Merge branch 'x86-fpu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 FPU updates from Ingo Molnar:
 "The main changes in this cycle were:

   - do a large round of simplifications after all CPUs do 'eager' FPU
     context switching in v4.9: remove CR0 twiddling, remove leftover
     eager/lazy bts, etc (Andy Lutomirski)

   - more FPU code simplifications: remove struct fpu::counter, clarify
     nomenclature, remove unnecessary arguments/functions and better
     structure the code (Rik van Riel)"

* 'x86-fpu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/fpu: Remove clts()
  x86/fpu: Remove stts()
  x86/fpu: Handle #NM without FPU emulation as an error
  x86/fpu, lguest: Remove CR0.TS support
  x86/fpu, kvm: Remove host CR0.TS manipulation
  x86/fpu: Remove irq_ts_save() and irq_ts_restore()
  x86/fpu: Stop saving and restoring CR0.TS in fpu__init_check_bugs()
  x86/fpu: Get rid of two redundant clts() calls
  x86/fpu: Finish excising 'eagerfpu'
  x86/fpu: Split old_fpu & new_fpu handling into separate functions
  x86/fpu: Remove 'cpu' argument from __cpu_invalidate_fpregs_state()
  x86/fpu: Split old & new FPU code paths
  x86/fpu: Remove __fpregs_(de)activate()
  x86/fpu: Rename lazy restore functions to "register state valid"
  x86/fpu, kvm: Remove KVM vcpu->fpu_counter
  x86/fpu: Remove struct fpu::counter
  x86/fpu: Remove use_eager_fpu()
  x86/fpu: Remove the XFEATURE_MASK_EAGER/LAZY distinction
  x86/fpu: Hard-disable lazy FPU mode
  x86/crypto, x86/fpu: Remove X86_FEATURE_EAGER_FPU #ifdef from the crc32c code

6 files changed, 5 insertions, 68 deletions

diff --git a/drivers/char/hw_random/via-rng.c b/drivers/char/hw_random/via-rng.c
index 44ce80606944..d1f5bb534e0e 100644
--- a/drivers/char/hw_random/via-rng.c
+++ b/drivers/char/hw_random/via-rng.c
@@ -70,21 +70,17 @@ enum {
  * 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()
+ * Padlock instructions can generate a spurious DNA fault, but the
+ * kernel doesn't use CR0.TS, so this doesn't matter.
  */
 
 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" (edx_in), "+D" (addr));
 
-	irq_ts_restore(ts_state);
 	return eax_out;
 }
 
diff --git a/drivers/crypto/padlock-aes.c b/drivers/crypto/padlock-aes.c
index 441e86b23571..b3869748cc6b 100644
--- a/drivers/crypto/padlock-aes.c
+++ b/drivers/crypto/padlock-aes.c
@@ -183,8 +183,8 @@ static inline void padlock_store_cword(struct cword *cword)
 
 /*
  * 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
+ * generate a spurious DNA fault when CR0.TS is '1'.  Fortunately,
+ * the kernel doesn't use CR0.TS.
  */
 
 static inline void rep_xcrypt_ecb(const u8 *input, u8 *output, void *key,
@@ -298,24 +298,18 @@ 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(&ctx->cword.encrypt);
-	ts_state = irq_ts_save();
 	ecb_crypt(in, out, ctx->E, &ctx->cword.encrypt, 1);
-	irq_ts_restore(ts_state);
 	padlock_store_cword(&ctx->cword.encrypt);
 }
 
 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(&ctx->cword.encrypt);
-	ts_state = irq_ts_save();
 	ecb_crypt(in, out, ctx->D, &ctx->cword.decrypt, 1);
-	irq_ts_restore(ts_state);
 	padlock_store_cword(&ctx->cword.encrypt);
 }
 
@@ -346,14 +340,12 @@ 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(&ctx->cword.encrypt);
 
 	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,
@@ -361,7 +353,6 @@ 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);
 
 	padlock_store_cword(&ctx->cword.encrypt);
 
@@ -375,14 +366,12 @@ 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(&ctx->cword.decrypt);
 
 	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,
@@ -390,7 +379,6 @@ 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);
 
 	padlock_store_cword(&ctx->cword.encrypt);
 
@@ -425,14 +413,12 @@ 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(&ctx->cword.encrypt);
 
 	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,
@@ -442,7 +428,6 @@ 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);
 
 	padlock_store_cword(&ctx->cword.decrypt);
 
@@ -456,14 +441,12 @@ 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(&ctx->cword.encrypt);
 
 	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,
@@ -472,8 +455,6 @@ static int cbc_aes_decrypt(struct blkcipher_desc *desc,
 		err = blkcipher_walk_done(desc, &walk, nbytes);
 	}
 
-	irq_ts_restore(ts_state);
-
 	padlock_store_cword(&ctx->cword.encrypt);
 
 	return err;
diff --git a/drivers/crypto/padlock-sha.c b/drivers/crypto/padlock-sha.c
index 8c5f90647b7a..bc72d20c32c3 100644
--- a/drivers/crypto/padlock-sha.c
+++ b/drivers/crypto/padlock-sha.c
@@ -89,7 +89,6 @@ static int padlock_sha1_finup(struct shash_desc *desc, const u8 *in,
 	struct sha1_state state;
 	unsigned int space;
 	unsigned int leftover;
-	int ts_state;
 	int err;
 
 	dctx->fallback.flags = desc->flags & CRYPTO_TFM_REQ_MAY_SLEEP;
@@ -120,14 +119,11 @@ static int padlock_sha1_finup(struct shash_desc *desc, const u8 *in,
 
 	memcpy(result, &state.state, SHA1_DIGEST_SIZE);
 
-	/* prevent taking the spurious DNA fault with padlock. */
-	ts_state = irq_ts_save();
 	asm volatile (".byte 0xf3,0x0f,0xa6,0xc8" /* rep xsha1 */
 		      : \
 		      : "c"((unsigned long)state.count + count), \
 			"a"((unsigned long)state.count), \
 			"S"(in), "D"(result));
-	irq_ts_restore(ts_state);
 
 	padlock_output_block((uint32_t *)result, (uint32_t *)out, 5);
 
@@ -155,7 +151,6 @@ static int padlock_sha256_finup(struct shash_desc *desc, const u8 *in,
 	struct sha256_state state;
 	unsigned int space;
 	unsigned int leftover;
-	int ts_state;
 	int err;
 
 	dctx->fallback.flags = desc->flags & CRYPTO_TFM_REQ_MAY_SLEEP;
@@ -186,14 +181,11 @@ static int padlock_sha256_finup(struct shash_desc *desc, const u8 *in,
 
 	memcpy(result, &state.state, SHA256_DIGEST_SIZE);
 
-	/* prevent taking the spurious DNA fault with padlock. */
-	ts_state = irq_ts_save();
 	asm volatile (".byte 0xf3,0x0f,0xa6,0xd0" /* rep xsha256 */
 		      : \
 		      : "c"((unsigned long)state.count + count), \
 			"a"((unsigned long)state.count), \
 			"S"(in), "D"(result));
-	irq_ts_restore(ts_state);
 
 	padlock_output_block((uint32_t *)result, (uint32_t *)out, 8);
 
@@ -312,7 +304,6 @@ static int padlock_sha1_update_nano(struct shash_desc *desc,
 	u8 buf[128 + PADLOCK_ALIGNMENT - STACK_ALIGN] __attribute__
 		((aligned(STACK_ALIGN)));
 	u8 *dst = PTR_ALIGN(&buf[0], PADLOCK_ALIGNMENT);
-	int ts_state;
 
 	partial = sctx->count & 0x3f;
 	sctx->count += len;
@@ -328,23 +319,19 @@ static int padlock_sha1_update_nano(struct shash_desc *desc,
 			memcpy(sctx->buffer + partial, data,
 				done + SHA1_BLOCK_SIZE);
 			src = sctx->buffer;
-			ts_state = irq_ts_save();
 			asm volatile (".byte 0xf3,0x0f,0xa6,0xc8"
 			: "+S"(src), "+D"(dst) \
 			: "a"((long)-1), "c"((unsigned long)1));
-			irq_ts_restore(ts_state);
 			done += SHA1_BLOCK_SIZE;
 			src = data + done;
 		}
 
 		/* Process the left bytes from the input data */
 		if (len - done >= SHA1_BLOCK_SIZE) {
-			ts_state = irq_ts_save();
 			asm volatile (".byte 0xf3,0x0f,0xa6,0xc8"
 			: "+S"(src), "+D"(dst)
 			: "a"((long)-1),
 			"c"((unsigned long)((len - done) / SHA1_BLOCK_SIZE)));
-			irq_ts_restore(ts_state);
 			done += ((len - done) - (len - done) % SHA1_BLOCK_SIZE);
 			src = data + done;
 		}
@@ -401,7 +388,6 @@ static int padlock_sha256_update_nano(struct shash_desc *desc, const u8 *data,
 	u8 buf[128 + PADLOCK_ALIGNMENT - STACK_ALIGN] __attribute__
 		((aligned(STACK_ALIGN)));
 	u8 *dst = PTR_ALIGN(&buf[0], PADLOCK_ALIGNMENT);
-	int ts_state;
 
 	partial = sctx->count & 0x3f;
 	sctx->count += len;
@@ -417,23 +403,19 @@ static int padlock_sha256_update_nano(struct shash_desc *desc, const u8 *data,
 			memcpy(sctx->buf + partial, data,
 				done + SHA256_BLOCK_SIZE);
 			src = sctx->buf;
-			ts_state = irq_ts_save();
 			asm volatile (".byte 0xf3,0x0f,0xa6,0xd0"
 			: "+S"(src), "+D"(dst)
 			: "a"((long)-1), "c"((unsigned long)1));
-			irq_ts_restore(ts_state);
 			done += SHA256_BLOCK_SIZE;
 			src = data + done;
 		}
 
 		/* Process the left bytes from input data*/
 		if (len - done >= SHA256_BLOCK_SIZE) {
-			ts_state = irq_ts_save();
 			asm volatile (".byte 0xf3,0x0f,0xa6,0xd0"
 			: "+S"(src), "+D"(dst)
 			: "a"((long)-1),
 			"c"((unsigned long)((len - done) / 64)));
-			irq_ts_restore(ts_state);
 			done += ((len - done) - (len - done) % 64);
 			src = data + done;
 		}
diff --git a/drivers/lguest/hypercalls.c b/drivers/lguest/hypercalls.c
index 19a32280731d..601f81c04873 100644
--- a/drivers/lguest/hypercalls.c
+++ b/drivers/lguest/hypercalls.c
@@ -109,10 +109,6 @@ static void do_hcall(struct lg_cpu *cpu, struct hcall_args *args)
 	case LHCALL_SET_CLOCKEVENT:
 		guest_set_clockevent(cpu, args->arg1);
 		break;
-	case LHCALL_TS:
-		/* This sets the TS flag, as we saw used in run_guest(). */
-		cpu->ts = args->arg1;
-		break;
 	case LHCALL_HALT:
 		/* Similarly, this sets the halted flag for run_guest(). */
 		cpu->halted = 1;
diff --git a/drivers/lguest/lg.h b/drivers/lguest/lg.h
index 69b3814afd2f..2356a2318034 100644
--- a/drivers/lguest/lg.h
+++ b/drivers/lguest/lg.h
@@ -43,7 +43,6 @@ struct lg_cpu {
 	struct mm_struct *mm; 	/* == tsk->mm, but that becomes NULL on exit */
 
 	u32 cr2;
-	int ts;
 	u32 esp1;
 	u16 ss1;
 
diff --git a/drivers/lguest/x86/core.c b/drivers/lguest/x86/core.c
index 6e9042e3d2a9..743253fc638f 100644
--- a/drivers/lguest/x86/core.c
+++ b/drivers/lguest/x86/core.c
@@ -247,14 +247,6 @@ unsigned long *lguest_arch_regptr(struct lg_cpu *cpu, size_t reg_off, bool any)
 void lguest_arch_run_guest(struct lg_cpu *cpu)
 {
 	/*
-	 * Remember the awfully-named TS bit?  If the Guest has asked to set it
-	 * we set it now, so we can trap and pass that trap to the Guest if it
-	 * uses the FPU.
-	 */
-	if (cpu->ts && fpregs_active())
-		stts();
-
-	/*
 	 * SYSENTER is an optimized way of doing system calls.  We can't allow
 	 * it because it always jumps to privilege level 0.  A normal Guest
 	 * won't try it because we don't advertise it in CPUID, but a malicious
@@ -282,10 +274,6 @@ void lguest_arch_run_guest(struct lg_cpu *cpu)
 	 if (boot_cpu_has(X86_FEATURE_SEP))
 		wrmsr(MSR_IA32_SYSENTER_CS, __KERNEL_CS, 0);
 
-	/* Clear the host TS bit if it was set above. */
-	if (cpu->ts && fpregs_active())
-		clts();
-
 	/*
 	 * If the Guest page faulted, then the cr2 register will tell us the
 	 * bad virtual address.  We have to grab this now, because once we
@@ -421,12 +409,7 @@ void lguest_arch_handle_trap(struct lg_cpu *cpu)
 			kill_guest(cpu, "Writing cr2");
 		break;
 	case 7: /* We've intercepted a Device Not Available fault. */
-		/*
-		 * If the Guest doesn't want to know, we already restored the
-		 * Floating Point Unit, so we just continue without telling it.
-		 */
-		if (!cpu->ts)
-			return;
+		/* No special handling is needed here. */
 		break;
 	case 32 ... 255:
 		/* This might be a syscall. */