Commit 10a6d72e authored by Herbert Xu's avatar Herbert Xu
Browse files

crypto: lib/poly1305 - Use block-only interface



Now that every architecture provides a block function, use that
to implement the lib/poly1305 and remove the old per-arch code.

Signed-off-by: default avatarHerbert Xu <herbert@gondor.apana.org.au>
parent ceef731b
Loading
Loading
Loading
Loading
+0 −57
Original line number Diff line number Diff line
@@ -12,7 +12,6 @@
#include <linux/jump_label.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/string.h>
#include <linux/unaligned.h>

asmlinkage void poly1305_block_init_arch(
@@ -35,17 +34,6 @@ void __weak poly1305_blocks_neon(struct poly1305_block_state *state,

static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_neon);

void poly1305_init_arch(struct poly1305_desc_ctx *dctx, const u8 key[POLY1305_KEY_SIZE])
{
	dctx->s[0] = get_unaligned_le32(key + 16);
	dctx->s[1] = get_unaligned_le32(key + 20);
	dctx->s[2] = get_unaligned_le32(key + 24);
	dctx->s[3] = get_unaligned_le32(key + 28);
	dctx->buflen = 0;
	poly1305_block_init_arch(&dctx->state, key);
}
EXPORT_SYMBOL(poly1305_init_arch);

void poly1305_blocks_arch(struct poly1305_block_state *state, const u8 *src,
			  unsigned int len, u32 padbit)
{
@@ -67,51 +55,6 @@ void poly1305_blocks_arch(struct poly1305_block_state *state, const u8 *src,
}
EXPORT_SYMBOL_GPL(poly1305_blocks_arch);

void poly1305_update_arch(struct poly1305_desc_ctx *dctx, const u8 *src,
			  unsigned int nbytes)
{
	if (unlikely(dctx->buflen)) {
		u32 bytes = min(nbytes, POLY1305_BLOCK_SIZE - dctx->buflen);

		memcpy(dctx->buf + dctx->buflen, src, bytes);
		src += bytes;
		nbytes -= bytes;
		dctx->buflen += bytes;

		if (dctx->buflen == POLY1305_BLOCK_SIZE) {
			poly1305_blocks_arch(&dctx->state, dctx->buf,
					     POLY1305_BLOCK_SIZE, 1);
			dctx->buflen = 0;
		}
	}

	if (likely(nbytes >= POLY1305_BLOCK_SIZE)) {
		poly1305_blocks_arch(&dctx->state, src, nbytes, 1);
		src += round_down(nbytes, POLY1305_BLOCK_SIZE);
		nbytes %= POLY1305_BLOCK_SIZE;
	}

	if (unlikely(nbytes)) {
		dctx->buflen = nbytes;
		memcpy(dctx->buf, src, nbytes);
	}
}
EXPORT_SYMBOL(poly1305_update_arch);

void poly1305_final_arch(struct poly1305_desc_ctx *dctx, u8 *dst)
{
	if (unlikely(dctx->buflen)) {
		dctx->buf[dctx->buflen++] = 1;
		memset(dctx->buf + dctx->buflen, 0,
		       POLY1305_BLOCK_SIZE - dctx->buflen);
		poly1305_blocks_arch(&dctx->state, dctx->buf, POLY1305_BLOCK_SIZE, 0);
	}

	poly1305_emit_arch(&dctx->h, dst, dctx->s);
	*dctx = (struct poly1305_desc_ctx){};
}
EXPORT_SYMBOL(poly1305_final_arch);

bool poly1305_is_arch_optimized(void)
{
	/* We always can use at least the ARM scalar implementation. */
+0 −58
Original line number Diff line number Diff line
@@ -12,7 +12,6 @@
#include <linux/jump_label.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/string.h>
#include <linux/unaligned.h>

asmlinkage void poly1305_block_init_arch(
@@ -30,17 +29,6 @@ EXPORT_SYMBOL_GPL(poly1305_emit_arch);

static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_neon);

void poly1305_init_arch(struct poly1305_desc_ctx *dctx, const u8 key[POLY1305_KEY_SIZE])
{
	dctx->s[0] = get_unaligned_le32(key + 16);
	dctx->s[1] = get_unaligned_le32(key + 20);
	dctx->s[2] = get_unaligned_le32(key + 24);
	dctx->s[3] = get_unaligned_le32(key + 28);
	dctx->buflen = 0;
	poly1305_block_init_arch(&dctx->state, key);
}
EXPORT_SYMBOL(poly1305_init_arch);

void poly1305_blocks_arch(struct poly1305_block_state *state, const u8 *src,
			  unsigned int len, u32 padbit)
{
@@ -61,52 +49,6 @@ void poly1305_blocks_arch(struct poly1305_block_state *state, const u8 *src,
}
EXPORT_SYMBOL_GPL(poly1305_blocks_arch);

void poly1305_update_arch(struct poly1305_desc_ctx *dctx, const u8 *src,
			  unsigned int nbytes)
{
	if (unlikely(dctx->buflen)) {
		u32 bytes = min(nbytes, POLY1305_BLOCK_SIZE - dctx->buflen);

		memcpy(dctx->buf + dctx->buflen, src, bytes);
		src += bytes;
		nbytes -= bytes;
		dctx->buflen += bytes;

		if (dctx->buflen == POLY1305_BLOCK_SIZE) {
			poly1305_blocks_arch(&dctx->state, dctx->buf,
					     POLY1305_BLOCK_SIZE, 1);
			dctx->buflen = 0;
		}
	}

	if (likely(nbytes >= POLY1305_BLOCK_SIZE)) {
		poly1305_blocks_arch(&dctx->state, src, nbytes, 1);
		src += round_down(nbytes, POLY1305_BLOCK_SIZE);
		nbytes %= POLY1305_BLOCK_SIZE;
	}

	if (unlikely(nbytes)) {
		dctx->buflen = nbytes;
		memcpy(dctx->buf, src, nbytes);
	}
}
EXPORT_SYMBOL(poly1305_update_arch);

void poly1305_final_arch(struct poly1305_desc_ctx *dctx, u8 *dst)
{
	if (unlikely(dctx->buflen)) {
		dctx->buf[dctx->buflen++] = 1;
		memset(dctx->buf + dctx->buflen, 0,
		       POLY1305_BLOCK_SIZE - dctx->buflen);
		poly1305_blocks_arch(&dctx->state, dctx->buf,
				     POLY1305_BLOCK_SIZE, 0);
	}

	poly1305_emit_arch(&dctx->h, dst, dctx->s);
	memzero_explicit(dctx, sizeof(*dctx));
}
EXPORT_SYMBOL(poly1305_final_arch);

bool poly1305_is_arch_optimized(void)
{
	/* We always can use at least the ARM64 scalar implementation. */
+0 −60
Original line number Diff line number Diff line
@@ -9,7 +9,6 @@
#include <linux/cpufeature.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/string.h>
#include <linux/unaligned.h>

asmlinkage void poly1305_block_init_arch(
@@ -24,65 +23,6 @@ asmlinkage void poly1305_emit_arch(const struct poly1305_state *state,
				   const u32 nonce[4]);
EXPORT_SYMBOL_GPL(poly1305_emit_arch);

void poly1305_init_arch(struct poly1305_desc_ctx *dctx, const u8 key[POLY1305_KEY_SIZE])
{
	dctx->s[0] = get_unaligned_le32(key + 16);
	dctx->s[1] = get_unaligned_le32(key + 20);
	dctx->s[2] = get_unaligned_le32(key + 24);
	dctx->s[3] = get_unaligned_le32(key + 28);
	dctx->buflen = 0;
	poly1305_block_init_arch(&dctx->state, key);
}
EXPORT_SYMBOL(poly1305_init_arch);

void poly1305_update_arch(struct poly1305_desc_ctx *dctx, const u8 *src,
			  unsigned int nbytes)
{
	if (unlikely(dctx->buflen)) {
		u32 bytes = min(nbytes, POLY1305_BLOCK_SIZE - dctx->buflen);

		memcpy(dctx->buf + dctx->buflen, src, bytes);
		src += bytes;
		nbytes -= bytes;
		dctx->buflen += bytes;

		if (dctx->buflen == POLY1305_BLOCK_SIZE) {
			poly1305_blocks_arch(&dctx->state, dctx->buf,
					     POLY1305_BLOCK_SIZE, 1);
			dctx->buflen = 0;
		}
	}

	if (likely(nbytes >= POLY1305_BLOCK_SIZE)) {
		unsigned int len = round_down(nbytes, POLY1305_BLOCK_SIZE);

		poly1305_blocks_arch(&dctx->state, src, len, 1);
		src += len;
		nbytes %= POLY1305_BLOCK_SIZE;
	}

	if (unlikely(nbytes)) {
		dctx->buflen = nbytes;
		memcpy(dctx->buf, src, nbytes);
	}
}
EXPORT_SYMBOL(poly1305_update_arch);

void poly1305_final_arch(struct poly1305_desc_ctx *dctx, u8 *dst)
{
	if (unlikely(dctx->buflen)) {
		dctx->buf[dctx->buflen++] = 1;
		memset(dctx->buf + dctx->buflen, 0,
		       POLY1305_BLOCK_SIZE - dctx->buflen);
		poly1305_blocks_arch(&dctx->state, dctx->buf,
				     POLY1305_BLOCK_SIZE, 0);
	}

	poly1305_emit_arch(&dctx->h, dst, dctx->s);
	*dctx = (struct poly1305_desc_ctx){};
}
EXPORT_SYMBOL(poly1305_final_arch);

bool poly1305_is_arch_optimized(void)
{
	return true;
+0 −63
Original line number Diff line number Diff line
@@ -10,7 +10,6 @@
#include <linux/jump_label.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/string.h>
#include <linux/unaligned.h>

asmlinkage void poly1305_p10le_4blocks(struct poly1305_block_state *state, const u8 *m, u32 mlen);
@@ -45,17 +44,6 @@ void poly1305_block_init_arch(struct poly1305_block_state *dctx,
}
EXPORT_SYMBOL_GPL(poly1305_block_init_arch);

void poly1305_init_arch(struct poly1305_desc_ctx *dctx, const u8 key[POLY1305_KEY_SIZE])
{
	dctx->s[0] = get_unaligned_le32(key + 16);
	dctx->s[1] = get_unaligned_le32(key + 20);
	dctx->s[2] = get_unaligned_le32(key + 24);
	dctx->s[3] = get_unaligned_le32(key + 28);
	dctx->buflen = 0;
	poly1305_block_init_arch(&dctx->state, key);
}
EXPORT_SYMBOL(poly1305_init_arch);

void poly1305_blocks_arch(struct poly1305_block_state *state, const u8 *src,
			  unsigned int len, u32 padbit)
{
@@ -76,57 +64,6 @@ void poly1305_blocks_arch(struct poly1305_block_state *state, const u8 *src,
}
EXPORT_SYMBOL_GPL(poly1305_blocks_arch);

void poly1305_update_arch(struct poly1305_desc_ctx *dctx,
			  const u8 *src, unsigned int srclen)
{
	unsigned int bytes;

	if (!static_key_enabled(&have_p10))
		return poly1305_update_generic(dctx, src, srclen);

	if (unlikely(dctx->buflen)) {
		bytes = min(srclen, POLY1305_BLOCK_SIZE - dctx->buflen);
		memcpy(dctx->buf + dctx->buflen, src, bytes);
		src += bytes;
		srclen -= bytes;
		dctx->buflen += bytes;
		if (dctx->buflen < POLY1305_BLOCK_SIZE)
			return;
		poly1305_blocks_arch(&dctx->state, dctx->buf,
				     POLY1305_BLOCK_SIZE, 1);
		dctx->buflen = 0;
	}

	if (likely(srclen >= POLY1305_BLOCK_SIZE)) {
		poly1305_blocks_arch(&dctx->state, src, srclen, 1);
		src += srclen - (srclen % POLY1305_BLOCK_SIZE);
		srclen %= POLY1305_BLOCK_SIZE;
	}

	if (unlikely(srclen)) {
		dctx->buflen = srclen;
		memcpy(dctx->buf, src, srclen);
	}
}
EXPORT_SYMBOL(poly1305_update_arch);

void poly1305_final_arch(struct poly1305_desc_ctx *dctx, u8 *dst)
{
	if (!static_key_enabled(&have_p10))
		return poly1305_final_generic(dctx, dst);

	if (dctx->buflen) {
		dctx->buf[dctx->buflen++] = 1;
		memset(dctx->buf + dctx->buflen, 0,
		       POLY1305_BLOCK_SIZE - dctx->buflen);
		poly1305_blocks_arch(&dctx->state, dctx->buf,
				     POLY1305_BLOCK_SIZE, 0);
	}

	poly1305_emit_arch(&dctx->h, dst, dctx->s);
}
EXPORT_SYMBOL(poly1305_final_arch);

bool poly1305_is_arch_optimized(void)
{
	return static_key_enabled(&have_p10);
+0 −60
Original line number Diff line number Diff line
@@ -10,7 +10,6 @@
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/sizes.h>
#include <linux/string.h>
#include <linux/unaligned.h>

struct poly1305_arch_internal {
@@ -96,65 +95,6 @@ void poly1305_emit_arch(const struct poly1305_state *ctx,
}
EXPORT_SYMBOL_GPL(poly1305_emit_arch);

void poly1305_init_arch(struct poly1305_desc_ctx *dctx, const u8 key[POLY1305_KEY_SIZE])
{
	dctx->s[0] = get_unaligned_le32(&key[16]);
	dctx->s[1] = get_unaligned_le32(&key[20]);
	dctx->s[2] = get_unaligned_le32(&key[24]);
	dctx->s[3] = get_unaligned_le32(&key[28]);
	dctx->buflen = 0;
	poly1305_block_init_arch(&dctx->state, key);
}
EXPORT_SYMBOL(poly1305_init_arch);

void poly1305_update_arch(struct poly1305_desc_ctx *dctx, const u8 *src,
			  unsigned int srclen)
{
	unsigned int bytes;

	if (unlikely(dctx->buflen)) {
		bytes = min(srclen, POLY1305_BLOCK_SIZE - dctx->buflen);
		memcpy(dctx->buf + dctx->buflen, src, bytes);
		src += bytes;
		srclen -= bytes;
		dctx->buflen += bytes;

		if (dctx->buflen == POLY1305_BLOCK_SIZE) {
			poly1305_blocks_arch(&dctx->state, dctx->buf,
					     POLY1305_BLOCK_SIZE, 1);
			dctx->buflen = 0;
		}
	}

	if (likely(srclen >= POLY1305_BLOCK_SIZE)) {
		bytes = round_down(srclen, POLY1305_BLOCK_SIZE);
		poly1305_blocks_arch(&dctx->state, src, bytes, 1);
		src += bytes;
		srclen -= bytes;
	}

	if (unlikely(srclen)) {
		dctx->buflen = srclen;
		memcpy(dctx->buf, src, srclen);
	}
}
EXPORT_SYMBOL(poly1305_update_arch);

void poly1305_final_arch(struct poly1305_desc_ctx *dctx, u8 *dst)
{
	if (unlikely(dctx->buflen)) {
		dctx->buf[dctx->buflen++] = 1;
		memset(dctx->buf + dctx->buflen, 0,
		       POLY1305_BLOCK_SIZE - dctx->buflen);
		poly1305_blocks_arch(&dctx->state, dctx->buf,
				     POLY1305_BLOCK_SIZE, 0);
	}

	poly1305_emit_arch(&dctx->h, dst, dctx->s);
	memzero_explicit(dctx, sizeof(*dctx));
}
EXPORT_SYMBOL(poly1305_final_arch);

bool poly1305_is_arch_optimized(void)
{
	return static_key_enabled(&poly1305_use_avx);
Loading