powerpc: Create disable_kernel_{fp,altivec,vsx,spe}()

The enable_kernel_*() functions leave the relevant MSR bits enabled
until we exit the kernel sometime later. Create disable versions
that wrap the kernel use of FP, Altivec VSX or SPE.

While we don't want to disable it normally for performance reasons
(MSR writes are slow), it will be used for a debug boot option that
does this and catches bad uses in other areas of the kernel.
Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

arch/powerpc/crypto/aes-spe-glue.c

@@ -85,6 +85,7 @@ static void spe_begin(void)
 
 static void spe_end(void)
 {
+	disable_kernel_spe();
 	/* reenable preemption */
 	preempt_enable();
 }

arch/powerpc/crypto/sha1-spe-glue.c

@@ -46,6 +46,7 @@ static void spe_begin(void)
 
 static void spe_end(void)
 {
+	disable_kernel_spe();
 	/* reenable preemption */
 	preempt_enable();
 }

arch/powerpc/crypto/sha256-spe-glue.c

@@ -47,6 +47,7 @@ static void spe_begin(void)
 
 static void spe_end(void)
 {
+	disable_kernel_spe();
 	/* reenable preemption */
 	preempt_enable();
 }

arch/powerpc/include/asm/switch_to.h

@@ -26,6 +26,11 @@ extern void enable_kernel_spe(void);
 extern void load_up_spe(struct task_struct *);
 extern void switch_booke_debug_regs(struct debug_reg *new_debug);
 
+static inline void disable_kernel_fp(void) { }
+static inline void disable_kernel_altivec(void) { }
+static inline void disable_kernel_spe(void) { }
+static inline void disable_kernel_vsx(void) { }
+
 #ifdef CONFIG_PPC_FPU
 extern void flush_fp_to_thread(struct task_struct *);
 extern void giveup_fpu(struct task_struct *);

arch/powerpc/kernel/align.c

@@ -960,6 +960,7 @@ int fix_alignment(struct pt_regs *regs)
 			preempt_disable();
 			enable_kernel_fp();
 			cvt_df(&data.dd, (float *)&data.x32.low32);
+			disable_kernel_fp();
 			preempt_enable();
 #else
 			return 0;
@@ -1000,6 +1001,7 @@ int fix_alignment(struct pt_regs *regs)
 		preempt_disable();
 		enable_kernel_fp();
 		cvt_fd((float *)&data.x32.low32, &data.dd);
+		disable_kernel_fp();
 		preempt_enable();
 #else
 		return 0;

arch/powerpc/kvm/book3s_paired_singles.c

@@ -1265,6 +1265,7 @@ int kvmppc_emulate_paired_single(struct kvm_run *run, struct kvm_vcpu *vcpu)
 	if (rcomp)
 		kvmppc_set_cr(vcpu, cr);
 
+	disable_kernel_fp();
 	preempt_enable();
 
 	return emulated;

arch/powerpc/kvm/book3s_pr.c

@@ -751,6 +751,7 @@ static int kvmppc_handle_ext(struct kvm_vcpu *vcpu, unsigned int exit_nr,
 		preempt_disable();
 		enable_kernel_fp();
 		load_fp_state(&vcpu->arch.fp);
+		disable_kernel_fp();
 		t->fp_save_area = &vcpu->arch.fp;
 		preempt_enable();
 	}
@@ -760,6 +761,7 @@ static int kvmppc_handle_ext(struct kvm_vcpu *vcpu, unsigned int exit_nr,
 		preempt_disable();
 		enable_kernel_altivec();
 		load_vr_state(&vcpu->arch.vr);
+		disable_kernel_altivec();
 		t->vr_save_area = &vcpu->arch.vr;
 		preempt_enable();
 #endif
@@ -788,6 +790,7 @@ static void kvmppc_handle_lost_ext(struct kvm_vcpu *vcpu)
 		preempt_disable();
 		enable_kernel_fp();
 		load_fp_state(&vcpu->arch.fp);
+		disable_kernel_fp();
 		preempt_enable();
 	}
 #ifdef CONFIG_ALTIVEC
@@ -795,6 +798,7 @@ static void kvmppc_handle_lost_ext(struct kvm_vcpu *vcpu)
 		preempt_disable();
 		enable_kernel_altivec();
 		load_vr_state(&vcpu->arch.vr);
+		disable_kernel_altivec();
 		preempt_enable();
 	}
 #endif

arch/powerpc/kvm/booke.c

@@ -98,6 +98,7 @@ void kvmppc_vcpu_disable_spe(struct kvm_vcpu *vcpu)
 	preempt_disable();
 	enable_kernel_spe();
 	kvmppc_save_guest_spe(vcpu);
+	disable_kernel_spe();
 	vcpu->arch.shadow_msr &= ~MSR_SPE;
 	preempt_enable();
 }
@@ -107,6 +108,7 @@ static void kvmppc_vcpu_enable_spe(struct kvm_vcpu *vcpu)
 	preempt_disable();
 	enable_kernel_spe();
 	kvmppc_load_guest_spe(vcpu);
+	disable_kernel_spe();
 	vcpu->arch.shadow_msr |= MSR_SPE;
 	preempt_enable();
 }
@@ -141,6 +143,7 @@ static inline void kvmppc_load_guest_fp(struct kvm_vcpu *vcpu)
 	if (!(current->thread.regs->msr & MSR_FP)) {
 		enable_kernel_fp();
 		load_fp_state(&vcpu->arch.fp);
+		disable_kernel_fp();
 		current->thread.fp_save_area = &vcpu->arch.fp;
 		current->thread.regs->msr |= MSR_FP;
 	}
@@ -182,6 +185,7 @@ static inline void kvmppc_load_guest_altivec(struct kvm_vcpu *vcpu)
 		if (!(current->thread.regs->msr & MSR_VEC)) {
 			enable_kernel_altivec();
 			load_vr_state(&vcpu->arch.vr);
+			disable_kernel_altivec();
 			current->thread.vr_save_area = &vcpu->arch.vr;
 			current->thread.regs->msr |= MSR_VEC;
 		}

arch/powerpc/lib/vmx-helper.c

@@ -46,6 +46,7 @@ int enter_vmx_usercopy(void)
  */
 int exit_vmx_usercopy(void)
 {
+	disable_kernel_altivec();
 	pagefault_enable();
 	preempt_enable();
 	return 0;
@@ -70,6 +71,7 @@ int enter_vmx_copy(void)
  */
 void *exit_vmx_copy(void *dest)
 {
+	disable_kernel_altivec();
 	preempt_enable();
 	return dest;
 }

arch/powerpc/lib/xor_vmx.c

@@ -74,6 +74,7 @@ void xor_altivec_2(unsigned long bytes, unsigned long *v1_in,
 		v2 += 4;
 	} while (--lines > 0);
 
+	disable_kernel_altivec();
 	preempt_enable();
 }
 EXPORT_SYMBOL(xor_altivec_2);
@@ -102,6 +103,7 @@ void xor_altivec_3(unsigned long bytes, unsigned long *v1_in,
 		v3 += 4;
 	} while (--lines > 0);
 
+	disable_kernel_altivec();
 	preempt_enable();
 }
 EXPORT_SYMBOL(xor_altivec_3);
@@ -135,6 +137,7 @@ void xor_altivec_4(unsigned long bytes, unsigned long *v1_in,
 		v4 += 4;
 	} while (--lines > 0);
 
+	disable_kernel_altivec();
 	preempt_enable();
 }
 EXPORT_SYMBOL(xor_altivec_4);
@@ -172,6 +175,7 @@ void xor_altivec_5(unsigned long bytes, unsigned long *v1_in,
 		v5 += 4;
 	} while (--lines > 0);
 
+	disable_kernel_altivec();
 	preempt_enable();
 }
 EXPORT_SYMBOL(xor_altivec_5);

drivers/crypto/vmx/aes.c

@@ -86,6 +86,7 @@ static int p8_aes_setkey(struct crypto_tfm *tfm, const u8 *key,
 	enable_kernel_vsx();
 	ret = aes_p8_set_encrypt_key(key, keylen * 8, &ctx->enc_key);
 	ret += aes_p8_set_decrypt_key(key, keylen * 8, &ctx->dec_key);
+	disable_kernel_vsx();
 	pagefault_enable();
 	preempt_enable();
 
@@ -104,6 +105,7 @@ static void p8_aes_encrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src)
 		pagefault_disable();
 		enable_kernel_vsx();
 		aes_p8_encrypt(src, dst, &ctx->enc_key);
+		disable_kernel_vsx();
 		pagefault_enable();
 		preempt_enable();
 	}
@@ -120,6 +122,7 @@ static void p8_aes_decrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src)
 		pagefault_disable();
 		enable_kernel_vsx();
 		aes_p8_decrypt(src, dst, &ctx->dec_key);
+		disable_kernel_vsx();
 		pagefault_enable();
 		preempt_enable();
 	}

drivers/crypto/vmx/aes_cbc.c

@@ -87,6 +87,7 @@ static int p8_aes_cbc_setkey(struct crypto_tfm *tfm, const u8 *key,
 	enable_kernel_vsx();
 	ret = aes_p8_set_encrypt_key(key, keylen * 8, &ctx->enc_key);
 	ret += aes_p8_set_decrypt_key(key, keylen * 8, &ctx->dec_key);
+	disable_kernel_vsx();
 	pagefault_enable();
 	preempt_enable();
 
@@ -127,6 +128,7 @@ static int p8_aes_cbc_encrypt(struct blkcipher_desc *desc,
 			ret = blkcipher_walk_done(desc, &walk, nbytes);
 		}
 
+		disable_kernel_vsx();
 		pagefault_enable();
 		preempt_enable();
 	}
@@ -167,6 +169,7 @@ static int p8_aes_cbc_decrypt(struct blkcipher_desc *desc,
 			ret = blkcipher_walk_done(desc, &walk, nbytes);
 		}
 
+		disable_kernel_vsx();
 		pagefault_enable();
 		preempt_enable();
 	}

drivers/crypto/vmx/aes_ctr.c

@@ -83,6 +83,7 @@ static int p8_aes_ctr_setkey(struct crypto_tfm *tfm, const u8 *key,
 	pagefault_disable();
 	enable_kernel_vsx();
 	ret = aes_p8_set_encrypt_key(key, keylen * 8, &ctx->enc_key);
+	disable_kernel_vsx();
 	pagefault_enable();
 
 	ret += crypto_blkcipher_setkey(ctx->fallback, key, keylen);
@@ -101,6 +102,7 @@ static void p8_aes_ctr_final(struct p8_aes_ctr_ctx *ctx,
 	pagefault_disable();
 	enable_kernel_vsx();
 	aes_p8_encrypt(ctrblk, keystream, &ctx->enc_key);
+	disable_kernel_vsx();
 	pagefault_enable();
 
 	crypto_xor(keystream, src, nbytes);
@@ -139,6 +141,7 @@ static int p8_aes_ctr_crypt(struct blkcipher_desc *desc,
 						    AES_BLOCK_SIZE,
 						    &ctx->enc_key,
 						    walk.iv);
+			disable_kernel_vsx();
 			pagefault_enable();
 
 			/* We need to update IV mostly for last bytes/round */

drivers/crypto/vmx/ghash.c

@@ -120,6 +120,7 @@ static int p8_ghash_setkey(struct crypto_shash *tfm, const u8 *key,
 	pagefault_disable();
 	enable_kernel_vsx();
 	gcm_init_p8(ctx->htable, (const u64 *) key);
+	disable_kernel_vsx();
 	pagefault_enable();
 	preempt_enable();
 	return crypto_shash_setkey(ctx->fallback, key, keylen);
@@ -150,6 +151,7 @@ static int p8_ghash_update(struct shash_desc *desc,
 			enable_kernel_vsx();
 			gcm_ghash_p8(dctx->shash, ctx->htable,
 				     dctx->buffer, GHASH_DIGEST_SIZE);
+			disable_kernel_vsx();
 			pagefault_enable();
 			preempt_enable();
 			src += GHASH_DIGEST_SIZE - dctx->bytes;
@@ -162,6 +164,7 @@ static int p8_ghash_update(struct shash_desc *desc,
 			pagefault_disable();
 			enable_kernel_vsx();
 			gcm_ghash_p8(dctx->shash, ctx->htable, src, len);
+			disable_kernel_vsx();
 			pagefault_enable();
 			preempt_enable();
 			src += len;
@@ -192,6 +195,7 @@ static int p8_ghash_final(struct shash_desc *desc, u8 *out)
 			enable_kernel_vsx();
 			gcm_ghash_p8(dctx->shash, ctx->htable,
 				     dctx->buffer, GHASH_DIGEST_SIZE);
+			disable_kernel_vsx();
 			pagefault_enable();
 			preempt_enable();
 			dctx->bytes = 0;

lib/raid6/altivec.uc

@@ -101,6 +101,7 @@ static void raid6_altivec$#_gen_syndrome(int disks, size_t bytes, void **ptrs)
 
 	raid6_altivec$#_gen_syndrome_real(disks, bytes, ptrs);
 
+	disable_kernel_altivec();
 	preempt_enable();
 }