Merge tag 'v4.20-rc3' into for-4.21/block

Merge in -rc3 to resolve a few conflicts, but also to get a few
important fixes that have gone into mainline since the block
4.21 branch was forked off (most notably the SCSI queue issue,
which is both a conflict AND needed fix).
Signed-off-by: NJens Axboe <axboe@kernel.dk>

.mailmap

@@ -159,6 +159,7 @@ Peter Oruba <peter@oruba.de>
 Peter Oruba <peter.oruba@amd.com>
 Pratyush Anand <pratyush.anand@gmail.com> <pratyush.anand@st.com>
 Praveen BP <praveenbp@ti.com>
+Punit Agrawal <punitagrawal@gmail.com> <punit.agrawal@arm.com>
 Qais Yousef <qsyousef@gmail.com> <qais.yousef@imgtec.com>
 Oleksij Rempel <linux@rempel-privat.de> <bug-track@fisher-privat.net>
 Oleksij Rempel <linux@rempel-privat.de> <external.Oleksij.Rempel@de.bosch.com>

CREDITS

@@ -2138,6 +2138,10 @@ E: paul@laufernet.com
 D: Soundblaster driver fixes, ISAPnP quirk
 S: California, USA
 
+N: Jarkko Lavinen
+E: jarkko.lavinen@nokia.com
+D: OMAP MMC support
+
 N: Jonathan Layes
 D: ARPD support
 

Documentation/ABI/testing/sysfs-class-led-trigger-pattern

@@ -37,8 +37,8 @@ Description:
 		  0-|   /             \/             \/
 		    +---0----1----2----3----4----5----6------------> time (s)
 
-		2. To make the LED go instantly from one brigntess value to another,
-		we should use use zero-time lengths (the brightness must be same as
+		2. To make the LED go instantly from one brightness value to another,
+		we should use zero-time lengths (the brightness must be same as
 		the previous tuple's). So the format should be:
 		"brightness_1 duration_1 brightness_1 0 brightness_2 duration_2
 		brightness_2 0 ...". For example:

Documentation/admin-guide/pm/cpufreq.rst

@@ -150,7 +150,7 @@ data structures necessary to handle the given policy and, possibly, to add
 a governor ``sysfs`` interface to it.  Next, the governor is started by
 invoking its ``->start()`` callback.
 
-That callback it expected to register per-CPU utilization update callbacks for
+That callback is expected to register per-CPU utilization update callbacks for
 all of the online CPUs belonging to the given policy with the CPU scheduler.
 The utilization update callbacks will be invoked by the CPU scheduler on
 important events, like task enqueue and dequeue, on every iteration of the

Documentation/cpu-freq/cpufreq-stats.txt

@@ -86,9 +86,11 @@ transitions.
 This will give a fine grained information about all the CPU frequency
 transitions. The cat output here is a two dimensional matrix, where an entry
 <i,j> (row i, column j) represents the count of number of transitions from 
-Freq_i to Freq_j. Freq_i is in descending order with increasing rows and 
-Freq_j is in descending order with increasing columns. The output here also 
-contains the actual freq values for each row and column for better readability.
+Freq_i to Freq_j. Freq_i rows and Freq_j columns follow the sorting order in
+which the driver has provided the frequency table initially to the cpufreq core
+and so can be sorted (ascending or descending) or unsorted.  The output here
+also contains the actual freq values for each row and column for better
+readability.
 
 If the transition table is bigger than PAGE_SIZE, reading this will
 return an -EFBIG error.

Documentation/devicetree/bindings/cpufreq/arm_big_little_dt.txt

-Generic ARM big LITTLE cpufreq driver's DT glue
------------------------------------------------
-
-This is DT specific glue layer for generic cpufreq driver for big LITTLE
-systems.
-
-Both required and optional properties listed below must be defined
-under node /cpus/cpu@x. Where x is the first cpu inside a cluster.
-
-FIXME: Cpus should boot in the order specified in DT and all cpus for a cluster
-must be present contiguously. Generic DT driver will check only node 'x' for
-cpu:x.
-
-Required properties:
-- operating-points: Refer to Documentation/devicetree/bindings/opp/opp.txt
-  for details
-
-Optional properties:
-- clock-latency: Specify the possible maximum transition latency for clock,
-  in unit of nanoseconds.
-
-Examples:
-
-cpus {
-	#address-cells = <1>;
-	#size-cells = <0>;
-
-	cpu@0 {
-		compatible = "arm,cortex-a15";
-		reg = <0>;
-		next-level-cache = <&L2>;
-		operating-points = <
-			/* kHz    uV */
-			792000  1100000
-			396000  950000
-			198000  850000
-		>;
-		clock-latency = <61036>; /* two CLK32 periods */
-	};
-
-	cpu@1 {
-		compatible = "arm,cortex-a15";
-		reg = <1>;
-		next-level-cache = <&L2>;
-	};
-
-	cpu@100 {
-		compatible = "arm,cortex-a7";
-		reg = <100>;
-		next-level-cache = <&L2>;
-		operating-points = <
-			/* kHz    uV */
-			792000  950000
-			396000  750000
-			198000  450000
-		>;
-		clock-latency = <61036>; /* two CLK32 periods */
-	};
-
-	cpu@101 {
-		compatible = "arm,cortex-a7";
-		reg = <101>;
-		next-level-cache = <&L2>;
-	};
-};

Documentation/devicetree/bindings/i2c/i2c-omap.txt

 I2C for OMAP platforms
 
 Required properties :
-- compatible : Must be "ti,omap2420-i2c", "ti,omap2430-i2c", "ti,omap3-i2c"
-  or "ti,omap4-i2c"
+- compatible : Must be
+	"ti,omap2420-i2c" for OMAP2420 SoCs
+	"ti,omap2430-i2c" for OMAP2430 SoCs
+	"ti,omap3-i2c" for OMAP3 SoCs
+	"ti,omap4-i2c" for OMAP4+ SoCs
+	"ti,am654-i2c", "ti,omap4-i2c" for AM654 SoCs
 - ti,hwmods : Must be "i2c<n>", n being the instance number (1-based)
 - #address-cells = <1>;
 - #size-cells = <0>;

Documentation/i2c/busses/i2c-nvidia-gpu

+Kernel driver i2c-nvidia-gpu
+
+Datasheet: not publicly available.
+
+Authors:
+	Ajay Gupta <ajayg@nvidia.com>
+
+Description
+-----------
+
+i2c-nvidia-gpu is a driver for I2C controller included in NVIDIA Turing
+and later GPUs and it is used to communicate with Type-C controller on GPUs.
+
+If your 'lspci -v' listing shows something like the following,
+
+01:00.3 Serial bus controller [0c80]: NVIDIA Corporation Device 1ad9 (rev a1)
+
+then this driver should support the I2C controller of your GPU.

Documentation/x86/x86_64/mm.txt

@@ -34,23 +34,24 @@ __________________|____________|__________________|_________|___________________
 ____________________________________________________________|___________________________________________________________
                   |            |                  |         |
  ffff800000000000 | -128    TB | ffff87ffffffffff |    8 TB | ... guard hole, also reserved for hypervisor
- ffff880000000000 | -120    TB | ffffc7ffffffffff |   64 TB | direct mapping of all physical memory (page_offset_base)
- ffffc80000000000 |  -56    TB | ffffc8ffffffffff |    1 TB | ... unused hole
+ ffff880000000000 | -120    TB | ffff887fffffffff |  0.5 TB | LDT remap for PTI
+ ffff888000000000 | -119.5  TB | ffffc87fffffffff |   64 TB | direct mapping of all physical memory (page_offset_base)
+ ffffc88000000000 |  -55.5  TB | ffffc8ffffffffff |  0.5 TB | ... unused hole
  ffffc90000000000 |  -55    TB | ffffe8ffffffffff |   32 TB | vmalloc/ioremap space (vmalloc_base)
  ffffe90000000000 |  -23    TB | ffffe9ffffffffff |    1 TB | ... unused hole
  ffffea0000000000 |  -22    TB | ffffeaffffffffff |    1 TB | virtual memory map (vmemmap_base)
  ffffeb0000000000 |  -21    TB | ffffebffffffffff |    1 TB | ... unused hole
  ffffec0000000000 |  -20    TB | fffffbffffffffff |   16 TB | KASAN shadow memory
- fffffc0000000000 |   -4    TB | fffffdffffffffff |    2 TB | ... unused hole
-                  |            |                  |         | vaddr_end for KASLR
- fffffe0000000000 |   -2    TB | fffffe7fffffffff |  0.5 TB | cpu_entry_area mapping
- fffffe8000000000 |   -1.5  TB | fffffeffffffffff |  0.5 TB | LDT remap for PTI
- ffffff0000000000 |   -1    TB | ffffff7fffffffff |  0.5 TB | %esp fixup stacks
 __________________|____________|__________________|_________|____________________________________________________________
                                                             |
-                                                            | Identical layout to the 47-bit one from here on:
+                                                            | Identical layout to the 56-bit one from here on:
 ____________________________________________________________|____________________________________________________________
                   |            |                  |         |
+ fffffc0000000000 |   -4    TB | fffffdffffffffff |    2 TB | ... unused hole
+                  |            |                  |         | vaddr_end for KASLR
+ fffffe0000000000 |   -2    TB | fffffe7fffffffff |  0.5 TB | cpu_entry_area mapping
+ fffffe8000000000 |   -1.5  TB | fffffeffffffffff |  0.5 TB | ... unused hole
+ ffffff0000000000 |   -1    TB | ffffff7fffffffff |  0.5 TB | %esp fixup stacks
  ffffff8000000000 | -512    GB | ffffffeeffffffff |  444 GB | ... unused hole
  ffffffef00000000 |  -68    GB | fffffffeffffffff |   64 GB | EFI region mapping space
  ffffffff00000000 |   -4    GB | ffffffff7fffffff |    2 GB | ... unused hole
@@ -83,7 +84,7 @@ Notes:
 __________________|____________|__________________|_________|___________________________________________________________
                   |            |                  |         |
  0000800000000000 |  +64    PB | ffff7fffffffffff | ~16K PB | ... huge, still almost 64 bits wide hole of non-canonical
-                  |            |                  |         |     virtual memory addresses up to the -128 TB
+                  |            |                  |         |     virtual memory addresses up to the -64 PB
                   |            |                  |         |     starting offset of kernel mappings.
 __________________|____________|__________________|_________|___________________________________________________________
                                                             |
@@ -91,23 +92,24 @@ __________________|____________|__________________|_________|___________________
 ____________________________________________________________|___________________________________________________________
                   |            |                  |         |
  ff00000000000000 |  -64    PB | ff0fffffffffffff |    4 PB | ... guard hole, also reserved for hypervisor
- ff10000000000000 |  -60    PB | ff8fffffffffffff |   32 PB | direct mapping of all physical memory (page_offset_base)
- ff90000000000000 |  -28    PB | ff9fffffffffffff |    4 PB | LDT remap for PTI
+ ff10000000000000 |  -60    PB | ff10ffffffffffff | 0.25 PB | LDT remap for PTI
+ ff11000000000000 |  -59.75 PB | ff90ffffffffffff |   32 PB | direct mapping of all physical memory (page_offset_base)
+ ff91000000000000 |  -27.75 PB | ff9fffffffffffff | 3.75 PB | ... unused hole
  ffa0000000000000 |  -24    PB | ffd1ffffffffffff | 12.5 PB | vmalloc/ioremap space (vmalloc_base)
  ffd2000000000000 |  -11.5  PB | ffd3ffffffffffff |  0.5 PB | ... unused hole
  ffd4000000000000 |  -11    PB | ffd5ffffffffffff |  0.5 PB | virtual memory map (vmemmap_base)
  ffd6000000000000 |  -10.5  PB | ffdeffffffffffff | 2.25 PB | ... unused hole
  ffdf000000000000 |   -8.25 PB | fffffdffffffffff |   ~8 PB | KASAN shadow memory
- fffffc0000000000 |   -4    TB | fffffdffffffffff |    2 TB | ... unused hole
-                  |            |                  |         | vaddr_end for KASLR
- fffffe0000000000 |   -2    TB | fffffe7fffffffff |  0.5 TB | cpu_entry_area mapping
- fffffe8000000000 |   -1.5  TB | fffffeffffffffff |  0.5 TB | ... unused hole
- ffffff0000000000 |   -1    TB | ffffff7fffffffff |  0.5 TB | %esp fixup stacks
 __________________|____________|__________________|_________|____________________________________________________________
                                                             |
                                                             | Identical layout to the 47-bit one from here on:
 ____________________________________________________________|____________________________________________________________
                   |            |                  |         |
+ fffffc0000000000 |   -4    TB | fffffdffffffffff |    2 TB | ... unused hole
+                  |            |                  |         | vaddr_end for KASLR
+ fffffe0000000000 |   -2    TB | fffffe7fffffffff |  0.5 TB | cpu_entry_area mapping
+ fffffe8000000000 |   -1.5  TB | fffffeffffffffff |  0.5 TB | ... unused hole
+ ffffff0000000000 |   -1    TB | ffffff7fffffffff |  0.5 TB | %esp fixup stacks
  ffffff8000000000 | -512    GB | ffffffeeffffffff |  444 GB | ... unused hole
  ffffffef00000000 |  -68    GB | fffffffeffffffff |   64 GB | EFI region mapping space
  ffffffff00000000 |   -4    GB | ffffffff7fffffff |    2 GB | ... unused hole

Documentation/x86/zero-page.txt

@@ -25,7 +25,7 @@ Offset	Proto	Name		Meaning
 0C8/004	ALL	ext_cmd_line_ptr  cmd_line_ptr high 32bits
 140/080	ALL	edid_info	Video mode setup (struct edid_info)
 1C0/020	ALL	efi_info	EFI 32 information (struct efi_info)
-1E0/004	ALL	alk_mem_k	Alternative mem check, in KB
+1E0/004	ALL	alt_mem_k	Alternative mem check, in KB
 1E4/004	ALL	scratch		Scratch field for the kernel setup code
 1E8/001	ALL	e820_entries	Number of entries in e820_table (below)
 1E9/001	ALL	eddbuf_entries	Number of entries in eddbuf (below)

MAINTAINERS

@@ -6861,6 +6861,13 @@ L:	linux-acpi@vger.kernel.org
 S:	Maintained
 F:	drivers/i2c/i2c-core-acpi.c
 
+I2C CONTROLLER DRIVER FOR NVIDIA GPU
+M:	Ajay Gupta <ajayg@nvidia.com>
+L:	linux-i2c@vger.kernel.org
+S:	Maintained
+F:	Documentation/i2c/busses/i2c-nvidia-gpu
+F:	drivers/i2c/busses/i2c-nvidia-gpu.c
+
 I2C MUXES
 M:	Peter Rosin <peda@axentia.se>
 L:	linux-i2c@vger.kernel.org
@@ -8367,7 +8374,7 @@ F:	drivers/media/dvb-frontends/lgdt3305.*
 LIBATA PATA ARASAN COMPACT FLASH CONTROLLER
 M:	Viresh Kumar <vireshk@kernel.org>
 L:	linux-ide@vger.kernel.org
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tj/libata.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux-block.git
 S:	Maintained
 F:	include/linux/pata_arasan_cf_data.h
 F:	drivers/ata/pata_arasan_cf.c
@@ -8384,7 +8391,7 @@ F:	drivers/ata/ata_generic.c
 LIBATA PATA FARADAY FTIDE010 AND GEMINI SATA BRIDGE DRIVERS
 M:	Linus Walleij <linus.walleij@linaro.org>
 L:	linux-ide@vger.kernel.org
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tj/libata.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux-block.git
 S:	Maintained
 F:	drivers/ata/pata_ftide010.c
 F:	drivers/ata/sata_gemini.c
@@ -8403,7 +8410,7 @@ F:	include/linux/ahci_platform.h
 LIBATA SATA PROMISE TX2/TX4 CONTROLLER DRIVER
 M:	Mikael Pettersson <mikpelinux@gmail.com>
 L:	linux-ide@vger.kernel.org
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tj/libata.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux-block.git
 S:	Maintained
 F:	drivers/ata/sata_promise.*
 
@@ -10784,6 +10791,14 @@ L:	linux-omap@vger.kernel.org
 S:	Maintained
 F:	arch/arm/mach-omap2/omap_hwmod.*
 
+OMAP I2C DRIVER
+M:	Vignesh R <vigneshr@ti.com>
+L:	linux-omap@vger.kernel.org
+L:	linux-i2c@vger.kernel.org
+S:	Maintained
+F:	Documentation/devicetree/bindings/i2c/i2c-omap.txt
+F:	drivers/i2c/busses/i2c-omap.c
+
 OMAP IMAGING SUBSYSTEM (OMAP3 ISP and OMAP4 ISS)
 M:	Laurent Pinchart <laurent.pinchart@ideasonboard.com>
 L:	linux-media@vger.kernel.org
@@ -10793,9 +10808,9 @@ F:	drivers/media/platform/omap3isp/
 F:	drivers/staging/media/omap4iss/
 
 OMAP MMC SUPPORT
-M:	Jarkko Lavinen <jarkko.lavinen@nokia.com>
+M:	Aaro Koskinen <aaro.koskinen@iki.fi>
 L:	linux-omap@vger.kernel.org
-S:	Maintained
+S:	Odd Fixes
 F:	drivers/mmc/host/omap.c
 
 OMAP POWER MANAGEMENT SUPPORT
@@ -11730,6 +11745,7 @@ F:	Documentation/devicetree/bindings/pinctrl/fsl,*
 PIN CONTROLLER - INTEL
 M:	Mika Westerberg <mika.westerberg@linux.intel.com>
 M:	Andy Shevchenko <andriy.shevchenko@linux.intel.com>
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/pinctrl/intel.git
 S:	Maintained
 F:	drivers/pinctrl/intel/
 

Makefile

@@ -2,7 +2,7 @@
 VERSION = 4
 PATCHLEVEL = 20
 SUBLEVEL = 0
-EXTRAVERSION = -rc1
+EXTRAVERSION = -rc3
 NAME = "People's Front"
 
 # *DOCUMENTATION*

arch/alpha/include/asm/termios.h

@@ -73,9 +73,15 @@
 })
 
 #define user_termios_to_kernel_termios(k, u) \
-	copy_from_user(k, u, sizeof(struct termios))
+	copy_from_user(k, u, sizeof(struct termios2))
 
 #define kernel_termios_to_user_termios(u, k) \
+	copy_to_user(u, k, sizeof(struct termios2))
+
+#define user_termios_to_kernel_termios_1(k, u) \
+	copy_from_user(k, u, sizeof(struct termios))
+
+#define kernel_termios_to_user_termios_1(u, k) \
 	copy_to_user(u, k, sizeof(struct termios))
 
 #endif	/* _ALPHA_TERMIOS_H */

arch/alpha/include/uapi/asm/ioctls.h

@@ -32,6 +32,11 @@
 #define TCXONC		_IO('t', 30)
 #define TCFLSH		_IO('t', 31)
 
+#define TCGETS2		_IOR('T', 42, struct termios2)
+#define TCSETS2		_IOW('T', 43, struct termios2)
+#define TCSETSW2	_IOW('T', 44, struct termios2)
+#define TCSETSF2	_IOW('T', 45, struct termios2)
+
 #define TIOCSWINSZ	_IOW('t', 103, struct winsize)
 #define TIOCGWINSZ	_IOR('t', 104, struct winsize)
 #define	TIOCSTART	_IO('t', 110)		/* start output, like ^Q */

arch/alpha/include/uapi/asm/termbits.h

@@ -26,6 +26,19 @@ struct termios {
 	speed_t c_ospeed;		/* output speed */
 };
 
+/* Alpha has identical termios and termios2 */
+
+struct termios2 {
+	tcflag_t c_iflag;		/* input mode flags */
+	tcflag_t c_oflag;		/* output mode flags */
+	tcflag_t c_cflag;		/* control mode flags */
+	tcflag_t c_lflag;		/* local mode flags */
+	cc_t c_cc[NCCS];		/* control characters */
+	cc_t c_line;			/* line discipline (== c_cc[19]) */
+	speed_t c_ispeed;		/* input speed */
+	speed_t c_ospeed;		/* output speed */
+};
+
 /* Alpha has matching termios and ktermios */
 
 struct ktermios {
@@ -152,6 +165,7 @@ struct ktermios {
 #define B3000000  00034
 #define B3500000  00035
 #define B4000000  00036
+#define BOTHER    00037
 
 #define CSIZE	00001400
 #define   CS5	00000000
@@ -169,6 +183,9 @@ struct ktermios {
 #define CMSPAR	  010000000000		/* mark or space (stick) parity */
 #define CRTSCTS	  020000000000		/* flow control */
 
+#define CIBAUD	07600000
+#define IBSHIFT	16
+
 /* c_lflag bits */
 #define ISIG	0x00000080
 #define ICANON	0x00000100

arch/arm/include/asm/cputype.h

@@ -111,6 +111,7 @@
 #include <linux/kernel.h>
 
 extern unsigned int processor_id;
+struct proc_info_list *lookup_processor(u32 midr);
 
 #ifdef CONFIG_CPU_CP15
 #define read_cpuid(reg)							\

arch/arm/include/asm/pgtable-2level.h

@@ -10,7 +10,7 @@
 #ifndef _ASM_PGTABLE_2LEVEL_H
 #define _ASM_PGTABLE_2LEVEL_H
 
-#define __PAGETABLE_PMD_FOLDED
+#define __PAGETABLE_PMD_FOLDED 1
 
 /*
  * Hardware-wise, we have a two level page table structure, where the first

arch/arm/include/asm/proc-fns.h

@@ -23,7 +23,7 @@ struct mm_struct;
 /*
  * Don't change this structure - ASM code relies on it.
  */
-extern struct processor {
+struct processor {
 	/* MISC
 	 * get data abort address/flags
 	 */
@@ -79,9 +79,13 @@ extern struct processor {
 	unsigned int suspend_size;
 	void (*do_suspend)(void *);
 	void (*do_resume)(void *);
-} processor;
+};
 
 #ifndef MULTI_CPU
+static inline void init_proc_vtable(const struct processor *p)
+{
+}
+
 extern void cpu_proc_init(void);
 extern void cpu_proc_fin(void);
 extern int cpu_do_idle(void);
@@ -98,17 +102,50 @@ extern void cpu_reset(unsigned long addr, bool hvc) __attribute__((noreturn));
 extern void cpu_do_suspend(void *);
 extern void cpu_do_resume(void *);
 #else
-#define cpu_proc_init			processor._proc_init
-#define cpu_proc_fin			processor._proc_fin
-#define cpu_reset			processor.reset
-#define cpu_do_idle			processor._do_idle
-#define cpu_dcache_clean_area		processor.dcache_clean_area
-#define cpu_set_pte_ext			processor.set_pte_ext
-#define cpu_do_switch_mm		processor.switch_mm
 
-/* These three are private to arch/arm/kernel/suspend.c */
-#define cpu_do_suspend			processor.do_suspend
-#define cpu_do_resume			processor.do_resume
+extern struct processor processor;
+#if defined(CONFIG_BIG_LITTLE) && defined(CONFIG_HARDEN_BRANCH_PREDICTOR)
+#include <linux/smp.h>
+/*
+ * This can't be a per-cpu variable because we need to access it before
+ * per-cpu has been initialised.  We have a couple of functions that are
+ * called in a pre-emptible context, and so can't use smp_processor_id()
+ * there, hence PROC_TABLE().  We insist in init_proc_vtable() that the
+ * function pointers for these are identical across all CPUs.
+ */
+extern struct processor *cpu_vtable[];
+#define PROC_VTABLE(f)			cpu_vtable[smp_processor_id()]->f
+#define PROC_TABLE(f)			cpu_vtable[0]->f
+static inline void init_proc_vtable(const struct processor *p)
+{
+	unsigned int cpu = smp_processor_id();
+	*cpu_vtable[cpu] = *p;
+	WARN_ON_ONCE(cpu_vtable[cpu]->dcache_clean_area !=
+		     cpu_vtable[0]->dcache_clean_area);
+	WARN_ON_ONCE(cpu_vtable[cpu]->set_pte_ext !=
+		     cpu_vtable[0]->set_pte_ext);
+}
+#else
+#define PROC_VTABLE(f)			processor.f
+#define PROC_TABLE(f)			processor.f
+static inline void init_proc_vtable(const struct processor *p)
+{
+	processor = *p;
+}
+#endif
+
+#define cpu_proc_init			PROC_VTABLE(_proc_init)
+#define cpu_check_bugs			PROC_VTABLE(check_bugs)
+#define cpu_proc_fin			PROC_VTABLE(_proc_fin)
+#define cpu_reset			PROC_VTABLE(reset)
+#define cpu_do_idle			PROC_VTABLE(_do_idle)
+#define cpu_dcache_clean_area		PROC_TABLE(dcache_clean_area)
+#define cpu_set_pte_ext			PROC_TABLE(set_pte_ext)
+#define cpu_do_switch_mm		PROC_VTABLE(switch_mm)
+
+/* These two are private to arch/arm/kernel/suspend.c */
+#define cpu_do_suspend			PROC_VTABLE(do_suspend)
+#define cpu_do_resume			PROC_VTABLE(do_resume)
 #endif
 
 extern void cpu_resume(void);

arch/arm/kernel/bugs.c

@@ -6,8 +6,8 @@
 void check_other_bugs(void)
 {
 #ifdef MULTI_CPU
-	if (processor.check_bugs)
-		processor.check_bugs();
+	if (cpu_check_bugs)
+		cpu_check_bugs();
 #endif
 }
 

arch/arm/kernel/head-common.S

@@ -145,6 +145,9 @@ __mmap_switched_data:
 #endif
 	.size	__mmap_switched_data, . - __mmap_switched_data
 
+	__FINIT
+	.text
+
 /*
  * This provides a C-API version of __lookup_processor_type
  */
@@ -156,9 +159,6 @@ ENTRY(lookup_processor_type)
 	ldmfd	sp!, {r4 - r6, r9, pc}
 ENDPROC(lookup_processor_type)
 
-	__FINIT
-	.text
-
 /*
  * Read processor ID register (CP#15, CR0), and look up in the linker-built
  * supported processor list.  Note that we can't use the absolute addresses

arch/arm/kernel/setup.c

@@ -114,6 +114,11 @@ EXPORT_SYMBOL(elf_hwcap2);
 
 #ifdef MULTI_CPU
 struct processor processor __ro_after_init;
+#if defined(CONFIG_BIG_LITTLE) && defined(CONFIG_HARDEN_BRANCH_PREDICTOR)
+struct processor *cpu_vtable[NR_CPUS] = {
+	[0] = &processor,
+};
+#endif
 #endif
 #ifdef MULTI_TLB
 struct cpu_tlb_fns cpu_tlb __ro_after_init;
@@ -666,28 +671,33 @@ static void __init smp_build_mpidr_hash(void)
 }
 #endif
 
-static void __init setup_processor(void)
+/*
+ * locate processor in the list of supported processor types.  The linker
+ * builds this table for us from the entries in arch/arm/mm/proc-*.S
+ */
+struct proc_info_list *lookup_processor(u32 midr)
 {
-	struct proc_info_list *list;
+	struct proc_info_list *list = lookup_processor_type(midr);
 
-	/*
-	 * locate processor in the list of supported processor
-	 * types.  The linker builds this table for us from the
-	 * entries in arch/arm/mm/proc-*.S
-	 */
-	list = lookup_processor_type(read_cpuid_id());
 	if (!list) {
-		pr_err("CPU configuration botched (ID %08x), unable to continue.\n",
-		       read_cpuid_id());
-		while (1);
+		pr_err("CPU%u: configuration botched (ID %08x), CPU halted\n",
+		       smp_processor_id(), midr);
+		while (1)
+		/* can't use cpu_relax() here as it may require MMU setup */;
 	}
 
+	return list;
+}
+
+static void __init setup_processor(void)
+{
+	unsigned int midr = read_cpuid_id();
+	struct proc_info_list *list = lookup_processor(midr);
+
 	cpu_name = list->cpu_name;
 	__cpu_architecture = __get_cpu_architecture();
 
-#ifdef MULTI_CPU
-	processor = *list->proc;
-#endif
+	init_proc_vtable(list->proc);
 #ifdef MULTI_TLB
 	cpu_tlb = *list->tlb;
 #endif
@@ -699,7 +709,7 @@ static void __init setup_processor(void)
 #endif
 
 	pr_info("CPU: %s [%08x] revision %d (ARMv%s), cr=%08lx\n",
-		cpu_name, read_cpuid_id(), read_cpuid_id() & 15,
+		list->cpu_name, midr, midr & 15,
 		proc_arch[cpu_architecture()], get_cr());
 
 	snprintf(init_utsname()->machine, __NEW_UTS_LEN + 1, "%s%c",

arch/arm/kernel/smp.c

@@ -42,6 +42,7 @@
 #include <asm/mmu_context.h>
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
+#include <asm/procinfo.h>
 #include <asm/processor.h>
 #include <asm/sections.h>
 #include <asm/tlbflush.h>
@@ -102,6 +103,30 @@ static unsigned long get_arch_pgd(pgd_t *pgd)
 #endif
 }
 
+#if defined(CONFIG_BIG_LITTLE) && defined(CONFIG_HARDEN_BRANCH_PREDICTOR)
+static int secondary_biglittle_prepare(unsigned int cpu)
+{
+	if (!cpu_vtable[cpu])
+		cpu_vtable[cpu] = kzalloc(sizeof(*cpu_vtable[cpu]), GFP_KERNEL);
+
+	return cpu_vtable[cpu] ? 0 : -ENOMEM;
+}
+
+static void secondary_biglittle_init(void)
+{
+	init_proc_vtable(lookup_processor(read_cpuid_id())->proc);
+}
+#else
+static int secondary_biglittle_prepare(unsigned int cpu)
+{
+	return 0;
+}
+
+static void secondary_biglittle_init(void)
+{
+}
+#endif
+
 int __cpu_up(unsigned int cpu, struct task_struct *idle)
 {
 	int ret;
@@ -109,6 +134,10 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle)
 	if (!smp_ops.smp_boot_secondary)
 		return -ENOSYS;
 
+	ret = secondary_biglittle_prepare(cpu);
+	if (ret)
+		return ret;
+
 	/*
 	 * We need to tell the secondary core where to find
 	 * its stack and the page tables.
@@ -359,6 +388,8 @@ asmlinkage void secondary_start_kernel(void)
 	struct mm_struct *mm = &init_mm;
 	unsigned int cpu;
 
+	secondary_biglittle_init();
+
 	/*
 	 * The identity mapping is uncached (strongly ordered), so
 	 * switch away from it before attempting any exclusive accesses.

arch/arm/mach-omap2/display.c

@@ -209,11 +209,61 @@ static int __init omapdss_init_fbdev(void)
 
 	return 0;
 }
-#else
-static inline int omapdss_init_fbdev(void)
+
+static const char * const omapdss_compat_names[] __initconst = {
+	"ti,omap2-dss",
+	"ti,omap3-dss",
+	"ti,omap4-dss",
+	"ti,omap5-dss",
+	"ti,dra7-dss",
+};
+
+static struct device_node * __init omapdss_find_dss_of_node(void)
 {
-	return 0;
+	struct device_node *node;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(omapdss_compat_names); ++i) {
+		node = of_find_compatible_node(NULL, NULL,
+			omapdss_compat_names[i]);
+		if (node)
+			return node;
+	}
+
+	return NULL;
 }
+
+static int __init omapdss_init_of(void)
+{
+	int r;
+	struct device_node *node;
+	struct platform_device *pdev;
+
+	/* only create dss helper devices if dss is enabled in the .dts */
+
+	node = omapdss_find_dss_of_node();
+	if (!node)
+		return 0;
+
+	if (!of_device_is_available(node))
+		return 0;
+
+	pdev = of_find_device_by_node(node);
+
+	if (!pdev) {
+		pr_err("Unable to find DSS platform device\n");
+		return -ENODEV;
+	}
+
+	r = of_platform_populate(node, NULL, NULL, &pdev->dev);
+	if (r) {
+		pr_err("Unable to populate DSS submodule devices\n");
+		return r;
+	}
+
+	return omapdss_init_fbdev();
+}
+omap_device_initcall(omapdss_init_of);
 #endif /* CONFIG_FB_OMAP2 */
 
 static void dispc_disable_outputs(void)
@@ -361,58 +411,3 @@ int omap_dss_reset(struct omap_hwmod *oh)
 
 	return r;
 }
-
-static const char * const omapdss_compat_names[] __initconst = {
-	"ti,omap2-dss",
-	"ti,omap3-dss",
-	"ti,omap4-dss",
-	"ti,omap5-dss",
-	"ti,dra7-dss",
-};
-
-static struct device_node * __init omapdss_find_dss_of_node(void)
-{
-	struct device_node *node;
-	int i;
-
-	for (i = 0; i < ARRAY_SIZE(omapdss_compat_names); ++i) {
-		node = of_find_compatible_node(NULL, NULL,
-			omapdss_compat_names[i]);
-		if (node)
-			return node;
-	}
-
-	return NULL;
-}
-
-static int __init omapdss_init_of(void)
-{
-	int r;
-	struct device_node *node;
-	struct platform_device *pdev;
-
-	/* only create dss helper devices if dss is enabled in the .dts */
-
-	node = omapdss_find_dss_of_node();
-	if (!node)
-		return 0;
-
-	if (!of_device_is_available(node))
-		return 0;
-
-	pdev = of_find_device_by_node(node);
-
-	if (!pdev) {
-		pr_err("Unable to find DSS platform device\n");
-		return -ENODEV;
-	}
-
-	r = of_platform_populate(node, NULL, NULL, &pdev->dev);
-	if (r) {
-		pr_err("Unable to populate DSS submodule devices\n");
-		return r;
-	}
-
-	return omapdss_init_fbdev();
-}
-omap_device_initcall(omapdss_init_of);

arch/arm/mm/proc-v7-bugs.c

@@ -52,8 +52,6 @@ static void cpu_v7_spectre_init(void)
 	case ARM_CPU_PART_CORTEX_A17:
 	case ARM_CPU_PART_CORTEX_A73:
 	case ARM_CPU_PART_CORTEX_A75:
-		if (processor.switch_mm != cpu_v7_bpiall_switch_mm)
-			goto bl_error;
 		per_cpu(harden_branch_predictor_fn, cpu) =
 			harden_branch_predictor_bpiall;
 		spectre_v2_method = "BPIALL";
@@ -61,8 +59,6 @@ static void cpu_v7_spectre_init(void)
 
 	case ARM_CPU_PART_CORTEX_A15:
 	case ARM_CPU_PART_BRAHMA_B15:
-		if (processor.switch_mm != cpu_v7_iciallu_switch_mm)
-			goto bl_error;
 		per_cpu(harden_branch_predictor_fn, cpu) =
 			harden_branch_predictor_iciallu;
 		spectre_v2_method = "ICIALLU";
@@ -88,11 +84,9 @@ static void cpu_v7_spectre_init(void)
 					  ARM_SMCCC_ARCH_WORKAROUND_1, &res);
 			if ((int)res.a0 != 0)
 				break;
-			if (processor.switch_mm != cpu_v7_hvc_switch_mm && cpu)
-				goto bl_error;
 			per_cpu(harden_branch_predictor_fn, cpu) =
 				call_hvc_arch_workaround_1;
-			processor.switch_mm = cpu_v7_hvc_switch_mm;
+			cpu_do_switch_mm = cpu_v7_hvc_switch_mm;
 			spectre_v2_method = "hypervisor";
 			break;
 
@@ -101,11 +95,9 @@ static void cpu_v7_spectre_init(void)
 					  ARM_SMCCC_ARCH_WORKAROUND_1, &res);
 			if ((int)res.a0 != 0)
 				break;
-			if (processor.switch_mm != cpu_v7_smc_switch_mm && cpu)
-				goto bl_error;
 			per_cpu(harden_branch_predictor_fn, cpu) =
 				call_smc_arch_workaround_1;
-			processor.switch_mm = cpu_v7_smc_switch_mm;
+			cpu_do_switch_mm = cpu_v7_smc_switch_mm;
 			spectre_v2_method = "firmware";
 			break;
 
@@ -119,11 +111,6 @@ static void cpu_v7_spectre_init(void)
 	if (spectre_v2_method)
 		pr_info("CPU%u: Spectre v2: using %s workaround\n",
 			smp_processor_id(), spectre_v2_method);
-	return;
-
-bl_error:
-	pr_err("CPU%u: Spectre v2: incorrect context switching function, system vulnerable\n",
-		cpu);
 }
 #else
 static void cpu_v7_spectre_init(void)

arch/arm/vfp/vfpmodule.c

@@ -573,7 +573,7 @@ int vfp_preserve_user_clear_hwstate(struct user_vfp *ufp,
 	 */
 	ufp_exc->fpexc = hwstate->fpexc;
 	ufp_exc->fpinst = hwstate->fpinst;
-	ufp_exc->fpinst2 = ufp_exc->fpinst2;
+	ufp_exc->fpinst2 = hwstate->fpinst2;
 
 	/* Ensure that VFP is disabled. */
 	vfp_flush_hwstate(thread);

arch/arm64/include/asm/processor.h

@@ -24,6 +24,14 @@
 #define KERNEL_DS	UL(-1)
 #define USER_DS		(TASK_SIZE_64 - 1)
 
+/*
+ * On arm64 systems, unaligned accesses by the CPU are cheap, and so there is
+ * no point in shifting all network buffers by 2 bytes just to make some IP
+ * header fields appear aligned in memory, potentially sacrificing some DMA
+ * performance on some platforms.
+ */
+#define NET_IP_ALIGN	0
+
 #ifndef __ASSEMBLY__
 #ifdef __KERNEL__
 

arch/arm64/kernel/setup.c

@@ -313,6 +313,7 @@ void __init setup_arch(char **cmdline_p)
 	arm64_memblock_init();
 
 	paging_init();
+	efi_apply_persistent_mem_reservations();
 
 	acpi_table_upgrade();
 

arch/arm64/mm/init.c

@@ -483,8 +483,6 @@ void __init arm64_memblock_init(void)
 	high_memory = __va(memblock_end_of_DRAM() - 1) + 1;
 
 	dma_contiguous_reserve(arm64_dma_phys_limit);
-
-	memblock_allow_resize();
 }
 
 void __init bootmem_init(void)

arch/arm64/mm/mmu.c

@@ -659,6 +659,8 @@ void __init paging_init(void)
 
 	memblock_free(__pa_symbol(init_pg_dir),
 		      __pa_symbol(init_pg_end) - __pa_symbol(init_pg_dir));
+
+	memblock_allow_resize();
 }
 
 /*

arch/m68k/include/asm/pgtable_mm.h

@@ -55,12 +55,12 @@
  */
 #ifdef CONFIG_SUN3
 #define PTRS_PER_PTE   16
-#define __PAGETABLE_PMD_FOLDED
+#define __PAGETABLE_PMD_FOLDED 1
 #define PTRS_PER_PMD   1
 #define PTRS_PER_PGD   2048
 #elif defined(CONFIG_COLDFIRE)
 #define PTRS_PER_PTE	512
-#define __PAGETABLE_PMD_FOLDED
+#define __PAGETABLE_PMD_FOLDED 1
 #define PTRS_PER_PMD	1
 #define PTRS_PER_PGD	1024
 #else

arch/microblaze/include/asm/pgtable.h

@@ -63,7 +63,7 @@ extern int mem_init_done;
 
 #include <asm-generic/4level-fixup.h>
 
-#define __PAGETABLE_PMD_FOLDED
+#define __PAGETABLE_PMD_FOLDED 1
 
 #ifdef __KERNEL__
 #ifndef __ASSEMBLY__

arch/mips/cavium-octeon/executive/cvmx-helper.c

@@ -67,7 +67,7 @@ void (*cvmx_override_pko_queue_priority) (int pko_port,
 void (*cvmx_override_ipd_port_setup) (int ipd_port);
 
 /* Port count per interface */
-static int interface_port_count[5];
+static int interface_port_count[9];
 
 /**
  * Return the number of interfaces the chip has. Each interface

arch/mips/mm/dma-noncoherent.c

@@ -50,7 +50,7 @@ void *arch_dma_alloc(struct device *dev, size_t size,
 	void *ret;
 
 	ret = dma_direct_alloc_pages(dev, size, dma_handle, gfp, attrs);
-	if (!ret && !(attrs & DMA_ATTR_NON_CONSISTENT)) {
+	if (ret && !(attrs & DMA_ATTR_NON_CONSISTENT)) {
 		dma_cache_wback_inv((unsigned long) ret, size);
 		ret = (void *)UNCAC_ADDR(ret);
 	}

arch/nds32/include/asm/pgtable.h

@@ -4,7 +4,7 @@
 #ifndef _ASMNDS32_PGTABLE_H
 #define _ASMNDS32_PGTABLE_H
 
-#define __PAGETABLE_PMD_FOLDED
+#define __PAGETABLE_PMD_FOLDED 1
 #include <asm-generic/4level-fixup.h>
 #include <asm-generic/sizes.h>
 

arch/parisc/include/asm/pgtable.h

@@ -111,7 +111,7 @@ static inline void purge_tlb_entries(struct mm_struct *mm, unsigned long addr)
 #if CONFIG_PGTABLE_LEVELS == 3
 #define BITS_PER_PMD	(PAGE_SHIFT + PMD_ORDER - BITS_PER_PMD_ENTRY)
 #else
-#define __PAGETABLE_PMD_FOLDED
+#define __PAGETABLE_PMD_FOLDED 1
 #define BITS_PER_PMD	0
 #endif
 #define PTRS_PER_PMD    (1UL << BITS_PER_PMD)

arch/parisc/include/asm/spinlock.h

@@ -37,8 +37,8 @@ static inline void arch_spin_unlock(arch_spinlock_t *x)
 	volatile unsigned int *a;
 
 	a = __ldcw_align(x);
-	/* Release with ordered store. */
-	__asm__ __volatile__("stw,ma %0,0(%1)" : : "r"(1), "r"(a) : "memory");
+	mb();
+	*a = 1;
 }
 
 static inline int arch_spin_trylock(arch_spinlock_t *x)

arch/parisc/kernel/syscall.S

@@ -640,7 +640,8 @@ cas_action:
 	sub,<>	%r28, %r25, %r0
 2:	stw	%r24, 0(%r26)
 	/* Free lock */
-	stw,ma	%r20, 0(%sr2,%r20)
+	sync
+	stw	%r20, 0(%sr2,%r20)
 #if ENABLE_LWS_DEBUG
 	/* Clear thread register indicator */
 	stw	%r0, 4(%sr2,%r20)
@@ -654,7 +655,8 @@ cas_action:
 3:		
 	/* Error occurred on load or store */
 	/* Free lock */
-	stw,ma	%r20, 0(%sr2,%r20)
+	sync
+	stw	%r20, 0(%sr2,%r20)
 #if ENABLE_LWS_DEBUG
 	stw	%r0, 4(%sr2,%r20)
 #endif
@@ -855,7 +857,8 @@ cas2_action:
 
 cas2_end:
 	/* Free lock */
-	stw,ma	%r20, 0(%sr2,%r20)
+	sync
+	stw	%r20, 0(%sr2,%r20)
 	/* Enable interrupts */
 	ssm	PSW_SM_I, %r0
 	/* Return to userspace, set no error */
@@ -865,7 +868,8 @@ cas2_end:
 22:
 	/* Error occurred on load or store */
 	/* Free lock */
-	stw,ma	%r20, 0(%sr2,%r20)
+	sync
+	stw	%r20, 0(%sr2,%r20)
 	ssm	PSW_SM_I, %r0
 	ldo	1(%r0),%r28
 	b	lws_exit

arch/powerpc/include/asm/io.h

@@ -268,19 +268,13 @@ extern void _memcpy_toio(volatile void __iomem *dest, const void *src,
  * their hooks, a bitfield is reserved for use by the platform near the
  * top of MMIO addresses (not PIO, those have to cope the hard way).
  *
- * This bit field is 12 bits and is at the top of the IO virtual
- * addresses PCI_IO_INDIRECT_TOKEN_MASK.
+ * The highest address in the kernel virtual space are:
  *
- * The kernel virtual space is thus:
+ *  d0003fffffffffff	# with Hash MMU
+ *  c00fffffffffffff	# with Radix MMU
  *
- *  0xD000000000000000		: vmalloc
- *  0xD000080000000000		: PCI PHB IO space
- *  0xD000080080000000		: ioremap
- *  0xD0000fffffffffff		: end of ioremap region
- *
- * Since the top 4 bits are reserved as the region ID, we use thus
- * the next 12 bits and keep 4 bits available for the future if the
- * virtual address space is ever to be extended.
+ * The top 4 bits are reserved as the region ID on hash, leaving us 8 bits
+ * that can be used for the field.
  *
  * The direct IO mapping operations will then mask off those bits
  * before doing the actual access, though that only happen when
@@ -292,8 +286,8 @@ extern void _memcpy_toio(volatile void __iomem *dest, const void *src,
  */
 
 #ifdef CONFIG_PPC_INDIRECT_MMIO
-#define PCI_IO_IND_TOKEN_MASK	0x0fff000000000000ul
-#define PCI_IO_IND_TOKEN_SHIFT	48
+#define PCI_IO_IND_TOKEN_SHIFT	52
+#define PCI_IO_IND_TOKEN_MASK	(0xfful << PCI_IO_IND_TOKEN_SHIFT)
 #define PCI_FIX_ADDR(addr)						\
 	((PCI_IO_ADDR)(((unsigned long)(addr)) & ~PCI_IO_IND_TOKEN_MASK))
 #define PCI_GET_ADDR_TOKEN(addr)					\

arch/powerpc/include/asm/ppc-opcode.h

@@ -493,6 +493,8 @@
 					__PPC_RS(t) | __PPC_RA0(a) | __PPC_RB(b))
 #define PPC_SLBFEE_DOT(t, b)	stringify_in_c(.long PPC_INST_SLBFEE | \
 					__PPC_RT(t) | __PPC_RB(b))
+#define __PPC_SLBFEE_DOT(t, b)	stringify_in_c(.long PPC_INST_SLBFEE |	\
+					       ___PPC_RT(t) | ___PPC_RB(b))
 #define PPC_ICBT(c,a,b)		stringify_in_c(.long PPC_INST_ICBT | \
 				       __PPC_CT(c) | __PPC_RA0(a) | __PPC_RB(b))
 /* PASemi instructions */

arch/powerpc/include/asm/ptrace.h

@@ -54,6 +54,7 @@ struct pt_regs
 
 #ifdef CONFIG_PPC64
 	unsigned long ppr;
+	unsigned long __pad;	/* Maintain 16 byte interrupt stack alignment */
 #endif
 };
 #endif

arch/powerpc/kernel/setup_64.c

@@ -636,6 +636,8 @@ static void *__init alloc_stack(unsigned long limit, int cpu)
 {
 	unsigned long pa;
 
+	BUILD_BUG_ON(STACK_INT_FRAME_SIZE % 16);
+
 	pa = memblock_alloc_base_nid(THREAD_SIZE, THREAD_SIZE, limit,
 					early_cpu_to_node(cpu), MEMBLOCK_NONE);
 	if (!pa) {

arch/powerpc/kvm/trace.h

@@ -6,8 +6,6 @@
 
 #undef TRACE_SYSTEM
 #define TRACE_SYSTEM kvm
-#define TRACE_INCLUDE_PATH .
-#define TRACE_INCLUDE_FILE trace
 
 /*
  * Tracepoint for guest mode entry.
@@ -120,4 +118,10 @@ TRACE_EVENT(kvm_check_requests,
 #endif /* _TRACE_KVM_H */
 
 /* This part must be outside protection */
+#undef TRACE_INCLUDE_PATH
+#undef TRACE_INCLUDE_FILE
+
+#define TRACE_INCLUDE_PATH .
+#define TRACE_INCLUDE_FILE trace
+
 #include <trace/define_trace.h>

arch/powerpc/kvm/trace_booke.h

@@ -6,8 +6,6 @@
 
 #undef TRACE_SYSTEM
 #define TRACE_SYSTEM kvm_booke
-#define TRACE_INCLUDE_PATH .
-#define TRACE_INCLUDE_FILE trace_booke
 
 #define kvm_trace_symbol_exit \
 	{0, "CRITICAL"}, \
@@ -218,4 +216,11 @@ TRACE_EVENT(kvm_booke_queue_irqprio,
 #endif
 
 /* This part must be outside protection */
+
+#undef TRACE_INCLUDE_PATH
+#undef TRACE_INCLUDE_FILE
+
+#define TRACE_INCLUDE_PATH .
+#define TRACE_INCLUDE_FILE trace_booke
+
 #include <trace/define_trace.h>

arch/powerpc/kvm/trace_hv.h

@@ -9,8 +9,6 @@
 
 #undef TRACE_SYSTEM
 #define TRACE_SYSTEM kvm_hv
-#define TRACE_INCLUDE_PATH .
-#define TRACE_INCLUDE_FILE trace_hv
 
 #define kvm_trace_symbol_hcall \
 	{H_REMOVE,			"H_REMOVE"}, \
@@ -497,4 +495,11 @@ TRACE_EVENT(kvmppc_run_vcpu_exit,
 #endif /* _TRACE_KVM_HV_H */
 
 /* This part must be outside protection */
+
+#undef TRACE_INCLUDE_PATH
+#undef TRACE_INCLUDE_FILE
+
+#define TRACE_INCLUDE_PATH .
+#define TRACE_INCLUDE_FILE trace_hv
+
 #include <trace/define_trace.h>

arch/powerpc/kvm/trace_pr.h

@@ -8,8 +8,6 @@
 
 #undef TRACE_SYSTEM
 #define TRACE_SYSTEM kvm_pr
-#define TRACE_INCLUDE_PATH .
-#define TRACE_INCLUDE_FILE trace_pr
 
 TRACE_EVENT(kvm_book3s_reenter,
 	TP_PROTO(int r, struct kvm_vcpu *vcpu),
@@ -257,4 +255,11 @@ TRACE_EVENT(kvm_exit,
 #endif /* _TRACE_KVM_H */
 
 /* This part must be outside protection */
+
+#undef TRACE_INCLUDE_PATH
+#undef TRACE_INCLUDE_FILE
+
+#define TRACE_INCLUDE_PATH .
+#define TRACE_INCLUDE_FILE trace_pr
+
 #include <trace/define_trace.h>

arch/powerpc/mm/numa.c

@@ -1178,7 +1178,7 @@ static long vphn_get_associativity(unsigned long cpu,
 
 	switch (rc) {
 	case H_FUNCTION:
-		printk(KERN_INFO
+		printk_once(KERN_INFO
 			"VPHN is not supported. Disabling polling...\n");
 		stop_topology_update();
 		break;

arch/powerpc/mm/slb.c

@@ -19,6 +19,7 @@
 #include <asm/mmu.h>
 #include <asm/mmu_context.h>
 #include <asm/paca.h>
+#include <asm/ppc-opcode.h>
 #include <asm/cputable.h>
 #include <asm/cacheflush.h>
 #include <asm/smp.h>
@@ -58,27 +59,19 @@ static inline unsigned long mk_vsid_data(unsigned long ea, int ssize,
 	return __mk_vsid_data(get_kernel_vsid(ea, ssize), ssize, flags);
 }
 
-static void assert_slb_exists(unsigned long ea)
+static void assert_slb_presence(bool present, unsigned long ea)
 {
 #ifdef CONFIG_DEBUG_VM
 	unsigned long tmp;
 
 	WARN_ON_ONCE(mfmsr() & MSR_EE);
 
-	asm volatile("slbfee. %0, %1" : "=r"(tmp) : "r"(ea) : "cr0");
-	WARN_ON(tmp == 0);
-#endif
-}
-
-static void assert_slb_notexists(unsigned long ea)
-{
-#ifdef CONFIG_DEBUG_VM
-	unsigned long tmp;
+	if (!cpu_has_feature(CPU_FTR_ARCH_206))
+		return;
 
-	WARN_ON_ONCE(mfmsr() & MSR_EE);
+	asm volatile(__PPC_SLBFEE_DOT(%0, %1) : "=r"(tmp) : "r"(ea) : "cr0");
 
-	asm volatile("slbfee. %0, %1" : "=r"(tmp) : "r"(ea) : "cr0");
-	WARN_ON(tmp != 0);
+	WARN_ON(present == (tmp == 0));
 #endif
 }
 
@@ -114,7 +107,7 @@ static inline void create_shadowed_slbe(unsigned long ea, int ssize,
 	 */
 	slb_shadow_update(ea, ssize, flags, index);
 
-	assert_slb_notexists(ea);
+	assert_slb_presence(false, ea);
 	asm volatile("slbmte  %0,%1" :
 		     : "r" (mk_vsid_data(ea, ssize, flags)),
 		       "r" (mk_esid_data(ea, ssize, index))
@@ -137,7 +130,7 @@ void __slb_restore_bolted_realmode(void)
 		       "r" (be64_to_cpu(p->save_area[index].esid)));
 	}
 
-	assert_slb_exists(local_paca->kstack);
+	assert_slb_presence(true, local_paca->kstack);
 }
 
 /*
@@ -185,7 +178,7 @@ void slb_flush_and_restore_bolted(void)
 		     :: "r" (be64_to_cpu(p->save_area[KSTACK_INDEX].vsid)),
 			"r" (be64_to_cpu(p->save_area[KSTACK_INDEX].esid))
 		     : "memory");
-	assert_slb_exists(get_paca()->kstack);
+	assert_slb_presence(true, get_paca()->kstack);
 
 	get_paca()->slb_cache_ptr = 0;
 
@@ -443,9 +436,9 @@ void switch_slb(struct task_struct *tsk, struct mm_struct *mm)
 				ea = (unsigned long)
 					get_paca()->slb_cache[i] << SID_SHIFT;
 				/*
-				 * Could assert_slb_exists here, but hypervisor
-				 * or machine check could have come in and
-				 * removed the entry at this point.
+				 * Could assert_slb_presence(true) here, but
+				 * hypervisor or machine check could have come
+				 * in and removed the entry at this point.
 				 */
 
 				slbie_data = ea;
@@ -676,7 +669,7 @@ static long slb_insert_entry(unsigned long ea, unsigned long context,
 	 * User preloads should add isync afterwards in case the kernel
 	 * accesses user memory before it returns to userspace with rfid.
 	 */
-	assert_slb_notexists(ea);
+	assert_slb_presence(false, ea);
 	asm volatile("slbmte %0, %1" : : "r" (vsid_data), "r" (esid_data));
 
 	barrier();
@@ -715,7 +708,7 @@ static long slb_allocate_kernel(unsigned long ea, unsigned long id)
 			return -EFAULT;
 
 		if (ea < H_VMALLOC_END)
-			flags = get_paca()->vmalloc_sllp;
+			flags = local_paca->vmalloc_sllp;
 		else
 			flags = SLB_VSID_KERNEL | mmu_psize_defs[mmu_io_psize].sllp;
 	} else {

arch/powerpc/platforms/powernv/npu-dma.c

@@ -102,63 +102,6 @@ struct pci_dev *pnv_pci_get_npu_dev(struct pci_dev *gpdev, int index)
 }
 EXPORT_SYMBOL(pnv_pci_get_npu_dev);
 
-#define NPU_DMA_OP_UNSUPPORTED()					\
-	dev_err_once(dev, "%s operation unsupported for NVLink devices\n", \
-		__func__)
-
-static void *dma_npu_alloc(struct device *dev, size_t size,
-			   dma_addr_t *dma_handle, gfp_t flag,
-			   unsigned long attrs)
-{
-	NPU_DMA_OP_UNSUPPORTED();
-	return NULL;
-}
-
-static void dma_npu_free(struct device *dev, size_t size,
-			 void *vaddr, dma_addr_t dma_handle,
-			 unsigned long attrs)
-{
-	NPU_DMA_OP_UNSUPPORTED();
-}
-
-static dma_addr_t dma_npu_map_page(struct device *dev, struct page *page,
-				   unsigned long offset, size_t size,
-				   enum dma_data_direction direction,
-				   unsigned long attrs)
-{
-	NPU_DMA_OP_UNSUPPORTED();
-	return 0;
-}
-
-static int dma_npu_map_sg(struct device *dev, struct scatterlist *sglist,
-			  int nelems, enum dma_data_direction direction,
-			  unsigned long attrs)
-{
-	NPU_DMA_OP_UNSUPPORTED();
-	return 0;
-}
-
-static int dma_npu_dma_supported(struct device *dev, u64 mask)
-{
-	NPU_DMA_OP_UNSUPPORTED();
-	return 0;
-}
-
-static u64 dma_npu_get_required_mask(struct device *dev)
-{
-	NPU_DMA_OP_UNSUPPORTED();
-	return 0;
-}
-
-static const struct dma_map_ops dma_npu_ops = {
-	.map_page		= dma_npu_map_page,
-	.map_sg			= dma_npu_map_sg,
-	.alloc			= dma_npu_alloc,
-	.free			= dma_npu_free,
-	.dma_supported		= dma_npu_dma_supported,
-	.get_required_mask	= dma_npu_get_required_mask,
-};
-
 /*
  * Returns the PE assoicated with the PCI device of the given
  * NPU. Returns the linked pci device if pci_dev != NULL.
@@ -270,10 +213,11 @@ static void pnv_npu_dma_set_32(struct pnv_ioda_pe *npe)
 	rc = pnv_npu_set_window(npe, 0, gpe->table_group.tables[0]);
 
 	/*
-	 * We don't initialise npu_pe->tce32_table as we always use
-	 * dma_npu_ops which are nops.
+	 * NVLink devices use the same TCE table configuration as
+	 * their parent device so drivers shouldn't be doing DMA
+	 * operations directly on these devices.
 	 */
-	set_dma_ops(&npe->pdev->dev, &dma_npu_ops);
+	set_dma_ops(&npe->pdev->dev, NULL);
 }
 
 /*

arch/riscv/Makefile

@@ -77,4 +77,8 @@ core-y += arch/riscv/kernel/ arch/riscv/mm/
 
 libs-y += arch/riscv/lib/
 
+PHONY += vdso_install
+vdso_install:
+	$(Q)$(MAKE) $(build)=arch/riscv/kernel/vdso $@
+
 all: vmlinux

arch/riscv/configs/defconfig

@@ -76,4 +76,5 @@ CONFIG_NFS_V4_1=y
 CONFIG_NFS_V4_2=y
 CONFIG_ROOT_NFS=y
 CONFIG_CRYPTO_USER_API_HASH=y
+CONFIG_PRINTK_TIME=y
 # CONFIG_RCU_TRACE is not set

arch/riscv/include/asm/ptrace.h

@@ -56,8 +56,8 @@ struct pt_regs {
 	unsigned long sstatus;
 	unsigned long sbadaddr;
 	unsigned long scause;
-        /* a0 value before the syscall */
-        unsigned long orig_a0;
+	/* a0 value before the syscall */
+	unsigned long orig_a0;
 };
 
 #ifdef CONFIG_64BIT

arch/riscv/kernel/module.c

@@ -21,7 +21,7 @@ static int apply_r_riscv_32_rela(struct module *me, u32 *location, Elf_Addr v)
 {
 	if (v != (u32)v) {
 		pr_err("%s: value %016llx out of range for 32-bit field\n",
-		       me->name, v);
+		       me->name, (long long)v);
 		return -EINVAL;
 	}
 	*location = v;
@@ -102,7 +102,7 @@ static int apply_r_riscv_pcrel_hi20_rela(struct module *me, u32 *location,
 	if (offset != (s32)offset) {
 		pr_err(
 		  "%s: target %016llx can not be addressed by the 32-bit offset from PC = %p\n",
-		  me->name, v, location);
+		  me->name, (long long)v, location);
 		return -EINVAL;
 	}
 
@@ -144,7 +144,7 @@ static int apply_r_riscv_hi20_rela(struct module *me, u32 *location,
 	if (IS_ENABLED(CMODEL_MEDLOW)) {
 		pr_err(
 		  "%s: target %016llx can not be addressed by the 32-bit offset from PC = %p\n",
-		  me->name, v, location);
+		  me->name, (long long)v, location);
 		return -EINVAL;
 	}
 
@@ -188,7 +188,7 @@ static int apply_r_riscv_got_hi20_rela(struct module *me, u32 *location,
 	} else {
 		pr_err(
 		  "%s: can not generate the GOT entry for symbol = %016llx from PC = %p\n",
-		  me->name, v, location);
+		  me->name, (long long)v, location);
 		return -EINVAL;
 	}
 
@@ -212,7 +212,7 @@ static int apply_r_riscv_call_plt_rela(struct module *me, u32 *location,
 		} else {
 			pr_err(
 			  "%s: target %016llx can not be addressed by the 32-bit offset from PC = %p\n",
-			  me->name, v, location);
+			  me->name, (long long)v, location);
 			return -EINVAL;
 		}
 	}
@@ -234,7 +234,7 @@ static int apply_r_riscv_call_rela(struct module *me, u32 *location,
 	if (offset != fill_v) {
 		pr_err(
 		  "%s: target %016llx can not be addressed by the 32-bit offset from PC = %p\n",
-		  me->name, v, location);
+		  me->name, (long long)v, location);
 		return -EINVAL;
 	}
 

arch/riscv/lib/Makefile

@@ -3,6 +3,6 @@ lib-y	+= memcpy.o
 lib-y	+= memset.o
 lib-y	+= uaccess.o
 
-lib-(CONFIG_64BIT) += tishift.o
+lib-$(CONFIG_64BIT) += tishift.o
 
 lib-$(CONFIG_32BIT) += udivdi3.o

arch/s390/Makefile

@@ -27,7 +27,7 @@ KBUILD_CFLAGS_DECOMPRESSOR += $(call cc-option,-ffreestanding)
 KBUILD_CFLAGS_DECOMPRESSOR += $(if $(CONFIG_DEBUG_INFO),-g)
 KBUILD_CFLAGS_DECOMPRESSOR += $(if $(CONFIG_DEBUG_INFO_DWARF4), $(call cc-option, -gdwarf-4,))
 UTS_MACHINE	:= s390x
-STACK_SIZE	:= $(if $(CONFIG_KASAN),32768,16384)
+STACK_SIZE	:= $(if $(CONFIG_KASAN),65536,16384)
 CHECKFLAGS	+= -D__s390__ -D__s390x__
 
 export LD_BFD

arch/s390/boot/compressed/Makefile

@@ -22,10 +22,10 @@ OBJCOPYFLAGS :=
 OBJECTS := $(addprefix $(obj)/,$(obj-y))
 
 LDFLAGS_vmlinux := --oformat $(LD_BFD) -e startup -T
-$(obj)/vmlinux: $(obj)/vmlinux.lds $(objtree)/arch/s390/boot/startup.a $(OBJECTS)
+$(obj)/vmlinux: $(obj)/vmlinux.lds $(objtree)/arch/s390/boot/startup.a $(OBJECTS) FORCE
 	$(call if_changed,ld)
 
-OBJCOPYFLAGS_info.bin := -O binary --only-section=.vmlinux.info
+OBJCOPYFLAGS_info.bin := -O binary --only-section=.vmlinux.info --set-section-flags .vmlinux.info=load
 $(obj)/info.bin: vmlinux FORCE
 	$(call if_changed,objcopy)
 
@@ -46,17 +46,17 @@ suffix-$(CONFIG_KERNEL_LZMA)  := .lzma
 suffix-$(CONFIG_KERNEL_LZO)  := .lzo
 suffix-$(CONFIG_KERNEL_XZ)  := .xz
 
-$(obj)/vmlinux.bin.gz: $(vmlinux.bin.all-y)
+$(obj)/vmlinux.bin.gz: $(vmlinux.bin.all-y) FORCE
 	$(call if_changed,gzip)
-$(obj)/vmlinux.bin.bz2: $(vmlinux.bin.all-y)
+$(obj)/vmlinux.bin.bz2: $(vmlinux.bin.all-y) FORCE
 	$(call if_changed,bzip2)
-$(obj)/vmlinux.bin.lz4: $(vmlinux.bin.all-y)
+$(obj)/vmlinux.bin.lz4: $(vmlinux.bin.all-y) FORCE
 	$(call if_changed,lz4)
-$(obj)/vmlinux.bin.lzma: $(vmlinux.bin.all-y)
+$(obj)/vmlinux.bin.lzma: $(vmlinux.bin.all-y) FORCE
 	$(call if_changed,lzma)
-$(obj)/vmlinux.bin.lzo: $(vmlinux.bin.all-y)
+$(obj)/vmlinux.bin.lzo: $(vmlinux.bin.all-y) FORCE
 	$(call if_changed,lzo)
-$(obj)/vmlinux.bin.xz: $(vmlinux.bin.all-y)
+$(obj)/vmlinux.bin.xz: $(vmlinux.bin.all-y) FORCE
 	$(call if_changed,xzkern)
 
 OBJCOPYFLAGS_piggy.o := -I binary -O elf64-s390 -B s390:64-bit --rename-section .data=.vmlinux.bin.compressed

arch/s390/configs/debug_defconfig

@@ -64,6 +64,8 @@ CONFIG_NUMA=y
 CONFIG_PREEMPT=y
 CONFIG_HZ_100=y
 CONFIG_KEXEC_FILE=y
+CONFIG_EXPOLINE=y
+CONFIG_EXPOLINE_AUTO=y
 CONFIG_MEMORY_HOTPLUG=y
 CONFIG_MEMORY_HOTREMOVE=y
 CONFIG_KSM=y
@@ -84,9 +86,11 @@ CONFIG_PCI_DEBUG=y
 CONFIG_HOTPLUG_PCI=y
 CONFIG_HOTPLUG_PCI_S390=y
 CONFIG_CHSC_SCH=y
+CONFIG_VFIO_AP=m
 CONFIG_CRASH_DUMP=y
 CONFIG_BINFMT_MISC=m
 CONFIG_HIBERNATION=y
+CONFIG_PM_DEBUG=y
 CONFIG_NET=y
 CONFIG_PACKET=y
 CONFIG_PACKET_DIAG=m
@@ -161,8 +165,6 @@ CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_CT_NETLINK=m
 CONFIG_NF_CT_NETLINK_TIMEOUT=m
 CONFIG_NF_TABLES=m
-CONFIG_NFT_EXTHDR=m
-CONFIG_NFT_META=m
 CONFIG_NFT_CT=m
 CONFIG_NFT_COUNTER=m
 CONFIG_NFT_LOG=m
@@ -365,6 +367,8 @@ CONFIG_NET_ACT_SKBEDIT=m
 CONFIG_NET_ACT_CSUM=m
 CONFIG_DNS_RESOLVER=y
 CONFIG_OPENVSWITCH=m
+CONFIG_VSOCKETS=m
+CONFIG_VIRTIO_VSOCKETS=m
 CONFIG_NETLINK_DIAG=m
 CONFIG_CGROUP_NET_PRIO=y
 CONFIG_BPF_JIT=y
@@ -461,6 +465,7 @@ CONFIG_PPTP=m
 CONFIG_PPPOL2TP=m
 CONFIG_PPP_ASYNC=m
 CONFIG_PPP_SYNC_TTY=m
+CONFIG_ISM=m
 CONFIG_INPUT_EVDEV=y
 # CONFIG_INPUT_KEYBOARD is not set
 # CONFIG_INPUT_MOUSE is not set
@@ -486,9 +491,12 @@ CONFIG_MLX4_INFINIBAND=m
 CONFIG_MLX5_INFINIBAND=m
 CONFIG_VFIO=m
 CONFIG_VFIO_PCI=m
+CONFIG_VFIO_MDEV=m
+CONFIG_VFIO_MDEV_DEVICE=m
 CONFIG_VIRTIO_PCI=m
 CONFIG_VIRTIO_BALLOON=m
 CONFIG_VIRTIO_INPUT=y
+CONFIG_S390_AP_IOMMU=y
 CONFIG_EXT4_FS=y
 CONFIG_EXT4_FS_POSIX_ACL=y
 CONFIG_EXT4_FS_SECURITY=y
@@ -615,7 +623,6 @@ CONFIG_DEBUG_CREDENTIALS=y
 CONFIG_RCU_TORTURE_TEST=m
 CONFIG_RCU_CPU_STALL_TIMEOUT=300
 CONFIG_NOTIFIER_ERROR_INJECTION=m
-CONFIG_PM_NOTIFIER_ERROR_INJECT=m
 CONFIG_NETDEV_NOTIFIER_ERROR_INJECT=m
 CONFIG_FAULT_INJECTION=y
 CONFIG_FAILSLAB=y
@@ -727,3 +734,4 @@ CONFIG_APPLDATA_BASE=y
 CONFIG_KVM=m
 CONFIG_KVM_S390_UCONTROL=y
 CONFIG_VHOST_NET=m
+CONFIG_VHOST_VSOCK=m

arch/s390/configs/performance_defconfig

@@ -65,6 +65,8 @@ CONFIG_NR_CPUS=512
 CONFIG_NUMA=y
 CONFIG_HZ_100=y
 CONFIG_KEXEC_FILE=y
+CONFIG_EXPOLINE=y
+CONFIG_EXPOLINE_AUTO=y
 CONFIG_MEMORY_HOTPLUG=y
 CONFIG_MEMORY_HOTREMOVE=y
 CONFIG_KSM=y
@@ -82,9 +84,11 @@ CONFIG_PCI=y
 CONFIG_HOTPLUG_PCI=y
 CONFIG_HOTPLUG_PCI_S390=y
 CONFIG_CHSC_SCH=y
+CONFIG_VFIO_AP=m
 CONFIG_CRASH_DUMP=y
 CONFIG_BINFMT_MISC=m
 CONFIG_HIBERNATION=y
+CONFIG_PM_DEBUG=y
 CONFIG_NET=y
 CONFIG_PACKET=y
 CONFIG_PACKET_DIAG=m
@@ -159,8 +163,6 @@ CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_CT_NETLINK=m
 CONFIG_NF_CT_NETLINK_TIMEOUT=m
 CONFIG_NF_TABLES=m
-CONFIG_NFT_EXTHDR=m
-CONFIG_NFT_META=m
 CONFIG_NFT_CT=m
 CONFIG_NFT_COUNTER=m
 CONFIG_NFT_LOG=m
@@ -362,6 +364,8 @@ CONFIG_NET_ACT_SKBEDIT=m
 CONFIG_NET_ACT_CSUM=m
 CONFIG_DNS_RESOLVER=y
 CONFIG_OPENVSWITCH=m
+CONFIG_VSOCKETS=m
+CONFIG_VIRTIO_VSOCKETS=m
 CONFIG_NETLINK_DIAG=m
 CONFIG_CGROUP_NET_PRIO=y
 CONFIG_BPF_JIT=y
@@ -458,6 +462,7 @@ CONFIG_PPTP=m
 CONFIG_PPPOL2TP=m
 CONFIG_PPP_ASYNC=m
 CONFIG_PPP_SYNC_TTY=m
+CONFIG_ISM=m
 CONFIG_INPUT_EVDEV=y
 # CONFIG_INPUT_KEYBOARD is not set
 # CONFIG_INPUT_MOUSE is not set
@@ -483,9 +488,12 @@ CONFIG_MLX4_INFINIBAND=m
 CONFIG_MLX5_INFINIBAND=m
 CONFIG_VFIO=m
 CONFIG_VFIO_PCI=m
+CONFIG_VFIO_MDEV=m
+CONFIG_VFIO_MDEV_DEVICE=m
 CONFIG_VIRTIO_PCI=m
 CONFIG_VIRTIO_BALLOON=m
 CONFIG_VIRTIO_INPUT=y
+CONFIG_S390_AP_IOMMU=y
 CONFIG_EXT4_FS=y
 CONFIG_EXT4_FS_POSIX_ACL=y
 CONFIG_EXT4_FS_SECURITY=y
@@ -666,3 +674,4 @@ CONFIG_APPLDATA_BASE=y
 CONFIG_KVM=m
 CONFIG_KVM_S390_UCONTROL=y
 CONFIG_VHOST_NET=m
+CONFIG_VHOST_VSOCK=m

arch/s390/defconfig

@@ -26,14 +26,23 @@ CONFIG_CGROUP_CPUACCT=y
 CONFIG_CGROUP_PERF=y
 CONFIG_NAMESPACES=y
 CONFIG_USER_NS=y
+CONFIG_CHECKPOINT_RESTORE=y
 CONFIG_BLK_DEV_INITRD=y
 CONFIG_EXPERT=y
 # CONFIG_SYSFS_SYSCALL is not set
-CONFIG_CHECKPOINT_RESTORE=y
 CONFIG_BPF_SYSCALL=y
 CONFIG_USERFAULTFD=y
 # CONFIG_COMPAT_BRK is not set
 CONFIG_PROFILING=y
+CONFIG_LIVEPATCH=y
+CONFIG_NR_CPUS=256
+CONFIG_NUMA=y
+CONFIG_HZ_100=y
+CONFIG_KEXEC_FILE=y
+CONFIG_CRASH_DUMP=y
+CONFIG_HIBERNATION=y
+CONFIG_PM_DEBUG=y
+CONFIG_CMM=m
 CONFIG_OPROFILE=y
 CONFIG_KPROBES=y
 CONFIG_JUMP_LABEL=y
@@ -44,11 +53,7 @@ CONFIG_BLK_DEV_INTEGRITY=y
 CONFIG_PARTITION_ADVANCED=y
 CONFIG_IBM_PARTITION=y
 CONFIG_DEFAULT_DEADLINE=y
-CONFIG_LIVEPATCH=y
-CONFIG_NR_CPUS=256
-CONFIG_NUMA=y
-CONFIG_HZ_100=y
-CONFIG_KEXEC_FILE=y
+CONFIG_BINFMT_MISC=m
 CONFIG_MEMORY_HOTPLUG=y
 CONFIG_MEMORY_HOTREMOVE=y
 CONFIG_KSM=y
@@ -60,9 +65,6 @@ CONFIG_ZBUD=m
 CONFIG_ZSMALLOC=m
 CONFIG_ZSMALLOC_STAT=y
 CONFIG_IDLE_PAGE_TRACKING=y
-CONFIG_CRASH_DUMP=y
-CONFIG_BINFMT_MISC=m
-CONFIG_HIBERNATION=y
 CONFIG_NET=y
 CONFIG_PACKET=y
 CONFIG_UNIX=y
@@ -98,6 +100,7 @@ CONFIG_BLK_DEV_NBD=m
 CONFIG_BLK_DEV_RAM=y
 CONFIG_VIRTIO_BLK=y
 CONFIG_SCSI=y
+# CONFIG_SCSI_MQ_DEFAULT is not set
 CONFIG_BLK_DEV_SD=y
 CONFIG_CHR_DEV_ST=y
 CONFIG_BLK_DEV_SR=y
@@ -131,6 +134,7 @@ CONFIG_EQUALIZER=m
 CONFIG_TUN=m
 CONFIG_VIRTIO_NET=y
 # CONFIG_NET_VENDOR_ALACRITECH is not set
+# CONFIG_NET_VENDOR_AURORA is not set
 # CONFIG_NET_VENDOR_CORTINA is not set
 # CONFIG_NET_VENDOR_SOLARFLARE is not set
 # CONFIG_NET_VENDOR_SOCIONEXT is not set
@@ -157,33 +161,6 @@ CONFIG_TMPFS=y
 CONFIG_TMPFS_POSIX_ACL=y
 CONFIG_HUGETLBFS=y
 # CONFIG_NETWORK_FILESYSTEMS is not set
-CONFIG_DEBUG_INFO=y
-CONFIG_DEBUG_INFO_DWARF4=y
-CONFIG_GDB_SCRIPTS=y
-CONFIG_UNUSED_SYMBOLS=y
-CONFIG_DEBUG_SECTION_MISMATCH=y
-CONFIG_DEBUG_FORCE_WEAK_PER_CPU=y
-CONFIG_MAGIC_SYSRQ=y
-CONFIG_DEBUG_PAGEALLOC=y
-CONFIG_DETECT_HUNG_TASK=y
-CONFIG_PANIC_ON_OOPS=y
-CONFIG_PROVE_LOCKING=y
-CONFIG_LOCK_STAT=y
-CONFIG_DEBUG_LOCKDEP=y
-CONFIG_DEBUG_ATOMIC_SLEEP=y
-CONFIG_DEBUG_LIST=y
-CONFIG_DEBUG_SG=y
-CONFIG_DEBUG_NOTIFIERS=y
-CONFIG_RCU_CPU_STALL_TIMEOUT=60
-CONFIG_LATENCYTOP=y
-CONFIG_SCHED_TRACER=y
-CONFIG_FTRACE_SYSCALLS=y
-CONFIG_TRACER_SNAPSHOT_PER_CPU_SWAP=y
-CONFIG_STACK_TRACER=y
-CONFIG_BLK_DEV_IO_TRACE=y
-CONFIG_FUNCTION_PROFILER=y
-# CONFIG_RUNTIME_TESTING_MENU is not set
-CONFIG_S390_PTDUMP=y
 CONFIG_CRYPTO_CRYPTD=m
 CONFIG_CRYPTO_AUTHENC=m
 CONFIG_CRYPTO_TEST=m
@@ -193,6 +170,7 @@ CONFIG_CRYPTO_CBC=y
 CONFIG_CRYPTO_CFB=m
 CONFIG_CRYPTO_CTS=m
 CONFIG_CRYPTO_LRW=m
+CONFIG_CRYPTO_OFB=m
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_XTS=m
 CONFIG_CRYPTO_CMAC=m
@@ -231,7 +209,6 @@ CONFIG_CRYPTO_USER_API_HASH=m
 CONFIG_CRYPTO_USER_API_SKCIPHER=m
 CONFIG_CRYPTO_USER_API_RNG=m
 CONFIG_ZCRYPT=m
-CONFIG_ZCRYPT_MULTIDEVNODES=y
 CONFIG_PKEY=m
 CONFIG_CRYPTO_PAES_S390=m
 CONFIG_CRYPTO_SHA1_S390=m
@@ -247,4 +224,30 @@ CONFIG_CRC7=m
 # CONFIG_XZ_DEC_ARM is not set
 # CONFIG_XZ_DEC_ARMTHUMB is not set
 # CONFIG_XZ_DEC_SPARC is not set
-CONFIG_CMM=m
+CONFIG_DEBUG_INFO=y
+CONFIG_DEBUG_INFO_DWARF4=y
+CONFIG_GDB_SCRIPTS=y
+CONFIG_UNUSED_SYMBOLS=y
+CONFIG_DEBUG_SECTION_MISMATCH=y
+CONFIG_DEBUG_FORCE_WEAK_PER_CPU=y
+CONFIG_MAGIC_SYSRQ=y
+CONFIG_DEBUG_PAGEALLOC=y
+CONFIG_DETECT_HUNG_TASK=y
+CONFIG_PANIC_ON_OOPS=y
+CONFIG_PROVE_LOCKING=y
+CONFIG_LOCK_STAT=y
+CONFIG_DEBUG_LOCKDEP=y
+CONFIG_DEBUG_ATOMIC_SLEEP=y
+CONFIG_DEBUG_LIST=y
+CONFIG_DEBUG_SG=y
+CONFIG_DEBUG_NOTIFIERS=y
+CONFIG_RCU_CPU_STALL_TIMEOUT=60
+CONFIG_LATENCYTOP=y
+CONFIG_SCHED_TRACER=y
+CONFIG_FTRACE_SYSCALLS=y
+CONFIG_TRACER_SNAPSHOT_PER_CPU_SWAP=y
+CONFIG_STACK_TRACER=y
+CONFIG_BLK_DEV_IO_TRACE=y
+CONFIG_FUNCTION_PROFILER=y
+# CONFIG_RUNTIME_TESTING_MENU is not set
+CONFIG_S390_PTDUMP=y

arch/s390/include/asm/mmu_context.h

@@ -46,8 +46,6 @@ static inline int init_new_context(struct task_struct *tsk,
 		mm->context.asce_limit = STACK_TOP_MAX;
 		mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH |
 				   _ASCE_USER_BITS | _ASCE_TYPE_REGION3;
-		/* pgd_alloc() did not account this pud */
-		mm_inc_nr_puds(mm);
 		break;
 	case -PAGE_SIZE:
 		/* forked 5-level task, set new asce with new_mm->pgd */
@@ -63,9 +61,6 @@ static inline int init_new_context(struct task_struct *tsk,
 		/* forked 2-level compat task, set new asce with new mm->pgd */
 		mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH |
 				   _ASCE_USER_BITS | _ASCE_TYPE_SEGMENT;
-		/* pgd_alloc() did not account this pmd */
-		mm_inc_nr_pmds(mm);
-		mm_inc_nr_puds(mm);
 	}
 	crst_table_init((unsigned long *) mm->pgd, pgd_entry_type(mm));
 	return 0;

arch/s390/include/asm/pgalloc.h

@@ -36,11 +36,11 @@ static inline void crst_table_init(unsigned long *crst, unsigned long entry)
 
 static inline unsigned long pgd_entry_type(struct mm_struct *mm)
 {
-	if (mm->context.asce_limit <= _REGION3_SIZE)
+	if (mm_pmd_folded(mm))
 		return _SEGMENT_ENTRY_EMPTY;
-	if (mm->context.asce_limit <= _REGION2_SIZE)
+	if (mm_pud_folded(mm))
 		return _REGION3_ENTRY_EMPTY;
-	if (mm->context.asce_limit <= _REGION1_SIZE)
+	if (mm_p4d_folded(mm))
 		return _REGION2_ENTRY_EMPTY;
 	return _REGION1_ENTRY_EMPTY;
 }

arch/s390/include/asm/pgtable.h

@@ -493,6 +493,24 @@ static inline int is_module_addr(void *addr)
 				   _REGION_ENTRY_PROTECT | \
 				   _REGION_ENTRY_NOEXEC)
 
+static inline bool mm_p4d_folded(struct mm_struct *mm)
+{
+	return mm->context.asce_limit <= _REGION1_SIZE;
+}
+#define mm_p4d_folded(mm) mm_p4d_folded(mm)
+
+static inline bool mm_pud_folded(struct mm_struct *mm)
+{
+	return mm->context.asce_limit <= _REGION2_SIZE;
+}
+#define mm_pud_folded(mm) mm_pud_folded(mm)
+
+static inline bool mm_pmd_folded(struct mm_struct *mm)
+{
+	return mm->context.asce_limit <= _REGION3_SIZE;
+}
+#define mm_pmd_folded(mm) mm_pmd_folded(mm)
+
 static inline int mm_has_pgste(struct mm_struct *mm)
 {
 #ifdef CONFIG_PGSTE

arch/s390/include/asm/thread_info.h

@@ -14,7 +14,7 @@
  * General size of kernel stacks
  */
 #ifdef CONFIG_KASAN
-#define THREAD_SIZE_ORDER 3
+#define THREAD_SIZE_ORDER 4
 #else
 #define THREAD_SIZE_ORDER 2
 #endif

arch/s390/include/asm/tlb.h

@@ -136,7 +136,7 @@ static inline void pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte,
 static inline void pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd,
 				unsigned long address)
 {
-	if (tlb->mm->context.asce_limit <= _REGION3_SIZE)
+	if (mm_pmd_folded(tlb->mm))
 		return;
 	pgtable_pmd_page_dtor(virt_to_page(pmd));
 	tlb_remove_table(tlb, pmd);
@@ -152,7 +152,7 @@ static inline void pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd,
 static inline void p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d,
 				unsigned long address)
 {
-	if (tlb->mm->context.asce_limit <= _REGION1_SIZE)
+	if (mm_p4d_folded(tlb->mm))
 		return;
 	tlb_remove_table(tlb, p4d);
 }
@@ -167,7 +167,7 @@ static inline void p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d,
 static inline void pud_free_tlb(struct mmu_gather *tlb, pud_t *pud,
 				unsigned long address)
 {
-	if (tlb->mm->context.asce_limit <= _REGION2_SIZE)
+	if (mm_pud_folded(tlb->mm))
 		return;
 	tlb_remove_table(tlb, pud);
 }

arch/s390/kernel/entry.S

@@ -236,10 +236,10 @@ ENTRY(__switch_to)
 	stmg	%r6,%r15,__SF_GPRS(%r15)	# store gprs of prev task
 	lghi	%r4,__TASK_stack
 	lghi	%r1,__TASK_thread
-	lg	%r5,0(%r4,%r3)			# start of kernel stack of next
+	llill	%r5,STACK_INIT
 	stg	%r15,__THREAD_ksp(%r1,%r2)	# store kernel stack of prev
-	lgr	%r15,%r5
-	aghi	%r15,STACK_INIT			# end of kernel stack of next
+	lg	%r15,0(%r4,%r3)			# start of kernel stack of next
+	agr	%r15,%r5			# end of kernel stack of next
 	stg	%r3,__LC_CURRENT		# store task struct of next
 	stg	%r15,__LC_KERNEL_STACK		# store end of kernel stack
 	lg	%r15,__THREAD_ksp(%r1,%r3)	# load kernel stack of next

arch/s390/kernel/perf_cpum_cf.c

@@ -373,7 +373,7 @@ static int __hw_perf_event_init(struct perf_event *event)
 		return -ENOENT;
 
 	if (ev > PERF_CPUM_CF_MAX_CTR)
-		return -EINVAL;
+		return -ENOENT;
 
 	/* Obtain the counter set to which the specified counter belongs */
 	set = get_counter_set(ev);

arch/s390/kernel/perf_cpum_sf.c

@@ -1842,10 +1842,30 @@ static void cpumsf_pmu_del(struct perf_event *event, int flags)
 CPUMF_EVENT_ATTR(SF, SF_CYCLES_BASIC, PERF_EVENT_CPUM_SF);
 CPUMF_EVENT_ATTR(SF, SF_CYCLES_BASIC_DIAG, PERF_EVENT_CPUM_SF_DIAG);
 
-static struct attribute *cpumsf_pmu_events_attr[] = {
-	CPUMF_EVENT_PTR(SF, SF_CYCLES_BASIC),
-	NULL,
-	NULL,
+/* Attribute list for CPU_SF.
+ *
+ * The availablitiy depends on the CPU_MF sampling facility authorization
+ * for basic + diagnositic samples. This is determined at initialization
+ * time by the sampling facility device driver.
+ * If the authorization for basic samples is turned off, it should be
+ * also turned off for diagnostic sampling.
+ *
+ * During initialization of the device driver, check the authorization
+ * level for diagnostic sampling and installs the attribute
+ * file for diagnostic sampling if necessary.
+ *
+ * For now install a placeholder to reference all possible attributes:
+ * SF_CYCLES_BASIC and SF_CYCLES_BASIC_DIAG.
+ * Add another entry for the final NULL pointer.
+ */
+enum {
+	SF_CYCLES_BASIC_ATTR_IDX = 0,
+	SF_CYCLES_BASIC_DIAG_ATTR_IDX,
+	SF_CYCLES_ATTR_MAX
+};
+
+static struct attribute *cpumsf_pmu_events_attr[SF_CYCLES_ATTR_MAX + 1] = {
+	[SF_CYCLES_BASIC_ATTR_IDX] = CPUMF_EVENT_PTR(SF, SF_CYCLES_BASIC)
 };
 
 PMU_FORMAT_ATTR(event, "config:0-63");
@@ -2040,7 +2060,10 @@ static int __init init_cpum_sampling_pmu(void)
 
 	if (si.ad) {
 		sfb_set_limits(CPUM_SF_MIN_SDB, CPUM_SF_MAX_SDB);
-		cpumsf_pmu_events_attr[1] =
+		/* Sampling of diagnostic data authorized,
+		 * install event into attribute list of PMU device.
+		 */
+		cpumsf_pmu_events_attr[SF_CYCLES_BASIC_DIAG_ATTR_IDX] =
 			CPUMF_EVENT_PTR(SF, SF_CYCLES_BASIC_DIAG);
 	}
 

arch/s390/kernel/vdso32/Makefile

@@ -37,7 +37,7 @@ KASAN_SANITIZE := n
 $(obj)/vdso32_wrapper.o : $(obj)/vdso32.so
 
 # link rule for the .so file, .lds has to be first
-$(obj)/vdso32.so.dbg: $(src)/vdso32.lds $(obj-vdso32)
+$(obj)/vdso32.so.dbg: $(src)/vdso32.lds $(obj-vdso32) FORCE
 	$(call if_changed,vdso32ld)
 
 # strip rule for the .so file
@@ -46,12 +46,12 @@ $(obj)/%.so: $(obj)/%.so.dbg FORCE
 	$(call if_changed,objcopy)
 
 # assembly rules for the .S files
-$(obj-vdso32): %.o: %.S
+$(obj-vdso32): %.o: %.S FORCE
 	$(call if_changed_dep,vdso32as)
 
 # actual build commands
 quiet_cmd_vdso32ld = VDSO32L $@
-      cmd_vdso32ld = $(CC) $(c_flags) -Wl,-T $^ -o $@
+      cmd_vdso32ld = $(CC) $(c_flags) -Wl,-T $(filter %.lds %.o,$^) -o $@
 quiet_cmd_vdso32as = VDSO32A $@
       cmd_vdso32as = $(CC) $(a_flags) -c -o $@ $<
 

arch/s390/kernel/vdso64/Makefile

@@ -37,7 +37,7 @@ KASAN_SANITIZE := n
 $(obj)/vdso64_wrapper.o : $(obj)/vdso64.so
 
 # link rule for the .so file, .lds has to be first
-$(obj)/vdso64.so.dbg: $(src)/vdso64.lds $(obj-vdso64)
+$(obj)/vdso64.so.dbg: $(src)/vdso64.lds $(obj-vdso64) FORCE
 	$(call if_changed,vdso64ld)
 
 # strip rule for the .so file
@@ -46,12 +46,12 @@ $(obj)/%.so: $(obj)/%.so.dbg FORCE
 	$(call if_changed,objcopy)
 
 # assembly rules for the .S files
-$(obj-vdso64): %.o: %.S
+$(obj-vdso64): %.o: %.S FORCE
 	$(call if_changed_dep,vdso64as)
 
 # actual build commands
 quiet_cmd_vdso64ld = VDSO64L $@
-      cmd_vdso64ld = $(CC) $(c_flags) -Wl,-T $^ -o $@
+      cmd_vdso64ld = $(CC) $(c_flags) -Wl,-T $(filter %.lds %.o,$^) -o $@
 quiet_cmd_vdso64as = VDSO64A $@
       cmd_vdso64as = $(CC) $(a_flags) -c -o $@ $<
 

arch/s390/kernel/vmlinux.lds.S

@@ -154,14 +154,14 @@ SECTIONS
 	 * uncompressed image info used by the decompressor
 	 * it should match struct vmlinux_info
 	 */
-	.vmlinux.info 0 : {
+	.vmlinux.info 0 (INFO) : {
 		QUAD(_stext)					/* default_lma */
 		QUAD(startup_continue)				/* entry */
 		QUAD(__bss_start - _stext)			/* image_size */
 		QUAD(__bss_stop - __bss_start)			/* bss_size */
 		QUAD(__boot_data_start)				/* bootdata_off */
 		QUAD(__boot_data_end - __boot_data_start)	/* bootdata_size */
-	}
+	} :NONE
 
 	/* Debugging sections.	*/
 	STABS_DEBUG

arch/s390/mm/pgalloc.c

@@ -101,6 +101,7 @@ int crst_table_upgrade(struct mm_struct *mm, unsigned long end)
 			mm->context.asce_limit = _REGION1_SIZE;
 			mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH |
 				_ASCE_USER_BITS | _ASCE_TYPE_REGION2;
+			mm_inc_nr_puds(mm);
 		} else {
 			crst_table_init(table, _REGION1_ENTRY_EMPTY);
 			pgd_populate(mm, (pgd_t *) table, (p4d_t *) pgd);

arch/s390/numa/numa.c

@@ -53,6 +53,7 @@ int __node_distance(int a, int b)
 {
 	return mode->distance ? mode->distance(a, b) : 0;
 }
+EXPORT_SYMBOL(__node_distance);
 
 int numa_debug_enabled;
 

arch/um/drivers/ubd_kern.c

@@ -1305,6 +1305,7 @@ static int ubd_queue_one_vec(struct blk_mq_hw_ctx *hctx, struct request *req,
 		io_req->fds[0] = dev->cow.fd;
 	else
 		io_req->fds[0] = dev->fd;
+	io_req->error = 0;
 
 	if (req_op(req) == REQ_OP_FLUSH) {
 		io_req->op = UBD_FLUSH;
@@ -1313,9 +1314,7 @@ static int ubd_queue_one_vec(struct blk_mq_hw_ctx *hctx, struct request *req,
 		io_req->cow_offset = -1;
 		io_req->offset = off;
 		io_req->length = bvec->bv_len;
-		io_req->error = 0;
 		io_req->sector_mask = 0;
-
 		io_req->op = rq_data_dir(req) == READ ? UBD_READ : UBD_WRITE;
 		io_req->offsets[0] = 0;
 		io_req->offsets[1] = dev->cow.data_offset;
@@ -1341,11 +1340,14 @@ static int ubd_queue_one_vec(struct blk_mq_hw_ctx *hctx, struct request *req,
 static blk_status_t ubd_queue_rq(struct blk_mq_hw_ctx *hctx,
 				 const struct blk_mq_queue_data *bd)
 {
+	struct ubd *ubd_dev = hctx->queue->queuedata;
 	struct request *req = bd->rq;
 	int ret = 0;
 
 	blk_mq_start_request(req);
 
+	spin_lock_irq(&ubd_dev->lock);
+
 	if (req_op(req) == REQ_OP_FLUSH) {
 		ret = ubd_queue_one_vec(hctx, req, 0, NULL);
 	} else {
@@ -1361,9 +1363,11 @@ static blk_status_t ubd_queue_rq(struct blk_mq_hw_ctx *hctx,
 		}
 	}
 out:
-	if (ret < 0) {
+	spin_unlock_irq(&ubd_dev->lock);
+
+	if (ret < 0)
 		blk_mq_requeue_request(req, true);
-	}
+
 	return BLK_STS_OK;
 }
 

arch/x86/Kconfig

@@ -525,7 +525,6 @@ config X86_VSMP
 	bool "ScaleMP vSMP"
 	select HYPERVISOR_GUEST
 	select PARAVIRT
-	select PARAVIRT_XXL
 	depends on X86_64 && PCI
 	depends on X86_EXTENDED_PLATFORM
 	depends on SMP

arch/x86/Makefile

@@ -213,8 +213,6 @@ ifdef CONFIG_X86_64
 KBUILD_LDFLAGS += $(call ld-option, -z max-page-size=0x200000)
 endif
 
-# Speed up the build
-KBUILD_CFLAGS += -pipe
 # Workaround for a gcc prelease that unfortunately was shipped in a suse release
 KBUILD_CFLAGS += -Wno-sign-compare
 #
@@ -239,7 +237,7 @@ archheaders:
 archmacros:
 	$(Q)$(MAKE) $(build)=arch/x86/kernel arch/x86/kernel/macros.s
 
-ASM_MACRO_FLAGS = -Wa,arch/x86/kernel/macros.s -Wa,-
+ASM_MACRO_FLAGS = -Wa,arch/x86/kernel/macros.s
 export ASM_MACRO_FLAGS
 KBUILD_CFLAGS += $(ASM_MACRO_FLAGS)
 

arch/x86/events/intel/uncore.h

@@ -129,8 +129,15 @@ struct intel_uncore_box {
 	struct intel_uncore_extra_reg shared_regs[0];
 };
 
-#define UNCORE_BOX_FLAG_INITIATED	0
-#define UNCORE_BOX_FLAG_CTL_OFFS8	1 /* event config registers are 8-byte apart */
+/* CFL uncore 8th cbox MSRs */
+#define CFL_UNC_CBO_7_PERFEVTSEL0		0xf70
+#define CFL_UNC_CBO_7_PER_CTR0			0xf76
+
+#define UNCORE_BOX_FLAG_INITIATED		0
+/* event config registers are 8-byte apart */
+#define UNCORE_BOX_FLAG_CTL_OFFS8		1
+/* CFL 8th CBOX has different MSR space */
+#define UNCORE_BOX_FLAG_CFL8_CBOX_MSR_OFFS	2
 
 struct uncore_event_desc {
 	struct kobj_attribute attr;
@@ -297,17 +304,27 @@ unsigned int uncore_freerunning_counter(struct intel_uncore_box *box,
 static inline
 unsigned uncore_msr_event_ctl(struct intel_uncore_box *box, int idx)
 {
-	return box->pmu->type->event_ctl +
-		(box->pmu->type->pair_ctr_ctl ? 2 * idx : idx) +
-		uncore_msr_box_offset(box);
+	if (test_bit(UNCORE_BOX_FLAG_CFL8_CBOX_MSR_OFFS, &box->flags)) {
+		return CFL_UNC_CBO_7_PERFEVTSEL0 +
+		       (box->pmu->type->pair_ctr_ctl ? 2 * idx : idx);
+	} else {
+		return box->pmu->type->event_ctl +
+		       (box->pmu->type->pair_ctr_ctl ? 2 * idx : idx) +
+		       uncore_msr_box_offset(box);
+	}
 }
 
 static inline
 unsigned uncore_msr_perf_ctr(struct intel_uncore_box *box, int idx)
 {
-	return box->pmu->type->perf_ctr +
-		(box->pmu->type->pair_ctr_ctl ? 2 * idx : idx) +
-		uncore_msr_box_offset(box);
+	if (test_bit(UNCORE_BOX_FLAG_CFL8_CBOX_MSR_OFFS, &box->flags)) {
+		return CFL_UNC_CBO_7_PER_CTR0 +
+		       (box->pmu->type->pair_ctr_ctl ? 2 * idx : idx);
+	} else {
+		return box->pmu->type->perf_ctr +
+		       (box->pmu->type->pair_ctr_ctl ? 2 * idx : idx) +
+		       uncore_msr_box_offset(box);
+	}
 }
 
 static inline

arch/x86/events/intel/uncore_snb.c

@@ -15,6 +15,25 @@
 #define PCI_DEVICE_ID_INTEL_SKL_HQ_IMC	0x1910
 #define PCI_DEVICE_ID_INTEL_SKL_SD_IMC	0x190f
 #define PCI_DEVICE_ID_INTEL_SKL_SQ_IMC	0x191f
+#define PCI_DEVICE_ID_INTEL_KBL_Y_IMC	0x590c
+#define PCI_DEVICE_ID_INTEL_KBL_U_IMC	0x5904
+#define PCI_DEVICE_ID_INTEL_KBL_UQ_IMC	0x5914
+#define PCI_DEVICE_ID_INTEL_KBL_SD_IMC	0x590f
+#define PCI_DEVICE_ID_INTEL_KBL_SQ_IMC	0x591f
+#define PCI_DEVICE_ID_INTEL_CFL_2U_IMC	0x3ecc
+#define PCI_DEVICE_ID_INTEL_CFL_4U_IMC	0x3ed0
+#define PCI_DEVICE_ID_INTEL_CFL_4H_IMC	0x3e10
+#define PCI_DEVICE_ID_INTEL_CFL_6H_IMC	0x3ec4
+#define PCI_DEVICE_ID_INTEL_CFL_2S_D_IMC	0x3e0f
+#define PCI_DEVICE_ID_INTEL_CFL_4S_D_IMC	0x3e1f
+#define PCI_DEVICE_ID_INTEL_CFL_6S_D_IMC	0x3ec2
+#define PCI_DEVICE_ID_INTEL_CFL_8S_D_IMC	0x3e30
+#define PCI_DEVICE_ID_INTEL_CFL_4S_W_IMC	0x3e18
+#define PCI_DEVICE_ID_INTEL_CFL_6S_W_IMC	0x3ec6
+#define PCI_DEVICE_ID_INTEL_CFL_8S_W_IMC	0x3e31
+#define PCI_DEVICE_ID_INTEL_CFL_4S_S_IMC	0x3e33
+#define PCI_DEVICE_ID_INTEL_CFL_6S_S_IMC	0x3eca
+#define PCI_DEVICE_ID_INTEL_CFL_8S_S_IMC	0x3e32
 
 /* SNB event control */
 #define SNB_UNC_CTL_EV_SEL_MASK			0x000000ff
@@ -202,6 +221,10 @@ static void skl_uncore_msr_init_box(struct intel_uncore_box *box)
 		wrmsrl(SKL_UNC_PERF_GLOBAL_CTL,
 			SNB_UNC_GLOBAL_CTL_EN | SKL_UNC_GLOBAL_CTL_CORE_ALL);
 	}
+
+	/* The 8th CBOX has different MSR space */
+	if (box->pmu->pmu_idx == 7)
+		__set_bit(UNCORE_BOX_FLAG_CFL8_CBOX_MSR_OFFS, &box->flags);
 }
 
 static void skl_uncore_msr_enable_box(struct intel_uncore_box *box)
@@ -228,7 +251,7 @@ static struct intel_uncore_ops skl_uncore_msr_ops = {
 static struct intel_uncore_type skl_uncore_cbox = {
 	.name		= "cbox",
 	.num_counters   = 4,
-	.num_boxes	= 5,
+	.num_boxes	= 8,
 	.perf_ctr_bits	= 44,
 	.fixed_ctr_bits	= 48,
 	.perf_ctr	= SNB_UNC_CBO_0_PER_CTR0,
@@ -569,7 +592,82 @@ static const struct pci_device_id skl_uncore_pci_ids[] = {
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SKL_SQ_IMC),
 		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
 	},
-
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_KBL_Y_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_KBL_U_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_KBL_UQ_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_KBL_SD_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_KBL_SQ_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_2U_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_4U_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_4H_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_6H_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_2S_D_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_4S_D_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_6S_D_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_8S_D_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_4S_W_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_6S_W_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_8S_W_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_4S_S_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_6S_S_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_8S_S_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
 	{ /* end: all zeroes */ },
 };
 
@@ -618,6 +716,25 @@ static const struct imc_uncore_pci_dev desktop_imc_pci_ids[] = {
 	IMC_DEV(SKL_HQ_IMC, &skl_uncore_pci_driver),  /* 6th Gen Core H Quad Core */
 	IMC_DEV(SKL_SD_IMC, &skl_uncore_pci_driver),  /* 6th Gen Core S Dual Core */
 	IMC_DEV(SKL_SQ_IMC, &skl_uncore_pci_driver),  /* 6th Gen Core S Quad Core */
+	IMC_DEV(KBL_Y_IMC, &skl_uncore_pci_driver),  /* 7th Gen Core Y */
+	IMC_DEV(KBL_U_IMC, &skl_uncore_pci_driver),  /* 7th Gen Core U */
+	IMC_DEV(KBL_UQ_IMC, &skl_uncore_pci_driver),  /* 7th Gen Core U Quad Core */
+	IMC_DEV(KBL_SD_IMC, &skl_uncore_pci_driver),  /* 7th Gen Core S Dual Core */
+	IMC_DEV(KBL_SQ_IMC, &skl_uncore_pci_driver),  /* 7th Gen Core S Quad Core */
+	IMC_DEV(CFL_2U_IMC, &skl_uncore_pci_driver),  /* 8th Gen Core U 2 Cores */
+	IMC_DEV(CFL_4U_IMC, &skl_uncore_pci_driver),  /* 8th Gen Core U 4 Cores */
+	IMC_DEV(CFL_4H_IMC, &skl_uncore_pci_driver),  /* 8th Gen Core H 4 Cores */
+	IMC_DEV(CFL_6H_IMC, &skl_uncore_pci_driver),  /* 8th Gen Core H 6 Cores */
+	IMC_DEV(CFL_2S_D_IMC, &skl_uncore_pci_driver),  /* 8th Gen Core S 2 Cores Desktop */
+	IMC_DEV(CFL_4S_D_IMC, &skl_uncore_pci_driver),  /* 8th Gen Core S 4 Cores Desktop */
+	IMC_DEV(CFL_6S_D_IMC, &skl_uncore_pci_driver),  /* 8th Gen Core S 6 Cores Desktop */
+	IMC_DEV(CFL_8S_D_IMC, &skl_uncore_pci_driver),  /* 8th Gen Core S 8 Cores Desktop */
+	IMC_DEV(CFL_4S_W_IMC, &skl_uncore_pci_driver),  /* 8th Gen Core S 4 Cores Work Station */
+	IMC_DEV(CFL_6S_W_IMC, &skl_uncore_pci_driver),  /* 8th Gen Core S 6 Cores Work Station */
+	IMC_DEV(CFL_8S_W_IMC, &skl_uncore_pci_driver),  /* 8th Gen Core S 8 Cores Work Station */
+	IMC_DEV(CFL_4S_S_IMC, &skl_uncore_pci_driver),  /* 8th Gen Core S 4 Cores Server */
+	IMC_DEV(CFL_6S_S_IMC, &skl_uncore_pci_driver),  /* 8th Gen Core S 6 Cores Server */
+	IMC_DEV(CFL_8S_S_IMC, &skl_uncore_pci_driver),  /* 8th Gen Core S 8 Cores Server */
 	{  /* end marker */ }
 };
 

arch/x86/include/asm/mce.h

@@ -221,6 +221,8 @@ static inline void mce_hygon_feature_init(struct cpuinfo_x86 *c) { return mce_am
 
 int mce_available(struct cpuinfo_x86 *c);
 bool mce_is_memory_error(struct mce *m);
+bool mce_is_correctable(struct mce *m);
+int mce_usable_address(struct mce *m);
 
 DECLARE_PER_CPU(unsigned, mce_exception_count);
 DECLARE_PER_CPU(unsigned, mce_poll_count);

arch/x86/include/asm/mshyperv.h

@@ -232,7 +232,7 @@ static inline u64 hv_do_fast_hypercall16(u16 code, u64 input1, u64 input2)
 				      : "cc");
 	}
 #endif
-		return hv_status;
+	return hv_status;
 }
 
 /*

arch/x86/include/asm/page_64_types.h

@@ -33,12 +33,14 @@
 
 /*
  * Set __PAGE_OFFSET to the most negative possible address +
- * PGDIR_SIZE*16 (pgd slot 272).  The gap is to allow a space for a
- * hypervisor to fit.  Choosing 16 slots here is arbitrary, but it's
- * what Xen requires.
+ * PGDIR_SIZE*17 (pgd slot 273).
+ *
+ * The gap is to allow a space for LDT remap for PTI (1 pgd slot) and space for
+ * a hypervisor (16 slots). Choosing 16 slots for a hypervisor is arbitrary,
+ * but it's what Xen requires.
  */
-#define __PAGE_OFFSET_BASE_L5	_AC(0xff10000000000000, UL)
-#define __PAGE_OFFSET_BASE_L4	_AC(0xffff880000000000, UL)
+#define __PAGE_OFFSET_BASE_L5	_AC(0xff11000000000000, UL)
+#define __PAGE_OFFSET_BASE_L4	_AC(0xffff888000000000, UL)
 
 #ifdef CONFIG_DYNAMIC_MEMORY_LAYOUT
 #define __PAGE_OFFSET           page_offset_base

arch/x86/include/asm/pgtable_64_types.h

@@ -111,9 +111,7 @@ extern unsigned int ptrs_per_p4d;
  */
 #define MAXMEM			(1UL << MAX_PHYSMEM_BITS)
 
-#define LDT_PGD_ENTRY_L4	-3UL
-#define LDT_PGD_ENTRY_L5	-112UL
-#define LDT_PGD_ENTRY		(pgtable_l5_enabled() ? LDT_PGD_ENTRY_L5 : LDT_PGD_ENTRY_L4)
+#define LDT_PGD_ENTRY		-240UL
 #define LDT_BASE_ADDR		(LDT_PGD_ENTRY << PGDIR_SHIFT)
 #define LDT_END_ADDR		(LDT_BASE_ADDR + PGDIR_SIZE)
 

arch/x86/include/asm/qspinlock.h

@@ -13,12 +13,15 @@
 #define queued_fetch_set_pending_acquire queued_fetch_set_pending_acquire
 static __always_inline u32 queued_fetch_set_pending_acquire(struct qspinlock *lock)
 {
-	u32 val = 0;
-
-	if (GEN_BINARY_RMWcc(LOCK_PREFIX "btsl", lock->val.counter, c,
-			     "I", _Q_PENDING_OFFSET))
-		val |= _Q_PENDING_VAL;
+	u32 val;
 
+	/*
+	 * We can't use GEN_BINARY_RMWcc() inside an if() stmt because asm goto
+	 * and CONFIG_PROFILE_ALL_BRANCHES=y results in a label inside a
+	 * statement expression, which GCC doesn't like.
+	 */
+	val = GEN_BINARY_RMWcc(LOCK_PREFIX "btsl", lock->val.counter, c,
+			       "I", _Q_PENDING_OFFSET) * _Q_PENDING_VAL;
 	val |= atomic_read(&lock->val) & ~_Q_PENDING_MASK;
 
 	return val;

arch/x86/include/asm/xen/page.h

@@ -9,7 +9,7 @@
 #include <linux/mm.h>
 #include <linux/device.h>
 
-#include <linux/uaccess.h>
+#include <asm/extable.h>
 #include <asm/page.h>
 #include <asm/pgtable.h>
 
@@ -93,12 +93,39 @@ clear_foreign_p2m_mapping(struct gnttab_unmap_grant_ref *unmap_ops,
  */
 static inline int xen_safe_write_ulong(unsigned long *addr, unsigned long val)
 {
-	return __put_user(val, (unsigned long __user *)addr);
+	int ret = 0;
+
+	asm volatile("1: mov %[val], %[ptr]\n"
+		     "2:\n"
+		     ".section .fixup, \"ax\"\n"
+		     "3: sub $1, %[ret]\n"
+		     "   jmp 2b\n"
+		     ".previous\n"
+		     _ASM_EXTABLE(1b, 3b)
+		     : [ret] "+r" (ret), [ptr] "=m" (*addr)
+		     : [val] "r" (val));
+
+	return ret;
 }
 
-static inline int xen_safe_read_ulong(unsigned long *addr, unsigned long *val)
+static inline int xen_safe_read_ulong(const unsigned long *addr,
+				      unsigned long *val)
 {
-	return __get_user(*val, (unsigned long __user *)addr);
+	int ret = 0;
+	unsigned long rval = ~0ul;
+
+	asm volatile("1: mov %[ptr], %[rval]\n"
+		     "2:\n"
+		     ".section .fixup, \"ax\"\n"
+		     "3: sub $1, %[ret]\n"
+		     "   jmp 2b\n"
+		     ".previous\n"
+		     _ASM_EXTABLE(1b, 3b)
+		     : [ret] "+r" (ret), [rval] "+r" (rval)
+		     : [ptr] "m" (*addr));
+	*val = rval;
+
+	return ret;
 }
 
 #ifdef CONFIG_XEN_PV

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

@@ -485,7 +485,7 @@ static void mce_report_event(struct pt_regs *regs)
  * be somewhat complicated (e.g. segment offset would require an instruction
  * parser). So only support physical addresses up to page granuality for now.
  */
-static int mce_usable_address(struct mce *m)
+int mce_usable_address(struct mce *m)
 {
 	if (!(m->status & MCI_STATUS_ADDRV))
 		return 0;
@@ -505,6 +505,7 @@ static int mce_usable_address(struct mce *m)
 
 	return 1;
 }
+EXPORT_SYMBOL_GPL(mce_usable_address);
 
 bool mce_is_memory_error(struct mce *m)
 {
@@ -534,7 +535,7 @@ bool mce_is_memory_error(struct mce *m)
 }
 EXPORT_SYMBOL_GPL(mce_is_memory_error);
 
-static bool mce_is_correctable(struct mce *m)
+bool mce_is_correctable(struct mce *m)
 {
 	if (m->cpuvendor == X86_VENDOR_AMD && m->status & MCI_STATUS_DEFERRED)
 		return false;
@@ -547,6 +548,7 @@ static bool mce_is_correctable(struct mce *m)
 
 	return true;
 }
+EXPORT_SYMBOL_GPL(mce_is_correctable);
 
 static bool cec_add_mce(struct mce *m)
 {

arch/x86/kernel/cpu/mshyperv.c

@@ -20,6 +20,7 @@
 #include <linux/interrupt.h>
 #include <linux/irq.h>
 #include <linux/kexec.h>
+#include <linux/i8253.h>
 #include <asm/processor.h>
 #include <asm/hypervisor.h>
 #include <asm/hyperv-tlfs.h>
@@ -295,6 +296,16 @@ static void __init ms_hyperv_init_platform(void)
 	if (efi_enabled(EFI_BOOT))
 		x86_platform.get_nmi_reason = hv_get_nmi_reason;
 
+	/*
+	 * Hyper-V VMs have a PIT emulation quirk such that zeroing the
+	 * counter register during PIT shutdown restarts the PIT. So it
+	 * continues to interrupt @18.2 HZ. Setting i8253_clear_counter
+	 * to false tells pit_shutdown() not to zero the counter so that
+	 * the PIT really is shutdown. Generation 2 VMs don't have a PIT,
+	 * and setting this value has no effect.
+	 */
+	i8253_clear_counter_on_shutdown = false;
+
 #if IS_ENABLED(CONFIG_HYPERV)
 	/*
 	 * Setup the hook to get control post apic initialization.

arch/x86/kernel/cpu/vmware.c

@@ -77,7 +77,7 @@ static __init int setup_vmw_sched_clock(char *s)
 }
 early_param("no-vmw-sched-clock", setup_vmw_sched_clock);
 
-static unsigned long long vmware_sched_clock(void)
+static unsigned long long notrace vmware_sched_clock(void)
 {
 	unsigned long long ns;
 

arch/x86/kernel/ldt.c

@@ -199,14 +199,6 @@ static void sanity_check_ldt_mapping(struct mm_struct *mm)
 /*
  * If PTI is enabled, this maps the LDT into the kernelmode and
  * usermode tables for the given mm.
- *
- * There is no corresponding unmap function.  Even if the LDT is freed, we
- * leave the PTEs around until the slot is reused or the mm is destroyed.
- * This is harmless: the LDT is always in ordinary memory, and no one will
- * access the freed slot.
- *
- * If we wanted to unmap freed LDTs, we'd also need to do a flush to make
- * it useful, and the flush would slow down modify_ldt().
  */
 static int
 map_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt, int slot)
@@ -214,8 +206,7 @@ map_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt, int slot)
 	unsigned long va;
 	bool is_vmalloc;
 	spinlock_t *ptl;
-	pgd_t *pgd;
-	int i;
+	int i, nr_pages;
 
 	if (!static_cpu_has(X86_FEATURE_PTI))
 		return 0;
@@ -229,16 +220,11 @@ map_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt, int slot)
 	/* Check if the current mappings are sane */
 	sanity_check_ldt_mapping(mm);
 
-	/*
-	 * Did we already have the top level entry allocated?  We can't
-	 * use pgd_none() for this because it doens't do anything on
-	 * 4-level page table kernels.
-	 */
-	pgd = pgd_offset(mm, LDT_BASE_ADDR);
-
 	is_vmalloc = is_vmalloc_addr(ldt->entries);
 
-	for (i = 0; i * PAGE_SIZE < ldt->nr_entries * LDT_ENTRY_SIZE; i++) {
+	nr_pages = DIV_ROUND_UP(ldt->nr_entries * LDT_ENTRY_SIZE, PAGE_SIZE);
+
+	for (i = 0; i < nr_pages; i++) {
 		unsigned long offset = i << PAGE_SHIFT;
 		const void *src = (char *)ldt->entries + offset;
 		unsigned long pfn;
@@ -272,13 +258,39 @@ map_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt, int slot)
 	/* Propagate LDT mapping to the user page-table */
 	map_ldt_struct_to_user(mm);
 
-	va = (unsigned long)ldt_slot_va(slot);
-	flush_tlb_mm_range(mm, va, va + LDT_SLOT_STRIDE, PAGE_SHIFT, false);
-
 	ldt->slot = slot;
 	return 0;
 }
 
+static void unmap_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt)
+{
+	unsigned long va;
+	int i, nr_pages;
+
+	if (!ldt)
+		return;
+
+	/* LDT map/unmap is only required for PTI */
+	if (!static_cpu_has(X86_FEATURE_PTI))
+		return;
+
+	nr_pages = DIV_ROUND_UP(ldt->nr_entries * LDT_ENTRY_SIZE, PAGE_SIZE);
+
+	for (i = 0; i < nr_pages; i++) {
+		unsigned long offset = i << PAGE_SHIFT;
+		spinlock_t *ptl;
+		pte_t *ptep;
+
+		va = (unsigned long)ldt_slot_va(ldt->slot) + offset;
+		ptep = get_locked_pte(mm, va, &ptl);
+		pte_clear(mm, va, ptep);
+		pte_unmap_unlock(ptep, ptl);
+	}
+
+	va = (unsigned long)ldt_slot_va(ldt->slot);
+	flush_tlb_mm_range(mm, va, va + nr_pages * PAGE_SIZE, PAGE_SHIFT, false);
+}
+
 #else /* !CONFIG_PAGE_TABLE_ISOLATION */
 
 static int
@@ -286,6 +298,10 @@ map_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt, int slot)
 {
 	return 0;
 }
+
+static void unmap_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt)
+{
+}
 #endif /* CONFIG_PAGE_TABLE_ISOLATION */
 
 static void free_ldt_pgtables(struct mm_struct *mm)
@@ -524,6 +540,7 @@ static int write_ldt(void __user *ptr, unsigned long bytecount, int oldmode)
 	}
 
 	install_ldt(mm, new_ldt);
+	unmap_ldt_struct(mm, old_ldt);
 	free_ldt_struct(old_ldt);
 	error = 0;
 

arch/x86/kernel/vsmp_64.c

@@ -26,65 +26,8 @@
 
 #define TOPOLOGY_REGISTER_OFFSET 0x10
 
-#if defined CONFIG_PCI && defined CONFIG_PARAVIRT_XXL
-/*
- * Interrupt control on vSMPowered systems:
- * ~AC is a shadow of IF.  If IF is 'on' AC should be 'off'
- * and vice versa.
- */
-
-asmlinkage __visible unsigned long vsmp_save_fl(void)
-{
-	unsigned long flags = native_save_fl();
-
-	if (!(flags & X86_EFLAGS_IF) || (flags & X86_EFLAGS_AC))
-		flags &= ~X86_EFLAGS_IF;
-	return flags;
-}
-PV_CALLEE_SAVE_REGS_THUNK(vsmp_save_fl);
-
-__visible void vsmp_restore_fl(unsigned long flags)
-{
-	if (flags & X86_EFLAGS_IF)
-		flags &= ~X86_EFLAGS_AC;
-	else
-		flags |= X86_EFLAGS_AC;
-	native_restore_fl(flags);
-}
-PV_CALLEE_SAVE_REGS_THUNK(vsmp_restore_fl);
-
-asmlinkage __visible void vsmp_irq_disable(void)
-{
-	unsigned long flags = native_save_fl();
-
-	native_restore_fl((flags & ~X86_EFLAGS_IF) | X86_EFLAGS_AC);
-}
-PV_CALLEE_SAVE_REGS_THUNK(vsmp_irq_disable);
-
-asmlinkage __visible void vsmp_irq_enable(void)
-{
-	unsigned long flags = native_save_fl();
-
-	native_restore_fl((flags | X86_EFLAGS_IF) & (~X86_EFLAGS_AC));
-}
-PV_CALLEE_SAVE_REGS_THUNK(vsmp_irq_enable);
-
-static unsigned __init vsmp_patch(u8 type, void *ibuf,
-				  unsigned long addr, unsigned len)
-{
-	switch (type) {
-	case PARAVIRT_PATCH(irq.irq_enable):
-	case PARAVIRT_PATCH(irq.irq_disable):
-	case PARAVIRT_PATCH(irq.save_fl):
-	case PARAVIRT_PATCH(irq.restore_fl):
-		return paravirt_patch_default(type, ibuf, addr, len);
-	default:
-		return native_patch(type, ibuf, addr, len);
-	}
-
-}
-
-static void __init set_vsmp_pv_ops(void)
+#ifdef CONFIG_PCI
+static void __init set_vsmp_ctl(void)
 {
 	void __iomem *address;
 	unsigned int cap, ctl, cfg;
@@ -109,28 +52,12 @@ static void __init set_vsmp_pv_ops(void)
 	}
 #endif
 
-	if (cap & ctl & (1 << 4)) {
-		/* Setup irq ops and turn on vSMP  IRQ fastpath handling */
-		pv_ops.irq.irq_disable = PV_CALLEE_SAVE(vsmp_irq_disable);
-		pv_ops.irq.irq_enable = PV_CALLEE_SAVE(vsmp_irq_enable);
-		pv_ops.irq.save_fl = PV_CALLEE_SAVE(vsmp_save_fl);
-		pv_ops.irq.restore_fl = PV_CALLEE_SAVE(vsmp_restore_fl);
-		pv_ops.init.patch = vsmp_patch;
-		ctl &= ~(1 << 4);
-	}
 	writel(ctl, address + 4);
 	ctl = readl(address + 4);
 	pr_info("vSMP CTL: control set to:0x%08x\n", ctl);
 
 	early_iounmap(address, 8);
 }
-#else
-static void __init set_vsmp_pv_ops(void)
-{
-}
-#endif
-
-#ifdef CONFIG_PCI
 static int is_vsmp = -1;
 
 static void __init detect_vsmp_box(void)
@@ -164,11 +91,14 @@ static int is_vsmp_box(void)
 {
 	return 0;
 }
+static void __init set_vsmp_ctl(void)
+{
+}
 #endif
 
 static void __init vsmp_cap_cpus(void)
 {
-#if !defined(CONFIG_X86_VSMP) && defined(CONFIG_SMP)
+#if !defined(CONFIG_X86_VSMP) && defined(CONFIG_SMP) && defined(CONFIG_PCI)
 	void __iomem *address;
 	unsigned int cfg, topology, node_shift, maxcpus;
 
@@ -221,6 +151,6 @@ void __init vsmp_init(void)
 
 	vsmp_cap_cpus();
 
-	set_vsmp_pv_ops();
+	set_vsmp_ctl();
 	return;
 }

arch/x86/xen/mmu_pv.c

@@ -1905,7 +1905,7 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn)
 	init_top_pgt[0] = __pgd(0);
 
 	/* Pre-constructed entries are in pfn, so convert to mfn */
-	/* L4[272] -> level3_ident_pgt  */
+	/* L4[273] -> level3_ident_pgt  */
 	/* L4[511] -> level3_kernel_pgt */
 	convert_pfn_mfn(init_top_pgt);
 
@@ -1925,8 +1925,8 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn)
 	addr[0] = (unsigned long)pgd;
 	addr[1] = (unsigned long)l3;
 	addr[2] = (unsigned long)l2;
-	/* Graft it onto L4[272][0]. Note that we creating an aliasing problem:
-	 * Both L4[272][0] and L4[511][510] have entries that point to the same
+	/* Graft it onto L4[273][0]. Note that we creating an aliasing problem:
+	 * Both L4[273][0] and L4[511][510] have entries that point to the same
 	 * L2 (PMD) tables. Meaning that if you modify it in __va space
 	 * it will be also modified in the __ka space! (But if you just
 	 * modify the PMD table to point to other PTE's or none, then you

arch/x86/xen/p2m.c

@@ -656,8 +656,7 @@ bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn)
 
 	/*
 	 * The interface requires atomic updates on p2m elements.
-	 * xen_safe_write_ulong() is using __put_user which does an atomic
-	 * store via asm().
+	 * xen_safe_write_ulong() is using an atomic store via asm().
 	 */
 	if (likely(!xen_safe_write_ulong(xen_p2m_addr + pfn, mfn)))
 		return true;

arch/x86/xen/spinlock.c

@@ -9,6 +9,7 @@
 #include <linux/log2.h>
 #include <linux/gfp.h>
 #include <linux/slab.h>
+#include <linux/atomic.h>
 
 #include <asm/paravirt.h>
 #include <asm/qspinlock.h>
@@ -21,6 +22,7 @@
 
 static DEFINE_PER_CPU(int, lock_kicker_irq) = -1;
 static DEFINE_PER_CPU(char *, irq_name);
+static DEFINE_PER_CPU(atomic_t, xen_qlock_wait_nest);
 static bool xen_pvspin = true;
 
 static void xen_qlock_kick(int cpu)
@@ -39,25 +41,25 @@ static void xen_qlock_kick(int cpu)
  */
 static void xen_qlock_wait(u8 *byte, u8 val)
 {
-	unsigned long flags;
 	int irq = __this_cpu_read(lock_kicker_irq);
+	atomic_t *nest_cnt = this_cpu_ptr(&xen_qlock_wait_nest);
 
 	/* If kicker interrupts not initialized yet, just spin */
 	if (irq == -1 || in_nmi())
 		return;
 
-	/* Guard against reentry. */
-	local_irq_save(flags);
+	/* Detect reentry. */
+	atomic_inc(nest_cnt);
 
-	/* If irq pending already clear it. */
-	if (xen_test_irq_pending(irq)) {
+	/* If irq pending already and no nested call clear it. */
+	if (atomic_read(nest_cnt) == 1 && xen_test_irq_pending(irq)) {
 		xen_clear_irq_pending(irq);
 	} else if (READ_ONCE(*byte) == val) {
 		/* Block until irq becomes pending (or a spurious wakeup) */
 		xen_poll_irq(irq);
 	}
 
-	local_irq_restore(flags);
+	atomic_dec(nest_cnt);
 }
 
 static irqreturn_t dummy_handler(int irq, void *dev_id)

arch/xtensa/include/asm/processor.h

@@ -23,7 +23,11 @@
 # error Linux requires the Xtensa Windowed Registers Option.
 #endif
 
-#define ARCH_SLAB_MINALIGN	XCHAL_DATA_WIDTH
+/* Xtensa ABI requires stack alignment to be at least 16 */
+
+#define STACK_ALIGN (XCHAL_DATA_WIDTH > 16 ? XCHAL_DATA_WIDTH : 16)
+
+#define ARCH_SLAB_MINALIGN STACK_ALIGN
 
 /*
  * User space process size: 1 GB.

arch/xtensa/kernel/head.S

@@ -88,9 +88,12 @@ _SetupMMU:
 	initialize_mmu
 #if defined(CONFIG_MMU) && XCHAL_HAVE_PTP_MMU && XCHAL_HAVE_SPANNING_WAY
 	rsr	a2, excsave1
-	movi	a3, 0x08000000
+	movi	a3, XCHAL_KSEG_PADDR
+	bltu	a2, a3, 1f
+	sub	a2, a2, a3
+	movi	a3, XCHAL_KSEG_SIZE
 	bgeu	a2, a3, 1f
-	movi	a3, 0xd0000000
+	movi	a3, XCHAL_KSEG_CACHED_VADDR
 	add	a2, a2, a3
 	wsr	a2, excsave1
 1:

block/bio.c

@@ -605,6 +605,7 @@ void __bio_clone_fast(struct bio *bio, struct bio *bio_src)
 	if (bio_flagged(bio_src, BIO_THROTTLED))
 		bio_set_flag(bio, BIO_THROTTLED);
 	bio->bi_opf = bio_src->bi_opf;
+	bio->bi_ioprio = bio_src->bi_ioprio;
 	bio->bi_write_hint = bio_src->bi_write_hint;
 	bio->bi_iter = bio_src->bi_iter;
 	bio->bi_io_vec = bio_src->bi_io_vec;
@@ -1260,6 +1261,7 @@ struct bio *bio_copy_user_iov(struct request_queue *q,
 		if (ret)
 			goto cleanup;
 	} else {
+		zero_fill_bio(bio);
 		iov_iter_advance(iter, bio->bi_iter.bi_size);
 	}
 

block/blk-core.c

@@ -352,9 +352,8 @@ void blk_cleanup_queue(struct request_queue *q)
 	 * dispatch may still be in-progress since we dispatch requests
 	 * from more than one contexts.
 	 *
-	 * No need to quiesce queue if it isn't initialized yet since
-	 * blk_freeze_queue() should be enough for cases of passthrough
-	 * request.
+	 * We rely on driver to deal with the race in case that queue
+	 * initialization isn't done.
 	 */
 	if (queue_is_mq(q) && blk_queue_init_done(q))
 		blk_mq_quiesce_queue(q);

block/blk-lib.c

@@ -51,16 +51,14 @@ int __blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 	if ((sector | nr_sects) & bs_mask)
 		return -EINVAL;
 
-	while (nr_sects) {
-		unsigned int req_sects = nr_sects;
-		sector_t end_sect;
+	if (!nr_sects)
+		return -EINVAL;
 
-		if (!req_sects)
-			goto fail;
-		if (req_sects > UINT_MAX >> 9)
-			req_sects = UINT_MAX >> 9;
+	while (nr_sects) {
+		sector_t req_sects = min_t(sector_t, nr_sects,
+				bio_allowed_max_sectors(q));
 
-		end_sect = sector + req_sects;
+		WARN_ON_ONCE((req_sects << 9) > UINT_MAX);
 
 		bio = blk_next_bio(bio, 0, gfp_mask);
 		bio->bi_iter.bi_sector = sector;
@@ -68,8 +66,8 @@ int __blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 		bio_set_op_attrs(bio, op, 0);
 
 		bio->bi_iter.bi_size = req_sects << 9;
+		sector += req_sects;
 		nr_sects -= req_sects;
-		sector = end_sect;
 
 		/*
 		 * We can loop for a long time in here, if someone does
@@ -82,14 +80,6 @@ int __blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 
 	*biop = bio;
 	return 0;
-
-fail:
-	if (bio) {
-		submit_bio_wait(bio);
-		bio_put(bio);
-	}
-	*biop = NULL;
-	return -EOPNOTSUPP;
 }
 EXPORT_SYMBOL(__blkdev_issue_discard);
 
@@ -161,7 +151,7 @@ static int __blkdev_issue_write_same(struct block_device *bdev, sector_t sector,
 		return -EOPNOTSUPP;
 
 	/* Ensure that max_write_same_sectors doesn't overflow bi_size */
-	max_write_same_sectors = UINT_MAX >> 9;
+	max_write_same_sectors = bio_allowed_max_sectors(q);
 
 	while (nr_sects) {
 		bio = blk_next_bio(bio, 1, gfp_mask);

block/blk-merge.c

@@ -46,7 +46,7 @@ static inline bool bio_will_gap(struct request_queue *q,
 		bio_get_first_bvec(prev_rq->bio, &pb);
 	else
 		bio_get_first_bvec(prev, &pb);
-	if (pb.bv_offset)
+	if (pb.bv_offset & queue_virt_boundary(q))
 		return true;
 
 	/*
@@ -90,7 +90,8 @@ static struct bio *blk_bio_discard_split(struct request_queue *q,
 	/* Zero-sector (unknown) and one-sector granularities are the same.  */
 	granularity = max(q->limits.discard_granularity >> 9, 1U);
 
-	max_discard_sectors = min(q->limits.max_discard_sectors, UINT_MAX >> 9);
+	max_discard_sectors = min(q->limits.max_discard_sectors,
+			bio_allowed_max_sectors(q));
 	max_discard_sectors -= max_discard_sectors % granularity;
 
 	if (unlikely(!max_discard_sectors)) {

block/blk.h

@@ -85,7 +85,7 @@ static inline bool biovec_phys_mergeable(struct request_queue *q,
 static inline bool __bvec_gap_to_prev(struct request_queue *q,
 		struct bio_vec *bprv, unsigned int offset)
 {
-	return offset ||
+	return (offset & queue_virt_boundary(q)) ||
 		((bprv->bv_offset + bprv->bv_len) & queue_virt_boundary(q));
 }
 
@@ -233,6 +233,16 @@ static inline void req_set_nomerge(struct request_queue *q, struct request *req)
 		q->last_merge = NULL;
 }
 
+/*
+ * The max size one bio can handle is UINT_MAX becasue bvec_iter.bi_size
+ * is defined as 'unsigned int', meantime it has to aligned to with logical
+ * block size which is the minimum accepted unit by hardware.
+ */
+static inline unsigned int bio_allowed_max_sectors(struct request_queue *q)
+{
+	return round_down(UINT_MAX, queue_logical_block_size(q)) >> 9;
+}
+
 /*
  * Internal io_context interface
  */

block/bounce.c

@@ -248,6 +248,7 @@ static struct bio *bounce_clone_bio(struct bio *bio_src, gfp_t gfp_mask,
 		return NULL;
 	bio->bi_disk		= bio_src->bi_disk;
 	bio->bi_opf		= bio_src->bi_opf;
+	bio->bi_ioprio		= bio_src->bi_ioprio;
 	bio->bi_write_hint	= bio_src->bi_write_hint;
 	bio->bi_iter.bi_sector	= bio_src->bi_iter.bi_sector;
 	bio->bi_iter.bi_size	= bio_src->bi_iter.bi_size;

crypto/crypto_user_base.c

@@ -84,7 +84,7 @@ static int crypto_report_cipher(struct sk_buff *skb, struct crypto_alg *alg)
 {
 	struct crypto_report_cipher rcipher;
 
-	strlcpy(rcipher.type, "cipher", sizeof(rcipher.type));
+	strncpy(rcipher.type, "cipher", sizeof(rcipher.type));
 
 	rcipher.blocksize = alg->cra_blocksize;
 	rcipher.min_keysize = alg->cra_cipher.cia_min_keysize;
@@ -103,7 +103,7 @@ static int crypto_report_comp(struct sk_buff *skb, struct crypto_alg *alg)
 {
 	struct crypto_report_comp rcomp;
 
-	strlcpy(rcomp.type, "compression", sizeof(rcomp.type));
+	strncpy(rcomp.type, "compression", sizeof(rcomp.type));
 	if (nla_put(skb, CRYPTOCFGA_REPORT_COMPRESS,
 		    sizeof(struct crypto_report_comp), &rcomp))
 		goto nla_put_failure;
@@ -117,7 +117,7 @@ static int crypto_report_acomp(struct sk_buff *skb, struct crypto_alg *alg)
 {
 	struct crypto_report_acomp racomp;
 
-	strlcpy(racomp.type, "acomp", sizeof(racomp.type));
+	strncpy(racomp.type, "acomp", sizeof(racomp.type));
 
 	if (nla_put(skb, CRYPTOCFGA_REPORT_ACOMP,
 		    sizeof(struct crypto_report_acomp), &racomp))
@@ -132,7 +132,7 @@ static int crypto_report_akcipher(struct sk_buff *skb, struct crypto_alg *alg)
 {
 	struct crypto_report_akcipher rakcipher;
 
-	strlcpy(rakcipher.type, "akcipher", sizeof(rakcipher.type));
+	strncpy(rakcipher.type, "akcipher", sizeof(rakcipher.type));
 
 	if (nla_put(skb, CRYPTOCFGA_REPORT_AKCIPHER,
 		    sizeof(struct crypto_report_akcipher), &rakcipher))
@@ -147,7 +147,7 @@ static int crypto_report_kpp(struct sk_buff *skb, struct crypto_alg *alg)
 {
 	struct crypto_report_kpp rkpp;
 
-	strlcpy(rkpp.type, "kpp", sizeof(rkpp.type));
+	strncpy(rkpp.type, "kpp", sizeof(rkpp.type));
 
 	if (nla_put(skb, CRYPTOCFGA_REPORT_KPP,
 		    sizeof(struct crypto_report_kpp), &rkpp))
@@ -161,10 +161,10 @@ static int crypto_report_kpp(struct sk_buff *skb, struct crypto_alg *alg)
 static int crypto_report_one(struct crypto_alg *alg,
 			     struct crypto_user_alg *ualg, struct sk_buff *skb)
 {
-	strlcpy(ualg->cru_name, alg->cra_name, sizeof(ualg->cru_name));
-	strlcpy(ualg->cru_driver_name, alg->cra_driver_name,
+	strncpy(ualg->cru_name, alg->cra_name, sizeof(ualg->cru_name));
+	strncpy(ualg->cru_driver_name, alg->cra_driver_name,
 		sizeof(ualg->cru_driver_name));
-	strlcpy(ualg->cru_module_name, module_name(alg->cra_module),
+	strncpy(ualg->cru_module_name, module_name(alg->cra_module),
 		sizeof(ualg->cru_module_name));
 
 	ualg->cru_type = 0;
@@ -177,7 +177,7 @@ static int crypto_report_one(struct crypto_alg *alg,
 	if (alg->cra_flags & CRYPTO_ALG_LARVAL) {
 		struct crypto_report_larval rl;
 
-		strlcpy(rl.type, "larval", sizeof(rl.type));
+		strncpy(rl.type, "larval", sizeof(rl.type));
 		if (nla_put(skb, CRYPTOCFGA_REPORT_LARVAL,
 			    sizeof(struct crypto_report_larval), &rl))
 			goto nla_put_failure;

crypto/crypto_user_stat.c

@@ -37,6 +37,8 @@ static int crypto_report_aead(struct sk_buff *skb, struct crypto_alg *alg)
 	u64 v64;
 	u32 v32;
 
+	memset(&raead, 0, sizeof(raead));
+
 	strncpy(raead.type, "aead", sizeof(raead.type));
 
 	v32 = atomic_read(&alg->encrypt_cnt);
@@ -65,6 +67,8 @@ static int crypto_report_cipher(struct sk_buff *skb, struct crypto_alg *alg)
 	u64 v64;
 	u32 v32;
 
+	memset(&rcipher, 0, sizeof(rcipher));
+
 	strlcpy(rcipher.type, "cipher", sizeof(rcipher.type));
 
 	v32 = atomic_read(&alg->encrypt_cnt);
@@ -93,6 +97,8 @@ static int crypto_report_comp(struct sk_buff *skb, struct crypto_alg *alg)
 	u64 v64;
 	u32 v32;
 
+	memset(&rcomp, 0, sizeof(rcomp));
+
 	strlcpy(rcomp.type, "compression", sizeof(rcomp.type));
 	v32 = atomic_read(&alg->compress_cnt);
 	rcomp.stat_compress_cnt = v32;
@@ -120,6 +126,8 @@ static int crypto_report_acomp(struct sk_buff *skb, struct crypto_alg *alg)
 	u64 v64;
 	u32 v32;
 
+	memset(&racomp, 0, sizeof(racomp));
+
 	strlcpy(racomp.type, "acomp", sizeof(racomp.type));
 	v32 = atomic_read(&alg->compress_cnt);
 	racomp.stat_compress_cnt = v32;
@@ -147,6 +155,8 @@ static int crypto_report_akcipher(struct sk_buff *skb, struct crypto_alg *alg)
 	u64 v64;
 	u32 v32;
 
+	memset(&rakcipher, 0, sizeof(rakcipher));
+
 	strncpy(rakcipher.type, "akcipher", sizeof(rakcipher.type));
 	v32 = atomic_read(&alg->encrypt_cnt);
 	rakcipher.stat_encrypt_cnt = v32;
@@ -177,6 +187,8 @@ static int crypto_report_kpp(struct sk_buff *skb, struct crypto_alg *alg)
 	struct crypto_stat rkpp;
 	u32 v;
 
+	memset(&rkpp, 0, sizeof(rkpp));
+
 	strlcpy(rkpp.type, "kpp", sizeof(rkpp.type));
 
 	v = atomic_read(&alg->setsecret_cnt);
@@ -203,6 +215,8 @@ static int crypto_report_ahash(struct sk_buff *skb, struct crypto_alg *alg)
 	u64 v64;
 	u32 v32;
 
+	memset(&rhash, 0, sizeof(rhash));
+
 	strncpy(rhash.type, "ahash", sizeof(rhash.type));
 
 	v32 = atomic_read(&alg->hash_cnt);
@@ -227,6 +241,8 @@ static int crypto_report_shash(struct sk_buff *skb, struct crypto_alg *alg)
 	u64 v64;
 	u32 v32;
 
+	memset(&rhash, 0, sizeof(rhash));
+
 	strncpy(rhash.type, "shash", sizeof(rhash.type));
 
 	v32 = atomic_read(&alg->hash_cnt);
@@ -251,6 +267,8 @@ static int crypto_report_rng(struct sk_buff *skb, struct crypto_alg *alg)
 	u64 v64;
 	u32 v32;
 
+	memset(&rrng, 0, sizeof(rrng));
+
 	strncpy(rrng.type, "rng", sizeof(rrng.type));
 
 	v32 = atomic_read(&alg->generate_cnt);
@@ -275,6 +293,8 @@ static int crypto_reportstat_one(struct crypto_alg *alg,
 				 struct crypto_user_alg *ualg,
 				 struct sk_buff *skb)
 {
+	memset(ualg, 0, sizeof(*ualg));
+
 	strlcpy(ualg->cru_name, alg->cra_name, sizeof(ualg->cru_name));
 	strlcpy(ualg->cru_driver_name, alg->cra_driver_name,
 		sizeof(ualg->cru_driver_name));
@@ -291,6 +311,7 @@ static int crypto_reportstat_one(struct crypto_alg *alg,
 	if (alg->cra_flags & CRYPTO_ALG_LARVAL) {
 		struct crypto_stat rl;
 
+		memset(&rl, 0, sizeof(rl));
 		strlcpy(rl.type, "larval", sizeof(rl.type));
 		if (nla_put(skb, CRYPTOCFGA_STAT_LARVAL,
 			    sizeof(struct crypto_stat), &rl))