From 4d3ae294f900fb7232fb6c890dbd3176b8a5f121 Mon Sep 17 00:00:00 2001 From: Anton Protopopov Date: Fri, 13 Dec 2024 13:09:31 +0000 Subject: bpf: Add fd_array_cnt attribute for prog_load The fd_array attribute of the BPF_PROG_LOAD syscall may contain a set of file descriptors: maps or btfs. This field was introduced as a sparse array. Introduce a new attribute, fd_array_cnt, which, if present, indicates that the fd_array is a continuous array of the corresponding length. If fd_array_cnt is non-zero, then every map in the fd_array will be bound to the program, as if it was used by the program. This functionality is similar to the BPF_PROG_BIND_MAP syscall, but such maps can be used by the verifier during the program load. Signed-off-by: Anton Protopopov Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20241213130934.1087929-5-aspsk@isovalent.com --- kernel/bpf/syscall.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel/bpf/syscall.c') diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 5684e8ce132d..4e88797fdbeb 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -2730,7 +2730,7 @@ static bool is_perfmon_prog_type(enum bpf_prog_type prog_type) } /* last field in 'union bpf_attr' used by this command */ -#define BPF_PROG_LOAD_LAST_FIELD prog_token_fd +#define BPF_PROG_LOAD_LAST_FIELD fd_array_cnt static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) { -- cgit From 4b7e7cd1c105cc5881f4054805dfbb92aa24eb78 Mon Sep 17 00:00:00 2001 From: Hou Tao Date: Wed, 8 Jan 2025 09:07:22 +0800 Subject: bpf: Disable migration before calling ops->map_free() The freeing of all map elements may invoke bpf_obj_free_fields() to free the special fields in the map value. Since these special fields may be allocated from bpf memory allocator, migrate_{disable|enable} pairs are necessary for the freeing of these special fields. To simplify reasoning about when migrate_disable() is needed for the freeing of these special fields, let the caller to guarantee migration is disabled before invoking bpf_obj_free_fields(). Therefore, disabling migration before calling ops->map_free() to simplify the freeing of map values or special fields allocated from bpf memory allocator. After disabling migration in bpf_map_free(), there is no need for additional migration_{disable|enable} pairs in these ->map_free() callbacks. Remove these redundant invocations. The migrate_{disable|enable} pairs in the underlying implementation of bpf_obj_free_fields() will be removed by the following patch. Signed-off-by: Hou Tao Link: https://lore.kernel.org/r/20250108010728.207536-11-houtao@huaweicloud.com Signed-off-by: Alexei Starovoitov --- kernel/bpf/syscall.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'kernel/bpf/syscall.c') diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 4e88797fdbeb..5d2420492946 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -835,8 +835,14 @@ static void bpf_map_free(struct bpf_map *map) struct btf_record *rec = map->record; struct btf *btf = map->btf; - /* implementation dependent freeing */ + /* implementation dependent freeing. Disabling migration to simplify + * the free of values or special fields allocated from bpf memory + * allocator. + */ + migrate_disable(); map->ops->map_free(map); + migrate_enable(); + /* Delay freeing of btf_record for maps, as map_free * callback usually needs access to them. It is better to do it here * than require each callback to do the free itself manually. -- cgit From 1d2dbe7120e89090ed4f6be03d6fbadfbfff59bf Mon Sep 17 00:00:00 2001 From: Hou Tao Date: Wed, 8 Jan 2025 09:07:23 +0800 Subject: bpf: Remove migrate_{disable|enable} in bpf_obj_free_fields() The callers of bpf_obj_free_fields() have already guaranteed that the migration is disabled, therefore, there is no need to invoke migrate_{disable,enable} pair in bpf_obj_free_fields()'s underly implementation. This patch removes unnecessary migrate_{disable|enable} pairs from bpf_obj_free_fields() and its callees: bpf_list_head_free() and bpf_rb_root_free(). Signed-off-by: Hou Tao Link: https://lore.kernel.org/r/20250108010728.207536-12-houtao@huaweicloud.com Signed-off-by: Alexei Starovoitov --- kernel/bpf/syscall.c | 2 -- 1 file changed, 2 deletions(-) (limited to 'kernel/bpf/syscall.c') diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 5d2420492946..0daf098e3207 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -796,11 +796,9 @@ void bpf_obj_free_fields(const struct btf_record *rec, void *obj) if (!btf_is_kernel(field->kptr.btf)) { pointee_struct_meta = btf_find_struct_meta(field->kptr.btf, field->kptr.btf_id); - migrate_disable(); __bpf_obj_drop_impl(xchgd_field, pointee_struct_meta ? pointee_struct_meta->record : NULL, fields[i].type == BPF_KPTR_PERCPU); - migrate_enable(); } else { field->kptr.dtor(xchgd_field); } -- cgit From 1751f872cc97f992ed5c4c72c55588db1f0021e1 Mon Sep 17 00:00:00 2001 From: Joel Granados Date: Tue, 28 Jan 2025 13:48:37 +0100 Subject: treewide: const qualify ctl_tables where applicable Add the const qualifier to all the ctl_tables in the tree except for watchdog_hardlockup_sysctl, memory_allocation_profiling_sysctls, loadpin_sysctl_table and the ones calling register_net_sysctl (./net, drivers/inifiniband dirs). These are special cases as they use a registration function with a non-const qualified ctl_table argument or modify the arrays before passing them on to the registration function. Constifying ctl_table structs will prevent the modification of proc_handler function pointers as the arrays would reside in .rodata. This is made possible after commit 78eb4ea25cd5 ("sysctl: treewide: constify the ctl_table argument of proc_handlers") constified all the proc_handlers. Created this by running an spatch followed by a sed command: Spatch: virtual patch @ depends on !(file in "net") disable optional_qualifier @ identifier table_name != { watchdog_hardlockup_sysctl, iwcm_ctl_table, ucma_ctl_table, memory_allocation_profiling_sysctls, loadpin_sysctl_table }; @@ + const struct ctl_table table_name [] = { ... }; sed: sed --in-place \ -e "s/struct ctl_table .table = &uts_kern/const struct ctl_table *table = \&uts_kern/" \ kernel/utsname_sysctl.c Reviewed-by: Song Liu Acked-by: Steven Rostedt (Google) # for kernel/trace/ Reviewed-by: Martin K. Petersen # SCSI Reviewed-by: Darrick J. Wong # xfs Acked-by: Jani Nikula Acked-by: Corey Minyard Acked-by: Wei Liu Acked-by: Thomas Gleixner Reviewed-by: Bill O'Donnell Acked-by: Baoquan He Acked-by: Ashutosh Dixit Acked-by: Anna Schumaker Signed-off-by: Joel Granados --- kernel/bpf/syscall.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel/bpf/syscall.c') diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 0daf098e3207..c420edbfb7c8 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -6128,7 +6128,7 @@ static int bpf_unpriv_handler(const struct ctl_table *table, int write, return ret; } -static struct ctl_table bpf_syscall_table[] = { +static const struct ctl_table bpf_syscall_table[] = { { .procname = "unprivileged_bpf_disabled", .data = &sysctl_unprivileged_bpf_disabled, -- cgit