Re: [PATCH v2 18/30] virtio_fs, dax: Set up virtio_fs dax_device

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



On Wed, 15 May 2019 15:27:03 -0400
Vivek Goyal <vgoyal@xxxxxxxxxx> wrote:

> From: Stefan Hajnoczi <stefanha@xxxxxxxxxx>
> 
> Setup a dax device.
> 
> Use the shm capability to find the cache entry and map it.
> 
> The DAX window is accessed by the fs/dax.c infrastructure and must have
> struct pages (at least on x86).  Use devm_memremap_pages() to map the
> DAX window PCI BAR and allocate struct page.
>

Sorry for being this late. I don't see any more recent version so I will
comment here.

I'm trying to figure out how is this supposed to work on s390. My concern
is, that on s390 PCI memory needs to be accessed by special
instructions. This is taken care of by the stuff defined in
arch/s390/include/asm/io.h. E.g. we 'override' __raw_writew so it uses
the appropriate s390 instruction. However if the code does not use the
linux abstractions for accessing PCI memory, but assumes it can be
accessed like RAM, we have a problem.

Looking at this patch, it seems to me, that we might end up with exactly
the case described. For example AFAICT copy_to_iter() (3) resolves to
the function in lib/iov_iter.c which does not seem to cater for s390
oddities.

I didn't have the time to investigate this properly, and since virtio-fs
is virtual, we may be able to get around what is otherwise a
limitation on s390. My understanding of these areas is admittedly
shallow, and since I'm not sure I'll have much more time to
invest in the near future I decided to raise concern.

Any opinions?

[CCing some s390 people who are probably more knowledgeable than my on
these matters.]

Regards,
Halil


> Signed-off-by: Stefan Hajnoczi <stefanha@xxxxxxxxxx>
> Signed-off-by: Dr. David Alan Gilbert <dgilbert@xxxxxxxxxx>
> Signed-off-by: Vivek Goyal <vgoyal@xxxxxxxxxx>
> Signed-off-by: Sebastien Boeuf <sebastien.boeuf@xxxxxxxxx>
> Signed-off-by: Liu Bo <bo.liu@xxxxxxxxxxxxxxxxx>
> ---

[..]
  
> +/* Map a window offset to a page frame number.  The window offset will have
> + * been produced by .iomap_begin(), which maps a file offset to a window
> + * offset.
> + */
> +static long virtio_fs_direct_access(struct dax_device *dax_dev, pgoff_t pgoff,
> +				    long nr_pages, void **kaddr, pfn_t *pfn)
> +{
> +	struct virtio_fs *fs = dax_get_private(dax_dev);
> +	phys_addr_t offset = PFN_PHYS(pgoff);
> +	size_t max_nr_pages = fs->window_len/PAGE_SIZE - pgoff;
> +
> +	if (kaddr)
> +		*kaddr = fs->window_kaddr + offset;

(2) Here we use fs->window_kaddr, basically directing the access to the
virtio shared memory region.

> +	if (pfn)
> +		*pfn = phys_to_pfn_t(fs->window_phys_addr + offset,
> +					PFN_DEV | PFN_MAP);
> +	return nr_pages > max_nr_pages ? max_nr_pages : nr_pages;
> +}
> +
> +static size_t virtio_fs_copy_from_iter(struct dax_device *dax_dev,
> +				       pgoff_t pgoff, void *addr,
> +				       size_t bytes, struct iov_iter *i)
> +{
> +	return copy_from_iter(addr, bytes, i);
> +}
> +
> +static size_t virtio_fs_copy_to_iter(struct dax_device *dax_dev,
> +				       pgoff_t pgoff, void *addr,
> +				       size_t bytes, struct iov_iter *i)
> +{
> +	return copy_to_iter(addr, bytes, i);

(3) And this should be the access to it. Which does not seem to use.

> +}
> +
> +static const struct dax_operations virtio_fs_dax_ops = {
> +	.direct_access = virtio_fs_direct_access,
> +	.copy_from_iter = virtio_fs_copy_from_iter,
> +	.copy_to_iter = virtio_fs_copy_to_iter,
> +};
> +
> +static void virtio_fs_percpu_release(struct percpu_ref *ref)
> +{
> +	struct virtio_fs_memremap_info *mi =
> +		container_of(ref, struct virtio_fs_memremap_info, ref);
> +
> +	complete(&mi->completion);
> +}
> +
> +static void virtio_fs_percpu_exit(void *data)
> +{
> +	struct virtio_fs_memremap_info *mi = data;
> +
> +	wait_for_completion(&mi->completion);
> +	percpu_ref_exit(&mi->ref);
> +}
> +
> +static void virtio_fs_percpu_kill(struct percpu_ref *ref)
> +{
> +	percpu_ref_kill(ref);
> +}
> +
> +static void virtio_fs_cleanup_dax(void *data)
> +{
> +	struct virtio_fs *fs = data;
> +
> +	kill_dax(fs->dax_dev);
> +	put_dax(fs->dax_dev);
> +}
> +
> +static int virtio_fs_setup_dax(struct virtio_device *vdev, struct virtio_fs *fs)
> +{
> +	struct virtio_shm_region cache_reg;
> +	struct virtio_fs_memremap_info *mi;
> +	struct dev_pagemap *pgmap;
> +	bool have_cache;
> +	int ret;
> +
> +	if (!IS_ENABLED(CONFIG_DAX_DRIVER))
> +		return 0;
> +
> +	/* Get cache region */
> +	have_cache = virtio_get_shm_region(vdev,
> +					   &cache_reg,
> +					   (u8)VIRTIO_FS_SHMCAP_ID_CACHE);
> +	if (!have_cache) {
> +		dev_err(&vdev->dev, "%s: No cache capability\n", __func__);
> +		return -ENXIO;
> +	} else {
> +		dev_notice(&vdev->dev, "Cache len: 0x%llx @ 0x%llx\n",
> +			   cache_reg.len, cache_reg.addr);
> +	}
> +
> +	mi = devm_kzalloc(&vdev->dev, sizeof(*mi), GFP_KERNEL);
> +	if (!mi)
> +		return -ENOMEM;
> +
> +	init_completion(&mi->completion);
> +	ret = percpu_ref_init(&mi->ref, virtio_fs_percpu_release, 0,
> +			      GFP_KERNEL);
> +	if (ret < 0) {
> +		dev_err(&vdev->dev, "%s: percpu_ref_init failed (%d)\n",
> +			__func__, ret);
> +		return ret;
> +	}
> +
> +	ret = devm_add_action(&vdev->dev, virtio_fs_percpu_exit, mi);
> +	if (ret < 0) {
> +		percpu_ref_exit(&mi->ref);
> +		return ret;
> +	}
> +
> +	pgmap = &mi->pgmap;
> +	pgmap->altmap_valid = false;
> +	pgmap->ref = &mi->ref;
> +	pgmap->kill = virtio_fs_percpu_kill;
> +	pgmap->type = MEMORY_DEVICE_FS_DAX;
> +
> +	/* Ideally we would directly use the PCI BAR resource but
> +	 * devm_memremap_pages() wants its own copy in pgmap.  So
> +	 * initialize a struct resource from scratch (only the start
> +	 * and end fields will be used).
> +	 */
> +	pgmap->res = (struct resource){
> +		.name = "virtio-fs dax window",
> +		.start = (phys_addr_t) cache_reg.addr,
> +		.end = (phys_addr_t) cache_reg.addr + cache_reg.len - 1,
> +	};
> +
> +	fs->window_kaddr = devm_memremap_pages(&vdev->dev, pgmap);

(1) Here we assign fs->window_kaddr basically from the virtio shm region.

> +	if (IS_ERR(fs->window_kaddr))
> +		return PTR_ERR(fs->window_kaddr);
> +
> +	fs->window_phys_addr = (phys_addr_t) cache_reg.addr;
> +	fs->window_len = (phys_addr_t) cache_reg.len;
> +
> +	dev_dbg(&vdev->dev, "%s: window kaddr 0x%px phys_addr 0x%llx"
> +		" len 0x%llx\n", __func__, fs->window_kaddr, cache_reg.addr,
> +		cache_reg.len);
> +
> +	fs->dax_dev = alloc_dax(fs, NULL, &virtio_fs_dax_ops);
> +	if (!fs->dax_dev)
> +		return -ENOMEM;
> +
> +	return devm_add_action_or_reset(&vdev->dev, virtio_fs_cleanup_dax, fs);
> +}
> +

[..]




[Index of Archives]     [Linux Ext4 Filesystem]     [Union Filesystem]     [Filesystem Testing]     [Ceph Users]     [Ecryptfs]     [AutoFS]     [Kernel Newbies]     [Share Photos]     [Security]     [Netfilter]     [Bugtraq]     [Yosemite News]     [MIPS Linux]     [ARM Linux]     [Linux Security]     [Linux Cachefs]     [Reiser Filesystem]     [Linux RAID]     [Samba]     [Device Mapper]     [CEPH Development]

  Powered by Linux