Add runtime detection for MADV_DONTNEED zeroes pages (mostly for qemu)

qemu does not support this, yet [1], and you can get very tricky assert
if you will run program with jemalloc in use under qemu:

    <jemalloc>: ../contrib/jemalloc/src/extent.c:1195: Failed assertion: "p[i] == 0"

  [1]: https://patchwork.kernel.org/patch/10576637/

Here is a simple example that shows the problem [2]:

    // Gist to check possible issues with MADV_DONTNEED
    // For example it does not supported by qemu user
    // There is a patch for this [1], but it hasn't been applied.
    //   [1]: https://lists.gnu.org/archive/html/qemu-devel/2018-08/msg05422.html

    #include <sys/mman.h>
    #include <stdio.h>
    #include <stddef.h>
    #include <assert.h>
    #include <string.h>

    int main(int argc, char **argv)
    {
        void *addr = mmap(NULL, 1<<16, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANONYMOUS, -1, 0);
        if (addr == MAP_FAILED) {
            perror("mmap");
            return 1;
        }
        memset(addr, 'A', 1<<16);

        if (!madvise(addr, 1<<16, MADV_DONTNEED)) {
            puts("MADV_DONTNEED does not return error. Check memory.");
            for (int i = 0; i < 1<<16; ++i) {
                assert(((unsigned char *)addr)[i] == 0);
            }
        } else {
            perror("madvise");
        }

        if (munmap(addr, 1<<16)) {
            perror("munmap");
            return 1;
        }

        return 0;
    }

  ### unpatched qemu

      $ qemu-x86_64-static /tmp/test-MADV_DONTNEED
      MADV_DONTNEED does not return error. Check memory.
      test-MADV_DONTNEED: /tmp/test-MADV_DONTNEED.c:19: main: Assertion `((unsigned char *)addr)[i] == 0' failed.
      qemu: uncaught target signal 6 (Aborted) - core dumped
      Aborted (core dumped)

  ### patched qemu (by returning ENOSYS error)

      $ qemu-x86_64 /tmp/test-MADV_DONTNEED
      madvise: Success

  ### patch for qemu to return ENOSYS

      diff --git a/linux-user/syscall.c b/linux-user/syscall.c
      index 897d20c076..5540792e0e 100644
      --- a/linux-user/syscall.c
      +++ b/linux-user/syscall.c
      @@ -11775,7 +11775,7 @@ static abi_long do_syscall1(void *cpu_env, int num, abi_long arg1,
                  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 ENOSYS;
       #endif
       #ifdef TARGET_NR_fcntl64
           case TARGET_NR_fcntl64:

  [2]: https://gist.github.com/azat/12ba2c825b710653ece34dba7f926ece

v2:
- review fixes
- add opt_dont_trust_madvise
v3:
- review fixes
- rename opt_dont_trust_madvise to opt_trust_madvise
This commit is contained in:
Azat Khuzhin 2020-12-18 22:23:35 +03:00 committed by David Goldblatt
parent 2e3104ba07
commit a943172b73
6 changed files with 94 additions and 2 deletions

View file

@ -90,6 +90,7 @@ CTL_PROTO(config_utrace)
CTL_PROTO(config_xmalloc)
CTL_PROTO(opt_abort)
CTL_PROTO(opt_abort_conf)
CTL_PROTO(opt_trust_madvise)
CTL_PROTO(opt_confirm_conf)
CTL_PROTO(opt_hpa)
CTL_PROTO(opt_hpa_slab_max_alloc)
@ -372,6 +373,7 @@ static const ctl_named_node_t config_node[] = {
static const ctl_named_node_t opt_node[] = {
{NAME("abort"), CTL(opt_abort)},
{NAME("abort_conf"), CTL(opt_abort_conf)},
{NAME("trust_madvise"), CTL(opt_trust_madvise)},
{NAME("confirm_conf"), CTL(opt_confirm_conf)},
{NAME("hpa"), CTL(opt_hpa)},
{NAME("hpa_slab_max_alloc"), CTL(opt_hpa_slab_max_alloc)},
@ -2045,6 +2047,7 @@ CTL_RO_CONFIG_GEN(config_xmalloc, bool)
CTL_RO_NL_GEN(opt_abort, opt_abort, bool)
CTL_RO_NL_GEN(opt_abort_conf, opt_abort_conf, bool)
CTL_RO_NL_GEN(opt_trust_madvise, opt_trust_madvise, bool)
CTL_RO_NL_GEN(opt_confirm_conf, opt_confirm_conf, bool)
CTL_RO_NL_GEN(opt_hpa, opt_hpa, bool)
CTL_RO_NL_GEN(opt_hpa_slab_max_alloc, opt_hpa_slab_max_alloc, size_t)