From cdd77d3e193031cc67426cd671d8aa370f7dfee4 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Fri, 17 Nov 2017 16:23:08 -0800 Subject: nfit, libnvdimm: deprecate the generic SMART ioctl The kernel's ND_IOCTL_SMART_THRESHOLD command is based on a payload definition that has become broken / out-of-sync with recent versions of the NVDIMM_FAMILY_INTEL definition. Deprecate the use of the ND_IOCTL_SMART_THRESHOLD command in favor of the ND_CMD_CALL approach taken by NVDIMM_FAMILY_{HPE,MSFT}, where we can manage the per-vendor variance in userspace. In a couple years, when the new scheme is widely deployed in userspace packages, the ND_IOCTL_SMART_THRESHOLD support can be removed. For now we prevent new binaries from compiling against the kernel header definitions, but kernel still compatible with old binaries. The libndctl.h [1] header is now the authoritative interface definition for NVDIMM SMART. [1]: https://github.com/pmem/ndctl Signed-off-by: Dan Williams --- include/uapi/linux/ndctl.h | 54 ---------------------------------------------- 1 file changed, 54 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/ndctl.h b/include/uapi/linux/ndctl.h index 3f03567631cb..30ef1236aafa 100644 --- a/include/uapi/linux/ndctl.h +++ b/include/uapi/linux/ndctl.h @@ -15,54 +15,6 @@ #include -struct nd_cmd_smart { - __u32 status; - __u8 data[128]; -} __packed; - -#define ND_SMART_HEALTH_VALID (1 << 0) -#define ND_SMART_SPARES_VALID (1 << 1) -#define ND_SMART_USED_VALID (1 << 2) -#define ND_SMART_TEMP_VALID (1 << 3) -#define ND_SMART_CTEMP_VALID (1 << 4) -#define ND_SMART_ALARM_VALID (1 << 9) -#define ND_SMART_SHUTDOWN_VALID (1 << 10) -#define ND_SMART_VENDOR_VALID (1 << 11) -#define ND_SMART_SPARE_TRIP (1 << 0) -#define ND_SMART_TEMP_TRIP (1 << 1) -#define ND_SMART_CTEMP_TRIP (1 << 2) -#define ND_SMART_NON_CRITICAL_HEALTH (1 << 0) -#define ND_SMART_CRITICAL_HEALTH (1 << 1) -#define ND_SMART_FATAL_HEALTH (1 << 2) - -struct nd_smart_payload { - __u32 flags; - __u8 reserved0[4]; - __u8 health; - __u8 spares; - __u8 life_used; - __u8 alarm_flags; - __u16 temperature; - __u16 ctrl_temperature; - __u8 reserved1[15]; - __u8 shutdown_state; - __u32 vendor_size; - __u8 vendor_data[92]; -} __packed; - -struct nd_cmd_smart_threshold { - __u32 status; - __u8 data[8]; -} __packed; - -struct nd_smart_threshold_payload { - __u8 alarm_control; - __u8 reserved0; - __u16 temperature; - __u8 spares; - __u8 reserved[3]; -} __packed; - struct nd_cmd_dimm_flags { __u32 status; __u32 flags; @@ -211,12 +163,6 @@ static inline const char *nvdimm_cmd_name(unsigned cmd) #define ND_IOCTL 'N' -#define ND_IOCTL_SMART _IOWR(ND_IOCTL, ND_CMD_SMART,\ - struct nd_cmd_smart) - -#define ND_IOCTL_SMART_THRESHOLD _IOWR(ND_IOCTL, ND_CMD_SMART_THRESHOLD,\ - struct nd_cmd_smart_threshold) - #define ND_IOCTL_DIMM_FLAGS _IOWR(ND_IOCTL, ND_CMD_DIMM_FLAGS,\ struct nd_cmd_dimm_flags) -- cgit v1.2.3 From 8e37d00a850160bbfadbb3bf4ce49539770c5d2c Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 29 Dec 2017 08:53:50 +0100 Subject: memremap: provide stubs for vmem_altmap_offset and vmem_altmap_free Currently all calls to those functions are eliminated by the compiler when CONFIG_ZONE_DEVICE is not set, but this soon won't be the case. Signed-off-by: Christoph Hellwig Signed-off-by: Dan Williams --- include/linux/memremap.h | 18 ++++++++++++++---- 1 file changed, 14 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/memremap.h b/include/linux/memremap.h index 10d23c367048..d5a6736d9737 100644 --- a/include/linux/memremap.h +++ b/include/linux/memremap.h @@ -26,9 +26,6 @@ struct vmem_altmap { unsigned long alloc; }; -unsigned long vmem_altmap_offset(struct vmem_altmap *altmap); -void vmem_altmap_free(struct vmem_altmap *altmap, unsigned long nr_pfns); - #ifdef CONFIG_ZONE_DEVICE struct vmem_altmap *to_vmem_altmap(unsigned long memmap_start); #else @@ -138,6 +135,9 @@ void *devm_memremap_pages(struct device *dev, struct resource *res, struct percpu_ref *ref, struct vmem_altmap *altmap); struct dev_pagemap *find_dev_pagemap(resource_size_t phys); +unsigned long vmem_altmap_offset(struct vmem_altmap *altmap); +void vmem_altmap_free(struct vmem_altmap *altmap, unsigned long nr_pfns); + static inline bool is_zone_device_page(const struct page *page); #else static inline void *devm_memremap_pages(struct device *dev, @@ -157,7 +157,17 @@ static inline struct dev_pagemap *find_dev_pagemap(resource_size_t phys) { return NULL; } -#endif + +static inline unsigned long vmem_altmap_offset(struct vmem_altmap *altmap) +{ + return 0; +} + +static inline void vmem_altmap_free(struct vmem_altmap *altmap, + unsigned long nr_pfns) +{ +} +#endif /* CONFIG_ZONE_DEVICE */ #if defined(CONFIG_DEVICE_PRIVATE) || defined(CONFIG_DEVICE_PUBLIC) static inline bool is_device_private_page(const struct page *page) -- cgit v1.2.3 From 24e6d5a59ac7d31adc0322de2d0117dfa370936f Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 29 Dec 2017 08:53:53 +0100 Subject: mm: pass the vmem_altmap to arch_add_memory and __add_pages We can just pass this on instead of having to do a radix tree lookup without proper locking 2 levels into the callchain. Signed-off-by: Christoph Hellwig Signed-off-by: Dan Williams --- include/linux/memory_hotplug.h | 17 ++++++++++------- 1 file changed, 10 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 58e110aee7ab..db276afbefcc 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -13,6 +13,7 @@ struct pglist_data; struct mem_section; struct memory_block; struct resource; +struct vmem_altmap; #ifdef CONFIG_MEMORY_HOTPLUG /* @@ -131,18 +132,19 @@ extern int __remove_pages(struct zone *zone, unsigned long start_pfn, #endif /* CONFIG_MEMORY_HOTREMOVE */ /* reasonably generic interface to expand the physical pages */ -extern int __add_pages(int nid, unsigned long start_pfn, - unsigned long nr_pages, bool want_memblock); +extern int __add_pages(int nid, unsigned long start_pfn, unsigned long nr_pages, + struct vmem_altmap *altmap, bool want_memblock); #ifndef CONFIG_ARCH_HAS_ADD_PAGES static inline int add_pages(int nid, unsigned long start_pfn, - unsigned long nr_pages, bool want_memblock) + unsigned long nr_pages, struct vmem_altmap *altmap, + bool want_memblock) { - return __add_pages(nid, start_pfn, nr_pages, want_memblock); + return __add_pages(nid, start_pfn, nr_pages, altmap, want_memblock); } #else /* ARCH_HAS_ADD_PAGES */ -int add_pages(int nid, unsigned long start_pfn, - unsigned long nr_pages, bool want_memblock); +int add_pages(int nid, unsigned long start_pfn, unsigned long nr_pages, + struct vmem_altmap *altmap, bool want_memblock); #endif /* ARCH_HAS_ADD_PAGES */ #ifdef CONFIG_NUMA @@ -318,7 +320,8 @@ extern int walk_memory_range(unsigned long start_pfn, unsigned long end_pfn, void *arg, int (*func)(struct memory_block *, void *)); extern int add_memory(int nid, u64 start, u64 size); extern int add_memory_resource(int nid, struct resource *resource, bool online); -extern int arch_add_memory(int nid, u64 start, u64 size, bool want_memblock); +extern int arch_add_memory(int nid, u64 start, u64 size, + struct vmem_altmap *altmap, bool want_memblock); extern void move_pfn_range_to_zone(struct zone *zone, unsigned long start_pfn, unsigned long nr_pages); extern int offline_pages(unsigned long start_pfn, unsigned long nr_pages); -- cgit v1.2.3 From 7b73d978a5d0d2a3637bdd57191cb6ffbad3feca Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 29 Dec 2017 08:53:54 +0100 Subject: mm: pass the vmem_altmap to vmemmap_populate We can just pass this on instead of having to do a radix tree lookup without proper locking a few levels into the callchain. Signed-off-by: Christoph Hellwig Signed-off-by: Dan Williams --- include/linux/memory_hotplug.h | 3 ++- include/linux/mm.h | 6 ++++-- 2 files changed, 6 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index db276afbefcc..cbdd6d52e877 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -327,7 +327,8 @@ extern void move_pfn_range_to_zone(struct zone *zone, unsigned long start_pfn, extern int offline_pages(unsigned long start_pfn, unsigned long nr_pages); extern bool is_memblock_offlined(struct memory_block *mem); extern void remove_memory(int nid, u64 start, u64 size); -extern int sparse_add_one_section(struct pglist_data *pgdat, unsigned long start_pfn); +extern int sparse_add_one_section(struct pglist_data *pgdat, + unsigned long start_pfn, struct vmem_altmap *altmap); extern void sparse_remove_one_section(struct zone *zone, struct mem_section *ms, unsigned long map_offset); extern struct page *sparse_decode_mem_map(unsigned long coded_mem_map, diff --git a/include/linux/mm.h b/include/linux/mm.h index ea818ff739cd..2f3a7ebecbe2 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2538,7 +2538,8 @@ void sparse_mem_maps_populate_node(struct page **map_map, unsigned long map_count, int nodeid); -struct page *sparse_mem_map_populate(unsigned long pnum, int nid); +struct page *sparse_mem_map_populate(unsigned long pnum, int nid, + struct vmem_altmap *altmap); pgd_t *vmemmap_pgd_populate(unsigned long addr, int node); p4d_t *vmemmap_p4d_populate(pgd_t *pgd, unsigned long addr, int node); pud_t *vmemmap_pud_populate(p4d_t *p4d, unsigned long addr, int node); @@ -2556,7 +2557,8 @@ static inline void *vmemmap_alloc_block_buf(unsigned long size, int node) void vmemmap_verify(pte_t *, int, unsigned long, unsigned long); int vmemmap_populate_basepages(unsigned long start, unsigned long end, int node); -int vmemmap_populate(unsigned long start, unsigned long end, int node); +int vmemmap_populate(unsigned long start, unsigned long end, int node, + struct vmem_altmap *altmap); void vmemmap_populate_print_last(void); #ifdef CONFIG_MEMORY_HOTPLUG void vmemmap_free(unsigned long start, unsigned long end); -- cgit v1.2.3 From da024512a1fa5c979257e442130ee1d468285057 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 29 Dec 2017 08:53:55 +0100 Subject: mm: pass the vmem_altmap to arch_remove_memory and __remove_pages We can just pass this on instead of having to do a radix tree lookup without proper locking 2 levels into the callchain. Signed-off-by: Christoph Hellwig Signed-off-by: Dan Williams --- include/linux/memory_hotplug.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index cbdd6d52e877..e71927d0d46b 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -126,9 +126,10 @@ static inline bool movable_node_is_enabled(void) #ifdef CONFIG_MEMORY_HOTREMOVE extern bool is_pageblock_removable_nolock(struct page *page); -extern int arch_remove_memory(u64 start, u64 size); +extern int arch_remove_memory(u64 start, u64 size, + struct vmem_altmap *altmap); extern int __remove_pages(struct zone *zone, unsigned long start_pfn, - unsigned long nr_pages); + unsigned long nr_pages, struct vmem_altmap *altmap); #endif /* CONFIG_MEMORY_HOTREMOVE */ /* reasonably generic interface to expand the physical pages */ -- cgit v1.2.3 From 24b6d4164348370c6b6a58b4248babd85ff9e982 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 29 Dec 2017 08:53:56 +0100 Subject: mm: pass the vmem_altmap to vmemmap_free We can just pass this on instead of having to do a radix tree lookup without proper locking a few levels into the callchain. Signed-off-by: Christoph Hellwig Signed-off-by: Dan Williams --- include/linux/memory_hotplug.h | 2 +- include/linux/mm.h | 3 ++- 2 files changed, 3 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index e71927d0d46b..20dd98ad44a0 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -331,7 +331,7 @@ extern void remove_memory(int nid, u64 start, u64 size); extern int sparse_add_one_section(struct pglist_data *pgdat, unsigned long start_pfn, struct vmem_altmap *altmap); extern void sparse_remove_one_section(struct zone *zone, struct mem_section *ms, - unsigned long map_offset); + unsigned long map_offset, struct vmem_altmap *altmap); extern struct page *sparse_decode_mem_map(unsigned long coded_mem_map, unsigned long pnum); extern bool allow_online_pfn_range(int nid, unsigned long pfn, unsigned long nr_pages, diff --git a/include/linux/mm.h b/include/linux/mm.h index 2f3a7ebecbe2..9d4cd4c1dc6d 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2561,7 +2561,8 @@ int vmemmap_populate(unsigned long start, unsigned long end, int node, struct vmem_altmap *altmap); void vmemmap_populate_print_last(void); #ifdef CONFIG_MEMORY_HOTPLUG -void vmemmap_free(unsigned long start, unsigned long end); +void vmemmap_free(unsigned long start, unsigned long end, + struct vmem_altmap *altmap); #endif void register_page_bootmem_memmap(unsigned long section_nr, struct page *map, unsigned long nr_pages); -- cgit v1.2.3 From a99583e780c751003ac9c0105eec9a3b23ec3bc4 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 29 Dec 2017 08:53:57 +0100 Subject: mm: pass the vmem_altmap to memmap_init_zone Pass the vmem_altmap two levels down instead of needing a lookup. Signed-off-by: Christoph Hellwig Signed-off-by: Dan Williams --- include/linux/memory_hotplug.h | 2 +- include/linux/mm.h | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 20dd98ad44a0..aba5f86eb038 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -324,7 +324,7 @@ extern int add_memory_resource(int nid, struct resource *resource, bool online); extern int arch_add_memory(int nid, u64 start, u64 size, struct vmem_altmap *altmap, bool want_memblock); extern void move_pfn_range_to_zone(struct zone *zone, unsigned long start_pfn, - unsigned long nr_pages); + unsigned long nr_pages, struct vmem_altmap *altmap); extern int offline_pages(unsigned long start_pfn, unsigned long nr_pages); extern bool is_memblock_offlined(struct memory_block *mem); extern void remove_memory(int nid, u64 start, u64 size); diff --git a/include/linux/mm.h b/include/linux/mm.h index 9d4cd4c1dc6d..fd01135324b6 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2069,8 +2069,8 @@ static inline void zero_resv_unavail(void) {} #endif extern void set_dma_reserve(unsigned long new_dma_reserve); -extern void memmap_init_zone(unsigned long, int, unsigned long, - unsigned long, enum memmap_context); +extern void memmap_init_zone(unsigned long, int, unsigned long, unsigned long, + enum memmap_context, struct vmem_altmap *); extern void setup_per_zone_wmarks(void); extern int __meminit init_per_zone_wmark_min(void); extern void mem_init(void); -- cgit v1.2.3 From a8fc357b2875da8732c91eb085862a0648d82767 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 29 Dec 2017 08:53:58 +0100 Subject: mm: split altmap memory map allocation from normal case No functional changes, just untangling the call chain and document why the altmap is passed around the hotplug code. Signed-off-by: Christoph Hellwig Reviewed-by: Logan Gunthorpe Signed-off-by: Dan Williams --- include/linux/mm.h | 9 ++------- 1 file changed, 2 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index fd01135324b6..09637c353de0 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2547,13 +2547,8 @@ pmd_t *vmemmap_pmd_populate(pud_t *pud, unsigned long addr, int node); pte_t *vmemmap_pte_populate(pmd_t *pmd, unsigned long addr, int node); void *vmemmap_alloc_block(unsigned long size, int node); struct vmem_altmap; -void *__vmemmap_alloc_block_buf(unsigned long size, int node, - struct vmem_altmap *altmap); -static inline void *vmemmap_alloc_block_buf(unsigned long size, int node) -{ - return __vmemmap_alloc_block_buf(size, node, NULL); -} - +void *vmemmap_alloc_block_buf(unsigned long size, int node); +void *altmap_alloc_block_buf(unsigned long size, struct vmem_altmap *altmap); void vmemmap_verify(pte_t *, int, unsigned long, unsigned long); int vmemmap_populate_basepages(unsigned long start, unsigned long end, int node); -- cgit v1.2.3 From 0822acb86cf340cd45b3af6436cec7e3bb24ebd2 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 29 Dec 2017 08:54:00 +0100 Subject: mm: move get_dev_pagemap out of line MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This is a pretty big function, which should be out of line in general, and a no-op stub if CONFIG_ZONE_DEVICЕ is not set. Signed-off-by: Christoph Hellwig Reviewed-by: Logan Gunthorpe Signed-off-by: Dan Williams --- include/linux/memremap.h | 39 ++++----------------------------------- 1 file changed, 4 insertions(+), 35 deletions(-) (limited to 'include') diff --git a/include/linux/memremap.h b/include/linux/memremap.h index d5a6736d9737..26e8aaba27d5 100644 --- a/include/linux/memremap.h +++ b/include/linux/memremap.h @@ -133,7 +133,8 @@ struct dev_pagemap { #ifdef CONFIG_ZONE_DEVICE void *devm_memremap_pages(struct device *dev, struct resource *res, struct percpu_ref *ref, struct vmem_altmap *altmap); -struct dev_pagemap *find_dev_pagemap(resource_size_t phys); +struct dev_pagemap *get_dev_pagemap(unsigned long pfn, + struct dev_pagemap *pgmap); unsigned long vmem_altmap_offset(struct vmem_altmap *altmap); void vmem_altmap_free(struct vmem_altmap *altmap, unsigned long nr_pfns); @@ -153,7 +154,8 @@ static inline void *devm_memremap_pages(struct device *dev, return ERR_PTR(-ENXIO); } -static inline struct dev_pagemap *find_dev_pagemap(resource_size_t phys) +static inline struct dev_pagemap *get_dev_pagemap(unsigned long pfn, + struct dev_pagemap *pgmap) { return NULL; } @@ -183,39 +185,6 @@ static inline bool is_device_public_page(const struct page *page) } #endif /* CONFIG_DEVICE_PRIVATE || CONFIG_DEVICE_PUBLIC */ -/** - * get_dev_pagemap() - take a new live reference on the dev_pagemap for @pfn - * @pfn: page frame number to lookup page_map - * @pgmap: optional known pgmap that already has a reference - * - * @pgmap allows the overhead of a lookup to be bypassed when @pfn lands in the - * same mapping. - */ -static inline struct dev_pagemap *get_dev_pagemap(unsigned long pfn, - struct dev_pagemap *pgmap) -{ - const struct resource *res = pgmap ? pgmap->res : NULL; - resource_size_t phys = PFN_PHYS(pfn); - - /* - * In the cached case we're already holding a live reference so - * we can simply do a blind increment - */ - if (res && phys >= res->start && phys <= res->end) { - percpu_ref_get(pgmap->ref); - return pgmap; - } - - /* fall back to slow path lookup */ - rcu_read_lock(); - pgmap = find_dev_pagemap(phys); - if (pgmap && !percpu_ref_tryget_live(pgmap->ref)) - pgmap = NULL; - rcu_read_unlock(); - - return pgmap; -} - static inline void put_dev_pagemap(struct dev_pagemap *pgmap) { if (pgmap) -- cgit v1.2.3 From 0628b8c650718f4dfedfcdc9ed136bf7e394aae7 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 29 Dec 2017 08:54:02 +0100 Subject: memremap: remove to_vmem_altmap All callers are gone now. Signed-off-by: Christoph Hellwig Signed-off-by: Dan Williams --- include/linux/memremap.h | 9 --------- 1 file changed, 9 deletions(-) (limited to 'include') diff --git a/include/linux/memremap.h b/include/linux/memremap.h index 26e8aaba27d5..3fddcfe57bb0 100644 --- a/include/linux/memremap.h +++ b/include/linux/memremap.h @@ -26,15 +26,6 @@ struct vmem_altmap { unsigned long alloc; }; -#ifdef CONFIG_ZONE_DEVICE -struct vmem_altmap *to_vmem_altmap(unsigned long memmap_start); -#else -static inline struct vmem_altmap *to_vmem_altmap(unsigned long memmap_start) -{ - return NULL; -} -#endif - /* * Specialize ZONE_DEVICE memory into multiple types each having differents * usage. -- cgit v1.2.3 From e7744aa25cffe26d3767c9ffcf4e130cca1dff00 Mon Sep 17 00:00:00 2001 From: Logan Gunthorpe Date: Fri, 29 Dec 2017 08:54:04 +0100 Subject: memremap: drop private struct page_map 'struct page_map' is a private structure of 'struct dev_pagemap' but the latter replicates all the same fields as the former so there isn't much value in it. Thus drop it in favour of a completely public struct. This is a clean up in preperation for a more generally useful 'devm_memeremap_pages' interface. Signed-off-by: Logan Gunthorpe Signed-off-by: Christoph Hellwig Signed-off-by: Dan Williams --- include/linux/memremap.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/memremap.h b/include/linux/memremap.h index 3fddcfe57bb0..1cb5f39d25c1 100644 --- a/include/linux/memremap.h +++ b/include/linux/memremap.h @@ -113,8 +113,9 @@ typedef void (*dev_page_free_t)(struct page *page, void *data); struct dev_pagemap { dev_page_fault_t page_fault; dev_page_free_t page_free; - struct vmem_altmap *altmap; - const struct resource *res; + struct vmem_altmap altmap; + bool altmap_valid; + struct resource res; struct percpu_ref *ref; struct device *dev; void *data; -- cgit v1.2.3 From e8d5134833006a46fcbefc5f4a84d0b62bd520e7 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 29 Dec 2017 08:54:05 +0100 Subject: memremap: change devm_memremap_pages interface to use struct dev_pagemap This new interface is similar to how struct device (and many others) work. The caller initializes a 'struct dev_pagemap' as required and calls 'devm_memremap_pages'. This allows the pagemap structure to be embedded in another structure and thus container_of can be used. In this way application specific members can be stored in a containing struct. This will be used by the P2P infrastructure and HMM could probably be cleaned up to use it as well (instead of having it's own, similar 'hmm_devmem_pages_create' function). Signed-off-by: Logan Gunthorpe Signed-off-by: Christoph Hellwig Signed-off-by: Dan Williams --- include/linux/memremap.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/memremap.h b/include/linux/memremap.h index 1cb5f39d25c1..7b4899c06f49 100644 --- a/include/linux/memremap.h +++ b/include/linux/memremap.h @@ -123,8 +123,7 @@ struct dev_pagemap { }; #ifdef CONFIG_ZONE_DEVICE -void *devm_memremap_pages(struct device *dev, struct resource *res, - struct percpu_ref *ref, struct vmem_altmap *altmap); +void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap); struct dev_pagemap *get_dev_pagemap(unsigned long pfn, struct dev_pagemap *pgmap); @@ -134,8 +133,7 @@ void vmem_altmap_free(struct vmem_altmap *altmap, unsigned long nr_pfns); static inline bool is_zone_device_page(const struct page *page); #else static inline void *devm_memremap_pages(struct device *dev, - struct resource *res, struct percpu_ref *ref, - struct vmem_altmap *altmap) + struct dev_pagemap *pgmap) { /* * Fail attempts to call devm_memremap_pages() without -- cgit v1.2.3 From 785a3fab4adbf91b2189c928a59ae219c54ba95e Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Mon, 23 Oct 2017 07:20:00 -0700 Subject: mm, dax: introduce pfn_t_special() In support of removing the VM_MIXEDMAP indication from DAX VMAs, introduce pfn_t_special() for drivers to indicate that _PAGE_SPECIAL should be used for DAX ptes. This also helps identify drivers like dccssblk that only want to use DAX in a read-only fashion without get_user_pages() support. Ideally we could delete axonram and dcssblk DAX support, but if we need to keep it better make it explicit that axonram and dcssblk only support a sub-set of DAX due to missing _PAGE_DEVMAP support. Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Michael Ellerman Cc: Martin Schwidefsky Cc: Heiko Carstens Signed-off-by: Dan Williams --- include/linux/pfn_t.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include') diff --git a/include/linux/pfn_t.h b/include/linux/pfn_t.h index 43b1d7648e82..a03c2642a87c 100644 --- a/include/linux/pfn_t.h +++ b/include/linux/pfn_t.h @@ -15,8 +15,10 @@ #define PFN_SG_LAST (1ULL << (BITS_PER_LONG_LONG - 2)) #define PFN_DEV (1ULL << (BITS_PER_LONG_LONG - 3)) #define PFN_MAP (1ULL << (BITS_PER_LONG_LONG - 4)) +#define PFN_SPECIAL (1ULL << (BITS_PER_LONG_LONG - 5)) #define PFN_FLAGS_TRACE \ + { PFN_SPECIAL, "SPECIAL" }, \ { PFN_SG_CHAIN, "SG_CHAIN" }, \ { PFN_SG_LAST, "SG_LAST" }, \ { PFN_DEV, "DEV" }, \ @@ -120,4 +122,15 @@ pud_t pud_mkdevmap(pud_t pud); #endif #endif /* __HAVE_ARCH_PTE_DEVMAP */ +#ifdef __HAVE_ARCH_PTE_SPECIAL +static inline bool pfn_t_special(pfn_t pfn) +{ + return (pfn.val & PFN_SPECIAL) == PFN_SPECIAL; +} +#else +static inline bool pfn_t_special(pfn_t pfn) +{ + return false; +} +#endif /* __HAVE_ARCH_PTE_SPECIAL */ #endif /* _LINUX_PFN_T_H_ */ -- cgit v1.2.3 From 06e8ccdab15f46dfd31292e2b75d744bc5fc2a7c Mon Sep 17 00:00:00 2001 From: Dave Jiang Date: Wed, 31 Jan 2018 12:45:38 -0700 Subject: acpi: nfit: Add support for detect platform CPU cache flush on power loss In ACPI 6.2a the platform capability structure has been added to the NFIT tables. That provides software the ability to determine whether a system supports the auto flushing of CPU caches on power loss. If the capability is supported, we do not need to do dax_flush(). Plumbing the path to set the property on per region from the NFIT tables. This patch depends on the ACPI NFIT 6.2a platform capabilities support code in include/acpi/actbl1.h. Signed-off-by: Dave Jiang Reviewed-by: Ross Zwisler Signed-off-by: Ross Zwisler --- include/linux/libnvdimm.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/libnvdimm.h b/include/linux/libnvdimm.h index f8109ddb5ef1..f2fc0da4da04 100644 --- a/include/linux/libnvdimm.h +++ b/include/linux/libnvdimm.h @@ -47,6 +47,11 @@ enum { /* region flag indicating to direct-map persistent memory by default */ ND_REGION_PAGEMAP = 0, + /* + * Platform ensures entire CPU store data path is flushed to pmem on + * system power loss. + */ + ND_REGION_PERSIST_CACHE = 1, /* mark newly adjusted resources as requiring a label update */ DPA_RESOURCE_ADJUSTED = 1 << 0, -- cgit v1.2.3 From 30e6d7bf29daa79d80711d35211c9b60894dbc44 Mon Sep 17 00:00:00 2001 From: Dave Jiang Date: Wed, 31 Jan 2018 12:45:43 -0700 Subject: acpi: nfit: add persistent memory control flag for nd_region Propagate the ADR attribute flag from the NFIT platform capabilities sub-table to nd_region. Signed-off-by: Dave Jiang Reviewed-by: Ross Zwisler Signed-off-by: Ross Zwisler --- include/linux/libnvdimm.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/libnvdimm.h b/include/linux/libnvdimm.h index f2fc0da4da04..ff855ed965fb 100644 --- a/include/linux/libnvdimm.h +++ b/include/linux/libnvdimm.h @@ -52,6 +52,12 @@ enum { * system power loss. */ ND_REGION_PERSIST_CACHE = 1, + /* + * Platform provides mechanisms to automatically flush outstanding + * write data from memory controler to pmem on system power loss. + * (ADR) + */ + ND_REGION_PERSIST_MEMCTRL = 2, /* mark newly adjusted resources as requiring a label update */ DPA_RESOURCE_ADJUSTED = 1 << 0, -- cgit v1.2.3 From f2ba5a5baecf795c2150826bd0c95fc3f7f3d226 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Thu, 1 Feb 2018 21:27:22 -0800 Subject: libnvdimm, namespace: make min namespace size 4K The arbitrary 4MB minimum namespace size turns out to be too large for some environments. Quoting Cheng-mean Liu: In the case of emulated NVDIMM devices in the VM environment, there are scenarios that NVDIMM device with much smaller sizes are desired, for example, we might use a single enumerated NVDIMM DAX device for representing each container layer, which in some cases could be just a few KBs size. PAGE_SIZE is the minimum where we can still support DAX of at least a single page. Cc: Matthew Wilcox Reported-by: Cheng-mean Liu Signed-off-by: Dan Williams --- include/uapi/linux/ndctl.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/ndctl.h b/include/uapi/linux/ndctl.h index 30ef1236aafa..7e27070b9440 100644 --- a/include/uapi/linux/ndctl.h +++ b/include/uapi/linux/ndctl.h @@ -209,7 +209,7 @@ enum nd_driver_flags { }; enum { - ND_MIN_NAMESPACE_SIZE = 0x00400000, + ND_MIN_NAMESPACE_SIZE = PAGE_SIZE, }; enum ars_masks { -- cgit v1.2.3