diff options
Diffstat (limited to 'mm/mempolicy.c')
| -rw-r--r-- | mm/mempolicy.c | 138 |
1 files changed, 98 insertions, 40 deletions
diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 65e0874fce17..977c641f78cf 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -68,7 +68,7 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/mempolicy.h> -#include <linux/mm.h> +#include <linux/pagewalk.h> #include <linux/highmem.h> #include <linux/hugetlb.h> #include <linux/kernel.h> @@ -410,7 +410,9 @@ struct queue_pages { struct list_head *pagelist; unsigned long flags; nodemask_t *nmask; - struct vm_area_struct *prev; + unsigned long start; + unsigned long end; + struct vm_area_struct *first; }; /* @@ -618,6 +620,22 @@ static int queue_pages_test_walk(unsigned long start, unsigned long end, unsigned long endvma = vma->vm_end; unsigned long flags = qp->flags; + /* range check first */ + VM_BUG_ON((vma->vm_start > start) || (vma->vm_end < end)); + + if (!qp->first) { + qp->first = vma; + if (!(flags & MPOL_MF_DISCONTIG_OK) && + (qp->start < vma->vm_start)) + /* hole at head side of range */ + return -EFAULT; + } + if (!(flags & MPOL_MF_DISCONTIG_OK) && + ((vma->vm_end < qp->end) && + (!vma->vm_next || vma->vm_end < vma->vm_next->vm_start))) + /* hole at middle or tail of range */ + return -EFAULT; + /* * Need check MPOL_MF_STRICT to return -EIO if possible * regardless of vma_migratable @@ -628,17 +646,6 @@ static int queue_pages_test_walk(unsigned long start, unsigned long end, if (endvma > end) endvma = end; - if (vma->vm_start > start) - start = vma->vm_start; - - if (!(flags & MPOL_MF_DISCONTIG_OK)) { - if (!vma->vm_next && vma->vm_end < end) - return -EFAULT; - if (qp->prev && qp->prev->vm_end < vma->vm_start) - return -EFAULT; - } - - qp->prev = vma; if (flags & MPOL_MF_LAZY) { /* Similar to task_numa_work, skip inaccessible VMAs */ @@ -655,6 +662,12 @@ static int queue_pages_test_walk(unsigned long start, unsigned long end, return 1; } +static const struct mm_walk_ops queue_pages_walk_ops = { + .hugetlb_entry = queue_pages_hugetlb, + .pmd_entry = queue_pages_pte_range, + .test_walk = queue_pages_test_walk, +}; + /* * Walk through page tables and collect pages to be migrated. * @@ -666,28 +679,32 @@ static int queue_pages_test_walk(unsigned long start, unsigned long end, * 1 - there is unmovable page, but MPOL_MF_MOVE* & MPOL_MF_STRICT were * specified. * 0 - queue pages successfully or no misplaced page. - * -EIO - there is misplaced page and only MPOL_MF_STRICT was specified. + * errno - i.e. misplaced pages with MPOL_MF_STRICT specified (-EIO) or + * memory range specified by nodemask and maxnode points outside + * your accessible address space (-EFAULT) */ static int queue_pages_range(struct mm_struct *mm, unsigned long start, unsigned long end, nodemask_t *nodes, unsigned long flags, struct list_head *pagelist) { + int err; struct queue_pages qp = { .pagelist = pagelist, .flags = flags, .nmask = nodes, - .prev = NULL, - }; - struct mm_walk queue_pages_walk = { - .hugetlb_entry = queue_pages_hugetlb, - .pmd_entry = queue_pages_pte_range, - .test_walk = queue_pages_test_walk, - .mm = mm, - .private = &qp, + .start = start, + .end = end, + .first = NULL, }; - return walk_page_range(start, end, &queue_pages_walk); + err = walk_page_range(mm, start, end, &queue_pages_walk_ops, &qp); + + if (!qp.first) + /* whole range in hole */ + err = -EFAULT; + + return err; } /* @@ -739,8 +756,7 @@ static int mbind_range(struct mm_struct *mm, unsigned long start, unsigned long vmend; vma = find_vma(mm, start); - if (!vma || vma->vm_start > start) - return -EFAULT; + VM_BUG_ON(!vma); prev = vma->vm_prev; if (start > vma->vm_start) @@ -1180,8 +1196,8 @@ static struct page *new_page(struct page *page, unsigned long start) } else if (PageTransHuge(page)) { struct page *thp; - thp = alloc_pages_vma(GFP_TRANSHUGE, HPAGE_PMD_ORDER, vma, - address, numa_node_id()); + thp = alloc_hugepage_vma(GFP_TRANSHUGE, vma, address, + HPAGE_PMD_ORDER); if (!thp) return NULL; prep_transhuge_page(thp); @@ -1287,7 +1303,7 @@ static long do_mbind(unsigned long start, unsigned long len, flags | MPOL_MF_INVERT, &pagelist); if (ret < 0) { - err = -EIO; + err = ret; goto up_out; } @@ -1306,10 +1322,12 @@ static long do_mbind(unsigned long start, unsigned long len, if ((ret > 0) || (nr_failed && (flags & MPOL_MF_STRICT))) err = -EIO; - } else - putback_movable_pages(&pagelist); - + } else { up_out: + if (!list_empty(&pagelist)) + putback_movable_pages(&pagelist); + } + up_write(&mm->mmap_sem); mpol_out: mpol_put(new); @@ -1406,6 +1424,7 @@ static long kernel_mbind(unsigned long start, unsigned long len, int err; unsigned short mode_flags; + start = untagged_addr(start); mode_flags = mode & MPOL_MODE_FLAGS; mode &= ~MPOL_MODE_FLAGS; if (mode >= MPOL_MAX) @@ -1513,10 +1532,6 @@ static int kernel_migrate_pages(pid_t pid, unsigned long maxnode, if (nodes_empty(*new)) goto out_put; - nodes_and(*new, *new, node_states[N_MEMORY]); - if (nodes_empty(*new)) - goto out_put; - err = security_task_movememory(task); if (err) goto out_put; @@ -1563,6 +1578,8 @@ static int kernel_get_mempolicy(int __user *policy, int uninitialized_var(pval); nodemask_t nodes; + addr = untagged_addr(addr); + if (nmask != NULL && maxnode < nr_node_ids) return -EINVAL; @@ -1734,7 +1751,7 @@ 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. */ -struct mempolicy *get_vma_policy(struct vm_area_struct *vma, +static struct mempolicy *get_vma_policy(struct vm_area_struct *vma, unsigned long addr) { struct mempolicy *pol = __get_vma_policy(vma, addr); @@ -2083,6 +2100,7 @@ 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. @@ -2093,7 +2111,7 @@ 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) + unsigned long addr, int node, bool hugepage) { struct mempolicy *pol; struct page *page; @@ -2111,6 +2129,46 @@ 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); + /* + * First, try to allocate THP only on local node, but + * don't reclaim unnecessarily, just compact. + */ + page = __alloc_pages_node(hpage_node, + gfp | __GFP_THISNODE | __GFP_NORETRY, order); + + /* + * If hugepage allocations are configured to always + * synchronous compact or the vma has been madvised + * to prefer hugepage backing, retry allowing remote + * memory with both reclaim and compact as well. + */ + if (!page && (gfp & __GFP_DIRECT_RECLAIM)) + 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); @@ -2763,6 +2821,9 @@ int mpol_parse_str(char *str, struct mempolicy **mpol) char *flags = strchr(str, '='); int err = 1, mode; + if (flags) + *flags++ = '\0'; /* terminate mode string */ + if (nodelist) { /* NUL-terminate mode or flags string */ *nodelist++ = '\0'; @@ -2773,9 +2834,6 @@ int mpol_parse_str(char *str, struct mempolicy **mpol) } else nodes_clear(nodes); - if (flags) - *flags++ = '\0'; /* terminate mode string */ - mode = match_string(policy_modes, MPOL_MAX, str); if (mode < 0) goto out; |
