diff options
author | Ryan Roberts | 2023-12-07 16:12:04 +0000 |
---|---|---|
committer | Andrew Morton | 2023-12-20 14:48:12 -0800 |
commit | 3485b88390b0af9e05dc2c3f57e9936f41e159a0 (patch) | |
tree | 023201bcd36dff0107643d203289c09e9879baef /mm/khugepaged.c | |
parent | 372cbd4d5a0665bf7e181c72f5e40e1bf59b0b08 (diff) |
mm: thp: introduce multi-size THP sysfs interface
In preparation for adding support for anonymous multi-size THP, introduce
new sysfs structure that will be used to control the new behaviours. A
new directory is added under transparent_hugepage for each supported THP
size, and contains an `enabled` file, which can be set to "inherit" (to
inherit the global setting), "always", "madvise" or "never". For now, the
kernel still only supports PMD-sized anonymous THP, so only 1 directory is
populated.
The first half of the change converts transhuge_vma_suitable() and
hugepage_vma_check() so that they take a bitfield of orders for which the
user wants to determine support, and the functions filter out all the
orders that can't be supported, given the current sysfs configuration and
the VMA dimensions. The resulting functions are renamed to
thp_vma_suitable_orders() and thp_vma_allowable_orders() respectively.
Convenience functions that take a single, unencoded order and return a
boolean are also defined as thp_vma_suitable_order() and
thp_vma_allowable_order().
The second half of the change implements the new sysfs interface. It has
been done so that each supported THP size has a `struct thpsize`, which
describes the relevant metadata and is itself a kobject. This is pretty
minimal for now, but should make it easy to add new per-thpsize files to
the interface if needed in future (e.g. per-size defrag). Rather than
keep the `enabled` state directly in the struct thpsize, I've elected to
directly encode it into huge_anon_orders_[always|madvise|inherit]
bitfields since this reduces the amount of work required in
thp_vma_allowable_orders() which is called for every page fault.
See Documentation/admin-guide/mm/transhuge.rst, as modified by this
commit, for details of how the new sysfs interface works.
[ryan.roberts@arm.com: fix build warning when CONFIG_SYSFS is disabled]
Link: https://lkml.kernel.org/r/20231211125320.3997543-1-ryan.roberts@arm.com
Link: https://lkml.kernel.org/r/20231207161211.2374093-4-ryan.roberts@arm.com
Signed-off-by: Ryan Roberts <ryan.roberts@arm.com>
Reviewed-by: Barry Song <v-songbaohua@oppo.com>
Tested-by: Kefeng Wang <wangkefeng.wang@huawei.com>
Tested-by: John Hubbard <jhubbard@nvidia.com>
Acked-by: David Hildenbrand <david@redhat.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: David Rientjes <rientjes@google.com>
Cc: "Huang, Ying" <ying.huang@intel.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Itaru Kitayama <itaru.kitayama@gmail.com>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Luis Chamberlain <mcgrof@kernel.org>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Yang Shi <shy828301@gmail.com>
Cc: Yin Fengwei <fengwei.yin@intel.com>
Cc: Yu Zhao <yuzhao@google.com>
Cc: Zi Yan <ziy@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Diffstat (limited to 'mm/khugepaged.c')
-rw-r--r-- | mm/khugepaged.c | 20 |
1 files changed, 12 insertions, 8 deletions
diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 064654717843..d72aecd3624a 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -446,7 +446,8 @@ void khugepaged_enter_vma(struct vm_area_struct *vma, { if (!test_bit(MMF_VM_HUGEPAGE, &vma->vm_mm->flags) && hugepage_flags_enabled()) { - if (hugepage_vma_check(vma, vm_flags, false, false, true)) + if (thp_vma_allowable_order(vma, vm_flags, false, false, true, + PMD_ORDER)) __khugepaged_enter(vma->vm_mm); } } @@ -922,16 +923,16 @@ static int hugepage_vma_revalidate(struct mm_struct *mm, unsigned long address, if (!vma) return SCAN_VMA_NULL; - if (!transhuge_vma_suitable(vma, address)) + if (!thp_vma_suitable_order(vma, address, PMD_ORDER)) return SCAN_ADDRESS_RANGE; - if (!hugepage_vma_check(vma, vma->vm_flags, false, false, - cc->is_khugepaged)) + if (!thp_vma_allowable_order(vma, vma->vm_flags, false, false, + cc->is_khugepaged, PMD_ORDER)) return SCAN_VMA_CHECK; /* * Anon VMA expected, the address may be unmapped then * remapped to file after khugepaged reaquired the mmap_lock. * - * hugepage_vma_check may return true for qualified file + * thp_vma_allowable_order may return true for qualified file * vmas. */ if (expect_anon && (!(*vmap)->anon_vma || !vma_is_anonymous(*vmap))) @@ -1503,7 +1504,8 @@ int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr, * and map it by a PMD, regardless of sysfs THP settings. As such, let's * analogously elide sysfs THP settings here. */ - if (!hugepage_vma_check(vma, vma->vm_flags, false, false, false)) + if (!thp_vma_allowable_order(vma, vma->vm_flags, false, false, false, + PMD_ORDER)) return SCAN_VMA_CHECK; /* Keep pmd pgtable for uffd-wp; see comment in retract_page_tables() */ @@ -2368,7 +2370,8 @@ static unsigned int khugepaged_scan_mm_slot(unsigned int pages, int *result, progress++; break; } - if (!hugepage_vma_check(vma, vma->vm_flags, false, false, true)) { + if (!thp_vma_allowable_order(vma, vma->vm_flags, false, false, + true, PMD_ORDER)) { skip: progress++; continue; @@ -2705,7 +2708,8 @@ int madvise_collapse(struct vm_area_struct *vma, struct vm_area_struct **prev, *prev = vma; - if (!hugepage_vma_check(vma, vma->vm_flags, false, false, false)) + if (!thp_vma_allowable_order(vma, vma->vm_flags, false, false, false, + PMD_ORDER)) return -EINVAL; cc = kmalloc(sizeof(*cc), GFP_KERNEL); |