Currently QEMU ignores madvise(MADV_DONTNEED), which break apps that
rely on this for zeroing out memory [1]. Improve the situation by doing
a passthrough when the range in question is a host-page-aligned
anonymous mapping.

This is based on the patches from Simon Hausmann [2] and Chris Fallin
[3]. The structure is taken from Simon's patch. The PAGE_MAP_ANONYMOUS
bits are superseded by commit 26bab757d41b ("linux-user: Introduce
PAGE_ANON"). In the end the patch acts like the one from Chris: we
either pass-through the entire syscall, or do nothing, since doing this
only partially would not help the affected applications much. Finally,
add some extra checks to match the behavior of the Linux kernel [4].

[1] https://gitlab.com/qemu-project/qemu/-/issues/326
[2] https://patchew.org/QEMU/20180827084037.25316-1-simon.hausm...@qt.io/
[3] 
https://github.com/bytecodealliance/wasmtime/blob/v0.37.0/ci/qemu-madvise.patch
[4] 
https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/mm/madvise.c?h=v5.19-rc3#n1368

Signed-off-by: Ilya Leoshkevich <i...@linux.ibm.com>
---
 linux-user/mmap.c      | 68 ++++++++++++++++++++++++++++++++++++++++++
 linux-user/syscall.c   |  6 +---
 linux-user/user-mmap.h |  1 +
 3 files changed, 70 insertions(+), 5 deletions(-)

diff --git a/linux-user/mmap.c b/linux-user/mmap.c
index 48e1373796..900df7b28c 100644
--- a/linux-user/mmap.c
+++ b/linux-user/mmap.c
@@ -835,3 +835,71 @@ abi_long target_mremap(abi_ulong old_addr, abi_ulong 
old_size,
     mmap_unlock();
     return new_addr;
 }
+
+static bool can_passthrough_madv_dontneed(abi_ulong start, abi_ulong end)
+{
+    ulong addr;
+
+    if ((start | end) & ~qemu_host_page_mask) {
+        return false;
+    }
+
+    for (addr = start; addr < end; addr += TARGET_PAGE_SIZE) {
+        if (!(page_get_flags(addr) & PAGE_ANON)) {
+            return false;
+        }
+    }
+
+    return true;
+}
+
+int target_madvise(abi_ulong start, abi_ulong len_in, int advice)
+{
+    abi_ulong len, end;
+    int ret = 0;
+
+    if (start & ~TARGET_PAGE_MASK) {
+        errno = EINVAL;
+        return -1;
+    }
+    len = TARGET_PAGE_ALIGN(len_in);
+
+    if (len_in && !len) {
+        errno = EINVAL;
+        return -1;
+    }
+
+    end = start + len;
+    if (end < start) {
+        errno = EINVAL;
+        return -1;
+    }
+
+    if (end == start) {
+        return 0;
+    }
+
+    if (!guest_range_valid_untagged(start, len)) {
+        errno = EINVAL;
+        return -1;
+    }
+
+    /*
+     * A straight passthrough may not be safe because qemu sometimes turns
+     * private file-backed mappings into anonymous mappings.
+     *
+     * This is a hint, so ignoring and returning success is ok.
+     *
+     * This breaks MADV_DONTNEED, completely implementing which is quite
+     * complicated. However, there is one low-hanging fruit: host-page-aligned
+     * anonymous mappings. In this case passthrough is safe, so do it.
+     */
+    mmap_lock();
+    if ((advice & MADV_DONTNEED) &&
+        can_passthrough_madv_dontneed(start, end)) {
+        ret = madvise(g2h_untagged(start), len, MADV_DONTNEED);
+    }
+    mmap_unlock();
+
+    return ret;
+}
diff --git a/linux-user/syscall.c b/linux-user/syscall.c
index f55cdebee5..d25759b992 100644
--- a/linux-user/syscall.c
+++ b/linux-user/syscall.c
@@ -11807,11 +11807,7 @@ static abi_long do_syscall1(CPUArchState *cpu_env, int 
num, abi_long arg1,
 
 #ifdef TARGET_NR_madvise
     case TARGET_NR_madvise:
-        /* A straight passthrough may not be safe because qemu sometimes
-           turns private file-backed mappings into anonymous mappings.
-           This will break MADV_DONTNEED.
-           This is a hint, so ignoring and returning success is ok.  */
-        return 0;
+        return get_errno(target_madvise(arg1, arg2, arg3));
 #endif
 #ifdef TARGET_NR_fcntl64
     case TARGET_NR_fcntl64:
diff --git a/linux-user/user-mmap.h b/linux-user/user-mmap.h
index d1dec99c02..41cd358c7a 100644
--- a/linux-user/user-mmap.h
+++ b/linux-user/user-mmap.h
@@ -25,6 +25,7 @@ int target_munmap(abi_ulong start, abi_ulong len);
 abi_long target_mremap(abi_ulong old_addr, abi_ulong old_size,
                        abi_ulong new_size, unsigned long flags,
                        abi_ulong new_addr);
+int target_madvise(abi_ulong start, abi_ulong len_in, int advice);
 extern unsigned long last_brk;
 extern abi_ulong mmap_next_start;
 abi_ulong mmap_find_vma(abi_ulong, abi_ulong, abi_ulong);
-- 
2.35.3


Reply via email to