* + mm-hmm-mirror-device-page-fault-handler.patch added to -mm tree
@ 2017-03-16 20:52 akpm
0 siblings, 0 replies; 2+ messages in thread
From: akpm @ 2017-03-16 20:52 UTC (permalink / raw)
To: jglisse, SCheung, ebaskakov, jhubbard, mhairgrove, sgutti, mm-commits
The patch titled
Subject: mm/hmm/mirror: device page fault handler
has been added to the -mm tree. Its filename is
mm-hmm-mirror-device-page-fault-handler.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/mm-hmm-mirror-device-page-fault-handler.patch
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/mm-hmm-mirror-device-page-fault-handler.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/SubmitChecklist 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@redhat.com>
Subject: mm/hmm/mirror: device page fault handler
This handle page fault on behalf of device driver, unlike
handle_mm_fault() it does not trigger migration back to system memory for
device memory.
Link: http://lkml.kernel.org/r/1489680335-6594-13-git-send-email-jglisse@redhat.com
Signed-off-by: Jérôme Glisse <jglisse@redhat.com>
Signed-off-by: Evgeny Baskakov <ebaskakov@nvidia.com>
Signed-off-by: John Hubbard <jhubbard@nvidia.com>
Signed-off-by: Mark Hairgrove <mhairgrove@nvidia.com>
Signed-off-by: Sherry Cheung <SCheung@nvidia.com>
Signed-off-by: Subhash Gutti <sgutti@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
include/linux/hmm.h | 27 ++++
mm/hmm.c | 269 +++++++++++++++++++++++++++++++++++++-----
2 files changed, 268 insertions(+), 28 deletions(-)
diff -puN include/linux/hmm.h~mm-hmm-mirror-device-page-fault-handler include/linux/hmm.h
--- a/include/linux/hmm.h~mm-hmm-mirror-device-page-fault-handler
+++ a/include/linux/hmm.h
@@ -291,6 +291,33 @@ int hmm_vma_get_pfns(struct vm_area_stru
unsigned long end,
hmm_pfn_t *pfns);
bool hmm_vma_range_done(struct vm_area_struct *vma, struct hmm_range *range);
+
+
+/*
+ * Fault memory on behalf of device driver. Unlike handle_mm_fault(), this will
+ * not migrate any device memory back to system memory. The hmm_pfn_t array will
+ * be updated with the fault result and current snapshot of the CPU page table
+ * for the range.
+ *
+ * The mmap_sem must be taken in read mode before entering and it might be
+ * dropped by the function if block argument is false. In that case, the
+ * function returns -EAGAIN.
+ *
+ * Return value does not reflect if the fault was successful for every single
+ * address or not. Therefore, the caller must to inspect the hmm_pfn_t array to
+ * determine fault status for each address.
+ *
+ * Trying to fault inside an invalid vma will result in -EINVAL.
+ *
+ * See function description in mm/hmm.c for further documentation.
+ */
+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);
#endif /* IS_ENABLED(CONFIG_HMM_MIRROR) */
diff -puN mm/hmm.c~mm-hmm-mirror-device-page-fault-handler mm/hmm.c
--- a/mm/hmm.c~mm-hmm-mirror-device-page-fault-handler
+++ a/mm/hmm.c
@@ -288,6 +288,15 @@ void hmm_mirror_unregister(struct hmm_mi
}
EXPORT_SYMBOL(hmm_mirror_unregister);
+
+static void hmm_pfns_error(hmm_pfn_t *pfns,
+ unsigned long addr,
+ unsigned long end)
+{
+ for (; addr < end; addr += PAGE_SIZE, pfns++)
+ *pfns = HMM_PFN_ERROR;
+}
+
static void hmm_pfns_empty(hmm_pfn_t *pfns,
unsigned long addr,
unsigned long end)
@@ -304,10 +313,43 @@ static void hmm_pfns_special(hmm_pfn_t *
*pfns = HMM_PFN_SPECIAL;
}
-static void hmm_vma_walk(struct vm_area_struct *vma,
- unsigned long start,
- unsigned long end,
- hmm_pfn_t *pfns)
+static void hmm_pfns_clear(hmm_pfn_t *pfns,
+ unsigned long addr,
+ unsigned long end)
+{
+ unsigned long npfns = (end - addr) >> PAGE_SHIFT;
+
+ memset(pfns, 0, sizeof(*pfns) * npfns);
+}
+
+static int hmm_vma_do_fault(struct vm_area_struct *vma,
+ const hmm_pfn_t fault,
+ unsigned long addr,
+ hmm_pfn_t *pfn,
+ bool block)
+{
+ unsigned flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_REMOTE;
+ int r;
+
+ flags |= block ? 0 : FAULT_FLAG_ALLOW_RETRY;
+ flags |= (fault & HMM_PFN_WRITE) ? FAULT_FLAG_WRITE : 0;
+ r = handle_mm_fault(vma, addr, flags);
+ if (r & VM_FAULT_RETRY)
+ return -EAGAIN;
+ if (r & VM_FAULT_ERROR) {
+ *pfn = HMM_PFN_ERROR;
+ return -EFAULT;
+ }
+
+ return 0;
+}
+
+static int hmm_vma_walk(struct vm_area_struct *vma,
+ const hmm_pfn_t fault,
+ unsigned long start,
+ unsigned long end,
+ hmm_pfn_t *pfns,
+ bool block)
{
unsigned long addr, next;
hmm_pfn_t flag;
@@ -321,6 +363,7 @@ static void hmm_vma_walk(struct vm_area_
pmd_t *pmdp;
pte_t *ptep;
pmd_t pmd;
+ int ret;
/*
* We are accessing/faulting for a device from an unknown
@@ -331,15 +374,37 @@ static void hmm_vma_walk(struct vm_area_
next = pgd_addr_end(addr, end);
pgdp = pgd_offset(vma->vm_mm, addr);
if (pgd_none(*pgdp) || pgd_bad(*pgdp)) {
- hmm_pfns_empty(&pfns[i], addr, next);
- continue;
+ if (!(vma->vm_flags & VM_READ)) {
+ hmm_pfns_empty(&pfns[i], addr, next);
+ continue;
+ }
+ if (!fault) {
+ hmm_pfns_empty(&pfns[i], addr, next);
+ continue;
+ }
+ pudp = pud_alloc(vma->vm_mm, pgdp, addr);
+ if (!pudp) {
+ hmm_pfns_error(&pfns[i], addr, next);
+ continue;
+ }
}
next = pud_addr_end(addr, end);
pudp = pud_offset(pgdp, addr);
if (pud_none(*pudp) || pud_bad(*pudp)) {
- hmm_pfns_empty(&pfns[i], addr, next);
- continue;
+ if (!(vma->vm_flags & VM_READ)) {
+ hmm_pfns_empty(&pfns[i], addr, next);
+ continue;
+ }
+ if (!fault) {
+ hmm_pfns_empty(&pfns[i], addr, next);
+ continue;
+ }
+ pmdp = pmd_alloc(vma->vm_mm, pudp, addr);
+ if (!pmdp) {
+ hmm_pfns_error(&pfns[i], addr, next);
+ continue;
+ }
}
next = pmd_addr_end(addr, end);
@@ -347,8 +412,24 @@ static void hmm_vma_walk(struct vm_area_
pmd = pmd_read_atomic(pmdp);
barrier();
if (pmd_none(pmd) || pmd_bad(pmd)) {
- hmm_pfns_empty(&pfns[i], addr, next);
- continue;
+ if (!(vma->vm_flags & VM_READ)) {
+ hmm_pfns_empty(&pfns[i], addr, next);
+ continue;
+ }
+ if (!fault) {
+ hmm_pfns_empty(&pfns[i], addr, next);
+ continue;
+ }
+ /*
+ * Use pte_alloc() instead of pte_alloc_map, because we
+ * can't run pte_offset_map on the pmd, if a huge pmd
+ * could materialize from under us.
+ */
+ if (unlikely(pte_alloc(vma->vm_mm, pmdp, addr))) {
+ hmm_pfns_error(&pfns[i], addr, next);
+ continue;
+ }
+ pmd = *pmdp;
}
if (pmd_trans_huge(pmd) || pmd_devmap(pmd)) {
unsigned long pfn = pmd_pfn(pmd) + pte_index(addr);
@@ -356,10 +437,14 @@ static void hmm_vma_walk(struct vm_area_
if (pmd_protnone(pmd)) {
hmm_pfns_clear(&pfns[i], addr, next);
+ if (fault)
+ goto fault;
continue;
}
flags |= pmd_write(*pmdp) ? HMM_PFN_WRITE : 0;
flags |= pmd_devmap(pmd) ? HMM_PFN_DEVICE : 0;
+ if ((flags & fault) != fault)
+ goto fault;
for (; addr < next; addr += PAGE_SIZE, i++, pfn++)
pfns[i] = hmm_pfn_from_pfn(pfn) | flags;
continue;
@@ -370,41 +455,63 @@ static void hmm_vma_walk(struct vm_area_
swp_entry_t entry;
pte_t pte = *ptep;
- pfns[i] = 0;
-
if (pte_none(pte)) {
+ if (fault) {
+ pte_unmap(ptep);
+ goto fault;
+ }
pfns[i] = HMM_PFN_EMPTY;
continue;
}
entry = pte_to_swp_entry(pte);
if (!pte_present(pte) && !non_swap_entry(entry)) {
+ if (fault) {
+ pte_unmap(ptep);
+ goto fault;
+ }
+ pfns[i] = 0;
continue;
}
if (pte_present(pte)) {
pfns[i] = hmm_pfn_from_pfn(pte_pfn(pte))|flag;
pfns[i] |= pte_write(pte) ? HMM_PFN_WRITE : 0;
- continue;
- }
-
- /*
- * This is a special swap entry, ignore migration, use
- * device and report anything else as error.
- */
- if (is_device_entry(entry)) {
+ } else if (is_device_entry(entry)) {
+ /* Do not fault device entry */
pfns[i] = hmm_pfn_from_pfn(swp_offset(entry));
if (is_write_device_entry(entry))
pfns[i] |= HMM_PFN_WRITE;
pfns[i] |= HMM_PFN_DEVICE;
pfns[i] |= HMM_PFN_UNADDRESSABLE;
pfns[i] |= flag;
- } else if (!is_migration_entry(entry)) {
+ } else if (is_migration_entry(entry) && fault) {
+ migration_entry_wait(vma->vm_mm, pmdp, addr);
+ /* Start again for current address */
+ next = addr;
+ ptep++;
+ break;
+ } else {
+ /* Report error for everything else */
pfns[i] = HMM_PFN_ERROR;
}
+ if ((fault & pfns[i]) != fault) {
+ pte_unmap(ptep);
+ goto fault;
+ }
}
pte_unmap(ptep - 1);
+ continue;
+
+fault:
+ ret = hmm_vma_do_fault(vma, fault, addr, &pfns[i], block);
+ if (ret)
+ return ret;
+ /* Start again for current address */
+ next = addr;
}
+
+ return 0;
}
/*
@@ -463,7 +570,7 @@ int hmm_vma_get_pfns(struct vm_area_stru
list_add_rcu(&range->list, &hmm->ranges);
spin_unlock(&hmm->lock);
- hmm_vma_walk(vma, start, end, pfns);
+ hmm_vma_walk(vma, 0, start, end, pfns, false);
return 0;
}
EXPORT_SYMBOL(hmm_vma_get_pfns);
@@ -474,14 +581,22 @@ EXPORT_SYMBOL(hmm_vma_get_pfns);
* @range: range being track
* Returns: false if range data have been invalidated, true otherwise
*
- * Range struct is use to track update to CPU page table after call to
- * hmm_vma_get_pfns(). Once device driver is done using or want to lock update
- * to data it gots from this function it calls hmm_vma_range_done() which stop
- * the tracking.
+ * Range struct is use to track update to CPU page table after call to either
+ * hmm_vma_get_pfns() or hmm_vma_fault(). Once device driver is done using or
+ * want to lock update to data it gots from those functions it must call the
+ * hmm_vma_range_done() function which stop tracking CPU page table update.
+ *
+ * Note that device driver must still implement general CPU page table update
+ * tracking either by using hmm_mirror (see hmm_mirror_register()) or by using
+ * mmu_notifier API directly.
+ *
+ * CPU page table update tracking done through hmm_range is only temporary and
+ * to be use while trying to duplicate CPU page table content for a range of
+ * virtual address.
*
* There is 2 way to use this :
* again:
- * hmm_vma_get_pfns(vma, range, start, end, pfns);
+ * hmm_vma_get_pfns(vma, range, start, end, pfns); or hmm_vma_fault(...);
* trans = device_build_page_table_update_transaction(pfns);
* device_page_table_lock();
* if (!hmm_vma_range_done(vma, range)) {
@@ -492,7 +607,7 @@ EXPORT_SYMBOL(hmm_vma_get_pfns);
* device_page_table_unlock();
*
* Or:
- * hmm_vma_get_pfns(vma, range, start, end, pfns);
+ * hmm_vma_get_pfns(vma, range, start, end, pfns); or hmm_vma_fault(...);
* device_page_table_lock();
* hmm_vma_range_done(vma, range);
* device_update_page_table(pfns);
@@ -521,4 +636,102 @@ bool hmm_vma_range_done(struct vm_area_s
return range->valid;
}
EXPORT_SYMBOL(hmm_vma_range_done);
+
+/*
+ * hmm_vma_fault() - try to fault some address in a virtual address range
+ * @vma: virtual memory area containing the virtual address range
+ * @range: use to track pfns array content validity
+ * @start: fault range virtual start address (inclusive)
+ * @end: fault range virtual end address (exclusive)
+ * @pfns: array of hmm_pfn_t, only entry with fault flag set will be faulted
+ * @write: is it a write fault
+ * @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)
+ *
+ * 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.
+ *
+ * On error, for one virtual address in the range, the function will set the
+ * hmm_pfn_t error flag for the corresponding pfn entry.
+ *
+ * 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(vma, start, end, pfns, allow_retry);
+ * switch (ret) {
+ * case -EAGAIN:
+ * hmm_vma_range_done(vma, 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;
+ * 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(vma, 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 WARN !
+ */
+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)
+{
+ hmm_pfn_t fault = HMM_PFN_READ | (write ? HMM_PFN_WRITE : 0);
+ struct hmm *hmm;
+ int ret;
+
+ /* Sanity check, this really should not happen ! */
+ if (start < vma->vm_start || start >= vma->vm_end)
+ return -EINVAL;
+ if (end < vma->vm_start || end > vma->vm_end)
+ return -EINVAL;
+
+ hmm = hmm_register(vma->vm_mm);
+ if (!hmm) {
+ hmm_pfns_clear(pfns, start, end);
+ return -ENOMEM;
+ }
+ /* Caller must have registered a mirror using hmm_mirror_register() */
+ if (!hmm->mmu_notifier.ops)
+ return -EINVAL;
+
+ /* Initialize range to track CPU page table update */
+ range->start = start;
+ range->pfns = pfns;
+ range->end = end;
+ spin_lock(&hmm->lock);
+ range->valid = true;
+ list_add_rcu(&range->list, &hmm->ranges);
+ spin_unlock(&hmm->lock);
+
+ /* FIXME support hugetlb fs */
+ if (is_vm_hugetlb_page(vma) || (vma->vm_flags & VM_SPECIAL)) {
+ hmm_pfns_special(pfns, start, end);
+ return 0;
+ }
+
+ ret = hmm_vma_walk(vma, fault, start, end, pfns, block);
+ if (ret)
+ hmm_vma_range_done(vma, range);
+ return ret;
+}
+EXPORT_SYMBOL(hmm_vma_fault);
#endif /* IS_ENABLED(CONFIG_HMM_MIRROR) */
_
Patches currently in -mm which might be from jglisse@redhat.com are
mm-memory-hotplug-convert-device-bool-to-int-to-allow-for-more-flags-v3.patch
mm-put_page-move-ref-decrement-to-put_zone_device_page.patch
mm-zone_device-free-page-callback-when-page-is-freed-v3.patch
mm-zone_device-unaddressable-add-support-for-un-addressable-device-memory-v3.patch
mm-zone_device-x86-add-support-for-un-addressable-device-memory.patch
mm-migrate-add-new-boolean-copy-flag-to-migratepage-callback.patch
mm-migrate-new-memory-migration-helper-for-use-with-device-memory-v4.patch
mm-migrate-migrate_vma-unmap-page-from-vma-while-collecting-pages.patch
mm-hmm-heterogeneous-memory-management-hmm-for-short.patch
mm-hmm-mirror-mirror-process-address-space-on-device-with-hmm-helpers.patch
mm-hmm-mirror-helper-to-snapshot-cpu-page-table-v2.patch
mm-hmm-mirror-device-page-fault-handler.patch
mm-hmm-migrate-support-un-addressable-zone_device-page-in-migration.patch
mm-migrate-allow-migrate_vma-to-alloc-new-page-on-empty-entry.patch
mm-hmm-devmem-device-memory-hotplug-using-zone_device.patch
mm-hmm-devmem-dummy-hmm-device-for-zone_device-memory-v2.patch
^ permalink raw reply [flat|nested] 2+ messages in thread
* + mm-hmm-mirror-device-page-fault-handler.patch added to -mm tree
@ 2017-08-17 21:41 akpm
0 siblings, 0 replies; 2+ messages in thread
From: akpm @ 2017-08-17 21:41 UTC (permalink / raw)
To: jglisse, SCheung, aneesh.kumar, benh, bsingharora,
dan.j.williams, dnellans, ebaskakov, hannes, jhubbard,
kirill.shutemov, mhairgrove, mhocko, paulmck, ross.zwisler,
sgutti, vdavydov.dev, mm-commits
The patch titled
Subject: mm/hmm/mirror: device page fault handler
has been added to the -mm tree. Its filename is
mm-hmm-mirror-device-page-fault-handler.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/mm-hmm-mirror-device-page-fault-handler.patch
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/mm-hmm-mirror-device-page-fault-handler.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/SubmitChecklist 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@redhat.com>
Subject: mm/hmm/mirror: device page fault handler
This handles page fault on behalf of device driver, unlike
handle_mm_fault() it does not trigger migration back to system memory for
device memory.
Link: http://lkml.kernel.org/r/20170817000548.32038-6-jglisse@redhat.com
Signed-off-by: Jérôme Glisse <jglisse@redhat.com>
Signed-off-by: Evgeny Baskakov <ebaskakov@nvidia.com>
Signed-off-by: John Hubbard <jhubbard@nvidia.com>
Signed-off-by: Mark Hairgrove <mhairgrove@nvidia.com>
Signed-off-by: Sherry Cheung <SCheung@nvidia.com>
Signed-off-by: Subhash Gutti <sgutti@nvidia.com>
Cc: Aneesh Kumar <aneesh.kumar@linux.vnet.ibm.com>
Cc: Balbir Singh <bsingharora@gmail.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: David Nellans <dnellans@nvidia.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Ross Zwisler <ross.zwisler@linux.intel.com>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
include/linux/hmm.h | 27 ++++
mm/hmm.c | 256 ++++++++++++++++++++++++++++++++++++++++--
2 files changed, 271 insertions(+), 12 deletions(-)
diff -puN include/linux/hmm.h~mm-hmm-mirror-device-page-fault-handler include/linux/hmm.h
--- a/include/linux/hmm.h~mm-hmm-mirror-device-page-fault-handler
+++ a/include/linux/hmm.h
@@ -292,6 +292,33 @@ int hmm_vma_get_pfns(struct vm_area_stru
unsigned long end,
hmm_pfn_t *pfns);
bool hmm_vma_range_done(struct vm_area_struct *vma, struct hmm_range *range);
+
+
+/*
+ * Fault memory on behalf of device driver. Unlike handle_mm_fault(), this will
+ * not migrate any device memory back to system memory. The hmm_pfn_t array will
+ * be updated with the fault result and current snapshot of the CPU page table
+ * for the range.
+ *
+ * The mmap_sem must be taken in read mode before entering and it might be
+ * dropped by the function if the block argument is false. In that case, the
+ * function returns -EAGAIN.
+ *
+ * Return value does not reflect if the fault was successful for every single
+ * address or not. Therefore, the caller must to inspect the hmm_pfn_t array to
+ * determine fault status for each address.
+ *
+ * Trying to fault inside an invalid vma will result in -EINVAL.
+ *
+ * See the function description in mm/hmm.c for further documentation.
+ */
+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);
#endif /* IS_ENABLED(CONFIG_HMM_MIRROR) */
diff -puN mm/hmm.c~mm-hmm-mirror-device-page-fault-handler mm/hmm.c
--- a/mm/hmm.c~mm-hmm-mirror-device-page-fault-handler
+++ a/mm/hmm.c
@@ -236,6 +236,36 @@ void hmm_mirror_unregister(struct hmm_mi
}
EXPORT_SYMBOL(hmm_mirror_unregister);
+struct hmm_vma_walk {
+ struct hmm_range *range;
+ unsigned long last;
+ bool fault;
+ bool block;
+ bool write;
+};
+
+static int hmm_vma_do_fault(struct mm_walk *walk,
+ unsigned long addr,
+ hmm_pfn_t *pfn)
+{
+ unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_REMOTE;
+ struct hmm_vma_walk *hmm_vma_walk = walk->private;
+ struct vm_area_struct *vma = walk->vma;
+ int r;
+
+ flags |= hmm_vma_walk->block ? 0 : FAULT_FLAG_ALLOW_RETRY;
+ flags |= hmm_vma_walk->write ? FAULT_FLAG_WRITE : 0;
+ r = handle_mm_fault(vma, addr, flags);
+ if (r & VM_FAULT_RETRY)
+ return -EBUSY;
+ if (r & VM_FAULT_ERROR) {
+ *pfn = HMM_PFN_ERROR;
+ return -EFAULT;
+ }
+
+ return -EAGAIN;
+}
+
static void hmm_pfns_special(hmm_pfn_t *pfns,
unsigned long addr,
unsigned long end)
@@ -259,34 +289,62 @@ static int hmm_pfns_bad(unsigned long ad
return 0;
}
+static void hmm_pfns_clear(hmm_pfn_t *pfns,
+ unsigned long addr,
+ unsigned long end)
+{
+ for (; addr < end; addr += PAGE_SIZE, pfns++)
+ *pfns = 0;
+}
+
static int hmm_vma_walk_hole(unsigned long addr,
unsigned long end,
struct mm_walk *walk)
{
- struct hmm_range *range = walk->private;
+ struct hmm_vma_walk *hmm_vma_walk = walk->private;
+ struct hmm_range *range = hmm_vma_walk->range;
hmm_pfn_t *pfns = range->pfns;
unsigned long i;
+ hmm_vma_walk->last = addr;
i = (addr - range->start) >> PAGE_SHIFT;
- for (; addr < end; addr += PAGE_SIZE, i++)
+ for (; addr < end; addr += PAGE_SIZE, i++) {
pfns[i] = HMM_PFN_EMPTY;
+ if (hmm_vma_walk->fault) {
+ int ret;
- return 0;
+ ret = hmm_vma_do_fault(walk, addr, &pfns[i]);
+ if (ret != -EAGAIN)
+ return ret;
+ }
+ }
+
+ return hmm_vma_walk->fault ? -EAGAIN : 0;
}
static int hmm_vma_walk_clear(unsigned long addr,
unsigned long end,
struct mm_walk *walk)
{
- struct hmm_range *range = walk->private;
+ struct hmm_vma_walk *hmm_vma_walk = walk->private;
+ struct hmm_range *range = hmm_vma_walk->range;
hmm_pfn_t *pfns = range->pfns;
unsigned long i;
+ hmm_vma_walk->last = addr;
i = (addr - range->start) >> PAGE_SHIFT;
- for (; addr < end; addr += PAGE_SIZE, i++)
+ for (; addr < end; addr += PAGE_SIZE, i++) {
pfns[i] = 0;
+ if (hmm_vma_walk->fault) {
+ int ret;
- return 0;
+ ret = hmm_vma_do_fault(walk, addr, &pfns[i]);
+ if (ret != -EAGAIN)
+ return ret;
+ }
+ }
+
+ return hmm_vma_walk->fault ? -EAGAIN : 0;
}
static int hmm_vma_walk_pmd(pmd_t *pmdp,
@@ -294,15 +352,18 @@ static int hmm_vma_walk_pmd(pmd_t *pmdp,
unsigned long end,
struct mm_walk *walk)
{
- struct hmm_range *range = walk->private;
+ struct hmm_vma_walk *hmm_vma_walk = walk->private;
+ struct hmm_range *range = hmm_vma_walk->range;
struct vm_area_struct *vma = walk->vma;
hmm_pfn_t *pfns = range->pfns;
unsigned long addr = start, i;
+ bool write_fault;
hmm_pfn_t flag;
pte_t *ptep;
i = (addr - range->start) >> PAGE_SHIFT;
flag = vma->vm_flags & VM_READ ? HMM_PFN_READ : 0;
+ write_fault = hmm_vma_walk->fault & hmm_vma_walk->write;
again:
if (pmd_none(*pmdp))
@@ -331,6 +392,9 @@ again:
if (pmd_protnone(pmd))
return hmm_vma_walk_clear(start, end, walk);
+ if (write_fault && !pmd_write(pmd))
+ return hmm_vma_walk_clear(start, end, walk);
+
pfn = pmd_pfn(pmd) + pte_index(addr);
flag |= pmd_write(pmd) ? HMM_PFN_WRITE : 0;
for (; addr < end; addr += PAGE_SIZE, i++, pfn++)
@@ -347,13 +411,55 @@ again:
pfns[i] = 0;
- if (pte_none(pte) || !pte_present(pte)) {
+ if (pte_none(pte)) {
pfns[i] = HMM_PFN_EMPTY;
+ if (hmm_vma_walk->fault)
+ goto fault;
continue;
}
+ if (!pte_present(pte)) {
+ swp_entry_t entry;
+
+ if (!non_swap_entry(entry)) {
+ if (hmm_vma_walk->fault)
+ goto fault;
+ continue;
+ }
+
+ entry = pte_to_swp_entry(pte);
+
+ /*
+ * This is a special swap entry, ignore migration, use
+ * device and report anything else as error.
+ */
+ if (is_migration_entry(entry)) {
+ if (hmm_vma_walk->fault) {
+ pte_unmap(ptep);
+ hmm_vma_walk->last = addr;
+ migration_entry_wait(vma->vm_mm,
+ pmdp, addr);
+ return -EAGAIN;
+ }
+ continue;
+ } else {
+ /* Report error for everything else */
+ pfns[i] = HMM_PFN_ERROR;
+ }
+ continue;
+ }
+
+ if (write_fault && !pte_write(pte))
+ goto fault;
+
pfns[i] = hmm_pfn_t_from_pfn(pte_pfn(pte)) | flag;
pfns[i] |= pte_write(pte) ? HMM_PFN_WRITE : 0;
+ continue;
+
+fault:
+ pte_unmap(ptep);
+ /* Fault all pages in range */
+ return hmm_vma_walk_clear(start, end, walk);
}
pte_unmap(ptep - 1);
@@ -386,6 +492,7 @@ int hmm_vma_get_pfns(struct vm_area_stru
unsigned long end,
hmm_pfn_t *pfns)
{
+ struct hmm_vma_walk hmm_vma_walk;
struct mm_walk mm_walk;
struct hmm *hmm;
@@ -417,9 +524,12 @@ int hmm_vma_get_pfns(struct vm_area_stru
list_add_rcu(&range->list, &hmm->ranges);
spin_unlock(&hmm->lock);
+ hmm_vma_walk.fault = false;
+ hmm_vma_walk.range = range;
+ mm_walk.private = &hmm_vma_walk;
+
mm_walk.vma = vma;
mm_walk.mm = vma->vm_mm;
- mm_walk.private = range;
mm_walk.pte_entry = NULL;
mm_walk.test_walk = NULL;
mm_walk.hugetlb_entry = NULL;
@@ -427,7 +537,6 @@ int hmm_vma_get_pfns(struct vm_area_stru
mm_walk.pte_hole = hmm_vma_walk_hole;
walk_page_range(start, end, &mm_walk);
-
return 0;
}
EXPORT_SYMBOL(hmm_vma_get_pfns);
@@ -454,7 +563,7 @@ EXPORT_SYMBOL(hmm_vma_get_pfns);
*
* There are two ways to use this :
* again:
- * hmm_vma_get_pfns(vma, range, start, end, pfns);
+ * hmm_vma_get_pfns(vma, range, start, end, pfns); or hmm_vma_fault(...);
* trans = device_build_page_table_update_transaction(pfns);
* device_page_table_lock();
* if (!hmm_vma_range_done(vma, range)) {
@@ -465,7 +574,7 @@ EXPORT_SYMBOL(hmm_vma_get_pfns);
* device_page_table_unlock();
*
* Or:
- * hmm_vma_get_pfns(vma, range, start, end, pfns);
+ * hmm_vma_get_pfns(vma, range, start, end, pfns); or hmm_vma_fault(...);
* device_page_table_lock();
* hmm_vma_range_done(vma, range);
* device_update_page_table(pfns);
@@ -494,4 +603,127 @@ bool hmm_vma_range_done(struct vm_area_s
return range->valid;
}
EXPORT_SYMBOL(hmm_vma_range_done);
+
+/*
+ * hmm_vma_fault() - try to fault some address in a virtual address range
+ * @vma: virtual memory area containing the virtual address range
+ * @range: use to track pfns array content validity
+ * @start: fault range virtual start address (inclusive)
+ * @end: fault range virtual end address (exclusive)
+ * @pfns: array of hmm_pfn_t, only entry with fault flag set will be faulted
+ * @write: is it a write fault
+ * @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)
+ *
+ * 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.
+ *
+ * On error, for one virtual address in the range, the function will set the
+ * hmm_pfn_t error flag for the corresponding pfn entry.
+ *
+ * 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(vma, start, end, pfns, allow_retry);
+ * switch (ret) {
+ * case -EAGAIN:
+ * hmm_vma_range_done(vma, 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;
+ * 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(vma, 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 vm_area_struct *vma,
+ struct hmm_range *range,
+ unsigned long start,
+ unsigned long end,
+ hmm_pfn_t *pfns,
+ bool write,
+ bool block)
+{
+ struct hmm_vma_walk hmm_vma_walk;
+ struct mm_walk mm_walk;
+ struct hmm *hmm;
+ int ret;
+
+ /* Sanity check, this really should not happen ! */
+ if (start < vma->vm_start || start >= vma->vm_end)
+ return -EINVAL;
+ if (end < vma->vm_start || end > vma->vm_end)
+ return -EINVAL;
+
+ hmm = hmm_register(vma->vm_mm);
+ if (!hmm) {
+ hmm_pfns_clear(pfns, start, end);
+ return -ENOMEM;
+ }
+ /* Caller must have registered a mirror using hmm_mirror_register() */
+ if (!hmm->mmu_notifier.ops)
+ return -EINVAL;
+
+ /* Initialize range to track CPU page table update */
+ range->start = start;
+ range->pfns = pfns;
+ range->end = end;
+ spin_lock(&hmm->lock);
+ range->valid = true;
+ list_add_rcu(&range->list, &hmm->ranges);
+ spin_unlock(&hmm->lock);
+
+ /* FIXME support hugetlb fs */
+ if (is_vm_hugetlb_page(vma) || (vma->vm_flags & VM_SPECIAL)) {
+ hmm_pfns_special(pfns, start, end);
+ return 0;
+ }
+
+ hmm_vma_walk.fault = true;
+ hmm_vma_walk.write = write;
+ hmm_vma_walk.block = block;
+ hmm_vma_walk.range = range;
+ mm_walk.private = &hmm_vma_walk;
+ hmm_vma_walk.last = range->start;
+
+ mm_walk.vma = vma;
+ mm_walk.mm = vma->vm_mm;
+ mm_walk.pte_entry = NULL;
+ mm_walk.test_walk = NULL;
+ mm_walk.hugetlb_entry = NULL;
+ mm_walk.pmd_entry = hmm_vma_walk_pmd;
+ mm_walk.pte_hole = hmm_vma_walk_hole;
+
+ do {
+ ret = walk_page_range(start, end, &mm_walk);
+ start = hmm_vma_walk.last;
+ } while (ret == -EAGAIN);
+
+ if (ret) {
+ unsigned long i;
+
+ i = (hmm_vma_walk.last - range->start) >> PAGE_SHIFT;
+ hmm_pfns_clear(&pfns[i], hmm_vma_walk.last, end);
+ hmm_vma_range_done(vma, range);
+ }
+ return ret;
+}
+EXPORT_SYMBOL(hmm_vma_fault);
#endif /* IS_ENABLED(CONFIG_HMM_MIRROR) */
_
Patches currently in -mm which might be from jglisse@redhat.com are
hmm-heterogeneous-memory-management-documentation-v3.patch
mm-hmm-heterogeneous-memory-management-hmm-for-short-v5.patch
mm-hmm-mirror-mirror-process-address-space-on-device-with-hmm-helpers-v3.patch
mm-hmm-mirror-helper-to-snapshot-cpu-page-table-v4.patch
mm-hmm-mirror-device-page-fault-handler.patch
mm-zone_device-new-type-of-zone_device-for-unaddressable-memory-v5.patch
mm-zone_device-special-case-put_page-for-device-private-pages-v4.patch
mm-memcontrol-allow-to-uncharge-page-without-using-page-lru-field.patch
mm-memcontrol-support-memory_device_private-v4.patch
mm-hmm-devmem-device-memory-hotplug-using-zone_device-v7.patch
mm-hmm-devmem-dummy-hmm-device-for-zone_device-memory-v3.patch
mm-migrate-new-migrate-mode-migrate_sync_no_copy.patch
mm-migrate-new-memory-migration-helper-for-use-with-device-memory-v5.patch
mm-migrate-migrate_vma-unmap-page-from-vma-while-collecting-pages.patch
mm-migrate-support-un-addressable-zone_device-page-in-migration-v3.patch
mm-migrate-allow-migrate_vma-to-alloc-new-page-on-empty-entry-v4.patch
mm-device-public-memory-device-memory-cache-coherent-with-cpu-v5.patch
mm-hmm-add-new-helper-to-hotplug-cdm-memory-region-v3.patch
lib-interval_tree-fast-overlap-detection-fix.patch
^ permalink raw reply [flat|nested] 2+ messages in thread
end of thread, other threads:[~2017-08-17 21:41 UTC | newest]
Thread overview: 2+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2017-03-16 20:52 + mm-hmm-mirror-device-page-fault-handler.patch added to -mm tree akpm
2017-08-17 21:41 akpm
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).