[PATCH v2 01/12] x86/crypto: Fix RBP usage in blowfish-x86_64-asm_64.S

[Josh Poimboeuf]

Using RBP as a temporary register breaks frame pointer convention and
breaks stack traces when unwinding from an interrupt in the crypto code.

Use R12 instead of RBP.  R12 can't be used as the RT0 register because
of x86 instruction encoding limitations.  So use R12 for CTX and RDI for
CTX.  This means that CTX is no longer an implicit function argument.
Instead it needs to be explicitly copied from RDI.

Reported-by: Eric Biggers <ebiggers@xxxxxxxxxx>
Reported-by: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Tested-by: Eric Biggers <ebiggers@xxxxxxxxxx>
Acked-by: Eric Biggers <ebiggers@xxxxxxxxxx>
Signed-off-by: Josh Poimboeuf <jpoimboe@xxxxxxxxxx>
---
 arch/x86/crypto/blowfish-x86_64-asm_64.S | 48 +++++++++++++++++---------------
 1 file changed, 26 insertions(+), 22 deletions(-)

diff --git a/arch/x86/crypto/blowfish-x86_64-asm_64.S b/arch/x86/crypto/blowfish-x86_64-asm_64.S
index 246c67006ed0..8c1fcb6bad21 100644
--- a/arch/x86/crypto/blowfish-x86_64-asm_64.S
+++ b/arch/x86/crypto/blowfish-x86_64-asm_64.S
@@ -33,7 +33,7 @@
 #define s3	((16 + 2 + (3 * 256)) * 4)
 
 /* register macros */
-#define CTX %rdi
+#define CTX %r12
 #define RIO %rsi
 
 #define RX0 %rax
@@ -56,12 +56,12 @@
 #define RX2bh %ch
 #define RX3bh %dh
 
-#define RT0 %rbp
+#define RT0 %rdi
 #define RT1 %rsi
 #define RT2 %r8
 #define RT3 %r9
 
-#define RT0d %ebp
+#define RT0d %edi
 #define RT1d %esi
 #define RT2d %r8d
 #define RT3d %r9d
@@ -120,13 +120,14 @@
 
 ENTRY(__blowfish_enc_blk)
 	/* input:
-	 *	%rdi: ctx, CTX
+	 *	%rdi: ctx
 	 *	%rsi: dst
 	 *	%rdx: src
 	 *	%rcx: bool, if true: xor output
 	 */
-	movq %rbp, %r11;
+	movq %r12, %r11;
 
+	movq %rdi, CTX;
 	movq %rsi, %r10;
 	movq %rdx, RIO;
 
@@ -142,7 +143,7 @@ ENTRY(__blowfish_enc_blk)
 	round_enc(14);
 	add_roundkey_enc(16);
 
-	movq %r11, %rbp;
+	movq %r11, %r12;
 
 	movq %r10, RIO;
 	test %cl, %cl;
@@ -157,12 +158,13 @@ ENDPROC(__blowfish_enc_blk)
 
 ENTRY(blowfish_dec_blk)
 	/* input:
-	 *	%rdi: ctx, CTX
+	 *	%rdi: ctx
 	 *	%rsi: dst
 	 *	%rdx: src
 	 */
-	movq %rbp, %r11;
+	movq %r12, %r11;
 
+	movq %rdi, CTX;
 	movq %rsi, %r10;
 	movq %rdx, RIO;
 
@@ -181,7 +183,7 @@ ENTRY(blowfish_dec_blk)
 	movq %r10, RIO;
 	write_block();
 
-	movq %r11, %rbp;
+	movq %r11, %r12;
 
 	ret;
 ENDPROC(blowfish_dec_blk)
@@ -298,20 +300,21 @@ ENDPROC(blowfish_dec_blk)
 
 ENTRY(__blowfish_enc_blk_4way)
 	/* input:
-	 *	%rdi: ctx, CTX
+	 *	%rdi: ctx
 	 *	%rsi: dst
 	 *	%rdx: src
 	 *	%rcx: bool, if true: xor output
 	 */
-	pushq %rbp;
+	pushq %r12;
 	pushq %rbx;
 	pushq %rcx;
 
-	preload_roundkey_enc(0);
-
+	movq %rdi, CTX
 	movq %rsi, %r11;
 	movq %rdx, RIO;
 
+	preload_roundkey_enc(0);
+
 	read_block4();
 
 	round_enc4(0);
@@ -324,39 +327,40 @@ ENTRY(__blowfish_enc_blk_4way)
 	round_enc4(14);
 	add_preloaded_roundkey4();
 
-	popq %rbp;
+	popq %r12;
 	movq %r11, RIO;
 
-	test %bpl, %bpl;
+	test %r12b, %r12b;
 	jnz .L__enc_xor4;
 
 	write_block4();
 
 	popq %rbx;
-	popq %rbp;
+	popq %r12;
 	ret;
 
 .L__enc_xor4:
 	xor_block4();
 
 	popq %rbx;
-	popq %rbp;
+	popq %r12;
 	ret;
 ENDPROC(__blowfish_enc_blk_4way)
 
 ENTRY(blowfish_dec_blk_4way)
 	/* input:
-	 *	%rdi: ctx, CTX
+	 *	%rdi: ctx
 	 *	%rsi: dst
 	 *	%rdx: src
 	 */
-	pushq %rbp;
+	pushq %r12;
 	pushq %rbx;
-	preload_roundkey_dec(17);
 
-	movq %rsi, %r11;
+	movq %rdi, CTX;
+	movq %rsi, %r11
 	movq %rdx, RIO;
 
+	preload_roundkey_dec(17);
 	read_block4();
 
 	round_dec4(17);
@@ -373,7 +377,7 @@ ENTRY(blowfish_dec_blk_4way)
 	write_block4();
 
 	popq %rbx;
-	popq %rbp;
+	popq %r12;
 
 	ret;
 ENDPROC(blowfish_dec_blk_4way)
-- 
2.13.5