From 89c83fb539f95491be80cdd5158e6f0ce329e317 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Fri, 2 Nov 2018 15:48:31 -0700 Subject: mm, thp: consolidate THP gfp handling into alloc_hugepage_direct_gfpmask THP allocation mode is quite complex and it depends on the defrag mode. This complexity is hidden in alloc_hugepage_direct_gfpmask from a large part currently. The NUMA special casing (namely __GFP_THISNODE) is however independent and placed in alloc_pages_vma currently. This both adds an unnecessary branch to all vma based page allocation requests and it makes the code more complex unnecessarily as well. Not to mention that e.g. shmem THP used to do the node reclaiming unconditionally regardless of the defrag mode until recently. This was not only unexpected behavior but it was also hardly a good default behavior and I strongly suspect it was just a side effect of the code sharing more than a deliberate decision which suggests that such a layering is wrong. Get rid of the thp special casing from alloc_pages_vma and move the logic to alloc_hugepage_direct_gfpmask. __GFP_THISNODE is applied to the resulting gfp mask only when the direct reclaim is not requested and when there is no explicit numa binding to preserve the current logic. Please note that there's also a slight difference wrt MPOL_BIND now. The previous code would avoid using __GFP_THISNODE if the local node was outside of policy_nodemask(). After this patch __GFP_THISNODE is avoided for all MPOL_BIND policies. So there's a difference that if local node is actually allowed by the bind policy's nodemask, previously __GFP_THISNODE would be added, but now it won't be. From the behavior POV this is still correct because the policy nodemask is used. Link: http://lkml.kernel.org/r/20180925120326.24392-3-mhocko@kernel.org Signed-off-by: Michal Hocko Acked-by: Vlastimil Babka Cc: Alex Williamson Cc: Andrea Arcangeli Cc: David Rientjes Cc: "Kirill A. Shutemov" Cc: Mel Gorman Cc: Stefan Priebe - Profihost AG Cc: Zi Yan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/mempolicy.c | 63 ++++------------------------------------------------------ 1 file changed, 4 insertions(+), 59 deletions(-) (limited to 'mm/mempolicy.c') diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 58fb833fce0c..5837a067124d 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -1116,8 +1116,8 @@ static struct page *new_page(struct page *page, unsigned long start) } else if (PageTransHuge(page)) { struct page *thp; - thp = alloc_hugepage_vma(GFP_TRANSHUGE, vma, address, - HPAGE_PMD_ORDER); + thp = alloc_pages_vma(GFP_TRANSHUGE, HPAGE_PMD_ORDER, vma, + address, numa_node_id()); if (!thp) return NULL; prep_transhuge_page(thp); @@ -1662,7 +1662,7 @@ struct mempolicy *__get_vma_policy(struct vm_area_struct *vma, * freeing by another task. It is the caller's responsibility to free the * extra reference for shared policies. */ -static struct mempolicy *get_vma_policy(struct vm_area_struct *vma, +struct mempolicy *get_vma_policy(struct vm_area_struct *vma, unsigned long addr) { struct mempolicy *pol = __get_vma_policy(vma, addr); @@ -2011,7 +2011,6 @@ static struct page *alloc_page_interleave(gfp_t gfp, unsigned order, * @vma: Pointer to VMA or NULL if not available. * @addr: Virtual Address of the allocation. Must be inside the VMA. * @node: Which node to prefer for allocation (modulo policy). - * @hugepage: for hugepages try only the preferred node if possible * * This function allocates a page from the kernel page pool and applies * a NUMA policy associated with the VMA or the current process. @@ -2022,7 +2021,7 @@ static struct page *alloc_page_interleave(gfp_t gfp, unsigned order, */ struct page * alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma, - unsigned long addr, int node, bool hugepage) + unsigned long addr, int node) { struct mempolicy *pol; struct page *page; @@ -2040,60 +2039,6 @@ alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma, goto out; } - if (unlikely(IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && hugepage)) { - int hpage_node = node; - - /* - * For hugepage allocation and non-interleave policy which - * allows the current node (or other explicitly preferred - * node) we only try to allocate from the current/preferred - * node and don't fall back to other nodes, as the cost of - * remote accesses would likely offset THP benefits. - * - * If the policy is interleave, or does not allow the current - * node in its nodemask, we allocate the standard way. - */ - if (pol->mode == MPOL_PREFERRED && - !(pol->flags & MPOL_F_LOCAL)) - hpage_node = pol->v.preferred_node; - - nmask = policy_nodemask(gfp, pol); - if (!nmask || node_isset(hpage_node, *nmask)) { - mpol_cond_put(pol); - /* - * We cannot invoke reclaim if __GFP_THISNODE - * is set. Invoking reclaim with - * __GFP_THISNODE set, would cause THP - * allocations to trigger heavy swapping - * despite there may be tons of free memory - * (including potentially plenty of THP - * already available in the buddy) on all the - * other NUMA nodes. - * - * At most we could invoke compaction when - * __GFP_THISNODE is set (but we would need to - * refrain from invoking reclaim even if - * compaction returned COMPACT_SKIPPED because - * there wasn't not enough memory to succeed - * compaction). For now just avoid - * __GFP_THISNODE instead of limiting the - * allocation path to a strict and single - * compaction invocation. - * - * Supposedly if direct reclaim was enabled by - * the caller, the app prefers THP regardless - * of the node it comes from so this would be - * more desiderable behavior than only - * providing THP originated from the local - * node in such case. - */ - if (!(gfp & __GFP_DIRECT_RECLAIM)) - gfp |= __GFP_THISNODE; - page = __alloc_pages_node(hpage_node, gfp, order); - goto out; - } - } - nmask = policy_nodemask(gfp, pol); preferred_nid = policy_node(gfp, pol, node); page = __alloc_pages_nodemask(gfp, order, preferred_nid, nmask); -- cgit v1.2.3-59-g8ed1b