accel/tcg: Avoid reading too much in load_atom_{2,4}

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.

If there are more than 8 bytes remaining, then both the "aligned 16"
and "aligned 8" paths align down so that the read has at least
16 bytes remaining on the page.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

3 files changed, 47 insertions, 3 deletions

diff --git a/accel/tcg/ldst_atomicity.c.inc b/accel/tcg/ldst_atomicity.c.inc
index e5c590a..1b793e6 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 > 8)) {
+            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 > 8)) {
+            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 617f821..681dfa0 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
 
diff --git a/tests/tcg/aarch64/lse2-fault.c b/tests/tcg/aarch64/lse2-fault.c
new file mode 100644
index 0000000..2187219
--- /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);
+}