From: Linus Torvalds <torvalds@linux-foundation.org>
To: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Minchan Kim <minchan.kim@gmail.com>,
Peter Zijlstra <a.p.zijlstra@chello.nl>,
"Paul E. McKenney" <paulmck@linux.vnet.ibm.com>,
Peter Zijlstra <peterz@infradead.org>,
"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
"linux-mm@kvack.org" <linux-mm@kvack.org>,
cl@linux-foundation.org,
"hugh.dickins" <hugh.dickins@tiscali.co.uk>,
Nick Piggin <nickpiggin@yahoo.com.au>,
Ingo Molnar <mingo@elte.hu>
Subject: Re: [RFC][PATCH 6/8] mm: handle_speculative_fault()
Date: Tue, 5 Jan 2010 17:37:08 -0800 (PST) [thread overview]
Message-ID: <alpine.LFD.2.00.1001051718100.3630@localhost.localdomain> (raw)
In-Reply-To: <20100106092212.c8766aa8.kamezawa.hiroyu@jp.fujitsu.com>
On Wed, 6 Jan 2010, KAMEZAWA Hiroyuki wrote:
>
> I think this is the 1st reason but haven't rewrote rwsem itself and tested,
> sorry.
Here's a totally untested patch! It may or may not work. It builds for me,
but that may be some cosmic accident. I _think_ I got the callee-clobbered
register set right, but somebody should check the comment in the new
rwsem_64.S, and double-check that the code actually matches what I tried
to do.
I had to change the inline asm to get the register sizes right too, so for
all I know this screws up x86-32 too.
In other words: UNTESTED! It may molest your pets and drink all your beer.
You have been warned.
(Is a 16-bit rwsem count even enough for x86-64? Possibly not. That's a
separate issue entirely, though).
Linus
---
arch/x86/Kconfig.cpu | 2 +-
arch/x86/include/asm/rwsem.h | 18 +++++-----
arch/x86/lib/Makefile | 1 +
arch/x86/lib/rwsem_64.S | 81 ++++++++++++++++++++++++++++++++++++++++++
4 files changed, 92 insertions(+), 10 deletions(-)
diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu
index f20ddf8..a198293 100644
--- a/arch/x86/Kconfig.cpu
+++ b/arch/x86/Kconfig.cpu
@@ -319,7 +319,7 @@ config X86_L1_CACHE_SHIFT
config X86_XADD
def_bool y
- depends on X86_32 && !M386
+ depends on X86_64 || !M386
config X86_PPRO_FENCE
bool "PentiumPro memory ordering errata workaround"
diff --git a/arch/x86/include/asm/rwsem.h b/arch/x86/include/asm/rwsem.h
index ca7517d..625baca 100644
--- a/arch/x86/include/asm/rwsem.h
+++ b/arch/x86/include/asm/rwsem.h
@@ -65,7 +65,7 @@ extern asmregparm struct rw_semaphore *
#define RWSEM_ACTIVE_WRITE_BIAS (RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS)
struct rw_semaphore {
- signed long count;
+ __s32 count;
spinlock_t wait_lock;
struct list_head wait_list;
#ifdef CONFIG_DEBUG_LOCK_ALLOC
@@ -105,7 +105,7 @@ do { \
static inline void __down_read(struct rw_semaphore *sem)
{
asm volatile("# beginning down_read\n\t"
- LOCK_PREFIX " incl (%%eax)\n\t"
+ LOCK_PREFIX " incl (%1)\n\t"
/* adds 0x00000001, returns the old value */
" jns 1f\n"
" call call_rwsem_down_read_failed\n"
@@ -147,7 +147,7 @@ static inline void __down_write_nested(struct rw_semaphore *sem, int subclass)
tmp = RWSEM_ACTIVE_WRITE_BIAS;
asm volatile("# beginning down_write\n\t"
- LOCK_PREFIX " xadd %%edx,(%%eax)\n\t"
+ LOCK_PREFIX " xaddl %%edx,(%2)\n\t"
/* subtract 0x0000ffff, returns the old value */
" testl %%edx,%%edx\n\t"
/* was the count 0 before? */
@@ -170,9 +170,9 @@ static inline void __down_write(struct rw_semaphore *sem)
*/
static inline int __down_write_trylock(struct rw_semaphore *sem)
{
- signed long ret = cmpxchg(&sem->count,
- RWSEM_UNLOCKED_VALUE,
- RWSEM_ACTIVE_WRITE_BIAS);
+ __s32 ret = cmpxchg(&sem->count,
+ RWSEM_UNLOCKED_VALUE,
+ RWSEM_ACTIVE_WRITE_BIAS);
if (ret == RWSEM_UNLOCKED_VALUE)
return 1;
return 0;
@@ -185,7 +185,7 @@ static inline void __up_read(struct rw_semaphore *sem)
{
__s32 tmp = -RWSEM_ACTIVE_READ_BIAS;
asm volatile("# beginning __up_read\n\t"
- LOCK_PREFIX " xadd %%edx,(%%eax)\n\t"
+ LOCK_PREFIX " xaddl %%edx,(%2)\n\t"
/* subtracts 1, returns the old value */
" jns 1f\n\t"
" call call_rwsem_wake\n"
@@ -203,7 +203,7 @@ static inline void __up_write(struct rw_semaphore *sem)
{
asm volatile("# beginning __up_write\n\t"
" movl %2,%%edx\n\t"
- LOCK_PREFIX " xaddl %%edx,(%%eax)\n\t"
+ LOCK_PREFIX " xaddl %%edx,(%1)\n\t"
/* tries to transition
0xffff0001 -> 0x00000000 */
" jz 1f\n"
@@ -221,7 +221,7 @@ static inline void __up_write(struct rw_semaphore *sem)
static inline void __downgrade_write(struct rw_semaphore *sem)
{
asm volatile("# beginning __downgrade_write\n\t"
- LOCK_PREFIX " addl %2,(%%eax)\n\t"
+ LOCK_PREFIX " addl %2,(%1)\n\t"
/* transitions 0xZZZZ0001 -> 0xYYYY0001 */
" jns 1f\n\t"
" call call_rwsem_downgrade_wake\n"
diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile
index cffd754..c802451 100644
--- a/arch/x86/lib/Makefile
+++ b/arch/x86/lib/Makefile
@@ -39,4 +39,5 @@ else
lib-y += thunk_64.o clear_page_64.o copy_page_64.o
lib-y += memmove_64.o memset_64.o
lib-y += copy_user_64.o rwlock_64.o copy_user_nocache_64.o
+ lib-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem_64.o
endif
diff --git a/arch/x86/lib/rwsem_64.S b/arch/x86/lib/rwsem_64.S
new file mode 100644
index 0000000..15acecf
--- /dev/null
+++ b/arch/x86/lib/rwsem_64.S
@@ -0,0 +1,81 @@
+/*
+ * x86-64 rwsem wrappers
+ *
+ * This interfaces the inline asm code to the slow-path
+ * C routines. We need to save the call-clobbered regs
+ * that the asm does not mark as clobbered, and move the
+ * argument from %rax to %rdi.
+ *
+ * NOTE! We don't need to save %rax, because the functions
+ * will always return the semaphore pointer in %rax (which
+ * is also the input argument to these helpers)
+ *
+ * The following can clobber %rdx because the asm clobbers it:
+ * call_rwsem_down_write_failed
+ * call_rwsem_wake
+ * but %rdi, %rsi, %rcx, %r8-r11 always need saving.
+ */
+
+#include <linux/linkage.h>
+#include <asm/rwlock.h>
+#include <asm/alternative-asm.h>
+#include <asm/frame.h>
+#include <asm/dwarf2.h>
+
+#define save_common_regs \
+ pushq %rdi; \
+ pushq %rsi; \
+ pushq %rcx; \
+ pushq %r8; \
+ pushq %r9; \
+ pushq %r10; \
+ pushq %r11
+
+#define restore_common_regs \
+ popq %r11; \
+ popq %r10; \
+ popq %r9; \
+ popq %r8; \
+ popq %rcx; \
+ popq %rsi; \
+ popq %rdi
+
+/* Fix up special calling conventions */
+ENTRY(call_rwsem_down_read_failed)
+ save_common_regs
+ pushq %rdx
+ movq %rax,%rdi
+ call rwsem_down_read_failed
+ popq %rdx
+ restore_common_regs
+ ret
+ ENDPROC(call_rwsem_down_read_failed)
+
+ENTRY(call_rwsem_down_write_failed)
+ save_common_regs
+ movq %rax,%rdi
+ call rwsem_down_write_failed
+ restore_common_regs
+ ret
+ ENDPROC(call_rwsem_down_write_failed)
+
+ENTRY(call_rwsem_wake)
+ decw %dx /* do nothing if still outstanding active readers */
+ jnz 1f
+ save_common_regs
+ movq %rax,%rdi
+ call rwsem_wake
+ restore_common_regs
+1: ret
+ ENDPROC(call_rwsem_wake)
+
+/* Fix up special calling conventions */
+ENTRY(call_rwsem_downgrade_wake)
+ save_common_regs
+ pushq %rdx
+ movq %rax,%rdi
+ call rwsem_downgrade_wake
+ popq %rdx
+ restore_common_regs
+ ret
+ ENDPROC(call_rwsem_downgrade_wake)
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
next prev parent reply other threads:[~2010-01-06 1:37 UTC|newest]
Thread overview: 121+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-01-04 18:24 [RFC][PATCH 0/8] Speculative pagefault -v3 Peter Zijlstra
2010-01-04 18:24 ` [RFC][PATCH 1/8] mm: Remove pte reference from fault path Peter Zijlstra
2010-01-04 18:24 ` [RFC][PATCH 2/8] mm: Speculative pagefault infrastructure Peter Zijlstra
2010-01-04 18:24 ` [RFC][PATCH 3/8] mm: Add vma sequence count Peter Zijlstra
2010-01-04 18:24 ` [RFC][PATCH 4/8] mm: RCU free vmas Peter Zijlstra
2010-01-05 2:43 ` Paul E. McKenney
2010-01-05 8:28 ` Peter Zijlstra
2010-01-05 16:05 ` Paul E. McKenney
2010-01-04 18:24 ` [RFC][PATCH 5/8] mm: Speculative pte_map_lock() Peter Zijlstra
2010-01-04 18:24 ` [RFC][PATCH 6/8] mm: handle_speculative_fault() Peter Zijlstra
2010-01-05 0:25 ` KAMEZAWA Hiroyuki
2010-01-05 3:13 ` Linus Torvalds
2010-01-05 8:17 ` Peter Zijlstra
2010-01-05 8:57 ` Peter Zijlstra
2010-01-05 15:34 ` Linus Torvalds
2010-01-05 15:40 ` Al Viro
2010-01-05 16:10 ` Linus Torvalds
2010-01-06 15:41 ` Peter Zijlstra
2010-01-05 9:37 ` Peter Zijlstra
2010-01-05 23:35 ` Linus Torvalds
2010-01-05 4:29 ` Minchan Kim
2010-01-05 4:43 ` KAMEZAWA Hiroyuki
2010-01-05 5:10 ` Linus Torvalds
2010-01-05 5:30 ` KAMEZAWA Hiroyuki
2010-01-05 7:39 ` KAMEZAWA Hiroyuki
2010-01-05 15:26 ` Linus Torvalds
2010-01-05 16:14 ` Linus Torvalds
2010-01-05 17:25 ` Andi Kleen
2010-01-05 17:47 ` Christoph Lameter
2010-01-05 18:00 ` Andi Kleen
2010-01-05 17:55 ` Linus Torvalds
2010-01-05 18:13 ` Christoph Lameter
2010-01-05 18:25 ` Linus Torvalds
2010-01-05 18:46 ` Christoph Lameter
2010-01-05 18:56 ` Linus Torvalds
2010-01-05 19:15 ` Christoph Lameter
2010-01-05 19:28 ` Linus Torvalds
2010-01-05 18:55 ` Paul E. McKenney
2010-01-05 19:08 ` Linus Torvalds
2010-01-05 19:23 ` Paul E. McKenney
2010-01-05 20:29 ` Peter Zijlstra
2010-01-05 20:46 ` Linus Torvalds
2010-01-05 21:00 ` Linus Torvalds
2010-01-05 23:29 ` Paul E. McKenney
2010-01-06 0:22 ` KAMEZAWA Hiroyuki
2010-01-06 1:37 ` Linus Torvalds [this message]
2010-01-06 2:52 ` KAMEZAWA Hiroyuki
2010-01-06 3:27 ` Linus Torvalds
2010-01-06 3:56 ` KAMEZAWA Hiroyuki
2010-01-06 4:20 ` Linus Torvalds
2010-01-06 7:06 ` KAMEZAWA Hiroyuki
2010-01-06 7:49 ` Minchan Kim
2010-01-06 9:39 ` Linus Torvalds
2010-01-07 1:00 ` KAMEZAWA Hiroyuki
2010-01-08 16:53 ` Peter Zijlstra
2010-01-08 17:22 ` Linus Torvalds
2010-01-08 17:43 ` Christoph Lameter
2010-01-08 17:52 ` Linus Torvalds
2010-01-08 18:33 ` Christoph Lameter
2010-01-08 18:46 ` Andi Kleen
2010-01-08 18:56 ` Christoph Lameter
2010-01-08 19:10 ` Andi Kleen
2010-01-08 19:11 ` Linus Torvalds
2010-01-08 19:28 ` Andi Kleen
2010-01-08 19:39 ` Linus Torvalds
2010-01-08 19:42 ` Linus Torvalds
2010-01-08 21:36 ` Linus Torvalds
2010-01-08 21:46 ` Christoph Lameter
2010-01-08 22:43 ` Linus Torvalds
2010-01-08 22:43 ` Linus Torvalds
2010-01-09 14:47 ` Ed Tomlinson
2010-01-10 5:27 ` Nitin Gupta
2010-01-05 15:14 ` Christoph Lameter
2010-01-05 8:18 ` Peter Zijlstra
2010-01-05 6:00 ` Minchan Kim
2010-01-05 4:48 ` Linus Torvalds
2010-01-05 6:09 ` Minchan Kim
2010-01-05 6:09 ` KAMEZAWA Hiroyuki
2010-01-05 6:24 ` Minchan Kim
2010-01-05 8:35 ` Peter Zijlstra
2010-01-05 13:45 ` Arjan van de Ven
2010-01-05 14:15 ` Andi Kleen
2010-01-05 15:17 ` Christoph Lameter
2010-01-06 3:22 ` Arjan van de Ven
2010-01-07 16:11 ` Christoph Lameter
2010-01-07 16:19 ` Linus Torvalds
2010-01-07 16:31 ` Linus Torvalds
2010-01-07 16:34 ` Paul E. McKenney
2010-01-07 16:36 ` Christoph Lameter
2010-01-08 4:49 ` Arjan van de Ven
2010-01-08 5:00 ` Linus Torvalds
2010-01-08 15:51 ` Christoph Lameter
2010-01-09 15:55 ` Arjan van de Ven
2010-01-07 17:22 ` Peter Zijlstra
2010-01-07 17:36 ` Linus Torvalds
2010-01-07 17:49 ` Linus Torvalds
2010-01-07 18:00 ` Peter Zijlstra
2010-01-07 18:15 ` Linus Torvalds
2010-01-07 21:49 ` Peter Zijlstra
2010-01-07 18:44 ` Linus Torvalds
2010-01-07 19:20 ` Paul E. McKenney
2010-01-07 20:06 ` Linus Torvalds
2010-01-07 20:25 ` Paul E. McKenney
2010-01-07 19:24 ` Christoph Lameter
2010-01-07 20:08 ` Linus Torvalds
2010-01-07 20:13 ` Linus Torvalds
2010-01-07 21:44 ` Peter Zijlstra
2010-01-07 22:33 ` Linus Torvalds
2010-01-08 0:23 ` KAMEZAWA Hiroyuki
2010-01-08 0:25 ` KAMEZAWA Hiroyuki
2010-01-08 0:39 ` Linus Torvalds
2010-01-08 0:41 ` Linus Torvalds
2010-01-07 23:51 ` Rik van Riel
2010-01-04 18:24 ` [RFC][PATCH 7/8] mm,x86: speculative pagefault support Peter Zijlstra
2010-01-04 18:24 ` [RFC][PATCH 8/8] mm: Optimize pte_map_lock() Peter Zijlstra
2010-01-04 21:41 ` [RFC][PATCH 0/8] Speculative pagefault -v3 Rik van Riel
2010-01-04 21:46 ` Peter Zijlstra
2010-01-04 23:20 ` Rik van Riel
2010-01-04 21:59 ` Christoph Lameter
2010-01-05 0:28 ` KAMEZAWA Hiroyuki
2010-01-05 2:26 ` Minchan Kim
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=alpine.LFD.2.00.1001051718100.3630@localhost.localdomain \
--to=torvalds@linux-foundation.org \
--cc=a.p.zijlstra@chello.nl \
--cc=cl@linux-foundation.org \
--cc=hugh.dickins@tiscali.co.uk \
--cc=kamezawa.hiroyu@jp.fujitsu.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=minchan.kim@gmail.com \
--cc=mingo@elte.hu \
--cc=nickpiggin@yahoo.com.au \
--cc=paulmck@linux.vnet.ibm.com \
--cc=peterz@infradead.org \
/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;
as well as URLs for NNTP newsgroup(s).