From ea70faa1f244ea0bd30f413e4ec7c79a3b5b96f1 Mon Sep 17 00:00:00 2001 From: Ihor Solodrai Date: Thu, 30 Jan 2025 12:12:35 -0800 Subject: docs/bpf: Document the semantics of BTF tags with kind_flag Explain the meaning of kind_flag in BTF type_tags and decl_tags. Update uapi btf.h kind_flag comment to reflect the changes. Signed-off-by: Ihor Solodrai Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20250130201239.1429648-3-ihor.solodrai@linux.dev --- include/uapi/linux/btf.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/btf.h b/include/uapi/linux/btf.h index ec1798b6d3ff..266d4ffa6c07 100644 --- a/include/uapi/linux/btf.h +++ b/include/uapi/linux/btf.h @@ -36,7 +36,8 @@ struct btf_type { * bits 24-28: kind (e.g. int, ptr, array...etc) * bits 29-30: unused * bit 31: kind_flag, currently used by - * struct, union, enum, fwd and enum64 + * struct, union, enum, fwd, enum64, + * decl_tag and type_tag */ __u32 info; /* "size" is used by INT, ENUM, STRUCT, UNION, DATASEC and ENUM64. -- cgit v1.2.3 From 0abff462d802a352c87b7f5e71b442b09bf9cfff Mon Sep 17 00:00:00 2001 From: Levi Zim Date: Tue, 4 Feb 2025 10:00:21 +0800 Subject: bpf: Add comment about helper freeze Put a comment after the bpf helper list in uapi bpf.h to prevent people from trying to add new helpers there and direct them to kfuncs. Suggested-by: Andrii Nakryiko Signed-off-by: Levi Zim Signed-off-by: Andrii Nakryiko Reviewed-by: Bagas Sanjaya Acked-by: Daniel Xu Link: https://lore.kernel.org/bpf/CAEf4BzZvQF+QQ=oip4vdz5A=9bd+OmN-CXk5YARYieaipK9s+A@mail.gmail.com/ Link: https://lore.kernel.org/bpf/20221231004213.h5fx3loccbs5hyzu@macbook-pro-6.dhcp.thefacebook.com/ Link: https://lore.kernel.org/bpf/20250204-bpf-helper-freeze-v1-1-46efd9ff20dc@outlook.com --- include/uapi/linux/bpf.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 2acf9b336371..fff6cdb8d11a 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -6019,7 +6019,10 @@ union bpf_attr { FN(user_ringbuf_drain, 209, ##ctx) \ FN(cgrp_storage_get, 210, ##ctx) \ FN(cgrp_storage_delete, 211, ##ctx) \ - /* */ + /* This helper list is effectively frozen. If you are trying to \ + * add a new helper, you should add a kfunc instead which has \ + * less stability guarantees. See Documentation/bpf/kfuncs.rst \ + */ /* backwards-compatibility macros for users of __BPF_FUNC_MAPPER that don't * know or care about integer value that is now passed as second argument -- cgit v1.2.3 From 531118f1ccfc209d6d100f338eed064636f6da9b Mon Sep 17 00:00:00 2001 From: Song Liu Date: Thu, 30 Jan 2025 13:35:45 -0800 Subject: fs/xattr: bpf: Introduce security.bpf. xattr name prefix Introduct new xattr name prefix security.bpf., and enable reading these xattrs from bpf kfuncs bpf_get_[file|dentry]_xattr(). As we are on it, correct the comments for return value of bpf_get_[file|dentry]_xattr(), i.e. return length the xattr value on success. Signed-off-by: Song Liu Acked-by: Christian Brauner Reviewed-by: Jan Kara Reviewed-by: Matt Bobrowski Link: https://lore.kernel.org/r/20250130213549.3353349-2-song@kernel.org Signed-off-by: Alexei Starovoitov --- fs/bpf_fs_kfuncs.c | 36 +++++++++++++++++++++++++----------- include/uapi/linux/xattr.h | 4 ++++ 2 files changed, 29 insertions(+), 11 deletions(-) (limited to 'include/uapi/linux') diff --git a/fs/bpf_fs_kfuncs.c b/fs/bpf_fs_kfuncs.c index 3fe9f59ef867..db5c8e855517 100644 --- a/fs/bpf_fs_kfuncs.c +++ b/fs/bpf_fs_kfuncs.c @@ -93,6 +93,24 @@ __bpf_kfunc int bpf_path_d_path(struct path *path, char *buf, size_t buf__sz) return len; } +static bool match_security_bpf_prefix(const char *name__str) +{ + return !strncmp(name__str, XATTR_NAME_BPF_LSM, XATTR_NAME_BPF_LSM_LEN); +} + +static int bpf_xattr_read_permission(const char *name, struct inode *inode) +{ + if (WARN_ON(!inode)) + return -EINVAL; + + /* Allow reading xattr with user. and security.bpf. prefix */ + if (strncmp(name, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN) && + !match_security_bpf_prefix(name)) + return -EPERM; + + return inode_permission(&nop_mnt_idmap, inode, MAY_READ); +} + /** * bpf_get_dentry_xattr - get xattr of a dentry * @dentry: dentry to get xattr from @@ -101,9 +119,10 @@ __bpf_kfunc int bpf_path_d_path(struct path *path, char *buf, size_t buf__sz) * * Get xattr *name__str* of *dentry* and store the output in *value_ptr*. * - * For security reasons, only *name__str* with prefix "user." is allowed. + * For security reasons, only *name__str* with prefixes "user." or + * "security.bpf." are allowed. * - * Return: 0 on success, a negative value on error. + * Return: length of the xattr value on success, a negative value on error. */ __bpf_kfunc int bpf_get_dentry_xattr(struct dentry *dentry, const char *name__str, struct bpf_dynptr *value_p) @@ -114,18 +133,12 @@ __bpf_kfunc int bpf_get_dentry_xattr(struct dentry *dentry, const char *name__st void *value; int ret; - if (WARN_ON(!inode)) - return -EINVAL; - - if (strncmp(name__str, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN)) - return -EPERM; - value_len = __bpf_dynptr_size(value_ptr); value = __bpf_dynptr_data_rw(value_ptr, value_len); if (!value) return -EINVAL; - ret = inode_permission(&nop_mnt_idmap, inode, MAY_READ); + ret = bpf_xattr_read_permission(name__str, inode); if (ret) return ret; return __vfs_getxattr(dentry, inode, name__str, value, value_len); @@ -139,9 +152,10 @@ __bpf_kfunc int bpf_get_dentry_xattr(struct dentry *dentry, const char *name__st * * Get xattr *name__str* of *file* and store the output in *value_ptr*. * - * For security reasons, only *name__str* with prefix "user." is allowed. + * For security reasons, only *name__str* with prefixes "user." or + * "security.bpf." are allowed. * - * Return: 0 on success, a negative value on error. + * Return: length of the xattr value on success, a negative value on error. */ __bpf_kfunc int bpf_get_file_xattr(struct file *file, const char *name__str, struct bpf_dynptr *value_p) diff --git a/include/uapi/linux/xattr.h b/include/uapi/linux/xattr.h index 9854f9cff3c6..c7c85bb504ba 100644 --- a/include/uapi/linux/xattr.h +++ b/include/uapi/linux/xattr.h @@ -83,6 +83,10 @@ struct xattr_args { #define XATTR_CAPS_SUFFIX "capability" #define XATTR_NAME_CAPS XATTR_SECURITY_PREFIX XATTR_CAPS_SUFFIX +#define XATTR_BPF_LSM_SUFFIX "bpf." +#define XATTR_NAME_BPF_LSM (XATTR_SECURITY_PREFIX XATTR_BPF_LSM_SUFFIX) +#define XATTR_NAME_BPF_LSM_LEN (sizeof(XATTR_NAME_BPF_LSM) - 1) + #define XATTR_POSIX_ACL_ACCESS "posix_acl_access" #define XATTR_NAME_POSIX_ACL_ACCESS XATTR_SYSTEM_PREFIX XATTR_POSIX_ACL_ACCESS #define XATTR_POSIX_ACL_DEFAULT "posix_acl_default" -- cgit v1.2.3 From 4b82b181a26cff8bf7adc3a85a88d121d92edeaf Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Mon, 24 Feb 2025 15:01:16 -0800 Subject: bpf: Allow pre-ordering for bpf cgroup progs Currently for bpf progs in a cgroup hierarchy, the effective prog array is computed from bottom cgroup to upper cgroups (post-ordering). For example, the following cgroup hierarchy root cgroup: p1, p2 subcgroup: p3, p4 have BPF_F_ALLOW_MULTI for both cgroup levels. The effective cgroup array ordering looks like p3 p4 p1 p2 and at run time, progs will execute based on that order. But in some cases, it is desirable to have root prog executes earlier than children progs (pre-ordering). For example, - prog p1 intends to collect original pkt dest addresses. - prog p3 will modify original pkt dest addresses to a proxy address for security reason. The end result is that prog p1 gets proxy address which is not what it wants. Putting p1 to every child cgroup is not desirable either as it will duplicate itself in many child cgroups. And this is exactly a use case we are encountering in Meta. To fix this issue, let us introduce a flag BPF_F_PREORDER. If the flag is specified at attachment time, the prog has higher priority and the ordering with that flag will be from top to bottom (pre-ordering). For example, in the above example, root cgroup: p1, p2 subcgroup: p3, p4 Let us say p2 and p4 are marked with BPF_F_PREORDER. The final effective array ordering will be p2 p4 p3 p1 Suggested-by: Andrii Nakryiko Acked-by: Andrii Nakryiko Signed-off-by: Yonghong Song Link: https://lore.kernel.org/r/20250224230116.283071-1-yonghong.song@linux.dev Signed-off-by: Alexei Starovoitov --- include/linux/bpf-cgroup.h | 1 + include/uapi/linux/bpf.h | 1 + kernel/bpf/cgroup.c | 33 +++++++++++++++++++++++++-------- kernel/bpf/syscall.c | 3 ++- tools/include/uapi/linux/bpf.h | 1 + 5 files changed, 30 insertions(+), 9 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index 7fc69083e745..9de7adb68294 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -111,6 +111,7 @@ struct bpf_prog_list { struct bpf_prog *prog; struct bpf_cgroup_link *link; struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE]; + u32 flags; }; int cgroup_bpf_inherit(struct cgroup *cgrp); diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index fff6cdb8d11a..beac5cdf2d2c 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1207,6 +1207,7 @@ enum bpf_perf_event_type { #define BPF_F_BEFORE (1U << 3) #define BPF_F_AFTER (1U << 4) #define BPF_F_ID (1U << 5) +#define BPF_F_PREORDER (1U << 6) #define BPF_F_LINK BPF_F_LINK /* 1 << 13 */ /* If BPF_F_STRICT_ALIGNMENT is used in BPF_PROG_LOAD command, the diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index 46e5db65dbc8..84f58f3d028a 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -369,7 +369,7 @@ static struct bpf_prog *prog_list_prog(struct bpf_prog_list *pl) /* count number of elements in the list. * it's slow but the list cannot be long */ -static u32 prog_list_length(struct hlist_head *head) +static u32 prog_list_length(struct hlist_head *head, int *preorder_cnt) { struct bpf_prog_list *pl; u32 cnt = 0; @@ -377,6 +377,8 @@ static u32 prog_list_length(struct hlist_head *head) hlist_for_each_entry(pl, head, node) { if (!prog_list_prog(pl)) continue; + if (preorder_cnt && (pl->flags & BPF_F_PREORDER)) + (*preorder_cnt)++; cnt++; } return cnt; @@ -400,7 +402,7 @@ static bool hierarchy_allows_attach(struct cgroup *cgrp, if (flags & BPF_F_ALLOW_MULTI) return true; - cnt = prog_list_length(&p->bpf.progs[atype]); + cnt = prog_list_length(&p->bpf.progs[atype], NULL); WARN_ON_ONCE(cnt > 1); if (cnt == 1) return !!(flags & BPF_F_ALLOW_OVERRIDE); @@ -423,12 +425,12 @@ static int compute_effective_progs(struct cgroup *cgrp, struct bpf_prog_array *progs; struct bpf_prog_list *pl; struct cgroup *p = cgrp; - int cnt = 0; + int i, j, cnt = 0, preorder_cnt = 0, fstart, bstart, init_bstart; /* count number of effective programs by walking parents */ do { if (cnt == 0 || (p->bpf.flags[atype] & BPF_F_ALLOW_MULTI)) - cnt += prog_list_length(&p->bpf.progs[atype]); + cnt += prog_list_length(&p->bpf.progs[atype], &preorder_cnt); p = cgroup_parent(p); } while (p); @@ -439,20 +441,34 @@ static int compute_effective_progs(struct cgroup *cgrp, /* populate the array with effective progs */ cnt = 0; p = cgrp; + fstart = preorder_cnt; + bstart = preorder_cnt - 1; do { if (cnt > 0 && !(p->bpf.flags[atype] & BPF_F_ALLOW_MULTI)) continue; + init_bstart = bstart; hlist_for_each_entry(pl, &p->bpf.progs[atype], node) { if (!prog_list_prog(pl)) continue; - item = &progs->items[cnt]; + if (pl->flags & BPF_F_PREORDER) { + item = &progs->items[bstart]; + bstart--; + } else { + item = &progs->items[fstart]; + fstart++; + } item->prog = prog_list_prog(pl); bpf_cgroup_storages_assign(item->cgroup_storage, pl->storage); cnt++; } + + /* reverse pre-ordering progs at this cgroup level */ + for (i = bstart + 1, j = init_bstart; i < j; i++, j--) + swap(progs->items[i], progs->items[j]); + } while ((p = cgroup_parent(p))); *array = progs; @@ -663,7 +679,7 @@ static int __cgroup_bpf_attach(struct cgroup *cgrp, */ return -EPERM; - if (prog_list_length(progs) >= BPF_CGROUP_MAX_PROGS) + if (prog_list_length(progs, NULL) >= BPF_CGROUP_MAX_PROGS) return -E2BIG; pl = find_attach_entry(progs, prog, link, replace_prog, @@ -698,6 +714,7 @@ static int __cgroup_bpf_attach(struct cgroup *cgrp, pl->prog = prog; pl->link = link; + pl->flags = flags; bpf_cgroup_storages_assign(pl->storage, storage); cgrp->bpf.flags[atype] = saved_flags; @@ -1073,7 +1090,7 @@ static int __cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr, lockdep_is_held(&cgroup_mutex)); total_cnt += bpf_prog_array_length(effective); } else { - total_cnt += prog_list_length(&cgrp->bpf.progs[atype]); + total_cnt += prog_list_length(&cgrp->bpf.progs[atype], NULL); } } @@ -1105,7 +1122,7 @@ static int __cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr, u32 id; progs = &cgrp->bpf.progs[atype]; - cnt = min_t(int, prog_list_length(progs), total_cnt); + cnt = min_t(int, prog_list_length(progs, NULL), total_cnt); i = 0; hlist_for_each_entry(pl, progs, node) { prog = prog_list_prog(pl); diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index dbd89c13dd32..d799fe8f568e 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -4170,7 +4170,8 @@ static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog, #define BPF_F_ATTACH_MASK_BASE \ (BPF_F_ALLOW_OVERRIDE | \ BPF_F_ALLOW_MULTI | \ - BPF_F_REPLACE) + BPF_F_REPLACE | \ + BPF_F_PREORDER) #define BPF_F_ATTACH_MASK_MPROG \ (BPF_F_REPLACE | \ diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index fff6cdb8d11a..beac5cdf2d2c 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1207,6 +1207,7 @@ enum bpf_perf_event_type { #define BPF_F_BEFORE (1U << 3) #define BPF_F_AFTER (1U << 4) #define BPF_F_ID (1U << 5) +#define BPF_F_PREORDER (1U << 6) #define BPF_F_LINK BPF_F_LINK /* 1 << 13 */ /* If BPF_F_STRICT_ALIGNMENT is used in BPF_PROG_LOAD command, the -- cgit v1.2.3 From 880442305a3908589bf4d6fc1d79edb577ee497c Mon Sep 17 00:00:00 2001 From: Peilin Ye Date: Tue, 4 Mar 2025 01:06:13 +0000 Subject: bpf: Introduce load-acquire and store-release instructions Introduce BPF instructions with load-acquire and store-release semantics, as discussed in [1]. Define 2 new flags: #define BPF_LOAD_ACQ 0x100 #define BPF_STORE_REL 0x110 A "load-acquire" is a BPF_STX | BPF_ATOMIC instruction with the 'imm' field set to BPF_LOAD_ACQ (0x100). Similarly, a "store-release" is a BPF_STX | BPF_ATOMIC instruction with the 'imm' field set to BPF_STORE_REL (0x110). Unlike existing atomic read-modify-write operations that only support BPF_W (32-bit) and BPF_DW (64-bit) size modifiers, load-acquires and store-releases also support BPF_B (8-bit) and BPF_H (16-bit). As an exception, however, 64-bit load-acquires/store-releases are not supported on 32-bit architectures (to fix a build error reported by the kernel test robot). An 8- or 16-bit load-acquire zero-extends the value before writing it to a 32-bit register, just like ARM64 instruction LDARH and friends. Similar to existing atomic read-modify-write operations, misaligned load-acquires/store-releases are not allowed (even if BPF_F_ANY_ALIGNMENT is set). As an example, consider the following 64-bit load-acquire BPF instruction (assuming little-endian): db 10 00 00 00 01 00 00 r0 = load_acquire((u64 *)(r1 + 0x0)) opcode (0xdb): BPF_ATOMIC | BPF_DW | BPF_STX imm (0x00000100): BPF_LOAD_ACQ Similarly, a 16-bit BPF store-release: cb 21 00 00 10 01 00 00 store_release((u16 *)(r1 + 0x0), w2) opcode (0xcb): BPF_ATOMIC | BPF_H | BPF_STX imm (0x00000110): BPF_STORE_REL In arch/{arm64,s390,x86}/net/bpf_jit_comp.c, have bpf_jit_supports_insn(..., /*in_arena=*/true) return false for the new instructions, until the corresponding JIT compiler supports them in arena. [1] https://lore.kernel.org/all/20240729183246.4110549-1-yepeilin@google.com/ Acked-by: Eduard Zingerman Acked-by: Ilya Leoshkevich Cc: kernel test robot Signed-off-by: Peilin Ye Link: https://lore.kernel.org/r/a217f46f0e445fbd573a1a024be5c6bf1d5fe716.1741049567.git.yepeilin@google.com Signed-off-by: Alexei Starovoitov --- arch/arm64/net/bpf_jit_comp.c | 4 +++ arch/s390/net/bpf_jit_comp.c | 14 ++++++--- arch/x86/net/bpf_jit_comp.c | 4 +++ include/linux/bpf.h | 15 ++++++++++ include/linux/filter.h | 2 ++ include/uapi/linux/bpf.h | 3 ++ kernel/bpf/core.c | 67 ++++++++++++++++++++++++++++++++++++++---- kernel/bpf/disasm.c | 12 ++++++++ kernel/bpf/verifier.c | 55 ++++++++++++++++++++++++++++++++-- tools/include/uapi/linux/bpf.h | 3 ++ 10 files changed, 166 insertions(+), 13 deletions(-) (limited to 'include/uapi/linux') diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index 7409c8acbde3..bdda5a77bb16 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -2667,8 +2667,12 @@ bool bpf_jit_supports_insn(struct bpf_insn *insn, bool in_arena) if (!in_arena) return true; switch (insn->code) { + case BPF_STX | BPF_ATOMIC | BPF_B: + case BPF_STX | BPF_ATOMIC | BPF_H: case BPF_STX | BPF_ATOMIC | BPF_W: case BPF_STX | BPF_ATOMIC | BPF_DW: + if (bpf_atomic_is_load_store(insn)) + return false; if (!cpus_have_cap(ARM64_HAS_LSE_ATOMICS)) return false; } diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c index 9d440a0b729e..0776dfde2dba 100644 --- a/arch/s390/net/bpf_jit_comp.c +++ b/arch/s390/net/bpf_jit_comp.c @@ -2919,10 +2919,16 @@ bool bpf_jit_supports_arena(void) bool bpf_jit_supports_insn(struct bpf_insn *insn, bool in_arena) { - /* - * Currently the verifier uses this function only to check which - * atomic stores to arena are supported, and they all are. - */ + if (!in_arena) + return true; + switch (insn->code) { + case BPF_STX | BPF_ATOMIC | BPF_B: + case BPF_STX | BPF_ATOMIC | BPF_H: + case BPF_STX | BPF_ATOMIC | BPF_W: + case BPF_STX | BPF_ATOMIC | BPF_DW: + if (bpf_atomic_is_load_store(insn)) + return false; + } return true; } diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index f3e9ef6b5329..fb541e3b1762 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -3771,8 +3771,12 @@ bool bpf_jit_supports_insn(struct bpf_insn *insn, bool in_arena) if (!in_arena) return true; switch (insn->code) { + case BPF_STX | BPF_ATOMIC | BPF_B: + case BPF_STX | BPF_ATOMIC | BPF_H: case BPF_STX | BPF_ATOMIC | BPF_W: case BPF_STX | BPF_ATOMIC | BPF_DW: + if (bpf_atomic_is_load_store(insn)) + return false; if (insn->imm == (BPF_AND | BPF_FETCH) || insn->imm == (BPF_OR | BPF_FETCH) || insn->imm == (BPF_XOR | BPF_FETCH)) diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 6af8b2db8b15..0d7b70124d81 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -991,6 +991,21 @@ static inline bool bpf_pseudo_func(const struct bpf_insn *insn) return bpf_is_ldimm64(insn) && insn->src_reg == BPF_PSEUDO_FUNC; } +/* Given a BPF_ATOMIC instruction @atomic_insn, return true if it is an + * atomic load or store, and false if it is a read-modify-write instruction. + */ +static inline bool +bpf_atomic_is_load_store(const struct bpf_insn *atomic_insn) +{ + switch (atomic_insn->imm) { + case BPF_LOAD_ACQ: + case BPF_STORE_REL: + return true; + default: + return false; + } +} + struct bpf_prog_ops { int (*test_run)(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); diff --git a/include/linux/filter.h b/include/linux/filter.h index 02dda5c53d91..590476743f7a 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -364,6 +364,8 @@ static inline bool insn_is_cast_user(const struct bpf_insn *insn) * BPF_XOR | BPF_FETCH src_reg = atomic_fetch_xor(dst_reg + off16, src_reg); * BPF_XCHG src_reg = atomic_xchg(dst_reg + off16, src_reg) * BPF_CMPXCHG r0 = atomic_cmpxchg(dst_reg + off16, r0, src_reg) + * BPF_LOAD_ACQ dst_reg = smp_load_acquire(src_reg + off16) + * BPF_STORE_REL smp_store_release(dst_reg + off16, src_reg) */ #define BPF_ATOMIC_OP(SIZE, OP, DST, SRC, OFF) \ diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index beac5cdf2d2c..bb37897c0393 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -51,6 +51,9 @@ #define BPF_XCHG (0xe0 | BPF_FETCH) /* atomic exchange */ #define BPF_CMPXCHG (0xf0 | BPF_FETCH) /* atomic compare-and-write */ +#define BPF_LOAD_ACQ 0x100 /* load-acquire */ +#define BPF_STORE_REL 0x110 /* store-release */ + enum bpf_cond_pseudo_jmp { BPF_MAY_GOTO = 0, }; diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index e583c19a0291..62cb9557ad3b 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -1663,14 +1663,17 @@ EXPORT_SYMBOL_GPL(__bpf_call_base); INSN_3(JMP, JSET, K), \ INSN_2(JMP, JA), \ INSN_2(JMP32, JA), \ + /* Atomic operations. */ \ + INSN_3(STX, ATOMIC, B), \ + INSN_3(STX, ATOMIC, H), \ + INSN_3(STX, ATOMIC, W), \ + INSN_3(STX, ATOMIC, DW), \ /* Store instructions. */ \ /* Register based. */ \ INSN_3(STX, MEM, B), \ INSN_3(STX, MEM, H), \ INSN_3(STX, MEM, W), \ INSN_3(STX, MEM, DW), \ - INSN_3(STX, ATOMIC, W), \ - INSN_3(STX, ATOMIC, DW), \ /* Immediate based. */ \ INSN_3(ST, MEM, B), \ INSN_3(ST, MEM, H), \ @@ -2152,24 +2155,33 @@ out: if (BPF_SIZE(insn->code) == BPF_W) \ atomic_##KOP((u32) SRC, (atomic_t *)(unsigned long) \ (DST + insn->off)); \ - else \ + else if (BPF_SIZE(insn->code) == BPF_DW) \ atomic64_##KOP((u64) SRC, (atomic64_t *)(unsigned long) \ (DST + insn->off)); \ + else \ + goto default_label; \ break; \ case BOP | BPF_FETCH: \ if (BPF_SIZE(insn->code) == BPF_W) \ SRC = (u32) atomic_fetch_##KOP( \ (u32) SRC, \ (atomic_t *)(unsigned long) (DST + insn->off)); \ - else \ + else if (BPF_SIZE(insn->code) == BPF_DW) \ SRC = (u64) atomic64_fetch_##KOP( \ (u64) SRC, \ (atomic64_t *)(unsigned long) (DST + insn->off)); \ + else \ + goto default_label; \ break; STX_ATOMIC_DW: STX_ATOMIC_W: + STX_ATOMIC_H: + STX_ATOMIC_B: switch (IMM) { + /* Atomic read-modify-write instructions support only W and DW + * size modifiers. + */ ATOMIC_ALU_OP(BPF_ADD, add) ATOMIC_ALU_OP(BPF_AND, and) ATOMIC_ALU_OP(BPF_OR, or) @@ -2181,20 +2193,63 @@ out: SRC = (u32) atomic_xchg( (atomic_t *)(unsigned long) (DST + insn->off), (u32) SRC); - else + else if (BPF_SIZE(insn->code) == BPF_DW) SRC = (u64) atomic64_xchg( (atomic64_t *)(unsigned long) (DST + insn->off), (u64) SRC); + else + goto default_label; break; case BPF_CMPXCHG: if (BPF_SIZE(insn->code) == BPF_W) BPF_R0 = (u32) atomic_cmpxchg( (atomic_t *)(unsigned long) (DST + insn->off), (u32) BPF_R0, (u32) SRC); - else + else if (BPF_SIZE(insn->code) == BPF_DW) BPF_R0 = (u64) atomic64_cmpxchg( (atomic64_t *)(unsigned long) (DST + insn->off), (u64) BPF_R0, (u64) SRC); + else + goto default_label; + break; + /* Atomic load and store instructions support all size + * modifiers. + */ + case BPF_LOAD_ACQ: + switch (BPF_SIZE(insn->code)) { +#define LOAD_ACQUIRE(SIZEOP, SIZE) \ + case BPF_##SIZEOP: \ + DST = (SIZE)smp_load_acquire( \ + (SIZE *)(unsigned long)(SRC + insn->off)); \ + break; + LOAD_ACQUIRE(B, u8) + LOAD_ACQUIRE(H, u16) + LOAD_ACQUIRE(W, u32) +#ifdef CONFIG_64BIT + LOAD_ACQUIRE(DW, u64) +#endif +#undef LOAD_ACQUIRE + default: + goto default_label; + } + break; + case BPF_STORE_REL: + switch (BPF_SIZE(insn->code)) { +#define STORE_RELEASE(SIZEOP, SIZE) \ + case BPF_##SIZEOP: \ + smp_store_release( \ + (SIZE *)(unsigned long)(DST + insn->off), (SIZE)SRC); \ + break; + STORE_RELEASE(B, u8) + STORE_RELEASE(H, u16) + STORE_RELEASE(W, u32) +#ifdef CONFIG_64BIT + STORE_RELEASE(DW, u64) +#endif +#undef STORE_RELEASE + default: + goto default_label; + } break; default: diff --git a/kernel/bpf/disasm.c b/kernel/bpf/disasm.c index 309c4aa1b026..974d172d6735 100644 --- a/kernel/bpf/disasm.c +++ b/kernel/bpf/disasm.c @@ -267,6 +267,18 @@ void print_bpf_insn(const struct bpf_insn_cbs *cbs, BPF_SIZE(insn->code) == BPF_DW ? "64" : "", bpf_ldst_string[BPF_SIZE(insn->code) >> 3], insn->dst_reg, insn->off, insn->src_reg); + } else if (BPF_MODE(insn->code) == BPF_ATOMIC && + insn->imm == BPF_LOAD_ACQ) { + verbose(cbs->private_data, "(%02x) r%d = load_acquire((%s *)(r%d %+d))\n", + insn->code, insn->dst_reg, + bpf_ldst_string[BPF_SIZE(insn->code) >> 3], + insn->src_reg, insn->off); + } else if (BPF_MODE(insn->code) == BPF_ATOMIC && + insn->imm == BPF_STORE_REL) { + verbose(cbs->private_data, "(%02x) store_release((%s *)(r%d %+d), r%d)\n", + insn->code, + bpf_ldst_string[BPF_SIZE(insn->code) >> 3], + insn->dst_reg, insn->off, insn->src_reg); } else { verbose(cbs->private_data, "BUG_%02x\n", insn->code); } diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 4ec1d1aa25ea..b6664d0f6914 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -579,6 +579,13 @@ static bool is_cmpxchg_insn(const struct bpf_insn *insn) insn->imm == BPF_CMPXCHG; } +static bool is_atomic_load_insn(const struct bpf_insn *insn) +{ + return BPF_CLASS(insn->code) == BPF_STX && + BPF_MODE(insn->code) == BPF_ATOMIC && + insn->imm == BPF_LOAD_ACQ; +} + static int __get_spi(s32 off) { return (-off - 1) / BPF_REG_SIZE; @@ -3567,7 +3574,7 @@ static bool is_reg64(struct bpf_verifier_env *env, struct bpf_insn *insn, } if (class == BPF_STX) { - /* BPF_STX (including atomic variants) has multiple source + /* BPF_STX (including atomic variants) has one or more source * operands, one of which is a ptr. Check whether the caller is * asking about it. */ @@ -4181,7 +4188,7 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx, * dreg still needs precision before this insn */ } - } else if (class == BPF_LDX) { + } else if (class == BPF_LDX || is_atomic_load_insn(insn)) { if (!bt_is_reg_set(bt, dreg)) return 0; bt_clear_reg(bt, dreg); @@ -7766,6 +7773,32 @@ static int check_atomic_rmw(struct bpf_verifier_env *env, return 0; } +static int check_atomic_load(struct bpf_verifier_env *env, + struct bpf_insn *insn) +{ + if (!atomic_ptr_type_ok(env, insn->src_reg, insn)) { + verbose(env, "BPF_ATOMIC loads from R%d %s is not allowed\n", + insn->src_reg, + reg_type_str(env, reg_state(env, insn->src_reg)->type)); + return -EACCES; + } + + return check_load_mem(env, insn, true, false, false, "atomic_load"); +} + +static int check_atomic_store(struct bpf_verifier_env *env, + struct bpf_insn *insn) +{ + if (!atomic_ptr_type_ok(env, insn->dst_reg, insn)) { + verbose(env, "BPF_ATOMIC stores into R%d %s is not allowed\n", + insn->dst_reg, + reg_type_str(env, reg_state(env, insn->dst_reg)->type)); + return -EACCES; + } + + return check_store_reg(env, insn, true); +} + static int check_atomic(struct bpf_verifier_env *env, struct bpf_insn *insn) { switch (insn->imm) { @@ -7780,6 +7813,20 @@ static int check_atomic(struct bpf_verifier_env *env, struct bpf_insn *insn) case BPF_XCHG: case BPF_CMPXCHG: return check_atomic_rmw(env, insn); + case BPF_LOAD_ACQ: + if (BPF_SIZE(insn->code) == BPF_DW && BITS_PER_LONG != 64) { + verbose(env, + "64-bit load-acquires are only supported on 64-bit arches\n"); + return -EOPNOTSUPP; + } + return check_atomic_load(env, insn); + case BPF_STORE_REL: + if (BPF_SIZE(insn->code) == BPF_DW && BITS_PER_LONG != 64) { + verbose(env, + "64-bit store-releases are only supported on 64-bit arches\n"); + return -EOPNOTSUPP; + } + return check_atomic_store(env, insn); default: verbose(env, "BPF_ATOMIC uses invalid atomic opcode %02x\n", insn->imm); @@ -20605,7 +20652,9 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) insn->code == (BPF_ST | BPF_MEM | BPF_W) || insn->code == (BPF_ST | BPF_MEM | BPF_DW)) { type = BPF_WRITE; - } else if ((insn->code == (BPF_STX | BPF_ATOMIC | BPF_W) || + } else if ((insn->code == (BPF_STX | BPF_ATOMIC | BPF_B) || + insn->code == (BPF_STX | BPF_ATOMIC | BPF_H) || + insn->code == (BPF_STX | BPF_ATOMIC | BPF_W) || insn->code == (BPF_STX | BPF_ATOMIC | BPF_DW)) && env->insn_aux_data[i + delta].ptr_type == PTR_TO_ARENA) { insn->code = BPF_STX | BPF_PROBE_ATOMIC | BPF_SIZE(insn->code); diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index beac5cdf2d2c..bb37897c0393 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -51,6 +51,9 @@ #define BPF_XCHG (0xe0 | BPF_FETCH) /* atomic exchange */ #define BPF_CMPXCHG (0xf0 | BPF_FETCH) /* atomic compare-and-write */ +#define BPF_LOAD_ACQ 0x100 /* load-acquire */ +#define BPF_STORE_REL 0x110 /* store-release */ + enum bpf_cond_pseudo_jmp { BPF_MAY_GOTO = 0, }; -- cgit v1.2.3 From 0de445d18e36ca5914337217c118016ba5db574d Mon Sep 17 00:00:00 2001 From: Mykyta Yatsenko Date: Mon, 17 Mar 2025 17:40:36 +0000 Subject: bpf: BPF token support for BPF_BTF_GET_FD_BY_ID Currently BPF_BTF_GET_FD_BY_ID requires CAP_SYS_ADMIN, which does not allow running it from user namespace. This creates a problem when freplace program running from user namespace needs to query target program BTF. This patch relaxes capable check from CAP_SYS_ADMIN to CAP_BPF and adds support for BPF token that can be passed in attributes to syscall. Signed-off-by: Mykyta Yatsenko Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20250317174039.161275-2-mykyta.yatsenko5@gmail.com --- include/uapi/linux/bpf.h | 1 + kernel/bpf/syscall.c | 23 +++++++++++++++++++++-- tools/include/uapi/linux/bpf.h | 1 + 3 files changed, 23 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index bb37897c0393..661de2444965 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1652,6 +1652,7 @@ union bpf_attr { }; __u32 next_id; __u32 open_flags; + __s32 fd_by_id_token_fd; }; struct { /* anonymous struct used by BPF_OBJ_GET_INFO_BY_FD */ diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 6a8f20ee2851..419f82c78203 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -5120,15 +5120,34 @@ static int bpf_btf_load(const union bpf_attr *attr, bpfptr_t uattr, __u32 uattr_ return btf_new_fd(attr, uattr, uattr_size); } -#define BPF_BTF_GET_FD_BY_ID_LAST_FIELD btf_id +#define BPF_BTF_GET_FD_BY_ID_LAST_FIELD fd_by_id_token_fd static int bpf_btf_get_fd_by_id(const union bpf_attr *attr) { + struct bpf_token *token = NULL; + if (CHECK_ATTR(BPF_BTF_GET_FD_BY_ID)) return -EINVAL; - if (!capable(CAP_SYS_ADMIN)) + if (attr->open_flags & ~BPF_F_TOKEN_FD) + return -EINVAL; + + if (attr->open_flags & BPF_F_TOKEN_FD) { + token = bpf_token_get_from_fd(attr->fd_by_id_token_fd); + if (IS_ERR(token)) + return PTR_ERR(token); + if (!bpf_token_allow_cmd(token, BPF_BTF_GET_FD_BY_ID)) { + bpf_token_put(token); + token = NULL; + } + } + + if (!bpf_token_capable(token, CAP_SYS_ADMIN)) { + bpf_token_put(token); return -EPERM; + } + + bpf_token_put(token); return btf_get_fd_by_id(attr->btf_id); } diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index bb37897c0393..661de2444965 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1652,6 +1652,7 @@ union bpf_attr { }; __u32 next_id; __u32 open_flags; + __s32 fd_by_id_token_fd; }; struct { /* anonymous struct used by BPF_OBJ_GET_INFO_BY_FD */ -- cgit v1.2.3