summaryrefslogtreecommitdiff
path: root/arch/riscv/lib
diff options
context:
space:
mode:
authorBjörn Töpel <bjorn@rivosinc.com>2023-02-28 19:42:10 +0100
committerPalmer Dabbelt <palmer@rivosinc.com>2023-02-28 18:42:38 -0800
commit81a1dd10b072fd432f37cd5dc9eb3ed6ec5d386e (patch)
treee8155beaacbfae26643c824cee09c2ec8fb2d7a2 /arch/riscv/lib
parent6934cf8a3e0b4a8318ce8f1342348e967e29192f (diff)
riscv, lib: Fix Zbb strncmp
The Zbb optimized strncmp has two parts; a fast path that does XLEN/8B per iteration, and a slow that does one byte per iteration. The idea is to compare aligned XLEN chunks for most of strings, and do the remainder tail in the slow path. The Zbb strncmp has two issues in the fast path: Incorrect remainder handling (wrong compare): Assume that the string length is 9. On 64b systems, the fast path should do one iteration, and one iteration in the slow path. Instead, both were done in the fast path, which lead to incorrect results. An example: strncmp("/dev/vda", "/dev/", 5); Correct by changing "bgt" to "bge". Missing NULL checks in the second string: This could lead to incorrect results for: strncmp("/dev/vda", "/dev/vda\0", 8); Correct by adding an additional check. Fixes: b6fcdb191e36 ("RISC-V: add zbb support to string functions") Suggested-by: Heiko Stuebner <heiko.stuebner@vrull.eu> Signed-off-by: Björn Töpel <bjorn@rivosinc.com> Tested-by: Conor Dooley <conor.dooley@microchip.com> Tested-by: Guenter Roeck <linux@roeck-us.net> Link: https://lore.kernel.org/r/20230228184211.1585641-1-bjorn@kernel.org Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
Diffstat (limited to 'arch/riscv/lib')
-rw-r--r--arch/riscv/lib/strncmp.S4
1 files changed, 3 insertions, 1 deletions
diff --git a/arch/riscv/lib/strncmp.S b/arch/riscv/lib/strncmp.S
index e09de79e62b9..7ac2f667285a 100644
--- a/arch/riscv/lib/strncmp.S
+++ b/arch/riscv/lib/strncmp.S
@@ -78,11 +78,13 @@ strncmp_zbb:
/* Main loop for aligned string. */
.p2align 3
1:
- bgt a0, t6, 3f
+ bge a0, t6, 3f
REG_L t0, 0(a0)
REG_L t1, 0(a1)
orc.b t3, t0
bne t3, t5, 2f
+ orc.b t3, t1
+ bne t3, t5, 2f
addi a0, a0, SZREG
addi a1, a1, SZREG
beq t0, t1, 1b