libnvdimm, pmem: Restore page attributes when clearing errors

Use clear_mce_nospec() to restore WB mode for the kernel linear mapping
of a pmem page that was marked 'HWPoison'. A page with 'HWPoison' set
has also been marked UC in PAT (page attribute table) via
set_mce_nospec() to prevent speculative retrievals of poison.

The 'HWPoison' flag is only cleared when overwriting an entire page.

Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Dave Jiang <dave.jiang@intel.com>

diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index 8b1fd7f1a224eedebf08cddfe2258949c50a6bcf..55c7a69751d39306659e906af9b0c49fb344a042 100644 (file)
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -20,6 +20,7 @@
 #include <linux/hdreg.h>
 #include <linux/init.h>
 #include <linux/platform_device.h>
+#include <linux/set_memory.h>
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/badblocks.h>
@@ -51,6 +52,30 @@ static struct nd_region *to_region(struct pmem_device *pmem)
        return to_nd_region(to_dev(pmem)->parent);
 }
 
+static void hwpoison_clear(struct pmem_device *pmem,
+               phys_addr_t phys, unsigned int len)
+{
+       unsigned long pfn_start, pfn_end, pfn;
+
+       /* only pmem in the linear map supports HWPoison */
+       if (is_vmalloc_addr(pmem->virt_addr))
+               return;
+
+       pfn_start = PHYS_PFN(phys);
+       pfn_end = pfn_start + PHYS_PFN(len);
+       for (pfn = pfn_start; pfn < pfn_end; pfn++) {
+               struct page *page = pfn_to_page(pfn);
+
+               /*
+                * Note, no need to hold a get_dev_pagemap() reference
+                * here since we're in the driver I/O path and
+                * outstanding I/O requests pin the dev_pagemap.
+                */
+               if (test_and_clear_pmem_poison(page))
+                       clear_mce_nospec(pfn);
+       }
+}
+
 static blk_status_t pmem_clear_poison(struct pmem_device *pmem,
                phys_addr_t offset, unsigned int len)
 {
@@ -65,6 +90,7 @@ static blk_status_t pmem_clear_poison(struct pmem_device *pmem,
        if (cleared < len)
                rc = BLK_STS_IOERR;
        if (cleared > 0 && cleared / 512) {
+               hwpoison_clear(pmem, pmem->phys_addr + offset, cleared);
                cleared /= 512;
                dev_dbg(dev, "%#llx clear %ld sector%s\n",
                                (unsigned long long) sector, cleared,

diff --git a/drivers/nvdimm/pmem.h b/drivers/nvdimm/pmem.h
index a64ebc78b5dffbac4072fc722d9961650e681f88..59cfe13ea8a85c3bcccf9211409ae237196626d5 100644 (file)
--- a/drivers/nvdimm/pmem.h
+++ b/drivers/nvdimm/pmem.h
@@ -1,6 +1,7 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __NVDIMM_PMEM_H__
 #define __NVDIMM_PMEM_H__
+#include <linux/page-flags.h>
 #include <linux/badblocks.h>
 #include <linux/types.h>
 #include <linux/pfn_t.h>
@@ -27,4 +28,16 @@ struct pmem_device {
 
 long __pmem_direct_access(struct pmem_device *pmem, pgoff_t pgoff,
                long nr_pages, void **kaddr, pfn_t *pfn);
+
+#ifdef CONFIG_MEMORY_FAILURE
+static inline bool test_and_clear_pmem_poison(struct page *page)
+{
+       return TestClearPageHWPoison(page);
+}
+#else
+static inline bool test_and_clear_pmem_poison(struct page *page)
+{
+       return false;
+}
+#endif
 #endif /* __NVDIMM_PMEM_H__ */