[PATCH 5/8] blk-mq: allow the driver to pass in an affinity mask

[Christoph Hellwig]

Allow drivers to pass in the affinity mask from the generic interrupt
layer, and spread queues based on that.  If the driver doesn't pass in
a mask we will create it using the genirq helper.  As this helper was
modelled after the blk-mq algorithm there should be no change in behavior.

XXX: Just as with the core IRQ spreading code this doesn't handle CPU
hotplug yet.

Signed-off-by: Christoph Hellwig 
---
 block/Makefile |   2 +-
 block/blk-mq-cpumap.c  | 120 -
 block/blk-mq.c |  60 -
 block/blk-mq.h |   8 
 include/linux/blk-mq.h |   1 +
 5 files changed, 60 insertions(+), 131 deletions(-)
 delete mode 100644 block/blk-mq-cpumap.c

diff --git a/block/Makefile b/block/Makefile
index 9eda232..aeb318d 100644
--- a/block/Makefile
+++ b/block/Makefile
@@ -6,7 +6,7 @@ obj-$(CONFIG_BLOCK) := bio.o elevator.o blk-core.o blk-tag.o 
blk-sysfs.o \
blk-flush.o blk-settings.o blk-ioc.o blk-map.o \
blk-exec.o blk-merge.o blk-softirq.o blk-timeout.o \
blk-lib.o blk-mq.o blk-mq-tag.o \
-   blk-mq-sysfs.o blk-mq-cpu.o blk-mq-cpumap.o ioctl.o \
+   blk-mq-sysfs.o blk-mq-cpu.o ioctl.o \
genhd.o scsi_ioctl.o partition-generic.o ioprio.o \
badblocks.o partitions/
 
diff --git a/block/blk-mq-cpumap.c b/block/blk-mq-cpumap.c
deleted file mode 100644
index d0634bc..000
--- a/block/blk-mq-cpumap.c
+++ /dev/null
@@ -1,120 +0,0 @@
-/*
- * CPU <-> hardware queue mapping helpers
- *
- * Copyright (C) 2013-2014 Jens Axboe
- */
-#include 
-#include 
-#include 
-#include 
-#include 
-#include 
-
-#include 
-#include "blk.h"
-#include "blk-mq.h"
-
-static int cpu_to_queue_index(unsigned int nr_cpus, unsigned int nr_queues,
- const int cpu)
-{
-   return cpu * nr_queues / nr_cpus;
-}
-
-static int get_first_sibling(unsigned int cpu)
-{
-   unsigned int ret;
-
-   ret = cpumask_first(topology_sibling_cpumask(cpu));
-   if (ret < nr_cpu_ids)
-   return ret;
-
-   return cpu;
-}
-
-int blk_mq_update_queue_map(unsigned int *map, unsigned int nr_queues,
-   const struct cpumask *online_mask)
-{
-   unsigned int i, nr_cpus, nr_uniq_cpus, queue, first_sibling;
-   cpumask_var_t cpus;
-
-   if (!alloc_cpumask_var(, GFP_ATOMIC))
-   return 1;
-
-   cpumask_clear(cpus);
-   nr_cpus = nr_uniq_cpus = 0;
-   for_each_cpu(i, online_mask) {
-   nr_cpus++;
-   first_sibling = get_first_sibling(i);
-   if (!cpumask_test_cpu(first_sibling, cpus))
-   nr_uniq_cpus++;
-   cpumask_set_cpu(i, cpus);
-   }
-
-   queue = 0;
-   for_each_possible_cpu(i) {
-   if (!cpumask_test_cpu(i, online_mask)) {
-   map[i] = 0;
-   continue;
-   }
-
-   /*
-* Easy case - we have equal or more hardware queues. Or
-* there are no thread siblings to take into account. Do
-* 1:1 if enough, or sequential mapping if less.
-*/
-   if (nr_queues >= nr_cpus || nr_cpus == nr_uniq_cpus) {
-   map[i] = cpu_to_queue_index(nr_cpus, nr_queues, queue);
-   queue++;
-   continue;
-   }
-
-   /*
-* Less then nr_cpus queues, and we have some number of
-* threads per cores. Map sibling threads to the same
-* queue.
-*/
-   first_sibling = get_first_sibling(i);
-   if (first_sibling == i) {
-   map[i] = cpu_to_queue_index(nr_uniq_cpus, nr_queues,
-   queue);
-   queue++;
-   } else
-   map[i] = map[first_sibling];
-   }
-
-   free_cpumask_var(cpus);
-   return 0;
-}
-
-unsigned int *blk_mq_make_queue_map(struct blk_mq_tag_set *set)
-{
-   unsigned int *map;
-
-   /* If cpus are offline, map them to first hctx */
-   map = kzalloc_node(sizeof(*map) * nr_cpu_ids, GFP_KERNEL,
-   set->numa_node);
-   if (!map)
-   return NULL;
-
-   if (!blk_mq_update_queue_map(map, set->nr_hw_queues, cpu_online_mask))
-   return map;
-
-   kfree(map);
-   return NULL;
-}
-
-/*
- * We have no quick way of doing reverse lookups. This is only used at
- * queue init time, so runtime isn't important.
- */
-int blk_mq_hw_queue_to_node(unsigned int *mq_map, unsigned int index)
-{
-   int i;
-
-   for_each_possible_cpu(i) {
-   if (index == mq_map[i])
-   return 

[PATCH 5/8] blk-mq: allow the driver to pass in an affinity mask

[Christoph Hellwig]

Allow drivers to pass in the affinity mask from the generic interrupt
layer, and spread queues based on that.  If the driver doesn't pass in
a mask we will create it using the genirq helper.  As this helper was
modelled after the blk-mq algorithm there should be no change in behavior.

XXX: Just as with the core IRQ spreading code this doesn't handle CPU
hotplug yet.

Signed-off-by: Christoph Hellwig 
---
 block/Makefile |   2 +-
 block/blk-mq-cpumap.c  | 120 -
 block/blk-mq.c |  60 -
 block/blk-mq.h |   8 
 include/linux/blk-mq.h |   1 +
 5 files changed, 60 insertions(+), 131 deletions(-)
 delete mode 100644 block/blk-mq-cpumap.c

diff --git a/block/Makefile b/block/Makefile
index 9eda232..aeb318d 100644
--- a/block/Makefile
+++ b/block/Makefile
@@ -6,7 +6,7 @@ obj-$(CONFIG_BLOCK) := bio.o elevator.o blk-core.o blk-tag.o 
blk-sysfs.o \
blk-flush.o blk-settings.o blk-ioc.o blk-map.o \
blk-exec.o blk-merge.o blk-softirq.o blk-timeout.o \
blk-lib.o blk-mq.o blk-mq-tag.o \
-   blk-mq-sysfs.o blk-mq-cpu.o blk-mq-cpumap.o ioctl.o \
+   blk-mq-sysfs.o blk-mq-cpu.o ioctl.o \
genhd.o scsi_ioctl.o partition-generic.o ioprio.o \
badblocks.o partitions/
 
diff --git a/block/blk-mq-cpumap.c b/block/blk-mq-cpumap.c
deleted file mode 100644
index d0634bc..000
--- a/block/blk-mq-cpumap.c
+++ /dev/null
@@ -1,120 +0,0 @@
-/*
- * CPU <-> hardware queue mapping helpers
- *
- * Copyright (C) 2013-2014 Jens Axboe
- */
-#include 
-#include 
-#include 
-#include 
-#include 
-#include 
-
-#include 
-#include "blk.h"
-#include "blk-mq.h"
-
-static int cpu_to_queue_index(unsigned int nr_cpus, unsigned int nr_queues,
- const int cpu)
-{
-   return cpu * nr_queues / nr_cpus;
-}
-
-static int get_first_sibling(unsigned int cpu)
-{
-   unsigned int ret;
-
-   ret = cpumask_first(topology_sibling_cpumask(cpu));
-   if (ret < nr_cpu_ids)
-   return ret;
-
-   return cpu;
-}
-
-int blk_mq_update_queue_map(unsigned int *map, unsigned int nr_queues,
-   const struct cpumask *online_mask)
-{
-   unsigned int i, nr_cpus, nr_uniq_cpus, queue, first_sibling;
-   cpumask_var_t cpus;
-
-   if (!alloc_cpumask_var(, GFP_ATOMIC))
-   return 1;
-
-   cpumask_clear(cpus);
-   nr_cpus = nr_uniq_cpus = 0;
-   for_each_cpu(i, online_mask) {
-   nr_cpus++;
-   first_sibling = get_first_sibling(i);
-   if (!cpumask_test_cpu(first_sibling, cpus))
-   nr_uniq_cpus++;
-   cpumask_set_cpu(i, cpus);
-   }
-
-   queue = 0;
-   for_each_possible_cpu(i) {
-   if (!cpumask_test_cpu(i, online_mask)) {
-   map[i] = 0;
-   continue;
-   }
-
-   /*
-* Easy case - we have equal or more hardware queues. Or
-* there are no thread siblings to take into account. Do
-* 1:1 if enough, or sequential mapping if less.
-*/
-   if (nr_queues >= nr_cpus || nr_cpus == nr_uniq_cpus) {
-   map[i] = cpu_to_queue_index(nr_cpus, nr_queues, queue);
-   queue++;
-   continue;
-   }
-
-   /*
-* Less then nr_cpus queues, and we have some number of
-* threads per cores. Map sibling threads to the same
-* queue.
-*/
-   first_sibling = get_first_sibling(i);
-   if (first_sibling == i) {
-   map[i] = cpu_to_queue_index(nr_uniq_cpus, nr_queues,
-   queue);
-   queue++;
-   } else
-   map[i] = map[first_sibling];
-   }
-
-   free_cpumask_var(cpus);
-   return 0;
-}
-
-unsigned int *blk_mq_make_queue_map(struct blk_mq_tag_set *set)
-{
-   unsigned int *map;
-
-   /* If cpus are offline, map them to first hctx */
-   map = kzalloc_node(sizeof(*map) * nr_cpu_ids, GFP_KERNEL,
-   set->numa_node);
-   if (!map)
-   return NULL;
-
-   if (!blk_mq_update_queue_map(map, set->nr_hw_queues, cpu_online_mask))
-   return map;
-
-   kfree(map);
-   return NULL;
-}
-
-/*
- * We have no quick way of doing reverse lookups. This is only used at
- * queue init time, so runtime isn't important.
- */
-int blk_mq_hw_queue_to_node(unsigned int *mq_map, unsigned int index)
-{
-   int i;
-
-   for_each_possible_cpu(i) {
-   if (index == mq_map[i])
-   return local_memory_node(cpu_to_node(i));
-