAGE_SIZE / __genradix_obj_size(_radix))) + __genradix_objs_per_page(_radix))) + +void *__genradix_iter_peek_prev(struct genradix_iter *, struct __genradix *, + size_t, size_t); + +/** + * genradix_iter_peek_prev - get first entry at or below iterator's current + * position + * @_iter: a genradix_iter + * @_radix: genradix being iterated over + * + * If no more entries exist at or below @_iter's current position, returns NULL + */ +#define genradix_iter_peek_prev(_iter, _radix) \ + (__genradix_cast(_radix) \ + __genradix_iter_peek_prev(_iter, &(_radix)->tree, \ + __genradix_objs_per_page(_radix), \ + __genradix_obj_size(_radix) + \ + __genradix_page_remainder(_radix))) static inline void __genradix_iter_advance(struct genradix_iter *iter, size_t obj_size) { + if (iter->offset + obj_size < iter->offset) { + iter->offset = SIZE_MAX; + iter->pos = SIZE_MAX; + return; + } + iter->offset += obj_size; if (!is_power_of_2(obj_size) && @@ -196,6 +226,25 @@ static inline void __genradix_iter_advance(struct genradix_iter *iter, #define genradix_iter_advance(_iter, _radix) \ __genradix_iter_advance(_iter, __genradix_obj_size(_radix)) +static inline void __genradix_iter_rewind(struct genradix_iter *iter, + size_t obj_size) +{ + if (iter->offset == 0 || + iter->offset == SIZE_MAX) { + iter->offset = SIZE_MAX; + return; + } + + if ((iter->offset & (PAGE_SIZE - 1)) == 0) + iter->offset -= PAGE_SIZE % obj_size; + + iter->offset -= obj_size; + iter->pos--; +} + +#define genradix_iter_rewind(_iter, _radix) \ + __genradix_iter_rewind(_iter, __genradix_obj_size(_radix)) + #define genradix_for_each_from(_radix, _iter, _p, _start) \ for (_iter = genradix_iter_init(_radix, _start); \ (_p = genradix_iter_peek(&_iter, _radix)) != NULL; \ @@ -213,6 +262,23 @@ static inline void __genradix_iter_advance(struct genradix_iter *iter, #define genradix_for_each(_radix, _iter, _p) \ genradix_for_each_from(_radix, _iter, _p, 0) +#define genradix_last_pos(_radix) \ + (SIZE_MAX / PAGE_SIZE * __genradix_objs_per_page(_radix) - 1) + +/** + * genradix_for_each_reverse - iterate over entry in a genradix, reverse order + * @_radix: genradix to iterate over + * @_iter: a genradix_iter to track current position + * @_p: pointer to genradix entry type + * + * On every iteration, @_p will point to the current entry, and @_iter.pos + * will be the current entry's index. + */ +#define genradix_for_each_reverse(_radix, _iter, _p) \ + for (_iter = genradix_iter_init(_radix, genradix_last_pos(_radix));\ + (_p = genradix_iter_peek_prev(&_iter, _radix)) != NULL;\ + genradix_iter_rewind(&_iter, _radix)) + int __genradix_prealloc(struct __genradix *, size_t, gfp_t); /** diff --git a/include/linux/gpio/consumer.h b/include/linux/gpio/consumer.h index 1c4385a00f88..db2dfbae8edb 100644 --- a/include/linux/gpio/consumer.h +++ b/include/linux/gpio/consumer.h @@ -159,7 +159,6 @@ int gpiod_set_raw_array_value_cansleep(unsigned int array_size, int gpiod_set_config(struct gpio_desc *desc, unsigned long config); int gpiod_set_debounce(struct gpio_desc *desc, unsigned int debounce); -int gpiod_set_transitory(struct gpio_desc *desc, bool transitory); void gpiod_toggle_active_low(struct gpio_desc *desc); int gpiod_is_active_low(const struct gpio_desc *desc); @@ -494,13 +493,6 @@ static inline int gpiod_set_debounce(struct gpio_desc *desc, unsigned int deboun return -ENOSYS; } -static inline int gpiod_set_transitory(struct gpio_desc *desc, bool transitory) -{ - /* GPIO can never have been requested */ - WARN_ON(desc); - return -ENOSYS; -} - static inline void gpiod_toggle_active_low(struct gpio_desc *desc) { /* GPIO can never have been requested */ @@ -614,8 +606,6 @@ void acpi_dev_remove_driver_gpios(struct acpi_device *adev); int devm_acpi_dev_add_driver_gpios(struct device *dev, const struct acpi_gpio_mapping *gpios); -struct gpio_desc *acpi_get_and_request_gpiod(char *path, unsigned int pin, char *label); - #else /* CONFIG_GPIOLIB && CONFIG_ACPI */ #include <linux/err.h> @@ -633,12 +623,6 @@ static inline int devm_acpi_dev_add_driver_gpios(struct device *dev, return -ENXIO; } -static inline struct gpio_desc *acpi_get_and_request_gpiod(char *path, unsigned int pin, - char *label) -{ - return ERR_PTR(-ENOSYS); -} - #endif /* CONFIG_GPIOLIB && CONFIG_ACPI */ diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index 4f0c5d62c8f3..1d454dc944b3 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -3,6 +3,8 @@ #define __LINUX_GPIO_DRIVER_H #include <linux/bits.h> +#include <linux/cleanup.h> +#include <linux/err.h> #include <linux/irqchip/chained_irq.h> #include <linux/irqdomain.h> #include <linux/irqhandler.h> @@ -529,8 +531,7 @@ struct gpio_chip { #endif /* CONFIG_OF_GPIO */ }; -extern const char *gpiochip_is_requested(struct gpio_chip *gc, - unsigned int offset); +const char *gpiochip_is_requested(struct gpio_chip *gc, unsigned int offset); /** * for_each_requested_gpio_in_range - iterates over requested GPIOs in a given range @@ -549,9 +550,9 @@ extern const char *gpiochip_is_requested(struct gpio_chip *gc, for_each_requested_gpio_in_range(chip, i, 0, chip->ngpio, label) /* add/remove chips */ -extern int gpiochip_add_data_with_key(struct gpio_chip *gc, void *data, - struct lock_class_key *lock_key, - struct lock_class_key *request_key); +int gpiochip_add_data_with_key(struct gpio_chip *gc, void *data, + struct lock_class_key *lock_key, + struct lock_class_key *request_key); /** * gpiochip_add_data() - register a gpio_chip @@ -599,13 +600,26 @@ static inline int gpiochip_add(struct gpio_chip *gc) { return gpiochip_add_data(gc, NULL); } -extern void gpiochip_remove(struct gpio_chip *gc); -extern int devm_gpiochip_add_data_with_key(struct device *dev, struct gpio_chip *gc, void *data, - struct lock_class_key *lock_key, - struct lock_class_key *request_key); +void gpiochip_remove(struct gpio_chip *gc); +int devm_gpiochip_add_data_with_key(struct device *dev, struct gpio_chip *gc, + void *data, struct lock_class_key *lock_key, + struct lock_class_key *request_key); + +struct gpio_chip *gpiochip_find(void *data, + int (*match)(struct gpio_chip *gc, void *data)); + +struct gpio_device *gpio_device_find(void *data, + int (*match)(struct gpio_chip *gc, void *data)); +struct gpio_device *gpio_device_find_by_label(const char *label); +struct gpio_device *gpio_device_find_by_fwnode(const struct fwnode_handle *fwnode); + +struct gpio_device *gpio_device_get(struct gpio_device *gdev); +void gpio_device_put(struct gpio_device *gdev); + +DEFINE_FREE(gpio_device_put, struct gpio_device *, + if (IS_ERR_OR_NULL(_T)) gpio_device_put(_T)); -extern struct gpio_chip *gpiochip_find(void *data, - int (*match)(struct gpio_chip *gc, void *data)); +struct device *gpio_device_to_device(struct gpio_device *gdev); bool gpiochip_line_is_irq(struct gpio_chip *gc, unsigned int offset); int gpiochip_reqres_irq(struct gpio_chip *gc, unsigned int offset); @@ -758,14 +772,23 @@ struct gpio_desc *gpiochip_request_own_desc(struct gpio_chip *gc, enum gpiod_flags dflags); void gpiochip_free_own_desc(struct gpio_desc *desc); +struct gpio_desc *gpiochip_get_desc(struct gpio_chip *gc, unsigned int hwnum); +struct gpio_desc * +gpio_device_get_desc(struct gpio_device *gdev, unsigned int hwnum); + +struct gpio_chip *gpio_device_get_chip(struct gpio_device *gdev); + #ifdef CONFIG_GPIOLIB /* lock/unlock as IRQ */ int gpiochip_lock_as_irq(struct gpio_chip *gc, unsigned int offset); void gpiochip_unlock_as_irq(struct gpio_chip *gc, unsigned int offset); - struct gpio_chip *gpiod_to_chip(const struct gpio_desc *desc); +struct gpio_device *gpiod_to_gpio_device(struct gpio_desc *desc); + +/* struct gpio_device getters */ +int gpio_device_get_base(struct gpio_device *gdev); #else /* CONFIG_GPIOLIB */ diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 5b2626063f4f..47d25a5e1933 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -60,6 +60,7 @@ struct resv_map { long adds_in_progress; struct list_head region_cache; long region_cache_count; + struct rw_semaphore rw_sema; #ifdef CONFIG_CGROUP_HUGETLB /* * On private mappings, the counter to uncharge reservations is stored @@ -138,7 +139,7 @@ struct page *hugetlb_follow_page_mask(struct vm_area_struct *vma, void unmap_hugepage_range(struct vm_area_struct *, unsigned long, unsigned long, struct page *, zap_flags_t); -void __unmap_hugepage_range_final(struct mmu_gather *tlb, +void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long start, unsigned long end, struct page *ref_page, zap_flags_t zap_flags); @@ -245,6 +246,25 @@ int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma, void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma, unsigned long *start, unsigned long *end); +extern void __hugetlb_zap_begin(struct vm_area_struct *vma, + unsigned long *begin, unsigned long *end); +extern void __hugetlb_zap_end(struct vm_area_struct *vma, + struct zap_details *details); + +static inline void hugetlb_zap_begin(struct vm_area_struct *vma, + unsigned long *start, unsigned long *end) +{ + if (is_vm_hugetlb_page(vma)) + __hugetlb_zap_begin(vma, start, end); +} + +static inline void hugetlb_zap_end(struct vm_area_struct *vma, + struct zap_details *details) +{ + if (is_vm_hugetlb_page(vma)) + __hugetlb_zap_end(vma, details); +} + void hugetlb_vma_lock_read(struct vm_area_struct *vma); void hugetlb_vma_unlock_read(struct vm_area_struct *vma); void hugetlb_vma_lock_write(struct vm_area_struct *vma); @@ -296,6 +316,18 @@ static inline void adjust_range_if_pmd_sharing_possible( { } +static inline void hugetlb_zap_begin( + struct vm_area_struct *vma, + unsigned long *start, unsigned long *end) +{ +} + +static inline void hugetlb_zap_end( + struct vm_area_struct *vma, + struct zap_details *details) +{ +} + static inline struct page *hugetlb_follow_page_mask( struct vm_area_struct *vma, unsigned long address, unsigned int flags, unsigned int *page_mask) @@ -441,7 +473,7 @@ static inline long hugetlb_change_protection( return 0; } -static inline void __unmap_hugepage_range_final(struct mmu_gather *tlb, +static inline void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long start, unsigned long end, struct page *ref_page, zap_flags_t zap_flags) @@ -984,7 +1016,9 @@ static inline void huge_ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, pte_t old_pte, pte_t pte) { - set_huge_pte_at(vma->vm_mm, addr, ptep, pte); + unsigned long psize = huge_page_size(hstate_vma(vma)); + + set_huge_pte_at(vma->vm_mm, addr, ptep, pte, psize); } #endif @@ -1173,7 +1207,7 @@ static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma, } static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, - pte_t *ptep, pte_t pte) + pte_t *ptep, pte_t pte, unsigned long sz) { } @@ -1231,6 +1265,11 @@ static inline bool __vma_shareable_lock(struct vm_area_struct *vma) return (vma->vm_flags & VM_MAYSHARE) && vma->vm_private_data; } +static inline bool __vma_private_lock(struct vm_area_struct *vma) +{ + return (!(vma->vm_flags & VM_MAYSHARE)) && vma->vm_private_data; +} + /* * Safe version of huge_pte_offset() to check the locks. See comments * above huge_pte_offset(). diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 3430cc2b05a6..0dae9db27538 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -237,7 +237,6 @@ enum i2c_driver_flags { * struct i2c_driver - represent an I2C device driver * @class: What kind of i2c device we instantiate (for detect) * @probe: Callback for device binding - * @probe_new: Transitional callback for device binding - do not use * @remove: Callback for device unbinding * @shutdown: Callback for device shutdown * @alert: Alert callback, for example for the SMBus alert protocol @@ -272,16 +271,8 @@ enum i2c_driver_flags { struct i2c_driver { unsigned int class; - union { /* Standard driver model interfaces */ - int (*probe)(struct i2c_client *client); - /* - * Legacy callback that was part of a conversion of .probe(). - * Today it has the same semantic as .probe(). Don't use for new - * code. - */ - int (*probe_new)(struct i2c_client *client); - }; + int (*probe)(struct i2c_client *client); void (*remove)(struct i2c_client *client); diff --git a/include/linux/i3c/master.h b/include/linux/i3c/master.h index 0b52da4f2346..db909ef79be4 100644 --- a/include/linux/i3c/master.h +++ b/include/linux/i3c/master.h @@ -24,6 +24,12 @@ struct i2c_client; +/* notifier actions. notifier call data is the struct i3c_bus */ +enum { + I3C_NOTIFY_BUS_ADD, + I3C_NOTIFY_BUS_REMOVE, +}; + struct i3c_master_controller; struct i3c_bus; struct i3c_device; @@ -652,4 +658,9 @@ void i3c_master_queue_ibi(struct i3c_dev_desc *dev, struct i3c_ibi_slot *slot); struct i3c_ibi_slot *i3c_master_get_free_ibi_slot(struct i3c_dev_desc *dev); +void i3c_for_each_bus_locked(int (*fn)(struct i3c_bus *bus, void *data), + void *data); +int i3c_register_notifier(struct notifier_block *nb); +int i3c_unregister_notifier(struct notifier_block *nb); + #endif /* I3C_MASTER_H */ diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index bd2f6e19c357..958771bac9c0 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -307,6 +307,13 @@ static inline u16 ieee80211_sn_sub(u16 sn1, u16 sn2) #define IEEE80211_TRIGGER_TYPE_BQRP 0x6 #define IEEE80211_TRIGGER_TYPE_NFRP 0x7 +/* UL-bandwidth within common_info of trigger frame */ +#define IEEE80211_TRIGGER_ULBW_MASK 0xc0000 +#define IEEE80211_TRIGGER_ULBW_20MHZ 0x0 +#define IEEE80211_TRIGGER_ULBW_40MHZ 0x1 +#define IEEE80211_TRIGGER_ULBW_80MHZ 0x2 +#define IEEE80211_TRIGGER_ULBW_160_80P80MHZ 0x3 + struct ieee80211_hdr { __le16 frame_control; __le16 duration_id; @@ -951,17 +958,24 @@ struct ieee80211_wide_bw_chansw_ie { * @dtim_count: DTIM Count * @dtim_period: DTIM Period * @bitmap_ctrl: Bitmap Control + * @required_octet: "Syntatic sugar" to force the struct size to the + * minimum valid size when carried in a non-S1G PPDU * @virtual_map: Partial Virtual Bitmap * * This structure represents the payload of the "TIM element" as - * described in IEEE Std 802.11-2020 section 9.4.2.5. + * described in IEEE Std 802.11-2020 section 9.4.2.5. Note that this + * definition is only applicable when the element is carried in a + * non-S1G PPDU. When the TIM is carried in an S1G PPDU, the Bitmap + * Control and Partial Virtual Bitmap may not be present. */ struct ieee80211_tim_ie { u8 dtim_count; u8 dtim_period; u8 bitmap_ctrl; - /* variable size: 1 - 251 bytes */ - u8 virtual_map[1]; + union { + u8 required_octet; + DECLARE_FLEX_ARRAY(u8, virtual_map); + }; } __packed; /** @@ -1239,6 +1253,30 @@ struct ieee80211_twt_setup { u8 params[]; } __packed; +#define IEEE80211_TTLM_MAX_CNT 2 +#define IEEE80211_TTLM_CONTROL_DIRECTION 0x03 +#define IEEE80211_TTLM_CONTROL_DEF_LINK_MAP 0x04 +#define IEEE80211_TTLM_CONTROL_SWITCH_TIME_PRESENT 0x08 +#define IEEE80211_TTLM_CONTROL_EXPECTED_DUR_PRESENT 0x10 +#define IEEE80211_TTLM_CONTROL_LINK_MAP_SIZE 0x20 + +#define IEEE80211_TTLM_DIRECTION_DOWN 0 +#define IEEE80211_TTLM_DIRECTION_UP 1 +#define IEEE80211_TTLM_DIRECTION_BOTH 2 + +/** + * struct ieee80211_ttlm_elem - TID-To-Link Mapping element + * + * Defined in section 9.4.2.314 in P802.11be_D4 + * + * @control: the first part of control field + * @optional: the second part of control field + */ +struct ieee80211_ttlm_elem { + u8 control; + u8 optional[]; +} __packed; + struct ieee80211_mgmt { __le16 frame_control; __le16 duration; @@ -1674,6 +1712,8 @@ struct ieee80211_mcs_info { #define IEEE80211_HT_MCS_TX_MAX_STREAMS 4 #define IEEE80211_HT_MCS_TX_UNEQUAL_MODULATION 0x10 +#define IEEE80211_HT_MCS_CHAINS(mcs) ((mcs) == 32 ? 1 : (1 + ((mcs) >> 3))) + /* * 802.11n D5.0 20.3.5 / 20.6 says: * - indices 0 to 7 and 32 are single spatial stream @@ -3132,6 +3172,28 @@ ieee80211_eht_oper_size_ok(const u8 *data, u8 len) return len >= needed; } +#define IEEE80211_BW_IND_DIS_SUBCH_PRESENT BIT(1) + +struct ieee80211_bandwidth_indication { + u8 params; + struct ieee80211_eht_operation_info info; +} __packed; + +static inline bool +ieee80211_bandwidth_indication_size_ok(const u8 *data, u8 len) +{ + const struct ieee80211_bandwidth_indication *bwi = (const void *)data; + + if (len < sizeof(*bwi)) + return false; + + if (bwi->params & IEEE80211_BW_IND_DIS_SUBCH_PRESENT && + len < sizeof(*bwi) + 2) + return false; + + return true; +} + #define LISTEN_INT_USF GENMASK(15, 14) #define LISTEN_INT_UI GENMASK(13, 0) @@ -3589,6 +3651,8 @@ enum ieee80211_eid_ext { WLAN_EID_EXT_EHT_OPERATION = 106, WLAN_EID_EXT_EHT_MULTI_LINK = 107, WLAN_EID_EXT_EHT_CAPABILITY = 108, + WLAN_EID_EXT_TID_TO_LINK_MAPPING = 109, + WLAN_EID_EXT_BANDWIDTH_INDICATION = 135, }; /* Action category code */ @@ -4356,6 +4420,35 @@ static inline bool ieee80211_is_public_action(struct ieee80211_hdr *hdr, } /** + * ieee80211_is_protected_dual_of_public_action - check if skb contains a + * protected dual of public action management frame + * @skb: the skb containing the frame, length will be checked + * + * Return: true if the skb contains a protected dual of public action + * management frame, false otherwise. + */ +static inline bool +ieee80211_is_protected_dual_of_public_action(struct sk_buff *skb) +{ + u8 action; + + if (!ieee80211_is_public_action((void *)skb->data, skb->len) || + skb->len < IEEE80211_MIN_ACTION_SIZE + 1) + return false; + + action = *(u8 *)(skb->data + IEEE80211_MIN_ACTION_SIZE); + + return action != WLAN_PUB_ACTION_20_40_BSS_COEX && + action != WLAN_PUB_ACTION_DSE_REG_LOC_ANN && + action != WLAN_PUB_ACTION_MSMT_PILOT && + action != WLAN_PUB_ACTION_TDLS_DISCOVER_RES && + action != WLAN_PUB_ACTION_LOC_TRACK_NOTI && + action != WLAN_PUB_ACTION_FTM_REQUEST && + action != WLAN_PUB_ACTION_FTM_RESPONSE && + action != WLAN_PUB_ACTION_FILS_DISCOVERY; +} + +/** * _ieee80211_is_group_privacy_action - check if frame is a group addressed * privacy action frame * @hdr: the frame @@ -4426,12 +4519,11 @@ static inline bool ieee80211_check_tim(const struct ieee80211_tim_ie *tim, /** * ieee80211_get_tdls_action - get tdls packet action (or -1, if not tdls packet) * @skb: the skb containing the frame, length will not be checked - * @hdr_size: the size of the ieee80211_hdr that starts at skb->data * * This function assumes the frame is a data frame, and that the network header * is in the correct place. */ -static inline int ieee80211_get_tdls_action(struct sk_buff *skb, u32 hdr_size) +static inline int ieee80211_get_tdls_action(struct sk_buff *skb) { if (!skb_is_nonlinear(skb) && skb->len > (skb_network_offset(skb) + 2)) { @@ -5125,6 +5217,39 @@ static inline bool ieee80211_mle_reconf_sta_prof_size_ok(const u8 *data, fixed + prof->sta_info_len - 1 <= len; } +static inline bool ieee80211_tid_to_link_map_size_ok(const u8 *data, size_t len) +{ + const struct ieee80211_ttlm_elem *t2l = (const void *)data; + u8 control, fixed = sizeof(*t2l), elem_len = 0; + + if (len < fixed) + return false; + + control = t2l->control; + + if (control & IEEE80211_TTLM_CONTROL_SWITCH_TIME_PRESENT) + elem_len += 2; + if (control & IEEE80211_TTLM_CONTROL_EXPECTED_DUR_PRESENT) + elem_len += 3; + + if (!(control & IEEE80211_TTLM_CONTROL_DEF_LINK_MAP)) { + u8 bm_size; + + elem_len += 1; + if (len < fixed + elem_len) + return false; + + if (control & IEEE80211_TTLM_CONTROL_LINK_MAP_SIZE) + bm_size = 1; + else + bm_size = 2; + + elem_len += hweight8(t2l->optional[0]) * bm_size; + } + + return len >= fixed + elem_len; +} + #define for_each_mle_subelement(_elem, _data, _len) \ if (ieee80211_mle_size_ok(_data, _len)) \ for_each_element(_elem, \ diff --git a/include/linux/if_team.h b/include/linux/if_team.h index 1b9b15a492fa..cdc684e04a2f 100644 --- a/include/linux/if_team.h +++ b/include/linux/if_team.h @@ -189,6 +189,8 @@ struct team { struct net_device *dev; /* associated netdevice */ struct team_pcpu_stats __percpu *pcpu_stats; + const struct header_ops *header_ops_cache; + struct mutex lock; /* used for overall locking, e.g. port lists write */ /* diff --git a/include/linux/igmp.h b/include/linux/igmp.h index ebf4349a53af..5171231f70a8 100644 --- a/include/linux/igmp.h +++ b/include/linux/igmp.h @@ -39,7 +39,7 @@ struct ip_sf_socklist { unsigned int sl_max; unsigned int sl_count; struct rcu_head rcu; - __be32 sl_addr[]; + __be32 sl_addr[] __counted_by(sl_max); }; #define IP_SFBLOCK 10 /* allocate this many at once */ diff --git a/include/linux/instruction_pointer.h b/include/linux/instruction_pointer.h index cda1f706eaeb..aa0b3ffea935 100644 --- a/include/linux/instruction_pointer.h +++ b/include/linux/instruction_pointer.h @@ -2,7 +2,12 @@ #ifndef _LINUX_INSTRUCTION_POINTER_H #define _LINUX_INSTRUCTION_POINTER_H +#include <asm/linkage.h> + #define _RET_IP_ (unsigned long)__builtin_return_address(0) + +#ifndef _THIS_IP_ #define _THIS_IP_ ({ __label__ __here; __here: (unsigned long)&&__here; }) +#endif #endif /* _LINUX_INSTRUCTION_POINTER_H */ diff --git a/include/linux/intel_tpmi.h b/include/linux/intel_tpmi.h index 04d937ad4dc4..ee07393445f9 100644 --- a/include/linux/intel_tpmi.h +++ b/include/linux/intel_tpmi.h @@ -6,6 +6,12 @@ #ifndef _INTEL_TPMI_H_ #define _INTEL_TPMI_H_ +#include <linux/bitfield.h> + +#define TPMI_VERSION_INVALID 0xff +#define TPMI_MINOR_VERSION(val) FIELD_GET(GENMASK(4, 0), val) +#define TPMI_MAJOR_VERSION(val) FIELD_GET(GENMASK(7, 5), val) + /** * struct intel_tpmi_plat_info - Platform information for a TPMI device instance * @package_id: CPU Package id diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index a92bce40b04b..76121c2bb4f8 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -566,11 +566,15 @@ enum * * _ RCU: * 1) rcutree_migrate_callbacks() migrates the queue. - * 2) rcu_report_dead() reports the final quiescent states. + * 2) rcutree_report_cpu_dead() reports the final quiescent states. * * _ IRQ_POLL: irq_poll_cpu_dead() migrates the queue + * + * _ (HR)TIMER_SOFTIRQ: (hr)timers_dead_cpu() migrates the queue */ -#define SOFTIRQ_HOTPLUG_SAFE_MASK (BIT(RCU_SOFTIRQ) | BIT(IRQ_POLL_SOFTIRQ)) +#define SOFTIRQ_HOTPLUG_SAFE_MASK (BIT(TIMER_SOFTIRQ) | BIT(IRQ_POLL_SOFTIRQ) |\ + BIT(HRTIMER_SOFTIRQ) | BIT(RCU_SOFTIRQ)) + /* map softirq index to softirq name. update 'softirq_to_name' in * kernel/softirq.c when adding a new softirq. diff --git a/include/linux/iov_iter.h b/include/linux/iov_iter.h new file mode 100644 index 000000000000..270454a6703d --- /dev/null +++ b/include/linux/iov_iter.h @@ -0,0 +1,274 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* I/O iterator iteration building functions. + * + * Copyright (C) 2023 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + */ + +#ifndef _LINUX_IOV_ITER_H +#define _LINUX_IOV_ITER_H + +#include <linux/uio.h> +#include <linux/bvec.h> + +typedef size_t (*iov_step_f)(void *iter_base, size_t progress, size_t len, + void *priv, void *priv2); +typedef size_t (*iov_ustep_f)(void __user *iter_base, size_t progress, size_t len, + void *priv, void *priv2); + +/* + * Handle ITER_UBUF. + */ +static __always_inline +size_t iterate_ubuf(struct iov_iter *iter, size_t len, void *priv, void *priv2, + iov_ustep_f step) +{ + void __user *base = iter->ubuf; + size_t progress = 0, remain; + + remain = step(base + iter->iov_offset, 0, len, priv, priv2); + progress = len - remain; + iter->iov_offset += progress; + iter->count -= progress; + return progress; +} + +/* + * Handle ITER_IOVEC. + */ +static __always_inline +size_t iterate_iovec(struct iov_iter *iter, size_t len, void *priv, void *priv2, + iov_ustep_f step) +{ + const struct iovec *p = iter->__iov; + size_t progress = 0, skip = iter->iov_offset; + + do { + size_t remain, consumed; + size_t part = min(len, p->iov_len - skip); + + if (likely(part)) { + remain = step(p->iov_base + skip, progress, part, priv, priv2); + consumed = part - remain; + progress += consumed; + skip += consumed; + len -= consumed; + if (skip < p->iov_len) + break; + } + p++; + skip = 0; + } while (len); + + iter->nr_segs -= p - iter->__iov; + iter->__iov = p; + iter->iov_offset = skip; + iter->count -= progress; + return progress; +} + +/* + * Handle ITER_KVEC. + */ +static __always_inline +size_t iterate_kvec(struct iov_iter *iter, size_t len, void *priv, void *priv2, + iov_step_f step) +{ + const struct kvec *p = iter->kvec; + size_t progress = 0, skip = iter->iov_offset; + + do { + size_t remain, consumed; + size_t part = min(len, p->iov_len - skip); + + if (likely(part)) { + remain = step(p->iov_base + skip, progress, part, priv, priv2); + consumed = part - remain; + progress += consumed; + skip += consumed; + len -= consumed; + if (skip < p->iov_len) + break; + } + p++; + skip = 0; + } while (len); + + iter->nr_segs -= p - iter->kvec; + iter->kvec = p; + iter->iov_offset = skip; + iter->count -= progress; + return progress; +} + +/* + * Handle ITER_BVEC. + */ +static __always_inline +size_t iterate_bvec(struct iov_iter *iter, size_t len, void *priv, void *priv2, + iov_step_f step) +{ + const struct bio_vec *p = iter->bvec; + size_t progress = 0, skip = iter->iov_offset; + + do { + size_t remain, consumed; + size_t offset = p->bv_offset + skip, part; + void *kaddr = kmap_local_page(p->bv_page + offset / PAGE_SIZE); + + part = min3(len, + (size_t)(p->bv_len - skip), + (size_t)(PAGE_SIZE - offset % PAGE_SIZE)); + remain = step(kaddr + offset % PAGE_SIZE, progress, part, priv, priv2); + kunmap_local(kaddr); + consumed = part - remain; + len -= consumed; + progress += consumed; + skip += consumed; + if (skip >= p->bv_len) { + skip = 0; + p++; + } + if (remain) + break; + } while (len); + + iter->nr_segs -= p - iter->bvec; + iter->bvec = p; + iter->iov_offset = skip; + iter->count -= progress; + return progress; +} + +/* + * Handle ITER_XARRAY. + */ +static __always_inline +size_t iterate_xarray(struct iov_iter *iter, size_t len, void *priv, void *priv2, + iov_step_f step) +{ + struct folio *folio; + size_t progress = 0; + loff_t start = iter->xarray_start + iter->iov_offset; + pgoff_t index = start / PAGE_SIZE; + XA_STATE(xas, iter->xarray, index); + + rcu_read_lock(); + xas_for_each(&xas, folio, ULONG_MAX) { + size_t remain, consumed, offset, part, flen; + + if (xas_retry(&xas, folio)) + continue; + if (WARN_ON(xa_is_value(folio))) + break; + if (WARN_ON(folio_test_hugetlb(folio))) + break; + + offset = offset_in_folio(folio, start + progress); + flen = min(folio_size(folio) - offset, len); + + while (flen) { + void *base = kmap_local_folio(folio, offset); + + part = min_t(size_t, flen, + PAGE_SIZE - offset_in_page(offset)); + remain = step(base, progress, part, priv, priv2); + kunmap_local(base); + + consumed = part - remain; + progress += consumed; + len -= consumed; + + if (remain || len == 0) + goto out; + flen -= consumed; + offset += consumed; + } + } + +out: + rcu_read_unlock(); + iter->iov_offset += progress; + iter->count -= progress; + return progress; +} + +/* + * Handle ITER_DISCARD. + */ +static __always_inline +size_t iterate_discard(struct iov_iter *iter, size_t len, void *priv, void *priv2, + iov_step_f step) +{ + size_t progress = len; + + iter->count -= progress; + return progress; +} + +/** + * iterate_and_advance2 - Iterate over an iterator + * @iter: The iterator to iterate over. + * @len: The amount to iterate over. + * @priv: Data for the step functions. + * @priv2: More data for the step functions. + * @ustep: Function for UBUF/IOVEC iterators; given __user addresses. + * @step: Function for other iterators; given kernel addresses. + * + * Iterate over the next part of an iterator, up to the specified length. The + * buffer is presented in segments, which for kernel iteration are broken up by + * physical pages and mapped, with the mapped address being presented. + * + * Two step functions, @step and @ustep, must be provided, one for handling + * mapped kernel addresses and the other is given user addresses which have the + * potential to fault since no pinning is performed. + * + * The step functions are passed the address and length of the segment, @priv, + * @priv2 and the amount of data so far iterated over (which can, for example, + * be added to @priv to point to the right part of a second buffer). The step + * functions should return the amount of the segment they didn't process (ie. 0 + * indicates complete processsing). + * + * This function returns the amount of data processed (ie. 0 means nothing was + * processed and the value of @len means processes to completion). + */ +static __always_inline +size_t iterate_and_advance2(struct iov_iter *iter, size_t len, void *priv, + void *priv2, iov_ustep_f ustep, iov_step_f step) +{ + if (unlikely(iter->count < len)) + len = iter->count; + if (unlikely(!len)) + return 0; + + if (likely(iter_is_ubuf(iter))) + return iterate_ubuf(iter, len, priv, priv2, ustep); + if (likely(iter_is_iovec(iter))) + return iterate_iovec(iter, len, priv, priv2, ustep); + if (iov_iter_is_bvec(iter)) + return iterate_bvec(iter, len, priv, priv2, step); + if (iov_iter_is_kvec(iter)) + return iterate_kvec(iter, len, priv, priv2, step); + if (iov_iter_is_xarray(iter)) + return iterate_xarray(iter, len, priv, priv2, step); + return iterate_discard(iter, len, priv, priv2, step); +} + +/** + * iterate_and_advance - Iterate over an iterator + * @iter: The iterator to iterate over. + * @len: The amount to iterate over. + * @priv: Data for the step functions. + * @ustep: Function for UBUF/IOVEC iterators; given __user addresses. + * @step: Function for other iterators; given kernel addresses. + * + * As iterate_and_advance2(), but priv2 is always NULL. + */ +static __always_inline +size_t iterate_and_advance(struct iov_iter *iter, size_t len, void *priv, + iov_ustep_f ustep, iov_step_f step) +{ + return iterate_and_advance2(iter, len, priv, NULL, ustep, step); +} + +#endif /* _LINUX_IOV_ITER_H */ diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index af8a771a053c..5e605e384aac 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -82,6 +82,7 @@ struct ipv6_devconf { __u32 ioam6_id_wide; __u8 ioam6_enabled; __u8 ndisc_evict_nocarrier; + __u8 ra_honor_pio_life; struct ctl_table_header *sysctl_header; }; @@ -213,28 +214,9 @@ struct ipv6_pinfo { __be32 flow_label; __u32 frag_size; - /* - * Packed in 16bits. - * Omit one shift by putting the signed field at MSB. - */ -#if defined(__BIG_ENDIAN_BITFIELD) - __s16 hop_limit:9; - __u16 __unused_1:7; -#else - __u16 __unused_1:7; - __s16 hop_limit:9; -#endif + s16 hop_limit; + u8 mcast_hops; -#if defined(__BIG_ENDIAN_BITFIELD) - /* Packed in 16bits. */ - __s16 mcast_hops:9; - __u16 __unused_2:6, - mc_loop:1; -#else - __u16 mc_loop:1, - __unused_2:6; - __s16 mcast_hops:9; -#endif int ucast_oif; int mcast_oif; @@ -262,21 +244,11 @@ struct ipv6_pinfo { } rxopt; /* sockopt flags */ - __u16 recverr:1, - sndflow:1, - repflow:1, - pmtudisc:3, - padding:1, /* 1 bit hole */ - srcprefs:3, /* 001: prefer temporary address + __u8 srcprefs; /* 001: prefer temporary address * 010: prefer public address * 100: prefer care-of address */ - dontfrag:1, - autoflowlabel:1, - autoflowlabel_set:1, - mc_all:1, - recverr_rfc4884:1, - rtalert_isolate:1; + __u8 pmtudisc; __u8 min_hopcount; __u8 tclass; __be32 rcv_flowinfo; @@ -293,6 +265,18 @@ struct ipv6_pinfo { struct inet6_cork cork; }; +/* We currently use available bits from inet_sk(sk)->inet_flags, + * this could change in the future. + */ +#define inet6_test_bit(nr, sk) \ + test_bit(INET_FLAGS_##nr, &inet_sk(sk)->inet_flags) +#define inet6_set_bit(nr, sk) \ + set_bit(INET_FLAGS_##nr, &inet_sk(sk)->inet_flags) +#define inet6_clear_bit(nr, sk) \ + clear_bit(INET_FLAGS_##nr, &inet_sk(sk)->inet_flags) +#define inet6_assign_bit(nr, sk, val) \ + assign_bit(INET_FLAGS_##nr, &inet_sk(sk)->inet_flags, val) + /* WARNING: don't change the layout of the members in {raw,udp,tcp}6_sock! */ struct raw6_sock { /* inet_sock has to be the first member of raw6_sock */ diff --git a/include/linux/irq.h b/include/linux/irq.h index d8a6fdce9373..90081afa10ce 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -215,8 +215,6 @@ struct irq_data { * IRQD_SINGLE_TARGET - IRQ allows only a single affinity target * IRQD_DEFAULT_TRIGGER_SET - Expected trigger already been set * IRQD_CAN_RESERVE - Can use reservation mode - * IRQD_MSI_NOMASK_QUIRK - Non-maskable MSI quirk for affinity change - * required * IRQD_HANDLE_ENFORCE_IRQCTX - Enforce that handle_irq_*() is only invoked * from actual interrupt context. * IRQD_AFFINITY_ON_ACTIVATE - Affinity is set on activation. Don't call @@ -247,11 +245,10 @@ enum { IRQD_SINGLE_TARGET = BIT(24), IRQD_DEFAULT_TRIGGER_SET = BIT(25), IRQD_CAN_RESERVE = BIT(26), - IRQD_MSI_NOMASK_QUIRK = BIT(27), - IRQD_HANDLE_ENFORCE_IRQCTX = BIT(28), - IRQD_AFFINITY_ON_ACTIVATE = BIT(29), - IRQD_IRQ_ENABLED_ON_SUSPEND = BIT(30), - IRQD_RESEND_WHEN_IN_PROGRESS = BIT(31), + IRQD_HANDLE_ENFORCE_IRQCTX = BIT(27), + IRQD_AFFINITY_ON_ACTIVATE = BIT(28), + IRQD_IRQ_ENABLED_ON_SUSPEND = BIT(29), + IRQD_RESEND_WHEN_IN_PROGRESS = BIT(30), }; #define __irqd_to_state(d) ACCESS_PRIVATE((d)->common, state_use_accessors) @@ -426,21 +423,6 @@ static inline bool irqd_can_reserve(struct irq_data *d) return __irqd_to_state(d) & IRQD_CAN_RESERVE; } -static inline void irqd_set_msi_nomask_quirk(struct irq_data *d) -{ - __irqd_to_state(d) |= IRQD_MSI_NOMASK_QUIRK; -} - -static inline void irqd_clr_msi_nomask_quirk(struct irq_data *d) -{ - __irqd_to_state(d) &= ~IRQD_MSI_NOMASK_QUIRK; -} - -static inline bool irqd_msi_nomask_quirk(struct irq_data *d) -{ - return __irqd_to_state(d) & IRQD_MSI_NOMASK_QUIRK; -} - static inline void irqd_set_affinity_on_activate(struct irq_data *d) { __irqd_to_state(d) |= IRQD_AFFINITY_ON_ACTIVATE; diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h index 51c254b7fec2..ee0a82c60508 100644 --- a/include/linux/irqdomain.h +++ b/include/linux/irqdomain.h @@ -174,7 +174,7 @@ struct irq_domain { irq_hw_number_t hwirq_max; unsigned int revmap_size; struct radix_tree_root revmap_tree; - struct irq_data __rcu *revmap[]; + struct irq_data __rcu *revmap[] __counted_by(revmap_size); }; /* Irq domain flags */ diff --git a/include/linux/iversion.h b/include/linux/iversion.h index f174ff1b59ee..8f972eaca2ed 100644 --- a/include/linux/iversion.h +++ b/include/linux/iversion.h @@ -256,7 +256,7 @@ inode_peek_iversion(const struct inode *inode) * For filesystems without any sort of change attribute, the best we can * do is fake one up from the ctime: */ -static inline u64 time_to_chattr(struct timespec64 *t) +static inline u64 time_to_chattr(const struct timespec64 *t) { u64 chattr = t->tv_sec; diff --git a/include/linux/kasan.h b/include/linux/kasan.h index 3df5499f7936..72cb693b075b 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -54,7 +54,7 @@ extern p4d_t kasan_early_shadow_p4d[MAX_PTRS_PER_P4D]; int kasan_populate_early_shadow(const void *shadow_start, const void *shadow_end); -#ifndef __HAVE_ARCH_SHADOW_MAP +#ifndef kasan_mem_to_shadow static inline void *kasan_mem_to_shadow(const void *addr) { return (void *)((unsigned long)addr >> KASAN_SHADOW_SCALE_SHIFT) @@ -285,8 +285,10 @@ static inline bool kasan_check_byte(const void *address) #if defined(CONFIG_KASAN) && defined(CONFIG_KASAN_STACK) void kasan_unpoison_task_stack(struct task_struct *task); +asmlinkage void kasan_unpoison_task_stack_below(const void *watermark); #else static inline void kasan_unpoison_task_stack(struct task_struct *task) {} +static inline void kasan_unpoison_task_stack_below(const void *watermark) {} #endif #ifdef CONFIG_KASAN_GENERIC @@ -466,10 +468,10 @@ static inline void kasan_free_module_shadow(const struct vm_struct *vm) {} #endif /* (CONFIG_KASAN_GENERIC || CONFIG_KASAN_SW_TAGS) && !CONFIG_KASAN_VMALLOC */ -#ifdef CONFIG_KASAN_INLINE +#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS) void kasan_non_canonical_hook(unsigned long addr); -#else /* CONFIG_KASAN_INLINE */ +#else /* CONFIG_KASAN_GENERIC || CONFIG_KASAN_SW_TAGS */ static inline void kasan_non_canonical_hook(unsigned long addr) { } -#endif /* CONFIG_KASAN_INLINE */ +#endif /* CONFIG_KASAN_GENERIC || CONFIG_KASAN_SW_TAGS */ #endif /* LINUX_KASAN_H */ diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index fb6c6109fdca..4944136efaa2 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -664,7 +664,7 @@ struct kvm_irq_routing_table { * Array indexed by gsi. Each entry contains list of irq chips * the gsi is connected to. */ - struct hlist_head map[]; + struct hlist_head map[] __counted_by(nr_rt_entries); }; #endif diff --git a/include/linux/libata.h b/include/linux/libata.h index 52d58b13e5ee..2a7d2af0ed80 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -192,6 +192,7 @@ enum { ATA_PFLAG_UNLOADING = (1 << 9), /* driver is being unloaded */ ATA_PFLAG_UNLOADED = (1 << 10), /* driver is unloaded */ + ATA_PFLAG_RESUMING = (1 << 16), /* port is being resumed */ ATA_PFLAG_SUSPENDED = (1 << 17), /* port is suspended (power) */ ATA_PFLAG_PM_PENDING = (1 << 18), /* PM operation pending */ ATA_PFLAG_INIT_GTM_VALID = (1 << 19), /* initial gtm data valid */ @@ -222,6 +223,10 @@ enum { ATA_HOST_PARALLEL_SCAN = (1 << 2), /* Ports on this host can be scanned in parallel */ ATA_HOST_IGNORE_ATA = (1 << 3), /* Ignore ATA devices on this host. */ + ATA_HOST_NO_PART = (1 << 4), /* Host does not support partial */ + ATA_HOST_NO_SSC = (1 << 5), /* Host does not support slumber */ + ATA_HOST_NO_DEVSLP = (1 << 6), /* Host does not support devslp */ + /* bits 24:31 of host->flags are reserved for LLD specific flags */ /* various lengths of time */ @@ -255,7 +260,7 @@ enum { * advised to wait only for the following duration before * doing SRST. */ - ATA_TMOUT_PMP_SRST_WAIT = 5000, + ATA_TMOUT_PMP_SRST_WAIT = 10000, /* When the LPM policy is set to ATA_LPM_MAX_POWER, there might * be a spurious PHY event, so ignore the first PHY event that @@ -314,9 +319,10 @@ enum { ATA_EH_ENABLE_LINK = (1 << 3), ATA_EH_PARK = (1 << 5), /* unload heads and stop I/O */ ATA_EH_GET_SUCCESS_SENSE = (1 << 6), /* Get sense data for successful cmd */ + ATA_EH_SET_ACTIVE = (1 << 7), /* Set a device to active power mode */ ATA_EH_PERDEV_MASK = ATA_EH_REVALIDATE | ATA_EH_PARK | - ATA_EH_GET_SUCCESS_SENSE, + ATA_EH_GET_SUCCESS_SENSE | ATA_EH_SET_ACTIVE, ATA_EH_ALL_ACTIONS = ATA_EH_REVALIDATE | ATA_EH_RESET | ATA_EH_ENABLE_LINK, @@ -353,7 +359,7 @@ enum { /* This should match the actual table size of * ata_eh_cmd_timeout_table in libata-eh.c. */ - ATA_EH_CMD_TIMEOUT_TABLE_SIZE = 7, + ATA_EH_CMD_TIMEOUT_TABLE_SIZE = 8, /* Horkage types. May be set by libata or controller on drives (some horkage may be drive/controller pair dependent */ @@ -1144,6 +1150,7 @@ extern int ata_std_bios_param(struct scsi_device *sdev, struct block_device *bdev, sector_t capacity, int geom[]); extern void ata_scsi_unlock_native_capacity(struct scsi_device *sdev); +extern int ata_scsi_slave_alloc(struct scsi_device *sdev); extern int ata_scsi_slave_config(struct scsi_device *sdev); extern void ata_scsi_slave_destroy(struct scsi_device *sdev); extern int ata_scsi_change_queue_depth(struct scsi_device *sdev, @@ -1392,6 +1399,7 @@ extern const struct attribute_group *ata_common_sdev_groups[]; .this_id = ATA_SHT_THIS_ID, \ .emulated = ATA_SHT_EMULATED, \ .proc_name = drv_name, \ + .slave_alloc = ata_scsi_slave_alloc, \ .slave_destroy = ata_scsi_slave_destroy, \ .bios_param = ata_std_bios_param, \ .unlock_native_capacity = ata_scsi_unlock_native_capacity,\ diff --git a/include/linux/linkmode.h b/include/linux/linkmode.h index 15e0e0209da4..7303b4bc2ce0 100644 --- a/include/linux/linkmode.h +++ b/include/linux/linkmode.h @@ -43,15 +43,6 @@ static inline void linkmode_set_bit(int nr, volatile unsigned long *addr) __set_bit(nr, addr); } -static inline void linkmode_set_bit_array(const int *array, int array_size, - unsigned long *addr) -{ - int i; - - for (i = 0; i < array_size; i++) - linkmode_set_bit(array[i], addr); -} - static inline void linkmode_clear_bit(int nr, volatile unsigned long *addr) { __clear_bit(nr, addr); @@ -71,6 +62,15 @@ static inline int linkmode_test_bit(int nr, const volatile unsigned long *addr) return test_bit(nr, addr); } +static inline void linkmode_set_bit_array(const int *array, int array_size, + unsigned long *addr) +{ + int i; + + for (i = 0; i < array_size; i++) + linkmode_set_bit(array[i], addr); +} + static inline int linkmode_equal(const unsigned long *src1, const unsigned long *src2) { diff --git a/include/linux/list.h b/include/linux/list.h index 164b4d0e9d2a..1837caedf723 100644 --- a/include/linux/list.h +++ b/include/linux/list.h @@ -687,6 +687,14 @@ static inline void list_splice_tail_init(struct list_head *list, for (pos = (head)->next; !list_is_head(pos, (head)); pos = pos->next) /** + * list_for_each_reverse - iterate backwards over a list + * @pos: the &struct list_head to use as a loop cursor. + * @head: the head for your list. + */ +#define list_for_each_reverse(pos, head) \ + for (pos = (head)->prev; pos != (head); pos = pos->prev) + +/** * list_for_each_rcu - Iterate over a list in an RCU-safe fashion * @pos: the &struct list_head to use as a loop cursor. * @head: the head for your list. diff --git a/include/linux/llist.h b/include/linux/llist.h index 85bda2d02d65..2c982ff7475a 100644 --- a/include/linux/llist.h +++ b/include/linux/llist.h @@ -74,6 +74,33 @@ static inline void init_llist_head(struct llist_head *list) } /** + * init_llist_node - initialize lock-less list node + * @node: the node to be initialised + * + * In cases where there is a need to test if a node is on + * a list or not, this initialises the node to clearly + * not be on any list. + */ +static inline void init_llist_node(struct llist_node *node) +{ + node->next = node; +} + +/** + * llist_on_list - test if a lock-list list node is on a list + * @node: the node to test + * + * When a node is on a list the ->next pointer will be NULL or + * some other node. It can never point to itself. We use that + * in init_llist_node() to record that a node is not on any list, + * and here to test whether it is on any list. + */ +static inline bool llist_on_list(const struct llist_node *node) +{ + return node->next != node; +} + +/** * llist_entry - get the struct of this entry * @ptr: the &struct llist_node pointer. * @type: the type of the struct this is embedded in. @@ -249,6 +276,25 @@ static inline struct llist_node *__llist_del_all(struct llist_head *head) extern struct llist_node *llist_del_first(struct llist_head *head); +/** + * llist_del_first_init - delete first entry from lock-list and mark is as being off-list + * @head: the head of lock-less list to delete from. + * + * This behave the same as llist_del_first() except that llist_init_node() is called + * on the returned node so that llist_on_list() will report false for the node. + */ +static inline struct llist_node *llist_del_first_init(struct llist_head *head) +{ + struct llist_node *n = llist_del_first(head); + + if (n) + init_llist_node(n); + return n; +} + +extern bool llist_del_first_this(struct llist_head *head, + struct llist_node *this); + struct llist_node *llist_reverse_order(struct llist_node *head); #endif /* LLIST_H */ diff --git a/include/linux/lockd/lockd.h b/include/linux/lockd/lockd.h index 0f016d69c996..9f565416d186 100644 --- a/include/linux/lockd/lockd.h +++ b/include/linux/lockd/lockd.h @@ -282,7 +282,7 @@ __be32 nlmsvc_testlock(struct svc_rqst *, struct nlm_file *, struct nlm_host *, struct nlm_lock *, struct nlm_lock *, struct nlm_cookie *); __be32 nlmsvc_cancel_blocked(struct net *net, struct nlm_file *, struct nlm_lock *); -void nlmsvc_retry_blocked(void); +void nlmsvc_retry_blocked(struct svc_rqst *rqstp); void nlmsvc_traverse_blocks(struct nlm_host *, struct nlm_file *, nlm_host_match_fn_t match); void nlmsvc_grant_reply(struct nlm_cookie *, __be32); diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index ac962c4cb44b..99b8176c3738 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -43,17 +43,17 @@ LSM_HOOK(int, 0, capset, struct cred *new, const struct cred *old, const kernel_cap_t *permitted) LSM_HOOK(int, 0, capable, const struct cred *cred, struct user_namespace *ns, int cap, unsigned int opts) -LSM_HOOK(int, 0, quotactl, int cmds, int type, int id, struct super_block *sb) +LSM_HOOK(int, 0, quotactl, int cmds, int type, int id, const struct super_block *sb) LSM_HOOK(int, 0, quota_on, struct dentry *dentry) LSM_HOOK(int, 0, syslog, int type) LSM_HOOK(int, 0, settime, const struct timespec64 *ts, const struct timezone *tz) LSM_HOOK(int, 0, vm_enough_memory, struct mm_struct *mm, long pages) LSM_HOOK(int, 0, bprm_creds_for_exec, struct linux_binprm *bprm) -LSM_HOOK(int, 0, bprm_creds_from_file, struct linux_binprm *bprm, struct file *file) +LSM_HOOK(int, 0, bprm_creds_from_file, struct linux_binprm *bprm, const struct file *file) LSM_HOOK(int, 0, bprm_check_security, struct linux_binprm *bprm) -LSM_HOOK(void, LSM_RET_VOID, bprm_committing_creds, struct linux_binprm *bprm) -LSM_HOOK(void, LSM_RET_VOID, bprm_committed_creds, struct linux_binprm *bprm) +LSM_HOOK(void, LSM_RET_VOID, bprm_committing_creds, const struct linux_binprm *bprm) +LSM_HOOK(void, LSM_RET_VOID, bprm_committed_creds, const struct linux_binprm *bprm) LSM_HOOK(int, 0, fs_context_submount, struct fs_context *fc, struct super_block *reference) LSM_HOOK(int, 0, fs_context_dup, struct fs_context *fc, struct fs_context *src_sc) @@ -66,7 +66,7 @@ LSM_HOOK(void, LSM_RET_VOID, sb_free_mnt_opts, void *mnt_opts) LSM_HOOK(int, 0, sb_eat_lsm_opts, char *orig, void **mnt_opts) LSM_HOOK(int, 0, sb_mnt_opts_compat, struct super_block *sb, void *mnt_opts) LSM_HOOK(int, 0, sb_remount, struct super_block *sb, void *mnt_opts) -LSM_HOOK(int, 0, sb_kern_mount, struct super_block *sb) +LSM_HOOK(int, 0, sb_kern_mount, const struct super_block *sb) LSM_HOOK(int, 0, sb_show_options, struct seq_file *m, struct super_block *sb) LSM_HOOK(int, 0, sb_statfs, struct dentry *dentry) LSM_HOOK(int, 0, sb_mount, const char *dev_name, const struct path *path, diff --git a/include/linux/lwq.h b/include/linux/lwq.h new file mode 100644 index 000000000000..d081d5cf8e33 --- /dev/null +++ b/include/linux/lwq.h @@ -0,0 +1,124 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#ifndef LWQ_H +#define LWQ_H +/* + * Light-weight single-linked queue built from llist + * + * Entries can be enqueued from any context with no locking. + * Entries can be dequeued from process context with integrated locking. + * + * This is particularly suitable when work items are queued in + * BH or IRQ context, and where work items are handled one at a time + * by dedicated threads. + */ +#include <linux/container_of.h> +#include <linux/spinlock.h> +#include <linux/llist.h> + +struct lwq_node { + struct llist_node node; +}; + +struct lwq { + spinlock_t lock; + struct llist_node *ready; /* entries to be dequeued */ + struct llist_head new; /* entries being enqueued */ +}; + +/** + * lwq_init - initialise a lwq + * @q: the lwq object + */ +static inline void lwq_init(struct lwq *q) +{ + spin_lock_init(&q->lock); + q->ready = NULL; + init_llist_head(&q->new); +} + +/** + * lwq_empty - test if lwq contains any entry + * @q: the lwq object + * + * This empty test contains an acquire barrier so that if a wakeup + * is sent when lwq_dequeue returns true, it is safe to go to sleep after + * a test on lwq_empty(). + */ +static inline bool lwq_empty(struct lwq *q) +{ + /* acquire ensures ordering wrt lwq_enqueue() */ + return smp_load_acquire(&q->ready) == NULL && llist_empty(&q->new); +} + +struct llist_node *__lwq_dequeue(struct lwq *q); +/** + * lwq_dequeue - dequeue first (oldest) entry from lwq + * @q: the queue to dequeue from + * @type: the type of object to return + * @member: them member in returned object which is an lwq_node. + * + * Remove a single object from the lwq and return it. This will take + * a spinlock and so must always be called in the same context, typcially + * process contet. + */ +#define lwq_dequeue(q, type, member) \ + ({ struct llist_node *_n = __lwq_dequeue(q); \ + _n ? container_of(_n, type, member.node) : NULL; }) + +struct llist_node *lwq_dequeue_all(struct lwq *q); + +/** + * lwq_for_each_safe - iterate over detached queue allowing deletion + * @_n: iterator variable + * @_t1: temporary struct llist_node ** + * @_t2: temporary struct llist_node * + * @_l: address of llist_node pointer from lwq_dequeue_all() + * @_member: member in _n where lwq_node is found. + * + * Iterate over members in a dequeued list. If the iterator variable + * is set to NULL, the iterator removes that entry from the queue. + */ +#define lwq_for_each_safe(_n, _t1, _t2, _l, _member) \ + for (_t1 = (_l); \ + *(_t1) ? (_n = container_of(*(_t1), typeof(*(_n)), _member.node),\ + _t2 = ((*_t1)->next), \ + true) \ + : false; \ + (_n) ? (_t1 = &(_n)->_member.node.next, 0) \ + : ((*(_t1) = (_t2)), 0)) + +/** + * lwq_enqueue - add a new item to the end of the queue + * @n - the lwq_node embedded in the item to be added + * @q - the lwq to append to. + * + * No locking is needed to append to the queue so this can + * be called from any context. + * Return %true is the list may have previously been empty. + */ +static inline bool lwq_enqueue(struct lwq_node *n, struct lwq *q) +{ + /* acquire enqures ordering wrt lwq_dequeue */ + return llist_add(&n->node, &q->new) && + smp_load_acquire(&q->ready) == NULL; +} + +/** + * lwq_enqueue_batch - add a list of new items to the end of the queue + * @n - the lwq_node embedded in the first item to be added + * @q - the lwq to append to. + * + * No locking is needed to append to the queue so this can + * be called from any context. + * Return %true is the list may have previously been empty. + */ +static inline bool lwq_enqueue_batch(struct llist_node *n, struct lwq *q) +{ + struct llist_node *e = n; + + /* acquire enqures ordering wrt lwq_dequeue */ + return llist_add_batch(llist_reverse_order(n), e, &q->new) && + smp_load_acquire(&q->ready) == NULL; +} +#endif /* LWQ_H */ diff --git a/include/linux/maple_tree.h b/include/linux/maple_tree.h index e41c70ac7744..d01e850b570f 100644 --- a/include/linux/maple_tree.h +++ b/include/linux/maple_tree.h @@ -428,6 +428,8 @@ struct ma_wr_state { #define MAS_ROOT ((struct maple_enode *)5UL) #define MAS_NONE ((struct maple_enode *)9UL) #define MAS_PAUSE ((struct maple_enode *)17UL) +#define MAS_OVERFLOW ((struct maple_enode *)33UL) +#define MAS_UNDERFLOW ((struct maple_enode *)65UL) #define MA_ERROR(err) \ ((struct maple_enode *)(((unsigned long)err << 2) | 2UL)) @@ -511,6 +513,15 @@ static inline bool mas_is_paused(const struct ma_state *mas) return mas->node == MAS_PAUSE; } +/* Check if the mas is pointing to a node or not */ +static inline bool mas_is_active(struct ma_state *mas) +{ + if ((unsigned long)mas->node >= MAPLE_RESERVED_RANGE) + return true; + + return false; +} + /** * mas_reset() - Reset a Maple Tree operation state. * @mas: Maple Tree operation state. diff --git a/include/linux/mcb.h b/include/linux/mcb.h index 1e5893138afe..0b971b24a804 100644 --- a/include/linux/mcb.h +++ b/include/linux/mcb.h @@ -63,7 +63,6 @@ static inline struct mcb_bus *to_mcb_bus(struct device *dev) struct mcb_device { struct device dev; struct mcb_bus *bus; - bool is_added; struct mcb_driver *driver; u16 id; int inst; diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index ab94ad4597d0..e4e24da16d2c 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -920,7 +920,7 @@ unsigned long mem_cgroup_get_zone_lru_size(struct lruvec *lruvec, return READ_ONCE(mz->lru_zone_size[zone_idx][lru]); } -void mem_cgroup_handle_over_high(void); +void mem_cgroup_handle_over_high(gfp_t gfp_mask); unsigned long mem_cgroup_get_max(struct mem_cgroup *memcg); @@ -1458,7 +1458,7 @@ static inline void mem_cgroup_unlock_pages(void) rcu_read_unlock(); } -static inline void mem_cgroup_handle_over_high(void) +static inline void mem_cgroup_handle_over_high(gfp_t gfp_mask) { } diff --git a/include/linux/mfd/mt6358/registers.h b/include/linux/mfd/mt6358/registers.h index 3d33517f178c..d83e87298ac4 100644 --- a/include/linux/mfd/mt6358/registers.h +++ b/include/linux/mfd/mt6358/registers.h @@ -262,6 +262,12 @@ #define MT6358_LDO_VBIF28_CON3 0x1db0 #define MT6358_VCAMA1_ANA_CON0 0x1e08 #define MT6358_VCAMA2_ANA_CON0 0x1e0c +#define MT6358_VFE28_ANA_CON0 0x1e10 +#define MT6358_VCN28_ANA_CON0 0x1e14 +#define MT6358_VBIF28_ANA_CON0 0x1e18 +#define MT6358_VAUD28_ANA_CON0 0x1e1c +#define MT6358_VAUX18_ANA_CON0 0x1e20 +#define MT6358_VXO22_ANA_CON0 0x1e24 #define MT6358_VCN33_ANA_CON0 0x1e28 #define MT6358_VSIM1_ANA_CON0 0x1e2c #define MT6358_VSIM2_ANA_CON0 0x1e30 @@ -288,4 +294,21 @@ #define MT6358_AUD_TOP_INT_CON0 0x2228 #define MT6358_AUD_TOP_INT_STATUS0 0x2234 +/* + * MT6366 has no VCAM*, but has other regulators in its place. The names + * keep the MT6358 prefix for ease of use in the regulator driver. + */ +#define MT6358_LDO_VSRAM_CON5 0x1bf8 +#define MT6358_LDO_VM18_CON0 MT6358_LDO_VCAMA1_CON0 +#define MT6358_LDO_VM18_CON1 MT6358_LDO_VCAMA1_CON1 +#define MT6358_LDO_VM18_CON2 MT6358_LDO_VCAMA1_CON2 +#define MT6358_LDO_VMDDR_CON0 MT6358_LDO_VCAMA2_CON0 +#define MT6358_LDO_VMDDR_CON1 MT6358_LDO_VCAMA2_CON1 +#define MT6358_LDO_VMDDR_CON2 MT6358_LDO_VCAMA2_CON2 +#define MT6358_LDO_VSRAM_CORE_CON0 MT6358_LDO_VCAMD_CON0 +#define MT6358_LDO_VSRAM_CORE_DBG0 0x1cb6 +#define MT6358_LDO_VSRAM_CORE_DBG1 0x1cb8 +#define MT6358_VM18_ANA_CON0 MT6358_VCAMA1_ANA_CON0 +#define MT6358_VMDDR_ANA_CON0 MT6358_VCAMD_ANA_CON0 + #endif /* __MFD_MT6358_REGISTERS_H__ */ diff --git a/include/linux/micrel_phy.h b/include/linux/micrel_phy.h index 4e27ca7c49de..591bf5b5e8dc 100644 --- a/include/linux/micrel_phy.h +++ b/include/linux/micrel_phy.h @@ -64,6 +64,10 @@ #define KSZ886X_BMCR_DISABLE_TRANSMIT BIT(1) #define KSZ886X_BMCR_DISABLE_LED BIT(0) +/* PHY Special Control/Status Register (Reg 31) */ #define KSZ886X_CTRL_MDIX_STAT BIT(4) +#define KSZ886X_CTRL_FORCE_LINK BIT(3) +#define KSZ886X_CTRL_PWRSAVE BIT(2) +#define KSZ886X_CTRL_REMOTE_LOOPBACK BIT(1) #endif /* _MICREL_PHY_H */ diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 4d5be378fa8c..820bca965fb6 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -366,6 +366,9 @@ enum mlx5_driver_event { MLX5_DRIVER_EVENT_UPLINK_NETDEV, MLX5_DRIVER_EVENT_MACSEC_SA_ADDED, MLX5_DRIVER_EVENT_MACSEC_SA_DELETED, + MLX5_DRIVER_EVENT_SF_PEER_DEVLINK, + MLX5_DRIVER_EVENT_AFFILIATION_DONE, + MLX5_DRIVER_EVENT_AFFILIATION_REMOVED, }; enum { diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 3033bbaeac81..d2b8d4a74a30 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -155,6 +155,8 @@ enum { MLX5_REG_MCC = 0x9062, MLX5_REG_MCDA = 0x9063, MLX5_REG_MCAM = 0x907f, + MLX5_REG_MSECQ = 0x9155, + MLX5_REG_MSEES = 0x9156, MLX5_REG_MIRC = 0x9162, MLX5_REG_SBCAM = 0xB01F, MLX5_REG_RESOURCE_DUMP = 0xC000, @@ -613,6 +615,7 @@ struct mlx5_priv { int adev_idx; int sw_vhca_id; struct mlx5_events *events; + struct mlx5_vhca_events *vhca_events; struct mlx5_flow_steering *steering; struct mlx5_mpfs *mpfs; @@ -621,6 +624,7 @@ struct mlx5_priv { struct mlx5_lag *lag; u32 flags; struct mlx5_devcom_dev *devc; + struct mlx5_devcom_comp_dev *hca_devcom_comp; struct mlx5_fw_reset *fw_reset; struct mlx5_core_roce roce; struct mlx5_fc_stats fc_stats; @@ -1027,6 +1031,8 @@ bool mlx5_cmd_is_down(struct mlx5_core_dev *dev); void mlx5_core_uplink_netdev_set(struct mlx5_core_dev *mdev, struct net_device *netdev); void mlx5_core_uplink_netdev_event_replay(struct mlx5_core_dev *mdev); +void mlx5_core_mp_event_replay(struct mlx5_core_dev *dev, u32 event, void *data); + void mlx5_health_cleanup(struct mlx5_core_dev *dev); int mlx5_health_init(struct mlx5_core_dev *dev); void mlx5_start_health_poll(struct mlx5_core_dev *dev); @@ -1037,10 +1043,6 @@ void mlx5_trigger_health_work(struct mlx5_core_dev *dev); int mlx5_frag_buf_alloc_node(struct mlx5_core_dev *dev, int size, struct mlx5_frag_buf *buf, int node); void mlx5_frag_buf_free(struct mlx5_core_dev *dev, struct mlx5_frag_buf *buf); -struct mlx5_cmd_mailbox *mlx5_alloc_cmd_mailbox_chain(struct mlx5_core_dev *dev, - gfp_t flags, int npages); -void mlx5_free_cmd_mailbox_chain(struct mlx5_core_dev *dev, - struct mlx5_cmd_mailbox *head); int mlx5_core_create_mkey(struct mlx5_core_dev *dev, u32 *mkey, u32 *in, int inlen); int mlx5_core_destroy_mkey(struct mlx5_core_dev *dev, u32 mkey); @@ -1054,8 +1056,6 @@ void mlx5_pagealloc_start(struct mlx5_core_dev *dev); void mlx5_pagealloc_stop(struct mlx5_core_dev *dev); void mlx5_pages_debugfs_init(struct mlx5_core_dev *dev); void mlx5_pages_debugfs_cleanup(struct mlx5_core_dev *dev); -void mlx5_core_req_pages_handler(struct mlx5_core_dev *dev, u16 func_id, - s32 npages, bool ec_function); int mlx5_satisfy_startup_pages(struct mlx5_core_dev *dev, int boot); int mlx5_reclaim_startup_pages(struct mlx5_core_dev *dev); void mlx5_register_debugfs(void); @@ -1095,8 +1095,6 @@ int mlx5_core_create_psv(struct mlx5_core_dev *dev, u32 pdn, int mlx5_core_destroy_psv(struct mlx5_core_dev *dev, int psv_num); __be32 mlx5_core_get_terminate_scatter_list_mkey(struct mlx5_core_dev *dev); void mlx5_core_put_rsc(struct mlx5_core_rsc_common *common); -int mlx5_query_odp_caps(struct mlx5_core_dev *dev, - struct mlx5_odp_caps *odp_caps); int mlx5_init_rl_table(struct mlx5_core_dev *dev); void mlx5_cleanup_rl_table(struct mlx5_core_dev *dev); @@ -1198,12 +1196,6 @@ int mlx5_sriov_blocking_notifier_register(struct mlx5_core_dev *mdev, void mlx5_sriov_blocking_notifier_unregister(struct mlx5_core_dev *mdev, int vf_id, struct notifier_block *nb); -#ifdef CONFIG_MLX5_CORE_IPOIB -struct net_device *mlx5_rdma_netdev_alloc(struct mlx5_core_dev *mdev, - struct ib_device *ibdev, - const char *name, - void (*setup)(struct net_device *)); -#endif /* CONFIG_MLX5_CORE_IPOIB */ int mlx5_rdma_rn_get_params(struct mlx5_core_dev *mdev, struct ib_device *device, struct rdma_netdev_alloc_params *params); diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index 1e00c2436377..6f7725238abc 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -67,6 +67,7 @@ enum { MLX5_FLOW_TABLE_TERMINATION = BIT(2), MLX5_FLOW_TABLE_UNMANAGED = BIT(3), MLX5_FLOW_TABLE_OTHER_VPORT = BIT(4), + MLX5_FLOW_TABLE_UPLINK_VPORT = BIT(5), }; #define LEFTOVERS_RULE_NUM 2 diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index fc3db401f8a2..4df6d1c12437 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -312,6 +312,7 @@ enum { MLX5_CMD_OP_QUERY_VHCA_STATE = 0xb0d, MLX5_CMD_OP_MODIFY_VHCA_STATE = 0xb0e, MLX5_CMD_OP_SYNC_CRYPTO = 0xb12, + MLX5_CMD_OP_ALLOW_OTHER_VHCA_ACCESS = 0xb16, MLX5_CMD_OP_MAX }; @@ -1934,6 +1935,14 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 match_definer_format_supported[0x40]; }; +enum { + MLX5_CROSS_VHCA_OBJ_TO_OBJ_SUPPORTED_LOCAL_FLOW_TABLE_TO_REMOTE_FLOW_TABLE_MISS = 0x80000, +}; + +enum { + MLX5_ALLOWED_OBJ_FOR_OTHER_VHCA_ACCESS_FLOW_TABLE = 0x200, +}; + struct mlx5_ifc_cmd_hca_cap_2_bits { u8 reserved_at_0[0x80]; @@ -1948,9 +1957,15 @@ struct mlx5_ifc_cmd_hca_cap_2_bits { u8 reserved_at_c0[0x8]; u8 migration_multi_load[0x1]; u8 migration_tracking_state[0x1]; - u8 reserved_at_ca[0x16]; + u8 reserved_at_ca[0x6]; + u8 migration_in_chunks[0x1]; + u8 reserved_at_d1[0xf]; + + u8 cross_vhca_object_to_object_supported[0x20]; + + u8 allowed_object_for_other_vhca_access[0x40]; - u8 reserved_at_e0[0xc0]; + u8 reserved_at_140[0x60]; u8 flow_table_type_2_type[0x8]; u8 reserved_at_1a8[0x3]; @@ -6369,6 +6384,28 @@ struct mlx5_ifc_general_obj_out_cmd_hdr_bits { u8 reserved_at_60[0x20]; }; +struct mlx5_ifc_allow_other_vhca_access_in_bits { + u8 opcode[0x10]; + u8 uid[0x10]; + u8 reserved_at_20[0x10]; + u8 op_mod[0x10]; + u8 reserved_at_40[0x50]; + u8 object_type_to_be_accessed[0x10]; + u8 object_id_to_be_accessed[0x20]; + u8 reserved_at_c0[0x40]; + union { + u8 access_key_raw[0x100]; + u8 access_key[8][0x20]; + }; +}; + +struct mlx5_ifc_allow_other_vhca_access_out_bits { + u8 status[0x8]; + u8 reserved_at_8[0x18]; + u8 syndrome[0x20]; + u8 reserved_at_40[0x40]; +}; + struct mlx5_ifc_modify_header_arg_bits { u8 reserved_at_0[0x80]; @@ -6391,6 +6428,24 @@ struct mlx5_ifc_create_match_definer_out_bits { struct mlx5_ifc_general_obj_out_cmd_hdr_bits general_obj_out_cmd_hdr; }; +struct mlx5_ifc_alias_context_bits { + u8 vhca_id_to_be_accessed[0x10]; + u8 reserved_at_10[0xd]; + u8 status[0x3]; + u8 object_id_to_be_accessed[0x20]; + u8 reserved_at_40[0x40]; + union { + u8 access_key_raw[0x100]; + u8 access_key[8][0x20]; + }; + u8 metadata[0x80]; +}; + +struct mlx5_ifc_create_alias_obj_in_bits { + struct mlx5_ifc_general_obj_in_cmd_hdr_bits hdr; + struct mlx5_ifc_alias_context_bits alias_ctx; +}; + enum { MLX5_QUERY_FLOW_GROUP_OUT_MATCH_CRITERIA_ENABLE_OUTER_HEADERS = 0x0, MLX5_QUERY_FLOW_GROUP_OUT_MATCH_CRITERIA_ENABLE_MISC_PARAMETERS = 0x1, @@ -10176,7 +10231,9 @@ struct mlx5_ifc_mcam_access_reg_bits2 { u8 mirc[0x1]; u8 regs_97_to_96[0x2]; - u8 regs_95_to_64[0x20]; + u8 regs_95_to_87[0x09]; + u8 synce_registers[0x2]; + u8 regs_84_to_64[0x15]; u8 regs_63_to_32[0x20]; @@ -10572,6 +10629,7 @@ enum { MLX5_INITIAL_SEG_HEALTH_SYNDROME_EQ_INV = 0xe, MLX5_INITIAL_SEG_HEALTH_SYNDROME_FFSER_ERR = 0xf, MLX5_INITIAL_SEG_HEALTH_SYNDROME_HIGH_TEMP_ERR = 0x10, + MLX5_INITIAL_SEG_HEALTH_SYNDROME_ICM_PCI_POISONED_ERR = 0x12, }; struct mlx5_ifc_initial_seg_bits { @@ -11917,6 +11975,7 @@ enum { MLX5_GENERAL_OBJECT_TYPES_FLOW_METER_ASO = 0x24, MLX5_GENERAL_OBJECT_TYPES_MACSEC = 0x27, MLX5_GENERAL_OBJECT_TYPES_INT_KEK = 0x47, + MLX5_GENERAL_OBJECT_TYPES_FLOW_TABLE_ALIAS = 0xff15, }; enum { @@ -12392,7 +12451,8 @@ struct mlx5_ifc_query_vhca_migration_state_in_bits { u8 op_mod[0x10]; u8 incremental[0x1]; - u8 reserved_at_41[0xf]; + u8 chunk[0x1]; + u8 reserved_at_42[0xe]; u8 vhca_id[0x10]; u8 reserved_at_60[0x20]; @@ -12408,7 +12468,11 @@ struct mlx5_ifc_query_vhca_migration_state_out_bits { u8 required_umem_size[0x20]; - u8 reserved_at_a0[0x160]; + u8 reserved_at_a0[0x20]; + + u8 remaining_total_size[0x40]; + + u8 reserved_at_100[0x100]; }; struct mlx5_ifc_save_vhca_state_in_bits { @@ -12440,7 +12504,7 @@ struct mlx5_ifc_save_vhca_state_out_bits { u8 actual_image_size[0x20]; - u8 reserved_at_60[0x20]; + u8 next_required_umem_size[0x20]; }; struct mlx5_ifc_load_vhca_state_in_bits { @@ -12549,4 +12613,59 @@ struct mlx5_ifc_modify_page_track_obj_in_bits { struct mlx5_ifc_page_track_bits obj_context; }; +struct mlx5_ifc_msecq_reg_bits { + u8 reserved_at_0[0x20]; + + u8 reserved_at_20[0x12]; + u8 network_option[0x2]; + u8 local_ssm_code[0x4]; + u8 local_enhanced_ssm_code[0x8]; + + u8 local_clock_identity[0x40]; + + u8 reserved_at_80[0x180]; +}; + +enum { + MLX5_MSEES_FIELD_SELECT_ENABLE = BIT(0), + MLX5_MSEES_FIELD_SELECT_ADMIN_STATUS = BIT(1), + MLX5_MSEES_FIELD_SELECT_ADMIN_FREQ_MEASURE = BIT(2), +}; + +enum mlx5_msees_admin_status { + MLX5_MSEES_ADMIN_STATUS_FREE_RUNNING = 0x0, + MLX5_MSEES_ADMIN_STATUS_TRACK = 0x1, +}; + +enum mlx5_msees_oper_status { + MLX5_MSEES_OPER_STATUS_FREE_RUNNING = 0x0, + MLX5_MSEES_OPER_STATUS_SELF_TRACK = 0x1, + MLX5_MSEES_OPER_STATUS_OTHER_TRACK = 0x2, + MLX5_MSEES_OPER_STATUS_HOLDOVER = 0x3, + MLX5_MSEES_OPER_STATUS_FAIL_HOLDOVER = 0x4, + MLX5_MSEES_OPER_STATUS_FAIL_FREE_RUNNING = 0x5, +}; + +struct mlx5_ifc_msees_reg_bits { + u8 reserved_at_0[0x8]; + u8 local_port[0x8]; + u8 pnat[0x2]; + u8 lp_msb[0x2]; + u8 reserved_at_14[0xc]; + + u8 field_select[0x20]; + + u8 admin_status[0x4]; + u8 oper_status[0x4]; + u8 ho_acq[0x1]; + u8 reserved_at_49[0xc]; + u8 admin_freq_measure[0x1]; + u8 oper_freq_measure[0x1]; + u8 failure_reason[0x9]; + + u8 frequency_diff[0x20]; + + u8 reserved_at_80[0x180]; +}; + #endif /* MLX5_IFC_H */ diff --git a/include/linux/mm.h b/include/linux/mm.h index bf5d0b1b16f4..116c28c51468 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1726,8 +1726,8 @@ static inline void vma_set_access_pid_bit(struct vm_area_struct *vma) unsigned int pid_bit; pid_bit = hash_32(current->pid, ilog2(BITS_PER_LONG)); - if (vma->numab_state && !test_bit(pid_bit, &vma->numab_state->access_pids[1])) { - __set_bit(pid_bit, &vma->numab_state->access_pids[1]); + if (vma->numab_state && !test_bit(pid_bit, &vma->numab_state->pids_active[1])) { + __set_bit(pid_bit, &vma->numab_state->pids_active[1]); } } #else /* !CONFIG_NUMA_BALANCING */ @@ -3308,8 +3308,7 @@ static inline void mm_populate(unsigned long addr, unsigned long len) static inline void mm_populate(unsigned long addr, unsigned long len) {} #endif -/* These take the mm semaphore themselves */ -extern int __must_check vm_brk(unsigned long, unsigned long); +/* This takes the mm semaphore itself */ extern int __must_check vm_brk_flags(unsigned long, unsigned long, unsigned long); extern int vm_munmap(unsigned long, size_t); extern unsigned long __must_check vm_mmap(struct file *, unsigned long, diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 36c5b43999e6..4be8e310b189 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -125,18 +125,7 @@ struct page { struct page_pool *pp; unsigned long _pp_mapping_pad; unsigned long dma_addr; - union { - /** - * dma_addr_upper: might require a 64-bit - * value on 32-bit architectures. - */ - unsigned long dma_addr_upper; - /** - * For frag page support, not supported in - * 32-bit architectures with 64-bit DMA. - */ - atomic_long_t pp_frag_count; - }; + atomic_long_t pp_frag_count; }; struct { /* Tail pages of compound page */ unsigned long compound_head; /* Bit zero is set */ @@ -551,9 +540,36 @@ struct vma_lock { }; struct vma_numab_state { + /* + * Initialised as time in 'jiffies' after which VMA + * should be scanned. Delays first scan of new VMA by at + * least sysctl_numa_balancing_scan_delay: + */ unsigned long next_scan; - unsigned long next_pid_reset; - unsigned long access_pids[2]; + + /* + * Time in jiffies when pids_active[] is reset to + * detect phase change behaviour: + */ + unsigned long pids_active_reset; + + /* + * Approximate tracking of PIDs that trapped a NUMA hinting + * fault. May produce false positives due to hash collisions. + * + * [0] Previous PID tracking + * [1] Current PID tracking + * + * Window moves after next_pid_reset has expired approximately + * every VMA_PID_RESET_PERIOD jiffies: + */ + unsigned long pids_active[2]; + + /* + * MM scan sequence ID when the VMA was last completely scanned. + * A VMA is not eligible for scanning if prev_scan_seq == numa_scan_seq + */ + int prev_scan_seq; }; /* diff --git a/include/linux/mount.h b/include/linux/mount.h index 4f40b40306d0..ac3dd2876197 100644 --- a/include/linux/mount.h +++ b/include/linux/mount.h @@ -92,8 +92,8 @@ extern bool __mnt_is_readonly(struct vfsmount *mnt); extern bool mnt_may_suid(struct vfsmount *mnt); extern struct vfsmount *clone_private_mount(const struct path *path); -extern int __mnt_want_write(struct vfsmount *); -extern void __mnt_drop_write(struct vfsmount *); +int mnt_get_write_access(struct vfsmount *mnt); +void mnt_put_write_access(struct vfsmount *mnt); extern struct vfsmount *fc_mount(struct fs_context *fc); extern struct vfsmount *vfs_create_mount(struct fs_context *fc); diff --git a/include/linux/msi.h b/include/linux/msi.h index a50ea79522f8..ddace8c34dcf 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -547,12 +547,6 @@ enum { MSI_FLAG_ALLOC_SIMPLE_MSI_DESCS = (1 << 5), /* Free MSI descriptors */ MSI_FLAG_FREE_MSI_DESCS = (1 << 6), - /* - * Quirk to handle MSI implementations which do not provide - * masking. Currently known to affect x86, but has to be partially - * handled in the core MSI code. - */ - MSI_FLAG_NOMASK_QUIRK = (1 << 7), /* Mask for the generic functionality */ MSI_GENERIC_FLAGS_MASK = GENMASK(15, 0), diff --git a/include/linux/mtd/jedec.h b/include/linux/mtd/jedec.h index 0b6b59f7cfbd..56047a4e54c9 100644 --- a/include/linux/mtd/jedec.h +++ b/include/linux/mtd/jedec.h @@ -21,6 +21,9 @@ struct jedec_ecc_info { /* JEDEC features */ #define JEDEC_FEATURE_16_BIT_BUS (1 << 0) +/* JEDEC Optional Commands */ +#define JEDEC_OPT_CMD_READ_CACHE BIT(1) + struct nand_jedec_params { /* rev info and features block */ /* 'J' 'E' 'S' 'D' */ diff --git a/include/linux/mtd/onfi.h b/include/linux/mtd/onfi.h index a7376f9beddf..55ab2e4d62f9 100644 --- a/include/linux/mtd/onfi.h +++ b/include/linux/mtd/onfi.h @@ -55,6 +55,7 @@ #define ONFI_SUBFEATURE_PARAM_LEN 4 /* ONFI optional commands SET/GET FEATURES supported? */ +#define ONFI_OPT_CMD_READ_CACHE BIT(1) #define ONFI_OPT_CMD_SET_GET_FEATURES BIT(2) struct nand_onfi_params { diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 90a141ba2a5a..c29ace15a053 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -225,6 +225,7 @@ struct gpio_desc; * struct nand_parameters - NAND generic parameters from the parameter page * @model: Model name * @supports_set_get_features: The NAND chip supports setting/getting features + * @supports_read_cache: The NAND chip supports read cache operations * @set_feature_list: Bitmap of features that can be set * @get_feature_list: Bitmap of features that can be get * @onfi: ONFI specific parameters @@ -233,6 +234,7 @@ struct nand_parameters { /* Generic parameters */ const char *model; bool supports_set_get_features; + bool supports_read_cache; DECLARE_BITMAP(set_feature_list, ONFI_FEATURE_NUMBER); DECLARE_BITMAP(get_feature_list, ONFI_FEATURE_NUMBER); diff --git a/include/linux/namei.h b/include/linux/namei.h index 1463cbda4888..3100371b5e32 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -92,6 +92,30 @@ extern struct dentry *lock_rename(struct dentry *, struct dentry *); extern struct dentry *lock_rename_child(struct dentry *, struct dentry *); extern void unlock_rename(struct dentry *, struct dentry *); +/** + * mode_strip_umask - handle vfs umask stripping + * @dir: parent directory of the new inode + * @mode: mode of the new inode to be created in @dir + * + * In most filesystems, umask stripping depends on whether or not the + * filesystem supports POSIX ACLs. If the filesystem doesn't support it umask + * stripping is done directly in here. If the filesystem does support POSIX + * ACLs umask stripping is deferred until the filesystem calls + * posix_acl_create(). + * + * Some filesystems (like NFSv4) also want to avoid umask stripping by the + * VFS, but don't support POSIX ACLs. Those filesystems can set SB_I_NOUMASK + * to get this effect without declaring that they support POSIX ACLs. + * + * Returns: mode + */ +static inline umode_t __must_check mode_strip_umask(const struct inode *dir, umode_t mode) +{ + if (!IS_POSIXACL(dir) && !(dir->i_sb->s_iflags & SB_I_NOUMASK)) + mode &= ~current_umask(); + return mode; +} + extern int __must_check nd_jump_link(const struct path *path); static inline void nd_terminate_link(void *name, size_t len, size_t maxlen) @@ -112,7 +136,7 @@ static inline void nd_terminate_link(void *name, size_t len, size_t maxlen) static inline bool retry_estale(const long error, const unsigned int flags) { - return error == -ESTALE && !(flags & LOOKUP_REVAL); + return unlikely(error == -ESTALE && !(flags & LOOKUP_REVAL)); } #endif /* _LINUX_NAMEI_H */ diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 0896aaa91dd7..a16c9cc063fe 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -79,6 +79,8 @@ struct xdp_buff; struct xdp_frame; struct xdp_metadata_ops; struct xdp_md; +/* DPLL specific */ +struct dpll_pin; typedef u32 xdp_features_t; @@ -480,6 +482,29 @@ static inline bool napi_prefer_busy_poll(struct napi_struct *n) return test_bit(NAPI_STATE_PREFER_BUSY_POLL, &n->state); } +/** + * napi_is_scheduled - test if NAPI is scheduled + * @n: NAPI context + * + * This check is "best-effort". With no locking implemented, + * a NAPI can be scheduled or terminate right after this check + * and produce not precise results. + * + * NAPI_STATE_SCHED is an internal state, napi_is_scheduled + * should not be used normally and napi_schedule should be + * used instead. + * + * Use only if the driver really needs to check if a NAPI + * is scheduled for example in the context of delayed timer + * that can be skipped if a NAPI is already scheduled. + * + * Return True if NAPI is scheduled, False otherwise. + */ +static inline bool napi_is_scheduled(struct napi_struct *n) +{ + return test_bit(NAPI_STATE_SCHED, &n->state); +} + bool napi_schedule_prep(struct napi_struct *n); /** @@ -488,11 +513,18 @@ bool napi_schedule_prep(struct napi_struct *n); * * Schedule NAPI poll routine to be called if it is not already * running. + * Return true if we schedule a NAPI or false if not. + * Refer to napi_schedule_prep() for additional reason on why + * a NAPI might not be scheduled. */ -static inline void napi_schedule(struct napi_struct *n) +static inline bool napi_schedule(struct napi_struct *n) { - if (napi_schedule_prep(n)) + if (napi_schedule_prep(n)) { __napi_schedule(n); + return true; + } + + return false; } /** @@ -507,16 +539,6 @@ static inline void napi_schedule_irqoff(struct napi_struct *n) __napi_schedule_irqoff(n); } -/* Try to reschedule poll. Called by dev->poll() after napi_complete(). */ -static inline bool napi_reschedule(struct napi_struct *napi) -{ - if (napi_schedule_prep(napi)) { - __napi_schedule(napi); - return true; - } - return false; -} - /** * napi_complete_done - NAPI processing complete * @n: NAPI context @@ -917,6 +939,7 @@ struct net_device_path { u8 queue; u16 wcid; u8 bss; + u8 amsdu; } mtk_wdma; }; }; @@ -1287,9 +1310,7 @@ struct netdev_net_notifier { * struct net_device *dev, * const unsigned char *addr, u16 vid) * Deletes the FDB entry from dev coresponding to addr. - * int (*ndo_fdb_del_bulk)(struct ndmsg *ndm, struct nlattr *tb[], - * struct net_device *dev, - * u16 vid, + * int (*ndo_fdb_del_bulk)(struct nlmsghdr *nlh, struct net_device *dev, * struct netlink_ext_ack *extack); * int (*ndo_fdb_dump)(struct sk_buff *skb, struct netlink_callback *cb, * struct net_device *dev, struct net_device *filter_dev, @@ -1564,10 +1585,8 @@ struct net_device_ops { struct net_device *dev, const unsigned char *addr, u16 vid, struct netlink_ext_ack *extack); - int (*ndo_fdb_del_bulk)(struct ndmsg *ndm, - struct nlattr *tb[], + int (*ndo_fdb_del_bulk)(struct nlmsghdr *nlh, struct net_device *dev, - u16 vid, struct netlink_ext_ack *extack); int (*ndo_fdb_dump)(struct sk_buff *skb, struct netlink_callback *cb, @@ -1590,6 +1609,10 @@ struct net_device_ops { int (*ndo_mdb_dump)(struct net_device *dev, struct sk_buff *skb, struct netlink_callback *cb); + int (*ndo_mdb_get)(struct net_device *dev, + struct nlattr *tb[], u32 portid, + u32 seq, + struct netlink_ext_ack *extack); int (*ndo_bridge_setlink)(struct net_device *dev, struct nlmsghdr *nlh, u16 flags, @@ -2049,6 +2072,9 @@ enum netdev_ml_priv_type { * SET_NETDEV_DEVLINK_PORT macro. This pointer is static * during the time netdevice is registered. * + * @dpll_pin: Pointer to the SyncE source pin of a DPLL subsystem, + * where the clock is recovered. + * * FIXME: cleanup struct net_device such that network protocol info * moves out. */ @@ -2405,6 +2431,10 @@ struct net_device { struct rtnl_hw_stats64 *offload_xstats_l3; struct devlink_port *devlink_port; + +#if IS_ENABLED(CONFIG_DPLL) + struct dpll_pin *dpll_pin; +#endif }; #define to_net_dev(d) container_of(d, struct net_device, dev) @@ -3940,6 +3970,18 @@ int dev_get_mac_address(struct sockaddr *sa, struct net *net, char *dev_name); int dev_get_port_parent_id(struct net_device *dev, struct netdev_phys_item_id *ppid, bool recurse); bool netdev_port_same_parent_id(struct net_device *a, struct net_device *b); +void netdev_dpll_pin_set(struct net_device *dev, struct dpll_pin *dpll_pin); +void netdev_dpll_pin_clear(struct net_device *dev); + +static inline struct dpll_pin *netdev_dpll_pin(const struct net_device *dev) +{ +#if IS_ENABLED(CONFIG_DPLL) + return dev->dpll_pin; +#else + return NULL; +#endif +} + struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *dev, bool *again); struct sk_buff *dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, struct netdev_queue *txq, int *ret); @@ -3980,32 +4022,19 @@ static __always_inline bool __is_skb_forwardable(const struct net_device *dev, return false; } -struct net_device_core_stats __percpu *netdev_core_stats_alloc(struct net_device *dev); - -static inline struct net_device_core_stats __percpu *dev_core_stats(struct net_device *dev) -{ - /* This READ_ONCE() pairs with the write in netdev_core_stats_alloc() */ - struct net_device_core_stats __percpu *p = READ_ONCE(dev->core_stats); - - if (likely(p)) - return p; - - return netdev_core_stats_alloc(dev); -} +void netdev_core_stats_inc(struct net_device *dev, u32 offset); #define DEV_CORE_STATS_INC(FIELD) \ static inline void dev_core_stats_##FIELD##_inc(struct net_device *dev) \ { \ - struct net_device_core_stats __percpu *p; \ - \ - p = dev_core_stats(dev); \ - if (p) \ - this_cpu_inc(p->FIELD); \ + netdev_core_stats_inc(dev, \ + offsetof(struct net_device_core_stats, FIELD)); \ } DEV_CORE_STATS_INC(rx_dropped) DEV_CORE_STATS_INC(tx_dropped) DEV_CORE_STATS_INC(rx_nohandler) DEV_CORE_STATS_INC(rx_otherhost_dropped) +#undef DEV_CORE_STATS_INC static __always_inline int ____dev_forward_skb(struct net_device *dev, struct sk_buff *skb, @@ -5214,5 +5243,6 @@ extern struct net_device *blackhole_netdev; #define DEV_STATS_INC(DEV, FIELD) atomic_long_inc(&(DEV)->stats.__##FIELD) #define DEV_STATS_ADD(DEV, FIELD, VAL) \ atomic_long_add((VAL), &(DEV)->stats.__##FIELD) +#define DEV_STATS_READ(DEV, FIELD) atomic_long_read(&(DEV)->stats.__##FIELD) #endif /* _LINUX_NETDEVICE_H */ diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index d68644b7c299..80900d910992 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -22,6 +22,16 @@ static inline int NF_DROP_GETERR(int verdict) return -(verdict >> NF_VERDICT_QBITS); } +static __always_inline int +NF_DROP_REASON(struct sk_buff *skb, enum skb_drop_reason reason, u32 err) +{ + BUILD_BUG_ON(err > 0xffff); + + kfree_skb_reason(skb, reason); + + return ((err << 16) | NF_STOLEN); +} + static inline int nf_inet_addr_cmp(const union nf_inet_addr *a1, const union nf_inet_addr *a2) { diff --git a/include/linux/netfilter/nf_conntrack_sctp.h b/include/linux/netfilter/nf_conntrack_sctp.h index 625f491b95de..fb31312825ae 100644 --- a/include/linux/netfilter/nf_conntrack_sctp.h +++ b/include/linux/netfilter/nf_conntrack_sctp.h @@ -9,6 +9,7 @@ struct ip_ct_sctp { enum sctp_conntrack state; __be32 vtag[IP_CT_DIR_MAX]; + u8 init[IP_CT_DIR_MAX]; u8 last_dir; u8 flags; }; diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index 730003c4f4af..c11c4db34639 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -150,7 +150,7 @@ enum nfs_opnum4 { OP_WRITE_SAME = 70, OP_CLONE = 71, - /* xattr support (RFC8726) */ + /* xattr support (RFC8276) */ OP_GETXATTR = 72, OP_SETXATTR = 73, OP_LISTXATTRS = 74, @@ -389,79 +389,203 @@ enum lock_type4 { NFS4_WRITEW_LT = 4 }; +/* + * Symbol names and values are from RFC 7531 Section 2. + * "XDR Description of NFSv4.0" + */ +enum { + FATTR4_SUPPORTED_ATTRS = 0, + FATTR4_TYPE = 1, + FATTR4_FH_EXPIRE_TYPE = 2, + FATTR4_CHANGE = 3, + FATTR4_SIZE = 4, + FATTR4_LINK_SUPPORT = 5, + FATTR4_SYMLINK_SUPPORT = 6, + FATTR4_NAMED_ATTR = 7, + FATTR4_FSID = 8, + FATTR4_UNIQUE_HANDLES = 9, + FATTR4_LEASE_TIME = 10, + FATTR4_RDATTR_ERROR = 11, + FATTR4_ACL = 12, + FATTR4_ACLSUPPORT = 13, + FATTR4_ARCHIVE = 14, + FATTR4_CANSETTIME = 15, + FATTR4_CASE_INSENSITIVE = 16, + FATTR4_CASE_PRESERVING = 17, + FATTR4_CHOWN_RESTRICTED = 18, + FATTR4_FILEHANDLE = 19, + FATTR4_FILEID = 20, + FATTR4_FILES_AVAIL = 21, + FATTR4_FILES_FREE = 22, + FATTR4_FILES_TOTAL = 23, + FATTR4_FS_LOCATIONS = 24, + FATTR4_HIDDEN = 25, + FATTR4_HOMOGENEOUS = 26, + FATTR4_MAXFILESIZE = 27, + FATTR4_MAXLINK = 28, + FATTR4_MAXNAME = 29, + FATTR4_MAXREAD = 30, + FATTR4_MAXWRITE = 31, + FATTR4_MIMETYPE = 32, + FATTR4_MODE = 33, + FATTR4_NO_TRUNC = 34, + FATTR4_NUMLINKS = 35, + FATTR4_OWNER = 36, + FATTR4_OWNER_GROUP = 37, + FATTR4_QUOTA_AVAIL_HARD = 38, + FATTR4_QUOTA_AVAIL_SOFT = 39, + FATTR4_QUOTA_USED = 40, + FATTR4_RAWDEV = 41, + FATTR4_SPACE_AVAIL = 42, + FATTR4_SPACE_FREE = 43, + FATTR4_SPACE_TOTAL = 44, + FATTR4_SPACE_USED = 45, + FATTR4_SYSTEM = 46, + FATTR4_TIME_ACCESS = 47, + FATTR4_TIME_ACCESS_SET = 48, + FATTR4_TIME_BACKUP = 49, + FATTR4_TIME_CREATE = 50, + FATTR4_TIME_DELTA = 51, + FATTR4_TIME_METADATA = 52, + FATTR4_TIME_MODIFY = 53, + FATTR4_TIME_MODIFY_SET = 54, + FATTR4_MOUNTED_ON_FILEID = 55, +}; + +/* + * Symbol names and values are from RFC 5662 Section 2. + * "XDR Description of NFSv4.1" + */ +enum { + FATTR4_DIR_NOTIF_DELAY = 56, + FATTR4_DIRENT_NOTIF_DELAY = 57, + FATTR4_DACL = 58, + FATTR4_SACL = 59, + FATTR4_CHANGE_POLICY = 60, + FATTR4_FS_STATUS = 61, + FATTR4_FS_LAYOUT_TYPES = 62, + FATTR4_LAYOUT_HINT = 63, + FATTR4_LAYOUT_TYPES = 64, + FATTR4_LAYOUT_BLKSIZE = 65, + FATTR4_LAYOUT_ALIGNMENT = 66, + FATTR4_FS_LOCATIONS_INFO = 67, + FATTR4_MDSTHRESHOLD = 68, + FATTR4_RETENTION_GET = 69, + FATTR4_RETENTION_SET = 70, + FATTR4_RETENTEVT_GET = 71, + FATTR4_RETENTEVT_SET = 72, + FATTR4_RETENTION_HOLD = 73, + FATTR4_MODE_SET_MASKED = 74, + FATTR4_SUPPATTR_EXCLCREAT = 75, + FATTR4_FS_CHARSET_CAP = 76, +}; + +/* + * Symbol names and values are from RFC 7863 Section 2. + * "XDR Description of NFSv4.2" + */ +enum { + FATTR4_CLONE_BLKSIZE = 77, + FATTR4_SPACE_FREED = 78, + FATTR4_CHANGE_ATTR_TYPE = 79, + FATTR4_SEC_LABEL = 80, +}; + +/* + * Symbol names and values are from RFC 8275 Section 5. + * "The mode_umask Attribute" + */ +enum { + FATTR4_MODE_UMASK = 81, +}; + +/* + * Symbol names and values are from RFC 8276 Section 8.6. + * "Numeric Values Assigned to Protocol Extensions" + */ +enum { + FATTR4_XATTR_SUPPORT = 82, +}; + +/* + * The following internal definitions enable processing the above + * attribute bits within 32-bit word boundaries. + */ /* Mandatory Attributes */ -#define FATTR4_WORD0_SUPPORTED_ATTRS (1UL << 0) -#define FATTR4_WORD0_TYPE (1UL << 1) -#define FATTR4_WORD0_FH_EXPIRE_TYPE (1UL << 2) -#define FATTR4_WORD0_CHANGE (1UL << 3) -#define FATTR4_WORD0_SIZE (1UL << 4) -#define FATTR4_WORD0_LINK_SUPPORT (1UL << 5) -#define FATTR4_WORD0_SYMLINK_SUPPORT (1UL << 6) -#define FATTR4_WORD0_NAMED_ATTR (1UL << 7) -#define FATTR4_WORD0_FSID (1UL << 8) -#define FATTR4_WORD0_UNIQUE_HANDLES (1UL << 9) -#define FATTR4_WORD0_LEASE_TIME (1UL << 10) -#define FATTR4_WORD0_RDATTR_ERROR (1UL << 11) +#define FATTR4_WORD0_SUPPORTED_ATTRS BIT(FATTR4_SUPPORTED_ATTRS) +#define FATTR4_WORD0_TYPE BIT(FATTR4_TYPE) +#define FATTR4_WORD0_FH_EXPIRE_TYPE BIT(FATTR4_FH_EXPIRE_TYPE) +#define FATTR4_WORD0_CHANGE BIT(FATTR4_CHANGE) +#define FATTR4_WORD0_SIZE BIT(FATTR4_SIZE) +#define FATTR4_WORD0_LINK_SUPPORT BIT(FATTR4_LINK_SUPPORT) +#define FATTR4_WORD0_SYMLINK_SUPPORT BIT(FATTR4_SYMLINK_SUPPORT) +#define FATTR4_WORD0_NAMED_ATTR BIT(FATTR4_NAMED_ATTR) +#define FATTR4_WORD0_FSID BIT(FATTR4_FSID) +#define FATTR4_WORD0_UNIQUE_HANDLES BIT(FATTR4_UNIQUE_HANDLES) +#define FATTR4_WORD0_LEASE_TIME BIT(FATTR4_LEASE_TIME) +#define FATTR4_WORD0_RDATTR_ERROR BIT(FATTR4_RDATTR_ERROR) /* Mandatory in NFSv4.1 */ -#define FATTR4_WORD2_SUPPATTR_EXCLCREAT (1UL << 11) +#define FATTR4_WORD2_SUPPATTR_EXCLCREAT BIT(FATTR4_SUPPATTR_EXCLCREAT - 64) /* Recommended Attributes */ -#define FATTR4_WORD0_ACL (1UL << 12) -#define FATTR4_WORD0_ACLSUPPORT (1UL << 13) -#define FATTR4_WORD0_ARCHIVE (1UL << 14) -#define FATTR4_WORD0_CANSETTIME (1UL << 15) -#define FATTR4_WORD0_CASE_INSENSITIVE (1UL << 16) -#define FATTR4_WORD0_CASE_PRESERVING (1UL << 17) -#define FATTR4_WORD0_CHOWN_RESTRICTED (1UL << 18) -#define FATTR4_WORD0_FILEHANDLE (1UL << 19) -#define FATTR4_WORD0_FILEID (1UL << 20) -#define FATTR4_WORD0_FILES_AVAIL (1UL << 21) -#define FATTR4_WORD0_FILES_FREE (1UL << 22) -#define FATTR4_WORD0_FILES_TOTAL (1UL << 23) -#define FATTR4_WORD0_FS_LOCATIONS (1UL << 24) -#define FATTR4_WORD0_HIDDEN (1UL << 25) -#define FATTR4_WORD0_HOMOGENEOUS (1UL << 26) -#define FATTR4_WORD0_MAXFILESIZE (1UL << 27) -#define FATTR4_WORD0_MAXLINK (1UL << 28) -#define FATTR4_WORD0_MAXNAME (1UL << 29) -#define FATTR4_WORD0_MAXREAD (1UL << 30) -#define FATTR4_WORD0_MAXWRITE (1UL << 31) -#define FATTR4_WORD1_MIMETYPE (1UL << 0) -#define FATTR4_WORD1_MODE (1UL << 1) -#define FATTR4_WORD1_NO_TRUNC (1UL << 2) -#define FATTR4_WORD1_NUMLINKS (1UL << 3) -#define FATTR4_WORD1_OWNER (1UL << 4) -#define FATTR4_WORD1_OWNER_GROUP (1UL << 5) -#define FATTR4_WORD1_QUOTA_HARD (1UL << 6) -#define FATTR4_WORD1_QUOTA_SOFT (1UL << 7) -#define FATTR4_WORD1_QUOTA_USED (1UL << 8) -#define FATTR4_WORD1_RAWDEV (1UL << 9) -#define FATTR4_WORD1_SPACE_AVAIL (1UL << 10) -#define FATTR4_WORD1_SPACE_FREE (1UL << 11) -#define FATTR4_WORD1_SPACE_TOTAL (1UL << 12) -#define FATTR4_WORD1_SPACE_USED (1UL << 13) -#define FATTR4_WORD1_SYSTEM (1UL << 14) -#define FATTR4_WORD1_TIME_ACCESS (1UL << 15) -#define FATTR4_WORD1_TIME_ACCESS_SET (1UL << 16) -#define FATTR4_WORD1_TIME_BACKUP (1UL << 17) -#define FATTR4_WORD1_TIME_CREATE (1UL << 18) -#define FATTR4_WORD1_TIME_DELTA (1UL << 19) -#define FATTR4_WORD1_TIME_METADATA (1UL << 20) -#define FATTR4_WORD1_TIME_MODIFY (1UL << 21) -#define FATTR4_WORD1_TIME_MODIFY_SET (1UL << 22) -#define FATTR4_WORD1_MOUNTED_ON_FILEID (1UL << 23) -#define FATTR4_WORD1_DACL (1UL << 26) -#define FATTR4_WORD1_SACL (1UL << 27) -#define FATTR4_WORD1_FS_LAYOUT_TYPES (1UL << 30) -#define FATTR4_WORD2_LAYOUT_TYPES (1UL << 0) -#define FATTR4_WORD2_LAYOUT_BLKSIZE (1UL << 1) -#define FATTR4_WORD2_MDSTHRESHOLD (1UL << 4) -#define FATTR4_WORD2_CLONE_BLKSIZE (1UL << 13) -#define FATTR4_WORD2_CHANGE_ATTR_TYPE (1UL << 15) -#define FATTR4_WORD2_SECURITY_LABEL (1UL << 16) -#define FATTR4_WORD2_MODE_UMASK (1UL << 17) -#define FATTR4_WORD2_XATTR_SUPPORT (1UL << 18) +#define FATTR4_WORD0_ACL BIT(FATTR4_ACL) +#define FATTR4_WORD0_ACLSUPPORT BIT(FATTR4_ACLSUPPORT) +#define FATTR4_WORD0_ARCHIVE BIT(FATTR4_ARCHIVE) +#define FATTR4_WORD0_CANSETTIME BIT(FATTR4_CANSETTIME) +#define FATTR4_WORD0_CASE_INSENSITIVE BIT(FATTR4_CASE_INSENSITIVE) +#define FATTR4_WORD0_CASE_PRESERVING BIT(FATTR4_CASE_PRESERVING) +#define FATTR4_WORD0_CHOWN_RESTRICTED BIT(FATTR4_CHOWN_RESTRICTED) +#define FATTR4_WORD0_FILEHANDLE BIT(FATTR4_FILEHANDLE) +#define FATTR4_WORD0_FILEID BIT(FATTR4_FILEID) +#define FATTR4_WORD0_FILES_AVAIL BIT(FATTR4_FILES_AVAIL) +#define FATTR4_WORD0_FILES_FREE BIT(FATTR4_FILES_FREE) +#define FATTR4_WORD0_FILES_TOTAL BIT(FATTR4_FILES_TOTAL) +#define FATTR4_WORD0_FS_LOCATIONS BIT(FATTR4_FS_LOCATIONS) +#define FATTR4_WORD0_HIDDEN BIT(FATTR4_HIDDEN) +#define FATTR4_WORD0_HOMOGENEOUS BIT(FATTR4_HOMOGENEOUS) +#define FATTR4_WORD0_MAXFILESIZE BIT(FATTR4_MAXFILESIZE) +#define FATTR4_WORD0_MAXLINK BIT(FATTR4_MAXLINK) +#define FATTR4_WORD0_MAXNAME BIT(FATTR4_MAXNAME) +#define FATTR4_WORD0_MAXREAD BIT(FATTR4_MAXREAD) +#define FATTR4_WORD0_MAXWRITE BIT(FATTR4_MAXWRITE) + +#define FATTR4_WORD1_MIMETYPE BIT(FATTR4_MIMETYPE - 32) +#define FATTR4_WORD1_MODE BIT(FATTR4_MODE - 32) +#define FATTR4_WORD1_NO_TRUNC BIT(FATTR4_NO_TRUNC - 32) +#define FATTR4_WORD1_NUMLINKS BIT(FATTR4_NUMLINKS - 32) +#define FATTR4_WORD1_OWNER BIT(FATTR4_OWNER - 32) +#define FATTR4_WORD1_OWNER_GROUP BIT(FATTR4_OWNER_GROUP - 32) +#define FATTR4_WORD1_QUOTA_HARD BIT(FATTR4_QUOTA_AVAIL_HARD - 32) +#define FATTR4_WORD1_QUOTA_SOFT BIT(FATTR4_QUOTA_AVAIL_SOFT - 32) +#define FATTR4_WORD1_QUOTA_USED BIT(FATTR4_QUOTA_USED - 32) +#define FATTR4_WORD1_RAWDEV BIT(FATTR4_RAWDEV - 32) +#define FATTR4_WORD1_SPACE_AVAIL BIT(FATTR4_SPACE_AVAIL - 32) +#define FATTR4_WORD1_SPACE_FREE BIT(FATTR4_SPACE_FREE - 32) +#define FATTR4_WORD1_SPACE_TOTAL BIT(FATTR4_SPACE_TOTAL - 32) +#define FATTR4_WORD1_SPACE_USED BIT(FATTR4_SPACE_USED - 32) +#define FATTR4_WORD1_SYSTEM BIT(FATTR4_SYSTEM - 32) +#define FATTR4_WORD1_TIME_ACCESS BIT(FATTR4_TIME_ACCESS - 32) +#define FATTR4_WORD1_TIME_ACCESS_SET BIT(FATTR4_TIME_ACCESS_SET - 32) +#define FATTR4_WORD1_TIME_BACKUP BIT(FATTR4_TIME_BACKUP - 32) +#define FATTR4_WORD1_TIME_CREATE BIT(FATTR4_TIME_CREATE - 32) +#define FATTR4_WORD1_TIME_DELTA BIT(FATTR4_TIME_DELTA - 32) +#define FATTR4_WORD1_TIME_METADATA BIT(FATTR4_TIME_METADATA - 32) +#define FATTR4_WORD1_TIME_MODIFY BIT(FATTR4_TIME_MODIFY - 32) +#define FATTR4_WORD1_TIME_MODIFY_SET BIT(FATTR4_TIME_MODIFY_SET - 32) +#define FATTR4_WORD1_MOUNTED_ON_FILEID BIT(FATTR4_MOUNTED_ON_FILEID - 32) +#define FATTR4_WORD1_DACL BIT(FATTR4_DACL - 32) +#define FATTR4_WORD1_SACL BIT(FATTR4_SACL - 32) +#define FATTR4_WORD1_FS_LAYOUT_TYPES BIT(FATTR4_FS_LAYOUT_TYPES - 32) + +#define FATTR4_WORD2_LAYOUT_TYPES BIT(FATTR4_LAYOUT_TYPES - 64) +#define FATTR4_WORD2_LAYOUT_BLKSIZE BIT(FATTR4_LAYOUT_BLKSIZE - 64) +#define FATTR4_WORD2_MDSTHRESHOLD BIT(FATTR4_MDSTHRESHOLD - 64) +#define FATTR4_WORD2_CLONE_BLKSIZE BIT(FATTR4_CLONE_BLKSIZE - 64) +#define FATTR4_WORD2_CHANGE_ATTR_TYPE BIT(FATTR4_CHANGE_ATTR_TYPE - 64) +#define FATTR4_WORD2_SECURITY_LABEL BIT(FATTR4_SEC_LABEL - 64) +#define FATTR4_WORD2_MODE_UMASK BIT(FATTR4_MODE_UMASK - 64) +#define FATTR4_WORD2_XATTR_SUPPORT BIT(FATTR4_XATTR_SUPPORT - 64) /* MDS threshold bitmap bits */ #define THRESHOLD_RD (1UL << 0) diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index 20eeba8b009d..cd628c4b011e 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -48,6 +48,7 @@ struct nfs_client { #define NFS_CS_NOPING 6 /* - don't ping on connect */ #define NFS_CS_DS 7 /* - Server is a DS */ #define NFS_CS_REUSEPORT 8 /* - reuse src port on reconnect */ +#define NFS_CS_PNFS 9 /* - Server used for pnfs */ struct sockaddr_storage cl_addr; /* server identifier */ size_t cl_addrlen; char * cl_hostname; /* hostname of server */ diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h index aa9f4c6ebe26..1c315f854ea8 100644 --- a/include/linux/nfs_page.h +++ b/include/linux/nfs_page.h @@ -157,7 +157,9 @@ extern void nfs_unlock_request(struct nfs_page *req); extern void nfs_unlock_and_release_request(struct nfs_page *); extern struct nfs_page *nfs_page_group_lock_head(struct nfs_page *req); extern int nfs_page_group_lock_subrequests(struct nfs_page *head); -extern void nfs_join_page_group(struct nfs_page *head, struct inode *inode); +extern void nfs_join_page_group(struct nfs_page *head, + struct nfs_commit_info *cinfo, + struct inode *inode); extern int nfs_page_group_lock(struct nfs_page *); extern void nfs_page_group_unlock(struct nfs_page *); extern bool nfs_page_group_sync_on_bit(struct nfs_page *, unsigned int); diff --git a/include/linux/numa.h b/include/linux/numa.h index 59df211d051f..a904861de800 100644 --- a/include/linux/numa.h +++ b/include/linux/numa.h @@ -12,6 +12,7 @@ #define MAX_NUMNODES (1 << NODES_SHIFT) #define NUMA_NO_NODE (-1) +#define NUMA_NO_MEMBLK (-1) /* optionally keep NUMA memory info available post init */ #ifdef CONFIG_NUMA_KEEP_MEMINFO @@ -25,7 +26,7 @@ #include <asm/sparsemem.h> /* Generic implementation available */ -int numa_map_to_online_node(int node); +int numa_nearest_node(int node, unsigned int state); #ifndef memory_add_physaddr_to_nid static inline int memory_add_physaddr_to_nid(u64 start) @@ -43,11 +44,18 @@ static inline int phys_to_target_node(u64 start) return 0; } #endif +#ifndef numa_fill_memblks +static inline int __init numa_fill_memblks(u64 start, u64 end) +{ + return NUMA_NO_MEMBLK; +} +#endif #else /* !CONFIG_NUMA */ -static inline int numa_map_to_online_node(int node) +static inline int numa_nearest_node(int node, unsigned int state) { return NUMA_NO_NODE; } + static inline int memory_add_physaddr_to_nid(u64 start) { return 0; @@ -58,6 +66,8 @@ static inline int phys_to_target_node(u64 start) } #endif +#define numa_map_to_online_node(node) numa_nearest_node(node, N_ONLINE) + #ifdef CONFIG_HAVE_ARCH_NODE_DEV_GROUP extern const struct attribute_group arch_node_dev_group; #endif diff --git a/include/linux/nvme-fc-driver.h b/include/linux/nvme-fc-driver.h index f6ef8cf5d774..4109f1bd6128 100644 --- a/include/linux/nvme-fc-driver.h +++ b/include/linux/nvme-fc-driver.h @@ -53,10 +53,10 @@ struct nvmefc_ls_req { void *rqstaddr; dma_addr_t rqstdma; - __le32 rqstlen; + u32 rqstlen; void *rspaddr; dma_addr_t rspdma; - __le32 rsplen; + u32 rsplen; u32 timeout; void *private; @@ -120,7 +120,7 @@ struct nvmefc_ls_req { struct nvmefc_ls_rsp { void *rspbuf; dma_addr_t rspdma; - __le32 rsplen; + u16 rsplen; void (*done)(struct nvmefc_ls_rsp *rsp); void *nvme_fc_private; /* LLDD is not to access !! */ diff --git a/include/linux/objtool.h b/include/linux/objtool.h index 03f82c2c2ebf..33212e93f4a6 100644 --- a/include/linux/objtool.h +++ b/include/linux/objtool.h @@ -48,13 +48,13 @@ #define ANNOTATE_NOENDBR \ "986: \n\t" \ ".pushsection .discard.noendbr\n\t" \ - ".long 986b - .\n\t" \ + ".long 986b\n\t" \ ".popsection\n\t" #define ASM_REACHABLE \ "998:\n\t" \ ".pushsection .discard.reachable\n\t" \ - ".long 998b - .\n\t" \ + ".long 998b\n\t" \ ".popsection\n\t" #else /* __ASSEMBLY__ */ @@ -66,7 +66,7 @@ #define ANNOTATE_INTRA_FUNCTION_CALL \ 999: \ .pushsection .discard.intra_function_calls; \ - .long 999b - .; \ + .long 999b; \ .popsection; /* @@ -118,7 +118,7 @@ .macro ANNOTATE_NOENDBR .Lhere_\@: .pushsection .discard.noendbr - .long .Lhere_\@ - . + .long .Lhere_\@ .popsection .endm @@ -130,7 +130,8 @@ * it will be ignored. */ .macro VALIDATE_UNRET_BEGIN -#if defined(CONFIG_NOINSTR_VALIDATION) && defined(CONFIG_CPU_UNRET_ENTRY) +#if defined(CONFIG_NOINSTR_VALIDATION) && \ + (defined(CONFIG_CPU_UNRET_ENTRY) || defined(CONFIG_CPU_SRSO)) .Lhere_\@: .pushsection .discard.validate_unret .long .Lhere_\@ - . @@ -141,7 +142,7 @@ .macro REACHABLE .Lhere_\@: .pushsection .discard.reachable - .long .Lhere_\@ - . + .long .Lhere_\@ .popsection .endm diff --git a/include/linux/overflow.h b/include/linux/overflow.h index f9b60313eaea..7b5cf4a5cd19 100644 --- a/include/linux/overflow.h +++ b/include/linux/overflow.h @@ -309,4 +309,39 @@ static inline size_t __must_check size_sub(size_t minuend, size_t subtrahend) #define struct_size_t(type, member, count) \ struct_size((type *)NULL, member, count) +/** + * _DEFINE_FLEX() - helper macro for DEFINE_FLEX() family. + * Enables caller macro to pass (different) initializer. + * + * @type: structure type name, including "struct" keyword. + * @name: Name for a variable to define. + * @member: Name of the array member. + * @count: Number of elements in the array; must be compile-time const. + * @initializer: initializer expression (could be empty for no init). + */ +#define _DEFINE_FLEX(type, name, member, count, initializer) \ + _Static_assert(__builtin_constant_p(count), \ + "onstack flex array members require compile-time const count"); \ + union { \ + u8 bytes[struct_size_t(type, member, count)]; \ + type obj; \ + } name##_u initializer; \ + type *name = (type *)&name##_u + +/** + * DEFINE_FLEX() - Define an on-stack instance of structure with a trailing + * flexible array member. + * + * @type: structure type name, including "struct" keyword. + * @name: Name for a variable to define. + * @member: Name of the array member. + * @count: Number of elements in the array; must be compile-time const. + * + * Define a zeroed, on-stack, instance of @type structure with a trailing + * flexible array member. + * Use __struct_size(@name) to get compile-time size of it afterwards. + */ +#define DEFINE_FLEX(type, name, member, count) \ + _DEFINE_FLEX(type, name, member, count, = {}) + #endif /* __LINUX_OVERFLOW_H */ diff --git a/include/linux/pci.h b/include/linux/pci.h index 8c7c2c3c6c65..b56417276042 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1624,6 +1624,8 @@ struct msix_entry { u16 entry; /* Driver uses to specify entry, OS writes */ }; +struct msi_domain_template; + #ifdef CONFIG_PCI_MSI int pci_msi_vec_count(struct pci_dev *dev); void pci_disable_msi(struct pci_dev *dev); @@ -1656,6 +1658,11 @@ void pci_msix_free_irq(struct pci_dev *pdev, struct msi_map map); void pci_free_irq_vectors(struct pci_dev *dev); int pci_irq_vector(struct pci_dev *dev, unsigned int nr); const struct cpumask *pci_irq_get_affinity(struct pci_dev *pdev, int vec); +bool pci_create_ims_domain(struct pci_dev *pdev, const struct msi_domain_template *template, + unsigned int hwsize, void *data); +struct msi_map pci_ims_alloc_irq(struct pci_dev *pdev, union msi_instance_cookie *icookie, + const struct irq_affinity_desc *affdesc); +void pci_ims_free_irq(struct pci_dev *pdev, struct msi_map map); #else static inline int pci_msi_vec_count(struct pci_dev *dev) { return -ENOSYS; } @@ -1719,6 +1726,25 @@ static inline const struct cpumask *pci_irq_get_affinity(struct pci_dev *pdev, { return cpu_possible_mask; } + +static inline bool pci_create_ims_domain(struct pci_dev *pdev, + const struct msi_domain_template *template, + unsigned int hwsize, void *data) +{ return false; } + +static inline struct msi_map pci_ims_alloc_irq(struct pci_dev *pdev, + union msi_instance_cookie *icookie, + const struct irq_affinity_desc *affdesc) +{ + struct msi_map map = { .index = -ENOSYS, }; + + return map; +} + +static inline void pci_ims_free_irq(struct pci_dev *pdev, struct msi_map map) +{ +} + #endif /** @@ -2616,14 +2642,6 @@ static inline bool pci_is_thunderbolt_attached(struct pci_dev *pdev) void pci_uevent_ers(struct pci_dev *pdev, enum pci_ers_result err_type); #endif -struct msi_domain_template; - -bool pci_create_ims_domain(struct pci_dev *pdev, const struct msi_domain_template *template, - unsigned int hwsize, void *data); -struct msi_map pci_ims_alloc_irq(struct pci_dev *pdev, union msi_instance_cookie *icookie, - const struct irq_affinity_desc *affdesc); -void pci_ims_free_irq(struct pci_dev *pdev, struct msi_map map); - #include <linux/dma-mapping.h> #define pci_printk(level, pdev, fmt, arg...) \ diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 5fb3d4c393a9..91c1f6d5b44f 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -180,6 +180,8 @@ #define PCI_DEVICE_ID_BERKOM_A4T 0xffa4 #define PCI_DEVICE_ID_BERKOM_SCITEL_QUADRO 0xffa8 +#define PCI_VENDOR_ID_ITTIM 0x0b48 + #define PCI_VENDOR_ID_COMPAQ 0x0e11 #define PCI_DEVICE_ID_COMPAQ_TOKENRING 0x0508 #define PCI_DEVICE_ID_COMPAQ_TACHYON 0xa0fc @@ -579,6 +581,7 @@ #define PCI_DEVICE_ID_AMD_1AH_M00H_DF_F3 0x12c3 #define PCI_DEVICE_ID_AMD_1AH_M20H_DF_F3 0x16fb #define PCI_DEVICE_ID_AMD_MI200_DF_F3 0x14d3 +#define PCI_DEVICE_ID_AMD_MI300_DF_F3 0x152b #define PCI_DEVICE_ID_AMD_CNB17H_F3 0x1703 #define PCI_DEVICE_ID_AMD_LANCE 0x2000 #define PCI_DEVICE_ID_AMD_LANCE_HOME 0x2001 diff --git a/include/linux/pds/pds_core_if.h b/include/linux/pds/pds_core_if.h index e838a2b90440..17a87c1a55d7 100644 --- a/include/linux/pds/pds_core_if.h +++ b/include/linux/pds/pds_core_if.h @@ -79,6 +79,7 @@ enum pds_core_status_code { PDS_RC_EVFID = 31, /* VF ID does not exist */ PDS_RC_BAD_FW = 32, /* FW file is invalid or corrupted */ PDS_RC_ECLIENT = 33, /* No such client id */ + PDS_RC_BAD_PCI = 255, /* Broken PCI when reading status */ }; /** diff --git a/include/linux/percpu.h b/include/linux/percpu.h index 68fac2e7cbe6..8c677f185901 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -132,6 +132,7 @@ extern void __init setup_per_cpu_areas(void); extern void __percpu *__alloc_percpu_gfp(size_t size, size_t align, gfp_t gfp) __alloc_size(1); extern void __percpu *__alloc_percpu(size_t size, size_t align) __alloc_size(1); extern void free_percpu(void __percpu *__pdata); +extern size_t pcpu_alloc_size(void __percpu *__pdata); DEFINE_FREE(free_percpu, void __percpu *, free_percpu(_T)) diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index e85cd1c0eaf3..afb028c54f33 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -704,6 +704,7 @@ struct perf_event { /* The cumulative AND of all event_caps for events in this group. */ int group_caps; + unsigned int group_generation; struct perf_event *group_leader; /* * event->pmu will always point to pmu in which this event belongs. @@ -878,6 +879,7 @@ struct perf_event_pmu_context { unsigned int embedded : 1; unsigned int nr_events; + unsigned int nr_cgroups; atomic_t refcount; /* event <-> epc */ struct rcu_head rcu_head; @@ -1573,7 +1575,7 @@ extern int sysctl_perf_cpu_time_max_percent; extern void perf_sample_event_took(u64 sample_len_ns); -int perf_proc_update_handler(struct ctl_table *table, int write, +int perf_event_max_sample_rate_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); int perf_cpu_time_max_percent_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index 1fba072b3dac..af7639c3b0a3 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -206,6 +206,14 @@ static inline int pmd_young(pmd_t pmd) #endif #ifndef set_ptes + +#ifndef pte_next_pfn +static inline pte_t pte_next_pfn(pte_t pte) +{ + return __pte(pte_val(pte) + (1UL << PFN_PTE_SHIFT)); +} +#endif + /** * set_ptes - Map consecutive pages to a contiguous range of addresses. * @mm: Address space to map the pages into. @@ -231,7 +239,7 @@ static inline void set_ptes(struct mm_struct *mm, unsigned long addr, if (--nr == 0) break; ptep++; - pte = __pte(pte_val(pte) + (1UL << PFN_PTE_SHIFT)); + pte = pte_next_pfn(pte); } arch_leave_lazy_mmu_mode(); } diff --git a/include/linux/phy.h b/include/linux/phy.h index 1351b802ffcf..3cc52826f18e 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1736,6 +1736,7 @@ void phy_detach(struct phy_device *phydev); void phy_start(struct phy_device *phydev); void phy_stop(struct phy_device *phydev); int phy_config_aneg(struct phy_device *phydev); +int _phy_start_aneg(struct phy_device *phydev); int phy_start_aneg(struct phy_device *phydev); int phy_aneg_done(struct phy_device *phydev); int phy_speed_down(struct phy_device *phydev, bool sync); diff --git a/include/linux/phylink.h b/include/linux/phylink.h index 2b886ea654bb..875439ab45de 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -227,7 +227,7 @@ void phylink_limit_mac_speed(struct phylink_config *config, u32 max_speed); /** * struct phylink_mac_ops - MAC operations structure. - * @validate: Validate and update the link configuration. + * @mac_get_caps: Get MAC capabilities for interface mode. * @mac_select_pcs: Select a PCS for the interface mode. * @mac_prepare: prepare for a major reconfiguration of the interface. * @mac_config: configure the MAC for the selected mode and state. @@ -238,9 +238,8 @@ void phylink_limit_mac_speed(struct phylink_config *config, u32 max_speed); * The individual methods are described more fully below. */ struct phylink_mac_ops { - void (*validate)(struct phylink_config *config, - unsigned long *supported, - struct phylink_link_state *state); + unsigned long (*mac_get_caps)(struct phylink_config *config, + phy_interface_t interface); struct phylink_pcs *(*mac_select_pcs)(struct phylink_config *config, phy_interface_t interface); int (*mac_prepare)(struct phylink_config *config, unsigned int mode, @@ -259,39 +258,17 @@ struct phylink_mac_ops { #if 0 /* For kernel-doc purposes only. */ /** - * validate - Validate and update the link configuration + * mac_get_caps: Get MAC capabilities for interface mode. * @config: a pointer to a &struct phylink_config. - * @supported: ethtool bitmask for supported link modes. - * @state: a pointer to a &struct phylink_link_state. - * - * Clear bits in the @supported and @state->advertising masks that - * are not supportable by the MAC. - * - * Note that the PHY may be able to transform from one connection - * technology to another, so, eg, don't clear 1000BaseX just - * because the MAC is unable to BaseX mode. This is more about - * clearing unsupported speeds and duplex settings. The port modes - * should not be cleared; phylink_set_port_modes() will help with this. - * - * When @config->supported_interfaces has been set, phylink will iterate - * over the supported interfaces to determine the full capability of the - * MAC. The validation function must not print errors if @state->interface - * is set to an unexpected value. + * @interface: PHY interface mode. * - * When @config->supported_interfaces is empty, phylink will call this - * function with @state->interface set to %PHY_INTERFACE_MODE_NA, and - * expects the MAC driver to return all supported link modes. - * - * If the @state->interface mode is not supported, then the @supported - * mask must be cleared. - * - * This member is optional; if not set, the generic validator will be - * used making use of @config->mac_capabilities and - * @config->supported_interfaces to determine which link modes are - * supported. + * Optional method. When not provided, config->mac_capabilities will be used. + * When implemented, this returns the MAC capabilities for the specified + * interface mode where there is some special handling required by the MAC + * driver (e.g. not supporting half-duplex in certain interface modes.) */ -void validate(struct phylink_config *config, unsigned long *supported, - struct phylink_link_state *state); +unsigned long mac_get_caps(struct phylink_config *config, + phy_interface_t interface); /** * mac_select_pcs: Select a PCS for the interface mode. * @config: a pointer to a &struct phylink_config. @@ -636,17 +613,6 @@ void pcs_link_up(struct phylink_pcs *pcs, unsigned int neg_mode, phy_interface_t interface, int speed, int duplex); #endif -void phylink_caps_to_linkmodes(unsigned long *linkmodes, unsigned long caps); -unsigned long phylink_get_capabilities(phy_interface_t interface, - unsigned long mac_capabilities, - int rate_matching); -void phylink_validate_mask_caps(unsigned long *supported, - struct phylink_link_state *state, - unsigned long caps); -void phylink_generic_validate(struct phylink_config *config, - unsigned long *supported, - struct phylink_link_state *state); - struct phylink *phylink_create(struct phylink_config *, const struct fwnode_handle *, phy_interface_t, diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h index 608a9eb86bff..8ff23bf5a819 100644 --- a/include/linux/pipe_fs_i.h +++ b/include/linux/pipe_fs_i.h @@ -62,9 +62,6 @@ struct pipe_inode_info { unsigned int tail; unsigned int max_usage; unsigned int ring_size; -#ifdef CONFIG_WATCH_QUEUE - bool note_loss; -#endif unsigned int nr_accounted; unsigned int readers; unsigned int writers; @@ -72,6 +69,9 @@ struct pipe_inode_info { unsigned int r_counter; unsigned int w_counter; bool poll_usage; +#ifdef CONFIG_WATCH_QUEUE + bool note_loss; +#endif struct page *tmp_page; struct fasync_struct *fasync_readers; struct fasync_struct *fasync_writers; @@ -125,6 +125,22 @@ struct pipe_buf_operations { }; /** + * pipe_has_watch_queue - Check whether the pipe is a watch_queue, + * i.e. it was created with O_NOTIFICATION_PIPE + * @pipe: The pipe to check + * + * Return: true if pipe is a watch queue, false otherwise. + */ +static inline bool pipe_has_watch_queue(const struct pipe_inode_info *pipe) +{ +#ifdef CONFIG_WATCH_QUEUE + return pipe->watch_queue != NULL; +#else + return false; +#endif +} + +/** * pipe_empty - Return true if the pipe is empty * @head: The pipe ring head pointer * @tail: The pipe ring tail pointer diff --git a/include/linux/pktcdvd.h b/include/linux/pktcdvd.h index 80cb00db42a4..79594aeb160d 100644 --- a/include/linux/pktcdvd.h +++ b/include/linux/pktcdvd.h @@ -154,7 +154,9 @@ struct packet_stacked_data struct pktcdvd_device { - struct block_device *bdev; /* dev attached */ + struct bdev_handle *bdev_handle; /* dev attached */ + /* handle acquired for bdev during pkt_open_dev() */ + struct bdev_handle *open_bdev_handle; dev_t pkt_dev; /* our dev */ struct packet_settings settings; struct packet_stats stats; diff --git a/include/linux/platform_data/cros_ec_proto.h b/include/linux/platform_data/cros_ec_proto.h index 4f9f756bc17c..8865e350c12a 100644 --- a/include/linux/platform_data/cros_ec_proto.h +++ b/include/linux/platform_data/cros_ec_proto.h @@ -258,7 +258,7 @@ bool cros_ec_check_features(struct cros_ec_dev *ec, int feature); int cros_ec_get_sensor_count(struct cros_ec_dev *ec); -int cros_ec_cmd(struct cros_ec_device *ec_dev, unsigned int version, int command, void *outdata, +int cros_ec_cmd(struct cros_ec_device *ec_dev, unsigned int version, int command, const void *outdata, size_t outsize, void *indata, size_t insize); /** diff --git a/include/linux/platform_data/gpio-omap.h b/include/linux/platform_data/gpio-omap.h index f377817ce75c..cdd8cfb424f5 100644 --- a/include/linux/platform_data/gpio-omap.h +++ b/include/linux/platform_data/gpio-omap.h @@ -144,9 +144,6 @@ #define OMAP_MAX_GPIO_LINES 192 -#define OMAP_MPUIO(nr) (OMAP_MAX_GPIO_LINES + (nr)) -#define OMAP_GPIO_IS_MPUIO(nr) ((nr) >= OMAP_MAX_GPIO_LINES) - #ifndef __ASSEMBLER__ struct omap_gpio_reg_offs { u16 revision; diff --git a/include/linux/platform_data/gsc_hwmon.h b/include/linux/platform_data/gsc_hwmon.h index f2781aa7eff8..70e8a6bec0f6 100644 --- a/include/linux/platform_data/gsc_hwmon.h +++ b/include/linux/platform_data/gsc_hwmon.h @@ -40,6 +40,6 @@ struct gsc_hwmon_platform_data { unsigned int resolution; unsigned int vreference; unsigned int fan_base; - struct gsc_hwmon_channel channels[]; + struct gsc_hwmon_channel channels[] __counted_by(nchannels); }; #endif diff --git a/include/linux/platform_data/pca953x.h b/include/linux/platform_data/pca953x.h index 96c1a14ab365..3c3787c4d96c 100644 --- a/include/linux/platform_data/pca953x.h +++ b/include/linux/platform_data/pca953x.h @@ -11,21 +11,8 @@ struct pca953x_platform_data { /* number of the first GPIO */ unsigned gpio_base; - /* initial polarity inversion setting */ - u32 invert; - /* interrupt base */ int irq_base; - - void *context; /* param to setup/teardown */ - - int (*setup)(struct i2c_client *client, - unsigned gpio, unsigned ngpio, - void *context); - void (*teardown)(struct i2c_client *client, - unsigned gpio, unsigned ngpio, - void *context); - const char *const *names; }; #endif /* _LINUX_PCA953X_H */ diff --git a/include/linux/platform_data/x86/asus-wmi.h b/include/linux/platform_data/x86/asus-wmi.h index 16e99a1c37fc..63e630276499 100644 --- a/include/linux/platform_data/x86/asus-wmi.h +++ b/include/linux/platform_data/x86/asus-wmi.h @@ -58,6 +58,10 @@ #define ASUS_WMI_DEVID_KBD_BACKLIGHT 0x00050021 #define ASUS_WMI_DEVID_LIGHT_SENSOR 0x00050022 /* ?? */ #define ASUS_WMI_DEVID_LIGHTBAR 0x00050025 +/* This can only be used to disable the screen, not re-enable */ +#define ASUS_WMI_DEVID_SCREENPAD_POWER 0x00050031 +/* Writing a brightness re-enables the screen if disabled */ +#define ASUS_WMI_DEVID_SCREENPAD_LIGHT 0x00050032 #define ASUS_WMI_DEVID_FAN_BOOST_MODE 0x00110018 #define ASUS_WMI_DEVID_THROTTLE_THERMAL_POLICY 0x00120075 diff --git a/include/linux/pm.h b/include/linux/pm.h index 1400c37b29c7..92a4f69de0e8 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -374,24 +374,39 @@ const struct dev_pm_ops name = { \ RUNTIME_PM_OPS(runtime_suspend_fn, runtime_resume_fn, idle_fn) \ } -#ifdef CONFIG_PM -#define _EXPORT_DEV_PM_OPS(name, license, ns) \ +#define _EXPORT_PM_OPS(name, license, ns) \ const struct dev_pm_ops name; \ __EXPORT_SYMBOL(name, license, ns); \ const struct dev_pm_ops name -#define EXPORT_PM_FN_GPL(name) EXPORT_SYMBOL_GPL(name) -#define EXPORT_PM_FN_NS_GPL(name, ns) EXPORT_SYMBOL_NS_GPL(name, ns) -#else -#define _EXPORT_DEV_PM_OPS(name, license, ns) \ + +#define _DISCARD_PM_OPS(name, license, ns) \ static __maybe_unused const struct dev_pm_ops __static_##name + +#ifdef CONFIG_PM +#define _EXPORT_DEV_PM_OPS(name, license, ns) _EXPORT_PM_OPS(name, license, ns) +#define EXPORT_PM_FN_GPL(name) EXPORT_SYMBOL_GPL(name) +#define EXPORT_PM_FN_NS_GPL(name, ns) EXPORT_SYMBOL_NS_GPL(name, ns) +#else +#define _EXPORT_DEV_PM_OPS(name, license, ns) _DISCARD_PM_OPS(name, license, ns) #define EXPORT_PM_FN_GPL(name) #define EXPORT_PM_FN_NS_GPL(name, ns) #endif -#define EXPORT_DEV_PM_OPS(name) _EXPORT_DEV_PM_OPS(name, "", "") -#define EXPORT_GPL_DEV_PM_OPS(name) _EXPORT_DEV_PM_OPS(name, "GPL", "") -#define EXPORT_NS_DEV_PM_OPS(name, ns) _EXPORT_DEV_PM_OPS(name, "", #ns) -#define EXPORT_NS_GPL_DEV_PM_OPS(name, ns) _EXPORT_DEV_PM_OPS(name, "GPL", #ns) +#ifdef CONFIG_PM_SLEEP +#define _EXPORT_DEV_SLEEP_PM_OPS(name, license, ns) _EXPORT_PM_OPS(name, license, ns) +#else +#define _EXPORT_DEV_SLEEP_PM_OPS(name, license, ns) _DISCARD_PM_OPS(name, license, ns) +#endif + +#define EXPORT_DEV_PM_OPS(name) _EXPORT_DEV_PM_OPS(name, "", "") +#define EXPORT_GPL_DEV_PM_OPS(name) _EXPORT_DEV_PM_OPS(name, "GPL", "") +#define EXPORT_NS_DEV_PM_OPS(name, ns) _EXPORT_DEV_PM_OPS(name, "", #ns) +#define EXPORT_NS_GPL_DEV_PM_OPS(name, ns) _EXPORT_DEV_PM_OPS(name, "GPL", #ns) + +#define EXPORT_DEV_SLEEP_PM_OPS(name) _EXPORT_DEV_SLEEP_PM_OPS(name, "", "") +#define EXPORT_GPL_DEV_SLEEP_PM_OPS(name) _EXPORT_DEV_SLEEP_PM_OPS(name, "GPL", "") +#define EXPORT_NS_DEV_SLEEP_PM_OPS(name, ns) _EXPORT_DEV_SLEEP_PM_OPS(name, "", #ns) +#define EXPORT_NS_GPL_DEV_SLEEP_PM_OPS(name, ns) _EXPORT_DEV_SLEEP_PM_OPS(name, "GPL", #ns) /* * Use this if you want to use the same suspend and resume callbacks for suspend @@ -404,19 +419,19 @@ const struct dev_pm_ops name = { \ _DEFINE_DEV_PM_OPS(name, suspend_fn, resume_fn, NULL, NULL, NULL) #define EXPORT_SIMPLE_DEV_PM_OPS(name, suspend_fn, resume_fn) \ - EXPORT_DEV_PM_OPS(name) = { \ + EXPORT_DEV_SLEEP_PM_OPS(name) = { \ SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) \ } #define EXPORT_GPL_SIMPLE_DEV_PM_OPS(name, suspend_fn, resume_fn) \ - EXPORT_GPL_DEV_PM_OPS(name) = { \ + EXPORT_GPL_DEV_SLEEP_PM_OPS(name) = { \ SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) \ } #define EXPORT_NS_SIMPLE_DEV_PM_OPS(name, suspend_fn, resume_fn, ns) \ - EXPORT_NS_DEV_PM_OPS(name, ns) = { \ + EXPORT_NS_DEV_SLEEP_PM_OPS(name, ns) = { \ SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) \ } #define EXPORT_NS_GPL_SIMPLE_DEV_PM_OPS(name, suspend_fn, resume_fn, ns) \ - EXPORT_NS_GPL_DEV_PM_OPS(name, ns) = { \ + EXPORT_NS_GPL_DEV_SLEEP_PM_OPS(name, ns) = { \ SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) \ } @@ -719,6 +734,7 @@ extern void dev_pm_put_subsys_data(struct device *dev); * @activate: Called before executing probe routines for bus types and drivers. * @sync: Called after successful driver probe. * @dismiss: Called after unsuccessful driver probe and after driver removal. + * @set_performance_state: Called to request a new performance state. * * Power domains provide callbacks that are executed during system suspend, * hibernation, system resume and during runtime PM transitions instead of @@ -731,6 +747,7 @@ struct dev_pm_domain { int (*activate)(struct device *dev); void (*sync)(struct device *dev); void (*dismiss)(struct device *dev); + int (*set_performance_state)(struct device *dev, unsigned int state); }; /* diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index f776fb93eaa0..bda2964a0a56 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -430,6 +430,7 @@ struct device *dev_pm_domain_attach_by_name(struct device *dev, void dev_pm_domain_detach(struct device *dev, bool power_off); int dev_pm_domain_start(struct device *dev); void dev_pm_domain_set(struct device *dev, struct dev_pm_domain *pd); +int dev_pm_domain_set_performance_state(struct device *dev, unsigned int state); #else static inline int dev_pm_domain_attach(struct device *dev, bool power_on) { @@ -452,6 +453,11 @@ static inline int dev_pm_domain_start(struct device *dev) } static inline void dev_pm_domain_set(struct device *dev, struct dev_pm_domain *pd) {} +static inline int dev_pm_domain_set_performance_state(struct device *dev, + unsigned int state) +{ + return 0; +} #endif #endif /* _LINUX_PM_DOMAIN_H */ diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h index 91f87d7e807c..ccd97bcef269 100644 --- a/include/linux/pm_opp.h +++ b/include/linux/pm_opp.h @@ -92,6 +92,18 @@ struct dev_pm_opp_config { struct device ***virt_devs; }; +/** + * struct dev_pm_opp_data - The data to use to initialize an OPP. + * @level: The performance level for the OPP. + * @freq: The clock rate in Hz for the OPP. + * @u_volt: The voltage in uV for the OPP. + */ +struct dev_pm_opp_data { + unsigned int level; + unsigned long freq; + unsigned long u_volt; +}; + #if defined(CONFIG_PM_OPP) struct opp_table *dev_pm_opp_get_opp_table(struct device *dev); @@ -144,6 +156,9 @@ struct dev_pm_opp *dev_pm_opp_find_level_exact(struct device *dev, struct dev_pm_opp *dev_pm_opp_find_level_ceil(struct device *dev, unsigned int *level); +struct dev_pm_opp *dev_pm_opp_find_level_floor(struct device *dev, + unsigned long *level); + struct dev_pm_opp *dev_pm_opp_find_bw_ceil(struct device *dev, unsigned int *bw, int index); @@ -152,8 +167,8 @@ struct dev_pm_opp *dev_pm_opp_find_bw_floor(struct device *dev, void dev_pm_opp_put(struct dev_pm_opp *opp); -int dev_pm_opp_add(struct device *dev, unsigned long freq, - unsigned long u_volt); +int dev_pm_opp_add_dynamic(struct device *dev, struct dev_pm_opp_data *opp); + void dev_pm_opp_remove(struct device *dev, unsigned long freq); void dev_pm_opp_remove_all_dynamic(struct device *dev); @@ -308,6 +323,12 @@ static inline struct dev_pm_opp *dev_pm_opp_find_level_ceil(struct device *dev, return ERR_PTR(-EOPNOTSUPP); } +static inline struct dev_pm_opp *dev_pm_opp_find_level_floor(struct device *dev, + unsigned long *level) +{ + return ERR_PTR(-EOPNOTSUPP); +} + static inline struct dev_pm_opp *dev_pm_opp_find_bw_ceil(struct device *dev, unsigned int *bw, int index) { @@ -322,8 +343,8 @@ static inline struct dev_pm_opp *dev_pm_opp_find_bw_floor(struct device *dev, static inline void dev_pm_opp_put(struct dev_pm_opp *opp) {} -static inline int dev_pm_opp_add(struct device *dev, unsigned long freq, - unsigned long u_volt) +static inline int +dev_pm_opp_add_dynamic(struct device *dev, struct dev_pm_opp_data *opp) { return -EOPNOTSUPP; } @@ -519,6 +540,17 @@ static inline int dev_pm_opp_of_find_icc_paths(struct device *dev, struct opp_ta /* OPP Configuration helpers */ +static inline int dev_pm_opp_add(struct device *dev, unsigned long freq, + unsigned long u_volt) +{ + struct dev_pm_opp_data data = { + .freq = freq, + .u_volt = u_volt, + }; + + return dev_pm_opp_add_dynamic(dev, &data); +} + /* Regulators helpers */ static inline int dev_pm_opp_set_regulators(struct device *dev, const char * const names[]) diff --git a/include/linux/pnp.h b/include/linux/pnp.h index c2a7cfbca713..267fb8a4fb6e 100644 --- a/include/linux/pnp.h +++ b/include/linux/pnp.h @@ -291,7 +291,7 @@ static inline void pnp_set_drvdata(struct pnp_dev *pdev, void *data) struct pnp_fixup { char id[7]; - void (*quirk_function) (struct pnp_dev * dev); /* fixup function */ + void (*quirk_function) (struct pnp_dev *dev); /* fixup function */ }; /* config parameters */ @@ -419,8 +419,8 @@ struct pnp_protocol { /* protocol specific suspend/resume */ bool (*can_wakeup) (struct pnp_dev *dev); - int (*suspend) (struct pnp_dev * dev, pm_message_t state); - int (*resume) (struct pnp_dev * dev); + int (*suspend) (struct pnp_dev *dev, pm_message_t state); + int (*resume) (struct pnp_dev *dev); /* used by pnp layer only (look but don't touch) */ unsigned char number; /* protocol number */ @@ -492,7 +492,7 @@ static inline int pnp_start_dev(struct pnp_dev *dev) { return -ENODEV; } static inline int pnp_stop_dev(struct pnp_dev *dev) { return -ENODEV; } static inline int pnp_activate_dev(struct pnp_dev *dev) { return -ENODEV; } static inline int pnp_disable_dev(struct pnp_dev *dev) { return -ENODEV; } -static inline int pnp_range_reserved(resource_size_t start, resource_size_t end) { return 0;} +static inline int pnp_range_reserved(resource_size_t start, resource_size_t end) { return 0; } /* protocol helpers */ static inline int pnp_is_active(struct pnp_dev *dev) { return 0; } diff --git a/include/linux/posix-clock.h b/include/linux/posix-clock.h index 468328b1e1dd..ef8619f48920 100644 --- a/include/linux/posix-clock.h +++ b/include/linux/posix-clock.h @@ -14,6 +14,7 @@ #include <linux/rwsem.h> struct posix_clock; +struct posix_clock_context; /** * struct posix_clock_operations - functional interface to the clock @@ -50,18 +51,18 @@ struct posix_clock_operations { /* * Optional character device methods: */ - long (*ioctl) (struct posix_clock *pc, - unsigned int cmd, unsigned long arg); + long (*ioctl)(struct posix_clock_context *pccontext, unsigned int cmd, + unsigned long arg); - int (*open) (struct posix_clock *pc, fmode_t f_mode); + int (*open)(struct posix_clock_context *pccontext, fmode_t f_mode); - __poll_t (*poll) (struct posix_clock *pc, - struct file *file, poll_table *wait); + __poll_t (*poll)(struct posix_clock_context *pccontext, struct file *file, + poll_table *wait); - int (*release) (struct posix_clock *pc); + int (*release)(struct posix_clock_context *pccontext); - ssize_t (*read) (struct posix_clock *pc, - uint flags, char __user *buf, size_t cnt); + ssize_t (*read)(struct posix_clock_context *pccontext, uint flags, + char __user *buf, size_t cnt); }; /** @@ -91,6 +92,24 @@ struct posix_clock { }; /** + * struct posix_clock_context - represents clock file operations context + * + * @clk: Pointer to the clock + * @private_clkdata: Pointer to user data + * + * Drivers should use struct posix_clock_context during specific character + * device file operation methods to access the posix clock. + * + * Drivers can store a private data structure during the open operation + * if they have specific information that is required in other file + * operations. + */ +struct posix_clock_context { + struct posix_clock *clk; + void *private_clkdata; +}; + +/** * posix_clock_register() - register a new clock * @clk: Pointer to the clock. Caller must provide 'ops' field * @dev: Pointer to the initialized device. Caller must provide diff --git a/include/linux/preempt.h b/include/linux/preempt.h index 1424670df161..9aa6358a1a16 100644 --- a/include/linux/preempt.h +++ b/include/linux/preempt.h @@ -99,14 +99,21 @@ static __always_inline unsigned char interrupt_context_level(void) return level; } +/* + * These macro definitions avoid redundant invocations of preempt_count() + * because such invocations would result in redundant loads given that + * preempt_count() is commonly implemented with READ_ONCE(). + */ + #define nmi_count() (preempt_count() & NMI_MASK) #define hardirq_count() (preempt_count() & HARDIRQ_MASK) #ifdef CONFIG_PREEMPT_RT # define softirq_count() (current->softirq_disable_cnt & SOFTIRQ_MASK) +# define irq_count() ((preempt_count() & (NMI_MASK | HARDIRQ_MASK)) | softirq_count()) #else # define softirq_count() (preempt_count() & SOFTIRQ_MASK) +# define irq_count() (preempt_count() & (NMI_MASK | HARDIRQ_MASK | SOFTIRQ_MASK)) #endif -#define irq_count() (nmi_count() | hardirq_count() | softirq_count()) /* * Macros to retrieve the current execution context: @@ -119,7 +126,11 @@ static __always_inline unsigned char interrupt_context_level(void) #define in_nmi() (nmi_count()) #define in_hardirq() (hardirq_count()) #define in_serving_softirq() (softirq_count() & SOFTIRQ_OFFSET) -#define in_task() (!(in_nmi() | in_hardirq() | in_serving_softirq())) +#ifdef CONFIG_PREEMPT_RT +# define in_task() (!((preempt_count() & (NMI_MASK | HARDIRQ_MASK)) | in_serving_softirq())) +#else +# define in_task() (!(preempt_count() & (NMI_MASK | HARDIRQ_MASK | SOFTIRQ_OFFSET))) +#endif /* * The following macros are deprecated and should not be used in new code: diff --git a/include/linux/pseudo_fs.h b/include/linux/pseudo_fs.h index eceda1d1407a..730f77381d55 100644 --- a/include/linux/pseudo_fs.h +++ b/include/linux/pseudo_fs.h @@ -5,7 +5,7 @@ struct pseudo_fs_context { const struct super_operations *ops; - const struct xattr_handler **xattr; + const struct xattr_handler * const *xattr; const struct dentry_operations *dops; unsigned long magic; }; diff --git a/include/linux/quota.h b/include/linux/quota.h index fd692b4a41d5..07071e64abf3 100644 --- a/include/linux/quota.h +++ b/include/linux/quota.h @@ -285,7 +285,9 @@ static inline void dqstats_dec(unsigned int type) #define DQ_FAKE_B 3 /* no limits only usage */ #define DQ_READ_B 4 /* dquot was read into memory */ #define DQ_ACTIVE_B 5 /* dquot is active (dquot_release not called) */ -#define DQ_LASTSET_B 6 /* Following 6 bits (see QIF_) are reserved\ +#define DQ_RELEASING_B 6 /* dquot is in releasing_dquots list waiting + * to be cleaned up */ +#define DQ_LASTSET_B 7 /* Following 6 bits (see QIF_) are reserved\ * for the mask of entries set via SETQUOTA\ * quotactl. They are set under dq_data_lock\ * and the quota format handling dquot can\ diff --git a/include/linux/quotaops.h b/include/linux/quotaops.h index 11a4becff3a9..4fa4ef0a173a 100644 --- a/include/linux/quotaops.h +++ b/include/linux/quotaops.h @@ -57,7 +57,7 @@ static inline bool dquot_is_busy(struct dquot *dquot) { if (test_bit(DQ_MOD_B, &dquot->dq_flags)) return true; - if (atomic_read(&dquot->dq_count) > 1) + if (atomic_read(&dquot->dq_count) > 0) return true; return false; } diff --git a/include/linux/rcu_notifier.h b/include/linux/rcu_notifier.h new file mode 100644 index 000000000000..ebf371364581 --- /dev/null +++ b/include/linux/rcu_notifier.h @@ -0,0 +1,32 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * Read-Copy Update notifiers, initially RCU CPU stall notifier. + * Separate from rcupdate.h to avoid #include loops. + * + * Copyright (C) 2023 Paul E. McKenney. + */ + +#ifndef __LINUX_RCU_NOTIFIER_H +#define __LINUX_RCU_NOTIFIER_H + +// Actions for RCU CPU stall notifier calls. +#define RCU_STALL_NOTIFY_NORM 1 +#define RCU_STALL_NOTIFY_EXP 2 + +#ifdef CONFIG_RCU_STALL_COMMON + +#include <linux/notifier.h> +#include <linux/types.h> + +int rcu_stall_chain_notifier_register(struct notifier_block *n); +int rcu_stall_chain_notifier_unregister(struct notifier_block *n); + +#else // #ifdef CONFIG_RCU_STALL_COMMON + +// No RCU CPU stall warnings in Tiny RCU. +static inline int rcu_stall_chain_notifier_register(struct notifier_block *n) { return -EEXIST; } +static inline int rcu_stall_chain_notifier_unregister(struct notifier_block *n) { return -ENOENT; } + +#endif // #else // #ifdef CONFIG_RCU_STALL_COMMON + +#endif /* __LINUX_RCU_NOTIFIER_H */ diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 5e5f920ade90..f7206b2623c9 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -122,8 +122,6 @@ static inline void call_rcu_hurry(struct rcu_head *head, rcu_callback_t func) void rcu_init(void); extern int rcu_scheduler_active; void rcu_sched_clock_irq(int user); -void rcu_report_dead(unsigned int cpu); -void rcutree_migrate_callbacks(int cpu); #ifdef CONFIG_TASKS_RCU_GENERIC void rcu_init_tasks_generic(void); diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index 7b949292908a..d9ac7b136aea 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -171,6 +171,6 @@ static inline void rcu_all_qs(void) { barrier(); } #define rcutree_offline_cpu NULL #define rcutree_dead_cpu NULL #define rcutree_dying_cpu NULL -static inline void rcu_cpu_starting(unsigned int cpu) { } +static inline void rcutree_report_cpu_starting(unsigned int cpu) { } #endif /* __LINUX_RCUTINY_H */ diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index 126f6b418f6a..254244202ea9 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -37,7 +37,6 @@ void synchronize_rcu_expedited(void); void kvfree_call_rcu(struct rcu_head *head, void *ptr); void rcu_barrier(void); -bool rcu_eqs_special_set(int cpu); void rcu_momentary_dyntick_idle(void); void kfree_rcu_scheduler_running(void); bool rcu_gp_might_be_stalled(void); @@ -111,9 +110,21 @@ void rcu_all_qs(void); /* RCUtree hotplug events */ int rcutree_prepare_cpu(unsigned int cpu); int rcutree_online_cpu(unsigned int cpu); -int rcutree_offline_cpu(unsigned int cpu); +void rcutree_report_cpu_starting(unsigned int cpu); + +#ifdef CONFIG_HOTPLUG_CPU int rcutree_dead_cpu(unsigned int cpu); int rcutree_dying_cpu(unsigned int cpu); -void rcu_cpu_starting(unsigned int cpu); +int rcutree_offline_cpu(unsigned int cpu); +#else +#define rcutree_dead_cpu NULL +#define rcutree_dying_cpu NULL +#define rcutree_offline_cpu NULL +#endif + +void rcutree_migrate_callbacks(int cpu); + +/* Called from hotplug and also arm64 early secondary boot failure */ +void rcutree_report_cpu_dead(void); #endif /* __LINUX_RCUTREE_H */ diff --git a/include/linux/regulator/mt6358-regulator.h b/include/linux/regulator/mt6358-regulator.h index c71a6a9fce7a..562386f9b80e 100644 --- a/include/linux/regulator/mt6358-regulator.h +++ b/include/linux/regulator/mt6358-regulator.h @@ -86,6 +86,9 @@ enum { MT6366_ID_VMC, MT6366_ID_VAUD28, MT6366_ID_VSIM2, + MT6366_ID_VM18, + MT6366_ID_VMDDR, + MT6366_ID_VSRAM_CORE, MT6366_ID_RG_MAX, }; diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h index 8334eeacfec5..66942d7fba7f 100644 --- a/include/linux/resctrl.h +++ b/include/linux/resctrl.h @@ -94,7 +94,7 @@ struct rdt_domain { * zero CBM. * @shareable_bits: Bitmask of shareable resource with other * executing entities - * @arch_has_sparse_bitmaps: True if a bitmap like f00f is valid. + * @arch_has_sparse_bitmasks: True if a bitmask like f00f is valid. * @arch_has_per_cpu_cfg: True if QOS_CFG register for this cache * level has CPU scope. */ @@ -102,7 +102,7 @@ struct resctrl_cache { unsigned int cbm_len; unsigned int min_cbm_bits; unsigned int shareable_bits; - bool arch_has_sparse_bitmaps; + bool arch_has_sparse_bitmasks; bool arch_has_per_cpu_cfg; }; diff --git a/include/linux/resume_user_mode.h b/include/linux/resume_user_mode.h index 285189454449..f8f3e958e9cf 100644 --- a/include/linux/resume_user_mode.h +++ b/include/linux/resume_user_mode.h @@ -55,7 +55,7 @@ static inline void resume_user_mode_work(struct pt_regs *regs) } #endif - mem_cgroup_handle_over_high(); + mem_cgroup_handle_over_high(GFP_KERNEL); blkcg_maybe_throttle_current(); rseq_handle_notify_resume(NULL, regs); diff --git a/include/linux/rtc.h b/include/linux/rtc.h index 4c0bcbeb1f00..5f8e438a0312 100644 --- a/include/linux/rtc.h +++ b/include/linux/rtc.h @@ -225,6 +225,23 @@ static inline bool is_leap_year(unsigned int year) return (!(year % 4) && (year % 100)) || !(year % 400); } +/** + * rtc_bound_alarmtime() - Return alarm time bound by rtc limit + * @rtc: Pointer to rtc device structure + * @requested: Requested alarm timeout + * + * Return: Alarm timeout bound by maximum alarm time supported by rtc. + */ +static inline ktime_t rtc_bound_alarmtime(struct rtc_device *rtc, + ktime_t requested) +{ + if (rtc->alarm_offset_max && + rtc->alarm_offset_max * MSEC_PER_SEC < ktime_to_ms(requested)) + return ms_to_ktime(rtc->alarm_offset_max * MSEC_PER_SEC); + + return requested; +} + #define devm_rtc_register_device(device) \ __devm_rtc_register_device(THIS_MODULE, device) diff --git a/include/linux/sched.h b/include/linux/sched.h index 77f01ac385f7..12ec109ce8c9 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -63,7 +63,6 @@ struct robust_list_head; struct root_domain; struct rq; struct sched_attr; -struct sched_param; struct seq_file; struct sighand_struct; struct signal_struct; @@ -370,6 +369,10 @@ extern struct root_domain def_root_domain; extern struct mutex sched_domains_mutex; #endif +struct sched_param { + int sched_priority; +}; + struct sched_info { #ifdef CONFIG_SCHED_INFO /* Cumulative counters: */ @@ -750,10 +753,8 @@ struct task_struct { #endif unsigned int __state; -#ifdef CONFIG_PREEMPT_RT /* saved state for "spinlock sleepers" */ unsigned int saved_state; -#endif /* * This begins the randomizable portion of task_struct. Only @@ -875,6 +876,7 @@ struct task_struct { struct mm_struct *mm; struct mm_struct *active_mm; + struct address_space *faults_disabled_mapping; int exit_state; int exit_code; @@ -911,6 +913,9 @@ struct task_struct { * ->sched_remote_wakeup gets used, so it can be in this word. */ unsigned sched_remote_wakeup:1; +#ifdef CONFIG_RT_MUTEXES + unsigned sched_rt_mutex:1; +#endif /* Bit to tell LSMs we're in execve(): */ unsigned in_execve:1; diff --git a/include/linux/sched/deadline.h b/include/linux/sched/deadline.h index 7c83d4d5a971..df3aca89d4f5 100644 --- a/include/linux/sched/deadline.h +++ b/include/linux/sched/deadline.h @@ -1,4 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_SCHED_DEADLINE_H +#define _LINUX_SCHED_DEADLINE_H /* * SCHED_DEADLINE tasks has negative priorities, reflecting @@ -34,3 +36,5 @@ extern void dl_add_task_root_domain(struct task_struct *p); extern void dl_clear_root_domain(struct root_domain *rd); #endif /* CONFIG_SMP */ + +#endif /* _LINUX_SCHED_DEADLINE_H */ diff --git a/include/linux/sched/numa_balancing.h b/include/linux/sched/numa_balancing.h index 3988762efe15..b69afb8630db 100644 --- a/include/linux/sched/numa_balancing.h +++ b/include/linux/sched/numa_balancing.h @@ -15,6 +15,16 @@ #define TNF_FAULT_LOCAL 0x08 #define TNF_MIGRATE_FAIL 0x10 +enum numa_vmaskip_reason { + NUMAB_SKIP_UNSUITABLE, + NUMAB_SKIP_SHARED_RO, + NUMAB_SKIP_INACCESSIBLE, + NUMAB_SKIP_SCAN_DELAY, + NUMAB_SKIP_PID_INACTIVE, + NUMAB_SKIP_IGNORE_PID, + NUMAB_SKIP_SEQ_COMPLETED, +}; + #ifdef CONFIG_NUMA_BALANCING extern void task_numa_fault(int last_node, int node, int pages, int flags); extern pid_t task_numa_group_id(struct task_struct *p); diff --git a/include/linux/sched/rt.h b/include/linux/sched/rt.h index 994c25640e15..b2b9e6eb9683 100644 --- a/include/linux/sched/rt.h +++ b/include/linux/sched/rt.h @@ -30,6 +30,10 @@ static inline bool task_is_realtime(struct task_struct *tsk) } #ifdef CONFIG_RT_MUTEXES +extern void rt_mutex_pre_schedule(void); +extern void rt_mutex_schedule(void); +extern void rt_mutex_post_schedule(void); + /* * Must hold either p->pi_lock or task_rq(p)->lock. */ diff --git a/include/linux/sched/sd_flags.h b/include/linux/sched/sd_flags.h index fad77b5172e2..a8b28647aafc 100644 --- a/include/linux/sched/sd_flags.h +++ b/include/linux/sched/sd_flags.h @@ -110,6 +110,13 @@ SD_FLAG(SD_ASYM_CPUCAPACITY_FULL, SDF_SHARED_PARENT | SDF_NEEDS_GROUPS) SD_FLAG(SD_SHARE_CPUCAPACITY, SDF_SHARED_CHILD | SDF_NEEDS_GROUPS) /* + * Domain members share CPU cluster (LLC tags or L2 cache) + * + * NEEDS_GROUPS: Clusters are shared between groups. + */ +SD_FLAG(SD_CLUSTER, SDF_NEEDS_GROUPS) + +/* * Domain members share CPU package resources (i.e. caches) * * SHARED_CHILD: Set from the base domain up until spanned CPUs no longer share diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index 0014d3adaf84..9610bad018a3 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -656,7 +656,8 @@ extern bool current_is_single_threaded(void); while ((t = next_thread(t)) != g) #define __for_each_thread(signal, t) \ - list_for_each_entry_rcu(t, &(signal)->thread_head, thread_node) + list_for_each_entry_rcu(t, &(signal)->thread_head, thread_node, \ + lockdep_is_held(&tasklist_lock)) #define for_each_thread(p, t) \ __for_each_thread((p)->signal, t) diff --git a/include/linux/sched/smt.h b/include/linux/sched/smt.h index 59d3736c454c..fb1e295e7e63 100644 --- a/include/linux/sched/smt.h +++ b/include/linux/sched/smt.h @@ -17,4 +17,4 @@ static inline bool sched_smt_active(void) { return false; } void arch_smt_update(void); -#endif +#endif /* _LINUX_SCHED_SMT_H */ diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h index 67b573d5bf28..de545ba85218 100644 --- a/include/linux/sched/topology.h +++ b/include/linux/sched/topology.h @@ -45,7 +45,7 @@ static inline int cpu_smt_flags(void) #ifdef CONFIG_SCHED_CLUSTER static inline int cpu_cluster_flags(void) { - return SD_SHARE_PKG_RESOURCES; + return SD_CLUSTER | SD_SHARE_PKG_RESOURCES; } #endif @@ -109,8 +109,6 @@ struct sched_domain { u64 max_newidle_lb_cost; unsigned long last_decay_max_lb_cost; - u64 avg_scan_cost; /* select_idle_sibling */ - #ifdef CONFIG_SCHEDSTATS /* load_balance() stats */ unsigned int lb_count[CPU_MAX_IDLE_TYPES]; @@ -179,6 +177,7 @@ cpumask_var_t *alloc_sched_domains(unsigned int ndoms); void free_sched_domains(cpumask_var_t doms[], unsigned int ndoms); bool cpus_share_cache(int this_cpu, int that_cpu); +bool cpus_share_resources(int this_cpu, int that_cpu); typedef const struct cpumask *(*sched_domain_mask_f)(int cpu); typedef int (*sched_domain_flags_f)(void); @@ -232,6 +231,11 @@ static inline bool cpus_share_cache(int this_cpu, int that_cpu) return true; } +static inline bool cpus_share_resources(int this_cpu, int that_cpu) +{ + return true; +} + #endif /* !CONFIG_SMP */ #if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL) diff --git a/include/linux/sched/types.h b/include/linux/sched/types.h index 3c3e049224ae..969aaf5ef9d6 100644 --- a/include/linux/sched/types.h +++ b/include/linux/sched/types.h @@ -20,4 +20,4 @@ struct task_cputime { unsigned long long sum_exec_runtime; }; -#endif +#endif /* _LINUX_SCHED_TYPES_H */ diff --git a/include/linux/sched/vhost_task.h b/include/linux/sched/vhost_task.h index 837a23624a66..bc60243d43b3 100644 --- a/include/linux/sched/vhost_task.h +++ b/include/linux/sched/vhost_task.h @@ -1,7 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _LINUX_VHOST_TASK_H -#define _LINUX_VHOST_TASK_H - +#ifndef _LINUX_SCHED_VHOST_TASK_H +#define _LINUX_SCHED_VHOST_TASK_H struct vhost_task; @@ -11,4 +10,4 @@ void vhost_task_start(struct vhost_task *vtsk); void vhost_task_stop(struct vhost_task *vtsk); void vhost_task_wake(struct vhost_task *vtsk); -#endif +#endif /* _LINUX_SCHED_VHOST_TASK_H */ diff --git a/include/linux/security.h b/include/linux/security.h index 5f16eecde00b..1d1df326c881 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -151,7 +151,7 @@ extern int cap_capset(struct cred *new, const struct cred *old, const kernel_cap_t *effective, const kernel_cap_t *inheritable, const kernel_cap_t *permitted); -extern int cap_bprm_creds_from_file(struct linux_binprm *bprm, struct file *file); +extern int cap_bprm_creds_from_file(struct linux_binprm *bprm, const struct file *file); int cap_inode_setxattr(struct dentry *dentry, const char *name, const void *value, size_t size, int flags); int cap_inode_removexattr(struct mnt_idmap *idmap, @@ -284,16 +284,16 @@ int security_capable(const struct cred *cred, struct user_namespace *ns, int cap, unsigned int opts); -int security_quotactl(int cmds, int type, int id, struct super_block *sb); +int security_quotactl(int cmds, int type, int id, const struct super_block *sb); int security_quota_on(struct dentry *dentry); int security_syslog(int type); int security_settime64(const struct timespec64 *ts, const struct timezone *tz); int security_vm_enough_memory_mm(struct mm_struct *mm, long pages); int security_bprm_creds_for_exec(struct linux_binprm *bprm); -int security_bprm_creds_from_file(struct linux_binprm *bprm, struct file *file); +int security_bprm_creds_from_file(struct linux_binprm *bprm, const struct file *file); int security_bprm_check(struct linux_binprm *bprm); -void security_bprm_committing_creds(struct linux_binprm *bprm); -void security_bprm_committed_creds(struct linux_binprm *bprm); +void security_bprm_committing_creds(const struct linux_binprm *bprm); +void security_bprm_committed_creds(const struct linux_binprm *bprm); int security_fs_context_submount(struct fs_context *fc, struct super_block *reference); int security_fs_context_dup(struct fs_context *fc, struct fs_context *src_fc); int security_fs_context_parse_param(struct fs_context *fc, struct fs_parameter *param); @@ -304,7 +304,7 @@ void security_free_mnt_opts(void **mnt_opts); int security_sb_eat_lsm_opts(char *options, void **mnt_opts); int security_sb_mnt_opts_compat(struct super_block *sb, void *mnt_opts); int security_sb_remount(struct super_block *sb, void *mnt_opts); -int security_sb_kern_mount(struct super_block *sb); +int security_sb_kern_mount(const struct super_block *sb); int security_sb_show_options(struct seq_file *m, struct super_block *sb); int security_sb_statfs(struct dentry *dentry); int security_sb_mount(const char *dev_name, const struct path *path, @@ -581,7 +581,7 @@ static inline int security_capable(const struct cred *cred, } static inline int security_quotactl(int cmds, int type, int id, - struct super_block *sb) + const struct super_block *sb) { return 0; } @@ -613,7 +613,7 @@ static inline int security_bprm_creds_for_exec(struct linux_binprm *bprm) } static inline int security_bprm_creds_from_file(struct linux_binprm *bprm, - struct file *file) + const struct file *file) { return cap_bprm_creds_from_file(bprm, file); } @@ -623,11 +623,11 @@ static inline int security_bprm_check(struct linux_binprm *bprm) return 0; } -static inline void security_bprm_committing_creds(struct linux_binprm *bprm) +static inline void security_bprm_committing_creds(const struct linux_binprm *bprm) { } -static inline void security_bprm_committed_creds(struct linux_binprm *bprm) +static inline void security_bprm_committed_creds(const struct linux_binprm *bprm) { } diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h index 987a59d977c5..e92f9d5577ba 100644 --- a/include/linux/seqlock.h +++ b/include/linux/seqlock.h @@ -191,11 +191,9 @@ static inline void seqcount_lockdep_reader_access(const seqcount_t *s) * @lockname: "LOCKNAME" part of seqcount_LOCKNAME_t * @locktype: LOCKNAME canonical C data type * @preemptible: preemptibility of above locktype - * @lockmember: argument for lockdep_assert_held() - * @lockbase: associated lock release function (prefix only) - * @lock_acquire: associated lock acquisition function (full call) + * @lockbase: prefix for associated lock/unlock */ -#define SEQCOUNT_LOCKNAME(lockname, locktype, preemptible, lockmember, lockbase, lock_acquire) \ +#define SEQCOUNT_LOCKNAME(lockname, locktype, preemptible, lockbase) \ typedef struct seqcount_##lockname { \ seqcount_t seqcount; \ __SEQ_LOCK(locktype *lock); \ @@ -207,6 +205,12 @@ __seqprop_##lockname##_ptr(seqcount_##lockname##_t *s) \ return &s->seqcount; \ } \ \ +static __always_inline const seqcount_t * \ +__seqprop_##lockname##_const_ptr(const seqcount_##lockname##_t *s) \ +{ \ + return &s->seqcount; \ +} \ + \ static __always_inline unsigned \ __seqprop_##lockname##_sequence(const seqcount_##lockname##_t *s) \ { \ @@ -216,7 +220,7 @@ __seqprop_##lockname##_sequence(const seqcount_##lockname##_t *s) \ return seq; \ \ if (preemptible && unlikely(seq & 1)) { \ - __SEQ_LOCK(lock_acquire); \ + __SEQ_LOCK(lockbase##_lock(s->lock)); \ __SEQ_LOCK(lockbase##_unlock(s->lock)); \ \ /* \ @@ -242,7 +246,7 @@ __seqprop_##lockname##_preemptible(const seqcount_##lockname##_t *s) \ static __always_inline void \ __seqprop_##lockname##_assert(const seqcount_##lockname##_t *s) \ { \ - __SEQ_LOCK(lockdep_assert_held(lockmember)); \ + __SEQ_LOCK(lockdep_assert_held(s->lock)); \ } /* @@ -254,6 +258,11 @@ static inline seqcount_t *__seqprop_ptr(seqcount_t *s) return s; } +static inline const seqcount_t *__seqprop_const_ptr(const seqcount_t *s) +{ + return s; +} + static inline unsigned __seqprop_sequence(const seqcount_t *s) { return READ_ONCE(s->sequence); @@ -271,10 +280,10 @@ static inline void __seqprop_assert(const seqcount_t *s) #define __SEQ_RT IS_ENABLED(CONFIG_PREEMPT_RT) -SEQCOUNT_LOCKNAME(raw_spinlock, raw_spinlock_t, false, s->lock, raw_spin, raw_spin_lock(s->lock)) -SEQCOUNT_LOCKNAME(spinlock, spinlock_t, __SEQ_RT, s->lock, spin, spin_lock(s->lock)) -SEQCOUNT_LOCKNAME(rwlock, rwlock_t, __SEQ_RT, s->lock, read, read_lock(s->lock)) -SEQCOUNT_LOCKNAME(mutex, struct mutex, true, s->lock, mutex, mutex_lock(s->lock)) +SEQCOUNT_LOCKNAME(raw_spinlock, raw_spinlock_t, false, raw_spin) +SEQCOUNT_LOCKNAME(spinlock, spinlock_t, __SEQ_RT, spin) +SEQCOUNT_LOCKNAME(rwlock, rwlock_t, __SEQ_RT, read) +SEQCOUNT_LOCKNAME(mutex, struct mutex, true, mutex) /* * SEQCNT_LOCKNAME_ZERO - static initializer for seqcount_LOCKNAME_t @@ -294,19 +303,20 @@ SEQCOUNT_LOCKNAME(mutex, struct mutex, true, s->lock, mutex #define SEQCNT_WW_MUTEX_ZERO(name, lock) SEQCOUNT_LOCKNAME_ZERO(name, lock) #define __seqprop_case(s, lockname, prop) \ - seqcount_##lockname##_t: __seqprop_##lockname##_##prop((void *)(s)) + seqcount_##lockname##_t: __seqprop_##lockname##_##prop #define __seqprop(s, prop) _Generic(*(s), \ - seqcount_t: __seqprop_##prop((void *)(s)), \ + seqcount_t: __seqprop_##prop, \ __seqprop_case((s), raw_spinlock, prop), \ __seqprop_case((s), spinlock, prop), \ __seqprop_case((s), rwlock, prop), \ __seqprop_case((s), mutex, prop)) -#define seqprop_ptr(s) __seqprop(s, ptr) -#define seqprop_sequence(s) __seqprop(s, sequence) -#define seqprop_preemptible(s) __seqprop(s, preemptible) -#define seqprop_assert(s) __seqprop(s, assert) +#define seqprop_ptr(s) __seqprop(s, ptr)(s) +#define seqprop_const_ptr(s) __seqprop(s, const_ptr)(s) +#define seqprop_sequence(s) __seqprop(s, sequence)(s) +#define seqprop_preemptible(s) __seqprop(s, preemptible)(s) +#define seqprop_assert(s) __seqprop(s, assert)(s) /** * __read_seqcount_begin() - begin a seqcount_t read section w/o barrier @@ -355,7 +365,7 @@ SEQCOUNT_LOCKNAME(mutex, struct mutex, true, s->lock, mutex */ #define read_seqcount_begin(s) \ ({ \ - seqcount_lockdep_reader_access(seqprop_ptr(s)); \ + seqcount_lockdep_reader_access(seqprop_const_ptr(s)); \ raw_read_seqcount_begin(s); \ }) @@ -421,7 +431,7 @@ SEQCOUNT_LOCKNAME(mutex, struct mutex, true, s->lock, mutex * Return: true if a read section retry is required, else false */ #define __read_seqcount_retry(s, start) \ - do___read_seqcount_retry(seqprop_ptr(s), start) + do___read_seqcount_retry(seqprop_const_ptr(s), start) static inline int do___read_seqcount_retry(const seqcount_t *s, unsigned start) { @@ -441,7 +451,7 @@ static inline int do___read_seqcount_retry(const seqcount_t *s, unsigned start) * Return: true if a read section retry is required, else false */ #define read_seqcount_retry(s, start) \ - do_read_seqcount_retry(seqprop_ptr(s), start) + do_read_seqcount_retry(seqprop_const_ptr(s), start) static inline int do_read_seqcount_retry(const seqcount_t *s, unsigned start) { @@ -512,8 +522,8 @@ do { \ static inline void do_write_seqcount_begin_nested(seqcount_t *s, int subclass) { - do_raw_write_seqcount_begin(s); seqcount_acquire(&s->dep_map, subclass, 0, _RET_IP_); + do_raw_write_seqcount_begin(s); } /** @@ -574,7 +584,7 @@ static inline void do_write_seqcount_end(seqcount_t *s) * via WRITE_ONCE): a) to ensure the writes become visible to other threads * atomically, avoiding compiler optimizations; b) to document which writes are * meant to propagate to the reader critical section. This is necessary because - * neither writes before and after the barrier are enclosed in a seq-writer + * neither writes before nor after the barrier are enclosed in a seq-writer * critical section that would ensure readers are aware of ongoing writes:: * * seqcount_t seq; @@ -864,7 +874,7 @@ static inline unsigned read_seqretry(const seqlock_t *sl, unsigned start) } /* - * For all seqlock_t write side functions, use the the internal + * For all seqlock_t write side functions, use the internal * do_write_seqcount_begin() instead of generic write_seqcount_begin(). * This way, no redundant lockdep_assert_held() checks are added. */ diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 4174c4b82d13..27998f73183e 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1309,7 +1309,7 @@ struct sk_buff_fclones { * * Returns true if skb is a fast clone, and its clone is not freed. * Some drivers call skb_orphan() in their ndo_start_xmit(), - * so we also check that this didnt happen. + * so we also check that didn't happen. */ static inline bool skb_fclone_busy(const struct sock *sk, const struct sk_buff *skb) @@ -2016,7 +2016,7 @@ static inline struct sk_buff *skb_share_check(struct sk_buff *skb, gfp_t pri) * Copy shared buffers into a new sk_buff. We effectively do COW on * packets to handle cases where we have a local reader and forward * and a couple of other messy ones. The normal one is tcpdumping - * a packet thats being forwarded. + * a packet that's being forwarded. */ /** @@ -3679,6 +3679,9 @@ static inline int __must_check skb_put_padto(struct sk_buff *skb, unsigned int l return __skb_put_padto(skb, len, true); } +bool csum_and_copy_from_iter_full(void *addr, size_t bytes, __wsum *csum, struct iov_iter *i) + __must_check; + static inline int skb_add_data(struct sk_buff *skb, struct iov_iter *from, int copy) { diff --git a/include/linux/slab.h b/include/linux/slab.h index 8228d1276a2f..ff56ab804bf6 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -245,8 +245,9 @@ DEFINE_FREE(kfree, void *, if (_T) kfree(_T)) size_t ksize(const void *objp); #ifdef CONFIG_PRINTK -bool kmem_valid_obj(void *object); -void kmem_dump_obj(void *object); +bool kmem_dump_obj(void *object); +#else +static inline bool kmem_dump_obj(void *object) { return false; } #endif /* diff --git a/include/linux/smp.h b/include/linux/smp.h index 91ea4a67f8ca..e87520dc2959 100644 --- a/include/linux/smp.h +++ b/include/linux/smp.h @@ -53,7 +53,7 @@ int smp_call_function_single(int cpuid, smp_call_func_t func, void *info, void on_each_cpu_cond_mask(smp_cond_func_t cond_func, smp_call_func_t func, void *info, bool wait, const struct cpumask *mask); -int smp_call_function_single_async(int cpu, struct __call_single_data *csd); +int smp_call_function_single_async(int cpu, call_single_data_t *csd); /* * Cpus stopping functions in panic. All have default weak definitions. diff --git a/include/linux/soc/mediatek/mtk_wed.h b/include/linux/soc/mediatek/mtk_wed.h index b2b28180dff7..a476648858a6 100644 --- a/include/linux/soc/mediatek/mtk_wed.h +++ b/include/linux/soc/mediatek/mtk_wed.h @@ -10,6 +10,7 @@ #define MTK_WED_TX_QUEUES 2 #define MTK_WED_RX_QUEUES 2 +#define MTK_WED_RX_PAGE_QUEUES 3 #define WED_WO_STA_REC 0x6 @@ -45,7 +46,7 @@ enum mtk_wed_wo_cmd { MTK_WED_WO_CMD_WED_END }; -struct mtk_rxbm_desc { +struct mtk_wed_bm_desc { __le32 buf0; __le32 token; } __packed __aligned(4); @@ -76,6 +77,11 @@ struct mtk_wed_wo_rx_stats { __le32 rx_drop_cnt; }; +struct mtk_wed_buf { + void *p; + dma_addr_t phy_addr; +}; + struct mtk_wed_device { #ifdef CONFIG_NET_MEDIATEK_SOC_WED const struct mtk_wed_ops *ops; @@ -94,17 +100,20 @@ struct mtk_wed_device { struct mtk_wed_ring txfree_ring; struct mtk_wed_ring tx_wdma[MTK_WED_TX_QUEUES]; struct mtk_wed_ring rx_wdma[MTK_WED_RX_QUEUES]; + struct mtk_wed_ring rx_rro_ring[MTK_WED_RX_QUEUES]; + struct mtk_wed_ring rx_page_ring[MTK_WED_RX_PAGE_QUEUES]; + struct mtk_wed_ring ind_cmd_ring; struct { int size; - void **pages; + struct mtk_wed_buf *pages; struct mtk_wdma_desc *desc; dma_addr_t desc_phys; } tx_buf_ring; struct { int size; - struct mtk_rxbm_desc *desc; + struct mtk_wed_bm_desc *desc; dma_addr_t desc_phys; } rx_buf_ring; @@ -114,6 +123,13 @@ struct mtk_wed_device { dma_addr_t fdbk_phys; } rro; + struct { + int size; + struct mtk_wed_buf *pages; + struct mtk_wed_bm_desc *desc; + dma_addr_t desc_phys; + } hw_rro; + /* filled by driver: */ struct { union { @@ -123,6 +139,7 @@ struct mtk_wed_device { enum mtk_wed_bus_tye bus_type; void __iomem *base; u32 phy_base; + u32 id; u32 wpdma_phys; u32 wpdma_int; @@ -131,18 +148,35 @@ struct mtk_wed_device { u32 wpdma_txfree; u32 wpdma_rx_glo; u32 wpdma_rx; + u32 wpdma_rx_rro[MTK_WED_RX_QUEUES]; + u32 wpdma_rx_pg; bool wcid_512; + bool hw_rro; + bool msi; u16 token_start; unsigned int nbuf; unsigned int rx_nbuf; unsigned int rx_npkt; unsigned int rx_size; + unsigned int amsdu_max_len; u8 tx_tbit[MTK_WED_TX_QUEUES]; u8 rx_tbit[MTK_WED_RX_QUEUES]; + u8 rro_rx_tbit[MTK_WED_RX_QUEUES]; + u8 rx_pg_tbit[MTK_WED_RX_PAGE_QUEUES]; u8 txfree_tbit; + u8 amsdu_max_subframes; + + struct { + u8 se_group_nums; + u16 win_size; + u16 particular_sid; + u32 ack_sn_addr; + dma_addr_t particular_se_phys; + dma_addr_t addr_elem_phys[1024]; + } ind_cmd; u32 (*init_buf)(void *ptr, dma_addr_t phys, int token_id); int (*offload_enable)(struct mtk_wed_device *wed); @@ -182,6 +216,14 @@ struct mtk_wed_ops { void (*irq_set_mask)(struct mtk_wed_device *dev, u32 mask); int (*setup_tc)(struct mtk_wed_device *wed, struct net_device *dev, enum tc_setup_type type, void *type_data); + void (*start_hw_rro)(struct mtk_wed_device *dev, u32 irq_mask, + bool reset); + void (*rro_rx_ring_setup)(struct mtk_wed_device *dev, int ring, + void __iomem *regs); + void (*msdu_pg_rx_ring_setup)(struct mtk_wed_device *dev, int ring, + void __iomem *regs); + int (*ind_rx_ring_setup)(struct mtk_wed_device *dev, + void __iomem *regs); }; extern const struct mtk_wed_ops __rcu *mtk_soc_wed_ops; @@ -206,16 +248,27 @@ mtk_wed_device_attach(struct mtk_wed_device *dev) return ret; } -static inline bool -mtk_wed_get_rx_capa(struct mtk_wed_device *dev) +static inline bool mtk_wed_get_rx_capa(struct mtk_wed_device *dev) { #ifdef CONFIG_NET_MEDIATEK_SOC_WED + if (dev->version == 3) + return dev->wlan.hw_rro; + return dev->version != 1; #else return false; #endif } +static inline bool mtk_wed_is_amsdu_supported(struct mtk_wed_device *dev) +{ +#ifdef CONFIG_NET_MEDIATEK_SOC_WED + return dev->version == 3; +#else + return false; +#endif +} + #ifdef CONFIG_NET_MEDIATEK_SOC_WED #define mtk_wed_device_active(_dev) !!(_dev)->ops #define mtk_wed_device_detach(_dev) (_dev)->ops->detach(_dev) @@ -242,6 +295,15 @@ mtk_wed_get_rx_capa(struct mtk_wed_device *dev) #define mtk_wed_device_dma_reset(_dev) (_dev)->ops->reset_dma(_dev) #define mtk_wed_device_setup_tc(_dev, _netdev, _type, _type_data) \ (_dev)->ops->setup_tc(_dev, _netdev, _type, _type_data) +#define mtk_wed_device_start_hw_rro(_dev, _mask, _reset) \ + (_dev)->ops->start_hw_rro(_dev, _mask, _reset) +#define mtk_wed_device_rro_rx_ring_setup(_dev, _ring, _regs) \ + (_dev)->ops->rro_rx_ring_setup(_dev, _ring, _regs) +#define mtk_wed_device_msdu_pg_rx_ring_setup(_dev, _ring, _regs) \ + (_dev)->ops->msdu_pg_rx_ring_setup(_dev, _ring, _regs) +#define mtk_wed_device_ind_rx_ring_setup(_dev, _regs) \ + (_dev)->ops->ind_rx_ring_setup(_dev, _regs) + #else static inline bool mtk_wed_device_active(struct mtk_wed_device *dev) { @@ -261,6 +323,10 @@ static inline bool mtk_wed_device_active(struct mtk_wed_device *dev) #define mtk_wed_device_stop(_dev) do {} while (0) #define mtk_wed_device_dma_reset(_dev) do {} while (0) #define mtk_wed_device_setup_tc(_dev, _netdev, _type, _type_data) -EOPNOTSUPP +#define mtk_wed_device_start_hw_rro(_dev, _mask, _reset) do {} while (0) +#define mtk_wed_device_rro_rx_ring_setup(_dev, _ring, _regs) -ENODEV +#define mtk_wed_device_msdu_pg_rx_ring_setup(_dev, _ring, _regs) -ENODEV +#define mtk_wed_device_ind_rx_ring_setup(_dev, _regs) -ENODEV #endif #endif diff --git a/include/linux/socket.h b/include/linux/socket.h index 39b74d83c7c4..cfcb7e2c3813 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -383,6 +383,7 @@ struct ucred { #define SOL_MPTCP 284 #define SOL_MCTP 285 #define SOL_SMC 286 +#define SOL_VSOCK 287 /* IPX options */ #define IPX_TYPE 1 diff --git a/include/linux/sockptr.h b/include/linux/sockptr.h index bae5e2369b4f..307961b41541 100644 --- a/include/linux/sockptr.h +++ b/include/linux/sockptr.h @@ -55,6 +55,29 @@ static inline int copy_from_sockptr(void *dst, sockptr_t src, size_t size) return copy_from_sockptr_offset(dst, src, 0, size); } +static inline int copy_struct_from_sockptr(void *dst, size_t ksize, + sockptr_t src, size_t usize) +{ + size_t size = min(ksize, usize); + size_t rest = max(ksize, usize) - size; + + if (!sockptr_is_kernel(src)) + return copy_struct_from_user(dst, ksize, src.user, size); + + if (usize < ksize) { + memset(dst + size, 0, rest); + } else if (usize > ksize) { + char *p = src.kernel; + + while (rest--) { + if (*p++) + return -E2BIG; + } + } + memcpy(dst, src.kernel, size); + return 0; +} + static inline int copy_to_sockptr_offset(sockptr_t dst, size_t offset, const void *src, size_t size) { diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 7f8b478fdeb3..86825c88b576 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -867,6 +867,7 @@ extern int devm_spi_register_controller(struct device *dev, extern void spi_unregister_controller(struct spi_controller *ctlr); #if IS_ENABLED(CONFIG_ACPI) +extern struct spi_controller *acpi_spi_find_controller_by_adev(struct acpi_device *adev); extern struct spi_device *acpi_spi_device_alloc(struct spi_controller *ctlr, struct acpi_device *adev, int index); @@ -1086,8 +1087,6 @@ struct spi_transfer { * @state: for use by whichever driver currently owns the message * @resources: for resource management when the SPI message is processed * @prepared: spi_prepare_message was called for the this message - * @t: for use with spi_message_alloc() when message and transfers have - * been allocated together * * A @spi_message is used to execute an atomic sequence of data transfers, * each represented by a struct spi_transfer. The sequence is "atomic" @@ -1142,9 +1141,6 @@ struct spi_message { /* List of spi_res resources when the SPI message is processed */ struct list_head resources; - - /* For embedding transfers into the memory of the message */ - struct spi_transfer t[]; }; static inline void spi_message_init_no_memset(struct spi_message *m) @@ -1203,17 +1199,21 @@ struct spi_transfer *xfers, unsigned int num_xfers) */ static inline struct spi_message *spi_message_alloc(unsigned ntrans, gfp_t flags) { - struct spi_message *m; + struct spi_message_with_transfers { + struct spi_message m; + struct spi_transfer t[]; + } *mwt; + unsigned i; + + mwt = kzalloc(struct_size(mwt, t, ntrans), flags); + if (!mwt) + return NULL; - m = kzalloc(struct_size(m, t, ntrans), flags); - if (m) { - unsigned i; + spi_message_init_no_memset(&mwt->m); + for (i = 0; i < ntrans; i++) + spi_message_add_tail(&mwt->t[i], &mwt->m); - spi_message_init_no_memset(m); - for (i = 0; i < ntrans; i++) - spi_message_add_tail(&m->t[i], m); - } - return m; + return &mwt->m; } static inline void spi_message_free(struct spi_message *m) diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index ce89cc3e4913..0b4658a7eceb 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -139,6 +139,7 @@ struct stmmac_rxq_cfg { struct stmmac_txq_cfg { u32 weight; + bool coe_unsupported; u8 mode_to_use; /* Credit Base Shaper parameters */ u32 send_slope; @@ -302,7 +303,6 @@ struct plat_stmmacenet_data { unsigned int eee_usecs_rate; struct pci_dev *pdev; int int_snapshot_num; - int ext_snapshot_num; int msi_mac_vec; int msi_wol_vec; int msi_lpi_vec; diff --git a/include/linux/string.h b/include/linux/string.h index dbfc66400050..9e3cb6923b0e 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -277,10 +277,12 @@ void memcpy_and_pad(void *dest, size_t dest_len, const void *src, size_t count, */ #define strtomem_pad(dest, src, pad) do { \ const size_t _dest_len = __builtin_object_size(dest, 1); \ + const size_t _src_len = __builtin_object_size(src, 1); \ \ BUILD_BUG_ON(!__builtin_constant_p(_dest_len) || \ _dest_len == (size_t)-1); \ - memcpy_and_pad(dest, _dest_len, src, strnlen(src, _dest_len), pad); \ + memcpy_and_pad(dest, _dest_len, src, \ + strnlen(src, min(_src_len, _dest_len)), pad); \ } while (0) /** @@ -298,10 +300,11 @@ void memcpy_and_pad(void *dest, size_t dest_len, const void *src, size_t count, */ #define strtomem(dest, src) do { \ const size_t _dest_len = __builtin_object_size(dest, 1); \ + const size_t _src_len = __builtin_object_size(src, 1); \ \ BUILD_BUG_ON(!__builtin_constant_p(_dest_len) || \ _dest_len == (size_t)-1); \ - memcpy(dest, src, min(_dest_len, strnlen(src, _dest_len))); \ + memcpy(dest, src, strnlen(src, min(_src_len, _dest_len))); \ } while (0) /** diff --git a/include/linux/string_helpers.h b/include/linux/string_helpers.h index 9d1f5bb74dd5..58fb1f90eda5 100644 --- a/include/linux/string_helpers.h +++ b/include/linux/string_helpers.h @@ -24,8 +24,8 @@ enum string_size_units { STRING_UNITS_2, /* use binary powers of 2^10 */ }; -void string_get_size(u64 size, u64 blk_size, enum string_size_units units, - char *buf, int len); +int string_get_size(u64 size, u64 blk_size, enum string_size_units units, + char *buf, int len); int parse_int_array_user(const char __user *from, size_t count, int **array); diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index dbf5b21feafe..b10f987509cc 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -17,6 +17,7 @@ #include <linux/sunrpc/xdr.h> #include <linux/sunrpc/auth.h> #include <linux/sunrpc/svcauth.h> +#include <linux/lwq.h> #include <linux/wait.h> #include <linux/mm.h> #include <linux/pagevec.h> @@ -33,10 +34,10 @@ */ struct svc_pool { unsigned int sp_id; /* pool id; also node id on NUMA */ - spinlock_t sp_lock; /* protects all fields */ - struct list_head sp_sockets; /* pending sockets */ - unsigned int sp_nrthreads; /* # of threads in pool */ + struct lwq sp_xprts; /* pending transports */ + atomic_t sp_nrthreads; /* # of threads in pool */ struct list_head sp_all_threads; /* all server threads */ + struct llist_head sp_idle_threads; /* idle server threads */ /* statistics on pool operation */ struct percpu_counter sp_messages_arrived; @@ -49,7 +50,8 @@ struct svc_pool { /* bits for sp_flags */ enum { SP_TASK_PENDING, /* still work to do even if no xprt is queued */ - SP_CONGESTED, /* all threads are busy, none idle */ + SP_NEED_VICTIM, /* One thread needs to agree to exit */ + SP_VICTIM_REMAINS, /* One thread needs to actually exit */ }; @@ -88,12 +90,9 @@ struct svc_serv { int (*sv_threadfn)(void *data); #if defined(CONFIG_SUNRPC_BACKCHANNEL) - struct list_head sv_cb_list; /* queue for callback requests + struct lwq sv_cb_list; /* queue for callback requests * that arrive over the same * connection */ - spinlock_t sv_cb_lock; /* protects the svc_cb_list */ - wait_queue_head_t sv_cb_waitq; /* sleep here if there are no - * entries in the svc_cb_list */ bool sv_bc_enabled; /* service uses backchannel */ #endif /* CONFIG_SUNRPC_BACKCHANNEL */ }; @@ -186,6 +185,7 @@ extern u32 svc_max_payload(const struct svc_rqst *rqstp); */ struct svc_rqst { struct list_head rq_all; /* all threads list */ + struct llist_node rq_idle; /* On the idle list */ struct rcu_head rq_rcu_head; /* for RCU deferred kfree */ struct svc_xprt * rq_xprt; /* transport ptr */ @@ -251,6 +251,7 @@ struct svc_rqst { * net namespace */ void ** rq_lease_breaker; /* The v4 client breaking a lease */ + unsigned int rq_status_counter; /* RPC processing counter */ }; /* bits for rq_flags */ @@ -261,8 +262,7 @@ enum { RQ_DROPME, /* drop current reply */ RQ_SPLICE_OK, /* turned off in gss privacy to prevent * encrypting page cache pages */ - RQ_VICTIM, /* about to be shut down */ - RQ_BUSY, /* request is busy */ + RQ_VICTIM, /* Have agreed to shut down */ RQ_DATA, /* request has data */ }; @@ -301,6 +301,28 @@ static inline struct sockaddr *svc_daddr(const struct svc_rqst *rqst) return (struct sockaddr *) &rqst->rq_daddr; } +/** + * svc_thread_should_stop - check if this thread should stop + * @rqstp: the thread that might need to stop + * + * To stop an svc thread, the pool flags SP_NEED_VICTIM and SP_VICTIM_REMAINS + * are set. The first thread which sees SP_NEED_VICTIM clears it, becoming + * the victim using this function. It should then promptly call + * svc_exit_thread() to complete the process, clearing SP_VICTIM_REMAINS + * so the task waiting for a thread to exit can wake and continue. + * + * Return values: + * %true: caller should invoke svc_exit_thread() + * %false: caller should do nothing + */ +static inline bool svc_thread_should_stop(struct svc_rqst *rqstp) +{ + if (test_and_clear_bit(SP_NEED_VICTIM, &rqstp->rq_pool->sp_flags)) + set_bit(RQ_VICTIM, &rqstp->rq_flags); + + return test_bit(RQ_VICTIM, &rqstp->rq_flags); +} + struct svc_deferred_req { u32 prot; /* protocol (UDP or TCP) */ struct svc_xprt *xprt; @@ -413,8 +435,7 @@ struct svc_serv * svc_create_pooled(struct svc_program *, unsigned int, int svc_set_num_threads(struct svc_serv *, struct svc_pool *, int); int svc_pool_stats_open(struct svc_serv *serv, struct file *file); void svc_process(struct svc_rqst *rqstp); -int bc_svc_process(struct svc_serv *, struct rpc_rqst *, - struct svc_rqst *); +void svc_process_bc(struct rpc_rqst *req, struct svc_rqst *rqstp); int svc_register(const struct svc_serv *, struct net *, const int, const unsigned short, const unsigned short); diff --git a/include/linux/sunrpc/svc_xprt.h b/include/linux/sunrpc/svc_xprt.h index fa55d12dc765..8e20cd60e2e7 100644 --- a/include/linux/sunrpc/svc_xprt.h +++ b/include/linux/sunrpc/svc_xprt.h @@ -54,7 +54,7 @@ struct svc_xprt { const struct svc_xprt_ops *xpt_ops; struct kref xpt_ref; struct list_head xpt_list; - struct list_head xpt_ready; + struct lwq_node xpt_ready; unsigned long xpt_flags; struct svc_serv *xpt_server; /* service for transport */ diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h index 5b4fb3c791bc..2f8dc47f1eb0 100644 --- a/include/linux/sunrpc/xdr.h +++ b/include/linux/sunrpc/xdr.h @@ -779,7 +779,9 @@ xdr_stream_decode_uint32_array(struct xdr_stream *xdr, if (unlikely(xdr_stream_decode_u32(xdr, &len) < 0)) return -EBADMSG; - p = xdr_inline_decode(xdr, size_mul(len, sizeof(*p))); + if (U32_MAX >= SIZE_MAX / sizeof(*p) && len > SIZE_MAX / sizeof(*p)) + return -EBADMSG; + p = xdr_inline_decode(xdr, len * sizeof(*p)); if (unlikely(!p)) return -EBADMSG; if (array == NULL) diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 4ecc89301eb7..f85d3a0daca2 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -57,6 +57,7 @@ struct xprt_class; struct seq_file; struct svc_serv; struct net; +#include <linux/lwq.h> /* * This describes a complete RPC request @@ -121,7 +122,7 @@ struct rpc_rqst { int rq_ntrans; #if defined(CONFIG_SUNRPC_BACKCHANNEL) - struct list_head rq_bc_list; /* Callback service list */ + struct lwq_node rq_bc_list; /* Callback service list */ unsigned long rq_bc_pa_state; /* Backchannel prealloc state */ struct list_head rq_bc_pa_list; /* Backchannel prealloc list */ #endif /* CONFIG_SUNRPC_BACKCHANEL */ diff --git a/include/linux/surface_aggregator/controller.h b/include/linux/surface_aggregator/controller.h index cb7980805920..5b67f0f47d80 100644 --- a/include/linux/surface_aggregator/controller.h +++ b/include/linux/surface_aggregator/controller.h @@ -44,7 +44,7 @@ struct ssam_event { u8 command_id; u8 instance_id; u16 length; - u8 data[]; + u8 data[] __counted_by(length); }; /** diff --git a/include/linux/swap.h b/include/linux/swap.h index 493487ed7c38..f6dd6575b905 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -298,6 +298,7 @@ struct swap_info_struct { unsigned int __percpu *cluster_next_cpu; /*percpu index for next allocation */ struct percpu_cluster __percpu *percpu_cluster; /* per cpu's swap location */ struct rb_root swap_extent_root;/* root of the swap extent rbtree */ + struct bdev_handle *bdev_handle;/* open handle of the bdev */ struct block_device *bdev; /* swap device or bdev of swap file */ struct file *swap_file; /* seldom referenced */ unsigned int old_block_size; /* seldom referenced */ diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index b4536626f8ff..ecde0312dd52 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -172,14 +172,23 @@ static inline bool is_swiotlb_buffer(struct device *dev, phys_addr_t paddr) if (!mem) return false; - if (IS_ENABLED(CONFIG_SWIOTLB_DYNAMIC)) { - /* Pairs with smp_wmb() in swiotlb_find_slots() and - * swiotlb_dyn_alloc(), which modify the RCU lists. - */ - smp_rmb(); - return swiotlb_find_pool(dev, paddr); - } +#ifdef CONFIG_SWIOTLB_DYNAMIC + /* + * All SWIOTLB buffer addresses must have been returned by + * swiotlb_tbl_map_single() and passed to a device driver. + * If a SWIOTLB address is checked on another CPU, then it was + * presumably loaded by the device driver from an unspecified private + * data structure. Make sure that this load is ordered before reading + * dev->dma_uses_io_tlb here and mem->pools in swiotlb_find_pool(). + * + * This barrier pairs with smp_mb() in swiotlb_find_slots(). + */ + smp_rmb(); + return READ_ONCE(dev->dma_uses_io_tlb) && + swiotlb_find_pool(dev, paddr); +#else return paddr >= mem->defpool.start && paddr < mem->defpool.end; +#endif } static inline bool is_swiotlb_force_bounce(struct device *dev) diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 22bc6bc147f8..0901af60d971 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -549,6 +549,16 @@ asmlinkage long sys_set_robust_list(struct robust_list_head __user *head, asmlinkage long sys_futex_waitv(struct futex_waitv *waiters, unsigned int nr_futexes, unsigned int flags, struct __kernel_timespec __user *timeout, clockid_t clockid); + +asmlinkage long sys_futex_wake(void __user *uaddr, unsigned long mask, int nr, unsigned int flags); + +asmlinkage long sys_futex_wait(void __user *uaddr, unsigned long val, unsigned long mask, + unsigned int flags, struct __kernel_timespec __user *timespec, + clockid_t clockid); + +asmlinkage long sys_futex_requeue(struct futex_waitv __user *waiters, + unsigned int flags, int nr_wake, int nr_requeue); + asmlinkage long sys_nanosleep(struct __kernel_timespec __user *rqtp, struct __kernel_timespec __user *rmtp); asmlinkage long sys_nanosleep_time32(struct old_timespec32 __user *rqtp, diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 3c5efeeb024f..ec4e9367f5b0 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -152,6 +152,7 @@ struct tcp_request_sock { u64 snt_synack; /* first SYNACK sent time */ bool tfo_listener; bool is_mptcp; + s8 req_usec_ts; #if IS_ENABLED(CONFIG_MPTCP) bool drop_req; #endif @@ -165,6 +166,11 @@ struct tcp_request_sock { * after data-in-SYN. */ u8 syn_tos; +#ifdef CONFIG_TCP_AO + u8 ao_keyid; + u8 ao_rcv_next; + u8 maclen; +#endif }; static inline struct tcp_request_sock *tcp_rsk(const struct request_sock *req) @@ -172,6 +178,19 @@ static inline struct tcp_request_sock *tcp_rsk(const struct request_sock *req) return (struct tcp_request_sock *)req; } +static inline bool tcp_rsk_used_ao(const struct request_sock *req) +{ + /* The real length of MAC is saved in the request socket, + * signing anything with zero-length makes no sense, so here is + * a little hack.. + */ +#ifndef CONFIG_TCP_AO + return false; +#else + return tcp_rsk(req)->maclen != 0; +#endif +} + #define TCP_RMEM_TO_WIN_SCALE 8 struct tcp_sock { @@ -257,7 +276,8 @@ struct tcp_sock { u8 compressed_ack; u8 dup_ack_counter:2, tlp_retrans:1, /* TLP is a retransmission */ - unused:5; + tcp_usec_ts:1, /* TSval values in usec */ + unused:4; u32 chrono_start; /* Start time in jiffies of a TCP chrono */ u32 chrono_stat[3]; /* Time in jiffies for chrono_stat stats */ u8 chrono_type:2, /* current chronograph type */ @@ -377,6 +397,14 @@ struct tcp_sock { * Total data bytes retransmitted */ u32 total_retrans; /* Total retransmits for entire connection */ + u32 rto_stamp; /* Start time (ms) of last CA_Loss recovery */ + u16 total_rto; /* Total number of RTO timeouts, including + * SYN/SYN-ACK and recurring timeouts. + */ + u16 total_rto_recoveries; /* Total number of RTO recoveries, + * including any unfinished recovery. + */ + u32 total_rto_time; /* ms spent in (completed) RTO recoveries. */ u32 urg_seq; /* Seq of received urgent pointer */ unsigned int keepalive_time; /* time before keep alive takes place */ @@ -437,13 +465,18 @@ struct tcp_sock { bool syn_smc; /* SYN includes SMC */ #endif -#ifdef CONFIG_TCP_MD5SIG -/* TCP AF-Specific parts; only used by MD5 Signature support so far */ +#if defined(CONFIG_TCP_MD5SIG) || defined(CONFIG_TCP_AO) +/* TCP AF-Specific parts; only used by TCP-AO/MD5 Signature support so far */ const struct tcp_sock_af_ops *af_specific; +#ifdef CONFIG_TCP_MD5SIG /* TCP MD5 Signature Option information */ struct tcp_md5sig_info __rcu *md5sig_info; #endif +#ifdef CONFIG_TCP_AO + struct tcp_ao_info __rcu *ao_info; +#endif +#endif /* TCP fastopen related information */ struct tcp_fastopen_request *fastopen_req; @@ -463,15 +496,17 @@ enum tsq_enum { TCP_MTU_REDUCED_DEFERRED, /* tcp_v{4|6}_err() could not call * tcp_v{4|6}_mtu_reduced() */ + TCP_ACK_DEFERRED, /* TX pure ack is deferred */ }; enum tsq_flags { - TSQF_THROTTLED = (1UL << TSQ_THROTTLED), - TSQF_QUEUED = (1UL << TSQ_QUEUED), - TCPF_TSQ_DEFERRED = (1UL << TCP_TSQ_DEFERRED), - TCPF_WRITE_TIMER_DEFERRED = (1UL << TCP_WRITE_TIMER_DEFERRED), - TCPF_DELACK_TIMER_DEFERRED = (1UL << TCP_DELACK_TIMER_DEFERRED), - TCPF_MTU_REDUCED_DEFERRED = (1UL << TCP_MTU_REDUCED_DEFERRED), + TSQF_THROTTLED = BIT(TSQ_THROTTLED), + TSQF_QUEUED = BIT(TSQ_QUEUED), + TCPF_TSQ_DEFERRED = BIT(TCP_TSQ_DEFERRED), + TCPF_WRITE_TIMER_DEFERRED = BIT(TCP_WRITE_TIMER_DEFERRED), + TCPF_DELACK_TIMER_DEFERRED = BIT(TCP_DELACK_TIMER_DEFERRED), + TCPF_MTU_REDUCED_DEFERRED = BIT(TCP_MTU_REDUCED_DEFERRED), + TCPF_ACK_DEFERRED = BIT(TCP_ACK_DEFERRED), }; #define tcp_sk(ptr) container_of_const(ptr, struct tcp_sock, inet_conn.icsk_inet.sk) @@ -497,6 +532,9 @@ struct tcp_timewait_sock { #ifdef CONFIG_TCP_MD5SIG struct tcp_md5sig_key *tw_md5_key; #endif +#ifdef CONFIG_TCP_AO + struct tcp_ao_info __rcu *ao_info; +#endif }; static inline struct tcp_timewait_sock *tcp_twsk(const struct sock *sk) @@ -566,4 +604,9 @@ void tcp_sock_set_quickack(struct sock *sk, int val); int tcp_sock_set_syncnt(struct sock *sk, int val); int tcp_sock_set_user_timeout(struct sock *sk, int val); +static inline bool dst_tcp_usec_ts(const struct dst_entry *dst) +{ + return dst_feature(dst, RTAX_FEATURE_TCP_USEC_TS); +} + #endif /* _LINUX_TCP_H */ diff --git a/include/linux/thermal.h b/include/linux/thermal.h index c99440aac1a1..cee814d5d1ac 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -80,8 +80,8 @@ struct thermal_zone_device_ops { int (*set_trip_hyst) (struct thermal_zone_device *, int, int); int (*get_crit_temp) (struct thermal_zone_device *, int *); int (*set_emul_temp) (struct thermal_zone_device *, int); - int (*get_trend) (struct thermal_zone_device *, struct thermal_trip *, - enum thermal_trend *); + int (*get_trend) (struct thermal_zone_device *, + const struct thermal_trip *, enum thermal_trend *); void (*hot)(struct thermal_zone_device *); void (*critical)(struct thermal_zone_device *); }; @@ -122,7 +122,6 @@ struct thermal_cooling_device { * @devdata: private pointer for device private data * @trips: an array of struct thermal_trip * @num_trips: number of trip points the thermal zone supports - * @trips_disabled; bitmap for disabled trips * @passive_delay_jiffies: number of jiffies to wait between polls when * performing passive cooling. * @polling_delay_jiffies: number of jiffies to wait between polls when @@ -163,7 +162,6 @@ struct thermal_zone_device { void *devdata; struct thermal_trip *trips; int num_trips; - unsigned long trips_disabled; /* bitmap for disabled trips */ unsigned long passive_delay_jiffies; unsigned long polling_delay_jiffies; int temperature; @@ -201,7 +199,8 @@ struct thermal_governor { char name[THERMAL_NAME_LENGTH]; int (*bind_to_tz)(struct thermal_zone_device *tz); void (*unbind_from_tz)(struct thermal_zone_device *tz); - int (*throttle)(struct thermal_zone_device *tz, int trip); + int (*throttle)(struct thermal_zone_device *tz, + const struct thermal_trip *trip); struct list_head governor_list; }; @@ -288,6 +287,9 @@ int thermal_zone_set_trip(struct thermal_zone_device *tz, int trip_id, int for_each_thermal_trip(struct thermal_zone_device *tz, int (*cb)(struct thermal_trip *, void *), void *data); +int thermal_zone_for_each_trip(struct thermal_zone_device *tz, + int (*cb)(struct thermal_trip *, void *), + void *data); int thermal_zone_get_num_trips(struct thermal_zone_device *tz); int thermal_zone_get_crit_temp(struct thermal_zone_device *tz, int *temp); @@ -322,18 +324,22 @@ const char *thermal_zone_device_type(struct thermal_zone_device *tzd); int thermal_zone_device_id(struct thermal_zone_device *tzd); struct device *thermal_zone_device(struct thermal_zone_device *tzd); +int thermal_bind_cdev_to_trip(struct thermal_zone_device *tz, + const struct thermal_trip *trip, + struct thermal_cooling_device *cdev, + unsigned long upper, unsigned long lower, + unsigned int weight); int thermal_zone_bind_cooling_device(struct thermal_zone_device *, int, struct thermal_cooling_device *, unsigned long, unsigned long, unsigned int); +int thermal_unbind_cdev_from_trip(struct thermal_zone_device *tz, + const struct thermal_trip *trip, + struct thermal_cooling_device *cdev); int thermal_zone_unbind_cooling_device(struct thermal_zone_device *, int, struct thermal_cooling_device *); void thermal_zone_device_update(struct thermal_zone_device *, enum thermal_notify_event); -void thermal_zone_device_exec(struct thermal_zone_device *tz, - void (*cb)(struct thermal_zone_device *, - unsigned long), - unsigned long data); struct thermal_cooling_device *thermal_cooling_device_register(const char *, void *, const struct thermal_cooling_device_ops *); diff --git a/include/linux/tick.h b/include/linux/tick.h index 9459fef5b857..716d17f31c45 100644 --- a/include/linux/tick.h +++ b/include/linux/tick.h @@ -140,14 +140,6 @@ extern unsigned long tick_nohz_get_idle_calls(void); extern unsigned long tick_nohz_get_idle_calls_cpu(int cpu); extern u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time); extern u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time); - -static inline void tick_nohz_idle_stop_tick_protected(void) -{ - local_irq_disable(); - tick_nohz_idle_stop_tick(); - local_irq_enable(); -} - #else /* !CONFIG_NO_HZ_COMMON */ #define tick_nohz_enabled (0) static inline int tick_nohz_tick_stopped(void) { return 0; } @@ -170,8 +162,6 @@ static inline ktime_t tick_nohz_get_sleep_length(ktime_t *delta_next) } static inline u64 get_cpu_idle_time_us(int cpu, u64 *unused) { return -1; } static inline u64 get_cpu_iowait_time_us(int cpu, u64 *unused) { return -1; } - -static inline void tick_nohz_idle_stop_tick_protected(void) { } #endif /* !CONFIG_NO_HZ_COMMON */ #ifdef CONFIG_NO_HZ_FULL diff --git a/include/linux/topology.h b/include/linux/topology.h index fea32377f7c7..52f5850730b3 100644 --- a/include/linux/topology.h +++ b/include/linux/topology.h @@ -251,7 +251,7 @@ extern const struct cpumask *sched_numa_hop_mask(unsigned int node, unsigned int #else static __always_inline int sched_numa_find_nth_cpu(const struct cpumask *cpus, int cpu, int node) { - return cpumask_nth(cpu, cpus); + return cpumask_nth_and(cpu, cpus, cpu_online_mask); } static inline const struct cpumask * diff --git a/include/linux/torture.h b/include/linux/torture.h index bb466eec01e4..c98d0c83d117 100644 --- a/include/linux/torture.h +++ b/include/linux/torture.h @@ -81,7 +81,8 @@ static inline void torture_random_init(struct torture_random_state *trsp) } /* Definitions for high-resolution-timer sleeps. */ -int torture_hrtimeout_ns(ktime_t baset_ns, u32 fuzzt_ns, struct torture_random_state *trsp); +int torture_hrtimeout_ns(ktime_t baset_ns, u32 fuzzt_ns, const enum hrtimer_mode mode, + struct torture_random_state *trsp); int torture_hrtimeout_us(u32 baset_us, u32 fuzzt_ns, struct torture_random_state *trsp); int torture_hrtimeout_ms(u32 baset_ms, u32 fuzzt_us, struct torture_random_state *trsp); int torture_hrtimeout_jiffies(u32 baset_j, struct torture_random_state *trsp); @@ -120,10 +121,15 @@ void _torture_stop_kthread(char *m, struct task_struct **tp); #define torture_stop_kthread(n, tp) \ _torture_stop_kthread("Stopping " #n " task", &(tp)) +/* Scheduler-related definitions. */ #ifdef CONFIG_PREEMPTION #define torture_preempt_schedule() __preempt_schedule() #else #define torture_preempt_schedule() do { } while (0) #endif +#if IS_ENABLED(CONFIG_RCU_TORTURE_TEST) || IS_MODULE(CONFIG_RCU_TORTURE_TEST) || IS_ENABLED(CONFIG_LOCK_TORTURE_TEST) || IS_MODULE(CONFIG_LOCK_TORTURE_TEST) +long torture_sched_setaffinity(pid_t pid, const struct cpumask *in_mask); +#endif + #endif /* __LINUX_TORTURE_H */ diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index eb5c3add939b..5eb88a66eb68 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -62,13 +62,13 @@ void trace_event_printf(struct trace_iterator *iter, const char *fmt, ...); /* Used to find the offset and length of dynamic fields in trace events */ struct trace_dynamic_info { #ifdef CONFIG_CPU_BIG_ENDIAN - u16 offset; u16 len; + u16 offset; #else - u16 len; u16 offset; + u16 len; #endif -}; +} __packed; /* * The trace entry - the most basic unit of tracing. This is what @@ -650,7 +650,6 @@ struct trace_event_file { struct trace_event_call *event_call; struct event_filter __rcu *filter; struct eventfs_file *ef; - struct dentry *dir; struct trace_array *tr; struct trace_subsystem_dir *system; struct list_head triggers; @@ -762,7 +761,8 @@ struct bpf_raw_event_map *bpf_get_raw_tracepoint(const char *name); void bpf_put_raw_tracepoint(struct bpf_raw_event_map *btp); int bpf_get_perf_event_info(const struct perf_event *event, u32 *prog_id, u32 *fd_type, const char **buf, - u64 *probe_offset, u64 *probe_addr); + u64 *probe_offset, u64 *probe_addr, + unsigned long *missed); int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *prog); int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *prog); #else @@ -802,7 +802,7 @@ static inline void bpf_put_raw_tracepoint(struct bpf_raw_event_map *btp) static inline int bpf_get_perf_event_info(const struct perf_event *event, u32 *prog_id, u32 *fd_type, const char **buf, u64 *probe_offset, - u64 *probe_addr) + u64 *probe_addr, unsigned long *missed) { return -EOPNOTSUPP; } @@ -878,6 +878,7 @@ extern void perf_kprobe_destroy(struct perf_event *event); extern int bpf_get_kprobe_info(const struct perf_event *event, u32 *fd_type, const char **symbol, u64 *probe_offset, u64 *probe_addr, + unsigned long *missed, bool perf_type_tracepoint); #endif #ifdef CONFIG_UPROBE_EVENTS diff --git a/include/linux/udp.h b/include/linux/udp.h index 43c1fb2d2c21..d04188714dca 100644 --- a/include/linux/udp.h +++ b/include/linux/udp.h @@ -32,25 +32,30 @@ static inline u32 udp_hashfn(const struct net *net, u32 num, u32 mask) return (num + net_hash_mix(net)) & mask; } +enum { + UDP_FLAGS_CORK, /* Cork is required */ + UDP_FLAGS_NO_CHECK6_TX, /* Send zero UDP6 checksums on TX? */ + UDP_FLAGS_NO_CHECK6_RX, /* Allow zero UDP6 checksums on RX? */ + UDP_FLAGS_GRO_ENABLED, /* Request GRO aggregation */ + UDP_FLAGS_ACCEPT_FRAGLIST, + UDP_FLAGS_ACCEPT_L4, + UDP_FLAGS_ENCAP_ENABLED, /* This socket enabled encap */ + UDP_FLAGS_UDPLITE_SEND_CC, /* set via udplite setsockopt */ + UDP_FLAGS_UDPLITE_RECV_CC, /* set via udplite setsockopt */ +}; + struct udp_sock { /* inet_sock has to be the first member */ struct inet_sock inet; #define udp_port_hash inet.sk.__sk_common.skc_u16hashes[0] #define udp_portaddr_hash inet.sk.__sk_common.skc_u16hashes[1] #define udp_portaddr_node inet.sk.__sk_common.skc_portaddr_node + + unsigned long udp_flags; + int pending; /* Any pending frames ? */ - unsigned int corkflag; /* Cork is required */ __u8 encap_type; /* Is this an Encapsulation socket? */ - unsigned char no_check6_tx:1,/* Send zero UDP6 checksums on TX? */ - no_check6_rx:1,/* Allow zero UDP6 checksums on RX? */ - encap_enabled:1, /* This socket enabled encap - * processing; UDP tunnels and - * different encapsulation layer set - * this - */ - gro_enabled:1, /* Request GRO aggregation */ - accept_udp_l4:1, - accept_udp_fraglist:1; + /* * Following member retains the information to create a UDP header * when the socket is uncorked. @@ -62,12 +67,6 @@ struct udp_sock { */ __u16 pcslen; __u16 pcrlen; -/* indicator bits used by pcflag: */ -#define UDPLITE_BIT 0x1 /* set by udplite proto init function */ -#define UDPLITE_SEND_CC 0x2 /* set via udplite setsockopt */ -#define UDPLITE_RECV_CC 0x4 /* set via udplite setsocktopt */ - __u8 pcflag; /* marks socket as UDP-Lite if > 0 */ - __u8 unused[3]; /* * For encapsulation sockets. */ @@ -95,28 +94,39 @@ struct udp_sock { int forward_threshold; }; +#define udp_test_bit(nr, sk) \ + test_bit(UDP_FLAGS_##nr, &udp_sk(sk)->udp_flags) +#define udp_set_bit(nr, sk) \ + set_bit(UDP_FLAGS_##nr, &udp_sk(sk)->udp_flags) +#define udp_test_and_set_bit(nr, sk) \ + test_and_set_bit(UDP_FLAGS_##nr, &udp_sk(sk)->udp_flags) +#define udp_clear_bit(nr, sk) \ + clear_bit(UDP_FLAGS_##nr, &udp_sk(sk)->udp_flags) +#define udp_assign_bit(nr, sk, val) \ + assign_bit(UDP_FLAGS_##nr, &udp_sk(sk)->udp_flags, val) + #define UDP_MAX_SEGMENTS (1 << 6UL) #define udp_sk(ptr) container_of_const(ptr, struct udp_sock, inet.sk) static inline void udp_set_no_check6_tx(struct sock *sk, bool val) { - udp_sk(sk)->no_check6_tx = val; + udp_assign_bit(NO_CHECK6_TX, sk, val); } static inline void udp_set_no_check6_rx(struct sock *sk, bool val) { - udp_sk(sk)->no_check6_rx = val; + udp_assign_bit(NO_CHECK6_RX, sk, val); } -static inline bool udp_get_no_check6_tx(struct sock *sk) +static inline bool udp_get_no_check6_tx(const struct sock *sk) { - return udp_sk(sk)->no_check6_tx; + return udp_test_bit(NO_CHECK6_TX, sk); } -static inline bool udp_get_no_check6_rx(struct sock *sk) +static inline bool udp_get_no_check6_rx(const struct sock *sk) { - return udp_sk(sk)->no_check6_rx; + return udp_test_bit(NO_CHECK6_RX, sk); } static inline void udp_cmsg_recv(struct msghdr *msg, struct sock *sk, @@ -135,10 +145,12 @@ static inline bool udp_unexpected_gso(struct sock *sk, struct sk_buff *skb) if (!skb_is_gso(skb)) return false; - if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4 && !udp_sk(sk)->accept_udp_l4) + if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4 && + !udp_test_bit(ACCEPT_L4, sk)) return true; - if (skb_shinfo(skb)->gso_type & SKB_GSO_FRAGLIST && !udp_sk(sk)->accept_udp_fraglist) + if (skb_shinfo(skb)->gso_type & SKB_GSO_FRAGLIST && + !udp_test_bit(ACCEPT_FRAGLIST, sk)) return true; return false; @@ -146,8 +158,8 @@ static inline bool udp_unexpected_gso(struct sock *sk, struct sk_buff *skb) static inline void udp_allow_gso(struct sock *sk) { - udp_sk(sk)->accept_udp_l4 = 1; - udp_sk(sk)->accept_udp_fraglist = 1; + udp_set_bit(ACCEPT_L4, sk); + udp_set_bit(ACCEPT_FRAGLIST, sk); } #define udp_portaddr_for_each_entry(__sk, list) \ diff --git a/include/linux/uio.h b/include/linux/uio.h index 42bce38a8e87..b6214cbf2a43 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -21,12 +21,12 @@ struct kvec { enum iter_type { /* iter types */ + ITER_UBUF, ITER_IOVEC, - ITER_KVEC, ITER_BVEC, + ITER_KVEC, ITER_XARRAY, ITER_DISCARD, - ITER_UBUF, }; #define ITER_SOURCE 1 // == WRITE @@ -43,11 +43,7 @@ struct iov_iter { bool copy_mc; bool nofault; bool data_source; - bool user_backed; - union { - size_t iov_offset; - int last_offset; - }; + size_t iov_offset; /* * Hack alert: overlay ubuf_iovec with iovec + count, so * that the members resolve correctly regardless of the type @@ -143,7 +139,7 @@ static inline unsigned char iov_iter_rw(const struct iov_iter *i) static inline bool user_backed_iter(const struct iov_iter *i) { - return i->user_backed; + return iter_is_ubuf(i) || iter_is_iovec(i); } /* @@ -342,27 +338,6 @@ iov_iter_npages_cap(struct iov_iter *i, int maxpages, size_t max_bytes) return npages; } -struct csum_state { - __wsum csum; - size_t off; -}; - -size_t csum_and_copy_to_iter(const void *addr, size_t bytes, void *csstate, struct iov_iter *i); -size_t csum_and_copy_from_iter(void *addr, size_t bytes, __wsum *csum, struct iov_iter *i); - -static __always_inline __must_check -bool csum_and_copy_from_iter_full(void *addr, size_t bytes, - __wsum *csum, struct iov_iter *i) -{ - size_t copied = csum_and_copy_from_iter(addr, bytes, csum, i); - if (likely(copied == bytes)) - return true; - iov_iter_revert(i, copied); - return false; -} -size_t hash_and_copy_to_iter(const void *addr, size_t bytes, void *hashp, - struct iov_iter *i); - struct iovec *iovec_from_user(const struct iovec __user *uvector, unsigned long nr_segs, unsigned long fast_segs, struct iovec *fast_iov, bool compat); @@ -383,7 +358,6 @@ static inline void iov_iter_ubuf(struct iov_iter *i, unsigned int direction, *i = (struct iov_iter) { .iter_type = ITER_UBUF, .copy_mc = false, - .user_backed = true, .data_source = direction, .ubuf = buf, .count = count, diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h index 45f09bec02c4..6030a8235617 100644 --- a/include/linux/user_namespace.h +++ b/include/linux/user_namespace.h @@ -65,6 +65,10 @@ enum rlimit_type { UCOUNT_RLIMIT_COUNTS, }; +#if IS_ENABLED(CONFIG_BINFMT_MISC) +struct binfmt_misc; +#endif + struct user_namespace { struct uid_gid_map uid_map; struct uid_gid_map gid_map; @@ -102,6 +106,10 @@ struct user_namespace { struct ucounts *ucounts; long ucount_max[UCOUNT_COUNTS]; long rlimit_max[UCOUNT_RLIMIT_COUNTS]; + +#if IS_ENABLED(CONFIG_BINFMT_MISC) + struct binfmt_misc *binfmt_misc; +#endif } __randomize_layout; struct ucounts { diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h index 7b4dd69555e4..27cc1d464321 100644 --- a/include/linux/virtio_net.h +++ b/include/linux/virtio_net.h @@ -3,8 +3,8 @@ #define _LINUX_VIRTIO_NET_H #include <linux/if_vlan.h> +#include <linux/udp.h> #include <uapi/linux/tcp.h> -#include <uapi/linux/udp.h> #include <uapi/linux/virtio_net.h> static inline bool virtio_net_hdr_match_proto(__be16 protocol, __u8 gso_type) @@ -151,9 +151,22 @@ retry: unsigned int nh_off = p_off; struct skb_shared_info *shinfo = skb_shinfo(skb); - /* UFO may not include transport header in gso_size. */ - if (gso_type & SKB_GSO_UDP) + switch (gso_type & ~SKB_GSO_TCP_ECN) { + case SKB_GSO_UDP: + /* UFO may not include transport header in gso_size. */ nh_off -= thlen; + break; + case SKB_GSO_UDP_L4: + if (!(hdr->flags & VIRTIO_NET_HDR_F_NEEDS_CSUM)) + return -EINVAL; + if (skb->csum_offset != offsetof(struct udphdr, check)) + return -EINVAL; + if (skb->len - p_off > gso_size * UDP_MAX_SEGMENTS) + return -EINVAL; + if (gso_type != SKB_GSO_UDP_L4) + return -EINVAL; + break; + } /* Kernel has a special handling for GSO_BY_FRAGS. */ if (gso_size == GSO_BY_FRAGS) diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h index c58453699ee9..ebb3ce63d64d 100644 --- a/include/linux/virtio_vsock.h +++ b/include/linux/virtio_vsock.h @@ -12,6 +12,7 @@ struct virtio_vsock_skb_cb { bool reply; bool tap_delivered; + u32 offset; }; #define VIRTIO_VSOCK_SKB_CB(skb) ((struct virtio_vsock_skb_cb *)((skb)->cb)) @@ -159,6 +160,15 @@ struct virtio_transport { /* Takes ownership of the packet */ int (*send_pkt)(struct sk_buff *skb); + + /* Used in MSG_ZEROCOPY mode. Checks, that provided data + * (number of buffers) could be transmitted with zerocopy + * mode. If this callback is not implemented for the current + * transport - this means that this transport doesn't need + * extra checks and can perform zerocopy transmission by + * default. + */ + bool (*can_msgzerocopy)(int bufs_num); }; ssize_t diff --git a/include/linux/watch_queue.h b/include/linux/watch_queue.h index 45cd42f55d49..429c7b6afead 100644 --- a/include/linux/watch_queue.h +++ b/include/linux/watch_queue.h @@ -32,7 +32,7 @@ struct watch_filter { DECLARE_BITMAP(type_filter, WATCH_TYPE__NR); }; u32 nr_filters; /* Number of filters */ - struct watch_type_filter filters[]; + struct watch_type_filter filters[] __counted_by(nr_filters); }; struct watch_queue { diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 1c1d06804d45..24b1e5070f4d 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -274,18 +274,16 @@ static inline unsigned int work_static(struct work_struct *work) { return 0; } * to generate better code. */ #ifdef CONFIG_LOCKDEP -#define __INIT_WORK(_work, _func, _onstack) \ +#define __INIT_WORK_KEY(_work, _func, _onstack, _key) \ do { \ - static struct lock_class_key __key; \ - \ __init_work((_work), _onstack); \ (_work)->data = (atomic_long_t) WORK_DATA_INIT(); \ - lockdep_init_map(&(_work)->lockdep_map, "(work_completion)"#_work, &__key, 0); \ + lockdep_init_map(&(_work)->lockdep_map, "(work_completion)"#_work, (_key), 0); \ INIT_LIST_HEAD(&(_work)->entry); \ (_work)->func = (_func); \ } while (0) #else -#define __INIT_WORK(_work, _func, _onstack) \ +#define __INIT_WORK_KEY(_work, _func, _onstack, _key) \ do { \ __init_work((_work), _onstack); \ (_work)->data = (atomic_long_t) WORK_DATA_INIT(); \ @@ -294,12 +292,22 @@ static inline unsigned int work_static(struct work_struct *work) { return 0; } } while (0) #endif +#define __INIT_WORK(_work, _func, _onstack) \ + do { \ + static __maybe_unused struct lock_class_key __key; \ + \ + __INIT_WORK_KEY(_work, _func, _onstack, &__key); \ + } while (0) + #define INIT_WORK(_work, _func) \ __INIT_WORK((_work), (_func), 0) #define INIT_WORK_ONSTACK(_work, _func) \ __INIT_WORK((_work), (_func), 1) +#define INIT_WORK_ONSTACK_KEY(_work, _func, _key) \ + __INIT_WORK_KEY((_work), (_func), 1, _key) + #define __INIT_DELAYED_WORK(_work, _func, _tflags) \ do { \ INIT_WORK(&(_work)->work, (_func)); \ @@ -693,8 +701,32 @@ static inline long work_on_cpu_safe(int cpu, long (*fn)(void *), void *arg) return fn(arg); } #else -long work_on_cpu(int cpu, long (*fn)(void *), void *arg); -long work_on_cpu_safe(int cpu, long (*fn)(void *), void *arg); +long work_on_cpu_key(int cpu, long (*fn)(void *), + void *arg, struct lock_class_key *key); +/* + * A new key is defined for each caller to make sure the work + * associated with the function doesn't share its locking class. + */ +#define work_on_cpu(_cpu, _fn, _arg) \ +({ \ + static struct lock_class_key __key; \ + \ + work_on_cpu_key(_cpu, _fn, _arg, &__key); \ +}) + +long work_on_cpu_safe_key(int cpu, long (*fn)(void *), + void *arg, struct lock_class_key *key); + +/* + * A new key is defined for each caller to make sure the work + * associated with the function doesn't share its locking class. + */ +#define work_on_cpu_safe(_cpu, _fn, _arg) \ +({ \ + static struct lock_class_key __key; \ + \ + work_on_cpu_safe_key(_cpu, _fn, _arg, &__key); \ +}) #endif /* CONFIG_SMP */ #ifdef CONFIG_FREEZER |