linux/block/blk-softirq.c

187 lines
4.4 KiB
C
Raw Normal View History

/*
* Functions related to softirq rq completions
*/
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/init.h>
#include <linux/bio.h>
#include <linux/blkdev.h>
#include <linux/interrupt.h>
#include <linux/cpu.h>
#include <linux/sched.h>
#include "blk.h"
static DEFINE_PER_CPU(struct list_head, blk_cpu_done);
/*
* Softirq action handler - move entries to local list and loop over them
* while passing them to the queue registered handler.
*/
static void blk_done_softirq(struct softirq_action *h)
{
struct list_head *cpu_list, local_list;
local_irq_disable();
block: Replace __get_cpu_var uses __get_cpu_var() is used for multiple purposes in the kernel source. One of them is address calculation via the form &__get_cpu_var(x). This calculates the address for the instance of the percpu variable of the current processor based on an offset. Other use cases are for storing and retrieving data from the current processors percpu area. __get_cpu_var() can be used as an lvalue when writing data or on the right side of an assignment. __get_cpu_var() is defined as : #define __get_cpu_var(var) (*this_cpu_ptr(&(var))) __get_cpu_var() always only does an address determination. However, store and retrieve operations could use a segment prefix (or global register on other platforms) to avoid the address calculation. this_cpu_write() and this_cpu_read() can directly take an offset into a percpu area and use optimized assembly code to read and write per cpu variables. This patch converts __get_cpu_var into either an explicit address calculation using this_cpu_ptr() or into a use of this_cpu operations that use the offset. Thereby address calculations are avoided and less registers are used when code is generated. At the end of the patch set all uses of __get_cpu_var have been removed so the macro is removed too. The patch set includes passes over all arches as well. Once these operations are used throughout then specialized macros can be defined in non -x86 arches as well in order to optimize per cpu access by f.e. using a global register that may be set to the per cpu base. Transformations done to __get_cpu_var() 1. Determine the address of the percpu instance of the current processor. DEFINE_PER_CPU(int, y); int *x = &__get_cpu_var(y); Converts to int *x = this_cpu_ptr(&y); 2. Same as #1 but this time an array structure is involved. DEFINE_PER_CPU(int, y[20]); int *x = __get_cpu_var(y); Converts to int *x = this_cpu_ptr(y); 3. Retrieve the content of the current processors instance of a per cpu variable. DEFINE_PER_CPU(int, y); int x = __get_cpu_var(y) Converts to int x = __this_cpu_read(y); 4. Retrieve the content of a percpu struct DEFINE_PER_CPU(struct mystruct, y); struct mystruct x = __get_cpu_var(y); Converts to memcpy(&x, this_cpu_ptr(&y), sizeof(x)); 5. Assignment to a per cpu variable DEFINE_PER_CPU(int, y) __get_cpu_var(y) = x; Converts to this_cpu_write(y, x); 6. Increment/Decrement etc of a per cpu variable DEFINE_PER_CPU(int, y); __get_cpu_var(y)++ Converts to this_cpu_inc(y) Signed-off-by: Christoph Lameter <cl@linux.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2013-10-15 20:22:29 +02:00
cpu_list = this_cpu_ptr(&blk_cpu_done);
list_replace_init(cpu_list, &local_list);
local_irq_enable();
while (!list_empty(&local_list)) {
struct request *rq;
block: fix regression with block enabled tagging Martin reported that his test system would not boot with current git, it oopsed with this: BUG: unable to handle kernel paging request at ffff88046c6c9e80 IP: [<ffffffff812971e0>] blk_queue_start_tag+0x90/0x150 PGD 1ddf067 PUD 1de2067 PMD 47fc7d067 PTE 800000046c6c9060 Oops: 0002 [#1] SMP DEBUG_PAGEALLOC Modules linked in: sd_mod lpfc(+) scsi_transport_fc scsi_tgt oracleasm rpcsec_gss_krb5 ipv6 igb dca i2c_algo_bit i2c_core hwmon CPU: 3 PID: 87 Comm: kworker/u17:1 Not tainted 3.14.0+ #246 Hardware name: Supermicro X9DRX+-F/X9DRX+-F, BIOS 3.00 07/09/2013 Workqueue: events_unbound async_run_entry_fn task: ffff8802743c2150 ti: ffff880273d02000 task.ti: ffff880273d02000 RIP: 0010:[<ffffffff812971e0>] [<ffffffff812971e0>] blk_queue_start_tag+0x90/0x150 RSP: 0018:ffff880273d03a58 EFLAGS: 00010092 RAX: ffff88046c6c9e78 RBX: ffff880077208e78 RCX: 00000000fffc8da6 RDX: 00000000fffc186d RSI: 0000000000000009 RDI: 00000000fffc8d9d RBP: ffff880273d03a88 R08: 0000000000000001 R09: ffff8800021c2410 R10: 0000000000000005 R11: 0000000000015b30 R12: ffff88046c5bb8a0 R13: ffff88046c5c0890 R14: 000000000000001e R15: 000000000000001e FS: 0000000000000000(0000) GS:ffff880277b00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: ffff88046c6c9e80 CR3: 00000000018f6000 CR4: 00000000000407e0 Stack: ffff880273d03a98 ffff880474b18800 0000000000000000 ffff880474157000 ffff88046c5c0890 ffff880077208e78 ffff880273d03ae8 ffffffff813b9e62 ffff880200000010 ffff880474b18968 ffff880474b18848 ffff88046c5c0cd8 Call Trace: [<ffffffff813b9e62>] scsi_request_fn+0xf2/0x510 [<ffffffff81293167>] __blk_run_queue+0x37/0x50 [<ffffffff8129ac43>] blk_execute_rq_nowait+0xb3/0x130 [<ffffffff8129ad24>] blk_execute_rq+0x64/0xf0 [<ffffffff8108d2b0>] ? bit_waitqueue+0xd0/0xd0 [<ffffffff813bba35>] scsi_execute+0xe5/0x180 [<ffffffff813bbe4a>] scsi_execute_req_flags+0x9a/0x110 [<ffffffffa01b1304>] sd_spinup_disk+0x94/0x460 [sd_mod] [<ffffffff81160000>] ? __unmap_hugepage_range+0x200/0x2f0 [<ffffffffa01b2b9a>] sd_revalidate_disk+0xaa/0x3f0 [sd_mod] [<ffffffffa01b2fb8>] sd_probe_async+0xd8/0x200 [sd_mod] [<ffffffff8107703f>] async_run_entry_fn+0x3f/0x140 [<ffffffff8106a1c5>] process_one_work+0x175/0x410 [<ffffffff8106b373>] worker_thread+0x123/0x400 [<ffffffff8106b250>] ? manage_workers+0x160/0x160 [<ffffffff8107104e>] kthread+0xce/0xf0 [<ffffffff81070f80>] ? kthread_freezable_should_stop+0x70/0x70 [<ffffffff815f0bac>] ret_from_fork+0x7c/0xb0 [<ffffffff81070f80>] ? kthread_freezable_should_stop+0x70/0x70 Code: 48 0f ab 11 72 db 48 81 4b 40 00 00 10 00 89 83 08 01 00 00 48 89 df 49 8b 04 24 48 89 1c d0 e8 f7 a8 ff ff 49 8b 85 28 05 00 00 <48> 89 58 08 48 89 03 49 8d 85 28 05 00 00 48 89 43 08 49 89 9d RIP [<ffffffff812971e0>] blk_queue_start_tag+0x90/0x150 RSP <ffff880273d03a58> CR2: ffff88046c6c9e80 Martin bisected and found this to be the problem patch; commit 6d113398dcf4dfcd9787a4ead738b186f7b7ff0f Author: Jan Kara <jack@suse.cz> Date: Mon Feb 24 16:39:54 2014 +0100 block: Stop abusing rq->csd.list in blk-softirq and the problem was immediately apparent. The patch states that it is safe to reuse queuelist at completion time, since it is no longer used. However, that is not true if a device is using block enabled tagging. If that is the case, then the queuelist is reused to keep track of busy tags. If a device also ended up using softirq completions, we'd reuse ->queuelist for the IPI handling while block tagging was still using it. Boom. Fix this by adding a new ipi_list list head, and share the memory used with the request hash table. The hash table is never used after the request is moved to the dispatch list, which happens long before any potential completion of the request. Add a new request bit for this, so we don't have cases that check rq->hash while it could potentially have been reused for the IPI completion. Reported-by: Martin K. Petersen <martin.petersen@oracle.com> Tested-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Jens Axboe <axboe@fb.com>
2014-04-10 04:27:01 +02:00
rq = list_entry(local_list.next, struct request, ipi_list);
list_del_init(&rq->ipi_list);
rq->q->softirq_done_fn(rq);
}
}
#ifdef CONFIG_SMP
static void trigger_softirq(void *data)
{
struct request *rq = data;
unsigned long flags;
struct list_head *list;
local_irq_save(flags);
block: Replace __get_cpu_var uses __get_cpu_var() is used for multiple purposes in the kernel source. One of them is address calculation via the form &__get_cpu_var(x). This calculates the address for the instance of the percpu variable of the current processor based on an offset. Other use cases are for storing and retrieving data from the current processors percpu area. __get_cpu_var() can be used as an lvalue when writing data or on the right side of an assignment. __get_cpu_var() is defined as : #define __get_cpu_var(var) (*this_cpu_ptr(&(var))) __get_cpu_var() always only does an address determination. However, store and retrieve operations could use a segment prefix (or global register on other platforms) to avoid the address calculation. this_cpu_write() and this_cpu_read() can directly take an offset into a percpu area and use optimized assembly code to read and write per cpu variables. This patch converts __get_cpu_var into either an explicit address calculation using this_cpu_ptr() or into a use of this_cpu operations that use the offset. Thereby address calculations are avoided and less registers are used when code is generated. At the end of the patch set all uses of __get_cpu_var have been removed so the macro is removed too. The patch set includes passes over all arches as well. Once these operations are used throughout then specialized macros can be defined in non -x86 arches as well in order to optimize per cpu access by f.e. using a global register that may be set to the per cpu base. Transformations done to __get_cpu_var() 1. Determine the address of the percpu instance of the current processor. DEFINE_PER_CPU(int, y); int *x = &__get_cpu_var(y); Converts to int *x = this_cpu_ptr(&y); 2. Same as #1 but this time an array structure is involved. DEFINE_PER_CPU(int, y[20]); int *x = __get_cpu_var(y); Converts to int *x = this_cpu_ptr(y); 3. Retrieve the content of the current processors instance of a per cpu variable. DEFINE_PER_CPU(int, y); int x = __get_cpu_var(y) Converts to int x = __this_cpu_read(y); 4. Retrieve the content of a percpu struct DEFINE_PER_CPU(struct mystruct, y); struct mystruct x = __get_cpu_var(y); Converts to memcpy(&x, this_cpu_ptr(&y), sizeof(x)); 5. Assignment to a per cpu variable DEFINE_PER_CPU(int, y) __get_cpu_var(y) = x; Converts to this_cpu_write(y, x); 6. Increment/Decrement etc of a per cpu variable DEFINE_PER_CPU(int, y); __get_cpu_var(y)++ Converts to this_cpu_inc(y) Signed-off-by: Christoph Lameter <cl@linux.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2013-10-15 20:22:29 +02:00
list = this_cpu_ptr(&blk_cpu_done);
block: fix regression with block enabled tagging Martin reported that his test system would not boot with current git, it oopsed with this: BUG: unable to handle kernel paging request at ffff88046c6c9e80 IP: [<ffffffff812971e0>] blk_queue_start_tag+0x90/0x150 PGD 1ddf067 PUD 1de2067 PMD 47fc7d067 PTE 800000046c6c9060 Oops: 0002 [#1] SMP DEBUG_PAGEALLOC Modules linked in: sd_mod lpfc(+) scsi_transport_fc scsi_tgt oracleasm rpcsec_gss_krb5 ipv6 igb dca i2c_algo_bit i2c_core hwmon CPU: 3 PID: 87 Comm: kworker/u17:1 Not tainted 3.14.0+ #246 Hardware name: Supermicro X9DRX+-F/X9DRX+-F, BIOS 3.00 07/09/2013 Workqueue: events_unbound async_run_entry_fn task: ffff8802743c2150 ti: ffff880273d02000 task.ti: ffff880273d02000 RIP: 0010:[<ffffffff812971e0>] [<ffffffff812971e0>] blk_queue_start_tag+0x90/0x150 RSP: 0018:ffff880273d03a58 EFLAGS: 00010092 RAX: ffff88046c6c9e78 RBX: ffff880077208e78 RCX: 00000000fffc8da6 RDX: 00000000fffc186d RSI: 0000000000000009 RDI: 00000000fffc8d9d RBP: ffff880273d03a88 R08: 0000000000000001 R09: ffff8800021c2410 R10: 0000000000000005 R11: 0000000000015b30 R12: ffff88046c5bb8a0 R13: ffff88046c5c0890 R14: 000000000000001e R15: 000000000000001e FS: 0000000000000000(0000) GS:ffff880277b00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: ffff88046c6c9e80 CR3: 00000000018f6000 CR4: 00000000000407e0 Stack: ffff880273d03a98 ffff880474b18800 0000000000000000 ffff880474157000 ffff88046c5c0890 ffff880077208e78 ffff880273d03ae8 ffffffff813b9e62 ffff880200000010 ffff880474b18968 ffff880474b18848 ffff88046c5c0cd8 Call Trace: [<ffffffff813b9e62>] scsi_request_fn+0xf2/0x510 [<ffffffff81293167>] __blk_run_queue+0x37/0x50 [<ffffffff8129ac43>] blk_execute_rq_nowait+0xb3/0x130 [<ffffffff8129ad24>] blk_execute_rq+0x64/0xf0 [<ffffffff8108d2b0>] ? bit_waitqueue+0xd0/0xd0 [<ffffffff813bba35>] scsi_execute+0xe5/0x180 [<ffffffff813bbe4a>] scsi_execute_req_flags+0x9a/0x110 [<ffffffffa01b1304>] sd_spinup_disk+0x94/0x460 [sd_mod] [<ffffffff81160000>] ? __unmap_hugepage_range+0x200/0x2f0 [<ffffffffa01b2b9a>] sd_revalidate_disk+0xaa/0x3f0 [sd_mod] [<ffffffffa01b2fb8>] sd_probe_async+0xd8/0x200 [sd_mod] [<ffffffff8107703f>] async_run_entry_fn+0x3f/0x140 [<ffffffff8106a1c5>] process_one_work+0x175/0x410 [<ffffffff8106b373>] worker_thread+0x123/0x400 [<ffffffff8106b250>] ? manage_workers+0x160/0x160 [<ffffffff8107104e>] kthread+0xce/0xf0 [<ffffffff81070f80>] ? kthread_freezable_should_stop+0x70/0x70 [<ffffffff815f0bac>] ret_from_fork+0x7c/0xb0 [<ffffffff81070f80>] ? kthread_freezable_should_stop+0x70/0x70 Code: 48 0f ab 11 72 db 48 81 4b 40 00 00 10 00 89 83 08 01 00 00 48 89 df 49 8b 04 24 48 89 1c d0 e8 f7 a8 ff ff 49 8b 85 28 05 00 00 <48> 89 58 08 48 89 03 49 8d 85 28 05 00 00 48 89 43 08 49 89 9d RIP [<ffffffff812971e0>] blk_queue_start_tag+0x90/0x150 RSP <ffff880273d03a58> CR2: ffff88046c6c9e80 Martin bisected and found this to be the problem patch; commit 6d113398dcf4dfcd9787a4ead738b186f7b7ff0f Author: Jan Kara <jack@suse.cz> Date: Mon Feb 24 16:39:54 2014 +0100 block: Stop abusing rq->csd.list in blk-softirq and the problem was immediately apparent. The patch states that it is safe to reuse queuelist at completion time, since it is no longer used. However, that is not true if a device is using block enabled tagging. If that is the case, then the queuelist is reused to keep track of busy tags. If a device also ended up using softirq completions, we'd reuse ->queuelist for the IPI handling while block tagging was still using it. Boom. Fix this by adding a new ipi_list list head, and share the memory used with the request hash table. The hash table is never used after the request is moved to the dispatch list, which happens long before any potential completion of the request. Add a new request bit for this, so we don't have cases that check rq->hash while it could potentially have been reused for the IPI completion. Reported-by: Martin K. Petersen <martin.petersen@oracle.com> Tested-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Jens Axboe <axboe@fb.com>
2014-04-10 04:27:01 +02:00
list_add_tail(&rq->ipi_list, list);
block: fix regression with block enabled tagging Martin reported that his test system would not boot with current git, it oopsed with this: BUG: unable to handle kernel paging request at ffff88046c6c9e80 IP: [<ffffffff812971e0>] blk_queue_start_tag+0x90/0x150 PGD 1ddf067 PUD 1de2067 PMD 47fc7d067 PTE 800000046c6c9060 Oops: 0002 [#1] SMP DEBUG_PAGEALLOC Modules linked in: sd_mod lpfc(+) scsi_transport_fc scsi_tgt oracleasm rpcsec_gss_krb5 ipv6 igb dca i2c_algo_bit i2c_core hwmon CPU: 3 PID: 87 Comm: kworker/u17:1 Not tainted 3.14.0+ #246 Hardware name: Supermicro X9DRX+-F/X9DRX+-F, BIOS 3.00 07/09/2013 Workqueue: events_unbound async_run_entry_fn task: ffff8802743c2150 ti: ffff880273d02000 task.ti: ffff880273d02000 RIP: 0010:[<ffffffff812971e0>] [<ffffffff812971e0>] blk_queue_start_tag+0x90/0x150 RSP: 0018:ffff880273d03a58 EFLAGS: 00010092 RAX: ffff88046c6c9e78 RBX: ffff880077208e78 RCX: 00000000fffc8da6 RDX: 00000000fffc186d RSI: 0000000000000009 RDI: 00000000fffc8d9d RBP: ffff880273d03a88 R08: 0000000000000001 R09: ffff8800021c2410 R10: 0000000000000005 R11: 0000000000015b30 R12: ffff88046c5bb8a0 R13: ffff88046c5c0890 R14: 000000000000001e R15: 000000000000001e FS: 0000000000000000(0000) GS:ffff880277b00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: ffff88046c6c9e80 CR3: 00000000018f6000 CR4: 00000000000407e0 Stack: ffff880273d03a98 ffff880474b18800 0000000000000000 ffff880474157000 ffff88046c5c0890 ffff880077208e78 ffff880273d03ae8 ffffffff813b9e62 ffff880200000010 ffff880474b18968 ffff880474b18848 ffff88046c5c0cd8 Call Trace: [<ffffffff813b9e62>] scsi_request_fn+0xf2/0x510 [<ffffffff81293167>] __blk_run_queue+0x37/0x50 [<ffffffff8129ac43>] blk_execute_rq_nowait+0xb3/0x130 [<ffffffff8129ad24>] blk_execute_rq+0x64/0xf0 [<ffffffff8108d2b0>] ? bit_waitqueue+0xd0/0xd0 [<ffffffff813bba35>] scsi_execute+0xe5/0x180 [<ffffffff813bbe4a>] scsi_execute_req_flags+0x9a/0x110 [<ffffffffa01b1304>] sd_spinup_disk+0x94/0x460 [sd_mod] [<ffffffff81160000>] ? __unmap_hugepage_range+0x200/0x2f0 [<ffffffffa01b2b9a>] sd_revalidate_disk+0xaa/0x3f0 [sd_mod] [<ffffffffa01b2fb8>] sd_probe_async+0xd8/0x200 [sd_mod] [<ffffffff8107703f>] async_run_entry_fn+0x3f/0x140 [<ffffffff8106a1c5>] process_one_work+0x175/0x410 [<ffffffff8106b373>] worker_thread+0x123/0x400 [<ffffffff8106b250>] ? manage_workers+0x160/0x160 [<ffffffff8107104e>] kthread+0xce/0xf0 [<ffffffff81070f80>] ? kthread_freezable_should_stop+0x70/0x70 [<ffffffff815f0bac>] ret_from_fork+0x7c/0xb0 [<ffffffff81070f80>] ? kthread_freezable_should_stop+0x70/0x70 Code: 48 0f ab 11 72 db 48 81 4b 40 00 00 10 00 89 83 08 01 00 00 48 89 df 49 8b 04 24 48 89 1c d0 e8 f7 a8 ff ff 49 8b 85 28 05 00 00 <48> 89 58 08 48 89 03 49 8d 85 28 05 00 00 48 89 43 08 49 89 9d RIP [<ffffffff812971e0>] blk_queue_start_tag+0x90/0x150 RSP <ffff880273d03a58> CR2: ffff88046c6c9e80 Martin bisected and found this to be the problem patch; commit 6d113398dcf4dfcd9787a4ead738b186f7b7ff0f Author: Jan Kara <jack@suse.cz> Date: Mon Feb 24 16:39:54 2014 +0100 block: Stop abusing rq->csd.list in blk-softirq and the problem was immediately apparent. The patch states that it is safe to reuse queuelist at completion time, since it is no longer used. However, that is not true if a device is using block enabled tagging. If that is the case, then the queuelist is reused to keep track of busy tags. If a device also ended up using softirq completions, we'd reuse ->queuelist for the IPI handling while block tagging was still using it. Boom. Fix this by adding a new ipi_list list head, and share the memory used with the request hash table. The hash table is never used after the request is moved to the dispatch list, which happens long before any potential completion of the request. Add a new request bit for this, so we don't have cases that check rq->hash while it could potentially have been reused for the IPI completion. Reported-by: Martin K. Petersen <martin.petersen@oracle.com> Tested-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Jens Axboe <axboe@fb.com>
2014-04-10 04:27:01 +02:00
if (list->next == &rq->ipi_list)
raise_softirq_irqoff(BLOCK_SOFTIRQ);
local_irq_restore(flags);
}
/*
* Setup and invoke a run of 'trigger_softirq' on the given cpu.
*/
static int raise_blk_irq(int cpu, struct request *rq)
{
if (cpu_online(cpu)) {
struct call_single_data *data = &rq->csd;
data->func = trigger_softirq;
data->info = rq;
data->flags = 0;
smp_call_function_single_async(cpu, data);
return 0;
}
return 1;
}
#else /* CONFIG_SMP */
static int raise_blk_irq(int cpu, struct request *rq)
{
return 1;
}
#endif
static int blk_cpu_notify(struct notifier_block *self, unsigned long action,
void *hcpu)
{
/*
* If a CPU goes away, splice its entries to the current CPU
* and trigger a run of the softirq
*/
if (action == CPU_DEAD || action == CPU_DEAD_FROZEN) {
int cpu = (unsigned long) hcpu;
local_irq_disable();
list_splice_init(&per_cpu(blk_cpu_done, cpu),
block: Replace __get_cpu_var uses __get_cpu_var() is used for multiple purposes in the kernel source. One of them is address calculation via the form &__get_cpu_var(x). This calculates the address for the instance of the percpu variable of the current processor based on an offset. Other use cases are for storing and retrieving data from the current processors percpu area. __get_cpu_var() can be used as an lvalue when writing data or on the right side of an assignment. __get_cpu_var() is defined as : #define __get_cpu_var(var) (*this_cpu_ptr(&(var))) __get_cpu_var() always only does an address determination. However, store and retrieve operations could use a segment prefix (or global register on other platforms) to avoid the address calculation. this_cpu_write() and this_cpu_read() can directly take an offset into a percpu area and use optimized assembly code to read and write per cpu variables. This patch converts __get_cpu_var into either an explicit address calculation using this_cpu_ptr() or into a use of this_cpu operations that use the offset. Thereby address calculations are avoided and less registers are used when code is generated. At the end of the patch set all uses of __get_cpu_var have been removed so the macro is removed too. The patch set includes passes over all arches as well. Once these operations are used throughout then specialized macros can be defined in non -x86 arches as well in order to optimize per cpu access by f.e. using a global register that may be set to the per cpu base. Transformations done to __get_cpu_var() 1. Determine the address of the percpu instance of the current processor. DEFINE_PER_CPU(int, y); int *x = &__get_cpu_var(y); Converts to int *x = this_cpu_ptr(&y); 2. Same as #1 but this time an array structure is involved. DEFINE_PER_CPU(int, y[20]); int *x = __get_cpu_var(y); Converts to int *x = this_cpu_ptr(y); 3. Retrieve the content of the current processors instance of a per cpu variable. DEFINE_PER_CPU(int, y); int x = __get_cpu_var(y) Converts to int x = __this_cpu_read(y); 4. Retrieve the content of a percpu struct DEFINE_PER_CPU(struct mystruct, y); struct mystruct x = __get_cpu_var(y); Converts to memcpy(&x, this_cpu_ptr(&y), sizeof(x)); 5. Assignment to a per cpu variable DEFINE_PER_CPU(int, y) __get_cpu_var(y) = x; Converts to this_cpu_write(y, x); 6. Increment/Decrement etc of a per cpu variable DEFINE_PER_CPU(int, y); __get_cpu_var(y)++ Converts to this_cpu_inc(y) Signed-off-by: Christoph Lameter <cl@linux.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2013-10-15 20:22:29 +02:00
this_cpu_ptr(&blk_cpu_done));
raise_softirq_irqoff(BLOCK_SOFTIRQ);
local_irq_enable();
}
return NOTIFY_OK;
}
static struct notifier_block blk_cpu_notifier = {
.notifier_call = blk_cpu_notify,
};
void __blk_complete_request(struct request *req)
{
int ccpu, cpu;
struct request_queue *q = req->q;
unsigned long flags;
bool shared = false;
BUG_ON(!q->softirq_done_fn);
local_irq_save(flags);
cpu = smp_processor_id();
/*
* Select completion CPU
*/
if (req->cpu != -1) {
ccpu = req->cpu;
if (!test_bit(QUEUE_FLAG_SAME_FORCE, &q->queue_flags))
shared = cpus_share_cache(cpu, ccpu);
} else
ccpu = cpu;
/*
* If current CPU and requested CPU share a cache, run the softirq on
* the current CPU. One might concern this is just like
* QUEUE_FLAG_SAME_FORCE, but actually not. blk_complete_request() is
* running in interrupt handler, and currently I/O controller doesn't
* support multiple interrupts, so current CPU is unique actually. This
* avoids IPI sending from current CPU to the first CPU of a group.
*/
if (ccpu == cpu || shared) {
struct list_head *list;
do_local:
block: Replace __get_cpu_var uses __get_cpu_var() is used for multiple purposes in the kernel source. One of them is address calculation via the form &__get_cpu_var(x). This calculates the address for the instance of the percpu variable of the current processor based on an offset. Other use cases are for storing and retrieving data from the current processors percpu area. __get_cpu_var() can be used as an lvalue when writing data or on the right side of an assignment. __get_cpu_var() is defined as : #define __get_cpu_var(var) (*this_cpu_ptr(&(var))) __get_cpu_var() always only does an address determination. However, store and retrieve operations could use a segment prefix (or global register on other platforms) to avoid the address calculation. this_cpu_write() and this_cpu_read() can directly take an offset into a percpu area and use optimized assembly code to read and write per cpu variables. This patch converts __get_cpu_var into either an explicit address calculation using this_cpu_ptr() or into a use of this_cpu operations that use the offset. Thereby address calculations are avoided and less registers are used when code is generated. At the end of the patch set all uses of __get_cpu_var have been removed so the macro is removed too. The patch set includes passes over all arches as well. Once these operations are used throughout then specialized macros can be defined in non -x86 arches as well in order to optimize per cpu access by f.e. using a global register that may be set to the per cpu base. Transformations done to __get_cpu_var() 1. Determine the address of the percpu instance of the current processor. DEFINE_PER_CPU(int, y); int *x = &__get_cpu_var(y); Converts to int *x = this_cpu_ptr(&y); 2. Same as #1 but this time an array structure is involved. DEFINE_PER_CPU(int, y[20]); int *x = __get_cpu_var(y); Converts to int *x = this_cpu_ptr(y); 3. Retrieve the content of the current processors instance of a per cpu variable. DEFINE_PER_CPU(int, y); int x = __get_cpu_var(y) Converts to int x = __this_cpu_read(y); 4. Retrieve the content of a percpu struct DEFINE_PER_CPU(struct mystruct, y); struct mystruct x = __get_cpu_var(y); Converts to memcpy(&x, this_cpu_ptr(&y), sizeof(x)); 5. Assignment to a per cpu variable DEFINE_PER_CPU(int, y) __get_cpu_var(y) = x; Converts to this_cpu_write(y, x); 6. Increment/Decrement etc of a per cpu variable DEFINE_PER_CPU(int, y); __get_cpu_var(y)++ Converts to this_cpu_inc(y) Signed-off-by: Christoph Lameter <cl@linux.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2013-10-15 20:22:29 +02:00
list = this_cpu_ptr(&blk_cpu_done);
block: fix regression with block enabled tagging Martin reported that his test system would not boot with current git, it oopsed with this: BUG: unable to handle kernel paging request at ffff88046c6c9e80 IP: [<ffffffff812971e0>] blk_queue_start_tag+0x90/0x150 PGD 1ddf067 PUD 1de2067 PMD 47fc7d067 PTE 800000046c6c9060 Oops: 0002 [#1] SMP DEBUG_PAGEALLOC Modules linked in: sd_mod lpfc(+) scsi_transport_fc scsi_tgt oracleasm rpcsec_gss_krb5 ipv6 igb dca i2c_algo_bit i2c_core hwmon CPU: 3 PID: 87 Comm: kworker/u17:1 Not tainted 3.14.0+ #246 Hardware name: Supermicro X9DRX+-F/X9DRX+-F, BIOS 3.00 07/09/2013 Workqueue: events_unbound async_run_entry_fn task: ffff8802743c2150 ti: ffff880273d02000 task.ti: ffff880273d02000 RIP: 0010:[<ffffffff812971e0>] [<ffffffff812971e0>] blk_queue_start_tag+0x90/0x150 RSP: 0018:ffff880273d03a58 EFLAGS: 00010092 RAX: ffff88046c6c9e78 RBX: ffff880077208e78 RCX: 00000000fffc8da6 RDX: 00000000fffc186d RSI: 0000000000000009 RDI: 00000000fffc8d9d RBP: ffff880273d03a88 R08: 0000000000000001 R09: ffff8800021c2410 R10: 0000000000000005 R11: 0000000000015b30 R12: ffff88046c5bb8a0 R13: ffff88046c5c0890 R14: 000000000000001e R15: 000000000000001e FS: 0000000000000000(0000) GS:ffff880277b00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: ffff88046c6c9e80 CR3: 00000000018f6000 CR4: 00000000000407e0 Stack: ffff880273d03a98 ffff880474b18800 0000000000000000 ffff880474157000 ffff88046c5c0890 ffff880077208e78 ffff880273d03ae8 ffffffff813b9e62 ffff880200000010 ffff880474b18968 ffff880474b18848 ffff88046c5c0cd8 Call Trace: [<ffffffff813b9e62>] scsi_request_fn+0xf2/0x510 [<ffffffff81293167>] __blk_run_queue+0x37/0x50 [<ffffffff8129ac43>] blk_execute_rq_nowait+0xb3/0x130 [<ffffffff8129ad24>] blk_execute_rq+0x64/0xf0 [<ffffffff8108d2b0>] ? bit_waitqueue+0xd0/0xd0 [<ffffffff813bba35>] scsi_execute+0xe5/0x180 [<ffffffff813bbe4a>] scsi_execute_req_flags+0x9a/0x110 [<ffffffffa01b1304>] sd_spinup_disk+0x94/0x460 [sd_mod] [<ffffffff81160000>] ? __unmap_hugepage_range+0x200/0x2f0 [<ffffffffa01b2b9a>] sd_revalidate_disk+0xaa/0x3f0 [sd_mod] [<ffffffffa01b2fb8>] sd_probe_async+0xd8/0x200 [sd_mod] [<ffffffff8107703f>] async_run_entry_fn+0x3f/0x140 [<ffffffff8106a1c5>] process_one_work+0x175/0x410 [<ffffffff8106b373>] worker_thread+0x123/0x400 [<ffffffff8106b250>] ? manage_workers+0x160/0x160 [<ffffffff8107104e>] kthread+0xce/0xf0 [<ffffffff81070f80>] ? kthread_freezable_should_stop+0x70/0x70 [<ffffffff815f0bac>] ret_from_fork+0x7c/0xb0 [<ffffffff81070f80>] ? kthread_freezable_should_stop+0x70/0x70 Code: 48 0f ab 11 72 db 48 81 4b 40 00 00 10 00 89 83 08 01 00 00 48 89 df 49 8b 04 24 48 89 1c d0 e8 f7 a8 ff ff 49 8b 85 28 05 00 00 <48> 89 58 08 48 89 03 49 8d 85 28 05 00 00 48 89 43 08 49 89 9d RIP [<ffffffff812971e0>] blk_queue_start_tag+0x90/0x150 RSP <ffff880273d03a58> CR2: ffff88046c6c9e80 Martin bisected and found this to be the problem patch; commit 6d113398dcf4dfcd9787a4ead738b186f7b7ff0f Author: Jan Kara <jack@suse.cz> Date: Mon Feb 24 16:39:54 2014 +0100 block: Stop abusing rq->csd.list in blk-softirq and the problem was immediately apparent. The patch states that it is safe to reuse queuelist at completion time, since it is no longer used. However, that is not true if a device is using block enabled tagging. If that is the case, then the queuelist is reused to keep track of busy tags. If a device also ended up using softirq completions, we'd reuse ->queuelist for the IPI handling while block tagging was still using it. Boom. Fix this by adding a new ipi_list list head, and share the memory used with the request hash table. The hash table is never used after the request is moved to the dispatch list, which happens long before any potential completion of the request. Add a new request bit for this, so we don't have cases that check rq->hash while it could potentially have been reused for the IPI completion. Reported-by: Martin K. Petersen <martin.petersen@oracle.com> Tested-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Jens Axboe <axboe@fb.com>
2014-04-10 04:27:01 +02:00
list_add_tail(&req->ipi_list, list);
/*
* if the list only contains our just added request,
* signal a raise of the softirq. If there are already
* entries there, someone already raised the irq but it
* hasn't run yet.
*/
block: fix regression with block enabled tagging Martin reported that his test system would not boot with current git, it oopsed with this: BUG: unable to handle kernel paging request at ffff88046c6c9e80 IP: [<ffffffff812971e0>] blk_queue_start_tag+0x90/0x150 PGD 1ddf067 PUD 1de2067 PMD 47fc7d067 PTE 800000046c6c9060 Oops: 0002 [#1] SMP DEBUG_PAGEALLOC Modules linked in: sd_mod lpfc(+) scsi_transport_fc scsi_tgt oracleasm rpcsec_gss_krb5 ipv6 igb dca i2c_algo_bit i2c_core hwmon CPU: 3 PID: 87 Comm: kworker/u17:1 Not tainted 3.14.0+ #246 Hardware name: Supermicro X9DRX+-F/X9DRX+-F, BIOS 3.00 07/09/2013 Workqueue: events_unbound async_run_entry_fn task: ffff8802743c2150 ti: ffff880273d02000 task.ti: ffff880273d02000 RIP: 0010:[<ffffffff812971e0>] [<ffffffff812971e0>] blk_queue_start_tag+0x90/0x150 RSP: 0018:ffff880273d03a58 EFLAGS: 00010092 RAX: ffff88046c6c9e78 RBX: ffff880077208e78 RCX: 00000000fffc8da6 RDX: 00000000fffc186d RSI: 0000000000000009 RDI: 00000000fffc8d9d RBP: ffff880273d03a88 R08: 0000000000000001 R09: ffff8800021c2410 R10: 0000000000000005 R11: 0000000000015b30 R12: ffff88046c5bb8a0 R13: ffff88046c5c0890 R14: 000000000000001e R15: 000000000000001e FS: 0000000000000000(0000) GS:ffff880277b00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: ffff88046c6c9e80 CR3: 00000000018f6000 CR4: 00000000000407e0 Stack: ffff880273d03a98 ffff880474b18800 0000000000000000 ffff880474157000 ffff88046c5c0890 ffff880077208e78 ffff880273d03ae8 ffffffff813b9e62 ffff880200000010 ffff880474b18968 ffff880474b18848 ffff88046c5c0cd8 Call Trace: [<ffffffff813b9e62>] scsi_request_fn+0xf2/0x510 [<ffffffff81293167>] __blk_run_queue+0x37/0x50 [<ffffffff8129ac43>] blk_execute_rq_nowait+0xb3/0x130 [<ffffffff8129ad24>] blk_execute_rq+0x64/0xf0 [<ffffffff8108d2b0>] ? bit_waitqueue+0xd0/0xd0 [<ffffffff813bba35>] scsi_execute+0xe5/0x180 [<ffffffff813bbe4a>] scsi_execute_req_flags+0x9a/0x110 [<ffffffffa01b1304>] sd_spinup_disk+0x94/0x460 [sd_mod] [<ffffffff81160000>] ? __unmap_hugepage_range+0x200/0x2f0 [<ffffffffa01b2b9a>] sd_revalidate_disk+0xaa/0x3f0 [sd_mod] [<ffffffffa01b2fb8>] sd_probe_async+0xd8/0x200 [sd_mod] [<ffffffff8107703f>] async_run_entry_fn+0x3f/0x140 [<ffffffff8106a1c5>] process_one_work+0x175/0x410 [<ffffffff8106b373>] worker_thread+0x123/0x400 [<ffffffff8106b250>] ? manage_workers+0x160/0x160 [<ffffffff8107104e>] kthread+0xce/0xf0 [<ffffffff81070f80>] ? kthread_freezable_should_stop+0x70/0x70 [<ffffffff815f0bac>] ret_from_fork+0x7c/0xb0 [<ffffffff81070f80>] ? kthread_freezable_should_stop+0x70/0x70 Code: 48 0f ab 11 72 db 48 81 4b 40 00 00 10 00 89 83 08 01 00 00 48 89 df 49 8b 04 24 48 89 1c d0 e8 f7 a8 ff ff 49 8b 85 28 05 00 00 <48> 89 58 08 48 89 03 49 8d 85 28 05 00 00 48 89 43 08 49 89 9d RIP [<ffffffff812971e0>] blk_queue_start_tag+0x90/0x150 RSP <ffff880273d03a58> CR2: ffff88046c6c9e80 Martin bisected and found this to be the problem patch; commit 6d113398dcf4dfcd9787a4ead738b186f7b7ff0f Author: Jan Kara <jack@suse.cz> Date: Mon Feb 24 16:39:54 2014 +0100 block: Stop abusing rq->csd.list in blk-softirq and the problem was immediately apparent. The patch states that it is safe to reuse queuelist at completion time, since it is no longer used. However, that is not true if a device is using block enabled tagging. If that is the case, then the queuelist is reused to keep track of busy tags. If a device also ended up using softirq completions, we'd reuse ->queuelist for the IPI handling while block tagging was still using it. Boom. Fix this by adding a new ipi_list list head, and share the memory used with the request hash table. The hash table is never used after the request is moved to the dispatch list, which happens long before any potential completion of the request. Add a new request bit for this, so we don't have cases that check rq->hash while it could potentially have been reused for the IPI completion. Reported-by: Martin K. Petersen <martin.petersen@oracle.com> Tested-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Jens Axboe <axboe@fb.com>
2014-04-10 04:27:01 +02:00
if (list->next == &req->ipi_list)
raise_softirq_irqoff(BLOCK_SOFTIRQ);
} else if (raise_blk_irq(ccpu, req))
goto do_local;
local_irq_restore(flags);
}
/**
* blk_complete_request - end I/O on a request
* @req: the request being processed
*
* Description:
* Ends all I/O on a request. It does not handle partial completions,
* unless the driver actually implements this in its completion callback
* through requeueing. The actual completion happens out-of-order,
* through a softirq handler. The user must have registered a completion
* callback through blk_queue_softirq_done().
**/
void blk_complete_request(struct request *req)
{
if (unlikely(blk_should_fake_timeout(req->q)))
return;
if (!blk_mark_rq_complete(req))
__blk_complete_request(req);
}
EXPORT_SYMBOL(blk_complete_request);
static __init int blk_softirq_init(void)
{
int i;
for_each_possible_cpu(i)
INIT_LIST_HEAD(&per_cpu(blk_cpu_done, i));
open_softirq(BLOCK_SOFTIRQ, blk_done_softirq);
register_hotcpu_notifier(&blk_cpu_notifier);
return 0;
}
subsys_initcall(blk_softirq_init);