Linux-PCI Archive on lore.kernel.org
 help / color / Atom feed
From: Ralph Campbell <rcampbell@nvidia.com>
To: "Christoph Hellwig" <hch@lst.de>,
	"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>
Subject: Re: [PATCH 10/22] memremap: add a migrate callback to struct dev_pagemap_ops
Date: Thu, 13 Jun 2019 16:42:07 -0700
Message-ID: <d6916d71-c17e-74df-58f2-c28ff8044b96@nvidia.com> (raw)
In-Reply-To: <20190613094326.24093-11-hch@lst.de>


On 6/13/19 2:43 AM, Christoph Hellwig wrote:
> 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>
> ---
>   include/linux/hmm.h      |  6 ------
>   include/linux/memremap.h |  6 ++++++
>   include/linux/swapops.h  | 15 ---------------
>   kernel/memremap.c        | 31 -------------------------------
>   mm/hmm.c                 | 13 +++++--------
>   mm/memory.c              |  9 ++-------
>   6 files changed, 13 insertions(+), 67 deletions(-)
> 
> diff --git a/include/linux/hmm.h b/include/linux/hmm.h
> index 5761a39221a6..3c9a59dbfdb8 100644
> --- a/include/linux/hmm.h
> +++ b/include/linux/hmm.h
> @@ -658,11 +658,6 @@ 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;
> @@ -673,7 +668,6 @@ 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 96a3a6d564ad..03a4099be701 100644
> --- a/include/linux/memremap.h
> +++ b/include/linux/memremap.h
> @@ -75,6 +75,12 @@ struct dev_pagemap_ops {
>   	 * Transition the percpu_ref in struct dev_pagemap to the dead state.
>   	 */
>   	void (*kill)(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)(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 6a3183cac764..7167e717647d 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)
> @@ -48,36 +47,6 @@ static inline int dev_pagemap_enable(struct device *dev)
>   }
>   #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),
> diff --git a/mm/hmm.c b/mm/hmm.c
> index 6dc769feb2e1..aab799677c7d 100644
> --- a/mm/hmm.c
> +++ b/mm/hmm.c
> @@ -1330,15 +1330,12 @@ 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(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)
> @@ -1351,6 +1348,7 @@ static void hmm_devmem_free(struct page *page, void *data)
>   static const struct dev_pagemap_ops hmm_pagemap_ops = {
>   	.page_free		= hmm_devmem_free,
>   	.kill			= hmm_devmem_ref_kill,
> +	.migrate		= hmm_devmem_migrate,
>   };
>   
>   /*
> @@ -1405,7 +1403,6 @@ 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 ddf20bd0c317..cbf3cb598436 100644
> --- a/mm/memory.c
> +++ b/mm/memory.c
> @@ -2782,13 +2782,8 @@ 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 = page->pgmap->ops->migrate(vmf);

This needs to either initialize "page" or be changed to "vmf->page".
Otherwise, it is a NULL pointer dereference.

>   		} else if (is_hwpoison_entry(entry)) {
>   			ret = VM_FAULT_HWPOISON;
>   		} else {
> 

You can add:
Reviewed-by: Ralph Campbell <rcampbell@nvidia.com>

  reply index

Thread overview: 103+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-06-13  9:43 dev_pagemap related cleanups Christoph Hellwig
2019-06-13  9:43 ` [PATCH 01/22] mm: remove the unused ARCH_HAS_HMM_DEVICE Kconfig option Christoph Hellwig
2019-06-13 18:30   ` Jason Gunthorpe
2019-06-13  9:43 ` [PATCH 02/22] mm: remove the struct hmm_device infrastructure Christoph Hellwig
2019-06-13 18:46   ` Jason Gunthorpe
2019-06-13 23:06   ` [Nouveau] " John Hubbard
2019-06-13  9:43 ` [PATCH 03/22] mm: remove hmm_devmem_add_resource Christoph Hellwig
2019-06-13 18:52   ` Jason Gunthorpe
2019-06-14  6:19     ` Christoph Hellwig
2019-06-14  0:54   ` [Nouveau] " John Hubbard
2019-06-20 19:32   ` Michal Hocko
2019-06-13  9:43 ` [PATCH 04/22] mm: don't clear ->mapping in hmm_devmem_free Christoph Hellwig
2019-06-13 19:05   ` Jason Gunthorpe
2019-06-14  6:21     ` Christoph Hellwig
2019-06-14  1:46   ` John Hubbard
2019-06-20 19:36   ` Michal Hocko
2019-06-13  9:43 ` [PATCH 05/22] mm: export alloc_pages_vma Christoph Hellwig
2019-06-14  1:47   ` John Hubbard
2019-06-14  6:23     ` Christoph Hellwig
2019-06-20 19:17   ` Michal Hocko
2019-06-24 18:24     ` Dan Williams
2019-06-25  7:23       ` Christoph Hellwig
2019-06-25 15:00         ` Michal Hocko
2019-06-25 18:03           ` Dan Williams
2019-06-25 19:00             ` Michal Hocko
2019-06-25 19:52               ` Dan Williams
2019-06-26  5:46                 ` Michal Hocko
2019-06-26 16:14                   ` Dan Williams
2019-06-27  6:41                     ` Michal Hocko
2019-06-13  9:43 ` [PATCH 06/22] mm: factor out a devm_request_free_mem_region helper Christoph Hellwig
2019-06-13 19:16   ` Jason Gunthorpe
2019-06-14  6:24     ` Christoph Hellwig
2019-06-15  2:21   ` John Hubbard
2019-06-15 14:30     ` Christoph Hellwig
2019-06-13  9:43 ` [PATCH 07/22] memremap: move dev_pagemap callbacks into a separate structure Christoph Hellwig
2019-06-13 19:18   ` Jason Gunthorpe
2019-06-13 20:14   ` Logan Gunthorpe
2019-06-13  9:43 ` [PATCH 08/22] memremap: pass a struct dev_pagemap to ->kill Christoph Hellwig
2019-06-13 19:26   ` Jason Gunthorpe
2019-06-13 20:12   ` Logan Gunthorpe
2019-06-13 20:15     ` Dan Williams
2019-06-13  9:43 ` [PATCH 09/22] memremap: lift the devmap_enable manipulation into devm_memremap_pages Christoph Hellwig
2019-06-13 19:34   ` Jason Gunthorpe
2019-06-13 20:13     ` Dan Williams
2019-06-14  6:28     ` Christoph Hellwig
2019-06-13  9:43 ` [PATCH 10/22] memremap: add a migrate callback to struct dev_pagemap_ops Christoph Hellwig
2019-06-13 23:42   ` Ralph Campbell [this message]
2019-06-14  6:33     ` Christoph Hellwig
2019-06-13  9:43 ` [PATCH 11/22] memremap: remove the data field in struct dev_pagemap Christoph Hellwig
2019-06-13 19:37   ` Jason Gunthorpe
2019-06-13  9:43 ` [PATCH 12/22] memremap: provide an optional internal refcount " Christoph Hellwig
2019-06-13  9:43 ` [PATCH 13/22] device-dax: use the dev_pagemap internal refcount Christoph Hellwig
2019-06-14  0:22   ` Ira Weiny
2019-06-14  6:35     ` Christoph Hellwig
2019-06-13  9:43 ` [PATCH 14/22] nouveau: use alloc_page_vma directly Christoph Hellwig
2019-06-13 19:39   ` Jason Gunthorpe
2019-06-13  9:43 ` [PATCH 15/22] nouveau: use devm_memremap_pages directly Christoph Hellwig
2019-06-13  9:43 ` [PATCH 16/22] mm: remove hmm_vma_alloc_locked_page Christoph Hellwig
2019-06-13  9:43 ` [PATCH 17/22] mm: remove hmm_devmem_add Christoph Hellwig
2019-06-13 19:42   ` Jason Gunthorpe
2019-06-14  6:39     ` Christoph Hellwig
2019-06-13  9:43 ` [PATCH 18/22] mm: mark DEVICE_PUBLIC as broken Christoph Hellwig
2019-06-13 19:44   ` Jason Gunthorpe
2019-06-13 19:53     ` Ralph Campbell
2019-06-13 19:58       ` Jason Gunthorpe
2019-06-14  0:43         ` Ira Weiny
2019-06-14  1:23           ` John Hubbard
2019-06-19 19:27             ` Jason Gunthorpe
2019-06-19 19:46               ` Dan Williams
2019-06-26  3:15               ` John Hubbard
2019-06-26  5:45                 ` Michal Hocko
2019-06-26  6:07                   ` John Hubbard
2019-06-14  6:43           ` Christoph Hellwig
2019-06-20 19:26   ` Michal Hocko
2019-06-25  7:29     ` Christoph Hellwig
2019-06-25 11:44       ` Jason Gunthorpe
2019-06-25 11:59         ` Christoph Hellwig
2019-06-13  9:43 ` [PATCH 19/22] mm: simplify ZONE_DEVICE page private data Christoph Hellwig
2019-06-13  9:43 ` [PATCH 20/22] mm: sort out the DEVICE_PRIVATE Kconfig mess Christoph Hellwig
2019-06-13 19:55   ` Jason Gunthorpe
2019-06-13  9:43 ` [PATCH 21/22] mm: remove the HMM config option Christoph Hellwig
2019-06-13 20:01   ` Jason Gunthorpe
2019-06-14  6:47     ` Christoph Hellwig
2019-06-13  9:43 ` [PATCH 22/22] mm: don't select MIGRATE_VMA_HELPER from HMM_MIRROR Christoph Hellwig
2019-06-13 20:04   ` Jason Gunthorpe
2019-06-14  1:53   ` [Nouveau] " John Hubbard
2019-06-14  6:48     ` Christoph Hellwig
2019-06-13 14:16 ` dev_pagemap related cleanups Jason Gunthorpe
2019-06-14  6:12   ` Christoph Hellwig
2019-06-13 18:27 ` Dan Williams
2019-06-13 20:17   ` Logan Gunthorpe
2019-06-13 20:21     ` Dan Williams
2019-06-13 20:24       ` Logan Gunthorpe
2019-06-13 20:48         ` Andrew Morton
2019-06-13 20:40   ` Jason Gunthorpe
2019-06-13 21:21     ` Christoph Hellwig
2019-06-13 23:10       ` Jason Gunthorpe
2019-06-14  6:14         ` Christoph Hellwig
2019-06-14  0:31     ` Ira Weiny
2019-06-14  6:13   ` Christoph Hellwig
2019-06-15  1:14     ` Dan Williams
2019-06-15  8:33       ` Christoph Hellwig
2019-06-15 18:09         ` Dan Williams

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=d6916d71-c17e-74df-58f2-c28ff8044b96@nvidia.com \
    --to=rcampbell@nvidia.com \
    --cc=bskeggs@redhat.com \
    --cc=dan.j.williams@intel.com \
    --cc=dri-devel@lists.freedesktop.org \
    --cc=hch@lst.de \
    --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 \
    /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 linux-pci@archiver.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