From: Alexei Starovoitov <alexei.starovoitov@gmail.com>
To: bpf@vger.kernel.org
Cc: daniel@iogearbox.net, andrii@kernel.org, martin.lau@kernel.org,
memxor@gmail.com, eddyz87@gmail.com, tj@kernel.org,
brho@google.com, hannes@cmpxchg.org, linux-mm@kvack.org,
kernel-team@fb.com
Subject: [PATCH bpf-next 08/16] bpf: Recognize cast_kern/user instructions in the verifier.
Date: Tue, 6 Feb 2024 14:04:33 -0800 [thread overview]
Message-ID: <20240206220441.38311-9-alexei.starovoitov@gmail.com> (raw)
In-Reply-To: <20240206220441.38311-1-alexei.starovoitov@gmail.com>
From: Alexei Starovoitov <ast@kernel.org>
rX = bpf_cast_kern(rY, addr_space) tells the verifier that rX->type = PTR_TO_ARENA.
Any further operations on PTR_TO_ARENA register have to be in 32-bit domain.
The verifier will mark load/store through PTR_TO_ARENA with PROBE_MEM32.
JIT will generate them as kern_vm_start + 32bit_addr memory accesses.
rX = bpf_cast_user(rY, addr_space) tells the verifier that rX->type = unknown scalar.
If arena->map_flags has BPF_F_NO_USER_CONV set then convert cast_user to mov32 as well.
Otherwise JIT will convert it to:
rX = (u32)rY;
if (rX)
rX |= arena->user_vm_start & ~(u64)~0U;
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
include/linux/bpf.h | 1 +
include/linux/bpf_verifier.h | 1 +
kernel/bpf/log.c | 3 ++
kernel/bpf/verifier.c | 94 +++++++++++++++++++++++++++++++++---
4 files changed, 92 insertions(+), 7 deletions(-)
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index a0d737bb86d1..82f7727e434a 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -886,6 +886,7 @@ enum bpf_reg_type {
* an explicit null check is required for this struct.
*/
PTR_TO_MEM, /* reg points to valid memory region */
+ PTR_TO_ARENA,
PTR_TO_BUF, /* reg points to a read/write buffer */
PTR_TO_FUNC, /* reg points to a bpf program function */
CONST_PTR_TO_DYNPTR, /* reg points to a const struct bpf_dynptr */
diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index 84365e6dd85d..43c95e3e2a3c 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -547,6 +547,7 @@ struct bpf_insn_aux_data {
u32 seen; /* this insn was processed by the verifier at env->pass_cnt */
bool sanitize_stack_spill; /* subject to Spectre v4 sanitation */
bool zext_dst; /* this insn zero extends dst reg */
+ bool needs_zext; /* alu op needs to clear upper bits */
bool storage_get_func_atomic; /* bpf_*_storage_get() with atomic memory alloc */
bool is_iter_next; /* bpf_iter_<type>_next() kfunc call */
bool call_with_percpu_alloc_ptr; /* {this,per}_cpu_ptr() with prog percpu alloc */
diff --git a/kernel/bpf/log.c b/kernel/bpf/log.c
index 594a234f122b..677076c760ff 100644
--- a/kernel/bpf/log.c
+++ b/kernel/bpf/log.c
@@ -416,6 +416,7 @@ const char *reg_type_str(struct bpf_verifier_env *env, enum bpf_reg_type type)
[PTR_TO_XDP_SOCK] = "xdp_sock",
[PTR_TO_BTF_ID] = "ptr_",
[PTR_TO_MEM] = "mem",
+ [PTR_TO_ARENA] = "arena",
[PTR_TO_BUF] = "buf",
[PTR_TO_FUNC] = "func",
[PTR_TO_MAP_KEY] = "map_key",
@@ -651,6 +652,8 @@ static void print_reg_state(struct bpf_verifier_env *env,
}
verbose(env, "%s", reg_type_str(env, t));
+ if (t == PTR_TO_ARENA)
+ return;
if (t == PTR_TO_STACK) {
if (state->frameno != reg->frameno)
verbose(env, "[%d]", reg->frameno);
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 3c77a3ab1192..6bd5a0f30f72 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -4370,6 +4370,7 @@ static bool is_spillable_regtype(enum bpf_reg_type type)
case PTR_TO_MEM:
case PTR_TO_FUNC:
case PTR_TO_MAP_KEY:
+ case PTR_TO_ARENA:
return true;
default:
return false;
@@ -5805,6 +5806,8 @@ static int check_ptr_alignment(struct bpf_verifier_env *env,
case PTR_TO_XDP_SOCK:
pointer_desc = "xdp_sock ";
break;
+ case PTR_TO_ARENA:
+ return 0;
default:
break;
}
@@ -6906,6 +6909,9 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
if (!err && value_regno >= 0 && (rdonly_mem || t == BPF_READ))
mark_reg_unknown(env, regs, value_regno);
+ } else if (reg->type == PTR_TO_ARENA) {
+ if (t == BPF_READ && value_regno >= 0)
+ mark_reg_unknown(env, regs, value_regno);
} else {
verbose(env, "R%d invalid mem access '%s'\n", regno,
reg_type_str(env, reg->type));
@@ -8377,6 +8383,7 @@ static int check_func_arg_reg_off(struct bpf_verifier_env *env,
case PTR_TO_MEM | MEM_RINGBUF:
case PTR_TO_BUF:
case PTR_TO_BUF | MEM_RDONLY:
+ case PTR_TO_ARENA:
case SCALAR_VALUE:
return 0;
/* All the rest must be rejected, except PTR_TO_BTF_ID which allows
@@ -13837,6 +13844,21 @@ static int adjust_reg_min_max_vals(struct bpf_verifier_env *env,
dst_reg = ®s[insn->dst_reg];
src_reg = NULL;
+
+ if (dst_reg->type == PTR_TO_ARENA) {
+ struct bpf_insn_aux_data *aux = cur_aux(env);
+
+ if (BPF_CLASS(insn->code) == BPF_ALU64)
+ /*
+ * 32-bit operations zero upper bits automatically.
+ * 64-bit operations need to be converted to 32.
+ */
+ aux->needs_zext = true;
+
+ /* Any arithmetic operations are allowed on arena pointers */
+ return 0;
+ }
+
if (dst_reg->type != SCALAR_VALUE)
ptr_reg = dst_reg;
else
@@ -13954,16 +13976,17 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
} else if (opcode == BPF_MOV) {
if (BPF_SRC(insn->code) == BPF_X) {
- if (insn->imm != 0) {
- verbose(env, "BPF_MOV uses reserved fields\n");
- return -EINVAL;
- }
-
if (BPF_CLASS(insn->code) == BPF_ALU) {
- if (insn->off != 0 && insn->off != 8 && insn->off != 16) {
+ if ((insn->off != 0 && insn->off != 8 && insn->off != 16) ||
+ insn->imm) {
verbose(env, "BPF_MOV uses reserved fields\n");
return -EINVAL;
}
+ } else if (insn->off == BPF_ARENA_CAST_KERN || insn->off == BPF_ARENA_CAST_USER) {
+ if (!insn->imm) {
+ verbose(env, "cast_kern/user insn must have non zero imm32\n");
+ return -EINVAL;
+ }
} else {
if (insn->off != 0 && insn->off != 8 && insn->off != 16 &&
insn->off != 32) {
@@ -13993,7 +14016,12 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
struct bpf_reg_state *dst_reg = regs + insn->dst_reg;
if (BPF_CLASS(insn->code) == BPF_ALU64) {
- if (insn->off == 0) {
+ if (insn->imm) {
+ /* off == BPF_ARENA_CAST_KERN || off == BPF_ARENA_CAST_USER */
+ mark_reg_unknown(env, regs, insn->dst_reg);
+ if (insn->off == BPF_ARENA_CAST_KERN)
+ dst_reg->type = PTR_TO_ARENA;
+ } else if (insn->off == 0) {
/* case: R1 = R2
* copy register state to dest reg
*/
@@ -14059,6 +14087,9 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
dst_reg->subreg_def = env->insn_idx + 1;
coerce_subreg_to_size_sx(dst_reg, insn->off >> 3);
}
+ } else if (src_reg->type == PTR_TO_ARENA) {
+ mark_reg_unknown(env, regs, insn->dst_reg);
+ dst_reg->type = PTR_TO_ARENA;
} else {
mark_reg_unknown(env, regs,
insn->dst_reg);
@@ -16519,6 +16550,8 @@ static bool regsafe(struct bpf_verifier_env *env, struct bpf_reg_state *rold,
* the same stack frame, since fp-8 in foo != fp-8 in bar
*/
return regs_exact(rold, rcur, idmap) && rold->frameno == rcur->frameno;
+ case PTR_TO_ARENA:
+ return true;
default:
return regs_exact(rold, rcur, idmap);
}
@@ -18235,6 +18268,27 @@ static int resolve_pseudo_ldimm64(struct bpf_verifier_env *env)
fdput(f);
return -EBUSY;
}
+ if (map->map_type == BPF_MAP_TYPE_ARENA) {
+ if (env->prog->aux->arena) {
+ verbose(env, "Only one arena per program\n");
+ fdput(f);
+ return -EBUSY;
+ }
+ if (!env->allow_ptr_leaks || !env->bpf_capable) {
+ verbose(env, "CAP_BPF and CAP_PERFMON are required to use arena\n");
+ fdput(f);
+ return -EPERM;
+ }
+ if (!env->prog->jit_requested) {
+ verbose(env, "JIT is required to use arena\n");
+ return -EOPNOTSUPP;
+ }
+ if (!bpf_jit_supports_arena()) {
+ verbose(env, "JIT doesn't support arena\n");
+ return -EOPNOTSUPP;
+ }
+ env->prog->aux->arena = (void *)map;
+ }
fdput(f);
next_insn:
@@ -18799,6 +18853,18 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
insn->code == (BPF_ST | BPF_MEM | BPF_W) ||
insn->code == (BPF_ST | BPF_MEM | BPF_DW)) {
type = BPF_WRITE;
+ } else if (insn->code == (BPF_ALU64 | BPF_MOV | BPF_X) && insn->imm) {
+ if (insn->off == BPF_ARENA_CAST_KERN ||
+ (((struct bpf_map *)env->prog->aux->arena)->map_flags & BPF_F_NO_USER_CONV)) {
+ /* convert to 32-bit mov that clears upper 32-bit */
+ insn->code = BPF_ALU | BPF_MOV | BPF_X;
+ /* clear off, so it's a normal 'wX = wY' from JIT pov */
+ insn->off = 0;
+ } /* else insn->off == BPF_ARENA_CAST_USER should be handled by JIT */
+ continue;
+ } else if (env->insn_aux_data[i + delta].needs_zext) {
+ /* Convert BPF_CLASS(insn->code) == BPF_ALU64 to 32-bit ALU */
+ insn->code = BPF_ALU | BPF_OP(insn->code) | BPF_SRC(insn->code);
} else {
continue;
}
@@ -18856,6 +18922,14 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
env->prog->aux->num_exentries++;
}
continue;
+ case PTR_TO_ARENA:
+ if (BPF_MODE(insn->code) == BPF_MEMSX) {
+ verbose(env, "sign extending loads from arena are not supported yet\n");
+ return -EOPNOTSUPP;
+ }
+ insn->code = BPF_CLASS(insn->code) | BPF_PROBE_MEM32 | BPF_SIZE(insn->code);
+ env->prog->aux->num_exentries++;
+ continue;
default:
continue;
}
@@ -19041,13 +19115,19 @@ static int jit_subprogs(struct bpf_verifier_env *env)
func[i]->aux->nr_linfo = prog->aux->nr_linfo;
func[i]->aux->jited_linfo = prog->aux->jited_linfo;
func[i]->aux->linfo_idx = env->subprog_info[i].linfo_idx;
+ func[i]->aux->arena = prog->aux->arena;
num_exentries = 0;
insn = func[i]->insnsi;
for (j = 0; j < func[i]->len; j++, insn++) {
if (BPF_CLASS(insn->code) == BPF_LDX &&
(BPF_MODE(insn->code) == BPF_PROBE_MEM ||
+ BPF_MODE(insn->code) == BPF_PROBE_MEM32 ||
BPF_MODE(insn->code) == BPF_PROBE_MEMSX))
num_exentries++;
+ if ((BPF_CLASS(insn->code) == BPF_STX ||
+ BPF_CLASS(insn->code) == BPF_ST) &&
+ BPF_MODE(insn->code) == BPF_PROBE_MEM32)
+ num_exentries++;
}
func[i]->aux->num_exentries = num_exentries;
func[i]->aux->tail_call_reachable = env->subprog_info[i].tail_call_reachable;
--
2.34.1
next prev parent reply other threads:[~2024-02-06 22:05 UTC|newest]
Thread overview: 56+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-02-06 22:04 [PATCH bpf-next 00/16] bpf: Introduce BPF arena Alexei Starovoitov
2024-02-06 22:04 ` [PATCH bpf-next 01/16] bpf: Allow kfuncs return 'void *' Alexei Starovoitov
2024-02-08 19:40 ` Andrii Nakryiko
2024-02-09 0:09 ` Alexei Starovoitov
2024-02-09 19:09 ` Andrii Nakryiko
2024-02-10 2:32 ` Alexei Starovoitov
2024-02-09 16:06 ` David Vernet
2024-02-06 22:04 ` [PATCH bpf-next 02/16] bpf: Recognize '__map' suffix in kfunc arguments Alexei Starovoitov
2024-02-09 16:57 ` David Vernet
2024-02-09 17:46 ` Alexei Starovoitov
2024-02-09 18:11 ` David Vernet
2024-02-09 18:59 ` Alexei Starovoitov
2024-02-09 19:18 ` David Vernet
2024-02-06 22:04 ` [PATCH bpf-next 03/16] mm: Expose vmap_pages_range() to the rest of the kernel Alexei Starovoitov
2024-02-07 21:07 ` Lorenzo Stoakes
2024-02-07 22:56 ` Alexei Starovoitov
2024-02-08 5:44 ` Johannes Weiner
2024-02-08 23:55 ` Alexei Starovoitov
2024-02-09 6:36 ` Lorenzo Stoakes
2024-02-14 8:31 ` Christoph Hellwig
2024-02-06 22:04 ` [PATCH bpf-next 04/16] bpf: Introduce bpf_arena Alexei Starovoitov
2024-02-07 18:40 ` Barret Rhoden
2024-02-07 20:55 ` Alexei Starovoitov
2024-02-07 21:11 ` Barret Rhoden
2024-02-08 6:26 ` Alexei Starovoitov
2024-02-08 21:58 ` Barret Rhoden
2024-02-08 23:36 ` Alexei Starovoitov
2024-02-08 23:50 ` Barret Rhoden
2024-02-06 22:04 ` [PATCH bpf-next 05/16] bpf: Disasm support for cast_kern/user instructions Alexei Starovoitov
2024-02-06 22:04 ` [PATCH bpf-next 06/16] bpf: Add x86-64 JIT support for PROBE_MEM32 pseudo instructions Alexei Starovoitov
2024-02-06 22:04 ` [PATCH bpf-next 07/16] bpf: Add x86-64 JIT support for bpf_cast_user instruction Alexei Starovoitov
2024-02-06 22:04 ` Alexei Starovoitov [this message]
2024-02-06 22:04 ` [PATCH bpf-next 09/16] bpf: Recognize btf_decl_tag("arg:arena") as PTR_TO_ARENA Alexei Starovoitov
2024-02-06 22:04 ` [PATCH bpf-next 10/16] libbpf: Add __arg_arena to bpf_helpers.h Alexei Starovoitov
2024-02-06 22:04 ` [PATCH bpf-next 11/16] libbpf: Add support for bpf_arena Alexei Starovoitov
2024-02-08 1:15 ` Andrii Nakryiko
2024-02-08 1:38 ` Alexei Starovoitov
2024-02-08 18:29 ` Andrii Nakryiko
2024-02-08 18:45 ` Alexei Starovoitov
2024-02-08 18:54 ` Andrii Nakryiko
2024-02-08 18:59 ` Alexei Starovoitov
2024-02-06 22:04 ` [PATCH bpf-next 12/16] libbpf: Allow specifying 64-bit integers in map BTF Alexei Starovoitov
2024-02-08 1:16 ` Andrii Nakryiko
2024-02-08 1:58 ` Alexei Starovoitov
2024-02-08 18:16 ` Andrii Nakryiko
2024-02-06 22:04 ` [PATCH bpf-next 13/16] bpf: Tell bpf programs kernel's PAGE_SIZE Alexei Starovoitov
2024-02-06 22:04 ` [PATCH bpf-next 14/16] bpf: Add helper macro bpf_arena_cast() Alexei Starovoitov
2024-02-06 22:04 ` [PATCH bpf-next 15/16] selftests/bpf: Add bpf_arena_list test Alexei Starovoitov
2024-02-07 17:04 ` Eduard Zingerman
2024-02-08 2:59 ` Alexei Starovoitov
2024-02-08 11:10 ` Jose E. Marchesi
2024-02-06 22:04 ` [PATCH bpf-next 16/16] selftests/bpf: Add bpf_arena_htab test Alexei Starovoitov
2024-02-07 12:34 ` [PATCH bpf-next 00/16] bpf: Introduce BPF arena Donald Hunter
2024-02-07 13:33 ` Barret Rhoden
2024-02-07 20:16 ` Alexei Starovoitov
2024-02-07 20:12 ` Alexei Starovoitov
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20240206220441.38311-9-alexei.starovoitov@gmail.com \
--to=alexei.starovoitov@gmail.com \
--cc=andrii@kernel.org \
--cc=bpf@vger.kernel.org \
--cc=brho@google.com \
--cc=daniel@iogearbox.net \
--cc=eddyz87@gmail.com \
--cc=hannes@cmpxchg.org \
--cc=kernel-team@fb.com \
--cc=linux-mm@kvack.org \
--cc=martin.lau@kernel.org \
--cc=memxor@gmail.com \
--cc=tj@kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox