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

2 files changed, 29 insertions, 26 deletions

diff --git a/lib/Kconfig b/lib/Kconfig
index b4b98a03ff98..b46a9fd122c8 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -635,7 +635,12 @@ config UACCESS_MEMCPY
 config ARCH_HAS_UACCESS_FLUSHCACHE
 	bool
 
-config ARCH_HAS_UACCESS_MCSAFE
+# arch has a concept of a recoverable synchronous exception due to a
+# memory-read error like x86 machine-check or ARM data-abort, and
+# implements copy_mc_to_{user,kernel} to abort and report
+# 'bytes-transferred' if that exception fires when accessing the source
+# buffer.
+config ARCH_HAS_COPY_MC
 	bool
 
 # Temporary. Goes away when all archs are cleaned up
diff --git a/lib/iov_iter.c b/lib/iov_iter.c
index 5e40786c8f12..d13304a034f5 100644
--- a/lib/iov_iter.c
+++ b/lib/iov_iter.c
@@ -637,30 +637,30 @@ size_t _copy_to_iter(const void *addr, size_t bytes, struct iov_iter *i)
 }
 EXPORT_SYMBOL(_copy_to_iter);
 
-#ifdef CONFIG_ARCH_HAS_UACCESS_MCSAFE
-static int copyout_mcsafe(void __user *to, const void *from, size_t n)
+#ifdef CONFIG_ARCH_HAS_COPY_MC
+static int copyout_mc(void __user *to, const void *from, size_t n)
 {
 	if (access_ok(to, n)) {
 		instrument_copy_to_user(to, from, n);
-		n = copy_to_user_mcsafe((__force void *) to, from, n);
+		n = copy_mc_to_user((__force void *) to, from, n);
 	}
 	return n;
 }
 
-static unsigned long memcpy_mcsafe_to_page(struct page *page, size_t offset,
+static unsigned long copy_mc_to_page(struct page *page, size_t offset,
 		const char *from, size_t len)
 {
 	unsigned long ret;
 	char *to;
 
 	to = kmap_atomic(page);
-	ret = memcpy_mcsafe(to + offset, from, len);
+	ret = copy_mc_to_kernel(to + offset, from, len);
 	kunmap_atomic(to);
 
 	return ret;
 }
 
-static size_t copy_pipe_to_iter_mcsafe(const void *addr, size_t bytes,
+static size_t copy_mc_pipe_to_iter(const void *addr, size_t bytes,
 				struct iov_iter *i)
 {
 	struct pipe_inode_info *pipe = i->pipe;
@@ -678,7 +678,7 @@ static size_t copy_pipe_to_iter_mcsafe(const void *addr, size_t bytes,
 		size_t chunk = min_t(size_t, n, PAGE_SIZE - off);
 		unsigned long rem;
 
-		rem = memcpy_mcsafe_to_page(pipe->bufs[i_head & p_mask].page,
+		rem = copy_mc_to_page(pipe->bufs[i_head & p_mask].page,
 					    off, addr, chunk);
 		i->head = i_head;
 		i->iov_offset = off + chunk - rem;
@@ -695,18 +695,17 @@ static size_t copy_pipe_to_iter_mcsafe(const void *addr, size_t bytes,
 }
 
 /**
- * _copy_to_iter_mcsafe - copy to user with source-read error exception handling
+ * _copy_mc_to_iter - copy to iter with source memory error exception handling
  * @addr: source kernel address
  * @bytes: total transfer length
  * @iter: destination iterator
  *
- * The pmem driver arranges for filesystem-dax to use this facility via
- * dax_copy_to_iter() for protecting read/write to persistent memory.
- * Unless / until an architecture can guarantee identical performance
- * between _copy_to_iter_mcsafe() and _copy_to_iter() it would be a
- * performance regression to switch more users to the mcsafe version.
+ * The pmem driver deploys this for the dax operation
+ * (dax_copy_to_iter()) for dax reads (bypass page-cache and the
+ * block-layer). Upon #MC read(2) aborts and returns EIO or the bytes
+ * successfully copied.
  *
- * Otherwise, the main differences between this and typical _copy_to_iter().
+ * The main differences between this and typical _copy_to_iter().
  *
  * * Typical tail/residue handling after a fault retries the copy
  *   byte-by-byte until the fault happens again. Re-triggering machine
@@ -717,23 +716,22 @@ static size_t copy_pipe_to_iter_mcsafe(const void *addr, size_t bytes,
  * * ITER_KVEC, ITER_PIPE, and ITER_BVEC can return short copies.
  *   Compare to copy_to_iter() where only ITER_IOVEC attempts might return
  *   a short copy.
- *
- * See MCSAFE_TEST for self-test.
  */
-size_t _copy_to_iter_mcsafe(const void *addr, size_t bytes, struct iov_iter *i)
+size_t _copy_mc_to_iter(const void *addr, size_t bytes, struct iov_iter *i)
 {
 	const char *from = addr;
 	unsigned long rem, curr_addr, s_addr = (unsigned long) addr;
 
 	if (unlikely(iov_iter_is_pipe(i)))
-		return copy_pipe_to_iter_mcsafe(addr, bytes, i);
+		return copy_mc_pipe_to_iter(addr, bytes, i);
 	if (iter_is_iovec(i))
 		might_fault();
 	iterate_and_advance(i, bytes, v,
-		copyout_mcsafe(v.iov_base, (from += v.iov_len) - v.iov_len, v.iov_len),
+		copyout_mc(v.iov_base, (from += v.iov_len) - v.iov_len,
+			   v.iov_len),
 		({
-		rem = memcpy_mcsafe_to_page(v.bv_page, v.bv_offset,
-                               (from += v.bv_len) - v.bv_len, v.bv_len);
+		rem = copy_mc_to_page(v.bv_page, v.bv_offset,
+				      (from += v.bv_len) - v.bv_len, v.bv_len);
 		if (rem) {
 			curr_addr = (unsigned long) from;
 			bytes = curr_addr - s_addr - rem;
@@ -741,8 +739,8 @@ size_t _copy_to_iter_mcsafe(const void *addr, size_t bytes, struct iov_iter *i)
 		}
 		}),
 		({
-		rem = memcpy_mcsafe(v.iov_base, (from += v.iov_len) - v.iov_len,
-				v.iov_len);
+		rem = copy_mc_to_kernel(v.iov_base, (from += v.iov_len)
+					- v.iov_len, v.iov_len);
 		if (rem) {
 			curr_addr = (unsigned long) from;
 			bytes = curr_addr - s_addr - rem;
@@ -753,8 +751,8 @@ size_t _copy_to_iter_mcsafe(const void *addr, size_t bytes, struct iov_iter *i)
 
 	return bytes;
 }
-EXPORT_SYMBOL_GPL(_copy_to_iter_mcsafe);
-#endif /* CONFIG_ARCH_HAS_UACCESS_MCSAFE */
+EXPORT_SYMBOL_GPL(_copy_mc_to_iter);
+#endif /* CONFIG_ARCH_HAS_COPY_MC */
 
 size_t _copy_from_iter(void *addr, size_t bytes, struct iov_iter *i)
 {