x86/asm: Ensure function alignment

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
ammarfaizi2 · Jul 20, 2022 · 0f16b39 · 0f16b39
1 parent 4e3d90f
commit 0f16b39
Show file tree

Hide file tree

Showing 19 changed files with 18 additions and 38 deletions.
diff --git a/arch/x86/crypto/camellia-aesni-avx-asm_64.S b/arch/x86/crypto/camellia-aesni-avx-asm_64.S
@@ -712,7 +712,6 @@ SYM_FUNC_END(roundsm16_x4_x5_x6_x7_x0_x1_x2_x3_y4_y5_y6_y7_y0_y1_y2_y3_ab)
 
 .text
 
-.align 8
 SYM_FUNC_START_LOCAL(__camellia_enc_blk16)
 	/* input:
 	 *	%rdi: ctx, CTX
@@ -799,7 +798,6 @@ SYM_FUNC_START_LOCAL(__camellia_enc_blk16)
 	jmp .Lenc_done;
 SYM_FUNC_END(__camellia_enc_blk16)
 
-.align 8
 SYM_FUNC_START_LOCAL(__camellia_dec_blk16)
 	/* input:
 	 *	%rdi: ctx, CTX

diff --git a/arch/x86/crypto/camellia-aesni-avx2-asm_64.S b/arch/x86/crypto/camellia-aesni-avx2-asm_64.S
@@ -221,15 +221,13 @@
  * Size optimization... with inlined roundsm32 binary would be over 5 times
  * larger and would only marginally faster.
  */
-.align 8
 SYM_FUNC_START_LOCAL(roundsm32_x0_x1_x2_x3_x4_x5_x6_x7_y0_y1_y2_y3_y4_y5_y6_y7_cd)
 	roundsm32(%ymm0, %ymm1, %ymm2, %ymm3, %ymm4, %ymm5, %ymm6, %ymm7,
 		  %ymm8, %ymm9, %ymm10, %ymm11, %ymm12, %ymm13, %ymm14, %ymm15,
 		  %rcx, (%r9));
 	RET;
 SYM_FUNC_END(roundsm32_x0_x1_x2_x3_x4_x5_x6_x7_y0_y1_y2_y3_y4_y5_y6_y7_cd)
 
-.align 8
 SYM_FUNC_START_LOCAL(roundsm32_x4_x5_x6_x7_x0_x1_x2_x3_y4_y5_y6_y7_y0_y1_y2_y3_ab)
 	roundsm32(%ymm4, %ymm5, %ymm6, %ymm7, %ymm0, %ymm1, %ymm2, %ymm3,
 		  %ymm12, %ymm13, %ymm14, %ymm15, %ymm8, %ymm9, %ymm10, %ymm11,
@@ -748,7 +746,6 @@ SYM_FUNC_END(roundsm32_x4_x5_x6_x7_x0_x1_x2_x3_y4_y5_y6_y7_y0_y1_y2_y3_ab)
 
 .text
 
-.align 8
 SYM_FUNC_START_LOCAL(__camellia_enc_blk32)
 	/* input:
 	 *	%rdi: ctx, CTX
@@ -835,7 +832,6 @@ SYM_FUNC_START_LOCAL(__camellia_enc_blk32)
 	jmp .Lenc_done;
 SYM_FUNC_END(__camellia_enc_blk32)
 
-.align 8
 SYM_FUNC_START_LOCAL(__camellia_dec_blk32)
 	/* input:
 	 *	%rdi: ctx, CTX

diff --git a/arch/x86/crypto/cast5-avx-x86_64-asm_64.S b/arch/x86/crypto/cast5-avx-x86_64-asm_64.S
@@ -208,7 +208,6 @@
 
 .text
 
-.align 16
 SYM_FUNC_START_LOCAL(__cast5_enc_blk16)
 	/* input:
 	 *	%rdi: ctx
@@ -282,7 +281,6 @@ SYM_FUNC_START_LOCAL(__cast5_enc_blk16)
 	RET;
 SYM_FUNC_END(__cast5_enc_blk16)
 
-.align 16
 SYM_FUNC_START_LOCAL(__cast5_dec_blk16)
 	/* input:
 	 *	%rdi: ctx

diff --git a/arch/x86/crypto/crct10dif-pcl-asm_64.S b/arch/x86/crypto/crct10dif-pcl-asm_64.S
@@ -94,7 +94,6 @@
 #
 # Assumes len >= 16.
 #
-.align 16
 SYM_FUNC_START(crc_t10dif_pcl)
 
 	movdqa	.Lbswap_mask(%rip), BSWAP_MASK

diff --git a/arch/x86/crypto/serpent-avx-x86_64-asm_64.S b/arch/x86/crypto/serpent-avx-x86_64-asm_64.S
@@ -550,7 +550,6 @@
 #define write_blocks(x0, x1, x2, x3, t0, t1, t2) \
 	transpose_4x4(x0, x1, x2, x3, t0, t1, t2)
 
-.align 8
 SYM_FUNC_START_LOCAL(__serpent_enc_blk8_avx)
 	/* input:
 	 *	%rdi: ctx, CTX
@@ -604,7 +603,6 @@ SYM_FUNC_START_LOCAL(__serpent_enc_blk8_avx)
 	RET;
 SYM_FUNC_END(__serpent_enc_blk8_avx)
 
-.align 8
 SYM_FUNC_START_LOCAL(__serpent_dec_blk8_avx)
 	/* input:
 	 *	%rdi: ctx, CTX

diff --git a/arch/x86/crypto/serpent-avx2-asm_64.S b/arch/x86/crypto/serpent-avx2-asm_64.S
@@ -550,7 +550,6 @@
 #define write_blocks(x0, x1, x2, x3, t0, t1, t2) \
 	transpose_4x4(x0, x1, x2, x3, t0, t1, t2)
 
-.align 8
 SYM_FUNC_START_LOCAL(__serpent_enc_blk16)
 	/* input:
 	 *	%rdi: ctx, CTX
@@ -604,7 +603,6 @@ SYM_FUNC_START_LOCAL(__serpent_enc_blk16)
 	RET;
 SYM_FUNC_END(__serpent_enc_blk16)
 
-.align 8
 SYM_FUNC_START_LOCAL(__serpent_dec_blk16)
 	/* input:
 	 *	%rdi: ctx, CTX

diff --git a/arch/x86/crypto/sha1_ni_asm.S b/arch/x86/crypto/sha1_ni_asm.S
@@ -92,7 +92,6 @@
  * numBlocks: Number of blocks to process
  */
 .text
-.align 32
 SYM_FUNC_START(sha1_ni_transform)
 	push		%rbp
 	mov		%rsp, %rbp

diff --git a/arch/x86/crypto/sha256-avx-asm.S b/arch/x86/crypto/sha256-avx-asm.S
@@ -347,7 +347,6 @@ a = TMP_
 ########################################################################
 .text
 SYM_FUNC_START(sha256_transform_avx)
-.align 32
 	pushq   %rbx
 	pushq   %r12
 	pushq   %r13

diff --git a/arch/x86/crypto/sha256-avx2-asm.S b/arch/x86/crypto/sha256-avx2-asm.S
@@ -524,7 +524,6 @@ STACK_SIZE	= _CTX      + _CTX_SIZE
 ########################################################################
 .text
 SYM_FUNC_START(sha256_transform_rorx)
-.align 32
 	pushq	%rbx
 	pushq	%r12
 	pushq	%r13

diff --git a/arch/x86/crypto/sha256-ssse3-asm.S b/arch/x86/crypto/sha256-ssse3-asm.S
@@ -356,7 +356,6 @@ a = TMP_
 ########################################################################
 .text
 SYM_FUNC_START(sha256_transform_ssse3)
-.align 32
 	pushq   %rbx
 	pushq   %r12
 	pushq   %r13

diff --git a/arch/x86/crypto/sha256_ni_asm.S b/arch/x86/crypto/sha256_ni_asm.S
@@ -96,7 +96,6 @@
  */
 
 .text
-.align 32
 SYM_FUNC_START(sha256_ni_transform)
 
 	shl		$6, NUM_BLKS		/*  convert to bytes */

diff --git a/arch/x86/crypto/sm3-avx-asm_64.S b/arch/x86/crypto/sm3-avx-asm_64.S
@@ -327,7 +327,6 @@
  * void sm3_transform_avx(struct sm3_state *state,
  *                        const u8 *data, int nblocks);
  */
-.align 16
 SYM_FUNC_START(sm3_transform_avx)
 	/* input:
 	 *	%rdi: ctx, CTX

diff --git a/arch/x86/crypto/sm4-aesni-avx-asm_64.S b/arch/x86/crypto/sm4-aesni-avx-asm_64.S
@@ -139,13 +139,11 @@
 
 
 .text
-.align 16
 
 /*
  * void sm4_aesni_avx_crypt4(const u32 *rk, u8 *dst,
  *                           const u8 *src, int nblocks)
  */
-.align 8
 SYM_FUNC_START(sm4_aesni_avx_crypt4)
 	/* input:
 	 *	%rdi: round key array, CTX
@@ -249,7 +247,6 @@ SYM_FUNC_START(sm4_aesni_avx_crypt4)
 	RET;
 SYM_FUNC_END(sm4_aesni_avx_crypt4)
 
-.align 8
 SYM_FUNC_START_LOCAL(__sm4_crypt_blk8)
 	/* input:
 	 *	%rdi: round key array, CTX
@@ -363,7 +360,6 @@ SYM_FUNC_END(__sm4_crypt_blk8)
  * void sm4_aesni_avx_crypt8(const u32 *rk, u8 *dst,
  *                           const u8 *src, int nblocks)
  */
-.align 8
 SYM_FUNC_START(sm4_aesni_avx_crypt8)
 	/* input:
 	 *	%rdi: round key array, CTX
@@ -419,7 +415,6 @@ SYM_FUNC_END(sm4_aesni_avx_crypt8)
  * void sm4_aesni_avx_ctr_enc_blk8(const u32 *rk, u8 *dst,
  *                                 const u8 *src, u8 *iv)
  */
-.align 8
 SYM_FUNC_START(sm4_aesni_avx_ctr_enc_blk8)
 	/* input:
 	 *	%rdi: round key array, CTX
@@ -494,7 +489,6 @@ SYM_FUNC_END(sm4_aesni_avx_ctr_enc_blk8)
  * void sm4_aesni_avx_cbc_dec_blk8(const u32 *rk, u8 *dst,
  *                                 const u8 *src, u8 *iv)
  */
-.align 8
 SYM_FUNC_START(sm4_aesni_avx_cbc_dec_blk8)
 	/* input:
 	 *	%rdi: round key array, CTX
@@ -544,7 +538,6 @@ SYM_FUNC_END(sm4_aesni_avx_cbc_dec_blk8)
  * void sm4_aesni_avx_cfb_dec_blk8(const u32 *rk, u8 *dst,
  *                                 const u8 *src, u8 *iv)
  */
-.align 8
 SYM_FUNC_START(sm4_aesni_avx_cfb_dec_blk8)
 	/* input:
 	 *	%rdi: round key array, CTX

diff --git a/arch/x86/crypto/sm4-aesni-avx2-asm_64.S b/arch/x86/crypto/sm4-aesni-avx2-asm_64.S
@@ -153,9 +153,6 @@
 	.long 0xdeadbeef, 0xdeadbeef, 0xdeadbeef
 
 .text
-.align 16
-
-.align 8
 SYM_FUNC_START_LOCAL(__sm4_crypt_blk16)
 	/* input:
 	 *	%rdi: round key array, CTX
@@ -281,7 +278,6 @@ SYM_FUNC_END(__sm4_crypt_blk16)
  * void sm4_aesni_avx2_ctr_enc_blk16(const u32 *rk, u8 *dst,
  *                                   const u8 *src, u8 *iv)
  */
-.align 8
 SYM_FUNC_START(sm4_aesni_avx2_ctr_enc_blk16)
 	/* input:
 	 *	%rdi: round key array, CTX
@@ -394,7 +390,6 @@ SYM_FUNC_END(sm4_aesni_avx2_ctr_enc_blk16)
  * void sm4_aesni_avx2_cbc_dec_blk16(const u32 *rk, u8 *dst,
  *                                   const u8 *src, u8 *iv)
  */
-.align 8
 SYM_FUNC_START(sm4_aesni_avx2_cbc_dec_blk16)
 	/* input:
 	 *	%rdi: round key array, CTX
@@ -448,7 +443,6 @@ SYM_FUNC_END(sm4_aesni_avx2_cbc_dec_blk16)
  * void sm4_aesni_avx2_cfb_dec_blk16(const u32 *rk, u8 *dst,
  *                                   const u8 *src, u8 *iv)
  */
-.align 8
 SYM_FUNC_START(sm4_aesni_avx2_cfb_dec_blk16)
 	/* input:
 	 *	%rdi: round key array, CTX

diff --git a/arch/x86/crypto/twofish-avx-x86_64-asm_64.S b/arch/x86/crypto/twofish-avx-x86_64-asm_64.S
@@ -228,7 +228,6 @@
 	vpxor		x2, wkey, x2; \
 	vpxor		x3, wkey, x3;
 
-.align 8
 SYM_FUNC_START_LOCAL(__twofish_enc_blk8)
 	/* input:
 	 *	%rdi: ctx, CTX
@@ -270,7 +269,6 @@ SYM_FUNC_START_LOCAL(__twofish_enc_blk8)
 	RET;
 SYM_FUNC_END(__twofish_enc_blk8)
 
-.align 8
 SYM_FUNC_START_LOCAL(__twofish_dec_blk8)
 	/* input:
 	 *	%rdi: ctx, CTX

diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
@@ -284,6 +284,7 @@ SYM_FUNC_END(__switch_to_asm)
  * r12: kernel thread arg
  */
 .pushsection .text, "ax"
+	__FUNC_ALIGN
 SYM_CODE_START(ret_from_fork)
 	UNWIND_HINT_EMPTY
 	ANNOTATE_NOENDBR // copy_thread
@@ -828,6 +829,7 @@ EXPORT_SYMBOL(asm_load_gs_index)
  *
  * C calling convention: exc_xen_hypervisor_callback(struct *pt_regs)
  */
+	__FUNC_ALIGN
 SYM_CODE_START_LOCAL(exc_xen_hypervisor_callback)
 
 /*
@@ -856,6 +858,7 @@ SYM_CODE_END(exc_xen_hypervisor_callback)
  * We distinguish between categories by comparing each saved segment register
  * with its current contents: any discrepancy means we in category 1.
  */
+	__FUNC_ALIGN
 SYM_CODE_START(xen_failsafe_callback)
 	UNWIND_HINT_EMPTY
 	ENDBR
@@ -1516,6 +1519,7 @@ SYM_CODE_END(ignore_sysret)
 #endif
 
 .pushsection .text, "ax"
+	__FUNC_ALIGN
 SYM_CODE_START(rewind_stack_and_make_dead)
 	UNWIND_HINT_FUNC
 	/* Prevent any naive code from trying to unwind to our caller. */

diff --git a/arch/x86/include/asm/linkage.h b/arch/x86/include/asm/linkage.h
@@ -44,9 +44,18 @@
 
 #endif /* __ASSEMBLY__ */
 
+#if CONFIG_FUNCTION_ALIGNMENT == 16
+# define __FUNC_ALIGN		.p2align 4, 0x90;
+# define ASM_FUNC_ALIGN		".p2align 4, 0x90;"
+# define SYM_F_ALIGN		__FUNC_ALIGN
+#else
+# define ASM_FUNC_ALIGN		""
+# define SYM_F_ALIGN		SYM_A_ALIGN
+#endif
+
 /* SYM_FUNC_START -- use for global functions */
 #define SYM_FUNC_START(name)				\
-	SYM_START(name, SYM_L_GLOBAL, SYM_A_ALIGN)	\
+	SYM_START(name, SYM_L_GLOBAL, SYM_F_ALIGN)	\
 	ENDBR
 
 /* SYM_FUNC_START_NOALIGN -- use for global functions, w/o alignment */
@@ -56,7 +65,7 @@
 
 /* SYM_FUNC_START_LOCAL -- use for local functions */
 #define SYM_FUNC_START_LOCAL(name)			\
-	SYM_START(name, SYM_L_LOCAL, SYM_A_ALIGN)	\
+	SYM_START(name, SYM_L_LOCAL, SYM_F_ALIGN)	\
 	ENDBR
 
 /* SYM_FUNC_START_LOCAL_NOALIGN -- use for local functions, w/o alignment */
@@ -66,7 +75,7 @@
 
 /* SYM_FUNC_START_WEAK -- use for weak functions */
 #define SYM_FUNC_START_WEAK(name)			\
-	SYM_START(name, SYM_L_WEAK, SYM_A_ALIGN)	\
+	SYM_START(name, SYM_L_WEAK, SYM_F_ALIGN)	\
 	ENDBR
 
 /* SYM_FUNC_START_WEAK_NOALIGN -- use for weak functions, w/o alignment */

diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
@@ -663,6 +663,7 @@ bool __raw_callee_save___native_vcpu_is_preempted(long cpu);
 	extern typeof(func) __raw_callee_save_##func;			\
 									\
 	asm(".pushsection " section ", \"ax\";"				\
+	    ASM_FUNC_ALIGN						\
 	    ".globl " PV_THUNK_NAME(func) ";"				\
 	    ".type " PV_THUNK_NAME(func) ", @function;"			\
 	    PV_THUNK_NAME(func) ":"					\

diff --git a/arch/x86/include/asm/qspinlock_paravirt.h b/arch/x86/include/asm/qspinlock_paravirt.h
@@ -37,9 +37,9 @@ PV_CALLEE_SAVE_REGS_THUNK(__pv_queued_spin_unlock_slowpath);
  *   rdx = internal variable (set to 0)
  */
 asm    (".pushsection .text;"
+	ASM_FUNC_ALIGN
 	".globl " PV_UNLOCK ";"
 	".type " PV_UNLOCK ", @function;"
-	".align 4,0x90;"
 	PV_UNLOCK ": "
 	ASM_ENDBR
 	FRAME_BEGIN