Merge tag 'libnvdimm-for-4.19_dax-memory-failure' of gitolite.kernel.org:pub/scm/linux/kernel/git/nvdimm/nvdimm

Pull libnvdimm memory-failure update from Dave Jiang:
 "As it stands, memory_failure() gets thoroughly confused by dev_pagemap
  backed mappings. The recovery code has specific enabling for several
  possible page states and needs new enabling to handle poison in dax
  mappings.

  In order to support reliable reverse mapping of user space addresses:

   1/ Add new locking in the memory_failure() rmap path to prevent races
      that would typically be handled by the page lock.

   2/ Since dev_pagemap pages are hidden from the page allocator and the
      "compound page" accounting machinery, add a mechanism to determine
      the size of the mapping that encompasses a given poisoned pfn.

   3/ Given pmem errors can be repaired, change the speculatively
      accessed poison protection, mce_unmap_kpfn(), to be reversible and
      otherwise allow ongoing access from the kernel.

  A side effect of this enabling is that MADV_HWPOISON becomes usable
  for dax mappings, however the primary motivation is to allow the
  system to survive userspace consumption of hardware-poison via dax.
  Specifically the current behavior is:

     mce: Uncorrected hardware memory error in user-access at af34214200
     {1}[Hardware Error]: It has been corrected by h/w and requires no further action
     mce: [Hardware Error]: Machine check events logged
     {1}[Hardware Error]: event severity: corrected
     Memory failure: 0xaf34214: reserved kernel page still referenced by 1 users
     [..]
     Memory failure: 0xaf34214: recovery action for reserved kernel page: Failed
     mce: Memory error not recovered
     <reboot>

  ...and with these changes:

     Injecting memory failure for pfn 0x20cb00 at process virtual address 0x7f763dd00000
     Memory failure: 0x20cb00: Killing dax-pmd:5421 due to hardware memory corruption
     Memory failure: 0x20cb00: recovery action for dax page: Recovered

  Given all the cross dependencies I propose taking this through
  nvdimm.git with acks from Naoya, x86/core, x86/RAS, and of course dax
  folks"

* tag 'libnvdimm-for-4.19_dax-memory-failure' of gitolite.kernel.org:pub/scm/linux/kernel/git/nvdimm/nvdimm:
  libnvdimm, pmem: Restore page attributes when clearing errors
  x86/memory_failure: Introduce {set, clear}_mce_nospec()
  x86/mm/pat: Prepare {reserve, free}_memtype() for "decoy" addresses
  mm, memory_failure: Teach memory_failure() about dev_pagemap pages
  filesystem-dax: Introduce dax_lock_mapping_entry()
  mm, memory_failure: Collect mapping size in collect_procs()
  mm, madvise_inject_error: Let memory_failure() optionally take a page reference
  mm, dev_pagemap: Do not clear ->mapping on final put
  mm, madvise_inject_error: Disable MADV_SOFT_OFFLINE for ZONE_DEVICE pages
  filesystem-dax: Set page->index
  device-dax: Set page->index
  device-dax: Enable page_mapping()
  device-dax: Convert to vmf_insert_mixed and vm_fault_t

4 files changed, 31 insertions, 2 deletions

diff --git a/include/linux/dax.h b/include/linux/dax.h
index deb0f663252f..450b28db9533 100644
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@ -88,6 +88,8 @@ int dax_writeback_mapping_range(struct address_space *mapping,
 		struct block_device *bdev, struct writeback_control *wbc);
 
 struct page *dax_layout_busy_page(struct address_space *mapping);
+bool dax_lock_mapping_entry(struct page *page);
+void dax_unlock_mapping_entry(struct page *page);
 #else
 static inline bool bdev_dax_supported(struct block_device *bdev,
 		int blocksize)
@@ -119,6 +121,17 @@ static inline int dax_writeback_mapping_range(struct address_space *mapping,
 {
 	return -EOPNOTSUPP;
 }
+
+static inline bool dax_lock_mapping_entry(struct page *page)
+{
+	if (IS_DAX(page->mapping->host))
+		return true;
+	return false;
+}
+
+static inline void dax_unlock_mapping_entry(struct page *page)
+{
+}
 #endif
 
 int dax_read_lock(void);
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index 27e3e32135a8..99c19b06d9a4 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -3,6 +3,7 @@
 #define _LINUX_HUGE_MM_H
 
 #include <linux/sched/coredump.h>
+#include <linux/mm_types.h>
 
 #include <linux/fs.h> /* only for vma_is_dax() */
 
@@ -46,9 +47,9 @@ extern bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr,
 extern int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
 			unsigned long addr, pgprot_t newprot,
 			int prot_numa);
-int vmf_insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr,
+vm_fault_t vmf_insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr,
 			pmd_t *pmd, pfn_t pfn, bool write);
-int vmf_insert_pfn_pud(struct vm_area_struct *vma, unsigned long addr,
+vm_fault_t vmf_insert_pfn_pud(struct vm_area_struct *vma, unsigned long addr,
 			pud_t *pud, pfn_t pfn, bool write);
 enum transparent_hugepage_flag {
 	TRANSPARENT_HUGEPAGE_FLAG,
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 8fcc36660de6..a61ebe8ad4ca 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2731,6 +2731,7 @@ enum mf_action_page_type {
 	MF_MSG_TRUNCATED_LRU,
 	MF_MSG_BUDDY,
 	MF_MSG_BUDDY_2ND,
+	MF_MSG_DAX,
 	MF_MSG_UNKNOWN,
 };
 
diff --git a/include/linux/set_memory.h b/include/linux/set_memory.h
index da5178216da5..2a986d282a97 100644
--- a/include/linux/set_memory.h
+++ b/include/linux/set_memory.h
@@ -17,6 +17,20 @@ static inline int set_memory_x(unsigned long addr,  int numpages) { return 0; }
 static inline int set_memory_nx(unsigned long addr, int numpages) { return 0; }
 #endif
 
+#ifndef set_mce_nospec
+static inline int set_mce_nospec(unsigned long pfn)
+{
+	return 0;
+}
+#endif
+
+#ifndef clear_mce_nospec
+static inline int clear_mce_nospec(unsigned long pfn)
+{
+	return 0;
+}
+#endif
+
 #ifndef CONFIG_ARCH_HAS_MEM_ENCRYPT
 static inline int set_memory_encrypted(unsigned long addr, int numpages)
 {