summaryrefslogtreecommitdiff
path: root/ipc
diff options
context:
space:
mode:
authorHugh Dickins <hughd@google.com>2023-10-19 23:39:08 +0300
committerAndrew Morton <akpm@linux-foundation.org>2023-10-26 02:47:16 +0300
commitddc1a5cbc05dc62743a2f409b96faa5cf95ba064 (patch)
tree6d3b7083fd984acd1391818a32ef9a7dd46049e7 /ipc
parent23e4883248f0472d806c8b3422ba6257e67bf1a5 (diff)
downloadlinux-ddc1a5cbc05dc62743a2f409b96faa5cf95ba064.tar.xz
mempolicy: alloc_pages_mpol() for NUMA policy without vma
Shrink shmem's stack usage by eliminating the pseudo-vma from its folio allocation. alloc_pages_mpol(gfp, order, pol, ilx, nid) becomes the principal actor for passing mempolicy choice down to __alloc_pages(), rather than vma_alloc_folio(gfp, order, vma, addr, hugepage). vma_alloc_folio() and alloc_pages() remain, but as wrappers around alloc_pages_mpol(). alloc_pages_bulk_*() untouched, except to provide the additional args to policy_nodemask(), which subsumes policy_node(). Cleanup throughout, cutting out some unhelpful "helpers". It would all be much simpler without MPOL_INTERLEAVE, but that adds a dynamic to the constant mpol: complicated by v3.6 commit 09c231cb8bfd ("tmpfs: distribute interleave better across nodes"), which added ino bias to the interleave, hidden from mm/mempolicy.c until this commit. Hence "ilx" throughout, the "interleave index". Originally I thought it could be done just with nid, but that's wrong: the nodemask may come from the shared policy layer below a shmem vma, or it may come from the task layer above a shmem vma; and without the final nodemask then nodeid cannot be decided. And how ilx is applied depends also on page order. The interleave index is almost always irrelevant unless MPOL_INTERLEAVE: with one exception in alloc_pages_mpol(), where the NO_INTERLEAVE_INDEX passed down from vma-less alloc_pages() is also used as hint not to use THP-style hugepage allocation - to avoid the overhead of a hugepage arg (though I don't understand why we never just added a GFP bit for THP - if it actually needs a different allocation strategy from other pages of the same order). vma_alloc_folio() still carries its hugepage arg here, but it is not used, and should be removed when agreed. get_vma_policy() no longer allows a NULL vma: over time I believe we've eradicated all the places which used to need it e.g. swapoff and madvise used to pass NULL vma to read_swap_cache_async(), but now know the vma. [hughd@google.com: handle NULL mpol being passed to __read_swap_cache_async()] Link: https://lkml.kernel.org/r/ea419956-4751-0102-21f7-9c93cb957892@google.com Link: https://lkml.kernel.org/r/74e34633-6060-f5e3-aee-7040d43f2e93@google.com Link: https://lkml.kernel.org/r/1738368e-bac0-fd11-ed7f-b87142a939fe@google.com Signed-off-by: Hugh Dickins <hughd@google.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Christoph Lameter <cl@linux.com> Cc: David Hildenbrand <david@redhat.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Huang Ying <ying.huang@intel.com> Cc: Kefeng Wang <wangkefeng.wang@huawei.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Mel Gorman <mgorman@techsingularity.net> Cc: Michal Hocko <mhocko@suse.com> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Nhat Pham <nphamcs@gmail.com> Cc: Sidhartha Kumar <sidhartha.kumar@oracle.com> Cc: Suren Baghdasaryan <surenb@google.com> Cc: Tejun heo <tj@kernel.org> Cc: Vishal Moola (Oracle) <vishal.moola@gmail.com> Cc: Yang Shi <shy828301@gmail.com> Cc: Yosry Ahmed <yosryahmed@google.com> Cc: Domenico Cerasuolo <mimmocerasuolo@gmail.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Diffstat (limited to 'ipc')
-rw-r--r--ipc/shm.c21
1 files changed, 8 insertions, 13 deletions
diff --git a/ipc/shm.c b/ipc/shm.c
index 576a543b7cff..222aaf035afb 100644
--- a/ipc/shm.c
+++ b/ipc/shm.c
@@ -562,30 +562,25 @@ static unsigned long shm_pagesize(struct vm_area_struct *vma)
}
#ifdef CONFIG_NUMA
-static int shm_set_policy(struct vm_area_struct *vma, struct mempolicy *new)
+static int shm_set_policy(struct vm_area_struct *vma, struct mempolicy *mpol)
{
- struct file *file = vma->vm_file;
- struct shm_file_data *sfd = shm_file_data(file);
+ struct shm_file_data *sfd = shm_file_data(vma->vm_file);
int err = 0;
if (sfd->vm_ops->set_policy)
- err = sfd->vm_ops->set_policy(vma, new);
+ err = sfd->vm_ops->set_policy(vma, mpol);
return err;
}
static struct mempolicy *shm_get_policy(struct vm_area_struct *vma,
- unsigned long addr)
+ unsigned long addr, pgoff_t *ilx)
{
- struct file *file = vma->vm_file;
- struct shm_file_data *sfd = shm_file_data(file);
- struct mempolicy *pol = NULL;
+ struct shm_file_data *sfd = shm_file_data(vma->vm_file);
+ struct mempolicy *mpol = vma->vm_policy;
if (sfd->vm_ops->get_policy)
- pol = sfd->vm_ops->get_policy(vma, addr);
- else if (vma->vm_policy)
- pol = vma->vm_policy;
-
- return pol;
+ mpol = sfd->vm_ops->get_policy(vma, addr, ilx);
+ return mpol;
}
#endif