Merge tag 'libnvdimm-for-5.19' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm

Pull libnvdimm and DAX updates from Dan Williams:
 "New support for clearing memory errors when a file is in DAX mode,
  alongside with some other fixes and cleanups.

  Previously it was only possible to clear these errors using a truncate
  or hole-punch operation to trigger the filesystem to reallocate the
  block, now, any page aligned write can opportunistically clear errors
  as well.

  This change spans x86/mm, nvdimm, and fs/dax, and has received the
  appropriate sign-offs. Thanks to Jane for her work on this.

  Summary:

   - Add support for clearing memory error via pwrite(2) on DAX

   - Fix 'security overwrite' support in the presence of media errors

   - Miscellaneous cleanups and fixes for nfit_test (nvdimm unit tests)"

* tag 'libnvdimm-for-5.19' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm:
  pmem: implement pmem_recovery_write()
  pmem: refactor pmem_clear_poison()
  dax: add .recovery_write dax_operation
  dax: introduce DAX_RECOVERY_WRITE dax access mode
  mce: fix set_mce_nospec to always unmap the whole page
  x86/mce: relocate set{clear}_mce_nospec() functions
  acpi/nfit: rely on mce->misc to determine poison granularity
  testing: nvdimm: asm/mce.h is not needed in nfit.c
  testing: nvdimm: iomap: make __nfit_test_ioremap a macro
  nvdimm: Allow overwrite in the presence of disabled dimms
  tools/testing/nvdimm: remove unneeded flush_workqueue

Author: torvalds

arch/x86/include/asm/set_memory.h

@@ -86,56 +86,4 @@ bool kernel_page_present(struct page *page);
 
 extern int kernel_set_to_readonly;
 
-#ifdef CONFIG_X86_64
-/*
- * Prevent speculative access to the page by either unmapping
- * it (if we do not require access to any part of the page) or
- * marking it uncacheable (if we want to try to retrieve data
- * from non-poisoned lines in the page).
- */
-static inline int set_mce_nospec(unsigned long pfn, bool unmap)
-{
-	unsigned long decoy_addr;
-	int rc;
-
-	/* SGX pages are not in the 1:1 map */
-	if (arch_is_platform_page(pfn << PAGE_SHIFT))
-		return 0;
-	/*
-	 * We would like to just call:
-	 *      set_memory_XX((unsigned long)pfn_to_kaddr(pfn), 1);
-	 * but doing that would radically increase the odds of a
-	 * speculative access to the poison page because we'd have
-	 * the virtual address of the kernel 1:1 mapping sitting
-	 * around in registers.
-	 * Instead we get tricky.  We create a non-canonical address
-	 * that looks just like the one we want, but has bit 63 flipped.
-	 * This relies on set_memory_XX() properly sanitizing any __pa()
-	 * results with __PHYSICAL_MASK or PTE_PFN_MASK.
-	 */
-	decoy_addr = (pfn << PAGE_SHIFT) + (PAGE_OFFSET ^ BIT(63));
-
-	if (unmap)
-		rc = set_memory_np(decoy_addr, 1);
-	else
-		rc = set_memory_uc(decoy_addr, 1);
-	if (rc)
-		pr_warn("Could not invalidate pfn=0x%lx from 1:1 map\n", pfn);
-	return rc;
-}
-#define set_mce_nospec set_mce_nospec
-
-/* Restore full speculative operation to the pfn. */
-static inline int clear_mce_nospec(unsigned long pfn)
-{
-	return set_memory_wb((unsigned long) pfn_to_kaddr(pfn), 1);
-}
-#define clear_mce_nospec clear_mce_nospec
-#else
-/*
- * Few people would run a 32-bit kernel on a machine that supports
- * recoverable errors because they have too much memory to boot 32-bit.
- */
-#endif
-
 #endif /* _ASM_X86_SET_MEMORY_H */

arch/x86/kernel/cpu/mce/core.c

@@ -581,7 +581,7 @@ static int uc_decode_notifier(struct notifier_block *nb, unsigned long val,
 
 	pfn = mce->addr >> PAGE_SHIFT;
 	if (!memory_failure(pfn, 0)) {
-		set_mce_nospec(pfn, whole_page(mce));
+		set_mce_nospec(pfn);
 		mce->kflags |= MCE_HANDLED_UC;
 	}
 
@@ -1318,7 +1318,7 @@ static void kill_me_maybe(struct callback_head *cb)
 
 	ret = memory_failure(p->mce_addr >> PAGE_SHIFT, flags);
 	if (!ret) {
-		set_mce_nospec(p->mce_addr >> PAGE_SHIFT, p->mce_whole_page);
+		set_mce_nospec(p->mce_addr >> PAGE_SHIFT);
 		sync_core();
 		return;
 	}
@@ -1344,7 +1344,7 @@ static void kill_me_never(struct callback_head *cb)
 	p->mce_count = 0;
 	pr_err("Kernel accessed poison in user space at %llx\n", p->mce_addr);
 	if (!memory_failure(p->mce_addr >> PAGE_SHIFT, 0))
-		set_mce_nospec(p->mce_addr >> PAGE_SHIFT, p->mce_whole_page);
+		set_mce_nospec(p->mce_addr >> PAGE_SHIFT);
 }
 
 static void queue_task_work(struct mce *m, char *msg, void (*func)(struct callback_head *))

arch/x86/mm/pat/set_memory.c

@@ -19,6 +19,7 @@
 #include <linux/vmstat.h>
 #include <linux/kernel.h>
 #include <linux/cc_platform.h>
+#include <linux/set_memory.h>
 
 #include <asm/e820/api.h>
 #include <asm/processor.h>
@@ -29,7 +30,6 @@
 #include <asm/pgalloc.h>
 #include <asm/proto.h>
 #include <asm/memtype.h>
-#include <asm/set_memory.h>
 #include <asm/hyperv-tlfs.h>
 #include <asm/mshyperv.h>
 
@@ -1805,7 +1805,7 @@ static inline int cpa_clear_pages_array(struct page **pages, int numpages,
 }
 
 /*
- * _set_memory_prot is an internal helper for callers that have been passed
+ * __set_memory_prot is an internal helper for callers that have been passed
  * a pgprot_t value from upper layers and a reservation has already been taken.
  * If you want to set the pgprot to a specific page protocol, use the
  * set_memory_xx() functions.
@@ -1914,6 +1914,51 @@ int set_memory_wb(unsigned long addr, int numpages)
 }
 EXPORT_SYMBOL(set_memory_wb);
 
+/* Prevent speculative access to a page by marking it not-present */
+#ifdef CONFIG_X86_64
+int set_mce_nospec(unsigned long pfn)
+{
+	unsigned long decoy_addr;
+	int rc;
+
+	/* SGX pages are not in the 1:1 map */
+	if (arch_is_platform_page(pfn << PAGE_SHIFT))
+		return 0;
+	/*
+	 * We would like to just call:
+	 *      set_memory_XX((unsigned long)pfn_to_kaddr(pfn), 1);
+	 * but doing that would radically increase the odds of a
+	 * speculative access to the poison page because we'd have
+	 * the virtual address of the kernel 1:1 mapping sitting
+	 * around in registers.
+	 * Instead we get tricky.  We create a non-canonical address
+	 * that looks just like the one we want, but has bit 63 flipped.
+	 * This relies on set_memory_XX() properly sanitizing any __pa()
+	 * results with __PHYSICAL_MASK or PTE_PFN_MASK.
+	 */
+	decoy_addr = (pfn << PAGE_SHIFT) + (PAGE_OFFSET ^ BIT(63));
+
+	rc = set_memory_np(decoy_addr, 1);
+	if (rc)
+		pr_warn("Could not invalidate pfn=0x%lx from 1:1 map\n", pfn);
+	return rc;
+}
+
+static int set_memory_present(unsigned long *addr, int numpages)
+{
+	return change_page_attr_set(addr, numpages, __pgprot(_PAGE_PRESENT), 0);
+}
+
+/* Restore full speculative operation to the pfn. */
+int clear_mce_nospec(unsigned long pfn)
+{
+	unsigned long addr = (unsigned long) pfn_to_kaddr(pfn);
+
+	return set_memory_present(&addr, 1);
+}
+EXPORT_SYMBOL_GPL(clear_mce_nospec);
+#endif /* CONFIG_X86_64 */
+
 int set_memory_x(unsigned long addr, int numpages)
 {
 	if (!(__supported_pte_mask & _PAGE_NX))

drivers/acpi/nfit/mce.c

@@ -32,6 +32,7 @@ static int nfit_handle_mce(struct notifier_block *nb, unsigned long val,
 	 */
 	mutex_lock(&acpi_desc_lock);
 	list_for_each_entry(acpi_desc, &acpi_descs, list) {
+		unsigned int align = 1UL << MCI_MISC_ADDR_LSB(mce->misc);
 		struct device *dev = acpi_desc->dev;
 		int found_match = 0;
 
@@ -63,8 +64,7 @@ static int nfit_handle_mce(struct notifier_block *nb, unsigned long val,
 
 		/* If this fails due to an -ENOMEM, there is little we can do */
 		nvdimm_bus_add_badrange(acpi_desc->nvdimm_bus,
-				ALIGN(mce->addr, L1_CACHE_BYTES),
-				L1_CACHE_BYTES);
+				ALIGN_DOWN(mce->addr, align), align);
 		nvdimm_region_notify(nfit_spa->nd_region,
 				NVDIMM_REVALIDATE_POISON);
 

drivers/dax/super.c

@@ -117,14 +117,15 @@ enum dax_device_flags {
  * @dax_dev: a dax_device instance representing the logical memory range
  * @pgoff: offset in pages from the start of the device to translate
  * @nr_pages: number of consecutive pages caller can handle relative to @pfn
+ * @mode: indicator on normal access or recovery write
  * @kaddr: output parameter that returns a virtual address mapping of pfn
  * @pfn: output parameter that returns an absolute pfn translation of @pgoff
  *
  * Return: negative errno if an error occurs, otherwise the number of
  * pages accessible at the device relative @pgoff.
  */
 long dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, long nr_pages,
-		void **kaddr, pfn_t *pfn)
+		enum dax_access_mode mode, void **kaddr, pfn_t *pfn)
 {
 	long avail;
 
@@ -138,7 +139,7 @@ long dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, long nr_pages,
 		return -EINVAL;
 
 	avail = dax_dev->ops->direct_access(dax_dev, pgoff, nr_pages,
-			kaddr, pfn);
+			mode, kaddr, pfn);
 	if (!avail)
 		return -ERANGE;
 	return min(avail, nr_pages);
@@ -194,6 +195,15 @@ int dax_zero_page_range(struct dax_device *dax_dev, pgoff_t pgoff,
 }
 EXPORT_SYMBOL_GPL(dax_zero_page_range);
 
+size_t dax_recovery_write(struct dax_device *dax_dev, pgoff_t pgoff,
+		void *addr, size_t bytes, struct iov_iter *iter)
+{
+	if (!dax_dev->ops->recovery_write)
+		return 0;
+	return dax_dev->ops->recovery_write(dax_dev, pgoff, addr, bytes, iter);
+}
+EXPORT_SYMBOL_GPL(dax_recovery_write);
+
 #ifdef CONFIG_ARCH_HAS_PMEM_API
 void arch_wb_cache_pmem(void *addr, size_t size);
 void dax_flush(struct dax_device *dax_dev, void *addr, size_t size)

drivers/md/dm-linear.c

@@ -165,11 +165,12 @@ static struct dax_device *linear_dax_pgoff(struct dm_target *ti, pgoff_t *pgoff)
 }
 
 static long linear_dax_direct_access(struct dm_target *ti, pgoff_t pgoff,
-		long nr_pages, void **kaddr, pfn_t *pfn)
+		long nr_pages, enum dax_access_mode mode, void **kaddr,
+		pfn_t *pfn)
 {
 	struct dax_device *dax_dev = linear_dax_pgoff(ti, &pgoff);
 
-	return dax_direct_access(dax_dev, pgoff, nr_pages, kaddr, pfn);
+	return dax_direct_access(dax_dev, pgoff, nr_pages, mode, kaddr, pfn);
 }
 
 static int linear_dax_zero_page_range(struct dm_target *ti, pgoff_t pgoff,
@@ -180,9 +181,18 @@ static int linear_dax_zero_page_range(struct dm_target *ti, pgoff_t pgoff,
 	return dax_zero_page_range(dax_dev, pgoff, nr_pages);
 }
 
+static size_t linear_dax_recovery_write(struct dm_target *ti, pgoff_t pgoff,
+		void *addr, size_t bytes, struct iov_iter *i)
+{
+	struct dax_device *dax_dev = linear_dax_pgoff(ti, &pgoff);
+
+	return dax_recovery_write(dax_dev, pgoff, addr, bytes, i);
+}
+
 #else
 #define linear_dax_direct_access NULL
 #define linear_dax_zero_page_range NULL
+#define linear_dax_recovery_write NULL
 #endif
 
 static struct target_type linear_target = {
@@ -200,6 +210,7 @@ static struct target_type linear_target = {
 	.iterate_devices = linear_iterate_devices,
 	.direct_access = linear_dax_direct_access,
 	.dax_zero_page_range = linear_dax_zero_page_range,
+	.dax_recovery_write = linear_dax_recovery_write,
 };
 
 int __init dm_linear_init(void)

drivers/md/dm-log-writes.c

@@ -888,11 +888,12 @@ static struct dax_device *log_writes_dax_pgoff(struct dm_target *ti,
 }
 
 static long log_writes_dax_direct_access(struct dm_target *ti, pgoff_t pgoff,
-					 long nr_pages, void **kaddr, pfn_t *pfn)
+		long nr_pages, enum dax_access_mode mode, void **kaddr,
+		pfn_t *pfn)
 {
 	struct dax_device *dax_dev = log_writes_dax_pgoff(ti, &pgoff);
 
-	return dax_direct_access(dax_dev, pgoff, nr_pages, kaddr, pfn);
+	return dax_direct_access(dax_dev, pgoff, nr_pages, mode, kaddr, pfn);
 }
 
 static int log_writes_dax_zero_page_range(struct dm_target *ti, pgoff_t pgoff,
@@ -903,9 +904,18 @@ static int log_writes_dax_zero_page_range(struct dm_target *ti, pgoff_t pgoff,
 	return dax_zero_page_range(dax_dev, pgoff, nr_pages << PAGE_SHIFT);
 }
 
+static size_t log_writes_dax_recovery_write(struct dm_target *ti,
+		pgoff_t pgoff, void *addr, size_t bytes, struct iov_iter *i)
+{
+	struct dax_device *dax_dev = log_writes_dax_pgoff(ti, &pgoff);
+
+	return dax_recovery_write(dax_dev, pgoff, addr, bytes, i);
+}
+
 #else
 #define log_writes_dax_direct_access NULL
 #define log_writes_dax_zero_page_range NULL
+#define log_writes_dax_recovery_write NULL
 #endif
 
 static struct target_type log_writes_target = {
@@ -923,6 +933,7 @@ static struct target_type log_writes_target = {
 	.io_hints = log_writes_io_hints,
 	.direct_access = log_writes_dax_direct_access,
 	.dax_zero_page_range = log_writes_dax_zero_page_range,
+	.dax_recovery_write = log_writes_dax_recovery_write,
 };
 
 static int __init dm_log_writes_init(void)

drivers/md/dm-stripe.c

@@ -315,11 +315,12 @@ static struct dax_device *stripe_dax_pgoff(struct dm_target *ti, pgoff_t *pgoff)
 }
 
 static long stripe_dax_direct_access(struct dm_target *ti, pgoff_t pgoff,
-		long nr_pages, void **kaddr, pfn_t *pfn)
+		long nr_pages, enum dax_access_mode mode, void **kaddr,
+		pfn_t *pfn)
 {
 	struct dax_device *dax_dev = stripe_dax_pgoff(ti, &pgoff);
 
-	return dax_direct_access(dax_dev, pgoff, nr_pages, kaddr, pfn);
+	return dax_direct_access(dax_dev, pgoff, nr_pages, mode, kaddr, pfn);
 }
 
 static int stripe_dax_zero_page_range(struct dm_target *ti, pgoff_t pgoff,
@@ -330,9 +331,18 @@ static int stripe_dax_zero_page_range(struct dm_target *ti, pgoff_t pgoff,
 	return dax_zero_page_range(dax_dev, pgoff, nr_pages);
 }
 
+static size_t stripe_dax_recovery_write(struct dm_target *ti, pgoff_t pgoff,
+		void *addr, size_t bytes, struct iov_iter *i)
+{
+	struct dax_device *dax_dev = stripe_dax_pgoff(ti, &pgoff);
+
+	return dax_recovery_write(dax_dev, pgoff, addr, bytes, i);
+}
+
 #else
 #define stripe_dax_direct_access NULL
 #define stripe_dax_zero_page_range NULL
+#define stripe_dax_recovery_write NULL
 #endif
 
 /*
@@ -469,6 +479,7 @@ static struct target_type stripe_target = {
 	.io_hints = stripe_io_hints,
 	.direct_access = stripe_dax_direct_access,
 	.dax_zero_page_range = stripe_dax_zero_page_range,
+	.dax_recovery_write = stripe_dax_recovery_write,
 };
 
 int __init dm_stripe_init(void)

drivers/md/dm-target.c

@@ -10,6 +10,7 @@
 #include <linux/init.h>
 #include <linux/kmod.h>
 #include <linux/bio.h>
+#include <linux/dax.h>
 
 #define DM_MSG_PREFIX "target"
 
@@ -142,7 +143,8 @@ static void io_err_release_clone_rq(struct request *clone,
 }
 
 static long io_err_dax_direct_access(struct dm_target *ti, pgoff_t pgoff,
-		long nr_pages, void **kaddr, pfn_t *pfn)
+		long nr_pages, enum dax_access_mode mode, void **kaddr,
+		pfn_t *pfn)
 {
 	return -EIO;
 }

drivers/md/dm-writecache.c

@@ -286,7 +286,8 @@ static int persistent_memory_claim(struct dm_writecache *wc)
 
 	id = dax_read_lock();
 
-	da = dax_direct_access(wc->ssd_dev->dax_dev, offset, p, &wc->memory_map, &pfn);
+	da = dax_direct_access(wc->ssd_dev->dax_dev, offset, p, DAX_ACCESS,
+			&wc->memory_map, &pfn);
 	if (da < 0) {
 		wc->memory_map = NULL;
 		r = da;
@@ -308,8 +309,8 @@ static int persistent_memory_claim(struct dm_writecache *wc)
 		i = 0;
 		do {
 			long daa;
-			daa = dax_direct_access(wc->ssd_dev->dax_dev, offset + i, p - i,
-						NULL, &pfn);
+			daa = dax_direct_access(wc->ssd_dev->dax_dev, offset + i,
+					p - i, DAX_ACCESS, NULL, &pfn);
 			if (daa <= 0) {
 				r = daa ? daa : -EINVAL;
 				goto err3;