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
  ...

1 files changed, 104 insertions, 0 deletions

diff --git a/tools/testing/nvdimm/test/nfit.c b/tools/testing/nvdimm/test/nfit.c
index 4ea385be528f..a8fb63edcf89 100644
--- a/tools/testing/nvdimm/test/nfit.c
+++ b/tools/testing/nvdimm/test/nfit.c
@@ -29,6 +29,8 @@
 #include "nfit_test.h"
 #include "../watermark.h"
 
+#include <asm/mcsafe_test.h>
+
 /*
  * Generate an NFIT table to describe the following topology:
  *
@@ -2681,6 +2683,107 @@ static struct platform_driver nfit_test_driver = {
 	.id_table = nfit_test_id,
 };
 
+static char mcsafe_buf[PAGE_SIZE] __attribute__((__aligned__(PAGE_SIZE)));
+
+enum INJECT {
+	INJECT_NONE,
+	INJECT_SRC,
+	INJECT_DST,
+};
+
+static void mcsafe_test_init(char *dst, char *src, size_t size)
+{
+	size_t i;
+
+	memset(dst, 0xff, size);
+	for (i = 0; i < size; i++)
+		src[i] = (char) i;
+}
+
+static bool mcsafe_test_validate(unsigned char *dst, unsigned char *src,
+		size_t size, unsigned long rem)
+{
+	size_t i;
+
+	for (i = 0; i < size - rem; i++)
+		if (dst[i] != (unsigned char) i) {
+			pr_info_once("%s:%d: offset: %zd got: %#x expect: %#x\n",
+					__func__, __LINE__, i, dst[i],
+					(unsigned char) i);
+			return false;
+		}
+	for (i = size - rem; i < size; i++)
+		if (dst[i] != 0xffU) {
+			pr_info_once("%s:%d: offset: %zd got: %#x expect: 0xff\n",
+					__func__, __LINE__, i, dst[i]);
+			return false;
+		}
+	return true;
+}
+
+void mcsafe_test(void)
+{
+	char *inject_desc[] = { "none", "source", "destination" };
+	enum INJECT inj;
+
+	if (IS_ENABLED(CONFIG_MCSAFE_TEST)) {
+		pr_info("%s: run...\n", __func__);
+	} else {
+		pr_info("%s: disabled, skip.\n", __func__);
+		return;
+	}
+
+	for (inj = INJECT_NONE; inj <= INJECT_DST; inj++) {
+		int i;
+
+		pr_info("%s: inject: %s\n", __func__, inject_desc[inj]);
+		for (i = 0; i < 512; i++) {
+			unsigned long expect, rem;
+			void *src, *dst;
+			bool valid;
+
+			switch (inj) {
+			case INJECT_NONE:
+				mcsafe_inject_src(NULL);
+				mcsafe_inject_dst(NULL);
+				dst = &mcsafe_buf[2048];
+				src = &mcsafe_buf[1024 - i];
+				expect = 0;
+				break;
+			case INJECT_SRC:
+				mcsafe_inject_src(&mcsafe_buf[1024]);
+				mcsafe_inject_dst(NULL);
+				dst = &mcsafe_buf[2048];
+				src = &mcsafe_buf[1024 - i];
+				expect = 512 - i;
+				break;
+			case INJECT_DST:
+				mcsafe_inject_src(NULL);
+				mcsafe_inject_dst(&mcsafe_buf[2048]);
+				dst = &mcsafe_buf[2048 - i];
+				src = &mcsafe_buf[1024];
+				expect = 512 - i;
+				break;
+			}
+
+			mcsafe_test_init(dst, src, 512);
+			rem = __memcpy_mcsafe(dst, src, 512);
+			valid = mcsafe_test_validate(dst, src, 512, expect);
+			if (rem == expect && valid)
+				continue;
+			pr_info("%s: copy(%#lx, %#lx, %d) off: %d rem: %ld %s expect: %ld\n",
+					__func__,
+					((unsigned long) dst) & ~PAGE_MASK,
+					((unsigned long ) src) & ~PAGE_MASK,
+					512, i, rem, valid ? "valid" : "bad",
+					expect);
+		}
+	}
+
+	mcsafe_inject_src(NULL);
+	mcsafe_inject_dst(NULL);
+}
+
 static __init int nfit_test_init(void)
 {
 	int rc, i;
@@ -2689,6 +2792,7 @@ static __init int nfit_test_init(void)
 	libnvdimm_test();
 	acpi_nfit_test();
 	device_dax_test();
+	mcsafe_test();
 
 	nfit_test_setup(nfit_test_lookup, nfit_test_evaluate_dsm);