search for: memory_device_fs_dax

...old code[1] it worked for me. I am thinking when we map two different devices (e.g with device mapper), will start & end pfn still point to same pgmap? Or there is something else which I am missing here. Note: I tested only EXT4. [1] - if (pgmap && pgmap->type == MEMORY_DEVICE_FS_DAX) + end_pgmap = get_dev_pagemap(pfn_t_to_pfn(end_pfn), NULL); + if (pgmap && pgmap == end_pgmap && pgmap->type == MEMORY_DEVICE_FS_DAX + && pfn_t_to_page(pfn)->pgmap == pgmap + &...

...old code[1] it worked for me. I am thinking when we map two different devices (e.g with device mapper), will start & end pfn still point to same pgmap? Or there is something else which I am missing here. Note: I tested only EXT4. [1] - if (pgmap && pgmap->type == MEMORY_DEVICE_FS_DAX) + end_pgmap = get_dev_pagemap(pfn_t_to_pfn(end_pfn), NULL); + if (pgmap && pgmap == end_pgmap && pgmap->type == MEMORY_DEVICE_FS_DAX + && pfn_t_to_page(pfn)->pgmap == pgmap + &...

...p { * wakeup is used to coordinate physical address space management (ex: * fs truncate/hole punch) vs pinned pages (ex: device dma). * + * MEMORY_DEVICE_DEVDAX: + * Host memory that has similar access semantics as System RAM i.e. DMA + * coherent and supports page pinning. In contrast to + * MEMORY_DEVICE_FS_DAX, this memory is access via a device-dax + * character device. + * * MEMORY_DEVICE_PCI_P2PDMA: * Device memory residing in a PCI BAR intended for use with Peer-to-Peer * transactions. */ enum memory_type { + /* 0 is reserved to catch uninitialized type fields */ MEMORY_DEVICE_PRIVATE = 1,...

...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)) - return -ENOMEM; - pgmap->type = MEMORY_DEVICE_FS_DAX; - pgmap->ops = &fsdax_pagemap_ops; - return 0; -} - static int pmem_attach_disk(struct device *dev, struct nd_namespace_common *ndns) { @@ -421,8 +406,8 @@ static int pmem_attach_disk(struct device *dev, pmem->pfn_flags = PFN_DEV; pmem->pgmap.ref = &q->q_usage_counter;...

...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)) - return -ENOMEM; - pgmap->type = MEMORY_DEVICE_FS_DAX; - pgmap->ops = &fsdax_pagemap_ops; - return 0; -} - static int pmem_attach_disk(struct device *dev, struct nd_namespace_common *ndns) { @@ -423,8 +408,8 @@ static int pmem_attach_disk(struct device *dev, pmem->pfn_flags = PFN_DEV; pmem->pgmap.ref = &q->q_usage_counter;...

...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)) - return -ENOMEM; - pgmap->type = MEMORY_DEVICE_FS_DAX; - pgmap->ops = &fsdax_pagemap_ops; - return 0; -} - static int pmem_attach_disk(struct device *dev, struct nd_namespace_common *ndns) { @@ -415,8 +400,8 @@ static int pmem_attach_disk(struct device *dev, pmem->pfn_flags = PFN_DEV; pmem->pgmap.ref = &q->q_usage_counter;...

...to mm/internal.h. > +#ifdef CONFIG_DEV_PAGEMAP_OPS > +static void __put_devmap_managed_page(struct page *page) > +{ > + if (!static_branch_unlikely(&devmap_managed_key)) > + return; > + > + switch (page->pgmap->type) { > + case MEMORY_DEVICE_PRIVATE: > + case MEMORY_DEVICE_FS_DAX: > + free_devmap_managed_page(page); > + break; > + default: > + break; > + } > +} > +#else > +static inline void __put_devmap_managed_page(struct page *page) > +{ > +} > +#endif I think this should be moved to mm/memremap.c or even better actually be folded int...

...CONFIG_DEV_PAGEMAP_OPS >> +static void __put_devmap_managed_page(struct page *page) >> +{ >> + if (!static_branch_unlikely(&devmap_managed_key)) >> + return; >> + >> + switch (page->pgmap->type) { >> + case MEMORY_DEVICE_PRIVATE: >> + case MEMORY_DEVICE_FS_DAX: >> + free_devmap_managed_page(page); >> + break; >> + default: >> + break; >> + } >> +} >> +#else >> +static inline void __put_devmap_managed_page(struct page *page) >> +{ >> +} >> +#endif > > I think this should be moved...

...> .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)) > - return -ENOMEM; > - pgmap->type = MEMORY_DEVICE_FS_DAX; > - pgmap->ops = &fsdax_pagemap_ops; > - return 0; > -} > - > static int pmem_attach_disk(struct device *dev, > struct nd_namespace_common *ndns) > { > @@ -415,8 +400,8 @@ static int pmem_attach_disk(struct device *dev, > pmem->pfn_flags = PFN_DEV; >...

...m thinking when we map two different devices (e.g with device mapper), will > start & end pfn still point to same pgmap? Or there is something else which > I am missing here. > > Note: I tested only EXT4. > > [1] > > - if (pgmap && pgmap->type == MEMORY_DEVICE_FS_DAX) > + end_pgmap = get_dev_pagemap(pfn_t_to_pfn(end_pfn), NULL); > + if (pgmap && pgmap == end_pgmap && pgmap->type == MEMORY_DEVICE_FS_DAX > + && pfn_t_to_page(pfn)->pgmap == pgmap > +...

...TIC_KEY_FALSE(devmap_managed_key); - -static inline bool page_is_devmap_managed(struct page *page) -{ - if (!static_branch_unlikely(&devmap_managed_key)) - return false; - if (!is_zone_device_page(page)) - return false; - switch (page->pgmap->type) { - case MEMORY_DEVICE_PRIVATE: - case MEMORY_DEVICE_FS_DAX: - return true; - default: - break; - } - return false; -} - -void put_devmap_managed_page(struct page *page); - -#else /* CONFIG_DEV_PAGEMAP_OPS */ -static inline bool page_is_devmap_managed(struct page *page) -{ - return false; -} - -static inline void put_devmap_managed_page(struct page *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

On Fri, May 10, 2019 at 5:45 PM Pankaj Gupta <pagupta at redhat.com> wrote: > > > > > > > > > This patch adds 'DAXDEV_SYNC' flag which is set > > > for nd_region doing synchronous flush. This later > > > is used to disable MAP_SYNC functionality for > > > ext4 & xfs filesystem for devices don't support > > >

...form that have an advance system bus (like CAPI or CCIX). A - * driver can hotplug the device memory using ZONE_DEVICE and with that memory - * type. Any page of a process can be migrated to such memory. However no one - * should be allow to pin such memory so that it can always be evicted. - * * MEMORY_DEVICE_FS_DAX: * Host memory that has similar access semantics as System RAM i.e. DMA * coherent and supports page pinning. In support of coordinating page @@ -58,7 +51,6 @@ struct vmem_altmap { */ enum memory_type { MEMORY_DEVICE_PRIVATE = 1, - MEMORY_DEVICE_PUBLIC, MEMORY_DEVICE_FS_DAX, MEMORY_DEV...

...af..7a7013c57a4a 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1110,14 +1110,7 @@ static inline bool page_is_devmap_managed(struct page *page) return false; if (!is_zone_device_page(page)) return false; - switch (page->pgmap->type) { - case MEMORY_DEVICE_PRIVATE: - case MEMORY_DEVICE_FS_DAX: - return true; - default: - break; - } - return false; + return page->pgmap->type == MEMORY_DEVICE_FS_DAX; } void put_devmap_managed_page(struct page *page); diff --git a/lib/test_hmm.c b/lib/test_hmm.c index e151a7f10519..bf92a261fa6f 100644 --- a/lib/test_hmm.c +++ b/lib/test_hmm.c @...

...migration code in the mean time. > > I think P2P is pretty trivial, given that ZONE_DEVICE pages are used like > a normal memory allocator. DAX is the interesting case, any specific > help that you need with that? There are 4 types of ZONE_DEVICE struct pages: MEMORY_DEVICE_PRIVATE, MEMORY_DEVICE_FS_DAX, MEMORY_DEVICE_GENERIC, and MEMORY_DEVICE_PCI_P2PDMA. Currently, memremap_pages() allocates struct pages for a physical address range with a page_ref_count(page) of one and increments the pgmap->ref per CPU reference count by the number of pages created since each ZONE_DEVICE struct page has a...

...2e..ac848eeb2a1d 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1110,14 +1110,7 @@ static inline bool page_is_devmap_managed(struct page *page) return false; if (!is_zone_device_page(page)) return false; - switch (page->pgmap->type) { - case MEMORY_DEVICE_PRIVATE: - case MEMORY_DEVICE_FS_DAX: - return true; - default: - break; - } - return false; + return page->pgmap->type == MEMORY_DEVICE_FS_DAX; } void put_devmap_managed_page(struct page *page); diff --git a/lib/test_hmm.c b/lib/test_hmm.c index e151a7f10519..bf92a261fa6f 100644 --- a/lib/test_hmm.c +++ b/lib/test_hmm.c @...

...atic inline bool page_is_devmap_managed(struct page *page) > -{ > - if (!static_branch_unlikely(&devmap_managed_key)) > - return false; > - if (!is_zone_device_page(page)) > - return false; > - switch (page->pgmap->type) { > - case MEMORY_DEVICE_PRIVATE: > - case MEMORY_DEVICE_FS_DAX: > - return true; > - default: > - break; > - } > - return false; > -} > - > -void put_devmap_managed_page(struct page *page); > - > -#else /* CONFIG_DEV_PAGEMAP_OPS */ > -static inline bool page_is_devmap_managed(struct page *page) > -{ > - return false; &g...

Hi Dan, Jérôme and Jason, below is a series that cleans up the dev_pagemap interface so that it is more easily usable, which removes the need to wrap it in hmm and thus allowing to kill a lot of code Note: this series is on top of Linux 5.2-rc5 and has some minor conflicts with the hmm tree that are easy to resolve. Diffstat summary: 32 files changed, 361 insertions(+), 1012 deletions(-) Git

...)) { + WARN(1, "Device private memory not supported\n"); + return ERR_PTR(-EINVAL); + } + break; + case MEMORY_DEVICE_PUBLIC: + if (!IS_ENABLED(CONFIG_DEVICE_PUBLIC)) { + WARN(1, "Device public memory not supported\n"); + return ERR_PTR(-EINVAL); + } + break; + case MEMORY_DEVICE_FS_DAX: + if (!IS_ENABLED(CONFIG_ZONE_DEVICE) || + IS_ENABLED(CONFIG_FS_DAX_LIMITED)) { + WARN(1, "File system DAX not supported\n"); + return ERR_PTR(-EINVAL); + } + break; + case MEMORY_DEVICE_PCI_P2PDMA: + break; + default: + WARN(1, "Invalid pgmap type %d\n", pgmap-&g...