Skip to contentSkip to conversation

target/riscv: fix vector LD/ST instruction

PATCH In review Chao Liu 3 participants 5 messages Aug 15, 2025 – Aug 16, 2025 RISC-V

lore
Share & tools
lore
author
#1 lore raw

PATCH v2 1/2 target/riscv: fix vector register address calculation in strided LD/ST

In reply to Chao Liu

This patch fixes a critical bug in the RISC-V vector instruction translation that caused incorrect data handling in strided load operations (e.g., vlsseg8e32).

Problem Description:

The get_log2 function in trans_rvv.c.inc returned a value 1 higher than the actual log2 value. For example, get_log2(4) incorrectly returned 3 instead of 2.

This led to erroneous vector register offset calculations, resulting in data overlap where bytes 32-47 were incorrectly copied to positions 16-31 in ChaCha20 encryption code.

rvv_test_func:

    vsetivli    zero, 1, e32, m1, ta, ma
    li          t0, 64

    vlsseg8e32.v v0, (a0), t0
    addi        a0, a0, 32
    vlsseg8e32.v v8, (a0), t0

    vssseg8e32.v v0, (a1), t0
    addi        a1, a1, 32
    vssseg8e32.v v8, (a1), t0
    ret

Analysis:

The original implementation counted the number of right shifts until zero, including the final shift that reduced the value to zero:

static inline uint32_t get_log2(uint32_t a)

{
    uint32_t i = 0;
    for (; a > 0;) {
        a >>= 1;
        i++;
    }
    return i; // Returns 3 for a=4 (0b100 → 0b10 → 0b1 → 0b0)
}

Fix:

The corrected function stops shifting when only the highest bit remains and handles the special case of a=0:

static inline uint32_t get_log2(uint32_t a)

{
    uint32_t i = 0;
    if (a == 0) {
        return i; // Handle edge case
    }
    for (; a > 1; a >>= 1) {
        i++;
    }
    return i; // Now returns 2 for a=4
}
Fixes 28c12c1f2f ("Generate strided vector loads/stores with tcg nodes.")
---
 target/riscv/insn_trans/trans_rvv.c.inc | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)
target/riscv/insn_trans/trans_rvv.c.inc +4 -1
index 2b6077ac06..f50b62b1d8 100644
@@ -877,7 +877,10 @@ static inline uint32_t MAXSZ(DisasContext *s)
 static inline uint32_t get_log2(uint32_t a)
 {
     uint32_t i = 0;
-    for (; a > 0;) {
+    if (a == 0) {
+        return i;
+    }
+    for (; a > 1;) {
         a >>= 1;
         i++;
     }
Signature · 1 line
2.50.1
author
#4 lore raw

PATCH v2 2/2 tests/tcg/riscv64: Add test for vlsseg8e32 instruction

In reply to Chao Liu

This case, it copied 64 bytes from a0 to a1 with vlsseg8e32.

---
 tests/tcg/riscv64/Makefile.softmmu-target |   8 +-
 tests/tcg/riscv64/test-vlsseg8e32.S       | 108 ++++++++++++++++++++++
 2 files changed, 114 insertions(+), 2 deletions(-)
 create mode 100644 tests/tcg/riscv64/test-vlsseg8e32.S
tests/tcg/riscv64/Makefile.softmmu-target +6 -2
index 7c1d44d3f4..c3c5b66713 100644
@@ -7,18 +7,22 @@ VPATH += $(TEST_SRC)
 
 LINK_SCRIPT = $(TEST_SRC)/semihost.ld
 LDFLAGS = -T $(LINK_SCRIPT)
-CFLAGS += -g -Og
+CFLAGS += -march=rv64gcv -mabi=lp64d -g -Og
 
 %.o: %.S
 	$(CC) $(CFLAGS) $< -Wa,--noexecstack -c -o $@
 %: %.o $(LINK_SCRIPT)
 	$(LD) $(LDFLAGS) $< -o $@
 
-QEMU_OPTS += -M virt -display none -semihosting -device loader,file=
+QEMU_OPTS += -M virt -cpu rv64,v=true -display none -semihosting -device loader,file=
 
 EXTRA_RUNS += run-issue1060
 run-issue1060: issue1060
 	$(call run-test, $<, $(QEMU) $(QEMU_OPTS)$<)
 
+EXTRA_RUNS += run-vlsseg8e32
+run-vlsseg8e32: test-vlsseg8e32
+	$(call run-test, $<, $(QEMU) $(QEMU_OPTS)$<)
+
 # We don't currently support the multiarch system tests
 undefine MULTIARCH_TESTS
tests/tcg/riscv64/test-vlsseg8e32.S new file +108 -0

108 lines not on this page · raw message

Signature · 1 line
2.50.1

Chao Liu

author
#0 lore raw

v2 cover target/riscv: fix vector LD/ST instruction

Hi Paolo, Eric, Daniel,

I have attempted to fix this issue. Thanks to Eric for providing the test case.

This patch fixes a critical bug in the RISC-V vector instruction translation that caused incorrect data handling in strided load operations (e.g.,vlsseg8e32).

patch v2 changes:
- Fix the commit message of the patch v1.

#### Problem Description

The get_log2 function in trans_rvv.c.inc returned a value 1 higher than the actual log2 value. For example, get_log2(4) incorrectly returned 3 instead of 2.

This led to erroneous vector register offset calculations, resulting in data overlap where bytes 32-47 were incorrectly copied to positions 16-31 in ChaCha20 encryption code.

rvv_test_func:

    vsetivli    zero, 1, e32, m1, ta, ma
    li          t0, 64

    vlsseg8e32.v v0, (a0), t0
    addi        a0, a0, 32
    vlsseg8e32.v v8, (a0), t0

    vssseg8e32.v v0, (a1), t0
    addi        a1, a1, 32
    vssseg8e32.v v8, (a1), t0
    ret

#### Root Cause Analysis

The original implementation counted the number of right shifts until zero, including the final shift that reduced the value to zero:

static inline uint32_t get_log2(uint32_t a)

{
    uint32_t i = 0;
    for (; a > 0;) {
        a >>= 1;
        i++;
    }
    return i; // Returns 3 for a=4 (0b100 → 0b10 → 0b1 → 0b0)
}

#### Fix Implementation

The corrected function stops shifting when only the highest bit remains and handles the special case of a=0:

static inline uint32_t get_log2(uint32_t a)

{
    uint32_t i = 0;
    if (a == 0) {
        return i; // Handle edge case
    }
    for (; a > 1; a >>= 1) {
        i++;
    }
    return i; // Now returns 2 for a=4
}

#### Testing

This fix has been verified with:
1. The provided ChaCha20 vector optimization test case
2. RVV strided load instruction tests in test-vlsseg8e32.S

All tests now pass with correct data handling and no memory overlap.

Test using the following command:

    ./configure --target-list=riscv64-softmmu \
                --cross-prefix-riscv64=riscv64-unknown-elf-

    ninja -j$(nproc) -C build && make check-tcg

Expected result:

    BUILD   riscv64-softmmu guest-tests
    RUN     riscv64-softmmu guest-tests
    TEST    issue1060 on riscv64
    TEST    test-vlsseg8e32 on riscv64

Best regards,

Chao

Chao Liu (2):
target/riscv: fix vector register address calculation in strided LD/ST tests/tcg/riscv64: Add test for vlsseg8e32 instruction

 target/riscv/insn_trans/trans_rvv.c.inc   |   5 +-
 tests/tcg/riscv64/Makefile.softmmu-target |   8 +-
 tests/tcg/riscv64/test-vlsseg8e32.S       | 108 ++++++++++++++++++++++
 3 files changed, 118 insertions(+), 3 deletions(-)
 create mode 100644 tests/tcg/riscv64/test-vlsseg8e32.S
Signature · 1 line
2.50.1
Tested-by on v2 1/2
#2 lore raw

Re: [PATCH v2 1/2] target/riscv: fix vector register address calculation in strided LD/ST

In reply to Chao Liu
Quoted 59 lines · Chao Liu

This patch fixes a critical bug in the RISC-V vector instruction translation that caused incorrect data handling in strided load operations (e.g., vlsseg8e32).

Problem Description:

The get_log2 function in trans_rvv.c.inc returned a value 1 higher than the actual log2 value. For example, get_log2(4) incorrectly returned 3 instead of 2.

This led to erroneous vector register offset calculations, resulting in data overlap where bytes 32-47 were incorrectly copied to positions 16-31 in ChaCha20 encryption code.

rvv_test_func:

    vsetivli    zero, 1, e32, m1, ta, ma
    li          t0, 64

    vlsseg8e32.v v0, (a0), t0
    addi        a0, a0, 32
    vlsseg8e32.v v8, (a0), t0

    vssseg8e32.v v0, (a1), t0
    addi        a1, a1, 32
    vssseg8e32.v v8, (a1), t0
    ret

Analysis:

The original implementation counted the number of right shifts until zero, including the final shift that reduced the value to zero:

static inline uint32_t get_log2(uint32_t a)

{
    uint32_t i = 0;
    for (; a > 0;) {
        a >>= 1;
        i++;
    }
    return i; // Returns 3 for a=4 (0b100 → 0b10 → 0b1 → 0b0)
}

Fix:

The corrected function stops shifting when only the highest bit remains and handles the special case of a=0:

static inline uint32_t get_log2(uint32_t a)

{
    uint32_t i = 0;
    if (a == 0) {
        return i; // Handle edge case
    }
    for (; a > 1; a >>= 1) {
        i++;
    }
    return i; // Now returns 2 for a=4
}
Quoted 7 lines
Fixes 28c12c1f2f ("Generate strided vector loads/stores with tcg nodes.")
---
 target/riscv/insn_trans/trans_rvv.c.inc | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

But, to get this to apply I had to re-apply the fixed commit (which was reverted), then resolve a conflict. You'll need to send out a new series which applies to the latest master branch.

- Eric

#3 lore raw

Re: [PATCH v2 1/2] target/riscv: fix vector register address calculation in strided LD/ST

In reply to Chao Liu
Quoted 72 lines · Chao Liu

This patch fixes a critical bug in the RISC-V vector instruction translation that caused incorrect data handling in strided load operations (e.g., vlsseg8e32).

Problem Description:

The get_log2 function in trans_rvv.c.inc returned a value 1 higher than the actual log2 value. For example, get_log2(4) incorrectly returned 3 instead of 2.

This led to erroneous vector register offset calculations, resulting in data overlap where bytes 32-47 were incorrectly copied to positions 16-31 in ChaCha20 encryption code.

rvv_test_func:

     vsetivli    zero, 1, e32, m1, ta, ma
     li          t0, 64

     vlsseg8e32.v v0, (a0), t0
     addi        a0, a0, 32
     vlsseg8e32.v v8, (a0), t0

     vssseg8e32.v v0, (a1), t0
     addi        a1, a1, 32
     vssseg8e32.v v8, (a1), t0
     ret

Analysis:

The original implementation counted the number of right shifts until zero, including the final shift that reduced the value to zero:

static inline uint32_t get_log2(uint32_t a)

{
     uint32_t i = 0;
     for (; a > 0;) {
         a >>= 1;
         i++;
     }
     return i; // Returns 3 for a=4 (0b100 → 0b10 → 0b1 → 0b0)
}

Fix:

The corrected function stops shifting when only the highest bit remains and handles the special case of a=0:

static inline uint32_t get_log2(uint32_t a)

{
     uint32_t i = 0;
     if (a == 0) {
         return i; // Handle edge case
     }
     for (; a > 1; a >>= 1) {
         i++;
     }
     return i; // Now returns 2 for a=4
}
Fixes 28c12c1f2f ("Generate strided vector loads/stores with tcg nodes.")
---
  target/riscv/insn_trans/trans_rvv.c.inc | 5 ++++-
  1 file changed, 4 insertions(+), 1 deletion(-)
target/riscv/insn_trans/trans_rvv.c.inc +0 -0
index 2b6077ac06..f50b62b1d8 100644
@@ -877,7 +877,10 @@ static inline uint32_t MAXSZ(DisasContext *s)
  static inline uint32_t get_log2(uint32_t a)

target/riscv/insn_trans/trans_rvv.c.inc static inline uint32_t MAXSZ(DisasContext *s) · line 886

Quoted 10 lines
target/riscv/insn_trans/trans_rvv.c.inc +4 -1
  {
      uint32_t i = 0;
-    for (; a > 0;) {
+    if (a == 0) {
+        return i;
+    }
+    for (; a > 1;) {
          a >>= 1;
          i++;
      }

I suggest

    assert(is_power_of_2(a));
    return ctz32(a);

I was surprised we don't have such a function in qemu/host-utils.h already.

r~