Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

All three conflicts were cases of simple overlapping
changes.

Signed-off-by: David S. Miller <davem@davemloft.net>

Documentation/PCI/MSI-HOWTO.txt

@@ -94,14 +94,11 @@ has a requirements for a minimum number of vectors the driver can pass a
 min_vecs argument set to this limit, and the PCI core will return -ENOSPC
 if it can't meet the minimum number of vectors.
 
-The flags argument should normally be set to 0, but can be used to pass the
-PCI_IRQ_NOMSI and PCI_IRQ_NOMSIX flag in case a device claims to support
-MSI or MSI-X, but the support is broken, or to pass PCI_IRQ_NOLEGACY in
-case the device does not support legacy interrupt lines.
-
-By default this function will spread the interrupts around the available
-CPUs, but this feature can be disabled by passing the PCI_IRQ_NOAFFINITY
-flag.
+The flags argument is used to specify which type of interrupt can be used
+by the device and the driver (PCI_IRQ_LEGACY, PCI_IRQ_MSI, PCI_IRQ_MSIX).
+A convenient short-hand (PCI_IRQ_ALL_TYPES) is also available to ask for
+any possible kind of interrupt.  If the PCI_IRQ_AFFINITY flag is set,
+pci_alloc_irq_vectors() will spread the interrupts around the available CPUs.
 
 To get the Linux IRQ numbers passed to request_irq() and free_irq() and the
 vectors, use the following function:
@@ -131,7 +128,7 @@ larger than the number supported by the device it will automatically be
 capped to the supported limit, so there is no need to query the number of
 vectors supported beforehand:
 
-	nvec = pci_alloc_irq_vectors(pdev, 1, nvec, 0);
+	nvec = pci_alloc_irq_vectors(pdev, 1, nvec, PCI_IRQ_ALL_TYPES)
 	if (nvec < 0)
 		goto out_err;
 
@@ -140,7 +137,7 @@ interrupts it can request a particular number of interrupts by passing that
 number to pci_alloc_irq_vectors() function as both 'min_vecs' and
 'max_vecs' parameters:
 
-	ret = pci_alloc_irq_vectors(pdev, nvec, nvec, 0);
+	ret = pci_alloc_irq_vectors(pdev, nvec, nvec, PCI_IRQ_ALL_TYPES);
 	if (ret < 0)
 		goto out_err;
 
@@ -148,15 +145,14 @@ The most notorious example of the request type described above is enabling
 the single MSI mode for a device.  It could be done by passing two 1s as
 'min_vecs' and 'max_vecs':
 
-	ret = pci_alloc_irq_vectors(pdev, 1, 1, 0);
+	ret = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_ALL_TYPES);
 	if (ret < 0)
 		goto out_err;
 
 Some devices might not support using legacy line interrupts, in which case
-the PCI_IRQ_NOLEGACY flag can be used to fail the request if the platform
-can't provide MSI or MSI-X interrupts:
+the driver can specify that only MSI or MSI-X is acceptable:
 
-	nvec = pci_alloc_irq_vectors(pdev, 1, nvec, PCI_IRQ_NOLEGACY);
+	nvec = pci_alloc_irq_vectors(pdev, 1, nvec, PCI_IRQ_MSI | PCI_IRQ_MSIX);
 	if (nvec < 0)
 		goto out_err;
 

Documentation/arm64/silicon-errata.txt

@@ -53,6 +53,7 @@ stable kernels.
 | ARM            | Cortex-A57      | #832075         | ARM64_ERRATUM_832075    |
 | ARM            | Cortex-A57      | #852523         | N/A                     |
 | ARM            | Cortex-A57      | #834220         | ARM64_ERRATUM_834220    |
+| ARM            | Cortex-A72      | #853709         | N/A                     |
 | ARM            | MMU-500         | #841119,#826419 | N/A                     |
 |                |                 |                 |                         |
 | Cavium         | ThunderX ITS    | #22375, #24313  | CAVIUM_ERRATUM_22375    |

Documentation/conf.py

@@ -131,7 +131,7 @@ pygments_style = 'sphinx'
 todo_include_todos = False
 
 primary_domain = 'C'
-highlight_language = 'C'
+highlight_language = 'guess'
 
 # -- Options for HTML output ----------------------------------------------
 

Documentation/devicetree/bindings/sound/omap-mcpdm.txt

@@ -8,8 +8,6 @@ Required properties:
 - interrupts: Interrupt number for McPDM
 - interrupt-parent: The parent interrupt controller
 - ti,hwmods: Name of the hwmod associated to the McPDM
-- clocks:  phandle for the pdmclk provider, likely <&twl6040>
-- clock-names: Must be "pdmclk"
 
 Example:
 
@@ -21,11 +19,3 @@ mcpdm: mcpdm@40132000 {
 	interrupt-parent = <&gic>;
 	ti,hwmods = "mcpdm";
 };
-
-In board DTS file the pdmclk needs to be added:
-
-&mcpdm {
-	clocks = <&twl6040>;
-	clock-names = "pdmclk";
-	status = "okay";
-};

Documentation/devicetree/bindings/thermal/thermal.txt

@@ -62,7 +62,7 @@ For more examples of cooling devices, refer to the example sections below.
 Required properties:
 - #cooling-cells:	Used to provide cooling device specific information
   Type: unsigned	while referring to it. Must be at least 2, in order
-  Size: one cell      	to specify minimum and maximum cooling state used
+  Size: one cell	to specify minimum and maximum cooling state used
 			in the reference. The first cell is the minimum
 			cooling state requested and the second cell is
 			the maximum cooling state requested in the reference.
@@ -119,7 +119,7 @@ Required properties:
 Optional property:
 - contribution:		The cooling contribution to the thermal zone of the
   Type: unsigned	referred cooling device at the referred trip point.
-  Size: one cell      	The contribution is a ratio of the sum
+  Size: one cell	The contribution is a ratio of the sum
 			of all cooling contributions within a thermal zone.
 
 Note: Using the THERMAL_NO_LIMIT (-1UL) constant in the cooling-device phandle
@@ -145,7 +145,7 @@ Required properties:
   Size: one cell
 
 - thermal-sensors:	A list of thermal sensor phandles and sensor specifier
-  Type: list of 	used while monitoring the thermal zone.
+  Type: list of		used while monitoring the thermal zone.
   phandles + sensor
   specifier
 
@@ -473,7 +473,7 @@ thermal-zones {
 				  <&adc>;	/* pcb north */
 
 		/* hotspot = 100 * bandgap - 120 * adc + 484 */
-		coefficients = 		<100	-120	484>;
+		coefficients =		<100	-120	484>;
 
 		trips {
 			...
@@ -502,7 +502,7 @@ from the ADC sensor. The binding would be then:
         thermal-sensors =  <&adc>;
 
 		/* hotspot = 1 * adc + 6000 */
-	coefficients = 		<1	6000>;
+	coefficients =		<1	6000>;
 
 (d) - Board thermal
 

Documentation/hwmon/ftsteutates

@@ -19,5 +19,5 @@ enhancements. It can monitor up to 4 voltages, 16 temperatures and
 implemented in this driver.
 
 Specification of the chip can be found here:
-ftp:///pub/Mainboard-OEM-Sales/Services/Software&Tools/Linux_SystemMonitoring&Watchdog&GPIO/BMC-Teutates_Specification_V1.21.pdf
-ftp:///pub/Mainboard-OEM-Sales/Services/Software&Tools/Linux_SystemMonitoring&Watchdog&GPIO/Fujitsu_mainboards-1-Sensors_HowTo-en-US.pdf
+ftp://ftp.ts.fujitsu.com/pub/Mainboard-OEM-Sales/Services/Software&Tools/Linux_SystemMonitoring&Watchdog&GPIO/BMC-Teutates_Specification_V1.21.pdf
+ftp://ftp.ts.fujitsu.com/pub/Mainboard-OEM-Sales/Services/Software&Tools/Linux_SystemMonitoring&Watchdog&GPIO/Fujitsu_mainboards-1-Sensors_HowTo-en-US.pdf

Documentation/kernel-documentation.rst

@@ -366,8 +366,6 @@ Domain`_ references.
 Cross-referencing from reStructuredText
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
-.. highlight:: none
-
 To cross-reference the functions and types defined in the kernel-doc comments
 from reStructuredText documents, please use the `Sphinx C Domain`_
 references. For example::
@@ -390,8 +388,6 @@ For further details, please refer to the `Sphinx C Domain`_ documentation.
 Function documentation
 ----------------------
 
-.. highlight:: c
-
 The general format of a function and function-like macro kernel-doc comment is::
 
   /**
@@ -572,8 +568,6 @@ DocBook XML [DEPRECATED]
 Converting DocBook to Sphinx
 ----------------------------
 
-.. highlight:: none
-
 Over time, we expect all of the documents under ``Documentation/DocBook`` to be
 converted to Sphinx and reStructuredText. For most DocBook XML documents, a good
 enough solution is to use the simple ``Documentation/sphinx/tmplcvt`` script,

Documentation/kernel-parameters.txt

@@ -3032,6 +3032,10 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 				PAGE_SIZE is used as alignment.
 				PCI-PCI bridge can be specified, if resource
 				windows need to be expanded.
+				To specify the alignment for several
+				instances of a device, the PCI vendor,
+				device, subvendor, and subdevice may be
+				specified, e.g., 4096@pci:8086:9c22:103c:198f
 		ecrc=		Enable/disable PCIe ECRC (transaction layer
 				end-to-end CRC checking).
 				bios: Use BIOS/firmware settings. This is the

Documentation/networking/dsa/dsa.txt

@@ -587,26 +587,6 @@ of DSA, would be the its port-based VLAN, used by the associated bridge device.
 TODO
 ====
 
-The platform device problem
----------------------------
-DSA is currently implemented as a platform device driver which is far from ideal
-as was discussed in this thread:
-
-http://permalink.gmane.org/gmane.linux.network/329848
-
-This basically prevents the device driver model to be properly used and applied,
-and support non-MDIO, non-MMIO Ethernet connected switches.
-
-Another problem with the platform device driver approach is that it prevents the
-use of a modular switch drivers build due to a circular dependency, illustrated
-here:
-
-http://comments.gmane.org/gmane.linux.network/345803
-
-Attempts of reworking this has been done here:
-
-https://lwn.net/Articles/643149/
-
 Making SWITCHDEV and DSA converge towards an unified codebase
 -------------------------------------------------------------
 

Documentation/power/basic-pm-debugging.txt

@@ -164,7 +164,32 @@ load n/2 modules more and try again.
 Again, if you find the offending module(s), it(they) must be unloaded every time
 before hibernation, and please report the problem with it(them).
 
-c) Advanced debugging
+c) Using the "test_resume" hibernation option
+
+/sys/power/disk generally tells the kernel what to do after creating a
+hibernation image.  One of the available options is "test_resume" which
+causes the just created image to be used for immediate restoration.  Namely,
+after doing:
+
+# echo test_resume > /sys/power/disk
+# echo disk > /sys/power/state
+
+a hibernation image will be created and a resume from it will be triggered
+immediately without involving the platform firmware in any way.
+
+That test can be used to check if failures to resume from hibernation are
+related to bad interactions with the platform firmware.  That is, if the above
+works every time, but resume from actual hibernation does not work or is
+unreliable, the platform firmware may be responsible for the failures.
+
+On architectures and platforms that support using different kernels to restore
+hibernation images (that is, the kernel used to read the image from storage and
+load it into memory is different from the one included in the image) or support
+kernel address space randomization, it also can be used to check if failures
+to resume may be related to the differences between the restore and image
+kernels.
+
+d) Advanced debugging
 
 In case that hibernation does not work on your system even in the minimal
 configuration and compiling more drivers as modules is not practical or some

Documentation/power/interface.txt

@@ -1,75 +1,76 @@
-Power Management Interface
-
-
-The power management subsystem provides a unified sysfs interface to 
-userspace, regardless of what architecture or platform one is
-running. The interface exists in /sys/power/ directory (assuming sysfs
-is mounted at /sys). 
-
-/sys/power/state controls system power state. Reading from this file
-returns what states are supported, which is hard-coded to 'freeze',
-'standby' (Power-On Suspend), 'mem' (Suspend-to-RAM), and 'disk'
-(Suspend-to-Disk). 
-
-Writing to this file one of those strings causes the system to
-transition into that state. Please see the file
-Documentation/power/states.txt for a description of each of those
-states.
-
-
-/sys/power/disk controls the operating mode of the suspend-to-disk
-mechanism. Suspend-to-disk can be handled in several ways. We have a
-few options for putting the system to sleep - using the platform driver
-(e.g. ACPI or other suspend_ops), powering off the system or rebooting the
-system (for testing).
-
-Additionally, /sys/power/disk can be used to turn on one of the two testing
-modes of the suspend-to-disk mechanism: 'testproc' or 'test'.  If the
-suspend-to-disk mechanism is in the 'testproc' mode, writing 'disk' to
-/sys/power/state will cause the kernel to disable nonboot CPUs and freeze
-tasks, wait for 5 seconds, unfreeze tasks and enable nonboot CPUs.  If it is
-in the 'test' mode, writing 'disk' to /sys/power/state will cause the kernel
-to disable nonboot CPUs and freeze tasks, shrink memory, suspend devices, wait
-for 5 seconds, resume devices, unfreeze tasks and enable nonboot CPUs.  Then,
-we are able to look in the log messages and work out, for example, which code
-is being slow and which device drivers are misbehaving.
-
-Reading from this file will display all supported modes and the currently
-selected one in brackets, for example
-
-	[shutdown] reboot test testproc
-
-Writing to this file will accept one of
-
-       'platform' (only if the platform supports it)
-       'shutdown'
-       'reboot'
-       'testproc'
-       'test'
-
-/sys/power/image_size controls the size of the image created by
-the suspend-to-disk mechanism.  It can be written a string
-representing a non-negative integer that will be used as an upper
-limit of the image size, in bytes.  The suspend-to-disk mechanism will
-do its best to ensure the image size will not exceed that number.  However,
-if this turns out to be impossible, it will try to suspend anyway using the
-smallest image possible.  In particular, if "0" is written to this file, the
-suspend image will be as small as possible.
-
-Reading from this file will display the current image size limit, which
-is set to 2/5 of available RAM by default.
-
-/sys/power/pm_trace controls the code which saves the last PM event point in
-the RTC across reboots, so that you can debug a machine that just hangs
-during suspend (or more commonly, during resume).  Namely, the RTC is only
-used to save the last PM event point if this file contains '1'.  Initially it
-contains '0' which may be changed to '1' by writing a string representing a
-nonzero integer into it.
-
-To use this debugging feature you should attempt to suspend the machine, then
-reboot it and run
-
-	dmesg -s 1000000 | grep 'hash matches'
-
-CAUTION: Using it will cause your machine's real-time (CMOS) clock to be
-set to a random invalid time after a resume.
+Power Management Interface for System Sleep
+
+Copyright (c) 2016 Intel Corp., Rafael J. Wysocki <rafael.j.wysocki@intel.com>
+
+The power management subsystem provides userspace with a unified sysfs interface
+for system sleep regardless of the underlying system architecture or platform.
+The interface is located in the /sys/power/ directory (assuming that sysfs is
+mounted at /sys).
+
+/sys/power/state is the system sleep state control file.
+
+Reading from it returns a list of supported sleep states, encoded as:
+
+'freeze' (Suspend-to-Idle)
+'standby' (Power-On Suspend)
+'mem' (Suspend-to-RAM)
+'disk' (Suspend-to-Disk)
+
+Suspend-to-Idle is always supported.  Suspend-to-Disk is always supported
+too as long the kernel has been configured to support hibernation at all
+(ie. CONFIG_HIBERNATION is set in the kernel configuration file).  Support
+for Suspend-to-RAM and Power-On Suspend depends on the capabilities of the
+platform.
+
+If one of the strings listed in /sys/power/state is written to it, the system
+will attempt to transition into the corresponding sleep state.  Refer to
+Documentation/power/states.txt for a description of each of those states.
+
+/sys/power/disk controls the operating mode of hibernation (Suspend-to-Disk).
+Specifically, it tells the kernel what to do after creating a hibernation image.
+
+Reading from it returns a list of supported options encoded as:
+
+'platform' (put the system into sleep using a platform-provided method)
+'shutdown' (shut the system down)
+'reboot' (reboot the system)
+'suspend' (trigger a Suspend-to-RAM transition)
+'test_resume' (resume-after-hibernation test mode)
+
+The currently selected option is printed in square brackets.
+
+The 'platform' option is only available if the platform provides a special
+mechanism to put the system to sleep after creating a hibernation image (ACPI
+does that, for example).  The 'suspend' option is available if Suspend-to-RAM
+is supported.  Refer to Documentation/power/basic_pm_debugging.txt for the
+description of the 'test_resume' option.
+
+To select an option, write the string representing it to /sys/power/disk.
+
+/sys/power/image_size controls the size of hibernation images.
+
+It can be written a string representing a non-negative integer that will be
+used as a best-effort upper limit of the image size, in bytes.  The hibernation
+core will do its best to ensure that the image size will not exceed that number.
+However, if that turns out to be impossible to achieve, a hibernation image will
+still be created and its size will be as small as possible.  In particular,
+writing '0' to this file will enforce hibernation images to be as small as
+possible.
+
+Reading from this file returns the current image size limit, which is set to
+around 2/5 of available RAM by default.
+
+/sys/power/pm_trace controls the PM trace mechanism saving the last suspend
+or resume event point in the RTC across reboots.
+
+It helps to debug hard lockups or reboots due to device driver failures that
+occur during system suspend or resume (which is more common) more effectively.
+
+If /sys/power/pm_trace contains '1', the fingerprint of each suspend/resume
+event point in turn will be stored in the RTC memory (overwriting the actual
+RTC information), so it will survive a system crash if one occurs right after
+storing it and it can be used later to identify the driver that caused the crash
+to happen (see Documentation/power/s2ram.txt for more information).
+
+Initially it contains '0' which may be changed to '1' by writing a string
+representing a nonzero integer into it.

Documentation/powerpc/transactional_memory.txt

@@ -167,6 +167,8 @@ signal will be rolled back anyway.
 For signals taken in non-TM or suspended mode, we use the
 normal/non-checkpointed stack pointer.
 
+Any transaction initiated inside a sighandler and suspended on return
+from the sighandler to the kernel will get reclaimed and discarded.
 
 Failure cause codes used by kernel
 ==================================

Documentation/sphinx-static/theme_overrides.css

@@ -42,11 +42,12 @@
     caption a.headerlink { opacity: 0; }
     caption a.headerlink:hover { opacity: 1; }
 
-    /* inline literal: drop the borderbox and red color */
+    /* inline literal: drop the borderbox, padding and red color */
 
     code, .rst-content tt, .rst-content code {
         color: inherit;
         border: none;
+        padding: unset;
         background: inherit;
         font-size: 85%;
     }

MAINTAINERS

@@ -890,6 +890,15 @@ S:	Supported
 F:	drivers/gpu/drm/arc/
 F:	Documentation/devicetree/bindings/display/snps,arcpgu.txt
 
+ARM ARCHITECTED TIMER DRIVER
+M:	Mark Rutland <mark.rutland@arm.com>
+M:	Marc Zyngier <marc.zyngier@arm.com>
+L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
+S:	Maintained
+F:	arch/arm/include/asm/arch_timer.h
+F:	arch/arm64/include/asm/arch_timer.h
+F:	drivers/clocksource/arm_arch_timer.c
+
 ARM HDLCD DRM DRIVER
 M:	Liviu Dudau <liviu.dudau@arm.com>
 S:	Supported
@@ -4534,6 +4543,12 @@ L:	linux-edac@vger.kernel.org
 S:	Maintained
 F:	drivers/edac/sb_edac.c
 
+EDAC-SKYLAKE
+M:	Tony Luck <tony.luck@intel.com>
+L:	linux-edac@vger.kernel.org
+S:	Maintained
+F:	drivers/edac/skx_edac.c
+
 EDAC-XGENE
 APPLIED MICRO (APM) X-GENE SOC EDAC
 M:     Loc Ho <lho@apm.com>
@@ -7664,7 +7679,7 @@ L:	linux-rdma@vger.kernel.org
 S:	Supported
 W:	https://github.com/SoftRoCE/rxe-dev/wiki/rxe-dev:-Home
 Q:	http://patchwork.kernel.org/project/linux-rdma/list/
-F:	drivers/infiniband/hw/rxe/
+F:	drivers/infiniband/sw/rxe/
 F:	include/uapi/rdma/rdma_user_rxe.h
 
 MEMBARRIER SUPPORT

Makefile

@@ -1,7 +1,7 @@
 VERSION = 4
 PATCHLEVEL = 8
 SUBLEVEL = 0
-EXTRAVERSION = -rc2
+EXTRAVERSION = -rc4
 NAME = Psychotic Stoned Sheep
 
 # *DOCUMENTATION*

arch/arc/include/asm/entry.h

@@ -142,7 +142,7 @@
 
 #ifdef CONFIG_ARC_CURR_IN_REG
 	; Retrieve orig r25 and save it with rest of callee_regs
-	ld.as   r12, [r12, PT_user_r25]
+	ld	r12, [r12, PT_user_r25]
 	PUSH	r12
 #else
 	PUSH	r25
@@ -198,7 +198,7 @@
 
 	; SP is back to start of pt_regs
 #ifdef CONFIG_ARC_CURR_IN_REG
-	st.as   r12, [sp, PT_user_r25]
+	st	r12, [sp, PT_user_r25]
 #endif
 .endm
 

arch/arc/include/asm/irqflags-compact.h

@@ -188,10 +188,10 @@ static inline int arch_irqs_disabled(void)
 .endm
 
 .macro IRQ_ENABLE  scratch
+	TRACE_ASM_IRQ_ENABLE
 	lr	\scratch, [status32]
 	or	\scratch, \scratch, (STATUS_E1_MASK | STATUS_E2_MASK)
 	flag	\scratch
-	TRACE_ASM_IRQ_ENABLE
 .endm
 
 #endif	/* __ASSEMBLY__ */

arch/arc/include/asm/pgtable.h

@@ -280,7 +280,7 @@ static inline void pmd_set(pmd_t *pmdp, pte_t *ptep)
 
 #define pte_page(pte)		pfn_to_page(pte_pfn(pte))
 #define mk_pte(page, prot)	pfn_pte(page_to_pfn(page), prot)
-#define pfn_pte(pfn, prot)	(__pte(((pte_t)(pfn) << PAGE_SHIFT) | pgprot_val(prot)))
+#define pfn_pte(pfn, prot)	__pte(((pfn) << PAGE_SHIFT) | pgprot_val(prot))
 
 /* Don't use virt_to_pfn for macros below: could cause truncations for PAE40*/
 #define pte_pfn(pte)		(pte_val(pte) >> PAGE_SHIFT)

arch/arc/include/uapi/asm/elf.h

@@ -13,8 +13,15 @@
 
 /* Machine specific ELF Hdr flags */
 #define EF_ARC_OSABI_MSK	0x00000f00
-#define EF_ARC_OSABI_ORIG	0x00000000   /* MUST be zero for back-compat */
-#define EF_ARC_OSABI_CURRENT	0x00000300   /* v3 (no legacy syscalls) */
+
+#define EF_ARC_OSABI_V3		0x00000300   /* v3 (no legacy syscalls) */
+#define EF_ARC_OSABI_V4		0x00000400   /* v4 (64bit data any reg align) */
+
+#if __GNUC__ < 6
+#define EF_ARC_OSABI_CURRENT	EF_ARC_OSABI_V3
+#else
+#define EF_ARC_OSABI_CURRENT	EF_ARC_OSABI_V4
+#endif
 
 typedef unsigned long elf_greg_t;
 typedef unsigned long elf_fpregset_t;

arch/arc/kernel/arcksyms.c

@@ -28,6 +28,7 @@ extern void __muldf3(void);
 extern void __divdf3(void);
 extern void __floatunsidf(void);
 extern void __floatunsisf(void);
+extern void __udivdi3(void);
 
 EXPORT_SYMBOL(__ashldi3);
 EXPORT_SYMBOL(__ashrdi3);
@@ -45,6 +46,7 @@ EXPORT_SYMBOL(__muldf3);
 EXPORT_SYMBOL(__divdf3);
 EXPORT_SYMBOL(__floatunsidf);
 EXPORT_SYMBOL(__floatunsisf);
+EXPORT_SYMBOL(__udivdi3);
 
 /* ARC optimised assembler routines */
 EXPORT_SYMBOL(memset);

arch/arc/kernel/process.c

@@ -199,7 +199,7 @@ int elf_check_arch(const struct elf32_hdr *x)
 	}
 
 	eflags = x->e_flags;
-	if ((eflags & EF_ARC_OSABI_MSK) < EF_ARC_OSABI_CURRENT) {
+	if ((eflags & EF_ARC_OSABI_MSK) != EF_ARC_OSABI_CURRENT) {
 		pr_err("ABI mismatch - you need newer toolchain\n");
 		force_sigsegv(SIGSEGV, current);
 		return 0;

arch/arc/kernel/setup.c

@@ -291,8 +291,10 @@ static char *arc_extn_mumbojumbo(int cpu_id, char *buf, int len)
 			       cpu->dccm.base_addr, TO_KB(cpu->dccm.sz),
 			       cpu->iccm.base_addr, TO_KB(cpu->iccm.sz));
 
-	n += scnprintf(buf + n, len - n,
-		       "OS ABI [v3]\t: no-legacy-syscalls\n");
+	n += scnprintf(buf + n, len - n, "OS ABI [v%d]\t: %s\n",
+			EF_ARC_OSABI_CURRENT >> 8,
+			EF_ARC_OSABI_CURRENT == EF_ARC_OSABI_V3 ?
+			"no-legacy-syscalls" : "64-bit data any register aligned");
 
 	return buf;
 }

arch/arc/mm/cache.c

@@ -921,6 +921,15 @@ void arc_cache_init(void)
 
 	printk(arc_cache_mumbojumbo(0, str, sizeof(str)));
 
+	/*
+	 * Only master CPU needs to execute rest of function:
+	 *  - Assume SMP so all cores will have same cache config so
+	 *    any geomtry checks will be same for all
+	 *  - IOC setup / dma callbacks only need to be setup once
+	 */
+	if (cpu)
+		return;
+
 	if (IS_ENABLED(CONFIG_ARC_HAS_ICACHE)) {
 		struct cpuinfo_arc_cache *ic = &cpuinfo_arc700[cpu].icache;
 

arch/arc/mm/highmem.c

@@ -61,6 +61,7 @@ void *kmap(struct page *page)
 
 	return kmap_high(page);
 }
+EXPORT_SYMBOL(kmap);
 
 void *kmap_atomic(struct page *page)
 {

arch/arm/kernel/entry-armv.S

@@ -295,6 +295,7 @@ __und_svc_fault:
 	bl	__und_fault
 
 __und_svc_finish:
+	get_thread_info tsk
 	ldr	r5, [sp, #S_PSR]		@ Get SVC cpsr
 	svc_exit r5				@ return from exception
  UNWIND(.fnend		)

arch/arm/kvm/mmu.c

@@ -1309,7 +1309,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	smp_rmb();
 
 	pfn = gfn_to_pfn_prot(kvm, gfn, write_fault, &writable);
-	if (is_error_pfn(pfn))
+	if (is_error_noslot_pfn(pfn))
 		return -EFAULT;
 
 	if (kvm_is_device_pfn(pfn)) {

arch/arm/mach-imx/gpc.c

@@ -271,6 +271,12 @@ static int __init imx_gpc_init(struct device_node *node,
 	for (i = 0; i < IMR_NUM; i++)
 		writel_relaxed(~0, gpc_base + GPC_IMR1 + i * 4);
 
+	/*
+	 * Clear the OF_POPULATED flag set in of_irq_init so that
+	 * later the GPC power domain driver will not be skipped.
+	 */
+	of_node_clear_flag(node, OF_POPULATED);
+
 	return 0;
 }
 IRQCHIP_DECLARE(imx_gpc, "fsl,imx6q-gpc", imx_gpc_init);

arch/arm/mach-pxa/idp.c

@@ -83,7 +83,8 @@ static struct resource smc91x_resources[] = {
 };
 
 static struct smc91x_platdata smc91x_platdata = {
-	.flags = SMC91X_USE_32BIT | SMC91X_USE_DMA | SMC91X_NOWAIT,
+	.flags = SMC91X_USE_8BIT | SMC91X_USE_16BIT | SMC91X_USE_32BIT |
+		 SMC91X_USE_DMA | SMC91X_NOWAIT,
 };
 
 static struct platform_device smc91x_device = {

arch/arm/mach-pxa/xcep.c

@@ -120,7 +120,8 @@ static struct resource smc91x_resources[] = {
 };
 
 static struct smc91x_platdata xcep_smc91x_info = {
-	.flags	= SMC91X_USE_32BIT | SMC91X_NOWAIT | SMC91X_USE_DMA,
+	.flags	= SMC91X_USE_8BIT | SMC91X_USE_16BIT | SMC91X_USE_32BIT |
+		  SMC91X_NOWAIT | SMC91X_USE_DMA,
 };
 
 static struct platform_device smc91x_device = {

arch/arm/mach-realview/core.c

@@ -93,7 +93,8 @@ static struct smsc911x_platform_config smsc911x_config = {
 };
 
 static struct smc91x_platdata smc91x_platdata = {
-	.flags = SMC91X_USE_32BIT | SMC91X_NOWAIT,
+	.flags = SMC91X_USE_8BIT | SMC91X_USE_16BIT | SMC91X_USE_32BIT |
+		 SMC91X_NOWAIT,
 };
 
 static struct platform_device realview_eth_device = {

arch/arm/mach-sa1100/pleb.c

@@ -45,7 +45,7 @@ static struct resource smc91x_resources[] = {
 };
 
 static struct smc91x_platdata smc91x_platdata = {
-	.flags = SMC91X_USE_16BIT | SMC91X_NOWAIT,
+	.flags = SMC91X_USE_16BIT | SMC91X_USE_8BIT | SMC91X_NOWAIT,
 };
 
 static struct platform_device smc91x_device = {

arch/arm/mm/mmu.c

@@ -728,7 +728,8 @@ static void *__init late_alloc(unsigned long sz)
 {
 	void *ptr = (void *)__get_free_pages(PGALLOC_GFP, get_order(sz));
 
-	BUG_ON(!ptr);
+	if (!ptr || !pgtable_page_ctor(virt_to_page(ptr)))
+		BUG();
 	return ptr;
 }
 
@@ -1155,10 +1156,19 @@ void __init sanity_check_meminfo(void)
 {
 	phys_addr_t memblock_limit = 0;
 	int highmem = 0;
-	phys_addr_t vmalloc_limit = __pa(vmalloc_min - 1) + 1;
+	u64 vmalloc_limit;
 	struct memblock_region *reg;
 	bool should_use_highmem = false;
 
+	/*
+	 * Let's use our own (unoptimized) equivalent of __pa() that is
+	 * not affected by wrap-arounds when sizeof(phys_addr_t) == 4.
+	 * The result is used as the upper bound on physical memory address
+	 * and may itself be outside the valid range for which phys_addr_t
+	 * and therefore __pa() is defined.
+	 */
+	vmalloc_limit = (u64)(uintptr_t)vmalloc_min - PAGE_OFFSET + PHYS_OFFSET;
+
 	for_each_memblock(memory, reg) {
 		phys_addr_t block_start = reg->base;
 		phys_addr_t block_end = reg->base + reg->size;
@@ -1183,10 +1193,11 @@ void __init sanity_check_meminfo(void)
 			if (reg->size > size_limit) {
 				phys_addr_t overlap_size = reg->size - size_limit;
 
-				pr_notice("Truncating RAM at %pa-%pa to -%pa",
-					  &block_start, &block_end, &vmalloc_limit);
-				memblock_remove(vmalloc_limit, overlap_size);
+				pr_notice("Truncating RAM at %pa-%pa",
+					  &block_start, &block_end);
 				block_end = vmalloc_limit;
+				pr_cont(" to -%pa", &block_end);
+				memblock_remove(vmalloc_limit, overlap_size);
 				should_use_highmem = true;
 			}
 		}

arch/arm/xen/enlighten.c

@@ -50,7 +50,7 @@ DEFINE_PER_CPU(struct vcpu_info *, xen_vcpu);
 static struct vcpu_info __percpu *xen_vcpu_info;
 
 /* Linux <-> Xen vCPU id mapping */
-DEFINE_PER_CPU(int, xen_vcpu_id) = -1;
+DEFINE_PER_CPU(uint32_t, xen_vcpu_id);
 EXPORT_PER_CPU_SYMBOL(xen_vcpu_id);
 
 /* These are unused until we support booting "pre-ballooned" */

arch/arm64/kernel/head.S

@@ -757,6 +757,9 @@ ENTRY(__enable_mmu)
 	isb
 	bl	__create_page_tables		// recreate kernel mapping
 
+	tlbi	vmalle1				// Remove any stale TLB entries
+	dsb	nsh
+
 	msr	sctlr_el1, x19			// re-enable the MMU
 	isb
 	ic	iallu				// flush instructions fetched

arch/arm64/kernel/sleep.S

@@ -101,12 +101,20 @@ ENTRY(cpu_resume)
 	bl	el2_setup		// if in EL2 drop to EL1 cleanly
 	/* enable the MMU early - so we can access sleep_save_stash by va */
 	adr_l	lr, __enable_mmu	/* __cpu_setup will return here */
-	ldr	x27, =_cpu_resume	/* __enable_mmu will branch here */
+	adr_l	x27, _resume_switched	/* __enable_mmu will branch here */
 	adrp	x25, idmap_pg_dir
 	adrp	x26, swapper_pg_dir
 	b	__cpu_setup
 ENDPROC(cpu_resume)
 
+	.pushsection	".idmap.text", "ax"
+_resume_switched:
+	ldr	x8, =_cpu_resume
+	br	x8
+ENDPROC(_resume_switched)
+	.ltorg
+	.popsection
+
 ENTRY(_cpu_resume)
 	mrs	x1, mpidr_el1
 	adrp	x8, mpidr_hash

arch/arm64/kvm/hyp/switch.c

@@ -256,7 +256,7 @@ static int __hyp_text __guest_run(struct kvm_vcpu *vcpu)
 
 	/*
 	 * We must restore the 32-bit state before the sysregs, thanks
-	 * to Cortex-A57 erratum #852523.
+	 * to erratum #852523 (Cortex-A57) or #853709 (Cortex-A72).
 	 */
 	__sysreg32_restore_state(vcpu);
 	__sysreg_restore_guest_state(guest_ctxt);

arch/arm64/kvm/sys_regs.c

@@ -823,14 +823,6 @@ static bool access_pmuserenr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
  * Architected system registers.
  * Important: Must be sorted ascending by Op0, Op1, CRn, CRm, Op2
  *
- * We could trap ID_DFR0 and tell the guest we don't support performance
- * monitoring.  Unfortunately the patch to make the kernel check ID_DFR0 was
- * NAKed, so it will read the PMCR anyway.
- *
- * Therefore we tell the guest we have 0 counters.  Unfortunately, we
- * must always support PMCCNTR (the cycle counter): we just RAZ/WI for
- * all PM registers, which doesn't crash the guest kernel at least.
- *
  * Debug handling: We do trap most, if not all debug related system
  * registers. The implementation is good enough to ensure that a guest
  * can use these with minimal performance degradation. The drawback is
@@ -1360,7 +1352,7 @@ static const struct sys_reg_desc cp15_regs[] = {
 	{ Op1( 0), CRn(10), CRm( 3), Op2( 1), access_vm_reg, NULL, c10_AMAIR1 },
 
 	/* ICC_SRE */
-	{ Op1( 0), CRn(12), CRm(12), Op2( 5), trap_raz_wi },
+	{ Op1( 0), CRn(12), CRm(12), Op2( 5), access_gic_sre },
 
 	{ Op1( 0), CRn(13), CRm( 0), Op2( 1), access_vm_reg, NULL, c13_CID },
 

arch/arm64/mm/dump.c

@@ -242,7 +242,7 @@ static void note_page(struct pg_state *st, unsigned long addr, unsigned level,
 
 static void walk_pte(struct pg_state *st, pmd_t *pmd, unsigned long start)
 {
-	pte_t *pte = pte_offset_kernel(pmd, 0);
+	pte_t *pte = pte_offset_kernel(pmd, 0UL);
 	unsigned long addr;
 	unsigned i;
 
@@ -254,7 +254,7 @@ static void walk_pte(struct pg_state *st, pmd_t *pmd, unsigned long start)
 
 static void walk_pmd(struct pg_state *st, pud_t *pud, unsigned long start)
 {
-	pmd_t *pmd = pmd_offset(pud, 0);
+	pmd_t *pmd = pmd_offset(pud, 0UL);
 	unsigned long addr;
 	unsigned i;
 
@@ -271,7 +271,7 @@ static void walk_pmd(struct pg_state *st, pud_t *pud, unsigned long start)
 
 static void walk_pud(struct pg_state *st, pgd_t *pgd, unsigned long start)
 {
-	pud_t *pud = pud_offset(pgd, 0);
+	pud_t *pud = pud_offset(pgd, 0UL);
 	unsigned long addr;
 	unsigned i;
 

arch/arm64/mm/numa.c

@@ -23,6 +23,8 @@
 #include <linux/module.h>
 #include <linux/of.h>
 
+#include <asm/acpi.h>
+
 struct pglist_data *node_data[MAX_NUMNODES] __read_mostly;
 EXPORT_SYMBOL(node_data);
 nodemask_t numa_nodes_parsed __initdata;

arch/blackfin/mach-bf561/boards/cm_bf561.c

@@ -146,7 +146,8 @@ static struct platform_device hitachi_fb_device = {
 #include <linux/smc91x.h>
 
 static struct smc91x_platdata smc91x_info = {
-	.flags = SMC91X_USE_32BIT | SMC91X_NOWAIT,
+	.flags = SMC91X_USE_8BIT | SMC91X_USE_16BIT | SMC91X_USE_32BIT |
+		 SMC91X_NOWAIT,
 	.leda = RPC_LED_100_10,
 	.ledb = RPC_LED_TX_RX,
 };

arch/blackfin/mach-bf561/boards/ezkit.c

@@ -134,7 +134,8 @@ static struct platform_device net2272_bfin_device = {
 #include <linux/smc91x.h>
 
 static struct smc91x_platdata smc91x_info = {
-	.flags = SMC91X_USE_32BIT | SMC91X_NOWAIT,
+	.flags = SMC91X_USE_8BIT | SMC91X_USE_16BIT | SMC91X_USE_32BIT |
+		 SMC91X_NOWAIT,
 	.leda = RPC_LED_100_10,
 	.ledb = RPC_LED_TX_RX,
 };

arch/mips/include/asm/page.h

@@ -164,7 +164,7 @@ typedef struct { unsigned long pgprot; } pgprot_t;
  */
 static inline unsigned long ___pa(unsigned long x)
 {
-	if (config_enabled(CONFIG_64BIT)) {
+	if (IS_ENABLED(CONFIG_64BIT)) {
 		/*
 		 * For MIPS64 the virtual address may either be in one of
 		 * the compatibility segements ckseg0 or ckseg1, or it may
@@ -173,7 +173,7 @@ static inline unsigned long ___pa(unsigned long x)
 		return x < CKSEG0 ? XPHYSADDR(x) : CPHYSADDR(x);
 	}
 
-	if (!config_enabled(CONFIG_EVA)) {
+	if (!IS_ENABLED(CONFIG_EVA)) {
 		/*
 		 * We're using the standard MIPS32 legacy memory map, ie.
 		 * the address x is going to be in kseg0 or kseg1. We can

arch/mips/kvm/mmu.c

@@ -40,7 +40,7 @@ static int kvm_mips_map_page(struct kvm *kvm, gfn_t gfn)
 	srcu_idx = srcu_read_lock(&kvm->srcu);
 	pfn = gfn_to_pfn(kvm, gfn);
 
-	if (is_error_pfn(pfn)) {
+	if (is_error_noslot_pfn(pfn)) {
 		kvm_err("Couldn't get pfn for gfn %#llx!\n", gfn);
 		err = -EFAULT;
 		goto out;

arch/parisc/include/uapi/asm/errno.h

@@ -97,10 +97,10 @@
 #define	ENOTCONN	235	/* Transport endpoint is not connected */
 #define	ESHUTDOWN	236	/* Cannot send after transport endpoint shutdown */
 #define	ETOOMANYREFS	237	/* Too many references: cannot splice */
-#define EREFUSED	ECONNREFUSED	/* for HP's NFS apparently */
 #define	ETIMEDOUT	238	/* Connection timed out */
 #define	ECONNREFUSED	239	/* Connection refused */
-#define EREMOTERELEASE	240	/* Remote peer released connection */
+#define	EREFUSED	ECONNREFUSED	/* for HP's NFS apparently */
+#define	EREMOTERELEASE	240	/* Remote peer released connection */
 #define	EHOSTDOWN	241	/* Host is down */
 #define	EHOSTUNREACH	242	/* No route to host */
 

arch/parisc/kernel/processor.c

@@ -51,8 +51,6 @@ EXPORT_SYMBOL(_parisc_requires_coherency);
 
 DEFINE_PER_CPU(struct cpuinfo_parisc, cpu_data);
 
-extern int update_cr16_clocksource(void);	/* from time.c */
-
 /*
 **  	PARISC CPU driver - claim "device" and initialize CPU data structures.
 **
@@ -228,12 +226,6 @@ static int processor_probe(struct parisc_device *dev)
 	}
 #endif
 
-	/* If we've registered more than one cpu,
-	 * we'll use the jiffies clocksource since cr16
-	 * is not synchronized between CPUs.
-	 */
-	update_cr16_clocksource();
-
 	return 0;
 }
 

arch/parisc/kernel/time.c

@@ -221,18 +221,6 @@ static struct clocksource clocksource_cr16 = {
 	.flags			= CLOCK_SOURCE_IS_CONTINUOUS,
 };
 
-int update_cr16_clocksource(void)
-{
-	/* since the cr16 cycle counters are not synchronized across CPUs,
-	   we'll check if we should switch to a safe clocksource: */
-	if (clocksource_cr16.rating != 0 && num_online_cpus() > 1) {
-		clocksource_change_rating(&clocksource_cr16, 0);
-		return 1;
-	}
-
-	return 0;
-}
-
 void __init start_cpu_itimer(void)
 {
 	unsigned int cpu = smp_processor_id();

arch/powerpc/include/asm/cputhreads.h

@@ -3,6 +3,7 @@
 
 #ifndef __ASSEMBLY__
 #include <linux/cpumask.h>
+#include <asm/cpu_has_feature.h>
 
 /*
  * Mapping of threads to cores

arch/powerpc/include/asm/hmi.h

@@ -21,7 +21,7 @@
 #ifndef __ASM_PPC64_HMI_H__
 #define __ASM_PPC64_HMI_H__
 
-#ifdef CONFIG_PPC_BOOK3S_64
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
 
 #define	CORE_TB_RESYNC_REQ_BIT		63
 #define MAX_SUBCORE_PER_CORE		4

arch/powerpc/include/asm/paca.h

@@ -183,11 +183,6 @@ struct paca_struct {
 	 */
 	u16 in_mce;
 	u8 hmi_event_available;		 /* HMI event is available */
-	/*
-	 * Bitmap for sibling subcore status. See kvm/book3s_hv_ras.c for
-	 * more details
-	 */
-	struct sibling_subcore_state *sibling_subcore_state;
 #endif
 
 	/* Stuff for accurate time accounting */
@@ -202,6 +197,13 @@ struct paca_struct {
 	struct kvmppc_book3s_shadow_vcpu shadow_vcpu;
 #endif
 	struct kvmppc_host_state kvm_hstate;
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+	/*
+	 * Bitmap for sibling subcore status. See kvm/book3s_hv_ras.c for
+	 * more details
+	 */
+	struct sibling_subcore_state *sibling_subcore_state;
+#endif
 #endif
 };
 

arch/powerpc/include/asm/pci-bridge.h

@@ -301,6 +301,7 @@ extern void pci_process_bridge_OF_ranges(struct pci_controller *hose,
 /* Allocate & free a PCI host bridge structure */
 extern struct pci_controller *pcibios_alloc_controller(struct device_node *dev);
 extern void pcibios_free_controller(struct pci_controller *phb);
+extern void pcibios_free_controller_deferred(struct pci_host_bridge *bridge);
 
 #ifdef CONFIG_PCI
 extern int pcibios_vaddr_is_ioport(void __iomem *address);

arch/powerpc/kernel/Makefile

@@ -41,7 +41,7 @@ obj-$(CONFIG_VDSO32)		+= vdso32/
 obj-$(CONFIG_HAVE_HW_BREAKPOINT)	+= hw_breakpoint.o
 obj-$(CONFIG_PPC_BOOK3S_64)	+= cpu_setup_ppc970.o cpu_setup_pa6t.o
 obj-$(CONFIG_PPC_BOOK3S_64)	+= cpu_setup_power.o
-obj-$(CONFIG_PPC_BOOK3S_64)	+= mce.o mce_power.o hmi.o
+obj-$(CONFIG_PPC_BOOK3S_64)	+= mce.o mce_power.o
 obj-$(CONFIG_PPC_BOOK3E_64)	+= exceptions-64e.o idle_book3e.o
 obj-$(CONFIG_PPC64)		+= vdso64/
 obj-$(CONFIG_ALTIVEC)		+= vecemu.o

arch/powerpc/kernel/entry_64.S

@@ -368,13 +368,13 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
 tabort_syscall:
 	/* Firstly we need to enable TM in the kernel */
 	mfmsr	r10
-	li	r13, 1
-	rldimi	r10, r13, MSR_TM_LG, 63-MSR_TM_LG
+	li	r9, 1
+	rldimi	r10, r9, MSR_TM_LG, 63-MSR_TM_LG
 	mtmsrd	r10, 0
 
 	/* tabort, this dooms the transaction, nothing else */
-	li	r13, (TM_CAUSE_SYSCALL|TM_CAUSE_PERSISTENT)
-	TABORT(R13)
+	li	r9, (TM_CAUSE_SYSCALL|TM_CAUSE_PERSISTENT)
+	TABORT(R9)
 
 	/*
 	 * Return directly to userspace. We have corrupted user register state,
@@ -382,8 +382,8 @@ tabort_syscall:
 	 * resume after the tbegin of the aborted transaction with the
 	 * checkpointed register state.
 	 */
-	li	r13, MSR_RI
-	andc	r10, r10, r13
+	li	r9, MSR_RI
+	andc	r10, r10, r9
 	mtmsrd	r10, 1
 	mtspr	SPRN_SRR0, r11
 	mtspr	SPRN_SRR1, r12

arch/powerpc/kernel/exceptions-64s.S

@@ -485,7 +485,23 @@ machine_check_fwnmi:
 	EXCEPTION_PROLOG_0(PACA_EXMC)
 machine_check_pSeries_0:
 	EXCEPTION_PROLOG_1(PACA_EXMC, KVMTEST, 0x200)
-	EXCEPTION_PROLOG_PSERIES_1(machine_check_common, EXC_STD)
+	/*
+	 * The following is essentially EXCEPTION_PROLOG_PSERIES_1 with the
+	 * difference that MSR_RI is not enabled, because PACA_EXMC is being
+	 * used, so nested machine check corrupts it. machine_check_common
+	 * enables MSR_RI.
+	 */
+	ld	r12,PACAKBASE(r13)
+	ld	r10,PACAKMSR(r13)
+	xori	r10,r10,MSR_RI
+	mfspr	r11,SPRN_SRR0
+	LOAD_HANDLER(r12, machine_check_common)
+	mtspr	SPRN_SRR0,r12
+	mfspr	r12,SPRN_SRR1
+	mtspr	SPRN_SRR1,r10
+	rfid
+	b	.	/* prevent speculative execution */
+
 	KVM_HANDLER_SKIP(PACA_EXMC, EXC_STD, 0x200)
 	KVM_HANDLER_SKIP(PACA_EXGEN, EXC_STD, 0x300)
 	KVM_HANDLER_SKIP(PACA_EXSLB, EXC_STD, 0x380)
@@ -969,14 +985,17 @@ ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX)
 machine_check_common:
 
 	mfspr	r10,SPRN_DAR
-	std	r10,PACA_EXGEN+EX_DAR(r13)
+	std	r10,PACA_EXMC+EX_DAR(r13)
 	mfspr	r10,SPRN_DSISR
-	stw	r10,PACA_EXGEN+EX_DSISR(r13)
+	stw	r10,PACA_EXMC+EX_DSISR(r13)
 	EXCEPTION_PROLOG_COMMON(0x200, PACA_EXMC)
 	FINISH_NAP
 	RECONCILE_IRQ_STATE(r10, r11)
-	ld	r3,PACA_EXGEN+EX_DAR(r13)
-	lwz	r4,PACA_EXGEN+EX_DSISR(r13)
+	ld	r3,PACA_EXMC+EX_DAR(r13)
+	lwz	r4,PACA_EXMC+EX_DSISR(r13)
+	/* Enable MSR_RI when finished with PACA_EXMC */
+	li	r10,MSR_RI
+	mtmsrd 	r10,1
 	std	r3,_DAR(r1)
 	std	r4,_DSISR(r1)
 	bl	save_nvgprs

arch/powerpc/kernel/kprobes.c

@@ -29,7 +29,7 @@
 #include <linux/kprobes.h>
 #include <linux/ptrace.h>
 #include <linux/preempt.h>
-#include <linux/module.h>
+#include <linux/extable.h>
 #include <linux/kdebug.h>
 #include <linux/slab.h>
 #include <asm/code-patching.h>

arch/powerpc/kernel/pci-common.c

@@ -153,6 +153,42 @@ void pcibios_free_controller(struct pci_controller *phb)
 }
 EXPORT_SYMBOL_GPL(pcibios_free_controller);
 
+/*
+ * This function is used to call pcibios_free_controller()
+ * in a deferred manner: a callback from the PCI subsystem.
+ *
+ * _*DO NOT*_ call pcibios_free_controller() explicitly if
+ * this is used (or it may access an invalid *phb pointer).
+ *
+ * The callback occurs when all references to the root bus
+ * are dropped (e.g., child buses/devices and their users).
+ *
+ * It's called as .release_fn() of 'struct pci_host_bridge'
+ * which is associated with the 'struct pci_controller.bus'
+ * (root bus) - it expects .release_data to hold a pointer
+ * to 'struct pci_controller'.
+ *
+ * In order to use it, register .release_fn()/release_data
+ * like this:
+ *
+ * pci_set_host_bridge_release(bridge,
+ *                             pcibios_free_controller_deferred
+ *                             (void *) phb);
+ *
+ * e.g. in the pcibios_root_bridge_prepare() callback from
+ * pci_create_root_bus().
+ */
+void pcibios_free_controller_deferred(struct pci_host_bridge *bridge)
+{
+	struct pci_controller *phb = (struct pci_controller *)
+					 bridge->release_data;
+
+	pr_debug("domain %d, dynamic %d\n", phb->global_number, phb->is_dynamic);
+
+	pcibios_free_controller(phb);
+}
+EXPORT_SYMBOL_GPL(pcibios_free_controller_deferred);
+
 /*
  * The function is used to return the minimal alignment
  * for memory or I/O windows of the associated P2P bridge.

arch/powerpc/kernel/prom_init.c

@@ -695,7 +695,7 @@ unsigned char ibm_architecture_vec[] = {
 	OV4_MIN_ENT_CAP,		/* minimum VP entitled capacity */
 
 	/* option vector 5: PAPR/OF options */
-	VECTOR_LENGTH(18),		/* length */
+	VECTOR_LENGTH(21),		/* length */
 	0,				/* don't ignore, don't halt */
 	OV5_FEAT(OV5_LPAR) | OV5_FEAT(OV5_SPLPAR) | OV5_FEAT(OV5_LARGE_PAGES) |
 	OV5_FEAT(OV5_DRCONF_MEMORY) | OV5_FEAT(OV5_DONATE_DEDICATE_CPU) |
@@ -726,8 +726,11 @@ unsigned char ibm_architecture_vec[] = {
 	0,
 	0,
 	OV5_FEAT(OV5_PFO_HW_RNG) | OV5_FEAT(OV5_PFO_HW_ENCR) |
-	OV5_FEAT(OV5_PFO_HW_842),
-	OV5_FEAT(OV5_SUB_PROCESSORS),
+	OV5_FEAT(OV5_PFO_HW_842),				/* Byte 17 */
+	0,							/* Byte 18 */
+	0,							/* Byte 19 */
+	0,							/* Byte 20 */
+	OV5_FEAT(OV5_SUB_PROCESSORS),				/* Byte 21 */
 
 	/* option vector 6: IBM PAPR hints */
 	VECTOR_LENGTH(3),		/* length */

arch/powerpc/kernel/signal_32.c

@@ -1226,7 +1226,21 @@ long sys_rt_sigreturn(int r3, int r4, int r5, int r6, int r7, int r8,
 		(regs->gpr[1] + __SIGNAL_FRAMESIZE + 16);
 	if (!access_ok(VERIFY_READ, rt_sf, sizeof(*rt_sf)))
 		goto bad;
+
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+	/*
+	 * If there is a transactional state then throw it away.
+	 * The purpose of a sigreturn is to destroy all traces of the
+	 * signal frame, this includes any transactional state created
+	 * within in. We only check for suspended as we can never be
+	 * active in the kernel, we are active, there is nothing better to
+	 * do than go ahead and Bad Thing later.
+	 * The cause is not important as there will never be a
+	 * recheckpoint so it's not user visible.
+	 */
+	if (MSR_TM_SUSPENDED(mfmsr()))
+		tm_reclaim_current(0);
+
 	if (__get_user(tmp, &rt_sf->uc.uc_link))
 		goto bad;
 	uc_transact = (struct ucontext __user *)(uintptr_t)tmp;

arch/powerpc/kernel/signal_64.c

@@ -676,7 +676,21 @@ int sys_rt_sigreturn(unsigned long r3, unsigned long r4, unsigned long r5,
 	if (__copy_from_user(&set, &uc->uc_sigmask, sizeof(set)))
 		goto badframe;
 	set_current_blocked(&set);
+
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+	/*
+	 * If there is a transactional state then throw it away.
+	 * The purpose of a sigreturn is to destroy all traces of the
+	 * signal frame, this includes any transactional state created
+	 * within in. We only check for suspended as we can never be
+	 * active in the kernel, we are active, there is nothing better to
+	 * do than go ahead and Bad Thing later.
+	 * The cause is not important as there will never be a
+	 * recheckpoint so it's not user visible.
+	 */
+	if (MSR_TM_SUSPENDED(mfmsr()))
+		tm_reclaim_current(0);
+
 	if (__get_user(msr, &uc->uc_mcontext.gp_regs[PT_MSR]))
 		goto badframe;
 	if (MSR_TM_ACTIVE(msr)) {

arch/powerpc/kernel/smp.c

@@ -830,7 +830,7 @@ int __cpu_disable(void)
 
 	/* Update sibling maps */
 	base = cpu_first_thread_sibling(cpu);
-	for (i = 0; i < threads_per_core; i++) {
+	for (i = 0; i < threads_per_core && base + i < nr_cpu_ids; i++) {
 		cpumask_clear_cpu(cpu, cpu_sibling_mask(base + i));
 		cpumask_clear_cpu(base + i, cpu_sibling_mask(cpu));
 		cpumask_clear_cpu(cpu, cpu_core_mask(base + i));

arch/powerpc/kernel/traps.c

@@ -25,7 +25,8 @@
 #include <linux/user.h>
 #include <linux/interrupt.h>
 #include <linux/init.h>
-#include <linux/module.h>
+#include <linux/extable.h>
+#include <linux/module.h>	/* print_modules */
 #include <linux/prctl.h>
 #include <linux/delay.h>
 #include <linux/kprobes.h>

arch/powerpc/kvm/Makefile

@@ -78,6 +78,7 @@ kvm-book3s_64-builtin-xics-objs-$(CONFIG_KVM_XICS) := \
 
 ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
 kvm-book3s_64-builtin-objs-$(CONFIG_KVM_BOOK3S_64_HANDLER) += \
+	book3s_hv_hmi.o \
 	book3s_hv_rmhandlers.o \
 	book3s_hv_rm_mmu.o \
 	book3s_hv_ras.o \

arch/powerpc/mm/fault.c

@@ -26,7 +26,7 @@
 #include <linux/mm.h>
 #include <linux/interrupt.h>
 #include <linux/highmem.h>
-#include <linux/module.h>
+#include <linux/extable.h>
 #include <linux/kprobes.h>
 #include <linux/kdebug.h>
 #include <linux/perf_event.h>

arch/powerpc/platforms/512x/mpc512x_lpbfifo.c

@@ -528,7 +528,6 @@ static struct platform_driver mpc512x_lpbfifo_driver = {
 	.remove = mpc512x_lpbfifo_remove,
 	.driver = {
 		.name = DRV_NAME,
-		.owner = THIS_MODULE,
 		.of_match_table = mpc512x_lpbfifo_match,
 	},
 };

arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c

@@ -222,7 +222,6 @@ static const struct of_device_id mcu_of_match_table[] = {
 static struct i2c_driver mcu_driver = {
 	.driver = {
 		.name = "mcu-mpc8349emitx",
-		.owner = THIS_MODULE,
 		.of_match_table = mcu_of_match_table,
 	},
 	.probe = mcu_probe,

arch/powerpc/platforms/embedded6xx/holly.c

@@ -26,7 +26,7 @@
 #include <linux/tty.h>
 #include <linux/serial_core.h>
 #include <linux/of_platform.h>
-#include <linux/module.h>
+#include <linux/extable.h>
 
 #include <asm/time.h>
 #include <asm/machdep.h>

arch/powerpc/platforms/embedded6xx/mpc7448_hpc2.c

@@ -23,7 +23,7 @@
 #include <linux/pci.h>
 #include <linux/kdev_t.h>
 #include <linux/console.h>
-#include <linux/module.h>
+#include <linux/extable.h>
 #include <linux/delay.h>
 #include <linux/irq.h>
 #include <linux/seq_file.h>

arch/powerpc/platforms/powernv/opal-dump.c

@@ -370,6 +370,7 @@ static irqreturn_t process_dump(int irq, void *data)
 	uint32_t dump_id, dump_size, dump_type;
 	struct dump_obj *dump;
 	char name[22];
+	struct kobject *kobj;
 
 	rc = dump_read_info(&dump_id, &dump_size, &dump_type);
 	if (rc != OPAL_SUCCESS)
@@ -381,8 +382,12 @@ static irqreturn_t process_dump(int irq, void *data)
 	 * that gracefully and not create two conflicting
 	 * entries.
 	 */
-	if (kset_find_obj(dump_kset, name))
+	kobj = kset_find_obj(dump_kset, name);
+	if (kobj) {
+		/* Drop reference added by kset_find_obj() */
+		kobject_put(kobj);
 		return 0;
+	}
 
 	dump = create_dump_obj(dump_id, dump_size, dump_type);
 	if (!dump)

arch/powerpc/platforms/powernv/opal-elog.c

@@ -247,6 +247,7 @@ static irqreturn_t elog_event(int irq, void *data)
 	uint64_t elog_type;
 	int rc;
 	char name[2+16+1];
+	struct kobject *kobj;
 
 	rc = opal_get_elog_size(&id, &size, &type);
 	if (rc != OPAL_SUCCESS) {
@@ -269,8 +270,12 @@ static irqreturn_t elog_event(int irq, void *data)
 	 * that gracefully and not create two conflicting
 	 * entries.
 	 */
-	if (kset_find_obj(elog_kset, name))
+	kobj = kset_find_obj(elog_kset, name);
+	if (kobj) {
+		/* Drop reference added by kset_find_obj() */
+		kobject_put(kobj);
 		return IRQ_HANDLED;
+	}
 
 	create_elog_obj(log_id, elog_size, elog_type);
 

arch/powerpc/platforms/powernv/pci-ioda.c

@@ -149,7 +149,7 @@ static void pnv_ioda_reserve_pe(struct pnv_phb *phb, int pe_no)
 
 static struct pnv_ioda_pe *pnv_ioda_alloc_pe(struct pnv_phb *phb)
 {
-	unsigned long pe = phb->ioda.total_pe_num - 1;
+	long pe;
 
 	for (pe = phb->ioda.total_pe_num - 1; pe >= 0; pe--) {
 		if (!test_and_set_bit(pe, phb->ioda.pe_alloc))

arch/powerpc/platforms/pseries/pci.c

@@ -119,6 +119,10 @@ int pseries_root_bridge_prepare(struct pci_host_bridge *bridge)
 
 	bus = bridge->bus;
 
+	/* Rely on the pcibios_free_controller_deferred() callback. */
+	pci_set_host_bridge_release(bridge, pcibios_free_controller_deferred,
+					(void *) pci_bus_to_host(bus));
+
 	dn = pcibios_get_phb_of_node(bus);
 	if (!dn)
 		return 0;

arch/powerpc/platforms/pseries/pci_dlpar.c

@@ -106,8 +106,11 @@ int remove_phb_dynamic(struct pci_controller *phb)
 		release_resource(res);
 	}
 
-	/* Free pci_controller data structure */
-	pcibios_free_controller(phb);
+	/*
+	 * The pci_controller data structure is freed by
+	 * the pcibios_free_controller_deferred() callback;
+	 * see pseries_root_bridge_prepare().
+	 */
 
 	return 0;
 }

arch/powerpc/sysdev/cpm1.c

@@ -534,7 +534,8 @@ struct cpm1_gpio16_chip {
 
 static void cpm1_gpio16_save_regs(struct of_mm_gpio_chip *mm_gc)
 {
-	struct cpm1_gpio16_chip *cpm1_gc = gpiochip_get_data(&mm_gc->gc);
+	struct cpm1_gpio16_chip *cpm1_gc =
+		container_of(mm_gc, struct cpm1_gpio16_chip, mm_gc);
 	struct cpm_ioport16 __iomem *iop = mm_gc->regs;
 
 	cpm1_gc->cpdata = in_be16(&iop->dat);
@@ -649,7 +650,8 @@ struct cpm1_gpio32_chip {
 
 static void cpm1_gpio32_save_regs(struct of_mm_gpio_chip *mm_gc)
 {
-	struct cpm1_gpio32_chip *cpm1_gc = gpiochip_get_data(&mm_gc->gc);
+	struct cpm1_gpio32_chip *cpm1_gc =
+		container_of(mm_gc, struct cpm1_gpio32_chip, mm_gc);
 	struct cpm_ioport32b __iomem *iop = mm_gc->regs;
 
 	cpm1_gc->cpdata = in_be32(&iop->dat);

arch/powerpc/sysdev/cpm_common.c

@@ -94,7 +94,8 @@ struct cpm2_gpio32_chip {
 
 static void cpm2_gpio32_save_regs(struct of_mm_gpio_chip *mm_gc)
 {
-	struct cpm2_gpio32_chip *cpm2_gc = gpiochip_get_data(&mm_gc->gc);
+	struct cpm2_gpio32_chip *cpm2_gc =
+		container_of(mm_gc, struct cpm2_gpio32_chip, mm_gc);
 	struct cpm2_ioports __iomem *iop = mm_gc->regs;
 
 	cpm2_gc->cpdata = in_be32(&iop->dat);

arch/powerpc/sysdev/fsl_rio.c

@@ -23,7 +23,7 @@
  */
 
 #include <linux/init.h>
-#include <linux/module.h>
+#include <linux/extable.h>
 #include <linux/types.h>
 #include <linux/dma-mapping.h>
 #include <linux/interrupt.h>

arch/s390/kernel/setup.c

@@ -204,11 +204,9 @@ static void __init conmode_default(void)
 #endif
 		}
 	} else if (MACHINE_IS_KVM) {
-		if (sclp.has_vt220 &&
-		    config_enabled(CONFIG_SCLP_VT220_CONSOLE))
+		if (sclp.has_vt220 && IS_ENABLED(CONFIG_SCLP_VT220_CONSOLE))
 			SET_CONSOLE_VT220;
-		else if (sclp.has_linemode &&
-			 config_enabled(CONFIG_SCLP_CONSOLE))
+		else if (sclp.has_linemode && IS_ENABLED(CONFIG_SCLP_CONSOLE))
 			SET_CONSOLE_SCLP;
 		else
 			SET_CONSOLE_HVC;

arch/um/include/asm/common.lds.S

@@ -81,7 +81,7 @@
   .altinstr_replacement : { *(.altinstr_replacement) }
   /* .exit.text is discard at runtime, not link time, to deal with references
      from .altinstructions and .eh_frame */
-  .exit.text : { *(.exit.text) }
+  .exit.text : { EXIT_TEXT }
   .exit.data : { *(.exit.data) }
 
   .preinit_array : {

arch/x86/crypto/sha256-mb/sha256_mb.c

@@ -485,10 +485,10 @@ static int sha_complete_job(struct mcryptd_hash_request_ctx *rctx,
 
 			req = cast_mcryptd_ctx_to_req(req_ctx);
 			if (irqs_disabled())
-				rctx->complete(&req->base, ret);
+				req_ctx->complete(&req->base, ret);
 			else {
 				local_bh_disable();
-				rctx->complete(&req->base, ret);
+				req_ctx->complete(&req->base, ret);
 				local_bh_enable();
 			}
 		}

arch/x86/crypto/sha256-mb/sha256_mb_mgr_flush_avx2.S

@@ -265,13 +265,14 @@ ENTRY(sha256_mb_mgr_get_comp_job_avx2)
 	vpinsrd	$1, _args_digest+1*32(state, idx, 4), %xmm0, %xmm0
 	vpinsrd	$2, _args_digest+2*32(state, idx, 4), %xmm0, %xmm0
 	vpinsrd	$3, _args_digest+3*32(state, idx, 4), %xmm0, %xmm0
-	movl	_args_digest+4*32(state, idx, 4), tmp2_w
+	vmovd   _args_digest(state , idx, 4) , %xmm0
 	vpinsrd	$1, _args_digest+5*32(state, idx, 4), %xmm1, %xmm1
 	vpinsrd	$2, _args_digest+6*32(state, idx, 4), %xmm1, %xmm1
 	vpinsrd	$3, _args_digest+7*32(state, idx, 4), %xmm1, %xmm1
 
-	vmovdqu	%xmm0, _result_digest(job_rax)
-	movl	tmp2_w, _result_digest+1*16(job_rax)
+        vmovdqu %xmm0, _result_digest(job_rax)
+        offset =  (_result_digest + 1*16)
+        vmovdqu %xmm1, offset(job_rax)
 
 	pop	%rbx
 

arch/x86/crypto/sha512-mb/sha512_mb.c

@@ -497,10 +497,10 @@ static int sha_complete_job(struct mcryptd_hash_request_ctx *rctx,
 
 			req = cast_mcryptd_ctx_to_req(req_ctx);
 			if (irqs_disabled())
-				rctx->complete(&req->base, ret);
+				req_ctx->complete(&req->base, ret);
 			else {
 				local_bh_disable();
-				rctx->complete(&req->base, ret);
+				req_ctx->complete(&req->base, ret);
 				local_bh_enable();
 			}
 		}

arch/x86/kernel/apic/apic.c

@@ -1623,6 +1623,9 @@ void __init enable_IR_x2apic(void)
 	unsigned long flags;
 	int ret, ir_stat;
 
+	if (skip_ioapic_setup)
+		return;
+
 	ir_stat = irq_remapping_prepare();
 	if (ir_stat < 0 && !x2apic_supported())
 		return;

arch/x86/kernel/cpu/microcode/amd.c

@@ -355,6 +355,7 @@ void load_ucode_amd_ap(void)
 	unsigned int cpu = smp_processor_id();
 	struct equiv_cpu_entry *eq;
 	struct microcode_amd *mc;
+	u8 *cont = container;
 	u32 rev, eax;
 	u16 eq_id;
 
@@ -371,8 +372,11 @@ void load_ucode_amd_ap(void)
 	if (check_current_patch_level(&rev, false))
 		return;
 
+	/* Add CONFIG_RANDOMIZE_MEMORY offset. */
+	cont += PAGE_OFFSET - __PAGE_OFFSET_BASE;
+
 	eax = cpuid_eax(0x00000001);
-	eq  = (struct equiv_cpu_entry *)(container + CONTAINER_HDR_SZ);
+	eq  = (struct equiv_cpu_entry *)(cont + CONTAINER_HDR_SZ);
 
 	eq_id = find_equiv_id(eq, eax);
 	if (!eq_id)
@@ -434,6 +438,9 @@ int __init save_microcode_in_initrd_amd(void)
 	else
 		container = cont_va;
 
+	/* Add CONFIG_RANDOMIZE_MEMORY offset. */
+	container += PAGE_OFFSET - __PAGE_OFFSET_BASE;
+
 	eax   = cpuid_eax(0x00000001);
 	eax   = ((eax >> 8) & 0xf) + ((eax >> 20) & 0xff);
 

arch/x86/kernel/smpboot.c

@@ -100,10 +100,11 @@ EXPORT_PER_CPU_SYMBOL(cpu_info);
 /* Logical package management. We might want to allocate that dynamically */
 static int *physical_to_logical_pkg __read_mostly;
 static unsigned long *physical_package_map __read_mostly;;
-static unsigned long *logical_package_map  __read_mostly;
 static unsigned int max_physical_pkg_id __read_mostly;
 unsigned int __max_logical_packages __read_mostly;
 EXPORT_SYMBOL(__max_logical_packages);
+static unsigned int logical_packages __read_mostly;
+static bool logical_packages_frozen __read_mostly;
 
 /* Maximum number of SMT threads on any online core */
 int __max_smt_threads __read_mostly;
@@ -277,14 +278,14 @@ int topology_update_package_map(unsigned int apicid, unsigned int cpu)
 	if (test_and_set_bit(pkg, physical_package_map))
 		goto found;
 
-	new = find_first_zero_bit(logical_package_map, __max_logical_packages);
-	if (new >= __max_logical_packages) {
+	if (logical_packages_frozen) {
 		physical_to_logical_pkg[pkg] = -1;
-		pr_warn("APIC(%x) Package %u exceeds logical package map\n",
+		pr_warn("APIC(%x) Package %u exceeds logical package max\n",
 			apicid, pkg);
 		return -ENOSPC;
 	}
-	set_bit(new, logical_package_map);
+
+	new = logical_packages++;
 	pr_info("APIC(%x) Converting physical %u to logical package %u\n",
 		apicid, pkg, new);
 	physical_to_logical_pkg[pkg] = new;
@@ -341,6 +342,7 @@ static void __init smp_init_package_map(void)
 	}
 
 	__max_logical_packages = DIV_ROUND_UP(total_cpus, ncpus);
+	logical_packages = 0;
 
 	/*
 	 * Possibly larger than what we need as the number of apic ids per
@@ -352,10 +354,6 @@ static void __init smp_init_package_map(void)
 	memset(physical_to_logical_pkg, 0xff, size);
 	size = BITS_TO_LONGS(max_physical_pkg_id) * sizeof(unsigned long);
 	physical_package_map = kzalloc(size, GFP_KERNEL);
-	size = BITS_TO_LONGS(__max_logical_packages) * sizeof(unsigned long);
-	logical_package_map = kzalloc(size, GFP_KERNEL);
-
-	pr_info("Max logical packages: %u\n", __max_logical_packages);
 
 	for_each_present_cpu(cpu) {
 		unsigned int apicid = apic->cpu_present_to_apicid(cpu);
@@ -369,6 +367,15 @@ static void __init smp_init_package_map(void)
 		set_cpu_possible(cpu, false);
 		set_cpu_present(cpu, false);
 	}
+
+	if (logical_packages > __max_logical_packages) {
+		pr_warn("Detected more packages (%u), then computed by BIOS data (%u).\n",
+			logical_packages, __max_logical_packages);
+		logical_packages_frozen = true;
+		__max_logical_packages  = logical_packages;
+	}
+
+	pr_info("Max logical packages: %u\n", __max_logical_packages);
 }
 
 void __init smp_store_boot_cpu_info(void)

arch/x86/kvm/vmx.c

@@ -422,6 +422,7 @@ struct nested_vmx {
 	struct list_head vmcs02_pool;
 	int vmcs02_num;
 	u64 vmcs01_tsc_offset;
+	bool change_vmcs01_virtual_x2apic_mode;
 	/* L2 must run next, and mustn't decide to exit to L1. */
 	bool nested_run_pending;
 	/*
@@ -435,6 +436,8 @@ struct nested_vmx {
 	bool pi_pending;
 	u16 posted_intr_nv;
 
+	unsigned long *msr_bitmap;
+
 	struct hrtimer preemption_timer;
 	bool preemption_timer_expired;
 
@@ -924,7 +927,6 @@ static unsigned long *vmx_msr_bitmap_legacy;
 static unsigned long *vmx_msr_bitmap_longmode;
 static unsigned long *vmx_msr_bitmap_legacy_x2apic;
 static unsigned long *vmx_msr_bitmap_longmode_x2apic;
-static unsigned long *vmx_msr_bitmap_nested;
 static unsigned long *vmx_vmread_bitmap;
 static unsigned long *vmx_vmwrite_bitmap;
 
@@ -2198,6 +2200,12 @@ static void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu)
 			new.control) != old.control);
 }
 
+static void decache_tsc_multiplier(struct vcpu_vmx *vmx)
+{
+	vmx->current_tsc_ratio = vmx->vcpu.arch.tsc_scaling_ratio;
+	vmcs_write64(TSC_MULTIPLIER, vmx->current_tsc_ratio);
+}
+
 /*
  * Switches to specified vcpu, until a matching vcpu_put(), but assumes
  * vcpu mutex is already taken.
@@ -2256,10 +2264,8 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 
 	/* Setup TSC multiplier */
 	if (kvm_has_tsc_control &&
-	    vmx->current_tsc_ratio != vcpu->arch.tsc_scaling_ratio) {
-		vmx->current_tsc_ratio = vcpu->arch.tsc_scaling_ratio;
-		vmcs_write64(TSC_MULTIPLIER, vmx->current_tsc_ratio);
-	}
+	    vmx->current_tsc_ratio != vcpu->arch.tsc_scaling_ratio)
+		decache_tsc_multiplier(vmx);
 
 	vmx_vcpu_pi_load(vcpu, cpu);
 	vmx->host_pkru = read_pkru();
@@ -2508,7 +2514,7 @@ static void vmx_set_msr_bitmap(struct kvm_vcpu *vcpu)
 	unsigned long *msr_bitmap;
 
 	if (is_guest_mode(vcpu))
-		msr_bitmap = vmx_msr_bitmap_nested;
+		msr_bitmap = to_vmx(vcpu)->nested.msr_bitmap;
 	else if (cpu_has_secondary_exec_ctrls() &&
 		 (vmcs_read32(SECONDARY_VM_EXEC_CONTROL) &
 		  SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE)) {
@@ -6363,13 +6369,6 @@ static __init int hardware_setup(void)
 	if (!vmx_msr_bitmap_longmode_x2apic)
 		goto out4;
 
-	if (nested) {
-		vmx_msr_bitmap_nested =
-			(unsigned long *)__get_free_page(GFP_KERNEL);
-		if (!vmx_msr_bitmap_nested)
-			goto out5;
-	}
-
 	vmx_vmread_bitmap = (unsigned long *)__get_free_page(GFP_KERNEL);
 	if (!vmx_vmread_bitmap)
 		goto out6;
@@ -6392,8 +6391,6 @@ static __init int hardware_setup(void)
 
 	memset(vmx_msr_bitmap_legacy, 0xff, PAGE_SIZE);
 	memset(vmx_msr_bitmap_longmode, 0xff, PAGE_SIZE);
-	if (nested)
-		memset(vmx_msr_bitmap_nested, 0xff, PAGE_SIZE);
 
 	if (setup_vmcs_config(&vmcs_config) < 0) {
 		r = -EIO;
@@ -6529,9 +6526,6 @@ out8:
 out7:
 	free_page((unsigned long)vmx_vmread_bitmap);
 out6:
-	if (nested)
-		free_page((unsigned long)vmx_msr_bitmap_nested);
-out5:
 	free_page((unsigned long)vmx_msr_bitmap_longmode_x2apic);
 out4:
 	free_page((unsigned long)vmx_msr_bitmap_longmode);
@@ -6557,8 +6551,6 @@ static __exit void hardware_unsetup(void)
 	free_page((unsigned long)vmx_io_bitmap_a);
 	free_page((unsigned long)vmx_vmwrite_bitmap);
 	free_page((unsigned long)vmx_vmread_bitmap);
-	if (nested)
-		free_page((unsigned long)vmx_msr_bitmap_nested);
 
 	free_kvm_area();
 }
@@ -6995,16 +6987,21 @@ static int handle_vmon(struct kvm_vcpu *vcpu)
 		return 1;
 	}
 
+	if (cpu_has_vmx_msr_bitmap()) {
+		vmx->nested.msr_bitmap =
+				(unsigned long *)__get_free_page(GFP_KERNEL);
+		if (!vmx->nested.msr_bitmap)
+			goto out_msr_bitmap;
+	}
+
 	vmx->nested.cached_vmcs12 = kmalloc(VMCS12_SIZE, GFP_KERNEL);
 	if (!vmx->nested.cached_vmcs12)
-		return -ENOMEM;
+		goto out_cached_vmcs12;
 
 	if (enable_shadow_vmcs) {
 		shadow_vmcs = alloc_vmcs();
-		if (!shadow_vmcs) {
-			kfree(vmx->nested.cached_vmcs12);
-			return -ENOMEM;
-		}
+		if (!shadow_vmcs)
+			goto out_shadow_vmcs;
 		/* mark vmcs as shadow */
 		shadow_vmcs->revision_id |= (1u << 31);
 		/* init shadow vmcs */
@@ -7024,6 +7021,15 @@ static int handle_vmon(struct kvm_vcpu *vcpu)
 	skip_emulated_instruction(vcpu);
 	nested_vmx_succeed(vcpu);
 	return 1;
+
+out_shadow_vmcs:
+	kfree(vmx->nested.cached_vmcs12);
+
+out_cached_vmcs12:
+	free_page((unsigned long)vmx->nested.msr_bitmap);
+
+out_msr_bitmap:
+	return -ENOMEM;
 }
 
 /*
@@ -7098,6 +7104,10 @@ static void free_nested(struct vcpu_vmx *vmx)
 	vmx->nested.vmxon = false;
 	free_vpid(vmx->nested.vpid02);
 	nested_release_vmcs12(vmx);
+	if (vmx->nested.msr_bitmap) {
+		free_page((unsigned long)vmx->nested.msr_bitmap);
+		vmx->nested.msr_bitmap = NULL;
+	}
 	if (enable_shadow_vmcs)
 		free_vmcs(vmx->nested.current_shadow_vmcs);
 	kfree(vmx->nested.cached_vmcs12);
@@ -8419,6 +8429,12 @@ static void vmx_set_virtual_x2apic_mode(struct kvm_vcpu *vcpu, bool set)
 {
 	u32 sec_exec_control;
 
+	/* Postpone execution until vmcs01 is the current VMCS. */
+	if (is_guest_mode(vcpu)) {
+		to_vmx(vcpu)->nested.change_vmcs01_virtual_x2apic_mode = true;
+		return;
+	}
+
 	/*
 	 * There is not point to enable virtualize x2apic without enable
 	 * apicv
@@ -9472,8 +9488,10 @@ static inline bool nested_vmx_merge_msr_bitmap(struct kvm_vcpu *vcpu,
 {
 	int msr;
 	struct page *page;
-	unsigned long *msr_bitmap;
+	unsigned long *msr_bitmap_l1;
+	unsigned long *msr_bitmap_l0 = to_vmx(vcpu)->nested.msr_bitmap;
 
+	/* This shortcut is ok because we support only x2APIC MSRs so far. */
 	if (!nested_cpu_has_virt_x2apic_mode(vmcs12))
 		return false;
 
@@ -9482,63 +9500,37 @@ static inline bool nested_vmx_merge_msr_bitmap(struct kvm_vcpu *vcpu,
 		WARN_ON(1);
 		return false;
 	}
-	msr_bitmap = (unsigned long *)kmap(page);
-	if (!msr_bitmap) {
+	msr_bitmap_l1 = (unsigned long *)kmap(page);
+	if (!msr_bitmap_l1) {
 		nested_release_page_clean(page);
 		WARN_ON(1);
 		return false;
 	}
 
+	memset(msr_bitmap_l0, 0xff, PAGE_SIZE);
+
 	if (nested_cpu_has_virt_x2apic_mode(vmcs12)) {
 		if (nested_cpu_has_apic_reg_virt(vmcs12))
 			for (msr = 0x800; msr <= 0x8ff; msr++)
 				nested_vmx_disable_intercept_for_msr(
-					msr_bitmap,
-					vmx_msr_bitmap_nested,
+					msr_bitmap_l1, msr_bitmap_l0,
 					msr, MSR_TYPE_R);
-		/* TPR is allowed */
-		nested_vmx_disable_intercept_for_msr(msr_bitmap,
-				vmx_msr_bitmap_nested,
+
+		nested_vmx_disable_intercept_for_msr(
+				msr_bitmap_l1, msr_bitmap_l0,
 				APIC_BASE_MSR + (APIC_TASKPRI >> 4),
 				MSR_TYPE_R | MSR_TYPE_W);
+
 		if (nested_cpu_has_vid(vmcs12)) {
-			/* EOI and self-IPI are allowed */
 			nested_vmx_disable_intercept_for_msr(
-				msr_bitmap,
-				vmx_msr_bitmap_nested,
+				msr_bitmap_l1, msr_bitmap_l0,
 				APIC_BASE_MSR + (APIC_EOI >> 4),
 				MSR_TYPE_W);
 			nested_vmx_disable_intercept_for_msr(
-				msr_bitmap,
-				vmx_msr_bitmap_nested,
+				msr_bitmap_l1, msr_bitmap_l0,
 				APIC_BASE_MSR + (APIC_SELF_IPI >> 4),
 				MSR_TYPE_W);
 		}
-	} else {
-		/*
-		 * Enable reading intercept of all the x2apic
-		 * MSRs. We should not rely on vmcs12 to do any
-		 * optimizations here, it may have been modified
-		 * by L1.
-		 */
-		for (msr = 0x800; msr <= 0x8ff; msr++)
-			__vmx_enable_intercept_for_msr(
-				vmx_msr_bitmap_nested,
-				msr,
-				MSR_TYPE_R);
-
-		__vmx_enable_intercept_for_msr(
-				vmx_msr_bitmap_nested,
-				APIC_BASE_MSR + (APIC_TASKPRI >> 4),
-				MSR_TYPE_W);
-		__vmx_enable_intercept_for_msr(
-				vmx_msr_bitmap_nested,
-				APIC_BASE_MSR + (APIC_EOI >> 4),
-				MSR_TYPE_W);
-		__vmx_enable_intercept_for_msr(
-				vmx_msr_bitmap_nested,
-				APIC_BASE_MSR + (APIC_SELF_IPI >> 4),
-				MSR_TYPE_W);
 	}
 	kunmap(page);
 	nested_release_page_clean(page);
@@ -9957,10 +9949,10 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
 	}
 
 	if (cpu_has_vmx_msr_bitmap() &&
-	    exec_control & CPU_BASED_USE_MSR_BITMAPS) {
-		nested_vmx_merge_msr_bitmap(vcpu, vmcs12);
-		/* MSR_BITMAP will be set by following vmx_set_efer. */
-	} else
+	    exec_control & CPU_BASED_USE_MSR_BITMAPS &&
+	    nested_vmx_merge_msr_bitmap(vcpu, vmcs12))
+		; /* MSR_BITMAP will be set by following vmx_set_efer. */
+	else
 		exec_control &= ~CPU_BASED_USE_MSR_BITMAPS;
 
 	/*
@@ -10011,6 +10003,8 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
 			vmx->nested.vmcs01_tsc_offset + vmcs12->tsc_offset);
 	else
 		vmcs_write64(TSC_OFFSET, vmx->nested.vmcs01_tsc_offset);
+	if (kvm_has_tsc_control)
+		decache_tsc_multiplier(vmx);
 
 	if (enable_vpid) {
 		/*
@@ -10767,6 +10761,14 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
 	else
 		vmcs_set_bits(PIN_BASED_VM_EXEC_CONTROL,
 			      PIN_BASED_VMX_PREEMPTION_TIMER);
+	if (kvm_has_tsc_control)
+		decache_tsc_multiplier(vmx);
+
+	if (vmx->nested.change_vmcs01_virtual_x2apic_mode) {
+		vmx->nested.change_vmcs01_virtual_x2apic_mode = false;
+		vmx_set_virtual_x2apic_mode(vcpu,
+				vcpu->arch.apic_base & X2APIC_ENABLE);
+	}
 
 	/* This is needed for same reason as it was needed in prepare_vmcs02 */
 	vmx->host_rsp = 0;

arch/x86/mm/kaslr.c

@@ -77,7 +77,7 @@ static inline unsigned long get_padding(struct kaslr_memory_region *region)
  */
 static inline bool kaslr_memory_enabled(void)
 {
-	return kaslr_enabled() && !config_enabled(CONFIG_KASAN);
+	return kaslr_enabled() && !IS_ENABLED(CONFIG_KASAN);
 }
 
 /* Initialize base and padding for each memory region randomized with KASLR */

arch/x86/pci/vmd.c

@@ -41,6 +41,7 @@ static DEFINE_RAW_SPINLOCK(list_lock);
  * @node:	list item for parent traversal.
  * @rcu:	RCU callback item for freeing.
  * @irq:	back pointer to parent.
+ * @enabled:	true if driver enabled IRQ
  * @virq:	the virtual IRQ value provided to the requesting driver.
  *
  * Every MSI/MSI-X IRQ requested for a device in a VMD domain will be mapped to
@@ -50,6 +51,7 @@ struct vmd_irq {
 	struct list_head	node;
 	struct rcu_head		rcu;
 	struct vmd_irq_list	*irq;
+	bool			enabled;
 	unsigned int		virq;
 };
 
@@ -122,7 +124,9 @@ static void vmd_irq_enable(struct irq_data *data)
 	unsigned long flags;
 
 	raw_spin_lock_irqsave(&list_lock, flags);
+	WARN_ON(vmdirq->enabled);
 	list_add_tail_rcu(&vmdirq->node, &vmdirq->irq->irq_list);
+	vmdirq->enabled = true;
 	raw_spin_unlock_irqrestore(&list_lock, flags);
 
 	data->chip->irq_unmask(data);
@@ -136,8 +140,10 @@ static void vmd_irq_disable(struct irq_data *data)
 	data->chip->irq_mask(data);
 
 	raw_spin_lock_irqsave(&list_lock, flags);
-	list_del_rcu(&vmdirq->node);
-	INIT_LIST_HEAD_RCU(&vmdirq->node);
+	if (vmdirq->enabled) {
+		list_del_rcu(&vmdirq->node);
+		vmdirq->enabled = false;
+	}
 	raw_spin_unlock_irqrestore(&list_lock, flags);
 }
 

arch/x86/power/hibernate_64.c

@@ -113,7 +113,7 @@ static int set_up_temporary_mappings(void)
 			return result;
 	}
 
-	temp_level4_pgt = (unsigned long)pgd - __PAGE_OFFSET;
+	temp_level4_pgt = __pa(pgd);
 	return 0;
 }
 

arch/x86/xen/enlighten.c

@@ -118,7 +118,7 @@ DEFINE_PER_CPU(struct vcpu_info *, xen_vcpu);
 DEFINE_PER_CPU(struct vcpu_info, xen_vcpu_info);
 
 /* Linux <-> Xen vCPU id mapping */
-DEFINE_PER_CPU(int, xen_vcpu_id) = -1;
+DEFINE_PER_CPU(uint32_t, xen_vcpu_id);
 EXPORT_PER_CPU_SYMBOL(xen_vcpu_id);
 
 enum xen_domain_type xen_domain_type = XEN_NATIVE;

block/bio.c

@@ -667,18 +667,19 @@ struct bio *bio_clone_bioset(struct bio *bio_src, gfp_t gfp_mask,
 	bio->bi_iter.bi_sector	= bio_src->bi_iter.bi_sector;
 	bio->bi_iter.bi_size	= bio_src->bi_iter.bi_size;
 
-	if (bio_op(bio) == REQ_OP_DISCARD)
-		goto integrity_clone;
-
-	if (bio_op(bio) == REQ_OP_WRITE_SAME) {
+	switch (bio_op(bio)) {
+	case REQ_OP_DISCARD:
+	case REQ_OP_SECURE_ERASE:
+		break;
+	case REQ_OP_WRITE_SAME:
 		bio->bi_io_vec[bio->bi_vcnt++] = bio_src->bi_io_vec[0];
-		goto integrity_clone;
+		break;
+	default:
+		bio_for_each_segment(bv, bio_src, iter)
+			bio->bi_io_vec[bio->bi_vcnt++] = bv;
+		break;
 	}
 
-	bio_for_each_segment(bv, bio_src, iter)
-		bio->bi_io_vec[bio->bi_vcnt++] = bv;
-
-integrity_clone:
 	if (bio_integrity(bio_src)) {
 		int ret;
 
@@ -1788,7 +1789,7 @@ struct bio *bio_split(struct bio *bio, int sectors,
 	 * Discards need a mutable bio_vec to accommodate the payload
 	 * required by the DSM TRIM and UNMAP commands.
 	 */
-	if (bio_op(bio) == REQ_OP_DISCARD)
+	if (bio_op(bio) == REQ_OP_DISCARD || bio_op(bio) == REQ_OP_SECURE_ERASE)
 		split = bio_clone_bioset(bio, gfp, bs);
 	else
 		split = bio_clone_fast(bio, gfp, bs);

block/blk-core.c

@@ -515,7 +515,9 @@ EXPORT_SYMBOL_GPL(blk_queue_bypass_end);
 
 void blk_set_queue_dying(struct request_queue *q)
 {
-	queue_flag_set_unlocked(QUEUE_FLAG_DYING, q);
+	spin_lock_irq(q->queue_lock);
+	queue_flag_set(QUEUE_FLAG_DYING, q);
+	spin_unlock_irq(q->queue_lock);
 
 	if (q->mq_ops)
 		blk_mq_wake_waiters(q);

block/blk-merge.c

@@ -94,8 +94,30 @@ static struct bio *blk_bio_segment_split(struct request_queue *q,
 	bool do_split = true;
 	struct bio *new = NULL;
 	const unsigned max_sectors = get_max_io_size(q, bio);
+	unsigned bvecs = 0;
 
 	bio_for_each_segment(bv, bio, iter) {
+		/*
+		 * With arbitrary bio size, the incoming bio may be very
+		 * big. We have to split the bio into small bios so that
+		 * each holds at most BIO_MAX_PAGES bvecs because
+		 * bio_clone() can fail to allocate big bvecs.
+		 *
+		 * It should have been better to apply the limit per
+		 * request queue in which bio_clone() is involved,
+		 * instead of globally. The biggest blocker is the
+		 * bio_clone() in bio bounce.
+		 *
+		 * If bio is splitted by this reason, we should have
+		 * allowed to continue bios merging, but don't do
+		 * that now for making the change simple.
+		 *
+		 * TODO: deal with bio bounce's bio_clone() gracefully
+		 * and convert the global limit into per-queue limit.
+		 */
+		if (bvecs++ >= BIO_MAX_PAGES)
+			goto split;
+
 		/*
 		 * If the queue doesn't support SG gaps and adding this
 		 * offset would create a gap, disallow it.
@@ -172,12 +194,18 @@ void blk_queue_split(struct request_queue *q, struct bio **bio,
 	struct bio *split, *res;
 	unsigned nsegs;
 
-	if (bio_op(*bio) == REQ_OP_DISCARD)
+	switch (bio_op(*bio)) {
+	case REQ_OP_DISCARD:
+	case REQ_OP_SECURE_ERASE:
 		split = blk_bio_discard_split(q, *bio, bs, &nsegs);
-	else if (bio_op(*bio) == REQ_OP_WRITE_SAME)
+		break;
+	case REQ_OP_WRITE_SAME:
 		split = blk_bio_write_same_split(q, *bio, bs, &nsegs);
-	else
+		break;
+	default:
 		split = blk_bio_segment_split(q, *bio, q->bio_split, &nsegs);
+		break;
+	}
 
 	/* physical segments can be figured out during splitting */
 	res = split ? split : *bio;
@@ -213,7 +241,7 @@ static unsigned int __blk_recalc_rq_segments(struct request_queue *q,
 	 * This should probably be returning 0, but blk_add_request_payload()
 	 * (Christoph!!!!)
 	 */
-	if (bio_op(bio) == REQ_OP_DISCARD)
+	if (bio_op(bio) == REQ_OP_DISCARD || bio_op(bio) == REQ_OP_SECURE_ERASE)
 		return 1;
 
 	if (bio_op(bio) == REQ_OP_WRITE_SAME)
@@ -385,7 +413,9 @@ static int __blk_bios_map_sg(struct request_queue *q, struct bio *bio,
 	nsegs = 0;
 	cluster = blk_queue_cluster(q);
 
-	if (bio_op(bio) == REQ_OP_DISCARD) {
+	switch (bio_op(bio)) {
+	case REQ_OP_DISCARD:
+	case REQ_OP_SECURE_ERASE:
 		/*
 		 * This is a hack - drivers should be neither modifying the
 		 * biovec, nor relying on bi_vcnt - but because of
@@ -393,19 +423,16 @@ static int __blk_bios_map_sg(struct request_queue *q, struct bio *bio,
 		 * a payload we need to set up here (thank you Christoph) and
 		 * bi_vcnt is really the only way of telling if we need to.
 		 */
-
-		if (bio->bi_vcnt)
-			goto single_segment;
-
-		return 0;
-	}
-
-	if (bio_op(bio) == REQ_OP_WRITE_SAME) {
-single_segment:
+		if (!bio->bi_vcnt)
+			return 0;
+		/* Fall through */
+	case REQ_OP_WRITE_SAME:
 		*sg = sglist;
 		bvec = bio_iovec(bio);
 		sg_set_page(*sg, bvec.bv_page, bvec.bv_len, bvec.bv_offset);
 		return 1;
+	default:
+		break;
 	}
 
 	for_each_bio(bio)

block/blk-mq.c

@@ -793,11 +793,12 @@ static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx)
 	struct list_head *dptr;
 	int queued;
 
-	WARN_ON(!cpumask_test_cpu(raw_smp_processor_id(), hctx->cpumask));
-
 	if (unlikely(test_bit(BLK_MQ_S_STOPPED, &hctx->state)))
 		return;
 
+	WARN_ON(!cpumask_test_cpu(raw_smp_processor_id(), hctx->cpumask) &&
+		cpu_online(hctx->next_cpu));
+
 	hctx->run++;
 
 	/*
@@ -1036,10 +1037,11 @@ void blk_mq_delay_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs)
 EXPORT_SYMBOL(blk_mq_delay_queue);
 
 static inline void __blk_mq_insert_req_list(struct blk_mq_hw_ctx *hctx,
-					    struct blk_mq_ctx *ctx,
 					    struct request *rq,
 					    bool at_head)
 {
+	struct blk_mq_ctx *ctx = rq->mq_ctx;
+
 	trace_block_rq_insert(hctx->queue, rq);
 
 	if (at_head)
@@ -1053,20 +1055,16 @@ static void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx,
 {
 	struct blk_mq_ctx *ctx = rq->mq_ctx;
 
-	__blk_mq_insert_req_list(hctx, ctx, rq, at_head);
+	__blk_mq_insert_req_list(hctx, rq, at_head);
 	blk_mq_hctx_mark_pending(hctx, ctx);
 }
 
 void blk_mq_insert_request(struct request *rq, bool at_head, bool run_queue,
-		bool async)
+			   bool async)
 {
+	struct blk_mq_ctx *ctx = rq->mq_ctx;
 	struct request_queue *q = rq->q;
 	struct blk_mq_hw_ctx *hctx;
-	struct blk_mq_ctx *ctx = rq->mq_ctx, *current_ctx;
-
-	current_ctx = blk_mq_get_ctx(q);
-	if (!cpu_online(ctx->cpu))
-		rq->mq_ctx = ctx = current_ctx;
 
 	hctx = q->mq_ops->map_queue(q, ctx->cpu);
 
@@ -1076,8 +1074,6 @@ void blk_mq_insert_request(struct request *rq, bool at_head, bool run_queue,
 
 	if (run_queue)
 		blk_mq_run_hw_queue(hctx, async);
-
-	blk_mq_put_ctx(current_ctx);
 }
 
 static void blk_mq_insert_requests(struct request_queue *q,
@@ -1088,14 +1084,9 @@ static void blk_mq_insert_requests(struct request_queue *q,
 
 {
 	struct blk_mq_hw_ctx *hctx;
-	struct blk_mq_ctx *current_ctx;
 
 	trace_block_unplug(q, depth, !from_schedule);
 
-	current_ctx = blk_mq_get_ctx(q);
-
-	if (!cpu_online(ctx->cpu))
-		ctx = current_ctx;
 	hctx = q->mq_ops->map_queue(q, ctx->cpu);
 
 	/*
@@ -1107,15 +1098,14 @@ static void blk_mq_insert_requests(struct request_queue *q,
 		struct request *rq;
 
 		rq = list_first_entry(list, struct request, queuelist);
+		BUG_ON(rq->mq_ctx != ctx);
 		list_del_init(&rq->queuelist);
-		rq->mq_ctx = ctx;
-		__blk_mq_insert_req_list(hctx, ctx, rq, false);
+		__blk_mq_insert_req_list(hctx, rq, false);
 	}
 	blk_mq_hctx_mark_pending(hctx, ctx);
 	spin_unlock(&ctx->lock);
 
 	blk_mq_run_hw_queue(hctx, from_schedule);
-	blk_mq_put_ctx(current_ctx);
 }
 
 static int plug_ctx_cmp(void *priv, struct list_head *a, struct list_head *b)
@@ -1630,16 +1620,17 @@ static int blk_mq_alloc_bitmap(struct blk_mq_ctxmap *bitmap, int node)
 	return 0;
 }
 
+/*
+ * 'cpu' is going away. splice any existing rq_list entries from this
+ * software queue to the hw queue dispatch list, and ensure that it
+ * gets run.
+ */
 static int blk_mq_hctx_cpu_offline(struct blk_mq_hw_ctx *hctx, int cpu)
 {
-	struct request_queue *q = hctx->queue;
 	struct blk_mq_ctx *ctx;
 	LIST_HEAD(tmp);
 
-	/*
-	 * Move ctx entries to new CPU, if this one is going away.
-	 */
-	ctx = __blk_mq_get_ctx(q, cpu);
+	ctx = __blk_mq_get_ctx(hctx->queue, cpu);
 
 	spin_lock(&ctx->lock);
 	if (!list_empty(&ctx->rq_list)) {
@@ -1651,24 +1642,11 @@ static int blk_mq_hctx_cpu_offline(struct blk_mq_hw_ctx *hctx, int cpu)
 	if (list_empty(&tmp))
 		return NOTIFY_OK;
 
-	ctx = blk_mq_get_ctx(q);
-	spin_lock(&ctx->lock);
-
-	while (!list_empty(&tmp)) {
-		struct request *rq;
-
-		rq = list_first_entry(&tmp, struct request, queuelist);
-		rq->mq_ctx = ctx;
-		list_move_tail(&rq->queuelist, &ctx->rq_list);
-	}
-
-	hctx = q->mq_ops->map_queue(q, ctx->cpu);
-	blk_mq_hctx_mark_pending(hctx, ctx);
-
-	spin_unlock(&ctx->lock);
+	spin_lock(&hctx->lock);
+	list_splice_tail_init(&tmp, &hctx->dispatch);
+	spin_unlock(&hctx->lock);
 
 	blk_mq_run_hw_queue(hctx, true);
-	blk_mq_put_ctx(ctx);
 	return NOTIFY_OK;
 }
 

block/elevator.c

@@ -366,7 +366,7 @@ void elv_dispatch_sort(struct request_queue *q, struct request *rq)
 	list_for_each_prev(entry, &q->queue_head) {
 		struct request *pos = list_entry_rq(entry);
 
-		if ((req_op(rq) == REQ_OP_DISCARD) != (req_op(pos) == REQ_OP_DISCARD))
+		if (req_op(rq) != req_op(pos))
 			break;
 		if (rq_data_dir(rq) != rq_data_dir(pos))
 			break;

drivers/block/floppy.c

@@ -3706,22 +3706,21 @@ static int floppy_open(struct block_device *bdev, fmode_t mode)
 	if (UFDCS->rawcmd == 1)
 		UFDCS->rawcmd = 2;
 
-	if (mode & (FMODE_READ|FMODE_WRITE)) {
-		UDRS->last_checked = 0;
-		clear_bit(FD_OPEN_SHOULD_FAIL_BIT, &UDRS->flags);
-		check_disk_change(bdev);
-		if (test_bit(FD_DISK_CHANGED_BIT, &UDRS->flags))
-			goto out;
-		if (test_bit(FD_OPEN_SHOULD_FAIL_BIT, &UDRS->flags))
+	if (!(mode & FMODE_NDELAY)) {
+		if (mode & (FMODE_READ|FMODE_WRITE)) {
+			UDRS->last_checked = 0;
+			clear_bit(FD_OPEN_SHOULD_FAIL_BIT, &UDRS->flags);
+			check_disk_change(bdev);
+			if (test_bit(FD_DISK_CHANGED_BIT, &UDRS->flags))
+				goto out;
+			if (test_bit(FD_OPEN_SHOULD_FAIL_BIT, &UDRS->flags))
+				goto out;
+		}
+		res = -EROFS;
+		if ((mode & FMODE_WRITE) &&
+		    !test_bit(FD_DISK_WRITABLE_BIT, &UDRS->flags))
 			goto out;
 	}
-
-	res = -EROFS;
-
-	if ((mode & FMODE_WRITE) &&
-			!test_bit(FD_DISK_WRITABLE_BIT, &UDRS->flags))
-		goto out;
-
 	mutex_unlock(&open_lock);
 	mutex_unlock(&floppy_mutex);
 	return 0;

drivers/block/xen-blkfront.c

@@ -189,6 +189,8 @@ struct blkfront_info
 	struct mutex mutex;
 	struct xenbus_device *xbdev;
 	struct gendisk *gd;
+	u16 sector_size;
+	unsigned int physical_sector_size;
 	int vdevice;
 	blkif_vdev_t handle;
 	enum blkif_state connected;
@@ -910,9 +912,45 @@ static struct blk_mq_ops blkfront_mq_ops = {
 	.map_queue = blk_mq_map_queue,
 };
 
+static void blkif_set_queue_limits(struct blkfront_info *info)
+{
+	struct request_queue *rq = info->rq;
+	struct gendisk *gd = info->gd;
+	unsigned int segments = info->max_indirect_segments ? :
+				BLKIF_MAX_SEGMENTS_PER_REQUEST;
+
+	queue_flag_set_unlocked(QUEUE_FLAG_VIRT, rq);
+
+	if (info->feature_discard) {
+		queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, rq);
+		blk_queue_max_discard_sectors(rq, get_capacity(gd));
+		rq->limits.discard_granularity = info->discard_granularity;
+		rq->limits.discard_alignment = info->discard_alignment;
+		if (info->feature_secdiscard)
+			queue_flag_set_unlocked(QUEUE_FLAG_SECERASE, rq);
+	}
+
+	/* Hard sector size and max sectors impersonate the equiv. hardware. */
+	blk_queue_logical_block_size(rq, info->sector_size);
+	blk_queue_physical_block_size(rq, info->physical_sector_size);
+	blk_queue_max_hw_sectors(rq, (segments * XEN_PAGE_SIZE) / 512);
+
+	/* Each segment in a request is up to an aligned page in size. */
+	blk_queue_segment_boundary(rq, PAGE_SIZE - 1);
+	blk_queue_max_segment_size(rq, PAGE_SIZE);
+
+	/* Ensure a merged request will fit in a single I/O ring slot. */
+	blk_queue_max_segments(rq, segments / GRANTS_PER_PSEG);
+
+	/* Make sure buffer addresses are sector-aligned. */
+	blk_queue_dma_alignment(rq, 511);
+
+	/* Make sure we don't use bounce buffers. */
+	blk_queue_bounce_limit(rq, BLK_BOUNCE_ANY);
+}
+
 static int xlvbd_init_blk_queue(struct gendisk *gd, u16 sector_size,
-				unsigned int physical_sector_size,
-				unsigned int segments)
+				unsigned int physical_sector_size)
 {
 	struct request_queue *rq;
 	struct blkfront_info *info = gd->private_data;
@@ -944,36 +982,11 @@ static int xlvbd_init_blk_queue(struct gendisk *gd, u16 sector_size,
 	}
 
 	rq->queuedata = info;
-	queue_flag_set_unlocked(QUEUE_FLAG_VIRT, rq);
-
-	if (info->feature_discard) {
-		queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, rq);
-		blk_queue_max_discard_sectors(rq, get_capacity(gd));
-		rq->limits.discard_granularity = info->discard_granularity;
-		rq->limits.discard_alignment = info->discard_alignment;
-		if (info->feature_secdiscard)
-			queue_flag_set_unlocked(QUEUE_FLAG_SECERASE, rq);
-	}
-
-	/* Hard sector size and max sectors impersonate the equiv. hardware. */
-	blk_queue_logical_block_size(rq, sector_size);
-	blk_queue_physical_block_size(rq, physical_sector_size);
-	blk_queue_max_hw_sectors(rq, (segments * XEN_PAGE_SIZE) / 512);
-
-	/* Each segment in a request is up to an aligned page in size. */
-	blk_queue_segment_boundary(rq, PAGE_SIZE - 1);
-	blk_queue_max_segment_size(rq, PAGE_SIZE);
-
-	/* Ensure a merged request will fit in a single I/O ring slot. */
-	blk_queue_max_segments(rq, segments / GRANTS_PER_PSEG);
-
-	/* Make sure buffer addresses are sector-aligned. */
-	blk_queue_dma_alignment(rq, 511);
-
-	/* Make sure we don't use bounce buffers. */
-	blk_queue_bounce_limit(rq, BLK_BOUNCE_ANY);
-
-	gd->queue = rq;
+	info->rq = gd->queue = rq;
+	info->gd = gd;
+	info->sector_size = sector_size;
+	info->physical_sector_size = physical_sector_size;
+	blkif_set_queue_limits(info);
 
 	return 0;
 }
@@ -1136,16 +1149,11 @@ static int xlvbd_alloc_gendisk(blkif_sector_t capacity,
 	gd->private_data = info;
 	set_capacity(gd, capacity);
 
-	if (xlvbd_init_blk_queue(gd, sector_size, physical_sector_size,
-				 info->max_indirect_segments ? :
-				 BLKIF_MAX_SEGMENTS_PER_REQUEST)) {
+	if (xlvbd_init_blk_queue(gd, sector_size, physical_sector_size)) {
 		del_gendisk(gd);
 		goto release;
 	}
 
-	info->rq = gd->queue;
-	info->gd = gd;
-
 	xlvbd_flush(info);
 
 	if (vdisk_info & VDISK_READONLY)
@@ -1315,7 +1323,7 @@ free_shadow:
 			rinfo->ring_ref[i] = GRANT_INVALID_REF;
 		}
 	}
-	free_pages((unsigned long)rinfo->ring.sring, get_order(info->nr_ring_pages * PAGE_SIZE));
+	free_pages((unsigned long)rinfo->ring.sring, get_order(info->nr_ring_pages * XEN_PAGE_SIZE));
 	rinfo->ring.sring = NULL;
 
 	if (rinfo->irq)
@@ -2007,8 +2015,10 @@ static int blkif_recover(struct blkfront_info *info)
 	struct split_bio *split_bio;
 
 	blkfront_gather_backend_features(info);
+	/* Reset limits changed by blk_mq_update_nr_hw_queues(). */
+	blkif_set_queue_limits(info);
 	segs = info->max_indirect_segments ? : BLKIF_MAX_SEGMENTS_PER_REQUEST;
-	blk_queue_max_segments(info->rq, segs);
+	blk_queue_max_segments(info->rq, segs / GRANTS_PER_PSEG);
 
 	for (r_index = 0; r_index < info->nr_rings; r_index++) {
 		struct blkfront_ring_info *rinfo = &info->rinfo[r_index];
@@ -2432,7 +2442,7 @@ static void blkfront_connect(struct blkfront_info *info)
 	if (err) {
 		xenbus_dev_fatal(info->xbdev, err, "xlvbd_add at %s",
 				 info->xbdev->otherend);
-		return;
+		goto fail;
 	}
 
 	xenbus_switch_state(info->xbdev, XenbusStateConnected);
@@ -2445,6 +2455,11 @@ static void blkfront_connect(struct blkfront_info *info)
 	device_add_disk(&info->xbdev->dev, info->gd);
 
 	info->is_ready = 1;
+	return;
+
+fail:
+	blkif_free(info, 0);
+	return;
 }
 
 /**

drivers/clocksource/bcm_kona_timer.c

@@ -66,10 +66,10 @@ static void kona_timer_disable_and_clear(void __iomem *base)
 
 }
 
-static void
+static int
 kona_timer_get_counter(void __iomem *timer_base, uint32_t *msw, uint32_t *lsw)
 {
-	int loop_limit = 4;
+	int loop_limit = 3;
 
 	/*
 	 * Read 64-bit free running counter
@@ -83,18 +83,19 @@ kona_timer_get_counter(void __iomem *timer_base, uint32_t *msw, uint32_t *lsw)
 	 *      if new hi-word is equal to previously read hi-word then stop.
 	 */
 
-	while (--loop_limit) {
+	do {
 		*msw = readl(timer_base + KONA_GPTIMER_STCHI_OFFSET);
 		*lsw = readl(timer_base + KONA_GPTIMER_STCLO_OFFSET);
 		if (*msw == readl(timer_base + KONA_GPTIMER_STCHI_OFFSET))
 			break;
-	}
+	} while (--loop_limit);
 	if (!loop_limit) {
 		pr_err("bcm_kona_timer: getting counter failed.\n");
 		pr_err(" Timer will be impacted\n");
+		return -ETIMEDOUT;
 	}
 
-	return;
+	return 0;
 }
 
 static int kona_timer_set_next_event(unsigned long clc,
@@ -112,8 +113,11 @@ static int kona_timer_set_next_event(unsigned long clc,
 
 	uint32_t lsw, msw;
 	uint32_t reg;
+	int ret;
 
-	kona_timer_get_counter(timers.tmr_regs, &msw, &lsw);
+	ret = kona_timer_get_counter(timers.tmr_regs, &msw, &lsw);
+	if (ret)
+		return ret;
 
 	/* Load the "next" event tick value */
 	writel(lsw + clc, timers.tmr_regs + KONA_GPTIMER_STCM0_OFFSET);

drivers/clocksource/mips-gic-timer.c

@@ -164,7 +164,7 @@ void __init gic_clocksource_init(unsigned int frequency)
 	gic_start_count();
 }
 
-static void __init gic_clocksource_of_init(struct device_node *node)
+static int __init gic_clocksource_of_init(struct device_node *node)
 {
 	struct clk *clk;
 	int ret;

drivers/clocksource/pxa_timer.c

@@ -21,6 +21,8 @@
 #include <linux/of_irq.h>
 #include <linux/sched_clock.h>
 
+#include <clocksource/pxa.h>
+
 #include <asm/div64.h>
 
 #define OSMR0		0x00	/* OS Timer 0 Match Register */

drivers/clocksource/sun4i_timer.c

@@ -123,12 +123,16 @@ static struct clock_event_device sun4i_clockevent = {
 	.set_next_event = sun4i_clkevt_next_event,
 };
 
+static void sun4i_timer_clear_interrupt(void)
+{
+	writel(TIMER_IRQ_EN(0), timer_base + TIMER_IRQ_ST_REG);
+}
 
 static irqreturn_t sun4i_timer_interrupt(int irq, void *dev_id)
 {
 	struct clock_event_device *evt = (struct clock_event_device *)dev_id;
 
-	writel(0x1, timer_base + TIMER_IRQ_ST_REG);
+	sun4i_timer_clear_interrupt();
 	evt->event_handler(evt);
 
 	return IRQ_HANDLED;
@@ -208,6 +212,9 @@ static int __init sun4i_timer_init(struct device_node *node)
 	/* Make sure timer is stopped before playing with interrupts */
 	sun4i_clkevt_time_stop(0);
 
+	/* clear timer0 interrupt */
+	sun4i_timer_clear_interrupt();
+
 	sun4i_clockevent.cpumask = cpu_possible_mask;
 	sun4i_clockevent.irq = irq;
 

drivers/clocksource/time-armada-370-xp.c

@@ -338,7 +338,6 @@ static int __init armada_xp_timer_init(struct device_node *np)
 	struct clk *clk = of_clk_get_by_name(np, "fixed");
 	int ret;
 
-	clk = of_clk_get(np, 0);
 	if (IS_ERR(clk)) {
 		pr_err("Failed to get clock");
 		return PTR_ERR(clk);