From aaf14e40a33a2c9350471387031ca40c00f5a006 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Mon, 10 Jul 2017 15:49:08 -0700 Subject: mm, hugetlb: unclutter hugetlb allocation layers Patch series "mm, hugetlb: allow proper node fallback dequeue". While working on a hugetlb migration issue addressed in a separate patchset[1] I have noticed that the hugetlb allocations from the preallocated pool are quite subotimal. [1] //lkml.kernel.org/r/20170608074553.22152-1-mhocko@kernel.org There is no fallback mechanism implemented and no notion of preferred node. I have tried to work around it but Vlastimil was right to push back for a more robust solution. It seems that such a solution is to reuse zonelist approach we use for the page alloctor. This series has 3 patches. The first one tries to make hugetlb allocation layers more clear. The second one implements the zonelist hugetlb pool allocation and introduces a preferred node semantic which is used by the migration callbacks. The last patch is a clean up. This patch (of 3): Hugetlb allocation path for fresh huge pages is unnecessarily complex and it mixes different interfaces between layers. __alloc_buddy_huge_page is the central place to perform a new allocation. It checks for the hugetlb overcommit and then relies on __hugetlb_alloc_buddy_huge_page to invoke the page allocator. This is all good except that __alloc_buddy_huge_page pushes vma and address down the callchain and so __hugetlb_alloc_buddy_huge_page has to deal with two different allocation modes - one for memory policy and other node specific (or to make it more obscure node non-specific) requests. This just screams for a reorganization. This patch pulls out all the vma specific handling up to __alloc_buddy_huge_page_with_mpol where it belongs. __alloc_buddy_huge_page will get nodemask argument and __hugetlb_alloc_buddy_huge_page will become a trivial wrapper over the page allocator. In short: __alloc_buddy_huge_page_with_mpol - memory policy handling __alloc_buddy_huge_page - overcommit handling and accounting __hugetlb_alloc_buddy_huge_page - page allocator layer Also note that __hugetlb_alloc_buddy_huge_page and its cpuset retry loop is not really needed because the page allocator already handles the cpusets update. Finally __hugetlb_alloc_buddy_huge_page had a special case for node specific allocations (when no policy is applied and there is a node given). This has relied on __GFP_THISNODE to not fallback to a different node. alloc_huge_page_node is the only caller which relies on this behavior so move the __GFP_THISNODE there. Not only does this remove quite some code it also should make those layers easier to follow and clear wrt responsibilities. Link: http://lkml.kernel.org/r/20170622193034.28972-2-mhocko@kernel.org Signed-off-by: Michal Hocko Acked-by: Vlastimil Babka Reviewed-by: Mike Kravetz Tested-by: Mike Kravetz Cc: Naoya Horiguchi Cc: Mel Gorman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/hugetlb.c | 133 +++++++++++++---------------------------------------------- 1 file changed, 29 insertions(+), 104 deletions(-) (limited to 'mm/hugetlb.c') diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 907786581812..fd6e0c50f949 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1521,82 +1521,19 @@ int dissolve_free_huge_pages(unsigned long start_pfn, unsigned long end_pfn) return rc; } -/* - * There are 3 ways this can get called: - * 1. With vma+addr: we use the VMA's memory policy - * 2. With !vma, but nid=NUMA_NO_NODE: We try to allocate a huge - * page from any node, and let the buddy allocator itself figure - * it out. - * 3. With !vma, but nid!=NUMA_NO_NODE. We allocate a huge page - * strictly from 'nid' - */ static struct page *__hugetlb_alloc_buddy_huge_page(struct hstate *h, - struct vm_area_struct *vma, unsigned long addr, int nid) + gfp_t gfp_mask, int nid, nodemask_t *nmask) { int order = huge_page_order(h); - gfp_t gfp = htlb_alloc_mask(h)|__GFP_COMP|__GFP_REPEAT|__GFP_NOWARN; - unsigned int cpuset_mems_cookie; - /* - * We need a VMA to get a memory policy. If we do not - * have one, we use the 'nid' argument. - * - * The mempolicy stuff below has some non-inlined bits - * and calls ->vm_ops. That makes it hard to optimize at - * compile-time, even when NUMA is off and it does - * nothing. This helps the compiler optimize it out. - */ - if (!IS_ENABLED(CONFIG_NUMA) || !vma) { - /* - * If a specific node is requested, make sure to - * get memory from there, but only when a node - * is explicitly specified. - */ - if (nid != NUMA_NO_NODE) - gfp |= __GFP_THISNODE; - /* - * Make sure to call something that can handle - * nid=NUMA_NO_NODE - */ - return alloc_pages_node(nid, gfp, order); - } - - /* - * OK, so we have a VMA. Fetch the mempolicy and try to - * allocate a huge page with it. We will only reach this - * when CONFIG_NUMA=y. - */ - do { - struct page *page; - struct mempolicy *mpol; - int nid; - nodemask_t *nodemask; - - cpuset_mems_cookie = read_mems_allowed_begin(); - nid = huge_node(vma, addr, gfp, &mpol, &nodemask); - mpol_cond_put(mpol); - page = __alloc_pages_nodemask(gfp, order, nid, nodemask); - if (page) - return page; - } while (read_mems_allowed_retry(cpuset_mems_cookie)); - - return NULL; + gfp_mask |= __GFP_COMP|__GFP_REPEAT|__GFP_NOWARN; + if (nid == NUMA_NO_NODE) + nid = numa_mem_id(); + return __alloc_pages_nodemask(gfp_mask, order, nid, nmask); } -/* - * There are two ways to allocate a huge page: - * 1. When you have a VMA and an address (like a fault) - * 2. When you have no VMA (like when setting /proc/.../nr_hugepages) - * - * 'vma' and 'addr' are only for (1). 'nid' is always NUMA_NO_NODE in - * this case which signifies that the allocation should be done with - * respect for the VMA's memory policy. - * - * For (2), we ignore 'vma' and 'addr' and use 'nid' exclusively. This - * implies that memory policies will not be taken in to account. - */ -static struct page *__alloc_buddy_huge_page(struct hstate *h, - struct vm_area_struct *vma, unsigned long addr, int nid) +static struct page *__alloc_buddy_huge_page(struct hstate *h, gfp_t gfp_mask, + int nid, nodemask_t *nmask) { struct page *page; unsigned int r_nid; @@ -1604,15 +1541,6 @@ static struct page *__alloc_buddy_huge_page(struct hstate *h, if (hstate_is_gigantic(h)) return NULL; - /* - * Make sure that anyone specifying 'nid' is not also specifying a VMA. - * This makes sure the caller is picking _one_ of the modes with which - * we can call this function, not both. - */ - if (vma || (addr != -1)) { - VM_WARN_ON_ONCE(addr == -1); - VM_WARN_ON_ONCE(nid != NUMA_NO_NODE); - } /* * Assume we will successfully allocate the surplus page to * prevent racing processes from causing the surplus to exceed @@ -1646,7 +1574,7 @@ static struct page *__alloc_buddy_huge_page(struct hstate *h, } spin_unlock(&hugetlb_lock); - page = __hugetlb_alloc_buddy_huge_page(h, vma, addr, nid); + page = __hugetlb_alloc_buddy_huge_page(h, gfp_mask, nid, nmask); spin_lock(&hugetlb_lock); if (page) { @@ -1670,19 +1598,6 @@ static struct page *__alloc_buddy_huge_page(struct hstate *h, return page; } -/* - * Allocate a huge page from 'nid'. Note, 'nid' may be - * NUMA_NO_NODE, which means that it may be allocated - * anywhere. - */ -static -struct page *__alloc_buddy_huge_page_no_mpol(struct hstate *h, int nid) -{ - unsigned long addr = -1; - - return __alloc_buddy_huge_page(h, NULL, addr, nid); -} - /* * Use the VMA's mpolicy to allocate a huge page from the buddy. */ @@ -1690,7 +1605,17 @@ static struct page *__alloc_buddy_huge_page_with_mpol(struct hstate *h, struct vm_area_struct *vma, unsigned long addr) { - return __alloc_buddy_huge_page(h, vma, addr, NUMA_NO_NODE); + struct page *page; + struct mempolicy *mpol; + gfp_t gfp_mask = htlb_alloc_mask(h); + int nid; + nodemask_t *nodemask; + + nid = huge_node(vma, addr, gfp_mask, &mpol, &nodemask); + page = __alloc_buddy_huge_page(h, gfp_mask, nid, nodemask); + mpol_cond_put(mpol); + + return page; } /* @@ -1700,21 +1625,26 @@ struct page *__alloc_buddy_huge_page_with_mpol(struct hstate *h, */ struct page *alloc_huge_page_node(struct hstate *h, int nid) { + gfp_t gfp_mask = htlb_alloc_mask(h); struct page *page = NULL; + if (nid != NUMA_NO_NODE) + gfp_mask |= __GFP_THISNODE; + spin_lock(&hugetlb_lock); if (h->free_huge_pages - h->resv_huge_pages > 0) page = dequeue_huge_page_node(h, nid); spin_unlock(&hugetlb_lock); if (!page) - page = __alloc_buddy_huge_page_no_mpol(h, nid); + page = __alloc_buddy_huge_page(h, gfp_mask, nid, NULL); return page; } -struct page *alloc_huge_page_nodemask(struct hstate *h, const nodemask_t *nmask) +struct page *alloc_huge_page_nodemask(struct hstate *h, nodemask_t *nmask) { + gfp_t gfp_mask = htlb_alloc_mask(h); struct page *page = NULL; int node; @@ -1731,13 +1661,7 @@ struct page *alloc_huge_page_nodemask(struct hstate *h, const nodemask_t *nmask) return page; /* No reservations, try to overcommit */ - for_each_node_mask(node, *nmask) { - page = __alloc_buddy_huge_page_no_mpol(h, node); - if (page) - return page; - } - - return NULL; + return __alloc_buddy_huge_page(h, gfp_mask, NUMA_NO_NODE, nmask); } /* @@ -1765,7 +1689,8 @@ static int gather_surplus_pages(struct hstate *h, int delta) retry: spin_unlock(&hugetlb_lock); for (i = 0; i < needed; i++) { - page = __alloc_buddy_huge_page_no_mpol(h, NUMA_NO_NODE); + page = __alloc_buddy_huge_page(h, htlb_alloc_mask(h), + NUMA_NO_NODE, NULL); if (!page) { alloc_ok = false; break; -- cgit v1.2.3-59-g8ed1b