Re: Linux 4.8.12

[Greg KH <gregkh@linuxfoundation.org>]

diff --git a/Makefile b/Makefile
index 2b1bcbacebcd..7b0c92f53169 100644
--- a/Makefile
+++ b/Makefile
@@ -1,6 +1,6 @@
 VERSION = 4
 PATCHLEVEL = 8
-SUBLEVEL = 11
+SUBLEVEL = 12
 EXTRAVERSION =
 NAME = Psychotic Stoned Sheep
 
diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig
index af12c2db9bb8..81c11a62b1fa 100644
--- a/arch/parisc/Kconfig
+++ b/arch/parisc/Kconfig
@@ -33,7 +33,9 @@ config PARISC
 	select HAVE_ARCH_HASH
 	select HAVE_ARCH_SECCOMP_FILTER
 	select HAVE_ARCH_TRACEHOOK
-	select HAVE_UNSTABLE_SCHED_CLOCK if (SMP || !64BIT)
+	select GENERIC_SCHED_CLOCK
+	select HAVE_UNSTABLE_SCHED_CLOCK if SMP
+	select GENERIC_CLOCKEVENTS
 	select ARCH_NO_COHERENT_DMA_MMAP
 	select CPU_NO_EFFICIENT_FFS
 
diff --git a/arch/parisc/kernel/cache.c b/arch/parisc/kernel/cache.c
index 67001277256c..c2259d4a3c33 100644
--- a/arch/parisc/kernel/cache.c
+++ b/arch/parisc/kernel/cache.c
@@ -369,6 +369,7 @@ void __init parisc_setup_cache_timing(void)
 {
 	unsigned long rangetime, alltime;
 	unsigned long size, start;
+	unsigned long threshold;
 
 	alltime = mfctl(16);
 	flush_data_cache();
@@ -382,17 +383,12 @@ void __init parisc_setup_cache_timing(void)
 	printk(KERN_DEBUG "Whole cache flush %lu cycles, flushing %lu bytes %lu cycles\n",
 		alltime, size, rangetime);
 
-	/* Racy, but if we see an intermediate value, it's ok too... */
-	parisc_cache_flush_threshold = size * alltime / rangetime;
-
-	parisc_cache_flush_threshold = L1_CACHE_ALIGN(parisc_cache_flush_threshold);
-	if (!parisc_cache_flush_threshold)
-		parisc_cache_flush_threshold = FLUSH_THRESHOLD;
-
-	if (parisc_cache_flush_threshold > cache_info.dc_size)
-		parisc_cache_flush_threshold = cache_info.dc_size;
-
-	printk(KERN_INFO "Setting cache flush threshold to %lu kB\n",
+	threshold = L1_CACHE_ALIGN(size * alltime / rangetime);
+	if (threshold > cache_info.dc_size)
+		threshold = cache_info.dc_size;
+	if (threshold)
+		parisc_cache_flush_threshold = threshold;
+	printk(KERN_INFO "Cache flush threshold set to %lu KiB\n",
 		parisc_cache_flush_threshold/1024);
 
 	/* calculate TLB flush threshold */
@@ -401,7 +397,7 @@ void __init parisc_setup_cache_timing(void)
 	flush_tlb_all();
 	alltime = mfctl(16) - alltime;
 
-	size = PAGE_SIZE;
+	size = 0;
 	start = (unsigned long) _text;
 	rangetime = mfctl(16);
 	while (start < (unsigned long) _end) {
@@ -414,13 +410,10 @@ void __init parisc_setup_cache_timing(void)
 	printk(KERN_DEBUG "Whole TLB flush %lu cycles, flushing %lu bytes %lu cycles\n",
 		alltime, size, rangetime);
 
-	parisc_tlb_flush_threshold = size * alltime / rangetime;
-	parisc_tlb_flush_threshold *= num_online_cpus();
-	parisc_tlb_flush_threshold = PAGE_ALIGN(parisc_tlb_flush_threshold);
-	if (!parisc_tlb_flush_threshold)
-		parisc_tlb_flush_threshold = FLUSH_TLB_THRESHOLD;
-
-	printk(KERN_INFO "Setting TLB flush threshold to %lu kB\n",
+	threshold = PAGE_ALIGN(num_online_cpus() * size * alltime / rangetime);
+	if (threshold)
+		parisc_tlb_flush_threshold = threshold;
+	printk(KERN_INFO "TLB flush threshold set to %lu KiB\n",
 		parisc_tlb_flush_threshold/1024);
 }
 
diff --git a/arch/parisc/kernel/pacache.S b/arch/parisc/kernel/pacache.S
index b743a80eaba0..675521919229 100644
--- a/arch/parisc/kernel/pacache.S
+++ b/arch/parisc/kernel/pacache.S
@@ -96,7 +96,7 @@ fitmanyloop:					/* Loop if LOOP >= 2 */
 
 fitmanymiddle:					/* Loop if LOOP >= 2 */
 	addib,COND(>)		-1, %r31, fitmanymiddle	/* Adjusted inner loop decr */
-	pitlbe		0(%sr1, %r28)
+	pitlbe		%r0(%sr1, %r28)
 	pitlbe,m	%arg1(%sr1, %r28)	/* Last pitlbe and addr adjust */
 	addib,COND(>)		-1, %r29, fitmanymiddle	/* Middle loop decr */
 	copy		%arg3, %r31		/* Re-init inner loop count */
@@ -139,7 +139,7 @@ fdtmanyloop:					/* Loop if LOOP >= 2 */
 
 fdtmanymiddle:					/* Loop if LOOP >= 2 */
 	addib,COND(>)		-1, %r31, fdtmanymiddle	/* Adjusted inner loop decr */
-	pdtlbe		0(%sr1, %r28)
+	pdtlbe		%r0(%sr1, %r28)
 	pdtlbe,m	%arg1(%sr1, %r28)	/* Last pdtlbe and addr adjust */
 	addib,COND(>)		-1, %r29, fdtmanymiddle	/* Middle loop decr */
 	copy		%arg3, %r31		/* Re-init inner loop count */
@@ -620,12 +620,12 @@ ENTRY(copy_user_page_asm)
 	/* Purge any old translations */
 
 #ifdef CONFIG_PA20
-	pdtlb,l		0(%r28)
-	pdtlb,l		0(%r29)
+	pdtlb,l		%r0(%r28)
+	pdtlb,l		%r0(%r29)
 #else
 	tlb_lock	%r20,%r21,%r22
-	pdtlb		0(%r28)
-	pdtlb		0(%r29)
+	pdtlb		%r0(%r28)
+	pdtlb		%r0(%r29)
 	tlb_unlock	%r20,%r21,%r22
 #endif
 
@@ -768,10 +768,10 @@ ENTRY(clear_user_page_asm)
 	/* Purge any old translation */
 
 #ifdef CONFIG_PA20
-	pdtlb,l		0(%r28)
+	pdtlb,l		%r0(%r28)
 #else
 	tlb_lock	%r20,%r21,%r22
-	pdtlb		0(%r28)
+	pdtlb		%r0(%r28)
 	tlb_unlock	%r20,%r21,%r22
 #endif
 
@@ -852,10 +852,10 @@ ENTRY(flush_dcache_page_asm)
 	/* Purge any old translation */
 
 #ifdef CONFIG_PA20
-	pdtlb,l		0(%r28)
+	pdtlb,l		%r0(%r28)
 #else
 	tlb_lock	%r20,%r21,%r22
-	pdtlb		0(%r28)
+	pdtlb		%r0(%r28)
 	tlb_unlock	%r20,%r21,%r22
 #endif
 
@@ -892,10 +892,10 @@ ENTRY(flush_dcache_page_asm)
 	sync
 
 #ifdef CONFIG_PA20
-	pdtlb,l		0(%r25)
+	pdtlb,l		%r0(%r25)
 #else
 	tlb_lock	%r20,%r21,%r22
-	pdtlb		0(%r25)
+	pdtlb		%r0(%r25)
 	tlb_unlock	%r20,%r21,%r22
 #endif
 
@@ -925,13 +925,18 @@ ENTRY(flush_icache_page_asm)
 	depwi		0, 31,PAGE_SHIFT, %r28	/* Clear any offset bits */
 #endif
 
-	/* Purge any old translation */
+	/* Purge any old translation.  Note that the FIC instruction
+	 * may use either the instruction or data TLB.  Given that we
+	 * have a flat address space, it's not clear which TLB will be
+	 * used.  So, we purge both entries.  */
 
 #ifdef CONFIG_PA20
+	pdtlb,l		%r0(%r28)
 	pitlb,l         %r0(%sr4,%r28)
 #else
 	tlb_lock        %r20,%r21,%r22
-	pitlb           (%sr4,%r28)
+	pdtlb		%r0(%r28)
+	pitlb           %r0(%sr4,%r28)
 	tlb_unlock      %r20,%r21,%r22
 #endif
 
@@ -970,10 +975,12 @@ ENTRY(flush_icache_page_asm)
 	sync
 
 #ifdef CONFIG_PA20
+	pdtlb,l		%r0(%r28)
 	pitlb,l         %r0(%sr4,%r25)
 #else
 	tlb_lock        %r20,%r21,%r22
-	pitlb           (%sr4,%r25)
+	pdtlb		%r0(%r28)
+	pitlb           %r0(%sr4,%r25)
 	tlb_unlock      %r20,%r21,%r22
 #endif
 
diff --git a/arch/parisc/kernel/pci-dma.c b/arch/parisc/kernel/pci-dma.c
index 02d9ed0f3949..494ff6e8c88a 100644
--- a/arch/parisc/kernel/pci-dma.c
+++ b/arch/parisc/kernel/pci-dma.c
@@ -95,8 +95,8 @@ static inline int map_pte_uncached(pte_t * pte,
 
 		if (!pte_none(*pte))
 			printk(KERN_ERR "map_pte_uncached: page already exists\n");
-		set_pte(pte, __mk_pte(*paddr_ptr, PAGE_KERNEL_UNC));
 		purge_tlb_start(flags);
+		set_pte(pte, __mk_pte(*paddr_ptr, PAGE_KERNEL_UNC));
 		pdtlb_kernel(orig_vaddr);
 		purge_tlb_end(flags);
 		vaddr += PAGE_SIZE;
diff --git a/arch/parisc/kernel/setup.c b/arch/parisc/kernel/setup.c
index 81d6f6391944..2e66a887788e 100644
--- a/arch/parisc/kernel/setup.c
+++ b/arch/parisc/kernel/setup.c
@@ -334,6 +334,10 @@ static int __init parisc_init(void)
 	/* tell PDC we're Linux. Nevermind failure. */
 	pdc_stable_write(0x40, &osid, sizeof(osid));
 	
+	/* start with known state */
+	flush_cache_all_local();
+	flush_tlb_all_local(NULL);
+
 	processor_init();
 #ifdef CONFIG_SMP
 	pr_info("CPU(s): %d out of %d %s at %d.%06d MHz online\n",
diff --git a/arch/parisc/kernel/time.c b/arch/parisc/kernel/time.c
index 9b63b876a13a..325f30d82b64 100644
--- a/arch/parisc/kernel/time.c
+++ b/arch/parisc/kernel/time.c
@@ -14,6 +14,7 @@
 #include <linux/module.h>
 #include <linux/rtc.h>
 #include <linux/sched.h>
+#include <linux/sched_clock.h>
 #include <linux/kernel.h>
 #include <linux/param.h>
 #include <linux/string.h>
@@ -39,18 +40,6 @@
 
 static unsigned long clocktick __read_mostly;	/* timer cycles per tick */
 
-#ifndef CONFIG_64BIT
-/*
- * The processor-internal cycle counter (Control Register 16) is used as time
- * source for the sched_clock() function.  This register is 64bit wide on a
- * 64-bit kernel and 32bit on a 32-bit kernel. Since sched_clock() always
- * requires a 64bit counter we emulate on the 32-bit kernel the higher 32bits
- * with a per-cpu variable which we increase every time the counter
- * wraps-around (which happens every ~4 secounds).
- */
-static DEFINE_PER_CPU(unsigned long, cr16_high_32_bits);
-#endif
-
 /*
  * We keep time on PA-RISC Linux by using the Interval Timer which is
  * a pair of registers; one is read-only and one is write-only; both
@@ -121,12 +110,6 @@ irqreturn_t __irq_entry timer_interrupt(int irq, void *dev_id)
 	 */
 	mtctl(next_tick, 16);
 
-#if !defined(CONFIG_64BIT)
-	/* check for overflow on a 32bit kernel (every ~4 seconds). */
-	if (unlikely(next_tick < now))
-		this_cpu_inc(cr16_high_32_bits);
-#endif
-
 	/* Skip one clocktick on purpose if we missed next_tick.
 	 * The new CR16 must be "later" than current CR16 otherwise
 	 * itimer would not fire until CR16 wrapped - e.g 4 seconds
@@ -208,7 +191,7 @@ EXPORT_SYMBOL(profile_pc);
 
 /* clock source code */
 
-static cycle_t read_cr16(struct clocksource *cs)
+static cycle_t notrace read_cr16(struct clocksource *cs)
 {
 	return get_cycles();
 }
@@ -287,26 +270,9 @@ void read_persistent_clock(struct timespec *ts)
 }
 
 
-/*
- * sched_clock() framework
- */
-
-static u32 cyc2ns_mul __read_mostly;
-static u32 cyc2ns_shift __read_mostly;
-
-u64 sched_clock(void)
+static u64 notrace read_cr16_sched_clock(void)
 {
-	u64 now;
-
-	/* Get current cycle counter (Control Register 16). */
-#ifdef CONFIG_64BIT
-	now = mfctl(16);
-#else
-	now = mfctl(16) + (((u64) this_cpu_read(cr16_high_32_bits)) << 32);
-#endif
-
-	/* return the value in ns (cycles_2_ns) */
-	return mul_u64_u32_shr(now, cyc2ns_mul, cyc2ns_shift);
+	return get_cycles();
 }
 
 
@@ -316,17 +282,16 @@ u64 sched_clock(void)
 
 void __init time_init(void)
 {
-	unsigned long current_cr16_khz;
+	unsigned long cr16_hz;
 
-	current_cr16_khz = PAGE0->mem_10msec/10;  /* kHz */
 	clocktick = (100 * PAGE0->mem_10msec) / HZ;
-
-	/* calculate mult/shift values for cr16 */
-	clocks_calc_mult_shift(&cyc2ns_mul, &cyc2ns_shift, current_cr16_khz,
-				NSEC_PER_MSEC, 0);
-
 	start_cpu_itimer();	/* get CPU 0 started */
 
+	cr16_hz = 100 * PAGE0->mem_10msec;  /* Hz */
+
 	/* register at clocksource framework */
-	clocksource_register_khz(&clocksource_cr16, current_cr16_khz);
+	clocksource_register_hz(&clocksource_cr16, cr16_hz);
+
+	/* register as sched_clock source */
+	sched_clock_register(read_cr16_sched_clock, BITS_PER_LONG, cr16_hz);
 }
diff --git a/arch/powerpc/boot/main.c b/arch/powerpc/boot/main.c
index d80161b633f4..60522d22a428 100644
--- a/arch/powerpc/boot/main.c
+++ b/arch/powerpc/boot/main.c
@@ -217,8 +217,12 @@ void start(void)
 		console_ops.close();
 
 	kentry = (kernel_entry_t) vmlinux.addr;
-	if (ft_addr)
-		kentry(ft_addr, 0, NULL);
+	if (ft_addr) {
+		if(platform_ops.kentry)
+			platform_ops.kentry(ft_addr, vmlinux.addr);
+		else
+			kentry(ft_addr, 0, NULL);
+	}
 	else
 		kentry((unsigned long)initrd.addr, initrd.size,
 		       loader_info.promptr);
diff --git a/arch/powerpc/boot/opal-calls.S b/arch/powerpc/boot/opal-calls.S
index ff2f1b97bc53..2a99fc9a3ccf 100644
--- a/arch/powerpc/boot/opal-calls.S
+++ b/arch/powerpc/boot/opal-calls.S
@@ -12,6 +12,19 @@
 
 	.text
 
+	.globl opal_kentry
+opal_kentry:
+	/* r3 is the fdt ptr */
+	mtctr r4
+	li	r4, 0
+	li	r5, 0
+	li	r6, 0
+	li	r7, 0
+	ld	r11,opal@got(r2)
+	ld	r8,0(r11)
+	ld	r9,8(r11)
+	bctr
+
 #define OPAL_CALL(name, token)				\
 	.globl name;					\
 name:							\
diff --git a/arch/powerpc/boot/opal.c b/arch/powerpc/boot/opal.c
index 1f37e1c1d6d8..d7b4fd47eb44 100644
--- a/arch/powerpc/boot/opal.c
+++ b/arch/powerpc/boot/opal.c
@@ -23,14 +23,25 @@ struct opal {
 
 static u32 opal_con_id;
 
+/* see opal-wrappers.S */
 int64_t opal_console_write(int64_t term_number, u64 *length, const u8 *buffer);
 int64_t opal_console_read(int64_t term_number, uint64_t *length, u8 *buffer);
 int64_t opal_console_write_buffer_space(uint64_t term_number, uint64_t *length);
 int64_t opal_console_flush(uint64_t term_number);
 int64_t opal_poll_events(uint64_t *outstanding_event_mask);
 
+void opal_kentry(unsigned long fdt_addr, void *vmlinux_addr);
+
 static int opal_con_open(void)
 {
+	/*
+	 * When OPAL loads the boot kernel it stashes the OPAL base and entry
+	 * address in r8 and r9 so the kernel can use the OPAL console
+	 * before unflattening the devicetree. While executing the wrapper will
+	 * probably trash r8 and r9 so this kentry hook restores them before
+	 * entering the decompressed kernel.
+	 */
+	platform_ops.kentry = opal_kentry;
 	return 0;
 }
 
diff --git a/arch/powerpc/boot/ops.h b/arch/powerpc/boot/ops.h
index e19b64ef977a..deeae6f6ba9c 100644
--- a/arch/powerpc/boot/ops.h
+++ b/arch/powerpc/boot/ops.h
@@ -30,6 +30,7 @@ struct platform_ops {
 	void *	(*realloc)(void *ptr, unsigned long size);
 	void	(*exit)(void);
 	void *	(*vmlinux_alloc)(unsigned long size);
+	void  	(*kentry)(unsigned long fdt_addr, void *vmlinux_addr);
 };
 extern struct platform_ops platform_ops;
 
diff --git a/arch/powerpc/include/asm/mmu.h b/arch/powerpc/include/asm/mmu.h
index e2fb408f8398..fd10b582fb2d 100644
--- a/arch/powerpc/include/asm/mmu.h
+++ b/arch/powerpc/include/asm/mmu.h
@@ -29,6 +29,12 @@
  */
 
 /*
+ * Kernel read only support.
+ * We added the ppp value 0b110 in ISA 2.04.
+ */
+#define MMU_FTR_KERNEL_RO		ASM_CONST(0x00004000)
+
+/*
  * We need to clear top 16bits of va (from the remaining 64 bits )in
  * tlbie* instructions
  */
@@ -103,10 +109,10 @@
 #define MMU_FTRS_POWER4		MMU_FTRS_DEFAULT_HPTE_ARCH_V2
 #define MMU_FTRS_PPC970		MMU_FTRS_POWER4 | MMU_FTR_TLBIE_CROP_VA
 #define MMU_FTRS_POWER5		MMU_FTRS_POWER4 | MMU_FTR_LOCKLESS_TLBIE
-#define MMU_FTRS_POWER6		MMU_FTRS_POWER4 | MMU_FTR_LOCKLESS_TLBIE
-#define MMU_FTRS_POWER7		MMU_FTRS_POWER4 | MMU_FTR_LOCKLESS_TLBIE
-#define MMU_FTRS_POWER8		MMU_FTRS_POWER4 | MMU_FTR_LOCKLESS_TLBIE
-#define MMU_FTRS_POWER9		MMU_FTRS_POWER4 | MMU_FTR_LOCKLESS_TLBIE
+#define MMU_FTRS_POWER6		MMU_FTRS_POWER4 | MMU_FTR_LOCKLESS_TLBIE | MMU_FTR_KERNEL_RO
+#define MMU_FTRS_POWER7		MMU_FTRS_POWER4 | MMU_FTR_LOCKLESS_TLBIE | MMU_FTR_KERNEL_RO
+#define MMU_FTRS_POWER8		MMU_FTRS_POWER4 | MMU_FTR_LOCKLESS_TLBIE | MMU_FTR_KERNEL_RO
+#define MMU_FTRS_POWER9		MMU_FTRS_POWER4 | MMU_FTR_LOCKLESS_TLBIE | MMU_FTR_KERNEL_RO
 #define MMU_FTRS_CELL		MMU_FTRS_DEFAULT_HPTE_ARCH_V2 | \
 				MMU_FTR_CI_LARGE_PAGE
 #define MMU_FTRS_PA6T		MMU_FTRS_DEFAULT_HPTE_ARCH_V2 | \
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index 978dada662ae..52cbf043e960 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -355,6 +355,7 @@
 #define     LPCR_PECE0		ASM_CONST(0x0000000000004000)	/* ext. exceptions can cause exit */
 #define     LPCR_PECE1		ASM_CONST(0x0000000000002000)	/* decrementer can cause exit */
 #define     LPCR_PECE2		ASM_CONST(0x0000000000001000)	/* machine check etc can cause exit */
+#define     LPCR_PECE_HVEE	ASM_CONST(0x0000400000000000)	/* P9 Wakeup on HV interrupts */
 #define   LPCR_MER		ASM_CONST(0x0000000000000800)	/* Mediated External Exception */
 #define   LPCR_MER_SH		11
 #define   LPCR_TC		ASM_CONST(0x0000000000000200)	/* Translation control */
diff --git a/arch/powerpc/kernel/cpu_setup_power.S b/arch/powerpc/kernel/cpu_setup_power.S
index 52ff3f025437..37c027ca83b2 100644
--- a/arch/powerpc/kernel/cpu_setup_power.S
+++ b/arch/powerpc/kernel/cpu_setup_power.S
@@ -98,8 +98,8 @@ _GLOBAL(__setup_cpu_power9)
 	li	r0,0
 	mtspr	SPRN_LPID,r0
 	mfspr	r3,SPRN_LPCR
-	ori	r3, r3, LPCR_PECEDH
-	ori	r3, r3, LPCR_HVICE
+	LOAD_REG_IMMEDIATE(r4, LPCR_PECEDH | LPCR_PECE_HVEE | LPCR_HVICE)
+	or	r3, r3, r4
 	bl	__init_LPCR
 	bl	__init_HFSCR
 	bl	__init_tlb_power9
@@ -118,8 +118,8 @@ _GLOBAL(__restore_cpu_power9)
 	li	r0,0
 	mtspr	SPRN_LPID,r0
 	mfspr   r3,SPRN_LPCR
-	ori	r3, r3, LPCR_PECEDH
-	ori	r3, r3, LPCR_HVICE
+	LOAD_REG_IMMEDIATE(r4, LPCR_PECEDH | LPCR_PECE_HVEE | LPCR_HVICE)
+	or	r3, r3, r4
 	bl	__init_LPCR
 	bl	__init_HFSCR
 	bl	__init_tlb_power9
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index 28923b2e2df1..8dff9ce6fbc1 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -190,8 +190,12 @@ unsigned long htab_convert_pte_flags(unsigned long pteflags)
 		/*
 		 * Kernel read only mapped with ppp bits 0b110
 		 */
-		if (!(pteflags & _PAGE_WRITE))
-			rflags |= (HPTE_R_PP0 | 0x2);
+		if (!(pteflags & _PAGE_WRITE)) {
+			if (mmu_has_feature(MMU_FTR_KERNEL_RO))
+				rflags |= (HPTE_R_PP0 | 0x2);
+			else
+				rflags |= 0x3;
+		}
 	} else {
 		if (pteflags & _PAGE_RWX)
 			rflags |= 0x2;
diff --git a/arch/tile/kernel/time.c b/arch/tile/kernel/time.c
index 178989e6d3e3..ea960d660917 100644
--- a/arch/tile/kernel/time.c
+++ b/arch/tile/kernel/time.c
@@ -218,8 +218,8 @@ void do_timer_interrupt(struct pt_regs *regs, int fault_num)
  */
 unsigned long long sched_clock(void)
 {
-	return clocksource_cyc2ns(get_cycles(),
-				  sched_clock_mult, SCHED_CLOCK_SHIFT);
+	return mult_frac(get_cycles(),
+			 sched_clock_mult, 1ULL << SCHED_CLOCK_SHIFT);
 }
 
 int setup_profiling_timer(unsigned int multiplier)
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 9b983a474253..8fc714b4f18a 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -1070,20 +1070,20 @@ static void setup_pebs_sample_data(struct perf_event *event,
 	}
 
 	/*
-	 * We use the interrupt regs as a base because the PEBS record
-	 * does not contain a full regs set, specifically it seems to
-	 * lack segment descriptors, which get used by things like
-	 * user_mode().
+	 * We use the interrupt regs as a base because the PEBS record does not
+	 * contain a full regs set, specifically it seems to lack segment
+	 * descriptors, which get used by things like user_mode().
 	 *
-	 * In the simple case fix up only the IP and BP,SP regs, for
-	 * PERF_SAMPLE_IP and PERF_SAMPLE_CALLCHAIN to function properly.
-	 * A possible PERF_SAMPLE_REGS will have to transfer all regs.
+	 * In the simple case fix up only the IP for PERF_SAMPLE_IP.
+	 *
+	 * We must however always use BP,SP from iregs for the unwinder to stay
+	 * sane; the record BP,SP can point into thin air when the record is
+	 * from a previous PMI context or an (I)RET happend between the record
+	 * and PMI.
 	 */
 	*regs = *iregs;
 	regs->flags = pebs->flags;
 	set_linear_ip(regs, pebs->ip);
-	regs->bp = pebs->bp;
-	regs->sp = pebs->sp;
 
 	if (sample_type & PERF_SAMPLE_REGS_INTR) {
 		regs->ax = pebs->ax;
@@ -1092,10 +1092,21 @@ static void setup_pebs_sample_data(struct perf_event *event,
 		regs->dx = pebs->dx;
 		regs->si = pebs->si;
 		regs->di = pebs->di;
-		regs->bp = pebs->bp;
-		regs->sp = pebs->sp;
 
-		regs->flags = pebs->flags;
+		/*
+		 * Per the above; only set BP,SP if we don't need callchains.
+		 *
+		 * XXX: does this make sense?
+		 */
+		if (!(sample_type & PERF_SAMPLE_CALLCHAIN)) {
+			regs->bp = pebs->bp;
+			regs->sp = pebs->sp;
+		}
+
+		/*
+		 * Preserve PERF_EFLAGS_VM from set_linear_ip().
+		 */
+		regs->flags = pebs->flags | (regs->flags & PERF_EFLAGS_VM);
 #ifndef CONFIG_X86_32
 		regs->r8 = pebs->r8;
 		regs->r9 = pebs->r9;
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index 8c4a47706296..181c238d4df9 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -113,7 +113,7 @@ struct debug_store {
  * Per register state.
  */
 struct er_account {
-	raw_spinlock_t		lock;	/* per-core: protect structure */
+	raw_spinlock_t      lock;	/* per-core: protect structure */
 	u64                 config;	/* extra MSR config */
 	u64                 reg;	/* extra MSR number */
 	atomic_t            ref;	/* reference count */
diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index 3fc03a09a93b..c289e2f4a6e5 100644
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -517,14 +517,14 @@ void fpu__clear(struct fpu *fpu)
 {
 	WARN_ON_FPU(fpu != &current->thread.fpu); /* Almost certainly an anomaly */
 
-	if (!use_eager_fpu() || !static_cpu_has(X86_FEATURE_FPU)) {
-		/* FPU state will be reallocated lazily at the first use. */
-		fpu__drop(fpu);
-	} else {
-		if (!fpu->fpstate_active) {
-			fpu__activate_curr(fpu);
-			user_fpu_begin();
-		}
+	fpu__drop(fpu);
+
+	/*
+	 * Make sure fpstate is cleared and initialized.
+	 */
+	if (static_cpu_has(X86_FEATURE_FPU)) {
+		fpu__activate_curr(fpu);
+		user_fpu_begin();
 		copy_init_fpstate_to_fpregs();
 	}
 }
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index cbd7b92585bb..a3ce9d260d68 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -2105,16 +2105,10 @@ static int em_iret(struct x86_emulate_ctxt *ctxt)
 static int em_jmp_far(struct x86_emulate_ctxt *ctxt)
 {
 	int rc;
-	unsigned short sel, old_sel;
-	struct desc_struct old_desc, new_desc;
-	const struct x86_emulate_ops *ops = ctxt->ops;
+	unsigned short sel;
+	struct desc_struct new_desc;
 	u8 cpl = ctxt->ops->cpl(ctxt);
 
-	/* Assignment of RIP may only fail in 64-bit mode */
-	if (ctxt->mode == X86EMUL_MODE_PROT64)
-		ops->get_segment(ctxt, &old_sel, &old_desc, NULL,
-				 VCPU_SREG_CS);
-
 	memcpy(&sel, ctxt->src.valptr + ctxt->op_bytes, 2);
 
 	rc = __load_segment_descriptor(ctxt, sel, VCPU_SREG_CS, cpl,
@@ -2124,12 +2118,10 @@ static int em_jmp_far(struct x86_emulate_ctxt *ctxt)
 		return rc;
 
 	rc = assign_eip_far(ctxt, ctxt->src.val, &new_desc);
-	if (rc != X86EMUL_CONTINUE) {
-		WARN_ON(ctxt->mode != X86EMUL_MODE_PROT64);
-		/* assigning eip failed; restore the old cs */
-		ops->set_segment(ctxt, old_sel, &old_desc, 0, VCPU_SREG_CS);
-		return rc;
-	}
+	/* Error handling is not implemented. */
+	if (rc != X86EMUL_CONTINUE)
+		return X86EMUL_UNHANDLEABLE;
+
 	return rc;
 }
 
@@ -2189,14 +2181,8 @@ static int em_ret_far(struct x86_emulate_ctxt *ctxt)
 {
 	int rc;
 	unsigned long eip, cs;
-	u16 old_cs;
 	int cpl = ctxt->ops->cpl(ctxt);
-	struct desc_struct old_desc, new_desc;
-	const struct x86_emulate_ops *ops = ctxt->ops;
-
-	if (ctxt->mode == X86EMUL_MODE_PROT64)
-		ops->get_segment(ctxt, &old_cs, &old_desc, NULL,
-				 VCPU_SREG_CS);
+	struct desc_struct new_desc;
 
 	rc = emulate_pop(ctxt, &eip, ctxt->op_bytes);
 	if (rc != X86EMUL_CONTINUE)
@@ -2213,10 +2199,10 @@ static int em_ret_far(struct x86_emulate_ctxt *ctxt)
 	if (rc != X86EMUL_CONTINUE)
 		return rc;
 	rc = assign_eip_far(ctxt, eip, &new_desc);
-	if (rc != X86EMUL_CONTINUE) {
-		WARN_ON(ctxt->mode != X86EMUL_MODE_PROT64);
-		ops->set_segment(ctxt, old_cs, &old_desc, 0, VCPU_SREG_CS);
-	}
+	/* Error handling is not implemented. */
+	if (rc != X86EMUL_CONTINUE)
+		return X86EMUL_UNHANDLEABLE;
+
 	return rc;
 }
 
diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c
index 1a22de70f7f7..6e219e5c07d2 100644
--- a/arch/x86/kvm/ioapic.c
+++ b/arch/x86/kvm/ioapic.c
@@ -94,7 +94,7 @@ static unsigned long ioapic_read_indirect(struct kvm_ioapic *ioapic,
 static void rtc_irq_eoi_tracking_reset(struct kvm_ioapic *ioapic)
 {
 	ioapic->rtc_status.pending_eoi = 0;
-	bitmap_zero(ioapic->rtc_status.dest_map.map, KVM_MAX_VCPUS);
+	bitmap_zero(ioapic->rtc_status.dest_map.map, KVM_MAX_VCPU_ID);
 }
 
 static void kvm_rtc_eoi_tracking_restore_all(struct kvm_ioapic *ioapic);
diff --git a/arch/x86/kvm/ioapic.h b/arch/x86/kvm/ioapic.h
index 7d2692a49657..1cc6e54436db 100644
--- a/arch/x86/kvm/ioapic.h
+++ b/arch/x86/kvm/ioapic.h
@@ -42,13 +42,13 @@ struct kvm_vcpu;
 
 struct dest_map {
 	/* vcpu bitmap where IRQ has been sent */
-	DECLARE_BITMAP(map, KVM_MAX_VCPUS);
+	DECLARE_BITMAP(map, KVM_MAX_VCPU_ID);
 
 	/*
 	 * Vector sent to a given vcpu, only valid when
 	 * the vcpu's bit in map is set
 	 */
-	u8 vectors[KVM_MAX_VCPUS];
+	u8 vectors[KVM_MAX_VCPU_ID];
 };
 
 
diff --git a/arch/x86/kvm/irq_comm.c b/arch/x86/kvm/irq_comm.c
index 25810b144b58..e7a112ac51a8 100644
--- a/arch/x86/kvm/irq_comm.c
+++ b/arch/x86/kvm/irq_comm.c
@@ -41,6 +41,15 @@ static int kvm_set_pic_irq(struct kvm_kernel_irq_routing_entry *e,
 			   bool line_status)
 {
 	struct kvm_pic *pic = pic_irqchip(kvm);
+
+	/*
+	 * XXX: rejecting pic routes when pic isn't in use would be better,
+	 * but the default routing table is installed while kvm->arch.vpic is
+	 * NULL and KVM_CREATE_IRQCHIP can race with KVM_IRQ_LINE.
+	 */
+	if (!pic)
+		return -1;
+
 	return kvm_pic_set_irq(pic, e->irqchip.pin, irq_source_id, level);
 }
 
@@ -49,6 +58,10 @@ static int kvm_set_ioapic_irq(struct kvm_kernel_irq_routing_entry *e,
 			      bool line_status)
 {
 	struct kvm_ioapic *ioapic = kvm->arch.vioapic;
+
+	if (!ioapic)
+		return -1;
+
 	return kvm_ioapic_set_irq(ioapic, e->irqchip.pin, irq_source_id, level,
 				line_status);
 }
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index b62c85229711..d2255e4f9589 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -138,7 +138,7 @@ static inline bool kvm_apic_map_get_logical_dest(struct kvm_apic_map *map,
 		*mask = dest_id & 0xff;
 		return true;
 	case KVM_APIC_MODE_XAPIC_CLUSTER:
-		*cluster = map->xapic_cluster_map[dest_id >> 4];
+		*cluster = map->xapic_cluster_map[(dest_id >> 4) & 0xf];
 		*mask = dest_id & 0xf;
 		return true;
 	default:
diff --git a/arch/x86/mm/extable.c b/arch/x86/mm/extable.c
index 832b98f822be..a3a983fd4248 100644
--- a/arch/x86/mm/extable.c
+++ b/arch/x86/mm/extable.c
@@ -135,7 +135,12 @@ void __init early_fixup_exception(struct pt_regs *regs, int trapnr)
 	if (early_recursion_flag > 2)
 		goto halt_loop;
 
-	if (regs->cs != __KERNEL_CS)
+	/*
+	 * Old CPUs leave the high bits of CS on the stack
+	 * undefined.  I'm not sure which CPUs do this, but at least
+	 * the 486 DX works this way.
+	 */
+	if ((regs->cs & 0xFFFF) != __KERNEL_CS)
 		goto fail;
 
 	/*
diff --git a/crypto/asymmetric_keys/x509_cert_parser.c b/crypto/asymmetric_keys/x509_cert_parser.c
index 865f46ea724f..c80765b211cf 100644
--- a/crypto/asymmetric_keys/x509_cert_parser.c
+++ b/crypto/asymmetric_keys/x509_cert_parser.c
@@ -133,7 +133,6 @@ struct x509_certificate *x509_cert_parse(const void *data, size_t datalen)
 	return cert;
 
 error_decode:
-	kfree(cert->pub->key);
 	kfree(ctx);
 error_no_ctx:
 	x509_free_certificate(cert);
diff --git a/drivers/dax/dax.c b/drivers/dax/dax.c
index 29f600f2c447..ff64313770bd 100644
--- a/drivers/dax/dax.c
+++ b/drivers/dax/dax.c
@@ -323,8 +323,8 @@ static int check_vma(struct dax_dev *dax_dev, struct vm_area_struct *vma,
 	if (!dax_dev->alive)
 		return -ENXIO;
 
-	/* prevent private / writable mappings from being established */
-	if ((vma->vm_flags & (VM_NORESERVE|VM_SHARED|VM_WRITE)) == VM_WRITE) {
+	/* prevent private mappings from being established */
+	if ((vma->vm_flags & VM_SHARED) != VM_SHARED) {
 		dev_info(dev, "%s: %s: fail, attempted private mapping\n",
 				current->comm, func);
 		return -EINVAL;
diff --git a/drivers/dax/pmem.c b/drivers/dax/pmem.c
index 73ae849f5170..76dd42dd7088 100644
--- a/drivers/dax/pmem.c
+++ b/drivers/dax/pmem.c
@@ -77,7 +77,9 @@ static int dax_pmem_probe(struct device *dev)
 	nsio = to_nd_namespace_io(&ndns->dev);
 
 	/* parse the 'pfn' info block via ->rw_bytes */
-	devm_nsio_enable(dev, nsio);
+	rc = devm_nsio_enable(dev, nsio);
+	if (rc)
+		return rc;
 	altmap = nvdimm_setup_pfn(nd_pfn, &res, &__altmap);
 	if (IS_ERR(altmap))
 		return PTR_ERR(altmap);
diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c
index 58470f5ced04..8c53748a769d 100644
--- a/drivers/iommu/dmar.c
+++ b/drivers/iommu/dmar.c
@@ -338,7 +338,9 @@ static int dmar_pci_bus_notifier(struct notifier_block *nb,
 	struct pci_dev *pdev = to_pci_dev(data);
 	struct dmar_pci_notify_info *info;
 
-	/* Only care about add/remove events for physical functions */
+	/* Only care about add/remove events for physical functions.
+	 * For VFs we actually do the lookup based on the corresponding
+	 * PF in device_to_iommu() anyway. */
 	if (pdev->is_virtfn)
 		return NOTIFY_DONE;
 	if (action != BUS_NOTIFY_ADD_DEVICE &&
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index 1257b0b80296..7fb538708cec 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -892,7 +892,13 @@ static struct intel_iommu *device_to_iommu(struct device *dev, u8 *bus, u8 *devf
 		return NULL;
 
 	if (dev_is_pci(dev)) {
+		struct pci_dev *pf_pdev;
+
 		pdev = to_pci_dev(dev);
+		/* VFs aren't listed in scope tables; we need to look up
+		 * the PF instead to find the IOMMU. */
+		pf_pdev = pci_physfn(pdev);
+		dev = &pf_pdev->dev;
 		segment = pci_domain_nr(pdev->bus);
 	} else if (has_acpi_companion(dev))
 		dev = &ACPI_COMPANION(dev)->dev;
@@ -905,6 +911,13 @@ static struct intel_iommu *device_to_iommu(struct device *dev, u8 *bus, u8 *devf
 		for_each_active_dev_scope(drhd->devices,
 					  drhd->devices_cnt, i, tmp) {
 			if (tmp == dev) {
+				/* For a VF use its original BDF# not that of the PF
+				 * which we used for the IOMMU lookup. Strictly speaking
+				 * we could do this for all PCI devices; we only need to
+				 * get the BDF# from the scope table for ACPI matches. */
+				if (pdev->is_virtfn)
+					goto got_pdev;
+
 				*bus = drhd->devices[i].bus;
 				*devfn = drhd->devices[i].devfn;
 				goto out;
diff --git a/drivers/iommu/intel-svm.c b/drivers/iommu/intel-svm.c
index 8ebb3530afa7..cb72e0011310 100644
--- a/drivers/iommu/intel-svm.c
+++ b/drivers/iommu/intel-svm.c
@@ -39,10 +39,18 @@ int intel_svm_alloc_pasid_tables(struct intel_iommu *iommu)
 	struct page *pages;
 	int order;
 
-	order = ecap_pss(iommu->ecap) + 7 - PAGE_SHIFT;
-	if (order < 0)
-		order = 0;
-
+	/* Start at 2 because it's defined as 2^(1+PSS) */
+	iommu->pasid_max = 2 << ecap_pss(iommu->ecap);
+
+	/* Eventually I'm promised we will get a multi-level PASID table
+	 * and it won't have to be physically contiguous. Until then,
+	 * limit the size because 8MiB contiguous allocations can be hard
+	 * to come by. The limit of 0x20000, which is 1MiB for each of
+	 * the PASID and PASID-state tables, is somewhat arbitrary. */
+	if (iommu->pasid_max > 0x20000)
+		iommu->pasid_max = 0x20000;
+
+	order = get_order(sizeof(struct pasid_entry) * iommu->pasid_max);
 	pages = alloc_pages(GFP_KERNEL | __GFP_ZERO, order);
 	if (!pages) {
 		pr_warn("IOMMU: %s: Failed to allocate PASID table\n",
@@ -53,6 +61,8 @@ int intel_svm_alloc_pasid_tables(struct intel_iommu *iommu)
 	pr_info("%s: Allocated order %d PASID table.\n", iommu->name, order);
 
 	if (ecap_dis(iommu->ecap)) {
+		/* Just making it explicit... */
+		BUILD_BUG_ON(sizeof(struct pasid_entry) != sizeof(struct pasid_state_entry));
 		pages = alloc_pages(GFP_KERNEL | __GFP_ZERO, order);
 		if (pages)
 			iommu->pasid_state_table = page_address(pages);
@@ -68,11 +78,7 @@ int intel_svm_alloc_pasid_tables(struct intel_iommu *iommu)
 
 int intel_svm_free_pasid_tables(struct intel_iommu *iommu)
 {
-	int order;
-
-	order = ecap_pss(iommu->ecap) + 7 - PAGE_SHIFT;
-	if (order < 0)
-		order = 0;
+	int order = get_order(sizeof(struct pasid_entry) * iommu->pasid_max);
 
 	if (iommu->pasid_table) {
 		free_pages((unsigned long)iommu->pasid_table, order);
@@ -371,8 +377,8 @@ int intel_svm_bind_mm(struct device *dev, int *pasid, int flags, struct svm_dev_
 		}
 		svm->iommu = iommu;
 
-		if (pasid_max > 2 << ecap_pss(iommu->ecap))
-			pasid_max = 2 << ecap_pss(iommu->ecap);
+		if (pasid_max > iommu->pasid_max)
+			pasid_max = iommu->pasid_max;
 
 		/* Do not use PASID 0 in caching mode (virtualised IOMMU) */
 		ret = idr_alloc(&iommu->pasid_idr, svm,
diff --git a/drivers/media/tuners/tuner-xc2028.c b/drivers/media/tuners/tuner-xc2028.c
index 317ef63ee789..8d96a22647b3 100644
--- a/drivers/media/tuners/tuner-xc2028.c
+++ b/drivers/media/tuners/tuner-xc2028.c
@@ -281,6 +281,14 @@ static void free_firmware(struct xc2028_data *priv)
 	int i;
 	tuner_dbg("%s called\n", __func__);
 
+	/* free allocated f/w string */
+	if (priv->fname != firmware_name)
+		kfree(priv->fname);
+	priv->fname = NULL;
+
+	priv->state = XC2028_NO_FIRMWARE;
+	memset(&priv->cur_fw, 0, sizeof(priv->cur_fw));
+
 	if (!priv->firm)
 		return;
 
@@ -291,9 +299,6 @@ static void free_firmware(struct xc2028_data *priv)
 
 	priv->firm = NULL;
 	priv->firm_size = 0;
-	priv->state = XC2028_NO_FIRMWARE;
-
-	memset(&priv->cur_fw, 0, sizeof(priv->cur_fw));
 }
 
 static int load_all_firmwares(struct dvb_frontend *fe,
@@ -884,9 +889,8 @@ read_not_reliable:
 	return 0;
 
 fail:
-	priv->state = XC2028_NO_FIRMWARE;
+	free_firmware(priv);
 
-	memset(&priv->cur_fw, 0, sizeof(priv->cur_fw));
 	if (retry_count < 8) {
 		msleep(50);
 		retry_count++;
@@ -1332,11 +1336,8 @@ static int xc2028_dvb_release(struct dvb_frontend *fe)
 	mutex_lock(&xc2028_list_mutex);
 
 	/* only perform final cleanup if this is the last instance */
-	if (hybrid_tuner_report_instance_count(priv) == 1) {
+	if (hybrid_tuner_report_instance_count(priv) == 1)
 		free_firmware(priv);
-		kfree(priv->ctrl.fname);
-		priv->ctrl.fname = NULL;
-	}
 
 	if (priv)
 		hybrid_tuner_release_state(priv);
@@ -1399,19 +1400,8 @@ static int xc2028_set_config(struct dvb_frontend *fe, void *priv_cfg)
 
 	/*
 	 * Copy the config data.
-	 * For the firmware name, keep a local copy of the string,
-	 * in order to avoid troubles during device release.
 	 */
-	kfree(priv->ctrl.fname);
-	priv->ctrl.fname = NULL;
 	memcpy(&priv->ctrl, p, sizeof(priv->ctrl));
-	if (p->fname) {
-		priv->ctrl.fname = kstrdup(p->fname, GFP_KERNEL);
-		if (priv->ctrl.fname == NULL) {
-			rc = -ENOMEM;
-			goto unlock;
-		}
-	}
 
 	/*
 	 * If firmware name changed, frees firmware. As free_firmware will
@@ -1426,10 +1416,15 @@ static int xc2028_set_config(struct dvb_frontend *fe, void *priv_cfg)
 
 	if (priv->state == XC2028_NO_FIRMWARE) {
 		if (!firmware_name[0])
-			priv->fname = priv->ctrl.fname;
+			priv->fname = kstrdup(p->fname, GFP_KERNEL);
 		else
 			priv->fname = firmware_name;
 
+		if (!priv->fname) {
+			rc = -ENOMEM;
+			goto unlock;
+		}
+
 		rc = request_firmware_nowait(THIS_MODULE, 1,
 					     priv->fname,
 					     priv->i2c_props.adap->dev.parent,
diff --git a/drivers/mmc/host/sdhci-of-esdhc.c b/drivers/mmc/host/sdhci-of-esdhc.c
index 239be2fde242..2267601f0ac1 100644
--- a/drivers/mmc/host/sdhci-of-esdhc.c
+++ b/drivers/mmc/host/sdhci-of-esdhc.c
@@ -66,6 +66,20 @@ static u32 esdhc_readl_fixup(struct sdhci_host *host,
 			return ret;
 		}
 	}
+	/*
+	 * The DAT[3:0] line signal levels and the CMD line signal level are
+	 * not compatible with standard SDHC register. The line signal levels
+	 * DAT[7:0] are at bits 31:24 and the command line signal level is at
+	 * bit 23. All other bits are the same as in the standard SDHC
+	 * register.
+	 */
+	if (spec_reg == SDHCI_PRESENT_STATE) {
+		ret = value & 0x000fffff;
+		ret |= (value >> 4) & SDHCI_DATA_LVL_MASK;
+		ret |= (value << 1) & SDHCI_CMD_LVL;
+		return ret;
+	}
+
 	ret = value;
 	return ret;
 }
diff --git a/drivers/mmc/host/sdhci.h b/drivers/mmc/host/sdhci.h
index 0411c9f36461..1b3bd1c7f4f6 100644
--- a/drivers/mmc/host/sdhci.h
+++ b/drivers/mmc/host/sdhci.h
@@ -73,6 +73,7 @@
 #define  SDHCI_DATA_LVL_MASK	0x00F00000
 #define   SDHCI_DATA_LVL_SHIFT	20
 #define   SDHCI_DATA_0_LVL_MASK	0x00100000
+#define  SDHCI_CMD_LVL		0x01000000
 
 #define SDHCI_HOST_CONTROL	0x28
 #define  SDHCI_CTRL_LED		0x01
diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
index 46c0f5ecd99d..58e60298a360 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
@@ -3894,6 +3894,11 @@ _scsih_temp_threshold_events(struct MPT3SAS_ADAPTER *ioc,
 	}
 }
 
+static inline bool ata_12_16_cmd(struct scsi_cmnd *scmd)
+{
+	return (scmd->cmnd[0] == ATA_12 || scmd->cmnd[0] == ATA_16);
+}
+
 /**
  * _scsih_flush_running_cmds - completing outstanding commands.
  * @ioc: per adapter object
@@ -3915,6 +3920,9 @@ _scsih_flush_running_cmds(struct MPT3SAS_ADAPTER *ioc)
 		if (!scmd)
 			continue;
 		count++;
+		if (ata_12_16_cmd(scmd))
+			scsi_internal_device_unblock(scmd->device,
+							SDEV_RUNNING);
 		mpt3sas_base_free_smid(ioc, smid);
 		scsi_dma_unmap(scmd);
 		if (ioc->pci_error_recovery)
@@ -4019,8 +4027,6 @@ _scsih_eedp_error_handling(struct scsi_cmnd *scmd, u16 ioc_status)
 	    SAM_STAT_CHECK_CONDITION;
 }
 
-
-
 /**
  * scsih_qcmd - main scsi request entry point
  * @scmd: pointer to scsi command object
@@ -4047,6 +4053,13 @@ scsih_qcmd(struct Scsi_Host *shost, struct scsi_cmnd *scmd)
 	if (ioc->logging_level & MPT_DEBUG_SCSI)
 		scsi_print_command(scmd);
 
+	/*
+	 * Lock the device for any subsequent command until command is
+	 * done.
+	 */
+	if (ata_12_16_cmd(scmd))
+		scsi_internal_device_block(scmd->device);
+
 	sas_device_priv_data = scmd->device->hostdata;
 	if (!sas_device_priv_data || !sas_device_priv_data->sas_target) {
 		scmd->result = DID_NO_CONNECT << 16;
@@ -4622,6 +4635,9 @@ _scsih_io_done(struct MPT3SAS_ADAPTER *ioc, u16 smid, u8 msix_index, u32 reply)
 	if (scmd == NULL)
 		return 1;
 
+	if (ata_12_16_cmd(scmd))
+		scsi_internal_device_unblock(scmd->device, SDEV_RUNNING);
+
 	mpi_request = mpt3sas_base_get_msg_frame(ioc, smid);
 
 	if (mpi_reply == NULL) {
diff --git a/drivers/thermal/intel_powerclamp.c b/drivers/thermal/intel_powerclamp.c
index 7a223074df3d..afada655f861 100644
--- a/drivers/thermal/intel_powerclamp.c
+++ b/drivers/thermal/intel_powerclamp.c
@@ -669,9 +669,16 @@ static struct thermal_cooling_device_ops powerclamp_cooling_ops = {
 	.set_cur_state = powerclamp_set_cur_state,
 };
 
+static const struct x86_cpu_id __initconst intel_powerclamp_ids[] = {
+	{ X86_VENDOR_INTEL, X86_FAMILY_ANY, X86_MODEL_ANY, X86_FEATURE_MWAIT },
+	{}
+};
+MODULE_DEVICE_TABLE(x86cpu, intel_powerclamp_ids);
+
 static int __init powerclamp_probe(void)
 {
-	if (!boot_cpu_has(X86_FEATURE_MWAIT)) {
+
+	if (!x86_match_cpu(intel_powerclamp_ids)) {
 		pr_err("CPU does not support MWAIT");
 		return -ENODEV;
 	}
diff --git a/drivers/usb/chipidea/core.c b/drivers/usb/chipidea/core.c
index 69426e644d17..3dbb4a21ab44 100644
--- a/drivers/usb/chipidea/core.c
+++ b/drivers/usb/chipidea/core.c
@@ -914,6 +914,7 @@ static int ci_hdrc_probe(struct platform_device *pdev)
 	if (!ci)
 		return -ENOMEM;
 
+	spin_lock_init(&ci->lock);
 	ci->dev = dev;
 	ci->platdata = dev_get_platdata(dev);
 	ci->imx28_write_fix = !!(ci->platdata->flags &
diff --git a/drivers/usb/chipidea/udc.c b/drivers/usb/chipidea/udc.c
index b93356834bb5..bced28fa1cbd 100644
--- a/drivers/usb/chipidea/udc.c
+++ b/drivers/usb/chipidea/udc.c
@@ -1895,8 +1895,6 @@ static int udc_start(struct ci_hdrc *ci)
 	struct usb_otg_caps *otg_caps = &ci->platdata->ci_otg_caps;
 	int retval = 0;
 
-	spin_lock_init(&ci->lock);
-
 	ci->gadget.ops          = &usb_gadget_ops;
 	ci->gadget.speed        = USB_SPEED_UNKNOWN;
 	ci->gadget.max_speed    = USB_SPEED_HIGH;
diff --git a/drivers/usb/serial/cp210x.c b/drivers/usb/serial/cp210x.c
index f61477bed3a8..243ac5ebe46a 100644
--- a/drivers/usb/serial/cp210x.c
+++ b/drivers/usb/serial/cp210x.c
@@ -131,6 +131,7 @@ static const struct usb_device_id id_table[] = {
 	{ USB_DEVICE(0x10C4, 0x88A4) }, /* MMB Networks ZigBee USB Device */
 	{ USB_DEVICE(0x10C4, 0x88A5) }, /* Planet Innovation Ingeni ZigBee USB Device */
 	{ USB_DEVICE(0x10C4, 0x8946) }, /* Ketra N1 Wireless Interface */
+	{ USB_DEVICE(0x10C4, 0x8962) }, /* Brim Brothers charging dock */
 	{ USB_DEVICE(0x10C4, 0x8977) },	/* CEL MeshWorks DevKit Device */
 	{ USB_DEVICE(0x10C4, 0x8998) }, /* KCF Technologies PRN */
 	{ USB_DEVICE(0x10C4, 0x8A2A) }, /* HubZ dual ZigBee and Z-Wave dongle */
diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c
index 0ff7f38d7800..6e9fc8bcc285 100644
--- a/drivers/usb/serial/ftdi_sio.c
+++ b/drivers/usb/serial/ftdi_sio.c
@@ -1012,6 +1012,8 @@ static const struct usb_device_id id_table_combined[] = {
 	{ USB_DEVICE(ICPDAS_VID, ICPDAS_I7561U_PID) },
 	{ USB_DEVICE(ICPDAS_VID, ICPDAS_I7563U_PID) },
 	{ USB_DEVICE(WICED_VID, WICED_USB20706V2_PID) },
+	{ USB_DEVICE(TI_VID, TI_CC3200_LAUNCHPAD_PID),
+		.driver_info = (kernel_ulong_t)&ftdi_jtag_quirk },
 	{ }					/* Terminating entry */
 };
 
diff --git a/drivers/usb/serial/ftdi_sio_ids.h b/drivers/usb/serial/ftdi_sio_ids.h
index 21011c0a4c64..48ee04c94a75 100644
--- a/drivers/usb/serial/ftdi_sio_ids.h
+++ b/drivers/usb/serial/ftdi_sio_ids.h
@@ -596,6 +596,12 @@
 #define STK541_PID		0x2109 /* Zigbee Controller */
 
 /*
+ * Texas Instruments
+ */
+#define TI_VID			0x0451
+#define TI_CC3200_LAUNCHPAD_PID	0xC32A /* SimpleLink Wi-Fi CC3200 LaunchPad */
+
+/*
  * Blackfin gnICE JTAG
  * http://docs.blackfin.uclinux.org/doku.php?id=hw:jtag:gnice
  */
diff --git a/drivers/usb/storage/transport.c b/drivers/usb/storage/transport.c
index ffd086733421..1a59f335b063 100644
--- a/drivers/usb/storage/transport.c
+++ b/drivers/usb/storage/transport.c
@@ -954,10 +954,15 @@ int usb_stor_CB_transport(struct scsi_cmnd *srb, struct us_data *us)
 
 	/* COMMAND STAGE */
 	/* let's send the command via the control pipe */
+	/*
+	 * Command is sometime (f.e. after scsi_eh_prep_cmnd) on the stack.
+	 * Stack may be vmallocated.  So no DMA for us.  Make a copy.
+	 */
+	memcpy(us->iobuf, srb->cmnd, srb->cmd_len);
 	result = usb_stor_ctrl_transfer(us, us->send_ctrl_pipe,
 				      US_CBI_ADSC, 
 				      USB_TYPE_CLASS | USB_RECIP_INTERFACE, 0, 
-				      us->ifnum, srb->cmnd, srb->cmd_len);
+				      us->ifnum, us->iobuf, srb->cmd_len);
 
 	/* check the return code for the command */
 	usb_stor_dbg(us, "Call to usb_stor_ctrl_transfer() returned %d\n",
diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c
index 52a28311e2a4..48efe62e1302 100644
--- a/fs/nfs/callback.c
+++ b/fs/nfs/callback.c
@@ -261,7 +261,7 @@ static int nfs_callback_up_net(int minorversion, struct svc_serv *serv,
 	}
 
 	ret = -EPROTONOSUPPORT;
-	if (minorversion == 0)
+	if (!IS_ENABLED(CONFIG_NFS_V4_1) || minorversion == 0)
 		ret = nfs4_callback_up_net(serv, net);
 	else if (xprt->ops->bc_up)
 		ret = xprt->ops->bc_up(serv, net);
diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h
index 2d9b650047a5..d49e26c6cdc7 100644
--- a/include/linux/intel-iommu.h
+++ b/include/linux/intel-iommu.h
@@ -429,6 +429,7 @@ struct intel_iommu {
 	struct page_req_dsc *prq;
 	unsigned char prq_name[16];    /* Name for PRQ interrupt */
 	struct idr pasid_idr;
+	u32 pasid_max;
 #endif
 	struct q_inval  *qi;            /* Queued invalidation info */
 	u32 *iommu_state; /* Store iommu states between suspend and resume.*/
diff --git a/kernel/events/core.c b/kernel/events/core.c
index fc9bb2225291..f8c5f5ec666e 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -7908,6 +7908,7 @@ restart:
  * if <size> is not specified, the range is treated as a single address.
  */
 enum {
+	IF_ACT_NONE = -1,
 	IF_ACT_FILTER,
 	IF_ACT_START,
 	IF_ACT_STOP,
@@ -7931,6 +7932,7 @@ static const match_table_t if_tokens = {
 	{ IF_SRC_KERNEL,	"%u/%u" },
 	{ IF_SRC_FILEADDR,	"%u@%s" },
 	{ IF_SRC_KERNELADDR,	"%u" },
+	{ IF_ACT_NONE,		NULL },
 };
 
 /*
diff --git a/lib/mpi/mpi-pow.c b/lib/mpi/mpi-pow.c
index 5464c8744ea9..e24388a863a7 100644
--- a/lib/mpi/mpi-pow.c
+++ b/lib/mpi/mpi-pow.c
@@ -64,8 +64,13 @@ int mpi_powm(MPI res, MPI base, MPI exp, MPI mod)
 	if (!esize) {
 		/* Exponent is zero, result is 1 mod MOD, i.e., 1 or 0
 		 * depending on if MOD equals 1.  */
-		rp[0] = 1;
 		res->nlimbs = (msize == 1 && mod->d[0] == 1) ? 0 : 1;
+		if (res->nlimbs) {
+			if (mpi_resize(res, 1) < 0)
+				goto enomem;
+			rp = res->d;
+			rp[0] = 1;
+		}
 		res->sign = 0;
 		goto leave;
 	}
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index a2214c64ed3c..7401e996009a 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -3161,6 +3161,16 @@ should_compact_retry(struct alloc_context *ac, unsigned int order, int alloc_fla
 	if (!order || order > PAGE_ALLOC_COSTLY_ORDER)
 		return false;
 
+#ifdef CONFIG_COMPACTION
+	/*
+	 * This is a gross workaround to compensate a lack of reliable compaction
+	 * operation. We cannot simply go OOM with the current state of the compaction
+	 * code because this can lead to pre mature OOM declaration.
+	 */
+	if (order <= PAGE_ALLOC_COSTLY_ORDER)
+		return true;
+#endif
+
 	/*
 	 * There are setups with compaction disabled which would prefer to loop
 	 * inside the allocator rather than hit the oom killer prematurely.
diff --git a/net/can/bcm.c b/net/can/bcm.c
index 8af9d25ff988..436a7537e6a9 100644
--- a/net/can/bcm.c
+++ b/net/can/bcm.c
@@ -77,7 +77,7 @@
 		     (CAN_EFF_MASK | CAN_EFF_FLAG | CAN_RTR_FLAG) : \
 		     (CAN_SFF_MASK | CAN_EFF_FLAG | CAN_RTR_FLAG))
 
-#define CAN_BCM_VERSION "20160617"
+#define CAN_BCM_VERSION "20161123"
 
 MODULE_DESCRIPTION("PF_CAN broadcast manager protocol");
 MODULE_LICENSE("Dual BSD/GPL");
@@ -109,8 +109,9 @@ struct bcm_op {
 	u32 count;
 	u32 nframes;
 	u32 currframe;
-	struct canfd_frame *frames;
-	struct canfd_frame *last_frames;
+	/* void pointers to arrays of struct can[fd]_frame */
+	void *frames;
+	void *last_frames;
 	struct canfd_frame sframe;
 	struct canfd_frame last_sframe;
 	struct sock *sk;
@@ -681,7 +682,7 @@ static void bcm_rx_handler(struct sk_buff *skb, void *data)
 
 	if (op->flags & RX_FILTER_ID) {
 		/* the easiest case */
-		bcm_rx_update_and_send(op, &op->last_frames[0], rxframe);
+		bcm_rx_update_and_send(op, op->last_frames, rxframe);
 		goto rx_starttimer;
 	}
 
@@ -1068,7 +1069,7 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 
 		if (msg_head->nframes) {
 			/* update CAN frames content */
-			err = memcpy_from_msg((u8 *)op->frames, msg,
+			err = memcpy_from_msg(op->frames, msg,
 					      msg_head->nframes * op->cfsiz);
 			if (err < 0)
 				return err;
@@ -1118,7 +1119,7 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 		}
 
 		if (msg_head->nframes) {
-			err = memcpy_from_msg((u8 *)op->frames, msg,
+			err = memcpy_from_msg(op->frames, msg,
 					      msg_head->nframes * op->cfsiz);
 			if (err < 0) {
 				if (op->frames != &op->sframe)
@@ -1163,6 +1164,7 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 	/* check flags */
 
 	if (op->flags & RX_RTR_FRAME) {
+		struct canfd_frame *frame0 = op->frames;
 
 		/* no timers in RTR-mode */
 		hrtimer_cancel(&op->thrtimer);
@@ -1174,8 +1176,8 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 		 * prevent a full-load-loopback-test ... ;-]
 		 */
 		if ((op->flags & TX_CP_CAN_ID) ||
-		    (op->frames[0].can_id == op->can_id))
-			op->frames[0].can_id = op->can_id & ~CAN_RTR_FLAG;
+		    (frame0->can_id == op->can_id))
+			frame0->can_id = op->can_id & ~CAN_RTR_FLAG;
 
 	} else {
 		if (op->flags & SETTIMER) {
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 5550a86f7264..396aac7e6e79 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -945,4 +945,4 @@ static int __init init_default_flow_dissectors(void)
 	return 0;
 }
 
-late_initcall_sync(init_default_flow_dissectors);
+core_initcall(init_default_flow_dissectors);
diff --git a/net/wireless/core.h b/net/wireless/core.h
index eee91443924d..66f2a1145d7c 100644
--- a/net/wireless/core.h
+++ b/net/wireless/core.h
@@ -71,6 +71,7 @@ struct cfg80211_registered_device {
 	struct list_head bss_list;
 	struct rb_root bss_tree;
 	u32 bss_generation;
+	u32 bss_entries;
 	struct cfg80211_scan_request *scan_req; /* protected by RTNL */
 	struct sk_buff *scan_msg;
 	struct cfg80211_sched_scan_request __rcu *sched_scan_req;
diff --git a/net/wireless/scan.c b/net/wireless/scan.c
index 0358e12be54b..438143a3827d 100644
--- a/net/wireless/scan.c
+++ b/net/wireless/scan.c
@@ -57,6 +57,19 @@
  * also linked into the probe response struct.
  */
 
+/*
+ * Limit the number of BSS entries stored in mac80211. Each one is
+ * a bit over 4k at most, so this limits to roughly 4-5M of memory.
+ * If somebody wants to really attack this though, they'd likely
+ * use small beacons, and only one type of frame, limiting each of
+ * the entries to a much smaller size (in order to generate more
+ * entries in total, so overhead is bigger.)
+ */
+static int bss_entries_limit = 1000;
+module_param(bss_entries_limit, int, 0644);
+MODULE_PARM_DESC(bss_entries_limit,
+                 "limit to number of scan BSS entries (per wiphy, default 1000)");
+
 #define IEEE80211_SCAN_RESULT_EXPIRE	(30 * HZ)
 
 static void bss_free(struct cfg80211_internal_bss *bss)
@@ -137,6 +150,10 @@ static bool __cfg80211_unlink_bss(struct cfg80211_registered_device *rdev,
 
 	list_del_init(&bss->list);
 	rb_erase(&bss->rbn, &rdev->bss_tree);
+	rdev->bss_entries--;
+	WARN_ONCE((rdev->bss_entries == 0) ^ list_empty(&rdev->bss_list),
+		  "rdev bss entries[%d]/list[empty:%d] corruption\n",
+		  rdev->bss_entries, list_empty(&rdev->bss_list));
 	bss_ref_put(rdev, bss);
 	return true;
 }
@@ -163,6 +180,40 @@ static void __cfg80211_bss_expire(struct cfg80211_registered_device *rdev,
 		rdev->bss_generation++;
 }
 
+static bool cfg80211_bss_expire_oldest(struct cfg80211_registered_device *rdev)
+{
+	struct cfg80211_internal_bss *bss, *oldest = NULL;
+	bool ret;
+
+	lockdep_assert_held(&rdev->bss_lock);
+
+	list_for_each_entry(bss, &rdev->bss_list, list) {
+		if (atomic_read(&bss->hold))
+			continue;
+
+		if (!list_empty(&bss->hidden_list) &&
+		    !bss->pub.hidden_beacon_bss)
+			continue;
+
+		if (oldest && time_before(oldest->ts, bss->ts))
+			continue;
+		oldest = bss;
+	}
+
+	if (WARN_ON(!oldest))
+		return false;
+
+	/*
+	 * The callers make sure to increase rdev->bss_generation if anything
+	 * gets removed (and a new entry added), so there's no need to also do
+	 * it here.
+	 */
+
+	ret = __cfg80211_unlink_bss(rdev, oldest);
+	WARN_ON(!ret);
+	return ret;
+}
+
 void ___cfg80211_scan_done(struct cfg80211_registered_device *rdev,
 			   bool send_message)
 {
@@ -693,6 +744,7 @@ static bool cfg80211_combine_bsses(struct cfg80211_registered_device *rdev,
 	const u8 *ie;
 	int i, ssidlen;
 	u8 fold = 0;
+	u32 n_entries = 0;
 
 	ies = rcu_access_pointer(new->pub.beacon_ies);
 	if (WARN_ON(!ies))
@@ -716,6 +768,12 @@ static bool cfg80211_combine_bsses(struct cfg80211_registered_device *rdev,
 	/* This is the bad part ... */
 
 	list_for_each_entry(bss, &rdev->bss_list, list) {
+		/*
+		 * we're iterating all the entries anyway, so take the
+		 * opportunity to validate the list length accounting
+		 */
+		n_entries++;
+
 		if (!ether_addr_equal(bss->pub.bssid, new->pub.bssid))
 			continue;
 		if (bss->pub.channel != new->pub.channel)
@@ -744,6 +802,10 @@ static bool cfg80211_combine_bsses(struct cfg80211_registered_device *rdev,
 				   new->pub.beacon_ies);
 	}
 
+	WARN_ONCE(n_entries != rdev->bss_entries,
+		  "rdev bss entries[%d]/list[len:%d] corruption\n",
+		  rdev->bss_entries, n_entries);
+
 	return true;
 }
 
@@ -898,7 +960,14 @@ cfg80211_bss_update(struct cfg80211_registered_device *rdev,
 			}
 		}
 
+		if (rdev->bss_entries >= bss_entries_limit &&
+		    !cfg80211_bss_expire_oldest(rdev)) {
+			kfree(new);
+			goto drop;
+		}
+
 		list_add_tail(&new->list, &rdev->bss_list);
+		rdev->bss_entries++;
 		rb_insert_bss(rdev, new);
 		found = new;
 	}
diff --git a/security/apparmor/domain.c b/security/apparmor/domain.c
index fc3036b34e51..a4d90aa1045a 100644
--- a/security/apparmor/domain.c
+++ b/security/apparmor/domain.c
@@ -621,8 +621,8 @@ int aa_change_hat(const char *hats[], int count, u64 token, bool permtest)
 	/* released below */
 	cred = get_current_cred();
 	cxt = cred_cxt(cred);
-	profile = aa_cred_profile(cred);
-	previous_profile = cxt->previous;
+	profile = aa_get_newest_profile(aa_cred_profile(cred));
+	previous_profile = aa_get_newest_profile(cxt->previous);
 
 	if (unconfined(profile)) {
 		info = "unconfined";
@@ -718,6 +718,8 @@ audit:
 out:
 	aa_put_profile(hat);
 	kfree(name);
+	aa_put_profile(profile);
+	aa_put_profile(previous_profile);
 	put_cred(cred);
 
 	return error;