Merge 4.4.140 into android-4.4

Changes in 4.4.140
	usb: cdc_acm: Add quirk for Uniden UBC125 scanner
	USB: serial: cp210x: add CESINEL device ids
	USB: serial: cp210x: add Silicon Labs IDs for Windows Update
	n_tty: Fix stall at n_tty_receive_char_special().
	staging: android: ion: Return an ERR_PTR in ion_map_kernel
	n_tty: Access echo_* variables carefully.
	x86/boot: Fix early command-line parsing when matching at end
	ath10k: fix rfc1042 header retrieval in QCA4019 with eth decap mode
	i2c: rcar: fix resume by always initializing registers before transfer
	ipv4: Fix error return value in fib_convert_metrics()
	kprobes/x86: Do not modify singlestep buffer while resuming
	nvme-pci: initialize queue memory before interrupts
	netfilter: nf_tables: use WARN_ON_ONCE instead of BUG_ON in nft_do_chain()
	ARM: dts: imx6q: Use correct SDMA script for SPI5 core
	ubi: fastmap: Correctly handle interrupted erasures in EBA
	mm: hugetlb: yield when prepping struct pages
	tracing: Fix missing return symbol in function_graph output
	scsi: sg: mitigate read/write abuse
	s390: Correct register corruption in critical section cleanup
	drbd: fix access after free
	cifs: Fix infinite loop when using hard mount option
	jbd2: don't mark block as modified if the handle is out of credits
	ext4: make sure bitmaps and the inode table don't overlap with bg descriptors
	ext4: always check block group bounds in ext4_init_block_bitmap()
	ext4: only look at the bg_flags field if it is valid
	ext4: verify the depth of extent tree in ext4_find_extent()
	ext4: include the illegal physical block in the bad map ext4_error msg
	ext4: clear i_data in ext4_inode_info when removing inline data
	ext4: add more inode number paranoia checks
	ext4: add more mount time checks of the superblock
	ext4: check superblock mapped prior to committing
	HID: i2c-hid: Fix "incomplete report" noise
	HID: hiddev: fix potential Spectre v1
	HID: debug: check length before copy_to_user()
	x86/mce: Detect local MCEs properly
	x86/mce: Fix incorrect "Machine check from unknown source" message
	media: cx25840: Use subdev host data for PLL override
	mm, page_alloc: do not break __GFP_THISNODE by zonelist reset
	dm bufio: avoid sleeping while holding the dm_bufio lock
	dm bufio: drop the lock when doing GFP_NOIO allocation
	mtd: rawnand: mxc: set spare area size register explicitly
	dm bufio: don't take the lock in dm_bufio_shrink_count
	mtd: cfi_cmdset_0002: Change definition naming to retry write operation
	mtd: cfi_cmdset_0002: Change erase functions to retry for error
	mtd: cfi_cmdset_0002: Change erase functions to check chip good only
	netfilter: nf_log: don't hold nf_log_mutex during user access
	staging: comedi: quatech_daqp_cs: fix no-op loop daqp_ao_insn_write()
	Linux 4.4.140

Change-Id: I1eb015e1fee548fb958c7e5eb4754b425cfab6b7
Signed-off-by: Greg Kroah-Hartman <gregkh@google.com>

1 files changed, 34 insertions, 17 deletions

diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 6edb9530d7e9..ddc9b8125918 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -980,11 +980,12 @@ void do_machine_check(struct pt_regs *regs, long error_code)
 	int i;
 	int worst = 0;
 	int severity;
+
 	/*
 	 * Establish sequential order between the CPUs entering the machine
 	 * check handler.
 	 */
-	int order;
+	int order = -1;
 	/*
 	 * If no_way_out gets set, there is no safe way to recover from this
 	 * MCE.  If mca_cfg.tolerant is cranked up, we'll try anyway.
@@ -1000,7 +1001,12 @@ void do_machine_check(struct pt_regs *regs, long error_code)
 	char *msg = "Unknown";
 	u64 recover_paddr = ~0ull;
 	int flags = MF_ACTION_REQUIRED;
-	int lmce = 0;
+
+	/*
+	 * MCEs are always local on AMD. Same is determined by MCG_STATUS_LMCES
+	 * on Intel.
+	 */
+	int lmce = 1;
 
 	/* If this CPU is offline, just bail out. */
 	if (cpu_is_offline(smp_processor_id())) {
@@ -1039,17 +1045,23 @@ void do_machine_check(struct pt_regs *regs, long error_code)
 		kill_it = 1;
 
 	/*
-	 * Check if this MCE is signaled to only this logical processor
+	 * Check if this MCE is signaled to only this logical processor,
+	 * on Intel only.
 	 */
-	if (m.mcgstatus & MCG_STATUS_LMCES)
-		lmce = 1;
-	else {
-		/*
-		 * Go through all the banks in exclusion of the other CPUs.
-		 * This way we don't report duplicated events on shared banks
-		 * because the first one to see it will clear it.
-		 * If this is a Local MCE, then no need to perform rendezvous.
-		 */
+	if (m.cpuvendor == X86_VENDOR_INTEL)
+		lmce = m.mcgstatus & MCG_STATUS_LMCES;
+
+	/*
+	 * Local machine check may already know that we have to panic.
+	 * Broadcast machine check begins rendezvous in mce_start()
+	 * Go through all banks in exclusion of the other CPUs. This way we
+	 * don't report duplicated events on shared banks because the first one
+	 * to see it will clear it.
+	 */
+	if (lmce) {
+		if (no_way_out)
+			mce_panic("Fatal local machine check", &m, msg);
+	} else {
 		order = mce_start(&no_way_out);
 	}
 
@@ -1128,12 +1140,17 @@ void do_machine_check(struct pt_regs *regs, long error_code)
 			no_way_out = worst >= MCE_PANIC_SEVERITY;
 	} else {
 		/*
-		 * Local MCE skipped calling mce_reign()
-		 * If we found a fatal error, we need to panic here.
+		 * If there was a fatal machine check we should have
+		 * already called mce_panic earlier in this function.
+		 * Since we re-read the banks, we might have found
+		 * something new. Check again to see if we found a
+		 * fatal error. We call "mce_severity()" again to
+		 * make sure we have the right "msg".
 		 */
-		 if (worst >= MCE_PANIC_SEVERITY && mca_cfg.tolerant < 3)
-			mce_panic("Machine check from unknown source",
-				NULL, NULL);
+		if (worst >= MCE_PANIC_SEVERITY && mca_cfg.tolerant < 3) {
+			mce_severity(&m, cfg->tolerant, &msg, true);
+			mce_panic("Local fatal machine check!", &m, msg);
+		}
 	}
 
 	/*