6 files changed, 351 insertions, 10 deletions

diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index c9eef36739a9..06344d986eb9 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -597,7 +597,7 @@ endmenu # "Memory Debugging"
 
 config DEBUG_SHIRQ
         bool "Debug shared IRQ handlers"
-        depends on DEBUG_KERNEL && GENERIC_HARDIRQS
+        depends on DEBUG_KERNEL
         help
           Enable this to generate a spurious interrupt as soon as a shared
           interrupt handler is registered, and just before one is deregistered.
diff --git a/lib/Makefile b/lib/Makefile
index f2cb3082697c..f3bb2cb98adf 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -13,7 +13,7 @@ lib-y := ctype.o string.o vsprintf.o cmdline.o \
          sha1.o md5.o irq_regs.o reciprocal_div.o argv_split.o \
          proportions.o flex_proportions.o prio_heap.o ratelimit.o show_mem.o \
          is_single_threaded.o plist.o decompress.o kobject_uevent.o \
-         earlycpio.o percpu-refcount.o
+         earlycpio.o percpu-refcount.o percpu_ida.o
 
 obj-$(CONFIG_ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS) += usercopy.o
 lib-$(CONFIG_MMU) += ioremap.o
@@ -25,7 +25,8 @@ obj-y	+= lockref.o
 obj-y += bcd.o div64.o sort.o parser.o halfmd4.o debug_locks.o random32.o \
          bust_spinlocks.o hexdump.o kasprintf.o bitmap.o scatterlist.o \
          gcd.o lcm.o list_sort.o uuid.o flex_array.o iovec.o clz_ctz.o \
-         bsearch.o find_last_bit.o find_next_bit.o llist.o memweight.o kfifo.o
+         bsearch.o find_last_bit.o find_next_bit.o llist.o memweight.o kfifo.o \
+         percpu_ida.o
 obj-y += string_helpers.o
 obj-$(CONFIG_TEST_STRING_HELPERS) += test-string_helpers.o
 obj-y += kstrtox.o
diff --git a/lib/cpu_rmap.c b/lib/cpu_rmap.c
index 5fbed5caba6e..4f134d8907a7 100644
--- a/lib/cpu_rmap.c
+++ b/lib/cpu_rmap.c
@@ -8,9 +8,7 @@
  */
 
 #include <linux/cpu_rmap.h>
-#ifdef CONFIG_GENERIC_HARDIRQS
 #include <linux/interrupt.h>
-#endif
 #include <linux/export.h>
 
 /*
@@ -213,8 +211,6 @@ int cpu_rmap_update(struct cpu_rmap *rmap, u16 index,
 }
 EXPORT_SYMBOL(cpu_rmap_update);
 
-#ifdef CONFIG_GENERIC_HARDIRQS
-
 /* Glue between IRQ affinity notifiers and CPU rmaps */
 
 struct irq_glue {
@@ -309,5 +305,3 @@ int irq_cpu_rmap_add(struct cpu_rmap *rmap, int irq)
         return rc;
 }
 EXPORT_SYMBOL(irq_cpu_rmap_add);
-
-#endif /* CONFIG_GENERIC_HARDIRQS */
diff --git a/lib/crc-t10dif.c b/lib/crc-t10dif.c
index 43bc5b071f96..dfe6ec17c0a5 100644
--- a/lib/crc-t10dif.c
+++ b/lib/crc-t10dif.c
@@ -14,8 +14,10 @@
 #include <linux/err.h>
 #include <linux/init.h>
 #include <crypto/hash.h>
+#include <linux/static_key.h>
 
 static struct crypto_shash *crct10dif_tfm;
+static struct static_key crct10dif_fallback __read_mostly;
 
 __u16 crc_t10dif(const unsigned char *buffer, size_t len)
 {
@@ -25,6 +27,9 @@ __u16 crc_t10dif(const unsigned char *buffer, size_t len)
         } desc;
         int err;
 
+        if (static_key_false(&crct10dif_fallback))
+                return crc_t10dif_generic(0, buffer, len);
+
         desc.shash.tfm = crct10dif_tfm;
         desc.shash.flags = 0;
         *(__u16 *)desc.ctx = 0;
@@ -39,7 +44,11 @@ EXPORT_SYMBOL(crc_t10dif);
 static int __init crc_t10dif_mod_init(void)
 {
         crct10dif_tfm = crypto_alloc_shash("crct10dif", 0, 0);
-        return PTR_RET(crct10dif_tfm);
+        if (IS_ERR(crct10dif_tfm)) {
+                static_key_slow_inc(&crct10dif_fallback);
+                crct10dif_tfm = NULL;
+        }
+        return 0;
 }
 
 static void __exit crc_t10dif_mod_fini(void)
diff --git a/lib/hexdump.c b/lib/hexdump.c
index 3f0494c9d57a..8499c810909a 100644
--- a/lib/hexdump.c
+++ b/lib/hexdump.c
@@ -14,6 +14,8 @@
 
 const char hex_asc[] = "0123456789abcdef";
 EXPORT_SYMBOL(hex_asc);
+const char hex_asc_upper[] = "0123456789ABCDEF";
+EXPORT_SYMBOL(hex_asc_upper);
 
 /**
  * hex_to_bin - convert a hex digit to its real value
diff --git a/lib/percpu_ida.c b/lib/percpu_ida.c
new file mode 100644
index 000000000000..bab1ba2a4c71
--- /dev/null
+++ b/lib/percpu_ida.c
@@ -0,0 +1,335 @@
+/*
+ * Percpu IDA library
+ *
+ * Copyright (C) 2013 Datera, Inc. Kent Overstreet
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation; either version 2, or (at
+ * your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ */
+
+#include <linux/bitmap.h>
+#include <linux/bitops.h>
+#include <linux/bug.h>
+#include <linux/err.h>
+#include <linux/export.h>
+#include <linux/hardirq.h>
+#include <linux/idr.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/percpu.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/spinlock.h>
+#include <linux/percpu_ida.h>
+
+/*
+ * Number of tags we move between the percpu freelist and the global freelist at
+ * a time
+ */
+#define IDA_PCPU_BATCH_MOVE     32U
+
+/* Max size of percpu freelist, */
+#define IDA_PCPU_SIZE           ((IDA_PCPU_BATCH_MOVE * 3) / 2)
+
+struct percpu_ida_cpu {
+        /*
+         * Even though this is percpu, we need a lock for tag stealing by remote
+         * CPUs:
+         */
+        spinlock_t                      lock;
+
+        /* nr_free/freelist form a stack of free IDs */
+        unsigned                        nr_free;
+        unsigned                        freelist[];
+};
+
+static inline void move_tags(unsigned *dst, unsigned *dst_nr,
+                             unsigned *src, unsigned *src_nr,
+                             unsigned nr)
+{
+        *src_nr -= nr;
+        memcpy(dst + *dst_nr, src + *src_nr, sizeof(unsigned) * nr);
+        *dst_nr += nr;
+}
+
+/*
+ * Try to steal tags from a remote cpu's percpu freelist.
+ *
+ * We first check how many percpu freelists have tags - we don't steal tags
+ * unless enough percpu freelists have tags on them that it's possible more than
+ * half the total tags could be stuck on remote percpu freelists.
+ *
+ * Then we iterate through the cpus until we find some tags - we don't attempt
+ * to find the "best" cpu to steal from, to keep cacheline bouncing to a
+ * minimum.
+ */
+static inline void steal_tags(struct percpu_ida *pool,
+                              struct percpu_ida_cpu *tags)
+{
+        unsigned cpus_have_tags, cpu = pool->cpu_last_stolen;
+        struct percpu_ida_cpu *remote;
+
+        for (cpus_have_tags = cpumask_weight(&pool->cpus_have_tags);
+             cpus_have_tags * IDA_PCPU_SIZE > pool->nr_tags / 2;
+             cpus_have_tags--) {
+                cpu = cpumask_next(cpu, &pool->cpus_have_tags);
+
+                if (cpu >= nr_cpu_ids) {
+                        cpu = cpumask_first(&pool->cpus_have_tags);
+                        if (cpu >= nr_cpu_ids)
+                                BUG();
+                }
+
+                pool->cpu_last_stolen = cpu;
+                remote = per_cpu_ptr(pool->tag_cpu, cpu);
+
+                cpumask_clear_cpu(cpu, &pool->cpus_have_tags);
+
+                if (remote == tags)
+                        continue;
+
+                spin_lock(&remote->lock);
+
+                if (remote->nr_free) {
+                        memcpy(tags->freelist,
+                               remote->freelist,
+                               sizeof(unsigned) * remote->nr_free);
+
+                        tags->nr_free = remote->nr_free;
+                        remote->nr_free = 0;
+                }
+
+                spin_unlock(&remote->lock);
+
+                if (tags->nr_free)
+                        break;
+        }
+}
+
+/*
+ * Pop up to IDA_PCPU_BATCH_MOVE IDs off the global freelist, and push them onto
+ * our percpu freelist:
+ */
+static inline void alloc_global_tags(struct percpu_ida *pool,
+                                     struct percpu_ida_cpu *tags)
+{
+        move_tags(tags->freelist, &tags->nr_free,
+                  pool->freelist, &pool->nr_free,
+                  min(pool->nr_free, IDA_PCPU_BATCH_MOVE));
+}
+
+static inline unsigned alloc_local_tag(struct percpu_ida *pool,
+                                       struct percpu_ida_cpu *tags)
+{
+        int tag = -ENOSPC;
+
+        spin_lock(&tags->lock);
+        if (tags->nr_free)
+                tag = tags->freelist[--tags->nr_free];
+        spin_unlock(&tags->lock);
+
+        return tag;
+}
+
+/**
+ * percpu_ida_alloc - allocate a tag
+ * @pool: pool to allocate from
+ * @gfp: gfp flags
+ *
+ * Returns a tag - an integer in the range [0..nr_tags) (passed to
+ * tag_pool_init()), or otherwise -ENOSPC on allocation failure.
+ *
+ * Safe to be called from interrupt context (assuming it isn't passed
+ * __GFP_WAIT, of course).
+ *
+ * @gfp indicates whether or not to wait until a free id is available (it's not
+ * used for internal memory allocations); thus if passed __GFP_WAIT we may sleep
+ * however long it takes until another thread frees an id (same semantics as a
+ * mempool).
+ *
+ * Will not fail if passed __GFP_WAIT.
+ */
+int percpu_ida_alloc(struct percpu_ida *pool, gfp_t gfp)
+{
+        DEFINE_WAIT(wait);
+        struct percpu_ida_cpu *tags;
+        unsigned long flags;
+        int tag;
+
+        local_irq_save(flags);
+        tags = this_cpu_ptr(pool->tag_cpu);
+
+        /* Fastpath */
+        tag = alloc_local_tag(pool, tags);
+        if (likely(tag >= 0)) {
+                local_irq_restore(flags);
+                return tag;
+        }
+
+        while (1) {
+                spin_lock(&pool->lock);
+
+                /*
+                 * prepare_to_wait() must come before steal_tags(), in case
+                 * percpu_ida_free() on another cpu flips a bit in
+                 * cpus_have_tags
+                 *
+                 * global lock held and irqs disabled, don't need percpu lock
+                 */
+                prepare_to_wait(&pool->wait, &wait, TASK_UNINTERRUPTIBLE);
+
+                if (!tags->nr_free)
+                        alloc_global_tags(pool, tags);
+                if (!tags->nr_free)
+                        steal_tags(pool, tags);
+
+                if (tags->nr_free) {
+                        tag = tags->freelist[--tags->nr_free];
+                        if (tags->nr_free)
+                                cpumask_set_cpu(smp_processor_id(),
+                                                &pool->cpus_have_tags);
+                }
+
+                spin_unlock(&pool->lock);
+                local_irq_restore(flags);
+
+                if (tag >= 0 || !(gfp & __GFP_WAIT))
+                        break;
+
+                schedule();
+
+                local_irq_save(flags);
+                tags = this_cpu_ptr(pool->tag_cpu);
+        }
+
+        finish_wait(&pool->wait, &wait);
+        return tag;
+}
+EXPORT_SYMBOL_GPL(percpu_ida_alloc);
+
+/**
+ * percpu_ida_free - free a tag
+ * @pool: pool @tag was allocated from
+ * @tag: a tag previously allocated with percpu_ida_alloc()
+ *
+ * Safe to be called from interrupt context.
+ */
+void percpu_ida_free(struct percpu_ida *pool, unsigned tag)
+{
+        struct percpu_ida_cpu *tags;
+        unsigned long flags;
+        unsigned nr_free;
+
+        BUG_ON(tag >= pool->nr_tags);
+
+        local_irq_save(flags);
+        tags = this_cpu_ptr(pool->tag_cpu);
+
+        spin_lock(&tags->lock);
+        tags->freelist[tags->nr_free++] = tag;
+
+        nr_free = tags->nr_free;
+        spin_unlock(&tags->lock);
+
+        if (nr_free == 1) {
+                cpumask_set_cpu(smp_processor_id(),
+                                &pool->cpus_have_tags);
+                wake_up(&pool->wait);
+        }
+
+        if (nr_free == IDA_PCPU_SIZE) {
+                spin_lock(&pool->lock);
+
+                /*
+                 * Global lock held and irqs disabled, don't need percpu
+                 * lock
+                 */
+                if (tags->nr_free == IDA_PCPU_SIZE) {
+                        move_tags(pool->freelist, &pool->nr_free,
+                                  tags->freelist, &tags->nr_free,
+                                  IDA_PCPU_BATCH_MOVE);
+
+                        wake_up(&pool->wait);
+                }
+                spin_unlock(&pool->lock);
+        }
+
+        local_irq_restore(flags);
+}
+EXPORT_SYMBOL_GPL(percpu_ida_free);
+
+/**
+ * percpu_ida_destroy - release a tag pool's resources
+ * @pool: pool to free
+ *
+ * Frees the resources allocated by percpu_ida_init().
+ */
+void percpu_ida_destroy(struct percpu_ida *pool)
+{
+        free_percpu(pool->tag_cpu);
+        free_pages((unsigned long) pool->freelist,
+                   get_order(pool->nr_tags * sizeof(unsigned)));
+}
+EXPORT_SYMBOL_GPL(percpu_ida_destroy);
+
+/**
+ * percpu_ida_init - initialize a percpu tag pool
+ * @pool: pool to initialize
+ * @nr_tags: number of tags that will be available for allocation
+ *
+ * Initializes @pool so that it can be used to allocate tags - integers in the
+ * range [0, nr_tags). Typically, they'll be used by driver code to refer to a
+ * preallocated array of tag structures.
+ *
+ * Allocation is percpu, but sharding is limited by nr_tags - for best
+ * performance, the workload should not span more cpus than nr_tags / 128.
+ */
+int percpu_ida_init(struct percpu_ida *pool, unsigned long nr_tags)
+{
+        unsigned i, cpu, order;
+
+        memset(pool, 0, sizeof(*pool));
+
+        init_waitqueue_head(&pool->wait);
+        spin_lock_init(&pool->lock);
+        pool->nr_tags = nr_tags;
+
+        /* Guard against overflow */
+        if (nr_tags > (unsigned) INT_MAX + 1) {
+                pr_err("percpu_ida_init(): nr_tags too large\n");
+                return -EINVAL;
+        }
+
+        order = get_order(nr_tags * sizeof(unsigned));
+        pool->freelist = (void *) __get_free_pages(GFP_KERNEL, order);
+        if (!pool->freelist)
+                return -ENOMEM;
+
+        for (i = 0; i < nr_tags; i++)
+                pool->freelist[i] = i;
+
+        pool->nr_free = nr_tags;
+
+        pool->tag_cpu = __alloc_percpu(sizeof(struct percpu_ida_cpu) +
+                                       IDA_PCPU_SIZE * sizeof(unsigned),
+                                       sizeof(unsigned));
+        if (!pool->tag_cpu)
+                goto err;
+
+        for_each_possible_cpu(cpu)
+                spin_lock_init(&per_cpu_ptr(pool->tag_cpu, cpu)->lock);
+
+        return 0;
+err:
+        percpu_ida_destroy(pool);
+        return -ENOMEM;
+}
+EXPORT_SYMBOL_GPL(percpu_ida_init);