original_kernel/lib/sbitmap.c

690 lines
16 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright (C) 2016 Facebook
* Copyright (C) 2013-2014 Jens Axboe
*/
#include <linux/sched.h>
#include <linux/random.h>
#include <linux/sbitmap.h>
#include <linux/seq_file.h>
/*
* See if we have deferred clears that we can batch move
*/
static inline bool sbitmap_deferred_clear(struct sbitmap *sb, int index)
{
unsigned long mask, val;
bool ret = false;
unsigned long flags;
spin_lock_irqsave(&sb->map[index].swap_lock, flags);
if (!sb->map[index].cleared)
goto out_unlock;
/*
* First get a stable cleared mask, setting the old mask to 0.
*/
mask = xchg(&sb->map[index].cleared, 0);
/*
* Now clear the masked bits in our free word
*/
do {
val = sb->map[index].word;
} while (cmpxchg(&sb->map[index].word, val, val & ~mask) != val);
ret = true;
out_unlock:
spin_unlock_irqrestore(&sb->map[index].swap_lock, flags);
return ret;
}
int sbitmap_init_node(struct sbitmap *sb, unsigned int depth, int shift,
gfp_t flags, int node)
{
unsigned int bits_per_word;
unsigned int i;
if (shift < 0) {
shift = ilog2(BITS_PER_LONG);
/*
* If the bitmap is small, shrink the number of bits per word so
* we spread over a few cachelines, at least. If less than 4
* bits, just forget about it, it's not going to work optimally
* anyway.
*/
if (depth >= 4) {
while ((4U << shift) > depth)
shift--;
}
}
bits_per_word = 1U << shift;
if (bits_per_word > BITS_PER_LONG)
return -EINVAL;
sb->shift = shift;
sb->depth = depth;
sb->map_nr = DIV_ROUND_UP(sb->depth, bits_per_word);
if (depth == 0) {
sb->map = NULL;
return 0;
}
treewide: kzalloc_node() -> kcalloc_node() The kzalloc_node() function has a 2-factor argument form, kcalloc_node(). This patch replaces cases of: kzalloc_node(a * b, gfp, node) with: kcalloc_node(a * b, gfp, node) as well as handling cases of: kzalloc_node(a * b * c, gfp, node) with: kzalloc_node(array3_size(a, b, c), gfp, node) as it's slightly less ugly than: kcalloc_node(array_size(a, b), c, gfp, node) This does, however, attempt to ignore constant size factors like: kzalloc_node(4 * 1024, gfp, node) though any constants defined via macros get caught up in the conversion. Any factors with a sizeof() of "unsigned char", "char", and "u8" were dropped, since they're redundant. The Coccinelle script used for this was: // Fix redundant parens around sizeof(). @@ type TYPE; expression THING, E; @@ ( kzalloc_node( - (sizeof(TYPE)) * E + sizeof(TYPE) * E , ...) | kzalloc_node( - (sizeof(THING)) * E + sizeof(THING) * E , ...) ) // Drop single-byte sizes and redundant parens. @@ expression COUNT; typedef u8; typedef __u8; @@ ( kzalloc_node( - sizeof(u8) * (COUNT) + COUNT , ...) | kzalloc_node( - sizeof(__u8) * (COUNT) + COUNT , ...) | kzalloc_node( - sizeof(char) * (COUNT) + COUNT , ...) | kzalloc_node( - sizeof(unsigned char) * (COUNT) + COUNT , ...) | kzalloc_node( - sizeof(u8) * COUNT + COUNT , ...) | kzalloc_node( - sizeof(__u8) * COUNT + COUNT , ...) | kzalloc_node( - sizeof(char) * COUNT + COUNT , ...) | kzalloc_node( - sizeof(unsigned char) * COUNT + COUNT , ...) ) // 2-factor product with sizeof(type/expression) and identifier or constant. @@ type TYPE; expression THING; identifier COUNT_ID; constant COUNT_CONST; @@ ( - kzalloc_node + kcalloc_node ( - sizeof(TYPE) * (COUNT_ID) + COUNT_ID, sizeof(TYPE) , ...) | - kzalloc_node + kcalloc_node ( - sizeof(TYPE) * COUNT_ID + COUNT_ID, sizeof(TYPE) , ...) | - kzalloc_node + kcalloc_node ( - sizeof(TYPE) * (COUNT_CONST) + COUNT_CONST, sizeof(TYPE) , ...) | - kzalloc_node + kcalloc_node ( - sizeof(TYPE) * COUNT_CONST + COUNT_CONST, sizeof(TYPE) , ...) | - kzalloc_node + kcalloc_node ( - sizeof(THING) * (COUNT_ID) + COUNT_ID, sizeof(THING) , ...) | - kzalloc_node + kcalloc_node ( - sizeof(THING) * COUNT_ID + COUNT_ID, sizeof(THING) , ...) | - kzalloc_node + kcalloc_node ( - sizeof(THING) * (COUNT_CONST) + COUNT_CONST, sizeof(THING) , ...) | - kzalloc_node + kcalloc_node ( - sizeof(THING) * COUNT_CONST + COUNT_CONST, sizeof(THING) , ...) ) // 2-factor product, only identifiers. @@ identifier SIZE, COUNT; @@ - kzalloc_node + kcalloc_node ( - SIZE * COUNT + COUNT, SIZE , ...) // 3-factor product with 1 sizeof(type) or sizeof(expression), with // redundant parens removed. @@ expression THING; identifier STRIDE, COUNT; type TYPE; @@ ( kzalloc_node( - sizeof(TYPE) * (COUNT) * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kzalloc_node( - sizeof(TYPE) * (COUNT) * STRIDE + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kzalloc_node( - sizeof(TYPE) * COUNT * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kzalloc_node( - sizeof(TYPE) * COUNT * STRIDE + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kzalloc_node( - sizeof(THING) * (COUNT) * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kzalloc_node( - sizeof(THING) * (COUNT) * STRIDE + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kzalloc_node( - sizeof(THING) * COUNT * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kzalloc_node( - sizeof(THING) * COUNT * STRIDE + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) ) // 3-factor product with 2 sizeof(variable), with redundant parens removed. @@ expression THING1, THING2; identifier COUNT; type TYPE1, TYPE2; @@ ( kzalloc_node( - sizeof(TYPE1) * sizeof(TYPE2) * COUNT + array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2)) , ...) | kzalloc_node( - sizeof(TYPE1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2)) , ...) | kzalloc_node( - sizeof(THING1) * sizeof(THING2) * COUNT + array3_size(COUNT, sizeof(THING1), sizeof(THING2)) , ...) | kzalloc_node( - sizeof(THING1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(THING1), sizeof(THING2)) , ...) | kzalloc_node( - sizeof(TYPE1) * sizeof(THING2) * COUNT + array3_size(COUNT, sizeof(TYPE1), sizeof(THING2)) , ...) | kzalloc_node( - sizeof(TYPE1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(TYPE1), sizeof(THING2)) , ...) ) // 3-factor product, only identifiers, with redundant parens removed. @@ identifier STRIDE, SIZE, COUNT; @@ ( kzalloc_node( - (COUNT) * STRIDE * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc_node( - COUNT * (STRIDE) * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc_node( - COUNT * STRIDE * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc_node( - (COUNT) * (STRIDE) * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc_node( - COUNT * (STRIDE) * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc_node( - (COUNT) * STRIDE * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc_node( - (COUNT) * (STRIDE) * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc_node( - COUNT * STRIDE * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) ) // Any remaining multi-factor products, first at least 3-factor products, // when they're not all constants... @@ expression E1, E2, E3; constant C1, C2, C3; @@ ( kzalloc_node(C1 * C2 * C3, ...) | kzalloc_node( - (E1) * E2 * E3 + array3_size(E1, E2, E3) , ...) | kzalloc_node( - (E1) * (E2) * E3 + array3_size(E1, E2, E3) , ...) | kzalloc_node( - (E1) * (E2) * (E3) + array3_size(E1, E2, E3) , ...) | kzalloc_node( - E1 * E2 * E3 + array3_size(E1, E2, E3) , ...) ) // And then all remaining 2 factors products when they're not all constants, // keeping sizeof() as the second factor argument. @@ expression THING, E1, E2; type TYPE; constant C1, C2, C3; @@ ( kzalloc_node(sizeof(THING) * C2, ...) | kzalloc_node(sizeof(TYPE) * C2, ...) | kzalloc_node(C1 * C2 * C3, ...) | kzalloc_node(C1 * C2, ...) | - kzalloc_node + kcalloc_node ( - sizeof(TYPE) * (E2) + E2, sizeof(TYPE) , ...) | - kzalloc_node + kcalloc_node ( - sizeof(TYPE) * E2 + E2, sizeof(TYPE) , ...) | - kzalloc_node + kcalloc_node ( - sizeof(THING) * (E2) + E2, sizeof(THING) , ...) | - kzalloc_node + kcalloc_node ( - sizeof(THING) * E2 + E2, sizeof(THING) , ...) | - kzalloc_node + kcalloc_node ( - (E1) * E2 + E1, E2 , ...) | - kzalloc_node + kcalloc_node ( - (E1) * (E2) + E1, E2 , ...) | - kzalloc_node + kcalloc_node ( - E1 * E2 + E1, E2 , ...) ) Signed-off-by: Kees Cook <keescook@chromium.org>
2018-06-13 05:04:20 +08:00
sb->map = kcalloc_node(sb->map_nr, sizeof(*sb->map), flags, node);
if (!sb->map)
return -ENOMEM;
for (i = 0; i < sb->map_nr; i++) {
sb->map[i].depth = min(depth, bits_per_word);
depth -= sb->map[i].depth;
spin_lock_init(&sb->map[i].swap_lock);
}
return 0;
}
EXPORT_SYMBOL_GPL(sbitmap_init_node);
void sbitmap_resize(struct sbitmap *sb, unsigned int depth)
{
unsigned int bits_per_word = 1U << sb->shift;
unsigned int i;
for (i = 0; i < sb->map_nr; i++)
sbitmap_deferred_clear(sb, i);
sb->depth = depth;
sb->map_nr = DIV_ROUND_UP(sb->depth, bits_per_word);
for (i = 0; i < sb->map_nr; i++) {
sb->map[i].depth = min(depth, bits_per_word);
depth -= sb->map[i].depth;
}
}
EXPORT_SYMBOL_GPL(sbitmap_resize);
static int __sbitmap_get_word(unsigned long *word, unsigned long depth,
unsigned int hint, bool wrap)
{
unsigned int orig_hint = hint;
int nr;
while (1) {
nr = find_next_zero_bit(word, depth, hint);
if (unlikely(nr >= depth)) {
/*
* We started with an offset, and we didn't reset the
* offset to 0 in a failure case, so start from 0 to
* exhaust the map.
*/
if (orig_hint && hint && wrap) {
hint = orig_hint = 0;
continue;
}
return -1;
}
if (!test_and_set_bit_lock(nr, word))
break;
hint = nr + 1;
if (hint >= depth - 1)
hint = 0;
}
return nr;
}
static int sbitmap_find_bit_in_index(struct sbitmap *sb, int index,
unsigned int alloc_hint, bool round_robin)
{
int nr;
do {
nr = __sbitmap_get_word(&sb->map[index].word,
sb->map[index].depth, alloc_hint,
!round_robin);
if (nr != -1)
break;
if (!sbitmap_deferred_clear(sb, index))
break;
} while (1);
return nr;
}
int sbitmap_get(struct sbitmap *sb, unsigned int alloc_hint, bool round_robin)
{
unsigned int i, index;
int nr = -1;
index = SB_NR_TO_INDEX(sb, alloc_hint);
/*
* Unless we're doing round robin tag allocation, just use the
* alloc_hint to find the right word index. No point in looping
* twice in find_next_zero_bit() for that case.
*/
if (round_robin)
alloc_hint = SB_NR_TO_BIT(sb, alloc_hint);
else
alloc_hint = 0;
for (i = 0; i < sb->map_nr; i++) {
nr = sbitmap_find_bit_in_index(sb, index, alloc_hint,
round_robin);
if (nr != -1) {
nr += index << sb->shift;
break;
}
/* Jump to next index. */
alloc_hint = 0;
if (++index >= sb->map_nr)
index = 0;
}
return nr;
}
EXPORT_SYMBOL_GPL(sbitmap_get);
int sbitmap_get_shallow(struct sbitmap *sb, unsigned int alloc_hint,
unsigned long shallow_depth)
{
unsigned int i, index;
int nr = -1;
index = SB_NR_TO_INDEX(sb, alloc_hint);
for (i = 0; i < sb->map_nr; i++) {
again:
nr = __sbitmap_get_word(&sb->map[index].word,
min(sb->map[index].depth, shallow_depth),
SB_NR_TO_BIT(sb, alloc_hint), true);
if (nr != -1) {
nr += index << sb->shift;
break;
}
if (sbitmap_deferred_clear(sb, index))
goto again;
/* Jump to next index. */
index++;
alloc_hint = index << sb->shift;
if (index >= sb->map_nr) {
index = 0;
alloc_hint = 0;
}
}
return nr;
}
EXPORT_SYMBOL_GPL(sbitmap_get_shallow);
bool sbitmap_any_bit_set(const struct sbitmap *sb)
{
unsigned int i;
for (i = 0; i < sb->map_nr; i++) {
if (sb->map[i].word & ~sb->map[i].cleared)
return true;
}
return false;
}
EXPORT_SYMBOL_GPL(sbitmap_any_bit_set);
static unsigned int __sbitmap_weight(const struct sbitmap *sb, bool set)
{
unsigned int i, weight = 0;
for (i = 0; i < sb->map_nr; i++) {
const struct sbitmap_word *word = &sb->map[i];
if (set)
weight += bitmap_weight(&word->word, word->depth);
else
weight += bitmap_weight(&word->cleared, word->depth);
}
return weight;
}
static unsigned int sbitmap_weight(const struct sbitmap *sb)
{
return __sbitmap_weight(sb, true);
}
static unsigned int sbitmap_cleared(const struct sbitmap *sb)
{
return __sbitmap_weight(sb, false);
}
void sbitmap_show(struct sbitmap *sb, struct seq_file *m)
{
seq_printf(m, "depth=%u\n", sb->depth);
seq_printf(m, "busy=%u\n", sbitmap_weight(sb) - sbitmap_cleared(sb));
seq_printf(m, "cleared=%u\n", sbitmap_cleared(sb));
seq_printf(m, "bits_per_word=%u\n", 1U << sb->shift);
seq_printf(m, "map_nr=%u\n", sb->map_nr);
}
EXPORT_SYMBOL_GPL(sbitmap_show);
static inline void emit_byte(struct seq_file *m, unsigned int offset, u8 byte)
{
if ((offset & 0xf) == 0) {
if (offset != 0)
seq_putc(m, '\n');
seq_printf(m, "%08x:", offset);
}
if ((offset & 0x1) == 0)
seq_putc(m, ' ');
seq_printf(m, "%02x", byte);
}
void sbitmap_bitmap_show(struct sbitmap *sb, struct seq_file *m)
{
u8 byte = 0;
unsigned int byte_bits = 0;
unsigned int offset = 0;
int i;
for (i = 0; i < sb->map_nr; i++) {
unsigned long word = READ_ONCE(sb->map[i].word);
unsigned int word_bits = READ_ONCE(sb->map[i].depth);
while (word_bits > 0) {
unsigned int bits = min(8 - byte_bits, word_bits);
byte |= (word & (BIT(bits) - 1)) << byte_bits;
byte_bits += bits;
if (byte_bits == 8) {
emit_byte(m, offset, byte);
byte = 0;
byte_bits = 0;
offset++;
}
word >>= bits;
word_bits -= bits;
}
}
if (byte_bits) {
emit_byte(m, offset, byte);
offset++;
}
if (offset)
seq_putc(m, '\n');
}
EXPORT_SYMBOL_GPL(sbitmap_bitmap_show);
static unsigned int sbq_calc_wake_batch(struct sbitmap_queue *sbq,
unsigned int depth)
{
unsigned int wake_batch;
unsigned int shallow_depth;
/*
* For each batch, we wake up one queue. We need to make sure that our
* batch size is small enough that the full depth of the bitmap,
* potentially limited by a shallow depth, is enough to wake up all of
* the queues.
*
* Each full word of the bitmap has bits_per_word bits, and there might
* be a partial word. There are depth / bits_per_word full words and
* depth % bits_per_word bits left over. In bitwise arithmetic:
*
* bits_per_word = 1 << shift
* depth / bits_per_word = depth >> shift
* depth % bits_per_word = depth & ((1 << shift) - 1)
*
* Each word can be limited to sbq->min_shallow_depth bits.
*/
shallow_depth = min(1U << sbq->sb.shift, sbq->min_shallow_depth);
depth = ((depth >> sbq->sb.shift) * shallow_depth +
min(depth & ((1U << sbq->sb.shift) - 1), shallow_depth));
wake_batch = clamp_t(unsigned int, depth / SBQ_WAIT_QUEUES, 1,
SBQ_WAKE_BATCH);
return wake_batch;
}
int sbitmap_queue_init_node(struct sbitmap_queue *sbq, unsigned int depth,
int shift, bool round_robin, gfp_t flags, int node)
{
int ret;
int i;
ret = sbitmap_init_node(&sbq->sb, depth, shift, flags, node);
if (ret)
return ret;
sbq->alloc_hint = alloc_percpu_gfp(unsigned int, flags);
if (!sbq->alloc_hint) {
sbitmap_free(&sbq->sb);
return -ENOMEM;
}
if (depth && !round_robin) {
for_each_possible_cpu(i)
*per_cpu_ptr(sbq->alloc_hint, i) = prandom_u32() % depth;
}
sbq->min_shallow_depth = UINT_MAX;
sbq->wake_batch = sbq_calc_wake_batch(sbq, depth);
atomic_set(&sbq->wake_index, 0);
atomic_set(&sbq->ws_active, 0);
sbq->ws = kzalloc_node(SBQ_WAIT_QUEUES * sizeof(*sbq->ws), flags, node);
if (!sbq->ws) {
free_percpu(sbq->alloc_hint);
sbitmap_free(&sbq->sb);
return -ENOMEM;
}
for (i = 0; i < SBQ_WAIT_QUEUES; i++) {
init_waitqueue_head(&sbq->ws[i].wait);
atomic_set(&sbq->ws[i].wait_cnt, sbq->wake_batch);
}
sbq->round_robin = round_robin;
return 0;
}
EXPORT_SYMBOL_GPL(sbitmap_queue_init_node);
static void sbitmap_queue_update_wake_batch(struct sbitmap_queue *sbq,
unsigned int depth)
{
unsigned int wake_batch = sbq_calc_wake_batch(sbq, depth);
int i;
if (sbq->wake_batch != wake_batch) {
WRITE_ONCE(sbq->wake_batch, wake_batch);
/*
* Pairs with the memory barrier in sbitmap_queue_wake_up()
* to ensure that the batch size is updated before the wait
* counts.
*/
smp_mb();
for (i = 0; i < SBQ_WAIT_QUEUES; i++)
atomic_set(&sbq->ws[i].wait_cnt, 1);
}
}
void sbitmap_queue_resize(struct sbitmap_queue *sbq, unsigned int depth)
{
sbitmap_queue_update_wake_batch(sbq, depth);
sbitmap_resize(&sbq->sb, depth);
}
EXPORT_SYMBOL_GPL(sbitmap_queue_resize);
int __sbitmap_queue_get(struct sbitmap_queue *sbq)
{
unsigned int hint, depth;
int nr;
hint = this_cpu_read(*sbq->alloc_hint);
depth = READ_ONCE(sbq->sb.depth);
if (unlikely(hint >= depth)) {
hint = depth ? prandom_u32() % depth : 0;
this_cpu_write(*sbq->alloc_hint, hint);
}
nr = sbitmap_get(&sbq->sb, hint, sbq->round_robin);
if (nr == -1) {
/* If the map is full, a hint won't do us much good. */
this_cpu_write(*sbq->alloc_hint, 0);
} else if (nr == hint || unlikely(sbq->round_robin)) {
/* Only update the hint if we used it. */
hint = nr + 1;
if (hint >= depth - 1)
hint = 0;
this_cpu_write(*sbq->alloc_hint, hint);
}
return nr;
}
EXPORT_SYMBOL_GPL(__sbitmap_queue_get);
int __sbitmap_queue_get_shallow(struct sbitmap_queue *sbq,
unsigned int shallow_depth)
{
unsigned int hint, depth;
int nr;
WARN_ON_ONCE(shallow_depth < sbq->min_shallow_depth);
hint = this_cpu_read(*sbq->alloc_hint);
depth = READ_ONCE(sbq->sb.depth);
if (unlikely(hint >= depth)) {
hint = depth ? prandom_u32() % depth : 0;
this_cpu_write(*sbq->alloc_hint, hint);
}
nr = sbitmap_get_shallow(&sbq->sb, hint, shallow_depth);
if (nr == -1) {
/* If the map is full, a hint won't do us much good. */
this_cpu_write(*sbq->alloc_hint, 0);
} else if (nr == hint || unlikely(sbq->round_robin)) {
/* Only update the hint if we used it. */
hint = nr + 1;
if (hint >= depth - 1)
hint = 0;
this_cpu_write(*sbq->alloc_hint, hint);
}
return nr;
}
EXPORT_SYMBOL_GPL(__sbitmap_queue_get_shallow);
void sbitmap_queue_min_shallow_depth(struct sbitmap_queue *sbq,
unsigned int min_shallow_depth)
{
sbq->min_shallow_depth = min_shallow_depth;
sbitmap_queue_update_wake_batch(sbq, sbq->sb.depth);
}
EXPORT_SYMBOL_GPL(sbitmap_queue_min_shallow_depth);
static struct sbq_wait_state *sbq_wake_ptr(struct sbitmap_queue *sbq)
{
int i, wake_index;
if (!atomic_read(&sbq->ws_active))
return NULL;
wake_index = atomic_read(&sbq->wake_index);
for (i = 0; i < SBQ_WAIT_QUEUES; i++) {
struct sbq_wait_state *ws = &sbq->ws[wake_index];
if (waitqueue_active(&ws->wait)) {
if (wake_index != atomic_read(&sbq->wake_index))
atomic_set(&sbq->wake_index, wake_index);
return ws;
}
wake_index = sbq_index_inc(wake_index);
}
return NULL;
}
static bool __sbq_wake_up(struct sbitmap_queue *sbq)
{
struct sbq_wait_state *ws;
unsigned int wake_batch;
int wait_cnt;
ws = sbq_wake_ptr(sbq);
if (!ws)
return false;
wait_cnt = atomic_dec_return(&ws->wait_cnt);
if (wait_cnt <= 0) {
int ret;
wake_batch = READ_ONCE(sbq->wake_batch);
/*
* Pairs with the memory barrier in sbitmap_queue_resize() to
* ensure that we see the batch size update before the wait
* count is reset.
*/
smp_mb__before_atomic();
/*
* For concurrent callers of this, the one that failed the
* atomic_cmpxhcg() race should call this function again
* to wakeup a new batch on a different 'ws'.
*/
ret = atomic_cmpxchg(&ws->wait_cnt, wait_cnt, wake_batch);
if (ret == wait_cnt) {
sbq_index_atomic_inc(&sbq->wake_index);
wake_up_nr(&ws->wait, wake_batch);
return false;
}
return true;
}
return false;
}
void sbitmap_queue_wake_up(struct sbitmap_queue *sbq)
{
while (__sbq_wake_up(sbq))
;
}
EXPORT_SYMBOL_GPL(sbitmap_queue_wake_up);
void sbitmap_queue_clear(struct sbitmap_queue *sbq, unsigned int nr,
unsigned int cpu)
{
sbitmap: order READ/WRITE freed instance and setting clear bit Inside sbitmap_queue_clear(), once the clear bit is set, it will be visiable to allocation path immediately. Meantime READ/WRITE on old associated instance(such as request in case of blk-mq) may be out-of-order with the setting clear bit, so race with re-allocation may be triggered. Adds one memory barrier for ordering READ/WRITE of the freed associated instance with setting clear bit for avoiding race with re-allocation. The following kernel oops triggerd by block/006 on aarch64 may be fixed: [ 142.330954] Unable to handle kernel NULL pointer dereference at virtual address 0000000000000330 [ 142.338794] Mem abort info: [ 142.341554] ESR = 0x96000005 [ 142.344632] Exception class = DABT (current EL), IL = 32 bits [ 142.350500] SET = 0, FnV = 0 [ 142.353544] EA = 0, S1PTW = 0 [ 142.356678] Data abort info: [ 142.359528] ISV = 0, ISS = 0x00000005 [ 142.363343] CM = 0, WnR = 0 [ 142.366305] user pgtable: 64k pages, 48-bit VAs, pgdp = 000000002a3c51c0 [ 142.372983] [0000000000000330] pgd=0000000000000000, pud=0000000000000000 [ 142.379777] Internal error: Oops: 96000005 [#1] SMP [ 142.384613] Modules linked in: null_blk ib_isert iscsi_target_mod ib_srpt target_core_mod ib_srp scsi_transport_srp vfat fat rpcrdma sunrpc rdma_ucm ib_iser rdma_cm iw_cm libiscsi ib_umad scsi_transport_iscsi ib_ipoib ib_cm mlx5_ib ib_uverbs ib_core sbsa_gwdt crct10dif_ce ghash_ce ipmi_ssif sha2_ce ipmi_devintf sha256_arm64 sg sha1_ce ipmi_msghandler ip_tables xfs libcrc32c mlx5_core sdhci_acpi mlxfw ahci_platform at803x sdhci libahci_platform qcom_emac mmc_core hdma hdma_mgmt i2c_dev [last unloaded: null_blk] [ 142.429753] CPU: 7 PID: 1983 Comm: fio Not tainted 5.0.0.cki #2 [ 142.449458] pstate: 00400005 (nzcv daif +PAN -UAO) [ 142.454239] pc : __blk_mq_free_request+0x4c/0xa8 [ 142.458830] lr : blk_mq_free_request+0xec/0x118 [ 142.463344] sp : ffff00003360f6a0 [ 142.466646] x29: ffff00003360f6a0 x28: ffff000010e70000 [ 142.471941] x27: ffff801729a50048 x26: 0000000000010000 [ 142.477232] x25: ffff00003360f954 x24: ffff7bdfff021440 [ 142.482529] x23: 0000000000000000 x22: 00000000ffffffff [ 142.487830] x21: ffff801729810000 x20: 0000000000000000 [ 142.493123] x19: ffff801729a50000 x18: 0000000000000000 [ 142.498413] x17: 0000000000000000 x16: 0000000000000001 [ 142.503709] x15: 00000000000000ff x14: ffff7fe000000000 [ 142.509003] x13: ffff8017dcde09a0 x12: 0000000000000000 [ 142.514308] x11: 0000000000000001 x10: 0000000000000008 [ 142.519597] x9 : ffff8017dcde09a0 x8 : 0000000000002000 [ 142.524889] x7 : ffff8017dcde0a00 x6 : 000000015388f9be [ 142.530187] x5 : 0000000000000001 x4 : 0000000000000000 [ 142.535478] x3 : 0000000000000000 x2 : 0000000000000000 [ 142.540777] x1 : 0000000000000001 x0 : ffff00001041b194 [ 142.546071] Process fio (pid: 1983, stack limit = 0x000000006460a0ea) [ 142.552500] Call trace: [ 142.554926] __blk_mq_free_request+0x4c/0xa8 [ 142.559181] blk_mq_free_request+0xec/0x118 [ 142.563352] blk_mq_end_request+0xfc/0x120 [ 142.567444] end_cmd+0x3c/0xa8 [null_blk] [ 142.571434] null_complete_rq+0x20/0x30 [null_blk] [ 142.576194] blk_mq_complete_request+0x108/0x148 [ 142.580797] null_handle_cmd+0x1d4/0x718 [null_blk] [ 142.585662] null_queue_rq+0x60/0xa8 [null_blk] [ 142.590171] blk_mq_try_issue_directly+0x148/0x280 [ 142.594949] blk_mq_try_issue_list_directly+0x9c/0x108 [ 142.600064] blk_mq_sched_insert_requests+0xb0/0xd0 [ 142.604926] blk_mq_flush_plug_list+0x16c/0x2a0 [ 142.609441] blk_flush_plug_list+0xec/0x118 [ 142.613608] blk_finish_plug+0x3c/0x4c [ 142.617348] blkdev_direct_IO+0x3b4/0x428 [ 142.621336] generic_file_read_iter+0x84/0x180 [ 142.625761] blkdev_read_iter+0x50/0x78 [ 142.629579] aio_read.isra.6+0xf8/0x190 [ 142.633409] __io_submit_one.isra.8+0x148/0x738 [ 142.637912] io_submit_one.isra.9+0x88/0xb8 [ 142.642078] __arm64_sys_io_submit+0xe0/0x238 [ 142.646428] el0_svc_handler+0xa0/0x128 [ 142.650238] el0_svc+0x8/0xc [ 142.653104] Code: b9402a63 f9000a7f 3100047f 540000a0 (f9419a81) [ 142.659202] ---[ end trace 467586bc175eb09d ]--- Fixes: ea86ea2cdced20057da ("sbitmap: ammortize cost of clearing bits") Reported-and-bisected_and_tested-by: Yi Zhang <yi.zhang@redhat.com> Cc: Yi Zhang <yi.zhang@redhat.com> Cc: "jianchao.wang" <jianchao.w.wang@oracle.com> Reviewed-by: Omar Sandoval <osandov@fb.com> Signed-off-by: Ming Lei <ming.lei@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2019-03-22 09:13:51 +08:00
/*
* Once the clear bit is set, the bit may be allocated out.
*
* Orders READ/WRITE on the asssociated instance(such as request
* of blk_mq) by this bit for avoiding race with re-allocation,
* and its pair is the memory barrier implied in __sbitmap_get_word.
*
* One invariant is that the clear bit has to be zero when the bit
* is in use.
*/
smp_mb__before_atomic();
sbitmap_deferred_clear_bit(&sbq->sb, nr);
/*
* Pairs with the memory barrier in set_current_state() to ensure the
* proper ordering of clear_bit_unlock()/waitqueue_active() in the waker
* and test_and_set_bit_lock()/prepare_to_wait()/finish_wait() in the
* waiter. See the comment on waitqueue_active().
*/
smp_mb__after_atomic();
sbitmap_queue_wake_up(sbq);
if (likely(!sbq->round_robin && nr < sbq->sb.depth))
*per_cpu_ptr(sbq->alloc_hint, cpu) = nr;
}
EXPORT_SYMBOL_GPL(sbitmap_queue_clear);
void sbitmap_queue_wake_all(struct sbitmap_queue *sbq)
{
int i, wake_index;
/*
* Pairs with the memory barrier in set_current_state() like in
* sbitmap_queue_wake_up().
*/
smp_mb();
wake_index = atomic_read(&sbq->wake_index);
for (i = 0; i < SBQ_WAIT_QUEUES; i++) {
struct sbq_wait_state *ws = &sbq->ws[wake_index];
if (waitqueue_active(&ws->wait))
wake_up(&ws->wait);
wake_index = sbq_index_inc(wake_index);
}
}
EXPORT_SYMBOL_GPL(sbitmap_queue_wake_all);
void sbitmap_queue_show(struct sbitmap_queue *sbq, struct seq_file *m)
{
bool first;
int i;
sbitmap_show(&sbq->sb, m);
seq_puts(m, "alloc_hint={");
first = true;
for_each_possible_cpu(i) {
if (!first)
seq_puts(m, ", ");
first = false;
seq_printf(m, "%u", *per_cpu_ptr(sbq->alloc_hint, i));
}
seq_puts(m, "}\n");
seq_printf(m, "wake_batch=%u\n", sbq->wake_batch);
seq_printf(m, "wake_index=%d\n", atomic_read(&sbq->wake_index));
seq_printf(m, "ws_active=%d\n", atomic_read(&sbq->ws_active));
seq_puts(m, "ws={\n");
for (i = 0; i < SBQ_WAIT_QUEUES; i++) {
struct sbq_wait_state *ws = &sbq->ws[i];
seq_printf(m, "\t{.wait_cnt=%d, .wait=%s},\n",
atomic_read(&ws->wait_cnt),
waitqueue_active(&ws->wait) ? "active" : "inactive");
}
seq_puts(m, "}\n");
seq_printf(m, "round_robin=%d\n", sbq->round_robin);
seq_printf(m, "min_shallow_depth=%u\n", sbq->min_shallow_depth);
}
EXPORT_SYMBOL_GPL(sbitmap_queue_show);
void sbitmap_add_wait_queue(struct sbitmap_queue *sbq,
struct sbq_wait_state *ws,
struct sbq_wait *sbq_wait)
{
if (!sbq_wait->sbq) {
sbq_wait->sbq = sbq;
atomic_inc(&sbq->ws_active);
sbitmap: only queue kyber's wait callback if not already active Under heavy loads where the kyber I/O scheduler hits the token limits for its scheduling domains, kyber can become stuck. When active requests complete, kyber may not be woken up leaving the I/O requests in kyber stuck. This stuck state is due to a race condition with kyber and the sbitmap functions it uses to run a callback when enough requests have completed. The running of a sbt_wait callback can race with the attempt to insert the sbt_wait. Since sbitmap_del_wait_queue removes the sbt_wait from the list first then sets the sbq field to NULL, kyber can see the item as not on a list but the call to sbitmap_add_wait_queue will see sbq as non-NULL. This results in the sbt_wait being inserted onto the wait list but ws_active doesn't get incremented. So the sbitmap queue does not know there is a waiter on a wait list. Since sbitmap doesn't think there is a waiter, kyber may never be informed that there are domain tokens available and the I/O never advances. With the sbt_wait on a wait list, kyber believes it has an active waiter so cannot insert a new waiter when reaching the domain's full state. This race can be fixed by only adding the sbt_wait to the queue if the sbq field is NULL. If sbq is not NULL, there is already an action active which will trigger the re-running of kyber. Let it run and add the sbt_wait to the wait list if still needing to wait. Reviewed-by: Omar Sandoval <osandov@fb.com> Signed-off-by: David Jeffery <djeffery@redhat.com> Reported-by: John Pittman <jpittman@redhat.com> Tested-by: John Pittman <jpittman@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2019-12-18 00:00:24 +08:00
add_wait_queue(&ws->wait, &sbq_wait->wait);
}
}
EXPORT_SYMBOL_GPL(sbitmap_add_wait_queue);
void sbitmap_del_wait_queue(struct sbq_wait *sbq_wait)
{
list_del_init(&sbq_wait->wait.entry);
if (sbq_wait->sbq) {
atomic_dec(&sbq_wait->sbq->ws_active);
sbq_wait->sbq = NULL;
}
}
EXPORT_SYMBOL_GPL(sbitmap_del_wait_queue);
void sbitmap_prepare_to_wait(struct sbitmap_queue *sbq,
struct sbq_wait_state *ws,
struct sbq_wait *sbq_wait, int state)
{
if (!sbq_wait->sbq) {
atomic_inc(&sbq->ws_active);
sbq_wait->sbq = sbq;
}
prepare_to_wait_exclusive(&ws->wait, &sbq_wait->wait, state);
}
EXPORT_SYMBOL_GPL(sbitmap_prepare_to_wait);
void sbitmap_finish_wait(struct sbitmap_queue *sbq, struct sbq_wait_state *ws,
struct sbq_wait *sbq_wait)
{
finish_wait(&ws->wait, &sbq_wait->wait);
if (sbq_wait->sbq) {
atomic_dec(&sbq->ws_active);
sbq_wait->sbq = NULL;
}
}
EXPORT_SYMBOL_GPL(sbitmap_finish_wait);