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 <hch@lst.de>
Reviewed-by: Ira Weiny <ira.weiny@intel.com>
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
Tested-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
This commit is contained in:
Christoph Hellwig 2019-06-26 14:27:10 +02:00 committed by Jason Gunthorpe
parent d8668bb045
commit f6a55e1a3f
4 changed files with 41 additions and 53 deletions

View File

@ -334,11 +334,6 @@ static void pmem_release_disk(void *__pmem)
put_disk(pmem->disk); 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) static void pmem_pagemap_page_free(struct page *page, void *data)
{ {
wake_up_var(&page->_refcount); wake_up_var(&page->_refcount);
@ -350,16 +345,6 @@ static const struct dev_pagemap_ops fsdax_pagemap_ops = {
.cleanup = pmem_pagemap_cleanup, .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, static int pmem_attach_disk(struct device *dev,
struct nd_namespace_common *ndns) struct nd_namespace_common *ndns)
{ {
@ -415,8 +400,8 @@ static int pmem_attach_disk(struct device *dev,
pmem->pfn_flags = PFN_DEV; pmem->pfn_flags = PFN_DEV;
pmem->pgmap.ref = &q->q_usage_counter; pmem->pgmap.ref = &q->q_usage_counter;
if (is_nd_pfn(dev)) { if (is_nd_pfn(dev)) {
if (setup_pagemap_fsdax(dev, &pmem->pgmap)) pmem->pgmap.type = MEMORY_DEVICE_FS_DAX;
return -ENOMEM; pmem->pgmap.ops = &fsdax_pagemap_ops;
addr = devm_memremap_pages(dev, &pmem->pgmap); addr = devm_memremap_pages(dev, &pmem->pgmap);
pfn_sb = nd_pfn->pfn_sb; pfn_sb = nd_pfn->pfn_sb;
pmem->data_offset = le64_to_cpu(pfn_sb->dataoff); pmem->data_offset = le64_to_cpu(pfn_sb->dataoff);
@ -428,8 +413,8 @@ static int pmem_attach_disk(struct device *dev,
} else if (pmem_should_map_pages(dev)) { } else if (pmem_should_map_pages(dev)) {
memcpy(&pmem->pgmap.res, &nsio->res, sizeof(pmem->pgmap.res)); memcpy(&pmem->pgmap.res, &nsio->res, sizeof(pmem->pgmap.res));
pmem->pgmap.altmap_valid = false; pmem->pgmap.altmap_valid = false;
if (setup_pagemap_fsdax(dev, &pmem->pgmap)) pmem->pgmap.type = MEMORY_DEVICE_FS_DAX;
return -ENOMEM; pmem->pgmap.ops = &fsdax_pagemap_ops;
addr = devm_memremap_pages(dev, &pmem->pgmap); addr = devm_memremap_pages(dev, &pmem->pgmap);
pmem->pfn_flags |= PFN_MAP; pmem->pfn_flags |= PFN_MAP;
memcpy(&bb_res, &pmem->pgmap.res, sizeof(bb_res)); memcpy(&bb_res, &pmem->pgmap.res, sizeof(bb_res));

View File

@ -932,8 +932,6 @@ static inline bool is_zone_device_page(const struct page *page)
#endif #endif
#ifdef CONFIG_DEV_PAGEMAP_OPS #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); void __put_devmap_managed_page(struct page *page);
DECLARE_STATIC_KEY_FALSE(devmap_managed_key); DECLARE_STATIC_KEY_FALSE(devmap_managed_key);
static inline bool put_devmap_managed_page(struct page *page) 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 */ #endif /* CONFIG_PCI_P2PDMA */
#else /* CONFIG_DEV_PAGEMAP_OPS */ #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) static inline bool put_devmap_managed_page(struct page *page)
{ {
return false; return false;

View File

@ -17,6 +17,35 @@ static DEFINE_XARRAY(pgmap_array);
#define SECTION_MASK ~((1UL << PA_SECTION_SHIFT) - 1) #define SECTION_MASK ~((1UL << PA_SECTION_SHIFT) - 1)
#define SECTION_SIZE (1UL << PA_SECTION_SHIFT) #define SECTION_SIZE (1UL << PA_SECTION_SHIFT)
#ifdef CONFIG_DEV_PAGEMAP_OPS
DEFINE_STATIC_KEY_FALSE(devmap_managed_key);
EXPORT_SYMBOL(devmap_managed_key);
static atomic_t devmap_managed_enable;
static void devmap_managed_enable_put(void *data)
{
if (atomic_dec_and_test(&devmap_managed_enable))
static_branch_disable(&devmap_managed_key);
}
static int devmap_managed_enable_get(struct device *dev, struct dev_pagemap *pgmap)
{
if (!pgmap->ops->page_free) {
WARN(1, "Missing page_free method\n");
return -EINVAL;
}
if (atomic_inc_return(&devmap_managed_enable) == 1)
static_branch_enable(&devmap_managed_key);
return devm_add_action_or_reset(dev, devmap_managed_enable_put, NULL);
}
#else
static int devmap_managed_enable_get(struct device *dev, struct dev_pagemap *pgmap)
{
return -EINVAL;
}
#endif /* CONFIG_DEV_PAGEMAP_OPS */
#if IS_ENABLED(CONFIG_DEVICE_PRIVATE) #if IS_ENABLED(CONFIG_DEVICE_PRIVATE)
vm_fault_t device_private_entry_fault(struct vm_area_struct *vma, vm_fault_t device_private_entry_fault(struct vm_area_struct *vma,
unsigned long addr, unsigned long addr,
@ -156,6 +185,7 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
}; };
pgprot_t pgprot = PAGE_KERNEL; pgprot_t pgprot = PAGE_KERNEL;
int error, nid, is_ram; int error, nid, is_ram;
bool need_devmap_managed = true;
switch (pgmap->type) { switch (pgmap->type) {
case MEMORY_DEVICE_PRIVATE: case MEMORY_DEVICE_PRIVATE:
@ -173,6 +203,7 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
break; break;
case MEMORY_DEVICE_DEVDAX: case MEMORY_DEVICE_DEVDAX:
case MEMORY_DEVICE_PCI_P2PDMA: case MEMORY_DEVICE_PCI_P2PDMA:
need_devmap_managed = false;
break; break;
default: default:
WARN(1, "Invalid pgmap type %d\n", pgmap->type); WARN(1, "Invalid pgmap type %d\n", pgmap->type);
@ -185,6 +216,12 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
return ERR_PTR(-EINVAL); return ERR_PTR(-EINVAL);
} }
if (need_devmap_managed) {
error = devmap_managed_enable_get(dev, pgmap);
if (error)
return ERR_PTR(error);
}
align_start = res->start & ~(SECTION_SIZE - 1); align_start = res->start & ~(SECTION_SIZE - 1);
align_size = ALIGN(res->start + resource_size(res), SECTION_SIZE) align_size = ALIGN(res->start + resource_size(res), SECTION_SIZE)
- align_start; - align_start;
@ -351,28 +388,6 @@ struct dev_pagemap *get_dev_pagemap(unsigned long pfn,
EXPORT_SYMBOL_GPL(get_dev_pagemap); EXPORT_SYMBOL_GPL(get_dev_pagemap);
#ifdef CONFIG_DEV_PAGEMAP_OPS #ifdef CONFIG_DEV_PAGEMAP_OPS
DEFINE_STATIC_KEY_FALSE(devmap_managed_key);
EXPORT_SYMBOL(devmap_managed_key);
static atomic_t devmap_enable;
/*
* Toggle the static key for ->page_free() callbacks when dev_pagemap
* pages go idle.
*/
void dev_pagemap_get_ops(void)
{
if (atomic_inc_return(&devmap_enable) == 1)
static_branch_enable(&devmap_managed_key);
}
EXPORT_SYMBOL_GPL(dev_pagemap_get_ops);
void dev_pagemap_put_ops(void)
{
if (atomic_dec_and_test(&devmap_enable))
static_branch_disable(&devmap_managed_key);
}
EXPORT_SYMBOL_GPL(dev_pagemap_put_ops);
void __put_devmap_managed_page(struct page *page) void __put_devmap_managed_page(struct page *page)
{ {
int count = page_ref_dec_return(page); int count = page_ref_dec_return(page);

View File

@ -1415,8 +1415,6 @@ struct hmm_devmem *hmm_devmem_add(const struct hmm_devmem_ops *ops,
void *result; void *result;
int ret; int ret;
dev_pagemap_get_ops();
devmem = devm_kzalloc(device, sizeof(*devmem), GFP_KERNEL); devmem = devm_kzalloc(device, sizeof(*devmem), GFP_KERNEL);
if (!devmem) if (!devmem)
return ERR_PTR(-ENOMEM); return ERR_PTR(-ENOMEM);