[PATCH V9 44/45] nvdimm/pmem: Enable stray access protection

[ira . weiny]

From: Ira Weiny <ira.weiny@xxxxxxxxx>

The persistent memory (PMEM) driver uses the memremap_pages facility to
provide 'struct page' metadata (vmemmap) for PMEM.  Given that PMEM
capacity maybe orders of magnitude higher capacity than System RAM it
presents a large vulnerability surface to stray writes.  Unlike stray
writes to System RAM, which may result in a crash or other undesirable
behavior, stray writes to PMEM additionally are more likely to result in
permanent data loss. Reboot is not a remediation for PMEM corruption
like it is for System RAM.

Now that all valid kernel access' to PMEM have been annotated with
{__}pgmap_set_{readwrite,noaccess}() PGMAP_PROTECTION is safe to enable
in the pmem layer.

Set PGMAP_PROTECTION if pgmap protections are available and set the
pgmap property of the dax device for it's use.

Internally, the pmem driver uses a cached virtual address,
pmem->virt_addr (pmem_addr).  Call __pgmap_set_{readwrite,noaccess}()
directly when PGMAP_PROTECTION is active on those mappings.

Signed-off-by: Ira Weiny <ira.weiny@xxxxxxxxx>

---
Changes for V9
	Remove the dax operations and pass the pgmap to the dax_device
		for its use.
	s/pgmap_mk_*/pgmap_set_*/
	s/pmem_mk_*/pmem_set_*/

Changes for V8
	Rebase to 5.17-rc1
	Remove global param
	Add internal structure which uses the pmem device and pgmap
		device directly in the *_mk_*() calls.
	Add pmem dax ops callbacks
	Use pgmap_protection_available()
	s/PGMAP_PKEY_PROTECT/PGMAP_PROTECTION
---
 drivers/nvdimm/pmem.c | 26 ++++++++++++++++++++++++++
 1 file changed, 26 insertions(+)

diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index 58d95242a836..2c7b18da7974 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -138,6 +138,18 @@ static blk_status_t read_pmem(struct page *page, unsigned int off,
 	return BLK_STS_OK;
 }
 
+static void pmem_set_readwrite(struct pmem_device *pmem)
+{
+	if (pmem->pgmap.flags & PGMAP_PROTECTION)
+		__pgmap_set_readwrite(&pmem->pgmap);
+}
+
+static void pmem_set_noaccess(struct pmem_device *pmem)
+{
+	if (pmem->pgmap.flags & PGMAP_PROTECTION)
+		__pgmap_set_noaccess(&pmem->pgmap);
+}
+
 static blk_status_t pmem_do_read(struct pmem_device *pmem,
 			struct page *page, unsigned int page_off,
 			sector_t sector, unsigned int len)
@@ -149,7 +161,11 @@ static blk_status_t pmem_do_read(struct pmem_device *pmem,
 	if (unlikely(is_bad_pmem(&pmem->bb, sector, len)))
 		return BLK_STS_IOERR;
 
+	/* Enable direct use of pmem->virt_addr */
+	pmem_set_readwrite(pmem);
 	rc = read_pmem(page, page_off, pmem_addr, len);
+	pmem_set_noaccess(pmem);
+
 	flush_dcache_page(page);
 	return rc;
 }
@@ -181,11 +197,15 @@ static blk_status_t pmem_do_write(struct pmem_device *pmem,
 	 * after clear poison.
 	 */
 	flush_dcache_page(page);
+
+	/* Enable direct use of pmem->virt_addr */
+	pmem_set_readwrite(pmem);
 	write_pmem(pmem_addr, page, page_off, len);
 	if (unlikely(bad_pmem)) {
 		rc = pmem_clear_poison(pmem, pmem_off, len);
 		write_pmem(pmem_addr, page, page_off, len);
 	}
+	pmem_set_noaccess(pmem);
 
 	return rc;
 }
@@ -427,6 +447,8 @@ static int pmem_attach_disk(struct device *dev,
 	pmem->pfn_flags = PFN_DEV;
 	if (is_nd_pfn(dev)) {
 		pmem->pgmap.type = MEMORY_DEVICE_FS_DAX;
+		if (pgmap_protection_available())
+			pmem->pgmap.flags |= PGMAP_PROTECTION;
 		addr = devm_memremap_pages(dev, &pmem->pgmap);
 		pfn_sb = nd_pfn->pfn_sb;
 		pmem->data_offset = le64_to_cpu(pfn_sb->dataoff);
@@ -440,6 +462,8 @@ static int pmem_attach_disk(struct device *dev,
 		pmem->pgmap.range.end = res->end;
 		pmem->pgmap.nr_range = 1;
 		pmem->pgmap.type = MEMORY_DEVICE_FS_DAX;
+		if (pgmap_protection_available())
+			pmem->pgmap.flags |= PGMAP_PROTECTION;
 		addr = devm_memremap_pages(dev, &pmem->pgmap);
 		pmem->pfn_flags |= PFN_MAP;
 		bb_range = pmem->pgmap.range;
@@ -481,6 +505,8 @@ static int pmem_attach_disk(struct device *dev,
 	}
 	set_dax_nocache(dax_dev);
 	set_dax_nomc(dax_dev);
+	if (pmem->pgmap.flags & PGMAP_PROTECTION)
+		set_dax_pgmap(dax_dev, &pmem->pgmap);
 	if (is_nvdimm_sync(nd_region))
 		set_dax_synchronous(dax_dev);
 	rc = dax_add_host(dax_dev, disk);
-- 
2.35.1