[RFC PATCH 3/3] powerpc/mm/iommu: Allow migration of cma allocated pages during mm_iommu_get
Aneesh Kumar K.V
aneesh.kumar at linux.ibm.com
Tue Sep 4 02:37:33 AEST 2018
Current code doesn't do page migration if the page allocated is a compound page.
With HugeTLB migration support, we can end up allocating hugetlb pages from
CMA region. Also THP pages can be allocated from CMA region. This patch updates
the code to handle compound pages correctly.
This add a new helper get_user_pages_cma_migrate. It does one get_user_pages
with right count, instead of doing one get_user_pages per page. That avoids
reading page table multiple times. The helper could possibly used by other
subystem if we have more users.
The patch also convert the hpas member of mm_iommu_table_group_mem_t to a union.
We use the same storage location to store pointers to struct page. We cannot
update alll the code path use struct page *, because we access hpas in real mode
and we can't do that struct page * to pfn conversion in real mode.
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar at linux.ibm.com>
---
arch/powerpc/mm/mmu_context_iommu.c | 195 ++++++++++++++++++----------
1 file changed, 123 insertions(+), 72 deletions(-)
diff --git a/arch/powerpc/mm/mmu_context_iommu.c b/arch/powerpc/mm/mmu_context_iommu.c
index f472965f7638..597b88a0abce 100644
--- a/arch/powerpc/mm/mmu_context_iommu.c
+++ b/arch/powerpc/mm/mmu_context_iommu.c
@@ -20,6 +20,7 @@
#include <linux/swap.h>
#include <asm/mmu_context.h>
#include <asm/pte-walk.h>
+#include <linux/mm_inline.h>
static DEFINE_MUTEX(mem_list_mutex);
@@ -30,8 +31,18 @@ struct mm_iommu_table_group_mem_t {
atomic64_t mapped;
unsigned int pageshift;
u64 ua; /* userspace address */
- u64 entries; /* number of entries in hpas[] */
- u64 *hpas; /* vmalloc'ed */
+ u64 entries; /* number of entries in hpages[] */
+ /*
+ * in mm_iommu_get we temporarily use this to store
+ * struct page address.
+ *
+ * We need to convert ua to hpa in real mode. Make it
+ * simpler by storing physicall address.
+ */
+ union {
+ struct page **hpages; /* vmalloc'ed */
+ phys_addr_t *hpas;
+ };
};
static long mm_iommu_adjust_locked_vm(struct mm_struct *mm,
@@ -75,62 +86,112 @@ bool mm_iommu_preregistered(struct mm_struct *mm)
EXPORT_SYMBOL_GPL(mm_iommu_preregistered);
/*
- * Taken from alloc_migrate_target with changes to remove CMA allocations
+ * Taken from alloc_migrate_target/alloc_migrate_huge_page with changes to remove
+ * CMA allocations
+ * Is this the right allocator for hugetlb?
*/
struct page *new_iommu_non_cma_page(struct page *page, unsigned long private)
{
- gfp_t gfp_mask = GFP_USER;
- struct page *new_page;
+ /* is this the right nid? */
+ int nid = numa_mem_id();
+ gfp_t gfp_mask = GFP_HIGHUSER;
- if (PageCompound(page))
- return NULL;
+ if (PageHuge(page)) {
- if (PageHighMem(page))
- gfp_mask |= __GFP_HIGHMEM;
+ struct hstate *h = page_hstate(page);
+ /*
+ * We don't want to dequeue from the pool because pool pages will
+ * mostly be from the CMA region.
+ */
+ return alloc_migrate_huge_page(h, gfp_mask, nid, NULL);
- /*
- * We don't want the allocation to force an OOM if possibe
- */
- new_page = alloc_page(gfp_mask | __GFP_NORETRY | __GFP_NOWARN);
- return new_page;
+ } else if (PageTransHuge(page)) {
+ struct page *thp;
+ gfp_t thp_gfpmask = GFP_TRANSHUGE & ~__GFP_MOVABLE;
+
+ thp = __alloc_pages_node(nid, thp_gfpmask, HPAGE_PMD_ORDER);
+ if (!thp)
+ return NULL;
+ prep_transhuge_page(thp);
+ return thp;
+ }
+ return __alloc_pages_node(nid, gfp_mask, 0);
}
-static int mm_iommu_move_page_from_cma(struct page *page)
+int get_user_pages_cma_migrate(unsigned long start, int nr_pages, int write,
+ struct page **pages)
{
- int ret = 0;
- LIST_HEAD(cma_migrate_pages);
-
- /* Ignore huge pages for now */
- if (PageCompound(page))
- return -EBUSY;
-
- lru_add_drain();
- ret = isolate_lru_page(page);
- if (ret)
+ int i, ret;
+ bool drain_allow = true;
+ bool migrate_allow = true;
+ LIST_HEAD(cma_page_list);
+
+get_user_again:
+ ret = get_user_pages_fast(start, nr_pages, write, pages);
+ if (ret <= 0)
return ret;
- list_add(&page->lru, &cma_migrate_pages);
- put_page(page); /* Drop the gup reference */
-
- ret = migrate_pages(&cma_migrate_pages, new_iommu_non_cma_page,
- NULL, 0, MIGRATE_SYNC, MR_CONTIG_RANGE);
- if (ret) {
- if (!list_empty(&cma_migrate_pages))
- putback_movable_pages(&cma_migrate_pages);
+ for (i = 0; i < ret; ++i) {
+ /*
+ * If we get a page from the CMA zone, since we are going to
+ * be pinning these entries, we might as well move them out
+ * of the CMA zone if possible.
+ */
+ if (is_migrate_cma_page(pages[i]) && migrate_allow) {
+ if (PageHuge(pages[i]))
+ isolate_huge_page(pages[i], &cma_page_list);
+ else {
+ struct page *head = compound_head(pages[i]);
+
+ if (!PageLRU(head) && drain_allow) {
+ lru_add_drain_all();
+ drain_allow = false;
+ }
+
+ if (!isolate_lru_page(head)) {
+ list_add_tail(&head->lru, &cma_page_list);
+ mod_node_page_state(page_pgdat(head),
+ NR_ISOLATED_ANON +
+ page_is_file_cache(head),
+ hpage_nr_pages(head));
+ }
+ }
+ }
}
-
- return 0;
+ if (!list_empty(&cma_page_list)) {
+ /*
+ * drop the above get_user_pages reference.
+ */
+ for (i = 0; i < ret; ++i)
+ put_page(pages[i]);
+
+ if (migrate_pages(&cma_page_list, new_iommu_non_cma_page,
+ NULL, 0, MIGRATE_SYNC, MR_CONTIG_RANGE)) {
+ /*
+ * some of the pages failed migration. Do get_user_pages
+ * without migration.
+ */
+ migrate_allow = false;
+
+ if (!list_empty(&cma_page_list))
+ putback_movable_pages(&cma_page_list);
+ }
+ /*
+ * We did migrate all the pages, Try to get the page references again
+ * migrating any new CMA pages which we failed to isolate earlier.
+ */
+ drain_allow = true;
+ goto get_user_again;
+ }
+ return ret;
}
long mm_iommu_get(struct mm_struct *mm, unsigned long ua, unsigned long entries,
struct mm_iommu_table_group_mem_t **pmem)
{
struct mm_iommu_table_group_mem_t *mem;
- long i, j, ret = 0, locked_entries = 0;
+ long i, ret = 0, locked_entries = 0;
unsigned int pageshift;
- unsigned long flags;
- unsigned long cur_ua;
- struct page *page = NULL;
mutex_lock(&mem_list_mutex);
@@ -177,47 +238,37 @@ long mm_iommu_get(struct mm_struct *mm, unsigned long ua, unsigned long entries,
goto unlock_exit;
}
+ ret = get_user_pages_cma_migrate(ua, entries, 1, mem->hpages);
+ if (ret != entries) {
+ /* free the reference taken */
+ for (i = 0; i < ret; i++)
+ put_page(mem->hpages[i]);
+
+ vfree(mem->hpas);
+ kfree(mem);
+ ret = -EFAULT;
+ goto unlock_exit;
+ } else
+ ret = 0;
+
+ pageshift = PAGE_SHIFT;
for (i = 0; i < entries; ++i) {
- cur_ua = ua + (i << PAGE_SHIFT);
- if (1 != get_user_pages_fast(cur_ua,
- 1/* pages */, 1/* iswrite */, &page)) {
- ret = -EFAULT;
- for (j = 0; j < i; ++j)
- put_page(pfn_to_page(mem->hpas[j] >>
- PAGE_SHIFT));
- vfree(mem->hpas);
- kfree(mem);
- goto unlock_exit;
- }
+ struct page *page = mem->hpages[i];
/*
- * If we get a page from the CMA zone, since we are going to
- * be pinning these entries, we might as well move them out
- * of the CMA zone if possible. NOTE: faulting in + migration
- * can be expensive. Batching can be considered later
+ * Allow to use larger than 64k IOMMU pages. Only do that
+ * if we are backed by hugetlb.
*/
- if (is_migrate_cma_page(page)) {
- if (mm_iommu_move_page_from_cma(page))
- goto populate;
- if (1 != get_user_pages_fast(cur_ua,
- 1/* pages */, 1/* iswrite */,
- &page)) {
- ret = -EFAULT;
- for (j = 0; j < i; ++j)
- put_page(pfn_to_page(mem->hpas[j] >>
- PAGE_SHIFT));
- vfree(mem->hpas);
- kfree(mem);
- goto unlock_exit;
- }
- }
-populate:
- pageshift = PAGE_SHIFT;
- if (mem->pageshift > PAGE_SHIFT && PageHuge(page)) {
+ if ((mem->pageshift > PAGE_SHIFT) && PageHuge(page)) {
struct page *head = compound_head(page);
pageshift = compound_order(head) + PAGE_SHIFT;
}
mem->pageshift = min(mem->pageshift, pageshift);
+ /*
+ * We don't need struct page reference any more, switch
+ * physicall address.
+ */
mem->hpas[i] = page_to_pfn(page) << PAGE_SHIFT;
+
}
atomic64_set(&mem->mapped, 1);
--
2.17.1
More information about the Linuxppc-dev
mailing list