From 13ce0c4a399a654effc40a9a57e87ac23cf19267 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 1 Oct 2013 16:54:05 +1000 Subject: powerpc: Fix parameter clobber in csum_partial_copy_generic() commit d9813c3681a36774b254c0cdc9cce53c9e22c756 upstream. The csum_partial_copy_generic() uses register r7 to adjust the remaining bytes to process. Unfortunately, r7 also holds a parameter, namely the address of the flag to set in case of access exceptions while reading the source buffer. Lacking a quantum implementation of PowerPC, this commit instead uses register r9 to do the adjusting, leaving r7's pointer uncorrupted. Signed-off-by: Paul E. McKenney Signed-off-by: Anton Blanchard Signed-off-by: Benjamin Herrenschmidt Signed-off-by: Ben Hutchings --- arch/powerpc/lib/checksum_64.S | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch/powerpc/lib/checksum_64.S') diff --git a/arch/powerpc/lib/checksum_64.S b/arch/powerpc/lib/checksum_64.S index 18245af..afa2eba 100644 --- a/arch/powerpc/lib/checksum_64.S +++ b/arch/powerpc/lib/checksum_64.S @@ -272,8 +272,8 @@ _GLOBAL(csum_partial_copy_generic) rldicl. r6,r3,64-1,64-2 /* r6 = (r3 & 0x3) >> 1 */ beq .Lcopy_aligned - li r7,4 - sub r6,r7,r6 + li r9,4 + sub r6,r9,r6 mtctr r6 1: -- cgit v1.1 From 0b2d10f8f2e686c9f4b718251765f09f77ee8088 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 1 Oct 2013 17:11:35 +1000 Subject: powerpc: Restore registers on error exit from csum_partial_copy_generic() commit 8f21bd0090052e740944f9397e2be5ac7957ded7 upstream. The csum_partial_copy_generic() function saves the PowerPC non-volatile r14, r15, and r16 registers for the main checksum-and-copy loop. Unfortunately, it fails to restore them upon error exit from this loop, which results in silent corruption of these registers in the presumably rare event of an access exception within that loop. This commit therefore restores these register on error exit from the loop. Signed-off-by: Paul E. McKenney Signed-off-by: Anton Blanchard Signed-off-by: Benjamin Herrenschmidt [bwh: Backported to 3.2: register name macros use lower-case 'r'] Signed-off-by: Ben Hutchings --- arch/powerpc/lib/checksum_64.S | 54 +++++++++++++++++++++++++++++++----------- 1 file changed, 40 insertions(+), 14 deletions(-) (limited to 'arch/powerpc/lib/checksum_64.S') diff --git a/arch/powerpc/lib/checksum_64.S b/arch/powerpc/lib/checksum_64.S index afa2eba..3cdbc64 100644 --- a/arch/powerpc/lib/checksum_64.S +++ b/arch/powerpc/lib/checksum_64.S @@ -229,19 +229,35 @@ _GLOBAL(csum_partial) blr - .macro source + .macro srcnr 100: .section __ex_table,"a" .align 3 - .llong 100b,.Lsrc_error + .llong 100b,.Lsrc_error_nr .previous .endm - .macro dest + .macro source +150: + .section __ex_table,"a" + .align 3 + .llong 150b,.Lsrc_error + .previous + .endm + + .macro dstnr 200: .section __ex_table,"a" .align 3 - .llong 200b,.Ldest_error + .llong 200b,.Ldest_error_nr + .previous + .endm + + .macro dest +250: + .section __ex_table,"a" + .align 3 + .llong 250b,.Ldest_error .previous .endm @@ -277,11 +293,11 @@ _GLOBAL(csum_partial_copy_generic) mtctr r6 1: -source; lhz r6,0(r3) /* align to doubleword */ +srcnr; lhz r6,0(r3) /* align to doubleword */ subi r5,r5,2 addi r3,r3,2 adde r0,r0,r6 -dest; sth r6,0(r4) +dstnr; sth r6,0(r4) addi r4,r4,2 bdnz 1b @@ -395,10 +411,10 @@ dest; std r16,56(r4) mtctr r6 3: -source; ld r6,0(r3) +srcnr; ld r6,0(r3) addi r3,r3,8 adde r0,r0,r6 -dest; std r6,0(r4) +dstnr; std r6,0(r4) addi r4,r4,8 bdnz 3b @@ -408,10 +424,10 @@ dest; std r6,0(r4) srdi. r6,r5,2 beq .Lcopy_tail_halfword -source; lwz r6,0(r3) +srcnr; lwz r6,0(r3) addi r3,r3,4 adde r0,r0,r6 -dest; stw r6,0(r4) +dstnr; stw r6,0(r4) addi r4,r4,4 subi r5,r5,4 @@ -419,10 +435,10 @@ dest; stw r6,0(r4) srdi. r6,r5,1 beq .Lcopy_tail_byte -source; lhz r6,0(r3) +srcnr; lhz r6,0(r3) addi r3,r3,2 adde r0,r0,r6 -dest; sth r6,0(r4) +dstnr; sth r6,0(r4) addi r4,r4,2 subi r5,r5,2 @@ -430,10 +446,10 @@ dest; sth r6,0(r4) andi. r6,r5,1 beq .Lcopy_finish -source; lbz r6,0(r3) +srcnr; lbz r6,0(r3) sldi r9,r6,8 /* Pad the byte out to 16 bits */ adde r0,r0,r9 -dest; stb r6,0(r4) +dstnr; stb r6,0(r4) .Lcopy_finish: addze r0,r0 /* add in final carry */ @@ -443,6 +459,11 @@ dest; stb r6,0(r4) blr .Lsrc_error: + ld r14,STK_REG(r14)(r1) + ld r15,STK_REG(r15)(r1) + ld r16,STK_REG(r16)(r1) + addi r1,r1,STACKFRAMESIZE +.Lsrc_error_nr: cmpdi 0,r7,0 beqlr li r6,-EFAULT @@ -450,6 +471,11 @@ dest; stb r6,0(r4) blr .Ldest_error: + ld r14,STK_REG(r14)(r1) + ld r15,STK_REG(r15)(r1) + ld r16,STK_REG(r16)(r1) + addi r1,r1,STACKFRAMESIZE +.Ldest_error_nr: cmpdi 0,r8,0 beqlr li r6,-EFAULT -- cgit v1.1