Linux-PCI Archive on lore.kernel.org
 help / color / Atom feed
From: Christoph Hellwig <hch@lst.de>
To: "Dan Williams" <dan.j.williams@intel.com>,
	"Jérôme Glisse" <jglisse@redhat.com>,
	"Jason Gunthorpe" <jgg@mellanox.com>,
	"Ben Skeggs" <bskeggs@redhat.com>
Cc: linux-mm@kvack.org, nouveau@lists.freedesktop.org,
	dri-devel@lists.freedesktop.org, linux-nvdimm@lists.01.org,
	linux-pci@vger.kernel.org, linux-kernel@vger.kernel.org,
	Ralph Campbell <rcampbell@nvidia.com>
Subject: [PATCH 12/25] memremap: add a migrate_to_ram method to struct dev_pagemap_ops
Date: Wed, 26 Jun 2019 14:27:11 +0200
Message-ID: <20190626122724.13313-13-hch@lst.de> (raw)
In-Reply-To: <20190626122724.13313-1-hch@lst.de>

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 <hch@lst.de>
Reviewed-by: Ralph Campbell <rcampbell@nvidia.com>
---
 include/linux/hmm.h      |  6 ------
 include/linux/memremap.h |  6 ++++++
 include/linux/swapops.h  | 15 ---------------
 kernel/memremap.c        | 35 ++++-------------------------------
 mm/hmm.c                 | 13 +++++--------
 mm/memory.c              |  9 ++-------
 6 files changed, 17 insertions(+), 67 deletions(-)

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
diff --git a/kernel/memremap.c b/kernel/memremap.c
index 3219a4c91d07..c06a5487dda7 100644
--- a/kernel/memremap.c
+++ b/kernel/memremap.c
@@ -11,7 +11,6 @@
 #include <linux/types.h>
 #include <linux/wait_bit.h>
 #include <linux/xarray.h>
-#include <linux/hmm.h>
 
 static DEFINE_XARRAY(pgmap_array);
 #define SECTION_MASK ~((1UL << PA_SECTION_SHIFT) - 1)
@@ -46,36 +45,6 @@ static int devmap_managed_enable_get(struct device *dev, struct dev_pagemap *pgm
 }
 #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,
-		       swp_entry_t entry,
-		       unsigned int flags,
-		       pmd_t *pmdp)
-{
-	struct page *page = device_private_entry_to_page(entry);
-	struct hmm_devmem *devmem;
-
-	devmem = container_of(page->pgmap, typeof(*devmem), pagemap);
-
-	/*
-	 * The page_fault() callback must migrate page back to system memory
-	 * so that CPU can access it. This might fail for various reasons
-	 * (device issue, device was unsafely unplugged, ...). When such
-	 * error conditions happen, the callback must return VM_FAULT_SIGBUS.
-	 *
-	 * Note that because memory cgroup charges are accounted to the device
-	 * memory, this should never fail because of memory restrictions (but
-	 * allocation of regular system page might still fail because we are
-	 * out of memory).
-	 *
-	 * There is a more in-depth description of what that callback can and
-	 * cannot do, in include/linux/memremap.h
-	 */
-	return devmem->page_fault(vma, addr, page, flags, pmdp);
-}
-#endif /* CONFIG_DEVICE_PRIVATE */
-
 static void pgmap_array_delete(struct resource *res)
 {
 	xa_store_range(&pgmap_array, PHYS_PFN(res->start), PHYS_PFN(res->end),
@@ -193,6 +162,10 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
 			WARN(1, "Device private memory not supported\n");
 			return ERR_PTR(-EINVAL);
 		}
+		if (!pgmap->ops || !pgmap->ops->migrate_to_ram) {
+			WARN(1, "Missing migrate_to_ram method\n");
+			return ERR_PTR(-EINVAL);
+		}
 		break;
 	case MEMORY_DEVICE_FS_DAX:
 		if (!IS_ENABLED(CONFIG_ZONE_DEVICE) ||
diff --git a/mm/hmm.c b/mm/hmm.c
index 5b0bd5f6a74f..96633ee066d8 100644
--- a/mm/hmm.c
+++ b/mm/hmm.c
@@ -1366,15 +1366,12 @@ static void hmm_devmem_ref_kill(struct dev_pagemap *pgmap)
 	percpu_ref_kill(pgmap->ref);
 }
 
-static vm_fault_t hmm_devmem_fault(struct vm_area_struct *vma,
-			    unsigned long addr,
-			    const struct page *page,
-			    unsigned int flags,
-			    pmd_t *pmdp)
+static vm_fault_t hmm_devmem_migrate_to_ram(struct vm_fault *vmf)
 {
-	struct hmm_devmem *devmem = page->pgmap->data;
+	struct hmm_devmem *devmem = vmf->page->pgmap->data;
 
-	return devmem->ops->fault(devmem, vma, addr, page, flags, pmdp);
+	return devmem->ops->fault(devmem, vmf->vma, vmf->address, vmf->page,
+			vmf->flags, vmf->pmd);
 }
 
 static void hmm_devmem_free(struct page *page, void *data)
@@ -1388,6 +1385,7 @@ static const struct dev_pagemap_ops hmm_pagemap_ops = {
 	.page_free		= hmm_devmem_free,
 	.kill			= hmm_devmem_ref_kill,
 	.cleanup		= hmm_devmem_ref_exit,
+	.migrate_to_ram		= hmm_devmem_migrate_to_ram,
 };
 
 /*
@@ -1438,7 +1436,6 @@ struct hmm_devmem *hmm_devmem_add(const struct hmm_devmem_ops *ops,
 	devmem->pfn_first = devmem->resource->start >> PAGE_SHIFT;
 	devmem->pfn_last = devmem->pfn_first +
 			   (resource_size(devmem->resource) >> PAGE_SHIFT);
-	devmem->page_fault = hmm_devmem_fault;
 
 	devmem->pagemap.type = MEMORY_DEVICE_PRIVATE;
 	devmem->pagemap.res = *devmem->resource;
diff --git a/mm/memory.c b/mm/memory.c
index bd21e7063bf0..293d2936fd6c 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2748,13 +2748,8 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 			migration_entry_wait(vma->vm_mm, vmf->pmd,
 					     vmf->address);
 		} else if (is_device_private_entry(entry)) {
-			/*
-			 * For un-addressable device memory we call the pgmap
-			 * fault handler callback. The callback must migrate
-			 * the page back to some CPU accessible page.
-			 */
-			ret = device_private_entry_fault(vma, vmf->address, entry,
-						 vmf->flags, vmf->pmd);
+			vmf->page = device_private_entry_to_page(entry);
+			ret = vmf->page->pgmap->ops->migrate_to_ram(vmf);
 		} else if (is_hwpoison_entry(entry)) {
 			ret = VM_FAULT_HWPOISON;
 		} else {
-- 
2.20.1


  parent reply index

Thread overview: 59+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-06-26 12:26 dev_pagemap related cleanups v3 Christoph Hellwig
2019-06-26 12:27 ` [PATCH 01/25] mm: remove the unused ARCH_HAS_HMM_DEVICE Kconfig option Christoph Hellwig
2019-06-26 12:27 ` [PATCH 02/25] mm: remove the struct hmm_device infrastructure Christoph Hellwig
2019-06-26 12:27 ` [PATCH 03/25] mm: remove hmm_devmem_add_resource Christoph Hellwig
2019-06-27 16:18   ` Jason Gunthorpe
2019-06-27 16:54     ` Christoph Hellwig
2019-06-26 12:27 ` [PATCH 04/25] mm: remove MEMORY_DEVICE_PUBLIC support Christoph Hellwig
2019-06-26 16:00   ` Dan Williams
2019-06-26 17:14     ` Ira Weiny
2019-06-26 18:49       ` Ira Weiny
2019-06-26 12:27 ` [PATCH 05/25] mm: don't clear ->mapping in hmm_devmem_free Christoph Hellwig
2019-06-26 12:27 ` [PATCH 06/25] mm: export alloc_pages_vma Christoph Hellwig
2019-06-26 12:36   ` Michal Hocko
2019-06-26 12:27 ` [PATCH 07/25] mm: factor out a devm_request_free_mem_region helper Christoph Hellwig
2019-06-26 12:27 ` [PATCH 08/25] memremap: validate the pagemap type passed to devm_memremap_pages Christoph Hellwig
2019-06-26 18:01   ` Ira Weiny
2019-06-26 12:27 ` [PATCH 09/25] memremap: move dev_pagemap callbacks into a separate structure Christoph Hellwig
2019-06-26 12:27 ` [PATCH 10/25] memremap: pass a struct dev_pagemap to ->kill and ->cleanup Christoph Hellwig
2019-06-26 12:27 ` [PATCH 11/25] memremap: lift the devmap_enable manipulation into devm_memremap_pages Christoph Hellwig
2019-06-26 19:04   ` Ira Weiny
2019-06-27  8:50     ` Christoph Hellwig
2019-06-26 12:27 ` Christoph Hellwig [this message]
2019-06-27 16:29   ` [PATCH 12/25] memremap: add a migrate_to_ram method to struct dev_pagemap_ops Jason Gunthorpe
2019-06-27 16:53     ` Christoph Hellwig
2019-06-26 12:27 ` [PATCH 13/25] memremap: remove the data field in struct dev_pagemap Christoph Hellwig
2019-06-26 12:27 ` [PATCH 14/25] memremap: replace the altmap_valid field with a PGMAP_ALTMAP_VALID flag Christoph Hellwig
2019-06-26 21:13   ` Ira Weiny
2019-06-26 12:27 ` [PATCH 15/25] memremap: provide an optional internal refcount in struct dev_pagemap Christoph Hellwig
2019-06-26 21:47   ` Ira Weiny
2019-06-27  8:51     ` Christoph Hellwig
2019-06-26 12:27 ` [PATCH 16/25] device-dax: use the dev_pagemap internal refcount Christoph Hellwig
2019-06-26 21:48   ` Ira Weiny
2019-06-28 15:38   ` Jason Gunthorpe
2019-06-28 16:27     ` Dan Williams
2019-06-28 17:02       ` Jason Gunthorpe
2019-06-28 17:08         ` Dan Williams
2019-06-28 17:10           ` Dan Williams
2019-06-28 18:29             ` Jason Gunthorpe
2019-06-28 18:44               ` Dan Williams
2019-06-28 18:51                 ` Christoph Hellwig
2019-06-28 18:59                   ` Dan Williams
2019-06-28 19:02                     ` Christoph Hellwig
2019-06-28 19:14                       ` Dan Williams
2019-07-02 22:35                         ` Andrew Morton
2019-06-26 12:27 ` [PATCH 17/25] PCI/P2PDMA: " Christoph Hellwig
2019-06-26 21:49   ` Ira Weiny
2019-06-27 18:49   ` Logan Gunthorpe
2019-06-26 12:27 ` [PATCH 18/25] nouveau: use alloc_page_vma directly Christoph Hellwig
2019-06-26 12:27 ` [PATCH 19/25] nouveau: use devm_memremap_pages directly Christoph Hellwig
2019-06-26 12:27 ` [PATCH 20/25] mm: remove hmm_vma_alloc_locked_page Christoph Hellwig
2019-06-27 16:26   ` Jason Gunthorpe
2019-06-26 12:27 ` [PATCH 21/25] mm: remove hmm_devmem_add Christoph Hellwig
2019-06-26 12:27 ` [PATCH 22/25] mm: simplify ZONE_DEVICE page private data Christoph Hellwig
2019-06-26 12:27 ` [PATCH 23/25] mm: sort out the DEVICE_PRIVATE Kconfig mess Christoph Hellwig
2019-06-26 21:36   ` Ira Weiny
2019-06-26 12:27 ` [PATCH 24/25] mm: remove the HMM config option Christoph Hellwig
2019-06-26 21:38   ` Ira Weiny
2019-06-27 16:29   ` Jason Gunthorpe
2019-06-26 12:27 ` [PATCH 25/25] mm: don't select MIGRATE_VMA_HELPER from HMM_MIRROR Christoph Hellwig

Reply instructions:

You may reply publically to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20190626122724.13313-13-hch@lst.de \
    --to=hch@lst.de \
    --cc=bskeggs@redhat.com \
    --cc=dan.j.williams@intel.com \
    --cc=dri-devel@lists.freedesktop.org \
    --cc=jgg@mellanox.com \
    --cc=jglisse@redhat.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=linux-nvdimm@lists.01.org \
    --cc=linux-pci@vger.kernel.org \
    --cc=nouveau@lists.freedesktop.org \
    --cc=rcampbell@nvidia.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

Linux-PCI Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-pci/0 linux-pci/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 linux-pci linux-pci/ https://lore.kernel.org/linux-pci \
		linux-pci@vger.kernel.org
	public-inbox-index linux-pci

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.linux-pci


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git