From 07ec38917e68f0114b9c8aeeb1c584b5e73e4dd6 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 26 Jun 2019 14:27:01 +0200 Subject: mm: remove the struct hmm_device infrastructure This code is a trivial wrapper around device model helpers, which should have been integrated into the driver device model usage from the start. Assuming it actually had users, which it never had since the code was added more than 1 1/2 years ago. Signed-off-by: Christoph Hellwig Reviewed-by: Jason Gunthorpe Reviewed-by: John Hubbard Reviewed-by: Dan Williams Signed-off-by: Jason Gunthorpe --- include/linux/hmm.h | 20 -------------------- 1 file changed, 20 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hmm.h b/include/linux/hmm.h index 044a36d7c3f8..99765be3284d 100644 --- a/include/linux/hmm.h +++ b/include/linux/hmm.h @@ -751,26 +751,6 @@ static inline unsigned long hmm_devmem_page_get_drvdata(const struct page *page) { return page->hmm_data; } - - -/* - * struct hmm_device - fake device to hang device memory onto - * - * @device: device struct - * @minor: device minor number - */ -struct hmm_device { - struct device device; - unsigned int minor; -}; - -/* - * A device driver that wants to handle multiple devices memory through a - * single fake device can use hmm_device to do so. This is purely a helper and - * it is not strictly needed, in order to make use of any HMM functionality. - */ -struct hmm_device *hmm_device_new(void *drvdata); -void hmm_device_put(struct hmm_device *hmm_device); #endif /* CONFIG_DEVICE_PRIVATE || CONFIG_DEVICE_PUBLIC */ #else /* IS_ENABLED(CONFIG_HMM) */ static inline void hmm_mm_destroy(struct mm_struct *mm) {} -- cgit v1.2.3 From 25b2995a35b609119cf96f6b62eccd56c0234c7d Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 13 Jun 2019 22:50:49 +0200 Subject: mm: remove MEMORY_DEVICE_PUBLIC support The code hasn't been used since it was added to the tree, and doesn't appear to actually be usable. Signed-off-by: Christoph Hellwig Reviewed-by: Jason Gunthorpe Acked-by: Michal Hocko Reviewed-by: Dan Williams Tested-by: Dan Williams Signed-off-by: Jason Gunthorpe --- include/linux/hmm.h | 7 ++----- include/linux/ioport.h | 1 - include/linux/memremap.h | 8 -------- include/linux/mm.h | 18 ++---------------- 4 files changed, 4 insertions(+), 30 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hmm.h b/include/linux/hmm.h index 99765be3284d..44a5ac738bb5 100644 --- a/include/linux/hmm.h +++ b/include/linux/hmm.h @@ -584,7 +584,7 @@ static inline void hmm_mm_destroy(struct mm_struct *mm) {} static inline void hmm_mm_init(struct mm_struct *mm) {} #endif /* IS_ENABLED(CONFIG_HMM_MIRROR) */ -#if IS_ENABLED(CONFIG_DEVICE_PRIVATE) || IS_ENABLED(CONFIG_DEVICE_PUBLIC) +#if IS_ENABLED(CONFIG_DEVICE_PRIVATE) struct hmm_devmem; struct page *hmm_vma_alloc_locked_page(struct vm_area_struct *vma, @@ -722,9 +722,6 @@ struct hmm_devmem { struct hmm_devmem *hmm_devmem_add(const struct hmm_devmem_ops *ops, struct device *device, unsigned long size); -struct hmm_devmem *hmm_devmem_add_resource(const struct hmm_devmem_ops *ops, - struct device *device, - struct resource *res); /* * hmm_devmem_page_set_drvdata - set per-page driver data field @@ -751,7 +748,7 @@ static inline unsigned long hmm_devmem_page_get_drvdata(const struct page *page) { return page->hmm_data; } -#endif /* CONFIG_DEVICE_PRIVATE || CONFIG_DEVICE_PUBLIC */ +#endif /* CONFIG_DEVICE_PRIVATE */ #else /* IS_ENABLED(CONFIG_HMM) */ static inline void hmm_mm_destroy(struct mm_struct *mm) {} static inline void hmm_mm_init(struct mm_struct *mm) {} diff --git a/include/linux/ioport.h b/include/linux/ioport.h index da0ebaec25f0..dd961882bc74 100644 --- a/include/linux/ioport.h +++ b/include/linux/ioport.h @@ -132,7 +132,6 @@ enum { IORES_DESC_PERSISTENT_MEMORY = 4, IORES_DESC_PERSISTENT_MEMORY_LEGACY = 5, IORES_DESC_DEVICE_PRIVATE_MEMORY = 6, - IORES_DESC_DEVICE_PUBLIC_MEMORY = 7, }; /* helpers to define resources */ diff --git a/include/linux/memremap.h b/include/linux/memremap.h index 1732dea030b2..995c62c5a48b 100644 --- a/include/linux/memremap.h +++ b/include/linux/memremap.h @@ -37,13 +37,6 @@ struct vmem_altmap { * A more complete discussion of unaddressable memory may be found in * include/linux/hmm.h and Documentation/vm/hmm.rst. * - * MEMORY_DEVICE_PUBLIC: - * Device memory that is cache coherent from device and CPU point of view. This - * is use on platform 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_DEVICE_PCI_P2PDMA, }; diff --git a/include/linux/mm.h b/include/linux/mm.h index dd0b5f4e1e45..7399f9f08de6 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -944,7 +944,6 @@ static inline bool put_devmap_managed_page(struct page *page) return false; switch (page->pgmap->type) { case MEMORY_DEVICE_PRIVATE: - case MEMORY_DEVICE_PUBLIC: case MEMORY_DEVICE_FS_DAX: __put_devmap_managed_page(page); return true; @@ -960,12 +959,6 @@ static inline bool is_device_private_page(const struct page *page) page->pgmap->type == MEMORY_DEVICE_PRIVATE; } -static inline bool is_device_public_page(const struct page *page) -{ - return is_zone_device_page(page) && - page->pgmap->type == MEMORY_DEVICE_PUBLIC; -} - #ifdef CONFIG_PCI_P2PDMA static inline bool is_pci_p2pdma_page(const struct page *page) { @@ -998,11 +991,6 @@ static inline bool is_device_private_page(const struct page *page) return false; } -static inline bool is_device_public_page(const struct page *page) -{ - return false; -} - static inline bool is_pci_p2pdma_page(const struct page *page) { return false; @@ -1431,10 +1419,8 @@ struct zap_details { pgoff_t last_index; /* Highest page->index to unmap */ }; -struct page *_vm_normal_page(struct vm_area_struct *vma, unsigned long addr, - pte_t pte, bool with_public_device); -#define vm_normal_page(vma, addr, pte) _vm_normal_page(vma, addr, pte, false) - +struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, + pte_t pte); struct page *vm_normal_page_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t pmd); -- cgit v1.2.3 From 0092908d16c604b8207c2141ec64b0fa4473bb03 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 26 Jun 2019 14:27:06 +0200 Subject: mm: factor out a devm_request_free_mem_region helper Keep the physical address allocation that hmm_add_device does with the rest of the resource code, and allow future reuse of it without the hmm wrapper. Signed-off-by: Christoph Hellwig Reviewed-by: Jason Gunthorpe Reviewed-by: John Hubbard Reviewed-by: Dan Williams Signed-off-by: Jason Gunthorpe --- include/linux/ioport.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ioport.h b/include/linux/ioport.h index dd961882bc74..a02b290ca08a 100644 --- a/include/linux/ioport.h +++ b/include/linux/ioport.h @@ -285,6 +285,8 @@ static inline bool resource_overlaps(struct resource *r1, struct resource *r2) return (r1->start <= r2->end && r1->end >= r2->start); } +struct resource *devm_request_free_mem_region(struct device *dev, + struct resource *base, unsigned long size); #endif /* __ASSEMBLY__ */ #endif /* _LINUX_IOPORT_H */ -- cgit v1.2.3 From 3ed2dcdf54d5bf1f9823b5faf1a702e7cee53982 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 26 Jun 2019 14:27:07 +0200 Subject: memremap: validate the pagemap type passed to devm_memremap_pages Most pgmap types are only supported when certain config options are enabled. Check for a type that is valid for the current configuration before setting up the pagemap. For this the usage of the 0 type for device dax gets replaced with an explicit MEMORY_DEVICE_DEVDAX type. Signed-off-by: Christoph Hellwig Reviewed-by: Ira Weiny Reviewed-by: Dan Williams Tested-by: Dan Williams Signed-off-by: Jason Gunthorpe --- include/linux/memremap.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/memremap.h b/include/linux/memremap.h index 995c62c5a48b..0c86f2c5ac9c 100644 --- a/include/linux/memremap.h +++ b/include/linux/memremap.h @@ -45,13 +45,21 @@ struct vmem_altmap { * 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, MEMORY_DEVICE_FS_DAX, + MEMORY_DEVICE_DEVDAX, MEMORY_DEVICE_PCI_P2PDMA, }; -- cgit v1.2.3 From 1e240e8d4a7d92232b6214e02a0a4197a53afd6c Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 26 Jun 2019 14:27:08 +0200 Subject: memremap: move dev_pagemap callbacks into a separate structure The dev_pagemap is a growing too many callbacks. Move them into a separate ops structure so that they are not duplicated for multiple instances, and an attacker can't easily overwrite them. Signed-off-by: Christoph Hellwig Reviewed-by: Logan Gunthorpe Reviewed-by: Jason Gunthorpe Reviewed-by: Dan Williams Tested-by: Dan Williams Signed-off-by: Jason Gunthorpe --- include/linux/memremap.h | 36 ++++++++++++++++++++---------------- 1 file changed, 20 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memremap.h b/include/linux/memremap.h index 0c86f2c5ac9c..919755f48c7e 100644 --- a/include/linux/memremap.h +++ b/include/linux/memremap.h @@ -63,41 +63,45 @@ enum memory_type { MEMORY_DEVICE_PCI_P2PDMA, }; -/* - * Additional notes about MEMORY_DEVICE_PRIVATE may be found in - * include/linux/hmm.h and Documentation/vm/hmm.rst. There is also a brief - * explanation in include/linux/memory_hotplug.h. - * - * The page_free() callback is called once the page refcount reaches 1 - * (ZONE_DEVICE pages never reach 0 refcount unless there is a refcount bug. - * This allows the device driver to implement its own memory management.) - */ -typedef void (*dev_page_free_t)(struct page *page, void *data); +struct dev_pagemap_ops { + /* + * Called once the page refcount reaches 1. (ZONE_DEVICE pages never + * reach 0 refcount unless there is a refcount bug. This allows the + * device driver to implement its own memory management.) + */ + void (*page_free)(struct page *page, void *data); + + /* + * Transition the refcount in struct dev_pagemap to the dead state. + */ + void (*kill)(struct percpu_ref *ref); + + /* + * Wait for refcount in struct dev_pagemap to be idle and reap it. + */ + void (*cleanup)(struct percpu_ref *ref); +}; /** * struct dev_pagemap - metadata for ZONE_DEVICE mappings - * @page_free: free page callback when page refcount reaches 1 * @altmap: pre-allocated/reserved memory for vmemmap allocations * @res: physical address range covered by @ref * @ref: reference count that pins the devm_memremap_pages() mapping - * @kill: callback to transition @ref to the dead state - * @cleanup: callback to wait for @ref to be idle and reap it * @dev: host device of the mapping for debug * @data: private data pointer for page_free() * @type: memory type: see MEMORY_* in memory_hotplug.h + * @ops: method table */ struct dev_pagemap { - dev_page_free_t page_free; struct vmem_altmap altmap; bool altmap_valid; struct resource res; struct percpu_ref *ref; - void (*kill)(struct percpu_ref *ref); - void (*cleanup)(struct percpu_ref *ref); struct device *dev; void *data; enum memory_type type; u64 pci_p2pdma_bus_offset; + const struct dev_pagemap_ops *ops; }; #ifdef CONFIG_ZONE_DEVICE -- cgit v1.2.3 From d8668bb0451c3c45b59dbcde2654e0539aad1d2a Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 26 Jun 2019 14:27:09 +0200 Subject: memremap: pass a struct dev_pagemap to ->kill and ->cleanup Passing the actual typed structure leads to more understandable code vs just passing the ref member. Reported-by: Logan Gunthorpe Signed-off-by: Christoph Hellwig Reviewed-by: Logan Gunthorpe Reviewed-by: Jason Gunthorpe Reviewed-by: Dan Williams Tested-by: Dan Williams Signed-off-by: Jason Gunthorpe --- include/linux/memremap.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memremap.h b/include/linux/memremap.h index 919755f48c7e..b8666a0d8665 100644 --- a/include/linux/memremap.h +++ b/include/linux/memremap.h @@ -74,12 +74,12 @@ struct dev_pagemap_ops { /* * Transition the refcount in struct dev_pagemap to the dead state. */ - void (*kill)(struct percpu_ref *ref); + void (*kill)(struct dev_pagemap *pgmap); /* * Wait for refcount in struct dev_pagemap to be idle and reap it. */ - void (*cleanup)(struct percpu_ref *ref); + void (*cleanup)(struct dev_pagemap *pgmap); }; /** -- cgit v1.2.3 From f6a55e1a3fe6b3bb294a80a05437fcf86488d819 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 26 Jun 2019 14:27:10 +0200 Subject: memremap: lift the devmap_enable manipulation into devm_memremap_pages Just check if there is a ->page_free operation set and take care of the static key enable, as well as the put using device managed resources. Also check that a ->page_free is provided for the pgmaps types that require it, and check for a valid type as well while we are at it. Note that this also fixes the fact that hmm never called dev_pagemap_put_ops and thus would leave the slow path enabled forever, even after a device driver unload or disable. Signed-off-by: Christoph Hellwig Reviewed-by: Ira Weiny Reviewed-by: Dan Williams Tested-by: Dan Williams Signed-off-by: Jason Gunthorpe --- include/linux/mm.h | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 7399f9f08de6..2425f4167ec2 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -932,8 +932,6 @@ static inline bool is_zone_device_page(const struct page *page) #endif #ifdef CONFIG_DEV_PAGEMAP_OPS -void dev_pagemap_get_ops(void); -void dev_pagemap_put_ops(void); void __put_devmap_managed_page(struct page *page); DECLARE_STATIC_KEY_FALSE(devmap_managed_key); static inline bool put_devmap_managed_page(struct page *page) @@ -973,14 +971,6 @@ static inline bool is_pci_p2pdma_page(const struct page *page) #endif /* CONFIG_PCI_P2PDMA */ #else /* CONFIG_DEV_PAGEMAP_OPS */ -static inline void dev_pagemap_get_ops(void) -{ -} - -static inline void dev_pagemap_put_ops(void) -{ -} - static inline bool put_devmap_managed_page(struct page *page) { return false; -- cgit v1.2.3 From 897e6365cda6ba6356e83a3aaa68dec82ef4c548 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 26 Jun 2019 14:27:11 +0200 Subject: memremap: add a migrate_to_ram method to struct dev_pagemap_ops This replaces the hacky ->fault callback, which is currently directly called from common code through a hmm specific data structure as an exercise in layering violations. Signed-off-by: Christoph Hellwig Reviewed-by: Ralph Campbell Reviewed-by: Jason Gunthorpe Reviewed-by: Dan Williams Tested-by: Dan Williams Signed-off-by: Jason Gunthorpe --- include/linux/hmm.h | 6 ------ include/linux/memremap.h | 6 ++++++ include/linux/swapops.h | 15 --------------- 3 files changed, 6 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hmm.h b/include/linux/hmm.h index 44a5ac738bb5..ba19c19e24ed 100644 --- a/include/linux/hmm.h +++ b/include/linux/hmm.h @@ -692,11 +692,6 @@ struct hmm_devmem_ops { * chunk, as an optimization. It must, however, prioritize the faulting address * over all the others. */ -typedef vm_fault_t (*dev_page_fault_t)(struct vm_area_struct *vma, - unsigned long addr, - const struct page *page, - unsigned int flags, - pmd_t *pmdp); struct hmm_devmem { struct completion completion; @@ -707,7 +702,6 @@ struct hmm_devmem { struct dev_pagemap pagemap; const struct hmm_devmem_ops *ops; struct percpu_ref ref; - dev_page_fault_t page_fault; }; /* diff --git a/include/linux/memremap.h b/include/linux/memremap.h index b8666a0d8665..ac985bd03a7f 100644 --- a/include/linux/memremap.h +++ b/include/linux/memremap.h @@ -80,6 +80,12 @@ struct dev_pagemap_ops { * Wait for refcount in struct dev_pagemap to be idle and reap it. */ void (*cleanup)(struct dev_pagemap *pgmap); + + /* + * Used for private (un-addressable) device memory only. Must migrate + * the page back to a CPU accessible page. + */ + vm_fault_t (*migrate_to_ram)(struct vm_fault *vmf); }; /** diff --git a/include/linux/swapops.h b/include/linux/swapops.h index 4d961668e5fc..15bdb6fe71e5 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -129,12 +129,6 @@ static inline struct page *device_private_entry_to_page(swp_entry_t entry) { return pfn_to_page(swp_offset(entry)); } - -vm_fault_t device_private_entry_fault(struct vm_area_struct *vma, - unsigned long addr, - swp_entry_t entry, - unsigned int flags, - pmd_t *pmdp); #else /* CONFIG_DEVICE_PRIVATE */ static inline swp_entry_t make_device_private_entry(struct page *page, bool write) { @@ -164,15 +158,6 @@ static inline struct page *device_private_entry_to_page(swp_entry_t entry) { return NULL; } - -static inline vm_fault_t device_private_entry_fault(struct vm_area_struct *vma, - unsigned long addr, - swp_entry_t entry, - unsigned int flags, - pmd_t *pmdp) -{ - return VM_FAULT_SIGBUS; -} #endif /* CONFIG_DEVICE_PRIVATE */ #ifdef CONFIG_MIGRATION -- cgit v1.2.3 From 80a72d0af05ae97a8b106c172e431072ba587492 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 26 Jun 2019 14:27:12 +0200 Subject: memremap: remove the data field in struct dev_pagemap struct dev_pagemap is always embedded into a containing structure, so there is no need to an additional private data field. Signed-off-by: Christoph Hellwig Reviewed-by: Jason Gunthorpe Reviewed-by: Dan Williams Tested-by: Dan Williams Signed-off-by: Jason Gunthorpe --- include/linux/memremap.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memremap.h b/include/linux/memremap.h index ac985bd03a7f..336eca601dad 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 driver to implement its own memory management.) */ - void (*page_free)(struct page *page, void *data); + void (*page_free)(struct page *page); /* * Transition the refcount in struct dev_pagemap to the dead state. @@ -104,7 +104,6 @@ struct dev_pagemap { struct resource res; struct percpu_ref *ref; struct device *dev; - void *data; enum memory_type type; u64 pci_p2pdma_bus_offset; const struct dev_pagemap_ops *ops; -- cgit v1.2.3 From 514caf23a70fd697fa2ece238b2cd8dcc73fb16f Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 26 Jun 2019 14:27:13 +0200 Subject: memremap: replace the altmap_valid field with a PGMAP_ALTMAP_VALID flag Add a flags field to struct dev_pagemap to replace the altmap_valid boolean to be a little more extensible. Also add a pgmap_altmap() helper to find the optional altmap and clean up the code using the altmap using it. Signed-off-by: Christoph Hellwig Reviewed-by: Ira Weiny Reviewed-by: Dan Williams Tested-by: Dan Williams Signed-off-by: Jason Gunthorpe --- include/linux/memremap.h | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/memremap.h b/include/linux/memremap.h index 336eca601dad..e25685b878e9 100644 --- a/include/linux/memremap.h +++ b/include/linux/memremap.h @@ -88,6 +88,8 @@ struct dev_pagemap_ops { vm_fault_t (*migrate_to_ram)(struct vm_fault *vmf); }; +#define PGMAP_ALTMAP_VALID (1 << 0) + /** * struct dev_pagemap - metadata for ZONE_DEVICE mappings * @altmap: pre-allocated/reserved memory for vmemmap allocations @@ -96,19 +98,27 @@ struct dev_pagemap_ops { * @dev: host device of the mapping for debug * @data: private data pointer for page_free() * @type: memory type: see MEMORY_* in memory_hotplug.h + * @flags: PGMAP_* flags to specify defailed behavior * @ops: method table */ struct dev_pagemap { struct vmem_altmap altmap; - bool altmap_valid; struct resource res; struct percpu_ref *ref; struct device *dev; enum memory_type type; + unsigned int flags; u64 pci_p2pdma_bus_offset; const struct dev_pagemap_ops *ops; }; +static inline struct vmem_altmap *pgmap_altmap(struct dev_pagemap *pgmap) +{ + if (pgmap->flags & PGMAP_ALTMAP_VALID) + return &pgmap->altmap; + return NULL; +} + #ifdef CONFIG_ZONE_DEVICE void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap); void devm_memunmap_pages(struct device *dev, struct dev_pagemap *pgmap); -- cgit v1.2.3 From 24917f6b1041a73993178920656e13364f847995 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 26 Jun 2019 14:27:14 +0200 Subject: memremap: provide an optional internal refcount in struct dev_pagemap Provide an internal refcounting logic if no ->ref field is provided in the pagemap passed into devm_memremap_pages so that callers don't have to reinvent it poorly. Signed-off-by: Christoph Hellwig Reviewed-by: Ira Weiny Reviewed-by: Dan Williams Tested-by: Dan Williams Signed-off-by: Jason Gunthorpe --- include/linux/memremap.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/memremap.h b/include/linux/memremap.h index e25685b878e9..f8a5b2a19945 100644 --- a/include/linux/memremap.h +++ b/include/linux/memremap.h @@ -95,6 +95,8 @@ struct dev_pagemap_ops { * @altmap: pre-allocated/reserved memory for vmemmap allocations * @res: physical address range covered by @ref * @ref: reference count that pins the devm_memremap_pages() mapping + * @internal_ref: internal reference if @ref is not provided by the caller + * @done: completion for @internal_ref * @dev: host device of the mapping for debug * @data: private data pointer for page_free() * @type: memory type: see MEMORY_* in memory_hotplug.h @@ -105,6 +107,8 @@ struct dev_pagemap { struct vmem_altmap altmap; struct resource res; struct percpu_ref *ref; + struct percpu_ref internal_ref; + struct completion done; struct device *dev; enum memory_type type; unsigned int flags; -- cgit v1.2.3 From 47e9d836a5e827acdaa5cb6175648fbef15b4e84 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 26 Jun 2019 14:27:19 +0200 Subject: mm: remove hmm_vma_alloc_locked_page The only user of it has just been removed, and there wasn't really any need to wrap a basic memory allocator to start with. Signed-off-by: Christoph Hellwig Reviewed-by: Jason Gunthorpe Reviewed-by: Dan Williams Signed-off-by: Jason Gunthorpe --- include/linux/hmm.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hmm.h b/include/linux/hmm.h index ba19c19e24ed..1d55b7ea2da6 100644 --- a/include/linux/hmm.h +++ b/include/linux/hmm.h @@ -587,9 +587,6 @@ static inline void hmm_mm_init(struct mm_struct *mm) {} #if IS_ENABLED(CONFIG_DEVICE_PRIVATE) struct hmm_devmem; -struct page *hmm_vma_alloc_locked_page(struct vm_area_struct *vma, - unsigned long addr); - /* * struct hmm_devmem_ops - callback for ZONE_DEVICE memory events * -- cgit v1.2.3 From eee3ae41b153e55e25d6cf7bd5b5098ba0afe705 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 26 Jun 2019 14:27:20 +0200 Subject: mm: remove hmm_devmem_add There isn't really much value add in the hmm_devmem_add wrapper and more, as using devm_memremap_pages directly now is just as simple. Signed-off-by: Christoph Hellwig Reviewed-by: Jason Gunthorpe Reviewed-by: Dan Williams Signed-off-by: Jason Gunthorpe --- include/linux/hmm.h | 129 ---------------------------------------------------- 1 file changed, 129 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hmm.h b/include/linux/hmm.h index 1d55b7ea2da6..86aa4ec3404c 100644 --- a/include/linux/hmm.h +++ b/include/linux/hmm.h @@ -585,135 +585,6 @@ static inline void hmm_mm_init(struct mm_struct *mm) {} #endif /* IS_ENABLED(CONFIG_HMM_MIRROR) */ #if IS_ENABLED(CONFIG_DEVICE_PRIVATE) -struct hmm_devmem; - -/* - * struct hmm_devmem_ops - callback for ZONE_DEVICE memory events - * - * @free: call when refcount on page reach 1 and thus is no longer use - * @fault: call when there is a page fault to unaddressable memory - * - * Both callback happens from page_free() and page_fault() callback of struct - * dev_pagemap respectively. See include/linux/memremap.h for more details on - * those. - * - * The hmm_devmem_ops callback are just here to provide a coherent and - * uniq API to device driver and device driver should not register their - * own page_free() or page_fault() but rely on the hmm_devmem_ops call- - * back. - */ -struct hmm_devmem_ops { - /* - * free() - free a device page - * @devmem: device memory structure (see struct hmm_devmem) - * @page: pointer to struct page being freed - * - * Call back occurs whenever a device page refcount reach 1 which - * means that no one is holding any reference on the page anymore - * (ZONE_DEVICE page have an elevated refcount of 1 as default so - * that they are not release to the general page allocator). - * - * Note that callback has exclusive ownership of the page (as no - * one is holding any reference). - */ - void (*free)(struct hmm_devmem *devmem, struct page *page); - /* - * fault() - CPU page fault or get user page (GUP) - * @devmem: device memory structure (see struct hmm_devmem) - * @vma: virtual memory area containing the virtual address - * @addr: virtual address that faulted or for which there is a GUP - * @page: pointer to struct page backing virtual address (unreliable) - * @flags: FAULT_FLAG_* (see include/linux/mm.h) - * @pmdp: page middle directory - * Returns: VM_FAULT_MINOR/MAJOR on success or one of VM_FAULT_ERROR - * on error - * - * The callback occurs whenever there is a CPU page fault or GUP on a - * virtual address. This means that the device driver must migrate the - * page back to regular memory (CPU accessible). - * - * The device driver is free to migrate more than one page from the - * fault() callback as an optimization. However if device decide to - * migrate more than one page it must always priotirize the faulting - * address over the others. - * - * The struct page pointer is only given as an hint to allow quick - * lookup of internal device driver data. A concurrent migration - * might have already free that page and the virtual address might - * not longer be back by it. So it should not be modified by the - * callback. - * - * Note that mmap semaphore is held in read mode at least when this - * callback occurs, hence the vma is valid upon callback entry. - */ - vm_fault_t (*fault)(struct hmm_devmem *devmem, - struct vm_area_struct *vma, - unsigned long addr, - const struct page *page, - unsigned int flags, - pmd_t *pmdp); -}; - -/* - * struct hmm_devmem - track device memory - * - * @completion: completion object for device memory - * @pfn_first: first pfn for this resource (set by hmm_devmem_add()) - * @pfn_last: last pfn for this resource (set by hmm_devmem_add()) - * @resource: IO resource reserved for this chunk of memory - * @pagemap: device page map for that chunk - * @device: device to bind resource to - * @ops: memory operations callback - * @ref: per CPU refcount - * @page_fault: callback when CPU fault on an unaddressable device page - * - * This an helper structure for device drivers that do not wish to implement - * the gory details related to hotplugging new memoy and allocating struct - * pages. - * - * Device drivers can directly use ZONE_DEVICE memory on their own if they - * wish to do so. - * - * The page_fault() callback must migrate page back, from device memory to - * system memory, so that the CPU can access it. This might fail for various - * reasons (device issues, device have been unplugged, ...). When such error - * conditions happen, the page_fault() callback must return VM_FAULT_SIGBUS and - * set the CPU page table entry to "poisoned". - * - * Note that because memory cgroup charges are transferred to the device memory, - * this should never fail due to memory restrictions. However, allocation - * of a regular system page might still fail because we are out of memory. If - * that happens, the page_fault() callback must return VM_FAULT_OOM. - * - * The page_fault() callback can also try to migrate back multiple pages in one - * chunk, as an optimization. It must, however, prioritize the faulting address - * over all the others. - */ - -struct hmm_devmem { - struct completion completion; - unsigned long pfn_first; - unsigned long pfn_last; - struct resource *resource; - struct device *device; - struct dev_pagemap pagemap; - const struct hmm_devmem_ops *ops; - struct percpu_ref ref; -}; - -/* - * To add (hotplug) device memory, HMM assumes that there is no real resource - * that reserves a range in the physical address space (this is intended to be - * use by unaddressable device memory). It will reserve a physical range big - * enough and allocate struct page for it. - * - * The device driver can wrap the hmm_devmem struct inside a private device - * driver struct. - */ -struct hmm_devmem *hmm_devmem_add(const struct hmm_devmem_ops *ops, - struct device *device, - unsigned long size); - /* * hmm_devmem_page_set_drvdata - set per-page driver data field * -- cgit v1.2.3 From 8a164fef9c4ccf6ff7757170397222860e40d192 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 26 Jun 2019 14:27:21 +0200 Subject: mm: simplify ZONE_DEVICE page private data Remove the clumsy hmm_devmem_page_{get,set}_drvdata helpers, and instead just access the page directly. Also make the page data a void pointer, and thus much easier to use. Signed-off-by: Christoph Hellwig Reviewed-by: Dan Williams Signed-off-by: Jason Gunthorpe --- include/linux/hmm.h | 32 -------------------------------- include/linux/mm_types.h | 2 +- 2 files changed, 1 insertion(+), 33 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hmm.h b/include/linux/hmm.h index 86aa4ec3404c..3d00e9550e77 100644 --- a/include/linux/hmm.h +++ b/include/linux/hmm.h @@ -584,36 +584,4 @@ static inline void hmm_mm_destroy(struct mm_struct *mm) {} static inline void hmm_mm_init(struct mm_struct *mm) {} #endif /* IS_ENABLED(CONFIG_HMM_MIRROR) */ -#if IS_ENABLED(CONFIG_DEVICE_PRIVATE) -/* - * hmm_devmem_page_set_drvdata - set per-page driver data field - * - * @page: pointer to struct page - * @data: driver data value to set - * - * Because page can not be on lru we have an unsigned long that driver can use - * to store a per page field. This just a simple helper to do that. - */ -static inline void hmm_devmem_page_set_drvdata(struct page *page, - unsigned long data) -{ - page->hmm_data = data; -} - -/* - * hmm_devmem_page_get_drvdata - get per page driver data field - * - * @page: pointer to struct page - * Return: driver data value - */ -static inline unsigned long hmm_devmem_page_get_drvdata(const struct page *page) -{ - return page->hmm_data; -} -#endif /* CONFIG_DEVICE_PRIVATE */ -#else /* IS_ENABLED(CONFIG_HMM) */ -static inline void hmm_mm_destroy(struct mm_struct *mm) {} -static inline void hmm_mm_init(struct mm_struct *mm) {} -#endif /* IS_ENABLED(CONFIG_HMM) */ - #endif /* LINUX_HMM_H */ diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 8ec38b11b361..f33a1289c101 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -158,7 +158,7 @@ struct page { struct { /* ZONE_DEVICE pages */ /** @pgmap: Points to the hosting device page map. */ struct dev_pagemap *pgmap; - unsigned long hmm_data; + void *zone_device_data; unsigned long _zd_pad_1; /* uses mapping */ }; -- cgit v1.2.3 From 43535b0aefab29ea6564e608de4c783ed2ab6c49 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 26 Jun 2019 14:27:23 +0200 Subject: mm: remove the HMM config option All the mm/hmm.c code is better keyed off HMM_MIRROR. Also let nouveau depend on it instead of the mix of a dummy dependency symbol plus the actually selected one. Drop various odd dependencies, as the code is pretty portable. Signed-off-by: Christoph Hellwig Reviewed-by: Ira Weiny Reviewed-by: Jason Gunthorpe Reviewed-by: Dan Williams Signed-off-by: Jason Gunthorpe --- include/linux/hmm.h | 5 +---- include/linux/mm_types.h | 2 +- 2 files changed, 2 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hmm.h b/include/linux/hmm.h index 3d00e9550e77..b697496e85ba 100644 --- a/include/linux/hmm.h +++ b/include/linux/hmm.h @@ -62,7 +62,7 @@ #include #include -#if IS_ENABLED(CONFIG_HMM) +#ifdef CONFIG_HMM_MIRROR #include #include @@ -332,9 +332,6 @@ static inline uint64_t hmm_pfn_from_pfn(const struct hmm_range *range, return hmm_device_entry_from_pfn(range, pfn); } - - -#if IS_ENABLED(CONFIG_HMM_MIRROR) /* * Mirroring: how to synchronize device page table with CPU page table. * diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index f33a1289c101..8d37182f8dbe 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -501,7 +501,7 @@ struct mm_struct { #endif struct work_struct async_put_work; -#if IS_ENABLED(CONFIG_HMM) +#ifdef CONFIG_HMM_MIRROR /* HMM needs to track a few things per mm */ struct hmm *hmm; #endif -- cgit v1.2.3