diff options
| -rw-r--r-- | drivers/char/hw_random/via-rng.c | 8 | ||||
| -rw-r--r-- | drivers/crypto/padlock-aes.c | 28 | ||||
| -rw-r--r-- | drivers/crypto/padlock-sha.c | 9 | ||||
| -rw-r--r-- | include/asm-x86/i387.h | 32 |
4 files changed, 76 insertions, 1 deletions
diff --git a/drivers/char/hw_random/via-rng.c b/drivers/char/hw_random/via-rng.c index f7feae4..128202e 100644 --- a/drivers/char/hw_random/via-rng.c +++ b/drivers/char/hw_random/via-rng.c @@ -31,6 +31,7 @@ #include <asm/io.h> #include <asm/msr.h> #include <asm/cpufeature.h> +#include <asm/i387.h> #define PFX KBUILD_MODNAME ": " @@ -67,16 +68,23 @@ enum { * Another possible performance boost may come from simply buffering * until we have 4 bytes, thus returning a u32 at a time, * instead of the current u8-at-a-time. + * + * Padlock instructions can generate a spurious DNA fault, so + * we have to call them in the context of irq_ts_save/restore() */ static inline u32 xstore(u32 *addr, u32 edx_in) { u32 eax_out; + int ts_state; + + ts_state = irq_ts_save(); asm(".byte 0x0F,0xA7,0xC0 /* xstore %%edi (addr=%0) */" :"=m"(*addr), "=a"(eax_out) :"D"(addr), "d"(edx_in)); + irq_ts_restore(ts_state); return eax_out; } diff --git a/drivers/crypto/padlock-aes.c b/drivers/crypto/padlock-aes.c index 54a2a16..bf2917d 100644 --- a/drivers/crypto/padlock-aes.c +++ b/drivers/crypto/padlock-aes.c @@ -16,6 +16,7 @@ #include <linux/interrupt.h> #include <linux/kernel.h> #include <asm/byteorder.h> +#include <asm/i387.h> #include "padlock.h" /* Control word. */ @@ -141,6 +142,12 @@ static inline void padlock_reset_key(void) asm volatile ("pushfl; popfl"); } +/* + * While the padlock instructions don't use FP/SSE registers, they + * generate a spurious DNA fault when cr0.ts is '1'. These instructions + * should be used only inside the irq_ts_save/restore() context + */ + static inline void padlock_xcrypt(const u8 *input, u8 *output, void *key, void *control_word) { @@ -205,15 +212,23 @@ static inline u8 *padlock_xcrypt_cbc(const u8 *input, u8 *output, void *key, static void aes_encrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in) { struct aes_ctx *ctx = aes_ctx(tfm); + int ts_state; padlock_reset_key(); + + ts_state = irq_ts_save(); aes_crypt(in, out, ctx->E, &ctx->cword.encrypt); + irq_ts_restore(ts_state); } static void aes_decrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in) { struct aes_ctx *ctx = aes_ctx(tfm); + int ts_state; padlock_reset_key(); + + ts_state = irq_ts_save(); aes_crypt(in, out, ctx->D, &ctx->cword.decrypt); + irq_ts_restore(ts_state); } static struct crypto_alg aes_alg = { @@ -244,12 +259,14 @@ static int ecb_aes_encrypt(struct blkcipher_desc *desc, struct aes_ctx *ctx = blk_aes_ctx(desc->tfm); struct blkcipher_walk walk; int err; + int ts_state; padlock_reset_key(); blkcipher_walk_init(&walk, dst, src, nbytes); err = blkcipher_walk_virt(desc, &walk); + ts_state = irq_ts_save(); while ((nbytes = walk.nbytes)) { padlock_xcrypt_ecb(walk.src.virt.addr, walk.dst.virt.addr, ctx->E, &ctx->cword.encrypt, @@ -257,6 +274,7 @@ static int ecb_aes_encrypt(struct blkcipher_desc *desc, nbytes &= AES_BLOCK_SIZE - 1; err = blkcipher_walk_done(desc, &walk, nbytes); } + irq_ts_restore(ts_state); return err; } @@ -268,12 +286,14 @@ static int ecb_aes_decrypt(struct blkcipher_desc *desc, struct aes_ctx *ctx = blk_aes_ctx(desc->tfm); struct blkcipher_walk walk; int err; + int ts_state; padlock_reset_key(); blkcipher_walk_init(&walk, dst, src, nbytes); err = blkcipher_walk_virt(desc, &walk); + ts_state = irq_ts_save(); while ((nbytes = walk.nbytes)) { padlock_xcrypt_ecb(walk.src.virt.addr, walk.dst.virt.addr, ctx->D, &ctx->cword.decrypt, @@ -281,7 +301,7 @@ static int ecb_aes_decrypt(struct blkcipher_desc *desc, nbytes &= AES_BLOCK_SIZE - 1; err = blkcipher_walk_done(desc, &walk, nbytes); } - + irq_ts_restore(ts_state); return err; } @@ -314,12 +334,14 @@ static int cbc_aes_encrypt(struct blkcipher_desc *desc, struct aes_ctx *ctx = blk_aes_ctx(desc->tfm); struct blkcipher_walk walk; int err; + int ts_state; padlock_reset_key(); blkcipher_walk_init(&walk, dst, src, nbytes); err = blkcipher_walk_virt(desc, &walk); + ts_state = irq_ts_save(); while ((nbytes = walk.nbytes)) { u8 *iv = padlock_xcrypt_cbc(walk.src.virt.addr, walk.dst.virt.addr, ctx->E, @@ -329,6 +351,7 @@ static int cbc_aes_encrypt(struct blkcipher_desc *desc, nbytes &= AES_BLOCK_SIZE - 1; err = blkcipher_walk_done(desc, &walk, nbytes); } + irq_ts_restore(ts_state); return err; } @@ -340,12 +363,14 @@ static int cbc_aes_decrypt(struct blkcipher_desc *desc, struct aes_ctx *ctx = blk_aes_ctx(desc->tfm); struct blkcipher_walk walk; int err; + int ts_state; padlock_reset_key(); blkcipher_walk_init(&walk, dst, src, nbytes); err = blkcipher_walk_virt(desc, &walk); + ts_state = irq_ts_save(); while ((nbytes = walk.nbytes)) { padlock_xcrypt_cbc(walk.src.virt.addr, walk.dst.virt.addr, ctx->D, walk.iv, &ctx->cword.decrypt, @@ -354,6 +379,7 @@ static int cbc_aes_decrypt(struct blkcipher_desc *desc, err = blkcipher_walk_done(desc, &walk, nbytes); } + irq_ts_restore(ts_state); return err; } diff --git a/drivers/crypto/padlock-sha.c b/drivers/crypto/padlock-sha.c index 40d5680..a7fbade 100644 --- a/drivers/crypto/padlock-sha.c +++ b/drivers/crypto/padlock-sha.c @@ -22,6 +22,7 @@ #include <linux/interrupt.h> #include <linux/kernel.h> #include <linux/scatterlist.h> +#include <asm/i387.h> #include "padlock.h" #define SHA1_DEFAULT_FALLBACK "sha1-generic" @@ -102,6 +103,7 @@ static void padlock_do_sha1(const char *in, char *out, int count) * PadLock microcode needs it that big. */ char buf[128+16]; char *result = NEAREST_ALIGNED(buf); + int ts_state; ((uint32_t *)result)[0] = SHA1_H0; ((uint32_t *)result)[1] = SHA1_H1; @@ -109,9 +111,12 @@ static void padlock_do_sha1(const char *in, char *out, int count) ((uint32_t *)result)[3] = SHA1_H3; ((uint32_t *)result)[4] = SHA1_H4; + /* prevent taking the spurious DNA fault with padlock. */ + ts_state = irq_ts_save(); asm volatile (".byte 0xf3,0x0f,0xa6,0xc8" /* rep xsha1 */ : "+S"(in), "+D"(result) : "c"(count), "a"(0)); + irq_ts_restore(ts_state); padlock_output_block((uint32_t *)result, (uint32_t *)out, 5); } @@ -123,6 +128,7 @@ static void padlock_do_sha256(const char *in, char *out, int count) * PadLock microcode needs it that big. */ char buf[128+16]; char *result = NEAREST_ALIGNED(buf); + int ts_state; ((uint32_t *)result)[0] = SHA256_H0; ((uint32_t *)result)[1] = SHA256_H1; @@ -133,9 +139,12 @@ static void padlock_do_sha256(const char *in, char *out, int count) ((uint32_t *)result)[6] = SHA256_H6; ((uint32_t *)result)[7] = SHA256_H7; + /* prevent taking the spurious DNA fault with padlock. */ + ts_state = irq_ts_save(); asm volatile (".byte 0xf3,0x0f,0xa6,0xd0" /* rep xsha256 */ : "+S"(in), "+D"(result) : "c"(count), "a"(0)); + irq_ts_restore(ts_state); padlock_output_block((uint32_t *)result, (uint32_t *)out, 8); } diff --git a/include/asm-x86/i387.h b/include/asm-x86/i387.h index 96fa844..6d3b210 100644 --- a/include/asm-x86/i387.h +++ b/include/asm-x86/i387.h @@ -13,6 +13,7 @@ #include <linux/sched.h> #include <linux/kernel_stat.h> #include <linux/regset.h> +#include <linux/hardirq.h> #include <asm/asm.h> #include <asm/processor.h> #include <asm/sigcontext.h> @@ -236,6 +237,37 @@ static inline void kernel_fpu_end(void) preempt_enable(); } +/* + * Some instructions like VIA's padlock instructions generate a spurious + * DNA fault but don't modify SSE registers. And these instructions + * get used from interrupt context aswell. To prevent these kernel instructions + * in interrupt context interact wrongly with other user/kernel fpu usage, we + * should use them only in the context of irq_ts_save/restore() + */ +static inline int irq_ts_save(void) +{ + /* + * If we are in process context, we are ok to take a spurious DNA fault. + * Otherwise, doing clts() in process context require pre-emption to + * be disabled or some heavy lifting like kernel_fpu_begin() + */ + if (!in_interrupt()) + return 0; + + if (read_cr0() & X86_CR0_TS) { + clts(); + return 1; + } + + return 0; +} + +static inline void irq_ts_restore(int TS_state) +{ + if (TS_state) + stts(); +} + #ifdef CONFIG_X86_64 static inline void save_init_fpu(struct task_struct *tsk) |
