kernel-ark/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 18:22:29 +00:00
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;
rq = list_entry(local_list.next, struct request, csd.list);
list_del_init(&rq->csd.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 18:22:29 +00:00
list = this_cpu_ptr(&blk_cpu_done);
list_add_tail(&rq->csd.list, list);
if (list->next == &rq->csd.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(cpu, data, 0);
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 18:22:29 +00:00
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 18:22:29 +00:00
list = this_cpu_ptr(&blk_cpu_done);
list_add_tail(&req->csd.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.
*/
if (list->next == &req->csd.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);