linux-toradex.git/lib/percpu_counter.c, branch T20_LinuxImageV2.0Beta1_20121218 Linux kernel for Apalis and Colibri modules percpucounter: Optimize __percpu_counter_add a bit through the use of this_cpu() options. 2010-12-17T14:07:18+00:00 Christoph Lameter cl@linux.com 2010-12-06T17:16:19+00:00 819a72af8d6653daa48334f24ce0a935ccdd33c7 The this_cpu_* options can be used to optimize __percpu_counter_add a bit. Avoids some address arithmetic and saves 12 bytes. Before: 00000000000001d3 <__percpu_counter_add>: 1d3: 55 push %rbp 1d4: 48 89 e5 mov %rsp,%rbp 1d7: 41 55 push %r13 1d9: 41 54 push %r12 1db: 53 push %rbx 1dc: 48 89 fb mov %rdi,%rbx 1df: 48 83 ec 08 sub $0x8,%rsp 1e3: 4c 8b 67 30 mov 0x30(%rdi),%r12 1e7: 65 4c 03 24 25 00 00 add %gs:0x0,%r12 1ee: 00 00 1f0: 4d 63 2c 24 movslq (%r12),%r13 1f4: 48 63 c2 movslq %edx,%rax 1f7: 49 01 f5 add %rsi,%r13 1fa: 49 39 c5 cmp %rax,%r13 1fd: 7d 0a jge 209 <__percpu_counter_add+0x36> 1ff: f7 da neg %edx 201: 48 63 d2 movslq %edx,%rdx 204: 49 39 d5 cmp %rdx,%r13 207: 7f 1e jg 227 <__percpu_counter_add+0x54> 209: 48 89 df mov %rbx,%rdi 20c: e8 00 00 00 00 callq 211 <__percpu_counter_add+0x3e> 211: 4c 01 6b 18 add %r13,0x18(%rbx) 215: 48 89 df mov %rbx,%rdi 218: 41 c7 04 24 00 00 00 movl $0x0,(%r12) 21f: 00 220: e8 00 00 00 00 callq 225 <__percpu_counter_add+0x52> 225: eb 04 jmp 22b <__percpu_counter_add+0x58> 227: 45 89 2c 24 mov %r13d,(%r12) 22b: 5b pop %rbx 22c: 5b pop %rbx 22d: 41 5c pop %r12 22f: 41 5d pop %r13 231: c9 leaveq 232: c3 retq After: 00000000000001d3 <__percpu_counter_add>: 1d3: 55 push %rbp 1d4: 48 63 ca movslq %edx,%rcx 1d7: 48 89 e5 mov %rsp,%rbp 1da: 41 54 push %r12 1dc: 53 push %rbx 1dd: 48 89 fb mov %rdi,%rbx 1e0: 48 8b 47 30 mov 0x30(%rdi),%rax 1e4: 65 44 8b 20 mov %gs:(%rax),%r12d 1e8: 4d 63 e4 movslq %r12d,%r12 1eb: 49 01 f4 add %rsi,%r12 1ee: 49 39 cc cmp %rcx,%r12 1f1: 7d 0a jge 1fd <__percpu_counter_add+0x2a> 1f3: f7 da neg %edx 1f5: 48 63 d2 movslq %edx,%rdx 1f8: 49 39 d4 cmp %rdx,%r12 1fb: 7f 21 jg 21e <__percpu_counter_add+0x4b> 1fd: 48 89 df mov %rbx,%rdi 200: e8 00 00 00 00 callq 205 <__percpu_counter_add+0x32> 205: 4c 01 63 18 add %r12,0x18(%rbx) 209: 48 8b 43 30 mov 0x30(%rbx),%rax 20d: 48 89 df mov %rbx,%rdi 210: 65 c7 00 00 00 00 00 movl $0x0,%gs:(%rax) 217: e8 00 00 00 00 callq 21c <__percpu_counter_add+0x49> 21c: eb 04 jmp 222 <__percpu_counter_add+0x4f> 21e: 65 44 89 20 mov %r12d,%gs:(%rax) 222: 5b pop %rbx 223: 41 5c pop %r12 225: c9 leaveq 226: c3 retq Reviewed-by: Pekka Enberg <penberg@kernel.org> Reviewed-by: Tejun Heo <tj@kernel.org> Reviewed-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Acked-by: H. Peter Anvin <hpa@zytor.com> Signed-off-by: Christoph Lameter <cl@linux.com> Signed-off-by: Tejun Heo <tj@kernel.org> 
The this_cpu_* options can be used to optimize __percpu_counter_add a bit. Avoids
some address arithmetic and saves 12 bytes.

Before:


00000000000001d3 <__percpu_counter_add>:
 1d3:	55                   	push   %rbp
 1d4:	48 89 e5             	mov    %rsp,%rbp
 1d7:	41 55                	push   %r13
 1d9:	41 54                	push   %r12
 1db:	53                   	push   %rbx
 1dc:	48 89 fb             	mov    %rdi,%rbx
 1df:	48 83 ec 08          	sub    $0x8,%rsp
 1e3:	4c 8b 67 30          	mov    0x30(%rdi),%r12
 1e7:	65 4c 03 24 25 00 00 	add    %gs:0x0,%r12
 1ee:	00 00
 1f0:	4d 63 2c 24          	movslq (%r12),%r13
 1f4:	48 63 c2             	movslq %edx,%rax
 1f7:	49 01 f5             	add    %rsi,%r13
 1fa:	49 39 c5             	cmp    %rax,%r13
 1fd:	7d 0a                	jge    209 <__percpu_counter_add+0x36>
 1ff:	f7 da                	neg    %edx
 201:	48 63 d2             	movslq %edx,%rdx
 204:	49 39 d5             	cmp    %rdx,%r13
 207:	7f 1e                	jg     227 <__percpu_counter_add+0x54>
 209:	48 89 df             	mov    %rbx,%rdi
 20c:	e8 00 00 00 00       	callq  211 <__percpu_counter_add+0x3e>
 211:	4c 01 6b 18          	add    %r13,0x18(%rbx)
 215:	48 89 df             	mov    %rbx,%rdi
 218:	41 c7 04 24 00 00 00 	movl   $0x0,(%r12)
 21f:	00
 220:	e8 00 00 00 00       	callq  225 <__percpu_counter_add+0x52>
 225:	eb 04                	jmp    22b <__percpu_counter_add+0x58>
 227:	45 89 2c 24          	mov    %r13d,(%r12)
 22b:	5b                   	pop    %rbx
 22c:	5b                   	pop    %rbx
 22d:	41 5c                	pop    %r12
 22f:	41 5d                	pop    %r13
 231:	c9                   	leaveq
 232:	c3                   	retq


After:

00000000000001d3 <__percpu_counter_add>:
 1d3:	55                   	push   %rbp
 1d4:	48 63 ca             	movslq %edx,%rcx
 1d7:	48 89 e5             	mov    %rsp,%rbp
 1da:	41 54                	push   %r12
 1dc:	53                   	push   %rbx
 1dd:	48 89 fb             	mov    %rdi,%rbx
 1e0:	48 8b 47 30          	mov    0x30(%rdi),%rax
 1e4:	65 44 8b 20          	mov    %gs:(%rax),%r12d
 1e8:	4d 63 e4             	movslq %r12d,%r12
 1eb:	49 01 f4             	add    %rsi,%r12
 1ee:	49 39 cc             	cmp    %rcx,%r12
 1f1:	7d 0a                	jge    1fd <__percpu_counter_add+0x2a>
 1f3:	f7 da                	neg    %edx
 1f5:	48 63 d2             	movslq %edx,%rdx
 1f8:	49 39 d4             	cmp    %rdx,%r12
 1fb:	7f 21                	jg     21e <__percpu_counter_add+0x4b>
 1fd:	48 89 df             	mov    %rbx,%rdi
 200:	e8 00 00 00 00       	callq  205 <__percpu_counter_add+0x32>
 205:	4c 01 63 18          	add    %r12,0x18(%rbx)
 209:	48 8b 43 30          	mov    0x30(%rbx),%rax
 20d:	48 89 df             	mov    %rbx,%rdi
 210:	65 c7 00 00 00 00 00 	movl   $0x0,%gs:(%rax)
 217:	e8 00 00 00 00       	callq  21c <__percpu_counter_add+0x49>
 21c:	eb 04                	jmp    222 <__percpu_counter_add+0x4f>
 21e:	65 44 89 20          	mov    %r12d,%gs:(%rax)
 222:	5b                   	pop    %rbx
 223:	41 5c                	pop    %r12
 225:	c9                   	leaveq
 226:	c3                   	retq

Reviewed-by: Pekka Enberg <penberg@kernel.org>
Reviewed-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Acked-by: H. Peter Anvin <hpa@zytor.com>
Signed-off-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
percpu_counter: use this_cpu_ptr() instead of per_cpu_ptr() 2010-10-26T23:52:19+00:00 Christoph Lameter cl@linux.com 2010-10-26T21:23:09+00:00 ea00c30b5b31baa91be29bee966204eccc15e9d3 this_cpu_ptr() avoids an array lookup and can use the percpu offset of the local cpu directly. Signed-off-by: Christoph Lameter <cl@linux.com> Cc: Eric Dumazet <eric.dumazet@gmail.com> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> 
this_cpu_ptr() avoids an array lookup and can use the percpu offset of the
local cpu directly.

Signed-off-by: Christoph Lameter <cl@linux.com>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Tejun Heo <tj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
percpu_counter: add debugobj support 2010-10-26T23:52:18+00:00 Tejun Heo tj@kernel.org 2010-10-26T21:23:05+00:00 e2852ae825dba5ebc159788720baec1a28a57125 All percpu counters are linked to a global list on initialization and removed from it on destruction. The list is walked during CPU up/down. If a percpu counter is freed without being properly destroyed, the system will oops only on the next CPU up/down making it pretty nasty to track down. This patch adds debugobj support for percpu counters so that such problems can be found easily. As percpu counters don't make sense on stack and can't be statically initialized, debugobj support is pretty simple. It's initialized and activated on counter initialization, and deactivatd and destroyed on counter destruction. With this patch applied, the bug fixed by commit 602586a83b719df0fbd94196a1359ed35aeb2df3 (shmem: put_super must percpu_counter_destroy) triggers the following warning on tmpfs unmount and the system won't oops on the next cpu up/down operation. ------------[ cut here ]------------ WARNING: at lib/debugobjects.c:259 debug_print_object+0x5c/0x70() Hardware name: Bochs ODEBUG: free active (active state 0) object type: percpu_counter Modules linked in: Pid: 3999, comm: umount Not tainted 2.6.36-rc2-work+ #5 Call Trace: [<ffffffff81083f7f>] warn_slowpath_common+0x7f/0xc0 [<ffffffff81084076>] warn_slowpath_fmt+0x46/0x50 [<ffffffff813b45cc>] debug_print_object+0x5c/0x70 [<ffffffff813b50e5>] debug_check_no_obj_freed+0x125/0x210 [<ffffffff811577d3>] kfree+0xb3/0x2f0 [<ffffffff81132edd>] shmem_put_super+0x1d/0x30 [<ffffffff81162e96>] generic_shutdown_super+0x56/0xe0 [<ffffffff81162f86>] kill_anon_super+0x16/0x60 [<ffffffff81162ff7>] kill_litter_super+0x27/0x30 [<ffffffff81163295>] deactivate_locked_super+0x45/0x60 [<ffffffff81163cfa>] deactivate_super+0x4a/0x70 [<ffffffff8117d446>] mntput_no_expire+0x86/0xe0 [<ffffffff8117df7f>] sys_umount+0x6f/0x360 [<ffffffff8103f01b>] system_call_fastpath+0x16/0x1b ---[ end trace cce2a341ba3611a7 ]--- Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Thomas Gleixner <tglxlinutronix.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> 
All percpu counters are linked to a global list on initialization and
removed from it on destruction.  The list is walked during CPU up/down.
If a percpu counter is freed without being properly destroyed, the system
will oops only on the next CPU up/down making it pretty nasty to track
down.  This patch adds debugobj support for percpu counters so that such
problems can be found easily.

As percpu counters don't make sense on stack and can't be statically
initialized, debugobj support is pretty simple.  It's initialized and
activated on counter initialization, and deactivatd and destroyed on
counter destruction.  With this patch applied, the bug fixed by commit
602586a83b719df0fbd94196a1359ed35aeb2df3 (shmem: put_super must
percpu_counter_destroy) triggers the following warning on tmpfs unmount
and the system won't oops on the next cpu up/down operation.

 ------------[ cut here ]------------
 WARNING: at lib/debugobjects.c:259 debug_print_object+0x5c/0x70()
 Hardware name: Bochs
 ODEBUG: free active (active state 0) object type: percpu_counter
 Modules linked in:
 Pid: 3999, comm: umount Not tainted 2.6.36-rc2-work+ #5
 Call Trace:
  [<ffffffff81083f7f>] warn_slowpath_common+0x7f/0xc0
  [<ffffffff81084076>] warn_slowpath_fmt+0x46/0x50
  [<ffffffff813b45cc>] debug_print_object+0x5c/0x70
  [<ffffffff813b50e5>] debug_check_no_obj_freed+0x125/0x210
  [<ffffffff811577d3>] kfree+0xb3/0x2f0
  [<ffffffff81132edd>] shmem_put_super+0x1d/0x30
  [<ffffffff81162e96>] generic_shutdown_super+0x56/0xe0
  [<ffffffff81162f86>] kill_anon_super+0x16/0x60
  [<ffffffff81162ff7>] kill_litter_super+0x27/0x30
  [<ffffffff81163295>] deactivate_locked_super+0x45/0x60
  [<ffffffff81163cfa>] deactivate_super+0x4a/0x70
  [<ffffffff8117d446>] mntput_no_expire+0x86/0xe0
  [<ffffffff8117df7f>] sys_umount+0x6f/0x360
  [<ffffffff8103f01b>] system_call_fastpath+0x16/0x1b
 ---[ end trace cce2a341ba3611a7 ]---

Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Thomas Gleixner <tglxlinutronix.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
percpu: fix list_head init bug in __percpu_counter_init() 2010-10-26T23:52:04+00:00 Masanori ITOH itoumsn@nttdata.co.jp 2010-10-26T21:21:20+00:00 8474b591faf3bb0a1e08a60d21d6baac498f15e4 WARNING: at lib/list_debug.c:26 __list_add+0x3f/0x81() Hardware name: Express5800/B120a [N8400-085] list_add corruption. next->prev should be prev (ffffffff81a7ea00), but was dead000000200200. (next=ffff88080b872d58). Modules linked in: aoe ipt_MASQUERADE iptable_nat nf_nat autofs4 sunrpc bridge 8021q garp stp llc ipv6 cpufreq_ondemand acpi_cpufreq freq_table dm_round_robin dm_multipath kvm_intel kvm uinput lpfc scsi_transport_fc igb ioatdma scsi_tgt i2c_i801 i2c_core dca iTCO_wdt iTCO_vendor_support pcspkr shpchp megaraid_sas [last unloaded: aoe] Pid: 54, comm: events/3 Tainted: G W 2.6.34-vanilla1 #1 Call Trace: [<ffffffff8104bd77>] warn_slowpath_common+0x7c/0x94 [<ffffffff8104bde6>] warn_slowpath_fmt+0x41/0x43 [<ffffffff8120fd2e>] __list_add+0x3f/0x81 [<ffffffff81212a12>] __percpu_counter_init+0x59/0x6b [<ffffffff810d8499>] bdi_init+0x118/0x17e [<ffffffff811f2c50>] blk_alloc_queue_node+0x79/0x143 [<ffffffff811f2d2b>] blk_alloc_queue+0x11/0x13 [<ffffffffa02a931d>] aoeblk_gdalloc+0x8e/0x1c9 [aoe] [<ffffffffa02aa655>] aoecmd_sleepwork+0x25/0xa8 [aoe] [<ffffffff8106186c>] worker_thread+0x1a9/0x237 [<ffffffffa02aa630>] ? aoecmd_sleepwork+0x0/0xa8 [aoe] [<ffffffff81065827>] ? autoremove_wake_function+0x0/0x39 [<ffffffff810616c3>] ? worker_thread+0x0/0x237 [<ffffffff810653ad>] kthread+0x7f/0x87 [<ffffffff8100aa24>] kernel_thread_helper+0x4/0x10 [<ffffffff8106532e>] ? kthread+0x0/0x87 [<ffffffff8100aa20>] ? kernel_thread_helper+0x0/0x10 It's because there is no initialization code for a list_head contained in the struct backing_dev_info under CONFIG_HOTPLUG_CPU, and the bug comes up when block device drivers calling blk_alloc_queue() are used. In case of me, I got them by using aoe. Signed-off-by: Masanori Itoh <itoumsn@nttdata.co.jp> Cc: Tejun Heo <tj@kernel.org> Cc: <stable@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> 
WARNING: at lib/list_debug.c:26 __list_add+0x3f/0x81()
Hardware name: Express5800/B120a [N8400-085]
list_add corruption. next->prev should be prev (ffffffff81a7ea00), but was dead000000200200. (next=ffff88080b872d58).
Modules linked in: aoe ipt_MASQUERADE iptable_nat nf_nat autofs4 sunrpc bridge 8021q garp stp llc ipv6 cpufreq_ondemand acpi_cpufreq freq_table dm_round_robin dm_multipath kvm_intel kvm uinput lpfc scsi_transport_fc igb ioatdma scsi_tgt i2c_i801 i2c_core dca iTCO_wdt iTCO_vendor_support pcspkr shpchp megaraid_sas [last unloaded: aoe]
Pid: 54, comm: events/3 Tainted: G        W  2.6.34-vanilla1 #1
Call Trace:
[<ffffffff8104bd77>] warn_slowpath_common+0x7c/0x94
[<ffffffff8104bde6>] warn_slowpath_fmt+0x41/0x43
[<ffffffff8120fd2e>] __list_add+0x3f/0x81
[<ffffffff81212a12>] __percpu_counter_init+0x59/0x6b
[<ffffffff810d8499>] bdi_init+0x118/0x17e
[<ffffffff811f2c50>] blk_alloc_queue_node+0x79/0x143
[<ffffffff811f2d2b>] blk_alloc_queue+0x11/0x13
[<ffffffffa02a931d>] aoeblk_gdalloc+0x8e/0x1c9 [aoe]
[<ffffffffa02aa655>] aoecmd_sleepwork+0x25/0xa8 [aoe]
[<ffffffff8106186c>] worker_thread+0x1a9/0x237
[<ffffffffa02aa630>] ? aoecmd_sleepwork+0x0/0xa8 [aoe]
[<ffffffff81065827>] ? autoremove_wake_function+0x0/0x39
[<ffffffff810616c3>] ? worker_thread+0x0/0x237
[<ffffffff810653ad>] kthread+0x7f/0x87
[<ffffffff8100aa24>] kernel_thread_helper+0x4/0x10
[<ffffffff8106532e>] ? kthread+0x0/0x87
[<ffffffff8100aa20>] ? kernel_thread_helper+0x0/0x10

It's because there is no initialization code for a list_head contained in
the struct backing_dev_info under CONFIG_HOTPLUG_CPU, and the bug comes up
when block device drivers calling blk_alloc_queue() are used.  In case of
me, I got them by using aoe.

Signed-off-by: Masanori Itoh <itoumsn@nttdata.co.jp>
Cc: Tejun Heo <tj@kernel.org>
Cc: <stable@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
tmpfs: add accurate compare function to percpu_counter library 2010-08-10T03:44:58+00:00 Tim Chen tim.c.chen@linux.intel.com 2010-08-10T00:19:04+00:00 27f5e0f694fd0600274a76854636c0749e3bb1f6 Add percpu_counter_compare that allows for a quick but accurate comparison of percpu_counter with a given value. A rough count is provided by the count field in percpu_counter structure, without accounting for the other values stored in individual cpu counters. The actual count is a sum of count and the cpu counters. However, count field is never different from the actual value by a factor of batch*num_online_cpu. We do not need to get actual count for comparison if count is different from the given value by this factor and allows for quick comparison without summing up all the per cpu counters. Signed-off-by: Tim Chen <tim.c.chen@linux.intel.com> Cc: Hugh Dickins <hughd@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> 
Add percpu_counter_compare that allows for a quick but accurate comparison
of percpu_counter with a given value.

A rough count is provided by the count field in percpu_counter structure,
without accounting for the other values stored in individual cpu counters.

The actual count is a sum of count and the cpu counters.  However, count
field is never different from the actual value by a factor of
batch*num_online_cpu.  We do not need to get actual count for comparison
if count is different from the given value by this factor and allows for
quick comparison without summing up all the per cpu counters.

Signed-off-by: Tim Chen <tim.c.chen@linux.intel.com>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Merge branch 'core-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip 2009-01-07T01:10:04+00:00 Linus Torvalds torvalds@linux-foundation.org 2009-01-07T01:10:04+00:00 f94181da7192f4ed8ccb1b633ea4ce56954df130 * 'core-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: rcu: fix rcutorture bug rcu: eliminate synchronize_rcu_xxx macro rcu: make treercu safe for suspend and resume rcu: fix rcutree grace-period-latency bug on small systems futex: catch certain assymetric (get|put)_futex_key calls futex: make futex_(get|put)_key() calls symmetric locking, percpu counters: introduce separate lock classes swiotlb: clean up EXPORT_SYMBOL usage swiotlb: remove unnecessary declaration swiotlb: replace architecture-specific swiotlb.h with linux/swiotlb.h swiotlb: add support for systems with highmem swiotlb: store phys address in io_tlb_orig_addr array swiotlb: add hwdev to swiotlb_phys_to_bus() / swiotlb_sg_to_bus() 
* 'core-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
  rcu: fix rcutorture bug
  rcu: eliminate synchronize_rcu_xxx macro
  rcu: make treercu safe for suspend and resume
  rcu: fix rcutree grace-period-latency bug on small systems
  futex: catch certain assymetric (get|put)_futex_key calls
  futex: make futex_(get|put)_key() calls symmetric
  locking, percpu counters: introduce separate lock classes
  swiotlb: clean up EXPORT_SYMBOL usage
  swiotlb: remove unnecessary declaration
  swiotlb: replace architecture-specific swiotlb.h with linux/swiotlb.h
  swiotlb: add support for systems with highmem
  swiotlb: store phys address in io_tlb_orig_addr array
  swiotlb: add hwdev to swiotlb_phys_to_bus() / swiotlb_sg_to_bus()
percpu_counter: FBC_BATCH should be a variable 2009-01-06T23:59:13+00:00 Eric Dumazet dada1@cosmosbay.com 2009-01-06T22:41:04+00:00 179f7ebff6be45738c6e2fa68c8d2cc5c2c6308e For NR_CPUS >= 16 values, FBC_BATCH is 2*NR_CPUS Considering more and more distros are using high NR_CPUS values, it makes sense to use a more sensible value for FBC_BATCH, and get rid of NR_CPUS. A sensible value is 2*num_online_cpus(), with a minimum value of 32 (This minimum value helps branch prediction in __percpu_counter_add()) We already have a hotcpu notifier, so we can adjust FBC_BATCH dynamically. We rename FBC_BATCH to percpu_counter_batch since its not a constant anymore. Signed-off-by: Eric Dumazet <dada1@cosmosbay.com> Acked-by: David S. Miller <davem@davemloft.net> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> 
For NR_CPUS >= 16 values, FBC_BATCH is 2*NR_CPUS

Considering more and more distros are using high NR_CPUS values, it makes
sense to use a more sensible value for FBC_BATCH, and get rid of NR_CPUS.

A sensible value is 2*num_online_cpus(), with a minimum value of 32 (This
minimum value helps branch prediction in __percpu_counter_add())

We already have a hotcpu notifier, so we can adjust FBC_BATCH dynamically.

We rename FBC_BATCH to percpu_counter_batch since its not a constant
anymore.

Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Acked-by: David S. Miller <davem@davemloft.net>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Merge branches 'core/futexes', 'core/locking', 'core/rcu' and 'linus' into core/urgent 2009-01-06T08:32:11+00:00 Ingo Molnar mingo@elte.hu 2009-01-06T08:32:11+00:00 fdbc0450df12cc9cb397f3497db4b0cad7c1a8ff 






locking, percpu counters: introduce separate lock classes
2008-12-29T12:43:00+00:00

Peter Zijlstra
a.p.zijlstra@chello.nl

2008-12-26T14:08:55+00:00

ea319518ba3de282c13ae1cf4bf2215c5e03e67e

Impact: fix lockdep false positives

Classify percpu_counter instances similar to regular lock objects --
that is, per instantiation site.

The networking code has increased its use of percpu_counters, which
leads to false positives if they are treated as a single class.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>





Impact: fix lockdep false positives

Classify percpu_counter instances similar to regular lock objects --
that is, per instantiation site.

The networking code has increased its use of percpu_counters, which
leads to false positives if they are treated as a single class.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>







revert "percpu_counter: new function percpu_counter_sum_and_set"
2008-12-10T16:01:52+00:00

Andrew Morton
akpm@linux-foundation.org

2008-12-09T21:14:14+00:00

02d211688727ad02bb4555b1aa8ae2de16b21b39

Revert

    commit e8ced39d5e8911c662d4d69a342b9d053eaaac4e
    Author: Mingming Cao <cmm@us.ibm.com>
    Date:   Fri Jul 11 19:27:31 2008 -0400

        percpu_counter: new function percpu_counter_sum_and_set

As described in

	revert "percpu counter: clean up percpu_counter_sum_and_set()"

the new percpu_counter_sum_and_set() is racy against updates to the
cpu-local accumulators on other CPUs.  Revert that change.

This means that ext4 will be slow again.  But correct.

Reported-by: Eric Dumazet <dada1@cosmosbay.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Mingming Cao <cmm@us.ibm.com>
Cc: <linux-ext4@vger.kernel.org>
Cc: <stable@kernel.org>		[2.6.27.x]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>





Revert

    commit e8ced39d5e8911c662d4d69a342b9d053eaaac4e
    Author: Mingming Cao <cmm@us.ibm.com>
    Date:   Fri Jul 11 19:27:31 2008 -0400

        percpu_counter: new function percpu_counter_sum_and_set

As described in

	revert "percpu counter: clean up percpu_counter_sum_and_set()"

the new percpu_counter_sum_and_set() is racy against updates to the
cpu-local accumulators on other CPUs.  Revert that change.

This means that ext4 will be slow again.  But correct.

Reported-by: Eric Dumazet <dada1@cosmosbay.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Mingming Cao <cmm@us.ibm.com>
Cc: <linux-ext4@vger.kernel.org>
Cc: <stable@kernel.org>		[2.6.27.x]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>