search for: _refcount

On Fri, Sep 25, 2020 at 01:44:41PM -0700, Ralph Campbell wrote: > error = ___wait_var_event(&page->_refcount, > - atomic_read(&page->_refcount) == 1, > + dax_layout_is_idle_page(page), > TASK_INTERRUPTIBLE, 0, 0, > ext4_wait_dax_page(ei)); > +++ b/fs/xfs/xfs_file.c > @@ -750,7 +750,7 @@ xfs_break_dax_layouts( > > *retry = true; > return ___wait_var_...

..., or other * get_user_pages() usages. * diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index bf596467c234..d9f8ad55523a 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -3927,7 +3927,7 @@ int ext4_break_layouts(struct inode *inode) return 0; error = ___wait_var_event(&page->_refcount, - atomic_read(&page->_refcount) == 1, + dax_layout_is_idle_page(page), TASK_INTERRUPTIBLE, 0, 0, ext4_wait_dax_page(ei)); } while (error == 0); diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index a29f78a663ca..29ab96541bc1 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/x...

...urn page; } return NULL; diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index bf596467c234..4c3b80e68121 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -3926,10 +3926,7 @@ int ext4_break_layouts(struct inode *inode) if (!page) return 0; - error = ___wait_var_event(&page->_refcount, - atomic_read(&page->_refcount) == 1, - TASK_INTERRUPTIBLE, 0, 0, - ext4_wait_dax_page(ei)); + error = dax_wait_page(ei, page, ext4_wait_dax_page); } while (error == 0); return error; diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 3d1b95124744..a5304aaeaa3a 100644...

...successfully run xfstests on ext4 with the memmap kernel boot option to simulate pmem. One of the big changes in v2 is that devm_memremap_pages() and memremap_pages() now return the struct pages' reference count set to zero instead of one. Normally, get_page() will VM_BUG_ON_PAGE() if page->_refcount is zero. I didn't see any such warnings running the xfstests with dax/pmem but I'm not clear how the zero to one reference count is handled. Other changes in v2: Rebased to Linux-5.9.0-rc6 to include pmem fixes. I added patch 1 to introduce a page refcount helper for ext4 and xfs as sugges...

On Mon, Sep 14, 2020 at 04:10:38PM -0700, Dan Williams wrote: > You also need to fix up ext4_break_layouts() and > xfs_break_dax_layouts() to expect ->_refcount is 0 instead of 1. This > also needs some fstests exposure. While we're at it, can we add a wait_fsdax_unref helper macro that hides the _refcount access from the file systems?

...node.c b/fs/ext4/inode.c > index bf596467c234..d9f8ad55523a 100644 > --- a/fs/ext4/inode.c > +++ b/fs/ext4/inode.c > @@ -3927,7 +3927,7 @@ int ext4_break_layouts(struct inode *inode) > return 0; > > error = ___wait_var_event(&page->_refcount, > - atomic_read(&page->_refcount) == 1, > + dax_layout_is_idle_page(page), > TASK_INTERRUPTIBLE, 0, 0, > ext4_wait_dax_page(ei)); > } while (err...

.... Added a helper for dax_wait_page() as suggested by Christoph Hellwig. Changes in v2: One of the big changes in v2 is that devm_memremap_pages() and memremap_pages() now return the struct pages' reference count set to zero instead of one. Normally, get_page() will VM_BUG_ON_PAGE() if page->_refcount is zero. I didn't see any such warnings running the xfstests with dax/pmem but I'm not clear how the zero to one reference count is handled. Other changes in v2: Rebased to Linux-5.9.0-rc6 to include pmem fixes. I added patch 1 to introduce a page refcount helper for ext4 and xfs as sugges...

On 9/15/20 11:10 PM, Christoph Hellwig wrote: > On Mon, Sep 14, 2020 at 04:10:38PM -0700, Dan Williams wrote: >> You also need to fix up ext4_break_layouts() and >> xfs_break_dax_layouts() to expect ->_refcount is 0 instead of 1. This >> also needs some fstests exposure. > > While we're at it, can we add a wait_fsdax_unref helper macro that hides > the _refcount access from the file systems? Sure. I'll add a separate patch for it in v2.

...*page) mem_cgroup_uncharge(page); + /* + * ZONE_DEVICE drivers keep a reference to the page while it is on + * the driver's free list so we reset the reference count here. + * This matches the initial reference when the struct pages are + * created by memremap_pages(). + */ + set_page_refcounted(page); + /* * When a device_private page is freed, the page->mapping field * may still contain a (stale) mapping value. For example, the diff --git a/mm/migrate.c b/mm/migrate.c index 4f89360d9e77..be1586582b52 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -380,11 +380,6 @@ static in...

...unsigned long pfn, EXPORT_SYMBOL_GPL(get_dev_pagemap); #ifdef CONFIG_DEV_PAGEMAP_OPS -void free_devmap_managed_page(struct page *page) +static void free_device_private_page(struct page *page) { - /* notify page idle for dax */ - if (!is_device_private_page(page)) { - wake_up_var(&page->_refcount); - return; - } - __ClearPageWaiters(page); - mem_cgroup_uncharge(page); /* @@ -540,4 +495,19 @@ void free_devmap_managed_page(struct page *page) page->mapping = NULL; page->pgmap->ops->page_free(page); } + +void free_zone_device_page(struct page *page) +{ + switch (page-&...

...ev_pagemap); > > #ifdef CONFIG_DEV_PAGEMAP_OPS > -void free_devmap_managed_page(struct page *page) > +static void free_device_private_page(struct page *page) > { > - /* notify page idle for dax */ > - if (!is_device_private_page(page)) { > - wake_up_var(&page->_refcount); > - return; > - } > - > __ClearPageWaiters(page); > - > mem_cgroup_uncharge(page); > > /* > @@ -540,4 +495,19 @@ void free_devmap_managed_page(struct page *page) > page->mapping = NULL; > page->pgmap->ops->page_free(page); > } &...

On Fri, Nov 06, 2020 at 01:26:50PM -0800, Ralph Campbell wrote: > > On 11/6/20 12:03 AM, Christoph Hellwig wrote: >> I hate the extra pin count magic here. IMHO we really need to finish >> off the series to get rid of the extra references on the ZONE_DEVICE >> pages first. > > First, thanks for the review comments. > > I don't like the extra refcount

...unsigned long pfn, EXPORT_SYMBOL_GPL(get_dev_pagemap); #ifdef CONFIG_DEV_PAGEMAP_OPS -void free_devmap_managed_page(struct page *page) +static void free_device_private_page(struct page *page) { - /* notify page idle for dax */ - if (!is_device_private_page(page)) { - wake_up_var(&page->_refcount); - return; - } - /* Clear Active bit in case of parallel mark_page_accessed */ __ClearPageActive(page); __ClearPageWaiters(page); @@ -481,4 +420,19 @@ void free_devmap_managed_page(struct page *page) page->mapping = NULL; page->pgmap->ops->page_free(page); } + +void free_zo...

...-- a/drivers/nvdimm/pmem.c +++ b/drivers/nvdimm/pmem.c @@ -334,7 +334,7 @@ static void pmem_release_disk(void *__pmem) put_disk(pmem->disk); } -static void pmem_fsdax_page_free(struct page *page, void *data) +static void pmem_fsdax_page_free(struct page *page) { wake_up_var(&page->_refcount); } diff --git a/include/linux/memremap.h b/include/linux/memremap.h index 03a4099be701..75b80de6394a 100644 --- a/include/linux/memremap.h +++ b/include/linux/memremap.h @@ -69,7 +69,7 @@ struct dev_pagemap_ops { * reach 0 refcount unless there is a refcount bug. This allows the * device dr...

...unsigned long pfn, EXPORT_SYMBOL_GPL(get_dev_pagemap); #ifdef CONFIG_DEV_PAGEMAP_OPS -void free_devmap_managed_page(struct page *page) +static void free_device_private_page(struct page *page) { - /* notify page idle for dax */ - if (!is_device_private_page(page)) { - wake_up_var(&page->_refcount); - return; - } - __ClearPageWaiters(page); - mem_cgroup_uncharge(page); /* @@ -540,4 +487,19 @@ void free_devmap_managed_page(struct page *page) page->mapping = NULL; page->pgmap->ops->page_free(page); } + +void free_zone_device_page(struct page *page) +{ + switch (page-&...

...ince then, struct page has been reorganized to not collide the ->pgmap back pointer with the ->lru list and there have been other cleanups for page pinning that might make this incremental cleanup viable. You also need to fix up ext4_break_layouts() and xfs_break_dax_layouts() to expect ->_refcount is 0 instead of 1. This also needs some fstests exposure. > I have a modified THP migration patch series that applies on top of > this one and is cleaner since I don't have to add code to handle the > +1 reference count. The link below is for the earlier v2: > ("mm/hmm/nouveau...

.../drivers/nvdimm/pmem.c @@ -334,11 +334,6 @@ static void pmem_release_disk(void *__pmem) put_disk(pmem->disk); } -static void pmem_release_pgmap_ops(void *__pgmap) -{ - dev_pagemap_put_ops(); -} - static void pmem_fsdax_page_free(struct page *page, void *data) { wake_up_var(&page->_refcount); @@ -353,16 +348,6 @@ static const struct dev_pagemap_ops pmem_legacy_pagemap_ops = { .kill = pmem_kill, }; -static int setup_pagemap_fsdax(struct device *dev, struct dev_pagemap *pgmap) -{ - dev_pagemap_get_ops(); - if (devm_add_action_or_reset(dev, pmem_release_pgmap_ops, pgmap)) - retur...

...rivers/nvdimm/pmem.c @@ -342,11 +342,6 @@ static void pmem_release_disk(void *__pmem) put_disk(pmem->disk); } -static void pmem_release_pgmap_ops(void *__pgmap) -{ - dev_pagemap_put_ops(); -} - static void pmem_pagemap_page_free(struct page *page, void *data) { wake_up_var(&page->_refcount); @@ -358,16 +353,6 @@ static const struct dev_pagemap_ops fsdax_pagemap_ops = { .cleanup = pmem_pagemap_cleanup, }; -static int setup_pagemap_fsdax(struct device *dev, struct dev_pagemap *pgmap) -{ - dev_pagemap_get_ops(); - if (devm_add_action_or_reset(dev, pmem_release_pgmap_ops, pgmap)) -...

...vate(folio)) > refs++; > > return refs; > --- a/mm/vmscan.c 2022-07-06 14:24:44.531942217 -0700 > +++ b/mm/vmscan.c 2022-07-06 15:49:37.000000000 -0700 > @@ -2494,6 +2494,10 @@ shrink_inactive_list(unsigned long nr_to > * The downside is that we have to touch folio->_refcount against each folio. > * But we had to alter folio->flags anyway. > */ > +static inline bool folio_counted_private(struct folio *folio) > +{ > + return !folio_test_swapcache(folio) && folio_get_private(folio); > +} > static void shrink_active_list(unsigned long n...

...vate(folio)) > refs++; > > return refs; > --- a/mm/vmscan.c 2022-07-06 14:24:44.531942217 -0700 > +++ b/mm/vmscan.c 2022-07-06 15:49:37.000000000 -0700 > @@ -2494,6 +2494,10 @@ shrink_inactive_list(unsigned long nr_to > * The downside is that we have to touch folio->_refcount against each folio. > * But we had to alter folio->flags anyway. > */ > +static inline bool folio_counted_private(struct folio *folio) > +{ > + return !folio_test_swapcache(folio) && folio_get_private(folio); > +} > static void shrink_active_list(unsigned long n...