Linux-PCI Archive on lore.kernel.org
 help / color / Atom feed
From: Ira Weiny <ira.weiny@intel.com>
To: Christoph Hellwig <hch@lst.de>
Cc: "Dan Williams" <dan.j.williams@intel.com>,
	"Jérôme Glisse" <jglisse@redhat.com>,
	"Jason Gunthorpe" <jgg@mellanox.com>,
	"Ben Skeggs" <bskeggs@redhat.com>,
	linux-nvdimm@lists.01.org, linux-pci@vger.kernel.org,
	linux-kernel@vger.kernel.org, dri-devel@lists.freedesktop.org,
	linux-mm@kvack.org, nouveau@lists.freedesktop.org
Subject: Re: [PATCH 14/25] memremap: replace the altmap_valid field with a PGMAP_ALTMAP_VALID flag
Date: Wed, 26 Jun 2019 14:13:00 -0700
Message-ID: <20190626211300.GF4605@iweiny-DESK2.sc.intel.com> (raw)
In-Reply-To: <20190626122724.13313-15-hch@lst.de>

On Wed, Jun 26, 2019 at 02:27:13PM +0200, Christoph Hellwig wrote:
> 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 <hch@lst.de>

Reviewed-by: Ira Weiny <ira.weiny@intel.com>

> ---
>  arch/powerpc/mm/mem.c     | 10 +---------
>  arch/x86/mm/init_64.c     |  8 ++------
>  drivers/nvdimm/pfn_devs.c |  3 +--
>  drivers/nvdimm/pmem.c     |  1 -
>  include/linux/memremap.h  | 12 +++++++++++-
>  kernel/memremap.c         | 26 ++++++++++----------------
>  mm/hmm.c                  |  1 -
>  mm/memory_hotplug.c       |  6 ++----
>  mm/page_alloc.c           |  5 ++---
>  9 files changed, 29 insertions(+), 43 deletions(-)
> 
> diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
> index cba29131bccc..f774d80df025 100644
> --- a/arch/powerpc/mm/mem.c
> +++ b/arch/powerpc/mm/mem.c
> @@ -131,17 +131,9 @@ void __ref arch_remove_memory(int nid, u64 start, u64 size,
>  {
>  	unsigned long start_pfn = start >> PAGE_SHIFT;
>  	unsigned long nr_pages = size >> PAGE_SHIFT;
> -	struct page *page;
> +	struct page *page = pfn_to_page(start_pfn) + vmem_altmap_offset(altmap);
>  	int ret;
>  
> -	/*
> -	 * If we have an altmap then we need to skip over any reserved PFNs
> -	 * when querying the zone.
> -	 */
> -	page = pfn_to_page(start_pfn);
> -	if (altmap)
> -		page += vmem_altmap_offset(altmap);
> -
>  	__remove_pages(page_zone(page), start_pfn, nr_pages, altmap);
>  
>  	/* Remove htab bolted mappings for this section of memory */
> diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
> index 693aaf28d5fe..3139e992ef9d 100644
> --- a/arch/x86/mm/init_64.c
> +++ b/arch/x86/mm/init_64.c
> @@ -1211,13 +1211,9 @@ void __ref arch_remove_memory(int nid, u64 start, u64 size,
>  {
>  	unsigned long start_pfn = start >> PAGE_SHIFT;
>  	unsigned long nr_pages = size >> PAGE_SHIFT;
> -	struct page *page = pfn_to_page(start_pfn);
> -	struct zone *zone;
> +	struct page *page = pfn_to_page(start_pfn) + vmem_altmap_offset(altmap);
> +	struct zone *zone = page_zone(page);
>  
> -	/* With altmap the first mapped page is offset from @start */
> -	if (altmap)
> -		page += vmem_altmap_offset(altmap);
> -	zone = page_zone(page);
>  	__remove_pages(zone, start_pfn, nr_pages, altmap);
>  	kernel_physical_mapping_remove(start, start + size);
>  }
> diff --git a/drivers/nvdimm/pfn_devs.c b/drivers/nvdimm/pfn_devs.c
> index 0f81fc56bbfd..55fb6b7433ed 100644
> --- a/drivers/nvdimm/pfn_devs.c
> +++ b/drivers/nvdimm/pfn_devs.c
> @@ -622,7 +622,6 @@ static int __nvdimm_setup_pfn(struct nd_pfn *nd_pfn, struct dev_pagemap *pgmap)
>  		if (offset < reserve)
>  			return -EINVAL;
>  		nd_pfn->npfns = le64_to_cpu(pfn_sb->npfns);
> -		pgmap->altmap_valid = false;
>  	} else if (nd_pfn->mode == PFN_MODE_PMEM) {
>  		nd_pfn->npfns = PFN_SECTION_ALIGN_UP((resource_size(res)
>  					- offset) / PAGE_SIZE);
> @@ -634,7 +633,7 @@ static int __nvdimm_setup_pfn(struct nd_pfn *nd_pfn, struct dev_pagemap *pgmap)
>  		memcpy(altmap, &__altmap, sizeof(*altmap));
>  		altmap->free = PHYS_PFN(offset - reserve);
>  		altmap->alloc = 0;
> -		pgmap->altmap_valid = true;
> +		pgmap->flags |= PGMAP_ALTMAP_VALID;
>  	} else
>  		return -ENXIO;
>  
> diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
> index 093408ce40ad..e7d8cc9f41e8 100644
> --- a/drivers/nvdimm/pmem.c
> +++ b/drivers/nvdimm/pmem.c
> @@ -412,7 +412,6 @@ static int pmem_attach_disk(struct device *dev,
>  		bb_res.start += pmem->data_offset;
>  	} else if (pmem_should_map_pages(dev)) {
>  		memcpy(&pmem->pgmap.res, &nsio->res, sizeof(pmem->pgmap.res));
> -		pmem->pgmap.altmap_valid = false;
>  		pmem->pgmap.type = MEMORY_DEVICE_FS_DAX;
>  		pmem->pgmap.ops = &fsdax_pagemap_ops;
>  		addr = devm_memremap_pages(dev, &pmem->pgmap);
> 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);
> diff --git a/kernel/memremap.c b/kernel/memremap.c
> index 6c3dbb692037..eee490e7d7e1 100644
> --- a/kernel/memremap.c
> +++ b/kernel/memremap.c
> @@ -54,14 +54,8 @@ static void pgmap_array_delete(struct resource *res)
>  
>  static unsigned long pfn_first(struct dev_pagemap *pgmap)
>  {
> -	const struct resource *res = &pgmap->res;
> -	struct vmem_altmap *altmap = &pgmap->altmap;
> -	unsigned long pfn;
> -
> -	pfn = res->start >> PAGE_SHIFT;
> -	if (pgmap->altmap_valid)
> -		pfn += vmem_altmap_offset(altmap);
> -	return pfn;
> +	return (pgmap->res.start >> PAGE_SHIFT) +
> +		vmem_altmap_offset(pgmap_altmap(pgmap));
>  }
>  
>  static unsigned long pfn_end(struct dev_pagemap *pgmap)
> @@ -109,7 +103,7 @@ static void devm_memremap_pages_release(void *data)
>  				align_size >> PAGE_SHIFT, NULL);
>  	} else {
>  		arch_remove_memory(nid, align_start, align_size,
> -				pgmap->altmap_valid ? &pgmap->altmap : NULL);
> +				pgmap_altmap(pgmap));
>  		kasan_remove_zero_shadow(__va(align_start), align_size);
>  	}
>  	mem_hotplug_done();
> @@ -129,8 +123,8 @@ static void devm_memremap_pages_release(void *data)
>   * 1/ At a minimum the res, ref and type and ops members of @pgmap must be
>   *    initialized by the caller before passing it to this function
>   *
> - * 2/ The altmap field may optionally be initialized, in which case altmap_valid
> - *    must be set to true
> + * 2/ The altmap field may optionally be initialized, in which case
> + *    PGMAP_ALTMAP_VALID must be set in pgmap->flags.
>   *
>   * 3/ pgmap->ref must be 'live' on entry and will be killed and reaped
>   *    at devm_memremap_pages_release() time, or if this routine fails.
> @@ -142,15 +136,13 @@ static void devm_memremap_pages_release(void *data)
>  void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
>  {
>  	resource_size_t align_start, align_size, align_end;
> -	struct vmem_altmap *altmap = pgmap->altmap_valid ?
> -			&pgmap->altmap : NULL;
>  	struct resource *res = &pgmap->res;
>  	struct dev_pagemap *conflict_pgmap;
>  	struct mhp_restrictions restrictions = {
>  		/*
>  		 * We do not want any optional features only our own memmap
>  		*/
> -		.altmap = altmap,
> +		.altmap = pgmap_altmap(pgmap),
>  	};
>  	pgprot_t pgprot = PAGE_KERNEL;
>  	int error, nid, is_ram;
> @@ -274,7 +266,7 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
>  
>  		zone = &NODE_DATA(nid)->node_zones[ZONE_DEVICE];
>  		move_pfn_range_to_zone(zone, align_start >> PAGE_SHIFT,
> -				align_size >> PAGE_SHIFT, altmap);
> +				align_size >> PAGE_SHIFT, pgmap_altmap(pgmap));
>  	}
>  
>  	mem_hotplug_done();
> @@ -319,7 +311,9 @@ EXPORT_SYMBOL_GPL(devm_memunmap_pages);
>  unsigned long vmem_altmap_offset(struct vmem_altmap *altmap)
>  {
>  	/* number of pfns from base where pfn_to_page() is valid */
> -	return altmap->reserve + altmap->free;
> +	if (altmap)
> +		return altmap->reserve + altmap->free;
> +	return 0;
>  }
>  
>  void vmem_altmap_free(struct vmem_altmap *altmap, unsigned long nr_pfns)
> diff --git a/mm/hmm.c b/mm/hmm.c
> index 36e25cdbdac1..e4470462298f 100644
> --- a/mm/hmm.c
> +++ b/mm/hmm.c
> @@ -1442,7 +1442,6 @@ struct hmm_devmem *hmm_devmem_add(const struct hmm_devmem_ops *ops,
>  	devmem->pagemap.type = MEMORY_DEVICE_PRIVATE;
>  	devmem->pagemap.res = *devmem->resource;
>  	devmem->pagemap.ops = &hmm_pagemap_ops;
> -	devmem->pagemap.altmap_valid = false;
>  	devmem->pagemap.ref = &devmem->ref;
>  
>  	result = devm_memremap_pages(devmem->device, &devmem->pagemap);
> diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
> index e096c987d261..6166ba5a15f3 100644
> --- a/mm/memory_hotplug.c
> +++ b/mm/memory_hotplug.c
> @@ -557,10 +557,8 @@ void __remove_pages(struct zone *zone, unsigned long phys_start_pfn,
>  	int sections_to_remove;
>  
>  	/* In the ZONE_DEVICE case device driver owns the memory region */
> -	if (is_dev_zone(zone)) {
> -		if (altmap)
> -			map_offset = vmem_altmap_offset(altmap);
> -	}
> +	if (is_dev_zone(zone))
> +		map_offset = vmem_altmap_offset(altmap);
>  
>  	clear_zone_contiguous(zone);
>  
> diff --git a/mm/page_alloc.c b/mm/page_alloc.c
> index d66bc8abe0af..17a39d40a556 100644
> --- a/mm/page_alloc.c
> +++ b/mm/page_alloc.c
> @@ -5853,6 +5853,7 @@ void __ref memmap_init_zone_device(struct zone *zone,
>  {
>  	unsigned long pfn, end_pfn = start_pfn + size;
>  	struct pglist_data *pgdat = zone->zone_pgdat;
> +	struct vmem_altmap *altmap = pgmap_altmap(pgmap);
>  	unsigned long zone_idx = zone_idx(zone);
>  	unsigned long start = jiffies;
>  	int nid = pgdat->node_id;
> @@ -5865,9 +5866,7 @@ void __ref memmap_init_zone_device(struct zone *zone,
>  	 * of the pages reserved for the memmap, so we can just jump to
>  	 * the end of that region and start processing the device pages.
>  	 */
> -	if (pgmap->altmap_valid) {
> -		struct vmem_altmap *altmap = &pgmap->altmap;
> -
> +	if (altmap) {
>  		start_pfn = altmap->base_pfn + vmem_altmap_offset(altmap);
>  		size = end_pfn - start_pfn;
>  	}
> -- 
> 2.20.1
> 
> _______________________________________________
> Linux-nvdimm mailing list
> Linux-nvdimm@lists.01.org
> https://lists.01.org/mailman/listinfo/linux-nvdimm

  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 ` [PATCH 12/25] memremap: add a migrate_to_ram method to struct dev_pagemap_ops Christoph Hellwig
2019-06-27 16:29   ` 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 [this message]
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=20190626211300.GF4605@iweiny-DESK2.sc.intel.com \
    --to=ira.weiny@intel.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


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