The patch titled Subject: mm/shmem.c: thp, shmem: fix conflict of above-47bit hint address and PMD alignment has been added to the -mm tree. Its filename is thp-shmem-fix-conflict-of-above-47bit-hint-address-and-pmd-alignment.patch This patch should soon appear at http://ozlabs.org/~akpm/mmots/broken-out/thp-shmem-fix-conflict-of-above-47bit-hint-address-and-pmd-alignment.patch and later at http://ozlabs.org/~akpm/mmotm/broken-out/thp-shmem-fix-conflict-of-above-47bit-hint-address-and-pmd-alignment.patch Before you just go and hit "reply", please: a) Consider who else should be cc'ed b) Prefer to cc a suitable mailing list as well c) Ideally: find the original patch on the mailing list and do a reply-to-all to that, adding suitable additional cc's *** Remember to use Documentation/process/submit-checklist.rst when testing your code *** The -mm tree is included into linux-next and is updated there every 3-4 working days ------------------------------------------------------ From: "Kirill A. Shutemov" <kirill@xxxxxxxxxxxxx> Subject: mm/shmem.c: thp, shmem: fix conflict of above-47bit hint address and PMD alignment Shmem/tmpfs tries to provide THP-friendly mappings if huge pages are enabled. But it doesn't work well with above-47bit hint address. Normally, the kernel doesn't create userspace mappings above 47-bit, even if the machine allows this (such as with 5-level paging on x86-64). Not all user space is ready to handle wide addresses. It's known that at least some JIT compilers use higher bits in pointers to encode their information. Userspace can ask for allocation from full address space by specifying hint address (with or without MAP_FIXED) above 47-bits. If the application doesn't need a particular address, but wants to allocate from whole address space it can specify -1 as a hint address. Unfortunately, this trick breaks THP alignment in shmem/tmp: shmem_get_unmapped_area() would not try to allocate PMD-aligned area if *any* hint address specified. This can be fixed by requesting the aligned area if the we failed to allocated at user-specified hint address. The request with inflated length will also take the user-specified hint address. This way we will not lose an allocation request from the full address space. Link: http://lkml.kernel.org/r/20191220142548.7118-3-kirill.shutemov@xxxxxxxxxxxxxxx Fixes: b569bab78d8d ("x86/mm: Prepare to expose larger address space to userspace") Signed-off-by: Kirill A. Shutemov <kirill.shutemov@xxxxxxxxxxxxxxx> Cc: "Willhalm, Thomas" <thomas.willhalm@xxxxxxxxx> Cc: Dan Williams <dan.j.williams@xxxxxxxxx> Cc: "Bruggeman, Otto G" <otto.g.bruggeman@xxxxxxxxx> Cc: "Aneesh Kumar K . V" <aneesh.kumar@xxxxxxxxxxxxxxxxxx> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> --- mm/shmem.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) --- a/mm/shmem.c~thp-shmem-fix-conflict-of-above-47bit-hint-address-and-pmd-alignment +++ a/mm/shmem.c @@ -2107,9 +2107,10 @@ unsigned long shmem_get_unmapped_area(st /* * Our priority is to support MAP_SHARED mapped hugely; * and support MAP_PRIVATE mapped hugely too, until it is COWed. - * But if caller specified an address hint, respect that as before. + * But if caller specified an address hint and we allocated area there + * successfully, respect that as before. */ - if (uaddr) + if (uaddr == addr) return addr; if (shmem_huge != SHMEM_HUGE_FORCE) { @@ -2143,7 +2144,7 @@ unsigned long shmem_get_unmapped_area(st if (inflated_len < len) return addr; - inflated_addr = get_area(NULL, 0, inflated_len, 0, flags); + inflated_addr = get_area(uaddr, 0, inflated_len, 0, flags); if (IS_ERR_VALUE(inflated_addr)) return addr; if (inflated_addr & ~PAGE_MASK) _ Patches currently in -mm which might be from kirill@xxxxxxxxxxxxx are thp-fix-conflict-of-above-47bit-hint-address-and-pmd-alignment.patch thp-shmem-fix-conflict-of-above-47bit-hint-address-and-pmd-alignment.patch