| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <Y+D3F2pg7X4XFT4r@hirez.programming.kicks-ass.net>
Date: Mon, 6 Feb 2023 13:48:23 +0100
From: Peter Zijlstra <peterz@...radead.org>
To: Arnd Bergmann <arnd@...db.de>
Cc: Linus Torvalds <torvalds@...ux-foundation.org>,
Jonathan Corbet <corbet@....net>,
Will Deacon <will@...nel.org>,
Boqun Feng <boqun.feng@...il.com>,
Mark Rutland <mark.rutland@....com>,
Catalin Marinas <catalin.marinas@....com>, dennis@...nel.org,
Tejun Heo <tj@...nel.org>, Christoph Lameter <cl@...ux.com>,
Heiko Carstens <hca@...ux.ibm.com>, gor@...ux.ibm.com,
Alexander Gordeev <agordeev@...ux.ibm.com>,
borntraeger@...ux.ibm.com, Sven Schnelle <svens@...ux.ibm.com>,
Thomas Gleixner <tglx@...utronix.de>,
Ingo Molnar <mingo@...hat.com>, Borislav Petkov <bp@...en8.de>,
Dave Hansen <dave.hansen@...ux.intel.com>, x86@...nel.org,
"H. Peter Anvin" <hpa@...or.com>, Joerg Roedel <joro@...tes.org>,
suravee.suthikulpanit@....com, Robin Murphy <robin.murphy@....com>,
dwmw2@...radead.org, Baolu Lu <baolu.lu@...ux.intel.com>,
Herbert Xu <herbert@...dor.apana.org.au>,
"David S . Miller" <davem@...emloft.net>,
Pekka Enberg <penberg@...nel.org>,
David Rientjes <rientjes@...gle.com>,
Joonsoo Kim <iamjoonsoo.kim@....com>,
Andrew Morton <akpm@...ux-foundation.org>,
Vlastimil Babka <vbabka@...e.cz>,
Roman Gushchin <roman.gushchin@...ux.dev>,
Hyeonggon Yoo <42.hyeyoo@...il.com>, linux-doc@...r.kernel.org,
linux-kernel@...r.kernel.org, linux-mm@...ck.org,
linux-s390@...r.kernel.org, iommu@...ts.linux.dev,
Linux-Arch <linux-arch@...r.kernel.org>,
linux-crypto@...r.kernel.org
Subject: Re: [PATCH v2 05/10] percpu: Wire up cmpxchg128
On Mon, Feb 06, 2023 at 01:14:28PM +0100, Peter Zijlstra wrote:
> On Mon, Feb 06, 2023 at 12:24:00PM +0100, Peter Zijlstra wrote:
>
> > > Unless I have misunderstood what you are doing, my concerns are
> > > still the same:
> > >
> > > > #define this_cpu_cmpxchg(pcp, oval, nval) \
> > > > - __pcpu_size_call_return2(this_cpu_cmpxchg_, pcp, oval, nval)
> > > > + __pcpu_size16_call_return2(this_cpu_cmpxchg_, pcp, oval, nval)
> > > > #define this_cpu_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1,
> > > > nval2) \
> > > > __pcpu_double_call_return_bool(this_cpu_cmpxchg_double_, pcp1, pcp2,
> > > > oval1, oval2, nval1, nval2)
> > >
> > > Having a variable-length this_cpu_cmpxchg() that turns into cmpxchg128()
> > > and cmpxchg64() even on CPUs where this traps (!X86_FEATURE_CX16) seems
> > > like a bad design to me.
> > >
> > > I would much prefer fixed-length this_cpu_cmpxchg64()/this_cpu_cmpxchg128()
> > > calls that never trap but fall back to the generic version on CPUs that
> > > are lacking the atomics.
> >
> > You're thinking acidental usage etc..? Lemme see what I can do.
>
> So lookng at this I remember why I did it like this, currently 32bit
> archs silently fall back to the generics for most/all 64bit ops.
>
> And personally I would just as soon drop support for the
> !X86_FEATURE_CX* cpus... :/ Those are some serious museum pieces.
>
> One problem with silent downgrades like this is that semantics vs NMI
> change, which makes for subtle bugs on said museum pieces.
>
> Basically, using 64bit percpu ops on 32bit is already somewhat dangerous
> -- wiring up native cmpxchg64 support in that case seemed an
> improvement.
>
> Anyway... let me get on with doing explicit
> {raw,this}_cpu_cmpxchg{64,128}() thingies.
I only converted x86 and didn't do the automagic downgrade...
Opinions?
---
arch/x86/include/asm/percpu.h | 11 +++++++----
include/asm-generic/percpu.h | 18 ++++++++++++++----
include/linux/percpu-defs.h | 20 ++------------------
mm/slab.h | 2 ++
mm/slub.c | 21 +++++++++++----------
5 files changed, 36 insertions(+), 36 deletions(-)
diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index 4c803a1fd0e7..7515e065369b 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -214,7 +214,7 @@ do { \
#define percpu_cmpxchg64_op(size, qual, _var, _oval, _nval) \
({ \
union { \
- typeof(_var) var; \
+ u64 val; \
struct { \
u32 low, high; \
}; \
@@ -234,15 +234,18 @@ do { \
old__.var; \
})
-#define raw_cpu_cmpxchg_8(pcp, oval, nval) percpu_cmpxchg64_op(8, , pcp, oval, nval)
-#define this_cpu_cmpxchg_8(pcp, oval, nval) percpu_cmpxchg64_op(8, volatile, pcp, oval, nval)
+#define raw_cpu_cmpxchg64(pcp, oval, nval) percpu_cmpxchg64_op(8, , pcp, oval, nval)
+#define this_cpu_cmpxchg64(pcp, oval, nval) percpu_cmpxchg64_op(8, volatile, pcp, oval, nval)
#endif
#ifdef CONFIG_X86_64
+#define raw_cpu_cmpxchg64(pcp, oval, nval) percpu_cmpxchg_op(8, , pcp, oval, nval);
+#define this_cpu_cmpxchg64(pcp, oval, nval) percpu_cmpxchg_op(8, volatile, pcp, oval, nval);
+
#define percpu_cmpxchg128_op(size, qual, _var, _oval, _nval) \
({ \
union { \
- typeof(_var) var; \
+ u128 var; \
struct { \
u64 low, high; \
}; \
diff --git a/include/asm-generic/percpu.h b/include/asm-generic/percpu.h
index ad254a20fe68..7da7d1793411 100644
--- a/include/asm-generic/percpu.h
+++ b/include/asm-generic/percpu.h
@@ -274,8 +274,13 @@ do { \
#define raw_cpu_cmpxchg_8(pcp, oval, nval) \
raw_cpu_generic_cmpxchg(pcp, oval, nval)
#endif
-#ifndef raw_cpu_cmpxchg_16
-#define raw_cpu_cmpxchg_16(pcp, oval, nval) \
+
+#ifndef raw_cpu_cmpxchg64
+#define raw_cpu_cmpxchg64(pcp, oval, nval) \
+ raw_cpu_generic_cmpxchg(pcp, oval, nval)
+#endif
+#ifndef raw_cpu_cmpxchg128
+#define raw_cpu_cmpxchg128(pcp, oval, nval) \
raw_cpu_generic_cmpxchg(pcp, oval, nval)
#endif
@@ -386,8 +391,13 @@ do { \
#define this_cpu_cmpxchg_8(pcp, oval, nval) \
this_cpu_generic_cmpxchg(pcp, oval, nval)
#endif
-#ifndef this_cpu_cmpxchg_16
-#define this_cpu_cmpxchg_16(pcp, oval, nval) \
+
+#ifndef this_cpu_cmpxchg64
+#define this_cpu_cmpxchg64(pcp, oval, nval) \
+ this_cpu_generic_cmpxchg(pcp, oval, nval)
+#endif
+#ifndef this_cpu_cmpxchg128
+#define this_cpu_cmpxchg128(pcp, oval, nval) \
this_cpu_generic_cmpxchg(pcp, oval, nval)
#endif
diff --git a/include/linux/percpu-defs.h b/include/linux/percpu-defs.h
index fe3c7fc2d411..7cd614a46af4 100644
--- a/include/linux/percpu-defs.h
+++ b/include/linux/percpu-defs.h
@@ -343,22 +343,6 @@ static inline void __this_cpu_preempt_check(const char *op) { }
pscr2_ret__; \
})
-#define __pcpu_size16_call_return2(stem, variable, ...) \
-({ \
- typeof(variable) pscr2_ret__; \
- __verify_pcpu_ptr(&(variable)); \
- switch(sizeof(variable)) { \
- case 1: pscr2_ret__ = stem##1(variable, __VA_ARGS__); break; \
- case 2: pscr2_ret__ = stem##2(variable, __VA_ARGS__); break; \
- case 4: pscr2_ret__ = stem##4(variable, __VA_ARGS__); break; \
- case 8: pscr2_ret__ = stem##8(variable, __VA_ARGS__); break; \
- case 16: pscr2_ret__ = stem##16(variable, __VA_ARGS__); break; \
- default: \
- __bad_size_call_parameter(); break; \
- } \
- pscr2_ret__; \
-})
-
#define __pcpu_size_call(stem, variable, ...) \
do { \
__verify_pcpu_ptr(&(variable)); \
@@ -414,7 +398,7 @@ do { \
#define raw_cpu_add_return(pcp, val) __pcpu_size_call_return2(raw_cpu_add_return_, pcp, val)
#define raw_cpu_xchg(pcp, nval) __pcpu_size_call_return2(raw_cpu_xchg_, pcp, nval)
#define raw_cpu_cmpxchg(pcp, oval, nval) \
- __pcpu_size16_call_return2(raw_cpu_cmpxchg_, pcp, oval, nval)
+ __pcpu_size_call_return2(raw_cpu_cmpxchg_, pcp, oval, nval)
#define raw_cpu_sub(pcp, val) raw_cpu_add(pcp, -(val))
#define raw_cpu_inc(pcp) raw_cpu_add(pcp, 1)
#define raw_cpu_dec(pcp) raw_cpu_sub(pcp, 1)
@@ -493,7 +477,7 @@ do { \
#define this_cpu_add_return(pcp, val) __pcpu_size_call_return2(this_cpu_add_return_, pcp, val)
#define this_cpu_xchg(pcp, nval) __pcpu_size_call_return2(this_cpu_xchg_, pcp, nval)
#define this_cpu_cmpxchg(pcp, oval, nval) \
- __pcpu_size16_call_return2(this_cpu_cmpxchg_, pcp, oval, nval)
+ __pcpu_size_call_return2(this_cpu_cmpxchg_, pcp, oval, nval)
#define this_cpu_sub(pcp, val) this_cpu_add(pcp, -(typeof(pcp))(val))
#define this_cpu_inc(pcp) this_cpu_add(pcp, 1)
#define this_cpu_dec(pcp) this_cpu_sub(pcp, 1)
diff --git a/mm/slab.h b/mm/slab.h
index 19e1899673ef..50b5edd6a950 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -25,11 +25,13 @@ typedef union {
# ifdef system_has_cmpxchg128
# define system_has_freelist_aba() system_has_cmpxchg128()
# define try_cmpxchg_freelist try_cmpxchg128
+# define this_cpu_cmpxchg_freelist this_cpu_cmpxchg128
# endif
#else /* CONFIG_64BIT */
# ifdef system_has_cmpxchg64
# define system_has_freelist_aba() system_has_cmpxchg64()
# define try_cmpxchg_freelist try_cmpxchg64
+# define this_cpu_cmpxchg_freelist this_cpu_cmpxchg64
# endif
#endif /* CONFIG_64BIT */
diff --git a/mm/slub.c b/mm/slub.c
index 45f2b28d60e1..35939c5aa28a 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -523,17 +523,14 @@ __update_freelist_fast(struct slab *slab,
void *freelist_old, unsigned long counters_old,
void *freelist_new, unsigned long counters_new)
{
-
- bool ret = false;
-
-#ifdef system_has_freelist_aba
+#ifdef syste_has_freelist_aba
freelist_aba_t old = { .freelist = freelist_old, .counter = counters_old };
freelist_aba_t new = { .freelist = freelist_new, .counter = counters_new };
- ret = try_cmpxchg_freelist(&slab->freelist_counter.full, &old.full, new.full);
-#endif /* system_has_freelist_aba */
-
- return ret;
+ return try_cmpxchg_freelist(&slab->freelist_counter.full, &old.full, new.full);
+#else
+ return false;
+#endif
}
static inline bool
@@ -3039,11 +3036,15 @@ __update_cpu_freelist_fast(struct kmem_cache *s,
void *freelist_old, void *freelist_new,
unsigned long tid)
{
+#ifdef system_has_freelist_aba
freelist_aba_t old = { .freelist = freelist_old, .counter = tid };
freelist_aba_t new = { .freelist = freelist_new, .counter = next_tid(tid) };
- return this_cpu_cmpxchg(s->cpu_slab->freelist_tid.full,
- old.full, new.full) == old.full;
+ return this_cpu_cmpxchg_freelist(s->cpu_slab->freelist_tid.full,
+ old.full, new.full) == old.full;
+#else
+ return false;
+#endif
}
/*
Powered by blists - more mailing lists