diff mbox series

[v3,bpf,2/3] bpf: Avoid iter->offset making backward progress in bpf_iter_udp

Message ID 20240112190530.3751661-3-martin.lau@linux.dev (mailing list archive)
State Accepted
Commit 2242fd537fab52d5f4d2fbb1845f047c01fad0cf
Delegated to: BPF
Headers show
Series bpf: Fix backward progress bug in bpf_iter_udp | expand

Checks

Context Check Description
bpf/vmtest-bpf-PR success PR summary
netdev/series_format success Posting correctly formatted
netdev/tree_selection success Clearly marked for bpf
netdev/ynl success SINGLE THREAD; Generated files up to date; no warnings/errors; no diff in generated;
netdev/fixes_present success Fixes tag present in non-next series
netdev/header_inline success No static functions without inline keyword in header files
netdev/build_32bit success Errors and warnings before: 1100 this patch: 1100
netdev/cc_maintainers success CCed 0 of 0 maintainers
netdev/build_clang success Errors and warnings before: 1108 this patch: 1108
netdev/verify_signedoff success Signed-off-by tag matches author and committer
netdev/deprecated_api success None detected
netdev/check_selftest success No net selftest shell script
netdev/verify_fixes success Fixes tag looks correct
netdev/build_allmodconfig_warn success Errors and warnings before: 1115 this patch: 1115
netdev/checkpatch success total: 0 errors, 0 warnings, 0 checks, 54 lines checked
netdev/build_clang_rust success No Rust files in patch. Skipping build
netdev/kdoc success Errors and warnings before: 0 this patch: 0
netdev/source_inline success Was 0 now: 0
bpf/vmtest-bpf-VM_Test-0 success Logs for Lint
bpf/vmtest-bpf-VM_Test-1 success Logs for ShellCheck
bpf/vmtest-bpf-VM_Test-2 success Logs for Unittests
bpf/vmtest-bpf-VM_Test-3 success Logs for Validate matrix.py
bpf/vmtest-bpf-VM_Test-5 success Logs for aarch64-gcc / build-release
bpf/vmtest-bpf-VM_Test-6 success Logs for aarch64-gcc / test (test_maps, false, 360) / test_maps on aarch64 with gcc
bpf/vmtest-bpf-VM_Test-4 success Logs for aarch64-gcc / build / build for aarch64 with gcc
bpf/vmtest-bpf-VM_Test-9 success Logs for aarch64-gcc / test (test_verifier, false, 360) / test_verifier on aarch64 with gcc
bpf/vmtest-bpf-VM_Test-10 success Logs for aarch64-gcc / veristat
bpf/vmtest-bpf-VM_Test-12 success Logs for s390x-gcc / build-release
bpf/vmtest-bpf-VM_Test-15 success Logs for x86_64-gcc / build-release
bpf/vmtest-bpf-VM_Test-14 success Logs for x86_64-gcc / build / build for x86_64 with gcc
bpf/vmtest-bpf-VM_Test-13 success Logs for set-matrix
bpf/vmtest-bpf-VM_Test-29 success Logs for x86_64-llvm-17 / veristat
bpf/vmtest-bpf-VM_Test-33 success Logs for x86_64-llvm-17 / test (test_verifier, false, 360) / test_verifier on x86_64 with llvm-17
bpf/vmtest-bpf-VM_Test-34 success Logs for x86_64-llvm-17 / veristat
bpf/vmtest-bpf-VM_Test-35 success Logs for x86_64-llvm-18 / build / build for x86_64 with llvm-18
bpf/vmtest-bpf-VM_Test-17 success Logs for s390x-gcc / veristat
bpf/vmtest-bpf-VM_Test-27 success Logs for x86_64-gcc / veristat / veristat on x86_64 with gcc
bpf/vmtest-bpf-VM_Test-30 success Logs for x86_64-llvm-17 / test (test_maps, false, 360) / test_maps on x86_64 with llvm-17
bpf/vmtest-bpf-VM_Test-18 success Logs for set-matrix
bpf/vmtest-bpf-VM_Test-37 success Logs for x86_64-llvm-18 / test (test_maps, false, 360) / test_maps on x86_64 with llvm-18
bpf/vmtest-bpf-VM_Test-19 success Logs for x86_64-gcc / build / build for x86_64 with gcc
bpf/vmtest-bpf-VM_Test-26 success Logs for x86_64-gcc / test (test_verifier, false, 360) / test_verifier on x86_64 with gcc
bpf/vmtest-bpf-VM_Test-7 success Logs for aarch64-gcc / test (test_progs, false, 360) / test_progs on aarch64 with gcc
bpf/vmtest-bpf-VM_Test-21 success Logs for x86_64-gcc / test (test_maps, false, 360) / test_maps on x86_64 with gcc
bpf/vmtest-bpf-VM_Test-20 success Logs for x86_64-gcc / build-release
bpf/vmtest-bpf-VM_Test-8 success Logs for aarch64-gcc / test (test_progs_no_alu32, false, 360) / test_progs_no_alu32 on aarch64 with gcc
bpf/vmtest-bpf-VM_Test-24 success Logs for x86_64-gcc / test (test_progs_no_alu32_parallel, true, 30) / test_progs_no_alu32_parallel on x86_64 with gcc
bpf/vmtest-bpf-VM_Test-11 success Logs for s390x-gcc / build / build for s390x with gcc
bpf/vmtest-bpf-VM_Test-25 success Logs for x86_64-gcc / test (test_progs_parallel, true, 30) / test_progs_parallel on x86_64 with gcc
bpf/vmtest-bpf-VM_Test-28 success Logs for x86_64-llvm-17 / build / build for x86_64 with llvm-17
bpf/vmtest-bpf-VM_Test-42 success Logs for x86_64-llvm-18 / veristat
bpf/vmtest-bpf-VM_Test-16 success Logs for s390x-gcc / test (test_verifier, false, 360) / test_verifier on s390x with gcc
bpf/vmtest-bpf-VM_Test-32 success Logs for x86_64-llvm-17 / test (test_progs_no_alu32, false, 360) / test_progs_no_alu32 on x86_64 with llvm-17
bpf/vmtest-bpf-VM_Test-22 success Logs for x86_64-gcc / test (test_progs, false, 360) / test_progs on x86_64 with gcc
bpf/vmtest-bpf-VM_Test-23 success Logs for x86_64-gcc / test (test_progs_no_alu32, false, 360) / test_progs_no_alu32 on x86_64 with gcc
bpf/vmtest-bpf-VM_Test-31 success Logs for x86_64-llvm-17 / test (test_progs, false, 360) / test_progs on x86_64 with llvm-17
bpf/vmtest-bpf-VM_Test-36 success Logs for x86_64-llvm-18 / build-release / build for x86_64 with llvm-18 and -O2 optimization
bpf/vmtest-bpf-VM_Test-38 success Logs for x86_64-llvm-18 / test (test_progs, false, 360) / test_progs on x86_64 with llvm-18
bpf/vmtest-bpf-VM_Test-39 success Logs for x86_64-llvm-18 / test (test_progs_cpuv4, false, 360) / test_progs_cpuv4 on x86_64 with llvm-18
bpf/vmtest-bpf-VM_Test-40 success Logs for x86_64-llvm-18 / test (test_progs_no_alu32, false, 360) / test_progs_no_alu32 on x86_64 with llvm-18
bpf/vmtest-bpf-VM_Test-41 success Logs for x86_64-llvm-18 / test (test_verifier, false, 360) / test_verifier on x86_64 with llvm-18

Commit Message

Martin KaFai Lau Jan. 12, 2024, 7:05 p.m. UTC 
From: Martin KaFai Lau <martin.lau@kernel.org>

There is a bug in the bpf_iter_udp_batch() function that stops
the userspace from making forward progress.

The case that triggers the bug is the userspace passed in
a very small read buffer. When the bpf prog does bpf_seq_printf,
the userspace read buffer is not enough to capture the whole bucket.

When the read buffer is not large enough, the kernel will remember
the offset of the bucket in iter->offset such that the next userspace
read() can continue from where it left off.

The kernel will skip the number (== "iter->offset") of sockets in
the next read(). However, the code directly decrements the
"--iter->offset". This is incorrect because the next read() may
not consume the whole bucket either and then the next-next read()
will start from offset 0. The net effect is the userspace will
keep reading from the beginning of a bucket and the process will
never finish. "iter->offset" must always go forward until the
whole bucket is consumed.

This patch fixes it by using a local variable "resume_offset"
and "resume_bucket". "iter->offset" is always reset to 0 before
it may be used. "iter->offset" will be advanced to the
"resume_offset" when it continues from the "resume_bucket" (i.e.
"state->bucket == resume_bucket"). This brings it closer to
the bpf_iter_tcp's offset handling which does not suffer
the same bug.

Cc: Aditi Ghag <aditi.ghag@isovalent.com>
Fixes: c96dac8d369f ("bpf: udp: Implement batching for sockets iterator")
Acked-by: Yonghong Song <yonghong.song@linux.dev>
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 net/ipv4/udp.c | 21 ++++++++++-----------
 1 file changed, 10 insertions(+), 11 deletions(-)

Comments

Aditi Ghag Jan. 12, 2024, 11:57 p.m. UTC | #1 
> On Jan 12, 2024, at 11:05 AM, Martin KaFai Lau <martin.lau@linux.dev> wrote:
> 
> From: Martin KaFai Lau <martin.lau@kernel.org>
> 
> There is a bug in the bpf_iter_udp_batch() function that stops
> the userspace from making forward progress.
> 
> The case that triggers the bug is the userspace passed in
> a very small read buffer. When the bpf prog does bpf_seq_printf,
> the userspace read buffer is not enough to capture the whole bucket.
> 
> When the read buffer is not large enough, the kernel will remember
> the offset of the bucket in iter->offset such that the next userspace
> read() can continue from where it left off.
> 
> The kernel will skip the number (== "iter->offset") of sockets in
> the next read(). However, the code directly decrements the
> "--iter->offset". This is incorrect because the next read() may
> not consume the whole bucket either and then the next-next read()
> will start from offset 0. The net effect is the userspace will
> keep reading from the beginning of a bucket and the process will
> never finish. "iter->offset" must always go forward until the
> whole bucket is consumed.
> 
> This patch fixes it by using a local variable "resume_offset"
> and "resume_bucket". "iter->offset" is always reset to 0 before
> it may be used. "iter->offset" will be advanced to the
> "resume_offset" when it continues from the "resume_bucket" (i.e.
> "state->bucket == resume_bucket"). This brings it closer to
> the bpf_iter_tcp's offset handling which does not suffer
> the same bug.
> 
> Cc: Aditi Ghag <aditi.ghag@isovalent.com>
> Fixes: c96dac8d369f ("bpf: udp: Implement batching for sockets iterator")
> Acked-by: Yonghong Song <yonghong.song@linux.dev>
> Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>

Reviewed-by: Aditi Ghag <aditi.ghag@isovalent.com>
 
Thanks!

> ---
> net/ipv4/udp.c | 21 ++++++++++-----------
> 1 file changed, 10 insertions(+), 11 deletions(-)
> 
> diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
> index 978b83d3c094..04c534a9ef89 100644
> --- a/net/ipv4/udp.c
> +++ b/net/ipv4/udp.c
> @@ -3137,16 +3137,18 @@ static struct sock *bpf_iter_udp_batch(struct seq_file *seq)
> 	struct bpf_udp_iter_state *iter = seq->private;
> 	struct udp_iter_state *state = &iter->state;
> 	struct net *net = seq_file_net(seq);
> +	int resume_bucket, resume_offset;
> 	struct udp_table *udptable;
> 	unsigned int batch_sks = 0;
> 	bool resized = false;
> 	struct sock *sk;
> 
> +	resume_bucket = state->bucket;
> +	resume_offset = iter->offset;
> +
> 	/* The current batch is done, so advance the bucket. */
> -	if (iter->st_bucket_done) {
> +	if (iter->st_bucket_done)
> 		state->bucket++;
> -		iter->offset = 0;
> -	}
> 
> 	udptable = udp_get_table_seq(seq, net);
> 
> @@ -3166,19 +3168,19 @@ static struct sock *bpf_iter_udp_batch(struct seq_file *seq)
> 	for (; state->bucket <= udptable->mask; state->bucket++) {
> 		struct udp_hslot *hslot2 = &udptable->hash2[state->bucket];
> 
> -		if (hlist_empty(&hslot2->head)) {
> -			iter->offset = 0;
> +		if (hlist_empty(&hslot2->head))
> 			continue;
> -		}
> 
> +		iter->offset = 0;
> 		spin_lock_bh(&hslot2->lock);
> 		udp_portaddr_for_each_entry(sk, &hslot2->head) {
> 			if (seq_sk_match(seq, sk)) {
> 				/* Resume from the last iterated socket at the
> 				 * offset in the bucket before iterator was stopped.
> 				 */
> -				if (iter->offset) {
> -					--iter->offset;
> +				if (state->bucket == resume_bucket &&
> +				    iter->offset < resume_offset) {

I like this invariant of ensuring that the batching and resume operations are performed for the same bucket under consideration.


> +					++iter->offset;
> 					continue;
> 				}
> 				if (iter->end_sk < iter->max_sk) {
> @@ -3192,9 +3194,6 @@ static struct sock *bpf_iter_udp_batch(struct seq_file *seq)
> 
> 		if (iter->end_sk)
> 			break;
> -
> -		/* Reset the current bucket's offset before moving to the next bucket. */
> -		iter->offset = 0;
> 	}
> 
> 	/* All done: no batch made. */
> -- 
> 2.34.1
>
diff mbox series

Patch

diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 978b83d3c094..04c534a9ef89 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -3137,16 +3137,18 @@  static struct sock *bpf_iter_udp_batch(struct seq_file *seq)
 	struct bpf_udp_iter_state *iter = seq->private;
 	struct udp_iter_state *state = &iter->state;
 	struct net *net = seq_file_net(seq);
+	int resume_bucket, resume_offset;
 	struct udp_table *udptable;
 	unsigned int batch_sks = 0;
 	bool resized = false;
 	struct sock *sk;
 
+	resume_bucket = state->bucket;
+	resume_offset = iter->offset;
+
 	/* The current batch is done, so advance the bucket. */
-	if (iter->st_bucket_done) {
+	if (iter->st_bucket_done)
 		state->bucket++;
-		iter->offset = 0;
-	}
 
 	udptable = udp_get_table_seq(seq, net);
 
@@ -3166,19 +3168,19 @@  static struct sock *bpf_iter_udp_batch(struct seq_file *seq)
 	for (; state->bucket <= udptable->mask; state->bucket++) {
 		struct udp_hslot *hslot2 = &udptable->hash2[state->bucket];
 
-		if (hlist_empty(&hslot2->head)) {
-			iter->offset = 0;
+		if (hlist_empty(&hslot2->head))
 			continue;
-		}
 
+		iter->offset = 0;
 		spin_lock_bh(&hslot2->lock);
 		udp_portaddr_for_each_entry(sk, &hslot2->head) {
 			if (seq_sk_match(seq, sk)) {
 				/* Resume from the last iterated socket at the
 				 * offset in the bucket before iterator was stopped.
 				 */
-				if (iter->offset) {
-					--iter->offset;
+				if (state->bucket == resume_bucket &&
+				    iter->offset < resume_offset) {
+					++iter->offset;
 					continue;
 				}
 				if (iter->end_sk < iter->max_sk) {
@@ -3192,9 +3194,6 @@  static struct sock *bpf_iter_udp_batch(struct seq_file *seq)
 
 		if (iter->end_sk)
 			break;
-
-		/* Reset the current bucket's offset before moving to the next bucket. */
-		iter->offset = 0;
 	}
 
 	/* All done: no batch made. */