Commit db168263 authored by Linus Torvalds's avatar Linus Torvalds
Browse files

Merge branch 'hwpoison' of git://git.kernel.org/pub/scm/linux/kernel/git/ak/linux-mce-2.6 

* 'hwpoison' of git://git.kernel.org/pub/scm/linux/kernel/git/ak/linux-mce-2.6: (21 commits)
  HWPOISON: Enable error_remove_page on btrfs
  HWPOISON: Add simple debugfs interface to inject hwpoison on arbitary PFNs
  HWPOISON: Add madvise() based injector for hardware poisoned pages v4
  HWPOISON: Enable error_remove_page for NFS
  HWPOISON: Enable .remove_error_page for migration aware file systems
  HWPOISON: The high level memory error handler in the VM v7
  HWPOISON: Add PR_MCE_KILL prctl to control early kill behaviour per process
  HWPOISON: shmem: call set_page_dirty() with locked page
  HWPOISON: Define a new error_remove_page address space op for async truncation
  HWPOISON: Add invalidate_inode_page
  HWPOISON: Refactor truncate to allow direct truncating of page v2
  HWPOISON: check and isolate corrupted free pages v2
  HWPOISON: Handle hardware poisoned pages in try_to_unmap
  HWPOISON: Use bitmask/action code for try_to_unmap behaviour
  HWPOISON: x86: Add VM_FAULT_HWPOISON handling to x86 page fault handler v2
  HWPOISON: Add poison check to page fault handling
  HWPOISON: Add basic support for poisoned pages in fault handler v3
  HWPOISON: Add new SIGBUS error codes for hardware poison signals
  HWPOISON: Add support for poison swap entries v2
  HWPOISON: Export some rmap vma locking to outside world
  ...
parents cd604513 465fdd97

Documentation/filesystems/vfs.txt

+7 −0
Original line number Diff line number Diff line
@@ -536,6 +536,7 @@ struct address_space_operations { 
	/* migrate the contents of a page to the specified target */

	int (*migratepage) (struct page *, struct page *);

	int (*launder_page) (struct page *);

	int (*error_remove_page) (struct mapping *mapping, struct page *page);

};



  writepage: called by the VM to write a dirty page to backing store.
@@ -694,6 +695,12 @@ struct address_space_operations { 
  	prevent redirtying the page, it is kept locked during the whole

	operation.



  error_remove_page: normally set to generic_error_remove_page if truncation

	is ok for this address space. Used for memory failure handling.

	Setting this implies you deal with pages going away under you,

	unless you have them locked or reference counts increased.





The File Object

===============

Documentation/sysctl/vm.txt

+40 −1
Original line number Diff line number Diff line
@@ -32,6 +32,8 @@ Currently, these files are in /proc/sys/vm: 
- legacy_va_layout

- lowmem_reserve_ratio

- max_map_count

- memory_failure_early_kill

- memory_failure_recovery

- min_free_kbytes

- min_slab_ratio

- min_unmapped_ratio
@@ -53,7 +55,6 @@ Currently, these files are in /proc/sys/vm: 
- vfs_cache_pressure

- zone_reclaim_mode





==============================================================



block_dump
@@ -275,6 +276,44 @@ e.g., up to one or two maps per allocation. 


The default value is 65536.



=============================================================



memory_failure_early_kill:



Control how to kill processes when uncorrected memory error (typically

a 2bit error in a memory module) is detected in the background by hardware

that cannot be handled by the kernel. In some cases (like the page

still having a valid copy on disk) the kernel will handle the failure

transparently without affecting any applications. But if there is

no other uptodate copy of the data it will kill to prevent any data

corruptions from propagating.



1: Kill all processes that have the corrupted and not reloadable page mapped

as soon as the corruption is detected.  Note this is not supported

for a few types of pages, like kernel internally allocated data or

the swap cache, but works for the majority of user pages.



0: Only unmap the corrupted page from all processes and only kill a process

who tries to access it.



The kill is done using a catchable SIGBUS with BUS_MCEERR_AO, so processes can

handle this if they want to.



This is only active on architectures/platforms with advanced machine

check handling and depends on the hardware capabilities.



Applications can override this setting individually with the PR_MCE_KILL prctl



==============================================================



memory_failure_recovery



Enable memory failure recovery (when supported by the platform)



1: Attempt recovery.



0: Always panic on a memory failure.



==============================================================



min_free_kbytes:

arch/x86/mm/fault.c

+15 −4
Original line number Diff line number Diff line
@@ -167,6 +167,7 @@ force_sig_info_fault(int si_signo, int si_code, unsigned long address, 
	info.si_errno	= 0;

	info.si_code	= si_code;

	info.si_addr	= (void __user *)address;

	info.si_addr_lsb = si_code == BUS_MCEERR_AR ? PAGE_SHIFT : 0;



	force_sig_info(si_signo, &info, tsk);

}
@@ -790,10 +791,12 @@ out_of_memory(struct pt_regs *regs, unsigned long error_code, 
}



static void

do_sigbus(struct pt_regs *regs, unsigned long error_code, unsigned long address)

do_sigbus(struct pt_regs *regs, unsigned long error_code, unsigned long address,

	  unsigned int fault)

{

	struct task_struct *tsk = current;

	struct mm_struct *mm = tsk->mm;

	int code = BUS_ADRERR;



	up_read(&mm->mmap_sem);
@@ -809,7 +812,15 @@ do_sigbus(struct pt_regs *regs, unsigned long error_code, unsigned long address) 
	tsk->thread.error_code	= error_code;

	tsk->thread.trap_no	= 14;



	force_sig_info_fault(SIGBUS, BUS_ADRERR, address, tsk);

#ifdef CONFIG_MEMORY_FAILURE

	if (fault & VM_FAULT_HWPOISON) {

		printk(KERN_ERR

	"MCE: Killing %s:%d due to hardware memory corruption fault at %lx\n",

			tsk->comm, tsk->pid, address);

		code = BUS_MCEERR_AR;

	}

#endif

	force_sig_info_fault(SIGBUS, code, address, tsk);

}



static noinline void
@@ -819,8 +830,8 @@ mm_fault_error(struct pt_regs *regs, unsigned long error_code, 
	if (fault & VM_FAULT_OOM) {

		out_of_memory(regs, error_code, address);

	} else {

		if (fault & VM_FAULT_SIGBUS)

			do_sigbus(regs, error_code, address);

		if (fault & (VM_FAULT_SIGBUS|VM_FAULT_HWPOISON))

			do_sigbus(regs, error_code, address, fault);

		else

			BUG();

	}

fs/btrfs/inode.c

+1 −0
Original line number Diff line number Diff line
@@ -5269,6 +5269,7 @@ static const struct address_space_operations btrfs_aops = { 
	.invalidatepage = btrfs_invalidatepage,

	.releasepage	= btrfs_releasepage,

	.set_page_dirty	= btrfs_set_page_dirty,

	.error_remove_page = generic_error_remove_page,

};



static const struct address_space_operations btrfs_symlink_aops = {

fs/ext2/inode.c

+2 −0
Original line number Diff line number Diff line
@@ -819,6 +819,7 @@ const struct address_space_operations ext2_aops = { 
	.writepages		= ext2_writepages,

	.migratepage		= buffer_migrate_page,

	.is_partially_uptodate	= block_is_partially_uptodate,

	.error_remove_page	= generic_error_remove_page,

};



const struct address_space_operations ext2_aops_xip = {
@@ -837,6 +838,7 @@ const struct address_space_operations ext2_nobh_aops = { 
	.direct_IO		= ext2_direct_IO,

	.writepages		= ext2_writepages,

	.migratepage		= buffer_migrate_page,

	.error_remove_page	= generic_error_remove_page,

};



/*

CRA Git | Maintained and supported by SUSTech CRA and CCSE