Compiler CSE and SSA GVN optimizations can cause the address dependency
of addresses returned by rcu_dereference to be lost when comparing those
pointers with either constants or previously loaded pointers.
Introduce ptr_eq() to compare two addresses while preserving the address
dependencies for later use of the address. It should be used when
comparing an address returned by rcu_dereference().
This is needed to prevent the compiler CSE and SSA GVN optimizations
from using @a (or @b) in places where the source refers to @b (or @a)
based on the fact that after the comparison, the two are known to be
equal, which does not preserve address dependencies and allows the
following misordering speculations:
- If @b is a constant, the compiler can issue the loads which depend
on @a before loading @a.
- If @b is a register populated by a prior load, weakly-ordered
CPUs can speculate loads which depend on @a before loading @a.
The same logic applies with @a and @b swapped.
Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Suggested-by: Boqun Feng <boqun.feng@gmail.com>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Reviewed-by: Boqun Feng <boqun.feng@gmail.com>
Acked-by: "Paul E. McKenney" <paulmck@kernel.org>
Acked-by: Alan Stern <stern@rowland.harvard.edu>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: "Paul E. McKenney" <paulmck@kernel.org>
Cc: Will Deacon <will@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: John Stultz <jstultz@google.com>
Cc: Neeraj Upadhyay <Neeraj.Upadhyay@amd.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Frederic Weisbecker <frederic@kernel.org>
Cc: Joel Fernandes <joel@joelfernandes.org>
Cc: Josh Triplett <josh@joshtriplett.org>
Cc: Uladzislau Rezki <urezki@gmail.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Lai Jiangshan <jiangshanlai@gmail.com>
Cc: Zqiang <qiang.zhang1211@gmail.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Waiman Long <longman@redhat.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: maged.michael@gmail.com
Cc: Mateusz Guzik <mjguzik@gmail.com>
Cc: Gary Guo <gary@garyguo.net>
Cc: Jonas Oberhauser <jonas.oberhauser@huaweicloud.com>
Cc: rcu@vger.kernel.org
Cc: linux-mm@kvack.org
Cc: lkmm@lists.linux.dev
Cc: Nikita Popov <github@npopov.com>
Cc: llvm@lists.linux.dev
---
Changes since v0:
- Include feedback from Alan Stern.
---
include/linux/compiler.h | 63 ++++++++++++++++++++++++++++++++++++++++
1 file changed, 63 insertions(+)
diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index 2df665fa2964..75a378ae7af1 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -186,6 +186,69 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val,
__asm__ ("" : "=r" (var) : "0" (var))
#endif
+/*
+ * Compare two addresses while preserving the address dependencies for
+ * later use of the address. It should be used when comparing an address
+ * returned by rcu_dereference().
+ *
+ * This is needed to prevent the compiler CSE and SSA GVN optimizations
+ * from using @a (or @b) in places where the source refers to @b (or @a)
+ * based on the fact that after the comparison, the two are known to be
+ * equal, which does not preserve address dependencies and allows the
+ * following misordering speculations:
+ *
+ * - If @b is a constant, the compiler can issue the loads which depend
+ * on @a before loading @a.
+ * - If @b is a register populated by a prior load, weakly-ordered
+ * CPUs can speculate loads which depend on @a before loading @a.
+ *
+ * The same logic applies with @a and @b swapped.
+ *
+ * Return value: true if pointers are equal, false otherwise.
+ *
+ * The compiler barrier() is ineffective at fixing this issue. It does
+ * not prevent the compiler CSE from losing the address dependency:
+ *
+ * int fct_2_volatile_barriers(void)
+ * {
+ * int *a, *b;
+ *
+ * do {
+ * a = READ_ONCE(p);
+ * asm volatile ("" : : : "memory");
+ * b = READ_ONCE(p);
+ * } while (a != b);
+ * asm volatile ("" : : : "memory"); <-- barrier()
+ * return *b;
+ * }
+ *
+ * With gcc 14.2 (arm64):
+ *
+ * fct_2_volatile_barriers:
+ * adrp x0, .LANCHOR0
+ * add x0, x0, :lo12:.LANCHOR0
+ * .L2:
+ * ldr x1, [x0] <-- x1 populated by first load.
+ * ldr x2, [x0]
+ * cmp x1, x2
+ * bne .L2
+ * ldr w0, [x1] <-- x1 is used for access which should depend on b.
+ * ret
+ *
+ * On weakly-ordered architectures, this lets CPU speculation use the
+ * result from the first load to speculate "ldr w0, [x1]" before
+ * "ldr x2, [x0]".
+ * Based on the RCU documentation, the control dependency does not
+ * prevent the CPU from speculating loads.
+ */
+static __always_inline
+int ptr_eq(const volatile void *a, const volatile void *b)
+{
+ OPTIMIZER_HIDE_VAR(a);
+ OPTIMIZER_HIDE_VAR(b);
+ return a == b;
+}
+
#define __UNIQUE_ID(prefix) __PASTE(__PASTE(__UNIQUE_ID_, prefix), __COUNTER__)
/**
--
2.39.2On Tue, Oct 01, 2024 at 09:02:02PM -0400, Mathieu Desnoyers wrote:
> Compiler CSE and SSA GVN optimizations can cause the address dependency
> of addresses returned by rcu_dereference to be lost when comparing those
> pointers with either constants or previously loaded pointers.
>
> Introduce ptr_eq() to compare two addresses while preserving the address
> dependencies for later use of the address. It should be used when
> comparing an address returned by rcu_dereference().
>
> This is needed to prevent the compiler CSE and SSA GVN optimizations
> from using @a (or @b) in places where the source refers to @b (or @a)
> based on the fact that after the comparison, the two are known to be
> equal, which does not preserve address dependencies and allows the
> following misordering speculations:
>
> - If @b is a constant, the compiler can issue the loads which depend
> on @a before loading @a.
> - If @b is a register populated by a prior load, weakly-ordered
> CPUs can speculate loads which depend on @a before loading @a.
>
> The same logic applies with @a and @b swapped.
>
[...]
> +/*
> + * Compare two addresses while preserving the address dependencies for
> + * later use of the address. It should be used when comparing an address
> + * returned by rcu_dereference().
> + *
> + * This is needed to prevent the compiler CSE and SSA GVN optimizations
> + * from using @a (or @b) in places where the source refers to @b (or @a)
> + * based on the fact that after the comparison, the two are known to be
> + * equal, which does not preserve address dependencies and allows the
> + * following misordering speculations:
> + *
> + * - If @b is a constant, the compiler can issue the loads which depend
> + * on @a before loading @a.
> + * - If @b is a register populated by a prior load, weakly-ordered
> + * CPUs can speculate loads which depend on @a before loading @a.
> + *
> + * The same logic applies with @a and @b swapped.
> + *
> + * Return value: true if pointers are equal, false otherwise.
> + *
> + * The compiler barrier() is ineffective at fixing this issue. It does
> + * not prevent the compiler CSE from losing the address dependency:
> + *
> + * int fct_2_volatile_barriers(void)
> + * {
> + * int *a, *b;
> + *
> + * do {
> + * a = READ_ONCE(p);
> + * asm volatile ("" : : : "memory");
> + * b = READ_ONCE(p);
> + * } while (a != b);
> + * asm volatile ("" : : : "memory"); <-- barrier()
> + * return *b;
> + * }
> + *
> + * With gcc 14.2 (arm64):
> + *
> + * fct_2_volatile_barriers:
> + * adrp x0, .LANCHOR0
> + * add x0, x0, :lo12:.LANCHOR0
> + * .L2:
> + * ldr x1, [x0] <-- x1 populated by first load.
> + * ldr x2, [x0]
> + * cmp x1, x2
> + * bne .L2
> + * ldr w0, [x1] <-- x1 is used for access which should depend on b.
> + * ret
> + *
I could reproduce this in compiler explorer, but I'm curious what flags are
you using? For me it does a bunch of usage of the stack for temporary storage
(still incorrectly returns *a though as you pointed).
Interestingly, if I just move the comparison into an an __always_inline__
function like below, but without the optimizer hide stuff, gcc 14.2 on arm64
does generate the correct code:
static inline __attribute__((__always_inline__)) int ptr_eq(const volatile void *a, const volatile void *b)
{
/* No OPTIMIZER_HIDE_VAR */
return a == b;
}
volatile int *p = 0;
int fct_2_volatile_barriers()
{
int *a, *b;
do {
a = READ_ONCE(p);
asm volatile ("" : : : "memory");
b = READ_ONCE(p);
} while (!ptr_eq(a, b));
asm volatile ("" : : : "memory"); // barrier()
return *b;
}
But not sure if it fixes the speculation issue you referred to.
Putting back the OPTIMIZER_HIDE_VAR() then just seems to pass the a and b
stored on the stack through a washing machine:
ldr x0, [sp, 8]
str x0, [sp, 8]
ldr x0, [sp]
str x0, [sp]
And here I thought the "" in OPTIMIZER_HIDE_VAR was not supposed to generate
any code but I guess it is still a NOOP.
Anyway, as such this LGTM since whether OPTIMIZER_HIDE_VAR() used or not, it
does fix the problem.
Reviewed-by: Joel Fernandes (Google) <joel@joelfernandes.org>
thanks,
- Joel
On 2024-10-03 02:08, Joel Fernandes wrote:
> On Tue, Oct 01, 2024 at 09:02:02PM -0400, Mathieu Desnoyers wrote:
>> Compiler CSE and SSA GVN optimizations can cause the address dependency
>> of addresses returned by rcu_dereference to be lost when comparing those
>> pointers with either constants or previously loaded pointers.
>>
>> Introduce ptr_eq() to compare two addresses while preserving the address
>> dependencies for later use of the address. It should be used when
>> comparing an address returned by rcu_dereference().
>>
>> This is needed to prevent the compiler CSE and SSA GVN optimizations
>> from using @a (or @b) in places where the source refers to @b (or @a)
>> based on the fact that after the comparison, the two are known to be
>> equal, which does not preserve address dependencies and allows the
>> following misordering speculations:
>>
>> - If @b is a constant, the compiler can issue the loads which depend
>> on @a before loading @a.
>> - If @b is a register populated by a prior load, weakly-ordered
>> CPUs can speculate loads which depend on @a before loading @a.
>>
>> The same logic applies with @a and @b swapped.
>>
> [...]
>> +/*
>> + * Compare two addresses while preserving the address dependencies for
>> + * later use of the address. It should be used when comparing an address
>> + * returned by rcu_dereference().
>> + *
>> + * This is needed to prevent the compiler CSE and SSA GVN optimizations
>> + * from using @a (or @b) in places where the source refers to @b (or @a)
>> + * based on the fact that after the comparison, the two are known to be
>> + * equal, which does not preserve address dependencies and allows the
>> + * following misordering speculations:
>> + *
>> + * - If @b is a constant, the compiler can issue the loads which depend
>> + * on @a before loading @a.
>> + * - If @b is a register populated by a prior load, weakly-ordered
>> + * CPUs can speculate loads which depend on @a before loading @a.
>> + *
>> + * The same logic applies with @a and @b swapped.
>> + *
>> + * Return value: true if pointers are equal, false otherwise.
>> + *
>> + * The compiler barrier() is ineffective at fixing this issue. It does
>> + * not prevent the compiler CSE from losing the address dependency:
>> + *
>> + * int fct_2_volatile_barriers(void)
>> + * {
>> + * int *a, *b;
>> + *
>> + * do {
>> + * a = READ_ONCE(p);
>> + * asm volatile ("" : : : "memory");
>> + * b = READ_ONCE(p);
>> + * } while (a != b);
>> + * asm volatile ("" : : : "memory"); <-- barrier()
>> + * return *b;
>> + * }
>> + *
>> + * With gcc 14.2 (arm64):
>> + *
>> + * fct_2_volatile_barriers:
>> + * adrp x0, .LANCHOR0
>> + * add x0, x0, :lo12:.LANCHOR0
>> + * .L2:
>> + * ldr x1, [x0] <-- x1 populated by first load.
>> + * ldr x2, [x0]
>> + * cmp x1, x2
>> + * bne .L2
>> + * ldr w0, [x1] <-- x1 is used for access which should depend on b.
>> + * ret
>> + *
>
> I could reproduce this in compiler explorer, but I'm curious what flags are
> you using? For me it does a bunch of usage of the stack for temporary storage
> (still incorrectly returns *a though as you pointed).
You are probably missing "-O2".
>
> Interestingly, if I just move the comparison into an an __always_inline__
> function like below, but without the optimizer hide stuff, gcc 14.2 on arm64
> does generate the correct code:
Make sure you compile in -O2. Based on a quick check here the hide var
is needed to make sure the compiler does the intended behavior in O2.
>
> static inline __attribute__((__always_inline__)) int ptr_eq(const volatile void *a, const volatile void *b)
> {
> /* No OPTIMIZER_HIDE_VAR */
> return a == b;
> }
>
> volatile int *p = 0;
>
> int fct_2_volatile_barriers()
> {
> int *a, *b;
>
> do {
> a = READ_ONCE(p);
> asm volatile ("" : : : "memory");
> b = READ_ONCE(p);
> } while (!ptr_eq(a, b));
> asm volatile ("" : : : "memory"); // barrier()
> return *b;
> }
>
> But not sure if it fixes the speculation issue you referred to.
Not in -O2.
>
> Putting back the OPTIMIZER_HIDE_VAR() then just seems to pass the a and b
> stored on the stack through a washing machine:
>
> ldr x0, [sp, 8]
> str x0, [sp, 8]
> ldr x0, [sp]
> str x0, [sp]
That washing machine looks like the result of -O0.
>
> And here I thought the "" in OPTIMIZER_HIDE_VAR was not supposed to generate
> any code but I guess it is still a NOOP.
The hide var will only emit an extra register movement to copy the
register to a temporary. That's one extra instruction but not as bad
as what you observe in -O0.
>
> Anyway, as such this LGTM since whether OPTIMIZER_HIDE_VAR() used or not, it
> does fix the problem.
hide var is needed in O2.
>
> Reviewed-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Please double-check with -O2, and let me know if you still agree with
the patch :)
Thanks,
Mathieu
>
> thanks,
>
> - Joel
>
--
Mathieu Desnoyers
EfficiOS Inc.
https://www.efficios.com
On Thu, Oct 3, 2024 at 10:21 AM Mathieu Desnoyers <mathieu.desnoyers@efficios.com> wrote: > > > > Reviewed-by: Joel Fernandes (Google) <joel@joelfernandes.org> > > Please double-check with -O2, and let me know if you still agree with > the patch :) > You are quite right, with -O2 I can indeed see that the optimize hide var fixes it. FWIW: Tested-by: Joel Fernandes (Google) <joel@joelfernandes.org> Thanks! - Joel
© 2016 - 2024 Red Hat, Inc.