The patch titled
Subject: powerpc/mm/iommu: allow migration of cma allocated pages during mm_iommu_do_alloc
has been added to the -mm tree. Its filename is
powerpc-mm-iommu-allow-migration-of-cma-allocated-pages-during-mm_iommu_do_alloc.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/powerpc-mm-iommu-allow-migration-of-cma-allocated-pages-during-mm_iommu_do_alloc.patch
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/powerpc-mm-iommu-allow-migration-of-cma-allocated-pages-during-mm_iommu_do_alloc.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next and is updated
there every 3-4 working days
------------------------------------------------------
From: "Aneesh Kumar K.V" <aneesh.kumar@xxxxxxxxxxxxx>
Subject: powerpc/mm/iommu: allow migration of cma allocated pages during mm_iommu_do_alloc
The 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.
The patch also switches to a single get_user_pages with the right count,
instead of doing one get_user_pages per page. That avoids reading page
table multiple times.
Since these page reference updates are long term pin, switch to
get_user_pages_longterm. That makes sure we fail correctly if the guest
RAM is backed by DAX pages.
The patch also converts 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 all 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.
Link: http://lkml.kernel.org/r/20190114095438.32470-5-aneesh.kumar@xxxxxxxxxxxxx
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@xxxxxxxxxxxxx>
Cc: Alexey Kardashevskiy <aik@xxxxxxxxx>
Cc: Andrea Arcangeli <aarcange@xxxxxxxxxx>
Cc: David Gibson <david@xxxxxxxxxxxxxxxxxxxxx>
Cc: Michael Ellerman <mpe@xxxxxxxxxxxxxx>
Cc: Michal Hocko <mhocko@xxxxxxxxxx>
Cc: Mel Gorman <mgorman@xxxxxxxxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
arch/powerpc/mm/mmu_context_iommu.c | 126 ++++++++------------------
1 file changed, 39 insertions(+), 87 deletions(-)
--- a/arch/powerpc/mm/mmu_context_iommu.c~powerpc-mm-iommu-allow-migration-of-cma-allocated-pages-during-mm_iommu_do_alloc
+++ a/arch/powerpc/mm/mmu_context_iommu.c
@@ -21,6 +21,7 @@
#include <linux/sizes.h>
#include <asm/mmu_context.h>
#include <asm/pte-walk.h>
+#include <linux/mm_inline.h>
static DEFINE_MUTEX(mem_list_mutex);
@@ -34,8 +35,18 @@ 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 hpas/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 physical address.
+ */
+ union {
+ struct page **hpages; /* vmalloc'ed */
+ phys_addr_t *hpas;
+ };
#define MM_IOMMU_TABLE_INVALID_HPA ((uint64_t)-1)
u64 dev_hpa; /* Device memory base address */
};
@@ -80,64 +91,15 @@ bool mm_iommu_preregistered(struct mm_st
}
EXPORT_SYMBOL_GPL(mm_iommu_preregistered);
-/*
- * Taken from alloc_migrate_target with changes to remove CMA allocations
- */
-struct page *new_iommu_non_cma_page(struct page *page, unsigned long private)
-{
- gfp_t gfp_mask = GFP_USER;
- struct page *new_page;
-
- if (PageCompound(page))
- return NULL;
-
- if (PageHighMem(page))
- gfp_mask |= __GFP_HIGHMEM;
-
- /*
- * 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;
-}
-
-static int mm_iommu_move_page_from_cma(struct page *page)
-{
- 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)
- 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);
- }
-
- return 0;
-}
-
static long mm_iommu_do_alloc(struct mm_struct *mm, unsigned long ua,
- unsigned long entries, unsigned long dev_hpa,
- struct mm_iommu_table_group_mem_t **pmem)
+ unsigned long entries, unsigned long dev_hpa,
+ 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);
@@ -187,41 +149,27 @@ static long mm_iommu_do_alloc(struct mm_
goto unlock_exit;
}
+ down_read(&mm->mmap_sem);
+ ret = get_user_pages_longterm(ua, entries, FOLL_WRITE, mem->hpages, NULL);
+ up_read(&mm->mmap_sem);
+ 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) {
+ struct page *page = mem->hpages[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;
- }
- /*
- * 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
- */
- 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 && PageCompound(page)) {
pte_t *pte;
struct page *head = compound_head(page);
@@ -239,6 +187,10 @@ populate:
local_irq_restore(flags);
}
mem->pageshift = min(mem->pageshift, pageshift);
+ /*
+ * We don't need struct page reference any more, switch
+ * to physical address.
+ */
mem->hpas[i] = page_to_pfn(page) << PAGE_SHIFT;
}
_
Patches currently in -mm which might be from aneesh.kumar@xxxxxxxxxxxxx are
mm-update-ptep_modify_prot_start-commit-to-take-vm_area_struct-as-arg.patch
mm-update-ptep_modify_prot_commit-to-take-old-pte-value-as-arg.patch
arch-powerpc-mm-nest-mmu-workaround-for-mprotect-rw-upgrade.patch
mm-hugetlb-add-prot_modify_start-commit-sequence-for-hugetlb-update.patch
arch-powerpc-mm-hugetlb-nestmmu-workaround-for-hugetlb-mprotect-rw-upgrade.patch
mm-cma-add-pf-flag-to-force-non-cma-alloc.patch
mm-update-get_user_pages_longterm-to-migrate-pages-allocated-from-cma-region.patch
powerpc-mm-iommu-allow-migration-of-cma-allocated-pages-during-mm_iommu_do_alloc.patch
powerpc-mm-iommu-allow-large-iommu-page-size-only-for-hugetlb-backing.patch
