On Wed, Oct 9, 2024 at 9:04 AM Avi Kivity <avi@xxxxxxxxxxxx> wrote:
>
> On Linux 6.10.10 with CONFIG_READ_ONLY_THP_FOR_FS=y,
> madvise(MADV_COLLAPSE) on program text fails with EINVAL.
>
> To reproduce, compile the reproducer with
>
> clang -g -o text-hugepage text-hugepage.c \
> -fuse-ld=lld \
> -Wl,-zcommon-page-size=2097152 -Wl,-zmax-page-size=2097152 \
> -Wl,-z,separate-loadable-segments
>
> and run:
Didn't clang make the page cache dirty?
Having sync between clang and the execution made the problem go away for me.
>
> $ strace -e trace=madvise ./text-hugepage
> madvise(0x400000, 2097152, MADV_HUGEPAGE) = 0
> madvise(0x400000, 2097152, MADV_POPULATE_READ) = 0
> madvise(0x400000, 2097152, MADV_COLLAPSE) = -1 EINVAL (Invalid
> argument)
>
> (the funky linker options are needed to make sure the .text vma spans a
> hugepage).
>
>
> I say "possible regression" since I haven't tried it with an older
> kernel, but I believe it worked at some point or other seeing that
> others managed to get it to work.
>
> ==== text-hugepage.c ====
> #include <stdlib.h>
> #include <stdint.h>
> #include <stdio.h>
> #include <string.h>
>
> #include <sys/mman.h>
>
> static
> void
> try_remap_text_segment() {
> FILE *fp = fopen("/proc/self/maps", "r");
> if (!fp) {
> return;
> }
> char *buf = NULL;
> size_t n;
> while (getline(&buf, &n, fp) >= 0) {
> char *lstart = buf;
> char *lmid = strchr(lstart, '-');
> if (!lmid) {
> continue;
> }
> *lmid++ = '\0';
> char *lend = strchr(lmid, ' ');
> if (!lend) {
> continue;
> }
> *lend = '\0';
>
> size_t start = strtoul(lstart, NULL, 16);
> size_t end = strtoul(lmid, NULL, 16);
> uintptr_t some_text_addr = (uintptr_t)&try_remap_text_segment;
> if (some_text_addr >= start && some_text_addr < end) {
> end &= ~(uintptr_t)0x1fffff;
> madvise((void*)start, end - start, MADV_HUGEPAGE);
> madvise((void*)start, end - start, MADV_POPULATE_READ);
> madvise((void*)start, end - start, MADV_COLLAPSE);
> break;
> }
> }
> free(buf);
> fclose(fp);
> }
>
> void
> huge_function() {
> // Make sure .text is has a huge page full of stuff
> asm volatile (".fill 4000000, 1, 0x90");
> }
>
> int
> main() {
> try_remap_text_segment();
> }
> ==== end text-hugepage.c ====
>
