CVE-2024-42317: mm/huge_memory: avoid PMD-size page cache if needed

In the Linux kernel, the following vulnerability has been resolved:

mm/hugememory: avoid PMD-size page cache if needed

xarray can't support arbitrary page cache size. the largest and supported page cache size is defined as MAXPAGECACHEORDER by commit 099d90642a71 ("mm/filemap: make MAXPAGECACHEORDER acceptable to xarray"). However, it's possible to have 512MB page cache in the huge memory's collapsing path on ARM64 system whose base page size is 64KB. 512MB page cache is breaking the limitation and a warning is raised when the xarray entry is split as shown in the following example.

[root@dhcp-10-26-1-207 ~]# cat /proc/1/smaps | grep KernelPageSize KernelPageSize: 64 kB [root@dhcp-10-26-1-207 ~]# cat /tmp/test.c : int main(int argc, char argv) { const char filename = TESTXFSFILENAME; int fd = 0; void buf = (void )-1, p; int pgsize = getpagesize(); int ret = 0;

if (pgsize != 0x10000) { fprintf(stdout, "System with 64KB base page size is required!\n"); return -EPERM; }

system("echo 0 > /sys/devices/virtual/bdi/253:0/readaheadkb"); system("echo 1 > /proc/sys/vm/dropcaches");

/ Open the xfs file / fd = open(filename, ORDONLY); assert(fd > 0);

/ Create VMA / buf = mmap(NULL, TESTMEMSIZE, PROTREAD, MAPSHARED, fd, 0); assert(buf != (void )-1); fprintf(stdout, "mapped buffer at 0x%p\n", buf);

/ Populate VMA / ret = madvise(buf, TESTMEMSIZE, MADVNOHUGEPAGE); assert(ret == 0); ret = madvise(buf, TESTMEMSIZE, MADVPOPULATEREAD); assert(ret == 0);

/ Collapse VMA / ret = madvise(buf, TESTMEMSIZE, MADVHUGEPAGE); assert(ret == 0); ret = madvise(buf, TESTMEMSIZE, MADVCOLLAPSE); if (ret) { fprintf(stdout, "Error %d to madvise(MADVCOLLAPSE)\n", errno); goto out; }

/ Split xarray entry. Write permission is needed / munmap(buf, TESTMEMSIZE); buf = (void )-1; close(fd); fd = open(filename, ORDWR); assert(fd > 0); fallocate(fd, FALLOCFLKEEPSIZE | FALLOCFLPUNCHHOLE, TESTMEMSIZE - pgsize, pgsize); out: if (buf != (void )-1) munmap(buf, TESTMEMSIZE); if (fd > 0) close(fd);

return ret; }

[root@dhcp-10-26-1-207 ~]# gcc /tmp/test.c -o /tmp/test [root@dhcp-10-26-1-207 ~]# /tmp/test ------------[ cut here ]------------ WARNING: CPU: 25 PID: 7560 at lib/xarray.c:1025 xassplitalloc+0xf8/0x128 Modules linked in: nftfibinet nftfibipv4 nftfibipv6 nftfib \ nftrejectinet nfrejectipv4 nfrejectipv6 nftreject nftct \ nftchainnat nfnat nfconntrack nfdefragipv6 nfdefragipv4 \ ipset rfkill nftables nfnetlink vfat fat virtioballoon drm fuse \ xfs libcrc32c crct10difce ghashce sha2ce sha256arm64 virtionet \ sha1ce netfailover virtioblk virtioconsole failover dimlib virtiommio CPU: 25 PID: 7560 Comm: test Kdump: loaded Not tainted 6.10.0-rc7-gavin+ #9 Hardware name: QEMU KVM Virtual Machine, BIOS edk2-20240524-1.el9 05/24/2024 pstate: 83400005 (Nzcv daif +PAN -UAO +TCO +DIT -SSBS BTYPE=--) pc : xassplitalloc+0xf8/0x128 lr : splithugepagetolisttoorder+0x1c4/0x780 sp : ffff8000ac32f660 x29: ffff8000ac32f660 x28: ffff0000e0969eb0 x27: ffff8000ac32f6c0 x26: 0000000000000c40 x25: ffff0000e0969eb0 x24: 000000000000000d x23: ffff8000ac32f6c0 x22: ffffffdfc0700000 x21: 0000000000000000 x20: 0000000000000000 x19: ffffffdfc0700000 x18: 0000000000000000 x17: 0000000000000000 x16: ffffd5f3708ffc70 x15: 0000000000000000 x14: 0000000000000000 x13: 0000000000000000 x12: 0000000000000000 x11: ffffffffffffffc0 x10: 0000000000000040 x9 : ffffd5f3708e692c x8 : 0000000000000003 x7 : 0000000000000000 x6 : ffff0000e0969eb8 x5 : ffffd5f37289e378 x4 : 0000000000000000 x3 : 0000000000000c40 x2 : 000000000000000d x1 : 000000000000000c x0 : 0000000000000000 Call trace: xassplitalloc+0xf8/0x128 splithugepagetolisttoorder+0x1c4/0x780 truncateinodepartialfolio+0xdc/0x160 truncateinodepagesrange+0x1b4/0x4a8 truncatepagecacherange+0x84/0xa ---truncated---