On Mon, May 13, 2024 at 08:57:16AM -0700, Boqun Feng wrote:
> On Mon, May 13, 2024 at 08:41:27AM -0700, Paul E. McKenney wrote:
> [...]
> > > > +#include <linux/types.h>
> > > > +#include <linux/export.h>
> > > > +#include <linux/instrumented.h>
> > > > +#include <linux/atomic.h>
> > > > +#include <linux/panic.h>
> > > > +#include <linux/bug.h>
> > > > +#include <asm-generic/rwonce.h>
> > > > +#include <linux/cmpxchg-emu.h>
> > > > +
> > > > +union u8_32 {
> > > > + u8 b[4];
> > > > + u32 w;
> > > > +};
> > > > +
> > > > +/* Emulate one-byte cmpxchg() in terms of 4-byte cmpxchg. */
> > > > +uintptr_t cmpxchg_emu_u8(volatile u8 *p, uintptr_t old, uintptr_t new)
> > > > +{
> > > > + u32 *p32 = (u32 *)(((uintptr_t)p) & ~0x3);
> > > > + int i = ((uintptr_t)p) & 0x3;
> > > > + union u8_32 old32;
> > > > + union u8_32 new32;
> > > > + u32 ret;
> > > > +
> > > > + ret = READ_ONCE(*p32);
> > > > + do {
> > > > + old32.w = ret;
> > > > + if (old32.b[i] != old)
> > > > + return old32.b[i];
> > > > + new32.w = old32.w;
> > > > + new32.b[i] = new;
> > > > + instrument_atomic_read_write(p, 1);
> > > > + ret = data_race(cmpxchg(p32, old32.w, new32.w)); // Overridden above.
> > >
> > > Just out of curiosity, why is this `data_race` needed? cmpxchg is atomic
> > > so there should be no chance for a data race?
> >
> > That is what I thought, too. ;-)
> >
> > The problem is that the cmpxchg() covers 32 bits, and so without that
> > data_race(), KCSAN would complain about data races with perfectly
> > legitimate concurrent accesses to the other three bytes.
> >
> > The instrument_atomic_read_write(p, 1) beforehand tells KCSAN to complain
> > about concurrent accesses, but only to that one byte.
> >
>
> Oh, I see. For that purpose, maybe we can just use raw_cmpxchg() here,
> i.e. a cmpxchg() without any instrument in it. Cc Mark in case I'm
> missing something.
>
I just realized that the KCSAN instrumentation is already done in
cmpxchg() layer:
#define cmpxchg(ptr, ...) \
({ \
typeof(ptr) __ai_ptr = (ptr); \
kcsan_mb(); \
instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
raw_cmpxchg(__ai_ptr, __VA_ARGS__); \
})
and, this function is lower in the layer, so it shouldn't have the
instrumentation itself. How about the following (based on today's RCU
dev branch)?
Regards,
Boqun
-------------------------------------------->8
Subject: [PATCH] lib: cmpxchg-emu: Make cmpxchg_emu_u8() noinstr
Currently, cmpxchg_emu_u8() is called via cmpxchg() or raw_cmpxchg()
which already makes the instrumentation decision:
* cmpxchg() case:
cmpxchg():
kcsan_mb();
instrument_atomic_read_write(...);
raw_cmpxchg():
arch_cmpxchg():
cmpxchg_emu_u8();
... should have KCSAN instrumentation.
* raw_cmpxchg() case:
raw_cmpxchg():
arch_cmpxchg():
cmpxchg_emu_u8();
... shouldn't have KCSAN instrumentation.
Therefore it's redundant to put KCSAN instrumentation in
cmpxchg_emu_u8() (along with the data_race() to get away the
instrumentation).
So make cmpxchg_emu_u8() a noinstr function, and remove the KCSAN
instrumentation inside it.
Signed-off-by: Boqun Feng <boqun.feng@xxxxxxxxx>
---
include/linux/cmpxchg-emu.h | 4 +++-
lib/cmpxchg-emu.c | 14 ++++++++++----
2 files changed, 13 insertions(+), 5 deletions(-)
diff --git a/include/linux/cmpxchg-emu.h b/include/linux/cmpxchg-emu.h
index 998deec67740..c4c85f41d9f4 100644
--- a/include/linux/cmpxchg-emu.h
+++ b/include/linux/cmpxchg-emu.h
@@ -10,6 +10,8 @@
#ifndef __LINUX_CMPXCHG_EMU_H
#define __LINUX_CMPXCHG_EMU_H
-uintptr_t cmpxchg_emu_u8(volatile u8 *p, uintptr_t old, uintptr_t new);
+#include <linux/compiler.h>
+
+noinstr uintptr_t cmpxchg_emu_u8(volatile u8 *p, uintptr_t old, uintptr_t new);
#endif /* __LINUX_CMPXCHG_EMU_H */
diff --git a/lib/cmpxchg-emu.c b/lib/cmpxchg-emu.c
index 27f6f97cb60d..788c22cd4462 100644
--- a/lib/cmpxchg-emu.c
+++ b/lib/cmpxchg-emu.c
@@ -21,8 +21,13 @@ union u8_32 {
u32 w;
};
-/* Emulate one-byte cmpxchg() in terms of 4-byte cmpxchg. */
-uintptr_t cmpxchg_emu_u8(volatile u8 *p, uintptr_t old, uintptr_t new)
+/*
+ * Emulate one-byte cmpxchg() in terms of 4-byte cmpxchg.
+ *
+ * This function is marked as 'noinstr' as the instrumentation should be done at
+ * outer layer.
+ */
+noinstr uintptr_t cmpxchg_emu_u8(volatile u8 *p, uintptr_t old, uintptr_t new)
{
u32 *p32 = (u32 *)(((uintptr_t)p) & ~0x3);
int i = ((uintptr_t)p) & 0x3;
@@ -37,8 +42,9 @@ uintptr_t cmpxchg_emu_u8(volatile u8 *p, uintptr_t old, uintptr_t new)
return old32.b[i];
new32.w = old32.w;
new32.b[i] = new;
- instrument_atomic_read_write(p, 1);
- ret = data_race(cmpxchg(p32, old32.w, new32.w)); // Overridden above.
+
+ // raw_cmpxchg() is used here to avoid instrumentation.
+ ret = raw_cmpxchg(p32, old32.w, new32.w); // Overridden above.
} while (ret != old32.w);
return old;
}
--
2.44.0
