The patch titled
Subject: this_cpu_cmpxchg: x86: switch this_cpu_cmpxchg to locked, add _local function
has been added to the -mm mm-unstable branch. Its filename is
this_cpu_cmpxchg-x86-switch-this_cpu_cmpxchg-to-locked-add-_local-function.patch
This patch will shortly appear at
https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/this_cpu_cmpxchg-x86-switch-this_cpu_cmpxchg-to-locked-add-_local-function.patch
This patch will later appear in the mm-unstable branch at
git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next via the mm-everything
branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
and is updated there every 2-3 working days
------------------------------------------------------
From: Marcelo Tosatti <mtosatti@xxxxxxxxxx>
Subject: this_cpu_cmpxchg: x86: switch this_cpu_cmpxchg to locked, add _local function
Date: Mon, 13 Mar 2023 13:25:11 -0300
Goal is to have vmstat_shepherd to transfer from per-CPU counters to
global counters remotely. For this, an atomic this_cpu_cmpxchg is
necessary.
Following the kernel convention for cmpxchg/cmpxchg_local, change x86's
this_cpu_cmpxchg_ helpers to be atomic. and add this_cpu_cmpxchg_local_
helpers which are not atomic.
Link: https://lkml.kernel.org/r/20230313162634.359258017@xxxxxxxxxx
Signed-off-by: Marcelo Tosatti <mtosatti@xxxxxxxxxx>
Cc: Aaron Tomlin <atomlin@xxxxxxxxxxx>
Cc: Christian König <christian.koenig@xxxxxxx>
Cc: Christoph Lameter <cl@xxxxxxxxx>
Cc: Dan Williams <dan.j.williams@xxxxxxxxx>
Cc: Frederic Weisbecker <frederic@xxxxxxxxxx>
Cc: Heiko Carstens <hca@xxxxxxxxxxxxx>
Cc: Huacai Chen <chenhuacai@xxxxxxxxxx>
Cc: Jason Gunthorpe <jgg@xxxxxxxx>
Cc: Kirill A. Shutemov <kirill.shutemov@xxxxxxxxxxxxxxx>
Cc: Lorenzo Stoakes <lstoakes@xxxxxxxxx>
Cc: Matthew Wilcox (Oracle) <willy@xxxxxxxxxxxxx>
Cc: Michal Hocko <mhocko@xxxxxxxx>
Cc: Peter Xu <peterx@xxxxxxxxxx>
Cc: "Russell King (Oracle)" <linux@xxxxxxxxxxxxxxx>
Cc: Thomas Hellström <thomas.hellstrom@xxxxxxxxxxxxxxx>
Cc: Vlastimil Babka <vbabka@xxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
--- a/arch/x86/include/asm/percpu.h~this_cpu_cmpxchg-x86-switch-this_cpu_cmpxchg-to-locked-add-_local-function
+++ a/arch/x86/include/asm/percpu.h
@@ -197,11 +197,11 @@ do { \
* cmpxchg has no such implied lock semantics as a result it is much
* more efficient for cpu local operations.
*/
-#define percpu_cmpxchg_op(size, qual, _var, _oval, _nval) \
+#define percpu_cmpxchg_op(size, qual, _var, _oval, _nval, lockp) \
({ \
__pcpu_type_##size pco_old__ = __pcpu_cast_##size(_oval); \
__pcpu_type_##size pco_new__ = __pcpu_cast_##size(_nval); \
- asm qual (__pcpu_op2_##size("cmpxchg", "%[nval]", \
+ asm qual (__pcpu_op2_##size(lockp "cmpxchg", "%[nval]", \
__percpu_arg([var])) \
: [oval] "+a" (pco_old__), \
[var] "+m" (_var) \
@@ -279,16 +279,20 @@ do { \
#define raw_cpu_add_return_1(pcp, val) percpu_add_return_op(1, , pcp, val)
#define raw_cpu_add_return_2(pcp, val) percpu_add_return_op(2, , pcp, val)
#define raw_cpu_add_return_4(pcp, val) percpu_add_return_op(4, , pcp, val)
-#define raw_cpu_cmpxchg_1(pcp, oval, nval) percpu_cmpxchg_op(1, , pcp, oval, nval)
-#define raw_cpu_cmpxchg_2(pcp, oval, nval) percpu_cmpxchg_op(2, , pcp, oval, nval)
-#define raw_cpu_cmpxchg_4(pcp, oval, nval) percpu_cmpxchg_op(4, , pcp, oval, nval)
+#define raw_cpu_cmpxchg_1(pcp, oval, nval) percpu_cmpxchg_op(1, , pcp, oval, nval, "")
+#define raw_cpu_cmpxchg_2(pcp, oval, nval) percpu_cmpxchg_op(2, , pcp, oval, nval, "")
+#define raw_cpu_cmpxchg_4(pcp, oval, nval) percpu_cmpxchg_op(4, , pcp, oval, nval, "")
#define this_cpu_add_return_1(pcp, val) percpu_add_return_op(1, volatile, pcp, val)
#define this_cpu_add_return_2(pcp, val) percpu_add_return_op(2, volatile, pcp, val)
#define this_cpu_add_return_4(pcp, val) percpu_add_return_op(4, volatile, pcp, val)
-#define this_cpu_cmpxchg_1(pcp, oval, nval) percpu_cmpxchg_op(1, volatile, pcp, oval, nval)
-#define this_cpu_cmpxchg_2(pcp, oval, nval) percpu_cmpxchg_op(2, volatile, pcp, oval, nval)
-#define this_cpu_cmpxchg_4(pcp, oval, nval) percpu_cmpxchg_op(4, volatile, pcp, oval, nval)
+#define this_cpu_cmpxchg_local_1(pcp, oval, nval) percpu_cmpxchg_op(1, volatile, pcp, oval, nval, "")
+#define this_cpu_cmpxchg_local_2(pcp, oval, nval) percpu_cmpxchg_op(2, volatile, pcp, oval, nval, "")
+#define this_cpu_cmpxchg_local_4(pcp, oval, nval) percpu_cmpxchg_op(4, volatile, pcp, oval, nval, "")
+
+#define this_cpu_cmpxchg_1(pcp, oval, nval) percpu_cmpxchg_op(1, volatile, pcp, oval, nval, LOCK_PREFIX)
+#define this_cpu_cmpxchg_2(pcp, oval, nval) percpu_cmpxchg_op(2, volatile, pcp, oval, nval, LOCK_PREFIX)
+#define this_cpu_cmpxchg_4(pcp, oval, nval) percpu_cmpxchg_op(4, volatile, pcp, oval, nval, LOCK_PREFIX)
#ifdef CONFIG_X86_CMPXCHG64
#define percpu_cmpxchg8b_double(pcp1, pcp2, o1, o2, n1, n2) \
@@ -319,16 +323,17 @@ do { \
#define raw_cpu_or_8(pcp, val) percpu_to_op(8, , "or", (pcp), val)
#define raw_cpu_add_return_8(pcp, val) percpu_add_return_op(8, , pcp, val)
#define raw_cpu_xchg_8(pcp, nval) raw_percpu_xchg_op(pcp, nval)
-#define raw_cpu_cmpxchg_8(pcp, oval, nval) percpu_cmpxchg_op(8, , pcp, oval, nval)
+#define raw_cpu_cmpxchg_8(pcp, oval, nval) percpu_cmpxchg_op(8, , pcp, oval, nval, "")
-#define this_cpu_read_8(pcp) percpu_from_op(8, volatile, "mov", pcp)
-#define this_cpu_write_8(pcp, val) percpu_to_op(8, volatile, "mov", (pcp), val)
-#define this_cpu_add_8(pcp, val) percpu_add_op(8, volatile, (pcp), val)
-#define this_cpu_and_8(pcp, val) percpu_to_op(8, volatile, "and", (pcp), val)
-#define this_cpu_or_8(pcp, val) percpu_to_op(8, volatile, "or", (pcp), val)
-#define this_cpu_add_return_8(pcp, val) percpu_add_return_op(8, volatile, pcp, val)
-#define this_cpu_xchg_8(pcp, nval) percpu_xchg_op(8, volatile, pcp, nval)
-#define this_cpu_cmpxchg_8(pcp, oval, nval) percpu_cmpxchg_op(8, volatile, pcp, oval, nval)
+#define this_cpu_read_8(pcp) percpu_from_op(8, volatile, "mov", pcp)
+#define this_cpu_write_8(pcp, val) percpu_to_op(8, volatile, "mov", (pcp), val)
+#define this_cpu_add_8(pcp, val) percpu_add_op(8, volatile, (pcp), val)
+#define this_cpu_and_8(pcp, val) percpu_to_op(8, volatile, "and", (pcp), val)
+#define this_cpu_or_8(pcp, val) percpu_to_op(8, volatile, "or", (pcp), val)
+#define this_cpu_add_return_8(pcp, val) percpu_add_return_op(8, volatile, pcp, val)
+#define this_cpu_xchg_8(pcp, nval) percpu_xchg_op(8, volatile, pcp, nval)
+#define this_cpu_cmpxchg_local_8(pcp, oval, nval) percpu_cmpxchg_op(8, volatile, pcp, oval, nval, "")
+#define this_cpu_cmpxchg_8(pcp, oval, nval) percpu_cmpxchg_op(8, volatile, pcp, oval, nval, LOCK_PREFIX)
/*
* Pretty complex macro to generate cmpxchg16 instruction. The instruction
_
Patches currently in -mm which might be from mtosatti@xxxxxxxxxx are
this_cpu_cmpxchg-arm64-switch-this_cpu_cmpxchg-to-locked-add-_local-function.patch
this_cpu_cmpxchg-loongarch-switch-this_cpu_cmpxchg-to-locked-add-_local-function.patch
this_cpu_cmpxchg-s390-switch-this_cpu_cmpxchg-to-locked-add-_local-function.patch
this_cpu_cmpxchg-x86-switch-this_cpu_cmpxchg-to-locked-add-_local-function.patch
add-this_cpu_cmpxchg_local-and-asm-generic-definitions.patch
convert-this_cpu_cmpxchg-users-to-this_cpu_cmpxchg_local.patch
mm-vmstat-switch-counter-modification-to-cmpxchg.patch
vmstat-switch-per-cpu-vmstat-counters-to-32-bits.patch
mm-vmstat-use-xchg-in-cpu_vm_stats_fold.patch
mm-vmstat-switch-vmstat-shepherd-to-flush-per-cpu-counters-remotely.patch
mm-vmstat-refresh-stats-remotely-instead-of-via-work-item.patch
vmstat-add-pcp-remote-node-draining-via-cpu_vm_stats_fold.patch
