From 50252e4b5e989ce64555c7aef7516bdefc2fea72 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Wed, 8 Dec 2021 17:04:55 -0800 Subject: aio: fix use-after-free due to missing POLLFREE handling signalfd_poll() and binder_poll() are special in that they use a waitqueue whose lifetime is the current task, rather than the struct file as is normally the case. This is okay for blocking polls, since a blocking poll occurs within one task; however, non-blocking polls require another solution. This solution is for the queue to be cleared before it is freed, by sending a POLLFREE notification to all waiters. Unfortunately, only eventpoll handles POLLFREE. A second type of non-blocking poll, aio poll, was added in kernel v4.18, and it doesn't handle POLLFREE. This allows a use-after-free to occur if a signalfd or binder fd is polled with aio poll, and the waitqueue gets freed. Fix this by making aio poll handle POLLFREE. A patch by Ramji Jiyani (https://lore.kernel.org/r/20211027011834.2497484-1-ramjiyani@google.com) tried to do this by making aio_poll_wake() always complete the request inline if POLLFREE is seen. However, that solution had two bugs. First, it introduced a deadlock, as it unconditionally locked the aio context while holding the waitqueue lock, which inverts the normal locking order. Second, it didn't consider that POLLFREE notifications are missed while the request has been temporarily de-queued. The second problem was solved by my previous patch. This patch then properly fixes the use-after-free by handling POLLFREE in a deadlock-free way. It does this by taking advantage of the fact that freeing of the waitqueue is RCU-delayed, similar to what eventpoll does. Fixes: 2c14fa838cbe ("aio: implement IOCB_CMD_POLL") Cc: # v4.18+ Link: https://lore.kernel.org/r/20211209010455.42744-6-ebiggers@kernel.org Signed-off-by: Eric Biggers --- include/uapi/asm-generic/poll.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/asm-generic/poll.h b/include/uapi/asm-generic/poll.h index 41b509f410bf..f9c520ce4bf4 100644 --- a/include/uapi/asm-generic/poll.h +++ b/include/uapi/asm-generic/poll.h @@ -29,7 +29,7 @@ #define POLLRDHUP 0x2000 #endif -#define POLLFREE (__force __poll_t)0x4000 /* currently only for epoll */ +#define POLLFREE (__force __poll_t)0x4000 #define POLL_BUSY_LOOP (__force __poll_t)0x8000 -- cgit v1.2.3 From 9dcc38e2813e0cd3b195940c98b181ce6ede8f20 Mon Sep 17 00:00:00 2001 From: Drew DeVault Date: Fri, 10 Dec 2021 14:46:09 -0800 Subject: Increase default MLOCK_LIMIT to 8 MiB This limit has not been updated since 2008, when it was increased to 64 KiB at the request of GnuPG. Until recently, the main use-cases for this feature were (1) preventing sensitive memory from being swapped, as in GnuPG's use-case; and (2) real-time use-cases. In the first case, little memory is called for, and in the second case, the user is generally in a position to increase it if they need more. The introduction of IOURING_REGISTER_BUFFERS adds a third use-case: preparing fixed buffers for high-performance I/O. This use-case will take as much of this memory as it can get, but is still limited to 64 KiB by default, which is very little. This increases the limit to 8 MB, which was chosen fairly arbitrarily as a more generous, but still conservative, default value. It is also possible to raise this limit in userspace. This is easily done, for example, in the use-case of a network daemon: systemd, for instance, provides for this via LimitMEMLOCK in the service file; OpenRC via the rc_ulimit variables. However, there is no established userspace facility for configuring this outside of daemons: end-user applications do not presently have access to a convenient means of raising their limits. The buck, as it were, stops with the kernel. It's much easier to address it here than it is to bring it to hundreds of distributions, and it can only realistically be relied upon to be high-enough by end-user software if it is more-or-less ubiquitous. Most distros don't change this particular rlimit from the kernel-supplied default value, so a change here will easily provide that ubiquity. Link: https://lkml.kernel.org/r/20211028080813.15966-1-sir@cmpwn.com Signed-off-by: Drew DeVault Acked-by: Jens Axboe Acked-by: Cyril Hrubis Acked-by: Johannes Weiner Cc: Pavel Begunkov Cc: David Hildenbrand Cc: Jason Gunthorpe Cc: Andrew Dona-Couch Cc: Ammar Faizi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/uapi/linux/resource.h | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/resource.h b/include/uapi/linux/resource.h index 74ef57b38f9f..ac5d6a3031db 100644 --- a/include/uapi/linux/resource.h +++ b/include/uapi/linux/resource.h @@ -66,10 +66,17 @@ struct rlimit64 { #define _STK_LIM (8*1024*1024) /* - * GPG2 wants 64kB of mlocked memory, to make sure pass phrases - * and other sensitive information are never written to disk. + * Limit the amount of locked memory by some sane default: + * root can always increase this limit if needed. + * + * The main use-cases are (1) preventing sensitive memory + * from being swapped; (2) real-time operations; (3) via + * IOURING_REGISTER_BUFFERS. + * + * The first two don't need much. The latter will take as + * much as it can get. 8MB is a reasonably sane default. */ -#define MLOCK_LIMIT ((PAGE_SIZE > 64*1024) ? PAGE_SIZE : 64*1024) +#define MLOCK_LIMIT (8*1024*1024) /* * Due to binary compatibility, the actual resource numbers -- cgit v1.2.3 From 6813b1928758ce64fabbb8ef157f994b7c2235fa Mon Sep 17 00:00:00 2001 From: Matthieu Baerts Date: Tue, 14 Dec 2021 15:16:04 -0800 Subject: mptcp: add missing documented NL params 'loc_id' and 'rem_id' are set in all events linked to subflows but those were missing in the events description in the comments. Fixes: b911c97c7dc7 ("mptcp: add netlink event support") Signed-off-by: Matthieu Baerts Signed-off-by: Mat Martineau Signed-off-by: Jakub Kicinski --- include/uapi/linux/mptcp.h | 18 ++++++++++-------- 1 file changed, 10 insertions(+), 8 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/mptcp.h b/include/uapi/linux/mptcp.h index c8cc46f80a16..f106a3941cdf 100644 --- a/include/uapi/linux/mptcp.h +++ b/include/uapi/linux/mptcp.h @@ -136,19 +136,21 @@ struct mptcp_info { * MPTCP_EVENT_REMOVED: token, rem_id * An address has been lost by the peer. * - * MPTCP_EVENT_SUB_ESTABLISHED: token, family, saddr4 | saddr6, - * daddr4 | daddr6, sport, dport, backup, - * if_idx [, error] + * MPTCP_EVENT_SUB_ESTABLISHED: token, family, loc_id, rem_id, + * saddr4 | saddr6, daddr4 | daddr6, sport, + * dport, backup, if_idx [, error] * A new subflow has been established. 'error' should not be set. * - * MPTCP_EVENT_SUB_CLOSED: token, family, saddr4 | saddr6, daddr4 | daddr6, - * sport, dport, backup, if_idx [, error] + * MPTCP_EVENT_SUB_CLOSED: token, family, loc_id, rem_id, saddr4 | saddr6, + * daddr4 | daddr6, sport, dport, backup, if_idx + * [, error] * A subflow has been closed. An error (copy of sk_err) could be set if an * error has been detected for this subflow. * - * MPTCP_EVENT_SUB_PRIORITY: token, family, saddr4 | saddr6, daddr4 | daddr6, - * sport, dport, backup, if_idx [, error] - * The priority of a subflow has changed. 'error' should not be set. + * MPTCP_EVENT_SUB_PRIORITY: token, family, loc_id, rem_id, saddr4 | saddr6, + * daddr4 | daddr6, sport, dport, backup, if_idx + * [, error] + * The priority of a subflow has changed. 'error' should not be set. */ enum mptcp_event_type { MPTCP_EVENT_UNSPEC = 0, -- cgit v1.2.3