diff mbox series

[net-next,v1,6/7] net: fix SO_DEVMEM_DONTNEED looping too long

Message ID 20241029205524.1306364-2-almasrymina@google.com (mailing list archive)
State New
Headers show
Series devmem TCP fixes | expand

Commit Message

Mina Almasry Oct. 29, 2024, 8:55 p.m. UTC 
Check we're going to free a reasonable number of frags in token_count
before starting the loop, to prevent looping too long.

Also minor code cleanups:
- Flip checks to reduce indentation.
- Use sizeof(*tokens) everywhere for consistentcy.

Cc: Yi Lai <yi1.lai@linux.intel.com>

Signed-off-by: Mina Almasry <almasrymina@google.com>

---
 net/core/sock.c | 46 ++++++++++++++++++++++++++++------------------
 1 file changed, 28 insertions(+), 18 deletions(-)

--
2.47.0.163.g1226f6d8fa-goog

Comments

Stanislav Fomichev Oct. 30, 2024, 2:33 p.m. UTC | #1 
On 10/29, Mina Almasry wrote:
> Check we're going to free a reasonable number of frags in token_count
> before starting the loop, to prevent looping too long.
> 
> Also minor code cleanups:
> - Flip checks to reduce indentation.
> - Use sizeof(*tokens) everywhere for consistentcy.
> 
> Cc: Yi Lai <yi1.lai@linux.intel.com>
> 
> Signed-off-by: Mina Almasry <almasrymina@google.com>
> 
> ---
>  net/core/sock.c | 46 ++++++++++++++++++++++++++++------------------
>  1 file changed, 28 insertions(+), 18 deletions(-)
> 
> diff --git a/net/core/sock.c b/net/core/sock.c
> index 7f398bd07fb7..8603b8d87f2e 100644
> --- a/net/core/sock.c
> +++ b/net/core/sock.c
> @@ -1047,11 +1047,12 @@ static int sock_reserve_memory(struct sock *sk, int bytes)
> 
>  #ifdef CONFIG_PAGE_POOL
> 
> -/* This is the number of tokens that the user can SO_DEVMEM_DONTNEED in
> +/* This is the number of frags that the user can SO_DEVMEM_DONTNEED in
>   * 1 syscall. The limit exists to limit the amount of memory the kernel
> - * allocates to copy these tokens.
> + * allocates to copy these tokens, and to prevent looping over the frags for
> + * too long.
>   */
> -#define MAX_DONTNEED_TOKENS 128
> +#define MAX_DONTNEED_FRAGS 1024
> 
>  static noinline_for_stack int
>  sock_devmem_dontneed(struct sock *sk, sockptr_t optval, unsigned int optlen)
> @@ -1059,43 +1060,52 @@ sock_devmem_dontneed(struct sock *sk, sockptr_t optval, unsigned int optlen)
>  	unsigned int num_tokens, i, j, k, netmem_num = 0;
>  	struct dmabuf_token *tokens;
>  	netmem_ref netmems[16];
> +	u64 num_frags = 0;
>  	int ret = 0;
> 
>  	if (!sk_is_tcp(sk))
>  		return -EBADF;
> 
> -	if (optlen % sizeof(struct dmabuf_token) ||
> -	    optlen > sizeof(*tokens) * MAX_DONTNEED_TOKENS)
> +	if (optlen % sizeof(*tokens) ||
> +	    optlen > sizeof(*tokens) * MAX_DONTNEED_FRAGS)
>  		return -EINVAL;
> 
> -	tokens = kvmalloc_array(optlen, sizeof(*tokens), GFP_KERNEL);
> +	num_tokens = optlen / sizeof(*tokens);
> +	tokens = kvmalloc_array(num_tokens, sizeof(*tokens), GFP_KERNEL);
>  	if (!tokens)
>  		return -ENOMEM;
> 
> -	num_tokens = optlen / sizeof(struct dmabuf_token);
>  	if (copy_from_sockptr(tokens, optval, optlen)) {
>  		kvfree(tokens);
>  		return -EFAULT;
>  	}
> 
> +	for (i = 0; i < num_tokens; i++) {
> +		num_frags += tokens[i].token_count;
> +		if (num_frags > MAX_DONTNEED_FRAGS) {
> +			kvfree(tokens);
> +			return -E2BIG;
> +		}
> +	}
> +
>  	xa_lock_bh(&sk->sk_user_frags);
>  	for (i = 0; i < num_tokens; i++) {
>  		for (j = 0; j < tokens[i].token_count; j++) {
>  			netmem_ref netmem = (__force netmem_ref)__xa_erase(
>  				&sk->sk_user_frags, tokens[i].token_start + j);
> 
> -			if (netmem &&
> -			    !WARN_ON_ONCE(!netmem_is_net_iov(netmem))) {
> -				netmems[netmem_num++] = netmem;
> -				if (netmem_num == ARRAY_SIZE(netmems)) {
> -					xa_unlock_bh(&sk->sk_user_frags);
> -					for (k = 0; k < netmem_num; k++)
> -						WARN_ON_ONCE(!napi_pp_put_page(netmems[k]));
> -					netmem_num = 0;
> -					xa_lock_bh(&sk->sk_user_frags);
> -				}
> -				ret++;

[..]

> +			if (!netmem || WARN_ON_ONCE(!netmem_is_net_iov(netmem)))
> +				continue;

Any reason we are not returning explicit error to the callers here?
That probably needs some mechanism to signal which particular one failed
so the users can restart?
Mina Almasry Oct. 30, 2024, 2:46 p.m. UTC | #2 
On Wed, Oct 30, 2024 at 7:33 AM Stanislav Fomichev <stfomichev@gmail.com> wrote:
>
> On 10/29, Mina Almasry wrote:
> > Check we're going to free a reasonable number of frags in token_count
> > before starting the loop, to prevent looping too long.
> >
> > Also minor code cleanups:
> > - Flip checks to reduce indentation.
> > - Use sizeof(*tokens) everywhere for consistentcy.
> >
> > Cc: Yi Lai <yi1.lai@linux.intel.com>
> >
> > Signed-off-by: Mina Almasry <almasrymina@google.com>
> >
> > ---
> >  net/core/sock.c | 46 ++++++++++++++++++++++++++++------------------
> >  1 file changed, 28 insertions(+), 18 deletions(-)
> >
> > diff --git a/net/core/sock.c b/net/core/sock.c
> > index 7f398bd07fb7..8603b8d87f2e 100644
> > --- a/net/core/sock.c
> > +++ b/net/core/sock.c
> > @@ -1047,11 +1047,12 @@ static int sock_reserve_memory(struct sock *sk, int bytes)
> >
> >  #ifdef CONFIG_PAGE_POOL
> >
> > -/* This is the number of tokens that the user can SO_DEVMEM_DONTNEED in
> > +/* This is the number of frags that the user can SO_DEVMEM_DONTNEED in
> >   * 1 syscall. The limit exists to limit the amount of memory the kernel
> > - * allocates to copy these tokens.
> > + * allocates to copy these tokens, and to prevent looping over the frags for
> > + * too long.
> >   */
> > -#define MAX_DONTNEED_TOKENS 128
> > +#define MAX_DONTNEED_FRAGS 1024
> >
> >  static noinline_for_stack int
> >  sock_devmem_dontneed(struct sock *sk, sockptr_t optval, unsigned int optlen)
> > @@ -1059,43 +1060,52 @@ sock_devmem_dontneed(struct sock *sk, sockptr_t optval, unsigned int optlen)
> >       unsigned int num_tokens, i, j, k, netmem_num = 0;
> >       struct dmabuf_token *tokens;
> >       netmem_ref netmems[16];
> > +     u64 num_frags = 0;
> >       int ret = 0;
> >
> >       if (!sk_is_tcp(sk))
> >               return -EBADF;
> >
> > -     if (optlen % sizeof(struct dmabuf_token) ||
> > -         optlen > sizeof(*tokens) * MAX_DONTNEED_TOKENS)
> > +     if (optlen % sizeof(*tokens) ||
> > +         optlen > sizeof(*tokens) * MAX_DONTNEED_FRAGS)
> >               return -EINVAL;
> >
> > -     tokens = kvmalloc_array(optlen, sizeof(*tokens), GFP_KERNEL);
> > +     num_tokens = optlen / sizeof(*tokens);
> > +     tokens = kvmalloc_array(num_tokens, sizeof(*tokens), GFP_KERNEL);
> >       if (!tokens)
> >               return -ENOMEM;
> >
> > -     num_tokens = optlen / sizeof(struct dmabuf_token);
> >       if (copy_from_sockptr(tokens, optval, optlen)) {
> >               kvfree(tokens);
> >               return -EFAULT;
> >       }
> >
> > +     for (i = 0; i < num_tokens; i++) {
> > +             num_frags += tokens[i].token_count;
> > +             if (num_frags > MAX_DONTNEED_FRAGS) {
> > +                     kvfree(tokens);
> > +                     return -E2BIG;
> > +             }
> > +     }
> > +
> >       xa_lock_bh(&sk->sk_user_frags);
> >       for (i = 0; i < num_tokens; i++) {
> >               for (j = 0; j < tokens[i].token_count; j++) {
> >                       netmem_ref netmem = (__force netmem_ref)__xa_erase(
> >                               &sk->sk_user_frags, tokens[i].token_start + j);
> >
> > -                     if (netmem &&
> > -                         !WARN_ON_ONCE(!netmem_is_net_iov(netmem))) {
> > -                             netmems[netmem_num++] = netmem;
> > -                             if (netmem_num == ARRAY_SIZE(netmems)) {
> > -                                     xa_unlock_bh(&sk->sk_user_frags);
> > -                                     for (k = 0; k < netmem_num; k++)
> > -                                             WARN_ON_ONCE(!napi_pp_put_page(netmems[k]));
> > -                                     netmem_num = 0;
> > -                                     xa_lock_bh(&sk->sk_user_frags);
> > -                             }
> > -                             ret++;
>
> [..]
>
> > +                     if (!netmem || WARN_ON_ONCE(!netmem_is_net_iov(netmem)))
> > +                             continue;
>
> Any reason we are not returning explicit error to the callers here?
> That probably needs some mechanism to signal which particular one failed
> so the users can restart?

Only because I can't think of a simple way to return an array of frags
failed to DONTNEED to the user.

Also, this error should be extremely rare or never hit really. I don't
know how we end up not finding a netmem here or the netmem is page.
The only way is if the user is malicious (messing with the token ids
passed to the kernel) or if a kernel bug is happening.

Also, the information is useless to the user. If the user sees 'frag
128 failed to free'. There is nothing really the user can do to
recover at runtime. Only usefulness that could come is for the user to
log the error. We already WARN_ON_ONCE on the error the user would not
be able to trigger.
Stanislav Fomichev Oct. 30, 2024, 3:06 p.m. UTC | #3 
On 10/30, Mina Almasry wrote:
> On Wed, Oct 30, 2024 at 7:33 AM Stanislav Fomichev <stfomichev@gmail.com> wrote:
> >
> > On 10/29, Mina Almasry wrote:
> > > Check we're going to free a reasonable number of frags in token_count
> > > before starting the loop, to prevent looping too long.
> > >
> > > Also minor code cleanups:
> > > - Flip checks to reduce indentation.
> > > - Use sizeof(*tokens) everywhere for consistentcy.
> > >
> > > Cc: Yi Lai <yi1.lai@linux.intel.com>
> > >
> > > Signed-off-by: Mina Almasry <almasrymina@google.com>
> > >
> > > ---
> > >  net/core/sock.c | 46 ++++++++++++++++++++++++++++------------------
> > >  1 file changed, 28 insertions(+), 18 deletions(-)
> > >
> > > diff --git a/net/core/sock.c b/net/core/sock.c
> > > index 7f398bd07fb7..8603b8d87f2e 100644
> > > --- a/net/core/sock.c
> > > +++ b/net/core/sock.c
> > > @@ -1047,11 +1047,12 @@ static int sock_reserve_memory(struct sock *sk, int bytes)
> > >
> > >  #ifdef CONFIG_PAGE_POOL
> > >
> > > -/* This is the number of tokens that the user can SO_DEVMEM_DONTNEED in
> > > +/* This is the number of frags that the user can SO_DEVMEM_DONTNEED in
> > >   * 1 syscall. The limit exists to limit the amount of memory the kernel
> > > - * allocates to copy these tokens.
> > > + * allocates to copy these tokens, and to prevent looping over the frags for
> > > + * too long.
> > >   */
> > > -#define MAX_DONTNEED_TOKENS 128
> > > +#define MAX_DONTNEED_FRAGS 1024
> > >
> > >  static noinline_for_stack int
> > >  sock_devmem_dontneed(struct sock *sk, sockptr_t optval, unsigned int optlen)
> > > @@ -1059,43 +1060,52 @@ sock_devmem_dontneed(struct sock *sk, sockptr_t optval, unsigned int optlen)
> > >       unsigned int num_tokens, i, j, k, netmem_num = 0;
> > >       struct dmabuf_token *tokens;
> > >       netmem_ref netmems[16];
> > > +     u64 num_frags = 0;
> > >       int ret = 0;
> > >
> > >       if (!sk_is_tcp(sk))
> > >               return -EBADF;
> > >
> > > -     if (optlen % sizeof(struct dmabuf_token) ||
> > > -         optlen > sizeof(*tokens) * MAX_DONTNEED_TOKENS)
> > > +     if (optlen % sizeof(*tokens) ||
> > > +         optlen > sizeof(*tokens) * MAX_DONTNEED_FRAGS)
> > >               return -EINVAL;
> > >
> > > -     tokens = kvmalloc_array(optlen, sizeof(*tokens), GFP_KERNEL);
> > > +     num_tokens = optlen / sizeof(*tokens);
> > > +     tokens = kvmalloc_array(num_tokens, sizeof(*tokens), GFP_KERNEL);
> > >       if (!tokens)
> > >               return -ENOMEM;
> > >
> > > -     num_tokens = optlen / sizeof(struct dmabuf_token);
> > >       if (copy_from_sockptr(tokens, optval, optlen)) {
> > >               kvfree(tokens);
> > >               return -EFAULT;
> > >       }
> > >
> > > +     for (i = 0; i < num_tokens; i++) {
> > > +             num_frags += tokens[i].token_count;
> > > +             if (num_frags > MAX_DONTNEED_FRAGS) {
> > > +                     kvfree(tokens);
> > > +                     return -E2BIG;
> > > +             }
> > > +     }
> > > +
> > >       xa_lock_bh(&sk->sk_user_frags);
> > >       for (i = 0; i < num_tokens; i++) {
> > >               for (j = 0; j < tokens[i].token_count; j++) {
> > >                       netmem_ref netmem = (__force netmem_ref)__xa_erase(
> > >                               &sk->sk_user_frags, tokens[i].token_start + j);
> > >
> > > -                     if (netmem &&
> > > -                         !WARN_ON_ONCE(!netmem_is_net_iov(netmem))) {
> > > -                             netmems[netmem_num++] = netmem;
> > > -                             if (netmem_num == ARRAY_SIZE(netmems)) {
> > > -                                     xa_unlock_bh(&sk->sk_user_frags);
> > > -                                     for (k = 0; k < netmem_num; k++)
> > > -                                             WARN_ON_ONCE(!napi_pp_put_page(netmems[k]));
> > > -                                     netmem_num = 0;
> > > -                                     xa_lock_bh(&sk->sk_user_frags);
> > > -                             }
> > > -                             ret++;
> >
> > [..]
> >
> > > +                     if (!netmem || WARN_ON_ONCE(!netmem_is_net_iov(netmem)))
> > > +                             continue;
> >
> > Any reason we are not returning explicit error to the callers here?
> > That probably needs some mechanism to signal which particular one failed
> > so the users can restart?
> 
> Only because I can't think of a simple way to return an array of frags
> failed to DONTNEED to the user.

I'd expect the call to return as soon as it hits the invalid frag
entry (plus the number of entries that it successfully refilled up to
the invalid one). But too late I guess.

> Also, this error should be extremely rare or never hit really. I don't
> know how we end up not finding a netmem here or the netmem is page.
> The only way is if the user is malicious (messing with the token ids
> passed to the kernel) or if a kernel bug is happening.

I do hit this error with 1500 mtu, so it would've been nice to
understand which particular token triggered that. It might be
something buggy on the driver side, I need to investigate. (it's
super low prio because 1500)

> Also, the information is useless to the user. If the user sees 'frag
> 128 failed to free'. There is nothing really the user can do to
> recover at runtime. Only usefulness that could come is for the user to
> log the error. We already WARN_ON_ONCE on the error the user would not
> be able to trigger.

I'm thinking from the pow of user application. It might have bugs as
well and try to refill something that should not have been refilled.
Having info about which particular token has failed (even just for
the logging purposes) might have been nice.
diff mbox series

Patch

diff --git a/net/core/sock.c b/net/core/sock.c
index 7f398bd07fb7..8603b8d87f2e 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1047,11 +1047,12 @@  static int sock_reserve_memory(struct sock *sk, int bytes)

 #ifdef CONFIG_PAGE_POOL

-/* This is the number of tokens that the user can SO_DEVMEM_DONTNEED in
+/* This is the number of frags that the user can SO_DEVMEM_DONTNEED in
  * 1 syscall. The limit exists to limit the amount of memory the kernel
- * allocates to copy these tokens.
+ * allocates to copy these tokens, and to prevent looping over the frags for
+ * too long.
  */
-#define MAX_DONTNEED_TOKENS 128
+#define MAX_DONTNEED_FRAGS 1024

 static noinline_for_stack int
 sock_devmem_dontneed(struct sock *sk, sockptr_t optval, unsigned int optlen)
@@ -1059,43 +1060,52 @@  sock_devmem_dontneed(struct sock *sk, sockptr_t optval, unsigned int optlen)
 	unsigned int num_tokens, i, j, k, netmem_num = 0;
 	struct dmabuf_token *tokens;
 	netmem_ref netmems[16];
+	u64 num_frags = 0;
 	int ret = 0;

 	if (!sk_is_tcp(sk))
 		return -EBADF;

-	if (optlen % sizeof(struct dmabuf_token) ||
-	    optlen > sizeof(*tokens) * MAX_DONTNEED_TOKENS)
+	if (optlen % sizeof(*tokens) ||
+	    optlen > sizeof(*tokens) * MAX_DONTNEED_FRAGS)
 		return -EINVAL;

-	tokens = kvmalloc_array(optlen, sizeof(*tokens), GFP_KERNEL);
+	num_tokens = optlen / sizeof(*tokens);
+	tokens = kvmalloc_array(num_tokens, sizeof(*tokens), GFP_KERNEL);
 	if (!tokens)
 		return -ENOMEM;

-	num_tokens = optlen / sizeof(struct dmabuf_token);
 	if (copy_from_sockptr(tokens, optval, optlen)) {
 		kvfree(tokens);
 		return -EFAULT;
 	}

+	for (i = 0; i < num_tokens; i++) {
+		num_frags += tokens[i].token_count;
+		if (num_frags > MAX_DONTNEED_FRAGS) {
+			kvfree(tokens);
+			return -E2BIG;
+		}
+	}
+
 	xa_lock_bh(&sk->sk_user_frags);
 	for (i = 0; i < num_tokens; i++) {
 		for (j = 0; j < tokens[i].token_count; j++) {
 			netmem_ref netmem = (__force netmem_ref)__xa_erase(
 				&sk->sk_user_frags, tokens[i].token_start + j);

-			if (netmem &&
-			    !WARN_ON_ONCE(!netmem_is_net_iov(netmem))) {
-				netmems[netmem_num++] = netmem;
-				if (netmem_num == ARRAY_SIZE(netmems)) {
-					xa_unlock_bh(&sk->sk_user_frags);
-					for (k = 0; k < netmem_num; k++)
-						WARN_ON_ONCE(!napi_pp_put_page(netmems[k]));
-					netmem_num = 0;
-					xa_lock_bh(&sk->sk_user_frags);
-				}
-				ret++;
+			if (!netmem || WARN_ON_ONCE(!netmem_is_net_iov(netmem)))
+				continue;
+
+			netmems[netmem_num++] = netmem;
+			if (netmem_num == ARRAY_SIZE(netmems)) {
+				xa_unlock_bh(&sk->sk_user_frags);
+				for (k = 0; k < netmem_num; k++)
+					WARN_ON_ONCE(!napi_pp_put_page(netmems[k]));
+				netmem_num = 0;
+				xa_lock_bh(&sk->sk_user_frags);
 			}
+			ret++;
 		}
 	}