diff mbox series

[for-8.1] accel/tcg: Avoid reading too much in load_atom_{2,4}

Message ID 20230810154802.16663-1-richard.henderson@linaro.org
State Superseded
Headers show
Series [for-8.1] accel/tcg: Avoid reading too much in load_atom_{2,4} | expand

Commit Message

Richard Henderson Aug. 10, 2023, 3:48 p.m. UTC
When load_atom_extract_al16_or_al8 is inexpensive, we want to use
it early, in order to avoid the overhead of required_atomicity.
However, we must not read past the end of the page.

Reported-by: Mark Cave-Ayland <mark.cave-ayland@ilande.co.uk>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---

This should solve the problem that Mark reported for m68k.  In his
system-mode scenario, we would need a tlb fault on the final 7 bytes
of the final page of system ram.

With aarch64 FEAT_LSE2 I can create an internal alignment fault that
leads to the same code path -- the test case fails before the fix.


r~

---
 tests/tcg/aarch64/lse2-fault.c    | 38 +++++++++++++++++++++++++++++++
 accel/tcg/ldst_atomicity.c.inc    | 10 ++++++--
 tests/tcg/aarch64/Makefile.target |  2 +-
 3 files changed, 47 insertions(+), 3 deletions(-)
 create mode 100644 tests/tcg/aarch64/lse2-fault.c

Comments

Philippe Mathieu-Daudé Aug. 10, 2023, 3:53 p.m. UTC | #1
On 10/8/23 17:48, Richard Henderson wrote:
> When load_atom_extract_al16_or_al8 is inexpensive, we want to use
> it early, in order to avoid the overhead of required_atomicity.
> However, we must not read past the end of the page.
> 
> Reported-by: Mark Cave-Ayland <mark.cave-ayland@ilande.co.uk>
> Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
> ---


> diff --git a/accel/tcg/ldst_atomicity.c.inc b/accel/tcg/ldst_atomicity.c.inc
> index e5c590a499..5d92485a49 100644
> --- a/accel/tcg/ldst_atomicity.c.inc
> +++ b/accel/tcg/ldst_atomicity.c.inc
> @@ -404,7 +404,10 @@ static uint16_t load_atom_2(CPUArchState *env, uintptr_t ra,
>           return load_atomic2(pv);
>       }
>       if (HAVE_ATOMIC128_RO) {
> -        return load_atom_extract_al16_or_al8(pv, 2);
> +        intptr_t left_in_page = pi | TARGET_PAGE_MASK;
> +        if (likely(left_in_page <= -16)) {
> +            return load_atom_extract_al16_or_al8(pv, 2);
> +        }
>       }
>   
>       atmax = required_atomicity(env, pi, memop);
> @@ -443,7 +446,10 @@ static uint32_t load_atom_4(CPUArchState *env, uintptr_t ra,
>           return load_atomic4(pv);
>       }
>       if (HAVE_ATOMIC128_RO) {
> -        return load_atom_extract_al16_or_al8(pv, 4);
> +        intptr_t left_in_page = pi | TARGET_PAGE_MASK;
> +        if (likely(left_in_page <= -16)) {
> +            return load_atom_extract_al16_or_al8(pv, 4);
> +        }
>       }

Makes sense, so to the best of my knowledge:

Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Peter Maydell Aug. 10, 2023, 3:56 p.m. UTC | #2
On Thu, 10 Aug 2023 at 16:49, Richard Henderson
<richard.henderson@linaro.org> wrote:
>
> When load_atom_extract_al16_or_al8 is inexpensive, we want to use
> it early, in order to avoid the overhead of required_atomicity.
> However, we must not read past the end of the page.
>
> Reported-by: Mark Cave-Ayland <mark.cave-ayland@ilande.co.uk>
> Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
> ---



>      if (HAVE_ATOMIC128_RO) {
> -        return load_atom_extract_al16_or_al8(pv, 2);
> +        intptr_t left_in_page = pi | TARGET_PAGE_MASK;

isn't left_in_page actually -(pi | TARGET_PAGE_MASK) ?
I feel like that would be clearer than leaving it
the negative of the number of bytes left in the page
and comparing against -16 (and assume the compiler
generates equivalent code).

(I always have trouble with expressions that combine
boolean operations and 2s-complement arithmetic, though.)

> +        if (likely(left_in_page <= -16)) {
> +            return load_atom_extract_al16_or_al8(pv, 2);
> +        }
>      }

Either way
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>

thanks
-- PMM
diff mbox series

Patch

diff --git a/tests/tcg/aarch64/lse2-fault.c b/tests/tcg/aarch64/lse2-fault.c
new file mode 100644
index 0000000000..2187219a08
--- /dev/null
+++ b/tests/tcg/aarch64/lse2-fault.c
@@ -0,0 +1,38 @@ 
+#include <sys/mman.h>
+#include <sys/shm.h>
+#include <unistd.h>
+#include <stdio.h>
+
+int main()
+{
+    int psize = getpagesize();
+    int id;
+    void *p;
+
+    /*
+     * We need a shared mapping to enter CF_PARALLEL mode.
+     * The easiest way to get that is shmat.
+     */
+    id = shmget(IPC_PRIVATE, 2 * psize, IPC_CREAT | 0600);
+    if (id < 0) {
+        perror("shmget");
+        return 2;
+    }
+    p = shmat(id, NULL, 0);
+    if (p == MAP_FAILED) {
+        perror("shmat");
+        return 2;
+    }
+
+    /* Protect the second page. */
+    if (mprotect(p + psize, psize, PROT_NONE) < 0) {
+        perror("mprotect");
+        return 2;
+    }
+
+    /*
+     * Load 4 bytes, 6 bytes from the end of the page.
+     * On success this will load 0 from the newly allocated shm.
+     */
+    return *(int *)(p + psize - 6);
+}
diff --git a/accel/tcg/ldst_atomicity.c.inc b/accel/tcg/ldst_atomicity.c.inc
index e5c590a499..5d92485a49 100644
--- a/accel/tcg/ldst_atomicity.c.inc
+++ b/accel/tcg/ldst_atomicity.c.inc
@@ -404,7 +404,10 @@  static uint16_t load_atom_2(CPUArchState *env, uintptr_t ra,
         return load_atomic2(pv);
     }
     if (HAVE_ATOMIC128_RO) {
-        return load_atom_extract_al16_or_al8(pv, 2);
+        intptr_t left_in_page = pi | TARGET_PAGE_MASK;
+        if (likely(left_in_page <= -16)) {
+            return load_atom_extract_al16_or_al8(pv, 2);
+        }
     }
 
     atmax = required_atomicity(env, pi, memop);
@@ -443,7 +446,10 @@  static uint32_t load_atom_4(CPUArchState *env, uintptr_t ra,
         return load_atomic4(pv);
     }
     if (HAVE_ATOMIC128_RO) {
-        return load_atom_extract_al16_or_al8(pv, 4);
+        intptr_t left_in_page = pi | TARGET_PAGE_MASK;
+        if (likely(left_in_page <= -16)) {
+            return load_atom_extract_al16_or_al8(pv, 4);
+        }
     }
 
     atmax = required_atomicity(env, pi, memop);
diff --git a/tests/tcg/aarch64/Makefile.target b/tests/tcg/aarch64/Makefile.target
index 617f821613..681dfa077c 100644
--- a/tests/tcg/aarch64/Makefile.target
+++ b/tests/tcg/aarch64/Makefile.target
@@ -9,7 +9,7 @@  AARCH64_SRC=$(SRC_PATH)/tests/tcg/aarch64
 VPATH 		+= $(AARCH64_SRC)
 
 # Base architecture tests
-AARCH64_TESTS=fcvt pcalign-a64
+AARCH64_TESTS=fcvt pcalign-a64 lse2-fault
 
 fcvt: LDFLAGS+=-lm