user/sven/linux.git/include/linux/seqlock.h, branch v4.9.243

seqlock: Require WRITE_ONCE surrounding raw_seqcount_barrier

2020-10-01T18:40:04Z

[ Upstream commit bf07132f96d426bcbf2098227fb680915cf44498 ] This patch proposes to require marked atomic accesses surrounding raw_write_seqcount_barrier. We reason that otherwise there is no way to guarantee propagation nor atomicity of writes before/after the barrier [1]. For example, consider the compiler tears stores either before or after the barrier; in this case, readers may observe a partial value, and because readers are unaware that writes are going on (writes are not in a seq-writer critical section), will complete the seq-reader critical section while having observed some partial state. [1] https://lwn.net/Articles/793253/ This came up when designing and implementing KCSAN, because KCSAN would flag these accesses as data-races. After careful analysis, our reasoning as above led us to conclude that the best thing to do is to propose an amendment to the raw_seqcount_barrier usage. Signed-off-by: Marco Elver Acked-by: Paul E. McKenney Signed-off-by: Paul E. McKenney Signed-off-by: Sasha Levin

locking/seqcount: Re-fix raw_read_seqcount_latch()

2016-06-03T06:37:25Z

Commit 50755bc1c305 ("seqlock: fix raw_read_seqcount_latch()") broke raw_read_seqcount_latch(). If you look at the comment that was modified; the thing that changes is the seq count, not the latch pointer. * void latch_modify(struct latch_struct *latch, ...) * { * smp_wmb(); <- Ensure that the last data[1] update is visible * latch->seq++; * smp_wmb(); <- Ensure that the seqcount update is visible * * modify(latch->data[0], ...); * * smp_wmb(); <- Ensure that the data[0] update is visible * latch->seq++; * smp_wmb(); <- Ensure that the seqcount update is visible * * modify(latch->data[1], ...); * } * * The query will have a form like: * * struct entry *latch_query(struct latch_struct *latch, ...) * { * struct entry *entry; * unsigned seq, idx; * * do { * seq = lockless_dereference(latch->seq); So here we have: seq = READ_ONCE(latch->seq); smp_read_barrier_depends(); Which is exactly what we want; the new code: seq = ({ p = READ_ONCE(latch); smp_read_barrier_depends(); p })->seq; is just wrong; because it looses the volatile read on seq, which can now be torn or worse 'optimized'. And the read_depend barrier is also placed wrong, we want it after the load of seq, to match the above data[] up-to-date wmb()s. Such that when we dereference latch->data[] below, we're guaranteed to observe the right data. * * idx = seq & 0x01; * entry = data_query(latch->data[idx], ...); * * smp_rmb(); * } while (seq != latch->seq); * * return entry; * } So yes, not passing a pointer is not pretty, but the code was correct, and isn't anymore now. Change to explicit READ_ONCE()+smp_read_barrier_depends() to avoid confusion and allow strict lockless_dereference() checking. Signed-off-by: Peter Zijlstra (Intel) Cc: Alexey Dobriyan Cc: Andrew Morton Cc: Linus Torvalds Cc: Paul E. McKenney Cc: Paul McKenney Cc: Peter Zijlstra Cc: Thomas Gleixner Fixes: 50755bc1c305 ("seqlock: fix raw_read_seqcount_latch()") Link: http://lkml.kernel.org/r/20160527111117.GL3192@twins.programming.kicks-ass.net Signed-off-by: Ingo Molnar

seqlock: fix raw_read_seqcount_latch()

2016-05-26T22:35:44Z

lockless_dereference() is supposed to take pointer not integer. Link: http://lkml.kernel.org/r/20160521201448.GA7429@p183.telecom.by Signed-off-by: Alexey Dobriyan Cc: Peter Zijlstra Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds

Merge tag 'modules-next-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rusty/linux

2015-07-01T17:49:25Z

Pull module updates from Rusty Russell: "Main excitement here is Peter Zijlstra's lockless rbtree optimization to speed module address lookup. He found some abusers of the module lock doing that too. A little bit of parameter work here too; including Dan Streetman's breaking up the big param mutex so writing a parameter can load another module (yeah, really). Unfortunately that broke the usual suspects, !CONFIG_MODULES and !CONFIG_SYSFS, so those fixes were appended too" * tag 'modules-next-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rusty/linux: (26 commits) modules: only use mod->param_lock if CONFIG_MODULES param: fix module param locks when !CONFIG_SYSFS. rcu: merge fix for Convert ACCESS_ONCE() to READ_ONCE() and WRITE_ONCE() module: add per-module param_lock module: make perm const params: suppress unused variable error, warn once just in case code changes. modules: clarify CONFIG_MODULE_COMPRESS help, suggest 'N'. kernel/module.c: avoid ifdefs for sig_enforce declaration kernel/workqueue.c: remove ifdefs over wq_power_efficient kernel/params.c: export param_ops_bool_enable_only kernel/params.c: generalize bool_enable_only kernel/module.c: use generic module param operaters for sig_enforce kernel/params: constify struct kernel_param_ops uses sysfs: tightened sysfs permission checks module: Rework module_addr_{min,max} module: Use __module_address() for module_address_lookup() module: Make the mod_tree stuff conditional on PERF_EVENTS || TRACING module: Optimize __module_address() using a latched RB-tree rbtree: Implement generic latch_tree seqlock: Introduce raw_read_seqcount_latch() ...

seqcount: Introduce raw_write_seqcount_barrier()

2015-06-18T22:09:56Z

Introduce raw_write_seqcount_barrier(), a new construct that can be used to provide write barrier semantics in seqcount read loops instead of the usual consistency guarantee. raw_write_seqcount_barier() is equivalent to: raw_write_seqcount_begin(); raw_write_seqcount_end(); But avoids issueing two back-to-back smp_wmb() instructions. This construct works because the read side will 'stall' when observing odd values. This means that -- referring to the example in the comment below -- even though there is no (matching) read barrier between the loads of X and Y, we cannot observe !x && !y, because: - if we observe Y == false we must observe the first sequence increment, which makes us loop, until - we observe !(seq & 1) -- the second sequence increment -- at which time we must also observe T == true. Suggested-by: Oleg Nesterov Signed-off-by: Peter Zijlstra (Intel) Cc: umgwanakikbuti@gmail.com Cc: ktkhai@parallels.com Cc: rostedt@goodmis.org Cc: juri.lelli@gmail.com Cc: pang.xunlei@linaro.org Cc: oleg@redhat.com Cc: wanpeng.li@linux.intel.com Cc: Al Viro Cc: Linus Torvalds Cc: Paul E. McKenney Link: http://lkml.kernel.org/r/20150617122924.GP3644@twins.programming.kicks-ass.net Signed-off-by: Thomas Gleixner

seqcount: Rename write_seqcount_barrier()

2015-06-18T22:09:56Z

I'll shortly be introducing another seqcount primitive that's useful to provide ordering semantics and would like to use the write_seqcount_barrier() name for that. Seeing how there's only one user of the current primitive, lets rename it to invalidate, as that appears what its doing. While there, employ lockdep_assert_held() instead of assert_spin_locked() to not generate debug code for regular kernels. Signed-off-by: Peter Zijlstra (Intel) Cc: ktkhai@parallels.com Cc: rostedt@goodmis.org Cc: juri.lelli@gmail.com Cc: pang.xunlei@linaro.org Cc: Oleg Nesterov Cc: wanpeng.li@linux.intel.com Cc: Paul McKenney Cc: Al Viro Cc: Linus Torvalds Cc: umgwanakikbuti@gmail.com Link: http://lkml.kernel.org/r/20150611124743.279926217@infradead.org Signed-off-by: Thomas Gleixner

seqlock: Introduce raw_read_seqcount_latch()

2015-05-28T02:02:06Z

Because with latches there is a strict data dependency on the seq load we can avoid the rmb in favour of a read_barrier_depends. Suggested-by: Ingo Molnar Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Rusty Russell

seqlock: Better document raw_write_seqcount_latch()

2015-05-28T02:02:04Z

Improve the documentation of the latch technique as used in the current timekeeping code, such that it can be readily employed elsewhere. Borrow from the comments in timekeeping and replace those with a reference to this more generic comment. Cc: Andrea Arcangeli Cc: David Woodhouse Cc: Rik van Riel Cc: "Paul E. McKenney" Cc: Oleg Nesterov Reviewed-by: Mathieu Desnoyers Acked-by: Michel Lespinasse Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Rusty Russell

locking: Remove ACCESS_ONCE() usage

2015-02-24T07:44:16Z

With the new standardized functions, we can replace all ACCESS_ONCE() calls across relevant locking - this includes lockref and seqlock while at it. ACCESS_ONCE() does not work reliably on non-scalar types. For example gcc 4.6 and 4.7 might remove the volatile tag for such accesses during the SRA (scalar replacement of aggregates) step: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=58145 Update the new calls regardless of if it is a scalar type, this is cleaner than having three alternatives. Signed-off-by: Davidlohr Bueso Cc: Peter Zijlstra Cc: Linus Torvalds Cc: Andrew Morton Cc: Thomas Gleixner Cc: Paul E. McKenney Link: http://lkml.kernel.org/r/1424662301.6539.18.camel@stgolabs.net Signed-off-by: Ingo Molnar

seqlock: Add irqsave variant of read_seqbegin_or_lock()

2014-09-19T10:35:16Z

There are cases where read_seqbegin_or_lock() needs to block irqs, because the seqlock in question nests inside a lock that is also be taken from irq context. Add read_seqbegin_or_lock_irqsave() and done_seqretry_irqrestore(), which are almost identical to read_seqbegin_or_lock() and done_seqretry(). Signed-off-by: Rik van Riel Signed-off-by: Peter Zijlstra (Intel) Cc: prarit@redhat.com Cc: oleg@redhat.com Cc: sgruszka@redhat.com Cc: Al Viro Cc: John Stultz Cc: Linus Torvalds Cc: Mathieu Desnoyers Cc: Stephen Boyd Cc: Trond Myklebust Link: http://lkml.kernel.org/r/1410527535-9814-2-git-send-email-riel@redhat.com [ Improved the readability of the code a bit. ] Signed-off-by: Ingo Molnar