From 3f6719c7b62f0327c9091e26d0da10e65668229e Mon Sep 17 00:00:00 2001 From: KP Singh Date: Tue, 17 Nov 2020 23:29:28 +0000 Subject: bpf: Add bpf_bprm_opts_set helper The helper allows modification of certain bits on the linux_binprm struct starting with the secureexec bit which can be updated using the BPF_F_BPRM_SECUREEXEC flag. secureexec can be set by the LSM for privilege gaining executions to set the AT_SECURE auxv for glibc. When set, the dynamic linker disables the use of certain environment variables (like LD_PRELOAD). Signed-off-by: KP Singh Signed-off-by: Daniel Borkmann Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/20201117232929.2156341-1-kpsingh@chromium.org --- kernel/bpf/bpf_lsm.c | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) (limited to 'kernel') diff --git a/kernel/bpf/bpf_lsm.c b/kernel/bpf/bpf_lsm.c index 553107f4706a..b4f27a874092 100644 --- a/kernel/bpf/bpf_lsm.c +++ b/kernel/bpf/bpf_lsm.c @@ -7,6 +7,7 @@ #include #include #include +#include #include #include #include @@ -51,6 +52,29 @@ int bpf_lsm_verify_prog(struct bpf_verifier_log *vlog, return 0; } +/* Mask for all the currently supported BPRM option flags */ +#define BPF_F_BRPM_OPTS_MASK BPF_F_BPRM_SECUREEXEC + +BPF_CALL_2(bpf_bprm_opts_set, struct linux_binprm *, bprm, u64, flags) +{ + if (flags & ~BPF_F_BRPM_OPTS_MASK) + return -EINVAL; + + bprm->secureexec = (flags & BPF_F_BPRM_SECUREEXEC); + return 0; +} + +BTF_ID_LIST_SINGLE(bpf_bprm_opts_set_btf_ids, struct, linux_binprm) + +const static struct bpf_func_proto bpf_bprm_opts_set_proto = { + .func = bpf_bprm_opts_set, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_BTF_ID, + .arg1_btf_id = &bpf_bprm_opts_set_btf_ids[0], + .arg2_type = ARG_ANYTHING, +}; + static const struct bpf_func_proto * bpf_lsm_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { @@ -71,6 +95,8 @@ bpf_lsm_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_task_storage_get_proto; case BPF_FUNC_task_storage_delete: return &bpf_task_storage_delete_proto; + case BPF_FUNC_bprm_opts_set: + return &bpf_bprm_opts_set_proto; default: return tracing_prog_func_proto(func_id, prog); } -- cgit v1.2.3 From d055126180564a57fe533728a4e93d0cb53d49b3 Mon Sep 17 00:00:00 2001 From: Dmitrii Banshchikov Date: Tue, 17 Nov 2020 18:45:49 +0000 Subject: bpf: Add bpf_ktime_get_coarse_ns helper The helper uses CLOCK_MONOTONIC_COARSE source of time that is less accurate but more performant. We have a BPF CGROUP_SKB firewall that supports event logging through bpf_perf_event_output(). Each event has a timestamp and currently we use bpf_ktime_get_ns() for it. Use of bpf_ktime_get_coarse_ns() saves ~15-20 ns in time required for event logging. bpf_ktime_get_ns(): EgressLogByRemoteEndpoint 113.82ns 8.79M bpf_ktime_get_coarse_ns(): EgressLogByRemoteEndpoint 95.40ns 10.48M Signed-off-by: Dmitrii Banshchikov Signed-off-by: Daniel Borkmann Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/20201117184549.257280-1-me@ubique.spb.ru --- include/linux/bpf.h | 1 + include/uapi/linux/bpf.h | 11 +++++++++++ kernel/bpf/core.c | 1 + kernel/bpf/helpers.c | 13 +++++++++++++ kernel/trace/bpf_trace.c | 2 ++ tools/include/uapi/linux/bpf.h | 11 +++++++++++ 6 files changed, 39 insertions(+) (limited to 'kernel') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 581b2a2e78eb..e1bcb6d7345c 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1842,6 +1842,7 @@ extern const struct bpf_func_proto bpf_copy_from_user_proto; extern const struct bpf_func_proto bpf_snprintf_btf_proto; extern const struct bpf_func_proto bpf_per_cpu_ptr_proto; extern const struct bpf_func_proto bpf_this_cpu_ptr_proto; +extern const struct bpf_func_proto bpf_ktime_get_coarse_ns_proto; const struct bpf_func_proto *bpf_tracing_func_proto( enum bpf_func_id func_id, const struct bpf_prog *prog); diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index a52299b80b9d..3ca6146f001a 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -3797,6 +3797,16 @@ union bpf_attr { * is cleared if the flag is not specified. * Return * **-EINVAL** if invalid *flags* are passed, zero otherwise. + * + * u64 bpf_ktime_get_coarse_ns(void) + * Description + * Return a coarse-grained version of the time elapsed since + * system boot, in nanoseconds. Does not include time the system + * was suspended. + * + * See: **clock_gettime**\ (**CLOCK_MONOTONIC_COARSE**) + * Return + * Current *ktime*. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -3959,6 +3969,7 @@ union bpf_attr { FN(task_storage_delete), \ FN(get_current_task_btf), \ FN(bprm_opts_set), \ + FN(ktime_get_coarse_ns), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 55454d2278b1..ff55cbcfbab4 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -2211,6 +2211,7 @@ const struct bpf_func_proto bpf_get_smp_processor_id_proto __weak; const struct bpf_func_proto bpf_get_numa_node_id_proto __weak; const struct bpf_func_proto bpf_ktime_get_ns_proto __weak; const struct bpf_func_proto bpf_ktime_get_boot_ns_proto __weak; +const struct bpf_func_proto bpf_ktime_get_coarse_ns_proto __weak; const struct bpf_func_proto bpf_get_current_pid_tgid_proto __weak; const struct bpf_func_proto bpf_get_current_uid_gid_proto __weak; diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 25520f5eeaf6..2c395deae279 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -167,6 +167,17 @@ const struct bpf_func_proto bpf_ktime_get_boot_ns_proto = { .ret_type = RET_INTEGER, }; +BPF_CALL_0(bpf_ktime_get_coarse_ns) +{ + return ktime_get_coarse_ns(); +} + +const struct bpf_func_proto bpf_ktime_get_coarse_ns_proto = { + .func = bpf_ktime_get_coarse_ns, + .gpl_only = false, + .ret_type = RET_INTEGER, +}; + BPF_CALL_0(bpf_get_current_pid_tgid) { struct task_struct *task = current; @@ -685,6 +696,8 @@ bpf_base_func_proto(enum bpf_func_id func_id) return &bpf_ktime_get_ns_proto; case BPF_FUNC_ktime_get_boot_ns: return &bpf_ktime_get_boot_ns_proto; + case BPF_FUNC_ktime_get_coarse_ns: + return &bpf_ktime_get_coarse_ns_proto; case BPF_FUNC_ringbuf_output: return &bpf_ringbuf_output_proto; case BPF_FUNC_ringbuf_reserve: diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 02986c7b90eb..d255bc9b2bfa 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -1280,6 +1280,8 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_ktime_get_ns_proto; case BPF_FUNC_ktime_get_boot_ns: return &bpf_ktime_get_boot_ns_proto; + case BPF_FUNC_ktime_get_coarse_ns: + return &bpf_ktime_get_coarse_ns_proto; case BPF_FUNC_tail_call: return &bpf_tail_call_proto; case BPF_FUNC_get_current_pid_tgid: diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index a52299b80b9d..3ca6146f001a 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -3797,6 +3797,16 @@ union bpf_attr { * is cleared if the flag is not specified. * Return * **-EINVAL** if invalid *flags* are passed, zero otherwise. + * + * u64 bpf_ktime_get_coarse_ns(void) + * Description + * Return a coarse-grained version of the time elapsed since + * system boot, in nanoseconds. Does not include time the system + * was suspended. + * + * See: **clock_gettime**\ (**CLOCK_MONOTONIC_COARSE**) + * Return + * Current *ktime*. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -3959,6 +3969,7 @@ union bpf_attr { FN(task_storage_delete), \ FN(get_current_task_btf), \ FN(bprm_opts_set), \ + FN(ktime_get_coarse_ns), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper -- cgit v1.2.3 From 91b2db27d3ff9ad29e8b3108dfbf1e2f49fe9bd3 Mon Sep 17 00:00:00 2001 From: Song Liu Date: Thu, 19 Nov 2020 16:28:33 -0800 Subject: bpf: Simplify task_file_seq_get_next() Simplify task_file_seq_get_next() by removing two in/out arguments: task and fstruct. Use info->task and info->files instead. Signed-off-by: Song Liu Signed-off-by: Daniel Borkmann Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/20201120002833.2481110-1-songliubraving@fb.com --- kernel/bpf/task_iter.c | 54 ++++++++++++++++---------------------------------- 1 file changed, 17 insertions(+), 37 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/task_iter.c b/kernel/bpf/task_iter.c index 1fdb2fc196cd..0458a40edf10 100644 --- a/kernel/bpf/task_iter.c +++ b/kernel/bpf/task_iter.c @@ -136,8 +136,7 @@ struct bpf_iter_seq_task_file_info { }; static struct file * -task_file_seq_get_next(struct bpf_iter_seq_task_file_info *info, - struct task_struct **task, struct files_struct **fstruct) +task_file_seq_get_next(struct bpf_iter_seq_task_file_info *info) { struct pid_namespace *ns = info->common.ns; u32 curr_tid = info->tid, max_fds; @@ -150,14 +149,17 @@ task_file_seq_get_next(struct bpf_iter_seq_task_file_info *info, * Otherwise, it does not hold any reference. */ again: - if (*task) { - curr_task = *task; - curr_files = *fstruct; + if (info->task) { + curr_task = info->task; + curr_files = info->files; curr_fd = info->fd; } else { curr_task = task_seq_get_next(ns, &curr_tid, true); - if (!curr_task) + if (!curr_task) { + info->task = NULL; + info->files = NULL; return NULL; + } curr_files = get_files_struct(curr_task); if (!curr_files) { @@ -167,9 +169,8 @@ again: goto again; } - /* set *fstruct, *task and info->tid */ - *fstruct = curr_files; - *task = curr_task; + info->files = curr_files; + info->task = curr_task; if (curr_tid == info->tid) { curr_fd = info->fd; } else { @@ -199,8 +200,8 @@ again: rcu_read_unlock(); put_files_struct(curr_files); put_task_struct(curr_task); - *task = NULL; - *fstruct = NULL; + info->task = NULL; + info->files = NULL; info->fd = 0; curr_tid = ++(info->tid); goto again; @@ -209,21 +210,13 @@ again: static void *task_file_seq_start(struct seq_file *seq, loff_t *pos) { struct bpf_iter_seq_task_file_info *info = seq->private; - struct files_struct *files = NULL; - struct task_struct *task = NULL; struct file *file; - file = task_file_seq_get_next(info, &task, &files); - if (!file) { - info->files = NULL; - info->task = NULL; - return NULL; - } - - if (*pos == 0) + info->task = NULL; + info->files = NULL; + file = task_file_seq_get_next(info); + if (file && *pos == 0) ++*pos; - info->task = task; - info->files = files; return file; } @@ -231,24 +224,11 @@ static void *task_file_seq_start(struct seq_file *seq, loff_t *pos) static void *task_file_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct bpf_iter_seq_task_file_info *info = seq->private; - struct files_struct *files = info->files; - struct task_struct *task = info->task; - struct file *file; ++*pos; ++info->fd; fput((struct file *)v); - file = task_file_seq_get_next(info, &task, &files); - if (!file) { - info->files = NULL; - info->task = NULL; - return NULL; - } - - info->task = task; - info->files = files; - - return file; + return task_file_seq_get_next(info); } struct bpf_iter__task_file { -- cgit v1.2.3 From 607c543f939d8ca6fed7afe90b3a8d6f6684dd17 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Fri, 20 Nov 2020 23:08:29 -0800 Subject: bpf: Sanitize BTF data pointer after module is loaded Given .BTF section is not allocatable, it will get trimmed after module is loaded. BPF system handles that properly by creating an independent copy of data. But prevent any accidental misused by resetting the pointer to BTF data. Fixes: 36e68442d1af ("bpf: Load and verify kernel module BTFs") Suggested-by: Jessica Yu Signed-off-by: Andrii Nakryiko Signed-off-by: Daniel Borkmann Acked-by: Jessica Yu Cc: Greg Kroah-Hartman Link: https://lore.kernel.org/bpf/20201121070829.2612884-2-andrii@kernel.org --- kernel/module.c | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'kernel') diff --git a/kernel/module.c b/kernel/module.c index f2996b02ab2e..18f259d61d14 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -3709,6 +3709,11 @@ static noinline int do_init_module(struct module *mod) mod->init_layout.ro_size = 0; mod->init_layout.ro_after_init_size = 0; mod->init_layout.text_size = 0; +#ifdef CONFIG_DEBUG_INFO_BTF_MODULES + /* .BTF is not SHF_ALLOC and will get removed, so sanitize pointer */ + mod->btf_data = NULL; + mod->btf_data_size = 0; +#endif /* * We want to free module_init, but be aware that kallsyms may be * walking this with preempt disabled. In all the failure paths, we -- cgit v1.2.3 From 59e2e27d227a0a4e7ec0e22c63ca36a5ad1ab438 Mon Sep 17 00:00:00 2001 From: Wedson Almeida Filho Date: Sat, 21 Nov 2020 01:55:09 +0000 Subject: bpf: Refactor check_cfg to use a structured loop. The current implementation uses a number of gotos to implement a loop and different paths within the loop, which makes the code less readable than it would be with an explicit while-loop. This patch also replaces a chain of if/if-elses keyed on the same expression with a switch statement. No change in behaviour is intended. Signed-off-by: Wedson Almeida Filho Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20201121015509.3594191-1-wedsonaf@google.com --- kernel/bpf/verifier.c | 179 +++++++++++++++++++++++++++----------------------- 1 file changed, 95 insertions(+), 84 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index fb2943ea715d..e333ce43f281 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -8047,6 +8047,11 @@ static void init_explored_state(struct bpf_verifier_env *env, int idx) env->insn_aux_data[idx].prune_point = true; } +enum { + DONE_EXPLORING = 0, + KEEP_EXPLORING = 1, +}; + /* t, w, e - match pseudo-code above: * t - index of current instruction * w - next instruction @@ -8059,10 +8064,10 @@ static int push_insn(int t, int w, int e, struct bpf_verifier_env *env, int *insn_state = env->cfg.insn_state; if (e == FALLTHROUGH && insn_state[t] >= (DISCOVERED | FALLTHROUGH)) - return 0; + return DONE_EXPLORING; if (e == BRANCH && insn_state[t] >= (DISCOVERED | BRANCH)) - return 0; + return DONE_EXPLORING; if (w < 0 || w >= env->prog->len) { verbose_linfo(env, t, "%d: ", t); @@ -8081,10 +8086,10 @@ static int push_insn(int t, int w, int e, struct bpf_verifier_env *env, if (env->cfg.cur_stack >= env->prog->len) return -E2BIG; insn_stack[env->cfg.cur_stack++] = w; - return 1; + return KEEP_EXPLORING; } else if ((insn_state[w] & 0xF0) == DISCOVERED) { if (loop_ok && env->bpf_capable) - return 0; + return DONE_EXPLORING; verbose_linfo(env, t, "%d: ", t); verbose_linfo(env, w, "%d: ", w); verbose(env, "back-edge from insn %d to %d\n", t, w); @@ -8096,7 +8101,74 @@ static int push_insn(int t, int w, int e, struct bpf_verifier_env *env, verbose(env, "insn state internal bug\n"); return -EFAULT; } - return 0; + return DONE_EXPLORING; +} + +/* Visits the instruction at index t and returns one of the following: + * < 0 - an error occurred + * DONE_EXPLORING - the instruction was fully explored + * KEEP_EXPLORING - there is still work to be done before it is fully explored + */ +static int visit_insn(int t, int insn_cnt, struct bpf_verifier_env *env) +{ + struct bpf_insn *insns = env->prog->insnsi; + int ret; + + /* All non-branch instructions have a single fall-through edge. */ + if (BPF_CLASS(insns[t].code) != BPF_JMP && + BPF_CLASS(insns[t].code) != BPF_JMP32) + return push_insn(t, t + 1, FALLTHROUGH, env, false); + + switch (BPF_OP(insns[t].code)) { + case BPF_EXIT: + return DONE_EXPLORING; + + case BPF_CALL: + ret = push_insn(t, t + 1, FALLTHROUGH, env, false); + if (ret) + return ret; + + if (t + 1 < insn_cnt) + init_explored_state(env, t + 1); + if (insns[t].src_reg == BPF_PSEUDO_CALL) { + init_explored_state(env, t); + ret = push_insn(t, t + insns[t].imm + 1, BRANCH, + env, false); + } + return ret; + + case BPF_JA: + if (BPF_SRC(insns[t].code) != BPF_K) + return -EINVAL; + + /* unconditional jump with single edge */ + ret = push_insn(t, t + insns[t].off + 1, FALLTHROUGH, env, + true); + if (ret) + return ret; + + /* unconditional jmp is not a good pruning point, + * but it's marked, since backtracking needs + * to record jmp history in is_state_visited(). + */ + init_explored_state(env, t + insns[t].off + 1); + /* tell verifier to check for equivalent states + * after every call and jump + */ + if (t + 1 < insn_cnt) + init_explored_state(env, t + 1); + + return ret; + + default: + /* conditional jump with two edges */ + init_explored_state(env, t); + ret = push_insn(t, t + 1, FALLTHROUGH, env, true); + if (ret) + return ret; + + return push_insn(t, t + insns[t].off + 1, BRANCH, env, true); + } } /* non-recursive depth-first-search to detect loops in BPF program @@ -8104,11 +8176,10 @@ static int push_insn(int t, int w, int e, struct bpf_verifier_env *env, */ static int check_cfg(struct bpf_verifier_env *env) { - struct bpf_insn *insns = env->prog->insnsi; int insn_cnt = env->prog->len; int *insn_stack, *insn_state; int ret = 0; - int i, t; + int i; insn_state = env->cfg.insn_state = kvcalloc(insn_cnt, sizeof(int), GFP_KERNEL); if (!insn_state) @@ -8124,92 +8195,32 @@ static int check_cfg(struct bpf_verifier_env *env) insn_stack[0] = 0; /* 0 is the first instruction */ env->cfg.cur_stack = 1; -peek_stack: - if (env->cfg.cur_stack == 0) - goto check_state; - t = insn_stack[env->cfg.cur_stack - 1]; - - if (BPF_CLASS(insns[t].code) == BPF_JMP || - BPF_CLASS(insns[t].code) == BPF_JMP32) { - u8 opcode = BPF_OP(insns[t].code); - - if (opcode == BPF_EXIT) { - goto mark_explored; - } else if (opcode == BPF_CALL) { - ret = push_insn(t, t + 1, FALLTHROUGH, env, false); - if (ret == 1) - goto peek_stack; - else if (ret < 0) - goto err_free; - if (t + 1 < insn_cnt) - init_explored_state(env, t + 1); - if (insns[t].src_reg == BPF_PSEUDO_CALL) { - init_explored_state(env, t); - ret = push_insn(t, t + insns[t].imm + 1, BRANCH, - env, false); - if (ret == 1) - goto peek_stack; - else if (ret < 0) - goto err_free; - } - } else if (opcode == BPF_JA) { - if (BPF_SRC(insns[t].code) != BPF_K) { - ret = -EINVAL; - goto err_free; - } - /* unconditional jump with single edge */ - ret = push_insn(t, t + insns[t].off + 1, - FALLTHROUGH, env, true); - if (ret == 1) - goto peek_stack; - else if (ret < 0) - goto err_free; - /* unconditional jmp is not a good pruning point, - * but it's marked, since backtracking needs - * to record jmp history in is_state_visited(). - */ - init_explored_state(env, t + insns[t].off + 1); - /* tell verifier to check for equivalent states - * after every call and jump - */ - if (t + 1 < insn_cnt) - init_explored_state(env, t + 1); - } else { - /* conditional jump with two edges */ - init_explored_state(env, t); - ret = push_insn(t, t + 1, FALLTHROUGH, env, true); - if (ret == 1) - goto peek_stack; - else if (ret < 0) - goto err_free; + while (env->cfg.cur_stack > 0) { + int t = insn_stack[env->cfg.cur_stack - 1]; - ret = push_insn(t, t + insns[t].off + 1, BRANCH, env, true); - if (ret == 1) - goto peek_stack; - else if (ret < 0) - goto err_free; - } - } else { - /* all other non-branch instructions with single - * fall-through edge - */ - ret = push_insn(t, t + 1, FALLTHROUGH, env, false); - if (ret == 1) - goto peek_stack; - else if (ret < 0) + ret = visit_insn(t, insn_cnt, env); + switch (ret) { + case DONE_EXPLORING: + insn_state[t] = EXPLORED; + env->cfg.cur_stack--; + break; + case KEEP_EXPLORING: + break; + default: + if (ret > 0) { + verbose(env, "visit_insn internal bug\n"); + ret = -EFAULT; + } goto err_free; + } } -mark_explored: - insn_state[t] = EXPLORED; - if (env->cfg.cur_stack-- <= 0) { + if (env->cfg.cur_stack < 0) { verbose(env, "pop stack internal bug\n"); ret = -EFAULT; goto err_free; } - goto peek_stack; -check_state: for (i = 0; i < insn_cnt; i++) { if (insn_state[i] != EXPLORED) { verbose(env, "unreachable insn %d\n", i); -- cgit v1.2.3 From 27672f0d280a3f286a410a8db2004f46ace72a17 Mon Sep 17 00:00:00 2001 From: KP Singh Date: Tue, 24 Nov 2020 15:12:09 +0000 Subject: bpf: Add a BPF helper for getting the IMA hash of an inode Provide a wrapper function to get the IMA hash of an inode. This helper is useful in fingerprinting files (e.g executables on execution) and using these fingerprints in detections like an executable unlinking itself. Since the ima_inode_hash can sleep, it's only allowed for sleepable LSM hooks. Signed-off-by: KP Singh Signed-off-by: Daniel Borkmann Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/20201124151210.1081188-3-kpsingh@chromium.org --- include/uapi/linux/bpf.h | 11 +++++++++++ kernel/bpf/bpf_lsm.c | 26 ++++++++++++++++++++++++++ scripts/bpf_helpers_doc.py | 2 ++ tools/include/uapi/linux/bpf.h | 11 +++++++++++ 4 files changed, 50 insertions(+) (limited to 'kernel') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 3ca6146f001a..c3458ec1f30a 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -3807,6 +3807,16 @@ union bpf_attr { * See: **clock_gettime**\ (**CLOCK_MONOTONIC_COARSE**) * Return * Current *ktime*. + * + * long bpf_ima_inode_hash(struct inode *inode, void *dst, u32 size) + * Description + * Returns the stored IMA hash of the *inode* (if it's avaialable). + * If the hash is larger than *size*, then only *size* + * bytes will be copied to *dst* + * Return + * The **hash_algo** is returned on success, + * **-EOPNOTSUP** if IMA is disabled or **-EINVAL** if + * invalid arguments are passed. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -3970,6 +3980,7 @@ union bpf_attr { FN(get_current_task_btf), \ FN(bprm_opts_set), \ FN(ktime_get_coarse_ns), \ + FN(ima_inode_hash), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper diff --git a/kernel/bpf/bpf_lsm.c b/kernel/bpf/bpf_lsm.c index b4f27a874092..70e5e0b6d69d 100644 --- a/kernel/bpf/bpf_lsm.c +++ b/kernel/bpf/bpf_lsm.c @@ -15,6 +15,7 @@ #include #include #include +#include /* For every LSM hook that allows attachment of BPF programs, declare a nop * function where a BPF program can be attached. @@ -75,6 +76,29 @@ const static struct bpf_func_proto bpf_bprm_opts_set_proto = { .arg2_type = ARG_ANYTHING, }; +BPF_CALL_3(bpf_ima_inode_hash, struct inode *, inode, void *, dst, u32, size) +{ + return ima_inode_hash(inode, dst, size); +} + +static bool bpf_ima_inode_hash_allowed(const struct bpf_prog *prog) +{ + return bpf_lsm_is_sleepable_hook(prog->aux->attach_btf_id); +} + +BTF_ID_LIST_SINGLE(bpf_ima_inode_hash_btf_ids, struct, inode) + +const static struct bpf_func_proto bpf_ima_inode_hash_proto = { + .func = bpf_ima_inode_hash, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_BTF_ID, + .arg1_btf_id = &bpf_ima_inode_hash_btf_ids[0], + .arg2_type = ARG_PTR_TO_UNINIT_MEM, + .arg3_type = ARG_CONST_SIZE, + .allowed = bpf_ima_inode_hash_allowed, +}; + static const struct bpf_func_proto * bpf_lsm_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { @@ -97,6 +121,8 @@ bpf_lsm_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_task_storage_delete_proto; case BPF_FUNC_bprm_opts_set: return &bpf_bprm_opts_set_proto; + case BPF_FUNC_ima_inode_hash: + return prog->aux->sleepable ? &bpf_ima_inode_hash_proto : NULL; default: return tracing_prog_func_proto(func_id, prog); } diff --git a/scripts/bpf_helpers_doc.py b/scripts/bpf_helpers_doc.py index c5bc947a70ad..8b829748d488 100755 --- a/scripts/bpf_helpers_doc.py +++ b/scripts/bpf_helpers_doc.py @@ -436,6 +436,7 @@ class PrinterHelpers(Printer): 'struct xdp_md', 'struct path', 'struct btf_ptr', + 'struct inode', ] known_types = { '...', @@ -480,6 +481,7 @@ class PrinterHelpers(Printer): 'struct task_struct', 'struct path', 'struct btf_ptr', + 'struct inode', } mapped_types = { 'u8': '__u8', diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 3ca6146f001a..c3458ec1f30a 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -3807,6 +3807,16 @@ union bpf_attr { * See: **clock_gettime**\ (**CLOCK_MONOTONIC_COARSE**) * Return * Current *ktime*. + * + * long bpf_ima_inode_hash(struct inode *inode, void *dst, u32 size) + * Description + * Returns the stored IMA hash of the *inode* (if it's avaialable). + * If the hash is larger than *size*, then only *size* + * bytes will be copied to *dst* + * Return + * The **hash_algo** is returned on success, + * **-EOPNOTSUP** if IMA is disabled or **-EINVAL** if + * invalid arguments are passed. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -3970,6 +3980,7 @@ union bpf_attr { FN(get_current_task_btf), \ FN(bprm_opts_set), \ FN(ktime_get_coarse_ns), \ + FN(ima_inode_hash), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper -- cgit v1.2.3 From bcfe06bf2622f7c4899468e427683aec49070687 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Tue, 1 Dec 2020 13:58:27 -0800 Subject: mm: memcontrol: Use helpers to read page's memcg data Patch series "mm: allow mapping accounted kernel pages to userspace", v6. Currently a non-slab kernel page which has been charged to a memory cgroup can't be mapped to userspace. The underlying reason is simple: PageKmemcg flag is defined as a page type (like buddy, offline, etc), so it takes a bit from a page->mapped counter. Pages with a type set can't be mapped to userspace. But in general the kmemcg flag has nothing to do with mapping to userspace. It only means that the page has been accounted by the page allocator, so it has to be properly uncharged on release. Some bpf maps are mapping the vmalloc-based memory to userspace, and their memory can't be accounted because of this implementation detail. This patchset removes this limitation by moving the PageKmemcg flag into one of the free bits of the page->mem_cgroup pointer. Also it formalizes accesses to the page->mem_cgroup and page->obj_cgroups using new helpers, adds several checks and removes a couple of obsolete functions. As the result the code became more robust with fewer open-coded bit tricks. This patch (of 4): Currently there are many open-coded reads of the page->mem_cgroup pointer, as well as a couple of read helpers, which are barely used. It creates an obstacle on a way to reuse some bits of the pointer for storing additional bits of information. In fact, we already do this for slab pages, where the last bit indicates that a pointer has an attached vector of objcg pointers instead of a regular memcg pointer. This commits uses 2 existing helpers and introduces a new helper to converts all read sides to calls of these helpers: struct mem_cgroup *page_memcg(struct page *page); struct mem_cgroup *page_memcg_rcu(struct page *page); struct mem_cgroup *page_memcg_check(struct page *page); page_memcg_check() is intended to be used in cases when the page can be a slab page and have a memcg pointer pointing at objcg vector. It does check the lowest bit, and if set, returns NULL. page_memcg() contains a VM_BUG_ON_PAGE() check for the page not being a slab page. To make sure nobody uses a direct access, struct page's mem_cgroup/obj_cgroups is converted to unsigned long memcg_data. Signed-off-by: Roman Gushchin Signed-off-by: Andrew Morton Signed-off-by: Alexei Starovoitov Reviewed-by: Shakeel Butt Acked-by: Johannes Weiner Acked-by: Michal Hocko Link: https://lkml.kernel.org/r/20201027001657.3398190-1-guro@fb.com Link: https://lkml.kernel.org/r/20201027001657.3398190-2-guro@fb.com Link: https://lore.kernel.org/bpf/20201201215900.3569844-2-guro@fb.com --- fs/buffer.c | 2 +- fs/iomap/buffered-io.c | 2 +- include/linux/memcontrol.h | 114 +++++++++++++++++++++++++++++++++--- include/linux/mm.h | 22 ------- include/linux/mm_types.h | 5 +- include/trace/events/writeback.h | 2 +- kernel/fork.c | 7 ++- mm/debug.c | 4 +- mm/huge_memory.c | 4 +- mm/memcontrol.c | 121 ++++++++++++++++++--------------------- mm/page_alloc.c | 4 +- mm/page_io.c | 6 +- mm/slab.h | 9 ++- mm/workingset.c | 2 +- 14 files changed, 184 insertions(+), 120 deletions(-) (limited to 'kernel') diff --git a/fs/buffer.c b/fs/buffer.c index 23f645657488..b56f99f82b5b 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -657,7 +657,7 @@ int __set_page_dirty_buffers(struct page *page) } while (bh != head); } /* - * Lock out page->mem_cgroup migration to keep PageDirty + * Lock out page's memcg migration to keep PageDirty * synchronized with per-memcg dirty page counters. */ lock_page_memcg(page); diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index 10cc7979ce38..16a1e82e3aeb 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -650,7 +650,7 @@ iomap_set_page_dirty(struct page *page) return !TestSetPageDirty(page); /* - * Lock out page->mem_cgroup migration to keep PageDirty + * Lock out page's memcg migration to keep PageDirty * synchronized with per-memcg dirty page counters. */ lock_page_memcg(page); diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index e391e3c56de5..f95c1433461c 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -343,6 +343,79 @@ struct mem_cgroup { extern struct mem_cgroup *root_mem_cgroup; +/* + * page_memcg - get the memory cgroup associated with a page + * @page: a pointer to the page struct + * + * Returns a pointer to the memory cgroup associated with the page, + * or NULL. This function assumes that the page is known to have a + * proper memory cgroup pointer. It's not safe to call this function + * against some type of pages, e.g. slab pages or ex-slab pages. + * + * Any of the following ensures page and memcg binding stability: + * - the page lock + * - LRU isolation + * - lock_page_memcg() + * - exclusive reference + */ +static inline struct mem_cgroup *page_memcg(struct page *page) +{ + VM_BUG_ON_PAGE(PageSlab(page), page); + return (struct mem_cgroup *)page->memcg_data; +} + +/* + * page_memcg_rcu - locklessly get the memory cgroup associated with a page + * @page: a pointer to the page struct + * + * Returns a pointer to the memory cgroup associated with the page, + * or NULL. This function assumes that the page is known to have a + * proper memory cgroup pointer. It's not safe to call this function + * against some type of pages, e.g. slab pages or ex-slab pages. + */ +static inline struct mem_cgroup *page_memcg_rcu(struct page *page) +{ + VM_BUG_ON_PAGE(PageSlab(page), page); + WARN_ON_ONCE(!rcu_read_lock_held()); + + return (struct mem_cgroup *)READ_ONCE(page->memcg_data); +} + +/* + * page_memcg_check - get the memory cgroup associated with a page + * @page: a pointer to the page struct + * + * Returns a pointer to the memory cgroup associated with the page, + * or NULL. This function unlike page_memcg() can take any page + * as an argument. It has to be used in cases when it's not known if a page + * has an associated memory cgroup pointer or an object cgroups vector. + * + * Any of the following ensures page and memcg binding stability: + * - the page lock + * - LRU isolation + * - lock_page_memcg() + * - exclusive reference + */ +static inline struct mem_cgroup *page_memcg_check(struct page *page) +{ + /* + * Because page->memcg_data might be changed asynchronously + * for slab pages, READ_ONCE() should be used here. + */ + unsigned long memcg_data = READ_ONCE(page->memcg_data); + + /* + * The lowest bit set means that memcg isn't a valid + * memcg pointer, but a obj_cgroups pointer. + * In this case the page is shared and doesn't belong + * to any specific memory cgroup. + */ + if (memcg_data & 0x1UL) + return NULL; + + return (struct mem_cgroup *)memcg_data; +} + static __always_inline bool memcg_stat_item_in_bytes(int idx) { if (idx == MEMCG_PERCPU_B) @@ -743,15 +816,19 @@ static inline void mod_memcg_state(struct mem_cgroup *memcg, static inline void __mod_memcg_page_state(struct page *page, int idx, int val) { - if (page->mem_cgroup) - __mod_memcg_state(page->mem_cgroup, idx, val); + struct mem_cgroup *memcg = page_memcg(page); + + if (memcg) + __mod_memcg_state(memcg, idx, val); } static inline void mod_memcg_page_state(struct page *page, int idx, int val) { - if (page->mem_cgroup) - mod_memcg_state(page->mem_cgroup, idx, val); + struct mem_cgroup *memcg = page_memcg(page); + + if (memcg) + mod_memcg_state(memcg, idx, val); } static inline unsigned long lruvec_page_state(struct lruvec *lruvec, @@ -834,16 +911,17 @@ static inline void __mod_lruvec_page_state(struct page *page, enum node_stat_item idx, int val) { struct page *head = compound_head(page); /* rmap on tail pages */ + struct mem_cgroup *memcg = page_memcg(head); pg_data_t *pgdat = page_pgdat(page); struct lruvec *lruvec; /* Untracked pages have no memcg, no lruvec. Update only the node */ - if (!head->mem_cgroup) { + if (!memcg) { __mod_node_page_state(pgdat, idx, val); return; } - lruvec = mem_cgroup_lruvec(head->mem_cgroup, pgdat); + lruvec = mem_cgroup_lruvec(memcg, pgdat); __mod_lruvec_state(lruvec, idx, val); } @@ -878,8 +956,10 @@ static inline void count_memcg_events(struct mem_cgroup *memcg, static inline void count_memcg_page_event(struct page *page, enum vm_event_item idx) { - if (page->mem_cgroup) - count_memcg_events(page->mem_cgroup, idx, 1); + struct mem_cgroup *memcg = page_memcg(page); + + if (memcg) + count_memcg_events(memcg, idx, 1); } static inline void count_memcg_event_mm(struct mm_struct *mm, @@ -941,6 +1021,22 @@ void mem_cgroup_split_huge_fixup(struct page *head); struct mem_cgroup; +static inline struct mem_cgroup *page_memcg(struct page *page) +{ + return NULL; +} + +static inline struct mem_cgroup *page_memcg_rcu(struct page *page) +{ + WARN_ON_ONCE(!rcu_read_lock_held()); + return NULL; +} + +static inline struct mem_cgroup *page_memcg_check(struct page *page) +{ + return NULL; +} + static inline bool mem_cgroup_is_root(struct mem_cgroup *memcg) { return true; @@ -1430,7 +1526,7 @@ static inline void mem_cgroup_track_foreign_dirty(struct page *page, if (mem_cgroup_disabled()) return; - if (unlikely(&page->mem_cgroup->css != wb->memcg_css)) + if (unlikely(&page_memcg(page)->css != wb->memcg_css)) mem_cgroup_track_foreign_dirty_slowpath(page, wb); } diff --git a/include/linux/mm.h b/include/linux/mm.h index db6ae4d3fb4e..6b0c9d2c1d10 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1484,28 +1484,6 @@ static inline void set_page_links(struct page *page, enum zone_type zone, #endif } -#ifdef CONFIG_MEMCG -static inline struct mem_cgroup *page_memcg(struct page *page) -{ - return page->mem_cgroup; -} -static inline struct mem_cgroup *page_memcg_rcu(struct page *page) -{ - WARN_ON_ONCE(!rcu_read_lock_held()); - return READ_ONCE(page->mem_cgroup); -} -#else -static inline struct mem_cgroup *page_memcg(struct page *page) -{ - return NULL; -} -static inline struct mem_cgroup *page_memcg_rcu(struct page *page) -{ - WARN_ON_ONCE(!rcu_read_lock_held()); - return NULL; -} -#endif - /* * Some inline functions in vmstat.h depend on page_zone() */ diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 5a9238f6caad..80f5d755c037 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -199,10 +199,7 @@ struct page { atomic_t _refcount; #ifdef CONFIG_MEMCG - union { - struct mem_cgroup *mem_cgroup; - struct obj_cgroup **obj_cgroups; - }; + unsigned long memcg_data; #endif /* diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h index e7cbccc7c14c..39a40dfb578a 100644 --- a/include/trace/events/writeback.h +++ b/include/trace/events/writeback.h @@ -257,7 +257,7 @@ TRACE_EVENT(track_foreign_dirty, __entry->ino = inode ? inode->i_ino : 0; __entry->memcg_id = wb->memcg_css->id; __entry->cgroup_ino = __trace_wb_assign_cgroup(wb); - __entry->page_cgroup_ino = cgroup_ino(page->mem_cgroup->css.cgroup); + __entry->page_cgroup_ino = cgroup_ino(page_memcg(page)->css.cgroup); ), TP_printk("bdi %s[%llu]: ino=%lu memcg_id=%u cgroup_ino=%lu page_cgroup_ino=%lu", diff --git a/kernel/fork.c b/kernel/fork.c index 6d266388d380..cbd4f6f58409 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -404,9 +404,10 @@ static int memcg_charge_kernel_stack(struct task_struct *tsk) for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++) { /* - * If memcg_kmem_charge_page() fails, page->mem_cgroup - * pointer is NULL, and memcg_kmem_uncharge_page() in - * free_thread_stack() will ignore this page. + * If memcg_kmem_charge_page() fails, page's + * memory cgroup pointer is NULL, and + * memcg_kmem_uncharge_page() in free_thread_stack() + * will ignore this page. */ ret = memcg_kmem_charge_page(vm->pages[i], GFP_KERNEL, 0); diff --git a/mm/debug.c b/mm/debug.c index ccca576b2899..8a40b3fefbeb 100644 --- a/mm/debug.c +++ b/mm/debug.c @@ -182,8 +182,8 @@ hex_only: pr_warn("page dumped because: %s\n", reason); #ifdef CONFIG_MEMCG - if (!page_poisoned && page->mem_cgroup) - pr_warn("page->mem_cgroup:%px\n", page->mem_cgroup); + if (!page_poisoned && page->memcg_data) + pr_warn("pages's memcg:%lx\n", page->memcg_data); #endif } diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 9474dbc150ed..cedfb3503411 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -470,7 +470,7 @@ pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma) #ifdef CONFIG_MEMCG static inline struct deferred_split *get_deferred_split_queue(struct page *page) { - struct mem_cgroup *memcg = compound_head(page)->mem_cgroup; + struct mem_cgroup *memcg = page_memcg(compound_head(page)); struct pglist_data *pgdat = NODE_DATA(page_to_nid(page)); if (memcg) @@ -2765,7 +2765,7 @@ void deferred_split_huge_page(struct page *page) { struct deferred_split *ds_queue = get_deferred_split_queue(page); #ifdef CONFIG_MEMCG - struct mem_cgroup *memcg = compound_head(page)->mem_cgroup; + struct mem_cgroup *memcg = page_memcg(compound_head(page)); #endif unsigned long flags; diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 3dcbf24d2227..3968d68503cb 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -533,7 +533,7 @@ struct cgroup_subsys_state *mem_cgroup_css_from_page(struct page *page) { struct mem_cgroup *memcg; - memcg = page->mem_cgroup; + memcg = page_memcg(page); if (!memcg || !cgroup_subsys_on_dfl(memory_cgrp_subsys)) memcg = root_mem_cgroup; @@ -560,16 +560,7 @@ ino_t page_cgroup_ino(struct page *page) unsigned long ino = 0; rcu_read_lock(); - memcg = page->mem_cgroup; - - /* - * The lowest bit set means that memcg isn't a valid - * memcg pointer, but a obj_cgroups pointer. - * In this case the page is shared and doesn't belong - * to any specific memory cgroup. - */ - if ((unsigned long) memcg & 0x1UL) - memcg = NULL; + memcg = page_memcg_check(page); while (memcg && !(memcg->css.flags & CSS_ONLINE)) memcg = parent_mem_cgroup(memcg); @@ -1050,7 +1041,7 @@ EXPORT_SYMBOL(get_mem_cgroup_from_mm); */ struct mem_cgroup *get_mem_cgroup_from_page(struct page *page) { - struct mem_cgroup *memcg = page->mem_cgroup; + struct mem_cgroup *memcg = page_memcg(page); if (mem_cgroup_disabled()) return NULL; @@ -1349,7 +1340,7 @@ struct lruvec *mem_cgroup_page_lruvec(struct page *page, struct pglist_data *pgd goto out; } - memcg = page->mem_cgroup; + memcg = page_memcg(page); /* * Swapcache readahead pages are added to the LRU - and * possibly migrated - before they are charged. @@ -2109,7 +2100,7 @@ void mem_cgroup_print_oom_group(struct mem_cgroup *memcg) } /** - * lock_page_memcg - lock a page->mem_cgroup binding + * lock_page_memcg - lock a page and memcg binding * @page: the page * * This function protects unlocked LRU pages from being moved to @@ -2141,7 +2132,7 @@ struct mem_cgroup *lock_page_memcg(struct page *page) if (mem_cgroup_disabled()) return NULL; again: - memcg = head->mem_cgroup; + memcg = page_memcg(head); if (unlikely(!memcg)) return NULL; @@ -2149,7 +2140,7 @@ again: return memcg; spin_lock_irqsave(&memcg->move_lock, flags); - if (memcg != head->mem_cgroup) { + if (memcg != page_memcg(head)) { spin_unlock_irqrestore(&memcg->move_lock, flags); goto again; } @@ -2187,14 +2178,14 @@ void __unlock_page_memcg(struct mem_cgroup *memcg) } /** - * unlock_page_memcg - unlock a page->mem_cgroup binding + * unlock_page_memcg - unlock a page and memcg binding * @page: the page */ void unlock_page_memcg(struct page *page) { struct page *head = compound_head(page); - __unlock_page_memcg(head->mem_cgroup); + __unlock_page_memcg(page_memcg(head)); } EXPORT_SYMBOL(unlock_page_memcg); @@ -2884,7 +2875,7 @@ static void cancel_charge(struct mem_cgroup *memcg, unsigned int nr_pages) static void commit_charge(struct page *page, struct mem_cgroup *memcg) { - VM_BUG_ON_PAGE(page->mem_cgroup, page); + VM_BUG_ON_PAGE(page_memcg(page), page); /* * Any of the following ensures page->mem_cgroup stability: * @@ -2893,7 +2884,7 @@ static void commit_charge(struct page *page, struct mem_cgroup *memcg) * - lock_page_memcg() * - exclusive reference */ - page->mem_cgroup = memcg; + page->memcg_data = (unsigned long)memcg; } #ifdef CONFIG_MEMCG_KMEM @@ -2908,8 +2899,7 @@ int memcg_alloc_page_obj_cgroups(struct page *page, struct kmem_cache *s, if (!vec) return -ENOMEM; - if (cmpxchg(&page->obj_cgroups, NULL, - (struct obj_cgroup **) ((unsigned long)vec | 0x1UL))) + if (cmpxchg(&page->memcg_data, 0, (unsigned long)vec | 0x1UL)) kfree(vec); else kmemleak_not_leak(vec); @@ -2920,6 +2910,12 @@ int memcg_alloc_page_obj_cgroups(struct page *page, struct kmem_cache *s, /* * Returns a pointer to the memory cgroup to which the kernel object is charged. * + * A passed kernel object can be a slab object or a generic kernel page, so + * different mechanisms for getting the memory cgroup pointer should be used. + * In certain cases (e.g. kernel stacks or large kmallocs with SLUB) the caller + * can not know for sure how the kernel object is implemented. + * mem_cgroup_from_obj() can be safely used in such cases. + * * The caller must ensure the memcg lifetime, e.g. by taking rcu_read_lock(), * cgroup_mutex, etc. */ @@ -2932,17 +2928,6 @@ struct mem_cgroup *mem_cgroup_from_obj(void *p) page = virt_to_head_page(p); - /* - * If page->mem_cgroup is set, it's either a simple mem_cgroup pointer - * or a pointer to obj_cgroup vector. In the latter case the lowest - * bit of the pointer is set. - * The page->mem_cgroup pointer can be asynchronously changed - * from NULL to (obj_cgroup_vec | 0x1UL), but can't be changed - * from a valid memcg pointer to objcg vector or back. - */ - if (!page->mem_cgroup) - return NULL; - /* * Slab objects are accounted individually, not per-page. * Memcg membership data for each individual object is saved in @@ -2960,8 +2945,14 @@ struct mem_cgroup *mem_cgroup_from_obj(void *p) return NULL; } - /* All other pages use page->mem_cgroup */ - return page->mem_cgroup; + /* + * page_memcg_check() is used here, because page_has_obj_cgroups() + * check above could fail because the object cgroups vector wasn't set + * at that moment, but it can be set concurrently. + * page_memcg_check(page) will guarantee that a proper memory + * cgroup pointer or NULL will be returned. + */ + return page_memcg_check(page); } __always_inline struct obj_cgroup *get_obj_cgroup_from_current(void) @@ -3099,7 +3090,7 @@ int __memcg_kmem_charge_page(struct page *page, gfp_t gfp, int order) if (memcg && !mem_cgroup_is_root(memcg)) { ret = __memcg_kmem_charge(memcg, gfp, 1 << order); if (!ret) { - page->mem_cgroup = memcg; + page->memcg_data = (unsigned long)memcg; __SetPageKmemcg(page); return 0; } @@ -3115,7 +3106,7 @@ int __memcg_kmem_charge_page(struct page *page, gfp_t gfp, int order) */ void __memcg_kmem_uncharge_page(struct page *page, int order) { - struct mem_cgroup *memcg = page->mem_cgroup; + struct mem_cgroup *memcg = page_memcg(page); unsigned int nr_pages = 1 << order; if (!memcg) @@ -3123,7 +3114,7 @@ void __memcg_kmem_uncharge_page(struct page *page, int order) VM_BUG_ON_PAGE(mem_cgroup_is_root(memcg), page); __memcg_kmem_uncharge(memcg, nr_pages); - page->mem_cgroup = NULL; + page->memcg_data = 0; css_put(&memcg->css); /* slab pages do not have PageKmemcg flag set */ @@ -3274,7 +3265,7 @@ void obj_cgroup_uncharge(struct obj_cgroup *objcg, size_t size) */ void mem_cgroup_split_huge_fixup(struct page *head) { - struct mem_cgroup *memcg = head->mem_cgroup; + struct mem_cgroup *memcg = page_memcg(head); int i; if (mem_cgroup_disabled()) @@ -3282,7 +3273,7 @@ void mem_cgroup_split_huge_fixup(struct page *head) for (i = 1; i < HPAGE_PMD_NR; i++) { css_get(&memcg->css); - head[i].mem_cgroup = memcg; + head[i].memcg_data = (unsigned long)memcg; } } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ @@ -4664,7 +4655,7 @@ void mem_cgroup_wb_stats(struct bdi_writeback *wb, unsigned long *pfilepages, void mem_cgroup_track_foreign_dirty_slowpath(struct page *page, struct bdi_writeback *wb) { - struct mem_cgroup *memcg = page->mem_cgroup; + struct mem_cgroup *memcg = page_memcg(page); struct memcg_cgwb_frn *frn; u64 now = get_jiffies_64(); u64 oldest_at = now; @@ -5641,14 +5632,14 @@ static int mem_cgroup_move_account(struct page *page, /* * Prevent mem_cgroup_migrate() from looking at - * page->mem_cgroup of its source page while we change it. + * page's memory cgroup of its source page while we change it. */ ret = -EBUSY; if (!trylock_page(page)) goto out; ret = -EINVAL; - if (page->mem_cgroup != from) + if (page_memcg(page) != from) goto out_unlock; pgdat = page_pgdat(page); @@ -5703,13 +5694,13 @@ static int mem_cgroup_move_account(struct page *page, /* * All state has been migrated, let's switch to the new memcg. * - * It is safe to change page->mem_cgroup here because the page + * It is safe to change page's memcg here because the page * is referenced, charged, isolated, and locked: we can't race * with (un)charging, migration, LRU putback, or anything else - * that would rely on a stable page->mem_cgroup. + * that would rely on a stable page's memory cgroup. * * Note that lock_page_memcg is a memcg lock, not a page lock, - * to save space. As soon as we switch page->mem_cgroup to a + * to save space. As soon as we switch page's memory cgroup to a * new memcg that isn't locked, the above state can change * concurrently again. Make sure we're truly done with it. */ @@ -5718,7 +5709,7 @@ static int mem_cgroup_move_account(struct page *page, css_get(&to->css); css_put(&from->css); - page->mem_cgroup = to; + page->memcg_data = (unsigned long)to; __unlock_page_memcg(from); @@ -5784,7 +5775,7 @@ static enum mc_target_type get_mctgt_type(struct vm_area_struct *vma, * mem_cgroup_move_account() checks the page is valid or * not under LRU exclusion. */ - if (page->mem_cgroup == mc.from) { + if (page_memcg(page) == mc.from) { ret = MC_TARGET_PAGE; if (is_device_private_page(page)) ret = MC_TARGET_DEVICE; @@ -5828,7 +5819,7 @@ static enum mc_target_type get_mctgt_type_thp(struct vm_area_struct *vma, VM_BUG_ON_PAGE(!page || !PageHead(page), page); if (!(mc.flags & MOVE_ANON)) return ret; - if (page->mem_cgroup == mc.from) { + if (page_memcg(page) == mc.from) { ret = MC_TARGET_PAGE; if (target) { get_page(page); @@ -6774,12 +6765,12 @@ int mem_cgroup_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask) /* * Every swap fault against a single page tries to charge the * page, bail as early as possible. shmem_unuse() encounters - * already charged pages, too. page->mem_cgroup is protected - * by the page lock, which serializes swap cache removal, which - * in turn serializes uncharging. + * already charged pages, too. page and memcg binding is + * protected by the page lock, which serializes swap cache + * removal, which in turn serializes uncharging. */ VM_BUG_ON_PAGE(!PageLocked(page), page); - if (compound_head(page)->mem_cgroup) + if (page_memcg(compound_head(page))) goto out; id = lookup_swap_cgroup_id(ent); @@ -6863,21 +6854,21 @@ static void uncharge_page(struct page *page, struct uncharge_gather *ug) VM_BUG_ON_PAGE(PageLRU(page), page); - if (!page->mem_cgroup) + if (!page_memcg(page)) return; /* * Nobody should be changing or seriously looking at - * page->mem_cgroup at this point, we have fully + * page_memcg(page) at this point, we have fully * exclusive access to the page. */ - if (ug->memcg != page->mem_cgroup) { + if (ug->memcg != page_memcg(page)) { if (ug->memcg) { uncharge_batch(ug); uncharge_gather_clear(ug); } - ug->memcg = page->mem_cgroup; + ug->memcg = page_memcg(page); /* pairs with css_put in uncharge_batch */ css_get(&ug->memcg->css); @@ -6894,7 +6885,7 @@ static void uncharge_page(struct page *page, struct uncharge_gather *ug) } ug->dummy_page = page; - page->mem_cgroup = NULL; + page->memcg_data = 0; css_put(&ug->memcg->css); } @@ -6937,7 +6928,7 @@ void mem_cgroup_uncharge(struct page *page) return; /* Don't touch page->lru of any random page, pre-check: */ - if (!page->mem_cgroup) + if (!page_memcg(page)) return; uncharge_gather_clear(&ug); @@ -6987,11 +6978,11 @@ void mem_cgroup_migrate(struct page *oldpage, struct page *newpage) return; /* Page cache replacement: new page already charged? */ - if (newpage->mem_cgroup) + if (page_memcg(newpage)) return; /* Swapcache readahead pages can get replaced before being charged */ - memcg = oldpage->mem_cgroup; + memcg = page_memcg(oldpage); if (!memcg) return; @@ -7186,7 +7177,7 @@ void mem_cgroup_swapout(struct page *page, swp_entry_t entry) if (cgroup_subsys_on_dfl(memory_cgrp_subsys)) return; - memcg = page->mem_cgroup; + memcg = page_memcg(page); /* Readahead page, never charged */ if (!memcg) @@ -7207,7 +7198,7 @@ void mem_cgroup_swapout(struct page *page, swp_entry_t entry) VM_BUG_ON_PAGE(oldid, page); mod_memcg_state(swap_memcg, MEMCG_SWAP, nr_entries); - page->mem_cgroup = NULL; + page->memcg_data = 0; if (!mem_cgroup_is_root(memcg)) page_counter_uncharge(&memcg->memory, nr_entries); @@ -7250,7 +7241,7 @@ int mem_cgroup_try_charge_swap(struct page *page, swp_entry_t entry) if (!cgroup_subsys_on_dfl(memory_cgrp_subsys)) return 0; - memcg = page->mem_cgroup; + memcg = page_memcg(page); /* Readahead page, never charged */ if (!memcg) @@ -7331,7 +7322,7 @@ bool mem_cgroup_swap_full(struct page *page) if (cgroup_memory_noswap || !cgroup_subsys_on_dfl(memory_cgrp_subsys)) return false; - memcg = page->mem_cgroup; + memcg = page_memcg(page); if (!memcg) return false; diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 23f5066bd4a5..271133b8243b 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1092,7 +1092,7 @@ static inline bool page_expected_state(struct page *page, if (unlikely((unsigned long)page->mapping | page_ref_count(page) | #ifdef CONFIG_MEMCG - (unsigned long)page->mem_cgroup | + (unsigned long)page_memcg(page) | #endif (page->flags & check_flags))) return false; @@ -1117,7 +1117,7 @@ static const char *page_bad_reason(struct page *page, unsigned long flags) bad_reason = "PAGE_FLAGS_CHECK_AT_FREE flag(s) set"; } #ifdef CONFIG_MEMCG - if (unlikely(page->mem_cgroup)) + if (unlikely(page_memcg(page))) bad_reason = "page still charged to cgroup"; #endif return bad_reason; diff --git a/mm/page_io.c b/mm/page_io.c index 433df1263349..9bca17ecc4df 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -291,12 +291,14 @@ static inline void count_swpout_vm_event(struct page *page) static void bio_associate_blkg_from_page(struct bio *bio, struct page *page) { struct cgroup_subsys_state *css; + struct mem_cgroup *memcg; - if (!page->mem_cgroup) + memcg = page_memcg(page); + if (!memcg) return; rcu_read_lock(); - css = cgroup_e_css(page->mem_cgroup->css.cgroup, &io_cgrp_subsys); + css = cgroup_e_css(memcg->css.cgroup, &io_cgrp_subsys); bio_associate_blkg_from_css(bio, css); rcu_read_unlock(); } diff --git a/mm/slab.h b/mm/slab.h index 6d7c6a5056ba..e2535cee0d33 100644 --- a/mm/slab.h +++ b/mm/slab.h @@ -242,18 +242,17 @@ static inline bool kmem_cache_debug_flags(struct kmem_cache *s, slab_flags_t fla static inline struct obj_cgroup **page_obj_cgroups(struct page *page) { /* - * page->mem_cgroup and page->obj_cgroups are sharing the same + * Page's memory cgroup and obj_cgroups vector are sharing the same * space. To distinguish between them in case we don't know for sure * that the page is a slab page (e.g. page_cgroup_ino()), let's * always set the lowest bit of obj_cgroups. */ - return (struct obj_cgroup **) - ((unsigned long)page->obj_cgroups & ~0x1UL); + return (struct obj_cgroup **)(page->memcg_data & ~0x1UL); } static inline bool page_has_obj_cgroups(struct page *page) { - return ((unsigned long)page->obj_cgroups & 0x1UL); + return page->memcg_data & 0x1UL; } int memcg_alloc_page_obj_cgroups(struct page *page, struct kmem_cache *s, @@ -262,7 +261,7 @@ int memcg_alloc_page_obj_cgroups(struct page *page, struct kmem_cache *s, static inline void memcg_free_page_obj_cgroups(struct page *page) { kfree(page_obj_cgroups(page)); - page->obj_cgroups = NULL; + page->memcg_data = 0; } static inline size_t obj_full_size(struct kmem_cache *s) diff --git a/mm/workingset.c b/mm/workingset.c index 975a4d2dd02e..130348cbf40a 100644 --- a/mm/workingset.c +++ b/mm/workingset.c @@ -257,7 +257,7 @@ void *workingset_eviction(struct page *page, struct mem_cgroup *target_memcg) struct lruvec *lruvec; int memcgid; - /* Page is fully exclusive and pins page->mem_cgroup */ + /* Page is fully exclusive and pins page's memory cgroup pointer */ VM_BUG_ON_PAGE(PageLRU(page), page); VM_BUG_ON_PAGE(page_count(page), page); VM_BUG_ON_PAGE(!PageLocked(page), page); -- cgit v1.2.3 From ddf8503c7c434374a1112e89bcedfe1ccb3057df Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Tue, 1 Dec 2020 13:58:31 -0800 Subject: bpf: Memcg-based memory accounting for bpf progs Include memory used by bpf programs into the memcg-based accounting. This includes the memory used by programs itself, auxiliary data, statistics and bpf line info. A memory cgroup containing the process which loads the program is getting charged. Signed-off-by: Roman Gushchin Signed-off-by: Alexei Starovoitov Acked-by: Song Liu Link: https://lore.kernel.org/bpf/20201201215900.3569844-6-guro@fb.com --- kernel/bpf/core.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index ff55cbcfbab4..2921f58c03a8 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -77,7 +77,7 @@ void *bpf_internal_load_pointer_neg_helper(const struct sk_buff *skb, int k, uns struct bpf_prog *bpf_prog_alloc_no_stats(unsigned int size, gfp_t gfp_extra_flags) { - gfp_t gfp_flags = GFP_KERNEL | __GFP_ZERO | gfp_extra_flags; + gfp_t gfp_flags = GFP_KERNEL_ACCOUNT | __GFP_ZERO | gfp_extra_flags; struct bpf_prog_aux *aux; struct bpf_prog *fp; @@ -86,7 +86,7 @@ struct bpf_prog *bpf_prog_alloc_no_stats(unsigned int size, gfp_t gfp_extra_flag if (fp == NULL) return NULL; - aux = kzalloc(sizeof(*aux), GFP_KERNEL | gfp_extra_flags); + aux = kzalloc(sizeof(*aux), GFP_KERNEL_ACCOUNT | gfp_extra_flags); if (aux == NULL) { vfree(fp); return NULL; @@ -106,7 +106,7 @@ struct bpf_prog *bpf_prog_alloc_no_stats(unsigned int size, gfp_t gfp_extra_flag struct bpf_prog *bpf_prog_alloc(unsigned int size, gfp_t gfp_extra_flags) { - gfp_t gfp_flags = GFP_KERNEL | __GFP_ZERO | gfp_extra_flags; + gfp_t gfp_flags = GFP_KERNEL_ACCOUNT | __GFP_ZERO | gfp_extra_flags; struct bpf_prog *prog; int cpu; @@ -138,7 +138,7 @@ int bpf_prog_alloc_jited_linfo(struct bpf_prog *prog) prog->aux->jited_linfo = kcalloc(prog->aux->nr_linfo, sizeof(*prog->aux->jited_linfo), - GFP_KERNEL | __GFP_NOWARN); + GFP_KERNEL_ACCOUNT | __GFP_NOWARN); if (!prog->aux->jited_linfo) return -ENOMEM; @@ -219,7 +219,7 @@ void bpf_prog_free_linfo(struct bpf_prog *prog) struct bpf_prog *bpf_prog_realloc(struct bpf_prog *fp_old, unsigned int size, gfp_t gfp_extra_flags) { - gfp_t gfp_flags = GFP_KERNEL | __GFP_ZERO | gfp_extra_flags; + gfp_t gfp_flags = GFP_KERNEL_ACCOUNT | __GFP_ZERO | gfp_extra_flags; struct bpf_prog *fp; u32 pages, delta; int ret; -- cgit v1.2.3 From 48edc1f78aabeba35ed00e40c36f211de89e0090 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Tue, 1 Dec 2020 13:58:32 -0800 Subject: bpf: Prepare for memcg-based memory accounting for bpf maps Bpf maps can be updated from an interrupt context and in such case there is no process which can be charged. It makes the memory accounting of bpf maps non-trivial. Fortunately, after commit 4127c6504f25 ("mm: kmem: enable kernel memcg accounting from interrupt contexts") and commit b87d8cefe43c ("mm, memcg: rework remote charging API to support nesting") it's finally possible. To make the ownership model simple and consistent, when the map is created, the memory cgroup of the current process is recorded. All subsequent allocations related to the bpf map are charged to the same memory cgroup. It includes allocations made by any processes (even if they do belong to a different cgroup) and from interrupts. This commit introduces 3 new helpers, which will be used by following commits to enable the accounting of bpf maps memory: - bpf_map_kmalloc_node() - bpf_map_kzalloc() - bpf_map_alloc_percpu() They are wrapping popular memory allocation functions. They set the active memory cgroup to the map's memory cgroup and add __GFP_ACCOUNT to the passed gfp flags. Then they call into the corresponding memory allocation function and restore the original active memory cgroup. These helpers are supposed to use everywhere except the map creation path. During the map creation when the map structure is allocated by itself, it cannot be passed to those helpers. In those cases default memory allocation function will be used with the __GFP_ACCOUNT flag. Signed-off-by: Roman Gushchin Acked-by: Daniel Borkmann Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20201201215900.3569844-7-guro@fb.com --- include/linux/bpf.h | 34 ++++++++++++++++++++++++++++ kernel/bpf/syscall.c | 63 ++++++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 97 insertions(+) (limited to 'kernel') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index e1bcb6d7345c..e1f2c95c15ec 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -20,6 +20,8 @@ #include #include #include +#include +#include struct bpf_verifier_env; struct bpf_verifier_log; @@ -37,6 +39,7 @@ struct bpf_iter_aux_info; struct bpf_local_storage; struct bpf_local_storage_map; struct kobject; +struct mem_cgroup; extern struct idr btf_idr; extern spinlock_t btf_idr_lock; @@ -161,6 +164,9 @@ struct bpf_map { u32 btf_value_type_id; struct btf *btf; struct bpf_map_memory memory; +#ifdef CONFIG_MEMCG_KMEM + struct mem_cgroup *memcg; +#endif char name[BPF_OBJ_NAME_LEN]; u32 btf_vmlinux_value_type_id; bool bypass_spec_v1; @@ -1240,6 +1246,34 @@ int generic_map_delete_batch(struct bpf_map *map, struct bpf_map *bpf_map_get_curr_or_next(u32 *id); struct bpf_prog *bpf_prog_get_curr_or_next(u32 *id); +#ifdef CONFIG_MEMCG_KMEM +void *bpf_map_kmalloc_node(const struct bpf_map *map, size_t size, gfp_t flags, + int node); +void *bpf_map_kzalloc(const struct bpf_map *map, size_t size, gfp_t flags); +void __percpu *bpf_map_alloc_percpu(const struct bpf_map *map, size_t size, + size_t align, gfp_t flags); +#else +static inline void * +bpf_map_kmalloc_node(const struct bpf_map *map, size_t size, gfp_t flags, + int node) +{ + return kmalloc_node(size, flags, node); +} + +static inline void * +bpf_map_kzalloc(const struct bpf_map *map, size_t size, gfp_t flags) +{ + return kzalloc(size, flags); +} + +static inline void __percpu * +bpf_map_alloc_percpu(const struct bpf_map *map, size_t size, size_t align, + gfp_t flags) +{ + return __alloc_percpu_gfp(size, align, flags); +} +#endif + extern int sysctl_unprivileged_bpf_disabled; static inline bool bpf_allow_ptr_leaks(void) diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index f3fe9f53f93c..dedbf6d4cd84 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -31,6 +31,7 @@ #include #include #include +#include #define IS_FD_ARRAY(map) ((map)->map_type == BPF_MAP_TYPE_PERF_EVENT_ARRAY || \ (map)->map_type == BPF_MAP_TYPE_CGROUP_ARRAY || \ @@ -456,6 +457,65 @@ void bpf_map_free_id(struct bpf_map *map, bool do_idr_lock) __release(&map_idr_lock); } +#ifdef CONFIG_MEMCG_KMEM +static void bpf_map_save_memcg(struct bpf_map *map) +{ + map->memcg = get_mem_cgroup_from_mm(current->mm); +} + +static void bpf_map_release_memcg(struct bpf_map *map) +{ + mem_cgroup_put(map->memcg); +} + +void *bpf_map_kmalloc_node(const struct bpf_map *map, size_t size, gfp_t flags, + int node) +{ + struct mem_cgroup *old_memcg; + void *ptr; + + old_memcg = set_active_memcg(map->memcg); + ptr = kmalloc_node(size, flags | __GFP_ACCOUNT, node); + set_active_memcg(old_memcg); + + return ptr; +} + +void *bpf_map_kzalloc(const struct bpf_map *map, size_t size, gfp_t flags) +{ + struct mem_cgroup *old_memcg; + void *ptr; + + old_memcg = set_active_memcg(map->memcg); + ptr = kzalloc(size, flags | __GFP_ACCOUNT); + set_active_memcg(old_memcg); + + return ptr; +} + +void __percpu *bpf_map_alloc_percpu(const struct bpf_map *map, size_t size, + size_t align, gfp_t flags) +{ + struct mem_cgroup *old_memcg; + void __percpu *ptr; + + old_memcg = set_active_memcg(map->memcg); + ptr = __alloc_percpu_gfp(size, align, flags | __GFP_ACCOUNT); + set_active_memcg(old_memcg); + + return ptr; +} + +#else +static void bpf_map_save_memcg(struct bpf_map *map) +{ +} + +static void bpf_map_release_memcg(struct bpf_map *map) +{ +} +#endif + /* called from workqueue */ static void bpf_map_free_deferred(struct work_struct *work) { @@ -464,6 +524,7 @@ static void bpf_map_free_deferred(struct work_struct *work) bpf_map_charge_move(&mem, &map->memory); security_bpf_map_free(map); + bpf_map_release_memcg(map); /* implementation dependent freeing */ map->ops->map_free(map); bpf_map_charge_finish(&mem); @@ -875,6 +936,8 @@ static int map_create(union bpf_attr *attr) if (err) goto free_map_sec; + bpf_map_save_memcg(map); + err = bpf_map_new_fd(map, f_flags); if (err < 0) { /* failed to allocate fd. -- cgit v1.2.3 From d5299b67dd59445902cd30cbc60a03c869cf1adb Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Tue, 1 Dec 2020 13:58:33 -0800 Subject: bpf: Memcg-based memory accounting for bpf maps This patch enables memcg-based memory accounting for memory allocated by __bpf_map_area_alloc(), which is used by many types of bpf maps for large initial memory allocations. Please note, that __bpf_map_area_alloc() should not be used outside of map creation paths without setting the active memory cgroup to the map's memory cgroup. Following patches in the series will refine the accounting for some of the map types. Signed-off-by: Roman Gushchin Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20201201215900.3569844-8-guro@fb.com --- kernel/bpf/syscall.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index dedbf6d4cd84..dff3a5f62d7a 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -268,6 +268,10 @@ static int bpf_map_copy_value(struct bpf_map *map, void *key, void *value, return err; } +/* Please, do not use this function outside from the map creation path + * (e.g. in map update path) without taking care of setting the active + * memory cgroup (see at bpf_map_kmalloc_node() for example). + */ static void *__bpf_map_area_alloc(u64 size, int numa_node, bool mmapable) { /* We really just want to fail instead of triggering OOM killer @@ -280,7 +284,7 @@ static void *__bpf_map_area_alloc(u64 size, int numa_node, bool mmapable) * __GFP_RETRY_MAYFAIL to avoid such situations. */ - const gfp_t gfp = __GFP_NOWARN | __GFP_ZERO; + const gfp_t gfp = __GFP_NOWARN | __GFP_ZERO | __GFP_ACCOUNT; unsigned int flags = 0; unsigned long align = 1; void *area; -- cgit v1.2.3 From 6d192c7938b7e53a6bb55b90b86bd02ea0153731 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Tue, 1 Dec 2020 13:58:34 -0800 Subject: bpf: Refine memcg-based memory accounting for arraymap maps Include percpu arrays and auxiliary data into the memcg-based memory accounting. Signed-off-by: Roman Gushchin Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20201201215900.3569844-9-guro@fb.com --- kernel/bpf/arraymap.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index c6c81eceb68f..d837e0603c89 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -34,8 +34,8 @@ static int bpf_array_alloc_percpu(struct bpf_array *array) int i; for (i = 0; i < array->map.max_entries; i++) { - ptr = __alloc_percpu_gfp(array->elem_size, 8, - GFP_USER | __GFP_NOWARN); + ptr = bpf_map_alloc_percpu(&array->map, array->elem_size, 8, + GFP_USER | __GFP_NOWARN); if (!ptr) { bpf_array_free_percpu(array); return -ENOMEM; @@ -1018,7 +1018,7 @@ static struct bpf_map *prog_array_map_alloc(union bpf_attr *attr) struct bpf_array_aux *aux; struct bpf_map *map; - aux = kzalloc(sizeof(*aux), GFP_KERNEL); + aux = kzalloc(sizeof(*aux), GFP_KERNEL_ACCOUNT); if (!aux) return ERR_PTR(-ENOMEM); -- cgit v1.2.3 From e88cc05b61f3fe8bd4bd8ce1a0a2d03357225305 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Tue, 1 Dec 2020 13:58:35 -0800 Subject: bpf: Refine memcg-based memory accounting for cpumap maps Include metadata and percpu data into the memcg-based memory accounting. Signed-off-by: Roman Gushchin Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20201201215900.3569844-10-guro@fb.com --- kernel/bpf/cpumap.c | 21 ++++++++++++--------- 1 file changed, 12 insertions(+), 9 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c index c61a23b564aa..90b949666605 100644 --- a/kernel/bpf/cpumap.c +++ b/kernel/bpf/cpumap.c @@ -97,7 +97,7 @@ static struct bpf_map *cpu_map_alloc(union bpf_attr *attr) attr->map_flags & ~BPF_F_NUMA_NODE) return ERR_PTR(-EINVAL); - cmap = kzalloc(sizeof(*cmap), GFP_USER); + cmap = kzalloc(sizeof(*cmap), GFP_USER | __GFP_ACCOUNT); if (!cmap) return ERR_PTR(-ENOMEM); @@ -412,7 +412,8 @@ static int __cpu_map_load_bpf_program(struct bpf_cpu_map_entry *rcpu, int fd) } static struct bpf_cpu_map_entry * -__cpu_map_entry_alloc(struct bpf_cpumap_val *value, u32 cpu, int map_id) +__cpu_map_entry_alloc(struct bpf_map *map, struct bpf_cpumap_val *value, + u32 cpu) { int numa, err, i, fd = value->bpf_prog.fd; gfp_t gfp = GFP_KERNEL | __GFP_NOWARN; @@ -422,13 +423,13 @@ __cpu_map_entry_alloc(struct bpf_cpumap_val *value, u32 cpu, int map_id) /* Have map->numa_node, but choose node of redirect target CPU */ numa = cpu_to_node(cpu); - rcpu = kzalloc_node(sizeof(*rcpu), gfp, numa); + rcpu = bpf_map_kmalloc_node(map, sizeof(*rcpu), gfp | __GFP_ZERO, numa); if (!rcpu) return NULL; /* Alloc percpu bulkq */ - rcpu->bulkq = __alloc_percpu_gfp(sizeof(*rcpu->bulkq), - sizeof(void *), gfp); + rcpu->bulkq = bpf_map_alloc_percpu(map, sizeof(*rcpu->bulkq), + sizeof(void *), gfp); if (!rcpu->bulkq) goto free_rcu; @@ -438,7 +439,8 @@ __cpu_map_entry_alloc(struct bpf_cpumap_val *value, u32 cpu, int map_id) } /* Alloc queue */ - rcpu->queue = kzalloc_node(sizeof(*rcpu->queue), gfp, numa); + rcpu->queue = bpf_map_kmalloc_node(map, sizeof(*rcpu->queue), gfp, + numa); if (!rcpu->queue) goto free_bulkq; @@ -447,7 +449,7 @@ __cpu_map_entry_alloc(struct bpf_cpumap_val *value, u32 cpu, int map_id) goto free_queue; rcpu->cpu = cpu; - rcpu->map_id = map_id; + rcpu->map_id = map->id; rcpu->value.qsize = value->qsize; if (fd > 0 && __cpu_map_load_bpf_program(rcpu, fd)) @@ -455,7 +457,8 @@ __cpu_map_entry_alloc(struct bpf_cpumap_val *value, u32 cpu, int map_id) /* Setup kthread */ rcpu->kthread = kthread_create_on_node(cpu_map_kthread_run, rcpu, numa, - "cpumap/%d/map:%d", cpu, map_id); + "cpumap/%d/map:%d", cpu, + map->id); if (IS_ERR(rcpu->kthread)) goto free_prog; @@ -571,7 +574,7 @@ static int cpu_map_update_elem(struct bpf_map *map, void *key, void *value, rcpu = NULL; /* Same as deleting */ } else { /* Updating qsize cause re-allocation of bpf_cpu_map_entry */ - rcpu = __cpu_map_entry_alloc(&cpumap_value, key_cpu, map->id); + rcpu = __cpu_map_entry_alloc(map, &cpumap_value, key_cpu); if (!rcpu) return -ENOMEM; rcpu->cmap = cmap; -- cgit v1.2.3 From 3a61c7c58b3012ac28c166801842615ca99b49c5 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Tue, 1 Dec 2020 13:58:36 -0800 Subject: bpf: Memcg-based memory accounting for cgroup storage maps Account memory used by cgroup storage maps including metadata structures. Account the percpu memory for the percpu flavor of cgroup storage. Signed-off-by: Roman Gushchin Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20201201215900.3569844-11-guro@fb.com --- kernel/bpf/local_storage.c | 23 +++++++++++------------ 1 file changed, 11 insertions(+), 12 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c index 571bb351ed3b..74dcee8926e5 100644 --- a/kernel/bpf/local_storage.c +++ b/kernel/bpf/local_storage.c @@ -164,10 +164,10 @@ static int cgroup_storage_update_elem(struct bpf_map *map, void *key, return 0; } - new = kmalloc_node(sizeof(struct bpf_storage_buffer) + - map->value_size, - __GFP_ZERO | GFP_ATOMIC | __GFP_NOWARN, - map->numa_node); + new = bpf_map_kmalloc_node(map, sizeof(struct bpf_storage_buffer) + + map->value_size, + __GFP_ZERO | GFP_ATOMIC | __GFP_NOWARN, + map->numa_node); if (!new) return -ENOMEM; @@ -313,7 +313,7 @@ static struct bpf_map *cgroup_storage_map_alloc(union bpf_attr *attr) return ERR_PTR(ret); map = kmalloc_node(sizeof(struct bpf_cgroup_storage_map), - __GFP_ZERO | GFP_USER, numa_node); + __GFP_ZERO | GFP_USER | __GFP_ACCOUNT, numa_node); if (!map) { bpf_map_charge_finish(&mem); return ERR_PTR(-ENOMEM); @@ -496,9 +496,9 @@ static size_t bpf_cgroup_storage_calculate_size(struct bpf_map *map, u32 *pages) struct bpf_cgroup_storage *bpf_cgroup_storage_alloc(struct bpf_prog *prog, enum bpf_cgroup_storage_type stype) { + const gfp_t gfp = __GFP_ZERO | GFP_USER; struct bpf_cgroup_storage *storage; struct bpf_map *map; - gfp_t flags; size_t size; u32 pages; @@ -511,20 +511,19 @@ struct bpf_cgroup_storage *bpf_cgroup_storage_alloc(struct bpf_prog *prog, if (bpf_map_charge_memlock(map, pages)) return ERR_PTR(-EPERM); - storage = kmalloc_node(sizeof(struct bpf_cgroup_storage), - __GFP_ZERO | GFP_USER, map->numa_node); + storage = bpf_map_kmalloc_node(map, sizeof(struct bpf_cgroup_storage), + gfp, map->numa_node); if (!storage) goto enomem; - flags = __GFP_ZERO | GFP_USER; - if (stype == BPF_CGROUP_STORAGE_SHARED) { - storage->buf = kmalloc_node(size, flags, map->numa_node); + storage->buf = bpf_map_kmalloc_node(map, size, gfp, + map->numa_node); if (!storage->buf) goto enomem; check_and_init_map_lock(map, storage->buf->data); } else { - storage->percpu_buf = __alloc_percpu_gfp(size, 8, flags); + storage->percpu_buf = bpf_map_alloc_percpu(map, size, 8, gfp); if (!storage->percpu_buf) goto enomem; } -- cgit v1.2.3 From 1440290adf7bb27602bbb7d8b2dc3d903ed3c6c9 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Tue, 1 Dec 2020 13:58:37 -0800 Subject: bpf: Refine memcg-based memory accounting for devmap maps Include map metadata and the node size (struct bpf_dtab_netdev) into the accounting. Signed-off-by: Roman Gushchin Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20201201215900.3569844-12-guro@fb.com --- kernel/bpf/devmap.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c index 2b5ca93c17de..b43ab247302d 100644 --- a/kernel/bpf/devmap.c +++ b/kernel/bpf/devmap.c @@ -175,7 +175,7 @@ static struct bpf_map *dev_map_alloc(union bpf_attr *attr) if (!capable(CAP_NET_ADMIN)) return ERR_PTR(-EPERM); - dtab = kzalloc(sizeof(*dtab), GFP_USER); + dtab = kzalloc(sizeof(*dtab), GFP_USER | __GFP_ACCOUNT); if (!dtab) return ERR_PTR(-ENOMEM); @@ -602,8 +602,9 @@ static struct bpf_dtab_netdev *__dev_map_alloc_node(struct net *net, struct bpf_prog *prog = NULL; struct bpf_dtab_netdev *dev; - dev = kmalloc_node(sizeof(*dev), GFP_ATOMIC | __GFP_NOWARN, - dtab->map.numa_node); + dev = bpf_map_kmalloc_node(&dtab->map, sizeof(*dev), + GFP_ATOMIC | __GFP_NOWARN, + dtab->map.numa_node); if (!dev) return ERR_PTR(-ENOMEM); -- cgit v1.2.3 From 881456811a33b9d3952897f4d01ee4d74fa2f30e Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Tue, 1 Dec 2020 13:58:38 -0800 Subject: bpf: Refine memcg-based memory accounting for hashtab maps Include percpu objects and the size of map metadata into the accounting. Signed-off-by: Roman Gushchin Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20201201215900.3569844-13-guro@fb.com --- kernel/bpf/hashtab.c | 24 ++++++++++++++---------- 1 file changed, 14 insertions(+), 10 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index ec46266aaf1c..bf70fb3ed9c1 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -292,7 +292,8 @@ static int prealloc_init(struct bpf_htab *htab) u32 size = round_up(htab->map.value_size, 8); void __percpu *pptr; - pptr = __alloc_percpu_gfp(size, 8, GFP_USER | __GFP_NOWARN); + pptr = bpf_map_alloc_percpu(&htab->map, size, 8, + GFP_USER | __GFP_NOWARN); if (!pptr) goto free_elems; htab_elem_set_ptr(get_htab_elem(htab, i), htab->map.key_size, @@ -346,8 +347,8 @@ static int alloc_extra_elems(struct bpf_htab *htab) struct pcpu_freelist_node *l; int cpu; - pptr = __alloc_percpu_gfp(sizeof(struct htab_elem *), 8, - GFP_USER | __GFP_NOWARN); + pptr = bpf_map_alloc_percpu(&htab->map, sizeof(struct htab_elem *), 8, + GFP_USER | __GFP_NOWARN); if (!pptr) return -ENOMEM; @@ -444,7 +445,7 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) int err, i; u64 cost; - htab = kzalloc(sizeof(*htab), GFP_USER); + htab = kzalloc(sizeof(*htab), GFP_USER | __GFP_ACCOUNT); if (!htab) return ERR_PTR(-ENOMEM); @@ -502,8 +503,10 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) goto free_charge; for (i = 0; i < HASHTAB_MAP_LOCK_COUNT; i++) { - htab->map_locked[i] = __alloc_percpu_gfp(sizeof(int), - sizeof(int), GFP_USER); + htab->map_locked[i] = bpf_map_alloc_percpu(&htab->map, + sizeof(int), + sizeof(int), + GFP_USER); if (!htab->map_locked[i]) goto free_map_locked; } @@ -925,8 +928,9 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key, l_new = ERR_PTR(-E2BIG); goto dec_count; } - l_new = kmalloc_node(htab->elem_size, GFP_ATOMIC | __GFP_NOWARN, - htab->map.numa_node); + l_new = bpf_map_kmalloc_node(&htab->map, htab->elem_size, + GFP_ATOMIC | __GFP_NOWARN, + htab->map.numa_node); if (!l_new) { l_new = ERR_PTR(-ENOMEM); goto dec_count; @@ -942,8 +946,8 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key, pptr = htab_elem_get_ptr(l_new, key_size); } else { /* alloc_percpu zero-fills */ - pptr = __alloc_percpu_gfp(size, 8, - GFP_ATOMIC | __GFP_NOWARN); + pptr = bpf_map_alloc_percpu(&htab->map, size, 8, + GFP_ATOMIC | __GFP_NOWARN); if (!pptr) { kfree(l_new); l_new = ERR_PTR(-ENOMEM); -- cgit v1.2.3 From 353e7af4bf5e7247c35e9ba5beab42904f1b3499 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Tue, 1 Dec 2020 13:58:39 -0800 Subject: bpf: Memcg-based memory accounting for lpm_trie maps Include lpm trie and lpm trie node objects into the memcg-based memory accounting. Signed-off-by: Roman Gushchin Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20201201215900.3569844-14-guro@fb.com --- kernel/bpf/lpm_trie.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c index 00e32f2ec3e6..1a6981203d7f 100644 --- a/kernel/bpf/lpm_trie.c +++ b/kernel/bpf/lpm_trie.c @@ -282,8 +282,8 @@ static struct lpm_trie_node *lpm_trie_node_alloc(const struct lpm_trie *trie, if (value) size += trie->map.value_size; - node = kmalloc_node(size, GFP_ATOMIC | __GFP_NOWARN, - trie->map.numa_node); + node = bpf_map_kmalloc_node(&trie->map, size, GFP_ATOMIC | __GFP_NOWARN, + trie->map.numa_node); if (!node) return NULL; @@ -557,7 +557,7 @@ static struct bpf_map *trie_alloc(union bpf_attr *attr) attr->value_size > LPM_VAL_SIZE_MAX) return ERR_PTR(-EINVAL); - trie = kzalloc(sizeof(*trie), GFP_USER | __GFP_NOWARN); + trie = kzalloc(sizeof(*trie), GFP_USER | __GFP_NOWARN | __GFP_ACCOUNT); if (!trie) return ERR_PTR(-ENOMEM); -- cgit v1.2.3 From be4035c734d12918866c5eb2c496d420aa80adeb Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Tue, 1 Dec 2020 13:58:40 -0800 Subject: bpf: Memcg-based memory accounting for bpf ringbuffer Enable the memcg-based memory accounting for the memory used by the bpf ringbuffer. Signed-off-by: Roman Gushchin Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20201201215900.3569844-15-guro@fb.com --- kernel/bpf/ringbuf.c | 11 ++++------- 1 file changed, 4 insertions(+), 7 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/ringbuf.c b/kernel/bpf/ringbuf.c index 31cb04a4dd2d..8983a46f6580 100644 --- a/kernel/bpf/ringbuf.c +++ b/kernel/bpf/ringbuf.c @@ -60,8 +60,8 @@ struct bpf_ringbuf_hdr { static struct bpf_ringbuf *bpf_ringbuf_area_alloc(size_t data_sz, int numa_node) { - const gfp_t flags = GFP_KERNEL | __GFP_RETRY_MAYFAIL | __GFP_NOWARN | - __GFP_ZERO; + const gfp_t flags = GFP_KERNEL_ACCOUNT | __GFP_RETRY_MAYFAIL | + __GFP_NOWARN | __GFP_ZERO; int nr_meta_pages = RINGBUF_PGOFF + RINGBUF_POS_PAGES; int nr_data_pages = data_sz >> PAGE_SHIFT; int nr_pages = nr_meta_pages + nr_data_pages; @@ -88,10 +88,7 @@ static struct bpf_ringbuf *bpf_ringbuf_area_alloc(size_t data_sz, int numa_node) * user-space implementations significantly. */ array_size = (nr_meta_pages + 2 * nr_data_pages) * sizeof(*pages); - if (array_size > PAGE_SIZE) - pages = vmalloc_node(array_size, numa_node); - else - pages = kmalloc_node(array_size, flags, numa_node); + pages = bpf_map_area_alloc(array_size, numa_node); if (!pages) return NULL; @@ -167,7 +164,7 @@ static struct bpf_map *ringbuf_map_alloc(union bpf_attr *attr) return ERR_PTR(-E2BIG); #endif - rb_map = kzalloc(sizeof(*rb_map), GFP_USER); + rb_map = kzalloc(sizeof(*rb_map), GFP_USER | __GFP_ACCOUNT); if (!rb_map) return ERR_PTR(-ENOMEM); -- cgit v1.2.3 From e9aae8beba825e4670463ddcf420b954f18d5ced Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Tue, 1 Dec 2020 13:58:41 -0800 Subject: bpf: Memcg-based memory accounting for bpf local storage maps Account memory used by bpf local storage maps: per-socket, per-inode and per-task storages. Signed-off-by: Roman Gushchin Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20201201215900.3569844-16-guro@fb.com --- kernel/bpf/bpf_local_storage.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/bpf_local_storage.c b/kernel/bpf/bpf_local_storage.c index 5d3a7af9ba9b..023a3eaa4d74 100644 --- a/kernel/bpf/bpf_local_storage.c +++ b/kernel/bpf/bpf_local_storage.c @@ -67,7 +67,8 @@ bpf_selem_alloc(struct bpf_local_storage_map *smap, void *owner, if (charge_mem && mem_charge(smap, owner, smap->elem_size)) return NULL; - selem = kzalloc(smap->elem_size, GFP_ATOMIC | __GFP_NOWARN); + selem = bpf_map_kzalloc(&smap->map, smap->elem_size, + GFP_ATOMIC | __GFP_NOWARN); if (selem) { if (value) memcpy(SDATA(selem)->data, value, smap->map.value_size); @@ -264,7 +265,8 @@ int bpf_local_storage_alloc(void *owner, if (err) return err; - storage = kzalloc(sizeof(*storage), GFP_ATOMIC | __GFP_NOWARN); + storage = bpf_map_kzalloc(&smap->map, sizeof(*storage), + GFP_ATOMIC | __GFP_NOWARN); if (!storage) { err = -ENOMEM; goto uncharge; @@ -546,7 +548,7 @@ struct bpf_local_storage_map *bpf_local_storage_map_alloc(union bpf_attr *attr) u64 cost; int ret; - smap = kzalloc(sizeof(*smap), GFP_USER | __GFP_NOWARN); + smap = kzalloc(sizeof(*smap), GFP_USER | __GFP_NOWARN | __GFP_ACCOUNT); if (!smap) return ERR_PTR(-ENOMEM); bpf_map_init_from_attr(&smap->map, attr); @@ -564,7 +566,7 @@ struct bpf_local_storage_map *bpf_local_storage_map_alloc(union bpf_attr *attr) } smap->buckets = kvcalloc(sizeof(*smap->buckets), nbuckets, - GFP_USER | __GFP_NOWARN); + GFP_USER | __GFP_NOWARN | __GFP_ACCOUNT); if (!smap->buckets) { bpf_map_charge_finish(&smap->map.memory); kfree(smap); -- cgit v1.2.3 From 1bc5975613ed155fc57ee321041d3463e580b4a3 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Tue, 1 Dec 2020 13:58:44 -0800 Subject: bpf: Eliminate rlimit-based memory accounting for arraymap maps Do not use rlimit-based memory accounting for arraymap maps. It has been replaced with the memcg-based memory accounting. Signed-off-by: Roman Gushchin Signed-off-by: Alexei Starovoitov Acked-by: Song Liu Link: https://lore.kernel.org/bpf/20201201215900.3569844-19-guro@fb.com --- kernel/bpf/arraymap.c | 24 ++++-------------------- 1 file changed, 4 insertions(+), 20 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index d837e0603c89..1f8453343bf2 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -81,11 +81,10 @@ int array_map_alloc_check(union bpf_attr *attr) static struct bpf_map *array_map_alloc(union bpf_attr *attr) { bool percpu = attr->map_type == BPF_MAP_TYPE_PERCPU_ARRAY; - int ret, numa_node = bpf_map_attr_numa_node(attr); + int numa_node = bpf_map_attr_numa_node(attr); u32 elem_size, index_mask, max_entries; bool bypass_spec_v1 = bpf_bypass_spec_v1(); - u64 cost, array_size, mask64; - struct bpf_map_memory mem; + u64 array_size, mask64; struct bpf_array *array; elem_size = round_up(attr->value_size, 8); @@ -126,44 +125,29 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr) } } - /* make sure there is no u32 overflow later in round_up() */ - cost = array_size; - if (percpu) - cost += (u64)attr->max_entries * elem_size * num_possible_cpus(); - - ret = bpf_map_charge_init(&mem, cost); - if (ret < 0) - return ERR_PTR(ret); - /* allocate all map elements and zero-initialize them */ if (attr->map_flags & BPF_F_MMAPABLE) { void *data; /* kmalloc'ed memory can't be mmap'ed, use explicit vmalloc */ data = bpf_map_area_mmapable_alloc(array_size, numa_node); - if (!data) { - bpf_map_charge_finish(&mem); + if (!data) return ERR_PTR(-ENOMEM); - } array = data + PAGE_ALIGN(sizeof(struct bpf_array)) - offsetof(struct bpf_array, value); } else { array = bpf_map_area_alloc(array_size, numa_node); } - if (!array) { - bpf_map_charge_finish(&mem); + if (!array) return ERR_PTR(-ENOMEM); - } array->index_mask = index_mask; array->map.bypass_spec_v1 = bypass_spec_v1; /* copy mandatory map attributes */ bpf_map_init_from_attr(&array->map, attr); - bpf_map_charge_move(&array->map.memory, &mem); array->elem_size = elem_size; if (percpu && bpf_array_alloc_percpu(array)) { - bpf_map_charge_finish(&array->map.memory); bpf_map_area_free(array); return ERR_PTR(-ENOMEM); } -- cgit v1.2.3 From f043733f31e5e12c6254045a03e519290543fa1b Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Tue, 1 Dec 2020 13:58:45 -0800 Subject: bpf: Eliminate rlimit-based memory accounting for bpf_struct_ops maps Do not use rlimit-based memory accounting for bpf_struct_ops maps. It has been replaced with the memcg-based memory accounting. Signed-off-by: Roman Gushchin Signed-off-by: Alexei Starovoitov Acked-by: Song Liu Link: https://lore.kernel.org/bpf/20201201215900.3569844-20-guro@fb.com --- kernel/bpf/bpf_struct_ops.c | 19 +++---------------- 1 file changed, 3 insertions(+), 16 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c index 4c3b543bb33b..1a666a975416 100644 --- a/kernel/bpf/bpf_struct_ops.c +++ b/kernel/bpf/bpf_struct_ops.c @@ -548,12 +548,10 @@ static int bpf_struct_ops_map_alloc_check(union bpf_attr *attr) static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr) { const struct bpf_struct_ops *st_ops; - size_t map_total_size, st_map_size; + size_t st_map_size; struct bpf_struct_ops_map *st_map; const struct btf_type *t, *vt; - struct bpf_map_memory mem; struct bpf_map *map; - int err; if (!bpf_capable()) return ERR_PTR(-EPERM); @@ -573,20 +571,11 @@ static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr) * struct bpf_struct_ops_tcp_congestions_ops */ (vt->size - sizeof(struct bpf_struct_ops_value)); - map_total_size = st_map_size + - /* uvalue */ - sizeof(vt->size) + - /* struct bpf_progs **progs */ - btf_type_vlen(t) * sizeof(struct bpf_prog *); - err = bpf_map_charge_init(&mem, map_total_size); - if (err < 0) - return ERR_PTR(err); st_map = bpf_map_area_alloc(st_map_size, NUMA_NO_NODE); - if (!st_map) { - bpf_map_charge_finish(&mem); + if (!st_map) return ERR_PTR(-ENOMEM); - } + st_map->st_ops = st_ops; map = &st_map->map; @@ -597,14 +586,12 @@ static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr) st_map->image = bpf_jit_alloc_exec(PAGE_SIZE); if (!st_map->uvalue || !st_map->progs || !st_map->image) { bpf_struct_ops_map_free(map); - bpf_map_charge_finish(&mem); return ERR_PTR(-ENOMEM); } mutex_init(&st_map->lock); set_vm_flush_reset_perms(st_map->image); bpf_map_init_from_attr(map, attr); - bpf_map_charge_move(&map->memory, &mem); return map; } -- cgit v1.2.3 From 711cabaf1432fbec4a5f9ffcfbfe2ed7a78cd096 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Tue, 1 Dec 2020 13:58:46 -0800 Subject: bpf: Eliminate rlimit-based memory accounting for cpumap maps Do not use rlimit-based memory accounting for cpumap maps. It has been replaced with the memcg-based memory accounting. Signed-off-by: Roman Gushchin Signed-off-by: Alexei Starovoitov Acked-by: Song Liu Link: https://lore.kernel.org/bpf/20201201215900.3569844-21-guro@fb.com --- kernel/bpf/cpumap.c | 16 +--------------- 1 file changed, 1 insertion(+), 15 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c index 90b949666605..747313698178 100644 --- a/kernel/bpf/cpumap.c +++ b/kernel/bpf/cpumap.c @@ -84,8 +84,6 @@ static struct bpf_map *cpu_map_alloc(union bpf_attr *attr) u32 value_size = attr->value_size; struct bpf_cpu_map *cmap; int err = -ENOMEM; - u64 cost; - int ret; if (!bpf_capable()) return ERR_PTR(-EPERM); @@ -109,26 +107,14 @@ static struct bpf_map *cpu_map_alloc(union bpf_attr *attr) goto free_cmap; } - /* make sure page count doesn't overflow */ - cost = (u64) cmap->map.max_entries * sizeof(struct bpf_cpu_map_entry *); - - /* Notice returns -EPERM on if map size is larger than memlock limit */ - ret = bpf_map_charge_init(&cmap->map.memory, cost); - if (ret) { - err = ret; - goto free_cmap; - } - /* Alloc array for possible remote "destination" CPUs */ cmap->cpu_map = bpf_map_area_alloc(cmap->map.max_entries * sizeof(struct bpf_cpu_map_entry *), cmap->map.numa_node); if (!cmap->cpu_map) - goto free_charge; + goto free_cmap; return &cmap->map; -free_charge: - bpf_map_charge_finish(&cmap->map.memory); free_cmap: kfree(cmap); return ERR_PTR(err); -- cgit v1.2.3 From 087b0d39fe22dcc2ddcef7ed699c658f0e725bac Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Tue, 1 Dec 2020 13:58:47 -0800 Subject: bpf: Eliminate rlimit-based memory accounting for cgroup storage maps Do not use rlimit-based memory accounting for cgroup storage maps. It has been replaced with the memcg-based memory accounting. Signed-off-by: Roman Gushchin Signed-off-by: Alexei Starovoitov Acked-by: Song Liu Link: https://lore.kernel.org/bpf/20201201215900.3569844-22-guro@fb.com --- kernel/bpf/local_storage.c | 21 +-------------------- 1 file changed, 1 insertion(+), 20 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c index 74dcee8926e5..2d4f9ac12377 100644 --- a/kernel/bpf/local_storage.c +++ b/kernel/bpf/local_storage.c @@ -287,8 +287,6 @@ static struct bpf_map *cgroup_storage_map_alloc(union bpf_attr *attr) { int numa_node = bpf_map_attr_numa_node(attr); struct bpf_cgroup_storage_map *map; - struct bpf_map_memory mem; - int ret; if (attr->key_size != sizeof(struct bpf_cgroup_storage_key) && attr->key_size != sizeof(__u64)) @@ -308,18 +306,10 @@ static struct bpf_map *cgroup_storage_map_alloc(union bpf_attr *attr) /* max_entries is not used and enforced to be 0 */ return ERR_PTR(-EINVAL); - ret = bpf_map_charge_init(&mem, sizeof(struct bpf_cgroup_storage_map)); - if (ret < 0) - return ERR_PTR(ret); - map = kmalloc_node(sizeof(struct bpf_cgroup_storage_map), __GFP_ZERO | GFP_USER | __GFP_ACCOUNT, numa_node); - if (!map) { - bpf_map_charge_finish(&mem); + if (!map) return ERR_PTR(-ENOMEM); - } - - bpf_map_charge_move(&map->map.memory, &mem); /* copy mandatory map attributes */ bpf_map_init_from_attr(&map->map, attr); @@ -508,9 +498,6 @@ struct bpf_cgroup_storage *bpf_cgroup_storage_alloc(struct bpf_prog *prog, size = bpf_cgroup_storage_calculate_size(map, &pages); - if (bpf_map_charge_memlock(map, pages)) - return ERR_PTR(-EPERM); - storage = bpf_map_kmalloc_node(map, sizeof(struct bpf_cgroup_storage), gfp, map->numa_node); if (!storage) @@ -533,7 +520,6 @@ struct bpf_cgroup_storage *bpf_cgroup_storage_alloc(struct bpf_prog *prog, return storage; enomem: - bpf_map_uncharge_memlock(map, pages); kfree(storage); return ERR_PTR(-ENOMEM); } @@ -560,16 +546,11 @@ void bpf_cgroup_storage_free(struct bpf_cgroup_storage *storage) { enum bpf_cgroup_storage_type stype; struct bpf_map *map; - u32 pages; if (!storage) return; map = &storage->map->map; - - bpf_cgroup_storage_calculate_size(map, &pages); - bpf_map_uncharge_memlock(map, pages); - stype = cgroup_storage_type(map); if (stype == BPF_CGROUP_STORAGE_SHARED) call_rcu(&storage->rcu, free_shared_cgroup_storage_rcu); -- cgit v1.2.3 From 844f157f6c0a905d039d2e20212ab3231f2e5eaf Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Tue, 1 Dec 2020 13:58:48 -0800 Subject: bpf: Eliminate rlimit-based memory accounting for devmap maps Do not use rlimit-based memory accounting for devmap maps. It has been replaced with the memcg-based memory accounting. Signed-off-by: Roman Gushchin Signed-off-by: Alexei Starovoitov Acked-by: Song Liu Link: https://lore.kernel.org/bpf/20201201215900.3569844-23-guro@fb.com --- kernel/bpf/devmap.c | 18 ++---------------- 1 file changed, 2 insertions(+), 16 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c index b43ab247302d..f6e9c68afdd4 100644 --- a/kernel/bpf/devmap.c +++ b/kernel/bpf/devmap.c @@ -109,8 +109,6 @@ static inline struct hlist_head *dev_map_index_hash(struct bpf_dtab *dtab, static int dev_map_init_map(struct bpf_dtab *dtab, union bpf_attr *attr) { u32 valsize = attr->value_size; - u64 cost = 0; - int err; /* check sanity of attributes. 2 value sizes supported: * 4 bytes: ifindex @@ -135,21 +133,13 @@ static int dev_map_init_map(struct bpf_dtab *dtab, union bpf_attr *attr) if (!dtab->n_buckets) /* Overflow check */ return -EINVAL; - cost += (u64) sizeof(struct hlist_head) * dtab->n_buckets; - } else { - cost += (u64) dtab->map.max_entries * sizeof(struct bpf_dtab_netdev *); } - /* if map size is larger than memlock limit, reject it */ - err = bpf_map_charge_init(&dtab->map.memory, cost); - if (err) - return -EINVAL; - if (attr->map_type == BPF_MAP_TYPE_DEVMAP_HASH) { dtab->dev_index_head = dev_map_create_hash(dtab->n_buckets, dtab->map.numa_node); if (!dtab->dev_index_head) - goto free_charge; + return -ENOMEM; spin_lock_init(&dtab->index_lock); } else { @@ -157,14 +147,10 @@ static int dev_map_init_map(struct bpf_dtab *dtab, union bpf_attr *attr) sizeof(struct bpf_dtab_netdev *), dtab->map.numa_node); if (!dtab->netdev_map) - goto free_charge; + return -ENOMEM; } return 0; - -free_charge: - bpf_map_charge_finish(&dtab->map.memory); - return -ENOMEM; } static struct bpf_map *dev_map_alloc(union bpf_attr *attr) -- cgit v1.2.3 From 755e5d55367af5ff75a4db9b6cf439416878e2c7 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Tue, 1 Dec 2020 13:58:49 -0800 Subject: bpf: Eliminate rlimit-based memory accounting for hashtab maps Do not use rlimit-based memory accounting for hashtab maps. It has been replaced with the memcg-based memory accounting. Signed-off-by: Roman Gushchin Signed-off-by: Alexei Starovoitov Acked-by: Song Liu Link: https://lore.kernel.org/bpf/20201201215900.3569844-24-guro@fb.com --- kernel/bpf/hashtab.c | 19 +------------------ 1 file changed, 1 insertion(+), 18 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index bf70fb3ed9c1..fe7a0733a63a 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -443,7 +443,6 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) bool prealloc = !(attr->map_flags & BPF_F_NO_PREALLOC); struct bpf_htab *htab; int err, i; - u64 cost; htab = kzalloc(sizeof(*htab), GFP_USER | __GFP_ACCOUNT); if (!htab) @@ -481,26 +480,12 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) htab->n_buckets > U32_MAX / sizeof(struct bucket)) goto free_htab; - cost = (u64) htab->n_buckets * sizeof(struct bucket) + - (u64) htab->elem_size * htab->map.max_entries; - - if (percpu) - cost += (u64) round_up(htab->map.value_size, 8) * - num_possible_cpus() * htab->map.max_entries; - else - cost += (u64) htab->elem_size * num_possible_cpus(); - - /* if map size is larger than memlock limit, reject it */ - err = bpf_map_charge_init(&htab->map.memory, cost); - if (err) - goto free_htab; - err = -ENOMEM; htab->buckets = bpf_map_area_alloc(htab->n_buckets * sizeof(struct bucket), htab->map.numa_node); if (!htab->buckets) - goto free_charge; + goto free_htab; for (i = 0; i < HASHTAB_MAP_LOCK_COUNT; i++) { htab->map_locked[i] = bpf_map_alloc_percpu(&htab->map, @@ -541,8 +526,6 @@ free_map_locked: for (i = 0; i < HASHTAB_MAP_LOCK_COUNT; i++) free_percpu(htab->map_locked[i]); bpf_map_area_free(htab->buckets); -free_charge: - bpf_map_charge_finish(&htab->map.memory); free_htab: lockdep_unregister_key(&htab->lockdep_key); kfree(htab); -- cgit v1.2.3 From cbddcb574d419fd5b70c5f87ba733feec6147aeb Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Tue, 1 Dec 2020 13:58:50 -0800 Subject: bpf: Eliminate rlimit-based memory accounting for lpm_trie maps Do not use rlimit-based memory accounting for lpm_trie maps. It has been replaced with the memcg-based memory accounting. Signed-off-by: Roman Gushchin Signed-off-by: Alexei Starovoitov Acked-by: Song Liu Link: https://lore.kernel.org/bpf/20201201215900.3569844-25-guro@fb.com --- kernel/bpf/lpm_trie.c | 13 ------------- 1 file changed, 13 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c index 1a6981203d7f..cec792a17e5f 100644 --- a/kernel/bpf/lpm_trie.c +++ b/kernel/bpf/lpm_trie.c @@ -540,8 +540,6 @@ out: static struct bpf_map *trie_alloc(union bpf_attr *attr) { struct lpm_trie *trie; - u64 cost = sizeof(*trie), cost_per_node; - int ret; if (!bpf_capable()) return ERR_PTR(-EPERM); @@ -567,20 +565,9 @@ static struct bpf_map *trie_alloc(union bpf_attr *attr) offsetof(struct bpf_lpm_trie_key, data); trie->max_prefixlen = trie->data_size * 8; - cost_per_node = sizeof(struct lpm_trie_node) + - attr->value_size + trie->data_size; - cost += (u64) attr->max_entries * cost_per_node; - - ret = bpf_map_charge_init(&trie->map.memory, cost); - if (ret) - goto out_err; - spin_lock_init(&trie->lock); return &trie->map; -out_err: - kfree(trie); - return ERR_PTR(ret); } static void trie_free(struct bpf_map *map) -- cgit v1.2.3 From a37fb7ef24a475012547fa28f0148d2e538ad5d4 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Tue, 1 Dec 2020 13:58:51 -0800 Subject: bpf: Eliminate rlimit-based memory accounting for queue_stack_maps maps Do not use rlimit-based memory accounting for queue_stack maps. It has been replaced with the memcg-based memory accounting. Signed-off-by: Roman Gushchin Signed-off-by: Alexei Starovoitov Acked-by: Song Liu Link: https://lore.kernel.org/bpf/20201201215900.3569844-26-guro@fb.com --- kernel/bpf/queue_stack_maps.c | 16 ++++------------ 1 file changed, 4 insertions(+), 12 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/queue_stack_maps.c b/kernel/bpf/queue_stack_maps.c index 0ee2347ba510..f9c734aaa990 100644 --- a/kernel/bpf/queue_stack_maps.c +++ b/kernel/bpf/queue_stack_maps.c @@ -66,29 +66,21 @@ static int queue_stack_map_alloc_check(union bpf_attr *attr) static struct bpf_map *queue_stack_map_alloc(union bpf_attr *attr) { - int ret, numa_node = bpf_map_attr_numa_node(attr); - struct bpf_map_memory mem = {0}; + int numa_node = bpf_map_attr_numa_node(attr); struct bpf_queue_stack *qs; - u64 size, queue_size, cost; + u64 size, queue_size; size = (u64) attr->max_entries + 1; - cost = queue_size = sizeof(*qs) + size * attr->value_size; - - ret = bpf_map_charge_init(&mem, cost); - if (ret < 0) - return ERR_PTR(ret); + queue_size = sizeof(*qs) + size * attr->value_size; qs = bpf_map_area_alloc(queue_size, numa_node); - if (!qs) { - bpf_map_charge_finish(&mem); + if (!qs) return ERR_PTR(-ENOMEM); - } memset(qs, 0, sizeof(*qs)); bpf_map_init_from_attr(&qs->map, attr); - bpf_map_charge_move(&qs->map.memory, &mem); qs->size = size; raw_spin_lock_init(&qs->lock); -- cgit v1.2.3 From db54330d3e137c23bea26784cecf5ae17e72e4c6 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Tue, 1 Dec 2020 13:58:52 -0800 Subject: bpf: Eliminate rlimit-based memory accounting for reuseport_array maps Do not use rlimit-based memory accounting for reuseport_array maps. It has been replaced with the memcg-based memory accounting. Signed-off-by: Roman Gushchin Signed-off-by: Alexei Starovoitov Acked-by: Song Liu Link: https://lore.kernel.org/bpf/20201201215900.3569844-27-guro@fb.com --- kernel/bpf/reuseport_array.c | 12 ++---------- 1 file changed, 2 insertions(+), 10 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/reuseport_array.c b/kernel/bpf/reuseport_array.c index a55cd542f2ce..4838922f723d 100644 --- a/kernel/bpf/reuseport_array.c +++ b/kernel/bpf/reuseport_array.c @@ -150,9 +150,8 @@ static void reuseport_array_free(struct bpf_map *map) static struct bpf_map *reuseport_array_alloc(union bpf_attr *attr) { - int err, numa_node = bpf_map_attr_numa_node(attr); + int numa_node = bpf_map_attr_numa_node(attr); struct reuseport_array *array; - struct bpf_map_memory mem; u64 array_size; if (!bpf_capable()) @@ -161,20 +160,13 @@ static struct bpf_map *reuseport_array_alloc(union bpf_attr *attr) array_size = sizeof(*array); array_size += (u64)attr->max_entries * sizeof(struct sock *); - err = bpf_map_charge_init(&mem, array_size); - if (err) - return ERR_PTR(err); - /* allocate all map elements and zero-initialize them */ array = bpf_map_area_alloc(array_size, numa_node); - if (!array) { - bpf_map_charge_finish(&mem); + if (!array) return ERR_PTR(-ENOMEM); - } /* copy mandatory map attributes */ bpf_map_init_from_attr(&array->map, attr); - bpf_map_charge_move(&array->map.memory, &mem); return &array->map; } -- cgit v1.2.3 From abbdd0813f347f9d1eea376409a68295318b2ef5 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Tue, 1 Dec 2020 13:58:53 -0800 Subject: bpf: Eliminate rlimit-based memory accounting for bpf ringbuffer Do not use rlimit-based memory accounting for bpf ringbuffer. It has been replaced with the memcg-based memory accounting. bpf_ringbuf_alloc() can't return anything except ERR_PTR(-ENOMEM) and a valid pointer, so to simplify the code make it return NULL in the first case. This allows to drop a couple of lines in ringbuf_map_alloc() and also makes it look similar to other memory allocating function like kmalloc(). Signed-off-by: Roman Gushchin Signed-off-by: Alexei Starovoitov Acked-by: Song Liu Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20201201215900.3569844-28-guro@fb.com --- kernel/bpf/ringbuf.c | 24 ++++-------------------- 1 file changed, 4 insertions(+), 20 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/ringbuf.c b/kernel/bpf/ringbuf.c index 8983a46f6580..f25b719ac786 100644 --- a/kernel/bpf/ringbuf.c +++ b/kernel/bpf/ringbuf.c @@ -48,7 +48,6 @@ struct bpf_ringbuf { struct bpf_ringbuf_map { struct bpf_map map; - struct bpf_map_memory memory; struct bpf_ringbuf *rb; }; @@ -131,7 +130,7 @@ static struct bpf_ringbuf *bpf_ringbuf_alloc(size_t data_sz, int numa_node) rb = bpf_ringbuf_area_alloc(data_sz, numa_node); if (!rb) - return ERR_PTR(-ENOMEM); + return NULL; spin_lock_init(&rb->spinlock); init_waitqueue_head(&rb->waitq); @@ -147,8 +146,6 @@ static struct bpf_ringbuf *bpf_ringbuf_alloc(size_t data_sz, int numa_node) static struct bpf_map *ringbuf_map_alloc(union bpf_attr *attr) { struct bpf_ringbuf_map *rb_map; - u64 cost; - int err; if (attr->map_flags & ~RINGBUF_CREATE_FLAG_MASK) return ERR_PTR(-EINVAL); @@ -170,26 +167,13 @@ static struct bpf_map *ringbuf_map_alloc(union bpf_attr *attr) bpf_map_init_from_attr(&rb_map->map, attr); - cost = sizeof(struct bpf_ringbuf_map) + - sizeof(struct bpf_ringbuf) + - attr->max_entries; - err = bpf_map_charge_init(&rb_map->map.memory, cost); - if (err) - goto err_free_map; - rb_map->rb = bpf_ringbuf_alloc(attr->max_entries, rb_map->map.numa_node); - if (IS_ERR(rb_map->rb)) { - err = PTR_ERR(rb_map->rb); - goto err_uncharge; + if (!rb_map->rb) { + kfree(rb_map); + return ERR_PTR(-ENOMEM); } return &rb_map->map; - -err_uncharge: - bpf_map_charge_finish(&rb_map->map.memory); -err_free_map: - kfree(rb_map); - return ERR_PTR(err); } static void bpf_ringbuf_free(struct bpf_ringbuf *rb) -- cgit v1.2.3 From 370868107bf6624cc104038bf38be2ca153eeb2e Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Tue, 1 Dec 2020 13:58:55 -0800 Subject: bpf: Eliminate rlimit-based memory accounting for stackmap maps Do not use rlimit-based memory accounting for stackmap maps. It has been replaced with the memcg-based memory accounting. Signed-off-by: Roman Gushchin Signed-off-by: Alexei Starovoitov Acked-by: Song Liu Link: https://lore.kernel.org/bpf/20201201215900.3569844-30-guro@fb.com --- kernel/bpf/stackmap.c | 16 +++------------- 1 file changed, 3 insertions(+), 13 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index 06065fa27124..3325add8e629 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -90,7 +90,6 @@ static struct bpf_map *stack_map_alloc(union bpf_attr *attr) { u32 value_size = attr->value_size; struct bpf_stack_map *smap; - struct bpf_map_memory mem; u64 cost, n_buckets; int err; @@ -119,15 +118,9 @@ static struct bpf_map *stack_map_alloc(union bpf_attr *attr) cost = n_buckets * sizeof(struct stack_map_bucket *) + sizeof(*smap); cost += n_buckets * (value_size + sizeof(struct stack_map_bucket)); - err = bpf_map_charge_init(&mem, cost); - if (err) - return ERR_PTR(err); - smap = bpf_map_area_alloc(cost, bpf_map_attr_numa_node(attr)); - if (!smap) { - bpf_map_charge_finish(&mem); + if (!smap) return ERR_PTR(-ENOMEM); - } bpf_map_init_from_attr(&smap->map, attr); smap->map.value_size = value_size; @@ -135,20 +128,17 @@ static struct bpf_map *stack_map_alloc(union bpf_attr *attr) err = get_callchain_buffers(sysctl_perf_event_max_stack); if (err) - goto free_charge; + goto free_smap; err = prealloc_elems_and_freelist(smap); if (err) goto put_buffers; - bpf_map_charge_move(&smap->map.memory, &mem); - return &smap->map; put_buffers: put_callchain_buffers(); -free_charge: - bpf_map_charge_finish(&mem); +free_smap: bpf_map_area_free(smap); return ERR_PTR(err); } -- cgit v1.2.3 From ab31be378a63a8bc1868c9890d28b0206f81396e Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Tue, 1 Dec 2020 13:58:57 -0800 Subject: bpf: Eliminate rlimit-based memory accounting for bpf local storage maps Do not use rlimit-based memory accounting for bpf local storage maps. It has been replaced with the memcg-based memory accounting. Signed-off-by: Roman Gushchin Signed-off-by: Alexei Starovoitov Acked-by: Song Liu Link: https://lore.kernel.org/bpf/20201201215900.3569844-32-guro@fb.com --- kernel/bpf/bpf_local_storage.c | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/bpf_local_storage.c b/kernel/bpf/bpf_local_storage.c index 023a3eaa4d74..dd5aedee99e7 100644 --- a/kernel/bpf/bpf_local_storage.c +++ b/kernel/bpf/bpf_local_storage.c @@ -545,8 +545,6 @@ struct bpf_local_storage_map *bpf_local_storage_map_alloc(union bpf_attr *attr) struct bpf_local_storage_map *smap; unsigned int i; u32 nbuckets; - u64 cost; - int ret; smap = kzalloc(sizeof(*smap), GFP_USER | __GFP_NOWARN | __GFP_ACCOUNT); if (!smap) @@ -557,18 +555,10 @@ struct bpf_local_storage_map *bpf_local_storage_map_alloc(union bpf_attr *attr) /* Use at least 2 buckets, select_bucket() is undefined behavior with 1 bucket */ nbuckets = max_t(u32, 2, nbuckets); smap->bucket_log = ilog2(nbuckets); - cost = sizeof(*smap->buckets) * nbuckets + sizeof(*smap); - - ret = bpf_map_charge_init(&smap->map.memory, cost); - if (ret < 0) { - kfree(smap); - return ERR_PTR(ret); - } smap->buckets = kvcalloc(sizeof(*smap->buckets), nbuckets, GFP_USER | __GFP_NOWARN | __GFP_ACCOUNT); if (!smap->buckets) { - bpf_map_charge_finish(&smap->map.memory); kfree(smap); return ERR_PTR(-ENOMEM); } -- cgit v1.2.3 From 80ee81e0403c48f4eb342f7c8d40477c89b8836a Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Tue, 1 Dec 2020 13:58:58 -0800 Subject: bpf: Eliminate rlimit-based memory accounting infra for bpf maps Remove rlimit-based accounting infrastructure code, which is not used anymore. To provide a backward compatibility, use an approximation of the bpf map memory footprint as a "memlock" value, available to a user via map info. The approximation is based on the maximal number of elements and key and value sizes. Signed-off-by: Roman Gushchin Signed-off-by: Alexei Starovoitov Acked-by: Song Liu Link: https://lore.kernel.org/bpf/20201201215900.3569844-33-guro@fb.com --- include/linux/bpf.h | 12 --- kernel/bpf/syscall.c | 96 ++++------------------ .../testing/selftests/bpf/progs/bpf_iter_bpf_map.c | 2 +- tools/testing/selftests/bpf/progs/map_ptr_kern.c | 7 -- 4 files changed, 17 insertions(+), 100 deletions(-) (limited to 'kernel') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index e1f2c95c15ec..61331a148cde 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -138,11 +138,6 @@ struct bpf_map_ops { const struct bpf_iter_seq_info *iter_seq_info; }; -struct bpf_map_memory { - u32 pages; - struct user_struct *user; -}; - 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). @@ -163,7 +158,6 @@ struct bpf_map { u32 btf_key_type_id; u32 btf_value_type_id; struct btf *btf; - struct bpf_map_memory memory; #ifdef CONFIG_MEMCG_KMEM struct mem_cgroup *memcg; #endif @@ -1224,12 +1218,6 @@ void bpf_map_inc_with_uref(struct bpf_map *map); 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); -int bpf_map_charge_memlock(struct bpf_map *map, u32 pages); -void bpf_map_uncharge_memlock(struct bpf_map *map, u32 pages); -int bpf_map_charge_init(struct bpf_map_memory *mem, u64 size); -void bpf_map_charge_finish(struct bpf_map_memory *mem); -void bpf_map_charge_move(struct bpf_map_memory *dst, - struct bpf_map_memory *src); void *bpf_map_area_alloc(u64 size, int numa_node); void *bpf_map_area_mmapable_alloc(u64 size, int numa_node); void bpf_map_area_free(void *base); diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index dff3a5f62d7a..29096d96d989 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -128,7 +128,7 @@ static struct bpf_map *find_and_alloc_map(union bpf_attr *attr) return map; } -static u32 bpf_map_value_size(struct bpf_map *map) +static u32 bpf_map_value_size(const struct bpf_map *map) { if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH || map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH || @@ -346,77 +346,6 @@ void bpf_map_init_from_attr(struct bpf_map *map, union bpf_attr *attr) map->numa_node = bpf_map_attr_numa_node(attr); } -static int bpf_charge_memlock(struct user_struct *user, u32 pages) -{ - unsigned long memlock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT; - - if (atomic_long_add_return(pages, &user->locked_vm) > memlock_limit) { - atomic_long_sub(pages, &user->locked_vm); - return -EPERM; - } - return 0; -} - -static void bpf_uncharge_memlock(struct user_struct *user, u32 pages) -{ - if (user) - atomic_long_sub(pages, &user->locked_vm); -} - -int bpf_map_charge_init(struct bpf_map_memory *mem, u64 size) -{ - u32 pages = round_up(size, PAGE_SIZE) >> PAGE_SHIFT; - struct user_struct *user; - int ret; - - if (size >= U32_MAX - PAGE_SIZE) - return -E2BIG; - - user = get_current_user(); - ret = bpf_charge_memlock(user, pages); - if (ret) { - free_uid(user); - return ret; - } - - mem->pages = pages; - mem->user = user; - - return 0; -} - -void bpf_map_charge_finish(struct bpf_map_memory *mem) -{ - bpf_uncharge_memlock(mem->user, mem->pages); - free_uid(mem->user); -} - -void bpf_map_charge_move(struct bpf_map_memory *dst, - struct bpf_map_memory *src) -{ - *dst = *src; - - /* Make sure src will not be used for the redundant uncharging. */ - memset(src, 0, sizeof(struct bpf_map_memory)); -} - -int bpf_map_charge_memlock(struct bpf_map *map, u32 pages) -{ - int ret; - - ret = bpf_charge_memlock(map->memory.user, pages); - if (ret) - return ret; - map->memory.pages += pages; - return ret; -} - -void bpf_map_uncharge_memlock(struct bpf_map *map, u32 pages) -{ - bpf_uncharge_memlock(map->memory.user, pages); - map->memory.pages -= pages; -} - static int bpf_map_alloc_id(struct bpf_map *map) { int id; @@ -524,14 +453,11 @@ static void bpf_map_release_memcg(struct bpf_map *map) static void bpf_map_free_deferred(struct work_struct *work) { struct bpf_map *map = container_of(work, struct bpf_map, work); - struct bpf_map_memory mem; - bpf_map_charge_move(&mem, &map->memory); security_bpf_map_free(map); bpf_map_release_memcg(map); /* implementation dependent freeing */ map->ops->map_free(map); - bpf_map_charge_finish(&mem); } static void bpf_map_put_uref(struct bpf_map *map) @@ -592,6 +518,19 @@ static fmode_t map_get_sys_perms(struct bpf_map *map, struct fd f) } #ifdef CONFIG_PROC_FS +/* Provides an approximation of the map's memory footprint. + * Used only to provide a backward compatibility and display + * a reasonable "memlock" info. + */ +static unsigned long bpf_map_memory_footprint(const struct bpf_map *map) +{ + unsigned long size; + + size = round_up(map->key_size + bpf_map_value_size(map), 8); + + return round_up(map->max_entries * size, PAGE_SIZE); +} + static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp) { const struct bpf_map *map = filp->private_data; @@ -610,7 +549,7 @@ static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp) "value_size:\t%u\n" "max_entries:\t%u\n" "map_flags:\t%#x\n" - "memlock:\t%llu\n" + "memlock:\t%lu\n" "map_id:\t%u\n" "frozen:\t%u\n", map->map_type, @@ -618,7 +557,7 @@ static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp) map->value_size, map->max_entries, map->map_flags, - map->memory.pages * 1ULL << PAGE_SHIFT, + bpf_map_memory_footprint(map), map->id, READ_ONCE(map->frozen)); if (type) { @@ -861,7 +800,6 @@ static int map_check_btf(struct bpf_map *map, const struct btf *btf, static int map_create(union bpf_attr *attr) { int numa_node = bpf_map_attr_numa_node(attr); - struct bpf_map_memory mem; struct bpf_map *map; int f_flags; int err; @@ -960,9 +898,7 @@ free_map_sec: security_bpf_map_free(map); free_map: btf_put(map->btf); - bpf_map_charge_move(&mem, &map->memory); map->ops->map_free(map); - bpf_map_charge_finish(&mem); return err; } diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_map.c b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_map.c index 08651b23edba..b83b5d2e17dc 100644 --- a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_map.c +++ b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_map.c @@ -23,6 +23,6 @@ int dump_bpf_map(struct bpf_iter__bpf_map *ctx) BPF_SEQ_PRINTF(seq, "%8u %8ld %8ld %10lu\n", map->id, map->refcnt.counter, map->usercnt.counter, - map->memory.user->locked_vm.counter); + 0LLU); return 0; } diff --git a/tools/testing/selftests/bpf/progs/map_ptr_kern.c b/tools/testing/selftests/bpf/progs/map_ptr_kern.c index c325405751e2..d8850bc6a9f1 100644 --- a/tools/testing/selftests/bpf/progs/map_ptr_kern.c +++ b/tools/testing/selftests/bpf/progs/map_ptr_kern.c @@ -26,17 +26,12 @@ __u32 g_line = 0; return 0; \ }) -struct bpf_map_memory { - __u32 pages; -} __attribute__((preserve_access_index)); - struct bpf_map { enum bpf_map_type map_type; __u32 key_size; __u32 value_size; __u32 max_entries; __u32 id; - struct bpf_map_memory memory; } __attribute__((preserve_access_index)); static inline int check_bpf_map_fields(struct bpf_map *map, __u32 key_size, @@ -47,7 +42,6 @@ static inline int check_bpf_map_fields(struct bpf_map *map, __u32 key_size, VERIFY(map->value_size == value_size); VERIFY(map->max_entries == max_entries); VERIFY(map->id > 0); - VERIFY(map->memory.pages > 0); return 1; } @@ -60,7 +54,6 @@ static inline int check_bpf_map_ptr(struct bpf_map *indirect, VERIFY(indirect->value_size == direct->value_size); VERIFY(indirect->max_entries == direct->max_entries); VERIFY(indirect->id == direct->id); - VERIFY(indirect->memory.pages == direct->memory.pages); return 1; } -- cgit v1.2.3 From 3ac1f01b43b6e2759cc34d3a715ba5eed04c5805 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Tue, 1 Dec 2020 13:58:59 -0800 Subject: bpf: Eliminate rlimit-based memory accounting for bpf progs Do not use rlimit-based memory accounting for bpf progs. It has been replaced with memcg-based memory accounting. Signed-off-by: Roman Gushchin Signed-off-by: Alexei Starovoitov Acked-by: Song Liu Link: https://lore.kernel.org/bpf/20201201215900.3569844-34-guro@fb.com --- include/linux/bpf.h | 11 --------- kernel/bpf/core.c | 12 ++------- kernel/bpf/syscall.c | 69 ++++++++-------------------------------------------- 3 files changed, 12 insertions(+), 80 deletions(-) (limited to 'kernel') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 61331a148cde..a9de5711b23f 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1202,8 +1202,6 @@ void bpf_prog_sub(struct bpf_prog *prog, int i); void bpf_prog_inc(struct bpf_prog *prog); struct bpf_prog * __must_check bpf_prog_inc_not_zero(struct bpf_prog *prog); void bpf_prog_put(struct bpf_prog *prog); -int __bpf_prog_charge(struct user_struct *user, u32 pages); -void __bpf_prog_uncharge(struct user_struct *user, u32 pages); void __bpf_free_used_maps(struct bpf_prog_aux *aux, struct bpf_map **used_maps, u32 len); @@ -1512,15 +1510,6 @@ bpf_prog_inc_not_zero(struct bpf_prog *prog) return ERR_PTR(-EOPNOTSUPP); } -static inline int __bpf_prog_charge(struct user_struct *user, u32 pages) -{ - return 0; -} - -static inline void __bpf_prog_uncharge(struct user_struct *user, u32 pages) -{ -} - static inline void bpf_link_init(struct bpf_link *link, enum bpf_link_type type, const struct bpf_link_ops *ops, struct bpf_prog *prog) diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 2921f58c03a8..261f8692d0d2 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -221,23 +221,15 @@ struct bpf_prog *bpf_prog_realloc(struct bpf_prog *fp_old, unsigned int size, { gfp_t gfp_flags = GFP_KERNEL_ACCOUNT | __GFP_ZERO | gfp_extra_flags; struct bpf_prog *fp; - u32 pages, delta; - int ret; + u32 pages; size = round_up(size, PAGE_SIZE); pages = size / PAGE_SIZE; if (pages <= fp_old->pages) return fp_old; - delta = pages - fp_old->pages; - ret = __bpf_prog_charge(fp_old->aux->user, delta); - if (ret) - return NULL; - fp = __vmalloc(size, gfp_flags); - if (fp == NULL) { - __bpf_prog_uncharge(fp_old->aux->user, delta); - } else { + if (fp) { memcpy(fp, fp_old, fp_old->pages * PAGE_SIZE); fp->pages = pages; fp->aux->prog = fp; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 29096d96d989..d16dd4945100 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1632,51 +1632,6 @@ static void bpf_audit_prog(const struct bpf_prog *prog, unsigned int op) audit_log_end(ab); } -int __bpf_prog_charge(struct user_struct *user, u32 pages) -{ - unsigned long memlock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT; - unsigned long user_bufs; - - if (user) { - user_bufs = atomic_long_add_return(pages, &user->locked_vm); - if (user_bufs > memlock_limit) { - atomic_long_sub(pages, &user->locked_vm); - return -EPERM; - } - } - - return 0; -} - -void __bpf_prog_uncharge(struct user_struct *user, u32 pages) -{ - if (user) - atomic_long_sub(pages, &user->locked_vm); -} - -static int bpf_prog_charge_memlock(struct bpf_prog *prog) -{ - struct user_struct *user = get_current_user(); - int ret; - - ret = __bpf_prog_charge(user, prog->pages); - if (ret) { - free_uid(user); - return ret; - } - - prog->aux->user = user; - return 0; -} - -static void bpf_prog_uncharge_memlock(struct bpf_prog *prog) -{ - struct user_struct *user = prog->aux->user; - - __bpf_prog_uncharge(user, prog->pages); - free_uid(user); -} - static int bpf_prog_alloc_id(struct bpf_prog *prog) { int id; @@ -1726,7 +1681,7 @@ static void __bpf_prog_put_rcu(struct rcu_head *rcu) kvfree(aux->func_info); kfree(aux->func_info_aux); - bpf_prog_uncharge_memlock(aux->prog); + free_uid(aux->user); security_bpf_prog_free(aux); bpf_prog_free(aux->prog); } @@ -2164,7 +2119,7 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr) dst_prog = bpf_prog_get(attr->attach_prog_fd); if (IS_ERR(dst_prog)) { err = PTR_ERR(dst_prog); - goto free_prog_nouncharge; + goto free_prog; } prog->aux->dst_prog = dst_prog; } @@ -2174,18 +2129,15 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr) err = security_bpf_prog_alloc(prog->aux); if (err) - goto free_prog_nouncharge; - - err = bpf_prog_charge_memlock(prog); - if (err) - goto free_prog_sec; + goto free_prog; + prog->aux->user = get_current_user(); prog->len = attr->insn_cnt; err = -EFAULT; if (copy_from_user(prog->insns, u64_to_user_ptr(attr->insns), bpf_prog_insn_size(prog)) != 0) - goto free_prog; + goto free_prog_sec; prog->orig_prog = NULL; prog->jited = 0; @@ -2196,19 +2148,19 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr) if (bpf_prog_is_dev_bound(prog->aux)) { err = bpf_prog_offload_init(prog, attr); if (err) - goto free_prog; + goto free_prog_sec; } /* find program type: socket_filter vs tracing_filter */ err = find_prog_type(type, prog); if (err < 0) - goto free_prog; + goto free_prog_sec; prog->aux->load_time = ktime_get_boottime_ns(); err = bpf_obj_name_cpy(prog->aux->name, attr->prog_name, sizeof(attr->prog_name)); if (err < 0) - goto free_prog; + goto free_prog_sec; /* run eBPF verifier */ err = bpf_check(&prog, attr, uattr); @@ -2253,11 +2205,10 @@ free_used_maps: */ __bpf_prog_put_noref(prog, prog->aux->func_cnt); return err; -free_prog: - bpf_prog_uncharge_memlock(prog); free_prog_sec: + free_uid(prog->aux->user); security_bpf_prog_free(prog->aux); -free_prog_nouncharge: +free_prog: bpf_prog_free(prog); return err; } -- cgit v1.2.3 From 12cc126df82c96c89706aa207ad27c56f219047c Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Thu, 3 Dec 2020 12:46:21 -0800 Subject: bpf: Fix bpf_put_raw_tracepoint()'s use of __module_address() __module_address() needs to be called with preemption disabled or with module_mutex taken. preempt_disable() is enough for read-only uses, which is what this fix does. Also, module_put() does internal check for NULL, so drop it as well. Fixes: a38d1107f937 ("bpf: support raw tracepoints in modules") Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/20201203204634.1325171-2-andrii@kernel.org --- kernel/trace/bpf_trace.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index d255bc9b2bfa..23a390aac524 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -2060,10 +2060,12 @@ struct bpf_raw_event_map *bpf_get_raw_tracepoint(const char *name) void bpf_put_raw_tracepoint(struct bpf_raw_event_map *btp) { - struct module *mod = __module_address((unsigned long)btp); + struct module *mod; - if (mod) - module_put(mod); + preempt_disable(); + mod = __module_address((unsigned long)btp); + module_put(mod); + preempt_enable(); } static __always_inline -- cgit v1.2.3 From 2fe8890848c799515a881502339a0a7b2b555988 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Thu, 3 Dec 2020 12:46:22 -0800 Subject: bpf: Keep module's btf_data_size intact after load Having real btf_data_size stored in struct module is benefitial to quickly determine which kernel modules have associated BTF object and which don't. There is no harm in keeping this info, as opposed to keeping invalid pointer. Fixes: 607c543f939d ("bpf: Sanitize BTF data pointer after module is loaded") Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20201203204634.1325171-3-andrii@kernel.org --- kernel/module.c | 1 - 1 file changed, 1 deletion(-) (limited to 'kernel') diff --git a/kernel/module.c b/kernel/module.c index 18f259d61d14..c3a9e972d3b2 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -3712,7 +3712,6 @@ static noinline int do_init_module(struct module *mod) #ifdef CONFIG_DEBUG_INFO_BTF_MODULES /* .BTF is not SHF_ALLOC and will get removed, so sanitize pointer */ mod->btf_data = NULL; - mod->btf_data_size = 0; #endif /* * We want to free module_init, but be aware that kallsyms may be -- cgit v1.2.3 From 22dc4a0f5ed11b6dc8fd73a0892fa0ea1a4c3cdf Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Thu, 3 Dec 2020 12:46:29 -0800 Subject: bpf: Remove hard-coded btf_vmlinux assumption from BPF verifier Remove a permeating assumption thoughout BPF verifier of vmlinux BTF. Instead, wherever BTF type IDs are involved, also track the instance of struct btf that goes along with the type ID. This allows to gradually add support for kernel module BTFs and using/tracking module types across BPF helper calls and registers. This patch also renames btf_id() function to btf_obj_id() to minimize naming clash with using btf_id to denote BTF *type* ID, rather than BTF *object*'s ID. Also, altough btf_vmlinux can't get destructed and thus doesn't need refcounting, module BTFs need that, so apply BTF refcounting universally when BPF program is using BTF-powered attachment (tp_btf, fentry/fexit, etc). This makes for simpler clean up code. Now that BTF type ID is not enough to uniquely identify a BTF type, extend BPF trampoline key to include BTF object ID. To differentiate that from target program BPF ID, set 31st bit of type ID. BTF type IDs (at least currently) are not allowed to take full 32 bits, so there is no danger of confusing that bit with a valid BTF type ID. Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20201203204634.1325171-10-andrii@kernel.org --- include/linux/bpf.h | 13 +++++--- include/linux/bpf_verifier.h | 28 ++++++++++++---- include/linux/btf.h | 5 ++- kernel/bpf/btf.c | 65 +++++++++++++++++++++++++------------ kernel/bpf/syscall.c | 24 ++++++++++++-- kernel/bpf/verifier.c | 77 +++++++++++++++++++++++++++----------------- net/ipv4/bpf_tcp_ca.c | 3 +- 7 files changed, 148 insertions(+), 67 deletions(-) (limited to 'kernel') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index a9de5711b23f..d05e75ed8c1b 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -421,7 +421,10 @@ struct bpf_insn_access_aux { enum bpf_reg_type reg_type; union { int ctx_field_size; - u32 btf_id; + struct { + struct btf *btf; + u32 btf_id; + }; }; struct bpf_verifier_log *log; /* for verbose logs */ }; @@ -458,6 +461,7 @@ struct bpf_verifier_ops { struct bpf_insn *dst, struct bpf_prog *prog, u32 *target_size); int (*btf_struct_access)(struct bpf_verifier_log *log, + const struct btf *btf, const struct btf_type *t, int off, int size, enum bpf_access_type atype, u32 *next_btf_id); @@ -771,6 +775,7 @@ struct bpf_prog_aux { u32 ctx_arg_info_size; u32 max_rdonly_access; u32 max_rdwr_access; + struct btf *attach_btf; const struct bpf_ctx_arg_aux *ctx_arg_info; struct mutex dst_mutex; /* protects dst_* pointers below, *after* prog becomes visible */ struct bpf_prog *dst_prog; @@ -1005,7 +1010,6 @@ struct bpf_event_entry { bool bpf_prog_array_compatible(struct bpf_array *array, const struct bpf_prog *fp); int bpf_prog_calc_tag(struct bpf_prog *fp); -const char *kernel_type_name(u32 btf_type_id); const struct bpf_func_proto *bpf_get_trace_printk_proto(void); @@ -1450,12 +1454,13 @@ int bpf_prog_test_run_raw_tp(struct bpf_prog *prog, bool btf_ctx_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info); -int btf_struct_access(struct bpf_verifier_log *log, +int btf_struct_access(struct bpf_verifier_log *log, const struct btf *btf, const struct btf_type *t, int off, int size, enum bpf_access_type atype, u32 *next_btf_id); bool btf_struct_ids_match(struct bpf_verifier_log *log, - int off, u32 id, u32 need_type_id); + const struct btf *btf, u32 id, int off, + const struct btf *need_btf, u32 need_type_id); int btf_distill_func_proto(struct bpf_verifier_log *log, struct btf *btf, diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 306869d4743b..e941fe1484e5 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -5,6 +5,7 @@ #define _LINUX_BPF_VERIFIER_H 1 #include /* for enum bpf_reg_type */ +#include /* for struct btf and btf_id() */ #include /* for MAX_BPF_STACK */ #include @@ -43,6 +44,8 @@ enum bpf_reg_liveness { struct bpf_reg_state { /* Ordering of fields matters. See states_equal() */ enum bpf_reg_type type; + /* Fixed part of pointer offset, pointer types only */ + s32 off; union { /* valid when type == PTR_TO_PACKET */ int range; @@ -52,15 +55,20 @@ struct bpf_reg_state { */ struct bpf_map *map_ptr; - u32 btf_id; /* for PTR_TO_BTF_ID */ + /* for PTR_TO_BTF_ID */ + struct { + struct btf *btf; + u32 btf_id; + }; u32 mem_size; /* for PTR_TO_MEM | PTR_TO_MEM_OR_NULL */ /* Max size from any of the above. */ - unsigned long raw; + struct { + unsigned long raw1; + unsigned long raw2; + } raw; }; - /* Fixed part of pointer offset, pointer types only */ - s32 off; /* For PTR_TO_PACKET, used to find other pointers with the same variable * offset, so they can share range knowledge. * For PTR_TO_MAP_VALUE_OR_NULL this is used to share which map value we @@ -311,7 +319,10 @@ struct bpf_insn_aux_data { struct { enum bpf_reg_type reg_type; /* type of pseudo_btf_id */ union { - u32 btf_id; /* btf_id for struct typed var */ + struct { + struct btf *btf; + u32 btf_id; /* btf_id for struct typed var */ + }; u32 mem_size; /* mem_size for non-struct typed var */ }; } btf_var; @@ -459,9 +470,12 @@ int check_ctx_reg(struct bpf_verifier_env *env, /* 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, - u32 btf_id) + struct btf *btf, u32 btf_id) { - return tgt_prog ? (((u64)tgt_prog->aux->id) << 32 | btf_id) : btf_id; + if (tgt_prog) + return ((u64)tgt_prog->aux->id << 32) | btf_id; + else + return ((u64)btf_obj_id(btf) << 32) | 0x80000000 | btf_id; } int bpf_check_attach_target(struct bpf_verifier_log *log, diff --git a/include/linux/btf.h b/include/linux/btf.h index 2bf641829664..fb608e4de076 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -18,6 +18,7 @@ struct btf_show; 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); struct btf *btf_get_by_fd(int fd); @@ -88,7 +89,7 @@ int btf_type_snprintf_show(const struct btf *btf, u32 type_id, void *obj, char *buf, int len, u64 flags); int btf_get_fd_by_id(u32 id); -u32 btf_id(const struct btf *btf); +u32 btf_obj_id(const struct btf *btf); bool btf_member_is_reg_int(const struct btf *btf, const struct btf_type *s, const struct btf_member *m, u32 expected_offset, u32 expected_size); @@ -206,6 +207,8 @@ static inline const struct btf_var_secinfo *btf_type_var_secinfo( } #ifdef CONFIG_BPF_SYSCALL +struct bpf_prog; + const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id); const char *btf_name_by_offset(const struct btf *btf, u32 offset); struct btf *btf_parse_vmlinux(void); diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 6b2d508b33d4..7a19bf5bfe97 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -1524,6 +1524,11 @@ static void btf_free_rcu(struct rcu_head *rcu) btf_free(btf); } +void btf_get(struct btf *btf) +{ + refcount_inc(&btf->refcnt); +} + void btf_put(struct btf *btf) { if (btf && refcount_dec_and_test(&btf->refcnt)) { @@ -4555,11 +4560,10 @@ struct btf *bpf_prog_get_target_btf(const struct bpf_prog *prog) { struct bpf_prog *tgt_prog = prog->aux->dst_prog; - if (tgt_prog) { + if (tgt_prog) return tgt_prog->aux->btf; - } else { - return btf_vmlinux; - } + else + return prog->aux->attach_btf; } static bool is_string_ptr(struct btf *btf, const struct btf_type *t) @@ -4700,6 +4704,7 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type, if (ctx_arg_info->offset == off) { info->reg_type = ctx_arg_info->reg_type; + info->btf = btf_vmlinux; info->btf_id = ctx_arg_info->btf_id; return true; } @@ -4716,6 +4721,7 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type, ret = btf_translate_to_vmlinux(log, btf, t, tgt_type, arg); if (ret > 0) { + info->btf = btf_vmlinux; info->btf_id = ret; return true; } else { @@ -4723,6 +4729,7 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type, } } + info->btf = btf; info->btf_id = t->type; t = btf_type_by_id(btf, t->type); /* skip modifiers */ @@ -4749,7 +4756,7 @@ enum bpf_struct_walk_result { WALK_STRUCT, }; -static int btf_struct_walk(struct bpf_verifier_log *log, +static int btf_struct_walk(struct bpf_verifier_log *log, const struct btf *btf, const struct btf_type *t, int off, int size, u32 *next_btf_id) { @@ -4760,7 +4767,7 @@ static int btf_struct_walk(struct bpf_verifier_log *log, u32 vlen, elem_id, mid; again: - tname = __btf_name_by_offset(btf_vmlinux, t->name_off); + tname = __btf_name_by_offset(btf, t->name_off); if (!btf_type_is_struct(t)) { bpf_log(log, "Type '%s' is not a struct\n", tname); return -EINVAL; @@ -4777,7 +4784,7 @@ again: goto error; member = btf_type_member(t) + vlen - 1; - mtype = btf_type_skip_modifiers(btf_vmlinux, member->type, + mtype = btf_type_skip_modifiers(btf, member->type, NULL); if (!btf_type_is_array(mtype)) goto error; @@ -4793,7 +4800,7 @@ again: /* Only allow structure for now, can be relaxed for * other types later. */ - t = btf_type_skip_modifiers(btf_vmlinux, array_elem->type, + t = btf_type_skip_modifiers(btf, array_elem->type, NULL); if (!btf_type_is_struct(t)) goto error; @@ -4851,10 +4858,10 @@ error: /* type of the field */ mid = member->type; - mtype = btf_type_by_id(btf_vmlinux, member->type); - mname = __btf_name_by_offset(btf_vmlinux, member->name_off); + mtype = btf_type_by_id(btf, member->type); + mname = __btf_name_by_offset(btf, member->name_off); - mtype = __btf_resolve_size(btf_vmlinux, mtype, &msize, + mtype = __btf_resolve_size(btf, mtype, &msize, &elem_type, &elem_id, &total_nelems, &mid); if (IS_ERR(mtype)) { @@ -4949,7 +4956,7 @@ error: mname, moff, tname, off, size); return -EACCES; } - stype = btf_type_skip_modifiers(btf_vmlinux, mtype->type, &id); + stype = btf_type_skip_modifiers(btf, mtype->type, &id); if (btf_type_is_struct(stype)) { *next_btf_id = id; return WALK_PTR; @@ -4975,7 +4982,7 @@ error: return -EINVAL; } -int btf_struct_access(struct bpf_verifier_log *log, +int btf_struct_access(struct bpf_verifier_log *log, const struct btf *btf, const struct btf_type *t, int off, int size, enum bpf_access_type atype __maybe_unused, u32 *next_btf_id) @@ -4984,7 +4991,7 @@ int btf_struct_access(struct bpf_verifier_log *log, u32 id; do { - err = btf_struct_walk(log, t, off, size, &id); + err = btf_struct_walk(log, btf, t, off, size, &id); switch (err) { case WALK_PTR: @@ -5000,7 +5007,7 @@ int btf_struct_access(struct bpf_verifier_log *log, * by diving in it. At this point the offset is * aligned with the new type, so set it to 0. */ - t = btf_type_by_id(btf_vmlinux, id); + t = btf_type_by_id(btf, id); off = 0; break; default: @@ -5016,21 +5023,37 @@ int btf_struct_access(struct bpf_verifier_log *log, return -EINVAL; } +/* Check that two BTF types, each specified as an BTF object + id, are exactly + * the same. Trivial ID check is not enough due to module BTFs, because we can + * end up with two different module BTFs, but IDs point to the common type in + * vmlinux BTF. + */ +static bool btf_types_are_same(const struct btf *btf1, u32 id1, + const struct btf *btf2, u32 id2) +{ + if (id1 != id2) + return false; + if (btf1 == btf2) + return true; + return btf_type_by_id(btf1, id1) == btf_type_by_id(btf2, id2); +} + bool btf_struct_ids_match(struct bpf_verifier_log *log, - int off, u32 id, u32 need_type_id) + const struct btf *btf, u32 id, int off, + const struct btf *need_btf, u32 need_type_id) { const struct btf_type *type; int err; /* Are we already done? */ - if (need_type_id == id && off == 0) + if (off == 0 && btf_types_are_same(btf, id, need_btf, need_type_id)) return true; again: - type = btf_type_by_id(btf_vmlinux, id); + type = btf_type_by_id(btf, id); if (!type) return false; - err = btf_struct_walk(log, type, off, 1, &id); + err = btf_struct_walk(log, btf, type, off, 1, &id); if (err != WALK_STRUCT) return false; @@ -5039,7 +5062,7 @@ again: * continue the search with offset 0 in the new * type. */ - if (need_type_id != id) { + if (!btf_types_are_same(btf, id, need_btf, need_type_id)) { off = 0; goto again; } @@ -5710,7 +5733,7 @@ int btf_get_fd_by_id(u32 id) return fd; } -u32 btf_id(const struct btf *btf) +u32 btf_obj_id(const struct btf *btf) { return btf->id; } diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index d16dd4945100..184204169949 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1691,6 +1691,8 @@ static void __bpf_prog_put_noref(struct bpf_prog *prog, bool deferred) bpf_prog_kallsyms_del_all(prog); btf_put(prog->aux->btf); bpf_prog_free_linfo(prog); + if (prog->aux->attach_btf) + btf_put(prog->aux->attach_btf); if (deferred) { if (prog->aux->sleepable) @@ -2113,6 +2115,20 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr) prog->expected_attach_type = attr->expected_attach_type; prog->aux->attach_btf_id = attr->attach_btf_id; + + if (attr->attach_btf_id && !attr->attach_prog_fd) { + struct btf *btf; + + btf = bpf_get_btf_vmlinux(); + if (IS_ERR(btf)) + return PTR_ERR(btf); + if (!btf) + return -EINVAL; + + btf_get(btf); + prog->aux->attach_btf = btf; + } + if (attr->attach_prog_fd) { struct bpf_prog *dst_prog; @@ -2209,6 +2225,8 @@ free_prog_sec: free_uid(prog->aux->user); security_bpf_prog_free(prog->aux); free_prog: + if (prog->aux->attach_btf) + btf_put(prog->aux->attach_btf); bpf_prog_free(prog); return err; } @@ -2566,7 +2584,7 @@ static int bpf_tracing_prog_attach(struct bpf_prog *prog, goto out_put_prog; } - key = bpf_trampoline_compute_key(tgt_prog, btf_id); + key = bpf_trampoline_compute_key(tgt_prog, NULL, btf_id); } link = kzalloc(sizeof(*link), GFP_USER); @@ -3543,7 +3561,7 @@ static int bpf_prog_get_info_by_fd(struct file *file, } if (prog->aux->btf) - info.btf_id = btf_id(prog->aux->btf); + info.btf_id = btf_obj_id(prog->aux->btf); ulen = info.nr_func_info; info.nr_func_info = prog->aux->func_info_cnt; @@ -3646,7 +3664,7 @@ static int bpf_map_get_info_by_fd(struct file *file, memcpy(info.name, map->name, sizeof(map->name)); if (map->btf) { - info.btf_id = btf_id(map->btf); + info.btf_id = btf_obj_id(map->btf); info.btf_key_type_id = map->btf_key_type_id; info.btf_value_type_id = map->btf_value_type_id; } diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index e333ce43f281..2f3950839b85 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -238,7 +238,9 @@ struct bpf_call_arg_meta { u64 msize_max_value; int ref_obj_id; int func_id; + struct btf *btf; u32 btf_id; + struct btf *ret_btf; u32 ret_btf_id; }; @@ -556,10 +558,9 @@ static struct bpf_func_state *func(struct bpf_verifier_env *env, return cur->frame[reg->frameno]; } -const char *kernel_type_name(u32 id) +static const char *kernel_type_name(const struct btf* btf, u32 id) { - return btf_name_by_offset(btf_vmlinux, - btf_type_by_id(btf_vmlinux, id)->name_off); + return btf_name_by_offset(btf, btf_type_by_id(btf, id)->name_off); } static void print_verifier_state(struct bpf_verifier_env *env, @@ -589,7 +590,7 @@ static void print_verifier_state(struct bpf_verifier_env *env, if (t == PTR_TO_BTF_ID || t == PTR_TO_BTF_ID_OR_NULL || t == PTR_TO_PERCPU_BTF_ID) - verbose(env, "%s", kernel_type_name(reg->btf_id)); + verbose(env, "%s", kernel_type_name(reg->btf, reg->btf_id)); verbose(env, "(id=%d", reg->id); if (reg_type_may_be_refcounted_or_null(t)) verbose(env, ",ref_obj_id=%d", reg->ref_obj_id); @@ -1383,7 +1384,8 @@ static void mark_reg_not_init(struct bpf_verifier_env *env, static void mark_btf_ld_reg(struct bpf_verifier_env *env, struct bpf_reg_state *regs, u32 regno, - enum bpf_reg_type reg_type, u32 btf_id) + enum bpf_reg_type reg_type, + struct btf *btf, u32 btf_id) { if (reg_type == SCALAR_VALUE) { mark_reg_unknown(env, regs, regno); @@ -1391,6 +1393,7 @@ static void mark_btf_ld_reg(struct bpf_verifier_env *env, } mark_reg_known_zero(env, regs, regno); regs[regno].type = PTR_TO_BTF_ID; + regs[regno].btf = btf; regs[regno].btf_id = btf_id; } @@ -2764,7 +2767,7 @@ static int check_packet_access(struct bpf_verifier_env *env, u32 regno, int off, /* check access to 'struct bpf_context' fields. Supports fixed offsets only */ static int check_ctx_access(struct bpf_verifier_env *env, int insn_idx, int off, int size, enum bpf_access_type t, enum bpf_reg_type *reg_type, - u32 *btf_id) + struct btf **btf, u32 *btf_id) { struct bpf_insn_access_aux info = { .reg_type = *reg_type, @@ -2782,10 +2785,12 @@ static int check_ctx_access(struct bpf_verifier_env *env, int insn_idx, int off, */ *reg_type = info.reg_type; - if (*reg_type == PTR_TO_BTF_ID || *reg_type == PTR_TO_BTF_ID_OR_NULL) + if (*reg_type == PTR_TO_BTF_ID || *reg_type == PTR_TO_BTF_ID_OR_NULL) { + *btf = info.btf; *btf_id = info.btf_id; - else + } else { env->insn_aux_data[insn_idx].ctx_field_size = info.ctx_field_size; + } /* remember the offset of last byte accessed in ctx */ if (env->prog->aux->max_ctx_offset < off + size) env->prog->aux->max_ctx_offset = off + size; @@ -3297,8 +3302,8 @@ static int check_ptr_to_btf_access(struct bpf_verifier_env *env, int value_regno) { struct bpf_reg_state *reg = regs + regno; - const struct btf_type *t = btf_type_by_id(btf_vmlinux, reg->btf_id); - const char *tname = btf_name_by_offset(btf_vmlinux, t->name_off); + const struct btf_type *t = btf_type_by_id(reg->btf, reg->btf_id); + const char *tname = btf_name_by_offset(reg->btf, t->name_off); u32 btf_id; int ret; @@ -3319,23 +3324,23 @@ static int check_ptr_to_btf_access(struct bpf_verifier_env *env, } if (env->ops->btf_struct_access) { - ret = env->ops->btf_struct_access(&env->log, t, off, size, - atype, &btf_id); + ret = env->ops->btf_struct_access(&env->log, reg->btf, t, + off, size, atype, &btf_id); } else { if (atype != BPF_READ) { verbose(env, "only read is supported\n"); return -EACCES; } - ret = btf_struct_access(&env->log, t, off, size, atype, - &btf_id); + ret = btf_struct_access(&env->log, reg->btf, t, off, size, + atype, &btf_id); } if (ret < 0) return ret; if (atype == BPF_READ && value_regno >= 0) - mark_btf_ld_reg(env, regs, value_regno, ret, btf_id); + mark_btf_ld_reg(env, regs, value_regno, ret, reg->btf, btf_id); return 0; } @@ -3385,12 +3390,12 @@ static int check_ptr_to_map_access(struct bpf_verifier_env *env, return -EACCES; } - ret = btf_struct_access(&env->log, t, off, size, atype, &btf_id); + ret = btf_struct_access(&env->log, btf_vmlinux, t, off, size, atype, &btf_id); if (ret < 0) return ret; if (value_regno >= 0) - mark_btf_ld_reg(env, regs, value_regno, ret, btf_id); + mark_btf_ld_reg(env, regs, value_regno, ret, btf_vmlinux, btf_id); return 0; } @@ -3466,6 +3471,7 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn mark_reg_unknown(env, regs, value_regno); } else if (reg->type == PTR_TO_CTX) { enum bpf_reg_type reg_type = SCALAR_VALUE; + struct btf *btf = NULL; u32 btf_id = 0; if (t == BPF_WRITE && value_regno >= 0 && @@ -3478,7 +3484,7 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn if (err < 0) return err; - err = check_ctx_access(env, insn_idx, off, size, t, ®_type, &btf_id); + err = check_ctx_access(env, insn_idx, off, size, t, ®_type, &btf, &btf_id); if (err) verbose_linfo(env, insn_idx, "; "); if (!err && t == BPF_READ && value_regno >= 0) { @@ -3500,8 +3506,10 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn */ regs[value_regno].subreg_def = DEF_NOT_SUBREG; if (reg_type == PTR_TO_BTF_ID || - reg_type == PTR_TO_BTF_ID_OR_NULL) + reg_type == PTR_TO_BTF_ID_OR_NULL) { + regs[value_regno].btf = btf; regs[value_regno].btf_id = btf_id; + } } regs[value_regno].type = reg_type; } @@ -4118,11 +4126,11 @@ found: arg_btf_id = compatible->btf_id; } - if (!btf_struct_ids_match(&env->log, reg->off, reg->btf_id, - *arg_btf_id)) { + if (!btf_struct_ids_match(&env->log, reg->btf, reg->btf_id, reg->off, + btf_vmlinux, *arg_btf_id)) { verbose(env, "R%d is of type %s but %s is expected\n", - regno, kernel_type_name(reg->btf_id), - kernel_type_name(*arg_btf_id)); + regno, kernel_type_name(reg->btf, reg->btf_id), + kernel_type_name(btf_vmlinux, *arg_btf_id)); return -EACCES; } @@ -4244,6 +4252,7 @@ skip_type_check: verbose(env, "Helper has invalid btf_id in R%d\n", regno); return -EACCES; } + meta->ret_btf = reg->btf; meta->ret_btf_id = reg->btf_id; } else if (arg_type == ARG_PTR_TO_SPIN_LOCK) { if (meta->func_id == BPF_FUNC_spin_lock) { @@ -5190,16 +5199,16 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn const struct btf_type *t; mark_reg_known_zero(env, regs, BPF_REG_0); - t = btf_type_skip_modifiers(btf_vmlinux, meta.ret_btf_id, NULL); + t = btf_type_skip_modifiers(meta.ret_btf, meta.ret_btf_id, NULL); if (!btf_type_is_struct(t)) { u32 tsize; const struct btf_type *ret; const char *tname; /* resolve the type size of ksym. */ - ret = btf_resolve_size(btf_vmlinux, t, &tsize); + ret = btf_resolve_size(meta.ret_btf, t, &tsize); if (IS_ERR(ret)) { - tname = btf_name_by_offset(btf_vmlinux, t->name_off); + tname = btf_name_by_offset(meta.ret_btf, t->name_off); verbose(env, "unable to resolve the size of type '%s': %ld\n", tname, PTR_ERR(ret)); return -EINVAL; @@ -5212,6 +5221,7 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn regs[BPF_REG_0].type = fn->ret_type == RET_PTR_TO_MEM_OR_BTF_ID ? PTR_TO_BTF_ID : PTR_TO_BTF_ID_OR_NULL; + regs[BPF_REG_0].btf = meta.ret_btf; regs[BPF_REG_0].btf_id = meta.ret_btf_id; } } else if (fn->ret_type == RET_PTR_TO_BTF_ID_OR_NULL || @@ -5228,6 +5238,10 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn fn->ret_type, func_id_name(func_id), func_id); return -EINVAL; } + /* current BPF helper definitions are only coming from + * built-in code with type IDs from vmlinux BTF + */ + regs[BPF_REG_0].btf = btf_vmlinux; regs[BPF_REG_0].btf_id = ret_btf_id; } else { verbose(env, "unknown return type %d of func %s#%d\n", @@ -5627,7 +5641,7 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, if (reg_is_pkt_pointer(ptr_reg)) { dst_reg->id = ++env->id_gen; /* something was added to pkt_ptr, set range to zero */ - dst_reg->raw = 0; + memset(&dst_reg->raw, 0, sizeof(dst_reg->raw)); } break; case BPF_SUB: @@ -5692,7 +5706,7 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, dst_reg->id = ++env->id_gen; /* something was added to pkt_ptr, set range to zero */ if (smin_val < 0) - dst_reg->raw = 0; + memset(&dst_reg->raw, 0, sizeof(dst_reg->raw)); } break; case BPF_AND: @@ -7744,6 +7758,7 @@ static int check_ld_imm(struct bpf_verifier_env *env, struct bpf_insn *insn) break; case PTR_TO_BTF_ID: case PTR_TO_PERCPU_BTF_ID: + dst_reg->btf = aux->btf_var.btf; dst_reg->btf_id = aux->btf_var.btf_id; break; default: @@ -9739,6 +9754,7 @@ static int check_pseudo_btf_id(struct bpf_verifier_env *env, t = btf_type_skip_modifiers(btf_vmlinux, type, NULL); if (percpu) { aux->btf_var.reg_type = PTR_TO_PERCPU_BTF_ID; + aux->btf_var.btf = btf_vmlinux; aux->btf_var.btf_id = type; } else if (!btf_type_is_struct(t)) { const struct btf_type *ret; @@ -9757,6 +9773,7 @@ static int check_pseudo_btf_id(struct bpf_verifier_env *env, aux->btf_var.mem_size = tsize; } else { aux->btf_var.reg_type = PTR_TO_BTF_ID; + aux->btf_var.btf = btf_vmlinux; aux->btf_var.btf_id = type; } return 0; @@ -11609,7 +11626,7 @@ int bpf_check_attach_target(struct bpf_verifier_log *log, bpf_log(log, "Tracing programs must provide btf_id\n"); return -EINVAL; } - btf = tgt_prog ? tgt_prog->aux->btf : btf_vmlinux; + btf = tgt_prog ? tgt_prog->aux->btf : prog->aux->attach_btf; if (!btf) { bpf_log(log, "FENTRY/FEXIT program can only be attached to another program annotated with BTF\n"); @@ -11885,7 +11902,7 @@ static int check_attach_btf_id(struct bpf_verifier_env *env) return ret; } - key = bpf_trampoline_compute_key(tgt_prog, btf_id); + key = bpf_trampoline_compute_key(tgt_prog, prog->aux->attach_btf, btf_id); tr = bpf_trampoline_get(key, &tgt_info); if (!tr) return -ENOMEM; diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c index 618954f82764..d520e61649c8 100644 --- a/net/ipv4/bpf_tcp_ca.c +++ b/net/ipv4/bpf_tcp_ca.c @@ -95,6 +95,7 @@ static bool bpf_tcp_ca_is_valid_access(int off, int size, } static int bpf_tcp_ca_btf_struct_access(struct bpf_verifier_log *log, + const struct btf *btf, const struct btf_type *t, int off, int size, enum bpf_access_type atype, u32 *next_btf_id) @@ -102,7 +103,7 @@ static int bpf_tcp_ca_btf_struct_access(struct bpf_verifier_log *log, size_t end; if (atype == BPF_READ) - return btf_struct_access(log, t, off, size, atype, next_btf_id); + return btf_struct_access(log, btf, t, off, size, atype, next_btf_id); if (t != tcp_sock_type) { bpf_log(log, "only read is supported\n"); -- cgit v1.2.3 From 290248a5b7d829871b3ea3c62578613a580a1744 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Thu, 3 Dec 2020 12:46:30 -0800 Subject: bpf: Allow to specify kernel module BTFs when attaching BPF programs Add ability for user-space programs to specify non-vmlinux BTF when attaching BTF-powered BPF programs: raw_tp, fentry/fexit/fmod_ret, LSM, etc. For this, attach_prog_fd (now with the alias name attach_btf_obj_fd) should specify FD of a module or vmlinux BTF object. For backwards compatibility reasons, 0 denotes vmlinux BTF. Only kernel BTF (vmlinux or module) can be specified. Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20201203204634.1325171-11-andrii@kernel.org --- include/linux/btf.h | 1 + include/uapi/linux/bpf.h | 7 +++- kernel/bpf/btf.c | 5 +++ kernel/bpf/syscall.c | 82 ++++++++++++++++++++++++++---------------- tools/include/uapi/linux/bpf.h | 7 +++- 5 files changed, 69 insertions(+), 33 deletions(-) (limited to 'kernel') diff --git a/include/linux/btf.h b/include/linux/btf.h index fb608e4de076..4c200f5d242b 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -90,6 +90,7 @@ int btf_type_snprintf_show(const struct btf *btf, u32 type_id, void *obj, int btf_get_fd_by_id(u32 id); u32 btf_obj_id(const struct btf *btf); +bool btf_is_kernel(const struct btf *btf); bool btf_member_is_reg_int(const struct btf *btf, const struct btf_type *s, const struct btf_member *m, u32 expected_offset, u32 expected_size); diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index c3458ec1f30a..1233f14f659f 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -557,7 +557,12 @@ union bpf_attr { __aligned_u64 line_info; /* line info */ __u32 line_info_cnt; /* number of bpf_line_info records */ __u32 attach_btf_id; /* in-kernel BTF type id to attach to */ - __u32 attach_prog_fd; /* 0 to attach to vmlinux */ + union { + /* valid prog_fd to attach to bpf prog */ + __u32 attach_prog_fd; + /* or valid module BTF object fd or 0 to attach to vmlinux */ + __u32 attach_btf_obj_fd; + }; }; struct { /* anonymous struct used by BPF_OBJ_* commands */ diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 7a19bf5bfe97..8d6bdb4f4d61 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -5738,6 +5738,11 @@ u32 btf_obj_id(const struct btf *btf) return btf->id; } +bool btf_is_kernel(const struct btf *btf) +{ + return btf->kernel_btf; +} + static int btf_id_cmp_func(const void *a, const void *b) { const int *pa = a, *pb = b; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 184204169949..0cd3cc2af9c1 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1926,12 +1926,16 @@ static void bpf_prog_load_fixup_attach_type(union bpf_attr *attr) static int bpf_prog_load_check_attach(enum bpf_prog_type prog_type, enum bpf_attach_type expected_attach_type, - u32 btf_id, u32 prog_fd) + struct btf *attach_btf, u32 btf_id, + struct bpf_prog *dst_prog) { if (btf_id) { if (btf_id > BTF_MAX_TYPE) return -EINVAL; + if (!attach_btf && !dst_prog) + return -EINVAL; + switch (prog_type) { case BPF_PROG_TYPE_TRACING: case BPF_PROG_TYPE_LSM: @@ -1943,7 +1947,10 @@ bpf_prog_load_check_attach(enum bpf_prog_type prog_type, } } - if (prog_fd && prog_type != BPF_PROG_TYPE_TRACING && + if (attach_btf && (!btf_id || dst_prog)) + return -EINVAL; + + if (dst_prog && prog_type != BPF_PROG_TYPE_TRACING && prog_type != BPF_PROG_TYPE_EXT) return -EINVAL; @@ -2060,7 +2067,8 @@ static bool is_perfmon_prog_type(enum bpf_prog_type prog_type) static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr) { enum bpf_prog_type type = attr->prog_type; - struct bpf_prog *prog; + struct bpf_prog *prog, *dst_prog = NULL; + struct btf *attach_btf = NULL; int err; char license[128]; bool is_gpl; @@ -2102,44 +2110,56 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr) if (is_perfmon_prog_type(type) && !perfmon_capable()) return -EPERM; + /* attach_prog_fd/attach_btf_obj_fd can specify fd of either bpf_prog + * or btf, we need to check which one it is + */ + if (attr->attach_prog_fd) { + dst_prog = bpf_prog_get(attr->attach_prog_fd); + if (IS_ERR(dst_prog)) { + dst_prog = NULL; + attach_btf = btf_get_by_fd(attr->attach_btf_obj_fd); + if (IS_ERR(attach_btf)) + return -EINVAL; + if (!btf_is_kernel(attach_btf)) { + btf_put(attach_btf); + return -EINVAL; + } + } + } else if (attr->attach_btf_id) { + /* fall back to vmlinux BTF, if BTF type ID is specified */ + attach_btf = bpf_get_btf_vmlinux(); + if (IS_ERR(attach_btf)) + return PTR_ERR(attach_btf); + if (!attach_btf) + return -EINVAL; + btf_get(attach_btf); + } + bpf_prog_load_fixup_attach_type(attr); if (bpf_prog_load_check_attach(type, attr->expected_attach_type, - attr->attach_btf_id, - attr->attach_prog_fd)) + attach_btf, attr->attach_btf_id, + dst_prog)) { + if (dst_prog) + bpf_prog_put(dst_prog); + if (attach_btf) + btf_put(attach_btf); return -EINVAL; + } /* plain bpf_prog allocation */ prog = bpf_prog_alloc(bpf_prog_size(attr->insn_cnt), GFP_USER); - if (!prog) + if (!prog) { + if (dst_prog) + bpf_prog_put(dst_prog); + if (attach_btf) + btf_put(attach_btf); return -ENOMEM; + } prog->expected_attach_type = attr->expected_attach_type; + prog->aux->attach_btf = attach_btf; prog->aux->attach_btf_id = attr->attach_btf_id; - - if (attr->attach_btf_id && !attr->attach_prog_fd) { - struct btf *btf; - - btf = bpf_get_btf_vmlinux(); - if (IS_ERR(btf)) - return PTR_ERR(btf); - if (!btf) - return -EINVAL; - - btf_get(btf); - prog->aux->attach_btf = btf; - } - - if (attr->attach_prog_fd) { - struct bpf_prog *dst_prog; - - dst_prog = bpf_prog_get(attr->attach_prog_fd); - if (IS_ERR(dst_prog)) { - err = PTR_ERR(dst_prog); - goto free_prog; - } - prog->aux->dst_prog = dst_prog; - } - + prog->aux->dst_prog = dst_prog; prog->aux->offload_requested = !!attr->prog_ifindex; prog->aux->sleepable = attr->prog_flags & BPF_F_SLEEPABLE; diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index c3458ec1f30a..1233f14f659f 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -557,7 +557,12 @@ union bpf_attr { __aligned_u64 line_info; /* line info */ __u32 line_info_cnt; /* number of bpf_line_info records */ __u32 attach_btf_id; /* in-kernel BTF type id to attach to */ - __u32 attach_prog_fd; /* 0 to attach to vmlinux */ + union { + /* valid prog_fd to attach to bpf prog */ + __u32 attach_prog_fd; + /* or valid module BTF object fd or 0 to attach to vmlinux */ + __u32 attach_btf_obj_fd; + }; }; struct { /* anonymous struct used by BPF_OBJ_* commands */ -- cgit v1.2.3