From: Vishal Verma <vishal.l.verma@intel.com> To: linux-nvdimm@lists.01.org Cc: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>, linux-acpi@vger.kernel.org Subject: [PATCH 2/3] pmem: reduce kmap_atomic sections to the memcpys only Date: Fri, 30 Sep 2016 17:19:30 -0600 [thread overview] Message-ID: <1475277571-10152-3-git-send-email-vishal.l.verma@intel.com> (raw) In-Reply-To: <1475277571-10152-1-git-send-email-vishal.l.verma@intel.com> pmem_do_bvec used to kmap_atomic at the begin, and only unmap at the end. Things like nvdimm_clear_poison may want to do nvdimm subsystem bookkeeping operations that may involve taking locks or doing memory allocations, and we can't do that from the atomic context. Reduce the atomic context to just what needs it - the memcpy to/from pmem. Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Signed-off-by: Vishal Verma <vishal.l.verma@intel.com> --- drivers/nvdimm/pmem.c | 28 +++++++++++++++++++++++----- 1 file changed, 23 insertions(+), 5 deletions(-) diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c index 571a6c7..42b3a82 100644 --- a/drivers/nvdimm/pmem.c +++ b/drivers/nvdimm/pmem.c @@ -66,13 +66,32 @@ static void pmem_clear_poison(struct pmem_device *pmem, phys_addr_t offset, invalidate_pmem(pmem->virt_addr + offset, len); } +static void write_pmem(void *pmem_addr, struct page *page, + unsigned int off, unsigned int len) +{ + void *mem = kmap_atomic(page); + + memcpy_to_pmem(pmem_addr, mem + off, len); + kunmap_atomic(mem); +} + +static int read_pmem(struct page *page, unsigned int off, + void *pmem_addr, unsigned int len) +{ + int rc; + void *mem = kmap_atomic(page); + + rc = memcpy_from_pmem(mem + off, pmem_addr, len); + kunmap_atomic(mem); + return rc; +} + static int pmem_do_bvec(struct pmem_device *pmem, struct page *page, unsigned int len, unsigned int off, bool is_write, sector_t sector) { int rc = 0; bool bad_pmem = false; - void *mem = kmap_atomic(page); phys_addr_t pmem_off = sector * 512 + pmem->data_offset; void *pmem_addr = pmem->virt_addr + pmem_off; @@ -83,7 +102,7 @@ static int pmem_do_bvec(struct pmem_device *pmem, struct page *page, if (unlikely(bad_pmem)) rc = -EIO; else { - rc = memcpy_from_pmem(mem + off, pmem_addr, len); + rc = read_pmem(page, off, pmem_addr, len); flush_dcache_page(page); } } else { @@ -102,14 +121,13 @@ static int pmem_do_bvec(struct pmem_device *pmem, struct page *page, * after clear poison. */ flush_dcache_page(page); - memcpy_to_pmem(pmem_addr, mem + off, len); + write_pmem(pmem_addr, page, off, len); if (unlikely(bad_pmem)) { pmem_clear_poison(pmem, pmem_off, len); - memcpy_to_pmem(pmem_addr, mem + off, len); + write_pmem(pmem_addr, page, off, len); } } - kunmap_atomic(mem); return rc; } -- 2.7.4 _______________________________________________ Linux-nvdimm mailing list Linux-nvdimm@lists.01.org https://lists.01.org/mailman/listinfo/linux-nvdimm
WARNING: multiple messages have this Message-ID (diff)
From: Vishal Verma <vishal.l.verma@intel.com> To: linux-nvdimm@lists.01.org Cc: Dan Williams <dan.j.williams@intel.com>, Ross Zwisler <ross.zwisler@linux.intel.com>, Linda Knippers <linda.knippers@hpe.com>, linux-acpi@vger.kernel.org, "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>, Vishal Verma <vishal.l.verma@intel.com> Subject: [PATCH 2/3] pmem: reduce kmap_atomic sections to the memcpys only Date: Fri, 30 Sep 2016 17:19:30 -0600 [thread overview] Message-ID: <1475277571-10152-3-git-send-email-vishal.l.verma@intel.com> (raw) In-Reply-To: <1475277571-10152-1-git-send-email-vishal.l.verma@intel.com> pmem_do_bvec used to kmap_atomic at the begin, and only unmap at the end. Things like nvdimm_clear_poison may want to do nvdimm subsystem bookkeeping operations that may involve taking locks or doing memory allocations, and we can't do that from the atomic context. Reduce the atomic context to just what needs it - the memcpy to/from pmem. Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Signed-off-by: Vishal Verma <vishal.l.verma@intel.com> --- drivers/nvdimm/pmem.c | 28 +++++++++++++++++++++++----- 1 file changed, 23 insertions(+), 5 deletions(-) diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c index 571a6c7..42b3a82 100644 --- a/drivers/nvdimm/pmem.c +++ b/drivers/nvdimm/pmem.c @@ -66,13 +66,32 @@ static void pmem_clear_poison(struct pmem_device *pmem, phys_addr_t offset, invalidate_pmem(pmem->virt_addr + offset, len); } +static void write_pmem(void *pmem_addr, struct page *page, + unsigned int off, unsigned int len) +{ + void *mem = kmap_atomic(page); + + memcpy_to_pmem(pmem_addr, mem + off, len); + kunmap_atomic(mem); +} + +static int read_pmem(struct page *page, unsigned int off, + void *pmem_addr, unsigned int len) +{ + int rc; + void *mem = kmap_atomic(page); + + rc = memcpy_from_pmem(mem + off, pmem_addr, len); + kunmap_atomic(mem); + return rc; +} + static int pmem_do_bvec(struct pmem_device *pmem, struct page *page, unsigned int len, unsigned int off, bool is_write, sector_t sector) { int rc = 0; bool bad_pmem = false; - void *mem = kmap_atomic(page); phys_addr_t pmem_off = sector * 512 + pmem->data_offset; void *pmem_addr = pmem->virt_addr + pmem_off; @@ -83,7 +102,7 @@ static int pmem_do_bvec(struct pmem_device *pmem, struct page *page, if (unlikely(bad_pmem)) rc = -EIO; else { - rc = memcpy_from_pmem(mem + off, pmem_addr, len); + rc = read_pmem(page, off, pmem_addr, len); flush_dcache_page(page); } } else { @@ -102,14 +121,13 @@ static int pmem_do_bvec(struct pmem_device *pmem, struct page *page, * after clear poison. */ flush_dcache_page(page); - memcpy_to_pmem(pmem_addr, mem + off, len); + write_pmem(pmem_addr, page, off, len); if (unlikely(bad_pmem)) { pmem_clear_poison(pmem, pmem_off, len); - memcpy_to_pmem(pmem_addr, mem + off, len); + write_pmem(pmem_addr, page, off, len); } } - kunmap_atomic(mem); return rc; } -- 2.7.4
next prev parent reply other threads:[~2016-09-30 23:20 UTC|newest] Thread overview: 10+ messages / expand[flat|nested] mbox.gz Atom feed top 2016-09-30 23:19 [PATCH 0/3] misc updates for Address Range Scrub Vishal Verma 2016-09-30 23:19 ` Vishal Verma 2016-09-30 23:19 ` [PATCH 1/3] nfit: don't start a full scrub by default for an MCE Vishal Verma 2016-09-30 23:19 ` Vishal Verma 2016-09-30 23:19 ` Vishal Verma [this message] 2016-09-30 23:19 ` [PATCH 2/3] pmem: reduce kmap_atomic sections to the memcpys only Vishal Verma 2016-09-30 23:19 ` [PATCH 3/3] libnvdimm: clear the internal poison_list when clearing badblocks Vishal Verma 2016-09-30 23:19 ` Vishal Verma -- strict thread matches above, loose matches on Subject: below -- 2016-09-29 0:10 [PATCH 0/3] misc updates for Address Range Scrub Vishal Verma 2016-09-29 0:10 ` [PATCH 2/3] pmem: reduce kmap_atomic sections to the memcpys only Vishal Verma 2016-09-29 0:10 ` Vishal Verma
Reply instructions: You may reply publicly 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=1475277571-10152-3-git-send-email-vishal.l.verma@intel.com \ --to=vishal.l.verma@intel.com \ --cc=linux-acpi@vger.kernel.org \ --cc=linux-nvdimm@lists.01.org \ --cc=rafael.j.wysocki@intel.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: linkBe sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes, see mirroring instructions on how to clone and mirror all data and code used by this external index.