From 5d5de3a431d87ac51d43da8d796891d014975ab7 Mon Sep 17 00:00:00 2001 From: Hou Tao Date: Thu, 16 Feb 2023 10:48:21 +0800 Subject: bpf: Only allocate one bpf_mem_cache for bpf_cpumask_ma The size of bpf_cpumask is fixed, so there is no need to allocate many bpf_mem_caches for bpf_cpumask_ma, just one bpf_mem_cache is enough. Also add comments for bpf_mem_alloc_init() in bpf_mem_alloc.h to prevent future miuse. Signed-off-by: Hou Tao Acked-by: Jiri Olsa Link: https://lore.kernel.org/r/20230216024821.2202916-1-houtao@huaweicloud.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf_mem_alloc.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf_mem_alloc.h b/include/linux/bpf_mem_alloc.h index 3e164b8efaa9..a7104af61ab4 100644 --- a/include/linux/bpf_mem_alloc.h +++ b/include/linux/bpf_mem_alloc.h @@ -14,6 +14,13 @@ struct bpf_mem_alloc { struct work_struct work; }; +/* 'size != 0' is for bpf_mem_alloc which manages fixed-size objects. + * Alloc and free are done with bpf_mem_cache_{alloc,free}(). + * + * 'size = 0' is for bpf_mem_alloc which manages many fixed-size objects. + * Alloc and free are done with bpf_mem_{alloc,free}() and the size of + * the returned object is given by the size argument of bpf_mem_alloc(). + */ int bpf_mem_alloc_init(struct bpf_mem_alloc *ma, int size, bool percpu); void bpf_mem_alloc_destroy(struct bpf_mem_alloc *ma); -- cgit v1.2.3 From d5f7638eb5fed0eb12e45a127764c4111b11c50e Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Mon, 24 Oct 2022 05:34:14 -0700 Subject: Input: matrix_keypad - replace header inclusions by forward declarations When the data structure is only referred by pointer, compiler may not need to see the contents of the data type. Thus, we may replace header inclusions by respective forward declarations. Signed-off-by: Andy Shevchenko Link: https://lore.kernel.org/r/20220923184632.2157-2-andriy.shevchenko@linux.intel.com Signed-off-by: Dmitry Torokhov --- include/linux/input/matrix_keypad.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/input/matrix_keypad.h b/include/linux/input/matrix_keypad.h index 9476768c3b90..b8d8d69eba29 100644 --- a/include/linux/input/matrix_keypad.h +++ b/include/linux/input/matrix_keypad.h @@ -3,8 +3,9 @@ #define _MATRIX_KEYPAD_H #include -#include -#include + +struct device; +struct input_dev; #define MATRIX_MAX_ROWS 32 #define MATRIX_MAX_COLS 32 -- cgit v1.2.3 From 7e0dac2807e6c4ae8c56941d74971fdb0763b4f9 Mon Sep 17 00:00:00 2001 From: Joanne Koong Date: Wed, 1 Mar 2023 07:49:45 -0800 Subject: bpf: Refactor process_dynptr_func This change cleans up process_dynptr_func's flow to be more intuitive and updates some comments with more context. Signed-off-by: Joanne Koong Link: https://lore.kernel.org/r/20230301154953.641654-3-joannelkoong@gmail.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf_verifier.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index cf1bb1cf4a7b..b26ff2a8f63b 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -616,9 +616,6 @@ int check_func_arg_reg_off(struct bpf_verifier_env *env, enum bpf_arg_type arg_type); int check_mem_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg, u32 regno, u32 mem_size); -struct bpf_call_arg_meta; -int process_dynptr_func(struct bpf_verifier_env *env, int regno, - enum bpf_arg_type arg_type, struct bpf_call_arg_meta *meta); /* this lives here instead of in bpf.h because it needs to dereference tgt_prog */ static inline u64 bpf_trampoline_compute_key(const struct bpf_prog *tgt_prog, -- cgit v1.2.3 From 8357b366cbb09b17c90e2cd758360a6bd2ea7507 Mon Sep 17 00:00:00 2001 From: Joanne Koong Date: Wed, 1 Mar 2023 07:49:47 -0800 Subject: bpf: Define no-ops for externally called bpf dynptr functions Some bpf dynptr functions will be called from places where if CONFIG_BPF_SYSCALL is not set, then the dynptr function is undefined. For example, when skb type dynptrs are added in the next commit, dynptr functions are called from net/core/filter.c This patch defines no-op implementations of these dynptr functions so that they do not break compilation by being an undefined reference. Signed-off-by: Joanne Koong Link: https://lore.kernel.org/r/20230301154953.641654-5-joannelkoong@gmail.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 75 ++++++++++++++++++++++++++++++++--------------------- 1 file changed, 45 insertions(+), 30 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 520b238abd5a..296841a31749 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1124,6 +1124,33 @@ static __always_inline __nocfi unsigned int bpf_dispatcher_nop_func( return bpf_func(ctx, insnsi); } +/* the implementation of the opaque uapi struct bpf_dynptr */ +struct bpf_dynptr_kern { + void *data; + /* Size represents the number of usable bytes of dynptr data. + * If for example the offset is at 4 for a local dynptr whose data is + * of type u64, the number of usable bytes is 4. + * + * The upper 8 bits are reserved. It is as follows: + * Bits 0 - 23 = size + * Bits 24 - 30 = dynptr type + * Bit 31 = whether dynptr is read-only + */ + u32 size; + u32 offset; +} __aligned(8); + +enum bpf_dynptr_type { + BPF_DYNPTR_TYPE_INVALID, + /* Points to memory that is local to the bpf program */ + BPF_DYNPTR_TYPE_LOCAL, + /* Underlying data is a ringbuf record */ + BPF_DYNPTR_TYPE_RINGBUF, +}; + +int bpf_dynptr_check_size(u32 size); +u32 bpf_dynptr_get_size(const struct bpf_dynptr_kern *ptr); + #ifdef CONFIG_BPF_JIT int bpf_trampoline_link_prog(struct bpf_tramp_link *link, struct bpf_trampoline *tr); int bpf_trampoline_unlink_prog(struct bpf_tramp_link *link, struct bpf_trampoline *tr); @@ -2266,6 +2293,11 @@ static inline bool has_current_bpf_ctx(void) } void notrace bpf_prog_inc_misses_counter(struct bpf_prog *prog); + +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); #else /* !CONFIG_BPF_SYSCALL */ static inline struct bpf_prog *bpf_prog_get(u32 ufd) { @@ -2495,6 +2527,19 @@ static inline void bpf_prog_inc_misses_counter(struct bpf_prog *prog) static inline void bpf_cgrp_storage_free(struct cgroup *cgroup) { } + +static inline void bpf_dynptr_init(struct bpf_dynptr_kern *ptr, void *data, + enum bpf_dynptr_type type, u32 offset, u32 size) +{ +} + +static inline void bpf_dynptr_set_null(struct bpf_dynptr_kern *ptr) +{ +} + +static inline void bpf_dynptr_set_rdonly(struct bpf_dynptr_kern *ptr) +{ +} #endif /* CONFIG_BPF_SYSCALL */ void __bpf_free_used_btfs(struct bpf_prog_aux *aux, @@ -2913,36 +2958,6 @@ int bpf_bprintf_prepare(char *fmt, u32 fmt_size, const u64 *raw_args, u32 num_args, struct bpf_bprintf_data *data); void bpf_bprintf_cleanup(struct bpf_bprintf_data *data); -/* the implementation of the opaque uapi struct bpf_dynptr */ -struct bpf_dynptr_kern { - void *data; - /* Size represents the number of usable bytes of dynptr data. - * If for example the offset is at 4 for a local dynptr whose data is - * of type u64, the number of usable bytes is 4. - * - * The upper 8 bits are reserved. It is as follows: - * Bits 0 - 23 = size - * Bits 24 - 30 = dynptr type - * Bit 31 = whether dynptr is read-only - */ - u32 size; - u32 offset; -} __aligned(8); - -enum bpf_dynptr_type { - BPF_DYNPTR_TYPE_INVALID, - /* Points to memory that is local to the bpf program */ - BPF_DYNPTR_TYPE_LOCAL, - /* Underlying data is a kernel-produced ringbuf record */ - BPF_DYNPTR_TYPE_RINGBUF, -}; - -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); -int bpf_dynptr_check_size(u32 size); -u32 bpf_dynptr_get_size(const struct bpf_dynptr_kern *ptr); - #ifdef CONFIG_BPF_LSM void bpf_cgroup_atype_get(u32 attach_btf_id, int cgroup_atype); void bpf_cgroup_atype_put(int cgroup_atype); -- cgit v1.2.3 From b5964b968ac64c2ec2debee7518499113b27c34e Mon Sep 17 00:00:00 2001 From: Joanne Koong Date: Wed, 1 Mar 2023 07:49:50 -0800 Subject: bpf: Add skb dynptrs Add skb dynptrs, which are dynptrs whose underlying pointer points to a skb. The dynptr acts on skb data. skb dynptrs have two main benefits. One is that they allow operations on sizes that are not statically known at compile-time (eg variable-sized accesses). Another is that parsing the packet data through dynptrs (instead of through direct access of skb->data and skb->data_end) can be more ergonomic and less brittle (eg does not need manual if checking for being within bounds of data_end). For bpf prog types that don't support writes on skb data, the dynptr is read-only (bpf_dynptr_write() will return an error) For reads and writes through the bpf_dynptr_read() and bpf_dynptr_write() interfaces, reading and writing from/to data in the head as well as from/to non-linear paged buffers is supported. Data slices through the bpf_dynptr_data API are not supported; instead bpf_dynptr_slice() and bpf_dynptr_slice_rdwr() (added in subsequent commit) should be used. For examples of how skb dynptrs can be used, please see the attached selftests. Signed-off-by: Joanne Koong Link: https://lore.kernel.org/r/20230301154953.641654-8-joannelkoong@gmail.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 14 +++++++++++++- include/linux/filter.h | 18 ++++++++++++++++++ 2 files changed, 31 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 296841a31749..e7436d7615b0 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -607,11 +607,14 @@ enum bpf_type_flag { */ NON_OWN_REF = BIT(14 + BPF_BASE_TYPE_BITS), + /* DYNPTR points to sk_buff */ + DYNPTR_TYPE_SKB = BIT(15 + BPF_BASE_TYPE_BITS), + __BPF_TYPE_FLAG_MAX, __BPF_TYPE_LAST_FLAG = __BPF_TYPE_FLAG_MAX - 1, }; -#define DYNPTR_TYPE_FLAG_MASK (DYNPTR_TYPE_LOCAL | DYNPTR_TYPE_RINGBUF) +#define DYNPTR_TYPE_FLAG_MASK (DYNPTR_TYPE_LOCAL | DYNPTR_TYPE_RINGBUF | DYNPTR_TYPE_SKB) /* Max number of base types. */ #define BPF_BASE_TYPE_LIMIT (1UL << BPF_BASE_TYPE_BITS) @@ -1146,6 +1149,8 @@ enum bpf_dynptr_type { BPF_DYNPTR_TYPE_LOCAL, /* Underlying data is a ringbuf record */ BPF_DYNPTR_TYPE_RINGBUF, + /* Underlying data is a sk_buff */ + BPF_DYNPTR_TYPE_SKB, }; int bpf_dynptr_check_size(u32 size); @@ -2846,6 +2851,8 @@ u32 bpf_sock_convert_ctx_access(enum bpf_access_type type, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size); +int bpf_dynptr_from_skb_rdonly(struct sk_buff *skb, u64 flags, + struct bpf_dynptr_kern *ptr); #else static inline bool bpf_sock_common_is_valid_access(int off, int size, enum bpf_access_type type, @@ -2867,6 +2874,11 @@ static inline u32 bpf_sock_convert_ctx_access(enum bpf_access_type type, { return 0; } +static inline int bpf_dynptr_from_skb_rdonly(struct sk_buff *skb, u64 flags, + struct bpf_dynptr_kern *ptr) +{ + return -EOPNOTSUPP; +} #endif #ifdef CONFIG_INET diff --git a/include/linux/filter.h b/include/linux/filter.h index 1727898f1641..de18e844d15e 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -1542,4 +1542,22 @@ static __always_inline int __bpf_xdp_redirect_map(struct bpf_map *map, u64 index return XDP_REDIRECT; } +#ifdef CONFIG_NET +int __bpf_skb_load_bytes(const struct sk_buff *skb, u32 offset, void *to, u32 len); +int __bpf_skb_store_bytes(struct sk_buff *skb, u32 offset, const void *from, + u32 len, u64 flags); +#else /* CONFIG_NET */ +static inline int __bpf_skb_load_bytes(const struct sk_buff *skb, u32 offset, + void *to, u32 len) +{ + return -EOPNOTSUPP; +} + +static inline int __bpf_skb_store_bytes(struct sk_buff *skb, u32 offset, + const void *from, u32 len, u64 flags) +{ + return -EOPNOTSUPP; +} +#endif /* CONFIG_NET */ + #endif /* __LINUX_FILTER_H__ */ -- cgit v1.2.3 From 05421aecd4ed65da0dc17b0c3c13779ef334e9e5 Mon Sep 17 00:00:00 2001 From: Joanne Koong Date: Wed, 1 Mar 2023 07:49:51 -0800 Subject: bpf: Add xdp dynptrs Add xdp dynptrs, which are dynptrs whose underlying pointer points to a xdp_buff. The dynptr acts on xdp data. xdp dynptrs have two main benefits. One is that they allow operations on sizes that are not statically known at compile-time (eg variable-sized accesses). Another is that parsing the packet data through dynptrs (instead of through direct access of xdp->data and xdp->data_end) can be more ergonomic and less brittle (eg does not need manual if checking for being within bounds of data_end). For reads and writes on the dynptr, this includes reading/writing from/to and across fragments. Data slices through the bpf_dynptr_data API are not supported; instead bpf_dynptr_slice() and bpf_dynptr_slice_rdwr() should be used. For examples of how xdp dynptrs can be used, please see the attached selftests. Signed-off-by: Joanne Koong Link: https://lore.kernel.org/r/20230301154953.641654-9-joannelkoong@gmail.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 8 +++++++- include/linux/filter.h | 14 ++++++++++++++ 2 files changed, 21 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index e7436d7615b0..23ec684e660d 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -610,11 +610,15 @@ enum bpf_type_flag { /* DYNPTR points to sk_buff */ DYNPTR_TYPE_SKB = BIT(15 + BPF_BASE_TYPE_BITS), + /* DYNPTR points to xdp_buff */ + DYNPTR_TYPE_XDP = BIT(16 + BPF_BASE_TYPE_BITS), + __BPF_TYPE_FLAG_MAX, __BPF_TYPE_LAST_FLAG = __BPF_TYPE_FLAG_MAX - 1, }; -#define DYNPTR_TYPE_FLAG_MASK (DYNPTR_TYPE_LOCAL | DYNPTR_TYPE_RINGBUF | DYNPTR_TYPE_SKB) +#define DYNPTR_TYPE_FLAG_MASK (DYNPTR_TYPE_LOCAL | DYNPTR_TYPE_RINGBUF | DYNPTR_TYPE_SKB \ + | DYNPTR_TYPE_XDP) /* Max number of base types. */ #define BPF_BASE_TYPE_LIMIT (1UL << BPF_BASE_TYPE_BITS) @@ -1151,6 +1155,8 @@ enum bpf_dynptr_type { BPF_DYNPTR_TYPE_RINGBUF, /* Underlying data is a sk_buff */ BPF_DYNPTR_TYPE_SKB, + /* Underlying data is a xdp_buff */ + BPF_DYNPTR_TYPE_XDP, }; int bpf_dynptr_check_size(u32 size); diff --git a/include/linux/filter.h b/include/linux/filter.h index de18e844d15e..3f6992261ec5 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -1546,6 +1546,8 @@ static __always_inline int __bpf_xdp_redirect_map(struct bpf_map *map, u64 index int __bpf_skb_load_bytes(const struct sk_buff *skb, u32 offset, void *to, u32 len); int __bpf_skb_store_bytes(struct sk_buff *skb, u32 offset, const void *from, u32 len, u64 flags); +int __bpf_xdp_load_bytes(struct xdp_buff *xdp, u32 offset, void *buf, u32 len); +int __bpf_xdp_store_bytes(struct xdp_buff *xdp, u32 offset, void *buf, u32 len); #else /* CONFIG_NET */ static inline int __bpf_skb_load_bytes(const struct sk_buff *skb, u32 offset, void *to, u32 len) @@ -1558,6 +1560,18 @@ static inline int __bpf_skb_store_bytes(struct sk_buff *skb, u32 offset, { return -EOPNOTSUPP; } + +static inline int __bpf_xdp_load_bytes(struct xdp_buff *xdp, u32 offset, + void *buf, u32 len) +{ + return -EOPNOTSUPP; +} + +static inline int __bpf_xdp_store_bytes(struct xdp_buff *xdp, u32 offset, + void *buf, u32 len) +{ + return -EOPNOTSUPP; +} #endif /* CONFIG_NET */ #endif /* __LINUX_FILTER_H__ */ -- cgit v1.2.3 From 66e3a13e7c2c44d0c9dd6bb244680ca7529a8845 Mon Sep 17 00:00:00 2001 From: Joanne Koong Date: Wed, 1 Mar 2023 07:49:52 -0800 Subject: bpf: Add bpf_dynptr_slice and bpf_dynptr_slice_rdwr Two new kfuncs are added, bpf_dynptr_slice and bpf_dynptr_slice_rdwr. The user must pass in a buffer to store the contents of the data slice if a direct pointer to the data cannot be obtained. For skb and xdp type dynptrs, these two APIs are the only way to obtain a data slice. However, for other types of dynptrs, there is no difference between bpf_dynptr_slice(_rdwr) and bpf_dynptr_data. For skb type dynptrs, the data is copied into the user provided buffer if any of the data is not in the linear portion of the skb. For xdp type dynptrs, the data is copied into the user provided buffer if the data is between xdp frags. If the skb is cloned and a call to bpf_dynptr_data_rdwr is made, then the skb will be uncloned (see bpf_unclone_prologue()). Please note that any bpf_dynptr_write() automatically invalidates any prior data slices of the skb dynptr. This is because the skb may be cloned or may need to pull its paged buffer into the head. As such, any bpf_dynptr_write() will automatically have its prior data slices invalidated, even if the write is to data in the skb head of an uncloned skb. Please note as well that any other helper calls that change the underlying packet buffer (eg bpf_skb_pull_data()) invalidates any data slices of the skb dynptr as well, for the same reasons. Signed-off-by: Joanne Koong Link: https://lore.kernel.org/r/20230301154953.641654-10-joannelkoong@gmail.com Signed-off-by: Alexei Starovoitov --- include/linux/filter.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index 3f6992261ec5..efa5d4a1677e 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -1548,6 +1548,9 @@ int __bpf_skb_store_bytes(struct sk_buff *skb, u32 offset, const void *from, u32 len, u64 flags); int __bpf_xdp_load_bytes(struct xdp_buff *xdp, u32 offset, void *buf, u32 len); int __bpf_xdp_store_bytes(struct xdp_buff *xdp, u32 offset, void *buf, u32 len); +void *bpf_xdp_pointer(struct xdp_buff *xdp, u32 offset, u32 len); +void bpf_xdp_copy_buf(struct xdp_buff *xdp, unsigned long off, + void *buf, unsigned long len, bool flush); #else /* CONFIG_NET */ static inline int __bpf_skb_load_bytes(const struct sk_buff *skb, u32 offset, void *to, u32 len) @@ -1572,6 +1575,17 @@ static inline int __bpf_xdp_store_bytes(struct xdp_buff *xdp, u32 offset, { return -EOPNOTSUPP; } + +static inline void *bpf_xdp_pointer(struct xdp_buff *xdp, u32 offset, u32 len) +{ + return NULL; +} + +static inline void *bpf_xdp_copy_buf(struct xdp_buff *xdp, unsigned long off, void *buf, + unsigned long len, bool flush) +{ + return NULL; +} #endif /* CONFIG_NET */ #endif /* __LINUX_FILTER_H__ */ -- cgit v1.2.3 From 9db44fdd8105da00669d425acab887c668df75f6 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Sat, 25 Feb 2023 16:40:09 +0100 Subject: bpf: Support kptrs in local storage maps Enable support for kptrs in local storage maps by wiring up the freeing of these kptrs from map value. Freeing of bpf_local_storage_map is only delayed in case there are special fields, therefore bpf_selem_free_* path can also only dereference smap safely in that case. This is recorded using a bool utilizing a hole in bpF_local_storage_elem. It could have been tagged in the pointer value smap using the lowest bit (since alignment > 1), but since there was already a hole I went with the simpler option. Only the map structure freeing is delayed using RCU barriers, as the buckets aren't used when selem is being freed, so they can be freed once all readers of the bucket lists can no longer access it. Cc: Martin KaFai Lau Cc: KP Singh Cc: Paul E. McKenney Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20230225154010.391965-3-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf_local_storage.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf_local_storage.h b/include/linux/bpf_local_storage.h index 6d37a40cd90e..0fe92986412b 100644 --- a/include/linux/bpf_local_storage.h +++ b/include/linux/bpf_local_storage.h @@ -74,6 +74,12 @@ struct bpf_local_storage_elem { struct hlist_node snode; /* Linked to bpf_local_storage */ struct bpf_local_storage __rcu *local_storage; struct rcu_head rcu; + bool can_use_smap; /* Is it safe to access smap in bpf_selem_free_* RCU + * callbacks? bpf_local_storage_map_free only + * executes rcu_barrier when there are special + * fields, this field remembers that to ensure we + * don't access already freed smap in sdata. + */ /* 8 bytes hole */ /* The data is stored in another cacheline to minimize * the number of cachelines access during a cache hit. -- cgit v1.2.3 From 20c09d92faeefb8536f705d3a4629e0dc314c8a1 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Thu, 2 Mar 2023 20:14:43 -0800 Subject: bpf: Introduce kptr_rcu. The life time of certain kernel structures like 'struct cgroup' is protected by RCU. Hence it's safe to dereference them directly from __kptr tagged pointers in bpf maps. The resulting pointer is MEM_RCU and can be passed to kfuncs that expect KF_RCU. Derefrence of other kptr-s returns PTR_UNTRUSTED. For example: struct map_value { struct cgroup __kptr *cgrp; }; SEC("tp_btf/cgroup_mkdir") int BPF_PROG(test_cgrp_get_ancestors, struct cgroup *cgrp_arg, const char *path) { struct cgroup *cg, *cg2; cg = bpf_cgroup_acquire(cgrp_arg); // cg is PTR_TRUSTED and ref_obj_id > 0 bpf_kptr_xchg(&v->cgrp, cg); cg2 = v->cgrp; // This is new feature introduced by this patch. // cg2 is PTR_MAYBE_NULL | MEM_RCU. // When cg2 != NULL, it's a valid cgroup, but its percpu_ref could be zero if (cg2) bpf_cgroup_ancestor(cg2, level); // safe to do. } Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Acked-by: Tejun Heo Acked-by: David Vernet Link: https://lore.kernel.org/bpf/20230303041446.3630-4-alexei.starovoitov@gmail.com --- include/linux/btf.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/btf.h b/include/linux/btf.h index 49e0fe6d8274..556b3e2e7471 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -70,7 +70,7 @@ #define KF_TRUSTED_ARGS (1 << 4) /* kfunc only takes trusted pointer arguments */ #define KF_SLEEPABLE (1 << 5) /* kfunc may sleep */ #define KF_DESTRUCTIVE (1 << 6) /* kfunc performs destructive actions */ -#define KF_RCU (1 << 7) /* kfunc only takes rcu pointer arguments */ +#define KF_RCU (1 << 7) /* kfunc takes either rcu or trusted pointer arguments */ /* * Tag marking a kernel function as a kfunc. This is meant to minimize the -- cgit v1.2.3 From 6fcd486b3a0a628c41f12b3a7329a18a2c74b351 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Thu, 2 Mar 2023 20:14:46 -0800 Subject: bpf: Refactor RCU enforcement in the verifier. bpf_rcu_read_lock/unlock() are only available in clang compiled kernels. Lack of such key mechanism makes it impossible for sleepable bpf programs to use RCU pointers. Allow bpf_rcu_read_lock/unlock() in GCC compiled kernels (though GCC doesn't support btf_type_tag yet) and allowlist certain field dereferences in important data structures like tast_struct, cgroup, socket that are used by sleepable programs either as RCU pointer or full trusted pointer (which is valid outside of RCU CS). Use BTF_TYPE_SAFE_RCU and BTF_TYPE_SAFE_TRUSTED macros for such tagging. They will be removed once GCC supports btf_type_tag. With that refactor check_ptr_to_btf_access(). Make it strict in enforcing PTR_TRUSTED and PTR_UNTRUSTED while deprecating old PTR_TO_BTF_ID without modifier flags. There is a chance that this strict enforcement might break existing programs (especially on GCC compiled kernels), but this cleanup has to start sooner than later. Note PTR_TO_CTX access still yields old deprecated PTR_TO_BTF_ID. Once it's converted to strict PTR_TRUSTED or PTR_UNTRUSTED the kfuncs and helpers will be able to default to KF_TRUSTED_ARGS. KF_RCU will remain as a weaker version of KF_TRUSTED_ARGS where obj refcnt could be 0. Adjust rcu_read_lock selftest to run on gcc and clang compiled kernels. Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Acked-by: David Vernet Link: https://lore.kernel.org/bpf/20230303041446.3630-7-alexei.starovoitov@gmail.com --- include/linux/bpf.h | 2 +- include/linux/bpf_verifier.h | 1 - 2 files changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 23ec684e660d..d3456804f7aa 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -2279,7 +2279,7 @@ struct bpf_core_ctx { bool btf_nested_type_is_trusted(struct bpf_verifier_log *log, const struct bpf_reg_state *reg, - int off); + int off, const char *suffix); bool btf_type_ids_nocast_alias(struct bpf_verifier_log *log, const struct btf *reg_btf, u32 reg_id, diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index b26ff2a8f63b..18538bad2b8c 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -537,7 +537,6 @@ struct bpf_verifier_env { bool bypass_spec_v1; bool bypass_spec_v4; bool seen_direct_write; - bool rcu_tag_supported; 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; -- cgit v1.2.3 From e768e3c5aab44ee63f58649d4c8cbbb3270e5c06 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Fri, 3 Mar 2023 15:15:42 +0100 Subject: bpf: Use separate RCU callbacks for freeing selem Martin suggested that instead of using a byte in the hole (which he has a use for in his future patch) in bpf_local_storage_elem, we can dispatch a different call_rcu callback based on whether we need to free special fields in bpf_local_storage_elem data. The free path, described in commit 9db44fdd8105 ("bpf: Support kptrs in local storage maps"), only waits for call_rcu callbacks when there are special (kptrs, etc.) fields in the map value, hence it is necessary that we only access smap in this case. Therefore, dispatch different RCU callbacks based on the BPF map has a valid btf_record, which dereference and use smap's btf_record only when it is valid. Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20230303141542.300068-1-memxor@gmail.com Signed-off-by: Martin KaFai Lau --- include/linux/bpf_local_storage.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf_local_storage.h b/include/linux/bpf_local_storage.h index 0fe92986412b..6d37a40cd90e 100644 --- a/include/linux/bpf_local_storage.h +++ b/include/linux/bpf_local_storage.h @@ -74,12 +74,6 @@ struct bpf_local_storage_elem { struct hlist_node snode; /* Linked to bpf_local_storage */ struct bpf_local_storage __rcu *local_storage; struct rcu_head rcu; - bool can_use_smap; /* Is it safe to access smap in bpf_selem_free_* RCU - * callbacks? bpf_local_storage_map_free only - * executes rcu_barrier when there are special - * fields, this field remembers that to ensure we - * don't access already freed smap in sdata. - */ /* 8 bytes hole */ /* The data is stored in another cacheline to minimize * the number of cachelines access during a cache hit. -- cgit v1.2.3 From a6ff3c0021468721b96e84892a8cae24bde8d65f Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Wed, 1 Mar 2023 21:14:29 +0100 Subject: thermal/core: Add a thermal zone 'devdata' accessor The thermal zone device structure is exposed to the different drivers and obviously they access the internals while that should be restricted to the core thermal code. In order to self-encapsulate the thermal core code, we need to prevent the drivers accessing directly the thermal zone structure and provide accessor functions to deal with. Provide an accessor to the 'devdata' structure and make use of it in the different drivers. No functional changes intended. Signed-off-by: Daniel Lezcano Acked-by: Rafael J. Wysocki Acked-by: Mark Brown Signed-off-by: Rafael J. Wysocki --- include/linux/thermal.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/thermal.h b/include/linux/thermal.h index 2bb4bf33f4f3..7dbb5712434c 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -365,6 +365,8 @@ thermal_zone_device_register_with_trips(const char *, struct thermal_trip *, int void *, struct thermal_zone_device_ops *, struct thermal_zone_params *, int, int); +void *thermal_zone_device_priv(struct thermal_zone_device *tzd); + int thermal_zone_bind_cooling_device(struct thermal_zone_device *, int, struct thermal_cooling_device *, unsigned long, unsigned long, @@ -436,6 +438,11 @@ static inline int thermal_zone_get_offset( struct thermal_zone_device *tz) { return -ENODEV; } +static inline void *thermal_zone_device_priv(struct thermal_zone_device *tz) +{ + return NULL; +} + static inline int thermal_zone_device_enable(struct thermal_zone_device *tz) { return -ENODEV; } -- cgit v1.2.3 From 072e35c98806100182c0a7263cf4cba09ce43463 Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Wed, 1 Mar 2023 21:14:38 +0100 Subject: thermal/core: Add thermal_zone_device structure 'type' accessor The thermal zone device structure is exposed via the exported thermal.h header. This structure should stay private the thermal core code. In order to encapsulate the structure, let's add an accessor to get the 'type' of the thermal zone. Signed-off-by: Daniel Lezcano Signed-off-by: Rafael J. Wysocki --- include/linux/thermal.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/thermal.h b/include/linux/thermal.h index 7dbb5712434c..21686e676b3d 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -366,6 +366,7 @@ thermal_zone_device_register_with_trips(const char *, struct thermal_trip *, int struct thermal_zone_params *, int, int); void *thermal_zone_device_priv(struct thermal_zone_device *tzd); +const char *thermal_zone_device_type(struct thermal_zone_device *tzd); int thermal_zone_bind_cooling_device(struct thermal_zone_device *, int, struct thermal_cooling_device *, @@ -443,6 +444,11 @@ static inline void *thermal_zone_device_priv(struct thermal_zone_device *tz) return NULL; } +static inline const char *thermal_zone_device_type(struct thermal_zone_device *tzd) +{ + return NULL; +} + static inline int thermal_zone_device_enable(struct thermal_zone_device *tz) { return -ENODEV; } -- cgit v1.2.3 From 3034f859b90d49ee661fad4d23593589d0d37779 Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Wed, 1 Mar 2023 21:14:40 +0100 Subject: thermal: Add a thermal zone id accessor In order to get the thermal zone id but without directly accessing the thermal zone device structure, add an accessor. Use the accessor in the hwmon_scmi and acpi_thermal. No functional change intented. Signed-off-by: Daniel Lezcano Acked-by: Guenter Roeck Acked-by: Rafael J. Wysocki Signed-off-by: Rafael J. Wysocki --- include/linux/thermal.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/thermal.h b/include/linux/thermal.h index 21686e676b3d..eb80cee4f64f 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -367,6 +367,7 @@ thermal_zone_device_register_with_trips(const char *, struct thermal_trip *, int void *thermal_zone_device_priv(struct thermal_zone_device *tzd); const char *thermal_zone_device_type(struct thermal_zone_device *tzd); +int thermal_zone_device_id(struct thermal_zone_device *tzd); int thermal_zone_bind_cooling_device(struct thermal_zone_device *, int, struct thermal_cooling_device *, @@ -449,6 +450,11 @@ static inline const char *thermal_zone_device_type(struct thermal_zone_device *t return NULL; } +static inline int thermal_zone_device_id(struct thermal_zone_device *tzd) +{ + return -ENODEV; +} + static inline int thermal_zone_device_enable(struct thermal_zone_device *tz) { return -ENODEV; } -- cgit v1.2.3 From 4d60cac951fd2dfbf261b83abb805748abc8b995 Mon Sep 17 00:00:00 2001 From: William Breathitt Gray Date: Mon, 27 Feb 2023 11:45:22 -0500 Subject: regmap-irq: Add no_status support Some devices lack status registers, yet expect to handle interrupts. Introduce a no_status flag to indicate such a configuration, where rather than read a status register to verify, all interrupts received are assumed to be active. Cc: Mark Brown Signed-off-by: William Breathitt Gray Link: https://lore.kernel.org/r/bd501b4b5ff88da24d467f75e8c71b4e0e6f21e2.1677515341.git.william.gray@linaro.org Signed-off-by: Mark Brown --- include/linux/regmap.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 4d10790adeb0..301286149643 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -1567,6 +1567,7 @@ struct regmap_irq_chip_data; * the need for a @sub_reg_offsets table. * @status_invert: Inverted status register: cleared bits are active interrupts. * @runtime_pm: Hold a runtime PM lock on the device when accessing it. + * @no_status: No status register: all interrupts assumed generated by device. * * @num_regs: Number of registers in each control bank. * @irqs: Descriptors for individual IRQs. Interrupt numbers are @@ -1631,6 +1632,7 @@ struct regmap_irq_chip { unsigned int clear_on_unmask:1; unsigned int not_fixed_stride:1; unsigned int status_invert:1; + unsigned int no_status:1; int num_regs; -- cgit v1.2.3 From 9b400171a69d2487c3196cc3b6de60de3b08e1ee Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Mon, 20 Feb 2023 17:33:34 +0200 Subject: regmap-irq: Place kernel doc of struct regmap_irq_chip in order It seems that a couple of members got lost theirorder, put them back. Besides that, split field descriptions into groups in the same way as it's done in the structure definition. Signed-off-by: Andy Shevchenko Link: https://lore.kernel.org/r/20230220153334.87049-1-andriy.shevchenko@linux.intel.com Signed-off-by: Mark Brown --- include/linux/regmap.h | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 4d10790adeb0..1c777566fb7d 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -1551,6 +1551,7 @@ struct regmap_irq_chip_data; * @use_ack: Use @ack register even if it is zero. * @ack_invert: Inverted ack register: cleared bits for ack. * @clear_ack: Use this to set 1 and 0 or vice-versa to clear interrupts. + * @status_invert: Inverted status register: cleared bits are active interrupts. * @wake_invert: Inverted wake register: cleared bits are wake enabled. * @type_in_mask: Use the mask registers for controlling irq type. Use this if * the hardware provides separate bits for rising/falling edge @@ -1560,18 +1561,19 @@ struct regmap_irq_chip_data; * @clear_on_unmask: For chips with interrupts cleared on read: read the status * registers before unmasking interrupts to clear any bits * set when they were masked. + * @runtime_pm: Hold a runtime PM lock on the device when accessing it. * @not_fixed_stride: Used when chip peripherals are not laid out with fixed * stride. Must be used with sub_reg_offsets containing the * offsets to each peripheral. Deprecated; the same thing * can be accomplished with a @get_irq_reg callback, without * the need for a @sub_reg_offsets table. - * @status_invert: Inverted status register: cleared bits are active interrupts. - * @runtime_pm: Hold a runtime PM lock on the device when accessing it. * * @num_regs: Number of registers in each control bank. + * * @irqs: Descriptors for individual IRQs. Interrupt numbers are * assigned based on the index in the array of the interrupt. * @num_irqs: Number of descriptors. + * * @num_type_reg: Number of type registers. Deprecated, use config registers * instead. * @num_virt_regs: Number of non-standard irq configuration registers. @@ -1579,6 +1581,7 @@ struct regmap_irq_chip_data; * instead. * @num_config_bases: Number of config base registers. * @num_config_regs: Number of config registers for each config base register. + * * @handle_pre_irq: Driver specific callback to handle interrupt from device * before regmap_irq_handler process the interrupts. * @handle_post_irq: Driver specific callback to handle interrupt from device @@ -1625,12 +1628,12 @@ struct regmap_irq_chip { unsigned int use_ack:1; unsigned int ack_invert:1; unsigned int clear_ack:1; + unsigned int status_invert:1; unsigned int wake_invert:1; - unsigned int runtime_pm:1; unsigned int type_in_mask:1; unsigned int clear_on_unmask:1; + unsigned int runtime_pm:1; unsigned int not_fixed_stride:1; - unsigned int status_invert:1; int num_regs; -- cgit v1.2.3 From ae2ade4ba58167f165fbf3db19380f9b72c56db8 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Wed, 1 Mar 2023 21:58:52 +0100 Subject: spi: Reorder fields in 'struct spi_message' Group some variables based on their sizes to reduce hole and avoid padding. On x86_64, this shrinks the size from 112 to 96 bytes. This should have no real impact on memory allocation because 'struct spi_message' is mostly used on stack, but it can save a few cycles when the structure is initialized with spi_message_init() and co. Signed-off-by: Christophe JAILLET Tested-by: Muhammad Usama Anjum Reviewed-by: Muhammad Usama Anjum Link: https://lore.kernel.org/r/c112aad16eb47808e1ec10abd87b3d273c969a68.1677704283.git.christophe.jaillet@wanadoo.fr Signed-off-by: Mark Brown --- include/linux/spi/spi.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 4fa26b9a3572..bdb35a91b4bf 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -1093,6 +1093,9 @@ struct spi_message { unsigned is_dma_mapped:1; + /* spi_prepare_message() was called for this message */ + bool prepared; + /* REVISIT: we might want a flag affecting the behavior of the * last transfer ... allowing things like "read 16 bit length L" * immediately followed by "read L bytes". Basically imposing @@ -1105,11 +1108,11 @@ struct spi_message { */ /* Completion is reported through a callback */ + int status; void (*complete)(void *context); void *context; unsigned frame_length; unsigned actual_length; - int status; /* For optional use by whatever driver currently owns the * spi_message ... between calls to spi_async and then later @@ -1120,9 +1123,6 @@ struct spi_message { /* List of spi_res reources when the spi message is processed */ struct list_head resources; - - /* spi_prepare_message() was called for this message */ - bool prepared; }; static inline void spi_message_init_no_memset(struct spi_message *m) -- cgit v1.2.3 From 0aaf08de8426f823bd0e36797445222e6392e374 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 19 Jan 2023 19:22:22 -0500 Subject: __blockdev_direct_IO(): get rid of submit_io callback always NULL... Signed-off-by: Al Viro --- include/linux/fs.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index c85916e9f7db..b07d13e546d3 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2778,7 +2778,7 @@ enum { ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, struct block_device *bdev, struct iov_iter *iter, get_block_t get_block, - dio_iodone_t end_io, dio_submit_t submit_io, + dio_iodone_t end_io, int flags); static inline ssize_t blockdev_direct_IO(struct kiocb *iocb, @@ -2787,7 +2787,7 @@ static inline ssize_t blockdev_direct_IO(struct kiocb *iocb, get_block_t get_block) { return __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev, iter, - get_block, NULL, NULL, DIO_LOCKING | DIO_SKIP_HOLES); + get_block, NULL, DIO_LOCKING | DIO_SKIP_HOLES); } #endif -- cgit v1.2.3 From 721da5cee9d43901105f5b8bd33fcb9101b12fc3 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Thu, 23 Feb 2023 08:33:26 +0100 Subject: driver core: remove CONFIG_SYSFS_DEPRECATED and CONFIG_SYSFS_DEPRECATED_V2 CONFIG_SYSFS_DEPRECATED was added in commit 88a22c985e35 ("CONFIG_SYSFS_DEPRECATED") in 2006 to allow systems with older versions of some tools (i.e. Fedora 3's version of udev) to boot properly. Four years later, in 2010, the option was attempted to be removed as most of userspace should have been fixed up properly by then, but some kernel developers clung to those old systems and refused to update, so we added CONFIG_SYSFS_DEPRECATED_V2 in commit e52eec13cd6b ("SYSFS: Allow boot time switching between deprecated and modern sysfs layout") to allow them to continue to boot properly, and we allowed a boot time parameter to be used to switch back to the old format if needed. Over time, the logic that was covered under these config options was slowly removed from individual driver subsystems successfully, removed, and the only thing that is now left in the kernel are some changes in the block layer's representation in sysfs where real directories are used instead of symlinks like normal. Because the original changes were done to userspace tools in 2006, and all distros that use those tools are long end-of-life, and older non-udev-based systems do not care about the block layer's sysfs representation, it is time to finally remove this old logic and the config entries from the kernel. Cc: Jonathan Corbet Cc: "Rafael J. Wysocki" Cc: linux-block@vger.kernel.org Cc: linux-doc@vger.kernel.org Acked-by: Jens Axboe Link: https://lore.kernel.org/r/20230223073326.2073220-1-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 1508e637bb26..19b6ba478fbf 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -1092,10 +1092,4 @@ int dev_err_probe(const struct device *dev, int err, const char *fmt, ...); #define MODULE_ALIAS_CHARDEV_MAJOR(major) \ MODULE_ALIAS("char-major-" __stringify(major) "-*") -#ifdef CONFIG_SYSFS_DEPRECATED -extern long sysfs_deprecated; -#else -#define sysfs_deprecated 0 -#endif - #endif /* _DEVICE_H_ */ -- cgit v1.2.3 From f2620f166e2a4db08f016b7b30b904ab28c265e4 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Wed, 1 Feb 2023 14:14:52 +0100 Subject: xattr: simplify listxattr helpers The generic_listxattr() and simple_xattr_list() helpers list xattrs and contain duplicated code. Add two helpers that both generic_listxattr() and simple_xattr_list() can use. Reviewed-by: Christoph Hellwig Signed-off-by: Christian Brauner (Microsoft) --- include/linux/posix_acl.h | 7 +++++++ include/linux/xattr.h | 1 + 2 files changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/posix_acl.h b/include/linux/posix_acl.h index 21cc29b8a9e8..0e65b3d634d9 100644 --- a/include/linux/posix_acl.h +++ b/include/linux/posix_acl.h @@ -106,6 +106,8 @@ struct posix_acl *vfs_get_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name); int vfs_remove_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name); +int posix_acl_listxattr(struct inode *inode, char **buffer, + ssize_t *remaining_size); #else static inline int posix_acl_chmod(struct mnt_idmap *idmap, struct dentry *dentry, umode_t mode) @@ -153,6 +155,11 @@ static inline int vfs_remove_acl(struct mnt_idmap *idmap, { return -EOPNOTSUPP; } +static inline int posix_acl_listxattr(struct inode *inode, char **buffer, + ssize_t *remaining_size) +{ + return 0; +} #endif /* CONFIG_FS_POSIX_ACL */ struct posix_acl *get_inode_acl(struct inode *inode, int type); diff --git a/include/linux/xattr.h b/include/linux/xattr.h index 6af72461397d..ce8fb0bd56c6 100644 --- a/include/linux/xattr.h +++ b/include/linux/xattr.h @@ -109,5 +109,6 @@ ssize_t simple_xattr_list(struct inode *inode, struct simple_xattrs *xattrs, char *buffer, size_t size); void simple_xattr_add(struct simple_xattrs *xattrs, struct simple_xattr *new_xattr); +int xattr_list_one(char **buffer, ssize_t *remaining_size, const char *name); #endif /* _LINUX_XATTR_H */ -- cgit v1.2.3 From 2db8a948046cab3a2f707561592906a3d096972f Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Wed, 1 Feb 2023 14:14:53 +0100 Subject: xattr: add listxattr helper Add a tiny helper to determine whether an xattr handler given a specific dentry supports listing the requested xattr. We will use this helper in various filesystems in later commits. Reviewed-by: Christoph Hellwig Signed-off-by: Christian Brauner (Microsoft) --- include/linux/xattr.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/xattr.h b/include/linux/xattr.h index ce8fb0bd56c6..7adf768d4396 100644 --- a/include/linux/xattr.h +++ b/include/linux/xattr.h @@ -47,6 +47,22 @@ struct xattr_handler { size_t size, int flags); }; +/** + * xattr_handler_can_list - check whether xattr can be listed + * @handler: handler for this type of xattr + * @dentry: dentry whose inode xattr to list + * + * Determine whether the xattr associated with @dentry can be listed given + * @handler. + * + * Return: true if xattr can be listed, false if not. + */ +static inline bool xattr_handler_can_list(const struct xattr_handler *handler, + struct dentry *dentry) +{ + return handler && (!handler->list || handler->list(dentry)); +} + const char *xattr_full_name(const struct xattr_handler *, const char *); struct xattr { -- cgit v1.2.3 From 831be973aa21d1cf8948bf4b1d4e73e6d5d028c0 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Wed, 1 Feb 2023 14:14:54 +0100 Subject: xattr: remove unused argument his helpers is really just used to check for user.* xattr support so don't make it pointlessly generic. Reviewed-by: Christoph Hellwig Signed-off-by: Christian Brauner (Microsoft) --- include/linux/xattr.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/xattr.h b/include/linux/xattr.h index 7adf768d4396..d591ef59aa98 100644 --- a/include/linux/xattr.h +++ b/include/linux/xattr.h @@ -94,7 +94,7 @@ int vfs_getxattr_alloc(struct mnt_idmap *idmap, struct dentry *dentry, const char *name, char **xattr_value, size_t size, gfp_t flags); -int xattr_supported_namespace(struct inode *inode, const char *prefix); +int xattr_supports_user_prefix(struct inode *inode); static inline const char *xattr_prefix(const struct xattr_handler *handler) { -- cgit v1.2.3 From d549b741740e63e87e661754e2d1b336fdc51d50 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Wed, 1 Feb 2023 14:14:58 +0100 Subject: fs: rename generic posix acl handlers Reflect in their naming and document that they are kept around for legacy reasons and shouldn't be used anymore by new code. Reviewed-by: Christoph Hellwig Signed-off-by: Christian Brauner (Microsoft) --- include/linux/posix_acl_xattr.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/posix_acl_xattr.h b/include/linux/posix_acl_xattr.h index 54cd7a14330d..e86f3b731da2 100644 --- a/include/linux/posix_acl_xattr.h +++ b/include/linux/posix_acl_xattr.h @@ -68,7 +68,8 @@ static inline int posix_acl_type(const char *name) return -1; } -extern const struct xattr_handler posix_acl_access_xattr_handler; -extern const struct xattr_handler posix_acl_default_xattr_handler; +/* These are legacy handlers. Don't use them for new code. */ +extern const struct xattr_handler nop_posix_acl_access; +extern const struct xattr_handler nop_posix_acl_default; #endif /* _POSIX_ACL_XATTR_H */ -- cgit v1.2.3 From 94d20f7d674d589e94aea77e2cbe37fc58541d04 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 7 Feb 2023 16:29:42 +0200 Subject: gpiolib: coldfire: remove custom asm/gpio.h Now that coldfire is the only user of a custom asm/gpio.h, it seems better to remove this as well, and have the same interface everywhere. For the gpio_get_value()/gpio_set_value()/gpio_to_irq(), gpio_cansleep() functions, the custom version is only a micro-optimization to inline the function for constant GPIO numbers. However, in the coldfire defconfigs, I was unable to find a single instance where this micro-optimization was even used, and according to Geert the only user appears to be the QSPI chip that is disabled everywhere. The custom gpio_request_one() function is even less useful, as it is guarded by an #ifdef that is never true. Reviewed-by: Geert Uytterhoeven Reviewed-by: Andy Shevchenko Acked-by: Bartosz Golaszewski Signed-off-by: Arnd Bergmann Reviewed-by: Linus Walleij Signed-off-by: Andy Shevchenko --- include/linux/gpio.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gpio.h b/include/linux/gpio.h index 85beb236c925..2b75017b3aad 100644 --- a/include/linux/gpio.h +++ b/include/linux/gpio.h @@ -54,11 +54,6 @@ struct gpio { }; #ifdef CONFIG_GPIOLIB - -#ifdef CONFIG_ARCH_HAVE_CUSTOM_GPIO_H -#include -#else - #include static inline int gpio_get_value(unsigned int gpio) @@ -81,8 +76,6 @@ static inline int gpio_to_irq(unsigned int gpio) return __gpio_to_irq(gpio); } -#endif /* ! CONFIG_ARCH_HAVE_CUSTOM_GPIO_H */ - /* CONFIG_GPIOLIB: bindings for managed devices that want to request gpios */ struct device; -- cgit v1.2.3 From eccb7a00613c804ec7244676090bf6ee43a23da2 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 8 Feb 2023 17:37:22 +0200 Subject: gpiolib: remove asm-generic/gpio.h The asm-generic/gpio.h file is now always included when using gpiolib, so just move its contents into linux/gpio.h with a few minor simplifications. Signed-off-by: Arnd Bergmann Reviewed-by: Linus Walleij Reviewed-by: Andy Shevchenko Signed-off-by: Andy Shevchenko --- include/linux/gpio.h | 94 ++++++++++++++++++++++++++++++++++++++++++++++------ 1 file changed, 84 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gpio.h b/include/linux/gpio.h index 2b75017b3aad..d5ce78e2bdd9 100644 --- a/include/linux/gpio.h +++ b/include/linux/gpio.h @@ -13,6 +13,7 @@ #define __LINUX_GPIO_H #include +#include /* see Documentation/driver-api/gpio/legacy.rst */ @@ -54,26 +55,100 @@ struct gpio { }; #ifdef CONFIG_GPIOLIB -#include -static inline int gpio_get_value(unsigned int gpio) +#include + +/* + * "valid" GPIO numbers are nonnegative and may be passed to + * setup routines like gpio_request(). Only some valid numbers + * can successfully be requested and used. + * + * Invalid GPIO numbers are useful for indicating no-such-GPIO in + * platform data and other tables. + */ +static inline bool gpio_is_valid(int number) +{ + /* only non-negative numbers are valid */ + return number >= 0; +} + +/* + * Platforms may implement their GPIO interface with library code, + * at a small performance cost for non-inlined operations and some + * extra memory (for code and for per-GPIO table entries). + */ + +/* + * At the end we want all GPIOs to be dynamically allocated from 0. + * However, some legacy drivers still perform fixed allocation. + * Until they are all fixed, leave 0-512 space for them. + */ +#define GPIO_DYNAMIC_BASE 512 + +/* Always use the library code for GPIO management calls, + * or when sleeping may be involved. + */ +int gpio_request(unsigned gpio, const char *label); +void gpio_free(unsigned gpio); + +static inline int gpio_direction_input(unsigned gpio) +{ + return gpiod_direction_input(gpio_to_desc(gpio)); +} +static inline int gpio_direction_output(unsigned gpio, int value) +{ + return gpiod_direction_output_raw(gpio_to_desc(gpio), value); +} + +static inline int gpio_set_debounce(unsigned gpio, unsigned debounce) +{ + return gpiod_set_debounce(gpio_to_desc(gpio), debounce); +} + +static inline int gpio_get_value_cansleep(unsigned gpio) +{ + return gpiod_get_raw_value_cansleep(gpio_to_desc(gpio)); +} +static inline void gpio_set_value_cansleep(unsigned gpio, int value) { - return __gpio_get_value(gpio); + return gpiod_set_raw_value_cansleep(gpio_to_desc(gpio), value); } -static inline void gpio_set_value(unsigned int gpio, int value) +static inline int gpio_get_value(unsigned gpio) +{ + return gpiod_get_raw_value(gpio_to_desc(gpio)); +} +static inline void gpio_set_value(unsigned gpio, int value) { - __gpio_set_value(gpio, value); + return gpiod_set_raw_value(gpio_to_desc(gpio), value); } -static inline int gpio_cansleep(unsigned int gpio) +static inline int gpio_cansleep(unsigned gpio) { - return __gpio_cansleep(gpio); + return gpiod_cansleep(gpio_to_desc(gpio)); } -static inline int gpio_to_irq(unsigned int gpio) +static inline int gpio_to_irq(unsigned gpio) { - return __gpio_to_irq(gpio); + return gpiod_to_irq(gpio_to_desc(gpio)); +} + +int gpio_request_one(unsigned gpio, unsigned long flags, const char *label); +int gpio_request_array(const struct gpio *array, size_t num); +void gpio_free_array(const struct gpio *array, size_t num); + +/* + * A sysfs interface can be exported by individual drivers if they want, + * but more typically is configured entirely from userspace. + */ +static inline int gpio_export(unsigned gpio, bool direction_may_change) +{ + return gpiod_export(gpio_to_desc(gpio), direction_may_change); +} + +static inline void gpio_unexport(unsigned gpio) +{ + gpiod_unexport(gpio_to_desc(gpio)); } /* CONFIG_GPIOLIB: bindings for managed devices that want to request gpios */ @@ -88,7 +163,6 @@ int devm_gpio_request_one(struct device *dev, unsigned gpio, #include #include -#include struct device; struct gpio_chip; -- cgit v1.2.3 From 0e685c3e7158d35626d6d76b9f859eae806d87fa Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 7 Feb 2023 16:29:44 +0200 Subject: gpiolib: remove gpio_set_debounce() gpio_set_debounce() only has a single user, which is trivially converted to gpiod_set_debounce(). Signed-off-by: Arnd Bergmann Reviewed-by: Linus Walleij Reviewed-by: Andy Shevchenko Signed-off-by: Andy Shevchenko --- include/linux/gpio.h | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gpio.h b/include/linux/gpio.h index d5ce78e2bdd9..fc56733e8514 100644 --- a/include/linux/gpio.h +++ b/include/linux/gpio.h @@ -100,11 +100,6 @@ static inline int gpio_direction_output(unsigned gpio, int value) return gpiod_direction_output_raw(gpio_to_desc(gpio), value); } -static inline int gpio_set_debounce(unsigned gpio, unsigned debounce) -{ - return gpiod_set_debounce(gpio_to_desc(gpio), debounce); -} - static inline int gpio_get_value_cansleep(unsigned gpio) { return gpiod_get_raw_value_cansleep(gpio_to_desc(gpio)); @@ -214,11 +209,6 @@ static inline int gpio_direction_output(unsigned gpio, int value) return -ENOSYS; } -static inline int gpio_set_debounce(unsigned gpio, unsigned debounce) -{ - return -ENOSYS; -} - static inline int gpio_get_value(unsigned gpio) { /* GPIO can never have been requested or set as {in,out}put */ -- cgit v1.2.3 From d74e316633e49f44756c23997fa071979a939405 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 7 Feb 2023 16:29:45 +0200 Subject: gpiolib: remove legacy gpio_export() There are only a handful of users of gpio_export() and related functions. As these are just wrappers around the modern gpiod_export() helper, remove the wrappers and open-code the gpio_to_desc in all callers to shrink the legacy API. Reviewed-by: Andy Shevchenko Signed-off-by: Arnd Bergmann Reviewed-by: Linus Walleij Signed-off-by: Andy Shevchenko --- include/linux/gpio.h | 27 --------------------------- 1 file changed, 27 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gpio.h b/include/linux/gpio.h index fc56733e8514..a86953696e47 100644 --- a/include/linux/gpio.h +++ b/include/linux/gpio.h @@ -132,20 +132,6 @@ int gpio_request_one(unsigned gpio, unsigned long flags, const char *label); int gpio_request_array(const struct gpio *array, size_t num); void gpio_free_array(const struct gpio *array, size_t num); -/* - * A sysfs interface can be exported by individual drivers if they want, - * but more typically is configured entirely from userspace. - */ -static inline int gpio_export(unsigned gpio, bool direction_may_change) -{ - return gpiod_export(gpio_to_desc(gpio), direction_may_change); -} - -static inline void gpio_unexport(unsigned gpio) -{ - gpiod_unexport(gpio_to_desc(gpio)); -} - /* CONFIG_GPIOLIB: bindings for managed devices that want to request gpios */ struct device; @@ -242,19 +228,6 @@ static inline void gpio_set_value_cansleep(unsigned gpio, int value) WARN_ON(1); } -static inline int gpio_export(unsigned gpio, bool direction_may_change) -{ - /* GPIO can never have been requested or set as {in,out}put */ - WARN_ON(1); - return -EINVAL; -} - -static inline void gpio_unexport(unsigned gpio) -{ - /* GPIO can never have been exported */ - WARN_ON(1); -} - static inline int gpio_to_irq(unsigned gpio) { /* GPIO can never have been requested or set as input */ -- cgit v1.2.3 From a8e59744e16b9ae18fab773a0fd3b23cdf21ad75 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 8 Feb 2023 17:41:47 +0200 Subject: gpiolib: split linux/gpio/driver.h out of linux/gpio.h Almost all gpio drivers include linux/gpio/driver.h, and other files should not rely on includes from this header. Remove the indirect include from here and include the correct headers directly from where they are used. Reviewed-by: Andy Shevchenko Signed-off-by: Arnd Bergmann Reviewed-by: Linus Walleij Signed-off-by: Andy Shevchenko Acked-by: Lee Jones --- include/linux/mfd/ucb1x00.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mfd/ucb1x00.h b/include/linux/mfd/ucb1x00.h index 43bcf35afe27..ede237384723 100644 --- a/include/linux/mfd/ucb1x00.h +++ b/include/linux/mfd/ucb1x00.h @@ -10,6 +10,7 @@ #include #include #include +#include #include #define UCB_IO_DATA 0x00 -- cgit v1.2.3 From a99cc66807d6c854a7f65f962766c530c91be149 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 7 Feb 2023 16:29:47 +0200 Subject: gpiolib: split of_mm_gpio_chip out of linux/of_gpio.h This is a rarely used feature that has nothing to do with the client-side of_gpio.h. Split it out with a separate header file and Kconfig option so it can be removed on its own timeline aside from removing the of_gpio consumer interfaces. Reviewed-by: Andy Shevchenko Signed-off-by: Arnd Bergmann Reviewed-by: Linus Walleij Signed-off-by: Andy Shevchenko --- include/linux/gpio/legacy-of-mm-gpiochip.h | 36 ++++++++++++++++++++++++++++++ include/linux/of_gpio.h | 21 ----------------- 2 files changed, 36 insertions(+), 21 deletions(-) create mode 100644 include/linux/gpio/legacy-of-mm-gpiochip.h (limited to 'include/linux') diff --git a/include/linux/gpio/legacy-of-mm-gpiochip.h b/include/linux/gpio/legacy-of-mm-gpiochip.h new file mode 100644 index 000000000000..2e2bd3b19cc3 --- /dev/null +++ b/include/linux/gpio/legacy-of-mm-gpiochip.h @@ -0,0 +1,36 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * OF helpers for the old of_mm_gpio_chip, used on ppc32 and nios2, + * do not use in new code. + * + * Copyright (c) 2007-2008 MontaVista Software, Inc. + * + * Author: Anton Vorontsov + */ + +#ifndef __LINUX_GPIO_LEGACY_OF_MM_GPIO_CHIP_H +#define __LINUX_GPIO_LEGACY_OF_MM_GPIO_CHIP_H + +#include +#include + +/* + * OF GPIO chip for memory mapped banks + */ +struct of_mm_gpio_chip { + struct gpio_chip gc; + void (*save_regs)(struct of_mm_gpio_chip *mm_gc); + void __iomem *regs; +}; + +static inline struct of_mm_gpio_chip *to_of_mm_gpio_chip(struct gpio_chip *gc) +{ + return container_of(gc, struct of_mm_gpio_chip, gc); +} + +extern int of_mm_gpiochip_add_data(struct device_node *np, + struct of_mm_gpio_chip *mm_gc, + void *data); +extern void of_mm_gpiochip_remove(struct of_mm_gpio_chip *mm_gc); + +#endif /* __LINUX_GPIO_LEGACY_OF_MM_GPIO_CHIP_H */ diff --git a/include/linux/of_gpio.h b/include/linux/of_gpio.h index 5d58b3b0a97e..d0f66a5e1b2a 100644 --- a/include/linux/of_gpio.h +++ b/include/linux/of_gpio.h @@ -19,30 +19,9 @@ struct device_node; #ifdef CONFIG_OF_GPIO -#include - -/* - * OF GPIO chip for memory mapped banks - */ -struct of_mm_gpio_chip { - struct gpio_chip gc; - void (*save_regs)(struct of_mm_gpio_chip *mm_gc); - void __iomem *regs; -}; - -static inline struct of_mm_gpio_chip *to_of_mm_gpio_chip(struct gpio_chip *gc) -{ - return container_of(gc, struct of_mm_gpio_chip, gc); -} - extern int of_get_named_gpio(const struct device_node *np, const char *list_name, int index); -extern int of_mm_gpiochip_add_data(struct device_node *np, - struct of_mm_gpio_chip *mm_gc, - void *data); -extern void of_mm_gpiochip_remove(struct of_mm_gpio_chip *mm_gc); - #else /* CONFIG_OF_GPIO */ #include -- cgit v1.2.3 From 6cfd84c4f4f61905088b642a3ef1038ee627cd98 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Tue, 7 Feb 2023 16:29:49 +0200 Subject: gpiolib: Drop unused forward declaration from driver.h There is no struct device_node pointers anywhere in the header, drop unused forward declaration. Signed-off-by: Andy Shevchenko --- include/linux/gpio/driver.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index ccd8a512d854..262a84ce9bcb 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -16,7 +16,6 @@ struct gpio_desc; struct of_phandle_args; -struct device_node; struct seq_file; struct gpio_device; struct module; -- cgit v1.2.3 From 91e5ae95a0af7d2db9e98e8f99436c02c304378b Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Tue, 7 Feb 2023 16:29:50 +0200 Subject: gpiolib: Deduplicate forward declarations in consumer.h The struct fwnode_handle pointer is used in both branches of ifdeffery, no need to have a copy of the same in each of them, just make it global. Signed-off-by: Andy Shevchenko --- include/linux/gpio/consumer.h | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gpio/consumer.h b/include/linux/gpio/consumer.h index 59cb20cfac3d..a7eb8aa1e54c 100644 --- a/include/linux/gpio/consumer.h +++ b/include/linux/gpio/consumer.h @@ -8,6 +8,7 @@ #include struct device; +struct fwnode_handle; struct gpio_desc; struct gpio_array; @@ -171,9 +172,6 @@ int gpiod_set_consumer_name(struct gpio_desc *desc, const char *name); struct gpio_desc *gpio_to_desc(unsigned gpio); int desc_to_gpio(const struct gpio_desc *desc); -/* Child properties interface */ -struct fwnode_handle; - struct gpio_desc *fwnode_gpiod_get_index(struct fwnode_handle *fwnode, const char *con_id, int index, enum gpiod_flags flags, @@ -546,9 +544,6 @@ static inline int desc_to_gpio(const struct gpio_desc *desc) return -EINVAL; } -/* Child properties interface */ -struct fwnode_handle; - static inline struct gpio_desc *fwnode_gpiod_get_index(struct fwnode_handle *fwnode, const char *con_id, int index, -- cgit v1.2.3 From 5b1911976ccf83e892452afb0363500228b35d81 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Tue, 7 Feb 2023 16:29:51 +0200 Subject: gpiolib: Group forward declarations in consumer.h For better maintenance group the forward declarations together. Signed-off-by: Andy Shevchenko --- include/linux/gpio/consumer.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gpio/consumer.h b/include/linux/gpio/consumer.h index a7eb8aa1e54c..5432e5d5fbfb 100644 --- a/include/linux/gpio/consumer.h +++ b/include/linux/gpio/consumer.h @@ -7,6 +7,7 @@ #include #include +struct acpi_device; struct device; struct fwnode_handle; struct gpio_desc; @@ -602,8 +603,6 @@ struct acpi_gpio_mapping { unsigned int quirks; }; -struct acpi_device; - #if IS_ENABLED(CONFIG_GPIOLIB) && IS_ENABLED(CONFIG_ACPI) int acpi_dev_add_driver_gpios(struct acpi_device *adev, -- cgit v1.2.3 From 380c7ba3923c6e471aff0f951a6cf42e8dec2c79 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Wed, 8 Feb 2023 19:07:28 +0200 Subject: gpiolib: Clean up headers There is a few things done: - include only the headers we are direct user of - when pointer is in use, provide a forward declaration - add missing headers - group generic headers and subsystem headers - sort each group alphabetically Signed-off-by: Andy Shevchenko --- include/linux/gpio.h | 10 ++++------ include/linux/gpio/consumer.h | 14 ++++++++++---- include/linux/gpio/driver.h | 30 +++++++++++++++++++++++------- 3 files changed, 37 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gpio.h b/include/linux/gpio.h index a86953696e47..8528353e073b 100644 --- a/include/linux/gpio.h +++ b/include/linux/gpio.h @@ -12,9 +12,10 @@ #ifndef __LINUX_GPIO_H #define __LINUX_GPIO_H -#include #include +struct device; + /* see Documentation/driver-api/gpio/legacy.rst */ /* make these flag values available regardless of GPIO kconfig options */ @@ -134,19 +135,16 @@ void gpio_free_array(const struct gpio *array, size_t num); /* CONFIG_GPIOLIB: bindings for managed devices that want to request gpios */ -struct device; - int devm_gpio_request(struct device *dev, unsigned gpio, const char *label); int devm_gpio_request_one(struct device *dev, unsigned gpio, unsigned long flags, const char *label); #else /* ! CONFIG_GPIOLIB */ -#include #include -struct device; -struct gpio_chip; +#include +#include static inline bool gpio_is_valid(int number) { diff --git a/include/linux/gpio/consumer.h b/include/linux/gpio/consumer.h index 5432e5d5fbfb..1c4385a00f88 100644 --- a/include/linux/gpio/consumer.h +++ b/include/linux/gpio/consumer.h @@ -3,15 +3,14 @@ #define __LINUX_GPIO_CONSUMER_H #include -#include -#include -#include +#include struct acpi_device; struct device; struct fwnode_handle; -struct gpio_desc; + struct gpio_array; +struct gpio_desc; /** * struct gpio_descs - Struct containing an array of descriptors that can be @@ -185,8 +184,11 @@ struct gpio_desc *devm_fwnode_gpiod_get_index(struct device *dev, #else /* CONFIG_GPIOLIB */ +#include #include +#include + static inline int gpiod_count(struct device *dev, const char *con_id) { return 0; @@ -616,6 +618,8 @@ struct gpio_desc *acpi_get_and_request_gpiod(char *path, unsigned int pin, char #else /* CONFIG_GPIOLIB && CONFIG_ACPI */ +#include + static inline int acpi_dev_add_driver_gpios(struct acpi_device *adev, const struct acpi_gpio_mapping *gpios) { @@ -647,6 +651,8 @@ void gpiod_unexport(struct gpio_desc *desc); #else /* CONFIG_GPIOLIB && CONFIG_GPIO_SYSFS */ +#include + static inline int gpiod_export(struct gpio_desc *desc, bool direction_may_change) { diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index 262a84ce9bcb..5c6db5533be6 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -2,27 +2,35 @@ #ifndef __LINUX_GPIO_DRIVER_H #define __LINUX_GPIO_DRIVER_H -#include -#include +#include #include #include +#include #include #include #include #include +#include #include +#ifdef CONFIG_GENERIC_MSI_IRQ #include +#endif -struct gpio_desc; +struct device; +struct irq_chip; +struct irq_data; +struct module; struct of_phandle_args; +struct pinctrl_dev; struct seq_file; -struct gpio_device; -struct module; -enum gpiod_flags; -enum gpio_lookup_flags; struct gpio_chip; +struct gpio_desc; +struct gpio_device; + +enum gpio_lookup_flags; +enum gpiod_flags; union gpio_irq_fwspec { struct irq_fwspec fwspec; @@ -679,6 +687,10 @@ bool gpiochip_irqchip_irq_valid(const struct gpio_chip *gc, int gpiochip_irqchip_add_domain(struct gpio_chip *gc, struct irq_domain *domain); #else + +#include +#include + static inline int gpiochip_irqchip_add_domain(struct gpio_chip *gc, struct irq_domain *domain) { @@ -756,6 +768,10 @@ struct gpio_chip *gpiod_to_chip(const struct gpio_desc *desc); #else /* CONFIG_GPIOLIB */ +#include + +#include + static inline struct gpio_chip *gpiod_to_chip(const struct gpio_desc *desc) { /* GPIO can never have been requested */ -- cgit v1.2.3 From dd4f373ef94bd186e18a7366adfb7b98bc31b786 Mon Sep 17 00:00:00 2001 From: "Roy-CW.Yeh" Date: Mon, 6 Feb 2023 17:11:07 +0800 Subject: soc: mediatek: mmsys: add config api for RSZ switching and DCM Due to MT8195 HW design, some RSZs have additional settings that need to be configured in MMSYS. Signed-off-by: Roy-CW.Yeh Signed-off-by: Moudy Ho Reviewed-by: AngeloGioacchino Del Regno Change-Id: I41978bf14951221c88abbe70d8c24cb0770e11e3 Link: https://lore.kernel.org/r/20230206091109.1324-5-moudy.ho@mediatek.com Signed-off-by: Matthias Brugger --- include/linux/soc/mediatek/mtk-mmsys.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/soc/mediatek/mtk-mmsys.h b/include/linux/soc/mediatek/mtk-mmsys.h index dc2963a0a0f7..37544ea6286d 100644 --- a/include/linux/soc/mediatek/mtk-mmsys.h +++ b/include/linux/soc/mediatek/mtk-mmsys.h @@ -99,4 +99,10 @@ void mtk_mmsys_mixer_in_config(struct device *dev, int idx, bool alpha_sel, u16 void mtk_mmsys_mixer_in_channel_swap(struct device *dev, int idx, bool channel_swap, struct cmdq_pkt *cmdq_pkt); +void mtk_mmsys_vpp_rsz_merge_config(struct device *dev, u32 id, bool enable, + struct cmdq_pkt *cmdq_pkt); + +void mtk_mmsys_vpp_rsz_dcm_config(struct device *dev, bool enable, + struct cmdq_pkt *cmdq_pkt); + #endif /* __MTK_MMSYS_H */ -- cgit v1.2.3 From 549053b69c54aecc6f44ddefe6c245a35f162cf4 Mon Sep 17 00:00:00 2001 From: "Roy-CW.Yeh" Date: Mon, 6 Feb 2023 17:11:09 +0800 Subject: soc: mediatek: mutex: support MT8195 VPPSYS Add MT8195 VPPSYS0 and VPPSYS1 mutex info to driver data Signed-off-by: Roy-CW.Yeh Signed-off-by: Moudy Ho Reviewed-by: AngeloGioacchino Del Regno Change-Id: Ie371dc9dcf35ea308d9460acd60fb9c3d6475deb Link: https://lore.kernel.org/r/20230206091109.1324-7-moudy.ho@mediatek.com Signed-off-by: Matthias Brugger --- include/linux/soc/mediatek/mtk-mutex.h | 35 ++++++++++++++++++++++++++++++++++ 1 file changed, 35 insertions(+) (limited to 'include/linux') diff --git a/include/linux/soc/mediatek/mtk-mutex.h b/include/linux/soc/mediatek/mtk-mutex.h index b335c2837cd8..635218e3ac68 100644 --- a/include/linux/soc/mediatek/mtk-mutex.h +++ b/include/linux/soc/mediatek/mtk-mutex.h @@ -22,6 +22,41 @@ enum mtk_mutex_mod_index { MUTEX_MOD_IDX_MDP_CCORR0, MUTEX_MOD_IDX_MDP_HDR0, MUTEX_MOD_IDX_MDP_COLOR0, + MUTEX_MOD_IDX_MDP_RDMA1, + MUTEX_MOD_IDX_MDP_RDMA2, + MUTEX_MOD_IDX_MDP_RDMA3, + MUTEX_MOD_IDX_MDP_STITCH0, + MUTEX_MOD_IDX_MDP_FG0, + MUTEX_MOD_IDX_MDP_FG1, + MUTEX_MOD_IDX_MDP_FG2, + MUTEX_MOD_IDX_MDP_FG3, + MUTEX_MOD_IDX_MDP_HDR1, + MUTEX_MOD_IDX_MDP_HDR2, + MUTEX_MOD_IDX_MDP_HDR3, + MUTEX_MOD_IDX_MDP_AAL1, + MUTEX_MOD_IDX_MDP_AAL2, + MUTEX_MOD_IDX_MDP_AAL3, + MUTEX_MOD_IDX_MDP_RSZ2, + MUTEX_MOD_IDX_MDP_RSZ3, + MUTEX_MOD_IDX_MDP_MERGE2, + MUTEX_MOD_IDX_MDP_MERGE3, + MUTEX_MOD_IDX_MDP_TDSHP1, + MUTEX_MOD_IDX_MDP_TDSHP2, + MUTEX_MOD_IDX_MDP_TDSHP3, + MUTEX_MOD_IDX_MDP_COLOR1, + MUTEX_MOD_IDX_MDP_COLOR2, + MUTEX_MOD_IDX_MDP_COLOR3, + MUTEX_MOD_IDX_MDP_OVL0, + MUTEX_MOD_IDX_MDP_OVL1, + MUTEX_MOD_IDX_MDP_PAD0, + MUTEX_MOD_IDX_MDP_PAD1, + MUTEX_MOD_IDX_MDP_PAD2, + MUTEX_MOD_IDX_MDP_PAD3, + MUTEX_MOD_IDX_MDP_TCC0, + MUTEX_MOD_IDX_MDP_TCC1, + MUTEX_MOD_IDX_MDP_WROT1, + MUTEX_MOD_IDX_MDP_WROT2, + MUTEX_MOD_IDX_MDP_WROT3, MUTEX_MOD_IDX_MAX /* ALWAYS keep at the end */ }; -- cgit v1.2.3 From 1661372c912d1966e21e0cb5463559984df8249b Mon Sep 17 00:00:00 2001 From: Paul Moore Date: Tue, 7 Feb 2023 17:06:51 -0500 Subject: lsm: move the program execution hook comments to security/security.c This patch relocates the LSM hook function comments to the function definitions, in keeping with the current kernel conventions. This should make the hook descriptions more easily discoverable and easier to maintain. While formatting changes have been done to better fit the kernel-doc style, content changes have been kept to a minimum and limited to text which was obviously incorrect and/or outdated. It is expected the future patches will improve the quality of the function header comments. Acked-by: Casey Schaufler Signed-off-by: Paul Moore --- include/linux/lsm_hooks.h | 52 ----------------------------------------------- 1 file changed, 52 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index 6e156d2acffc..784e19fd665b 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -32,58 +32,6 @@ /** * union security_list_options - Linux Security Module hook function list * - * Security hooks for program execution operations. - * - * @bprm_creds_for_exec: - * If the setup in prepare_exec_creds did not setup @bprm->cred->security - * properly for executing @bprm->file, update the LSM's portion of - * @bprm->cred->security to be what commit_creds needs to install for the - * new program. This hook may also optionally check permissions - * (e.g. for transitions between security domains). - * The hook must set @bprm->secureexec to 1 if AT_SECURE should be set to - * request libc enable secure mode. - * @bprm contains the linux_binprm structure. - * Return 0 if the hook is successful and permission is granted. - * @bprm_creds_from_file: - * If @file is setpcap, suid, sgid or otherwise marked to change - * privilege upon exec, update @bprm->cred to reflect that change. - * This is called after finding the binary that will be executed. - * without an interpreter. This ensures that the credentials will not - * be derived from a script that the binary will need to reopen, which - * when reopend may end up being a completely different file. This - * hook may also optionally check permissions (e.g. for transitions - * between security domains). - * The hook must set @bprm->secureexec to 1 if AT_SECURE should be set to - * request libc enable secure mode. - * The hook must add to @bprm->per_clear any personality flags that - * should be cleared from current->personality. - * @bprm contains the linux_binprm structure. - * Return 0 if the hook is successful and permission is granted. - * @bprm_check_security: - * This hook mediates the point when a search for a binary handler will - * begin. It allows a check against the @bprm->cred->security value - * which was set in the preceding creds_for_exec call. The argv list and - * envp list are reliably available in @bprm. This hook may be called - * multiple times during a single execve. - * @bprm contains the linux_binprm structure. - * Return 0 if the hook is successful and permission is granted. - * @bprm_committing_creds: - * Prepare to install the new security attributes of a process being - * transformed by an execve operation, based on the old credentials - * pointed to by @current->cred and the information set in @bprm->cred by - * the bprm_creds_for_exec hook. @bprm points to the linux_binprm - * structure. This hook is a good place to perform state changes on the - * process such as closing open file descriptors to which access will no - * longer be granted when the attributes are changed. This is called - * immediately before commit_creds(). - * @bprm_committed_creds: - * Tidy up after the installation of the new security attributes of a - * process being transformed by an execve operation. The new credentials - * have, by this point, been set to @current->cred. @bprm points to the - * linux_binprm structure. This hook is a good place to perform state - * changes on the process such as clearing out non-inheritable signal - * state. This is called immediately after commit_creds(). - * * Security hooks for mount using fs_context. * [See also Documentation/filesystems/mount_api.rst] * -- cgit v1.2.3 From 36819f185590c1e0e47d095f04bf5da20650fe4d Mon Sep 17 00:00:00 2001 From: Paul Moore Date: Tue, 7 Feb 2023 17:33:31 -0500 Subject: lsm: move the fs_context hook comments to security/security.c This patch relocates the LSM hook function comments to the function definitions, in keeping with the current kernel conventions. This should make the hook descriptions more easily discoverable and easier to maintain. While formatting changes have been done to better fit the kernel-doc style, content changes have been kept to a minimum and limited to text which was obviously incorrect and/or outdated. It is expected the future patches will improve the quality of the function header comments. Acked-by: Casey Schaufler Signed-off-by: Paul Moore --- include/linux/lsm_hooks.h | 17 ----------------- 1 file changed, 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index 784e19fd665b..a37f3a380918 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -32,23 +32,6 @@ /** * union security_list_options - Linux Security Module hook function list * - * Security hooks for mount using fs_context. - * [See also Documentation/filesystems/mount_api.rst] - * - * @fs_context_dup: - * Allocate and attach a security structure to sc->security. This pointer - * is initialised to NULL by the caller. - * @fc indicates the new filesystem context. - * @src_fc indicates the original filesystem context. - * Return 0 on success or a negative error code on failure. - * @fs_context_parse_param: - * Userspace provided a parameter to configure a superblock. The LSM may - * reject it with an error and may use it for itself, in which case it - * should return 0; otherwise it should return -ENOPARAM to pass it on to - * the filesystem. - * @fc indicates the filesystem context. - * @param The parameter. - * * Security hooks for filesystem operations. * * @sb_alloc_security: -- cgit v1.2.3 From 08526a902cc4bc57bb160e5b1114e67a56fc9280 Mon Sep 17 00:00:00 2001 From: Paul Moore Date: Tue, 7 Feb 2023 17:44:01 -0500 Subject: lsm: move the filesystem hook comments to security/security.c This patch relocates the LSM hook function comments to the function definitions, in keeping with the current kernel conventions. This should make the hook descriptions more easily discoverable and easier to maintain. While formatting changes have been done to better fit the kernel-doc style, content changes have been kept to a minimum and limited to text which was obviously incorrect and/or outdated. It is expected the future patches will improve the quality of the function header comments. Acked-by: Casey Schaufler Signed-off-by: Paul Moore --- include/linux/lsm_hooks.h | 106 ---------------------------------------------- 1 file changed, 106 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index a37f3a380918..3cd6e7abe0df 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -32,112 +32,6 @@ /** * union security_list_options - Linux Security Module hook function list * - * Security hooks for filesystem operations. - * - * @sb_alloc_security: - * Allocate and attach a security structure to the sb->s_security field. - * The s_security field is initialized to NULL when the structure is - * allocated. - * @sb contains the super_block structure to be modified. - * Return 0 if operation was successful. - * @sb_delete: - * Release objects tied to a superblock (e.g. inodes). - * @sb contains the super_block structure being released. - * @sb_free_security: - * Deallocate and clear the sb->s_security field. - * @sb contains the super_block structure to be modified. - * @sb_free_mnt_opts: - * Free memory associated with @mnt_ops. - * @sb_eat_lsm_opts: - * Eat (scan @orig options) and save them in @mnt_opts. - * Return 0 on success, negative values on failure. - * @sb_statfs: - * Check permission before obtaining filesystem statistics for the @mnt - * mountpoint. - * @dentry is a handle on the superblock for the filesystem. - * Return 0 if permission is granted. - * @sb_mount: - * Check permission before an object specified by @dev_name is mounted on - * the mount point named by @nd. For an ordinary mount, @dev_name - * identifies a device if the file system type requires a device. For a - * remount (@flags & MS_REMOUNT), @dev_name is irrelevant. For a - * loopback/bind mount (@flags & MS_BIND), @dev_name identifies the - * pathname of the object being mounted. - * @dev_name contains the name for object being mounted. - * @path contains the path for mount point object. - * @type contains the filesystem type. - * @flags contains the mount flags. - * @data contains the filesystem-specific data. - * Return 0 if permission is granted. - * @sb_mnt_opts_compat: - * Determine if the new mount options in @mnt_opts are allowed given - * the existing mounted filesystem at @sb. - * @sb superblock being compared. - * @mnt_opts new mount options. - * Return 0 if options are compatible. - * @sb_remount: - * Extracts security system specific mount options and verifies no changes - * are being made to those options. - * @sb superblock being remounted. - * @data contains the filesystem-specific data. - * Return 0 if permission is granted. - * @sb_kern_mount: - * Mount this @sb if allowed by permissions. - * Return 0 if permission is granted. - * @sb_show_options: - * Show (print on @m) mount options for this @sb. - * Return 0 on success, negative values on failure. - * @sb_umount: - * Check permission before the @mnt file system is unmounted. - * @mnt contains the mounted file system. - * @flags contains the unmount flags, e.g. MNT_FORCE. - * Return 0 if permission is granted. - * @sb_pivotroot: - * Check permission before pivoting the root filesystem. - * @old_path contains the path for the new location of the - * current root (put_old). - * @new_path contains the path for the new root (new_root). - * Return 0 if permission is granted. - * @sb_set_mnt_opts: - * Set the security relevant mount options used for a superblock - * @sb the superblock to set security mount options for. - * @opts binary data structure containing all lsm mount data. - * Return 0 on success, error on failure. - * @sb_clone_mnt_opts: - * Copy all security options from a given superblock to another - * @oldsb old superblock which contain information to clone. - * @newsb new superblock which needs filled in. - * Return 0 on success, error on failure. - * @move_mount: - * Check permission before a mount is moved. - * @from_path indicates the mount that is going to be moved. - * @to_path indicates the mountpoint that will be mounted upon. - * Return 0 if permission is granted. - * @dentry_init_security: - * Compute a context for a dentry as the inode is not yet available - * since NFSv4 has no label backed by an EA anyway. - * @dentry dentry to use in calculating the context. - * @mode mode used to determine resource type. - * @name name of the last path component used to create file. - * @xattr_name pointer to place the pointer to security xattr name. - * Caller does not have to free the resulting pointer. Its - * a pointer to static string. - * @ctx pointer to place the pointer to the resulting context in. - * @ctxlen point to place the length of the resulting context. - * Return 0 on success, negative values on failure. - * @dentry_create_files_as: - * Compute a context for a dentry as the inode is not yet available - * and set that context in passed in creds so that new files are - * created using that context. Context is calculated using the - * passed in creds and not the creds of the caller. - * @dentry dentry to use in calculating the context. - * @mode mode used to determine resource type. - * @name name of the last path component used to create file. - * @old creds which should be used for context calculation. - * @new creds to modify. - * Return 0 on success, error on failure. - * - * * Security hooks for inode operations. * * @inode_alloc_security: -- cgit v1.2.3 From 916e32584dfaff068792db70c89936801b476ad0 Mon Sep 17 00:00:00 2001 From: Paul Moore Date: Wed, 8 Feb 2023 16:31:55 -0500 Subject: lsm: move the inode hook comments to security/security.c This patch relocates the LSM hook function comments to the function definitions, in keeping with the current kernel conventions. This should make the hook descriptions more easily discoverable and easier to maintain. While formatting changes have been done to better fit the kernel-doc style, content changes have been kept to a minimum and limited to text which was obviously incorrect and/or outdated. It is expected the future patches will improve the quality of the function header comments. Acked-by: Casey Schaufler Signed-off-by: Paul Moore --- include/linux/lsm_hooks.h | 303 ---------------------------------------------- 1 file changed, 303 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index 3cd6e7abe0df..3cdd58424796 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -32,309 +32,6 @@ /** * union security_list_options - Linux Security Module hook function list * - * Security hooks for inode operations. - * - * @inode_alloc_security: - * Allocate and attach a security structure to @inode->i_security. The - * i_security field is initialized to NULL when the inode structure is - * allocated. - * @inode contains the inode structure. - * Return 0 if operation was successful. - * @inode_free_security: - * @inode contains the inode structure. - * Deallocate the inode security structure and set @inode->i_security to - * NULL. - * @inode_init_security: - * Obtain the security attribute name suffix and value to set on a newly - * created inode and set up the incore security field for the new inode. - * This hook is called by the fs code as part of the inode creation - * transaction and provides for atomic labeling of the inode, unlike - * the post_create/mkdir/... hooks called by the VFS. The hook function - * is expected to allocate the name and value via kmalloc, with the caller - * being responsible for calling kfree after using them. - * If the security module does not use security attributes or does - * not wish to put a security attribute on this particular inode, - * then it should return -EOPNOTSUPP to skip this processing. - * @inode contains the inode structure of the newly created inode. - * @dir contains the inode structure of the parent directory. - * @qstr contains the last path component of the new object. - * @name will be set to the allocated name suffix (e.g. selinux). - * @value will be set to the allocated attribute value. - * @len will be set to the length of the value. - * Returns 0 if @name and @value have been successfully set, - * -EOPNOTSUPP if no security attribute is needed, or - * -ENOMEM on memory allocation failure. - * @inode_init_security_anon: - * Set up the incore security field for the new anonymous inode - * and return whether the inode creation is permitted by the security - * module or not. - * @inode contains the inode structure. - * @name name of the anonymous inode class. - * @context_inode optional related inode. - * Returns 0 on success, -EACCES if the security module denies the - * creation of this inode, or another -errno upon other errors. - * @inode_create: - * Check permission to create a regular file. - * @dir contains inode structure of the parent of the new file. - * @dentry contains the dentry structure for the file to be created. - * @mode contains the file mode of the file to be created. - * Return 0 if permission is granted. - * @inode_link: - * Check permission before creating a new hard link to a file. - * @old_dentry contains the dentry structure for an existing - * link to the file. - * @dir contains the inode structure of the parent directory - * of the new link. - * @new_dentry contains the dentry structure for the new link. - * Return 0 if permission is granted. - * @path_link: - * Check permission before creating a new hard link to a file. - * @old_dentry contains the dentry structure for an existing link - * to the file. - * @new_dir contains the path structure of the parent directory of - * the new link. - * @new_dentry contains the dentry structure for the new link. - * Return 0 if permission is granted. - * @inode_unlink: - * Check the permission to remove a hard link to a file. - * @dir contains the inode structure of parent directory of the file. - * @dentry contains the dentry structure for file to be unlinked. - * Return 0 if permission is granted. - * @path_unlink: - * Check the permission to remove a hard link to a file. - * @dir contains the path structure of parent directory of the file. - * @dentry contains the dentry structure for file to be unlinked. - * Return 0 if permission is granted. - * @inode_symlink: - * Check the permission to create a symbolic link to a file. - * @dir contains the inode structure of parent directory of - * the symbolic link. - * @dentry contains the dentry structure of the symbolic link. - * @old_name contains the pathname of file. - * Return 0 if permission is granted. - * @path_symlink: - * Check the permission to create a symbolic link to a file. - * @dir contains the path structure of parent directory of - * the symbolic link. - * @dentry contains the dentry structure of the symbolic link. - * @old_name contains the pathname of file. - * Return 0 if permission is granted. - * @inode_mkdir: - * Check permissions to create a new directory in the existing directory - * associated with inode structure @dir. - * @dir contains the inode structure of parent of the directory - * to be created. - * @dentry contains the dentry structure of new directory. - * @mode contains the mode of new directory. - * Return 0 if permission is granted. - * @path_mkdir: - * Check permissions to create a new directory in the existing directory - * associated with path structure @path. - * @dir contains the path structure of parent of the directory - * to be created. - * @dentry contains the dentry structure of new directory. - * @mode contains the mode of new directory. - * Return 0 if permission is granted. - * @inode_rmdir: - * Check the permission to remove a directory. - * @dir contains the inode structure of parent of the directory - * to be removed. - * @dentry contains the dentry structure of directory to be removed. - * Return 0 if permission is granted. - * @path_rmdir: - * Check the permission to remove a directory. - * @dir contains the path structure of parent of the directory to be - * removed. - * @dentry contains the dentry structure of directory to be removed. - * Return 0 if permission is granted. - * @inode_mknod: - * Check permissions when creating a special file (or a socket or a fifo - * file created via the mknod system call). Note that if mknod operation - * is being done for a regular file, then the create hook will be called - * and not this hook. - * @dir contains the inode structure of parent of the new file. - * @dentry contains the dentry structure of the new file. - * @mode contains the mode of the new file. - * @dev contains the device number. - * Return 0 if permission is granted. - * @path_mknod: - * Check permissions when creating a file. Note that this hook is called - * even if mknod operation is being done for a regular file. - * @dir contains the path structure of parent of the new file. - * @dentry contains the dentry structure of the new file. - * @mode contains the mode of the new file. - * @dev contains the undecoded device number. Use new_decode_dev() to get - * the decoded device number. - * Return 0 if permission is granted. - * @inode_rename: - * Check for permission to rename a file or directory. - * @old_dir contains the inode structure for parent of the old link. - * @old_dentry contains the dentry structure of the old link. - * @new_dir contains the inode structure for parent of the new link. - * @new_dentry contains the dentry structure of the new link. - * Return 0 if permission is granted. - * @path_rename: - * Check for permission to rename a file or directory. - * @old_dir contains the path structure for parent of the old link. - * @old_dentry contains the dentry structure of the old link. - * @new_dir contains the path structure for parent of the new link. - * @new_dentry contains the dentry structure of the new link. - * @flags may contain rename options such as RENAME_EXCHANGE. - * Return 0 if permission is granted. - * @path_chmod: - * Check for permission to change a mode of the file @path. The new - * mode is specified in @mode. - * @path contains the path structure of the file to change the mode. - * @mode contains the new DAC's permission, which is a bitmask of - * constants from . - * Return 0 if permission is granted. - * @path_chown: - * Check for permission to change owner/group of a file or directory. - * @path contains the path structure. - * @uid contains new owner's ID. - * @gid contains new group's ID. - * Return 0 if permission is granted. - * @path_chroot: - * Check for permission to change root directory. - * @path contains the path structure. - * Return 0 if permission is granted. - * @path_notify: - * Check permissions before setting a watch on events as defined by @mask, - * on an object at @path, whose type is defined by @obj_type. - * Return 0 if permission is granted. - * @inode_readlink: - * Check the permission to read the symbolic link. - * @dentry contains the dentry structure for the file link. - * Return 0 if permission is granted. - * @inode_follow_link: - * Check permission to follow a symbolic link when looking up a pathname. - * @dentry contains the dentry structure for the link. - * @inode contains the inode, which itself is not stable in RCU-walk. - * @rcu indicates whether we are in RCU-walk mode. - * Return 0 if permission is granted. - * @inode_permission: - * Check permission before accessing an inode. This hook is called by the - * existing Linux permission function, so a security module can use it to - * provide additional checking for existing Linux permission checks. - * Notice that this hook is called when a file is opened (as well as many - * other operations), whereas the file_security_ops permission hook is - * called when the actual read/write operations are performed. - * @inode contains the inode structure to check. - * @mask contains the permission mask. - * Return 0 if permission is granted. - * @inode_setattr: - * Check permission before setting file attributes. Note that the kernel - * call to notify_change is performed from several locations, whenever - * file attributes change (such as when a file is truncated, chown/chmod - * operations, transferring disk quotas, etc). - * @dentry contains the dentry structure for the file. - * @attr is the iattr structure containing the new file attributes. - * Return 0 if permission is granted. - * @path_truncate: - * Check permission before truncating the file indicated by path. - * Note that truncation permissions may also be checked based on - * already opened files, using the @file_truncate hook. - * @path contains the path structure for the file. - * Return 0 if permission is granted. - * @inode_getattr: - * Check permission before obtaining file attributes. - * @path contains the path structure for the file. - * Return 0 if permission is granted. - * @inode_setxattr: - * Check permission before setting the extended attributes - * @value identified by @name for @dentry. - * Return 0 if permission is granted. - * @inode_post_setxattr: - * Update inode security field after successful setxattr operation. - * @value identified by @name for @dentry. - * @inode_getxattr: - * Check permission before obtaining the extended attributes - * identified by @name for @dentry. - * Return 0 if permission is granted. - * @inode_listxattr: - * Check permission before obtaining the list of extended attribute - * names for @dentry. - * Return 0 if permission is granted. - * @inode_removexattr: - * Check permission before removing the extended attribute - * identified by @name for @dentry. - * Return 0 if permission is granted. - * @inode_set_acl: - * Check permission before setting posix acls - * The posix acls in @kacl are identified by @acl_name. - * Return 0 if permission is granted. - * @inode_get_acl: - * Check permission before getting osix acls - * The posix acls are identified by @acl_name. - * Return 0 if permission is granted. - * @inode_remove_acl: - * Check permission before removing posix acls - * The posix acls are identified by @acl_name. - * Return 0 if permission is granted. - * @inode_getsecurity: - * Retrieve a copy of the extended attribute representation of the - * security label associated with @name for @inode via @buffer. Note that - * @name is the remainder of the attribute name after the security prefix - * has been removed. @alloc is used to specify if the call should return a - * value via the buffer or just the value length. - * Return size of buffer on success. - * @inode_setsecurity: - * Set the security label associated with @name for @inode from the - * extended attribute value @value. @size indicates the size of the - * @value in bytes. @flags may be XATTR_CREATE, XATTR_REPLACE, or 0. - * Note that @name is the remainder of the attribute name after the - * security. prefix has been removed. - * Return 0 on success. - * @inode_listsecurity: - * Copy the extended attribute names for the security labels - * associated with @inode into @buffer. The maximum size of @buffer - * is specified by @buffer_size. @buffer may be NULL to request - * the size of the buffer required. - * Returns number of bytes used/required on success. - * @inode_need_killpriv: - * Called when an inode has been changed. - * @dentry is the dentry being changed. - * Return <0 on error to abort the inode change operation. - * Return 0 if inode_killpriv does not need to be called. - * Return >0 if inode_killpriv does need to be called. - * @inode_killpriv: - * The setuid bit is being removed. Remove similar security labels. - * Called with the dentry->d_inode->i_mutex held. - * @idmap: idmap of the mount. - * @dentry is the dentry being changed. - * Return 0 on success. If error is returned, then the operation - * causing setuid bit removal is failed. - * @inode_getsecid: - * Get the secid associated with the node. - * @inode contains a pointer to the inode. - * @secid contains a pointer to the location where result will be saved. - * In case of failure, @secid will be set to zero. - * @inode_copy_up: - * A file is about to be copied up from lower layer to upper layer of - * overlay filesystem. Security module can prepare a set of new creds - * and modify as need be and return new creds. Caller will switch to - * new creds temporarily to create new file and release newly allocated - * creds. - * @src indicates the union dentry of file that is being copied up. - * @new pointer to pointer to return newly allocated creds. - * Returns 0 on success or a negative error code on error. - * @inode_copy_up_xattr: - * Filter the xattrs being copied up when a unioned file is copied - * up from a lower layer to the union/overlay layer. - * @name indicates the name of the xattr. - * Returns 0 to accept the xattr, 1 to discard the xattr, -EOPNOTSUPP if - * security module does not know about attribute or a negative error code - * to abort the copy up. Note that the caller is responsible for reading - * and writing the xattrs as this hook is merely a filter. - * @d_instantiate: - * Fill in @inode security information for a @dentry if allowed. - * @getprocattr: - * Read attribute @name for process @p and store it into @value if allowed. - * Return the length of @value on success, a negative value otherwise. - * @setprocattr: - * Write (set) attribute @name to @value, size @size if allowed. - * Return written bytes on success, a negative value otherwise. - * * Security hooks for kernfs node operations * * @kernfs_init_security: -- cgit v1.2.3 From 9348944b775d9a12ee7ab698df5bad85409bdd48 Mon Sep 17 00:00:00 2001 From: Paul Moore Date: Fri, 10 Feb 2023 13:20:33 -0500 Subject: lsm: move the kernfs hook comments to security/security.c This patch relocates the LSM hook function comments to the function definitions, in keeping with the current kernel conventions. This should make the hook descriptions more easily discoverable and easier to maintain. While formatting changes have been done to better fit the kernel-doc style, content changes have been kept to a minimum and limited to text which was obviously incorrect and/or outdated. It is expected the future patches will improve the quality of the function header comments. Acked-by: Casey Schaufler Signed-off-by: Paul Moore --- include/linux/lsm_hooks.h | 9 --------- 1 file changed, 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index 3cdd58424796..c953f6c356f2 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -32,15 +32,6 @@ /** * union security_list_options - Linux Security Module hook function list * - * Security hooks for kernfs node operations - * - * @kernfs_init_security: - * Initialize the security context of a newly created kernfs node based - * on its own and its parent's attributes. - * @kn_dir the parent kernfs node. - * @kn the new child kernfs node. - * Return 0 if permission is granted. - * * Security hooks for file operations * * @file_permission: -- cgit v1.2.3 From a0fd6480de489780cdf0940a38bb75b949976d6c Mon Sep 17 00:00:00 2001 From: Paul Moore Date: Fri, 10 Feb 2023 13:23:09 -0500 Subject: lsm: move the file hook comments to security/security.c This patch relocates the LSM hook function comments to the function definitions, in keeping with the current kernel conventions. This should make the hook descriptions more easily discoverable and easier to maintain. While formatting changes have been done to better fit the kernel-doc style, content changes have been kept to a minimum and limited to text which was obviously incorrect and/or outdated. It is expected the future patches will improve the quality of the function header comments. Acked-by: Casey Schaufler Signed-off-by: Paul Moore --- include/linux/lsm_hooks.h | 104 ---------------------------------------------- 1 file changed, 104 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index c953f6c356f2..7c58683b9288 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -32,110 +32,6 @@ /** * union security_list_options - Linux Security Module hook function list * - * Security hooks for file operations - * - * @file_permission: - * Check file permissions before accessing an open file. This hook is - * called by various operations that read or write files. A security - * module can use this hook to perform additional checking on these - * operations, e.g. to revalidate permissions on use to support privilege - * bracketing or policy changes. Notice that this hook is used when the - * actual read/write operations are performed, whereas the - * inode_security_ops hook is called when a file is opened (as well as - * many other operations). - * Caveat: Although this hook can be used to revalidate permissions for - * various system call operations that read or write files, it does not - * address the revalidation of permissions for memory-mapped files. - * Security modules must handle this separately if they need such - * revalidation. - * @file contains the file structure being accessed. - * @mask contains the requested permissions. - * Return 0 if permission is granted. - * @file_alloc_security: - * Allocate and attach a security structure to the file->f_security field. - * The security field is initialized to NULL when the structure is first - * created. - * @file contains the file structure to secure. - * Return 0 if the hook is successful and permission is granted. - * @file_free_security: - * Deallocate and free any security structures stored in file->f_security. - * @file contains the file structure being modified. - * @file_ioctl: - * @file contains the file structure. - * @cmd contains the operation to perform. - * @arg contains the operational arguments. - * Check permission for an ioctl operation on @file. Note that @arg - * sometimes represents a user space pointer; in other cases, it may be a - * simple integer value. When @arg represents a user space pointer, it - * should never be used by the security module. - * Return 0 if permission is granted. - * @mmap_addr: - * Check permissions for a mmap operation at @addr. - * @addr contains virtual address that will be used for the operation. - * Return 0 if permission is granted. - * @mmap_file: - * Check permissions for a mmap operation. The @file may be NULL, e.g. - * if mapping anonymous memory. - * @file contains the file structure for file to map (may be NULL). - * @reqprot contains the protection requested by the application. - * @prot contains the protection that will be applied by the kernel. - * @flags contains the operational flags. - * Return 0 if permission is granted. - * @file_mprotect: - * Check permissions before changing memory access permissions. - * @vma contains the memory region to modify. - * @reqprot contains the protection requested by the application. - * @prot contains the protection that will be applied by the kernel. - * Return 0 if permission is granted. - * @file_lock: - * Check permission before performing file locking operations. - * Note the hook mediates both flock and fcntl style locks. - * @file contains the file structure. - * @cmd contains the posix-translated lock operation to perform - * (e.g. F_RDLCK, F_WRLCK). - * Return 0 if permission is granted. - * @file_fcntl: - * Check permission before allowing the file operation specified by @cmd - * from being performed on the file @file. Note that @arg sometimes - * represents a user space pointer; in other cases, it may be a simple - * integer value. When @arg represents a user space pointer, it should - * never be used by the security module. - * @file contains the file structure. - * @cmd contains the operation to be performed. - * @arg contains the operational arguments. - * Return 0 if permission is granted. - * @file_set_fowner: - * Save owner security information (typically from current->security) in - * file->f_security for later use by the send_sigiotask hook. - * @file contains the file structure to update. - * Return 0 on success. - * @file_send_sigiotask: - * Check permission for the file owner @fown to send SIGIO or SIGURG to the - * process @tsk. Note that this hook is sometimes called from interrupt. - * Note that the fown_struct, @fown, is never outside the context of a - * struct file, so the file structure (and associated security information) - * can always be obtained: container_of(fown, struct file, f_owner) - * @tsk contains the structure of task receiving signal. - * @fown contains the file owner information. - * @sig is the signal that will be sent. When 0, kernel sends SIGIO. - * Return 0 if permission is granted. - * @file_receive: - * This hook allows security modules to control the ability of a process - * to receive an open file descriptor via socket IPC. - * @file contains the file structure being received. - * Return 0 if permission is granted. - * @file_truncate: - * Check permission before truncating a file, i.e. using ftruncate. - * Note that truncation permission may also be checked based on the path, - * using the @path_truncate hook. - * @file contains the file structure for the file. - * Return 0 if permission is granted. - * @file_open: - * Save open-time permission checking state for later use upon - * file_permission, and recheck access if anything has changed - * since inode_permission. - * Return 0 if permission is granted. - * * Security hooks for task operations. * * @task_alloc: -- cgit v1.2.3 From 130c53bfee4bc70919d356bd8b30137ba4d665b1 Mon Sep 17 00:00:00 2001 From: Paul Moore Date: Sat, 11 Feb 2023 19:27:58 -0500 Subject: lsm: move the task hook comments to security/security.c This patch relocates the LSM hook function comments to the function definitions, in keeping with the current kernel conventions. This should make the hook descriptions more easily discoverable and easier to maintain. While formatting changes have been done to better fit the kernel-doc style, content changes have been kept to a minimum and limited to text which was obviously incorrect and/or outdated. It is expected the future patches will improve the quality of the function header comments. Acked-by: Casey Schaufler Signed-off-by: Paul Moore --- include/linux/lsm_hooks.h | 210 ---------------------------------------------- 1 file changed, 210 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index 7c58683b9288..5578a13729bd 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -32,216 +32,6 @@ /** * union security_list_options - Linux Security Module hook function list * - * Security hooks for task operations. - * - * @task_alloc: - * @task task being allocated. - * @clone_flags contains the flags indicating what should be shared. - * Handle allocation of task-related resources. - * Returns a zero on success, negative values on failure. - * @task_free: - * @task task about to be freed. - * Handle release of task-related resources. (Note that this can be called - * from interrupt context.) - * @cred_alloc_blank: - * @cred points to the credentials. - * @gfp indicates the atomicity of any memory allocations. - * Only allocate sufficient memory and attach to @cred such that - * cred_transfer() will not get ENOMEM. - * Return 0 on success, negative values on failure. - * @cred_free: - * @cred points to the credentials. - * Deallocate and clear the cred->security field in a set of credentials. - * @cred_prepare: - * @new points to the new credentials. - * @old points to the original credentials. - * @gfp indicates the atomicity of any memory allocations. - * Prepare a new set of credentials by copying the data from the old set. - * Return 0 on success, negative values on failure. - * @cred_transfer: - * @new points to the new credentials. - * @old points to the original credentials. - * Transfer data from original creds to new creds - * @cred_getsecid: - * Retrieve the security identifier of the cred structure @c - * @c contains the credentials, secid will be placed into @secid. - * In case of failure, @secid will be set to zero. - * @kernel_act_as: - * Set the credentials for a kernel service to act as (subjective context). - * @new points to the credentials to be modified. - * @secid specifies the security ID to be set. - * The current task must be the one that nominated @secid. - * Return 0 if successful. - * @kernel_create_files_as: - * Set the file creation context in a set of credentials to be the same as - * the objective context of the specified inode. - * @new points to the credentials to be modified. - * @inode points to the inode to use as a reference. - * The current task must be the one that nominated @inode. - * Return 0 if successful. - * @kernel_module_request: - * Ability to trigger the kernel to automatically upcall to userspace for - * userspace to load a kernel module with the given name. - * @kmod_name name of the module requested by the kernel. - * Return 0 if successful. - * @kernel_load_data: - * Load data provided by userspace. - * @id kernel load data identifier. - * @contents if a subsequent @kernel_post_load_data will be called. - * Return 0 if permission is granted. - * @kernel_post_load_data: - * Load data provided by a non-file source (usually userspace buffer). - * @buf pointer to buffer containing the data contents. - * @size length of the data contents. - * @id kernel load data identifier. - * @description a text description of what was loaded, @id-specific. - * Return 0 if permission is granted. - * This must be paired with a prior @kernel_load_data call that had - * @contents set to true. - * @kernel_read_file: - * Read a file specified by userspace. - * @file contains the file structure pointing to the file being read - * by the kernel. - * @id kernel read file identifier. - * @contents if a subsequent @kernel_post_read_file will be called. - * Return 0 if permission is granted. - * @kernel_post_read_file: - * Read a file specified by userspace. - * @file contains the file structure pointing to the file being read - * by the kernel. - * @buf pointer to buffer containing the file contents. - * @size length of the file contents. - * @id kernel read file identifier. - * This must be paired with a prior @kernel_read_file call that had - * @contents set to true. - * Return 0 if permission is granted. - * @task_fix_setuid: - * Update the module's state after setting one or more of the user - * identity attributes of the current process. The @flags parameter - * indicates which of the set*uid system calls invoked this hook. If - * @new is the set of credentials that will be installed. Modifications - * should be made to this rather than to @current->cred. - * @old is the set of credentials that are being replaced. - * @flags contains one of the LSM_SETID_* values. - * Return 0 on success. - * @task_fix_setgid: - * Update the module's state after setting one or more of the group - * identity attributes of the current process. The @flags parameter - * indicates which of the set*gid system calls invoked this hook. - * @new is the set of credentials that will be installed. Modifications - * should be made to this rather than to @current->cred. - * @old is the set of credentials that are being replaced. - * @flags contains one of the LSM_SETID_* values. - * Return 0 on success. - * @task_fix_setgroups: - * Update the module's state after setting the supplementary group - * identity attributes of the current process. - * @new is the set of credentials that will be installed. Modifications - * should be made to this rather than to @current->cred. - * @old is the set of credentials that are being replaced. - * Return 0 on success. - * @task_setpgid: - * Check permission before setting the process group identifier of the - * process @p to @pgid. - * @p contains the task_struct for process being modified. - * @pgid contains the new pgid. - * Return 0 if permission is granted. - * @task_getpgid: - * Check permission before getting the process group identifier of the - * process @p. - * @p contains the task_struct for the process. - * Return 0 if permission is granted. - * @task_getsid: - * Check permission before getting the session identifier of the process - * @p. - * @p contains the task_struct for the process. - * Return 0 if permission is granted. - * @current_getsecid_subj: - * Retrieve the subjective security identifier of the current task and - * return it in @secid. - * In case of failure, @secid will be set to zero. - * @task_getsecid_obj: - * Retrieve the objective security identifier of the task_struct in @p - * and return it in @secid. - * In case of failure, @secid will be set to zero. - * - * @task_setnice: - * Check permission before setting the nice value of @p to @nice. - * @p contains the task_struct of process. - * @nice contains the new nice value. - * Return 0 if permission is granted. - * @task_setioprio: - * Check permission before setting the ioprio value of @p to @ioprio. - * @p contains the task_struct of process. - * @ioprio contains the new ioprio value. - * Return 0 if permission is granted. - * @task_getioprio: - * Check permission before getting the ioprio value of @p. - * @p contains the task_struct of process. - * Return 0 if permission is granted. - * @task_prlimit: - * Check permission before getting and/or setting the resource limits of - * another task. - * @cred points to the cred structure for the current task. - * @tcred points to the cred structure for the target task. - * @flags contains the LSM_PRLIMIT_* flag bits indicating whether the - * resource limits are being read, modified, or both. - * Return 0 if permission is granted. - * @task_setrlimit: - * Check permission before setting the resource limits of process @p - * for @resource to @new_rlim. The old resource limit values can - * be examined by dereferencing (p->signal->rlim + resource). - * @p points to the task_struct for the target task's group leader. - * @resource contains the resource whose limit is being set. - * @new_rlim contains the new limits for @resource. - * Return 0 if permission is granted. - * @task_setscheduler: - * Check permission before setting scheduling policy and/or parameters of - * process @p. - * @p contains the task_struct for process. - * Return 0 if permission is granted. - * @task_getscheduler: - * Check permission before obtaining scheduling information for process - * @p. - * @p contains the task_struct for process. - * Return 0 if permission is granted. - * @task_movememory: - * Check permission before moving memory owned by process @p. - * @p contains the task_struct for process. - * Return 0 if permission is granted. - * @task_kill: - * Check permission before sending signal @sig to @p. @info can be NULL, - * the constant 1, or a pointer to a kernel_siginfo structure. If @info is 1 or - * SI_FROMKERNEL(info) is true, then the signal should be viewed as coming - * from the kernel and should typically be permitted. - * SIGIO signals are handled separately by the send_sigiotask hook in - * file_security_ops. - * @p contains the task_struct for process. - * @info contains the signal information. - * @sig contains the signal value. - * @cred contains the cred of the process where the signal originated, or - * NULL if the current task is the originator. - * Return 0 if permission is granted. - * @task_prctl: - * Check permission before performing a process control operation on the - * current process. - * @option contains the operation. - * @arg2 contains a argument. - * @arg3 contains a argument. - * @arg4 contains a argument. - * @arg5 contains a argument. - * Return -ENOSYS if no-one wanted to handle this op, any other value to - * cause prctl() to return immediately with that value. - * @task_to_inode: - * Set the security attributes for an inode based on an associated task's - * security attributes, e.g. for /proc/pid inodes. - * @p contains the task_struct for the task. - * @inode contains the inode structure for the inode. - * @userns_create: - * Check permission prior to creating a new user namespace. - * @cred points to prepared creds. - * Return 0 if successful, otherwise < 0 error code. - * * Security hooks for Netlink messaging. * * @netlink_send: -- cgit v1.2.3 From 2bcf51bf2f03cc9fccd3316d361cdf9695fccd11 Mon Sep 17 00:00:00 2001 From: Paul Moore Date: Sun, 12 Feb 2023 15:06:59 -0500 Subject: lsm: move the netlink hook comments to security/security.c This patch relocates the LSM hook function comments to the function definitions, in keeping with the current kernel conventions. This should make the hook descriptions more easily discoverable and easier to maintain. While formatting changes have been done to better fit the kernel-doc style, content changes have been kept to a minimum and limited to text which was obviously incorrect and/or outdated. It is expected the future patches will improve the quality of the function header comments. Acked-by: Casey Schaufler Signed-off-by: Paul Moore --- include/linux/lsm_hooks.h | 13 ------------- 1 file changed, 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index 5578a13729bd..ba2daec1bc35 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -32,19 +32,6 @@ /** * union security_list_options - Linux Security Module hook function list * - * Security hooks for Netlink messaging. - * - * @netlink_send: - * Save security information for a netlink message so that permission - * checking can be performed when the message is processed. The security - * information can be saved using the eff_cap field of the - * netlink_skb_parms structure. Also may be used to provide fine - * grained control over message transmission. - * @sk associated sock of task sending the message. - * @skb contains the sk_buff structure for the netlink message. - * Return 0 if the information was successfully saved and message - * is allowed to be transmitted. - * * Security hooks for Unix domain networking. * * @unix_stream_connect: -- cgit v1.2.3 From 2c2442fd46cd162c0b6a07b4560095f03bd3275f Mon Sep 17 00:00:00 2001 From: Paul Moore Date: Sun, 12 Feb 2023 15:10:23 -0500 Subject: lsm: move the AF_UNIX hook comments to security/security.c This patch relocates the LSM hook function comments to the function definitions, in keeping with the current kernel conventions. This should make the hook descriptions more easily discoverable and easier to maintain. While formatting changes have been done to better fit the kernel-doc style, content changes have been kept to a minimum and limited to text which was obviously incorrect and/or outdated. It is expected the future patches will improve the quality of the function header comments. Acked-by: Casey Schaufler Signed-off-by: Paul Moore --- include/linux/lsm_hooks.h | 26 -------------------------- 1 file changed, 26 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index ba2daec1bc35..1fc1e2aa7d01 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -32,32 +32,6 @@ /** * union security_list_options - Linux Security Module hook function list * - * Security hooks for Unix domain networking. - * - * @unix_stream_connect: - * Check permissions before establishing a Unix domain stream connection - * between @sock and @other. - * @sock contains the sock structure. - * @other contains the peer sock structure. - * @newsk contains the new sock structure. - * Return 0 if permission is granted. - * @unix_may_send: - * Check permissions before connecting or sending datagrams from @sock to - * @other. - * @sock contains the socket structure. - * @other contains the peer socket structure. - * Return 0 if permission is granted. - * - * The @unix_stream_connect and @unix_may_send hooks were necessary because - * Linux provides an alternative to the conventional file name space for Unix - * domain sockets. Whereas binding and connecting to sockets in the file name - * space is mediated by the typical file permissions (and caught by the mknod - * and permission hooks in inode_security_ops), binding and connecting to - * sockets in the abstract name space is completely unmediated. Sufficient - * control of Unix domain sockets in the abstract name space isn't possible - * using only the socket layer hooks, since we need to know the actual target - * socket, which is not looked up until we are inside the af_unix code. - * * Security hooks for socket operations. * * @socket_create: -- cgit v1.2.3 From 6b6bbe8c02a1bc7ef7f0aa490a3601a16cd145fe Mon Sep 17 00:00:00 2001 From: Paul Moore Date: Sun, 12 Feb 2023 15:15:29 -0500 Subject: lsm: move the socket hook comments to security/security.c This patch relocates the LSM hook function comments to the function definitions, in keeping with the current kernel conventions. This should make the hook descriptions more easily discoverable and easier to maintain. While formatting changes have been done to better fit the kernel-doc style, content changes have been kept to a minimum and limited to text which was obviously incorrect and/or outdated. It is expected the future patches will improve the quality of the function header comments. Acked-by: Casey Schaufler Signed-off-by: Paul Moore --- include/linux/lsm_hooks.h | 191 ---------------------------------------------- 1 file changed, 191 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index 1fc1e2aa7d01..531d141083ed 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -32,197 +32,6 @@ /** * union security_list_options - Linux Security Module hook function list * - * Security hooks for socket operations. - * - * @socket_create: - * Check permissions prior to creating a new socket. - * @family contains the requested protocol family. - * @type contains the requested communications type. - * @protocol contains the requested protocol. - * @kern set to 1 if a kernel socket. - * Return 0 if permission is granted. - * @socket_post_create: - * This hook allows a module to update or allocate a per-socket security - * structure. Note that the security field was not added directly to the - * socket structure, but rather, the socket security information is stored - * in the associated inode. Typically, the inode alloc_security hook will - * allocate and attach security information to - * SOCK_INODE(sock)->i_security. This hook may be used to update the - * SOCK_INODE(sock)->i_security field with additional information that - * wasn't available when the inode was allocated. - * @sock contains the newly created socket structure. - * @family contains the requested protocol family. - * @type contains the requested communications type. - * @protocol contains the requested protocol. - * @kern set to 1 if a kernel socket. - * Return 0 if permission is granted. - * @socket_socketpair: - * Check permissions before creating a fresh pair of sockets. - * @socka contains the first socket structure. - * @sockb contains the second socket structure. - * Return 0 if permission is granted and the connection was established. - * @socket_bind: - * Check permission before socket protocol layer bind operation is - * performed and the socket @sock is bound to the address specified in the - * @address parameter. - * @sock contains the socket structure. - * @address contains the address to bind to. - * @addrlen contains the length of address. - * Return 0 if permission is granted. - * @socket_connect: - * Check permission before socket protocol layer connect operation - * attempts to connect socket @sock to a remote address, @address. - * @sock contains the socket structure. - * @address contains the address of remote endpoint. - * @addrlen contains the length of address. - * Return 0 if permission is granted. - * @socket_listen: - * Check permission before socket protocol layer listen operation. - * @sock contains the socket structure. - * @backlog contains the maximum length for the pending connection queue. - * Return 0 if permission is granted. - * @socket_accept: - * Check permission before accepting a new connection. Note that the new - * socket, @newsock, has been created and some information copied to it, - * but the accept operation has not actually been performed. - * @sock contains the listening socket structure. - * @newsock contains the newly created server socket for connection. - * Return 0 if permission is granted. - * @socket_sendmsg: - * Check permission before transmitting a message to another socket. - * @sock contains the socket structure. - * @msg contains the message to be transmitted. - * @size contains the size of message. - * Return 0 if permission is granted. - * @socket_recvmsg: - * Check permission before receiving a message from a socket. - * @sock contains the socket structure. - * @msg contains the message structure. - * @size contains the size of message structure. - * @flags contains the operational flags. - * Return 0 if permission is granted. - * @socket_getsockname: - * Check permission before the local address (name) of the socket object - * @sock is retrieved. - * @sock contains the socket structure. - * Return 0 if permission is granted. - * @socket_getpeername: - * Check permission before the remote address (name) of a socket object - * @sock is retrieved. - * @sock contains the socket structure. - * Return 0 if permission is granted. - * @socket_getsockopt: - * Check permissions before retrieving the options associated with socket - * @sock. - * @sock contains the socket structure. - * @level contains the protocol level to retrieve option from. - * @optname contains the name of option to retrieve. - * Return 0 if permission is granted. - * @socket_setsockopt: - * Check permissions before setting the options associated with socket - * @sock. - * @sock contains the socket structure. - * @level contains the protocol level to set options for. - * @optname contains the name of the option to set. - * Return 0 if permission is granted. - * @socket_shutdown: - * Checks permission before all or part of a connection on the socket - * @sock is shut down. - * @sock contains the socket structure. - * @how contains the flag indicating how future sends and receives - * are handled. - * Return 0 if permission is granted. - * @socket_sock_rcv_skb: - * Check permissions on incoming network packets. This hook is distinct - * from Netfilter's IP input hooks since it is the first time that the - * incoming sk_buff @skb has been associated with a particular socket, @sk. - * Must not sleep inside this hook because some callers hold spinlocks. - * @sk contains the sock (not socket) associated with the incoming sk_buff. - * @skb contains the incoming network data. - * Return 0 if permission is granted. - * @socket_getpeersec_stream: - * This hook allows the security module to provide peer socket security - * state for unix or connected tcp sockets to userspace via getsockopt - * SO_GETPEERSEC. For tcp sockets this can be meaningful if the - * socket is associated with an ipsec SA. - * @sock is the local socket. - * @optval memory where the security state is to be copied. - * @optlen memory where the module should copy the actual length - * of the security state. - * @len as input is the maximum length to copy to userspace provided - * by the caller. - * Return 0 if all is well, otherwise, typical getsockopt return - * values. - * @socket_getpeersec_dgram: - * This hook allows the security module to provide peer socket security - * state for udp sockets on a per-packet basis to userspace via - * getsockopt SO_GETPEERSEC. The application must first have indicated - * the IP_PASSSEC option via getsockopt. It can then retrieve the - * security state returned by this hook for a packet via the SCM_SECURITY - * ancillary message type. - * @sock contains the peer socket. May be NULL. - * @skb is the sk_buff for the packet being queried. May be NULL. - * @secid pointer to store the secid of the packet. - * Return 0 on success, error on failure. - * @sk_alloc_security: - * Allocate and attach a security structure to the sk->sk_security field, - * which is used to copy security attributes between local stream sockets. - * Return 0 on success, error on failure. - * @sk_free_security: - * Deallocate security structure. - * @sk_clone_security: - * Clone/copy security structure. - * @sk_getsecid: - * Retrieve the LSM-specific secid for the sock to enable caching - * of network authorizations. - * @sock_graft: - * Sets the socket's isec sid to the sock's sid. - * @inet_conn_request: - * Sets the openreq's sid to socket's sid with MLS portion taken - * from peer sid. - * Return 0 if permission is granted. - * @inet_csk_clone: - * Sets the new child socket's sid to the openreq sid. - * @inet_conn_established: - * Sets the connection's peersid to the secmark on skb. - * @secmark_relabel_packet: - * Check if the process should be allowed to relabel packets to - * the given secid. - * Return 0 if permission is granted. - * @secmark_refcount_inc: - * Tells the LSM to increment the number of secmark labeling rules loaded. - * @secmark_refcount_dec: - * Tells the LSM to decrement the number of secmark labeling rules loaded. - * @req_classify_flow: - * Sets the flow's sid to the openreq sid. - * @tun_dev_alloc_security: - * This hook allows a module to allocate a security structure for a TUN - * device. - * @security pointer to a security structure pointer. - * Returns a zero on success, negative values on failure. - * @tun_dev_free_security: - * This hook allows a module to free the security structure for a TUN - * device. - * @security pointer to the TUN device's security structure. - * @tun_dev_create: - * Check permissions prior to creating a new TUN device. - * Return 0 if permission is granted. - * @tun_dev_attach_queue: - * Check permissions prior to attaching to a TUN device queue. - * @security pointer to the TUN device's security structure. - * Return 0 if permission is granted. - * @tun_dev_attach: - * This hook can be used by the module to update any security state - * associated with the TUN device's sock structure. - * @sk contains the existing sock structure. - * @security pointer to the TUN device's security structure. - * Return 0 if permission is granted. - * @tun_dev_open: - * This hook can be used by the module to update any security state - * associated with the TUN device's security structure. - * @security pointer to the TUN devices's security structure. - * Return 0 if permission is granted. - * * Security hooks for SCTP * * @sctp_assoc_request: -- cgit v1.2.3 From 4a49f592e931962ab3feb9fbb43bea719517670d Mon Sep 17 00:00:00 2001 From: Paul Moore Date: Wed, 15 Feb 2023 17:47:10 -0500 Subject: lsm: move the SCTP hook comments to security/security.c This patch relocates the LSM hook function comments to the function definitions, in keeping with the current kernel conventions. This should make the hook descriptions more easily discoverable and easier to maintain. While formatting changes have been done to better fit the kernel-doc style, content changes have been kept to a minimum and limited to text which was obviously incorrect and/or outdated. It is expected the future patches will improve the quality of the function header comments. Acked-by: Casey Schaufler Signed-off-by: Paul Moore --- include/linux/lsm_hooks.h | 33 --------------------------------- 1 file changed, 33 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index 531d141083ed..bb460e0b1ff2 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -32,39 +32,6 @@ /** * union security_list_options - Linux Security Module hook function list * - * Security hooks for SCTP - * - * @sctp_assoc_request: - * Passes the @asoc and @chunk->skb of the association INIT packet to - * the security module. - * @asoc pointer to sctp association structure. - * @skb pointer to skbuff of association packet. - * Return 0 on success, error on failure. - * @sctp_bind_connect: - * Validiate permissions required for each address associated with sock - * @sk. Depending on @optname, the addresses will be treated as either - * for a connect or bind service. The @addrlen is calculated on each - * ipv4 and ipv6 address using sizeof(struct sockaddr_in) or - * sizeof(struct sockaddr_in6). - * @sk pointer to sock structure. - * @optname name of the option to validate. - * @address list containing one or more ipv4/ipv6 addresses. - * @addrlen total length of address(s). - * Return 0 on success, error on failure. - * @sctp_sk_clone: - * Called whenever a new socket is created by accept(2) (i.e. a TCP - * style socket) or when a socket is 'peeled off' e.g userspace - * calls sctp_peeloff(3). - * @asoc pointer to current sctp association structure. - * @sk pointer to current sock structure. - * @newsk pointer to new sock structure. - * @sctp_assoc_established: - * Passes the @asoc and @chunk->skb of the association COOKIE_ACK packet - * to the security module. - * @asoc pointer to sctp association structure. - * @skb pointer to skbuff of association packet. - * Return 0 if permission is granted. - * * Security hooks for Infiniband * * @ib_pkey_access: -- cgit v1.2.3 From ac318aed54987e6bd52dba90dd2ea3dca725b5c0 Mon Sep 17 00:00:00 2001 From: Paul Moore Date: Wed, 15 Feb 2023 18:07:41 -0500 Subject: lsm: move the Infiniband hook comments to security/security.c This patch relocates the LSM hook function comments to the function definitions, in keeping with the current kernel conventions. This should make the hook descriptions more easily discoverable and easier to maintain. While formatting changes have been done to better fit the kernel-doc style, content changes have been kept to a minimum and limited to text which was obviously incorrect and/or outdated. It is expected the future patches will improve the quality of the function header comments. Acked-by: Casey Schaufler Signed-off-by: Paul Moore --- include/linux/lsm_hooks.h | 22 ---------------------- 1 file changed, 22 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index bb460e0b1ff2..9fc6417af980 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -32,28 +32,6 @@ /** * union security_list_options - Linux Security Module hook function list * - * Security hooks for Infiniband - * - * @ib_pkey_access: - * Check permission to access a pkey when modifing a QP. - * @subnet_prefix the subnet prefix of the port being used. - * @pkey the pkey to be accessed. - * @sec pointer to a security structure. - * Return 0 if permission is granted. - * @ib_endport_manage_subnet: - * Check permissions to send and receive SMPs on a end port. - * @dev_name the IB device name (i.e. mlx4_0). - * @port_num the port number. - * @sec pointer to a security structure. - * Return 0 if permission is granted. - * @ib_alloc_security: - * Allocate a security structure for Infiniband objects. - * @sec pointer to a security structure pointer. - * Returns 0 on success, non-zero on failure. - * @ib_free_security: - * Deallocate an Infiniband security structure. - * @sec contains the security structure to be freed. - * * Security hooks for XFRM operations. * * @xfrm_policy_alloc_security: -- cgit v1.2.3 From 742b99456e86aa3e9176fb1c7db200101876c614 Mon Sep 17 00:00:00 2001 From: Paul Moore Date: Wed, 15 Feb 2023 18:14:01 -0500 Subject: lsm: move the xfrm hook comments to security/security.c This patch relocates the LSM hook function comments to the function definitions, in keeping with the current kernel conventions. This should make the hook descriptions more easily discoverable and easier to maintain. While formatting changes have been done to better fit the kernel-doc style, content changes have been kept to a minimum and limited to text which was obviously incorrect and/or outdated. It is expected the future patches will improve the quality of the function header comments. Acked-by: Casey Schaufler Signed-off-by: Paul Moore --- include/linux/lsm_hooks.h | 73 ----------------------------------------------- 1 file changed, 73 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index 9fc6417af980..9c5254e4e9d1 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -32,79 +32,6 @@ /** * union security_list_options - Linux Security Module hook function list * - * Security hooks for XFRM operations. - * - * @xfrm_policy_alloc_security: - * @ctxp is a pointer to the xfrm_sec_ctx being added to Security Policy - * Database used by the XFRM system. - * @sec_ctx contains the security context information being provided by - * the user-level policy update program (e.g., setkey). - * @gfp is to specify the context for the allocation. - * Allocate a security structure to the xp->security field; the security - * field is initialized to NULL when the xfrm_policy is allocated. - * Return 0 if operation was successful (memory to allocate, legal - * context). - * @xfrm_policy_clone_security: - * @old_ctx contains an existing xfrm_sec_ctx. - * @new_ctxp contains a new xfrm_sec_ctx being cloned from old. - * Allocate a security structure in new_ctxp that contains the - * information from the old_ctx structure. - * Return 0 if operation was successful (memory to allocate). - * @xfrm_policy_free_security: - * @ctx contains the xfrm_sec_ctx. - * Deallocate xp->security. - * @xfrm_policy_delete_security: - * @ctx contains the xfrm_sec_ctx. - * Authorize deletion of xp->security. - * Return 0 if permission is granted. - * @xfrm_state_alloc: - * @x contains the xfrm_state being added to the Security Association - * Database by the XFRM system. - * @sec_ctx contains the security context information being provided by - * the user-level SA generation program (e.g., setkey or racoon). - * Allocate a security structure to the x->security field; the security - * field is initialized to NULL when the xfrm_state is allocated. Set the - * context to correspond to sec_ctx. Return 0 if operation was successful - * (memory to allocate, legal context). - * @xfrm_state_alloc_acquire: - * @x contains the xfrm_state being added to the Security Association - * Database by the XFRM system. - * @polsec contains the policy's security context. - * @secid contains the secid from which to take the mls portion of the - * context. - * Allocate a security structure to the x->security field; the security - * field is initialized to NULL when the xfrm_state is allocated. Set the - * context to correspond to secid. Return 0 if operation was successful - * (memory to allocate, legal context). - * @xfrm_state_free_security: - * @x contains the xfrm_state. - * Deallocate x->security. - * @xfrm_state_delete_security: - * @x contains the xfrm_state. - * Authorize deletion of x->security. - * Return 0 if permission is granted. - * @xfrm_policy_lookup: - * @ctx contains the xfrm_sec_ctx for which the access control is being - * checked. - * @fl_secid contains the flow security label that is used to authorize - * access to the policy xp. - * @dir contains the direction of the flow (input or output). - * Check permission when a flow selects a xfrm_policy for processing - * XFRMs on a packet. The hook is called when selecting either a - * per-socket policy or a generic xfrm policy. - * Return 0 if permission is granted, -ESRCH otherwise, or -errno - * on other errors. - * @xfrm_state_pol_flow_match: - * @x contains the state to match. - * @xp contains the policy to check for a match. - * @flic contains the flowi_common struct to check for a match. - * Return 1 if there is a match. - * @xfrm_decode_session: - * @skb points to skb to decode. - * @secid points to the flow key secid to set. - * @ckall says if all xfrms used should be checked for same secid. - * Return 0 if ckall is zero or all xfrms used have the same secid. - * * Security hooks affecting all Key Management operations * * @key_alloc: -- cgit v1.2.3 From ecc419a4453530c410c7031bc69ef34782b1c8ff Mon Sep 17 00:00:00 2001 From: Paul Moore Date: Wed, 15 Feb 2023 21:46:31 -0500 Subject: lsm: move the key hook comments to security/security.c This patch relocates the LSM hook function comments to the function definitions, in keeping with the current kernel conventions. This should make the hook descriptions more easily discoverable and easier to maintain. While formatting changes have been done to better fit the kernel-doc style, content changes have been kept to a minimum and limited to text which was obviously incorrect and/or outdated. It is expected the future patches will improve the quality of the function header comments. Acked-by: Casey Schaufler Signed-off-by: Paul Moore --- include/linux/lsm_hooks.h | 32 -------------------------------- 1 file changed, 32 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index 9c5254e4e9d1..2cfa56e3abc3 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -32,38 +32,6 @@ /** * union security_list_options - Linux Security Module hook function list * - * Security hooks affecting all Key Management operations - * - * @key_alloc: - * Permit allocation of a key and assign security data. Note that key does - * not have a serial number assigned at this point. - * @key points to the key. - * @flags is the allocation flags. - * Return 0 if permission is granted, -ve error otherwise. - * @key_free: - * Notification of destruction; free security data. - * @key points to the key. - * No return value. - * @key_permission: - * See whether a specific operational right is granted to a process on a - * key. - * @key_ref refers to the key (key pointer + possession attribute bit). - * @cred points to the credentials to provide the context against which to - * evaluate the security data on the key. - * @perm describes the combination of permissions required of this key. - * Return 0 if permission is granted, -ve error otherwise. - * @key_getsecurity: - * Get a textual representation of the security context attached to a key - * for the purposes of honouring KEYCTL_GETSECURITY. This function - * allocates the storage for the NUL-terminated string and the caller - * should free it. - * @key points to the key to be queried. - * @_buffer points to a pointer that should be set to point to the - * resulting string (if no label or an error occurs). - * Return the length of the string (including terminating NUL) or -ve if - * an error. - * May also return 0 (and a NULL buffer pointer) if there is no label. - * * Security hooks affecting all System V IPC operations. * * @ipc_permission: -- cgit v1.2.3 From 43fad282187695e25c51425ee9f5f9f08fe5e15d Mon Sep 17 00:00:00 2001 From: Paul Moore Date: Thu, 16 Feb 2023 11:53:49 -0500 Subject: lsm: move the sysv hook comments to security/security.c This patch relocates the LSM hook function comments to the function definitions, in keeping with the current kernel conventions. This should make the hook descriptions more easily discoverable and easier to maintain. While formatting changes have been done to better fit the kernel-doc style, content changes have been kept to a minimum and limited to text which was obviously incorrect and/or outdated. It is expected the future patches will improve the quality of the function header comments. Acked-by: Casey Schaufler Signed-off-by: Paul Moore --- include/linux/lsm_hooks.h | 141 ---------------------------------------------- 1 file changed, 141 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index 2cfa56e3abc3..f6679fead627 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -32,147 +32,6 @@ /** * union security_list_options - Linux Security Module hook function list * - * Security hooks affecting all System V IPC operations. - * - * @ipc_permission: - * Check permissions for access to IPC - * @ipcp contains the kernel IPC permission structure. - * @flag contains the desired (requested) permission set. - * Return 0 if permission is granted. - * @ipc_getsecid: - * Get the secid associated with the ipc object. - * @ipcp contains the kernel IPC permission structure. - * @secid contains a pointer to the location where result will be saved. - * In case of failure, @secid will be set to zero. - * - * Security hooks for individual messages held in System V IPC message queues - * - * @msg_msg_alloc_security: - * Allocate and attach a security structure to the msg->security field. - * The security field is initialized to NULL when the structure is first - * created. - * @msg contains the message structure to be modified. - * Return 0 if operation was successful and permission is granted. - * @msg_msg_free_security: - * Deallocate the security structure for this message. - * @msg contains the message structure to be modified. - * - * Security hooks for System V IPC Message Queues - * - * @msg_queue_alloc_security: - * Allocate and attach a security structure to the - * @perm->security field. The security field is initialized to - * NULL when the structure is first created. - * @perm contains the IPC permissions of the message queue. - * Return 0 if operation was successful and permission is granted. - * @msg_queue_free_security: - * Deallocate security field @perm->security for the message queue. - * @perm contains the IPC permissions of the message queue. - * @msg_queue_associate: - * Check permission when a message queue is requested through the - * msgget system call. This hook is only called when returning the - * message queue identifier for an existing message queue, not when a - * new message queue is created. - * @perm contains the IPC permissions of the message queue. - * @msqflg contains the operation control flags. - * Return 0 if permission is granted. - * @msg_queue_msgctl: - * Check permission when a message control operation specified by @cmd - * is to be performed on the message queue with permissions @perm. - * The @perm may be NULL, e.g. for IPC_INFO or MSG_INFO. - * @perm contains the IPC permissions of the msg queue. May be NULL. - * @cmd contains the operation to be performed. - * Return 0 if permission is granted. - * @msg_queue_msgsnd: - * Check permission before a message, @msg, is enqueued on the message - * queue with permissions @perm. - * @perm contains the IPC permissions of the message queue. - * @msg contains the message to be enqueued. - * @msqflg contains operational flags. - * Return 0 if permission is granted. - * @msg_queue_msgrcv: - * Check permission before a message, @msg, is removed from the message - * queue. The @target task structure contains a pointer to the - * process that will be receiving the message (not equal to the current - * process when inline receives are being performed). - * @perm contains the IPC permissions of the message queue. - * @msg contains the message destination. - * @target contains the task structure for recipient process. - * @type contains the type of message requested. - * @mode contains the operational flags. - * Return 0 if permission is granted. - * - * Security hooks for System V Shared Memory Segments - * - * @shm_alloc_security: - * Allocate and attach a security structure to the @perm->security - * field. The security field is initialized to NULL when the structure is - * first created. - * @perm contains the IPC permissions of the shared memory structure. - * Return 0 if operation was successful and permission is granted. - * @shm_free_security: - * Deallocate the security structure @perm->security for the memory segment. - * @perm contains the IPC permissions of the shared memory structure. - * @shm_associate: - * Check permission when a shared memory region is requested through the - * shmget system call. This hook is only called when returning the shared - * memory region identifier for an existing region, not when a new shared - * memory region is created. - * @perm contains the IPC permissions of the shared memory structure. - * @shmflg contains the operation control flags. - * Return 0 if permission is granted. - * @shm_shmctl: - * Check permission when a shared memory control operation specified by - * @cmd is to be performed on the shared memory region with permissions @perm. - * The @perm may be NULL, e.g. for IPC_INFO or SHM_INFO. - * @perm contains the IPC permissions of the shared memory structure. - * @cmd contains the operation to be performed. - * Return 0 if permission is granted. - * @shm_shmat: - * Check permissions prior to allowing the shmat system call to attach the - * shared memory segment with permissions @perm to the data segment of the - * calling process. The attaching address is specified by @shmaddr. - * @perm contains the IPC permissions of the shared memory structure. - * @shmaddr contains the address to attach memory region to. - * @shmflg contains the operational flags. - * Return 0 if permission is granted. - * - * Security hooks for System V Semaphores - * - * @sem_alloc_security: - * Allocate and attach a security structure to the @perm->security - * field. The security field is initialized to NULL when the structure is - * first created. - * @perm contains the IPC permissions of the semaphore. - * Return 0 if operation was successful and permission is granted. - * @sem_free_security: - * Deallocate security structure @perm->security for the semaphore. - * @perm contains the IPC permissions of the semaphore. - * @sem_associate: - * Check permission when a semaphore is requested through the semget - * system call. This hook is only called when returning the semaphore - * identifier for an existing semaphore, not when a new one must be - * created. - * @perm contains the IPC permissions of the semaphore. - * @semflg contains the operation control flags. - * Return 0 if permission is granted. - * @sem_semctl: - * Check permission when a semaphore operation specified by @cmd is to be - * performed on the semaphore. The @perm may be NULL, e.g. for - * IPC_INFO or SEM_INFO. - * @perm contains the IPC permissions of the semaphore. May be NULL. - * @cmd contains the operation to be performed. - * Return 0 if permission is granted. - * @sem_semop: - * Check permissions before performing operations on members of the - * semaphore set. If the @alter flag is nonzero, the semaphore set - * may be modified. - * @perm contains the IPC permissions of the semaphore. - * @sops contains the operations to perform. - * @nsops contains the number of operations to perform. - * @alter contains the flag indicating whether changes are to be made. - * Return 0 if permission is granted. - * * @binder_set_context_mgr: * Check whether @mgr is allowed to be the binder context manager. * @mgr contains the struct cred for the current binder process. -- cgit v1.2.3 From 1427ddbe5cc1a3d4ac068cea78638baf95f16c18 Mon Sep 17 00:00:00 2001 From: Paul Moore Date: Thu, 16 Feb 2023 16:39:08 -0500 Subject: lsm: move the binder hook comments to security/security.c This patch relocates the LSM hook function comments to the function definitions, in keeping with the current kernel conventions. This should make the hook descriptions more easily discoverable and easier to maintain. While formatting changes have been done to better fit the kernel-doc style, content changes have been kept to a minimum and limited to text which was obviously incorrect and/or outdated. It is expected the future patches will improve the quality of the function header comments. Acked-by: Casey Schaufler Signed-off-by: Paul Moore --- include/linux/lsm_hooks.h | 22 ---------------------- 1 file changed, 22 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index f6679fead627..0a5b3b46fc2b 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -32,28 +32,6 @@ /** * union security_list_options - Linux Security Module hook function list * - * @binder_set_context_mgr: - * Check whether @mgr is allowed to be the binder context manager. - * @mgr contains the struct cred for the current binder process. - * Return 0 if permission is granted. - * @binder_transaction: - * Check whether @from is allowed to invoke a binder transaction call - * to @to. - * @from contains the struct cred for the sending process. - * @to contains the struct cred for the receiving process. - * Return 0 if permission is granted. - * @binder_transfer_binder: - * Check whether @from is allowed to transfer a binder reference to @to. - * @from contains the struct cred for the sending process. - * @to contains the struct cred for the receiving process. - * Return 0 if permission is granted. - * @binder_transfer_file: - * Check whether @from is allowed to transfer @file to @to. - * @from contains the struct cred for the sending process. - * @file contains the struct file being transferred. - * @to contains the struct cred for the receiving process. - * Return 0 if permission is granted. - * * @ptrace_access_check: * Check permission before allowing the current process to trace the * @child process. -- cgit v1.2.3 From b14faf9c94a66ef398c2c3fa6e141814f04e274e Mon Sep 17 00:00:00 2001 From: Paul Moore Date: Thu, 16 Feb 2023 17:00:01 -0500 Subject: lsm: move the audit hook comments to security/security.c This patch relocates the LSM hook function comments to the function definitions, in keeping with the current kernel conventions. This should make the hook descriptions more easily discoverable and easier to maintain. While formatting changes have been done to better fit the kernel-doc style, content changes have been kept to a minimum and limited to text which was obviously incorrect and/or outdated. It is expected the future patches will improve the quality of the function header comments. Acked-by: Casey Schaufler Signed-off-by: Paul Moore --- include/linux/lsm_hooks.h | 32 -------------------------------- 1 file changed, 32 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index 0a5b3b46fc2b..e36387f88083 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -135,38 +135,6 @@ * @secdata contains the security context. * @seclen contains the length of the security context. * - * Security hooks for Audit - * - * @audit_rule_init: - * Allocate and initialize an LSM audit rule structure. - * @field contains the required Audit action. - * Fields flags are defined in - * @op contains the operator the rule uses. - * @rulestr contains the context where the rule will be applied to. - * @lsmrule contains a pointer to receive the result. - * Return 0 if @lsmrule has been successfully set, - * -EINVAL in case of an invalid rule. - * - * @audit_rule_known: - * Specifies whether given @krule contains any fields related to - * current LSM. - * @krule contains the audit rule of interest. - * Return 1 in case of relation found, 0 otherwise. - * - * @audit_rule_match: - * Determine if given @secid matches a rule previously approved - * by @audit_rule_known. - * @secid contains the security id in question. - * @field contains the field which relates to current LSM. - * @op contains the operator that will be used for matching. - * @lrule points to the audit rule that will be checked against. - * Return 1 if secid matches the rule, 0 if it does not, -ERRNO on failure. - * - * @audit_rule_free: - * Deallocate the LSM audit rule structure previously allocated by - * audit_rule_init. - * @lsmrule contains the allocated rule. - * * @inode_invalidate_secctx: * Notify the security module that it must revalidate the security context * of an inode. -- cgit v1.2.3 From 55e853201a9e0383c9f6d5d800155e334685cd7e Mon Sep 17 00:00:00 2001 From: Paul Moore Date: Thu, 16 Feb 2023 17:13:40 -0500 Subject: lsm: move the bpf hook comments to security/security.c This patch relocates the LSM hook function comments to the function definitions, in keeping with the current kernel conventions. This should make the hook descriptions more easily discoverable and easier to maintain. While formatting changes have been done to better fit the kernel-doc style, content changes have been kept to a minimum and limited to text which was obviously incorrect and/or outdated. It is expected the future patches will improve the quality of the function header comments. Acked-by: Casey Schaufler Signed-off-by: Paul Moore --- include/linux/lsm_hooks.h | 36 ------------------------------------ 1 file changed, 36 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index e36387f88083..601d1ecdae0f 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -190,42 +190,6 @@ * @key: The key to watch. * Return 0 if permission is granted. * - * Security hooks for using the eBPF maps and programs functionalities through - * eBPF syscalls. - * - * @bpf: - * Do a initial check for all bpf syscalls after the attribute is copied - * into the kernel. The actual security module can implement their own - * rules to check the specific cmd they need. - * Return 0 if permission is granted. - * - * @bpf_map: - * Do a check when the kernel generate and return a file descriptor for - * eBPF maps. - * @map: bpf map that we want to access. - * @mask: the access flags. - * Return 0 if permission is granted. - * - * @bpf_prog: - * Do a check when the kernel generate and return a file descriptor for - * eBPF programs. - * @prog: bpf prog that userspace want to use. - * Return 0 if permission is granted. - * - * @bpf_map_alloc_security: - * Initialize the security field inside bpf map. - * Return 0 on success, error on failure. - * - * @bpf_map_free_security: - * Clean up the security information stored inside bpf map. - * - * @bpf_prog_alloc_security: - * Initialize the security field inside bpf program. - * Return 0 on success, error on failure. - * - * @bpf_prog_free_security: - * Clean up the security information stored inside bpf prog. - * * @locked_down: * Determine whether a kernel feature that potentially enables arbitrary * code execution in kernel space should be permitted. -- cgit v1.2.3 From 452b670c7222c7bf11b45b13f5a736f96d0be1e3 Mon Sep 17 00:00:00 2001 From: Paul Moore Date: Thu, 16 Feb 2023 17:22:36 -0500 Subject: lsm: move the perf hook comments to security/security.c This patch relocates the LSM hook function comments to the function definitions, in keeping with the current kernel conventions. This should make the hook descriptions more easily discoverable and easier to maintain. While formatting changes have been done to better fit the kernel-doc style, content changes have been kept to a minimum and limited to text which was obviously incorrect and/or outdated. It is expected the future patches will improve the quality of the function header comments. Acked-by: Casey Schaufler Signed-off-by: Paul Moore --- include/linux/lsm_hooks.h | 17 ----------------- 1 file changed, 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index 601d1ecdae0f..3d8d430e271a 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -196,23 +196,6 @@ * @what: kernel feature being accessed. * Return 0 if permission is granted. * - * Security hooks for perf events - * - * @perf_event_open: - * Check whether the @type of perf_event_open syscall is allowed. - * Return 0 if permission is granted. - * @perf_event_alloc: - * Allocate and save perf_event security info. - * Return 0 on success, error on failure. - * @perf_event_free: - * Release (free) perf_event security info. - * @perf_event_read: - * Read perf_event security info if allowed. - * Return 0 if permission is granted. - * @perf_event_write: - * Write perf_event security info if allowed. - * Return 0 if permission is granted. - * * Security hooks for io_uring * * @uring_override_creds: -- cgit v1.2.3 From 1cd2aca64a5dc4edb65539dc26f24e162ab0e11c Mon Sep 17 00:00:00 2001 From: Paul Moore Date: Thu, 16 Feb 2023 17:28:31 -0500 Subject: lsm: move the io_uring hook comments to security/security.c This patch relocates the LSM hook function comments to the function definitions, in keeping with the current kernel conventions. This should make the hook descriptions more easily discoverable and easier to maintain. While formatting changes have been done to better fit the kernel-doc style, content changes have been kept to a minimum and limited to text which was obviously incorrect and/or outdated. It is expected the future patches will improve the quality of the function header comments. Acked-by: Casey Schaufler Signed-off-by: Paul Moore --- include/linux/lsm_hooks.h | 17 ----------------- 1 file changed, 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index 3d8d430e271a..8e006df1db56 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -196,23 +196,6 @@ * @what: kernel feature being accessed. * Return 0 if permission is granted. * - * Security hooks for io_uring - * - * @uring_override_creds: - * Check if the current task, executing an io_uring operation, is allowed - * to override it's credentials with @new. - * @new: the new creds to use. - * Return 0 if permission is granted. - * - * @uring_sqpoll: - * Check whether the current task is allowed to spawn a io_uring polling - * thread (IORING_SETUP_SQPOLL). - * Return 0 if permission is granted. - * - * @uring_cmd: - * Check whether the file_operations uring_cmd is allowed to run. - * Return 0 if permission is granted. - * */ union security_list_options { #define LSM_HOOK(RET, DEFAULT, NAME, ...) RET (*NAME)(__VA_ARGS__); -- cgit v1.2.3 From e261301c851aee401cfc63179ca4d3facd2f098b Mon Sep 17 00:00:00 2001 From: Paul Moore Date: Thu, 16 Feb 2023 17:34:14 -0500 Subject: lsm: move the remaining LSM hook comments to security/security.c This patch relocates the LSM hook function comments to the function definitions, in keeping with the current kernel conventions. This should make the hook descriptions more easily discoverable and easier to maintain. While formatting changes have been done to better fit the kernel-doc style, content changes have been kept to a minimum and limited to text which was obviously incorrect and/or outdated. It is expected the future patches will improve the quality of the function header comments. Acked-by: Casey Schaufler Signed-off-by: Paul Moore --- include/linux/lsm_hooks.h | 168 ---------------------------------------------- 1 file changed, 168 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index 8e006df1db56..ddbbe89a7a48 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -29,174 +29,6 @@ #include #include -/** - * union security_list_options - Linux Security Module hook function list - * - * @ptrace_access_check: - * Check permission before allowing the current process to trace the - * @child process. - * Security modules may also want to perform a process tracing check - * during an execve in the set_security or apply_creds hooks of - * tracing check during an execve in the bprm_set_creds hook of - * binprm_security_ops if the process is being traced and its security - * attributes would be changed by the execve. - * @child contains the task_struct structure for the target process. - * @mode contains the PTRACE_MODE flags indicating the form of access. - * Return 0 if permission is granted. - * @ptrace_traceme: - * Check that the @parent process has sufficient permission to trace the - * current process before allowing the current process to present itself - * to the @parent process for tracing. - * @parent contains the task_struct structure for debugger process. - * Return 0 if permission is granted. - * @capget: - * Get the @effective, @inheritable, and @permitted capability sets for - * the @target process. The hook may also perform permission checking to - * determine if the current process is allowed to see the capability sets - * of the @target process. - * @target contains the task_struct structure for target process. - * @effective contains the effective capability set. - * @inheritable contains the inheritable capability set. - * @permitted contains the permitted capability set. - * Return 0 if the capability sets were successfully obtained. - * @capset: - * Set the @effective, @inheritable, and @permitted capability sets for - * the current process. - * @new contains the new credentials structure for target process. - * @old contains the current credentials structure for target process. - * @effective contains the effective capability set. - * @inheritable contains the inheritable capability set. - * @permitted contains the permitted capability set. - * Return 0 and update @new if permission is granted. - * @capable: - * Check whether the @tsk process has the @cap capability in the indicated - * credentials. - * @cred contains the credentials to use. - * @ns contains the user namespace we want the capability in. - * @cap contains the capability . - * @opts contains options for the capable check . - * Return 0 if the capability is granted for @tsk. - * @quotactl: - * Check whether the quotactl syscall is allowed for this @sb. - * Return 0 if permission is granted. - * @quota_on: - * Check whether QUOTAON is allowed for this @dentry. - * Return 0 if permission is granted. - * @syslog: - * Check permission before accessing the kernel message ring or changing - * logging to the console. - * See the syslog(2) manual page for an explanation of the @type values. - * @type contains the SYSLOG_ACTION_* constant from - * . - * Return 0 if permission is granted. - * @settime: - * Check permission to change the system time. - * struct timespec64 is defined in and timezone - * is defined in - * @ts contains new time. - * @tz contains new timezone. - * Return 0 if permission is granted. - * @vm_enough_memory: - * Check permissions for allocating a new virtual mapping. - * @mm contains the mm struct it is being added to. - * @pages contains the number of pages. - * Return 0 if permission is granted by the LSM infrastructure to the - * caller. If all LSMs return a positive value, __vm_enough_memory() will - * be called with cap_sys_admin set. If at least one LSM returns 0 or - * negative, __vm_enough_memory() will be called with cap_sys_admin - * cleared. - * - * @ismaclabel: - * Check if the extended attribute specified by @name - * represents a MAC label. Returns 1 if name is a MAC - * attribute otherwise returns 0. - * @name full extended attribute name to check against - * LSM as a MAC label. - * - * @secid_to_secctx: - * Convert secid to security context. If secdata is NULL the length of - * the result will be returned in seclen, but no secdata will be returned. - * This does mean that the length could change between calls to check the - * length and the next call which actually allocates and returns the - * secdata. - * @secid contains the security ID. - * @secdata contains the pointer that stores the converted security - * context. - * @seclen pointer which contains the length of the data. - * Return 0 on success, error on failure. - * @secctx_to_secid: - * Convert security context to secid. - * @secid contains the pointer to the generated security ID. - * @secdata contains the security context. - * Return 0 on success, error on failure. - * - * @release_secctx: - * Release the security context. - * @secdata contains the security context. - * @seclen contains the length of the security context. - * - * @inode_invalidate_secctx: - * Notify the security module that it must revalidate the security context - * of an inode. - * - * @inode_notifysecctx: - * Notify the security module of what the security context of an inode - * should be. Initializes the incore security context managed by the - * security module for this inode. Example usage: NFS client invokes - * this hook to initialize the security context in its incore inode to the - * value provided by the server for the file when the server returned the - * file's attributes to the client. - * Must be called with inode->i_mutex locked. - * @inode we wish to set the security context of. - * @ctx contains the string which we wish to set in the inode. - * @ctxlen contains the length of @ctx. - * Return 0 on success, error on failure. - * - * @inode_setsecctx: - * Change the security context of an inode. Updates the - * incore security context managed by the security module and invokes the - * fs code as needed (via __vfs_setxattr_noperm) to update any backing - * xattrs that represent the context. Example usage: NFS server invokes - * this hook to change the security context in its incore inode and on the - * backing filesystem to a value provided by the client on a SETATTR - * operation. - * Must be called with inode->i_mutex locked. - * @dentry contains the inode we wish to set the security context of. - * @ctx contains the string which we wish to set in the inode. - * @ctxlen contains the length of @ctx. - * Return 0 on success, error on failure. - * - * @inode_getsecctx: - * On success, returns 0 and fills out @ctx and @ctxlen with the security - * context for the given @inode. - * @inode we wish to get the security context of. - * @ctx is a pointer in which to place the allocated security context. - * @ctxlen points to the place to put the length of @ctx. - * Return 0 on success, error on failure. - * - * Security hooks for the general notification queue: - * - * @post_notification: - * Check to see if a watch notification can be posted to a particular - * queue. - * @w_cred: The credentials of the whoever set the watch. - * @cred: The event-triggerer's credentials. - * @n: The notification being posted. - * Return 0 if permission is granted. - * - * @watch_key: - * Check to see if a process is allowed to watch for event notifications - * from a key or keyring. - * @key: The key to watch. - * Return 0 if permission is granted. - * - * @locked_down: - * Determine whether a kernel feature that potentially enables arbitrary - * code execution in kernel space should be permitted. - * @what: kernel feature being accessed. - * Return 0 if permission is granted. - * - */ union security_list_options { #define LSM_HOOK(RET, DEFAULT, NAME, ...) RET (*NAME)(__VA_ARGS__); #include "lsm_hook_defs.h" -- cgit v1.2.3 From 01c7a5978993209f47ecfd95dcbd52f6c6672384 Mon Sep 17 00:00:00 2001 From: Alexander Aring Date: Mon, 6 Mar 2023 15:48:11 -0500 Subject: fs: dlm: remove deprecated code parts This patch removes code parts which was declared deprecated by commit 6b0afc0cc3e9 ("fs: dlm: don't use deprecated timeout features by default"). This contains the following dlm functionality: - start a cancel of a dlm request did not complete after certain timeout: The current way how dlm cancellation works and interfering with other dlm requests triggered by the user can end in an overlapping and returning in -EBUSY. The most user don't handle this case and are unaware that DLM can return such errno in such situation. Due the timeout the user are mostly unaware when this happens. - start a netlink warning messages for user space if dlm requests did not complete after certain timeout: This feature was never being built in the only known dlm user space side. As we are to remove the timeout cancellation feature we can directly remove this feature as well. There might be the possibility to bring the timeout cancellation feature back. However the current way of handling the -EBUSY case which is only a software limitation and not a hardware limitation should be changed. We minimize the current code base in DLM cancellation feature to not have to deal with those existing features while solving the DLM cancellation feature in general. UAPI define DLM_LSFL_TIMEWARN is commented as deprecated and reserved value. We should avoid at first to give it a new meaning but let possible users still compile by keeping this define. In far future we can give this flag a new meaning. The same for the DLM_LKF_TIMEOUT lock request flag. Signed-off-by: Alexander Aring Signed-off-by: David Teigland --- include/linux/dlm.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dlm.h b/include/linux/dlm.h index c6bc2b5ee7e6..c58c4f790c04 100644 --- a/include/linux/dlm.h +++ b/include/linux/dlm.h @@ -53,9 +53,6 @@ struct dlm_lockspace_ops { * The dlm should not use a resource directory, but statically assign * resource mastery to nodes based on the name hash that is otherwise * used to select the directory node. Must be the same on all nodes. - * DLM_LSFL_TIMEWARN - * The dlm should emit netlink messages if locks have been waiting - * for a configurable amount of time. (Unused.) * DLM_LSFL_NEWEXCL * dlm_new_lockspace() should return -EEXIST if the lockspace exists. * -- cgit v1.2.3 From 42bf4597b7da8d9e3bc6039260e5437902af925a Mon Sep 17 00:00:00 2001 From: Md Sadre Alam Date: Mon, 6 Mar 2023 20:18:10 +0530 Subject: mtd: rawnand: Fix spelling mistake waifunc() -> waitfunc() There is a spelling mistake in a chip->legacy.waifunc(). Fix it. Signed-off-by: Md Sadre Alam Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20230306144810.22078-1-quic_mdalam@quicinc.com --- include/linux/mtd/rawnand.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index f8d4be9c587a..5159d692f9ce 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1075,7 +1075,7 @@ static inline void nand_op_trace(const char *prefix, * @exec_op: controller specific method to execute NAND operations. * This method replaces chip->legacy.cmdfunc(), * chip->legacy.{read,write}_{buf,byte,word}(), - * chip->legacy.dev_ready() and chip->legacy.waifunc(). + * chip->legacy.dev_ready() and chip->legacy.waitfunc(). * @setup_interface: setup the data interface and timing. If chipnr is set to * %NAND_DATA_IFACE_CHECK_ONLY this means the configuration * should not be applied but only checked. -- cgit v1.2.3 From 2d5bcdcda8799cf21f9ab84598c946dd320207a2 Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Tue, 7 Mar 2023 08:14:06 -0700 Subject: bpf: Increase size of BTF_ID_LIST without CONFIG_DEBUG_INFO_BTF again After commit 66e3a13e7c2c ("bpf: Add bpf_dynptr_slice and bpf_dynptr_slice_rdwr"), clang builds without CONFIG_DEBUG_INFO_BTF warn: kernel/bpf/verifier.c:10298:24: warning: array index 16 is past the end of the array (that has type 'u32[16]' (aka 'unsigned int[16]')) [-Warray-bounds] meta.func_id == special_kfunc_list[KF_bpf_dynptr_slice_rdwr]) { ^ ~~~~~~~~~~~~~~~~~~~~~~~~ kernel/bpf/verifier.c:9150:1: note: array 'special_kfunc_list' declared here BTF_ID_LIST(special_kfunc_list) ^ include/linux/btf_ids.h:207:27: note: expanded from macro 'BTF_ID_LIST' #define BTF_ID_LIST(name) static u32 __maybe_unused name[16]; ^ 1 warning generated. A warning of this nature was previously addressed by commit beb3d47d1d3d ("bpf: Fix a BTF_ID_LIST bug with CONFIG_DEBUG_INFO_BTF not set") but there have been new kfuncs added since then. Quadruple the size of the CONFIG_DEBUG_INFO_BTF=n definition so that this problem is unlikely to show up for some time. Link: https://github.com/ClangBuiltLinux/linux/issues/1810 Signed-off-by: Nathan Chancellor Reviewed-by: Tom Rix Link: https://lore.kernel.org/r/20230307-bpf-kfuncs-warray-bounds-v1-1-00ad3191f3a6@kernel.org Signed-off-by: Alexei Starovoitov --- include/linux/btf_ids.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/btf_ids.h b/include/linux/btf_ids.h index 3a4f7cd882ca..00950cc03bff 100644 --- a/include/linux/btf_ids.h +++ b/include/linux/btf_ids.h @@ -204,7 +204,7 @@ extern struct btf_id_set8 name; #else -#define BTF_ID_LIST(name) static u32 __maybe_unused name[16]; +#define BTF_ID_LIST(name) static u32 __maybe_unused name[64]; #define BTF_ID(prefix, name) #define BTF_ID_FLAGS(prefix, name, ...) #define BTF_ID_UNUSED -- cgit v1.2.3 From 5da094ac80cd4f6d4114ad220468f602f86d9980 Mon Sep 17 00:00:00 2001 From: Manivannan Sadhasivam Date: Fri, 24 Feb 2023 17:31:47 +0530 Subject: bus: mhi: host: Remove mhi_poll() API mhi_poll() API is not used within the MHI stack and also not by any client drivers in mainline. So let's remove it until any consumer is available. Reviewed-by: Jeffrey Hugo Signed-off-by: Manivannan Sadhasivam --- include/linux/mhi.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mhi.h b/include/linux/mhi.h index a5441ad33c74..f6de4b6ecfc7 100644 --- a/include/linux/mhi.h +++ b/include/linux/mhi.h @@ -765,13 +765,6 @@ int mhi_prepare_for_transfer_autoqueue(struct mhi_device *mhi_dev); */ void mhi_unprepare_from_transfer(struct mhi_device *mhi_dev); -/** - * mhi_poll - Poll for any available data in DL direction - * @mhi_dev: Device associated with the channels - * @budget: # of events to process - */ -int mhi_poll(struct mhi_device *mhi_dev, u32 budget); - /** * mhi_queue_dma - Send or receive DMA mapped buffers from client device * over MHI channel -- cgit v1.2.3 From 90a5527d7686d3ebe0dd2a831356a6c7d7dc31bc Mon Sep 17 00:00:00 2001 From: Yafang Shao Date: Sun, 5 Mar 2023 12:45:58 +0000 Subject: bpf: add new map ops ->map_mem_usage Add a new map ops ->map_mem_usage to print the memory usage of a bpf map. This is a preparation for the followup change. Signed-off-by: Yafang Shao Link: https://lore.kernel.org/r/20230305124615.12358-2-laoar.shao@gmail.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index d3456804f7aa..9059520bbb5e 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -161,6 +161,8 @@ struct bpf_map_ops { bpf_callback_t callback_fn, void *callback_ctx, u64 flags); + u64 (*map_mem_usage)(const struct bpf_map *map); + /* BTF id of struct allocated by map_alloc */ int *map_btf_id; -- cgit v1.2.3 From 7490b7f1c02ef825ef98f7230662049d4a464a21 Mon Sep 17 00:00:00 2001 From: Yafang Shao Date: Sun, 5 Mar 2023 12:46:11 +0000 Subject: bpf, net: bpf_local_storage memory usage A new helper is introduced into bpf_local_storage map to calculate the memory usage. This helper is also used by other maps like bpf_cgrp_storage, bpf_inode_storage, bpf_task_storage and etc. Note that currently the dynamically allocated storage elements are not counted in the usage, since it will take extra runtime overhead in the elements update or delete path. So let's put it aside now, and implement it in the future when someone really need it. Signed-off-by: Yafang Shao Link: https://lore.kernel.org/r/20230305124615.12358-15-laoar.shao@gmail.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf_local_storage.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/bpf_local_storage.h b/include/linux/bpf_local_storage.h index 6d37a40cd90e..d934248b8e81 100644 --- a/include/linux/bpf_local_storage.h +++ b/include/linux/bpf_local_storage.h @@ -164,5 +164,6 @@ bpf_local_storage_update(void *owner, struct bpf_local_storage_map *smap, void *value, u64 map_flags, gfp_t gfp_flags); void bpf_local_storage_free_rcu(struct rcu_head *rcu); +u64 bpf_local_storage_map_mem_usage(const struct bpf_map *map); #endif /* _BPF_LOCAL_STORAGE_H */ -- cgit v1.2.3 From 9629363cd05642fe43aded44938adec067ad1da3 Mon Sep 17 00:00:00 2001 From: Yafang Shao Date: Sun, 5 Mar 2023 12:46:14 +0000 Subject: bpf: offload map memory usage A new helper is introduced to calculate offload map memory usage. But currently the memory dynamically allocated in netdev dev_ops, like nsim_map_update_elem, is not counted. Let's just put it aside now. Signed-off-by: Yafang Shao Link: https://lore.kernel.org/r/20230305124615.12358-18-laoar.shao@gmail.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 9059520bbb5e..6792a7940e1e 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -2624,6 +2624,7 @@ static inline bool bpf_map_is_offloaded(struct bpf_map *map) struct bpf_map *bpf_map_offload_map_alloc(union bpf_attr *attr); void bpf_map_offload_map_free(struct bpf_map *map); +u64 bpf_map_offload_map_mem_usage(const struct bpf_map *map); int bpf_prog_test_run_syscall(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); @@ -2695,6 +2696,11 @@ static inline void bpf_map_offload_map_free(struct bpf_map *map) { } +static inline u64 bpf_map_offload_map_mem_usage(const struct bpf_map *map) +{ + return 0; +} + static inline int bpf_prog_test_run_syscall(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr) -- cgit v1.2.3 From d70e2ecbc726a0ee794b72365730a8dbc9866080 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sun, 26 Feb 2023 17:17:00 -0800 Subject: instrumented.h: Fix all kernel-doc format warnings Fix 26 kernel-doc notation warnings by converting the function documentation to kernel-doc format. Warning example: instrumented.h:155: warning: Function parameter or member 'to' not described in 'instrument_copy_from_user_after' instrumented.h:155: warning: Function parameter or member 'from' not described in 'instrument_copy_from_user_after' instrumented.h:155: warning: Function parameter or member 'n' not described in 'instrument_copy_from_user_after' instrumented.h:155: warning: Function parameter or member 'left' not described in 'instrument_copy_from_user_after' Fixes: 36e4d4dd4fc4 ("include/linux: Add instrumented.h infrastructure") Fixes: 00047c2e6d7c ("instrumented.h: Introduce read-write instrumentation hooks") Fixes: 33b75c1d884e ("instrumented.h: allow instrumenting both sides of copy_from_user()") Fixes: 888f84a6da4d ("x86: asm: instrument usercopy in get_user() and put_user()") Signed-off-by: Randy Dunlap Cc: Arnd Bergmann Cc: Marco Elver Cc: Alexander Potapenko Cc: Andrew Morton Cc: Dmitry Vyukov Cc: Paul E. McKenney Cc: Ingo Molnar Reviewed-by: Marco Elver Signed-off-by: Paul E. McKenney --- include/linux/instrumented.h | 63 ++++++++++++++++++-------------------------- 1 file changed, 26 insertions(+), 37 deletions(-) (limited to 'include/linux') diff --git a/include/linux/instrumented.h b/include/linux/instrumented.h index 501fa8486749..1b608e00290a 100644 --- a/include/linux/instrumented.h +++ b/include/linux/instrumented.h @@ -15,12 +15,11 @@ /** * instrument_read - instrument regular read access + * @v: address of access + * @size: size of access * * Instrument a regular read access. The instrumentation should be inserted * before the actual read happens. - * - * @ptr address of access - * @size size of access */ static __always_inline void instrument_read(const volatile void *v, size_t size) { @@ -30,12 +29,11 @@ static __always_inline void instrument_read(const volatile void *v, size_t size) /** * instrument_write - instrument regular write access + * @v: address of access + * @size: size of access * * Instrument a regular write access. The instrumentation should be inserted * before the actual write happens. - * - * @ptr address of access - * @size size of access */ static __always_inline void instrument_write(const volatile void *v, size_t size) { @@ -45,12 +43,11 @@ static __always_inline void instrument_write(const volatile void *v, size_t size /** * instrument_read_write - instrument regular read-write access + * @v: address of access + * @size: size of access * * Instrument a regular write access. The instrumentation should be inserted * before the actual write happens. - * - * @ptr address of access - * @size size of access */ static __always_inline void instrument_read_write(const volatile void *v, size_t size) { @@ -60,12 +57,11 @@ static __always_inline void instrument_read_write(const volatile void *v, size_t /** * instrument_atomic_read - instrument atomic read access + * @v: address of access + * @size: size of access * * Instrument an atomic read access. The instrumentation should be inserted * before the actual read happens. - * - * @ptr address of access - * @size size of access */ static __always_inline void instrument_atomic_read(const volatile void *v, size_t size) { @@ -75,12 +71,11 @@ static __always_inline void instrument_atomic_read(const volatile void *v, size_ /** * instrument_atomic_write - instrument atomic write access + * @v: address of access + * @size: size of access * * Instrument an atomic write access. The instrumentation should be inserted * before the actual write happens. - * - * @ptr address of access - * @size size of access */ static __always_inline void instrument_atomic_write(const volatile void *v, size_t size) { @@ -90,12 +85,11 @@ static __always_inline void instrument_atomic_write(const volatile void *v, size /** * instrument_atomic_read_write - instrument atomic read-write access + * @v: address of access + * @size: size of access * * Instrument an atomic read-write access. The instrumentation should be * inserted before the actual write happens. - * - * @ptr address of access - * @size size of access */ static __always_inline void instrument_atomic_read_write(const volatile void *v, size_t size) { @@ -105,13 +99,12 @@ static __always_inline void instrument_atomic_read_write(const volatile void *v, /** * instrument_copy_to_user - instrument reads of copy_to_user + * @to: destination address + * @from: source address + * @n: number of bytes to copy * * Instrument reads from kernel memory, that are due to copy_to_user (and * variants). The instrumentation must be inserted before the accesses. - * - * @to destination address - * @from source address - * @n number of bytes to copy */ static __always_inline void instrument_copy_to_user(void __user *to, const void *from, unsigned long n) @@ -123,13 +116,12 @@ instrument_copy_to_user(void __user *to, const void *from, unsigned long n) /** * instrument_copy_from_user_before - add instrumentation before copy_from_user + * @to: destination address + * @from: source address + * @n: number of bytes to copy * * Instrument writes to kernel memory, that are due to copy_from_user (and * variants). The instrumentation should be inserted before the accesses. - * - * @to destination address - * @from source address - * @n number of bytes to copy */ static __always_inline void instrument_copy_from_user_before(const void *to, const void __user *from, unsigned long n) @@ -140,14 +132,13 @@ instrument_copy_from_user_before(const void *to, const void __user *from, unsign /** * instrument_copy_from_user_after - add instrumentation after copy_from_user + * @to: destination address + * @from: source address + * @n: number of bytes to copy + * @left: number of bytes not copied (as returned by copy_from_user) * * Instrument writes to kernel memory, that are due to copy_from_user (and * variants). The instrumentation should be inserted after the accesses. - * - * @to destination address - * @from source address - * @n number of bytes to copy - * @left number of bytes not copied (as returned by copy_from_user) */ static __always_inline void instrument_copy_from_user_after(const void *to, const void __user *from, @@ -158,12 +149,11 @@ instrument_copy_from_user_after(const void *to, const void __user *from, /** * instrument_get_user() - add instrumentation to get_user()-like macros + * @to: destination variable, may not be address-taken * * get_user() and friends are fragile, so it may depend on the implementation * whether the instrumentation happens before or after the data is copied from * the userspace. - * - * @to destination variable, may not be address-taken */ #define instrument_get_user(to) \ ({ \ @@ -175,14 +165,13 @@ instrument_copy_from_user_after(const void *to, const void __user *from, /** * instrument_put_user() - add instrumentation to put_user()-like macros + * @from: source address + * @ptr: userspace pointer to copy to + * @size: number of bytes to copy * * put_user() and friends are fragile, so it may depend on the implementation * whether the instrumentation happens before or after the data is copied from * the userspace. - * - * @from source address - * @ptr userspace pointer to copy to - * @size number of bytes to copy */ #define instrument_put_user(from, ptr, size) \ ({ \ -- cgit v1.2.3 From 0194b64578e905dc8f112e641a71c306bd58ddde Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Mon, 6 Mar 2023 22:51:35 +0100 Subject: net: phy: improve phy_read_poll_timeout cond sometimes is (val & MASK) what may result in a false positive if val is a negative errno. We shouldn't evaluate cond if val < 0. This has no functional impact here, but it's not nice. Therefore switch order of the checks. Signed-off-by: Heiner Kallweit Reviewed-by: Simon Horman Reviewed-by: Andrew Lunn Link: https://lore.kernel.org/r/6d8274ac-4344-23b4-d9a3-cad4c39517d4@gmail.com Signed-off-by: Jakub Kicinski --- include/linux/phy.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 36bf0bbc8efa..fefd5091bc24 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1130,16 +1130,15 @@ static inline int phy_read(struct phy_device *phydev, u32 regnum) #define phy_read_poll_timeout(phydev, regnum, val, cond, sleep_us, \ timeout_us, sleep_before_read) \ ({ \ - int __ret = read_poll_timeout(phy_read, val, (cond) || val < 0, \ + int __ret = read_poll_timeout(phy_read, val, val < 0 || (cond), \ sleep_us, timeout_us, sleep_before_read, phydev, regnum); \ - if (val < 0) \ + if (val < 0) \ __ret = val; \ if (__ret) \ phydev_err(phydev, "%s failed: %d\n", __func__, __ret); \ __ret; \ }) - /** * __phy_read - convenience function for reading a given PHY register * @phydev: the phy_device struct -- cgit v1.2.3 From 40bbae583ec38ea31e728bf42a4ea72bded22ab6 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 6 Mar 2023 20:43:13 +0000 Subject: net: remove enum skb_free_reason enum skb_drop_reason is more generic, we can adopt it instead. Provide dev_kfree_skb_irq_reason() and dev_kfree_skb_any_reason(). This means drivers can use more precise drop reasons if they want to. Signed-off-by: Eric Dumazet Reviewed-by: Simon Horman Reviewed-by: Yunsheng Lin Link: https://lore.kernel.org/r/20230306204313.10492-1-edumazet@google.com Signed-off-by: Jakub Kicinski --- include/linux/netdevice.h | 18 +++++++----------- 1 file changed, 7 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 6a14b7b11766..ee483071cf59 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -52,6 +52,7 @@ #include #include #include +#include struct netpoll_info; struct device; @@ -3804,13 +3805,8 @@ static inline unsigned int get_netdev_rx_queue_index( int netif_get_num_default_rss_queues(void); -enum skb_free_reason { - SKB_REASON_CONSUMED, - SKB_REASON_DROPPED, -}; - -void __dev_kfree_skb_irq(struct sk_buff *skb, enum skb_free_reason reason); -void __dev_kfree_skb_any(struct sk_buff *skb, enum skb_free_reason reason); +void dev_kfree_skb_irq_reason(struct sk_buff *skb, enum skb_drop_reason reason); +void dev_kfree_skb_any_reason(struct sk_buff *skb, enum skb_drop_reason reason); /* * It is not allowed to call kfree_skb() or consume_skb() from hardware @@ -3833,22 +3829,22 @@ void __dev_kfree_skb_any(struct sk_buff *skb, enum skb_free_reason reason); */ static inline void dev_kfree_skb_irq(struct sk_buff *skb) { - __dev_kfree_skb_irq(skb, SKB_REASON_DROPPED); + dev_kfree_skb_irq_reason(skb, SKB_DROP_REASON_NOT_SPECIFIED); } static inline void dev_consume_skb_irq(struct sk_buff *skb) { - __dev_kfree_skb_irq(skb, SKB_REASON_CONSUMED); + dev_kfree_skb_irq_reason(skb, SKB_CONSUMED); } static inline void dev_kfree_skb_any(struct sk_buff *skb) { - __dev_kfree_skb_any(skb, SKB_REASON_DROPPED); + dev_kfree_skb_any_reason(skb, SKB_DROP_REASON_NOT_SPECIFIED); } static inline void dev_consume_skb_any(struct sk_buff *skb) { - __dev_kfree_skb_any(skb, SKB_REASON_CONSUMED); + dev_kfree_skb_any_reason(skb, SKB_CONSUMED); } u32 bpf_prog_run_generic_xdp(struct sk_buff *skb, struct xdp_buff *xdp, -- cgit v1.2.3 From 10369080454d87ee5b2db211ce947cb3118f0e13 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 7 Mar 2023 14:59:59 +0000 Subject: net: reclaim skb->scm_io_uring bit Commit 0091bfc81741 ("io_uring/af_unix: defer registered files gc to io_uring release") added one bit to struct sk_buff. This structure is critical for networking, and we try very hard to not add bloat on it, unless absolutely required. For instance, we can use a specific destructor as a wrapper around unix_destruct_scm(), to identify skbs that unix_gc() has to special case. Signed-off-by: Eric Dumazet Cc: Pavel Begunkov Cc: Thadeu Lima de Souza Cascardo Cc: Jens Axboe Reviewed-by: Jens Axboe Reviewed-by: Pavel Begunkov Signed-off-by: David S. Miller --- include/linux/skbuff.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index ff7ad331fb82..fe661011644b 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -810,7 +810,6 @@ typedef unsigned char *sk_buff_data_t; * @csum_level: indicates the number of consecutive checksums found in * the packet minus one that have been verified as * CHECKSUM_UNNECESSARY (max 3) - * @scm_io_uring: SKB holds io_uring registered files * @dst_pending_confirm: need to confirm neighbour * @decrypted: Decrypted SKB * @slow_gro: state present at GRO time, slower prepare step required @@ -989,7 +988,6 @@ struct sk_buff { #endif __u8 slow_gro:1; __u8 csum_not_inet:1; - __u8 scm_io_uring:1; #ifdef CONFIG_NET_SCHED __u16 tc_index; /* traffic control index */ -- cgit v1.2.3 From 28e144cf5f72ce1c304571bc448e37c27495903a Mon Sep 17 00:00:00 2001 From: Xin Long Date: Tue, 7 Mar 2023 16:31:30 -0500 Subject: netfilter: move br_nf_check_hbh_len to utils Rename br_nf_check_hbh_len() to nf_ip6_check_hbh_len() and move it to netfilter utils, so that it can be used by other modules, like ovs and tc. Signed-off-by: Xin Long Reviewed-by: Simon Horman Reviewed-by: Nikolay Aleksandrov Reviewed-by: Aaron Conole Signed-off-by: Florian Westphal --- include/linux/netfilter_ipv6.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netfilter_ipv6.h b/include/linux/netfilter_ipv6.h index 48314ade1506..7834c0be2831 100644 --- a/include/linux/netfilter_ipv6.h +++ b/include/linux/netfilter_ipv6.h @@ -197,6 +197,8 @@ static inline int nf_cookie_v6_check(const struct ipv6hdr *iph, __sum16 nf_ip6_checksum(struct sk_buff *skb, unsigned int hook, unsigned int dataoff, u_int8_t protocol); +int nf_ip6_check_hbh_len(struct sk_buff *skb, u32 *plen); + int ipv6_netfilter_init(void); void ipv6_netfilter_fini(void); -- cgit v1.2.3 From 071c44e4278156f18a6a56958617223b6bffa6ab Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Mon, 13 Feb 2023 23:05:58 -0800 Subject: sched/idle: Mark arch_cpu_idle_dead() __noreturn Before commit 076cbf5d2163 ("x86/xen: don't let xen_pv_play_dead() return"), in Xen, when a previously offlined CPU was brought back online, it unexpectedly resumed execution where it left off in the middle of the idle loop. There were some hacks to make that work, but the behavior was surprising as do_idle() doesn't expect an offlined CPU to return from the dead (in arch_cpu_idle_dead()). Now that Xen has been fixed, and the arch-specific implementations of arch_cpu_idle_dead() also don't return, give it a __noreturn attribute. This will cause the compiler to complain if an arch-specific implementation might return. It also improves code generation for both caller and callee. Also fixes the following warning: vmlinux.o: warning: objtool: do_idle+0x25f: unreachable instruction Reported-by: Paul E. McKenney Tested-by: Paul E. McKenney Link: https://lore.kernel.org/r/60d527353da8c99d4cf13b6473131d46719ed16d.1676358308.git.jpoimboe@kernel.org Signed-off-by: Josh Poimboeuf --- include/linux/cpu.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cpu.h b/include/linux/cpu.h index f83e4519c5f0..8582a7142623 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -182,7 +182,7 @@ void arch_cpu_idle(void); void arch_cpu_idle_prepare(void); void arch_cpu_idle_enter(void); void arch_cpu_idle_exit(void); -void arch_cpu_idle_dead(void); +void __noreturn arch_cpu_idle_dead(void); int cpu_report_state(int cpu); int cpu_check_up_prepare(int cpu); -- cgit v1.2.3 From b3816cf8138b6814375ec65673bcba91d368ee9f Mon Sep 17 00:00:00 2001 From: Paul Moore Date: Wed, 8 Mar 2023 13:28:18 -0500 Subject: lsm: fix a badly named parameter in security_get_getsecurity() There is no good reason for why the "_buffer" parameter needs an underscore, get rid of it. Signed-off-by: Paul Moore --- include/linux/lsm_hook_defs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index 094b76dc7164..6bb55e61e8e8 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -381,7 +381,7 @@ LSM_HOOK(int, 0, key_alloc, struct key *key, const struct cred *cred, LSM_HOOK(void, LSM_RET_VOID, key_free, struct key *key) LSM_HOOK(int, 0, key_permission, key_ref_t key_ref, const struct cred *cred, enum key_need_perm need_perm) -LSM_HOOK(int, 0, key_getsecurity, struct key *key, char **_buffer) +LSM_HOOK(int, 0, key_getsecurity, struct key *key, char **buffer) #endif /* CONFIG_KEYS */ #ifdef CONFIG_AUDIT -- cgit v1.2.3 From 215bf4962f6c9605710012fad222a5fec001b3ad Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Wed, 8 Mar 2023 10:41:15 -0800 Subject: bpf: add iterator kfuncs registration and validation logic Add ability to register kfuncs that implement BPF open-coded iterator contract and enforce naming and function proto convention. Enforcement happens at the time of kfunc registration and significantly simplifies the rest of iterators logic in the verifier. More details follow in subsequent patches, but we enforce the following conditions. All kfuncs (constructor, next, destructor) have to be named consistenly as bpf_iter__{new,next,destroy}(), respectively. represents iterator type, and iterator state should be represented as a matching `struct bpf_iter_` state type. Also, all iter kfuncs should have a pointer to this `struct bpf_iter_` as the very first argument. Additionally: - Constructor, i.e., bpf_iter__new(), can have arbitrary extra number of arguments. Return type is not enforced either. - Next method, i.e., bpf_iter__next(), has to return a pointer type and should have exactly one argument: `struct bpf_iter_ *` (const/volatile/restrict and typedefs are ignored). - Destructor, i.e., bpf_iter__destroy(), should return void and should have exactly one argument, similar to the next method. - struct bpf_iter_ size is enforced to be positive and a multiple of 8 bytes (to fit stack slots correctly). Such strictness and consistency allows to build generic helpers abstracting important, but boilerplate, details to be able to use open-coded iterators effectively and ergonomically (see bpf_for_each() in subsequent patches). It also simplifies the verifier logic in some places. At the same time, this doesn't hurt generality of possible iterator implementations. Win-win. Constructor kfunc is marked with a new KF_ITER_NEW flags, next method is marked with KF_ITER_NEXT (and should also have KF_RET_NULL, of course), while destructor kfunc is marked as KF_ITER_DESTROY. Additionally, we add a trivial kfunc name validation: it should be a valid non-NULL and non-empty string. Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/r/20230308184121.1165081-3-andrii@kernel.org Signed-off-by: Alexei Starovoitov --- include/linux/bpf_verifier.h | 2 ++ include/linux/btf.h | 4 ++++ 2 files changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 18538bad2b8c..e2dc7f064449 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -59,6 +59,8 @@ struct bpf_active_lock { u32 id; }; +#define ITER_PREFIX "bpf_iter_" + struct bpf_reg_state { /* Ordering of fields matters. See states_equal() */ enum bpf_reg_type type; diff --git a/include/linux/btf.h b/include/linux/btf.h index 556b3e2e7471..1bba0827e8c4 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -71,6 +71,10 @@ #define KF_SLEEPABLE (1 << 5) /* kfunc may sleep */ #define KF_DESTRUCTIVE (1 << 6) /* kfunc performs destructive actions */ #define KF_RCU (1 << 7) /* kfunc takes either rcu or trusted pointer arguments */ +/* only one of KF_ITER_{NEW,NEXT,DESTROY} could be specified per kfunc */ +#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 */ /* * Tag marking a kernel function as a kfunc. This is meant to minimize the -- cgit v1.2.3 From 06accc8779c1d558a5b5a21f2ac82b0c95827ddd Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Wed, 8 Mar 2023 10:41:16 -0800 Subject: bpf: add support for open-coded iterator loops Teach verifier about the concept of the open-coded (or inline) iterators. This patch adds generic iterator loop verification logic, new STACK_ITER stack slot type to contain iterator state, and necessary kfunc plumbing for iterator's constructor, destructor and next methods. Next patch implements first specific iterator (numbers iterator for implementing for() loop logic). Such split allows to have more focused commits for verifier logic and separate commit that we could point later to demonstrating what does it take to add a new kind of iterator. Each kind of iterator has its own associated struct bpf_iter_, where denotes a specific type of iterator. struct bpf_iter_ state is supposed to live on BPF program stack, so there will be no way to change its size later on without breaking backwards compatibility, so choose wisely! But given this struct is specific to a given of iterator, this allows a lot of flexibility: simple iterators could be fine with just one stack slot (8 bytes), like numbers iterator in the next patch, while some other more complicated iterators might need way more to keep their iterator state. Either way, such design allows to avoid runtime memory allocations, which otherwise would be necessary if we fixed on-the-stack size and it turned out to be too small for a given iterator implementation. The way BPF verifier logic is implemented, there are no artificial restrictions on a number of active iterators, it should work correctly using multiple active iterators at the same time. This also means you can have multiple nested iteration loops. struct bpf_iter_ reference can be safely passed to subprograms as well. General flow is easiest to demonstrate with a simple example using number iterator implemented in next patch. Here's the simplest possible loop: struct bpf_iter_num it; int *v; bpf_iter_num_new(&it, 2, 5); while ((v = bpf_iter_num_next(&it))) { bpf_printk("X = %d", *v); } bpf_iter_num_destroy(&it); Above snippet should output "X = 2", "X = 3", "X = 4". Note that 5 is exclusive and is not returned. This matches similar APIs (e.g., slices in Go or Rust) that implement a range of elements, where end index is non-inclusive. In the above example, we see a trio of function: - constructor, bpf_iter_num_new(), which initializes iterator state (struct bpf_iter_num it) on the stack. If any of the input arguments are invalid, constructor should make sure to still initialize it such that subsequent bpf_iter_num_next() calls will return NULL. I.e., on error, return error and construct empty iterator. - next method, bpf_iter_num_next(), which accepts pointer to iterator state and produces an element. Next method should always return a pointer. The contract between BPF verifier is that next method will always eventually return NULL when elements are exhausted. Once NULL is returned, subsequent next calls should keep returning NULL. In the case of numbers iterator, bpf_iter_num_next() returns a pointer to an int (storage for this integer is inside the iterator state itself), which can be dereferenced after corresponding NULL check. - once done with the iterator, it's mandated that user cleans up its state with the call to destructor, bpf_iter_num_destroy() in this case. Destructor frees up any resources and marks stack space used by struct bpf_iter_num as usable for something else. Any other iterator implementation will have to implement at least these three methods. It is enforced that for any given type of iterator only applicable constructor/destructor/next are callable. I.e., verifier ensures you can't pass number iterator state into, say, cgroup iterator's next method. It is important to keep the naming pattern consistent to be able to create generic macros to help with BPF iter usability. E.g., one of the follow up patches adds generic bpf_for_each() macro to bpf_misc.h in selftests, which allows to utilize iterator "trio" nicely without having to code the above somewhat tedious loop explicitly every time. This is enforced at kfunc registration point by one of the previous patches in this series. At the implementation level, iterator state tracking for verification purposes is very similar to dynptr. We add STACK_ITER stack slot type, reserve necessary number of slots, depending on sizeof(struct bpf_iter_), and keep track of necessary extra state in the "main" slot, which is marked with non-zero ref_obj_id. Other slots are also marked as STACK_ITER, but have zero ref_obj_id. This is simpler than having a separate "is_first_slot" flag. Another big distinction is that STACK_ITER is *always refcounted*, which simplifies implementation without sacrificing usability. So no need for extra "iter_id", no need to anticipate reuse of STACK_ITER slots for new constructors, etc. Keeping it simple here. As far as the verification logic goes, there are two extensive comments: in process_iter_next_call() and iter_active_depths_differ() explaining some important and sometimes subtle aspects. Please refer to them for details. But from 10,000-foot point of view, next methods are the points of forking a verification state, which are conceptually similar to what verifier is doing when validating conditional jump. We branch out at a `call bpf_iter__next` instruction and simulate two outcomes: NULL (iteration is done) and non-NULL (new element is returned). NULL is simulated first and is supposed to reach exit without looping. After that non-NULL case is validated and it either reaches exit (for trivial examples with no real loop), or reaches another `call bpf_iter__next` instruction with the state equivalent to already (partially) validated one. State equivalency at that point means we technically are going to be looping forever without "breaking out" out of established "state envelope" (i.e., subsequent iterations don't add any new knowledge or constraints to the verifier state, so running 1, 2, 10, or a million of them doesn't matter). But taking into account the contract stating that iterator next method *has to* return NULL eventually, we can conclude that loop body is safe and will eventually terminate. Given we validated logic outside of the loop (NULL case), and concluded that loop body is safe (though potentially looping many times), verifier can claim safety of the overall program logic. The rest of the patch is necessary plumbing for state tracking, marking, validation, and necessary further kfunc plumbing to allow implementing iterator constructor, destructor, and next methods. Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/r/20230308184121.1165081-4-andrii@kernel.org Signed-off-by: Alexei Starovoitov --- include/linux/bpf_verifier.h | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index e2dc7f064449..0c052bc79940 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -61,6 +61,12 @@ struct bpf_active_lock { #define ITER_PREFIX "bpf_iter_" +enum bpf_iter_state { + BPF_ITER_STATE_INVALID, /* for non-first slot */ + BPF_ITER_STATE_ACTIVE, + BPF_ITER_STATE_DRAINED, +}; + struct bpf_reg_state { /* Ordering of fields matters. See states_equal() */ enum bpf_reg_type type; @@ -105,6 +111,18 @@ struct bpf_reg_state { bool first_slot; } dynptr; + /* For bpf_iter stack slots */ + struct { + /* BTF container and BTF type ID describing + * struct bpf_iter_ of an iterator state + */ + struct btf *btf; + u32 btf_id; + /* packing following two fields to fit iter state into 16 bytes */ + enum bpf_iter_state state:2; + int depth:30; + } iter; + /* Max size from any of the above. */ struct { unsigned long raw1; @@ -143,6 +161,8 @@ struct bpf_reg_state { * same reference to the socket, to determine proper reference freeing. * For stack slots that are dynptrs, this is used to track references to * the dynptr to determine proper reference freeing. + * Similarly to dynptrs, we use ID to track "belonging" of a reference + * to a specific instance of bpf_iter. */ u32 id; /* PTR_TO_SOCKET and PTR_TO_TCP_SOCK could be a ptr returned @@ -213,9 +233,11 @@ enum bpf_stack_slot_type { * is stored in bpf_stack_state->spilled_ptr.dynptr.type */ STACK_DYNPTR, + STACK_ITER, }; #define BPF_REG_SIZE 8 /* size of eBPF register in bytes */ + #define BPF_DYNPTR_SIZE sizeof(struct bpf_dynptr_kern) #define BPF_DYNPTR_NR_SLOTS (BPF_DYNPTR_SIZE / BPF_REG_SIZE) @@ -450,6 +472,7 @@ struct bpf_insn_aux_data { bool sanitize_stack_spill; /* subject to Spectre v4 sanitation */ 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__next() kfunc call */ u8 alu_state; /* used in combination with alu_limit */ /* below fields are initialized once */ -- cgit v1.2.3 From 6018e1f407cccf39b804d1f75ad4de7be4e6cc45 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Wed, 8 Mar 2023 10:41:17 -0800 Subject: bpf: implement numbers iterator Implement the first open-coded iterator type over a range of integers. It's public API consists of: - bpf_iter_num_new() constructor, which accepts [start, end) range (that is, start is inclusive, end is exclusive). - bpf_iter_num_next() which will keep returning read-only pointer to int until the range is exhausted, at which point NULL will be returned. If bpf_iter_num_next() is kept calling after this, NULL will be persistently returned. - bpf_iter_num_destroy() destructor, which needs to be called at some point to clean up iterator state. BPF verifier enforces that iterator destructor is called at some point before BPF program exits. Note that `start = end = X` is a valid combination to setup an empty iterator. bpf_iter_num_new() will return 0 (success) for any such combination. If bpf_iter_num_new() detects invalid combination of input arguments, it returns error, resets iterator state to, effectively, empty iterator, so any subsequent call to bpf_iter_num_next() will keep returning NULL. BPF verifier has no knowledge that returned integers are in the [start, end) value range, as both `start` and `end` are not statically known and enforced: they are runtime values. While the implementation is pretty trivial, some care needs to be taken to avoid overflows and underflows. Subsequent selftests will validate correctness of [start, end) semantics, especially around extremes (INT_MIN and INT_MAX). Similarly to bpf_loop(), we enforce that no more than BPF_MAX_LOOPS can be specified. bpf_iter_num_{new,next,destroy}() is a logical evolution from bounded BPF loops and bpf_loop() helper and is the basis for implementing ergonomic BPF loops with no statically known or verified bounds. Subsequent patches implement bpf_for() macro, demonstrating how this can be wrapped into something that works and feels like a normal for() loop in C language. Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/r/20230308184121.1165081-5-andrii@kernel.org Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 6792a7940e1e..e64ff1e89fb2 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1617,8 +1617,12 @@ struct bpf_array { #define BPF_COMPLEXITY_LIMIT_INSNS 1000000 /* yes. 1M insns */ #define MAX_TAIL_CALL_CNT 33 -/* Maximum number of loops for bpf_loop */ -#define BPF_MAX_LOOPS BIT(23) +/* Maximum number of loops for bpf_loop and bpf_iter_num. + * It's enum to expose it (and thus make it discoverable) through BTF. + */ +enum { + BPF_MAX_LOOPS = 8 * 1024 * 1024, +}; #define BPF_F_ACCESS_MASK (BPF_F_RDONLY | \ BPF_F_RDONLY_PROG | \ -- cgit v1.2.3 From 6486a57f05d3d40aa8698908de16feebe52e9f13 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Tue, 28 Feb 2023 15:11:06 +0300 Subject: livepatch: fix ELF typos ELF is acronym. Signed-off-by: Alexey Dobriyan Reviewed-by: Petr Mladek Signed-off-by: Petr Mladek Link: https://lore.kernel.org/r/Y/3vWjQ/SBA5a0i5@p183 --- include/linux/module.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/module.h b/include/linux/module.h index 4435ad9439ab..e65a71b04490 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -353,9 +353,9 @@ struct mod_kallsyms { #ifdef CONFIG_LIVEPATCH /** - * struct klp_modinfo - Elf information preserved from the livepatch module + * struct klp_modinfo - ELF information preserved from the livepatch module * - * @hdr: Elf header + * @hdr: ELF header * @sechdrs: Section header table * @secstrings: String table for the section headers * @symndx: The symbol table section index @@ -523,7 +523,7 @@ struct module { bool klp; /* Is this a livepatch module? */ bool klp_alive; - /* Elf information */ + /* ELF information */ struct klp_modinfo *klp_info; #endif -- cgit v1.2.3 From 85bce38a7e1f392f5051e67fd5fcfbffe71e9b81 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Fri, 17 Feb 2023 21:22:57 +0100 Subject: serial: 8250: Reorder fields in 'struct plat_serial8250_port' Group some variables based on their sizes to reduce hole and avoid padding. On x86_64, this shrinks the size of 'struct plat_serial8250_port' from 144 to 128 bytes. It saves a few bytes of memory. Signed-off-by: Christophe JAILLET Link: https://lore.kernel.org/r/f3cb1efe1454e0615840fd331ee335bc441589a9.1676665358.git.christophe.jaillet@wanadoo.fr Signed-off-by: Greg Kroah-Hartman --- include/linux/serial_8250.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/serial_8250.h b/include/linux/serial_8250.h index 19376bee9667..741ed4807a9c 100644 --- a/include/linux/serial_8250.h +++ b/include/linux/serial_8250.h @@ -18,16 +18,16 @@ struct plat_serial8250_port { unsigned long iobase; /* io base address */ void __iomem *membase; /* ioremap cookie or NULL */ resource_size_t mapbase; /* resource base */ + unsigned int uartclk; /* UART clock rate */ unsigned int irq; /* interrupt number */ unsigned long irqflags; /* request_irq flags */ - unsigned int uartclk; /* UART clock rate */ void *private_data; unsigned char regshift; /* register shift */ unsigned char iotype; /* UPIO_* */ unsigned char hub6; unsigned char has_sysrq; /* supports magic SysRq */ - upf_t flags; /* UPF_* flags */ unsigned int type; /* If UPF_FIXED_TYPE */ + upf_t flags; /* UPF_* flags */ unsigned int (*serial_in)(struct uart_port *, int); void (*serial_out)(struct uart_port *, int, int); void (*set_termios)(struct uart_port *, -- cgit v1.2.3 From 9b12f050c76f090cc6d0aebe0ef76fed79ec3f15 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Wed, 22 Feb 2023 10:23:02 +0100 Subject: char: pcmcia: remove all the drivers These char PCMCIA drivers are buggy[1] and receive only minimal care. It was concluded[2], that we should try to remove most pcmcia drivers completely. Let's start with these char broken one. Note that I also removed a UAPI header: include/uapi/linux/cm4000_cs.h. I found only coccinelle tests mentioning some ioctl constants from that file. But they are not actually used. Anyway, should someone complain, we may reintroduce the header (or its parts). [1] https://lore.kernel.org/all/f41c2765-80e0-48bc-b1e4-8cfd3230fd4a@www.fastmail.com/ [2] https://lore.kernel.org/all/c5b39544-a4fb-4796-a046-0b9be9853787@app.fastmail.com/ Signed-off-by: Jiri Slaby (SUSE) Cc: "Hyunwoo Kim" Cc: Harald Welte Cc: Lubomir Rintel Cc: Arnd Bergmann Cc: Greg Kroah-Hartman Acked-by: Dominik Brodowski Reviewed-by: Arnd Bergmann Link: https://lore.kernel.org/r/20230222092302.6348-2-jirislaby@kernel.org Signed-off-by: Greg Kroah-Hartman --- include/linux/cm4000_cs.h | 11 ----------- 1 file changed, 11 deletions(-) delete mode 100644 include/linux/cm4000_cs.h (limited to 'include/linux') diff --git a/include/linux/cm4000_cs.h b/include/linux/cm4000_cs.h deleted file mode 100644 index ea4958e07a14..000000000000 --- a/include/linux/cm4000_cs.h +++ /dev/null @@ -1,11 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _CM4000_H_ -#define _CM4000_H_ - -#include - - -#define DEVICE_NAME "cmm" -#define MODULE_NAME "cm4000_cs" - -#endif /* _CM4000_H_ */ -- cgit v1.2.3 From 8efc52743ecb5c69d2e4faba965a3e14418c2494 Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Tue, 7 Mar 2023 15:38:16 -0600 Subject: misc: alcor_pci: Use PCI core to manage ASPM instead of open-coding "priv->ext_config_dev_aspm" was never set to a non-zero value. Therefore, alcor_pci_aspm_ctrl(priv, 1) did nothing, and alcor_pci_aspm_ctrl(priv, 0) always disabled ASPM in the device and the upstream bridge. The driver disabled ASPM in alcor_pci_probe() and alcor_resume(), so it's possible the device doesn't work well when ASPM is enabled. Remove all the ASPM-related code and replace the alcor_pci_aspm_ctrl(0) calls with pci_disable_link_state(pdev, PCIE_LINK_STATE_L0S | PCIE_LINK_STATE_L1), which asks the PCI core to disable ASPM. Signed-off-by: Bjorn Helgaas Cc: Oleksij Rempel Reviewed-by: Oleksij Rempel Link: https://lore.kernel.org/r/20230307213816.886308-1-helgaas@kernel.org Signed-off-by: Greg Kroah-Hartman --- include/linux/alcor_pci.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/alcor_pci.h b/include/linux/alcor_pci.h index 8274ed525e9f..c4a0b23846d8 100644 --- a/include/linux/alcor_pci.h +++ b/include/linux/alcor_pci.h @@ -268,13 +268,6 @@ struct alcor_pci_priv { unsigned long id; /* idr id */ struct alcor_dev_cfg *cfg; - - /* PCI ASPM related vars */ - int pdev_cap_off; - u8 pdev_aspm_cap; - int parent_cap_off; - u8 parent_aspm_cap; - u8 ext_config_dev_aspm; }; void alcor_write8(struct alcor_pci_priv *priv, u8 val, unsigned int addr); -- cgit v1.2.3 From 8f118f61540e23fb0e4ec84aec361f6758dbe93a Mon Sep 17 00:00:00 2001 From: Nava kishore Manne Date: Fri, 24 Feb 2023 17:37:37 +0530 Subject: firmware: xilinx: Add pm api function for PL config reg readback Adds PM API for performing Programmable Logic(PL) configuration register readback. It provides an interface to the firmware(pmufw) to readback the FPGA configuration register. Signed-off-by: Nava kishore Manne Acked-by: Xu Yilun Link: https://lore.kernel.org/r/20230224120738.329416-2-nava.kishore.manne@amd.com Signed-off-by: Greg Kroah-Hartman --- include/linux/firmware/xlnx-zynqmp.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index 0e4c70987e6a..f5da51677069 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -71,6 +71,10 @@ #define XILINX_ZYNQMP_PM_FPGA_FULL 0x0U #define XILINX_ZYNQMP_PM_FPGA_PARTIAL BIT(0) +/* FPGA Status Reg */ +#define XILINX_ZYNQMP_PM_FPGA_CONFIG_STAT_OFFSET 7U +#define XILINX_ZYNQMP_PM_FPGA_READ_CONFIG_REG 0U + /* * Node IDs for the Error Events. */ @@ -124,6 +128,7 @@ enum pm_api_id { PM_CLOCK_GETRATE = 42, PM_CLOCK_SETPARENT = 43, PM_CLOCK_GETPARENT = 44, + PM_FPGA_READ = 46, PM_SECURE_AES = 47, PM_FEATURE_CHECK = 63, }; @@ -519,6 +524,7 @@ int zynqmp_pm_aes_engine(const u64 address, u32 *out); int zynqmp_pm_sha_hash(const u64 address, const u32 size, const u32 flags); int zynqmp_pm_fpga_load(const u64 address, const u32 size, const u32 flags); int zynqmp_pm_fpga_get_status(u32 *value); +int zynqmp_pm_fpga_get_config_status(u32 *value); int zynqmp_pm_write_ggs(u32 index, u32 value); int zynqmp_pm_read_ggs(u32 index, u32 *value); int zynqmp_pm_write_pggs(u32 index, u32 value); @@ -725,6 +731,11 @@ static inline int zynqmp_pm_fpga_get_status(u32 *value) return -ENODEV; } +static inline int zynqmp_pm_fpga_get_config_status(u32 *value) +{ + return -ENODEV; +} + static inline int zynqmp_pm_write_ggs(u32 index, u32 value) { return -ENODEV; -- cgit v1.2.3 From ac3b43283923440900b4f36ca5f9f0b1ca43b70e Mon Sep 17 00:00:00 2001 From: Song Liu Date: Mon, 6 Feb 2023 16:28:02 -0800 Subject: module: replace module_layout with module_memory module_layout manages different types of memory (text, data, rodata, etc.) in one allocation, which is problematic for some reasons: 1. It is hard to enable CONFIG_STRICT_MODULE_RWX. 2. It is hard to use huge pages in modules (and not break strict rwx). 3. Many archs uses module_layout for arch-specific data, but it is not obvious how these data are used (are they RO, RX, or RW?) Improve the scenario by replacing 2 (or 3) module_layout per module with up to 7 module_memory per module: MOD_TEXT, MOD_DATA, MOD_RODATA, MOD_RO_AFTER_INIT, MOD_INIT_TEXT, MOD_INIT_DATA, MOD_INIT_RODATA, and allocating them separately. This adds slightly more entries to mod_tree (from up to 3 entries per module, to up to 7 entries per module). However, this at most adds a small constant overhead to __module_address(), which is expected to be fast. Various archs use module_layout for different data. These data are put into different module_memory based on their location in module_layout. IOW, data that used to go with text is allocated with MOD_MEM_TYPE_TEXT; data that used to go with data is allocated with MOD_MEM_TYPE_DATA, etc. module_memory simplifies quite some of the module code. For example, ARCH_WANTS_MODULES_DATA_IN_VMALLOC is a lot cleaner, as it just uses a different allocator for the data. kernel/module/strict_rwx.c is also much cleaner with module_memory. Signed-off-by: Song Liu Cc: Luis Chamberlain Cc: Thomas Gleixner Cc: Peter Zijlstra Cc: Guenter Roeck Cc: Christophe Leroy Reviewed-by: Thomas Gleixner Reviewed-by: Christophe Leroy Reviewed-by: Luis Chamberlain Signed-off-by: Luis Chamberlain --- include/linux/module.h | 89 +++++++++++++++++++++++++++++++++++--------------- 1 file changed, 63 insertions(+), 26 deletions(-) (limited to 'include/linux') diff --git a/include/linux/module.h b/include/linux/module.h index 4435ad9439ab..c0593a96e158 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -320,17 +320,47 @@ struct mod_tree_node { struct latch_tree_node node; }; -struct module_layout { - /* The actual code + data. */ +enum mod_mem_type { + MOD_TEXT = 0, + MOD_DATA, + MOD_RODATA, + MOD_RO_AFTER_INIT, + MOD_INIT_TEXT, + MOD_INIT_DATA, + MOD_INIT_RODATA, + + MOD_MEM_NUM_TYPES, + MOD_INVALID = -1, +}; + +#define mod_mem_type_is_init(type) \ + ((type) == MOD_INIT_TEXT || \ + (type) == MOD_INIT_DATA || \ + (type) == MOD_INIT_RODATA) + +#define mod_mem_type_is_core(type) (!mod_mem_type_is_init(type)) + +#define mod_mem_type_is_text(type) \ + ((type) == MOD_TEXT || \ + (type) == MOD_INIT_TEXT) + +#define mod_mem_type_is_data(type) (!mod_mem_type_is_text(type)) + +#define mod_mem_type_is_core_data(type) \ + (mod_mem_type_is_core(type) && \ + mod_mem_type_is_data(type)) + +#define for_each_mod_mem_type(type) \ + for (enum mod_mem_type (type) = 0; \ + (type) < MOD_MEM_NUM_TYPES; (type)++) + +#define for_class_mod_mem_type(type, class) \ + for_each_mod_mem_type(type) \ + if (mod_mem_type_is_##class(type)) + +struct module_memory { void *base; - /* Total size. */ unsigned int size; - /* The size of the executable code. */ - unsigned int text_size; - /* Size of RO section of the module (text+rodata) */ - unsigned int ro_size; - /* Size of RO after init section */ - unsigned int ro_after_init_size; #ifdef CONFIG_MODULES_TREE_LOOKUP struct mod_tree_node mtn; @@ -339,9 +369,9 @@ struct module_layout { #ifdef CONFIG_MODULES_TREE_LOOKUP /* Only touch one cacheline for common rbtree-for-core-layout case. */ -#define __module_layout_align ____cacheline_aligned +#define __module_memory_align ____cacheline_aligned #else -#define __module_layout_align +#define __module_memory_align #endif struct mod_kallsyms { @@ -426,12 +456,7 @@ struct module { /* Startup function. */ int (*init)(void); - /* Core layout: rbtree is accessed frequently, so keep together. */ - struct module_layout core_layout __module_layout_align; - struct module_layout init_layout; -#ifdef CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC - struct module_layout data_layout; -#endif + struct module_memory mem[MOD_MEM_NUM_TYPES] __module_memory_align; /* Arch-specific module values */ struct mod_arch_specific arch; @@ -581,23 +606,35 @@ bool __is_module_percpu_address(unsigned long addr, unsigned long *can_addr); bool is_module_percpu_address(unsigned long addr); bool is_module_text_address(unsigned long addr); +static inline bool within_module_mem_type(unsigned long addr, + const struct module *mod, + enum mod_mem_type type) +{ + unsigned long base, size; + + base = (unsigned long)mod->mem[type].base; + size = mod->mem[type].size; + return addr - base < size; +} + static inline bool within_module_core(unsigned long addr, const struct module *mod) { -#ifdef CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC - if ((unsigned long)mod->data_layout.base <= addr && - addr < (unsigned long)mod->data_layout.base + mod->data_layout.size) - return true; -#endif - return (unsigned long)mod->core_layout.base <= addr && - addr < (unsigned long)mod->core_layout.base + mod->core_layout.size; + for_class_mod_mem_type(type, core) { + if (within_module_mem_type(addr, mod, type)) + return true; + } + return false; } static inline bool within_module_init(unsigned long addr, const struct module *mod) { - return (unsigned long)mod->init_layout.base <= addr && - addr < (unsigned long)mod->init_layout.base + mod->init_layout.size; + for_class_mod_mem_type(type, init) { + if (within_module_mem_type(addr, mod, type)) + return true; + } + return false; } static inline bool within_module(unsigned long addr, const struct module *mod) -- cgit v1.2.3 From 042edf1ebb49a63f299c4cdfb9c1e2ba299c0b91 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= Date: Sat, 4 Feb 2023 05:44:46 +0000 Subject: module: make module_ktype structure constant MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Since commit ee6d3dd4ed48 ("driver core: make kobj_type constant.") the driver core allows the usage of const struct kobj_type. Take advantage of this to constify the structure definition to prevent modification at runtime. Signed-off-by: Thomas Weißschuh Signed-off-by: Luis Chamberlain --- include/linux/module.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/module.h b/include/linux/module.h index c0593a96e158..dbc9124b71bc 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -871,7 +871,7 @@ void *dereference_module_function_descriptor(struct module *mod, void *ptr) #ifdef CONFIG_SYSFS extern struct kset *module_kset; -extern struct kobj_type module_ktype; +extern const struct kobj_type module_ktype; #endif /* CONFIG_SYSFS */ #define symbol_request(x) try_then_request_module(symbol_get(x), "symbol:" #x) -- cgit v1.2.3 From 7deabd67498869640c937c9bd83472574b7dea0b Mon Sep 17 00:00:00 2001 From: Jason Baron Date: Fri, 3 Mar 2023 11:50:56 -0500 Subject: dyndbg: use the module notifier callbacks Bring dynamic debug in line with other subsystems by using the module notifier callbacks. This results in a net decrease in core module code. Additionally, Jim Cromie has a new dynamic debug classmap feature, which requires that jump labels be initialized prior to dynamic debug. Specifically, the new feature toggles a jump label from the existing dynamic_debug_setup() function. However, this does not currently work properly, because jump labels are initialized via the 'module_notify_list' notifier chain, which is invoked after the current call to dynamic_debug_setup(). Thus, this patch ensures that jump labels are initialized prior to dynamic debug by setting the dynamic debug notifier priority to 0, while jump labels have the higher priority of 1. Tested by Jim using his new test case, and I've verfied the correct printing via: # modprobe test_dynamic_debug dyndbg. Link: https://lore.kernel.org/lkml/20230113193016.749791-21-jim.cromie@gmail.com/ Reported-by: kernel test robot Link: https://lore.kernel.org/oe-kbuild-all/202302190427.9iIK2NfJ-lkp@intel.com/ Tested-by: Jim Cromie Reviewed-by: Vincenzo Palazzo Cc: Peter Zijlstra CC: Jim Cromie Cc: Luis Chamberlain Cc: Greg Kroah-Hartman Signed-off-by: Jason Baron Signed-off-by: Luis Chamberlain --- include/linux/dynamic_debug.h | 13 ------------- include/linux/module.h | 4 ++++ 2 files changed, 4 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dynamic_debug.h b/include/linux/dynamic_debug.h index 41682278d2e8..f401414341fb 100644 --- a/include/linux/dynamic_debug.h +++ b/include/linux/dynamic_debug.h @@ -130,9 +130,6 @@ struct ddebug_class_param { #if defined(CONFIG_DYNAMIC_DEBUG_CORE) -int ddebug_add_module(struct _ddebug_info *dyndbg, const char *modname); - -extern int ddebug_remove_module(const char *mod_name); extern __printf(2, 3) void __dynamic_pr_debug(struct _ddebug *descriptor, const char *fmt, ...); @@ -304,16 +301,6 @@ int param_get_dyndbg_classes(char *buffer, const struct kernel_param *kp); #include #include -static inline int ddebug_add_module(struct _ddebug_info *dinfo, const char *modname) -{ - return 0; -} - -static inline int ddebug_remove_module(const char *mod) -{ - return 0; -} - static inline int ddebug_dyndbg_module_param_cb(char *param, char *val, const char *modname) { diff --git a/include/linux/module.h b/include/linux/module.h index dbc9124b71bc..91726444d55f 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -27,6 +27,7 @@ #include #include #include +#include #include #include @@ -579,6 +580,9 @@ struct module { struct error_injection_entry *ei_funcs; unsigned int num_ei_funcs; #endif +#ifdef CONFIG_DYNAMIC_DEBUG_CORE + struct _ddebug_info dyndbg_info; +#endif } ____cacheline_aligned __randomize_layout; #ifndef MODULE_ARCH_INIT #define MODULE_ARCH_INIT {} -- cgit v1.2.3 From 6978052448f9eb19f7b03243ac0416104e5ee50d Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Wed, 8 Mar 2023 15:20:06 +0100 Subject: netlink: remove unused 'compare' function No users in the tree. Tested with allmodconfig build. Signed-off-by: Florian Westphal Link: https://lore.kernel.org/r/20230308142006.20879-1-fw@strlen.de Signed-off-by: Jakub Kicinski --- include/linux/netlink.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netlink.h b/include/linux/netlink.h index c43ac7690eca..3e8743252167 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -50,7 +50,6 @@ struct netlink_kernel_cfg { struct mutex *cb_mutex; int (*bind)(struct net *net, int group); void (*unbind)(struct net *net, int group); - bool (*compare)(struct net *net, struct sock *sk); }; struct sock *__netlink_kernel_create(struct net *net, int unit, -- cgit v1.2.3 From 0433686c6092f65b552eadad651f620e51b6aad1 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Fri, 24 Feb 2023 22:07:45 +0200 Subject: devres: Pass unique name of the resource to devm_add_action() Pass the unique name of the resource to devm_add_action(), so it will be easier to debug managed resources. Signed-off-by: Andy Shevchenko Link: https://lore.kernel.org/r/20230224200745.17324-1-andriy.shevchenko@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 19b6ba478fbf..0f128520f6e5 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -243,10 +243,13 @@ void __iomem *devm_of_iomap(struct device *dev, resource_size_t *size); /* allows to add/remove a custom action to devres stack */ -int devm_add_action(struct device *dev, void (*action)(void *), void *data); void devm_remove_action(struct device *dev, void (*action)(void *), void *data); void devm_release_action(struct device *dev, void (*action)(void *), void *data); +int __devm_add_action(struct device *dev, void (*action)(void *), void *data, const char *name); +#define devm_add_action(release, action, data) \ + __devm_add_action(release, action, data, #action) + static inline int devm_add_action_or_reset(struct device *dev, void (*action)(void *), void *data) { -- cgit v1.2.3 From 740b2f03f80e8f50c3f96309bc123bea040de8d0 Mon Sep 17 00:00:00 2001 From: fengqi Date: Thu, 16 Feb 2023 16:48:30 +0800 Subject: HID: add KEY_CAMERA_FOCUS event in HID Our HID device need KEY_CAMERA_FOCUS event to control camera, but this event is non-existent in current HID driver. So we add this event in hid-input.c. Signed-off-by: fengqi Reviewed-by: Greg Kroah-Hartman Signed-off-by: Jiri Kosina --- include/linux/hid.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/hid.h b/include/linux/hid.h index 1ea8c7a3570b..bff9f459db36 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -156,6 +156,7 @@ struct hid_item { #define HID_UP_DIGITIZER 0x000d0000 #define HID_UP_PID 0x000f0000 #define HID_UP_BATTERY 0x00850000 +#define HID_UP_CAMERA 0x00900000 #define HID_UP_HPVENDOR 0xff7f0000 #define HID_UP_HPVENDOR2 0xff010000 #define HID_UP_MSVENDOR 0xff000000 -- cgit v1.2.3 From 4b5ce570dbef57a20acdd71b0c65376009012354 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Thu, 9 Mar 2023 22:01:49 -0800 Subject: bpf: ensure state checkpointing at iter_next() call sites State equivalence check and checkpointing performed in is_state_visited() employs certain heuristics to try to save memory by avoiding state checkpoints if not enough jumps and instructions happened since last checkpoint. This leads to unpredictability of whether a particular instruction will be checkpointed and how regularly. While normally this is not causing much problems (except inconveniences for predictable verifier tests, which we overcome with BPF_F_TEST_STATE_FREQ flag), turns out it's not the case for open-coded iterators. Checking and saving state checkpoints at iter_next() call is crucial for fast convergence of open-coded iterator loop logic, so we need to force it. If we don't do that, is_state_visited() might skip saving a checkpoint, causing unnecessarily long sequence of not checkpointed instructions and jumps, leading to exhaustion of jump history buffer, and potentially other undesired outcomes. It is expected that with correct open-coded iterators convergence will happen quickly, so we don't run a risk of exhausting memory. This patch adds, in addition to prune and jump instruction marks, also a "forced checkpoint" mark, and makes sure that any iter_next() call instruction is marked as such. Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/r/20230310060149.625887-1-andrii@kernel.org Signed-off-by: Alexei Starovoitov --- include/linux/bpf_verifier.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 0c052bc79940..81d525d057c7 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -477,8 +477,12 @@ struct bpf_insn_aux_data { /* below fields are initialized once */ unsigned int orig_idx; /* original instruction index */ - bool prune_point; bool jmp_point; + bool prune_point; + /* ensure we check state equivalence and save state checkpoint and + * this instruction, regardless of any heuristics + */ + bool force_checkpoint; }; #define MAX_USED_MAPS 64 /* max number of maps accessed by one eBPF program */ -- cgit v1.2.3 From 557aafac11530a283bebf2dea4cec62765d8df0f Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Fri, 10 Mar 2023 10:55:59 -0800 Subject: kernel/module: add documentation for try_module_get() There is quite a bit of tribal knowledge around proper use of try_module_get() and requiring *somehow* the module to still exist to use this call in a way that is safe. Document this bit of tribal knowledge. To be clear, you should only use try_module_get() *iff* you are 100% sure the module already does exist and is not on its way out. You can be sure the module still exists and is alive through: 1) Direct protection with its refcount: you know some earlier caller called __module_get() safely 2) Implied protection: there is an implied protection against module removal Having an idea of when you are sure __module_get() might be called earlier is easy to understand however the implied protection requires an example. We use sysfs an an example for implied protection without a direct module reference count bump. kernfs / sysfs uses its own internal reference counting for files being actively used, when such file are active they completely prevent the module from being removed. kernfs protects this with its kernfs_active(). Effort has been put into verifying the kernfs implied protection works by using a currently out-of-tree test_sysfs selftest test #32 [0]: ./tools/testing/selftests/sysfs/sysfs.sh -t 0032 Without kernfs / sysfs preventing module removal through its active reference count (kernfs_active()) the write would fail or worse, a crash would happen in this test and it does not. Similar safeguards are required for other users of try_module_get() *iff* they are not ensuring the above rule 1) is followed. [0] https://lore.kernel.org/lkml/20211029184500.2821444-4-mcgrof@kernel.org/ Signed-off-by: Luis Chamberlain --- include/linux/module.h | 40 ++++++++++++++++++++++++++++++++++++++-- 1 file changed, 38 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/module.h b/include/linux/module.h index 91726444d55f..c3b357196470 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -671,10 +671,46 @@ void symbol_put_addr(void *addr); to handle the error case (which only happens with rmmod --wait). */ extern void __module_get(struct module *module); -/* This is the Right Way to get a module: if it fails, it's being removed, - * so pretend it's not there. */ +/** + * try_module_get() - take module refcount unless module is being removed + * @module: the module we should check for + * + * Only try to get a module reference count if the module is not being removed. + * This call will fail if the module is already being removed. + * + * Care must also be taken to ensure the module exists and is alive prior to + * usage of this call. This can be gauranteed through two means: + * + * 1) Direct protection: you know an earlier caller must have increased the + * module reference through __module_get(). This can typically be achieved + * by having another entity other than the module itself increment the + * module reference count. + * + * 2) Implied protection: there is an implied protection against module + * removal. An example of this is the implied protection used by kernfs / + * sysfs. The sysfs store / read file operations are guaranteed to exist + * through the use of kernfs's active reference (see kernfs_active()) and a + * sysfs / kernfs file removal cannot happen unless the same file is not + * active. Therefore, if a sysfs file is being read or written to the module + * which created it must still exist. It is therefore safe to use + * try_module_get() on module sysfs store / read ops. + * + * One of the real values to try_module_get() is the module_is_live() check + * which ensures that the caller of try_module_get() can yield to userspace + * module removal requests and gracefully fail if the module is on its way out. + * + * Returns true if the reference count was successfully incremented. + */ extern bool try_module_get(struct module *module); +/** + * module_put() - release a reference count to a module + * @module: the module we should release a reference count for + * + * If you successfully bump a reference count to a module with try_module_get(), + * when you are finished you must call module_put() to release that reference + * count. + */ extern void module_put(struct module *module); #else /*!CONFIG_MODULE_UNLOAD*/ -- cgit v1.2.3 From 4cbd23cc92c49173e402753cab62b8a7754ed18f Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Tue, 7 Mar 2023 22:59:20 -0800 Subject: bpf: Move a few bpf_local_storage functions to static scope This patch moves the bpf_local_storage_free_rcu() and bpf_selem_unlink_map() to static because they are not used outside of bpf_local_storage.c. Signed-off-by: Martin KaFai Lau Link: https://lore.kernel.org/r/20230308065936.1550103-2-martin.lau@linux.dev Signed-off-by: Alexei Starovoitov --- include/linux/bpf_local_storage.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf_local_storage.h b/include/linux/bpf_local_storage.h index d934248b8e81..502ad7093f13 100644 --- a/include/linux/bpf_local_storage.h +++ b/include/linux/bpf_local_storage.h @@ -147,8 +147,6 @@ void bpf_selem_unlink(struct bpf_local_storage_elem *selem, bool use_trace_rcu); void bpf_selem_link_map(struct bpf_local_storage_map *smap, struct bpf_local_storage_elem *selem); -void bpf_selem_unlink_map(struct bpf_local_storage_elem *selem); - struct bpf_local_storage_elem * bpf_selem_alloc(struct bpf_local_storage_map *smap, void *owner, void *value, bool charge_mem, gfp_t gfp_flags); @@ -163,7 +161,6 @@ struct bpf_local_storage_data * bpf_local_storage_update(void *owner, struct bpf_local_storage_map *smap, void *value, u64 map_flags, gfp_t gfp_flags); -void bpf_local_storage_free_rcu(struct rcu_head *rcu); u64 bpf_local_storage_map_mem_usage(const struct bpf_map *map); #endif /* _BPF_LOCAL_STORAGE_H */ -- cgit v1.2.3 From 2ffcb6fc50174d1efc8f98633eb2647d84483c68 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Tue, 7 Mar 2023 22:59:21 -0800 Subject: bpf: Refactor codes into bpf_local_storage_destroy This patch first renames bpf_local_storage_unlink_nolock to bpf_local_storage_destroy(). It better reflects that it is only used when the storage's owner (sk/task/cgrp/inode) is being kfree(). All bpf_local_storage_destroy's caller is taking the spin lock and then free the storage. This patch also moves these two steps into the bpf_local_storage_destroy. This is a preparation work for a later patch that uses bpf_mem_cache_alloc/free in the bpf_local_storage. Signed-off-by: Martin KaFai Lau Link: https://lore.kernel.org/r/20230308065936.1550103-3-martin.lau@linux.dev Signed-off-by: Alexei Starovoitov --- include/linux/bpf_local_storage.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bpf_local_storage.h b/include/linux/bpf_local_storage.h index 502ad7093f13..5908a954ddc2 100644 --- a/include/linux/bpf_local_storage.h +++ b/include/linux/bpf_local_storage.h @@ -128,7 +128,7 @@ bpf_local_storage_lookup(struct bpf_local_storage *local_storage, struct bpf_local_storage_map *smap, bool cacheit_lockit); -bool bpf_local_storage_unlink_nolock(struct bpf_local_storage *local_storage); +void bpf_local_storage_destroy(struct bpf_local_storage *local_storage); void bpf_local_storage_map_free(struct bpf_map *map, struct bpf_local_storage_cache *cache, -- cgit v1.2.3 From fc6652aab6ad545de70b772550da9043d0b47f1c Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Tue, 7 Mar 2023 22:59:24 -0800 Subject: bpf: Remember smap in bpf_local_storage This patch remembers which smap triggers the allocation of a 'struct bpf_local_storage' object. The local_storage is allocated during the very first selem added to the owner. The smap pointer is needed when using the bpf_mem_cache_free in a later patch because it needs to free to the correct smap's bpf_mem_alloc object. When a selem is being removed, it needs to check if it is the selem that triggers the creation of the local_storage. If it is, the local_storage->smap pointer will be reset to NULL. This NULL reset is done under the local_storage->lock in bpf_selem_unlink_storage_nolock() when a selem is being removed. Also note that the local_storage may not go away even local_storage->smap is NULL because there may be other selem still stored in the local_storage. Signed-off-by: Martin KaFai Lau Link: https://lore.kernel.org/r/20230308065936.1550103-6-martin.lau@linux.dev Signed-off-by: Alexei Starovoitov --- include/linux/bpf_local_storage.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/bpf_local_storage.h b/include/linux/bpf_local_storage.h index 5908a954ddc2..613b1805ed9f 100644 --- a/include/linux/bpf_local_storage.h +++ b/include/linux/bpf_local_storage.h @@ -83,6 +83,7 @@ struct bpf_local_storage_elem { struct bpf_local_storage { struct bpf_local_storage_data __rcu *cache[BPF_LOCAL_STORAGE_CACHE_SIZE]; + struct bpf_local_storage_map __rcu *smap; struct hlist_head list; /* List of bpf_local_storage_elem */ void *owner; /* The object that owns the above "list" of * bpf_local_storage_elem. -- cgit v1.2.3 From a47eabf216f77cb6f22ceb38d46f1bb95968579c Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Tue, 7 Mar 2023 22:59:25 -0800 Subject: bpf: Repurpose use_trace_rcu to reuse_now in bpf_local_storage This patch re-purpose the use_trace_rcu to mean if the freed memory can be reused immediately or not. The use_trace_rcu is renamed to reuse_now. Other than the boolean test is reversed, it should be a no-op. The following explains the reason for the rename and how it will be used in a later patch. In a later patch, bpf_mem_cache_alloc/free will be used in the bpf_local_storage. The bpf mem allocator will reuse the freed memory immediately. Some of the free paths in bpf_local_storage does not support memory to be reused immediately. These paths are the "delete" elem cases from the bpf_*_storage_delete() helper and the map_delete_elem() syscall. Note that "delete" elem before the owner's (sk/task/cgrp/inode) lifetime ended is not the common usage for the local storage. The common free path, bpf_local_storage_destroy(), can reuse the memory immediately. This common path means the storage stays with its owner until the owner is destroyed. The above mentioned "delete" elem paths that cannot reuse immediately always has the 'use_trace_rcu == true'. The cases that is safe for immediate reuse always have 'use_trace_rcu == false'. Instead of adding another arg in a later patch, this patch re-purpose this arg to reuse_now and have the test logic reversed. In a later patch, 'reuse_now == true' will free to the bpf_mem_cache_free() where the memory can be reused immediately. 'reuse_now == false' will go through the call_rcu_tasks_trace(). Signed-off-by: Martin KaFai Lau Link: https://lore.kernel.org/r/20230308065936.1550103-7-martin.lau@linux.dev Signed-off-by: Alexei Starovoitov --- include/linux/bpf_local_storage.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bpf_local_storage.h b/include/linux/bpf_local_storage.h index 613b1805ed9f..18a31add2255 100644 --- a/include/linux/bpf_local_storage.h +++ b/include/linux/bpf_local_storage.h @@ -143,7 +143,7 @@ int bpf_local_storage_map_check_btf(const struct bpf_map *map, void bpf_selem_link_storage_nolock(struct bpf_local_storage *local_storage, struct bpf_local_storage_elem *selem); -void bpf_selem_unlink(struct bpf_local_storage_elem *selem, bool use_trace_rcu); +void bpf_selem_unlink(struct bpf_local_storage_elem *selem, bool reuse_now); void bpf_selem_link_map(struct bpf_local_storage_map *smap, struct bpf_local_storage_elem *selem); -- cgit v1.2.3 From c0d63f309186d8492577c67c67984c714b6b72bc Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Tue, 7 Mar 2023 22:59:28 -0800 Subject: bpf: Add bpf_selem_free() This patch refactors the selem freeing logic into bpf_selem_free(). It is a preparation work for a later patch using bpf_mem_cache_alloc/free. The other kfree(selem) cases are also changed to bpf_selem_free(..., reuse_now = true). Signed-off-by: Martin KaFai Lau Link: https://lore.kernel.org/r/20230308065936.1550103-10-martin.lau@linux.dev Signed-off-by: Alexei Starovoitov --- include/linux/bpf_local_storage.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf_local_storage.h b/include/linux/bpf_local_storage.h index 18a31add2255..a34f61467a2f 100644 --- a/include/linux/bpf_local_storage.h +++ b/include/linux/bpf_local_storage.h @@ -152,6 +152,10 @@ struct bpf_local_storage_elem * bpf_selem_alloc(struct bpf_local_storage_map *smap, void *owner, void *value, bool charge_mem, gfp_t gfp_flags); +void bpf_selem_free(struct bpf_local_storage_elem *selem, + struct bpf_local_storage_map *smap, + bool reuse_now); + int bpf_local_storage_alloc(void *owner, struct bpf_local_storage_map *smap, -- cgit v1.2.3 From d3c7ec7588508bd59bbb0e468d3820f3d3cba690 Mon Sep 17 00:00:00 2001 From: Palmer Dabbelt Date: Fri, 10 Mar 2023 17:07:55 +0100 Subject: Move bp_type_idx to include/linux/hw_breakpoint.h This has a "#ifdef CONFIG_*" that used to be exposed to userspace. The names in here are so generic that I don't think it's a good idea to expose them to userspace (or even the rest of the kernel). There are multiple in-kernel users, so it's been moved to a kernel header file. Signed-off-by: Palmer Dabbelt Reviewed-by: Andrew Waterman Reviewed-by: Albert Ou Message-Id: <1447119071-19392-10-git-send-email-palmer@dabbelt.com> [thuth: Remove it also from tools/include/uapi/linux/hw_breakpoint.h] Reviewed-by: Arnd Bergmann Reviewed-by: Christoph Hellwig Signed-off-by: Thomas Huth Signed-off-by: Arnd Bergmann --- include/linux/hw_breakpoint.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hw_breakpoint.h b/include/linux/hw_breakpoint.h index f319bd26b030..7fbb45911273 100644 --- a/include/linux/hw_breakpoint.h +++ b/include/linux/hw_breakpoint.h @@ -7,6 +7,16 @@ #ifdef CONFIG_HAVE_HW_BREAKPOINT +enum bp_type_idx { + TYPE_INST = 0, +#if defined(CONFIG_HAVE_MIXED_BREAKPOINTS_REGS) + TYPE_DATA = 0, +#else + TYPE_DATA = 1, +#endif + TYPE_MAX +}; + extern int __init init_hw_breakpoint(void); static inline void hw_breakpoint_init(struct perf_event_attr *attr) -- cgit v1.2.3 From 74843b57ec70af7b67b7e6153374834ee18d139f Mon Sep 17 00:00:00 2001 From: Dave Marchevsky Date: Thu, 9 Mar 2023 10:01:08 -0800 Subject: bpf: Change btf_record_find enum parameter to field_mask btf_record_find's 3rd parameter can be multiple enum btf_field_type's masked together. The function is called with BPF_KPTR in two places in verifier.c, so it works with masked values already. Signed-off-by: Dave Marchevsky Link: https://lore.kernel.org/r/20230309180111.1618459-4-davemarchevsky@fb.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index e64ff1e89fb2..3a38db315f7f 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1925,7 +1925,7 @@ void bpf_prog_free_id(struct bpf_prog *prog); void bpf_map_free_id(struct bpf_map *map); struct btf_field *btf_record_find(const struct btf_record *rec, - u32 offset, enum btf_field_type type); + u32 offset, u32 field_mask); void btf_record_free(struct btf_record *rec); void bpf_map_free_record(struct bpf_map *map); struct btf_record *btf_record_dup(const struct btf_record *rec); -- cgit v1.2.3 From 42994ee3cd7298b27698daa6848ed7168e72d056 Mon Sep 17 00:00:00 2001 From: Roberto Sassu Date: Fri, 10 Mar 2023 09:53:59 +0100 Subject: security: Introduce LSM_ORDER_LAST and set it for the integrity LSM Introduce LSM_ORDER_LAST, to satisfy the requirement of LSMs needing to be last, e.g. the 'integrity' LSM, without changing the kernel command line or configuration. Also, set this order for the 'integrity' LSM. While not enforced, this is the only LSM expected to use it. Similarly to LSM_ORDER_FIRST, LSMs with LSM_ORDER_LAST are always enabled and put at the end of the LSM list, if selected in the kernel configuration. Setting one of these orders alone, does not cause the LSMs to be selected and compiled built-in in the kernel. Finally, for LSM_ORDER_MUTABLE LSMs, set the found variable to true if an LSM is found, regardless of its order. In this way, the kernel would not wrongly report that the LSM is not built-in in the kernel if its order is LSM_ORDER_LAST. Fixes: 79f7865d844c ("LSM: Introduce "lsm=" for boottime LSM selection") Signed-off-by: Roberto Sassu Acked-by: Mimi Zohar Signed-off-by: Paul Moore --- include/linux/lsm_hooks.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index ddbbe89a7a48..c2be66c669ae 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -92,6 +92,7 @@ extern void security_add_hooks(struct security_hook_list *hooks, int count, enum lsm_order { LSM_ORDER_FIRST = -1, /* This is only for capabilities. */ LSM_ORDER_MUTABLE = 0, + LSM_ORDER_LAST = 1, /* This is only for integrity. */ }; struct lsm_info { -- cgit v1.2.3 From c8e18754091479fac3f5b6c053c6bc4be0b7fb11 Mon Sep 17 00:00:00 2001 From: Dave Marchevsky Date: Fri, 10 Mar 2023 15:07:41 -0800 Subject: bpf: Support __kptr to local kptrs If a PTR_TO_BTF_ID type comes from program BTF - not vmlinux or module BTF - it must have been allocated by bpf_obj_new and therefore must be free'd with bpf_obj_drop. Such a PTR_TO_BTF_ID is considered a "local kptr" and is tagged with MEM_ALLOC type tag by bpf_obj_new. This patch adds support for treating __kptr-tagged pointers to "local kptrs" as having an implicit bpf_obj_drop destructor for referenced kptr acquire / release semantics. Consider the following example: struct node_data { long key; long data; struct bpf_rb_node node; }; struct map_value { struct node_data __kptr *node; }; struct { __uint(type, BPF_MAP_TYPE_ARRAY); __type(key, int); __type(value, struct map_value); __uint(max_entries, 1); } some_nodes SEC(".maps"); If struct node_data had a matching definition in kernel BTF, the verifier would expect a destructor for the type to be registered. Since struct node_data does not match any type in kernel BTF, the verifier knows that there is no kfunc that provides a PTR_TO_BTF_ID to this type, and that such a PTR_TO_BTF_ID can only come from bpf_obj_new. So instead of searching for a registered dtor, a bpf_obj_drop dtor can be assumed. This allows the runtime to properly destruct such kptrs in bpf_obj_free_fields, which enables maps to clean up map_vals w/ such kptrs when going away. Implementation notes: * "kernel_btf" variable is renamed to "kptr_btf" in btf_parse_kptr. Before this patch, the variable would only ever point to vmlinux or module BTFs, but now it can point to some program BTF for local kptr type. It's later used to populate the (btf, btf_id) pair in kptr btf field. * It's necessary to btf_get the program BTF when populating btf_field for local kptr. btf_record_free later does a btf_put. * Behavior for non-local referenced kptrs is not modified, as bpf_find_btf_id helper only searches vmlinux and module BTFs for matching BTF type. If such a type is found, btf_field_kptr's btf will pass btf_is_kernel check, and the associated release function is some one-argument dtor. If btf_is_kernel check fails, associated release function is two-arg bpf_obj_drop_impl. Before this patch only btf_field_kptr's w/ kernel or module BTFs were created. Signed-off-by: Dave Marchevsky Link: https://lore.kernel.org/r/20230310230743.2320707-2-davemarchevsky@fb.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 11 ++++++++++- include/linux/btf.h | 2 -- 2 files changed, 10 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 3a38db315f7f..756b85f0d0d3 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -189,10 +189,19 @@ enum btf_field_type { BPF_RB_NODE | BPF_RB_ROOT, }; +typedef void (*btf_dtor_kfunc_t)(void *); +typedef void (*btf_dtor_obj_drop)(void *, const struct btf_record *); + struct btf_field_kptr { struct btf *btf; struct module *module; - btf_dtor_kfunc_t dtor; + union { + /* dtor used if btf_is_kernel(btf), otherwise the type + * is program-allocated and obj_drop is used + */ + btf_dtor_kfunc_t dtor; + btf_dtor_obj_drop obj_drop; + }; u32 btf_id; }; diff --git a/include/linux/btf.h b/include/linux/btf.h index 1bba0827e8c4..d53b10cc55f2 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -121,8 +121,6 @@ struct btf_struct_metas { struct btf_struct_meta types[]; }; -typedef void (*btf_dtor_kfunc_t)(void *); - extern const struct file_operations btf_fops; void btf_get(struct btf *btf); -- cgit v1.2.3 From 4ad682e04c1694aba95627f60e89f83178c277c2 Mon Sep 17 00:00:00 2001 From: Mehdi Djait Date: Thu, 2 Mar 2023 14:04:35 +0100 Subject: iio: Improve the kernel-doc of iio_trigger_poll Move the kernel-doc of the function to industrialio-trigger.c Add a note on the context where the function is expected to be called. Signed-off-by: Mehdi Djait Reviewed-by: Andy Shevchenko Link: https://lore.kernel.org/r/bd84fc17e9d22eab998bf48720297f9a77689f45.1677761379.git.mehdi.djait.k@gmail.com Signed-off-by: Jonathan Cameron --- include/linux/iio/trigger.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iio/trigger.h b/include/linux/iio/trigger.h index f6360d9a492d..42da55dc3aa7 100644 --- a/include/linux/iio/trigger.h +++ b/include/linux/iio/trigger.h @@ -151,12 +151,6 @@ void iio_trigger_unregister(struct iio_trigger *trig_info); **/ int iio_trigger_set_immutable(struct iio_dev *indio_dev, struct iio_trigger *trig); -/** - * iio_trigger_poll() - called on a trigger occurring - * @trig: trigger which occurred - * - * Typically called in relevant hardware interrupt handler. - **/ void iio_trigger_poll(struct iio_trigger *trig); void iio_trigger_poll_chained(struct iio_trigger *trig); -- cgit v1.2.3 From f700e55ef6ef9ec723164659ed4385900981c872 Mon Sep 17 00:00:00 2001 From: Mehdi Djait Date: Thu, 2 Mar 2023 14:04:36 +0100 Subject: iio: Rename iio_trigger_poll_chained and add kernel-doc Rename the function to iio_trigger_poll_nested. Add kernel-doc with a note on the context where the function is expected to be called. Signed-off-by: Mehdi Djait Link: https://lore.kernel.org/r/841b533cba28ca25a8e87280c44e45979166e8e2.1677761379.git.mehdi.djait.k@gmail.com Signed-off-by: Jonathan Cameron --- include/linux/iio/trigger.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/iio/trigger.h b/include/linux/iio/trigger.h index 42da55dc3aa7..51f52c5c6092 100644 --- a/include/linux/iio/trigger.h +++ b/include/linux/iio/trigger.h @@ -152,7 +152,7 @@ void iio_trigger_unregister(struct iio_trigger *trig_info); int iio_trigger_set_immutable(struct iio_dev *indio_dev, struct iio_trigger *trig); void iio_trigger_poll(struct iio_trigger *trig); -void iio_trigger_poll_chained(struct iio_trigger *trig); +void iio_trigger_poll_nested(struct iio_trigger *trig); irqreturn_t iio_trigger_generic_data_rdy_poll(int irq, void *private); -- cgit v1.2.3 From cf587db2ee0261c74d04f61f39783db88a0b65e4 Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Fri, 10 Mar 2023 16:03:23 -0600 Subject: kernel: Allow a kernel thread's name to be set in copy_process This patch allows kernel users to pass in the thread name so it can be set during creation instead of having to use set_task_comm after the thread is created. Signed-off-by: Mike Christie Acked-by: Michael S. Tsirkin Signed-off-by: Christian Brauner (Microsoft) --- include/linux/sched/task.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h index 357e0068497c..32c9f01af0a6 100644 --- a/include/linux/sched/task.h +++ b/include/linux/sched/task.h @@ -23,6 +23,7 @@ struct kernel_clone_args { int __user *pidfd; int __user *child_tid; int __user *parent_tid; + const char *name; int exit_signal; unsigned long stack; unsigned long stack_size; @@ -91,7 +92,8 @@ extern void exit_itimers(struct task_struct *); extern pid_t kernel_clone(struct kernel_clone_args *kargs); struct task_struct *create_io_thread(int (*fn)(void *), void *arg, int node); struct task_struct *fork_idle(int); -extern pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags); +extern pid_t kernel_thread(int (*fn)(void *), void *arg, const char *name, + unsigned long flags); extern pid_t user_mode_thread(int (*fn)(void *), void *arg, unsigned long flags); extern long kernel_wait4(pid_t, int __user *, int, struct rusage *); int kernel_wait(pid_t pid, int *stat); -- cgit v1.2.3 From c81cc5819faf5dd77124f5086aa654482281ac37 Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Fri, 10 Mar 2023 16:03:25 -0600 Subject: kernel: Make io_thread and kthread bit fields We only set args->io_thread/kthread to 0 or 1 then test if they are set, so make them bit fields. Signed-off-by: Mike Christie Acked-by: Michael S. Tsirkin Signed-off-by: Christian Brauner (Microsoft) --- include/linux/sched/task.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h index 32c9f01af0a6..268c77a42155 100644 --- a/include/linux/sched/task.h +++ b/include/linux/sched/task.h @@ -25,6 +25,8 @@ struct kernel_clone_args { int __user *parent_tid; const char *name; int exit_signal; + u32 kthread:1; + u32 io_thread:1; unsigned long stack; unsigned long stack_size; unsigned long tls; @@ -32,8 +34,6 @@ struct kernel_clone_args { /* Number of elements in *set_tid */ size_t set_tid_size; int cgroup; - int io_thread; - int kthread; int idle; int (*fn)(void *); void *fn_arg; -- cgit v1.2.3 From 54e6842d0775ba76db65cbe21311c3ca466e663d Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Fri, 10 Mar 2023 16:03:26 -0600 Subject: fork/vm: Move common PF_IO_WORKER behavior to new flag This adds a new flag, PF_USER_WORKER, that's used for behavior common to to both PF_IO_WORKER and users like vhost which will use a new helper instead of create_io_thread because they require different behavior for operations like signal handling. The common behavior PF_USER_WORKER covers is the vm reclaim handling. Signed-off-by: Mike Christie Acked-by: Michael S. Tsirkin Signed-off-by: Christian Brauner (Microsoft) --- include/linux/sched.h | 2 +- include/linux/sched/task.h | 1 + 2 files changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 63d242164b1a..e1e605b1255b 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1729,7 +1729,7 @@ extern struct pid *cad_pid; #define PF_MEMALLOC 0x00000800 /* Allocating memory */ #define PF_NPROC_EXCEEDED 0x00001000 /* set_user() noticed that RLIMIT_NPROC was exceeded */ #define PF_USED_MATH 0x00002000 /* If unset the fpu must be initialized before use */ -#define PF__HOLE__00004000 0x00004000 +#define PF_USER_WORKER 0x00004000 /* Kernel thread cloned from userspace thread */ #define PF_NOFREEZE 0x00008000 /* This thread should not be frozen */ #define PF__HOLE__00010000 0x00010000 #define PF_KSWAPD 0x00020000 /* I am kswapd */ diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h index 268c77a42155..2950e83d5382 100644 --- a/include/linux/sched/task.h +++ b/include/linux/sched/task.h @@ -27,6 +27,7 @@ struct kernel_clone_args { int exit_signal; u32 kthread:1; u32 io_thread:1; + u32 user_worker:1; unsigned long stack; unsigned long stack_size; unsigned long tls; -- cgit v1.2.3 From 11f3f500ec8a75c96087f3bed87aa2b1c5de7498 Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Fri, 10 Mar 2023 16:03:27 -0600 Subject: fork: add kernel_clone_args flag to not dup/clone files Each vhost device gets a thread that is used to perform IO and management operations. Instead of a thread that is accessing a device, the thread is part of the device, so when it creates a thread using a helper based on copy_process we can't dup or clone the parent's files/FDS because it would do an extra increment on ourself. Later, when we do: Qemu process exits: do_exit -> exit_files -> put_files_struct -> close_files we would leak the device's resources because of that extra refcount on the fd or file_struct. This patch adds a no_files option so these worker threads can prevent taking an extra refcount on themselves. Signed-off-by: Mike Christie Acked-by: Christian Brauner Acked-by: Michael S. Tsirkin Reviewed-by: Christoph Hellwig Signed-off-by: Christian Brauner (Microsoft) --- include/linux/sched/task.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h index 2950e83d5382..4f816048794f 100644 --- a/include/linux/sched/task.h +++ b/include/linux/sched/task.h @@ -28,6 +28,7 @@ struct kernel_clone_args { u32 kthread:1; u32 io_thread:1; u32 user_worker:1; + u32 no_files:1; unsigned long stack; unsigned long stack_size; unsigned long tls; -- cgit v1.2.3 From 094717586bf71ac20ae3b240d2654d826634b21e Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Fri, 10 Mar 2023 16:03:28 -0600 Subject: fork: Add kernel_clone_args flag to ignore signals Since: commit 10ab825bdef8 ("change kernel threads to ignore signals instead of blocking them") kthreads have been ignoring signals by default, and the vhost layer has never had a need to change that. This patch adds an option flag, USER_WORKER_SIG_IGN, handled in copy_process() after copy_sighand() and copy_signals() so vhost_tasks added in the next patches can continue to ignore singals. Signed-off-by: Christian Brauner Signed-off-by: Mike Christie Acked-by: Michael S. Tsirkin Reviewed-by: Christoph Hellwig Signed-off-by: Christian Brauner (Microsoft) --- include/linux/sched/task.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h index 4f816048794f..00c54bfac0b5 100644 --- a/include/linux/sched/task.h +++ b/include/linux/sched/task.h @@ -29,6 +29,7 @@ struct kernel_clone_args { u32 io_thread:1; u32 user_worker:1; u32 no_files:1; + u32 ignore_signals:1; unsigned long stack; unsigned long stack_size; unsigned long tls; -- cgit v1.2.3 From 89c8e98d8cfb0656dbeb648572df5b13e372247d Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Fri, 10 Mar 2023 16:03:29 -0600 Subject: fork: allow kernel code to call copy_process The next patch adds helpers like create_io_thread, but for use by the vhost layer. There are several functions, so they are in their own file instead of cluttering up fork.c. This patch allows that new file to call copy_process. Signed-off-by: Mike Christie Acked-by: Michael S. Tsirkin Signed-off-by: Christian Brauner (Microsoft) --- include/linux/sched/task.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h index 00c54bfac0b5..537cbf9a2ade 100644 --- a/include/linux/sched/task.h +++ b/include/linux/sched/task.h @@ -93,6 +93,8 @@ extern void exit_files(struct task_struct *); extern void exit_itimers(struct task_struct *); extern pid_t kernel_clone(struct kernel_clone_args *kargs); +struct task_struct *copy_process(struct pid *pid, int trace, int node, + struct kernel_clone_args *args); struct task_struct *create_io_thread(int (*fn)(void *), void *arg, int node); struct task_struct *fork_idle(int); extern pid_t kernel_thread(int (*fn)(void *), void *arg, const char *name, -- cgit v1.2.3 From 2d683175827171c982f91996fdbef4f3fd8b1b01 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 7 Mar 2023 15:31:25 +0100 Subject: mm,jfs: move write_one_page/folio_write_one to jfs The last remaining user of folio_write_one through the write_one_page wrapper is jfs, so move the functionality there and hard code the call to metapage_writepage. Note that the use of the pagecache by the JFS 'metapage' buffer cache is a bit odd, and we could probably do without VM-level dirty tracking at all, but that's a change for another time. Signed-off-by: Christoph Hellwig Acked-by: Dave Kleikamp Signed-off-by: Al Viro --- include/linux/pagemap.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 0acb8e1fb7af..853184a46411 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -1066,12 +1066,6 @@ static inline void folio_cancel_dirty(struct folio *folio) bool folio_clear_dirty_for_io(struct folio *folio); bool clear_page_dirty_for_io(struct page *page); void folio_invalidate(struct folio *folio, size_t offset, size_t length); -int __must_check folio_write_one(struct folio *folio); -static inline int __must_check write_one_page(struct page *page) -{ - return folio_write_one(page_folio(page)); -} - int __set_page_dirty_nobuffers(struct page *page); bool noop_dirty_folio(struct address_space *mapping, struct folio *folio); -- cgit v1.2.3 From ce48f955860db841eeb4bcf9bb973ea3ef177b3a Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Thu, 2 Mar 2023 18:12:06 +0200 Subject: =?UTF-8?q?i3c:=20Correct=20reference=20to=20the=20I=C2=B2C=20devi?= =?UTF-8?q?ce=20data=20type?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit I²C peripheral devices that are connected to the controller are represented in the Linux kernel as objects of the struct i2c_client. Fix this in the header file. Signed-off-by: Andy Shevchenko Link: https://lore.kernel.org/r/20230302161206.38106-1-andriy.shevchenko@linux.intel.com Signed-off-by: Alexandre Belloni --- include/linux/i3c/master.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/i3c/master.h b/include/linux/i3c/master.h index 604a126b78c8..a12cda9dc715 100644 --- a/include/linux/i3c/master.h +++ b/include/linux/i3c/master.h @@ -22,9 +22,10 @@ #define I3C_BROADCAST_ADDR 0x7e #define I3C_MAX_ADDR GENMASK(6, 0) +struct i2c_client; + struct i3c_master_controller; struct i3c_bus; -struct i2c_device; struct i3c_device; /** -- cgit v1.2.3 From e9d198f2be851f8c977b9ac47748edc4f9d0f26e Mon Sep 17 00:00:00 2001 From: Thorsten Scherer Date: Sun, 12 Mar 2023 13:23:15 +0100 Subject: slab: Adjust comment after refactoring of gfp.h Reflect the change from the commit below. Fixes: cb5a065b4ea9 ("headers/deps: mm: Split out of ") Signed-off-by: Thorsten Scherer Acked-by: Hyeonggon Yoo <42.hyeyoo@gmail.com> Signed-off-by: Vlastimil Babka --- include/linux/slab.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/slab.h b/include/linux/slab.h index 45af70315a94..87d687c43d8c 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -526,7 +526,7 @@ void *kmalloc_large_node(size_t size, gfp_t flags, int node) __assume_page_align * to be at least to the size. * * The @flags argument may be one of the GFP flags defined at - * include/linux/gfp.h and described at + * include/linux/gfp_types.h and described at * :ref:`Documentation/core-api/mm-api.rst ` * * The recommended usage of the @flags is described at -- cgit v1.2.3 From cc4b15670340315fb0b25d886c06bffb5f128f02 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Mon, 13 Mar 2023 11:58:35 +0100 Subject: spi: Constify spi_get_ctldata()'s spi parameter The "spi" parameter of spi_get_ctldata() can be const. Signed-off-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/8960e07adaad8d92d2c3aa045af9ee3c5d2130a8.1678704562.git.geert+renesas@glider.be Signed-off-by: Mark Brown --- include/linux/spi/spi.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index bdb35a91b4bf..6097d2f51266 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -244,7 +244,7 @@ static inline void spi_dev_put(struct spi_device *spi) } /* ctldata is for the bus_controller driver's runtime state */ -static inline void *spi_get_ctldata(struct spi_device *spi) +static inline void *spi_get_ctldata(const struct spi_device *spi) { return spi->controller_state; } -- cgit v1.2.3 From 38dca04d659a422d842f7edcecd32253c7a6fb5e Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Mon, 13 Mar 2023 11:58:36 +0100 Subject: spi: Constify spi_get_drvdata()'s spi parameter The "spi" parameter of spi_get_drvdata() can be const. dev_get_drvdata() has been taking a const pointer since commit 7d1d8999b4bec0ba ("i2c: Constify i2c_get_clientdata's parameter"). Signed-off-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/0f1700ade27a8f3935d04480ff7bef8a887331eb.1678704562.git.geert+renesas@glider.be Signed-off-by: Mark Brown --- include/linux/spi/spi.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 6097d2f51266..e09a61dd3459 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -261,7 +261,7 @@ static inline void spi_set_drvdata(struct spi_device *spi, void *data) dev_set_drvdata(&spi->dev, data); } -static inline void *spi_get_drvdata(struct spi_device *spi) +static inline void *spi_get_drvdata(const struct spi_device *spi) { return dev_get_drvdata(&spi->dev); } -- cgit v1.2.3 From d2f19eec510424caa55ea949f016ddabe2d8173a Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Mon, 13 Mar 2023 11:58:37 +0100 Subject: spi: Constify spi parameters of chip select APIs The "spi" parameters of spi_get_chipselect() and spi_get_csgpiod() can be const. Fixes: 303feb3cc06ac066 ("spi: Add APIs in spi core to set/get spi->chip_select and spi->cs_gpiod") Signed-off-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/b112de79e7a1e9095a3b6ff22b639f39e39d7748.1678704562.git.geert+renesas@glider.be Signed-off-by: Mark Brown --- include/linux/spi/spi.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index e09a61dd3459..74bff5a2f53d 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -266,7 +266,7 @@ static inline void *spi_get_drvdata(const struct spi_device *spi) return dev_get_drvdata(&spi->dev); } -static inline u8 spi_get_chipselect(struct spi_device *spi, u8 idx) +static inline u8 spi_get_chipselect(const struct spi_device *spi, u8 idx) { return spi->chip_select; } @@ -276,7 +276,7 @@ static inline void spi_set_chipselect(struct spi_device *spi, u8 idx, u8 chipsel spi->chip_select = chipselect; } -static inline struct gpio_desc *spi_get_csgpiod(struct spi_device *spi, u8 idx) +static inline struct gpio_desc *spi_get_csgpiod(const struct spi_device *spi, u8 idx) { return spi->cs_gpiod; } -- cgit v1.2.3 From 22df776a9a866713d9decfb92b633bcfdb571954 Mon Sep 17 00:00:00 2001 From: David Vernet Date: Wed, 15 Feb 2023 17:30:33 -0600 Subject: tasks: Extract rcu_users out of union In commit 3fbd7ee285b2b ("tasks: Add a count of task RCU users"), a count on the number of RCU users was added to struct task_struct. This was done so as to enable the removal of task_rcu_dereference(), and allow tasks to be protected by RCU even after exiting and being removed from the runqueue. In this commit, the 'refcount_t rcu_users' field that keeps track of this refcount was put into a union co-located with 'struct rcu_head rcu', so as to avoid taking up any extra space in task_struct. This was possible to do safely, because the field was only ever decremented by a static set of specific callers, and then never incremented again. While this restriction of there only being a small, static set of users of this field has worked fine, it prevents us from leveraging the field to use RCU to protect tasks in other contexts. During tracing, for example, it would be useful to be able to collect some tasks that performed a certain operation, put them in a map, and then periodically summarize who they are, which cgroup they're in, how much CPU time they've utilized, etc. While this can currently be done with 'usage', it becomes tricky when a task is already in a map, or if a reference should only be taken if a task is valid and will not soon be reaped. Ideally, we could do something like pass a reference to a map value, and then try to acquire a reference to the task in an RCU read region by using refcount_inc_not_zero(). Similarly, in sched_ext, schedulers are using integer pids to remember tasks, and then looking them up with find_task_by_pid_ns(). This is slow, error prone, and adds complexity. It would be more convenient and performant if BPF schedulers could instead store tasks directly in maps, and then leverage RCU to ensure they can be safely accessed with low overhead. Finally, overloading fields like this is error prone. Someone that wants to use 'rcu_users' could easily overlook the fact that once the rcu callback is scheduled, the refcount will go back to being nonzero, thus precluding the use of refcount_inc_not_zero(). Furthermore, as described below, it's possible to extract the fields of the union without changing the size of task_struct. There are several possible ways to enable this: 1. The lightest touch approach is likely the one proposed in this patch, which is to simply extract 'rcu_users' and 'rcu' from the union, so that scheduling the 'rcu' callback doesn't overwrite the 'rcu_users' refcount. If we have a trusted task pointer, this would allow us to use refcnt_inc_not_zero() inside of an RCU region to determine if we can safely acquire a reference to the task and store it in a map. As mentioned below, this can be done without changing the size of task_struct, by moving the location of the union to another location that has padding gaps we can fill in. 2. Removing 'refcount_t rcu_users', and instead having the entire task be freed in an rcu callback. This is likely the most sound overall design, though it changes the behavioral semantics exposed to callers, who currently expect that a task that's successfully looked up in e.g. the pid_list with find_task_by_pid_ns(), can always have a 'usage' reference acquired on them, as it's guaranteed to be > 0 until after the next gp. In order for this approach to work, we'd have to audit all callers. This approach also slightly changes behavior observed by user space by not invoking trace_sched_process_free() until the whole task_struct is actually being freed, rather than just after it's exited. It also may change timings, as memory will be freed in an RCU callback rather than immediately when the final 'usage' refcount drops to 0. This also is arguably a benefit, as it provides more predictable performance to callers who are refcounting tasks. 3. There may be other solutions as well that don't require changing the layout of task_struct. For example, we could possibly do something complex from the BPF side, such as listen for task exit and remove a task from a map when the task is exiting. This would likely require significant custom handling for task_struct in the verifier, so a more generalizable solution is likely warranted. As mentioned above, this patch proposes the lightest-touch approach which allows callers elsewhere in the kernel to use 'rcu_users' to ensure the lifetime of a task, by extracting 'rcu_users' and 'rcu' from the union. There is no size change in task_struct with this patch. Cc: Linus Torvalds Cc: Eric W. Biederman Cc: Peter Zijlstra Cc: Ingo Molnar Signed-off-by: David Vernet Acked-by: Oleg Nesterov Link: https://lore.kernel.org/r/20230215233033.889644-1-void@manifault.com Signed-off-by: Alexei Starovoitov --- include/linux/sched.h | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 63d242164b1a..b11b4517760f 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1318,11 +1318,6 @@ struct task_struct { struct tlbflush_unmap_batch tlb_ubc; - union { - refcount_t rcu_users; - struct rcu_head rcu; - }; - /* Cache last used pipe for splice(): */ struct pipe_inode_info *splice_pipe; @@ -1459,6 +1454,8 @@ struct task_struct { unsigned long saved_state_change; # endif #endif + struct rcu_head rcu; + refcount_t rcu_users; int pagefault_disabled; #ifdef CONFIG_MMU struct task_struct *oom_reaper_list; -- cgit v1.2.3 From 9e36a204bd43553a9cd4bd574612cd9a5df791ea Mon Sep 17 00:00:00 2001 From: Dave Marchevsky Date: Mon, 13 Mar 2023 14:46:41 -0700 Subject: bpf: Disable migration when freeing stashed local kptr using obj drop When a local kptr is stashed in a map and freed when the map goes away, currently an error like the below appears: [ 39.195695] BUG: using smp_processor_id() in preemptible [00000000] code: kworker/u32:15/2875 [ 39.196549] caller is bpf_mem_free+0x56/0xc0 [ 39.196958] CPU: 15 PID: 2875 Comm: kworker/u32:15 Tainted: G O 6.2.0-13016-g22df776a9a86 #4477 [ 39.197897] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.12.0-59-gc9ba5276e321-prebuilt.qemu.org 04/01/2014 [ 39.198949] Workqueue: events_unbound bpf_map_free_deferred [ 39.199470] Call Trace: [ 39.199703] [ 39.199911] dump_stack_lvl+0x60/0x70 [ 39.200267] check_preemption_disabled+0xbf/0xe0 [ 39.200704] bpf_mem_free+0x56/0xc0 [ 39.201032] ? bpf_obj_new_impl+0xa0/0xa0 [ 39.201430] bpf_obj_free_fields+0x1cd/0x200 [ 39.201838] array_map_free+0xad/0x220 [ 39.202193] ? finish_task_switch+0xe5/0x3c0 [ 39.202614] bpf_map_free_deferred+0xea/0x210 [ 39.203006] ? lockdep_hardirqs_on_prepare+0xe/0x220 [ 39.203460] process_one_work+0x64f/0xbe0 [ 39.203822] ? pwq_dec_nr_in_flight+0x110/0x110 [ 39.204264] ? do_raw_spin_lock+0x107/0x1c0 [ 39.204662] ? lockdep_hardirqs_on_prepare+0xe/0x220 [ 39.205107] worker_thread+0x74/0x7a0 [ 39.205451] ? process_one_work+0xbe0/0xbe0 [ 39.205818] kthread+0x171/0x1a0 [ 39.206111] ? kthread_complete_and_exit+0x20/0x20 [ 39.206552] ret_from_fork+0x1f/0x30 [ 39.206886] This happens because the call to __bpf_obj_drop_impl I added in the patch adding support for stashing local kptrs doesn't disable migration. Prior to that patch, __bpf_obj_drop_impl logic only ran when called by a BPF progarm, whereas now it can be called from map free path, so it's necessary to explicitly disable migration. Also, refactor a bit to just call __bpf_obj_drop_impl directly instead of bothering w/ dtor union and setting pointer-to-obj_drop. Fixes: c8e187540914 ("bpf: Support __kptr to local kptrs") Reported-by: Alexei Starovoitov Signed-off-by: Dave Marchevsky Link: https://lore.kernel.org/r/20230313214641.3731908-1-davemarchevsky@fb.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 12 ++++-------- 1 file changed, 4 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 756b85f0d0d3..71cc92a4ba48 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -190,18 +190,14 @@ enum btf_field_type { }; typedef void (*btf_dtor_kfunc_t)(void *); -typedef void (*btf_dtor_obj_drop)(void *, const struct btf_record *); struct btf_field_kptr { struct btf *btf; struct module *module; - union { - /* dtor used if btf_is_kernel(btf), otherwise the type - * is program-allocated and obj_drop is used - */ - btf_dtor_kfunc_t dtor; - btf_dtor_obj_drop obj_drop; - }; + /* dtor used if btf_is_kernel(btf), otherwise the type is + * program-allocated, dtor is NULL, and __bpf_obj_drop_impl is used + */ + btf_dtor_kfunc_t dtor; u32 btf_id; }; -- cgit v1.2.3 From fe8aa1ba078366ba23fc676efab57183b12a3a81 Mon Sep 17 00:00:00 2001 From: Visweswara Tanuku Date: Tue, 14 Feb 2023 21:05:28 -0800 Subject: soc: qcom: geni-se: Update Tx and Rx fifo depth based on QUP HW version From QUP HW Version 3.10 and above the Tx and Rx fifo depth bits are increased to 23:16 bits from 21:16 bits in SE_HW_PARAM registers accomodating 256bytes of fifo depth. Updated geni_se_get_tx_fifo_depth and geni_se_get_rx_fifo_depth to retrieve right fifo depth based on QUP HW version. Signed-off-by: Visweswara Tanuku Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20230215050528.9507-1-quic_vtanuku@quicinc.com --- include/linux/soc/qcom/geni-se.h | 42 ++++++++++++++++++++++++++++++++++------ 1 file changed, 36 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/soc/qcom/geni-se.h b/include/linux/soc/qcom/geni-se.h index 400213daa461..c55a0bc8cb0e 100644 --- a/include/linux/soc/qcom/geni-se.h +++ b/include/linux/soc/qcom/geni-se.h @@ -245,12 +245,22 @@ struct geni_se { /* SE_HW_PARAM_0 fields */ #define TX_FIFO_WIDTH_MSK GENMASK(29, 24) #define TX_FIFO_WIDTH_SHFT 24 +/* + * For QUP HW Version >= 3.10 Tx fifo depth support is increased + * to 256bytes and corresponding bits are 16 to 23 + */ +#define TX_FIFO_DEPTH_MSK_256_BYTES GENMASK(23, 16) #define TX_FIFO_DEPTH_MSK GENMASK(21, 16) #define TX_FIFO_DEPTH_SHFT 16 /* SE_HW_PARAM_1 fields */ #define RX_FIFO_WIDTH_MSK GENMASK(29, 24) #define RX_FIFO_WIDTH_SHFT 24 +/* + * For QUP HW Version >= 3.10 Rx fifo depth support is increased + * to 256bytes and corresponding bits are 16 to 23 + */ +#define RX_FIFO_DEPTH_MSK_256_BYTES GENMASK(23, 16) #define RX_FIFO_DEPTH_MSK GENMASK(21, 16) #define RX_FIFO_DEPTH_SHFT 16 @@ -391,7 +401,8 @@ static inline void geni_se_abort_s_cmd(struct geni_se *se) /** * geni_se_get_tx_fifo_depth() - Get the TX fifo depth of the serial engine - * @se: Pointer to the concerned serial engine. + * based on QUP HW version + * @se: Pointer to the concerned serial engine. * * This function is used to get the depth i.e. number of elements in the * TX fifo of the serial engine. @@ -400,11 +411,20 @@ static inline void geni_se_abort_s_cmd(struct geni_se *se) */ static inline u32 geni_se_get_tx_fifo_depth(struct geni_se *se) { - u32 val; + u32 val, hw_version, hw_major, hw_minor, tx_fifo_depth_mask; + + hw_version = geni_se_get_qup_hw_version(se); + hw_major = GENI_SE_VERSION_MAJOR(hw_version); + hw_minor = GENI_SE_VERSION_MINOR(hw_version); + + if ((hw_major == 3 && hw_minor >= 10) || hw_major > 3) + tx_fifo_depth_mask = TX_FIFO_DEPTH_MSK_256_BYTES; + else + tx_fifo_depth_mask = TX_FIFO_DEPTH_MSK; val = readl_relaxed(se->base + SE_HW_PARAM_0); - return (val & TX_FIFO_DEPTH_MSK) >> TX_FIFO_DEPTH_SHFT; + return (val & tx_fifo_depth_mask) >> TX_FIFO_DEPTH_SHFT; } /** @@ -427,7 +447,8 @@ static inline u32 geni_se_get_tx_fifo_width(struct geni_se *se) /** * geni_se_get_rx_fifo_depth() - Get the RX fifo depth of the serial engine - * @se: Pointer to the concerned serial engine. + * based on QUP HW version + * @se: Pointer to the concerned serial engine. * * This function is used to get the depth i.e. number of elements in the * RX fifo of the serial engine. @@ -436,11 +457,20 @@ static inline u32 geni_se_get_tx_fifo_width(struct geni_se *se) */ static inline u32 geni_se_get_rx_fifo_depth(struct geni_se *se) { - u32 val; + u32 val, hw_version, hw_major, hw_minor, rx_fifo_depth_mask; + + hw_version = geni_se_get_qup_hw_version(se); + hw_major = GENI_SE_VERSION_MAJOR(hw_version); + hw_minor = GENI_SE_VERSION_MINOR(hw_version); + + if ((hw_major == 3 && hw_minor >= 10) || hw_major > 3) + rx_fifo_depth_mask = RX_FIFO_DEPTH_MSK_256_BYTES; + else + rx_fifo_depth_mask = RX_FIFO_DEPTH_MSK; val = readl_relaxed(se->base + SE_HW_PARAM_1); - return (val & RX_FIFO_DEPTH_MSK) >> RX_FIFO_DEPTH_SHFT; + return (val & rx_fifo_depth_mask) >> RX_FIFO_DEPTH_SHFT; } void geni_se_init(struct geni_se *se, u32 rx_wm, u32 rx_rfr); -- cgit v1.2.3 From 0df4adf8682a017e43579ac8c9ec1a31c538e940 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Thu, 16 Feb 2023 18:35:11 +0800 Subject: crypto: aead - Count error stats differently Move all stat code specific to aead into the aead code. While we're at it, change the stats so that bytes and counts are always incremented even in case of error. This allows the reference counting to be removed as we can now increment the counters prior to the operation. After the operation we simply increase the error count if necessary. This is safe as errors can only occur synchronously (or rather, the existing code already ignored asynchronous errors which are only visible to the callback function). Signed-off-by: Herbert Xu --- include/linux/crypto.h | 24 ------------------------ 1 file changed, 24 deletions(-) (limited to 'include/linux') diff --git a/include/linux/crypto.h b/include/linux/crypto.h index bb1d9b0e1647..9eb6fc8ab69c 100644 --- a/include/linux/crypto.h +++ b/include/linux/crypto.h @@ -276,22 +276,6 @@ struct compress_alg { }; #ifdef CONFIG_CRYPTO_STATS -/* - * struct crypto_istat_aead - statistics for AEAD algorithm - * @encrypt_cnt: number of encrypt requests - * @encrypt_tlen: total data size handled by encrypt requests - * @decrypt_cnt: number of decrypt requests - * @decrypt_tlen: total data size handled by decrypt requests - * @err_cnt: number of error for AEAD requests - */ -struct crypto_istat_aead { - atomic64_t encrypt_cnt; - atomic64_t encrypt_tlen; - atomic64_t decrypt_cnt; - atomic64_t decrypt_tlen; - atomic64_t err_cnt; -}; - /* * struct crypto_istat_akcipher - statistics for akcipher algorithm * @encrypt_cnt: number of encrypt requests @@ -463,7 +447,6 @@ struct crypto_istat_rng { * @cra_destroy: internally used * * @stats: union of all possible crypto_istat_xxx structures - * @stats.aead: statistics for AEAD algorithm * @stats.akcipher: statistics for akcipher algorithm * @stats.cipher: statistics for cipher algorithm * @stats.compress: statistics for compress algorithm @@ -505,7 +488,6 @@ struct crypto_alg { #ifdef CONFIG_CRYPTO_STATS union { - struct crypto_istat_aead aead; struct crypto_istat_akcipher akcipher; struct crypto_istat_cipher cipher; struct crypto_istat_compress compress; @@ -520,8 +502,6 @@ struct crypto_alg { #ifdef CONFIG_CRYPTO_STATS void crypto_stats_init(struct crypto_alg *alg); void crypto_stats_get(struct crypto_alg *alg); -void crypto_stats_aead_encrypt(unsigned int cryptlen, struct crypto_alg *alg, int ret); -void crypto_stats_aead_decrypt(unsigned int cryptlen, struct crypto_alg *alg, int ret); void crypto_stats_ahash_update(unsigned int nbytes, int ret, struct crypto_alg *alg); void crypto_stats_ahash_final(unsigned int nbytes, int ret, struct crypto_alg *alg); void crypto_stats_akcipher_encrypt(unsigned int src_len, int ret, struct crypto_alg *alg); @@ -542,10 +522,6 @@ static inline void crypto_stats_init(struct crypto_alg *alg) {} static inline void crypto_stats_get(struct crypto_alg *alg) {} -static inline void crypto_stats_aead_encrypt(unsigned int cryptlen, struct crypto_alg *alg, int ret) -{} -static inline void crypto_stats_aead_decrypt(unsigned int cryptlen, struct crypto_alg *alg, int ret) -{} static inline void crypto_stats_ahash_update(unsigned int nbytes, int ret, struct crypto_alg *alg) {} static inline void crypto_stats_ahash_final(unsigned int nbytes, int ret, struct crypto_alg *alg) -- cgit v1.2.3 From 035d78a11c56828bb4923fa87eeb9ed2546d52bd Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Thu, 16 Feb 2023 18:35:13 +0800 Subject: crypto: akcipher - Count error stats differently Move all stat code specific to akcipher into the akcipher code. While we're at it, change the stats so that bytes and counts are always incremented even in case of error. This allows the reference counting to be removed as we can now increment the counters prior to the operation. After the operation we simply increase the error count if necessary. This is safe as errors can only occur synchronously (or rather, the existing code already ignored asynchronous errors which are only visible to the callback function). Signed-off-by: Herbert Xu --- include/linux/crypto.h | 34 ---------------------------------- 1 file changed, 34 deletions(-) (limited to 'include/linux') diff --git a/include/linux/crypto.h b/include/linux/crypto.h index 9eb6fc8ab69c..778cc05f76a8 100644 --- a/include/linux/crypto.h +++ b/include/linux/crypto.h @@ -276,26 +276,6 @@ struct compress_alg { }; #ifdef CONFIG_CRYPTO_STATS -/* - * struct crypto_istat_akcipher - statistics for akcipher algorithm - * @encrypt_cnt: number of encrypt requests - * @encrypt_tlen: total data size handled by encrypt requests - * @decrypt_cnt: number of decrypt requests - * @decrypt_tlen: total data size handled by decrypt requests - * @verify_cnt: number of verify operation - * @sign_cnt: number of sign requests - * @err_cnt: number of error for akcipher requests - */ -struct crypto_istat_akcipher { - atomic64_t encrypt_cnt; - atomic64_t encrypt_tlen; - atomic64_t decrypt_cnt; - atomic64_t decrypt_tlen; - atomic64_t verify_cnt; - atomic64_t sign_cnt; - atomic64_t err_cnt; -}; - /* * struct crypto_istat_cipher - statistics for cipher algorithm * @encrypt_cnt: number of encrypt requests @@ -447,7 +427,6 @@ struct crypto_istat_rng { * @cra_destroy: internally used * * @stats: union of all possible crypto_istat_xxx structures - * @stats.akcipher: statistics for akcipher algorithm * @stats.cipher: statistics for cipher algorithm * @stats.compress: statistics for compress algorithm * @stats.hash: statistics for hash algorithm @@ -488,7 +467,6 @@ struct crypto_alg { #ifdef CONFIG_CRYPTO_STATS union { - struct crypto_istat_akcipher akcipher; struct crypto_istat_cipher cipher; struct crypto_istat_compress compress; struct crypto_istat_hash hash; @@ -504,10 +482,6 @@ void crypto_stats_init(struct crypto_alg *alg); void crypto_stats_get(struct crypto_alg *alg); void crypto_stats_ahash_update(unsigned int nbytes, int ret, struct crypto_alg *alg); void crypto_stats_ahash_final(unsigned int nbytes, int ret, struct crypto_alg *alg); -void crypto_stats_akcipher_encrypt(unsigned int src_len, int ret, struct crypto_alg *alg); -void crypto_stats_akcipher_decrypt(unsigned int src_len, int ret, struct crypto_alg *alg); -void crypto_stats_akcipher_sign(int ret, struct crypto_alg *alg); -void crypto_stats_akcipher_verify(int ret, struct crypto_alg *alg); void crypto_stats_compress(unsigned int slen, int ret, struct crypto_alg *alg); void crypto_stats_decompress(unsigned int slen, int ret, struct crypto_alg *alg); void crypto_stats_kpp_set_secret(struct crypto_alg *alg, int ret); @@ -526,14 +500,6 @@ static inline void crypto_stats_ahash_update(unsigned int nbytes, int ret, struc {} static inline void crypto_stats_ahash_final(unsigned int nbytes, int ret, struct crypto_alg *alg) {} -static inline void crypto_stats_akcipher_encrypt(unsigned int src_len, int ret, struct crypto_alg *alg) -{} -static inline void crypto_stats_akcipher_decrypt(unsigned int src_len, int ret, struct crypto_alg *alg) -{} -static inline void crypto_stats_akcipher_sign(int ret, struct crypto_alg *alg) -{} -static inline void crypto_stats_akcipher_verify(int ret, struct crypto_alg *alg) -{} static inline void crypto_stats_compress(unsigned int slen, int ret, struct crypto_alg *alg) {} static inline void crypto_stats_decompress(unsigned int slen, int ret, struct crypto_alg *alg) -- cgit v1.2.3 From 42808e5dc602c12ef3eb42cf96cb416b55205fa4 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Thu, 16 Feb 2023 18:35:15 +0800 Subject: crypto: hash - Count error stats differently Move all stat code specific to hash into the hash code. While we're at it, change the stats so that bytes and counts are always incremented even in case of error. This allows the reference counting to be removed as we can now increment the counters prior to the operation. After the operation we simply increase the error count if necessary. This is safe as errors can only occur synchronously (or rather, the existing code already ignored asynchronous errors which are only visible to the callback function). Signed-off-by: Herbert Xu --- include/linux/crypto.h | 20 -------------------- 1 file changed, 20 deletions(-) (limited to 'include/linux') diff --git a/include/linux/crypto.h b/include/linux/crypto.h index 778cc05f76a8..caf759e4201c 100644 --- a/include/linux/crypto.h +++ b/include/linux/crypto.h @@ -308,18 +308,6 @@ struct crypto_istat_compress { atomic64_t err_cnt; }; -/* - * struct crypto_istat_hash - statistics for has algorithm - * @hash_cnt: number of hash requests - * @hash_tlen: total data size hashed - * @err_cnt: number of error for hash requests - */ -struct crypto_istat_hash { - atomic64_t hash_cnt; - atomic64_t hash_tlen; - atomic64_t err_cnt; -}; - /* * struct crypto_istat_kpp - statistics for KPP algorithm * @setsecret_cnt: number of setsecrey operation @@ -429,7 +417,6 @@ struct crypto_istat_rng { * @stats: union of all possible crypto_istat_xxx structures * @stats.cipher: statistics for cipher algorithm * @stats.compress: statistics for compress algorithm - * @stats.hash: statistics for hash algorithm * @stats.rng: statistics for rng algorithm * @stats.kpp: statistics for KPP algorithm * @@ -469,7 +456,6 @@ struct crypto_alg { union { struct crypto_istat_cipher cipher; struct crypto_istat_compress compress; - struct crypto_istat_hash hash; struct crypto_istat_rng rng; struct crypto_istat_kpp kpp; } stats; @@ -480,8 +466,6 @@ struct crypto_alg { #ifdef CONFIG_CRYPTO_STATS void crypto_stats_init(struct crypto_alg *alg); void crypto_stats_get(struct crypto_alg *alg); -void crypto_stats_ahash_update(unsigned int nbytes, int ret, struct crypto_alg *alg); -void crypto_stats_ahash_final(unsigned int nbytes, int ret, struct crypto_alg *alg); void crypto_stats_compress(unsigned int slen, int ret, struct crypto_alg *alg); void crypto_stats_decompress(unsigned int slen, int ret, struct crypto_alg *alg); void crypto_stats_kpp_set_secret(struct crypto_alg *alg, int ret); @@ -496,10 +480,6 @@ static inline void crypto_stats_init(struct crypto_alg *alg) {} static inline void crypto_stats_get(struct crypto_alg *alg) {} -static inline void crypto_stats_ahash_update(unsigned int nbytes, int ret, struct crypto_alg *alg) -{} -static inline void crypto_stats_ahash_final(unsigned int nbytes, int ret, struct crypto_alg *alg) -{} static inline void crypto_stats_compress(unsigned int slen, int ret, struct crypto_alg *alg) {} static inline void crypto_stats_decompress(unsigned int slen, int ret, struct crypto_alg *alg) -- cgit v1.2.3 From 0a742389bcc00053d63b5271fefb00d3a338d512 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Thu, 16 Feb 2023 18:35:17 +0800 Subject: crypto: acomp - Count error stats differently Move all stat code specific to acomp into the acomp code. While we're at it, change the stats so that bytes and counts are always incremented even in case of error. This allows the reference counting to be removed as we can now increment the counters prior to the operation. After the operation we simply increase the error count if necessary. This is safe as errors can only occur synchronously (or rather, the existing code already ignored asynchronous errors which are only visible to the callback function). Signed-off-by: Herbert Xu --- include/linux/crypto.h | 24 ------------------------ 1 file changed, 24 deletions(-) (limited to 'include/linux') diff --git a/include/linux/crypto.h b/include/linux/crypto.h index caf759e4201c..42bc55b642a0 100644 --- a/include/linux/crypto.h +++ b/include/linux/crypto.h @@ -292,22 +292,6 @@ struct crypto_istat_cipher { atomic64_t err_cnt; }; -/* - * struct crypto_istat_compress - statistics for compress algorithm - * @compress_cnt: number of compress requests - * @compress_tlen: total data size handled by compress requests - * @decompress_cnt: number of decompress requests - * @decompress_tlen: total data size handled by decompress requests - * @err_cnt: number of error for compress requests - */ -struct crypto_istat_compress { - atomic64_t compress_cnt; - atomic64_t compress_tlen; - atomic64_t decompress_cnt; - atomic64_t decompress_tlen; - atomic64_t err_cnt; -}; - /* * struct crypto_istat_kpp - statistics for KPP algorithm * @setsecret_cnt: number of setsecrey operation @@ -416,7 +400,6 @@ struct crypto_istat_rng { * * @stats: union of all possible crypto_istat_xxx structures * @stats.cipher: statistics for cipher algorithm - * @stats.compress: statistics for compress algorithm * @stats.rng: statistics for rng algorithm * @stats.kpp: statistics for KPP algorithm * @@ -455,7 +438,6 @@ struct crypto_alg { #ifdef CONFIG_CRYPTO_STATS union { struct crypto_istat_cipher cipher; - struct crypto_istat_compress compress; struct crypto_istat_rng rng; struct crypto_istat_kpp kpp; } stats; @@ -466,8 +448,6 @@ struct crypto_alg { #ifdef CONFIG_CRYPTO_STATS void crypto_stats_init(struct crypto_alg *alg); void crypto_stats_get(struct crypto_alg *alg); -void crypto_stats_compress(unsigned int slen, int ret, struct crypto_alg *alg); -void crypto_stats_decompress(unsigned int slen, int ret, struct crypto_alg *alg); void crypto_stats_kpp_set_secret(struct crypto_alg *alg, int ret); void crypto_stats_kpp_generate_public_key(struct crypto_alg *alg, int ret); void crypto_stats_kpp_compute_shared_secret(struct crypto_alg *alg, int ret); @@ -480,10 +460,6 @@ static inline void crypto_stats_init(struct crypto_alg *alg) {} static inline void crypto_stats_get(struct crypto_alg *alg) {} -static inline void crypto_stats_compress(unsigned int slen, int ret, struct crypto_alg *alg) -{} -static inline void crypto_stats_decompress(unsigned int slen, int ret, struct crypto_alg *alg) -{} static inline void crypto_stats_kpp_set_secret(struct crypto_alg *alg, int ret) {} static inline void crypto_stats_kpp_generate_public_key(struct crypto_alg *alg, int ret) -- cgit v1.2.3 From e2950bf166ef71ed5588437b7ee94f65ceaa6cd0 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Thu, 16 Feb 2023 18:35:19 +0800 Subject: crypto: kpp - Count error stats differently Move all stat code specific to kpp into the kpp code. While we're at it, change the stats so that bytes and counts are always incremented even in case of error. This allows the reference counting to be removed as we can now increment the counters prior to the operation. After the operation we simply increase the error count if necessary. This is safe as errors can only occur synchronously (or rather, the existing code already ignored asynchronous errors which are only visible to the callback function). Signed-off-by: Herbert Xu --- include/linux/crypto.h | 25 ------------------------- 1 file changed, 25 deletions(-) (limited to 'include/linux') diff --git a/include/linux/crypto.h b/include/linux/crypto.h index 42bc55b642a0..c66f7dc21cbb 100644 --- a/include/linux/crypto.h +++ b/include/linux/crypto.h @@ -292,20 +292,6 @@ struct crypto_istat_cipher { atomic64_t err_cnt; }; -/* - * struct crypto_istat_kpp - statistics for KPP algorithm - * @setsecret_cnt: number of setsecrey operation - * @generate_public_key_cnt: number of generate_public_key operation - * @compute_shared_secret_cnt: number of compute_shared_secret operation - * @err_cnt: number of error for KPP requests - */ -struct crypto_istat_kpp { - atomic64_t setsecret_cnt; - atomic64_t generate_public_key_cnt; - atomic64_t compute_shared_secret_cnt; - atomic64_t err_cnt; -}; - /* * struct crypto_istat_rng: statistics for RNG algorithm * @generate_cnt: number of RNG generate requests @@ -401,7 +387,6 @@ struct crypto_istat_rng { * @stats: union of all possible crypto_istat_xxx structures * @stats.cipher: statistics for cipher algorithm * @stats.rng: statistics for rng algorithm - * @stats.kpp: statistics for KPP algorithm * * The struct crypto_alg describes a generic Crypto API algorithm and is common * for all of the transformations. Any variable not documented here shall not @@ -439,7 +424,6 @@ struct crypto_alg { union { struct crypto_istat_cipher cipher; struct crypto_istat_rng rng; - struct crypto_istat_kpp kpp; } stats; #endif /* CONFIG_CRYPTO_STATS */ @@ -448,9 +432,6 @@ struct crypto_alg { #ifdef CONFIG_CRYPTO_STATS void crypto_stats_init(struct crypto_alg *alg); void crypto_stats_get(struct crypto_alg *alg); -void crypto_stats_kpp_set_secret(struct crypto_alg *alg, int ret); -void crypto_stats_kpp_generate_public_key(struct crypto_alg *alg, int ret); -void crypto_stats_kpp_compute_shared_secret(struct crypto_alg *alg, int ret); void crypto_stats_rng_seed(struct crypto_alg *alg, int ret); void crypto_stats_rng_generate(struct crypto_alg *alg, unsigned int dlen, int ret); void crypto_stats_skcipher_encrypt(unsigned int cryptlen, int ret, struct crypto_alg *alg); @@ -460,12 +441,6 @@ static inline void crypto_stats_init(struct crypto_alg *alg) {} static inline void crypto_stats_get(struct crypto_alg *alg) {} -static inline void crypto_stats_kpp_set_secret(struct crypto_alg *alg, int ret) -{} -static inline void crypto_stats_kpp_generate_public_key(struct crypto_alg *alg, int ret) -{} -static inline void crypto_stats_kpp_compute_shared_secret(struct crypto_alg *alg, int ret) -{} static inline void crypto_stats_rng_seed(struct crypto_alg *alg, int ret) {} static inline void crypto_stats_rng_generate(struct crypto_alg *alg, unsigned int dlen, int ret) -- cgit v1.2.3 From 1085680bbb7a5235351937bea938c7051b443103 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Thu, 16 Feb 2023 18:35:21 +0800 Subject: crypto: skcipher - Count error stats differently Move all stat code specific to skcipher into the skcipher code. While we're at it, change the stats so that bytes and counts are always incremented even in case of error. This allows the reference counting to be removed as we can now increment the counters prior to the operation. After the operation we simply increase the error count if necessary. This is safe as errors can only occur synchronously (or rather, the existing code already ignored asynchronous errors which are only visible to the callback function). Signed-off-by: Herbert Xu --- include/linux/crypto.h | 24 ------------------------ 1 file changed, 24 deletions(-) (limited to 'include/linux') diff --git a/include/linux/crypto.h b/include/linux/crypto.h index c66f7dc21cbb..e2db56160d5c 100644 --- a/include/linux/crypto.h +++ b/include/linux/crypto.h @@ -276,22 +276,6 @@ struct compress_alg { }; #ifdef CONFIG_CRYPTO_STATS -/* - * struct crypto_istat_cipher - statistics for cipher algorithm - * @encrypt_cnt: number of encrypt requests - * @encrypt_tlen: total data size handled by encrypt requests - * @decrypt_cnt: number of decrypt requests - * @decrypt_tlen: total data size handled by decrypt requests - * @err_cnt: number of error for cipher requests - */ -struct crypto_istat_cipher { - atomic64_t encrypt_cnt; - atomic64_t encrypt_tlen; - atomic64_t decrypt_cnt; - atomic64_t decrypt_tlen; - atomic64_t err_cnt; -}; - /* * struct crypto_istat_rng: statistics for RNG algorithm * @generate_cnt: number of RNG generate requests @@ -385,7 +369,6 @@ struct crypto_istat_rng { * @cra_destroy: internally used * * @stats: union of all possible crypto_istat_xxx structures - * @stats.cipher: statistics for cipher algorithm * @stats.rng: statistics for rng algorithm * * The struct crypto_alg describes a generic Crypto API algorithm and is common @@ -422,7 +405,6 @@ struct crypto_alg { #ifdef CONFIG_CRYPTO_STATS union { - struct crypto_istat_cipher cipher; struct crypto_istat_rng rng; } stats; #endif /* CONFIG_CRYPTO_STATS */ @@ -434,8 +416,6 @@ void crypto_stats_init(struct crypto_alg *alg); void crypto_stats_get(struct crypto_alg *alg); void crypto_stats_rng_seed(struct crypto_alg *alg, int ret); void crypto_stats_rng_generate(struct crypto_alg *alg, unsigned int dlen, int ret); -void crypto_stats_skcipher_encrypt(unsigned int cryptlen, int ret, struct crypto_alg *alg); -void crypto_stats_skcipher_decrypt(unsigned int cryptlen, int ret, struct crypto_alg *alg); #else static inline void crypto_stats_init(struct crypto_alg *alg) {} @@ -445,10 +425,6 @@ static inline void crypto_stats_rng_seed(struct crypto_alg *alg, int ret) {} static inline void crypto_stats_rng_generate(struct crypto_alg *alg, unsigned int dlen, int ret) {} -static inline void crypto_stats_skcipher_encrypt(unsigned int cryptlen, int ret, struct crypto_alg *alg) -{} -static inline void crypto_stats_skcipher_decrypt(unsigned int cryptlen, int ret, struct crypto_alg *alg) -{} #endif /* * A helper struct for waiting for completion of async crypto ops -- cgit v1.2.3 From 9807e49b6aab3451b00a99ced42acb4a535e8e22 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Thu, 16 Feb 2023 18:35:23 +0800 Subject: crypto: rng - Count error stats differently Move all stat code specific to rng into the rng code. While we're at it, change the stats so that bytes and counts are always incremented even in case of error. This allows the reference counting to be removed as we can now increment the counters prior to the operation. After the operation we simply increase the error count if necessary. This is safe as errors can only occur synchronously (or rather, the existing code already ignored asynchronous errors which are only visible to the callback function). Signed-off-by: Herbert Xu --- include/linux/crypto.h | 41 ----------------------------------------- 1 file changed, 41 deletions(-) (limited to 'include/linux') diff --git a/include/linux/crypto.h b/include/linux/crypto.h index e2db56160d5c..c26e59bb7bca 100644 --- a/include/linux/crypto.h +++ b/include/linux/crypto.h @@ -275,22 +275,6 @@ struct compress_alg { unsigned int slen, u8 *dst, unsigned int *dlen); }; -#ifdef CONFIG_CRYPTO_STATS -/* - * struct crypto_istat_rng: statistics for RNG algorithm - * @generate_cnt: number of RNG generate requests - * @generate_tlen: total data size of generated data by the RNG - * @seed_cnt: number of times the RNG was seeded - * @err_cnt: number of error for RNG requests - */ -struct crypto_istat_rng { - atomic64_t generate_cnt; - atomic64_t generate_tlen; - atomic64_t seed_cnt; - atomic64_t err_cnt; -}; -#endif /* CONFIG_CRYPTO_STATS */ - #define cra_cipher cra_u.cipher #define cra_compress cra_u.compress @@ -368,9 +352,6 @@ struct crypto_istat_rng { * @cra_refcnt: internally used * @cra_destroy: internally used * - * @stats: union of all possible crypto_istat_xxx structures - * @stats.rng: statistics for rng algorithm - * * The struct crypto_alg describes a generic Crypto API algorithm and is common * for all of the transformations. Any variable not documented here shall not * be used by a cipher implementation as it is internal to the Crypto API. @@ -402,30 +383,8 @@ struct crypto_alg { void (*cra_destroy)(struct crypto_alg *alg); struct module *cra_module; - -#ifdef CONFIG_CRYPTO_STATS - union { - struct crypto_istat_rng rng; - } stats; -#endif /* CONFIG_CRYPTO_STATS */ - } CRYPTO_MINALIGN_ATTR; -#ifdef CONFIG_CRYPTO_STATS -void crypto_stats_init(struct crypto_alg *alg); -void crypto_stats_get(struct crypto_alg *alg); -void crypto_stats_rng_seed(struct crypto_alg *alg, int ret); -void crypto_stats_rng_generate(struct crypto_alg *alg, unsigned int dlen, int ret); -#else -static inline void crypto_stats_init(struct crypto_alg *alg) -{} -static inline void crypto_stats_get(struct crypto_alg *alg) -{} -static inline void crypto_stats_rng_seed(struct crypto_alg *alg, int ret) -{} -static inline void crypto_stats_rng_generate(struct crypto_alg *alg, unsigned int dlen, int ret) -{} -#endif /* * A helper struct for waiting for completion of async crypto ops */ -- cgit v1.2.3 From 0c0edf6168ce1e02518ba44400b9269a13c3b9e6 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Thu, 16 Feb 2023 18:35:25 +0800 Subject: crypto: api - Move MODULE_ALIAS_CRYPTO to algapi.h This is part of the low-level API and should not be exposed to top-level Crypto API users. Signed-off-by: Herbert Xu --- include/linux/crypto.h | 13 ------------- 1 file changed, 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/crypto.h b/include/linux/crypto.h index c26e59bb7bca..d57597ebef6e 100644 --- a/include/linux/crypto.h +++ b/include/linux/crypto.h @@ -20,19 +20,6 @@ #include #include -/* - * Autoloaded crypto modules should only use a prefixed name to avoid allowing - * arbitrary modules to be loaded. Loading from userspace may still need the - * unprefixed names, so retains those aliases as well. - * This uses __MODULE_INFO directly instead of MODULE_ALIAS because pre-4.3 - * gcc (e.g. avr32 toolchain) uses __LINE__ for uniqueness, and this macro - * expands twice on the same line. Instead, use a separate base name for the - * alias. - */ -#define MODULE_ALIAS_CRYPTO(name) \ - __MODULE_INFO(alias, alias_userspace, name); \ - __MODULE_INFO(alias, alias_crypto, "crypto-" name) - /* * Algorithm masks and types. */ -- cgit v1.2.3 From 79963fbfc233759bd8a43462f120d15a1bd4f4fa Mon Sep 17 00:00:00 2001 From: Tanmay Shah Date: Fri, 10 Mar 2023 17:24:06 -0800 Subject: mailbox: zynqmp: Fix typo in IPI documentation Xilinx IPI message buffers allows 32-byte data transfer. Fix documentation that says 12 bytes Fixes: 4981b82ba2ff ("mailbox: ZynqMP IPI mailbox controller") Signed-off-by: Tanmay Shah Acked-by: Michal Simek Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230311012407.1292118-4-tanmay.shah@amd.com Signed-off-by: Mathieu Poirier --- include/linux/mailbox/zynqmp-ipi-message.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mailbox/zynqmp-ipi-message.h b/include/linux/mailbox/zynqmp-ipi-message.h index 35ce84c8ca02..31d8046d945e 100644 --- a/include/linux/mailbox/zynqmp-ipi-message.h +++ b/include/linux/mailbox/zynqmp-ipi-message.h @@ -9,7 +9,7 @@ * @data: message payload * * This is the structure for data used in mbox_send_message - * the maximum length of data buffer is fixed to 12 bytes. + * the maximum length of data buffer is fixed to 32 bytes. * Client is supposed to be aware of this. */ struct zynqmp_ipi_message { -- cgit v1.2.3 From 2c854e5fcd7e243f5a7cf6a6afa0ef83060c903c Mon Sep 17 00:00:00 2001 From: Alexander Lobakin Date: Mon, 13 Mar 2023 22:55:51 +0100 Subject: net: page_pool, skbuff: make skb_mark_for_recycle() always available skb_mark_for_recycle() is guarded with CONFIG_PAGE_POOL, this creates unneeded complication when using it in the generic code. For now, it's only used in the drivers always selecting Page Pool, so this works. Move the guards so that preprocessor will cut out only the operation itself and the function will still be a noop on !PAGE_POOL systems, but available there as well. No functional changes. Reported-by: kernel test robot Link: https://lore.kernel.org/oe-kbuild-all/202303020342.Wi2PRFFH-lkp@intel.com Signed-off-by: Alexander Lobakin Link: https://lore.kernel.org/r/20230313215553.1045175-3-aleksander.lobakin@intel.com Signed-off-by: Alexei Starovoitov --- include/linux/skbuff.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index fe661011644b..3f3a2a82a86b 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -5069,12 +5069,12 @@ static inline u64 skb_get_kcov_handle(struct sk_buff *skb) #endif } -#ifdef CONFIG_PAGE_POOL static inline void skb_mark_for_recycle(struct sk_buff *skb) { +#ifdef CONFIG_PAGE_POOL skb->pp_recycle = 1; -} #endif +} #endif /* __KERNEL__ */ #endif /* _LINUX_SKBUFF_H */ -- cgit v1.2.3 From 84706e9a75ffc3c950424bdfea06cabb4101a6b4 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Tue, 14 Mar 2023 09:54:00 +0800 Subject: soundwire: intel: add sync_arm/sync_go to ops The bus start/stop sequences can be reused between platforms if we add a couple of new callbacks. In following patches the code will be moved to a shared file. Signed-off-by: Pierre-Louis Bossart Reviewed-by: Rander Wang Signed-off-by: Bard Liao Link: https://lore.kernel.org/r/20230314015410.487311-7-yung-chuan.liao@linux.intel.com Signed-off-by: Vinod Koul --- include/linux/soundwire/sdw_intel.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/soundwire/sdw_intel.h b/include/linux/soundwire/sdw_intel.h index 91f0dc564fe5..06fa30929ebd 100644 --- a/include/linux/soundwire/sdw_intel.h +++ b/include/linux/soundwire/sdw_intel.h @@ -309,6 +309,10 @@ struct sdw_intel; * @shim_wake: enable/disable in-band wake management * @pre_bank_switch: helper for bus management * @post_bank_switch: helper for bus management + * @sync_arm: helper for multi-link synchronization + * @sync_go_unlocked: helper for multi-link synchronization - + * shim_lock is assumed to be locked at higher level + * @sync_go: helper for multi-link synchronization */ struct sdw_intel_hw_ops { void (*debugfs_init)(struct sdw_intel *sdw); @@ -330,6 +334,10 @@ struct sdw_intel_hw_ops { int (*pre_bank_switch)(struct sdw_intel *sdw); int (*post_bank_switch)(struct sdw_intel *sdw); + + void (*sync_arm)(struct sdw_intel *sdw); + int (*sync_go_unlocked)(struct sdw_intel *sdw); + int (*sync_go)(struct sdw_intel *sdw); }; extern const struct sdw_intel_hw_ops sdw_intel_cnl_hw_ops; -- cgit v1.2.3 From 1e76de2e5dfeff17f13afe8146449fec3f5b69f7 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Tue, 14 Mar 2023 09:54:03 +0800 Subject: soundwire: intel: add abstraction for cmdsync check If we add one more callback, we can have common bank switch sequences between old and new hardware: the only difference is where the CMDSYNC register is located. Signed-off-by: Pierre-Louis Bossart Reviewed-by: Rander Wang Signed-off-by: Bard Liao Link: https://lore.kernel.org/r/20230314015410.487311-10-yung-chuan.liao@linux.intel.com Signed-off-by: Vinod Koul --- include/linux/soundwire/sdw_intel.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/soundwire/sdw_intel.h b/include/linux/soundwire/sdw_intel.h index 06fa30929ebd..207701aeeb47 100644 --- a/include/linux/soundwire/sdw_intel.h +++ b/include/linux/soundwire/sdw_intel.h @@ -313,6 +313,8 @@ struct sdw_intel; * @sync_go_unlocked: helper for multi-link synchronization - * shim_lock is assumed to be locked at higher level * @sync_go: helper for multi-link synchronization + * @sync_check_cmdsync_unlocked: helper for multi-link synchronization + * and bank switch - shim_lock is assumed to be locked at higher level */ struct sdw_intel_hw_ops { void (*debugfs_init)(struct sdw_intel *sdw); @@ -338,6 +340,7 @@ struct sdw_intel_hw_ops { void (*sync_arm)(struct sdw_intel *sdw); int (*sync_go_unlocked)(struct sdw_intel *sdw); int (*sync_go)(struct sdw_intel *sdw); + bool (*sync_check_cmdsync_unlocked)(struct sdw_intel *sdw); }; extern const struct sdw_intel_hw_ops sdw_intel_cnl_hw_ops; -- cgit v1.2.3 From ee13b5008707948d3052c1b5aab485c6cd53658e Mon Sep 17 00:00:00 2001 From: Manivannan Sadhasivam Date: Tue, 14 Mar 2023 13:34:41 +0530 Subject: qcom: llcc/edac: Fix the base address used for accessing LLCC banks The Qualcomm LLCC/EDAC drivers were using a fixed register stride for accessing the (Control and Status Registers) CSRs of each LLCC bank. This stride only works for some SoCs like SDM845 for which driver support was initially added. But the later SoCs use different register stride that vary between the banks with holes in-between. So it is not possible to use a single register stride for accessing the CSRs of each bank. By doing so could result in a crash. For fixing this issue, let's obtain the base address of each LLCC bank from devicetree and get rid of the fixed stride. This also means, there is no need to rely on reg-names property and the base addresses can be obtained using the index. First index is LLCC bank 0 and last index is LLCC broadcast. If the SoC supports more than one bank, then those need to be defined in devicetree for index from 1..N-1. Reported-by: Parikshit Pareek Tested-by: Luca Weiss Tested-by: Steev Klimaszewski # Thinkpad X13s Tested-by: Andrew Halaney # sa8540p-ride Reviewed-by: Borislav Petkov (AMD) Signed-off-by: Manivannan Sadhasivam Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20230314080443.64635-13-manivannan.sadhasivam@linaro.org --- include/linux/soc/qcom/llcc-qcom.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/soc/qcom/llcc-qcom.h b/include/linux/soc/qcom/llcc-qcom.h index ad1fd718169d..423220e66026 100644 --- a/include/linux/soc/qcom/llcc-qcom.h +++ b/include/linux/soc/qcom/llcc-qcom.h @@ -120,7 +120,7 @@ struct llcc_edac_reg_offset { /** * struct llcc_drv_data - Data associated with the llcc driver - * @regmap: regmap associated with the llcc device + * @regmaps: regmaps associated with the llcc device * @bcast_regmap: regmap associated with llcc broadcast offset * @cfg: pointer to the data structure for slice configuration * @edac_reg_offset: Offset of the LLCC EDAC registers @@ -129,12 +129,11 @@ struct llcc_edac_reg_offset { * @max_slices: max slices as read from device tree * @num_banks: Number of llcc banks * @bitmap: Bit map to track the active slice ids - * @offsets: Pointer to the bank offsets array * @ecc_irq: interrupt for llcc cache error detection and reporting * @version: Indicates the LLCC version */ struct llcc_drv_data { - struct regmap *regmap; + struct regmap **regmaps; struct regmap *bcast_regmap; const struct llcc_slice_config *cfg; const struct llcc_edac_reg_offset *edac_reg_offset; @@ -143,7 +142,6 @@ struct llcc_drv_data { u32 max_slices; u32 num_banks; unsigned long *bitmap; - u32 *offsets; int ecc_irq; u32 version; }; -- cgit v1.2.3 From 968a26a07f75377afbd4f7bb18ef587a1443c244 Mon Sep 17 00:00:00 2001 From: Elliot Berman Date: Mon, 13 Feb 2023 10:18:29 -0800 Subject: firmware: qcom_scm: Use fixed width src vm bitmap The maximum VMID for assign_mem is 63. Use a u64 to represent this bitmap instead of architecture-dependent "unsigned int" which varies in size on 32-bit and 64-bit platforms. Acked-by: Kalle Valo (ath10k) Tested-by: Gokul krishna Krishnakumar Signed-off-by: Elliot Berman Reviewed-by: Bjorn Andersson Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20230213181832.3489174-1-quic_eberman@quicinc.com --- include/linux/firmware/qcom/qcom_scm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/firmware/qcom/qcom_scm.h b/include/linux/firmware/qcom/qcom_scm.h index 1e449a5d7f5c..250ea4efb7cb 100644 --- a/include/linux/firmware/qcom/qcom_scm.h +++ b/include/linux/firmware/qcom/qcom_scm.h @@ -94,7 +94,7 @@ extern int qcom_scm_mem_protect_video_var(u32 cp_start, u32 cp_size, u32 cp_nonpixel_start, u32 cp_nonpixel_size); extern int qcom_scm_assign_mem(phys_addr_t mem_addr, size_t mem_sz, - unsigned int *src, + u64 *src, const struct qcom_scm_vmperm *newvm, unsigned int dest_cnt); -- cgit v1.2.3 From 31bf1dbccfb0a9861d4846755096b3fff5687f8a Mon Sep 17 00:00:00 2001 From: Viktor Malik Date: Fri, 10 Mar 2023 08:40:59 +0100 Subject: bpf: Fix attaching fentry/fexit/fmod_ret/lsm to modules This resolves two problems with attachment of fentry/fexit/fmod_ret/lsm to functions located in modules: 1. The verifier tries to find the address to attach to in kallsyms. This is always done by searching the entire kallsyms, not respecting the module in which the function is located. Such approach causes an incorrect attachment address to be computed if the function to attach to is shadowed by a function of the same name located earlier in kallsyms. 2. If the address to attach to is located in a module, the module reference is only acquired in register_fentry. If the module is unloaded between the place where the address is found (bpf_check_attach_target in the verifier) and register_fentry, it is possible that another module is loaded to the same address which may lead to potential errors. Since the attachment must contain the BTF of the program to attach to, we extract the module from it and search for the function address in the correct module (resolving problem no. 1). Then, the module reference is taken directly in bpf_check_attach_target and stored in the bpf program (in bpf_prog_aux). The reference is only released when the program is unloaded (resolving problem no. 2). Signed-off-by: Viktor Malik Acked-by: Jiri Olsa Reviewed-by: Luis Chamberlain Link: https://lore.kernel.org/r/3f6a9d8ae850532b5ef864ef16327b0f7a669063.1678432753.git.vmalik@redhat.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 71cc92a4ba48..3ef98fb92987 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1103,6 +1103,7 @@ struct bpf_trampoline { struct bpf_attach_target_info { struct btf_func_model fmodel; long tgt_addr; + struct module *tgt_mod; const char *tgt_name; const struct btf_type *tgt_type; }; @@ -1406,6 +1407,7 @@ struct bpf_prog_aux { * main prog always has linfo_idx == 0 */ u32 linfo_idx; + struct module *mod; u32 num_exentries; struct exception_table_entry *extable; union { -- cgit v1.2.3 From c1fef618d611b31964ab397aa0bf0611da94bade Mon Sep 17 00:00:00 2001 From: Sandipan Patra Date: Mon, 13 Mar 2023 22:42:23 -0700 Subject: net/mlx5: Implement thermal zone Implement thermal zone support for mlx5 based HW. The NIC uses temperature sensor provided by ASIC to report current temperature to thermal core. Signed-off-by: Sandipan Patra Reviewed-by: Gal Pressman Signed-off-by: Saeed Mahameed Link: https://lore.kernel.org/r/20230314054234.267365-5-saeed@kernel.org Signed-off-by: Jakub Kicinski --- include/linux/mlx5/driver.h | 3 +++ include/linux/mlx5/mlx5_ifc.h | 26 ++++++++++++++++++++++++++ 2 files changed, 29 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index f33389b42209..7a898113b6b7 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -134,6 +134,7 @@ enum { MLX5_REG_PCAM = 0x507f, MLX5_REG_NODE_DESC = 0x6001, MLX5_REG_HOST_ENDIANNESS = 0x7004, + MLX5_REG_MTMP = 0x900A, MLX5_REG_MCIA = 0x9014, MLX5_REG_MFRL = 0x9028, MLX5_REG_MLCR = 0x902b, @@ -731,6 +732,7 @@ struct mlx5_fw_tracer; struct mlx5_vxlan; struct mlx5_geneve; struct mlx5_hv_vhca; +struct mlx5_thermal; #define MLX5_LOG_SW_ICM_BLOCK_SIZE(dev) (MLX5_CAP_DEV_MEM(dev, log_sw_icm_alloc_granularity)) #define MLX5_SW_ICM_BLOCK_SIZE(dev) (1 << MLX5_LOG_SW_ICM_BLOCK_SIZE(dev)) @@ -808,6 +810,7 @@ struct mlx5_core_dev { struct mlx5_rsc_dump *rsc_dump; u32 vsc_addr; struct mlx5_hv_vhca *hv_vhca; + struct mlx5_thermal *thermal; }; struct mlx5_db { diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 66d76e97a087..d2c164f0778c 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -10869,6 +10869,31 @@ struct mlx5_ifc_mrtc_reg_bits { u8 time_l[0x20]; }; +struct mlx5_ifc_mtmp_reg_bits { + u8 reserved_at_0[0x14]; + u8 sensor_index[0xc]; + + u8 reserved_at_20[0x10]; + u8 temperature[0x10]; + + u8 mte[0x1]; + u8 mtr[0x1]; + u8 reserved_at_42[0xe]; + u8 max_temperature[0x10]; + + u8 tee[0x2]; + u8 reserved_at_62[0xe]; + u8 temp_threshold_hi[0x10]; + + u8 reserved_at_80[0x10]; + u8 temp_threshold_lo[0x10]; + + u8 reserved_at_a0[0x20]; + + u8 sensor_name_hi[0x20]; + u8 sensor_name_lo[0x20]; +}; + union mlx5_ifc_ports_control_registers_document_bits { struct mlx5_ifc_bufferx_reg_bits bufferx_reg; struct mlx5_ifc_eth_2819_cntrs_grp_data_layout_bits eth_2819_cntrs_grp_data_layout; @@ -10931,6 +10956,7 @@ union mlx5_ifc_ports_control_registers_document_bits { struct mlx5_ifc_mfrl_reg_bits mfrl_reg; struct mlx5_ifc_mtutc_reg_bits mtutc_reg; struct mlx5_ifc_mrtc_reg_bits mrtc_reg; + struct mlx5_ifc_mtmp_reg_bits mtmp_reg; u8 reserved_at_0[0x60e0]; }; -- cgit v1.2.3 From 028522e2844393abc44f7bd7477eb4a455f01579 Mon Sep 17 00:00:00 2001 From: Gal Pressman Date: Mon, 13 Mar 2023 22:42:29 -0700 Subject: net/mlx5: Move needed PTYS functions to core layer Downstream patches require devlink params to access the PTYS register, move the needed functions from mlx5e to the core layer. Signed-off-by: Gal Pressman Reviewed-by: Tariq Toukan Signed-off-by: Saeed Mahameed Link: https://lore.kernel.org/r/20230314054234.267365-11-saeed@kernel.org Signed-off-by: Jakub Kicinski --- include/linux/mlx5/port.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/port.h b/include/linux/mlx5/port.h index e96ee1e348cb..98b2e1e149f9 100644 --- a/include/linux/mlx5/port.h +++ b/include/linux/mlx5/port.h @@ -141,6 +141,12 @@ enum mlx5_ptys_width { MLX5_PTYS_WIDTH_12X = 1 << 4, }; +struct mlx5_port_eth_proto { + u32 cap; + u32 admin; + u32 oper; +}; + #define MLX5E_PROT_MASK(link_mode) (1U << link_mode) #define MLX5_GET_ETH_PROTO(reg, out, ext, field) \ (ext ? MLX5_GET(reg, out, ext_##field) : \ @@ -218,4 +224,14 @@ int mlx5_set_trust_state(struct mlx5_core_dev *mdev, u8 trust_state); int mlx5_query_trust_state(struct mlx5_core_dev *mdev, u8 *trust_state); int mlx5_set_dscp2prio(struct mlx5_core_dev *mdev, u8 dscp, u8 prio); int mlx5_query_dscp2prio(struct mlx5_core_dev *mdev, u8 *dscp2prio); + +int mlx5_port_query_eth_proto(struct mlx5_core_dev *dev, u8 port, bool ext, + struct mlx5_port_eth_proto *eproto); +bool mlx5_ptys_ext_supported(struct mlx5_core_dev *mdev); +u32 mlx5_port_ptys2speed(struct mlx5_core_dev *mdev, u32 eth_proto_oper, + bool force_legacy); +u32 mlx5_port_speed2linkmodes(struct mlx5_core_dev *mdev, u32 speed, + bool force_legacy); +int mlx5_port_max_linkspeed(struct mlx5_core_dev *mdev, u32 *speed); + #endif /* __MLX5_PORT_H__ */ -- cgit v1.2.3 From 96ec2d9868c4afd3cea17f4ee18b84ccc1cde20f Mon Sep 17 00:00:00 2001 From: Orlando Chamberlain Date: Fri, 3 Mar 2023 22:28:41 +1100 Subject: platform/x86: apple-gmux: refactor gmux types Add apple_gmux_config struct containing operations and data specific to each mux type. This is in preparation for adding a third, MMIO based, gmux type. Reviewed-by: Hans de Goede Signed-off-by: Orlando Chamberlain Link: https://lore.kernel.org/r/20230303112842.3094-3-orlandoch.dev@gmail.com Signed-off-by: Hans de Goede --- include/linux/apple-gmux.h | 18 ++++++++++++------ 1 file changed, 12 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/apple-gmux.h b/include/linux/apple-gmux.h index 1f68b49bcd68..147dc1c52e08 100644 --- a/include/linux/apple-gmux.h +++ b/include/linux/apple-gmux.h @@ -36,6 +36,11 @@ #define GMUX_MIN_IO_LEN (GMUX_PORT_BRIGHTNESS + 4) +enum apple_gmux_type { + APPLE_GMUX_TYPE_PIO, + APPLE_GMUX_TYPE_INDEXED, +}; + #if IS_ENABLED(CONFIG_APPLE_GMUX) static inline bool apple_gmux_is_indexed(unsigned long iostart) { @@ -65,13 +70,13 @@ static inline bool apple_gmux_is_indexed(unsigned long iostart) * Return: %true if a supported gmux ACPI device is detected and the kernel * was configured with CONFIG_APPLE_GMUX, %false otherwise. */ -static inline bool apple_gmux_detect(struct pnp_dev *pnp_dev, bool *indexed_ret) +static inline bool apple_gmux_detect(struct pnp_dev *pnp_dev, enum apple_gmux_type *type_ret) { u8 ver_major, ver_minor, ver_release; struct device *dev = NULL; struct acpi_device *adev; struct resource *res; - bool indexed = false; + enum apple_gmux_type type = APPLE_GMUX_TYPE_PIO; bool ret = false; if (!pnp_dev) { @@ -99,13 +104,14 @@ static inline bool apple_gmux_detect(struct pnp_dev *pnp_dev, bool *indexed_ret) ver_minor = inb(res->start + GMUX_PORT_VERSION_MINOR); ver_release = inb(res->start + GMUX_PORT_VERSION_RELEASE); if (ver_major == 0xff && ver_minor == 0xff && ver_release == 0xff) { - indexed = apple_gmux_is_indexed(res->start); - if (!indexed) + if (apple_gmux_is_indexed(res->start)) + type = APPLE_GMUX_TYPE_INDEXED; + else goto out; } - if (indexed_ret) - *indexed_ret = indexed; + if (type_ret) + *type_ret = type; ret = true; out: -- cgit v1.2.3 From 0c18184de990e63f708b090bcb9fc6c0fbc427cd Mon Sep 17 00:00:00 2001 From: Orlando Chamberlain Date: Fri, 3 Mar 2023 22:28:42 +1100 Subject: platform/x86: apple-gmux: support MMIO gmux on T2 Macs In some newer dual gpu MacBooks, the T2 Coprocessor functions as the gmux, and the Intel side can interract with this new gmux type through MMIO. Add support for these gmux controllers to the apple-gmux driver. We start using the GMSP(0) acpi method on these gmux's when clearing interrupts, as this prevents a flood of status=0 interrupts that can't be cleared. It's unknown if this helps or hinders older gmux types, so it isn't enabled for those. Interestingly, the ACPI table only allocates 8 bytes for GMUX, but we actually need 16, and as such we request 16 with request_mem_region. Reading and writing from ports: 16 bytes from 0xfe0b0200 are used. 0x0 to 0x4 are where data to read appears, and where data to write goes. Writing to 0xe sets the gmux port being accessed, and writing to 0xf sends commands. These commands are 0x40 & data_length for write, and data_length for read, where data_length is 1, 2 or 4. Once byte base+0xf is 0, the command is done. Issues: As with other retina models, we can't switch DDC lines so switching at runtime doesn't work if the inactive gpu driver already disabled eDP due to it not being connected when that driver loaded. Additionally, turning on the dgpu back on on the MacBookPro16,1 does not work. Reviewed-by: Hans de Goede Signed-off-by: Orlando Chamberlain Link: https://lore.kernel.org/r/20230303112842.3094-4-orlandoch.dev@gmail.com Signed-off-by: Hans de Goede --- include/linux/apple-gmux.h | 56 +++++++++++++++++++++++++++++++++++----------- 1 file changed, 43 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/apple-gmux.h b/include/linux/apple-gmux.h index 147dc1c52e08..272f63f8fd7c 100644 --- a/include/linux/apple-gmux.h +++ b/include/linux/apple-gmux.h @@ -34,11 +34,18 @@ #define GMUX_PORT_READ 0xd0 #define GMUX_PORT_WRITE 0xd4 +#define GMUX_MMIO_PORT_SELECT 0x0e +#define GMUX_MMIO_COMMAND_SEND 0x0f + +#define GMUX_MMIO_READ 0x00 +#define GMUX_MMIO_WRITE 0x40 + #define GMUX_MIN_IO_LEN (GMUX_PORT_BRIGHTNESS + 4) enum apple_gmux_type { APPLE_GMUX_TYPE_PIO, APPLE_GMUX_TYPE_INDEXED, + APPLE_GMUX_TYPE_MMIO, }; #if IS_ENABLED(CONFIG_APPLE_GMUX) @@ -57,6 +64,24 @@ static inline bool apple_gmux_is_indexed(unsigned long iostart) return false; } +static inline bool apple_gmux_is_mmio(unsigned long iostart) +{ + u8 *__iomem iomem_base = ioremap(iostart, 16); + u8 val; + + if (!iomem_base) + return false; + + /* + * If this is 0xff, then gmux must not be present, as the gmux would + * reset it to 0x00, or it would be one of 0x1, 0x4, 0x41, 0x44 if a + * command is currently being processed. + */ + val = ioread8(iomem_base + GMUX_MMIO_COMMAND_SEND); + iounmap(iomem_base); + return (val != 0xff); +} + /** * apple_gmux_detect() - detect if gmux is built into the machine * @@ -93,19 +118,24 @@ static inline bool apple_gmux_detect(struct pnp_dev *pnp_dev, enum apple_gmux_ty } res = pnp_get_resource(pnp_dev, IORESOURCE_IO, 0); - if (!res || resource_size(res) < GMUX_MIN_IO_LEN) - goto out; - - /* - * Invalid version information may indicate either that the gmux - * device isn't present or that it's a new one that uses indexed io. - */ - ver_major = inb(res->start + GMUX_PORT_VERSION_MAJOR); - ver_minor = inb(res->start + GMUX_PORT_VERSION_MINOR); - ver_release = inb(res->start + GMUX_PORT_VERSION_RELEASE); - if (ver_major == 0xff && ver_minor == 0xff && ver_release == 0xff) { - if (apple_gmux_is_indexed(res->start)) - type = APPLE_GMUX_TYPE_INDEXED; + if (res && resource_size(res) >= GMUX_MIN_IO_LEN) { + /* + * Invalid version information may indicate either that the gmux + * device isn't present or that it's a new one that uses indexed io. + */ + ver_major = inb(res->start + GMUX_PORT_VERSION_MAJOR); + ver_minor = inb(res->start + GMUX_PORT_VERSION_MINOR); + ver_release = inb(res->start + GMUX_PORT_VERSION_RELEASE); + if (ver_major == 0xff && ver_minor == 0xff && ver_release == 0xff) { + if (apple_gmux_is_indexed(res->start)) + type = APPLE_GMUX_TYPE_INDEXED; + else + goto out; + } + } else { + res = pnp_get_resource(pnp_dev, IORESOURCE_MEM, 0); + if (res && apple_gmux_is_mmio(res->start)) + type = APPLE_GMUX_TYPE_MMIO; else goto out; } -- cgit v1.2.3 From b91e6107119f62be8b51b9955294be52c0b4fc80 Mon Sep 17 00:00:00 2001 From: Emanuele Ghidoli Date: Mon, 13 Mar 2023 17:50:39 +0100 Subject: usb: misc: usb3503: support usb3803 and bypass mode Add support for USB3803 and bypass mode, with this change is also possible to move the component out of bypass mode. In bypass mode the downstream port 3 is connected to the upstream port with low switch resistance R_on. Controlling mode of operations: | RESET_N | BYPASS_N | Mode | -------------------------------- | 0 | 0 | standby | | 1 | 0 | bypass | | 1 | 1 | hub | Datasheet: https://ww1.microchip.com/downloads/aemDocuments/documents/UNG/ProductDocuments/DataSheets/00001691D.pdf Signed-off-by: Emanuele Ghidoli Signed-off-by: Francesco Dolcini Link: https://lore.kernel.org/r/20230313165039.255579-4-francesco@dolcini.it Signed-off-by: Greg Kroah-Hartman --- include/linux/platform_data/usb3503.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/platform_data/usb3503.h b/include/linux/platform_data/usb3503.h index d01ef97ddf36..f3c942f396f8 100644 --- a/include/linux/platform_data/usb3503.h +++ b/include/linux/platform_data/usb3503.h @@ -12,6 +12,7 @@ enum usb3503_mode { USB3503_MODE_UNKNOWN, USB3503_MODE_HUB, USB3503_MODE_STANDBY, + USB3503_MODE_BYPASS, }; struct usb3503_platform_data { -- cgit v1.2.3 From ad3d0ee8dca5fa4a656057e20f9605bbe7ff067c Mon Sep 17 00:00:00 2001 From: Orlando Chamberlain Date: Thu, 9 Mar 2023 21:43:54 +1100 Subject: platform/x86: apple-gmux: Update apple_gmux_detect documentation Commit fc83fbc80e1a ("platform/x86: apple-gmux: refactor gmux types") neglected to update the documentation of apple_gmux_detect's arguments. Update the documentation to reflect that commit's changes. include/linux/apple-gmux.h:99: warning: Function parameter or member 'type_ret' not described in 'apple_gmux_detect' include/linux/apple-gmux.h:99: warning: Excess function parameter 'indexed_ret' description in 'apple_gmux_detect' Reported-by: Stephen Rothwell Link: https://lore.kernel.org/lkml/20230309122822.77435e33@canb.auug.org.au/ Fixes: fc83fbc80e1a ("platform/x86: apple-gmux: refactor gmux types") Signed-off-by: Orlando Chamberlain Link: https://lore.kernel.org/r/20230309104353.10905-1-orlandoch.dev@gmail.com Reviewed-by: Hans de Goede Signed-off-by: Hans de Goede --- include/linux/apple-gmux.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/apple-gmux.h b/include/linux/apple-gmux.h index 272f63f8fd7c..a7a7d430024b 100644 --- a/include/linux/apple-gmux.h +++ b/include/linux/apple-gmux.h @@ -86,7 +86,7 @@ static inline bool apple_gmux_is_mmio(unsigned long iostart) * apple_gmux_detect() - detect if gmux is built into the machine * * @pnp_dev: Device to probe or NULL to use the first matching device - * @indexed_ret: Returns (by reference) if the gmux is indexed or not + * @type_ret: Returns (by reference) the apple_gmux_type of the device * * Detect if a supported gmux device is present by actually probing it. * This avoids the false positives returned on some models by -- cgit v1.2.3 From 3608a2cd818a8d97bd3d4dc32f6c0afaf09b15ec Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Tue, 7 Mar 2023 13:05:40 +0100 Subject: backlight: apple_bl: Use acpi_video_get_backlight_type() On some MacBooks both the apple_bl and the apple-gmux backlight drivers may be able to export a /sys/class/backlight device. To avoid having 2 backlight devices for one LCD panel until now the apple-gmux driver has been calling apple_bl_unregister() to move the apple_bl backlight device out of the way when it loads. Similar problems exist on other x86 laptops and all backlight drivers which may be used on x86 laptops have moved to using acpi_video_get_backlight_type() to determine whether they should load or not. Switch apple_bl to this model too, so that it is consistent with all the other x86 backlight drivers. Besides code-simplification and consistency this has 2 other benefits: 1) It removes a race during boot where userspace will briefly see an apple_bl backlight and then have it disappear again, leading to e.g.: https://bbs.archlinux.org/viewtopic.php?id=269920 2) This allows user to switch between the drivers by passing acpi_backlight=apple_gmux or acpi_backlight=vendor on the kernel commandline. Signed-off-by: Hans de Goede Reviewed-by: Daniel Thompson Acked-by: Lee Jones Link: https://lore.kernel.org/r/20230307120540.389920-1-hdegoede@redhat.com --- include/linux/apple_bl.h | 27 --------------------------- 1 file changed, 27 deletions(-) delete mode 100644 include/linux/apple_bl.h (limited to 'include/linux') diff --git a/include/linux/apple_bl.h b/include/linux/apple_bl.h deleted file mode 100644 index 445af2e3cc21..000000000000 --- a/include/linux/apple_bl.h +++ /dev/null @@ -1,27 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * apple_bl exported symbols - */ - -#ifndef _LINUX_APPLE_BL_H -#define _LINUX_APPLE_BL_H - -#if defined(CONFIG_BACKLIGHT_APPLE) || defined(CONFIG_BACKLIGHT_APPLE_MODULE) - -extern int apple_bl_register(void); -extern void apple_bl_unregister(void); - -#else /* !CONFIG_BACKLIGHT_APPLE */ - -static inline int apple_bl_register(void) -{ - return 0; -} - -static inline void apple_bl_unregister(void) -{ -} - -#endif /* !CONFIG_BACKLIGHT_APPLE */ - -#endif /* _LINUX_APPLE_BL_H */ -- cgit v1.2.3 From 027781f3920ad16f40133890fc87247b8baa2d8d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Leonard=20G=C3=B6hrs?= Date: Fri, 10 Mar 2023 10:20:52 +0100 Subject: spi: core: add spi_split_transfers_maxwords MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add spi_split_transfers_maxwords() function that splits spi_transfers transparently into multiple transfers that are below a given number of SPI words. This function reuses most of its code from spi_split_transfers_maxsize() and for transfers with eight or less bits per word actually behaves the same. Signed-off-by: Leonard Göhrs Link: https://lore.kernel.org/r/20230310092053.1006459-1-l.goehrs@pengutronix.de Signed-off-by: Mark Brown --- include/linux/spi/spi.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 74bff5a2f53d..873ced6ae4ca 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -1295,6 +1295,10 @@ extern int spi_split_transfers_maxsize(struct spi_controller *ctlr, struct spi_message *msg, size_t maxsize, gfp_t gfp); +extern int spi_split_transfers_maxwords(struct spi_controller *ctlr, + struct spi_message *msg, + size_t maxwords, + gfp_t gfp); /*---------------------------------------------------------------------------*/ -- cgit v1.2.3 From 4e04143c869c5b6d499fbd5083caa860d5c942c3 Mon Sep 17 00:00:00 2001 From: Ondrej Mosnacek Date: Thu, 16 Mar 2023 14:07:51 +0100 Subject: fs_context: drop the unused lsm_flags member This isn't ever used by VFS now, and it couldn't even work. Any FS that uses the SECURITY_LSM_NATIVE_LABELS flag needs to also process the value returned back from the LSM, so it needs to do its security_sb_set_mnt_opts() call on its own anyway. Signed-off-by: Ondrej Mosnacek Signed-off-by: Christian Brauner (Microsoft) --- include/linux/fs_context.h | 1 - include/linux/security.h | 2 +- 2 files changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs_context.h b/include/linux/fs_context.h index 5469ffee21c7..ff6341e09925 100644 --- a/include/linux/fs_context.h +++ b/include/linux/fs_context.h @@ -104,7 +104,6 @@ struct fs_context { unsigned int sb_flags; /* Proposed superblock flags (SB_*) */ unsigned int sb_flags_mask; /* Superblock flags that were changed */ unsigned int s_iflags; /* OR'd with sb->s_iflags */ - unsigned int lsm_flags; /* Information flags from the fs to the LSM */ enum fs_context_purpose purpose:8; enum fs_context_phase phase:8; /* The phase the context is in */ bool need_free:1; /* Need to call ops->free() */ diff --git a/include/linux/security.h b/include/linux/security.h index 5984d0d550b4..db9b659b02b9 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -68,7 +68,7 @@ struct watch_notification; /* If capable is being called by a setid function */ #define CAP_OPT_INSETID BIT(2) -/* LSM Agnostic defines for fs_context::lsm_flags */ +/* LSM Agnostic defines for security_sb_set_mnt_opts() flags */ #define SECURITY_LSM_NATIVE_LABELS 1 struct ctl_table; -- cgit v1.2.3 From d8708b80fa0e6e21bc0c9e7276ad0bccef73b6e7 Mon Sep 17 00:00:00 2001 From: Thomas Huth Date: Wed, 8 Feb 2023 15:01:05 +0100 Subject: KVM: Change return type of kvm_arch_vm_ioctl() to "int" All kvm_arch_vm_ioctl() implementations now only deal with "int" types as return values, so we can change the return type of these functions to use "int" instead of "long". Signed-off-by: Thomas Huth Acked-by: Anup Patel Message-Id: <20230208140105.655814-7-thuth@redhat.com> Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 8ada23756b0e..90edc16d37e5 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1397,8 +1397,7 @@ int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_level, bool line_status); int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap); -long kvm_arch_vm_ioctl(struct file *filp, - unsigned int ioctl, unsigned long arg); +int kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg); long kvm_arch_vm_compat_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg); -- cgit v1.2.3 From 8af70e202ac4ea5dd2d5561cc2675bc09b30412e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= Date: Sat, 18 Feb 2023 17:21:21 +0000 Subject: leds: Fix reference to led_set_brightness() in doc MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The referenced function led_classdev_brightness_set() never existed. Fixes: 5ada28bf7675 ("led-class: always implement blinking") Signed-off-by: Thomas Weißschuh Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230218-typo-led-set-v1-1-3c35362a2f2d@weissschuh.net --- include/linux/leds.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/leds.h b/include/linux/leds.h index d71201a968b6..aedf34165354 100644 --- a/include/linux/leds.h +++ b/include/linux/leds.h @@ -256,7 +256,7 @@ struct led_classdev *__must_check devm_of_led_get(struct device *dev, * * Note that if software blinking is active, simply calling * led_cdev->brightness_set() will not stop the blinking, - * use led_classdev_brightness_set() instead. + * use led_set_brightness() instead. */ void led_blink_set(struct led_classdev *led_cdev, unsigned long *delay_on, unsigned long *delay_off); -- cgit v1.2.3 From 70493a63ba04f754f7a7dd53a4fcc82700181490 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Wed, 15 Mar 2023 11:39:03 -0700 Subject: blk-crypto: make blk_crypto_evict_key() return void blk_crypto_evict_key() is only called in contexts such as inode eviction where failure is not an option. So there is nothing the caller can do with errors except log them. (dm-table.c does "use" the error code, but only to pass on to upper layers, so it doesn't really count.) Just make blk_crypto_evict_key() return void and log errors itself. Cc: stable@vger.kernel.org Signed-off-by: Eric Biggers Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/20230315183907.53675-2-ebiggers@kernel.org Signed-off-by: Jens Axboe --- include/linux/blk-crypto.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk-crypto.h b/include/linux/blk-crypto.h index 1e3e5d0adf12..5e5822c18ee4 100644 --- a/include/linux/blk-crypto.h +++ b/include/linux/blk-crypto.h @@ -95,8 +95,8 @@ int blk_crypto_init_key(struct blk_crypto_key *blk_key, const u8 *raw_key, int blk_crypto_start_using_key(struct block_device *bdev, const struct blk_crypto_key *key); -int blk_crypto_evict_key(struct block_device *bdev, - const struct blk_crypto_key *key); +void blk_crypto_evict_key(struct block_device *bdev, + const struct blk_crypto_key *key); bool blk_crypto_config_supported_natively(struct block_device *bdev, const struct blk_crypto_config *cfg); -- cgit v1.2.3 From 053fdaa841bd1af9fe9c2c30bba81119059aac95 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Tue, 14 Mar 2023 15:13:08 -0500 Subject: nfc: mrvl: Move platform_data struct into driver There are no users of nfcmrvl platform_data struct outside of the driver and none will be added, so move it into the driver. Signed-off-by: Rob Herring Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- include/linux/platform_data/nfcmrvl.h | 48 ----------------------------------- 1 file changed, 48 deletions(-) delete mode 100644 include/linux/platform_data/nfcmrvl.h (limited to 'include/linux') diff --git a/include/linux/platform_data/nfcmrvl.h b/include/linux/platform_data/nfcmrvl.h deleted file mode 100644 index 9e75ac8d19be..000000000000 --- a/include/linux/platform_data/nfcmrvl.h +++ /dev/null @@ -1,48 +0,0 @@ -/* - * Copyright (C) 2015, Marvell International Ltd. - * - * This software file (the "File") is distributed by Marvell International - * Ltd. under the terms of the GNU General Public License Version 2, June 1991 - * (the "License"). You may use, redistribute and/or modify this File in - * accordance with the terms and conditions of the License, a copy of which - * is available on the worldwide web at - * http://www.gnu.org/licenses/old-licenses/gpl-2.0.txt. - * - * THE FILE IS DISTRIBUTED AS-IS, WITHOUT WARRANTY OF ANY KIND, AND THE - * IMPLIED WARRANTIES OF MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE - * ARE EXPRESSLY DISCLAIMED. The License provides additional details about - * this warranty disclaimer. - */ - -#ifndef _NFCMRVL_PTF_H_ -#define _NFCMRVL_PTF_H_ - -struct nfcmrvl_platform_data { - /* - * Generic - */ - - /* GPIO that is wired to RESET_N signal */ - int reset_n_io; - /* Tell if transport is muxed in HCI one */ - unsigned int hci_muxed; - - /* - * UART specific - */ - - /* Tell if UART needs flow control at init */ - unsigned int flow_control; - /* Tell if firmware supports break control for power management */ - unsigned int break_control; - - - /* - * I2C specific - */ - - unsigned int irq; - unsigned int irq_polarity; -}; - -#endif /* _NFCMRVL_PTF_H_ */ -- cgit v1.2.3 From 428e106ae1ad4e45d3fd6978a753db475d0d0ec9 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Sun, 12 Mar 2023 14:26:00 +0300 Subject: mm: Introduce untagged_addr_remote() untagged_addr() removes tags/metadata from the address and brings it to the canonical form. The helper is implemented on arm64 and sparc. Both of them do untagging based on global rules. However, Linear Address Masking (LAM) on x86 introduces per-process settings for untagging. As a result, untagged_addr() is now only suitable for untagging addresses for the current proccess. The new helper untagged_addr_remote() has to be used when the address targets remote process. It requires the mmap lock for target mm to be taken. Signed-off-by: Kirill A. Shutemov Signed-off-by: Dave Hansen Acked-by: Peter Zijlstra (Intel) Tested-by: Alexander Potapenko Link: https://lore.kernel.org/all/20230312112612.31869-6-kirill.shutemov%40linux.intel.com --- include/linux/mm.h | 11 ----------- include/linux/uaccess.h | 22 ++++++++++++++++++++++ 2 files changed, 22 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 1f79667824eb..289ae4caf878 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -96,17 +96,6 @@ extern int mmap_rnd_compat_bits __read_mostly; #include #include -/* - * Architectures that support memory tagging (assigning tags to memory regions, - * embedding these tags into addresses that point to these memory regions, and - * checking that the memory and the pointer tags match on memory accesses) - * redefine this macro to strip tags from pointers. - * It's defined as noop for architectures that don't support memory tagging. - */ -#ifndef untagged_addr -#define untagged_addr(addr) (addr) -#endif - #ifndef __pa_symbol #define __pa_symbol(x) __pa(RELOC_HIDE((unsigned long)(x), 0)) #endif diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index ab9728138ad6..3064314f4832 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -10,6 +10,28 @@ #include +/* + * Architectures that support memory tagging (assigning tags to memory regions, + * embedding these tags into addresses that point to these memory regions, and + * checking that the memory and the pointer tags match on memory accesses) + * redefine this macro to strip tags from pointers. + * + * Passing down mm_struct allows to define untagging rules on per-process + * basis. + * + * It's defined as noop for architectures that don't support memory tagging. + */ +#ifndef untagged_addr +#define untagged_addr(addr) (addr) +#endif + +#ifndef untagged_addr_remote +#define untagged_addr_remote(mm, addr) ({ \ + mmap_assert_locked(mm); \ + untagged_addr(addr); \ +}) +#endif + /* * Architectures should provide two primitives (raw_copy_{to,from}_user()) * and get rid of their private instances of copy_{to,from}_user() and -- cgit v1.2.3 From f7d304343b9d2456ffba23b99d2345408251ea45 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Sun, 12 Mar 2023 14:26:04 +0300 Subject: mm: Expose untagging mask in /proc/$PID/status Add a line in /proc/$PID/status to report untag_mask. It can be used to find out LAM status of the process from the outside. It is useful for debuggers. Signed-off-by: Kirill A. Shutemov Signed-off-by: Dave Hansen Acked-by: Catalin Marinas Acked-by: Peter Zijlstra (Intel) Tested-by: Alexander Potapenko Link: https://lore.kernel.org/all/20230312112612.31869-10-kirill.shutemov%40linux.intel.com --- include/linux/mmu_context.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmu_context.h b/include/linux/mmu_context.h index b9b970f7ab45..14b9c1fa05c4 100644 --- a/include/linux/mmu_context.h +++ b/include/linux/mmu_context.h @@ -28,4 +28,11 @@ static inline void leave_mm(int cpu) { } # define task_cpu_possible(cpu, p) cpumask_test_cpu((cpu), task_cpu_possible_mask(p)) #endif +#ifndef mm_untag_mask +static inline unsigned long mm_untag_mask(struct mm_struct *mm) +{ + return -1UL; +} +#endif + #endif -- cgit v1.2.3 From 400b9b93441cd4e2fe824a70140f3d5a2a9c802b Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Sun, 12 Mar 2023 14:26:05 +0300 Subject: iommu/sva: Replace pasid_valid() helper with mm_valid_pasid() Kernel has few users of pasid_valid() and all but one checks if the process has PASID allocated. The helper takes ioasid_t as the input. Replace the helper with mm_valid_pasid() that takes mm_struct as the argument. The only call that checks PASID that is not tied to mm_struct is open-codded now. This is preparatory patch. It helps avoid ifdeffery: no need to dereference mm->pasid in generic code to check if the process has PASID. Signed-off-by: Kirill A. Shutemov Signed-off-by: Dave Hansen Acked-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/all/20230312112612.31869-11-kirill.shutemov%40linux.intel.com --- include/linux/ioasid.h | 9 --------- include/linux/sched/mm.h | 8 +++++++- 2 files changed, 7 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ioasid.h b/include/linux/ioasid.h index af1c9d62e642..836ae09e92c2 100644 --- a/include/linux/ioasid.h +++ b/include/linux/ioasid.h @@ -40,10 +40,6 @@ void *ioasid_find(struct ioasid_set *set, ioasid_t ioasid, int ioasid_register_allocator(struct ioasid_allocator_ops *allocator); void ioasid_unregister_allocator(struct ioasid_allocator_ops *allocator); int ioasid_set_data(ioasid_t ioasid, void *data); -static inline bool pasid_valid(ioasid_t ioasid) -{ - return ioasid != INVALID_IOASID; -} #else /* !CONFIG_IOASID */ static inline ioasid_t ioasid_alloc(struct ioasid_set *set, ioasid_t min, @@ -74,10 +70,5 @@ static inline int ioasid_set_data(ioasid_t ioasid, void *data) return -ENOTSUPP; } -static inline bool pasid_valid(ioasid_t ioasid) -{ - return false; -} - #endif /* CONFIG_IOASID */ #endif /* __LINUX_IOASID_H */ diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index 2a243616f222..b69fe7e8c0ac 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -457,6 +457,11 @@ static inline void mm_pasid_init(struct mm_struct *mm) mm->pasid = INVALID_IOASID; } +static inline bool mm_valid_pasid(struct mm_struct *mm) +{ + return mm->pasid != INVALID_IOASID; +} + /* Associate a PASID with an mm_struct: */ static inline void mm_pasid_set(struct mm_struct *mm, u32 pasid) { @@ -465,13 +470,14 @@ static inline void mm_pasid_set(struct mm_struct *mm, u32 pasid) static inline void mm_pasid_drop(struct mm_struct *mm) { - if (pasid_valid(mm->pasid)) { + if (mm_valid_pasid(mm)) { ioasid_free(mm->pasid); mm->pasid = INVALID_IOASID; } } #else static inline void mm_pasid_init(struct mm_struct *mm) {} +static inline bool mm_valid_pasid(struct mm_struct *mm) { return false; } static inline void mm_pasid_set(struct mm_struct *mm, u32 pasid) {} static inline void mm_pasid_drop(struct mm_struct *mm) {} #endif -- cgit v1.2.3 From 23e5d9ec2bab53c4e5fbac675304e699726c1ac5 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Sun, 12 Mar 2023 14:26:06 +0300 Subject: x86/mm/iommu/sva: Make LAM and SVA mutually exclusive IOMMU and SVA-capable devices know nothing about LAM and only expect canonical addresses. An attempt to pass down tagged pointer will lead to address translation failure. By default do not allow to enable both LAM and use SVA in the same process. The new ARCH_FORCE_TAGGED_SVA arch_prctl() overrides the limitation. By using the arch_prctl() userspace takes responsibility to never pass tagged address to the device. Signed-off-by: Kirill A. Shutemov Signed-off-by: Dave Hansen Reviewed-by: Ashok Raj Reviewed-by: Jacob Pan Acked-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/all/20230312112612.31869-12-kirill.shutemov%40linux.intel.com --- include/linux/mmu_context.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmu_context.h b/include/linux/mmu_context.h index 14b9c1fa05c4..f2b7a3f04099 100644 --- a/include/linux/mmu_context.h +++ b/include/linux/mmu_context.h @@ -35,4 +35,11 @@ static inline unsigned long mm_untag_mask(struct mm_struct *mm) } #endif +#ifndef arch_pgtable_dma_compat +static inline bool arch_pgtable_dma_compat(struct mm_struct *mm) +{ + return true; +} +#endif + #endif -- cgit v1.2.3 From ae7d45fb7ca75e94b478e2404709ba3024774334 Mon Sep 17 00:00:00 2001 From: Mario Limonciello Date: Fri, 10 Mar 2023 15:19:45 -0600 Subject: crypto: ccp - Add a header for multiple drivers to use `__psp_pa` The TEE subdriver for CCP, the amdtee driver and the i2c-designware-amdpsp drivers all include `psp-sev.h` even though they don't use SEV functionality. Move the definition of `__psp_pa` into a common header to be included by all of these drivers. Reviewed-by: Jan Dabros Acked-by: Jarkko Nikula # For the drivers/i2c/busses/i2c-designware-amdpsp.c Acked-by: Sumit Garg # For TEE subsystem bits Acked-by: Tom Lendacky Acked-by: Sean Christopherson # KVM Signed-off-by: Mario Limonciello Signed-off-by: Herbert Xu --- include/linux/psp-sev.h | 8 -------- include/linux/psp.h | 14 ++++++++++++++ 2 files changed, 14 insertions(+), 8 deletions(-) create mode 100644 include/linux/psp.h (limited to 'include/linux') diff --git a/include/linux/psp-sev.h b/include/linux/psp-sev.h index 1595088c428b..7fd17e82bab4 100644 --- a/include/linux/psp-sev.h +++ b/include/linux/psp-sev.h @@ -14,14 +14,6 @@ #include -#ifdef CONFIG_X86 -#include - -#define __psp_pa(x) __sme_pa(x) -#else -#define __psp_pa(x) __pa(x) -#endif - #define SEV_FW_BLOB_MAX_SIZE 0x4000 /* 16KB */ /** diff --git a/include/linux/psp.h b/include/linux/psp.h new file mode 100644 index 000000000000..202162487ec3 --- /dev/null +++ b/include/linux/psp.h @@ -0,0 +1,14 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#ifndef __PSP_H +#define __PSP_H + +#ifdef CONFIG_X86 +#include + +#define __psp_pa(x) __sme_pa(x) +#else +#define __psp_pa(x) __pa(x) +#endif + +#endif /* __PSP_H */ -- cgit v1.2.3 From 1c5c1daf04d13916867ef68c6ba7ae4f5e73801f Mon Sep 17 00:00:00 2001 From: Mario Limonciello Date: Fri, 10 Mar 2023 15:19:46 -0600 Subject: crypto: ccp - Move some PSP mailbox bit definitions into common header Some of the bits and fields used for mailboxes communicating with the PSP are common across all mailbox implementations (SEV, TEE, etc). Move these bits into the common `linux/psp.h` so they don't need to be re-defined for each implementation. Acked-by: Rijo Thomas Acked-by: Tom Lendacky Signed-off-by: Mario Limonciello Acked-by: Jarkko Nikula Signed-off-by: Herbert Xu --- include/linux/psp.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/psp.h b/include/linux/psp.h index 202162487ec3..d3424790a70e 100644 --- a/include/linux/psp.h +++ b/include/linux/psp.h @@ -11,4 +11,16 @@ #define __psp_pa(x) __pa(x) #endif +/* + * Fields and bits used by most PSP mailboxes + * + * Note: Some mailboxes (such as SEV) have extra bits or different meanings + * and should include an appropriate local definition in their source file. + */ +#define PSP_CMDRESP_STS GENMASK(15, 0) +#define PSP_CMDRESP_CMD GENMASK(23, 16) +#define PSP_CMDRESP_RESERVED GENMASK(29, 24) +#define PSP_CMDRESP_RECOVERY BIT(30) +#define PSP_CMDRESP_RESP BIT(31) + #endif /* __PSP_H */ -- cgit v1.2.3 From 7ccc4f4e2e50e4a29f9ee8f5c9e187f8491bb6e7 Mon Sep 17 00:00:00 2001 From: Mario Limonciello Date: Fri, 10 Mar 2023 15:19:47 -0600 Subject: crypto: ccp - Add support for an interface for platform features Some platforms with a PSP support an interface for features that interact directly with the PSP instead of through a SEV or TEE environment. Initialize this interface so that other drivers can consume it. These drivers may either be subdrivers for the ccp module or external modules. For external modules, export a symbol for them to utilize. Acked-by: Tom Lendacky Signed-off-by: Mario Limonciello Signed-off-by: Herbert Xu --- include/linux/psp-platform-access.h | 49 +++++++++++++++++++++++++++++++++++++ 1 file changed, 49 insertions(+) create mode 100644 include/linux/psp-platform-access.h (limited to 'include/linux') diff --git a/include/linux/psp-platform-access.h b/include/linux/psp-platform-access.h new file mode 100644 index 000000000000..977df5cfd494 --- /dev/null +++ b/include/linux/psp-platform-access.h @@ -0,0 +1,49 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#ifndef __PSP_PLATFORM_ACCESS_H +#define __PSP_PLATFORM_ACCESS_H + +#include + +enum psp_platform_access_msg { + PSP_CMD_NONE = 0x0, +}; + +struct psp_req_buffer_hdr { + u32 payload_size; + u32 status; +} __packed; + +struct psp_request { + struct psp_req_buffer_hdr header; + void *buf; +} __packed; + +/** + * psp_send_platform_access_msg() - Send a message to control platform features + * + * This function is intended to be used by drivers outside of ccp to communicate + * with the platform. + * + * Returns: + * 0: success + * -%EBUSY: mailbox in recovery or in use + * -%ENODEV: driver not bound with PSP device + * -%ETIMEDOUT: request timed out + * -%EIO: unknown error (see kernel log) + */ +int psp_send_platform_access_msg(enum psp_platform_access_msg, struct psp_request *req); + +/** + * psp_check_platform_access_status() - Checks whether platform features is ready + * + * This function is intended to be used by drivers outside of ccp to determine + * if platform features has initialized. + * + * Returns: + * 0 platform features is ready + * -%ENODEV platform features is not ready or present + */ +int psp_check_platform_access_status(void); + +#endif /* __PSP_PLATFORM_ACCESS_H */ -- cgit v1.2.3 From d5812571f594b03438d0d7acd0dc044f73c1719e Mon Sep 17 00:00:00 2001 From: Mario Limonciello Date: Fri, 10 Mar 2023 15:19:50 -0600 Subject: crypto: ccp - Add support for ringing a platform doorbell Some platforms support using a doorbell to communicate. Export this feature for other drivers to utilize as well. Link: https://lore.kernel.org/linux-i2c/20220916131854.687371-3-jsd@semihalf.com/ Suggested-by: Jan Dabros Signed-off-by: Mario Limonciello Signed-off-by: Herbert Xu --- include/linux/psp-platform-access.h | 15 +++++++++++++++ include/linux/psp.h | 3 +++ 2 files changed, 18 insertions(+) (limited to 'include/linux') diff --git a/include/linux/psp-platform-access.h b/include/linux/psp-platform-access.h index 977df5cfd494..89df4549fada 100644 --- a/include/linux/psp-platform-access.h +++ b/include/linux/psp-platform-access.h @@ -34,6 +34,21 @@ struct psp_request { */ int psp_send_platform_access_msg(enum psp_platform_access_msg, struct psp_request *req); +/** + * psp_ring_platform_doorbell() - Ring platform doorbell + * + * This function is intended to be used by drivers outside of ccp to ring the + * platform doorbell with a message. + * + * Returns: + * 0: success + * -%EBUSY: mailbox in recovery or in use + * -%ENODEV: driver not bound with PSP device + * -%ETIMEDOUT: request timed out + * -%EIO: unknown error (see kernel log) + */ +int psp_ring_platform_doorbell(int msg); + /** * psp_check_platform_access_status() - Checks whether platform features is ready * diff --git a/include/linux/psp.h b/include/linux/psp.h index d3424790a70e..92e60aeef21e 100644 --- a/include/linux/psp.h +++ b/include/linux/psp.h @@ -23,4 +23,7 @@ #define PSP_CMDRESP_RECOVERY BIT(30) #define PSP_CMDRESP_RESP BIT(31) +#define PSP_DRBL_MSG PSP_CMDRESP_CMD +#define PSP_DRBL_RING BIT(0) + #endif /* __PSP_H */ -- cgit v1.2.3 From 8c44fa12c8fa09c6c12f0dc25129a6d13ee0a1ea Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Wed, 15 Mar 2023 15:11:45 +0200 Subject: net: Add MDB net device operations Add MDB net device operations that will be invoked by rtnetlink code in response to received RTM_{NEW,DEL,GET}MDB messages. Subsequent patches will implement these operations in the bridge and VXLAN drivers. Signed-off-by: Ido Schimmel Reviewed-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/linux/netdevice.h | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index ee483071cf59..23b0d7eaaadd 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1307,6 +1307,17 @@ struct netdev_net_notifier { * Used to add FDB entries to dump requests. Implementers should add * entries to skb and update idx with the number of entries. * + * int (*ndo_mdb_add)(struct net_device *dev, struct nlattr *tb[], + * u16 nlmsg_flags, struct netlink_ext_ack *extack); + * Adds an MDB entry to dev. + * int (*ndo_mdb_del)(struct net_device *dev, struct nlattr *tb[], + * struct netlink_ext_ack *extack); + * Deletes the MDB entry from dev. + * int (*ndo_mdb_dump)(struct net_device *dev, struct sk_buff *skb, + * struct netlink_callback *cb); + * Dumps MDB entries from dev. The first argument (marker) in the netlink + * callback is used by core rtnetlink code. + * * int (*ndo_bridge_setlink)(struct net_device *dev, struct nlmsghdr *nlh, * u16 flags, struct netlink_ext_ack *extack) * int (*ndo_bridge_getlink)(struct sk_buff *skb, u32 pid, u32 seq, @@ -1569,6 +1580,16 @@ struct net_device_ops { const unsigned char *addr, u16 vid, u32 portid, u32 seq, struct netlink_ext_ack *extack); + int (*ndo_mdb_add)(struct net_device *dev, + struct nlattr *tb[], + u16 nlmsg_flags, + struct netlink_ext_ack *extack); + int (*ndo_mdb_del)(struct net_device *dev, + struct nlattr *tb[], + struct netlink_ext_ack *extack); + int (*ndo_mdb_dump)(struct net_device *dev, + struct sk_buff *skb, + struct netlink_callback *cb); int (*ndo_bridge_setlink)(struct net_device *dev, struct nlmsghdr *nlh, u16 flags, -- cgit v1.2.3 From 33e972bdf0b0aa208b67164c64eef3c307e4b303 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 16 Mar 2023 15:31:56 +0000 Subject: ipv4: constify ip_mc_sf_allow() socket argument This clarifies ip_mc_sf_allow() intent. Signed-off-by: Eric Dumazet Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- include/linux/igmp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/igmp.h b/include/linux/igmp.h index b19d3284551f..ebf4349a53af 100644 --- a/include/linux/igmp.h +++ b/include/linux/igmp.h @@ -122,7 +122,7 @@ extern int ip_mc_msfget(struct sock *sk, struct ip_msfilter *msf, sockptr_t optval, sockptr_t optlen); extern int ip_mc_gsfget(struct sock *sk, struct group_filter *gsf, sockptr_t optval, size_t offset); -extern int ip_mc_sf_allow(struct sock *sk, __be32 local, __be32 rmt, +extern int ip_mc_sf_allow(const struct sock *sk, __be32 local, __be32 rmt, int dif, int sdif); extern void ip_mc_init_dev(struct in_device *); extern void ip_mc_destroy_dev(struct in_device *); -- cgit v1.2.3 From bd5314f8dd2d41330eecb60f0490c3fcfe1fc99d Mon Sep 17 00:00:00 2001 From: Viktor Malik Date: Fri, 17 Mar 2023 10:56:01 +0100 Subject: kallsyms, bpf: Move find_kallsyms_symbol_value out of internal header Moving find_kallsyms_symbol_value from kernel/module/internal.h to include/linux/module.h. The reason is that internal.h is not prepared to be included when CONFIG_MODULES=n. find_kallsyms_symbol_value is used by kernel/bpf/verifier.c and including internal.h from it (without modules) leads into a compilation error: In file included from ../include/linux/container_of.h:5, from ../include/linux/list.h:5, from ../include/linux/timer.h:5, from ../include/linux/workqueue.h:9, from ../include/linux/bpf.h:10, from ../include/linux/bpf-cgroup.h:5, from ../kernel/bpf/verifier.c:7: ../kernel/bpf/../module/internal.h: In function 'mod_find': ../include/linux/container_of.h:20:54: error: invalid use of undefined type 'struct module' 20 | static_assert(__same_type(*(ptr), ((type *)0)->member) || \ | ^~ [...] This patch fixes the above error. Fixes: 31bf1dbccfb0 ("bpf: Fix attaching fentry/fexit/fmod_ret/lsm to modules") Reported-by: kernel test robot Signed-off-by: Viktor Malik Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/oe-kbuild-all/202303161404.OrmfCy09-lkp@intel.com/ Link: https://lore.kernel.org/bpf/20230317095601.386738-1-vmalik@redhat.com --- include/linux/module.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/module.h b/include/linux/module.h index 4435ad9439ab..41cfd3be57e5 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -616,6 +616,8 @@ int module_get_kallsym(unsigned int symnum, unsigned long *value, char *type, /* Look for this name: can be of form module:name. */ unsigned long module_kallsyms_lookup_name(const char *name); +unsigned long find_kallsyms_symbol_value(struct module *mod, const char *name); + extern void __noreturn __module_put_and_kthread_exit(struct module *mod, long code); #define module_put_and_kthread_exit(code) __module_put_and_kthread_exit(THIS_MODULE, code) @@ -796,6 +798,12 @@ static inline unsigned long module_kallsyms_lookup_name(const char *name) return 0; } +static inline unsigned long find_kallsyms_symbol_value(struct module *mod, + const char *name) +{ + return 0; +} + static inline int register_module_notifier(struct notifier_block *nb) { /* no events will happen anyway, so this can always succeed */ -- cgit v1.2.3 From 6229ad9913ac794233fdb3ed20f1e899add0af6b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= Date: Thu, 9 Mar 2023 10:09:18 +0200 Subject: serial: Remove extern from func prototypes in headers MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Remove unnecessary externs from function prototypes in serial_8250.h and serial_core.h. Suggested-by: Jiri Slaby Signed-off-by: Ilpo Järvinen Link: https://lore.kernel.org/r/20230309080923.11778-4-ilpo.jarvinen@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- include/linux/serial_8250.h | 41 ++++++++++++++++++----------------------- include/linux/serial_core.h | 13 ++++++------- 2 files changed, 24 insertions(+), 30 deletions(-) (limited to 'include/linux') diff --git a/include/linux/serial_8250.h b/include/linux/serial_8250.h index 741ed4807a9c..6f78f302d272 100644 --- a/include/linux/serial_8250.h +++ b/include/linux/serial_8250.h @@ -151,26 +151,22 @@ void serial8250_unregister_port(int line); void serial8250_suspend_port(int line); void serial8250_resume_port(int line); -extern int early_serial_setup(struct uart_port *port); - -extern int early_serial8250_setup(struct earlycon_device *device, - const char *options); -extern void serial8250_update_uartclk(struct uart_port *port, - unsigned int uartclk); -extern void serial8250_do_set_termios(struct uart_port *port, - struct ktermios *termios, const struct ktermios *old); -extern void serial8250_do_set_ldisc(struct uart_port *port, - struct ktermios *termios); -extern unsigned int serial8250_do_get_mctrl(struct uart_port *port); -extern int serial8250_do_startup(struct uart_port *port); -extern void serial8250_do_shutdown(struct uart_port *port); -extern void serial8250_do_pm(struct uart_port *port, unsigned int state, - unsigned int oldstate); -extern void serial8250_do_set_mctrl(struct uart_port *port, unsigned int mctrl); -extern void serial8250_do_set_divisor(struct uart_port *port, unsigned int baud, - unsigned int quot, - unsigned int quot_frac); -extern int fsl8250_handle_irq(struct uart_port *port); +int early_serial_setup(struct uart_port *port); +int early_serial8250_setup(struct earlycon_device *device, const char *options); + +void serial8250_update_uartclk(struct uart_port *port, unsigned int uartclk); +void serial8250_do_set_termios(struct uart_port *port, struct ktermios *termios, + const struct ktermios *old); +void serial8250_do_set_ldisc(struct uart_port *port, struct ktermios *termios); +unsigned int serial8250_do_get_mctrl(struct uart_port *port); +int serial8250_do_startup(struct uart_port *port); +void serial8250_do_shutdown(struct uart_port *port); +void serial8250_do_pm(struct uart_port *port, unsigned int state, + unsigned int oldstate); +void serial8250_do_set_mctrl(struct uart_port *port, unsigned int mctrl); +void serial8250_do_set_divisor(struct uart_port *port, unsigned int baud, + unsigned int quot, unsigned int quot_frac); +int fsl8250_handle_irq(struct uart_port *port); int serial8250_handle_irq(struct uart_port *port, unsigned int iir); u16 serial8250_rx_chars(struct uart_8250_port *up, u16 lsr); void serial8250_read_char(struct uart_8250_port *up, u16 lsr); @@ -183,9 +179,8 @@ void serial8250_console_write(struct uart_8250_port *up, const char *s, int serial8250_console_setup(struct uart_port *port, char *options, bool probe); int serial8250_console_exit(struct uart_port *port); -extern void serial8250_set_isa_configurator(void (*v) - (int port, struct uart_port *up, - u32 *capabilities)); +void serial8250_set_isa_configurator(void (*v)(int port, struct uart_port *up, + u32 *capabilities)); #ifdef CONFIG_SERIAL_8250_RT288X unsigned int au_serial_in(struct uart_port *p, int offset); diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index 9e3e5e0d11b2..05d18a145b3a 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -812,9 +812,8 @@ extern const struct earlycon_id __earlycon_table_end[]; #define EARLYCON_DECLARE(_name, fn) OF_EARLYCON_DECLARE(_name, "", fn) -extern int of_setup_earlycon(const struct earlycon_id *match, - unsigned long node, - const char *options); +int of_setup_earlycon(const struct earlycon_id *match, unsigned long node, + const char *options); #ifdef CONFIG_SERIAL_EARLYCON extern bool earlycon_acpi_spcr_enable __initdata; @@ -897,11 +896,11 @@ static inline bool uart_softcts_mode(struct uart_port *uport) * The following are helper functions for the low level drivers. */ -extern void uart_handle_dcd_change(struct uart_port *uport, bool active); -extern void uart_handle_cts_change(struct uart_port *uport, bool active); +void uart_handle_dcd_change(struct uart_port *uport, bool active); +void uart_handle_cts_change(struct uart_port *uport, bool active); -extern void uart_insert_char(struct uart_port *port, unsigned int status, - unsigned int overrun, unsigned int ch, unsigned int flag); +void uart_insert_char(struct uart_port *port, unsigned int status, + unsigned int overrun, unsigned int ch, unsigned int flag); void uart_xchar_out(struct uart_port *uport, int offset); -- cgit v1.2.3 From b5def43a7b3e7e68d6b49a23166f8b886a26bb54 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= Date: Thu, 9 Mar 2023 10:09:21 +0200 Subject: serial: Make hw_stopped bool MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Convert hw_stopped in uart_port to bool because its more appropriate type for how it is used. Also convert the local variable in uart_change_line_settings() caching old hw_stopped to bool. Signed-off-by: Ilpo Järvinen Link: https://lore.kernel.org/r/20230309080923.11778-7-ilpo.jarvinen@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- include/linux/serial_core.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index 05d18a145b3a..66ecec15a1bf 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -553,7 +553,7 @@ struct uart_port { #define UPSTAT_AUTOXOFF ((__force upstat_t) (1 << 4)) #define UPSTAT_SYNC_FIFO ((__force upstat_t) (1 << 5)) - int hw_stopped; /* sw-assisted CTS flow state */ + bool hw_stopped; /* sw-assisted CTS flow state */ unsigned int mctrl; /* current modem ctrl settings */ unsigned int frame_time; /* frame timing in ns */ unsigned int type; /* port type */ -- cgit v1.2.3 From 035173c91c6b53144295a5b546c6bad3f40fb8a9 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= Date: Thu, 9 Mar 2023 10:20:35 +0200 Subject: tty: Convert hw_stopped in tty_struct to bool MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit hw_stopped in tty_struct is used like bool, convert the variable type to bool. Signed-off-by: Ilpo Järvinen Acked-by: Ulf Hansson # For MMC Link: https://lore.kernel.org/r/20230309082035.14880-9-ilpo.jarvinen@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index 093935e97f42..60871a9d3212 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -227,7 +227,7 @@ struct tty_struct { unsigned long unused[0]; } __aligned(sizeof(unsigned long)) ctrl; - int hw_stopped; + bool hw_stopped; unsigned int receive_room; int flow_change; -- cgit v1.2.3 From 410e7088e971ad656170fe9768b072b267a95310 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Mon, 13 Mar 2023 13:31:00 +0200 Subject: devres: Pass unique name of the resource to devm_add_action_or_reset() All the same as it's done in the commit e32c80bbd2f9 ("devres: Pass unique name of the resource to devm_add_action()") applies to the devm_add_action_or_reset(), which this change makes real. This helps with debug resource management. Reported-and-tested-by: Mirsad Goran Todorovac Signed-off-by: Andy Shevchenko Link: https://lore.kernel.org/r/20230313113100.59643-1-andriy.shevchenko@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 0f128520f6e5..12dc08aa5c0f 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -250,17 +250,19 @@ int __devm_add_action(struct device *dev, void (*action)(void *), void *data, co #define devm_add_action(release, action, data) \ __devm_add_action(release, action, data, #action) -static inline int devm_add_action_or_reset(struct device *dev, - void (*action)(void *), void *data) +static inline int __devm_add_action_or_reset(struct device *dev, void (*action)(void *), + void *data, const char *name) { int ret; - ret = devm_add_action(dev, action, data); + ret = __devm_add_action(dev, action, data, name); if (ret) action(data); return ret; } +#define devm_add_action_or_reset(release, action, data) \ + __devm_add_action_or_reset(release, action, data, #action) /** * devm_alloc_percpu - Resource-managed alloc_percpu -- cgit v1.2.3 From 4a46ac9d64030d9f6f18baaf115a3558880c1ae2 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 13 Mar 2023 19:18:32 +0100 Subject: driver core: class: specify the module owner in __class_register() There's no need to manually have to set the module owner of a class, the compiler should do it automatically for you, so add a module * to the __class_register() function and allow it to set the module owner automatically. This will let us move the module pointer out of struct class eventually, as it should not be embedded in there if we wish for it to be a read-only structure eventually. And, funny story, this module pointer isn't even being used for anything, so while we will keep it around for now, it's not like it even matters. Cc: "Rafael J. Wysocki" Link: https://lore.kernel.org/r/20230313181843.1207845-1-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- include/linux/device/class.h | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/device/class.h b/include/linux/device/class.h index 42cc3fb44a84..d1ba4ee235dc 100644 --- a/include/linux/device/class.h +++ b/include/linux/device/class.h @@ -85,15 +85,16 @@ struct class_dev_iter { extern struct kobject *sysfs_dev_block_kobj; extern struct kobject *sysfs_dev_char_kobj; extern int __must_check __class_register(struct class *class, + struct module *owner, struct lock_class_key *key); extern void class_unregister(struct class *class); /* This is a #define to keep the compiler from merging different * instances of the __key variable */ -#define class_register(class) \ -({ \ - static struct lock_class_key __key; \ - __class_register(class, &__key); \ +#define class_register(class) \ +({ \ + static struct lock_class_key __key; \ + __class_register(class, THIS_MODULE, &__key); \ }) struct class_compat; -- cgit v1.2.3 From 6e30a66433afee90e902ced95d7136e8f7edcc7e Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 13 Mar 2023 19:18:34 +0100 Subject: driver core: class: remove struct module owner out of struct class The module owner field for a struct class was never actually used, so remove it as it is not doing anything at all. Cc: "Rafael J. Wysocki" Link: https://lore.kernel.org/r/20230313181843.1207845-3-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- include/linux/device/class.h | 18 +++++++----------- 1 file changed, 7 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/device/class.h b/include/linux/device/class.h index d1ba4ee235dc..bf736f14f0c1 100644 --- a/include/linux/device/class.h +++ b/include/linux/device/class.h @@ -25,7 +25,6 @@ struct fwnode_handle; /** * struct class - device classes * @name: Name of the class. - * @owner: The module owner. * @class_groups: Default attributes of this class. * @dev_groups: Default attributes of the devices that belong to the class. * @dev_kobj: The kobject that represents this class and links it into the hierarchy. @@ -53,7 +52,6 @@ struct fwnode_handle; */ struct class { const char *name; - struct module *owner; const struct attribute_group **class_groups; const struct attribute_group **dev_groups; @@ -85,16 +83,15 @@ struct class_dev_iter { extern struct kobject *sysfs_dev_block_kobj; extern struct kobject *sysfs_dev_char_kobj; extern int __must_check __class_register(struct class *class, - struct module *owner, struct lock_class_key *key); extern void class_unregister(struct class *class); /* This is a #define to keep the compiler from merging different * instances of the __key variable */ -#define class_register(class) \ -({ \ - static struct lock_class_key __key; \ - __class_register(class, THIS_MODULE, &__key); \ +#define class_register(class) \ +({ \ + static struct lock_class_key __key; \ + __class_register(class, &__key); \ }) struct class_compat; @@ -250,8 +247,7 @@ struct class_interface { extern int __must_check class_interface_register(struct class_interface *); extern void class_interface_unregister(struct class_interface *); -extern struct class * __must_check __class_create(struct module *owner, - const char *name, +extern struct class * __must_check __class_create(const char *name, struct lock_class_key *key); extern void class_destroy(struct class *cls); @@ -260,7 +256,7 @@ extern void class_destroy(struct class *cls); /** * class_create - create a struct class structure - * @owner: pointer to the module that is to "own" this struct class + * @owner: dummy pointer, does nothing, will be removed soon. * @name: pointer to a string for the name of this class. * * This is used to create a struct class pointer that can then be used @@ -274,7 +270,7 @@ extern void class_destroy(struct class *cls); #define class_create(owner, name) \ ({ \ static struct lock_class_key __key; \ - __class_create(owner, name, &__key); \ + __class_create(name, &__key); \ }) -- cgit v1.2.3 From 1aaba11da9aa7d7d6b52a74d45b31cac118295a1 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 13 Mar 2023 19:18:35 +0100 Subject: driver core: class: remove module * from class_create() The module pointer in class_create() never actually did anything, and it shouldn't have been requred to be set as a parameter even if it did something. So just remove it and fix up all callers of the function in the kernel tree at the same time. Cc: "Rafael J. Wysocki" Acked-by: Benjamin Tissoires Link: https://lore.kernel.org/r/20230313181843.1207845-4-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- include/linux/device/class.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/device/class.h b/include/linux/device/class.h index bf736f14f0c1..cda598fc5fa0 100644 --- a/include/linux/device/class.h +++ b/include/linux/device/class.h @@ -256,7 +256,6 @@ extern void class_destroy(struct class *cls); /** * class_create - create a struct class structure - * @owner: dummy pointer, does nothing, will be removed soon. * @name: pointer to a string for the name of this class. * * This is used to create a struct class pointer that can then be used @@ -267,7 +266,7 @@ extern void class_destroy(struct class *cls); * Note, the pointer created here is to be destroyed when finished by * making a call to class_destroy(). */ -#define class_create(owner, name) \ +#define class_create(name) \ ({ \ static struct lock_class_key __key; \ __class_create(name, &__key); \ -- cgit v1.2.3 From a2fd6e42e4fb661e183977072022b7dd8dd65d90 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 13 Mar 2023 19:18:36 +0100 Subject: driver core: class: make class_dev_iter_init() options const class_dev_iter_init() does not modify the struct class or the struct device passed into it, so mark them as const * to enforce that. Cc: "Rafael J. Wysocki" Link: https://lore.kernel.org/r/20230313181843.1207845-5-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- include/linux/device/class.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/device/class.h b/include/linux/device/class.h index cda598fc5fa0..1f5cfae8db88 100644 --- a/include/linux/device/class.h +++ b/include/linux/device/class.h @@ -103,8 +103,8 @@ void class_compat_remove_link(struct class_compat *cls, struct device *dev, struct device *device_link); extern void class_dev_iter_init(struct class_dev_iter *iter, - struct class *class, - struct device *start, + const struct class *class, + const struct device *start, const struct device_type *type); extern struct device *class_dev_iter_next(struct class_dev_iter *iter); extern void class_dev_iter_exit(struct class_dev_iter *iter); -- cgit v1.2.3 From 69df024ebbf8b1d4d8f0808b5700688fed9e45e9 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 13 Mar 2023 19:18:37 +0100 Subject: driver core: class: make class_for_each_device() options const class_for_each_device() does not modify the struct class or the struct device passed into it, so mark them as const * to enforce that. Cc: "Rafael J. Wysocki" Link: https://lore.kernel.org/r/20230313181843.1207845-6-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- include/linux/device/class.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/device/class.h b/include/linux/device/class.h index 1f5cfae8db88..fdbcd487e508 100644 --- a/include/linux/device/class.h +++ b/include/linux/device/class.h @@ -109,7 +109,7 @@ extern void class_dev_iter_init(struct class_dev_iter *iter, extern struct device *class_dev_iter_next(struct class_dev_iter *iter); extern void class_dev_iter_exit(struct class_dev_iter *iter); -extern int class_for_each_device(struct class *class, struct device *start, +extern int class_for_each_device(const struct class *class, const struct device *start, void *data, int (*fn)(struct device *dev, void *data)); extern struct device *class_find_device(struct class *class, -- cgit v1.2.3 From cf41015ea8d3f2ae451d9b7e39ef42569caeb875 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 13 Mar 2023 19:18:38 +0100 Subject: driver core: class: make class_find_device*() options const The class_find_device*() functions do not modify the struct class or the struct device passed into it, so mark them as const * to enforce that. Cc: "Rafael J. Wysocki" Link: https://lore.kernel.org/r/20230313181843.1207845-7-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- include/linux/device/class.h | 25 ++++++++++++------------- 1 file changed, 12 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/device/class.h b/include/linux/device/class.h index fdbcd487e508..dfa8958105e7 100644 --- a/include/linux/device/class.h +++ b/include/linux/device/class.h @@ -112,8 +112,8 @@ extern void class_dev_iter_exit(struct class_dev_iter *iter); extern int class_for_each_device(const struct class *class, const struct device *start, void *data, int (*fn)(struct device *dev, void *data)); -extern struct device *class_find_device(struct class *class, - struct device *start, const void *data, +extern struct device *class_find_device(const struct class *class, + const struct device *start, const void *data, int (*match)(struct device *, const void *)); /** @@ -122,7 +122,7 @@ extern struct device *class_find_device(struct class *class, * @class: class type * @name: name of the device to match */ -static inline struct device *class_find_device_by_name(struct class *class, +static inline struct device *class_find_device_by_name(const struct class *class, const char *name) { return class_find_device(class, NULL, name, device_match_name); @@ -134,8 +134,8 @@ static inline struct device *class_find_device_by_name(struct class *class, * @class: class type * @np: of_node of the device to match. */ -static inline struct device * -class_find_device_by_of_node(struct class *class, const struct device_node *np) +static inline struct device *class_find_device_by_of_node(const struct class *class, + const struct device_node *np) { return class_find_device(class, NULL, np, device_match_of_node); } @@ -146,9 +146,8 @@ class_find_device_by_of_node(struct class *class, const struct device_node *np) * @class: class type * @fwnode: fwnode of the device to match. */ -static inline struct device * -class_find_device_by_fwnode(struct class *class, - const struct fwnode_handle *fwnode) +static inline struct device *class_find_device_by_fwnode(const struct class *class, + const struct fwnode_handle *fwnode) { return class_find_device(class, NULL, fwnode, device_match_fwnode); } @@ -159,7 +158,7 @@ class_find_device_by_fwnode(struct class *class, * @class: class type * @devt: device type of the device to match. */ -static inline struct device *class_find_device_by_devt(struct class *class, +static inline struct device *class_find_device_by_devt(const struct class *class, dev_t devt) { return class_find_device(class, NULL, &devt, device_match_devt); @@ -173,14 +172,14 @@ struct acpi_device; * @class: class type * @adev: ACPI_COMPANION device to match. */ -static inline struct device * -class_find_device_by_acpi_dev(struct class *class, const struct acpi_device *adev) +static inline struct device *class_find_device_by_acpi_dev(const struct class *class, + const struct acpi_device *adev) { return class_find_device(class, NULL, adev, device_match_acpi_dev); } #else -static inline struct device * -class_find_device_by_acpi_dev(struct class *class, const void *adev) +static inline struct device *class_find_device_by_acpi_dev(const struct class *class, + const void *adev) { return NULL; } -- cgit v1.2.3 From 80842a92907bd68454591f9c7a73778f130ac38f Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 13 Mar 2023 19:18:39 +0100 Subject: driver core: class: make class_create/remove_file*() options const The class_create_file*() and class_remove_file*() functions do not modify the struct class at all, so mark them as const * to enforce that. Cc: "Rafael J. Wysocki" Link: https://lore.kernel.org/r/20230313181843.1207845-8-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- include/linux/device/class.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/device/class.h b/include/linux/device/class.h index dfa8958105e7..75c1451fcc63 100644 --- a/include/linux/device/class.h +++ b/include/linux/device/class.h @@ -200,20 +200,20 @@ struct class_attribute { #define CLASS_ATTR_WO(_name) \ struct class_attribute class_attr_##_name = __ATTR_WO(_name) -extern int __must_check class_create_file_ns(struct class *class, +extern int __must_check class_create_file_ns(const struct class *class, const struct class_attribute *attr, const void *ns); -extern void class_remove_file_ns(struct class *class, +extern void class_remove_file_ns(const struct class *class, const struct class_attribute *attr, const void *ns); -static inline int __must_check class_create_file(struct class *class, - const struct class_attribute *attr) +static inline int __must_check class_create_file(const struct class *class, + const struct class_attribute *attr) { return class_create_file_ns(class, attr, NULL); } -static inline void class_remove_file(struct class *class, +static inline void class_remove_file(const struct class *class, const struct class_attribute *attr) { return class_remove_file_ns(class, attr, NULL); -- cgit v1.2.3 From d2fff09656369d5465585ad2c72d8ba8ada758b5 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 13 Mar 2023 19:18:40 +0100 Subject: driver core: device: make device_destroy() take a const class * device_destroy() does not modify the struct class passed into it, so mark it as const to enforce this rule. Cc: "Rafael J. Wysocki" Link: https://lore.kernel.org/r/20230313181843.1207845-9-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 12dc08aa5c0f..2562451b875b 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -1021,7 +1021,7 @@ __printf(6, 7) struct device * device_create_with_groups(struct class *cls, struct device *parent, dev_t devt, void *drvdata, const struct attribute_group **groups, const char *fmt, ...); -void device_destroy(struct class *cls, dev_t devt); +void device_destroy(const struct class *cls, dev_t devt); int __must_check device_add_groups(struct device *dev, const struct attribute_group **groups); -- cgit v1.2.3 From 9fa120fbd507e58af3494b8765427fdc8181e1eb Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 13 Mar 2023 19:18:42 +0100 Subject: driver core: device: mark struct class in struct device as constant The pointer to a struct class in a struct device should never be used to change anything in that class. So mark it as constant to enforce this requirement. This requires a few minor changes to some internal driver core functions to enforce the const * being used here now. Cc: "Rafael J. Wysocki" Link: https://lore.kernel.org/r/20230313181843.1207845-11-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 2562451b875b..ea07b95b06e5 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -631,7 +631,7 @@ struct device { spinlock_t devres_lock; struct list_head devres_head; - struct class *class; + const struct class *class; const struct attribute_group **groups; /* optional groups */ void (*release)(struct device *dev); -- cgit v1.2.3 From 2bd5c63978b771462da10d8771f56a1e656501d9 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 13 Mar 2023 19:18:43 +0100 Subject: driver core: device: make device_create*() take a const struct class * The functions device_create() and device_create_with_groups() do not modify the struct class passed into it, so enforce this by changing the function parameters to be struct const class. Cc: "Rafael J. Wysocki" Link: https://lore.kernel.org/r/20230313181843.1207845-12-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index ea07b95b06e5..862397ae520d 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -1015,10 +1015,10 @@ bool device_is_bound(struct device *dev); * Easy functions for dynamically creating devices on the fly */ __printf(5, 6) struct device * -device_create(struct class *cls, struct device *parent, dev_t devt, +device_create(const struct class *cls, struct device *parent, dev_t devt, void *drvdata, const char *fmt, ...); __printf(6, 7) struct device * -device_create_with_groups(struct class *cls, struct device *parent, dev_t devt, +device_create_with_groups(const struct class *cls, struct device *parent, dev_t devt, void *drvdata, const struct attribute_group **groups, const char *fmt, ...); void device_destroy(const struct class *cls, dev_t devt); -- cgit v1.2.3 From 2dd6d0ebf74049256160a3d03dabbd92fe0b8599 Mon Sep 17 00:00:00 2001 From: Wyes Karny Date: Tue, 7 Mar 2023 11:27:38 +0000 Subject: cpufreq: amd-pstate: Add guided autonomous mode From ACPI spec below 3 modes for CPPC can be defined: 1. Non autonomous: OS scaling governor specifies operating frequency/ performance level through `Desired Performance` register and platform follows that. 2. Guided autonomous: OS scaling governor specifies min and max frequencies/ performance levels through `Minimum Performance` and `Maximum Performance` register, and platform can autonomously select an operating frequency in this range. 3. Fully autonomous: OS only hints (via EPP) to platform for the required energy performance preference for the workload and platform autonomously scales the frequency. Currently (1) is supported by amd_pstate as passive mode, and (3) is implemented by EPP support. This change is to support (2). In guided autonomous mode the min_perf is based on the input from the scaling governor. For example, in case of schedutil this value depends on the current utilization. And max_perf is set to max capacity. To activate guided auto mode ``amd_pstate=guided`` command line parameter has to be passed in the kernel. Acked-by: Huang Rui Reviewed-by: Mario Limonciello Tested-by: Oleksandr Natalenko Signed-off-by: Wyes Karny Signed-off-by: Rafael J. Wysocki --- include/linux/amd-pstate.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/amd-pstate.h b/include/linux/amd-pstate.h index f5f22418e64b..c10ebf8c42e6 100644 --- a/include/linux/amd-pstate.h +++ b/include/linux/amd-pstate.h @@ -97,6 +97,7 @@ enum amd_pstate_mode { AMD_PSTATE_DISABLE = 0, AMD_PSTATE_PASSIVE, AMD_PSTATE_ACTIVE, + AMD_PSTATE_GUIDED, AMD_PSTATE_MAX, }; @@ -104,6 +105,7 @@ static const char * const amd_pstate_mode_string[] = { [AMD_PSTATE_DISABLE] = "disable", [AMD_PSTATE_PASSIVE] = "passive", [AMD_PSTATE_ACTIVE] = "active", + [AMD_PSTATE_GUIDED] = "guided", NULL, }; #endif /* _LINUX_AMD_PSTATE_H */ -- cgit v1.2.3 From 6365ba64b4dbe8b59ddaeaa724b281f3787715d5 Mon Sep 17 00:00:00 2001 From: Jeremi Piotrowski Date: Wed, 8 Mar 2023 15:05:31 +0000 Subject: ptp: kvm: Use decrypted memory in confidential guest on x86 KVM_HC_CLOCK_PAIRING currently fails inside SEV-SNP guests because the guest passes an address to static data to the host. In confidential computing the host can't access arbitrary guest memory so handling the hypercall runs into an "rmpfault". To make the hypercall work, the guest needs to explicitly mark the memory as decrypted. Do that in kvm_arch_ptp_init(), but retain the previous behavior for non-confidential guests to save us from having to allocate memory. Add a new arch-specific function (kvm_arch_ptp_exit()) to free the allocation and mark the memory as encrypted again. Signed-off-by: Jeremi Piotrowski Link: https://lore.kernel.org/r/20230308150531.477741-1-jpiotrowski@linux.microsoft.com Signed-off-by: Jakub Kicinski --- include/linux/ptp_kvm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/ptp_kvm.h b/include/linux/ptp_kvm.h index c2e28deef33a..746fd67c3480 100644 --- a/include/linux/ptp_kvm.h +++ b/include/linux/ptp_kvm.h @@ -14,6 +14,7 @@ struct timespec64; struct clocksource; int kvm_arch_ptp_init(void); +void kvm_arch_ptp_exit(void); int kvm_arch_ptp_get_clock(struct timespec64 *ts); int kvm_arch_ptp_get_crosststamp(u64 *cycle, struct timespec64 *tspec, struct clocksource **cs); -- cgit v1.2.3 From 36bd28c1cb0dbf48645cfe43159907fb3253b33a Mon Sep 17 00:00:00 2001 From: haozhe chang Date: Thu, 16 Mar 2023 17:58:20 +0800 Subject: wwan: core: Support slicing in port TX flow of WWAN subsystem wwan_port_fops_write inputs the SKB parameter to the TX callback of the WWAN device driver. However, the WWAN device (e.g., t7xx) may have an MTU less than the size of SKB, causing the TX buffer to be sliced and copied once more in the WWAN device driver. This patch implements the slicing in the WWAN subsystem and gives the WWAN devices driver the option to slice(by frag_len) or not. By doing so, the additional memory copy is reduced. Meanwhile, this patch gives WWAN devices driver the option to reserve headroom in fragments for the device-specific metadata. Signed-off-by: haozhe chang Reviewed-by: Loic Poulain Link: https://lore.kernel.org/r/20230316095826.181904-1-haozhe.chang@mediatek.com Signed-off-by: Jakub Kicinski --- include/linux/wwan.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/wwan.h b/include/linux/wwan.h index 24d76500b1cc..01fa15506286 100644 --- a/include/linux/wwan.h +++ b/include/linux/wwan.h @@ -64,11 +64,21 @@ struct wwan_port_ops { poll_table *wait); }; +/** struct wwan_port_caps - The WWAN port capbilities + * @frag_len: WWAN port TX fragments length + * @headroom_len: WWAN port TX fragments reserved headroom length + */ +struct wwan_port_caps { + size_t frag_len; + unsigned int headroom_len; +}; + /** * wwan_create_port - Add a new WWAN port * @parent: Device to use as parent and shared by all WWAN ports * @type: WWAN port type * @ops: WWAN port operations + * @caps: WWAN port capabilities * @drvdata: Pointer to caller driver data * * Allocate and register a new WWAN port. The port will be automatically exposed @@ -86,6 +96,7 @@ struct wwan_port_ops { struct wwan_port *wwan_create_port(struct device *parent, enum wwan_port_type type, const struct wwan_port_ops *ops, + struct wwan_port_caps *caps, void *drvdata); /** -- cgit v1.2.3 From 6ee44c518159c364e5d30ed85d357fe1d8e2c141 Mon Sep 17 00:00:00 2001 From: Gavin Li Date: Thu, 16 Mar 2023 09:07:58 +0200 Subject: net/mlx5e: TC, Add support for VxLAN GBP encap/decap flows offload Add HW offloading support for TC flows with VxLAN GBP encap/decap. Example of encap rule: tc filter add dev eth0 protocol ip ingress flower \ action tunnel_key set id 42 vxlan_opts 512 \ action mirred egress redirect dev vxlan1 Example of decap rule: tc filter add dev vxlan1 protocol ip ingress flower \ enc_key_id 42 enc_dst_port 4789 vxlan_opts 1024 \ action tunnel_key unset action mirred egress redirect dev eth0 Signed-off-by: Gavin Li Reviewed-by: Gavi Teitz Reviewed-by: Roi Dayan Reviewed-by: Maor Dickman Acked-by: Saeed Mahameed Signed-off-by: Jakub Kicinski --- include/linux/mlx5/device.h | 6 ++++++ include/linux/mlx5/mlx5_ifc.h | 13 +++++++++++-- 2 files changed, 17 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 71b06ebad402..af4dd536a52c 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -1357,6 +1357,12 @@ enum mlx5_qcam_feature_groups { #define MLX5_CAP_ESW_INGRESS_ACL_MAX(mdev, cap) \ MLX5_CAP_ESW_FLOWTABLE_MAX(mdev, flow_table_properties_esw_acl_ingress.cap) +#define MLX5_CAP_ESW_FT_FIELD_SUPPORT_2(mdev, cap) \ + MLX5_CAP_ESW_FLOWTABLE(mdev, ft_field_support_2_esw_fdb.cap) + +#define MLX5_CAP_ESW_FT_FIELD_SUPPORT_2_MAX(mdev, cap) \ + MLX5_CAP_ESW_FLOWTABLE_MAX(mdev, ft_field_support_2_esw_fdb.cap) + #define MLX5_CAP_ESW(mdev, cap) \ MLX5_GET(e_switch_cap, \ mdev->caps.hca[MLX5_CAP_ESWITCH]->cur, cap) diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index d2c164f0778c..e47d6c58da35 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -404,10 +404,13 @@ struct mlx5_ifc_flow_table_fields_supported_bits { u8 metadata_reg_c_0[0x1]; }; +/* Table 2170 - Flow Table Fields Supported 2 Format */ struct mlx5_ifc_flow_table_fields_supported_2_bits { u8 reserved_at_0[0xe]; u8 bth_opcode[0x1]; - u8 reserved_at_f[0x11]; + u8 reserved_at_f[0x1]; + u8 tunnel_header_0_1[0x1]; + u8 reserved_at_11[0xf]; u8 reserved_at_20[0x60]; }; @@ -895,7 +898,13 @@ struct mlx5_ifc_flow_table_eswitch_cap_bits { struct mlx5_ifc_flow_table_prop_layout_bits flow_table_properties_esw_acl_egress; - u8 reserved_at_800[0x1000]; + u8 reserved_at_800[0xC00]; + + struct mlx5_ifc_flow_table_fields_supported_2_bits ft_field_support_2_esw_fdb; + + struct mlx5_ifc_flow_table_fields_supported_2_bits ft_field_bitmask_support_2_esw_fdb; + + u8 reserved_at_1500[0x300]; u8 sw_steering_fdb_action_drop_icm_address_rx[0x40]; -- cgit v1.2.3 From 94c540fbfc80ef95ec398fc77da1920de2946edb Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 17 Mar 2023 15:55:30 +0000 Subject: udp: preserve const qualifier in udp_sk() We can change udp_sk() to propagate const qualifier of its argument, thanks to container_of_const() This should avoid some potential errors caused by accidental (const -> not_const) promotion. Signed-off-by: Eric Dumazet Cc: Willem de Bruijn Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- include/linux/udp.h | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/udp.h b/include/linux/udp.h index a2892e151644..43c1fb2d2c21 100644 --- a/include/linux/udp.h +++ b/include/linux/udp.h @@ -97,10 +97,7 @@ struct udp_sock { #define UDP_MAX_SEGMENTS (1 << 6UL) -static inline struct udp_sock *udp_sk(const struct sock *sk) -{ - return (struct udp_sock *)sk; -} +#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) { -- cgit v1.2.3 From 47fcae28b9ec409423ba7f67f93e8345acce8a36 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 17 Mar 2023 15:55:33 +0000 Subject: ipv6: raw: preserve const qualifier in raw6_sk() We can change raw6_sk() to propagate its argument const qualifier, thanks to container_of_const(). Signed-off-by: Eric Dumazet Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- include/linux/ipv6.h | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 37dfdcfcdd54..839247a4f48e 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -336,10 +336,7 @@ static inline struct ipv6_pinfo *inet6_sk(const struct sock *__sk) return sk_fullsock(__sk) ? inet_sk(__sk)->pinet6 : NULL; } -static inline struct raw6_sock *raw6_sk(const struct sock *sk) -{ - return (struct raw6_sock *)sk; -} +#define raw6_sk(ptr) container_of_const(ptr, struct raw6_sock, inet.sk) #define ipv6_only_sock(sk) (sk->sk_ipv6only) #define ipv6_sk_rxinfo(sk) ((sk)->sk_family == PF_INET6 && \ -- cgit v1.2.3 From ae6084b739925d84ef4a481d8eaa2187455f2e2f Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 17 Mar 2023 15:55:34 +0000 Subject: dccp: preserve const qualifier in dccp_sk() We can change dccp_sk() to propagate its argument const qualifier, thanks to container_of_const(). Signed-off-by: Eric Dumazet Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- include/linux/dccp.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dccp.h b/include/linux/dccp.h index 07e547c02fd8..325af611909f 100644 --- a/include/linux/dccp.h +++ b/include/linux/dccp.h @@ -305,10 +305,8 @@ struct dccp_sock { struct timer_list dccps_xmit_timer; }; -static inline struct dccp_sock *dccp_sk(const struct sock *sk) -{ - return (struct dccp_sock *)sk; -} +#define dccp_sk(ptr) container_of_const(ptr, struct dccp_sock, \ + dccps_inet_connection.icsk_inet.sk) static inline const char *dccp_role(const struct sock *sk) { -- cgit v1.2.3 From e9d9da91548b21e189fcd0259a0f2d26d1afc509 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 17 Mar 2023 15:55:39 +0000 Subject: tcp: preserve const qualifier in tcp_sk() We can change tcp_sk() to propagate its argument const qualifier, thanks to container_of_const(). We have two places where a const sock pointer has to be upgraded to a write one. We have been using const qualifier for lockless listeners to clearly identify points where writes could happen. Add tcp_sk_rw() helper to better document these. tcp_inbound_md5_hash(), __tcp_grow_window(), tcp_reset_check() and tcp_rack_reo_wnd() get an additional const qualififer for their @tp local variables. smc_check_reset_syn_req() also needs a similar change. Signed-off-by: Eric Dumazet Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- include/linux/tcp.h | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index ca7f05a130d2..b4c08ac86983 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -472,10 +472,12 @@ enum tsq_flags { TCPF_MTU_REDUCED_DEFERRED = (1UL << TCP_MTU_REDUCED_DEFERRED), }; -static inline struct tcp_sock *tcp_sk(const struct sock *sk) -{ - return (struct tcp_sock *)sk; -} +#define tcp_sk(ptr) container_of_const(ptr, struct tcp_sock, inet_conn.icsk_inet.sk) + +/* Variant of tcp_sk() upgrading a const sock to a read/write tcp socket. + * Used in context of (lockless) tcp listeners. + */ +#define tcp_sk_rw(ptr) container_of(ptr, struct tcp_sock, inet_conn.icsk_inet.sk) struct tcp_timewait_sock { struct inet_timewait_sock tw_sk; -- cgit v1.2.3 From 7ce93729091dff24e6a1c3578b58b36f4b1cf10a Mon Sep 17 00:00:00 2001 From: Jason Baron Date: Fri, 10 Mar 2023 16:27:28 -0500 Subject: dyndbg: cleanup dynamic usage in ib_srp.c Currently, in dynamic_debug.h we only provide DEFINE_DYNAMIC_DEBUG_METADATA() and DYNAMIC_DEBUG_BRANCH() definitions if CONFIG_DYNAMIC_CORE is enabled. Thus, drivers such as infiniband srp (see: drivers/infiniband/ulp/srp/ib_srp.c) must provide their own definitions for !CONFIG_DYNAMIC_CORE. Thus, let's move this !CONFIG_DYNAMIC_CORE case into dynamic_debug.h. However, the dynamic debug interfaces should really only be defined if CONFIG_DYNAMIC_DEBUG is set or CONFIG_DYNAMIC_CORE is set along with DYNAMIC_DEBUG_MODULE, (see: Documentation/admin-guide/dynamic-debug-howto.rst). Thus, the undefined case becomes: !((CONFIG_DYNAMIC_DEBUG || (CONFIG_DYNAMIC_CORE && DYNAMIC_DEBUG_MODULE)). With those changes in place, we can remove the !CONFIG_DYNAMIC_CORE case from ib_srp.c This change was prompted by a build breakeage in ib_srp.c stemming from the inclusion of dynamic_debug.h unconditionally in module.h, due to commit 7deabd674988 ("dyndbg: use the module notifier callbacks"). In that case, if we have CONFIG_DYNAMIC_CORE=y and CONFIG_DYNAMIC_DEBUG=n then the definitions for DEFINE_DYNAMIC_DEBUG_METADATA() and DYNAMIC_DEBUG_BRANCH() are defined once in ib_srp.c and then again in the dynamic_debug.h. This had been working prior to the above referenced commit because dynamic_debug.h was only pulled into ib_srp.c conditinally via printk.h if CONFIG_DYNAMIC_DEBUG was set. Also, the exported functions in lib/dynamic_debug.c itself may not have a prototype if CONFIG_DYNAMIC_DEBUG=n and CONFIG_DYNAMIC_CORE=y. This would trigger the -Wmissing-prototypes warning. The exported functions are behind (include/linux/dynamic_debug.h): if defined(CONFIG_DYNAMIC_DEBUG) || \ (defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE)) Thus, by adding -DDYNAMIC_CONFIG_MODULE to the lib/Makefile we can ensure that the exported functions have a prototype in all cases, since lib/dynamic_debug.c is built whenever CONFIG_DYNAMIC_DEBUG_CORE=y. Fixes: 7deabd674988 ("dyndbg: use the module notifier callbacks") Reported-by: kernel test robot Link: https://lore.kernel.org/oe-kbuild-all/202303071444.sIbZTDCy-lkp@intel.com/ Signed-off-by: Jason Baron [mcgrof: adjust commit log, and remove urldefense from URL] Signed-off-by: Luis Chamberlain --- include/linux/dynamic_debug.h | 59 +++++++++++++++++++++++++++---------------- 1 file changed, 37 insertions(+), 22 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dynamic_debug.h b/include/linux/dynamic_debug.h index f401414341fb..061dd84d09f3 100644 --- a/include/linux/dynamic_debug.h +++ b/include/linux/dynamic_debug.h @@ -128,14 +128,16 @@ struct ddebug_class_param { const struct ddebug_class_map *map; }; -#if defined(CONFIG_DYNAMIC_DEBUG_CORE) +/* + * pr_debug() and friends are globally enabled or modules have selectively + * enabled them. + */ +#if defined(CONFIG_DYNAMIC_DEBUG) || \ + (defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE)) extern __printf(2, 3) void __dynamic_pr_debug(struct _ddebug *descriptor, const char *fmt, ...); -extern int ddebug_dyndbg_module_param_cb(char *param, char *val, - const char *modname); - struct device; extern __printf(3, 4) @@ -284,10 +286,6 @@ void __dynamic_ibdev_dbg(struct _ddebug *descriptor, KERN_DEBUG, prefix_str, prefix_type, \ rowsize, groupsize, buf, len, ascii) -struct kernel_param; -int param_set_dyndbg_classes(const char *instr, const struct kernel_param *kp); -int param_get_dyndbg_classes(char *buffer, const struct kernel_param *kp); - /* for test only, generally expect drm.debug style macro wrappers */ #define __pr_debug_cls(cls, fmt, ...) do { \ BUILD_BUG_ON_MSG(!__builtin_constant_p(cls), \ @@ -295,23 +293,14 @@ int param_get_dyndbg_classes(char *buffer, const struct kernel_param *kp); dynamic_pr_debug_cls(cls, fmt, ##__VA_ARGS__); \ } while (0) -#else /* !CONFIG_DYNAMIC_DEBUG_CORE */ +#else /* !(CONFIG_DYNAMIC_DEBUG || (CONFIG_DYNAMIC_DEBUG_CORE && DYNAMIC_DEBUG_MODULE)) */ #include #include #include -static inline int ddebug_dyndbg_module_param_cb(char *param, char *val, - const char *modname) -{ - if (!strcmp(param, "dyndbg")) { - /* avoid pr_warn(), which wants pr_fmt() fully defined */ - printk(KERN_WARNING "dyndbg param is supported only in " - "CONFIG_DYNAMIC_DEBUG builds\n"); - return 0; /* allow and ignore */ - } - return -EINVAL; -} +#define DEFINE_DYNAMIC_DEBUG_METADATA(name, fmt) +#define DYNAMIC_DEBUG_BRANCH(descriptor) false #define dynamic_pr_debug(fmt, ...) \ do { if (0) printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__); } while (0) @@ -324,14 +313,40 @@ static inline int ddebug_dyndbg_module_param_cb(char *param, char *val, rowsize, groupsize, buf, len, ascii); \ } while (0) +#endif /* CONFIG_DYNAMIC_DEBUG || (CONFIG_DYNAMIC_DEBUG_CORE && DYNAMIC_DEBUG_MODULE) */ + + +#ifdef CONFIG_DYNAMIC_DEBUG_CORE + +extern int ddebug_dyndbg_module_param_cb(char *param, char *val, + const char *modname); +struct kernel_param; +int param_set_dyndbg_classes(const char *instr, const struct kernel_param *kp); +int param_get_dyndbg_classes(char *buffer, const struct kernel_param *kp); + +#else + +static inline int ddebug_dyndbg_module_param_cb(char *param, char *val, + const char *modname) +{ + if (!strcmp(param, "dyndbg")) { + /* avoid pr_warn(), which wants pr_fmt() fully defined */ + printk(KERN_WARNING "dyndbg param is supported only in " + "CONFIG_DYNAMIC_DEBUG builds\n"); + return 0; /* allow and ignore */ + } + return -EINVAL; +} + struct kernel_param; static inline int param_set_dyndbg_classes(const char *instr, const struct kernel_param *kp) { return 0; } static inline int param_get_dyndbg_classes(char *buffer, const struct kernel_param *kp) { return 0; } -#endif /* !CONFIG_DYNAMIC_DEBUG_CORE */ +#endif + extern const struct kernel_param_ops param_ops_dyndbg_classes; -#endif +#endif /* _DYNAMIC_DEBUG_H */ -- cgit v1.2.3 From 3703bd54cd37e7875f51ece8df8c85c184e40bba Mon Sep 17 00:00:00 2001 From: Zhen Lei Date: Wed, 8 Mar 2023 15:38:46 +0800 Subject: kallsyms: Delete an unused parameter related to {module_}kallsyms_on_each_symbol() The parameter 'struct module *' in the hook function associated with {module_}kallsyms_on_each_symbol() is no longer used. Delete it. Suggested-by: Petr Mladek Signed-off-by: Zhen Lei Reviewed-by: Vincenzo Palazzo Acked-by: Jiri Olsa Acked-by: Steven Rostedt (Google) Signed-off-by: Luis Chamberlain --- include/linux/kallsyms.h | 7 +++---- include/linux/module.h | 6 ++---- 2 files changed, 5 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kallsyms.h b/include/linux/kallsyms.h index 0065209cc004..fe3c9993b5bf 100644 --- a/include/linux/kallsyms.h +++ b/include/linux/kallsyms.h @@ -67,8 +67,7 @@ static inline void *dereference_symbol_descriptor(void *ptr) #ifdef CONFIG_KALLSYMS unsigned long kallsyms_sym_address(int idx); -int kallsyms_on_each_symbol(int (*fn)(void *, const char *, struct module *, - unsigned long), +int kallsyms_on_each_symbol(int (*fn)(void *, const char *, unsigned long), void *data); int kallsyms_on_each_match_symbol(int (*fn)(void *, unsigned long), const char *name, void *data); @@ -166,8 +165,8 @@ static inline bool kallsyms_show_value(const struct cred *cred) return false; } -static inline int kallsyms_on_each_symbol(int (*fn)(void *, const char *, struct module *, - unsigned long), void *data) +static inline int kallsyms_on_each_symbol(int (*fn)(void *, const char *, unsigned long), + void *data) { return -EOPNOTSUPP; } diff --git a/include/linux/module.h b/include/linux/module.h index c3b357196470..d2d900077bde 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -965,13 +965,11 @@ static inline bool module_sig_ok(struct module *module) #if defined(CONFIG_MODULES) && defined(CONFIG_KALLSYMS) int module_kallsyms_on_each_symbol(const char *modname, - int (*fn)(void *, const char *, - struct module *, unsigned long), + int (*fn)(void *, const char *, unsigned long), void *data); #else static inline int module_kallsyms_on_each_symbol(const char *modname, - int (*fn)(void *, const char *, - struct module *, unsigned long), + int (*fn)(void *, const char *, unsigned long), void *data) { return -EOPNOTSUPP; -- cgit v1.2.3 From a69e332b4ef9f697a4558bab9c442a02b3659fcb Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Sat, 18 Mar 2023 21:32:41 +0100 Subject: net: phy: smsc: export functions for use by meson-gxl PHY driver The Amlogic Meson internal PHY's have the same register layout as certain SMSC PHY's (also for non-c22-standard registers). This seems to be more than just coincidence. Apparently they also need the same workaround for EDPD mode (energy detect power down). Therefore let's export SMSC PHY driver functionality for use by the meson-gxl PHY driver. Signed-off-by: Heiner Kallweit Signed-off-by: Chris Healy Signed-off-by: David S. Miller --- include/linux/smscphy.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/smscphy.h b/include/linux/smscphy.h index 1a136271ba6a..80f37c1dba58 100644 --- a/include/linux/smscphy.h +++ b/include/linux/smscphy.h @@ -28,4 +28,10 @@ #define MII_LAN83C185_MODE_POWERDOWN 0xC0 /* Power Down mode */ #define MII_LAN83C185_MODE_ALL 0xE0 /* All capable mode */ +int smsc_phy_config_intr(struct phy_device *phydev); +irqreturn_t smsc_phy_handle_interrupt(struct phy_device *phydev); +int smsc_phy_config_init(struct phy_device *phydev); +int lan87xx_read_status(struct phy_device *phydev); +int smsc_phy_probe(struct phy_device *phydev); + #endif /* __LINUX_SMSCPHY_H__ */ -- cgit v1.2.3 From 419405c92299d793b95053aa54d95e2d3f45a1a4 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Mon, 6 Mar 2023 08:56:49 +0100 Subject: interconnect: drop racy registration API Now that all interconnect drivers have been converted to the new provider registration API, the old racy interface can be removed. Reviewed-by: Konrad Dybcio Signed-off-by: Johan Hovold Link: https://lore.kernel.org/r/20230306075651.2449-22-johan+linaro@kernel.org Signed-off-by: Georgi Djakov --- include/linux/interconnect-provider.h | 11 ----------- 1 file changed, 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/interconnect-provider.h b/include/linux/interconnect-provider.h index d12cd18aab3f..b9af9016a95e 100644 --- a/include/linux/interconnect-provider.h +++ b/include/linux/interconnect-provider.h @@ -125,8 +125,6 @@ int icc_nodes_remove(struct icc_provider *provider); void icc_provider_init(struct icc_provider *provider); int icc_provider_register(struct icc_provider *provider); void icc_provider_deregister(struct icc_provider *provider); -int icc_provider_add(struct icc_provider *provider); -void icc_provider_del(struct icc_provider *provider); struct icc_node_data *of_icc_get_from_provider(struct of_phandle_args *spec); void icc_sync_state(struct device *dev); @@ -179,15 +177,6 @@ static inline int icc_provider_register(struct icc_provider *provider) static inline void icc_provider_deregister(struct icc_provider *provider) { } -static inline int icc_provider_add(struct icc_provider *provider) -{ - return -ENOTSUPP; -} - -static inline void icc_provider_del(struct icc_provider *provider) -{ -} - static inline struct icc_node_data *of_icc_get_from_provider(struct of_phandle_args *spec) { return ERR_PTR(-ENOTSUPP); -- cgit v1.2.3 From f22f9aaf6c3d92ebd5ad9e67acc03afebaaeb289 Mon Sep 17 00:00:00 2001 From: Paul Moore Date: Fri, 17 Mar 2023 12:43:07 -0400 Subject: selinux: remove the runtime disable functionality After working with the larger SELinux-based distros for several years, we're finally at a place where we can disable the SELinux runtime disable functionality. The existing kernel deprecation notice explains the functionality and why we want to remove it: The selinuxfs "disable" node allows SELinux to be disabled at runtime prior to a policy being loaded into the kernel. If disabled via this mechanism, SELinux will remain disabled until the system is rebooted. The preferred method of disabling SELinux is via the "selinux=0" boot parameter, but the selinuxfs "disable" node was created to make it easier for systems with primitive bootloaders that did not allow for easy modification of the kernel command line. Unfortunately, allowing for SELinux to be disabled at runtime makes it difficult to secure the kernel's LSM hooks using the "__ro_after_init" feature. It is that last sentence, mentioning the '__ro_after_init' hardening, which is the real motivation for this change, and if you look at the diffstat you'll see that the impact of this patch reaches across all the different LSMs, helping prevent tampering at the LSM hook level. From a SELinux perspective, it is important to note that if you continue to disable SELinux via "/etc/selinux/config" it may appear that SELinux is disabled, but it is simply in an uninitialized state. If you load a policy with `load_policy -i`, you will see SELinux come alive just as if you had loaded the policy during early-boot. It is also worth noting that the "/sys/fs/selinux/disable" file is always writable now, regardless of the Kconfig settings, but writing to the file has no effect on the system, other than to display an error on the console if a non-zero/true value is written. Finally, in the several years where we have been working on deprecating this functionality, there has only been one instance of someone mentioning any user visible breakage. In this particular case it was an individual's kernel test system, and the workaround documented in the deprecation notice ("selinux=0" on the kernel command line) resolved the issue without problem. Acked-by: Casey Schaufler Signed-off-by: Paul Moore --- include/linux/lsm_hooks.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index 6e156d2acffc..af87b962f5f7 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -1763,13 +1763,6 @@ static inline void security_delete_hooks(struct security_hook_list *hooks, } #endif /* CONFIG_SECURITY_SELINUX_DISABLE */ -/* Currently required to handle SELinux runtime hook disable. */ -#ifdef CONFIG_SECURITY_WRITABLE_HOOKS -#define __lsm_ro_after_init -#else -#define __lsm_ro_after_init __ro_after_init -#endif /* CONFIG_SECURITY_WRITABLE_HOOKS */ - extern int lsm_inode_alloc(struct inode *inode); #endif /* ! __LINUX_LSM_HOOKS_H */ -- cgit v1.2.3 From 54bdd67d0f88489ac88f7664b56cb7c93799d84d Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Mon, 20 Mar 2023 12:49:26 -0700 Subject: blk-mq: remove hybrid polling io_uring provides the only way user space can poll completions, and that always sets BLK_POLL_NOSLEEP. This effectively makes hybrid polling dead code, so remove it and everything supporting it. Hybrid polling was effectively killed off with 9650b453a3d4b1, "block: ignore RWF_HIPRI hint for sync dio", but still potentially reachable through io_uring until d729cf9acb93119, "io_uring: don't sleep when polling for I/O", but hybrid polling probably should not have been reachable through that async interface from the beginning. Fixes: 9650b453a3d4 ("block: ignore RWF_HIPRI hint for sync dio") Fixes: d729cf9acb93 ("io_uring: don't sleep when polling for I/O") Signed-off-by: Keith Busch Link: https://lore.kernel.org/r/20230320194926.3353144-1-kbusch@meta.com Signed-off-by: Jens Axboe --- include/linux/blk-mq.h | 2 -- include/linux/blkdev.h | 12 ------------ 2 files changed, 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index dd5ce1137f04..1dacb2c81fdd 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -57,8 +57,6 @@ typedef __u32 __bitwise req_flags_t; #define RQF_SPECIAL_PAYLOAD ((__force req_flags_t)(1 << 18)) /* The per-zone write lock is held for this request */ #define RQF_ZONE_WRITE_LOCKED ((__force req_flags_t)(1 << 19)) -/* already slept for hybrid poll */ -#define RQF_MQ_POLL_SLEPT ((__force req_flags_t)(1 << 20)) /* ->timeout has been called, don't expire again */ #define RQF_TIMED_OUT ((__force req_flags_t)(1 << 21)) /* queue has elevator attached */ diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index d1aee08f8c18..6ede578dfbc6 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -44,12 +44,6 @@ extern const struct device_type disk_type; extern struct device_type part_type; extern struct class block_class; -/* Must be consistent with blk_mq_poll_stats_bkt() */ -#define BLK_MQ_POLL_STATS_BKTS 16 - -/* Doing classic polling */ -#define BLK_MQ_POLL_CLASSIC -1 - /* * Maximum number of blkcg policies allowed to be registered concurrently. * Defined here to simplify include dependency. @@ -468,10 +462,6 @@ struct request_queue { #endif unsigned int rq_timeout; - int poll_nsec; - - struct blk_stat_callback *poll_cb; - struct blk_rq_stat *poll_stat; struct timer_list timeout; struct work_struct timeout_work; @@ -870,8 +860,6 @@ blk_status_t errno_to_blk_status(int errno); /* only poll the hardware once, don't continue until a completion was found */ #define BLK_POLL_ONESHOT (1 << 0) -/* do not sleep to wait for the expected completion time */ -#define BLK_POLL_NOSLEEP (1 << 1) int bio_poll(struct bio *bio, struct io_comp_batch *iob, unsigned int flags); int iocb_bio_iopoll(struct kiocb *kiocb, struct io_comp_batch *iob, unsigned int flags); -- cgit v1.2.3 From d54c1fd4a51e8fbc7f9da86b0cd338a4f7cd2bb2 Mon Sep 17 00:00:00 2001 From: Qin Jian Date: Mon, 19 Dec 2022 09:51:30 +0800 Subject: clk: Add Sunplus SP7021 clock driver Add clock driver for Sunplus SP7021 SoC. Signed-off-by: Qin Jian Link: https://lore.kernel.org/r/20221219015130.42621-1-qinjian@cqplus1.com Signed-off-by: Stephen Boyd --- include/linux/clk-provider.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include/linux') diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index 842e72a5348f..0e3bc3eb9911 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -608,6 +608,25 @@ struct clk *clk_register_gate(struct device *dev, const char *name, __devm_clk_hw_register_gate((dev), NULL, (name), (parent_name), NULL, \ NULL, (flags), (reg), (bit_idx), \ (clk_gate_flags), (lock)) +/** + * devm_clk_hw_register_gate_parent_data - register a gate clock with the + * clock framework + * @dev: device that is registering this clock + * @name: name of this clock + * @parent_data: parent clk data + * @flags: framework-specific flags for this clock + * @reg: register address to control gating of this clock + * @bit_idx: which bit in the register controls gating of this clock + * @clk_gate_flags: gate-specific flags for this clock + * @lock: shared register lock for this clock + */ +#define devm_clk_hw_register_gate_parent_data(dev, name, parent_data, flags, \ + reg, bit_idx, clk_gate_flags, \ + lock) \ + __devm_clk_hw_register_gate((dev), NULL, (name), NULL, NULL, \ + (parent_data), (flags), (reg), (bit_idx), \ + (clk_gate_flags), (lock)) + void clk_unregister_gate(struct clk *clk); void clk_hw_unregister_gate(struct clk_hw *hw); int clk_gate_is_enabled(struct clk_hw *hw); -- cgit v1.2.3 From 4765a9722e09765866e131ec31f7b9cf4c1f4854 Mon Sep 17 00:00:00 2001 From: Daniel Golle Date: Sun, 19 Mar 2023 12:57:50 +0000 Subject: net: pcs: add driver for MediaTek SGMII PCS The SGMII core found in several MediaTek SoCs is identical to what can also be found in MediaTek's MT7531 Ethernet switch IC. As this has not always been clear, both drivers developed different implementations to deal with the PCS. Recently Alexander Couzens pointed out this fact which lead to the development of this shared driver. Add a dedicated driver, mostly by copying the code now found in the Ethernet driver. The now redundant code will be removed by a follow-up commit. Suggested-by: Alexander Couzens Suggested-by: Russell King (Oracle) Signed-off-by: Daniel Golle Tested-by: Frank Wunderlich Reviewed-by: Russell King (Oracle) Signed-off-by: Jakub Kicinski --- include/linux/pcs/pcs-mtk-lynxi.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) create mode 100644 include/linux/pcs/pcs-mtk-lynxi.h (limited to 'include/linux') diff --git a/include/linux/pcs/pcs-mtk-lynxi.h b/include/linux/pcs/pcs-mtk-lynxi.h new file mode 100644 index 000000000000..be3b4ab32f4a --- /dev/null +++ b/include/linux/pcs/pcs-mtk-lynxi.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LINUX_PCS_MTK_LYNXI_H +#define __LINUX_PCS_MTK_LYNXI_H + +#include +#include + +#define MTK_SGMII_FLAG_PN_SWAP BIT(0) +struct phylink_pcs *mtk_pcs_lynxi_create(struct device *dev, + struct regmap *regmap, + u32 ana_rgc3, u32 flags); +void mtk_pcs_lynxi_destroy(struct phylink_pcs *pcs); +#endif -- cgit v1.2.3 From 04aae213e719ec2bb310158c4025316ace50589b Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 20 Mar 2023 18:41:13 -0700 Subject: net: skbuff: rename __pkt_vlan_present_offset to __mono_tc_offset vlan_present is gone since commit 354259fa73e2 ("net: remove skb->vlan_present") rename the offset field to what BPF is currently looking for in this byte - mono_delivery_time and tc_at_ingress. Signed-off-by: Jakub Kicinski Link: https://lore.kernel.org/r/20230321014115.997841-2-kuba@kernel.org Signed-off-by: Martin KaFai Lau --- include/linux/skbuff.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 3f3a2a82a86b..5a63878a4550 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -955,7 +955,7 @@ struct sk_buff { __u8 csum_valid:1; /* private: */ - __u8 __pkt_vlan_present_offset[0]; + __u8 __mono_tc_offset[0]; /* public: */ __u8 remcsum_offload:1; __u8 csum_complete_sw:1; @@ -1078,7 +1078,7 @@ struct sk_buff { #define TC_AT_INGRESS_MASK (1 << 7) #define SKB_MONO_DELIVERY_TIME_MASK (1 << 5) #endif -#define PKT_VLAN_PRESENT_OFFSET offsetof(struct sk_buff, __pkt_vlan_present_offset) +#define SKB_BF_MONO_TC_OFFSET offsetof(struct sk_buff, __mono_tc_offset) #ifdef __KERNEL__ /* -- cgit v1.2.3 From b94e032b7ad6318b36615f0e0cc3b0d61a5531e8 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 20 Mar 2023 18:41:14 -0700 Subject: net: skbuff: reorder bytes 2 and 3 of the bitfield BPF needs to know the offsets of fields it tries to access. Zero-length fields are added to make offsetof() work. This unfortunately partitions the bitfield (fields across the zero-length members can't be coalesced). Reorder bytes 2 and 3, BPF needs to know the offset of fields previously in byte 3 and some fields in byte 2 should really be optional. The two bytes are always in the same cacheline so it should not matter. Signed-off-by: Jakub Kicinski Link: https://lore.kernel.org/r/20230321014115.997841-3-kuba@kernel.org Signed-off-by: Martin KaFai Lau --- include/linux/skbuff.h | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 5a63878a4550..36d31e74db37 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -944,16 +944,6 @@ struct sk_buff { __u8 ip_summed:2; __u8 ooo_okay:1; - __u8 l4_hash:1; - __u8 sw_hash:1; - __u8 wifi_acked_valid:1; - __u8 wifi_acked:1; - __u8 no_fcs:1; - /* Indicates the inner headers are valid in the skbuff. */ - __u8 encapsulation:1; - __u8 encap_hdr_csum:1; - __u8 csum_valid:1; - /* private: */ __u8 __mono_tc_offset[0]; /* public: */ @@ -966,6 +956,16 @@ struct sk_buff { __u8 tc_skip_classify:1; __u8 tc_at_ingress:1; /* See TC_AT_INGRESS_MASK */ #endif + + __u8 l4_hash:1; + __u8 sw_hash:1; + __u8 wifi_acked_valid:1; + __u8 wifi_acked:1; + __u8 no_fcs:1; + /* Indicates the inner headers are valid in the skbuff. */ + __u8 encapsulation:1; + __u8 encap_hdr_csum:1; + __u8 csum_valid:1; #ifdef CONFIG_IPV6_NDISC_NODETYPE __u8 ndisc_nodetype:2; #endif -- cgit v1.2.3 From c0ba861117c3e8deb03855d7dc5a7717958bbb18 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 20 Mar 2023 18:41:15 -0700 Subject: net: skbuff: move the fields BPF cares about directly next to the offset marker To avoid more possible BPF dependencies with moving bitfields around keep the fields BPF cares about right next to the offset marker. Signed-off-by: Jakub Kicinski Link: https://lore.kernel.org/r/20230321014115.997841-4-kuba@kernel.org Signed-off-by: Martin KaFai Lau --- include/linux/skbuff.h | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 36d31e74db37..6aeb0e7b9511 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -947,15 +947,15 @@ struct sk_buff { /* private: */ __u8 __mono_tc_offset[0]; /* public: */ - __u8 remcsum_offload:1; - __u8 csum_complete_sw:1; - __u8 csum_level:2; - __u8 dst_pending_confirm:1; __u8 mono_delivery_time:1; /* See SKB_MONO_DELIVERY_TIME_MASK */ #ifdef CONFIG_NET_CLS_ACT - __u8 tc_skip_classify:1; __u8 tc_at_ingress:1; /* See TC_AT_INGRESS_MASK */ + __u8 tc_skip_classify:1; #endif + __u8 remcsum_offload:1; + __u8 csum_complete_sw:1; + __u8 csum_level:2; + __u8 dst_pending_confirm:1; __u8 l4_hash:1; __u8 sw_hash:1; @@ -1072,11 +1072,11 @@ struct sk_buff { * around, you also must adapt these constants. */ #ifdef __BIG_ENDIAN_BITFIELD -#define TC_AT_INGRESS_MASK (1 << 0) -#define SKB_MONO_DELIVERY_TIME_MASK (1 << 2) +#define SKB_MONO_DELIVERY_TIME_MASK (1 << 7) +#define TC_AT_INGRESS_MASK (1 << 6) #else -#define TC_AT_INGRESS_MASK (1 << 7) -#define SKB_MONO_DELIVERY_TIME_MASK (1 << 5) +#define SKB_MONO_DELIVERY_TIME_MASK (1 << 0) +#define TC_AT_INGRESS_MASK (1 << 1) #endif #define SKB_BF_MONO_TC_OFFSET offsetof(struct sk_buff, __mono_tc_offset) -- cgit v1.2.3 From 2d337b7158f8c38dacf8394028ab87b8a25ed707 Mon Sep 17 00:00:00 2001 From: ZhangPeng Date: Wed, 1 Mar 2023 10:06:27 +0000 Subject: userfaultfd: move unprivileged_userfaultfd sysctl to its own file The sysctl_unprivileged_userfaultfd is part of userfaultfd, move it to its own file. Signed-off-by: ZhangPeng Signed-off-by: Luis Chamberlain --- include/linux/userfaultfd_k.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h index 3767f18114ef..fff49fec0258 100644 --- a/include/linux/userfaultfd_k.h +++ b/include/linux/userfaultfd_k.h @@ -36,8 +36,6 @@ #define UFFD_SHARED_FCNTL_FLAGS (O_CLOEXEC | O_NONBLOCK) #define UFFD_FLAGS_SET (EFD_SHARED_FCNTL_FLAGS) -extern int sysctl_unprivileged_userfaultfd; - extern vm_fault_t handle_userfault(struct vm_fault *vmf, unsigned long reason); /* -- cgit v1.2.3 From 962de54828c5bb100eb8de881b79ed9c8b7468c0 Mon Sep 17 00:00:00 2001 From: Kefeng Wang Date: Thu, 9 Mar 2023 20:20:11 +0800 Subject: mm: hugetlb: move hugeltb sysctls to its own file This moves all hugetlb sysctls to its own file, also kill an useless hugetlb_treat_movable_handler() defination. Signed-off-by: Kefeng Wang Reviewed-by: Luis Chamberlain Reviewed-by: Mike Kravetz Reviewed-by: Muchun Song Signed-off-by: Luis Chamberlain --- include/linux/hugetlb.h | 8 -------- 1 file changed, 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 7c977d234aba..4056b05d81ed 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -124,14 +124,6 @@ void hugepage_put_subpool(struct hugepage_subpool *spool); void hugetlb_dup_vma_private(struct vm_area_struct *vma); void clear_vma_resv_huge_pages(struct vm_area_struct *vma); -int hugetlb_sysctl_handler(struct ctl_table *, int, void *, size_t *, loff_t *); -int hugetlb_overcommit_handler(struct ctl_table *, int, void *, size_t *, - loff_t *); -int hugetlb_treat_movable_handler(struct ctl_table *, int, void *, size_t *, - loff_t *); -int hugetlb_mempolicy_sysctl_handler(struct ctl_table *, int, void *, size_t *, - loff_t *); - int move_hugetlb_page_tables(struct vm_area_struct *vma, struct vm_area_struct *new_vma, unsigned long old_addr, unsigned long new_addr, -- cgit v1.2.3 From 7062e1c727ec99a9c5b40586964304d60a43f240 Mon Sep 17 00:00:00 2001 From: Simon Trimmer Date: Mon, 20 Mar 2023 11:22:38 +0000 Subject: firmware: cs_dsp: Introduce no_core_startstop for self-booting DSPs There are devices containing Halo Core DSPs that self-boot, cs_dsp is used to manage the running firmware but the host does not have direct control over starting and stopping the DSP and so cs_dsp should consider the DSP to be always running. Signed-off-by: Simon Trimmer Signed-off-by: Richard Fitzgerald Link: https://lore.kernel.org/r/20230320112245.115720-2-rf@opensource.cirrus.com Signed-off-by: Mark Brown --- include/linux/firmware/cirrus/cs_dsp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/firmware/cirrus/cs_dsp.h b/include/linux/firmware/cirrus/cs_dsp.h index cad828e21c72..29cd11d5a3cf 100644 --- a/include/linux/firmware/cirrus/cs_dsp.h +++ b/include/linux/firmware/cirrus/cs_dsp.h @@ -156,6 +156,7 @@ struct cs_dsp { unsigned int sysclk_reg; unsigned int sysclk_mask; unsigned int sysclk_shift; + bool no_core_startstop; struct list_head alg_regions; -- cgit v1.2.3 From 59495740f79524bebe4ecb8097cf206f86587b25 Mon Sep 17 00:00:00 2001 From: Florent Revest Date: Tue, 21 Mar 2023 15:04:18 +0100 Subject: ftrace: Let unregister_ftrace_direct_multi() call ftrace_free_filter() A common pattern when using the ftrace_direct_multi API is to unregister the ops and also immediately free its filter. We've noticed it's very easy for users to miss calling ftrace_free_filter(). This adds a "free_filters" argument to unregister_ftrace_direct_multi() to both remind the user they should free filters and also to make their life easier. Link: https://lkml.kernel.org/r/20230321140424.345218-2-revest@chromium.org Suggested-by: Steven Rostedt Signed-off-by: Florent Revest Acked-by: Mark Rutland Acked-by: Jiri Olsa Signed-off-by: Steven Rostedt (Google) --- include/linux/ftrace.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 366c730beaa3..5b68ee874bc1 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -407,7 +407,8 @@ int ftrace_modify_direct_caller(struct ftrace_func_entry *entry, unsigned long new_addr); unsigned long ftrace_find_rec_direct(unsigned long ip); int register_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr); -int unregister_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr); +int unregister_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr, + bool free_filters); int modify_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr); int modify_ftrace_direct_multi_nolock(struct ftrace_ops *ops, unsigned long addr); @@ -446,7 +447,8 @@ static inline int register_ftrace_direct_multi(struct ftrace_ops *ops, unsigned { return -ENODEV; } -static inline int unregister_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr) +static inline int unregister_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr, + bool free_filters) { return -ENODEV; } -- cgit v1.2.3 From 8788ca164eb4bad9a2a82c7778223c15ef800b8b Mon Sep 17 00:00:00 2001 From: Florent Revest Date: Tue, 21 Mar 2023 15:04:20 +0100 Subject: ftrace: Remove the legacy _ftrace_direct API This API relies on a single global ops, used for all direct calls registered with it. However, to implement arm64 direct calls, we need each ops to point to a single direct call trampoline. Link: https://lkml.kernel.org/r/20230321140424.345218-4-revest@chromium.org Signed-off-by: Florent Revest Acked-by: Mark Rutland Tested-by: Mark Rutland Acked-by: Jiri Olsa Signed-off-by: Steven Rostedt (Google) --- include/linux/ftrace.h | 32 -------------------------------- 1 file changed, 32 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 5b68ee874bc1..2f400c9f0787 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -397,14 +397,6 @@ struct ftrace_func_entry { #ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS extern int ftrace_direct_func_count; -int register_ftrace_direct(unsigned long ip, unsigned long addr); -int unregister_ftrace_direct(unsigned long ip, unsigned long addr); -int modify_ftrace_direct(unsigned long ip, unsigned long old_addr, unsigned long new_addr); -struct ftrace_direct_func *ftrace_find_direct_func(unsigned long addr); -int ftrace_modify_direct_caller(struct ftrace_func_entry *entry, - struct dyn_ftrace *rec, - unsigned long old_addr, - unsigned long new_addr); unsigned long ftrace_find_rec_direct(unsigned long ip); int register_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr); int unregister_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr, @@ -415,30 +407,6 @@ int modify_ftrace_direct_multi_nolock(struct ftrace_ops *ops, unsigned long addr #else struct ftrace_ops; # define ftrace_direct_func_count 0 -static inline int register_ftrace_direct(unsigned long ip, unsigned long addr) -{ - return -ENOTSUPP; -} -static inline int unregister_ftrace_direct(unsigned long ip, unsigned long addr) -{ - return -ENOTSUPP; -} -static inline int modify_ftrace_direct(unsigned long ip, - unsigned long old_addr, unsigned long new_addr) -{ - return -ENOTSUPP; -} -static inline struct ftrace_direct_func *ftrace_find_direct_func(unsigned long addr) -{ - return NULL; -} -static inline int ftrace_modify_direct_caller(struct ftrace_func_entry *entry, - struct dyn_ftrace *rec, - unsigned long old_addr, - unsigned long new_addr) -{ - return -ENODEV; -} static inline unsigned long ftrace_find_rec_direct(unsigned long ip) { return 0; -- cgit v1.2.3 From da8bdfbd422333fbb7c85ac1d7f18592d17d6665 Mon Sep 17 00:00:00 2001 From: Florent Revest Date: Tue, 21 Mar 2023 15:04:21 +0100 Subject: ftrace: Rename _ftrace_direct_multi APIs to _ftrace_direct APIs Now that the original _ftrace_direct APIs are gone, the "_multi" suffixes only add confusion. Link: https://lkml.kernel.org/r/20230321140424.345218-5-revest@chromium.org Signed-off-by: Florent Revest Acked-by: Mark Rutland Tested-by: Mark Rutland Acked-by: Jiri Olsa Signed-off-by: Steven Rostedt (Google) --- include/linux/ftrace.h | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 2f400c9f0787..abee60865fc7 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -398,11 +398,11 @@ struct ftrace_func_entry { #ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS extern int ftrace_direct_func_count; unsigned long ftrace_find_rec_direct(unsigned long ip); -int register_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr); -int unregister_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr, - bool free_filters); -int modify_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr); -int modify_ftrace_direct_multi_nolock(struct ftrace_ops *ops, unsigned long addr); +int register_ftrace_direct(struct ftrace_ops *ops, unsigned long addr); +int unregister_ftrace_direct(struct ftrace_ops *ops, unsigned long addr, + bool free_filters); +int modify_ftrace_direct(struct ftrace_ops *ops, unsigned long addr); +int modify_ftrace_direct_nolock(struct ftrace_ops *ops, unsigned long addr); #else struct ftrace_ops; @@ -411,20 +411,20 @@ static inline unsigned long ftrace_find_rec_direct(unsigned long ip) { return 0; } -static inline int register_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr) +static inline int register_ftrace_direct(struct ftrace_ops *ops, unsigned long addr) { return -ENODEV; } -static inline int unregister_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr, - bool free_filters) +static inline int unregister_ftrace_direct(struct ftrace_ops *ops, unsigned long addr, + bool free_filters) { return -ENODEV; } -static inline int modify_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr) +static inline int modify_ftrace_direct(struct ftrace_ops *ops, unsigned long addr) { return -ENODEV; } -static inline int modify_ftrace_direct_multi_nolock(struct ftrace_ops *ops, unsigned long addr) +static inline int modify_ftrace_direct_nolock(struct ftrace_ops *ops, unsigned long addr) { return -ENODEV; } -- cgit v1.2.3 From dbaccb618fabde8b8596e341f8d76da63a9b0c2f Mon Sep 17 00:00:00 2001 From: Florent Revest Date: Tue, 21 Mar 2023 15:04:22 +0100 Subject: ftrace: Store direct called addresses in their ops All direct calls are now registered using the register_ftrace_direct API so each ops can jump to only one direct-called trampoline. By storing the direct called trampoline address directly in the ops we can save one hashmap lookup in the direct call ops and implement arm64 direct calls on top of call ops. Link: https://lkml.kernel.org/r/20230321140424.345218-6-revest@chromium.org Signed-off-by: Florent Revest Acked-by: Jiri Olsa Signed-off-by: Steven Rostedt (Google) --- include/linux/ftrace.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index abee60865fc7..6a532dd6789e 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -321,6 +321,9 @@ struct ftrace_ops { unsigned long trampoline_size; struct list_head list; ftrace_ops_func_t ops_func; +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS + unsigned long direct_call; +#endif #endif }; -- cgit v1.2.3 From 60c8971899f3b34ad24857913c0784dab08962f0 Mon Sep 17 00:00:00 2001 From: Florent Revest Date: Tue, 21 Mar 2023 15:04:23 +0100 Subject: ftrace: Make DIRECT_CALLS work WITH_ARGS and !WITH_REGS Direct called trampolines can be called in two ways: - either from the ftrace callsite. In this case, they do not access any struct ftrace_regs nor pt_regs - Or, if a ftrace ops is also attached, from the end of a ftrace trampoline. In this case, the call_direct_funcs ops is in charge of setting the direct call trampoline's address in a struct ftrace_regs Since: commit 9705bc709604 ("ftrace: pass fregs to arch_ftrace_set_direct_caller()") The later case no longer requires a full pt_regs. It only needs a struct ftrace_regs so DIRECT_CALLS can work with both WITH_ARGS or WITH_REGS. With architectures like arm64 already abandoning WITH_REGS in favor of WITH_ARGS, it's important to have DIRECT_CALLS work WITH_ARGS only. Link: https://lkml.kernel.org/r/20230321140424.345218-7-revest@chromium.org Signed-off-by: Florent Revest Co-developed-by: Mark Rutland Signed-off-by: Mark Rutland Acked-by: Jiri Olsa Signed-off-by: Steven Rostedt (Google) --- include/linux/ftrace.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 6a532dd6789e..31f1e1df2af3 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -241,6 +241,12 @@ enum { FTRACE_OPS_FL_DIRECT = BIT(17), }; +#ifndef CONFIG_DYNAMIC_FTRACE_WITH_ARGS +#define FTRACE_OPS_FL_SAVE_ARGS FTRACE_OPS_FL_SAVE_REGS +#else +#define FTRACE_OPS_FL_SAVE_ARGS 0 +#endif + /* * FTRACE_OPS_CMD_* commands allow the ftrace core logic to request changes * to a ftrace_ops. Note, the requests may fail. -- cgit v1.2.3 From fee86a4ed536f4e521f3a4530242e152dd2a466b Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Tue, 21 Mar 2023 15:04:24 +0100 Subject: ftrace: selftest: remove broken trace_direct_tramp The ftrace selftest code has a trace_direct_tramp() function which it uses as a direct call trampoline. This happens to work on x86, since the direct call's return address is in the usual place, and can be returned to via a RET, but in general the calling convention for direct calls is different from regular function calls, and requires a trampoline written in assembly. On s390, regular function calls place the return address in %r14, and an ftrace patch-site in an instrumented function places the trampoline's return address (which is within the instrumented function) in %r0, preserving the original %r14 value in-place. As a regular C function will return to the address in %r14, using a C function as the trampoline results in the trampoline returning to the caller of the instrumented function, skipping the body of the instrumented function. Note that the s390 issue is not detcted by the ftrace selftest code, as the instrumented function is trivial, and returning back into the caller happens to be equivalent. On arm64, regular function calls place the return address in x30, and an ftrace patch-site in an instrumented function saves this into r9 and places the trampoline's return address (within the instrumented function) in x30. A regular C function will return to the address in x30, but will not restore x9 into x30. Consequently, using a C function as the trampoline results in returning to the trampoline's return address having corrupted x30, such that when the instrumented function returns, it will return back into itself. To avoid future issues in this area, remove the trace_direct_tramp() function, and require that each architecture with direct calls provides a stub trampoline, named ftrace_stub_direct_tramp. This can be written to handle the architecture's trampoline calling convention, and in future could be used elsewhere (e.g. in the ftrace ops sample, to measure the overhead of direct calls), so we may as well always build it in. Link: https://lkml.kernel.org/r/20230321140424.345218-8-revest@chromium.org Signed-off-by: Mark Rutland Cc: Li Huafei Cc: Xu Kuohai Signed-off-by: Florent Revest Acked-by: Jiri Olsa Signed-off-by: Steven Rostedt (Google) --- include/linux/ftrace.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 31f1e1df2af3..931f3d904529 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -413,6 +413,8 @@ int unregister_ftrace_direct(struct ftrace_ops *ops, unsigned long addr, int modify_ftrace_direct(struct ftrace_ops *ops, unsigned long addr); int modify_ftrace_direct_nolock(struct ftrace_ops *ops, unsigned long addr); +void ftrace_stub_direct_tramp(void); + #else struct ftrace_ops; # define ftrace_direct_func_count 0 -- cgit v1.2.3 From e11b521a7b69c2621bb2e5920bb96f6d2facdc7e Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Google)" Date: Tue, 24 Jan 2023 09:56:53 -0500 Subject: ftrace: Show a list of all functions that have ever been enabled When debugging a crash that appears to be related to ftrace, but not for sure, it is useful to know if a function was ever enabled by ftrace or not. It could be that a BPF program was attached to it, or possibly a live patch. We are having crashes in the field where this information is not always known. But having ftrace set a flag if a function has ever been attached since boot up helps tremendously in trying to know if a crash had to do with something using ftrace. For analyzing crashes, the use of a kdump image can have access to the flags. When looking at issues where the kernel did not panic, the touched_functions file can simply be used. Link: https://lore.kernel.org/linux-trace-kernel/20230124095653.6fd1640e@gandalf.local.home Cc: Masami Hiramatsu Cc: Catalin Marinas Tested-by: Mark Rutland Tested-by: Chris Li Signed-off-by: Steven Rostedt (Google) --- include/linux/ftrace.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 931f3d904529..327046f1278d 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -548,6 +548,7 @@ bool is_ftrace_trampoline(unsigned long addr); * DIRECT - there is a direct function to call * CALL_OPS - the record can use callsite-specific ops * CALL_OPS_EN - the function is set up to use callsite-specific ops + * TOUCHED - A callback was added since boot up * * When a new ftrace_ops is registered and wants a function to save * pt_regs, the rec->flags REGS is set. When the function has been @@ -567,9 +568,10 @@ enum { FTRACE_FL_DIRECT_EN = (1UL << 23), FTRACE_FL_CALL_OPS = (1UL << 22), FTRACE_FL_CALL_OPS_EN = (1UL << 21), + FTRACE_FL_TOUCHED = (1UL << 20), }; -#define FTRACE_REF_MAX_SHIFT 21 +#define FTRACE_REF_MAX_SHIFT 20 #define FTRACE_REF_MAX ((1UL << FTRACE_REF_MAX_SHIFT) - 1) #define ftrace_rec_count(rec) ((rec)->flags & FTRACE_REF_MAX) @@ -628,6 +630,7 @@ enum { FTRACE_ITER_PROBE = (1 << 4), FTRACE_ITER_MOD = (1 << 5), FTRACE_ITER_ENABLED = (1 << 6), + FTRACE_ITER_TOUCHED = (1 << 7), }; void arch_ftrace_update_code(int command); -- cgit v1.2.3 From 0f74f8b6675cc36d689abb4d9b3d75ab4049b7d7 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Sun, 19 Mar 2023 00:33:07 +0100 Subject: i3c: Make i3c_master_unregister() return void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The function returned zero unconditionally. Switch the return type to void and simplify the callers accordingly. Signed-off-by: Uwe Kleine-König Reviewed-by: Miquel Raynal Link: https://lore.kernel.org/r/20230318233311.265186-2-u.kleine-koenig@pengutronix.de Signed-off-by: Alexandre Belloni --- include/linux/i3c/master.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/i3c/master.h b/include/linux/i3c/master.h index a12cda9dc715..0b52da4f2346 100644 --- a/include/linux/i3c/master.h +++ b/include/linux/i3c/master.h @@ -542,7 +542,7 @@ int i3c_master_register(struct i3c_master_controller *master, struct device *parent, const struct i3c_master_controller_ops *ops, bool secondary); -int i3c_master_unregister(struct i3c_master_controller *master); +void i3c_master_unregister(struct i3c_master_controller *master); /** * i3c_dev_get_master_data() - get master private data attached to an I3C -- cgit v1.2.3 From fbaa38214cd9e150764ccaa82e04ecf42cc1140c Mon Sep 17 00:00:00 2001 From: Lukas Wunner Date: Sat, 11 Mar 2023 15:40:01 +0100 Subject: cxl/pci: Fix CDAT retrieval on big endian The CDAT exposed in sysfs differs between little endian and big endian arches: On big endian, every 4 bytes are byte-swapped. PCI Configuration Space is little endian (PCI r3.0 sec 6.1). Accessors such as pci_read_config_dword() implicitly swap bytes on big endian. That way, the macros in include/uapi/linux/pci_regs.h work regardless of the arch's endianness. For an example of implicit byte-swapping, see ppc4xx_pciex_read_config(), which calls in_le32(), which uses lwbrx (Load Word Byte-Reverse Indexed). DOE Read/Write Data Mailbox Registers are unlike other registers in Configuration Space in that they contain or receive a 4 byte portion of an opaque byte stream (a "Data Object" per PCIe r6.0 sec 7.9.24.5f). They need to be copied to or from the request/response buffer verbatim. So amend pci_doe_send_req() and pci_doe_recv_resp() to undo the implicit byte-swapping. The CXL_DOE_TABLE_ACCESS_* and PCI_DOE_DATA_OBJECT_DISC_* macros assume implicit byte-swapping. Byte-swap requests after constructing them with those macros and byte-swap responses before parsing them. Change the request and response type to __le32 to avoid sparse warnings. Per a request from Jonathan, replace sizeof(u32) with sizeof(__le32) for consistency. Fixes: c97006046c79 ("cxl/port: Read CDAT table") Tested-by: Ira Weiny Signed-off-by: Lukas Wunner Reviewed-by: Dan Williams Cc: stable@vger.kernel.org # v6.0+ Reviewed-by: Jonathan Cameron Link: https://lore.kernel.org/r/3051114102f41d19df3debbee123129118fc5e6d.1678543498.git.lukas@wunner.de Signed-off-by: Dan Williams --- include/linux/pci-doe.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci-doe.h b/include/linux/pci-doe.h index ed9b4df792b8..43765eaf2342 100644 --- a/include/linux/pci-doe.h +++ b/include/linux/pci-doe.h @@ -34,6 +34,10 @@ struct pci_doe_mb; * @work: Used internally by the mailbox * @doe_mb: Used internally by the mailbox * + * Payloads are treated as opaque byte streams which are transmitted verbatim, + * without byte-swapping. If payloads contain little-endian register values, + * the caller is responsible for conversion with cpu_to_le32() / le32_to_cpu(). + * * The payload sizes and rv are specified in bytes with the following * restrictions concerning the protocol. * @@ -45,9 +49,9 @@ struct pci_doe_mb; */ struct pci_doe_task { struct pci_doe_protocol prot; - u32 *request_pl; + __le32 *request_pl; size_t request_pl_sz; - u32 *response_pl; + __le32 *response_pl; size_t response_pl_sz; int rv; void (*complete)(struct pci_doe_task *task); -- cgit v1.2.3 From fe602c87df1b6927562f4ee61edd851bb9578a49 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 21 Mar 2023 04:01:15 +0000 Subject: net: remove rcu_dereference_bh_rtnl() This helper is no longer used in the tree. Signed-off-by: Eric Dumazet Signed-off-by: Jakub Kicinski --- include/linux/rtnetlink.h | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index 92ad75549e9c..f0c87baaf6c0 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -61,16 +61,6 @@ static inline bool lockdep_rtnl_is_held(void) #define rcu_dereference_rtnl(p) \ rcu_dereference_check(p, lockdep_rtnl_is_held()) -/** - * rcu_dereference_bh_rtnl - rcu_dereference_bh with debug checking - * @p: The pointer to read, prior to dereference - * - * Do an rcu_dereference_bh(p), but check caller either holds rcu_read_lock_bh() - * or RTNL. Note : Please prefer rtnl_dereference() or rcu_dereference_bh() - */ -#define rcu_dereference_bh_rtnl(p) \ - rcu_dereference_bh_check(p, lockdep_rtnl_is_held()) - /** * rtnl_dereference - fetch RCU pointer when updates are prevented by RTNL * @p: The pointer to read, prior to dereferencing -- cgit v1.2.3 From e3ff7c609f39671d1aaff4fb4a8594e14f3e03f8 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Fri, 24 Feb 2023 08:50:00 -0800 Subject: livepatch,sched: Add livepatch task switching to cond_resched() There have been reports [1][2] of live patches failing to complete within a reasonable amount of time due to CPU-bound kthreads. Fix it by patching tasks in cond_resched(). There are four different flavors of cond_resched(), depending on the kernel configuration. Hook into all of them. A more elegant solution might be to use a preempt notifier. However, non-ORC unwinders can't unwind a preempted task reliably. [1] https://lore.kernel.org/lkml/20220507174628.2086373-1-song@kernel.org/ [2] https://lkml.kernel.org/lkml/20230120-vhost-klp-switching-v1-0-7c2b65519c43@kernel.org Signed-off-by: Josh Poimboeuf Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Petr Mladek Tested-by: Seth Forshee (DigitalOcean) Link: https://lore.kernel.org/r/4ae981466b7814ec221014fc2554b2f86f3fb70b.1677257135.git.jpoimboe@kernel.org --- include/linux/livepatch.h | 1 + include/linux/livepatch_sched.h | 29 +++++++++++++++++++++++++++++ include/linux/sched.h | 20 +++++++++++++++----- 3 files changed, 45 insertions(+), 5 deletions(-) create mode 100644 include/linux/livepatch_sched.h (limited to 'include/linux') diff --git a/include/linux/livepatch.h b/include/linux/livepatch.h index 293e29960c6e..9b9b38e89563 100644 --- a/include/linux/livepatch.h +++ b/include/linux/livepatch.h @@ -13,6 +13,7 @@ #include #include #include +#include #if IS_ENABLED(CONFIG_LIVEPATCH) diff --git a/include/linux/livepatch_sched.h b/include/linux/livepatch_sched.h new file mode 100644 index 000000000000..013794fb5da0 --- /dev/null +++ b/include/linux/livepatch_sched.h @@ -0,0 +1,29 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +#ifndef _LINUX_LIVEPATCH_SCHED_H_ +#define _LINUX_LIVEPATCH_SCHED_H_ + +#include +#include + +#ifdef CONFIG_LIVEPATCH + +void __klp_sched_try_switch(void); + +#if !defined(CONFIG_PREEMPT_DYNAMIC) || !defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL) + +DECLARE_STATIC_KEY_FALSE(klp_sched_try_switch_key); + +static __always_inline void klp_sched_try_switch(void) +{ + if (static_branch_unlikely(&klp_sched_try_switch_key)) + __klp_sched_try_switch(); +} + +#endif /* !CONFIG_PREEMPT_DYNAMIC || !CONFIG_HAVE_PREEMPT_DYNAMIC_CALL */ + +#else /* !CONFIG_LIVEPATCH */ +static inline void klp_sched_try_switch(void) {} +static inline void __klp_sched_try_switch(void) {} +#endif /* CONFIG_LIVEPATCH */ + +#endif /* _LINUX_LIVEPATCH_SCHED_H_ */ diff --git a/include/linux/sched.h b/include/linux/sched.h index 63d242164b1a..6d654eb4cabd 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -36,6 +36,7 @@ #include #include #include +#include #include /* task_struct member predeclarations (sorted alphabetically): */ @@ -2070,6 +2071,9 @@ extern int __cond_resched(void); #if defined(CONFIG_PREEMPT_DYNAMIC) && defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL) +void sched_dynamic_klp_enable(void); +void sched_dynamic_klp_disable(void); + DECLARE_STATIC_CALL(cond_resched, __cond_resched); static __always_inline int _cond_resched(void) @@ -2078,6 +2082,7 @@ static __always_inline int _cond_resched(void) } #elif defined(CONFIG_PREEMPT_DYNAMIC) && defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY) + extern int dynamic_cond_resched(void); static __always_inline int _cond_resched(void) @@ -2085,20 +2090,25 @@ static __always_inline int _cond_resched(void) return dynamic_cond_resched(); } -#else +#else /* !CONFIG_PREEMPTION */ static inline int _cond_resched(void) { + klp_sched_try_switch(); return __cond_resched(); } -#endif /* CONFIG_PREEMPT_DYNAMIC */ +#endif /* PREEMPT_DYNAMIC && CONFIG_HAVE_PREEMPT_DYNAMIC_CALL */ -#else +#else /* CONFIG_PREEMPTION && !CONFIG_PREEMPT_DYNAMIC */ -static inline int _cond_resched(void) { return 0; } +static inline int _cond_resched(void) +{ + klp_sched_try_switch(); + return 0; +} -#endif /* !defined(CONFIG_PREEMPTION) || defined(CONFIG_PREEMPT_DYNAMIC) */ +#endif /* !CONFIG_PREEMPTION || CONFIG_PREEMPT_DYNAMIC */ #define cond_resched() ({ \ __might_resched(__FILE__, __LINE__, 0); \ -- cgit v1.2.3 From d7ba4cc900bf1eea2d8c807c6b1fc6bd61f41237 Mon Sep 17 00:00:00 2001 From: JP Kobryn Date: Wed, 22 Mar 2023 12:47:54 -0700 Subject: bpf: return long from bpf_map_ops funcs This patch changes the return types of bpf_map_ops functions to long, where previously int was returned. Using long allows for bpf programs to maintain the sign bit in the absence of sign extension during situations where inlined bpf helper funcs make calls to the bpf_map_ops funcs and a negative error is returned. The definitions of the helper funcs are generated from comments in the bpf uapi header at `include/uapi/linux/bpf.h`. The return type of these helpers was previously changed from int to long in commit bdb7b79b4ce8. For any case where one of the map helpers call the bpf_map_ops funcs that are still returning 32-bit int, a compiler might not include sign extension instructions to properly convert the 32-bit negative value a 64-bit negative value. For example: bpf assembly excerpt of an inlined helper calling a kernel function and checking for a specific error: ; err = bpf_map_update_elem(&mymap, &key, &val, BPF_NOEXIST); ... 46: call 0xffffffffe103291c ; htab_map_update_elem ; if (err && err != -EEXIST) { 4b: cmp $0xffffffffffffffef,%rax ; cmp -EEXIST,%rax kernel function assembly excerpt of return value from `htab_map_update_elem` returning 32-bit int: movl $0xffffffef, %r9d ... movl %r9d, %eax ...results in the comparison: cmp $0xffffffffffffffef, $0x00000000ffffffef Fixes: bdb7b79b4ce8 ("bpf: Switch most helper return values from 32-bit int to 64-bit long") Tested-by: Eduard Zingerman Signed-off-by: JP Kobryn Link: https://lore.kernel.org/r/20230322194754.185781-3-inwardvessel@gmail.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 14 +++++++------- include/linux/filter.h | 6 +++--- 2 files changed, 10 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 3ef98fb92987..ec0df059f562 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -96,11 +96,11 @@ struct bpf_map_ops { /* funcs callable from userspace and from eBPF programs */ void *(*map_lookup_elem)(struct bpf_map *map, void *key); - int (*map_update_elem)(struct bpf_map *map, void *key, void *value, u64 flags); - int (*map_delete_elem)(struct bpf_map *map, void *key); - int (*map_push_elem)(struct bpf_map *map, void *value, u64 flags); - int (*map_pop_elem)(struct bpf_map *map, void *value); - int (*map_peek_elem)(struct bpf_map *map, void *value); + long (*map_update_elem)(struct bpf_map *map, void *key, void *value, u64 flags); + long (*map_delete_elem)(struct bpf_map *map, void *key); + long (*map_push_elem)(struct bpf_map *map, void *value, u64 flags); + long (*map_pop_elem)(struct bpf_map *map, void *value); + long (*map_peek_elem)(struct bpf_map *map, void *value); void *(*map_lookup_percpu_elem)(struct bpf_map *map, void *key, u32 cpu); /* funcs called by prog_array and perf_event_array map */ @@ -139,7 +139,7 @@ struct bpf_map_ops { struct bpf_local_storage __rcu ** (*map_owner_storage_ptr)(void *owner); /* Misc helpers.*/ - int (*map_redirect)(struct bpf_map *map, u64 key, u64 flags); + long (*map_redirect)(struct bpf_map *map, u64 key, u64 flags); /* map_meta_equal must be implemented for maps that can be * used as an inner map. It is a runtime check to ensure @@ -157,7 +157,7 @@ struct bpf_map_ops { int (*map_set_for_each_callback_args)(struct bpf_verifier_env *env, struct bpf_func_state *caller, struct bpf_func_state *callee); - int (*map_for_each_callback)(struct bpf_map *map, + long (*map_for_each_callback)(struct bpf_map *map, bpf_callback_t callback_fn, void *callback_ctx, u64 flags); diff --git a/include/linux/filter.h b/include/linux/filter.h index efa5d4a1677e..23c08c31bea9 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -1504,9 +1504,9 @@ static inline bool bpf_sk_lookup_run_v6(struct net *net, int protocol, } #endif /* IS_ENABLED(CONFIG_IPV6) */ -static __always_inline int __bpf_xdp_redirect_map(struct bpf_map *map, u64 index, - u64 flags, const u64 flag_mask, - void *lookup_elem(struct bpf_map *map, u32 key)) +static __always_inline long __bpf_xdp_redirect_map(struct bpf_map *map, u64 index, + u64 flags, const u64 flag_mask, + void *lookup_elem(struct bpf_map *map, u32 key)) { struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); const u64 action_mask = XDP_ABORTED | XDP_DROP | XDP_PASS | XDP_TX; -- cgit v1.2.3 From e02c625de580a1bc8166c5f95f23a50fa59ee1bf Mon Sep 17 00:00:00 2001 From: Ondrej Zary Date: Sat, 18 Feb 2023 23:01:23 +0100 Subject: ata: pata_parport: Remove pi_swab16 and pi_swab32 Convert comm and kbic drivers to use standard swab16. Remove pi_swab16 and pi_swab32. Reviewed-by: Sergey Shtylyov Signed-off-by: Ondrej Zary Signed-off-by: Damien Le Moal --- include/linux/pata_parport.h | 17 ----------------- 1 file changed, 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pata_parport.h b/include/linux/pata_parport.h index 58781846f282..458544fe5e6c 100644 --- a/include/linux/pata_parport.h +++ b/include/linux/pata_parport.h @@ -54,23 +54,6 @@ typedef struct pi_adapter PIA; /* for paride protocol modules */ #define r4w() (delay_p, inw(pi->port + 4)) #define r4l() (delay_p, inl(pi->port + 4)) -static inline u16 pi_swab16(char *b, int k) -{ - union { u16 u; char t[2]; } r; - - r.t[0] = b[2 * k + 1]; r.t[1] = b[2 * k]; - return r.u; -} - -static inline u32 pi_swab32(char *b, int k) -{ - union { u32 u; char f[4]; } r; - - r.f[0] = b[4 * k + 1]; r.f[1] = b[4 * k]; - r.f[2] = b[4 * k + 3]; r.f[3] = b[4 * k + 2]; - return r.u; -} - struct pi_protocol { char name[8]; -- cgit v1.2.3 From 2c08ec0f06a6ac71b78e26f82a88093094d70dc4 Mon Sep 17 00:00:00 2001 From: Ondrej Zary Date: Sat, 18 Feb 2023 23:01:25 +0100 Subject: ata: pata_parport: Introduce module_pata_parport_driver macro Introduce module_pata_parport_driver macro and use it in protocol drivers to reduce boilerplate code. Remove paride_(un)register compatibility defines. Reviewed-by: Sergey Shtylyov Signed-off-by: Ondrej Zary Signed-off-by: Damien Le Moal --- include/linux/pata_parport.h | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pata_parport.h b/include/linux/pata_parport.h index 458544fe5e6c..9614ce53470a 100644 --- a/include/linux/pata_parport.h +++ b/include/linux/pata_parport.h @@ -87,8 +87,16 @@ struct pi_protocol { int pata_parport_register_driver(struct pi_protocol *pr); void pata_parport_unregister_driver(struct pi_protocol *pr); -/* defines for old paride protocol modules */ -#define paride_register pata_parport_register_driver -#define paride_unregister pata_parport_unregister_driver + +/** + * module_pata_parport_driver() - Helper macro for registering a pata_parport driver + * @__pi_protocol: pi_protocol struct + * + * Helper macro for pata_parport drivers which do not do anything special in module + * init/exit. This eliminates a lot of boilerplate. Each module may only + * use this macro once, and calling it replaces module_init() and module_exit() + */ +#define module_pata_parport_driver(__pi_protocol) \ + module_driver(__pi_protocol, pata_parport_register_driver, pata_parport_unregister_driver) #endif /* LINUX_PATA_PARPORT_H */ -- cgit v1.2.3 From ec6e7a51d9eb1cd27840f7d8d5d05328631c9a15 Mon Sep 17 00:00:00 2001 From: Ondrej Zary Date: Sat, 18 Feb 2023 23:01:26 +0100 Subject: ata: pata_parport: remove devtype from struct pi_adapter Only bpck driver uses devtype but it never gets set in pata_parport. Remove it. As most bpck devices are CD-ROMs, always run the code that depends on devtype == PI_PCD. Reviewed-by: Sergey Shtylyov Signed-off-by: Ondrej Zary Signed-off-by: Damien Le Moal --- include/linux/pata_parport.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pata_parport.h b/include/linux/pata_parport.h index 9614ce53470a..3fc6b002c7c8 100644 --- a/include/linux/pata_parport.h +++ b/include/linux/pata_parport.h @@ -11,15 +11,12 @@ #include -#define PI_PCD 1 /* dummy for paride protocol modules */ - struct pi_adapter { struct device dev; struct pi_protocol *proto; /* adapter protocol */ int port; /* base address of parallel port */ int mode; /* transfer mode in use */ int delay; /* adapter delay setting */ - int devtype; /* dummy for paride protocol modules */ char *device; /* dummy for paride protocol modules */ int unit; /* unit number for chained adapters */ int saved_r0; /* saved port state */ -- cgit v1.2.3 From a4f2ff92ed4a0305920a46aba0ae8d50139548c0 Mon Sep 17 00:00:00 2001 From: Ondrej Zary Date: Sat, 18 Feb 2023 23:01:27 +0100 Subject: ata: pata_parport: remove device from struct pi_adapter device is never set in pata_parport, remove it. Reviewed-by: Sergey Shtylyov Signed-off-by: Ondrej Zary Signed-off-by: Damien Le Moal --- include/linux/pata_parport.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pata_parport.h b/include/linux/pata_parport.h index 3fc6b002c7c8..dcab769aa639 100644 --- a/include/linux/pata_parport.h +++ b/include/linux/pata_parport.h @@ -17,7 +17,6 @@ struct pi_adapter { int port; /* base address of parallel port */ int mode; /* transfer mode in use */ int delay; /* adapter delay setting */ - char *device; /* dummy for paride protocol modules */ int unit; /* unit number for chained adapters */ int saved_r0; /* saved port state */ int saved_r2; /* saved port state */ -- cgit v1.2.3 From 882ff0ca354ada5f52e26d74039b2210b3070dcc Mon Sep 17 00:00:00 2001 From: Ondrej Zary Date: Sat, 18 Feb 2023 23:01:28 +0100 Subject: ata: pata_parport: remove typedef struct PIA Remove typedef struct PIA and use struct pi_adapter directly. Fix formatting (excessive spaces) while at it. Reviewed-by: Sergey Shtylyov Signed-off-by: Ondrej Zary Signed-off-by: Damien Le Moal --- include/linux/pata_parport.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pata_parport.h b/include/linux/pata_parport.h index dcab769aa639..381b4d0e3574 100644 --- a/include/linux/pata_parport.h +++ b/include/linux/pata_parport.h @@ -24,8 +24,6 @@ struct pi_adapter { struct pardevice *pardev; /* pointer to pardevice */ }; -typedef struct pi_adapter PIA; /* for paride protocol modules */ - /* registers are addressed as (cont,regr) * cont: 0 for command register file, 1 for control register(s) * regr: 0-7 for register number. -- cgit v1.2.3 From 3a7474ba54ef29233af3de8b1f97ec006c2f902a Mon Sep 17 00:00:00 2001 From: Ondrej Zary Date: Sat, 18 Feb 2023 23:01:29 +0100 Subject: ata: pata_parport: remove verbose parameter from log_adapter() verbose parameter of log_adapter() is unused, remove it. Reviewed-by: Sergey Shtylyov Signed-off-by: Ondrej Zary Signed-off-by: Damien Le Moal --- include/linux/pata_parport.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pata_parport.h b/include/linux/pata_parport.h index 381b4d0e3574..033cabede51c 100644 --- a/include/linux/pata_parport.h +++ b/include/linux/pata_parport.h @@ -68,7 +68,7 @@ struct pi_protocol { int (*test_port)(struct pi_adapter *pi); int (*probe_unit)(struct pi_adapter *pi); int (*test_proto)(struct pi_adapter *pi, char *scratch, int verbose); - void (*log_adapter)(struct pi_adapter *pi, char *scratch, int verbose); + void (*log_adapter)(struct pi_adapter *pi, char *scratch); int (*init_proto)(struct pi_adapter *pi); void (*release_proto)(struct pi_adapter *pi); -- cgit v1.2.3 From 5b77db9ccff444ddd3755e43b7bfa8782a5ac125 Mon Sep 17 00:00:00 2001 From: Ondrej Zary Date: Sat, 18 Feb 2023 23:01:30 +0100 Subject: ata: pata_parport: remove scratch parameter from log_adapter() scratch parameter of log_adapter() is only used by bpck driver. Remove it. Reviewed-by: Sergey Shtylyov Signed-off-by: Ondrej Zary Signed-off-by: Damien Le Moal --- include/linux/pata_parport.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pata_parport.h b/include/linux/pata_parport.h index 033cabede51c..c44d30b3e886 100644 --- a/include/linux/pata_parport.h +++ b/include/linux/pata_parport.h @@ -68,7 +68,7 @@ struct pi_protocol { int (*test_port)(struct pi_adapter *pi); int (*probe_unit)(struct pi_adapter *pi); int (*test_proto)(struct pi_adapter *pi, char *scratch, int verbose); - void (*log_adapter)(struct pi_adapter *pi, char *scratch); + void (*log_adapter)(struct pi_adapter *pi); int (*init_proto)(struct pi_adapter *pi); void (*release_proto)(struct pi_adapter *pi); -- cgit v1.2.3 From 8d7494a06a14ce8e2d792b95f28c839367a8ebdc Mon Sep 17 00:00:00 2001 From: Ondrej Zary Date: Sat, 18 Feb 2023 23:01:35 +0100 Subject: ata: pata_parport: remove verbose parameter from test_proto() verbose parameter of test_proto() is now unused, remove it. Reviewed-by: Sergey Shtylyov Signed-off-by: Ondrej Zary Signed-off-by: Damien Le Moal --- include/linux/pata_parport.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pata_parport.h b/include/linux/pata_parport.h index c44d30b3e886..e45bb1896003 100644 --- a/include/linux/pata_parport.h +++ b/include/linux/pata_parport.h @@ -67,7 +67,7 @@ struct pi_protocol { int (*test_port)(struct pi_adapter *pi); int (*probe_unit)(struct pi_adapter *pi); - int (*test_proto)(struct pi_adapter *pi, char *scratch, int verbose); + int (*test_proto)(struct pi_adapter *pi, char *scratch); void (*log_adapter)(struct pi_adapter *pi); int (*init_proto)(struct pi_adapter *pi); -- cgit v1.2.3 From b42251a867a9859a57228c0eadd6f342a339b83d Mon Sep 17 00:00:00 2001 From: Ondrej Zary Date: Sat, 18 Feb 2023 23:01:36 +0100 Subject: ata: pata_parport: remove scratch parameter from test_proto() Don't pass around a pointer to scratch buffer. Use local buffers in protocols that need it. Reviewed-by: Sergey Shtylyov Signed-off-by: Ondrej Zary Signed-off-by: Damien Le Moal --- include/linux/pata_parport.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pata_parport.h b/include/linux/pata_parport.h index e45bb1896003..bbfa4e63ee85 100644 --- a/include/linux/pata_parport.h +++ b/include/linux/pata_parport.h @@ -67,7 +67,7 @@ struct pi_protocol { int (*test_port)(struct pi_adapter *pi); int (*probe_unit)(struct pi_adapter *pi); - int (*test_proto)(struct pi_adapter *pi, char *scratch); + int (*test_proto)(struct pi_adapter *pi); void (*log_adapter)(struct pi_adapter *pi); int (*init_proto)(struct pi_adapter *pi); -- cgit v1.2.3 From fe027ff984c61f4ac5e79823fef30ced4f46d23d Mon Sep 17 00:00:00 2001 From: Ondrej Zary Date: Sat, 18 Feb 2023 23:01:38 +0100 Subject: ata: pata_parport: move pata_parport.h to drivers/ata/pata_parport Now that paride is gone, pata_parport.h does not need to be in include/linux. Move it to drivers/ata/pata_parport. Reviewed-by: Sergey Shtylyov Signed-off-by: Ondrej Zary Signed-off-by: Damien Le Moal --- include/linux/pata_parport.h | 96 -------------------------------------------- 1 file changed, 96 deletions(-) delete mode 100644 include/linux/pata_parport.h (limited to 'include/linux') diff --git a/include/linux/pata_parport.h b/include/linux/pata_parport.h deleted file mode 100644 index bbfa4e63ee85..000000000000 --- a/include/linux/pata_parport.h +++ /dev/null @@ -1,96 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * pata_parport.h (c) 1997-8 Grant R. Guenther - * Under the terms of the GPL. - * - * This file defines the interface for parallel port IDE adapter chip drivers. - */ - -#ifndef LINUX_PATA_PARPORT_H -#define LINUX_PATA_PARPORT_H - -#include - -struct pi_adapter { - struct device dev; - struct pi_protocol *proto; /* adapter protocol */ - int port; /* base address of parallel port */ - int mode; /* transfer mode in use */ - int delay; /* adapter delay setting */ - int unit; /* unit number for chained adapters */ - int saved_r0; /* saved port state */ - int saved_r2; /* saved port state */ - unsigned long private; /* for protocol module */ - struct pardevice *pardev; /* pointer to pardevice */ -}; - -/* registers are addressed as (cont,regr) - * cont: 0 for command register file, 1 for control register(s) - * regr: 0-7 for register number. - */ - -/* macros and functions exported to the protocol modules */ -#define delay_p (pi->delay ? udelay(pi->delay) : (void)0) -#define out_p(offs, byte) do { outb(byte, pi->port + offs); delay_p; } while (0) -#define in_p(offs) (delay_p, inb(pi->port + offs)) - -#define w0(byte) out_p(0, byte) -#define r0() in_p(0) -#define w1(byte) out_p(1, byte) -#define r1() in_p(1) -#define w2(byte) out_p(2, byte) -#define r2() in_p(2) -#define w3(byte) out_p(3, byte) -#define w4(byte) out_p(4, byte) -#define r4() in_p(4) -#define w4w(data) do { outw(data, pi->port + 4); delay_p; } while (0) -#define w4l(data) do { outl(data, pi->port + 4); delay_p; } while (0) -#define r4w() (delay_p, inw(pi->port + 4)) -#define r4l() (delay_p, inl(pi->port + 4)) - -struct pi_protocol { - char name[8]; - - int max_mode; - int epp_first; /* modes >= this use 8 ports */ - - int default_delay; - int max_units; /* max chained units probed for */ - - void (*write_regr)(struct pi_adapter *pi, int cont, int regr, int val); - int (*read_regr)(struct pi_adapter *pi, int cont, int regr); - void (*write_block)(struct pi_adapter *pi, char *buf, int count); - void (*read_block)(struct pi_adapter *pi, char *buf, int count); - - void (*connect)(struct pi_adapter *pi); - void (*disconnect)(struct pi_adapter *pi); - - int (*test_port)(struct pi_adapter *pi); - int (*probe_unit)(struct pi_adapter *pi); - int (*test_proto)(struct pi_adapter *pi); - void (*log_adapter)(struct pi_adapter *pi); - - int (*init_proto)(struct pi_adapter *pi); - void (*release_proto)(struct pi_adapter *pi); - struct module *owner; - struct device_driver driver; - struct scsi_host_template sht; -}; - -#define PATA_PARPORT_SHT ATA_PIO_SHT - -int pata_parport_register_driver(struct pi_protocol *pr); -void pata_parport_unregister_driver(struct pi_protocol *pr); - -/** - * module_pata_parport_driver() - Helper macro for registering a pata_parport driver - * @__pi_protocol: pi_protocol struct - * - * Helper macro for pata_parport drivers which do not do anything special in module - * init/exit. This eliminates a lot of boilerplate. Each module may only - * use this macro once, and calling it replaces module_init() and module_exit() - */ -#define module_pata_parport_driver(__pi_protocol) \ - module_driver(__pi_protocol, pata_parport_register_driver, pata_parport_unregister_driver) - -#endif /* LINUX_PATA_PARPORT_H */ -- cgit v1.2.3 From 8d857540f517501d34e5810a369707a8181d1bbf Mon Sep 17 00:00:00 2001 From: Sergey Shtylyov Date: Fri, 24 Feb 2023 23:40:23 +0300 Subject: ata: drop unused ata_id_to_hd_driveid() This function was renamed from ide_id_to_hd_driveid() and moved from drivers/ide/ to but it never got used by libata, thus it became useless after drivers/ide/ removal... Signed-off-by: Sergey Shtylyov Signed-off-by: Damien Le Moal --- include/linux/ata.h | 21 --------------------- 1 file changed, 21 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ata.h b/include/linux/ata.h index 0c18499f60b6..3240116647d5 100644 --- a/include/linux/ata.h +++ b/include/linux/ata.h @@ -16,7 +16,6 @@ #include #include #include -#include /* defines only for the constants which don't work well as enums */ #define ATA_DMA_BOUNDARY 0xffffUL @@ -1067,26 +1066,6 @@ static inline bool ata_id_is_lba_capacity_ok(u16 *id) return false; /* LBA capacity value may be bad */ } -static inline void ata_id_to_hd_driveid(u16 *id) -{ -#ifdef __BIG_ENDIAN - /* accessed in struct hd_driveid as 8-bit values */ - id[ATA_ID_MAX_MULTSECT] = __cpu_to_le16(id[ATA_ID_MAX_MULTSECT]); - id[ATA_ID_CAPABILITY] = __cpu_to_le16(id[ATA_ID_CAPABILITY]); - id[ATA_ID_OLD_PIO_MODES] = __cpu_to_le16(id[ATA_ID_OLD_PIO_MODES]); - id[ATA_ID_OLD_DMA_MODES] = __cpu_to_le16(id[ATA_ID_OLD_DMA_MODES]); - id[ATA_ID_MULTSECT] = __cpu_to_le16(id[ATA_ID_MULTSECT]); - - /* as 32-bit values */ - *(u32 *)&id[ATA_ID_LBA_CAPACITY] = ata_id_u32(id, ATA_ID_LBA_CAPACITY); - *(u32 *)&id[ATA_ID_SPG] = ata_id_u32(id, ATA_ID_SPG); - - /* as 64-bit value */ - *(u64 *)&id[ATA_ID_LBA_CAPACITY_2] = - ata_id_u64(id, ATA_ID_LBA_CAPACITY_2); -#endif -} - static inline bool ata_ok(u8 status) { return ((status & (ATA_BUSY | ATA_DRDY | ATA_DF | ATA_DRQ | ATA_ERR)) -- cgit v1.2.3 From dc2e107e2d48ebe629985a080d457896ccf18f84 Mon Sep 17 00:00:00 2001 From: Sergey Shtylyov Date: Fri, 24 Feb 2023 23:40:24 +0300 Subject: ata: drop unused ata_id_is_lba_capacity_ok() This function was renamed from lba_capacity_is_ok()() and moved from drivers/ide/ to but it never got used by libata, thus it became useless after drivers/ide/ removal... Signed-off-by: Sergey Shtylyov Signed-off-by: Damien Le Moal --- include/linux/ata.h | 50 -------------------------------------------------- 1 file changed, 50 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ata.h b/include/linux/ata.h index 3240116647d5..c224dbddb9b2 100644 --- a/include/linux/ata.h +++ b/include/linux/ata.h @@ -1016,56 +1016,6 @@ static inline bool atapi_id_dmadir(const u16 *dev_id) return ata_id_major_version(dev_id) >= 7 && (dev_id[62] & 0x8000); } -/* - * ata_id_is_lba_capacity_ok() performs a sanity check on - * the claimed LBA capacity value for the device. - * - * Returns 1 if LBA capacity looks sensible, 0 otherwise. - * - * It is called only once for each device. - */ -static inline bool ata_id_is_lba_capacity_ok(u16 *id) -{ - unsigned long lba_sects, chs_sects, head, tail; - - /* No non-LBA info .. so valid! */ - if (id[ATA_ID_CYLS] == 0) - return true; - - lba_sects = ata_id_u32(id, ATA_ID_LBA_CAPACITY); - - /* - * The ATA spec tells large drives to return - * C/H/S = 16383/16/63 independent of their size. - * Some drives can be jumpered to use 15 heads instead of 16. - * Some drives can be jumpered to use 4092 cyls instead of 16383. - */ - if ((id[ATA_ID_CYLS] == 16383 || - (id[ATA_ID_CYLS] == 4092 && id[ATA_ID_CUR_CYLS] == 16383)) && - id[ATA_ID_SECTORS] == 63 && - (id[ATA_ID_HEADS] == 15 || id[ATA_ID_HEADS] == 16) && - (lba_sects >= 16383 * 63 * id[ATA_ID_HEADS])) - return true; - - chs_sects = id[ATA_ID_CYLS] * id[ATA_ID_HEADS] * id[ATA_ID_SECTORS]; - - /* perform a rough sanity check on lba_sects: within 10% is OK */ - if (lba_sects - chs_sects < chs_sects/10) - return true; - - /* some drives have the word order reversed */ - head = (lba_sects >> 16) & 0xffff; - tail = lba_sects & 0xffff; - lba_sects = head | (tail << 16); - - if (lba_sects - chs_sects < chs_sects/10) { - *(__le32 *)&id[ATA_ID_LBA_CAPACITY] = __cpu_to_le32(lba_sects); - return true; /* LBA capacity is (now) good */ - } - - return false; /* LBA capacity value may be bad */ -} - static inline bool ata_ok(u8 status) { return ((status & (ATA_BUSY | ATA_DRDY | ATA_DF | ATA_DRQ | ATA_ERR)) -- cgit v1.2.3 From 1cc6571f562774f1d928dc8b3cff50829b86e970 Mon Sep 17 00:00:00 2001 From: Nick Child Date: Tue, 21 Mar 2023 10:07:25 -0500 Subject: netdev: Enforce index cap in netdev_get_tx_queue When requesting a TX queue at a given index, warn on out-of-bounds referencing if the index is greater than the allocated number of queues. Specifically, since this function is used heavily in the networking stack use DEBUG_NET_WARN_ON_ONCE to avoid executing a new branch on every packet. Signed-off-by: Nick Child Link: https://lore.kernel.org/r/20230321150725.127229-2-nnac123@linux.ibm.com Signed-off-by: Jakub Kicinski --- include/linux/netdevice.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 7621c512765f..674ee5daa7b1 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2484,6 +2484,7 @@ static inline struct netdev_queue *netdev_get_tx_queue(const struct net_device *dev, unsigned int index) { + DEBUG_NET_WARN_ON_ONCE(index >= dev->num_tx_queues); return &dev->_tx[index]; } -- cgit v1.2.3 From 4ee9b0dcf09f426fbad7ed132d73ea2ba379d8ee Mon Sep 17 00:00:00 2001 From: "Russell King (Oracle)" Date: Tue, 21 Mar 2023 15:58:54 +0000 Subject: net: phylink: remove an_enabled The Autoneg bit in the advertising bitmap and state->an_enabled are always identical. state->an_enabled is now no longer used by any drivers, so lets kill this duplication. Signed-off-by: Russell King (Oracle) Reviewed-by: Simon Horman Signed-off-by: Jakub Kicinski --- include/linux/phylink.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/phylink.h b/include/linux/phylink.h index c492c26202b5..9ff56b050584 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -93,7 +93,6 @@ static inline bool phylink_autoneg_inband(unsigned int mode) * the medium link mode (@speed and @duplex) and the speed/duplex of the phy * interface mode (@interface) are different. * @link: true if the link is up. - * @an_enabled: true if autonegotiation is enabled/desired. * @an_complete: true if autonegotiation has completed. */ struct phylink_link_state { @@ -105,7 +104,6 @@ struct phylink_link_state { int pause; int rate_matching; unsigned int link:1; - unsigned int an_enabled:1; unsigned int an_complete:1; }; -- cgit v1.2.3 From b671c2067a04c0668df174ff5dfdb573d1f9b074 Mon Sep 17 00:00:00 2001 From: Kui-Feng Lee Date: Wed, 22 Mar 2023 20:23:58 -0700 Subject: bpf: Retire the struct_ops map kvalue->refcnt. We have replaced kvalue-refcnt with synchronize_rcu() to wait for an RCU grace period. Maintenance of kvalue->refcnt was a complicated task, as we had to simultaneously keep track of two reference counts: one for the reference count of bpf_map. When the kvalue->refcnt reaches zero, we also have to reduce the reference count on bpf_map - yet these steps are not performed in an atomic manner and require us to be vigilant when managing them. By eliminating kvalue->refcnt, we can make our maintenance more straightforward as the refcount of bpf_map is now solely managed! To prevent the trampoline image of a struct_ops from being released while it is still in use, we wait for an RCU grace period. The setsockopt(TCP_CONGESTION, "...") command allows you to change your socket's congestion control algorithm and can result in releasing the old struct_ops implementation. It is fine. However, this function is exposed through bpf_setsockopt(), it may be accessed by BPF programs as well. To ensure that the trampoline image belonging to struct_op can be safely called while its method is in use, the trampoline safeguarde the BPF program with rcu_read_lock(). Doing so prevents any destruction of the associated images before returning from a trampoline and requires us to wait for an RCU grace period. Signed-off-by: Kui-Feng Lee Link: https://lore.kernel.org/r/20230323032405.3735486-2-kuifeng@meta.com Signed-off-by: Martin KaFai Lau --- include/linux/bpf.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index ec0df059f562..f04098468d7a 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1945,6 +1945,7 @@ struct bpf_map *bpf_map_get_with_uref(u32 ufd); struct bpf_map *__bpf_map_get(struct fd f); void bpf_map_inc(struct bpf_map *map); void bpf_map_inc_with_uref(struct bpf_map *map); +struct bpf_map *__bpf_map_inc_not_zero(struct bpf_map *map, bool uref); struct bpf_map * __must_check bpf_map_inc_not_zero(struct bpf_map *map); void bpf_map_put_with_uref(struct bpf_map *map); void bpf_map_put(struct bpf_map *map); -- cgit v1.2.3 From 68b04864ca425d1894c96b8141d4fba1181f11cb Mon Sep 17 00:00:00 2001 From: Kui-Feng Lee Date: Wed, 22 Mar 2023 20:24:00 -0700 Subject: bpf: Create links for BPF struct_ops maps. Make bpf_link support struct_ops. Previously, struct_ops were always used alone without any associated links. Upon updating its value, a struct_ops would be activated automatically. Yet other BPF program types required to make a bpf_link with their instances before they could become active. Now, however, you can create an inactive struct_ops, and create a link to activate it later. With bpf_links, struct_ops has a behavior similar to other BPF program types. You can pin/unpin them from their links and the struct_ops will be deactivated when its link is removed while previously need someone to delete the value for it to be deactivated. bpf_links are responsible for registering their associated struct_ops. You can only use a struct_ops that has the BPF_F_LINK flag set to create a bpf_link, while a structs without this flag behaves in the same manner as before and is registered upon updating its value. The BPF_LINK_TYPE_STRUCT_OPS serves a dual purpose. Not only is it used to craft the links for BPF struct_ops programs, but also to create links for BPF struct_ops them-self. Since the links of BPF struct_ops programs are only used to create trampolines internally, they are never seen in other contexts. Thus, they can be reused for struct_ops themself. To maintain a reference to the map supporting this link, we add bpf_struct_ops_link as an additional type. The pointer of the map is RCU and won't be necessary until later in the patchset. Signed-off-by: Kui-Feng Lee Link: https://lore.kernel.org/r/20230323032405.3735486-4-kuifeng@meta.com Signed-off-by: Martin KaFai Lau --- include/linux/bpf.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index f04098468d7a..8552279efe46 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1518,6 +1518,7 @@ struct bpf_struct_ops { void *kdata, const void *udata); int (*reg)(void *kdata); void (*unreg)(void *kdata); + int (*validate)(void *kdata); const struct btf_type *type; const struct btf_type *value_type; const char *name; @@ -1552,6 +1553,7 @@ static inline void bpf_module_put(const void *data, struct module *owner) else module_put(owner); } +int bpf_struct_ops_link_create(union bpf_attr *attr); #ifdef CONFIG_NET /* Define it here to avoid the use of forward declaration */ @@ -1592,6 +1594,11 @@ static inline int bpf_struct_ops_map_sys_lookup_elem(struct bpf_map *map, { return -EINVAL; } +static inline int bpf_struct_ops_link_create(union bpf_attr *attr) +{ + return -EOPNOTSUPP; +} + #endif #if defined(CONFIG_CGROUP_BPF) && defined(CONFIG_BPF_LSM) -- cgit v1.2.3 From aef56f2e918bf8fc8de25f0b36e8c2aba44116ec Mon Sep 17 00:00:00 2001 From: Kui-Feng Lee Date: Wed, 22 Mar 2023 20:24:02 -0700 Subject: bpf: Update the struct_ops of a bpf_link. By improving the BPF_LINK_UPDATE command of bpf(), it should allow you to conveniently switch between different struct_ops on a single bpf_link. This would enable smoother transitions from one struct_ops to another. The struct_ops maps passing along with BPF_LINK_UPDATE should have the BPF_F_LINK flag. Signed-off-by: Kui-Feng Lee Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/r/20230323032405.3735486-6-kuifeng@meta.com Signed-off-by: Martin KaFai Lau --- include/linux/bpf.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 8552279efe46..2d8f3f639e68 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1476,6 +1476,8 @@ struct bpf_link_ops { void (*show_fdinfo)(const struct bpf_link *link, struct seq_file *seq); int (*fill_link_info)(const struct bpf_link *link, struct bpf_link_info *info); + int (*update_map)(struct bpf_link *link, struct bpf_map *new_map, + struct bpf_map *old_map); }; struct bpf_tramp_link { @@ -1518,6 +1520,7 @@ struct bpf_struct_ops { void *kdata, const void *udata); int (*reg)(void *kdata); void (*unreg)(void *kdata); + int (*update)(void *kdata, void *old_kdata); int (*validate)(void *kdata); const struct btf_type *type; const struct btf_type *value_type; -- cgit v1.2.3 From 6e2a3a324aab9d76e6b864eb6ebc60b197b5141a Mon Sep 17 00:00:00 2001 From: Or Har-Toov Date: Sun, 19 Mar 2023 14:59:30 +0200 Subject: net/mlx5: Expose bits for enabling out-of-order by default Add needed HW bits for enabling out-of-order by default and use go_back_n when out-of-order is not needed. Signed-off-by: Or Har-Toov Signed-off-by: Leon Romanovsky Link: https://lore.kernel.org/r/75d6dfe263989a05c08c43406132b336ea12d00a.1679230449.git.leon@kernel.org Signed-off-by: Leon Romanovsky --- include/linux/mlx5/mlx5_ifc.h | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 66d76e97a087..62039b147432 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1077,7 +1077,9 @@ struct mlx5_ifc_roce_cap_bits { u8 sw_r_roce_src_udp_port[0x1]; u8 fl_rc_qp_when_roce_disabled[0x1]; u8 fl_rc_qp_when_roce_enabled[0x1]; - u8 reserved_at_7[0x17]; + u8 reserved_at_7[0x1]; + u8 qp_ooo_transmit_default[0x1]; + u8 reserved_at_9[0x15]; u8 qp_ts_format[0x2]; u8 reserved_at_20[0x60]; @@ -1493,7 +1495,8 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_b0[0x1]; u8 uplink_follow[0x1]; u8 ts_cqe_to_dest_cqn[0x1]; - u8 reserved_at_b3[0x7]; + u8 reserved_at_b3[0x6]; + u8 go_back_n[0x1]; u8 shampo[0x1]; u8 reserved_at_bb[0x5]; @@ -3261,7 +3264,8 @@ struct mlx5_ifc_qpc_bits { u8 log_rq_stride[0x3]; u8 no_sq[0x1]; u8 log_sq_size[0x4]; - u8 reserved_at_55[0x3]; + u8 reserved_at_55[0x1]; + u8 retry_mode[0x2]; u8 ts_format[0x2]; u8 reserved_at_5a[0x1]; u8 rlky[0x1]; -- cgit v1.2.3 From 8d91f3f8ae57e6292142ca89f322e90fa0d6ac02 Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Sat, 11 Mar 2023 23:39:55 +0100 Subject: mmc: core: add helpers mmc_regulator_enable/disable_vqmmc There's a number of drivers (e.g. dw_mmc, meson-gx, mmci, sunxi) using the same mechanism and a private flag vqmmc_enabled to deal with enabling/disabling the vqmmc regulator. Move this to the core and create new helpers mmc_regulator_enable_vqmmc and mmc_regulator_disable_vqmmc. Signed-off-by: Heiner Kallweit Acked-by: Martin Blumenstingl Link: https://lore.kernel.org/r/71586432-360f-9b92-17f6-b05a8a971bc2@gmail.com Signed-off-by: Ulf Hansson --- include/linux/mmc/host.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index 812e6b583b25..461d1543893b 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -450,6 +450,7 @@ struct mmc_host { unsigned int retune_paused:1; /* re-tuning is temporarily disabled */ unsigned int retune_crc_disable:1; /* don't trigger retune upon crc */ unsigned int can_dma_map_merge:1; /* merging can be used */ + unsigned int vqmmc_enabled:1; /* vqmmc regulator is enabled */ int rescan_disable; /* disable card detection */ int rescan_entered; /* used with nonremovable devices */ @@ -598,6 +599,8 @@ static inline int mmc_regulator_set_vqmmc(struct mmc_host *mmc, #endif int mmc_regulator_get_supply(struct mmc_host *mmc); +int mmc_regulator_enable_vqmmc(struct mmc_host *mmc); +void mmc_regulator_disable_vqmmc(struct mmc_host *mmc); static inline int mmc_card_is_removable(struct mmc_host *host) { -- cgit v1.2.3 From e297cd54b3f81d652456ae6cb93941fc6b5c6683 Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Fri, 10 Mar 2023 16:03:30 -0600 Subject: vhost_task: Allow vhost layer to use copy_process Qemu will create vhost devices in the kernel which perform network, SCSI, etc IO and management operations from worker threads created by the kthread API. Because the kthread API does a copy_process on the kthreadd thread, the vhost layer has to use kthread_use_mm to access the Qemu thread's memory and cgroup_attach_task_all to add itself to the Qemu thread's cgroups, and it bypasses the RLIMIT_NPROC limit which can result in VMs creating more threads than the admin expected. This patch adds a new struct vhost_task which can be used instead of kthreads. They allow the vhost layer to use copy_process and inherit the userspace process's mm and cgroups, the task is accounted for under the userspace's nproc count and can be seen in its process tree, and other features like namespaces work and are inherited by default. Signed-off-by: Mike Christie Acked-by: Michael S. Tsirkin Signed-off-by: Christian Brauner (Microsoft) Signed-off-by: Christian Brauner --- include/linux/sched/vhost_task.h | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) create mode 100644 include/linux/sched/vhost_task.h (limited to 'include/linux') diff --git a/include/linux/sched/vhost_task.h b/include/linux/sched/vhost_task.h new file mode 100644 index 000000000000..6123c10b99cf --- /dev/null +++ b/include/linux/sched/vhost_task.h @@ -0,0 +1,23 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_VHOST_TASK_H +#define _LINUX_VHOST_TASK_H + +#include + +struct task_struct; + +struct vhost_task { + int (*fn)(void *data); + void *data; + struct completion exited; + unsigned long flags; + struct task_struct *task; +}; + +struct vhost_task *vhost_task_create(int (*fn)(void *), void *arg, + const char *name); +void vhost_task_start(struct vhost_task *vtsk); +void vhost_task_stop(struct vhost_task *vtsk); +bool vhost_task_should_stop(struct vhost_task *vtsk); + +#endif -- cgit v1.2.3 From 9cc61e5fbd619eea0401f519e7bac72fe3d4d1e8 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 13 Mar 2023 19:29:04 +0100 Subject: driver core: bus: move dev_root out of struct bus_type Now that all accesses of dev_root is through the bus_get_dev_root() call, move the pointer out of struct bus_type and into the private dynamic structure, subsys_private. With this change, there is no modifiable portions of struct bus_type so it can be marked as a constant structure and moved to read-only memory. Cc: "Rafael J. Wysocki" Link: https://lore.kernel.org/r/20230313182918.1312597-22-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- include/linux/device/bus.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/device/bus.h b/include/linux/device/bus.h index 6ce32ef4b8fd..c258e8770285 100644 --- a/include/linux/device/bus.h +++ b/include/linux/device/bus.h @@ -26,7 +26,6 @@ struct fwnode_handle; * * @name: The name of the bus. * @dev_name: Used for subsystems to enumerate devices like ("foo%u", dev->id). - * @dev_root: Default device to use as the parent. * @bus_groups: Default attributes of the bus. * @dev_groups: Default attributes of the devices on the bus. * @drv_groups: Default attributes of the device drivers on the bus. @@ -82,7 +81,6 @@ struct fwnode_handle; struct bus_type { const char *name; const char *dev_name; - struct device *dev_root; const struct attribute_group **bus_groups; const struct attribute_group **dev_groups; const struct attribute_group **drv_groups; -- cgit v1.2.3 From 75cff725d9566699a670a02b3cfd1c6e9e9ed53e Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 13 Mar 2023 19:29:05 +0100 Subject: driver core: bus: mark the struct bus_type for sysfs callbacks as constant struct bus_type should never be modified in a sysfs callback as there is nothing in the structure to modify, and frankly, the structure is almost never used in a sysfs callback, so mark it as constant to allow struct bus_type to be moved to read-only memory. Cc: "David S. Miller" Cc: "James E.J. Bottomley" Cc: "K. Y. Srinivasan" Cc: Alexander Gordeev Cc: Alexandre Bounine Cc: Alison Schofield Cc: Ben Widawsky Cc: Dexuan Cui Cc: Eric Dumazet Cc: Haiyang Zhang Cc: Hannes Reinecke Cc: Harald Freudenberger Cc: Heiko Carstens Cc: Hu Haowen Cc: Jakub Kicinski Cc: Jens Axboe Cc: Jonathan Corbet Cc: Laurentiu Tudor Cc: Matt Porter Cc: Michael Ellerman Cc: Paolo Abeni Cc: Stuart Yoder Cc: Vasily Gorbik Cc: Vishal Verma Cc: Yanteng Si Acked-by: Ilya Dryomov # rbd Acked-by: Ira Weiny # cxl Reviewed-by: Alex Shi Acked-by: Iwona Winiarska Acked-by: Dan Williams Acked-by: Bjorn Helgaas # pci Acked-by: Wei Liu Acked-by: Martin K. Petersen # scsi Link: https://lore.kernel.org/r/20230313182918.1312597-23-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- include/linux/device/bus.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/device/bus.h b/include/linux/device/bus.h index c258e8770285..78c875386c06 100644 --- a/include/linux/device/bus.h +++ b/include/linux/device/bus.h @@ -118,8 +118,8 @@ extern int __must_check bus_rescan_devices(struct bus_type *bus); struct bus_attribute { struct attribute attr; - ssize_t (*show)(struct bus_type *bus, char *buf); - ssize_t (*store)(struct bus_type *bus, const char *buf, size_t count); + ssize_t (*show)(const struct bus_type *bus, char *buf); + ssize_t (*store)(const struct bus_type *bus, const char *buf, size_t count); }; #define BUS_ATTR_RW(_name) \ -- cgit v1.2.3 From 00c4a3c47da761b4ba5d09c46b6fc77af5759081 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 13 Mar 2023 19:29:06 +0100 Subject: driver core: bus: constantify bus_register() bus_register() is now safe to take a constant * to bus_type, so make that change and mark the subsys_private bus_type * constant as well. Cc: "Rafael J. Wysocki" Link: https://lore.kernel.org/r/20230313182918.1312597-24-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- include/linux/device/bus.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/device/bus.h b/include/linux/device/bus.h index 78c875386c06..c30c4748c170 100644 --- a/include/linux/device/bus.h +++ b/include/linux/device/bus.h @@ -110,7 +110,7 @@ struct bus_type { bool need_parent_lock; }; -extern int __must_check bus_register(struct bus_type *bus); +extern int __must_check bus_register(const struct bus_type *bus); extern void bus_unregister(const struct bus_type *bus); -- cgit v1.2.3 From 9622b9f282e0f0d37683b21575b683039169e397 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 13 Mar 2023 19:29:07 +0100 Subject: driver core: bus: constify bus_rescan_devices() The bus_rescan_devices() function was missed in the previous change of the bus_for_each* constant pointer changes, so fix it up now to take a const * to struct bus_type. Cc: "Rafael J. Wysocki" Link: https://lore.kernel.org/r/20230313182918.1312597-25-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- include/linux/device/bus.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/device/bus.h b/include/linux/device/bus.h index c30c4748c170..b517b82d4723 100644 --- a/include/linux/device/bus.h +++ b/include/linux/device/bus.h @@ -114,7 +114,7 @@ extern int __must_check bus_register(const struct bus_type *bus); extern void bus_unregister(const struct bus_type *bus); -extern int __must_check bus_rescan_devices(struct bus_type *bus); +extern int __must_check bus_rescan_devices(const struct bus_type *bus); struct bus_attribute { struct attribute attr; -- cgit v1.2.3 From 7c06be04251a0b3349868622a2111a54cbfad8d4 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 13 Mar 2023 19:29:08 +0100 Subject: driver core: bus: constify driver_find() The driver_find() function can now take a const * to bus_type, not just a * so fix that up. Cc: "Rafael J. Wysocki" Link: https://lore.kernel.org/r/20230313182918.1312597-26-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- include/linux/device/driver.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/device/driver.h b/include/linux/device/driver.h index 50d0a416a5e7..ceb0e477c2c8 100644 --- a/include/linux/device/driver.h +++ b/include/linux/device/driver.h @@ -126,7 +126,7 @@ extern int __must_check driver_register(struct device_driver *drv); extern void driver_unregister(struct device_driver *drv); extern struct device_driver *driver_find(const char *name, - struct bus_type *bus); + const struct bus_type *bus); extern int driver_probe_done(void); extern void wait_for_device_probe(void); void __init wait_for_init_devices_probe(void); -- cgit v1.2.3 From c28dd08ef713d2127c5bad3f3e0e93d6ec0309a2 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 13 Mar 2023 19:29:10 +0100 Subject: driver core: make the bus_type in struct device_driver constant The pointer to struct bus_type in struct device_driver should only be pointing to something that can never change now that the driver core has fixed up the previously writable fields. So mark it as a constant pointer to enforce this and move forward with the goal of moving bus_type into read-only memory. Cc: "Rafael J. Wysocki" Link: https://lore.kernel.org/r/20230313182918.1312597-28-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- include/linux/device/driver.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/device/driver.h b/include/linux/device/driver.h index ceb0e477c2c8..0f22a6f46f8c 100644 --- a/include/linux/device/driver.h +++ b/include/linux/device/driver.h @@ -95,7 +95,7 @@ enum probe_type { */ struct device_driver { const char *name; - struct bus_type *bus; + const struct bus_type *bus; struct module *owner; const char *mod_name; /* used for built-in modules */ -- cgit v1.2.3 From b18d0a0f92a8fe9e56d812808184c8c4b9f18f92 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 13 Mar 2023 19:29:16 +0100 Subject: iommu: make the pointer to struct bus_type constant A number of iommu functions take a struct bus_type * and never modify the data passed in, so make them all const * as that is what the driver core is expecting to have passed into as well. This is a step toward making all struct bus_type pointers constant in the kernel. Cc: Will Deacon Cc: Robin Murphy Cc: iommu@lists.linux.dev Acked-by: Joerg Roedel Link: https://lore.kernel.org/r/20230313182918.1312597-34-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- include/linux/iommu.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 6595454d4f48..0fd4e6734d5b 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -455,11 +455,11 @@ static inline const struct iommu_ops *dev_iommu_ops(struct device *dev) return dev->iommu->iommu_dev->ops; } -extern int bus_iommu_probe(struct bus_type *bus); -extern bool iommu_present(struct bus_type *bus); +extern int bus_iommu_probe(const struct bus_type *bus); +extern bool iommu_present(const struct bus_type *bus); extern bool device_iommu_capable(struct device *dev, enum iommu_cap cap); extern bool iommu_group_has_isolated_msi(struct iommu_group *group); -extern struct iommu_domain *iommu_domain_alloc(struct bus_type *bus); +extern struct iommu_domain *iommu_domain_alloc(const struct bus_type *bus); extern struct iommu_group *iommu_group_get_by_id(int id); extern void iommu_domain_free(struct iommu_domain *domain); extern int iommu_attach_device(struct iommu_domain *domain, @@ -732,7 +732,7 @@ struct iommu_device {}; struct iommu_fault_param {}; struct iommu_iotlb_gather {}; -static inline bool iommu_present(struct bus_type *bus) +static inline bool iommu_present(const struct bus_type *bus) { return false; } @@ -742,7 +742,7 @@ static inline bool device_iommu_capable(struct device *dev, enum iommu_cap cap) return false; } -static inline struct iommu_domain *iommu_domain_alloc(struct bus_type *bus) +static inline struct iommu_domain *iommu_domain_alloc(const struct bus_type *bus) { return NULL; } -- cgit v1.2.3 From d492cc2573a08352c48a66d3e3f312a15fb3f363 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 13 Mar 2023 19:29:17 +0100 Subject: driver core: device.h: make struct bus_type a const * Now that all users who accessed the bus_type structure in struct device are properly using it as a const *, mark it as such so that no one can modify it going forward anymore. Cc: "Rafael J. Wysocki" Link: https://lore.kernel.org/r/20230313182918.1312597-35-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 862397ae520d..3b23772d3bbb 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -566,7 +566,7 @@ struct device { const char *init_name; /* initial name of the device */ const struct device_type *type; - struct bus_type *bus; /* type of bus device is on */ + const struct bus_type *bus; /* type of bus device is on */ struct device_driver *driver; /* which driver has allocated this device */ void *platform_data; /* Platform specific data, device -- cgit v1.2.3 From 9d11b13402d1b80f7f3ca5061d75f15cf8002555 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 13 Mar 2023 19:29:18 +0100 Subject: USB: mark all struct bus_type as const Now that the driver core can properly handle constant struct bus_type, move all of the USB subsystem struct bus_type structures as const, placing them into read-only memory which can not be modified at runtime. Cc: Johan Hovold Cc: Evan Green Cc: Alan Stern Cc: linux-usb@vger.kernel.org Acked-by: Heikki Krogerus Link: https://lore.kernel.org/r/20230313182918.1312597-36-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/serial.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/usb/serial.h b/include/linux/usb/serial.h index f7bfedb740f5..7eeb5f9c4f0d 100644 --- a/include/linux/usb/serial.h +++ b/include/linux/usb/serial.h @@ -378,7 +378,7 @@ void usb_serial_handle_dcd_change(struct usb_serial_port *usb_port, int usb_serial_bus_register(struct usb_serial_driver *device); void usb_serial_bus_deregister(struct usb_serial_driver *device); -extern struct bus_type usb_serial_bus_type; +extern const struct bus_type usb_serial_bus_type; extern struct tty_driver *usb_serial_tty_driver; static inline void usb_serial_debug_data(struct device *dev, -- cgit v1.2.3 From 1fb1ea0d9cb8359ae9d6f67f22666c74d5b9f47d Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Fri, 10 Mar 2023 19:07:47 +0200 Subject: mei: Move uuid.h to the MEI namespace There is only a single user of the UUID uAPI, let's make it part of that user. The way it's done is to prevent compilation time breakage for the user space that does #include In the future MEI user space tools can switch over to use mei_uuid.h. Signed-off-by: Andy Shevchenko Link: https://lore.kernel.org/r/20230310170747.22782-1-andriy.shevchenko@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- include/linux/mod_devicetable.h | 1 + include/linux/uuid.h | 3 --- 2 files changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index 549590e9c644..35203ca3fc37 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -9,6 +9,7 @@ #define LINUX_MOD_DEVICETABLE_H #ifdef __KERNEL__ +#include #include #include typedef unsigned long kernel_ulong_t; diff --git a/include/linux/uuid.h b/include/linux/uuid.h index 6b1a3efa1e0b..43d4a79b273d 100644 --- a/include/linux/uuid.h +++ b/include/linux/uuid.h @@ -107,7 +107,4 @@ extern const u8 uuid_index[16]; int guid_parse(const char *uuid, guid_t *u); int uuid_parse(const char *uuid, uuid_t *u); -/* MEI UUID type, don't use anywhere else */ -#include - #endif -- cgit v1.2.3 From f7515d9fe8fc4b80754cd4d98a5fcaee84adeebb Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Wed, 1 Mar 2023 07:13:07 -0800 Subject: objtool: Add objtool_types.h Reduce the amount of header sync churn by splitting the shared objtool.h types into a new file. Signed-off-by: Josh Poimboeuf Signed-off-by: Peter Zijlstra (Intel) Acked-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/dec622720851210ceafa12d4f4c5f9e73c832152.1677683419.git.jpoimboe@kernel.org --- include/linux/objtool.h | 42 +------------------------------------ include/linux/objtool_types.h | 48 +++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 49 insertions(+), 41 deletions(-) create mode 100644 include/linux/objtool_types.h (limited to 'include/linux') diff --git a/include/linux/objtool.h b/include/linux/objtool.h index 9ac3df3fccf0..8375792acfc0 100644 --- a/include/linux/objtool.h +++ b/include/linux/objtool.h @@ -2,47 +2,7 @@ #ifndef _LINUX_OBJTOOL_H #define _LINUX_OBJTOOL_H -#ifndef __ASSEMBLY__ - -#include - -/* - * This struct is used by asm and inline asm code to manually annotate the - * location of registers on the stack. - */ -struct unwind_hint { - u32 ip; - s16 sp_offset; - u8 sp_reg; - u8 type; - u8 signal; - u8 end; -}; -#endif - -/* - * UNWIND_HINT_TYPE_CALL: Indicates that sp_reg+sp_offset resolves to PREV_SP - * (the caller's SP right before it made the call). Used for all callable - * functions, i.e. all C code and all callable asm functions. - * - * UNWIND_HINT_TYPE_REGS: Used in entry code to indicate that sp_reg+sp_offset - * points to a fully populated pt_regs from a syscall, interrupt, or exception. - * - * UNWIND_HINT_TYPE_REGS_PARTIAL: Used in entry code to indicate that - * sp_reg+sp_offset points to the iret return frame. - * - * UNWIND_HINT_FUNC: Generate the unwind metadata of a callable function. - * Useful for code which doesn't have an ELF function annotation. - * - * UNWIND_HINT_ENTRY: machine entry without stack, SYSCALL/SYSENTER etc. - */ -#define UNWIND_HINT_TYPE_CALL 0 -#define UNWIND_HINT_TYPE_REGS 1 -#define UNWIND_HINT_TYPE_REGS_PARTIAL 2 -#define UNWIND_HINT_TYPE_FUNC 3 -#define UNWIND_HINT_TYPE_ENTRY 4 -#define UNWIND_HINT_TYPE_SAVE 5 -#define UNWIND_HINT_TYPE_RESTORE 6 +#include #ifdef CONFIG_OBJTOOL diff --git a/include/linux/objtool_types.h b/include/linux/objtool_types.h new file mode 100644 index 000000000000..8513537a30ed --- /dev/null +++ b/include/linux/objtool_types.h @@ -0,0 +1,48 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_OBJTOOL_TYPES_H +#define _LINUX_OBJTOOL_TYPES_H + +#ifndef __ASSEMBLY__ + +#include + +/* + * This struct is used by asm and inline asm code to manually annotate the + * location of registers on the stack. + */ +struct unwind_hint { + u32 ip; + s16 sp_offset; + u8 sp_reg; + u8 type; + u8 signal; + u8 end; +}; + +#endif /* __ASSEMBLY__ */ + +/* + * UNWIND_HINT_TYPE_CALL: Indicates that sp_reg+sp_offset resolves to PREV_SP + * (the caller's SP right before it made the call). Used for all callable + * functions, i.e. all C code and all callable asm functions. + * + * UNWIND_HINT_TYPE_REGS: Used in entry code to indicate that sp_reg+sp_offset + * points to a fully populated pt_regs from a syscall, interrupt, or exception. + * + * UNWIND_HINT_TYPE_REGS_PARTIAL: Used in entry code to indicate that + * sp_reg+sp_offset points to the iret return frame. + * + * UNWIND_HINT_FUNC: Generate the unwind metadata of a callable function. + * Useful for code which doesn't have an ELF function annotation. + * + * UNWIND_HINT_ENTRY: machine entry without stack, SYSCALL/SYSENTER etc. + */ +#define UNWIND_HINT_TYPE_CALL 0 +#define UNWIND_HINT_TYPE_REGS 1 +#define UNWIND_HINT_TYPE_REGS_PARTIAL 2 +#define UNWIND_HINT_TYPE_FUNC 3 +#define UNWIND_HINT_TYPE_ENTRY 4 +#define UNWIND_HINT_TYPE_SAVE 5 +#define UNWIND_HINT_TYPE_RESTORE 6 + +#endif /* _LINUX_OBJTOOL_TYPES_H */ -- cgit v1.2.3 From 1c0c1faf5692c18c127d044ecc0cc92c7bab3477 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Wed, 1 Mar 2023 07:13:08 -0800 Subject: objtool: Use relative pointers for annotations They produce the needed relocations while using half the space. Signed-off-by: Josh Poimboeuf Signed-off-by: Peter Zijlstra (Intel) Acked-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/bed05c64e28200220c9b1754a2f3ce71f73076ea.1677683419.git.jpoimboe@kernel.org --- include/linux/objtool.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/objtool.h b/include/linux/objtool.h index 8375792acfc0..2b0258d273fc 100644 --- a/include/linux/objtool.h +++ b/include/linux/objtool.h @@ -49,7 +49,7 @@ #define ANNOTATE_NOENDBR \ "986: \n\t" \ ".pushsection .discard.noendbr\n\t" \ - _ASM_PTR " 986b\n\t" \ + ".long 986b - .\n\t" \ ".popsection\n\t" #define ASM_REACHABLE \ @@ -67,7 +67,7 @@ #define ANNOTATE_INTRA_FUNCTION_CALL \ 999: \ .pushsection .discard.intra_function_calls; \ - .long 999b; \ + .long 999b - .; \ .popsection; /* @@ -92,10 +92,10 @@ * inconsistencies. */ .macro UNWIND_HINT type:req sp_reg=0 sp_offset=0 signal=0 end=0 -.Lunwind_hint_ip_\@: +.Lhere_\@: .pushsection .discard.unwind_hints /* struct unwind_hint */ - .long .Lunwind_hint_ip_\@ - . + .long .Lhere_\@ - . .short \sp_offset .byte \sp_reg .byte \type @@ -107,7 +107,7 @@ .macro STACK_FRAME_NON_STANDARD func:req .pushsection .discard.func_stack_frame_non_standard, "aw" - _ASM_PTR \func + .long \func - . .popsection .endm @@ -120,7 +120,7 @@ .macro ANNOTATE_NOENDBR .Lhere_\@: .pushsection .discard.noendbr - .quad .Lhere_\@ + .long .Lhere_\@ - . .popsection .endm -- cgit v1.2.3 From d88ebba45dfe67114a6ac8c6514f2c65b6ed64c7 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Wed, 1 Mar 2023 07:13:09 -0800 Subject: objtool: Change UNWIND_HINT() argument order The most important argument is 'type', make that one first. Signed-off-by: Josh Poimboeuf Signed-off-by: Peter Zijlstra (Intel) Acked-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/d994f8c29376c5618c75698df28fc03b52d3a868.1677683419.git.jpoimboe@kernel.org --- include/linux/objtool.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/objtool.h b/include/linux/objtool.h index 2b0258d273fc..725d7f0b6748 100644 --- a/include/linux/objtool.h +++ b/include/linux/objtool.h @@ -10,7 +10,7 @@ #ifndef __ASSEMBLY__ -#define UNWIND_HINT(sp_reg, sp_offset, type, signal, end) \ +#define UNWIND_HINT(type, sp_reg, sp_offset, signal, end) \ "987: \n\t" \ ".pushsection .discard.unwind_hints\n\t" \ /* struct unwind_hint */ \ @@ -137,8 +137,7 @@ #ifndef __ASSEMBLY__ -#define UNWIND_HINT(sp_reg, sp_offset, type, signal, end) \ - "\n\t" +#define UNWIND_HINT(type, sp_reg, sp_offset, signal, end) "\n\t" #define STACK_FRAME_NON_STANDARD(func) #define STACK_FRAME_NON_STANDARD_FP(func) #define ANNOTATE_NOENDBR -- cgit v1.2.3 From f902cfdd46aedd2afb3e8033223312dbf5fbb675 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Wed, 1 Mar 2023 07:13:10 -0800 Subject: x86,objtool: Introduce ORC_TYPE_* Unwind hints and ORC entry types are two distinct things. Separate them out more explicitly. Signed-off-by: Josh Poimboeuf Signed-off-by: Peter Zijlstra (Intel) Acked-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/cc879d38fff8a43f8f7beb2fd56e35a5a384d7cd.1677683419.git.jpoimboe@kernel.org --- include/linux/objtool_types.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/objtool_types.h b/include/linux/objtool_types.h index 8513537a30ed..9a83468c0039 100644 --- a/include/linux/objtool_types.h +++ b/include/linux/objtool_types.h @@ -40,6 +40,7 @@ struct unwind_hint { #define UNWIND_HINT_TYPE_CALL 0 #define UNWIND_HINT_TYPE_REGS 1 #define UNWIND_HINT_TYPE_REGS_PARTIAL 2 +/* The below hint types don't have corresponding ORC types */ #define UNWIND_HINT_TYPE_FUNC 3 #define UNWIND_HINT_TYPE_ENTRY 4 #define UNWIND_HINT_TYPE_SAVE 5 -- cgit v1.2.3 From 4708ea14bef314fc901857eefd65678236a9f2d9 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Wed, 1 Mar 2023 07:13:11 -0800 Subject: x86,objtool: Separate unret validation from unwind hints The ENTRY unwind hint type is serving double duty as both an empty unwind hint and an unret validation annotation. Unret validation is unrelated to unwinding. Separate it out into its own annotation. Signed-off-by: Josh Poimboeuf Signed-off-by: Peter Zijlstra (Intel) Acked-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/ff7448d492ea21b86d8a90264b105fbd0d751077.1677683419.git.jpoimboe@kernel.org --- include/linux/objtool.h | 16 ++++++++++++++++ include/linux/objtool_types.h | 5 ++--- 2 files changed, 18 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/objtool.h b/include/linux/objtool.h index 725d7f0b6748..5aa475118820 100644 --- a/include/linux/objtool.h +++ b/include/linux/objtool.h @@ -124,6 +124,22 @@ .popsection .endm +/* + * Use objtool to validate the entry requirement that all code paths do + * VALIDATE_UNRET_END before RET. + * + * NOTE: The macro must be used at the beginning of a global symbol, otherwise + * it will be ignored. + */ +.macro VALIDATE_UNRET_BEGIN +#if defined(CONFIG_NOINSTR_VALIDATION) && defined(CONFIG_CPU_UNRET_ENTRY) +.Lhere_\@: + .pushsection .discard.validate_unret + .long .Lhere_\@ - . + .popsection +#endif +.endm + .macro REACHABLE .Lhere_\@: .pushsection .discard.reachable diff --git a/include/linux/objtool_types.h b/include/linux/objtool_types.h index 9a83468c0039..9787ad0f2ef4 100644 --- a/include/linux/objtool_types.h +++ b/include/linux/objtool_types.h @@ -42,8 +42,7 @@ struct unwind_hint { #define UNWIND_HINT_TYPE_REGS_PARTIAL 2 /* The below hint types don't have corresponding ORC types */ #define UNWIND_HINT_TYPE_FUNC 3 -#define UNWIND_HINT_TYPE_ENTRY 4 -#define UNWIND_HINT_TYPE_SAVE 5 -#define UNWIND_HINT_TYPE_RESTORE 6 +#define UNWIND_HINT_TYPE_SAVE 4 +#define UNWIND_HINT_TYPE_RESTORE 5 #endif /* _LINUX_OBJTOOL_TYPES_H */ -- cgit v1.2.3 From fb799447ae2974a07907906dff5bd4b9e47b7123 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Wed, 1 Mar 2023 07:13:12 -0800 Subject: x86,objtool: Split UNWIND_HINT_EMPTY in two Mark reported that the ORC unwinder incorrectly marks an unwind as reliable when the unwind terminates prematurely in the dark corners of return_to_handler() due to lack of information about the next frame. The problem is UNWIND_HINT_EMPTY is used in two different situations: 1) The end of the kernel stack unwind before hitting user entry, boot code, or fork entry 2) A blind spot in ORC coverage where the unwinder has to bail due to lack of information about the next frame The ORC unwinder has no way to tell the difference between the two. When it encounters an undefined stack state with 'end=1', it blindly marks the stack reliable, which can break the livepatch consistency model. Fix it by splitting UNWIND_HINT_EMPTY into UNWIND_HINT_UNDEFINED and UNWIND_HINT_END_OF_STACK. Reported-by: Mark Rutland Signed-off-by: Josh Poimboeuf Signed-off-by: Peter Zijlstra (Intel) Acked-by: Steven Rostedt (Google) Acked-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/fd6212c8b450d3564b855e1cb48404d6277b4d9f.1677683419.git.jpoimboe@kernel.org --- include/linux/objtool.h | 10 ++++------ include/linux/objtool_types.h | 27 ++++++++++++++++++--------- 2 files changed, 22 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/objtool.h b/include/linux/objtool.h index 5aa475118820..03f82c2c2ebf 100644 --- a/include/linux/objtool.h +++ b/include/linux/objtool.h @@ -10,7 +10,7 @@ #ifndef __ASSEMBLY__ -#define UNWIND_HINT(type, sp_reg, sp_offset, signal, end) \ +#define UNWIND_HINT(type, sp_reg, sp_offset, signal) \ "987: \n\t" \ ".pushsection .discard.unwind_hints\n\t" \ /* struct unwind_hint */ \ @@ -19,7 +19,6 @@ ".byte " __stringify(sp_reg) "\n\t" \ ".byte " __stringify(type) "\n\t" \ ".byte " __stringify(signal) "\n\t" \ - ".byte " __stringify(end) "\n\t" \ ".balign 4 \n\t" \ ".popsection\n\t" @@ -91,7 +90,7 @@ * the debuginfo as necessary. It will also warn if it sees any * inconsistencies. */ -.macro UNWIND_HINT type:req sp_reg=0 sp_offset=0 signal=0 end=0 +.macro UNWIND_HINT type:req sp_reg=0 sp_offset=0 signal=0 .Lhere_\@: .pushsection .discard.unwind_hints /* struct unwind_hint */ @@ -100,7 +99,6 @@ .byte \sp_reg .byte \type .byte \signal - .byte \end .balign 4 .popsection .endm @@ -153,14 +151,14 @@ #ifndef __ASSEMBLY__ -#define UNWIND_HINT(type, sp_reg, sp_offset, signal, end) "\n\t" +#define UNWIND_HINT(type, sp_reg, sp_offset, signal) "\n\t" #define STACK_FRAME_NON_STANDARD(func) #define STACK_FRAME_NON_STANDARD_FP(func) #define ANNOTATE_NOENDBR #define ASM_REACHABLE #else #define ANNOTATE_INTRA_FUNCTION_CALL -.macro UNWIND_HINT type:req sp_reg=0 sp_offset=0 signal=0 end=0 +.macro UNWIND_HINT type:req sp_reg=0 sp_offset=0 signal=0 .endm .macro STACK_FRAME_NON_STANDARD func:req .endm diff --git a/include/linux/objtool_types.h b/include/linux/objtool_types.h index 9787ad0f2ef4..453a4f4ef39d 100644 --- a/include/linux/objtool_types.h +++ b/include/linux/objtool_types.h @@ -16,12 +16,18 @@ struct unwind_hint { u8 sp_reg; u8 type; u8 signal; - u8 end; }; #endif /* __ASSEMBLY__ */ /* + * UNWIND_HINT_TYPE_UNDEFINED: A blind spot in ORC coverage which can result in + * a truncated and unreliable stack unwind. + * + * UNWIND_HINT_TYPE_END_OF_STACK: The end of the kernel stack unwind before + * hitting user entry, boot code, or fork entry (when there are no pt_regs + * available). + * * UNWIND_HINT_TYPE_CALL: Indicates that sp_reg+sp_offset resolves to PREV_SP * (the caller's SP right before it made the call). Used for all callable * functions, i.e. all C code and all callable asm functions. @@ -32,17 +38,20 @@ struct unwind_hint { * UNWIND_HINT_TYPE_REGS_PARTIAL: Used in entry code to indicate that * sp_reg+sp_offset points to the iret return frame. * - * UNWIND_HINT_FUNC: Generate the unwind metadata of a callable function. + * UNWIND_HINT_TYPE_FUNC: Generate the unwind metadata of a callable function. * Useful for code which doesn't have an ELF function annotation. * - * UNWIND_HINT_ENTRY: machine entry without stack, SYSCALL/SYSENTER etc. + * UNWIND_HINT_TYPE_{SAVE,RESTORE}: Save the unwind metadata at a certain + * location so that it can be restored later. */ -#define UNWIND_HINT_TYPE_CALL 0 -#define UNWIND_HINT_TYPE_REGS 1 -#define UNWIND_HINT_TYPE_REGS_PARTIAL 2 +#define UNWIND_HINT_TYPE_UNDEFINED 0 +#define UNWIND_HINT_TYPE_END_OF_STACK 1 +#define UNWIND_HINT_TYPE_CALL 2 +#define UNWIND_HINT_TYPE_REGS 3 +#define UNWIND_HINT_TYPE_REGS_PARTIAL 4 /* The below hint types don't have corresponding ORC types */ -#define UNWIND_HINT_TYPE_FUNC 3 -#define UNWIND_HINT_TYPE_SAVE 4 -#define UNWIND_HINT_TYPE_RESTORE 5 +#define UNWIND_HINT_TYPE_FUNC 5 +#define UNWIND_HINT_TYPE_SAVE 6 +#define UNWIND_HINT_TYPE_RESTORE 7 #endif /* _LINUX_OBJTOOL_TYPES_H */ -- cgit v1.2.3 From f530b531fb9e05eb134cfc334242799ea974d111 Mon Sep 17 00:00:00 2001 From: Mathias Krause Date: Fri, 17 Feb 2023 20:33:36 +0100 Subject: KVM: Shrink struct kvm_mmu_memory_cache Move the 'capacity' member around to make use of the padding hole on 64 bit systems instead of introducing yet another one. This allows us to save 8 bytes per instance for 64 bit builds of which, e.g., x86's struct kvm_vcpu_arch has a few. Signed-off-by: Mathias Krause Link: https://lore.kernel.org/r/20230217193336.15278-3-minipli@grsecurity.net Signed-off-by: Sean Christopherson --- include/linux/kvm_types.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kvm_types.h b/include/linux/kvm_types.h index 2728d49bbdf6..6f4737d5046a 100644 --- a/include/linux/kvm_types.h +++ b/include/linux/kvm_types.h @@ -91,11 +91,11 @@ struct gfn_to_pfn_cache { * is topped up (__kvm_mmu_topup_memory_cache()). */ struct kvm_mmu_memory_cache { - int nobjs; gfp_t gfp_zero; gfp_t gfp_custom; struct kmem_cache *kmem_cache; int capacity; + int nobjs; void **objects; }; #endif -- cgit v1.2.3 From 0d57b970df352517a75f4533820c49de360c4123 Mon Sep 17 00:00:00 2001 From: Roberto Sassu Date: Tue, 14 Mar 2023 09:17:17 +0100 Subject: security: Remove security_old_inode_init_security() As the remaining two users reiserfs and ocfs2 switched to security_inode_init_security(), security_old_inode_init_security() can be now removed. Out-of-tree kernel modules should switch to security_inode_init_security() too. Signed-off-by: Roberto Sassu Reviewed-by: Casey Schaufler Reviewed-by: Mimi Zohar Signed-off-by: Paul Moore --- include/linux/security.h | 12 ------------ 1 file changed, 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/security.h b/include/linux/security.h index 5984d0d550b4..cd23221ce9e6 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -336,9 +336,6 @@ int security_inode_init_security(struct inode *inode, struct inode *dir, int security_inode_init_security_anon(struct inode *inode, const struct qstr *name, const struct inode *context_inode); -int security_old_inode_init_security(struct inode *inode, struct inode *dir, - const struct qstr *qstr, const char **name, - void **value, size_t *len); int security_inode_create(struct inode *dir, struct dentry *dentry, umode_t mode); int security_inode_link(struct dentry *old_dentry, struct inode *dir, struct dentry *new_dentry); @@ -778,15 +775,6 @@ static inline int security_inode_init_security_anon(struct inode *inode, return 0; } -static inline int security_old_inode_init_security(struct inode *inode, - struct inode *dir, - const struct qstr *qstr, - const char **name, - void **value, size_t *len) -{ - return -EOPNOTSUPP; -} - static inline int security_inode_create(struct inode *dir, struct dentry *dentry, umode_t mode) -- cgit v1.2.3 From 704bc669e1dda3eb8f6d5cb462b21e85558a3912 Mon Sep 17 00:00:00 2001 From: Jungseung Lee Date: Mon, 20 Mar 2023 12:29:05 +0900 Subject: workqueue: Introduce show_freezable_workqueues Currently show_all_workqueue is called if freeze fails at the time of freeze the workqueues, which shows the status of all workqueues and of all worker pools. In this cases we may only need to dump state of only workqueues that are freezable and busy. This patch defines show_freezable_workqueues, which uses show_one_workqueue, a granular function that shows the state of individual workqueues, so that dump only the state of freezable workqueues at that time. tj: Minor message adjustment. Signed-off-by: Jungseung Lee Signed-off-by: Tejun Heo --- include/linux/workqueue.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index ac551b8ee7d9..3992c994787f 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -472,6 +472,7 @@ extern unsigned int work_busy(struct work_struct *work); extern __printf(1, 2) void set_worker_desc(const char *fmt, ...); extern void print_worker_info(const char *log_lvl, struct task_struct *task); extern void show_all_workqueues(void); +extern void show_freezable_workqueues(void); extern void show_one_workqueue(struct workqueue_struct *wq); extern void wq_worker_comm(char *buf, size_t size, struct task_struct *task); -- cgit v1.2.3 From 8e4645226b4931e96d55546a1fb3863aa50b5e62 Mon Sep 17 00:00:00 2001 From: Haifeng Xu Date: Tue, 28 Feb 2023 08:35:37 +0000 Subject: cpuset: Clean up cpuset_node_allowed Commit 002f290627c2 ("cpuset: use static key better and convert to new API") has used __cpuset_node_allowed() instead of cpuset_node_allowed() to check whether we can allocate on a memory node. Now this function isn't used by anyone, so we can do the follow things to clean up it. 1. remove unused codes 2. rename __cpuset_node_allowed() to cpuset_node_allowed() 3. update comments in mm/page_alloc.c Suggested-by: Waiman Long Signed-off-by: Haifeng Xu Acked-by: Waiman Long Signed-off-by: Tejun Heo --- include/linux/cpuset.h | 16 ++-------------- 1 file changed, 2 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h index d58e0476ee8e..980b76a1237e 100644 --- a/include/linux/cpuset.h +++ b/include/linux/cpuset.h @@ -80,18 +80,11 @@ extern nodemask_t cpuset_mems_allowed(struct task_struct *p); void cpuset_init_current_mems_allowed(void); int cpuset_nodemask_valid_mems_allowed(nodemask_t *nodemask); -extern bool __cpuset_node_allowed(int node, gfp_t gfp_mask); - -static inline bool cpuset_node_allowed(int node, gfp_t gfp_mask) -{ - if (cpusets_enabled()) - return __cpuset_node_allowed(node, gfp_mask); - return true; -} +extern bool cpuset_node_allowed(int node, gfp_t gfp_mask); static inline bool __cpuset_zone_allowed(struct zone *z, gfp_t gfp_mask) { - return __cpuset_node_allowed(zone_to_nid(z), gfp_mask); + return cpuset_node_allowed(zone_to_nid(z), gfp_mask); } static inline bool cpuset_zone_allowed(struct zone *z, gfp_t gfp_mask) @@ -223,11 +216,6 @@ static inline int cpuset_nodemask_valid_mems_allowed(nodemask_t *nodemask) return 1; } -static inline bool cpuset_node_allowed(int node, gfp_t gfp_mask) -{ - return true; -} - static inline bool __cpuset_zone_allowed(struct zone *z, gfp_t gfp_mask) { return true; -- cgit v1.2.3 From 3eb8eea2a453463f5606ce3e46cf225f88671440 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Tue, 21 Mar 2023 22:38:48 -0700 Subject: docs: networking: document NAPI MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add basic documentation about NAPI. We can stop linking to the ancient doc on the LF wiki. Link: https://lore.kernel.org/all/20230315223044.471002-1-kuba@kernel.org/ Reviewed-by: Bagas Sanjaya Reviewed-by: Toke Høiland-Jørgensen Acked-by: Pavel Pisa # for ctucanfd-driver.rst Reviewed-by: Tony Nguyen Reviewed-by: Florian Fainelli Reviewed-by: Stephen Hemminger Reviewed-by: Randy Dunlap Link: https://lore.kernel.org/r/20230322053848.198452-1-kuba@kernel.org Signed-off-by: Jakub Kicinski --- include/linux/netdevice.h | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 674ee5daa7b1..18a5be6ddd0f 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -509,15 +509,18 @@ static inline bool napi_reschedule(struct napi_struct *napi) return false; } -bool napi_complete_done(struct napi_struct *n, int work_done); /** - * napi_complete - NAPI processing complete - * @n: NAPI context + * napi_complete_done - NAPI processing complete + * @n: NAPI context + * @work_done: number of packets processed * - * Mark NAPI processing as complete. - * Consider using napi_complete_done() instead. + * Mark NAPI processing as complete. Should only be called if poll budget + * has not been completely consumed. + * Prefer over napi_complete(). * Return false if device should avoid rearming interrupts. */ +bool napi_complete_done(struct napi_struct *n, int work_done); + static inline bool napi_complete(struct napi_struct *n) { return napi_complete_done(n, 0); -- cgit v1.2.3 From 4c8c3c7f70a6779d30f5492acbc9978f4636fe7a Mon Sep 17 00:00:00 2001 From: Valentin Schneider Date: Tue, 7 Mar 2023 14:35:56 +0000 Subject: treewide: Trace IPIs sent via smp_send_reschedule() To be able to trace invocations of smp_send_reschedule(), rename the arch-specific definitions of it to arch_smp_send_reschedule() and wrap it into an smp_send_reschedule() that contains a tracepoint. Changes to include the declaration of the tracepoint were driven by the following coccinelle script: @func_use@ @@ smp_send_reschedule(...); @include@ @@ #include @no_include depends on func_use && !include@ @@ #include <...> + + #include [csky bits] [riscv bits] Signed-off-by: Valentin Schneider Signed-off-by: Peter Zijlstra (Intel) Acked-by: Guo Ren Acked-by: Palmer Dabbelt Link: https://lore.kernel.org/r/20230307143558.294354-6-vschneid@redhat.com --- include/linux/smp.h | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/smp.h b/include/linux/smp.h index a80ab58ae3f1..c036a2228d8d 100644 --- a/include/linux/smp.h +++ b/include/linux/smp.h @@ -125,8 +125,15 @@ extern void smp_send_stop(void); /* * sends a 'reschedule' event to another CPU: */ -extern void smp_send_reschedule(int cpu); - +extern void arch_smp_send_reschedule(int cpu); +/* + * scheduler_ipi() is inline so can't be passed as callback reason, but the + * callsite IP should be sufficient for root-causing IPIs sent from here. + */ +#define smp_send_reschedule(cpu) ({ \ + trace_ipi_send_cpumask(cpumask_of(cpu), _RET_IP_, NULL); \ + arch_smp_send_reschedule(cpu); \ +}) /* * Prepare machine for booting other CPUs. -- cgit v1.2.3 From 68e2d17c9eb311ab59aeb6d0c38aad8985fa2596 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 22 Mar 2023 11:28:36 +0100 Subject: trace: Add trace_ipi_send_cpu() Because copying cpumasks around when targeting a single CPU is a bit daft... Tested-and-reviewed-by: Valentin Schneider Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20230322103004.GA571242%40hirez.programming.kicks-ass.net --- include/linux/smp.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/smp.h b/include/linux/smp.h index c036a2228d8d..ed8f344ba627 100644 --- a/include/linux/smp.h +++ b/include/linux/smp.h @@ -130,9 +130,9 @@ extern void arch_smp_send_reschedule(int cpu); * scheduler_ipi() is inline so can't be passed as callback reason, but the * callsite IP should be sufficient for root-causing IPIs sent from here. */ -#define smp_send_reschedule(cpu) ({ \ - trace_ipi_send_cpumask(cpumask_of(cpu), _RET_IP_, NULL); \ - arch_smp_send_reschedule(cpu); \ +#define smp_send_reschedule(cpu) ({ \ + trace_ipi_send_cpu(cpu, _RET_IP_, NULL); \ + arch_smp_send_reschedule(cpu); \ }) /* -- cgit v1.2.3 From 0a392354dbc3ff748e0856a75592fe8d0fdc7674 Mon Sep 17 00:00:00 2001 From: Russell King Date: Fri, 24 Mar 2023 09:26:47 +0000 Subject: device property: constify fwnode_get_phy_mode() argument fwnode_get_phy_mode() does not modify the fwnode argument, merely using it to obtain the phy-mode property value. Therefore, it can be made const. Signed-off-by: Russell King (Oracle) Reviewed-by: Andy Shevchenko Link: https://lore.kernel.org/r/E1pfdh9-00EQ8t-HB@rmk-PC.armlinux.org.uk Signed-off-by: Greg Kroah-Hartman --- include/linux/property.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/property.h b/include/linux/property.h index 0a29db15ff34..110634f5db2e 100644 --- a/include/linux/property.h +++ b/include/linux/property.h @@ -396,7 +396,7 @@ enum dev_dma_attr device_get_dma_attr(const struct device *dev); const void *device_get_match_data(const struct device *dev); int device_get_phy_mode(struct device *dev); -int fwnode_get_phy_mode(struct fwnode_handle *fwnode); +int fwnode_get_phy_mode(const struct fwnode_handle *fwnode); void __iomem *fwnode_iomap(struct fwnode_handle *fwnode, int index); -- cgit v1.2.3 From 5b9ff0ba11042096bfb396e506fa9038e6a61de7 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Fri, 24 Mar 2023 13:27:20 +0200 Subject: device property: Constify a few fwnode APIs The fwnode parameter is not altered in the following APIs: - fwnode_get_next_parent_dev() - fwnode_is_ancestor_of() - fwnode_graph_get_endpoint_count() so constify them. Reported-by: Russell King (Oracle) Signed-off-by: Andy Shevchenko Link: https://lore.kernel.org/r/20230324112720.71315-1-andriy.shevchenko@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- include/linux/property.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/property.h b/include/linux/property.h index 110634f5db2e..4a536548606b 100644 --- a/include/linux/property.h +++ b/include/linux/property.h @@ -105,11 +105,11 @@ struct fwnode_handle *fwnode_get_next_parent(struct fwnode_handle *fwnode); for (parent = fwnode_get_parent(fwnode); parent; \ parent = fwnode_get_next_parent(parent)) -struct device *fwnode_get_next_parent_dev(struct fwnode_handle *fwnode); +struct device *fwnode_get_next_parent_dev(const struct fwnode_handle *fwnode); unsigned int fwnode_count_parents(const struct fwnode_handle *fwn); struct fwnode_handle *fwnode_get_nth_parent(struct fwnode_handle *fwn, unsigned int depth); -bool fwnode_is_ancestor_of(struct fwnode_handle *ancestor, struct fwnode_handle *child); +bool fwnode_is_ancestor_of(const struct fwnode_handle *ancestor, const struct fwnode_handle *child); struct fwnode_handle *fwnode_get_next_child_node( const struct fwnode_handle *fwnode, struct fwnode_handle *child); struct fwnode_handle *fwnode_get_next_available_child_node( @@ -433,7 +433,7 @@ static inline bool fwnode_graph_is_endpoint(const struct fwnode_handle *fwnode) struct fwnode_handle * fwnode_graph_get_endpoint_by_id(const struct fwnode_handle *fwnode, u32 port, u32 endpoint, unsigned long flags); -unsigned int fwnode_graph_get_endpoint_count(struct fwnode_handle *fwnode, +unsigned int fwnode_graph_get_endpoint_count(const struct fwnode_handle *fwnode, unsigned long flags); #define fwnode_graph_for_each_endpoint(fwnode, child) \ -- cgit v1.2.3 From dcfbb67e48a2becfce7990386e985b9c45098ee5 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 24 Mar 2023 11:01:31 +0100 Subject: driver core: class: use lock_class_key already present in struct subsys_private In commit 37e98d9bedb5 ("driver core: bus: move lock_class_key into dynamic structure"), we moved the lock_class_key into the internal structure shared by busses and classes, but only used it for buses. Move the class code to use this structure as it is already present and being allocated, instead of the statically allocated on-the-stack variable that class_create() was using as part of a macro wrapper around the core function call. Reviewed-by: Rafael J. Wysocki Link: https://lore.kernel.org/r/20230324100132.1633647-1-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- include/linux/device/class.h | 36 ++---------------------------------- 1 file changed, 2 insertions(+), 34 deletions(-) (limited to 'include/linux') diff --git a/include/linux/device/class.h b/include/linux/device/class.h index 75c1451fcc63..03d2f99f84c5 100644 --- a/include/linux/device/class.h +++ b/include/linux/device/class.h @@ -82,18 +82,9 @@ struct class_dev_iter { extern struct kobject *sysfs_dev_block_kobj; extern struct kobject *sysfs_dev_char_kobj; -extern int __must_check __class_register(struct class *class, - struct lock_class_key *key); +extern int __must_check class_register(struct class *class); extern void class_unregister(struct class *class); -/* This is a #define to keep the compiler from merging different - * instances of the __key variable */ -#define class_register(class) \ -({ \ - static struct lock_class_key __key; \ - __class_register(class, &__key); \ -}) - struct class_compat; struct class_compat *class_compat_register(const char *name); void class_compat_unregister(struct class_compat *cls); @@ -246,30 +237,7 @@ struct class_interface { extern int __must_check class_interface_register(struct class_interface *); extern void class_interface_unregister(struct class_interface *); -extern struct class * __must_check __class_create(const char *name, - struct lock_class_key *key); +extern struct class * __must_check class_create(const char *name); extern void class_destroy(struct class *cls); -/* This is a #define to keep the compiler from merging different - * instances of the __key variable */ - -/** - * class_create - create a struct class structure - * @name: pointer to a string for the name of this class. - * - * This is used to create a struct class pointer that can then be used - * in calls to device_create(). - * - * Returns &struct class pointer on success, or ERR_PTR() on error. - * - * Note, the pointer created here is to be destroyed when finished by - * making a call to class_destroy(). - */ -#define class_create(name) \ -({ \ - static struct lock_class_key __key; \ - __class_create(name, &__key); \ -}) - - #endif /* _DEVICE_CLASS_H_ */ -- cgit v1.2.3 From 43718dca48429b9eb5b82cdd41e2a1f162a02fb9 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 24 Mar 2023 11:01:32 +0100 Subject: driver core: class.h: remove extern from function prototypes The kernel coding style does not require 'extern' in function prototypes in .h files, so remove them from include/linux/device/class.h as they are not needed. Acked-by: Rafael J. Wysocki Link: https://lore.kernel.org/r/20230324100132.1633647-2-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- include/linux/device/class.h | 46 +++++++++++++++++++------------------------- 1 file changed, 20 insertions(+), 26 deletions(-) (limited to 'include/linux') diff --git a/include/linux/device/class.h b/include/linux/device/class.h index 03d2f99f84c5..1dc7706cb42d 100644 --- a/include/linux/device/class.h +++ b/include/linux/device/class.h @@ -82,8 +82,9 @@ struct class_dev_iter { extern struct kobject *sysfs_dev_block_kobj; extern struct kobject *sysfs_dev_char_kobj; -extern int __must_check class_register(struct class *class); -extern void class_unregister(struct class *class); + +int __must_check class_register(struct class *class); +void class_unregister(struct class *class); struct class_compat; struct class_compat *class_compat_register(const char *name); @@ -93,19 +94,15 @@ int class_compat_create_link(struct class_compat *cls, struct device *dev, void class_compat_remove_link(struct class_compat *cls, struct device *dev, struct device *device_link); -extern void class_dev_iter_init(struct class_dev_iter *iter, - const struct class *class, - const struct device *start, - const struct device_type *type); -extern struct device *class_dev_iter_next(struct class_dev_iter *iter); -extern void class_dev_iter_exit(struct class_dev_iter *iter); +void class_dev_iter_init(struct class_dev_iter *iter, const struct class *class, + const struct device *start, const struct device_type *type); +struct device *class_dev_iter_next(struct class_dev_iter *iter); +void class_dev_iter_exit(struct class_dev_iter *iter); -extern int class_for_each_device(const struct class *class, const struct device *start, - void *data, - int (*fn)(struct device *dev, void *data)); -extern struct device *class_find_device(const struct class *class, - const struct device *start, const void *data, - int (*match)(struct device *, const void *)); +int class_for_each_device(const struct class *class, const struct device *start, void *data, + int (*fn)(struct device *dev, void *data)); +struct device *class_find_device(const struct class *class, const struct device *start, + const void *data, int (*match)(struct device *, const void *)); /** * class_find_device_by_name - device iterator for locating a particular device @@ -191,12 +188,10 @@ struct class_attribute { #define CLASS_ATTR_WO(_name) \ struct class_attribute class_attr_##_name = __ATTR_WO(_name) -extern int __must_check class_create_file_ns(const struct class *class, - const struct class_attribute *attr, - const void *ns); -extern void class_remove_file_ns(const struct class *class, - const struct class_attribute *attr, - const void *ns); +int __must_check class_create_file_ns(const struct class *class, const struct class_attribute *attr, + const void *ns); +void class_remove_file_ns(const struct class *class, const struct class_attribute *attr, + const void *ns); static inline int __must_check class_create_file(const struct class *class, const struct class_attribute *attr) @@ -223,8 +218,7 @@ struct class_attribute_string { struct class_attribute_string class_attr_##_name = \ _CLASS_ATTR_STRING(_name, _mode, _str) -extern ssize_t show_class_attr_string(struct class *class, struct class_attribute *attr, - char *buf); +ssize_t show_class_attr_string(struct class *class, struct class_attribute *attr, char *buf); struct class_interface { struct list_head node; @@ -234,10 +228,10 @@ struct class_interface { void (*remove_dev) (struct device *, struct class_interface *); }; -extern int __must_check class_interface_register(struct class_interface *); -extern void class_interface_unregister(struct class_interface *); +int __must_check class_interface_register(struct class_interface *); +void class_interface_unregister(struct class_interface *); -extern struct class * __must_check class_create(const char *name); -extern void class_destroy(struct class *cls); +struct class * __must_check class_create(const char *name); +void class_destroy(struct class *cls); #endif /* _DEVICE_CLASS_H_ */ -- cgit v1.2.3 From f43243c66e5e9ad839d235f82a58e73a7e7612af Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 24 Mar 2023 13:27:06 +0100 Subject: driver core: device.h: remove extern from function prototypes The kernel coding style does not require 'extern' in function prototypes in .h files, so remove them from include/linux/device.h as they are not needed. Acked-by: Rafael J. Wysocki Link: https://lore.kernel.org/r/20230324122711.2664537-1-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 3b23772d3bbb..472dd24d4823 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -1088,8 +1088,7 @@ void device_link_remove(void *consumer, struct device *supplier); void device_links_supplier_sync_state_pause(void); void device_links_supplier_sync_state_resume(void); -extern __printf(3, 4) -int dev_err_probe(const struct device *dev, int err, const char *fmt, ...); +__printf(3, 4) int dev_err_probe(const struct device *dev, int err, const char *fmt, ...); /* Create alias, so I can be autoloaded. */ #define MODULE_ALIAS_CHARDEV(major,minor) \ -- cgit v1.2.3 From 0d62b79fd8083ae2400f31e38f8d63db3bd59bff Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 24 Mar 2023 13:27:07 +0100 Subject: driver core: bus.h: remove extern from function prototypes The kernel coding style does not require 'extern' in function prototypes in .h files, so remove them from include/linux/device/bus.h as they are not needed. Acked-by: Rafael J. Wysocki Link: https://lore.kernel.org/r/20230324122711.2664537-2-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- include/linux/device/bus.h | 14 ++++++-------- 1 file changed, 6 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/device/bus.h b/include/linux/device/bus.h index b517b82d4723..65a5e2c0f04d 100644 --- a/include/linux/device/bus.h +++ b/include/linux/device/bus.h @@ -110,11 +110,11 @@ struct bus_type { bool need_parent_lock; }; -extern int __must_check bus_register(const struct bus_type *bus); +int __must_check bus_register(const struct bus_type *bus); -extern void bus_unregister(const struct bus_type *bus); +void bus_unregister(const struct bus_type *bus); -extern int __must_check bus_rescan_devices(const struct bus_type *bus); +int __must_check bus_rescan_devices(const struct bus_type *bus); struct bus_attribute { struct attribute attr; @@ -244,10 +244,8 @@ void bus_sort_breadthfirst(struct bus_type *bus, */ struct notifier_block; -extern int bus_register_notifier(const struct bus_type *bus, - struct notifier_block *nb); -extern int bus_unregister_notifier(const struct bus_type *bus, - struct notifier_block *nb); +int bus_register_notifier(const struct bus_type *bus, struct notifier_block *nb); +int bus_unregister_notifier(const struct bus_type *bus, struct notifier_block *nb); /** * enum bus_notifier_event - Bus Notifier events that have happened @@ -279,7 +277,7 @@ enum bus_notifier_event { BUS_NOTIFY_DRIVER_NOT_BOUND, }; -extern struct kset *bus_get_kset(const struct bus_type *bus); +struct kset *bus_get_kset(const struct bus_type *bus); struct device *bus_get_dev_root(const struct bus_type *bus); #endif -- cgit v1.2.3 From 8a2b9c84c708cf2a99499d5a685a642af7b68c37 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 24 Mar 2023 13:27:08 +0100 Subject: driver core: driver.h: remove extern from function prototypes The kernel coding style does not require 'extern' in function prototypes in .h files, so remove them from include/linux/device/driver.h as they are not needed. Acked-by: Rafael J. Wysocki Link: https://lore.kernel.org/r/20230324122711.2664537-3-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- include/linux/device/driver.h | 26 +++++++++++--------------- 1 file changed, 11 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/device/driver.h b/include/linux/device/driver.h index 0f22a6f46f8c..c244267a6744 100644 --- a/include/linux/device/driver.h +++ b/include/linux/device/driver.h @@ -122,13 +122,12 @@ struct device_driver { }; -extern int __must_check driver_register(struct device_driver *drv); -extern void driver_unregister(struct device_driver *drv); +int __must_check driver_register(struct device_driver *drv); +void driver_unregister(struct device_driver *drv); -extern struct device_driver *driver_find(const char *name, - const struct bus_type *bus); -extern int driver_probe_done(void); -extern void wait_for_device_probe(void); +struct device_driver *driver_find(const char *name, const struct bus_type *bus); +int driver_probe_done(void); +void wait_for_device_probe(void); void __init wait_for_init_devices_probe(void); /* sysfs interface for exporting driver attributes */ @@ -147,18 +146,15 @@ struct driver_attribute { #define DRIVER_ATTR_WO(_name) \ struct driver_attribute driver_attr_##_name = __ATTR_WO(_name) -extern int __must_check driver_create_file(struct device_driver *driver, - const struct driver_attribute *attr); -extern void driver_remove_file(struct device_driver *driver, - const struct driver_attribute *attr); +int __must_check driver_create_file(struct device_driver *driver, + const struct driver_attribute *attr); +void driver_remove_file(struct device_driver *driver, + const struct driver_attribute *attr); int driver_set_override(struct device *dev, const char **override, const char *s, size_t len); -extern int __must_check driver_for_each_device(struct device_driver *drv, - struct device *start, - void *data, - int (*fn)(struct device *dev, - void *)); +int __must_check driver_for_each_device(struct device_driver *drv, struct device *start, + void *data, int (*fn)(struct device *dev, void *)); struct device *driver_find_device(struct device_driver *drv, struct device *start, const void *data, int (*match)(struct device *dev, const void *data)); -- cgit v1.2.3 From 44650f33d3bd76dd968cb8880c8eedd465030cd5 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 24 Mar 2023 13:27:11 +0100 Subject: kobject.h remove extern from function prototypes The kernel coding style does not require 'extern' in function prototypes in .h files, so remove them from include/linux/kobject.h as they are not needed. Acked-by: Rafael J. Wysocki Link: https://lore.kernel.org/r/20230324122711.2664537-6-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- include/linux/kobject.h | 59 ++++++++++++++++++++++--------------------------- 1 file changed, 26 insertions(+), 33 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kobject.h b/include/linux/kobject.h index bdab370a24f4..c392c811d9ad 100644 --- a/include/linux/kobject.h +++ b/include/linux/kobject.h @@ -79,43 +79,37 @@ struct kobject { unsigned int uevent_suppress:1; }; -extern __printf(2, 3) -int kobject_set_name(struct kobject *kobj, const char *name, ...); -extern __printf(2, 0) -int kobject_set_name_vargs(struct kobject *kobj, const char *fmt, - va_list vargs); +__printf(2, 3) int kobject_set_name(struct kobject *kobj, const char *name, ...); +__printf(2, 0) int kobject_set_name_vargs(struct kobject *kobj, const char *fmt, va_list vargs); static inline const char *kobject_name(const struct kobject *kobj) { return kobj->name; } -extern void kobject_init(struct kobject *kobj, const struct kobj_type *ktype); -extern __printf(3, 4) __must_check -int kobject_add(struct kobject *kobj, struct kobject *parent, - const char *fmt, ...); -extern __printf(4, 5) __must_check -int kobject_init_and_add(struct kobject *kobj, - const struct kobj_type *ktype, struct kobject *parent, - const char *fmt, ...); +void kobject_init(struct kobject *kobj, const struct kobj_type *ktype); +__printf(3, 4) __must_check int kobject_add(struct kobject *kobj, + struct kobject *parent, + const char *fmt, ...); +__printf(4, 5) __must_check int kobject_init_and_add(struct kobject *kobj, + const struct kobj_type *ktype, + struct kobject *parent, + const char *fmt, ...); -extern void kobject_del(struct kobject *kobj); +void kobject_del(struct kobject *kobj); -extern struct kobject * __must_check kobject_create_and_add(const char *name, - struct kobject *parent); +struct kobject * __must_check kobject_create_and_add(const char *name, struct kobject *parent); -extern int __must_check kobject_rename(struct kobject *, const char *new_name); -extern int __must_check kobject_move(struct kobject *, struct kobject *); +int __must_check kobject_rename(struct kobject *, const char *new_name); +int __must_check kobject_move(struct kobject *, struct kobject *); -extern struct kobject *kobject_get(struct kobject *kobj); -extern struct kobject * __must_check kobject_get_unless_zero( - struct kobject *kobj); -extern void kobject_put(struct kobject *kobj); +struct kobject *kobject_get(struct kobject *kobj); +struct kobject * __must_check kobject_get_unless_zero(struct kobject *kobj); +void kobject_put(struct kobject *kobj); -extern const void *kobject_namespace(const struct kobject *kobj); -extern void kobject_get_ownership(const struct kobject *kobj, - kuid_t *uid, kgid_t *gid); -extern char *kobject_get_path(const struct kobject *kobj, gfp_t flag); +const void *kobject_namespace(const struct kobject *kobj); +void kobject_get_ownership(const struct kobject *kobj, kuid_t *uid, kgid_t *gid); +char *kobject_get_path(const struct kobject *kobj, gfp_t flag); struct kobj_type { void (*release)(struct kobject *kobj); @@ -176,12 +170,11 @@ struct kset { const struct kset_uevent_ops *uevent_ops; } __randomize_layout; -extern void kset_init(struct kset *kset); -extern int __must_check kset_register(struct kset *kset); -extern void kset_unregister(struct kset *kset); -extern struct kset * __must_check kset_create_and_add(const char *name, - const struct kset_uevent_ops *u, - struct kobject *parent_kobj); +void kset_init(struct kset *kset); +int __must_check kset_register(struct kset *kset); +void kset_unregister(struct kset *kset); +struct kset * __must_check kset_create_and_add(const char *name, const struct kset_uevent_ops *u, + struct kobject *parent_kobj); static inline struct kset *to_kset(struct kobject *kobj) { @@ -203,7 +196,7 @@ static inline const struct kobj_type *get_ktype(const struct kobject *kobj) return kobj->ktype; } -extern struct kobject *kset_find_obj(struct kset *, const char *); +struct kobject *kset_find_obj(struct kset *, const char *); /* The global /sys/kernel/ kobject for people to chain off of */ extern struct kobject *kernel_kobj; -- cgit v1.2.3 From b0d237087c674c43df76c1a0bc2737592f3038f4 Mon Sep 17 00:00:00 2001 From: Jun Miao Date: Thu, 23 Feb 2023 13:28:51 +0800 Subject: KVM: Fix comments that refer to the non-existent install_new_memslots() Fix stale comments that were left behind when install_new_memslots() was replaced by kvm_swap_active_memslots() as part of the scalable memslots rework. Fixes: a54d806688fe ("KVM: Keep memslots in tree-based structures instead of array-based ones") Signed-off-by: Jun Miao Link: https://lore.kernel.org/r/20230223052851.1054799-1-jun.miao@intel.com Signed-off-by: Sean Christopherson --- include/linux/kvm_host.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 90edc16d37e5..9696c2fb30e9 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -58,7 +58,7 @@ /* * Bit 63 of the memslot generation number is an "update in-progress flag", - * e.g. is temporarily set for the duration of install_new_memslots(). + * e.g. is temporarily set for the duration of kvm_swap_active_memslots(). * This flag effectively creates a unique generation number that is used to * mark cached memslot data, e.g. MMIO accesses, as potentially being stale, * i.e. may (or may not) have come from the previous memslots generation. @@ -713,7 +713,7 @@ struct kvm { * use by the VM. To be used under the slots_lock (above) or in a * kvm->srcu critical section where acquiring the slots_lock would * lead to deadlock with the synchronize_srcu in - * install_new_memslots. + * kvm_swap_active_memslots(). */ struct mutex slots_arch_lock; struct mm_struct *mm; /* userspace tied to this vm */ -- cgit v1.2.3 From 340133318800b55784792d762c7713265c96336a Mon Sep 17 00:00:00 2001 From: Lukas Bulwahn Date: Fri, 24 Mar 2023 10:21:14 +0100 Subject: selinux: clean up dead code after removing runtime disable Commit f22f9aaf6c3d ("selinux: remove the runtime disable functionality") removes the config SECURITY_SELINUX_DISABLE. This results in some dead code in lsm_hooks.h. Remove this dead code. Signed-off-by: Lukas Bulwahn Signed-off-by: Paul Moore --- include/linux/lsm_hooks.h | 23 ----------------------- 1 file changed, 23 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index af87b962f5f7..60cdc83bf8af 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -1740,29 +1740,6 @@ extern struct lsm_info __start_early_lsm_info[], __end_early_lsm_info[]; __used __section(".early_lsm_info.init") \ __aligned(sizeof(unsigned long)) -#ifdef CONFIG_SECURITY_SELINUX_DISABLE -/* - * Assuring the safety of deleting a security module is up to - * the security module involved. This may entail ordering the - * module's hook list in a particular way, refusing to disable - * the module once a policy is loaded or any number of other - * actions better imagined than described. - * - * The name of the configuration option reflects the only module - * that currently uses the mechanism. Any developer who thinks - * disabling their module is a good idea needs to be at least as - * careful as the SELinux team. - */ -static inline void security_delete_hooks(struct security_hook_list *hooks, - int count) -{ - int i; - - for (i = 0; i < count; i++) - hlist_del_rcu(&hooks[i].list); -} -#endif /* CONFIG_SECURITY_SELINUX_DISABLE */ - extern int lsm_inode_alloc(struct inode *inode); #endif /* ! __LINUX_LSM_HOOKS_H */ -- cgit v1.2.3 From 9821d8d4628e630ab56f47a8e6b878a2576e069b Mon Sep 17 00:00:00 2001 From: Eli Cohen Date: Tue, 14 Feb 2023 09:29:46 +0200 Subject: lib: cpu_rmap: Use allocator for rmap entries Use a proper allocator for rmap entries using a naive for loop. The allocator relies on whether an entry is NULL to be considered free. Remove the used field of rmap which is not needed. Also, avoid crashing the kernel if an entry is not available. Cc: Thomas Gleixner Signed-off-by: Eli Cohen Signed-off-by: Saeed Mahameed Reviewed-by: Jacob Keller --- include/linux/cpu_rmap.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpu_rmap.h b/include/linux/cpu_rmap.h index be8aea04d023..0ec745e6cd36 100644 --- a/include/linux/cpu_rmap.h +++ b/include/linux/cpu_rmap.h @@ -16,14 +16,13 @@ * struct cpu_rmap - CPU affinity reverse-map * @refcount: kref for object * @size: Number of objects to be reverse-mapped - * @used: Number of objects added * @obj: Pointer to array of object pointers * @near: For each CPU, the index and distance to the nearest object, * based on affinity masks */ struct cpu_rmap { struct kref refcount; - u16 size, used; + u16 size; void **obj; struct { u16 index; -- cgit v1.2.3 From 71f0a2478605c100358a9f9e174849fa643bf8a7 Mon Sep 17 00:00:00 2001 From: Eli Cohen Date: Tue, 14 Feb 2023 11:05:46 +0200 Subject: lib: cpu_rmap: Add irq_cpu_rmap_remove to complement irq_cpu_rmap_add Add a function to complement irq_cpu_rmap_add(). It removes the irq from the reverse mapping by setting the notifier to NULL. The function calls irq_set_affinity_notifier() with NULL at the notify argument which then cancel any pending notifier work and decrement reference on the notifier. When ref count reaches zero, the glue pointer is kfree and the rmap entry is set to NULL serving both to avoid second attempt to release it and also making the rmap entry available for subsequent mapping. It should be noted the drivers usually creates the reverse mapping at initialization time and remove it at unload time so we do not expect failures in allocating rmap due to kref holding the glue entry. Cc: Thomas Gleixner Signed-off-by: Eli Cohen Signed-off-by: Saeed Mahameed Reviewed-by: Jacob Keller --- include/linux/cpu_rmap.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/cpu_rmap.h b/include/linux/cpu_rmap.h index 0ec745e6cd36..cae324d10965 100644 --- a/include/linux/cpu_rmap.h +++ b/include/linux/cpu_rmap.h @@ -60,6 +60,7 @@ static inline struct cpu_rmap *alloc_irq_cpu_rmap(unsigned int size) } extern void free_irq_cpu_rmap(struct cpu_rmap *rmap); +int irq_cpu_rmap_remove(struct cpu_rmap *rmap, int irq); extern int irq_cpu_rmap_add(struct cpu_rmap *rmap, int irq); #endif /* __LINUX_CPU_RMAP_H */ -- cgit v1.2.3 From fb0a6a268dcd6fe144c99d60a1166e34c6991d5f Mon Sep 17 00:00:00 2001 From: Eli Cohen Date: Thu, 5 Jan 2023 11:31:46 +0200 Subject: net/mlx5: Provide external API for allocating vectors Provide external API to be used by other drivers relying on mlx5_core, for allocating MSIX vectors. An example for such a driver would be mlx5_vdpa. Signed-off-by: Eli Cohen Reviewed-by: Shay Drory Signed-off-by: Saeed Mahameed Reviewed-by: Jacob Keller --- include/linux/mlx5/driver.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index f33389b42209..df0f82110249 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -1308,4 +1308,10 @@ enum { MLX5_OCTWORD = 16, }; +struct msi_map mlx5_msix_alloc(struct mlx5_core_dev *dev, + irqreturn_t (*handler)(int, void *), + const struct irq_affinity_desc *affdesc, + const char *name); +void mlx5_msix_free(struct mlx5_core_dev *dev, struct msi_map map); + #endif /* MLX5_DRIVER_H */ -- cgit v1.2.3 From e0d3f2c694e5db309af270a07fc570fe19902ba4 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Wed, 22 Mar 2023 12:53:58 -0700 Subject: scsi: core: Declare SCSI host template pointer members const Declare the SCSI host template pointer members const and also the remaining SCSI host template pointers in the SCSI core. Reviewed-by: Benjamin Block Reviewed-by: John Garry Cc: Christoph Hellwig Cc: Ming Lei Cc: Hannes Reinecke Cc: Mike Christie Signed-off-by: Bart Van Assche Link: https://lore.kernel.org/r/20230322195515.1267197-4-bvanassche@acm.org Signed-off-by: Martin K. Petersen --- include/linux/raid_class.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/raid_class.h b/include/linux/raid_class.h index 5cdfcb873a8f..6a9b177d5c41 100644 --- a/include/linux/raid_class.h +++ b/include/linux/raid_class.h @@ -11,7 +11,7 @@ struct raid_template { }; struct raid_function_template { - void *cookie; + const void *cookie; int (*is_raid)(struct device *); void (*get_resync)(struct device *); void (*get_state)(struct device *); -- cgit v1.2.3 From 25df73d93323e20c1f05700776fe3df75d3b27b2 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Wed, 22 Mar 2023 12:53:59 -0700 Subject: scsi: ata: Declare SCSI host templates const Make it explicit that ATA host templates are not modified. Reviewed-by: Linus Walleij Acked-by: Damien Le Moal Reviewed-by: Serge Semin (for DWC AHCI SATA) Reviewed-by: John Garry Reviewed-by: Jon Hunter (for Tegra) Cc: Christoph Hellwig Cc: Ming Lei Cc: Hannes Reinecke Cc: John Garry Cc: Mike Christie Signed-off-by: Bart Van Assche Link: https://lore.kernel.org/r/20230322195515.1267197-5-bvanassche@acm.org Signed-off-by: Martin K. Petersen --- include/linux/ahci_platform.h | 2 +- include/linux/ata_platform.h | 2 +- include/linux/libata.h | 10 +++++----- 3 files changed, 7 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ahci_platform.h b/include/linux/ahci_platform.h index 17fa26215292..fe0760ce34c8 100644 --- a/include/linux/ahci_platform.h +++ b/include/linux/ahci_platform.h @@ -37,7 +37,7 @@ struct ahci_host_priv *ahci_platform_get_resources( int ahci_platform_init_host(struct platform_device *pdev, struct ahci_host_priv *hpriv, const struct ata_port_info *pi_template, - struct scsi_host_template *sht); + const struct scsi_host_template *sht); void ahci_platform_shutdown(struct platform_device *pdev); diff --git a/include/linux/ata_platform.h b/include/linux/ata_platform.h index 9cafec92282d..b9745cc08e38 100644 --- a/include/linux/ata_platform.h +++ b/include/linux/ata_platform.h @@ -19,7 +19,7 @@ extern int __pata_platform_probe(struct device *dev, struct resource *irq_res, unsigned int ioport_shift, int __pio_mask, - struct scsi_host_template *sht, + const struct scsi_host_template *sht, bool use16bit); /* diff --git a/include/linux/libata.h b/include/linux/libata.h index a759dfbdcc91..311cd93377c7 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -1065,10 +1065,10 @@ extern void ata_host_get(struct ata_host *host); extern void ata_host_put(struct ata_host *host); extern int ata_host_start(struct ata_host *host); extern int ata_host_register(struct ata_host *host, - struct scsi_host_template *sht); + const struct scsi_host_template *sht); extern int ata_host_activate(struct ata_host *host, int irq, irq_handler_t irq_handler, unsigned long irq_flags, - struct scsi_host_template *sht); + const struct scsi_host_template *sht); extern void ata_host_detach(struct ata_host *host); extern void ata_host_init(struct ata_host *, struct device *, struct ata_port_operations *); extern int ata_scsi_detect(struct scsi_host_template *sht); @@ -1980,10 +1980,10 @@ extern int ata_pci_sff_prepare_host(struct pci_dev *pdev, struct ata_host **r_host); extern int ata_pci_sff_activate_host(struct ata_host *host, irq_handler_t irq_handler, - struct scsi_host_template *sht); + const struct scsi_host_template *sht); extern int ata_pci_sff_init_one(struct pci_dev *pdev, const struct ata_port_info * const * ppi, - struct scsi_host_template *sht, void *host_priv, int hflags); + const struct scsi_host_template *sht, void *host_priv, int hflags); #endif /* CONFIG_PCI */ #ifdef CONFIG_ATA_BMDMA @@ -2019,7 +2019,7 @@ extern int ata_pci_bmdma_prepare_host(struct pci_dev *pdev, struct ata_host **r_host); extern int ata_pci_bmdma_init_one(struct pci_dev *pdev, const struct ata_port_info * const * ppi, - struct scsi_host_template *sht, + const struct scsi_host_template *sht, void *host_priv, int hflags); #endif /* CONFIG_PCI */ #endif /* CONFIG_ATA_BMDMA */ -- cgit v1.2.3 From 009455205e68ef017a429dc818b92c4a84b867c4 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 24 Mar 2023 10:08:14 +0100 Subject: driver core: bus: move documentation for lock_key to proper location. In commit 37e98d9bedb5 ("driver core: bus: move lock_class_key into dynamic structure"), the lock_key variable moved out of struct bus_type and into struct subsys_private, yet the documentation for it did not move. Fix that up and place the documentation comment in the correct location. Cc: "Rafael J. Wysocki" Fixes: 37e98d9bedb5 ("driver core: bus: move lock_class_key into dynamic structure") Link: https://lore.kernel.org/r/20230324090814.386654-1-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- include/linux/device/bus.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/device/bus.h b/include/linux/device/bus.h index 65a5e2c0f04d..ae10c4322754 100644 --- a/include/linux/device/bus.h +++ b/include/linux/device/bus.h @@ -65,7 +65,6 @@ struct fwnode_handle; * @iommu_ops: IOMMU specific operations for this bus, used to attach IOMMU * driver implementations to a bus and allow the driver to do * bus-specific setup - * @lock_key: Lock class key for use by the lock validator * @need_parent_lock: When probing or removing a device on this bus, the * device core should lock the device's parent. * -- cgit v1.2.3 From e65a5c6edbc6ca4853e6076bd81db1a410592a09 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Wed, 22 Mar 2023 14:52:42 -0700 Subject: bpf: Add a few bpf mem allocator functions This patch adds a few bpf mem allocator functions which will be used in the bpf_local_storage in a later patch. bpf_mem_cache_alloc_flags(..., gfp_t flags) is added. When the flags == GFP_KERNEL, it will fallback to __alloc(..., GFP_KERNEL). bpf_local_storage knows its running context is sleepable (GFP_KERNEL) and provides a better guarantee on memory allocation. bpf_local_storage has some uncommon cases that its selem cannot be reused immediately. It handles its own rcu_head and goes through a rcu_trace gp and then free it. bpf_mem_cache_raw_free() is added for direct free purpose without leaking the LLIST_NODE_SZ internal knowledge. During free time, the 'struct bpf_mem_alloc *ma' is no longer available. However, the caller should know if it is percpu memory or not and it can call different raw_free functions. bpf_local_storage does not support percpu value, so only the non-percpu 'bpf_mem_cache_raw_free()' is added in this patch. Signed-off-by: Martin KaFai Lau Link: https://lore.kernel.org/r/20230322215246.1675516-2-martin.lau@linux.dev Signed-off-by: Alexei Starovoitov --- include/linux/bpf_mem_alloc.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf_mem_alloc.h b/include/linux/bpf_mem_alloc.h index a7104af61ab4..3929be5743f4 100644 --- a/include/linux/bpf_mem_alloc.h +++ b/include/linux/bpf_mem_alloc.h @@ -31,5 +31,7 @@ void bpf_mem_free(struct bpf_mem_alloc *ma, void *ptr); /* kmem_cache_alloc/free equivalent: */ void *bpf_mem_cache_alloc(struct bpf_mem_alloc *ma); void bpf_mem_cache_free(struct bpf_mem_alloc *ma, void *ptr); +void bpf_mem_cache_raw_free(void *ptr); +void *bpf_mem_cache_alloc_flags(struct bpf_mem_alloc *ma, gfp_t flags); #endif /* _BPF_MEM_ALLOC_H */ -- cgit v1.2.3 From 08a7ce384e33e53e0732c500a8af67a73f8fceca Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Wed, 22 Mar 2023 14:52:43 -0700 Subject: bpf: Use bpf_mem_cache_alloc/free in bpf_local_storage_elem This patch uses bpf_mem_alloc for the task and cgroup local storage that the bpf prog can easily get a hold of the storage owner's PTR_TO_BTF_ID. eg. bpf_get_current_task_btf() can be used in some of the kmalloc code path which will cause deadlock/recursion. bpf_mem_cache_alloc is deadlock free and will solve a legit use case in [1]. For sk storage, its batch creation benchmark shows a few percent regression when the sk create/destroy batch size is larger than 32. The sk creation/destruction happens much more often and depends on external traffic. Considering it is hypothetical to be able to cause deadlock with sk storage, it can cross the bridge to use bpf_mem_alloc till a legit (ie. useful) use case comes up. For inode storage, bpf_local_storage_destroy() is called before waiting for a rcu gp and its memory cannot be reused immediately. inode stays with kmalloc/kfree after the rcu [or tasks_trace] gp. A 'bool bpf_ma' argument is added to bpf_local_storage_map_alloc(). Only task and cgroup storage have 'bpf_ma == true' which means to use bpf_mem_cache_alloc/free(). This patch only changes selem to use bpf_mem_alloc for task and cgroup. The next patch will change the local_storage to use bpf_mem_alloc also for task and cgroup. Here is some more details on the changes: * memory allocation: After bpf_mem_cache_alloc(), the SDATA(selem)->data is zero-ed because bpf_mem_cache_alloc() could return a reused selem. It is to keep the existing bpf_map_kzalloc() behavior. Only SDATA(selem)->data is zero-ed. SDATA(selem)->data is the visible part to the bpf prog. No need to use zero_map_value() to do the zeroing because bpf_selem_free(..., reuse_now = true) ensures no bpf prog is using the selem before returning the selem through bpf_mem_cache_free(). For the internal fields of selem, they will be initialized when linking to the new smap and the new local_storage. When 'bpf_ma == false', nothing changes in this patch. It will stay with the bpf_map_kzalloc(). * memory free: The bpf_selem_free() and bpf_selem_free_rcu() are modified to handle the bpf_ma == true case. For the common selem free path where its owner is also being destroyed, the mem is freed in bpf_local_storage_destroy(), the owner (task and cgroup) has gone through a rcu gp. The memory can be reused immediately, so bpf_local_storage_destroy() will call bpf_selem_free(..., reuse_now = true) which will do bpf_mem_cache_free() for immediate reuse consideration. An exception is the delete elem code path. The delete elem code path is called from the helper bpf_*_storage_delete() and the syscall bpf_map_delete_elem(). This path is an unusual case for local storage because the common use case is to have the local storage staying with its owner life time so that the bpf prog and the user space does not have to monitor the owner's destruction. For the delete elem path, the selem cannot be reused immediately because there could be bpf prog using it. It will call bpf_selem_free(..., reuse_now = false) and it will wait for a rcu tasks trace gp before freeing the elem. The rcu callback is changed to do bpf_mem_cache_raw_free() instead of kfree(). When 'bpf_ma == false', it should be the same as before. __bpf_selem_free() is added to do the kfree_rcu and call_tasks_trace_rcu(). A few words on the 'reuse_now == true'. When 'reuse_now == true', it is still racing with bpf_local_storage_map_free which is under rcu protection, so it still needs to wait for a rcu gp instead of kfree(). Otherwise, the selem may be reused by slab for a totally different struct while the bpf_local_storage_map_free() is still using it (as a rcu reader). For the inode case, there may be other rcu readers also. In short, when bpf_ma == false and reuse_now == true => vanilla rcu. [1]: https://lore.kernel.org/bpf/20221118190109.1512674-1-namhyung@kernel.org/ Cc: Namhyung Kim Signed-off-by: Martin KaFai Lau Link: https://lore.kernel.org/r/20230322215246.1675516-3-martin.lau@linux.dev Signed-off-by: Alexei Starovoitov --- include/linux/bpf_local_storage.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bpf_local_storage.h b/include/linux/bpf_local_storage.h index a34f61467a2f..30efbcab2798 100644 --- a/include/linux/bpf_local_storage.h +++ b/include/linux/bpf_local_storage.h @@ -13,6 +13,7 @@ #include #include #include +#include #include #define BPF_LOCAL_STORAGE_CACHE_SIZE 16 @@ -55,6 +56,8 @@ struct bpf_local_storage_map { u32 bucket_log; u16 elem_size; u16 cache_idx; + struct bpf_mem_alloc selem_ma; + bool bpf_ma; }; struct bpf_local_storage_data { @@ -122,7 +125,8 @@ int bpf_local_storage_map_alloc_check(union bpf_attr *attr); struct bpf_map * bpf_local_storage_map_alloc(union bpf_attr *attr, - struct bpf_local_storage_cache *cache); + struct bpf_local_storage_cache *cache, + bool bpf_ma); struct bpf_local_storage_data * bpf_local_storage_lookup(struct bpf_local_storage *local_storage, -- cgit v1.2.3 From 6ae9d5e99e1dd26babdd9502759fa25a3fd348ad Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Wed, 22 Mar 2023 14:52:44 -0700 Subject: bpf: Use bpf_mem_cache_alloc/free for bpf_local_storage This patch uses bpf_mem_cache_alloc/free for allocating and freeing bpf_local_storage for task and cgroup storage. The changes are similar to the previous patch. A few things that worth to mention for bpf_local_storage: The local_storage is freed when the last selem is deleted. Before deleting a selem from local_storage, it needs to retrieve the local_storage->smap because the bpf_selem_unlink_storage_nolock() may have set it to NULL. Note that local_storage->smap may have already been NULL when the selem created this local_storage has been removed. In this case, call_rcu will be used to free the local_storage. Also, the bpf_ma (true or false) value is needed before calling bpf_local_storage_free(). The bpf_ma can either be obtained from the local_storage->smap (if available) or any of its selem's smap. A new helper check_storage_bpf_ma() is added to obtain bpf_ma for a deleting bpf_local_storage. When bpf_local_storage_alloc getting a reused memory, all fields are either in the correct values or will be initialized. 'cache[]' must already be all NULLs. 'list' must be empty. Others will be initialized. Cc: Namhyung Kim Signed-off-by: Martin KaFai Lau Link: https://lore.kernel.org/r/20230322215246.1675516-4-martin.lau@linux.dev Signed-off-by: Alexei Starovoitov --- include/linux/bpf_local_storage.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/bpf_local_storage.h b/include/linux/bpf_local_storage.h index 30efbcab2798..173ec7f43ed1 100644 --- a/include/linux/bpf_local_storage.h +++ b/include/linux/bpf_local_storage.h @@ -57,6 +57,7 @@ struct bpf_local_storage_map { u16 elem_size; u16 cache_idx; struct bpf_mem_alloc selem_ma; + struct bpf_mem_alloc storage_ma; bool bpf_ma; }; -- cgit v1.2.3 From a90ac762d345890b40d88a1385a34a2449c2d75e Mon Sep 17 00:00:00 2001 From: "Russell King (Oracle)" Date: Fri, 24 Mar 2023 09:23:42 +0000 Subject: net: sfp: make sfp_bus_find_fwnode() take a const fwnode sfp_bus_find_fwnode() does not write to the fwnode, so let's make it const. Signed-off-by: Russell King (Oracle) Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- include/linux/sfp.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sfp.h b/include/linux/sfp.h index 52b98f9666a2..ef06a195b3c2 100644 --- a/include/linux/sfp.h +++ b/include/linux/sfp.h @@ -557,7 +557,7 @@ int sfp_get_module_eeprom_by_page(struct sfp_bus *bus, void sfp_upstream_start(struct sfp_bus *bus); void sfp_upstream_stop(struct sfp_bus *bus); void sfp_bus_put(struct sfp_bus *bus); -struct sfp_bus *sfp_bus_find_fwnode(struct fwnode_handle *fwnode); +struct sfp_bus *sfp_bus_find_fwnode(const struct fwnode_handle *fwnode); int sfp_bus_add_upstream(struct sfp_bus *bus, void *upstream, const struct sfp_upstream_ops *ops); void sfp_bus_del_upstream(struct sfp_bus *bus); @@ -619,7 +619,8 @@ static inline void sfp_bus_put(struct sfp_bus *bus) { } -static inline struct sfp_bus *sfp_bus_find_fwnode(struct fwnode_handle *fwnode) +static inline struct sfp_bus * +sfp_bus_find_fwnode(const struct fwnode_handle *fwnode) { return NULL; } -- cgit v1.2.3 From 4a0faa02d419a6728abef0f1d8a32d8c35ef95e6 Mon Sep 17 00:00:00 2001 From: "Russell King (Oracle)" Date: Fri, 24 Mar 2023 09:23:53 +0000 Subject: net: phy: constify fwnode_get_phy_node() fwnode argument fwnode_get_phy_node() does not motify the fwnode structure, so make the argument const, Signed-off-by: Russell King (Oracle) Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- include/linux/phy.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 36bf0bbc8efa..db7c0bd67559 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1547,7 +1547,7 @@ int fwnode_get_phy_id(struct fwnode_handle *fwnode, u32 *phy_id); struct mdio_device *fwnode_mdio_find_device(struct fwnode_handle *fwnode); struct phy_device *fwnode_phy_find_device(struct fwnode_handle *phy_fwnode); struct phy_device *device_phy_find_device(struct device *dev); -struct fwnode_handle *fwnode_get_phy_node(struct fwnode_handle *fwnode); +struct fwnode_handle *fwnode_get_phy_node(const struct fwnode_handle *fwnode); struct phy_device *get_phy_device(struct mii_bus *bus, int addr, bool is_c45); int phy_device_register(struct phy_device *phy); void phy_device_free(struct phy_device *phydev); -- cgit v1.2.3 From 7755cec63adeecea3cbbf4032047812c37cf7cc3 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Fri, 17 Mar 2023 15:50:20 -0400 Subject: arm64: perf: Move PMUv3 driver to drivers/perf Having the ARM PMUv3 driver sitting in arch/arm64/kernel is getting in the way of being able to use perf on ARMv8 cores running a 32bit kernel, such as 32bit KVM guests. This patch moves it into drivers/perf/arm_pmuv3.c, with an include file in include/linux/perf/arm_pmuv3.h. The only thing left in arch/arm64 is some mundane perf stuff. Signed-off-by: Marc Zyngier Signed-off-by: Zaid Al-Bassam Tested-by: Florian Fainelli Link: https://lore.kernel.org/r/20230317195027.3746949-2-zalbassam@google.com Signed-off-by: Will Deacon --- include/linux/perf/arm_pmuv3.h | 258 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 258 insertions(+) create mode 100644 include/linux/perf/arm_pmuv3.h (limited to 'include/linux') diff --git a/include/linux/perf/arm_pmuv3.h b/include/linux/perf/arm_pmuv3.h new file mode 100644 index 000000000000..53173abfc022 --- /dev/null +++ b/include/linux/perf/arm_pmuv3.h @@ -0,0 +1,258 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2012 ARM Ltd. + */ + +#ifndef __PERF_ARM_PMUV3_H +#define __PERF_ARM_PMUV3_H + +#define ARMV8_PMU_MAX_COUNTERS 32 +#define ARMV8_PMU_COUNTER_MASK (ARMV8_PMU_MAX_COUNTERS - 1) + +/* + * Common architectural and microarchitectural event numbers. + */ +#define ARMV8_PMUV3_PERFCTR_SW_INCR 0x0000 +#define ARMV8_PMUV3_PERFCTR_L1I_CACHE_REFILL 0x0001 +#define ARMV8_PMUV3_PERFCTR_L1I_TLB_REFILL 0x0002 +#define ARMV8_PMUV3_PERFCTR_L1D_CACHE_REFILL 0x0003 +#define ARMV8_PMUV3_PERFCTR_L1D_CACHE 0x0004 +#define ARMV8_PMUV3_PERFCTR_L1D_TLB_REFILL 0x0005 +#define ARMV8_PMUV3_PERFCTR_LD_RETIRED 0x0006 +#define ARMV8_PMUV3_PERFCTR_ST_RETIRED 0x0007 +#define ARMV8_PMUV3_PERFCTR_INST_RETIRED 0x0008 +#define ARMV8_PMUV3_PERFCTR_EXC_TAKEN 0x0009 +#define ARMV8_PMUV3_PERFCTR_EXC_RETURN 0x000A +#define ARMV8_PMUV3_PERFCTR_CID_WRITE_RETIRED 0x000B +#define ARMV8_PMUV3_PERFCTR_PC_WRITE_RETIRED 0x000C +#define ARMV8_PMUV3_PERFCTR_BR_IMMED_RETIRED 0x000D +#define ARMV8_PMUV3_PERFCTR_BR_RETURN_RETIRED 0x000E +#define ARMV8_PMUV3_PERFCTR_UNALIGNED_LDST_RETIRED 0x000F +#define ARMV8_PMUV3_PERFCTR_BR_MIS_PRED 0x0010 +#define ARMV8_PMUV3_PERFCTR_CPU_CYCLES 0x0011 +#define ARMV8_PMUV3_PERFCTR_BR_PRED 0x0012 +#define ARMV8_PMUV3_PERFCTR_MEM_ACCESS 0x0013 +#define ARMV8_PMUV3_PERFCTR_L1I_CACHE 0x0014 +#define ARMV8_PMUV3_PERFCTR_L1D_CACHE_WB 0x0015 +#define ARMV8_PMUV3_PERFCTR_L2D_CACHE 0x0016 +#define ARMV8_PMUV3_PERFCTR_L2D_CACHE_REFILL 0x0017 +#define ARMV8_PMUV3_PERFCTR_L2D_CACHE_WB 0x0018 +#define ARMV8_PMUV3_PERFCTR_BUS_ACCESS 0x0019 +#define ARMV8_PMUV3_PERFCTR_MEMORY_ERROR 0x001A +#define ARMV8_PMUV3_PERFCTR_INST_SPEC 0x001B +#define ARMV8_PMUV3_PERFCTR_TTBR_WRITE_RETIRED 0x001C +#define ARMV8_PMUV3_PERFCTR_BUS_CYCLES 0x001D +#define ARMV8_PMUV3_PERFCTR_CHAIN 0x001E +#define ARMV8_PMUV3_PERFCTR_L1D_CACHE_ALLOCATE 0x001F +#define ARMV8_PMUV3_PERFCTR_L2D_CACHE_ALLOCATE 0x0020 +#define ARMV8_PMUV3_PERFCTR_BR_RETIRED 0x0021 +#define ARMV8_PMUV3_PERFCTR_BR_MIS_PRED_RETIRED 0x0022 +#define ARMV8_PMUV3_PERFCTR_STALL_FRONTEND 0x0023 +#define ARMV8_PMUV3_PERFCTR_STALL_BACKEND 0x0024 +#define ARMV8_PMUV3_PERFCTR_L1D_TLB 0x0025 +#define ARMV8_PMUV3_PERFCTR_L1I_TLB 0x0026 +#define ARMV8_PMUV3_PERFCTR_L2I_CACHE 0x0027 +#define ARMV8_PMUV3_PERFCTR_L2I_CACHE_REFILL 0x0028 +#define ARMV8_PMUV3_PERFCTR_L3D_CACHE_ALLOCATE 0x0029 +#define ARMV8_PMUV3_PERFCTR_L3D_CACHE_REFILL 0x002A +#define ARMV8_PMUV3_PERFCTR_L3D_CACHE 0x002B +#define ARMV8_PMUV3_PERFCTR_L3D_CACHE_WB 0x002C +#define ARMV8_PMUV3_PERFCTR_L2D_TLB_REFILL 0x002D +#define ARMV8_PMUV3_PERFCTR_L2I_TLB_REFILL 0x002E +#define ARMV8_PMUV3_PERFCTR_L2D_TLB 0x002F +#define ARMV8_PMUV3_PERFCTR_L2I_TLB 0x0030 +#define ARMV8_PMUV3_PERFCTR_REMOTE_ACCESS 0x0031 +#define ARMV8_PMUV3_PERFCTR_LL_CACHE 0x0032 +#define ARMV8_PMUV3_PERFCTR_LL_CACHE_MISS 0x0033 +#define ARMV8_PMUV3_PERFCTR_DTLB_WALK 0x0034 +#define ARMV8_PMUV3_PERFCTR_ITLB_WALK 0x0035 +#define ARMV8_PMUV3_PERFCTR_LL_CACHE_RD 0x0036 +#define ARMV8_PMUV3_PERFCTR_LL_CACHE_MISS_RD 0x0037 +#define ARMV8_PMUV3_PERFCTR_REMOTE_ACCESS_RD 0x0038 +#define ARMV8_PMUV3_PERFCTR_L1D_CACHE_LMISS_RD 0x0039 +#define ARMV8_PMUV3_PERFCTR_OP_RETIRED 0x003A +#define ARMV8_PMUV3_PERFCTR_OP_SPEC 0x003B +#define ARMV8_PMUV3_PERFCTR_STALL 0x003C +#define ARMV8_PMUV3_PERFCTR_STALL_SLOT_BACKEND 0x003D +#define ARMV8_PMUV3_PERFCTR_STALL_SLOT_FRONTEND 0x003E +#define ARMV8_PMUV3_PERFCTR_STALL_SLOT 0x003F + +/* Statistical profiling extension microarchitectural events */ +#define ARMV8_SPE_PERFCTR_SAMPLE_POP 0x4000 +#define ARMV8_SPE_PERFCTR_SAMPLE_FEED 0x4001 +#define ARMV8_SPE_PERFCTR_SAMPLE_FILTRATE 0x4002 +#define ARMV8_SPE_PERFCTR_SAMPLE_COLLISION 0x4003 + +/* AMUv1 architecture events */ +#define ARMV8_AMU_PERFCTR_CNT_CYCLES 0x4004 +#define ARMV8_AMU_PERFCTR_STALL_BACKEND_MEM 0x4005 + +/* long-latency read miss events */ +#define ARMV8_PMUV3_PERFCTR_L1I_CACHE_LMISS 0x4006 +#define ARMV8_PMUV3_PERFCTR_L2D_CACHE_LMISS_RD 0x4009 +#define ARMV8_PMUV3_PERFCTR_L2I_CACHE_LMISS 0x400A +#define ARMV8_PMUV3_PERFCTR_L3D_CACHE_LMISS_RD 0x400B + +/* Trace buffer events */ +#define ARMV8_PMUV3_PERFCTR_TRB_WRAP 0x400C +#define ARMV8_PMUV3_PERFCTR_TRB_TRIG 0x400E + +/* Trace unit events */ +#define ARMV8_PMUV3_PERFCTR_TRCEXTOUT0 0x4010 +#define ARMV8_PMUV3_PERFCTR_TRCEXTOUT1 0x4011 +#define ARMV8_PMUV3_PERFCTR_TRCEXTOUT2 0x4012 +#define ARMV8_PMUV3_PERFCTR_TRCEXTOUT3 0x4013 +#define ARMV8_PMUV3_PERFCTR_CTI_TRIGOUT4 0x4018 +#define ARMV8_PMUV3_PERFCTR_CTI_TRIGOUT5 0x4019 +#define ARMV8_PMUV3_PERFCTR_CTI_TRIGOUT6 0x401A +#define ARMV8_PMUV3_PERFCTR_CTI_TRIGOUT7 0x401B + +/* additional latency from alignment events */ +#define ARMV8_PMUV3_PERFCTR_LDST_ALIGN_LAT 0x4020 +#define ARMV8_PMUV3_PERFCTR_LD_ALIGN_LAT 0x4021 +#define ARMV8_PMUV3_PERFCTR_ST_ALIGN_LAT 0x4022 + +/* Armv8.5 Memory Tagging Extension events */ +#define ARMV8_MTE_PERFCTR_MEM_ACCESS_CHECKED 0x4024 +#define ARMV8_MTE_PERFCTR_MEM_ACCESS_CHECKED_RD 0x4025 +#define ARMV8_MTE_PERFCTR_MEM_ACCESS_CHECKED_WR 0x4026 + +/* ARMv8 recommended implementation defined event types */ +#define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_RD 0x0040 +#define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_WR 0x0041 +#define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_REFILL_RD 0x0042 +#define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_REFILL_WR 0x0043 +#define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_REFILL_INNER 0x0044 +#define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_REFILL_OUTER 0x0045 +#define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_WB_VICTIM 0x0046 +#define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_WB_CLEAN 0x0047 +#define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_INVAL 0x0048 + +#define ARMV8_IMPDEF_PERFCTR_L1D_TLB_REFILL_RD 0x004C +#define ARMV8_IMPDEF_PERFCTR_L1D_TLB_REFILL_WR 0x004D +#define ARMV8_IMPDEF_PERFCTR_L1D_TLB_RD 0x004E +#define ARMV8_IMPDEF_PERFCTR_L1D_TLB_WR 0x004F +#define ARMV8_IMPDEF_PERFCTR_L2D_CACHE_RD 0x0050 +#define ARMV8_IMPDEF_PERFCTR_L2D_CACHE_WR 0x0051 +#define ARMV8_IMPDEF_PERFCTR_L2D_CACHE_REFILL_RD 0x0052 +#define ARMV8_IMPDEF_PERFCTR_L2D_CACHE_REFILL_WR 0x0053 + +#define ARMV8_IMPDEF_PERFCTR_L2D_CACHE_WB_VICTIM 0x0056 +#define ARMV8_IMPDEF_PERFCTR_L2D_CACHE_WB_CLEAN 0x0057 +#define ARMV8_IMPDEF_PERFCTR_L2D_CACHE_INVAL 0x0058 + +#define ARMV8_IMPDEF_PERFCTR_L2D_TLB_REFILL_RD 0x005C +#define ARMV8_IMPDEF_PERFCTR_L2D_TLB_REFILL_WR 0x005D +#define ARMV8_IMPDEF_PERFCTR_L2D_TLB_RD 0x005E +#define ARMV8_IMPDEF_PERFCTR_L2D_TLB_WR 0x005F +#define ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_RD 0x0060 +#define ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_WR 0x0061 +#define ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_SHARED 0x0062 +#define ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_NOT_SHARED 0x0063 +#define ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_NORMAL 0x0064 +#define ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_PERIPH 0x0065 +#define ARMV8_IMPDEF_PERFCTR_MEM_ACCESS_RD 0x0066 +#define ARMV8_IMPDEF_PERFCTR_MEM_ACCESS_WR 0x0067 +#define ARMV8_IMPDEF_PERFCTR_UNALIGNED_LD_SPEC 0x0068 +#define ARMV8_IMPDEF_PERFCTR_UNALIGNED_ST_SPEC 0x0069 +#define ARMV8_IMPDEF_PERFCTR_UNALIGNED_LDST_SPEC 0x006A + +#define ARMV8_IMPDEF_PERFCTR_LDREX_SPEC 0x006C +#define ARMV8_IMPDEF_PERFCTR_STREX_PASS_SPEC 0x006D +#define ARMV8_IMPDEF_PERFCTR_STREX_FAIL_SPEC 0x006E +#define ARMV8_IMPDEF_PERFCTR_STREX_SPEC 0x006F +#define ARMV8_IMPDEF_PERFCTR_LD_SPEC 0x0070 +#define ARMV8_IMPDEF_PERFCTR_ST_SPEC 0x0071 +#define ARMV8_IMPDEF_PERFCTR_LDST_SPEC 0x0072 +#define ARMV8_IMPDEF_PERFCTR_DP_SPEC 0x0073 +#define ARMV8_IMPDEF_PERFCTR_ASE_SPEC 0x0074 +#define ARMV8_IMPDEF_PERFCTR_VFP_SPEC 0x0075 +#define ARMV8_IMPDEF_PERFCTR_PC_WRITE_SPEC 0x0076 +#define ARMV8_IMPDEF_PERFCTR_CRYPTO_SPEC 0x0077 +#define ARMV8_IMPDEF_PERFCTR_BR_IMMED_SPEC 0x0078 +#define ARMV8_IMPDEF_PERFCTR_BR_RETURN_SPEC 0x0079 +#define ARMV8_IMPDEF_PERFCTR_BR_INDIRECT_SPEC 0x007A + +#define ARMV8_IMPDEF_PERFCTR_ISB_SPEC 0x007C +#define ARMV8_IMPDEF_PERFCTR_DSB_SPEC 0x007D +#define ARMV8_IMPDEF_PERFCTR_DMB_SPEC 0x007E + +#define ARMV8_IMPDEF_PERFCTR_EXC_UNDEF 0x0081 +#define ARMV8_IMPDEF_PERFCTR_EXC_SVC 0x0082 +#define ARMV8_IMPDEF_PERFCTR_EXC_PABORT 0x0083 +#define ARMV8_IMPDEF_PERFCTR_EXC_DABORT 0x0084 + +#define ARMV8_IMPDEF_PERFCTR_EXC_IRQ 0x0086 +#define ARMV8_IMPDEF_PERFCTR_EXC_FIQ 0x0087 +#define ARMV8_IMPDEF_PERFCTR_EXC_SMC 0x0088 + +#define ARMV8_IMPDEF_PERFCTR_EXC_HVC 0x008A +#define ARMV8_IMPDEF_PERFCTR_EXC_TRAP_PABORT 0x008B +#define ARMV8_IMPDEF_PERFCTR_EXC_TRAP_DABORT 0x008C +#define ARMV8_IMPDEF_PERFCTR_EXC_TRAP_OTHER 0x008D +#define ARMV8_IMPDEF_PERFCTR_EXC_TRAP_IRQ 0x008E +#define ARMV8_IMPDEF_PERFCTR_EXC_TRAP_FIQ 0x008F +#define ARMV8_IMPDEF_PERFCTR_RC_LD_SPEC 0x0090 +#define ARMV8_IMPDEF_PERFCTR_RC_ST_SPEC 0x0091 + +#define ARMV8_IMPDEF_PERFCTR_L3D_CACHE_RD 0x00A0 +#define ARMV8_IMPDEF_PERFCTR_L3D_CACHE_WR 0x00A1 +#define ARMV8_IMPDEF_PERFCTR_L3D_CACHE_REFILL_RD 0x00A2 +#define ARMV8_IMPDEF_PERFCTR_L3D_CACHE_REFILL_WR 0x00A3 + +#define ARMV8_IMPDEF_PERFCTR_L3D_CACHE_WB_VICTIM 0x00A6 +#define ARMV8_IMPDEF_PERFCTR_L3D_CACHE_WB_CLEAN 0x00A7 +#define ARMV8_IMPDEF_PERFCTR_L3D_CACHE_INVAL 0x00A8 + +/* + * Per-CPU PMCR: config reg + */ +#define ARMV8_PMU_PMCR_E (1 << 0) /* Enable all counters */ +#define ARMV8_PMU_PMCR_P (1 << 1) /* Reset all counters */ +#define ARMV8_PMU_PMCR_C (1 << 2) /* Cycle counter reset */ +#define ARMV8_PMU_PMCR_D (1 << 3) /* CCNT counts every 64th cpu cycle */ +#define ARMV8_PMU_PMCR_X (1 << 4) /* Export to ETM */ +#define ARMV8_PMU_PMCR_DP (1 << 5) /* Disable CCNT if non-invasive debug*/ +#define ARMV8_PMU_PMCR_LC (1 << 6) /* Overflow on 64 bit cycle counter */ +#define ARMV8_PMU_PMCR_LP (1 << 7) /* Long event counter enable */ +#define ARMV8_PMU_PMCR_N_SHIFT 11 /* Number of counters supported */ +#define ARMV8_PMU_PMCR_N_MASK 0x1f +#define ARMV8_PMU_PMCR_MASK 0xff /* Mask for writable bits */ + +/* + * PMOVSR: counters overflow flag status reg + */ +#define ARMV8_PMU_OVSR_MASK 0xffffffff /* Mask for writable bits */ +#define ARMV8_PMU_OVERFLOWED_MASK ARMV8_PMU_OVSR_MASK + +/* + * PMXEVTYPER: Event selection reg + */ +#define ARMV8_PMU_EVTYPE_MASK 0xc800ffff /* Mask for writable bits */ +#define ARMV8_PMU_EVTYPE_EVENT 0xffff /* Mask for EVENT bits */ + +/* + * Event filters for PMUv3 + */ +#define ARMV8_PMU_EXCLUDE_EL1 (1U << 31) +#define ARMV8_PMU_EXCLUDE_EL0 (1U << 30) +#define ARMV8_PMU_INCLUDE_EL2 (1U << 27) + +/* + * PMUSERENR: user enable reg + */ +#define ARMV8_PMU_USERENR_MASK 0xf /* Mask for writable bits */ +#define ARMV8_PMU_USERENR_EN (1 << 0) /* PMU regs can be accessed at EL0 */ +#define ARMV8_PMU_USERENR_SW (1 << 1) /* PMSWINC can be written at EL0 */ +#define ARMV8_PMU_USERENR_CR (1 << 2) /* Cycle counter can be read at EL0 */ +#define ARMV8_PMU_USERENR_ER (1 << 3) /* Event counter can be read at EL0 */ + +/* PMMIR_EL1.SLOTS mask */ +#define ARMV8_PMU_SLOTS_MASK 0xff + +#define ARMV8_PMU_BUS_SLOTS_SHIFT 8 +#define ARMV8_PMU_BUS_SLOTS_MASK 0xff +#define ARMV8_PMU_BUS_WIDTH_SHIFT 16 +#define ARMV8_PMU_BUS_WIDTH_MASK 0xf + +#endif -- cgit v1.2.3 From df29ddf4f04b00cf60669686dc7f534c3ed7c433 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Fri, 17 Mar 2023 15:50:21 -0400 Subject: arm64: perf: Abstract system register accesses away As we want to enable 32bit support, we need to distanciate the PMUv3 driver from the AArch64 system register names. This patch moves all system register accesses to an architecture specific include file, allowing the 32bit counterpart to be slotted in at a later time. Signed-off-by: Marc Zyngier Co-developed-by: Zaid Al-Bassam Signed-off-by: Zaid Al-Bassam Tested-by: Florian Fainelli Link: https://lore.kernel.org/r/20230317195027.3746949-3-zalbassam@google.com Signed-off-by: Will Deacon --- include/linux/perf/arm_pmuv3.h | 45 ++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 45 insertions(+) (limited to 'include/linux') diff --git a/include/linux/perf/arm_pmuv3.h b/include/linux/perf/arm_pmuv3.h index 53173abfc022..e3899bd77f5c 100644 --- a/include/linux/perf/arm_pmuv3.h +++ b/include/linux/perf/arm_pmuv3.h @@ -255,4 +255,49 @@ #define ARMV8_PMU_BUS_WIDTH_SHIFT 16 #define ARMV8_PMU_BUS_WIDTH_MASK 0xf +/* + * This code is really good + */ + +#define PMEVN_CASE(n, case_macro) \ + case n: case_macro(n); break + +#define PMEVN_SWITCH(x, case_macro) \ + do { \ + switch (x) { \ + PMEVN_CASE(0, case_macro); \ + PMEVN_CASE(1, case_macro); \ + PMEVN_CASE(2, case_macro); \ + PMEVN_CASE(3, case_macro); \ + PMEVN_CASE(4, case_macro); \ + PMEVN_CASE(5, case_macro); \ + PMEVN_CASE(6, case_macro); \ + PMEVN_CASE(7, case_macro); \ + PMEVN_CASE(8, case_macro); \ + PMEVN_CASE(9, case_macro); \ + PMEVN_CASE(10, case_macro); \ + PMEVN_CASE(11, case_macro); \ + PMEVN_CASE(12, case_macro); \ + PMEVN_CASE(13, case_macro); \ + PMEVN_CASE(14, case_macro); \ + PMEVN_CASE(15, case_macro); \ + PMEVN_CASE(16, case_macro); \ + PMEVN_CASE(17, case_macro); \ + PMEVN_CASE(18, case_macro); \ + PMEVN_CASE(19, case_macro); \ + PMEVN_CASE(20, case_macro); \ + PMEVN_CASE(21, case_macro); \ + PMEVN_CASE(22, case_macro); \ + PMEVN_CASE(23, case_macro); \ + PMEVN_CASE(24, case_macro); \ + PMEVN_CASE(25, case_macro); \ + PMEVN_CASE(26, case_macro); \ + PMEVN_CASE(27, case_macro); \ + PMEVN_CASE(28, case_macro); \ + PMEVN_CASE(29, case_macro); \ + PMEVN_CASE(30, case_macro); \ + default: WARN(1, "Invalid PMEV* index\n"); \ + } \ + } while (0) + #endif -- cgit v1.2.3 From d583fbd7066a2dea43050521a95d9770f7d7593e Mon Sep 17 00:00:00 2001 From: Dmytro Maluka Date: Wed, 22 Mar 2023 21:43:43 +0100 Subject: KVM: irqfd: Make resampler_list an RCU list It is useful to be able to do read-only traversal of the list of all the registered irqfd resamplers without locking the resampler_lock mutex. In particular, we are going to traverse it to search for a resampler registered for the given irq of an irqchip, and that will be done with an irqchip spinlock (ioapic->lock) held, so it is undesirable to lock a mutex in this context. So turn this list into an RCU list. For protecting the read side, reuse kvm->irq_srcu which is already used for protecting a number of irq related things (kvm->irq_routing, irqfd->resampler->list, kvm->irq_ack_notifier_list, kvm->arch.mask_notifier_list). Signed-off-by: Dmytro Maluka Message-Id: <20230322204344.50138-2-dmy@semihalf.com> Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 1 + include/linux/kvm_irqfd.h | 2 +- 2 files changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 8ada23756b0e..9f508c8e66e1 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -755,6 +755,7 @@ struct kvm { struct { spinlock_t lock; struct list_head items; + /* resampler_list update side is protected by resampler_lock. */ struct list_head resampler_list; struct mutex resampler_lock; } irqfds; diff --git a/include/linux/kvm_irqfd.h b/include/linux/kvm_irqfd.h index dac047abdba7..8ad43692e3bb 100644 --- a/include/linux/kvm_irqfd.h +++ b/include/linux/kvm_irqfd.h @@ -31,7 +31,7 @@ struct kvm_kernel_irqfd_resampler { /* * Entry in list of kvm->irqfd.resampler_list. Use for sharing * resamplers among irqfds on the same gsi. - * Accessed and modified under kvm->irqfds.resampler_lock + * RCU list modified under kvm->irqfds.resampler_lock */ struct list_head link; }; -- cgit v1.2.3 From fef8f2b90edbd7089a4278021314f11f056b0cbb Mon Sep 17 00:00:00 2001 From: Dmytro Maluka Date: Wed, 22 Mar 2023 21:43:44 +0100 Subject: KVM: x86/ioapic: Resample the pending state of an IRQ when unmasking KVM irqfd based emulation of level-triggered interrupts doesn't work quite correctly in some cases, particularly in the case of interrupts that are handled in a Linux guest as oneshot interrupts (IRQF_ONESHOT). Such an interrupt is acked to the device in its threaded irq handler, i.e. later than it is acked to the interrupt controller (EOI at the end of hardirq), not earlier. Linux keeps such interrupt masked until its threaded handler finishes, to prevent the EOI from re-asserting an unacknowledged interrupt. However, with KVM + vfio (or whatever is listening on the resamplefd) we always notify resamplefd at the EOI, so vfio prematurely unmasks the host physical IRQ, thus a new physical interrupt is fired in the host. This extra interrupt in the host is not a problem per se. The problem is that it is unconditionally queued for injection into the guest, so the guest sees an extra bogus interrupt. [*] There are observed at least 2 user-visible issues caused by those extra erroneous interrupts for a oneshot irq in the guest: 1. System suspend aborted due to a pending wakeup interrupt from ChromeOS EC (drivers/platform/chrome/cros_ec.c). 2. Annoying "invalid report id data" errors from ELAN0000 touchpad (drivers/input/mouse/elan_i2c_core.c), flooding the guest dmesg every time the touchpad is touched. The core issue here is that by the time when the guest unmasks the IRQ, the physical IRQ line is no longer asserted (since the guest has acked the interrupt to the device in the meantime), yet we unconditionally inject the interrupt queued into the guest by the previous resampling. So to fix the issue, we need a way to detect that the IRQ is no longer pending, and cancel the queued interrupt in this case. With IOAPIC we are not able to probe the physical IRQ line state directly (at least not if the underlying physical interrupt controller is an IOAPIC too), so in this patch we use irqfd resampler for that. Namely, instead of injecting the queued interrupt, we just notify the resampler that this interrupt is done. If the IRQ line is actually already deasserted, we are done. If it is still asserted, a new interrupt will be shortly triggered through irqfd and injected into the guest. In the case if there is no irqfd resampler registered for this IRQ, we cannot fix the issue, so we keep the existing behavior: immediately unconditionally inject the queued interrupt. This patch fixes the issue for x86 IOAPIC only. In the long run, we can fix it for other irqchips and other architectures too, possibly taking advantage of reading the physical state of the IRQ line, which is possible with some other irqchips (e.g. with arm64 GIC, maybe even with the legacy x86 PIC). [*] In this description we assume that the interrupt is a physical host interrupt forwarded to the guest e.g. by vfio. Potentially the same issue may occur also with a purely virtual interrupt from an emulated device, e.g. if the guest handles this interrupt, again, as a oneshot interrupt. Signed-off-by: Dmytro Maluka Link: https://lore.kernel.org/kvm/31420943-8c5f-125c-a5ee-d2fde2700083@semihalf.com/ Link: https://lore.kernel.org/lkml/87o7wrug0w.wl-maz@kernel.org/ Message-Id: <20230322204344.50138-3-dmy@semihalf.com> Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 9f508c8e66e1..a9adf75344be 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1987,6 +1987,9 @@ int kvm_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args); #ifdef CONFIG_HAVE_KVM_IRQFD int kvm_irqfd(struct kvm *kvm, struct kvm_irqfd *args); void kvm_irqfd_release(struct kvm *kvm); +bool kvm_notify_irqfd_resampler(struct kvm *kvm, + unsigned int irqchip, + unsigned int pin); void kvm_irq_routing_update(struct kvm *); #else static inline int kvm_irqfd(struct kvm *kvm, struct kvm_irqfd *args) @@ -1995,6 +1998,13 @@ static inline int kvm_irqfd(struct kvm *kvm, struct kvm_irqfd *args) } static inline void kvm_irqfd_release(struct kvm *kvm) {} + +static inline bool kvm_notify_irqfd_resampler(struct kvm *kvm, + unsigned int irqchip, + unsigned int pin) +{ + return false; +} #endif #else -- cgit v1.2.3 From 579d472b379983498a6a7d9f7b1dd74c20afdc50 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Mon, 27 Mar 2023 16:01:50 +0300 Subject: device property: Remove unused struct net_device forward declaration There is no users in the property.h for the struct net_device. Remove the latter for good. Signed-off-by: Andy Shevchenko Acked-by: Rafael J. Wysocki Link: https://lore.kernel.org/r/20230327130150.84114-2-andriy.shevchenko@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- include/linux/property.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/property.h b/include/linux/property.h index 4a536548606b..59f452198c64 100644 --- a/include/linux/property.h +++ b/include/linux/property.h @@ -16,7 +16,6 @@ #include struct device; -struct net_device; enum dev_prop_type { DEV_PROP_U8, -- cgit v1.2.3 From 5c9a27df4eb9a402770d5547af255a765e1c10ac Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 27 Mar 2023 18:03:19 +0200 Subject: driver core: move sysfs_dev_char_kobj out of class.h The structure sysfs_dev_char_kobj is local only to the driver core code, so move it out of the global class.h file and into the internal base.h file as no one else should be touching this symbol. Acked-by: Rafael J. Wysocki Link: https://lore.kernel.org/r/20230327160319.513974-1-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- include/linux/device/class.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/device/class.h b/include/linux/device/class.h index 1dc7706cb42d..d3960733c0fa 100644 --- a/include/linux/device/class.h +++ b/include/linux/device/class.h @@ -81,7 +81,6 @@ struct class_dev_iter { }; extern struct kobject *sysfs_dev_block_kobj; -extern struct kobject *sysfs_dev_char_kobj; int __must_check class_register(struct class *class); void class_unregister(struct class *class); -- cgit v1.2.3 From 2f1f043e7bea3fbf4c1869df2f7a0312bc8ca2bf Mon Sep 17 00:00:00 2001 From: Boqun Feng Date: Thu, 12 Jan 2023 22:59:53 -0800 Subject: locking/lockdep: Introduce lock_sync() Currently, functions like synchronize_srcu() do not have lockdep annotations resembling those of other write-side locking primitives. Such annotations might look as follows: lock_acquire(); lock_release(); Such annotations would tell lockdep that synchronize_srcu() acts like an empty critical section that waits for other (read-side) critical sections to finish. This would definitely catch some deadlock, but as pointed out by Paul Mckenney [1], this could also introduce false positives because of irq-safe/unsafe detection. Of course, there are tricks could help with this: might_sleep(); // Existing statement in __synchronize_srcu(). if (IS_ENABLED(CONFIG_PROVE_LOCKING)) { local_irq_disable(); lock_acquire(); lock_release(); local_irq_enable(); } But it would be better for lockdep to provide a separate annonation for functions like synchronize_srcu(), so that people won't need to repeat the ugly tricks above. Therefore introduce lock_sync(), which is simply an lock+unlock pair with no irq safe/unsafe deadlock check. This works because the to-be-annontated functions do not create real critical sections, and there is therefore no way that irq can create extra dependencies. [1]: https://lore.kernel.org/lkml/20180412021233.ewncg5jjuzjw3x62@tardis/ Signed-off-by: Boqun Feng Acked-by: Waiman Long Signed-off-by: Paul E. McKenney [ boqun: Fix typos reported by Davidlohr Bueso and Paul E. Mckenney ] Acked-by: Peter Zijlstra (Intel) Signed-off-by: Boqun Feng --- include/linux/lockdep.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index 1023f349af71..14d9dbedc6c1 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -268,6 +268,10 @@ extern void lock_acquire(struct lockdep_map *lock, unsigned int subclass, extern void lock_release(struct lockdep_map *lock, unsigned long ip); +extern void lock_sync(struct lockdep_map *lock, unsigned int subclass, + int read, int check, struct lockdep_map *nest_lock, + unsigned long ip); + /* lock_is_held_type() returns */ #define LOCK_STATE_UNKNOWN -1 #define LOCK_STATE_NOT_HELD 0 @@ -554,6 +558,7 @@ do { \ #define lock_map_acquire_read(l) lock_acquire_shared_recursive(l, 0, 0, NULL, _THIS_IP_) #define lock_map_acquire_tryread(l) lock_acquire_shared_recursive(l, 0, 1, NULL, _THIS_IP_) #define lock_map_release(l) lock_release(l, _THIS_IP_) +#define lock_map_sync(l) lock_sync(l, 0, 0, 1, NULL, _THIS_IP_) #ifdef CONFIG_PROVE_LOCKING # define might_lock(lock) \ -- cgit v1.2.3 From f0f44752f5f61ee4e3bd88ae033fdb888320aafe Mon Sep 17 00:00:00 2001 From: Boqun Feng Date: Thu, 12 Jan 2023 22:59:54 -0800 Subject: rcu: Annotate SRCU's update-side lockdep dependencies Although all flavors of RCU readers are annotated correctly with lockdep as recursive read locks, they do not set the lock_acquire 'check' parameter. This means that RCU read locks are not added to the lockdep dependency graph, which in turn means that lockdep cannot detect RCU-based deadlocks. This is not a problem for RCU flavors having atomic read-side critical sections because context-based annotations can catch these deadlocks, see for example the RCU_LOCKDEP_WARN() statement in synchronize_rcu(). But context-based annotations are not helpful for sleepable RCU, especially given that it is perfectly legal to do synchronize_srcu(&srcu1) within an srcu_read_lock(&srcu2). However, we can detect SRCU-based by: (1) Making srcu_read_lock() a 'check'ed recursive read lock and (2) Making synchronize_srcu() a empty write lock critical section. Even better, with the newly introduced lock_sync(), we can avoid false positives about irq-unsafe/safe. This commit therefore makes it so. Note that NMI-safe SRCU read side critical sections are currently not annotated, but might be annotated in the future. Signed-off-by: Boqun Feng Signed-off-by: Paul E. McKenney [ boqun: Add comments for annotation per Waiman's suggestion ] [ boqun: Fix comment warning reported by Stephen Rothwell ] Acked-by: Peter Zijlstra (Intel) Signed-off-by: Boqun Feng --- include/linux/srcu.h | 34 ++++++++++++++++++++++++++++++++-- 1 file changed, 32 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/srcu.h b/include/linux/srcu.h index 74796cd7e7a9..41c4b26fb1c1 100644 --- a/include/linux/srcu.h +++ b/include/linux/srcu.h @@ -102,6 +102,32 @@ static inline int srcu_read_lock_held(const struct srcu_struct *ssp) return lock_is_held(&ssp->dep_map); } +/* + * Annotations provide deadlock detection for SRCU. + * + * Similar to other lockdep annotations, except there is an additional + * srcu_lock_sync(), which is basically an empty *write*-side critical section, + * see lock_sync() for more information. + */ + +/* Annotates a srcu_read_lock() */ +static inline void srcu_lock_acquire(struct lockdep_map *map) +{ + lock_map_acquire_read(map); +} + +/* Annotates a srcu_read_lock() */ +static inline void srcu_lock_release(struct lockdep_map *map) +{ + lock_map_release(map); +} + +/* Annotates a synchronize_srcu() */ +static inline void srcu_lock_sync(struct lockdep_map *map) +{ + lock_map_sync(map); +} + #else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ static inline int srcu_read_lock_held(const struct srcu_struct *ssp) @@ -109,6 +135,10 @@ static inline int srcu_read_lock_held(const struct srcu_struct *ssp) return 1; } +#define srcu_lock_acquire(m) do { } while (0) +#define srcu_lock_release(m) do { } while (0) +#define srcu_lock_sync(m) do { } while (0) + #endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */ #define SRCU_NMI_UNKNOWN 0x0 @@ -182,7 +212,7 @@ static inline int srcu_read_lock(struct srcu_struct *ssp) __acquires(ssp) srcu_check_nmi_safety(ssp, false); retval = __srcu_read_lock(ssp); - rcu_lock_acquire(&(ssp)->dep_map); + srcu_lock_acquire(&(ssp)->dep_map); return retval; } @@ -254,7 +284,7 @@ static inline void srcu_read_unlock(struct srcu_struct *ssp, int idx) { WARN_ON_ONCE(idx & ~0x1); srcu_check_nmi_safety(ssp, false); - rcu_lock_release(&(ssp)->dep_map); + srcu_lock_release(&(ssp)->dep_map); __srcu_read_unlock(ssp, idx); } -- cgit v1.2.3 From 0471db447cb7de56bbe2fedd9256b4d2b8ef642a Mon Sep 17 00:00:00 2001 From: Boqun Feng Date: Fri, 13 Jan 2023 15:57:22 -0800 Subject: locking/lockdep: Improve the deadlock scenario print for sync and read lock Lock scenario print is always a weak spot of lockdep splats. Improvement can be made if we rework the dependency search and the error printing. However without touching the graph search, we can improve a little for the circular deadlock case, since we have the to-be-added lock dependency, and know whether these two locks are read/write/sync. In order to know whether a held_lock is sync or not, a bit was "stolen" from ->references, which reduce our limit for the same lock class nesting from 2^12 to 2^11, and it should still be good enough. Besides, since we now have bit in held_lock for sync, we don't need the "hardirqoffs being 1" trick, and also we can avoid the __lock_release() if we jump out of __lock_acquire() before the held_lock stored. With these changes, a deadlock case evolved with read lock and sync gets a better print-out from: [...] Possible unsafe locking scenario: [...] [...] CPU0 CPU1 [...] ---- ---- [...] lock(srcuA); [...] lock(srcuB); [...] lock(srcuA); [...] lock(srcuB); to [...] Possible unsafe locking scenario: [...] [...] CPU0 CPU1 [...] ---- ---- [...] rlock(srcuA); [...] lock(srcuB); [...] lock(srcuA); [...] sync(srcuB); Signed-off-by: Boqun Feng Signed-off-by: Paul E. McKenney Acked-by: Peter Zijlstra (Intel) Signed-off-by: Boqun Feng --- include/linux/lockdep.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index 14d9dbedc6c1..b32256e9e944 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -134,7 +134,8 @@ struct held_lock { unsigned int read:2; /* see lock_acquire() comment */ unsigned int check:1; /* see lock_acquire() comment */ unsigned int hardirqs_off:1; - unsigned int references:12; /* 32 bits */ + unsigned int sync:1; + unsigned int references:11; /* 32 bits */ unsigned int pin_count; }; -- cgit v1.2.3 From 3948b05950fdd64002a5f182c65ba5cf2d53cf71 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 23 Mar 2023 09:28:42 -0700 Subject: net: introduce a config option to tweak MAX_SKB_FRAGS Currently, MAX_SKB_FRAGS value is 17. For standard tcp sendmsg() traffic, no big deal because tcp_sendmsg() attempts order-3 allocations, stuffing 32768 bytes per frag. But with zero copy, we use order-0 pages. For BIG TCP to show its full potential, we add a config option to be able to fit up to 45 segments per skb. This is also needed for BIG TCP rx zerocopy, as zerocopy currently does not support skbs with frag list. We have used MAX_SKB_FRAGS=45 value for years at Google before we deployed 4K MTU, with no adverse effect, other than a recent issue in mlx4, fixed in commit 26782aad00cc ("net/mlx4: MLX4_TX_BOUNCE_BUFFER_SIZE depends on MAX_SKB_FRAGS") Back then, goal was to be able to receive full size (64KB) GRO packets without the frag_list overhead. Note that /proc/sys/net/core/max_skb_frags can also be used to limit the number of fragments TCP can use in tx packets. By default we keep the old/legacy value of 17 until we get more coverage for the updated values. Sizes of struct skb_shared_info on 64bit arches MAX_SKB_FRAGS | sizeof(struct skb_shared_info): ============================================== 17 320 21 320+64 = 384 25 320+128 = 448 29 320+192 = 512 33 320+256 = 576 37 320+320 = 640 41 320+384 = 704 45 320+448 = 768 This inflation might cause problems for drivers assuming they could pack both the incoming packet (for MTU=1500) and skb_shared_info in half a page, using build_skb(). v3: fix build error when CONFIG_NET=n v2: fix two build errors assuming MAX_SKB_FRAGS was "unsigned long" Signed-off-by: Eric Dumazet Reviewed-by: Nikolay Aleksandrov Reviewed-by: Jason Xing Link: https://lore.kernel.org/r/20230323162842.1935061-1-eric.dumazet@gmail.com Signed-off-by: Jakub Kicinski --- include/linux/skbuff.h | 16 +++++----------- 1 file changed, 5 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index fe661011644b..82511b2f61ea 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -345,18 +345,12 @@ struct sk_buff_head { struct sk_buff; -/* To allow 64K frame to be packed as single skb without frag_list we - * require 64K/PAGE_SIZE pages plus 1 additional page to allow for - * buffers which do not start on a page boundary. - * - * Since GRO uses frags we allocate at least 16 regardless of page - * size. - */ -#if (65536/PAGE_SIZE + 1) < 16 -#define MAX_SKB_FRAGS 16UL -#else -#define MAX_SKB_FRAGS (65536/PAGE_SIZE + 1) +#ifndef CONFIG_MAX_SKB_FRAGS +# define CONFIG_MAX_SKB_FRAGS 17 #endif + +#define MAX_SKB_FRAGS CONFIG_MAX_SKB_FRAGS + extern int sysctl_max_skb_frags; /* Set skb_shinfo(skb)->gso_size to this in case you want skb_segment to -- cgit v1.2.3 From 3e4d5ba9a3f85f21f1ebdee5a5901bb43389abc5 Mon Sep 17 00:00:00 2001 From: Shay Agroskin Date: Thu, 23 Mar 2023 18:36:04 +0200 Subject: netlink: Add a macro to set policy message with format string Similar to NL_SET_ERR_MSG_FMT, add a macro which sets netlink policy error message with a format string. Signed-off-by: Shay Agroskin Signed-off-by: Jakub Kicinski --- include/linux/netlink.h | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netlink.h b/include/linux/netlink.h index 3e8743252167..19c0791ed9d5 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -161,9 +161,31 @@ struct netlink_ext_ack { } \ } while (0) +#define NL_SET_ERR_MSG_ATTR_POL_FMT(extack, attr, pol, fmt, args...) do { \ + struct netlink_ext_ack *__extack = (extack); \ + \ + if (!__extack) \ + break; \ + \ + if (snprintf(__extack->_msg_buf, NETLINK_MAX_FMTMSG_LEN, \ + "%s" fmt "%s", "", ##args, "") >= \ + NETLINK_MAX_FMTMSG_LEN) \ + net_warn_ratelimited("%s" fmt "%s", "truncated extack: ", \ + ##args, "\n"); \ + \ + do_trace_netlink_extack(__extack->_msg_buf); \ + \ + __extack->_msg = __extack->_msg_buf; \ + __extack->bad_attr = (attr); \ + __extack->policy = (pol); \ +} while (0) + #define NL_SET_ERR_MSG_ATTR(extack, attr, msg) \ NL_SET_ERR_MSG_ATTR_POL(extack, attr, NULL, msg) +#define NL_SET_ERR_MSG_ATTR_FMT(extack, attr, msg, args...) \ + NL_SET_ERR_MSG_ATTR_POL_FMT(extack, attr, NULL, msg, ##args) + #define NL_SET_ERR_ATTR_MISS(extack, nest, type) do { \ struct netlink_ext_ack *__extack = (extack); \ \ -- cgit v1.2.3 From 233eb4e786b57ea686b51c13a04cc2839fd682fc Mon Sep 17 00:00:00 2001 From: Shay Agroskin Date: Thu, 23 Mar 2023 18:36:05 +0200 Subject: ethtool: Add support for configuring tx_push_buf_len This attribute, which is part of ethtool's ring param configuration allows the user to specify the maximum number of the packet's payload that can be written directly to the device. Example usage: # ethtool -G [interface] tx-push-buf-len [number of bytes] Co-developed-by: Jakub Kicinski Signed-off-by: Shay Agroskin Signed-off-by: Jakub Kicinski --- include/linux/ethtool.h | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 2792185dda22..798d35890118 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -75,6 +75,8 @@ enum { * @tx_push: The flag of tx push mode * @rx_push: The flag of rx push mode * @cqe_size: Size of TX/RX completion queue event + * @tx_push_buf_len: Size of TX push buffer + * @tx_push_buf_max_len: Maximum allowed size of TX push buffer */ struct kernel_ethtool_ringparam { u32 rx_buf_len; @@ -82,6 +84,8 @@ struct kernel_ethtool_ringparam { u8 tx_push; u8 rx_push; u32 cqe_size; + u32 tx_push_buf_len; + u32 tx_push_buf_max_len; }; /** @@ -90,12 +94,14 @@ struct kernel_ethtool_ringparam { * @ETHTOOL_RING_USE_CQE_SIZE: capture for setting cqe_size * @ETHTOOL_RING_USE_TX_PUSH: capture for setting tx_push * @ETHTOOL_RING_USE_RX_PUSH: capture for setting rx_push + * @ETHTOOL_RING_USE_TX_PUSH_BUF_LEN: capture for setting tx_push_buf_len */ enum ethtool_supported_ring_param { - ETHTOOL_RING_USE_RX_BUF_LEN = BIT(0), - ETHTOOL_RING_USE_CQE_SIZE = BIT(1), - ETHTOOL_RING_USE_TX_PUSH = BIT(2), - ETHTOOL_RING_USE_RX_PUSH = BIT(3), + ETHTOOL_RING_USE_RX_BUF_LEN = BIT(0), + ETHTOOL_RING_USE_CQE_SIZE = BIT(1), + ETHTOOL_RING_USE_TX_PUSH = BIT(2), + ETHTOOL_RING_USE_RX_PUSH = BIT(3), + ETHTOOL_RING_USE_TX_PUSH_BUF_LEN = BIT(4), }; #define __ETH_RSS_HASH_BIT(bit) ((u32)1 << (bit)) -- cgit v1.2.3 From 6f2656eab290f0dd437cd4b2ec956c3519172d3b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Lu=C3=ADs=20Henriques?= Date: Thu, 16 Mar 2023 18:14:11 +0000 Subject: fscrypt: new helper function - fscrypt_prepare_lookup_partial() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This patch introduces a new helper function which can be used both in lookups and in atomic_open operations by filesystems that want to handle filename encryption and no-key dentries themselves. The reason for this function to be used in atomic open is that this operation can act as a lookup if handed a dentry that is negative. And in this case we may need to set DCACHE_NOKEY_NAME. Signed-off-by: Luís Henriques Tested-by: Xiubo Li Reviewed-by: Xiubo Li [ebiggers: improved the function comment, and moved the function to just below __fscrypt_prepare_lookup()] Link: https://lore.kernel.org/r/20230320220149.21863-1-ebiggers@kernel.org Signed-off-by: Eric Biggers --- include/linux/fscrypt.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h index e0a49c3125eb..a69f1302051d 100644 --- a/include/linux/fscrypt.h +++ b/include/linux/fscrypt.h @@ -359,6 +359,7 @@ int __fscrypt_prepare_rename(struct inode *old_dir, struct dentry *old_dentry, unsigned int flags); int __fscrypt_prepare_lookup(struct inode *dir, struct dentry *dentry, struct fscrypt_name *fname); +int fscrypt_prepare_lookup_partial(struct inode *dir, struct dentry *dentry); int __fscrypt_prepare_readdir(struct inode *dir); int __fscrypt_prepare_setattr(struct dentry *dentry, struct iattr *attr); int fscrypt_prepare_setflags(struct inode *inode, @@ -673,6 +674,12 @@ static inline int __fscrypt_prepare_lookup(struct inode *dir, return -EOPNOTSUPP; } +static inline int fscrypt_prepare_lookup_partial(struct inode *dir, + struct dentry *dentry) +{ + return -EOPNOTSUPP; +} + static inline int __fscrypt_prepare_readdir(struct inode *dir) { return -EOPNOTSUPP; -- cgit v1.2.3 From 517d4927aabe488144863e72b52bb3e506fecd34 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Sat, 25 Mar 2023 09:45:26 +0100 Subject: driver core: bus: constify class_unregister/destroy() The class_unregister() and class_destroy() function should be taking a const * to struct class, not just a *, so fix that up. Cc: "Rafael J. Wysocki" Link: https://lore.kernel.org/r/20230325084526.3622123-1-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- include/linux/device/class.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/device/class.h b/include/linux/device/class.h index d3960733c0fa..73436c578d37 100644 --- a/include/linux/device/class.h +++ b/include/linux/device/class.h @@ -83,7 +83,7 @@ struct class_dev_iter { extern struct kobject *sysfs_dev_block_kobj; int __must_check class_register(struct class *class); -void class_unregister(struct class *class); +void class_unregister(const struct class *class); struct class_compat; struct class_compat *class_compat_register(const char *name); @@ -231,6 +231,6 @@ int __must_check class_interface_register(struct class_interface *); void class_interface_unregister(struct class_interface *); struct class * __must_check class_create(const char *name); -void class_destroy(struct class *cls); +void class_destroy(const struct class *cls); #endif /* _DEVICE_CLASS_H_ */ -- cgit v1.2.3 From e5ab9eff46b04c5a04778e40d7092fed3fda52ca Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 23 Mar 2023 21:55:30 +0100 Subject: atomics: Provide atomic_add_negative() variants atomic_add_negative() does not provide the relaxed/acquire/release variants. Provide them in preparation for a new scalable reference count algorithm. Signed-off-by: Thomas Gleixner Signed-off-by: Peter Zijlstra (Intel) Acked-by: Mark Rutland Link: https://lore.kernel.org/r/20230323102800.101763813@linutronix.de --- include/linux/atomic/atomic-arch-fallback.h | 208 ++++++++++++++++++++++++++-- include/linux/atomic/atomic-instrumented.h | 68 ++++++++- include/linux/atomic/atomic-long.h | 38 ++++- 3 files changed, 303 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/atomic/atomic-arch-fallback.h b/include/linux/atomic/atomic-arch-fallback.h index 77bc5522e61c..4226379a232d 100644 --- a/include/linux/atomic/atomic-arch-fallback.h +++ b/include/linux/atomic/atomic-arch-fallback.h @@ -1208,15 +1208,21 @@ arch_atomic_inc_and_test(atomic_t *v) #define arch_atomic_inc_and_test arch_atomic_inc_and_test #endif +#ifndef arch_atomic_add_negative_relaxed +#ifdef arch_atomic_add_negative +#define arch_atomic_add_negative_acquire arch_atomic_add_negative +#define arch_atomic_add_negative_release arch_atomic_add_negative +#define arch_atomic_add_negative_relaxed arch_atomic_add_negative +#endif /* arch_atomic_add_negative */ + #ifndef arch_atomic_add_negative /** - * arch_atomic_add_negative - add and test if negative + * arch_atomic_add_negative - Add and test if negative * @i: integer value to add * @v: pointer of type atomic_t * - * Atomically adds @i to @v and returns true - * if the result is negative, or false when - * result is greater than or equal to zero. + * Atomically adds @i to @v and returns true if the result is negative, + * or false when the result is greater than or equal to zero. */ static __always_inline bool arch_atomic_add_negative(int i, atomic_t *v) @@ -1226,6 +1232,95 @@ arch_atomic_add_negative(int i, atomic_t *v) #define arch_atomic_add_negative arch_atomic_add_negative #endif +#ifndef arch_atomic_add_negative_acquire +/** + * arch_atomic_add_negative_acquire - Add and test if negative + * @i: integer value to add + * @v: pointer of type atomic_t + * + * Atomically adds @i to @v and returns true if the result is negative, + * or false when the result is greater than or equal to zero. + */ +static __always_inline bool +arch_atomic_add_negative_acquire(int i, atomic_t *v) +{ + return arch_atomic_add_return_acquire(i, v) < 0; +} +#define arch_atomic_add_negative_acquire arch_atomic_add_negative_acquire +#endif + +#ifndef arch_atomic_add_negative_release +/** + * arch_atomic_add_negative_release - Add and test if negative + * @i: integer value to add + * @v: pointer of type atomic_t + * + * Atomically adds @i to @v and returns true if the result is negative, + * or false when the result is greater than or equal to zero. + */ +static __always_inline bool +arch_atomic_add_negative_release(int i, atomic_t *v) +{ + return arch_atomic_add_return_release(i, v) < 0; +} +#define arch_atomic_add_negative_release arch_atomic_add_negative_release +#endif + +#ifndef arch_atomic_add_negative_relaxed +/** + * arch_atomic_add_negative_relaxed - Add and test if negative + * @i: integer value to add + * @v: pointer of type atomic_t + * + * Atomically adds @i to @v and returns true if the result is negative, + * or false when the result is greater than or equal to zero. + */ +static __always_inline bool +arch_atomic_add_negative_relaxed(int i, atomic_t *v) +{ + return arch_atomic_add_return_relaxed(i, v) < 0; +} +#define arch_atomic_add_negative_relaxed arch_atomic_add_negative_relaxed +#endif + +#else /* arch_atomic_add_negative_relaxed */ + +#ifndef arch_atomic_add_negative_acquire +static __always_inline bool +arch_atomic_add_negative_acquire(int i, atomic_t *v) +{ + bool ret = arch_atomic_add_negative_relaxed(i, v); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic_add_negative_acquire arch_atomic_add_negative_acquire +#endif + +#ifndef arch_atomic_add_negative_release +static __always_inline bool +arch_atomic_add_negative_release(int i, atomic_t *v) +{ + __atomic_release_fence(); + return arch_atomic_add_negative_relaxed(i, v); +} +#define arch_atomic_add_negative_release arch_atomic_add_negative_release +#endif + +#ifndef arch_atomic_add_negative +static __always_inline bool +arch_atomic_add_negative(int i, atomic_t *v) +{ + bool ret; + __atomic_pre_full_fence(); + ret = arch_atomic_add_negative_relaxed(i, v); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic_add_negative arch_atomic_add_negative +#endif + +#endif /* arch_atomic_add_negative_relaxed */ + #ifndef arch_atomic_fetch_add_unless /** * arch_atomic_fetch_add_unless - add unless the number is already a given value @@ -2329,15 +2424,21 @@ arch_atomic64_inc_and_test(atomic64_t *v) #define arch_atomic64_inc_and_test arch_atomic64_inc_and_test #endif +#ifndef arch_atomic64_add_negative_relaxed +#ifdef arch_atomic64_add_negative +#define arch_atomic64_add_negative_acquire arch_atomic64_add_negative +#define arch_atomic64_add_negative_release arch_atomic64_add_negative +#define arch_atomic64_add_negative_relaxed arch_atomic64_add_negative +#endif /* arch_atomic64_add_negative */ + #ifndef arch_atomic64_add_negative /** - * arch_atomic64_add_negative - add and test if negative + * arch_atomic64_add_negative - Add and test if negative * @i: integer value to add * @v: pointer of type atomic64_t * - * Atomically adds @i to @v and returns true - * if the result is negative, or false when - * result is greater than or equal to zero. + * Atomically adds @i to @v and returns true if the result is negative, + * or false when the result is greater than or equal to zero. */ static __always_inline bool arch_atomic64_add_negative(s64 i, atomic64_t *v) @@ -2347,6 +2448,95 @@ arch_atomic64_add_negative(s64 i, atomic64_t *v) #define arch_atomic64_add_negative arch_atomic64_add_negative #endif +#ifndef arch_atomic64_add_negative_acquire +/** + * arch_atomic64_add_negative_acquire - Add and test if negative + * @i: integer value to add + * @v: pointer of type atomic64_t + * + * Atomically adds @i to @v and returns true if the result is negative, + * or false when the result is greater than or equal to zero. + */ +static __always_inline bool +arch_atomic64_add_negative_acquire(s64 i, atomic64_t *v) +{ + return arch_atomic64_add_return_acquire(i, v) < 0; +} +#define arch_atomic64_add_negative_acquire arch_atomic64_add_negative_acquire +#endif + +#ifndef arch_atomic64_add_negative_release +/** + * arch_atomic64_add_negative_release - Add and test if negative + * @i: integer value to add + * @v: pointer of type atomic64_t + * + * Atomically adds @i to @v and returns true if the result is negative, + * or false when the result is greater than or equal to zero. + */ +static __always_inline bool +arch_atomic64_add_negative_release(s64 i, atomic64_t *v) +{ + return arch_atomic64_add_return_release(i, v) < 0; +} +#define arch_atomic64_add_negative_release arch_atomic64_add_negative_release +#endif + +#ifndef arch_atomic64_add_negative_relaxed +/** + * arch_atomic64_add_negative_relaxed - Add and test if negative + * @i: integer value to add + * @v: pointer of type atomic64_t + * + * Atomically adds @i to @v and returns true if the result is negative, + * or false when the result is greater than or equal to zero. + */ +static __always_inline bool +arch_atomic64_add_negative_relaxed(s64 i, atomic64_t *v) +{ + return arch_atomic64_add_return_relaxed(i, v) < 0; +} +#define arch_atomic64_add_negative_relaxed arch_atomic64_add_negative_relaxed +#endif + +#else /* arch_atomic64_add_negative_relaxed */ + +#ifndef arch_atomic64_add_negative_acquire +static __always_inline bool +arch_atomic64_add_negative_acquire(s64 i, atomic64_t *v) +{ + bool ret = arch_atomic64_add_negative_relaxed(i, v); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic64_add_negative_acquire arch_atomic64_add_negative_acquire +#endif + +#ifndef arch_atomic64_add_negative_release +static __always_inline bool +arch_atomic64_add_negative_release(s64 i, atomic64_t *v) +{ + __atomic_release_fence(); + return arch_atomic64_add_negative_relaxed(i, v); +} +#define arch_atomic64_add_negative_release arch_atomic64_add_negative_release +#endif + +#ifndef arch_atomic64_add_negative +static __always_inline bool +arch_atomic64_add_negative(s64 i, atomic64_t *v) +{ + bool ret; + __atomic_pre_full_fence(); + ret = arch_atomic64_add_negative_relaxed(i, v); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic64_add_negative arch_atomic64_add_negative +#endif + +#endif /* arch_atomic64_add_negative_relaxed */ + #ifndef arch_atomic64_fetch_add_unless /** * arch_atomic64_fetch_add_unless - add unless the number is already a given value @@ -2456,4 +2646,4 @@ arch_atomic64_dec_if_positive(atomic64_t *v) #endif #endif /* _LINUX_ATOMIC_FALLBACK_H */ -// b5e87bdd5ede61470c29f7a7e4de781af3770f09 +// 00071fffa021cec66f6290d706d69c91df87bade diff --git a/include/linux/atomic/atomic-instrumented.h b/include/linux/atomic/atomic-instrumented.h index 7a139ec030b0..0496816738ca 100644 --- a/include/linux/atomic/atomic-instrumented.h +++ b/include/linux/atomic/atomic-instrumented.h @@ -592,6 +592,28 @@ atomic_add_negative(int i, atomic_t *v) return arch_atomic_add_negative(i, v); } +static __always_inline bool +atomic_add_negative_acquire(int i, atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_add_negative_acquire(i, v); +} + +static __always_inline bool +atomic_add_negative_release(int i, atomic_t *v) +{ + kcsan_release(); + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_add_negative_release(i, v); +} + +static __always_inline bool +atomic_add_negative_relaxed(int i, atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_add_negative_relaxed(i, v); +} + static __always_inline int atomic_fetch_add_unless(atomic_t *v, int a, int u) { @@ -1211,6 +1233,28 @@ atomic64_add_negative(s64 i, atomic64_t *v) return arch_atomic64_add_negative(i, v); } +static __always_inline bool +atomic64_add_negative_acquire(s64 i, atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_add_negative_acquire(i, v); +} + +static __always_inline bool +atomic64_add_negative_release(s64 i, atomic64_t *v) +{ + kcsan_release(); + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_add_negative_release(i, v); +} + +static __always_inline bool +atomic64_add_negative_relaxed(s64 i, atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_add_negative_relaxed(i, v); +} + static __always_inline s64 atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u) { @@ -1830,6 +1874,28 @@ atomic_long_add_negative(long i, atomic_long_t *v) return arch_atomic_long_add_negative(i, v); } +static __always_inline bool +atomic_long_add_negative_acquire(long i, atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_add_negative_acquire(i, v); +} + +static __always_inline bool +atomic_long_add_negative_release(long i, atomic_long_t *v) +{ + kcsan_release(); + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_add_negative_release(i, v); +} + +static __always_inline bool +atomic_long_add_negative_relaxed(long i, atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_add_negative_relaxed(i, v); +} + static __always_inline long atomic_long_fetch_add_unless(atomic_long_t *v, long a, long u) { @@ -2083,4 +2149,4 @@ atomic_long_dec_if_positive(atomic_long_t *v) }) #endif /* _LINUX_ATOMIC_INSTRUMENTED_H */ -// 764f741eb77a7ad565dc8d99ce2837d5542e8aee +// 1b485de9cbaa4900de59e14ee2084357eaeb1c3a diff --git a/include/linux/atomic/atomic-long.h b/include/linux/atomic/atomic-long.h index 800b8c35992d..2fc51ba66beb 100644 --- a/include/linux/atomic/atomic-long.h +++ b/include/linux/atomic/atomic-long.h @@ -479,6 +479,24 @@ arch_atomic_long_add_negative(long i, atomic_long_t *v) return arch_atomic64_add_negative(i, v); } +static __always_inline bool +arch_atomic_long_add_negative_acquire(long i, atomic_long_t *v) +{ + return arch_atomic64_add_negative_acquire(i, v); +} + +static __always_inline bool +arch_atomic_long_add_negative_release(long i, atomic_long_t *v) +{ + return arch_atomic64_add_negative_release(i, v); +} + +static __always_inline bool +arch_atomic_long_add_negative_relaxed(long i, atomic_long_t *v) +{ + return arch_atomic64_add_negative_relaxed(i, v); +} + static __always_inline long arch_atomic_long_fetch_add_unless(atomic_long_t *v, long a, long u) { @@ -973,6 +991,24 @@ arch_atomic_long_add_negative(long i, atomic_long_t *v) return arch_atomic_add_negative(i, v); } +static __always_inline bool +arch_atomic_long_add_negative_acquire(long i, atomic_long_t *v) +{ + return arch_atomic_add_negative_acquire(i, v); +} + +static __always_inline bool +arch_atomic_long_add_negative_release(long i, atomic_long_t *v) +{ + return arch_atomic_add_negative_release(i, v); +} + +static __always_inline bool +arch_atomic_long_add_negative_relaxed(long i, atomic_long_t *v) +{ + return arch_atomic_add_negative_relaxed(i, v); +} + static __always_inline long arch_atomic_long_fetch_add_unless(atomic_long_t *v, long a, long u) { @@ -1011,4 +1047,4 @@ arch_atomic_long_dec_if_positive(atomic_long_t *v) #endif /* CONFIG_64BIT */ #endif /* _LINUX_ATOMIC_LONG_H */ -// e8f0e08ff072b74d180eabe2ad001282b38c2c88 +// a194c07d7d2f4b0e178d3c118c919775d5d65f50 -- cgit v1.2.3 From ee1ee6db07795d9637bc5e8993a8ddcf886541ef Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 23 Mar 2023 21:55:31 +0100 Subject: atomics: Provide rcuref - scalable reference counting atomic_t based reference counting, including refcount_t, uses atomic_inc_not_zero() for acquiring a reference. atomic_inc_not_zero() is implemented with a atomic_try_cmpxchg() loop. High contention of the reference count leads to retry loops and scales badly. There is nothing to improve on this implementation as the semantics have to be preserved. Provide rcuref as a scalable alternative solution which is suitable for RCU managed objects. Similar to refcount_t it comes with overflow and underflow detection and mitigation. rcuref treats the underlying atomic_t as an unsigned integer and partitions this space into zones: 0x00000000 - 0x7FFFFFFF valid zone (1 .. (INT_MAX + 1) references) 0x80000000 - 0xBFFFFFFF saturation zone 0xC0000000 - 0xFFFFFFFE dead zone 0xFFFFFFFF no reference rcuref_get() unconditionally increments the reference count with atomic_add_negative_relaxed(). rcuref_put() unconditionally decrements the reference count with atomic_add_negative_release(). This unconditional increment avoids the inc_not_zero() problem, but requires a more complex implementation on the put() side when the count drops from 0 to -1. When this transition is detected then it is attempted to mark the reference count dead, by setting it to the midpoint of the dead zone with a single atomic_cmpxchg_release() operation. This operation can fail due to a concurrent rcuref_get() elevating the reference count from -1 to 0 again. If the unconditional increment in rcuref_get() hits a reference count which is marked dead (or saturated) it will detect it after the fact and bring back the reference count to the midpoint of the respective zone. The zones provide enough tolerance which makes it practically impossible to escape from a zone. The racy implementation of rcuref_put() requires to protect rcuref_put() against a grace period ending in order to prevent a subtle use after free. As RCU is the only mechanism which allows to protect against that, it is not possible to fully replace the atomic_inc_not_zero() based implementation of refcount_t with this scheme. The final drop is slightly more expensive than the atomic_dec_return() counterpart, but that's not the case which this is optimized for. The optimization is on the high frequeunt get()/put() pairs and their scalability. The performance of an uncontended rcuref_get()/put() pair where the put() is not dropping the last reference is still on par with the plain atomic operations, while at the same time providing overflow and underflow detection and mitigation. The performance of rcuref compared to plain atomic_inc_not_zero() and atomic_dec_return() based reference counting under contention: - Micro benchmark: All CPUs running a increment/decrement loop on an elevated reference count, which means the 0 to -1 transition never happens. The performance gain depends on microarchitecture and the number of CPUs and has been observed in the range of 1.3X to 4.7X - Conversion of dst_entry::__refcnt to rcuref and testing with the localhost memtier/memcached benchmark. That benchmark shows the reference count contention prominently. The performance gain depends on microarchitecture and the number of CPUs and has been observed in the range of 1.1X to 2.6X over the previous fix for the false sharing issue vs. struct dst_entry::__refcnt. When memtier is run over a real 1Gb network connection, there is a small gain on top of the false sharing fix. The two changes combined result in a 2%-5% total gain for that networked test. Reported-by: Wangyang Guo Reported-by: Arjan Van De Ven Signed-off-by: Thomas Gleixner Signed-off-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20230323102800.158429195@linutronix.de --- include/linux/rcuref.h | 155 +++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/types.h | 6 ++ 2 files changed, 161 insertions(+) create mode 100644 include/linux/rcuref.h (limited to 'include/linux') diff --git a/include/linux/rcuref.h b/include/linux/rcuref.h new file mode 100644 index 000000000000..2c8bfd0f1b6b --- /dev/null +++ b/include/linux/rcuref.h @@ -0,0 +1,155 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef _LINUX_RCUREF_H +#define _LINUX_RCUREF_H + +#include +#include +#include +#include +#include +#include + +#define RCUREF_ONEREF 0x00000000U +#define RCUREF_MAXREF 0x7FFFFFFFU +#define RCUREF_SATURATED 0xA0000000U +#define RCUREF_RELEASED 0xC0000000U +#define RCUREF_DEAD 0xE0000000U +#define RCUREF_NOREF 0xFFFFFFFFU + +/** + * rcuref_init - Initialize a rcuref reference count with the given reference count + * @ref: Pointer to the reference count + * @cnt: The initial reference count typically '1' + */ +static inline void rcuref_init(rcuref_t *ref, unsigned int cnt) +{ + atomic_set(&ref->refcnt, cnt - 1); +} + +/** + * rcuref_read - Read the number of held reference counts of a rcuref + * @ref: Pointer to the reference count + * + * Return: The number of held references (0 ... N) + */ +static inline unsigned int rcuref_read(rcuref_t *ref) +{ + unsigned int c = atomic_read(&ref->refcnt); + + /* Return 0 if within the DEAD zone. */ + return c >= RCUREF_RELEASED ? 0 : c + 1; +} + +extern __must_check bool rcuref_get_slowpath(rcuref_t *ref); + +/** + * rcuref_get - Acquire one reference on a rcuref reference count + * @ref: Pointer to the reference count + * + * Similar to atomic_inc_not_zero() but saturates at RCUREF_MAXREF. + * + * Provides no memory ordering, it is assumed the caller has guaranteed the + * object memory to be stable (RCU, etc.). It does provide a control dependency + * and thereby orders future stores. See documentation in lib/rcuref.c + * + * Return: + * False if the attempt to acquire a reference failed. This happens + * when the last reference has been put already + * + * True if a reference was successfully acquired + */ +static inline __must_check bool rcuref_get(rcuref_t *ref) +{ + /* + * Unconditionally increase the reference count. The saturation and + * dead zones provide enough tolerance for this. + */ + if (likely(!atomic_add_negative_relaxed(1, &ref->refcnt))) + return true; + + /* Handle the cases inside the saturation and dead zones */ + return rcuref_get_slowpath(ref); +} + +extern __must_check bool rcuref_put_slowpath(rcuref_t *ref); + +/* + * Internal helper. Do not invoke directly. + */ +static __always_inline __must_check bool __rcuref_put(rcuref_t *ref) +{ + RCU_LOCKDEP_WARN(!rcu_read_lock_held() && preemptible(), + "suspicious rcuref_put_rcusafe() usage"); + /* + * Unconditionally decrease the reference count. The saturation and + * dead zones provide enough tolerance for this. + */ + if (likely(!atomic_add_negative_release(-1, &ref->refcnt))) + return false; + + /* + * Handle the last reference drop and cases inside the saturation + * and dead zones. + */ + return rcuref_put_slowpath(ref); +} + +/** + * rcuref_put_rcusafe -- Release one reference for a rcuref reference count RCU safe + * @ref: Pointer to the reference count + * + * Provides release memory ordering, such that prior loads and stores are done + * before, and provides an acquire ordering on success such that free() + * must come after. + * + * Can be invoked from contexts, which guarantee that no grace period can + * happen which would free the object concurrently if the decrement drops + * the last reference and the slowpath races against a concurrent get() and + * put() pair. rcu_read_lock()'ed and atomic contexts qualify. + * + * Return: + * True if this was the last reference with no future references + * possible. This signals the caller that it can safely release the + * object which is protected by the reference counter. + * + * False if there are still active references or the put() raced + * with a concurrent get()/put() pair. Caller is not allowed to + * release the protected object. + */ +static inline __must_check bool rcuref_put_rcusafe(rcuref_t *ref) +{ + return __rcuref_put(ref); +} + +/** + * rcuref_put -- Release one reference for a rcuref reference count + * @ref: Pointer to the reference count + * + * Can be invoked from any context. + * + * Provides release memory ordering, such that prior loads and stores are done + * before, and provides an acquire ordering on success such that free() + * must come after. + * + * Return: + * + * True if this was the last reference with no future references + * possible. This signals the caller that it can safely schedule the + * object, which is protected by the reference counter, for + * deconstruction. + * + * False if there are still active references or the put() raced + * with a concurrent get()/put() pair. Caller is not allowed to + * deconstruct the protected object. + */ +static inline __must_check bool rcuref_put(rcuref_t *ref) +{ + bool released; + + preempt_disable(); + released = __rcuref_put(ref); + preempt_enable(); + return released; +} + +#endif diff --git a/include/linux/types.h b/include/linux/types.h index ea8cf60a8a79..688fb943556a 100644 --- a/include/linux/types.h +++ b/include/linux/types.h @@ -175,6 +175,12 @@ typedef struct { } atomic64_t; #endif +typedef struct { + atomic_t refcnt; +} rcuref_t; + +#define RCUREF_INIT(i) { .refcnt = ATOMIC_INIT(i - 1) } + struct list_head { struct list_head *next, *prev; }; -- cgit v1.2.3 From d2c48b2387eb89e0bf2a2e06e30987cf410acad4 Mon Sep 17 00:00:00 2001 From: Pierre Gondois Date: Thu, 16 Feb 2023 09:49:19 +0100 Subject: firmware: arm_sdei: Fix sleep from invalid context BUG Running a preempt-rt (v6.2-rc3-rt1) based kernel on an Ampere Altra triggers: BUG: sleeping function called from invalid context at kernel/locking/spinlock_rt.c:46 in_atomic(): 0, irqs_disabled(): 128, non_block: 0, pid: 24, name: cpuhp/0 preempt_count: 0, expected: 0 RCU nest depth: 0, expected: 0 3 locks held by cpuhp/0/24: #0: ffffda30217c70d0 (cpu_hotplug_lock){++++}-{0:0}, at: cpuhp_thread_fun+0x5c/0x248 #1: ffffda30217c7120 (cpuhp_state-up){+.+.}-{0:0}, at: cpuhp_thread_fun+0x5c/0x248 #2: ffffda3021c711f0 (sdei_list_lock){....}-{3:3}, at: sdei_cpuhp_up+0x3c/0x130 irq event stamp: 36 hardirqs last enabled at (35): [] finish_task_switch+0xb4/0x2b0 hardirqs last disabled at (36): [] cpuhp_thread_fun+0x21c/0x248 softirqs last enabled at (0): [] copy_process+0x63c/0x1ac0 softirqs last disabled at (0): [<0000000000000000>] 0x0 CPU: 0 PID: 24 Comm: cpuhp/0 Not tainted 5.19.0-rc3-rt5-[...] Hardware name: WIWYNN Mt.Jade Server [...] Call trace: dump_backtrace+0x114/0x120 show_stack+0x20/0x70 dump_stack_lvl+0x9c/0xd8 dump_stack+0x18/0x34 __might_resched+0x188/0x228 rt_spin_lock+0x70/0x120 sdei_cpuhp_up+0x3c/0x130 cpuhp_invoke_callback+0x250/0xf08 cpuhp_thread_fun+0x120/0x248 smpboot_thread_fn+0x280/0x320 kthread+0x130/0x140 ret_from_fork+0x10/0x20 sdei_cpuhp_up() is called in the STARTING hotplug section, which runs with interrupts disabled. Use a CPUHP_AP_ONLINE_DYN entry instead to execute the cpuhp cb later, with preemption enabled. SDEI originally got its own cpuhp slot to allow interacting with perf. It got superseded by pNMI and this early slot is not relevant anymore. [1] Some SDEI calls (e.g. SDEI_1_0_FN_SDEI_PE_MASK) take actions on the calling CPU. It is checked that preemption is disabled for them. _ONLINE cpuhp cb are executed in the 'per CPU hotplug thread'. Preemption is enabled in those threads, but their cpumask is limited to 1 CPU. Move 'WARN_ON_ONCE(preemptible())' statements so that SDEI cpuhp cb don't trigger them. Also add a check for the SDEI_1_0_FN_SDEI_PRIVATE_RESET SDEI call which acts on the calling CPU. [1]: https://lore.kernel.org/all/5813b8c5-ae3e-87fd-fccc-94c9cd08816d@arm.com/ Suggested-by: James Morse Signed-off-by: Pierre Gondois Reviewed-by: James Morse Link: https://lore.kernel.org/r/20230216084920.144064-1-pierre.gondois@arm.com Signed-off-by: Will Deacon --- include/linux/cpuhotplug.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index c6fab004104a..5066fa20e3e9 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -163,7 +163,6 @@ enum cpuhp_state { CPUHP_AP_PERF_X86_CSTATE_STARTING, CPUHP_AP_PERF_XTENSA_STARTING, CPUHP_AP_MIPS_OP_LOONGSON3_STARTING, - CPUHP_AP_ARM_SDEI_STARTING, CPUHP_AP_ARM_VFP_STARTING, CPUHP_AP_ARM64_DEBUG_MONITORS_STARTING, CPUHP_AP_PERF_ARM_HW_BREAKPOINT_STARTING, -- cgit v1.2.3 From 76d0de5729c0569c4071e7f21fcab394e502f03a Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Thu, 2 Feb 2023 00:56:01 +0900 Subject: fprobe: Pass entry_data to handlers Pass the private entry_data to the entry and exit handlers so that they can share the context data, something like saved function arguments etc. User must specify the private entry_data size by @entry_data_size field before registering the fprobe. Link: https://lkml.kernel.org/r/167526696173.433354.17408372048319432574.stgit@mhiramat.roam.corp.google.com Cc: Florent Revest Cc: Mark Rutland Cc: Will Deacon Signed-off-by: Masami Hiramatsu (Google) Signed-off-by: Steven Rostedt (Google) --- include/linux/fprobe.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fprobe.h b/include/linux/fprobe.h index 1c2bde0ead73..e0d4e6136249 100644 --- a/include/linux/fprobe.h +++ b/include/linux/fprobe.h @@ -13,6 +13,7 @@ * @nmissed: The counter for missing events. * @flags: The status flag. * @rethook: The rethook data structure. (internal data) + * @entry_data_size: The private data storage size. * @entry_handler: The callback function for function entry. * @exit_handler: The callback function for function exit. */ @@ -29,9 +30,12 @@ struct fprobe { unsigned long nmissed; unsigned int flags; struct rethook *rethook; + size_t entry_data_size; - void (*entry_handler)(struct fprobe *fp, unsigned long entry_ip, struct pt_regs *regs); - void (*exit_handler)(struct fprobe *fp, unsigned long entry_ip, struct pt_regs *regs); + void (*entry_handler)(struct fprobe *fp, unsigned long entry_ip, + struct pt_regs *regs, void *entry_data); + void (*exit_handler)(struct fprobe *fp, unsigned long entry_ip, + struct pt_regs *regs, void *entry_data); }; /* This fprobe is soft-disabled. */ -- cgit v1.2.3 From 59a7a298565aa0ce44ce8e4fbcbb89a19730013a Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Thu, 2 Feb 2023 00:56:19 +0900 Subject: fprobe: Add nr_maxactive to specify rethook_node pool size Add nr_maxactive to specify rethook_node pool size. This means the maximum number of actively running target functions concurrently for probing by exit_handler. Note that if the running function is preempted or sleep, it is still counted as 'active'. Link: https://lkml.kernel.org/r/167526697917.433354.17779774988245113106.stgit@mhiramat.roam.corp.google.com Cc: Florent Revest Cc: Mark Rutland Cc: Will Deacon Signed-off-by: Masami Hiramatsu (Google) Signed-off-by: Steven Rostedt (Google) --- include/linux/fprobe.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fprobe.h b/include/linux/fprobe.h index e0d4e6136249..678f741a7b33 100644 --- a/include/linux/fprobe.h +++ b/include/linux/fprobe.h @@ -14,6 +14,7 @@ * @flags: The status flag. * @rethook: The rethook data structure. (internal data) * @entry_data_size: The private data storage size. + * @nr_maxactive: The max number of active functions. * @entry_handler: The callback function for function entry. * @exit_handler: The callback function for function exit. */ @@ -31,6 +32,7 @@ struct fprobe { unsigned int flags; struct rethook *rethook; size_t entry_data_size; + int nr_maxactive; void (*entry_handler)(struct fprobe *fp, unsigned long entry_ip, struct pt_regs *regs, void *entry_data); -- cgit v1.2.3 From 39d954200bf6ad503c722e44d0be80c7b826fa42 Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Thu, 2 Feb 2023 00:56:38 +0900 Subject: fprobe: Skip exit_handler if entry_handler returns !0 Skip hooking function return and calling exit_handler if the entry_handler() returns !0. Link: https://lkml.kernel.org/r/167526699798.433354.10998365726830117303.stgit@mhiramat.roam.corp.google.com Cc: Florent Revest Cc: Mark Rutland Cc: Will Deacon Signed-off-by: Masami Hiramatsu (Google) Signed-off-by: Steven Rostedt (Google) --- include/linux/fprobe.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fprobe.h b/include/linux/fprobe.h index 678f741a7b33..47fefc7f363b 100644 --- a/include/linux/fprobe.h +++ b/include/linux/fprobe.h @@ -34,8 +34,8 @@ struct fprobe { size_t entry_data_size; int nr_maxactive; - void (*entry_handler)(struct fprobe *fp, unsigned long entry_ip, - struct pt_regs *regs, void *entry_data); + int (*entry_handler)(struct fprobe *fp, unsigned long entry_ip, + struct pt_regs *regs, void *entry_data); void (*exit_handler)(struct fprobe *fp, unsigned long entry_ip, struct pt_regs *regs, void *entry_data); }; -- cgit v1.2.3 From d155df53f31068c3340733d586eb9b3ddfd70fc5 Mon Sep 17 00:00:00 2001 From: Ma Wupeng Date: Fri, 17 Feb 2023 10:56:15 +0800 Subject: x86/mm/pat: clear VM_PAT if copy_p4d_range failed Syzbot reports a warning in untrack_pfn(). Digging into the root we found that this is due to memory allocation failure in pmd_alloc_one. And this failure is produced due to failslab. In copy_page_range(), memory alloaction for pmd failed. During the error handling process in copy_page_range(), mmput() is called to remove all vmas. While untrack_pfn this empty pfn, warning happens. Here's a simplified flow: dup_mm dup_mmap copy_page_range copy_p4d_range copy_pud_range copy_pmd_range pmd_alloc __pmd_alloc pmd_alloc_one page = alloc_pages(gfp, 0); if (!page) return NULL; mmput exit_mmap unmap_vmas unmap_single_vma untrack_pfn follow_phys WARN_ON_ONCE(1); Since this vma is not generate successfully, we can clear flag VM_PAT. In this case, untrack_pfn() will not be called while cleaning this vma. Function untrack_pfn_moved() has also been renamed to fit the new logic. Link: https://lkml.kernel.org/r/20230217025615.1595558-1-mawupeng1@huawei.com Signed-off-by: Ma Wupeng Reported-by: Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Dave Hansen Cc: Peter Zijlstra Cc: Suresh Siddha Cc: Toshi Kani Signed-off-by: Andrew Morton --- include/linux/pgtable.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index c63cd44777ec..9dc936bc77d1 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -1191,9 +1191,10 @@ static inline void untrack_pfn(struct vm_area_struct *vma, } /* - * untrack_pfn_moved is called while mremapping a pfnmap for a new region. + * untrack_pfn_clear is called while mremapping a pfnmap for a new region + * or fails to copy pgtable during duplicate vm area. */ -static inline void untrack_pfn_moved(struct vm_area_struct *vma) +static inline void untrack_pfn_clear(struct vm_area_struct *vma) { } #else @@ -1205,7 +1206,7 @@ extern void track_pfn_insert(struct vm_area_struct *vma, pgprot_t *prot, extern int track_pfn_copy(struct vm_area_struct *vma); extern void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn, unsigned long size, bool mm_wr_locked); -extern void untrack_pfn_moved(struct vm_area_struct *vma); +extern void untrack_pfn_clear(struct vm_area_struct *vma); #endif #ifdef CONFIG_MMU -- cgit v1.2.3 From 9a52b2f32a0942047348b30f866b846da5fcf4e3 Mon Sep 17 00:00:00 2001 From: "T.J. Alumbaugh" Date: Tue, 14 Feb 2023 03:54:44 +0000 Subject: mm: multi-gen LRU: clean up sysfs code This patch cleans up the sysfs code. Specifically, 1. use sysfs_emit(), 2. use __ATTR_RW(), and 3. constify multi-gen LRU struct attribute_group. Link: https://lkml.kernel.org/r/20230214035445.1250139-1-talumbau@google.com Signed-off-by: T.J. Alumbaugh Cc: Yu Zhao Signed-off-by: Andrew Morton --- include/linux/mmzone.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 9fb1b03b83b2..bf8786d45b31 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -1369,7 +1369,7 @@ typedef struct pglist_data { #ifdef CONFIG_LRU_GEN /* kswap mm walk data */ - struct lru_gen_mm_walk mm_walk; + struct lru_gen_mm_walk mm_walk; /* lru_gen_folio list */ struct lru_gen_memcg memcg_lru; #endif -- cgit v1.2.3 From aa464ba9a1e444d5ef95bb63ee3b2ef26fc96ed7 Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Fri, 3 Feb 2023 17:18:34 +1000 Subject: lazy tlb: introduce lazy tlb mm refcount helper functions Add explicit _lazy_tlb annotated functions for lazy tlb mm refcounting. This makes the lazy tlb mm references more obvious, and allows the refcounting scheme to be modified in later changes. There is no functional change with this patch. Link: https://lkml.kernel.org/r/20230203071837.1136453-3-npiggin@gmail.com Signed-off-by: Nicholas Piggin Acked-by: Linus Torvalds Cc: Andy Lutomirski Cc: Catalin Marinas Cc: Christophe Leroy Cc: Dave Hansen Cc: Michael Ellerman Cc: Nadav Amit Cc: Peter Zijlstra Cc: Rik van Riel Cc: Will Deacon Signed-off-by: Andrew Morton --- include/linux/sched/mm.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index 2a243616f222..5376caf6fcf3 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -79,6 +79,22 @@ static inline void mmdrop_sched(struct mm_struct *mm) } #endif +/* Helpers for lazy TLB mm refcounting */ +static inline void mmgrab_lazy_tlb(struct mm_struct *mm) +{ + mmgrab(mm); +} + +static inline void mmdrop_lazy_tlb(struct mm_struct *mm) +{ + mmdrop(mm); +} + +static inline void mmdrop_lazy_tlb_sched(struct mm_struct *mm) +{ + mmdrop_sched(mm); +} + /** * mmget() - Pin the address space associated with a &struct mm_struct. * @mm: The address space to pin. -- cgit v1.2.3 From 88e3009b5283bbd41447f0352d0b9df16cf6f183 Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Fri, 3 Feb 2023 17:18:35 +1000 Subject: lazy tlb: allow lazy tlb mm refcounting to be configurable Add CONFIG_MMU_TLB_REFCOUNT which enables refcounting of the lazy tlb mm when it is context switched. This can be disabled by architectures that don't require this refcounting if they clean up lazy tlb mms when the last refcount is dropped. Currently this is always enabled, so the patch introduces no functional change. Link: https://lkml.kernel.org/r/20230203071837.1136453-4-npiggin@gmail.com Signed-off-by: Nicholas Piggin Acked-by: Linus Torvalds Cc: Andy Lutomirski Cc: Catalin Marinas Cc: Christophe Leroy Cc: Dave Hansen Cc: Michael Ellerman Cc: Nadav Amit Cc: Peter Zijlstra Cc: Rik van Riel Cc: Will Deacon Signed-off-by: Andrew Morton --- include/linux/sched/mm.h | 18 +++++++++++++++--- 1 file changed, 15 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index 5376caf6fcf3..689dbe812563 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -82,17 +82,29 @@ static inline void mmdrop_sched(struct mm_struct *mm) /* Helpers for lazy TLB mm refcounting */ static inline void mmgrab_lazy_tlb(struct mm_struct *mm) { - mmgrab(mm); + if (IS_ENABLED(CONFIG_MMU_LAZY_TLB_REFCOUNT)) + mmgrab(mm); } static inline void mmdrop_lazy_tlb(struct mm_struct *mm) { - mmdrop(mm); + if (IS_ENABLED(CONFIG_MMU_LAZY_TLB_REFCOUNT)) { + mmdrop(mm); + } else { + /* + * mmdrop_lazy_tlb must provide a full memory barrier, see the + * membarrier comment finish_task_switch which relies on this. + */ + smp_mb(); + } } static inline void mmdrop_lazy_tlb_sched(struct mm_struct *mm) { - mmdrop_sched(mm); + if (IS_ENABLED(CONFIG_MMU_LAZY_TLB_REFCOUNT)) + mmdrop_sched(mm); + else + smp_mb(); /* see mmdrop_lazy_tlb() above */ } /** -- cgit v1.2.3 From 4c85c0be3d7a9a7ffe48bfe0954eacc0ba9d3c75 Mon Sep 17 00:00:00 2001 From: Hyeonggon Yoo <42.hyeyoo@gmail.com> Date: Mon, 30 Jan 2023 13:25:13 +0900 Subject: mm, printk: introduce new format %pGt for page_type %pGp format is used to display 'flags' field of a struct page. However, some page flags (i.e. PG_buddy, see page-flags.h for more details) are stored in page_type field. To display human-readable output of page_type, introduce %pGt format. It is important to note the meaning of bits are different in page_type. if page_type is 0xffffffff, no flags are set. Setting PG_buddy (0x00000080) flag results in a page_type of 0xffffff7f. Clearing a bit actually means setting a flag. Bits in page_type are inverted when displaying type names. Only values for which page_type_has_type() returns true are considered as page_type, to avoid confusion with mapcount values. if it returns false, only raw values are displayed and not page type names. Link: https://lkml.kernel.org/r/20230130042514.2418-3-42.hyeyoo@gmail.com Signed-off-by: Hyeonggon Yoo <42.hyeyoo@gmail.com> Reviewed-by: Petr Mladek [vsprintf part] Cc: Andy Shevchenko Cc: David Hildenbrand Cc: Joe Perches Cc: John Ogness Cc: Matthew Wilcox Cc: Sergey Senozhatsky Cc: Steven Rostedt (Google) Cc: Vlastimil Babka Signed-off-by: Andrew Morton --- include/linux/page-flags.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index a7e3a3405520..57287102c5bd 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -926,9 +926,14 @@ static inline bool is_page_hwpoison(struct page *page) #define PageType(page, flag) \ ((page->page_type & (PAGE_TYPE_BASE | flag)) == PAGE_TYPE_BASE) +static inline int page_type_has_type(unsigned int page_type) +{ + return (int)page_type < PAGE_MAPCOUNT_RESERVE; +} + static inline int page_has_type(struct page *page) { - return (int)page->page_type < PAGE_MAPCOUNT_RESERVE; + return page_type_has_type(page->page_type); } #define PAGE_TYPE_OPS(uname, lname) \ -- cgit v1.2.3 From 16d91faf09be148d9c1cf4999f4d15fb24a7cd72 Mon Sep 17 00:00:00 2001 From: Peter Collingbourne Date: Thu, 16 Feb 2023 11:59:24 -0800 Subject: kasan: call clear_page with a match-all tag instead of changing page tag Instead of changing the page's tag solely in order to obtain a pointer with a match-all tag and then changing it back again, just convert the pointer that we get from kmap_atomic() into one with a match-all tag before passing it to clear_page(). On a certain microarchitecture, this has been observed to cause a measurable improvement in microbenchmark performance, presumably as a result of being able to avoid the atomic operations on the page tag. Link: https://lkml.kernel.org/r/20230216195924.3287772-1-pcc@google.com Signed-off-by: Peter Collingbourne Link: https://linux-review.googlesource.com/id/I0249822cc29097ca7a04ad48e8eb14871f80e711 Reviewed-by: Andrey Konovalov Reviewed-by: Catalin Marinas Cc: Andrey Ryabinin Cc: Evgenii Stepanov Cc: Peter Collingbourne Cc: Vincenzo Frascino Cc: Will Deacon Signed-off-by: Andrew Morton --- include/linux/highmem.h | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/highmem.h b/include/linux/highmem.h index 8fc10089e19e..9c7cdaa3de8c 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -243,12 +243,10 @@ static inline void clear_highpage(struct page *page) static inline void clear_highpage_kasan_tagged(struct page *page) { - u8 tag; + void *kaddr = kmap_local_page(page); - tag = page_kasan_tag(page); - page_kasan_tag_reset(page); - clear_highpage(page); - page_kasan_tag_set(page, tag); + clear_page(kasan_reset_tag(kaddr)); + kunmap_local(kaddr); } #ifndef __HAVE_ARCH_TAG_CLEAR_HIGHPAGE -- cgit v1.2.3 From 3e4fb13ac34bad94cf390415b1e6bc3ca9520d65 Mon Sep 17 00:00:00 2001 From: Kefeng Wang Date: Thu, 2 Mar 2023 19:58:35 +0800 Subject: mm: swap: remove unneeded cgroup_throttle_swaprate() All the callers of cgroup_throttle_swaprate() are converted to folio_throttle_swaprate(), so make __cgroup_throttle_swaprate() to take a folio, and rename it to __folio_throttle_swaprate(), also rename gfp_mask to gfp and drop redundant extern keyword. finally, drop unused cgroup_throttle_swaprate(). Link: https://lkml.kernel.org/r/20230302115835.105364-8-wangkefeng.wang@huawei.com Signed-off-by: Kefeng Wang Reviewed-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton --- include/linux/swap.h | 12 ++++-------- 1 file changed, 4 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index 209a425739a9..d5d0b54e90e8 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -641,22 +641,18 @@ extern atomic_t zswap_stored_pages; #endif #if defined(CONFIG_SWAP) && defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP) -extern void __cgroup_throttle_swaprate(struct page *page, gfp_t gfp_mask); -static inline void cgroup_throttle_swaprate(struct page *page, gfp_t gfp_mask) +void __folio_throttle_swaprate(struct folio *folio, gfp_t gfp); +static inline void folio_throttle_swaprate(struct folio *folio, gfp_t gfp) { if (mem_cgroup_disabled()) return; - __cgroup_throttle_swaprate(page, gfp_mask); + __folio_throttle_swaprate(folio, gfp); } #else -static inline void cgroup_throttle_swaprate(struct page *page, gfp_t gfp_mask) -{ -} -#endif static inline void folio_throttle_swaprate(struct folio *folio, gfp_t gfp) { - cgroup_throttle_swaprate(&folio->page, gfp); } +#endif #if defined(CONFIG_MEMCG) && defined(CONFIG_SWAP) void mem_cgroup_swapout(struct folio *folio, swp_entry_t entry); -- cgit v1.2.3 From 99c29133639a29fa803ea27ec79bf9e732efd062 Mon Sep 17 00:00:00 2001 From: Gerald Schaefer Date: Mon, 6 Mar 2023 17:15:48 +0100 Subject: mm: add PTE pointer parameter to flush_tlb_fix_spurious_fault() s390 can do more fine-grained handling of spurious TLB protection faults, when there also is the PTE pointer available. Therefore, pass on the PTE pointer to flush_tlb_fix_spurious_fault() as an additional parameter. This will add no functional change to other architectures, but those with private flush_tlb_fix_spurious_fault() implementations need to be made aware of the new parameter. Link: https://lkml.kernel.org/r/20230306161548.661740-1-gerald.schaefer@linux.ibm.com Signed-off-by: Gerald Schaefer Reviewed-by: Alexander Gordeev Acked-by: Catalin Marinas [arm64] Acked-by: Michael Ellerman [powerpc] Acked-by: David Hildenbrand Cc: Anshuman Khandual Cc: Borislav Petkov (AMD) Cc: Christophe Leroy Cc: Dave Hansen Cc: Ingo Molnar Cc: Matthew Wilcox (Oracle) Cc: Nicholas Piggin Cc: Thomas Bogendoerfer Cc: Thomas Gleixner Cc: Will Deacon Signed-off-by: Andrew Morton --- include/linux/pgtable.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index 9dc936bc77d1..c5a51481bbb9 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -817,7 +817,7 @@ static inline void arch_swap_restore(swp_entry_t entry, struct folio *folio) #endif #ifndef flush_tlb_fix_spurious_fault -#define flush_tlb_fix_spurious_fault(vma, address) flush_tlb_page(vma, address) +#define flush_tlb_fix_spurious_fault(vma, address, ptep) flush_tlb_page(vma, address) #endif /* -- cgit v1.2.3 From 82b3aa2681ca92421c4b508e7c390000273c53fe Mon Sep 17 00:00:00 2001 From: Yue Zhao Date: Mon, 6 Mar 2023 23:41:36 +0800 Subject: mm, memcg: Prevent memory.swappiness load/store tearing The knob for cgroup v1 memory controller: memory.swappiness is not protected by any locking so it can be modified while it is used. This is not an actual problem because races are unlikely. But it is better to use [READ|WRITE]_ONCE to prevent compiler from doing anything funky. The access of memcg->swappiness and vm_swappiness is lockless, so both of them can be concurrently set at the same time as we are trying to read them. All occurrences of memcg->swappiness and vm_swappiness are updated with [READ|WRITE]_ONCE. [findns94@gmail.com: v3] Link: https://lkml.kernel.org/r/20230308162555.14195-3-findns94@gmail.com Link: https://lkml.kernel.org/r/20230306154138.3775-3-findns94@gmail.com Signed-off-by: Yue Zhao Acked-by: Michal Hocko Acked-by: Shakeel Butt Acked-by: Roman Gushchin Cc: Johannes Weiner Cc: Matthew Wilcox (Oracle) Cc: Muchun Song Cc: Tang Yizhou Signed-off-by: Andrew Morton --- include/linux/swap.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index d5d0b54e90e8..bfc3b06b5f8f 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -620,18 +620,18 @@ static inline int mem_cgroup_swappiness(struct mem_cgroup *memcg) { /* Cgroup2 doesn't have per-cgroup swappiness */ if (cgroup_subsys_on_dfl(memory_cgrp_subsys)) - return vm_swappiness; + return READ_ONCE(vm_swappiness); /* root ? */ if (mem_cgroup_disabled() || mem_cgroup_is_root(memcg)) - return vm_swappiness; + return READ_ONCE(vm_swappiness); - return memcg->swappiness; + return READ_ONCE(memcg->swappiness); } #else static inline int mem_cgroup_swappiness(struct mem_cgroup *mem) { - return vm_swappiness; + return READ_ONCE(vm_swappiness); } #endif -- cgit v1.2.3 From 452a8f40728065800b5a5b81f1152e9a16d39656 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 7 Mar 2023 15:31:25 +0100 Subject: mm,jfs: move write_one_page/folio_write_one to jfs The last remaining user of folio_write_one through the write_one_page wrapper is jfs, so move the functionality there and hard code the call to metapage_writepage. Note that the use of the pagecache by the JFS 'metapage' buffer cache is a bit odd, and we could probably do without VM-level dirty tracking at all, but that's a change for another time. Link: https://lkml.kernel.org/r/20230307143125.27778-4-hch@lst.de Signed-off-by: Christoph Hellwig Acked-by: Dave Kleikamp Cc: Changwei Ge Cc: Evgeniy Dushistov Cc: Gang He Cc: Jan Kara Cc: Jan Kara via Ocfs2-devel Cc: Joel Becker Cc: Joseph Qi Cc: Joseph Qi Cc: Jun Piao Cc: Junxiao Bi Cc: Mark Fasheh Cc: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton --- include/linux/pagemap.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 0acb8e1fb7af..853184a46411 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -1066,12 +1066,6 @@ static inline void folio_cancel_dirty(struct folio *folio) bool folio_clear_dirty_for_io(struct folio *folio); bool clear_page_dirty_for_io(struct page *page); void folio_invalidate(struct folio *folio, size_t offset, size_t length); -int __must_check folio_write_one(struct folio *folio); -static inline int __must_check write_one_page(struct page *page) -{ - return folio_write_one(page_folio(page)); -} - int __set_page_dirty_nobuffers(struct page *page); bool noop_dirty_folio(struct address_space *mapping, struct folio *folio); -- cgit v1.2.3 From 2c6efe9cf2d7841b75fe38ed1adbd41a90f51ba0 Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Thu, 9 Mar 2023 15:05:45 -0800 Subject: shmem: add support to ignore swap In doing experimentations with shmem having the option to avoid swap becomes a useful mechanism. One of the *raves* about brd over shmem is you can avoid swap, but that's not really a good reason to use brd if we can instead use shmem. Using brd has its own good reasons to exist, but just because "tmpfs" doesn't let you do that is not a great reason to avoid it if we can easily add support for it. I don't add support for reconfiguring incompatible options, but if we really wanted to we can add support for that. To avoid swap we use mapping_set_unevictable() upon inode creation, and put a WARN_ON_ONCE() stop-gap on writepages() for reclaim. Link: https://lkml.kernel.org/r/20230309230545.2930737-7-mcgrof@kernel.org Signed-off-by: Luis Chamberlain Acked-by: Christian Brauner Tested-by: Xin Hao Reviewed-by: Davidlohr Bueso Cc: Adam Manzanares Cc: David Hildenbrand Cc: Davidlohr Bueso Cc: Hugh Dickins Cc: Kees Cook Cc: Matthew Wilcox Cc: Pankaj Raghav Cc: Yosry Ahmed Signed-off-by: Andrew Morton --- include/linux/shmem_fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index 103d1000a5a2..50bf82b36995 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -45,6 +45,7 @@ struct shmem_sb_info { kuid_t uid; /* Mount uid for root directory */ kgid_t gid; /* Mount gid for root directory */ bool full_inums; /* If i_ino should be uint or ino_t */ + bool noswap; /* ignores VM reclaim / swap requests */ ino_t next_ino; /* The next per-sb inode number to use */ ino_t __percpu *ino_batch; /* The next per-cpu inode number to use */ struct mempolicy *mpol; /* default memory policy for mappings */ -- cgit v1.2.3 From 7eb16f23b9a415f062db22739e59bb144e0b24ab Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Fri, 10 Mar 2023 17:29:05 +0100 Subject: io-mapping: don't disable preempt on RT in io_mapping_map_atomic_wc(). io_mapping_map_atomic_wc() disables preemption and pagefaults for historical reasons. The conversion to io_mapping_map_local_wc(), which only disables migration, cannot be done wholesale because quite some call sites need to be updated to accommodate with the changed semantics. On PREEMPT_RT enabled kernels the io_mapping_map_atomic_wc() semantics are problematic due to the implicit disabling of preemption which makes it impossible to acquire 'sleeping' spinlocks within the mapped atomic sections. PREEMPT_RT replaces the preempt_disable() with a migrate_disable() for more than a decade. It could be argued that this is a justification to do this unconditionally, but PREEMPT_RT covers only a limited number of architectures and it disables some functionality which limits the coverage further. Limit the replacement to PREEMPT_RT for now. This is also done kmap_atomic(). Link: https://lkml.kernel.org/r/20230310162905.O57Pj7hh@linutronix.de Signed-off-by: Sebastian Andrzej Siewior Reported-by: Richard Weinberger Link: https://lore.kernel.org/CAFLxGvw0WMxaMqYqJ5WgvVSbKHq2D2xcXTOgMCpgq9nDC-MWTQ@mail.gmail.com Cc: Thomas Gleixner Signed-off-by: Andrew Morton --- include/linux/io-mapping.h | 20 ++++++++++++++++---- 1 file changed, 16 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/io-mapping.h b/include/linux/io-mapping.h index 09d4f17c8d3b..7376c1df9c90 100644 --- a/include/linux/io-mapping.h +++ b/include/linux/io-mapping.h @@ -69,7 +69,10 @@ io_mapping_map_atomic_wc(struct io_mapping *mapping, BUG_ON(offset >= mapping->size); phys_addr = mapping->base + offset; - preempt_disable(); + if (!IS_ENABLED(CONFIG_PREEMPT_RT)) + preempt_disable(); + else + migrate_disable(); pagefault_disable(); return __iomap_local_pfn_prot(PHYS_PFN(phys_addr), mapping->prot); } @@ -79,7 +82,10 @@ io_mapping_unmap_atomic(void __iomem *vaddr) { kunmap_local_indexed((void __force *)vaddr); pagefault_enable(); - preempt_enable(); + if (!IS_ENABLED(CONFIG_PREEMPT_RT)) + preempt_enable(); + else + migrate_enable(); } static inline void __iomem * @@ -162,7 +168,10 @@ static inline void __iomem * io_mapping_map_atomic_wc(struct io_mapping *mapping, unsigned long offset) { - preempt_disable(); + if (!IS_ENABLED(CONFIG_PREEMPT_RT)) + preempt_disable(); + else + migrate_disable(); pagefault_disable(); return io_mapping_map_wc(mapping, offset, PAGE_SIZE); } @@ -172,7 +181,10 @@ io_mapping_unmap_atomic(void __iomem *vaddr) { io_mapping_unmap(vaddr); pagefault_enable(); - preempt_enable(); + if (!IS_ENABLED(CONFIG_PREEMPT_RT)) + preempt_enable(); + else + migrate_enable(); } static inline void __iomem * -- cgit v1.2.3 From 0a54864f8dfb64b64c84c9db6ff70e0e93690a33 Mon Sep 17 00:00:00 2001 From: Peter Collingbourne Date: Thu, 9 Mar 2023 20:29:14 -0800 Subject: kasan: remove PG_skip_kasan_poison flag Code inspection reveals that PG_skip_kasan_poison is redundant with kasantag, because the former is intended to be set iff the latter is the match-all tag. It can also be observed that it's basically pointless to poison pages which have kasantag=0, because any pages with this tag would have been pointed to by pointers with match-all tags, so poisoning the pages would have little to no effect in terms of bug detection. Therefore, change the condition in should_skip_kasan_poison() to check kasantag instead, and remove PG_skip_kasan_poison and associated flags. Link: https://lkml.kernel.org/r/20230310042914.3805818-3-pcc@google.com Link: https://linux-review.googlesource.com/id/I57f825f2eaeaf7e8389d6cf4597c8a5821359838 Signed-off-by: Peter Collingbourne Reviewed-by: Andrey Konovalov Cc: Andrey Ryabinin Cc: Catalin Marinas Cc: Evgenii Stepanov Cc: Vincenzo Frascino Cc: Will Deacon Signed-off-by: Andrew Morton --- include/linux/gfp_types.h | 30 +++++++++++++----------------- include/linux/page-flags.h | 9 --------- 2 files changed, 13 insertions(+), 26 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gfp_types.h b/include/linux/gfp_types.h index 5088637fe5c2..6583a58670c5 100644 --- a/include/linux/gfp_types.h +++ b/include/linux/gfp_types.h @@ -47,16 +47,14 @@ typedef unsigned int __bitwise gfp_t; #define ___GFP_ACCOUNT 0x400000u #define ___GFP_ZEROTAGS 0x800000u #ifdef CONFIG_KASAN_HW_TAGS -#define ___GFP_SKIP_ZERO 0x1000000u -#define ___GFP_SKIP_KASAN_UNPOISON 0x2000000u -#define ___GFP_SKIP_KASAN_POISON 0x4000000u +#define ___GFP_SKIP_ZERO 0x1000000u +#define ___GFP_SKIP_KASAN 0x2000000u #else -#define ___GFP_SKIP_ZERO 0 -#define ___GFP_SKIP_KASAN_UNPOISON 0 -#define ___GFP_SKIP_KASAN_POISON 0 +#define ___GFP_SKIP_ZERO 0 +#define ___GFP_SKIP_KASAN 0 #endif #ifdef CONFIG_LOCKDEP -#define ___GFP_NOLOCKDEP 0x8000000u +#define ___GFP_NOLOCKDEP 0x4000000u #else #define ___GFP_NOLOCKDEP 0 #endif @@ -234,25 +232,24 @@ typedef unsigned int __bitwise gfp_t; * memory tags at the same time as zeroing memory has minimal additional * performace impact. * - * %__GFP_SKIP_KASAN_UNPOISON makes KASAN skip unpoisoning on page allocation. - * Only effective in HW_TAGS mode. - * - * %__GFP_SKIP_KASAN_POISON makes KASAN skip poisoning on page deallocation. - * Typically, used for userspace pages. Only effective in HW_TAGS mode. + * %__GFP_SKIP_KASAN makes KASAN skip unpoisoning on page allocation. + * Used for userspace and vmalloc pages; the latter are unpoisoned by + * kasan_unpoison_vmalloc instead. For userspace pages, results in + * poisoning being skipped as well, see should_skip_kasan_poison for + * details. Only effective in HW_TAGS mode. */ #define __GFP_NOWARN ((__force gfp_t)___GFP_NOWARN) #define __GFP_COMP ((__force gfp_t)___GFP_COMP) #define __GFP_ZERO ((__force gfp_t)___GFP_ZERO) #define __GFP_ZEROTAGS ((__force gfp_t)___GFP_ZEROTAGS) #define __GFP_SKIP_ZERO ((__force gfp_t)___GFP_SKIP_ZERO) -#define __GFP_SKIP_KASAN_UNPOISON ((__force gfp_t)___GFP_SKIP_KASAN_UNPOISON) -#define __GFP_SKIP_KASAN_POISON ((__force gfp_t)___GFP_SKIP_KASAN_POISON) +#define __GFP_SKIP_KASAN ((__force gfp_t)___GFP_SKIP_KASAN) /* Disable lockdep for GFP context tracking */ #define __GFP_NOLOCKDEP ((__force gfp_t)___GFP_NOLOCKDEP) /* Room for N __GFP_FOO bits */ -#define __GFP_BITS_SHIFT (27 + IS_ENABLED(CONFIG_LOCKDEP)) +#define __GFP_BITS_SHIFT (26 + IS_ENABLED(CONFIG_LOCKDEP)) #define __GFP_BITS_MASK ((__force gfp_t)((1 << __GFP_BITS_SHIFT) - 1)) /** @@ -335,8 +332,7 @@ typedef unsigned int __bitwise gfp_t; #define GFP_DMA __GFP_DMA #define GFP_DMA32 __GFP_DMA32 #define GFP_HIGHUSER (GFP_USER | __GFP_HIGHMEM) -#define GFP_HIGHUSER_MOVABLE (GFP_HIGHUSER | __GFP_MOVABLE | \ - __GFP_SKIP_KASAN_POISON | __GFP_SKIP_KASAN_UNPOISON) +#define GFP_HIGHUSER_MOVABLE (GFP_HIGHUSER | __GFP_MOVABLE | __GFP_SKIP_KASAN) #define GFP_TRANSHUGE_LIGHT ((GFP_HIGHUSER_MOVABLE | __GFP_COMP | \ __GFP_NOMEMALLOC | __GFP_NOWARN) & ~__GFP_RECLAIM) #define GFP_TRANSHUGE (GFP_TRANSHUGE_LIGHT | __GFP_DIRECT_RECLAIM) diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 57287102c5bd..dcda20c47b8f 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -135,9 +135,6 @@ enum pageflags { #ifdef CONFIG_ARCH_USES_PG_ARCH_X PG_arch_2, PG_arch_3, -#endif -#ifdef CONFIG_KASAN_HW_TAGS - PG_skip_kasan_poison, #endif __NR_PAGEFLAGS, @@ -594,12 +591,6 @@ TESTCLEARFLAG(Young, young, PF_ANY) PAGEFLAG(Idle, idle, PF_ANY) #endif -#ifdef CONFIG_KASAN_HW_TAGS -PAGEFLAG(SkipKASanPoison, skip_kasan_poison, PF_HEAD) -#else -PAGEFLAG_FALSE(SkipKASanPoison, skip_kasan_poison) -#endif - /* * PageReported() is used to track reported free pages within the Buddy * allocator. We can use the non-atomic version of the test and set -- cgit v1.2.3 From 42c9db39704839eeb77b27db4c1d57bfa2a54a5b Mon Sep 17 00:00:00 2001 From: Qi Zheng Date: Mon, 13 Mar 2023 19:28:12 +0800 Subject: mm: vmscan: add a map_nr_max field to shrinker_info MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Patch series "make slab shrink lockless", v5. This patch series aims to make slab shrink lockless. 1. Background ============= On our servers, we often find the following system cpu hotspots: 52.22% [kernel] [k] down_read_trylock 19.60% [kernel] [k] up_read 8.86% [kernel] [k] shrink_slab 2.44% [kernel] [k] idr_find 1.25% [kernel] [k] count_shadow_nodes 1.18% [kernel] [k] shrink lruvec 0.71% [kernel] [k] mem_cgroup_iter 0.71% [kernel] [k] shrink_node 0.55% [kernel] [k] find_next_bit And we used bpftrace to capture its calltrace as follows: @[ down_read_trylock+1 shrink_slab+128 shrink_node+371 do_try_to_free_pages+232 try_to_free_pages+243 _alloc_pages_slowpath+771 _alloc_pages_nodemask+702 pagecache_get_page+255 filemap_fault+1361 ext4_filemap_fault+44 __do_fault+76 handle_mm_fault+3543 do_user_addr_fault+442 do_page_fault+48 page_fault+62 ]: 1161690 @[ down_read_trylock+1 shrink_slab+128 shrink_node+371 balance_pgdat+690 kswapd+389 kthread+246 ret_from_fork+31 ]: 8424884 @[ down_read_trylock+1 shrink_slab+128 shrink_node+371 do_try_to_free_pages+232 try_to_free_pages+243 __alloc_pages_slowpath+771 __alloc_pages_nodemask+702 __do_page_cache_readahead+244 filemap_fault+1674 ext4_filemap_fault+44 __do_fault+76 handle_mm_fault+3543 do_user_addr_fault+442 do_page_fault+48 page_fault+62 ]: 20917631 We can see that down_read_trylock() of shrinker_rwsem is being called with high frequency at that time. Because of the poor multicore scalability of atomic operations, this can lead to a significant drop in IPC (instructions per cycle). And more, the shrinker_rwsem is a global read-write lock in shrinkers subsystem, which protects most operations such as slab shrink, registration and unregistration of shrinkers, etc. This can easily cause problems in the following cases. 1) When the memory pressure is high and there are many filesystems mounted or unmounted at the same time, slab shrink will be affected (down_read_trylock() failed). Such as the real workload mentioned by Kirill Tkhai: ``` One of the real workloads from my experience is start of an overcommitted node containing many starting containers after node crash (or many resuming containers after reboot for kernel update). In these cases memory pressure is huge, and the node goes round in long reclaim. ``` 2) If a shrinker is blocked (such as the case mentioned in [1]) and a writer comes in (such as mount a fs), then this writer will be blocked and cause all subsequent shrinker-related operations to be blocked. [1]. https://lore.kernel.org/lkml/20191129214541.3110-1-ptikhomirov@virtuozzo.com/ All the above cases can be solved by replacing the shrinker_rwsem trylocks with SRCU. 2. Survey ========= Before doing the code implementation, I found that there were many similar submissions in the community: a. Davidlohr Bueso submitted a patch in 2015. Subject: [PATCH -next v2] mm: srcu-ify shrinkers Link: https://lore.kernel.org/all/1437080113.3596.2.camel@stgolabs.net/ Result: It was finally merged into the linux-next branch, but failed on arm allnoconfig (without CONFIG_SRCU) b. Tetsuo Handa submitted a patchset in 2017. Subject: [PATCH 1/2] mm,vmscan: Kill global shrinker lock. Link: https://lore.kernel.org/lkml/1510609063-3327-1-git-send-email-penguin-kernel@I-love.SAKURA.ne.jp/ Result: Finally chose to use the current simple way (break when rwsem_is_contended()). And Christoph Hellwig suggested to using SRCU, but SRCU was not unconditionally enabled at the time. c. Kirill Tkhai submitted a patchset in 2018. Subject: [PATCH RFC 00/10] Introduce lockless shrink_slab() Link: https://lore.kernel.org/lkml/153365347929.19074.12509495712735843805.stgit@localhost.localdomain/ Result: At that time, SRCU was not unconditionally enabled, and there were some objections to enabling SRCU. Later, because Kirill's focus was moved to other things, this patchset was not continued to be updated. d. Sultan Alsawaf submitted a patch in 2021. Subject: [PATCH] mm: vmscan: Replace shrinker_rwsem trylocks with SRCU protection Link: https://lore.kernel.org/lkml/20210927074823.5825-1-sultan@kerneltoast.com/ Result: Rejected because SRCU was not unconditionally enabled. We can find that almost all these historical commits were abandoned because SRCU was not unconditionally enabled. But now SRCU has been unconditionally enable by Paul E. McKenney in 2023 [2], so it's time to replace shrinker_rwsem trylocks with SRCU. [2] https://lore.kernel.org/lkml/20230105003759.GA1769545@paulmck-ThinkPad-P17-Gen-1/ 3. Reproduction and testing =========================== We can reproduce the down_read_trylock() hotspot through the following script: ``` #!/bin/bash DIR="/root/shrinker/memcg/mnt" do_create() { mkdir -p /sys/fs/cgroup/memory/test mkdir -p /sys/fs/cgroup/perf_event/test echo 4G > /sys/fs/cgroup/memory/test/memory.limit_in_bytes for i in `seq 0 $1`; do mkdir -p /sys/fs/cgroup/memory/test/$i; echo $$ > /sys/fs/cgroup/memory/test/$i/cgroup.procs; echo $$ > /sys/fs/cgroup/perf_event/test/cgroup.procs; mkdir -p $DIR/$i; done } do_mount() { for i in `seq $1 $2`; do mount -t tmpfs $i $DIR/$i; done } do_touch() { for i in `seq $1 $2`; do echo $$ > /sys/fs/cgroup/memory/test/$i/cgroup.procs; echo $$ > /sys/fs/cgroup/perf_event/test/cgroup.procs; dd if=/dev/zero of=$DIR/$i/file$i bs=1M count=1 & done } case "$1" in touch) do_touch $2 $3 ;; test) do_create 4000 do_mount 0 4000 do_touch 0 3000 ;; *) exit 1 ;; esac ``` Save the above script, then run test and touch commands. Then we can use the following perf command to view hotspots: perf top -U -F 999 1) Before applying this patchset: 32.31% [kernel] [k] down_read_trylock 19.40% [kernel] [k] pv_native_safe_halt 16.24% [kernel] [k] up_read 15.70% [kernel] [k] shrink_slab 4.69% [kernel] [k] _find_next_bit 2.62% [kernel] [k] shrink_node 1.78% [kernel] [k] shrink_lruvec 0.76% [kernel] [k] do_shrink_slab 2) After applying this patchset: 27.83% [kernel] [k] _find_next_bit 16.97% [kernel] [k] shrink_slab 15.82% [kernel] [k] pv_native_safe_halt 9.58% [kernel] [k] shrink_node 8.31% [kernel] [k] shrink_lruvec 5.64% [kernel] [k] do_shrink_slab 3.88% [kernel] [k] mem_cgroup_iter At the same time, we use the following perf command to capture IPC information: perf stat -e cycles,instructions -G test -a --repeat 5 -- sleep 10 1) Before applying this patchset: Performance counter stats for 'system wide' (5 runs): 454187219766 cycles test ( +- 1.84% ) 78896433101 instructions test # 0.17 insn per cycle ( +- 0.44% ) 10.0020430 +- 0.0000366 seconds time elapsed ( +- 0.00% ) 2) After applying this patchset: Performance counter stats for 'system wide' (5 runs): 841954709443 cycles test ( +- 15.80% ) (98.69%) 527258677936 instructions test # 0.63 insn per cycle ( +- 15.11% ) (98.68%) 10.01064 +- 0.00831 seconds time elapsed ( +- 0.08% ) We can see that IPC drops very seriously when calling down_read_trylock() at high frequency. After using SRCU, the IPC is at a normal level. This patch (of 8): To prepare for the subsequent lockless memcg slab shrink, add a map_nr_max field to struct shrinker_info to records its own real shrinker_nr_max. Link: https://lkml.kernel.org/r/20230313112819.38938-1-zhengqi.arch@bytedance.com Link: https://lkml.kernel.org/r/20230313112819.38938-2-zhengqi.arch@bytedance.com Signed-off-by: Qi Zheng Suggested-by: Kirill Tkhai Acked-by: Vlastimil Babka Acked-by: Kirill Tkhai Acked-by: Roman Gushchin Cc: Christian König Cc: David Hildenbrand Cc: Davidlohr Bueso Cc: Johannes Weiner Cc: Michal Hocko Cc: Muchun Song Cc: Paul E. McKenney Cc: Qi Zheng Cc: Shakeel Butt Cc: Sultan Alsawaf Cc: Tetsuo Handa Cc: Yang Shi Signed-off-by: Andrew Morton --- include/linux/memcontrol.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index b6eda2ab205d..aa69ea98e2d8 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -97,6 +97,7 @@ struct shrinker_info { struct rcu_head rcu; atomic_long_t *nr_deferred; unsigned long *map; + int map_nr_max; }; struct lruvec_stats_percpu { -- cgit v1.2.3 From 3c556d2425b04054e22045d4ef7d34f163b7a71a Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Wed, 15 Mar 2023 13:16:42 -0400 Subject: mm/thp: rename TRANSPARENT_HUGEPAGE_NEVER_DAX to _UNSUPPORTED TRANSPARENT_HUGEPAGE_NEVER_DAX has nothing to do with DAX. It's set when has_transparent_hugepage() returns false, checked in hugepage_vma_check() and will disable THP completely if false. Rename it to TRANSPARENT_HUGEPAGE_UNSUPPORTED to reflect its real purpose. [peterx@redhat.com: fix comment, per David] Link: https://lkml.kernel.org/r/ZBMzQW674oHQJV7F@x1n Link: https://lkml.kernel.org/r/20230315171642.1244625-1-peterx@redhat.com Signed-off-by: Peter Xu Acked-by: David Hildenbrand Cc: Aneesh Kumar K.V Cc: Yang Shi Signed-off-by: Andrew Morton --- include/linux/huge_mm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 70bd867eba94..9a3a3af2dd80 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -79,7 +79,7 @@ static inline vm_fault_t vmf_insert_pfn_pud(struct vm_fault *vmf, pfn_t pfn, } enum transparent_hugepage_flag { - TRANSPARENT_HUGEPAGE_NEVER_DAX, + TRANSPARENT_HUGEPAGE_UNSUPPORTED, TRANSPARENT_HUGEPAGE_FLAG, TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, -- cgit v1.2.3 From 75a2d4226b53710380d1017b3f4c88f937ddba78 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Sat, 25 Mar 2023 09:45:37 +0100 Subject: driver core: class: mark the struct class for sysfs callbacks as constant struct class should never be modified in a sysfs callback as there is nothing in the structure to modify, and frankly, the structure is almost never used in a sysfs callback, so mark it as constant to allow struct class to be moved to read-only memory. While we are touching all class sysfs callbacks also mark the attribute as constant as it can not be modified. The bonding code still uses this structure so it can not be removed from the function callbacks. Cc: "David S. Miller" Cc: "Rafael J. Wysocki" Cc: Bartosz Golaszewski Cc: Eric Dumazet Cc: Jakub Kicinski Cc: Jens Axboe Cc: Johannes Berg Cc: Linus Walleij Cc: Minchan Kim Cc: Miquel Raynal Cc: Namjae Jeon Cc: Paolo Abeni Cc: Russ Weight Cc: Sergey Senozhatsky Cc: Steve French Cc: Vignesh Raghavendra Cc: linux-cifs@vger.kernel.org Cc: linux-gpio@vger.kernel.org Cc: linux-mtd@lists.infradead.org Cc: linux-rdma@vger.kernel.org Cc: linux-s390@vger.kernel.org Cc: linuxppc-dev@lists.ozlabs.org Cc: netdev@vger.kernel.org Reviewed-by: Luis Chamberlain Link: https://lore.kernel.org/r/20230325084537.3622280-1-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- include/linux/device/class.h | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/device/class.h b/include/linux/device/class.h index 73436c578d37..b53728ca56fb 100644 --- a/include/linux/device/class.h +++ b/include/linux/device/class.h @@ -174,10 +174,10 @@ static inline struct device *class_find_device_by_acpi_dev(const struct class *c struct class_attribute { struct attribute attr; - ssize_t (*show)(struct class *class, struct class_attribute *attr, + ssize_t (*show)(const struct class *class, const struct class_attribute *attr, char *buf); - ssize_t (*store)(struct class *class, struct class_attribute *attr, - const char *buf, size_t count); + ssize_t (*store)(const struct class *class, const struct class_attribute *attr, + const char *buf, size_t count); }; #define CLASS_ATTR_RW(_name) \ @@ -217,7 +217,8 @@ struct class_attribute_string { struct class_attribute_string class_attr_##_name = \ _CLASS_ATTR_STRING(_name, _mode, _str) -ssize_t show_class_attr_string(struct class *class, struct class_attribute *attr, char *buf); +ssize_t show_class_attr_string(const struct class *class, const struct class_attribute *attr, + char *buf); struct class_interface { struct list_head node; -- cgit v1.2.3 From 130eac4170859fb368681e00d390f20f44bbf27b Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 28 Mar 2023 15:10:43 +0200 Subject: xhci: use pm_ptr() instead of #ifdef for CONFIG_PM conditionals A recent patch caused an unused-function warning in builds with CONFIG_PM disabled, after the function became marked 'static': drivers/usb/host/xhci-pci.c:91:13: error: 'xhci_msix_sync_irqs' defined but not used [-Werror=unused-function] 91 | static void xhci_msix_sync_irqs(struct xhci_hcd *xhci) | ^~~~~~~~~~~~~~~~~~~ This could be solved by adding another #ifdef, but as there is a trend towards removing CONFIG_PM checks in favor of helper macros, do the same conversion here and use pm_ptr() to get either a function pointer or NULL but avoid the warning. As the hidden functions reference some other symbols, make sure those are visible at compile time, at the minimal cost of a few extra bytes for 'struct usb_device'. Fixes: 9abe15d55dcc ("xhci: Move xhci MSI sync function to to xhci-pci") Signed-off-by: Arnd Bergmann Link: https://lore.kernel.org/r/20230328131114.1296430-1-arnd@kernel.org Signed-off-by: Greg Kroah-Hartman --- include/linux/usb.h | 3 +-- include/linux/usb/hcd.h | 2 -- 2 files changed, 1 insertion(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb.h b/include/linux/usb.h index 9642ee02d713..d510fabcafa2 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -704,13 +704,12 @@ struct usb_device { unsigned long active_duration; -#ifdef CONFIG_PM unsigned long connect_time; unsigned do_remote_wakeup:1; unsigned reset_resume:1; unsigned port_is_suspended:1; -#endif + struct wusb_dev *wusb_dev; int slot_id; struct usb2_lpm_parameters l1_params; diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h index b51c07111729..094c77eaf455 100644 --- a/include/linux/usb/hcd.h +++ b/include/linux/usb/hcd.h @@ -488,9 +488,7 @@ extern void usb_hcd_pci_shutdown(struct pci_dev *dev); extern int usb_hcd_amd_remote_wakeup_quirk(struct pci_dev *dev); -#ifdef CONFIG_PM extern const struct dev_pm_ops usb_hcd_pci_pm_ops; -#endif #endif /* CONFIG_USB_PCI */ /* pci-ish (pdev null is ok) buffer alloc/mapping support */ -- cgit v1.2.3 From 77f7eb9f3416aace703971156133926e44e2195b Mon Sep 17 00:00:00 2001 From: Patrisious Haddad Date: Thu, 23 Mar 2023 12:13:51 +0200 Subject: net/mlx5: Introduce other vport query for Q-counters These new fields in QUERY_Q_COUNTER command allow us to access another vport counters during the query command, which is specially useful to query representor vports. In addition also add the required caps to check if this capability is actually supported. Signed-off-by: Patrisious Haddad Reviewed-by: Michael Guralnik Link: https://lore.kernel.org/r/75c73a4a0e60f18c37b35a4a11ca2e2415e4a6f3.1679566038.git.leon@kernel.org Signed-off-by: Leon Romanovsky --- include/linux/mlx5/mlx5_ifc.h | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 62039b147432..e4306cd87cd7 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1729,7 +1729,9 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 log_max_transport_domain[0x5]; u8 reserved_at_328[0x3]; u8 log_max_pd[0x5]; - u8 reserved_at_330[0xb]; + u8 reserved_at_330[0x9]; + u8 q_counter_aggregation[0x1]; + u8 q_counter_other_vport[0x1]; u8 log_max_xrcd[0x5]; u8 nic_receive_steering_discard[0x1]; @@ -5603,10 +5605,15 @@ struct mlx5_ifc_query_q_counter_in_bits { u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_at_40[0x80]; + u8 other_vport[0x1]; + u8 reserved_at_41[0xf]; + u8 vport_number[0x10]; + + u8 reserved_at_60[0x60]; u8 clear[0x1]; - u8 reserved_at_c1[0x1f]; + u8 aggregate[0x1]; + u8 reserved_at_c2[0x1e]; u8 reserved_at_e0[0x18]; u8 counter_set_id[0x8]; -- cgit v1.2.3 From 634f1a7110b439c65fd8a809171c1d2d28bcea6f Mon Sep 17 00:00:00 2001 From: Bobby Eshleman Date: Mon, 27 Mar 2023 19:11:51 +0000 Subject: vsock: support sockmap This patch adds sockmap support for vsock sockets. It is intended to be usable by all transports, but only the virtio and loopback transports are implemented. SOCK_STREAM, SOCK_DGRAM, and SOCK_SEQPACKET are all supported. Signed-off-by: Bobby Eshleman Acked-by: Michael S. Tsirkin Reviewed-by: Stefano Garzarella Signed-off-by: David S. Miller --- include/linux/virtio_vsock.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h index 3f9c16611306..c58453699ee9 100644 --- a/include/linux/virtio_vsock.h +++ b/include/linux/virtio_vsock.h @@ -245,4 +245,5 @@ u32 virtio_transport_get_credit(struct virtio_vsock_sock *vvs, u32 wanted); void virtio_transport_put_credit(struct virtio_vsock_sock *vvs, u32 credit); void virtio_transport_deliver_tap_pkt(struct sk_buff *skb); int virtio_transport_purge_skbs(void *vsk, struct sk_buff_head *list); +int virtio_transport_read_skb(struct vsock_sock *vsk, skb_read_actor_t read_actor); #endif /* _LINUX_VIRTIO_VSOCK_H */ -- cgit v1.2.3 From b93c2a68f3d9dc98ec30dcb342ae47c1c8d09d18 Mon Sep 17 00:00:00 2001 From: Elson Roy Serrao Date: Fri, 24 Mar 2023 14:47:57 -0700 Subject: usb: gadget: Properly configure the device for remote wakeup The wakeup bit in the bmAttributes field indicates whether the device is configured for remote wakeup. But this field should be allowed to set only if the UDC supports such wakeup mechanism. So configure this field based on UDC capability. Also inform the UDC whether the device is configured for remote wakeup by implementing a gadget op. Reviewed-by: Thinh Nguyen Signed-off-by: Elson Roy Serrao Link: https://lore.kernel.org/r/1679694482-16430-2-git-send-email-quic_eserrao@quicinc.com Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/composite.h | 2 ++ include/linux/usb/gadget.h | 8 ++++++++ 2 files changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/composite.h b/include/linux/usb/composite.h index 608dc962748b..d949e91ceb48 100644 --- a/include/linux/usb/composite.h +++ b/include/linux/usb/composite.h @@ -413,6 +413,8 @@ extern int composite_dev_prepare(struct usb_composite_driver *composite, extern int composite_os_desc_req_prepare(struct usb_composite_dev *cdev, struct usb_ep *ep0); void composite_dev_cleanup(struct usb_composite_dev *cdev); +void check_remote_wakeup_config(struct usb_gadget *g, + struct usb_configuration *c); static inline struct usb_composite_driver *to_cdriver( struct usb_gadget_driver *gdrv) diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h index 00750f7020f3..1d796128030b 100644 --- a/include/linux/usb/gadget.h +++ b/include/linux/usb/gadget.h @@ -310,6 +310,7 @@ struct usb_udc; struct usb_gadget_ops { int (*get_frame)(struct usb_gadget *); int (*wakeup)(struct usb_gadget *); + int (*set_remote_wakeup)(struct usb_gadget *, int set); int (*set_selfpowered) (struct usb_gadget *, int is_selfpowered); int (*vbus_session) (struct usb_gadget *, int is_active); int (*vbus_draw) (struct usb_gadget *, unsigned mA); @@ -384,6 +385,8 @@ struct usb_gadget_ops { * @connected: True if gadget is connected. * @lpm_capable: If the gadget max_speed is FULL or HIGH, this flag * indicates that it supports LPM as per the LPM ECN & errata. + * @wakeup_capable: True if gadget is capable of sending remote wakeup. + * @wakeup_armed: True if gadget is armed by the host for remote wakeup. * @irq: the interrupt number for device controller. * @id_number: a unique ID number for ensuring that gadget names are distinct * @@ -445,6 +448,8 @@ struct usb_gadget { unsigned deactivated:1; unsigned connected:1; unsigned lpm_capable:1; + unsigned wakeup_capable:1; + unsigned wakeup_armed:1; int irq; int id_number; }; @@ -601,6 +606,7 @@ static inline int gadget_is_otg(struct usb_gadget *g) #if IS_ENABLED(CONFIG_USB_GADGET) int usb_gadget_frame_number(struct usb_gadget *gadget); int usb_gadget_wakeup(struct usb_gadget *gadget); +int usb_gadget_set_remote_wakeup(struct usb_gadget *gadget, int set); int usb_gadget_set_selfpowered(struct usb_gadget *gadget); int usb_gadget_clear_selfpowered(struct usb_gadget *gadget); int usb_gadget_vbus_connect(struct usb_gadget *gadget); @@ -616,6 +622,8 @@ static inline int usb_gadget_frame_number(struct usb_gadget *gadget) { return 0; } static inline int usb_gadget_wakeup(struct usb_gadget *gadget) { return 0; } +static inline int usb_gadget_set_remote_wakeup(struct usb_gadget *gadget, int set) +{ return 0; } static inline int usb_gadget_set_selfpowered(struct usb_gadget *gadget) { return 0; } static inline int usb_gadget_clear_selfpowered(struct usb_gadget *gadget) -- cgit v1.2.3 From f0db885fb05d35befa81896db6b19eb3ee9ccdfe Mon Sep 17 00:00:00 2001 From: Elson Roy Serrao Date: Fri, 24 Mar 2023 14:47:59 -0700 Subject: usb: gadget: Add function wakeup support USB3.2 spec section 9.2.5.4 quotes that a function may signal that it wants to exit from Function Suspend by sending a Function Wake Notification to the host if it is enabled for function remote wakeup. Add an api in composite layer that can be used by the function drivers to support this feature. Also expose a gadget op so that composite layer can trigger a wakeup request to the UDC driver. Reviewed-by: Thinh Nguyen Signed-off-by: Elson Roy Serrao Link: https://lore.kernel.org/r/1679694482-16430-4-git-send-email-quic_eserrao@quicinc.com Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/composite.h | 6 ++++++ include/linux/usb/gadget.h | 1 + 2 files changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/composite.h b/include/linux/usb/composite.h index d949e91ceb48..a2448e98854f 100644 --- a/include/linux/usb/composite.h +++ b/include/linux/usb/composite.h @@ -150,6 +150,9 @@ struct usb_os_desc_table { * GetStatus() request when the recipient is Interface. * @func_suspend: callback to be called when * SetFeature(FUNCTION_SUSPEND) is reseived + * @func_suspended: Indicates whether the function is in function suspend state. + * @func_wakeup_armed: Indicates whether the function is armed by the host for + * wakeup signaling. * * A single USB function uses one or more interfaces, and should in most * cases support operation at both full and high speeds. Each function is @@ -220,6 +223,8 @@ struct usb_function { int (*get_status)(struct usb_function *); int (*func_suspend)(struct usb_function *, u8 suspend_opt); + bool func_suspended; + bool func_wakeup_armed; /* private: */ /* internals */ struct list_head list; @@ -241,6 +246,7 @@ int config_ep_by_speed_and_alt(struct usb_gadget *g, struct usb_function *f, int config_ep_by_speed(struct usb_gadget *g, struct usb_function *f, struct usb_ep *_ep); +int usb_func_wakeup(struct usb_function *func); #define MAX_CONFIG_INTERFACES 16 /* arbitrary; max 255 */ diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h index 1d796128030b..75bda0783395 100644 --- a/include/linux/usb/gadget.h +++ b/include/linux/usb/gadget.h @@ -310,6 +310,7 @@ struct usb_udc; struct usb_gadget_ops { int (*get_frame)(struct usb_gadget *); int (*wakeup)(struct usb_gadget *); + int (*func_wakeup)(struct usb_gadget *gadget, int intf_id); int (*set_remote_wakeup)(struct usb_gadget *, int set); int (*set_selfpowered) (struct usb_gadget *, int is_selfpowered); int (*vbus_session) (struct usb_gadget *, int is_active); -- cgit v1.2.3 From c4ba69f00c18524eb89990e9afda9d2a9b54de2f Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Tue, 28 Feb 2023 10:59:54 +0100 Subject: mm, page_flags: remove PG_slob_free With SLOB removed we no longer need the PG_slob_free alias for PG_private. Also update tools/mm/page-types. Signed-off-by: Vlastimil Babka Acked-by: Hyeonggon Yoo <42.hyeyoo@gmail.com> Acked-by: Lorenzo Stoakes Acked-by: Mike Rapoport (IBM) --- include/linux/page-flags.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index a7e3a3405520..2bdc41cb0594 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -174,9 +174,6 @@ enum pageflags { /* Remapped by swiotlb-xen. */ PG_xen_remapped = PG_owner_priv_1, - /* SLOB */ - PG_slob_free = PG_private, - #ifdef CONFIG_MEMORY_FAILURE /* * Compound pages. Stored in first tail page's flags. @@ -483,7 +480,6 @@ PAGEFLAG(Active, active, PF_HEAD) __CLEARPAGEFLAG(Active, active, PF_HEAD) PAGEFLAG(Workingset, workingset, PF_HEAD) TESTCLEARFLAG(Workingset, workingset, PF_HEAD) __PAGEFLAG(Slab, slab, PF_NO_TAIL) -__PAGEFLAG(SlobFree, slob_free, PF_NO_TAIL) PAGEFLAG(Checked, checked, PF_NO_COMPOUND) /* Used by some filesystems */ /* Xen */ -- cgit v1.2.3 From de4d6089b9271ed172e92148a04f31578b375525 Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Tue, 28 Feb 2023 15:34:17 +0100 Subject: mm/slab: remove CONFIG_SLOB code from slab common code CONFIG_SLOB has been removed from Kconfig. Remove code and #ifdef's specific to SLOB in the slab headers and common code. Signed-off-by: Vlastimil Babka Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com> Acked-by: Lorenzo Stoakes Acked-by: Mike Rapoport (IBM) --- include/linux/slab.h | 39 --------------------------------------- 1 file changed, 39 deletions(-) (limited to 'include/linux') diff --git a/include/linux/slab.h b/include/linux/slab.h index 45af70315a94..7f645a4c1298 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -298,19 +298,6 @@ static inline unsigned int arch_slab_minalign(void) #endif #endif -#ifdef CONFIG_SLOB -/* - * SLOB passes all requests larger than one page to the page allocator. - * No kmalloc array is necessary since objects of different sizes can - * be allocated from the same page. - */ -#define KMALLOC_SHIFT_HIGH PAGE_SHIFT -#define KMALLOC_SHIFT_MAX (MAX_ORDER + PAGE_SHIFT - 1) -#ifndef KMALLOC_SHIFT_LOW -#define KMALLOC_SHIFT_LOW 3 -#endif -#endif - /* Maximum allocatable size */ #define KMALLOC_MAX_SIZE (1UL << KMALLOC_SHIFT_MAX) /* Maximum size for which we actually use a slab cache */ @@ -366,7 +353,6 @@ enum kmalloc_cache_type { NR_KMALLOC_TYPES }; -#ifndef CONFIG_SLOB extern struct kmem_cache * kmalloc_caches[NR_KMALLOC_TYPES][KMALLOC_SHIFT_HIGH + 1]; @@ -458,7 +444,6 @@ static __always_inline unsigned int __kmalloc_index(size_t size, } static_assert(PAGE_SHIFT <= 20); #define kmalloc_index(s) __kmalloc_index(s, true) -#endif /* !CONFIG_SLOB */ void *__kmalloc(size_t size, gfp_t flags) __assume_kmalloc_alignment __alloc_size(1); @@ -487,10 +472,6 @@ void kmem_cache_free(struct kmem_cache *s, void *objp); void kmem_cache_free_bulk(struct kmem_cache *s, size_t size, void **p); int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size, void **p); -/* - * Caller must not use kfree_bulk() on memory not originally allocated - * by kmalloc(), because the SLOB allocator cannot handle this. - */ static __always_inline void kfree_bulk(size_t size, void **p) { kmem_cache_free_bulk(NULL, size, p); @@ -567,7 +548,6 @@ void *kmalloc_large_node(size_t size, gfp_t flags, int node) __assume_page_align * Try really hard to succeed the allocation but fail * eventually. */ -#ifndef CONFIG_SLOB static __always_inline __alloc_size(1) void *kmalloc(size_t size, gfp_t flags) { if (__builtin_constant_p(size) && size) { @@ -583,17 +563,7 @@ static __always_inline __alloc_size(1) void *kmalloc(size_t size, gfp_t flags) } return __kmalloc(size, flags); } -#else -static __always_inline __alloc_size(1) void *kmalloc(size_t size, gfp_t flags) -{ - if (__builtin_constant_p(size) && size > KMALLOC_MAX_CACHE_SIZE) - return kmalloc_large(size, flags); - - return __kmalloc(size, flags); -} -#endif -#ifndef CONFIG_SLOB static __always_inline __alloc_size(1) void *kmalloc_node(size_t size, gfp_t flags, int node) { if (__builtin_constant_p(size) && size) { @@ -609,15 +579,6 @@ static __always_inline __alloc_size(1) void *kmalloc_node(size_t size, gfp_t fla } return __kmalloc_node(size, flags, node); } -#else -static __always_inline __alloc_size(1) void *kmalloc_node(size_t size, gfp_t flags, int node) -{ - if (__builtin_constant_p(size) && size > KMALLOC_MAX_CACHE_SIZE) - return kmalloc_large_node(size, flags, node); - - return __kmalloc_node(size, flags, node); -} -#endif /** * kmalloc_array - allocate memory for an array. -- cgit v1.2.3 From ae65a5211d90e54ae604012ce9cf234c48780929 Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Thu, 2 Mar 2023 16:01:00 +0100 Subject: mm/slab: document kfree() as allowed for kmem_cache_alloc() objects This will make it easier to free objects in situations when they can come from either kmalloc() or kmem_cache_alloc(), and also allow kfree_rcu() for freeing objects from kmem_cache_alloc(). For the SLAB and SLUB allocators this was always possible so with SLOB gone, we can document it as supported. Signed-off-by: Vlastimil Babka Reviewed-by: Mike Rapoport (IBM) Cc: Jonathan Corbet Cc: "Paul E. McKenney" Cc: Frederic Weisbecker Cc: Neeraj Upadhyay Cc: Josh Triplett Cc: Steven Rostedt Cc: Mathieu Desnoyers Cc: Lai Jiangshan Cc: Joel Fernandes --- include/linux/rcupdate.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 094321c17e48..dcd2cf1e8326 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -976,8 +976,10 @@ static inline notrace void rcu_read_unlock_sched_notrace(void) * either fall back to use of call_rcu() or rearrange the structure to * position the rcu_head structure into the first 4096 bytes. * - * Note that the allowable offset might decrease in the future, for example, - * to allow something like kmem_cache_free_rcu(). + * The object to be freed can be allocated either by kmalloc() or + * kmem_cache_alloc(). + * + * Note that the allowable offset might decrease in the future. * * The BUILD_BUG_ON check must not involve any function calls, hence the * checks are done in macros here. -- cgit v1.2.3 From 2b76ffe81e32afd6d318dc4547e2ba8c46207b77 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Tue, 28 Mar 2023 19:15:29 -0700 Subject: linux/vt_buffer.h: allow either builtin or modular for macros Fix build errors on ARCH=alpha when CONFIG_MDA_CONSOLE=m. This allows the ARCH macros to be the only ones defined. In file included from ../drivers/video/console/mdacon.c:37: ../arch/alpha/include/asm/vga.h:17:40: error: expected identifier or '(' before 'volatile' 17 | static inline void scr_writew(u16 val, volatile u16 *addr) | ^~~~~~~~ ../include/linux/vt_buffer.h:24:34: note: in definition of macro 'scr_writew' 24 | #define scr_writew(val, addr) (*(addr) = (val)) | ^~~~ ../include/linux/vt_buffer.h:24:40: error: expected ')' before '=' token 24 | #define scr_writew(val, addr) (*(addr) = (val)) | ^ ../arch/alpha/include/asm/vga.h:17:20: note: in expansion of macro 'scr_writew' 17 | static inline void scr_writew(u16 val, volatile u16 *addr) | ^~~~~~~~~~ ../arch/alpha/include/asm/vga.h:25:29: error: expected identifier or '(' before 'volatile' 25 | static inline u16 scr_readw(volatile const u16 *addr) | ^~~~~~~~ Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Randy Dunlap Cc: Greg Kroah-Hartman Cc: Jiri Slaby Cc: dri-devel@lists.freedesktop.org Cc: linux-fbdev@vger.kernel.org Link: https://lore.kernel.org/r/20230329021529.16188-1-rdunlap@infradead.org Signed-off-by: Greg Kroah-Hartman --- include/linux/vt_buffer.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/vt_buffer.h b/include/linux/vt_buffer.h index 848db1b1569f..919d999a8c1d 100644 --- a/include/linux/vt_buffer.h +++ b/include/linux/vt_buffer.h @@ -16,7 +16,7 @@ #include -#if defined(CONFIG_VGA_CONSOLE) || defined(CONFIG_MDA_CONSOLE) +#if IS_ENABLED(CONFIG_VGA_CONSOLE) || IS_ENABLED(CONFIG_MDA_CONSOLE) #include #endif -- cgit v1.2.3 From 2959ab247061e67485d83b6af8feb3761ec08cb9 Mon Sep 17 00:00:00 2001 From: Nipun Gupta Date: Mon, 13 Mar 2023 18:56:30 +0530 Subject: cdx: add the cdx bus driver Introduce AMD CDX bus, which provides a mechanism for scanning and probing CDX devices. These devices are memory mapped on system bus for Application Processors(APUs). CDX devices can be changed dynamically in the Fabric and CDX bus interacts with CDX controller to rescan the bus and rediscover the devices. Signed-off-by: Nipun Gupta Reviewed-by: Pieter Jansen van Vuuren Tested-by: Nikhil Agarwal Link: https://lore.kernel.org/r/20230313132636.31850-2-nipun.gupta@amd.com Signed-off-by: Greg Kroah-Hartman --- include/linux/cdx/cdx_bus.h | 147 ++++++++++++++++++++++++++++++++++++++++ include/linux/mod_devicetable.h | 15 ++++ 2 files changed, 162 insertions(+) create mode 100644 include/linux/cdx/cdx_bus.h (limited to 'include/linux') diff --git a/include/linux/cdx/cdx_bus.h b/include/linux/cdx/cdx_bus.h new file mode 100644 index 000000000000..d134e0104724 --- /dev/null +++ b/include/linux/cdx/cdx_bus.h @@ -0,0 +1,147 @@ +/* SPDX-License-Identifier: GPL-2.0 + * + * CDX bus public interface + * + * Copyright (C) 2022-2023, Advanced Micro Devices, Inc. + * + */ + +#ifndef _CDX_BUS_H_ +#define _CDX_BUS_H_ + +#include +#include +#include + +#define MAX_CDX_DEV_RESOURCES 4 +#define CDX_ANY_ID (0xFFFF) +#define CDX_CONTROLLER_ID_SHIFT 4 +#define CDX_BUS_NUM_MASK 0xF + +/* Forward declaration for CDX controller */ +struct cdx_controller; + +typedef int (*cdx_scan_cb)(struct cdx_controller *cdx); + +/** + * CDX_DEVICE_DRIVER_OVERRIDE - macro used to describe a CDX device with + * override_only flags. + * @vend: the 16 bit CDX Vendor ID + * @dev: the 16 bit CDX Device ID + * @driver_override: the 32 bit CDX Device override_only + * + * This macro is used to create a struct cdx_device_id that matches only a + * driver_override device. + */ +#define CDX_DEVICE_DRIVER_OVERRIDE(vend, dev, driver_override) \ + .vendor = (vend), .device = (dev), .override_only = (driver_override) + +/** + * struct cdx_ops - Callbacks supported by CDX controller. + * @scan: scan the devices on the controller + */ +struct cdx_ops { + cdx_scan_cb scan; +}; + +/** + * struct cdx_controller: CDX controller object + * @dev: Linux device associated with the CDX controller. + * @priv: private data + * @id: Controller ID + * @ops: CDX controller ops + */ +struct cdx_controller { + struct device *dev; + void *priv; + u32 id; + struct cdx_ops *ops; +}; + +/** + * struct cdx_device - CDX device object + * @dev: Linux driver model device object + * @cdx: CDX controller associated with the device + * @vendor: Vendor ID for CDX device + * @device: Device ID for CDX device + * @bus_num: Bus number for this CDX device + * @dev_num: Device number for this device + * @res: array of MMIO region entries + * @res_attr: resource binary attribute + * @res_count: number of valid MMIO regions + * @dma_mask: Default DMA mask + * @flags: CDX device flags + * @req_id: Requestor ID associated with CDX device + * @driver_override: driver name to force a match; do not set directly, + * because core frees it; use driver_set_override() to + * set or clear it. + */ +struct cdx_device { + struct device dev; + struct cdx_controller *cdx; + u16 vendor; + u16 device; + u8 bus_num; + u8 dev_num; + struct resource res[MAX_CDX_DEV_RESOURCES]; + u8 res_count; + u64 dma_mask; + u16 flags; + u32 req_id; + const char *driver_override; +}; + +#define to_cdx_device(_dev) \ + container_of(_dev, struct cdx_device, dev) + +/** + * struct cdx_driver - CDX device driver + * @driver: Generic device driver + * @match_id_table: table of supported device matching Ids + * @probe: Function called when a device is added + * @remove: Function called when a device is removed + * @shutdown: Function called at shutdown time to quiesce the device + * @driver_managed_dma: Device driver doesn't use kernel DMA API for DMA. + * For most device drivers, no need to care about this flag + * as long as all DMAs are handled through the kernel DMA API. + * For some special ones, for example VFIO drivers, they know + * how to manage the DMA themselves and set this flag so that + * the IOMMU layer will allow them to setup and manage their + * own I/O address space. + */ +struct cdx_driver { + struct device_driver driver; + const struct cdx_device_id *match_id_table; + int (*probe)(struct cdx_device *dev); + int (*remove)(struct cdx_device *dev); + void (*shutdown)(struct cdx_device *dev); + bool driver_managed_dma; +}; + +#define to_cdx_driver(_drv) \ + container_of(_drv, struct cdx_driver, driver) + +/* Macro to avoid include chaining to get THIS_MODULE */ +#define cdx_driver_register(drv) \ + __cdx_driver_register(drv, THIS_MODULE) + +/** + * __cdx_driver_register - registers a CDX device driver + * @cdx_driver: CDX driver to register + * @owner: module owner + * + * Return: -errno on failure, 0 on success. + */ +int __must_check __cdx_driver_register(struct cdx_driver *cdx_driver, + struct module *owner); + +/** + * cdx_driver_unregister - unregisters a device driver from the + * CDX bus. + * @cdx_driver: CDX driver to register + */ +void cdx_driver_unregister(struct cdx_driver *cdx_driver); + +extern struct bus_type cdx_bus_type; + +#endif /* _CDX_BUS_H_ */ diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index 35203ca3fc37..ccaaeda792c0 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -912,4 +912,19 @@ struct ishtp_device_id { kernel_ulong_t driver_data; }; +/** + * struct cdx_device_id - CDX device identifier + * @vendor: Vendor ID + * @device: Device ID + * @override_only: Match only when dev->driver_override is this driver. + * + * Type of entries in the "device Id" table for CDX devices supported by + * a CDX device driver. + */ +struct cdx_device_id { + __u16 vendor; + __u16 device; + __u32 override_only; +}; + #endif /* LINUX_MOD_DEVICETABLE_H */ -- cgit v1.2.3 From 48a6c7bced2a781c911497f073347bec5ab4d7a5 Mon Sep 17 00:00:00 2001 From: Nipun Gupta Date: Mon, 13 Mar 2023 18:56:36 +0530 Subject: cdx: add device attributes Create sysfs entry for CDX devices. Sysfs entries provided in each of the CDX device detected by the CDX controller - vendor id - device id - remove - reset of the device. - driver override Signed-off-by: Puneet Gupta Signed-off-by: Nipun Gupta Signed-off-by: Tarak Reddy Reviewed-by: Pieter Jansen van Vuuren Tested-by: Nikhil Agarwal Link: https://lore.kernel.org/r/20230313132636.31850-8-nipun.gupta@amd.com Signed-off-by: Greg Kroah-Hartman --- include/linux/cdx/cdx_bus.h | 27 +++++++++++++++++++++++++++ 1 file changed, 27 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cdx/cdx_bus.h b/include/linux/cdx/cdx_bus.h index d134e0104724..35ef41d8a61a 100644 --- a/include/linux/cdx/cdx_bus.h +++ b/include/linux/cdx/cdx_bus.h @@ -21,8 +21,20 @@ /* Forward declaration for CDX controller */ struct cdx_controller; +enum { + CDX_DEV_RESET_CONF, +}; + +struct cdx_device_config { + u8 type; +}; + typedef int (*cdx_scan_cb)(struct cdx_controller *cdx); +typedef int (*cdx_dev_configure_cb)(struct cdx_controller *cdx, + u8 bus_num, u8 dev_num, + struct cdx_device_config *dev_config); + /** * CDX_DEVICE_DRIVER_OVERRIDE - macro used to describe a CDX device with * override_only flags. @@ -39,9 +51,12 @@ typedef int (*cdx_scan_cb)(struct cdx_controller *cdx); /** * struct cdx_ops - Callbacks supported by CDX controller. * @scan: scan the devices on the controller + * @dev_configure: configuration like reset, master_enable, + * msi_config etc for a CDX device */ struct cdx_ops { cdx_scan_cb scan; + cdx_dev_configure_cb dev_configure; }; /** @@ -101,6 +116,8 @@ struct cdx_device { * @probe: Function called when a device is added * @remove: Function called when a device is removed * @shutdown: Function called at shutdown time to quiesce the device + * @reset_prepare: Function called before is reset to notify driver + * @reset_done: Function called after reset is complete to notify driver * @driver_managed_dma: Device driver doesn't use kernel DMA API for DMA. * For most device drivers, no need to care about this flag * as long as all DMAs are handled through the kernel DMA API. @@ -115,6 +132,8 @@ struct cdx_driver { int (*probe)(struct cdx_device *dev); int (*remove)(struct cdx_device *dev); void (*shutdown)(struct cdx_device *dev); + void (*reset_prepare)(struct cdx_device *dev); + void (*reset_done)(struct cdx_device *dev); bool driver_managed_dma; }; @@ -144,4 +163,12 @@ void cdx_driver_unregister(struct cdx_driver *cdx_driver); extern struct bus_type cdx_bus_type; +/** + * cdx_dev_reset - Reset CDX device + * @dev: device pointer + * + * Return: 0 for success, -errno on failure + */ +int cdx_dev_reset(struct device *dev); + #endif /* _CDX_BUS_H_ */ -- cgit v1.2.3 From 74df43b3f626a3594a4de50556048852bf2753f7 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Tue, 28 Mar 2023 17:41:04 +0200 Subject: mtd: spi-nor: Enhance locking to support reads while writes On devices featuring several banks, the Read While Write (RWW) feature is here to improve the overall performance when performing parallel reads and writes at different locations (different banks). The following constraints have to be taken into account: 1#: A single operation can be performed in a given bank. 2#: Only a single program or erase operation can happen on the entire chip (common hardware limitation to limit costs) 3#: Reads must remain serialized even though reads crossing bank boundaries are allowed. 4#: The I/O bus is unique and thus is the most constrained resource, all spi-nor operations requiring access to the spi bus (through the spi controller) must be serialized until the bus exchanges are over. So we must ensure a single operation can be "sent" at a time. 5#: Any other operation that would not be either a read or a write or an erase is considered requiring access to the full chip and cannot be parallelized, we then need to ensure the full chip is in the idle state when this occurs. All these constraints can easily be managed with a proper locking model: 1#: Is enforced by a bitfield of the in-use banks, so that only a single operation can happen in a specific bank at any time. 2#: Is handled by the ongoing_pe boolean which is set before any write or erase, and is released only at the very end of the operation. This way, no other destructive operation on the chip can start during this time frame. 3#: An ongoing_rd boolean allows to track the ongoing reads, so that only one can be performed at a time. 4#: An ongoing_io boolean is introduced in order to capture and serialize bus accessed. This is the one being released "sooner" than before, because we only need to protect the chip against other SPI accesses during the I/O phase, which for the destructive operations is the beginning of the operation (when we send the command cycles and possibly the data), while the second part of the operation (the erase delay or the programmation delay) is when we can do something else in another bank. 5#: Is handled by the three booleans presented above, if any of them is set, the chip is not yet ready for the operation and must wait. All these internal variables are protected by the existing lock, so that changes in this structure are atomic. The serialization is handled with a wait queue. Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/r/20230328154105.448540-8-miquel.raynal@bootlin.com Signed-off-by: Tudor Ambarus --- include/linux/mtd/spi-nor.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h index a3f8cdca90c8..82547b4b3708 100644 --- a/include/linux/mtd/spi-nor.h +++ b/include/linux/mtd/spi-nor.h @@ -343,6 +343,12 @@ struct spi_nor_flash_parameter; * struct spi_nor - Structure for defining the SPI NOR layer * @mtd: an mtd_info structure * @lock: the lock for the read/write/erase/lock/unlock operations + * @rww: Read-While-Write (RWW) sync lock + * @rww.wait: wait queue for the RWW sync + * @rww.ongoing_io: the bus is busy + * @rww.ongoing_rd: a read is ongoing on the chip + * @rww.ongoing_pe: a program/erase is ongoing on the chip + * @rww.used_banks: bitmap of the banks in use * @dev: pointer to an SPI device or an SPI NOR controller device * @spimem: pointer to the SPI memory device * @bouncebuf: bounce buffer used when the buffer passed by the MTD @@ -376,6 +382,13 @@ struct spi_nor_flash_parameter; struct spi_nor { struct mtd_info mtd; struct mutex lock; + struct spi_nor_rww { + wait_queue_head_t wait; + bool ongoing_io; + bool ongoing_rd; + bool ongoing_pe; + unsigned int used_banks; + } rww; struct device *dev; struct spi_mem *spimem; u8 *bouncebuf; -- cgit v1.2.3 From e5a26a4048eeb9558e5c84f340a989c78db4adf4 Mon Sep 17 00:00:00 2001 From: Beau Belgrave Date: Tue, 28 Mar 2023 16:52:08 -0700 Subject: tracing/user_events: Split header into uapi and kernel The UAPI parts need to be split out from the kernel parts of user_events now that other parts of the kernel will reference it. Do so by moving the existing include/linux/user_events.h into include/uapi/linux/user_events.h. Link: https://lkml.kernel.org/r/20230328235219.203-2-beaub@linux.microsoft.com Signed-off-by: Beau Belgrave Signed-off-by: Steven Rostedt (Google) --- include/linux/user_events.h | 52 ++++++--------------------------------------- 1 file changed, 6 insertions(+), 46 deletions(-) (limited to 'include/linux') diff --git a/include/linux/user_events.h b/include/linux/user_events.h index 592a3fbed98e..13689589d36e 100644 --- a/include/linux/user_events.h +++ b/include/linux/user_events.h @@ -1,54 +1,14 @@ -/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* SPDX-License-Identifier: GPL-2.0-only */ /* - * Copyright (c) 2021, Microsoft Corporation. + * Copyright (c) 2022, Microsoft Corporation. * * Authors: * Beau Belgrave */ -#ifndef _UAPI_LINUX_USER_EVENTS_H -#define _UAPI_LINUX_USER_EVENTS_H -#include -#include +#ifndef _LINUX_USER_EVENTS_H +#define _LINUX_USER_EVENTS_H -#ifdef __KERNEL__ -#include -#else -#include -#endif +#include -#define USER_EVENTS_SYSTEM "user_events" -#define USER_EVENTS_PREFIX "u:" - -/* Create dynamic location entry within a 32-bit value */ -#define DYN_LOC(offset, size) ((size) << 16 | (offset)) - -/* - * Describes an event registration and stores the results of the registration. - * This structure is passed to the DIAG_IOCSREG ioctl, callers at a minimum - * must set the size and name_args before invocation. - */ -struct user_reg { - - /* Input: Size of the user_reg structure being used */ - __u32 size; - - /* Input: Pointer to string with event name, description and flags */ - __u64 name_args; - - /* Output: Bitwise index of the event within the status page */ - __u32 status_bit; - - /* Output: Index of the event to use when writing data */ - __u32 write_index; -} __attribute__((__packed__)); - -#define DIAG_IOC_MAGIC '*' - -/* Requests to register a user_event */ -#define DIAG_IOCSREG _IOWR(DIAG_IOC_MAGIC, 0, struct user_reg*) - -/* Requests to delete a user_event */ -#define DIAG_IOCSDEL _IOW(DIAG_IOC_MAGIC, 1, char*) - -#endif /* _UAPI_LINUX_USER_EVENTS_H */ +#endif /* _LINUX_USER_EVENTS_H */ -- cgit v1.2.3 From fd593511cdfc0b0e38af2eb21c99f5154a1d7acf Mon Sep 17 00:00:00 2001 From: Beau Belgrave Date: Tue, 28 Mar 2023 16:52:09 -0700 Subject: tracing/user_events: Track fork/exec/exit for mm lifetime During tracefs discussions it was decided instead of requiring a mapping within a user-process to track the lifetime of memory descriptors we should hook the appropriate calls. Do this by adding the minimal stubs required for task fork, exec, and exit. Currently this is just a NOP. Future patches will implement these calls fully. Link: https://lkml.kernel.org/r/20230328235219.203-3-beaub@linux.microsoft.com Suggested-by: Mathieu Desnoyers Signed-off-by: Beau Belgrave Signed-off-by: Steven Rostedt (Google) --- include/linux/sched.h | 5 +++++ include/linux/user_events.h | 18 ++++++++++++++++++ 2 files changed, 23 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 63d242164b1a..bf37846e90c2 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -69,6 +69,7 @@ struct sighand_struct; struct signal_struct; struct task_delay_info; struct task_group; +struct user_event_mm; /* * Task state bitmask. NOTE! These bits are also @@ -1528,6 +1529,10 @@ struct task_struct { union rv_task_monitor rv[RV_PER_TASK_MONITORS]; #endif +#ifdef CONFIG_USER_EVENTS + struct user_event_mm *user_event_mm; +#endif + /* * New fields for task_struct should be added above here, so that * they are included in the randomized portion of task_struct. diff --git a/include/linux/user_events.h b/include/linux/user_events.h index 13689589d36e..3d747c45d2fa 100644 --- a/include/linux/user_events.h +++ b/include/linux/user_events.h @@ -11,4 +11,22 @@ #include +#ifdef CONFIG_USER_EVENTS +struct user_event_mm { +}; +#endif + +static inline void user_events_fork(struct task_struct *t, + unsigned long clone_flags) +{ +} + +static inline void user_events_execve(struct task_struct *t) +{ +} + +static inline void user_events_exit(struct task_struct *t) +{ +} + #endif /* _LINUX_USER_EVENTS_H */ -- cgit v1.2.3 From 7235759084a4f8524a46bd2638885ff3b34ce279 Mon Sep 17 00:00:00 2001 From: Beau Belgrave Date: Tue, 28 Mar 2023 16:52:10 -0700 Subject: tracing/user_events: Use remote writes for event enablement As part of the discussions for user_events aligned with user space tracers, it was determined that user programs should register a aligned value to set or clear a bit when an event becomes enabled. Currently a shared page is being used that requires mmap(). Remove the shared page implementation and move to a user registered address implementation. In this new model during the event registration from user programs 3 new values are specified. The first is the address to update when the event is either enabled or disabled. The second is the bit to set/clear to reflect the event being enabled. The third is the size of the value at the specified address. This allows for a local 32/64-bit value in user programs to support both kernel and user tracers. As an example, setting bit 31 for kernel tracers when the event becomes enabled allows for user tracers to use the other bits for ref counts or other flags. The kernel side updates the bit atomically, user programs need to also update these values atomically. User provided addresses must be aligned on a natural boundary, this allows for single page checking and prevents odd behaviors such as a enable value straddling 2 pages instead of a single page. Currently page faults are only logged, future patches will handle these. Link: https://lkml.kernel.org/r/20230328235219.203-4-beaub@linux.microsoft.com Suggested-by: Mathieu Desnoyers Signed-off-by: Beau Belgrave Signed-off-by: Steven Rostedt (Google) --- include/linux/user_events.h | 53 ++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 52 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/user_events.h b/include/linux/user_events.h index 3d747c45d2fa..0120b3dd5b03 100644 --- a/include/linux/user_events.h +++ b/include/linux/user_events.h @@ -9,13 +9,63 @@ #ifndef _LINUX_USER_EVENTS_H #define _LINUX_USER_EVENTS_H +#include +#include +#include +#include #include #ifdef CONFIG_USER_EVENTS struct user_event_mm { + struct list_head link; + struct list_head enablers; + struct mm_struct *mm; + struct user_event_mm *next; + refcount_t refcnt; + refcount_t tasks; + struct rcu_work put_rwork; }; -#endif +extern void user_event_mm_dup(struct task_struct *t, + struct user_event_mm *old_mm); + +extern void user_event_mm_remove(struct task_struct *t); + +static inline void user_events_fork(struct task_struct *t, + unsigned long clone_flags) +{ + struct user_event_mm *old_mm; + + if (!t || !current->user_event_mm) + return; + + old_mm = current->user_event_mm; + + if (clone_flags & CLONE_VM) { + t->user_event_mm = old_mm; + refcount_inc(&old_mm->tasks); + return; + } + + user_event_mm_dup(t, old_mm); +} + +static inline void user_events_execve(struct task_struct *t) +{ + if (!t || !t->user_event_mm) + return; + + user_event_mm_remove(t); +} + +static inline void user_events_exit(struct task_struct *t) +{ + if (!t || !t->user_event_mm) + return; + + user_event_mm_remove(t); +} +#else static inline void user_events_fork(struct task_struct *t, unsigned long clone_flags) { @@ -28,5 +78,6 @@ static inline void user_events_execve(struct task_struct *t) static inline void user_events_exit(struct task_struct *t) { } +#endif /* CONFIG_USER_EVENTS */ #endif /* _LINUX_USER_EVENTS_H */ -- cgit v1.2.3 From a4c40c1349e32f9510707ed09e0961626980d8cb Mon Sep 17 00:00:00 2001 From: Beau Belgrave Date: Tue, 28 Mar 2023 16:52:19 -0700 Subject: tracing/user_events: Align structs with tabs for readability Add tabs to make struct members easier to read and unify the style of the code. Link: https://lkml.kernel.org/r/20230328235219.203-13-beaub@linux.microsoft.com Signed-off-by: Beau Belgrave Signed-off-by: Steven Rostedt (Google) --- include/linux/user_events.h | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/user_events.h b/include/linux/user_events.h index 0120b3dd5b03..2847f5a18a86 100644 --- a/include/linux/user_events.h +++ b/include/linux/user_events.h @@ -17,13 +17,13 @@ #ifdef CONFIG_USER_EVENTS struct user_event_mm { - struct list_head link; - struct list_head enablers; - struct mm_struct *mm; - struct user_event_mm *next; - refcount_t refcnt; - refcount_t tasks; - struct rcu_work put_rwork; + struct list_head link; + struct list_head enablers; + struct mm_struct *mm; + struct user_event_mm *next; + refcount_t refcnt; + refcount_t tasks; + struct rcu_work put_rwork; }; extern void user_event_mm_dup(struct task_struct *t, -- cgit v1.2.3 From 1e2bae6ae8f6b404b295edd5ba11a0bb1566544c Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Fri, 24 Mar 2023 16:21:49 +0000 Subject: regmap: Removed compressed cache support The compressed register cache support has assumptions that make it hard to cover in testing, mainly that it requires raw registers defaults be provided. Rather than either address these assumptions or leave it untested by the forthcoming KUnit tests let's remove it, the use case is quite thin and there are no current users. Signed-off-by: Mark Brown Link: https://lore.kernel.org/r/20230324-regcache-lzo-v1-1-08c5d63e2a5e@kernel.org --- include/linux/regmap.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 19d54f019cc4..b63204d51b35 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -50,7 +50,6 @@ struct sdw_slave; enum regcache_type { REGCACHE_NONE, REGCACHE_RBTREE, - REGCACHE_COMPRESSED, REGCACHE_FLAT, }; -- cgit v1.2.3 From 27a2195efa8d26447c40dd4a6299ea0247786d75 Mon Sep 17 00:00:00 2001 From: Sebastian Reichel Date: Fri, 17 Mar 2023 23:56:55 +0100 Subject: power: supply: core: auto-exposure of simple-battery data Automatically expose data from the simple-battery firmware node for all battery drivers. Reviewed-by: Linus Walleij Reviewed-by: Matti Vaittinen Signed-off-by: Sebastian Reichel --- include/linux/power_supply.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/power_supply.h b/include/linux/power_supply.h index aa2c4a7c4826..a427f13c757f 100644 --- a/include/linux/power_supply.h +++ b/include/linux/power_supply.h @@ -301,6 +301,7 @@ struct power_supply { bool initialized; bool removing; atomic_t use_cnt; + struct power_supply_battery_info *battery_info; #ifdef CONFIG_THERMAL struct thermal_zone_device *tzd; struct thermal_cooling_device *tcd; @@ -791,10 +792,17 @@ devm_power_supply_get_by_phandle(struct device *dev, const char *property) { return NULL; } #endif /* CONFIG_OF */ +extern const enum power_supply_property power_supply_battery_info_properties[]; +extern const size_t power_supply_battery_info_properties_size; extern int power_supply_get_battery_info(struct power_supply *psy, struct power_supply_battery_info **info_out); extern void power_supply_put_battery_info(struct power_supply *psy, struct power_supply_battery_info *info); +extern bool power_supply_battery_info_has_prop(struct power_supply_battery_info *info, + enum power_supply_property psp); +extern int power_supply_battery_info_get_prop(struct power_supply_battery_info *info, + enum power_supply_property psp, + union power_supply_propval *val); extern int power_supply_ocv2cap_simple(struct power_supply_battery_ocv_table *table, int table_len, int ocv); extern struct power_supply_battery_ocv_table * -- cgit v1.2.3 From c8f573f312f36861db8e40d9953b6d4b84f1321b Mon Sep 17 00:00:00 2001 From: Sebastian Reichel Date: Fri, 17 Mar 2023 23:56:58 +0100 Subject: power: supply: generic-adc-battery: drop jitter delay support Drop support for configuring IRQ jitter delay by using big enough fixed value. Reviewed-by: Linus Walleij Signed-off-by: Sebastian Reichel --- include/linux/power/generic-adc-battery.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/power/generic-adc-battery.h b/include/linux/power/generic-adc-battery.h index c68cbf34cd34..50eb4bf28286 100644 --- a/include/linux/power/generic-adc-battery.h +++ b/include/linux/power/generic-adc-battery.h @@ -11,13 +11,10 @@ * @battery_info: recommended structure to specify static power supply * parameters * @cal_charge: calculate charge level. - * @jitter_delay: delay required after the interrupt to check battery - * status.Default set is 10ms. */ struct gab_platform_data { struct power_supply_info battery_info; int (*cal_charge)(long value); - int jitter_delay; }; #endif /* GENERIC_ADC_BATTERY_H */ -- cgit v1.2.3 From 3b6fd262bfcd696aa98af99d71dcf952f289cbee Mon Sep 17 00:00:00 2001 From: Sebastian Reichel Date: Fri, 17 Mar 2023 23:56:59 +0100 Subject: power: supply: generic-adc-battery: drop charge now support Drop CHARGE_NOW support, which requires a platform specific calculation method. Reviewed-by: Linus Walleij Reviewed-by: Matti Vaittinen Signed-off-by: Sebastian Reichel --- include/linux/power/generic-adc-battery.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/power/generic-adc-battery.h b/include/linux/power/generic-adc-battery.h index 50eb4bf28286..54434e4304d3 100644 --- a/include/linux/power/generic-adc-battery.h +++ b/include/linux/power/generic-adc-battery.h @@ -10,11 +10,9 @@ * struct gab_platform_data - platform_data for generic adc iio battery driver. * @battery_info: recommended structure to specify static power supply * parameters - * @cal_charge: calculate charge level. */ struct gab_platform_data { struct power_supply_info battery_info; - int (*cal_charge)(long value); }; #endif /* GENERIC_ADC_BATTERY_H */ -- cgit v1.2.3 From 1b27bf793fd46219c882b8e545ec736cfadc0841 Mon Sep 17 00:00:00 2001 From: Sebastian Reichel Date: Fri, 17 Mar 2023 23:57:01 +0100 Subject: power: supply: generic-adc-battery: use simple-battery API Constant battery data is available through power-supply's simple-battery API. This works automatically, so the manual handling can be removed without loosing any feature :) Note, that the POWER_SUPPLY_STATUS_FULL check for the level variable can be dropped, since the variable is never written. It can be re-introduced properly once the driver gets functionality to calculate the current charge level. Apart from that the check must be done fuzzy anyways, since charge estimation usually is not precise enough to always return exactly the full charge capacity for a full battery. Reviewed-by: Linus Walleij Reviewed-by: Matti Vaittinen Signed-off-by: Sebastian Reichel --- include/linux/power/generic-adc-battery.h | 18 ------------------ 1 file changed, 18 deletions(-) delete mode 100644 include/linux/power/generic-adc-battery.h (limited to 'include/linux') diff --git a/include/linux/power/generic-adc-battery.h b/include/linux/power/generic-adc-battery.h deleted file mode 100644 index 54434e4304d3..000000000000 --- a/include/linux/power/generic-adc-battery.h +++ /dev/null @@ -1,18 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright (C) 2012, Anish Kumar - */ - -#ifndef GENERIC_ADC_BATTERY_H -#define GENERIC_ADC_BATTERY_H - -/** - * struct gab_platform_data - platform_data for generic adc iio battery driver. - * @battery_info: recommended structure to specify static power supply - * parameters - */ -struct gab_platform_data { - struct power_supply_info battery_info; -}; - -#endif /* GENERIC_ADC_BATTERY_H */ -- cgit v1.2.3 From 447286ebadaafa551550704ff0b42eb08b1d1cb2 Mon Sep 17 00:00:00 2001 From: Yangtao Li Date: Thu, 16 Feb 2023 21:53:24 +0800 Subject: f2fs: convert to use bitmap API Let's use BIT() and GENMASK() instead of open it. Signed-off-by: Yangtao Li Reviewed-by: Chao Yu Signed-off-by: Jaegeuk Kim --- include/linux/f2fs_fs.h | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h index 1701f25117ea..881eb9321967 100644 --- a/include/linux/f2fs_fs.h +++ b/include/linux/f2fs_fs.h @@ -40,9 +40,8 @@ #define F2FS_ENC_UTF8_12_1 1 -#define F2FS_IO_SIZE(sbi) (1 << F2FS_OPTION(sbi).write_io_size_bits) /* Blocks */ -#define F2FS_IO_SIZE_KB(sbi) (1 << (F2FS_OPTION(sbi).write_io_size_bits + 2)) /* KB */ -#define F2FS_IO_SIZE_BYTES(sbi) (1 << (F2FS_OPTION(sbi).write_io_size_bits + 12)) /* B */ +#define F2FS_IO_SIZE(sbi) BIT(F2FS_OPTION(sbi).write_io_size_bits) /* Blocks */ +#define F2FS_IO_SIZE_KB(sbi) BIT(F2FS_OPTION(sbi).write_io_size_bits + 2) /* KB */ #define F2FS_IO_SIZE_BITS(sbi) (F2FS_OPTION(sbi).write_io_size_bits) /* power of 2 */ #define F2FS_IO_SIZE_MASK(sbi) (F2FS_IO_SIZE(sbi) - 1) #define F2FS_IO_ALIGNED(sbi) (F2FS_IO_SIZE(sbi) > 1) @@ -340,7 +339,7 @@ enum { OFFSET_BIT_SHIFT }; -#define OFFSET_BIT_MASK (0x07) /* (0x01 << OFFSET_BIT_SHIFT) - 1 */ +#define OFFSET_BIT_MASK GENMASK(OFFSET_BIT_SHIFT - 1, 0) struct node_footer { __le32 nid; /* node id */ @@ -545,7 +544,7 @@ typedef __le32 f2fs_hash_t; #define MAX_DIR_HASH_DEPTH 63 /* MAX buckets in one level of dir */ -#define MAX_DIR_BUCKETS (1 << ((MAX_DIR_HASH_DEPTH / 2) - 1)) +#define MAX_DIR_BUCKETS BIT((MAX_DIR_HASH_DEPTH / 2) - 1) /* * space utilization of regular dentry and inline dentry (w/o extra reservation) -- cgit v1.2.3 From 4f704d9a8352f5c0a8fcdb6213b934630342bd44 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Tue, 14 Mar 2023 12:51:10 +0100 Subject: nfs: use vfs setgid helper We've aligned setgid behavior over multiple kernel releases. The details can be found in the following two merge messages: cf619f891971 ("Merge tag 'fs.ovl.setgid.v6.2') 426b4ca2d6a5 ("Merge tag 'fs.setgid.v6.0') Consistent setgid stripping behavior is now encapsulated in the setattr_should_drop_sgid() helper which is used by all filesystems that strip setgid bits outside of vfs proper. Switch nfs to rely on this helper as well. Without this patch the setgid stripping tests in xfstests will fail. Signed-off-by: Christian Brauner (Microsoft) Reviewed-by: Christoph Hellwig Message-Id: <20230313-fs-nfs-setgid-v2-1-9a59f436cfc0@kernel.org> Signed-off-by: Christian Brauner --- include/linux/fs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index c85916e9f7db..af95b64fc810 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2675,6 +2675,8 @@ extern struct inode *new_inode(struct super_block *sb); extern void free_inode_nonrcu(struct inode *inode); extern int setattr_should_drop_suidgid(struct mnt_idmap *, struct inode *); extern int file_remove_privs(struct file *); +int setattr_should_drop_sgid(struct mnt_idmap *idmap, + const struct inode *inode); /* * This must be used for allocating filesystems specific inodes to set -- cgit v1.2.3 From c59647c0dc679008886756a888368da1c6d4ccd3 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 28 Mar 2023 23:50:19 +0000 Subject: net: add softnet_data.in_net_rx_action We want to make two optimizations in napi_schedule_rps() and ____napi_schedule() which require to know if these helpers are called from net_rx_action(), instead of being called from other contexts. sd.in_net_rx_action is only read/written by the owning cpu. Signed-off-by: Eric Dumazet Reviewed-by: Jason Xing Tested-by: Jason Xing Signed-off-by: Paolo Abeni --- include/linux/netdevice.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 18a5be6ddd0f..c8c634091a65 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3188,6 +3188,7 @@ struct softnet_data { #ifdef CONFIG_RPS struct softnet_data *rps_ipi_list; #endif + bool in_net_rx_action; #ifdef CONFIG_NET_FLOW_LIMIT struct sd_flow_limit __rcu *flow_limit; #endif -- cgit v1.2.3 From e3d53ded577328f2b26d361f2e62fc70e85ab6a3 Mon Sep 17 00:00:00 2001 From: Jaewon Kim Date: Mon, 6 Mar 2023 10:42:39 +0900 Subject: spi: s3c64xx: add no_cs description This patch adds missing variable no_cs descriptions. Signed-off-by: Jaewon Kim Reviewed-by: Krzysztof Kozlowski Reviewed-by: Andi Shyti Link: https://lore.kernel.org/r/20230306014239.80570-1-jaewon02.kim@samsung.com Signed-off-by: Mark Brown --- include/linux/platform_data/spi-s3c64xx.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/platform_data/spi-s3c64xx.h b/include/linux/platform_data/spi-s3c64xx.h index 5df1ace6d2c9..3101152ce449 100644 --- a/include/linux/platform_data/spi-s3c64xx.h +++ b/include/linux/platform_data/spi-s3c64xx.h @@ -29,6 +29,7 @@ struct s3c64xx_spi_csinfo { * struct s3c64xx_spi_info - SPI Controller defining structure * @src_clk_nr: Clock source index for the CLK_CFG[SPI_CLKSEL] field. * @num_cs: Number of CS this controller emulates. + * @no_cs: Used when CS line is not connected. * @cfg_gpio: Configure pins for this SPI controller. */ struct s3c64xx_spi_info { -- cgit v1.2.3 From de4f5fed3f231a8ff4790bf52975f847b95b85ea Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 29 Mar 2023 08:52:15 -0600 Subject: iov_iter: add iter_iovec() helper This returns a pointer to the current iovec entry in the iterator. Only useful with ITER_IOVEC right now, but it prepares us to treat ITER_UBUF and ITER_IOVEC identically for the first segment. Rename struct iov_iter->iov to iov_iter->__iov to find any potentially troublesome spots, and also to prevent anyone from adding new code that accesses iter->iov directly. Signed-off-by: Jens Axboe --- include/linux/uio.h | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/uio.h b/include/linux/uio.h index 27e3fd942960..4218624b7f78 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -51,7 +51,8 @@ struct iov_iter { }; size_t count; union { - const struct iovec *iov; + /* use iter_iov() to get the current vec */ + const struct iovec *__iov; const struct kvec *kvec; const struct bio_vec *bvec; struct xarray *xarray; @@ -68,6 +69,8 @@ struct iov_iter { }; }; +#define iter_iov(iter) (iter)->__iov + static inline enum iter_type iov_iter_type(const struct iov_iter *i) { return i->iter_type; @@ -146,9 +149,9 @@ static inline size_t iov_length(const struct iovec *iov, unsigned long nr_segs) static inline struct iovec iov_iter_iovec(const struct iov_iter *iter) { return (struct iovec) { - .iov_base = iter->iov->iov_base + iter->iov_offset, + .iov_base = iter_iov(iter)->iov_base + iter->iov_offset, .iov_len = min(iter->count, - iter->iov->iov_len - iter->iov_offset), + iter_iov(iter)->iov_len - iter->iov_offset), }; } -- cgit v1.2.3 From 95e49cf8373a0a4d1ec85f0512080bb4f945df74 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 29 Mar 2023 09:16:45 -0600 Subject: iov_iter: add iter_iov_addr() and iter_iov_len() helpers These just return the address and length of the current iovec segment in the iterator. Convert existing iov_iter_iovec() users to use them instead of getting a copy of the current vec. Signed-off-by: Jens Axboe --- include/linux/uio.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/uio.h b/include/linux/uio.h index 4218624b7f78..b7fce87b720e 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -70,6 +70,8 @@ struct iov_iter { }; #define iter_iov(iter) (iter)->__iov +#define iter_iov_addr(iter) (iter_iov(iter)->iov_base + (iter)->iov_offset) +#define iter_iov_len(iter) (iter_iov(iter)->iov_len - (iter)->iov_offset) static inline enum iter_type iov_iter_type(const struct iov_iter *i) { -- cgit v1.2.3 From 6eb203e1a868187cbc23ae3bad443dc929ca6cca Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 29 Mar 2023 09:18:26 -0600 Subject: iov_iter: remove iov_iter_iovec() No more users are left of this function. Signed-off-by: Jens Axboe --- include/linux/uio.h | 9 --------- 1 file changed, 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/uio.h b/include/linux/uio.h index b7fce87b720e..7f585ceedcb2 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -148,15 +148,6 @@ static inline size_t iov_length(const struct iovec *iov, unsigned long nr_segs) return ret; } -static inline struct iovec iov_iter_iovec(const struct iov_iter *iter) -{ - return (struct iovec) { - .iov_base = iter_iov(iter)->iov_base + iter->iov_offset, - .iov_len = min(iter->count, - iter_iov(iter)->iov_len - iter->iov_offset), - }; -} - size_t copy_page_from_iter_atomic(struct page *page, unsigned offset, size_t bytes, struct iov_iter *i); void iov_iter_advance(struct iov_iter *i, size_t bytes); -- cgit v1.2.3 From cd0bd57a9de59019fe99e9305a2337a66a4f9d39 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 28 Mar 2023 14:29:03 -0600 Subject: iov_iter: set nr_segs = 1 for ITER_UBUF To avoid needing to check if a given user backed iov_iter is of type ITER_IOVEC or ITER_UBUF, set the number of segments for the ITER_UBUF case to 1 as we're carrying a single segment. Signed-off-by: Jens Axboe --- include/linux/uio.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/uio.h b/include/linux/uio.h index 7f585ceedcb2..5dbd2dcab35c 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -355,7 +355,8 @@ static inline void iov_iter_ubuf(struct iov_iter *i, unsigned int direction, .user_backed = true, .data_source = direction, .ubuf = buf, - .count = count + .count = count, + .nr_segs = 1 }; } /* Flags for iov_iter_get/extract_pages*() */ -- cgit v1.2.3 From 747b1f65d39ae729b7914075899b0c82d7f667db Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 28 Mar 2023 14:21:06 -0600 Subject: iov_iter: overlay struct iovec and ubuf/len Add an internal struct iovec that we can return as a pointer, with the fields of the iovec overlapping with the ITER_UBUF ubuf and length fields. Then we can have iter_iov() check for the appropriate type, and return &iter->__ubuf_iovec for ITER_UBUF and iter->__iov for ITER_IOVEC and things will magically work out for a single segment request regardless of either type. Signed-off-by: Jens Axboe --- include/linux/uio.h | 44 +++++++++++++++++++++++++++++++++++--------- 1 file changed, 35 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/uio.h b/include/linux/uio.h index 5dbd2dcab35c..ed35f4427a0a 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -49,15 +49,35 @@ struct iov_iter { size_t iov_offset; int last_offset; }; - size_t count; + /* + * Hack alert: overlay ubuf_iovec with iovec + count, so + * that the members resolve correctly regardless of the type + * of iterator used. This means that you can use: + * + * &iter->__ubuf_iovec or iter->__iov + * + * interchangably for the user_backed cases, hence simplifying + * some of the cases that need to deal with both. + */ union { - /* use iter_iov() to get the current vec */ - const struct iovec *__iov; - const struct kvec *kvec; - const struct bio_vec *bvec; - struct xarray *xarray; - struct pipe_inode_info *pipe; - void __user *ubuf; + /* + * This really should be a const, but we cannot do that without + * also modifying any of the zero-filling iter init functions. + * Leave it non-const for now, but it should be treated as such. + */ + struct iovec __ubuf_iovec; + struct { + union { + /* use iter_iov() to get the current vec */ + const struct iovec *__iov; + const struct kvec *kvec; + const struct bio_vec *bvec; + struct xarray *xarray; + struct pipe_inode_info *pipe; + void __user *ubuf; + }; + size_t count; + }; }; union { unsigned long nr_segs; @@ -69,7 +89,13 @@ struct iov_iter { }; }; -#define iter_iov(iter) (iter)->__iov +static inline const struct iovec *iter_iov(const struct iov_iter *iter) +{ + if (iter->iter_type == ITER_UBUF) + return (const struct iovec *) &iter->__ubuf_iovec; + return iter->__iov; +} + #define iter_iov_addr(iter) (iter_iov(iter)->iov_base + (iter)->iov_offset) #define iter_iov_len(iter) (iter_iov(iter)->iov_len - (iter)->iov_offset) -- cgit v1.2.3 From a0f5276716c80415230b47e321e1c46357d70993 Mon Sep 17 00:00:00 2001 From: Jason Gerecke Date: Wed, 19 Oct 2022 08:18:32 -0700 Subject: HID: Recognize "Digitizer" as a valid input application "Digitizer" is a generic usage that may be used by various devices but which is particularly used by non-display pen tablets. This patch adds the usage to the list of values matched by the IS_INPUT_APPLICATION() macro that determines if an input device should be allocated or not. Signed-off-by: Jason Gerecke Reviewed-by: Ping Cheng Link: https://lore.kernel.org/r/20221019151832.44522-1-jason.gerecke@wacom.com Signed-off-by: Benjamin Tissoires --- include/linux/hid.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/hid.h b/include/linux/hid.h index bff9f459db36..4e4c4fe36911 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -874,7 +874,7 @@ extern bool hid_is_usb(const struct hid_device *hdev); /* We ignore a few input applications that are not widely used */ #define IS_INPUT_APPLICATION(a) \ (((a >= HID_UP_GENDESK) && (a <= HID_GD_MULTIAXIS)) \ - || ((a >= HID_DG_PEN) && (a <= HID_DG_WHITEBOARD)) \ + || ((a >= HID_DG_DIGITIZER) && (a <= HID_DG_WHITEBOARD)) \ || (a == HID_GD_SYSTEM_CONTROL) || (a == HID_CP_CONSUMER_CONTROL) \ || (a == HID_GD_WIRELESS_RADIO_CTLS)) -- cgit v1.2.3 From 96a2ff2a6373259cd3bbc5dcaa79865ce271fa4b Mon Sep 17 00:00:00 2001 From: Joe Thornber Date: Mon, 20 Mar 2023 17:45:02 -0400 Subject: dm bufio: remove unused dm_bufio_release_move interface Was used by multi-snapshot DM target that never went upstream. Signed-off-by: Joe Thornber Acked-by: Mikulas Patocka Signed-off-by: Mike Snitzer --- include/linux/dm-bufio.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dm-bufio.h b/include/linux/dm-bufio.h index 2056743aaaaa..681656a1c03d 100644 --- a/include/linux/dm-bufio.h +++ b/include/linux/dm-bufio.h @@ -130,12 +130,6 @@ int dm_bufio_issue_flush(struct dm_bufio_client *c); */ int dm_bufio_issue_discard(struct dm_bufio_client *c, sector_t block, sector_t count); -/* - * Like dm_bufio_release but also move the buffer to the new - * block. dm_bufio_write_dirty_buffers is needed to commit the new block. - */ -void dm_bufio_release_move(struct dm_buffer *b, sector_t new_block); - /* * Free the given buffer. * This is just a hint, if the buffer is in use or dirty, this function -- cgit v1.2.3 From 06961c487a33a222fd3d84998dc6398ed0449373 Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Wed, 1 Mar 2023 12:48:43 -0500 Subject: dm: split discards further if target sets max_discard_granularity The block core (bio_split_discard) will already split discards based on the 'discard_granularity' and 'max_discard_sectors' queue_limits. But the DM thin target also needs to ensure that it doesn't receive a discard that spans a 'max_discard_sectors' boundary. Introduce a dm_target 'max_discard_granularity' flag that if set will cause DM core to split discard bios relative to 'max_discard_sectors'. This treats 'discard_granularity' as a "min_discard_granularity" and 'max_discard_sectors' as a "max_discard_granularity". Requested-by: Joe Thornber Signed-off-by: Mike Snitzer --- include/linux/device-mapper.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index 7975483816e4..8aa6b3ea91fa 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -358,6 +358,12 @@ struct dm_target { */ bool discards_supported:1; + /* + * Set if this target requires that discards be split on both + * 'discard_granularity' and 'max_discard_sectors' boundaries. + */ + bool max_discard_granularity:1; + /* * Set if we need to limit the number of in-flight bios when swapping. */ -- cgit v1.2.3 From cd3891158a77685aee6129f7374a018d13540b2c Mon Sep 17 00:00:00 2001 From: Jacob Pan Date: Wed, 22 Mar 2023 13:07:58 -0700 Subject: iommu/sva: Move PASID helpers to sva code Preparing to remove IOASID infrastructure, PASID management will be under SVA code. Decouple mm code from IOASID. Reviewed-by: Jason Gunthorpe Signed-off-by: Jacob Pan Reviewed-by: Kevin Tian Link: https://lore.kernel.org/r/20230322200803.869130-3-jacob.jun.pan@linux.intel.com Signed-off-by: Joerg Roedel --- include/linux/ioasid.h | 11 +---------- include/linux/iommu.h | 14 +++++++++++++- include/linux/sched/mm.h | 26 -------------------------- 3 files changed, 14 insertions(+), 37 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ioasid.h b/include/linux/ioasid.h index af1c9d62e642..734bf0e036ee 100644 --- a/include/linux/ioasid.h +++ b/include/linux/ioasid.h @@ -4,8 +4,8 @@ #include #include +#include -#define INVALID_IOASID ((ioasid_t)-1) typedef unsigned int ioasid_t; typedef ioasid_t (*ioasid_alloc_fn_t)(ioasid_t min, ioasid_t max, void *data); typedef void (*ioasid_free_fn_t)(ioasid_t ioasid, void *data); @@ -40,10 +40,6 @@ void *ioasid_find(struct ioasid_set *set, ioasid_t ioasid, int ioasid_register_allocator(struct ioasid_allocator_ops *allocator); void ioasid_unregister_allocator(struct ioasid_allocator_ops *allocator); int ioasid_set_data(ioasid_t ioasid, void *data); -static inline bool pasid_valid(ioasid_t ioasid) -{ - return ioasid != INVALID_IOASID; -} #else /* !CONFIG_IOASID */ static inline ioasid_t ioasid_alloc(struct ioasid_set *set, ioasid_t min, @@ -74,10 +70,5 @@ static inline int ioasid_set_data(ioasid_t ioasid, void *data) return -ENOTSUPP; } -static inline bool pasid_valid(ioasid_t ioasid) -{ - return false; -} - #endif /* CONFIG_IOASID */ #endif /* __LINUX_IOASID_H */ diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 6595454d4f48..d3f81dc6e4dd 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -13,7 +13,6 @@ #include #include #include -#include #include #define IOMMU_READ (1 << 0) @@ -192,6 +191,8 @@ enum iommu_dev_features { }; #define IOMMU_PASID_INVALID (-1U) +typedef unsigned int ioasid_t; +#define INVALID_IOASID ((ioasid_t)-1) #ifdef CONFIG_IOMMU_API @@ -1172,7 +1173,16 @@ static inline bool tegra_dev_iommu_get_stream_id(struct device *dev, u32 *stream return false; } +static inline bool pasid_valid(ioasid_t ioasid) +{ + return ioasid != INVALID_IOASID; +} #ifdef CONFIG_IOMMU_SVA +static inline void mm_pasid_init(struct mm_struct *mm) +{ + mm->pasid = INVALID_IOASID; +} +void mm_pasid_drop(struct mm_struct *mm); struct iommu_sva *iommu_sva_bind_device(struct device *dev, struct mm_struct *mm); void iommu_sva_unbind_device(struct iommu_sva *handle); @@ -1192,6 +1202,8 @@ static inline u32 iommu_sva_get_pasid(struct iommu_sva *handle) { return IOMMU_PASID_INVALID; } +static inline void mm_pasid_init(struct mm_struct *mm) {} +static inline void mm_pasid_drop(struct mm_struct *mm) {} #endif /* CONFIG_IOMMU_SVA */ #endif /* __LINUX_IOMMU_H */ diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index 2a243616f222..da9712a3ba73 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -8,7 +8,6 @@ #include #include #include -#include /* * Routines for handling mm_structs @@ -451,29 +450,4 @@ static inline void membarrier_update_current_mm(struct mm_struct *next_mm) } #endif -#ifdef CONFIG_IOMMU_SVA -static inline void mm_pasid_init(struct mm_struct *mm) -{ - mm->pasid = INVALID_IOASID; -} - -/* Associate a PASID with an mm_struct: */ -static inline void mm_pasid_set(struct mm_struct *mm, u32 pasid) -{ - mm->pasid = pasid; -} - -static inline void mm_pasid_drop(struct mm_struct *mm) -{ - if (pasid_valid(mm->pasid)) { - ioasid_free(mm->pasid); - mm->pasid = INVALID_IOASID; - } -} -#else -static inline void mm_pasid_init(struct mm_struct *mm) {} -static inline void mm_pasid_set(struct mm_struct *mm, u32 pasid) {} -static inline void mm_pasid_drop(struct mm_struct *mm) {} -#endif - #endif /* _LINUX_SCHED_MM_H */ -- cgit v1.2.3 From fffaed1e24b8d114e958d180cb4a8aed3febbb5a Mon Sep 17 00:00:00 2001 From: Jacob Pan Date: Wed, 22 Mar 2023 13:08:02 -0700 Subject: iommu/ioasid: Rename INVALID_IOASID INVALID_IOASID and IOMMU_PASID_INVALID are duplicated. Rename INVALID_IOASID and consolidate since we are moving away from IOASID infrastructure. Reviewed-by: Dave Jiang Reviewed-by: Jason Gunthorpe Reviewed-by: Kevin Tian Reviewed-by: Lu Baolu Signed-off-by: Jacob Pan Link: https://lore.kernel.org/r/20230322200803.869130-7-jacob.jun.pan@linux.intel.com Signed-off-by: Joerg Roedel --- include/linux/ioasid.h | 1 + include/linux/iommu.h | 6 +++--- 2 files changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ioasid.h b/include/linux/ioasid.h index 734bf0e036ee..bbc9c6fd3310 100644 --- a/include/linux/ioasid.h +++ b/include/linux/ioasid.h @@ -7,6 +7,7 @@ #include typedef unsigned int ioasid_t; +#define INVALID_IOASID ((ioasid_t)-1) typedef ioasid_t (*ioasid_alloc_fn_t)(ioasid_t min, ioasid_t max, void *data); typedef void (*ioasid_free_fn_t)(ioasid_t ioasid, void *data); diff --git a/include/linux/iommu.h b/include/linux/iommu.h index d3f81dc6e4dd..54f535ff9868 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -192,7 +192,6 @@ enum iommu_dev_features { #define IOMMU_PASID_INVALID (-1U) typedef unsigned int ioasid_t; -#define INVALID_IOASID ((ioasid_t)-1) #ifdef CONFIG_IOMMU_API @@ -1175,12 +1174,13 @@ static inline bool tegra_dev_iommu_get_stream_id(struct device *dev, u32 *stream static inline bool pasid_valid(ioasid_t ioasid) { - return ioasid != INVALID_IOASID; + return ioasid != IOMMU_PASID_INVALID; } + #ifdef CONFIG_IOMMU_SVA static inline void mm_pasid_init(struct mm_struct *mm) { - mm->pasid = INVALID_IOASID; + mm->pasid = IOMMU_PASID_INVALID; } void mm_pasid_drop(struct mm_struct *mm); struct iommu_sva *iommu_sva_bind_device(struct device *dev, -- cgit v1.2.3 From 99b5726b44230329f35b4c4d7fe1577d4f4edb31 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Wed, 22 Mar 2023 13:08:03 -0700 Subject: iommu: Remove ioasid infrastructure This has no use anymore, delete it all. Reviewed-by: Kevin Tian Reviewed-by: Lu Baolu Signed-off-by: Jason Gunthorpe Signed-off-by: Jacob Pan Link: https://lore.kernel.org/r/20230322200803.869130-8-jacob.jun.pan@linux.intel.com Signed-off-by: Joerg Roedel --- include/linux/ioasid.h | 75 -------------------------------------------------- 1 file changed, 75 deletions(-) delete mode 100644 include/linux/ioasid.h (limited to 'include/linux') diff --git a/include/linux/ioasid.h b/include/linux/ioasid.h deleted file mode 100644 index bbc9c6fd3310..000000000000 --- a/include/linux/ioasid.h +++ /dev/null @@ -1,75 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __LINUX_IOASID_H -#define __LINUX_IOASID_H - -#include -#include -#include - -typedef unsigned int ioasid_t; -#define INVALID_IOASID ((ioasid_t)-1) -typedef ioasid_t (*ioasid_alloc_fn_t)(ioasid_t min, ioasid_t max, void *data); -typedef void (*ioasid_free_fn_t)(ioasid_t ioasid, void *data); - -struct ioasid_set { - int dummy; -}; - -/** - * struct ioasid_allocator_ops - IOASID allocator helper functions and data - * - * @alloc: helper function to allocate IOASID - * @free: helper function to free IOASID - * @list: for tracking ops that share helper functions but not data - * @pdata: data belong to the allocator, provided when calling alloc() - */ -struct ioasid_allocator_ops { - ioasid_alloc_fn_t alloc; - ioasid_free_fn_t free; - struct list_head list; - void *pdata; -}; - -#define DECLARE_IOASID_SET(name) struct ioasid_set name = { 0 } - -#if IS_ENABLED(CONFIG_IOASID) -ioasid_t ioasid_alloc(struct ioasid_set *set, ioasid_t min, ioasid_t max, - void *private); -void ioasid_free(ioasid_t ioasid); -void *ioasid_find(struct ioasid_set *set, ioasid_t ioasid, - bool (*getter)(void *)); -int ioasid_register_allocator(struct ioasid_allocator_ops *allocator); -void ioasid_unregister_allocator(struct ioasid_allocator_ops *allocator); -int ioasid_set_data(ioasid_t ioasid, void *data); - -#else /* !CONFIG_IOASID */ -static inline ioasid_t ioasid_alloc(struct ioasid_set *set, ioasid_t min, - ioasid_t max, void *private) -{ - return INVALID_IOASID; -} - -static inline void ioasid_free(ioasid_t ioasid) { } - -static inline void *ioasid_find(struct ioasid_set *set, ioasid_t ioasid, - bool (*getter)(void *)) -{ - return NULL; -} - -static inline int ioasid_register_allocator(struct ioasid_allocator_ops *allocator) -{ - return -ENOTSUPP; -} - -static inline void ioasid_unregister_allocator(struct ioasid_allocator_ops *allocator) -{ -} - -static inline int ioasid_set_data(ioasid_t ioasid, void *data) -{ - return -ENOTSUPP; -} - -#endif /* CONFIG_IOASID */ -#endif /* __LINUX_IOASID_H */ -- cgit v1.2.3 From 16812c96550c30a8d5743167ef4e462d6fbe7472 Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Wed, 29 Mar 2023 21:47:21 +0800 Subject: iommu/vt-d: Fix an IOMMU perfmon warning when CPU hotplug A warning can be triggered when hotplug CPU 0. $ echo 0 > /sys/devices/system/cpu/cpu0/online ------------[ cut here ]------------ Voluntary context switch within RCU read-side critical section! WARNING: CPU: 0 PID: 19 at kernel/rcu/tree_plugin.h:318 rcu_note_context_switch+0x4f4/0x580 RIP: 0010:rcu_note_context_switch+0x4f4/0x580 Call Trace: ? perf_event_update_userpage+0x104/0x150 __schedule+0x8d/0x960 ? perf_event_set_state.part.82+0x11/0x50 schedule+0x44/0xb0 schedule_timeout+0x226/0x310 ? __perf_event_disable+0x64/0x1a0 ? _raw_spin_unlock+0x14/0x30 wait_for_completion+0x94/0x130 __wait_rcu_gp+0x108/0x130 synchronize_rcu+0x67/0x70 ? invoke_rcu_core+0xb0/0xb0 ? __bpf_trace_rcu_stall_warning+0x10/0x10 perf_pmu_migrate_context+0x121/0x370 iommu_pmu_cpu_offline+0x6a/0xa0 ? iommu_pmu_del+0x1e0/0x1e0 cpuhp_invoke_callback+0x129/0x510 cpuhp_thread_fun+0x94/0x150 smpboot_thread_fn+0x183/0x220 ? sort_range+0x20/0x20 kthread+0xe6/0x110 ? kthread_complete_and_exit+0x20/0x20 ret_from_fork+0x1f/0x30 ---[ end trace 0000000000000000 ]--- The synchronize_rcu() will be invoked in the perf_pmu_migrate_context(), when migrating a PMU to a new CPU. However, the current for_each_iommu() is within RCU read-side critical section. Two methods were considered to fix the issue. - Use the dmar_global_lock to replace the RCU read lock when going through the drhd list. But it triggers a lockdep warning. - Use the cpuhp_setup_state_multi() to set up a dedicated state for each IOMMU PMU. The lock can be avoided. The latter method is implemented in this patch. Since each IOMMU PMU has a dedicated state, add cpuhp_node and cpu in struct iommu_pmu to track the state. The state can be dynamically allocated now. Remove the CPUHP_AP_PERF_X86_IOMMU_PERF_ONLINE. Fixes: 46284c6ceb5e ("iommu/vt-d: Support cpumask for IOMMU perfmon") Reported-by: Ammy Yi Signed-off-by: Kan Liang Link: https://lore.kernel.org/r/20230328182028.1366416-1-kan.liang@linux.intel.com Signed-off-by: Lu Baolu Link: https://lore.kernel.org/r/20230329134721.469447-4-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- include/linux/cpuhotplug.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index c6fab004104a..5b2f8147d1ae 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -218,7 +218,6 @@ enum cpuhp_state { CPUHP_AP_PERF_X86_CQM_ONLINE, CPUHP_AP_PERF_X86_CSTATE_ONLINE, CPUHP_AP_PERF_X86_IDXD_ONLINE, - CPUHP_AP_PERF_X86_IOMMU_PERF_ONLINE, CPUHP_AP_PERF_S390_CF_ONLINE, CPUHP_AP_PERF_S390_SF_ONLINE, CPUHP_AP_PERF_ARM_CCI_ONLINE, -- cgit v1.2.3 From 653a180957a85c3fc30320cc7e84f5dc913a64f8 Mon Sep 17 00:00:00 2001 From: Michael Sit Wei Hong Date: Thu, 30 Mar 2023 17:14:02 +0800 Subject: net: phylink: add phylink_expects_phy() method Provide phylink_expects_phy() to allow MAC drivers to check if it is expecting a PHY to attach to. Since fixed-linked setups do not need to attach to a PHY. Provides a boolean value as to if the MAC should expect a PHY. Returns true if a PHY is expected. Reviewed-by: Russell King (Oracle) Signed-off-by: Michael Sit Wei Hong Signed-off-by: David S. Miller --- include/linux/phylink.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/phylink.h b/include/linux/phylink.h index c492c26202b5..637698ed5cb6 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -574,6 +574,7 @@ struct phylink *phylink_create(struct phylink_config *, struct fwnode_handle *, phy_interface_t iface, const struct phylink_mac_ops *mac_ops); void phylink_destroy(struct phylink *); +bool phylink_expects_phy(struct phylink *pl); int phylink_connect_phy(struct phylink *, struct phy_device *); int phylink_of_phy_connect(struct phylink *, struct device_node *, u32 flags); -- cgit v1.2.3 From 27fc5ec673b527dbc2f44787246a39c5ecc01de5 Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Wed, 1 Mar 2023 17:32:53 +0100 Subject: clk: Introduce devm_clk_hw_register_gate_parent_data() Add an API for clock gate that uses parent_data for the parent instead of a string parent_name. Reviewed-by: Peng Fan Reviewed-by: Fabio Estevam Tested-by: Adam Ford #imx8mp-beacon-kit Tested-by: Alexander Stein Signed-off-by: Marek Vasut Tested-by: Richard Leitner Reviewed-by: Stephen Boyd Signed-off-by: Abel Vesa Link: https://lore.kernel.org/r/20230301163257.49005-1-marex@denx.de --- include/linux/clk-provider.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include/linux') diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index 842e72a5348f..92b7c794c627 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -608,6 +608,25 @@ struct clk *clk_register_gate(struct device *dev, const char *name, __devm_clk_hw_register_gate((dev), NULL, (name), (parent_name), NULL, \ NULL, (flags), (reg), (bit_idx), \ (clk_gate_flags), (lock)) + +/** + * devm_clk_hw_register_gate - register a gate clock with the clock framework + * @dev: device that is registering this clock + * @name: name of this clock + * @parent_data: parent clk data + * @flags: framework-specific flags for this clock + * @reg: register address to control gating of this clock + * @bit_idx: which bit in the register controls gating of this clock + * @clk_gate_flags: gate-specific flags for this clock + * @lock: shared register lock for this clock + */ +#define devm_clk_hw_register_gate_parent_data(dev, name, parent_data, flags, \ + reg, bit_idx, clk_gate_flags, \ + lock) \ + __devm_clk_hw_register_gate((dev), NULL, (name), NULL, NULL, \ + (parent_data), (flags), (reg), (bit_idx), \ + (clk_gate_flags), (lock)) + void clk_unregister_gate(struct clk *clk); void clk_hw_unregister_gate(struct clk_hw *hw); int clk_gate_is_enabled(struct clk_hw *hw); -- cgit v1.2.3 From f806bea3093cb3568e01b4375d5e1d7c8c47c1d4 Mon Sep 17 00:00:00 2001 From: Vignesh Raghavendra Date: Thu, 23 Mar 2023 17:31:07 +0530 Subject: dmaengine: ti: k3-udma: Workaround errata i2234 Per [1], UDMA TR15 transactions may hang if ICNT0 is less than 64B Work around is to set EOL flag is to 1 for ICNT0. Since, there is no performance penalty / side effects of setting EOL flag event ICNTO > 64B, just set the flag for all UDMAP TR15 descriptors. [1] https://www.ti.com/lit/er/sprz455a/sprz455a.pdf Errata doc for J721E DRA829/TDA4VM Processors Silicon Revision 1.1/1.0 (Rev. A) Signed-off-by: Vignesh Raghavendra [j-choudhary@ti.com: minor cleanups] Signed-off-by: Jayesh Choudhary Link: https://lore.kernel.org/r/20230323120107.27638-1-j-choudhary@ti.com Signed-off-by: Vinod Koul --- include/linux/dma/ti-cppi5.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/dma/ti-cppi5.h b/include/linux/dma/ti-cppi5.h index efa2f0309f00..c53c0f6e3b1a 100644 --- a/include/linux/dma/ti-cppi5.h +++ b/include/linux/dma/ti-cppi5.h @@ -616,6 +616,7 @@ static inline void *cppi5_hdesc_get_swdata(struct cppi5_host_desc_t *desc) #define CPPI5_TR_CSF_SUPR_EVT BIT(2) #define CPPI5_TR_CSF_EOL_ADV_SHIFT (4U) #define CPPI5_TR_CSF_EOL_ADV_MASK GENMASK(6, 4) +#define CPPI5_TR_CSF_EOL_ICNT0 BIT(4) #define CPPI5_TR_CSF_EOP BIT(7) /** -- cgit v1.2.3 From 6f14c02220c791d5c46b0f965b9340c58f3d503d Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 31 Mar 2023 11:33:13 +0200 Subject: driver core: create class_is_registered() Some classes (i.e. gpio), want to know if they have been registered or not, and poke around in the class's internal structures to try to figure this out. Because this is not really a good idea, provide a function for classes to call to try to figure this out. Note, this is racy as the state of the class could change at any moment in time after the call is made, but as usually a class only wants to know if it has been registered yet or not, it should be fairly safe to use, and is just as safe as the previous "poke at the class internals" check was. Move the gpiolib code to use this function as proof that it works properly. Cc: Bartosz Golaszewski Cc: Sebastian Reichel Cc: Benjamin Tissoires Cc: linux-gpio@vger.kernel.org Reviewed-by: Linus Walleij Reviewed-by: Rafael J. Wysocki Link: https://lore.kernel.org/r/20230331093318.82288-2-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- include/linux/device/class.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/device/class.h b/include/linux/device/class.h index b53728ca56fb..9cb5db0588c8 100644 --- a/include/linux/device/class.h +++ b/include/linux/device/class.h @@ -84,6 +84,7 @@ extern struct kobject *sysfs_dev_block_kobj; int __must_check class_register(struct class *class); void class_unregister(const struct class *class); +bool class_is_registered(const struct class *class); struct class_compat; struct class_compat *class_compat_register(const char *name); -- cgit v1.2.3 From 2df418cf4b720fe3a0db4b4aab67be43d26af9dd Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 31 Mar 2023 11:33:14 +0200 Subject: driver core: class: remove subsystem private pointer from struct class Now that the last users of the subsystem private pointer in struct class are gone, the pointer can be removed, as no one is using it. One step closer to allowing struct class to be const and moved into read-only memory. Acked-by: Rafael J. Wysocki Link: https://lore.kernel.org/r/20230331093318.82288-3-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- include/linux/device/class.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/device/class.h b/include/linux/device/class.h index 9cb5db0588c8..f7aad64e256a 100644 --- a/include/linux/device/class.h +++ b/include/linux/device/class.h @@ -71,8 +71,6 @@ struct class { void (*get_ownership)(const struct device *dev, kuid_t *uid, kgid_t *gid); const struct dev_pm_ops *pm; - - struct subsys_private *p; }; struct class_dev_iter { -- cgit v1.2.3 From e78195d52981fc634a4e1e66610a316088bd7458 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 31 Mar 2023 11:33:16 +0200 Subject: driver core: class: remove dev_kobj from struct class The dev_kobj field in struct class is now only written to, but never read from, so it can be removed as it is useless. Acked-by: Rafael J. Wysocki Link: https://lore.kernel.org/r/20230331093318.82288-5-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- include/linux/device/class.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/device/class.h b/include/linux/device/class.h index f7aad64e256a..e946642c314e 100644 --- a/include/linux/device/class.h +++ b/include/linux/device/class.h @@ -27,7 +27,6 @@ struct fwnode_handle; * @name: Name of the class. * @class_groups: Default attributes of this class. * @dev_groups: Default attributes of the devices that belong to the class. - * @dev_kobj: The kobject that represents this class and links it into the hierarchy. * @dev_uevent: Called when a device is added, removed from this class, or a * few other things that generate uevents to add the environment * variables. @@ -55,7 +54,6 @@ struct class { const struct attribute_group **class_groups; const struct attribute_group **dev_groups; - struct kobject *dev_kobj; int (*dev_uevent)(const struct device *dev, struct kobj_uevent_env *env); char *(*devnode)(const struct device *dev, umode_t *mode); -- cgit v1.2.3 From 575ab414c90a317158db48475a88de42f37e0afa Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 31 Mar 2023 11:33:17 +0200 Subject: driver core: make sysfs_dev_block_kobj static Nothing outside of drivers/base/core.c uses sysfs_dev_block_kobj, so make it static and document what it is used for so we remember it the next time we touch it 15 years from now. Acked-by: Rafael J. Wysocki Link: https://lore.kernel.org/r/20230331093318.82288-6-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- include/linux/device/class.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/device/class.h b/include/linux/device/class.h index e946642c314e..7e4a1a6329f4 100644 --- a/include/linux/device/class.h +++ b/include/linux/device/class.h @@ -76,8 +76,6 @@ struct class_dev_iter { const struct device_type *type; }; -extern struct kobject *sysfs_dev_block_kobj; - int __must_check class_register(struct class *class); void class_unregister(const struct class *class); bool class_is_registered(const struct class *class); -- cgit v1.2.3 From 54b47585db6658a5eb898d4d45be18d1e581c1bf Mon Sep 17 00:00:00 2001 From: Nicolin Chen Date: Mon, 27 Mar 2023 02:33:47 -0700 Subject: iommufd: Create access in vfio_iommufd_emulated_bind() There are needs to created iommufd_access prior to have an IOAS and set IOAS later. Like the vfio device cdev needs to have an iommufd object to represent the bond (iommufd_access) and IOAS replacement. Moves the iommufd_access_create() call into vfio_iommufd_emulated_bind(), making it symmetric with the __vfio_iommufd_access_destroy() call in the vfio_iommufd_emulated_unbind(). This means an access is created/destroyed by the bind()/unbind(), and the vfio_iommufd_emulated_attach_ioas() only updates the access->ioas pointer. Since vfio_iommufd_emulated_bind() does not provide ioas_id, drop it from the argument list of iommufd_access_create(). Instead, add a new access API iommufd_access_attach() to set the access->ioas pointer. Also, set vdev->iommufd_attached accordingly, similar to the physical pathway. Link: https://lore.kernel.org/r/20230327093351.44505-3-yi.l.liu@intel.com Reviewed-by: Kevin Tian Reviewed-by: Jason Gunthorpe Tested-by: Terrence Xu Tested-by: Nicolin Chen Signed-off-by: Nicolin Chen Signed-off-by: Yi Liu Acked-by: Alex Williamson Signed-off-by: Jason Gunthorpe --- include/linux/iommufd.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/iommufd.h b/include/linux/iommufd.h index c0b5b3ac34f1..155d3630aedc 100644 --- a/include/linux/iommufd.h +++ b/include/linux/iommufd.h @@ -40,9 +40,10 @@ enum { }; struct iommufd_access * -iommufd_access_create(struct iommufd_ctx *ictx, u32 ioas_id, +iommufd_access_create(struct iommufd_ctx *ictx, const struct iommufd_access_ops *ops, void *data); void iommufd_access_destroy(struct iommufd_access *access); +int iommufd_access_attach(struct iommufd_access *access, u32 ioas_id); void iommufd_ctx_get(struct iommufd_ctx *ictx); -- cgit v1.2.3 From 4508a533fce4db0004c1e8dd047c1e77046fc9c5 Mon Sep 17 00:00:00 2001 From: Yi Liu Date: Mon, 27 Mar 2023 02:33:48 -0700 Subject: vfio-iommufd: No need to record iommufd_ctx in vfio_device iommufd_ctx is stored in vfio_device for emulated devices per bind_iommufd. However, as iommufd_access is created in bind, no more need to stored it since iommufd_access implicitly stores it. Link: https://lore.kernel.org/r/20230327093351.44505-4-yi.l.liu@intel.com Reviewed-by: Jason Gunthorpe Reviewed-by: Kevin Tian Tested-by: Terrence Xu Tested-by: Nicolin Chen Signed-off-by: Yi Liu Acked-by: Alex Williamson Signed-off-by: Jason Gunthorpe --- include/linux/vfio.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/vfio.h b/include/linux/vfio.h index 93134b023968..3188d8a374bd 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -60,7 +60,6 @@ struct vfio_device { void (*put_kvm)(struct kvm *kvm); #if IS_ENABLED(CONFIG_IOMMUFD) struct iommufd_device *iommufd_device; - struct iommufd_ctx *iommufd_ictx; bool iommufd_attached; #endif }; -- cgit v1.2.3 From 632fda7f912c845f98ff20e69c600160a189d803 Mon Sep 17 00:00:00 2001 From: Yi Liu Date: Mon, 27 Mar 2023 02:33:49 -0700 Subject: vfio-iommufd: Make vfio_iommufd_emulated_bind() return iommufd_access ID vfio device cdev needs to return iommufd_access ID to userspace if bind_iommufd succeeds. Link: https://lore.kernel.org/r/20230327093351.44505-5-yi.l.liu@intel.com Reviewed-by: Kevin Tian Reviewed-by: Jason Gunthorpe Tested-by: Terrence Xu Tested-by: Nicolin Chen Signed-off-by: Yi Liu Acked-by: Alex Williamson Signed-off-by: Jason Gunthorpe --- include/linux/iommufd.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/iommufd.h b/include/linux/iommufd.h index 155d3630aedc..1129a36a74c4 100644 --- a/include/linux/iommufd.h +++ b/include/linux/iommufd.h @@ -41,7 +41,7 @@ enum { struct iommufd_access * iommufd_access_create(struct iommufd_ctx *ictx, - const struct iommufd_access_ops *ops, void *data); + const struct iommufd_access_ops *ops, void *data, u32 *id); void iommufd_access_destroy(struct iommufd_access *access); int iommufd_access_attach(struct iommufd_access *access, u32 ioas_id); -- cgit v1.2.3 From 15ce79bd9daf956f2840959f81f8c97dce9d87c2 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Christoph=20B=C3=B6hmwalder?= Date: Thu, 30 Mar 2023 12:27:38 +0200 Subject: genetlink: make _genl_cmd_to_str static MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Primarily to silence warnings like: warning: no previous prototype for 'xxx_genl_cmd_to_str' [-Wmissing-prototypes] Signed-off-by: Christoph Böhmwalder Link: https://lore.kernel.org/r/20230330102744.2128122-2-christoph.boehmwalder@linbit.com Signed-off-by: Jens Axboe --- include/linux/genl_magic_func.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/genl_magic_func.h b/include/linux/genl_magic_func.h index 4a4b387181ad..2984b0cb24b1 100644 --- a/include/linux/genl_magic_func.h +++ b/include/linux/genl_magic_func.h @@ -209,7 +209,7 @@ static int s_name ## _from_attrs_for_change(struct s_name *s, \ * Magic: define op number to op name mapping {{{1 * {{{2 */ -const char *CONCAT_(GENL_MAGIC_FAMILY, _genl_cmd_to_str)(__u8 cmd) +static const char *CONCAT_(GENL_MAGIC_FAMILY, _genl_cmd_to_str)(__u8 cmd) { switch (cmd) { #undef GENL_op -- cgit v1.2.3 From dd2d6604407da5b1b260faee409cd601fe914ce9 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Thu, 30 Mar 2023 21:47:31 -0700 Subject: net: minor reshuffle of napi_struct napi_id is read by GRO and drivers to mark skbs, and it currently sits at the end of the structure, in a mostly unused cache line. Move it up into a hole, and separate the clearly control path fields from the important ones. Before: struct napi_struct { struct list_head poll_list; /* 0 16 */ long unsigned int state; /* 16 8 */ int weight; /* 24 4 */ int defer_hard_irqs_count; /* 28 4 */ long unsigned int gro_bitmask; /* 32 8 */ int (*poll)(struct napi_struct *, int); /* 40 8 */ int poll_owner; /* 48 4 */ /* XXX 4 bytes hole, try to pack */ struct net_device * dev; /* 56 8 */ /* --- cacheline 1 boundary (64 bytes) --- */ struct gro_list gro_hash[8]; /* 64 192 */ /* --- cacheline 4 boundary (256 bytes) --- */ struct sk_buff * skb; /* 256 8 */ struct list_head rx_list; /* 264 16 */ int rx_count; /* 280 4 */ /* XXX 4 bytes hole, try to pack */ struct hrtimer timer; /* 288 64 */ /* XXX last struct has 4 bytes of padding */ /* --- cacheline 5 boundary (320 bytes) was 32 bytes ago --- */ struct list_head dev_list; /* 352 16 */ struct hlist_node napi_hash_node; /* 368 16 */ /* --- cacheline 6 boundary (384 bytes) --- */ unsigned int napi_id; /* 384 4 */ /* XXX 4 bytes hole, try to pack */ struct task_struct * thread; /* 392 8 */ /* size: 400, cachelines: 7, members: 17 */ /* sum members: 388, holes: 3, sum holes: 12 */ /* paddings: 1, sum paddings: 4 */ /* last cacheline: 16 bytes */ }; After: struct napi_struct { struct list_head poll_list; /* 0 16 */ long unsigned int state; /* 16 8 */ int weight; /* 24 4 */ int defer_hard_irqs_count; /* 28 4 */ long unsigned int gro_bitmask; /* 32 8 */ int (*poll)(struct napi_struct *, int); /* 40 8 */ int poll_owner; /* 48 4 */ /* XXX 4 bytes hole, try to pack */ struct net_device * dev; /* 56 8 */ /* --- cacheline 1 boundary (64 bytes) --- */ struct gro_list gro_hash[8]; /* 64 192 */ /* --- cacheline 4 boundary (256 bytes) --- */ struct sk_buff * skb; /* 256 8 */ struct list_head rx_list; /* 264 16 */ int rx_count; /* 280 4 */ unsigned int napi_id; /* 284 4 */ struct hrtimer timer; /* 288 64 */ /* XXX last struct has 4 bytes of padding */ /* --- cacheline 5 boundary (320 bytes) was 32 bytes ago --- */ struct task_struct * thread; /* 352 8 */ struct list_head dev_list; /* 360 16 */ struct hlist_node napi_hash_node; /* 376 16 */ /* size: 392, cachelines: 7, members: 17 */ /* sum members: 388, holes: 1, sum holes: 4 */ /* paddings: 1, sum paddings: 4 */ /* forced alignments: 1 */ /* last cacheline: 8 bytes */ } __attribute__((__aligned__(8))); Signed-off-by: Jakub Kicinski Reviewed-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/netdevice.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index c8c634091a65..62e093a6d6d1 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -367,11 +367,12 @@ struct napi_struct { struct sk_buff *skb; struct list_head rx_list; /* Pending GRO_NORMAL skbs */ int rx_count; /* length of rx_list */ + unsigned int napi_id; struct hrtimer timer; + struct task_struct *thread; + /* control-path-only fields follow */ struct list_head dev_list; struct hlist_node napi_hash_node; - unsigned int napi_id; - struct task_struct *thread; }; enum { -- cgit v1.2.3 From eb0d8623b9b805cbcab87620a363292552c19359 Mon Sep 17 00:00:00 2001 From: AngeloGioacchino Del Regno Date: Wed, 22 Feb 2023 10:42:52 +0100 Subject: soc: mediatek: cmdq: Add inline functions for !CONFIG_MTK_CMDQ In preparation for a cleanup of ifdef instances of IS_REACHABLE() for the CONFIG_MTK_CMDQ configuration option, add inline functions that will either return a failure or, for void functions, do nothing. Signed-off-by: AngeloGioacchino Del Regno Reviewed-by: Chen-Yu Tsai Link: https://lore.kernel.org/r/20230222094253.23678-9-angelogioacchino.delregno@collabora.com Signed-off-by: Matthias Brugger --- include/linux/soc/mediatek/mtk-cmdq.h | 114 ++++++++++++++++++++++++++++++++++ 1 file changed, 114 insertions(+) (limited to 'include/linux') diff --git a/include/linux/soc/mediatek/mtk-cmdq.h b/include/linux/soc/mediatek/mtk-cmdq.h index 2b498f4f3946..649955d2cf5c 100644 --- a/include/linux/soc/mediatek/mtk-cmdq.h +++ b/include/linux/soc/mediatek/mtk-cmdq.h @@ -27,6 +27,8 @@ struct cmdq_client { struct mbox_chan *chan; }; +#if IS_ENABLED(CONFIG_MTK_CMDQ) + /** * cmdq_dev_get_client_reg() - parse cmdq client reg from the device * node of CMDQ client @@ -277,4 +279,116 @@ int cmdq_pkt_finalize(struct cmdq_pkt *pkt); */ int cmdq_pkt_flush_async(struct cmdq_pkt *pkt); +#else /* IS_ENABLED(CONFIG_MTK_CMDQ) */ + +static inline int cmdq_dev_get_client_reg(struct device *dev, + struct cmdq_client_reg *client_reg, int idx) +{ + return -ENODEV; +} + +static inline struct cmdq_client *cmdq_mbox_create(struct device *dev, int index) +{ + return ERR_PTR(-EINVAL); +} + +static inline void cmdq_mbox_destroy(struct cmdq_client *client) { } + +static inline struct cmdq_pkt *cmdq_pkt_create(struct cmdq_client *client, size_t size) +{ + return ERR_PTR(-EINVAL); +} + +static inline void cmdq_pkt_destroy(struct cmdq_pkt *pkt) { } + +static inline int cmdq_pkt_write(struct cmdq_pkt *pkt, u8 subsys, u16 offset, u32 value) +{ + return -ENOENT; +} + +static inline int cmdq_pkt_write_mask(struct cmdq_pkt *pkt, u8 subsys, + u16 offset, u32 value, u32 mask) +{ + return -ENOENT; +} + +static inline int cmdq_pkt_read_s(struct cmdq_pkt *pkt, u16 high_addr_reg_idx, + u16 addr_low, u16 reg_idx) +{ + return -ENOENT; +} + +static inline int cmdq_pkt_write_s(struct cmdq_pkt *pkt, u16 high_addr_reg_idx, + u16 addr_low, u16 src_reg_idx) +{ + return -ENOENT; +} + +static inline int cmdq_pkt_write_s_mask(struct cmdq_pkt *pkt, u16 high_addr_reg_idx, + u16 addr_low, u16 src_reg_idx, u32 mask) +{ + return -ENOENT; +} + +static inline int cmdq_pkt_write_s_value(struct cmdq_pkt *pkt, u8 high_addr_reg_idx, + u16 addr_low, u32 value) +{ + return -ENOENT; +} + +static inline int cmdq_pkt_write_s_mask_value(struct cmdq_pkt *pkt, u8 high_addr_reg_idx, + u16 addr_low, u32 value, u32 mask) +{ + return -ENOENT; +} + +static inline int cmdq_pkt_wfe(struct cmdq_pkt *pkt, u16 event, bool clear) +{ + return -EINVAL; +} + +static inline int cmdq_pkt_clear_event(struct cmdq_pkt *pkt, u16 event) +{ + return -EINVAL; +} + +static inline int cmdq_pkt_set_event(struct cmdq_pkt *pkt, u16 event) +{ + return -EINVAL; +} + +static inline int cmdq_pkt_poll(struct cmdq_pkt *pkt, u8 subsys, + u16 offset, u32 value) +{ + return -EINVAL; +} + +static inline int cmdq_pkt_poll_mask(struct cmdq_pkt *pkt, u8 subsys, + u16 offset, u32 value, u32 mask) +{ + return -EINVAL; +} + +static inline int cmdq_pkt_assign(struct cmdq_pkt *pkt, u16 reg_idx, u32 value) +{ + return -EINVAL; +} + +static inline int cmdq_pkt_jump(struct cmdq_pkt *pkt, dma_addr_t addr) +{ + return -EINVAL; +} + +static inline int cmdq_pkt_finalize(struct cmdq_pkt *pkt) +{ + return -EINVAL; +} + +static inline int cmdq_pkt_flush_async(struct cmdq_pkt *pkt) +{ + return -EINVAL; +} + +#endif /* IS_ENABLED(CONFIG_MTK_CMDQ) */ + #endif /* __MTK_CMDQ_H__ */ -- cgit v1.2.3 From c4bffeaa8d50b7279c5a76597efa4b06e709df63 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Sun, 2 Apr 2023 15:37:53 +0300 Subject: net: add struct kernel_hwtstamp_config and make net_hwtstamp_validate() use it Jakub Kicinski suggested that we may want to add new UAPI for controlling hardware timestamping through netlink in the future, and in that case, we will be limited to the struct hwtstamp_config that is currently passed in fixed binary format through the SIOCGHWTSTAMP and SIOCSHWTSTAMP ioctls. It would be good if new kernel code already started operating on an extensible kernel variant of that structure, similar in concept to struct kernel_ethtool_coalesce vs struct ethtool_coalesce. Since struct hwtstamp_config is in include/uapi/linux/net_tstamp.h, here we introduce include/linux/net_tstamp.h which shadows that other header, but also includes it, so that existing includers of this header work as before. In addition to that, we add the definition for the kernel-only structure, and a helper which translates all fields by manual copying. I am doing a manual copy in order to not force the alignment (or type) of the fields of struct kernel_hwtstamp_config to be the same as of struct hwtstamp_config, even though now, they are the same. Link: https://lore.kernel.org/netdev/20230330223519.36ce7d23@kernel.org/ Signed-off-by: Vladimir Oltean Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/net_tstamp.h | 33 +++++++++++++++++++++++++++++++++ 1 file changed, 33 insertions(+) create mode 100644 include/linux/net_tstamp.h (limited to 'include/linux') diff --git a/include/linux/net_tstamp.h b/include/linux/net_tstamp.h new file mode 100644 index 000000000000..fd67f3cc0c4b --- /dev/null +++ b/include/linux/net_tstamp.h @@ -0,0 +1,33 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef _LINUX_NET_TIMESTAMPING_H_ +#define _LINUX_NET_TIMESTAMPING_H_ + +#include + +/** + * struct kernel_hwtstamp_config - Kernel copy of struct hwtstamp_config + * + * @flags: see struct hwtstamp_config + * @tx_type: see struct hwtstamp_config + * @rx_filter: see struct hwtstamp_config + * + * Prefer using this structure for in-kernel processing of hardware + * timestamping configuration, over the inextensible struct hwtstamp_config + * exposed to the %SIOCGHWTSTAMP and %SIOCSHWTSTAMP ioctl UAPI. + */ +struct kernel_hwtstamp_config { + int flags; + int tx_type; + int rx_filter; +}; + +static inline void hwtstamp_config_to_kernel(struct kernel_hwtstamp_config *kernel_cfg, + const struct hwtstamp_config *cfg) +{ + kernel_cfg->flags = cfg->flags; + kernel_cfg->tx_type = cfg->tx_type; + kernel_cfg->rx_filter = cfg->rx_filter; +} + +#endif /* _LINUX_NET_TIMESTAMPING_H_ */ -- cgit v1.2.3 From 88c0a6b503b7f4fffb68a8d49c3987870c5b1d6b Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Sun, 2 Apr 2023 15:37:55 +0300 Subject: net: create a netdev notifier for DSA to reject PTP on DSA master The fact that PTP 2-step TX timestamping is broken on DSA switches if the master also timestamps the same packets is documented by commit f685e609a301 ("net: dsa: Deny PTP on master if switch supports it"). We attempt to help the users avoid shooting themselves in the foot by making DSA reject the timestamping ioctls on an interface that is a DSA master, and the switch tree beneath it contains switches which are aware of PTP. The only problem is that there isn't an established way of intercepting ndo_eth_ioctl calls, so DSA creates avoidable burden upon the network stack by creating a struct dsa_netdevice_ops with overlaid function pointers that are manually checked from the relevant call sites. There used to be 2 such dsa_netdevice_ops, but now, ndo_eth_ioctl is the only one left. There is an ongoing effort to migrate driver-visible hardware timestamping control from the ndo_eth_ioctl() based API to a new ndo_hwtstamp_set() model, but DSA actively prevents that migration, since dsa_master_ioctl() is currently coded to manually call the master's legacy ndo_eth_ioctl(), and so, whenever a network device driver would be converted to the new API, DSA's restrictions would be circumvented, because any device could be used as a DSA master. The established way for unrelated modules to react on a net device event is via netdevice notifiers. So we create a new notifier which gets called whenever there is an attempt to change hardware timestamping settings on a device. Finally, there is another reason why a netdev notifier will be a good idea, besides strictly DSA, and this has to do with PHY timestamping. With ndo_eth_ioctl(), all MAC drivers must manually call phy_has_hwtstamp() before deciding whether to act upon SIOCSHWTSTAMP, otherwise they must pass this ioctl to the PHY driver via phy_mii_ioctl(). With the new ndo_hwtstamp_set() API, it will be desirable to simply not make any calls into the MAC device driver when timestamping should be performed at the PHY level. But there exist drivers, such as the lan966x switch, which need to install packet traps for PTP regardless of whether they are the layer that provides the hardware timestamps, or the PHY is. That would be impossible to support with the new API. The proposal there, too, is to introduce a netdev notifier which acts as a better cue for switching drivers to add or remove PTP packet traps, than ndo_hwtstamp_set(). The one introduced here "almost" works there as well, except for the fact that packet traps should only be installed if the PHY driver succeeded to enable hardware timestamping, whereas here, we need to deny hardware timestamping on the DSA master before it actually gets enabled. This is why this notifier is called "PRE_", and the notifier that would get used for PHY timestamping and packet traps would be called NETDEV_CHANGE_HWTSTAMP. This isn't a new concept, for example NETDEV_CHANGEUPPER and NETDEV_PRECHANGEUPPER do the same thing. In expectation of future netlink UAPI, we also pass a non-NULL extack pointer to the netdev notifier, and we make DSA populate it with an informative reason for the rejection. To avoid making it go to waste, we make the ioctl-based dev_set_hwtstamp() create a fake extack and print the message to the kernel log. Link: https://lore.kernel.org/netdev/20230401191215.tvveoi3lkawgg6g4@skbuf/ Link: https://lore.kernel.org/netdev/20230310164451.ls7bbs6pdzs4m6pw@skbuf/ Signed-off-by: Vladimir Oltean Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/netdevice.h | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 62e093a6d6d1..a740be3bb911 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2878,6 +2878,7 @@ enum netdev_cmd { NETDEV_OFFLOAD_XSTATS_REPORT_USED, NETDEV_OFFLOAD_XSTATS_REPORT_DELTA, NETDEV_XDP_FEAT_CHANGE, + NETDEV_PRE_CHANGE_HWTSTAMP, }; const char *netdev_cmd_to_name(enum netdev_cmd cmd); @@ -2928,6 +2929,11 @@ struct netdev_notifier_pre_changeaddr_info { const unsigned char *dev_addr; }; +struct netdev_notifier_hwtstamp_info { + struct netdev_notifier_info info; /* must be first */ + struct kernel_hwtstamp_config *config; +}; + enum netdev_offload_xstats_type { NETDEV_OFFLOAD_XSTATS_TYPE_L3 = 1, }; @@ -2984,7 +2990,8 @@ netdev_notifier_info_to_extack(const struct netdev_notifier_info *info) } int call_netdevice_notifiers(unsigned long val, struct net_device *dev); - +int call_netdevice_notifiers_info(unsigned long val, + struct netdev_notifier_info *info); extern rwlock_t dev_base_lock; /* Device list lock */ -- cgit v1.2.3 From 657de1cf258dbe2489906c81bd91e4af536de255 Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Sun, 2 Apr 2023 17:16:56 +0200 Subject: net: phy: smsc: add support for edpd tunable This adds support for the EDPD PHY tunable. Per default EDPD is disabled in interrupt mode, the tunable can be used to override this, e.g. if the link partner doesn't use EDPD. The interval to check for energy can be chosen between 1000ms and 2000ms. Note that this value consists of the 1000ms phylib interval for state machine runs plus the time to wait for energy being detected. v2: - consider that phylib core holds phydev->lock when calling the phy tunable hooks Signed-off-by: Heiner Kallweit Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- include/linux/smscphy.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/smscphy.h b/include/linux/smscphy.h index 80f37c1dba58..e1c88627755a 100644 --- a/include/linux/smscphy.h +++ b/include/linux/smscphy.h @@ -32,6 +32,10 @@ int smsc_phy_config_intr(struct phy_device *phydev); irqreturn_t smsc_phy_handle_interrupt(struct phy_device *phydev); int smsc_phy_config_init(struct phy_device *phydev); int lan87xx_read_status(struct phy_device *phydev); +int smsc_phy_get_tunable(struct phy_device *phydev, + struct ethtool_tunable *tuna, void *data); +int smsc_phy_set_tunable(struct phy_device *phydev, + struct ethtool_tunable *tuna, const void *data); int smsc_phy_probe(struct phy_device *phydev); #endif /* __LINUX_SMSCPHY_H__ */ -- cgit v1.2.3 From 6ae930d9dbf2d093157be33428538c91966d8a9f Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Mon, 27 Mar 2023 20:22:51 +0200 Subject: pid: add pidfd_prepare() Add a new helper that allows to reserve a pidfd and allocates a new pidfd file that stashes the provided struct pid. This will allow us to remove places that either open code this function or that call pidfd_create() but then have to call close_fd() because there are still failure points after pidfd_create() has been called. Reviewed-by: Jan Kara Message-Id: <20230327-pidfd-file-api-v1-1-5c0e9a3158e4@kernel.org> Signed-off-by: Christian Brauner --- include/linux/pid.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pid.h b/include/linux/pid.h index 343abf22092e..b75de288a8c2 100644 --- a/include/linux/pid.h +++ b/include/linux/pid.h @@ -80,6 +80,7 @@ extern struct pid *pidfd_pid(const struct file *file); struct pid *pidfd_get_pid(unsigned int fd, unsigned int *flags); struct task_struct *pidfd_get_task(int pidfd, unsigned int *flags); int pidfd_create(struct pid *pid, unsigned int flags); +int pidfd_prepare(struct pid *pid, unsigned int flags, struct file **ret); static inline struct pid *get_pid(struct pid *pid) { -- cgit v1.2.3 From f98e0640c5c6b8bb00336dae8d06ede862754c28 Mon Sep 17 00:00:00 2001 From: Bastien Nocera Date: Thu, 2 Mar 2023 11:55:53 +0100 Subject: USB: core: Add wireless_status sysfs attribute MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add a wireless_status sysfs attribute to USB devices to keep track of whether a USB device that's comprised of a receiver dongle and an emitter device over a, most of the time proprietary, wireless link has its emitter connected or disconnected. This will be used by user-space OS components to determine whether the battery-powered part of the device is wirelessly connected or not, allowing, for example: - upower to hide the battery for devices where the device is turned off but the receiver plugged in, rather than showing 0%, or other values that could be confusing to users - Pipewire to hide a headset from the list of possible inputs or outputs or route audio appropriately if the headset is suddenly turned off, or turned on - libinput to determine whether a keyboard or mouse is present when its receiver is plugged in. This is done at the USB interface level as: - the interface on which the wireless status is detected is sometimes not the same as where it could be consumed (eg. the audio interface on a headset dongle will still appear even if the headset is turned off), and we cannot have synchronisation of status across subsystems. - this behaviour is not specific to HID devices, even if the protocols used to determine whether or not the remote device is connected can be HID. This is not an attribute that is meant to replace protocol specific APIs, such as the ones available for WWAN, WLAN/Wi-Fi, or Bluetooth or any other sort of networking, but solely for wireless devices with an ad-hoc “lose it and your device is e-waste” receiver dongle. The USB interface will only be exporting the wireless_status sysfs attribute if it gets set through the API exported in the next commit. Signed-off-by: Bastien Nocera Acked-by: Greg Kroah-Hartman Acked-by: Alan Stern Link: https://lore.kernel.org/r/20230302105555.51417-4-hadess@hadess.net Signed-off-by: Benjamin Tissoires --- include/linux/usb.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb.h b/include/linux/usb.h index 9642ee02d713..eee54cc961b4 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -170,6 +170,12 @@ usb_find_last_int_out_endpoint(struct usb_host_interface *alt, return usb_find_common_endpoints_reverse(alt, NULL, NULL, NULL, int_out); } +enum usb_wireless_status { + USB_WIRELESS_STATUS_NA = 0, + USB_WIRELESS_STATUS_DISCONNECTED, + USB_WIRELESS_STATUS_CONNECTED, +}; + /** * struct usb_interface - what usb device drivers talk to * @altsetting: array of interface structures, one for each alternate @@ -203,6 +209,8 @@ usb_find_last_int_out_endpoint(struct usb_host_interface *alt, * @reset_ws: Used for scheduling resets from atomic context. * @resetting_device: USB core reset the device, so use alt setting 0 as * current; needs bandwidth alloc after reset. + * @wireless_status: if the USB device uses a receiver/emitter combo, whether + * the emitter is connected. * * USB device drivers attach to interfaces on a physical device. Each * interface encapsulates a single high level function, such as feeding @@ -253,6 +261,7 @@ struct usb_interface { unsigned needs_binding:1; /* needs delayed unbind/rebind */ unsigned resetting_device:1; /* true: bandwidth alloc after reset */ unsigned authorized:1; /* used for interface authorization */ + enum usb_wireless_status wireless_status; struct device dev; /* interface specific device info */ struct device *usb_dev; -- cgit v1.2.3 From 0a4db185f0788dfc828512d0004c468921bf6c0a Mon Sep 17 00:00:00 2001 From: Bastien Nocera Date: Thu, 2 Mar 2023 11:55:54 +0100 Subject: USB: core: Add API to change the wireless_status This adds the API that allows device specific drivers to tell user-space about whether the wireless device is connected to its receiver dongle. See "USB: core: Add wireless_status sysfs attribute" for a detailed explanation of what this attribute should be used for. Signed-off-by: Bastien Nocera Acked-by: Greg Kroah-Hartman Acked-by: Alan Stern Link: https://lore.kernel.org/r/20230302105555.51417-5-hadess@hadess.net Signed-off-by: Benjamin Tissoires --- include/linux/usb.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb.h b/include/linux/usb.h index eee54cc961b4..6dfd59d3d695 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -262,6 +262,7 @@ struct usb_interface { unsigned resetting_device:1; /* true: bandwidth alloc after reset */ unsigned authorized:1; /* used for interface authorization */ enum usb_wireless_status wireless_status; + struct work_struct wireless_status_work; struct device dev; /* interface specific device info */ struct device *usb_dev; @@ -896,6 +897,10 @@ static inline int usb_interface_claimed(struct usb_interface *iface) extern void usb_driver_release_interface(struct usb_driver *driver, struct usb_interface *iface); + +int usb_set_wireless_status(struct usb_interface *iface, + enum usb_wireless_status status); + const struct usb_device_id *usb_match_id(struct usb_interface *interface, const struct usb_device_id *id); extern int usb_match_one_id(struct usb_interface *interface, -- cgit v1.2.3 From f033c26de5a5734625d2dd1dc196745fae186f1b Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Thu, 30 Mar 2023 01:10:24 +0100 Subject: regmap: Add maple tree based register cache The current state of the art for sparse register maps is the rbtree cache. This works well for most applications but isn't always ideal for sparser register maps since the rbtree can get deep, requiring a lot of walking. Fortunately the kernel has a data structure intended to address this very problem, the maple tree. Provide an initial implementation of a register cache based on the maple tree to start taking advantage of it. The entries stored in the maple tree are arrays of register values, with the maple tree keys holding the register addresses. We store data in host native format rather than device native format as we do for rbtree, this will be a benefit for devices where we don't marshal data within regmap and simplifies the code but will result in additional CPU overhead when syncing the cache on devices where we do marshal data in regmap. This should work well for a lot of devices, though there's some additional areas that could be looked at such as caching the last accessed entry like we do for rbtree and trying to minimise the maple tree level locking. We should also use bulk writes rather than single register writes when resyncing the cache where possible, even if we don't store in device native format. Very small register maps may continue to to better with rbtree longer term. Signed-off-by: Mark Brown Link: https://lore.kernel.org/r/20230325-regcache-maple-v3-2-23e271f93dc7@kernel.org Signed-off-by: Mark Brown --- include/linux/regmap.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index b63204d51b35..4d55ac88ba9e 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -51,6 +51,7 @@ enum regcache_type { REGCACHE_NONE, REGCACHE_RBTREE, REGCACHE_FLAT, + REGCACHE_MAPLE, }; /** -- cgit v1.2.3 From d8aeb44a9ae324c4b823689fabb30b6621d93c88 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 7 Mar 2023 09:40:28 -0700 Subject: fs: add FMODE_DIO_PARALLEL_WRITE flag Some filesystems support multiple threads writing to the same file with O_DIRECT without requiring exclusive access to it. io_uring can use this hint to avoid serializing dio writes to this inode, instead allowing them to run in parallel. XFS and ext4 both fall into this category, so set the flag for both of them. Reviewed-by: Darrick J. Wong Signed-off-by: Jens Axboe --- include/linux/fs.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index c85916e9f7db..475d88640d3d 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -168,6 +168,9 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, #define FMODE_NOREUSE ((__force fmode_t)0x800000) +/* File supports non-exclusive O_DIRECT writes from multiple threads */ +#define FMODE_DIO_PARALLEL_WRITE ((__force fmode_t)0x1000000) + /* File was opened by fanotify and shouldn't generate fanotify events */ #define FMODE_NONOTIFY ((__force fmode_t)0x4000000) -- cgit v1.2.3 From efba1a9e653e107577a48157b5424878c46f2285 Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Thu, 23 Feb 2023 08:43:52 -0800 Subject: io_uring: Move from hlist to io_wq_work_node Having cache entries linked using the hlist format brings no benefit, and also requires an unnecessary extra pointer address per cache entry. Use the internal io_wq_work_node single-linked list for the internal alloc caches (async_msghdr and async_poll) This is required to be able to use KASAN on cache entries, since we do not need to touch unused (and poisoned) cache entries when adding more entries to the list. Suggested-by: Pavel Begunkov Signed-off-by: Breno Leitao Link: https://lore.kernel.org/r/20230223164353.2839177-2-leitao@debian.org Signed-off-by: Jens Axboe --- include/linux/io_uring_types.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h index 00689c12f6ab..757105ebd8af 100644 --- a/include/linux/io_uring_types.h +++ b/include/linux/io_uring_types.h @@ -188,7 +188,7 @@ struct io_ev_fd { }; struct io_alloc_cache { - struct hlist_head list; + struct io_wq_work_node list; unsigned int nr_cached; }; -- cgit v1.2.3 From e1fe7ee885dc0712e982ee465d9f8b96254c30c1 Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Thu, 23 Feb 2023 08:43:53 -0800 Subject: io_uring: Add KASAN support for alloc_caches Add support for KASAN in the alloc_caches (apoll and netmsg_cache). Thus, if something touches the unused caches, it will raise a KASAN warning/exception. It poisons the object when the object is put to the cache, and unpoisons it when the object is gotten or freed. Signed-off-by: Breno Leitao Reviewed-by: Gabriel Krisman Bertazi Link: https://lore.kernel.org/r/20230223164353.2839177-2-leitao@debian.org Signed-off-by: Jens Axboe --- include/linux/io_uring_types.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h index 757105ebd8af..3d152bdcd30a 100644 --- a/include/linux/io_uring_types.h +++ b/include/linux/io_uring_types.h @@ -190,6 +190,7 @@ struct io_ev_fd { struct io_alloc_cache { struct io_wq_work_node list; unsigned int nr_cached; + size_t elem_size; }; struct io_ring_ctx { -- cgit v1.2.3 From a282967c848fb1d92c28334430c472da9c334e54 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Mon, 27 Mar 2023 16:38:15 +0100 Subject: io_uring: encapsulate task_work state For task works we're passing around a bool pointer for whether the current ring is locked or not, let's wrap it in a structure, that will make it more opaque preventing abuse and will also help us to pass more info in the future if needed. Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/1ecec9483d58696e248d1bfd52cf62b04442df1d.1679931367.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- include/linux/io_uring_types.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h index 3d152bdcd30a..561fa421c453 100644 --- a/include/linux/io_uring_types.h +++ b/include/linux/io_uring_types.h @@ -367,6 +367,11 @@ struct io_ring_ctx { unsigned evfd_last_cq_tail; }; +struct io_tw_state { + /* ->uring_lock is taken, callbacks can use io_tw_lock to lock it */ + bool locked; +}; + enum { REQ_F_FIXED_FILE_BIT = IOSQE_FIXED_FILE_BIT, REQ_F_IO_DRAIN_BIT = IOSQE_IO_DRAIN_BIT, @@ -473,7 +478,7 @@ enum { REQ_F_HASH_LOCKED = BIT(REQ_F_HASH_LOCKED_BIT), }; -typedef void (*io_req_tw_func_t)(struct io_kiocb *req, bool *locked); +typedef void (*io_req_tw_func_t)(struct io_kiocb *req, struct io_tw_state *ts); struct io_task_work { struct llist_node node; -- cgit v1.2.3 From ea65b41807a26495ff2a73dd8b1bab2751940887 Mon Sep 17 00:00:00 2001 From: John Keeping Date: Mon, 27 Mar 2023 18:36:46 +0100 Subject: ftrace: Mark get_lock_parent_ip() __always_inline If the compiler decides not to inline this function then preemption tracing will always show an IP inside the preemption disabling path and never the function actually calling preempt_{enable,disable}. Link: https://lore.kernel.org/linux-trace-kernel/20230327173647.1690849-1-john@metanate.com Cc: Masami Hiramatsu Cc: Mark Rutland Cc: stable@vger.kernel.org Fixes: f904f58263e1d ("sched/debug: Fix preempt_disable_ip recording for preempt_disable()") Signed-off-by: John Keeping Signed-off-by: Steven Rostedt (Google) --- include/linux/ftrace.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 366c730beaa3..402fc061de75 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -980,7 +980,7 @@ static inline void __ftrace_enabled_restore(int enabled) #define CALLER_ADDR5 ((unsigned long)ftrace_return_address(5)) #define CALLER_ADDR6 ((unsigned long)ftrace_return_address(6)) -static inline unsigned long get_lock_parent_ip(void) +static __always_inline unsigned long get_lock_parent_ip(void) { unsigned long addr = CALLER_ADDR0; -- cgit v1.2.3 From d74c36480a679b27ce8a70c2e88fed31b86323d9 Mon Sep 17 00:00:00 2001 From: Chuanhong Guo Date: Wed, 29 Mar 2023 14:42:40 +0300 Subject: mtd: spinand: add support for ESMT F50x1G41LB This patch adds support for ESMT F50L1G41LB and F50D1G41LB. It seems that ESMT likes to use random JEDEC ID from other vendors. Their 1G chips uses 0xc8 from GigaDevice and 2G/4G chips uses 0x2c from Micron. For this reason, the ESMT entry is named esmt_c8 with explicit JEDEC ID in variable name. Datasheets: https://www.esmt.com.tw/upload/pdf/ESMT/datasheets/F50L1G41LB(2M).pdf https://www.esmt.com.tw/upload/pdf/ESMT/datasheets/F50D1G41LB(2M).pdf Signed-off-by: Chuanhong Guo Signed-off-by: Martin Kurbanov Signed-off-by: Dmitry Rokosov Tested-by: Martin Kurbanov Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20230329114240.378722-1-mmkurbanov@sberdevices.ru --- include/linux/mtd/spinand.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mtd/spinand.h b/include/linux/mtd/spinand.h index 01be9f0f008a..3e285c09d16d 100644 --- a/include/linux/mtd/spinand.h +++ b/include/linux/mtd/spinand.h @@ -262,6 +262,7 @@ struct spinand_manufacturer { /* SPI NAND manufacturers */ extern const struct spinand_manufacturer alliancememory_spinand_manufacturer; extern const struct spinand_manufacturer ato_spinand_manufacturer; +extern const struct spinand_manufacturer esmt_c8_spinand_manufacturer; extern const struct spinand_manufacturer gigadevice_spinand_manufacturer; extern const struct spinand_manufacturer macronix_spinand_manufacturer; extern const struct spinand_manufacturer micron_spinand_manufacturer; -- cgit v1.2.3 From 979207cac517833c828133ffb2633bcdf6edce00 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Sun, 2 Apr 2023 19:58:46 +0200 Subject: driver core: class: mark class_release() as taking a const * The struct class callback, class_release(), is only called in 2 places, the pcmcia cardservices code, and in the class driver core code. Both places it is safe to mark the structure as a const *, to allow us to in the future mark all struct class usages as constant and move into read-only memory. Acked-by: Rafael J. Wysocki Link: https://lore.kernel.org/r/2023040248-outrage-obsolete-5a9a@gregkh Signed-off-by: Greg Kroah-Hartman --- include/linux/device/class.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/device/class.h b/include/linux/device/class.h index 7e4a1a6329f4..f3c418fa129a 100644 --- a/include/linux/device/class.h +++ b/include/linux/device/class.h @@ -58,7 +58,7 @@ struct class { int (*dev_uevent)(const struct device *dev, struct kobj_uevent_env *env); char *(*devnode)(const struct device *dev, umode_t *mode); - void (*class_release)(struct class *class); + void (*class_release)(const struct class *class); void (*dev_release)(struct device *dev); int (*shutdown_pre)(struct device *dev); -- cgit v1.2.3 From 43a7206b0963c2153c95d6985624d1dc1b3abd4d Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Sun, 2 Apr 2023 19:58:47 +0200 Subject: driver core: class: make class_register() take a const * Now that the class code is cleaned up to not modify the class pointer registered with it, change class_register() to take a const * to allow the structure to be placed into read-only memory. Acked-by: Rafael J. Wysocki Link: https://lore.kernel.org/r/2023040248-customary-release-4aec@gregkh Signed-off-by: Greg Kroah-Hartman --- include/linux/device/class.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/device/class.h b/include/linux/device/class.h index f3c418fa129a..4bf46f9bbb56 100644 --- a/include/linux/device/class.h +++ b/include/linux/device/class.h @@ -76,7 +76,7 @@ struct class_dev_iter { const struct device_type *type; }; -int __must_check class_register(struct class *class); +int __must_check class_register(const struct class *class); void class_unregister(const struct class *class); bool class_is_registered(const struct class *class); -- cgit v1.2.3 From 6b0d49be81cf4f1cf30ebd079cbf4643cab0a01d Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Sun, 2 Apr 2023 19:58:48 +0200 Subject: driver core: class: mark the struct class in struct class_interface constant The struct class pointer in struct class_interface is never modified, so mark it as const so that no one accidentally tries to modify it in the future. Acked-by: Rafael J. Wysocki Link: https://lore.kernel.org/r/2023040249-handball-gruffly-5da7@gregkh Signed-off-by: Greg Kroah-Hartman --- include/linux/device/class.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/device/class.h b/include/linux/device/class.h index 4bf46f9bbb56..53287aa105b8 100644 --- a/include/linux/device/class.h +++ b/include/linux/device/class.h @@ -217,7 +217,7 @@ ssize_t show_class_attr_string(const struct class *class, const struct class_att struct class_interface { struct list_head node; - struct class *class; + const struct class *class; int (*add_dev) (struct device *, struct class_interface *); void (*remove_dev) (struct device *, struct class_interface *); -- cgit v1.2.3 From 2243acd50ac4026e93ac4f024109be6dbd7f9098 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Sun, 2 Apr 2023 19:58:49 +0200 Subject: driver core: class: remove struct class_interface * from callbacks The add_dev and remove_dev callbacks in struct class_interface currently pass in a pointer back to the class_interface structure that is calling them, but none of the callback implementations actually use this pointer as it is pointless (the structure is known, the driver passed it in in the first place if it is really needed again.) So clean this up and just remove the pointer from the callbacks and fix up all callback functions. Cc: Jean Delvare Cc: Guenter Roeck Cc: "David S. Miller" Cc: Eric Dumazet Cc: Jakub Kicinski Cc: Paolo Abeni Cc: Kurt Schwemmer Cc: Jon Mason Cc: Dave Jiang Cc: Allen Hubbe Cc: Dominik Brodowski Cc: Matt Porter Cc: Alexandre Bounine Cc: "James E.J. Bottomley" Cc: "Martin K. Petersen" Cc: Doug Gilbert Cc: John Stultz Cc: Thomas Gleixner Cc: Stephen Boyd Cc: Hans de Goede Cc: Andrew Morton Cc: Wang Weiyang Cc: Yang Yingliang Cc: Jakob Koschel Cc: Cai Xinchen Acked-by: Rafael J. Wysocki Acked-by: Logan Gunthorpe Link: https://lore.kernel.org/r/2023040250-pushover-platter-509c@gregkh Signed-off-by: Greg Kroah-Hartman --- include/linux/device/class.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/device/class.h b/include/linux/device/class.h index 53287aa105b8..9deeaeb457bb 100644 --- a/include/linux/device/class.h +++ b/include/linux/device/class.h @@ -219,8 +219,8 @@ struct class_interface { struct list_head node; const struct class *class; - int (*add_dev) (struct device *, struct class_interface *); - void (*remove_dev) (struct device *, struct class_interface *); + int (*add_dev) (struct device *dev); + void (*remove_dev) (struct device *dev); }; int __must_check class_interface_register(struct class_interface *); -- cgit v1.2.3 From 862d8312eed994a8a9af7aa8e9e15456183b10a7 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Sun, 2 Apr 2023 19:58:50 +0200 Subject: tty: make tty_class a static const structure MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Now that the driver core allows for struct class to be in read-only memory, move the tty_class structure to be declared at build time placing it into read-only memory, instead of having to be dynamically allocated at boot time. Cc: "Ilpo Järvinen" Reviewed-by: Jiri Slaby Link: https://lore.kernel.org/r/2023040250-landowner-unfitted-11f4@gregkh Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index 093935e97f42..121eb4b0d325 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -387,7 +387,7 @@ extern struct ktermios tty_std_termios; int vcs_init(void); -extern struct class *tty_class; +extern const struct class tty_class; /** * tty_kref_get - get a tty reference -- cgit v1.2.3 From 7fe1b00d92eaceb83f95200b5114cf5df0919892 Mon Sep 17 00:00:00 2001 From: Tudor Ambarus Date: Fri, 31 Mar 2023 07:46:03 +0000 Subject: mtd: spi-nor: Stop exporting spi_nor_restore() Some SPI NOR controllers that used this method were moved to drivers/spi/. We don't accept new support for the existing SPI NOR controllers drivers under drivers/mtd/spi-nor/controllers/ and we encourage their owners to move the drivers under drivers/spi/. Make spi_nor_restore() private as we're going to use it just in core.c. Link: https://lore.kernel.org/r/20230331074606.3559258-8-tudor.ambarus@linaro.org Signed-off-by: Tudor Ambarus --- include/linux/mtd/spi-nor.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h index 82547b4b3708..cdcfe0fd2e7d 100644 --- a/include/linux/mtd/spi-nor.h +++ b/include/linux/mtd/spi-nor.h @@ -450,10 +450,4 @@ static inline struct device_node *spi_nor_get_flash_node(struct spi_nor *nor) int spi_nor_scan(struct spi_nor *nor, const char *name, const struct spi_nor_hwcaps *hwcaps); -/** - * spi_nor_restore_addr_mode() - restore the status of SPI NOR - * @nor: the spi_nor structure - */ -void spi_nor_restore(struct spi_nor *nor); - #endif -- cgit v1.2.3 From 8e15c0e71b8ae64fb7163532860f8d608165281f Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Tue, 4 Apr 2023 13:39:46 +0100 Subject: io_uring/rsrc: keep cached refs per node We cache refs of the current node (i.e. ctx->rsrc_node) in ctx->rsrc_cached_refs. We'll be moving away from atomics, so move the cached refs in struct io_rsrc_node for now. It's a prep patch and shouldn't change anything in practise. Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/9edc3669c1d71b06c2dca78b2b2b8bb9292738b9.1680576071.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- include/linux/io_uring_types.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h index 561fa421c453..a0a5b5964d3a 100644 --- a/include/linux/io_uring_types.h +++ b/include/linux/io_uring_types.h @@ -240,7 +240,6 @@ struct io_ring_ctx { * uring_lock, and updated through io_uring_register(2) */ struct io_rsrc_node *rsrc_node; - int rsrc_cached_refs; atomic_t cancel_seq; struct io_file_table file_table; unsigned nr_user_files; -- cgit v1.2.3 From 0a4813b1abdf06e44ce60cdebfd374cfd27c46bf Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Tue, 4 Apr 2023 13:39:50 +0100 Subject: io_uring/rsrc: kill rsrc_ref_lock We use ->rsrc_ref_lock spinlock to protect ->rsrc_ref_list in io_rsrc_node_ref_zero(). Now we removed pcpu refcounting, which means io_rsrc_node_ref_zero() is not executed from the irq context as an RCU callback anymore, and we also put it under ->uring_lock. io_rsrc_node_switch(), which queues up nodes into the list, is also protected by ->uring_lock, so we can safely get rid of ->rsrc_ref_lock. Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/6b60af883c263551190b526a55ff2c9d5ae07141.1680576071.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- include/linux/io_uring_types.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h index a0a5b5964d3a..9492889f00c0 100644 --- a/include/linux/io_uring_types.h +++ b/include/linux/io_uring_types.h @@ -333,8 +333,8 @@ struct io_ring_ctx { struct delayed_work rsrc_put_work; struct callback_head rsrc_put_tw; struct llist_head rsrc_put_llist; + /* protected by ->uring_lock */ struct list_head rsrc_ref_list; - spinlock_t rsrc_ref_lock; struct list_head io_buffers_pages; -- cgit v1.2.3 From 36b9818a5a84cb7c977fb723babca1c8d74f288f Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Tue, 4 Apr 2023 13:39:53 +0100 Subject: io_uring/rsrc: don't offload node free struct delayed_work rsrc_put_work was previously used to offload node freeing because io_rsrc_node_ref_zero() was previously called by RCU in the IRQ context. Now, as percpu refcounting is gone, we can do it eagerly at the spot without pushing it to a worker. Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/13fb1aac1e8d068ad8fd4a0c6d0d157ab61b90c0.1680576071.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- include/linux/io_uring_types.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h index 9492889f00c0..47496059e13a 100644 --- a/include/linux/io_uring_types.h +++ b/include/linux/io_uring_types.h @@ -330,9 +330,6 @@ struct io_ring_ctx { struct io_rsrc_data *file_data; struct io_rsrc_data *buf_data; - struct delayed_work rsrc_put_work; - struct callback_head rsrc_put_tw; - struct llist_head rsrc_put_llist; /* protected by ->uring_lock */ struct list_head rsrc_ref_list; -- cgit v1.2.3 From 9eae8655f9cd2eeed99fb7a0d2bb22816c17e497 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Tue, 4 Apr 2023 13:39:54 +0100 Subject: io_uring/rsrc: cache struct io_rsrc_node Add allocation cache for struct io_rsrc_node, it's always allocated and put under ->uring_lock, so it doesn't need any extra synchronisation around caches. Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/252a9d9ef9654e6467af30fdc02f57c0118fb76e.1680576071.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- include/linux/io_uring_types.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h index 47496059e13a..5d772e36e7fc 100644 --- a/include/linux/io_uring_types.h +++ b/include/linux/io_uring_types.h @@ -332,6 +332,7 @@ struct io_ring_ctx { /* protected by ->uring_lock */ struct list_head rsrc_ref_list; + struct io_alloc_cache rsrc_node_cache; struct list_head io_buffers_pages; -- cgit v1.2.3 From 69bbc6ade9d9d4e3c556cb83e77b6f3cd9ad3d18 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Tue, 4 Apr 2023 13:39:57 +0100 Subject: io_uring/rsrc: add custom limit for node caching The number of entries in the rsrc node cache is limited to 512, which still seems unnecessarily large. Add per cache thresholds and set to to 32 for the rsrc node cache. Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/d0cd538b944dac0bf878e276fc0199f21e6bccea.1680576071.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- include/linux/io_uring_types.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h index 5d772e36e7fc..4a6ce03a4903 100644 --- a/include/linux/io_uring_types.h +++ b/include/linux/io_uring_types.h @@ -190,6 +190,7 @@ struct io_ev_fd { struct io_alloc_cache { struct io_wq_work_node list; unsigned int nr_cached; + unsigned int max_cached; size_t elem_size; }; -- cgit v1.2.3 From 3e67cb8a3c6251c86e5d058d8ee4e1909bc25af0 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Fri, 17 Mar 2023 08:06:56 -0700 Subject: srcu: Add whitespace to __SRCU_STRUCT_INIT() & __DEFINE_SRCU() This is a whitespace-only commit with no change in functionality. Its purpose is to prepare for later commits that: (1) Cause statically allocated srcu_struct structures to rely on compile-time initialization and (2) Move fields from the srcu_struct structure to a new srcu_usage structure. Cc: Christoph Hellwig Tested-by: Sachin Sant Tested-by: "Zhang, Qiang1" Tested-by: Joel Fernandes (Google) Signed-off-by: Paul E. McKenney --- include/linux/srcutree.h | 28 ++++++++++++++-------------- 1 file changed, 14 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/srcutree.h b/include/linux/srcutree.h index 558057b517b7..488d0e5d1ba3 100644 --- a/include/linux/srcutree.h +++ b/include/linux/srcutree.h @@ -108,13 +108,13 @@ struct srcu_struct { #define SRCU_STATE_SCAN1 1 #define SRCU_STATE_SCAN2 2 -#define __SRCU_STRUCT_INIT(name, pcpu_name) \ -{ \ - .sda = &pcpu_name, \ - .lock = __SPIN_LOCK_UNLOCKED(name.lock), \ - .srcu_gp_seq_needed = -1UL, \ - .work = __DELAYED_WORK_INITIALIZER(name.work, NULL, 0), \ - __SRCU_DEP_MAP_INIT(name) \ +#define __SRCU_STRUCT_INIT(name, pcpu_name) \ +{ \ + .sda = &pcpu_name, \ + .lock = __SPIN_LOCK_UNLOCKED(name.lock), \ + .srcu_gp_seq_needed = -1UL, \ + .work = __DELAYED_WORK_INITIALIZER(name.work, NULL, 0), \ + __SRCU_DEP_MAP_INIT(name) \ } /* @@ -137,15 +137,15 @@ struct srcu_struct { * See include/linux/percpu-defs.h for the rules on per-CPU variables. */ #ifdef MODULE -# define __DEFINE_SRCU(name, is_static) \ - is_static struct srcu_struct name; \ - extern struct srcu_struct * const __srcu_struct_##name; \ - struct srcu_struct * const __srcu_struct_##name \ +# define __DEFINE_SRCU(name, is_static) \ + is_static struct srcu_struct name; \ + extern struct srcu_struct * const __srcu_struct_##name; \ + struct srcu_struct * const __srcu_struct_##name \ __section("___srcu_struct_ptrs") = &name #else -# define __DEFINE_SRCU(name, is_static) \ - static DEFINE_PER_CPU(struct srcu_data, name##_srcu_data); \ - is_static struct srcu_struct name = \ +# define __DEFINE_SRCU(name, is_static) \ + static DEFINE_PER_CPU(struct srcu_data, name##_srcu_data); \ + is_static struct srcu_struct name = \ __SRCU_STRUCT_INIT(name, name##_srcu_data) #endif #define DEFINE_SRCU(name) __DEFINE_SRCU(name, /* not static */) -- cgit v1.2.3 From f4d01a259374ef358cd6b00a96b4dfc0fb05a844 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Fri, 17 Mar 2023 13:28:04 -0700 Subject: srcu: Use static init for statically allocated in-module srcu_struct Further shrinking the srcu_struct structure is eased by requiring that in-module srcu_struct structures rely more heavily on static initialization. In particular, this preserves the property that a module-load-time srcu_struct initialization can fail only due to memory-allocation failure of the per-CPU srcu_data structures. It might also slightly improve robustness by keeping the number of memory allocations that must succeed down percpu_alloc() call. This is in preparation for splitting an srcu_usage structure out of the srcu_struct structure. [ paulmck: Fold in qiang1.zhang@intel.com feedback. ] Cc: Christoph Hellwig Tested-by: Sachin Sant Tested-by: "Zhang, Qiang1" Tested-by: Joel Fernandes (Google) Signed-off-by: Paul E. McKenney --- include/linux/srcutree.h | 19 ++++++++++++++----- 1 file changed, 14 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/srcutree.h b/include/linux/srcutree.h index 488d0e5d1ba3..3ce6deee1dbe 100644 --- a/include/linux/srcutree.h +++ b/include/linux/srcutree.h @@ -108,15 +108,24 @@ struct srcu_struct { #define SRCU_STATE_SCAN1 1 #define SRCU_STATE_SCAN2 2 -#define __SRCU_STRUCT_INIT(name, pcpu_name) \ -{ \ - .sda = &pcpu_name, \ +#define __SRCU_STRUCT_INIT_COMMON(name) \ .lock = __SPIN_LOCK_UNLOCKED(name.lock), \ .srcu_gp_seq_needed = -1UL, \ .work = __DELAYED_WORK_INITIALIZER(name.work, NULL, 0), \ - __SRCU_DEP_MAP_INIT(name) \ + __SRCU_DEP_MAP_INIT(name) + +#define __SRCU_STRUCT_INIT_MODULE(name) \ +{ \ + __SRCU_STRUCT_INIT_COMMON(name) \ } +#define __SRCU_STRUCT_INIT(name, pcpu_name) \ +{ \ + .sda = &pcpu_name, \ + __SRCU_STRUCT_INIT_COMMON(name) \ +} + + /* * Define and initialize a srcu struct at build time. * Do -not- call init_srcu_struct() nor cleanup_srcu_struct() on it. @@ -138,7 +147,7 @@ struct srcu_struct { */ #ifdef MODULE # define __DEFINE_SRCU(name, is_static) \ - is_static struct srcu_struct name; \ + is_static struct srcu_struct name = __SRCU_STRUCT_INIT_MODULE(name); \ extern struct srcu_struct * const __srcu_struct_##name; \ struct srcu_struct * const __srcu_struct_##name \ __section("___srcu_struct_ptrs") = &name -- cgit v1.2.3 From 95433f7263011e0e6e83caef85d98896dd99cab7 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 16 Mar 2023 17:58:51 -0700 Subject: srcu: Begin offloading srcu_struct fields to srcu_update MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The current srcu_struct structure is on the order of 200 bytes in size (depending on architecture and .config), which is much better than the old-style 26K bytes, but still all too inconvenient when one is trying to achieve good cache locality on a fastpath involving SRCU readers. However, only a few fields in srcu_struct are used by SRCU readers. The remaining fields could be offloaded to a new srcu_update structure, thus shrinking the srcu_struct structure down to a few tens of bytes. This commit begins this noble quest, a quest that is complicated by open-coded initialization of the srcu_struct within the srcu_notifier_head structure. This complication is addressed by updating the srcu_notifier_head structure's open coding, given that there does not appear to be a straightforward way of abstracting that initialization. This commit moves only the ->node pointer to srcu_update. Later commits will move additional fields. [ paulmck: Fold in qiang1.zhang@intel.com's memory-leak fix. ] Link: https://lore.kernel.org/all/20230320055751.4120251-1-qiang1.zhang@intel.com/ Suggested-by: Christoph Hellwig Cc: "Rafael J. Wysocki" Cc: "Michał Mirosław" Cc: Dmitry Osipenko Tested-by: Sachin Sant Tested-by: "Zhang, Qiang1" Acked-by: Rafael J. Wysocki Tested-by: Joel Fernandes (Google) Signed-off-by: Paul E. McKenney --- include/linux/notifier.h | 5 ++++- include/linux/srcutiny.h | 6 +++--- include/linux/srcutree.h | 27 ++++++++++++++++++--------- 3 files changed, 25 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/notifier.h b/include/linux/notifier.h index aef88c2d1173..2aba75145144 100644 --- a/include/linux/notifier.h +++ b/include/linux/notifier.h @@ -73,6 +73,9 @@ struct raw_notifier_head { struct srcu_notifier_head { struct mutex mutex; +#ifdef CONFIG_TREE_SRCU + struct srcu_usage srcuu; +#endif struct srcu_struct srcu; struct notifier_block __rcu *head; }; @@ -107,7 +110,7 @@ extern void srcu_init_notifier_head(struct srcu_notifier_head *nh); { \ .mutex = __MUTEX_INITIALIZER(name.mutex), \ .head = NULL, \ - .srcu = __SRCU_STRUCT_INIT(name.srcu, pcpu), \ + .srcu = __SRCU_STRUCT_INIT(name.srcu, name.srcuu, pcpu), \ } #define ATOMIC_NOTIFIER_HEAD(name) \ diff --git a/include/linux/srcutiny.h b/include/linux/srcutiny.h index 5aa5e0faf6a1..ebd72491af99 100644 --- a/include/linux/srcutiny.h +++ b/include/linux/srcutiny.h @@ -31,7 +31,7 @@ struct srcu_struct { void srcu_drive_gp(struct work_struct *wp); -#define __SRCU_STRUCT_INIT(name, __ignored) \ +#define __SRCU_STRUCT_INIT(name, __ignored, ___ignored) \ { \ .srcu_wq = __SWAIT_QUEUE_HEAD_INITIALIZER(name.srcu_wq), \ .srcu_cb_tail = &name.srcu_cb_head, \ @@ -44,9 +44,9 @@ void srcu_drive_gp(struct work_struct *wp); * Tree SRCU, which needs some per-CPU data. */ #define DEFINE_SRCU(name) \ - struct srcu_struct name = __SRCU_STRUCT_INIT(name, name) + struct srcu_struct name = __SRCU_STRUCT_INIT(name, name, name) #define DEFINE_STATIC_SRCU(name) \ - static struct srcu_struct name = __SRCU_STRUCT_INIT(name, name) + static struct srcu_struct name = __SRCU_STRUCT_INIT(name, name, name) void synchronize_srcu(struct srcu_struct *ssp); diff --git a/include/linux/srcutree.h b/include/linux/srcutree.h index 3ce6deee1dbe..276f325f1296 100644 --- a/include/linux/srcutree.h +++ b/include/linux/srcutree.h @@ -57,11 +57,17 @@ struct srcu_node { int grphi; /* Biggest CPU for node. */ }; +/* + * Per-SRCU-domain structure, update-side data linked from srcu_struct. + */ +struct srcu_usage { + struct srcu_node *node; /* Combining tree. */ +}; + /* * Per-SRCU-domain structure, similar in function to rcu_state. */ struct srcu_struct { - struct srcu_node *node; /* Combining tree. */ struct srcu_node *level[RCU_NUM_LVLS + 1]; /* First node at each level. */ int srcu_size_state; /* Small-to-big transition state. */ @@ -90,6 +96,7 @@ struct srcu_struct { unsigned long reschedule_count; struct delayed_work work; struct lockdep_map dep_map; + struct srcu_usage *srcu_sup; /* Update-side data. */ }; /* Values for size state variable (->srcu_size_state). */ @@ -108,24 +115,24 @@ struct srcu_struct { #define SRCU_STATE_SCAN1 1 #define SRCU_STATE_SCAN2 2 -#define __SRCU_STRUCT_INIT_COMMON(name) \ +#define __SRCU_STRUCT_INIT_COMMON(name, usage_name) \ .lock = __SPIN_LOCK_UNLOCKED(name.lock), \ .srcu_gp_seq_needed = -1UL, \ .work = __DELAYED_WORK_INITIALIZER(name.work, NULL, 0), \ + .srcu_sup = &usage_name, \ __SRCU_DEP_MAP_INIT(name) -#define __SRCU_STRUCT_INIT_MODULE(name) \ +#define __SRCU_STRUCT_INIT_MODULE(name, usage_name) \ { \ - __SRCU_STRUCT_INIT_COMMON(name) \ + __SRCU_STRUCT_INIT_COMMON(name, usage_name) \ } -#define __SRCU_STRUCT_INIT(name, pcpu_name) \ +#define __SRCU_STRUCT_INIT(name, usage_name, pcpu_name) \ { \ .sda = &pcpu_name, \ - __SRCU_STRUCT_INIT_COMMON(name) \ + __SRCU_STRUCT_INIT_COMMON(name, usage_name) \ } - /* * Define and initialize a srcu struct at build time. * Do -not- call init_srcu_struct() nor cleanup_srcu_struct() on it. @@ -147,15 +154,17 @@ struct srcu_struct { */ #ifdef MODULE # define __DEFINE_SRCU(name, is_static) \ - is_static struct srcu_struct name = __SRCU_STRUCT_INIT_MODULE(name); \ + static struct srcu_usage name##_srcu_usage; \ + is_static struct srcu_struct name = __SRCU_STRUCT_INIT_MODULE(name, name##_srcu_usage); \ extern struct srcu_struct * const __srcu_struct_##name; \ struct srcu_struct * const __srcu_struct_##name \ __section("___srcu_struct_ptrs") = &name #else # define __DEFINE_SRCU(name, is_static) \ static DEFINE_PER_CPU(struct srcu_data, name##_srcu_data); \ + static struct srcu_usage name##_srcu_usage; \ is_static struct srcu_struct name = \ - __SRCU_STRUCT_INIT(name, name##_srcu_data) + __SRCU_STRUCT_INIT(name, name##_srcu_usage, name##_srcu_data) #endif #define DEFINE_SRCU(name) __DEFINE_SRCU(name, /* not static */) #define DEFINE_STATIC_SRCU(name) __DEFINE_SRCU(name, static) -- cgit v1.2.3 From 208f41b1312443401353bec0c1939e2bfc28adce Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Fri, 17 Mar 2023 14:43:08 -0700 Subject: srcu: Move ->level from srcu_struct to srcu_usage This commit moves the ->level[] array from the srcu_struct structure to the srcu_usage structure to reduce the size of the former in order to improve cache locality. Suggested-by: Christoph Hellwig Tested-by: Sachin Sant Tested-by: "Zhang, Qiang1" Tested-by: Joel Fernandes (Google) Signed-off-by: Paul E. McKenney --- include/linux/srcutree.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/srcutree.h b/include/linux/srcutree.h index 276f325f1296..c7373fe5c14b 100644 --- a/include/linux/srcutree.h +++ b/include/linux/srcutree.h @@ -62,14 +62,14 @@ struct srcu_node { */ struct srcu_usage { struct srcu_node *node; /* Combining tree. */ + struct srcu_node *level[RCU_NUM_LVLS + 1]; + /* First node at each level. */ }; /* * Per-SRCU-domain structure, similar in function to rcu_state. */ struct srcu_struct { - struct srcu_node *level[RCU_NUM_LVLS + 1]; - /* First node at each level. */ int srcu_size_state; /* Small-to-big transition state. */ struct mutex srcu_cb_mutex; /* Serialize CB preparation. */ spinlock_t __private lock; /* Protect counters and size state. */ -- cgit v1.2.3 From a0d8cbd3821369dc9478cabd605417afb9eb24dc Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Fri, 17 Mar 2023 17:16:30 -0700 Subject: srcu: Move ->srcu_size_state from srcu_struct to srcu_usage This commit moves the ->srcu_size_state field from the srcu_struct structure to the srcu_usage structure to reduce the size of the former in order to improve cache locality. Suggested-by: Christoph Hellwig Tested-by: Sachin Sant Tested-by: "Zhang, Qiang1" Tested-by: Joel Fernandes (Google) Signed-off-by: Paul E. McKenney --- include/linux/srcutree.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/srcutree.h b/include/linux/srcutree.h index c7373fe5c14b..443d27a214ef 100644 --- a/include/linux/srcutree.h +++ b/include/linux/srcutree.h @@ -64,13 +64,13 @@ struct srcu_usage { struct srcu_node *node; /* Combining tree. */ struct srcu_node *level[RCU_NUM_LVLS + 1]; /* First node at each level. */ + int srcu_size_state; /* Small-to-big transition state. */ }; /* * Per-SRCU-domain structure, similar in function to rcu_state. */ struct srcu_struct { - int srcu_size_state; /* Small-to-big transition state. */ struct mutex srcu_cb_mutex; /* Serialize CB preparation. */ spinlock_t __private lock; /* Protect counters and size state. */ struct mutex srcu_gp_mutex; /* Serialize GP work. */ -- cgit v1.2.3 From 574dc1a7efe490dffe5c1ce0285306feec16a880 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Fri, 17 Mar 2023 17:22:27 -0700 Subject: srcu: Move ->srcu_cb_mutex from srcu_struct to srcu_usage This commit moves the ->srcu_cb_mutex field from the srcu_struct structure to the srcu_usage structure to reduce the size of the former in order to improve cache locality. Suggested-by: Christoph Hellwig Tested-by: Sachin Sant Tested-by: "Zhang, Qiang1" Tested-by: Joel Fernandes (Google) Signed-off-by: Paul E. McKenney --- include/linux/srcutree.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/srcutree.h b/include/linux/srcutree.h index 443d27a214ef..231de66ceb15 100644 --- a/include/linux/srcutree.h +++ b/include/linux/srcutree.h @@ -65,13 +65,13 @@ struct srcu_usage { struct srcu_node *level[RCU_NUM_LVLS + 1]; /* First node at each level. */ int srcu_size_state; /* Small-to-big transition state. */ + struct mutex srcu_cb_mutex; /* Serialize CB preparation. */ }; /* * Per-SRCU-domain structure, similar in function to rcu_state. */ struct srcu_struct { - struct mutex srcu_cb_mutex; /* Serialize CB preparation. */ spinlock_t __private lock; /* Protect counters and size state. */ struct mutex srcu_gp_mutex; /* Serialize GP work. */ unsigned int srcu_idx; /* Current rdr array element. */ -- cgit v1.2.3 From b3fb11f7e9c3c64dd86403409a070c996d8ac081 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Fri, 17 Mar 2023 18:29:38 -0700 Subject: srcu: Move ->lock from srcu_struct to srcu_usage This commit moves the ->lock field from the srcu_struct structure to the srcu_usage structure to reduce the size of the former in order to improve cache locality. Suggested-by: Christoph Hellwig Tested-by: Sachin Sant Tested-by: "Zhang, Qiang1" Tested-by: Joel Fernandes (Google) Signed-off-by: Paul E. McKenney --- include/linux/srcutree.h | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/srcutree.h b/include/linux/srcutree.h index 231de66ceb15..694d87b81917 100644 --- a/include/linux/srcutree.h +++ b/include/linux/srcutree.h @@ -66,13 +66,13 @@ struct srcu_usage { /* First node at each level. */ int srcu_size_state; /* Small-to-big transition state. */ struct mutex srcu_cb_mutex; /* Serialize CB preparation. */ + spinlock_t __private lock; /* Protect counters and size state. */ }; /* * Per-SRCU-domain structure, similar in function to rcu_state. */ struct srcu_struct { - spinlock_t __private lock; /* Protect counters and size state. */ struct mutex srcu_gp_mutex; /* Serialize GP work. */ unsigned int srcu_idx; /* Current rdr array element. */ unsigned long srcu_gp_seq; /* Grace-period seq #. */ @@ -116,7 +116,6 @@ struct srcu_struct { #define SRCU_STATE_SCAN2 2 #define __SRCU_STRUCT_INIT_COMMON(name, usage_name) \ - .lock = __SPIN_LOCK_UNLOCKED(name.lock), \ .srcu_gp_seq_needed = -1UL, \ .work = __DELAYED_WORK_INITIALIZER(name.work, NULL, 0), \ .srcu_sup = &usage_name, \ @@ -154,7 +153,9 @@ struct srcu_struct { */ #ifdef MODULE # define __DEFINE_SRCU(name, is_static) \ - static struct srcu_usage name##_srcu_usage; \ + static struct srcu_usage name##_srcu_usage = { \ + .lock = __SPIN_LOCK_UNLOCKED(name.lock), \ + }; \ is_static struct srcu_struct name = __SRCU_STRUCT_INIT_MODULE(name, name##_srcu_usage); \ extern struct srcu_struct * const __srcu_struct_##name; \ struct srcu_struct * const __srcu_struct_##name \ @@ -162,7 +163,9 @@ struct srcu_struct { #else # define __DEFINE_SRCU(name, is_static) \ static DEFINE_PER_CPU(struct srcu_data, name##_srcu_data); \ - static struct srcu_usage name##_srcu_usage; \ + static struct srcu_usage name##_srcu_usage = { \ + .lock = __SPIN_LOCK_UNLOCKED(name.lock), \ + }; \ is_static struct srcu_struct name = \ __SRCU_STRUCT_INIT(name, name##_srcu_usage, name##_srcu_data) #endif -- cgit v1.2.3 From e3a6ab25cfa0fcdcb31c346b9871a566d440980d Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Fri, 17 Mar 2023 19:13:16 -0700 Subject: srcu: Move ->srcu_gp_mutex from srcu_struct to srcu_usage This commit moves the ->srcu_gp_mutex field from the srcu_struct structure to the srcu_usage structure to reduce the size of the former in order to improve cache locality. Suggested-by: Christoph Hellwig Tested-by: Sachin Sant Tested-by: "Zhang, Qiang1" Tested-by: Joel Fernandes (Google) Signed-off-by: Paul E. McKenney --- include/linux/srcutree.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/srcutree.h b/include/linux/srcutree.h index 694d87b81917..d04e3da6181c 100644 --- a/include/linux/srcutree.h +++ b/include/linux/srcutree.h @@ -67,13 +67,13 @@ struct srcu_usage { int srcu_size_state; /* Small-to-big transition state. */ struct mutex srcu_cb_mutex; /* Serialize CB preparation. */ spinlock_t __private lock; /* Protect counters and size state. */ + struct mutex srcu_gp_mutex; /* Serialize GP work. */ }; /* * Per-SRCU-domain structure, similar in function to rcu_state. */ struct srcu_struct { - struct mutex srcu_gp_mutex; /* Serialize GP work. */ unsigned int srcu_idx; /* Current rdr array element. */ unsigned long srcu_gp_seq; /* Grace-period seq #. */ unsigned long srcu_gp_seq_needed; /* Latest gp_seq needed. */ -- cgit v1.2.3 From 03200b5ca3b4d4edf634dc052bf3b8eb8dc8bbbc Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Fri, 17 Mar 2023 19:30:50 -0700 Subject: srcu: Move grace-period fields from srcu_struct to srcu_usage This commit moves the ->srcu_gp_seq, ->srcu_gp_seq_needed, ->srcu_gp_seq_needed_exp, ->srcu_gp_start, and ->srcu_last_gp_end fields from the srcu_struct structure to the srcu_usage structure to reduce the size of the former in order to improve cache locality. Suggested-by: Christoph Hellwig Tested-by: Sachin Sant Tested-by: "Zhang, Qiang1" Tested-by: Joel Fernandes (Google) Signed-off-by: Paul E. McKenney --- include/linux/srcutree.h | 25 +++++++++++++------------ 1 file changed, 13 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/srcutree.h b/include/linux/srcutree.h index d04e3da6181c..372e35b0e8b6 100644 --- a/include/linux/srcutree.h +++ b/include/linux/srcutree.h @@ -68,6 +68,11 @@ struct srcu_usage { struct mutex srcu_cb_mutex; /* Serialize CB preparation. */ spinlock_t __private lock; /* Protect counters and size state. */ struct mutex srcu_gp_mutex; /* Serialize GP work. */ + unsigned long srcu_gp_seq; /* Grace-period seq #. */ + unsigned long srcu_gp_seq_needed; /* Latest gp_seq needed. */ + unsigned long srcu_gp_seq_needed_exp; /* Furthest future exp GP. */ + unsigned long srcu_gp_start; /* Last GP start timestamp (jiffies) */ + unsigned long srcu_last_gp_end; /* Last GP end timestamp (ns) */ }; /* @@ -75,11 +80,6 @@ struct srcu_usage { */ struct srcu_struct { unsigned int srcu_idx; /* Current rdr array element. */ - unsigned long srcu_gp_seq; /* Grace-period seq #. */ - unsigned long srcu_gp_seq_needed; /* Latest gp_seq needed. */ - unsigned long srcu_gp_seq_needed_exp; /* Furthest future exp GP. */ - unsigned long srcu_gp_start; /* Last GP start timestamp (jiffies) */ - unsigned long srcu_last_gp_end; /* Last GP end timestamp (ns) */ unsigned long srcu_size_jiffies; /* Current contention-measurement interval. */ unsigned long srcu_n_lock_retries; /* Contention events in current interval. */ unsigned long srcu_n_exp_nodelay; /* # expedited no-delays in current GP phase. */ @@ -115,8 +115,13 @@ struct srcu_struct { #define SRCU_STATE_SCAN1 1 #define SRCU_STATE_SCAN2 2 -#define __SRCU_STRUCT_INIT_COMMON(name, usage_name) \ +#define __SRCU_USAGE_INIT(name) \ +{ \ + .lock = __SPIN_LOCK_UNLOCKED(name.lock), \ .srcu_gp_seq_needed = -1UL, \ +} + +#define __SRCU_STRUCT_INIT_COMMON(name, usage_name) \ .work = __DELAYED_WORK_INITIALIZER(name.work, NULL, 0), \ .srcu_sup = &usage_name, \ __SRCU_DEP_MAP_INIT(name) @@ -153,9 +158,7 @@ struct srcu_struct { */ #ifdef MODULE # define __DEFINE_SRCU(name, is_static) \ - static struct srcu_usage name##_srcu_usage = { \ - .lock = __SPIN_LOCK_UNLOCKED(name.lock), \ - }; \ + static struct srcu_usage name##_srcu_usage = __SRCU_USAGE_INIT(name##_srcu_usage); \ is_static struct srcu_struct name = __SRCU_STRUCT_INIT_MODULE(name, name##_srcu_usage); \ extern struct srcu_struct * const __srcu_struct_##name; \ struct srcu_struct * const __srcu_struct_##name \ @@ -163,9 +166,7 @@ struct srcu_struct { #else # define __DEFINE_SRCU(name, is_static) \ static DEFINE_PER_CPU(struct srcu_data, name##_srcu_data); \ - static struct srcu_usage name##_srcu_usage = { \ - .lock = __SPIN_LOCK_UNLOCKED(name.lock), \ - }; \ + static struct srcu_usage name##_srcu_usage = __SRCU_USAGE_INIT(name##_srcu_usage); \ is_static struct srcu_struct name = \ __SRCU_STRUCT_INIT(name, name##_srcu_usage, name##_srcu_data) #endif -- cgit v1.2.3 From 3b46679c623c2766f4c56fd3f9ce8edbb38c5d20 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Fri, 17 Mar 2023 20:01:02 -0700 Subject: srcu: Move heuristics fields from srcu_struct to srcu_usage This commit moves the ->srcu_size_jiffies, ->srcu_n_lock_retries, and ->srcu_n_exp_nodelay fields from the srcu_struct structure to the srcu_usage structure to reduce the size of the former in order to improve cache locality. Suggested-by: Christoph Hellwig Tested-by: Sachin Sant Tested-by: "Zhang, Qiang1" Tested-by: Joel Fernandes (Google) Signed-off-by: Paul E. McKenney --- include/linux/srcutree.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/srcutree.h b/include/linux/srcutree.h index 372e35b0e8b6..3023492d8d89 100644 --- a/include/linux/srcutree.h +++ b/include/linux/srcutree.h @@ -73,6 +73,9 @@ struct srcu_usage { unsigned long srcu_gp_seq_needed_exp; /* Furthest future exp GP. */ unsigned long srcu_gp_start; /* Last GP start timestamp (jiffies) */ unsigned long srcu_last_gp_end; /* Last GP end timestamp (ns) */ + unsigned long srcu_size_jiffies; /* Current contention-measurement interval. */ + unsigned long srcu_n_lock_retries; /* Contention events in current interval. */ + unsigned long srcu_n_exp_nodelay; /* # expedited no-delays in current GP phase. */ }; /* @@ -80,9 +83,6 @@ struct srcu_usage { */ struct srcu_struct { unsigned int srcu_idx; /* Current rdr array element. */ - unsigned long srcu_size_jiffies; /* Current contention-measurement interval. */ - unsigned long srcu_n_lock_retries; /* Contention events in current interval. */ - unsigned long srcu_n_exp_nodelay; /* # expedited no-delays in current GP phase. */ struct srcu_data __percpu *sda; /* Per-CPU srcu_data array. */ bool sda_is_static; /* May ->sda be passed to free_percpu()? */ unsigned long srcu_barrier_seq; /* srcu_barrier seq #. */ -- cgit v1.2.3 From 660349ac79cb22bb64c44b026d879069783e97d5 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Fri, 17 Mar 2023 20:22:58 -0700 Subject: srcu: Move ->sda_is_static from srcu_struct to srcu_usage This commit moves the ->sda_is_static field from the srcu_struct structure to the srcu_usage structure to reduce the size of the former in order to improve cache locality. Suggested-by: Christoph Hellwig Tested-by: Sachin Sant Tested-by: "Zhang, Qiang1" Tested-by: Joel Fernandes (Google) Signed-off-by: Paul E. McKenney --- include/linux/srcutree.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/srcutree.h b/include/linux/srcutree.h index 3023492d8d89..d3534ecb806e 100644 --- a/include/linux/srcutree.h +++ b/include/linux/srcutree.h @@ -76,6 +76,7 @@ struct srcu_usage { unsigned long srcu_size_jiffies; /* Current contention-measurement interval. */ unsigned long srcu_n_lock_retries; /* Contention events in current interval. */ unsigned long srcu_n_exp_nodelay; /* # expedited no-delays in current GP phase. */ + bool sda_is_static; /* May ->sda be passed to free_percpu()? */ }; /* @@ -84,7 +85,6 @@ struct srcu_usage { struct srcu_struct { unsigned int srcu_idx; /* Current rdr array element. */ struct srcu_data __percpu *sda; /* Per-CPU srcu_data array. */ - bool sda_is_static; /* May ->sda be passed to free_percpu()? */ unsigned long srcu_barrier_seq; /* srcu_barrier seq #. */ struct mutex srcu_barrier_mutex; /* Serialize barrier ops. */ struct completion srcu_barrier_completion; -- cgit v1.2.3 From d20162e0bfc222183a7c94cd00e74b6bbf1a605b Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Fri, 17 Mar 2023 21:08:18 -0700 Subject: srcu: Move srcu_barrier() fields from srcu_struct to srcu_usage This commit moves the ->srcu_barrier_seq, ->srcu_barrier_mutex, ->srcu_barrier_completion, and ->srcu_barrier_cpu_cnt fields from the srcu_struct structure to the srcu_usage structure to reduce the size of the former in order to improve cache locality. Suggested-by: Christoph Hellwig Tested-by: Sachin Sant Tested-by: "Zhang, Qiang1" Tested-by: Joel Fernandes (Google) Signed-off-by: Paul E. McKenney --- include/linux/srcutree.h | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/srcutree.h b/include/linux/srcutree.h index d3534ecb806e..d544ec1c0c8e 100644 --- a/include/linux/srcutree.h +++ b/include/linux/srcutree.h @@ -77,6 +77,13 @@ struct srcu_usage { unsigned long srcu_n_lock_retries; /* Contention events in current interval. */ unsigned long srcu_n_exp_nodelay; /* # expedited no-delays in current GP phase. */ bool sda_is_static; /* May ->sda be passed to free_percpu()? */ + unsigned long srcu_barrier_seq; /* srcu_barrier seq #. */ + struct mutex srcu_barrier_mutex; /* Serialize barrier ops. */ + struct completion srcu_barrier_completion; + /* Awaken barrier rq at end. */ + atomic_t srcu_barrier_cpu_cnt; /* # CPUs not yet posting a */ + /* callback for the barrier */ + /* operation. */ }; /* @@ -85,13 +92,6 @@ struct srcu_usage { struct srcu_struct { unsigned int srcu_idx; /* Current rdr array element. */ struct srcu_data __percpu *sda; /* Per-CPU srcu_data array. */ - unsigned long srcu_barrier_seq; /* srcu_barrier seq #. */ - struct mutex srcu_barrier_mutex; /* Serialize barrier ops. */ - struct completion srcu_barrier_completion; - /* Awaken barrier rq at end. */ - atomic_t srcu_barrier_cpu_cnt; /* # CPUs not yet posting a */ - /* callback for the barrier */ - /* operation. */ unsigned long reschedule_jiffies; unsigned long reschedule_count; struct delayed_work work; -- cgit v1.2.3 From fd1b3f8e097b7fbbab8ac4a802b24fc23c703dcf Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Fri, 17 Mar 2023 21:30:32 -0700 Subject: srcu: Move work-scheduling fields from srcu_struct to srcu_usage This commit moves the ->reschedule_jiffies, ->reschedule_count, and ->work fields from the srcu_struct structure to the srcu_usage structure to reduce the size of the former in order to improve cache locality. However, this means that the container_of() calls cannot get a pointer to the srcu_struct because they are no longer in the srcu_struct. This issue is addressed by adding a ->srcu_ssp field in the srcu_usage structure that references the corresponding srcu_struct structure. And given the presence of the sup pointer to the srcu_usage structure, replace some ssp->srcu_usage-> instances with sup->. [ paulmck Apply feedback from kernel test robot. ] Link: https://lore.kernel.org/oe-kbuild-all/202303191400.iO5BOqka-lkp@intel.com/ Suggested-by: Christoph Hellwig Tested-by: Sachin Sant Tested-by: "Zhang, Qiang1" Tested-by: Joel Fernandes (Google) Signed-off-by: Paul E. McKenney --- include/linux/srcutree.h | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/srcutree.h b/include/linux/srcutree.h index d544ec1c0c8e..cd0cdd8142c5 100644 --- a/include/linux/srcutree.h +++ b/include/linux/srcutree.h @@ -84,6 +84,10 @@ struct srcu_usage { atomic_t srcu_barrier_cpu_cnt; /* # CPUs not yet posting a */ /* callback for the barrier */ /* operation. */ + unsigned long reschedule_jiffies; + unsigned long reschedule_count; + struct delayed_work work; + struct srcu_struct *srcu_ssp; }; /* @@ -92,9 +96,6 @@ struct srcu_usage { struct srcu_struct { unsigned int srcu_idx; /* Current rdr array element. */ struct srcu_data __percpu *sda; /* Per-CPU srcu_data array. */ - unsigned long reschedule_jiffies; - unsigned long reschedule_count; - struct delayed_work work; struct lockdep_map dep_map; struct srcu_usage *srcu_sup; /* Update-side data. */ }; @@ -119,10 +120,10 @@ struct srcu_struct { { \ .lock = __SPIN_LOCK_UNLOCKED(name.lock), \ .srcu_gp_seq_needed = -1UL, \ + .work = __DELAYED_WORK_INITIALIZER(name.work, NULL, 0), \ } #define __SRCU_STRUCT_INIT_COMMON(name, usage_name) \ - .work = __DELAYED_WORK_INITIALIZER(name.work, NULL, 0), \ .srcu_sup = &usage_name, \ __SRCU_DEP_MAP_INIT(name) -- cgit v1.2.3 From 144d204df78e40e6250201e71ef7d0e42d2a13fc Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Thu, 30 Mar 2023 19:24:29 +0300 Subject: PCI: Introduce pci_resource_n() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Introduce pci_resource_n() and replace open-coded implementations of it in pci.h. Link: https://lore.kernel.org/r/20230330162434.35055-3-andriy.shevchenko@linux.intel.com Signed-off-by: Andy Shevchenko Signed-off-by: Bjorn Helgaas Reviewed-by: Philippe Mathieu-Daudé --- include/linux/pci.h | 15 +++++++-------- 1 file changed, 7 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index fafd8020c6d7..0239f12d0ba9 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1994,14 +1994,13 @@ int pci_iobar_pfn(struct pci_dev *pdev, int bar, struct vm_area_struct *vma); * These helpers provide future and backwards compatibility * for accessing popular PCI BAR info */ -#define pci_resource_start(dev, bar) ((dev)->resource[(bar)].start) -#define pci_resource_end(dev, bar) ((dev)->resource[(bar)].end) -#define pci_resource_flags(dev, bar) ((dev)->resource[(bar)].flags) -#define pci_resource_len(dev,bar) \ - ((pci_resource_end((dev), (bar)) == 0) ? 0 : \ - \ - (pci_resource_end((dev), (bar)) - \ - pci_resource_start((dev), (bar)) + 1)) +#define pci_resource_n(dev, bar) (&(dev)->resource[(bar)]) +#define pci_resource_start(dev, bar) (pci_resource_n(dev, bar)->start) +#define pci_resource_end(dev, bar) (pci_resource_n(dev, bar)->end) +#define pci_resource_flags(dev, bar) (pci_resource_n(dev, bar)->flags) +#define pci_resource_len(dev,bar) \ + (pci_resource_end((dev), (bar)) ? \ + resource_size(pci_resource_n((dev), (bar))) : 0) /* * Similar to the helpers above, these manipulate per-pci_dev -- cgit v1.2.3 From 09cc900632400079619e9154604fd299c2cc9a5a Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Thu, 30 Mar 2023 19:24:30 +0300 Subject: PCI: Introduce pci_dev_for_each_resource() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Instead of open-coding it everywhere introduce a tiny helper that can be used to iterate over each resource of a PCI device, and convert the most obvious users into it. While at it drop doubled empty line before pdev_sort_resources(). No functional changes intended. Suggested-by: Andy Shevchenko Link: https://lore.kernel.org/r/20230330162434.35055-4-andriy.shevchenko@linux.intel.com Signed-off-by: Mika Westerberg Signed-off-by: Andy Shevchenko Signed-off-by: Bjorn Helgaas Reviewed-by: Krzysztof Wilczyński --- include/linux/pci.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 0239f12d0ba9..2234ef961bfe 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -2002,6 +2002,20 @@ int pci_iobar_pfn(struct pci_dev *pdev, int bar, struct vm_area_struct *vma); (pci_resource_end((dev), (bar)) ? \ resource_size(pci_resource_n((dev), (bar))) : 0) +#define __pci_dev_for_each_res0(dev, res, ...) \ + for (unsigned int __b = 0; \ + res = pci_resource_n(dev, __b), __b < PCI_NUM_RESOURCES; \ + __b++) + +#define __pci_dev_for_each_res1(dev, res, __b) \ + for (__b = 0; \ + res = pci_resource_n(dev, __b), __b < PCI_NUM_RESOURCES; \ + __b++) + +#define pci_dev_for_each_resource(dev, res, ...) \ + CONCATENATE(__pci_dev_for_each_res, COUNT_ARGS(__VA_ARGS__)) \ + (dev, res, __VA_ARGS__) + /* * Similar to the helpers above, these manipulate per-pci_dev * driver-specific data. They are really just a wrapper around -- cgit v1.2.3 From ceb928be5cab32043f230bcb1adeb0a9a9b8f0f2 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Thu, 30 Mar 2023 19:24:31 +0300 Subject: PCI: Document pci_bus_for_each_resource() There might be confusion about why pci_bus_for_each_resource() uses Logical OR. Document the entire macro and explain how it works and why the conditional needs to be like that. Link: https://lore.kernel.org/r/20230330162434.35055-5-andriy.shevchenko@linux.intel.com Signed-off-by: Andy Shevchenko Signed-off-by: Bjorn Helgaas --- include/linux/pci.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 2234ef961bfe..db3155562320 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1444,6 +1444,26 @@ int devm_request_pci_bus_resources(struct device *dev, /* Temporary until new and working PCI SBR API in place */ int pci_bridge_secondary_bus_reset(struct pci_dev *dev); +/** + * pci_bus_for_each_resource - iterate over PCI bus resources + * @bus: the PCI bus + * @res: pointer to the current resource + * @i: index of the current resource + * + * Iterate over PCI bus resources. The first part is to go over PCI bus + * resource array, which has at most the %PCI_BRIDGE_RESOURCE_NUM entries. + * After that continue with the separate list of the additional resources, + * if not empty. That's why the Logical OR is being used. + * + * Possible usage: + * + * struct pci_bus *bus = ...; + * struct resource *res; + * unsigned int i; + * + * pci_bus_for_each_resource(bus, res, i) + * pr_info("PCI bus resource[%u]: %pR\n", i, res); + */ #define pci_bus_for_each_resource(bus, res, i) \ for (i = 0; \ (res = pci_bus_resource_n(bus, i)) || i < PCI_BRIDGE_RESOURCE_NUM; \ -- cgit v1.2.3 From b7e852a9ec96635168c04204fb7cf1f7390b9a8c Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Mon, 3 Apr 2023 21:50:23 -0700 Subject: bpf: Remove unused arguments from btf_struct_access(). Remove unused arguments from btf_struct_access() callback. Signed-off-by: Alexei Starovoitov Signed-off-by: Andrii Nakryiko Acked-by: David Vernet Link: https://lore.kernel.org/bpf/20230404045029.82870-3-alexei.starovoitov@gmail.com --- include/linux/bpf.h | 3 +-- include/linux/filter.h | 3 +-- 2 files changed, 2 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 2d8f3f639e68..4f689dda748f 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -893,8 +893,7 @@ struct bpf_verifier_ops { struct bpf_prog *prog, u32 *target_size); int (*btf_struct_access)(struct bpf_verifier_log *log, const struct bpf_reg_state *reg, - int off, int size, enum bpf_access_type atype, - u32 *next_btf_id, enum bpf_type_flag *flag); + int off, int size); }; struct bpf_prog_offload_ops { diff --git a/include/linux/filter.h b/include/linux/filter.h index 23c08c31bea9..5364b0c52c1d 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -571,8 +571,7 @@ DECLARE_STATIC_KEY_FALSE(bpf_stats_enabled_key); extern struct mutex nf_conn_btf_access_lock; extern int (*nfct_btf_struct_access)(struct bpf_verifier_log *log, const struct bpf_reg_state *reg, - int off, int size, enum bpf_access_type atype, - u32 *next_btf_id, enum bpf_type_flag *flag); + int off, int size); typedef unsigned int (*bpf_dispatcher_fn)(const void *ctx, const struct bpf_insn *insnsi, -- cgit v1.2.3 From 63260df1396578226ac3134cf7f764690002e70e Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Mon, 3 Apr 2023 21:50:24 -0700 Subject: bpf: Refactor btf_nested_type_is_trusted(). btf_nested_type_is_trusted() tries to find a struct member at corresponding offset. It works for flat structures and falls apart in more complex structs with nested structs. The offset->member search is already performed by btf_struct_walk() including nested structs. Reuse this work and pass {field name, field btf id} into btf_nested_type_is_trusted() instead of offset to make BTF_TYPE_SAFE*() logic more robust. Signed-off-by: Alexei Starovoitov Signed-off-by: Andrii Nakryiko Acked-by: David Vernet Link: https://lore.kernel.org/bpf/20230404045029.82870-4-alexei.starovoitov@gmail.com --- include/linux/bpf.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 4f689dda748f..002a811b6b90 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -2263,7 +2263,7 @@ static inline bool bpf_tracing_btf_ctx_access(int off, int size, int btf_struct_access(struct bpf_verifier_log *log, const struct bpf_reg_state *reg, int off, int size, enum bpf_access_type atype, - u32 *next_btf_id, enum bpf_type_flag *flag); + u32 *next_btf_id, enum bpf_type_flag *flag, const char **field_name); bool btf_struct_ids_match(struct bpf_verifier_log *log, const struct btf *btf, u32 id, int off, const struct btf *need_btf, u32 need_type_id, @@ -2302,7 +2302,7 @@ struct bpf_core_ctx { bool btf_nested_type_is_trusted(struct bpf_verifier_log *log, const struct bpf_reg_state *reg, - int off, const char *suffix); + const char *field_name, u32 btf_id, const char *suffix); bool btf_type_ids_nocast_alias(struct bpf_verifier_log *log, const struct btf *reg_btf, u32 reg_id, @@ -2517,7 +2517,8 @@ static inline struct bpf_prog *bpf_prog_by_id(u32 id) static inline int btf_struct_access(struct bpf_verifier_log *log, const struct bpf_reg_state *reg, int off, int size, enum bpf_access_type atype, - u32 *next_btf_id, enum bpf_type_flag *flag) + u32 *next_btf_id, enum bpf_type_flag *flag, + const char **field_name) { return -EACCES; } -- cgit v1.2.3 From 65457b74aa9437418e552e8d52d7112d4f9901a6 Mon Sep 17 00:00:00 2001 From: Domenico Cerasuolo Date: Thu, 30 Mar 2023 12:54:16 +0200 Subject: sched/psi: Rename existing poll members in preparation Renaming in PSI implementation to make a clear distinction between privileged and unprivileged triggers code to be implemented in the next patch. Suggested-by: Johannes Weiner Signed-off-by: Domenico Cerasuolo Signed-off-by: Peter Zijlstra (Intel) Acked-by: Johannes Weiner Link: https://lore.kernel.org/r/20230330105418.77061-3-cerasuolodomenico@gmail.com --- include/linux/psi_types.h | 36 ++++++++++++++++++------------------ 1 file changed, 18 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/psi_types.h b/include/linux/psi_types.h index 1e0a0d7ace3a..1819afa8b198 100644 --- a/include/linux/psi_types.h +++ b/include/linux/psi_types.h @@ -175,26 +175,26 @@ struct psi_group { u64 total[NR_PSI_AGGREGATORS][NR_PSI_STATES - 1]; unsigned long avg[NR_PSI_STATES - 1][3]; - /* Monitor work control */ - struct task_struct __rcu *poll_task; - struct timer_list poll_timer; - wait_queue_head_t poll_wait; - atomic_t poll_wakeup; - atomic_t poll_scheduled; + /* Monitor RT polling work control */ + struct task_struct __rcu *rtpoll_task; + struct timer_list rtpoll_timer; + wait_queue_head_t rtpoll_wait; + atomic_t rtpoll_wakeup; + atomic_t rtpoll_scheduled; /* Protects data used by the monitor */ - struct mutex trigger_lock; - - /* Configured polling triggers */ - struct list_head triggers; - u32 nr_triggers[NR_PSI_STATES - 1]; - u32 poll_states; - u64 poll_min_period; - - /* Total stall times at the start of monitor activation */ - u64 polling_total[NR_PSI_STATES - 1]; - u64 polling_next_update; - u64 polling_until; + struct mutex rtpoll_trigger_lock; + + /* Configured RT polling triggers */ + struct list_head rtpoll_triggers; + u32 rtpoll_nr_triggers[NR_PSI_STATES - 1]; + u32 rtpoll_states; + u64 rtpoll_min_period; + + /* Total stall times at the start of RT polling monitor activation */ + u64 rtpoll_total[NR_PSI_STATES - 1]; + u64 rtpoll_next_update; + u64 rtpoll_until; }; #else /* CONFIG_PSI */ -- cgit v1.2.3 From d82caa273565b45fcf103148950549af76c314b0 Mon Sep 17 00:00:00 2001 From: Domenico Cerasuolo Date: Thu, 30 Mar 2023 12:54:18 +0200 Subject: sched/psi: Allow unprivileged polling of N*2s period PSI offers 2 mechanisms to get information about a specific resource pressure. One is reading from /proc/pressure/, which gives average pressures aggregated every 2s. The other is creating a pollable fd for a specific resource and cgroup. The trigger creation requires CAP_SYS_RESOURCE, and gives the possibility to pick specific time window and threshold, spawing an RT thread to aggregate the data. Systemd would like to provide containers the option to monitor pressure on their own cgroup and sub-cgroups. For example, if systemd launches a container that itself then launches services, the container should have the ability to poll() for pressure in individual services. But neither the container nor the services are privileged. This patch implements a mechanism to allow unprivileged users to create pressure triggers. The difference with privileged triggers creation is that unprivileged ones must have a time window that's a multiple of 2s. This is so that we can avoid unrestricted spawning of rt threads, and use instead the same aggregation mechanism done for the averages, which runs independently of any triggers. Suggested-by: Johannes Weiner Signed-off-by: Domenico Cerasuolo Signed-off-by: Peter Zijlstra (Intel) Acked-by: Johannes Weiner Link: https://lore.kernel.org/r/20230330105418.77061-5-cerasuolodomenico@gmail.com --- include/linux/psi.h | 2 +- include/linux/psi_types.h | 7 +++++++ 2 files changed, 8 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/psi.h b/include/linux/psi.h index b029a847def1..ab26200c2803 100644 --- a/include/linux/psi.h +++ b/include/linux/psi.h @@ -24,7 +24,7 @@ void psi_memstall_leave(unsigned long *flags); int psi_show(struct seq_file *s, struct psi_group *group, enum psi_res res); struct psi_trigger *psi_trigger_create(struct psi_group *group, - char *buf, enum psi_res res); + char *buf, enum psi_res res, struct file *file); void psi_trigger_destroy(struct psi_trigger *t); __poll_t psi_trigger_poll(void **trigger_ptr, struct file *file, diff --git a/include/linux/psi_types.h b/include/linux/psi_types.h index 1819afa8b198..040c089581c6 100644 --- a/include/linux/psi_types.h +++ b/include/linux/psi_types.h @@ -151,6 +151,9 @@ struct psi_trigger { /* Deferred event(s) from previous ratelimit window */ bool pending_event; + + /* Trigger type - PSI_AVGS for unprivileged, PSI_POLL for RT */ + enum psi_aggregators aggregator; }; struct psi_group { @@ -171,6 +174,10 @@ struct psi_group { /* Aggregator work control */ struct delayed_work avgs_work; + /* Unprivileged triggers against N*PSI_FREQ windows */ + struct list_head avg_triggers; + u32 avg_nr_triggers[NR_PSI_STATES - 1]; + /* Total stall times and sampled pressure averages */ u64 total[NR_PSI_AGGREGATORS][NR_PSI_STATES - 1]; unsigned long avg[NR_PSI_STATES - 1][3]; -- cgit v1.2.3 From b2d110cd5d28ded813f060b735cd68bfe2e5010f Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Mon, 6 Mar 2023 08:56:51 +0100 Subject: interconnect: drop unused icc_link_destroy() interface Now that the link array is deallocated when destroying nodes and the explicit link removal has been dropped from the exynos driver there are no further users of and no need for the icc_link_destroy() interface. Signed-off-by: Johan Hovold Link: https://lore.kernel.org/r/20230306075651.2449-24-johan+linaro@kernel.org Signed-off-by: Georgi Djakov --- include/linux/interconnect-provider.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/interconnect-provider.h b/include/linux/interconnect-provider.h index b9af9016a95e..e6d8aca6886d 100644 --- a/include/linux/interconnect-provider.h +++ b/include/linux/interconnect-provider.h @@ -118,7 +118,6 @@ int icc_std_aggregate(struct icc_node *node, u32 tag, u32 avg_bw, struct icc_node *icc_node_create(int id); void icc_node_destroy(int id); int icc_link_create(struct icc_node *node, const int dst_id); -int icc_link_destroy(struct icc_node *src, struct icc_node *dst); void icc_node_add(struct icc_node *node, struct icc_provider *provider); void icc_node_del(struct icc_node *node); int icc_nodes_remove(struct icc_provider *provider); @@ -150,11 +149,6 @@ static inline int icc_link_create(struct icc_node *node, const int dst_id) return -ENOTSUPP; } -static inline int icc_link_destroy(struct icc_node *src, struct icc_node *dst) -{ - return -ENOTSUPP; -} - static inline void icc_node_add(struct icc_node *node, struct icc_provider *provider) { } -- cgit v1.2.3 From 4c4dd04e75e8177311d17387326253674cb0558b Mon Sep 17 00:00:00 2001 From: Ondrej Kozina Date: Wed, 5 Apr 2023 13:12:23 +0200 Subject: sed-opal: Add command to read locking range parameters. It returns following attributes: locking range start locking range length read lock enabled write lock enabled lock state (RW, RO or LK) It can be retrieved by user authority provided the authority was added to locking range via prior IOC_OPAL_ADD_USR_TO_LR ioctl command. The command was extended to add user in ACE that allows to read attributes listed above. Signed-off-by: Ondrej Kozina Tested-by: Luca Boccassi Tested-by: Milan Broz Link: https://lore.kernel.org/r/20230405111223.272816-6-okozina@redhat.com Signed-off-by: Jens Axboe --- include/linux/sed-opal.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sed-opal.h b/include/linux/sed-opal.h index 31ac562a17d7..042c1e2cb0ce 100644 --- a/include/linux/sed-opal.h +++ b/include/linux/sed-opal.h @@ -45,6 +45,7 @@ static inline bool is_sed_ioctl(unsigned int cmd) case IOC_OPAL_WRITE_SHADOW_MBR: case IOC_OPAL_GENERIC_TABLE_RW: case IOC_OPAL_GET_STATUS: + case IOC_OPAL_GET_LR_STATUS: return true; } return false; -- cgit v1.2.3 From e15a19306004b3d7b6a5fe269e4e7cb7934aa3fe Mon Sep 17 00:00:00 2001 From: Pingfan Liu Date: Wed, 4 Jan 2023 12:29:01 -0800 Subject: srcu: Add comments for srcu_size_state The SRCU_SIZE_* names are not self-explanatory, so this commit therefore adds comments to the definitions. Signed-off-by: Pingfan Liu Cc: Lai Jiangshan Cc: "Paul E. McKenney" Cc: Frederic Weisbecker Cc: Josh Triplett Cc: Steven Rostedt Cc: Mathieu Desnoyers Cc: "Zhang, Qiang1" To: rcu@vger.kernel.org Reviewed-by: Paul E. McKenney Reviewed-by: Joel Fernandes (Google) Signed-off-by: Paul E. McKenney Signed-off-by: Joel Fernandes (Google) --- include/linux/srcutree.h | 33 +++++++++++++++++++++++---------- 1 file changed, 23 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/srcutree.h b/include/linux/srcutree.h index 558057b517b7..a6910805f9c5 100644 --- a/include/linux/srcutree.h +++ b/include/linux/srcutree.h @@ -92,16 +92,29 @@ struct srcu_struct { struct lockdep_map dep_map; }; -/* Values for size state variable (->srcu_size_state). */ -#define SRCU_SIZE_SMALL 0 -#define SRCU_SIZE_ALLOC 1 -#define SRCU_SIZE_WAIT_BARRIER 2 -#define SRCU_SIZE_WAIT_CALL 3 -#define SRCU_SIZE_WAIT_CBS1 4 -#define SRCU_SIZE_WAIT_CBS2 5 -#define SRCU_SIZE_WAIT_CBS3 6 -#define SRCU_SIZE_WAIT_CBS4 7 -#define SRCU_SIZE_BIG 8 +// Values for size state variable (->srcu_size_state). Once the state +// has been set to SRCU_SIZE_ALLOC, the grace-period code advances through +// this state machine one step per grace period until the SRCU_SIZE_BIG state +// is reached. Otherwise, the state machine remains in the SRCU_SIZE_SMALL +// state indefinitely. +#define SRCU_SIZE_SMALL 0 // No srcu_node combining tree, ->node == NULL +#define SRCU_SIZE_ALLOC 1 // An srcu_node tree is being allocated, initialized, + // and then referenced by ->node. It will not be used. +#define SRCU_SIZE_WAIT_BARRIER 2 // The srcu_node tree starts being used by everything + // except call_srcu(), especially by srcu_barrier(). + // By the end of this state, all CPUs and threads + // are aware of this tree's existence. +#define SRCU_SIZE_WAIT_CALL 3 // The srcu_node tree starts being used by call_srcu(). + // By the end of this state, all of the call_srcu() + // invocations that were running on a non-boot CPU + // and using the boot CPU's callback queue will have + // completed. +#define SRCU_SIZE_WAIT_CBS1 4 // Don't trust the ->srcu_have_cbs[] grace-period +#define SRCU_SIZE_WAIT_CBS2 5 // sequence elements or the ->srcu_data_have_cbs[] +#define SRCU_SIZE_WAIT_CBS3 6 // CPU-bitmask elements until all four elements of +#define SRCU_SIZE_WAIT_CBS4 7 // each array have been initialized. +#define SRCU_SIZE_BIG 8 // The srcu_node combining tree is fully initialized + // and all aspects of it are being put to use. /* Values for state variable (bottom bits of ->srcu_gp_seq). */ #define SRCU_STATE_IDLE 0 -- cgit v1.2.3 From 58d7668242647e661a20efe065519abd6454287e Mon Sep 17 00:00:00 2001 From: "Joel Fernandes (Google)" Date: Tue, 24 Jan 2023 17:31:26 +0000 Subject: tick/nohz: Fix cpu_is_hotpluggable() by checking with nohz subsystem For CONFIG_NO_HZ_FULL systems, the tick_do_timer_cpu cannot be offlined. However, cpu_is_hotpluggable() still returns true for those CPUs. This causes torture tests that do offlining to end up trying to offline this CPU causing test failures. Such failure happens on all architectures. Fix the repeated error messages thrown by this (even if the hotplug errors are harmless) by asking the opinion of the nohz subsystem on whether the CPU can be hotplugged. [ Apply Frederic Weisbecker feedback on refactoring tick_nohz_cpu_down(). ] For drivers/base/ portion: Acked-by: Greg Kroah-Hartman Acked-by: Frederic Weisbecker Cc: Frederic Weisbecker Cc: "Paul E. McKenney" Cc: Zhouyi Zhou Cc: Will Deacon Cc: Marc Zyngier Cc: rcu Cc: stable@vger.kernel.org Fixes: 2987557f52b9 ("driver-core/cpu: Expose hotpluggability to the rest of the kernel") Signed-off-by: Paul E. McKenney Signed-off-by: Joel Fernandes (Google) --- include/linux/tick.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tick.h b/include/linux/tick.h index bfd571f18cfd..9459fef5b857 100644 --- a/include/linux/tick.h +++ b/include/linux/tick.h @@ -216,6 +216,7 @@ extern void tick_nohz_dep_set_signal(struct task_struct *tsk, enum tick_dep_bits bit); extern void tick_nohz_dep_clear_signal(struct signal_struct *signal, enum tick_dep_bits bit); +extern bool tick_nohz_cpu_hotpluggable(unsigned int cpu); /* * The below are tick_nohz_[set,clear]_dep() wrappers that optimize off-cases @@ -280,6 +281,7 @@ static inline void tick_nohz_full_add_cpus_to(struct cpumask *mask) { } static inline void tick_nohz_dep_set_cpu(int cpu, enum tick_dep_bits bit) { } static inline void tick_nohz_dep_clear_cpu(int cpu, enum tick_dep_bits bit) { } +static inline bool tick_nohz_cpu_hotpluggable(unsigned int cpu) { return true; } static inline void tick_dep_set(enum tick_dep_bits bit) { } static inline void tick_dep_clear(enum tick_dep_bits bit) { } -- cgit v1.2.3 From 7697c64b9e4908196f0ae68aa6d423dd40607973 Mon Sep 17 00:00:00 2001 From: William Breathitt Gray Date: Wed, 5 Apr 2023 11:45:42 -0400 Subject: regmap: Pass irq_drv_data as a parameter for set_type_config() Allow the struct regmap_irq_chip set_type_config() callback to access irq_drv_data by passing it as a parameter. Signed-off-by: William Breathitt Gray Reviewed-by: Andy Shevchenko Link: https://lore.kernel.org/r/20e15cd3afae80922b7e0577c7741df86b3390c5.1680708357.git.william.gray@linaro.org Signed-off-by: Mark Brown --- include/linux/regmap.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 4d10790adeb0..fb92d0ac13af 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -1650,7 +1650,8 @@ struct regmap_irq_chip { int (*set_type_virt)(unsigned int **buf, unsigned int type, unsigned long hwirq, int reg); int (*set_type_config)(unsigned int **buf, unsigned int type, - const struct regmap_irq *irq_data, int idx); + const struct regmap_irq *irq_data, int idx, + void *irq_drv_data); unsigned int (*get_irq_reg)(struct regmap_irq_chip_data *data, unsigned int base, int index); void *irq_drv_data; @@ -1659,7 +1660,8 @@ struct regmap_irq_chip { unsigned int regmap_irq_get_irq_reg_linear(struct regmap_irq_chip_data *data, unsigned int base, int index); int regmap_irq_set_type_config_simple(unsigned int **buf, unsigned int type, - const struct regmap_irq *irq_data, int idx); + const struct regmap_irq *irq_data, + int idx, void *irq_drv_data); int regmap_add_irq_chip(struct regmap *map, int irq, int irq_flags, int irq_base, const struct regmap_irq_chip *chip, -- cgit v1.2.3 From 673aa1ed1c9b6710bf24e3f0957d85e2f46c77db Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Tue, 4 Apr 2023 18:21:16 +0100 Subject: of: Rename of_modalias_node() This helper does not produce a real modalias, but tries to get the "product" compatible part of the "vendor,product" compatibles only. It is far from creating a purely useful modalias string and does not seem to be used like that directly anyway, so let's try to give this helper a more meaningful name before moving there a real modalias helper (already existing under of/device.c). Also update the various documentations to refer to the strings as "aliases" rather than "modaliases" which has a real meaning in the Linux kernel. There is no functional change. Cc: Rafael J. Wysocki Cc: Len Brown Cc: Maarten Lankhorst Cc: Maxime Ripard Cc: Thomas Zimmermann Cc: Sebastian Reichel Cc: Wolfram Sang Cc: Mark Brown Signed-off-by: Miquel Raynal Reviewed-by: Rob Herring Acked-by: Mark Brown Signed-off-by: Srinivas Kandagatla Acked-by: Sebastian Reichel Link: https://lore.kernel.org/r/20230404172148.82422-9-srinivas.kandagatla@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/of.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/of.h b/include/linux/of.h index 0af611307db2..b1eea8569043 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -373,7 +373,8 @@ extern int of_n_addr_cells(struct device_node *np); extern int of_n_size_cells(struct device_node *np); extern const struct of_device_id *of_match_node( const struct of_device_id *matches, const struct device_node *node); -extern int of_modalias_node(struct device_node *node, char *modalias, int len); +extern int of_alias_from_compatible(const struct device_node *node, char *alias, + int len); extern void of_print_phandle_args(const char *msg, const struct of_phandle_args *args); extern int __of_parse_phandle_with_args(const struct device_node *np, const char *list_name, const char *cells_name, int cell_count, -- cgit v1.2.3 From bd7a7ed774afd1a4174df34227626c95573be517 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Tue, 4 Apr 2023 18:21:17 +0100 Subject: of: Move of_modalias() to module.c Create a specific .c file for OF related module handling. Move of_modalias() inside as a first step. The helper is exposed through of.h even though it is only used by core files because the users from device.c will soon be split into an OF-only helper in module.c as well as a device-oriented inline helper in of_device.h. Putting this helper in of_private.h would require to include of_private.h from of_device.h, which is not acceptable. Suggested-by: Rob Herring Signed-off-by: Miquel Raynal Reviewed-by: Rob Herring Signed-off-by: Srinivas Kandagatla Link: https://lore.kernel.org/r/20230404172148.82422-10-srinivas.kandagatla@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/of.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/of.h b/include/linux/of.h index b1eea8569043..be26c7e8ef9e 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -385,6 +385,9 @@ extern int of_parse_phandle_with_args_map(const struct device_node *np, extern int of_count_phandle_with_args(const struct device_node *np, const char *list_name, const char *cells_name); +/* module functions */ +extern ssize_t of_modalias(const struct device_node *np, char *str, ssize_t len); + /* phandle iterator functions */ extern int of_phandle_iterator_init(struct of_phandle_iterator *it, const struct device_node *np, @@ -742,6 +745,12 @@ static inline int of_count_phandle_with_args(const struct device_node *np, return -ENOSYS; } +static inline ssize_t of_modalias(const struct device_node *np, char *str, + ssize_t len) +{ + return -ENODEV; +} + static inline int of_phandle_iterator_init(struct of_phandle_iterator *it, const struct device_node *np, const char *list_name, -- cgit v1.2.3 From e6506f06d5e82765666902ccf9e9162f3e31d518 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Tue, 4 Apr 2023 18:21:18 +0100 Subject: of: Move the request module helper logic to module.c Depending on device.c for pure OF handling is considered backwards. Let's extract the content of of_device_request_module() to have the real logic under module.c. The next step will be to convert users of of_device_request_module() to use the new helper. Signed-off-by: Miquel Raynal Reviewed-by: Rob Herring Signed-off-by: Srinivas Kandagatla Link: https://lore.kernel.org/r/20230404172148.82422-11-srinivas.kandagatla@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/of.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/of.h b/include/linux/of.h index be26c7e8ef9e..9b7a99499ef3 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -387,6 +387,7 @@ extern int of_count_phandle_with_args(const struct device_node *np, /* module functions */ extern ssize_t of_modalias(const struct device_node *np, char *str, ssize_t len); +extern int of_request_module(const struct device_node *np); /* phandle iterator functions */ extern int of_phandle_iterator_init(struct of_phandle_iterator *it, @@ -751,6 +752,11 @@ static inline ssize_t of_modalias(const struct device_node *np, char *str, return -ENODEV; } +static inline int of_request_module(const struct device_node *np) +{ + return -ENODEV; +} + static inline int of_phandle_iterator_init(struct of_phandle_iterator *it, const struct device_node *np, const char *list_name, -- cgit v1.2.3 From 2f555f58f5ce33b201235e104823662d5573c4a5 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Tue, 4 Apr 2023 18:21:20 +0100 Subject: of: device: Kill of_device_request_module() A new helper has been introduced, of_request_module(). Users have been converted, this helper can now be deleted. Signed-off-by: Miquel Raynal Reviewed-by: Rob Herring Signed-off-by: Srinivas Kandagatla Link: https://lore.kernel.org/r/20230404172148.82422-13-srinivas.kandagatla@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/of_device.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/of_device.h b/include/linux/of_device.h index f4b57614979d..ce20d8b00b3e 100644 --- a/include/linux/of_device.h +++ b/include/linux/of_device.h @@ -33,7 +33,6 @@ extern void of_device_unregister(struct platform_device *ofdev); extern const void *of_device_get_match_data(const struct device *dev); extern ssize_t of_device_modalias(struct device *dev, char *str, ssize_t len); -extern int of_device_request_module(struct device *dev); extern void of_device_uevent(const struct device *dev, struct kobj_uevent_env *env); extern int of_device_uevent_modalias(const struct device *dev, struct kobj_uevent_env *env); @@ -78,11 +77,6 @@ static inline int of_device_modalias(struct device *dev, return -ENODEV; } -static inline int of_device_request_module(struct device *dev) -{ - return -ENODEV; -} - static inline int of_device_uevent_modalias(const struct device *dev, struct kobj_uevent_env *env) { -- cgit v1.2.3 From 266570f496b90dea8fda893c2cf7c28d63ae2bd9 Mon Sep 17 00:00:00 2001 From: Michael Walle Date: Tue, 4 Apr 2023 18:21:21 +0100 Subject: nvmem: core: introduce NVMEM layouts NVMEM layouts are used to generate NVMEM cells during runtime. Think of an EEPROM with a well-defined conent. For now, the content can be described by a device tree or a board file. But this only works if the offsets and lengths are static and don't change. One could also argue that putting the layout of the EEPROM in the device tree is the wrong place. Instead, the device tree should just have a specific compatible string. Right now there are two use cases: (1) The NVMEM cell needs special processing. E.g. if it only specifies a base MAC address offset and you need to add an offset, or it needs to parse a MAC from ASCII format or some proprietary format. (Post processing of cells is added in a later commit). (2) u-boot environment parsing. The cells don't have a particular offset but it needs parsing the content to determine the offsets and length. Co-developed-by: Miquel Raynal Signed-off-by: Miquel Raynal Signed-off-by: Michael Walle Signed-off-by: Srinivas Kandagatla Link: https://lore.kernel.org/r/20230404172148.82422-14-srinivas.kandagatla@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/nvmem-consumer.h | 7 ++++++ include/linux/nvmem-provider.h | 51 ++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 58 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nvmem-consumer.h b/include/linux/nvmem-consumer.h index 1f62f7ba71ca..fa030d93b768 100644 --- a/include/linux/nvmem-consumer.h +++ b/include/linux/nvmem-consumer.h @@ -239,6 +239,7 @@ struct nvmem_cell *of_nvmem_cell_get(struct device_node *np, const char *id); struct nvmem_device *of_nvmem_device_get(struct device_node *np, const char *name); +struct device_node *of_nvmem_layout_get_container(struct nvmem_device *nvmem); #else static inline struct nvmem_cell *of_nvmem_cell_get(struct device_node *np, const char *id) @@ -251,6 +252,12 @@ static inline struct nvmem_device *of_nvmem_device_get(struct device_node *np, { return ERR_PTR(-EOPNOTSUPP); } + +static inline struct device_node * +of_nvmem_layout_get_container(struct nvmem_device *nvmem) +{ + return ERR_PTR(-EOPNOTSUPP); +} #endif /* CONFIG_NVMEM && CONFIG_OF */ #endif /* ifndef _LINUX_NVMEM_CONSUMER_H */ diff --git a/include/linux/nvmem-provider.h b/include/linux/nvmem-provider.h index 0262b86194eb..535c5f9f3309 100644 --- a/include/linux/nvmem-provider.h +++ b/include/linux/nvmem-provider.h @@ -88,6 +88,7 @@ struct nvmem_cell_info { * @stride: Minimum read/write access stride. * @priv: User context passed to read/write callbacks. * @ignore_wp: Write Protect pin is managed by the provider. + * @layout: Fixed layout associated with this nvmem device. * * Note: A default "nvmem" name will be assigned to the device if * no name is specified in its configuration. In such case "" is @@ -109,6 +110,7 @@ struct nvmem_config { bool read_only; bool root_only; bool ignore_wp; + struct nvmem_layout *layout; struct device_node *of_node; bool no_of_node; nvmem_reg_read_t reg_read; @@ -142,6 +144,33 @@ struct nvmem_cell_table { struct list_head node; }; +/** + * struct nvmem_layout - NVMEM layout definitions + * + * @name: Layout name. + * @of_match_table: Open firmware match table. + * @add_cells: Will be called if a nvmem device is found which + * has this layout. The function will add layout + * specific cells with nvmem_add_one_cell(). + * @owner: Pointer to struct module. + * @node: List node. + * + * A nvmem device can hold a well defined structure which can just be + * evaluated during runtime. For example a TLV list, or a list of "name=val" + * pairs. A nvmem layout can parse the nvmem device and add appropriate + * cells. + */ +struct nvmem_layout { + const char *name; + const struct of_device_id *of_match_table; + int (*add_cells)(struct device *dev, struct nvmem_device *nvmem, + struct nvmem_layout *layout); + + /* private */ + struct module *owner; + struct list_head node; +}; + #if IS_ENABLED(CONFIG_NVMEM) struct nvmem_device *nvmem_register(const struct nvmem_config *cfg); @@ -156,6 +185,14 @@ void nvmem_del_cell_table(struct nvmem_cell_table *table); int nvmem_add_one_cell(struct nvmem_device *nvmem, const struct nvmem_cell_info *info); +int __nvmem_layout_register(struct nvmem_layout *layout, struct module *owner); +#define nvmem_layout_register(layout) \ + __nvmem_layout_register(layout, THIS_MODULE) +void nvmem_layout_unregister(struct nvmem_layout *layout); + +const void *nvmem_layout_get_match_data(struct nvmem_device *nvmem, + struct nvmem_layout *layout); + #else static inline struct nvmem_device *nvmem_register(const struct nvmem_config *c) @@ -179,5 +216,19 @@ static inline int nvmem_add_one_cell(struct nvmem_device *nvmem, return -EOPNOTSUPP; } +static inline int nvmem_layout_register(struct nvmem_layout *layout) +{ + return -EOPNOTSUPP; +} + +static inline void nvmem_layout_unregister(struct nvmem_layout *layout) {} + +static inline const void * +nvmem_layout_get_match_data(struct nvmem_device *nvmem, + struct nvmem_layout *layout) +{ + return NULL; +} + #endif /* CONFIG_NVMEM */ #endif /* ifndef _LINUX_NVMEM_PROVIDER_H */ -- cgit v1.2.3 From 345ec382cd4b736c36e01f155d08c913b225b736 Mon Sep 17 00:00:00 2001 From: Michael Walle Date: Tue, 4 Apr 2023 18:21:24 +0100 Subject: nvmem: core: add per-cell post processing Instead of relying on the name the consumer is using for the cell, like it is done for the nvmem .cell_post_process configuration parameter, provide a per-cell post processing hook. This can then be populated by the NVMEM provider (or the NVMEM layout) when adding the cell. Signed-off-by: Michael Walle Signed-off-by: Miquel Raynal Signed-off-by: Srinivas Kandagatla Link: https://lore.kernel.org/r/20230404172148.82422-17-srinivas.kandagatla@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/nvmem-provider.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nvmem-provider.h b/include/linux/nvmem-provider.h index 535c5f9f3309..3bfc23553a9e 100644 --- a/include/linux/nvmem-provider.h +++ b/include/linux/nvmem-provider.h @@ -54,6 +54,8 @@ struct nvmem_keepout { * @bit_offset: Bit offset if cell is smaller than a byte. * @nbits: Number of bits. * @np: Optional device_node pointer. + * @read_post_process: Callback for optional post processing of cell data + * on reads. */ struct nvmem_cell_info { const char *name; @@ -62,6 +64,7 @@ struct nvmem_cell_info { unsigned int bit_offset; unsigned int nbits; struct device_node *np; + nvmem_cell_post_process_t read_post_process; }; /** -- cgit v1.2.3 From de12c9691501ccba41a154c223869f82be4c12fd Mon Sep 17 00:00:00 2001 From: Michael Walle Date: Tue, 4 Apr 2023 18:21:25 +0100 Subject: nvmem: core: allow to modify a cell before adding it Provide a way to modify a cell before it will get added. This is useful to attach a custom post processing hook via a layout. Signed-off-by: Michael Walle Signed-off-by: Miquel Raynal Signed-off-by: Srinivas Kandagatla Link: https://lore.kernel.org/r/20230404172148.82422-18-srinivas.kandagatla@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/nvmem-provider.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nvmem-provider.h b/include/linux/nvmem-provider.h index 3bfc23553a9e..be81cc88eabc 100644 --- a/include/linux/nvmem-provider.h +++ b/include/linux/nvmem-provider.h @@ -155,6 +155,8 @@ struct nvmem_cell_table { * @add_cells: Will be called if a nvmem device is found which * has this layout. The function will add layout * specific cells with nvmem_add_one_cell(). + * @fixup_cell_info: Will be called before a cell is added. Can be + * used to modify the nvmem_cell_info. * @owner: Pointer to struct module. * @node: List node. * @@ -168,6 +170,9 @@ struct nvmem_layout { const struct of_device_id *of_match_table; int (*add_cells)(struct device *dev, struct nvmem_device *nvmem, struct nvmem_layout *layout); + void (*fixup_cell_info)(struct nvmem_device *nvmem, + struct nvmem_layout *layout, + struct nvmem_cell_info *cell); /* private */ struct module *owner; -- cgit v1.2.3 From 011e40a166fdaa65fb9946b7cd91efec85b70dbb Mon Sep 17 00:00:00 2001 From: Michael Walle Date: Tue, 4 Apr 2023 18:21:27 +0100 Subject: nvmem: cell: drop global cell_post_process There are no users anymore for the global cell_post_process callback anymore. New users should use proper nvmem layouts. Signed-off-by: Michael Walle Signed-off-by: Miquel Raynal Signed-off-by: Srinivas Kandagatla Link: https://lore.kernel.org/r/20230404172148.82422-20-srinivas.kandagatla@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/nvmem-provider.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nvmem-provider.h b/include/linux/nvmem-provider.h index be81cc88eabc..d3d7af86a283 100644 --- a/include/linux/nvmem-provider.h +++ b/include/linux/nvmem-provider.h @@ -85,7 +85,6 @@ struct nvmem_cell_info { * @no_of_node: Device should not use the parent's of_node even if it's !NULL. * @reg_read: Callback to read data. * @reg_write: Callback to write data. - * @cell_post_process: Callback for vendor specific post processing of cell data * @size: Device size. * @word_size: Minimum read/write access granularity. * @stride: Minimum read/write access stride. @@ -118,7 +117,6 @@ struct nvmem_config { bool no_of_node; nvmem_reg_read_t reg_read; nvmem_reg_write_t reg_write; - nvmem_cell_post_process_t cell_post_process; int size; int word_size; int stride; -- cgit v1.2.3 From 8a134fd9f9323f4c39ec27055b3d3723cfb5c1e9 Mon Sep 17 00:00:00 2001 From: Michael Walle Date: Tue, 4 Apr 2023 18:21:28 +0100 Subject: nvmem: core: provide own priv pointer in post process callback It doesn't make any more sense to have a opaque pointer set up by the nvmem device. Usually, the layout isn't associated with a particular nvmem device. Instead, let the caller who set the post process callback provide the priv pointer. Signed-off-by: Michael Walle Signed-off-by: Miquel Raynal Signed-off-by: Srinivas Kandagatla Link: https://lore.kernel.org/r/20230404172148.82422-21-srinivas.kandagatla@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/nvmem-provider.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nvmem-provider.h b/include/linux/nvmem-provider.h index d3d7af86a283..0cf9f9490514 100644 --- a/include/linux/nvmem-provider.h +++ b/include/linux/nvmem-provider.h @@ -20,7 +20,8 @@ typedef int (*nvmem_reg_write_t)(void *priv, unsigned int offset, void *val, size_t bytes); /* used for vendor specific post processing of cell data */ typedef int (*nvmem_cell_post_process_t)(void *priv, const char *id, int index, - unsigned int offset, void *buf, size_t bytes); + unsigned int offset, void *buf, + size_t bytes); enum nvmem_type { NVMEM_TYPE_UNKNOWN = 0, @@ -56,6 +57,7 @@ struct nvmem_keepout { * @np: Optional device_node pointer. * @read_post_process: Callback for optional post processing of cell data * on reads. + * @priv: Opaque data passed to the read_post_process hook. */ struct nvmem_cell_info { const char *name; @@ -65,6 +67,7 @@ struct nvmem_cell_info { unsigned int nbits; struct device_node *np; nvmem_cell_post_process_t read_post_process; + void *priv; }; /** -- cgit v1.2.3 From 55d4980ce55b6bb4be66877de4dbec513911b988 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Rafa=C5=82=20Mi=C5=82ecki?= Date: Tue, 4 Apr 2023 18:21:42 +0100 Subject: nvmem: core: support specifying both: cell raw data & post read lengths MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Callback .read_post_process() is designed to modify raw cell content before providing it to the consumer. So far we were dealing with modifications that didn't affect cell size (length). In some cases however cell content needs to be reformatted and resized. It's required e.g. to provide properly formatted MAC address in case it's stored in a non-binary format (e.g. using ASCII). There were few discussions how to optimally handle that. Following possible solutions were considered: 1. Allow .read_post_process() to realloc (resize) content buffer 2. Allow .read_post_process() to adjust (decrease) just buffer length 3. Register NVMEM cells using post-read sizes The preferred solution was the last one. The problem is that simply adjusting "bytes" in NVMEM providers would result in core code NOT passing whole raw data to .read_post_process() callbacks. It means callback functions couldn't do their job without somehow manually reading original cell content on their own. This patch deals with that by registering NVMEM cells with both lengths: raw content one and post read one. It allows: 1. Core code to read whole raw cell content 2. Callbacks to return content they want Signed-off-by: Rafał Miłecki Signed-off-by: Srinivas Kandagatla Link: https://lore.kernel.org/r/20230404172148.82422-35-srinivas.kandagatla@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/nvmem-provider.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nvmem-provider.h b/include/linux/nvmem-provider.h index 0cf9f9490514..8ffb42ba0f62 100644 --- a/include/linux/nvmem-provider.h +++ b/include/linux/nvmem-provider.h @@ -51,6 +51,7 @@ struct nvmem_keepout { * struct nvmem_cell_info - NVMEM cell description * @name: Name. * @offset: Offset within the NVMEM device. + * @raw_len: Length of raw data (without post processing). * @bytes: Length of the cell. * @bit_offset: Bit offset if cell is smaller than a byte. * @nbits: Number of bits. @@ -62,6 +63,7 @@ struct nvmem_keepout { struct nvmem_cell_info { const char *name; unsigned int offset; + size_t raw_len; unsigned int bytes; unsigned int bit_offset; unsigned int nbits; -- cgit v1.2.3 From 814c978f02db17f16e6aa2efa2a929372f06da09 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Tue, 4 Apr 2023 18:21:44 +0100 Subject: nvmem: Add macro to register nvmem layout drivers MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Provide a module_nvmem_layout_driver() macro at the end of the nvmem-provider.h header to reduce the boilerplate when registering nvmem layout drivers. Suggested-by: Srinivas Kandagatla Signed-off-by: Miquel Raynal Acked-by: Rafał Miłecki Signed-off-by: Srinivas Kandagatla Link: https://lore.kernel.org/r/20230404172148.82422-37-srinivas.kandagatla@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/nvmem-provider.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nvmem-provider.h b/include/linux/nvmem-provider.h index 8ffb42ba0f62..dae26295e6be 100644 --- a/include/linux/nvmem-provider.h +++ b/include/linux/nvmem-provider.h @@ -9,6 +9,7 @@ #ifndef _LINUX_NVMEM_PROVIDER_H #define _LINUX_NVMEM_PROVIDER_H +#include #include #include #include @@ -242,4 +243,9 @@ nvmem_layout_get_match_data(struct nvmem_device *nvmem, } #endif /* CONFIG_NVMEM */ + +#define module_nvmem_layout_driver(__layout_driver) \ + module_driver(__layout_driver, nvmem_layout_register, \ + nvmem_layout_unregister) + #endif /* ifndef _LINUX_NVMEM_PROVIDER_H */ -- cgit v1.2.3 From 14e985482111a2c6bc75a0348701a4acdc5558d8 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Sun, 2 Apr 2023 11:42:07 +0200 Subject: clk: Remove mmask and nmask fields in struct clk_fractional_divider All users of these fields have been removed. They are now computed when needed with [mn]shift and [mn]width. This shrinks the size of struct clk_fractional_divider from 72 to 56 bytes. Signed-off-by: Christophe JAILLET Link: https://lore.kernel.org/r/680357e5acb338433bfc94114b65b4a4ce2c99e2.1680423909.git.christophe.jaillet@wanadoo.fr Reviewed-by: Heiko Stuebner Signed-off-by: Stephen Boyd --- include/linux/clk-provider.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index 842e72a5348f..3271a2bc352f 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -1135,10 +1135,8 @@ struct clk_fractional_divider { void __iomem *reg; u8 mshift; u8 mwidth; - u32 mmask; u8 nshift; u8 nwidth; - u32 nmask; u8 flags; void (*approximation)(struct clk_hw *hw, unsigned long rate, unsigned long *parent_rate, -- cgit v1.2.3 From 02992064bdffc97403b6058491094cd41d1a11ef Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Tue, 4 Apr 2023 10:45:25 -0500 Subject: PCI: Make pci_bus_for_each_resource() index optional MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Refactor pci_bus_for_each_resource() in the same way as pci_dev_for_each_resource(). This allows the index to be hidden inside the implementation so the caller can omit it when it's not used otherwise. No functional changes intended. Link: https://lore.kernel.org/r/20230330162434.35055-6-andriy.shevchenko@linux.intel.com Signed-off-by: Andy Shevchenko Signed-off-by: Bjorn Helgaas Reviewed-by: Krzysztof Wilczyński Reviewed-by: Philippe Mathieu-Daudé --- include/linux/pci.h | 24 +++++++++++++++++++----- 1 file changed, 19 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index db3155562320..c048e70d42b9 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1444,11 +1444,21 @@ int devm_request_pci_bus_resources(struct device *dev, /* Temporary until new and working PCI SBR API in place */ int pci_bridge_secondary_bus_reset(struct pci_dev *dev); +#define __pci_bus_for_each_res0(bus, res, ...) \ + for (unsigned int __b = 0; \ + (res = pci_bus_resource_n(bus, __b)) || __b < PCI_BRIDGE_RESOURCE_NUM; \ + __b++) + +#define __pci_bus_for_each_res1(bus, res, __b) \ + for (__b = 0; \ + (res = pci_bus_resource_n(bus, __b)) || __b < PCI_BRIDGE_RESOURCE_NUM; \ + __b++) + /** * pci_bus_for_each_resource - iterate over PCI bus resources * @bus: the PCI bus * @res: pointer to the current resource - * @i: index of the current resource + * @...: optional index of the current resource * * Iterate over PCI bus resources. The first part is to go over PCI bus * resource array, which has at most the %PCI_BRIDGE_RESOURCE_NUM entries. @@ -1461,13 +1471,17 @@ int pci_bridge_secondary_bus_reset(struct pci_dev *dev); * struct resource *res; * unsigned int i; * + * // With optional index * pci_bus_for_each_resource(bus, res, i) * pr_info("PCI bus resource[%u]: %pR\n", i, res); + * + * // Without index + * pci_bus_for_each_resource(bus, res) + * _do_something_(res); */ -#define pci_bus_for_each_resource(bus, res, i) \ - for (i = 0; \ - (res = pci_bus_resource_n(bus, i)) || i < PCI_BRIDGE_RESOURCE_NUM; \ - i++) +#define pci_bus_for_each_resource(bus, res, ...) \ + CONCATENATE(__pci_bus_for_each_res, COUNT_ARGS(__VA_ARGS__)) \ + (bus, res, __VA_ARGS__) int __must_check pci_bus_alloc_resource(struct pci_bus *bus, struct resource *res, resource_size_t size, -- cgit v1.2.3 From 3dd4432549415f3c65dd52d5c687629efbf4ece1 Mon Sep 17 00:00:00 2001 From: "Liam R. Howlett" Date: Mon, 27 Feb 2023 09:36:07 -0800 Subject: mm: enable maple tree RCU mode by default Use the maple tree in RCU mode for VMA tracking. The maple tree tracks the stack and is able to update the pivot (lower/upper boundary) in-place to allow the page fault handler to write to the tree while holding just the mmap read lock. This is safe as the writes to the stack have a guard VMA which ensures there will always be a NULL in the direction of the growth and thus will only update a pivot. It is possible, but not recommended, to have VMAs that grow up/down without guard VMAs. syzbot has constructed a testcase which sets up a VMA to grow and consume the empty space. Overwriting the entire NULL entry causes the tree to be altered in a way that is not safe for concurrent readers; the readers may see a node being rewritten or one that does not match the maple state they are using. Enabling RCU mode allows the concurrent readers to see a stable node and will return the expected result. [Liam.Howlett@Oracle.com: we don't need to free the nodes with RCU[ Link: https://lore.kernel.org/linux-mm/000000000000b0a65805f663ace6@google.com/ Link: https://lkml.kernel.org/r/20230227173632.3292573-9-surenb@google.com Fixes: d4af56c5c7c6 ("mm: start tracking VMAs with maple tree") Signed-off-by: Liam R. Howlett Signed-off-by: Suren Baghdasaryan Reported-by: syzbot+8d95422d3537159ca390@syzkaller.appspotmail.com Cc: Signed-off-by: Andrew Morton --- include/linux/mm_types.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 0722859c3647..a57e6ae78e65 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -774,7 +774,8 @@ struct mm_struct { unsigned long cpu_bitmap[]; }; -#define MM_MT_FLAGS (MT_FLAGS_ALLOC_RANGE | MT_FLAGS_LOCK_EXTERN) +#define MM_MT_FLAGS (MT_FLAGS_ALLOC_RANGE | MT_FLAGS_LOCK_EXTERN | \ + MT_FLAGS_USE_RCU) extern struct mm_struct init_mm; /* Pointer magic because the dynamic array size confuses some compilers. */ -- cgit v1.2.3 From 10739ea3132861b1344264b110ea48d951a0e3b0 Mon Sep 17 00:00:00 2001 From: Shenwei Wang Date: Mon, 3 Apr 2023 17:23:01 -0500 Subject: net: stmmac: add support for platform specific reset This patch adds support for platform-specific reset logic in the stmmac driver. Some SoCs require a different reset mechanism than the standard dwmac IP reset. To support these platforms, a new function pointer 'fix_soc_reset' is added to the plat_stmmacenet_data structure. The stmmac_reset in hwif.h is modified to call the 'fix_soc_reset' function if it exists. This enables the driver to use the platform-specific reset logic when necessary. Signed-off-by: Shenwei Wang Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20230403222302.328262-1-shenwei.wang@nxp.com Signed-off-by: Jakub Kicinski --- include/linux/stmmac.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index a2414c187483..dafa001e9e7a 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -223,6 +223,7 @@ struct plat_stmmacenet_data { struct stmmac_rxq_cfg rx_queues_cfg[MTL_MAX_RX_QUEUES]; struct stmmac_txq_cfg tx_queues_cfg[MTL_MAX_TX_QUEUES]; void (*fix_mac_speed)(void *priv, unsigned int speed); + int (*fix_soc_reset)(void *priv, void __iomem *ioaddr); int (*serdes_powerup)(struct net_device *ndev, void *priv); void (*serdes_powerdown)(struct net_device *ndev, void *priv); void (*speed_mode_2500)(struct net_device *ndev, void *priv); -- cgit v1.2.3 From 263e721e3ba1f3b42ad61aed3d504f3c8c9c0eb6 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 7 Mar 2023 15:34:05 +0100 Subject: mm: make mapping_get_entry available outside of filemap.c mapping_get_entry is useful for page cache API users that need to know about xa_value internals. Rename it and make it available in pagemap.h. Link: https://lkml.kernel.org/r/20230307143410.28031-3-hch@lst.de Signed-off-by: Christoph Hellwig Reviewed-by: Matthew Wilcox (Oracle) Cc: Andreas Gruenbacher Cc: Hugh Dickins Cc: Ryusuke Konishi Signed-off-by: Andrew Morton --- include/linux/pagemap.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 853184a46411..bcfd798ce0b9 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -507,6 +507,7 @@ pgoff_t page_cache_prev_miss(struct address_space *mapping, #define FGP_ENTRY 0x00000080 #define FGP_STABLE 0x00000100 +void *filemap_get_entry(struct address_space *mapping, pgoff_t index); struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index, int fgp_flags, gfp_t gfp); struct page *pagecache_get_page(struct address_space *mapping, pgoff_t index, -- cgit v1.2.3 From 48c9d11375fc66f1e59d0e9b27d121e015a50904 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 7 Mar 2023 15:34:09 +0100 Subject: mm: remove FGP_ENTRY FGP_ENTRY is unused now, so remove it. Link: https://lkml.kernel.org/r/20230307143410.28031-7-hch@lst.de Signed-off-by: Christoph Hellwig Cc: Andreas Gruenbacher Cc: Hugh Dickins Cc: Matthew Wilcox (Oracle) Cc: Ryusuke Konishi Signed-off-by: Andrew Morton --- include/linux/pagemap.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index bcfd798ce0b9..306a0f63cea8 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -504,8 +504,7 @@ pgoff_t page_cache_prev_miss(struct address_space *mapping, #define FGP_NOFS 0x00000010 #define FGP_NOWAIT 0x00000020 #define FGP_FOR_MMAP 0x00000040 -#define FGP_ENTRY 0x00000080 -#define FGP_STABLE 0x00000100 +#define FGP_STABLE 0x00000080 void *filemap_get_entry(struct address_space *mapping, pgoff_t index); struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index, -- cgit v1.2.3 From 66dabbb65d673aef40dd17bf62c042be8f6d4a4b Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 7 Mar 2023 15:34:10 +0100 Subject: mm: return an ERR_PTR from __filemap_get_folio Instead of returning NULL for all errors, distinguish between: - no entry found and not asked to allocated (-ENOENT) - failed to allocate memory (-ENOMEM) - would block (-EAGAIN) so that callers don't have to guess the error based on the passed in flags. Also pass through the error through the direct callers: filemap_get_folio, filemap_lock_folio filemap_grab_folio and filemap_get_incore_folio. [hch@lst.de: fix null-pointer deref] Link: https://lkml.kernel.org/r/20230310070023.GA13563@lst.de Link: https://lkml.kernel.org/r/20230310043137.GA1624890@u2004 Link: https://lkml.kernel.org/r/20230307143410.28031-8-hch@lst.de Signed-off-by: Christoph Hellwig Acked-by: Ryusuke Konishi [nilfs2] Cc: Andreas Gruenbacher Cc: Hugh Dickins Cc: Matthew Wilcox (Oracle) Cc: Naoya Horiguchi Signed-off-by: Andrew Morton --- include/linux/pagemap.h | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 306a0f63cea8..fdcd595d2294 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -520,7 +520,8 @@ struct page *pagecache_get_page(struct address_space *mapping, pgoff_t index, * Looks up the page cache entry at @mapping & @index. If a folio is * present, it is returned with an increased refcount. * - * Otherwise, %NULL is returned. + * Return: A folio or ERR_PTR(-ENOENT) if there is no folio in the cache for + * this index. Will not return a shadow, swap or DAX entry. */ static inline struct folio *filemap_get_folio(struct address_space *mapping, pgoff_t index) @@ -537,8 +538,8 @@ static inline struct folio *filemap_get_folio(struct address_space *mapping, * present, it is returned locked with an increased refcount. * * Context: May sleep. - * Return: A folio or %NULL if there is no folio in the cache for this - * index. Will not return a shadow, swap or DAX entry. + * Return: A folio or ERR_PTR(-ENOENT) if there is no folio in the cache for + * this index. Will not return a shadow, swap or DAX entry. */ static inline struct folio *filemap_lock_folio(struct address_space *mapping, pgoff_t index) @@ -555,8 +556,8 @@ static inline struct folio *filemap_lock_folio(struct address_space *mapping, * a new folio is created. The folio is locked, marked as accessed, and * returned. * - * Return: A found or created folio. NULL if no folio is found and failed to - * create a folio. + * Return: A found or created folio. ERR_PTR(-ENOMEM) if no folio is found + * and failed to create a folio. */ static inline struct folio *filemap_grab_folio(struct address_space *mapping, pgoff_t index) -- cgit v1.2.3 From 2bad466cc9d9b4c3b4b16eb9c03c919b59561316 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Thu, 9 Mar 2023 17:37:10 -0500 Subject: mm/uffd: UFFD_FEATURE_WP_UNPOPULATED Patch series "mm/uffd: Add feature bit UFFD_FEATURE_WP_UNPOPULATED", v4. The new feature bit makes anonymous memory acts the same as file memory on userfaultfd-wp in that it'll also wr-protect none ptes. It can be useful in two cases: (1) Uffd-wp app that needs to wr-protect none ptes like QEMU snapshot, so pre-fault can be replaced by enabling this flag and speed up protections (2) It helps to implement async uffd-wp mode that Muhammad is working on [1] It's debatable whether this is the most ideal solution because with the new feature bit set, wr-protect none pte needs to pre-populate the pgtables to the last level (PAGE_SIZE). But it seems fine so far to service either purpose above, so we can leave optimizations for later. The series brings pte markers to anonymous memory too. There's some change in the common mm code path in the 1st patch, great to have some eye looking at it, but hopefully they're still relatively straightforward. This patch (of 2): This is a new feature that controls how uffd-wp handles none ptes. When it's set, the kernel will handle anonymous memory the same way as file memory, by allowing the user to wr-protect unpopulated ptes. File memories handles none ptes consistently by allowing wr-protecting of none ptes because of the unawareness of page cache being exist or not. For anonymous it was not as persistent because we used to assume that we don't need protections on none ptes or known zero pages. One use case of such a feature bit was VM live snapshot, where if without wr-protecting empty ptes the snapshot can contain random rubbish in the holes of the anonymous memory, which can cause misbehave of the guest when the guest OS assumes the pages should be all zeros. QEMU worked it around by pre-populate the section with reads to fill in zero page entries before starting the whole snapshot process [1]. Recently there's another need raised on using userfaultfd wr-protect for detecting dirty pages (to replace soft-dirty in some cases) [2]. In that case if without being able to wr-protect none ptes by default, the dirty info can get lost, since we cannot treat every none pte to be dirty (the current design is identify a page dirty based on uffd-wp bit being cleared). In general, we want to be able to wr-protect empty ptes too even for anonymous. This patch implements UFFD_FEATURE_WP_UNPOPULATED so that it'll make uffd-wp handling on none ptes being consistent no matter what the memory type is underneath. It doesn't have any impact on file memories so far because we already have pte markers taking care of that. So it only affects anonymous. The feature bit is by default off, so the old behavior will be maintained. Sometimes it may be wanted because the wr-protect of none ptes will contain overheads not only during UFFDIO_WRITEPROTECT (by applying pte markers to anonymous), but also on creating the pgtables to store the pte markers. So there's potentially less chance of using thp on the first fault for a none pmd or larger than a pmd. The major implementation part is teaching the whole kernel to understand pte markers even for anonymously mapped ranges, meanwhile allowing the UFFDIO_WRITEPROTECT ioctl to apply pte markers for anonymous too when the new feature bit is set. Note that even if the patch subject starts with mm/uffd, there're a few small refactors to major mm path of handling anonymous page faults. But they should be straightforward. With WP_UNPOPUATED, application like QEMU can avoid pre-read faults all the memory before wr-protect during taking a live snapshot. Quotting from Muhammad's test result here [3] based on a simple program [4]: (1) With huge page disabled echo madvise > /sys/kernel/mm/transparent_hugepage/enabled ./uffd_wp_perf Test DEFAULT: 4 Test PRE-READ: 1111453 (pre-fault 1101011) Test MADVISE: 278276 (pre-fault 266378) Test WP-UNPOPULATE: 11712 (2) With Huge page enabled echo always > /sys/kernel/mm/transparent_hugepage/enabled ./uffd_wp_perf Test DEFAULT: 4 Test PRE-READ: 22521 (pre-fault 22348) Test MADVISE: 4909 (pre-fault 4743) Test WP-UNPOPULATE: 14448 There'll be a great perf boost for no-thp case, while for thp enabled with extreme case of all-thp-zero WP_UNPOPULATED can be slower than MADVISE, but that's low possibility in reality, also the overhead was not reduced but postponed until a follow up write on any huge zero thp, so potentially it is faster by making the follow up writes slower. [1] https://lore.kernel.org/all/20210401092226.102804-4-andrey.gruzdev@virtuozzo.com/ [2] https://lore.kernel.org/all/Y+v2HJ8+3i%2FKzDBu@x1n/ [3] https://lore.kernel.org/all/d0eb0a13-16dc-1ac1-653a-78b7273781e3@collabora.com/ [4] https://github.com/xzpeter/clibs/blob/master/uffd-test/uffd-wp-perf.c [peterx@redhat.com: comment changes, oneliner fix to khugepaged] Link: https://lkml.kernel.org/r/ZB2/8jPhD3fpx5U8@x1n Link: https://lkml.kernel.org/r/20230309223711.823547-1-peterx@redhat.com Link: https://lkml.kernel.org/r/20230309223711.823547-2-peterx@redhat.com Signed-off-by: Peter Xu Acked-by: David Hildenbrand Cc: Andrea Arcangeli Cc: Axel Rasmussen Cc: Mike Rapoport Cc: Muhammad Usama Anjum Cc: Nadav Amit Cc: Paul Gofman Signed-off-by: Andrew Morton --- include/linux/mm_inline.h | 6 ++++++ include/linux/userfaultfd_k.h | 23 +++++++++++++++++++++++ 2 files changed, 29 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h index de1e622dd366..0e1d239a882c 100644 --- a/include/linux/mm_inline.h +++ b/include/linux/mm_inline.h @@ -557,6 +557,12 @@ pte_install_uffd_wp_if_needed(struct vm_area_struct *vma, unsigned long addr, /* The current status of the pte should be "cleared" before calling */ WARN_ON_ONCE(!pte_none(*pte)); + /* + * NOTE: userfaultfd_wp_unpopulated() doesn't need this whole + * thing, because when zapping either it means it's dropping the + * page, or in TTU where the present pte will be quickly replaced + * with a swap pte. There's no way of leaking the bit. + */ if (vma_is_anonymous(vma) || !userfaultfd_wp(vma)) return; diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h index 3767f18114ef..0cf8880219da 100644 --- a/include/linux/userfaultfd_k.h +++ b/include/linux/userfaultfd_k.h @@ -179,6 +179,7 @@ extern int userfaultfd_unmap_prep(struct mm_struct *mm, unsigned long start, unsigned long end, struct list_head *uf); extern void userfaultfd_unmap_complete(struct mm_struct *mm, struct list_head *uf); +extern bool userfaultfd_wp_unpopulated(struct vm_area_struct *vma); #else /* CONFIG_USERFAULTFD */ @@ -274,8 +275,30 @@ static inline bool uffd_disable_fault_around(struct vm_area_struct *vma) return false; } +static inline bool userfaultfd_wp_unpopulated(struct vm_area_struct *vma) +{ + return false; +} + #endif /* CONFIG_USERFAULTFD */ +static inline bool userfaultfd_wp_use_markers(struct vm_area_struct *vma) +{ + /* Only wr-protect mode uses pte markers */ + if (!userfaultfd_wp(vma)) + return false; + + /* File-based uffd-wp always need markers */ + if (!vma_is_anonymous(vma)) + return true; + + /* + * Anonymous uffd-wp only needs the markers if WP_UNPOPULATED + * enabled (to apply markers on zero pages). + */ + return userfaultfd_wp_unpopulated(vma); +} + static inline bool pte_marker_entry_uffd_wp(swp_entry_t entry) { #ifdef CONFIG_PTE_MARKER_UFFD_WP -- cgit v1.2.3 From 23baf831a32c04f9a968812511540b1b3e648bf5 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Wed, 15 Mar 2023 14:31:33 +0300 Subject: mm, treewide: redefine MAX_ORDER sanely MAX_ORDER currently defined as number of orders page allocator supports: user can ask buddy allocator for page order between 0 and MAX_ORDER-1. This definition is counter-intuitive and lead to number of bugs all over the kernel. Change the definition of MAX_ORDER to be inclusive: the range of orders user can ask from buddy allocator is 0..MAX_ORDER now. [kirill@shutemov.name: fix min() warning] Link: https://lkml.kernel.org/r/20230315153800.32wib3n5rickolvh@box [akpm@linux-foundation.org: fix another min_t warning] [kirill@shutemov.name: fixups per Zi Yan] Link: https://lkml.kernel.org/r/20230316232144.b7ic4cif4kjiabws@box.shutemov.name [akpm@linux-foundation.org: fix underlining in docs] Link: https://lore.kernel.org/oe-kbuild-all/202303191025.VRCTk6mP-lkp@intel.com/ Link: https://lkml.kernel.org/r/20230315113133.11326-11-kirill.shutemov@linux.intel.com Signed-off-by: Kirill A. Shutemov Reviewed-by: Michael Ellerman [powerpc] Cc: "Kirill A. Shutemov" Cc: Zi Yan Signed-off-by: Andrew Morton --- include/linux/hugetlb.h | 2 +- include/linux/mmzone.h | 10 +++++----- include/linux/pageblock-flags.h | 4 ++-- include/linux/slab.h | 6 +++--- 4 files changed, 11 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 7c977d234aba..8fb7d91cd0b1 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -818,7 +818,7 @@ static inline unsigned huge_page_shift(struct hstate *h) static inline bool hstate_is_gigantic(struct hstate *h) { - return huge_page_order(h) >= MAX_ORDER; + return huge_page_order(h) > MAX_ORDER; } static inline unsigned int pages_per_huge_page(const struct hstate *h) diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index bf8786d45b31..35b11cc210d9 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -26,11 +26,11 @@ /* Free memory management - zoned buddy allocator. */ #ifndef CONFIG_ARCH_FORCE_MAX_ORDER -#define MAX_ORDER 11 +#define MAX_ORDER 10 #else #define MAX_ORDER CONFIG_ARCH_FORCE_MAX_ORDER #endif -#define MAX_ORDER_NR_PAGES (1 << (MAX_ORDER - 1)) +#define MAX_ORDER_NR_PAGES (1 << MAX_ORDER) /* * PAGE_ALLOC_COSTLY_ORDER is the order at which allocations are deemed @@ -93,7 +93,7 @@ static inline bool migratetype_is_mergeable(int mt) } #define for_each_migratetype_order(order, type) \ - for (order = 0; order < MAX_ORDER; order++) \ + for (order = 0; order <= MAX_ORDER; order++) \ for (type = 0; type < MIGRATE_TYPES; type++) extern int page_group_by_mobility_disabled; @@ -922,7 +922,7 @@ struct zone { CACHELINE_PADDING(_pad1_); /* free areas of different sizes */ - struct free_area free_area[MAX_ORDER]; + struct free_area free_area[MAX_ORDER + 1]; /* zone flags, see below */ unsigned long flags; @@ -1745,7 +1745,7 @@ static inline bool movable_only_nodes(nodemask_t *nodes) #define SECTION_BLOCKFLAGS_BITS \ ((1UL << (PFN_SECTION_SHIFT - pageblock_order)) * NR_PAGEBLOCK_BITS) -#if (MAX_ORDER - 1 + PAGE_SHIFT) > SECTION_SIZE_BITS +#if (MAX_ORDER + PAGE_SHIFT) > SECTION_SIZE_BITS #error Allocator MAX_ORDER exceeds SECTION_SIZE #endif diff --git a/include/linux/pageblock-flags.h b/include/linux/pageblock-flags.h index 5f1ae07d724b..e83c4c095041 100644 --- a/include/linux/pageblock-flags.h +++ b/include/linux/pageblock-flags.h @@ -41,14 +41,14 @@ extern unsigned int pageblock_order; * Huge pages are a constant size, but don't exceed the maximum allocation * granularity. */ -#define pageblock_order min_t(unsigned int, HUGETLB_PAGE_ORDER, MAX_ORDER - 1) +#define pageblock_order min_t(unsigned int, HUGETLB_PAGE_ORDER, MAX_ORDER) #endif /* CONFIG_HUGETLB_PAGE_SIZE_VARIABLE */ #else /* CONFIG_HUGETLB_PAGE */ /* If huge pages are not used, group by MAX_ORDER_NR_PAGES */ -#define pageblock_order (MAX_ORDER-1) +#define pageblock_order MAX_ORDER #endif /* CONFIG_HUGETLB_PAGE */ diff --git a/include/linux/slab.h b/include/linux/slab.h index 45af70315a94..aa4575ef2965 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -284,7 +284,7 @@ static inline unsigned int arch_slab_minalign(void) * (PAGE_SIZE*2). Larger requests are passed to the page allocator. */ #define KMALLOC_SHIFT_HIGH (PAGE_SHIFT + 1) -#define KMALLOC_SHIFT_MAX (MAX_ORDER + PAGE_SHIFT - 1) +#define KMALLOC_SHIFT_MAX (MAX_ORDER + PAGE_SHIFT) #ifndef KMALLOC_SHIFT_LOW #define KMALLOC_SHIFT_LOW 5 #endif @@ -292,7 +292,7 @@ static inline unsigned int arch_slab_minalign(void) #ifdef CONFIG_SLUB #define KMALLOC_SHIFT_HIGH (PAGE_SHIFT + 1) -#define KMALLOC_SHIFT_MAX (MAX_ORDER + PAGE_SHIFT - 1) +#define KMALLOC_SHIFT_MAX (MAX_ORDER + PAGE_SHIFT) #ifndef KMALLOC_SHIFT_LOW #define KMALLOC_SHIFT_LOW 3 #endif @@ -305,7 +305,7 @@ static inline unsigned int arch_slab_minalign(void) * be allocated from the same page. */ #define KMALLOC_SHIFT_HIGH PAGE_SHIFT -#define KMALLOC_SHIFT_MAX (MAX_ORDER + PAGE_SHIFT - 1) +#define KMALLOC_SHIFT_MAX (MAX_ORDER + PAGE_SHIFT) #ifndef KMALLOC_SHIFT_LOW #define KMALLOC_SHIFT_LOW 3 #endif -- cgit v1.2.3 From a734991ccaec1985fff42fb26bb6d789d35defb4 Mon Sep 17 00:00:00 2001 From: Axel Rasmussen Date: Tue, 14 Mar 2023 15:12:47 -0700 Subject: mm: userfaultfd: rename functions for clarity + consistency Patch series "mm: userfaultfd: refactor and add UFFDIO_CONTINUE_MODE_WP", v5. - Commits 1-3 refactor userfaultfd ioctl code without behavior changes, with the main goal of improving consistency and reducing the number of function args. - Commit 4 adds UFFDIO_CONTINUE_MODE_WP. This patch (of 4): The basic problem is, over time we've added new userfaultfd ioctls, and we've refactored the code so functions which used to handle only one case are now re-used to deal with several cases. While this happened, we didn't bother to rename the functions. Similarly, as we added new functions, we cargo-culted pieces of the now-inconsistent naming scheme, so those functions too ended up with names that don't make a lot of sense. A key point here is, "copy" in most userfaultfd code refers specifically to UFFDIO_COPY, where we allocate a new page and copy its contents from userspace. There are many functions with "copy" in the name that don't actually do this (at least in some cases). So, rename things into a consistent scheme. The high level idea is that the call stack for userfaultfd ioctls becomes: userfaultfd_ioctl -> userfaultfd_(particular ioctl) -> mfill_atomic_(particular kind of fill operation) -> mfill_atomic /* loops over pages in range */ -> mfill_atomic_pte /* deals with single pages */ -> mfill_atomic_pte_(particular kind of fill operation) -> mfill_atomic_install_pte There are of course some special cases (shmem, hugetlb), but this is the general structure which all function names now adhere to. Link: https://lkml.kernel.org/r/20230314221250.682452-1-axelrasmussen@google.com Link: https://lkml.kernel.org/r/20230314221250.682452-2-axelrasmussen@google.com Signed-off-by: Axel Rasmussen Acked-by: Peter Xu Acked-by: Mike Rapoport (IBM) Cc: Al Viro Cc: Hugh Dickins Cc: James Houghton Cc: Jan Kara Cc: Liam R. Howlett Cc: Matthew Wilcox (Oracle) Cc: Mike Kravetz Cc: Muchun Song Cc: Nadav Amit Cc: Shuah Khan Signed-off-by: Andrew Morton --- include/linux/hugetlb.h | 30 +++++++++++++++--------------- include/linux/userfaultfd_k.h | 18 +++++++++--------- 2 files changed, 24 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 8fb7d91cd0b1..152434396c48 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -158,13 +158,13 @@ unsigned long hugetlb_total_pages(void); vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, unsigned int flags); #ifdef CONFIG_USERFAULTFD -int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm, pte_t *dst_pte, - struct vm_area_struct *dst_vma, - unsigned long dst_addr, - unsigned long src_addr, - enum mcopy_atomic_mode mode, - struct page **pagep, - bool wp_copy); +int hugetlb_mfill_atomic_pte(struct mm_struct *dst_mm, pte_t *dst_pte, + struct vm_area_struct *dst_vma, + unsigned long dst_addr, + unsigned long src_addr, + enum mcopy_atomic_mode mode, + struct page **pagep, + bool wp_copy); #endif /* CONFIG_USERFAULTFD */ bool hugetlb_reserve_pages(struct inode *inode, long from, long to, struct vm_area_struct *vma, @@ -393,14 +393,14 @@ static inline void hugetlb_free_pgd_range(struct mmu_gather *tlb, } #ifdef CONFIG_USERFAULTFD -static inline int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm, - pte_t *dst_pte, - struct vm_area_struct *dst_vma, - unsigned long dst_addr, - unsigned long src_addr, - enum mcopy_atomic_mode mode, - struct page **pagep, - bool wp_copy) +static inline int hugetlb_mfill_atomic_pte(struct mm_struct *dst_mm, + pte_t *dst_pte, + struct vm_area_struct *dst_vma, + unsigned long dst_addr, + unsigned long src_addr, + enum mcopy_atomic_mode mode, + struct page **pagep, + bool wp_copy) { BUG(); return 0; diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h index 0cf8880219da..ac178d810dc7 100644 --- a/include/linux/userfaultfd_k.h +++ b/include/linux/userfaultfd_k.h @@ -61,15 +61,15 @@ extern int mfill_atomic_install_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd, unsigned long dst_addr, struct page *page, bool newly_allocated, bool wp_copy); -extern ssize_t mcopy_atomic(struct mm_struct *dst_mm, unsigned long dst_start, - unsigned long src_start, unsigned long len, - atomic_t *mmap_changing, __u64 mode); -extern ssize_t mfill_zeropage(struct mm_struct *dst_mm, - unsigned long dst_start, - unsigned long len, - atomic_t *mmap_changing); -extern ssize_t mcopy_continue(struct mm_struct *dst_mm, unsigned long dst_start, - unsigned long len, atomic_t *mmap_changing); +extern ssize_t mfill_atomic_copy(struct mm_struct *dst_mm, unsigned long dst_start, + unsigned long src_start, unsigned long len, + atomic_t *mmap_changing, __u64 mode); +extern ssize_t mfill_atomic_zeropage(struct mm_struct *dst_mm, + unsigned long dst_start, + unsigned long len, + atomic_t *mmap_changing); +extern ssize_t mfill_atomic_continue(struct mm_struct *dst_mm, unsigned long dst_start, + unsigned long len, atomic_t *mmap_changing); extern int mwriteprotect_range(struct mm_struct *dst_mm, unsigned long start, unsigned long len, bool enable_wp, atomic_t *mmap_changing); -- cgit v1.2.3 From 61c5004022f56c443b86800e8985d8803f3a22aa Mon Sep 17 00:00:00 2001 From: Axel Rasmussen Date: Tue, 14 Mar 2023 15:12:48 -0700 Subject: mm: userfaultfd: don't pass around both mm and vma Quite a few userfaultfd functions took both mm and vma pointers as arguments. Since the mm is trivially accessible via vma->vm_mm, there's no reason to pass both; it just needlessly extends the already long argument list. Get rid of the mm pointer, where possible, to shorten the argument list. Link: https://lkml.kernel.org/r/20230314221250.682452-3-axelrasmussen@google.com Signed-off-by: Axel Rasmussen Acked-by: Peter Xu Acked-by: Mike Rapoport (IBM) Cc: Al Viro Cc: Hugh Dickins Cc: James Houghton Cc: Jan Kara Cc: Liam R. Howlett Cc: Matthew Wilcox (Oracle) Cc: Mike Kravetz Cc: Muchun Song Cc: Nadav Amit Cc: Shuah Khan Signed-off-by: Andrew Morton --- include/linux/hugetlb.h | 5 ++--- include/linux/shmem_fs.h | 4 ++-- include/linux/userfaultfd_k.h | 4 ++-- 3 files changed, 6 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 152434396c48..3cb7cd853fa8 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -158,7 +158,7 @@ unsigned long hugetlb_total_pages(void); vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, unsigned int flags); #ifdef CONFIG_USERFAULTFD -int hugetlb_mfill_atomic_pte(struct mm_struct *dst_mm, pte_t *dst_pte, +int hugetlb_mfill_atomic_pte(pte_t *dst_pte, struct vm_area_struct *dst_vma, unsigned long dst_addr, unsigned long src_addr, @@ -393,8 +393,7 @@ static inline void hugetlb_free_pgd_range(struct mmu_gather *tlb, } #ifdef CONFIG_USERFAULTFD -static inline int hugetlb_mfill_atomic_pte(struct mm_struct *dst_mm, - pte_t *dst_pte, +static inline int hugetlb_mfill_atomic_pte(pte_t *dst_pte, struct vm_area_struct *dst_vma, unsigned long dst_addr, unsigned long src_addr, diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index 50bf82b36995..922a2b45fe6f 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -152,14 +152,14 @@ extern void shmem_uncharge(struct inode *inode, long pages); #ifdef CONFIG_USERFAULTFD #ifdef CONFIG_SHMEM -extern int shmem_mfill_atomic_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd, +extern int shmem_mfill_atomic_pte(pmd_t *dst_pmd, struct vm_area_struct *dst_vma, unsigned long dst_addr, unsigned long src_addr, bool zeropage, bool wp_copy, struct page **pagep); #else /* !CONFIG_SHMEM */ -#define shmem_mfill_atomic_pte(dst_mm, dst_pmd, dst_vma, dst_addr, \ +#define shmem_mfill_atomic_pte(dst_pmd, dst_vma, dst_addr, \ src_addr, zeropage, wp_copy, pagep) ({ BUG(); 0; }) #endif /* CONFIG_SHMEM */ #endif /* CONFIG_USERFAULTFD */ diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h index ac178d810dc7..9458cd94a508 100644 --- a/include/linux/userfaultfd_k.h +++ b/include/linux/userfaultfd_k.h @@ -56,7 +56,7 @@ enum mcopy_atomic_mode { MCOPY_ATOMIC_CONTINUE, }; -extern int mfill_atomic_install_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd, +extern int mfill_atomic_install_pte(pmd_t *dst_pmd, struct vm_area_struct *dst_vma, unsigned long dst_addr, struct page *page, bool newly_allocated, bool wp_copy); @@ -73,7 +73,7 @@ extern ssize_t mfill_atomic_continue(struct mm_struct *dst_mm, unsigned long dst extern int mwriteprotect_range(struct mm_struct *dst_mm, unsigned long start, unsigned long len, bool enable_wp, atomic_t *mmap_changing); -extern long uffd_wp_range(struct mm_struct *dst_mm, struct vm_area_struct *vma, +extern long uffd_wp_range(struct vm_area_struct *vma, unsigned long start, unsigned long len, bool enable_wp); /* mm helpers */ -- cgit v1.2.3 From d9712937037e0ce887920f321429826e9dbfd960 Mon Sep 17 00:00:00 2001 From: Axel Rasmussen Date: Tue, 14 Mar 2023 15:12:49 -0700 Subject: mm: userfaultfd: combine 'mode' and 'wp_copy' arguments Many userfaultfd ioctl functions take both a 'mode' and a 'wp_copy' argument. In future commits we plan to plumb the flags through to more places, so we'd be proliferating the very long argument list even further. Let's take the time to simplify the argument list. Combine the two arguments into one - and generalize, so when we add more flags in the future, it doesn't imply more function arguments. Since the modes (copy, zeropage, continue) are mutually exclusive, store them as an integer value (0, 1, 2) in the low bits. Place combine-able flag bits in the high bits. This is quite similar to an earlier patch proposed by Nadav Amit ("userfaultfd: introduce uffd_flags" [1]). The main difference is that patch only handled flags, whereas this patch *also* combines the "mode" argument into the same type to shorten the argument list. [1]: https://lore.kernel.org/all/20220619233449.181323-2-namit@vmware.com/ Link: https://lkml.kernel.org/r/20230314221250.682452-4-axelrasmussen@google.com Signed-off-by: Axel Rasmussen Acked-by: James Houghton Acked-by: Peter Xu Acked-by: Mike Rapoport (IBM) Cc: Al Viro Cc: Hugh Dickins Cc: Jan Kara Cc: Liam R. Howlett Cc: Matthew Wilcox (Oracle) Cc: Mike Kravetz Cc: Muchun Song Cc: Shuah Khan Signed-off-by: Andrew Morton --- include/linux/hugetlb.h | 10 ++++------ include/linux/shmem_fs.h | 5 +++-- include/linux/userfaultfd_k.h | 46 ++++++++++++++++++++++++++++--------------- 3 files changed, 37 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 3cb7cd853fa8..2a758bcd6719 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -162,9 +162,8 @@ int hugetlb_mfill_atomic_pte(pte_t *dst_pte, struct vm_area_struct *dst_vma, unsigned long dst_addr, unsigned long src_addr, - enum mcopy_atomic_mode mode, - struct page **pagep, - bool wp_copy); + uffd_flags_t flags, + struct page **pagep); #endif /* CONFIG_USERFAULTFD */ bool hugetlb_reserve_pages(struct inode *inode, long from, long to, struct vm_area_struct *vma, @@ -397,9 +396,8 @@ static inline int hugetlb_mfill_atomic_pte(pte_t *dst_pte, struct vm_area_struct *dst_vma, unsigned long dst_addr, unsigned long src_addr, - enum mcopy_atomic_mode mode, - struct page **pagep, - bool wp_copy) + uffd_flags_t flags, + struct page **pagep) { BUG(); return 0; diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index 922a2b45fe6f..3bb8d21edbb3 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -9,6 +9,7 @@ #include #include #include +#include /* inode in-kernel data */ @@ -156,11 +157,11 @@ extern int shmem_mfill_atomic_pte(pmd_t *dst_pmd, struct vm_area_struct *dst_vma, unsigned long dst_addr, unsigned long src_addr, - bool zeropage, bool wp_copy, + uffd_flags_t flags, struct page **pagep); #else /* !CONFIG_SHMEM */ #define shmem_mfill_atomic_pte(dst_pmd, dst_vma, dst_addr, \ - src_addr, zeropage, wp_copy, pagep) ({ BUG(); 0; }) + src_addr, flags, pagep) ({ BUG(); 0; }) #endif /* CONFIG_SHMEM */ #endif /* CONFIG_USERFAULTFD */ diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h index 9458cd94a508..4c477dece540 100644 --- a/include/linux/userfaultfd_k.h +++ b/include/linux/userfaultfd_k.h @@ -40,30 +40,44 @@ extern int sysctl_unprivileged_userfaultfd; extern vm_fault_t handle_userfault(struct vm_fault *vmf, unsigned long reason); -/* - * The mode of operation for __mcopy_atomic and its helpers. - * - * This is almost an implementation detail (mcopy_atomic below doesn't take this - * as a parameter), but it's exposed here because memory-kind-specific - * implementations (e.g. hugetlbfs) need to know the mode of operation. - */ -enum mcopy_atomic_mode { - /* A normal copy_from_user into the destination range. */ - MCOPY_ATOMIC_NORMAL, - /* Don't copy; map the destination range to the zero page. */ - MCOPY_ATOMIC_ZEROPAGE, - /* Just install pte(s) with the existing page(s) in the page cache. */ - MCOPY_ATOMIC_CONTINUE, +/* A combined operation mode + behavior flags. */ +typedef unsigned int __bitwise uffd_flags_t; + +/* Mutually exclusive modes of operation. */ +enum mfill_atomic_mode { + MFILL_ATOMIC_COPY, + MFILL_ATOMIC_ZEROPAGE, + MFILL_ATOMIC_CONTINUE, + NR_MFILL_ATOMIC_MODES, }; +#define MFILL_ATOMIC_MODE_BITS (const_ilog2(NR_MFILL_ATOMIC_MODES - 1) + 1) +#define MFILL_ATOMIC_BIT(nr) BIT(MFILL_ATOMIC_MODE_BITS + (nr)) +#define MFILL_ATOMIC_FLAG(nr) ((__force uffd_flags_t) MFILL_ATOMIC_BIT(nr)) +#define MFILL_ATOMIC_MODE_MASK ((__force uffd_flags_t) (MFILL_ATOMIC_BIT(0) - 1)) + +static inline bool uffd_flags_mode_is(uffd_flags_t flags, enum mfill_atomic_mode expected) +{ + return (flags & MFILL_ATOMIC_MODE_MASK) == ((__force uffd_flags_t) expected); +} + +static inline uffd_flags_t uffd_flags_set_mode(uffd_flags_t flags, enum mfill_atomic_mode mode) +{ + flags &= ~MFILL_ATOMIC_MODE_MASK; + return flags | ((__force uffd_flags_t) mode); +} + +/* Flags controlling behavior. These behavior changes are mode-independent. */ +#define MFILL_ATOMIC_WP MFILL_ATOMIC_FLAG(0) + extern int mfill_atomic_install_pte(pmd_t *dst_pmd, struct vm_area_struct *dst_vma, unsigned long dst_addr, struct page *page, - bool newly_allocated, bool wp_copy); + bool newly_allocated, uffd_flags_t flags); extern ssize_t mfill_atomic_copy(struct mm_struct *dst_mm, unsigned long dst_start, unsigned long src_start, unsigned long len, - atomic_t *mmap_changing, __u64 mode); + atomic_t *mmap_changing, uffd_flags_t flags); extern ssize_t mfill_atomic_zeropage(struct mm_struct *dst_mm, unsigned long dst_start, unsigned long len, -- cgit v1.2.3 From 0289184476c845968ad6ac9083c96cc0f75ca505 Mon Sep 17 00:00:00 2001 From: Axel Rasmussen Date: Tue, 14 Mar 2023 15:12:50 -0700 Subject: mm: userfaultfd: add UFFDIO_CONTINUE_MODE_WP to install WP PTEs UFFDIO_COPY already has UFFDIO_COPY_MODE_WP, so when installing a new PTE to resolve a missing fault, one can install a write-protected one. This is useful when using UFFDIO_REGISTER_MODE_{MISSING,WP} in combination. This was motivated by testing HugeTLB HGM [1], and in particular its interaction with userfaultfd features. Existing userfaultfd code supports using WP and MINOR modes together (i.e. you can register an area with both enabled), but without this CONTINUE flag the combination is in practice unusable. So, add an analogous UFFDIO_CONTINUE_MODE_WP, which does the same thing as UFFDIO_COPY_MODE_WP, but for *minor* faults. Update the selftest to do some very basic exercising of the new flag. Update Documentation/ to describe how these flags are used (neither the COPY nor the new CONTINUE versions of this mode flag were described there before). [1]: https://patchwork.kernel.org/project/linux-mm/cover/20230218002819.1486479-1-jthoughton@google.com/ Link: https://lkml.kernel.org/r/20230314221250.682452-5-axelrasmussen@google.com Signed-off-by: Axel Rasmussen Acked-by: Peter Xu Acked-by: Mike Rapoport (IBM) Cc: Al Viro Cc: Hugh Dickins Cc: Jan Kara Cc: Liam R. Howlett Cc: Matthew Wilcox (Oracle) Cc: Mike Kravetz Cc: Muchun Song Cc: Nadav Amit Cc: Shuah Khan Signed-off-by: Andrew Morton --- include/linux/userfaultfd_k.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h index 4c477dece540..a2c53e98dfd6 100644 --- a/include/linux/userfaultfd_k.h +++ b/include/linux/userfaultfd_k.h @@ -83,7 +83,8 @@ extern ssize_t mfill_atomic_zeropage(struct mm_struct *dst_mm, unsigned long len, atomic_t *mmap_changing); extern ssize_t mfill_atomic_continue(struct mm_struct *dst_mm, unsigned long dst_start, - unsigned long len, atomic_t *mmap_changing); + unsigned long len, atomic_t *mmap_changing, + uffd_flags_t flags); extern int mwriteprotect_range(struct mm_struct *dst_mm, unsigned long start, unsigned long len, bool enable_wp, atomic_t *mmap_changing); -- cgit v1.2.3 From 5d671eb4ef7e1423a78fc0c12dd419c1dc1f6967 Mon Sep 17 00:00:00 2001 From: "Mike Rapoport (IBM)" Date: Sun, 19 Mar 2023 13:42:14 +0200 Subject: mm: move get_page_from_free_area() to mm/page_alloc.c The get_page_from_free_area() helper is only used in mm/page_alloc.c so move it there to reduce noise in include/linux/mmzone.h Link: https://lkml.kernel.org/r/20230319114214.2133332-1-rppt@kernel.org Signed-off-by: Mike Rapoport (IBM) Reviewed-by: Lorenzo Stoakes Acked-by: Kirill A. Shutemov Reviewed-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton --- include/linux/mmzone.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 35b11cc210d9..2d3d78d01283 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -108,13 +108,6 @@ struct free_area { unsigned long nr_free; }; -static inline struct page *get_page_from_free_area(struct free_area *area, - int migratetype) -{ - return list_first_entry_or_null(&area->free_list[migratetype], - struct page, lru); -} - static inline bool free_area_empty(struct free_area *area, int migratetype) { return list_empty(&area->free_list[migratetype]); -- cgit v1.2.3 From 9420f89db2dd611c5b436a13e13f74d65ecc3a6a Mon Sep 17 00:00:00 2001 From: "Mike Rapoport (IBM)" Date: Tue, 21 Mar 2023 19:05:02 +0200 Subject: mm: move most of core MM initialization to mm/mm_init.c The bulk of memory management initialization code is spread all over mm/page_alloc.c and makes navigating through page allocator functionality difficult. Move most of the functions marked __init and __meminit to mm/mm_init.c to make it better localized and allow some more spare room before mm/page_alloc.c reaches 10k lines. No functional changes. Link: https://lkml.kernel.org/r/20230321170513.2401534-4-rppt@kernel.org Signed-off-by: Mike Rapoport (IBM) Acked-by: David Hildenbrand Acked-by: Vlastimil Babka Cc: Doug Berger Cc: Matthew Wilcox (Oracle) Cc: Mel Gorman Cc: Michal Hocko Cc: Thomas Bogendoerfer Signed-off-by: Andrew Morton --- include/linux/gfp.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 65a78773dcca..7c554e4bd49f 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -361,9 +361,4 @@ extern struct page *alloc_contig_pages(unsigned long nr_pages, gfp_t gfp_mask, #endif void free_contig_range(unsigned long pfn, unsigned long nr_pages); -#ifdef CONFIG_CMA -/* CMA stuff */ -extern void init_cma_reserved_pageblock(struct page *page); -#endif - #endif /* __LINUX_GFP_H */ -- cgit v1.2.3 From c4fbed4b0284d91797ee3cf60983b94c84c396b6 Mon Sep 17 00:00:00 2001 From: "Mike Rapoport (IBM)" Date: Tue, 21 Mar 2023 19:05:04 +0200 Subject: mm/page_alloc: rename page_alloc_init() to page_alloc_init_cpuhp() The page_alloc_init() name is really misleading because all this function does is sets up CPU hotplug callbacks for the page allocator. Rename it to page_alloc_init_cpuhp() so that name will reflect what the function does. Link: https://lkml.kernel.org/r/20230321170513.2401534-6-rppt@kernel.org Signed-off-by: Mike Rapoport (IBM) Reviewed-by: David Hildenbrand Reviewed-by: Vlastimil Babka Cc: Doug Berger Cc: Matthew Wilcox (Oracle) Cc: Mel Gorman Cc: Michal Hocko Cc: Thomas Bogendoerfer Signed-off-by: Andrew Morton --- include/linux/gfp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 7c554e4bd49f..ed8cb537c6a7 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -319,7 +319,7 @@ extern void page_frag_free(void *addr); #define __free_page(page) __free_pages((page), 0) #define free_page(addr) free_pages((addr), 0) -void page_alloc_init(void); +void page_alloc_init_cpuhp(void); void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp); void drain_all_pages(struct zone *zone); void drain_local_pages(struct zone *zone); -- cgit v1.2.3 From b7ec1bf3e7b9dd9d3335c937f5d834680d74addf Mon Sep 17 00:00:00 2001 From: "Mike Rapoport (IBM)" Date: Tue, 21 Mar 2023 19:05:06 +0200 Subject: init,mm: move mm_init() to mm/mm_init.c and rename it to mm_core_init() Make mm_init() a part of mm/ codebase. mm_core_init() better describes what the function does and does not clash with mm_init() in kernel/fork.c Link: https://lkml.kernel.org/r/20230321170513.2401534-8-rppt@kernel.org Signed-off-by: Mike Rapoport (IBM) Acked-by: David Hildenbrand Reviewed-by: Vlastimil Babka Cc: Doug Berger Cc: Matthew Wilcox (Oracle) Cc: Mel Gorman Cc: Michal Hocko Cc: Thomas Bogendoerfer Signed-off-by: Andrew Morton --- include/linux/mm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 1f79667824eb..6be179cec081 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -38,6 +38,7 @@ struct pt_regs; extern int sysctl_page_lock_unfairness; +void mm_core_init(void); void init_mm_internals(void); #ifndef CONFIG_NUMA /* Don't use mapnrs, do it properly */ -- cgit v1.2.3 From 4cd1e9edf60efb20fad35cf5e9ade7ad75b34cd1 Mon Sep 17 00:00:00 2001 From: "Mike Rapoport (IBM)" Date: Tue, 21 Mar 2023 19:05:07 +0200 Subject: mm: call {ptlock,pgtable}_cache_init() directly from mm_core_init() and drop pgtable_init() as it has no real value and its name is misleading. Link: https://lkml.kernel.org/r/20230321170513.2401534-9-rppt@kernel.org Signed-off-by: Mike Rapoport (IBM) Reviewed-by: David Hildenbrand Reviewed-by: Vlastimil Babka Cc: Doug Berger Cc: Matthew Wilcox (Oracle) Cc: Mel Gorman Cc: Michal Hocko Cc: Thomas Bogendoerfer Cc: Sergei Shtylyov Signed-off-by: Andrew Morton --- include/linux/mm.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 6be179cec081..dfff8bcaa766 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2637,12 +2637,6 @@ static inline bool ptlock_init(struct page *page) { return true; } static inline void ptlock_free(struct page *page) {} #endif /* USE_SPLIT_PTE_PTLOCKS */ -static inline void pgtable_init(void) -{ - ptlock_cache_init(); - pgtable_cache_init(); -} - static inline bool pgtable_pte_page_ctor(struct page *page) { if (!ptlock_init(page)) -- cgit v1.2.3 From f2fc4b44ec2bb94c51c7ae1af9b1177d72705992 Mon Sep 17 00:00:00 2001 From: "Mike Rapoport (IBM)" Date: Tue, 21 Mar 2023 19:05:08 +0200 Subject: mm: move init_mem_debugging_and_hardening() to mm/mm_init.c init_mem_debugging_and_hardening() is only called from mm_core_init(). Move it close to the caller, make it static and rename it to mem_debugging_and_hardening_init() for consistency with surrounding convention. Link: https://lkml.kernel.org/r/20230321170513.2401534-10-rppt@kernel.org Signed-off-by: Mike Rapoport (IBM) Acked-by: David Hildenbrand Reviewed-by: Vlastimil Babka Cc: Doug Berger Cc: Matthew Wilcox (Oracle) Cc: Mel Gorman Cc: Michal Hocko Cc: Thomas Bogendoerfer Signed-off-by: Andrew Morton --- include/linux/mm.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index dfff8bcaa766..0fa6a6f94eda 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3251,7 +3251,6 @@ extern int apply_to_existing_page_range(struct mm_struct *mm, unsigned long address, unsigned long size, pte_fn_t fn, void *data); -extern void __init init_mem_debugging_and_hardening(void); #ifdef CONFIG_PAGE_POISONING extern void __kernel_poison_pages(struct page *page, int numpages); extern void __kernel_unpoison_pages(struct page *page, int numpages); -- cgit v1.2.3 From de57807e6f267a658a046dbca44dc40fe806d60f Mon Sep 17 00:00:00 2001 From: "Mike Rapoport (IBM)" Date: Tue, 21 Mar 2023 19:05:09 +0200 Subject: init,mm: fold late call to page_ext_init() to page_alloc_init_late() When deferred initialization of struct pages is enabled, page_ext_init() must be called after all the deferred initialization is done, but there is no point to keep it a separate call from kernel_init_freeable() right after page_alloc_init_late(). Fold the call to page_ext_init() into page_alloc_init_late() and localize deferred_struct_pages variable. Link: https://lkml.kernel.org/r/20230321170513.2401534-11-rppt@kernel.org Signed-off-by: Mike Rapoport (IBM) Reviewed-by: David Hildenbrand Reviewed-by: Vlastimil Babka Cc: Doug Berger Cc: Matthew Wilcox (Oracle) Cc: Mel Gorman Cc: Michal Hocko Cc: Thomas Bogendoerfer Signed-off-by: Andrew Morton --- include/linux/page_ext.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/page_ext.h b/include/linux/page_ext.h index bc2e39090a1f..67314f648aeb 100644 --- a/include/linux/page_ext.h +++ b/include/linux/page_ext.h @@ -29,8 +29,6 @@ struct page_ext_operations { bool need_shared_flags; }; -extern bool deferred_struct_pages; - #ifdef CONFIG_PAGE_EXTENSION /* -- cgit v1.2.3 From eb8589b4f8c107c346421881963c0ee0b8367c2c Mon Sep 17 00:00:00 2001 From: "Mike Rapoport (IBM)" Date: Tue, 21 Mar 2023 19:05:10 +0200 Subject: mm: move mem_init_print_info() to mm_init.c mem_init_print_info() is only called from mm_core_init(). Move it close to the caller and make it static. Link: https://lkml.kernel.org/r/20230321170513.2401534-12-rppt@kernel.org Signed-off-by: Mike Rapoport (IBM) Acked-by: David Hildenbrand Reviewed-by: Vlastimil Babka Cc: Doug Berger Cc: Matthew Wilcox (Oracle) Cc: Mel Gorman Cc: Michal Hocko Cc: Thomas Bogendoerfer Signed-off-by: Andrew Morton --- include/linux/mm.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 0fa6a6f94eda..c3abad7e6ccb 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2780,7 +2780,6 @@ extern unsigned long free_reserved_area(void *start, void *end, int poison, const char *s); extern void adjust_managed_page_count(struct page *page, long count); -extern void mem_init_print_info(void); extern void reserve_bootmem_region(phys_addr_t start, phys_addr_t end); -- cgit v1.2.3 From d5d2c02a4980c2e22037679457bf2d921b86a503 Mon Sep 17 00:00:00 2001 From: "Mike Rapoport (IBM)" Date: Tue, 21 Mar 2023 19:05:11 +0200 Subject: mm: move kmem_cache_init() declaration to mm/slab.h kmem_cache_init() is called only from mm_core_init(), there is no need to declare it in include/linux/slab.h Move kmem_cache_init() declaration to mm/slab.h Link: https://lkml.kernel.org/r/20230321170513.2401534-13-rppt@kernel.org Signed-off-by: Mike Rapoport (IBM) Reviewed-by: David Hildenbrand Reviewed-by: Vlastimil Babka Cc: Doug Berger Cc: Matthew Wilcox (Oracle) Cc: Mel Gorman Cc: Michal Hocko Cc: Thomas Bogendoerfer Signed-off-by: Andrew Morton --- include/linux/slab.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/slab.h b/include/linux/slab.h index aa4575ef2965..f8b1d63c63a3 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -167,7 +167,6 @@ struct mem_cgroup; /* * struct kmem_cache related prototypes */ -void __init kmem_cache_init(void); bool slab_is_available(void); struct kmem_cache *kmem_cache_create(const char *name, unsigned int size, -- cgit v1.2.3 From b671491199acd3609f87754d268f2f5cb10de18d Mon Sep 17 00:00:00 2001 From: "Mike Rapoport (IBM)" Date: Tue, 21 Mar 2023 19:05:12 +0200 Subject: mm: move vmalloc_init() declaration to mm/internal.h vmalloc_init() is called only from mm_core_init(), there is no need to declare it in include/linux/vmalloc.h Move vmalloc_init() declaration to mm/internal.h Link: https://lkml.kernel.org/r/20230321170513.2401534-14-rppt@kernel.org Signed-off-by: Mike Rapoport (IBM) Reviewed-by: David Hildenbrand Reviewed-by: Vlastimil Babka Cc: Doug Berger Cc: Matthew Wilcox (Oracle) Cc: Mel Gorman Cc: Michal Hocko Cc: Thomas Bogendoerfer Signed-off-by: Andrew Morton --- include/linux/vmalloc.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 69250efa03d1..351fc7697214 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -131,12 +131,8 @@ extern void *vm_map_ram(struct page **pages, unsigned int count, int node); extern void vm_unmap_aliases(void); #ifdef CONFIG_MMU -extern void __init vmalloc_init(void); extern unsigned long vmalloc_nr_pages(void); #else -static inline void vmalloc_init(void) -{ -} static inline unsigned long vmalloc_nr_pages(void) { return 0; } #endif -- cgit v1.2.3 From bd23024b9774e681cbe6cc3afcb24244dfcb2390 Mon Sep 17 00:00:00 2001 From: Tomas Mudrunka Date: Tue, 21 Mar 2023 11:34:30 +0100 Subject: mm/memtest: add results of early memtest to /proc/meminfo Currently the memtest results were only presented in dmesg. When running a large fleet of devices without ECC RAM it's currently not easy to do bulk monitoring for memory corruption. You have to parse dmesg, but that's a ring buffer so the error might disappear after some time. In general I do not consider dmesg to be a great API to query RAM status. In several companies I've seen such errors remain undetected and cause issues for way too long. So I think it makes sense to provide a monitoring API, so that we can safely detect and act upon them. This adds /proc/meminfo entry which can be easily used by scripts. Link: https://lkml.kernel.org/r/20230321103430.7130-1-tomas.mudrunka@gmail.com Signed-off-by: Tomas Mudrunka Cc: Jonathan Corbet Cc: Mike Rapoport (IBM) Signed-off-by: Andrew Morton --- include/linux/memblock.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 50ad19662a32..f82ee3fac1cd 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -597,6 +597,8 @@ extern int hashdist; /* Distribute hashes across NUMA nodes? */ #endif #ifdef CONFIG_MEMTEST +extern phys_addr_t early_memtest_bad_size; /* Size of faulty ram found by memtest */ +extern bool early_memtest_done; /* Was early memtest done? */ extern void early_memtest(phys_addr_t start, phys_addr_t end); #else static inline void early_memtest(phys_addr_t start, phys_addr_t end) -- cgit v1.2.3 From 28d8b812e97b31231e95864f36a6b32f4b307daa Mon Sep 17 00:00:00 2001 From: Lorenzo Stoakes Date: Sun, 12 Mar 2023 23:40:13 +0000 Subject: mm: remove unused vmf_insert_mixed_prot() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Patch series "Remove drm/ttm-specific mm changes". Functionality was added specifically for the DRM TTM driver to support mapping memory for VM_MIXEDMAP VMAs with customised protection flags, however this has now been rolled back as issues were found with this approach. This series removes the mm changes too, retaining some of the useful comments. This patch (of 3): The sole user of vmf_insert_mixed_prot(), the drm ttm module, stopped using this in commit f91142c62161 ("drm/ttm: nuke VM_MIXEDMAP on BO mappings v3") citing use of VM_MIXEDMAP in this case being terribly broken. Remove this now-dead code and references to it, but retain the useful description of the prot != vma->vm_page_prot case, moving it to vmf_insert_pfn_prot() instead. Link: https://lkml.kernel.org/r/cover.1678661628.git.lstoakes@gmail.com Link: https://lkml.kernel.org/r/a069644388e6f1593a7020d15840e6fc9f39bcaf.1678661628.git.lstoakes@gmail.com Signed-off-by: Lorenzo Stoakes Cc: Christian König Cc: Dan Williams Cc: Jason Gunthorpe Cc: Kirill A. Shutemov Cc: Matthew Wilcox (Oracle) Cc: Michal Hocko Cc: Thomas Hellström Cc: Aaron Tomlin Cc: Christoph Lameter Cc: Frederic Weisbecker Cc: Heiko Carstens Cc: Huacai Chen Cc: Marcelo Tosatti Cc: Peter Xu Cc: "Russell King (Oracle)" Cc: Vlastimil Babka Signed-off-by: Andrew Morton --- include/linux/mm.h | 2 -- include/linux/mm_types.h | 7 +------ 2 files changed, 1 insertion(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index c3abad7e6ccb..55d02356146c 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3179,8 +3179,6 @@ vm_fault_t vmf_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn, pgprot_t pgprot); vm_fault_t vmf_insert_mixed(struct vm_area_struct *vma, unsigned long addr, pfn_t pfn); -vm_fault_t vmf_insert_mixed_prot(struct vm_area_struct *vma, unsigned long addr, - pfn_t pfn, pgprot_t pgprot); vm_fault_t vmf_insert_mixed_mkwrite(struct vm_area_struct *vma, unsigned long addr, pfn_t pfn); int vm_iomap_memory(struct vm_area_struct *vma, phys_addr_t start, unsigned long len); diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 0722859c3647..651a5c256732 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -485,12 +485,7 @@ struct vm_area_struct { within vm_mm. */ struct mm_struct *vm_mm; /* The address space we belong to. */ - - /* - * Access permissions of this VMA. - * See vmf_insert_mixed_prot() for discussion. - */ - pgprot_t vm_page_prot; + pgprot_t vm_page_prot; /* Access permissions of this VMA. */ /* * Flags, see mm.h. -- cgit v1.2.3 From 7b806d229ef151c2997c041b791dfa89593e0e1b Mon Sep 17 00:00:00 2001 From: Lorenzo Stoakes Date: Sun, 12 Mar 2023 23:40:14 +0000 Subject: mm: remove vmf_insert_pfn_xxx_prot() for huge page-table entries MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This functionality's sole user, the drm ttm module, removed support for it in commit 0d979509539e ("drm/ttm: remove ttm_bo_vm_insert_huge()") as the whole approach is currently unworkable without a PMD/PUD special bit and updates to GUP. Link: https://lkml.kernel.org/r/604c2ad79659d4b8a6e3e1611c6219d5d3233988.1678661628.git.lstoakes@gmail.com Signed-off-by: Lorenzo Stoakes Cc: Christian König Cc: Dan Williams Cc: Jason Gunthorpe Cc: Kirill A. Shutemov Cc: Matthew Wilcox (Oracle) Cc: Michal Hocko Cc: Thomas Hellström Cc: Aaron Tomlin Cc: Christoph Lameter Cc: Frederic Weisbecker Cc: Heiko Carstens Cc: Huacai Chen Cc: Marcelo Tosatti Cc: Peter Xu Cc: "Russell King (Oracle)" Cc: Vlastimil Babka Signed-off-by: Andrew Morton --- include/linux/huge_mm.h | 39 ++------------------------------------- 1 file changed, 2 insertions(+), 37 deletions(-) (limited to 'include/linux') diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 9a3a3af2dd80..20284387b841 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -39,44 +39,9 @@ bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr, int change_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, pgprot_t newprot, unsigned long cp_flags); -vm_fault_t vmf_insert_pfn_pmd_prot(struct vm_fault *vmf, pfn_t pfn, - pgprot_t pgprot, bool write); -/** - * vmf_insert_pfn_pmd - insert a pmd size pfn - * @vmf: Structure describing the fault - * @pfn: pfn to insert - * @pgprot: page protection to use - * @write: whether it's a write fault - * - * Insert a pmd size pfn. See vmf_insert_pfn() for additional info. - * - * Return: vm_fault_t value. - */ -static inline vm_fault_t vmf_insert_pfn_pmd(struct vm_fault *vmf, pfn_t pfn, - bool write) -{ - return vmf_insert_pfn_pmd_prot(vmf, pfn, vmf->vma->vm_page_prot, write); -} -vm_fault_t vmf_insert_pfn_pud_prot(struct vm_fault *vmf, pfn_t pfn, - pgprot_t pgprot, bool write); - -/** - * vmf_insert_pfn_pud - insert a pud size pfn - * @vmf: Structure describing the fault - * @pfn: pfn to insert - * @pgprot: page protection to use - * @write: whether it's a write fault - * - * Insert a pud size pfn. See vmf_insert_pfn() for additional info. - * - * Return: vm_fault_t value. - */ -static inline vm_fault_t vmf_insert_pfn_pud(struct vm_fault *vmf, pfn_t pfn, - bool write) -{ - return vmf_insert_pfn_pud_prot(vmf, pfn, vmf->vma->vm_page_prot, write); -} +vm_fault_t vmf_insert_pfn_pmd(struct vm_fault *vmf, pfn_t pfn, bool write); +vm_fault_t vmf_insert_pfn_pud(struct vm_fault *vmf, pfn_t pfn, bool write); enum transparent_hugepage_flag { TRANSPARENT_HUGEPAGE_UNSUPPORTED, -- cgit v1.2.3 From 3f6dac0fd1b83178137e7b4e722d8f29612cbec1 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Tue, 21 Mar 2023 03:24:15 +0300 Subject: mm/page_alloc: make deferred page init free pages in MAX_ORDER blocks Normal page init path frees pages during the boot in MAX_ORDER chunks, but deferred page init path does it in pageblock blocks. Change deferred page init path to work in MAX_ORDER blocks. For cases when MAX_ORDER is larger than pageblock, set migrate type to MIGRATE_MOVABLE for all pageblocks covered by the page. Link: https://lkml.kernel.org/r/20230321002415.20843-1-kirill.shutemov@linux.intel.com Signed-off-by: Kirill A. Shutemov Reviewed-by: Vlastimil Babka Acked-by: David Hildenbrand Acked-by: Mel Gorman Acked-by: Mike Rapoport (IBM) Signed-off-by: Andrew Morton --- include/linux/mmzone.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 2d3d78d01283..2d22e47dc1eb 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -32,6 +32,8 @@ #endif #define MAX_ORDER_NR_PAGES (1 << MAX_ORDER) +#define IS_MAX_ORDER_ALIGNED(pfn) IS_ALIGNED(pfn, MAX_ORDER_NR_PAGES) + /* * PAGE_ALLOC_COSTLY_ORDER is the order at which allocations are deemed * costly to service. That is between allocation orders which should -- cgit v1.2.3 From 4f80818b4a58c9458dce0df7cce9abe107da445e Mon Sep 17 00:00:00 2001 From: Lorenzo Stoakes Date: Wed, 22 Mar 2023 18:57:03 +0000 Subject: iov_iter: add copy_page_to_iter_nofault() Provide a means to copy a page to user space from an iterator, aborting if a page fault would occur. This supports compound pages, but may be passed a tail page with an offset extending further into the compound page, so we cannot pass a folio. This allows for this function to be called from atomic context and _try_ to user pages if they are faulted in, aborting if not. The function does not use _copy_to_iter() in order to not specify might_fault(), this is similar to copy_page_from_iter_atomic(). This is being added in order that an iteratable form of vread() can be implemented while holding spinlocks. Link: https://lkml.kernel.org/r/19734729defb0f498a76bdec1bef3ac48a3af3e8.1679511146.git.lstoakes@gmail.com Signed-off-by: Lorenzo Stoakes Reviewed-by: Baoquan He Cc: Alexander Viro Cc: David Hildenbrand Cc: Jens Axboe Cc: Jiri Olsa Cc: Liu Shixin Cc: Matthew Wilcox (Oracle) Cc: Uladzislau Rezki (Sony) Signed-off-by: Andrew Morton --- include/linux/uio.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/uio.h b/include/linux/uio.h index 27e3fd942960..29eb18bb6feb 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -173,6 +173,8 @@ static inline size_t copy_folio_to_iter(struct folio *folio, size_t offset, { return copy_page_to_iter(&folio->page, offset, bytes, i); } +size_t copy_page_to_iter_nofault(struct page *page, unsigned offset, + size_t bytes, struct iov_iter *i); static __always_inline __must_check size_t copy_to_iter(const void *addr, size_t bytes, struct iov_iter *i) -- cgit v1.2.3 From 4c91c07c93bbbdd7f2d9de2beb7ee5c2a48ad8e7 Mon Sep 17 00:00:00 2001 From: Lorenzo Stoakes Date: Wed, 22 Mar 2023 18:57:04 +0000 Subject: mm: vmalloc: convert vread() to vread_iter() Having previously laid the foundation for converting vread() to an iterator function, pull the trigger and do so. This patch attempts to provide minimal refactoring and to reflect the existing logic as best we can, for example we continue to zero portions of memory not read, as before. Overall, there should be no functional difference other than a performance improvement in /proc/kcore access to vmalloc regions. Now we have eliminated the need for a bounce buffer in read_kcore_iter(), we dispense with it, and try to write to user memory optimistically but with faults disabled via copy_page_to_iter_nofault(). We already have preemption disabled by holding a spin lock. We continue faulting in until the operation is complete. Additionally, we must account for the fact that at any point a copy may fail (most likely due to a fault not being able to occur), we exit indicating fewer bytes retrieved than expected. [sfr@canb.auug.org.au: fix sparc64 warning] Link: https://lkml.kernel.org/r/20230320144721.663280c3@canb.auug.org.au [lstoakes@gmail.com: redo Stephen's sparc build fix] Link: https://lkml.kernel.org/r/8506cbc667c39205e65a323f750ff9c11a463798.1679566220.git.lstoakes@gmail.com [akpm@linux-foundation.org: unbreak uio.h includes] Link: https://lkml.kernel.org/r/941f88bc5ab928e6656e1e2593b91bf0f8c81e1b.1679511146.git.lstoakes@gmail.com Signed-off-by: Lorenzo Stoakes Signed-off-by: Stephen Rothwell Reviewed-by: Baoquan He Cc: Alexander Viro Cc: David Hildenbrand Cc: Jens Axboe Cc: Jiri Olsa Cc: Liu Shixin Cc: Matthew Wilcox (Oracle) Cc: Uladzislau Rezki (Sony) Signed-off-by: Andrew Morton --- include/linux/vmalloc.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 351fc7697214..c720be70c8dd 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -14,6 +14,7 @@ struct vm_area_struct; /* vma defining user mapping in mm_types.h */ struct notifier_block; /* in notifier.h */ +struct iov_iter; /* in uio.h */ /* bits in flags of vmalloc's vm_struct below */ #define VM_IOREMAP 0x00000001 /* ioremap() and friends */ @@ -247,7 +248,7 @@ static inline void set_vm_flush_reset_perms(void *addr) #endif /* for /proc/kcore */ -extern long vread(char *buf, char *addr, unsigned long count); +extern long vread_iter(struct iov_iter *iter, const char *addr, size_t count); /* * Internals. Don't use.. -- cgit v1.2.3 From 20cce633f4254cc0df39665449726e3172518f6c Mon Sep 17 00:00:00 2001 From: Michel Lespinasse Date: Mon, 27 Feb 2023 09:36:09 -0800 Subject: mm: rcu safe VMA freeing This prepares for page faults handling under VMA lock, looking up VMAs under protection of an rcu read lock, instead of the usual mmap read lock. Link: https://lkml.kernel.org/r/20230227173632.3292573-11-surenb@google.com Signed-off-by: Michel Lespinasse Signed-off-by: Suren Baghdasaryan Signed-off-by: Andrew Morton --- include/linux/mm_types.h | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 651a5c256732..f203e2562e00 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -480,9 +480,16 @@ struct anon_vma_name { struct vm_area_struct { /* The first cache line has the info for VMA tree walking. */ - unsigned long vm_start; /* Our start address within vm_mm. */ - unsigned long vm_end; /* The first byte after our end address - within vm_mm. */ + union { + struct { + /* VMA covers [vm_start; vm_end) addresses within mm */ + unsigned long vm_start; + unsigned long vm_end; + }; +#ifdef CONFIG_PER_VMA_LOCK + struct rcu_head vm_rcu; /* Used for deferred freeing. */ +#endif + }; struct mm_struct *vm_mm; /* The address space we belong to. */ pgprot_t vm_page_prot; /* Access permissions of this VMA. */ -- cgit v1.2.3 From 438b6e12cd603a9416ca7c5462ab75b2a8c4d5b9 Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Mon, 27 Feb 2023 09:36:10 -0800 Subject: mm: move mmap_lock assert function definitions Move mmap_lock assert function definitions up so that they can be used by other mmap_lock routines. Link: https://lkml.kernel.org/r/20230227173632.3292573-12-surenb@google.com Signed-off-by: Suren Baghdasaryan Signed-off-by: Andrew Morton --- include/linux/mmap_lock.h | 24 ++++++++++++------------ 1 file changed, 12 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmap_lock.h b/include/linux/mmap_lock.h index 96e113e23d04..e49ba91bb1f0 100644 --- a/include/linux/mmap_lock.h +++ b/include/linux/mmap_lock.h @@ -60,6 +60,18 @@ static inline void __mmap_lock_trace_released(struct mm_struct *mm, bool write) #endif /* CONFIG_TRACING */ +static inline void mmap_assert_locked(struct mm_struct *mm) +{ + lockdep_assert_held(&mm->mmap_lock); + VM_BUG_ON_MM(!rwsem_is_locked(&mm->mmap_lock), mm); +} + +static inline void mmap_assert_write_locked(struct mm_struct *mm) +{ + lockdep_assert_held_write(&mm->mmap_lock); + VM_BUG_ON_MM(!rwsem_is_locked(&mm->mmap_lock), mm); +} + static inline void mmap_init_lock(struct mm_struct *mm) { init_rwsem(&mm->mmap_lock); @@ -150,18 +162,6 @@ static inline void mmap_read_unlock_non_owner(struct mm_struct *mm) up_read_non_owner(&mm->mmap_lock); } -static inline void mmap_assert_locked(struct mm_struct *mm) -{ - lockdep_assert_held(&mm->mmap_lock); - VM_BUG_ON_MM(!rwsem_is_locked(&mm->mmap_lock), mm); -} - -static inline void mmap_assert_write_locked(struct mm_struct *mm) -{ - lockdep_assert_held_write(&mm->mmap_lock); - VM_BUG_ON_MM(!rwsem_is_locked(&mm->mmap_lock), mm); -} - static inline int mmap_lock_is_contended(struct mm_struct *mm) { return rwsem_is_contended(&mm->mmap_lock); -- cgit v1.2.3 From 5e31275cc997f8ec5d9e8d65fe9840ebed89db19 Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Mon, 27 Feb 2023 09:36:11 -0800 Subject: mm: add per-VMA lock and helper functions to control it Introduce per-VMA locking. The lock implementation relies on a per-vma and per-mm sequence counters to note exclusive locking: - read lock - (implemented by vma_start_read) requires the vma (vm_lock_seq) and mm (mm_lock_seq) sequence counters to differ. If they match then there must be a vma exclusive lock held somewhere. - read unlock - (implemented by vma_end_read) is a trivial vma->lock unlock. - write lock - (vma_start_write) requires the mmap_lock to be held exclusively and the current mm counter is assigned to the vma counter. This will allow multiple vmas to be locked under a single mmap_lock write lock (e.g. during vma merging). The vma counter is modified under exclusive vma lock. - write unlock - (vma_end_write_all) is a batch release of all vma locks held. It doesn't pair with a specific vma_start_write! It is done before exclusive mmap_lock is released by incrementing mm sequence counter (mm_lock_seq). - write downgrade - if the mmap_lock is downgraded to the read lock, all vma write locks are released as well (effectivelly same as write unlock). Link: https://lkml.kernel.org/r/20230227173632.3292573-13-surenb@google.com Signed-off-by: Suren Baghdasaryan Signed-off-by: Andrew Morton --- include/linux/mm.h | 82 +++++++++++++++++++++++++++++++++++++++++++++++ include/linux/mm_types.h | 8 +++++ include/linux/mmap_lock.h | 13 ++++++++ 3 files changed, 103 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 55d02356146c..53bfb42663ea 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -624,6 +624,87 @@ struct vm_operations_struct { unsigned long addr); }; +#ifdef CONFIG_PER_VMA_LOCK +static inline void vma_init_lock(struct vm_area_struct *vma) +{ + init_rwsem(&vma->lock); + vma->vm_lock_seq = -1; +} + +/* + * Try to read-lock a vma. The function is allowed to occasionally yield false + * locked result to avoid performance overhead, in which case we fall back to + * using mmap_lock. The function should never yield false unlocked result. + */ +static inline bool vma_start_read(struct vm_area_struct *vma) +{ + /* Check before locking. A race might cause false locked result. */ + if (vma->vm_lock_seq == READ_ONCE(vma->vm_mm->mm_lock_seq)) + return false; + + if (unlikely(down_read_trylock(&vma->lock) == 0)) + return false; + + /* + * Overflow might produce false locked result. + * False unlocked result is impossible because we modify and check + * vma->vm_lock_seq under vma->lock protection and mm->mm_lock_seq + * modification invalidates all existing locks. + */ + if (unlikely(vma->vm_lock_seq == READ_ONCE(vma->vm_mm->mm_lock_seq))) { + up_read(&vma->lock); + return false; + } + return true; +} + +static inline void vma_end_read(struct vm_area_struct *vma) +{ + rcu_read_lock(); /* keeps vma alive till the end of up_read */ + up_read(&vma->lock); + rcu_read_unlock(); +} + +static inline void vma_start_write(struct vm_area_struct *vma) +{ + int mm_lock_seq; + + mmap_assert_write_locked(vma->vm_mm); + + /* + * current task is holding mmap_write_lock, both vma->vm_lock_seq and + * mm->mm_lock_seq can't be concurrently modified. + */ + mm_lock_seq = READ_ONCE(vma->vm_mm->mm_lock_seq); + if (vma->vm_lock_seq == mm_lock_seq) + return; + + down_write(&vma->lock); + vma->vm_lock_seq = mm_lock_seq; + up_write(&vma->lock); +} + +static inline void vma_assert_write_locked(struct vm_area_struct *vma) +{ + mmap_assert_write_locked(vma->vm_mm); + /* + * current task is holding mmap_write_lock, both vma->vm_lock_seq and + * mm->mm_lock_seq can't be concurrently modified. + */ + VM_BUG_ON_VMA(vma->vm_lock_seq != READ_ONCE(vma->vm_mm->mm_lock_seq), vma); +} + +#else /* CONFIG_PER_VMA_LOCK */ + +static inline void vma_init_lock(struct vm_area_struct *vma) {} +static inline bool vma_start_read(struct vm_area_struct *vma) + { return false; } +static inline void vma_end_read(struct vm_area_struct *vma) {} +static inline void vma_start_write(struct vm_area_struct *vma) {} +static inline void vma_assert_write_locked(struct vm_area_struct *vma) {} + +#endif /* CONFIG_PER_VMA_LOCK */ + static inline void vma_init(struct vm_area_struct *vma, struct mm_struct *mm) { static const struct vm_operations_struct dummy_vm_ops = {}; @@ -632,6 +713,7 @@ static inline void vma_init(struct vm_area_struct *vma, struct mm_struct *mm) vma->vm_mm = mm; vma->vm_ops = &dummy_vm_ops; INIT_LIST_HEAD(&vma->anon_vma_chain); + vma_init_lock(vma); } /* Use when VMA is not part of the VMA tree and needs no locking */ diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index f203e2562e00..843a45893991 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -503,6 +503,11 @@ struct vm_area_struct { vm_flags_t __private __vm_flags; }; +#ifdef CONFIG_PER_VMA_LOCK + int vm_lock_seq; + struct rw_semaphore lock; +#endif + /* * For areas with an address space and backing store, * linkage into the address_space->i_mmap interval tree. @@ -639,6 +644,9 @@ struct mm_struct { * init_mm.mmlist, and are protected * by mmlist_lock */ +#ifdef CONFIG_PER_VMA_LOCK + int mm_lock_seq; +#endif unsigned long hiwater_rss; /* High-watermark of RSS usage */ diff --git a/include/linux/mmap_lock.h b/include/linux/mmap_lock.h index e49ba91bb1f0..aab8f1b28d26 100644 --- a/include/linux/mmap_lock.h +++ b/include/linux/mmap_lock.h @@ -72,6 +72,17 @@ static inline void mmap_assert_write_locked(struct mm_struct *mm) VM_BUG_ON_MM(!rwsem_is_locked(&mm->mmap_lock), mm); } +#ifdef CONFIG_PER_VMA_LOCK +static inline void vma_end_write_all(struct mm_struct *mm) +{ + mmap_assert_write_locked(mm); + /* No races during update due to exclusive mmap_lock being held */ + WRITE_ONCE(mm->mm_lock_seq, mm->mm_lock_seq + 1); +} +#else +static inline void vma_end_write_all(struct mm_struct *mm) {} +#endif + static inline void mmap_init_lock(struct mm_struct *mm) { init_rwsem(&mm->mmap_lock); @@ -114,12 +125,14 @@ static inline bool mmap_write_trylock(struct mm_struct *mm) static inline void mmap_write_unlock(struct mm_struct *mm) { __mmap_lock_trace_released(mm, true); + vma_end_write_all(mm); up_write(&mm->mmap_lock); } static inline void mmap_write_downgrade(struct mm_struct *mm) { __mmap_lock_trace_acquire_returned(mm, false, true); + vma_end_write_all(mm); downgrade_write(&mm->mmap_lock); } -- cgit v1.2.3 From c732293331a22187d59cd485879276a1da398387 Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Mon, 27 Feb 2023 09:36:12 -0800 Subject: mm: mark VMA as being written when changing vm_flags Updates to vm_flags have to be done with VMA marked as being written for preventing concurrent page faults or other modifications. Link: https://lkml.kernel.org/r/20230227173632.3292573-14-surenb@google.com Signed-off-by: Suren Baghdasaryan Signed-off-by: Andrew Morton --- include/linux/mm.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 53bfb42663ea..d0a6c99aba09 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -727,28 +727,28 @@ static inline void vm_flags_init(struct vm_area_struct *vma, static inline void vm_flags_reset(struct vm_area_struct *vma, vm_flags_t flags) { - mmap_assert_write_locked(vma->vm_mm); + vma_start_write(vma); vm_flags_init(vma, flags); } static inline void vm_flags_reset_once(struct vm_area_struct *vma, vm_flags_t flags) { - mmap_assert_write_locked(vma->vm_mm); + vma_start_write(vma); WRITE_ONCE(ACCESS_PRIVATE(vma, __vm_flags), flags); } static inline void vm_flags_set(struct vm_area_struct *vma, vm_flags_t flags) { - mmap_assert_write_locked(vma->vm_mm); + vma_start_write(vma); ACCESS_PRIVATE(vma, __vm_flags) |= flags; } static inline void vm_flags_clear(struct vm_area_struct *vma, vm_flags_t flags) { - mmap_assert_write_locked(vma->vm_mm); + vma_start_write(vma); ACCESS_PRIVATE(vma, __vm_flags) &= ~flags; } @@ -769,7 +769,7 @@ static inline void __vm_flags_mod(struct vm_area_struct *vma, static inline void vm_flags_mod(struct vm_area_struct *vma, vm_flags_t set, vm_flags_t clear) { - mmap_assert_write_locked(vma->vm_mm); + vma_start_write(vma); __vm_flags_mod(vma, set, clear); } -- cgit v1.2.3 From 55fd6fccad3172c0feaaa817f0a1283629ff183e Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Mon, 27 Feb 2023 09:36:14 -0800 Subject: mm/khugepaged: write-lock VMA while collapsing a huge page Protect VMA from concurrent page fault handler while collapsing a huge page. Page fault handler needs a stable PMD to use PTL and relies on per-VMA lock to prevent concurrent PMD changes. pmdp_collapse_flush(), set_huge_pmd() and collapse_and_free_pmd() can modify a PMD, which will not be detected by a page fault handler without proper locking. Before this patch, page tables can be walked under any one of the mmap_lock, the mapping lock, and the anon_vma lock; so when khugepaged unlinks and frees page tables, it must ensure that all of those either are locked or don't exist. This patch adds a fourth lock under which page tables can be traversed, and so khugepaged must also lock out that one. [surenb@google.com: vm_lock/i_mmap_rwsem inversion in retract_page_tables] Link: https://lkml.kernel.org/r/20230303213250.3555716-1-surenb@google.com [surenb@google.com: build fix] Link: https://lkml.kernel.org/r/CAJuCfpFjWhtzRE1X=J+_JjgJzNKhq-=JT8yTBSTHthwp0pqWZw@mail.gmail.com Link: https://lkml.kernel.org/r/20230227173632.3292573-16-surenb@google.com Signed-off-by: Suren Baghdasaryan Signed-off-by: Andrew Morton --- include/linux/mm.h | 41 ++++++++++++++++++++++++++++++----------- 1 file changed, 30 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index d0a6c99aba09..d6a2abc51e3d 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -665,18 +665,23 @@ static inline void vma_end_read(struct vm_area_struct *vma) rcu_read_unlock(); } -static inline void vma_start_write(struct vm_area_struct *vma) +static bool __is_vma_write_locked(struct vm_area_struct *vma, int *mm_lock_seq) { - int mm_lock_seq; - mmap_assert_write_locked(vma->vm_mm); /* * current task is holding mmap_write_lock, both vma->vm_lock_seq and * mm->mm_lock_seq can't be concurrently modified. */ - mm_lock_seq = READ_ONCE(vma->vm_mm->mm_lock_seq); - if (vma->vm_lock_seq == mm_lock_seq) + *mm_lock_seq = READ_ONCE(vma->vm_mm->mm_lock_seq); + return (vma->vm_lock_seq == *mm_lock_seq); +} + +static inline void vma_start_write(struct vm_area_struct *vma) +{ + int mm_lock_seq; + + if (__is_vma_write_locked(vma, &mm_lock_seq)) return; down_write(&vma->lock); @@ -684,14 +689,26 @@ static inline void vma_start_write(struct vm_area_struct *vma) up_write(&vma->lock); } +static inline bool vma_try_start_write(struct vm_area_struct *vma) +{ + int mm_lock_seq; + + if (__is_vma_write_locked(vma, &mm_lock_seq)) + return true; + + if (!down_write_trylock(&vma->vm_lock->lock)) + return false; + + vma->vm_lock_seq = mm_lock_seq; + up_write(&vma->vm_lock->lock); + return true; +} + static inline void vma_assert_write_locked(struct vm_area_struct *vma) { - mmap_assert_write_locked(vma->vm_mm); - /* - * current task is holding mmap_write_lock, both vma->vm_lock_seq and - * mm->mm_lock_seq can't be concurrently modified. - */ - VM_BUG_ON_VMA(vma->vm_lock_seq != READ_ONCE(vma->vm_mm->mm_lock_seq), vma); + int mm_lock_seq; + + VM_BUG_ON_VMA(!__is_vma_write_locked(vma, &mm_lock_seq), vma); } #else /* CONFIG_PER_VMA_LOCK */ @@ -701,6 +718,8 @@ static inline bool vma_start_read(struct vm_area_struct *vma) { return false; } static inline void vma_end_read(struct vm_area_struct *vma) {} static inline void vma_start_write(struct vm_area_struct *vma) {} +static inline bool vma_try_start_write(struct vm_area_struct *vma) + { return true; } static inline void vma_assert_write_locked(struct vm_area_struct *vma) {} #endif /* CONFIG_PER_VMA_LOCK */ -- cgit v1.2.3 From 457f67be5910a2b5f1fda8af06bfe4d3492a0a4f Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Mon, 27 Feb 2023 09:36:21 -0800 Subject: mm: introduce vma detached flag Per-vma locking mechanism will search for VMA under RCU protection and then after locking it, has to ensure it was not removed from the VMA tree after we found it. To make this check efficient, introduce a vma->detached flag to mark VMAs which were removed from the VMA tree. Link: https://lkml.kernel.org/r/20230227173632.3292573-23-surenb@google.com Signed-off-by: Suren Baghdasaryan Signed-off-by: Andrew Morton --- include/linux/mm.h | 11 +++++++++++ include/linux/mm_types.h | 3 +++ 2 files changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index d6a2abc51e3d..d0f289bfef01 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -711,6 +711,14 @@ static inline void vma_assert_write_locked(struct vm_area_struct *vma) VM_BUG_ON_VMA(!__is_vma_write_locked(vma, &mm_lock_seq), vma); } +static inline void vma_mark_detached(struct vm_area_struct *vma, bool detached) +{ + /* When detaching vma should be write-locked */ + if (detached) + vma_assert_write_locked(vma); + vma->detached = detached; +} + #else /* CONFIG_PER_VMA_LOCK */ static inline void vma_init_lock(struct vm_area_struct *vma) {} @@ -721,6 +729,8 @@ static inline void vma_start_write(struct vm_area_struct *vma) {} static inline bool vma_try_start_write(struct vm_area_struct *vma) { return true; } static inline void vma_assert_write_locked(struct vm_area_struct *vma) {} +static inline void vma_mark_detached(struct vm_area_struct *vma, + bool detached) {} #endif /* CONFIG_PER_VMA_LOCK */ @@ -732,6 +742,7 @@ static inline void vma_init(struct vm_area_struct *vma, struct mm_struct *mm) vma->vm_mm = mm; vma->vm_ops = &dummy_vm_ops; INIT_LIST_HEAD(&vma->anon_vma_chain); + vma_mark_detached(vma, false); vma_init_lock(vma); } diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 843a45893991..3248ae45cb2e 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -506,6 +506,9 @@ struct vm_area_struct { #ifdef CONFIG_PER_VMA_LOCK int vm_lock_seq; struct rw_semaphore lock; + + /* Flag to indicate areas detached from the mm->mm_mt tree */ + bool detached; #endif /* -- cgit v1.2.3 From 50ee32537206140e4cf6e47024be29a84d458d49 Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Mon, 27 Feb 2023 09:36:22 -0800 Subject: mm: introduce lock_vma_under_rcu to be used from arch-specific code Introduce lock_vma_under_rcu function to lookup and lock a VMA during page fault handling. When VMA is not found, can't be locked or changes after being locked, the function returns NULL. The lookup is performed under RCU protection to prevent the found VMA from being destroyed before the VMA lock is acquired. VMA lock statistics are updated according to the results. For now only anonymous VMAs can be searched this way. In other cases the function returns NULL. Link: https://lkml.kernel.org/r/20230227173632.3292573-24-surenb@google.com Signed-off-by: Suren Baghdasaryan Signed-off-by: Andrew Morton --- include/linux/mm.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index d0f289bfef01..0619f9fa7581 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -719,6 +719,9 @@ static inline void vma_mark_detached(struct vm_area_struct *vma, bool detached) vma->detached = detached; } +struct vm_area_struct *lock_vma_under_rcu(struct mm_struct *mm, + unsigned long address); + #else /* CONFIG_PER_VMA_LOCK */ static inline void vma_init_lock(struct vm_area_struct *vma) {} -- cgit v1.2.3 From 55324e46eb8b886ecd08c9a089d3a694c705b3b0 Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Mon, 27 Feb 2023 09:36:24 -0800 Subject: mm: add FAULT_FLAG_VMA_LOCK flag Add a new flag to distinguish page faults handled under protection of per-vma lock. [surenb@google.com: document FAULT_FLAG_VMA_LOCK flag] Link: https://lkml.kernel.org/r/20230301022720.1380780-2-surenb@google.com Link: https://lore.kernel.org/all/20230301113648.7c279865@canb.auug.org.au/ Link: https://lkml.kernel.org/r/20230227173632.3292573-26-surenb@google.com Signed-off-by: Suren Baghdasaryan Reviewed-by: Laurent Dufour Cc: Dan Carpenter Cc: David Hildenbrand Cc: David Howells Cc: Hugh Dickins Cc: Jason Gunthorpe Cc: Liam R. Howlett Cc: Mathieu Desnoyers Cc: Matthew Wilcox Cc: Pavel Tatashin Cc: Yu Zhao Signed-off-by: Andrew Morton --- include/linux/mm.h | 3 ++- include/linux/mm_types.h | 2 ++ 2 files changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 0619f9fa7581..1876825d6700 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -479,7 +479,8 @@ static inline bool fault_flag_allow_retry_first(enum fault_flag flags) { FAULT_FLAG_USER, "USER" }, \ { FAULT_FLAG_REMOTE, "REMOTE" }, \ { FAULT_FLAG_INSTRUCTION, "INSTRUCTION" }, \ - { FAULT_FLAG_INTERRUPTIBLE, "INTERRUPTIBLE" } + { FAULT_FLAG_INTERRUPTIBLE, "INTERRUPTIBLE" }, \ + { FAULT_FLAG_VMA_LOCK, "VMA_LOCK" } /* * vm_fault is filled by the pagefault handler and passed to the vma's diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 3248ae45cb2e..3a6cf4c2edd0 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -1049,6 +1049,7 @@ typedef struct { * mapped after the fault. * @FAULT_FLAG_ORIG_PTE_VALID: whether the fault has vmf->orig_pte cached. * We should only access orig_pte if this flag set. + * @FAULT_FLAG_VMA_LOCK: The fault is handled under VMA lock. * * About @FAULT_FLAG_ALLOW_RETRY and @FAULT_FLAG_TRIED: we can specify * whether we would allow page faults to retry by specifying these two @@ -1086,6 +1087,7 @@ enum fault_flag { FAULT_FLAG_INTERRUPTIBLE = 1 << 9, FAULT_FLAG_UNSHARE = 1 << 10, FAULT_FLAG_ORIG_PTE_VALID = 1 << 11, + FAULT_FLAG_VMA_LOCK = 1 << 12, }; typedef unsigned int __bitwise zap_flags_t; -- cgit v1.2.3 From 52f238653e452e0fda61e880f263a173d219acd1 Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Mon, 27 Feb 2023 09:36:27 -0800 Subject: mm: introduce per-VMA lock statistics Add a new CONFIG_PER_VMA_LOCK_STATS config option to dump extra statistics about handling page fault under VMA lock. Link: https://lkml.kernel.org/r/20230227173632.3292573-29-surenb@google.com Signed-off-by: Suren Baghdasaryan Signed-off-by: Andrew Morton --- include/linux/vm_event_item.h | 6 ++++++ include/linux/vmstat.h | 6 ++++++ 2 files changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h index 7f5d1caf5890..8abfa1240040 100644 --- a/include/linux/vm_event_item.h +++ b/include/linux/vm_event_item.h @@ -149,6 +149,12 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, #ifdef CONFIG_X86 DIRECT_MAP_LEVEL2_SPLIT, DIRECT_MAP_LEVEL3_SPLIT, +#endif +#ifdef CONFIG_PER_VMA_LOCK_STATS + VMA_LOCK_SUCCESS, + VMA_LOCK_ABORT, + VMA_LOCK_RETRY, + VMA_LOCK_MISS, #endif NR_VM_EVENT_ITEMS }; diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index 19cf5b6892ce..fed855bae6d8 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -125,6 +125,12 @@ static inline void vm_events_fold_cpu(int cpu) #define count_vm_tlb_events(x, y) do { (void)(y); } while (0) #endif +#ifdef CONFIG_PER_VMA_LOCK_STATS +#define count_vm_vma_lock_event(x) count_vm_event(x) +#else +#define count_vm_vma_lock_event(x) do {} while (0) +#endif + #define __count_zid_vm_events(item, zid, delta) \ __count_vm_events(item##_NORMAL - ZONE_NORMAL + zid, delta) -- cgit v1.2.3 From 0d2ebf9c3f7822e7ba3e4792ea3b6b19aa2da34a Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Mon, 27 Feb 2023 09:36:31 -0800 Subject: mm/mmap: free vm_area_struct without call_rcu in exit_mmap call_rcu() can take a long time when callback offloading is enabled. Its use in the vm_area_free can cause regressions in the exit path when multiple VMAs are being freed. Because exit_mmap() is called only after the last mm user drops its refcount, the page fault handlers can't be racing with it. Any other possible user like oom-reaper or process_mrelease are already synchronized using mmap_lock. Therefore exit_mmap() can free VMAs directly, without the use of call_rcu(). Expose __vm_area_free() and use it from exit_mmap() to avoid possible call_rcu() floods and performance regressions caused by it. Link: https://lkml.kernel.org/r/20230227173632.3292573-33-surenb@google.com Signed-off-by: Suren Baghdasaryan Signed-off-by: Andrew Morton --- include/linux/mm.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 1876825d6700..f31c75dc190e 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -257,6 +257,8 @@ void setup_initial_init_mm(void *start_code, void *end_code, struct vm_area_struct *vm_area_alloc(struct mm_struct *); struct vm_area_struct *vm_area_dup(struct vm_area_struct *); void vm_area_free(struct vm_area_struct *); +/* Use only if VMA has no other users */ +void __vm_area_free(struct vm_area_struct *vma); #ifndef CONFIG_MMU extern struct rb_root nommu_region_tree; -- cgit v1.2.3 From c7f8f31c00d187a2c71a241c7f2bd6aa102a4e6f Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Mon, 27 Feb 2023 09:36:32 -0800 Subject: mm: separate vma->lock from vm_area_struct vma->lock being part of the vm_area_struct causes performance regression during page faults because during contention its count and owner fields are constantly updated and having other parts of vm_area_struct used during page fault handling next to them causes constant cache line bouncing. Fix that by moving the lock outside of the vm_area_struct. All attempts to keep vma->lock inside vm_area_struct in a separate cache line still produce performance regression especially on NUMA machines. Smallest regression was achieved when lock is placed in the fourth cache line but that bloats vm_area_struct to 256 bytes. Considering performance and memory impact, separate lock looks like the best option. It increases memory footprint of each VMA but that can be optimized later if the new size causes issues. Note that after this change vma_init() does not allocate or initialize vma->lock anymore. A number of drivers allocate a pseudo VMA on the stack but they never use the VMA's lock, therefore it does not need to be allocated. The future drivers which might need the VMA lock should use vm_area_alloc()/vm_area_free() to allocate the VMA. Link: https://lkml.kernel.org/r/20230227173632.3292573-34-surenb@google.com Signed-off-by: Suren Baghdasaryan Signed-off-by: Andrew Morton --- include/linux/mm.h | 23 ++++++++++------------- include/linux/mm_types.h | 6 +++++- 2 files changed, 15 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index f31c75dc190e..f5487a86b154 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -628,12 +628,6 @@ struct vm_operations_struct { }; #ifdef CONFIG_PER_VMA_LOCK -static inline void vma_init_lock(struct vm_area_struct *vma) -{ - init_rwsem(&vma->lock); - vma->vm_lock_seq = -1; -} - /* * Try to read-lock a vma. The function is allowed to occasionally yield false * locked result to avoid performance overhead, in which case we fall back to @@ -645,17 +639,17 @@ static inline bool vma_start_read(struct vm_area_struct *vma) if (vma->vm_lock_seq == READ_ONCE(vma->vm_mm->mm_lock_seq)) return false; - if (unlikely(down_read_trylock(&vma->lock) == 0)) + if (unlikely(down_read_trylock(&vma->vm_lock->lock) == 0)) return false; /* * Overflow might produce false locked result. * False unlocked result is impossible because we modify and check - * vma->vm_lock_seq under vma->lock protection and mm->mm_lock_seq + * vma->vm_lock_seq under vma->vm_lock protection and mm->mm_lock_seq * modification invalidates all existing locks. */ if (unlikely(vma->vm_lock_seq == READ_ONCE(vma->vm_mm->mm_lock_seq))) { - up_read(&vma->lock); + up_read(&vma->vm_lock->lock); return false; } return true; @@ -664,7 +658,7 @@ static inline bool vma_start_read(struct vm_area_struct *vma) static inline void vma_end_read(struct vm_area_struct *vma) { rcu_read_lock(); /* keeps vma alive till the end of up_read */ - up_read(&vma->lock); + up_read(&vma->vm_lock->lock); rcu_read_unlock(); } @@ -687,9 +681,9 @@ static inline void vma_start_write(struct vm_area_struct *vma) if (__is_vma_write_locked(vma, &mm_lock_seq)) return; - down_write(&vma->lock); + down_write(&vma->vm_lock->lock); vma->vm_lock_seq = mm_lock_seq; - up_write(&vma->lock); + up_write(&vma->vm_lock->lock); } static inline bool vma_try_start_write(struct vm_area_struct *vma) @@ -740,6 +734,10 @@ static inline void vma_mark_detached(struct vm_area_struct *vma, #endif /* CONFIG_PER_VMA_LOCK */ +/* + * WARNING: vma_init does not initialize vma->vm_lock. + * Use vm_area_alloc()/vm_area_free() if vma needs locking. + */ static inline void vma_init(struct vm_area_struct *vma, struct mm_struct *mm) { static const struct vm_operations_struct dummy_vm_ops = {}; @@ -749,7 +747,6 @@ static inline void vma_init(struct vm_area_struct *vma, struct mm_struct *mm) vma->vm_ops = &dummy_vm_ops; INIT_LIST_HEAD(&vma->anon_vma_chain); vma_mark_detached(vma, false); - vma_init_lock(vma); } /* Use when VMA is not part of the VMA tree and needs no locking */ diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 3a6cf4c2edd0..1b3031e95215 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -471,6 +471,10 @@ struct anon_vma_name { char name[]; }; +struct vma_lock { + struct rw_semaphore lock; +}; + /* * This struct describes a virtual memory area. There is one of these * per VM-area/task. A VM area is any part of the process virtual memory @@ -505,7 +509,7 @@ struct vm_area_struct { #ifdef CONFIG_PER_VMA_LOCK int vm_lock_seq; - struct rw_semaphore lock; + struct vma_lock *vm_lock; /* Flag to indicate areas detached from the mm->mm_mt tree */ bool detached; -- cgit v1.2.3 From ef6a22b70f6d90449a5c797b8968a682824e2011 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Wed, 1 Mar 2023 17:49:00 +0530 Subject: sched/numa: apply the scan delay to every new vma Pach series "sched/numa: Enhance vma scanning", v3. The patchset proposes one of the enhancements to numa vma scanning suggested by Mel. This is continuation of [3]. Reposting the rebased patchset to akpm mm-unstable tree (March 1) Existing mechanism of scan period involves, scan period derived from per-thread stats. Process Adaptive autoNUMA [1] proposed to gather NUMA fault stats at per-process level to capture aplication behaviour better. During that course of discussion, Mel proposed several ideas to enhance current numa balancing. One of the suggestion was below Track what threads access a VMA. The suggestion was to use an unsigned long pid_mask and use the lower bits to tag approximately what threads access a VMA. Skip VMAs that did not trap a fault. This would be approximate because of PID collisions but would reduce scanning of areas the thread is not interested in. The above suggestion intends not to penalize threads that has no interest in the vma, thus reduce scanning overhead. V3 changes are mostly based on PeterZ comments (details below in changes) Summary of patchset: Current patchset implements: 1. Delay the vma scanning logic for newly created VMA's so that additional overhead of scanning is not incurred for short lived tasks (implementation by Mel) 2. Store the information of tasks accessing VMA in 2 windows. It is regularly cleared in (4*sysctl_numa_balancing_scan_delay) interval. The above time is derived from experimenting (Suggested by PeterZ) to balance between frequent clearing vs obsolete access data 3. hash_32 used to encode task index accessing VMA information 4. VMA's acess information is used to skip scanning for the tasks which had not accessed VMA Changes since V2: patch1: - Renaming of structure, macro to function, - Add explanation to heuristics - Adding more details from result (PeterZ) Patch2: - Usage of test and set bit (PeterZ) - Move storing access PID info to numa_migrate_prep() - Add a note on fainess among tasks allowed to scan (PeterZ) Patch3: - Maintain two windows of access PID information (PeterZ supported implementation and Gave idea to extend to N if needed) Patch4: - Apply hash_32 function to track VMA accessing PIDs (PeterZ) Changes since RFC V1: - Include Mel's vma scan delay patch - Change the accessing pid store logic (Thanks Mel) - Fencing structure / code to NUMA_BALANCING (David, Mel) - Adding clearing access PID logic (Mel) - Descriptive change log ( Mike Rapoport) Things to ponder over: ========================================== - Improvement to clearing accessing PIDs logic (discussed in-detail in patch3 itself (Done in this patchset by implementing 2 window history) - Current scan period is not changed in the patchset, so we do see frequent tries to scan. Relaxing scan period dynamically could improve results further. [1] sched/numa: Process Adaptive autoNUMA Link: https://lore.kernel.org/lkml/20220128052851.17162-1-bharata@amd.com/T/ [2] RFC V1 Link: https://lore.kernel.org/all/cover.1673610485.git.raghavendra.kt@amd.com/ [3] V2 Link: https://lore.kernel.org/lkml/cover.1675159422.git.raghavendra.kt@amd.com/ Results: Summary: Huge autonuma cost reduction seen in mmtest. Kernbench improvement is more than 5% and huge system time (80%+) improvement from mmtest autonuma. (dbench had huge std deviation to post) kernbench =========== 6.2.0-mmunstable-base 6.2.0-mmunstable-patched Amean user-256 22002.51 ( 0.00%) 22649.95 * -2.94%* Amean syst-256 10162.78 ( 0.00%) 8214.13 * 19.17%* Amean elsp-256 160.74 ( 0.00%) 156.92 * 2.38%* Duration User 66017.43 67959.84 Duration System 30503.15 24657.03 Duration Elapsed 504.61 493.12 6.2.0-mmunstable-base 6.2.0-mmunstable-patched Ops NUMA alloc hit 1738835089.00 1738780310.00 Ops NUMA alloc local 1738834448.00 1738779711.00 Ops NUMA base-page range updates 477310.00 392566.00 Ops NUMA PTE updates 477310.00 392566.00 Ops NUMA hint faults 96817.00 87555.00 Ops NUMA hint local faults % 10150.00 2192.00 Ops NUMA hint local percent 10.48 2.50 Ops NUMA pages migrated 86660.00 85363.00 Ops AutoNUMA cost 489.07 442.14 autonumabench =============== 6.2.0-mmunstable-base 6.2.0-mmunstable-patched Amean syst-NUMA01 399.50 ( 0.00%) 52.05 * 86.97%* Amean syst-NUMA01_THREADLOCAL 0.21 ( 0.00%) 0.22 * -5.41%* Amean syst-NUMA02 0.80 ( 0.00%) 0.78 * 2.68%* Amean syst-NUMA02_SMT 0.65 ( 0.00%) 0.68 * -3.95%* Amean elsp-NUMA01 313.26 ( 0.00%) 313.11 * 0.05%* Amean elsp-NUMA01_THREADLOCAL 1.06 ( 0.00%) 1.08 * -1.76%* Amean elsp-NUMA02 3.19 ( 0.00%) 3.24 * -1.52%* Amean elsp-NUMA02_SMT 3.72 ( 0.00%) 3.61 * 2.92%* Duration User 396433.47 324835.96 Duration System 2808.70 376.66 Duration Elapsed 2258.61 2258.12 6.2.0-mmunstable-base 6.2.0-mmunstable-patched Ops NUMA alloc hit 59921806.00 49623489.00 Ops NUMA alloc miss 0.00 0.00 Ops NUMA interleave hit 0.00 0.00 Ops NUMA alloc local 59920880.00 49622594.00 Ops NUMA base-page range updates 152259275.00 50075.00 Ops NUMA PTE updates 152259275.00 50075.00 Ops NUMA PMD updates 0.00 0.00 Ops NUMA hint faults 154660352.00 39014.00 Ops NUMA hint local faults % 138550501.00 23139.00 Ops NUMA hint local percent 89.58 59.31 Ops NUMA pages migrated 8179067.00 14147.00 Ops AutoNUMA cost 774522.98 195.69 This patch (of 4): Currently whenever a new task is created we wait for sysctl_numa_balancing_scan_delay to avoid unnessary scanning overhead. Extend the same logic to new or very short-lived VMAs. [raghavendra.kt@amd.com: add initialization in vm_area_dup())] Link: https://lkml.kernel.org/r/cover.1677672277.git.raghavendra.kt@amd.com Link: https://lkml.kernel.org/r/7a6fbba87c8b51e67efd3e74285bb4cb311a16ca.1677672277.git.raghavendra.kt@amd.com Signed-off-by: Mel Gorman Signed-off-by: Raghavendra K T Cc: Bharata B Rao Cc: David Hildenbrand Cc: Ingo Molnar Cc: Mike Rapoport Cc: Peter Zijlstra Cc: Disha Talreja Signed-off-by: Andrew Morton --- include/linux/mm.h | 16 ++++++++++++++++ include/linux/mm_types.h | 7 +++++++ 2 files changed, 23 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index f5487a86b154..9f08a11b355c 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -29,6 +29,7 @@ #include #include #include +#include struct mempolicy; struct anon_vma; @@ -627,6 +628,20 @@ struct vm_operations_struct { unsigned long addr); }; +#ifdef CONFIG_NUMA_BALANCING +static inline void vma_numab_state_init(struct vm_area_struct *vma) +{ + vma->numab_state = NULL; +} +static inline void vma_numab_state_free(struct vm_area_struct *vma) +{ + kfree(vma->numab_state); +} +#else +static inline void vma_numab_state_init(struct vm_area_struct *vma) {} +static inline void vma_numab_state_free(struct vm_area_struct *vma) {} +#endif /* CONFIG_NUMA_BALANCING */ + #ifdef CONFIG_PER_VMA_LOCK /* * Try to read-lock a vma. The function is allowed to occasionally yield false @@ -747,6 +762,7 @@ static inline void vma_init(struct vm_area_struct *vma, struct mm_struct *mm) vma->vm_ops = &dummy_vm_ops; INIT_LIST_HEAD(&vma->anon_vma_chain); vma_mark_detached(vma, false); + vma_numab_state_init(vma); } /* Use when VMA is not part of the VMA tree and needs no locking */ diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 1b3031e95215..3e1a42673769 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -475,6 +475,10 @@ struct vma_lock { struct rw_semaphore lock; }; +struct vma_numab_state { + unsigned long next_scan; +}; + /* * This struct describes a virtual memory area. There is one of these * per VM-area/task. A VM area is any part of the process virtual memory @@ -560,6 +564,9 @@ struct vm_area_struct { #endif #ifdef CONFIG_NUMA struct mempolicy *vm_policy; /* NUMA policy for the VMA */ +#endif +#ifdef CONFIG_NUMA_BALANCING + struct vma_numab_state *numab_state; /* NUMA Balancing state */ #endif struct vm_userfaultfd_ctx vm_userfaultfd_ctx; } __randomize_layout; -- cgit v1.2.3 From fc137c0ddab29b591db6a091dc6d7ce20ccb73f2 Mon Sep 17 00:00:00 2001 From: Raghavendra K T Date: Wed, 1 Mar 2023 17:49:01 +0530 Subject: sched/numa: enhance vma scanning logic During Numa scanning make sure only relevant vmas of the tasks are scanned. Before: All the tasks of a process participate in scanning the vma even if they do not access vma in it's lifespan. Now: Except cases of first few unconditional scans, if a process do not touch vma (exluding false positive cases of PID collisions) tasks no longer scan all vma Logic used: 1) 6 bits of PID used to mark active bit in vma numab status during fault to remember PIDs accessing vma. (Thanks Mel) 2) Subsequently in scan path, vma scanning is skipped if current PID had not accessed vma. 3) First two times we do allow unconditional scan to preserve earlier behaviour of scanning. Acknowledgement to Bharata B Rao for initial patch to store pid information and Peter Zijlstra (Usage of test and set bit) Link: https://lkml.kernel.org/r/092f03105c7c1d3450f4636b1ea350407f07640e.1677672277.git.raghavendra.kt@amd.com Signed-off-by: Raghavendra K T Suggested-by: Mel Gorman Cc: David Hildenbrand Cc: Disha Talreja Cc: Ingo Molnar Cc: Mike Rapoport Signed-off-by: Andrew Morton --- include/linux/mm.h | 14 ++++++++++++++ include/linux/mm_types.h | 1 + 2 files changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 9f08a11b355c..215327daffae 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1686,6 +1686,16 @@ static inline int xchg_page_access_time(struct page *page, int time) last_time = page_cpupid_xchg_last(page, time >> PAGE_ACCESS_TIME_BUCKETS); return last_time << PAGE_ACCESS_TIME_BUCKETS; } + +static inline void vma_set_access_pid_bit(struct vm_area_struct *vma) +{ + unsigned int pid_bit; + + pid_bit = current->pid % BITS_PER_LONG; + if (vma->numab_state && !test_bit(pid_bit, &vma->numab_state->access_pids)) { + __set_bit(pid_bit, &vma->numab_state->access_pids); + } +} #else /* !CONFIG_NUMA_BALANCING */ static inline int page_cpupid_xchg_last(struct page *page, int cpupid) { @@ -1735,6 +1745,10 @@ static inline bool cpupid_match_pid(struct task_struct *task, int cpupid) { return false; } + +static inline void vma_set_access_pid_bit(struct vm_area_struct *vma) +{ +} #endif /* CONFIG_NUMA_BALANCING */ #if defined(CONFIG_KASAN_SW_TAGS) || defined(CONFIG_KASAN_HW_TAGS) diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 3e1a42673769..f8cbd8efc7cb 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -477,6 +477,7 @@ struct vma_lock { struct vma_numab_state { unsigned long next_scan; + unsigned long access_pids; }; /* -- cgit v1.2.3 From 20f586486b87dcfe10b8c79398e24e720885588a Mon Sep 17 00:00:00 2001 From: Raghavendra K T Date: Wed, 1 Mar 2023 17:49:02 +0530 Subject: sched/numa: implement access PID reset logic This helps to ensure that only recently accessed PIDs scan the VMAs. Current implementation: (idea supported by PeterZ) 1. Accessing PID information is maintained in two windows. access_pids[1] being newest. 2. Reset old access PID info i.e. access_pid[0] every (4 * sysctl_numa_balancing_scan_delay) interval after initial scan delay period expires. The above interval seemed to be experimentally optimum since it avoids frequent reset of access info as well as helps clearing the old access info regularly. The reset logic is implemented in scan path. Link: https://lkml.kernel.org/r/f7a675f66d1442d048b4216b2baf94515012c405.1677672277.git.raghavendra.kt@amd.com Signed-off-by: Raghavendra K T Suggested-by: Mel Gorman Cc: Bharata B Rao Cc: David Hildenbrand Cc: Disha Talreja Cc: Ingo Molnar Cc: Mike Rapoport Cc: Peter Zijlstra Signed-off-by: Andrew Morton --- include/linux/mm.h | 4 ++-- include/linux/mm_types.h | 3 ++- 2 files changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 215327daffae..e05a878e186e 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1692,8 +1692,8 @@ static inline void vma_set_access_pid_bit(struct vm_area_struct *vma) unsigned int pid_bit; pid_bit = current->pid % BITS_PER_LONG; - if (vma->numab_state && !test_bit(pid_bit, &vma->numab_state->access_pids)) { - __set_bit(pid_bit, &vma->numab_state->access_pids); + if (vma->numab_state && !test_bit(pid_bit, &vma->numab_state->access_pids[1])) { + __set_bit(pid_bit, &vma->numab_state->access_pids[1]); } } #else /* !CONFIG_NUMA_BALANCING */ diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index f8cbd8efc7cb..092f842a854f 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -477,7 +477,8 @@ struct vma_lock { struct vma_numab_state { unsigned long next_scan; - unsigned long access_pids; + unsigned long next_pid_reset; + unsigned long access_pids[2]; }; /* -- cgit v1.2.3 From d46031f40e0f7f7bf63914bb3f2e404ad3886ecd Mon Sep 17 00:00:00 2001 From: Raghavendra K T Date: Wed, 1 Mar 2023 17:49:03 +0530 Subject: sched/numa: use hash_32 to mix up PIDs accessing VMA before: last 6 bits of PID is used as index to store information about tasks accessing VMA's. after: hash_32 is used to take of cases where tasks are created over a period of time, and thus improve collision probability. Result: The patch series overall improves autonuma cost. Kernbench around more than 5% improvement and system time in mmtest autonuma showed more than 80% improvement Link: https://lkml.kernel.org/r/d5a9f75513300caed74e5c8570bba9317b963c2b.1677672277.git.raghavendra.kt@amd.com Signed-off-by: Raghavendra K T Suggested-by: Peter Zijlstra Cc: Bharata B Rao Cc: David Hildenbrand Cc: Disha Talreja Cc: Ingo Molnar Cc: Mel Gorman Cc: Mike Rapoport Signed-off-by: Andrew Morton --- include/linux/mm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index e05a878e186e..e249208f8fbe 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1691,7 +1691,7 @@ static inline void vma_set_access_pid_bit(struct vm_area_struct *vma) { unsigned int pid_bit; - pid_bit = current->pid % BITS_PER_LONG; + 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]); } -- cgit v1.2.3 From 810c03d9d7c978b4ee5287d8987043a9be1d614e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Tue, 21 Mar 2023 16:40:37 +0100 Subject: rpmsg: qcom_smd: Make qcom_smd_unregister_edge() return void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This function returned zero unconditionally. Convert it to return no value instead. This makes it more obvious what happens in the callers. One caller is converted to return zero explicitly. The only other caller (smd_subdev_stop() in drivers/remoteproc/qcom_common.c) already ignored the return value before. Signed-off-by: Uwe Kleine-König Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20230321154039.355098-2-u.kleine-koenig@pengutronix.de --- include/linux/rpmsg/qcom_smd.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rpmsg/qcom_smd.h b/include/linux/rpmsg/qcom_smd.h index 2e92d7407a85..3379bf4e1cb1 100644 --- a/include/linux/rpmsg/qcom_smd.h +++ b/include/linux/rpmsg/qcom_smd.h @@ -11,7 +11,7 @@ struct qcom_smd_edge; struct qcom_smd_edge *qcom_smd_register_edge(struct device *parent, struct device_node *node); -int qcom_smd_unregister_edge(struct qcom_smd_edge *edge); +void qcom_smd_unregister_edge(struct qcom_smd_edge *edge); #else @@ -22,9 +22,8 @@ qcom_smd_register_edge(struct device *parent, return NULL; } -static inline int qcom_smd_unregister_edge(struct qcom_smd_edge *edge) +static inline void qcom_smd_unregister_edge(struct qcom_smd_edge *edge) { - return 0; } #endif -- cgit v1.2.3 From 34bf93472f8fb60b4189aa2872471017e739cf0a Mon Sep 17 00:00:00 2001 From: Viktor Malik Date: Thu, 30 Mar 2023 12:20:01 +0200 Subject: kallsyms: move module-related functions under correct configs Functions for searching module kallsyms should have non-empty definitions only if CONFIG_MODULES=y and CONFIG_KALLSYMS=y. Until now, only CONFIG_MODULES check was used for many of these, which may have caused complilation errors on some configs. This patch moves all relevant functions under the correct configs. Fixes: bd5314f8dd2d ("kallsyms, bpf: Move find_kallsyms_symbol_value out of internal header") Signed-off-by: Viktor Malik Reported-by: kernel test robot Link: https://lore.kernel.org/oe-kbuild-all/202303181535.RFDCnz3E-lkp@intel.com/ Link: https://lore.kernel.org/r/20230330102001.2183693-1-vmalik@redhat.com Signed-off-by: Alexei Starovoitov --- include/linux/module.h | 135 +++++++++++++++++++++++++++---------------------- 1 file changed, 74 insertions(+), 61 deletions(-) (limited to 'include/linux') diff --git a/include/linux/module.h b/include/linux/module.h index 41cfd3be57e5..886d24877c7c 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -608,16 +608,6 @@ static inline bool within_module(unsigned long addr, const struct module *mod) /* Search for module by name: must be in a RCU-sched critical section. */ struct module *find_module(const char *name); -/* Returns 0 and fills in value, defined and namebuf, or -ERANGE if - symnum out of range. */ -int module_get_kallsym(unsigned int symnum, unsigned long *value, char *type, - char *name, char *module_name, int *exported); - -/* Look for this name: can be of form module:name. */ -unsigned long module_kallsyms_lookup_name(const char *name); - -unsigned long find_kallsyms_symbol_value(struct module *mod, const char *name); - extern void __noreturn __module_put_and_kthread_exit(struct module *mod, long code); #define module_put_and_kthread_exit(code) __module_put_and_kthread_exit(THIS_MODULE, code) @@ -664,17 +654,6 @@ static inline void __module_get(struct module *module) /* Dereference module function descriptor */ void *dereference_module_function_descriptor(struct module *mod, void *ptr); -/* For kallsyms to ask for address resolution. namebuf should be at - * least KSYM_NAME_LEN long: a pointer to namebuf is returned if - * found, otherwise NULL. */ -const char *module_address_lookup(unsigned long addr, - unsigned long *symbolsize, - unsigned long *offset, - char **modname, const unsigned char **modbuildid, - char *namebuf); -int lookup_module_symbol_name(unsigned long addr, char *symname); -int lookup_module_symbol_attrs(unsigned long addr, unsigned long *size, unsigned long *offset, char *modname, char *name); - int register_module_notifier(struct notifier_block *nb); int unregister_module_notifier(struct notifier_block *nb); @@ -765,45 +744,6 @@ static inline void module_put(struct module *module) #define module_name(mod) "kernel" -/* For kallsyms to ask for address resolution. NULL means not found. */ -static inline const char *module_address_lookup(unsigned long addr, - unsigned long *symbolsize, - unsigned long *offset, - char **modname, - const unsigned char **modbuildid, - char *namebuf) -{ - return NULL; -} - -static inline int lookup_module_symbol_name(unsigned long addr, char *symname) -{ - return -ERANGE; -} - -static inline int lookup_module_symbol_attrs(unsigned long addr, unsigned long *size, unsigned long *offset, char *modname, char *name) -{ - return -ERANGE; -} - -static inline int module_get_kallsym(unsigned int symnum, unsigned long *value, - char *type, char *name, - char *module_name, int *exported) -{ - return -ERANGE; -} - -static inline unsigned long module_kallsyms_lookup_name(const char *name) -{ - return 0; -} - -static inline unsigned long find_kallsyms_symbol_value(struct module *mod, - const char *name) -{ - return 0; -} - static inline int register_module_notifier(struct notifier_block *nb) { /* no events will happen anyway, so this can always succeed */ @@ -899,7 +839,36 @@ int module_kallsyms_on_each_symbol(const char *modname, int (*fn)(void *, const char *, struct module *, unsigned long), void *data); -#else + +/* For kallsyms to ask for address resolution. namebuf should be at + * least KSYM_NAME_LEN long: a pointer to namebuf is returned if + * found, otherwise NULL. + */ +const char *module_address_lookup(unsigned long addr, + unsigned long *symbolsize, + unsigned long *offset, + char **modname, const unsigned char **modbuildid, + char *namebuf); +int lookup_module_symbol_name(unsigned long addr, char *symname); +int lookup_module_symbol_attrs(unsigned long addr, + unsigned long *size, + unsigned long *offset, + char *modname, + char *name); + +/* Returns 0 and fills in value, defined and namebuf, or -ERANGE if + * symnum out of range. + */ +int module_get_kallsym(unsigned int symnum, unsigned long *value, char *type, + char *name, char *module_name, int *exported); + +/* Look for this name: can be of form module:name. */ +unsigned long module_kallsyms_lookup_name(const char *name); + +unsigned long find_kallsyms_symbol_value(struct module *mod, const char *name); + +#else /* CONFIG_MODULES && CONFIG_KALLSYMS */ + static inline int module_kallsyms_on_each_symbol(const char *modname, int (*fn)(void *, const char *, struct module *, unsigned long), @@ -907,6 +876,50 @@ static inline int module_kallsyms_on_each_symbol(const char *modname, { return -EOPNOTSUPP; } + +/* For kallsyms to ask for address resolution. NULL means not found. */ +static inline const char *module_address_lookup(unsigned long addr, + unsigned long *symbolsize, + unsigned long *offset, + char **modname, + const unsigned char **modbuildid, + char *namebuf) +{ + return NULL; +} + +static inline int lookup_module_symbol_name(unsigned long addr, char *symname) +{ + return -ERANGE; +} + +static inline int lookup_module_symbol_attrs(unsigned long addr, + unsigned long *size, + unsigned long *offset, + char *modname, + char *name) +{ + return -ERANGE; +} + +static inline int module_get_kallsym(unsigned int symnum, unsigned long *value, + char *type, char *name, + char *module_name, int *exported) +{ + return -ERANGE; +} + +static inline unsigned long module_kallsyms_lookup_name(const char *name) +{ + return 0; +} + +static inline unsigned long find_kallsyms_symbol_value(struct module *mod, + const char *name) +{ + return 0; +} + #endif /* CONFIG_MODULES && CONFIG_KALLSYMS */ #endif /* _LINUX_MODULE_H */ -- cgit v1.2.3 From 94623f579ce338b5fa61b5acaa5beb8aa657fb9e Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 3 Apr 2023 13:54:37 +0200 Subject: netfilter: br_netfilter: fix recent physdev match breakage Recent attempt to ensure PREROUTING hook is executed again when a decrypted ipsec packet received on a bridge passes through the network stack a second time broke the physdev match in INPUT hook. We can't discard the nf_bridge info strct from sabotage_in hook, as this is needed by the physdev match. Keep the struct around and handle this with another conditional instead. Fixes: 2b272bb558f1 ("netfilter: br_netfilter: disable sabotage_in hook after first suppression") Reported-and-tested-by: Farid BENAMROUCHE Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/skbuff.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index ff7ad331fb82..1ec3530c8191 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -294,6 +294,7 @@ struct nf_bridge_info { u8 pkt_otherhost:1; u8 in_prerouting:1; u8 bridged_dnat:1; + u8 sabotage_in_done:1; __u16 frag_max_size; struct net_device *physindev; -- cgit v1.2.3 From fb131c472df92b2885262e747906c0a4038c82e5 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Tue, 4 Apr 2023 13:19:55 +0200 Subject: platform/x86: apple-gmux: Fix iomem_base __iomem annotation Fix the __iomem annotation of the iomem_base pointers in the apple-gmux code. The __iomem should go before the *. This fixes a bunch of sparse warnings like this one: drivers/platform/x86/apple-gmux.c:224:48: sparse: expected void const [noderef] __iomem * got unsigned char [usertype] * Fixes: 0c18184de990 ("platform/x86: apple-gmux: support MMIO gmux on T2 Macs") Reported-by: kernel test robot Link: https://lore.kernel.org/oe-kbuild-all/202304040401.IMxt7Ubi-lkp@intel.com/ Suggested-by: Dan Carpenter Signed-off-by: Hans de Goede Reviewed-by: Orlando Chamberlain Link: https://lore.kernel.org/r/20230404111955.43266-1-hdegoede@redhat.com --- include/linux/apple-gmux.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/apple-gmux.h b/include/linux/apple-gmux.h index a7a7d430024b..206d97ffda79 100644 --- a/include/linux/apple-gmux.h +++ b/include/linux/apple-gmux.h @@ -66,7 +66,7 @@ static inline bool apple_gmux_is_indexed(unsigned long iostart) static inline bool apple_gmux_is_mmio(unsigned long iostart) { - u8 *__iomem iomem_base = ioremap(iostart, 16); + u8 __iomem *iomem_base = ioremap(iostart, 16); u8 val; if (!iomem_base) -- cgit v1.2.3 From d0a4564bd024eaa81cab8c7255e7c44230bdd8a2 Mon Sep 17 00:00:00 2001 From: Olivier Moysan Date: Tue, 13 Dec 2022 11:27:07 +0100 Subject: pwm: stm32: Enforce settings for PWM capture MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The PWM capture assumes that the input selector is set to default input and that the slave mode is disabled. Force reset state for TISEL and SMCR registers to match this requirement. Note that slave mode disabling is not a pre-requisite by itself for capture mode, as hardware supports it for PWM capture. However, the current implementation of the driver does not allow slave mode for PWM capture. Setting slave mode for PWM capture results in wrong capture values. Signed-off-by: Olivier Moysan Acked-by: Lee Jones Acked-by: Uwe Kleine-König Signed-off-by: Thierry Reding --- include/linux/mfd/stm32-timers.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mfd/stm32-timers.h b/include/linux/mfd/stm32-timers.h index 5f5c43fd69dd..1b94325febb3 100644 --- a/include/linux/mfd/stm32-timers.h +++ b/include/linux/mfd/stm32-timers.h @@ -31,6 +31,7 @@ #define TIM_BDTR 0x44 /* Break and Dead-Time Reg */ #define TIM_DCR 0x48 /* DMA control register */ #define TIM_DMAR 0x4C /* DMA register for transfer */ +#define TIM_TISEL 0x68 /* Input Selection */ #define TIM_CR1_CEN BIT(0) /* Counter Enable */ #define TIM_CR1_DIR BIT(4) /* Counter Direction */ -- cgit v1.2.3 From 539adfedbd2d5cda2f9e2d83b35b364834b67d58 Mon Sep 17 00:00:00 2001 From: Bastien Nocera Date: Wed, 5 Apr 2023 11:27:54 +0200 Subject: USB: core: Fix docs warning caused by wireless_status feature Fix wrongly named 'dev' parameter in doc block, should have been iface: drivers/usb/core/message.c:1939: warning: Function parameter or member 'iface' not described in 'usb_set_wireless_status' drivers/usb/core/message.c:1939: warning: Excess function parameter 'dev' description in 'usb_set_wireless_status' And fix missing struct member doc in kernel API, and reorder to match struct: include/linux/usb.h:270: warning: Function parameter or member 'wireless_status_work' not described in 'usb_interface' Reported-by: Stephen Rothwell Link: https://lore.kernel.org/linux-next/20230405114807.5a57bf46@canb.auug.org.au/T/#t Fixes: 0a4db185f078 ("USB: core: Add API to change the wireless_status") Signed-off-by: Bastien Nocera Acked-by: Greg Kroah-Hartman Link: https://lore.kernel.org/r/20230405092754.36579-1-hadess@hadess.net [bentiss: fix checkpatch warning] Signed-off-by: Benjamin Tissoires --- include/linux/usb.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb.h b/include/linux/usb.h index 6dfd59d3d695..0a81e0f5beb4 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -203,14 +203,16 @@ enum usb_wireless_status { * following a reset or suspend operation it doesn't support. * @authorized: This allows to (de)authorize individual interfaces instead * a whole device in contrast to the device authorization. + * @wireless_status: if the USB device uses a receiver/emitter combo, whether + * the emitter is connected. + * @wireless_status_work: Used for scheduling wireless status changes + * from atomic context. * @dev: driver model's view of this device * @usb_dev: if an interface is bound to the USB major, this will point * to the sysfs representation for that device. * @reset_ws: Used for scheduling resets from atomic context. * @resetting_device: USB core reset the device, so use alt setting 0 as * current; needs bandwidth alloc after reset. - * @wireless_status: if the USB device uses a receiver/emitter combo, whether - * the emitter is connected. * * USB device drivers attach to interfaces on a physical device. Each * interface encapsulates a single high level function, such as feeding -- cgit v1.2.3 From e999a5c5a19cf3b679f3d93c49ad5f5c04e4806c Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Fri, 24 Mar 2023 18:01:01 +0000 Subject: fs: Add FGP_WRITEBEGIN This particular combination of flags is used by most filesystems in their ->write_begin method, although it does find use in a few other places. Before folios, it warranted its own function (grab_cache_page_write_begin()), but I think that just having specialised flags is enough. It certainly helps the few places that have been converted from grab_cache_page_write_begin() to __filemap_get_folio(). Signed-off-by: Matthew Wilcox (Oracle) Link: https://lore.kernel.org/r/20230324180129.1220691-2-willy@infradead.org Signed-off-by: Theodore Ts'o --- include/linux/pagemap.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 0acb8e1fb7af..51b75b89730e 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -507,6 +507,8 @@ pgoff_t page_cache_prev_miss(struct address_space *mapping, #define FGP_ENTRY 0x00000080 #define FGP_STABLE 0x00000100 +#define FGP_WRITEBEGIN (FGP_LOCK | FGP_WRITE | FGP_CREAT | FGP_STABLE) + struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index, int fgp_flags, gfp_t gfp); struct page *pagecache_get_page(struct address_space *mapping, pgoff_t index, -- cgit v1.2.3 From c76e14dc13bcf89f3b55fd9dcd036a453a822d79 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Fri, 24 Mar 2023 18:01:02 +0000 Subject: fscrypt: Add some folio helper functions fscrypt_is_bounce_folio() is the equivalent of fscrypt_is_bounce_page() and fscrypt_pagecache_folio() is the equivalent of fscrypt_pagecache_page(). Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Ritesh Harjani (IBM) Link: https://lore.kernel.org/r/20230324180129.1220691-3-willy@infradead.org Signed-off-by: Theodore Ts'o --- include/linux/fscrypt.h | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h index e0a49c3125eb..c068cb487aaa 100644 --- a/include/linux/fscrypt.h +++ b/include/linux/fscrypt.h @@ -273,6 +273,16 @@ static inline struct page *fscrypt_pagecache_page(struct page *bounce_page) return (struct page *)page_private(bounce_page); } +static inline bool fscrypt_is_bounce_folio(struct folio *folio) +{ + return folio->mapping == NULL; +} + +static inline struct folio *fscrypt_pagecache_folio(struct folio *bounce_folio) +{ + return bounce_folio->private; +} + void fscrypt_free_bounce_page(struct page *bounce_page); /* policy.c */ @@ -445,6 +455,17 @@ static inline struct page *fscrypt_pagecache_page(struct page *bounce_page) return ERR_PTR(-EINVAL); } +static inline bool fscrypt_is_bounce_folio(struct folio *folio) +{ + return false; +} + +static inline struct folio *fscrypt_pagecache_folio(struct folio *bounce_folio) +{ + WARN_ON_ONCE(1); + return ERR_PTR(-EINVAL); +} + static inline void fscrypt_free_bounce_page(struct page *bounce_page) { } -- cgit v1.2.3 From cd57b77197a434709aec0e7fb8b2e6ec8479aa4e Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Fri, 24 Mar 2023 18:01:03 +0000 Subject: ext4: Convert ext4_bio_write_page() to use a folio Remove several calls to compound_head() and the last caller of set_page_writeback_keepwrite(), so remove the wrapper too. Also export bio_add_folio() as this is the first caller from a module. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Ritesh Harjani (IBM) Reviewed-by: Theodore Ts'o Link: https://lore.kernel.org/r/20230324180129.1220691-4-willy@infradead.org Signed-off-by: Theodore Ts'o --- include/linux/page-flags.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index a7e3a3405520..2e00cc14a81c 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -766,11 +766,6 @@ bool set_page_writeback(struct page *page); #define folio_start_writeback_keepwrite(folio) \ __folio_start_writeback(folio, true) -static inline void set_page_writeback_keepwrite(struct page *page) -{ - folio_start_writeback_keepwrite(page_folio(page)); -} - static inline bool test_set_page_writeback(struct page *page) { return set_page_writeback(page); -- cgit v1.2.3 From 45166620b7254a9e9329a2b6cdfa369bc3ca9c5b Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Wed, 5 Apr 2023 15:27:24 -0500 Subject: ACPI: Replace irqdomain.h include with struct declarations linux/acpi.h includes irqdomain.h which includes of.h. Break the include chain by replacing the irqdomain include with forward declarations for struct irq_domain and irq_domain_ops which is sufficient for acpi.h. of.h also includes mod_devicetable.h which many drivers implicitly depend on. As acpi.h already includes it, just move it out of the '#ifdef CONFIG_ACPI'. Reviewed-by: Jacob Keller Reviewed-by: Greg Kroah-Hartman Signed-off-by: Rob Herring Signed-off-by: Rafael J. Wysocki --- include/linux/acpi.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index efff750f326d..96bd672dc336 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -10,12 +10,15 @@ #include #include /* for struct resource */ -#include #include #include +#include #include #include +struct irq_domain; +struct irq_domain_ops; + #ifndef _LINUX #define _LINUX #endif @@ -24,7 +27,6 @@ #ifdef CONFIG_ACPI #include -#include #include #include #include -- cgit v1.2.3 From 195d8e5da3acb17c5357526494f818a21e97cd10 Mon Sep 17 00:00:00 2001 From: Reinette Chatre Date: Wed, 29 Mar 2023 13:13:11 -0700 Subject: PCI/MSI: Provide missing stub for pci_msix_can_alloc_dyn() pci_msix_can_alloc_dyn() is not declared when CONFIG_PCI_MSI is disabled. There is no existing user of pci_msix_can_alloc_dyn() but work is in progress to change this. This work encounters the following error when CONFIG_PCI_MSI is disabled: drivers/vfio/pci/vfio_pci_intrs.c:427:21: error: implicit declaration of function 'pci_msix_can_alloc_dyn' [-Werror=implicit-function-declaration] Provide definition for pci_msix_can_alloc_dyn() in preparation for users that need to compile when CONFIG_PCI_MSI is disabled. [bhelgaas: Also reported by Arnd Bergmann in drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c; added his Fixes: line] Fixes: fb0a6a268dcd ("net/mlx5: Provide external API for allocating vectors") Fixes: 34026364df8e ("PCI/MSI: Provide post-enable dynamic allocation interfaces for MSI-X") Link: https://lore.kernel.org/oe-kbuild-all/202303291000.PWFqGCxH-lkp@intel.com/ Link: https://lore.kernel.org/r/310ecc4815dae4174031062f525245f0755c70e2.1680119924.git.reinette.chatre@intel.com Reported-by: kernel test robot Signed-off-by: Reinette Chatre Signed-off-by: Bjorn Helgaas Reviewed-by: Kuppuswamy Sathyanarayanan Cc: stable@vger.kernel.org # v6.2+ --- include/linux/pci.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index fafd8020c6d7..5e2dab675943 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1623,6 +1623,8 @@ pci_alloc_irq_vectors(struct pci_dev *dev, unsigned int min_vecs, flags, NULL); } +static inline bool pci_msix_can_alloc_dyn(struct pci_dev *dev) +{ return false; } static inline struct msi_map pci_msix_alloc_irq_at(struct pci_dev *dev, unsigned int index, const struct irq_affinity_desc *affdesc) { -- cgit v1.2.3 From 8751d15426a31baaf40f7570263c27c3e5d1dc44 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Thu, 6 Apr 2023 14:20:12 +0100 Subject: io_uring: reduce scheduling due to tw Every task_work will try to wake the task to be executed, which causes excessive scheduling and additional overhead. For some tw it's justified, but others won't do much but post a single CQE. When a task waits for multiple cqes, every such task_work will wake it up. Instead, the task may give a hint about how many cqes it waits for, io_req_local_work_add() will compare against it and skip wake ups if #cqes + #tw is not enough to satisfy the waiting condition. Task_work that uses the optimisation should be simple enough and never post more than one CQE. It's also ignored for non DEFER_TASKRUN rings. Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/d2b77e99d1e86624d8a69f7037d764b739dcd225.1680782017.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- include/linux/io_uring_types.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h index 4a6ce03a4903..fa621a508a01 100644 --- a/include/linux/io_uring_types.h +++ b/include/linux/io_uring_types.h @@ -296,7 +296,7 @@ struct io_ring_ctx { spinlock_t completion_lock; bool poll_multi_queue; - bool cq_waiting; + atomic_t cq_wait_nr; /* * ->iopoll_list is protected by the ctx->uring_lock for @@ -566,6 +566,7 @@ struct io_kiocb { atomic_t refs; atomic_t poll_refs; struct io_task_work io_task_work; + unsigned nr_tw; /* for polled requests, i.e. IORING_OP_POLL_ADD and async armed poll */ union { struct hlist_node hash_node; -- cgit v1.2.3 From fe4e5efa401fe15eab9259e358730145449e83a2 Mon Sep 17 00:00:00 2001 From: Jiaxun Yang Date: Sat, 1 Apr 2023 10:15:29 +0100 Subject: dma-mapping: provide a fallback dma_default_coherent dma_default_coherent was decleared unconditionally at kernel/dma/mapping.c but only decleared when any of non-coherent options is enabled in dma-map-ops.h. Guard the declaration in mapping.c with non-coherent options and provide a fallback definition. Signed-off-by: Jiaxun Yang Signed-off-by: Christoph Hellwig --- include/linux/dma-map-ops.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dma-map-ops.h b/include/linux/dma-map-ops.h index 41bf4bdb117a..31f114f486c4 100644 --- a/include/linux/dma-map-ops.h +++ b/include/linux/dma-map-ops.h @@ -269,6 +269,8 @@ static inline bool dev_is_dma_coherent(struct device *dev) return dev->dma_coherent; } #else +#define dma_default_coherent true + static inline bool dev_is_dma_coherent(struct device *dev) { return true; -- cgit v1.2.3 From 05f3ab7780b3c0cfe26a8134606bdf641c4f4bb2 Mon Sep 17 00:00:00 2001 From: Felix Fietkau Date: Wed, 5 Apr 2023 17:10:25 +0200 Subject: net: ethernet: mtk_eth_soc: add code for offloading flows from wlan devices WED version 2 (on MT7986 and later) can offload flows originating from wireless devices. In order to make that work, ndo_setup_tc needs to be implemented on the netdevs. This adds the required code to offload flows coming in from WED, while keeping track of the incoming wed index used for selecting the correct PPE device. Signed-off-by: Felix Fietkau Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- include/linux/soc/mediatek/mtk_wed.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/soc/mediatek/mtk_wed.h b/include/linux/soc/mediatek/mtk_wed.h index fd0b0605cf90..b2b28180dff7 100644 --- a/include/linux/soc/mediatek/mtk_wed.h +++ b/include/linux/soc/mediatek/mtk_wed.h @@ -6,6 +6,7 @@ #include #include #include +#include #define MTK_WED_TX_QUEUES 2 #define MTK_WED_RX_QUEUES 2 @@ -179,6 +180,8 @@ struct mtk_wed_ops { u32 (*irq_get)(struct mtk_wed_device *dev, u32 mask); 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); }; extern const struct mtk_wed_ops __rcu *mtk_soc_wed_ops; @@ -237,6 +240,8 @@ mtk_wed_get_rx_capa(struct mtk_wed_device *dev) (_dev)->ops->msg_update(_dev, _id, _msg, _len) #define mtk_wed_device_stop(_dev) (_dev)->ops->stop(_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) #else static inline bool mtk_wed_device_active(struct mtk_wed_device *dev) { @@ -255,6 +260,7 @@ static inline bool mtk_wed_device_active(struct mtk_wed_device *dev) #define mtk_wed_device_update_msg(_dev, _id, _msg, _len) -ENODEV #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 #endif #endif -- cgit v1.2.3 From ded2d383b1b441f380552897791ffb85a1377f08 Mon Sep 17 00:00:00 2001 From: Zhang Rui Date: Thu, 30 Mar 2023 18:45:26 +0800 Subject: thermal/core: Remove thermal_bind_params structure Remove struct thermal_bind_params because no one is using it for thermal binding now. Signed-off-by: Zhang Rui Signed-off-by: Daniel Lezcano Link: https://lore.kernel.org/r/20230330104526.3196-1-rui.zhang@intel.com --- include/linux/thermal.h | 38 -------------------------------------- 1 file changed, 38 deletions(-) (limited to 'include/linux') diff --git a/include/linux/thermal.h b/include/linux/thermal.h index fef625f799ae..ab7460bfdcf6 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -207,41 +207,6 @@ struct thermal_governor { struct list_head governor_list; }; -/* Structure that holds binding parameters for a zone */ -struct thermal_bind_params { - struct thermal_cooling_device *cdev; - - /* - * This is a measure of 'how effectively these devices can - * cool 'this' thermal zone. It shall be determined by - * platform characterization. This value is relative to the - * rest of the weights so a cooling device whose weight is - * double that of another cooling device is twice as - * effective. See Documentation/driver-api/thermal/sysfs-api.rst for more - * information. - */ - int weight; - - /* - * This is a bit mask that gives the binding relation between this - * thermal zone and cdev, for a particular trip point. - * See Documentation/driver-api/thermal/sysfs-api.rst for more information. - */ - int trip_mask; - - /* - * This is an array of cooling state limits. Must have exactly - * 2 * thermal_zone.number_of_trip_points. It is an array consisting - * of tuples of state limits. Each trip - * will be associated with one state limit tuple when binding. - * A NULL pointer means - * on all trips. - */ - unsigned long *binding_limits; - int (*match) (struct thermal_zone_device *tz, - struct thermal_cooling_device *cdev); -}; - /* Structure to define Thermal Zone parameters */ struct thermal_zone_params { char governor_name[THERMAL_NAME_LENGTH]; @@ -253,9 +218,6 @@ struct thermal_zone_params { */ bool no_hwmon; - int num_tbps; /* Number of tbp entries */ - struct thermal_bind_params *tbp; - /* * Sustainable power (heat) that this thermal zone can dissipate in * mW -- cgit v1.2.3 From a038895e25b296ca1ef0254f92673ea64bc1a2ee Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Tue, 4 Apr 2023 05:09:10 +0530 Subject: cpufreq: drivers with target_index() must set freq_table Since the cpufreq core directly uses freq_table, for cpufreq drivers that set their target_index() callback, make it mandatory for them to set the same. Since this is set per policy and normally from policy->init(), do this from cpufreq_table_validate_and_sort() which gets called right after ->init(). Reported-by: Yajun Deng Signed-off-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- include/linux/cpufreq.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 65623233ab2f..541013487a0e 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -237,6 +237,7 @@ bool cpufreq_supports_freq_invariance(void); struct kobject *get_governor_parent_kobj(struct cpufreq_policy *policy); void cpufreq_enable_fast_switch(struct cpufreq_policy *policy); void cpufreq_disable_fast_switch(struct cpufreq_policy *policy); +bool has_target_index(void); #else static inline unsigned int cpufreq_get(unsigned int cpu) { -- cgit v1.2.3 From d8cc9415a40f479b666fc03e7b1f4601868e6dc8 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Thu, 6 Apr 2023 22:29:56 +0200 Subject: hwmon: constify pointers to hwmon_channel_info HWmon core receives an array of pointers to hwmon_channel_info and it does not modify it, thus it can be array of const pointers for safety. This allows drivers to make them also const. Signed-off-by: Krzysztof Kozlowski Signed-off-by: Guenter Roeck --- include/linux/hwmon.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/hwmon.h b/include/linux/hwmon.h index c1b62384b6ee..492dd27a5dd8 100644 --- a/include/linux/hwmon.h +++ b/include/linux/hwmon.h @@ -430,7 +430,7 @@ struct hwmon_channel_info { */ struct hwmon_chip_info { const struct hwmon_ops *ops; - const struct hwmon_channel_info **info; + const struct hwmon_channel_info * const *info; }; /* hwmon_device_register() is deprecated */ -- cgit v1.2.3 From 4a670ac3e75e517c96cbd01ef870dbd598c3ce71 Mon Sep 17 00:00:00 2001 From: Maxime Chevallier Date: Fri, 7 Apr 2023 17:26:04 +0200 Subject: regmap: allow upshifting register addresses before performing operations Similar to the existing reg_downshift mechanism, that is used to translate register addresses on busses that have a smaller address stride, it's also possible to want to upshift register addresses. Such a case was encountered when network PHYs and PCS that usually sit on a MDIO bus (16-bits register with a stride of 1) are integrated directly as memory-mapped devices. Here, the same register layout defined in 802.3 is used, but the register now have a larger stride. Introduce a mechanism to also allow upshifting register addresses. Re-purpose reg_downshift into a more generic, signed reg_shift, whose sign indicates the direction of the shift. To avoid confusion, also introduce macros to explicitly indicate if we want to downshift or upshift. For bisectability, change any use of reg_downshift to use reg_shift. Signed-off-by: Maxime Chevallier Tested-by: Colin Foster Link: https://lore.kernel.org/r/20230407152604.105467-1-maxime.chevallier@bootlin.com Signed-off-by: Mark Brown --- include/linux/regmap.h | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 8743b177399e..c2b9cc5db824 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -46,6 +46,14 @@ struct sdw_slave; #define REGMAP_MDIO_C45_DEVAD_MASK GENMASK(20, 16) #define REGMAP_MDIO_C45_REGNUM_MASK GENMASK(15, 0) +/* + * regmap.reg_shift indicates by how much we must shift registers prior to + * performing any operation. It's a signed value, positive numbers means + * downshifting the register's address, while negative numbers means upshifting. + */ +#define REGMAP_UPSHIFT(s) (-(s)) +#define REGMAP_DOWNSHIFT(s) (s) + /* An enum of all the supported cache types */ enum regcache_type { REGCACHE_NONE, @@ -246,8 +254,9 @@ typedef void (*regmap_unlock)(void *); * @reg_stride: The register address stride. Valid register addresses are a * multiple of this value. If set to 0, a value of 1 will be * used. - * @reg_downshift: The number of bits to downshift the register before - * performing any operations. + * @reg_shift: The number of bits to shift the register before performing any + * operations. Any positive number will be downshifted, and negative + * values will be upshifted * @reg_base: Value to be added to every register address before performing any * operation. * @pad_bits: Number of bits of padding between register and value. @@ -381,7 +390,7 @@ struct regmap_config { int reg_bits; int reg_stride; - int reg_downshift; + int reg_shift; unsigned int reg_base; int pad_bits; int val_bits; -- cgit v1.2.3 From ac614a9b4c35bf766dec40d73cbbc7f37c1734f7 Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Tue, 4 Apr 2023 09:51:36 +0200 Subject: thermal/of: Unexport unused OF functions The functions thermal_of_zone_register() and thermal_of_zone_unregister() are no longer needed from the drivers as the devm_ variant is always used. Make them static in the C file and remove their declaration from thermal.h Signed-off-by: Daniel Lezcano Link: https://lore.kernel.org/r/20230404075138.2914680-2-daniel.lezcano@linaro.org --- include/linux/thermal.h | 17 ----------------- 1 file changed, 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/thermal.h b/include/linux/thermal.h index ab7460bfdcf6..82ddb32f9876 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -259,25 +259,12 @@ struct thermal_zone_params { /* Function declarations */ #ifdef CONFIG_THERMAL_OF -struct thermal_zone_device *thermal_of_zone_register(struct device_node *sensor, int id, void *data, - const struct thermal_zone_device_ops *ops); - struct thermal_zone_device *devm_thermal_of_zone_register(struct device *dev, int id, void *data, const struct thermal_zone_device_ops *ops); -void thermal_of_zone_unregister(struct thermal_zone_device *tz); - void devm_thermal_of_zone_unregister(struct device *dev, struct thermal_zone_device *tz); -void thermal_of_zone_unregister(struct thermal_zone_device *tz); - #else -static inline -struct thermal_zone_device *thermal_of_zone_register(struct device_node *sensor, int id, void *data, - const struct thermal_zone_device_ops *ops) -{ - return ERR_PTR(-ENOTSUPP); -} static inline struct thermal_zone_device *devm_thermal_of_zone_register(struct device *dev, int id, void *data, @@ -286,10 +273,6 @@ struct thermal_zone_device *devm_thermal_of_zone_register(struct device *dev, in return ERR_PTR(-ENOTSUPP); } -static inline void thermal_of_zone_unregister(struct thermal_zone_device *tz) -{ -} - static inline void devm_thermal_of_zone_unregister(struct device *dev, struct thermal_zone_device *tz) { -- cgit v1.2.3 From dee234032e767b3d6823fe122517770757306f04 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Wed, 15 Mar 2023 13:02:18 +0000 Subject: irqchip/gic: Drop support for board files With the last non-OF, non-ACPI user of the GIC being removed in e73307b9ebc4 ("ARM: cns3xxx: remove entire platform"), we can finally drop the entry point and do some minor cleanup. We also make the driver depend on CONFIG_OF, which is required even when CONFIG_ACPI is selected. Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20230315130218.3212033-1-maz@kernel.org --- include/linux/irqchip/arm-gic.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irqchip/arm-gic.h b/include/linux/irqchip/arm-gic.h index 5686711b0f40..2223f95079ce 100644 --- a/include/linux/irqchip/arm-gic.h +++ b/include/linux/irqchip/arm-gic.h @@ -151,12 +151,6 @@ int gic_of_init(struct device_node *node, struct device_node *parent); */ int gic_of_init_child(struct device *dev, struct gic_chip_data **gic, int irq); -/* - * Legacy platforms not converted to DT yet must use this to init - * their GIC - */ -void gic_init(void __iomem *dist , void __iomem *cpu); - void gic_send_sgi(unsigned int cpu_id, unsigned int irq); int gic_get_cpu_id(unsigned int cpu); void gic_migrate_target(unsigned int new_cpu_id); -- cgit v1.2.3 From 35727af2b15d98a2dd2811d631d3a3886111312e Mon Sep 17 00:00:00 2001 From: Shanker Donthineni Date: Sat, 18 Mar 2023 21:43:14 -0500 Subject: irqchip/gicv3: Workaround for NVIDIA erratum T241-FABRIC-4 The T241 platform suffers from the T241-FABRIC-4 erratum which causes unexpected behavior in the GIC when multiple transactions are received simultaneously from different sources. This hardware issue impacts NVIDIA server platforms that use more than two T241 chips interconnected. Each chip has support for 320 {E}SPIs. This issue occurs when multiple packets from different GICs are incorrectly interleaved at the target chip. The erratum text below specifies exactly what can cause multiple transfer packets susceptible to interleaving and GIC state corruption. GIC state corruption can lead to a range of problems, including kernel panics, and unexpected behavior. >From the erratum text: "In some cases, inter-socket AXI4 Stream packets with multiple transfers, may be interleaved by the fabric when presented to ARM Generic Interrupt Controller. GIC expects all transfers of a packet to be delivered without any interleaving. The following GICv3 commands may result in multiple transfer packets over inter-socket AXI4 Stream interface: - Register reads from GICD_I* and GICD_N* - Register writes to 64-bit GICD registers other than GICD_IROUTERn* - ITS command MOVALL Multiple commands in GICv4+ utilize multiple transfer packets, including VMOVP, VMOVI, VMAPP, and 64-bit register accesses." This issue impacts system configurations with more than 2 sockets, that require multi-transfer packets to be sent over inter-socket AXI4 Stream interface between GIC instances on different sockets. GICv4 cannot be supported. GICv3 SW model can only be supported with the workaround. Single and Dual socket configurations are not impacted by this issue and support GICv3 and GICv4." Link: https://developer.nvidia.com/docs/t241-fabric-4/nvidia-t241-fabric-4-errata.pdf Writing to the chip alias region of the GICD_In{E} registers except GICD_ICENABLERn has an equivalent effect as writing to the global distributor. The SPI interrupt deactivate path is not impacted by the erratum. To fix this problem, implement a workaround that ensures read accesses to the GICD_In{E} registers are directed to the chip that owns the SPI, and disable GICv4.x features. To simplify code changes, the gic_configure_irq() function uses the same alias region for both read and write operations to GICD_ICFGR. Co-developed-by: Vikram Sethi Signed-off-by: Vikram Sethi Signed-off-by: Shanker Donthineni Acked-by: Sudeep Holla (for SMCCC/SOC ID bits) Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20230319024314.3540573-2-sdonthineni@nvidia.com --- include/linux/arm-smccc.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include/linux') diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h index 220c8c60e021..f196c19f8e55 100644 --- a/include/linux/arm-smccc.h +++ b/include/linux/arm-smccc.h @@ -226,6 +226,24 @@ void __init arm_smccc_version_init(u32 version, enum arm_smccc_conduit conduit); extern u64 smccc_has_sve_hint; +/** + * arm_smccc_get_soc_id_version() + * + * Returns the SOC ID version. + * + * When ARM_SMCCC_ARCH_SOC_ID is not present, returns SMCCC_RET_NOT_SUPPORTED. + */ +s32 arm_smccc_get_soc_id_version(void); + +/** + * arm_smccc_get_soc_id_revision() + * + * Returns the SOC ID revision. + * + * When ARM_SMCCC_ARCH_SOC_ID is not present, returns SMCCC_RET_NOT_SUPPORTED. + */ +s32 arm_smccc_get_soc_id_revision(void); + /** * struct arm_smccc_res - Result from SMC/HVC call * @a0-a3 result values from registers 0 to 3 -- cgit v1.2.3 From 890a3ee3ce416e2f1aed41718a8c1d42c82cf1b2 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Thu, 23 Mar 2023 17:50:29 +0200 Subject: kernel.h: split the hexadecimal related helpers to hex.h For the sake of cleaning up the kernel.h split the hexadecimal related helpers to own header called 'hex.h'. Link: https://lkml.kernel.org/r/20230323155029.40000-1-andriy.shevchenko@linux.intel.com Signed-off-by: Andy Shevchenko Cc: Rasmus Villemoes Signed-off-by: Andrew Morton --- include/linux/hex.h | 35 +++++++++++++++++++++++++++++++++++ include/linux/kernel.h | 29 +---------------------------- 2 files changed, 36 insertions(+), 28 deletions(-) create mode 100644 include/linux/hex.h (limited to 'include/linux') diff --git a/include/linux/hex.h b/include/linux/hex.h new file mode 100644 index 000000000000..2618382e5b0c --- /dev/null +++ b/include/linux/hex.h @@ -0,0 +1,35 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_HEX_H +#define _LINUX_HEX_H + +#include + +extern const char hex_asc[]; +#define hex_asc_lo(x) hex_asc[((x) & 0x0f)] +#define hex_asc_hi(x) hex_asc[((x) & 0xf0) >> 4] + +static inline char *hex_byte_pack(char *buf, u8 byte) +{ + *buf++ = hex_asc_hi(byte); + *buf++ = hex_asc_lo(byte); + return buf; +} + +extern const char hex_asc_upper[]; +#define hex_asc_upper_lo(x) hex_asc_upper[((x) & 0x0f)] +#define hex_asc_upper_hi(x) hex_asc_upper[((x) & 0xf0) >> 4] + +static inline char *hex_byte_pack_upper(char *buf, u8 byte) +{ + *buf++ = hex_asc_upper_hi(byte); + *buf++ = hex_asc_upper_lo(byte); + return buf; +} + +extern int hex_to_bin(unsigned char ch); +extern int __must_check hex2bin(u8 *dst, const char *src, size_t count); +extern char *bin2hex(char *dst, const void *src, size_t count); + +bool mac_pton(const char *s, u8 *mac); + +#endif diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 40bce7495af8..0d91e0af0125 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -20,6 +20,7 @@ #include #include #include +#include #include #include #include @@ -263,34 +264,6 @@ extern enum system_states { SYSTEM_SUSPEND, } system_state; -extern const char hex_asc[]; -#define hex_asc_lo(x) hex_asc[((x) & 0x0f)] -#define hex_asc_hi(x) hex_asc[((x) & 0xf0) >> 4] - -static inline char *hex_byte_pack(char *buf, u8 byte) -{ - *buf++ = hex_asc_hi(byte); - *buf++ = hex_asc_lo(byte); - return buf; -} - -extern const char hex_asc_upper[]; -#define hex_asc_upper_lo(x) hex_asc_upper[((x) & 0x0f)] -#define hex_asc_upper_hi(x) hex_asc_upper[((x) & 0xf0) >> 4] - -static inline char *hex_byte_pack_upper(char *buf, u8 byte) -{ - *buf++ = hex_asc_upper_hi(byte); - *buf++ = hex_asc_upper_lo(byte); - return buf; -} - -extern int hex_to_bin(unsigned char ch); -extern int __must_check hex2bin(u8 *dst, const char *src, size_t count); -extern char *bin2hex(char *dst, const void *src, size_t count); - -bool mac_pton(const char *s, u8 *mac); - /* * General tracing related utility functions - trace_printk(), * tracing_on/tracing_off and tracing_start()/tracing_stop -- cgit v1.2.3 From 7982722ff7286596a1e2f343ec4219e309ddc82a Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Tue, 7 Mar 2023 16:44:15 -0600 Subject: x86/kexec: remove unnecessary arch_kexec_kernel_image_load() Patch series "kexec: Remove unnecessary arch hook", v2. There are no arch-specific things in arch_kexec_kernel_image_load(), so remove it and just use the generic version. This patch (of 2): The x86 implementation of arch_kexec_kernel_image_load() is functionally identical to the generic arch_kexec_kernel_image_load(): arch_kexec_kernel_image_load # x86 if (!image->fops || !image->fops->load) return ERR_PTR(-ENOEXEC); return image->fops->load(image, image->kernel_buf, ...) arch_kexec_kernel_image_load # generic kexec_image_load_default if (!image->fops || !image->fops->load) return ERR_PTR(-ENOEXEC); return image->fops->load(image, image->kernel_buf, ...) Remove the x86-specific version and use the generic arch_kexec_kernel_image_load(). No functional change intended. Link: https://lkml.kernel.org/r/20230307224416.907040-1-helgaas@kernel.org Link: https://lkml.kernel.org/r/20230307224416.907040-2-helgaas@kernel.org Signed-off-by: Bjorn Helgaas Reviewed-by: Simon Horman Acked-by: Baoquan He Cc: Borislav Petkov (AMD) Cc: Dave Hansen Cc: Eric Biederman Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Thomas Gleixner Signed-off-by: Andrew Morton --- include/linux/kexec.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kexec.h b/include/linux/kexec.h index 6883c5922701..4746bc9d39c9 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -207,12 +207,10 @@ static inline int arch_kimage_file_post_load_cleanup(struct kimage *image) } #endif -#ifndef arch_kexec_kernel_image_load static inline void *arch_kexec_kernel_image_load(struct kimage *image) { return kexec_image_load_default(image); } -#endif #ifdef CONFIG_KEXEC_SIG #ifdef CONFIG_SIGNED_PE_FILE_VERIFICATION -- cgit v1.2.3 From fb15abdca64503511bb32cb6ff70da306f24fa06 Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Tue, 7 Mar 2023 16:44:16 -0600 Subject: kexec: remove unnecessary arch_kexec_kernel_image_load() arch_kexec_kernel_image_load() only calls kexec_image_load_default(), and there are no arch-specific implementations. Remove the unnecessary arch_kexec_kernel_image_load() and make kexec_image_load_default() static. No functional change intended. Link: https://lkml.kernel.org/r/20230307224416.907040-3-helgaas@kernel.org Signed-off-by: Bjorn Helgaas Reviewed-by: Simon Horman Acked-by: Baoquan He Cc: Borislav Petkov (AMD) Cc: Dave Hansen Cc: Eric Biederman Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Thomas Gleixner Signed-off-by: Andrew Morton --- include/linux/kexec.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kexec.h b/include/linux/kexec.h index 4746bc9d39c9..22b5cd24f581 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -190,7 +190,6 @@ int kexec_purgatory_get_set_symbol(struct kimage *image, const char *name, void *buf, unsigned int size, bool get_value); void *kexec_purgatory_get_symbol_addr(struct kimage *image, const char *name); -void *kexec_image_load_default(struct kimage *image); #ifndef arch_kexec_kernel_image_probe static inline int @@ -207,11 +206,6 @@ static inline int arch_kimage_file_post_load_cleanup(struct kimage *image) } #endif -static inline void *arch_kexec_kernel_image_load(struct kimage *image) -{ - return kexec_image_load_default(image); -} - #ifdef CONFIG_KEXEC_SIG #ifdef CONFIG_SIGNED_PE_FILE_VERIFICATION int kexec_kernel_verify_pe_sig(const char *kernel, unsigned long kernel_len); -- cgit v1.2.3 From 5a17818682cf43ad0fdd6035945f3b7a8c9dc5e9 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Thu, 6 Apr 2023 14:42:46 +0300 Subject: net: dsa: replace NETDEV_PRE_CHANGE_HWTSTAMP notifier with a stub There was a sort of rush surrounding commit 88c0a6b503b7 ("net: create a netdev notifier for DSA to reject PTP on DSA master"), due to a desire to convert DSA's attempt to deny TX timestamping on a DSA master to something that doesn't block the kernel-wide API conversion from ndo_eth_ioctl() to ndo_hwtstamp_set(). What was required was a mechanism that did not depend on ndo_eth_ioctl(), and what was provided was a mechanism that did not depend on ndo_eth_ioctl(), while at the same time introducing something that wasn't absolutely necessary - a new netdev notifier. There have been objections from Jakub Kicinski that using notifiers in general when they are not absolutely necessary creates complications to the control flow and difficulties to maintainers who look at the code. So there is a desire to not use notifiers. In addition to that, the notifier chain gets called even if there is no DSA in the system and no one is interested in applying any restriction. Take the model of udp_tunnel_nic_ops and introduce a stub mechanism, through which net/core/dev_ioctl.c can call into DSA even when CONFIG_NET_DSA=m. Compared to the code that existed prior to the notifier conversion, aka what was added in commits: - 4cfab3566710 ("net: dsa: Add wrappers for overloaded ndo_ops") - 3369afba1e46 ("net: Call into DSA netdevice_ops wrappers") this is different because we are not overloading any struct net_device_ops of the DSA master anymore, but rather, we are exposing a rather specific functionality which is orthogonal to which API is used to enable it - ndo_eth_ioctl() or ndo_hwtstamp_set(). Also, what is similar is that both approaches use function pointers to get from built-in code to DSA. There is no point in replicating the function pointers towards __dsa_master_hwtstamp_validate() once for every CPU port (dev->dsa_ptr). Instead, it is sufficient to introduce a singleton struct dsa_stubs, built into the kernel, which contains a single function pointer to __dsa_master_hwtstamp_validate(). I find this approach preferable to what we had originally, because dev->dsa_ptr->netdev_ops->ndo_do_ioctl() used to require going through struct dsa_port (dev->dsa_ptr), and so, this was incompatible with any attempts to add any data encapsulation and hide DSA data structures from the outside world. Link: https://lore.kernel.org/netdev/20230403083019.120b72fd@kernel.org/ Signed-off-by: Vladimir Oltean Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/netdevice.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index a740be3bb911..1c25b39681b3 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2878,7 +2878,6 @@ enum netdev_cmd { NETDEV_OFFLOAD_XSTATS_REPORT_USED, NETDEV_OFFLOAD_XSTATS_REPORT_DELTA, NETDEV_XDP_FEAT_CHANGE, - NETDEV_PRE_CHANGE_HWTSTAMP, }; const char *netdev_cmd_to_name(enum netdev_cmd cmd); @@ -2929,11 +2928,6 @@ struct netdev_notifier_pre_changeaddr_info { const unsigned char *dev_addr; }; -struct netdev_notifier_hwtstamp_info { - struct netdev_notifier_info info; /* must be first */ - struct kernel_hwtstamp_config *config; -}; - enum netdev_offload_xstats_type { NETDEV_OFFLOAD_XSTATS_TYPE_L3 = 1, }; -- cgit v1.2.3 From 38416c28e16890b52fdd5eb73479299ec3f062f3 Mon Sep 17 00:00:00 2001 From: Matti Vaittinen Date: Fri, 31 Mar 2023 15:40:28 +0300 Subject: iio: light: Add gain-time-scale helpers Some light sensors can adjust both the HW-gain and integration time. There are cases where adjusting the integration time has similar impact to the scale of the reported values as gain setting has. IIO users do typically expect to handle scale by a single writable 'scale' entry. Driver should then adjust the gain/time accordingly. It however is difficult for a driver to know whether it should change gain or integration time to meet the requested scale. Usually it is preferred to have longer integration time which usually improves accuracy, but there may be use-cases where long measurement times can be an issue. Thus it can be preferable to allow also changing the integration time - but mitigate the scale impact by also changing the gain underneath. Eg, if integration time change doubles the measured values, the driver can reduce the HW-gain to half. The theory of the computations of gain-time-scale is simple. However, some people (undersigned) got that implemented wrong for more than once. Add some gain-time-scale helpers in order to not dublicate errors in all drivers needing these computations. Signed-off-by: Matti Vaittinen Link: https://lore.kernel.org/r/268d418e7cffcdaa2ece6738478bbc57692c213e.1680263956.git.mazziesaccount@gmail.com Signed-off-by: Jonathan Cameron --- include/linux/iio/iio-gts-helper.h | 206 +++++++++++++++++++++++++++++++++++++ 1 file changed, 206 insertions(+) create mode 100644 include/linux/iio/iio-gts-helper.h (limited to 'include/linux') diff --git a/include/linux/iio/iio-gts-helper.h b/include/linux/iio/iio-gts-helper.h new file mode 100644 index 000000000000..dd64e544a3da --- /dev/null +++ b/include/linux/iio/iio-gts-helper.h @@ -0,0 +1,206 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* gain-time-scale conversion helpers for IIO light sensors + * + * Copyright (c) 2023 Matti Vaittinen + */ + +#ifndef __IIO_GTS_HELPER__ +#define __IIO_GTS_HELPER__ + +#include + +struct device; + +/** + * struct iio_gain_sel_pair - gain - selector values + * + * In many cases devices like light sensors allow setting signal amplification + * (gain) using a register interface. This structure describes amplification + * and corresponding selector (register value) + * + * @gain: Gain (multiplication) value. Gain must be positive, negative + * values are reserved for error handling. + * @sel: Selector (usually register value) used to indicate this gain. + * NOTE: Only selectors >= 0 supported. + */ +struct iio_gain_sel_pair { + int gain; + int sel; +}; + +/** + * struct iio_itime_sel_mul - integration time description + * + * In many cases devices like light sensors allow setting the duration of + * collecting data. Typically this duration has also an impact to the magnitude + * of measured values (gain). This structure describes the relation of + * integration time and amplification as well as corresponding selector + * (register value). + * + * An example could be a sensor allowing 50, 100, 200 and 400 mS times. The + * respective multiplication values could be 50 mS => 1, 100 mS => 2, + * 200 mS => 4 and 400 mS => 8 assuming the impact of integration time would be + * linear in a way that when collecting data for 50 mS caused value X, doubling + * the data collection time caused value 2X etc. + * + * @time_us: Integration time in microseconds. Time values must be positive, + * negative values are reserved for error handling. + * @sel: Selector (usually register value) used to indicate this time + * NOTE: Only selectors >= 0 supported. + * @mul: Multiplication to the values caused by this time. + * NOTE: Only multipliers > 0 supported. + */ +struct iio_itime_sel_mul { + int time_us; + int sel; + int mul; +}; + +struct iio_gts { + u64 max_scale; + const struct iio_gain_sel_pair *hwgain_table; + int num_hwgain; + const struct iio_itime_sel_mul *itime_table; + int num_itime; + int **per_time_avail_scale_tables; + int *avail_all_scales_table; + int num_avail_all_scales; + int *avail_time_tables; + int num_avail_time_tables; +}; + +#define GAIN_SCALE_GAIN(_gain, _sel) \ +{ \ + .gain = (_gain), \ + .sel = (_sel), \ +} + +#define GAIN_SCALE_ITIME_US(_itime, _sel, _mul) \ +{ \ + .time_us = (_itime), \ + .sel = (_sel), \ + .mul = (_mul), \ +} + +static inline const struct iio_itime_sel_mul * +iio_gts_find_itime_by_time(struct iio_gts *gts, int time) +{ + int i; + + if (!gts->num_itime) + return NULL; + + for (i = 0; i < gts->num_itime; i++) + if (gts->itime_table[i].time_us == time) + return >s->itime_table[i]; + + return NULL; +} + +static inline const struct iio_itime_sel_mul * +iio_gts_find_itime_by_sel(struct iio_gts *gts, int sel) +{ + int i; + + for (i = 0; i < gts->num_itime; i++) + if (gts->itime_table[i].sel == sel) + return >s->itime_table[i]; + + return NULL; +} + +int devm_iio_init_iio_gts(struct device *dev, int max_scale_int, int max_scale_nano, + const struct iio_gain_sel_pair *gain_tbl, int num_gain, + const struct iio_itime_sel_mul *tim_tbl, int num_times, + struct iio_gts *gts); +/** + * iio_gts_find_int_time_by_sel - find integration time matching a selector + * @gts: Gain time scale descriptor + * @sel: selector for which matching integration time is searched for + * + * Return: integration time matching given selector or -EINVAL if + * integration time was not found. + */ +static inline int iio_gts_find_int_time_by_sel(struct iio_gts *gts, int sel) +{ + const struct iio_itime_sel_mul *itime; + + itime = iio_gts_find_itime_by_sel(gts, sel); + if (!itime) + return -EINVAL; + + return itime->time_us; +} + +/** + * iio_gts_find_sel_by_int_time - find selector matching integration time + * @gts: Gain time scale descriptor + * @gain: HW-gain for which matching selector is searched for + * + * Return: a selector matching given integration time or -EINVAL if + * selector was not found. + */ +static inline int iio_gts_find_sel_by_int_time(struct iio_gts *gts, int time) +{ + const struct iio_itime_sel_mul *itime; + + itime = iio_gts_find_itime_by_time(gts, time); + if (!itime) + return -EINVAL; + + return itime->sel; +} + +/** + * iio_gts_valid_time - check if given integration time is valid + * @gts: Gain time scale descriptor + * @time_us: Integration time to check + * + * Return: True if given time is supported by device. False if not. + */ +static inline bool iio_gts_valid_time(struct iio_gts *gts, int time_us) +{ + return iio_gts_find_itime_by_time(gts, time_us) != NULL; +} + +int iio_gts_find_sel_by_gain(struct iio_gts *gts, int gain); + +/** + * iio_gts_valid_gain - check if given HW-gain is valid + * @gts: Gain time scale descriptor + * @gain: HW-gain to check + * + * Return: True if given time is supported by device. False if not. + */ +static inline bool iio_gts_valid_gain(struct iio_gts *gts, int gain) +{ + return iio_gts_find_sel_by_gain(gts, gain) >= 0; +} + +int iio_find_closest_gain_low(struct iio_gts *gts, int gain, bool *in_range); +int iio_gts_find_gain_by_sel(struct iio_gts *gts, int sel); +int iio_gts_get_min_gain(struct iio_gts *gts); +int iio_gts_find_int_time_by_sel(struct iio_gts *gts, int sel); +int iio_gts_find_sel_by_int_time(struct iio_gts *gts, int time); + +int iio_gts_total_gain_to_scale(struct iio_gts *gts, int total_gain, + int *scale_int, int *scale_nano); +int iio_gts_find_gain_sel_for_scale_using_time(struct iio_gts *gts, int time_sel, + int scale_int, int scale_nano, + int *gain_sel); +int iio_gts_get_scale(struct iio_gts *gts, int gain, int time, int *scale_int, + int *scale_nano); +int iio_gts_find_new_gain_sel_by_old_gain_time(struct iio_gts *gts, + int old_gain, int old_time_sel, + int new_time_sel, int *new_gain); +int iio_gts_find_new_gain_by_old_gain_time(struct iio_gts *gts, int old_gain, + int old_time, int new_time, + int *new_gain); +int iio_gts_avail_times(struct iio_gts *gts, const int **vals, int *type, + int *length); +int iio_gts_all_avail_scales(struct iio_gts *gts, const int **vals, int *type, + int *length); +int iio_gts_avail_scales_for_time(struct iio_gts *gts, int time, + const int **vals, int *type, int *length); + +#endif -- cgit v1.2.3 From 0c9f4521958ff52b74967c8a39a8b5747ba8df41 Mon Sep 17 00:00:00 2001 From: Weizhao Ouyang Date: Tue, 4 Apr 2023 11:28:44 +0800 Subject: f2fs: use common implementation of file type Use common implementation of file type conversion helpers. Signed-off-by: Weizhao Ouyang Reviewed-by: Chao Yu Signed-off-by: Jaegeuk Kim --- include/linux/f2fs_fs.h | 15 --------------- 1 file changed, 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h index 881eb9321967..1d6402529d10 100644 --- a/include/linux/f2fs_fs.h +++ b/include/linux/f2fs_fs.h @@ -584,21 +584,6 @@ struct f2fs_dentry_block { __u8 filename[NR_DENTRY_IN_BLOCK][F2FS_SLOT_LEN]; } __packed; -/* file types used in inode_info->flags */ -enum { - F2FS_FT_UNKNOWN, - F2FS_FT_REG_FILE, - F2FS_FT_DIR, - F2FS_FT_CHRDEV, - F2FS_FT_BLKDEV, - F2FS_FT_FIFO, - F2FS_FT_SOCK, - F2FS_FT_SYMLINK, - F2FS_FT_MAX -}; - -#define S_SHIFT 12 - #define F2FS_DEF_PROJID 0 /* default project ID */ #endif /* _LINUX_F2FS_FS_H */ -- cgit v1.2.3 From 1dd5474ee6ee1d6ddc95f1423966ab8d4afda448 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Wed, 29 Mar 2023 10:51:58 -0500 Subject: of: Make devtree_lock declaration private Sparc is the only place devtree_lock is used outside of drivers/of/. Move the devtree_lock declaration into of_private.h and Sparc's prom.h so pulling in spinlock.h to of.h can be avoided for everything besides Sparc. Link: https://lore.kernel.org/r/20230329-dt-cpu-header-cleanups-v1-1-581e2605fe47@kernel.org Signed-off-by: Rob Herring --- include/linux/of.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/of.h b/include/linux/of.h index 0af611307db2..36cf94596eba 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -16,7 +16,6 @@ #include #include #include -#include #include #include #include @@ -145,7 +144,6 @@ extern struct device_node *of_root; extern struct device_node *of_chosen; extern struct device_node *of_aliases; extern struct device_node *of_stdout; -extern raw_spinlock_t devtree_lock; /* * struct device_node flag descriptions -- cgit v1.2.3 From 4c32fb7dcf65b16cc7b2837ccfc35d00be92bddb Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Wed, 29 Mar 2023 10:51:59 -0500 Subject: of: Move of_device_(add|register|unregister) to of_platform.h As of_device_(add|register|unregister) functions work on struct platform_device, they should be declared in of_platform.h instead. This move is transparent for now as both headers include each other. Link: https://lore.kernel.org/r/20230329-dt-cpu-header-cleanups-v1-2-581e2605fe47@kernel.org Signed-off-by: Rob Herring --- include/linux/of_device.h | 4 ---- include/linux/of_platform.h | 5 +++++ 2 files changed, 5 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/of_device.h b/include/linux/of_device.h index f4b57614979d..e4aa61cb2bd0 100644 --- a/include/linux/of_device.h +++ b/include/linux/of_device.h @@ -26,10 +26,6 @@ static inline int of_driver_match_device(struct device *dev, return of_match_device(drv->of_match_table, dev) != NULL; } -extern int of_device_add(struct platform_device *pdev); -extern int of_device_register(struct platform_device *ofdev); -extern void of_device_unregister(struct platform_device *ofdev); - extern const void *of_device_get_match_data(const struct device *dev); extern ssize_t of_device_modalias(struct device *dev, char *str, ssize_t len); diff --git a/include/linux/of_platform.h b/include/linux/of_platform.h index d15b6cd5e1c3..8ac5cb933dc3 100644 --- a/include/linux/of_platform.h +++ b/include/linux/of_platform.h @@ -52,6 +52,11 @@ extern const struct of_device_id of_default_bus_match_table[]; extern struct platform_device *of_device_alloc(struct device_node *np, const char *bus_id, struct device *parent); + +extern int of_device_add(struct platform_device *pdev); +extern int of_device_register(struct platform_device *ofdev); +extern void of_device_unregister(struct platform_device *ofdev); + #ifdef CONFIG_OF extern struct platform_device *of_find_device_by_node(struct device_node *np); #else -- cgit v1.2.3 From c91c46de6bbc1147ae5dfe046b87f5f3d6593215 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Thu, 6 Apr 2023 18:25:33 -0700 Subject: net: provide macros for commonly copied lockless queue stop/wake code A lot of drivers follow the same scheme to stop / start queues without introducing locks between xmit and NAPI tx completions. I'm guessing they all copy'n'paste each other's code. The original code dates back all the way to e1000 and Linux 2.6.19. Smaller drivers shy away from the scheme and introduce a lock which may cause deadlocks in netpoll. Provide macros which encapsulate the necessary logic. The macros do not prevent false wake ups, the extra barrier required to close that race is not worth it. See discussion in: https://lore.kernel.org/all/c39312a2-4537-14b4-270c-9fe1fbb91e89@gmail.com/ Acked-by: Herbert Xu Signed-off-by: Jakub Kicinski --- include/linux/netdevice.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 1c25b39681b3..7bec9a2be8ef 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3335,6 +3335,7 @@ static inline void netif_tx_wake_all_queues(struct net_device *dev) static __always_inline void netif_tx_stop_queue(struct netdev_queue *dev_queue) { + /* Must be an atomic op see netif_txq_try_stop() */ set_bit(__QUEUE_STATE_DRV_XOFF, &dev_queue->state); } -- cgit v1.2.3 From 301f227fc860624d37ba5dae9da57dcf371268db Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Thu, 6 Apr 2023 18:25:36 -0700 Subject: net: piggy back on the memory barrier in bql when waking queues Drivers call netdev_tx_completed_queue() right before netif_txq_maybe_wake(). If BQL is enabled netdev_tx_completed_queue() should issue a memory barrier, so we can depend on that separating the stop check from the consumer index update, instead of adding another barrier in netif_txq_maybe_wake(). This matters more than the barriers on the xmit path, because the wake condition is almost always true. So we issue the consumer side barrier often. Wrap netdev_tx_completed_queue() in a local helper to issue the barrier even if BQL is disabled. Keep the same semantics as netdev_tx_completed_queue() (barrier only if bytes != 0) to make it clear that the barrier is conditional. Plus since macro gets pkt/byte counts as arguments now - we can skip waking if there were no packets completed. Signed-off-by: Jakub Kicinski --- include/linux/netdevice.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 7bec9a2be8ef..fe355592dfde 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3532,7 +3532,7 @@ static inline void netdev_tx_completed_queue(struct netdev_queue *dev_queue, * netdev_tx_sent_queue will miss the update and cause the queue to * be stopped forever */ - smp_mb(); + smp_mb(); /* NOTE: netdev_txq_completed_mb() assumes this exists */ if (unlikely(dql_avail(&dev_queue->dql) < 0)) return; -- cgit v1.2.3 From 4294a0a7ab6282c3d92f03de84e762dda993c93d Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Thu, 6 Apr 2023 16:41:47 -0700 Subject: bpf: Split off basic BPF verifier log into separate file kernel/bpf/verifier.c file is large and growing larger all the time. So it's good to start splitting off more or less self-contained parts into separate files to keep source code size (somewhat) somewhat under control. This patch is a one step in this direction, moving some of BPF verifier log routines into a separate kernel/bpf/log.c. Right now it's most low-level and isolated routines to append data to log, reset log to previous position, etc. Eventually we could probably move verifier state printing logic here as well, but this patch doesn't attempt to do that yet. Subsequent patches will add more logic to verifier log management, so having basics in a separate file will make sure verifier.c doesn't grow more with new changes. Signed-off-by: Andrii Nakryiko Signed-off-by: Daniel Borkmann Acked-by: Lorenz Bauer Link: https://lore.kernel.org/bpf/20230406234205.323208-2-andrii@kernel.org --- include/linux/bpf_verifier.h | 19 +++++++------------ 1 file changed, 7 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 81d525d057c7..83dff25545ee 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -498,11 +498,6 @@ struct bpf_verifier_log { u32 len_total; }; -static inline bool bpf_verifier_log_full(const struct bpf_verifier_log *log) -{ - return log->len_used >= log->len_total - 1; -} - #define BPF_LOG_LEVEL1 1 #define BPF_LOG_LEVEL2 2 #define BPF_LOG_STATS 4 @@ -512,6 +507,11 @@ static inline bool bpf_verifier_log_full(const struct bpf_verifier_log *log) #define BPF_LOG_MIN_ALIGNMENT 8U #define BPF_LOG_ALIGNMENT 40U +static inline bool bpf_verifier_log_full(const struct bpf_verifier_log *log) +{ + return log->len_used >= log->len_total - 1; +} + static inline bool bpf_verifier_log_needed(const struct bpf_verifier_log *log) { return log && @@ -519,13 +519,6 @@ static inline bool bpf_verifier_log_needed(const struct bpf_verifier_log *log) log->level == BPF_LOG_KERNEL); } -static inline bool -bpf_verifier_log_attr_valid(const struct bpf_verifier_log *log) -{ - return log->len_total >= 128 && log->len_total <= UINT_MAX >> 2 && - log->level && log->ubuf && !(log->level & ~BPF_LOG_MASK); -} - #define BPF_MAX_SUBPROGS 256 struct bpf_subprog_info { @@ -608,12 +601,14 @@ struct bpf_verifier_env { char type_str_buf[TYPE_STR_BUF_LEN]; }; +bool bpf_verifier_log_attr_valid(const struct bpf_verifier_log *log); __printf(2, 0) void bpf_verifier_vlog(struct bpf_verifier_log *log, const char *fmt, va_list args); __printf(2, 3) void bpf_verifier_log_write(struct bpf_verifier_env *env, const char *fmt, ...); __printf(2, 3) void bpf_log(struct bpf_verifier_log *log, const char *fmt, ...); +void bpf_vlog_reset(struct bpf_verifier_log *log, u32 new_pos); static inline struct bpf_func_state *cur_func(struct bpf_verifier_env *env) { -- cgit v1.2.3 From 1216640938035e63bdbd32438e91c9bcc1fd8ee1 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Thu, 6 Apr 2023 16:41:49 -0700 Subject: bpf: Switch BPF verifier log to be a rotating log by default Currently, if user-supplied log buffer to collect BPF verifier log turns out to be too small to contain full log, bpf() syscall returns -ENOSPC, fails BPF program verification/load, and preserves first N-1 bytes of the verifier log (where N is the size of user-supplied buffer). This is problematic in a bunch of common scenarios, especially when working with real-world BPF programs that tend to be pretty complex as far as verification goes and require big log buffers. Typically, it's when debugging tricky cases at log level 2 (verbose). Also, when BPF program is successfully validated, log level 2 is the only way to actually see verifier state progression and all the important details. Even with log level 1, it's possible to get -ENOSPC even if the final verifier log fits in log buffer, if there is a code path that's deep enough to fill up entire log, even if normally it would be reset later on (there is a logic to chop off successfully validated portions of BPF verifier log). In short, it's not always possible to pre-size log buffer. Also, what's worse, in practice, the end of the log most often is way more important than the beginning, but verifier stops emitting log as soon as initial log buffer is filled up. This patch switches BPF verifier log behavior to effectively behave as rotating log. That is, if user-supplied log buffer turns out to be too short, verifier will keep overwriting previously written log, effectively treating user's log buffer as a ring buffer. -ENOSPC is still going to be returned at the end, to notify user that log contents was truncated, but the important last N bytes of the log would be returned, which might be all that user really needs. This consistent -ENOSPC behavior, regardless of rotating or fixed log behavior, allows to prevent backwards compatibility breakage. The only user-visible change is which portion of verifier log user ends up seeing *if buffer is too small*. Given contents of verifier log itself is not an ABI, there is no breakage due to this behavior change. Specialized tools that rely on specific contents of verifier log in -ENOSPC scenario are expected to be easily adapted to accommodate old and new behaviors. Importantly, though, to preserve good user experience and not require every user-space application to adopt to this new behavior, before exiting to user-space verifier will rotate log (in place) to make it start at the very beginning of user buffer as a continuous zero-terminated string. The contents will be a chopped off N-1 last bytes of full verifier log, of course. Given beginning of log is sometimes important as well, we add BPF_LOG_FIXED (which equals 8) flag to force old behavior, which allows tools like veristat to request first part of verifier log, if necessary. BPF_LOG_FIXED flag is also a simple and straightforward way to check if BPF verifier supports rotating behavior. On the implementation side, conceptually, it's all simple. We maintain 64-bit logical start and end positions. If we need to truncate the log, start position will be adjusted accordingly to lag end position by N bytes. We then use those logical positions to calculate their matching actual positions in user buffer and handle wrap around the end of the buffer properly. Finally, right before returning from bpf_check(), we rotate user log buffer contents in-place as necessary, to make log contents contiguous. See comments in relevant functions for details. Signed-off-by: Andrii Nakryiko Signed-off-by: Daniel Borkmann Reviewed-by: Lorenz Bauer Link: https://lore.kernel.org/bpf/20230406234205.323208-4-andrii@kernel.org --- include/linux/bpf_verifier.h | 33 ++++++++++++++++++++++++++------- 1 file changed, 26 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 83dff25545ee..4c926227f612 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -491,25 +491,42 @@ struct bpf_insn_aux_data { #define BPF_VERIFIER_TMP_LOG_SIZE 1024 struct bpf_verifier_log { - u32 level; - char kbuf[BPF_VERIFIER_TMP_LOG_SIZE]; + /* Logical start and end positions of a "log window" of the verifier log. + * start_pos == 0 means we haven't truncated anything. + * Once truncation starts to happen, start_pos + len_total == end_pos, + * except during log reset situations, in which (end_pos - start_pos) + * might get smaller than len_total (see bpf_vlog_reset()). + * Generally, (end_pos - start_pos) gives number of useful data in + * user log buffer. + */ + u64 start_pos; + u64 end_pos; char __user *ubuf; - u32 len_used; + u32 level; u32 len_total; + char kbuf[BPF_VERIFIER_TMP_LOG_SIZE]; }; #define BPF_LOG_LEVEL1 1 #define BPF_LOG_LEVEL2 2 #define BPF_LOG_STATS 4 +#define BPF_LOG_FIXED 8 #define BPF_LOG_LEVEL (BPF_LOG_LEVEL1 | BPF_LOG_LEVEL2) -#define BPF_LOG_MASK (BPF_LOG_LEVEL | BPF_LOG_STATS) +#define BPF_LOG_MASK (BPF_LOG_LEVEL | BPF_LOG_STATS | BPF_LOG_FIXED) #define BPF_LOG_KERNEL (BPF_LOG_MASK + 1) /* kernel internal flag */ #define BPF_LOG_MIN_ALIGNMENT 8U #define BPF_LOG_ALIGNMENT 40U +static inline u32 bpf_log_used(const struct bpf_verifier_log *log) +{ + return log->end_pos - log->start_pos; +} + static inline bool bpf_verifier_log_full(const struct bpf_verifier_log *log) { - return log->len_used >= log->len_total - 1; + if (log->level & BPF_LOG_FIXED) + return bpf_log_used(log) >= log->len_total - 1; + return false; } static inline bool bpf_verifier_log_needed(const struct bpf_verifier_log *log) @@ -596,7 +613,7 @@ struct bpf_verifier_env { u32 scratched_regs; /* Same as scratched_regs but for stack slots */ u64 scratched_stack_slots; - u32 prev_log_len, prev_insn_print_len; + u64 prev_log_pos, prev_insn_print_pos; /* buffer used in reg_type_str() to generate reg_type string */ char type_str_buf[TYPE_STR_BUF_LEN]; }; @@ -608,7 +625,9 @@ __printf(2, 3) void bpf_verifier_log_write(struct bpf_verifier_env *env, const char *fmt, ...); __printf(2, 3) void bpf_log(struct bpf_verifier_log *log, const char *fmt, ...); -void bpf_vlog_reset(struct bpf_verifier_log *log, u32 new_pos); +void bpf_vlog_reset(struct bpf_verifier_log *log, u64 new_pos); +void bpf_vlog_finalize(struct bpf_verifier_log *log); +bool bpf_vlog_truncated(const struct bpf_verifier_log *log); static inline struct bpf_func_state *cur_func(struct bpf_verifier_env *env) { -- cgit v1.2.3 From fa1c7d5cc404ac3b6e6b4ab6d00b07c76bd819be Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Thu, 6 Apr 2023 16:41:57 -0700 Subject: bpf: Keep track of total log content size in both fixed and rolling modes Change how we do accounting in BPF_LOG_FIXED mode and adopt log->end_pos as *logical* log position. This means that we can go beyond physical log buffer size now and be able to tell what log buffer size should be to fit entire log contents without -ENOSPC. To do this for BPF_LOG_FIXED mode, we need to remove a short-circuiting logic of not vsnprintf()'ing further log content once we filled up user-provided buffer, which is done by bpf_verifier_log_needed() checks. We modify these checks to always keep going if log->level is non-zero (i.e., log is requested), even if log->ubuf was NULL'ed out due to copying data to user-space, or if entire log buffer is physically full. We adopt bpf_verifier_vlog() routine to work correctly with log->ubuf == NULL condition, performing log formatting into temporary kernel buffer, doing all the necessary accounting, but just avoiding copying data out if buffer is full or NULL'ed out. With these changes, it's now possible to do this sort of determination of log contents size in both BPF_LOG_FIXED and default rolling log mode. We need to keep in mind bpf_vlog_reset(), though, which shrinks log contents after successful verification of a particular code path. This log reset means that log->end_pos isn't always increasing, so to return back to users what should be the log buffer size to fit all log content without causing -ENOSPC even in the presence of log resetting, we need to keep maximum over "lifetime" of logging. We do this accounting in bpf_vlog_update_len_max() helper. A related and subtle aspect is that with this logical log->end_pos even in BPF_LOG_FIXED mode we could temporary "overflow" buffer, but then reset it back with bpf_vlog_reset() to a position inside user-supplied log_buf. In such situation we still want to properly maintain terminating zero. We will eventually return -ENOSPC even if final log buffer is small (we detect this through log->len_max check). This behavior is simpler to reason about and is consistent with current behavior of verifier log. Handling of this required a small addition to bpf_vlog_reset() logic to avoid doing put_user() beyond physical log buffer dimensions. Another issue to keep in mind is that we limit log buffer size to 32-bit value and keep such log length as u32, but theoretically verifier could produce huge log stretching beyond 4GB. Instead of keeping (and later returning) 64-bit log length, we cap it at UINT_MAX. Current UAPI makes it impossible to specify log buffer size bigger than 4GB anyways, so we don't really loose anything here and keep everything consistently 32-bit in UAPI. This property will be utilized in next patch. Doing the same determination of maximum log buffer for rolling mode is trivial, as log->end_pos and log->start_pos are already logical positions, so there is nothing new there. These changes do incidentally fix one small issue with previous logging logic. Previously, if use provided log buffer of size N, and actual log output was exactly N-1 bytes + terminating \0, kernel logic coun't distinguish this condition from log truncation scenario which would end up with truncated log contents of N-1 bytes + terminating \0 as well. But now with log->end_pos being logical position that could go beyond actual log buffer size, we can distinguish these two conditions, which we do in this patch. This plays nicely with returning log_size_actual (implemented in UAPI in the next patch), as we can now guarantee that if user takes such log_size_actual and provides log buffer of that exact size, they will not get -ENOSPC in return. All in all, all these changes do conceptually unify fixed and rolling log modes much better, and allow a nice feature requested by users: knowing what should be the size of the buffer to avoid -ENOSPC. We'll plumb this through the UAPI and the code in the next patch. Signed-off-by: Andrii Nakryiko Signed-off-by: Daniel Borkmann Acked-by: Lorenz Bauer Link: https://lore.kernel.org/bpf/20230406234205.323208-12-andrii@kernel.org --- include/linux/bpf_verifier.h | 12 +++--------- 1 file changed, 3 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 4c926227f612..98d2eb382dbb 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -504,6 +504,7 @@ struct bpf_verifier_log { char __user *ubuf; u32 level; u32 len_total; + u32 len_max; char kbuf[BPF_VERIFIER_TMP_LOG_SIZE]; }; @@ -517,23 +518,16 @@ struct bpf_verifier_log { #define BPF_LOG_MIN_ALIGNMENT 8U #define BPF_LOG_ALIGNMENT 40U -static inline u32 bpf_log_used(const struct bpf_verifier_log *log) -{ - return log->end_pos - log->start_pos; -} - static inline bool bpf_verifier_log_full(const struct bpf_verifier_log *log) { if (log->level & BPF_LOG_FIXED) - return bpf_log_used(log) >= log->len_total - 1; + return log->end_pos >= log->len_total; return false; } static inline bool bpf_verifier_log_needed(const struct bpf_verifier_log *log) { - return log && - ((log->level && log->ubuf && !bpf_verifier_log_full(log)) || - log->level == BPF_LOG_KERNEL); + return log && log->level; } #define BPF_MAX_SUBPROGS 256 -- cgit v1.2.3 From 47a71c1f9af0a334c9dfa97633c41de4feda4287 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Thu, 6 Apr 2023 16:41:58 -0700 Subject: bpf: Add log_true_size output field to return necessary log buffer size Add output-only log_true_size and btf_log_true_size field to BPF_PROG_LOAD and BPF_BTF_LOAD commands, respectively. It will return the size of log buffer necessary to fit in all the log contents at specified log_level. This is very useful for BPF loader libraries like libbpf to be able to size log buffer correctly, but could be used by users directly, if necessary, as well. This patch plumbs all this through the code, taking into account actual bpf_attr size provided by user to determine if these new fields are expected by users. And if they are, set them from kernel on return. We refactory btf_parse() function to accommodate this, moving attr and uattr handling inside it. The rest is very straightforward code, which is split from the logging accounting changes in the previous patch to make it simpler to review logic vs UAPI changes. Signed-off-by: Andrii Nakryiko Signed-off-by: Daniel Borkmann Acked-by: Lorenz Bauer Link: https://lore.kernel.org/bpf/20230406234205.323208-13-andrii@kernel.org --- include/linux/bpf.h | 2 +- include/linux/btf.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 002a811b6b90..2c6095bd7d69 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -2175,7 +2175,7 @@ int bpf_check_uarg_tail_zero(bpfptr_t uaddr, size_t expected_size, size_t actual_size); /* verify correctness of eBPF program */ -int bpf_check(struct bpf_prog **fp, union bpf_attr *attr, bpfptr_t uattr); +int bpf_check(struct bpf_prog **fp, union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size); #ifndef CONFIG_BPF_JIT_ALWAYS_ON void bpf_patch_call_args(struct bpf_insn *insn, u32 stack_depth); diff --git a/include/linux/btf.h b/include/linux/btf.h index d53b10cc55f2..495250162422 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -125,7 +125,7 @@ extern const struct file_operations btf_fops; void btf_get(struct btf *btf); void btf_put(struct btf *btf); -int btf_new_fd(const union bpf_attr *attr, bpfptr_t uattr); +int btf_new_fd(const union bpf_attr *attr, bpfptr_t uattr, u32 uattr_sz); struct btf *btf_get_by_fd(int fd); int btf_get_info_by_fd(const struct btf *btf, const union bpf_attr *attr, -- cgit v1.2.3 From bdcab4144f5da97cc0fa7e1dd63b8475e10c8f0a Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Thu, 6 Apr 2023 16:41:59 -0700 Subject: bpf: Simplify internal verifier log interface Simplify internal verifier log API down to bpf_vlog_init() and bpf_vlog_finalize(). The former handles input arguments validation in one place and makes it easier to change it. The latter subsumes -ENOSPC (truncation) and -EFAULT handling and simplifies both caller's code (bpf_check() and btf_parse()). For btf_parse(), this patch also makes sure that verifier log finalization happens even if there is some error condition during BTF verification process prior to normal finalization step. Signed-off-by: Andrii Nakryiko Signed-off-by: Daniel Borkmann Acked-by: Lorenz Bauer Link: https://lore.kernel.org/bpf/20230406234205.323208-14-andrii@kernel.org --- include/linux/bpf_verifier.h | 13 +++---------- 1 file changed, 3 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 98d2eb382dbb..f03852b89d28 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -518,13 +518,6 @@ struct bpf_verifier_log { #define BPF_LOG_MIN_ALIGNMENT 8U #define BPF_LOG_ALIGNMENT 40U -static inline bool bpf_verifier_log_full(const struct bpf_verifier_log *log) -{ - if (log->level & BPF_LOG_FIXED) - return log->end_pos >= log->len_total; - return false; -} - static inline bool bpf_verifier_log_needed(const struct bpf_verifier_log *log) { return log && log->level; @@ -612,16 +605,16 @@ struct bpf_verifier_env { char type_str_buf[TYPE_STR_BUF_LEN]; }; -bool bpf_verifier_log_attr_valid(const struct bpf_verifier_log *log); __printf(2, 0) void bpf_verifier_vlog(struct bpf_verifier_log *log, const char *fmt, va_list args); __printf(2, 3) void bpf_verifier_log_write(struct bpf_verifier_env *env, const char *fmt, ...); __printf(2, 3) void bpf_log(struct bpf_verifier_log *log, const char *fmt, ...); +int bpf_vlog_init(struct bpf_verifier_log *log, u32 log_level, + char __user *log_buf, u32 log_size); void bpf_vlog_reset(struct bpf_verifier_log *log, u64 new_pos); -void bpf_vlog_finalize(struct bpf_verifier_log *log); -bool bpf_vlog_truncated(const struct bpf_verifier_log *log); +int bpf_vlog_finalize(struct bpf_verifier_log *log, u32 *log_size_actual); static inline struct bpf_func_state *cur_func(struct bpf_verifier_env *env) { -- cgit v1.2.3 From 3664ff82dae1ef9f14f7763d3dd30565e7ef9e14 Mon Sep 17 00:00:00 2001 From: Yangtao Li Date: Mon, 10 Apr 2023 00:43:37 +0800 Subject: dm: add helper macro for simple DM target module init and exit Eliminate duplicate boilerplate code for simple modules that contain a single DM target driver without any additional setup code. Add a new module_dm() macro, which replaces the module_init() and module_exit() with template functions that call dm_register_target() and dm_unregister_target() respectively. Signed-off-by: Yangtao Li Signed-off-by: Mike Snitzer --- include/linux/device-mapper.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include/linux') diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index 8aa6b3ea91fa..f2d9afb8a7e9 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -631,6 +631,26 @@ void dm_destroy_crypto_profile(struct blk_crypto_profile *profile); DMEMIT("target_name=%s,target_version=%u.%u.%u", \ (y)->name, (y)->version[0], (y)->version[1], (y)->version[2]) +/** + * module_dm() - Helper macro for DM targets that don't do anything + * special in their module_init and module_exit. + * Each module may only use this macro once, and calling it replaces + * module_init() and module_exit(). + * + * @name: DM target's name + */ +#define module_dm(name) \ +static int __init dm_##name##_init(void) \ +{ \ + return dm_register_target(&(name##_target)); \ +} \ +module_init(dm_##name##_init) \ +static void __exit dm_##name##_exit(void) \ +{ \ + dm_unregister_target(&(name##_target)); \ +} \ +module_exit(dm_##name##_exit) + /* * Definitions of return values from target end_io function. */ -- cgit v1.2.3 From 88a4d7bdeec97890cd543b58dd3588f1f879f51b Mon Sep 17 00:00:00 2001 From: Dave Wysochanski Date: Mon, 20 Feb 2023 08:43:05 -0500 Subject: NFS: Configure support for netfs when NFS fscache is configured As first steps for support of the netfs library when NFS_FSCACHE is configured, add NETFS_SUPPORT to Kconfig and add the required netfs_inode into struct nfs_inode. Using netfs requires we move the VFS inode structure to be stored inside struct netfs_inode, along with the fscache_cookie. Thus, if NFS_FSCACHE is configured, place netfs_inode inside an anonymous union so the vfs_inode memory is the same and we do not need to modify other non-fscache areas of NFS. In addition, inside the NFS fscache code, use the new helpers, netfs_inode() and netfs_i_cookie() helpers, and remove our own helper, nfs_i_fscache(). Later patches will convert NFS fscache to fully use netfs. Signed-off-by: Dave Wysochanski Tested-by: Daire Byrne Signed-off-by: Anna Schumaker --- include/linux/nfs_fs.h | 24 ++++++++++-------------- 1 file changed, 10 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index bf89fe6fc3ba..041e79a48f7a 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -31,6 +31,10 @@ #include #include +#ifdef CONFIG_NFS_FSCACHE +#include +#endif + #include #include #include @@ -204,14 +208,15 @@ struct nfs_inode { /* how many bytes have been written/read and how many bytes queued up */ __u64 write_io; __u64 read_io; -#ifdef CONFIG_NFS_FSCACHE - struct fscache_cookie *fscache; -#endif - struct inode vfs_inode; - #ifdef CONFIG_NFS_V4_2 struct nfs4_xattr_cache *xattr_cache; #endif + union { + struct inode vfs_inode; +#ifdef CONFIG_NFS_FSCACHE + struct netfs_inode netfs; /* netfs context and VFS inode */ +#endif + }; }; struct nfs4_copy_state { @@ -329,15 +334,6 @@ static inline int NFS_STALE(const struct inode *inode) return test_bit(NFS_INO_STALE, &NFS_I(inode)->flags); } -static inline struct fscache_cookie *nfs_i_fscache(struct inode *inode) -{ -#ifdef CONFIG_NFS_FSCACHE - return NFS_I(inode)->fscache; -#else - return NULL; -#endif -} - static inline __u64 NFS_FILEID(const struct inode *inode) { return NFS_I(inode)->fileid; -- cgit v1.2.3 From 000dbe0bec058cbf2ca9e156e4a5584f5158b0f9 Mon Sep 17 00:00:00 2001 From: Dave Wysochanski Date: Mon, 20 Feb 2023 08:43:06 -0500 Subject: NFS: Convert buffered read paths to use netfs when fscache is enabled Convert the NFS buffered read code paths to corresponding netfs APIs, but only when fscache is configured and enabled. The netfs API defines struct netfs_request_ops which must be filled in by the network filesystem. For NFS, we only need to define 5 of the functions, the main one being the issue_read() function. The issue_read() function is called by the netfs layer when a read cannot be fulfilled locally, and must be sent to the server (either the cache is not active, or it is active but the data is not available). Once the read from the server is complete, netfs requires a call to netfs_subreq_terminated() which conveys either how many bytes were read successfully, or an error. Note that issue_read() is called with a structure, netfs_io_subrequest, which defines the IO requested, and contains a start and a length (both in bytes), and assumes the underlying netfs will return a either an error on the whole region, or the number of bytes successfully read. The NFS IO path is page based and the main APIs are the pgio APIs defined in pagelist.c. For the pgio APIs, there is no way for the caller to know how many RPCs will be sent and how the pages will be broken up into underlying RPCs, each of which will have their own completion and return code. In contrast, netfs is subrequest based, a single subrequest may contain multiple pages, and a single subrequest is initiated with issue_read() and terminated with netfs_subreq_terminated(). Thus, to utilze the netfs APIs, NFS needs some way to accommodate the netfs API requirement on the single response to the whole subrequest, while also minimizing disruptive changes to the NFS pgio layer. The approach taken with this patch is to allocate a small structure for each nfs_netfs_issue_read() call, store the final error and number of bytes successfully transferred in the structure, and update these values as each RPC completes. The refcount on the structure is used as a marker for the last RPC completion, is incremented in nfs_netfs_read_initiate(), and decremented inside nfs_netfs_read_completion(), when a nfs_pgio_header contains a valid pointer to the data. On the final put (which signals the final outstanding RPC is complete) in nfs_netfs_read_completion(), call netfs_subreq_terminated() with either the final error value (if one or more READs complete with an error) or the number of bytes successfully transferred (if all RPCs complete successfully). Note that when all RPCs complete successfully, the number of bytes transferred is capped to the length of the subrequest. Capping the transferred length to the subrequest length prevents "Subreq overread" warnings from netfs. This is due to the "aligned_len" in nfs_pageio_add_page(), and the corner case where NFS requests a full page at the end of the file, even when i_size reflects only a partial page (NFS overread). Signed-off-by: Dave Wysochanski Tested-by: Daire Byrne Signed-off-by: Anna Schumaker --- include/linux/nfs_page.h | 3 +++ include/linux/nfs_xdr.h | 3 +++ 2 files changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h index a2f1ca657623..aa9f4c6ebe26 100644 --- a/include/linux/nfs_page.h +++ b/include/linux/nfs_page.h @@ -105,6 +105,9 @@ struct nfs_pageio_descriptor { struct pnfs_layout_segment *pg_lseg; struct nfs_io_completion *pg_io_completion; struct nfs_direct_req *pg_dreq; +#ifdef CONFIG_NFS_FSCACHE + void *pg_netfs; +#endif unsigned int pg_bsize; /* default bsize for mirrors */ u32 pg_mirror_count; diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index e86cf6642d21..e196ef595908 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1619,6 +1619,9 @@ struct nfs_pgio_header { const struct nfs_rw_ops *rw_ops; struct nfs_io_completion *io_completion; struct nfs_direct_req *dreq; +#ifdef CONFIG_NFS_FSCACHE + void *netfs; +#endif int pnfs_error; int error; /* merge with pnfs_error */ -- cgit v1.2.3 From 0631d5e02a1c722b90c11a47dcb6d83ef88ab47b Mon Sep 17 00:00:00 2001 From: Dave Wysochanski Date: Mon, 20 Feb 2023 08:43:07 -0500 Subject: NFS: Remove all NFSIOS_FSCACHE counters due to conversion to netfs API The old NFSIOS_FSCACHE counters are no longer accurate or useful with the conversion to the new netfs API. The new API does not have a page based interface, and so the counters in nfs_stat_fscachecounters are no longer obtainable. The new netfs the API has extensive statistics inside /proc/fs/fscache/stats so we no longer need NFS specific fscache stats. Note this also removes the 'fsc:' line from /proc/self/mountstats so it will be a user-visible change. Signed-off-by: Dave Wysochanski Reviewed-by: Jeff Layton Tested-by: Daire Byrne Signed-off-by: Anna Schumaker --- include/linux/nfs_iostat.h | 12 ------------ 1 file changed, 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfs_iostat.h b/include/linux/nfs_iostat.h index 027874c36c88..8d946089d151 100644 --- a/include/linux/nfs_iostat.h +++ b/include/linux/nfs_iostat.h @@ -119,16 +119,4 @@ enum nfs_stat_eventcounters { __NFSIOS_COUNTSMAX, }; -/* - * NFS local caching servicing counters - */ -enum nfs_stat_fscachecounters { - NFSIOS_FSCACHE_PAGES_READ_OK, - NFSIOS_FSCACHE_PAGES_READ_FAIL, - NFSIOS_FSCACHE_PAGES_WRITTEN_OK, - NFSIOS_FSCACHE_PAGES_WRITTEN_FAIL, - NFSIOS_FSCACHE_PAGES_UNCACHED, - __NFSIOS_FSCACHEMAX, -}; - #endif /* _LINUX_NFS_IOSTAT */ -- cgit v1.2.3 From 03f5bd75a4c19714a929a0f4e7bbf36b49e874c1 Mon Sep 17 00:00:00 2001 From: Dave Wysochanski Date: Mon, 20 Feb 2023 08:43:08 -0500 Subject: NFS: Remove fscache specific trace points and NFS_INO_FSCACHE bit The NFS specific trace points are no longer needed as tracing is well covered by netfs and fscache. Signed-off-by: Dave Wysochanski Reviewed-by: Jeff Layton Tested-by: Daire Byrne Signed-off-by: Anna Schumaker --- include/linux/nfs_fs.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 041e79a48f7a..12bb868f9a18 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -281,7 +281,6 @@ struct nfs4_copy_state { #define NFS_INO_ACL_LRU_SET (2) /* Inode is on the LRU list */ #define NFS_INO_INVALIDATING (3) /* inode is being invalidated */ #define NFS_INO_PRESERVE_UNLINKED (4) /* preserve file if removed while open */ -#define NFS_INO_FSCACHE (5) /* inode can be cached by FS-Cache */ #define NFS_INO_LAYOUTCOMMIT (9) /* layoutcommit required */ #define NFS_INO_LAYOUTCOMMITTING (10) /* layoutcommit inflight */ #define NFS_INO_LAYOUTSTATS (11) /* layoutstats inflight */ -- cgit v1.2.3 From 3db63daabe210af32a09533fe7d8d47c711a103c Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Wed, 22 Mar 2023 09:27:04 +1100 Subject: NFSv3: handle out-of-order write replies. NFSv3 includes pre/post wcc attributes which allow the client to determine if all changes to the file have been made by the client itself, or if any might have been made by some other client. If there are gaps in the pre/post ctime sequence it must be assumed that some other client changed the file in that gap and the local cache must be suspect. The next time the file is opened the cache should be invalidated. Since Commit 1c341b777501 ("NFS: Add deferred cache invalidation for close-to-open consistency violations") in linux 5.3 the Linux client has been triggering this invalidation. The chunk in nfs_update_inode() in particularly triggers. Unfortunately Linux NFS assumes that all replies will be processed in the order sent, and will arrive in the order processed. This is not true in general. Consequently Linux NFS might ignore the wcc info in a WRITE reply because the reply is in response to a WRITE that was sent before some other request for which a reply has already been seen. This is detected by Linux using the gencount tests in nfs_inode_attr_cmp(). Also, when the gencount tests pass it is still possible that the request were processed on the server in a different order, and a gap seen in the ctime sequence might be filled in by a subsequent reply, so gaps should not immediately trigger delayed invalidation. The net result is that writing to a server and then reading the file back can result in going to the server for the read rather than serving it from cache - all because a couple of replies arrived out-of-order. This is a performance regression over kernels before 5.3, though the change in 5.3 is a correctness improvement. This has been seen with Linux writing to a Netapp server which occasionally re-orders requests. In testing the majority of requests were in-order, but a few (maybe 2 or three at a time) could be re-ordered. This patch addresses the problem by recording any gaps seen in the pre/post ctime sequence and not triggering invalidation until either there are too many gaps to fit in the table, or until there are no more active writes and the remaining gaps cannot be resolved. We allocate a table of 16 gaps on demand. If the allocation fails we revert to current behaviour which is of little cost as we are unlikely to be able to cache the writes anyway. In the table we store "start->end" pair when iversion is updated and "end<-start" pairs pre/post pairs reported by the server. Usually these exactly cancel out and so nothing is stored. When there are out-of-order replies we do store gaps and these will eventually be cancelled against later replies when this client is the only writer. If the final write is out-of-order there may be one gap remaining when the file is closed. This will be noticed and if there is precisely on gap and if the iversion can be advanced to match it, then we do so. This patch makes no attempt to handle directories correctly. The same problem potentially exists in the out-of-order replies to create/unlink requests can cause future lookup requires to be sent to the server unnecessarily. A similar scheme using the same primitives could be used to notice and handle out-of-order replies. Signed-off-by: NeilBrown Signed-off-by: Anna Schumaker --- include/linux/nfs_fs.h | 47 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 47 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 12bb868f9a18..279262057a92 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -195,6 +195,39 @@ struct nfs_inode { /* Open contexts for shared mmap writes */ struct list_head open_files; + /* Keep track of out-of-order replies. + * The ooo array contains start/end pairs of + * numbers from the changeid sequence when + * the inode's iversion has been updated. + * It also contains end/start pair (i.e. reverse order) + * of sections of the changeid sequence that have + * been seen in replies from the server. + * Normally these should match and when both + * A:B and B:A are found in ooo, they are both removed. + * And if a reply with A:B causes an iversion update + * of A:B, then neither are added. + * When a reply has pre_change that doesn't match + * iversion, then the changeid pair and any consequent + * change in iversion ARE added. Later replies + * might fill in the gaps, or possibly a gap is caused + * by a change from another client. + * When a file or directory is opened, if the ooo table + * is not empty, then we assume the gaps were due to + * another client and we invalidate the cached data. + * + * We can only track a limited number of concurrent gaps. + * Currently that limit is 16. + * We allocate the table on demand. If there is insufficient + * memory, then we probably cannot cache the file anyway + * so there is no loss. + */ + struct { + int cnt; + struct { + u64 start, end; + } gap[16]; + } *ooo; + #if IS_ENABLED(CONFIG_NFS_V4) struct nfs4_cached_acl *nfs4_acl; /* NFSv4 state */ @@ -612,6 +645,20 @@ nfs_fileid_to_ino_t(u64 fileid) return ino; } +static inline void nfs_ooo_clear(struct nfs_inode *nfsi) +{ + nfsi->cache_validity &= ~NFS_INO_DATA_INVAL_DEFER; + kfree(nfsi->ooo); + nfsi->ooo = NULL; +} + +static inline bool nfs_ooo_test(struct nfs_inode *nfsi) +{ + return (nfsi->cache_validity & NFS_INO_DATA_INVAL_DEFER) || + (nfsi->ooo && nfsi->ooo->cnt > 0); + +} + #define NFS_JUKEBOX_RETRY_TIME (5 * HZ) /* We need to block new opens while a file is being unlinked. -- cgit v1.2.3 From 8eb8af4b3df5965dc65a24a32768043f39d82d59 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Mon, 27 Mar 2023 21:03:26 -0700 Subject: fsverity: use WARN_ON_ONCE instead of WARN_ON As per Linus's suggestion (https://lore.kernel.org/r/CAHk-=whefxRGyNGzCzG6BVeM=5vnvgb-XhSeFJVxJyAxAF8XRA@mail.gmail.com), use WARN_ON_ONCE instead of WARN_ON. This barely adds any extra overhead, and it makes it so that if any of these ever becomes reachable (they shouldn't, but that's the point), the logs can't be flooded. Link: https://lore.kernel.org/r/20230406181542.38894-1-ebiggers@kernel.org Reviewed-by: Chaitanya Kulkarni Reviewed-by: Christian Brauner Signed-off-by: Eric Biggers --- include/linux/fsverity.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fsverity.h b/include/linux/fsverity.h index 119a3266791f..e76605d5b36e 100644 --- a/include/linux/fsverity.h +++ b/include/linux/fsverity.h @@ -233,18 +233,18 @@ static inline int fsverity_ioctl_read_metadata(struct file *filp, static inline bool fsverity_verify_blocks(struct folio *folio, size_t len, size_t offset) { - WARN_ON(1); + WARN_ON_ONCE(1); return false; } static inline void fsverity_verify_bio(struct bio *bio) { - WARN_ON(1); + WARN_ON_ONCE(1); } static inline void fsverity_enqueue_verify_work(struct work_struct *work) { - WARN_ON(1); + WARN_ON_ONCE(1); } #endif /* !CONFIG_FS_VERITY */ -- cgit v1.2.3 From e5688f6fb9e3d0254a8fb1c714c38e407f0baa64 Mon Sep 17 00:00:00 2001 From: Vlad Buslov Date: Wed, 1 Mar 2023 10:33:55 +0100 Subject: net/mlx5: Add mlx5_ifc definitions for bridge multicast support Add the required hardware definitions to mlx5_ifc: fdb_uplink_hairpin, fdb_multi_path_any_table_limit_regc, fdb_multi_path_any_table. Signed-off-by: Vlad Buslov Reviewed-by: Maor Dickman Reviewed-by: Roi Dayan Signed-off-by: Saeed Mahameed --- include/linux/mlx5/mlx5_ifc.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index e47d6c58da35..02c628f4fe26 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -880,7 +880,12 @@ enum { struct mlx5_ifc_flow_table_eswitch_cap_bits { u8 fdb_to_vport_reg_c_id[0x8]; - u8 reserved_at_8[0xd]; + u8 reserved_at_8[0x5]; + u8 fdb_uplink_hairpin[0x1]; + u8 fdb_multi_path_any_table_limit_regc[0x1]; + u8 reserved_at_f[0x3]; + u8 fdb_multi_path_any_table[0x1]; + u8 reserved_at_13[0x2]; u8 fdb_modify_header_fwd_to_table[0x1]; u8 fdb_ipv4_ttl_modify[0x1]; u8 flow_source[0x1]; -- cgit v1.2.3 From 9df839a711aee437390b16ee39cf0b5c1620be6a Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Thu, 23 Apr 2020 08:27:59 -0500 Subject: net/mlx5: Create a new profile for SFs Create a new profile for SFs in order to disable the command cache. Each function command cache consumes ~500KB of memory, when using a large number of SFs this savings is notable on memory constarined systems. Use a new profile to provide for future differences between SFs and PFs. The mr_cache not used for non-PF functions, so it is excluded from the new profile. Signed-off-by: Parav Pandit Reviewed-by: Bodong Wang Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index f243bd10a5e1..135a3c8d8237 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -751,6 +751,7 @@ enum { struct mlx5_profile { u64 mask; u8 log_max_qp; + u8 num_cmd_caches; struct { int size; int limit; -- cgit v1.2.3 From 9fa7f1de3dda0bc74c964b5127b3f22bd8ef8fd2 Mon Sep 17 00:00:00 2001 From: Yevgeny Kliteynik Date: Tue, 30 Aug 2022 01:20:30 +0300 Subject: net/mlx5: Add mlx5_ifc bits for modify header argument Add enum value for modify-header argument object and mlx5_bits for the related capabilities. Signed-off-by: Muhammad Sammar Signed-off-by: Yevgeny Kliteynik Reviewed-by: Alex Vesker Signed-off-by: Saeed Mahameed --- include/linux/mlx5/mlx5_ifc.h | 28 +++++++++++++++++++++++++++- 1 file changed, 27 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 02c628f4fe26..6c84bf6eec85 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -78,12 +78,15 @@ enum { enum { MLX5_OBJ_TYPE_SW_ICM = 0x0008, + MLX5_OBJ_TYPE_HEADER_MODIFY_ARGUMENT = 0x23, }; enum { MLX5_GENERAL_OBJ_TYPES_CAP_SW_ICM = (1ULL << MLX5_OBJ_TYPE_SW_ICM), MLX5_GENERAL_OBJ_TYPES_CAP_GENEVE_TLV_OPT = (1ULL << 11), MLX5_GENERAL_OBJ_TYPES_CAP_VIRTIO_NET_Q = (1ULL << 13), + MLX5_GENERAL_OBJ_TYPES_CAP_HEADER_MODIFY_ARGUMENT = + (1ULL << MLX5_OBJ_TYPE_HEADER_MODIFY_ARGUMENT), MLX5_GENERAL_OBJ_TYPES_CAP_MACSEC_OFFLOAD = (1ULL << 39), }; @@ -321,6 +324,10 @@ enum { MLX5_FT_NIC_TX_RDMA_2_NIC_TX = BIT(1), }; +enum { + MLX5_CMD_OP_MOD_UPDATE_HEADER_MODIFY_ARGUMENT = 0x1, +}; + struct mlx5_ifc_flow_table_fields_supported_bits { u8 outer_dmac[0x1]; u8 outer_smac[0x1]; @@ -1927,7 +1934,14 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_750[0x4]; u8 max_dynamic_vf_msix_table_size[0xc]; - u8 reserved_at_760[0x20]; + u8 reserved_at_760[0x3]; + u8 log_max_num_header_modify_argument[0x5]; + u8 reserved_at_768[0x4]; + u8 log_header_modify_argument_granularity[0x4]; + u8 reserved_at_770[0x3]; + u8 log_header_modify_argument_max_alloc[0x5]; + u8 reserved_at_778[0x8]; + u8 vhca_tunnel_commands[0x40]; u8 match_definer_format_supported[0x40]; }; @@ -6361,6 +6375,18 @@ struct mlx5_ifc_general_obj_out_cmd_hdr_bits { u8 reserved_at_60[0x20]; }; +struct mlx5_ifc_modify_header_arg_bits { + u8 reserved_at_0[0x80]; + + u8 reserved_at_80[0x8]; + u8 access_pd[0x18]; +}; + +struct mlx5_ifc_create_modify_header_arg_in_bits { + struct mlx5_ifc_general_obj_in_cmd_hdr_bits hdr; + struct mlx5_ifc_modify_header_arg_bits arg; +}; + struct mlx5_ifc_create_match_definer_in_bits { struct mlx5_ifc_general_obj_in_cmd_hdr_bits general_obj_in_cmd_hdr; -- cgit v1.2.3 From 977c4a3e7c89d5b48fdc548773fb9ed3e6c50cf8 Mon Sep 17 00:00:00 2001 From: Yevgeny Kliteynik Date: Tue, 30 Aug 2022 01:20:40 +0300 Subject: net/mlx5: Add new WQE for updating flow table Add new WQE type: FLOW_TBL_ACCESS, which will be used for writing modify header arguments. This type has specific control segment and special data segment. Signed-off-by: Yevgeny Kliteynik Reviewed-by: Alex Vesker Signed-off-by: Saeed Mahameed --- include/linux/mlx5/device.h | 2 ++ include/linux/mlx5/qp.h | 10 ++++++++++ 2 files changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index af4dd536a52c..e4aa147ab390 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -442,6 +442,8 @@ enum { MLX5_OPCODE_UMR = 0x25, + MLX5_OPCODE_FLOW_TBL_ACCESS = 0x2c, + MLX5_OPCODE_ACCESS_ASO = 0x2d, }; diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h index df55fbb65717..bd53cf4be7bd 100644 --- a/include/linux/mlx5/qp.h +++ b/include/linux/mlx5/qp.h @@ -499,6 +499,16 @@ struct mlx5_stride_block_ctrl_seg { __be16 num_entries; }; +struct mlx5_wqe_flow_update_ctrl_seg { + __be32 flow_idx_update; + __be32 dest_handle; + u8 reserved0[40]; +}; + +struct mlx5_wqe_header_modify_argument_update_seg { + u8 argument_list[64]; +}; + struct mlx5_core_qp { struct mlx5_core_rsc_common common; /* must be first */ void (*event) (struct mlx5_core_qp *, int); -- cgit v1.2.3 From d8f48fbdfd9af268e92b33462472559d2840228c Mon Sep 17 00:00:00 2001 From: Vijendar Mukunda Date: Tue, 21 Mar 2023 10:38:55 +0530 Subject: soundwire: amd: Add support for AMD Manager driver AMD ACP(v6.x) IP block has two SoundWire manager devices. Add support for - Manager driver probe & remove sequence - Helper functions to enable/disable interrupts, Initialize sdw manager, enable sdw pads - Manager driver sdw_master_ops & port_ops callbacks Signed-off-by: Vijendar Mukunda Reviewed-by: Pierre-Louis Bossart Link: https://lore.kernel.org/lkml/20230310162554.699766-3-Vijendar.Mukunda@amd.com Link: https://lore.kernel.org/r/20230321050901.115439-3-Vijendar.Mukunda@amd.com Signed-off-by: Vinod Koul --- include/linux/soundwire/sdw_amd.h | 67 +++++++++++++++++++++++++++++++++++++++ 1 file changed, 67 insertions(+) create mode 100644 include/linux/soundwire/sdw_amd.h (limited to 'include/linux') diff --git a/include/linux/soundwire/sdw_amd.h b/include/linux/soundwire/sdw_amd.h new file mode 100644 index 000000000000..c14a291a40e8 --- /dev/null +++ b/include/linux/soundwire/sdw_amd.h @@ -0,0 +1,67 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * Copyright (C) 2023 Advanced Micro Devices, Inc. All rights reserved. + */ + +#ifndef __SDW_AMD_H +#define __SDW_AMD_H + +#include + +#define ACP_SDW0 0 +#define ACP_SDW1 1 + +struct acp_sdw_pdata { + u16 instance; + /* mutex to protect acp common register access */ + struct mutex *acp_sdw_lock; +}; + +struct sdw_manager_reg_mask { + u32 sw_pad_enable_mask; + u32 sw_pad_pulldown_mask; + u32 acp_sdw_intr_mask; +}; + +/** + * struct amd_sdw_manager - amd manager driver context + * @bus: bus handle + * @dev: linux device + * @mmio: SoundWire registers mmio base + * @acp_mmio: acp registers mmio base + * @reg_mask: register mask structure per manager instance + * @probe_work: SoundWire manager probe workqueue + * @acp_sdw_lock: mutex to protect acp share register access + * @num_din_ports: number of input ports + * @num_dout_ports: number of output ports + * @cols_index: Column index in frame shape + * @rows_index: Rows index in frame shape + * @instance: SoundWire manager instance + * @quirks: SoundWire manager quirks + * @wake_en_mask: wake enable mask per SoundWire manager + * @power_mode_mask: flag interprets amd SoundWire manager power mode + */ +struct amd_sdw_manager { + struct sdw_bus bus; + struct device *dev; + + void __iomem *mmio; + void __iomem *acp_mmio; + + struct sdw_manager_reg_mask *reg_mask; + struct work_struct probe_work; + /* mutex to protect acp common register access */ + struct mutex *acp_sdw_lock; + + int num_din_ports; + int num_dout_ports; + + int cols_index; + int rows_index; + + u32 instance; + u32 quirks; + u32 wake_en_mask; + u32 power_mode_mask; +}; +#endif -- cgit v1.2.3 From 2b13596f7c9c03b1653b21a440ce672c3d7e5233 Mon Sep 17 00:00:00 2001 From: Vijendar Mukunda Date: Tue, 21 Mar 2023 10:38:56 +0530 Subject: soundwire: amd: register SoundWire manager dai ops Register dai ops for SoundWire manager instances. Signed-off-by: Vijendar Mukunda Reviewed-by: Pierre-Louis Bossart Link: https://lore.kernel.org/lkml/20230227154801.50319-4-Vijendar.Mukunda@amd.com Link: https://lore.kernel.org/r/20230321050901.115439-4-Vijendar.Mukunda@amd.com Signed-off-by: Vinod Koul --- include/linux/soundwire/sdw_amd.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include/linux') diff --git a/include/linux/soundwire/sdw_amd.h b/include/linux/soundwire/sdw_amd.h index c14a291a40e8..ac537419301d 100644 --- a/include/linux/soundwire/sdw_amd.h +++ b/include/linux/soundwire/sdw_amd.h @@ -23,6 +23,21 @@ struct sdw_manager_reg_mask { u32 acp_sdw_intr_mask; }; +/** + * struct sdw_amd_dai_runtime: AMD sdw dai runtime data + * + * @name: SoundWire stream name + * @stream: stream runtime + * @bus: Bus handle + * @stream_type: Stream type + */ +struct sdw_amd_dai_runtime { + char *name; + struct sdw_stream_runtime *stream; + struct sdw_bus *bus; + enum sdw_stream_type stream_type; +}; + /** * struct amd_sdw_manager - amd manager driver context * @bus: bus handle @@ -40,6 +55,7 @@ struct sdw_manager_reg_mask { * @quirks: SoundWire manager quirks * @wake_en_mask: wake enable mask per SoundWire manager * @power_mode_mask: flag interprets amd SoundWire manager power mode + * @dai_runtime_array: dai runtime array */ struct amd_sdw_manager { struct sdw_bus bus; @@ -63,5 +79,7 @@ struct amd_sdw_manager { u32 quirks; u32 wake_en_mask; u32 power_mode_mask; + + struct sdw_amd_dai_runtime **dai_runtime_array; }; #endif -- cgit v1.2.3 From 65f93e4096a07abd41acf0d240715bd8c7ef7eeb Mon Sep 17 00:00:00 2001 From: Vijendar Mukunda Date: Tue, 21 Mar 2023 10:38:58 +0530 Subject: soundwire: amd: add SoundWire manager interrupt handling Add support for handling SoundWire manager interrupts. Signed-off-by: Vijendar Mukunda Signed-off-by: Mastan Katragadda Reviewed-by: Pierre-Louis Bossart Link: https://lore.kernel.org/lkml/20230227154801.50319-6-Vijendar.Mukunda@amd.com Link: https://lore.kernel.org/r/20230321050901.115439-6-Vijendar.Mukunda@amd.com Signed-off-by: Vinod Koul --- include/linux/soundwire/sdw_amd.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/soundwire/sdw_amd.h b/include/linux/soundwire/sdw_amd.h index ac537419301d..df60bc0de6fc 100644 --- a/include/linux/soundwire/sdw_amd.h +++ b/include/linux/soundwire/sdw_amd.h @@ -45,8 +45,11 @@ struct sdw_amd_dai_runtime { * @mmio: SoundWire registers mmio base * @acp_mmio: acp registers mmio base * @reg_mask: register mask structure per manager instance + * @amd_sdw_irq_thread: SoundWire manager irq workqueue + * @amd_sdw_work: peripheral status work queue * @probe_work: SoundWire manager probe workqueue * @acp_sdw_lock: mutex to protect acp share register access + * @status: peripheral devices status array * @num_din_ports: number of input ports * @num_dout_ports: number of output ports * @cols_index: Column index in frame shape @@ -65,10 +68,14 @@ struct amd_sdw_manager { void __iomem *acp_mmio; struct sdw_manager_reg_mask *reg_mask; + struct work_struct amd_sdw_irq_thread; + struct work_struct amd_sdw_work; struct work_struct probe_work; /* mutex to protect acp common register access */ struct mutex *acp_sdw_lock; + enum sdw_slave_status status[SDW_MAX_DEVICES + 1]; + int num_din_ports; int num_dout_ports; -- cgit v1.2.3 From 81ff58ff71ad9dcddf5caffcf912cde6589d07bd Mon Sep 17 00:00:00 2001 From: Vijendar Mukunda Date: Tue, 21 Mar 2023 10:38:59 +0530 Subject: soundwire: amd: add runtime pm ops for AMD SoundWire manager driver Add support for runtime pm ops for AMD SoundWire manager driver. Signed-off-by: Vijendar Mukunda Signed-off-by: Mastan Katragadda Reviewed-by: Pierre-Louis Bossart Link: https://lore.kernel.org/lkml/20230227154801.50319-7-Vijendar.Mukunda@amd.com Link: https://lore.kernel.org/r/20230321050901.115439-7-Vijendar.Mukunda@amd.com Signed-off-by: Vinod Koul --- include/linux/soundwire/sdw_amd.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include/linux') diff --git a/include/linux/soundwire/sdw_amd.h b/include/linux/soundwire/sdw_amd.h index df60bc0de6fc..ceecad74aef9 100644 --- a/include/linux/soundwire/sdw_amd.h +++ b/include/linux/soundwire/sdw_amd.h @@ -8,6 +8,21 @@ #include +/* AMD pm_runtime quirk definitions */ + +/* + * Force the clock to stop(ClockStopMode0) when suspend callback + * is invoked. + */ +#define AMD_SDW_CLK_STOP_MODE 1 + +/* + * Stop the bus when runtime suspend/system level suspend callback + * is invoked. If set, a complete bus reset and re-enumeration will + * be performed when the bus restarts. In-band wake interrupts are + * not supported in this mode. + */ +#define AMD_SDW_POWER_OFF_MODE 2 #define ACP_SDW0 0 #define ACP_SDW1 1 @@ -57,6 +72,7 @@ struct sdw_amd_dai_runtime { * @instance: SoundWire manager instance * @quirks: SoundWire manager quirks * @wake_en_mask: wake enable mask per SoundWire manager + * @clk_stopped: flag set to true when clock is stopped * @power_mode_mask: flag interprets amd SoundWire manager power mode * @dai_runtime_array: dai runtime array */ @@ -86,6 +102,7 @@ struct amd_sdw_manager { u32 quirks; u32 wake_en_mask; u32 power_mode_mask; + bool clk_stopped; struct sdw_amd_dai_runtime **dai_runtime_array; }; -- cgit v1.2.3 From 13186dae182ab1a2a52a53424672f49cf3e81f9b Mon Sep 17 00:00:00 2001 From: Benjamin Bara Date: Wed, 5 Apr 2023 19:14:34 +0200 Subject: regulator: da9063: add voltage monitoring registers Add the definitions for the registers responsible for voltage monitoring. Add a voltage monitor enable bitfield per regulator. Reviewed-by: Matti Vaittinen Reviewed-by: Adam Ward Signed-off-by: Benjamin Bara Link: https://lore.kernel.org/r/20230403-da9063-disable-unused-v3-1-cc4dc698864c@skidata.com Signed-off-by: Mark Brown --- include/linux/mfd/da9063/registers.h | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/da9063/registers.h b/include/linux/mfd/da9063/registers.h index 6e0f66a2e727..7b8364bd08a0 100644 --- a/include/linux/mfd/da9063/registers.h +++ b/include/linux/mfd/da9063/registers.h @@ -1040,6 +1040,29 @@ /* DA9063_REG_CONFIG_J (addr=0x10F) */ #define DA9063_TWOWIRE_TO 0x40 +/* DA9063_REG_MON_REG_2 (addr=0x115) */ +#define DA9063_LDO1_MON_EN 0x01 +#define DA9063_LDO2_MON_EN 0x02 +#define DA9063_LDO3_MON_EN 0x04 +#define DA9063_LDO4_MON_EN 0x08 +#define DA9063_LDO5_MON_EN 0x10 +#define DA9063_LDO6_MON_EN 0x20 +#define DA9063_LDO7_MON_EN 0x40 +#define DA9063_LDO8_MON_EN 0x80 + +/* DA9063_REG_MON_REG_3 (addr=0x116) */ +#define DA9063_LDO9_MON_EN 0x01 +#define DA9063_LDO10_MON_EN 0x02 +#define DA9063_LDO11_MON_EN 0x04 + +/* DA9063_REG_MON_REG_4 (addr=0x117) */ +#define DA9063_BCORE1_MON_EN 0x04 +#define DA9063_BCORE2_MON_EN 0x08 +#define DA9063_BPRO_MON_EN 0x10 +#define DA9063_BIO_MON_EN 0x20 +#define DA9063_BMEM_MON_EN 0x40 +#define DA9063_BPERI_MON_EN 0x80 + /* DA9063_REG_MON_REG_5 (addr=0x116) */ #define DA9063_MON_A8_IDX_MASK 0x07 #define DA9063_MON_A8_IDX_NONE 0x00 -- cgit v1.2.3 From 7d6d2dd326a8a8d32091e9748f3428dd3be68367 Mon Sep 17 00:00:00 2001 From: Martin Blumenstingl Date: Wed, 5 Apr 2023 22:07:26 +0200 Subject: mmc: sdio: add Realtek SDIO vendor ID and various wifi device IDs MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add the SDIO vendor ID for Realtek and some device IDs extracted from their GPL vendor driver. This will be useful in the future when the rtw88 driver gains support for these chips. Acked-by: Ulf Hansson Reviewed-by: Ping-Ke Shih Reviewed-by: Pali Rohár Signed-off-by: Martin Blumenstingl Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20230405200729.632435-7-martin.blumenstingl@googlemail.com --- include/linux/mmc/sdio_ids.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmc/sdio_ids.h b/include/linux/mmc/sdio_ids.h index 0e4ef9c5127a..66f503ed2448 100644 --- a/include/linux/mmc/sdio_ids.h +++ b/include/linux/mmc/sdio_ids.h @@ -112,6 +112,15 @@ #define SDIO_VENDOR_ID_MICROCHIP_WILC 0x0296 #define SDIO_DEVICE_ID_MICROCHIP_WILC1000 0x5347 +#define SDIO_VENDOR_ID_REALTEK 0x024c +#define SDIO_DEVICE_ID_REALTEK_RTW8723BS 0xb723 +#define SDIO_DEVICE_ID_REALTEK_RTW8821BS 0xb821 +#define SDIO_DEVICE_ID_REALTEK_RTW8822BS 0xb822 +#define SDIO_DEVICE_ID_REALTEK_RTW8821CS 0xc821 +#define SDIO_DEVICE_ID_REALTEK_RTW8822CS 0xc822 +#define SDIO_DEVICE_ID_REALTEK_RTW8723DS 0xd723 +#define SDIO_DEVICE_ID_REALTEK_RTW8821DS 0xd821 + #define SDIO_VENDOR_ID_SIANO 0x039a #define SDIO_DEVICE_ID_SIANO_NOVA_B0 0x0201 #define SDIO_DEVICE_ID_SIANO_NICE 0x0202 -- cgit v1.2.3 From 528407b1e0ea51260fff2cc8b669c632a65d7a09 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Tue, 11 Apr 2023 12:06:05 +0100 Subject: io_uring/rsrc: consolidate node caching We store one pre-allocated rsrc node in ->rsrc_backup_node, merge it with ->rsrc_node_cache. Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/6d5410e51ccd29be7a716be045b51d6b371baef6.1681210788.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- include/linux/io_uring_types.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h index fa621a508a01..40cab420b1bd 100644 --- a/include/linux/io_uring_types.h +++ b/include/linux/io_uring_types.h @@ -326,7 +326,6 @@ struct io_ring_ctx { struct io_restriction restrictions; /* slow path rsrc auxilary data, used by update/register */ - struct io_rsrc_node *rsrc_backup_node; struct io_mapped_ubuf *dummy_ubuf; struct io_rsrc_data *file_data; struct io_rsrc_data *buf_data; -- cgit v1.2.3 From 59d3efd27c11c59b32291e5ebc307bed2edb65ee Mon Sep 17 00:00:00 2001 From: Martin Willi Date: Tue, 11 Apr 2023 09:43:19 +0200 Subject: rtnetlink: Restore RTM_NEW/DELLINK notification behavior The commits referenced below allows userspace to use the NLM_F_ECHO flag for RTM_NEW/DELLINK operations to receive unicast notifications for the affected link. Prior to these changes, applications may have relied on multicast notifications to learn the same information without specifying the NLM_F_ECHO flag. For such applications, the mentioned commits changed the behavior for requests not using NLM_F_ECHO. Multicast notifications are still received, but now use the portid of the requester and the sequence number of the request instead of zero values used previously. For the application, this message may be unexpected and likely handled as a response to the NLM_F_ACKed request, especially if it uses the same socket to handle requests and notifications. To fix existing applications relying on the old notification behavior, set the portid and sequence number in the notification only if the request included the NLM_F_ECHO flag. This restores the old behavior for applications not using it, but allows unicasted notifications for others. Fixes: f3a63cce1b4f ("rtnetlink: Honour NLM_F_ECHO flag in rtnl_delete_link") Fixes: d88e136cab37 ("rtnetlink: Honour NLM_F_ECHO flag in rtnl_newlink_create") Signed-off-by: Martin Willi Acked-by: Guillaume Nault Acked-by: Hangbin Liu Link: https://lore.kernel.org/r/20230411074319.24133-1-martin@strongswan.org Signed-off-by: Jakub Kicinski --- include/linux/rtnetlink.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index 92ad75549e9c..b6e6378dcbbd 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -25,7 +25,8 @@ void rtmsg_ifinfo_newnet(int type, struct net_device *dev, unsigned int change, struct sk_buff *rtmsg_ifinfo_build_skb(int type, struct net_device *dev, unsigned change, u32 event, gfp_t flags, int *new_nsid, - int new_ifindex, u32 portid, u32 seq); + int new_ifindex, u32 portid, + const struct nlmsghdr *nlh); void rtmsg_ifinfo_send(struct sk_buff *skb, struct net_device *dev, gfp_t flags, u32 portid, const struct nlmsghdr *nlh); -- cgit v1.2.3 From edde9e70bb48301c853299f1bd7c0aa0745a38ea Mon Sep 17 00:00:00 2001 From: Sagi Grimberg Date: Wed, 22 Mar 2023 14:37:03 +0200 Subject: blk-mq-rdma: remove queue mapping helper for rdma devices No rdma device exposes its irq vectors affinity today. So the only mapping that we have left, is the default blk_mq_map_queues, which we fallback to anyways. Also fixup the only consumer of this helper (nvme-rdma). Remove this now dead code. Signed-off-by: Sagi Grimberg Acked-by: Keith Busch Signed-off-by: Christoph Hellwig --- include/linux/blk-mq-rdma.h | 11 ----------- 1 file changed, 11 deletions(-) delete mode 100644 include/linux/blk-mq-rdma.h (limited to 'include/linux') diff --git a/include/linux/blk-mq-rdma.h b/include/linux/blk-mq-rdma.h deleted file mode 100644 index 53b58c610e76..000000000000 --- a/include/linux/blk-mq-rdma.h +++ /dev/null @@ -1,11 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _LINUX_BLK_MQ_RDMA_H -#define _LINUX_BLK_MQ_RDMA_H - -struct blk_mq_tag_set; -struct ib_device; - -void blk_mq_rdma_map_queues(struct blk_mq_queue_map *map, - struct ib_device *dev, int first_vec); - -#endif /* _LINUX_BLK_MQ_RDMA_H */ -- cgit v1.2.3 From 6539cffa94957241c096099a57d05fa4d8c7db8a Mon Sep 17 00:00:00 2001 From: Radu Rendec Date: Wed, 12 Apr 2023 14:57:57 -0400 Subject: cacheinfo: Add arch specific early level initializer This patch gives architecture specific code the ability to initialize the cache level and allocate cacheinfo memory early, when cache level initialization runs on the primary CPU for all possible CPUs. This is part of a patch series that attempts to further the work in commit 5944ce092b97 ("arch_topology: Build cacheinfo from primary CPU"). Previously, in the absence of any DT/ACPI cache info, architecture specific cache detection and info allocation for secondary CPUs would happen in non-preemptible context during early CPU initialization and trigger a "BUG: sleeping function called from invalid context" splat on an RT kernel. More specifically, this patch adds the early_cache_level() function, which is called by fetch_cache_info() as a fallback when the number of cache leaves cannot be extracted from DT/ACPI. In the default generic (weak) implementation, this new function returns -ENOENT, which preserves the original behavior for architectures that do not implement the function. Since early detection can get the number of cache leaves wrong in some cases*, additional logic is added to still call init_cache_level() later on the secondary CPU, therefore giving the architecture specific code an opportunity to go back and fix the initial guess. Again, the original behavior is preserved for architectures that do not implement the new function. * For example, on arm64, CLIDR_EL1 detection works only when it runs on the current CPU. In other words, a CPU cannot detect the cache depth for any other CPU than itself. Signed-off-by: Radu Rendec Reviewed-by: Pierre Gondois Link: https://lore.kernel.org/r/20230412185759.755408-2-rrendec@redhat.com Signed-off-by: Sudeep Holla --- include/linux/cacheinfo.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cacheinfo.h b/include/linux/cacheinfo.h index 908e19d17f49..6147b2672555 100644 --- a/include/linux/cacheinfo.h +++ b/include/linux/cacheinfo.h @@ -76,9 +76,11 @@ struct cpu_cacheinfo { unsigned int num_levels; unsigned int num_leaves; bool cpu_map_populated; + bool early_ci_levels; }; struct cpu_cacheinfo *get_cpu_cacheinfo(unsigned int cpu); +int early_cache_level(unsigned int cpu); int init_cache_level(unsigned int cpu); int init_of_cache_level(unsigned int cpu); int populate_cache_leaves(unsigned int cpu); -- cgit v1.2.3 From 79d9622d622d49d6c14c51edec2059b8591e7975 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Patrik=20Dahlstr=C3=B6m?= Date: Sat, 8 Apr 2023 13:48:19 +0200 Subject: iio: adc: palmas: remove adc_wakeupX_data MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit It does not seem to be used by anyone and later patches in this series are made simpler by first removing this. There is now a lot of dead code that cannot be reached, until later patches revive it. Arguably, this is preferred over removing the code only to add it again. Signed-off-by: Patrik Dahlström Link: https://lore.kernel.org/r/20230408114825.824505-4-risca@dalakolonin.se Signed-off-by: Jonathan Cameron --- include/linux/mfd/palmas.h | 8 -------- 1 file changed, 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/palmas.h b/include/linux/mfd/palmas.h index 117d02708439..eda1ffd99c1a 100644 --- a/include/linux/mfd/palmas.h +++ b/include/linux/mfd/palmas.h @@ -128,12 +128,6 @@ struct palmas_pmic_driver_data { struct regulator_config config); }; -struct palmas_adc_wakeup_property { - int adc_channel_number; - int adc_high_threshold; - int adc_low_threshold; -}; - struct palmas_gpadc_platform_data { /* Channel 3 current source is only enabled during conversion */ int ch3_current; /* 0: off; 1: 10uA; 2: 400uA; 3: 800 uA */ @@ -152,8 +146,6 @@ struct palmas_gpadc_platform_data { int start_polarity; int auto_conversion_period_ms; - struct palmas_adc_wakeup_property *adc_wakeup1_data; - struct palmas_adc_wakeup_property *adc_wakeup2_data; }; struct palmas_reg_init { -- cgit v1.2.3 From 33719b57f52e5b761234373f98f55f4e036d61c9 Mon Sep 17 00:00:00 2001 From: Andrew Halaney Date: Tue, 11 Apr 2023 15:04:06 -0500 Subject: net: stmmac: dwmac4: Allow platforms to specify some DMA/MTL offsets Some platforms have dwmac4 implementations that have a different address space layout than the default, resulting in the need to define their own DMA/MTL offsets. Extend the functions to allow a platform driver to indicate what its addresses are, overriding the defaults. Signed-off-by: Andrew Halaney Reviewed-by: Jesse Brandeburg Tested-by: Brian Masney Signed-off-by: Paolo Abeni --- include/linux/stmmac.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include/linux') diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index dafa001e9e7a..225751a8fd8e 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -186,6 +186,24 @@ struct stmmac_safety_feature_cfg { u32 tmouten; }; +/* Addresses that may be customized by a platform */ +struct dwmac4_addrs { + u32 dma_chan; + u32 dma_chan_offset; + u32 mtl_chan; + u32 mtl_chan_offset; + u32 mtl_ets_ctrl; + u32 mtl_ets_ctrl_offset; + u32 mtl_txq_weight; + u32 mtl_txq_weight_offset; + u32 mtl_send_slp_cred; + u32 mtl_send_slp_cred_offset; + u32 mtl_high_cred; + u32 mtl_high_cred_offset; + u32 mtl_low_cred; + u32 mtl_low_cred_offset; +}; + struct plat_stmmacenet_data { int bus_id; int phy_addr; @@ -274,5 +292,6 @@ struct plat_stmmacenet_data { bool use_phy_wol; bool sph_disable; bool serdes_up_after_phy_linkup; + const struct dwmac4_addrs *dwmac4_addrs; }; #endif -- cgit v1.2.3 From 0af4d704ba8e5ee632b6e65015ffe4d229c1a9a9 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Wed, 12 Apr 2023 13:56:36 +0200 Subject: pwm: Delete deprecated functions pwm_request() and pwm_free() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Since commit 5a7fbe452ad9 ("backlight: pwm_bl: Drop support for legacy PWM probing") the last user of pwm_request() and pwm_free() is gone. So remove these functions that were deprecated over 10 years ago in commit 8138d2ddbcca ("pwm: Add table-based lookup for static mappings"). Signed-off-by: Uwe Kleine-König [thierry.reding@gmail.com: clean up a bit after removal] Signed-off-by: Thierry Reding --- include/linux/pwm.h | 13 ------------- 1 file changed, 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pwm.h b/include/linux/pwm.h index 7b7b93b6fb81..04ae1d9073a7 100644 --- a/include/linux/pwm.h +++ b/include/linux/pwm.h @@ -309,8 +309,6 @@ struct pwm_chip { #if IS_ENABLED(CONFIG_PWM) /* PWM user APIs */ -struct pwm_device *pwm_request(int pwm_id, const char *label); -void pwm_free(struct pwm_device *pwm); int pwm_apply_state(struct pwm_device *pwm, const struct pwm_state *state); int pwm_adjust_config(struct pwm_device *pwm); @@ -410,17 +408,6 @@ struct pwm_device *devm_fwnode_pwm_get(struct device *dev, struct fwnode_handle *fwnode, const char *con_id); #else -static inline struct pwm_device *pwm_request(int pwm_id, const char *label) -{ - might_sleep(); - return ERR_PTR(-ENODEV); -} - -static inline void pwm_free(struct pwm_device *pwm) -{ - might_sleep(); -} - static inline int pwm_apply_state(struct pwm_device *pwm, const struct pwm_state *state) { -- cgit v1.2.3 From 4668c7a2940d134bea50058e138591b97485c5da Mon Sep 17 00:00:00 2001 From: Akinobu Mita Date: Mon, 27 Mar 2023 23:37:32 +0900 Subject: fault-inject: allow configuration via configfs This provides a helper function to allow configuration of fault-injection for configfs-based drivers. The config items created by this function have the same interface as the one created under debugfs by fault_create_debugfs_attr(). Signed-off-by: Akinobu Mita Link: https://lore.kernel.org/r/20230327143733.14599-2-akinobu.mita@gmail.com Signed-off-by: Jens Axboe --- include/linux/fault-inject.h | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fault-inject.h b/include/linux/fault-inject.h index 444236dadcf0..481abf530b3c 100644 --- a/include/linux/fault-inject.h +++ b/include/linux/fault-inject.h @@ -6,6 +6,7 @@ #include #include +#include #include #include @@ -65,6 +66,27 @@ static inline struct dentry *fault_create_debugfs_attr(const char *name, #endif /* CONFIG_FAULT_INJECTION_DEBUG_FS */ +#ifdef CONFIG_FAULT_INJECTION_CONFIGFS + +struct fault_config { + struct fault_attr attr; + struct config_group group; +}; + +void fault_config_init(struct fault_config *config, const char *name); + +#else /* CONFIG_FAULT_INJECTION_CONFIGFS */ + +struct fault_config { +}; + +static inline void fault_config_init(struct fault_config *config, + const char *name) +{ +} + +#endif /* CONFIG_FAULT_INJECTION_CONFIGFS */ + #endif /* CONFIG_FAULT_INJECTION */ struct kmem_cache; -- cgit v1.2.3 From 4fdeb847130229dc94befa241461669c7359776b Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 31 Mar 2023 16:59:07 +0200 Subject: wifi: ieee80211: clean up public action codes WLAN_PUBLIC_ACTION_FTM_RESPONSE is duplicated with WLAN_PUB_ACTION_FTM, but that might better be called WLAN_PUB_ACTION_FTM_RESPONSE; clean up here. Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 11 +++-------- 1 file changed, 3 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 2463bdd2a382..0583b2b0ce1f 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -9,7 +9,7 @@ * Copyright (c) 2006, Michael Wu * Copyright (c) 2013 - 2014 Intel Mobile Communications GmbH * Copyright (c) 2016 - 2017 Intel Deutschland GmbH - * Copyright (c) 2018 - 2022 Intel Corporation + * Copyright (c) 2018 - 2023 Intel Corporation */ #ifndef LINUX_IEEE80211_H @@ -3557,11 +3557,6 @@ enum ieee80211_unprotected_wnm_actioncode { WLAN_UNPROTECTED_WNM_ACTION_TIMING_MEASUREMENT_RESPONSE = 1, }; -/* Public action codes */ -enum ieee80211_public_actioncode { - WLAN_PUBLIC_ACTION_FTM_RESPONSE = 33, -}; - /* Security key length */ enum ieee80211_key_len { WLAN_KEY_LEN_WEP40 = 5, @@ -3653,7 +3648,7 @@ enum ieee80211_pub_actioncode { WLAN_PUB_ACTION_NETWORK_CHANNEL_CONTROL = 30, WLAN_PUB_ACTION_WHITE_SPACE_MAP_ANN = 31, WLAN_PUB_ACTION_FTM_REQUEST = 32, - WLAN_PUB_ACTION_FTM = 33, + WLAN_PUB_ACTION_FTM_RESPONSE = 33, WLAN_PUB_ACTION_FILS_DISCOVERY = 34, }; @@ -4383,7 +4378,7 @@ static inline bool ieee80211_is_ftm(struct sk_buff *skb) return false; if (mgmt->u.action.u.ftm.action_code == - WLAN_PUBLIC_ACTION_FTM_RESPONSE && + WLAN_PUB_ACTION_FTM_RESPONSE && skb->len >= offsetofend(typeof(*mgmt), u.action.u.ftm)) return true; -- cgit v1.2.3 From 2c9abe653bc5134eeab411c46dde008d8a1c37b0 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 31 Mar 2023 16:59:08 +0200 Subject: wifi: ieee80211: correctly mark FTM frames non-bufferable The checks of whether or not a frame is bufferable were not taking into account that some action frames aren't, such as FTM. Check this, which requires some changes to the function ieee80211_is_bufferable_mmpdu() since we need the whole skb for the checks now. Reviewed-by: Ilan Peer Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 52 ++++++++++++++++++++++++++++++++++------------- 1 file changed, 38 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 0583b2b0ce1f..c4cf296e7eaf 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -782,20 +782,6 @@ static inline bool ieee80211_is_any_nullfunc(__le16 fc) return (ieee80211_is_nullfunc(fc) || ieee80211_is_qos_nullfunc(fc)); } -/** - * ieee80211_is_bufferable_mmpdu - check if frame is bufferable MMPDU - * @fc: frame control field in little-endian byteorder - */ -static inline bool ieee80211_is_bufferable_mmpdu(__le16 fc) -{ - /* IEEE 802.11-2012, definition of "bufferable management frame"; - * note that this ignores the IBSS special case. */ - return ieee80211_is_mgmt(fc) && - (ieee80211_is_action(fc) || - ieee80211_is_disassoc(fc) || - ieee80211_is_deauth(fc)); -} - /** * ieee80211_is_first_frag - check if IEEE80211_SCTL_FRAG is not set * @seq_ctrl: frame sequence control bytes in little-endian byteorder @@ -4132,6 +4118,44 @@ static inline u8 *ieee80211_get_DA(struct ieee80211_hdr *hdr) return hdr->addr1; } +/** + * ieee80211_is_bufferable_mmpdu - check if frame is bufferable MMPDU + * @skb: the skb to check, starting with the 802.11 header + */ +static inline bool ieee80211_is_bufferable_mmpdu(struct sk_buff *skb) +{ + struct ieee80211_mgmt *mgmt = (void *)skb->data; + __le16 fc = mgmt->frame_control; + + /* + * IEEE 802.11 REVme D2.0 definition of bufferable MMPDU; + * note that this ignores the IBSS special case. + */ + if (!ieee80211_is_mgmt(fc)) + return false; + + if (ieee80211_is_disassoc(fc) || ieee80211_is_deauth(fc)) + return true; + + if (!ieee80211_is_action(fc)) + return false; + + if (skb->len < offsetofend(typeof(*mgmt), u.action.u.ftm.action_code)) + return true; + + /* action frame - additionally check for non-bufferable FTM */ + + if (mgmt->u.action.category != WLAN_CATEGORY_PUBLIC && + mgmt->u.action.category != WLAN_CATEGORY_PROTECTED_DUAL_OF_ACTION) + return true; + + if (mgmt->u.action.u.ftm.action_code == WLAN_PUB_ACTION_FTM_REQUEST || + mgmt->u.action.u.ftm.action_code == WLAN_PUB_ACTION_FTM_RESPONSE) + return false; + + return true; +} + /** * _ieee80211_is_robust_mgmt_frame - check if frame is a robust management frame * @hdr: the frame (buffer must include at least the first octet of payload) -- cgit v1.2.3 From 0cd917a4a8ace70ff9082d797c899f6bf10de910 Mon Sep 17 00:00:00 2001 From: Jesper Dangaard Brouer Date: Wed, 12 Apr 2023 21:48:40 +0200 Subject: xdp: rss hash types representation MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The RSS hash type specifies what portion of packet data NIC hardware used when calculating RSS hash value. The RSS types are focused on Internet traffic protocols at OSI layers L3 and L4. L2 (e.g. ARP) often get hash value zero and no RSS type. For L3 focused on IPv4 vs. IPv6, and L4 primarily TCP vs UDP, but some hardware supports SCTP. Hardware RSS types are differently encoded for each hardware NIC. Most hardware represent RSS hash type as a number. Determining L3 vs L4 often requires a mapping table as there often isn't a pattern or sorting according to ISO layer. The patch introduce a XDP RSS hash type (enum xdp_rss_hash_type) that contains both BITs for the L3/L4 types, and combinations to be used by drivers for their mapping tables. The enum xdp_rss_type_bits get exposed to BPF via BTF, and it is up to the BPF-programmer to match using these defines. This proposal change the kfunc API bpf_xdp_metadata_rx_hash() adding a pointer value argument for provide the RSS hash type. Change signature for all xmo_rx_hash calls in drivers to make it compile. The RSS type implementations for each driver comes as separate patches. Fixes: 3d76a4d3d4e5 ("bpf: XDP metadata RX kfuncs") Signed-off-by: Jesper Dangaard Brouer Acked-by: Toke Høiland-Jørgensen Acked-by: Stanislav Fomichev Link: https://lore.kernel.org/r/168132892042.340624.582563003880565460.stgit@firesoul Signed-off-by: Alexei Starovoitov --- include/linux/netdevice.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 470085b121d3..c35f04f636f1 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1624,7 +1624,8 @@ struct net_device_ops { struct xdp_metadata_ops { int (*xmo_rx_timestamp)(const struct xdp_md *ctx, u64 *timestamp); - int (*xmo_rx_hash)(const struct xdp_md *ctx, u32 *hash); + int (*xmo_rx_hash)(const struct xdp_md *ctx, u32 *hash, + enum xdp_rss_hash_type *rss_type); }; /** -- cgit v1.2.3 From 67f245c2ec0af17d7a90c78910e28bc8b206297c Mon Sep 17 00:00:00 2001 From: Jesper Dangaard Brouer Date: Wed, 12 Apr 2023 21:48:45 +0200 Subject: mlx5: bpf_xdp_metadata_rx_hash add xdp rss hash type MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Update API for bpf_xdp_metadata_rx_hash() with arg for xdp rss hash type via mapping table. The mlx5 hardware can also identify and RSS hash IPSEC. This indicate hash includes SPI (Security Parameters Index) as part of IPSEC hash. Extend xdp core enum xdp_rss_hash_type with IPSEC hash type. Fixes: bc8d405b1ba9 ("net/mlx5e: Support RX XDP metadata") Signed-off-by: Jesper Dangaard Brouer Acked-by: Toke Høiland-Jørgensen Acked-by: Stanislav Fomichev Link: https://lore.kernel.org/r/168132892548.340624.11185734579430124869.stgit@firesoul Signed-off-by: Alexei Starovoitov --- include/linux/mlx5/device.h | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 71b06ebad402..1db19a9d26e3 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -36,6 +36,7 @@ #include #include #include +#include #if defined(__LITTLE_ENDIAN) #define MLX5_SET_HOST_ENDIANNESS 0 @@ -980,14 +981,23 @@ enum { }; enum { - CQE_RSS_HTYPE_IP = 0x3 << 2, + CQE_RSS_HTYPE_IP = GENMASK(3, 2), /* cqe->rss_hash_type[3:2] - IP destination selected for hash * (00 = none, 01 = IPv4, 10 = IPv6, 11 = Reserved) */ - CQE_RSS_HTYPE_L4 = 0x3 << 6, + CQE_RSS_IP_NONE = 0x0, + CQE_RSS_IPV4 = 0x1, + CQE_RSS_IPV6 = 0x2, + CQE_RSS_RESERVED = 0x3, + + CQE_RSS_HTYPE_L4 = GENMASK(7, 6), /* cqe->rss_hash_type[7:6] - L4 destination selected for hash * (00 = none, 01 = TCP. 10 = UDP, 11 = IPSEC.SPI */ + CQE_RSS_L4_NONE = 0x0, + CQE_RSS_L4_TCP = 0x1, + CQE_RSS_L4_UDP = 0x2, + CQE_RSS_L4_IPSEC = 0x3, }; enum { -- cgit v1.2.3 From 8cbc82f3ec0d58961cf9c1e5d99e56741f4bf134 Mon Sep 17 00:00:00 2001 From: Kefeng Wang Date: Mon, 20 Mar 2023 15:40:10 +0800 Subject: mm: memory-failure: Move memory failure sysctls to its own file The sysctl_memory_failure_early_kill and memory_failure_recovery are only used in memory-failure.c, move them to its own file. Acked-by: Naoya Horiguchi Signed-off-by: Kefeng Wang [mcgrof: fix by adding empty ctl entry, this caused a crash] Signed-off-by: Luis Chamberlain --- include/linux/mm.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 1f79667824eb..98da268b834a 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3442,8 +3442,6 @@ int mf_dax_kill_procs(struct address_space *mapping, pgoff_t index, extern int memory_failure(unsigned long pfn, int flags); extern void memory_failure_queue_kick(int cpu); extern int unpoison_memory(unsigned long pfn); -extern int sysctl_memory_failure_early_kill; -extern int sysctl_memory_failure_recovery; extern void shake_page(struct page *p); extern atomic_long_t num_poisoned_pages __read_mostly; extern int soft_offline_page(unsigned long pfn, int flags); -- cgit v1.2.3 From 48fe8ab8d5a39c7bc49cb41d0ad92c75f48a9550 Mon Sep 17 00:00:00 2001 From: Minghao Chi Date: Tue, 28 Mar 2023 14:46:28 +0800 Subject: mm: compaction: move compaction sysctl to its own file This moves all compaction sysctls to its own file. Move sysctl to where the functionality truly belongs to improve readability, reduce merge conflicts, and facilitate maintenance. I use x86_defconfig and linux-next-20230327 branch $ make defconfig;make all -jn CONFIG_COMPACTION=y add/remove: 1/0 grow/shrink: 1/1 up/down: 350/-256 (94) Function old new delta vm_compaction - 320 +320 kcompactd_init 180 210 +30 vm_table 2112 1856 -256 Total: Before=21119987, After=21120081, chg +0.00% Despite the addition of 94 bytes the patch still seems a worthwile cleanup. Link: https://lore.kernel.org/lkml/067f7347-ba10-5405-920c-0f5f985c84f4@suse.cz/ Signed-off-by: Minghao Chi Acked-by: Vlastimil Babka Signed-off-by: Luis Chamberlain --- include/linux/compaction.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compaction.h b/include/linux/compaction.h index 52a9ff65faee..a6e512cfb670 100644 --- a/include/linux/compaction.h +++ b/include/linux/compaction.h @@ -81,13 +81,6 @@ static inline unsigned long compact_gap(unsigned int order) } #ifdef CONFIG_COMPACTION -extern unsigned int sysctl_compaction_proactiveness; -extern int sysctl_compaction_handler(struct ctl_table *table, int write, - void *buffer, size_t *length, loff_t *ppos); -extern int compaction_proactiveness_sysctl_handler(struct ctl_table *table, - int write, void *buffer, size_t *length, loff_t *ppos); -extern int sysctl_extfrag_threshold; -extern int sysctl_compact_unevictable_allowed; extern unsigned int extfrag_for_order(struct zone *zone, unsigned int order); extern int fragmentation_index(struct zone *zone, unsigned int order); -- cgit v1.2.3 From 82174a0a9c5cf36a3e421fc1d2c86998d8023f61 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Wed, 29 Mar 2023 10:52:00 -0500 Subject: of: Move of_device_get_match_data() declaration of_device.h mostly defines functions for bus drivers whereas of_device_get_match_data() is used by drivers. Let's move it to of.h. Link: https://lore.kernel.org/r/20230329-dt-cpu-header-cleanups-v1-3-581e2605fe47@kernel.org Signed-off-by: Rob Herring --- include/linux/of.h | 6 ++++++ include/linux/of_device.h | 7 ------- 2 files changed, 6 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/of.h b/include/linux/of.h index 36cf94596eba..6dc47d4c4612 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -371,6 +371,7 @@ extern int of_n_addr_cells(struct device_node *np); extern int of_n_size_cells(struct device_node *np); extern const struct of_device_id *of_match_node( const struct of_device_id *matches, const struct device_node *node); +extern const void *of_device_get_match_data(const struct device *dev); extern int of_modalias_node(struct device_node *node, char *modalias, int len); extern void of_print_phandle_args(const char *msg, const struct of_phandle_args *args); extern int __of_parse_phandle_with_args(const struct device_node *np, @@ -852,6 +853,11 @@ static inline phys_addr_t of_dma_get_max_cpu_address(struct device_node *np) return PHYS_ADDR_MAX; } +static inline const void *of_device_get_match_data(const struct device *dev) +{ + return NULL; +} + #define of_match_ptr(_ptr) NULL #define of_match_node(_matches, _node) NULL #endif /* CONFIG_OF */ diff --git a/include/linux/of_device.h b/include/linux/of_device.h index e4aa61cb2bd0..a54df77370fa 100644 --- a/include/linux/of_device.h +++ b/include/linux/of_device.h @@ -26,8 +26,6 @@ static inline int of_driver_match_device(struct device *dev, return of_match_device(drv->of_match_table, dev) != NULL; } -extern const void *of_device_get_match_data(const struct device *dev); - extern ssize_t of_device_modalias(struct device *dev, char *str, ssize_t len); extern int of_device_request_module(struct device *dev); @@ -63,11 +61,6 @@ static inline int of_driver_match_device(struct device *dev, static inline void of_device_uevent(const struct device *dev, struct kobj_uevent_env *env) { } -static inline const void *of_device_get_match_data(const struct device *dev) -{ - return NULL; -} - static inline int of_device_modalias(struct device *dev, char *str, ssize_t len) { -- cgit v1.2.3 From b58fa269c59d0f401ca569c661c6d7f3e1a20eeb Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Wed, 29 Mar 2023 10:52:01 -0500 Subject: of: Move CPU node related functions to their own file drivers/of/base.c is quite long and we've accumulated a number of CPU node functions. Let's move them to a new file, cpu.c, along with the lone of_cpu_device_node_get() in of_device.h. Moving the declaration has no effect yet as of.h is included by of_device.h. This serves as preparation to disentangle the includes in of_device.h and of_platform.h. Reviewed-by: Sudeep Holla Link: https://lore.kernel.org/r/20230329-dt-cpu-header-cleanups-v1-4-581e2605fe47@kernel.org Signed-off-by: Rob Herring --- include/linux/of.h | 19 ++++++++++++------- include/linux/of_device.h | 14 -------------- 2 files changed, 12 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/include/linux/of.h b/include/linux/of.h index 6dc47d4c4612..ad3614537054 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -359,6 +359,8 @@ extern const void *of_get_property(const struct device_node *node, const char *name, int *lenp); extern struct device_node *of_get_cpu_node(int cpu, unsigned int *thread); +extern struct device_node *of_cpu_device_node_get(int cpu); +extern int of_cpu_node_to_id(struct device_node *np); extern struct device_node *of_get_next_cpu_node(struct device_node *prev); extern struct device_node *of_get_cpu_state_node(struct device_node *cpu_node, int index); @@ -438,8 +440,6 @@ const char *of_prop_next_string(struct property *prop, const char *cur); bool of_console_check(struct device_node *dn, char *name, int index); -extern int of_cpu_node_to_id(struct device_node *np); - int of_map_id(struct device_node *np, u32 id, const char *map_name, const char *map_mask_name, struct device_node **target, u32 *id_out); @@ -634,6 +634,16 @@ static inline struct device_node *of_get_cpu_node(int cpu, return NULL; } +static inline struct device_node *of_cpu_device_node_get(int cpu) +{ + return NULL; +} + +static inline int of_cpu_node_to_id(struct device_node *np) +{ + return -ENODEV; +} + static inline struct device_node *of_get_next_cpu_node(struct device_node *prev) { return NULL; @@ -836,11 +846,6 @@ static inline void of_property_clear_flag(struct property *p, unsigned long flag { } -static inline int of_cpu_node_to_id(struct device_node *np) -{ - return -ENODEV; -} - static inline int of_map_id(struct device_node *np, u32 id, const char *map_name, const char *map_mask_name, struct device_node **target, u32 *id_out) diff --git a/include/linux/of_device.h b/include/linux/of_device.h index a54df77370fa..fbe342fb729f 100644 --- a/include/linux/of_device.h +++ b/include/linux/of_device.h @@ -32,15 +32,6 @@ extern int of_device_request_module(struct device *dev); extern void of_device_uevent(const struct device *dev, struct kobj_uevent_env *env); extern int of_device_uevent_modalias(const struct device *dev, struct kobj_uevent_env *env); -static inline struct device_node *of_cpu_device_node_get(int cpu) -{ - struct device *cpu_dev; - cpu_dev = get_cpu_device(cpu); - if (!cpu_dev) - return of_get_cpu_node(cpu, NULL); - return of_node_get(cpu_dev->of_node); -} - int of_dma_configure_id(struct device *dev, struct device_node *np, bool force_dma, const u32 *id); @@ -84,11 +75,6 @@ static inline const struct of_device_id *of_match_device( return NULL; } -static inline struct device_node *of_cpu_device_node_get(int cpu) -{ - return NULL; -} - static inline int of_dma_configure_id(struct device *dev, struct device_node *np, bool force_dma, -- cgit v1.2.3 From 2e8fff668dc14e758ae80a898832eb9b6d60c463 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Wed, 29 Mar 2023 10:52:02 -0500 Subject: of: Drop unnecessary includes in headers Drop unnecessary includes in DT headers. Some simply aren't needed and some can be replaced with forward declarations. Link: https://lore.kernel.org/r/20230329-dt-cpu-header-cleanups-v1-5-581e2605fe47@kernel.org Signed-off-by: Rob Herring --- include/linux/of.h | 5 ++--- include/linux/of_device.h | 3 ++- include/linux/of_platform.h | 5 +++-- 3 files changed, 7 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/of.h b/include/linux/of.h index ad3614537054..bc2eb39dcf75 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -16,13 +16,10 @@ #include #include #include -#include -#include #include #include #include -#include typedef u32 phandle; typedef u32 ihandle; @@ -1521,6 +1518,8 @@ enum of_reconfig_change { OF_RECONFIG_CHANGE_REMOVE, }; +struct notifier_block; + #ifdef CONFIG_OF_DYNAMIC extern int of_reconfig_notifier_register(struct notifier_block *); extern int of_reconfig_notifier_unregister(struct notifier_block *); diff --git a/include/linux/of_device.h b/include/linux/of_device.h index fbe342fb729f..bafe50150d24 100644 --- a/include/linux/of_device.h +++ b/include/linux/of_device.h @@ -7,9 +7,10 @@ #include /* temporary until merge */ #include -#include struct device; +struct of_device_id; +struct kobj_uevent_env; #ifdef CONFIG_OF extern const struct of_device_id *of_match_device( diff --git a/include/linux/of_platform.h b/include/linux/of_platform.h index 8ac5cb933dc3..d8045bcfc35e 100644 --- a/include/linux/of_platform.h +++ b/include/linux/of_platform.h @@ -6,12 +6,13 @@ * */ -#include #include -#include #include #include +struct device; +struct of_device_id; + /** * struct of_dev_auxdata - lookup table entry for device names & platform_data * @compatible: compatible value of node to match against node -- cgit v1.2.3 From 21bb32b155dfe7b40e5e6545f2df53f81f2e69cc Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Wed, 29 Mar 2023 10:52:11 -0500 Subject: cpufreq: Adjust includes to remove of_device.h Now that of_cpu_device_node_get() is defined in of.h, of_device.h is just implicitly including other includes, and is no longer needed. Adjust the include files with what was implicitly included by of_device.h (cpu.h and of.h) and drop including of_device.h. Acked-by: Viresh Kumar Acked-by: Rafael J. Wysocki Link: https://lore.kernel.org/r/20230329-dt-cpu-header-cleanups-v1-14-581e2605fe47@kernel.org Signed-off-by: Rob Herring --- include/linux/cpufreq.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 65623233ab2f..3ac4a10d4651 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -15,7 +15,6 @@ #include #include #include -#include #include #include #include -- cgit v1.2.3 From 7e09cb0b84ac5d17086a65ca21479dfec600a232 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Wed, 29 Mar 2023 10:52:16 -0500 Subject: of: Drop cpu.h include from of_device.h Now that all users which had an implicit dependency on cpu.h have been fixed. the cpu.h include can be dropped from of_device.h Link: https://lore.kernel.org/r/20230329-dt-cpu-header-cleanups-v1-19-581e2605fe47@kernel.org Signed-off-by: Rob Herring --- include/linux/of_device.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/of_device.h b/include/linux/of_device.h index bafe50150d24..33f0ca348a62 100644 --- a/include/linux/of_device.h +++ b/include/linux/of_device.h @@ -2,7 +2,6 @@ #ifndef _LINUX_OF_DEVICE_H #define _LINUX_OF_DEVICE_H -#include #include #include /* temporary until merge */ -- cgit v1.2.3 From c75a79491835c50ca61938ae1ebd3ba5598f7410 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Tue, 28 Mar 2023 15:15:57 -0500 Subject: of/address: Add of_range_to_resource() helper A few users need to convert a specific "ranges" entry into a struct resource. Add a helper to similar to of_address_to_resource(). The existing of_pci_range_to_resource() helper isn't really PCI specific, so it can be used with the CONFIG_PCI check dropped. Link: https://lore.kernel.org/r/20230328-dt-address-helpers-v1-2-e2456c3e77ab@kernel.org Signed-off-by: Rob Herring --- include/linux/of_address.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/of_address.h b/include/linux/of_address.h index 376671594746..1d005439f026 100644 --- a/include/linux/of_address.h +++ b/include/linux/of_address.h @@ -68,6 +68,8 @@ extern int of_pci_address_to_resource(struct device_node *dev, int bar, extern int of_pci_range_to_resource(struct of_pci_range *range, struct device_node *np, struct resource *res); +extern int of_range_to_resource(struct device_node *np, int index, + struct resource *res); extern bool of_dma_is_coherent(struct device_node *np); #else /* CONFIG_OF_ADDRESS */ static inline void __iomem *of_io_request_and_map(struct device_node *device, @@ -120,6 +122,12 @@ static inline int of_pci_range_to_resource(struct of_pci_range *range, return -ENOSYS; } +static inline int of_range_to_resource(struct device_node *np, int index, + struct resource *res) +{ + return -ENOSYS; +} + static inline bool of_dma_is_coherent(struct device_node *np) { return false; -- cgit v1.2.3 From b50c788a56964a900ebcc817c8a5ad35ddad87b6 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Tue, 28 Mar 2023 15:15:59 -0500 Subject: of/address: Add of_range_count() helper Some users need a count of the number of ranges entries before iterating over the entries. Typically this is for allocating some data structure based on the size. Add a helper, of_range_count(), to get the count. The helper must be called with an struct of_range_parser initialized by of_range_parser_init(). Link: https://lore.kernel.org/r/20230328-dt-address-helpers-v1-4-e2456c3e77ab@kernel.org Signed-off-by: Rob Herring --- include/linux/of_address.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/of_address.h b/include/linux/of_address.h index 1d005439f026..5292f62c1baa 100644 --- a/include/linux/of_address.h +++ b/include/linux/of_address.h @@ -35,6 +35,22 @@ struct of_pci_range { for (; of_pci_range_parser_one(parser, range);) #define for_each_of_range for_each_of_pci_range +/* + * of_range_count - Get the number of "ranges" or "dma-ranges" entries + * @parser: Parser state initialized by of_range_parser_init() + * + * Returns the number of entries or 0 if none. + * + * Note that calling this within or after the for_each_of_range() iterator will + * be inaccurate giving the number of entries remaining. + */ +static inline int of_range_count(const struct of_range_parser *parser) +{ + if (!parser || !parser->node || !parser->range || parser->range == parser->end) + return 0; + return (parser->end - parser->range) / (parser->na + parser->pna + parser->ns); +} + /* Translate a DMA address from device space to CPU space */ extern u64 of_translate_dma_address(struct device_node *dev, const __be32 *in_addr); -- cgit v1.2.3 From ff61bacd77f258bd2ed145efb69e5449b115d4fe Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Tue, 28 Mar 2023 15:16:00 -0500 Subject: of/address: Add of_property_read_reg() helper Add a helper, of_property_read_reg(), to read "reg" entries untranslated address and size. This function is intended mainly for cases with an untranslatable "reg" address (i.e. not MMIO). There's also a few translatable cases such as address cells containing a bus chip-select number. Link: https://lore.kernel.org/r/20230328-dt-address-helpers-v1-5-e2456c3e77ab@kernel.org Signed-off-by: Rob Herring --- include/linux/of_address.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/of_address.h b/include/linux/of_address.h index 5292f62c1baa..26a19daf0d09 100644 --- a/include/linux/of_address.h +++ b/include/linux/of_address.h @@ -72,6 +72,8 @@ void __iomem *of_io_request_and_map(struct device_node *device, extern const __be32 *__of_get_address(struct device_node *dev, int index, int bar_no, u64 *size, unsigned int *flags); +int of_property_read_reg(struct device_node *np, int idx, u64 *addr, u64 *size); + extern int of_pci_range_parser_init(struct of_pci_range_parser *parser, struct device_node *node); extern int of_pci_dma_range_parser_init(struct of_pci_range_parser *parser, @@ -106,6 +108,11 @@ static inline const __be32 *__of_get_address(struct device_node *dev, int index, return NULL; } +static inline int of_property_read_reg(struct device_node *np, int idx, u64 *addr, u64 *size) +{ + return -ENOSYS; +} + static inline int of_pci_range_parser_init(struct of_pci_range_parser *parser, struct device_node *node) { -- cgit v1.2.3 From 987d2e0aaa55de40938435be760aa96428470fd6 Mon Sep 17 00:00:00 2001 From: Tiezhu Yang Date: Fri, 31 Mar 2023 17:15:52 +0800 Subject: module: Move is_arm_mapping_symbol() to module_symbol.h In order to avoid duplicated code, move is_arm_mapping_symbol() to include/linux/module_symbol.h, then remove is_arm_mapping_symbol() in the other places. Signed-off-by: Tiezhu Yang Signed-off-by: Luis Chamberlain --- include/linux/module_symbol.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) create mode 100644 include/linux/module_symbol.h (limited to 'include/linux') diff --git a/include/linux/module_symbol.h b/include/linux/module_symbol.h new file mode 100644 index 000000000000..9fa4173d0197 --- /dev/null +++ b/include/linux/module_symbol.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef _LINUX_MODULE_SYMBOL_H +#define _LINUX_MODULE_SYMBOL_H + +/* This ignores the intensely annoying "mapping symbols" found in ELF files. */ +static inline int is_arm_mapping_symbol(const char *str) +{ + if (str[0] == '.' && str[1] == 'L') + return true; + return str[0] == '$' && + (str[1] == 'a' || str[1] == 'd' || str[1] == 't' || str[1] == 'x') + && (str[2] == '\0' || str[2] == '.'); +} + +#endif /* _LINUX_MODULE_SYMBOL_H */ -- cgit v1.2.3 From 0a3bf86092c38f7b72c56c6901c78dd302411307 Mon Sep 17 00:00:00 2001 From: Tiezhu Yang Date: Fri, 31 Mar 2023 17:15:53 +0800 Subject: module: Ignore L0 and rename is_arm_mapping_symbol() The L0 symbol is generated when build module on LoongArch, ignore it in modpost and when looking at module symbols, otherwise we can not see the expected call trace. Now is_arm_mapping_symbol() is not only for ARM, in order to reflect the reality, rename is_arm_mapping_symbol() to is_mapping_symbol(). This is related with commit c17a2538704f ("mksysmap: Fix the mismatch of 'L0' symbols in System.map"). (1) Simple test case [loongson@linux hello]$ cat hello.c #include #include #include static void test_func(void) { pr_info("This is a test\n"); dump_stack(); } static int __init hello_init(void) { pr_warn("Hello, world\n"); test_func(); return 0; } static void __exit hello_exit(void) { pr_warn("Goodbye\n"); } module_init(hello_init); module_exit(hello_exit); MODULE_LICENSE("GPL"); [loongson@linux hello]$ cat Makefile obj-m:=hello.o ccflags-y += -g -Og all: make -C /lib/modules/$(shell uname -r)/build/ M=$(PWD) modules clean: make -C /lib/modules/$(shell uname -r)/build/ M=$(PWD) clean (2) Test environment system: LoongArch CLFS 5.5 https://github.com/sunhaiyong1978/CLFS-for-LoongArch/releases/tag/5.0 It needs to update grub to avoid booting error "invalid magic number". kernel: 6.3-rc1 with loongson3_defconfig + CONFIG_DYNAMIC_FTRACE=y (3) Test result Without this patch: [root@linux hello]# insmod hello.ko [root@linux hello]# dmesg ... Hello, world This is a test ... Call Trace: [<9000000000223728>] show_stack+0x68/0x18c [<90000000013374cc>] dump_stack_lvl+0x60/0x88 [] L0\x01+0x20/0x2c [hello] [] L0\x01+0x20/0x30 [hello] [<900000000022097c>] do_one_initcall+0x88/0x288 [<90000000002df890>] do_init_module+0x54/0x200 [<90000000002e1e18>] __do_sys_finit_module+0xc4/0x114 [<90000000013382e8>] do_syscall+0x7c/0x94 [<9000000000221e3c>] handle_syscall+0xbc/0x158 With this patch: [root@linux hello]# insmod hello.ko [root@linux hello]# dmesg ... Hello, world This is a test ... Call Trace: [<9000000000223728>] show_stack+0x68/0x18c [<90000000013374cc>] dump_stack_lvl+0x60/0x88 [] test_func+0x28/0x34 [hello] [] hello_init+0x28/0x38 [hello] [<900000000022097c>] do_one_initcall+0x88/0x288 [<90000000002df890>] do_init_module+0x54/0x200 [<90000000002e1e18>] __do_sys_finit_module+0xc4/0x114 [<90000000013382e8>] do_syscall+0x7c/0x94 [<9000000000221e3c>] handle_syscall+0xbc/0x158 Signed-off-by: Tiezhu Yang Tested-by: Youling Tang # for LoongArch Signed-off-by: Luis Chamberlain --- include/linux/module_symbol.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/module_symbol.h b/include/linux/module_symbol.h index 9fa4173d0197..7ace7ba30203 100644 --- a/include/linux/module_symbol.h +++ b/include/linux/module_symbol.h @@ -3,10 +3,12 @@ #define _LINUX_MODULE_SYMBOL_H /* This ignores the intensely annoying "mapping symbols" found in ELF files. */ -static inline int is_arm_mapping_symbol(const char *str) +static inline int is_mapping_symbol(const char *str) { if (str[0] == '.' && str[1] == 'L') return true; + if (str[0] == 'L' && str[1] == '0') + return true; return str[0] == '$' && (str[1] == 'a' || str[1] == 'd' || str[1] == 't' || str[1] == 'x') && (str[2] == '\0' || str[2] == '.'); -- cgit v1.2.3 From 1cf3bfc60f9836f44da951f58b6ae24680484b35 Mon Sep 17 00:00:00 2001 From: Ilya Leoshkevich Date: Thu, 13 Apr 2023 01:06:32 +0200 Subject: bpf: Support 64-bit pointers to kfuncs test_ksyms_module fails to emit a kfunc call targeting a module on s390x, because the verifier stores the difference between kfunc address and __bpf_call_base in bpf_insn.imm, which is s32, and modules are roughly (1 << 42) bytes away from the kernel on s390x. Fix by keeping BTF id in bpf_insn.imm for BPF_PSEUDO_KFUNC_CALLs, and storing the absolute address in bpf_kfunc_desc. Introduce bpf_jit_supports_far_kfunc_call() in order to limit this new behavior to the s390x JIT. Otherwise other JITs need to be modified, which is not desired. Introduce bpf_get_kfunc_addr() instead of exposing both find_kfunc_desc() and struct bpf_kfunc_desc. In addition to sorting kfuncs by imm, also sort them by offset, in order to handle conflicting imms from different modules. Do this on all architectures in order to simplify code. Factor out resolving specialized kfuncs (XPD and dynptr) from fixup_kfunc_call(). This was required in the first place, because fixup_kfunc_call() uses find_kfunc_desc(), which returns a const pointer, so it's not possible to modify kfunc addr without stripping const, which is not nice. It also removes repetition of code like: if (bpf_jit_supports_far_kfunc_call()) desc->addr = func; else insn->imm = BPF_CALL_IMM(func); and separates kfunc_desc_tab fixups from kfunc_call fixups. Suggested-by: Jiri Olsa Signed-off-by: Ilya Leoshkevich Acked-by: Jiri Olsa Link: https://lore.kernel.org/r/20230412230632.885985-1-iii@linux.ibm.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 10 ++++++++++ include/linux/filter.h | 1 + 2 files changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 2c6095bd7d69..88845aadc47d 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -2295,6 +2295,9 @@ bool bpf_prog_has_kfunc_call(const struct bpf_prog *prog); const struct btf_func_model * bpf_jit_find_kfunc_model(const struct bpf_prog *prog, const struct bpf_insn *insn); +int bpf_get_kfunc_addr(const struct bpf_prog *prog, u32 func_id, + u16 btf_fd_idx, u8 **func_addr); + struct bpf_core_ctx { struct bpf_verifier_log *log; const struct btf *btf; @@ -2545,6 +2548,13 @@ bpf_jit_find_kfunc_model(const struct bpf_prog *prog, return NULL; } +static inline int +bpf_get_kfunc_addr(const struct bpf_prog *prog, u32 func_id, + u16 btf_fd_idx, u8 **func_addr) +{ + return -ENOTSUPP; +} + static inline bool unprivileged_ebpf_enabled(void) { return false; diff --git a/include/linux/filter.h b/include/linux/filter.h index 5364b0c52c1d..bbce89937fde 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -920,6 +920,7 @@ void bpf_jit_compile(struct bpf_prog *prog); 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_helper_changes_pkt_data(void *func); static inline bool bpf_dump_raw_ok(const struct cred *cred) -- cgit v1.2.3 From d54151aa0f4b5c89561705a00d8a5ebb4230028c Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Tue, 11 Apr 2023 21:01:49 +0300 Subject: net: ethtool: create and export ethtool_dev_mm_supported() Create a wrapper over __ethtool_dev_mm_supported() which also calls ethnl_ops_begin() and ethnl_ops_complete(). It can be used by other code layers, such as tc, to make sure that preemptible TCs are supported (this is true if an underlying MAC Merge layer exists). Signed-off-by: Vladimir Oltean Reviewed-by: Ferenc Fejes Reviewed-by: Simon Horman Signed-off-by: Jakub Kicinski --- include/linux/ethtool_netlink.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ethtool_netlink.h b/include/linux/ethtool_netlink.h index 17003b385756..fae0dfb9a9c8 100644 --- a/include/linux/ethtool_netlink.h +++ b/include/linux/ethtool_netlink.h @@ -39,6 +39,7 @@ void ethtool_aggregate_pause_stats(struct net_device *dev, struct ethtool_pause_stats *pause_stats); void ethtool_aggregate_rmon_stats(struct net_device *dev, struct ethtool_rmon_stats *rmon_stats); +bool ethtool_dev_mm_supported(struct net_device *dev); #else static inline int ethnl_cable_test_alloc(struct phy_device *phydev, u8 cmd) @@ -112,5 +113,10 @@ ethtool_aggregate_rmon_stats(struct net_device *dev, { } +static inline bool ethtool_dev_mm_supported(struct net_device *dev) +{ + return false; +} + #endif /* IS_ENABLED(CONFIG_ETHTOOL_NETLINK) */ #endif /* _LINUX_ETHTOOL_NETLINK_H_ */ -- cgit v1.2.3 From ef9f643a9f8b62bcbcc51f0e0af8599adc2e17ed Mon Sep 17 00:00:00 2001 From: Pierre Gondois Date: Fri, 14 Apr 2023 10:14:52 +0200 Subject: cacheinfo: Add use_arch[|_cache]_info field/function The cache information can be extracted from either a Device Tree (DT), the PPTT ACPI table, or arch registers (clidr_el1 for arm64). The clidr_el1 register is used only if DT/ACPI information is not available. It does not states how caches are shared among CPUs. Add a use_arch_cache_info field/function to identify when the DT/ACPI doesn't provide cache information. Use this information to assume L1 caches are privates and L2 and higher are shared among all CPUs. Signed-off-by: Pierre Gondois Link: https://lore.kernel.org/r/20230414081453.244787-5-pierre.gondois@arm.com Signed-off-by: Sudeep Holla --- include/linux/cacheinfo.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cacheinfo.h b/include/linux/cacheinfo.h index 6147b2672555..a5cfd44fab45 100644 --- a/include/linux/cacheinfo.h +++ b/include/linux/cacheinfo.h @@ -131,4 +131,10 @@ static inline int get_cpu_cacheinfo_id(int cpu, int level) return -1; } +#ifdef CONFIG_ARM64 +#define use_arch_cache_info() (true) +#else +#define use_arch_cache_info() (false) +#endif + #endif /* _LINUX_CACHEINFO_H */ -- cgit v1.2.3 From 01f727cdc4dbecd36c6722977ff9535f16c11751 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Mon, 3 Apr 2023 12:48:42 +0800 Subject: crypto: api - Move low-level functions into algapi.h A number of low-level functions were exposed in crypto.h. Move them into algapi.h (and internal.h). Signed-off-by: Herbert Xu --- include/linux/crypto.h | 30 +++--------------------------- 1 file changed, 3 insertions(+), 27 deletions(-) (limited to 'include/linux') diff --git a/include/linux/crypto.h b/include/linux/crypto.h index d57597ebef6e..fdfa3e8eda43 100644 --- a/include/linux/crypto.h +++ b/include/linux/crypto.h @@ -12,13 +12,10 @@ #ifndef _LINUX_CRYPTO_H #define _LINUX_CRYPTO_H -#include -#include -#include -#include +#include #include #include -#include +#include /* * Algorithm masks and types. @@ -158,10 +155,9 @@ #define CRYPTO_MINALIGN_ATTR __attribute__ ((__aligned__(CRYPTO_MINALIGN))) -struct scatterlist; -struct crypto_async_request; struct crypto_tfm; struct crypto_type; +struct module; typedef void (*crypto_completion_t)(void *req, int err); @@ -411,14 +407,6 @@ static inline void crypto_init_wait(struct crypto_wait *wait) init_completion(&wait->completion); } -/* - * Algorithm registration interface. - */ -int crypto_register_alg(struct crypto_alg *alg); -void crypto_unregister_alg(struct crypto_alg *alg); -int crypto_register_algs(struct crypto_alg *algs, int count); -void crypto_unregister_algs(struct crypto_alg *algs, int count); - /* * Algorithm query interface. */ @@ -459,8 +447,6 @@ static inline void crypto_free_tfm(struct crypto_tfm *tfm) return crypto_destroy_tfm(tfm, tfm); } -int alg_test(const char *driver, const char *alg, u32 type, u32 mask); - /* * Transform helpers which query the underlying algorithm. */ @@ -474,16 +460,6 @@ static inline const char *crypto_tfm_alg_driver_name(struct crypto_tfm *tfm) return tfm->__crt_alg->cra_driver_name; } -static inline int crypto_tfm_alg_priority(struct crypto_tfm *tfm) -{ - return tfm->__crt_alg->cra_priority; -} - -static inline u32 crypto_tfm_alg_type(struct crypto_tfm *tfm) -{ - return tfm->__crt_alg->cra_flags & CRYPTO_ALG_TYPE_MASK; -} - static inline unsigned int crypto_tfm_alg_blocksize(struct crypto_tfm *tfm) { return tfm->__crt_alg->cra_blocksize; -- cgit v1.2.3 From a19c61b06585f71c4dc1303fe6a3af79dfe33678 Mon Sep 17 00:00:00 2001 From: Mario Limonciello Date: Mon, 3 Apr 2023 13:32:12 -0500 Subject: crypto: ccp - Return doorbell status code as an argument If the doorbell failed to ring we return -EIO, but the caller can't determine why it failed. Pass the reason for the failure in an argument for caller to investigate. Suggested-by: Mark Hasemeyer Signed-off-by: Mario Limonciello Reviewed-by: Mark Hasemeyer Tested-by: Mark Hasemeyer Signed-off-by: Herbert Xu --- include/linux/psp-platform-access.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/psp-platform-access.h b/include/linux/psp-platform-access.h index 89df4549fada..1b661341d8f3 100644 --- a/include/linux/psp-platform-access.h +++ b/include/linux/psp-platform-access.h @@ -45,9 +45,9 @@ int psp_send_platform_access_msg(enum psp_platform_access_msg, struct psp_reques * -%EBUSY: mailbox in recovery or in use * -%ENODEV: driver not bound with PSP device * -%ETIMEDOUT: request timed out - * -%EIO: unknown error (see kernel log) + * -%EIO: error will be stored in result argument */ -int psp_ring_platform_doorbell(int msg); +int psp_ring_platform_doorbell(int msg, u32 *result); /** * psp_check_platform_access_status() - Checks whether platform features is ready -- cgit v1.2.3 From e223864f8257afde5e23eca4c006a0d69581a7a2 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Wed, 12 Apr 2023 11:10:45 -0300 Subject: iommu: Make iommu_release_device() static This is not called outside the core code, and indeed cannot be called correctly outside the bus notifier. Make it static. Signed-off-by: Jason Gunthorpe Reviewed-by: Robin Murphy Link: https://lore.kernel.org/r/0-v1-c3da18124d2d+56-rm_iommu_release_jgg@nvidia.com Signed-off-by: Joerg Roedel --- include/linux/iommu.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 54f535ff9868..c892e06f8357 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -699,7 +699,6 @@ static inline void dev_iommu_priv_set(struct device *dev, void *priv) } int iommu_probe_device(struct device *dev); -void iommu_release_device(struct device *dev); int iommu_dev_enable_feature(struct device *dev, enum iommu_dev_features f); int iommu_dev_disable_feature(struct device *dev, enum iommu_dev_features f); -- cgit v1.2.3 From f7f9c054a227ad4922070d748b1f4fc4b5657329 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Wed, 12 Apr 2023 11:11:58 -0300 Subject: iommu: Remove iommu_group_get_by_id() This is never called. Signed-off-by: Jason Gunthorpe Reviewed-by: Robin Murphy Link: https://lore.kernel.org/r/0-v1-60bbc66d7e92+24-rm_iommu_get_by_id_jgg@nvidia.com Signed-off-by: Joerg Roedel --- include/linux/iommu.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index c892e06f8357..7dbdd13d7ce0 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -460,7 +460,6 @@ extern bool iommu_present(struct bus_type *bus); extern bool device_iommu_capable(struct device *dev, enum iommu_cap cap); extern bool iommu_group_has_isolated_msi(struct iommu_group *group); extern struct iommu_domain *iommu_domain_alloc(struct bus_type *bus); -extern struct iommu_group *iommu_group_get_by_id(int id); extern void iommu_domain_free(struct iommu_domain *domain); extern int iommu_attach_device(struct iommu_domain *domain, struct device *dev); @@ -746,11 +745,6 @@ static inline struct iommu_domain *iommu_domain_alloc(struct bus_type *bus) return NULL; } -static inline struct iommu_group *iommu_group_get_by_id(int id) -{ - return NULL; -} - static inline void iommu_domain_free(struct iommu_domain *domain) { } -- cgit v1.2.3 From cc4cffc3c142d57df48c07851862444e1d33bdaa Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Fri, 7 Apr 2023 22:37:52 +0200 Subject: wifi: brcmfmac: add Cypress 43439 SDIO ids Add SDIO ids for use with the muRata 1YN (Cypress CYW43439). The odd thing about this is that the previous 1YN populated on M.2 card for evaluation purposes had BRCM SDIO vendor ID, while the chip populated on real hardware has a Cypress one. The device ID also differs between the two devices. But they are both 43439 otherwise, so add the IDs for both. On-device 1YN (43439), the new one, chip label reads "1YN": ``` /sys/.../mmc_host/mmc2/mmc2:0001 # cat vendor device 0x04b4 0xbd3d ``` EA M.2 evaluation board 1YN (43439), the old one, chip label reads "1YN ES1.4": ``` /sys/.../mmc_host/mmc0/mmc0:0001/# cat vendor device 0x02d0 0xa9a6 ``` Reviewed-by: Hans de Goede Cc: stable@vger.kernel.org Signed-off-by: Marek Vasut Reviewed-by: Simon Horman Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20230407203752.128539-1-marex@denx.de --- include/linux/mmc/sdio_ids.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mmc/sdio_ids.h b/include/linux/mmc/sdio_ids.h index 66f503ed2448..c653accdc7fd 100644 --- a/include/linux/mmc/sdio_ids.h +++ b/include/linux/mmc/sdio_ids.h @@ -74,10 +74,13 @@ #define SDIO_DEVICE_ID_BROADCOM_43362 0xa962 #define SDIO_DEVICE_ID_BROADCOM_43364 0xa9a4 #define SDIO_DEVICE_ID_BROADCOM_43430 0xa9a6 -#define SDIO_DEVICE_ID_BROADCOM_CYPRESS_43439 0xa9af +#define SDIO_DEVICE_ID_BROADCOM_43439 0xa9af #define SDIO_DEVICE_ID_BROADCOM_43455 0xa9bf #define SDIO_DEVICE_ID_BROADCOM_CYPRESS_43752 0xaae8 +#define SDIO_VENDOR_ID_CYPRESS 0x04b4 +#define SDIO_DEVICE_ID_BROADCOM_CYPRESS_43439 0xbd3d + #define SDIO_VENDOR_ID_MARVELL 0x02df #define SDIO_DEVICE_ID_MARVELL_LIBERTAS 0x9103 #define SDIO_DEVICE_ID_MARVELL_8688_WLAN 0x9104 -- cgit v1.2.3 From e0b081d17a9f4e5c0cbb0e5fbeb1abe3de0f7e4e Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Wed, 12 Apr 2023 10:24:07 -0700 Subject: sched: Fix KCSAN noinstr violation With KCSAN enabled, end_of_stack() can get out-of-lined. Force it inline. Fixes the following warnings: vmlinux.o: warning: objtool: check_stackleak_irqoff+0x2b: call to end_of_stack() leaves .noinstr.text section Signed-off-by: Josh Poimboeuf Signed-off-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/cc1b4d73d3a428a00d206242a68fdf99a934ca7b.1681320026.git.jpoimboe@kernel.org --- include/linux/sched/task_stack.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched/task_stack.h b/include/linux/sched/task_stack.h index 5e799a47431e..f158b025c175 100644 --- a/include/linux/sched/task_stack.h +++ b/include/linux/sched/task_stack.h @@ -23,7 +23,7 @@ static __always_inline void *task_stack_page(const struct task_struct *task) #define setup_thread_stack(new,old) do { } while(0) -static inline unsigned long *end_of_stack(const struct task_struct *task) +static __always_inline unsigned long *end_of_stack(const struct task_struct *task) { #ifdef CONFIG_STACK_GROWSUP return (unsigned long *)((unsigned long)task->stack + THREAD_SIZE) - 1; -- cgit v1.2.3 From e8deb00c0c4808654d1bf96a8f79cf1deb59b631 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Wed, 12 Apr 2023 10:24:06 -0700 Subject: context_tracking: Fix KCSAN noinstr violation With KCSAN enabled, even empty inline stubs can be out-of-lined. Force the context_tracking_guest_exit() stub inline. Fixes the following warnings: vmlinux.o: warning: objtool: vmx_vcpu_enter_exit+0x1be: call to context_tracking_guest_exit() leaves .noinstr.text section vmlinux.o: warning: objtool: svm_vcpu_enter_exit+0x85: call to context_tracking_guest_exit() leaves .noinstr.text section Signed-off-by: Josh Poimboeuf Signed-off-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/dc93f45abdec90c171108b4b590b7fff5790963c.1681320026.git.jpoimboe@kernel.org --- include/linux/context_tracking.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/context_tracking.h b/include/linux/context_tracking.h index d4afa8508a80..5ae3abd767b4 100644 --- a/include/linux/context_tracking.h +++ b/include/linux/context_tracking.h @@ -97,7 +97,7 @@ static inline int exception_enter(void) { return 0; } static inline void exception_exit(enum ctx_state prev_ctx) { } static inline int ct_state(void) { return -1; } static __always_inline bool context_tracking_guest_enter(void) { return false; } -static inline void context_tracking_guest_exit(void) { } +static __always_inline void context_tracking_guest_exit(void) { } #define CT_WARN_ON(cond) do { } while (0) #endif /* !CONFIG_CONTEXT_TRACKING_USER */ -- cgit v1.2.3 From 9ea7e6b62c2bd2f7bbfc3f10099df803002dd33b Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Wed, 12 Apr 2023 16:49:31 -0700 Subject: init: Mark [arch_call_]rest_init() __noreturn In preparation for improving objtool's handling of weak noreturn functions, mark start_kernel(), arch_call_rest_init(), and rest_init() __noreturn. Signed-off-by: Josh Poimboeuf Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Nick Desaulniers Link: https://lore.kernel.org/r/7194ed8a989a85b98d92e62df660f4a90435a723.1681342859.git.jpoimboe@kernel.org --- include/linux/start_kernel.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/start_kernel.h b/include/linux/start_kernel.h index 8b369a41c03c..864921e54c92 100644 --- a/include/linux/start_kernel.h +++ b/include/linux/start_kernel.h @@ -9,7 +9,7 @@ up something else. */ extern asmlinkage void __init start_kernel(void); -extern void __init arch_call_rest_init(void); -extern void __ref rest_init(void); +extern void __init __noreturn arch_call_rest_init(void); +extern void __ref __noreturn rest_init(void); #endif /* _LINUX_START_KERNEL_H */ -- cgit v1.2.3 From 25a6917ca63ad4470bf88535c56f0dec72b570fe Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Wed, 12 Apr 2023 16:49:32 -0700 Subject: init: Mark start_kernel() __noreturn Now that arch_call_rest_init() is __noreturn, mark its caller start_kernel() __noreturn. Signed-off-by: Josh Poimboeuf Signed-off-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/7069acf026a195f26a88061227fba5a3b0337b9a.1681342859.git.jpoimboe@kernel.org --- include/linux/start_kernel.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/start_kernel.h b/include/linux/start_kernel.h index 864921e54c92..a9806a44a605 100644 --- a/include/linux/start_kernel.h +++ b/include/linux/start_kernel.h @@ -8,7 +8,7 @@ /* Define the prototype for start_kernel here, rather than cluttering up something else. */ -extern asmlinkage void __init start_kernel(void); +extern asmlinkage void __init __noreturn start_kernel(void); extern void __init __noreturn arch_call_rest_init(void); extern void __ref __noreturn rest_init(void); -- cgit v1.2.3 From 7412a60decec2a6744cf773280ff17a0f89e8395 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Wed, 12 Apr 2023 16:49:35 -0700 Subject: cpu: Mark panic_smp_self_stop() __noreturn In preparation for improving objtool's handling of weak noreturn functions, mark panic_smp_self_stop() __noreturn. Signed-off-by: Josh Poimboeuf Signed-off-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/92d76ab5c8bf660f04fdcd3da1084519212de248.1681342859.git.jpoimboe@kernel.org --- include/linux/smp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/smp.h b/include/linux/smp.h index a80ab58ae3f1..2a737b39cf0a 100644 --- a/include/linux/smp.h +++ b/include/linux/smp.h @@ -59,7 +59,7 @@ int smp_call_function_single_async(int cpu, struct __call_single_data *csd); * Cpus stopping functions in panic. All have default weak definitions. * Architecture-dependent code may override them. */ -void panic_smp_self_stop(void); +void __noreturn panic_smp_self_stop(void); void nmi_panic_self_stop(struct pt_regs *regs); void crash_smp_send_stop(void); -- cgit v1.2.3 From 27dea14c7f05106f39850a9239874cd38703b405 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Wed, 12 Apr 2023 16:49:36 -0700 Subject: cpu: Mark nmi_panic_self_stop() __noreturn In preparation for improving objtool's handling of weak noreturn functions, mark nmi_panic_self_stop() __noreturn. Signed-off-by: Josh Poimboeuf Signed-off-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/316fc6dfab5a8c4e024c7185484a1ee5fb0afb79.1681342859.git.jpoimboe@kernel.org --- include/linux/smp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/smp.h b/include/linux/smp.h index 2a737b39cf0a..7b93504eed26 100644 --- a/include/linux/smp.h +++ b/include/linux/smp.h @@ -60,7 +60,7 @@ int smp_call_function_single_async(int cpu, struct __call_single_data *csd); * Architecture-dependent code may override them. */ void __noreturn panic_smp_self_stop(void); -void nmi_panic_self_stop(struct pt_regs *regs); +void __noreturn nmi_panic_self_stop(struct pt_regs *regs); void crash_smp_send_stop(void); /* -- cgit v1.2.3 From 13f6facf3faeed34ca381aef4c9b153c7aed3972 Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Fri, 14 Apr 2023 12:07:27 -0400 Subject: dm: allow targets to require splitting WRITE_ZEROES and SECURE_ERASE Introduce max_write_zeroes_granularity and max_secure_erase_granularity flags in the dm_target struct. If a target sets these then DM core will split IO of these operation types accordingly (in terms of max_write_zeroes_sectors and max_secure_erase_sectors respectively). Signed-off-by: Mike Snitzer --- include/linux/device-mapper.h | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index f2d9afb8a7e9..983f1f0402b5 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -359,11 +359,23 @@ struct dm_target { bool discards_supported:1; /* - * Set if this target requires that discards be split on both - * 'discard_granularity' and 'max_discard_sectors' boundaries. + * Set if this target requires that discards be split on + * 'max_discard_sectors' boundaries. */ bool max_discard_granularity:1; + /* + * Set if this target requires that secure_erases be split on + * 'max_secure_erase_sectors' boundaries. + */ + bool max_secure_erase_granularity:1; + + /* + * Set if this target requires that write_zeroes be split on + * 'max_write_zeroes_sectors' boundaries. + */ + bool max_write_zeroes_granularity:1; + /* * Set if we need to limit the number of in-flight bios when swapping. */ -- cgit v1.2.3 From f7995089c508a5a11b0491c7b348d5c07217a4e8 Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Fri, 14 Apr 2023 12:32:20 -0400 Subject: dm: unexport dm_get_queue_limits() There are no dm_get_queue_limits() callers outside of DM core and there shouldn't be. Also, remove its BUG_ON(!atomic_read(&md->holders)) to micro-optimize __process_abnormal_io(). Signed-off-by: Mike Snitzer --- include/linux/device-mapper.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index 983f1f0402b5..a52d2b9a6846 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -530,8 +530,6 @@ int __init dm_early_create(struct dm_ioctl *dmi, struct dm_target_spec **spec_array, char **target_params_array); -struct queue_limits *dm_get_queue_limits(struct mapped_device *md); - /* * Geometry functions. */ -- cgit v1.2.3 From 38e4614c27210e63aafad1bb2e4a427515e46d71 Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Wed, 29 Mar 2023 14:06:03 +0200 Subject: vfio: correct kdoc for ops structures Address minor omissions from kdoc for ops structures flagged by check-kdoc: ./scripts/kernel-doc -Werror -none include/linux/vfio.h include/linux/vfio.h:114: warning: Function parameter or member 'name' not described in 'vfio_device_ops' include/linux/vfio.h:143: warning: Cannot understand * @migration_set_state: Optional callback to change the migration state for on line 143 - I thought it was a doc line include/linux/vfio.h:168: warning: Cannot understand * @log_start: Optional callback to ask the device start DMA logging. on line 168 - I thought it was a doc line Signed-off-by: Simon Horman Link: https://lore.kernel.org/r/20230329120603.468031-1-horms@kernel.org Signed-off-by: Alex Williamson --- include/linux/vfio.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/vfio.h b/include/linux/vfio.h index 93134b023968..cb46050045c0 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -68,6 +68,7 @@ struct vfio_device { /** * struct vfio_device_ops - VFIO bus driver device callbacks * + * @name: Name of the device driver. * @init: initialize private fields in device structure * @release: Reclaim private fields in device structure * @bind_iommufd: Called when binding the device to an iommufd @@ -140,6 +141,8 @@ int vfio_iommufd_emulated_attach_ioas(struct vfio_device *vdev, u32 *pt_id); #endif /** + * struct vfio_migration_ops - VFIO bus device driver migration callbacks + * * @migration_set_state: Optional callback to change the migration state for * devices that support migration. It's mandatory for * VFIO_DEVICE_FEATURE_MIGRATION migration support. @@ -165,6 +168,8 @@ struct vfio_migration_ops { }; /** + * struct vfio_log_ops - VFIO bus device driver logging callbacks + * * @log_start: Optional callback to ask the device start DMA logging. * @log_stop: Optional callback to ask the device stop DMA logging. * @log_read_and_clear: Optional callback to ask the device read -- cgit v1.2.3 From 8c48eea3adf3119e0a3fc57bd31f6966f26ee784 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 12 Apr 2023 21:26:04 -0700 Subject: page_pool: allow caching from safely localized NAPI Recent patches to mlx5 mentioned a regression when moving from driver local page pool to only using the generic page pool code. Page pool has two recycling paths (1) direct one, which runs in safe NAPI context (basically consumer context, so producing can be lockless); and (2) via a ptr_ring, which takes a spin lock because the freeing can happen from any CPU; producer and consumer may run concurrently. Since the page pool code was added, Eric introduced a revised version of deferred skb freeing. TCP skbs are now usually returned to the CPU which allocated them, and freed in softirq context. This places the freeing (producing of pages back to the pool) enticingly close to the allocation (consumer). If we can prove that we're freeing in the same softirq context in which the consumer NAPI will run - lockless use of the cache is perfectly fine, no need for the lock. Let drivers link the page pool to a NAPI instance. If the NAPI instance is scheduled on the same CPU on which we're freeing - place the pages in the direct cache. With that and patched bnxt (XDP enabled to engage the page pool, sigh, bnxt really needs page pool work :() I see a 2.6% perf boost with a TCP stream test (app on a different physical core than softirq). The CPU use of relevant functions decreases as expected: page_pool_refill_alloc_cache 1.17% -> 0% _raw_spin_lock 2.41% -> 0.98% Only consider lockless path to be safe when NAPI is scheduled - in practice this should cover majority if not all of steady state workloads. It's usually the NAPI kicking in that causes the skb flush. The main case we'll miss out on is when application runs on the same CPU as NAPI. In that case we don't use the deferred skb free path. Reviewed-by: Tariq Toukan Acked-by: Jesper Dangaard Brouer Tested-by: Dragos Tatulea Signed-off-by: Jakub Kicinski --- include/linux/netdevice.h | 3 +++ include/linux/skbuff.h | 20 +++++++++++++------- 2 files changed, 16 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 96d27d558b0c..203c0df2046c 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -360,8 +360,11 @@ struct napi_struct { unsigned long gro_bitmask; int (*poll)(struct napi_struct *, int); #ifdef CONFIG_NETPOLL + /* CPU actively polling if netpoll is configured */ int poll_owner; #endif + /* CPU on which NAPI has been scheduled for processing */ + int list_owner; struct net_device *dev; struct gro_list gro_hash[GRO_HASH_BUCKETS]; struct sk_buff *skb; diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 494a23a976b0..a823ec3aa326 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3386,6 +3386,18 @@ static inline void skb_frag_ref(struct sk_buff *skb, int f) __skb_frag_ref(&skb_shinfo(skb)->frags[f]); } +static inline void +napi_frag_unref(skb_frag_t *frag, bool recycle, bool napi_safe) +{ + struct page *page = skb_frag_page(frag); + +#ifdef CONFIG_PAGE_POOL + if (recycle && page_pool_return_skb_page(page, napi_safe)) + return; +#endif + put_page(page); +} + /** * __skb_frag_unref - release a reference on a paged fragment. * @frag: the paged fragment @@ -3396,13 +3408,7 @@ static inline void skb_frag_ref(struct sk_buff *skb, int f) */ static inline void __skb_frag_unref(skb_frag_t *frag, bool recycle) { - struct page *page = skb_frag_page(frag); - -#ifdef CONFIG_PAGE_POOL - if (recycle && page_pool_return_skb_page(page)) - return; -#endif - put_page(page); + napi_frag_unref(frag, recycle, false); } /** -- cgit v1.2.3 From 4ea15b56f0810f0d8795d475db1bb74b3a7c1b2f Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Thu, 13 Apr 2023 15:28:08 +0100 Subject: io_uring/rsrc: use wq for quiescing Replace completions with waitqueues for rsrc data quiesce, the main wakeup condition is when data refs hit zero. Note that data refs are only changes under ->uring_lock, so we prepare before mutex_unlock() reacquire it after taking the lock back. This change will be needed in the next patch. Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/1d0dbc74b3b4fd67c8f01819e680c5e0da252956.1681395792.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- include/linux/io_uring_types.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h index 40cab420b1bd..5c9645319770 100644 --- a/include/linux/io_uring_types.h +++ b/include/linux/io_uring_types.h @@ -333,6 +333,7 @@ struct io_ring_ctx { /* protected by ->uring_lock */ struct list_head rsrc_ref_list; struct io_alloc_cache rsrc_node_cache; + struct wait_queue_head rsrc_quiesce_wq; struct list_head io_buffers_pages; -- cgit v1.2.3 From 0b222eeb6514ba6c3457b667fa4f3645032e1fc9 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Thu, 13 Apr 2023 15:28:10 +0100 Subject: io_uring/rsrc: remove rsrc_data refs Instead of waiting for rsrc_data->refs to be downed to zero, check whether there are rsrc nodes queued for completion, that's easier then maintaining references. Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/8e33fd143d83e11af3e386aea28eb6d6c6a1be10.1681395792.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- include/linux/io_uring_types.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h index 5c9645319770..1b2a20a42413 100644 --- a/include/linux/io_uring_types.h +++ b/include/linux/io_uring_types.h @@ -334,6 +334,7 @@ struct io_ring_ctx { struct list_head rsrc_ref_list; struct io_alloc_cache rsrc_node_cache; struct wait_queue_head rsrc_quiesce_wq; + unsigned rsrc_quiesce; struct list_head io_buffers_pages; -- cgit v1.2.3 From cd2a8079014aced27da9b2e669784f31680f1351 Mon Sep 17 00:00:00 2001 From: Dave Marchevsky Date: Sat, 15 Apr 2023 13:18:03 -0700 Subject: bpf: Remove btf_field_offs, use btf_record's fields instead The btf_field_offs struct contains (offset, size) for btf_record fields, sorted by offset. btf_field_offs is always used in conjunction with btf_record, which has btf_field 'fields' array with (offset, type), the latter of which btf_field_offs' size is derived from via btf_field_type_size. This patch adds a size field to struct btf_field and sorts btf_record's fields by offset, making it possible to get rid of btf_field_offs. Less data duplication and less code complexity results. Since btf_field_offs' lifetime closely followed the btf_record used to populate it, most complexity wins are from removal of initialization code like: if (btf_record_successfully_initialized) { foffs = btf_parse_field_offs(rec); if (IS_ERR_OR_NULL(foffs)) // free the btf_record and return err } Other changes in this patch are pretty mechanical: * foffs->field_off[i] -> rec->fields[i].offset * foffs->field_sz[i] -> rec->fields[i].size * Sort rec->fields in btf_parse_fields before returning * It's possible that this is necessary independently of other changes in this patch. btf_record_find in syscall.c expects btf_record's fields to be sorted by offset, yet there's no explicit sorting of them before this patch, record's fields are populated in the order they're read from BTF struct definition. BTF docs don't say anything about the sortedness of struct fields. * All functions taking struct btf_field_offs * input now instead take struct btf_record *. All callsites of these functions already have access to the correct btf_record. Signed-off-by: Dave Marchevsky Link: https://lore.kernel.org/r/20230415201811.343116-2-davemarchevsky@fb.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 44 +++++++++++++++++++------------------------- include/linux/btf.h | 2 -- 2 files changed, 19 insertions(+), 27 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 88845aadc47d..7888ed497432 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -210,6 +210,7 @@ struct btf_field_graph_root { struct btf_field { u32 offset; + u32 size; enum btf_field_type type; union { struct btf_field_kptr kptr; @@ -225,12 +226,6 @@ struct btf_record { struct btf_field fields[]; }; -struct btf_field_offs { - u32 cnt; - u32 field_off[BTF_FIELDS_MAX]; - u8 field_sz[BTF_FIELDS_MAX]; -}; - struct bpf_map { /* The first two cachelines with read-mostly members of which some * are also accessed in fast-path (e.g. ops, max_entries). @@ -257,7 +252,6 @@ struct bpf_map { struct obj_cgroup *objcg; #endif char name[BPF_OBJ_NAME_LEN]; - struct btf_field_offs *field_offs; /* The 3rd and 4th cacheline with misc members to avoid false sharing * particularly with refcounting. */ @@ -360,14 +354,14 @@ static inline bool btf_record_has_field(const struct btf_record *rec, enum btf_f return rec->field_mask & type; } -static inline void bpf_obj_init(const struct btf_field_offs *foffs, void *obj) +static inline void bpf_obj_init(const struct btf_record *rec, void *obj) { int i; - if (!foffs) + if (IS_ERR_OR_NULL(rec)) return; - for (i = 0; i < foffs->cnt; i++) - memset(obj + foffs->field_off[i], 0, foffs->field_sz[i]); + for (i = 0; i < rec->cnt; i++) + memset(obj + rec->fields[i].offset, 0, rec->fields[i].size); } /* 'dst' must be a temporary buffer and should not point to memory that is being @@ -379,7 +373,7 @@ static inline void bpf_obj_init(const struct btf_field_offs *foffs, void *obj) */ static inline void check_and_init_map_value(struct bpf_map *map, void *dst) { - bpf_obj_init(map->field_offs, dst); + bpf_obj_init(map->record, dst); } /* memcpy that is used with 8-byte aligned pointers, power-of-8 size and @@ -399,14 +393,14 @@ static inline void bpf_long_memcpy(void *dst, const void *src, u32 size) } /* copy everything but bpf_spin_lock, bpf_timer, and kptrs. There could be one of each. */ -static inline void bpf_obj_memcpy(struct btf_field_offs *foffs, +static inline void bpf_obj_memcpy(struct btf_record *rec, void *dst, void *src, u32 size, bool long_memcpy) { u32 curr_off = 0; int i; - if (likely(!foffs)) { + if (IS_ERR_OR_NULL(rec)) { if (long_memcpy) bpf_long_memcpy(dst, src, round_up(size, 8)); else @@ -414,49 +408,49 @@ static inline void bpf_obj_memcpy(struct btf_field_offs *foffs, return; } - for (i = 0; i < foffs->cnt; i++) { - u32 next_off = foffs->field_off[i]; + for (i = 0; i < rec->cnt; i++) { + u32 next_off = rec->fields[i].offset; u32 sz = next_off - curr_off; memcpy(dst + curr_off, src + curr_off, sz); - curr_off += foffs->field_sz[i] + sz; + curr_off += rec->fields[i].size + sz; } memcpy(dst + curr_off, src + curr_off, size - curr_off); } static inline void copy_map_value(struct bpf_map *map, void *dst, void *src) { - bpf_obj_memcpy(map->field_offs, dst, src, map->value_size, false); + bpf_obj_memcpy(map->record, dst, src, map->value_size, false); } static inline void copy_map_value_long(struct bpf_map *map, void *dst, void *src) { - bpf_obj_memcpy(map->field_offs, dst, src, map->value_size, true); + bpf_obj_memcpy(map->record, dst, src, map->value_size, true); } -static inline void bpf_obj_memzero(struct btf_field_offs *foffs, void *dst, u32 size) +static inline void bpf_obj_memzero(struct btf_record *rec, void *dst, u32 size) { u32 curr_off = 0; int i; - if (likely(!foffs)) { + if (IS_ERR_OR_NULL(rec)) { memset(dst, 0, size); return; } - for (i = 0; i < foffs->cnt; i++) { - u32 next_off = foffs->field_off[i]; + for (i = 0; i < rec->cnt; i++) { + u32 next_off = rec->fields[i].offset; u32 sz = next_off - curr_off; memset(dst + curr_off, 0, sz); - curr_off += foffs->field_sz[i] + sz; + curr_off += rec->fields[i].size + sz; } memset(dst + curr_off, 0, size - curr_off); } static inline void zero_map_value(struct bpf_map *map, void *dst) { - bpf_obj_memzero(map->field_offs, dst, map->value_size); + bpf_obj_memzero(map->record, dst, map->value_size); } void copy_map_value_locked(struct bpf_map *map, void *dst, void *src, diff --git a/include/linux/btf.h b/include/linux/btf.h index 495250162422..813227bff58a 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -113,7 +113,6 @@ struct btf_id_dtor_kfunc { struct btf_struct_meta { u32 btf_id; struct btf_record *record; - struct btf_field_offs *field_offs; }; struct btf_struct_metas { @@ -207,7 +206,6 @@ int btf_find_timer(const struct btf *btf, const struct btf_type *t); struct btf_record *btf_parse_fields(const struct btf *btf, const struct btf_type *t, u32 field_mask, u32 value_size); int btf_check_and_fixup_fields(const struct btf *btf, struct btf_record *rec); -struct btf_field_offs *btf_parse_field_offs(struct btf_record *rec); bool btf_type_is_void(const struct btf_type *t); s32 btf_find_by_name_kind(const struct btf *btf, const char *name, u8 kind); const struct btf_type *btf_type_skip_modifiers(const struct btf *btf, -- cgit v1.2.3 From d54730b50bae1f3119bd686d551d66f0fcc387ca Mon Sep 17 00:00:00 2001 From: Dave Marchevsky Date: Sat, 15 Apr 2023 13:18:04 -0700 Subject: bpf: Introduce opaque bpf_refcount struct and add btf_record plumbing A 'struct bpf_refcount' is added to the set of opaque uapi/bpf.h types meant for use in BPF programs. Similarly to other opaque types like bpf_spin_lock and bpf_rbtree_node, the verifier needs to know where in user-defined struct types a bpf_refcount can be located, so necessary btf_record plumbing is added to enable this. bpf_refcount is sized to hold a refcount_t. Similarly to bpf_spin_lock, the offset of a bpf_refcount is cached in btf_record as refcount_off in addition to being in the field array. Caching refcount_off makes sense for this field because further patches in the series will modify functions that take local kptrs (e.g. bpf_obj_drop) to change their behavior if the type they're operating on is refcounted. So enabling fast "is this type refcounted?" checks is desirable. No such verifier behavior changes are introduced in this patch, just logic to recognize 'struct bpf_refcount' in btf_record. Signed-off-by: Dave Marchevsky Link: https://lore.kernel.org/r/20230415201811.343116-3-davemarchevsky@fb.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 7888ed497432..be44d765b7a4 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -187,6 +187,7 @@ enum btf_field_type { BPF_RB_NODE = (1 << 7), BPF_GRAPH_NODE_OR_ROOT = BPF_LIST_NODE | BPF_LIST_HEAD | BPF_RB_NODE | BPF_RB_ROOT, + BPF_REFCOUNT = (1 << 8), }; typedef void (*btf_dtor_kfunc_t)(void *); @@ -223,6 +224,7 @@ struct btf_record { u32 field_mask; int spin_lock_off; int timer_off; + int refcount_off; struct btf_field fields[]; }; @@ -293,6 +295,8 @@ static inline const char *btf_field_type_name(enum btf_field_type type) return "bpf_rb_root"; case BPF_RB_NODE: return "bpf_rb_node"; + case BPF_REFCOUNT: + return "bpf_refcount"; default: WARN_ON_ONCE(1); return "unknown"; @@ -317,6 +321,8 @@ static inline u32 btf_field_type_size(enum btf_field_type type) return sizeof(struct bpf_rb_root); case BPF_RB_NODE: return sizeof(struct bpf_rb_node); + case BPF_REFCOUNT: + return sizeof(struct bpf_refcount); default: WARN_ON_ONCE(1); return 0; @@ -341,6 +347,8 @@ static inline u32 btf_field_type_align(enum btf_field_type type) return __alignof__(struct bpf_rb_root); case BPF_RB_NODE: return __alignof__(struct bpf_rb_node); + case BPF_REFCOUNT: + return __alignof__(struct bpf_refcount); default: WARN_ON_ONCE(1); return 0; -- cgit v1.2.3 From 1512217c47f0e8ea076dd0e67262e5a668a78f01 Mon Sep 17 00:00:00 2001 From: Dave Marchevsky Date: Sat, 15 Apr 2023 13:18:05 -0700 Subject: bpf: Support refcounted local kptrs in existing semantics A local kptr is considered 'refcounted' when it is of a type that has a bpf_refcount field. When such a kptr is created, its refcount should be initialized to 1; when destroyed, the object should be free'd only if a refcount decr results in 0 refcount. Existing logic always frees the underlying memory when destroying a local kptr, and 0-initializes all btf_record fields. This patch adds checks for "is local kptr refcounted?" and new logic for that case in the appropriate places. This patch focuses on changing existing semantics and thus conspicuously does _not_ provide a way for BPF programs in increment refcount. That follows later in the series. __bpf_obj_drop_impl is modified to do the right thing when it sees a refcounted type. Container types for graph nodes (list, tree, stashed in map) are migrated to use __bpf_obj_drop_impl as a destructor for their nodes instead of each having custom destruction code in their _free paths. Now that "drop" isn't a synonym for "free" when the type is refcounted it makes sense to centralize this logic. Signed-off-by: Dave Marchevsky Link: https://lore.kernel.org/r/20230415201811.343116-4-davemarchevsky@fb.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index be44d765b7a4..b065de2cfcea 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -370,6 +370,9 @@ static inline void bpf_obj_init(const struct btf_record *rec, void *obj) return; for (i = 0; i < rec->cnt; i++) memset(obj + rec->fields[i].offset, 0, rec->fields[i].size); + + if (rec->refcount_off >= 0) + refcount_set((refcount_t *)(obj + rec->refcount_off), 1); } /* 'dst' must be a temporary buffer and should not point to memory that is being -- cgit v1.2.3 From d2dcc67df910dd85253a701b6a5b747f955d28f5 Mon Sep 17 00:00:00 2001 From: Dave Marchevsky Date: Sat, 15 Apr 2023 13:18:07 -0700 Subject: bpf: Migrate bpf_rbtree_add and bpf_list_push_{front,back} to possibly fail Consider this code snippet: struct node { long key; bpf_list_node l; bpf_rb_node r; bpf_refcount ref; } int some_bpf_prog(void *ctx) { struct node *n = bpf_obj_new(/*...*/), *m; bpf_spin_lock(&glock); bpf_rbtree_add(&some_tree, &n->r, /* ... */); m = bpf_refcount_acquire(n); bpf_rbtree_add(&other_tree, &m->r, /* ... */); bpf_spin_unlock(&glock); /* ... */ } After bpf_refcount_acquire, n and m point to the same underlying memory, and that node's bpf_rb_node field is being used by the some_tree insert, so overwriting it as a result of the second insert is an error. In order to properly support refcounted nodes, the rbtree and list insert functions must be allowed to fail. This patch adds such support. The kfuncs bpf_rbtree_add, bpf_list_push_{front,back} are modified to return an int indicating success/failure, with 0 -> success, nonzero -> failure. bpf_obj_drop on failure ======================= Currently the only reason an insert can fail is the example above: the bpf_{list,rb}_node is already in use. When such a failure occurs, the insert kfuncs will bpf_obj_drop the input node. This allows the insert operations to logically fail without changing their verifier owning ref behavior, namely the unconditional release_reference of the input owning ref. With insert that always succeeds, ownership of the node is always passed to the collection, since the node always ends up in the collection. With a possibly-failed insert w/ bpf_obj_drop, ownership of the node is always passed either to the collection (success), or to bpf_obj_drop (failure). Regardless, it's correct to continue unconditionally releasing the input owning ref, as something is always taking ownership from the calling program on insert. Keeping owning ref behavior unchanged results in a nice default UX for insert functions that can fail. If the program's reaction to a failed insert is "fine, just get rid of this owning ref for me and let me go on with my business", then there's no reason to check for failure since that's default behavior. e.g.: long important_failures = 0; int some_bpf_prog(void *ctx) { struct node *n, *m, *o; /* all bpf_obj_new'd */ bpf_spin_lock(&glock); bpf_rbtree_add(&some_tree, &n->node, /* ... */); bpf_rbtree_add(&some_tree, &m->node, /* ... */); if (bpf_rbtree_add(&some_tree, &o->node, /* ... */)) { important_failures++; } bpf_spin_unlock(&glock); } If we instead chose to pass ownership back to the program on failed insert - by returning NULL on success or an owning ref on failure - programs would always have to do something with the returned ref on failure. The most likely action is probably "I'll just get rid of this owning ref and go about my business", which ideally would look like: if (n = bpf_rbtree_add(&some_tree, &n->node, /* ... */)) bpf_obj_drop(n); But bpf_obj_drop isn't allowed in a critical section and inserts must occur within one, so in reality error handling would become a hard-to-parse mess. For refcounted nodes, we can replicate the "pass ownership back to program on failure" logic with this patch's semantics, albeit in an ugly way: struct node *n = bpf_obj_new(/* ... */), *m; bpf_spin_lock(&glock); m = bpf_refcount_acquire(n); if (bpf_rbtree_add(&some_tree, &n->node, /* ... */)) { /* Do something with m */ } bpf_spin_unlock(&glock); bpf_obj_drop(m); bpf_refcount_acquire is used to simulate "return owning ref on failure". This should be an uncommon occurrence, though. Addition of two verifier-fixup'd args to collection inserts =========================================================== The actual bpf_obj_drop kfunc is bpf_obj_drop_impl(void *, struct btf_struct_meta *), with bpf_obj_drop macro populating the second arg with 0 and the verifier later filling in the arg during insn fixup. Because bpf_rbtree_add and bpf_list_push_{front,back} now might do bpf_obj_drop, these kfuncs need a btf_struct_meta parameter that can be passed to bpf_obj_drop_impl. Similarly, because the 'node' param to those insert functions is the bpf_{list,rb}_node within the node type, and bpf_obj_drop expects a pointer to the beginning of the node, the insert functions need to be able to find the beginning of the node struct. A second verifier-populated param is necessary: the offset of {list,rb}_node within the node type. These two new params allow the insert kfuncs to correctly call __bpf_obj_drop_impl: beginning_of_node = bpf_rb_node_ptr - offset if (already_inserted) __bpf_obj_drop_impl(beginning_of_node, btf_struct_meta->record); Similarly to other kfuncs with "hidden" verifier-populated params, the insert functions are renamed with _impl prefix and a macro is provided for common usage. For example, bpf_rbtree_add kfunc is now bpf_rbtree_add_impl and bpf_rbtree_add is now a macro which sets "hidden" args to 0. Due to the two new args BPF progs will need to be recompiled to work with the new _impl kfuncs. This patch also rewrites the "hidden argument" explanation to more directly say why the BPF program writer doesn't need to populate the arguments with anything meaningful. How does this new logic affect non-owning references? ===================================================== Currently, non-owning refs are valid until the end of the critical section in which they're created. We can make this guarantee because, if a non-owning ref exists, the referent was added to some collection. The collection will drop() its nodes when it goes away, but it can't go away while our program is accessing it, so that's not a problem. If the referent is removed from the collection in the same CS that it was added in, it can't be bpf_obj_drop'd until after CS end. Those are the only two ways to free the referent's memory and neither can happen until after the non-owning ref's lifetime ends. On first glance, having these collection insert functions potentially bpf_obj_drop their input seems like it breaks the "can't be bpf_obj_drop'd until after CS end" line of reasoning. But we care about the memory not being _freed_ until end of CS end, and a previous patch in the series modified bpf_obj_drop such that it doesn't free refcounted nodes until refcount == 0. So the statement can be more accurately rewritten as "can't be free'd until after CS end". We can prove that this rewritten statement holds for any non-owning reference produced by collection insert functions: * If the input to the insert function is _not_ refcounted * We have an owning reference to the input, and can conclude it isn't in any collection * Inserting a node in a collection turns owning refs into non-owning, and since our input type isn't refcounted, there's no way to obtain additional owning refs to the same underlying memory * Because our node isn't in any collection, the insert operation cannot fail, so bpf_obj_drop will not execute * If bpf_obj_drop is guaranteed not to execute, there's no risk of memory being free'd * Otherwise, the input to the insert function is refcounted * If the insert operation fails due to the node's list_head or rb_root already being in some collection, there was some previous successful insert which passed refcount to the collection * We have an owning reference to the input, it must have been acquired via bpf_refcount_acquire, which bumped the refcount * refcount must be >= 2 since there's a valid owning reference and the node is already in a collection * Insert triggering bpf_obj_drop will decr refcount to >= 1, never resulting in a free So although we may do bpf_obj_drop during the critical section, this will never result in memory being free'd, and no changes to non-owning ref logic are needed in this patch. Signed-off-by: Dave Marchevsky Link: https://lore.kernel.org/r/20230415201811.343116-6-davemarchevsky@fb.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf_verifier.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index f03852b89d28..3dd29a53b711 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -464,7 +464,12 @@ struct bpf_insn_aux_data { */ struct bpf_loop_inline_state loop_inline_state; }; - u64 obj_new_size; /* remember the size of type passed to bpf_obj_new to rewrite R1 */ + union { + /* remember the size of type passed to bpf_obj_new to rewrite R1 */ + u64 obj_new_size; + /* remember the offset of node field within type to rewrite */ + u64 insert_off; + }; struct btf_struct_meta *kptr_struct_meta; u64 map_key_state; /* constant (32 bit) key tracking for maps */ int ctx_field_size; /* the ctx field size for load insn, maybe 0 */ -- cgit v1.2.3 From 3e81740a90626024a9d9c6f9bfa3d36204dafefb Mon Sep 17 00:00:00 2001 From: Dave Marchevsky Date: Sat, 15 Apr 2023 13:18:10 -0700 Subject: bpf: Centralize btf_field-specific initialization logic All btf_fields in an object are 0-initialized by memset in bpf_obj_init. This might not be a valid initial state for some field types, in which case kfuncs that use the type will properly initialize their input if it's been 0-initialized. Some BPF graph collection types and kfuncs do this: bpf_list_{head,node} and bpf_rb_node. An earlier patch in this series added the bpf_refcount field, for which the 0 state indicates that the refcounted object should be free'd. bpf_obj_init treats this field specially, setting refcount to 1 instead of relying on scattered "refcount is 0? Must have just been initialized, let's set to 1" logic in kfuncs. This patch extends this treatment to list and rbtree field types, allowing most scattered initialization logic in kfuncs to be removed. Note that bpf_{list_head,rb_root} may be inside a BPF map, in which case they'll be 0-initialized without passing through the newly-added logic, so scattered initialization logic must remain for these collection root types. Signed-off-by: Dave Marchevsky Link: https://lore.kernel.org/r/20230415201811.343116-9-davemarchevsky@fb.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 33 +++++++++++++++++++++++++++++---- 1 file changed, 29 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index b065de2cfcea..18b592fde896 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -355,6 +355,34 @@ static inline u32 btf_field_type_align(enum btf_field_type type) } } +static inline void bpf_obj_init_field(const struct btf_field *field, void *addr) +{ + memset(addr, 0, field->size); + + switch (field->type) { + case BPF_REFCOUNT: + refcount_set((refcount_t *)addr, 1); + break; + case BPF_RB_NODE: + RB_CLEAR_NODE((struct rb_node *)addr); + break; + case BPF_LIST_HEAD: + case BPF_LIST_NODE: + INIT_LIST_HEAD((struct list_head *)addr); + break; + case BPF_RB_ROOT: + /* RB_ROOT_CACHED 0-inits, no need to do anything after memset */ + case BPF_SPIN_LOCK: + case BPF_TIMER: + case BPF_KPTR_UNREF: + case BPF_KPTR_REF: + break; + default: + WARN_ON_ONCE(1); + return; + } +} + static inline bool btf_record_has_field(const struct btf_record *rec, enum btf_field_type type) { if (IS_ERR_OR_NULL(rec)) @@ -369,10 +397,7 @@ static inline void bpf_obj_init(const struct btf_record *rec, void *obj) if (IS_ERR_OR_NULL(rec)) return; for (i = 0; i < rec->cnt; i++) - memset(obj + rec->fields[i].offset, 0, rec->fields[i].size); - - if (rec->refcount_off >= 0) - refcount_set((refcount_t *)(obj + rec->refcount_off), 1); + bpf_obj_init_field(&rec->fields[i], obj + rec->fields[i].offset); } /* 'dst' must be a temporary buffer and should not point to memory that is being -- cgit v1.2.3 From 8b0977ecc8b30a30966e76fcb64cef5041626b02 Mon Sep 17 00:00:00 2001 From: Michael Kelley Date: Thu, 13 Apr 2023 10:57:37 -0700 Subject: swiotlb: track and report io_tlb_used high water marks in debugfs swiotlb currently reports the total number of slabs and the instantaneous in-use slabs in debugfs. But with increased usage of swiotlb for all I/O in Confidential Computing (coco) VMs, it has become difficult to know how much memory to allocate for swiotlb bounce buffers, either via the automatic algorithm in the kernel or by specifying a value on the kernel boot line. The current automatic algorithm generously allocates swiotlb bounce buffer memory, and may be wasting significant memory in many use cases. To support better understanding of swiotlb usage, add tracking of the the high water mark for usage of the default swiotlb bounce buffer memory pool and any reserved memory pools. Report these high water marks in debugfs along with the other swiotlb pool metrics. Allow the high water marks to be reset to zero at runtime by writing to them. Signed-off-by: Michael Kelley Signed-off-by: Christoph Hellwig --- include/linux/swiotlb.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index bcef10e20ea4..6dc4598d2260 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -87,6 +87,11 @@ dma_addr_t swiotlb_map(struct device *dev, phys_addr_t phys, * @for_alloc: %true if the pool is used for memory allocation * @nareas: The area number in the pool. * @area_nslabs: The slot number in the area. + * @total_used: The total number of slots in the pool that are currently used + * across all areas. Used only for calculating used_hiwater in + * debugfs. + * @used_hiwater: The high water mark for total_used. Used only for reporting + * in debugfs. */ struct io_tlb_mem { phys_addr_t start; @@ -102,6 +107,8 @@ struct io_tlb_mem { unsigned int area_nslabs; struct io_tlb_area *areas; struct io_tlb_slot *slots; + atomic_long_t total_used; + atomic_long_t used_hiwater; }; extern struct io_tlb_mem io_tlb_default_mem; -- cgit v1.2.3 From ccbbfe0682f2fff1e157413c30092dd27c50e20e Mon Sep 17 00:00:00 2001 From: Avihai Horon Date: Mon, 10 Apr 2023 16:07:52 +0300 Subject: net/mlx5: Update relaxed ordering read HCA capabilities Rename existing HCA capability relaxed_ordering_read to relaxed_ordering_read_pci_enabled. This is in accordance with recent PRM change to better describe the capability, as it's set only if both the device supports relaxed ordering (RO) read and RO is enabled in PCI config space. In addition, add new HCA capability relaxed_ordering_read which is set if the device supports RO read, regardless of RO in PCI config space. This will be used in the following patch to allow RO in VFs and VMs. Signed-off-by: Avihai Horon Reviewed-by: Shay Drory Link: https://lore.kernel.org/r/caa0002fd8135086357dfcc368e2f5cc73b08480.1681131553.git.leon@kernel.org Reviewed-by: Jacob Keller Signed-off-by: Leon Romanovsky --- include/linux/mlx5/mlx5_ifc.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index e4306cd87cd7..b54339a1b1c6 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1511,7 +1511,7 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 log_max_eq_sz[0x8]; u8 relaxed_ordering_write[0x1]; - u8 relaxed_ordering_read[0x1]; + u8 relaxed_ordering_read_pci_enabled[0x1]; u8 log_max_mkey[0x6]; u8 reserved_at_f0[0x6]; u8 terminate_scatter_list_mkey[0x1]; @@ -1727,7 +1727,8 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_320[0x3]; u8 log_max_transport_domain[0x5]; - u8 reserved_at_328[0x3]; + u8 reserved_at_328[0x2]; + u8 relaxed_ordering_read[0x1]; u8 log_max_pd[0x5]; u8 reserved_at_330[0x9]; u8 q_counter_aggregation[0x1]; -- cgit v1.2.3 From 3f67987cdc09778e75098f9f5168832f8f8e1f1c Mon Sep 17 00:00:00 2001 From: Gregory Price Date: Fri, 7 Apr 2023 13:18:33 -0400 Subject: ptrace: Provide set/get interface for syscall user dispatch The syscall user dispatch configuration can only be set by the task itself, but lacks a ptrace set/get interface which makes it impossible to implement checkpoint/restore for it. Add the required ptrace requests and the get/set functions in the syscall user dispatch code to make that possible. Signed-off-by: Gregory Price Signed-off-by: Thomas Gleixner Reviewed-by: Oleg Nesterov Link: https://lore.kernel.org/r/20230407171834.3558-4-gregory.price@memverge.com --- include/linux/syscall_user_dispatch.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include/linux') diff --git a/include/linux/syscall_user_dispatch.h b/include/linux/syscall_user_dispatch.h index a0ae443fb7df..641ca8880995 100644 --- a/include/linux/syscall_user_dispatch.h +++ b/include/linux/syscall_user_dispatch.h @@ -22,6 +22,12 @@ int set_syscall_user_dispatch(unsigned long mode, unsigned long offset, #define clear_syscall_work_syscall_user_dispatch(tsk) \ clear_task_syscall_work(tsk, SYSCALL_USER_DISPATCH) +int syscall_user_dispatch_get_config(struct task_struct *task, unsigned long size, + void __user *data); + +int syscall_user_dispatch_set_config(struct task_struct *task, unsigned long size, + void __user *data); + #else struct syscall_user_dispatch {}; @@ -35,6 +41,18 @@ static inline void clear_syscall_work_syscall_user_dispatch(struct task_struct * { } +static inline int syscall_user_dispatch_get_config(struct task_struct *task, + unsigned long size, void __user *data) +{ + return -EINVAL; +} + +static inline int syscall_user_dispatch_set_config(struct task_struct *task, + unsigned long size, void __user *data) +{ + return -EINVAL; +} + #endif /* CONFIG_GENERIC_ENTRY */ #endif /* _SYSCALL_USER_DISPATCH_H */ -- cgit v1.2.3 From 7b4ddf3920d247c2949073b9c274301c8131332a Mon Sep 17 00:00:00 2001 From: David Vernet Date: Sun, 16 Apr 2023 03:49:27 -0500 Subject: bpf: Remove KF_KPTR_GET kfunc flag We've managed to improve the UX for kptrs significantly over the last 9 months. All of the existing use cases which previously had KF_KPTR_GET kfuncs (struct bpf_cpumask *, struct task_struct *, and struct cgroup *) have all been updated to be synchronized using RCU. In other words, their KF_KPTR_GET kfuncs have been removed in favor of KF_RCU | KF_ACQUIRE kfuncs, with the pointers themselves also being readable from maps in an RCU read region thanks to the types being RCU safe. While KF_KPTR_GET was a logical starting point for kptrs, it's become clear that they're not the correct abstraction. KF_KPTR_GET is a flag that essentially does nothing other than enforcing that the argument to a function is a pointer to a referenced kptr map value. At first glance, that's a useful thing to guarantee to a kfunc. It gives kfuncs the ability to try and acquire a reference on that kptr without requiring the BPF prog to do something like this: struct kptr_type *in_map, *new = NULL; in_map = bpf_kptr_xchg(&map->value, NULL); if (in_map) { new = bpf_kptr_type_acquire(in_map); in_map = bpf_kptr_xchg(&map->value, in_map); if (in_map) bpf_kptr_type_release(in_map); } That's clearly a pretty ugly (and racy) UX, and if using KF_KPTR_GET is the only alternative, it's better than nothing. However, the problem with any KF_KPTR_GET kfunc lies in the fact that it always requires some kind of synchronization in order to safely do an opportunistic acquire of the kptr in the map. This is because a BPF program running on another CPU could do a bpf_kptr_xchg() on that map value, and free the kptr after it's been read by the KF_KPTR_GET kfunc. For example, the now-removed bpf_task_kptr_get() kfunc did the following: struct task_struct *bpf_task_kptr_get(struct task_struct **pp) { struct task_struct *p; rcu_read_lock(); p = READ_ONCE(*pp); /* If p is non-NULL, it could still be freed by another CPU, * so we have to do an opportunistic refcount_inc_not_zero() * and return NULL if the task will be freed after the * current RCU read region. */ |f (p && !refcount_inc_not_zero(&p->rcu_users)) p = NULL; rcu_read_unlock(); return p; } In other words, the kfunc uses RCU to ensure that the task remains valid after it's been peeked from the map. However, this is completely redundant with just defining a KF_RCU kfunc that itself does a refcount_inc_not_zero(), which is exactly what bpf_task_acquire() now does. So, the question of whether KF_KPTR_GET is useful is actually, "Are there any synchronization mechanisms / safety flags that are required by certain kptrs, but which are not provided by the verifier to kfuncs?" The answer to that question today is "No", because every kptr we currently care about is RCU protected. Even if the answer ever became "yes", the proper way to support that referenced kptr type would be to add support for whatever synchronization mechanism it requires in the verifier, rather than giving kfuncs a flag that says, "Here's a pointer to a referenced kptr in a map, do whatever you need to do." With all that said -- so as to allow us to consolidate the kfunc API, and simplify the verifier a bit, this patch removes KF_KPTR_GET, and all relevant logic from the verifier. Signed-off-by: David Vernet Link: https://lore.kernel.org/r/20230416084928.326135-3-void@manifault.com Signed-off-by: Alexei Starovoitov --- include/linux/btf.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/btf.h b/include/linux/btf.h index 813227bff58a..508199e38415 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -18,7 +18,6 @@ #define KF_ACQUIRE (1 << 0) /* kfunc is an acquire function */ #define KF_RELEASE (1 << 1) /* kfunc is a release function */ #define KF_RET_NULL (1 << 2) /* kfunc returns a pointer that may be NULL */ -#define KF_KPTR_GET (1 << 3) /* kfunc returns reference to a kptr */ /* Trusted arguments are those which are guaranteed to be valid when passed to * the kfunc. It is used to enforce that pointers obtained from either acquire * kfuncs, or from the main kernel on a tracepoint or struct_ops callback -- cgit v1.2.3 From 3838c406a594f15600ad6f83c1e3b16bfd1829d0 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 14 Apr 2023 07:30:16 -0600 Subject: block: re-arrange the struct block_device fields for better layout This moves struct device out-of-line as it's just used at open/close time, so we can keep some of the commonly used fields closer together. On a standard setup, it also reduces the size from 864 bytes to 848 bytes. Yes, struct device is a pig... Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blk_types.h | 20 ++++++++++++-------- 1 file changed, 12 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 99be590f952f..c1da616fadae 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -40,26 +40,25 @@ struct bio_crypt_ctx; struct block_device { sector_t bd_start_sect; sector_t bd_nr_sectors; + struct gendisk * bd_disk; + struct request_queue * bd_queue; struct disk_stats __percpu *bd_stats; unsigned long bd_stamp; bool bd_read_only; /* read-only policy */ + u8 bd_partno; + bool bd_write_holder; dev_t bd_dev; atomic_t bd_openers; + spinlock_t bd_size_lock; /* for bd_inode->i_size updates */ struct inode * bd_inode; /* will die */ struct super_block * bd_super; void * bd_claiming; - struct device bd_device; void * bd_holder; + /* The counter of freeze processes */ + int bd_fsfreeze_count; int bd_holders; - bool bd_write_holder; struct kobject *bd_holder_dir; - u8 bd_partno; - spinlock_t bd_size_lock; /* for bd_inode->i_size updates */ - struct gendisk * bd_disk; - struct request_queue * bd_queue; - /* The counter of freeze processes */ - int bd_fsfreeze_count; /* Mutex for freeze */ struct mutex bd_fsfreeze_mutex; struct super_block *bd_fsfreeze_sb; @@ -68,6 +67,11 @@ struct block_device { #ifdef CONFIG_FAIL_MAKE_REQUEST bool bd_make_it_fail; #endif + /* + * keep this out-of-line as it's both big and not needed in the fast + * path + */ + struct device bd_device; } __randomize_layout; #define bdev_whole(_bdev) \ -- cgit v1.2.3 From 9f4107b07b17b5ee68af680150f91227bea2df6f Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 14 Apr 2023 07:32:02 -0600 Subject: block: store bdev->bd_disk->fops->submit_bio state in bdev We have a long chain of memory dereferencing just to whether or not this disk has a special submit_bio helper. As that's not necessarily the common case, add a bd_has_submit_bio state in the bdev to avoid traversing this memory dependency chain if we don't need to. Signed-off-by: Jens Axboe --- include/linux/blk_types.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index c1da616fadae..3e8e9a97de46 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -47,6 +47,7 @@ struct block_device { bool bd_read_only; /* read-only policy */ u8 bd_partno; bool bd_write_holder; + bool bd_has_submit_bio; dev_t bd_dev; atomic_t bd_openers; spinlock_t bd_size_lock; /* for bd_inode->i_size updates */ -- cgit v1.2.3 From c55c0e91c813589dc55bea6bf9a9fbfaa10ae41d Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 17 Apr 2023 10:21:36 +0200 Subject: netfilter: nf_tables: fix ifdef to also consider nf_tables=m nftables can be built as a module, so fix the preprocessor conditional accordingly. Fixes: 478b360a47b7 ("netfilter: nf_tables: fix nf_trace always-on with XT_TRACE=n") Reported-by: Florian Fainelli Reported-by: Jakub Kicinski Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/skbuff.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 1ec3530c8191..dbcaac8b6966 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -4713,7 +4713,7 @@ static inline void nf_reset_ct(struct sk_buff *skb) static inline void nf_reset_trace(struct sk_buff *skb) { -#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) || defined(CONFIG_NF_TABLES) +#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) || IS_ENABLED(CONFIG_NF_TABLES) skb->nf_trace = 0; #endif } @@ -4733,7 +4733,7 @@ static inline void __nf_copy(struct sk_buff *dst, const struct sk_buff *src, dst->_nfct = src->_nfct; nf_conntrack_get(skb_nfct(src)); #endif -#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) || defined(CONFIG_NF_TABLES) +#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) || IS_ENABLED(CONFIG_NF_TABLES) if (copy) dst->nf_trace = src->nf_trace; #endif -- cgit v1.2.3 From 0a0596fbbe5bddd28b1dfae7e7ecb6d70bdbf059 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 27 Mar 2023 09:49:50 +0900 Subject: btrfs, mm: remove the punt_to_cgroup field in struct writeback_control punt_to_cgroup is only used by extent_write_locked_range, but that function also directly controls the bio flags for the actual submission. Remove th punt_to_cgroup field, and just set REQ_CGROUP_PUNT directly in extent_write_locked_range. Signed-off-by: Christoph Hellwig Signed-off-by: David Sterba --- include/linux/writeback.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 46020373e155..fba937999fbf 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -70,8 +70,6 @@ struct writeback_control { */ unsigned no_cgroup_owner:1; - unsigned punt_to_cgroup:1; /* cgrp punting, see __REQ_CGROUP_PUNT */ - /* To enable batching of swap writes to non-block-device backends, * "plug" can be set point to a 'struct swap_iocb *'. When all swap * writes have been submitted, if with swap_iocb is not NULL, @@ -97,9 +95,6 @@ static inline blk_opf_t wbc_to_write_flags(struct writeback_control *wbc) { blk_opf_t flags = 0; - if (wbc->punt_to_cgroup) - flags = REQ_CGROUP_PUNT; - if (wbc->sync_mode == WB_SYNC_ALL) flags |= REQ_SYNC; else if (wbc->for_kupdate || wbc->for_background) -- cgit v1.2.3 From 3480373ebdf7625ee29bee6508c9fc4ae70c00bf Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 27 Mar 2023 09:49:51 +0900 Subject: btrfs, block: move REQ_CGROUP_PUNT to btrfs REQ_CGROUP_PUNT is a bit annoying as it is hard to follow and adds a branch to the bio submission hot path. To fix this, export blkcg_punt_bio_submit and let btrfs call it directly. Add a new REQ_FS_PRIVATE flag for btrfs to indicate to it's own low-level bio submission code that a punt to the cgroup submission helper is required. Reviewed-by: Jens Axboe Signed-off-by: Christoph Hellwig Reviewed-by: David Sterba Signed-off-by: David Sterba --- include/linux/bio.h | 5 +++++ include/linux/blk_types.h | 18 +++++------------- 2 files changed, 10 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index d766be7152e1..b3e7529ff55e 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -500,6 +500,7 @@ void bio_associate_blkg(struct bio *bio); void bio_associate_blkg_from_css(struct bio *bio, struct cgroup_subsys_state *css); void bio_clone_blkg_association(struct bio *dst, struct bio *src); +void blkcg_punt_bio_submit(struct bio *bio); #else /* CONFIG_BLK_CGROUP */ static inline void bio_associate_blkg(struct bio *bio) { } static inline void bio_associate_blkg_from_css(struct bio *bio, @@ -507,6 +508,10 @@ static inline void bio_associate_blkg_from_css(struct bio *bio, { } static inline void bio_clone_blkg_association(struct bio *dst, struct bio *src) { } +static inline void blkcg_punt_bio_submit(struct bio *bio) +{ + submit_bio(bio); +} #endif /* CONFIG_BLK_CGROUP */ static inline void bio_set_dev(struct bio *bio, struct block_device *bdev) diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 99be590f952f..fb8843990d28 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -404,18 +404,11 @@ enum req_flag_bits { __REQ_RAHEAD, /* read ahead, can fail anytime */ __REQ_BACKGROUND, /* background IO */ __REQ_NOWAIT, /* Don't wait if request will block */ - /* - * When a shared kthread needs to issue a bio for a cgroup, doing - * so synchronously can lead to priority inversions as the kthread - * can be trapped waiting for that cgroup. CGROUP_PUNT flag makes - * submit_bio() punt the actual issuing to a dedicated per-blkcg - * work item to avoid such priority inversions. - */ - __REQ_CGROUP_PUNT, __REQ_POLLED, /* caller polls for completion using bio_poll */ __REQ_ALLOC_CACHE, /* allocate IO from cache if available */ __REQ_SWAP, /* swap I/O */ __REQ_DRV, /* for driver use */ + __REQ_FS_PRIVATE, /* for file system (submitter) use */ /* * Command specific flags, keep last: @@ -443,14 +436,13 @@ enum req_flag_bits { #define REQ_RAHEAD (__force blk_opf_t)(1ULL << __REQ_RAHEAD) #define REQ_BACKGROUND (__force blk_opf_t)(1ULL << __REQ_BACKGROUND) #define REQ_NOWAIT (__force blk_opf_t)(1ULL << __REQ_NOWAIT) -#define REQ_CGROUP_PUNT (__force blk_opf_t)(1ULL << __REQ_CGROUP_PUNT) - -#define REQ_NOUNMAP (__force blk_opf_t)(1ULL << __REQ_NOUNMAP) #define REQ_POLLED (__force blk_opf_t)(1ULL << __REQ_POLLED) #define REQ_ALLOC_CACHE (__force blk_opf_t)(1ULL << __REQ_ALLOC_CACHE) - -#define REQ_DRV (__force blk_opf_t)(1ULL << __REQ_DRV) #define REQ_SWAP (__force blk_opf_t)(1ULL << __REQ_SWAP) +#define REQ_DRV (__force blk_opf_t)(1ULL << __REQ_DRV) +#define REQ_FS_PRIVATE (__force blk_opf_t)(1ULL << __REQ_FS_PRIVATE) + +#define REQ_NOUNMAP (__force blk_opf_t)(1ULL << __REQ_NOUNMAP) #define REQ_FAILFAST_MASK \ (REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT | REQ_FAILFAST_DRIVER) -- cgit v1.2.3 From 7533583e125d65bac1435410ecb56433e95eade0 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 5 Apr 2023 07:49:05 +0200 Subject: libcrc32c: remove crc32c_impl This was only ever used by btrfs, and the usage just went away. This effectively reverts df91f56adce1 ("libcrc32c: Add crc32c_impl function"). Acked-by: Herbert Xu Signed-off-by: Christoph Hellwig Reviewed-by: David Sterba Signed-off-by: David Sterba --- include/linux/crc32c.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/crc32c.h b/include/linux/crc32c.h index bd21af828ff6..357ae4611a45 100644 --- a/include/linux/crc32c.h +++ b/include/linux/crc32c.h @@ -5,7 +5,6 @@ #include extern u32 crc32c(u32 crc, const void *address, unsigned int length); -extern const char *crc32c_impl(void); /* This macro exists for backwards-compatibility. */ #define crc32c_le crc32c -- cgit v1.2.3 From 1f6277bf716cc5ba0e3fa0c3e0af1adb4160fb5d Mon Sep 17 00:00:00 2001 From: Saurabh Sengar Date: Mon, 20 Mar 2023 00:47:37 -0700 Subject: ACPI: bus: Add stub acpi_sleep_state_supported() in non-ACPI cases acpi_sleep_state_supported() is defined only when CONFIG_ACPI=y. The function is in acpi_bus.h, and acpi_bus.h can only be used in CONFIG_ACPI=y cases. Add the stub function to linux/acpi.h to make compilation successful for !CONFIG_ACPI cases. Signed-off-by: Saurabh Sengar Acked-by: Rafael J. Wysocki Link: https://lore.kernel.org/r/1679298460-11855-3-git-send-email-ssengar@linux.microsoft.com Signed-off-by: Wei Liu --- include/linux/acpi.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index efff750f326d..d331f76b0c19 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -1075,6 +1075,11 @@ static inline u32 acpi_osc_ctx_get_cxl_control(struct acpi_osc_context *context) return 0; } +static inline bool acpi_sleep_state_supported(u8 sleep_state) +{ + return false; +} + #endif /* !CONFIG_ACPI */ #ifdef CONFIG_ACPI_HOTPLUG_IOAPIC -- cgit v1.2.3 From 0459ff4873739986dccafbb417cfc69e71bdacf4 Mon Sep 17 00:00:00 2001 From: Michael Kelley Date: Sun, 26 Mar 2023 06:52:02 -0700 Subject: swiotlb: Remove bounce buffer remapping for Hyper-V With changes to how Hyper-V guest VMs flip memory between private (encrypted) and shared (decrypted), creating a second kernel virtual mapping for shared memory is no longer necessary. Everything needed for the transition to shared is handled by set_memory_decrypted(). As such, remove swiotlb_unencrypted_base and the associated code. Signed-off-by: Michael Kelley Acked-by: Christoph Hellwig Acked-by: Borislav Petkov (AMD) Link: https://lore.kernel.org/r/1679838727-87310-8-git-send-email-mikelley@microsoft.com Signed-off-by: Wei Liu --- include/linux/swiotlb.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index bcef10e20ea4..2ef25e6fa1b4 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -180,6 +180,4 @@ static inline bool is_swiotlb_for_alloc(struct device *dev) } #endif /* CONFIG_DMA_RESTRICTED_POOL */ -extern phys_addr_t swiotlb_unencrypted_base; - #endif /* __LINUX_SWIOTLB_H */ -- cgit v1.2.3 From 59e498a3289f685261c076b998a8a2f8a516874f Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Mon, 17 Apr 2023 15:49:15 +0200 Subject: bpf: Set skb redirect and from_ingress info in __bpf_tx_skb MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit There are some use-cases where it is desirable to use bpf_redirect() in combination with ifb device, which currently is not supported, for example, around filtering inbound traffic with BPF to then push it to ifb which holds the qdisc for shaping in contrast to doing that on the egress device. Toke mentions the following case related to OpenWrt: Because there's not always a single egress on the other side. These are mainly home routers, which tend to have one or more WiFi devices bridged to one or more ethernet ports on the LAN side, and a single upstream WAN port. And the objective is to control the total amount of traffic going over the WAN link (in both directions), to deal with bufferbloat in the ISP network (which is sadly still all too prevalent). In this setup, the traffic can be split arbitrarily between the links on the LAN side, and the only "single bottleneck" is the WAN link. So we install both egress and ingress shapers on this, configured to something like 95-98% of the true link bandwidth, thus moving the queues into the qdisc layer in the router. It's usually necessary to set the ingress bandwidth shaper a bit lower than the egress due to being "downstream" of the bottleneck link, but it does work surprisingly well. We usually use something like a matchall filter to put all ingress traffic on the ifb, so doing the redirect from BPF has not been an immediate requirement thus far. However, it does seem a bit odd that this is not possible, and we do have a BPF-based filter that layers on top of this kind of setup, which currently uses u32 as the ingress filter and so it could presumably be improved to use BPF instead if that was available. Reported-by: Toke Høiland-Jørgensen Reported-by: Yafang Shao Reported-by: Tonghao Zhang Signed-off-by: Daniel Borkmann Acked-by: Yafang Shao Acked-by: Toke Høiland-Jørgensen Link: https://git.openwrt.org/?p=project/qosify.git;a=blob;f=README Link: https://lore.kernel.org/bpf/875y9yzbuy.fsf@toke.dk Link: https://lore.kernel.org/r/8cebc8b2b6e967e10cbafe2ffd6795050e74accd.1681739137.git.daniel@iogearbox.net Signed-off-by: Alexei Starovoitov --- include/linux/skbuff.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 494a23a976b0..9ff2e3d57329 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -5041,6 +5041,15 @@ static inline void skb_reset_redirect(struct sk_buff *skb) skb->redirected = 0; } +static inline void skb_set_redirected_noclear(struct sk_buff *skb, + bool from_ingress) +{ + skb->redirected = 1; +#ifdef CONFIG_NET_REDIRECT + skb->from_ingress = from_ingress; +#endif +} + static inline bool skb_csum_is_sctp(struct sk_buff *skb) { return skb->csum_not_inet; -- cgit v1.2.3 From 1210af3b99561bbe140af8d9a6b16d1bd0ba3fda Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Thu, 13 Apr 2023 15:29:19 +0300 Subject: net/mlx5e: Add IPsec packet offload tunnel bits Extend packet reformat types and flow table capabilities with IPsec packet offload tunnel bits. Reviewed-by: Simon Horman Signed-off-by: Leon Romanovsky Reviewed-by: Sridhar Samudrala Signed-off-by: Jakub Kicinski --- include/linux/mlx5/mlx5_ifc.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 6c84bf6eec85..20d00e09b168 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -463,9 +463,11 @@ struct mlx5_ifc_flow_table_prop_layout_bits { u8 max_ft_level[0x8]; u8 reformat_add_esp_trasport[0x1]; - u8 reserved_at_41[0x2]; + u8 reformat_l2_to_l3_esp_tunnel[0x1]; + u8 reserved_at_42[0x1]; u8 reformat_del_esp_trasport[0x1]; - u8 reserved_at_44[0x2]; + u8 reformat_l3_esp_tunnel_to_l2[0x1]; + u8 reserved_at_45[0x1]; u8 execute_aso[0x1]; u8 reserved_at_47[0x19]; @@ -6630,7 +6632,9 @@ enum mlx5_reformat_ctx_type { MLX5_REFORMAT_TYPE_L3_TUNNEL_TO_L2 = 0x3, MLX5_REFORMAT_TYPE_L2_TO_L3_TUNNEL = 0x4, MLX5_REFORMAT_TYPE_ADD_ESP_TRANSPORT_OVER_IPV4 = 0x5, + MLX5_REFORMAT_TYPE_L2_TO_L3_ESP_TUNNEL = 0x6, MLX5_REFORMAT_TYPE_DEL_ESP_TRANSPORT = 0x8, + MLX5_REFORMAT_TYPE_L3_ESP_TUNNEL_TO_L2 = 0x9, MLX5_REFORMAT_TYPE_ADD_ESP_TRANSPORT_OVER_IPV6 = 0xb, MLX5_REFORMAT_TYPE_INSERT_HDR = 0xf, MLX5_REFORMAT_TYPE_REMOVE_HDR = 0x10, -- cgit v1.2.3 From 3e358ea8614ddfbc59ca7a3f5dff5dde2b350b2c Mon Sep 17 00:00:00 2001 From: Mark Bloch Date: Thu, 13 Apr 2023 12:23:09 +0300 Subject: RDMA/mlx5: Fix flow counter query via DEVX Commit cited in "fixes" tag added bulk support for flow counters but it didn't account that's also possible to query a counter using a non-base id if the counter was allocated as bulk. When a user performs a query, validate the flow counter id given in the mailbox is inside the valid range taking bulk value into account. Fixes: 208d70f562e5 ("IB/mlx5: Support flow counters offset for bulk counters") Signed-off-by: Mark Bloch Reviewed-by: Maor Gottlieb Link: https://lore.kernel.org/r/79d7fbe291690128e44672418934256254d93115.1681377114.git.leon@kernel.org Signed-off-by: Leon Romanovsky --- include/linux/mlx5/mlx5_ifc.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index b54339a1b1c6..3976e6266bcc 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -9283,7 +9283,8 @@ struct mlx5_ifc_alloc_flow_counter_in_bits { u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_at_40[0x38]; + u8 reserved_at_40[0x33]; + u8 flow_counter_bulk_log_size[0x5]; u8 flow_counter_bulk[0x8]; }; -- cgit v1.2.3 From 85a953806557dbf25d16e8c132b5b9b100d16496 Mon Sep 17 00:00:00 2001 From: Elliot Berman Date: Mon, 10 Apr 2023 09:16:52 -0700 Subject: mailbox: Allow direct registration to a channel Support virtual mailbox controllers and clients which are not platform devices or come from the devicetree by allowing them to match client to channel via some other mechanism. Tested-by: Sudeep Holla (pcc) Signed-off-by: Elliot Berman Signed-off-by: Jassi Brar --- include/linux/mailbox_client.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mailbox_client.h b/include/linux/mailbox_client.h index 65229a45590f..734694912ef7 100644 --- a/include/linux/mailbox_client.h +++ b/include/linux/mailbox_client.h @@ -37,6 +37,7 @@ struct mbox_client { void (*tx_done)(struct mbox_client *cl, void *mssg, int r); }; +int mbox_bind_client(struct mbox_chan *chan, struct mbox_client *cl); struct mbox_chan *mbox_request_channel_byname(struct mbox_client *cl, const char *name); struct mbox_chan *mbox_request_channel(struct mbox_client *cl, int index); -- cgit v1.2.3 From 62e8b17ffc2ff0b0e29d5e05a18570c3e70b35ff Mon Sep 17 00:00:00 2001 From: Lukas Wunner Date: Sat, 11 Mar 2023 15:40:07 +0100 Subject: PCI/DOE: Provide synchronous API and use it internally The DOE API only allows asynchronous exchanges and forces callers to provide a completion callback. Yet all existing callers only perform synchronous exchanges. Upcoming commits for CMA (Component Measurement and Authentication, PCIe r6.0 sec 6.31) likewise require only synchronous DOE exchanges. Provide a synchronous pci_doe() API call which builds on the internal asynchronous machinery. Convert the internal pci_doe_discovery() to the new call. The new API allows submission of const-declared requests, necessitating the addition of a const qualifier in struct pci_doe_task. Tested-by: Ira Weiny Signed-off-by: Lukas Wunner Reviewed-by: Ming Li Reviewed-by: Ira Weiny Reviewed-by: Davidlohr Bueso Reviewed-by: Dan Williams Reviewed-by: Jonathan Cameron Acked-by: Bjorn Helgaas Link: https://lore.kernel.org/r/0f444206da9615c56301fbaff459c0f45d27f122.1678543498.git.lukas@wunner.de Signed-off-by: Dan Williams --- include/linux/pci-doe.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pci-doe.h b/include/linux/pci-doe.h index 43765eaf2342..5dcd54f892e5 100644 --- a/include/linux/pci-doe.h +++ b/include/linux/pci-doe.h @@ -49,7 +49,7 @@ struct pci_doe_mb; */ struct pci_doe_task { struct pci_doe_protocol prot; - __le32 *request_pl; + const __le32 *request_pl; size_t request_pl_sz; __le32 *response_pl; size_t response_pl_sz; @@ -78,4 +78,8 @@ struct pci_doe_mb *pcim_doe_create_mb(struct pci_dev *pdev, u16 cap_offset); bool pci_doe_supports_prot(struct pci_doe_mb *doe_mb, u16 vid, u8 type); int pci_doe_submit_task(struct pci_doe_mb *doe_mb, struct pci_doe_task *task); +int pci_doe(struct pci_doe_mb *doe_mb, u16 vendor, u8 type, + const void *request, size_t request_sz, + void *response, size_t response_sz); + #endif -- cgit v1.2.3 From 0821ff8ed059d38dfc9bec2106c5cc53bcaa15b1 Mon Sep 17 00:00:00 2001 From: Lukas Wunner Date: Sat, 11 Mar 2023 15:40:09 +0100 Subject: PCI/DOE: Make asynchronous API private A synchronous API for DOE has just been introduced. CXL (the only in-tree DOE user so far) was converted to use it instead of the asynchronous API. Consequently, pci_doe_submit_task() as well as the pci_doe_task struct are only used internally, so make them private. Tested-by: Ira Weiny Signed-off-by: Lukas Wunner Reviewed-by: Ming Li Reviewed-by: Ira Weiny Reviewed-by: Jonathan Cameron Acked-by: Bjorn Helgaas Link: https://lore.kernel.org/r/cc19544068483681e91dfe27545c2180cd09f931.1678543498.git.lukas@wunner.de Signed-off-by: Dan Williams --- include/linux/pci-doe.h | 48 ------------------------------------------------ 1 file changed, 48 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci-doe.h b/include/linux/pci-doe.h index 5dcd54f892e5..7f16749c6aa3 100644 --- a/include/linux/pci-doe.h +++ b/include/linux/pci-doe.h @@ -13,55 +13,8 @@ #ifndef LINUX_PCI_DOE_H #define LINUX_PCI_DOE_H -struct pci_doe_protocol { - u16 vid; - u8 type; -}; - struct pci_doe_mb; -/** - * struct pci_doe_task - represents a single query/response - * - * @prot: DOE Protocol - * @request_pl: The request payload - * @request_pl_sz: Size of the request payload (bytes) - * @response_pl: The response payload - * @response_pl_sz: Size of the response payload (bytes) - * @rv: Return value. Length of received response or error (bytes) - * @complete: Called when task is complete - * @private: Private data for the consumer - * @work: Used internally by the mailbox - * @doe_mb: Used internally by the mailbox - * - * Payloads are treated as opaque byte streams which are transmitted verbatim, - * without byte-swapping. If payloads contain little-endian register values, - * the caller is responsible for conversion with cpu_to_le32() / le32_to_cpu(). - * - * The payload sizes and rv are specified in bytes with the following - * restrictions concerning the protocol. - * - * 1) The request_pl_sz must be a multiple of double words (4 bytes) - * 2) The response_pl_sz must be >= a single double word (4 bytes) - * 3) rv is returned as bytes but it will be a multiple of double words - * - * NOTE there is no need for the caller to initialize work or doe_mb. - */ -struct pci_doe_task { - struct pci_doe_protocol prot; - const __le32 *request_pl; - size_t request_pl_sz; - __le32 *response_pl; - size_t response_pl_sz; - int rv; - void (*complete)(struct pci_doe_task *task); - void *private; - - /* No need for the user to initialize these fields */ - struct work_struct work; - struct pci_doe_mb *doe_mb; -}; - /** * pci_doe_for_each_off - Iterate each DOE capability * @pdev: struct pci_dev to iterate @@ -76,7 +29,6 @@ struct pci_doe_task { struct pci_doe_mb *pcim_doe_create_mb(struct pci_dev *pdev, u16 cap_offset); bool pci_doe_supports_prot(struct pci_doe_mb *doe_mb, u16 vid, u8 type); -int pci_doe_submit_task(struct pci_doe_mb *doe_mb, struct pci_doe_task *task); int pci_doe(struct pci_doe_mb *doe_mb, u16 vendor, u8 type, const void *request, size_t request_sz, -- cgit v1.2.3 From ac04840350e2c21a17d867b262a1586603b87a92 Mon Sep 17 00:00:00 2001 From: Lukas Wunner Date: Sat, 11 Mar 2023 15:40:12 +0100 Subject: PCI/DOE: Create mailboxes on device enumeration Currently a DOE instance cannot be shared by multiple drivers because each driver creates its own pci_doe_mb struct for a given DOE instance. For the same reason a DOE instance cannot be shared between the PCI core and a driver. Moreover, finding out which protocols a DOE instance supports requires creating a pci_doe_mb for it. If a device has multiple DOE instances, a driver looking for a specific protocol may need to create a pci_doe_mb for each of the device's DOE instances and then destroy those which do not support the desired protocol. That's obviously an inefficient way to do things. Overcome these issues by creating mailboxes in the PCI core on device enumeration. Provide a pci_find_doe_mailbox() API call to allow drivers to get a pci_doe_mb for a given (pci_dev, vendor, protocol) triple. This API is modeled after pci_find_capability() and can later be amended with a pci_find_next_doe_mailbox() call to iterate over all mailboxes of a given pci_dev which support a specific protocol. On removal, destroy the mailboxes in pci_destroy_dev(), after the driver is unbound. This allows drivers to use DOE in their ->remove() hook. On surprise removal, cancel ongoing DOE exchanges and prevent new ones from being scheduled. Thereby ensure that a hot-removed device doesn't needlessly wait for a running exchange to time out. Tested-by: Ira Weiny Signed-off-by: Lukas Wunner Reviewed-by: Ming Li Reviewed-by: Ira Weiny Reviewed-by: Jonathan Cameron Acked-by: Bjorn Helgaas Link: https://lore.kernel.org/r/40a6f973f72ef283d79dd55e7e6fddc7481199af.1678543498.git.lukas@wunner.de Signed-off-by: Dan Williams --- include/linux/pci-doe.h | 2 ++ include/linux/pci.h | 3 +++ 2 files changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci-doe.h b/include/linux/pci-doe.h index 7f16749c6aa3..d6192ee0ac07 100644 --- a/include/linux/pci-doe.h +++ b/include/linux/pci-doe.h @@ -29,6 +29,8 @@ struct pci_doe_mb; struct pci_doe_mb *pcim_doe_create_mb(struct pci_dev *pdev, u16 cap_offset); bool pci_doe_supports_prot(struct pci_doe_mb *doe_mb, u16 vid, u8 type); +struct pci_doe_mb *pci_find_doe_mailbox(struct pci_dev *pdev, u16 vendor, + u8 type); int pci_doe(struct pci_doe_mb *doe_mb, u16 vendor, u8 type, const void *request, size_t request_sz, diff --git a/include/linux/pci.h b/include/linux/pci.h index b50e5c79f7e3..29d99530ec17 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -511,6 +511,9 @@ struct pci_dev { #endif #ifdef CONFIG_PCI_P2PDMA struct pci_p2pdma __rcu *p2pdma; +#endif +#ifdef CONFIG_PCI_DOE + struct xarray doe_mbs; /* Data Object Exchange mailboxes */ #endif u16 acs_cap; /* ACS Capability offset */ phys_addr_t rom; /* Physical address if not from BAR */ -- cgit v1.2.3 From 74e491e5d1bcc35a699291df720191760ff4130e Mon Sep 17 00:00:00 2001 From: Lukas Wunner Date: Sat, 11 Mar 2023 15:40:14 +0100 Subject: PCI/DOE: Make mailbox creation API private The PCI core has just been amended to create a pci_doe_mb struct for every DOE instance on device enumeration. CXL (the only in-tree DOE user so far) has been migrated to use those mailboxes instead of creating its own. That leaves pcim_doe_create_mb() and pci_doe_for_each_off() without any callers, so drop them. pci_doe_supports_prot() is now only used internally, so declare it static. pci_doe_destroy_mb() is no longer used as callback for devm_add_action(), so refactor it to accept a struct pci_doe_mb pointer instead of a generic void pointer. Because pci_doe_create_mb() is only called on device enumeration, i.e. before driver binding, the workqueue name never contains a driver name. So replace dev_driver_string() with dev_bus_name() when generating the workqueue name. Tested-by: Ira Weiny Signed-off-by: Lukas Wunner Reviewed-by: Ming Li Reviewed-by: Ira Weiny Reviewed-by: Jonathan Cameron Acked-by: Bjorn Helgaas Link: https://lore.kernel.org/r/64f614b6584982986c55d2c6229b4ee2b276dd59.1678543498.git.lukas@wunner.de Signed-off-by: Dan Williams --- include/linux/pci-doe.h | 14 -------------- 1 file changed, 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci-doe.h b/include/linux/pci-doe.h index d6192ee0ac07..1f14aed4354b 100644 --- a/include/linux/pci-doe.h +++ b/include/linux/pci-doe.h @@ -15,20 +15,6 @@ struct pci_doe_mb; -/** - * pci_doe_for_each_off - Iterate each DOE capability - * @pdev: struct pci_dev to iterate - * @off: u16 of config space offset of each mailbox capability found - */ -#define pci_doe_for_each_off(pdev, off) \ - for (off = pci_find_next_ext_capability(pdev, off, \ - PCI_EXT_CAP_ID_DOE); \ - off > 0; \ - off = pci_find_next_ext_capability(pdev, off, \ - PCI_EXT_CAP_ID_DOE)) - -struct pci_doe_mb *pcim_doe_create_mb(struct pci_dev *pdev, u16 cap_offset); -bool pci_doe_supports_prot(struct pci_doe_mb *doe_mb, u16 vid, u8 type); struct pci_doe_mb *pci_find_doe_mailbox(struct pci_dev *pdev, u16 vendor, u8 type); -- cgit v1.2.3 From 48380368dec14859723b9e3fbd43e042638d9a76 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 29 Mar 2023 12:14:42 +0200 Subject: Change DEFINE_SEMAPHORE() to take a number argument Fundamentally semaphores are a counted primitive, but DEFINE_SEMAPHORE() does not expose this and explicitly creates a binary semaphore. Change DEFINE_SEMAPHORE() to take a number argument and use that in the few places that open-coded it using __SEMAPHORE_INITIALIZER(). Signed-off-by: Peter Zijlstra (Intel) [mcgrof: add some tribal knowledge about why some folks prefer binary sempahores over mutexes] Reviewed-by: Sergey Senozhatsky Reviewed-by: Davidlohr Bueso Signed-off-by: Luis Chamberlain --- include/linux/semaphore.h | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/semaphore.h b/include/linux/semaphore.h index 6694d0019a68..04655faadc2d 100644 --- a/include/linux/semaphore.h +++ b/include/linux/semaphore.h @@ -25,8 +25,14 @@ struct semaphore { .wait_list = LIST_HEAD_INIT((name).wait_list), \ } -#define DEFINE_SEMAPHORE(name) \ - struct semaphore name = __SEMAPHORE_INITIALIZER(name, 1) +/* + * Unlike mutexes, binary semaphores do not have an owner, so up() can + * be called in a different thread from the one which called down(). + * It is also safe to call down_trylock() and up() from interrupt + * context. + */ +#define DEFINE_SEMAPHORE(_name, _n) \ + struct semaphore _name = __SEMAPHORE_INITIALIZER(_name, _n) static inline void sema_init(struct semaphore *sem, int val) { -- cgit v1.2.3 From 47ebd0310e89c087f56e58c103c44b72a2f6b216 Mon Sep 17 00:00:00 2001 From: Alexander Potapenko Date: Thu, 13 Apr 2023 15:12:20 +0200 Subject: mm: kmsan: handle alloc failures in kmsan_vmap_pages_range_noflush() As reported by Dipanjan Das, when KMSAN is used together with kernel fault injection (or, generally, even without the latter), calls to kcalloc() or __vmap_pages_range_noflush() may fail, leaving the metadata mappings for the virtual mapping in an inconsistent state. When these metadata mappings are accessed later, the kernel crashes. To address the problem, we return a non-zero error code from kmsan_vmap_pages_range_noflush() in the case of any allocation/mapping failure inside it, and make vmap_pages_range_noflush() return an error if KMSAN fails to allocate the metadata. This patch also removes KMSAN_WARN_ON() from vmap_pages_range_noflush(), as these allocation failures are not fatal anymore. Link: https://lkml.kernel.org/r/20230413131223.4135168-1-glider@google.com Fixes: b073d7f8aee4 ("mm: kmsan: maintain KMSAN metadata for page operations") Signed-off-by: Alexander Potapenko Reported-by: Dipanjan Das Link: https://lore.kernel.org/linux-mm/CANX2M5ZRrRA64k0hOif02TjmY9kbbO2aCBPyq79es34RXZ=cAw@mail.gmail.com/ Reviewed-by: Marco Elver Cc: Christoph Hellwig Cc: Dmitry Vyukov Cc: Uladzislau Rezki (Sony) Cc: Signed-off-by: Andrew Morton --- include/linux/kmsan.h | 20 +++++++++++--------- 1 file changed, 11 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kmsan.h b/include/linux/kmsan.h index e38ae3c34618..c7ff3aefc5a1 100644 --- a/include/linux/kmsan.h +++ b/include/linux/kmsan.h @@ -134,11 +134,12 @@ void kmsan_kfree_large(const void *ptr); * @page_shift: page_shift passed to vmap_range_noflush(). * * KMSAN maps shadow and origin pages of @pages into contiguous ranges in - * vmalloc metadata address range. + * vmalloc metadata address range. Returns 0 on success, callers must check + * for non-zero return value. */ -void kmsan_vmap_pages_range_noflush(unsigned long start, unsigned long end, - pgprot_t prot, struct page **pages, - unsigned int page_shift); +int kmsan_vmap_pages_range_noflush(unsigned long start, unsigned long end, + pgprot_t prot, struct page **pages, + unsigned int page_shift); /** * kmsan_vunmap_kernel_range_noflush() - Notify KMSAN about a vunmap. @@ -281,12 +282,13 @@ static inline void kmsan_kfree_large(const void *ptr) { } -static inline void kmsan_vmap_pages_range_noflush(unsigned long start, - unsigned long end, - pgprot_t prot, - struct page **pages, - unsigned int page_shift) +static inline int kmsan_vmap_pages_range_noflush(unsigned long start, + unsigned long end, + pgprot_t prot, + struct page **pages, + unsigned int page_shift) { + return 0; } static inline void kmsan_vunmap_range_noflush(unsigned long start, -- cgit v1.2.3 From fdea03e12aa2a44a7bb34144208be97fc25dfd90 Mon Sep 17 00:00:00 2001 From: Alexander Potapenko Date: Thu, 13 Apr 2023 15:12:21 +0200 Subject: mm: kmsan: handle alloc failures in kmsan_ioremap_page_range() Similarly to kmsan_vmap_pages_range_noflush(), kmsan_ioremap_page_range() must also properly handle allocation/mapping failures. In the case of such, it must clean up the already created metadata mappings and return an error code, so that the error can be propagated to ioremap_page_range(). Without doing so, KMSAN may silently fail to bring the metadata for the page range into a consistent state, which will result in user-visible crashes when trying to access them. Link: https://lkml.kernel.org/r/20230413131223.4135168-2-glider@google.com Fixes: b073d7f8aee4 ("mm: kmsan: maintain KMSAN metadata for page operations") Signed-off-by: Alexander Potapenko Reported-by: Dipanjan Das Link: https://lore.kernel.org/linux-mm/CANX2M5ZRrRA64k0hOif02TjmY9kbbO2aCBPyq79es34RXZ=cAw@mail.gmail.com/ Reviewed-by: Marco Elver Cc: Christoph Hellwig Cc: Dmitry Vyukov Cc: Uladzislau Rezki (Sony) Cc: Signed-off-by: Andrew Morton --- include/linux/kmsan.h | 19 ++++++++++--------- 1 file changed, 10 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kmsan.h b/include/linux/kmsan.h index c7ff3aefc5a1..30b17647ce3c 100644 --- a/include/linux/kmsan.h +++ b/include/linux/kmsan.h @@ -160,11 +160,12 @@ void kmsan_vunmap_range_noflush(unsigned long start, unsigned long end); * @page_shift: page_shift argument passed to vmap_range_noflush(). * * KMSAN creates new metadata pages for the physical pages mapped into the - * virtual memory. + * virtual memory. Returns 0 on success, callers must check for non-zero return + * value. */ -void kmsan_ioremap_page_range(unsigned long addr, unsigned long end, - phys_addr_t phys_addr, pgprot_t prot, - unsigned int page_shift); +int kmsan_ioremap_page_range(unsigned long addr, unsigned long end, + phys_addr_t phys_addr, pgprot_t prot, + unsigned int page_shift); /** * kmsan_iounmap_page_range() - Notify KMSAN about a iounmap_page_range() call. @@ -296,12 +297,12 @@ static inline void kmsan_vunmap_range_noflush(unsigned long start, { } -static inline void kmsan_ioremap_page_range(unsigned long start, - unsigned long end, - phys_addr_t phys_addr, - pgprot_t prot, - unsigned int page_shift) +static inline int kmsan_ioremap_page_range(unsigned long start, + unsigned long end, + phys_addr_t phys_addr, pgprot_t prot, + unsigned int page_shift) { + return 0; } static inline void kmsan_iounmap_page_range(unsigned long start, -- cgit v1.2.3 From 5f300fd59a2ae90b8a7fb5ed3d5fd43768236c38 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 14 Apr 2023 10:03:53 +0200 Subject: mm: make arch_has_descending_max_zone_pfns() static clang produces a build failure on x86 for some randconfig builds after a change that moves around code to mm/mm_init.c: Cannot find symbol for section 2: .text. mm/mm_init.o: failed I have not been able to figure out why this happens, but the __weak annotation on arch_has_descending_max_zone_pfns() is the trigger here. Removing the weak function in favor of an open-coded Kconfig option check avoids the problem and becomes clearer as well as better to optimize by the compiler. [arnd@arndb.de: fix logic bug] Link: https://lkml.kernel.org/r/20230415081904.969049-1-arnd@kernel.org Link: https://lkml.kernel.org/r/20230414080418.110236-1-arnd@kernel.org Fixes: 9420f89db2dd ("mm: move most of core MM initialization to mm/mm_init.c") Signed-off-by: Arnd Bergmann Acked-by: Vlastimil Babka Tested-by: SeongJae Park Tested-by: Geert Uytterhoeven Acked-by: Mike Rapoport (IBM) Cc: kernel test robot Signed-off-by: Andrew Morton --- include/linux/mm.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index e249208f8fbe..5e5ef6ee4003 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3035,7 +3035,6 @@ extern void setup_per_cpu_pageset(void); extern int min_free_kbytes; extern int watermark_boost_factor; extern int watermark_scale_factor; -extern bool arch_has_descending_max_zone_pfns(void); /* nommu.c */ extern atomic_long_t mmap_pages_allocated; -- cgit v1.2.3 From a85c2257a8ac353af16dbcbf32c50d3380860bc5 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Fri, 17 Mar 2023 14:44:47 +0100 Subject: sched/isolation: add cpu_is_isolated() API Patch series "memcg, cpuisol: do not interfere pcp cache charges draining with cpuisol workloads". Leonardo has reported [1] that pcp memcg charge draining can interfere with cpu isolated workloads. The said draining is done from a WQ context with a pcp worker scheduled on each CPU which holds any cached charges for a specific memcg hierarchy. Operation is not really a common operation [2]. It can be triggered from the userspace though so some care is definitely due. Leonardo has tried to address the issue by allowing remote charge draining [3]. This approach requires an additional locking to synchronize pcp caches sync from a remote cpu from local pcp consumers. Even though the proposed lock was per-cpu there is still potential for contention and less predictable behavior. This patchset addresses the issue from a different angle. Rather than dealing with a potential synchronization, cpus which are isolated are simply never scheduled to be drained. This means that a small amount of charges could be laying around and waiting for a later use or they are flushed when a different memcg is charged from the same cpu. More details are in patch 2. The first patch from Frederic is implementing an abstraction to tell whether a specific cpu has been isolated and therefore require a special treatment. This patch (of 2): Provide this new API to check if a CPU has been isolated either through isolcpus= or nohz_full= kernel parameter. It aims at avoiding kernel load deemed to be safely spared on CPUs running sensitive workload that can't bear any disturbance, such as pcp cache draining. Link: https://lkml.kernel.org/r/20230317134448.11082-1-mhocko@kernel.org Link: https://lkml.kernel.org/r/20230317134448.11082-2-mhocko@kernel.org Signed-off-by: Frederic Weisbecker Signed-off-by: Michal Hocko Suggested-by: Michal Hocko Cc: Johannes Weiner Cc: Marcelo Tosatti Cc: Muchun Song Cc: Peter Zijlstra Cc: Roman Gushchin Cc: Shakeel Butt Cc: Thomas Gleixner Cc: Leonardo Bras Cc: Ingo Molnar Signed-off-by: Andrew Morton --- include/linux/sched/isolation.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched/isolation.h b/include/linux/sched/isolation.h index 8c15abd67aed..fe1a46f30d24 100644 --- a/include/linux/sched/isolation.h +++ b/include/linux/sched/isolation.h @@ -46,6 +46,12 @@ static inline bool housekeeping_enabled(enum hk_type type) static inline void housekeeping_affine(struct task_struct *t, enum hk_type type) { } + +static inline bool housekeeping_test_cpu(int cpu, enum hk_type type) +{ + return true; +} + static inline void housekeeping_init(void) { } #endif /* CONFIG_CPU_ISOLATION */ @@ -58,4 +64,10 @@ static inline bool housekeeping_cpu(int cpu, enum hk_type type) return true; } +static inline bool cpu_is_isolated(int cpu) +{ + return !housekeeping_test_cpu(cpu, HK_TYPE_DOMAIN) || + !housekeeping_test_cpu(cpu, HK_TYPE_TICK); +} + #endif /* _LINUX_SCHED_ISOLATION_H */ -- cgit v1.2.3 From 957ebbdf434013ee01f29f6c9174eced995ebbe7 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 27 Mar 2023 16:10:50 +0100 Subject: hugetlb: remove PageHeadHuge() Sidhartha Kumar removed the last caller of PageHeadHuge(), so we can now remove it and make folio_test_hugetlb() the real implementation. Add kernel-doc for folio_test_hugetlb(). Link: https://lkml.kernel.org/r/20230327151050.1787744-1-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Sidhartha Kumar Reviewed-by: Mike Kravetz Reviewed-by: David Hildenbrand Reviewed-by: Muchun Song Signed-off-by: Andrew Morton --- include/linux/page-flags.h | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index dcda20c47b8f..efc42fae3d96 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -815,14 +815,9 @@ static inline void ClearPageCompound(struct page *page) #ifdef CONFIG_HUGETLB_PAGE int PageHuge(struct page *page); -int PageHeadHuge(struct page *page); -static inline bool folio_test_hugetlb(struct folio *folio) -{ - return PageHeadHuge(&folio->page); -} +bool folio_test_hugetlb(struct folio *folio); #else TESTPAGEFLAG_FALSE(Huge, hugetlb) -TESTPAGEFLAG_FALSE(HeadHuge, headhuge) #endif #ifdef CONFIG_TRANSPARENT_HUGEPAGE -- cgit v1.2.3 From 62f31bd4dcedffe3c919deb76ed65bf62c3cf80b Mon Sep 17 00:00:00 2001 From: "Mike Rapoport (IBM)" Date: Sun, 26 Mar 2023 19:02:15 +0300 Subject: mm: move free_area_empty() to mm/internal.h The free_area_empty() helper is only used inside mm/ so move it there to reduce noise in include/linux/mmzone.h Link: https://lkml.kernel.org/r/20230326160215.2674531-1-rppt@kernel.org Signed-off-by: Mike Rapoport (IBM) Suggested-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton --- include/linux/mmzone.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 2d22e47dc1eb..337956748976 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -110,11 +110,6 @@ struct free_area { unsigned long nr_free; }; -static inline bool free_area_empty(struct free_area *area, int migratetype) -{ - return list_empty(&area->free_list[migratetype]); -} - struct pglist_data; #ifdef CONFIG_NUMA -- cgit v1.2.3 From 8bff9a04ca33476213ea6155850505787c540c25 Mon Sep 17 00:00:00 2001 From: Yosry Ahmed Date: Thu, 30 Mar 2023 19:17:54 +0000 Subject: cgroup: rename cgroup_rstat_flush_"irqsafe" to "atomic" MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Patch series "memcg: avoid flushing stats atomically where possible", v3. rstat flushing is an expensive operation that scales with the number of cpus and the number of cgroups in the system. The purpose of this series is to minimize the contexts where we flush stats atomically. Patches 1 and 2 are cleanups requested during reviews of prior versions of this series. Patch 3 makes sure we never try to flush from within an irq context. Patches 4 to 7 introduce separate variants of mem_cgroup_flush_stats() for atomic and non-atomic flushing, and make sure we only flush the stats atomically when necessary. Patch 8 is a slightly tangential optimization that limits the work done by rstat flushing in some scenarios. This patch (of 8): cgroup_rstat_flush_irqsafe() can be a confusing name. It may read as "irqs are disabled throughout", which is what the current implementation does (currently under discussion [1]), but is not the intention. The intention is that this function is safe to call from atomic contexts. Name it as such. Link: https://lkml.kernel.org/r/20230330191801.1967435-1-yosryahmed@google.com Link: https://lkml.kernel.org/r/20230330191801.1967435-2-yosryahmed@google.com Signed-off-by: Yosry Ahmed Suggested-by: Johannes Weiner Acked-by: Shakeel Butt Acked-by: Johannes Weiner Cc: Jens Axboe Cc: Josef Bacik Cc: Michal Hocko Cc: Michal Koutný Cc: Muchun Song Cc: Roman Gushchin Cc: Tejun Heo Cc: Vasily Averin Cc: Zefan Li Cc: Michal Hocko Signed-off-by: Andrew Morton --- include/linux/cgroup.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 3410aecffdb4..885f5395fcd0 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -692,7 +692,7 @@ static inline void cgroup_path_from_kernfs_id(u64 id, char *buf, size_t buflen) */ void cgroup_rstat_updated(struct cgroup *cgrp, int cpu); void cgroup_rstat_flush(struct cgroup *cgrp); -void cgroup_rstat_flush_irqsafe(struct cgroup *cgrp); +void cgroup_rstat_flush_atomic(struct cgroup *cgrp); void cgroup_rstat_flush_hold(struct cgroup *cgrp); void cgroup_rstat_flush_release(void); -- cgit v1.2.3 From 92fbbc7202ac4fb16250dc91c88211814ae2190b Mon Sep 17 00:00:00 2001 From: Yosry Ahmed Date: Thu, 30 Mar 2023 19:17:55 +0000 Subject: memcg: rename mem_cgroup_flush_stats_"delayed" to "ratelimited" MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit mem_cgroup_flush_stats_delayed() suggests his is using a delayed_work, but this is actually sometimes flushing directly from the callsite. What it's doing is ratelimited calls. A better name would be mem_cgroup_flush_stats_ratelimited(). Link: https://lkml.kernel.org/r/20230330191801.1967435-3-yosryahmed@google.com Signed-off-by: Yosry Ahmed Suggested-by: Johannes Weiner Acked-by: Shakeel Butt Acked-by: Johannes Weiner Acked-by: Michal Hocko Cc: Jens Axboe Cc: Josef Bacik Cc: Michal Hocko Cc: Michal Koutný Cc: Muchun Song Cc: Roman Gushchin Cc: Tejun Heo Cc: Vasily Averin Cc: Zefan Li Signed-off-by: Andrew Morton --- include/linux/memcontrol.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index aa69ea98e2d8..00a88cf947e1 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -1038,7 +1038,7 @@ static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec, } void mem_cgroup_flush_stats(void); -void mem_cgroup_flush_stats_delayed(void); +void mem_cgroup_flush_stats_ratelimited(void); void __mod_memcg_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, int val); @@ -1536,7 +1536,7 @@ static inline void mem_cgroup_flush_stats(void) { } -static inline void mem_cgroup_flush_stats_delayed(void) +static inline void mem_cgroup_flush_stats_ratelimited(void) { } -- cgit v1.2.3 From 9fad9aee1f267a8ad1f86b87ae70b2c4d6796164 Mon Sep 17 00:00:00 2001 From: Yosry Ahmed Date: Thu, 30 Mar 2023 19:17:58 +0000 Subject: memcg: sleep during flushing stats in safe contexts MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Currently, all contexts that flush memcg stats do so with sleeping not allowed. Some of these contexts are perfectly safe to sleep in, such as reading cgroup files from userspace or the background periodic flusher. Flushing is an expensive operation that scales with the number of cpus and the number of cgroups in the system, so avoid doing it atomically where possible. Refactor the code to make mem_cgroup_flush_stats() non-atomic (aka sleepable), and provide a separate atomic version. The atomic version is used in reclaim, refault, writeback, and in mem_cgroup_usage(). All other code paths are left to use the non-atomic version. This includes callbacks for userspace reads and the periodic flusher. Since refault is the only caller of mem_cgroup_flush_stats_ratelimited(), change it to mem_cgroup_flush_stats_atomic_ratelimited(). Reclaim and refault code paths are modified to do non-atomic flushing in separate later patches -- so it will eventually be changed back to mem_cgroup_flush_stats_ratelimited(). Link: https://lkml.kernel.org/r/20230330191801.1967435-6-yosryahmed@google.com Signed-off-by: Yosry Ahmed Acked-by: Shakeel Butt Acked-by: Michal Hocko Acked-by: Johannes Weiner Cc: Jens Axboe Cc: Josef Bacik Cc: Michal Hocko Cc: Michal Koutný Cc: Muchun Song Cc: Roman Gushchin Cc: Tejun Heo Cc: Vasily Averin Cc: Zefan Li Signed-off-by: Andrew Morton --- include/linux/memcontrol.h | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 00a88cf947e1..3db355e6677f 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -1038,7 +1038,8 @@ static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec, } void mem_cgroup_flush_stats(void); -void mem_cgroup_flush_stats_ratelimited(void); +void mem_cgroup_flush_stats_atomic(void); +void mem_cgroup_flush_stats_atomic_ratelimited(void); void __mod_memcg_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, int val); @@ -1536,7 +1537,11 @@ static inline void mem_cgroup_flush_stats(void) { } -static inline void mem_cgroup_flush_stats_ratelimited(void) +static inline void mem_cgroup_flush_stats_atomic(void) +{ +} + +static inline void mem_cgroup_flush_stats_atomic_ratelimited(void) { } -- cgit v1.2.3 From 4009b2f1887036d30637bc06dd0ade7e18408bb3 Mon Sep 17 00:00:00 2001 From: Yosry Ahmed Date: Thu, 30 Mar 2023 19:17:59 +0000 Subject: workingset: memcg: sleep when flushing stats in workingset_refault() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In workingset_refault(), we call mem_cgroup_flush_stats_atomic_ratelimited() to read accurate stats within an RCU read section and with sleeping disallowed. Move the call above the RCU read section to make it non-atomic. Flushing is an expensive operation that scales with the number of cpus and the number of cgroups in the system, so avoid doing it atomically where possible. Since workingset_refault() is the only caller of mem_cgroup_flush_stats_atomic_ratelimited(), just make it non-atomic, and rename it to mem_cgroup_flush_stats_ratelimited(). Link: https://lkml.kernel.org/r/20230330191801.1967435-7-yosryahmed@google.com Signed-off-by: Yosry Ahmed Acked-by: Shakeel Butt Acked-by: Johannes Weiner Acked-by: Michal Hocko Cc: Jens Axboe Cc: Josef Bacik Cc: Michal Hocko Cc: Michal Koutný Cc: Muchun Song Cc: Roman Gushchin Cc: Tejun Heo Cc: Vasily Averin Cc: Zefan Li Signed-off-by: Andrew Morton --- include/linux/memcontrol.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 3db355e6677f..222d7370134c 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -1039,7 +1039,7 @@ static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec, void mem_cgroup_flush_stats(void); void mem_cgroup_flush_stats_atomic(void); -void mem_cgroup_flush_stats_atomic_ratelimited(void); +void mem_cgroup_flush_stats_ratelimited(void); void __mod_memcg_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, int val); @@ -1541,7 +1541,7 @@ static inline void mem_cgroup_flush_stats_atomic(void) { } -static inline void mem_cgroup_flush_stats_atomic_ratelimited(void) +static inline void mem_cgroup_flush_stats_ratelimited(void) { } -- cgit v1.2.3 From 6efc7afb5cc98488410d44695685d003d832534d Mon Sep 17 00:00:00 2001 From: Jiaqi Yan Date: Wed, 29 Mar 2023 08:11:20 -0700 Subject: mm/hwpoison: introduce copy_mc_highpage Similar to how copy_mc_user_highpage is implemented for copy_user_highpage on #MC supported architecture, introduce the #MC handled version of copy_highpage. This helper has immediate usage when khugepaged wants to copy file-backed memory pages and tolerate #MC. Link: https://lkml.kernel.org/r/20230329151121.949896-3-jiaqiyan@google.com Signed-off-by: Jiaqi Yan Reviewed-by: Yang Shi Cc: David Stevens Cc: Hugh Dickins Cc: Kefeng Wang Cc: Kirill A. Shutemov Cc: "Kirill A. Shutemov" Cc: Miaohe Lin Cc: Naoya Horiguchi Cc: Oscar Salvador Cc: Tong Tiangen Cc: Tony Luck Signed-off-by: Andrew Morton --- include/linux/highmem.h | 54 +++++++++++++++++++++++++++++++++++++------------ 1 file changed, 41 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/highmem.h b/include/linux/highmem.h index 9c7cdaa3de8c..4de1dbcd3ef6 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -315,7 +315,29 @@ static inline void copy_user_highpage(struct page *to, struct page *from, #endif +#ifndef __HAVE_ARCH_COPY_HIGHPAGE + +static inline void copy_highpage(struct page *to, struct page *from) +{ + char *vfrom, *vto; + + vfrom = kmap_local_page(from); + vto = kmap_local_page(to); + copy_page(vto, vfrom); + kmsan_copy_page_meta(to, from); + kunmap_local(vto); + kunmap_local(vfrom); +} + +#endif + #ifdef copy_mc_to_kernel +/* + * If architecture supports machine check exception handling, define the + * #MC versions of copy_user_highpage and copy_highpage. They copy a memory + * page with #MC in source page (@from) handled, and return the number + * of bytes not copied if there was a #MC, otherwise 0 for success. + */ static inline int copy_mc_user_highpage(struct page *to, struct page *from, unsigned long vaddr, struct vm_area_struct *vma) { @@ -332,29 +354,35 @@ static inline int copy_mc_user_highpage(struct page *to, struct page *from, return ret; } -#else -static inline int copy_mc_user_highpage(struct page *to, struct page *from, - unsigned long vaddr, struct vm_area_struct *vma) -{ - copy_user_highpage(to, from, vaddr, vma); - return 0; -} -#endif -#ifndef __HAVE_ARCH_COPY_HIGHPAGE - -static inline void copy_highpage(struct page *to, struct page *from) +static inline int copy_mc_highpage(struct page *to, struct page *from) { + unsigned long ret; char *vfrom, *vto; vfrom = kmap_local_page(from); vto = kmap_local_page(to); - copy_page(vto, vfrom); - kmsan_copy_page_meta(to, from); + ret = copy_mc_to_kernel(vto, vfrom, PAGE_SIZE); + if (!ret) + kmsan_copy_page_meta(to, from); kunmap_local(vto); kunmap_local(vfrom); + + return ret; +} +#else +static inline int copy_mc_user_highpage(struct page *to, struct page *from, + unsigned long vaddr, struct vm_area_struct *vma) +{ + copy_user_highpage(to, from, vaddr, vma); + return 0; } +static inline int copy_mc_highpage(struct page *to, struct page *from) +{ + copy_highpage(to, from); + return 0; +} #endif static inline void memcpy_page(struct page *dst_page, size_t dst_off, -- cgit v1.2.3 From b4aca54792e76556bb9f8661bab07b4bf2eb4e5f Mon Sep 17 00:00:00 2001 From: Steven Price Date: Wed, 5 Apr 2023 11:38:19 +0100 Subject: smaps: fix defined but not used smaps_shmem_walk_ops MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When !CONFIG_SHMEM smaps_shmem_walk_ops is defined but not used, triggering a compiler warning. To avoid the warning remove the #ifdef around the usage. This has no effect because shmem_mapping() is a stub returning false when !CONFIG_SHMEM so the code will be compiled out, however we now need to also provide a stub for shmem_swap_usage(). Link: https://lkml.kernel.org/r/20230405103819.151246-1-steven.price@arm.com Fixes: 7b86ac3371b7 ("pagewalk: separate function pointers from iterator data") Signed-off-by: Steven Price Reported-by: kernel test robot Link: https://lore.kernel.org/oe-kbuild-all/202304031749.UiyJpxzF-lkp@intel.com/ Reviewed-by: Jason Gunthorpe Cc: Christoph Hellwig Cc: Alexey Dobriyan Cc: Thomas Hellström Signed-off-by: Andrew Morton --- include/linux/shmem_fs.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index 3bb8d21edbb3..b9516a9802bf 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -96,7 +96,14 @@ int shmem_unuse(unsigned int type); extern bool shmem_is_huge(struct inode *inode, pgoff_t index, bool shmem_huge_force, struct mm_struct *mm, unsigned long vm_flags); +#ifdef CONFIG_SHMEM extern unsigned long shmem_swap_usage(struct vm_area_struct *vma); +#else +static inline unsigned long shmem_swap_usage(struct vm_area_struct *vma) +{ + return 0; +} +#endif extern unsigned long shmem_partial_swap_usage(struct address_space *mapping, pgoff_t start, pgoff_t end); -- cgit v1.2.3 From e87340ca5c9cecc8a11daf1a2dcabf23f06a4e10 Mon Sep 17 00:00:00 2001 From: ZhangPeng Date: Mon, 10 Apr 2023 21:39:29 +0800 Subject: userfaultfd: convert copy_huge_page_from_user() to copy_folio_from_user() Replace copy_huge_page_from_user() with copy_folio_from_user(). copy_folio_from_user() does the same as copy_huge_page_from_user(), but takes in a folio instead of a page. Convert page_kaddr to kaddr in copy_folio_from_user() to do indenting cleanup. Link: https://lkml.kernel.org/r/20230410133932.32288-4-zhangpeng362@huawei.com Signed-off-by: ZhangPeng Reviewed-by: Sidhartha Kumar Reviewed-by: Mike Kravetz Cc: Kefeng Wang Cc: Matthew Wilcox Cc: Muchun Song Cc: Nanyong Sun Cc: Vishal Moola (Oracle) Signed-off-by: Andrew Morton --- include/linux/mm.h | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 5e5ef6ee4003..01a009efc2cb 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3681,10 +3681,9 @@ extern void copy_user_huge_page(struct page *dst, struct page *src, unsigned long addr_hint, struct vm_area_struct *vma, unsigned int pages_per_huge_page); -extern long copy_huge_page_from_user(struct page *dst_page, - const void __user *usr_src, - unsigned int pages_per_huge_page, - bool allow_pagefault); +long copy_folio_from_user(struct folio *dst_folio, + const void __user *usr_src, + bool allow_pagefault); /** * vma_is_special_huge - Are transhuge page-table entries considered special? -- cgit v1.2.3 From 0169fd518a8934d8d723659752b07589ecc9f692 Mon Sep 17 00:00:00 2001 From: ZhangPeng Date: Mon, 10 Apr 2023 21:39:30 +0800 Subject: userfaultfd: convert mfill_atomic_hugetlb() to use a folio Convert hugetlb_mfill_atomic_pte() to take in a folio pointer instead of a page pointer. Convert mfill_atomic_hugetlb() to use a folio. Link: https://lkml.kernel.org/r/20230410133932.32288-5-zhangpeng362@huawei.com Signed-off-by: ZhangPeng Reviewed-by: Sidhartha Kumar Reviewed-by: Mike Kravetz Cc: Kefeng Wang Cc: Matthew Wilcox Cc: Muchun Song Cc: Nanyong Sun Cc: Vishal Moola (Oracle) Signed-off-by: Andrew Morton --- include/linux/hugetlb.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 2a758bcd6719..28703fe22386 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -163,7 +163,7 @@ int hugetlb_mfill_atomic_pte(pte_t *dst_pte, unsigned long dst_addr, unsigned long src_addr, uffd_flags_t flags, - struct page **pagep); + struct folio **foliop); #endif /* CONFIG_USERFAULTFD */ bool hugetlb_reserve_pages(struct inode *inode, long from, long to, struct vm_area_struct *vma, @@ -397,7 +397,7 @@ static inline int hugetlb_mfill_atomic_pte(pte_t *dst_pte, unsigned long dst_addr, unsigned long src_addr, uffd_flags_t flags, - struct page **pagep) + struct folio **foliop) { BUG(); return 0; -- cgit v1.2.3 From c0e8150e144b62ae467520d0b51c4707c09e897b Mon Sep 17 00:00:00 2001 From: ZhangPeng Date: Mon, 10 Apr 2023 21:39:31 +0800 Subject: mm: convert copy_user_huge_page() to copy_user_large_folio() Replace copy_user_huge_page() with copy_user_large_folio(). copy_user_large_folio() does the same as copy_user_huge_page(), but takes in folios instead of pages. Remove pages_per_huge_page from copy_user_large_folio(), because we can get that from folio_nr_pages(dst). Convert copy_user_gigantic_page() to take in folios. Link: https://lkml.kernel.org/r/20230410133932.32288-6-zhangpeng362@huawei.com Signed-off-by: ZhangPeng Cc: Kefeng Wang Cc: Matthew Wilcox Cc: Mike Kravetz Cc: Muchun Song Cc: Nanyong Sun Cc: Sidhartha Kumar Cc: Vishal Moola (Oracle) Signed-off-by: Andrew Morton --- include/linux/mm.h | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 01a009efc2cb..5a3eaa9a1f8c 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3677,10 +3677,9 @@ extern const struct attribute_group memory_failure_attr_group; extern void clear_huge_page(struct page *page, unsigned long addr_hint, unsigned int pages_per_huge_page); -extern void copy_user_huge_page(struct page *dst, struct page *src, - unsigned long addr_hint, - struct vm_area_struct *vma, - unsigned int pages_per_huge_page); +void copy_user_large_folio(struct folio *dst, struct folio *src, + unsigned long addr_hint, + struct vm_area_struct *vma); long copy_folio_from_user(struct folio *dst_folio, const void __user *usr_src, bool allow_pagefault); -- cgit v1.2.3 From d7be6d7eee1bbf98671d7a2c95654322241e2ae4 Mon Sep 17 00:00:00 2001 From: ZhangPeng Date: Mon, 10 Apr 2023 21:39:32 +0800 Subject: userfaultfd: convert mfill_atomic() to use a folio Convert mfill_atomic_pte_copy(), shmem_mfill_atomic_pte() and mfill_atomic_pte() to take in a folio pointer. Convert mfill_atomic() to use a folio. Convert page_kaddr to kaddr in mfill_atomic(). Link: https://lkml.kernel.org/r/20230410133932.32288-7-zhangpeng362@huawei.com Signed-off-by: ZhangPeng Reviewed-by: Mike Kravetz Cc: Kefeng Wang Cc: Matthew Wilcox Cc: Muchun Song Cc: Nanyong Sun Cc: Sidhartha Kumar Cc: Vishal Moola (Oracle) Signed-off-by: Andrew Morton --- include/linux/shmem_fs.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index b9516a9802bf..9029abd29b1c 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -165,10 +165,10 @@ extern int shmem_mfill_atomic_pte(pmd_t *dst_pmd, unsigned long dst_addr, unsigned long src_addr, uffd_flags_t flags, - struct page **pagep); + struct folio **foliop); #else /* !CONFIG_SHMEM */ #define shmem_mfill_atomic_pte(dst_pmd, dst_vma, dst_addr, \ - src_addr, flags, pagep) ({ BUG(); 0; }) + src_addr, flags, foliop) ({ BUG(); 0; }) #endif /* CONFIG_SHMEM */ #endif /* CONFIG_USERFAULTFD */ -- cgit v1.2.3 From 87a7ae75d7383afa998f57656d1d14e2a730cc47 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Tue, 11 Apr 2023 19:52:13 +0530 Subject: mm/vmemmap/devdax: fix kernel crash when probing devdax devices commit 4917f55b4ef9 ("mm/sparse-vmemmap: improve memory savings for compound devmaps") added support for using optimized vmmemap for devdax devices. But how vmemmap mappings are created are architecture specific. For example, powerpc with hash translation doesn't have vmemmap mappings in init_mm page table instead they are bolted table entries in the hardware page table vmemmap_populate_compound_pages() used by vmemmap optimization code is not aware of these architecture-specific mapping. Hence allow architecture to opt for this feature. I selected architectures supporting HUGETLB_PAGE_OPTIMIZE_VMEMMAP option as also supporting this feature. This patch fixes the below crash on ppc64. BUG: Unable to handle kernel data access on write at 0xc00c000100400038 Faulting instruction address: 0xc000000001269d90 Oops: Kernel access of bad area, sig: 11 [#1] LE PAGE_SIZE=64K MMU=Hash SMP NR_CPUS=2048 NUMA pSeries Modules linked in: CPU: 7 PID: 1 Comm: swapper/0 Not tainted 6.3.0-rc5-150500.34-default+ #2 5c90a668b6bbd142599890245c2fb5de19d7d28a Hardware name: IBM,9009-42G POWER9 (raw) 0x4e0202 0xf000005 of:IBM,FW950.40 (VL950_099) hv:phyp pSeries NIP: c000000001269d90 LR: c0000000004c57d4 CTR: 0000000000000000 REGS: c000000003632c30 TRAP: 0300 Not tainted (6.3.0-rc5-150500.34-default+) MSR: 8000000000009033 CR: 24842228 XER: 00000000 CFAR: c0000000004c57d0 DAR: c00c000100400038 DSISR: 42000000 IRQMASK: 0 .... NIP [c000000001269d90] __init_single_page.isra.74+0x14/0x4c LR [c0000000004c57d4] __init_zone_device_page+0x44/0xd0 Call Trace: [c000000003632ed0] [c000000003632f60] 0xc000000003632f60 (unreliable) [c000000003632f10] [c0000000004c5ca0] memmap_init_zone_device+0x170/0x250 [c000000003632fe0] [c0000000005575f8] memremap_pages+0x2c8/0x7f0 [c0000000036330c0] [c000000000557b5c] devm_memremap_pages+0x3c/0xa0 [c000000003633100] [c000000000d458a8] dev_dax_probe+0x108/0x3e0 [c0000000036331a0] [c000000000d41430] dax_bus_probe+0xb0/0x140 [c0000000036331d0] [c000000000cef27c] really_probe+0x19c/0x520 [c000000003633260] [c000000000cef6b4] __driver_probe_device+0xb4/0x230 [c0000000036332e0] [c000000000cef888] driver_probe_device+0x58/0x120 [c000000003633320] [c000000000cefa6c] __device_attach_driver+0x11c/0x1e0 [c0000000036333a0] [c000000000cebc58] bus_for_each_drv+0xa8/0x130 [c000000003633400] [c000000000ceefcc] __device_attach+0x15c/0x250 [c0000000036334a0] [c000000000ced458] bus_probe_device+0x108/0x110 [c0000000036334f0] [c000000000ce92dc] device_add+0x7fc/0xa10 [c0000000036335b0] [c000000000d447c8] devm_create_dev_dax+0x1d8/0x530 [c000000003633640] [c000000000d46b60] __dax_pmem_probe+0x200/0x270 [c0000000036337b0] [c000000000d46bf0] dax_pmem_probe+0x20/0x70 [c0000000036337d0] [c000000000d2279c] nvdimm_bus_probe+0xac/0x2b0 [c000000003633860] [c000000000cef27c] really_probe+0x19c/0x520 [c0000000036338f0] [c000000000cef6b4] __driver_probe_device+0xb4/0x230 [c000000003633970] [c000000000cef888] driver_probe_device+0x58/0x120 [c0000000036339b0] [c000000000cefd08] __driver_attach+0x1d8/0x240 [c000000003633a30] [c000000000cebb04] bus_for_each_dev+0xb4/0x130 [c000000003633a90] [c000000000cee564] driver_attach+0x34/0x50 [c000000003633ab0] [c000000000ced878] bus_add_driver+0x218/0x300 [c000000003633b40] [c000000000cf1144] driver_register+0xa4/0x1b0 [c000000003633bb0] [c000000000d21a0c] __nd_driver_register+0x5c/0x100 [c000000003633c10] [c00000000206a2e8] dax_pmem_init+0x34/0x48 [c000000003633c30] [c0000000000132d0] do_one_initcall+0x60/0x320 [c000000003633d00] [c0000000020051b0] kernel_init_freeable+0x360/0x400 [c000000003633de0] [c000000000013764] kernel_init+0x34/0x1d0 [c000000003633e50] [c00000000000de14] ret_from_kernel_thread+0x5c/0x64 Link: https://lkml.kernel.org/r/20230411142214.64464-1-aneesh.kumar@linux.ibm.com Fixes: 4917f55b4ef9 ("mm/sparse-vmemmap: improve memory savings for compound devmaps") Signed-off-by: Aneesh Kumar K.V Reported-by: Tarun Sahu Reviewed-by: Joao Martins Cc: Muchun Song Cc: Dan Williams Cc: Mike Kravetz Cc: Signed-off-by: Andrew Morton --- include/linux/mm.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 5a3eaa9a1f8c..21a7e2460084 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3560,6 +3560,22 @@ void vmemmap_populate_print_last(void); void vmemmap_free(unsigned long start, unsigned long end, struct vmem_altmap *altmap); #endif + +#ifdef CONFIG_ARCH_WANT_HUGETLB_PAGE_OPTIMIZE_VMEMMAP +static inline bool vmemmap_can_optimize(struct vmem_altmap *altmap, + struct dev_pagemap *pgmap) +{ + return is_power_of_2(sizeof(struct page)) && + pgmap && (pgmap_vmemmap_nr(pgmap) > 1) && !altmap; +} +#else +static inline bool vmemmap_can_optimize(struct vmem_altmap *altmap, + struct dev_pagemap *pgmap) +{ + return false; +} +#endif + void register_page_bootmem_memmap(unsigned long section_nr, struct page *map, unsigned long nr_pages); -- cgit v1.2.3 From 0b376f1e0ff555435597fa16823ae0f30b2883e3 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Wed, 12 Apr 2023 10:30:25 +0530 Subject: mm/hugetlb_vmemmap: rename ARCH_WANT_HUGETLB_PAGE_OPTIMIZE_VMEMMAP Now we use ARCH_WANT_HUGETLB_PAGE_OPTIMIZE_VMEMMAP config option to indicate devdax and hugetlb vmemmap optimization support. Hence rename that to a generic ARCH_WANT_OPTIMIZE_VMEMMAP Link: https://lkml.kernel.org/r/20230412050025.84346-2-aneesh.kumar@linux.ibm.com Signed-off-by: Aneesh Kumar K.V Reviewed-by: Muchun Song Cc: Joao Martins Cc: Dan Williams Cc: Mike Kravetz Cc: Tarun Sahu Signed-off-by: Andrew Morton --- include/linux/mm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 21a7e2460084..0b514de43143 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3561,7 +3561,7 @@ void vmemmap_free(unsigned long start, unsigned long end, struct vmem_altmap *altmap); #endif -#ifdef CONFIG_ARCH_WANT_HUGETLB_PAGE_OPTIMIZE_VMEMMAP +#ifdef CONFIG_ARCH_WANT_OPTIMIZE_VMEMMAP static inline bool vmemmap_can_optimize(struct vmem_altmap *altmap, struct dev_pagemap *pgmap) { -- cgit v1.2.3 From 1cb9dc4b475c7418f925ab0c97b6750007d9f52e Mon Sep 17 00:00:00 2001 From: Liu Shixin Date: Thu, 13 Apr 2023 21:13:49 +0800 Subject: mm: hwpoison: support recovery from HugePage copy-on-write faults copy-on-write of hugetlb user pages with uncorrectable errors will result in a kernel crash. This is because the copy is performed in kernel mode and in general we can not handle accessing memory with such errors while in kernel mode. Commit a873dfe1032a ("mm, hwpoison: try to recover from copy-on write faults") introduced the routine copy_user_highpage_mc() to gracefully handle copying of user pages with uncorrectable errors. However, the separate hugetlb copy-on-write code paths were not modified as part of commit a873dfe1032a. Modify hugetlb copy-on-write code paths to use copy_mc_user_highpage() so that they can also gracefully handle uncorrectable errors in user pages. This involves changing the hugetlb specific routine copy_user_large_folio() from type void to int so that it can return an error. Modify the hugetlb userfaultfd code in the same way so that it can return -EHWPOISON if it encounters an uncorrectable error. Link: https://lkml.kernel.org/r/20230413131349.2524210-1-liushixin2@huawei.com Signed-off-by: Liu Shixin Acked-by: Mike Kravetz Reviewed-by: Naoya Horiguchi Cc: Miaohe Lin Cc: Muchun Song Cc: Tony Luck Signed-off-by: Andrew Morton --- include/linux/mm.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 0b514de43143..2772a1800cf3 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3693,9 +3693,9 @@ extern const struct attribute_group memory_failure_attr_group; extern void clear_huge_page(struct page *page, unsigned long addr_hint, unsigned int pages_per_huge_page); -void copy_user_large_folio(struct folio *dst, struct folio *src, - unsigned long addr_hint, - struct vm_area_struct *vma); +int copy_user_large_folio(struct folio *dst, struct folio *src, + unsigned long addr_hint, + struct vm_area_struct *vma); long copy_folio_from_user(struct folio *dst_folio, const void __user *usr_src, bool allow_pagefault); -- cgit v1.2.3 From bb1508c24c9c361e6344308c8de2cb81d7f228ba Mon Sep 17 00:00:00 2001 From: Alexander Potapenko Date: Thu, 13 Apr 2023 15:12:22 +0200 Subject: mm: kmsan: apply __must_check to non-void functions Non-void KMSAN hooks may return error codes that indicate that KMSAN failed to reflect the changed memory state in the metadata (e.g. it could not create the necessary memory mappings). In such cases the callers should handle the errors to prevent the tool from using the inconsistent metadata in the future. We mark non-void hooks with __must_check so that error handling is not skipped. Link: https://lkml.kernel.org/r/20230413131223.4135168-3-glider@google.com Signed-off-by: Alexander Potapenko Reviewed-by: Marco Elver Cc: Christoph Hellwig Cc: Dipanjan Das Cc: Dmitry Vyukov Cc: Uladzislau Rezki (Sony) Signed-off-by: Andrew Morton --- include/linux/kmsan.h | 43 ++++++++++++++++++++++--------------------- 1 file changed, 22 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kmsan.h b/include/linux/kmsan.h index 30b17647ce3c..e0c23a32cdf0 100644 --- a/include/linux/kmsan.h +++ b/include/linux/kmsan.h @@ -54,7 +54,8 @@ void __init kmsan_init_runtime(void); * Freed pages are either returned to buddy allocator or held back to be used * as metadata pages. */ -bool __init kmsan_memblock_free_pages(struct page *page, unsigned int order); +bool __init __must_check kmsan_memblock_free_pages(struct page *page, + unsigned int order); /** * kmsan_alloc_page() - Notify KMSAN about an alloc_pages() call. @@ -137,9 +138,11 @@ void kmsan_kfree_large(const void *ptr); * vmalloc metadata address range. Returns 0 on success, callers must check * for non-zero return value. */ -int kmsan_vmap_pages_range_noflush(unsigned long start, unsigned long end, - pgprot_t prot, struct page **pages, - unsigned int page_shift); +int __must_check kmsan_vmap_pages_range_noflush(unsigned long start, + unsigned long end, + pgprot_t prot, + struct page **pages, + unsigned int page_shift); /** * kmsan_vunmap_kernel_range_noflush() - Notify KMSAN about a vunmap. @@ -163,9 +166,9 @@ void kmsan_vunmap_range_noflush(unsigned long start, unsigned long end); * virtual memory. Returns 0 on success, callers must check for non-zero return * value. */ -int kmsan_ioremap_page_range(unsigned long addr, unsigned long end, - phys_addr_t phys_addr, pgprot_t prot, - unsigned int page_shift); +int __must_check kmsan_ioremap_page_range(unsigned long addr, unsigned long end, + phys_addr_t phys_addr, pgprot_t prot, + unsigned int page_shift); /** * kmsan_iounmap_page_range() - Notify KMSAN about a iounmap_page_range() call. @@ -237,8 +240,8 @@ static inline void kmsan_init_runtime(void) { } -static inline bool kmsan_memblock_free_pages(struct page *page, - unsigned int order) +static inline bool __must_check kmsan_memblock_free_pages(struct page *page, + unsigned int order) { return true; } @@ -251,10 +254,9 @@ static inline void kmsan_task_exit(struct task_struct *task) { } -static inline int kmsan_alloc_page(struct page *page, unsigned int order, - gfp_t flags) +static inline void kmsan_alloc_page(struct page *page, unsigned int order, + gfp_t flags) { - return 0; } static inline void kmsan_free_page(struct page *page, unsigned int order) @@ -283,11 +285,9 @@ static inline void kmsan_kfree_large(const void *ptr) { } -static inline int kmsan_vmap_pages_range_noflush(unsigned long start, - unsigned long end, - pgprot_t prot, - struct page **pages, - unsigned int page_shift) +static inline int __must_check kmsan_vmap_pages_range_noflush( + unsigned long start, unsigned long end, pgprot_t prot, + struct page **pages, unsigned int page_shift) { return 0; } @@ -297,10 +297,11 @@ static inline void kmsan_vunmap_range_noflush(unsigned long start, { } -static inline int kmsan_ioremap_page_range(unsigned long start, - unsigned long end, - phys_addr_t phys_addr, pgprot_t prot, - unsigned int page_shift) +static inline int __must_check kmsan_ioremap_page_range(unsigned long start, + unsigned long end, + phys_addr_t phys_addr, + pgprot_t prot, + unsigned int page_shift) { return 0; } -- cgit v1.2.3 From c7b23b68e2aa93f86a206222d23ccd9a21f5982a Mon Sep 17 00:00:00 2001 From: Yosry Ahmed Date: Thu, 13 Apr 2023 10:40:34 +0000 Subject: mm: vmscan: refactor updating current->reclaim_state During reclaim, we keep track of pages reclaimed from other means than LRU-based reclaim through scan_control->reclaim_state->reclaimed_slab, which we stash a pointer to in current task_struct. However, we keep track of more than just reclaimed slab pages through this. We also use it for clean file pages dropped through pruned inodes, and xfs buffer pages freed. Rename reclaimed_slab to reclaimed, and add a helper function that wraps updating it through current, so that future changes to this logic are contained within include/linux/swap.h. Link: https://lkml.kernel.org/r/20230413104034.1086717-4-yosryahmed@google.com Signed-off-by: Yosry Ahmed Acked-by: Michal Hocko Cc: Alexander Viro Cc: Christoph Lameter Cc: Darrick J. Wong Cc: Dave Chinner Cc: David Hildenbrand Cc: David Rientjes Cc: Hyeonggon Yoo <42.hyeyoo@gmail.com> Cc: Johannes Weiner Cc: Joonsoo Kim Cc: Matthew Wilcox Cc: Miaohe Lin Cc: NeilBrown Cc: Peter Xu Cc: Roman Gushchin Cc: Shakeel Butt Cc: Tim Chen Cc: Vlastimil Babka Cc: Yu Zhao Signed-off-by: Andrew Morton --- include/linux/swap.h | 17 ++++++++++++++++- 1 file changed, 16 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index bfc3b06b5f8f..7f7d5b9ddf7e 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -153,13 +153,28 @@ union swap_header { * memory reclaim */ struct reclaim_state { - unsigned long reclaimed_slab; + /* pages reclaimed outside of LRU-based reclaim */ + unsigned long reclaimed; #ifdef CONFIG_LRU_GEN /* per-thread mm walk data */ struct lru_gen_mm_walk *mm_walk; #endif }; +/* + * mm_account_reclaimed_pages(): account reclaimed pages outside of LRU-based + * reclaim + * @pages: number of pages reclaimed + * + * If the current process is undergoing a reclaim operation, increment the + * number of reclaimed pages by @pages. + */ +static inline void mm_account_reclaimed_pages(unsigned long pages) +{ + if (current->reclaim_state) + current->reclaim_state->reclaimed += pages; +} + #ifdef __KERNEL__ struct address_space; -- cgit v1.2.3 From 7f63cf2d9b9bbe7b90f808927558a66ff737d399 Mon Sep 17 00:00:00 2001 From: Kalesh Singh Date: Thu, 13 Apr 2023 14:43:26 -0700 Subject: mm: Multi-gen LRU: remove wait_event_killable() Android 14 and later default to MGLRU [1] and field telemetry showed occasional long tail latency (>100ms) in the reclaim path. Tracing revealed priority inversion in the reclaim path. In try_to_inc_max_seq(), when high priority tasks were blocked on wait_event_killable(), the preemption of the low priority task to call wake_up_all() caused those high priority tasks to wait longer than necessary. In general, this problem is not different from others of its kind, e.g., one caused by mutex_lock(). However, it is specific to MGLRU because it introduced the new wait queue lruvec->mm_state.wait. The purpose of this new wait queue is to avoid the thundering herd problem. If many direct reclaimers rush into try_to_inc_max_seq(), only one can succeed, i.e., the one to wake up the rest, and the rest who failed might cause premature OOM kills if they do not wait. So far there is no evidence supporting this scenario, based on how often the wait has been hit. And this begs the question how useful the wait queue is in practice. Based on Minchan's recommendation, which is in line with his commit 6d4675e60135 ("mm: don't be stuck to rmap lock on reclaim path") and the rest of the MGLRU code which also uses trylock when possible, remove the wait queue. [1] https://android-review.googlesource.com/q/I7ed7fbfd6ef9ce10053347528125dd98c39e50bf Link: https://lkml.kernel.org/r/20230413214326.2147568-1-kaleshsingh@google.com Fixes: bd74fdaea146 ("mm: multi-gen LRU: support page table walks") Signed-off-by: Kalesh Singh Suggested-by: Minchan Kim Reported-by: Wei Wang Acked-by: Yu Zhao Cc: Minchan Kim Cc: Jan Alexander Steffens (heftig) Cc: Oleksandr Natalenko Cc: Suleiman Souhlal Cc: Suren Baghdasaryan Signed-off-by: Andrew Morton --- include/linux/mmzone.h | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 337956748976..a4889c9d4055 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -443,18 +443,14 @@ enum { struct lru_gen_mm_state { /* set to max_seq after each iteration */ unsigned long seq; - /* where the current iteration continues (inclusive) */ + /* where the current iteration continues after */ struct list_head *head; - /* where the last iteration ended (exclusive) */ + /* where the last iteration ended before */ struct list_head *tail; - /* to wait for the last page table walker to finish */ - struct wait_queue_head wait; /* Bloom filters flip after each iteration */ unsigned long *filters[NR_BLOOM_FILTERS]; /* the mm stats for debugging */ unsigned long stats[NR_HIST_GENS][NR_MM_STATS]; - /* the number of concurrent page table walkers */ - int nr_walkers; }; struct lru_gen_mm_walk { -- cgit v1.2.3 From f7b8f70ba44fb63df47b6fc3204d49ac2885de64 Mon Sep 17 00:00:00 2001 From: Luca Vizzarro Date: Fri, 14 Apr 2023 16:24:58 +0100 Subject: memfd: pass argument of memfd_fcntl as int The interface for fcntl expects the argument passed for the command F_ADD_SEALS to be of type int. The current code wrongly treats it as a long. In order to avoid access to undefined bits, we should explicitly cast the argument to int. This commit changes the signature of all the related and helper functions so that they treat the argument as int instead of long. Link: https://lkml.kernel.org/r/20230414152459.816046-5-Luca.Vizzarro@arm.com Signed-off-by: Luca Vizzarro Cc: Alexander Viro Cc: Christian Brauner Cc: Jeff Layton Cc: Chuck Lever Cc: Kevin Brodsky Cc: Vincenzo Frascino Cc: Szabolcs Nagy Cc: "Theodore Ts'o" Cc: David Laight Cc: Mark Rutland Signed-off-by: Andrew Morton --- include/linux/memfd.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memfd.h b/include/linux/memfd.h index 4f1600413f91..e7abf6fa4c52 100644 --- a/include/linux/memfd.h +++ b/include/linux/memfd.h @@ -5,9 +5,9 @@ #include #ifdef CONFIG_MEMFD_CREATE -extern long memfd_fcntl(struct file *file, unsigned int cmd, unsigned long arg); +extern long memfd_fcntl(struct file *file, unsigned int cmd, unsigned int arg); #else -static inline long memfd_fcntl(struct file *f, unsigned int c, unsigned long a) +static inline long memfd_fcntl(struct file *f, unsigned int c, unsigned int a) { return -EINVAL; } -- cgit v1.2.3 From b0687c1119b4e8c88a651b6e876b7eae28d076e3 Mon Sep 17 00:00:00 2001 From: Noah Goldstein Date: Tue, 4 Apr 2023 17:13:51 -0500 Subject: lib/rbtree: use '+' instead of '|' for setting color. This has a slight benefit for x86 and has no effect on other targets. The benefit to x86 is it change the codegen for setting a node to block from `mov %r0, %r1; or $RB_BLACK, %r1` to `lea RB_BLACK(%r0), %r1` which saves an instructions. In all other cases it just replace ALU with ALU (or -> and) which perform the same on all machines I am aware of. Total instructions in rbtree.o: Before - 802 After - 782 so it saves about 20 `mov` instructions. Link: https://lkml.kernel.org/r/20230404221350.3806566-1-goldstein.w.n@gmail.com Signed-off-by: Noah Goldstein Cc: Michel Lespinasse Signed-off-by: Andrew Morton --- include/linux/rbtree_augmented.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rbtree_augmented.h b/include/linux/rbtree_augmented.h index d1c53e9d8c75..7ee7ed5de722 100644 --- a/include/linux/rbtree_augmented.h +++ b/include/linux/rbtree_augmented.h @@ -156,13 +156,13 @@ RB_DECLARE_CALLBACKS(RBSTATIC, RBNAME, \ static inline void rb_set_parent(struct rb_node *rb, struct rb_node *p) { - rb->__rb_parent_color = rb_color(rb) | (unsigned long)p; + rb->__rb_parent_color = rb_color(rb) + (unsigned long)p; } static inline void rb_set_parent_color(struct rb_node *rb, struct rb_node *p, int color) { - rb->__rb_parent_color = (unsigned long)p | color; + rb->__rb_parent_color = (unsigned long)p + color; } static inline void -- cgit v1.2.3 From a3b2aeac9d154e5e15ddbf19de934c0c606b6acd Mon Sep 17 00:00:00 2001 From: Yang Yang Date: Sat, 8 Apr 2023 17:28:35 +0800 Subject: delayacct: track delays from IRQ/SOFTIRQ Delay accounting does not track the delay of IRQ/SOFTIRQ. While IRQ/SOFTIRQ could have obvious impact on some workloads productivity, such as when workloads are running on system which is busy handling network IRQ/SOFTIRQ. Get the delay of IRQ/SOFTIRQ could help users to reduce such delay. Such as setting interrupt affinity or task affinity, using kernel thread for NAPI etc. This is inspired by "sched/psi: Add PSI_IRQ to track IRQ/SOFTIRQ pressure"[1]. Also fix some code indent problems of older code. And update tools/accounting/getdelays.c: / # ./getdelays -p 156 -di print delayacct stats ON printing IO accounting PID 156 CPU count real total virtual total delay total delay average 15 15836008 16218149 275700790 18.380ms IO count delay total delay average 0 0 0.000ms SWAP count delay total delay average 0 0 0.000ms RECLAIM count delay total delay average 0 0 0.000ms THRASHING count delay total delay average 0 0 0.000ms COMPACT count delay total delay average 0 0 0.000ms WPCOPY count delay total delay average 36 7586118 0.211ms IRQ count delay total delay average 42 929161 0.022ms [1] commit 52b1364ba0b1("sched/psi: Add PSI_IRQ to track IRQ/SOFTIRQ pressure") Link: https://lkml.kernel.org/r/202304081728353557233@zte.com.cn Signed-off-by: Yang Yang Cc: Jiang Xuexin Cc: wangyong Cc: junhua huang Cc: Balbir Singh Cc: Ingo Molnar Cc: Jonathan Corbet Cc: Juri Lelli Cc: Peter Zijlstra Signed-off-by: Andrew Morton --- include/linux/delayacct.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/delayacct.h b/include/linux/delayacct.h index 0da97dba9ef8..6639f48dac36 100644 --- a/include/linux/delayacct.h +++ b/include/linux/delayacct.h @@ -48,10 +48,13 @@ struct task_delay_info { u64 wpcopy_start; u64 wpcopy_delay; /* wait for write-protect copy */ + u64 irq_delay; /* wait for IRQ/SOFTIRQ */ + u32 freepages_count; /* total count of memory reclaim */ u32 thrashing_count; /* total count of thrash waits */ u32 compact_count; /* total count of memory compact */ u32 wpcopy_count; /* total count of write-protect copy */ + u32 irq_count; /* total count of IRQ/SOFTIRQ */ }; #endif @@ -81,6 +84,7 @@ extern void __delayacct_compact_start(void); extern void __delayacct_compact_end(void); extern void __delayacct_wpcopy_start(void); extern void __delayacct_wpcopy_end(void); +extern void __delayacct_irq(struct task_struct *task, u32 delta); static inline void delayacct_tsk_init(struct task_struct *tsk) { @@ -215,6 +219,15 @@ static inline void delayacct_wpcopy_end(void) __delayacct_wpcopy_end(); } +static inline void delayacct_irq(struct task_struct *task, u32 delta) +{ + if (!static_branch_unlikely(&delayacct_key)) + return; + + if (task->delays) + __delayacct_irq(task, delta); +} + #else static inline void delayacct_init(void) {} @@ -253,6 +266,8 @@ static inline void delayacct_wpcopy_start(void) {} static inline void delayacct_wpcopy_end(void) {} +static inline void delayacct_irq(struct task_struct *task, u32 delta) +{} #endif /* CONFIG_TASK_DELAY_ACCT */ -- cgit v1.2.3 From 4248d0083ec5817eebfb916c54950d100b3468ee Mon Sep 17 00:00:00 2001 From: Longlong Xia Date: Fri, 14 Apr 2023 10:17:41 +0800 Subject: mm: ksm: support hwpoison for ksm page hwpoison_user_mappings() is updated to support ksm pages, and add collect_procs_ksm() to collect processes when the error hit an ksm page. The difference from collect_procs_anon() is that it also needs to traverse the rmap-item list on the stable node of the ksm page. At the same time, add_to_kill_ksm() is added to handle ksm pages. And task_in_to_kill_list() is added to avoid duplicate addition of tsk to the to_kill list. This is because when scanning the list, if the pages that make up the ksm page all come from the same process, they may be added repeatedly. Link: https://lkml.kernel.org/r/20230414021741.2597273-3-xialonglong1@huawei.com Signed-off-by: Longlong Xia Tested-by: Naoya Horiguchi Reviewed-by: Kefeng Wang Cc: Miaohe Lin Cc: Nanyong Sun Signed-off-by: Andrew Morton --- include/linux/ksm.h | 11 +++++++++++ include/linux/mm.h | 7 +++++++ 2 files changed, 18 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ksm.h b/include/linux/ksm.h index 7e232ba59b86..d9e701326a88 100644 --- a/include/linux/ksm.h +++ b/include/linux/ksm.h @@ -51,6 +51,10 @@ struct page *ksm_might_need_to_copy(struct page *page, void rmap_walk_ksm(struct folio *folio, struct rmap_walk_control *rwc); void folio_migrate_ksm(struct folio *newfolio, struct folio *folio); +#ifdef CONFIG_MEMORY_FAILURE +void collect_procs_ksm(struct page *page, struct list_head *to_kill, + int force_early); +#endif #else /* !CONFIG_KSM */ static inline int ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm) @@ -62,6 +66,13 @@ static inline void ksm_exit(struct mm_struct *mm) { } +#ifdef CONFIG_MEMORY_FAILURE +static inline void collect_procs_ksm(struct page *page, + struct list_head *to_kill, int force_early) +{ +} +#endif + #ifdef CONFIG_MMU static inline int ksm_madvise(struct vm_area_struct *vma, unsigned long start, unsigned long end, int advice, unsigned long *vm_flags) diff --git a/include/linux/mm.h b/include/linux/mm.h index 2772a1800cf3..37554b08bb28 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3604,6 +3604,7 @@ extern int __get_huge_page_for_hwpoison(unsigned long pfn, int flags, bool *migratable_cleared); void num_poisoned_pages_inc(unsigned long pfn); void num_poisoned_pages_sub(unsigned long pfn, long i); +struct task_struct *task_early_kill(struct task_struct *tsk, int force_early); #else static inline void memory_failure_queue(unsigned long pfn, int flags) { @@ -3624,6 +3625,12 @@ static inline void num_poisoned_pages_sub(unsigned long pfn, long i) } #endif +#if defined(CONFIG_MEMORY_FAILURE) && defined(CONFIG_KSM) +void add_to_kill_ksm(struct task_struct *tsk, struct page *p, + struct vm_area_struct *vma, struct list_head *to_kill, + unsigned long ksm_addr); +#endif + #if defined(CONFIG_MEMORY_FAILURE) && defined(CONFIG_MEMORY_HOTPLUG) extern void memblk_nr_poison_inc(unsigned long pfn); extern void memblk_nr_poison_sub(unsigned long pfn, long i); -- cgit v1.2.3 From 980f0799a15c75403f1f9284a32b6056b9660144 Mon Sep 17 00:00:00 2001 From: Hangbin Liu Date: Tue, 18 Apr 2023 11:48:41 +0800 Subject: bonding: add software tx timestamping support Currently, bonding only obtain the timestamp (ts) information of the active slave, which is available only for modes 1, 5, and 6. For other modes, bonding only has software rx timestamping support. However, some users who use modes such as LACP also want tx timestamp support. To address this issue, let's check the ts information of each slave. If all slaves support tx timestamping, we can enable tx timestamping support for the bond. Add a note that the get_ts_info may be called with RCU, or rtnl or reference on the device in ethtool.h> Suggested-by: Miroslav Lichvar Signed-off-by: Hangbin Liu Acked-by: Jay Vosburgh Link: https://lore.kernel.org/r/20230418034841.2566262-1-liuhangbin@gmail.com Signed-off-by: Jakub Kicinski --- include/linux/ethtool.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 798d35890118..62b61527bcc4 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -711,6 +711,7 @@ struct ethtool_mm_stats { * @get_dump_data: Get dump data. * @set_dump: Set dump specific flags to the device. * @get_ts_info: Get the time stamping and PTP hardware clock capabilities. + * It may be called with RCU, or rtnl or reference on the device. * Drivers supporting transmit time stamps in software should set this to * ethtool_op_get_ts_info(). * @get_module_info: Get the size and type of the eeprom contained within -- cgit v1.2.3 From e5029edd53937a29801ef507cee12e657ff31ea9 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Mon, 17 Apr 2023 17:17:26 +0200 Subject: leds: Provide stubs for when CLASS_LED & NEW_LEDS are disabled Provide stubs for devm_led_classdev_register_ext() and led_init_default_state_get() so that LED drivers embedded within other drivers such as PHYs and Ethernet switches still build when LEDS_CLASS or NEW_LEDS are disabled. This also helps with Kconfig dependencies, which are somewhat hairy for phylib and mdio and only get worse when adding a dependency on LED_CLASS. Signed-off-by: Andrew Lunn Signed-off-by: Christian Marangi Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/leds.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include/linux') diff --git a/include/linux/leds.h b/include/linux/leds.h index d71201a968b6..aa48e643f655 100644 --- a/include/linux/leds.h +++ b/include/linux/leds.h @@ -82,7 +82,15 @@ struct led_init_data { bool devname_mandatory; }; +#if IS_ENABLED(CONFIG_NEW_LEDS) enum led_default_state led_init_default_state_get(struct fwnode_handle *fwnode); +#else +static inline enum led_default_state +led_init_default_state_get(struct fwnode_handle *fwnode) +{ + return LEDS_DEFSTATE_OFF; +} +#endif struct led_hw_trigger_type { int dummy; @@ -217,9 +225,19 @@ static inline int led_classdev_register(struct device *parent, return led_classdev_register_ext(parent, led_cdev, NULL); } +#if IS_ENABLED(CONFIG_LEDS_CLASS) int devm_led_classdev_register_ext(struct device *parent, struct led_classdev *led_cdev, struct led_init_data *init_data); +#else +static inline int +devm_led_classdev_register_ext(struct device *parent, + struct led_classdev *led_cdev, + struct led_init_data *init_data) +{ + return 0; +} +#endif static inline int devm_led_classdev_register(struct device *parent, struct led_classdev *led_cdev) -- cgit v1.2.3 From 01e5b728e9e43ae444e0369695a5f72209906464 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Mon, 17 Apr 2023 17:17:27 +0200 Subject: net: phy: Add a binding for PHY LEDs Define common binding parsing for all PHY drivers with LEDs using phylib. Parse the DT as part of the phy_probe and add LEDs to the linux LED class infrastructure. For the moment, provide a dummy brightness function, which will later be replaced with a call into the PHY driver. This allows testing since the LED core might otherwise reject an LED whose brightness cannot be set. Add a dependency on LED_CLASS. It either needs to be built in, or not enabled, since a modular build can result in linker errors. Signed-off-by: Andrew Lunn Signed-off-by: Christian Marangi Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/phy.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 2f83cfc206e5..bd6b5e9bb729 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -14,6 +14,7 @@ #include #include #include +#include #include #include #include @@ -600,6 +601,7 @@ struct macsec_ops; * @phy_num_led_triggers: Number of triggers in @phy_led_triggers * @led_link_trigger: LED trigger for link up/down * @last_triggered: last LED trigger for link speed + * @leds: list of PHY LED structures * @master_slave_set: User requested master/slave configuration * @master_slave_get: Current master/slave advertisement * @master_slave_state: Current master/slave configuration @@ -699,6 +701,7 @@ struct phy_device { struct phy_led_trigger *led_link_trigger; #endif + struct list_head leds; /* * Interrupt number for this PHY @@ -834,6 +837,19 @@ struct phy_plca_status { bool pst; }; +/** + * struct phy_led: An LED driven by the PHY + * + * @list: List of LEDs + * @led_cdev: Standard LED class structure + * @index: Number of the LED + */ +struct phy_led { + struct list_head list; + struct led_classdev led_cdev; + u8 index; +}; + /** * struct phy_driver - Driver structure for a particular PHY type * -- cgit v1.2.3 From 684818189b04b095b34964ed4a3ea5249a840eab Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Mon, 17 Apr 2023 17:17:28 +0200 Subject: net: phy: phy_device: Call into the PHY driver to set LED brightness Linux LEDs can be software controlled via the brightness file in /sys. LED drivers need to implement a brightness_set function which the core will call. Implement an intermediary in phy_device, which will call into the phy driver if it implements the necessary function. Signed-off-by: Andrew Lunn Signed-off-by: Christian Marangi Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/phy.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index bd6b5e9bb729..f3c7e3c99f24 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -841,15 +841,19 @@ struct phy_plca_status { * struct phy_led: An LED driven by the PHY * * @list: List of LEDs + * @phydev: PHY this LED is attached to * @led_cdev: Standard LED class structure * @index: Number of the LED */ struct phy_led { struct list_head list; + struct phy_device *phydev; struct led_classdev led_cdev; u8 index; }; +#define to_phy_led(d) container_of(d, struct phy_led, led_cdev) + /** * struct phy_driver - Driver structure for a particular PHY type * @@ -1072,6 +1076,15 @@ struct phy_driver { /** @get_plca_status: Return the current PLCA status info */ int (*get_plca_status)(struct phy_device *dev, struct phy_plca_status *plca_st); + + /** + * @led_brightness_set: Set a PHY LED brightness. Index + * indicates which of the PHYs led should be set. Value + * follows the standard LED class meaning, e.g. LED_OFF, + * LED_HALF, LED_FULL. + */ + int (*led_brightness_set)(struct phy_device *dev, + u8 index, enum led_brightness value); }; #define to_phy_driver(d) container_of(to_mdio_common_driver(d), \ struct phy_driver, mdiodrv) -- cgit v1.2.3 From 4e901018432e38eab35d2a352661ce4727795be1 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Mon, 17 Apr 2023 17:17:30 +0200 Subject: net: phy: phy_device: Call into the PHY driver to set LED blinking Linux LEDs can be requested to perform hardware accelerated blinking. Pass this to the PHY driver, if it implements the op. Signed-off-by: Andrew Lunn Signed-off-by: Christian Marangi Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/phy.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index f3c7e3c99f24..c5a0dc829714 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1085,6 +1085,18 @@ struct phy_driver { */ int (*led_brightness_set)(struct phy_device *dev, u8 index, enum led_brightness value); + + /** + * @led_blink_set: Set a PHY LED brightness. Index indicates + * which of the PHYs led should be configured to blink. Delays + * are in milliseconds and if both are zero then a sensible + * default should be chosen. The call should adjust the + * timings in that case and if it can't match the values + * specified exactly. + */ + int (*led_blink_set)(struct phy_device *dev, u8 index, + unsigned long *delay_on, + unsigned long *delay_off); }; #define to_phy_driver(d) container_of(to_mdio_common_driver(d), \ struct phy_driver, mdiodrv) -- cgit v1.2.3 From eb6fba7555a812c07aa984fb9e8e9b151a65ca16 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 17 Apr 2023 08:53:46 -0700 Subject: net: skbuff: hide wifi_acked when CONFIG_WIRELESS not set Datacenter kernel builds will very likely not include WIRELESS, so let them shave 2 bits off the skb by hiding the wifi fields. Reviewed-by: Florian Fainelli Reviewed-by: Eric Dumazet Signed-off-by: Jakub Kicinski Acked-by: Johannes Berg Signed-off-by: David S. Miller --- include/linux/skbuff.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index a823ec3aa326..513f03b23a73 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -953,8 +953,10 @@ struct sk_buff { __u8 l4_hash:1; __u8 sw_hash:1; +#ifdef CONFIG_WIRELESS __u8 wifi_acked_valid:1; __u8 wifi_acked:1; +#endif __u8 no_fcs:1; /* Indicates the inner headers are valid in the skbuff. */ __u8 encapsulation:1; @@ -1187,6 +1189,15 @@ static inline unsigned int skb_napi_id(const struct sk_buff *skb) #endif } +static inline bool skb_wifi_acked_valid(const struct sk_buff *skb) +{ +#ifdef CONFIG_WIRELESS + return skb->wifi_acked_valid; +#else + return 0; +#endif +} + /** * skb_unref - decrement the skb's reference count * @skb: buffer -- cgit v1.2.3 From c24831a13ba2e472f874483525084da2f2feb890 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 17 Apr 2023 08:53:47 -0700 Subject: net: skbuff: hide csum_not_inet when CONFIG_IP_SCTP not set SCTP is not universally deployed, allow hiding its bit from the skb. Reviewed-by: Florian Fainelli Reviewed-by: Eric Dumazet Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/linux/skbuff.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 513f03b23a73..98d6b48f4dcf 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -983,7 +983,9 @@ struct sk_buff { __u8 decrypted:1; #endif __u8 slow_gro:1; +#if IS_ENABLED(CONFIG_IP_SCTP) __u8 csum_not_inet:1; +#endif #ifdef CONFIG_NET_SCHED __u16 tc_index; /* traffic control index */ @@ -5060,7 +5062,19 @@ static inline void skb_reset_redirect(struct sk_buff *skb) static inline bool skb_csum_is_sctp(struct sk_buff *skb) { +#if IS_ENABLED(CONFIG_IP_SCTP) return skb->csum_not_inet; +#else + return 0; +#endif +} + +static inline void skb_reset_csum_not_inet(struct sk_buff *skb) +{ + skb->ip_summed = CHECKSUM_NONE; +#if IS_ENABLED(CONFIG_IP_SCTP) + skb->csum_not_inet = 0; +#endif } static inline void skb_set_kcov_handle(struct sk_buff *skb, -- cgit v1.2.3 From 4398f3f6d1380d9f71a484e1e5d869ba0eaf23d5 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 17 Apr 2023 08:53:48 -0700 Subject: net: skbuff: move alloc_cpu into a potential hole alloc_cpu is currently between 4 byte fields, so it's almost guaranteed to create a 2B hole. It has a knock on effect of creating a 4B hole after @end (and @end and @tail being in different cachelines). None of this matters hugely, but for kernel configs which don't enable all the features there may well be a 2B hole after the bitfield. Move alloc_cpu there. Reviewed-by: Florian Fainelli Reviewed-by: Eric Dumazet Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/linux/skbuff.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 98d6b48f4dcf..2595b2cfba0d 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -991,6 +991,8 @@ struct sk_buff { __u16 tc_index; /* traffic control index */ #endif + u16 alloc_cpu; + union { __wsum csum; struct { @@ -1014,7 +1016,6 @@ struct sk_buff { unsigned int sender_cpu; }; #endif - u16 alloc_cpu; #ifdef CONFIG_NETWORK_SECMARK __u32 secmark; #endif -- cgit v1.2.3 From 4c60d04c2888a542f96fe77ecbdfc242b484f943 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 17 Apr 2023 08:53:49 -0700 Subject: net: skbuff: push nf_trace down the bitfield nf_trace is a debug feature, AFAIU, and yet it sits oddly high in the sk_buff bitfield. Move it down, pushing up dst_pending_confirm and inner_protocol_type. Next change will make nf_trace optional (under Kconfig) and all optional fields should be placed after 2b fields to avoid 2b fields straddling bytes. dst_pending_confirm is L3, so it makes sense next to ignore_df. inner_protocol_type goes up just to keep the balance. Acked-by: Florian Westphal Reviewed-by: Florian Fainelli Reviewed-by: Eric Dumazet Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/linux/skbuff.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 2595b2cfba0d..3ae9e8868afa 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -934,7 +934,7 @@ struct sk_buff { /* public: */ __u8 pkt_type:3; /* see PKT_TYPE_MAX */ __u8 ignore_df:1; - __u8 nf_trace:1; + __u8 dst_pending_confirm:1; __u8 ip_summed:2; __u8 ooo_okay:1; @@ -949,7 +949,7 @@ struct sk_buff { __u8 remcsum_offload:1; __u8 csum_complete_sw:1; __u8 csum_level:2; - __u8 dst_pending_confirm:1; + __u8 inner_protocol_type:1; __u8 l4_hash:1; __u8 sw_hash:1; @@ -967,7 +967,7 @@ struct sk_buff { #endif __u8 ipvs_property:1; - __u8 inner_protocol_type:1; + __u8 nf_trace:1; #ifdef CONFIG_NET_SWITCHDEV __u8 offload_fwd_mark:1; __u8 offload_l3_fwd_mark:1; -- cgit v1.2.3 From 48d80c394d3d1afcb49d26398917f5be27bf44cb Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 17 Apr 2023 08:53:50 -0700 Subject: net: skbuff: hide nf_trace and ipvs_property Accesses to nf_trace and ipvs_property are already wrapped by ifdefs where necessary. Don't allocate the bits for those fields at all if possible. Acked-by: Florian Westphal Acked-by: Simon Horman Reviewed-by: Eric Dumazet Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/linux/skbuff.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 3ae9e8868afa..5f120bbab9da 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -966,8 +966,12 @@ struct sk_buff { __u8 ndisc_nodetype:2; #endif +#if IS_ENABLED(CONFIG_IP_VS) __u8 ipvs_property:1; +#endif +#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) || IS_ENABLED(CONFIG_NF_TABLES) __u8 nf_trace:1; +#endif #ifdef CONFIG_NET_SWITCHDEV __u8 offload_fwd_mark:1; __u8 offload_l3_fwd_mark:1; -- cgit v1.2.3 From 9e05a2599a37295eb2dc5c03441daa6741abed4b Mon Sep 17 00:00:00 2001 From: Ondrej Kozina Date: Tue, 11 Apr 2023 11:09:31 +0200 Subject: sed-opal: geometry feature reporting command Locking range start and locking range length attributes may be require to satisfy restrictions exposed by OPAL2 geometry feature reporting. Geometry reporting feature is described in TCG OPAL SSC, section 3.1.1.4 (ALIGN, LogicalBlockSize, AlignmentGranularity and LowestAlignedLBA). 4.3.5.2.1.1 RangeStart Behavior: [ StartAlignment = (RangeStart modulo AlignmentGranularity) - LowestAlignedLBA ] When processing a Set method or CreateRow method on the Locking table for a non-Global Range row, if: a) the AlignmentRequired (ALIGN above) column in the LockingInfo table is TRUE; b) RangeStart is non-zero; and c) StartAlignment is non-zero, then the method SHALL fail and return an error status code INVALID_PARAMETER. 4.3.5.2.1.2 RangeLength Behavior: If RangeStart is zero, then [ LengthAlignment = (RangeLength modulo AlignmentGranularity) - LowestAlignedLBA ] If RangeStart is non-zero, then [ LengthAlignment = (RangeLength modulo AlignmentGranularity) ] When processing a Set method or CreateRow method on the Locking table for a non-Global Range row, if: a) the AlignmentRequired (ALIGN above) column in the LockingInfo table is TRUE; b) RangeLength is non-zero; and c) LengthAlignment is non-zero, then the method SHALL fail and return an error status code INVALID_PARAMETER In userspace we stuck to logical block size reported by general block device (via sysfs or ioctl), but we can not read 'AlignmentGranularity' or 'LowestAlignedLBA' anywhere else and we need to get those values from sed-opal interface otherwise we will not be able to report or avoid locking range setup INVALID_PARAMETER errors above. Signed-off-by: Ondrej Kozina Reviewed-by: Christoph Hellwig Reviewed-by: Christian Brauner Tested-by: Milan Broz Link: https://lore.kernel.org/r/20230411090931.9193-2-okozina@redhat.com Signed-off-by: Jens Axboe --- include/linux/sed-opal.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sed-opal.h b/include/linux/sed-opal.h index 042c1e2cb0ce..bbae1e52ab4f 100644 --- a/include/linux/sed-opal.h +++ b/include/linux/sed-opal.h @@ -46,6 +46,7 @@ static inline bool is_sed_ioctl(unsigned int cmd) case IOC_OPAL_GENERIC_TABLE_RW: case IOC_OPAL_GET_STATUS: case IOC_OPAL_GET_LR_STATUS: + case IOC_OPAL_GET_GEOMETRY: return true; } return false; -- cgit v1.2.3 From 691d0b782066a6eeeecbfceb7910a8f6184e6105 Mon Sep 17 00:00:00 2001 From: Dai Ngo Date: Tue, 18 Apr 2023 13:19:02 -0700 Subject: SUNRPC: remove the maximum number of retries in call_bind_status Currently call_bind_status places a hard limit of 3 to the number of retries on EACCES error. This limit was done to prevent NLM unlock requests from being hang forever when the server keeps returning garbage. However this change causes problem for cases when NLM service takes longer than 9 seconds to register with the port mapper after a restart. This patch removes this hard coded limit and let the RPC handles the retry based on the standard hard/soft task semantics. Fixes: 0b760113a3a1 ("NLM: Don't hang forever on NLM unlock requests") Reported-by: Helen Chao Tested-by: Helen Chao Signed-off-by: Dai Ngo Reviewed-by: Jeff Layton Signed-off-by: Anna Schumaker --- include/linux/sunrpc/sched.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h index b8ca3ecaf8d7..8ada7dc802d3 100644 --- a/include/linux/sunrpc/sched.h +++ b/include/linux/sunrpc/sched.h @@ -90,8 +90,7 @@ struct rpc_task { #endif unsigned char tk_priority : 2,/* Task priority */ tk_garb_retry : 2, - tk_cred_retry : 2, - tk_rebind_retry : 2; + tk_cred_retry : 2; }; typedef void (*rpc_action)(struct rpc_task *); -- cgit v1.2.3 From f52cc627b832e08a7bcf1b7e81e650ec308fe1d8 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Thu, 13 Apr 2023 15:25:47 -0700 Subject: Revert "net/mlx5: Enable management PF initialization" This reverts commit fe998a3c77b9f989a30a2a01fb00d3729a6d53a4. Paul reports that it causes a regression with IB on CX4 and FW 12.18.1000. In addition I think that the concept of "management PF" is not fully accepted and requires a discussion. Fixes: fe998a3c77b9 ("net/mlx5: Enable management PF initialization") Reported-by: Paul Moore Link: https://lore.kernel.org/all/CAHC9VhQ7A4+msL38WpbOMYjAqLp0EtOjeLh4Dc6SQtD6OUvCQg@mail.gmail.com/ Link: https://lore.kernel.org/r/20230413222547.56901-1-kuba@kernel.org Signed-off-by: Jakub Kicinski --- include/linux/mlx5/driver.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index f33389b42209..7e225e41d55b 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -1211,11 +1211,6 @@ static inline bool mlx5_core_is_vf(const struct mlx5_core_dev *dev) return dev->coredev_type == MLX5_COREDEV_VF; } -static inline bool mlx5_core_is_management_pf(const struct mlx5_core_dev *dev) -{ - return MLX5_CAP_GEN(dev, num_ports) == 1 && !MLX5_CAP_GEN(dev, native_port_num); -} - static inline bool mlx5_core_is_ecpf(const struct mlx5_core_dev *dev) { return dev->caps.embedded_cpu; -- cgit v1.2.3 From 13890626501ffda22b18213ddaf7930473da5792 Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Mon, 10 Apr 2023 15:37:07 -0400 Subject: USB: core: Add routines for endpoint checks in old drivers Many of the older USB drivers in the Linux USB stack were written based simply on a vendor's device specification. They use the endpoint information in the spec and assume these endpoints will always be present, with the properties listed, in any device matching the given vendor and product IDs. While that may have been true back then, with spoofing and fuzzing it is not true any more. More and more we are finding that those old drivers need to perform at least a minimum of checking before they try to use any endpoint other than ep0. To make this checking as simple as possible, we now add a couple of utility routines to the USB core. usb_check_bulk_endpoints() and usb_check_int_endpoints() take an interface pointer together with a list of endpoint addresses (numbers and directions). They check that the interface's current alternate setting includes endpoints with those addresses and that each of these endpoints has the right type: bulk or interrupt, respectively. Although we already have usb_find_common_endpoints() and related routines meant for a similar purpose, they are not well suited for this kind of checking. Those routines find endpoints of various kinds, but only one (either the first or the last) of each kind, and they don't verify that the endpoints' addresses agree with what the caller expects. In theory the new routines could be more general: They could take a particular altsetting as their argument instead of always using the interface's current altsetting. In practice I think this won't matter too much; multiple altsettings tend to be used for transferring media (audio or visual) over isochronous endpoints, not bulk or interrupt. Drivers for such devices will generally require more sophisticated checking than these simplistic routines provide. Signed-off-by: Alan Stern Link: https://lore.kernel.org/r/dd2c8e8c-2c87-44ea-ba17-c64b97e201c9@rowland.harvard.edu Signed-off-by: Greg Kroah-Hartman --- include/linux/usb.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb.h b/include/linux/usb.h index d510fabcafa2..4ae0466c846c 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -291,6 +291,11 @@ void usb_put_intf(struct usb_interface *intf); #define USB_MAXINTERFACES 32 #define USB_MAXIADS (USB_MAXINTERFACES/2) +bool usb_check_bulk_endpoints( + const struct usb_interface *intf, const u8 *ep_addrs); +bool usb_check_int_endpoints( + const struct usb_interface *intf, const u8 *ep_addrs); + /* * USB Resume Timer: Every Host controller driver should drive the resume * signalling on the bus for the amount of time defined by this macro. -- cgit v1.2.3 From ae131f4970f0778f35ed06aeb15bde2fbc1d9619 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Thu, 13 Apr 2023 14:24:15 +0800 Subject: crypto: api - Add crypto_tfm_get Add a crypto_tfm_get interface to allow tfm objects to be shared. They can still be freed in the usual way. This should only be done with tfm objects with no keys. You must also not modify the tfm flags in any way once it becomes shared. Signed-off-by: Herbert Xu Reviewed-by: Simon Horman Signed-off-by: Herbert Xu --- include/linux/crypto.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/crypto.h b/include/linux/crypto.h index fdfa3e8eda43..fa310ac1db59 100644 --- a/include/linux/crypto.h +++ b/include/linux/crypto.h @@ -419,6 +419,7 @@ int crypto_has_alg(const char *name, u32 type, u32 mask); */ struct crypto_tfm { + refcount_t refcnt; u32 crt_flags; -- cgit v1.2.3 From 440da737cf8d35a1b2205678cc1879fa90948f7a Mon Sep 17 00:00:00 2001 From: Mario Limonciello Date: Fri, 14 Apr 2023 09:40:07 -0500 Subject: i2c: designware: Use PCI PSP driver for communication Currently the PSP semaphore communication base address is discovered by using an MSR that is not architecturally guaranteed for future platforms. Also the mailbox that is utilized for communication with the PSP may have other consumers in the kernel, so it's better to make all communication go through a single driver. Signed-off-by: Mario Limonciello Reviewed-by: Mark Hasemeyer Acked-by: Jarkko Nikula Tested-by: Mark Hasemeyer Acked-by: Wolfram Sang Signed-off-by: Herbert Xu --- include/linux/psp-platform-access.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/psp-platform-access.h b/include/linux/psp-platform-access.h index 1b661341d8f3..75da8f5f7ad8 100644 --- a/include/linux/psp-platform-access.h +++ b/include/linux/psp-platform-access.h @@ -7,6 +7,7 @@ enum psp_platform_access_msg { PSP_CMD_NONE = 0x0, + PSP_I2C_REQ_BUS_CMD = 0x64, }; struct psp_req_buffer_hdr { -- cgit v1.2.3 From 046b6a171009e1ed9ede02194025e9ccd709beb2 Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Wed, 19 Apr 2023 09:41:27 -0700 Subject: device property: make device_property functions take const device * device_property functions do not modify the device pointer passed to them. The underlying of_device and fwnode_ functions actually already take const * arguments. Mark the parameter constant to simplify conversion from of_property to device_property functions, and to let the calling code use const device pointers where possible. Cc: Chris Packham Reviewed-by: Chris Packham Reviewed-by: Sakari Ailus Signed-off-by: Guenter Roeck Link: https://lore.kernel.org/r/20230419164127.3773278-1-linux@roeck-us.net Signed-off-by: Greg Kroah-Hartman --- include/linux/property.h | 36 ++++++++++++++++++------------------ 1 file changed, 18 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/property.h b/include/linux/property.h index 59f452198c64..66df1a15d518 100644 --- a/include/linux/property.h +++ b/include/linux/property.h @@ -39,20 +39,20 @@ struct fwnode_handle *__dev_fwnode(struct device *dev); const struct device *: __dev_fwnode_const, \ struct device *: __dev_fwnode)(dev) -bool device_property_present(struct device *dev, const char *propname); -int device_property_read_u8_array(struct device *dev, const char *propname, +bool device_property_present(const struct device *dev, const char *propname); +int device_property_read_u8_array(const struct device *dev, const char *propname, u8 *val, size_t nval); -int device_property_read_u16_array(struct device *dev, const char *propname, +int device_property_read_u16_array(const struct device *dev, const char *propname, u16 *val, size_t nval); -int device_property_read_u32_array(struct device *dev, const char *propname, +int device_property_read_u32_array(const struct device *dev, const char *propname, u32 *val, size_t nval); -int device_property_read_u64_array(struct device *dev, const char *propname, +int device_property_read_u64_array(const struct device *dev, const char *propname, u64 *val, size_t nval); -int device_property_read_string_array(struct device *dev, const char *propname, +int device_property_read_string_array(const struct device *dev, const char *propname, const char **val, size_t nval); -int device_property_read_string(struct device *dev, const char *propname, +int device_property_read_string(const struct device *dev, const char *propname, const char **val); -int device_property_match_string(struct device *dev, +int device_property_match_string(const struct device *dev, const char *propname, const char *string); bool fwnode_property_present(const struct fwnode_handle *fwnode, @@ -142,57 +142,57 @@ int fwnode_irq_get_byname(const struct fwnode_handle *fwnode, const char *name); unsigned int device_get_child_node_count(const struct device *dev); -static inline bool device_property_read_bool(struct device *dev, +static inline bool device_property_read_bool(const struct device *dev, const char *propname) { return device_property_present(dev, propname); } -static inline int device_property_read_u8(struct device *dev, +static inline int device_property_read_u8(const struct device *dev, const char *propname, u8 *val) { return device_property_read_u8_array(dev, propname, val, 1); } -static inline int device_property_read_u16(struct device *dev, +static inline int device_property_read_u16(const struct device *dev, const char *propname, u16 *val) { return device_property_read_u16_array(dev, propname, val, 1); } -static inline int device_property_read_u32(struct device *dev, +static inline int device_property_read_u32(const struct device *dev, const char *propname, u32 *val) { return device_property_read_u32_array(dev, propname, val, 1); } -static inline int device_property_read_u64(struct device *dev, +static inline int device_property_read_u64(const struct device *dev, const char *propname, u64 *val) { return device_property_read_u64_array(dev, propname, val, 1); } -static inline int device_property_count_u8(struct device *dev, const char *propname) +static inline int device_property_count_u8(const struct device *dev, const char *propname) { return device_property_read_u8_array(dev, propname, NULL, 0); } -static inline int device_property_count_u16(struct device *dev, const char *propname) +static inline int device_property_count_u16(const struct device *dev, const char *propname) { return device_property_read_u16_array(dev, propname, NULL, 0); } -static inline int device_property_count_u32(struct device *dev, const char *propname) +static inline int device_property_count_u32(const struct device *dev, const char *propname) { return device_property_read_u32_array(dev, propname, NULL, 0); } -static inline int device_property_count_u64(struct device *dev, const char *propname) +static inline int device_property_count_u64(const struct device *dev, const char *propname) { return device_property_read_u64_array(dev, propname, NULL, 0); } -static inline int device_property_string_array_count(struct device *dev, +static inline int device_property_string_array_count(const struct device *dev, const char *propname) { return device_property_read_string_array(dev, propname, NULL, 0); -- cgit v1.2.3 From ec274aff21b6a94c7973384ca80a503c1bc3b173 Mon Sep 17 00:00:00 2001 From: Petr Tesarik Date: Thu, 20 Apr 2023 11:58:58 +0200 Subject: swiotlb: Omit total_used and used_hiwater if !CONFIG_DEBUG_FS The tracking of used_hiwater adds an atomic operation to the hot path. This is acceptable only when debugging the kernel. To make sure that the fields can never be used by mistake, do not even include them in struct io_tlb_mem if CONFIG_DEBUG_FS is not set. The build fails after doing that. To fix it, it is necessary to remove all code specific to debugfs and instead provide a stub implementation of swiotlb_create_debugfs_files(). As a bonus, this change allows to remove one __maybe_unused attribute. Signed-off-by: Petr Tesarik Signed-off-by: Christoph Hellwig --- include/linux/swiotlb.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index 6dc4598d2260..44767844e12b 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -107,8 +107,10 @@ struct io_tlb_mem { unsigned int area_nslabs; struct io_tlb_area *areas; struct io_tlb_slot *slots; +#ifdef CONFIG_DEBUG_FS atomic_long_t total_used; atomic_long_t used_hiwater; +#endif }; extern struct io_tlb_mem io_tlb_default_mem; -- cgit v1.2.3 From 038585573d0544bc717cdc5b3be4e95206d3ee3d Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Tue, 18 Apr 2023 15:49:47 +0200 Subject: efi/pe: Import new BTI/IBT header flags from the spec The latest version of your favorite fork of the PE/COFF spec includes a new type of header flag that is intended to be used in the context of EFI firmware to indicate to the image loader that the executable regions of an image can be mapped with BTI/IBT enforcement enabled. So let's import these definitions so we can use them in subsequent patches. Signed-off-by: Ard Biesheuvel --- include/linux/pe.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pe.h b/include/linux/pe.h index 6ffabf1e6d03..5e1e11540870 100644 --- a/include/linux/pe.h +++ b/include/linux/pe.h @@ -118,6 +118,9 @@ #define IMAGE_DLLCHARACTERISTICS_WDM_DRIVER 0x2000 #define IMAGE_DLLCHARACTERISTICS_TERMINAL_SERVER_AWARE 0x8000 +#define IMAGE_DLLCHARACTERISTICS_EX_CET_COMPAT 0x0001 +#define IMAGE_DLLCHARACTERISTICS_EX_FORWARD_CFI_COMPAT 0x0040 + /* they actually defined 0x00000000 as well, but I think we'll skip that one. */ #define IMAGE_SCN_RESERVED_0 0x00000001 #define IMAGE_SCN_RESERVED_1 0x00000002 @@ -165,6 +168,7 @@ #define IMAGE_SCN_MEM_WRITE 0x80000000 /* writeable */ #define IMAGE_DEBUG_TYPE_CODEVIEW 2 +#define IMAGE_DEBUG_TYPE_EX_DLLCHARACTERISTICS 20 #ifndef __ASSEMBLY__ -- cgit v1.2.3 From b52124a78ab34eb0754e32edc0c9996937779176 Mon Sep 17 00:00:00 2001 From: Mario Limonciello Date: Mon, 17 Apr 2023 10:27:05 -0500 Subject: PM: Add sysfs files to represent time spent in hardware sleep state Userspace can't easily discover how much of a sleep cycle was spent in a hardware sleep state without using kernel tracing and vendor specific sysfs or debugfs files. To make this information more discoverable, introduce 3 new sysfs files: 1) The time spent in a hw sleep state for last cycle. 2) The time spent in a hw sleep state since the kernel booted 3) The maximum time that the hardware can report for a sleep cycle. All of these files will be present only if the system supports s2idle. Reviewed-by: Hans de Goede Signed-off-by: Mario Limonciello Signed-off-by: Rafael J. Wysocki --- include/linux/suspend.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/suspend.h b/include/linux/suspend.h index cfe19a028918..d0d4598a7b3f 100644 --- a/include/linux/suspend.h +++ b/include/linux/suspend.h @@ -68,6 +68,9 @@ struct suspend_stats { int last_failed_errno; int errno[REC_FAILED_NUM]; int last_failed_step; + u64 last_hw_sleep; + u64 total_hw_sleep; + u64 max_hw_sleep; enum suspend_stat_step failed_steps[REC_FAILED_NUM]; }; @@ -489,6 +492,8 @@ void restore_processor_state(void); extern int register_pm_notifier(struct notifier_block *nb); extern int unregister_pm_notifier(struct notifier_block *nb); extern void ksys_sync_helper(void); +extern void pm_report_hw_sleep_time(u64 t); +extern void pm_report_max_hw_sleep(u64 t); #define pm_notifier(fn, pri) { \ static struct notifier_block fn##_nb = \ @@ -526,6 +531,9 @@ static inline int unregister_pm_notifier(struct notifier_block *nb) return 0; } +static inline void pm_report_hw_sleep_time(u64 t) {}; +static inline void pm_report_max_hw_sleep(u64 t) {}; + static inline void ksys_sync_helper(void) {} #define pm_notifier(fn, pri) do { (void)(fn); } while (0) -- cgit v1.2.3 From b0bc615df488abd0e95107e4a9ecefb9bf8c250a Mon Sep 17 00:00:00 2001 From: Maher Sanalla Date: Tue, 21 Mar 2023 00:10:16 +0200 Subject: net/mlx5: Add vnic devlink health reporter to PFs/VFs Create a vnic devlink health reporter for PFs/VFs interfaces. The reporter's diagnose callback displays the values of vNIC/vport transport debug counters of PFs/VFs, as follows: $ devlink health diagnose pci/0000:08:00.0 reporter vnic vNIC env counters: total_error_queues: 0 send_queue_priority_update_flow: 0 comp_eq_overrun: 0 async_eq_overrun: 0 cq_overrun: 0 invalid_command: 0 quota_exceeded_command: 0 nic_receive_steering_discard: 0 Moreover, add documentation on the reporter functionality and the counters description. While at it, expose the vNIC counters diagnose function to be used by the downstream patch, which will reveal the counters for representor interfaces. Signed-off-by: Maher Sanalla Reviewed-by: Moshe Shemesh Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 135a3c8d8237..5d25c4c73046 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -439,6 +439,7 @@ struct mlx5_core_health { struct work_struct report_work; struct devlink_health_reporter *fw_reporter; struct devlink_health_reporter *fw_fatal_reporter; + struct devlink_health_reporter *vnic_reporter; struct delayed_work update_fw_log_ts_work; }; -- cgit v1.2.3 From f9c895a72a390656f9582e048fdcc3d2cec1dd7c Mon Sep 17 00:00:00 2001 From: Roi Dayan Date: Wed, 22 Mar 2023 10:21:46 +0200 Subject: net/mlx5: Update op_mode to op_mod for port selection To be consistent with the other enum keys use OP_MOD instead of OP_MODE. Signed-off-by: Roi Dayan Reviewed-by: Maor Dickman Signed-off-by: Saeed Mahameed --- include/linux/mlx5/mlx5_ifc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 20d00e09b168..b42696d74c9f 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -69,7 +69,7 @@ enum { MLX5_SET_HCA_CAP_OP_MOD_ATOMIC = 0x3, MLX5_SET_HCA_CAP_OP_MOD_ROCE = 0x4, MLX5_SET_HCA_CAP_OP_MOD_GENERAL_DEVICE2 = 0x20, - MLX5_SET_HCA_CAP_OP_MODE_PORT_SELECTION = 0x25, + MLX5_SET_HCA_CAP_OP_MOD_PORT_SELECTION = 0x25, }; enum { -- cgit v1.2.3 From 8fa66e4a1bdd41d55d7842928e60a40fed65715d Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 19 Apr 2023 19:00:05 -0700 Subject: net: skbuff: update and rename __kfree_skb_defer() __kfree_skb_defer() uses the old naming where "defer" meant slab bulk free/alloc APIs. In the meantime we also made __kfree_skb_defer() feed the per-NAPI skb cache, which implies bulk APIs. So take away the 'defer' and add 'napi'. While at it add a drop reason. This only matters on the tx_action path, if the skb has a frag_list. But getting rid of a SKB_DROP_REASON_NOT_SPECIFIED seems like a net benefit so why not. Reviewed-by: Alexander Lobakin Link: https://lore.kernel.org/r/20230420020005.815854-1-kuba@kernel.org Signed-off-by: Jakub Kicinski --- include/linux/skbuff.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index db5973559042..03aa7ed076f0 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3253,7 +3253,7 @@ static inline struct sk_buff *napi_alloc_skb(struct napi_struct *napi, void napi_consume_skb(struct sk_buff *skb, int budget); void napi_skb_free_stolen_head(struct sk_buff *skb); -void __kfree_skb_defer(struct sk_buff *skb); +void __napi_kfree_skb(struct sk_buff *skb, enum skb_drop_reason reason); /** * __dev_alloc_pages - allocate page for network Rx -- cgit v1.2.3 From 211db0ac9e3dc6c46f2dd53395b34d76af929faf Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Thu, 16 Mar 2023 07:34:33 +0900 Subject: ksmbd: remove internal.h include Since vfs_path_lookup is exported, It should not be internal. Move vfs_path_lookup prototype in internal.h to linux/namei.h. Suggested-by: Al Viro Reviewed-by: Christian Brauner Signed-off-by: Namjae Jeon Signed-off-by: Al Viro --- include/linux/namei.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/namei.h b/include/linux/namei.h index 0d797f3367ca..ba9b32b4d1b0 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -63,6 +63,8 @@ extern struct dentry *kern_path_create(int, const char *, struct path *, unsigne extern struct dentry *user_path_create(int, const char __user *, struct path *, unsigned int); extern void done_path_create(struct path *, struct dentry *); extern struct dentry *kern_path_locked(const char *, struct path *); +int vfs_path_lookup(struct dentry *, struct vfsmount *, const char *, + unsigned int, struct path *); extern struct dentry *try_lookup_one_len(const char *, struct dentry *, int); extern struct dentry *lookup_one_len(const char *, struct dentry *, int); -- cgit v1.2.3 From 9bc37e04823b5280dd0f22b6680fc23fe81ca325 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 16 Mar 2023 07:34:34 +0900 Subject: fs: introduce lock_rename_child() helper Pass the dentry of a source file and the dentry of a destination directory to lock parent inodes for rename. As soon as this function returns, ->d_parent of the source file dentry is stable and inodes are properly locked for calling vfs-rename. This helper is needed for ksmbd server. rename request of SMB protocol has to rename an opened file, no matter which directory it's in. Signed-off-by: Al Viro Signed-off-by: Namjae Jeon Signed-off-by: Al Viro --- include/linux/namei.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/namei.h b/include/linux/namei.h index ba9b32b4d1b0..5864e4d82e56 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -83,6 +83,7 @@ extern int follow_down(struct path *path, unsigned int flags); extern int follow_up(struct path *); 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 *); extern int __must_check nd_jump_link(const struct path *path); -- cgit v1.2.3 From 38e124086282715e3b9b3d193d9308bb3499b46c Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 15 May 2022 18:16:54 -0400 Subject: kill the last remaining user of proc_ns_fget() lookups by descriptor are better off closer to syscall surface... Reviewed-by: Christian Brauner Signed-off-by: Al Viro --- include/linux/proc_ns.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/proc_ns.h b/include/linux/proc_ns.h index 75807ecef880..49539bc416ce 100644 --- a/include/linux/proc_ns.h +++ b/include/linux/proc_ns.h @@ -72,7 +72,6 @@ static inline int ns_alloc_inum(struct ns_common *ns) #define ns_free_inum(ns) proc_free_inum((ns)->inum) -extern struct file *proc_ns_fget(int fd); #define get_proc_ns(inode) ((struct ns_common *)(inode)->i_private) extern int ns_get_path(struct path *path, struct task_struct *task, const struct proc_ns_operations *ns_ops); -- cgit v1.2.3 From 5b8285cca6fed9bc5baabe2e5699a5a5c0d96371 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 19 Apr 2023 14:52:52 +0200 Subject: net: move dropreason.h to dropreason-core.h This will, after the next patch, hold only the core drop reasons and minimal infrastructure. Fix a small kernel-doc issue while at it, to avoid the move triggering a checker. Signed-off-by: Johannes Berg Signed-off-by: Jakub Kicinski --- include/linux/netdevice.h | 2 +- include/linux/skbuff.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 203c0df2046c..a6a3e9457d6c 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -52,7 +52,7 @@ #include #include #include -#include +#include struct netpoll_info; struct device; diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 03aa7ed076f0..eb9e7bb76fa6 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -37,7 +37,7 @@ #include #endif #include -#include +#include /** * DOC: skb checksums -- cgit v1.2.3 From 48cd6bc5b22d68b8bbc8601f3c7ddeed99541a0b Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Sat, 18 Feb 2023 09:10:31 +0100 Subject: virtio: Reorder fields in 'struct virtqueue' Group some variables based on their sizes to reduce hole and avoid padding. On x86_64, this shrinks the size of 'struct virtqueue' from 72 to 68 bytes. It saves a few bytes of memory. Signed-off-by: Christophe JAILLET Message-Id: <8f3d2e49270a2158717e15008e7ed7228196ba02.1676707807.git.christophe.jaillet@wanadoo.fr> Signed-off-by: Michael S. Tsirkin Acked-by: Peter Lafreniere Reviewed-by: Stefano Garzarella --- include/linux/virtio.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/virtio.h b/include/linux/virtio.h index 2b472514c49b..d6e161aa532e 100644 --- a/include/linux/virtio.h +++ b/include/linux/virtio.h @@ -34,8 +34,8 @@ struct virtqueue { unsigned int index; unsigned int num_free; unsigned int num_max; - void *priv; bool reset; + void *priv; }; int virtqueue_add_outbuf(struct virtqueue *vq, -- cgit v1.2.3 From 4b6ec919b84830949313c805c586fb34f141ce0c Mon Sep 17 00:00:00 2001 From: Feng Liu Date: Fri, 10 Mar 2023 07:34:28 +0200 Subject: virtio_ring: Use const to annotate read-only pointer params Add const to make the read-only pointer parameters clear, similar to many existing functions. To implement this change, the commit also introduces the use of `container_of_const` to implement `to_vvq`, which ensures the const-ness of read-only parameters and avoids accidental modification of their members. Signed-off-by: Feng Liu Reviewed-by: Jiri Pirko Reviewed-by: Parav Pandit Reviewed-by: Gavin Li Reviewed-by: Bodong Wang Message-Id: <20230310053428.3376-4-feliu@nvidia.com> Signed-off-by: Michael S. Tsirkin --- include/linux/virtio.h | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/virtio.h b/include/linux/virtio.h index d6e161aa532e..b93238db94e3 100644 --- a/include/linux/virtio.h +++ b/include/linux/virtio.h @@ -84,14 +84,14 @@ bool virtqueue_enable_cb_delayed(struct virtqueue *vq); void *virtqueue_detach_unused_buf(struct virtqueue *vq); -unsigned int virtqueue_get_vring_size(struct virtqueue *vq); +unsigned int virtqueue_get_vring_size(const struct virtqueue *vq); -bool virtqueue_is_broken(struct virtqueue *vq); +bool virtqueue_is_broken(const struct virtqueue *vq); -const struct vring *virtqueue_get_vring(struct virtqueue *vq); -dma_addr_t virtqueue_get_desc_addr(struct virtqueue *vq); -dma_addr_t virtqueue_get_avail_addr(struct virtqueue *vq); -dma_addr_t virtqueue_get_used_addr(struct virtqueue *vq); +const struct vring *virtqueue_get_vring(const struct virtqueue *vq); +dma_addr_t virtqueue_get_desc_addr(const struct virtqueue *vq); +dma_addr_t virtqueue_get_avail_addr(const struct virtqueue *vq); +dma_addr_t virtqueue_get_used_addr(const struct virtqueue *vq); int virtqueue_resize(struct virtqueue *vq, u32 num, void (*recycle)(struct virtqueue *vq, void *buf)); @@ -147,7 +147,7 @@ int virtio_device_restore(struct virtio_device *dev); #endif void virtio_reset_device(struct virtio_device *dev); -size_t virtio_max_dma_size(struct virtio_device *vdev); +size_t virtio_max_dma_size(const struct virtio_device *vdev); #define virtio_device_for_each_vq(vdev, vq) \ list_for_each_entry(vq, &vdev->vqs, list) -- cgit v1.2.3 From 1d24692732fb299c94b0dcc032b48ac8fa85c854 Mon Sep 17 00:00:00 2001 From: Xie Yongji Date: Thu, 23 Mar 2023 13:30:34 +0800 Subject: vdpa: Add set/get_vq_affinity callbacks in vdpa_config_ops This introduces set/get_vq_affinity callbacks in vdpa_config_ops to support virtqueue affinity management for vdpa device drivers. Signed-off-by: Xie Yongji Acked-by: Jason Wang Message-Id: <20230323053043.35-3-xieyongji@bytedance.com> Signed-off-by: Michael S. Tsirkin --- include/linux/vdpa.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index 43f59ef10cc9..2313db735773 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -250,6 +250,15 @@ struct vdpa_map_file { * @vdev: vdpa device * Returns the iova range supported by * the device. + * @set_vq_affinity: Set the affinity of virtqueue (optional) + * @vdev: vdpa device + * @idx: virtqueue index + * @cpu_mask: the affinity mask + * Returns integer: success (0) or error (< 0) + * @get_vq_affinity: Get the affinity of virtqueue (optional) + * @vdev: vdpa device + * @idx: virtqueue index + * Returns the affinity mask * @set_group_asid: Set address space identifier for a * virtqueue group (optional) * @vdev: vdpa device @@ -340,6 +349,10 @@ struct vdpa_config_ops { const void *buf, unsigned int len); u32 (*get_generation)(struct vdpa_device *vdev); struct vdpa_iova_range (*get_iova_range)(struct vdpa_device *vdev); + int (*set_vq_affinity)(struct vdpa_device *vdev, u16 idx, + const struct cpumask *cpu_mask); + const struct cpumask *(*get_vq_affinity)(struct vdpa_device *vdev, + u16 idx); /* DMA ops */ int (*set_map)(struct vdpa_device *vdev, unsigned int asid, -- cgit v1.2.3 From 5e68470f4e80a4120e9ecec408f6ab4ad386bd4a Mon Sep 17 00:00:00 2001 From: Xie Yongji Date: Thu, 23 Mar 2023 13:30:40 +0800 Subject: vdpa: Add eventfd for the vdpa callback Add eventfd for the vdpa callback so that user can signal it directly instead of triggering the callback. It will be used for vhost-vdpa case. Signed-off-by: Xie Yongji Message-Id: <20230323053043.35-9-xieyongji@bytedance.com> Signed-off-by: Michael S. Tsirkin Acked-by: Jason Wang --- include/linux/vdpa.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index 2313db735773..f2064fa2d2da 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -13,10 +13,16 @@ * struct vdpa_calllback - vDPA callback definition. * @callback: interrupt callback function * @private: the data passed to the callback function + * @trigger: the eventfd for the callback (Optional). + * When it is set, the vDPA driver must guarantee that + * signaling it is functional equivalent to triggering + * the callback. Then vDPA parent can signal it directly + * instead of triggering the callback. */ struct vdpa_callback { irqreturn_t (*callback)(void *data); void *private; + struct eventfd_ctx *trigger; }; /** -- cgit v1.2.3 From c618c84d4ccc6268c3da7609c7388b6cb305c639 Mon Sep 17 00:00:00 2001 From: Stefano Garzarella Date: Tue, 4 Apr 2023 15:13:18 +0200 Subject: vdpa: add bind_mm/unbind_mm callbacks These new optional callbacks is used to bind/unbind the device to a specific address space so the vDPA framework can use VA when these callbacks are implemented. Suggested-by: Jason Wang Acked-by: Jason Wang Signed-off-by: Stefano Garzarella Message-Id: <20230404131326.44403-2-sgarzare@redhat.com> Signed-off-by: Michael S. Tsirkin --- include/linux/vdpa.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index f2064fa2d2da..2f1af73b3a1a 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -305,6 +305,14 @@ struct vdpa_map_file { * @vdev: vdpa device * @idx: virtqueue index * Returns pointer to structure device or error (NULL) + * @bind_mm: Bind the device to a specific address space + * so the vDPA framework can use VA when this + * callback is implemented. (optional) + * @vdev: vdpa device + * @mm: address space to bind + * @unbind_mm: Unbind the device from the address space + * bound using the bind_mm callback. (optional) + * @vdev: vdpa device * @free: Free resources that belongs to vDPA (optional) * @vdev: vdpa device */ @@ -370,6 +378,8 @@ struct vdpa_config_ops { int (*set_group_asid)(struct vdpa_device *vdev, unsigned int group, unsigned int asid); struct device *(*get_vq_dma_dev)(struct vdpa_device *vdev, u16 idx); + int (*bind_mm)(struct vdpa_device *vdev, struct mm_struct *mm); + void (*unbind_mm)(struct vdpa_device *vdev); /* Free device resources */ void (*free)(struct vdpa_device *vdev); -- cgit v1.2.3 From 42823a871fd4e17b34034f43b36ae57bd2ed8a67 Mon Sep 17 00:00:00 2001 From: Stefano Garzarella Date: Tue, 4 Apr 2023 15:17:16 +0200 Subject: vringh: support VA with iotlb MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit vDPA supports the possibility to use user VA in the iotlb messages. So, let's add support for user VA in vringh to use it in the vDPA simulators. Acked-by: Eugenio Pérez Signed-off-by: Stefano Garzarella Message-Id: <20230404131716.45855-1-sgarzare@redhat.com> Signed-off-by: Michael S. Tsirkin --- include/linux/vringh.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/vringh.h b/include/linux/vringh.h index 1991a02c6431..b4edfadf5479 100644 --- a/include/linux/vringh.h +++ b/include/linux/vringh.h @@ -32,6 +32,9 @@ struct vringh { /* Can we get away with weak barriers? */ bool weak_barriers; + /* Use user's VA */ + bool use_va; + /* Last available index we saw (ie. where we're up to). */ u16 last_avail_idx; @@ -284,6 +287,12 @@ int vringh_init_iotlb(struct vringh *vrh, u64 features, struct vring_avail *avail, struct vring_used *used); +int vringh_init_iotlb_va(struct vringh *vrh, u64 features, + unsigned int num, bool weak_barriers, + struct vring_desc *desc, + struct vring_avail *avail, + struct vring_used *used); + int vringh_getdesc_iotlb(struct vringh *vrh, struct vringh_kiov *riov, struct vringh_kiov *wiov, -- cgit v1.2.3 From 9be5d2d424a19a0c6d643a1baecba3d58e725012 Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Fri, 31 Mar 2023 10:56:55 +0200 Subject: vdpa: address kdoc warnings This patch addresses the following minor kdoc problems. * Incorrect spelling of 'callback' and 'notification' * Unrecognised kdoc format for 'struct vdpa_map_file' * Missing documentation of 'get_vendor_vq_stats' member of 'struct vdpa_config_ops' * Missing documentation of 'max_supported_vqs' and 'supported_features' members of 'struct vdpa_mgmt_dev' Most of these problems were flagged by: $ ./scripts/kernel-doc -Werror -none include/linux/vdpa.h include/linux/vdpa.h:20: warning: expecting prototype for struct vdpa_calllback. Prototype was for struct vdpa_callback instead include/linux/vdpa.h:117: warning: This comment starts with '/**', but isn't a kernel-doc comment. Refer Documentation/doc-guide/kernel-doc.rst * Corresponding file area for device memory mapping include/linux/vdpa.h:357: warning: Function parameter or member 'get_vendor_vq_stats' not described in 'vdpa_config_ops' include/linux/vdpa.h:518: warning: Function parameter or member 'supported_features' not described in 'vdpa_mgmt_dev' include/linux/vdpa.h:518: warning: Function parameter or member 'max_supported_vqs' not described in 'vdpa_mgmt_dev' The misspelling of 'notification' was flagged by: $ ./scripts/checkpatch.pl --codespell --showfile --strict -f include/linux/vdpa.h include/linux/vdpa.h:171: CHECK: 'notifcation' may be misspelled - perhaps 'notification'? ... Signed-off-by: Simon Horman Message-Id: <20230331-vhost-fixes-v1-1-1f046e735b9e@kernel.org> Signed-off-by: Michael S. Tsirkin Acked-by: Jason Wang --- include/linux/vdpa.h | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index 2f1af73b3a1a..c0d3f5433af7 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -10,7 +10,7 @@ #include /** - * struct vdpa_calllback - vDPA callback definition. + * struct vdpa_callback - vDPA callback definition. * @callback: interrupt callback function * @private: the data passed to the callback function * @trigger: the eventfd for the callback (Optional). @@ -120,7 +120,7 @@ struct vdpa_dev_set_config { }; /** - * Corresponding file area for device memory mapping + * struct vdpa_map_file - file area for device memory mapping * @file: vma->vm_file for the mapping * @offset: mapping offset in the vm_file */ @@ -171,10 +171,16 @@ struct vdpa_map_file { * @vdev: vdpa device * @idx: virtqueue index * @state: pointer to returned state (last_avail_idx) + * @get_vendor_vq_stats: Get the vendor statistics of a device. + * @vdev: vdpa device + * @idx: virtqueue index + * @msg: socket buffer holding stats message + * @extack: extack for reporting error messages + * Returns integer: success (0) or error (< 0) * @get_vq_notification: Get the notification area for a virtqueue (optional) * @vdev: vdpa device * @idx: virtqueue index - * Returns the notifcation area + * Returns the notification area * @get_vq_irq: Get the irq number of a virtqueue (optional, * but must implemented if require vq irq offloading) * @vdev: vdpa device @@ -535,6 +541,8 @@ struct vdpa_mgmtdev_ops { * @config_attr_mask: bit mask of attributes of type enum vdpa_attr that * management device support during dev_add callback * @list: list entry + * @supported_features: features supported by device + * @max_supported_vqs: maximum number of virtqueues supported by device */ struct vdpa_mgmt_dev { struct device *device; -- cgit v1.2.3 From b2ffaa672edaf1a681537a9f47bc14ab6c9e8845 Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Fri, 31 Mar 2023 10:56:56 +0200 Subject: vringh: address kdoc warnings Address some minor kdoc warnings in vring.h. * Place kdoc for 'struct vringh_config_ops' immediately before the structure * Add missing documentation of members of 'vringh_iov' and 'vringh_kiov' Warnings flagged by: $ ./scripts/kernel-doc -none include/linux/vringh.h include/linux/vringh.h:68: error: Cannot parse struct or union! include/linux/vringh.h:92: warning: Function parameter or member 'iov' not described in 'vringh_iov' include/linux/vringh.h:92: warning: Function parameter or member 'consumed' not described in 'vringh_iov' include/linux/vringh.h:92: warning: Function parameter or member 'i' not described in 'vringh_iov' include/linux/vringh.h:92: warning: Function parameter or member 'used' not described in 'vringh_iov' include/linux/vringh.h:92: warning: Function parameter or member 'max_num' not described in 'vringh_iov' include/linux/vringh.h:104: warning: Function parameter or member 'iov' not described in 'vringh_kiov' include/linux/vringh.h:104: warning: Function parameter or member 'consumed' not described in 'vringh_kiov' include/linux/vringh.h:104: warning: Function parameter or member 'i' not described in 'vringh_kiov' include/linux/vringh.h:104: warning: Function parameter or member 'used' not described in 'vringh_kiov' include/linux/vringh.h:104: warning: Function parameter or member 'max_num' not described in 'vringh_kiov' Signed-off-by: Simon Horman Message-Id: <20230331-vhost-fixes-v1-2-1f046e735b9e@kernel.org> Signed-off-by: Michael S. Tsirkin --- include/linux/vringh.h | 17 +++++++++++++++-- 1 file changed, 15 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/vringh.h b/include/linux/vringh.h index b4edfadf5479..c3a8117dabe8 100644 --- a/include/linux/vringh.h +++ b/include/linux/vringh.h @@ -57,6 +57,9 @@ struct vringh { void (*notify)(struct vringh *); }; +struct virtio_device; +typedef void vrh_callback_t(struct virtio_device *, struct vringh *); + /** * struct vringh_config_ops - ops for creating a host vring from a virtio driver * @find_vrhs: find the host vrings and instantiate them @@ -68,8 +71,6 @@ struct vringh { * Returns 0 on success or error status * @del_vrhs: free the host vrings found by find_vrhs(). */ -struct virtio_device; -typedef void vrh_callback_t(struct virtio_device *, struct vringh *); struct vringh_config_ops { int (*find_vrhs)(struct virtio_device *vdev, unsigned nhvrs, struct vringh *vrhs[], vrh_callback_t *callbacks[]); @@ -84,6 +85,12 @@ struct vringh_range { /** * struct vringh_iov - iovec mangler. + * @iov: array of iovecs to operate on + * @consumed: number of bytes consumed within iov[i] + * @i: index of current iovec + * @used: number of iovecs present in @iov + * @max_num: maximum number of iovecs. + * corresponds to allocated memory of @iov * * Mangles iovec in place, and restores it. * Remaining data is iov + i, of used - i elements. @@ -96,6 +103,12 @@ struct vringh_iov { /** * struct vringh_kiov - kvec mangler. + * @iov: array of iovecs to operate on + * @consumed: number of bytes consumed within iov[i] + * @i: index of current iovec + * @used: number of iovecs present in @iov + * @max_num: maximum number of iovecs. + * corresponds to allocated memory of @iov * * Mangles kvec in place, and restores it. * Remaining data is iov + i, of used - i elements. -- cgit v1.2.3 From af8ececda185078c096852edb4e1d7a2349e6856 Mon Sep 17 00:00:00 2001 From: Viktor Prutyanov Date: Thu, 13 Apr 2023 11:18:54 +0300 Subject: virtio: add VIRTIO_F_NOTIFICATION_DATA feature support According to VirtIO spec v1.2, VIRTIO_F_NOTIFICATION_DATA feature indicates that the driver passes extra data along with the queue notifications. In a split queue case, the extra data is 16-bit available index. In a packed queue case, the extra data is 1-bit wrap counter and 15-bit available index. Add support for this feature for MMIO, channel I/O and modern PCI transports. Signed-off-by: Viktor Prutyanov Acked-by: Jason Wang Reviewed-by: Xuan Zhuo Message-Id: <20230413081855.36643-2-alvaro.karsz@solid-run.com> Signed-off-by: Michael S. Tsirkin --- include/linux/virtio_ring.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/virtio_ring.h b/include/linux/virtio_ring.h index 8b95b69ef694..2550c9170f4f 100644 --- a/include/linux/virtio_ring.h +++ b/include/linux/virtio_ring.h @@ -117,4 +117,6 @@ void vring_del_virtqueue(struct virtqueue *vq); void vring_transport_features(struct virtio_device *vdev); irqreturn_t vring_interrupt(int irq, void *_vq); + +u32 vring_notification_data(struct virtqueue *_vq); #endif /* _LINUX_VIRTIO_RING_H */ -- cgit v1.2.3 From 2c4e4a22a3b090e06191f8544d21e0e1d72ce518 Mon Sep 17 00:00:00 2001 From: Alvaro Karsz Date: Thu, 13 Apr 2023 11:18:55 +0300 Subject: virtio-vdpa: add VIRTIO_F_NOTIFICATION_DATA feature support Add VIRTIO_F_NOTIFICATION_DATA support for vDPA transport. If this feature is negotiated, the driver passes extra data when kicking a virtqueue. A device that offers this feature needs to implement the kick_vq_with_data callback. kick_vq_with_data receives the vDPA device and data. data includes: 16 bits vqn and 16 bits next available index for split virtqueues. 16 bits vqs, 15 least significant bits of next available index and 1 bit next_wrap for packed virtqueues. This patch follows a patch [1] by Viktor Prutyanov which adds support for the MMIO, channel I/O and modern PCI transports. Signed-off-by: Alvaro Karsz Message-Id: <20230413081855.36643-3-alvaro.karsz@solid-run.com> Signed-off-by: Michael S. Tsirkin Acked-by: Jason Wang --- include/linux/vdpa.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index c0d3f5433af7..db1b0eaef4eb 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -149,6 +149,14 @@ struct vdpa_map_file { * @kick_vq: Kick the virtqueue * @vdev: vdpa device * @idx: virtqueue index + * @kick_vq_with_data: Kick the virtqueue and supply extra data + * (only if VIRTIO_F_NOTIFICATION_DATA is negotiated) + * @vdev: vdpa device + * @data for split virtqueue: + * 16 bits vqn and 16 bits next available index. + * @data for packed virtqueue: + * 16 bits vqn, 15 least significant bits of + * next available index and 1 bit next_wrap. * @set_vq_cb: Set the interrupt callback function for * a virtqueue * @vdev: vdpa device @@ -329,6 +337,7 @@ struct vdpa_config_ops { u64 device_area); void (*set_vq_num)(struct vdpa_device *vdev, u16 idx, u32 num); void (*kick_vq)(struct vdpa_device *vdev, u16 idx); + void (*kick_vq_with_data)(struct vdpa_device *vdev, u32 data); void (*set_vq_cb)(struct vdpa_device *vdev, u16 idx, struct vdpa_callback *cb); void (*set_vq_ready)(struct vdpa_device *vdev, u16 idx, bool ready); -- cgit v1.2.3 From 38fc29ea754711e9a8c4e9ca2678ab41353a4662 Mon Sep 17 00:00:00 2001 From: Shunsuke Mie Date: Mon, 17 Apr 2023 11:20:36 +0900 Subject: virtio_ring: add a struct device forward declaration The virtio_ring header file uses the struct device without a forward declaration. Signed-off-by: Shunsuke Mie Message-Id: <20230417022037.917668-1-mie@igel.co.jp> Signed-off-by: Michael S. Tsirkin --- include/linux/virtio_ring.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/virtio_ring.h b/include/linux/virtio_ring.h index 2550c9170f4f..9b33df741b63 100644 --- a/include/linux/virtio_ring.h +++ b/include/linux/virtio_ring.h @@ -58,6 +58,7 @@ do { \ struct virtio_device; struct virtqueue; +struct device; /* * Creates a virtqueue and allocates the descriptor ring. If -- cgit v1.2.3 From add7370a398930077c6bc257ef5016b040d476eb Mon Sep 17 00:00:00 2001 From: Xin Long Date: Wed, 19 Apr 2023 11:16:28 -0400 Subject: sctp: delete the nested flexible array params This patch deletes the flexible-array params[] from the structure sctp_inithdr, sctp_addiphdr and sctp_reconf_chunk to avoid some sparse warnings: # make C=2 CF="-Wflexible-array-nested" M=./net/sctp/ net/sctp/input.c: note: in included file (through include/net/sctp/structs.h, include/net/sctp/sctp.h): ./include/linux/sctp.h:278:29: warning: nested flexible array ./include/linux/sctp.h:675:30: warning: nested flexible array This warning is reported if a structure having a flexible array member is included by other structures. Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/linux/sctp.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sctp.h b/include/linux/sctp.h index 358dc08e0831..0ff36a2737a3 100644 --- a/include/linux/sctp.h +++ b/include/linux/sctp.h @@ -270,7 +270,7 @@ struct sctp_inithdr { __be16 num_outbound_streams; __be16 num_inbound_streams; __be32 initial_tsn; - __u8 params[]; + /* __u8 params[]; */ }; struct sctp_init_chunk { @@ -667,7 +667,7 @@ struct sctp_addip_param { struct sctp_addiphdr { __be32 serial; - __u8 params[]; + /* __u8 params[]; */ }; struct sctp_addip_chunk { @@ -742,7 +742,7 @@ struct sctp_infox { struct sctp_reconf_chunk { struct sctp_chunkhdr chunk_hdr; - __u8 params[]; + /* __u8 params[]; */ }; struct sctp_strreset_outreq { -- cgit v1.2.3 From 73175a042955e531ec355a8708585befa67a22db Mon Sep 17 00:00:00 2001 From: Xin Long Date: Wed, 19 Apr 2023 11:16:29 -0400 Subject: sctp: delete the nested flexible array skip This patch deletes the flexible-array skip[] from the structure sctp_ifwdtsn/fwdtsn_hdr to avoid some sparse warnings: # make C=2 CF="-Wflexible-array-nested" M=./net/sctp/ net/sctp/stream_interleave.c: note: in included file (through include/net/sctp/structs.h, include/net/sctp/sctp.h): ./include/linux/sctp.h:611:32: warning: nested flexible array ./include/linux/sctp.h:628:33: warning: nested flexible array Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/linux/sctp.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sctp.h b/include/linux/sctp.h index 0ff36a2737a3..9815b801fec0 100644 --- a/include/linux/sctp.h +++ b/include/linux/sctp.h @@ -603,7 +603,7 @@ struct sctp_fwdtsn_skip { struct sctp_fwdtsn_hdr { __be32 new_cum_tsn; - struct sctp_fwdtsn_skip skip[]; + /* struct sctp_fwdtsn_skip skip[]; */ }; struct sctp_fwdtsn_chunk { @@ -620,7 +620,7 @@ struct sctp_ifwdtsn_skip { struct sctp_ifwdtsn_hdr { __be32 new_cum_tsn; - struct sctp_ifwdtsn_skip skip[]; + /* struct sctp_ifwdtsn_skip skip[]; */ }; struct sctp_ifwdtsn_chunk { -- cgit v1.2.3 From 9789c1c6619e0a5eccfc31abe49b1ce5ca3cd11f Mon Sep 17 00:00:00 2001 From: Xin Long Date: Wed, 19 Apr 2023 11:16:30 -0400 Subject: sctp: delete the nested flexible array variable This patch deletes the flexible-array variable[] from the structure sctp_sackhdr and sctp_errhdr to avoid some sparse warnings: # make C=2 CF="-Wflexible-array-nested" M=./net/sctp/ net/sctp/sm_statefuns.c: note: in included file (through include/net/sctp/structs.h, include/net/sctp/sctp.h): ./include/linux/sctp.h:451:28: warning: nested flexible array ./include/linux/sctp.h:393:29: warning: nested flexible array Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/linux/sctp.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sctp.h b/include/linux/sctp.h index 9815b801fec0..01a0eb7e9fa1 100644 --- a/include/linux/sctp.h +++ b/include/linux/sctp.h @@ -385,7 +385,7 @@ struct sctp_sackhdr { __be32 a_rwnd; __be16 num_gap_ack_blocks; __be16 num_dup_tsns; - union sctp_sack_variable variable[]; + /* union sctp_sack_variable variable[]; */ }; struct sctp_sack_chunk { @@ -443,7 +443,7 @@ struct sctp_shutdown_chunk { struct sctp_errhdr { __be16 cause; __be16 length; - __u8 variable[]; + /* __u8 variable[]; */ }; struct sctp_operr_chunk { -- cgit v1.2.3 From 2ab399a931dddacdf7202cd4b49a5187154623d1 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Wed, 19 Apr 2023 11:16:32 -0400 Subject: sctp: delete the nested flexible array hmac This patch deletes the flexible-array hmac[] from the structure sctp_authhdr to avoid some sparse warnings: # make C=2 CF="-Wflexible-array-nested" M=./net/sctp/ net/sctp/auth.c: note: in included file (through include/net/sctp/structs.h, include/net/sctp/sctp.h): ./include/linux/sctp.h:735:29: warning: nested flexible array Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/linux/sctp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sctp.h b/include/linux/sctp.h index 01a0eb7e9fa1..d182e8c41985 100644 --- a/include/linux/sctp.h +++ b/include/linux/sctp.h @@ -727,7 +727,7 @@ struct sctp_addip_chunk { struct sctp_authhdr { __be16 shkey_id; __be16 hmac_id; - __u8 hmac[]; + /* __u8 hmac[]; */ }; struct sctp_auth_chunk { -- cgit v1.2.3 From dbda0fba7a14f14835c34d59fd329cb90a887862 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Wed, 19 Apr 2023 11:16:33 -0400 Subject: sctp: delete the nested flexible array payload This patch deletes the flexible-array payload[] from the structure sctp_datahdr to avoid some sparse warnings: # make C=2 CF="-Wflexible-array-nested" M=./net/sctp/ net/sctp/socket.c: note: in included file (through include/net/sctp/structs.h, include/net/sctp/sctp.h): ./include/linux/sctp.h:230:29: warning: nested flexible array This member is not even used anywhere. Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/linux/sctp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sctp.h b/include/linux/sctp.h index d182e8c41985..836a7e200f39 100644 --- a/include/linux/sctp.h +++ b/include/linux/sctp.h @@ -222,7 +222,7 @@ struct sctp_datahdr { __be16 stream; __be16 ssn; __u32 ppid; - __u8 payload[]; + /* __u8 payload[]; */ }; struct sctp_data_chunk { -- cgit v1.2.3 From a714e3ec230892039b5d5ae6902b58bb084a15c1 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Wed, 19 Apr 2023 18:34:54 +0300 Subject: bridge: Add internal flags for per-{Port, VLAN} neighbor suppression Add two internal flags that will be used to enable / disable per-{Port, VLAN} neighbor suppression: 1. 'BR_NEIGH_VLAN_SUPPRESS': A per-port flag used to indicate that per-{Port, VLAN} neighbor suppression is enabled on the bridge port. When set, 'BR_NEIGH_SUPPRESS' has no effect. 2. 'BR_VLFLAG_NEIGH_SUPPRESS_ENABLED': A per-VLAN flag used to indicate that neighbor suppression is enabled on the given VLAN. Signed-off-by: Ido Schimmel Acked-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/linux/if_bridge.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h index 1668ac4d7adc..3ff96ae31bf6 100644 --- a/include/linux/if_bridge.h +++ b/include/linux/if_bridge.h @@ -60,6 +60,7 @@ struct br_ip_list { #define BR_TX_FWD_OFFLOAD BIT(20) #define BR_PORT_LOCKED BIT(21) #define BR_PORT_MAB BIT(22) +#define BR_NEIGH_VLAN_SUPPRESS BIT(23) #define BR_DEFAULT_AGEING_TIME (300 * HZ) -- cgit v1.2.3 From 55435ea7729accb5b8a330de751836c4be524834 Mon Sep 17 00:00:00 2001 From: Shannon Nelson Date: Wed, 19 Apr 2023 10:04:14 -0700 Subject: pds_core: initial framework for pds_core PF driver This is the initial PCI driver framework for the new pds_core device driver and its family of devices. This does the very basics of registering for the new PF PCI device 1dd8:100c, setting up debugfs entries, and registering with devlink. Signed-off-by: Shannon Nelson Acked-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/linux/pds/pds_common.h | 14 + include/linux/pds/pds_core_if.h | 571 ++++++++++++++++++++++++++++++++++++++++ 2 files changed, 585 insertions(+) create mode 100644 include/linux/pds/pds_common.h create mode 100644 include/linux/pds/pds_core_if.h (limited to 'include/linux') diff --git a/include/linux/pds/pds_common.h b/include/linux/pds/pds_common.h new file mode 100644 index 000000000000..bd041a5170a6 --- /dev/null +++ b/include/linux/pds/pds_common.h @@ -0,0 +1,14 @@ +/* SPDX-License-Identifier: (GPL-2.0 OR Linux-OpenIB) OR BSD-2-Clause */ +/* Copyright(c) 2023 Advanced Micro Devices, Inc. */ + +#ifndef _PDS_COMMON_H_ +#define _PDS_COMMON_H_ + +#define PDS_CORE_DRV_NAME "pds_core" + +/* the device's internal addressing uses up to 52 bits */ +#define PDS_CORE_ADDR_LEN 52 +#define PDS_CORE_ADDR_MASK (BIT_ULL(PDS_ADDR_LEN) - 1) +#define PDS_PAGE_SIZE 4096 + +#endif /* _PDS_COMMON_H_ */ diff --git a/include/linux/pds/pds_core_if.h b/include/linux/pds/pds_core_if.h new file mode 100644 index 000000000000..e838a2b90440 --- /dev/null +++ b/include/linux/pds/pds_core_if.h @@ -0,0 +1,571 @@ +/* SPDX-License-Identifier: (GPL-2.0 OR Linux-OpenIB) OR BSD-2-Clause */ +/* Copyright(c) 2023 Advanced Micro Devices, Inc. */ + +#ifndef _PDS_CORE_IF_H_ +#define _PDS_CORE_IF_H_ + +#define PCI_VENDOR_ID_PENSANDO 0x1dd8 +#define PCI_DEVICE_ID_PENSANDO_CORE_PF 0x100c +#define PCI_DEVICE_ID_VIRTIO_NET_TRANS 0x1000 +#define PCI_DEVICE_ID_PENSANDO_IONIC_ETH_VF 0x1003 +#define PCI_DEVICE_ID_PENSANDO_VDPA_VF 0x100b +#define PDS_CORE_BARS_MAX 4 +#define PDS_CORE_PCI_BAR_DBELL 1 + +/* Bar0 */ +#define PDS_CORE_DEV_INFO_SIGNATURE 0x44455649 /* 'DEVI' */ +#define PDS_CORE_BAR0_SIZE 0x8000 +#define PDS_CORE_BAR0_DEV_INFO_REGS_OFFSET 0x0000 +#define PDS_CORE_BAR0_DEV_CMD_REGS_OFFSET 0x0800 +#define PDS_CORE_BAR0_DEV_CMD_DATA_REGS_OFFSET 0x0c00 +#define PDS_CORE_BAR0_INTR_STATUS_OFFSET 0x1000 +#define PDS_CORE_BAR0_INTR_CTRL_OFFSET 0x2000 +#define PDS_CORE_DEV_CMD_DONE 0x00000001 + +#define PDS_CORE_DEVCMD_TIMEOUT 5 + +#define PDS_CORE_CLIENT_ID 0 +#define PDS_CORE_ASIC_TYPE_CAPRI 0 + +/* + * enum pds_core_cmd_opcode - Device commands + */ +enum pds_core_cmd_opcode { + /* Core init */ + PDS_CORE_CMD_NOP = 0, + PDS_CORE_CMD_IDENTIFY = 1, + PDS_CORE_CMD_RESET = 2, + PDS_CORE_CMD_INIT = 3, + + PDS_CORE_CMD_FW_DOWNLOAD = 4, + PDS_CORE_CMD_FW_CONTROL = 5, + + /* SR/IOV commands */ + PDS_CORE_CMD_VF_GETATTR = 60, + PDS_CORE_CMD_VF_SETATTR = 61, + PDS_CORE_CMD_VF_CTRL = 62, + + /* Add commands before this line */ + PDS_CORE_CMD_MAX, + PDS_CORE_CMD_COUNT +}; + +/* + * enum pds_core_status_code - Device command return codes + */ +enum pds_core_status_code { + PDS_RC_SUCCESS = 0, /* Success */ + PDS_RC_EVERSION = 1, /* Incorrect version for request */ + PDS_RC_EOPCODE = 2, /* Invalid cmd opcode */ + PDS_RC_EIO = 3, /* I/O error */ + PDS_RC_EPERM = 4, /* Permission denied */ + PDS_RC_EQID = 5, /* Bad qid */ + PDS_RC_EQTYPE = 6, /* Bad qtype */ + PDS_RC_ENOENT = 7, /* No such element */ + PDS_RC_EINTR = 8, /* operation interrupted */ + PDS_RC_EAGAIN = 9, /* Try again */ + PDS_RC_ENOMEM = 10, /* Out of memory */ + PDS_RC_EFAULT = 11, /* Bad address */ + PDS_RC_EBUSY = 12, /* Device or resource busy */ + PDS_RC_EEXIST = 13, /* object already exists */ + PDS_RC_EINVAL = 14, /* Invalid argument */ + PDS_RC_ENOSPC = 15, /* No space left or alloc failure */ + PDS_RC_ERANGE = 16, /* Parameter out of range */ + PDS_RC_BAD_ADDR = 17, /* Descriptor contains a bad ptr */ + PDS_RC_DEV_CMD = 18, /* Device cmd attempted on AdminQ */ + PDS_RC_ENOSUPP = 19, /* Operation not supported */ + PDS_RC_ERROR = 29, /* Generic error */ + PDS_RC_ERDMA = 30, /* Generic RDMA error */ + 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 */ +}; + +/** + * struct pds_core_drv_identity - Driver identity information + * @drv_type: Driver type (enum pds_core_driver_type) + * @os_dist: OS distribution, numeric format + * @os_dist_str: OS distribution, string format + * @kernel_ver: Kernel version, numeric format + * @kernel_ver_str: Kernel version, string format + * @driver_ver_str: Driver version, string format + */ +struct pds_core_drv_identity { + __le32 drv_type; + __le32 os_dist; + char os_dist_str[128]; + __le32 kernel_ver; + char kernel_ver_str[32]; + char driver_ver_str[32]; +}; + +#define PDS_DEV_TYPE_MAX 16 +/** + * struct pds_core_dev_identity - Device identity information + * @version: Version of device identify + * @type: Identify type (0 for now) + * @state: Device state + * @rsvd: Word boundary padding + * @nlifs: Number of LIFs provisioned + * @nintrs: Number of interrupts provisioned + * @ndbpgs_per_lif: Number of doorbell pages per LIF + * @intr_coal_mult: Interrupt coalescing multiplication factor + * Scale user-supplied interrupt coalescing + * value in usecs to device units using: + * device units = usecs * mult / div + * @intr_coal_div: Interrupt coalescing division factor + * Scale user-supplied interrupt coalescing + * value in usecs to device units using: + * device units = usecs * mult / div + * @vif_types: How many of each VIF device type is supported + */ +struct pds_core_dev_identity { + u8 version; + u8 type; + u8 state; + u8 rsvd; + __le32 nlifs; + __le32 nintrs; + __le32 ndbpgs_per_lif; + __le32 intr_coal_mult; + __le32 intr_coal_div; + __le16 vif_types[PDS_DEV_TYPE_MAX]; +}; + +#define PDS_CORE_IDENTITY_VERSION_1 1 + +/** + * struct pds_core_dev_identify_cmd - Driver/device identify command + * @opcode: Opcode PDS_CORE_CMD_IDENTIFY + * @ver: Highest version of identify supported by driver + * + * Expects to find driver identification info (struct pds_core_drv_identity) + * in cmd_regs->data. Driver should keep the devcmd interface locked + * while preparing the driver info. + */ +struct pds_core_dev_identify_cmd { + u8 opcode; + u8 ver; +}; + +/** + * struct pds_core_dev_identify_comp - Device identify command completion + * @status: Status of the command (enum pds_core_status_code) + * @ver: Version of identify returned by device + * + * Device identification info (struct pds_core_dev_identity) can be found + * in cmd_regs->data. Driver should keep the devcmd interface locked + * while reading the results. + */ +struct pds_core_dev_identify_comp { + u8 status; + u8 ver; +}; + +/** + * struct pds_core_dev_reset_cmd - Device reset command + * @opcode: Opcode PDS_CORE_CMD_RESET + * + * Resets and clears all LIFs, VDevs, and VIFs on the device. + */ +struct pds_core_dev_reset_cmd { + u8 opcode; +}; + +/** + * struct pds_core_dev_reset_comp - Reset command completion + * @status: Status of the command (enum pds_core_status_code) + */ +struct pds_core_dev_reset_comp { + u8 status; +}; + +/* + * struct pds_core_dev_init_data - Pointers and info needed for the Core + * initialization PDS_CORE_CMD_INIT command. The in and out structs are + * overlays on the pds_core_dev_cmd_regs.data space for passing data down + * to the firmware on init, and then returning initialization results. + */ +struct pds_core_dev_init_data_in { + __le64 adminq_q_base; + __le64 adminq_cq_base; + __le64 notifyq_cq_base; + __le32 flags; + __le16 intr_index; + u8 adminq_ring_size; + u8 notifyq_ring_size; +}; + +struct pds_core_dev_init_data_out { + __le32 core_hw_index; + __le32 adminq_hw_index; + __le32 notifyq_hw_index; + u8 adminq_hw_type; + u8 notifyq_hw_type; +}; + +/** + * struct pds_core_dev_init_cmd - Core device initialize + * @opcode: opcode PDS_CORE_CMD_INIT + * + * Initializes the core device and sets up the AdminQ and NotifyQ. + * Expects to find initialization data (struct pds_core_dev_init_data_in) + * in cmd_regs->data. Driver should keep the devcmd interface locked + * while preparing the driver info. + */ +struct pds_core_dev_init_cmd { + u8 opcode; +}; + +/** + * struct pds_core_dev_init_comp - Core init completion + * @status: Status of the command (enum pds_core_status_code) + * + * Initialization result data (struct pds_core_dev_init_data_in) + * is found in cmd_regs->data. + */ +struct pds_core_dev_init_comp { + u8 status; +}; + +/** + * struct pds_core_fw_download_cmd - Firmware download command + * @opcode: opcode + * @rsvd: Word boundary padding + * @addr: DMA address of the firmware buffer + * @offset: offset of the firmware buffer within the full image + * @length: number of valid bytes in the firmware buffer + */ +struct pds_core_fw_download_cmd { + u8 opcode; + u8 rsvd[3]; + __le32 offset; + __le64 addr; + __le32 length; +}; + +/** + * struct pds_core_fw_download_comp - Firmware download completion + * @status: Status of the command (enum pds_core_status_code) + */ +struct pds_core_fw_download_comp { + u8 status; +}; + +/** + * enum pds_core_fw_control_oper - FW control operations + * @PDS_CORE_FW_INSTALL_ASYNC: Install firmware asynchronously + * @PDS_CORE_FW_INSTALL_STATUS: Firmware installation status + * @PDS_CORE_FW_ACTIVATE_ASYNC: Activate firmware asynchronously + * @PDS_CORE_FW_ACTIVATE_STATUS: Firmware activate status + * @PDS_CORE_FW_UPDATE_CLEANUP: Cleanup any firmware update leftovers + * @PDS_CORE_FW_GET_BOOT: Return current active firmware slot + * @PDS_CORE_FW_SET_BOOT: Set active firmware slot for next boot + * @PDS_CORE_FW_GET_LIST: Return list of installed firmware images + */ +enum pds_core_fw_control_oper { + PDS_CORE_FW_INSTALL_ASYNC = 0, + PDS_CORE_FW_INSTALL_STATUS = 1, + PDS_CORE_FW_ACTIVATE_ASYNC = 2, + PDS_CORE_FW_ACTIVATE_STATUS = 3, + PDS_CORE_FW_UPDATE_CLEANUP = 4, + PDS_CORE_FW_GET_BOOT = 5, + PDS_CORE_FW_SET_BOOT = 6, + PDS_CORE_FW_GET_LIST = 7, +}; + +enum pds_core_fw_slot { + PDS_CORE_FW_SLOT_INVALID = 0, + PDS_CORE_FW_SLOT_A = 1, + PDS_CORE_FW_SLOT_B = 2, + PDS_CORE_FW_SLOT_GOLD = 3, +}; + +/** + * struct pds_core_fw_control_cmd - Firmware control command + * @opcode: opcode + * @rsvd: Word boundary padding + * @oper: firmware control operation (enum pds_core_fw_control_oper) + * @slot: slot to operate on (enum pds_core_fw_slot) + */ +struct pds_core_fw_control_cmd { + u8 opcode; + u8 rsvd[3]; + u8 oper; + u8 slot; +}; + +/** + * struct pds_core_fw_control_comp - Firmware control copletion + * @status: Status of the command (enum pds_core_status_code) + * @rsvd: Word alignment space + * @slot: Slot number (enum pds_core_fw_slot) + * @rsvd1: Struct padding + * @color: Color bit + */ +struct pds_core_fw_control_comp { + u8 status; + u8 rsvd[3]; + u8 slot; + u8 rsvd1[10]; + u8 color; +}; + +struct pds_core_fw_name_info { +#define PDS_CORE_FWSLOT_BUFLEN 8 +#define PDS_CORE_FWVERS_BUFLEN 32 + char slotname[PDS_CORE_FWSLOT_BUFLEN]; + char fw_version[PDS_CORE_FWVERS_BUFLEN]; +}; + +struct pds_core_fw_list_info { +#define PDS_CORE_FWVERS_LIST_LEN 16 + u8 num_fw_slots; + struct pds_core_fw_name_info fw_names[PDS_CORE_FWVERS_LIST_LEN]; +} __packed; + +enum pds_core_vf_attr { + PDS_CORE_VF_ATTR_SPOOFCHK = 1, + PDS_CORE_VF_ATTR_TRUST = 2, + PDS_CORE_VF_ATTR_MAC = 3, + PDS_CORE_VF_ATTR_LINKSTATE = 4, + PDS_CORE_VF_ATTR_VLAN = 5, + PDS_CORE_VF_ATTR_RATE = 6, + PDS_CORE_VF_ATTR_STATSADDR = 7, +}; + +/** + * enum pds_core_vf_link_status - Virtual Function link status + * @PDS_CORE_VF_LINK_STATUS_AUTO: Use link state of the uplink + * @PDS_CORE_VF_LINK_STATUS_UP: Link always up + * @PDS_CORE_VF_LINK_STATUS_DOWN: Link always down + */ +enum pds_core_vf_link_status { + PDS_CORE_VF_LINK_STATUS_AUTO = 0, + PDS_CORE_VF_LINK_STATUS_UP = 1, + PDS_CORE_VF_LINK_STATUS_DOWN = 2, +}; + +/** + * struct pds_core_vf_setattr_cmd - Set VF attributes on the NIC + * @opcode: Opcode + * @attr: Attribute type (enum pds_core_vf_attr) + * @vf_index: VF index + * @macaddr: mac address + * @vlanid: vlan ID + * @maxrate: max Tx rate in Mbps + * @spoofchk: enable address spoof checking + * @trust: enable VF trust + * @linkstate: set link up or down + * @stats: stats addr struct + * @stats.pa: set DMA address for VF stats + * @stats.len: length of VF stats space + * @pad: force union to specific size + */ +struct pds_core_vf_setattr_cmd { + u8 opcode; + u8 attr; + __le16 vf_index; + union { + u8 macaddr[6]; + __le16 vlanid; + __le32 maxrate; + u8 spoofchk; + u8 trust; + u8 linkstate; + struct { + __le64 pa; + __le32 len; + } stats; + u8 pad[60]; + } __packed; +}; + +struct pds_core_vf_setattr_comp { + u8 status; + u8 attr; + __le16 vf_index; + __le16 comp_index; + u8 rsvd[9]; + u8 color; +}; + +/** + * struct pds_core_vf_getattr_cmd - Get VF attributes from the NIC + * @opcode: Opcode + * @attr: Attribute type (enum pds_core_vf_attr) + * @vf_index: VF index + */ +struct pds_core_vf_getattr_cmd { + u8 opcode; + u8 attr; + __le16 vf_index; +}; + +struct pds_core_vf_getattr_comp { + u8 status; + u8 attr; + __le16 vf_index; + union { + u8 macaddr[6]; + __le16 vlanid; + __le32 maxrate; + u8 spoofchk; + u8 trust; + u8 linkstate; + __le64 stats_pa; + u8 pad[11]; + } __packed; + u8 color; +}; + +enum pds_core_vf_ctrl_opcode { + PDS_CORE_VF_CTRL_START_ALL = 0, + PDS_CORE_VF_CTRL_START = 1, +}; + +/** + * struct pds_core_vf_ctrl_cmd - VF control command + * @opcode: Opcode for the command + * @ctrl_opcode: VF control operation type + * @vf_index: VF Index. It is unused if op START_ALL is used. + */ + +struct pds_core_vf_ctrl_cmd { + u8 opcode; + u8 ctrl_opcode; + __le16 vf_index; +}; + +/** + * struct pds_core_vf_ctrl_comp - VF_CTRL command completion. + * @status: Status of the command (enum pds_core_status_code) + */ +struct pds_core_vf_ctrl_comp { + u8 status; +}; + +/* + * union pds_core_dev_cmd - Overlay of core device command structures + */ +union pds_core_dev_cmd { + u8 opcode; + u32 words[16]; + + struct pds_core_dev_identify_cmd identify; + struct pds_core_dev_init_cmd init; + struct pds_core_dev_reset_cmd reset; + struct pds_core_fw_download_cmd fw_download; + struct pds_core_fw_control_cmd fw_control; + + struct pds_core_vf_setattr_cmd vf_setattr; + struct pds_core_vf_getattr_cmd vf_getattr; + struct pds_core_vf_ctrl_cmd vf_ctrl; +}; + +/* + * union pds_core_dev_comp - Overlay of core device completion structures + */ +union pds_core_dev_comp { + u8 status; + u8 bytes[16]; + + struct pds_core_dev_identify_comp identify; + struct pds_core_dev_reset_comp reset; + struct pds_core_dev_init_comp init; + struct pds_core_fw_download_comp fw_download; + struct pds_core_fw_control_comp fw_control; + + struct pds_core_vf_setattr_comp vf_setattr; + struct pds_core_vf_getattr_comp vf_getattr; + struct pds_core_vf_ctrl_comp vf_ctrl; +}; + +/** + * struct pds_core_dev_hwstamp_regs - Hardware current timestamp registers + * @tick_low: Low 32 bits of hardware timestamp + * @tick_high: High 32 bits of hardware timestamp + */ +struct pds_core_dev_hwstamp_regs { + u32 tick_low; + u32 tick_high; +}; + +/** + * struct pds_core_dev_info_regs - Device info register format (read-only) + * @signature: Signature value of 0x44455649 ('DEVI') + * @version: Current version of info + * @asic_type: Asic type + * @asic_rev: Asic revision + * @fw_status: Firmware status + * bit 0 - 1 = fw running + * bit 4-7 - 4 bit generation number, changes on fw restart + * @fw_heartbeat: Firmware heartbeat counter + * @serial_num: Serial number + * @fw_version: Firmware version + * @oprom_regs: oprom_regs to store oprom debug enable/disable and bmp + * @rsvd_pad1024: Struct padding + * @hwstamp: Hardware current timestamp registers + * @rsvd_pad2048: Struct padding + */ +struct pds_core_dev_info_regs { +#define PDS_CORE_DEVINFO_FWVERS_BUFLEN 32 +#define PDS_CORE_DEVINFO_SERIAL_BUFLEN 32 + u32 signature; + u8 version; + u8 asic_type; + u8 asic_rev; +#define PDS_CORE_FW_STS_F_STOPPED 0x00 +#define PDS_CORE_FW_STS_F_RUNNING 0x01 +#define PDS_CORE_FW_STS_F_GENERATION 0xF0 + u8 fw_status; + __le32 fw_heartbeat; + char fw_version[PDS_CORE_DEVINFO_FWVERS_BUFLEN]; + char serial_num[PDS_CORE_DEVINFO_SERIAL_BUFLEN]; + u8 oprom_regs[32]; /* reserved */ + u8 rsvd_pad1024[916]; + struct pds_core_dev_hwstamp_regs hwstamp; /* on 1k boundary */ + u8 rsvd_pad2048[1016]; +} __packed; + +/** + * struct pds_core_dev_cmd_regs - Device command register format (read-write) + * @doorbell: Device Cmd Doorbell, write-only + * Write a 1 to signal device to process cmd + * @done: Command completed indicator, poll for completion + * bit 0 == 1 when command is complete + * @cmd: Opcode-specific command bytes + * @comp: Opcode-specific response bytes + * @rsvd: Struct padding + * @data: Opcode-specific side-data + */ +struct pds_core_dev_cmd_regs { + u32 doorbell; + u32 done; + union pds_core_dev_cmd cmd; + union pds_core_dev_comp comp; + u8 rsvd[48]; + u32 data[478]; +} __packed; + +/** + * struct pds_core_dev_regs - Device register format for bar 0 page 0 + * @info: Device info registers + * @devcmd: Device command registers + */ +struct pds_core_dev_regs { + struct pds_core_dev_info_regs info; + struct pds_core_dev_cmd_regs devcmd; +} __packed; + +#ifndef __CHECKER__ +static_assert(sizeof(struct pds_core_drv_identity) <= 1912); +static_assert(sizeof(struct pds_core_dev_identity) <= 1912); +static_assert(sizeof(union pds_core_dev_cmd) == 64); +static_assert(sizeof(union pds_core_dev_comp) == 16); +static_assert(sizeof(struct pds_core_dev_info_regs) == 2048); +static_assert(sizeof(struct pds_core_dev_cmd_regs) == 2048); +static_assert(sizeof(struct pds_core_dev_regs) == 4096); +#endif /* __CHECKER__ */ + +#endif /* _PDS_CORE_IF_H_ */ -- cgit v1.2.3 From 523847df1b3718d6286dce0ed1c83742fe0ffa94 Mon Sep 17 00:00:00 2001 From: Shannon Nelson Date: Wed, 19 Apr 2023 10:04:15 -0700 Subject: pds_core: add devcmd device interfaces The devcmd interface is the basic connection to the device through the PCI BAR for low level identification and command services. This does the early device initialization and finds the identity data, and adds devcmd routines to be used by later driver bits. Signed-off-by: Shannon Nelson Acked-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/linux/pds/pds_common.h | 30 ++++++++ include/linux/pds/pds_intr.h | 163 +++++++++++++++++++++++++++++++++++++++++ 2 files changed, 193 insertions(+) create mode 100644 include/linux/pds/pds_intr.h (limited to 'include/linux') diff --git a/include/linux/pds/pds_common.h b/include/linux/pds/pds_common.h index bd041a5170a6..f0798ce01acf 100644 --- a/include/linux/pds/pds_common.h +++ b/include/linux/pds/pds_common.h @@ -11,4 +11,34 @@ #define PDS_CORE_ADDR_MASK (BIT_ULL(PDS_ADDR_LEN) - 1) #define PDS_PAGE_SIZE 4096 +enum pds_core_driver_type { + PDS_DRIVER_LINUX = 1, + PDS_DRIVER_WIN = 2, + PDS_DRIVER_DPDK = 3, + PDS_DRIVER_FREEBSD = 4, + PDS_DRIVER_IPXE = 5, + PDS_DRIVER_ESXI = 6, +}; + +#define PDS_CORE_IFNAMSIZ 16 + +/** + * enum pds_core_logical_qtype - Logical Queue Types + * @PDS_CORE_QTYPE_ADMINQ: Administrative Queue + * @PDS_CORE_QTYPE_NOTIFYQ: Notify Queue + * @PDS_CORE_QTYPE_RXQ: Receive Queue + * @PDS_CORE_QTYPE_TXQ: Transmit Queue + * @PDS_CORE_QTYPE_EQ: Event Queue + * @PDS_CORE_QTYPE_MAX: Max queue type supported + */ +enum pds_core_logical_qtype { + PDS_CORE_QTYPE_ADMINQ = 0, + PDS_CORE_QTYPE_NOTIFYQ = 1, + PDS_CORE_QTYPE_RXQ = 2, + PDS_CORE_QTYPE_TXQ = 3, + PDS_CORE_QTYPE_EQ = 4, + + PDS_CORE_QTYPE_MAX = 16 /* don't change - used in struct size */ +}; + #endif /* _PDS_COMMON_H_ */ diff --git a/include/linux/pds/pds_intr.h b/include/linux/pds/pds_intr.h new file mode 100644 index 000000000000..56277c37248c --- /dev/null +++ b/include/linux/pds/pds_intr.h @@ -0,0 +1,163 @@ +/* SPDX-License-Identifier: (GPL-2.0 OR Linux-OpenIB) OR BSD-2-Clause */ +/* Copyright(c) 2023 Advanced Micro Devices, Inc. */ + +#ifndef _PDS_INTR_H_ +#define _PDS_INTR_H_ + +/* + * Interrupt control register + * @coal_init: Coalescing timer initial value, in + * device units. Use @identity->intr_coal_mult + * and @identity->intr_coal_div to convert from + * usecs to device units: + * + * coal_init = coal_usecs * coal_mutl / coal_div + * + * When an interrupt is sent the interrupt + * coalescing timer current value + * (@coalescing_curr) is initialized with this + * value and begins counting down. No more + * interrupts are sent until the coalescing + * timer reaches 0. When @coalescing_init=0 + * interrupt coalescing is effectively disabled + * and every interrupt assert results in an + * interrupt. Reset value: 0 + * @mask: Interrupt mask. When @mask=1 the interrupt + * resource will not send an interrupt. When + * @mask=0 the interrupt resource will send an + * interrupt if an interrupt event is pending + * or on the next interrupt assertion event. + * Reset value: 1 + * @credits: Interrupt credits. This register indicates + * how many interrupt events the hardware has + * sent. When written by software this + * register atomically decrements @int_credits + * by the value written. When @int_credits + * becomes 0 then the "pending interrupt" bit + * in the Interrupt Status register is cleared + * by the hardware and any pending but unsent + * interrupts are cleared. + * !!!IMPORTANT!!! This is a signed register. + * @flags: Interrupt control flags + * @unmask -- When this bit is written with a 1 + * the interrupt resource will set mask=0. + * @coal_timer_reset -- When this + * bit is written with a 1 the + * @coalescing_curr will be reloaded with + * @coalescing_init to reset the coalescing + * timer. + * @mask_on_assert: Automatically mask on assertion. When + * @mask_on_assert=1 the interrupt resource + * will set @mask=1 whenever an interrupt is + * sent. When using interrupts in Legacy + * Interrupt mode the driver must select + * @mask_on_assert=0 for proper interrupt + * operation. + * @coalescing_curr: Coalescing timer current value, in + * microseconds. When this value reaches 0 + * the interrupt resource is again eligible to + * send an interrupt. If an interrupt event + * is already pending when @coalescing_curr + * reaches 0 the pending interrupt will be + * sent, otherwise an interrupt will be sent + * on the next interrupt assertion event. + */ +struct pds_core_intr { + u32 coal_init; + u32 mask; + u16 credits; + u16 flags; +#define PDS_CORE_INTR_F_UNMASK 0x0001 +#define PDS_CORE_INTR_F_TIMER_RESET 0x0002 + u32 mask_on_assert; + u32 coalescing_curr; + u32 rsvd6[3]; +}; + +#ifndef __CHECKER__ +static_assert(sizeof(struct pds_core_intr) == 32); +#endif /* __CHECKER__ */ + +#define PDS_CORE_INTR_CTRL_REGS_MAX 2048 +#define PDS_CORE_INTR_CTRL_COAL_MAX 0x3F +#define PDS_CORE_INTR_INDEX_NOT_ASSIGNED -1 + +struct pds_core_intr_status { + u32 status[2]; +}; + +/** + * enum pds_core_intr_mask_vals - valid values for mask and mask_assert. + * @PDS_CORE_INTR_MASK_CLEAR: unmask interrupt. + * @PDS_CORE_INTR_MASK_SET: mask interrupt. + */ +enum pds_core_intr_mask_vals { + PDS_CORE_INTR_MASK_CLEAR = 0, + PDS_CORE_INTR_MASK_SET = 1, +}; + +/** + * enum pds_core_intr_credits_bits - Bitwise composition of credits values. + * @PDS_CORE_INTR_CRED_COUNT: bit mask of credit count, no shift needed. + * @PDS_CORE_INTR_CRED_COUNT_SIGNED: bit mask of credit count, including sign bit. + * @PDS_CORE_INTR_CRED_UNMASK: unmask the interrupt. + * @PDS_CORE_INTR_CRED_RESET_COALESCE: reset the coalesce timer. + * @PDS_CORE_INTR_CRED_REARM: unmask the and reset the timer. + */ +enum pds_core_intr_credits_bits { + PDS_CORE_INTR_CRED_COUNT = 0x7fffu, + PDS_CORE_INTR_CRED_COUNT_SIGNED = 0xffffu, + PDS_CORE_INTR_CRED_UNMASK = 0x10000u, + PDS_CORE_INTR_CRED_RESET_COALESCE = 0x20000u, + PDS_CORE_INTR_CRED_REARM = (PDS_CORE_INTR_CRED_UNMASK | + PDS_CORE_INTR_CRED_RESET_COALESCE), +}; + +static inline void +pds_core_intr_coal_init(struct pds_core_intr __iomem *intr_ctrl, u32 coal) +{ + iowrite32(coal, &intr_ctrl->coal_init); +} + +static inline void +pds_core_intr_mask(struct pds_core_intr __iomem *intr_ctrl, u32 mask) +{ + iowrite32(mask, &intr_ctrl->mask); +} + +static inline void +pds_core_intr_credits(struct pds_core_intr __iomem *intr_ctrl, + u32 cred, u32 flags) +{ + if (WARN_ON_ONCE(cred > PDS_CORE_INTR_CRED_COUNT)) { + cred = ioread32(&intr_ctrl->credits); + cred &= PDS_CORE_INTR_CRED_COUNT_SIGNED; + } + + iowrite32(cred | flags, &intr_ctrl->credits); +} + +static inline void +pds_core_intr_clean_flags(struct pds_core_intr __iomem *intr_ctrl, u32 flags) +{ + u32 cred; + + cred = ioread32(&intr_ctrl->credits); + cred &= PDS_CORE_INTR_CRED_COUNT_SIGNED; + cred |= flags; + iowrite32(cred, &intr_ctrl->credits); +} + +static inline void +pds_core_intr_clean(struct pds_core_intr __iomem *intr_ctrl) +{ + pds_core_intr_clean_flags(intr_ctrl, PDS_CORE_INTR_CRED_RESET_COALESCE); +} + +static inline void +pds_core_intr_mask_assert(struct pds_core_intr __iomem *intr_ctrl, u32 mask) +{ + iowrite32(mask, &intr_ctrl->mask_on_assert); +} + +#endif /* _PDS_INTR_H_ */ -- cgit v1.2.3 From 45d76f492938cdc27ddadc16e1e75103f4cfbf56 Mon Sep 17 00:00:00 2001 From: Shannon Nelson Date: Wed, 19 Apr 2023 10:04:18 -0700 Subject: pds_core: set up device and adminq Set up the basic adminq and notifyq queue structures. These are used mostly by the client drivers for feature configuration. These are essentially the same adminq and notifyq as in the ionic driver. Part of this includes querying for device identity and FW information, so we can make that available to devlink dev info. $ devlink dev info pci/0000:b5:00.0 pci/0000:b5:00.0: driver pds_core serial_number FLM18420073 versions: fixed: asic.id 0x0 asic.rev 0x0 running: fw 1.51.0-73 stored: fw.goldfw 1.15.9-C-22 fw.mainfwa 1.60.0-73 fw.mainfwb 1.60.0-57 Signed-off-by: Shannon Nelson Acked-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/linux/pds/pds_adminq.h | 638 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 638 insertions(+) create mode 100644 include/linux/pds/pds_adminq.h (limited to 'include/linux') diff --git a/include/linux/pds/pds_adminq.h b/include/linux/pds/pds_adminq.h new file mode 100644 index 000000000000..dd5fbe3ee141 --- /dev/null +++ b/include/linux/pds/pds_adminq.h @@ -0,0 +1,638 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2023 Advanced Micro Devices, Inc */ + +#ifndef _PDS_CORE_ADMINQ_H_ +#define _PDS_CORE_ADMINQ_H_ + +enum pds_core_adminq_flags { + PDS_AQ_FLAG_FASTPOLL = BIT(1), /* completion poll at 1ms */ +}; + +/* + * enum pds_core_adminq_opcode - AdminQ command opcodes + * These commands are only processed on AdminQ, not available in devcmd + */ +enum pds_core_adminq_opcode { + PDS_AQ_CMD_NOP = 0, + + /* Client control */ + PDS_AQ_CMD_CLIENT_REG = 6, + PDS_AQ_CMD_CLIENT_UNREG = 7, + PDS_AQ_CMD_CLIENT_CMD = 8, + + /* LIF commands */ + PDS_AQ_CMD_LIF_IDENTIFY = 20, + PDS_AQ_CMD_LIF_INIT = 21, + PDS_AQ_CMD_LIF_RESET = 22, + PDS_AQ_CMD_LIF_GETATTR = 23, + PDS_AQ_CMD_LIF_SETATTR = 24, + PDS_AQ_CMD_LIF_SETPHC = 25, + + PDS_AQ_CMD_RX_MODE_SET = 30, + PDS_AQ_CMD_RX_FILTER_ADD = 31, + PDS_AQ_CMD_RX_FILTER_DEL = 32, + + /* Queue commands */ + PDS_AQ_CMD_Q_IDENTIFY = 39, + PDS_AQ_CMD_Q_INIT = 40, + PDS_AQ_CMD_Q_CONTROL = 41, + + /* SR/IOV commands */ + PDS_AQ_CMD_VF_GETATTR = 60, + PDS_AQ_CMD_VF_SETATTR = 61, +}; + +/* + * enum pds_core_notifyq_opcode - NotifyQ event codes + */ +enum pds_core_notifyq_opcode { + PDS_EVENT_LINK_CHANGE = 1, + PDS_EVENT_RESET = 2, + PDS_EVENT_XCVR = 5, + PDS_EVENT_CLIENT = 6, +}; + +#define PDS_COMP_COLOR_MASK 0x80 + +/** + * struct pds_core_notifyq_event - Generic event reporting structure + * @eid: event number + * @ecode: event code + * + * This is the generic event report struct from which the other + * actual events will be formed. + */ +struct pds_core_notifyq_event { + __le64 eid; + __le16 ecode; +}; + +/** + * struct pds_core_link_change_event - Link change event notification + * @eid: event number + * @ecode: event code = PDS_EVENT_LINK_CHANGE + * @link_status: link up/down, with error bits + * @link_speed: speed of the network link + * + * Sent when the network link state changes between UP and DOWN + */ +struct pds_core_link_change_event { + __le64 eid; + __le16 ecode; + __le16 link_status; + __le32 link_speed; /* units of 1Mbps: e.g. 10000 = 10Gbps */ +}; + +/** + * struct pds_core_reset_event - Reset event notification + * @eid: event number + * @ecode: event code = PDS_EVENT_RESET + * @reset_code: reset type + * @state: 0=pending, 1=complete, 2=error + * + * Sent when the NIC or some subsystem is going to be or + * has been reset. + */ +struct pds_core_reset_event { + __le64 eid; + __le16 ecode; + u8 reset_code; + u8 state; +}; + +/** + * struct pds_core_client_event - Client event notification + * @eid: event number + * @ecode: event code = PDS_EVENT_CLIENT + * @client_id: client to sent event to + * @client_event: wrapped event struct for the client + * + * Sent when an event needs to be passed on to a client + */ +struct pds_core_client_event { + __le64 eid; + __le16 ecode; + __le16 client_id; + u8 client_event[54]; +}; + +/** + * struct pds_core_notifyq_cmd - Placeholder for building qcq + * @data: anonymous field for building the qcq + */ +struct pds_core_notifyq_cmd { + __le32 data; /* Not used but needed for qcq structure */ +}; + +/* + * union pds_core_notifyq_comp - Overlay of notifyq event structures + */ +union pds_core_notifyq_comp { + struct { + __le64 eid; + __le16 ecode; + }; + struct pds_core_notifyq_event event; + struct pds_core_link_change_event link_change; + struct pds_core_reset_event reset; + u8 data[64]; +}; + +#define PDS_DEVNAME_LEN 32 +/** + * struct pds_core_client_reg_cmd - Register a new client with DSC + * @opcode: opcode PDS_AQ_CMD_CLIENT_REG + * @rsvd: word boundary padding + * @devname: text name of client device + * @vif_type: what type of device (enum pds_core_vif_types) + * + * Tell the DSC of the new client, and receive a client_id from DSC. + */ +struct pds_core_client_reg_cmd { + u8 opcode; + u8 rsvd[3]; + char devname[PDS_DEVNAME_LEN]; + u8 vif_type; +}; + +/** + * struct pds_core_client_reg_comp - Client registration completion + * @status: Status of the command (enum pdc_core_status_code) + * @rsvd: Word boundary padding + * @comp_index: Index in the descriptor ring for which this is the completion + * @client_id: New id assigned by DSC + * @rsvd1: Word boundary padding + * @color: Color bit + */ +struct pds_core_client_reg_comp { + u8 status; + u8 rsvd; + __le16 comp_index; + __le16 client_id; + u8 rsvd1[9]; + u8 color; +}; + +/** + * struct pds_core_client_unreg_cmd - Unregister a client from DSC + * @opcode: opcode PDS_AQ_CMD_CLIENT_UNREG + * @rsvd: word boundary padding + * @client_id: id of client being removed + * + * Tell the DSC this client is going away and remove its context + * This uses the generic completion. + */ +struct pds_core_client_unreg_cmd { + u8 opcode; + u8 rsvd; + __le16 client_id; +}; + +/** + * struct pds_core_client_request_cmd - Pass along a wrapped client AdminQ cmd + * @opcode: opcode PDS_AQ_CMD_CLIENT_CMD + * @rsvd: word boundary padding + * @client_id: id of client being removed + * @client_cmd: the wrapped client command + * + * Proxy post an adminq command for the client. + * This uses the generic completion. + */ +struct pds_core_client_request_cmd { + u8 opcode; + u8 rsvd; + __le16 client_id; + u8 client_cmd[60]; +}; + +#define PDS_CORE_MAX_FRAGS 16 + +#define PDS_CORE_QCQ_F_INITED BIT(0) +#define PDS_CORE_QCQ_F_SG BIT(1) +#define PDS_CORE_QCQ_F_INTR BIT(2) +#define PDS_CORE_QCQ_F_TX_STATS BIT(3) +#define PDS_CORE_QCQ_F_RX_STATS BIT(4) +#define PDS_CORE_QCQ_F_NOTIFYQ BIT(5) +#define PDS_CORE_QCQ_F_CMB_RINGS BIT(6) +#define PDS_CORE_QCQ_F_CORE BIT(7) + +enum pds_core_lif_type { + PDS_CORE_LIF_TYPE_DEFAULT = 0, +}; + +/** + * union pds_core_lif_config - LIF configuration + * @state: LIF state (enum pds_core_lif_state) + * @rsvd: Word boundary padding + * @name: LIF name + * @rsvd2: Word boundary padding + * @features: LIF features active (enum pds_core_hw_features) + * @queue_count: Queue counts per queue-type + * @words: Full union buffer size + */ +union pds_core_lif_config { + struct { + u8 state; + u8 rsvd[3]; + char name[PDS_CORE_IFNAMSIZ]; + u8 rsvd2[12]; + __le64 features; + __le32 queue_count[PDS_CORE_QTYPE_MAX]; + } __packed; + __le32 words[64]; +}; + +/** + * struct pds_core_lif_status - LIF status register + * @eid: most recent NotifyQ event id + * @rsvd: full struct size + */ +struct pds_core_lif_status { + __le64 eid; + u8 rsvd[56]; +}; + +/** + * struct pds_core_lif_info - LIF info structure + * @config: LIF configuration structure + * @status: LIF status structure + */ +struct pds_core_lif_info { + union pds_core_lif_config config; + struct pds_core_lif_status status; +}; + +/** + * struct pds_core_lif_identity - LIF identity information (type-specific) + * @features: LIF features (see enum pds_core_hw_features) + * @version: Identify structure version + * @hw_index: LIF hardware index + * @rsvd: Word boundary padding + * @max_nb_sessions: Maximum number of sessions supported + * @rsvd2: buffer padding + * @config: LIF config struct with features, q counts + */ +struct pds_core_lif_identity { + __le64 features; + u8 version; + u8 hw_index; + u8 rsvd[2]; + __le32 max_nb_sessions; + u8 rsvd2[120]; + union pds_core_lif_config config; +}; + +/** + * struct pds_core_lif_identify_cmd - Get LIF identity info command + * @opcode: Opcode PDS_AQ_CMD_LIF_IDENTIFY + * @type: LIF type (enum pds_core_lif_type) + * @client_id: Client identifier + * @ver: Version of identify returned by device + * @rsvd: Word boundary padding + * @ident_pa: DMA address to receive identity info + * + * Firmware will copy LIF identity data (struct pds_core_lif_identity) + * into the buffer address given. + */ +struct pds_core_lif_identify_cmd { + u8 opcode; + u8 type; + __le16 client_id; + u8 ver; + u8 rsvd[3]; + __le64 ident_pa; +}; + +/** + * struct pds_core_lif_identify_comp - LIF identify command completion + * @status: Status of the command (enum pds_core_status_code) + * @ver: Version of identify returned by device + * @bytes: Bytes copied into the buffer + * @rsvd: Word boundary padding + * @color: Color bit + */ +struct pds_core_lif_identify_comp { + u8 status; + u8 ver; + __le16 bytes; + u8 rsvd[11]; + u8 color; +}; + +/** + * struct pds_core_lif_init_cmd - LIF init command + * @opcode: Opcode PDS_AQ_CMD_LIF_INIT + * @type: LIF type (enum pds_core_lif_type) + * @client_id: Client identifier + * @rsvd: Word boundary padding + * @info_pa: Destination address for LIF info (struct pds_core_lif_info) + */ +struct pds_core_lif_init_cmd { + u8 opcode; + u8 type; + __le16 client_id; + __le32 rsvd; + __le64 info_pa; +}; + +/** + * struct pds_core_lif_init_comp - LIF init command completion + * @status: Status of the command (enum pds_core_status_code) + * @rsvd: Word boundary padding + * @hw_index: Hardware index of the initialized LIF + * @rsvd1: Word boundary padding + * @color: Color bit + */ +struct pds_core_lif_init_comp { + u8 status; + u8 rsvd; + __le16 hw_index; + u8 rsvd1[11]; + u8 color; +}; + +/** + * struct pds_core_lif_reset_cmd - LIF reset command + * Will reset only the specified LIF. + * @opcode: Opcode PDS_AQ_CMD_LIF_RESET + * @rsvd: Word boundary padding + * @client_id: Client identifier + */ +struct pds_core_lif_reset_cmd { + u8 opcode; + u8 rsvd; + __le16 client_id; +}; + +/** + * enum pds_core_lif_attr - List of LIF attributes + * @PDS_CORE_LIF_ATTR_STATE: LIF state attribute + * @PDS_CORE_LIF_ATTR_NAME: LIF name attribute + * @PDS_CORE_LIF_ATTR_FEATURES: LIF features attribute + * @PDS_CORE_LIF_ATTR_STATS_CTRL: LIF statistics control attribute + */ +enum pds_core_lif_attr { + PDS_CORE_LIF_ATTR_STATE = 0, + PDS_CORE_LIF_ATTR_NAME = 1, + PDS_CORE_LIF_ATTR_FEATURES = 4, + PDS_CORE_LIF_ATTR_STATS_CTRL = 6, +}; + +/** + * struct pds_core_lif_setattr_cmd - Set LIF attributes on the NIC + * @opcode: Opcode PDS_AQ_CMD_LIF_SETATTR + * @attr: Attribute type (enum pds_core_lif_attr) + * @client_id: Client identifier + * @state: LIF state (enum pds_core_lif_state) + * @name: The name string, 0 terminated + * @features: Features (enum pds_core_hw_features) + * @stats_ctl: Stats control commands (enum pds_core_stats_ctl_cmd) + * @rsvd: Command Buffer padding + */ +struct pds_core_lif_setattr_cmd { + u8 opcode; + u8 attr; + __le16 client_id; + union { + u8 state; + char name[PDS_CORE_IFNAMSIZ]; + __le64 features; + u8 stats_ctl; + u8 rsvd[60]; + } __packed; +}; + +/** + * struct pds_core_lif_setattr_comp - LIF set attr command completion + * @status: Status of the command (enum pds_core_status_code) + * @rsvd: Word boundary padding + * @comp_index: Index in the descriptor ring for which this is the completion + * @features: Features (enum pds_core_hw_features) + * @rsvd2: Word boundary padding + * @color: Color bit + */ +struct pds_core_lif_setattr_comp { + u8 status; + u8 rsvd; + __le16 comp_index; + union { + __le64 features; + u8 rsvd2[11]; + } __packed; + u8 color; +}; + +/** + * struct pds_core_lif_getattr_cmd - Get LIF attributes from the NIC + * @opcode: Opcode PDS_AQ_CMD_LIF_GETATTR + * @attr: Attribute type (enum pds_core_lif_attr) + * @client_id: Client identifier + */ +struct pds_core_lif_getattr_cmd { + u8 opcode; + u8 attr; + __le16 client_id; +}; + +/** + * struct pds_core_lif_getattr_comp - LIF get attr command completion + * @status: Status of the command (enum pds_core_status_code) + * @rsvd: Word boundary padding + * @comp_index: Index in the descriptor ring for which this is the completion + * @state: LIF state (enum pds_core_lif_state) + * @name: LIF name string, 0 terminated + * @features: Features (enum pds_core_hw_features) + * @rsvd2: Word boundary padding + * @color: Color bit + */ +struct pds_core_lif_getattr_comp { + u8 status; + u8 rsvd; + __le16 comp_index; + union { + u8 state; + __le64 features; + u8 rsvd2[11]; + } __packed; + u8 color; +}; + +/** + * union pds_core_q_identity - Queue identity information + * @version: Queue type version that can be used with FW + * @supported: Bitfield of queue versions, first bit = ver 0 + * @rsvd: Word boundary padding + * @features: Queue features + * @desc_sz: Descriptor size + * @comp_sz: Completion descriptor size + * @rsvd2: Word boundary padding + */ +struct pds_core_q_identity { + u8 version; + u8 supported; + u8 rsvd[6]; +#define PDS_CORE_QIDENT_F_CQ 0x01 /* queue has completion ring */ + __le64 features; + __le16 desc_sz; + __le16 comp_sz; + u8 rsvd2[6]; +}; + +/** + * struct pds_core_q_identify_cmd - queue identify command + * @opcode: Opcode PDS_AQ_CMD_Q_IDENTIFY + * @type: Logical queue type (enum pds_core_logical_qtype) + * @client_id: Client identifier + * @ver: Highest queue type version that the driver supports + * @rsvd: Word boundary padding + * @ident_pa: DMA address to receive the data (struct pds_core_q_identity) + */ +struct pds_core_q_identify_cmd { + u8 opcode; + u8 type; + __le16 client_id; + u8 ver; + u8 rsvd[3]; + __le64 ident_pa; +}; + +/** + * struct pds_core_q_identify_comp - queue identify command completion + * @status: Status of the command (enum pds_core_status_code) + * @rsvd: Word boundary padding + * @comp_index: Index in the descriptor ring for which this is the completion + * @ver: Queue type version that can be used with FW + * @rsvd1: Word boundary padding + * @color: Color bit + */ +struct pds_core_q_identify_comp { + u8 status; + u8 rsvd; + __le16 comp_index; + u8 ver; + u8 rsvd1[10]; + u8 color; +}; + +/** + * struct pds_core_q_init_cmd - Queue init command + * @opcode: Opcode PDS_AQ_CMD_Q_INIT + * @type: Logical queue type + * @client_id: Client identifier + * @ver: Queue type version + * @rsvd: Word boundary padding + * @index: (LIF, qtype) relative admin queue index + * @intr_index: Interrupt control register index, or Event queue index + * @pid: Process ID + * @flags: + * IRQ: Interrupt requested on completion + * ENA: Enable the queue. If ENA=0 the queue is initialized + * but remains disabled, to be later enabled with the + * Queue Enable command. If ENA=1, then queue is + * initialized and then enabled. + * @cos: Class of service for this queue + * @ring_size: Queue ring size, encoded as a log2(size), in + * number of descriptors. The actual ring size is + * (1 << ring_size). For example, to select a ring size + * of 64 descriptors write ring_size = 6. The minimum + * ring_size value is 2 for a ring of 4 descriptors. + * The maximum ring_size value is 12 for a ring of 4k + * descriptors. Values of ring_size <2 and >12 are + * reserved. + * @ring_base: Queue ring base address + * @cq_ring_base: Completion queue ring base address + */ +struct pds_core_q_init_cmd { + u8 opcode; + u8 type; + __le16 client_id; + u8 ver; + u8 rsvd[3]; + __le32 index; + __le16 pid; + __le16 intr_index; + __le16 flags; +#define PDS_CORE_QINIT_F_IRQ 0x01 /* Request interrupt on completion */ +#define PDS_CORE_QINIT_F_ENA 0x02 /* Enable the queue */ + u8 cos; +#define PDS_CORE_QSIZE_MIN_LG2 2 +#define PDS_CORE_QSIZE_MAX_LG2 12 + u8 ring_size; + __le64 ring_base; + __le64 cq_ring_base; +} __packed; + +/** + * struct pds_core_q_init_comp - Queue init command completion + * @status: Status of the command (enum pds_core_status_code) + * @rsvd: Word boundary padding + * @comp_index: Index in the descriptor ring for which this is the completion + * @hw_index: Hardware Queue ID + * @hw_type: Hardware Queue type + * @rsvd2: Word boundary padding + * @color: Color + */ +struct pds_core_q_init_comp { + u8 status; + u8 rsvd; + __le16 comp_index; + __le32 hw_index; + u8 hw_type; + u8 rsvd2[6]; + u8 color; +}; + +union pds_core_adminq_cmd { + u8 opcode; + u8 bytes[64]; + + struct pds_core_client_reg_cmd client_reg; + struct pds_core_client_unreg_cmd client_unreg; + struct pds_core_client_request_cmd client_request; + + struct pds_core_lif_identify_cmd lif_ident; + struct pds_core_lif_init_cmd lif_init; + struct pds_core_lif_reset_cmd lif_reset; + struct pds_core_lif_setattr_cmd lif_setattr; + struct pds_core_lif_getattr_cmd lif_getattr; + + struct pds_core_q_identify_cmd q_ident; + struct pds_core_q_init_cmd q_init; +}; + +union pds_core_adminq_comp { + struct { + u8 status; + u8 rsvd; + __le16 comp_index; + u8 rsvd2[11]; + u8 color; + }; + u32 words[4]; + + struct pds_core_client_reg_comp client_reg; + + struct pds_core_lif_identify_comp lif_ident; + struct pds_core_lif_init_comp lif_init; + struct pds_core_lif_setattr_comp lif_setattr; + struct pds_core_lif_getattr_comp lif_getattr; + + struct pds_core_q_identify_comp q_ident; + struct pds_core_q_init_comp q_init; +}; + +#ifndef __CHECKER__ +static_assert(sizeof(union pds_core_adminq_cmd) == 64); +static_assert(sizeof(union pds_core_adminq_comp) == 16); +static_assert(sizeof(union pds_core_notifyq_comp) == 64); +#endif /* __CHECKER__ */ + +/* The color bit is a 'done' bit for the completion descriptors + * where the meaning alternates between '1' and '0' for alternating + * passes through the completion descriptor ring. + */ +static inline u8 pdsc_color_match(u8 color, u8 done_color) +{ + return (!!(color & PDS_COMP_COLOR_MASK)) == done_color; +} +#endif /* _PDS_CORE_ADMINQ_H_ */ -- cgit v1.2.3 From 01ba61b55b2041a39c54aefb3153c770dd59a0ef Mon Sep 17 00:00:00 2001 From: Shannon Nelson Date: Wed, 19 Apr 2023 10:04:19 -0700 Subject: pds_core: Add adminq processing and commands Add the service routines for submitting and processing the adminq messages and for handling notifyq events. Signed-off-by: Shannon Nelson Acked-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/linux/pds/pds_adminq.h | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pds/pds_adminq.h b/include/linux/pds/pds_adminq.h index dd5fbe3ee141..98a60ce87b92 100644 --- a/include/linux/pds/pds_adminq.h +++ b/include/linux/pds/pds_adminq.h @@ -4,6 +4,8 @@ #ifndef _PDS_CORE_ADMINQ_H_ #define _PDS_CORE_ADMINQ_H_ +#define PDSC_ADMINQ_MAX_POLL_INTERVAL 256 + enum pds_core_adminq_flags { PDS_AQ_FLAG_FASTPOLL = BIT(1), /* completion poll at 1ms */ }; @@ -631,8 +633,15 @@ static_assert(sizeof(union pds_core_notifyq_comp) == 64); * where the meaning alternates between '1' and '0' for alternating * passes through the completion descriptor ring. */ -static inline u8 pdsc_color_match(u8 color, u8 done_color) +static inline bool pdsc_color_match(u8 color, bool done_color) { return (!!(color & PDS_COMP_COLOR_MASK)) == done_color; } + +struct pdsc; +int pdsc_adminq_post(struct pdsc *pdsc, + union pds_core_adminq_cmd *cmd, + union pds_core_adminq_comp *comp, + bool fast_poll); + #endif /* _PDS_CORE_ADMINQ_H_ */ -- cgit v1.2.3 From 65e0185ad764d2801811bb2e7c122e92557208c4 Mon Sep 17 00:00:00 2001 From: Shannon Nelson Date: Wed, 19 Apr 2023 10:04:21 -0700 Subject: pds_core: set up the VIF definitions and defaults The Virtual Interfaces (VIFs) supported by the DSC's configuration (vDPA, Eth, RDMA, etc) are reported in the dev_ident struct and made visible in debugfs. At this point only vDPA is supported in this driver so we only setup devices for that feature. Signed-off-by: Shannon Nelson Acked-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/linux/pds/pds_common.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pds/pds_common.h b/include/linux/pds/pds_common.h index f0798ce01acf..b2be14ebadb6 100644 --- a/include/linux/pds/pds_common.h +++ b/include/linux/pds/pds_common.h @@ -20,6 +20,25 @@ enum pds_core_driver_type { PDS_DRIVER_ESXI = 6, }; +enum pds_core_vif_types { + PDS_DEV_TYPE_CORE = 0, + PDS_DEV_TYPE_VDPA = 1, + PDS_DEV_TYPE_VFIO = 2, + PDS_DEV_TYPE_ETH = 3, + PDS_DEV_TYPE_RDMA = 4, + PDS_DEV_TYPE_LM = 5, + + /* new ones added before this line */ + PDS_DEV_TYPE_MAX = 16 /* don't change - used in struct size */ +}; + +#define PDS_DEV_TYPE_CORE_STR "Core" +#define PDS_DEV_TYPE_VDPA_STR "vDPA" +#define PDS_DEV_TYPE_VFIO_STR "VFio" +#define PDS_DEV_TYPE_ETH_STR "Eth" +#define PDS_DEV_TYPE_RDMA_STR "RDMA" +#define PDS_DEV_TYPE_LM_STR "LM" + #define PDS_CORE_IFNAMSIZ 16 /** -- cgit v1.2.3 From 4569cce43bc61e4cdd76597a1cf9b608846c18cc Mon Sep 17 00:00:00 2001 From: Shannon Nelson Date: Wed, 19 Apr 2023 10:04:23 -0700 Subject: pds_core: add auxiliary_bus devices An auxiliary_bus device is created for each vDPA type VF at VF probe and destroyed at VF remove. The aux device name comes from the driver name + VIF type + the unique id assigned at PCI probe. The VFs are always removed on PF remove, so there should be no issues with VFs trying to access missing PF structures. The auxiliary_device names will look like "pds_core.vDPA.nn" where 'nn' is the VF's uid. Signed-off-by: Shannon Nelson Acked-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/linux/pds/pds_auxbus.h | 14 ++++++++++++++ include/linux/pds/pds_common.h | 1 + 2 files changed, 15 insertions(+) create mode 100644 include/linux/pds/pds_auxbus.h (limited to 'include/linux') diff --git a/include/linux/pds/pds_auxbus.h b/include/linux/pds/pds_auxbus.h new file mode 100644 index 000000000000..493f75b1995e --- /dev/null +++ b/include/linux/pds/pds_auxbus.h @@ -0,0 +1,14 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2023 Advanced Micro Devices, Inc */ + +#ifndef _PDSC_AUXBUS_H_ +#define _PDSC_AUXBUS_H_ + +#include + +struct pds_auxiliary_dev { + struct auxiliary_device aux_dev; + struct pci_dev *vf_pdev; + u16 client_id; +}; +#endif /* _PDSC_AUXBUS_H_ */ diff --git a/include/linux/pds/pds_common.h b/include/linux/pds/pds_common.h index b2be14ebadb6..961b3d02c69f 100644 --- a/include/linux/pds/pds_common.h +++ b/include/linux/pds/pds_common.h @@ -60,4 +60,5 @@ enum pds_core_logical_qtype { PDS_CORE_QTYPE_MAX = 16 /* don't change - used in struct size */ }; +void *pdsc_get_pf_struct(struct pci_dev *vf_pdev); #endif /* _PDS_COMMON_H_ */ -- cgit v1.2.3 From 10659034c622738bc1bfab8a76fc576c52d5acce Mon Sep 17 00:00:00 2001 From: Shannon Nelson Date: Wed, 19 Apr 2023 10:04:25 -0700 Subject: pds_core: add the aux client API Add the client API operations for running adminq commands. The core registers the client with the FW, then the client has a context for requesting adminq services. We expect to add additional operations for other clients, including requesting additional private adminqs and IRQs, but don't have the need yet. Signed-off-by: Shannon Nelson Acked-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/linux/pds/pds_auxbus.h | 6 ++++++ include/linux/pds/pds_common.h | 2 ++ 2 files changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pds/pds_auxbus.h b/include/linux/pds/pds_auxbus.h index 493f75b1995e..214ef12302d0 100644 --- a/include/linux/pds/pds_auxbus.h +++ b/include/linux/pds/pds_auxbus.h @@ -11,4 +11,10 @@ struct pds_auxiliary_dev { struct pci_dev *vf_pdev; u16 client_id; }; + +int pds_client_adminq_cmd(struct pds_auxiliary_dev *padev, + union pds_core_adminq_cmd *req, + size_t req_len, + union pds_core_adminq_comp *resp, + u64 flags); #endif /* _PDSC_AUXBUS_H_ */ diff --git a/include/linux/pds/pds_common.h b/include/linux/pds/pds_common.h index 961b3d02c69f..4b37675fde3e 100644 --- a/include/linux/pds/pds_common.h +++ b/include/linux/pds/pds_common.h @@ -61,4 +61,6 @@ enum pds_core_logical_qtype { }; void *pdsc_get_pf_struct(struct pci_dev *vf_pdev); +int pds_client_register(struct pci_dev *pf_pdev, char *devname); +int pds_client_unregister(struct pci_dev *pf_pdev, u16 client_id); #endif /* _PDS_COMMON_H_ */ -- cgit v1.2.3 From d24c28278a01dc4c80d1470533c667cf406f0e88 Mon Sep 17 00:00:00 2001 From: Shannon Nelson Date: Wed, 19 Apr 2023 10:04:26 -0700 Subject: pds_core: publish events to the clients When the Core device gets an event from the device, or notices the device FW to be up or down, it needs to send those events on to the clients that have an event handler. Add the code to pass along the events to the clients. The entry points pdsc_register_notify() and pdsc_unregister_notify() are EXPORTed for other drivers that want to listen for these events. Signed-off-by: Shannon Nelson Acked-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/linux/pds/pds_common.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pds/pds_common.h b/include/linux/pds/pds_common.h index 4b37675fde3e..060331486d50 100644 --- a/include/linux/pds/pds_common.h +++ b/include/linux/pds/pds_common.h @@ -60,6 +60,8 @@ enum pds_core_logical_qtype { PDS_CORE_QTYPE_MAX = 16 /* don't change - used in struct size */ }; +int pdsc_register_notify(struct notifier_block *nb); +void pdsc_unregister_notify(struct notifier_block *nb); void *pdsc_get_pf_struct(struct pci_dev *vf_pdev); int pds_client_register(struct pci_dev *pf_pdev, char *devname); int pds_client_unregister(struct pci_dev *pf_pdev, u16 client_id); -- cgit v1.2.3 From 223baf9d17f25e2608dbdff7232c095c1e612268 Mon Sep 17 00:00:00 2001 From: Mathieu Desnoyers Date: Thu, 20 Apr 2023 10:55:48 -0400 Subject: sched: Fix performance regression introduced by mm_cid Introduce per-mm/cpu current concurrency id (mm_cid) to fix a PostgreSQL sysbench regression reported by Aaron Lu. Keep track of the currently allocated mm_cid for each mm/cpu rather than freeing them immediately on context switch. This eliminates most atomic operations when context switching back and forth between threads belonging to different memory spaces in multi-threaded scenarios (many processes, each with many threads). The per-mm/per-cpu mm_cid values are serialized by their respective runqueue locks. Thread migration is handled by introducing invocation to sched_mm_cid_migrate_to() (with destination runqueue lock held) in activate_task() for migrating tasks. If the destination cpu's mm_cid is unset, and if the source runqueue is not actively using its mm_cid, then the source cpu's mm_cid is moved to the destination cpu on migration. Introduce a task-work executed periodically, similarly to NUMA work, which delays reclaim of cid values when they are unused for a period of time. Keep track of the allocation time for each per-cpu cid, and let the task work clear them when they are observed to be older than SCHED_MM_CID_PERIOD_NS and unused. This task work also clears all mm_cids which are greater or equal to the Hamming weight of the mm cidmask to keep concurrency ids compact. Because we want to ensure the mm_cid converges towards the smaller values as migrations happen, the prior optimization that was done when context switching between threads belonging to the same mm is removed, because it could delay the lazy release of the destination runqueue mm_cid after it has been replaced by a migration. Removing this prior optimization is not an issue performance-wise because the introduced per-mm/per-cpu mm_cid tracking also covers this more specific case. Fixes: af7f588d8f73 ("sched: Introduce per-memory-map concurrency ID") Reported-by: Aaron Lu Signed-off-by: Mathieu Desnoyers Signed-off-by: Peter Zijlstra (Intel) Tested-by: Aaron Lu Link: https://lore.kernel.org/lkml/20230327080502.GA570847@ziqianlu-desk2/ --- include/linux/mm_types.h | 82 +++++++++++++++++++++++++++++++++++++++++++----- include/linux/sched.h | 3 ++ include/linux/sched/mm.h | 5 +++ 3 files changed, 82 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index a57e6ae78e65..5eab61156f0e 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -550,6 +550,13 @@ struct vm_area_struct { struct vm_userfaultfd_ctx vm_userfaultfd_ctx; } __randomize_layout; +#ifdef CONFIG_SCHED_MM_CID +struct mm_cid { + u64 time; + int cid; +}; +#endif + struct kioctx_table; struct mm_struct { struct { @@ -600,15 +607,19 @@ struct mm_struct { atomic_t mm_count; #ifdef CONFIG_SCHED_MM_CID /** - * @cid_lock: Protect cid bitmap updates vs lookups. + * @pcpu_cid: Per-cpu current cid. * - * Prevent situations where updates to the cid bitmap happen - * concurrently with lookups. Those can lead to situations - * where a lookup cannot find a free bit simply because it was - * unlucky enough to load, non-atomically, bitmap words as they - * were being concurrently updated by the updaters. + * Keep track of the currently allocated mm_cid for each cpu. + * The per-cpu mm_cid values are serialized by their respective + * runqueue locks. */ - raw_spinlock_t cid_lock; + struct mm_cid __percpu *pcpu_cid; + /* + * @mm_cid_next_scan: Next mm_cid scan (in jiffies). + * + * When the next mm_cid scan is due (in jiffies). + */ + unsigned long mm_cid_next_scan; #endif #ifdef CONFIG_MMU atomic_long_t pgtables_bytes; /* size of all page tables */ @@ -873,6 +884,37 @@ static inline void vma_iter_init(struct vma_iterator *vmi, } #ifdef CONFIG_SCHED_MM_CID + +enum mm_cid_state { + MM_CID_UNSET = -1U, /* Unset state has lazy_put flag set. */ + MM_CID_LAZY_PUT = (1U << 31), +}; + +static inline bool mm_cid_is_unset(int cid) +{ + return cid == MM_CID_UNSET; +} + +static inline bool mm_cid_is_lazy_put(int cid) +{ + return !mm_cid_is_unset(cid) && (cid & MM_CID_LAZY_PUT); +} + +static inline bool mm_cid_is_valid(int cid) +{ + return !(cid & MM_CID_LAZY_PUT); +} + +static inline int mm_cid_set_lazy_put(int cid) +{ + return cid | MM_CID_LAZY_PUT; +} + +static inline int mm_cid_clear_lazy_put(int cid) +{ + return cid & ~MM_CID_LAZY_PUT; +} + /* Accessor for struct mm_struct's cidmask. */ static inline cpumask_t *mm_cidmask(struct mm_struct *mm) { @@ -886,16 +928,40 @@ static inline cpumask_t *mm_cidmask(struct mm_struct *mm) static inline void mm_init_cid(struct mm_struct *mm) { - raw_spin_lock_init(&mm->cid_lock); + int i; + + for_each_possible_cpu(i) { + struct mm_cid *pcpu_cid = per_cpu_ptr(mm->pcpu_cid, i); + + pcpu_cid->cid = MM_CID_UNSET; + pcpu_cid->time = 0; + } cpumask_clear(mm_cidmask(mm)); } +static inline int mm_alloc_cid(struct mm_struct *mm) +{ + mm->pcpu_cid = alloc_percpu(struct mm_cid); + if (!mm->pcpu_cid) + return -ENOMEM; + mm_init_cid(mm); + return 0; +} + +static inline void mm_destroy_cid(struct mm_struct *mm) +{ + free_percpu(mm->pcpu_cid); + mm->pcpu_cid = NULL; +} + static inline unsigned int mm_cid_size(void) { return cpumask_size(); } #else /* CONFIG_SCHED_MM_CID */ static inline void mm_init_cid(struct mm_struct *mm) { } +static inline int mm_alloc_cid(struct mm_struct *mm) { return 0; } +static inline void mm_destroy_cid(struct mm_struct *mm) { } static inline unsigned int mm_cid_size(void) { return 0; diff --git a/include/linux/sched.h b/include/linux/sched.h index 6d654eb4cabd..675298d6eb36 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1314,7 +1314,10 @@ struct task_struct { #ifdef CONFIG_SCHED_MM_CID int mm_cid; /* Current cid in mm */ + int last_mm_cid; /* Most recent cid in mm */ + int migrate_from_cpu; int mm_cid_active; /* Whether cid bitmap is active */ + struct callback_head cid_work; #endif struct tlbflush_unmap_batch tlb_ubc; diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index 2a243616f222..f20fc0600fcc 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -37,6 +37,11 @@ static inline void mmgrab(struct mm_struct *mm) atomic_inc(&mm->mm_count); } +static inline void smp_mb__after_mmgrab(void) +{ + smp_mb__after_atomic(); +} + extern void __mmdrop(struct mm_struct *mm); static inline void mmdrop(struct mm_struct *mm) -- cgit v1.2.3 From f7abf14f0001a5a47539d9f60bbdca649e43536b Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 17 Apr 2023 15:37:55 +0200 Subject: posix-cpu-timers: Implement the missing timer_wait_running callback For some unknown reason the introduction of the timer_wait_running callback missed to fixup posix CPU timers, which went unnoticed for almost four years. Marco reported recently that the WARN_ON() in timer_wait_running() triggers with a posix CPU timer test case. Posix CPU timers have two execution models for expiring timers depending on CONFIG_POSIX_CPU_TIMERS_TASK_WORK: 1) If not enabled, the expiry happens in hard interrupt context so spin waiting on the remote CPU is reasonably time bound. Implement an empty stub function for that case. 2) If enabled, the expiry happens in task work before returning to user space or guest mode. The expired timers are marked as firing and moved from the timer queue to a local list head with sighand lock held. Once the timers are moved, sighand lock is dropped and the expiry happens in fully preemptible context. That means the expiring task can be scheduled out, migrated, interrupted etc. So spin waiting on it is more than suboptimal. The timer wheel has a timer_wait_running() mechanism for RT, which uses a per CPU timer-base expiry lock which is held by the expiry code and the task waiting for the timer function to complete blocks on that lock. This does not work in the same way for posix CPU timers as there is no timer base and expiry for process wide timers can run on any task belonging to that process, but the concept of waiting on an expiry lock can be used too in a slightly different way: - Add a mutex to struct posix_cputimers_work. This struct is per task and used to schedule the expiry task work from the timer interrupt. - Add a task_struct pointer to struct cpu_timer which is used to store a the task which runs the expiry. That's filled in when the task moves the expired timers to the local expiry list. That's not affecting the size of the k_itimer union as there are bigger union members already - Let the task take the expiry mutex around the expiry function - Let the waiter acquire a task reference with rcu_read_lock() held and block on the expiry mutex This avoids spin-waiting on a task which might not even be on a CPU and works nicely for RT too. Fixes: ec8f954a40da ("posix-timers: Use a callback for cancel synchronization on PREEMPT_RT") Reported-by: Marco Elver Signed-off-by: Thomas Gleixner Tested-by: Marco Elver Tested-by: Sebastian Andrzej Siewior Reviewed-by: Frederic Weisbecker Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/87zg764ojw.ffs@tglx --- include/linux/posix-timers.h | 17 +++++++++++------ 1 file changed, 11 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h index 2c6e99ca48af..d607f51404fc 100644 --- a/include/linux/posix-timers.h +++ b/include/linux/posix-timers.h @@ -4,6 +4,7 @@ #include #include +#include #include #include @@ -62,16 +63,18 @@ static inline int clockid_to_fd(const clockid_t clk) * cpu_timer - Posix CPU timer representation for k_itimer * @node: timerqueue node to queue in the task/sig * @head: timerqueue head on which this timer is queued - * @task: Pointer to target task + * @pid: Pointer to target task PID * @elist: List head for the expiry list * @firing: Timer is currently firing + * @handling: Pointer to the task which handles expiry */ struct cpu_timer { - struct timerqueue_node node; - struct timerqueue_head *head; - struct pid *pid; - struct list_head elist; - int firing; + struct timerqueue_node node; + struct timerqueue_head *head; + struct pid *pid; + struct list_head elist; + int firing; + struct task_struct __rcu *handling; }; static inline bool cpu_timer_enqueue(struct timerqueue_head *head, @@ -135,10 +138,12 @@ struct posix_cputimers { /** * posix_cputimers_work - Container for task work based posix CPU timer expiry * @work: The task work to be scheduled + * @mutex: Mutex held around expiry in context of this task work * @scheduled: @work has been scheduled already, no further processing */ struct posix_cputimers_work { struct callback_head work; + struct mutex mutex; unsigned int scheduled; }; -- cgit v1.2.3 From 67a142dc9eb96a5cc018e5db62390665eb5f038c Mon Sep 17 00:00:00 2001 From: Krishna Yarlagadda Date: Fri, 21 Apr 2023 14:43:07 +0530 Subject: spi: Add TPM HW flow flag TPM specification [1] defines flow control over SPI. Client device can insert a wait state on MISO when address is transmitted by controller on MOSI. Detecting the wait state in software is only possible for full duplex controllers. For controllers that support only half- duplex, the wait state detection needs to be implemented in hardware. Add a flag SPI_TPM_HW_FLOW for TPM device to set when software flow control is not possible and hardware flow control is expected from SPI controller. Reference: [1] https://trustedcomputinggroup.org/resource/pc-client-platform-tpm -profile-ptp-specification/ Signed-off-by: Krishna Yarlagadda Reviewed-by: Jerry Snitselaar Link: https://lore.kernel.org/r/20230421091309.2672-2-kyarlagadda@nvidia.com Signed-off-by: Mark Brown --- include/linux/spi/spi.h | 16 +++++++++++++--- 1 file changed, 13 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 873ced6ae4ca..cfe42f8cd7a4 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -184,8 +184,18 @@ struct spi_device { u8 chip_select; u8 bits_per_word; bool rt; -#define SPI_NO_TX BIT(31) /* No transmit wire */ -#define SPI_NO_RX BIT(30) /* No receive wire */ +#define SPI_NO_TX BIT(31) /* No transmit wire */ +#define SPI_NO_RX BIT(30) /* No receive wire */ + /* + * TPM specification defines flow control over SPI. Client device + * can insert a wait state on MISO when address is transmitted by + * controller on MOSI. Detecting the wait state in software is only + * possible for full duplex controllers. For controllers that support + * only half-duplex, the wait state detection needs to be implemented + * in hardware. TPM devices would set this flag when hardware flow + * control is expected from SPI controller. + */ +#define SPI_TPM_HW_FLOW BIT(29) /* TPM HW flow control */ /* * All bits defined above should be covered by SPI_MODE_KERNEL_MASK. * The SPI_MODE_KERNEL_MASK has the SPI_MODE_USER_MASK counterpart, @@ -195,7 +205,7 @@ struct spi_device { * These bits must not overlap. A static assert check should make sure of that. * If adding extra bits, make sure to decrease the bit index below as well. */ -#define SPI_MODE_KERNEL_MASK (~(BIT(30) - 1)) +#define SPI_MODE_KERNEL_MASK (~(BIT(29) - 1)) u32 mode; int irq; void *controller_state; -- cgit v1.2.3 From f6c73a11133ef991284311387ca707b48bf53912 Mon Sep 17 00:00:00 2001 From: "Ritesh Harjani (IBM)" Date: Fri, 21 Apr 2023 08:52:42 -0700 Subject: fs.h: Add TRACE_IOCB_STRINGS for use in trace points Add TRACE_IOCB_STRINGS macro which can be used in the trace point patch to print different flag values with meaningful string output. Tested-by: Disha Goel Reviewed-by: Christoph Hellwig Signed-off-by: Ritesh Harjani (IBM) Reviewed-by: Darrick J. Wong [djwong: line up strings all prettylike] Signed-off-by: Darrick J. Wong --- include/linux/fs.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index c85916e9f7db..75d24fa082e5 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -340,6 +340,20 @@ enum rw_hint { /* can use bio alloc cache */ #define IOCB_ALLOC_CACHE (1 << 21) +/* for use in trace events */ +#define TRACE_IOCB_STRINGS \ + { IOCB_HIPRI, "HIPRI" }, \ + { IOCB_DSYNC, "DSYNC" }, \ + { IOCB_SYNC, "SYNC" }, \ + { IOCB_NOWAIT, "NOWAIT" }, \ + { IOCB_APPEND, "APPEND" }, \ + { IOCB_EVENTFD, "EVENTFD"}, \ + { IOCB_DIRECT, "DIRECT" }, \ + { IOCB_WRITE, "WRITE" }, \ + { IOCB_WAITQ, "WAITQ" }, \ + { IOCB_NOIO, "NOIO" }, \ + { IOCB_ALLOC_CACHE, "ALLOC_CACHE" } + struct kiocb { struct file *ki_filp; loff_t ki_pos; -- cgit v1.2.3 From d3bff1fc50d4fcaccddbd63917dd94172e80c40e Mon Sep 17 00:00:00 2001 From: "Ritesh Harjani (IBM)" Date: Fri, 21 Apr 2023 08:52:43 -0700 Subject: iomap: Remove IOMAP_DIO_NOSYNC unused dio flag IOMAP_DIO_NOSYNC earlier was added for use in btrfs. But it seems for aio dsync writes this is not useful anyway. For aio dsync case, we we queue the request and return -EIOCBQUEUED. Now, since IOMAP_DIO_NOSYNC doesn't let iomap_dio_complete() to call generic_write_sync(), hence we may lose the sync write. Hence kill this flag as it is not in use by any FS now. Tested-by: Disha Goel Reviewed-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Signed-off-by: Ritesh Harjani (IBM) Signed-off-by: Darrick J. Wong --- include/linux/iomap.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 0f8123504e5e..e2b836c2e119 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -377,12 +377,6 @@ struct iomap_dio_ops { */ #define IOMAP_DIO_PARTIAL (1 << 2) -/* - * The caller will sync the write if needed; do not sync it within - * iomap_dio_rw. Overrides IOMAP_DIO_FORCE_WAIT. - */ -#define IOMAP_DIO_NOSYNC (1 << 3) - ssize_t iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, const struct iomap_ops *ops, const struct iomap_dio_ops *dops, unsigned int dio_flags, void *private, size_t done_before); -- cgit v1.2.3 From 84601d6ee68ae820dec97450934797046d62db4b Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Fri, 21 Apr 2023 19:02:54 +0200 Subject: bpf: add bpf_link support for BPF_NETFILTER programs Add bpf_link support skeleton. To keep this reviewable, no bpf program can be invoked yet, if a program is attached only a c-stub is called and not the actual bpf program. Defaults to 'y' if both netfilter and bpf syscall are enabled in kconfig. Uapi example usage: union bpf_attr attr = { }; attr.link_create.prog_fd = progfd; attr.link_create.attach_type = 0; /* unused */ attr.link_create.netfilter.pf = PF_INET; attr.link_create.netfilter.hooknum = NF_INET_LOCAL_IN; attr.link_create.netfilter.priority = -128; err = bpf(BPF_LINK_CREATE, &attr, sizeof(attr)); ... this would attach progfd to ipv4:input hook. Such hook gets removed automatically if the calling program exits. BPF_NETFILTER program invocation is added in followup change. NF_HOOK_OP_BPF enum will eventually be read from nfnetlink_hook, it allows to tell userspace which program is attached at the given hook when user runs 'nft hook list' command rather than just the priority and not-very-helpful 'this hook runs a bpf prog but I can't tell which one'. Will also be used to disallow registration of two bpf programs with same priority in a followup patch. v4: arm32 cmpxchg only supports 32bit operand s/prio/priority/ v3: restrict prog attachment to ip/ip6 for now, lets lift restrictions if more use cases pop up (arptables, ebtables, netdev ingress/egress etc). Signed-off-by: Florian Westphal Link: https://lore.kernel.org/r/20230421170300.24115-2-fw@strlen.de Signed-off-by: Alexei Starovoitov --- include/linux/netfilter.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index c8e03bcaecaa..0762444e3767 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -80,6 +80,7 @@ typedef unsigned int nf_hookfn(void *priv, enum nf_hook_ops_type { NF_HOOK_OP_UNDEFINED, NF_HOOK_OP_NF_TABLES, + NF_HOOK_OP_BPF, }; struct nf_hook_ops { -- cgit v1.2.3 From fd9c663b9ad67dedfc9a3fd3429ddd3e83782b4d Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Fri, 21 Apr 2023 19:02:55 +0200 Subject: bpf: minimal support for programs hooked into netfilter framework This adds minimal support for BPF_PROG_TYPE_NETFILTER bpf programs that will be invoked via the NF_HOOK() points in the ip stack. Invocation incurs an indirect call. This is not a necessity: Its possible to add 'DEFINE_BPF_DISPATCHER(nf_progs)' and handle the program invocation with the same method already done for xdp progs. This isn't done here to keep the size of this chunk down. Verifier restricts verdicts to either DROP or ACCEPT. Signed-off-by: Florian Westphal Link: https://lore.kernel.org/r/20230421170300.24115-3-fw@strlen.de Signed-off-by: Alexei Starovoitov --- include/linux/bpf_types.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index d4ee3ccd3753..39a999abb0ce 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -79,6 +79,10 @@ BPF_PROG_TYPE(BPF_PROG_TYPE_LSM, lsm, #endif BPF_PROG_TYPE(BPF_PROG_TYPE_SYSCALL, bpf_syscall, void *, void *) +#ifdef CONFIG_NETFILTER +BPF_PROG_TYPE(BPF_PROG_TYPE_NETFILTER, netfilter, + struct bpf_nf_ctx, struct bpf_nf_ctx) +#endif BPF_MAP_TYPE(BPF_MAP_TYPE_ARRAY, array_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_PERCPU_ARRAY, percpu_array_map_ops) -- cgit v1.2.3 From 2b99ef22e0d237e08bfc437e7d051f78f352aeb2 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Fri, 21 Apr 2023 19:02:59 +0200 Subject: bpf: add test_run support for netfilter program type add glue code so a bpf program can be run using userspace-provided netfilter state and packet/skb. Default is to use ipv4:output hook point, but this can be overridden by userspace. Userspace provided netfilter state is restricted, only hook and protocol families can be overridden and only to ipv4/ipv6. Signed-off-by: Florian Westphal Link: https://lore.kernel.org/r/20230421170300.24115-7-fw@strlen.de Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 18b592fde896..e53ceee1df37 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -2264,6 +2264,9 @@ int bpf_prog_test_run_raw_tp(struct bpf_prog *prog, int bpf_prog_test_run_sk_lookup(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); +int bpf_prog_test_run_nf(struct bpf_prog *prog, + const union bpf_attr *kattr, + union bpf_attr __user *uattr); bool btf_ctx_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info); -- cgit v1.2.3 From 465e5e6a1698f3325f5d2262d2875779b06b50c7 Mon Sep 17 00:00:00 2001 From: Pankaj Raghav Date: Mon, 17 Apr 2023 14:36:15 +0200 Subject: fs/buffer: add folio_set_bh helper Patch series "convert create_page_buffers to folio_create_buffers". One of the first kernel panic we hit when we try to increase the block size > 4k is inside create_page_buffers()[1]. Even though buffer.c function do not support large folios (folios > PAGE_SIZE) at the moment, these changes are required when we want to remove that constraint. This patch (of 4): The folio version of set_bh_page(). This is required to convert create_page_buffers() to folio_create_buffers() later in the series. Link: https://lkml.kernel.org/r/20230417123618.22094-1-p.raghav@samsung.com Link: https://lkml.kernel.org/r/20230417123618.22094-2-p.raghav@samsung.com Signed-off-by: Pankaj Raghav Reviewed-by: Matthew Wilcox (Oracle) Reviewed-by: Hannes Reinecke Cc: Alexander Viro Cc: Christian Brauner Cc: Luis Chamberlain Signed-off-by: Andrew Morton --- include/linux/buffer_head.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 8f14dca5fed7..7e92d23f4782 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -196,6 +196,8 @@ void mark_buffer_write_io_error(struct buffer_head *bh); void touch_buffer(struct buffer_head *bh); void set_bh_page(struct buffer_head *bh, struct page *page, unsigned long offset); +void folio_set_bh(struct buffer_head *bh, struct folio *folio, + unsigned long offset); bool try_to_free_buffers(struct folio *); struct buffer_head *alloc_page_buffers(struct page *page, unsigned long size, bool retry); -- cgit v1.2.3 From c71124a8afa441af203d2001a92c91f114446687 Mon Sep 17 00:00:00 2001 From: Pankaj Raghav Date: Mon, 17 Apr 2023 14:36:16 +0200 Subject: buffer: add folio_alloc_buffers() helper Folio version of alloc_page_buffers() helper. This is required to convert create_page_buffers() to folio_create_buffers() later in the series. alloc_page_buffers() has been modified to call folio_alloc_buffers() which adds one call to compound_head() but folio_alloc_buffers() removes one call to compound_head() compared to the existing alloc_page_buffers() implementation. Link: https://lkml.kernel.org/r/20230417123618.22094-3-p.raghav@samsung.com Signed-off-by: Pankaj Raghav Reviewed-by: Matthew Wilcox (Oracle) Reviewed-by: Hannes Reinecke Cc: Alexander Viro Cc: Christian Brauner Cc: Luis Chamberlain Signed-off-by: Andrew Morton --- include/linux/buffer_head.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 7e92d23f4782..0b14eab41bd1 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -199,6 +199,8 @@ void set_bh_page(struct buffer_head *bh, void folio_set_bh(struct buffer_head *bh, struct folio *folio, unsigned long offset); bool try_to_free_buffers(struct folio *); +struct buffer_head *folio_alloc_buffers(struct folio *folio, unsigned long size, + bool retry); struct buffer_head *alloc_page_buffers(struct page *page, unsigned long size, bool retry); void create_empty_buffers(struct page *, unsigned long, -- cgit v1.2.3 From 8e2e17560bed73c2a73c94cbe378719f6cf850ee Mon Sep 17 00:00:00 2001 From: Pankaj Raghav Date: Mon, 17 Apr 2023 14:36:17 +0200 Subject: fs/buffer: add folio_create_empty_buffers helper Folio version of create_empty_buffers(). This is required to convert create_page_buffers() to folio_create_buffers() later in the series. It removes several calls to compound_head() as it works directly on folio compared to create_empty_buffers(). Hence, create_empty_buffers() has been modified to call folio_create_empty_buffers(). Link: https://lkml.kernel.org/r/20230417123618.22094-4-p.raghav@samsung.com Signed-off-by: Pankaj Raghav Reviewed-by: Matthew Wilcox (Oracle) Reviewed-by: Hannes Reinecke Cc: Alexander Viro Cc: Christian Brauner Cc: Luis Chamberlain Signed-off-by: Andrew Morton --- include/linux/buffer_head.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 0b14eab41bd1..1520793c72da 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -205,6 +205,8 @@ struct buffer_head *alloc_page_buffers(struct page *page, unsigned long size, bool retry); void create_empty_buffers(struct page *, unsigned long, unsigned long b_state); +void folio_create_empty_buffers(struct folio *folio, unsigned long blocksize, + unsigned long b_state); void end_buffer_read_sync(struct buffer_head *bh, int uptodate); void end_buffer_write_sync(struct buffer_head *bh, int uptodate); void end_buffer_async_write(struct buffer_head *bh, int uptodate); -- cgit v1.2.3 From 4bf4f155bfbc77a12ad2c9e12d9f57718adb9a5c Mon Sep 17 00:00:00 2001 From: Kefeng Wang Date: Mon, 17 Apr 2023 19:48:07 +0800 Subject: mm: correct arg in reclaim_pages()/reclaim_clean_pages_from_list() Both of them change the arg from page_list to folio_list when convert them to use a folio, but not the declaration, let's correct it, also move the reclaim_pages() from swap.h to internal.h as it only used in mm. Link: https://lkml.kernel.org/r/20230417114807.186786-1-wangkefeng.wang@huawei.com Signed-off-by: Kefeng Wang Reviwed-by: Matthew Wilcox (Oracle) Reviewed-by: SeongJae Park Reviewed-by: David Hildenbrand Cc: Hugh Dickins Signed-off-by: Andrew Morton --- include/linux/swap.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index 7f7d5b9ddf7e..3c69cb653cb9 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -442,7 +442,6 @@ extern unsigned long shrink_all_memory(unsigned long nr_pages); extern int vm_swappiness; long remove_mapping(struct address_space *mapping, struct folio *folio); -extern unsigned long reclaim_pages(struct list_head *page_list); #ifdef CONFIG_NUMA extern int node_reclaim_mode; extern int sysctl_min_unmapped_ratio; -- cgit v1.2.3 From d7597f59d1d33e9efbffa7060deb9ee5bd119e62 Mon Sep 17 00:00:00 2001 From: Stefan Roesch Date: Mon, 17 Apr 2023 22:13:40 -0700 Subject: mm: add new api to enable ksm per process Patch series "mm: process/cgroup ksm support", v9. So far KSM can only be enabled by calling madvise for memory regions. To be able to use KSM for more workloads, KSM needs to have the ability to be enabled / disabled at the process / cgroup level. Use case 1: The madvise call is not available in the programming language. An example for this are programs with forked workloads using a garbage collected language without pointers. In such a language madvise cannot be made available. In addition the addresses of objects get moved around as they are garbage collected. KSM sharing needs to be enabled "from the outside" for these type of workloads. Use case 2: The same interpreter can also be used for workloads where KSM brings no benefit or even has overhead. We'd like to be able to enable KSM on a workload by workload basis. Use case 3: With the madvise call sharing opportunities are only enabled for the current process: it is a workload-local decision. A considerable number of sharing opportunities may exist across multiple workloads or jobs (if they are part of the same security domain). Only a higler level entity like a job scheduler or container can know for certain if its running one or more instances of a job. That job scheduler however doesn't have the necessary internal workload knowledge to make targeted madvise calls. Security concerns: In previous discussions security concerns have been brought up. The problem is that an individual workload does not have the knowledge about what else is running on a machine. Therefore it has to be very conservative in what memory areas can be shared or not. However, if the system is dedicated to running multiple jobs within the same security domain, its the job scheduler that has the knowledge that sharing can be safely enabled and is even desirable. Performance: Experiments with using UKSM have shown a capacity increase of around 20%. Here are the metrics from an instagram workload (taken from a machine with 64GB main memory): full_scans: 445 general_profit: 20158298048 max_page_sharing: 256 merge_across_nodes: 1 pages_shared: 129547 pages_sharing: 5119146 pages_to_scan: 4000 pages_unshared: 1760924 pages_volatile: 10761341 run: 1 sleep_millisecs: 20 stable_node_chains: 167 stable_node_chains_prune_millisecs: 2000 stable_node_dups: 2751 use_zero_pages: 0 zero_pages_sharing: 0 After the service is running for 30 minutes to an hour, 4 to 5 million shared pages are common for this workload when using KSM. Detailed changes: 1. New options for prctl system command This patch series adds two new options to the prctl system call. The first one allows to enable KSM at the process level and the second one to query the setting. The setting will be inherited by child processes. With the above setting, KSM can be enabled for the seed process of a cgroup and all processes in the cgroup will inherit the setting. 2. Changes to KSM processing When KSM is enabled at the process level, the KSM code will iterate over all the VMA's and enable KSM for the eligible VMA's. When forking a process that has KSM enabled, the setting will be inherited by the new child process. 3. Add general_profit metric The general_profit metric of KSM is specified in the documentation, but not calculated. This adds the general profit metric to /sys/kernel/debug/mm/ksm. 4. Add more metrics to ksm_stat This adds the process profit metric to /proc//ksm_stat. 5. Add more tests to ksm_tests and ksm_functional_tests This adds an option to specify the merge type to the ksm_tests. This allows to test madvise and prctl KSM. It also adds a two new tests to ksm_functional_tests: one to test the new prctl options and the other one is a fork test to verify that the KSM process setting is inherited by client processes. This patch (of 3): So far KSM can only be enabled by calling madvise for memory regions. To be able to use KSM for more workloads, KSM needs to have the ability to be enabled / disabled at the process / cgroup level. 1. New options for prctl system command This patch series adds two new options to the prctl system call. The first one allows to enable KSM at the process level and the second one to query the setting. The setting will be inherited by child processes. With the above setting, KSM can be enabled for the seed process of a cgroup and all processes in the cgroup will inherit the setting. 2. Changes to KSM processing When KSM is enabled at the process level, the KSM code will iterate over all the VMA's and enable KSM for the eligible VMA's. When forking a process that has KSM enabled, the setting will be inherited by the new child process. 1) Introduce new MMF_VM_MERGE_ANY flag This introduces the new flag MMF_VM_MERGE_ANY flag. When this flag is set, kernel samepage merging (ksm) gets enabled for all vma's of a process. 2) Setting VM_MERGEABLE on VMA creation When a VMA is created, if the MMF_VM_MERGE_ANY flag is set, the VM_MERGEABLE flag will be set for this VMA. 3) support disabling of ksm for a process This adds the ability to disable ksm for a process if ksm has been enabled for the process with prctl. 4) add new prctl option to get and set ksm for a process This adds two new options to the prctl system call - enable ksm for all vmas of a process (if the vmas support it). - query if ksm has been enabled for a process. 3. Disabling MMF_VM_MERGE_ANY for storage keys in s390 In the s390 architecture when storage keys are used, the MMF_VM_MERGE_ANY will be disabled. Link: https://lkml.kernel.org/r/20230418051342.1919757-1-shr@devkernel.io Link: https://lkml.kernel.org/r/20230418051342.1919757-2-shr@devkernel.io Signed-off-by: Stefan Roesch Acked-by: David Hildenbrand Cc: David Hildenbrand Cc: Johannes Weiner Cc: Michal Hocko Cc: Rik van Riel Cc: Bagas Sanjaya Signed-off-by: Andrew Morton --- include/linux/ksm.h | 21 +++++++++++++++++++-- include/linux/sched/coredump.h | 1 + 2 files changed, 20 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ksm.h b/include/linux/ksm.h index d9e701326a88..4647b0c70c12 100644 --- a/include/linux/ksm.h +++ b/include/linux/ksm.h @@ -18,13 +18,26 @@ #ifdef CONFIG_KSM int ksm_madvise(struct vm_area_struct *vma, unsigned long start, unsigned long end, int advice, unsigned long *vm_flags); + +void ksm_add_vma(struct vm_area_struct *vma); +int ksm_enable_merge_any(struct mm_struct *mm); + int __ksm_enter(struct mm_struct *mm); void __ksm_exit(struct mm_struct *mm); static inline int ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm) { - if (test_bit(MMF_VM_MERGEABLE, &oldmm->flags)) - return __ksm_enter(mm); + int ret; + + if (test_bit(MMF_VM_MERGEABLE, &oldmm->flags)) { + ret = __ksm_enter(mm); + if (ret) + return ret; + } + + if (test_bit(MMF_VM_MERGE_ANY, &oldmm->flags)) + set_bit(MMF_VM_MERGE_ANY, &mm->flags); + return 0; } @@ -57,6 +70,10 @@ void collect_procs_ksm(struct page *page, struct list_head *to_kill, #endif #else /* !CONFIG_KSM */ +static inline void ksm_add_vma(struct vm_area_struct *vma) +{ +} + static inline int ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm) { return 0; diff --git a/include/linux/sched/coredump.h b/include/linux/sched/coredump.h index 0e17ae7fbfd3..0ee96ea7a0e9 100644 --- a/include/linux/sched/coredump.h +++ b/include/linux/sched/coredump.h @@ -90,4 +90,5 @@ static inline int get_dumpable(struct mm_struct *mm) #define MMF_INIT_MASK (MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK |\ MMF_DISABLE_THP_MASK | MMF_HAS_MDWE_MASK) +#define MMF_VM_MERGE_ANY 29 #endif /* _LINUX_SCHED_COREDUMP_H */ -- cgit v1.2.3 From d21077fbc2fc987c2e593c34dc3b4d84e546dc9f Mon Sep 17 00:00:00 2001 From: Stefan Roesch Date: Mon, 17 Apr 2023 22:13:41 -0700 Subject: mm: add new KSM process and sysfs knobs This adds the general_profit KSM sysfs knob and the process profit metric knobs to ksm_stat. 1) expose general_profit metric The documentation mentions a general profit metric, however this metric is not calculated. In addition the formula depends on the size of internal structures, which makes it more difficult for an administrator to make the calculation. Adding the metric for a better user experience. 2) document general_profit sysfs knob 3) calculate ksm process profit metric The ksm documentation mentions the process profit metric and how to calculate it. This adds the calculation of the metric. 4) mm: expose ksm process profit metric in ksm_stat This exposes the ksm process profit metric in /proc//ksm_stat. The documentation mentions the formula for the ksm process profit metric, however it does not calculate it. In addition the formula depends on the size of internal structures. So it makes sense to expose it. 5) document new procfs ksm knobs Link: https://lkml.kernel.org/r/20230418051342.1919757-3-shr@devkernel.io Signed-off-by: Stefan Roesch Reviewed-by: Bagas Sanjaya Acked-by: David Hildenbrand Cc: David Hildenbrand Cc: Johannes Weiner Cc: Michal Hocko Cc: Rik van Riel Signed-off-by: Andrew Morton --- include/linux/ksm.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ksm.h b/include/linux/ksm.h index 4647b0c70c12..7a9b76fb6c3f 100644 --- a/include/linux/ksm.h +++ b/include/linux/ksm.h @@ -68,6 +68,11 @@ void folio_migrate_ksm(struct folio *newfolio, struct folio *folio); void collect_procs_ksm(struct page *page, struct list_head *to_kill, int force_early); #endif + +#ifdef CONFIG_PROC_FS +long ksm_process_profit(struct mm_struct *); +#endif /* CONFIG_PROC_FS */ + #else /* !CONFIG_KSM */ static inline void ksm_add_vma(struct vm_area_struct *vma) -- cgit v1.2.3 From f724392415b3e1ae844d2766669c0d955fe9a17b Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Tue, 18 Apr 2023 22:22:02 -0700 Subject: hugetlb: pte_alloc_huge() to replace huge pte_alloc_map() Some architectures can have their hugetlb pages down at the lowest PTE level: their huge_pte_alloc() using pte_alloc_map(), but without any following pte_unmap(). Since none of these arches uses CONFIG_HIGHPTE, this is not seen as a problem at present; but would become a problem if forthcoming changes were to add an rcu_read_lock() into pte_offset_map(), with the rcu_read_unlock() expected in pte_unmap(). Similarly in their huge_pte_offset(): pte_offset_kernel() is good enough for that, but it's probably less confusing if we define pte_offset_huge() along with pte_alloc_huge(). Only define them without CONFIG_HIGHPTE: so there would be a build error to signal if ever more work is needed. For ease of development, define these now for 6.4-rc1, ahead of any use: then architectures can integrate patches using them, independent from mm. Link: https://lkml.kernel.org/r/ae9e7d98-8a3a-cfd9-4762-bcddffdf96cf@google.com Signed-off-by: Hugh Dickins Reviewed-by: Mike Kravetz Cc: Muchun Song Signed-off-by: Andrew Morton --- include/linux/hugetlb.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 28703fe22386..cbe1e97a15a1 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -191,6 +191,23 @@ extern struct list_head huge_boot_pages; /* arch callbacks */ +#ifndef CONFIG_HIGHPTE +/* + * pte_offset_huge() and pte_alloc_huge() are helpers for those architectures + * which may go down to the lowest PTE level in their huge_pte_offset() and + * huge_pte_alloc(): to avoid reliance on pte_offset_map() without pte_unmap(). + */ +static inline pte_t *pte_offset_huge(pmd_t *pmd, unsigned long address) +{ + return pte_offset_kernel(pmd, address); +} +static inline pte_t *pte_alloc_huge(struct mm_struct *mm, pmd_t *pmd, + unsigned long address) +{ + return pte_alloc(mm, pmd) ? NULL : pte_offset_huge(pmd, address); +} +#endif + pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, unsigned long sz); /* -- cgit v1.2.3 From 9a32e9850686599ed194ccdceb6cd3dd56b2d9b9 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 13 Apr 2023 17:13:19 +0200 Subject: netfilter: nf_tables: don't write table validation state without mutex The ->cleanup callback needs to be removed, this doesn't work anymore as the transaction mutex is already released in the ->abort function. Just do it after a successful validation pass, this either happens from commit or abort phases where transaction mutex is held. Fixes: f102d66b335a ("netfilter: nf_tables: use dedicated mutex to guard transactions") Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/nfnetlink.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/nfnetlink.h b/include/linux/netfilter/nfnetlink.h index 241e005f290a..e9a9ab34a7cc 100644 --- a/include/linux/netfilter/nfnetlink.h +++ b/include/linux/netfilter/nfnetlink.h @@ -45,7 +45,6 @@ struct nfnetlink_subsystem { int (*commit)(struct net *net, struct sk_buff *skb); int (*abort)(struct net *net, struct sk_buff *skb, enum nfnl_abort_action action); - void (*cleanup)(struct net *net); bool (*valid_genid)(struct net *net, u32 genid); }; -- cgit v1.2.3 From 6d26d985eeda89faedabbcf6607c37454b9691b0 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Sat, 22 Apr 2023 09:35:44 +0200 Subject: bpf: fix link failure with NETFILTER=y INET=n Explicitly check if NETFILTER_BPF_LINK is enabled, else configs that have NETFILTER=y but CONFIG_INET=n fail to link: > kernel/bpf/syscall.o: undefined reference to `netfilter_prog_ops' > kernel/bpf/verifier.o: undefined reference to `netfilter_verifier_ops' Fixes: fd9c663b9ad6 ("bpf: minimal support for programs hooked into netfilter framework") Reported-by: kernel test robot Link: https://lore.kernel.org/oe-kbuild-all/202304220903.fRZTJtxe-lkp@intel.com/ Signed-off-by: Florian Westphal Link: https://lore.kernel.org/r/20230422073544.17634-1-fw@strlen.de Signed-off-by: Alexei Starovoitov --- include/linux/bpf_types.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index 39a999abb0ce..fc0d6f32c687 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -79,7 +79,7 @@ BPF_PROG_TYPE(BPF_PROG_TYPE_LSM, lsm, #endif BPF_PROG_TYPE(BPF_PROG_TYPE_SYSCALL, bpf_syscall, void *, void *) -#ifdef CONFIG_NETFILTER +#ifdef CONFIG_NETFILTER_BPF_LINK BPF_PROG_TYPE(BPF_PROG_TYPE_NETFILTER, netfilter, struct bpf_nf_ctx, struct bpf_nf_ctx) #endif -- cgit v1.2.3 From 87eff2ec57b6d68d294013d8dd21e839a1175e3a Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 21 Apr 2023 09:43:57 +0000 Subject: net: optimize napi_threaded_poll() vs RPS/RFS We use napi_threaded_poll() in order to reduce our softirq dependency. We can add a followup of 821eba962d95 ("net: optimize napi_schedule_rps()") to further remove the need of firing NET_RX_SOFTIRQ whenever RPS/RFS are used. Signed-off-by: Eric Dumazet Acked-by: Paolo Abeni Signed-off-by: David S. Miller --- include/linux/netdevice.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index a6a3e9457d6c..08fbd4622ccf 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3194,7 +3194,10 @@ struct softnet_data { #ifdef CONFIG_RPS struct softnet_data *rps_ipi_list; #endif + bool in_net_rx_action; + bool in_napi_threaded_poll; + #ifdef CONFIG_NET_FLOW_LIMIT struct sd_flow_limit __rcu *flow_limit; #endif -- cgit v1.2.3 From f90615ada0b1e21a9d93ff89b04549fd7a92c92b Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 21 Apr 2023 01:55:53 +0300 Subject: net: vlan: don't adjust MAC header in __vlan_insert_inner_tag() unless set This is a preparatory change for the deletion of skb_reset_mac_header(skb) from __dev_queue_xmit(). After that deletion, skb_mac_header(skb) will no longer be set in TX paths, from which __vlan_insert_inner_tag() can still be called (perhaps indirectly). If we don't make this change, then an unset MAC header (equal to ~0U) will become set after the adjustment with VLAN_HLEN. Signed-off-by: Vladimir Oltean Reviewed-by: Eric Dumazet Reviewed-by: Simon Horman Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/if_vlan.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index 6864b89ef868..90b76d63c11c 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -351,7 +351,8 @@ static inline int __vlan_insert_inner_tag(struct sk_buff *skb, /* Move the mac header sans proto to the beginning of the new header. */ if (likely(mac_len > ETH_TLEN)) memmove(skb->data, skb->data + VLAN_HLEN, mac_len - ETH_TLEN); - skb->mac_header -= VLAN_HLEN; + if (skb_mac_header_was_set(skb)) + skb->mac_header -= VLAN_HLEN; veth = (struct vlan_ethhdr *)(skb->data + mac_len - ETH_HLEN); -- cgit v1.2.3 From 1f5020acb33f926030f62563c86dffca35c7b701 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 21 Apr 2023 01:55:54 +0300 Subject: net: vlan: introduce skb_vlan_eth_hdr() Similar to skb_eth_hdr() introduced in commit 96cc4b69581d ("macvlan: do not assume mac_header is set in macvlan_broadcast()"), let's introduce a skb_vlan_eth_hdr() helper which can be used in TX-only code paths to get to the VLAN header based on skb->data rather than based on the skb_mac_header(skb). We also consolidate the drivers that dereference skb->data to go through this helper. Signed-off-by: Vladimir Oltean Reviewed-by: Eric Dumazet Reviewed-by: Simon Horman Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/if_vlan.h | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index 90b76d63c11c..3698f2b391cd 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -62,6 +62,14 @@ static inline struct vlan_ethhdr *vlan_eth_hdr(const struct sk_buff *skb) return (struct vlan_ethhdr *)skb_mac_header(skb); } +/* Prefer this version in TX path, instead of + * skb_reset_mac_header() + vlan_eth_hdr() + */ +static inline struct vlan_ethhdr *skb_vlan_eth_hdr(const struct sk_buff *skb) +{ + return (struct vlan_ethhdr *)skb->data; +} + #define VLAN_PRIO_MASK 0xe000 /* Priority Code Point */ #define VLAN_PRIO_SHIFT 13 #define VLAN_CFI_MASK 0x1000 /* Canonical Format Indicator / Drop Eligible Indicator */ @@ -529,7 +537,7 @@ static inline void __vlan_hwaccel_put_tag(struct sk_buff *skb, */ static inline int __vlan_get_tag(const struct sk_buff *skb, u16 *vlan_tci) { - struct vlan_ethhdr *veth = (struct vlan_ethhdr *)skb->data; + struct vlan_ethhdr *veth = skb_vlan_eth_hdr(skb); if (!eth_type_vlan(veth->h_vlan_proto)) return -EINVAL; @@ -713,7 +721,7 @@ static inline bool skb_vlan_tagged_multi(struct sk_buff *skb) if (unlikely(!pskb_may_pull(skb, VLAN_ETH_HLEN))) return false; - veh = (struct vlan_ethhdr *)skb->data; + veh = skb_vlan_eth_hdr(skb); protocol = veh->h_vlan_encapsulated_proto; } -- cgit v1.2.3 From 0bcf2e4aca6c29a07555b713f2fb461dc38d5977 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 21 Apr 2023 01:56:01 +0300 Subject: net: dsa: tag_ocelot: call only the relevant portion of __skb_vlan_pop() on TX ocelot_xmit_get_vlan_info() calls __skb_vlan_pop() as the most appropriate helper I could find which strips away a VLAN header. That's all I need it to do, but __skb_vlan_pop() has more logic, which will become incompatible with the future revert of commit 6d1ccff62780 ("net: reset mac header in dev_start_xmit()"). Namely, it performs a sanity check on skb_mac_header(), which will stop being set after the above revert, so it will return an error instead of removing the VLAN tag. ocelot_xmit_get_vlan_info() gets called in 2 circumstances: (1) the port is under a VLAN-aware bridge and the bridge sends VLAN-tagged packets (2) the port is under a VLAN-aware bridge and somebody else (an 8021q upper) sends VLAN-tagged packets (using a VID that isn't in the bridge vlan tables) In case (1), there is actually no bug to defend against, because br_dev_xmit() calls skb_reset_mac_header() and things continue to work. However, in case (2), illustrated using the commands below, it can be seen that our intervention is needed, since __skb_vlan_pop() complains: $ ip link add br0 type bridge vlan_filtering 1 && ip link set br0 up $ ip link set $eth master br0 && ip link set $eth up $ ip link add link $eth name $eth.100 type vlan id 100 && ip link set $eth.100 up $ ip addr add 192.168.100.1/24 dev $eth.100 I could fend off the checks in __skb_vlan_pop() with some skb_mac_header_was_set() calls, but seeing how few callers of __skb_vlan_pop() there are from TX paths, that seems rather unproductive. As an alternative solution, extract the bare minimum logic to strip a VLAN header, and move it to a new helper named vlan_remove_tag(), close to the definition of vlan_insert_tag(). Document it appropriately and make ocelot_xmit_get_vlan_info() call this smaller helper instead. Seeing that it doesn't appear illegal to test skb->protocol in the TX path, I guess it would be a good for vlan_remove_tag() to also absorb the vlan_set_encap_proto() function call. Signed-off-by: Vladimir Oltean Reviewed-by: Simon Horman Reviewed-by: Florian Fainelli Reviewed-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/if_vlan.h | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) (limited to 'include/linux') diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index 3698f2b391cd..0f40f379d75c 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -685,6 +685,27 @@ static inline void vlan_set_encap_proto(struct sk_buff *skb, skb->protocol = htons(ETH_P_802_2); } +/** + * vlan_remove_tag - remove outer VLAN tag from payload + * @skb: skbuff to remove tag from + * @vlan_tci: buffer to store value + * + * Expects the skb to contain a VLAN tag in the payload, and to have skb->data + * pointing at the MAC header. + * + * Returns a new pointer to skb->data, or NULL on failure to pull. + */ +static inline void *vlan_remove_tag(struct sk_buff *skb, u16 *vlan_tci) +{ + struct vlan_hdr *vhdr = (struct vlan_hdr *)(skb->data + ETH_HLEN); + + *vlan_tci = ntohs(vhdr->h_vlan_TCI); + + memmove(skb->data + VLAN_HLEN, skb->data, 2 * ETH_ALEN); + vlan_set_encap_proto(skb, vhdr); + return __skb_pull(skb, VLAN_HLEN); +} + /** * skb_vlan_tagged - check if skb is vlan tagged. * @skb: skbuff to query -- cgit v1.2.3 From 29f93a687f3c435e94d026ee1fc8ad18ce56b7fb Mon Sep 17 00:00:00 2001 From: Neeraj Sanjay Kale Date: Thu, 16 Mar 2023 22:52:11 +0530 Subject: serdev: Replace all instances of ENOTSUPP with EOPNOTSUPP This replaces all instances of ENOTSUPP with EOPNOTSUPP since ENOTSUPP is not a standard error code. This will help maintain consistency in error codes when new serdev API's are added. Signed-off-by: Neeraj Sanjay Kale Reviewed-by: Simon Horman Signed-off-by: Luiz Augusto von Dentz --- include/linux/serdev.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/serdev.h b/include/linux/serdev.h index 5f6bfe4f6d95..babedb13785b 100644 --- a/include/linux/serdev.h +++ b/include/linux/serdev.h @@ -250,11 +250,11 @@ static inline int serdev_device_write_buf(struct serdev_device *serdev, static inline void serdev_device_wait_until_sent(struct serdev_device *sdev, long timeout) {} static inline int serdev_device_get_tiocm(struct serdev_device *serdev) { - return -ENOTSUPP; + return -EOPNOTSUPP; } static inline int serdev_device_set_tiocm(struct serdev_device *serdev, int set, int clear) { - return -ENOTSUPP; + return -EOPNOTSUPP; } static inline int serdev_device_write(struct serdev_device *sdev, const unsigned char *buf, size_t count, unsigned long timeout) -- cgit v1.2.3 From 8eaf839e4ac4feadf06e03eeff34059795450712 Mon Sep 17 00:00:00 2001 From: Neeraj Sanjay Kale Date: Thu, 16 Mar 2023 22:52:12 +0530 Subject: serdev: Add method to assert break signal over tty UART port Adds serdev_device_break_ctl() and an implementation for ttyport. This function simply calls the break_ctl in tty layer, which can assert a break signal over UART-TX line, if the tty and the underlying platform and UART peripheral supports this operation. Signed-off-by: Neeraj Sanjay Kale Reviewed-by: Simon Horman Signed-off-by: Luiz Augusto von Dentz --- include/linux/serdev.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/serdev.h b/include/linux/serdev.h index babedb13785b..f5f97fa25e8a 100644 --- a/include/linux/serdev.h +++ b/include/linux/serdev.h @@ -93,6 +93,7 @@ struct serdev_controller_ops { void (*wait_until_sent)(struct serdev_controller *, long); int (*get_tiocm)(struct serdev_controller *); int (*set_tiocm)(struct serdev_controller *, unsigned int, unsigned int); + int (*break_ctl)(struct serdev_controller *ctrl, unsigned int break_state); }; /** @@ -203,6 +204,7 @@ int serdev_device_write_buf(struct serdev_device *, const unsigned char *, size_ void serdev_device_wait_until_sent(struct serdev_device *, long); int serdev_device_get_tiocm(struct serdev_device *); int serdev_device_set_tiocm(struct serdev_device *, int, int); +int serdev_device_break_ctl(struct serdev_device *serdev, int break_state); void serdev_device_write_wakeup(struct serdev_device *); int serdev_device_write(struct serdev_device *, const unsigned char *, size_t, long); void serdev_device_write_flush(struct serdev_device *); @@ -256,6 +258,10 @@ static inline int serdev_device_set_tiocm(struct serdev_device *serdev, int set, { return -EOPNOTSUPP; } +static inline int serdev_device_break_ctl(struct serdev_device *serdev, int break_state) +{ + return -EOPNOTSUPP; +} static inline int serdev_device_write(struct serdev_device *sdev, const unsigned char *buf, size_t count, unsigned long timeout) { -- cgit v1.2.3 From 74d7970febf7e9005375aeda0df821d2edffc9f7 Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Fri, 21 Apr 2023 16:09:01 +0900 Subject: ksmbd: fix racy issue from using ->d_parent and ->d_name Al pointed out that ksmbd has racy issue from using ->d_parent and ->d_name in ksmbd_vfs_unlink and smb2_vfs_rename(). and use new lock_rename_child() to lock stable parent while underlying rename racy. Introduce vfs_path_parent_lookup helper to avoid out of share access and export vfs functions like the following ones to use vfs_path_parent_lookup(). - rename __lookup_hash() to lookup_one_qstr_excl(). - export lookup_one_qstr_excl(). - export getname_kernel() and putname(). vfs_path_parent_lookup() is used for parent lookup of destination file using absolute pathname given from FILE_RENAME_INFORMATION request. Signed-off-by: Namjae Jeon Signed-off-by: Steve French --- include/linux/namei.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/namei.h b/include/linux/namei.h index 5864e4d82e56..1463cbda4888 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -57,12 +57,18 @@ static inline int user_path_at(int dfd, const char __user *name, unsigned flags, return user_path_at_empty(dfd, name, flags, path, NULL); } +struct dentry *lookup_one_qstr_excl(const struct qstr *name, + struct dentry *base, + unsigned int flags); extern int kern_path(const char *, unsigned, struct path *); extern struct dentry *kern_path_create(int, const char *, struct path *, unsigned int); extern struct dentry *user_path_create(int, const char __user *, struct path *, unsigned int); extern void done_path_create(struct path *, struct dentry *); extern struct dentry *kern_path_locked(const char *, struct path *); +int vfs_path_parent_lookup(struct filename *filename, unsigned int flags, + struct path *parent, struct qstr *last, int *type, + const struct path *root); int vfs_path_lookup(struct dentry *, struct vfsmount *, const char *, unsigned int, struct path *); -- cgit v1.2.3 From 32d2a15ec54a3d8b708b343e50072ccb0e5da83f Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Mon, 6 Mar 2023 14:59:04 -0600 Subject: platform/chrome: Replace fake flexible arrays with flexible-array member MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Zero-length arrays as fake flexible arrays are deprecated and we are moving towards adopting C99 flexible-array members instead. Use the DECLARE_FLEX_ARRAY() helper macro to transform zero-length arrays in unions with flexible-array members. Address the following warning found with GCC-13 and -fstrict-flex-arrays=3 enabled: drivers/iio/accel/cros_ec_accel_legacy.c:66:46: warning: array subscript is outside array bounds of ‘struct ec_response_motion_sensor_data[0]’ [-Warray-bounds=] This helps with the ongoing efforts to tighten the FORTIFY_SOURCE routines on memcpy() and help us make progress towards globally enabling -fstrict-flex-arrays=3 [1]. Link: https://github.com/KSPP/linux/issues/21 Link: https://github.com/KSPP/linux/issues/193 Link: https://github.com/KSPP/linux/issues/262 Link: https://gcc.gnu.org/pipermail/gcc-patches/2022-October/602902.html [1] Signed-off-by: Gustavo A. R. Silva Signed-off-by: Tzung-Bi Shih Link: https://lore.kernel.org/r/ZAZUGBmSLc5wg7AK@work --- include/linux/platform_data/cros_ec_commands.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/cros_ec_commands.h b/include/linux/platform_data/cros_ec_commands.h index 7e9c76aedd2d..ab721cf13a98 100644 --- a/include/linux/platform_data/cros_ec_commands.h +++ b/include/linux/platform_data/cros_ec_commands.h @@ -2701,7 +2701,7 @@ struct ec_response_motion_sense { * Sensor data is truncated if response_max is too small * for holding all the data. */ - struct ec_response_motion_sensor_data sensor[0]; + DECLARE_FLEX_ARRAY(struct ec_response_motion_sensor_data, sensor); } dump; /* Used for MOTIONSENSE_CMD_INFO. */ -- cgit v1.2.3 From bfff83c4824308f7acce47baf88858b52bc1314f Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Tue, 28 Mar 2023 19:15:29 -0700 Subject: linux/vt_buffer.h: allow either builtin or modular for macros Fix build errors on ARCH=alpha when CONFIG_MDA_CONSOLE=m. This allows the ARCH macros to be the only ones defined. In file included from ../drivers/video/console/mdacon.c:37: ../arch/alpha/include/asm/vga.h:17:40: error: expected identifier or '(' before 'volatile' 17 | static inline void scr_writew(u16 val, volatile u16 *addr) | ^~~~~~~~ ../include/linux/vt_buffer.h:24:34: note: in definition of macro 'scr_writew' 24 | #define scr_writew(val, addr) (*(addr) = (val)) | ^~~~ ../include/linux/vt_buffer.h:24:40: error: expected ')' before '=' token 24 | #define scr_writew(val, addr) (*(addr) = (val)) | ^ ../arch/alpha/include/asm/vga.h:17:20: note: in expansion of macro 'scr_writew' 17 | static inline void scr_writew(u16 val, volatile u16 *addr) | ^~~~~~~~~~ ../arch/alpha/include/asm/vga.h:25:29: error: expected identifier or '(' before 'volatile' 25 | static inline u16 scr_readw(volatile const u16 *addr) | ^~~~~~~~ Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Randy Dunlap Cc: Greg Kroah-Hartman Cc: Jiri Slaby Cc: dri-devel@lists.freedesktop.org Cc: linux-fbdev@vger.kernel.org Signed-off-by: Helge Deller --- include/linux/vt_buffer.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/vt_buffer.h b/include/linux/vt_buffer.h index 848db1b1569f..919d999a8c1d 100644 --- a/include/linux/vt_buffer.h +++ b/include/linux/vt_buffer.h @@ -16,7 +16,7 @@ #include -#if defined(CONFIG_VGA_CONSOLE) || defined(CONFIG_MDA_CONSOLE) +#if IS_ENABLED(CONFIG_VGA_CONSOLE) || IS_ENABLED(CONFIG_MDA_CONSOLE) #include #endif -- cgit v1.2.3 From 96928d9032a7c34f12a88df879665562bcebf59a Mon Sep 17 00:00:00 2001 From: Sergey Senozhatsky Date: Sat, 15 Apr 2023 19:01:10 +0900 Subject: seq_buf: Add seq_buf_do_printk() helper Sometimes we use seq_buf to format a string buffer, which we then pass to printk(). However, in certain situations the seq_buf string buffer can get too big, exceeding the PRINTKRB_RECORD_MAX bytes limit, and causing printk() to truncate the string. Add a new seq_buf helper. This helper prints the seq_buf string buffer line by line, using \n as a delimiter, rather than passing the whole string buffer to printk() at once. Link: https://lkml.kernel.org/r/20230415100110.1419872-1-senozhatsky@chromium.org Cc: Andrew Morton Signed-off-by: Sergey Senozhatsky Reviewed-by: Petr Mladek Tested-by: Yosry Ahmed Signed-off-by: Steven Rostedt (Google) --- include/linux/seq_buf.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/seq_buf.h b/include/linux/seq_buf.h index 5b31c5147969..515d7fcb9634 100644 --- a/include/linux/seq_buf.h +++ b/include/linux/seq_buf.h @@ -159,4 +159,6 @@ extern int seq_buf_bprintf(struct seq_buf *s, const char *fmt, const u32 *binary); #endif +void seq_buf_do_printk(struct seq_buf *s, const char *lvl); + #endif /* _LINUX_SEQ_BUF_H */ -- cgit v1.2.3 From f736d2c0caa8348b0bcd897972e470f7a596caad Mon Sep 17 00:00:00 2001 From: David Virag Date: Tue, 31 Jan 2023 19:30:06 +0100 Subject: mfd: sec: Remove PMICs without compatibles The S5M8751 and S5M8763 PMIC chips have no corresponding compatible values, so since board file support was removed for this driver, there is no way to specify these PMICs as present in boards anymore. Remove leftovers of these chips since it's dead code. Signed-off-by: David Virag Reviewed-by: Krzysztof Kozlowski Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230131183008.4451-2-virag.david003@gmail.com --- include/linux/mfd/samsung/core.h | 1 - include/linux/mfd/samsung/s5m8763.h | 90 ------------------------------------- 2 files changed, 91 deletions(-) delete mode 100644 include/linux/mfd/samsung/s5m8763.h (limited to 'include/linux') diff --git a/include/linux/mfd/samsung/core.h b/include/linux/mfd/samsung/core.h index f92fe090473d..07aae649a86f 100644 --- a/include/linux/mfd/samsung/core.h +++ b/include/linux/mfd/samsung/core.h @@ -36,7 +36,6 @@ struct gpio_desc; enum sec_device_type { - S5M8751X, S5M8763X, S5M8767X, S2MPA01, diff --git a/include/linux/mfd/samsung/s5m8763.h b/include/linux/mfd/samsung/s5m8763.h deleted file mode 100644 index c534f086ca16..000000000000 --- a/include/linux/mfd/samsung/s5m8763.h +++ /dev/null @@ -1,90 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0+ */ -/* - * Copyright (c) 2011 Samsung Electronics Co., Ltd - * http://www.samsung.com - */ - -#ifndef __LINUX_MFD_S5M8763_H -#define __LINUX_MFD_S5M8763_H - -/* S5M8763 registers */ -enum s5m8763_reg { - S5M8763_REG_IRQ1, - S5M8763_REG_IRQ2, - S5M8763_REG_IRQ3, - S5M8763_REG_IRQ4, - S5M8763_REG_IRQM1, - S5M8763_REG_IRQM2, - S5M8763_REG_IRQM3, - S5M8763_REG_IRQM4, - S5M8763_REG_STATUS1, - S5M8763_REG_STATUS2, - S5M8763_REG_STATUSM1, - S5M8763_REG_STATUSM2, - S5M8763_REG_CHGR1, - S5M8763_REG_CHGR2, - S5M8763_REG_LDO_ACTIVE_DISCHARGE1, - S5M8763_REG_LDO_ACTIVE_DISCHARGE2, - S5M8763_REG_BUCK_ACTIVE_DISCHARGE3, - S5M8763_REG_ONOFF1, - S5M8763_REG_ONOFF2, - S5M8763_REG_ONOFF3, - S5M8763_REG_ONOFF4, - S5M8763_REG_BUCK1_VOLTAGE1, - S5M8763_REG_BUCK1_VOLTAGE2, - S5M8763_REG_BUCK1_VOLTAGE3, - S5M8763_REG_BUCK1_VOLTAGE4, - S5M8763_REG_BUCK2_VOLTAGE1, - S5M8763_REG_BUCK2_VOLTAGE2, - S5M8763_REG_BUCK3, - S5M8763_REG_BUCK4, - S5M8763_REG_LDO1_LDO2, - S5M8763_REG_LDO3, - S5M8763_REG_LDO4, - S5M8763_REG_LDO5, - S5M8763_REG_LDO6, - S5M8763_REG_LDO7, - S5M8763_REG_LDO7_LDO8, - S5M8763_REG_LDO9_LDO10, - S5M8763_REG_LDO11, - S5M8763_REG_LDO12, - S5M8763_REG_LDO13, - S5M8763_REG_LDO14, - S5M8763_REG_LDO15, - S5M8763_REG_LDO16, - S5M8763_REG_BKCHR, - S5M8763_REG_LBCNFG1, - S5M8763_REG_LBCNFG2, -}; - -/* S5M8763 regulator ids */ -enum s5m8763_regulators { - S5M8763_LDO1, - S5M8763_LDO2, - S5M8763_LDO3, - S5M8763_LDO4, - S5M8763_LDO5, - S5M8763_LDO6, - S5M8763_LDO7, - S5M8763_LDO8, - S5M8763_LDO9, - S5M8763_LDO10, - S5M8763_LDO11, - S5M8763_LDO12, - S5M8763_LDO13, - S5M8763_LDO14, - S5M8763_LDO15, - S5M8763_LDO16, - S5M8763_BUCK1, - S5M8763_BUCK2, - S5M8763_BUCK3, - S5M8763_BUCK4, - S5M8763_AP_EN32KHZ, - S5M8763_CP_EN32KHZ, - S5M8763_ENCHGVI, - S5M8763_ESAFEUSB1, - S5M8763_ESAFEUSB2, -}; - -#define S5M8763_ENRAMP (1 << 4) -#endif /* __LINUX_MFD_S5M8763_H */ -- cgit v1.2.3 From a3165abaa9bda3e729b434a3e684fcfa205f252a Mon Sep 17 00:00:00 2001 From: David Virag Date: Tue, 31 Jan 2023 19:30:07 +0100 Subject: rtc: s5m: Drop S5M8763 support The S5M8763 MFD has no device tree compatible, and since board file support for it was removed, there's no way to use this MFD. After removing the remaining code for it from the MFD driver, also remove support for it in the s5m RTC driver, and all remaining references to it. Signed-off-by: David Virag Acked-by: Alexandre Belloni Reviewed-by: Krzysztof Kozlowski Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230131183008.4451-3-virag.david003@gmail.com --- include/linux/mfd/samsung/core.h | 1 - include/linux/mfd/samsung/irq.h | 50 ---------------------------------------- 2 files changed, 51 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/samsung/core.h b/include/linux/mfd/samsung/core.h index 07aae649a86f..a212b9f72bc9 100644 --- a/include/linux/mfd/samsung/core.h +++ b/include/linux/mfd/samsung/core.h @@ -36,7 +36,6 @@ struct gpio_desc; enum sec_device_type { - S5M8763X, S5M8767X, S2MPA01, S2MPS11X, diff --git a/include/linux/mfd/samsung/irq.h b/include/linux/mfd/samsung/irq.h index 6cfe4201a106..3fd2775eb9bb 100644 --- a/include/linux/mfd/samsung/irq.h +++ b/include/linux/mfd/samsung/irq.h @@ -194,54 +194,4 @@ enum s5m8767_irq { #define S5M8767_IRQ_RTC1S_MASK (1 << 4) #define S5M8767_IRQ_WTSR_MASK (1 << 5) -enum s5m8763_irq { - S5M8763_IRQ_DCINF, - S5M8763_IRQ_DCINR, - S5M8763_IRQ_JIGF, - S5M8763_IRQ_JIGR, - S5M8763_IRQ_PWRONF, - S5M8763_IRQ_PWRONR, - - S5M8763_IRQ_WTSREVNT, - S5M8763_IRQ_SMPLEVNT, - S5M8763_IRQ_ALARM1, - S5M8763_IRQ_ALARM0, - - S5M8763_IRQ_ONKEY1S, - S5M8763_IRQ_TOPOFFR, - S5M8763_IRQ_DCINOVPR, - S5M8763_IRQ_CHGRSTF, - S5M8763_IRQ_DONER, - S5M8763_IRQ_CHGFAULT, - - S5M8763_IRQ_LOBAT1, - S5M8763_IRQ_LOBAT2, - - S5M8763_IRQ_NR, -}; - -#define S5M8763_IRQ_DCINF_MASK (1 << 2) -#define S5M8763_IRQ_DCINR_MASK (1 << 3) -#define S5M8763_IRQ_JIGF_MASK (1 << 4) -#define S5M8763_IRQ_JIGR_MASK (1 << 5) -#define S5M8763_IRQ_PWRONF_MASK (1 << 6) -#define S5M8763_IRQ_PWRONR_MASK (1 << 7) - -#define S5M8763_IRQ_WTSREVNT_MASK (1 << 0) -#define S5M8763_IRQ_SMPLEVNT_MASK (1 << 1) -#define S5M8763_IRQ_ALARM1_MASK (1 << 2) -#define S5M8763_IRQ_ALARM0_MASK (1 << 3) - -#define S5M8763_IRQ_ONKEY1S_MASK (1 << 0) -#define S5M8763_IRQ_TOPOFFR_MASK (1 << 2) -#define S5M8763_IRQ_DCINOVPR_MASK (1 << 3) -#define S5M8763_IRQ_CHGRSTF_MASK (1 << 4) -#define S5M8763_IRQ_DONER_MASK (1 << 5) -#define S5M8763_IRQ_CHGFAULT_MASK (1 << 7) - -#define S5M8763_IRQ_LOBAT1_MASK (1 << 0) -#define S5M8763_IRQ_LOBAT2_MASK (1 << 1) - -#define S5M8763_ENRAMP (1 << 4) - #endif /* __LINUX_MFD_SEC_IRQ_H */ -- cgit v1.2.3 From 86c6bb0edffa9fc02b4e3801b48c8e82114f1352 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Tue, 14 Feb 2023 09:58:59 +0100 Subject: mfd: core: Reorder fields in 'struct mfd_cell' to save some memory Group some variables based on their sizes to reduce hole and avoid padding. On x86_64, this shrinks the size from 144 to 128 bytes. As an example: $ size drivers/mfd/as3722.o (Before) text data bss dec hex filename 9441 680 16 10137 2799 drivers/mfd/as3722.o $ size drivers/mfd/as3722.o (After) text data bss dec hex filename 9345 680 16 10041 2739 drivers/mfd/as3722.o Signed-off-by: Christophe JAILLET Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/bb631974888dfe1af593b6280cf30fb913d2d1a4.1676365116.git.christophe.jaillet@wanadoo.fr --- include/linux/mfd/core.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/core.h b/include/linux/mfd/core.h index 14ca7b471576..fc4a0e9fb3bb 100644 --- a/include/linux/mfd/core.h +++ b/include/linux/mfd/core.h @@ -78,6 +78,9 @@ struct mfd_cell { void *platform_data; size_t pdata_size; + /* Matches ACPI */ + const struct mfd_cell_acpi_match *acpi_match; + /* Software node for the device. */ const struct software_node *swnode; @@ -97,9 +100,6 @@ struct mfd_cell { /* Set to 'true' to use 'of_reg' (above) - allows for of_reg=0 */ bool use_of_reg; - /* Matches ACPI */ - const struct mfd_cell_acpi_match *acpi_match; - /* * These resources can be specified relative to the parent device. * For accessing hardware you should use resources from the platform dev @@ -119,8 +119,8 @@ struct mfd_cell { /* A list of regulator supplies that should be mapped to the MFD * device rather than the child device when requested */ - const char * const *parent_supplies; int num_parent_supplies; + const char * const *parent_supplies; }; /* -- cgit v1.2.3 From b8fd17d9505e18001d10ceaa350c118a82b467bb Mon Sep 17 00:00:00 2001 From: Jakob Hauser Date: Tue, 28 Feb 2023 23:32:20 +0100 Subject: mfd: rt5033: Fix comments and style in includes Fix comments and remove some empty lines in rt5033-private.h. Align struct rt5033_charger in rt5033.h. Signed-off-by: Jakob Hauser Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/606950da6f4b36f5a124ff13756c78644fc89804.1677620677.git.jahau@rocketmail.com --- include/linux/mfd/rt5033-private.h | 17 +++++++---------- include/linux/mfd/rt5033.h | 7 +++---- 2 files changed, 10 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/rt5033-private.h b/include/linux/mfd/rt5033-private.h index 2d1895c3efbf..6bb432f6a96c 100644 --- a/include/linux/mfd/rt5033-private.h +++ b/include/linux/mfd/rt5033-private.h @@ -107,14 +107,13 @@ enum rt5033_reg { #define RT5033_LDO_CTRL_MASK 0x1f /* RT5033 charger property - model, manufacturer */ - #define RT5033_CHARGER_MODEL "RT5033WSC Charger" #define RT5033_MANUFACTURER "Richtek Technology Corporation" /* - * RT5033 charger fast-charge current lmits (as in CHGCTRL1 register), - * AICR mode limits the input current for example, - * the AIRC 100 mode limits the input current to 100 mA. + * While RT5033 charger can limit the fast-charge current (as in CHGCTRL1 + * register), AICR mode limits the input current. For example, the AIRC 100 + * mode limits the input current to 100 mA. */ #define RT5033_AICR_100_MODE 0x20 #define RT5033_AICR_500_MODE 0x40 @@ -139,10 +138,9 @@ enum rt5033_reg { #define RT5033_TE_ENABLE_MASK 0x08 /* - * RT5033 charger opa mode. RT50300 have two opa mode charger mode - * and boost mode for OTG + * RT5033 charger opa mode. RT5033 has two opa modes for OTG: charger mode + * and boost mode. */ - #define RT5033_CHARGER_MODE 0x00 #define RT5033_BOOST_MODE 0x01 @@ -181,18 +179,17 @@ enum rt5033_reg { * RT5033 charger pre-charge threshold volt limits * (as in CHGCTRL5 register), uV */ - #define RT5033_CHARGER_PRE_THRESHOLD_LIMIT_MIN 2300000U #define RT5033_CHARGER_PRE_THRESHOLD_STEP_NUM 100000U #define RT5033_CHARGER_PRE_THRESHOLD_LIMIT_MAX 3800000U /* - * RT5033 charger enable UUG, If UUG enable MOS auto control by H/W charger + * RT5033 charger UUG. It enables MOS auto control by H/W charger * circuit. */ #define RT5033_CHARGER_UUG_ENABLE 0x02 -/* RT5033 charger High impedance mode */ +/* RT5033 charger high impedance mode */ #define RT5033_CHARGER_HZ_DISABLE 0x00 #define RT5033_CHARGER_HZ_ENABLE 0x01 diff --git a/include/linux/mfd/rt5033.h b/include/linux/mfd/rt5033.h index 3c23b6220c04..8f306ac15a27 100644 --- a/include/linux/mfd/rt5033.h +++ b/include/linux/mfd/rt5033.h @@ -49,10 +49,9 @@ struct rt5033_charger_data { }; struct rt5033_charger { - struct device *dev; - struct rt5033_dev *rt5033; - struct power_supply psy; - + struct device *dev; + struct rt5033_dev *rt5033; + struct power_supply psy; struct rt5033_charger_data *chg; }; -- cgit v1.2.3 From 0742c2a6335281608ac9e9aee67493e9e30f6195 Mon Sep 17 00:00:00 2001 From: Patrick Rudolph Date: Tue, 7 Mar 2023 13:12:45 +0100 Subject: mfd: max597x: Add support for MAX5970 and MAX5978 Implement a regulator driver with IRQ support for fault management. Written against documentation [1] and [2] and tested on real hardware. Every channel has it's own regulator supply nammed 'vss1-supply' and 'vss2-supply'. The regulator supply is used to determine the output voltage, as the smart switch provides no output regulation. The driver requires the 'shunt-resistor-micro-ohms' to be present in the devicetree to properly calculate current related values. You must specify compatible devictree layout: regulator@3a { reg = <0x3a>; vss1-supply = <&p3v3>; compatible = "maxim,max5978"; ... regulators { sw0_ref: SW0 { regulator-compatible = "SW0"; shunt-resistor-micro-ohms = <12000>; ... } } } 1: https://datasheets.maximintegrated.com/en/ds/MAX5970.pdf 2: https://datasheets.maximintegrated.com/en/ds/MAX5978.pdf ... Changes in V12: - Use simple_mfd_i2c driver and remove previous implementation. - Remove newline - Use _MFD_MAX597X_H in header file - Successfull build need following patch from regulator: https://lore.kernel.org/r/20230216075302.68935-1-Naresh.Solanki@9elements.com https://lore.kernel.org/r/20230210163225.1208035-1-Naresh.Solanki@9elements.com Signed-off-by: Patrick Rudolph Signed-off-by: Marcello Sylvester Bauer Signed-off-by: Naresh Solanki Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230307121246.127425-2-Naresh.Solanki@9elements.com --- include/linux/mfd/max597x.h | 96 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 96 insertions(+) create mode 100644 include/linux/mfd/max597x.h (limited to 'include/linux') diff --git a/include/linux/mfd/max597x.h b/include/linux/mfd/max597x.h new file mode 100644 index 000000000000..a850b2e02e6a --- /dev/null +++ b/include/linux/mfd/max597x.h @@ -0,0 +1,96 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Device driver for regulators in MAX5970 and MAX5978 IC + * + * Copyright (c) 2022 9elements GmbH + * + * Author: Patrick Rudolph + */ + +#ifndef _MFD_MAX597X_H +#define _MFD_MAX597X_H + +#include + +#define MAX5970_NUM_SWITCHES 2 +#define MAX5978_NUM_SWITCHES 1 +#define MAX597X_NUM_LEDS 4 + +struct max597x_data { + int num_switches; + u32 irng[MAX5970_NUM_SWITCHES]; + u32 mon_rng[MAX5970_NUM_SWITCHES]; + u32 shunt_micro_ohms[MAX5970_NUM_SWITCHES]; +}; + +enum max597x_chip_type { + MAX597x_TYPE_MAX5978 = 1, + MAX597x_TYPE_MAX5970, +}; + +#define MAX5970_REG_CURRENT_L(ch) (0x01 + (ch) * 4) +#define MAX5970_REG_CURRENT_H(ch) (0x00 + (ch) * 4) +#define MAX5970_REG_VOLTAGE_L(ch) (0x03 + (ch) * 4) +#define MAX5970_REG_VOLTAGE_H(ch) (0x02 + (ch) * 4) +#define MAX5970_REG_MON_RANGE 0x18 +#define MAX5970_MON_MASK 0x3 +#define MAX5970_MON(reg, ch) (((reg) >> ((ch) * 2)) & MAX5970_MON_MASK) +#define MAX5970_MON_MAX_RANGE_UV 16000000 + +#define MAX5970_REG_CH_UV_WARN_H(ch) (0x1A + (ch) * 10) +#define MAX5970_REG_CH_UV_WARN_L(ch) (0x1B + (ch) * 10) +#define MAX5970_REG_CH_UV_CRIT_H(ch) (0x1C + (ch) * 10) +#define MAX5970_REG_CH_UV_CRIT_L(ch) (0x1D + (ch) * 10) +#define MAX5970_REG_CH_OV_WARN_H(ch) (0x1E + (ch) * 10) +#define MAX5970_REG_CH_OV_WARN_L(ch) (0x1F + (ch) * 10) +#define MAX5970_REG_CH_OV_CRIT_H(ch) (0x20 + (ch) * 10) +#define MAX5970_REG_CH_OV_CRIT_L(ch) (0x21 + (ch) * 10) + +#define MAX5970_VAL2REG_H(x) (((x) >> 2) & 0xFF) +#define MAX5970_VAL2REG_L(x) ((x) & 0x3) + +#define MAX5970_REG_DAC_FAST(ch) (0x2E + (ch)) + +#define MAX5970_FAST2SLOW_RATIO 200 + +#define MAX5970_REG_STATUS0 0x31 +#define MAX5970_CB_IFAULTF(ch) (1 << (ch)) +#define MAX5970_CB_IFAULTS(ch) (1 << ((ch) + 4)) + +#define MAX5970_REG_STATUS1 0x32 +#define STATUS1_PROT_MASK 0x3 +#define STATUS1_PROT(reg) \ + (((reg) >> 6) & STATUS1_PROT_MASK) +#define STATUS1_PROT_SHUTDOWN 0 +#define STATUS1_PROT_CLEAR_PG 1 +#define STATUS1_PROT_ALERT_ONLY 2 + +#define MAX5970_REG_STATUS2 0x33 +#define MAX5970_IRNG_MASK 0x3 +#define MAX5970_IRNG(reg, ch) \ + (((reg) >> ((ch) * 2)) & MAX5970_IRNG_MASK) + +#define MAX5970_REG_STATUS3 0x34 +#define MAX5970_STATUS3_ALERT BIT(4) +#define MAX5970_STATUS3_PG(ch) BIT(ch) + +#define MAX5970_REG_FAULT0 0x35 +#define UV_STATUS_WARN(ch) (1 << (ch)) +#define UV_STATUS_CRIT(ch) (1 << ((ch) + 4)) + +#define MAX5970_REG_FAULT1 0x36 +#define OV_STATUS_WARN(ch) (1 << (ch)) +#define OV_STATUS_CRIT(ch) (1 << ((ch) + 4)) + +#define MAX5970_REG_FAULT2 0x37 +#define OC_STATUS_WARN(ch) (1 << (ch)) + +#define MAX5970_REG_CHXEN 0x3b +#define CHXEN(ch) (3 << ((ch) * 2)) + +#define MAX5970_REG_LED_FLASH 0x43 + +#define MAX_REGISTERS 0x49 +#define ADC_MASK 0x3FF + +#endif /* _MFD_MAX597X_H */ -- cgit v1.2.3 From a0b9becad8a7d62a81530035a69f744c0e389737 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Wed, 8 Mar 2023 10:12:57 +0100 Subject: mfd: core: Remove .enable() and .disable() callbacks MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit With commit dd77f5fa97d3 ("mfd: Remove toshiba tmio drivers") the last mfd driver that implements these callbacks is gone and since commit 652719b1003a ("w1: remove ds1wm driver") the last user is gone. The corresponding functions mfd_cell_enable() and mfd_cell_disable() are also unused (since commit 0ca222c81977 ("leds: Remove asic3 driver")). Signed-off-by: Uwe Kleine-König Acked-by: Arnd Bergmann Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230308091257.2404932-1-u.kleine-koenig@pengutronix.de --- include/linux/mfd/core.h | 12 ------------ 1 file changed, 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/core.h b/include/linux/mfd/core.h index fc4a0e9fb3bb..47e7a3a61ce6 100644 --- a/include/linux/mfd/core.h +++ b/include/linux/mfd/core.h @@ -68,9 +68,6 @@ struct mfd_cell { int id; int level; - int (*enable)(struct platform_device *dev); - int (*disable)(struct platform_device *dev); - int (*suspend)(struct platform_device *dev); int (*resume)(struct platform_device *dev); @@ -123,15 +120,6 @@ struct mfd_cell { const char * const *parent_supplies; }; -/* - * Convenience functions for clients using shared cells. Refcounting - * happens automatically, with the cell's enable/disable callbacks - * being called only when a device is first being enabled or no other - * clients are making use of it. - */ -extern int mfd_cell_enable(struct platform_device *pdev); -extern int mfd_cell_disable(struct platform_device *pdev); - /* * Given a platform device that's been created by mfd_add_devices(), fetch * the mfd_cell that created it. -- cgit v1.2.3 From 67d6c76fc815cddc77de9529221f9ff8dd1fb10e Mon Sep 17 00:00:00 2001 From: Min Li Date: Mon, 27 Mar 2023 14:39:53 -0400 Subject: mfd: rsmu: Support 32-bit address space We used to assume 0x2010xxxx address. Now that we need to access 0x2011xxxx address, we need to support read/write the whole 32-bit address space. Also defined RSMU_MAX_WRITE_COUNT and RSMU_MAX_READ_COUNT for readability Signed-off-by: Min Li Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/MW5PR03MB693295AF31ABCAF6AE52EE74A08B9@MW5PR03MB6932.namprd03.prod.outlook.com --- include/linux/mfd/rsmu.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mfd/rsmu.h b/include/linux/mfd/rsmu.h index 6870de608233..0379aa207428 100644 --- a/include/linux/mfd/rsmu.h +++ b/include/linux/mfd/rsmu.h @@ -8,6 +8,9 @@ #ifndef __LINUX_MFD_RSMU_H #define __LINUX_MFD_RSMU_H +#define RSMU_MAX_WRITE_COUNT (255) +#define RSMU_MAX_READ_COUNT (255) + /* The supported devices are ClockMatrix, Sabre and SnowLotus */ enum rsmu_type { RSMU_CM = 0x34000, @@ -31,6 +34,6 @@ struct rsmu_ddata { struct regmap *regmap; struct mutex lock; enum rsmu_type type; - u16 page; + u32 page; }; #endif /* __LINUX_MFD_RSMU_H */ -- cgit v1.2.3 From 654c293e1687b31819f9bf1ac71b5a85a8053210 Mon Sep 17 00:00:00 2001 From: Biju Das Date: Thu, 30 Mar 2023 12:16:28 +0100 Subject: mfd: Add Renesas RZ/G2L MTU3a core driver The RZ/G2L multi-function timer pulse unit 3 (MTU3a) is embedded in the Renesas RZ/G2L family SoCs. It consists of eight 16-bit timer channels and one 32-bit timer channel. It supports the following functions - Counter - Timer - PWM The 8/16/32 bit registers are mixed in each channel. Add MTU3a core driver for RZ/G2L SoC. The core driver shares the clk and channel register access for the other child devices like Counter, PWM and Clock event. Signed-off-by: Biju Das Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230330111632.169434-3-biju.das.jz@bp.renesas.com --- include/linux/mfd/rz-mtu3.h | 257 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 257 insertions(+) create mode 100644 include/linux/mfd/rz-mtu3.h (limited to 'include/linux') diff --git a/include/linux/mfd/rz-mtu3.h b/include/linux/mfd/rz-mtu3.h new file mode 100644 index 000000000000..c5173bc06270 --- /dev/null +++ b/include/linux/mfd/rz-mtu3.h @@ -0,0 +1,257 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2022 Renesas Electronics Corporation + */ +#ifndef __MFD_RZ_MTU3_H__ +#define __MFD_RZ_MTU3_H__ + +#include +#include +#include + +/* 8-bit shared register offsets macros */ +#define RZ_MTU3_TSTRA 0x080 /* Timer start register A */ +#define RZ_MTU3_TSTRB 0x880 /* Timer start register B */ + +/* 16-bit shared register offset macros */ +#define RZ_MTU3_TDDRA 0x016 /* Timer dead time data register A */ +#define RZ_MTU3_TDDRB 0x816 /* Timer dead time data register B */ +#define RZ_MTU3_TCDRA 0x014 /* Timer cycle data register A */ +#define RZ_MTU3_TCDRB 0x814 /* Timer cycle data register B */ +#define RZ_MTU3_TCBRA 0x022 /* Timer cycle buffer register A */ +#define RZ_MTU3_TCBRB 0x822 /* Timer cycle buffer register B */ +#define RZ_MTU3_TCNTSA 0x020 /* Timer subcounter A */ +#define RZ_MTU3_TCNTSB 0x820 /* Timer subcounter B */ + +/* + * MTU5 contains 3 timer counter registers and is totaly different + * from other channels, so we must separate its offset + */ + +/* 8-bit register offset macros of MTU3 channels except MTU5 */ +#define RZ_MTU3_TIER 0 /* Timer interrupt register */ +#define RZ_MTU3_NFCR 1 /* Noise filter control register */ +#define RZ_MTU3_TSR 2 /* Timer status register */ +#define RZ_MTU3_TCR 3 /* Timer control register */ +#define RZ_MTU3_TCR2 4 /* Timer control register 2 */ + +/* Timer mode register 1 */ +#define RZ_MTU3_TMDR1 5 +#define RZ_MTU3_TMDR1_MD GENMASK(3, 0) +#define RZ_MTU3_TMDR1_MD_NORMAL FIELD_PREP(RZ_MTU3_TMDR1_MD, 0) +#define RZ_MTU3_TMDR1_MD_PWMMODE1 FIELD_PREP(RZ_MTU3_TMDR1_MD, 2) + +#define RZ_MTU3_TIOR 6 /* Timer I/O control register */ +#define RZ_MTU3_TIORH 6 /* Timer I/O control register H */ +#define RZ_MTU3_TIORL 7 /* Timer I/O control register L */ +/* Only MTU3/4/6/7 have TBTM registers */ +#define RZ_MTU3_TBTM 8 /* Timer buffer operation transfer mode register */ + +/* 8-bit MTU5 register offset macros */ +#define RZ_MTU3_TSTR 2 /* MTU5 Timer start register */ +#define RZ_MTU3_TCNTCMPCLR 3 /* MTU5 Timer compare match clear register */ +#define RZ_MTU3_TCRU 4 /* Timer control register U */ +#define RZ_MTU3_TCR2U 5 /* Timer control register 2U */ +#define RZ_MTU3_TIORU 6 /* Timer I/O control register U */ +#define RZ_MTU3_TCRV 7 /* Timer control register V */ +#define RZ_MTU3_TCR2V 8 /* Timer control register 2V */ +#define RZ_MTU3_TIORV 9 /* Timer I/O control register V */ +#define RZ_MTU3_TCRW 10 /* Timer control register W */ +#define RZ_MTU3_TCR2W 11 /* Timer control register 2W */ +#define RZ_MTU3_TIORW 12 /* Timer I/O control register W */ + +/* 16-bit register offset macros of MTU3 channels except MTU5 */ +#define RZ_MTU3_TCNT 0 /* Timer counter */ +#define RZ_MTU3_TGRA 1 /* Timer general register A */ +#define RZ_MTU3_TGRB 2 /* Timer general register B */ +#define RZ_MTU3_TGRC 3 /* Timer general register C */ +#define RZ_MTU3_TGRD 4 /* Timer general register D */ +#define RZ_MTU3_TGRE 5 /* Timer general register E */ +#define RZ_MTU3_TGRF 6 /* Timer general register F */ +/* Timer A/D converter start request registers */ +#define RZ_MTU3_TADCR 7 /* control register */ +#define RZ_MTU3_TADCORA 8 /* cycle set register A */ +#define RZ_MTU3_TADCORB 9 /* cycle set register B */ +#define RZ_MTU3_TADCOBRA 10 /* cycle set buffer register A */ +#define RZ_MTU3_TADCOBRB 11 /* cycle set buffer register B */ + +/* 16-bit MTU5 register offset macros */ +#define RZ_MTU3_TCNTU 0 /* MTU5 Timer counter U */ +#define RZ_MTU3_TGRU 1 /* MTU5 Timer general register U */ +#define RZ_MTU3_TCNTV 2 /* MTU5 Timer counter V */ +#define RZ_MTU3_TGRV 3 /* MTU5 Timer general register V */ +#define RZ_MTU3_TCNTW 4 /* MTU5 Timer counter W */ +#define RZ_MTU3_TGRW 5 /* MTU5 Timer general register W */ + +/* 32-bit register offset */ +#define RZ_MTU3_TCNTLW 0 /* Timer longword counter */ +#define RZ_MTU3_TGRALW 1 /* Timer longword general register A */ +#define RZ_MTU3_TGRBLW 2 /* Timer longowrd general register B */ + +#define RZ_MTU3_TMDR3 0x191 /* MTU1 Timer Mode Register 3 */ + +/* Macros for setting registers */ +#define RZ_MTU3_TCR_CCLR GENMASK(7, 5) +#define RZ_MTU3_TCR_CKEG GENMASK(4, 3) +#define RZ_MTU3_TCR_TPCS GENMASK(2, 0) +#define RZ_MTU3_TCR_CCLR_TGRA BIT(5) +#define RZ_MTU3_TCR_CCLR_TGRC FIELD_PREP(RZ_MTU3_TCR_CCLR, 5) +#define RZ_MTU3_TCR_CKEG_RISING FIELD_PREP(RZ_MTU3_TCR_CKEG, 0) + +#define RZ_MTU3_TIOR_IOB GENMASK(7, 4) +#define RZ_MTU3_TIOR_IOA GENMASK(3, 0) +#define RZ_MTU3_TIOR_OC_RETAIN 0 +#define RZ_MTU3_TIOR_OC_INIT_OUT_LO_HI_OUT 2 +#define RZ_MTU3_TIOR_OC_INIT_OUT_HI_TOGGLE_OUT 7 + +#define RZ_MTU3_TIOR_OC_IOA_H_COMP_MATCH \ + FIELD_PREP(RZ_MTU3_TIOR_IOA, RZ_MTU3_TIOR_OC_INIT_OUT_LO_HI_OUT) +#define RZ_MTU3_TIOR_OC_IOB_TOGGLE \ + FIELD_PREP(RZ_MTU3_TIOR_IOB, RZ_MTU3_TIOR_OC_INIT_OUT_HI_TOGGLE_OUT) + +enum rz_mtu3_channels { + RZ_MTU3_CHAN_0, + RZ_MTU3_CHAN_1, + RZ_MTU3_CHAN_2, + RZ_MTU3_CHAN_3, + RZ_MTU3_CHAN_4, + RZ_MTU3_CHAN_5, + RZ_MTU3_CHAN_6, + RZ_MTU3_CHAN_7, + RZ_MTU3_CHAN_8, + RZ_MTU_NUM_CHANNELS +}; + +/** + * struct rz_mtu3_channel - MTU3 channel private data + * + * @dev: device handle + * @channel_number: channel number + * @lock: Lock to protect channel state + * @is_busy: channel state + */ +struct rz_mtu3_channel { + struct device *dev; + unsigned int channel_number; + struct mutex lock; + bool is_busy; +}; + +/** + * struct rz_mtu3 - MTU3 core private data + * + * @clk: MTU3 module clock + * @rz_mtu3_channel: HW channels + * @priv_data: MTU3 core driver private data + */ +struct rz_mtu3 { + struct clk *clk; + struct rz_mtu3_channel channels[RZ_MTU_NUM_CHANNELS]; + + void *priv_data; +}; + +#if IS_ENABLED(CONFIG_RZ_MTU3) +static inline bool rz_mtu3_request_channel(struct rz_mtu3_channel *ch) +{ + mutex_lock(&ch->lock); + if (ch->is_busy) { + mutex_unlock(&ch->lock); + return false; + } + + ch->is_busy = true; + mutex_unlock(&ch->lock); + + return true; +} + +static inline void rz_mtu3_release_channel(struct rz_mtu3_channel *ch) +{ + mutex_lock(&ch->lock); + ch->is_busy = false; + mutex_unlock(&ch->lock); +} + +bool rz_mtu3_is_enabled(struct rz_mtu3_channel *ch); +void rz_mtu3_disable(struct rz_mtu3_channel *ch); +int rz_mtu3_enable(struct rz_mtu3_channel *ch); + +u8 rz_mtu3_8bit_ch_read(struct rz_mtu3_channel *ch, u16 off); +u16 rz_mtu3_16bit_ch_read(struct rz_mtu3_channel *ch, u16 off); +u32 rz_mtu3_32bit_ch_read(struct rz_mtu3_channel *ch, u16 off); +u16 rz_mtu3_shared_reg_read(struct rz_mtu3_channel *ch, u16 off); + +void rz_mtu3_8bit_ch_write(struct rz_mtu3_channel *ch, u16 off, u8 val); +void rz_mtu3_16bit_ch_write(struct rz_mtu3_channel *ch, u16 off, u16 val); +void rz_mtu3_32bit_ch_write(struct rz_mtu3_channel *ch, u16 off, u32 val); +void rz_mtu3_shared_reg_write(struct rz_mtu3_channel *ch, u16 off, u16 val); +void rz_mtu3_shared_reg_update_bit(struct rz_mtu3_channel *ch, u16 off, + u16 pos, u8 val); +#else +static inline bool rz_mtu3_request_channel(struct rz_mtu3_channel *ch) +{ + return false; +} + +static inline void rz_mtu3_release_channel(struct rz_mtu3_channel *ch) +{ +} + +static inline bool rz_mtu3_is_enabled(struct rz_mtu3_channel *ch) +{ + return false; +} + +static inline void rz_mtu3_disable(struct rz_mtu3_channel *ch) +{ +} + +static inline int rz_mtu3_enable(struct rz_mtu3_channel *ch) +{ + return 0; +} + +static inline u8 rz_mtu3_8bit_ch_read(struct rz_mtu3_channel *ch, u16 off) +{ + return 0; +} + +static inline u16 rz_mtu3_16bit_ch_read(struct rz_mtu3_channel *ch, u16 off) +{ + return 0; +} + +static inline u32 rz_mtu3_32bit_ch_read(struct rz_mtu3_channel *ch, u16 off) +{ + return 0; +} + +static inline u16 rz_mtu3_shared_reg_read(struct rz_mtu3_channel *ch, u16 off) +{ + return 0; +} + +static inline void rz_mtu3_8bit_ch_write(struct rz_mtu3_channel *ch, u16 off, u8 val) +{ +} + +static inline void rz_mtu3_16bit_ch_write(struct rz_mtu3_channel *ch, u16 off, u16 val) +{ +} + +static inline void rz_mtu3_32bit_ch_write(struct rz_mtu3_channel *ch, u16 off, u32 val) +{ +} + +static inline void rz_mtu3_shared_reg_write(struct rz_mtu3_channel *ch, u16 off, u16 val) +{ +} + +static inline void rz_mtu3_shared_reg_update_bit(struct rz_mtu3_channel *ch, + u16 off, u16 pos, u8 val) +{ +} +#endif + +#endif /* __MFD_RZ_MTU3_H__ */ -- cgit v1.2.3 From dcb779fcd4ed5984ad15991d574943d12a8693d1 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Wed, 15 Feb 2023 06:53:54 -0500 Subject: nfsd: allow reaping files still under writeback On most filesystems, there is no reason to delay reaping an nfsd_file just because its underlying inode is still under writeback. nfsd just relies on client activity or the local flusher threads to do writeback. The main exception is NFS, which flushes all of its dirty data on last close. Add a new EXPORT_OP_FLUSH_ON_CLOSE flag to allow filesystems to signal that they do this, and only skip closing files under writeback on such filesystems. Also, remove a redundant NULL file pointer check in nfsd_file_check_writeback, and clean up nfs's export op flag definitions. Signed-off-by: Jeff Layton Acked-by: Anna Schumaker Signed-off-by: Chuck Lever --- include/linux/exportfs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/exportfs.h b/include/linux/exportfs.h index 601700fedc91..9edb29101ec8 100644 --- a/include/linux/exportfs.h +++ b/include/linux/exportfs.h @@ -220,6 +220,7 @@ struct export_operations { #define EXPORT_OP_NOATOMIC_ATTR (0x10) /* Filesystem cannot supply atomic attribute updates */ +#define EXPORT_OP_FLUSH_ON_CLOSE (0x20) /* fs flushes file data on close */ unsigned long flags; }; -- cgit v1.2.3 From c88c680c6de5077292667fae4a147fd5a6523479 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Fri, 3 Mar 2023 07:15:58 -0500 Subject: lockd: remove 2 unused helper functions Signed-off-by: Jeff Layton Signed-off-by: Chuck Lever --- include/linux/lockd/lockd.h | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lockd/lockd.h b/include/linux/lockd/lockd.h index 0168ac9fdda8..26c2aed31a0c 100644 --- a/include/linux/lockd/lockd.h +++ b/include/linux/lockd/lockd.h @@ -99,21 +99,11 @@ struct nsm_handle { /* * Rigorous type checking on sockaddr type conversions */ -static inline struct sockaddr_in *nlm_addr_in(const struct nlm_host *host) -{ - return (struct sockaddr_in *)&host->h_addr; -} - static inline struct sockaddr *nlm_addr(const struct nlm_host *host) { return (struct sockaddr *)&host->h_addr; } -static inline struct sockaddr_in *nlm_srcaddr_in(const struct nlm_host *host) -{ - return (struct sockaddr_in *)&host->h_srcaddr; -} - static inline struct sockaddr *nlm_srcaddr(const struct nlm_host *host) { return (struct sockaddr *)&host->h_srcaddr; -- cgit v1.2.3 From f0aa4852e63f9c1cfd4322c770e69d7e6817e906 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Fri, 3 Mar 2023 07:15:59 -0500 Subject: lockd: move struct nlm_wait to lockd.h The next patch needs struct nlm_wait in fs/lockd/clntproc.c, so move the definition to a shared header file. As an added clean-up, drop the unused b_reclaim field. Signed-off-by: Jeff Layton Signed-off-by: Chuck Lever --- include/linux/lockd/lockd.h | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/lockd/lockd.h b/include/linux/lockd/lockd.h index 26c2aed31a0c..de5ad2c2179a 100644 --- a/include/linux/lockd/lockd.h +++ b/include/linux/lockd/lockd.h @@ -121,7 +121,16 @@ struct nlm_lockowner { uint32_t pid; }; -struct nlm_wait; +/* + * This is the representation of a blocked client lock. + */ +struct nlm_wait { + struct list_head b_list; /* linked list */ + wait_queue_head_t b_wait; /* where to wait on */ + struct nlm_host *b_host; + struct file_lock *b_lock; /* local file lock */ + __be32 b_status; /* grant callback status */ +}; /* * Memory chunk for NLM client RPC request. -- cgit v1.2.3 From 2005f5b9c35bd736c81e9f24f5c5051967c022ee Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Fri, 3 Mar 2023 07:16:00 -0500 Subject: lockd: fix races in client GRANTED_MSG wait logic After the wait for a grant is done (for whatever reason), nlmclnt_block updates the status of the nlm_rqst with the status of the block. At the point it does this, however, the block is still queued its status could change at any time. This is particularly a problem when the waiting task is signaled during the wait. We can end up giving up on the lock just before the GRANTED_MSG callback comes in, and accept it even though the lock request gets back an error, leaving a dangling lock on the server. Since the nlm_wait never lives beyond the end of nlmclnt_lock, put it on the stack and add functions to allow us to enqueue and dequeue the block. Enqueue it just before the lock/wait loop, and dequeue it just after we exit the loop instead of waiting until the end of the function. Also, scrape the status at the time that we dequeue it to ensure that it's final. Reported-by: Yongcheng Yang Link: https://bugzilla.redhat.com/show_bug.cgi?id=2063818 Signed-off-by: Jeff Layton Signed-off-by: Chuck Lever --- include/linux/lockd/lockd.h | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lockd/lockd.h b/include/linux/lockd/lockd.h index de5ad2c2179a..f42594a9efe0 100644 --- a/include/linux/lockd/lockd.h +++ b/include/linux/lockd/lockd.h @@ -211,9 +211,11 @@ struct nlm_rqst * nlm_alloc_call(struct nlm_host *host); int nlm_async_call(struct nlm_rqst *, u32, const struct rpc_call_ops *); int nlm_async_reply(struct nlm_rqst *, u32, const struct rpc_call_ops *); void nlmclnt_release_call(struct nlm_rqst *); -struct nlm_wait * nlmclnt_prepare_block(struct nlm_host *host, struct file_lock *fl); -void nlmclnt_finish_block(struct nlm_wait *block); -int nlmclnt_block(struct nlm_wait *block, struct nlm_rqst *req, long timeout); +void nlmclnt_prepare_block(struct nlm_wait *block, struct nlm_host *host, + struct file_lock *fl); +void nlmclnt_queue_block(struct nlm_wait *block); +__be32 nlmclnt_dequeue_block(struct nlm_wait *block); +int nlmclnt_wait(struct nlm_wait *block, struct nlm_rqst *req, long timeout); __be32 nlmclnt_grant(const struct sockaddr *addr, const struct nlm_lock *lock); void nlmclnt_recovery(struct nlm_host *); -- cgit v1.2.3 From e59fb6749ed833deee5b3cfd7e89925296d41f49 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Fri, 3 Mar 2023 07:16:02 -0500 Subject: nfs: move nfs_fhandle_hash to common include file lockd needs to be able to hash filehandles for tracepoints. Move the nfs_fhandle_hash() helper to a common nfs include file. Signed-off-by: Jeff Layton Signed-off-by: Chuck Lever --- include/linux/nfs.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nfs.h b/include/linux/nfs.h index b06375e88e58..ceb70a926b95 100644 --- a/include/linux/nfs.h +++ b/include/linux/nfs.h @@ -10,6 +10,7 @@ #include #include +#include #include /* @@ -44,4 +45,23 @@ enum nfs3_stable_how { /* used by direct.c to mark verf as invalid */ NFS_INVALID_STABLE_HOW = -1 }; + +#ifdef CONFIG_CRC32 +/** + * nfs_fhandle_hash - calculate the crc32 hash for the filehandle + * @fh - pointer to filehandle + * + * returns a crc32 hash for the filehandle that is compatible with + * the one displayed by "wireshark". + */ +static inline u32 nfs_fhandle_hash(const struct nfs_fh *fh) +{ + return ~crc32_le(0xFFFFFFFF, &fh->data[0], fh->size); +} +#else /* CONFIG_CRC32 */ +static inline u32 nfs_fhandle_hash(const struct nfs_fh *fh) +{ + return 0; +} +#endif /* CONFIG_CRC32 */ #endif /* _LINUX_NFS_H */ -- cgit v1.2.3 From cf64b9bce95095b80f4589e4f54572cc5d8c1538 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Wed, 8 Mar 2023 17:51:00 +1100 Subject: SUNRPC: return proper error from get_expiry() The get_expiry() function currently returns a timestamp, and uses the special return value of 0 to indicate an error. Unfortunately this causes a problem when 0 is the correct return value. On a system with no RTC it is possible that the boot time will be seen to be "3". When exportfs probes to see if a particular filesystem supports NFS export it tries to cache information with an expiry time of "3". The intention is for this to be "long in the past". Even with no RTC it will not be far in the future (at most a second or two) so this is harmless. But if the boot time happens to have been calculated to be "3", then get_expiry will fail incorrectly as it converts the number to "seconds since bootime" - 0. To avoid this problem we change get_expiry() to report the error quite separately from the expiry time. The error is now the return value. The expiry time is reported through a by-reference parameter. Reported-by: Jerry Zhang Tested-by: Jerry Zhang Signed-off-by: NeilBrown Reviewed-by: Jeff Layton Signed-off-by: Chuck Lever --- include/linux/sunrpc/cache.h | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/cache.h b/include/linux/sunrpc/cache.h index ec5a555df96f..518bd28f5ab8 100644 --- a/include/linux/sunrpc/cache.h +++ b/include/linux/sunrpc/cache.h @@ -300,17 +300,18 @@ static inline int get_time(char **bpp, time64_t *time) return 0; } -static inline time64_t get_expiry(char **bpp) +static inline int get_expiry(char **bpp, time64_t *rvp) { - time64_t rv; + int error; struct timespec64 boot; - if (get_time(bpp, &rv)) - return 0; - if (rv < 0) - return 0; + error = get_time(bpp, rvp); + if (error) + return error; + getboottime64(&boot); - return rv - boot.tv_sec; + (*rvp) -= boot.tv_sec; + return 0; } #endif /* _LINUX_SUNRPC_CACHE_H_ */ -- cgit v1.2.3 From 0f5162480bd25bd97b91c9153db7afbd89698804 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Fri, 17 Mar 2023 17:09:20 -0400 Subject: NFSD: Watch for rq_pages bounds checking errors in nfsd_splice_actor() There have been several bugs over the years where the NFSD splice actor has attempted to write outside the rq_pages array. This is a "should never happen" condition, but if for some reason the pipe splice actor should attempt to walk past the end of rq_pages, it needs to terminate the READ operation to prevent corruption of the pointer addresses in the fields just beyond the array. A server crash is thus prevented. Since the code is not behaving, the READ operation returns -EIO to the client. None of the READ payload data can be trusted if the splice actor isn't operating as expected. Suggested-by: Jeff Layton Signed-off-by: Chuck Lever Reviewed-by: Jeff Layton --- include/linux/sunrpc/svc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 877891536c2f..f5af055280ff 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -422,7 +422,7 @@ struct svc_serv *svc_create(struct svc_program *, unsigned int, int (*threadfn)(void *data)); struct svc_rqst *svc_rqst_alloc(struct svc_serv *serv, struct svc_pool *pool, int node); -void svc_rqst_replace_page(struct svc_rqst *rqstp, +bool svc_rqst_replace_page(struct svc_rqst *rqstp, struct page *page); void svc_rqst_free(struct svc_rqst *); void svc_exit_thread(struct svc_rqst *); -- cgit v1.2.3 From 55fcc7d9159de886296626e47db2c81f8578c7e1 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Mon, 3 Apr 2023 13:53:07 -0400 Subject: SUNRPC: Ignore return value of ->xpo_sendto Clean up: All callers of svc_process() ignore its return value, so svc_process() can safely be converted to return void. Ditto for svc_send(). The return value of ->xpo_sendto() is now used only as part of a trace event. Signed-off-by: Chuck Lever --- include/linux/sunrpc/svc.h | 2 +- include/linux/sunrpc/svcsock.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index f5af055280ff..2d31121fc2e6 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -430,7 +430,7 @@ struct svc_serv * svc_create_pooled(struct svc_program *, unsigned int, int (*threadfn)(void *data)); int svc_set_num_threads(struct svc_serv *, struct svc_pool *, int); int svc_pool_stats_open(struct svc_serv *serv, struct file *file); -int svc_process(struct svc_rqst *); +void svc_process(struct svc_rqst *rqstp); int bc_svc_process(struct svc_serv *, struct rpc_rqst *, struct svc_rqst *); int svc_register(const struct svc_serv *, struct net *, const int, diff --git a/include/linux/sunrpc/svcsock.h b/include/linux/sunrpc/svcsock.h index bcc555c7ae9c..dd73fa174af5 100644 --- a/include/linux/sunrpc/svcsock.h +++ b/include/linux/sunrpc/svcsock.h @@ -56,7 +56,7 @@ static inline u32 svc_sock_final_rec(struct svc_sock *svsk) */ void svc_close_net(struct svc_serv *, struct net *); int svc_recv(struct svc_rqst *, long); -int svc_send(struct svc_rqst *); +void svc_send(struct svc_rqst *rqstp); void svc_drop(struct svc_rqst *); void svc_sock_update_bufs(struct svc_serv *serv); bool svc_alien_sock(struct net *net, int fd); -- cgit v1.2.3 From b20cb39def085723868972182fb58fa906839a4f Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Fri, 14 Apr 2023 20:17:56 -0400 Subject: SUNRPC: Relocate svc_free_res_pages() Clean-up: There doesn't seem to be a reason why this function is stuck in a header. One thing it prevents is the convenient addition of tracing. Moving it to a source file also makes the rq_respages clean-up logic easier to find. Reviewed-by: Calum Mackay Signed-off-by: Chuck Lever --- include/linux/sunrpc/svc.h | 12 +----------- 1 file changed, 1 insertion(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 2d31121fc2e6..762d7231e574 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -309,17 +309,6 @@ static inline struct sockaddr *svc_daddr(const struct svc_rqst *rqst) return (struct sockaddr *) &rqst->rq_daddr; } -static inline void svc_free_res_pages(struct svc_rqst *rqstp) -{ - while (rqstp->rq_next_page != rqstp->rq_respages) { - struct page **pp = --rqstp->rq_next_page; - if (*pp) { - put_page(*pp); - *pp = NULL; - } - } -} - struct svc_deferred_req { u32 prot; /* protocol (UDP or TCP) */ struct svc_xprt *xprt; @@ -424,6 +413,7 @@ struct svc_rqst *svc_rqst_alloc(struct svc_serv *serv, struct svc_pool *pool, int node); bool svc_rqst_replace_page(struct svc_rqst *rqstp, struct page *page); +void svc_rqst_release_pages(struct svc_rqst *rqstp); void svc_rqst_free(struct svc_rqst *); void svc_exit_thread(struct svc_rqst *); struct svc_serv * svc_create_pooled(struct svc_program *, unsigned int, -- cgit v1.2.3 From e0f8ad2a705367518b5c56bf9d6da89681467c02 Mon Sep 17 00:00:00 2001 From: Shengyu Qu Date: Fri, 21 Apr 2023 23:08:15 +0800 Subject: mfd: axp20x: Add support for AXP15060 PMIC The AXP15060 is a PMIC chip produced by X-Powers, and could be connected via an I2C bus. Describe the regmap and the MFD bits, along with the registers exposed via I2C. Eventually advertise the device using a new compatible string and add support for power off the system. The driver would disable PEK function if IRQ is not configured in device tree, since some boards (For example, Starfive Visionfive 2) didn't connect IRQ line of PMIC to SOC. GPIO function isn't enabled in this commit, since its configuration operation is different from any existing AXP PMICs and needs logic modification on existing driver. GPIO support might come in later patches. Signed-off-by: Shengyu Qu Reviewed-by: Krzysztof Kozlowski Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/TY3P286MB261162D57695AC8164ED50E298609@TY3P286MB2611.JPNP286.PROD.OUTLOOK.COM --- include/linux/mfd/axp20x.h | 85 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 85 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/axp20x.h b/include/linux/mfd/axp20x.h index 2058194807bd..beb3f44f85c5 100644 --- a/include/linux/mfd/axp20x.h +++ b/include/linux/mfd/axp20x.h @@ -21,6 +21,7 @@ enum axp20x_variants { AXP806_ID, AXP809_ID, AXP813_ID, + AXP15060_ID, NR_AXP20X_VARIANTS, }; @@ -131,6 +132,39 @@ enum axp20x_variants { /* Other DCDC regulator control registers are the same as AXP803 */ #define AXP813_DCDC7_V_OUT 0x26 +#define AXP15060_STARTUP_SRC 0x00 +#define AXP15060_PWR_OUT_CTRL1 0x10 +#define AXP15060_PWR_OUT_CTRL2 0x11 +#define AXP15060_PWR_OUT_CTRL3 0x12 +#define AXP15060_DCDC1_V_CTRL 0x13 +#define AXP15060_DCDC2_V_CTRL 0x14 +#define AXP15060_DCDC3_V_CTRL 0x15 +#define AXP15060_DCDC4_V_CTRL 0x16 +#define AXP15060_DCDC5_V_CTRL 0x17 +#define AXP15060_DCDC6_V_CTRL 0x18 +#define AXP15060_ALDO1_V_CTRL 0x19 +#define AXP15060_DCDC_MODE_CTRL1 0x1a +#define AXP15060_DCDC_MODE_CTRL2 0x1b +#define AXP15060_OUTPUT_MONITOR_DISCHARGE 0x1e +#define AXP15060_IRQ_PWROK_VOFF 0x1f +#define AXP15060_ALDO2_V_CTRL 0x20 +#define AXP15060_ALDO3_V_CTRL 0x21 +#define AXP15060_ALDO4_V_CTRL 0x22 +#define AXP15060_ALDO5_V_CTRL 0x23 +#define AXP15060_BLDO1_V_CTRL 0x24 +#define AXP15060_BLDO2_V_CTRL 0x25 +#define AXP15060_BLDO3_V_CTRL 0x26 +#define AXP15060_BLDO4_V_CTRL 0x27 +#define AXP15060_BLDO5_V_CTRL 0x28 +#define AXP15060_CLDO1_V_CTRL 0x29 +#define AXP15060_CLDO2_V_CTRL 0x2a +#define AXP15060_CLDO3_V_CTRL 0x2b +#define AXP15060_CLDO4_V_CTRL 0x2d +#define AXP15060_CPUSLDO_V_CTRL 0x2e +#define AXP15060_PWR_WAKEUP_CTRL 0x31 +#define AXP15060_PWR_DISABLE_DOWN_SEQ 0x32 +#define AXP15060_PEK_KEY 0x36 + /* Interrupt */ #define AXP152_IRQ1_EN 0x40 #define AXP152_IRQ2_EN 0x41 @@ -152,6 +186,11 @@ enum axp20x_variants { #define AXP20X_IRQ5_STATE 0x4c #define AXP20X_IRQ6_STATE 0x4d +#define AXP15060_IRQ1_EN 0x40 +#define AXP15060_IRQ2_EN 0x41 +#define AXP15060_IRQ1_STATE 0x48 +#define AXP15060_IRQ2_STATE 0x49 + /* ADC */ #define AXP20X_ACIN_V_ADC_H 0x56 #define AXP20X_ACIN_V_ADC_L 0x57 @@ -222,6 +261,8 @@ enum axp20x_variants { #define AXP22X_GPIO_STATE 0x94 #define AXP22X_GPIO_PULL_DOWN 0x95 +#define AXP15060_CLDO4_GPIO2_MODESET 0x2c + /* Battery */ #define AXP20X_CHRG_CC_31_24 0xb0 #define AXP20X_CHRG_CC_23_16 0xb1 @@ -419,6 +460,33 @@ enum { AXP813_REG_ID_MAX, }; +enum { + AXP15060_DCDC1 = 0, + AXP15060_DCDC2, + AXP15060_DCDC3, + AXP15060_DCDC4, + AXP15060_DCDC5, + AXP15060_DCDC6, + AXP15060_ALDO1, + AXP15060_ALDO2, + AXP15060_ALDO3, + AXP15060_ALDO4, + AXP15060_ALDO5, + AXP15060_BLDO1, + AXP15060_BLDO2, + AXP15060_BLDO3, + AXP15060_BLDO4, + AXP15060_BLDO5, + AXP15060_CLDO1, + AXP15060_CLDO2, + AXP15060_CLDO3, + AXP15060_CLDO4, + AXP15060_CPUSLDO, + AXP15060_SW, + AXP15060_RTC_LDO, + AXP15060_REG_ID_MAX, +}; + /* IRQs */ enum { AXP152_IRQ_LDO0IN_CONNECT = 1, @@ -637,6 +705,23 @@ enum axp809_irqs { AXP809_IRQ_GPIO0_INPUT, }; +enum axp15060_irqs { + AXP15060_IRQ_DIE_TEMP_HIGH_LV1 = 1, + AXP15060_IRQ_DIE_TEMP_HIGH_LV2, + AXP15060_IRQ_DCDC1_V_LOW, + AXP15060_IRQ_DCDC2_V_LOW, + AXP15060_IRQ_DCDC3_V_LOW, + AXP15060_IRQ_DCDC4_V_LOW, + AXP15060_IRQ_DCDC5_V_LOW, + AXP15060_IRQ_DCDC6_V_LOW, + AXP15060_IRQ_PEK_LONG, + AXP15060_IRQ_PEK_SHORT, + AXP15060_IRQ_GPIO1_INPUT, + AXP15060_IRQ_PEK_FAL_EDGE, + AXP15060_IRQ_PEK_RIS_EDGE, + AXP15060_IRQ_GPIO2_INPUT, +}; + struct axp20x_dev { struct device *dev; int irq; -- cgit v1.2.3 From ff53cd52d9bdbf4074d2bbe9b591729997780bd3 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= Date: Sat, 18 Mar 2023 17:36:25 +0000 Subject: blk-integrity: register sysfs attributes on struct device MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The "integrity" kobject only acted as a holder for static sysfs entries. It also was embedded into struct gendisk without managing it, violating assumptions of the driver core. Instead register the sysfs entries directly onto the struct device. Also drop the now unused member integrity_kobj from struct gendisk. Suggested-by: Christoph Hellwig Signed-off-by: Thomas Weißschuh Reviewed-by: Christoph Hellwig Reviewed-by: Martin K. Petersen Link: https://lore.kernel.org/r/20230309-kobj_release-gendisk_integrity-v3-3-ceccb4493c46@weissschuh.net Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 6ede578dfbc6..aac5c8d7a9ff 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -157,9 +157,6 @@ struct gendisk { struct timer_rand_state *random; atomic_t sync_io; /* RAID */ struct disk_events *ev; -#ifdef CONFIG_BLK_DEV_INTEGRITY - struct kobject integrity_kobj; -#endif /* CONFIG_BLK_DEV_INTEGRITY */ #ifdef CONFIG_BLK_DEV_ZONED /* -- cgit v1.2.3 From 7cefbaf081eb7c114299f7478ed4fa0d90ec90bb Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Wed, 19 Apr 2023 10:33:38 +0200 Subject: thermal: core: Encapsulate tz->device field There are still some drivers needing to play with the thermal zone device internals. That is not the best but until we can figure out if the information is really needed, let's encapsulate the field used in the thermal zone device structure, so we can move forward relocating the thermal zone device structure definition in the thermal framework private headers. Some drivers are accessing tz->device, that implies they need to have the knowledge of the thermal_zone_device structure but we want to self-encapsulate this structure and reduce the scope of the structure to the thermal core only. By adding this wrapper, these drivers won't need the thermal zone device structure definition and are no longer an obstacle to its relocation to the private thermal core headers. Signed-off-by: Daniel Lezcano Signed-off-by: Rafael J. Wysocki --- include/linux/thermal.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/thermal.h b/include/linux/thermal.h index 82ddb32f9876..87837094d549 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -313,6 +313,7 @@ thermal_zone_device_register_with_trips(const char *, struct thermal_trip *, int void *thermal_zone_device_priv(struct thermal_zone_device *tzd); 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_zone_bind_cooling_device(struct thermal_zone_device *, int, struct thermal_cooling_device *, -- cgit v1.2.3 From 4f20b7471c57032860065591a17efd3325216bde Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Fri, 21 Apr 2023 16:54:24 +0200 Subject: libgcc: add forward declarations for generic library routines With W=1 on platforms that use the generic gcc library routines (csky/loongarch/mips/riscv/sh/xtensa): lib/ashldi3.c:9:19: warning: no previous prototype for '__ashldi3' [-Wmissing-prototypes] 9 | long long notrace __ashldi3(long long u, word_type b) | ^~~~~~~~~ CC lib/ashrdi3.o lib/ashrdi3.c:9:19: warning: no previous prototype for '__ashrdi3' [-Wmissing-prototypes] 9 | long long notrace __ashrdi3(long long u, word_type b) | ^~~~~~~~~ CC lib/cmpdi2.o lib/cmpdi2.c:9:19: warning: no previous prototype for '__cmpdi2' [-Wmissing-prototypes] 9 | word_type notrace __cmpdi2(long long a, long long b) | ^~~~~~~~ CC lib/lshrdi3.o lib/lshrdi3.c:9:19: warning: no previous prototype for '__lshrdi3' [-Wmissing-prototypes] 9 | long long notrace __lshrdi3(long long u, word_type b) | ^~~~~~~~~ CC lib/muldi3.o lib/muldi3.c:49:19: warning: no previous prototype for '__muldi3' [-Wmissing-prototypes] 49 | long long notrace __muldi3(long long u, long long v) | ^~~~~~~~ CC lib/ucmpdi2.o lib/ucmpdi2.c:8:19: warning: no previous prototype for '__ucmpdi2' [-Wmissing-prototypes] 8 | word_type notrace __ucmpdi2(unsigned long long a, unsigned long long b) | ^~~~~~~~~ Fix this by adding forward declarations to the common libgcc header file. Link: https://lkml.kernel.org/r/5cdbe08296693dd53849f199c3933e16e97b33c1.1682088593.git.geert+renesas@glider.be Signed-off-by: Geert Uytterhoeven Reported-by: kernel test robot Link: https://lore.kernel.org/oe-kbuild-all/202303272214.RxzpA6bP-lkp@intel.com/ Acked-by: Arnd Bergmann Cc: Chris Zankel Cc: Max Filippov Signed-off-by: Andrew Morton --- include/linux/libgcc.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/libgcc.h b/include/linux/libgcc.h index b8dc75f0c830..fc388da6a027 100644 --- a/include/linux/libgcc.h +++ b/include/linux/libgcc.h @@ -27,4 +27,11 @@ typedef union { long long ll; } DWunion; +long long notrace __ashldi3(long long u, word_type b); +long long notrace __ashrdi3(long long u, word_type b); +word_type notrace __cmpdi2(long long a, long long b); +long long notrace __lshrdi3(long long u, word_type b); +long long notrace __muldi3(long long u, long long v); +word_type notrace __ucmpdi2(unsigned long long a, unsigned long long b); + #endif /* __ASM_LIBGCC_H */ -- cgit v1.2.3 From b3cbf98e2fdf3cb147a95161560cd25987284330 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Thu, 20 Apr 2023 13:56:24 -0400 Subject: SUNRPC: Support TLS handshake in the server-side TCP socket code This patch adds opportunitistic RPC-with-TLS to the Linux in-kernel NFS server. If the client requests RPC-with-TLS and the user space handshake agent is running, the server will set up a TLS session. There are no policy settings yet. For example, the server cannot yet require the use of RPC-with-TLS to access its data. Signed-off-by: Chuck Lever --- include/linux/sunrpc/svc_xprt.h | 5 ++++- include/linux/sunrpc/svcsock.h | 2 ++ 2 files changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc_xprt.h b/include/linux/sunrpc/svc_xprt.h index 775368802762..867479204840 100644 --- a/include/linux/sunrpc/svc_xprt.h +++ b/include/linux/sunrpc/svc_xprt.h @@ -27,7 +27,7 @@ struct svc_xprt_ops { void (*xpo_detach)(struct svc_xprt *); void (*xpo_free)(struct svc_xprt *); void (*xpo_kill_temp_xprt)(struct svc_xprt *); - void (*xpo_start_tls)(struct svc_xprt *); + void (*xpo_handshake)(struct svc_xprt *xprt); }; struct svc_xprt_class { @@ -70,6 +70,9 @@ struct svc_xprt { #define XPT_LOCAL 12 /* connection from loopback interface */ #define XPT_KILL_TEMP 13 /* call xpo_kill_temp_xprt before closing */ #define XPT_CONG_CTRL 14 /* has congestion control */ +#define XPT_HANDSHAKE 15 /* xprt requests a handshake */ +#define XPT_TLS_SESSION 16 /* transport-layer security established */ +#define XPT_PEER_AUTH 17 /* peer has been authenticated */ struct svc_serv *xpt_server; /* service for transport */ atomic_t xpt_reserved; /* space on outq that is rsvd */ diff --git a/include/linux/sunrpc/svcsock.h b/include/linux/sunrpc/svcsock.h index dd73fa174af5..d16ae621782c 100644 --- a/include/linux/sunrpc/svcsock.h +++ b/include/linux/sunrpc/svcsock.h @@ -38,6 +38,8 @@ struct svc_sock { /* Number of queued send requests */ atomic_t sk_sendqlen; + struct completion sk_handshake_done; + struct page * sk_pages[RPCSVC_MAXPAGES]; /* received data */ }; -- cgit v1.2.3 From 0c8862de05c1a087795ee0a87bf61a6394306cc0 Mon Sep 17 00:00:00 2001 From: Jarkko Sakkinen Date: Wed, 26 Apr 2023 21:49:37 +0300 Subject: tpm: Re-enable TPM chip boostrapping non-tpm_tis TPM drivers TPM chip bootstrapping was removed from tpm_chip_register(), and it was relocated to tpm_tis_core. This breaks all drivers which are not based on tpm_tis because the chip will not get properly initialized. Take the corrective steps: 1. Rename tpm_chip_startup() as tpm_chip_bootstrap() and make it one-shot. 2. Call tpm_chip_bootstrap() in tpm_chip_register(), which reverts the things as tehy used to be. Cc: Lino Sanfilippo Fixes: 548eb516ec0f ("tpm, tpm_tis: startup chip before testing for interrupts") Reported-by: Pengfei Xu Link: https://lore.kernel.org/all/ZEjqhwHWBnxcaRV5@xpf.sh.intel.com/ Tested-by: Pengfei Xu Signed-off-by: Jarkko Sakkinen --- include/linux/tpm.h | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tpm.h b/include/linux/tpm.h index 4dc97b9f65fb..77693389c3f9 100644 --- a/include/linux/tpm.h +++ b/include/linux/tpm.h @@ -274,13 +274,14 @@ enum tpm2_cc_attrs { #define TPM_VID_ATML 0x1114 enum tpm_chip_flags { - TPM_CHIP_FLAG_TPM2 = BIT(1), - TPM_CHIP_FLAG_IRQ = BIT(2), - TPM_CHIP_FLAG_VIRTUAL = BIT(3), - TPM_CHIP_FLAG_HAVE_TIMEOUTS = BIT(4), - TPM_CHIP_FLAG_ALWAYS_POWERED = BIT(5), + TPM_CHIP_FLAG_BOOTSTRAPPED = BIT(0), + TPM_CHIP_FLAG_TPM2 = BIT(1), + TPM_CHIP_FLAG_IRQ = BIT(2), + TPM_CHIP_FLAG_VIRTUAL = BIT(3), + TPM_CHIP_FLAG_HAVE_TIMEOUTS = BIT(4), + TPM_CHIP_FLAG_ALWAYS_POWERED = BIT(5), TPM_CHIP_FLAG_FIRMWARE_POWER_MANAGED = BIT(6), - TPM_CHIP_FLAG_FIRMWARE_UPGRADE = BIT(7), + TPM_CHIP_FLAG_FIRMWARE_UPGRADE = BIT(7), }; #define to_tpm_chip(d) container_of(d, struct tpm_chip, dev) -- cgit v1.2.3 From fbd2a05f29a95d5b42b294bf47e55a711424965b Mon Sep 17 00:00:00 2001 From: Anna Schumaker Date: Thu, 6 Apr 2023 15:16:52 -0400 Subject: NFSv4.2: Rework scratch handling for READ_PLUS Instead of using a tiny, static scratch buffer, we should use a kmalloc()-ed buffer that is allocated when checking for read plus usage. This lets us use the buffer before decoding any part of the READ_PLUS operation instead of setting it right before segment decoding, meaning it should be a little more robust. Signed-off-by: Anna Schumaker --- include/linux/nfs_xdr.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index e196ef595908..29a1b39794bf 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -670,6 +670,7 @@ struct nfs_pgio_res { struct { unsigned int replen; /* used by read */ int eof; /* used by read */ + void * scratch; /* used by read */ }; struct { struct nfs_writeverf * verf; /* used by write */ -- cgit v1.2.3 From e6ce9d741163af0b846637ce6550ae8a671b1588 Mon Sep 17 00:00:00 2001 From: Uros Bizjak Date: Wed, 5 Apr 2023 16:17:06 +0200 Subject: locking/atomic: Add generic try_cmpxchg{,64}_local() support Add generic support for try_cmpxchg{,64}_local() and their falbacks. These provides the generic try_cmpxchg_local family of functions from the arch_ prefixed version, also adding explicit instrumentation. Signed-off-by: Uros Bizjak Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Acked-by: Mark Rutland Link: https://lore.kernel.org/r/20230405141710.3551-2-ubizjak@gmail.com Cc: Linus Torvalds --- include/linux/atomic/atomic-arch-fallback.h | 24 +++++++++++++++++++++++- include/linux/atomic/atomic-instrumented.h | 20 +++++++++++++++++++- 2 files changed, 42 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/atomic/atomic-arch-fallback.h b/include/linux/atomic/atomic-arch-fallback.h index 4226379a232d..a6e4437c5f36 100644 --- a/include/linux/atomic/atomic-arch-fallback.h +++ b/include/linux/atomic/atomic-arch-fallback.h @@ -217,6 +217,28 @@ #endif /* arch_try_cmpxchg64_relaxed */ +#ifndef arch_try_cmpxchg_local +#define arch_try_cmpxchg_local(_ptr, _oldp, _new) \ +({ \ + typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \ + ___r = arch_cmpxchg_local((_ptr), ___o, (_new)); \ + if (unlikely(___r != ___o)) \ + *___op = ___r; \ + likely(___r == ___o); \ +}) +#endif /* arch_try_cmpxchg_local */ + +#ifndef arch_try_cmpxchg64_local +#define arch_try_cmpxchg64_local(_ptr, _oldp, _new) \ +({ \ + typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \ + ___r = arch_cmpxchg64_local((_ptr), ___o, (_new)); \ + if (unlikely(___r != ___o)) \ + *___op = ___r; \ + likely(___r == ___o); \ +}) +#endif /* arch_try_cmpxchg64_local */ + #ifndef arch_atomic_read_acquire static __always_inline int arch_atomic_read_acquire(const atomic_t *v) @@ -2646,4 +2668,4 @@ arch_atomic64_dec_if_positive(atomic64_t *v) #endif #endif /* _LINUX_ATOMIC_FALLBACK_H */ -// 00071fffa021cec66f6290d706d69c91df87bade +// ad2e2b4d168dbc60a73922616047a9bfa446af36 diff --git a/include/linux/atomic/atomic-instrumented.h b/include/linux/atomic/atomic-instrumented.h index 0496816738ca..245ba661c493 100644 --- a/include/linux/atomic/atomic-instrumented.h +++ b/include/linux/atomic/atomic-instrumented.h @@ -2132,6 +2132,24 @@ atomic_long_dec_if_positive(atomic_long_t *v) arch_sync_cmpxchg(__ai_ptr, __VA_ARGS__); \ }) +#define try_cmpxchg_local(ptr, oldp, ...) \ +({ \ + typeof(ptr) __ai_ptr = (ptr); \ + typeof(oldp) __ai_oldp = (oldp); \ + instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_atomic_write(__ai_oldp, sizeof(*__ai_oldp)); \ + arch_try_cmpxchg_local(__ai_ptr, __ai_oldp, __VA_ARGS__); \ +}) + +#define try_cmpxchg64_local(ptr, oldp, ...) \ +({ \ + typeof(ptr) __ai_ptr = (ptr); \ + typeof(oldp) __ai_oldp = (oldp); \ + instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_atomic_write(__ai_oldp, sizeof(*__ai_oldp)); \ + arch_try_cmpxchg64_local(__ai_ptr, __ai_oldp, __VA_ARGS__); \ +}) + #define cmpxchg_double(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ @@ -2149,4 +2167,4 @@ atomic_long_dec_if_positive(atomic_long_t *v) }) #endif /* _LINUX_ATOMIC_INSTRUMENTED_H */ -// 1b485de9cbaa4900de59e14ee2084357eaeb1c3a +// 97fe4d79aa058d2164df824632cbc4f716d2a407 -- cgit v1.2.3 From ec570320b09f76d52819e60abdccf372658216b6 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Thu, 13 Apr 2023 17:06:44 +0100 Subject: locking/atomic: Correct (cmp)xchg() instrumentation All xchg() and cmpxchg() ops are atomic RMWs, but currently we instrument these with instrument_atomic_write() rather than instrument_atomic_read_write(), missing the read aspect. Similarly, all try_cmpxchg() ops are non-atomic RMWs on *oldp, but we instrument these accesses with instrument_atomic_write() rather than instrument_read_write(), missing the read aspect and erroneously marking these as atomic. Fix the instrumentation for both points. Signed-off-by: Mark Rutland Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Link: https://lkml.kernel.org/r/20230413160644.490976-1-mark.rutland@arm.com Cc: Linus Torvalds --- include/linux/atomic/atomic-instrumented.h | 76 +++++++++++++++--------------- 1 file changed, 38 insertions(+), 38 deletions(-) (limited to 'include/linux') diff --git a/include/linux/atomic/atomic-instrumented.h b/include/linux/atomic/atomic-instrumented.h index 245ba661c493..03a232a1fa57 100644 --- a/include/linux/atomic/atomic-instrumented.h +++ b/include/linux/atomic/atomic-instrumented.h @@ -1948,14 +1948,14 @@ atomic_long_dec_if_positive(atomic_long_t *v) ({ \ typeof(ptr) __ai_ptr = (ptr); \ kcsan_mb(); \ - instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ arch_xchg(__ai_ptr, __VA_ARGS__); \ }) #define xchg_acquire(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ - instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ arch_xchg_acquire(__ai_ptr, __VA_ARGS__); \ }) @@ -1963,14 +1963,14 @@ atomic_long_dec_if_positive(atomic_long_t *v) ({ \ typeof(ptr) __ai_ptr = (ptr); \ kcsan_release(); \ - instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ arch_xchg_release(__ai_ptr, __VA_ARGS__); \ }) #define xchg_relaxed(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ - instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ arch_xchg_relaxed(__ai_ptr, __VA_ARGS__); \ }) @@ -1978,14 +1978,14 @@ atomic_long_dec_if_positive(atomic_long_t *v) ({ \ typeof(ptr) __ai_ptr = (ptr); \ kcsan_mb(); \ - instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ arch_cmpxchg(__ai_ptr, __VA_ARGS__); \ }) #define cmpxchg_acquire(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ - instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ arch_cmpxchg_acquire(__ai_ptr, __VA_ARGS__); \ }) @@ -1993,14 +1993,14 @@ atomic_long_dec_if_positive(atomic_long_t *v) ({ \ typeof(ptr) __ai_ptr = (ptr); \ kcsan_release(); \ - instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ arch_cmpxchg_release(__ai_ptr, __VA_ARGS__); \ }) #define cmpxchg_relaxed(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ - instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ arch_cmpxchg_relaxed(__ai_ptr, __VA_ARGS__); \ }) @@ -2008,14 +2008,14 @@ atomic_long_dec_if_positive(atomic_long_t *v) ({ \ typeof(ptr) __ai_ptr = (ptr); \ kcsan_mb(); \ - instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ arch_cmpxchg64(__ai_ptr, __VA_ARGS__); \ }) #define cmpxchg64_acquire(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ - instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ arch_cmpxchg64_acquire(__ai_ptr, __VA_ARGS__); \ }) @@ -2023,14 +2023,14 @@ atomic_long_dec_if_positive(atomic_long_t *v) ({ \ typeof(ptr) __ai_ptr = (ptr); \ kcsan_release(); \ - instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ arch_cmpxchg64_release(__ai_ptr, __VA_ARGS__); \ }) #define cmpxchg64_relaxed(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ - instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ arch_cmpxchg64_relaxed(__ai_ptr, __VA_ARGS__); \ }) @@ -2039,8 +2039,8 @@ atomic_long_dec_if_positive(atomic_long_t *v) typeof(ptr) __ai_ptr = (ptr); \ typeof(oldp) __ai_oldp = (oldp); \ kcsan_mb(); \ - instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ - instrument_atomic_write(__ai_oldp, sizeof(*__ai_oldp)); \ + instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \ arch_try_cmpxchg(__ai_ptr, __ai_oldp, __VA_ARGS__); \ }) @@ -2048,8 +2048,8 @@ atomic_long_dec_if_positive(atomic_long_t *v) ({ \ typeof(ptr) __ai_ptr = (ptr); \ typeof(oldp) __ai_oldp = (oldp); \ - instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ - instrument_atomic_write(__ai_oldp, sizeof(*__ai_oldp)); \ + instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \ arch_try_cmpxchg_acquire(__ai_ptr, __ai_oldp, __VA_ARGS__); \ }) @@ -2058,8 +2058,8 @@ atomic_long_dec_if_positive(atomic_long_t *v) typeof(ptr) __ai_ptr = (ptr); \ typeof(oldp) __ai_oldp = (oldp); \ kcsan_release(); \ - instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ - instrument_atomic_write(__ai_oldp, sizeof(*__ai_oldp)); \ + instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \ arch_try_cmpxchg_release(__ai_ptr, __ai_oldp, __VA_ARGS__); \ }) @@ -2067,8 +2067,8 @@ atomic_long_dec_if_positive(atomic_long_t *v) ({ \ typeof(ptr) __ai_ptr = (ptr); \ typeof(oldp) __ai_oldp = (oldp); \ - instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ - instrument_atomic_write(__ai_oldp, sizeof(*__ai_oldp)); \ + instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \ arch_try_cmpxchg_relaxed(__ai_ptr, __ai_oldp, __VA_ARGS__); \ }) @@ -2077,8 +2077,8 @@ atomic_long_dec_if_positive(atomic_long_t *v) typeof(ptr) __ai_ptr = (ptr); \ typeof(oldp) __ai_oldp = (oldp); \ kcsan_mb(); \ - instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ - instrument_atomic_write(__ai_oldp, sizeof(*__ai_oldp)); \ + instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \ arch_try_cmpxchg64(__ai_ptr, __ai_oldp, __VA_ARGS__); \ }) @@ -2086,8 +2086,8 @@ atomic_long_dec_if_positive(atomic_long_t *v) ({ \ typeof(ptr) __ai_ptr = (ptr); \ typeof(oldp) __ai_oldp = (oldp); \ - instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ - instrument_atomic_write(__ai_oldp, sizeof(*__ai_oldp)); \ + instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \ arch_try_cmpxchg64_acquire(__ai_ptr, __ai_oldp, __VA_ARGS__); \ }) @@ -2096,8 +2096,8 @@ atomic_long_dec_if_positive(atomic_long_t *v) typeof(ptr) __ai_ptr = (ptr); \ typeof(oldp) __ai_oldp = (oldp); \ kcsan_release(); \ - instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ - instrument_atomic_write(__ai_oldp, sizeof(*__ai_oldp)); \ + instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \ arch_try_cmpxchg64_release(__ai_ptr, __ai_oldp, __VA_ARGS__); \ }) @@ -2105,22 +2105,22 @@ atomic_long_dec_if_positive(atomic_long_t *v) ({ \ typeof(ptr) __ai_ptr = (ptr); \ typeof(oldp) __ai_oldp = (oldp); \ - instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ - instrument_atomic_write(__ai_oldp, sizeof(*__ai_oldp)); \ + instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \ arch_try_cmpxchg64_relaxed(__ai_ptr, __ai_oldp, __VA_ARGS__); \ }) #define cmpxchg_local(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ - instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ arch_cmpxchg_local(__ai_ptr, __VA_ARGS__); \ }) #define cmpxchg64_local(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ - instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ arch_cmpxchg64_local(__ai_ptr, __VA_ARGS__); \ }) @@ -2128,7 +2128,7 @@ atomic_long_dec_if_positive(atomic_long_t *v) ({ \ typeof(ptr) __ai_ptr = (ptr); \ kcsan_mb(); \ - instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ arch_sync_cmpxchg(__ai_ptr, __VA_ARGS__); \ }) @@ -2136,8 +2136,8 @@ atomic_long_dec_if_positive(atomic_long_t *v) ({ \ typeof(ptr) __ai_ptr = (ptr); \ typeof(oldp) __ai_oldp = (oldp); \ - instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ - instrument_atomic_write(__ai_oldp, sizeof(*__ai_oldp)); \ + instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \ arch_try_cmpxchg_local(__ai_ptr, __ai_oldp, __VA_ARGS__); \ }) @@ -2145,8 +2145,8 @@ atomic_long_dec_if_positive(atomic_long_t *v) ({ \ typeof(ptr) __ai_ptr = (ptr); \ typeof(oldp) __ai_oldp = (oldp); \ - instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ - instrument_atomic_write(__ai_oldp, sizeof(*__ai_oldp)); \ + instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \ arch_try_cmpxchg64_local(__ai_ptr, __ai_oldp, __VA_ARGS__); \ }) @@ -2154,7 +2154,7 @@ atomic_long_dec_if_positive(atomic_long_t *v) ({ \ typeof(ptr) __ai_ptr = (ptr); \ kcsan_mb(); \ - instrument_atomic_write(__ai_ptr, 2 * sizeof(*__ai_ptr)); \ + instrument_atomic_read_write(__ai_ptr, 2 * sizeof(*__ai_ptr)); \ arch_cmpxchg_double(__ai_ptr, __VA_ARGS__); \ }) @@ -2162,9 +2162,9 @@ atomic_long_dec_if_positive(atomic_long_t *v) #define cmpxchg_double_local(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ - instrument_atomic_write(__ai_ptr, 2 * sizeof(*__ai_ptr)); \ + instrument_atomic_read_write(__ai_ptr, 2 * sizeof(*__ai_ptr)); \ arch_cmpxchg_double_local(__ai_ptr, __VA_ARGS__); \ }) #endif /* _LINUX_ATOMIC_INSTRUMENTED_H */ -// 97fe4d79aa058d2164df824632cbc4f716d2a407 +// 6b513a42e1a1b5962532a019b7fc91eaa044ad5e -- cgit v1.2.3 From 24139c07f413ef4b555482c758343d71392a19bc Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Sat, 22 Apr 2023 22:54:18 +0200 Subject: mm/ksm: unmerge and clear VM_MERGEABLE when setting PR_SET_MEMORY_MERGE=0 Patch series "mm/ksm: improve PR_SET_MEMORY_MERGE=0 handling and cleanup disabling KSM", v2. (1) Make PR_SET_MEMORY_MERGE=0 unmerge pages like setting MADV_UNMERGEABLE does, (2) add a selftest for it and (3) factor out disabling of KSM from s390/gmap code. This patch (of 3): Let's unmerge any KSM pages when setting PR_SET_MEMORY_MERGE=0, and clear the VM_MERGEABLE flag from all VMAs -- just like KSM would. Of course, only do that if we previously set PR_SET_MEMORY_MERGE=1. Link: https://lkml.kernel.org/r/20230422205420.30372-1-david@redhat.com Link: https://lkml.kernel.org/r/20230422205420.30372-2-david@redhat.com Signed-off-by: David Hildenbrand Acked-by: Stefan Roesch Cc: Christian Borntraeger Cc: Claudio Imbrenda Cc: Heiko Carstens Cc: Janosch Frank Cc: Johannes Weiner Cc: Michal Hocko Cc: Rik van Riel Cc: Shuah Khan Cc: Sven Schnelle Cc: Vasily Gorbik Signed-off-by: Andrew Morton --- include/linux/ksm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/ksm.h b/include/linux/ksm.h index 7a9b76fb6c3f..429efa6ff4ae 100644 --- a/include/linux/ksm.h +++ b/include/linux/ksm.h @@ -21,6 +21,7 @@ int ksm_madvise(struct vm_area_struct *vma, unsigned long start, void ksm_add_vma(struct vm_area_struct *vma); int ksm_enable_merge_any(struct mm_struct *mm); +int ksm_disable_merge_any(struct mm_struct *mm); int __ksm_enter(struct mm_struct *mm); void __ksm_exit(struct mm_struct *mm); -- cgit v1.2.3 From 2c281f54f556e1f3266c8cb104adf9eea7a7b742 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Sat, 22 Apr 2023 23:01:56 +0200 Subject: mm/ksm: move disabling KSM from s390/gmap code to KSM code Let's factor out actual disabling of KSM. The existing "mm->def_flags &= ~VM_MERGEABLE;" was essentially a NOP and can be dropped, because def_flags should never include VM_MERGEABLE. Note that we don't currently prevent re-enabling KSM. This should now be faster in case KSM was never enabled, because we only conditionally iterate all VMAs. Further, it certainly looks cleaner. Link: https://lkml.kernel.org/r/20230422210156.33630-1-david@redhat.com Signed-off-by: David Hildenbrand Acked-by: Janosch Frank Acked-by: Stefan Roesch Cc: Christian Borntraeger Cc: Claudio Imbrenda Cc: Heiko Carstens Cc: Johannes Weiner Cc: Michal Hocko Cc: Rik van Riel Cc: Shuah Khan Cc: Sven Schnelle Cc: Vasily Gorbik Signed-off-by: Andrew Morton --- include/linux/ksm.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ksm.h b/include/linux/ksm.h index 429efa6ff4ae..899a314bc487 100644 --- a/include/linux/ksm.h +++ b/include/linux/ksm.h @@ -22,6 +22,7 @@ int ksm_madvise(struct vm_area_struct *vma, unsigned long start, void ksm_add_vma(struct vm_area_struct *vma); int ksm_enable_merge_any(struct mm_struct *mm); int ksm_disable_merge_any(struct mm_struct *mm); +int ksm_disable(struct mm_struct *mm); int __ksm_enter(struct mm_struct *mm); void __ksm_exit(struct mm_struct *mm); @@ -80,6 +81,11 @@ static inline void ksm_add_vma(struct vm_area_struct *vma) { } +static inline int ksm_disable(struct mm_struct *mm) +{ + return 0; +} + static inline int ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm) { return 0; -- cgit v1.2.3 From 245f0922689364b21163af4937a05ea0ba576fae Mon Sep 17 00:00:00 2001 From: Kefeng Wang Date: Mon, 17 Apr 2023 12:53:23 +0800 Subject: mm: hwpoison: coredump: support recovery from dump_user_range() dump_user_range() is used to copy the user page to a coredump file, but if a hardware memory error occurred during copy, which called from __kernel_write_iter() in dump_user_range(), it crashes, CPU: 112 PID: 7014 Comm: mca-recover Not tainted 6.3.0-rc2 #425 pc : __memcpy+0x110/0x260 lr : _copy_from_iter+0x3bc/0x4c8 ... Call trace: __memcpy+0x110/0x260 copy_page_from_iter+0xcc/0x130 pipe_write+0x164/0x6d8 __kernel_write_iter+0x9c/0x210 dump_user_range+0xc8/0x1d8 elf_core_dump+0x308/0x368 do_coredump+0x2e8/0xa40 get_signal+0x59c/0x788 do_signal+0x118/0x1f8 do_notify_resume+0xf0/0x280 el0_da+0x130/0x138 el0t_64_sync_handler+0x68/0xc0 el0t_64_sync+0x188/0x190 Generally, the '->write_iter' of file ops will use copy_page_from_iter() and copy_page_from_iter_atomic(), change memcpy() to copy_mc_to_kernel() in both of them to handle #MC during source read, which stop coredump processing and kill the task instead of kernel panic, but the source address may not always a user address, so introduce a new copy_mc flag in struct iov_iter{} to indicate that the iter could do a safe memory copy, also introduce the helpers to set/cleck the flag, for now, it's only used in coredump's dump_user_range(), but it could expand to any other scenarios to fix the similar issue. Link: https://lkml.kernel.org/r/20230417045323.11054-1-wangkefeng.wang@huawei.com Signed-off-by: Kefeng Wang Cc: Alexander Viro Cc: Christian Brauner Cc: Miaohe Lin Cc: Naoya Horiguchi Cc: Tong Tiangen Cc: Jens Axboe Signed-off-by: Andrew Morton --- include/linux/uio.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/uio.h b/include/linux/uio.h index 3d386849a758..044c1d8c230c 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -42,6 +42,7 @@ struct iov_iter_state { struct iov_iter { u8 iter_type; + bool copy_mc; bool nofault; bool data_source; bool user_backed; @@ -256,8 +257,22 @@ size_t _copy_from_iter_flushcache(void *addr, size_t bytes, struct iov_iter *i); #ifdef CONFIG_ARCH_HAS_COPY_MC size_t _copy_mc_to_iter(const void *addr, size_t bytes, struct iov_iter *i); +static inline void iov_iter_set_copy_mc(struct iov_iter *i) +{ + i->copy_mc = true; +} + +static inline bool iov_iter_is_copy_mc(const struct iov_iter *i) +{ + return i->copy_mc; +} #else #define _copy_mc_to_iter _copy_to_iter +static inline void iov_iter_set_copy_mc(struct iov_iter *i) { } +static inline bool iov_iter_is_copy_mc(const struct iov_iter *i) +{ + return false; +} #endif size_t iov_iter_zero(size_t bytes, struct iov_iter *); @@ -380,6 +395,7 @@ static inline void iov_iter_ubuf(struct iov_iter *i, unsigned int direction, WARN_ON(direction & ~(READ | WRITE)); *i = (struct iov_iter) { .iter_type = ITER_UBUF, + .copy_mc = false, .user_backed = true, .data_source = direction, .ubuf = buf, -- cgit v1.2.3 From 0199849acd07d07e2a8e42757653ca8b14a122f5 Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Tue, 2 May 2023 18:30:04 -0700 Subject: sysctl: remove register_sysctl_paths() The deprecation for register_sysctl_paths() is over. We can rejoice as we nuke register_sysctl_paths(). The routine register_sysctl_table() was the only user left of register_sysctl_paths(), so we can now just open code and move the implementation over to what used to be to __register_sysctl_paths(). The old dynamic struct ctl_table_set *set is now the point to sysctl_table_root.default_set. The old dynamic const struct ctl_path *path was being used in the routine register_sysctl_paths() with a static: static const struct ctl_path null_path[] = { {} }; Since this is a null path we can now just simplfy the old routine and remove its use as its always empty. This saves us a total of 230 bytes. $ ./scripts/bloat-o-meter vmlinux.old vmlinux add/remove: 2/7 grow/shrink: 1/1 up/down: 1015/-1245 (-230) Function old new delta register_leaf_sysctl_tables.constprop - 524 +524 register_sysctl_table 22 497 +475 __pfx_register_leaf_sysctl_tables.constprop - 16 +16 null_path 8 - -8 __pfx_register_sysctl_paths 16 - -16 __pfx_register_leaf_sysctl_tables 16 - -16 __pfx___register_sysctl_paths 16 - -16 __register_sysctl_base 29 12 -17 register_sysctl_paths 18 - -18 register_leaf_sysctl_tables 534 - -534 __register_sysctl_paths 620 - -620 Total: Before=21259666, After=21259436, chg -0.00% Signed-off-by: Luis Chamberlain --- include/linux/sysctl.h | 12 ------------ 1 file changed, 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index 780690dc08cd..3d08277959af 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -221,14 +221,8 @@ extern void retire_sysctl_set(struct ctl_table_set *set); struct ctl_table_header *__register_sysctl_table( struct ctl_table_set *set, const char *path, struct ctl_table *table); -struct ctl_table_header *__register_sysctl_paths( - struct ctl_table_set *set, - const struct ctl_path *path, struct ctl_table *table); struct ctl_table_header *register_sysctl(const char *path, struct ctl_table *table); struct ctl_table_header *register_sysctl_table(struct ctl_table * table); -struct ctl_table_header *register_sysctl_paths(const struct ctl_path *path, - struct ctl_table *table); - void unregister_sysctl_table(struct ctl_table_header * table); extern int sysctl_init_bases(void); @@ -277,12 +271,6 @@ static inline struct ctl_table_header *register_sysctl_mount_point(const char *p return NULL; } -static inline struct ctl_table_header *register_sysctl_paths( - const struct ctl_path *path, struct ctl_table *table) -{ - return NULL; -} - static inline struct ctl_table_header *register_sysctl(const char *path, struct ctl_table *table) { return NULL; -- cgit v1.2.3 From 5d388143fa6c351d985ffd23ea50c91c8839141b Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 3 Apr 2023 09:49:13 +0200 Subject: i2c: gxp: fix build failure without CONFIG_I2C_SLAVE The gxp_i2c_slave_irq_handler() is hidden in an #ifdef, but the caller uses an IS_ENABLED() check: drivers/i2c/busses/i2c-gxp.c: In function 'gxp_i2c_irq_handler': drivers/i2c/busses/i2c-gxp.c:467:29: error: implicit declaration of function 'gxp_i2c_slave_irq_handler'; did you mean 'gxp_i2c_irq_handler'? [-Werror=implicit-function-declaration] It has to consistently use one method or the other to avoid warnings, so move to IS_ENABLED() here for readability and build coverage, and move the #ifdef in linux/i2c.h to allow building it as dead code. Fixes: 4a55ed6f89f5 ("i2c: Add GXP SoC I2C Controller") Signed-off-by: Arnd Bergmann Reviewed-by: Nick Hawkins Signed-off-by: Wolfram Sang --- include/linux/i2c.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 5ba89663ea86..13a1ce38cb0c 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -385,7 +385,6 @@ static inline void i2c_set_clientdata(struct i2c_client *client, void *data) /* I2C slave support */ -#if IS_ENABLED(CONFIG_I2C_SLAVE) enum i2c_slave_event { I2C_SLAVE_READ_REQUESTED, I2C_SLAVE_WRITE_REQUESTED, @@ -396,9 +395,10 @@ enum i2c_slave_event { int i2c_slave_register(struct i2c_client *client, i2c_slave_cb_t slave_cb); int i2c_slave_unregister(struct i2c_client *client); -bool i2c_detect_slave_mode(struct device *dev); int i2c_slave_event(struct i2c_client *client, enum i2c_slave_event event, u8 *val); +#if IS_ENABLED(CONFIG_I2C_SLAVE) +bool i2c_detect_slave_mode(struct device *dev); #else static inline bool i2c_detect_slave_mode(struct device *dev) { return false; } #endif -- cgit v1.2.3 From fd9b8547bc5c34186dc42ea05fb4380d21695374 Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Thu, 4 May 2023 05:18:55 -0700 Subject: io_uring: Pass whole sqe to commands Currently uring CMD operation relies on having large SQEs, but future operations might want to use normal SQE. The io_uring_cmd currently only saves the payload (cmd) part of the SQE, but, for commands that use normal SQE size, it might be necessary to access the initial SQE fields outside of the payload/cmd block. So, saves the whole SQE other than just the pdu. This changes slightly how the io_uring_cmd works, since the cmd structures and callbacks are not opaque to io_uring anymore. I.e, the callbacks can look at the SQE entries, not only, in the cmd structure. The main advantage is that we don't need to create custom structures for simple commands. Creates io_uring_sqe_cmd() that returns the cmd private data as a null pointer and avoids casting in the callee side. Also, make most of ublk_drv's sqe->cmd priv structure into const, and use io_uring_sqe_cmd() to get the private structure, removing the unwanted cast. (There is one case where the cast is still needed since the header->{len,addr} is updated in the private structure) Suggested-by: Pavel Begunkov Signed-off-by: Breno Leitao Reviewed-by: Keith Busch Reviewed-by: Christoph Hellwig Reviewed-by: Pavel Begunkov Link: https://lore.kernel.org/r/20230504121856.904491-3-leitao@debian.org Signed-off-by: Jens Axboe --- include/linux/io_uring.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h index 35b9328ca335..3399d979ee1c 100644 --- a/include/linux/io_uring.h +++ b/include/linux/io_uring.h @@ -24,7 +24,7 @@ enum io_uring_cmd_flags { struct io_uring_cmd { struct file *file; - const void *cmd; + const struct io_uring_sqe *sqe; union { /* callback to defer completions to task context */ void (*task_work_cb)(struct io_uring_cmd *cmd, unsigned); @@ -66,6 +66,11 @@ static inline void io_uring_free(struct task_struct *tsk) if (tsk->io_uring) __io_uring_free(tsk); } + +static inline const void *io_uring_sqe_cmd(const struct io_uring_sqe *sqe) +{ + return sqe->cmd; +} #else static inline int io_uring_cmd_import_fixed(u64 ubuf, unsigned long len, int rw, struct iov_iter *iter, void *ioucmd) -- cgit v1.2.3 From 6ce2c04fcbcaa5eb086e5142ab359be306cbc3e1 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Google)" Date: Tue, 2 May 2023 21:32:33 -0400 Subject: ftrace: Add MODIFIED flag to show if IPMODIFY or direct was attached If a function had ever had IPMODIFY or DIRECT attached to it, where this is how live kernel patching and BPF overrides work, mark them and display an "M" in the enabled_functions and touched_functions files. This can be used for debugging. If a function had been modified and later there's a bug in the code related to that function, this can be used to know if the cause is possibly from a live kernel patch or a BPF program that changed the behavior of the code. Also update the documentation on the enabled_functions and touched_functions output, as it was missing direct callers and CALL_OPS. And include this new modify attribute. Link: https://lore.kernel.org/linux-trace-kernel/20230502213233.004e3ae4@gandalf.local.home Cc: Mark Rutland Acked-by: Masami Hiramatsu (Google) Signed-off-by: Steven Rostedt (Google) --- include/linux/ftrace.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 327046f1278d..7dffd740e784 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -549,6 +549,7 @@ bool is_ftrace_trampoline(unsigned long addr); * CALL_OPS - the record can use callsite-specific ops * CALL_OPS_EN - the function is set up to use callsite-specific ops * TOUCHED - A callback was added since boot up + * MODIFIED - The function had IPMODIFY or DIRECT attached to it * * When a new ftrace_ops is registered and wants a function to save * pt_regs, the rec->flags REGS is set. When the function has been @@ -569,9 +570,10 @@ enum { FTRACE_FL_CALL_OPS = (1UL << 22), FTRACE_FL_CALL_OPS_EN = (1UL << 21), FTRACE_FL_TOUCHED = (1UL << 20), + FTRACE_FL_MODIFIED = (1UL << 19), }; -#define FTRACE_REF_MAX_SHIFT 20 +#define FTRACE_REF_MAX_SHIFT 19 #define FTRACE_REF_MAX ((1UL << FTRACE_REF_MAX_SHIFT) - 1) #define ftrace_rec_count(rec) ((rec)->flags & FTRACE_REF_MAX) -- cgit v1.2.3