From: "André Almeida" <andrealmeid@igalia.com>
To: Thomas Gleixner <tglx@kernel.org>
Cc: "Mathieu Desnoyers" <mathieu.desnoyers@efficios.com>,
"Sebastian Andrzej Siewior" <bigeasy@linutronix.de>,
"Carlos O'Donell" <carlos@redhat.com>,
"Peter Zijlstra" <peterz@infradead.org>,
"Florian Weimer" <fweimer@redhat.com>,
"Rich Felker" <dalias@aerifal.cx>,
LKML <linux-kernel@vger.kernel.org>,
"Torvald Riegel" <triegel@redhat.com>,
"Darren Hart" <dvhart@infradead.org>,
"Ingo Molnar" <mingo@kernel.org>,
"Davidlohr Bueso" <dave@stgolabs.net>,
"Arnd Bergmann" <arnd@arndb.de>,
"Liam R . Howlett" <Liam.Howlett@oracle.com>,
"Uros Bizjak" <ubizjak@gmail.com>,
"Thomas Weißschuh" <linux@weissschuh.net>,
kernel-dev@igalia.com
Subject: Re: [patch V4 12/14] x86/vdso: Implement __vdso_futex_robust_try_unlock()
Date: Fri, 29 May 2026 12:36:31 -0300 [thread overview]
Message-ID: <c7f5ad25-7bf7-4e3e-a852-c3cd74f12750@igalia.com> (raw)
In-Reply-To: <20260402151940.418303527@kernel.org>
Em 02/04/2026 12:22, Thomas Gleixner escreveu:
> When the FUTEX_ROBUST_UNLOCK mechanism is used for unlocking (PI-)futexes,
> then the unlock sequence in userspace looks like this:
>
> 1) robust_list_set_op_pending(mutex);
> 2) robust_list_remove(mutex);
>
> lval = gettid();
> 3) if (atomic_try_cmpxchg(&mutex->lock, lval, 0))
> 4) robust_list_clear_op_pending();
> else
> 5) sys_futex(OP,...FUTEX_ROBUST_UNLOCK);
>
> That still leaves a minimal race window between #3 and #4 where the mutex
> could be acquired by some other task which observes that it is the last
> user and:
>
> 1) unmaps the mutex memory
> 2) maps a different file, which ends up covering the same address
>
> When then the original task exits before reaching #5 then the kernel robust
> list handling observes the pending op entry and tries to fix up user space.
>
> In case that the newly mapped data contains the TID of the exiting thread
> at the address of the mutex/futex the kernel will set the owner died bit in
> that memory and therefore corrupt unrelated data.
>
> Provide a VDSO function which exposes the critical section window in the
> VDSO symbol table. The resulting addresses are updated in the task's mm
> when the VDSO is (re)map()'ed.
>
> The core code detects when a task was interrupted within the critical
> section and is about to deliver a signal. It then invokes an architecture
> specific function which determines whether the pending op pointer has to be
> cleared or not. The unlock assembly sequence on 64-bit is:
>
> mov %esi,%eax // Load TID into EAX
> xor %ecx,%ecx // Set ECX to 0
> lock cmpxchg %ecx,(%rdi) // Try the TID -> 0 transition
> .Lstart:
> jnz .Lend
> movq %rcx,(%rdx) // Clear list_op_pending
> .Lend:
> ret
>
> So the decision can be simply based on the ZF state in regs->flags. The
> pending op pointer is always in DX independent of the build mode
> (32/64-bit) to make the pending op pointer retrieval uniform. The size of
> the pointer is stored in the matching criticial section range struct and
> the core code retrieves it from there. So the pointer retrieval function
> does not have to care. It is bit-size independent:
>
> return regs->flags & X86_EFLAGS_ZF ? regs->dx : NULL;
>
> There are two entry points to handle the different robust list pending op
> pointer size:
>
> __vdso_futex_robust_list64_try_unlock()
> __vdso_futex_robust_list32_try_unlock()
>
> The 32-bit VDSO provides only __vdso_futex_robust_list32_try_unlock().
>
> The 64-bit VDSO provides always __vdso_futex_robust_list64_try_unlock() and
> when COMPAT is enabled also the list32 variant, which is required to
> support multi-size robust list pointers used by gaming emulators.
>
> The unlock function is inspired by an idea from Mathieu Desnoyers.
>
> Signed-off-by: Thomas Gleixner <tglx@kernel.org>
> Acked-by: Uros Bizjak <ubizjak@gmail.com>
> Link: https://lore.kernel.org/20260311185409.1988269-1-mathieu.desnoyers@efficios.com
Reviewed-by: André Almeida <andrealmeid@igalia.com>
next prev parent reply other threads:[~2026-05-29 15:37 UTC|newest]
Thread overview: 32+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-04-02 15:21 [patch V4 00/14] futex: Address the robust futex unlock race for real Thomas Gleixner
2026-04-02 15:21 ` [patch V4 01/14] futex: Move futex task related data into a struct Thomas Gleixner
2026-04-02 15:21 ` [patch V4 02/14] futex: Make futex_mm_init() void Thomas Gleixner
2026-04-02 15:21 ` [patch V4 03/14] futex: Move futex related mm_struct data into a struct Thomas Gleixner
2026-04-09 11:11 ` Nam Cao
2026-04-10 14:20 ` Thomas Gleixner
2026-04-02 15:21 ` [patch V4 04/14] futex: Provide UABI defines for robust list entry modifiers Thomas Gleixner
2026-04-02 15:21 ` [patch V4 05/14] uaccess: Provide unsafe_atomic_store_release_user() Thomas Gleixner
2026-04-02 15:21 ` [patch V4 06/14] x86: Select ARCH_MEMORY_ORDER_TSO Thomas Gleixner
2026-04-02 15:21 ` [patch V4 07/14] futex: Cleanup UAPI defines Thomas Gleixner
2026-04-02 15:21 ` [patch V4 08/14] futex: Add support for unlocking robust futexes Thomas Gleixner
2026-04-02 15:21 ` [patch V4 09/14] futex: Add robust futex unlock IP range Thomas Gleixner
2026-05-28 1:02 ` André Almeida
2026-05-29 21:30 ` Thomas Gleixner
2026-04-02 15:21 ` [patch V4 10/14] futex: Provide infrastructure to plug the non contended robust futex unlock race Thomas Gleixner
2026-05-28 1:08 ` André Almeida
2026-05-29 21:14 ` Thomas Gleixner
2026-04-02 15:21 ` [patch V4 11/14] x86/vdso: Prepare for robust futex unlock support Thomas Gleixner
2026-05-28 1:14 ` André Almeida
2026-04-02 15:22 ` [patch V4 12/14] x86/vdso: Implement __vdso_futex_robust_try_unlock() Thomas Gleixner
2026-04-29 8:44 ` Thomas Weißschuh
2026-05-07 9:29 ` Thomas Gleixner
2026-05-07 9:48 ` Thomas Weißschuh
2026-05-07 16:51 ` Thomas Gleixner
2026-05-29 15:36 ` André Almeida [this message]
2026-04-02 15:22 ` [patch V4 13/14] Documentation: futex: Add a note about robust list race condition Thomas Gleixner
2026-04-02 15:22 ` [patch V4 14/14] selftests: futex: Add tests for robust release operations Thomas Gleixner
2026-04-04 9:39 ` [PATCH 15/14] selftests: futex: Add tests for robust unlock within the critical section Sebastian Andrzej Siewior
2026-04-04 20:13 ` Thomas Gleixner
2026-05-22 22:16 ` André Almeida
2026-05-28 2:55 ` André Almeida
2026-05-29 21:27 ` Thomas Gleixner
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=c7f5ad25-7bf7-4e3e-a852-c3cd74f12750@igalia.com \
--to=andrealmeid@igalia.com \
--cc=Liam.Howlett@oracle.com \
--cc=arnd@arndb.de \
--cc=bigeasy@linutronix.de \
--cc=carlos@redhat.com \
--cc=dalias@aerifal.cx \
--cc=dave@stgolabs.net \
--cc=dvhart@infradead.org \
--cc=fweimer@redhat.com \
--cc=kernel-dev@igalia.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux@weissschuh.net \
--cc=mathieu.desnoyers@efficios.com \
--cc=mingo@kernel.org \
--cc=peterz@infradead.org \
--cc=tglx@kernel.org \
--cc=triegel@redhat.com \
--cc=ubizjak@gmail.com \
/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
all inboxes | Powered by JetHome®