diff options
Diffstat (limited to 'lib')
-rw-r--r-- | lib/Makefile | 2 | ||||
-rw-r--r-- | lib/halfmd4.c | 67 | ||||
-rw-r--r-- | lib/sbitmap.c | 139 |
3 files changed, 132 insertions, 76 deletions
diff --git a/lib/Makefile b/lib/Makefile index bc4073a8cd08..19ea76149a37 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -31,7 +31,7 @@ lib-$(CONFIG_HAS_DMA) += dma-noop.o lib-y += kobject.o klist.o obj-y += lockref.o -obj-y += bcd.o div64.o sort.o parser.o halfmd4.o debug_locks.o random32.o \ +obj-y += bcd.o div64.o sort.o parser.o debug_locks.o random32.o \ bust_spinlocks.o kasprintf.o bitmap.o scatterlist.o \ gcd.o lcm.o list_sort.o uuid.o flex_array.o iov_iter.o clz_ctz.o \ bsearch.o find_bit.o llist.o memweight.o kfifo.o \ diff --git a/lib/halfmd4.c b/lib/halfmd4.c deleted file mode 100644 index 137e861d9690..000000000000 --- a/lib/halfmd4.c +++ /dev/null @@ -1,67 +0,0 @@ -#include <linux/compiler.h> -#include <linux/export.h> -#include <linux/cryptohash.h> -#include <linux/bitops.h> - -/* F, G and H are basic MD4 functions: selection, majority, parity */ -#define F(x, y, z) ((z) ^ ((x) & ((y) ^ (z)))) -#define G(x, y, z) (((x) & (y)) + (((x) ^ (y)) & (z))) -#define H(x, y, z) ((x) ^ (y) ^ (z)) - -/* - * The generic round function. The application is so specific that - * we don't bother protecting all the arguments with parens, as is generally - * good macro practice, in favor of extra legibility. - * Rotation is separate from addition to prevent recomputation - */ -#define ROUND(f, a, b, c, d, x, s) \ - (a += f(b, c, d) + x, a = rol32(a, s)) -#define K1 0 -#define K2 013240474631UL -#define K3 015666365641UL - -/* - * Basic cut-down MD4 transform. Returns only 32 bits of result. - */ -__u32 half_md4_transform(__u32 buf[4], __u32 const in[8]) -{ - __u32 a = buf[0], b = buf[1], c = buf[2], d = buf[3]; - - /* Round 1 */ - ROUND(F, a, b, c, d, in[0] + K1, 3); - ROUND(F, d, a, b, c, in[1] + K1, 7); - ROUND(F, c, d, a, b, in[2] + K1, 11); - ROUND(F, b, c, d, a, in[3] + K1, 19); - ROUND(F, a, b, c, d, in[4] + K1, 3); - ROUND(F, d, a, b, c, in[5] + K1, 7); - ROUND(F, c, d, a, b, in[6] + K1, 11); - ROUND(F, b, c, d, a, in[7] + K1, 19); - - /* Round 2 */ - ROUND(G, a, b, c, d, in[1] + K2, 3); - ROUND(G, d, a, b, c, in[3] + K2, 5); - ROUND(G, c, d, a, b, in[5] + K2, 9); - ROUND(G, b, c, d, a, in[7] + K2, 13); - ROUND(G, a, b, c, d, in[0] + K2, 3); - ROUND(G, d, a, b, c, in[2] + K2, 5); - ROUND(G, c, d, a, b, in[4] + K2, 9); - ROUND(G, b, c, d, a, in[6] + K2, 13); - - /* Round 3 */ - ROUND(H, a, b, c, d, in[3] + K3, 3); - ROUND(H, d, a, b, c, in[7] + K3, 9); - ROUND(H, c, d, a, b, in[2] + K3, 11); - ROUND(H, b, c, d, a, in[6] + K3, 15); - ROUND(H, a, b, c, d, in[1] + K3, 3); - ROUND(H, d, a, b, c, in[5] + K3, 9); - ROUND(H, c, d, a, b, in[0] + K3, 11); - ROUND(H, b, c, d, a, in[4] + K3, 15); - - buf[0] += a; - buf[1] += b; - buf[2] += c; - buf[3] += d; - - return buf[1]; /* "most hashed" word */ -} -EXPORT_SYMBOL(half_md4_transform); diff --git a/lib/sbitmap.c b/lib/sbitmap.c index 2cecf05c82fd..55e11c4b2f3b 100644 --- a/lib/sbitmap.c +++ b/lib/sbitmap.c @@ -17,6 +17,7 @@ #include <linux/random.h> #include <linux/sbitmap.h> +#include <linux/seq_file.h> int sbitmap_init_node(struct sbitmap *sb, unsigned int depth, int shift, gfp_t flags, int node) @@ -180,6 +181,62 @@ unsigned int sbitmap_weight(const struct sbitmap *sb) } EXPORT_SYMBOL_GPL(sbitmap_weight); +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)); + 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(unsigned int depth) { unsigned int wake_batch; @@ -239,7 +296,19 @@ EXPORT_SYMBOL_GPL(sbitmap_queue_init_node); void sbitmap_queue_resize(struct sbitmap_queue *sbq, unsigned int depth) { - sbq->wake_batch = sbq_calc_wake_batch(depth); + unsigned int wake_batch = sbq_calc_wake_batch(depth); + int i; + + if (sbq->wake_batch != wake_batch) { + WRITE_ONCE(sbq->wake_batch, wake_batch); + /* + * Pairs with the memory barrier in sbq_wake_up() to ensure that + * the batch size is updated before the wait counts. + */ + smp_mb__before_atomic(); + for (i = 0; i < SBQ_WAIT_QUEUES; i++) + atomic_set(&sbq->ws[i].wait_cnt, 1); + } sbitmap_resize(&sbq->sb, depth); } EXPORT_SYMBOL_GPL(sbitmap_queue_resize); @@ -297,20 +366,39 @@ static struct sbq_wait_state *sbq_wake_ptr(struct sbitmap_queue *sbq) static void sbq_wake_up(struct sbitmap_queue *sbq) { struct sbq_wait_state *ws; + unsigned int wake_batch; int wait_cnt; - /* Ensure that the wait list checks occur after clear_bit(). */ - smp_mb(); + /* + * Pairs with the memory barrier in set_current_state() to ensure the + * proper ordering of clear_bit()/waitqueue_active() in the waker and + * test_and_set_bit()/prepare_to_wait()/finish_wait() in the waiter. See + * the comment on waitqueue_active(). This is __after_atomic because we + * just did clear_bit() in the caller. + */ + smp_mb__after_atomic(); ws = sbq_wake_ptr(sbq); if (!ws) return; wait_cnt = atomic_dec_return(&ws->wait_cnt); - if (unlikely(wait_cnt < 0)) - wait_cnt = atomic_inc_return(&ws->wait_cnt); - if (wait_cnt == 0) { - atomic_add(sbq->wake_batch, &ws->wait_cnt); + if (wait_cnt <= 0) { + 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(); + /* + * If there are concurrent callers to sbq_wake_up(), the last + * one to decrement the wait count below zero will bump it back + * up. If there is a concurrent resize, the count reset will + * either cause the cmpxchg to fail or overwrite after the + * cmpxchg. + */ + atomic_cmpxchg(&ws->wait_cnt, wait_cnt, wait_cnt + wake_batch); sbq_index_atomic_inc(&sbq->wake_index); wake_up(&ws->wait); } @@ -331,7 +419,8 @@ void sbitmap_queue_wake_all(struct sbitmap_queue *sbq) int i, wake_index; /* - * Make sure all changes prior to this are visible from other CPUs. + * Pairs with the memory barrier in set_current_state() like in + * sbq_wake_up(). */ smp_mb(); wake_index = atomic_read(&sbq->wake_index); @@ -345,3 +434,37 @@ void sbitmap_queue_wake_all(struct sbitmap_queue *sbq) } } 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_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); +} +EXPORT_SYMBOL_GPL(sbitmap_queue_show); |