The patch titled
Subject: mm/hmm: improve and rename hmm_vma_fault() to hmm_range_fault()
has been added to the -mm tree. Its filename is
mm-hmm-improve-and-rename-hmm_vma_fault-to-hmm_range_fault-v3.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/mm-hmm-improve-and-rename-hmm_vma_fault-to-hmm_range_fault-v3.patch
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/mm-hmm-improve-and-rename-hmm_vma_fault-to-hmm_range_fault-v3.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: Jérôme Glisse <jglisse@xxxxxxxxxx>
Subject: mm/hmm: improve and rename hmm_vma_fault() to hmm_range_fault()
Minor optimization around hmm_pte_need_fault(). Rename for consistency
between code, comments and documentation. Also improves the comments on
all the possible returns values. Improve the function by returning the
number of populated entries in pfns array.
Link: http://lkml.kernel.org/r/20190403193318.16478-6-jglisse@xxxxxxxxxx
Signed-off-by: Jérôme Glisse <jglisse@xxxxxxxxxx>
Reviewed-by: Ralph Campbell <rcampbell@xxxxxxxxxx>
Cc: John Hubbard <jhubbard@xxxxxxxxxx>
Cc: Dan Williams <dan.j.williams@xxxxxxxxx>
Cc: Arnd Bergmann <arnd@xxxxxxxx>
Cc: Balbir Singh <bsingharora@xxxxxxxxx>
Cc: Dan Carpenter <dan.carpenter@xxxxxxxxxx>
Cc: Ira Weiny <ira.weiny@xxxxxxxxx>
Cc: Matthew Wilcox <willy@xxxxxxxxxxxxx>
Cc: Souptick Joarder <jrdr.linux@xxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
Documentation/vm/hmm.rst | 8 ---
include/linux/hmm.h | 13 ++++-
mm/hmm.c | 91 +++++++++++++++----------------------
3 files changed, 52 insertions(+), 60 deletions(-)
--- a/Documentation/vm/hmm.rst~mm-hmm-improve-and-rename-hmm_vma_fault-to-hmm_range_fault-v3
+++ a/Documentation/vm/hmm.rst
@@ -190,13 +190,7 @@ When the device driver wants to populate
use either::
long hmm_range_snapshot(struct hmm_range *range);
- int hmm_vma_fault(struct vm_area_struct *vma,
- struct hmm_range *range,
- unsigned long start,
- unsigned long end,
- hmm_pfn_t *pfns,
- bool write,
- bool block);
+ long hmm_range_fault(struct hmm_range *range, bool block);
The first one (hmm_range_snapshot()) will only fetch present CPU page table
entries and will not trigger a page fault on missing or non-present entries.
--- a/include/linux/hmm.h~mm-hmm-improve-and-rename-hmm_vma_fault-to-hmm_range_fault-v3
+++ a/include/linux/hmm.h
@@ -391,7 +391,18 @@ bool hmm_vma_range_done(struct hmm_range
*
* See the function description in mm/hmm.c for further documentation.
*/
-int hmm_vma_fault(struct hmm_range *range, bool block);
+long hmm_range_fault(struct hmm_range *range, bool block);
+
+/* This is a temporary helper to avoid merge conflict between trees. */
+static inline int hmm_vma_fault(struct hmm_range *range, bool block)
+{
+ long ret = hmm_range_fault(range, block);
+ if (ret == -EBUSY)
+ ret = -EAGAIN;
+ else if (ret == -EAGAIN)
+ ret = -EBUSY;
+ return ret < 0 ? ret : 0;
+}
/* Below are for HMM internal use only! Not to be used by device driver! */
void hmm_mm_destroy(struct mm_struct *mm);
--- a/mm/hmm.c~mm-hmm-improve-and-rename-hmm_vma_fault-to-hmm_range_fault-v3
+++ a/mm/hmm.c
@@ -340,13 +340,13 @@ static int hmm_vma_do_fault(struct mm_wa
flags |= write_fault ? FAULT_FLAG_WRITE : 0;
ret = handle_mm_fault(vma, addr, flags);
if (ret & VM_FAULT_RETRY)
- return -EBUSY;
+ return -EAGAIN;
if (ret & VM_FAULT_ERROR) {
*pfn = range->values[HMM_PFN_ERROR];
return -EFAULT;
}
- return -EAGAIN;
+ return -EBUSY;
}
static int hmm_pfns_bad(unsigned long addr,
@@ -372,7 +372,7 @@ static int hmm_pfns_bad(unsigned long ad
* @fault: should we fault or not ?
* @write_fault: write fault ?
* @walk: mm_walk structure
- * Returns: 0 on success, -EAGAIN after page fault, or page fault error
+ * Returns: 0 on success, -EBUSY after page fault, or page fault error
*
* This function will be called whenever pmd_none() or pte_none() returns true,
* or whenever there is no page directory covering the virtual address range.
@@ -395,12 +395,12 @@ static int hmm_vma_walk_hole_(unsigned l
ret = hmm_vma_do_fault(walk, addr, write_fault,
&pfns[i]);
- if (ret != -EAGAIN)
+ if (ret != -EBUSY)
return ret;
}
}
- return (fault || write_fault) ? -EAGAIN : 0;
+ return (fault || write_fault) ? -EBUSY : 0;
}
static inline void hmm_pte_need_fault(const struct hmm_vma_walk *hmm_vma_walk,
@@ -531,11 +531,11 @@ static int hmm_vma_handle_pte(struct mm_
uint64_t orig_pfn = *pfn;
*pfn = range->values[HMM_PFN_NONE];
- cpu_flags = pte_to_hmm_pfn_flags(range, pte);
- hmm_pte_need_fault(hmm_vma_walk, orig_pfn, cpu_flags,
- &fault, &write_fault);
+ fault = write_fault = false;
if (pte_none(pte)) {
+ hmm_pte_need_fault(hmm_vma_walk, orig_pfn, 0,
+ &fault, &write_fault);
if (fault || write_fault)
goto fault;
return 0;
@@ -574,7 +574,7 @@ static int hmm_vma_handle_pte(struct mm_
hmm_vma_walk->last = addr;
migration_entry_wait(vma->vm_mm,
pmdp, addr);
- return -EAGAIN;
+ return -EBUSY;
}
return 0;
}
@@ -582,6 +582,10 @@ static int hmm_vma_handle_pte(struct mm_
/* Report error for everything else */
*pfn = range->values[HMM_PFN_ERROR];
return -EFAULT;
+ } else {
+ cpu_flags = pte_to_hmm_pfn_flags(range, pte);
+ hmm_pte_need_fault(hmm_vma_walk, orig_pfn, cpu_flags,
+ &fault, &write_fault);
}
if (fault || write_fault)
@@ -632,7 +636,7 @@ again:
if (fault || write_fault) {
hmm_vma_walk->last = addr;
pmd_migration_entry_wait(vma->vm_mm, pmdp);
- return -EAGAIN;
+ return -EBUSY;
}
return 0;
} else if (!pmd_present(pmd))
@@ -860,53 +864,34 @@ bool hmm_vma_range_done(struct hmm_range
EXPORT_SYMBOL(hmm_vma_range_done);
/*
- * hmm_vma_fault() - try to fault some address in a virtual address range
+ * hmm_range_fault() - try to fault some address in a virtual address range
* @range: range being faulted
* @block: allow blocking on fault (if true it sleeps and do not drop mmap_sem)
- * Returns: 0 success, error otherwise (-EAGAIN means mmap_sem have been drop)
+ * Returns: number of valid pages in range->pfns[] (from range start
+ * address). This may be zero. If the return value is negative,
+ * then one of the following values may be returned:
+ *
+ * -EINVAL invalid arguments or mm or virtual address are in an
+ * invalid vma (ie either hugetlbfs or device file vma).
+ * -ENOMEM: Out of memory.
+ * -EPERM: Invalid permission (for instance asking for write and
+ * range is read only).
+ * -EAGAIN: If you need to retry and mmap_sem was drop. This can only
+ * happens if block argument is false.
+ * -EBUSY: If the the range is being invalidated and you should wait
+ * for invalidation to finish.
+ * -EFAULT: Invalid (ie either no valid vma or it is illegal to access
+ * that range), number of valid pages in range->pfns[] (from
+ * range start address).
*
* This is similar to a regular CPU page fault except that it will not trigger
- * any memory migration if the memory being faulted is not accessible by CPUs.
+ * any memory migration if the memory being faulted is not accessible by CPUs
+ * and caller does not ask for migration.
*
* On error, for one virtual address in the range, the function will mark the
* corresponding HMM pfn entry with an error flag.
- *
- * Expected use pattern:
- * retry:
- * down_read(&mm->mmap_sem);
- * // Find vma and address device wants to fault, initialize hmm_pfn_t
- * // array accordingly
- * ret = hmm_vma_fault(range, write, block);
- * switch (ret) {
- * case -EAGAIN:
- * hmm_vma_range_done(range);
- * // You might want to rate limit or yield to play nicely, you may
- * // also commit any valid pfn in the array assuming that you are
- * // getting true from hmm_vma_range_monitor_end()
- * goto retry;
- * case 0:
- * break;
- * case -ENOMEM:
- * case -EINVAL:
- * case -EPERM:
- * default:
- * // Handle error !
- * up_read(&mm->mmap_sem)
- * return;
- * }
- * // Take device driver lock that serialize device page table update
- * driver_lock_device_page_table_update();
- * hmm_vma_range_done(range);
- * // Commit pfns we got from hmm_vma_fault()
- * driver_unlock_device_page_table_update();
- * up_read(&mm->mmap_sem)
- *
- * YOU MUST CALL hmm_vma_range_done() AFTER THIS FUNCTION RETURN SUCCESS (0)
- * BEFORE FREEING THE range struct OR YOU WILL HAVE SERIOUS MEMORY CORRUPTION !
- *
- * YOU HAVE BEEN WARNED !
*/
-int hmm_vma_fault(struct hmm_range *range, bool block)
+long hmm_range_fault(struct hmm_range *range, bool block)
{
struct vm_area_struct *vma = range->vma;
unsigned long start = range->start;
@@ -978,7 +963,8 @@ int hmm_vma_fault(struct hmm_range *rang
do {
ret = walk_page_range(start, range->end, &mm_walk);
start = hmm_vma_walk.last;
- } while (ret == -EAGAIN);
+ /* Keep trying while the range is valid. */
+ } while (ret == -EBUSY && range->valid);
if (ret) {
unsigned long i;
@@ -988,6 +974,7 @@ int hmm_vma_fault(struct hmm_range *rang
range->end);
hmm_vma_range_done(range);
hmm_put(hmm);
+ return ret;
} else {
/*
* Transfer hmm reference to the range struct it will be drop
@@ -997,9 +984,9 @@ int hmm_vma_fault(struct hmm_range *rang
range->hmm = hmm;
}
- return ret;
+ return (hmm_vma_walk.last - range->start) >> PAGE_SHIFT;
}
-EXPORT_SYMBOL(hmm_vma_fault);
+EXPORT_SYMBOL(hmm_range_fault);
#endif /* IS_ENABLED(CONFIG_HMM_MIRROR) */
_
Patches currently in -mm which might be from jglisse@xxxxxxxxxx are
mm-hmm-select-mmu-notifier-when-selecting-hmm-v2.patch
mm-hmm-use-reference-counting-for-hmm-struct-v3.patch
mm-hmm-do-not-erase-snapshot-when-a-range-is-invalidated.patch
mm-hmm-improve-and-rename-hmm_vma_get_pfns-to-hmm_range_snapshot-v2.patch
mm-hmm-improve-and-rename-hmm_vma_fault-to-hmm_range_fault-v3.patch
mm-hmm-improve-driver-api-to-work-and-wait-over-a-range-v3.patch
mm-hmm-add-default-fault-flags-to-avoid-the-need-to-pre-fill-pfns-arrays-v2.patch
mm-hmm-mirror-hugetlbfs-snapshoting-faulting-and-dma-mapping-v3.patch
mm-hmm-allow-to-mirror-vma-of-a-file-on-a-dax-backed-filesystem-v3.patch
mm-hmm-add-helpers-to-test-if-mm-is-still-alive-or-not.patch
mm-hmm-add-an-helper-function-that-fault-pages-and-map-them-to-a-device-v3.patch
mm-hmm-convert-various-hmm_pfn_-to-device_entry-which-is-a-better-name.patch
