Commit 7d3bf613 authored by Linus Torvalds's avatar Linus Torvalds
Browse files

Merge tag 'libnvdimm-for-4.18' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm 

Pull libnvdimm updates from Dan Williams:
 "This adds a user for the new 'bytes-remaining' updates to
  memcpy_mcsafe() that you already received through Ingo via the
  x86-dax- for-linus pull.

  Not included here, but still targeting this cycle, is support for
  handling memory media errors (poison) consumed via userspace dax
  mappings.

  Summary:

   - DAX broke a fundamental assumption of truncate of file mapped
     pages. The truncate path assumed that it is safe to disconnect a
     pinned page from a file and let the filesystem reclaim the physical
     block. With DAX the page is equivalent to the filesystem block.
     Introduce dax_layout_busy_page() to enable filesystems to wait for
     pinned DAX pages to be released. Without this wait a filesystem
     could allocate blocks under active device-DMA to a new file.

   - DAX arranges for the block layer to be bypassed and uses
     dax_direct_access() + copy_to_iter() to satisfy read(2) calls.
     However, the memcpy_mcsafe() facility is available through the pmem
     block driver. In order to safely handle media errors, via the DAX
     block-layer bypass, introduce copy_to_iter_mcsafe().

   - Fix cache management policy relative to the ACPI NFIT Platform
     Capabilities Structure to properly elide cache flushes when they
     are not necessary. The table indicates whether CPU caches are
     power-fail protected. Clarify that a deep flush is always performed
     on REQ_{FUA,PREFLUSH} requests"

* tag 'libnvdimm-for-4.18' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm: (21 commits)
  dax: Use dax_write_cache* helpers
  libnvdimm, pmem: Do not flush power-fail protected CPU caches
  libnvdimm, pmem: Unconditionally deep flush on *sync
  libnvdimm, pmem: Complete REQ_FLUSH => REQ_PREFLUSH
  acpi, nfit: Remove ecc_unit_size
  dax: dax_insert_mapping_entry always succeeds
  libnvdimm, e820: Register all pmem resources
  libnvdimm: Debug probe times
  linvdimm, pmem: Preserve read-only setting for pmem devices
  x86, nfit_test: Add unit test for memcpy_mcsafe()
  pmem: Switch to copy_to_iter_mcsafe()
  dax: Report bytes remaining in dax_iomap_actor()
  dax: Introduce a ->copy_to_iter dax operation
  uio, lib: Fix CONFIG_ARCH_HAS_UACCESS_MCSAFE compilation
  xfs, dax: introduce xfs_break_dax_layouts()
  xfs: prepare xfs_break_layouts() for another layout type
  xfs: prepare xfs_break_layouts() to be called with XFS_MMAPLOCK_EXCL
  mm, fs, dax: handle layout changes to pinned dax mappings
  mm: fix __gup_device_huge vs unmap
  mm: introduce MEMORY_DEVICE_FS_DAX and CONFIG_DEV_PAGEMAP_OPS
  ...
parents a3818841 930218af

Documentation/ABI/removed/sysfs-bus-nfit

0 → 100644
+17 −0
Original line number Diff line number Diff line 
What:		/sys/bus/nd/devices/regionX/nfit/ecc_unit_size

Date:		Aug, 2017

KernelVersion:	v4.14 (Removed v4.18)

Contact:	linux-nvdimm@lists.01.org

Description:

		(RO) Size of a write request to a DIMM that will not incur a

		read-modify-write cycle at the memory controller.



		When the nfit driver initializes it runs an ARS (Address Range

		Scrub) operation across every pmem range. Part of that process

		involves determining the ARS capabilities of a given address

		range. One of the capabilities that is reported is the 'Clear

		Uncorrectable Error Range Length Unit Size' (see: ACPI 6.2

		section 9.20.7.4 Function Index 1 - Query ARS Capabilities).

		This property indicates the boundary at which the NVDIMM may

		need to perform read-modify-write cycles to maintain ECC (Error

		Correcting Code) blocks.

Documentation/ABI/testing/sysfs-bus-nfit

+0 −19
Original line number Diff line number Diff line
@@ -212,22 +212,3 @@ Description: 
		range. Used by NVDIMM Region Mapping Structure to uniquely refer

		to this structure. Value of 0 is reserved and not used as an

		index.
 




What:		/sys/bus/nd/devices/regionX/nfit/ecc_unit_size

Date:		Aug, 2017

KernelVersion:	v4.14

Contact:	linux-nvdimm@lists.01.org

Description:

		(RO) Size of a write request to a DIMM that will not incur a

		read-modify-write cycle at the memory controller.



		When the nfit driver initializes it runs an ARS (Address Range

		Scrub) operation across every pmem range. Part of that process

		involves determining the ARS capabilities of a given address

		range. One of the capabilities that is reported is the 'Clear

		Uncorrectable Error Range Length Unit Size' (see: ACPI 6.2

		section 9.20.7.4 Function Index 1 - Query ARS Capabilities).

		This property indicates the boundary at which the NVDIMM may

		need to perform read-modify-write cycles to maintain ECC (Error

		Correcting Code) blocks.

arch/x86/Kconfig.debug

+3 −0
Original line number Diff line number Diff line
@@ -72,6 +72,9 @@ config EARLY_PRINTK_USB_XDBC 
	  You should normally say N here, unless you want to debug early

	  crashes or need a very simple printk logging facility.



config MCSAFE_TEST

	def_bool n



config X86_PTDUMP_CORE

	def_bool n

arch/x86/include/asm/mcsafe_test.h

0 → 100644
+75 −0
Original line number Diff line number Diff line 
/* SPDX-License-Identifier: GPL-2.0 */

#ifndef _MCSAFE_TEST_H_

#define _MCSAFE_TEST_H_



#ifndef __ASSEMBLY__

#ifdef CONFIG_MCSAFE_TEST

extern unsigned long mcsafe_test_src;

extern unsigned long mcsafe_test_dst;



static inline void mcsafe_inject_src(void *addr)

{

	if (addr)

		mcsafe_test_src = (unsigned long) addr;

	else

		mcsafe_test_src = ~0UL;

}



static inline void mcsafe_inject_dst(void *addr)

{

	if (addr)

		mcsafe_test_dst = (unsigned long) addr;

	else

		mcsafe_test_dst = ~0UL;

}

#else /* CONFIG_MCSAFE_TEST */

static inline void mcsafe_inject_src(void *addr)

{

}



static inline void mcsafe_inject_dst(void *addr)

{

}

#endif /* CONFIG_MCSAFE_TEST */



#else /* __ASSEMBLY__ */

#include <asm/export.h>



#ifdef CONFIG_MCSAFE_TEST

.macro MCSAFE_TEST_CTL

	.pushsection .data

	.align 8

	.globl mcsafe_test_src

	mcsafe_test_src:

		.quad 0

	EXPORT_SYMBOL_GPL(mcsafe_test_src)

	.globl mcsafe_test_dst

	mcsafe_test_dst:

		.quad 0

	EXPORT_SYMBOL_GPL(mcsafe_test_dst)

	.popsection

.endm



.macro MCSAFE_TEST_SRC reg count target

	leaq \count(\reg), %r9

	cmp mcsafe_test_src, %r9

	ja \target

.endm



.macro MCSAFE_TEST_DST reg count target

	leaq \count(\reg), %r9

	cmp mcsafe_test_dst, %r9

	ja \target

.endm

#else

.macro MCSAFE_TEST_CTL

.endm



.macro MCSAFE_TEST_SRC reg count target

.endm



.macro MCSAFE_TEST_DST reg count target

.endm

#endif /* CONFIG_MCSAFE_TEST */

#endif /* __ASSEMBLY__ */

#endif /* _MCSAFE_TEST_H_ */

arch/x86/lib/memcpy_64.S

+10 −0
Original line number Diff line number Diff line
@@ -3,6 +3,7 @@ 
#include <linux/linkage.h>

#include <asm/errno.h>

#include <asm/cpufeatures.h>

#include <asm/mcsafe_test.h>

#include <asm/alternative-asm.h>

#include <asm/export.h>
@@ -183,6 +184,9 @@ ENTRY(memcpy_orig) 
ENDPROC(memcpy_orig)



#ifndef CONFIG_UML



MCSAFE_TEST_CTL



/*

 * __memcpy_mcsafe - memory copy with machine check exception handling

 * Note that we only catch machine checks when reading the source addresses.
@@ -206,6 +210,8 @@ ENTRY(__memcpy_mcsafe) 
	subl %ecx, %edx

.L_read_leading_bytes:

	movb (%rsi), %al

	MCSAFE_TEST_SRC %rsi 1 .E_leading_bytes

	MCSAFE_TEST_DST %rdi 1 .E_leading_bytes

.L_write_leading_bytes:

	movb %al, (%rdi)

	incq %rsi
@@ -221,6 +227,8 @@ ENTRY(__memcpy_mcsafe) 


.L_read_words:

	movq (%rsi), %r8

	MCSAFE_TEST_SRC %rsi 8 .E_read_words

	MCSAFE_TEST_DST %rdi 8 .E_write_words

.L_write_words:

	movq %r8, (%rdi)

	addq $8, %rsi
@@ -237,6 +245,8 @@ ENTRY(__memcpy_mcsafe) 
	movl %edx, %ecx

.L_read_trailing_bytes:

	movb (%rsi), %al

	MCSAFE_TEST_SRC %rsi 1 .E_trailing_bytes

	MCSAFE_TEST_DST %rdi 1 .E_trailing_bytes

.L_write_trailing_bytes:

	movb %al, (%rdi)

	incq %rsi

CRA Git | Maintained and supported by SUSTech CRA and CCSE