[10/25] memremap: lift the devmap_enable manipulation into devm_memremap_pages

Submitted by Christoph Hellwig on June 17, 2019, 12:27 p.m.

Details

Message ID 20190617122733.22432-11-hch@lst.de
State New
Headers show
Series "dev_pagemap related cleanups v2" ( rev: 2 1 ) in Nouveau

Not browsing as part of any series.

Commit Message

Christoph Hellwig June 17, 2019, 12:27 p.m.
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>
---
 drivers/nvdimm/pmem.c | 23 +++--------------
 include/linux/mm.h    | 10 --------
 kernel/memremap.c     | 57 ++++++++++++++++++++++++++-----------------
 mm/hmm.c              |  2 --
 4 files changed, 39 insertions(+), 53 deletions(-)

Patch hide | download patch | download mbox

diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index 469a0f5b3380..85364c59c607 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/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))
-		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;
 	if (is_nd_pfn(dev)) {
-		if (setup_pagemap_fsdax(dev, &pmem->pgmap))
-			return -ENOMEM;
+		pmem->pgmap.type = MEMORY_DEVICE_FS_DAX;
+		pmem->pgmap.ops = &fsdax_pagemap_ops;
 		addr = devm_memremap_pages(dev, &pmem->pgmap);
 		pfn_sb = nd_pfn->pfn_sb;
 		pmem->data_offset = le64_to_cpu(pfn_sb->dataoff);
@@ -436,8 +421,8 @@  static int pmem_attach_disk(struct device *dev,
 	} else if (pmem_should_map_pages(dev)) {
 		memcpy(&pmem->pgmap.res, &nsio->res, sizeof(pmem->pgmap.res));
 		pmem->pgmap.altmap_valid = false;
-		if (setup_pagemap_fsdax(dev, &pmem->pgmap))
-			return -ENOMEM;
+		pmem->pgmap.type = MEMORY_DEVICE_FS_DAX;
+		pmem->pgmap.ops = &fsdax_pagemap_ops;
 		addr = devm_memremap_pages(dev, &pmem->pgmap);
 		pmem->pfn_flags |= PFN_MAP;
 		memcpy(&bb_res, &pmem->pgmap.res, sizeof(bb_res));
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 0e8834ac32b7..edcf2b821647 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -921,8 +921,6 @@  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)
@@ -969,14 +967,6 @@  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;
diff --git a/kernel/memremap.c b/kernel/memremap.c
index ba7156bd52d1..7272027fbdd7 100644
--- a/kernel/memremap.c
+++ b/kernel/memremap.c
@@ -17,6 +17,35 @@  static DEFINE_XARRAY(pgmap_array);
 #define SECTION_MASK ~((1UL << PA_SECTION_SHIFT) - 1)
 #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_enable;
+
+static void dev_pagemap_put_ops(void *data)
+{
+	if (atomic_dec_and_test(&devmap_enable))
+		static_branch_disable(&devmap_managed_key);
+}
+
+static int dev_pagemap_get_ops(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_enable) == 1)
+		static_branch_enable(&devmap_managed_key);
+	return devm_add_action_or_reset(dev, dev_pagemap_put_ops, NULL);
+}
+#else
+static int dev_pagemap_get_ops(struct device *dev, struct dev_pagemap *pgmap)
+{
+	return -EINVAL;
+}
+#endif /* CONFIG_DEV_PAGEMAP_OPS */
+
 #if IS_ENABLED(CONFIG_DEVICE_PRIVATE)
 vm_fault_t device_private_entry_fault(struct vm_area_struct *vma,
 		       unsigned long addr,
@@ -190,6 +219,12 @@  void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
 		return ERR_PTR(-EINVAL);
 	}
 
+	if (pgmap->type != MEMORY_DEVICE_PCI_P2PDMA) {
+		error = dev_pagemap_get_ops(dev, pgmap);
+		if (error)
+			return ERR_PTR(error);
+	}
+
 	align_start = res->start & ~(SECTION_SIZE - 1);
 	align_size = ALIGN(res->start + resource_size(res), SECTION_SIZE)
 		- align_start;
@@ -356,28 +391,6 @@  struct dev_pagemap *get_dev_pagemap(unsigned long pfn,
 EXPORT_SYMBOL_GPL(get_dev_pagemap);
 
 #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)
 {
 	int count = page_ref_dec_return(page);
diff --git a/mm/hmm.c b/mm/hmm.c
index ec3bf2c5c699..0add50944d64 100644
--- a/mm/hmm.c
+++ b/mm/hmm.c
@@ -1412,8 +1412,6 @@  struct hmm_devmem *hmm_devmem_add(const struct hmm_devmem_ops *ops,
 	void *result;
 	int ret;
 
-	dev_pagemap_get_ops();
-
 	devmem = devm_kzalloc(device, sizeof(*devmem), GFP_KERNEL);
 	if (!devmem)
 		return ERR_PTR(-ENOMEM);

Comments

On Mon, Jun 17, 2019 at 5:28 AM Christoph Hellwig <hch@lst.de> wrote:
>
> 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>
> ---
>  drivers/nvdimm/pmem.c | 23 +++--------------
>  include/linux/mm.h    | 10 --------
>  kernel/memremap.c     | 57 ++++++++++++++++++++++++++-----------------
>  mm/hmm.c              |  2 --
>  4 files changed, 39 insertions(+), 53 deletions(-)
>
[..]
> diff --git a/kernel/memremap.c b/kernel/memremap.c
> index ba7156bd52d1..7272027fbdd7 100644
> --- a/kernel/memremap.c
> +++ b/kernel/memremap.c
[..]
> @@ -190,6 +219,12 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
>                 return ERR_PTR(-EINVAL);
>         }
>
> +       if (pgmap->type != MEMORY_DEVICE_PCI_P2PDMA) {

Once we have MEMORY_DEVICE_DEVDAX then this check needs to be fixed up
to skip that case as well, otherwise:

 Missing page_free method
 WARNING: CPU: 19 PID: 1518 at kernel/memremap.c:33
devm_memremap_pages+0x745/0x7d0
 RIP: 0010:devm_memremap_pages+0x745/0x7d0
 Call Trace:
  dev_dax_probe+0xc6/0x1e0 [device_dax]
  really_probe+0xef/0x390
  ? driver_allows_async_probing+0x50/0x50
  driver_probe_device+0xb4/0x100