Merge tag 'ras_updates_for_v5.10' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull RAS updates from Borislav Petkov:

 - Extend the recovery from MCE in kernel space also to processes which
   encounter an MCE in kernel space but while copying from user memory
   by sending them a SIGBUS on return to user space and umapping the
   faulty memory, by Tony Luck and Youquan Song.

 - memcpy_mcsafe() rework by splitting the functionality into
   copy_mc_to_user() and copy_mc_to_kernel(). This, as a result, enables
   support for new hardware which can recover from a machine check
   encountered during a fast string copy and makes that the default and
   lets the older hardware which does not support that advance recovery,
   opt in to use the old, fragile, slow variant, by Dan Williams.

 - New AMD hw enablement, by Yazen Ghannam and Akshay Gupta.

 - Do not use MSR-tracing accessors in #MC context and flag any fault
   while accessing MCA architectural MSRs as an architectural violation
   with the hope that such hw/fw misdesigns are caught early during the
   hw eval phase and they don't make it into production.

 - Misc fixes, improvements and cleanups, as always.

* tag 'ras_updates_for_v5.10' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/mce: Allow for copy_mc_fragile symbol checksum to be generated
  x86/mce: Decode a kernel instruction to determine if it is copying from user
  x86/mce: Recover from poison found while copying from user space
  x86/mce: Avoid tail copy when machine check terminated a copy from user
  x86/mce: Add _ASM_EXTABLE_CPY for copy user access
  x86/mce: Provide method to find out the type of an exception handler
  x86/mce: Pass pointer to saved pt_regs to severity calculation routines
  x86/copy_mc: Introduce copy_mc_enhanced_fast_string()
  x86, powerpc: Rename memcpy_mcsafe() to copy_mc_to_{user, kernel}()
  x86/mce: Drop AMD-specific "DEFERRED" case from Intel severity rule list
  x86/mce: Add Skylake quirk for patrol scrub reported errors
  RAS/CEC: Convert to DEFINE_SHOW_ATTRIBUTE()
  x86/mce: Annotate mce_rd/wrmsrl() with noinstr
  x86/mce/dev-mcelog: Do not update kflags on AMD systems
  x86/mce: Stop mce_reign() from re-computing severity for every CPU
  x86/mce: Make mce_rdmsrl() panic on an inaccessible MSR
  x86/mce: Increase maximum number of banks to 64
  x86/mce: Delay clearing IA32_MCG_STATUS to the end of do_machine_check()
  x86/MCE/AMD, EDAC/mce_amd: Remove struct smca_hwid.xec_bitmap
  RAS/CEC: Fix cec_init() prototype

5 files changed, 22 insertions, 31 deletions

diff --git a/drivers/edac/mce_amd.c b/drivers/edac/mce_amd.c
index 4fd06a3dc6fe..7f28edb070bd 100644
--- a/drivers/edac/mce_amd.c
+++ b/drivers/edac/mce_amd.c
@@ -999,10 +999,8 @@ static void decode_smca_error(struct mce *m)
 	pr_emerg(HW_ERR "%s Ext. Error Code: %d", ip_name, xec);
 
 	/* Only print the decode of valid error codes */
-	if (xec < smca_mce_descs[bank_type].num_descs &&
-			(hwid->xec_bitmap & BIT_ULL(xec))) {
+	if (xec < smca_mce_descs[bank_type].num_descs)
 		pr_cont(", %s.\n", smca_mce_descs[bank_type].descs[xec]);
-	}
 
 	if (bank_type == SMCA_UMC && xec == 0 && decode_dram_ecc)
 		decode_dram_ecc(cpu_to_node(m->extcpu), m);
diff --git a/drivers/md/dm-writecache.c b/drivers/md/dm-writecache.c
index 6271d1e741cf..9ae4ce7df95c 100644
--- a/drivers/md/dm-writecache.c
+++ b/drivers/md/dm-writecache.c
@@ -49,7 +49,7 @@ do {								\
 #define pmem_assign(dest, src)	((dest) = (src))
 #endif
 
-#if defined(__HAVE_ARCH_MEMCPY_MCSAFE) && defined(DM_WRITECACHE_HAS_PMEM)
+#if IS_ENABLED(CONFIG_ARCH_HAS_COPY_MC) && defined(DM_WRITECACHE_HAS_PMEM)
 #define DM_WRITECACHE_HANDLE_HARDWARE_ERRORS
 #endif
 
@@ -992,7 +992,8 @@ static void writecache_resume(struct dm_target *ti)
 	}
 	wc->freelist_size = 0;
 
-	r = memcpy_mcsafe(&sb_seq_count, &sb(wc)->seq_count, sizeof(uint64_t));
+	r = copy_mc_to_kernel(&sb_seq_count, &sb(wc)->seq_count,
+			      sizeof(uint64_t));
 	if (r) {
 		writecache_error(wc, r, "hardware memory error when reading superblock: %d", r);
 		sb_seq_count = cpu_to_le64(0);
@@ -1008,7 +1009,8 @@ static void writecache_resume(struct dm_target *ti)
 			e->seq_count = -1;
 			continue;
 		}
-		r = memcpy_mcsafe(&wme, memory_entry(wc, e), sizeof(struct wc_memory_entry));
+		r = copy_mc_to_kernel(&wme, memory_entry(wc, e),
+				      sizeof(struct wc_memory_entry));
 		if (r) {
 			writecache_error(wc, r, "hardware memory error when reading metadata entry %lu: %d",
 					 (unsigned long)b, r);
@@ -1206,7 +1208,7 @@ static void bio_copy_block(struct dm_writecache *wc, struct bio *bio, void *data
 
 		if (rw == READ) {
 			int r;
-			r = memcpy_mcsafe(buf, data, size);
+			r = copy_mc_to_kernel(buf, data, size);
 			flush_dcache_page(bio_page(bio));
 			if (unlikely(r)) {
 				writecache_error(wc, r, "hardware memory error when reading data: %d", r);
@@ -2349,7 +2351,7 @@ invalid_optional:
 		}
 	}
 
-	r = memcpy_mcsafe(&s, sb(wc), sizeof(struct wc_memory_superblock));
+	r = copy_mc_to_kernel(&s, sb(wc), sizeof(struct wc_memory_superblock));
 	if (r) {
 		ti->error = "Hardware memory error when reading superblock";
 		goto bad;
@@ -2360,7 +2362,8 @@ invalid_optional:
 			ti->error = "Unable to initialize device";
 			goto bad;
 		}
-		r = memcpy_mcsafe(&s, sb(wc), sizeof(struct wc_memory_superblock));
+		r = copy_mc_to_kernel(&s, sb(wc),
+				      sizeof(struct wc_memory_superblock));
 		if (r) {
 			ti->error = "Hardware memory error when reading superblock";
 			goto bad;
diff --git a/drivers/nvdimm/claim.c b/drivers/nvdimm/claim.c
index 45964acba944..22d865ba6353 100644
--- a/drivers/nvdimm/claim.c
+++ b/drivers/nvdimm/claim.c
@@ -268,7 +268,7 @@ static int nsio_rw_bytes(struct nd_namespace_common *ndns,
 	if (rw == READ) {
 		if (unlikely(is_bad_pmem(&nsio->bb, sector, sz_align)))
 			return -EIO;
-		if (memcpy_mcsafe(buf, nsio->addr + offset, size) != 0)
+		if (copy_mc_to_kernel(buf, nsio->addr + offset, size) != 0)
 			return -EIO;
 		return 0;
 	}
diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index fab29b514372..5c6939e004e2 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -125,7 +125,7 @@ static blk_status_t read_pmem(struct page *page, unsigned int off,
 	while (len) {
 		mem = kmap_atomic(page);
 		chunk = min_t(unsigned int, len, PAGE_SIZE - off);
-		rem = memcpy_mcsafe(mem + off, pmem_addr, chunk);
+		rem = copy_mc_to_kernel(mem + off, pmem_addr, chunk);
 		kunmap_atomic(mem);
 		if (rem)
 			return BLK_STS_IOERR;
@@ -304,7 +304,7 @@ static long pmem_dax_direct_access(struct dax_device *dax_dev,
 
 /*
  * Use the 'no check' versions of copy_from_iter_flushcache() and
- * copy_to_iter_mcsafe() to bypass HARDENED_USERCOPY overhead. Bounds
+ * copy_mc_to_iter() to bypass HARDENED_USERCOPY overhead. Bounds
  * checking, both file offset and device offset, is handled by
  * dax_iomap_actor()
  */
@@ -317,7 +317,7 @@ static size_t pmem_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff,
 static size_t pmem_copy_to_iter(struct dax_device *dax_dev, pgoff_t pgoff,
 		void *addr, size_t bytes, struct iov_iter *i)
 {
-	return _copy_to_iter_mcsafe(addr, bytes, i);
+	return _copy_mc_to_iter(addr, bytes, i);
 }
 
 static const struct dax_operations pmem_dax_ops = {
diff --git a/drivers/ras/cec.c b/drivers/ras/cec.c
index 569d9ad2c594..ddecf25b5dd4 100644
--- a/drivers/ras/cec.c
+++ b/drivers/ras/cec.c
@@ -435,7 +435,7 @@ DEFINE_DEBUGFS_ATTRIBUTE(action_threshold_ops, u64_get, action_threshold_set, "%
 
 static const char * const bins[] = { "00", "01", "10", "11" };
 
-static int array_dump(struct seq_file *m, void *v)
+static int array_show(struct seq_file *m, void *v)
 {
 	struct ce_array *ca = &ce_arr;
 	int i;
@@ -467,18 +467,7 @@ static int array_dump(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int array_open(struct inode *inode, struct file *filp)
-{
-	return single_open(filp, array_dump, NULL);
-}
-
-static const struct file_operations array_ops = {
-	.owner	 = THIS_MODULE,
-	.open	 = array_open,
-	.read	 = seq_read,
-	.llseek	 = seq_lseek,
-	.release = single_release,
-};
+DEFINE_SHOW_ATTRIBUTE(array);
 
 static int __init create_debugfs_nodes(void)
 {
@@ -513,7 +502,7 @@ static int __init create_debugfs_nodes(void)
 		goto err;
 	}
 
-	array = debugfs_create_file("array", S_IRUSR, d, NULL, &array_ops);
+	array = debugfs_create_file("array", S_IRUSR, d, NULL, &array_fops);
 	if (!array) {
 		pr_warn("Error creating array debugfs node!\n");
 		goto err;
@@ -553,20 +542,20 @@ static struct notifier_block cec_nb = {
 	.priority	= MCE_PRIO_CEC,
 };
 
-static void __init cec_init(void)
+static int __init cec_init(void)
 {
 	if (ce_arr.disabled)
-		return;
+		return -ENODEV;
 
 	ce_arr.array = (void *)get_zeroed_page(GFP_KERNEL);
 	if (!ce_arr.array) {
 		pr_err("Error allocating CE array page!\n");
-		return;
+		return -ENOMEM;
 	}
 
 	if (create_debugfs_nodes()) {
 		free_page((unsigned long)ce_arr.array);
-		return;
+		return -ENOMEM;
 	}
 
 	INIT_DELAYED_WORK(&cec_work, cec_work_fn);
@@ -575,6 +564,7 @@ static void __init cec_init(void)
 	mce_register_decode_chain(&cec_nb);
 
 	pr_info("Correctable Errors collector initialized.\n");
+	return 0;
 }
 late_initcall(cec_init);