| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <CAPcyv4ij8VxaeosTsRFgUTnSpRRaxWnxWK6xvUJrhmT-7ae+-Q@mail.gmail.com>
Date: Mon, 11 Apr 2022 17:08:21 -0700
From: Dan Williams <dan.j.williams@...el.com>
To: Jane Chu <jane.chu@...cle.com>
Cc: david <david@...morbit.com>, "Darrick J. Wong" <djwong@...nel.org>,
Christoph Hellwig <hch@...radead.org>,
Vishal L Verma <vishal.l.verma@...el.com>,
Dave Jiang <dave.jiang@...el.com>,
Alasdair Kergon <agk@...hat.com>,
Mike Snitzer <snitzer@...hat.com>,
device-mapper development <dm-devel@...hat.com>,
"Weiny, Ira" <ira.weiny@...el.com>,
Matthew Wilcox <willy@...radead.org>,
Vivek Goyal <vgoyal@...hat.com>,
linux-fsdevel <linux-fsdevel@...r.kernel.org>,
Linux NVDIMM <nvdimm@...ts.linux.dev>,
Linux Kernel Mailing List <linux-kernel@...r.kernel.org>,
linux-xfs <linux-xfs@...r.kernel.org>, X86 ML <x86@...nel.org>
Subject: Re: [PATCH v7 4/6] dax: add DAX_RECOVERY flag and .recovery_write dev_pgmap_ops
On Tue, Apr 5, 2022 at 12:48 PM Jane Chu <jane.chu@...cle.com> wrote:
>
> Introduce DAX_RECOVERY flag to dax_direct_access(). The flag is
> not set by default in dax_direct_access() such that the helper
> does not translate a pmem range to kernel virtual address if the
> range contains uncorrectable errors. When the flag is set,
> the helper ignores the UEs and return kernel virtual adderss so
> that the caller may get on with data recovery via write.
>
> Also introduce a new dev_pagemap_ops .recovery_write function.
> The function is applicable to FSDAX device only. The device
> page backend driver provides .recovery_write function if the
> device has underlying mechanism to clear the uncorrectable
> errors on the fly.
>
> Signed-off-by: Jane Chu <jane.chu@...cle.com>
> ---
> drivers/dax/super.c | 17 ++++++++--
> drivers/md/dm-linear.c | 4 +--
> drivers/md/dm-log-writes.c | 5 +--
> drivers/md/dm-stripe.c | 4 +--
> drivers/md/dm-target.c | 2 +-
> drivers/md/dm-writecache.c | 5 +--
> drivers/md/dm.c | 5 +--
> drivers/nvdimm/pmem.c | 57 +++++++++++++++++++++++++++------
> drivers/nvdimm/pmem.h | 2 +-
> drivers/s390/block/dcssblk.c | 4 +--
> fs/dax.c | 24 ++++++++++----
> fs/fuse/dax.c | 4 +--
> include/linux/dax.h | 11 +++++--
> include/linux/device-mapper.h | 2 +-
> include/linux/memremap.h | 7 ++++
> tools/testing/nvdimm/pmem-dax.c | 2 +-
> 16 files changed, 116 insertions(+), 39 deletions(-)
>
> diff --git a/drivers/dax/super.c b/drivers/dax/super.c
> index 0211e6f7b47a..8252858cd25a 100644
> --- a/drivers/dax/super.c
> +++ b/drivers/dax/super.c
> @@ -13,6 +13,7 @@
> #include <linux/uio.h>
> #include <linux/dax.h>
> #include <linux/fs.h>
> +#include <linux/memremap.h>
> #include "dax-private.h"
>
> /**
> @@ -117,6 +118,7 @@ enum dax_device_flags {
> * @dax_dev: a dax_device instance representing the logical memory range
> * @pgoff: offset in pages from the start of the device to translate
> * @nr_pages: number of consecutive pages caller can handle relative to @pfn
> + * @flags: by default 0, set to DAX_RECOVERY to kick start dax recovery
> * @kaddr: output parameter that returns a virtual address mapping of pfn
> * @pfn: output parameter that returns an absolute pfn translation of @pgoff
> *
> @@ -124,7 +126,7 @@ enum dax_device_flags {
> * pages accessible at the device relative @pgoff.
> */
> long dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, long nr_pages,
> - void **kaddr, pfn_t *pfn)
> + int flags, void **kaddr, pfn_t *pfn)
> {
> long avail;
>
> @@ -137,7 +139,7 @@ long dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, long nr_pages,
> if (nr_pages < 0)
> return -EINVAL;
>
> - avail = dax_dev->ops->direct_access(dax_dev, pgoff, nr_pages,
> + avail = dax_dev->ops->direct_access(dax_dev, pgoff, nr_pages, flags,
> kaddr, pfn);
> if (!avail)
> return -ERANGE;
> @@ -194,6 +196,17 @@ int dax_zero_page_range(struct dax_device *dax_dev, pgoff_t pgoff,
> }
> EXPORT_SYMBOL_GPL(dax_zero_page_range);
>
> +size_t dax_recovery_write(struct dax_device *dax_dev, pgoff_t pgoff,
> + pfn_t pfn, void *addr, size_t bytes, struct iov_iter *iter)
> +{
> + struct dev_pagemap *pgmap = get_dev_pagemap(pfn_t_to_pfn(pfn), NULL);
> +
> + if (!pgmap || !pgmap->ops || !pgmap->ops->recovery_write)
> + return 0;
> + return pgmap->ops->recovery_write(pgmap, pgoff, addr, bytes, iter);
> +}
> +EXPORT_SYMBOL_GPL(dax_recovery_write);
> +
> #ifdef CONFIG_ARCH_HAS_PMEM_API
> void arch_wb_cache_pmem(void *addr, size_t size);
> void dax_flush(struct dax_device *dax_dev, void *addr, size_t size)
> diff --git a/drivers/md/dm-linear.c b/drivers/md/dm-linear.c
> index 76b486e4d2be..9e6d8bdf3b2a 100644
> --- a/drivers/md/dm-linear.c
> +++ b/drivers/md/dm-linear.c
> @@ -172,11 +172,11 @@ static struct dax_device *linear_dax_pgoff(struct dm_target *ti, pgoff_t *pgoff)
> }
>
> static long linear_dax_direct_access(struct dm_target *ti, pgoff_t pgoff,
> - long nr_pages, void **kaddr, pfn_t *pfn)
> + long nr_pages, int flags, void **kaddr, pfn_t *pfn)
> {
> struct dax_device *dax_dev = linear_dax_pgoff(ti, &pgoff);
>
> - return dax_direct_access(dax_dev, pgoff, nr_pages, kaddr, pfn);
> + return dax_direct_access(dax_dev, pgoff, nr_pages, flags, kaddr, pfn);
> }
>
> static int linear_dax_zero_page_range(struct dm_target *ti, pgoff_t pgoff,
> diff --git a/drivers/md/dm-log-writes.c b/drivers/md/dm-log-writes.c
> index c9d036d6bb2e..e23f062ade5f 100644
> --- a/drivers/md/dm-log-writes.c
> +++ b/drivers/md/dm-log-writes.c
> @@ -889,11 +889,12 @@ static struct dax_device *log_writes_dax_pgoff(struct dm_target *ti,
> }
>
> static long log_writes_dax_direct_access(struct dm_target *ti, pgoff_t pgoff,
> - long nr_pages, void **kaddr, pfn_t *pfn)
> + long nr_pages, int flags,
> + void **kaddr, pfn_t *pfn)
> {
> struct dax_device *dax_dev = log_writes_dax_pgoff(ti, &pgoff);
>
> - return dax_direct_access(dax_dev, pgoff, nr_pages, kaddr, pfn);
> + return dax_direct_access(dax_dev, pgoff, nr_pages, flags, kaddr, pfn);
> }
>
> static int log_writes_dax_zero_page_range(struct dm_target *ti, pgoff_t pgoff,
> diff --git a/drivers/md/dm-stripe.c b/drivers/md/dm-stripe.c
> index c81d331d1afe..b89339c78702 100644
> --- a/drivers/md/dm-stripe.c
> +++ b/drivers/md/dm-stripe.c
> @@ -315,11 +315,11 @@ static struct dax_device *stripe_dax_pgoff(struct dm_target *ti, pgoff_t *pgoff)
> }
>
> static long stripe_dax_direct_access(struct dm_target *ti, pgoff_t pgoff,
> - long nr_pages, void **kaddr, pfn_t *pfn)
> + long nr_pages, int flags, void **kaddr, pfn_t *pfn)
> {
> struct dax_device *dax_dev = stripe_dax_pgoff(ti, &pgoff);
>
> - return dax_direct_access(dax_dev, pgoff, nr_pages, kaddr, pfn);
> + return dax_direct_access(dax_dev, pgoff, nr_pages, flags, kaddr, pfn);
> }
>
> static int stripe_dax_zero_page_range(struct dm_target *ti, pgoff_t pgoff,
> diff --git a/drivers/md/dm-target.c b/drivers/md/dm-target.c
> index 64dd0b34fcf4..24b1e5628f3a 100644
> --- a/drivers/md/dm-target.c
> +++ b/drivers/md/dm-target.c
> @@ -142,7 +142,7 @@ static void io_err_release_clone_rq(struct request *clone,
> }
>
> static long io_err_dax_direct_access(struct dm_target *ti, pgoff_t pgoff,
> - long nr_pages, void **kaddr, pfn_t *pfn)
> + long nr_pages, int flags, void **kaddr, pfn_t *pfn)
> {
> return -EIO;
> }
> diff --git a/drivers/md/dm-writecache.c b/drivers/md/dm-writecache.c
> index 5630b470ba42..180ca8fa383e 100644
> --- a/drivers/md/dm-writecache.c
> +++ b/drivers/md/dm-writecache.c
> @@ -286,7 +286,8 @@ static int persistent_memory_claim(struct dm_writecache *wc)
>
> id = dax_read_lock();
>
> - da = dax_direct_access(wc->ssd_dev->dax_dev, offset, p, &wc->memory_map, &pfn);
> + da = dax_direct_access(wc->ssd_dev->dax_dev, offset, p, 0,
> + &wc->memory_map, &pfn);
> if (da < 0) {
> wc->memory_map = NULL;
> r = da;
> @@ -309,7 +310,7 @@ static int persistent_memory_claim(struct dm_writecache *wc)
> do {
> long daa;
> daa = dax_direct_access(wc->ssd_dev->dax_dev, offset + i, p - i,
> - NULL, &pfn);
> + 0, NULL, &pfn);
> if (daa <= 0) {
> r = daa ? daa : -EINVAL;
> goto err3;
> diff --git a/drivers/md/dm.c b/drivers/md/dm.c
> index ad2e0bbeb559..a8c697bb6603 100644
> --- a/drivers/md/dm.c
> +++ b/drivers/md/dm.c
> @@ -1087,7 +1087,8 @@ static struct dm_target *dm_dax_get_live_target(struct mapped_device *md,
> }
>
> static long dm_dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff,
> - long nr_pages, void **kaddr, pfn_t *pfn)
> + long nr_pages, int flags, void **kaddr,
> + pfn_t *pfn)
> {
> struct mapped_device *md = dax_get_private(dax_dev);
> sector_t sector = pgoff * PAGE_SECTORS;
> @@ -1105,7 +1106,7 @@ static long dm_dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff,
> if (len < 1)
> goto out;
> nr_pages = min(len, nr_pages);
> - ret = ti->type->direct_access(ti, pgoff, nr_pages, kaddr, pfn);
> + ret = ti->type->direct_access(ti, pgoff, nr_pages, flags, kaddr, pfn);
>
> out:
> dm_put_live_table(md, srcu_idx);
> diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
> index 30c71a68175b..0400c5a7ba39 100644
> --- a/drivers/nvdimm/pmem.c
> +++ b/drivers/nvdimm/pmem.c
> @@ -238,12 +238,23 @@ static int pmem_rw_page(struct block_device *bdev, sector_t sector,
>
> /* see "strong" declaration in tools/testing/nvdimm/pmem-dax.c */
> __weak long __pmem_direct_access(struct pmem_device *pmem, pgoff_t pgoff,
> - long nr_pages, void **kaddr, pfn_t *pfn)
> + long nr_pages, int flags, void **kaddr, pfn_t *pfn)
> {
> resource_size_t offset = PFN_PHYS(pgoff) + pmem->data_offset;
> + sector_t sector = PFN_PHYS(pgoff) >> SECTOR_SHIFT;
> + unsigned int num = PFN_PHYS(nr_pages) >> SECTOR_SHIFT;
> + struct badblocks *bb = &pmem->bb;
> + sector_t first_bad;
> + int num_bad;
> + bool bad_in_range;
> + long actual_nr;
> +
> + if (!bb->count)
> + bad_in_range = false;
> + else
> + bad_in_range = !!badblocks_check(bb, sector, num, &first_bad, &num_bad);
Why all this change...
>
> - if (unlikely(is_bad_pmem(&pmem->bb, PFN_PHYS(pgoff) / 512,
> - PFN_PHYS(nr_pages))))
...instead of adding "&& !(flags & DAX_RECOVERY)" to this statement?
> + if (bad_in_range && !(flags & DAX_RECOVERY))
> return -EIO;
>
> if (kaddr)
> @@ -251,13 +262,26 @@ __weak long __pmem_direct_access(struct pmem_device *pmem, pgoff_t pgoff,
> if (pfn)
> *pfn = phys_to_pfn_t(pmem->phys_addr + offset, pmem->pfn_flags);
>
> + if (!bad_in_range) {
> + /*
> + * If badblock is present but not in the range, limit known good range
> + * to the requested range.
> + */
> + if (bb->count)
> + return nr_pages;
> + return PHYS_PFN(pmem->size - pmem->pfn_pad - offset);
> + }
> +
> /*
> - * If badblocks are present, limit known good range to the
> - * requested range.
> + * In case poison is found in the given range and DAX_RECOVERY flag is set,
> + * recovery stride is set to kernel page size because the underlying driver and
> + * firmware clear poison functions don't appear to handle large chunk (such as
> + * 2MiB) reliably.
> */
> - if (unlikely(pmem->bb.count))
> - return nr_pages;
> - return PHYS_PFN(pmem->size - pmem->pfn_pad - offset);
> + actual_nr = PHYS_PFN(PAGE_ALIGN((first_bad - sector) << SECTOR_SHIFT));
> + dev_dbg(pmem->bb.dev, "start sector(%llu), nr_pages(%ld), first_bad(%llu), actual_nr(%ld)\n",
> + sector, nr_pages, first_bad, actual_nr);
> + return (actual_nr == 0) ? 1 : actual_nr;
Similar feedback as above that this is more change than I would expect.
I think just adding...
if (flags & DAX_RECOVERY)
return 1;
...before the typical return path is enough.
Powered by blists - more mailing lists