Re: Linux 4.4.191

[Greg KH]

diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 7a9fd54a0186..5b94c0bfba85 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -3415,6 +3415,13 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			Run specified binary instead of /init from the ramdisk,
 			used for early userspace startup. See initrd.
 
+	rdrand=		[X86]
+			force - Override the decision by the kernel to hide the
+				advertisement of RDRAND support (this affects
+				certain AMD processors because of buggy BIOS
+				support, specifically around the suspend/resume
+				path).
+
 	reboot=		[KNL]
 			Format (x86 or x86_64):
 				[w[arm] | c[old] | h[ard] | s[oft] | g[pio]] \
diff --git a/Documentation/siphash.txt b/Documentation/siphash.txt
new file mode 100644
index 000000000000..908d348ff777
--- /dev/null
+++ b/Documentation/siphash.txt
@@ -0,0 +1,175 @@
+         SipHash - a short input PRF
+-----------------------------------------------
+Written by Jason A. Donenfeld <jason@xxxxxxxxx>
+
+SipHash is a cryptographically secure PRF -- a keyed hash function -- that
+performs very well for short inputs, hence the name. It was designed by
+cryptographers Daniel J. Bernstein and Jean-Philippe Aumasson. It is intended
+as a replacement for some uses of: `jhash`, `md5_transform`, `sha_transform`,
+and so forth.
+
+SipHash takes a secret key filled with randomly generated numbers and either
+an input buffer or several input integers. It spits out an integer that is
+indistinguishable from random. You may then use that integer as part of secure
+sequence numbers, secure cookies, or mask it off for use in a hash table.
+
+1. Generating a key
+
+Keys should always be generated from a cryptographically secure source of
+random numbers, either using get_random_bytes or get_random_once:
+
+siphash_key_t key;
+get_random_bytes(&key, sizeof(key));
+
+If you're not deriving your key from here, you're doing it wrong.
+
+2. Using the functions
+
+There are two variants of the function, one that takes a list of integers, and
+one that takes a buffer:
+
+u64 siphash(const void *data, size_t len, const siphash_key_t *key);
+
+And:
+
+u64 siphash_1u64(u64, const siphash_key_t *key);
+u64 siphash_2u64(u64, u64, const siphash_key_t *key);
+u64 siphash_3u64(u64, u64, u64, const siphash_key_t *key);
+u64 siphash_4u64(u64, u64, u64, u64, const siphash_key_t *key);
+u64 siphash_1u32(u32, const siphash_key_t *key);
+u64 siphash_2u32(u32, u32, const siphash_key_t *key);
+u64 siphash_3u32(u32, u32, u32, const siphash_key_t *key);
+u64 siphash_4u32(u32, u32, u32, u32, const siphash_key_t *key);
+
+If you pass the generic siphash function something of a constant length, it
+will constant fold at compile-time and automatically choose one of the
+optimized functions.
+
+3. Hashtable key function usage:
+
+struct some_hashtable {
+	DECLARE_HASHTABLE(hashtable, 8);
+	siphash_key_t key;
+};
+
+void init_hashtable(struct some_hashtable *table)
+{
+	get_random_bytes(&table->key, sizeof(table->key));
+}
+
+static inline hlist_head *some_hashtable_bucket(struct some_hashtable *table, struct interesting_input *input)
+{
+	return &table->hashtable[siphash(input, sizeof(*input), &table->key) & (HASH_SIZE(table->hashtable) - 1)];
+}
+
+You may then iterate like usual over the returned hash bucket.
+
+4. Security
+
+SipHash has a very high security margin, with its 128-bit key. So long as the
+key is kept secret, it is impossible for an attacker to guess the outputs of
+the function, even if being able to observe many outputs, since 2^128 outputs
+is significant.
+
+Linux implements the "2-4" variant of SipHash.
+
+5. Struct-passing Pitfalls
+
+Often times the XuY functions will not be large enough, and instead you'll
+want to pass a pre-filled struct to siphash. When doing this, it's important
+to always ensure the struct has no padding holes. The easiest way to do this
+is to simply arrange the members of the struct in descending order of size,
+and to use offsetendof() instead of sizeof() for getting the size. For
+performance reasons, if possible, it's probably a good thing to align the
+struct to the right boundary. Here's an example:
+
+const struct {
+	struct in6_addr saddr;
+	u32 counter;
+	u16 dport;
+} __aligned(SIPHASH_ALIGNMENT) combined = {
+	.saddr = *(struct in6_addr *)saddr,
+	.counter = counter,
+	.dport = dport
+};
+u64 h = siphash(&combined, offsetofend(typeof(combined), dport), &secret);
+
+6. Resources
+
+Read the SipHash paper if you're interested in learning more:
+https://131002.net/siphash/siphash.pdf
+
+
+~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~
+
+HalfSipHash - SipHash's insecure younger cousin
+-----------------------------------------------
+Written by Jason A. Donenfeld <jason@xxxxxxxxx>
+
+On the off-chance that SipHash is not fast enough for your needs, you might be
+able to justify using HalfSipHash, a terrifying but potentially useful
+possibility. HalfSipHash cuts SipHash's rounds down from "2-4" to "1-3" and,
+even scarier, uses an easily brute-forcable 64-bit key (with a 32-bit output)
+instead of SipHash's 128-bit key. However, this may appeal to some
+high-performance `jhash` users.
+
+Danger!
+
+Do not ever use HalfSipHash except for as a hashtable key function, and only
+then when you can be absolutely certain that the outputs will never be
+transmitted out of the kernel. This is only remotely useful over `jhash` as a
+means of mitigating hashtable flooding denial of service attacks.
+
+1. Generating a key
+
+Keys should always be generated from a cryptographically secure source of
+random numbers, either using get_random_bytes or get_random_once:
+
+hsiphash_key_t key;
+get_random_bytes(&key, sizeof(key));
+
+If you're not deriving your key from here, you're doing it wrong.
+
+2. Using the functions
+
+There are two variants of the function, one that takes a list of integers, and
+one that takes a buffer:
+
+u32 hsiphash(const void *data, size_t len, const hsiphash_key_t *key);
+
+And:
+
+u32 hsiphash_1u32(u32, const hsiphash_key_t *key);
+u32 hsiphash_2u32(u32, u32, const hsiphash_key_t *key);
+u32 hsiphash_3u32(u32, u32, u32, const hsiphash_key_t *key);
+u32 hsiphash_4u32(u32, u32, u32, u32, const hsiphash_key_t *key);
+
+If you pass the generic hsiphash function something of a constant length, it
+will constant fold at compile-time and automatically choose one of the
+optimized functions.
+
+3. Hashtable key function usage:
+
+struct some_hashtable {
+	DECLARE_HASHTABLE(hashtable, 8);
+	hsiphash_key_t key;
+};
+
+void init_hashtable(struct some_hashtable *table)
+{
+	get_random_bytes(&table->key, sizeof(table->key));
+}
+
+static inline hlist_head *some_hashtable_bucket(struct some_hashtable *table, struct interesting_input *input)
+{
+	return &table->hashtable[hsiphash(input, sizeof(*input), &table->key) & (HASH_SIZE(table->hashtable) - 1)];
+}
+
+You may then iterate like usual over the returned hash bucket.
+
+4. Performance
+
+HalfSipHash is roughly 3 times slower than JenkinsHash. For many replacements,
+this will not be a problem, as the hashtable lookup isn't the bottleneck. And
+in general, this is probably a good sacrifice to make for the security and DoS
+resistance of HalfSipHash.
diff --git a/MAINTAINERS b/MAINTAINERS
index f4d4a5544dc1..20a31b357929 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -9749,6 +9749,13 @@ F:	arch/arm/mach-s3c24xx/mach-bast.c
 F:	arch/arm/mach-s3c24xx/bast-ide.c
 F:	arch/arm/mach-s3c24xx/bast-irq.c
 
+SIPHASH PRF ROUTINES
+M:	Jason A. Donenfeld <Jason@xxxxxxxxx>
+S:	Maintained
+F:	lib/siphash.c
+F:	lib/test_siphash.c
+F:	include/linux/siphash.h
+
 TI DAVINCI MACHINE SUPPORT
 M:	Sekhar Nori <nsekhar@xxxxxx>
 M:	Kevin Hilman <khilman@xxxxxxxxxxxxxxxxxxx>
diff --git a/Makefile b/Makefile
index 83acf2d6c55e..266c3d7e0120 100644
--- a/Makefile
+++ b/Makefile
@@ -1,6 +1,6 @@
 VERSION = 4
 PATCHLEVEL = 4
-SUBLEVEL = 190
+SUBLEVEL = 191
 EXTRAVERSION =
 NAME = Blurry Fish Butt
 
diff --git a/arch/mips/kernel/i8253.c b/arch/mips/kernel/i8253.c
index c5bc344fc745..73039746ae36 100644
--- a/arch/mips/kernel/i8253.c
+++ b/arch/mips/kernel/i8253.c
@@ -31,7 +31,8 @@ void __init setup_pit_timer(void)
 
 static int __init init_pit_clocksource(void)
 {
-	if (num_possible_cpus() > 1) /* PIT does not scale! */
+	if (num_possible_cpus() > 1 || /* PIT does not scale! */
+	    !clockevent_state_periodic(&i8253_clockevent))
 		return 0;
 
 	return clocksource_i8253_init();
diff --git a/arch/x86/include/asm/bootparam_utils.h b/arch/x86/include/asm/bootparam_utils.h
index 4a8cb8d7cbd5..0232b5a2a2d9 100644
--- a/arch/x86/include/asm/bootparam_utils.h
+++ b/arch/x86/include/asm/bootparam_utils.h
@@ -17,6 +17,20 @@
  * Note: efi_info is commonly left uninitialized, but that field has a
  * private magic, so it is better to leave it unchanged.
  */
+
+#define sizeof_mbr(type, member) ({ sizeof(((type *)0)->member); })
+
+#define BOOT_PARAM_PRESERVE(struct_member)				\
+	{								\
+		.start = offsetof(struct boot_params, struct_member),	\
+		.len   = sizeof_mbr(struct boot_params, struct_member),	\
+	}
+
+struct boot_params_to_save {
+	unsigned int start;
+	unsigned int len;
+};
+
 static void sanitize_boot_params(struct boot_params *boot_params)
 {
 	/* 
@@ -35,19 +49,39 @@ static void sanitize_boot_params(struct boot_params *boot_params)
 	 */
 	if (boot_params->sentinel) {
 		/* fields in boot_params are left uninitialized, clear them */
-		memset(&boot_params->ext_ramdisk_image, 0,
-		       (char *)&boot_params->efi_info -
-			(char *)&boot_params->ext_ramdisk_image);
-		memset(&boot_params->kbd_status, 0,
-		       (char *)&boot_params->hdr -
-		       (char *)&boot_params->kbd_status);
-		memset(&boot_params->_pad7[0], 0,
-		       (char *)&boot_params->edd_mbr_sig_buffer[0] -
-			(char *)&boot_params->_pad7[0]);
-		memset(&boot_params->_pad8[0], 0,
-		       (char *)&boot_params->eddbuf[0] -
-			(char *)&boot_params->_pad8[0]);
-		memset(&boot_params->_pad9[0], 0, sizeof(boot_params->_pad9));
+		static struct boot_params scratch;
+		char *bp_base = (char *)boot_params;
+		char *save_base = (char *)&scratch;
+		int i;
+
+		const struct boot_params_to_save to_save[] = {
+			BOOT_PARAM_PRESERVE(screen_info),
+			BOOT_PARAM_PRESERVE(apm_bios_info),
+			BOOT_PARAM_PRESERVE(tboot_addr),
+			BOOT_PARAM_PRESERVE(ist_info),
+			BOOT_PARAM_PRESERVE(hd0_info),
+			BOOT_PARAM_PRESERVE(hd1_info),
+			BOOT_PARAM_PRESERVE(sys_desc_table),
+			BOOT_PARAM_PRESERVE(olpc_ofw_header),
+			BOOT_PARAM_PRESERVE(efi_info),
+			BOOT_PARAM_PRESERVE(alt_mem_k),
+			BOOT_PARAM_PRESERVE(scratch),
+			BOOT_PARAM_PRESERVE(e820_entries),
+			BOOT_PARAM_PRESERVE(eddbuf_entries),
+			BOOT_PARAM_PRESERVE(edd_mbr_sig_buf_entries),
+			BOOT_PARAM_PRESERVE(edd_mbr_sig_buffer),
+			BOOT_PARAM_PRESERVE(hdr),
+			BOOT_PARAM_PRESERVE(eddbuf),
+		};
+
+		memset(&scratch, 0, sizeof(scratch));
+
+		for (i = 0; i < ARRAY_SIZE(to_save); i++) {
+			memcpy(save_base + to_save[i].start,
+			       bp_base + to_save[i].start, to_save[i].len);
+		}
+
+		memcpy(boot_params, save_base, sizeof(*boot_params));
 	}
 }
 
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index d4f5b8209393..30183770132a 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -311,6 +311,7 @@
 #define MSR_AMD64_PATCH_LEVEL		0x0000008b
 #define MSR_AMD64_TSC_RATIO		0xc0000104
 #define MSR_AMD64_NB_CFG		0xc001001f
+#define MSR_AMD64_CPUID_FN_1		0xc0011004
 #define MSR_AMD64_PATCH_LOADER		0xc0010020
 #define MSR_AMD64_OSVW_ID_LENGTH	0xc0010140
 #define MSR_AMD64_OSVW_STATUS		0xc0010141
diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h
index 5a10ac8c131e..20f822fec8af 100644
--- a/arch/x86/include/asm/msr.h
+++ b/arch/x86/include/asm/msr.h
@@ -32,6 +32,16 @@ struct msr_regs_info {
 	int err;
 };
 
+struct saved_msr {
+	bool valid;
+	struct msr_info info;
+};
+
+struct saved_msrs {
+	unsigned int num;
+	struct saved_msr *array;
+};
+
 static inline unsigned long long native_read_tscp(unsigned int *aux)
 {
 	unsigned long low, high;
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index e58c078f3d96..c3138ac80db2 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -151,7 +151,7 @@
 	"    	lfence;\n"					\
 	"       jmp    902b;\n"					\
 	"       .align 16\n"					\
-	"903:	addl   $4, %%esp;\n"				\
+	"903:	lea    4(%%esp), %%esp;\n"			\
 	"       pushl  %[thunk_target];\n"			\
 	"       ret;\n"						\
 	"       .align 16\n"					\
diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h
index 6271281f947d..0d8e0831b1a0 100644
--- a/arch/x86/include/asm/ptrace.h
+++ b/arch/x86/include/asm/ptrace.h
@@ -121,9 +121,9 @@ static inline int v8086_mode(struct pt_regs *regs)
 #endif
 }
 
-#ifdef CONFIG_X86_64
 static inline bool user_64bit_mode(struct pt_regs *regs)
 {
+#ifdef CONFIG_X86_64
 #ifndef CONFIG_PARAVIRT
 	/*
 	 * On non-paravirt systems, this is the only long mode CPL 3
@@ -134,8 +134,12 @@ static inline bool user_64bit_mode(struct pt_regs *regs)
 	/* Headers are too twisted for this to go in paravirt.h. */
 	return regs->cs == __USER_CS || regs->cs == pv_info.extra_user_64bit_cs;
 #endif
+#else /* !CONFIG_X86_64 */
+	return false;
+#endif
 }
 
+#ifdef CONFIG_X86_64
 #define current_user_stack_pointer()	current_pt_regs()->sp
 #define compat_user_stack_pointer()	current_pt_regs()->sp
 #endif
diff --git a/arch/x86/include/asm/suspend_32.h b/arch/x86/include/asm/suspend_32.h
index d1793f06854d..8e9dbe7b73a1 100644
--- a/arch/x86/include/asm/suspend_32.h
+++ b/arch/x86/include/asm/suspend_32.h
@@ -15,6 +15,7 @@ struct saved_context {
 	unsigned long cr0, cr2, cr3, cr4;
 	u64 misc_enable;
 	bool misc_enable_saved;
+	struct saved_msrs saved_msrs;
 	struct desc_ptr gdt_desc;
 	struct desc_ptr idt;
 	u16 ldt;
diff --git a/arch/x86/include/asm/suspend_64.h b/arch/x86/include/asm/suspend_64.h
index 7ebf0ebe4e68..6136a18152af 100644
--- a/arch/x86/include/asm/suspend_64.h
+++ b/arch/x86/include/asm/suspend_64.h
@@ -24,6 +24,7 @@ struct saved_context {
 	unsigned long cr0, cr2, cr3, cr4, cr8;
 	u64 misc_enable;
 	bool misc_enable_saved;
+	struct saved_msrs saved_msrs;
 	unsigned long efer;
 	u16 gdt_pad; /* Unused */
 	struct desc_ptr gdt_desc;
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index cc6c33249850..80c94fc8ad5a 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -593,7 +593,7 @@ static __initdata unsigned long lapic_cal_pm1, lapic_cal_pm2;
 static __initdata unsigned long lapic_cal_j1, lapic_cal_j2;
 
 /*
- * Temporary interrupt handler.
+ * Temporary interrupt handler and polled calibration function.
  */
 static void __init lapic_cal_handler(struct clock_event_device *dev)
 {
@@ -677,7 +677,8 @@ calibrate_by_pmtimer(long deltapm, long *delta, long *deltatsc)
 static int __init calibrate_APIC_clock(void)
 {
 	struct clock_event_device *levt = this_cpu_ptr(&lapic_events);
-	void (*real_handler)(struct clock_event_device *dev);
+	u64 tsc_perj = 0, tsc_start = 0;
+	unsigned long jif_start;
 	unsigned long deltaj;
 	long delta, deltatsc;
 	int pm_referenced = 0;
@@ -706,28 +707,64 @@ static int __init calibrate_APIC_clock(void)
 	apic_printk(APIC_VERBOSE, "Using local APIC timer interrupts.\n"
 		    "calibrating APIC timer ...\n");
 
+	/*
+	 * There are platforms w/o global clockevent devices. Instead of
+	 * making the calibration conditional on that, use a polling based
+	 * approach everywhere.
+	 */
 	local_irq_disable();
 
-	/* Replace the global interrupt handler */
-	real_handler = global_clock_event->event_handler;
-	global_clock_event->event_handler = lapic_cal_handler;
-
 	/*
 	 * Setup the APIC counter to maximum. There is no way the lapic
 	 * can underflow in the 100ms detection time frame
 	 */
 	__setup_APIC_LVTT(0xffffffff, 0, 0);
 
-	/* Let the interrupts run */
+	/*
+	 * Methods to terminate the calibration loop:
+	 *  1) Global clockevent if available (jiffies)
+	 *  2) TSC if available and frequency is known
+	 */
+	jif_start = READ_ONCE(jiffies);
+
+	if (tsc_khz) {
+		tsc_start = rdtsc();
+		tsc_perj = div_u64((u64)tsc_khz * 1000, HZ);
+	}
+
+	/*
+	 * Enable interrupts so the tick can fire, if a global
+	 * clockevent device is available
+	 */
 	local_irq_enable();
 
-	while (lapic_cal_loops <= LAPIC_CAL_LOOPS)
-		cpu_relax();
+	while (lapic_cal_loops <= LAPIC_CAL_LOOPS) {
+		/* Wait for a tick to elapse */
+		while (1) {
+			if (tsc_khz) {
+				u64 tsc_now = rdtsc();
+				if ((tsc_now - tsc_start) >= tsc_perj) {
+					tsc_start += tsc_perj;
+					break;
+				}
+			} else {
+				unsigned long jif_now = READ_ONCE(jiffies);
 
-	local_irq_disable();
+				if (time_after(jif_now, jif_start)) {
+					jif_start = jif_now;
+					break;
+				}
+			}
+			cpu_relax();
+		}
 
-	/* Restore the real event handler */
-	global_clock_event->event_handler = real_handler;
+		/* Invoke the calibration routine */
+		local_irq_disable();
+		lapic_cal_handler(NULL);
+		local_irq_enable();
+	}
+
+	local_irq_disable();
 
 	/* Build delta t1-t2 as apic timer counts down */
 	delta = lapic_cal_t1 - lapic_cal_t2;
@@ -778,10 +815,11 @@ static int __init calibrate_APIC_clock(void)
 	levt->features &= ~CLOCK_EVT_FEAT_DUMMY;
 
 	/*
-	 * PM timer calibration failed or not turned on
-	 * so lets try APIC timer based calibration
+	 * PM timer calibration failed or not turned on so lets try APIC
+	 * timer based calibration, if a global clockevent device is
+	 * available.
 	 */
-	if (!pm_referenced) {
+	if (!pm_referenced && global_clock_event) {
 		apic_printk(APIC_VERBOSE, "... verify APIC timer\n");
 
 		/*
@@ -993,6 +1031,10 @@ void clear_local_APIC(void)
 	apic_write(APIC_LVT0, v | APIC_LVT_MASKED);
 	v = apic_read(APIC_LVT1);
 	apic_write(APIC_LVT1, v | APIC_LVT_MASKED);
+	if (!x2apic_enabled()) {
+		v = apic_read(APIC_LDR) & ~APIC_LDR_MASK;
+		apic_write(APIC_LDR, v);
+	}
 	if (maxlvt >= 4) {
 		v = apic_read(APIC_LVTPC);
 		apic_write(APIC_LVTPC, v | APIC_LVT_MASKED);
diff --git a/arch/x86/kernel/apic/bigsmp_32.c b/arch/x86/kernel/apic/bigsmp_32.c
index 971cf8875939..d75f665dd022 100644
--- a/arch/x86/kernel/apic/bigsmp_32.c
+++ b/arch/x86/kernel/apic/bigsmp_32.c
@@ -37,32 +37,12 @@ static int bigsmp_early_logical_apicid(int cpu)
 	return early_per_cpu(x86_cpu_to_apicid, cpu);
 }
 
-static inline unsigned long calculate_ldr(int cpu)
-{
-	unsigned long val, id;
-
-	val = apic_read(APIC_LDR) & ~APIC_LDR_MASK;
-	id = per_cpu(x86_bios_cpu_apicid, cpu);
-	val |= SET_APIC_LOGICAL_ID(id);
-
-	return val;
-}
-
 /*
- * Set up the logical destination ID.
- *
- * Intel recommends to set DFR, LDR and TPR before enabling
- * an APIC.  See e.g. "AP-388 82489DX User's Manual" (Intel
- * document number 292116).  So here it goes...
+ * bigsmp enables physical destination mode
+ * and doesn't use LDR and DFR
  */
 static void bigsmp_init_apic_ldr(void)
 {
-	unsigned long val;
-	int cpu = smp_processor_id();
-
-	apic_write(APIC_DFR, APIC_DFR_FLAT);
-	val = calculate_ldr(cpu);
-	apic_write(APIC_LDR, val);
 }
 
 static void bigsmp_setup_apic_routing(void)
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 6f2483292de0..424d8a636615 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -684,6 +684,64 @@ static void init_amd_ln(struct cpuinfo_x86 *c)
 	msr_set_bit(MSR_AMD64_DE_CFG, 31);
 }
 
+static bool rdrand_force;
+
+static int __init rdrand_cmdline(char *str)
+{
+	if (!str)
+		return -EINVAL;
+
+	if (!strcmp(str, "force"))
+		rdrand_force = true;
+	else
+		return -EINVAL;
+
+	return 0;
+}
+early_param("rdrand", rdrand_cmdline);
+
+static void clear_rdrand_cpuid_bit(struct cpuinfo_x86 *c)
+{
+	/*
+	 * Saving of the MSR used to hide the RDRAND support during
+	 * suspend/resume is done by arch/x86/power/cpu.c, which is
+	 * dependent on CONFIG_PM_SLEEP.
+	 */
+	if (!IS_ENABLED(CONFIG_PM_SLEEP))
+		return;
+
+	/*
+	 * The nordrand option can clear X86_FEATURE_RDRAND, so check for
+	 * RDRAND support using the CPUID function directly.
+	 */
+	if (!(cpuid_ecx(1) & BIT(30)) || rdrand_force)
+		return;
+
+	msr_clear_bit(MSR_AMD64_CPUID_FN_1, 62);
+
+	/*
+	 * Verify that the CPUID change has occurred in case the kernel is
+	 * running virtualized and the hypervisor doesn't support the MSR.
+	 */
+	if (cpuid_ecx(1) & BIT(30)) {
+		pr_info_once("BIOS may not properly restore RDRAND after suspend, but hypervisor does not support hiding RDRAND via CPUID.\n");
+		return;
+	}
+
+	clear_cpu_cap(c, X86_FEATURE_RDRAND);
+	pr_info_once("BIOS may not properly restore RDRAND after suspend, hiding RDRAND via CPUID. Use rdrand=force to reenable.\n");
+}
+
+static void init_amd_jg(struct cpuinfo_x86 *c)
+{
+	/*
+	 * Some BIOS implementations do not restore proper RDRAND support
+	 * across suspend and resume. Check on whether to hide the RDRAND
+	 * instruction support via CPUID.
+	 */
+	clear_rdrand_cpuid_bit(c);
+}
+
 static void init_amd_bd(struct cpuinfo_x86 *c)
 {
 	u64 value;
@@ -711,6 +769,13 @@ static void init_amd_bd(struct cpuinfo_x86 *c)
 			wrmsrl_safe(0xc0011021, value);
 		}
 	}
+
+	/*
+	 * Some BIOS implementations do not restore proper RDRAND support
+	 * across suspend and resume. Check on whether to hide the RDRAND
+	 * instruction support via CPUID.
+	 */
+	clear_rdrand_cpuid_bit(c);
 }
 
 static void init_amd_zn(struct cpuinfo_x86 *c)
@@ -755,6 +820,7 @@ static void init_amd(struct cpuinfo_x86 *c)
 	case 0x10: init_amd_gh(c); break;
 	case 0x12: init_amd_ln(c); break;
 	case 0x15: init_amd_bd(c); break;
+	case 0x16: init_amd_jg(c); break;
 	case 0x17: init_amd_zn(c); break;
 	}
 
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index 1ca929767a1b..0b6d27dfc234 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -698,11 +698,10 @@ static unsigned long ptrace_get_debugreg(struct task_struct *tsk, int n)
 {
 	struct thread_struct *thread = &tsk->thread;
 	unsigned long val = 0;
-	int index = n;
 
 	if (n < HBP_NUM) {
+		int index = array_index_nospec(n, HBP_NUM);
 		struct perf_event *bp = thread->ptrace_bps[index];
-		index = array_index_nospec(index, HBP_NUM);
 
 		if (bp)
 			val = bp->hw.info.address;
diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c
index b8105289c60b..178d63cac321 100644
--- a/arch/x86/kernel/uprobes.c
+++ b/arch/x86/kernel/uprobes.c
@@ -514,9 +514,12 @@ struct uprobe_xol_ops {
 	void	(*abort)(struct arch_uprobe *, struct pt_regs *);
 };
 
-static inline int sizeof_long(void)
+static inline int sizeof_long(struct pt_regs *regs)
 {
-	return is_ia32_task() ? 4 : 8;
+	/*
+	 * Check registers for mode as in_xxx_syscall() does not apply here.
+	 */
+	return user_64bit_mode(regs) ? 8 : 4;
 }
 
 static int default_pre_xol_op(struct arch_uprobe *auprobe, struct pt_regs *regs)
@@ -527,9 +530,9 @@ static int default_pre_xol_op(struct arch_uprobe *auprobe, struct pt_regs *regs)
 
 static int push_ret_address(struct pt_regs *regs, unsigned long ip)
 {
-	unsigned long new_sp = regs->sp - sizeof_long();
+	unsigned long new_sp = regs->sp - sizeof_long(regs);
 
-	if (copy_to_user((void __user *)new_sp, &ip, sizeof_long()))
+	if (copy_to_user((void __user *)new_sp, &ip, sizeof_long(regs)))
 		return -EFAULT;
 
 	regs->sp = new_sp;
@@ -562,7 +565,7 @@ static int default_post_xol_op(struct arch_uprobe *auprobe, struct pt_regs *regs
 		long correction = utask->vaddr - utask->xol_vaddr;
 		regs->ip += correction;
 	} else if (auprobe->defparam.fixups & UPROBE_FIX_CALL) {
-		regs->sp += sizeof_long(); /* Pop incorrect return address */
+		regs->sp += sizeof_long(regs); /* Pop incorrect return address */
 		if (push_ret_address(regs, utask->vaddr + auprobe->defparam.ilen))
 			return -ERESTART;
 	}
@@ -671,7 +674,7 @@ static int branch_post_xol_op(struct arch_uprobe *auprobe, struct pt_regs *regs)
 	 * "call" insn was executed out-of-line. Just restore ->sp and restart.
 	 * We could also restore ->ip and try to call branch_emulate_op() again.
 	 */
-	regs->sp += sizeof_long();
+	regs->sp += sizeof_long(regs);
 	return -ERESTART;
 }
 
@@ -962,7 +965,7 @@ bool arch_uprobe_skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs)
 unsigned long
 arch_uretprobe_hijack_return_addr(unsigned long trampoline_vaddr, struct pt_regs *regs)
 {
-	int rasize = sizeof_long(), nleft;
+	int rasize = sizeof_long(regs), nleft;
 	unsigned long orig_ret_vaddr = 0; /* clear high bits for 32-bit apps */
 
 	if (copy_from_user(&orig_ret_vaddr, (void __user *)regs->sp, rasize))
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 8613422660b6..9f70de2ca0e2 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -5545,12 +5545,13 @@ restart:
 		unsigned long rflags = kvm_x86_ops->get_rflags(vcpu);
 		toggle_interruptibility(vcpu, ctxt->interruptibility);
 		vcpu->arch.emulate_regs_need_sync_to_vcpu = false;
-		kvm_rip_write(vcpu, ctxt->eip);
-		if (r == EMULATE_DONE && ctxt->tf)
-			kvm_vcpu_do_singlestep(vcpu, &r);
 		if (!ctxt->have_exception ||
-		    exception_type(ctxt->exception.vector) == EXCPT_TRAP)
+		    exception_type(ctxt->exception.vector) == EXCPT_TRAP) {
+			kvm_rip_write(vcpu, ctxt->eip);
+			if (r == EMULATE_DONE && ctxt->tf)
+				kvm_vcpu_do_singlestep(vcpu, &r);
 			__kvm_set_rflags(vcpu, ctxt->eflags);
+		}
 
 		/*
 		 * For STI, interrupts are shadowed; so KVM_REQ_EVENT will
diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c
index 9ab52791fed5..2e5052b2d238 100644
--- a/arch/x86/power/cpu.c
+++ b/arch/x86/power/cpu.c
@@ -12,6 +12,7 @@
 #include <linux/export.h>
 #include <linux/smp.h>
 #include <linux/perf_event.h>
+#include <linux/dmi.h>
 
 #include <asm/pgtable.h>
 #include <asm/proto.h>
@@ -23,6 +24,7 @@
 #include <asm/debugreg.h>
 #include <asm/cpu.h>
 #include <asm/mmu_context.h>
+#include <asm/cpu_device_id.h>
 
 #ifdef CONFIG_X86_32
 __visible unsigned long saved_context_ebx;
@@ -32,6 +34,29 @@ __visible unsigned long saved_context_eflags;
 #endif
 struct saved_context saved_context;
 
+static void msr_save_context(struct saved_context *ctxt)
+{
+	struct saved_msr *msr = ctxt->saved_msrs.array;
+	struct saved_msr *end = msr + ctxt->saved_msrs.num;
+
+	while (msr < end) {
+		msr->valid = !rdmsrl_safe(msr->info.msr_no, &msr->info.reg.q);
+		msr++;
+	}
+}
+
+static void msr_restore_context(struct saved_context *ctxt)
+{
+	struct saved_msr *msr = ctxt->saved_msrs.array;
+	struct saved_msr *end = msr + ctxt->saved_msrs.num;
+
+	while (msr < end) {
+		if (msr->valid)
+			wrmsrl(msr->info.msr_no, msr->info.reg.q);
+		msr++;
+	}
+}
+
 /**
  *	__save_processor_state - save CPU registers before creating a
  *		hibernation image and before restoring the memory state from it
@@ -111,6 +136,7 @@ static void __save_processor_state(struct saved_context *ctxt)
 #endif
 	ctxt->misc_enable_saved = !rdmsrl_safe(MSR_IA32_MISC_ENABLE,
 					       &ctxt->misc_enable);
+	msr_save_context(ctxt);
 }
 
 /* Needed by apm.c */
@@ -229,6 +255,7 @@ static void notrace __restore_processor_state(struct saved_context *ctxt)
 	x86_platform.restore_sched_clock_state();
 	mtrr_bp_restore();
 	perf_restore_debug_store();
+	msr_restore_context(ctxt);
 }
 
 /* Needed by apm.c */
@@ -320,3 +347,128 @@ static int __init bsp_pm_check_init(void)
 }
 
 core_initcall(bsp_pm_check_init);
+
+static int msr_build_context(const u32 *msr_id, const int num)
+{
+	struct saved_msrs *saved_msrs = &saved_context.saved_msrs;
+	struct saved_msr *msr_array;
+	int total_num;
+	int i, j;
+
+	total_num = saved_msrs->num + num;
+
+	msr_array = kmalloc_array(total_num, sizeof(struct saved_msr), GFP_KERNEL);
+	if (!msr_array) {
+		pr_err("x86/pm: Can not allocate memory to save/restore MSRs during suspend.\n");
+		return -ENOMEM;
+	}
+
+	if (saved_msrs->array) {
+		/*
+		 * Multiple callbacks can invoke this function, so copy any
+		 * MSR save requests from previous invocations.
+		 */
+		memcpy(msr_array, saved_msrs->array,
+		       sizeof(struct saved_msr) * saved_msrs->num);
+
+		kfree(saved_msrs->array);
+	}
+
+	for (i = saved_msrs->num, j = 0; i < total_num; i++, j++) {
+		msr_array[i].info.msr_no	= msr_id[j];
+		msr_array[i].valid		= false;
+		msr_array[i].info.reg.q		= 0;
+	}
+	saved_msrs->num   = total_num;
+	saved_msrs->array = msr_array;
+
+	return 0;
+}
+
+/*
+ * The following sections are a quirk framework for problematic BIOSen:
+ * Sometimes MSRs are modified by the BIOSen after suspended to
+ * RAM, this might cause unexpected behavior after wakeup.
+ * Thus we save/restore these specified MSRs across suspend/resume
+ * in order to work around it.
+ *
+ * For any further problematic BIOSen/platforms,
+ * please add your own function similar to msr_initialize_bdw.
+ */
+static int msr_initialize_bdw(const struct dmi_system_id *d)
+{
+	/* Add any extra MSR ids into this array. */
+	u32 bdw_msr_id[] = { MSR_IA32_THERM_CONTROL };
+
+	pr_info("x86/pm: %s detected, MSR saving is needed during suspending.\n", d->ident);
+	return msr_build_context(bdw_msr_id, ARRAY_SIZE(bdw_msr_id));
+}
+
+static struct dmi_system_id msr_save_dmi_table[] = {
+	{
+	 .callback = msr_initialize_bdw,
+	 .ident = "BROADWELL BDX_EP",
+	 .matches = {
+		DMI_MATCH(DMI_PRODUCT_NAME, "GRANTLEY"),
+		DMI_MATCH(DMI_PRODUCT_VERSION, "E63448-400"),
+		},
+	},
+	{}
+};
+
+static int msr_save_cpuid_features(const struct x86_cpu_id *c)
+{
+	u32 cpuid_msr_id[] = {
+		MSR_AMD64_CPUID_FN_1,
+	};
+
+	pr_info("x86/pm: family %#hx cpu detected, MSR saving is needed during suspending.\n",
+		c->family);
+
+	return msr_build_context(cpuid_msr_id, ARRAY_SIZE(cpuid_msr_id));
+}
+
+static const struct x86_cpu_id msr_save_cpu_table[] = {
+	{
+		.vendor = X86_VENDOR_AMD,
+		.family = 0x15,
+		.model = X86_MODEL_ANY,
+		.feature = X86_FEATURE_ANY,
+		.driver_data = (kernel_ulong_t)msr_save_cpuid_features,
+	},
+	{
+		.vendor = X86_VENDOR_AMD,
+		.family = 0x16,
+		.model = X86_MODEL_ANY,
+		.feature = X86_FEATURE_ANY,
+		.driver_data = (kernel_ulong_t)msr_save_cpuid_features,
+	},
+	{}
+};
+
+typedef int (*pm_cpu_match_t)(const struct x86_cpu_id *);
+static int pm_cpu_check(const struct x86_cpu_id *c)
+{
+	const struct x86_cpu_id *m;
+	int ret = 0;
+
+	m = x86_match_cpu(msr_save_cpu_table);
+	if (m) {
+		pm_cpu_match_t fn;
+
+		fn = (pm_cpu_match_t)m->driver_data;
+		ret = fn(m);
+	}
+
+	return ret;
+}
+
+static int pm_check_save_msr(void)
+{
+	dmi_check_system(msr_save_dmi_table);
+	pm_cpu_check(msr_save_cpu_table);
+
+	return 0;
+}
+
+device_initcall(pm_check_save_msr);
diff --git a/drivers/ata/libata-sff.c b/drivers/ata/libata-sff.c
index 18de4c457068..1d8901fc0bfa 100644
--- a/drivers/ata/libata-sff.c
+++ b/drivers/ata/libata-sff.c
@@ -703,6 +703,10 @@ static void ata_pio_sector(struct ata_queued_cmd *qc)
 	unsigned int offset;
 	unsigned char *buf;
 
+	if (!qc->cursg) {
+		qc->curbytes = qc->nbytes;
+		return;
+	}
 	if (qc->curbytes == qc->nbytes - qc->sect_size)
 		ap->hsm_task_state = HSM_ST_LAST;
 
@@ -742,6 +746,8 @@ static void ata_pio_sector(struct ata_queued_cmd *qc)
 
 	if (qc->cursg_ofs == qc->cursg->length) {
 		qc->cursg = sg_next(qc->cursg);
+		if (!qc->cursg)
+			ap->hsm_task_state = HSM_ST_LAST;
 		qc->cursg_ofs = 0;
 	}
 }
diff --git a/drivers/dma/ste_dma40.c b/drivers/dma/ste_dma40.c
index dd3e7ba273ad..0fede051f4e1 100644
--- a/drivers/dma/ste_dma40.c
+++ b/drivers/dma/ste_dma40.c
@@ -142,7 +142,7 @@ enum d40_events {
  * when the DMA hw is powered off.
  * TODO: Add save/restore of D40_DREG_GCC on dma40 v3 or later, if that works.
  */
-static u32 d40_backup_regs[] = {
+static __maybe_unused u32 d40_backup_regs[] = {
 	D40_DREG_LCPA,
 	D40_DREG_LCLA,
 	D40_DREG_PRMSE,
@@ -211,7 +211,7 @@ static u32 d40_backup_regs_v4b[] = {
 
 #define BACKUP_REGS_SZ_V4B ARRAY_SIZE(d40_backup_regs_v4b)
 
-static u32 d40_backup_regs_chan[] = {
+static __maybe_unused u32 d40_backup_regs_chan[] = {
 	D40_CHAN_REG_SSCFG,
 	D40_CHAN_REG_SSELT,
 	D40_CHAN_REG_SSPTR,
diff --git a/drivers/hid/hid-tmff.c b/drivers/hid/hid-tmff.c
index b83376077d72..cfa0cb22c9b3 100644
--- a/drivers/hid/hid-tmff.c
+++ b/drivers/hid/hid-tmff.c
@@ -34,6 +34,8 @@
 
 #include "hid-ids.h"
 
+#define THRUSTMASTER_DEVICE_ID_2_IN_1_DT	0xb320
+
 static const signed short ff_rumble[] = {
 	FF_RUMBLE,
 	-1
@@ -88,6 +90,7 @@ static int tmff_play(struct input_dev *dev, void *data,
 	struct hid_field *ff_field = tmff->ff_field;
 	int x, y;
 	int left, right;	/* Rumbling */
+	int motor_swap;
 
 	switch (effect->type) {
 	case FF_CONSTANT:
@@ -112,6 +115,13 @@ static int tmff_play(struct input_dev *dev, void *data,
 					ff_field->logical_minimum,
 					ff_field->logical_maximum);
 
+		/* 2-in-1 strong motor is left */
+		if (hid->product == THRUSTMASTER_DEVICE_ID_2_IN_1_DT) {
+			motor_swap = left;
+			left = right;
+			right = motor_swap;
+		}
+
 		dbg_hid("(left,right)=(%08x, %08x)\n", left, right);
 		ff_field->value[0] = left;
 		ff_field->value[1] = right;
@@ -238,6 +248,8 @@ static const struct hid_device_id tm_devices[] = {
 		.driver_data = (unsigned long)ff_rumble },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_THRUSTMASTER, 0xb304),   /* FireStorm Dual Power 2 (and 3) */
 		.driver_data = (unsigned long)ff_rumble },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_THRUSTMASTER, THRUSTMASTER_DEVICE_ID_2_IN_1_DT),   /* Dual Trigger 2-in-1 */
+		.driver_data = (unsigned long)ff_rumble },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_THRUSTMASTER, 0xb323),   /* Dual Trigger 3-in-1 (PC Mode) */
 		.driver_data = (unsigned long)ff_rumble },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_THRUSTMASTER, 0xb324),   /* Dual Trigger 3-in-1 (PS3 Mode) */
diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c
index b184956bd430..72a1fdd529be 100644
--- a/drivers/hid/wacom_wac.c
+++ b/drivers/hid/wacom_wac.c
@@ -674,7 +674,7 @@ static int wacom_remote_irq(struct wacom_wac *wacom_wac, size_t len)
 	input_report_key(input, BTN_BASE2, (data[11] & 0x02));
 
 	if (data[12] & 0x80)
-		input_report_abs(input, ABS_WHEEL, (data[12] & 0x7f));
+		input_report_abs(input, ABS_WHEEL, (data[12] & 0x7f) - 1);
 	else
 		input_report_abs(input, ABS_WHEEL, 0);
 
diff --git a/drivers/hwtracing/stm/core.c b/drivers/hwtracing/stm/core.c
index e880702a3784..5eb9c3bba216 100644
--- a/drivers/hwtracing/stm/core.c
+++ b/drivers/hwtracing/stm/core.c
@@ -1020,7 +1020,6 @@ int stm_source_register_device(struct device *parent,
 
 err:
 	put_device(&src->dev);
-	kfree(src);
 
 	return err;
 }
diff --git a/drivers/isdn/hardware/mISDN/hfcsusb.c b/drivers/isdn/hardware/mISDN/hfcsusb.c
index c60c7998af17..726fba452f5f 100644
--- a/drivers/isdn/hardware/mISDN/hfcsusb.c
+++ b/drivers/isdn/hardware/mISDN/hfcsusb.c
@@ -1402,6 +1402,7 @@ start_isoc_chain(struct usb_fifo *fifo, int num_packets_per_urb,
 				printk(KERN_DEBUG
 				       "%s: %s: alloc urb for fifo %i failed",
 				       hw->name, __func__, fifo->fifonum);
+				continue;
 			}
 			fifo->iso[i].owner_fifo = (struct usb_fifo *) fifo;
 			fifo->iso[i].indx = i;
@@ -1700,13 +1701,23 @@ hfcsusb_stop_endpoint(struct hfcsusb *hw, int channel)
 static int
 setup_hfcsusb(struct hfcsusb *hw)
 {
+	void *dmabuf = kmalloc(sizeof(u_char), GFP_KERNEL);
 	u_char b;
+	int ret;
 
 	if (debug & DBG_HFC_CALL_TRACE)
 		printk(KERN_DEBUG "%s: %s\n", hw->name, __func__);
 
+	if (!dmabuf)
+		return -ENOMEM;
+
+	ret = read_reg_atomic(hw, HFCUSB_CHIP_ID, dmabuf);
+
+	memcpy(&b, dmabuf, sizeof(u_char));
+	kfree(dmabuf);
+
 	/* check the chip id */
-	if (read_reg_atomic(hw, HFCUSB_CHIP_ID, &b) != 1) {
+	if (ret != 1) {
 		printk(KERN_DEBUG "%s: %s: cannot read chip id\n",
 		       hw->name, __func__);
 		return 1;
diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c
index 8a6e7646e1c9..b1d5fa0bc8f7 100644
--- a/drivers/md/dm-bufio.c
+++ b/drivers/md/dm-bufio.c
@@ -1561,7 +1561,9 @@ dm_bufio_shrink_scan(struct shrinker *shrink, struct shrink_control *sc)
 	unsigned long freed;
 
 	c = container_of(shrink, struct dm_bufio_client, shrinker);
-	if (!dm_bufio_trylock(c))
+	if (sc->gfp_mask & __GFP_FS)
+		dm_bufio_lock(c);
+	else if (!dm_bufio_trylock(c))
 		return SHRINK_STOP;
 
 	freed  = __scan(c, sc->nr_to_scan, sc->gfp_mask);
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index cb5d0daf53bb..466158d06ab1 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -1167,7 +1167,7 @@ void dm_table_event(struct dm_table *t)
 }
 EXPORT_SYMBOL(dm_table_event);
 
-sector_t dm_table_get_size(struct dm_table *t)
+inline sector_t dm_table_get_size(struct dm_table *t)
 {
 	return t->num_targets ? (t->highs[t->num_targets - 1] + 1) : 0;
 }
@@ -1192,6 +1192,9 @@ struct dm_target *dm_table_find_target(struct dm_table *t, sector_t sector)
 	unsigned int l, n = 0, k = 0;
 	sector_t *node;
 
+	if (unlikely(sector >= dm_table_get_size(t)))
+		return &t->targets[t->num_targets];
+
 	for (l = 0; l < t->depth; l++) {
 		n = get_child(n, k);
 		node = get_node(t, l, n);
diff --git a/drivers/md/persistent-data/dm-btree.c b/drivers/md/persistent-data/dm-btree.c
index 880b7dee9c52..fa9039a53ae5 100644
--- a/drivers/md/persistent-data/dm-btree.c
+++ b/drivers/md/persistent-data/dm-btree.c
@@ -616,39 +616,40 @@ static int btree_split_beneath(struct shadow_spine *s, uint64_t key)
 
 	new_parent = shadow_current(s);
 
+	pn = dm_block_data(new_parent);
+	size = le32_to_cpu(pn->header.flags) & INTERNAL_NODE ?
+		sizeof(__le64) : s->info->value_type.size;
+
+	/* create & init the left block */
 	r = new_block(s->info, &left);
 	if (r < 0)
 		return r;
 
+	ln = dm_block_data(left);
+	nr_left = le32_to_cpu(pn->header.nr_entries) / 2;
+
+	ln->header.flags = pn->header.flags;
+	ln->header.nr_entries = cpu_to_le32(nr_left);
+	ln->header.max_entries = pn->header.max_entries;
+	ln->header.value_size = pn->header.value_size;
+	memcpy(ln->keys, pn->keys, nr_left * sizeof(pn->keys[0]));
+	memcpy(value_ptr(ln, 0), value_ptr(pn, 0), nr_left * size);
+
+	/* create & init the right block */
 	r = new_block(s->info, &right);
 	if (r < 0) {
 		unlock_block(s->info, left);
 		return r;
 	}
 
-	pn = dm_block_data(new_parent);
-	ln = dm_block_data(left);
 	rn = dm_block_data(right);
-
-	nr_left = le32_to_cpu(pn->header.nr_entries) / 2;
 	nr_right = le32_to_cpu(pn->header.nr_entries) - nr_left;
 
-	ln->header.flags = pn->header.flags;
-	ln->header.nr_entries = cpu_to_le32(nr_left);
-	ln->header.max_entries = pn->header.max_entries;
-	ln->header.value_size = pn->header.value_size;
-
 	rn->header.flags = pn->header.flags;
 	rn->header.nr_entries = cpu_to_le32(nr_right);
 	rn->header.max_entries = pn->header.max_entries;
 	rn->header.value_size = pn->header.value_size;
-
-	memcpy(ln->keys, pn->keys, nr_left * sizeof(pn->keys[0]));
 	memcpy(rn->keys, pn->keys + nr_left, nr_right * sizeof(pn->keys[0]));
-
-	size = le32_to_cpu(pn->header.flags) & INTERNAL_NODE ?
-		sizeof(__le64) : s->info->value_type.size;
-	memcpy(value_ptr(ln, 0), value_ptr(pn, 0), nr_left * size);
 	memcpy(value_ptr(rn, 0), value_ptr(pn, nr_left),
 	       nr_right * size);
 
diff --git a/drivers/md/persistent-data/dm-space-map-metadata.c b/drivers/md/persistent-data/dm-space-map-metadata.c
index 20557e2c60c6..1d29771af380 100644
--- a/drivers/md/persistent-data/dm-space-map-metadata.c
+++ b/drivers/md/persistent-data/dm-space-map-metadata.c
@@ -248,7 +248,7 @@ static int out(struct sm_metadata *smm)
 	}
 
 	if (smm->recursion_count == 1)
-		apply_bops(smm);
+		r = apply_bops(smm);
 
 	smm->recursion_count--;
 
diff --git a/drivers/misc/vmw_vmci/vmci_doorbell.c b/drivers/misc/vmw_vmci/vmci_doorbell.c
index a8cee33ae8d2..305a3449e946 100644
--- a/drivers/misc/vmw_vmci/vmci_doorbell.c
+++ b/drivers/misc/vmw_vmci/vmci_doorbell.c
@@ -318,7 +318,8 @@ int vmci_dbell_host_context_notify(u32 src_cid, struct vmci_handle handle)
 
 	entry = container_of(resource, struct dbell_entry, resource);
 	if (entry->run_delayed) {
-		schedule_work(&entry->work);
+		if (!schedule_work(&entry->work))
+			vmci_resource_put(resource);
 	} else {
 		entry->notify_cb(entry->client_data);
 		vmci_resource_put(resource);
@@ -366,7 +367,8 @@ static void dbell_fire_entries(u32 notify_idx)
 		    atomic_read(&dbell->active) == 1) {
 			if (dbell->run_delayed) {
 				vmci_resource_get(&dbell->resource);
-				schedule_work(&dbell->work);
+				if (!schedule_work(&dbell->work))
+					vmci_resource_put(&dbell->resource);
 			} else {
 				dbell->notify_cb(dbell->client_data);
 			}
diff --git a/drivers/mmc/core/sd.c b/drivers/mmc/core/sd.c
index fb8741f18c1f..54ba1abb5460 100644
--- a/drivers/mmc/core/sd.c
+++ b/drivers/mmc/core/sd.c
@@ -1232,6 +1232,12 @@ int mmc_attach_sd(struct mmc_host *host)
 			goto err;
 	}
 
+	/*
+	 * Some SD cards claims an out of spec VDD voltage range. Let's treat
+	 * these bits as being in-valid and especially also bit7.
+	 */
+	ocr &= ~0x7FFF;
+
 	rocr = mmc_select_voltage(host, ocr);
 
 	/*
diff --git a/drivers/mmc/host/sdhci-of-at91.c b/drivers/mmc/host/sdhci-of-at91.c
index 06d0b50dfe71..4e374a05319c 100644
--- a/drivers/mmc/host/sdhci-of-at91.c
+++ b/drivers/mmc/host/sdhci-of-at91.c
@@ -144,6 +144,9 @@ static int sdhci_at91_probe(struct platform_device *pdev)
 
 	sdhci_get_of_property(pdev);
 
+	/* HS200 is broken at this moment */
+	host->quirks2 = SDHCI_QUIRK2_BROKEN_HS200;
+
 	ret = sdhci_add_host(host);
 	if (ret)
 		goto clocks_disable_unprepare;
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 168f2331194f..fd6aff9f0052 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -2081,6 +2081,15 @@ static void bond_miimon_commit(struct bonding *bond)
 	bond_for_each_slave(bond, slave, iter) {
 		switch (slave->new_link) {
 		case BOND_LINK_NOCHANGE:
+			/* For 802.3ad mode, check current slave speed and
+			 * duplex again in case its port was disabled after
+			 * invalid speed/duplex reporting but recovered before
+			 * link monitoring could make a decision on the actual
+			 * link status
+			 */
+			if (BOND_MODE(bond) == BOND_MODE_8023AD &&
+			    slave->link == BOND_LINK_UP)
+				bond_3ad_adapter_speed_duplex_changed(slave);
 			continue;
 
 		case BOND_LINK_UP:
diff --git a/drivers/net/can/dev.c b/drivers/net/can/dev.c
index 8b7c6425b681..9dd968ee792e 100644
--- a/drivers/net/can/dev.c
+++ b/drivers/net/can/dev.c
@@ -1065,6 +1065,8 @@ static struct rtnl_link_ops can_link_ops __read_mostly = {
 int register_candev(struct net_device *dev)
 {
 	dev->rtnl_link_ops = &can_link_ops;
+	netif_carrier_off(dev);
+
 	return register_netdev(dev);
 }
 EXPORT_SYMBOL_GPL(register_candev);
diff --git a/drivers/net/can/sja1000/peak_pcmcia.c b/drivers/net/can/sja1000/peak_pcmcia.c
index dd56133cc461..fc9f8b01ecae 100644
--- a/drivers/net/can/sja1000/peak_pcmcia.c
+++ b/drivers/net/can/sja1000/peak_pcmcia.c
@@ -487,7 +487,7 @@ static void pcan_free_channels(struct pcan_pccard *card)
 		if (!netdev)
 			continue;
 
-		strncpy(name, netdev->name, IFNAMSIZ);
+		strlcpy(name, netdev->name, IFNAMSIZ);
 
 		unregister_sja1000dev(netdev);
 
diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_core.c b/drivers/net/can/usb/peak_usb/pcan_usb_core.c
index e13bc27b4291..b1d68f49b398 100644
--- a/drivers/net/can/usb/peak_usb/pcan_usb_core.c
+++ b/drivers/net/can/usb/peak_usb/pcan_usb_core.c
@@ -881,7 +881,7 @@ static void peak_usb_disconnect(struct usb_interface *intf)
 
 		dev_prev_siblings = dev->prev_siblings;
 		dev->state &= ~PCAN_USB_STATE_CONNECTED;
-		strncpy(name, netdev->name, IFNAMSIZ);
+		strlcpy(name, netdev->name, IFNAMSIZ);
 
 		unregister_netdev(netdev);
 
diff --git a/drivers/net/ethernet/arc/emac_main.c b/drivers/net/ethernet/arc/emac_main.c
index 9cc5daed13ed..b0285ac203f0 100644
--- a/drivers/net/ethernet/arc/emac_main.c
+++ b/drivers/net/ethernet/arc/emac_main.c
@@ -163,7 +163,7 @@ static void arc_emac_tx_clean(struct net_device *ndev)
 		struct sk_buff *skb = tx_buff->skb;
 		unsigned int info = le32_to_cpu(txbd->info);
 
-		if ((info & FOR_EMAC) || !txbd->data)
+		if ((info & FOR_EMAC) || !txbd->data || !skb)
 			break;
 
 		if (unlikely(info & (DROP | DEFR | LTCL | UFLO))) {
@@ -191,6 +191,7 @@ static void arc_emac_tx_clean(struct net_device *ndev)
 
 		txbd->data = 0;
 		txbd->info = 0;
+		tx_buff->skb = NULL;
 
 		*txbd_dirty = (*txbd_dirty + 1) % TX_BD_NUM;
 	}
@@ -619,7 +620,6 @@ static int arc_emac_tx(struct sk_buff *skb, struct net_device *ndev)
 	dma_unmap_addr_set(&priv->tx_buff[*txbd_curr], addr, addr);
 	dma_unmap_len_set(&priv->tx_buff[*txbd_curr], len, len);
 
-	priv->tx_buff[*txbd_curr].skb = skb;
 	priv->txbd[*txbd_curr].data = cpu_to_le32(addr);
 
 	/* Make sure pointer to data buffer is set */
@@ -629,6 +629,11 @@ static int arc_emac_tx(struct sk_buff *skb, struct net_device *ndev)
 
 	*info = cpu_to_le32(FOR_EMAC | FIRST_OR_LAST_MASK | len);
 
+	/* Make sure info word is set */
+	wmb();
+
+	priv->tx_buff[*txbd_curr].skb = skb;
+
 	/* Increment index to point to the next BD */
 	*txbd_curr = (*txbd_curr + 1) % TX_BD_NUM;
 
diff --git a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c
index 3dd4c39640dc..bee615cddbdd 100644
--- a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c
@@ -3260,7 +3260,7 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (!adapter->regs) {
 		dev_err(&pdev->dev, "cannot map device registers\n");
 		err = -ENOMEM;
-		goto out_free_adapter;
+		goto out_free_adapter_nofail;
 	}
 
 	adapter->pdev = pdev;
@@ -3378,6 +3378,9 @@ out_free_dev:
 		if (adapter->port[i])
 			free_netdev(adapter->port[i]);
 
+out_free_adapter_nofail:
+	kfree_skb(adapter->nofail_skb);
+
 out_free_adapter:
 	kfree(adapter);
 
diff --git a/drivers/net/ethernet/hisilicon/hip04_eth.c b/drivers/net/ethernet/hisilicon/hip04_eth.c
index 60c727b0b7ab..def831c89d35 100644
--- a/drivers/net/ethernet/hisilicon/hip04_eth.c
+++ b/drivers/net/ethernet/hisilicon/hip04_eth.c
@@ -157,6 +157,7 @@ struct hip04_priv {
 	unsigned int reg_inten;
 
 	struct napi_struct napi;
+	struct device *dev;
 	struct net_device *ndev;
 
 	struct tx_desc *tx_desc;
@@ -185,7 +186,7 @@ struct hip04_priv {
 
 static inline unsigned int tx_count(unsigned int head, unsigned int tail)
 {
-	return (head - tail) % (TX_DESC_NUM - 1);
+	return (head - tail) % TX_DESC_NUM;
 }
 
 static void hip04_config_port(struct net_device *ndev, u32 speed, u32 duplex)
@@ -387,7 +388,7 @@ static int hip04_tx_reclaim(struct net_device *ndev, bool force)
 		}
 
 		if (priv->tx_phys[tx_tail]) {
-			dma_unmap_single(&ndev->dev, priv->tx_phys[tx_tail],
+			dma_unmap_single(priv->dev, priv->tx_phys[tx_tail],
 					 priv->tx_skb[tx_tail]->len,
 					 DMA_TO_DEVICE);
 			priv->tx_phys[tx_tail] = 0;
@@ -437,8 +438,8 @@ static int hip04_mac_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 		return NETDEV_TX_BUSY;
 	}
 
-	phys = dma_map_single(&ndev->dev, skb->data, skb->len, DMA_TO_DEVICE);
-	if (dma_mapping_error(&ndev->dev, phys)) {
+	phys = dma_map_single(priv->dev, skb->data, skb->len, DMA_TO_DEVICE);
+	if (dma_mapping_error(priv->dev, phys)) {
 		dev_kfree_skb(skb);
 		return NETDEV_TX_OK;
 	}
@@ -497,13 +498,16 @@ static int hip04_rx_poll(struct napi_struct *napi, int budget)
 	u16 len;
 	u32 err;
 
+	/* clean up tx descriptors */
+	tx_remaining = hip04_tx_reclaim(ndev, false);
+
 	while (cnt && !last) {
 		buf = priv->rx_buf[priv->rx_head];
 		skb = build_skb(buf, priv->rx_buf_size);
 		if (unlikely(!skb))
 			net_dbg_ratelimited("build_skb failed\n");
 
-		dma_unmap_single(&ndev->dev, priv->rx_phys[priv->rx_head],
+		dma_unmap_single(priv->dev, priv->rx_phys[priv->rx_head],
 				 RX_BUF_SIZE, DMA_FROM_DEVICE);
 		priv->rx_phys[priv->rx_head] = 0;
 
@@ -531,9 +535,9 @@ static int hip04_rx_poll(struct napi_struct *napi, int budget)
 		buf = netdev_alloc_frag(priv->rx_buf_size);
 		if (!buf)
 			goto done;
-		phys = dma_map_single(&ndev->dev, buf,
+		phys = dma_map_single(priv->dev, buf,
 				      RX_BUF_SIZE, DMA_FROM_DEVICE);
-		if (dma_mapping_error(&ndev->dev, phys))
+		if (dma_mapping_error(priv->dev, phys))
 			goto done;
 		priv->rx_buf[priv->rx_head] = buf;
 		priv->rx_phys[priv->rx_head] = phys;
@@ -554,8 +558,7 @@ static int hip04_rx_poll(struct napi_struct *napi, int budget)
 	}
 	napi_complete(napi);
 done:
-	/* clean up tx descriptors and start a new timer if necessary */
-	tx_remaining = hip04_tx_reclaim(ndev, false);
+	/* start a new timer if necessary */
 	if (rx < budget && tx_remaining)
 		hip04_start_tx_timer(priv);
 
@@ -637,9 +640,9 @@ static int hip04_mac_open(struct net_device *ndev)
 	for (i = 0; i < RX_DESC_NUM; i++) {
 		dma_addr_t phys;
 
-		phys = dma_map_single(&ndev->dev, priv->rx_buf[i],
+		phys = dma_map_single(priv->dev, priv->rx_buf[i],
 				      RX_BUF_SIZE, DMA_FROM_DEVICE);
-		if (dma_mapping_error(&ndev->dev, phys))
+		if (dma_mapping_error(priv->dev, phys))
 			return -EIO;
 
 		priv->rx_phys[i] = phys;
@@ -673,7 +676,7 @@ static int hip04_mac_stop(struct net_device *ndev)
 
 	for (i = 0; i < RX_DESC_NUM; i++) {
 		if (priv->rx_phys[i]) {
-			dma_unmap_single(&ndev->dev, priv->rx_phys[i],
+			dma_unmap_single(priv->dev, priv->rx_phys[i],
 					 RX_BUF_SIZE, DMA_FROM_DEVICE);
 			priv->rx_phys[i] = 0;
 		}
@@ -824,6 +827,7 @@ static int hip04_mac_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	priv = netdev_priv(ndev);
+	priv->dev = d;
 	priv->ndev = ndev;
 	platform_set_drvdata(pdev, ndev);
 
diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index ee6fefe92af4..4391430e2527 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -719,6 +719,7 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x2001, 0x7e35, 4)},	/* D-Link DWM-222 */
 	{QMI_FIXED_INTF(0x2020, 0x2031, 4)},	/* Olicard 600 */
 	{QMI_FIXED_INTF(0x2020, 0x2033, 4)},	/* BroadMobi BM806U */
+	{QMI_FIXED_INTF(0x2020, 0x2060, 4)},	/* BroadMobi BM818 */
 	{QMI_FIXED_INTF(0x0f3d, 0x68a2, 8)},    /* Sierra Wireless MC7700 */
 	{QMI_FIXED_INTF(0x114f, 0x68a2, 8)},    /* Sierra Wireless MC7750 */
 	{QMI_FIXED_INTF(0x1199, 0x68a2, 8)},	/* Sierra Wireless MC7710 in QMI mode */
diff --git a/drivers/nfc/st-nci/se.c b/drivers/nfc/st-nci/se.c
index dbab722a0654..6f9d9b90ac64 100644
--- a/drivers/nfc/st-nci/se.c
+++ b/drivers/nfc/st-nci/se.c
@@ -346,6 +346,8 @@ static int st_nci_hci_connectivity_event_received(struct nci_dev *ndev,
 
 		transaction = (struct nfc_evt_transaction *)devm_kzalloc(dev,
 					    skb->len - 2, GFP_KERNEL);
+		if (!transaction)
+			return -ENOMEM;
 
 		transaction->aid_len = skb->data[1];
 		memcpy(transaction->aid, &skb->data[2], transaction->aid_len);
diff --git a/drivers/nfc/st21nfca/se.c b/drivers/nfc/st21nfca/se.c
index c79d99b24c96..f1b96b5255e0 100644
--- a/drivers/nfc/st21nfca/se.c
+++ b/drivers/nfc/st21nfca/se.c
@@ -327,6 +327,8 @@ int st21nfca_connectivity_event_received(struct nfc_hci_dev *hdev, u8 host,
 
 		transaction = (struct nfc_evt_transaction *)devm_kzalloc(dev,
 						   skb->len - 2, GFP_KERNEL);
+		if (!transaction)
+			return -ENOMEM;
 
 		transaction->aid_len = skb->data[1];
 		memcpy(transaction->aid, &skb->data[2],
diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c
index b140e81c4f7d..fd8bbd2b5d0e 100644
--- a/drivers/scsi/ufs/ufshcd.c
+++ b/drivers/scsi/ufs/ufshcd.c
@@ -4418,6 +4418,9 @@ static inline int ufshcd_config_vreg_lpm(struct ufs_hba *hba,
 static inline int ufshcd_config_vreg_hpm(struct ufs_hba *hba,
 					 struct ufs_vreg *vreg)
 {
+	if (!vreg)
+		return 0;
+
 	return ufshcd_config_vreg_load(hba->dev, vreg, vreg->max_uA);
 }
 
diff --git a/drivers/usb/class/cdc-wdm.c b/drivers/usb/class/cdc-wdm.c
index 61ea87917433..71ad04d54212 100644
--- a/drivers/usb/class/cdc-wdm.c
+++ b/drivers/usb/class/cdc-wdm.c
@@ -577,10 +577,20 @@ static int wdm_flush(struct file *file, fl_owner_t id)
 {
 	struct wdm_device *desc = file->private_data;
 
-	wait_event(desc->wait, !test_bit(WDM_IN_USE, &desc->flags));
+	wait_event(desc->wait,
+			/*
+			 * needs both flags. We cannot do with one
+			 * because resetting it would cause a race
+			 * with write() yet we need to signal
+			 * a disconnect
+			 */
+			!test_bit(WDM_IN_USE, &desc->flags) ||
+			test_bit(WDM_DISCONNECTING, &desc->flags));
 
 	/* cannot dereference desc->intf if WDM_DISCONNECTING */
-	if (desc->werr < 0 && !test_bit(WDM_DISCONNECTING, &desc->flags))
+	if (test_bit(WDM_DISCONNECTING, &desc->flags))
+		return -ENODEV;
+	if (desc->werr < 0)
 		dev_err(&desc->intf->dev, "Error in flush path: %d\n",
 			desc->werr);
 
@@ -968,8 +978,6 @@ static void wdm_disconnect(struct usb_interface *intf)
 	spin_lock_irqsave(&desc->iuspin, flags);
 	set_bit(WDM_DISCONNECTING, &desc->flags);
 	set_bit(WDM_READ, &desc->flags);
-	/* to terminate pending flushes */
-	clear_bit(WDM_IN_USE, &desc->flags);
 	spin_unlock_irqrestore(&desc->iuspin, flags);
 	wake_up_all(&desc->wait);
 	mutex_lock(&desc->rlock);
diff --git a/drivers/usb/gadget/composite.c b/drivers/usb/gadget/composite.c
index 8bf54477f472..351a406b97af 100644
--- a/drivers/usb/gadget/composite.c
+++ b/drivers/usb/gadget/composite.c
@@ -1889,6 +1889,7 @@ void composite_disconnect(struct usb_gadget *gadget)
 	 * disconnect callbacks?
 	 */
 	spin_lock_irqsave(&cdev->lock, flags);
+	cdev->suspended = 0;
 	if (cdev->config)
 		reset_config(cdev);
 	if (cdev->driver->disconnect)
diff --git a/drivers/usb/host/fotg210-hcd.c b/drivers/usb/host/fotg210-hcd.c
index 2341af4f3490..11b3a8c57eab 100644
--- a/drivers/usb/host/fotg210-hcd.c
+++ b/drivers/usb/host/fotg210-hcd.c
@@ -1653,6 +1653,10 @@ static int fotg210_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue,
 			/* see what we found out */
 			temp = check_reset_complete(fotg210, wIndex, status_reg,
 					fotg210_readl(fotg210, status_reg));
+
+			/* restart schedule */
+			fotg210->command |= CMD_RUN;
+			fotg210_writel(fotg210, fotg210->command, &fotg210->regs->command);
 		}
 
 		if (!(temp & (PORT_RESUME|PORT_RESET))) {
diff --git a/drivers/usb/host/ohci-hcd.c b/drivers/usb/host/ohci-hcd.c
index 602c6e42c34d..27bd3e49fe8e 100644
--- a/drivers/usb/host/ohci-hcd.c
+++ b/drivers/usb/host/ohci-hcd.c
@@ -415,8 +415,7 @@ static void ohci_usb_reset (struct ohci_hcd *ohci)
  * other cases where the next software may expect clean state from the
  * "firmware".  this is bus-neutral, unlike shutdown() methods.
  */
-static void
-ohci_shutdown (struct usb_hcd *hcd)
+static void _ohci_shutdown(struct usb_hcd *hcd)
 {
 	struct ohci_hcd *ohci;
 
@@ -432,6 +431,16 @@ ohci_shutdown (struct usb_hcd *hcd)
 	ohci->rh_state = OHCI_RH_HALTED;
 }
 
+static void ohci_shutdown(struct usb_hcd *hcd)
+{
+	struct ohci_hcd	*ohci = hcd_to_ohci(hcd);
+	unsigned long flags;
+
+	spin_lock_irqsave(&ohci->lock, flags);
+	_ohci_shutdown(hcd);
+	spin_unlock_irqrestore(&ohci->lock, flags);
+}
+
 /*-------------------------------------------------------------------------*
  * HC functions
  *-------------------------------------------------------------------------*/
@@ -750,7 +759,7 @@ static void io_watchdog_func(unsigned long _ohci)
  died:
 			usb_hc_died(ohci_to_hcd(ohci));
 			ohci_dump(ohci);
-			ohci_shutdown(ohci_to_hcd(ohci));
+			_ohci_shutdown(ohci_to_hcd(ohci));
 			goto done;
 		} else {
 			/* No write back because the done queue was empty */
diff --git a/drivers/usb/storage/realtek_cr.c b/drivers/usb/storage/realtek_cr.c
index be432bec0c5b..f0ca9feaea1d 100644
--- a/drivers/usb/storage/realtek_cr.c
+++ b/drivers/usb/storage/realtek_cr.c
@@ -50,7 +50,7 @@ MODULE_VERSION("1.03");
 
 static int auto_delink_en = 1;
 module_param(auto_delink_en, int, S_IRUGO | S_IWUSR);
-MODULE_PARM_DESC(auto_delink_en, "enable auto delink");
+MODULE_PARM_DESC(auto_delink_en, "auto delink mode (0=firmware, 1=software [default])");
 
 #ifdef CONFIG_REALTEK_AUTOPM
 static int ss_en = 1;
@@ -1006,12 +1006,15 @@ static int init_realtek_cr(struct us_data *us)
 			goto INIT_FAIL;
 	}
 
-	if (CHECK_FW_VER(chip, 0x5888) || CHECK_FW_VER(chip, 0x5889) ||
-	    CHECK_FW_VER(chip, 0x5901))
-		SET_AUTO_DELINK(chip);
-	if (STATUS_LEN(chip) == 16) {
-		if (SUPPORT_AUTO_DELINK(chip))
+	if (CHECK_PID(chip, 0x0138) || CHECK_PID(chip, 0x0158) ||
+	    CHECK_PID(chip, 0x0159)) {
+		if (CHECK_FW_VER(chip, 0x5888) || CHECK_FW_VER(chip, 0x5889) ||
+				CHECK_FW_VER(chip, 0x5901))
 			SET_AUTO_DELINK(chip);
+		if (STATUS_LEN(chip) == 16) {
+			if (SUPPORT_AUTO_DELINK(chip))
+				SET_AUTO_DELINK(chip);
+		}
 	}
 #ifdef CONFIG_REALTEK_AUTOPM
 	if (ss_en)
diff --git a/drivers/usb/storage/unusual_devs.h b/drivers/usb/storage/unusual_devs.h
index d92b974f0635..a98259e136dd 100644
--- a/drivers/usb/storage/unusual_devs.h
+++ b/drivers/usb/storage/unusual_devs.h
@@ -2006,7 +2006,7 @@ UNUSUAL_DEV(  0x14cd, 0x6600, 0x0201, 0x0201,
 		US_FL_IGNORE_RESIDUE ),
 
 /* Reported by Michael Büsch <m@xxxxxxx> */
-UNUSUAL_DEV(  0x152d, 0x0567, 0x0114, 0x0116,
+UNUSUAL_DEV(  0x152d, 0x0567, 0x0114, 0x0117,
 		"JMicron",
 		"USB to ATA/ATAPI Bridge",
 		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index f46317135224..1459dc9fd701 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -39,6 +39,12 @@ MODULE_PARM_DESC(experimental_zcopytx, "Enable Zero Copy TX;"
  * Using this limit prevents one virtqueue from starving others. */
 #define VHOST_NET_WEIGHT 0x80000
 
+/* Max number of packets transferred before requeueing the job.
+ * Using this limit prevents one virtqueue from starving others with small
+ * pkts.
+ */
+#define VHOST_NET_PKT_WEIGHT 256
+
 /* MAX number of TX used buffers for outstanding zerocopy */
 #define VHOST_MAX_PEND 128
 #define VHOST_GOODCOPY_LEN 256
@@ -308,6 +314,7 @@ static void handle_tx(struct vhost_net *net)
 	struct socket *sock;
 	struct vhost_net_ubuf_ref *uninitialized_var(ubufs);
 	bool zcopy, zcopy_used;
+	int sent_pkts = 0;
 
 	mutex_lock(&vq->mutex);
 	sock = vq->private_data;
@@ -319,7 +326,7 @@ static void handle_tx(struct vhost_net *net)
 	hdr_size = nvq->vhost_hlen;
 	zcopy = nvq->ubufs;
 
-	for (;;) {
+	do {
 		/* Release DMAs done buffers first */
 		if (zcopy)
 			vhost_zerocopy_signal_used(net, vq);
@@ -408,11 +415,7 @@ static void handle_tx(struct vhost_net *net)
 			vhost_zerocopy_signal_used(net, vq);
 		total_len += len;
 		vhost_net_tx_packet(net);
-		if (unlikely(total_len >= VHOST_NET_WEIGHT)) {
-			vhost_poll_queue(&vq->poll);
-			break;
-		}
-	}
+	} while (likely(!vhost_exceeds_weight(vq, ++sent_pkts, total_len)));
 out:
 	mutex_unlock(&vq->mutex);
 }
@@ -539,6 +542,7 @@ static void handle_rx(struct vhost_net *net)
 	struct socket *sock;
 	struct iov_iter fixup;
 	__virtio16 num_buffers;
+	int recv_pkts = 0;
 
 	mutex_lock(&vq->mutex);
 	sock = vq->private_data;
@@ -553,7 +557,10 @@ static void handle_rx(struct vhost_net *net)
 		vq->log : NULL;
 	mergeable = vhost_has_feature(vq, VIRTIO_NET_F_MRG_RXBUF);
 
-	while ((sock_len = peek_head_len(sock->sk))) {
+	do {
+		sock_len = peek_head_len(sock->sk);
+		if (!sock_len)
+			break;
 		sock_len += sock_hlen;
 		vhost_len = sock_len + vhost_hlen;
 		headcount = get_rx_bufs(vq, vq->heads, vhost_len,
@@ -631,11 +638,8 @@ static void handle_rx(struct vhost_net *net)
 		if (unlikely(vq_log))
 			vhost_log_write(vq, vq_log, log, vhost_len);
 		total_len += vhost_len;
-		if (unlikely(total_len >= VHOST_NET_WEIGHT)) {
-			vhost_poll_queue(&vq->poll);
-			break;
-		}
-	}
+	} while (likely(!vhost_exceeds_weight(vq, ++recv_pkts, total_len)));
+
 out:
 	mutex_unlock(&vq->mutex);
 }
@@ -704,7 +708,8 @@ static int vhost_net_open(struct inode *inode, struct file *f)
 		n->vqs[i].vhost_hlen = 0;
 		n->vqs[i].sock_hlen = 0;
 	}
-	vhost_dev_init(dev, vqs, VHOST_NET_VQ_MAX);
+	vhost_dev_init(dev, vqs, VHOST_NET_VQ_MAX,
+		       VHOST_NET_PKT_WEIGHT, VHOST_NET_WEIGHT);
 
 	vhost_poll_init(n->poll + VHOST_NET_VQ_TX, handle_tx_net, POLLOUT, dev);
 	vhost_poll_init(n->poll + VHOST_NET_VQ_RX, handle_rx_net, POLLIN, dev);
diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c
index 8fc62a03637a..269cfdd2958d 100644
--- a/drivers/vhost/scsi.c
+++ b/drivers/vhost/scsi.c
@@ -58,6 +58,12 @@
 #define VHOST_SCSI_PREALLOC_UPAGES 2048
 #define VHOST_SCSI_PREALLOC_PROT_SGLS 512
 
+/* Max number of requests before requeueing the job.
+ * Using this limit prevents one virtqueue from starving others with
+ * request.
+ */
+#define VHOST_SCSI_WEIGHT 256
+
 struct vhost_scsi_inflight {
 	/* Wait for the flush operation to finish */
 	struct completion comp;
@@ -855,7 +861,7 @@ vhost_scsi_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq)
 	u64 tag;
 	u32 exp_data_len, data_direction;
 	unsigned out, in;
-	int head, ret, prot_bytes;
+	int head, ret, prot_bytes, c = 0;
 	size_t req_size, rsp_size = sizeof(struct virtio_scsi_cmd_resp);
 	size_t out_size, in_size;
 	u16 lun;
@@ -874,7 +880,7 @@ vhost_scsi_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq)
 
 	vhost_disable_notify(&vs->dev, vq);
 
-	for (;;) {
+	do {
 		head = vhost_get_vq_desc(vq, vq->iov,
 					 ARRAY_SIZE(vq->iov), &out, &in,
 					 NULL, NULL);
@@ -1090,7 +1096,7 @@ vhost_scsi_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq)
 		 */
 		INIT_WORK(&cmd->work, vhost_scsi_submission_work);
 		queue_work(vhost_scsi_workqueue, &cmd->work);
-	}
+	} while (likely(!vhost_exceeds_weight(vq, ++c, 0)));
 out:
 	mutex_unlock(&vq->mutex);
 }
@@ -1443,7 +1449,8 @@ static int vhost_scsi_open(struct inode *inode, struct file *f)
 		vqs[i] = &vs->vqs[i].vq;
 		vs->vqs[i].vq.handle_kick = vhost_scsi_handle_kick;
 	}
-	vhost_dev_init(&vs->dev, vqs, VHOST_SCSI_MAX_VQ);
+	vhost_dev_init(&vs->dev, vqs, VHOST_SCSI_MAX_VQ,
+		       VHOST_SCSI_WEIGHT, 0);
 
 	vhost_scsi_init_inflight(vs, NULL);
 
diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index 2ed0a356d1d3..0f653f314876 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -370,8 +370,24 @@ static void vhost_dev_free_iovecs(struct vhost_dev *dev)
 		vhost_vq_free_iovecs(dev->vqs[i]);
 }
 
+bool vhost_exceeds_weight(struct vhost_virtqueue *vq,
+			  int pkts, int total_len)
+{
+	struct vhost_dev *dev = vq->dev;
+
+	if ((dev->byte_weight && total_len >= dev->byte_weight) ||
+	    pkts >= dev->weight) {
+		vhost_poll_queue(&vq->poll);
+		return true;
+	}
+
+	return false;
+}
+EXPORT_SYMBOL_GPL(vhost_exceeds_weight);
+
 void vhost_dev_init(struct vhost_dev *dev,
-		    struct vhost_virtqueue **vqs, int nvqs)
+		    struct vhost_virtqueue **vqs, int nvqs,
+		    int weight, int byte_weight)
 {
 	struct vhost_virtqueue *vq;
 	int i;
@@ -386,6 +402,8 @@ void vhost_dev_init(struct vhost_dev *dev,
 	spin_lock_init(&dev->work_lock);
 	INIT_LIST_HEAD(&dev->work_list);
 	dev->worker = NULL;
+	dev->weight = weight;
+	dev->byte_weight = byte_weight;
 
 	for (i = 0; i < dev->nvqs; ++i) {
 		vq = dev->vqs[i];
diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h
index d3f767448a72..5ac486970569 100644
--- a/drivers/vhost/vhost.h
+++ b/drivers/vhost/vhost.h
@@ -127,9 +127,13 @@ struct vhost_dev {
 	spinlock_t work_lock;
 	struct list_head work_list;
 	struct task_struct *worker;
+	int weight;
+	int byte_weight;
 };
 
-void vhost_dev_init(struct vhost_dev *, struct vhost_virtqueue **vqs, int nvqs);
+bool vhost_exceeds_weight(struct vhost_virtqueue *vq, int pkts, int total_len);
+void vhost_dev_init(struct vhost_dev *, struct vhost_virtqueue **vqs,
+		    int nvqs, int weight, int byte_weight);
 long vhost_dev_set_owner(struct vhost_dev *dev);
 bool vhost_dev_has_owner(struct vhost_dev *dev);
 long vhost_dev_check_owner(struct vhost_dev *);
diff --git a/drivers/watchdog/bcm2835_wdt.c b/drivers/watchdog/bcm2835_wdt.c
index 8a5ce5b5a0b6..199b1fb3669c 100644
--- a/drivers/watchdog/bcm2835_wdt.c
+++ b/drivers/watchdog/bcm2835_wdt.c
@@ -248,6 +248,7 @@ module_param(nowayout, bool, 0);
 MODULE_PARM_DESC(nowayout, "Watchdog cannot be stopped once started (default="
 				__MODULE_STRING(WATCHDOG_NOWAYOUT) ")");
 
+MODULE_ALIAS("platform:bcm2835-wdt");
 MODULE_AUTHOR("Lubomir Rintel <lkundrak@xxxxx>");
 MODULE_DESCRIPTION("Driver for Broadcom BCM2835 watchdog timer");
 MODULE_LICENSE("GPL");
diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c
index ef24894edecc..9c159e6ad116 100644
--- a/fs/gfs2/rgrp.c
+++ b/fs/gfs2/rgrp.c
@@ -739,6 +739,7 @@ void gfs2_clear_rgrpd(struct gfs2_sbd *sdp)
 
 		gfs2_free_clones(rgd);
 		kfree(rgd->rd_bits);
+		rgd->rd_bits = NULL;
 		return_all_reservations(rgd);
 		kmem_cache_free(gfs2_rgrpd_cachep, rgd);
 	}
@@ -933,10 +934,6 @@ static int read_rindex_entry(struct gfs2_inode *ip)
 	if (error)
 		goto fail;
 
-	rgd->rd_gl->gl_object = rgd;
-	rgd->rd_gl->gl_vm.start = (rgd->rd_addr * bsize) & PAGE_CACHE_MASK;
-	rgd->rd_gl->gl_vm.end = PAGE_CACHE_ALIGN((rgd->rd_addr +
-						  rgd->rd_length) * bsize) - 1;
 	rgd->rd_rgl = (struct gfs2_rgrp_lvb *)rgd->rd_gl->gl_lksb.sb_lvbptr;
 	rgd->rd_flags &= ~(GFS2_RDF_UPTODATE | GFS2_RDF_PREFERRED);
 	if (rgd->rd_data > sdp->sd_max_rg_data)
@@ -944,14 +941,20 @@ static int read_rindex_entry(struct gfs2_inode *ip)
 	spin_lock(&sdp->sd_rindex_spin);
 	error = rgd_insert(rgd);
 	spin_unlock(&sdp->sd_rindex_spin);
-	if (!error)
+	if (!error) {
+		rgd->rd_gl->gl_object = rgd;
+		rgd->rd_gl->gl_vm.start = (rgd->rd_addr * bsize) & PAGE_MASK;
+		rgd->rd_gl->gl_vm.end = PAGE_ALIGN((rgd->rd_addr +
+						    rgd->rd_length) * bsize) - 1;
 		return 0;
+	}
 
 	error = 0; /* someone else read in the rgrp; free it and ignore it */
 	gfs2_glock_put(rgd->rd_gl);
 
 fail:
 	kfree(rgd->rd_bits);
+	rgd->rd_bits = NULL;
 	kmem_cache_free(gfs2_rgrpd_cachep, rgd);
 	return error;
 }
diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index 4afdee420d25..9f15696f55b9 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -416,7 +416,8 @@ static inline void nfs4_schedule_session_recovery(struct nfs4_session *session,
 
 extern struct nfs4_state_owner *nfs4_get_state_owner(struct nfs_server *, struct rpc_cred *, gfp_t);
 extern void nfs4_put_state_owner(struct nfs4_state_owner *);
-extern void nfs4_purge_state_owners(struct nfs_server *);
+extern void nfs4_purge_state_owners(struct nfs_server *, struct list_head *);
+extern void nfs4_free_state_owners(struct list_head *head);
 extern struct nfs4_state * nfs4_get_open_state(struct inode *, struct nfs4_state_owner *);
 extern void nfs4_put_open_state(struct nfs4_state *);
 extern void nfs4_close_state(struct nfs4_state *, fmode_t);
diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c
index ae91d1e450be..dac20f31f01f 100644
--- a/fs/nfs/nfs4client.c
+++ b/fs/nfs/nfs4client.c
@@ -685,9 +685,12 @@ found:
 
 static void nfs4_destroy_server(struct nfs_server *server)
 {
+	LIST_HEAD(freeme);
+
 	nfs_server_return_all_delegations(server);
 	unset_pnfs_layoutdriver(server);
-	nfs4_purge_state_owners(server);
+	nfs4_purge_state_owners(server, &freeme);
+	nfs4_free_state_owners(&freeme);
 }
 
 /*
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 5be61affeefd..ef3ed2b1fd27 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -611,24 +611,39 @@ void nfs4_put_state_owner(struct nfs4_state_owner *sp)
 /**
  * nfs4_purge_state_owners - Release all cached state owners
  * @server: nfs_server with cached state owners to release
+ * @head: resulting list of state owners
  *
  * Called at umount time.  Remaining state owners will be on
  * the LRU with ref count of zero.
+ * Note that the state owners are not freed, but are added
+ * to the list @head, which can later be used as an argument
+ * to nfs4_free_state_owners.
  */
-void nfs4_purge_state_owners(struct nfs_server *server)
+void nfs4_purge_state_owners(struct nfs_server *server, struct list_head *head)
 {
 	struct nfs_client *clp = server->nfs_client;
 	struct nfs4_state_owner *sp, *tmp;
-	LIST_HEAD(doomed);
 
 	spin_lock(&clp->cl_lock);
 	list_for_each_entry_safe(sp, tmp, &server->state_owners_lru, so_lru) {
-		list_move(&sp->so_lru, &doomed);
+		list_move(&sp->so_lru, head);
 		nfs4_remove_state_owner_locked(sp);
 	}
 	spin_unlock(&clp->cl_lock);
+}
 
-	list_for_each_entry_safe(sp, tmp, &doomed, so_lru) {
+/**
+ * nfs4_purge_state_owners - Release all cached state owners
+ * @head: resulting list of state owners
+ *
+ * Frees a list of state owners that was generated by
+ * nfs4_purge_state_owners
+ */
+void nfs4_free_state_owners(struct list_head *head)
+{
+	struct nfs4_state_owner *sp, *tmp;
+
+	list_for_each_entry_safe(sp, tmp, head, so_lru) {
 		list_del(&sp->so_lru);
 		nfs4_free_state_owner(sp);
 	}
@@ -1724,12 +1739,13 @@ static int nfs4_do_reclaim(struct nfs_client *clp, const struct nfs4_state_recov
 	struct nfs4_state_owner *sp;
 	struct nfs_server *server;
 	struct rb_node *pos;
+	LIST_HEAD(freeme);
 	int status = 0;
 
 restart:
 	rcu_read_lock();
 	list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) {
-		nfs4_purge_state_owners(server);
+		nfs4_purge_state_owners(server, &freeme);
 		spin_lock(&clp->cl_lock);
 		for (pos = rb_first(&server->state_owners);
 		     pos != NULL;
@@ -1758,6 +1774,7 @@ restart:
 		spin_unlock(&clp->cl_lock);
 	}
 	rcu_read_unlock();
+	nfs4_free_state_owners(&freeme);
 	return 0;
 }
 
diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index f187e02d267e..fe1c146f4032 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -431,6 +431,7 @@ static int userfaultfd_release(struct inode *inode, struct file *file)
 	/* len == 0 means wake all */
 	struct userfaultfd_wake_range range = { .len = 0, };
 	unsigned long new_flags;
+	bool still_valid;
 
 	ACCESS_ONCE(ctx->released) = true;
 
@@ -446,8 +447,7 @@ static int userfaultfd_release(struct inode *inode, struct file *file)
 	 * taking the mmap_sem for writing.
 	 */
 	down_write(&mm->mmap_sem);
-	if (!mmget_still_valid(mm))
-		goto skip_mm;
+	still_valid = mmget_still_valid(mm);
 	prev = NULL;
 	for (vma = mm->mmap; vma; vma = vma->vm_next) {
 		cond_resched();
@@ -458,19 +458,20 @@ static int userfaultfd_release(struct inode *inode, struct file *file)
 			continue;
 		}
 		new_flags = vma->vm_flags & ~(VM_UFFD_MISSING | VM_UFFD_WP);
-		prev = vma_merge(mm, prev, vma->vm_start, vma->vm_end,
-				 new_flags, vma->anon_vma,
-				 vma->vm_file, vma->vm_pgoff,
-				 vma_policy(vma),
-				 NULL_VM_UFFD_CTX);
-		if (prev)
-			vma = prev;
-		else
-			prev = vma;
+		if (still_valid) {
+			prev = vma_merge(mm, prev, vma->vm_start, vma->vm_end,
+					 new_flags, vma->anon_vma,
+					 vma->vm_file, vma->vm_pgoff,
+					 vma_policy(vma),
+					 NULL_VM_UFFD_CTX);
+			if (prev)
+				vma = prev;
+			else
+				prev = vma;
+		}
 		vma->vm_flags = new_flags;
 		vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
 	}
-skip_mm:
 	up_write(&mm->mmap_sem);
 	mmput(mm);
 wakeup:
diff --git a/include/linux/siphash.h b/include/linux/siphash.h
new file mode 100644
index 000000000000..bf21591a9e5e
--- /dev/null
+++ b/include/linux/siphash.h
@@ -0,0 +1,145 @@
+/* Copyright (C) 2016 Jason A. Donenfeld <Jason@xxxxxxxxx>. All Rights Reserved.
+ *
+ * This file is provided under a dual BSD/GPLv2 license.
+ *
+ * SipHash: a fast short-input PRF
+ * https://131002.net/siphash/
+ *
+ * This implementation is specifically for SipHash2-4 for a secure PRF
+ * and HalfSipHash1-3/SipHash1-3 for an insecure PRF only suitable for
+ * hashtables.
+ */
+
+#ifndef _LINUX_SIPHASH_H
+#define _LINUX_SIPHASH_H
+
+#include <linux/types.h>
+#include <linux/kernel.h>
+
+#define SIPHASH_ALIGNMENT __alignof__(u64)
+typedef struct {
+	u64 key[2];
+} siphash_key_t;
+
+static inline bool siphash_key_is_zero(const siphash_key_t *key)
+{
+	return !(key->key[0] | key->key[1]);
+}
+
+u64 __siphash_aligned(const void *data, size_t len, const siphash_key_t *key);
+#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
+u64 __siphash_unaligned(const void *data, size_t len, const siphash_key_t *key);
+#endif
+
+u64 siphash_1u64(const u64 a, const siphash_key_t *key);
+u64 siphash_2u64(const u64 a, const u64 b, const siphash_key_t *key);
+u64 siphash_3u64(const u64 a, const u64 b, const u64 c,
+		 const siphash_key_t *key);
+u64 siphash_4u64(const u64 a, const u64 b, const u64 c, const u64 d,
+		 const siphash_key_t *key);
+u64 siphash_1u32(const u32 a, const siphash_key_t *key);
+u64 siphash_3u32(const u32 a, const u32 b, const u32 c,
+		 const siphash_key_t *key);
+
+static inline u64 siphash_2u32(const u32 a, const u32 b,
+			       const siphash_key_t *key)
+{
+	return siphash_1u64((u64)b << 32 | a, key);
+}
+static inline u64 siphash_4u32(const u32 a, const u32 b, const u32 c,
+			       const u32 d, const siphash_key_t *key)
+{
+	return siphash_2u64((u64)b << 32 | a, (u64)d << 32 | c, key);
+}
+
+
+static inline u64 ___siphash_aligned(const __le64 *data, size_t len,
+				     const siphash_key_t *key)
+{
+	if (__builtin_constant_p(len) && len == 4)
+		return siphash_1u32(le32_to_cpup((const __le32 *)data), key);
+	if (__builtin_constant_p(len) && len == 8)
+		return siphash_1u64(le64_to_cpu(data[0]), key);
+	if (__builtin_constant_p(len) && len == 16)
+		return siphash_2u64(le64_to_cpu(data[0]), le64_to_cpu(data[1]),
+				    key);
+	if (__builtin_constant_p(len) && len == 24)
+		return siphash_3u64(le64_to_cpu(data[0]), le64_to_cpu(data[1]),
+				    le64_to_cpu(data[2]), key);
+	if (__builtin_constant_p(len) && len == 32)
+		return siphash_4u64(le64_to_cpu(data[0]), le64_to_cpu(data[1]),
+				    le64_to_cpu(data[2]), le64_to_cpu(data[3]),
+				    key);
+	return __siphash_aligned(data, len, key);
+}
+
+/**
+ * siphash - compute 64-bit siphash PRF value
+ * @data: buffer to hash
+ * @size: size of @data
+ * @key: the siphash key
+ */
+static inline u64 siphash(const void *data, size_t len,
+			  const siphash_key_t *key)
+{
+#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
+	if (!IS_ALIGNED((unsigned long)data, SIPHASH_ALIGNMENT))
+		return __siphash_unaligned(data, len, key);
+#endif
+	return ___siphash_aligned(data, len, key);
+}
+
+#define HSIPHASH_ALIGNMENT __alignof__(unsigned long)
+typedef struct {
+	unsigned long key[2];
+} hsiphash_key_t;
+
+u32 __hsiphash_aligned(const void *data, size_t len,
+		       const hsiphash_key_t *key);
+#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
+u32 __hsiphash_unaligned(const void *data, size_t len,
+			 const hsiphash_key_t *key);
+#endif
+
+u32 hsiphash_1u32(const u32 a, const hsiphash_key_t *key);
+u32 hsiphash_2u32(const u32 a, const u32 b, const hsiphash_key_t *key);
+u32 hsiphash_3u32(const u32 a, const u32 b, const u32 c,
+		  const hsiphash_key_t *key);
+u32 hsiphash_4u32(const u32 a, const u32 b, const u32 c, const u32 d,
+		  const hsiphash_key_t *key);
+
+static inline u32 ___hsiphash_aligned(const __le32 *data, size_t len,
+				      const hsiphash_key_t *key)
+{
+	if (__builtin_constant_p(len) && len == 4)
+		return hsiphash_1u32(le32_to_cpu(data[0]), key);
+	if (__builtin_constant_p(len) && len == 8)
+		return hsiphash_2u32(le32_to_cpu(data[0]), le32_to_cpu(data[1]),
+				     key);
+	if (__builtin_constant_p(len) && len == 12)
+		return hsiphash_3u32(le32_to_cpu(data[0]), le32_to_cpu(data[1]),
+				     le32_to_cpu(data[2]), key);
+	if (__builtin_constant_p(len) && len == 16)
+		return hsiphash_4u32(le32_to_cpu(data[0]), le32_to_cpu(data[1]),
+				     le32_to_cpu(data[2]), le32_to_cpu(data[3]),
+				     key);
+	return __hsiphash_aligned(data, len, key);
+}
+
+/**
+ * hsiphash - compute 32-bit hsiphash PRF value
+ * @data: buffer to hash
+ * @size: size of @data
+ * @key: the hsiphash key
+ */
+static inline u32 hsiphash(const void *data, size_t len,
+			   const hsiphash_key_t *key)
+{
+#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
+	if (!IS_ALIGNED((unsigned long)data, HSIPHASH_ALIGNMENT))
+		return __hsiphash_unaligned(data, len, key);
+#endif
+	return ___hsiphash_aligned(data, len, key);
+}
+
+#endif /* _LINUX_SIPHASH_H */
diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h
index fde4068eec0b..636e9e11bd5f 100644
--- a/include/net/netfilter/nf_conntrack.h
+++ b/include/net/netfilter/nf_conntrack.h
@@ -297,6 +297,8 @@ struct nf_conn *nf_ct_tmpl_alloc(struct net *net,
 				 gfp_t flags);
 void nf_ct_tmpl_free(struct nf_conn *tmpl);
 
+u32 nf_ct_get_id(const struct nf_conn *ct);
+
 #define NF_CT_STAT_INC(net, count)	  __this_cpu_inc((net)->ct.stat->count)
 #define NF_CT_STAT_INC_ATOMIC(net, count) this_cpu_inc((net)->ct.stat->count)
 
diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index 61c38f87ea07..e6f49f22e006 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -8,6 +8,7 @@
 #include <linux/uidgid.h>
 #include <net/inet_frag.h>
 #include <linux/rcupdate.h>
+#include <linux/siphash.h>
 
 struct tcpm_hash_bucket;
 struct ctl_table_header;
@@ -109,5 +110,6 @@ struct netns_ipv4 {
 #endif
 #endif
 	atomic_t	rt_genid;
+	siphash_key_t	ip_id_key;
 };
 #endif
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 0410fd29d569..4447195a0cd4 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1540,6 +1540,10 @@ static inline struct sk_buff *tcp_rtx_queue_tail(const struct sock *sk)
 {
 	struct sk_buff *skb = tcp_send_head(sk);
 
+	/* empty retransmit queue, for example due to zero window */
+	if (skb == tcp_write_queue_head(sk))
+		return NULL;
+
 	return skb ? tcp_write_queue_prev(sk, skb) : tcp_write_queue_tail(sk);
 }
 
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 5299618d6308..7a7c535f8a2f 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -784,6 +784,8 @@ static void put_css_set_locked(struct css_set *cset)
 
 static void put_css_set(struct css_set *cset)
 {
+	unsigned long flags;
+
 	/*
 	 * Ensure that the refcount doesn't hit zero while any readers
 	 * can see it. Similar to atomic_dec_and_lock(), but for an
@@ -792,9 +794,9 @@ static void put_css_set(struct css_set *cset)
 	if (atomic_add_unless(&cset->refcount, -1, 1))
 		return;
 
-	spin_lock_bh(&css_set_lock);
+	spin_lock_irqsave(&css_set_lock, flags);
 	put_css_set_locked(cset);
-	spin_unlock_bh(&css_set_lock);
+	spin_unlock_irqrestore(&css_set_lock, flags);
 }
 
 /*
@@ -1017,11 +1019,11 @@ static struct css_set *find_css_set(struct css_set *old_cset,
 
 	/* First see if we already have a cgroup group that matches
 	 * the desired set */
-	spin_lock_bh(&css_set_lock);
+	spin_lock_irq(&css_set_lock);
 	cset = find_existing_css_set(old_cset, cgrp, template);
 	if (cset)
 		get_css_set(cset);
-	spin_unlock_bh(&css_set_lock);
+	spin_unlock_irq(&css_set_lock);
 
 	if (cset)
 		return cset;
@@ -1049,7 +1051,7 @@ static struct css_set *find_css_set(struct css_set *old_cset,
 	 * find_existing_css_set() */
 	memcpy(cset->subsys, template, sizeof(cset->subsys));
 
-	spin_lock_bh(&css_set_lock);
+	spin_lock_irq(&css_set_lock);
 	/* Add reference counts and links from the new css_set. */
 	list_for_each_entry(link, &old_cset->cgrp_links, cgrp_link) {
 		struct cgroup *c = link->cgrp;
@@ -1075,7 +1077,7 @@ static struct css_set *find_css_set(struct css_set *old_cset,
 		css_get(css);
 	}
 
-	spin_unlock_bh(&css_set_lock);
+	spin_unlock_irq(&css_set_lock);
 
 	return cset;
 }
@@ -1139,7 +1141,7 @@ static void cgroup_destroy_root(struct cgroup_root *root)
 	 * Release all the links from cset_links to this hierarchy's
 	 * root cgroup
 	 */
-	spin_lock_bh(&css_set_lock);
+	spin_lock_irq(&css_set_lock);
 
 	list_for_each_entry_safe(link, tmp_link, &cgrp->cset_links, cset_link) {
 		list_del(&link->cset_link);
@@ -1147,7 +1149,7 @@ static void cgroup_destroy_root(struct cgroup_root *root)
 		kfree(link);
 	}
 
-	spin_unlock_bh(&css_set_lock);
+	spin_unlock_irq(&css_set_lock);
 
 	if (!list_empty(&root->root_list)) {
 		list_del(&root->root_list);
@@ -1551,11 +1553,11 @@ static int rebind_subsystems(struct cgroup_root *dst_root,
 		ss->root = dst_root;
 		css->cgroup = dcgrp;
 
-		spin_lock_bh(&css_set_lock);
+		spin_lock_irq(&css_set_lock);
 		hash_for_each(css_set_table, i, cset, hlist)
 			list_move_tail(&cset->e_cset_node[ss->id],
 				       &dcgrp->e_csets[ss->id]);
-		spin_unlock_bh(&css_set_lock);
+		spin_unlock_irq(&css_set_lock);
 
 		src_root->subsys_mask &= ~(1 << ssid);
 		scgrp->subtree_control &= ~(1 << ssid);
@@ -1832,7 +1834,7 @@ static void cgroup_enable_task_cg_lists(void)
 {
 	struct task_struct *p, *g;
 
-	spin_lock_bh(&css_set_lock);
+	spin_lock_irq(&css_set_lock);
 
 	if (use_task_css_set_links)
 		goto out_unlock;
@@ -1857,8 +1859,12 @@ static void cgroup_enable_task_cg_lists(void)
 		 * entry won't be deleted though the process has exited.
 		 * Do it while holding siglock so that we don't end up
 		 * racing against cgroup_exit().
+		 *
+		 * Interrupts were already disabled while acquiring
+		 * the css_set_lock, so we do not need to disable it
+		 * again when acquiring the sighand->siglock here.
 		 */
-		spin_lock_irq(&p->sighand->siglock);
+		spin_lock(&p->sighand->siglock);
 		if (!(p->flags & PF_EXITING)) {
 			struct css_set *cset = task_css_set(p);
 
@@ -1867,11 +1873,11 @@ static void cgroup_enable_task_cg_lists(void)
 			list_add_tail(&p->cg_list, &cset->tasks);
 			get_css_set(cset);
 		}
-		spin_unlock_irq(&p->sighand->siglock);
+		spin_unlock(&p->sighand->siglock);
 	} while_each_thread(g, p);
 	read_unlock(&tasklist_lock);
 out_unlock:
-	spin_unlock_bh(&css_set_lock);
+	spin_unlock_irq(&css_set_lock);
 }
 
 static void init_cgroup_housekeeping(struct cgroup *cgrp)
@@ -1976,13 +1982,13 @@ static int cgroup_setup_root(struct cgroup_root *root, unsigned long ss_mask)
 	 * Link the root cgroup in this hierarchy into all the css_set
 	 * objects.
 	 */
-	spin_lock_bh(&css_set_lock);
+	spin_lock_irq(&css_set_lock);
 	hash_for_each(css_set_table, i, cset, hlist) {
 		link_css_set(&tmp_links, cset, root_cgrp);
 		if (css_set_populated(cset))
 			cgroup_update_populated(root_cgrp, true);
 	}
-	spin_unlock_bh(&css_set_lock);
+	spin_unlock_irq(&css_set_lock);
 
 	BUG_ON(!list_empty(&root_cgrp->self.children));
 	BUG_ON(atomic_read(&root->nr_cgrps) != 1);
@@ -2215,7 +2221,7 @@ char *task_cgroup_path(struct task_struct *task, char *buf, size_t buflen)
 	char *path = NULL;
 
 	mutex_lock(&cgroup_mutex);
-	spin_lock_bh(&css_set_lock);
+	spin_lock_irq(&css_set_lock);
 
 	root = idr_get_next(&cgroup_hierarchy_idr, &hierarchy_id);
 
@@ -2228,7 +2234,7 @@ char *task_cgroup_path(struct task_struct *task, char *buf, size_t buflen)
 			path = buf;
 	}
 
-	spin_unlock_bh(&css_set_lock);
+	spin_unlock_irq(&css_set_lock);
 	mutex_unlock(&cgroup_mutex);
 	return path;
 }
@@ -2403,7 +2409,7 @@ static int cgroup_taskset_migrate(struct cgroup_taskset *tset,
 	 * the new cgroup.  There are no failure cases after here, so this
 	 * is the commit point.
 	 */
-	spin_lock_bh(&css_set_lock);
+	spin_lock_irq(&css_set_lock);
 	list_for_each_entry(cset, &tset->src_csets, mg_node) {
 		list_for_each_entry_safe(task, tmp_task, &cset->mg_tasks, cg_list) {
 			struct css_set *from_cset = task_css_set(task);
@@ -2414,7 +2420,7 @@ static int cgroup_taskset_migrate(struct cgroup_taskset *tset,
 			put_css_set_locked(from_cset);
 		}
 	}
-	spin_unlock_bh(&css_set_lock);
+	spin_unlock_irq(&css_set_lock);
 
 	/*
 	 * Migration is committed, all target tasks are now on dst_csets.
@@ -2443,13 +2449,13 @@ out_cancel_attach:
 		}
 	}
 out_release_tset:
-	spin_lock_bh(&css_set_lock);
+	spin_lock_irq(&css_set_lock);
 	list_splice_init(&tset->dst_csets, &tset->src_csets);
 	list_for_each_entry_safe(cset, tmp_cset, &tset->src_csets, mg_node) {
 		list_splice_tail_init(&cset->mg_tasks, &cset->tasks);
 		list_del_init(&cset->mg_node);
 	}
-	spin_unlock_bh(&css_set_lock);
+	spin_unlock_irq(&css_set_lock);
 	return ret;
 }
 
@@ -2466,14 +2472,14 @@ static void cgroup_migrate_finish(struct list_head *preloaded_csets)
 
 	lockdep_assert_held(&cgroup_mutex);
 
-	spin_lock_bh(&css_set_lock);
+	spin_lock_irq(&css_set_lock);
 	list_for_each_entry_safe(cset, tmp_cset, preloaded_csets, mg_preload_node) {
 		cset->mg_src_cgrp = NULL;
 		cset->mg_dst_cset = NULL;
 		list_del_init(&cset->mg_preload_node);
 		put_css_set_locked(cset);
 	}
-	spin_unlock_bh(&css_set_lock);
+	spin_unlock_irq(&css_set_lock);
 }
 
 /**
@@ -2623,7 +2629,7 @@ static int cgroup_migrate(struct task_struct *leader, bool threadgroup,
 	 * already PF_EXITING could be freed from underneath us unless we
 	 * take an rcu_read_lock.
 	 */
-	spin_lock_bh(&css_set_lock);
+	spin_lock_irq(&css_set_lock);
 	rcu_read_lock();
 	task = leader;
 	do {
@@ -2632,7 +2638,7 @@ static int cgroup_migrate(struct task_struct *leader, bool threadgroup,
 			break;
 	} while_each_thread(leader, task);
 	rcu_read_unlock();
-	spin_unlock_bh(&css_set_lock);
+	spin_unlock_irq(&css_set_lock);
 
 	return cgroup_taskset_migrate(&tset, cgrp);
 }
@@ -2653,7 +2659,7 @@ static int cgroup_attach_task(struct cgroup *dst_cgrp,
 	int ret;
 
 	/* look up all src csets */
-	spin_lock_bh(&css_set_lock);
+	spin_lock_irq(&css_set_lock);
 	rcu_read_lock();
 	task = leader;
 	do {
@@ -2663,7 +2669,7 @@ static int cgroup_attach_task(struct cgroup *dst_cgrp,
 			break;
 	} while_each_thread(leader, task);
 	rcu_read_unlock();
-	spin_unlock_bh(&css_set_lock);
+	spin_unlock_irq(&css_set_lock);
 
 	/* prepare dst csets and commit */
 	ret = cgroup_migrate_prepare_dst(dst_cgrp, &preloaded_csets);
@@ -2696,9 +2702,9 @@ static int cgroup_procs_write_permission(struct task_struct *task,
 		struct cgroup *cgrp;
 		struct inode *inode;
 
-		spin_lock_bh(&css_set_lock);
+		spin_lock_irq(&css_set_lock);
 		cgrp = task_cgroup_from_root(task, &cgrp_dfl_root);
-		spin_unlock_bh(&css_set_lock);
+		spin_unlock_irq(&css_set_lock);
 
 		while (!cgroup_is_descendant(dst_cgrp, cgrp))
 			cgrp = cgroup_parent(cgrp);
@@ -2800,9 +2806,9 @@ int cgroup_attach_task_all(struct task_struct *from, struct task_struct *tsk)
 		if (root == &cgrp_dfl_root)
 			continue;
 
-		spin_lock_bh(&css_set_lock);
+		spin_lock_irq(&css_set_lock);
 		from_cgrp = task_cgroup_from_root(from, root);
-		spin_unlock_bh(&css_set_lock);
+		spin_unlock_irq(&css_set_lock);
 
 		retval = cgroup_attach_task(from_cgrp, tsk, false);
 		if (retval)
@@ -2927,7 +2933,7 @@ static int cgroup_update_dfl_csses(struct cgroup *cgrp)
 	percpu_down_write(&cgroup_threadgroup_rwsem);
 
 	/* look up all csses currently attached to @cgrp's subtree */
-	spin_lock_bh(&css_set_lock);
+	spin_lock_irq(&css_set_lock);
 	css_for_each_descendant_pre(css, cgroup_css(cgrp, NULL)) {
 		struct cgrp_cset_link *link;
 
@@ -2939,14 +2945,14 @@ static int cgroup_update_dfl_csses(struct cgroup *cgrp)
 			cgroup_migrate_add_src(link->cset, cgrp,
 					       &preloaded_csets);
 	}
-	spin_unlock_bh(&css_set_lock);
+	spin_unlock_irq(&css_set_lock);
 
 	/* NULL dst indicates self on default hierarchy */
 	ret = cgroup_migrate_prepare_dst(NULL, &preloaded_csets);
 	if (ret)
 		goto out_finish;
 
-	spin_lock_bh(&css_set_lock);
+	spin_lock_irq(&css_set_lock);
 	list_for_each_entry(src_cset, &preloaded_csets, mg_preload_node) {
 		struct task_struct *task, *ntask;
 
@@ -2958,7 +2964,7 @@ static int cgroup_update_dfl_csses(struct cgroup *cgrp)
 		list_for_each_entry_safe(task, ntask, &src_cset->tasks, cg_list)
 			cgroup_taskset_add(task, &tset);
 	}
-	spin_unlock_bh(&css_set_lock);
+	spin_unlock_irq(&css_set_lock);
 
 	ret = cgroup_taskset_migrate(&tset, cgrp);
 out_finish:
@@ -3641,10 +3647,10 @@ static int cgroup_task_count(const struct cgroup *cgrp)
 	int count = 0;
 	struct cgrp_cset_link *link;
 
-	spin_lock_bh(&css_set_lock);
+	spin_lock_irq(&css_set_lock);
 	list_for_each_entry(link, &cgrp->cset_links, cset_link)
 		count += atomic_read(&link->cset->refcount);
-	spin_unlock_bh(&css_set_lock);
+	spin_unlock_irq(&css_set_lock);
 	return count;
 }
 
@@ -3982,7 +3988,7 @@ void css_task_iter_start(struct cgroup_subsys_state *css,
 
 	memset(it, 0, sizeof(*it));
 
-	spin_lock_bh(&css_set_lock);
+	spin_lock_irq(&css_set_lock);
 
 	it->ss = css->ss;
 
@@ -3995,7 +4001,7 @@ void css_task_iter_start(struct cgroup_subsys_state *css,
 
 	css_task_iter_advance_css_set(it);
 
-	spin_unlock_bh(&css_set_lock);
+	spin_unlock_irq(&css_set_lock);
 }
 
 /**
@@ -4013,7 +4019,7 @@ struct task_struct *css_task_iter_next(struct css_task_iter *it)
 		it->cur_task = NULL;
 	}
 
-	spin_lock_bh(&css_set_lock);
+	spin_lock_irq(&css_set_lock);
 
 	if (it->task_pos) {
 		it->cur_task = list_entry(it->task_pos, struct task_struct,
@@ -4022,7 +4028,7 @@ struct task_struct *css_task_iter_next(struct css_task_iter *it)
 		css_task_iter_advance(it);
 	}
 
-	spin_unlock_bh(&css_set_lock);
+	spin_unlock_irq(&css_set_lock);
 
 	return it->cur_task;
 }
@@ -4036,10 +4042,10 @@ struct task_struct *css_task_iter_next(struct css_task_iter *it)
 void css_task_iter_end(struct css_task_iter *it)
 {
 	if (it->cur_cset) {
-		spin_lock_bh(&css_set_lock);
+		spin_lock_irq(&css_set_lock);
 		list_del(&it->iters_node);
 		put_css_set_locked(it->cur_cset);
-		spin_unlock_bh(&css_set_lock);
+		spin_unlock_irq(&css_set_lock);
 	}
 
 	if (it->cur_task)
@@ -4068,10 +4074,10 @@ int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from)
 	mutex_lock(&cgroup_mutex);
 
 	/* all tasks in @from are being moved, all csets are source */
-	spin_lock_bh(&css_set_lock);
+	spin_lock_irq(&css_set_lock);
 	list_for_each_entry(link, &from->cset_links, cset_link)
 		cgroup_migrate_add_src(link->cset, to, &preloaded_csets);
-	spin_unlock_bh(&css_set_lock);
+	spin_unlock_irq(&css_set_lock);
 
 	ret = cgroup_migrate_prepare_dst(to, &preloaded_csets);
 	if (ret)
@@ -5180,10 +5186,10 @@ static int cgroup_destroy_locked(struct cgroup *cgrp)
 	 */
 	cgrp->self.flags &= ~CSS_ONLINE;
 
-	spin_lock_bh(&css_set_lock);
+	spin_lock_irq(&css_set_lock);
 	list_for_each_entry(link, &cgrp->cset_links, cset_link)
 		link->cset->dead = true;
-	spin_unlock_bh(&css_set_lock);
+	spin_unlock_irq(&css_set_lock);
 
 	/* initiate massacre of all css's */
 	for_each_css(css, ssid, cgrp)
@@ -5436,7 +5442,7 @@ int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns,
 		goto out;
 
 	mutex_lock(&cgroup_mutex);
-	spin_lock_bh(&css_set_lock);
+	spin_lock_irq(&css_set_lock);
 
 	for_each_root(root) {
 		struct cgroup_subsys *ss;
@@ -5488,7 +5494,7 @@ int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns,
 
 	retval = 0;
 out_unlock:
-	spin_unlock_bh(&css_set_lock);
+	spin_unlock_irq(&css_set_lock);
 	mutex_unlock(&cgroup_mutex);
 	kfree(buf);
 out:
@@ -5649,13 +5655,13 @@ void cgroup_post_fork(struct task_struct *child,
 	if (use_task_css_set_links) {
 		struct css_set *cset;
 
-		spin_lock_bh(&css_set_lock);
+		spin_lock_irq(&css_set_lock);
 		cset = task_css_set(current);
 		if (list_empty(&child->cg_list)) {
 			get_css_set(cset);
 			css_set_move_task(child, NULL, cset, false);
 		}
-		spin_unlock_bh(&css_set_lock);
+		spin_unlock_irq(&css_set_lock);
 	}
 
 	/*
@@ -5699,9 +5705,9 @@ void cgroup_exit(struct task_struct *tsk)
 	cset = task_css_set(tsk);
 
 	if (!list_empty(&tsk->cg_list)) {
-		spin_lock_bh(&css_set_lock);
+		spin_lock_irq(&css_set_lock);
 		css_set_move_task(tsk, cset, NULL, false);
-		spin_unlock_bh(&css_set_lock);
+		spin_unlock_irq(&css_set_lock);
 	} else {
 		get_css_set(cset);
 	}
@@ -5914,7 +5920,7 @@ static int current_css_set_cg_links_read(struct seq_file *seq, void *v)
 	if (!name_buf)
 		return -ENOMEM;
 
-	spin_lock_bh(&css_set_lock);
+	spin_lock_irq(&css_set_lock);
 	rcu_read_lock();
 	cset = rcu_dereference(current->cgroups);
 	list_for_each_entry(link, &cset->cgrp_links, cgrp_link) {
@@ -5925,7 +5931,7 @@ static int current_css_set_cg_links_read(struct seq_file *seq, void *v)
 			   c->root->hierarchy_id, name_buf);
 	}
 	rcu_read_unlock();
-	spin_unlock_bh(&css_set_lock);
+	spin_unlock_irq(&css_set_lock);
 	kfree(name_buf);
 	return 0;
 }
@@ -5936,7 +5942,7 @@ static int cgroup_css_links_read(struct seq_file *seq, void *v)
 	struct cgroup_subsys_state *css = seq_css(seq);
 	struct cgrp_cset_link *link;
 
-	spin_lock_bh(&css_set_lock);
+	spin_lock_irq(&css_set_lock);
 	list_for_each_entry(link, &css->cgroup->cset_links, cset_link) {
 		struct css_set *cset = link->cset;
 		struct task_struct *task;
@@ -5959,7 +5965,7 @@ static int cgroup_css_links_read(struct seq_file *seq, void *v)
 	overflow:
 		seq_puts(seq, "  ...\n");
 	}
-	spin_unlock_bh(&css_set_lock);
+	spin_unlock_irq(&css_set_lock);
 	return 0;
 }
 
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index f0602beeba26..fd1205a3dbdb 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -1706,6 +1706,16 @@ config TEST_RHASHTABLE
 
 	  If unsure, say N.
 
+config TEST_HASH
+	tristate "Perform selftest on hash functions"
+	default n
+	help
+	  Enable this option to test the kernel's siphash (<linux/siphash.h>)
+	  hash functions on boot (or module load).
+
+	  This is intended to help people writing architecture-specific
+	  optimized versions.  If unsure, say N.
+
 endmenu # runtime tests
 
 config PROVIDE_OHCI1394_DMA_INIT
diff --git a/lib/Makefile b/lib/Makefile
index cb4f6aa95013..6c6c1fb2fa04 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -13,7 +13,7 @@ lib-y := ctype.o string.o vsprintf.o cmdline.o \
 	 sha1.o md5.o irq_regs.o argv_split.o \
 	 proportions.o flex_proportions.o ratelimit.o show_mem.o \
 	 is_single_threaded.o plist.o decompress.o kobject_uevent.o \
-	 earlycpio.o seq_buf.o nmi_backtrace.o
+	 earlycpio.o seq_buf.o siphash.o nmi_backtrace.o
 
 obj-$(CONFIG_ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS) += usercopy.o
 lib-$(CONFIG_MMU) += ioremap.o
@@ -35,6 +35,7 @@ obj-$(CONFIG_TEST_HEXDUMP) += test-hexdump.o
 obj-y += kstrtox.o
 obj-$(CONFIG_TEST_BPF) += test_bpf.o
 obj-$(CONFIG_TEST_FIRMWARE) += test_firmware.o
+obj-$(CONFIG_TEST_HASH) += test_siphash.o
 obj-$(CONFIG_TEST_KASAN) += test_kasan.o
 obj-$(CONFIG_TEST_KSTRTOX) += test-kstrtox.o
 obj-$(CONFIG_TEST_LKM) += test_module.o
diff --git a/lib/siphash.c b/lib/siphash.c
new file mode 100644
index 000000000000..3ae58b4edad6
--- /dev/null
+++ b/lib/siphash.c
@@ -0,0 +1,551 @@
+/* Copyright (C) 2016 Jason A. Donenfeld <Jason@xxxxxxxxx>. All Rights Reserved.
+ *
+ * This file is provided under a dual BSD/GPLv2 license.
+ *
+ * SipHash: a fast short-input PRF
+ * https://131002.net/siphash/
+ *
+ * This implementation is specifically for SipHash2-4 for a secure PRF
+ * and HalfSipHash1-3/SipHash1-3 for an insecure PRF only suitable for
+ * hashtables.
+ */
+
+#include <linux/siphash.h>
+#include <asm/unaligned.h>
+
+#if defined(CONFIG_DCACHE_WORD_ACCESS) && BITS_PER_LONG == 64
+#include <linux/dcache.h>
+#include <asm/word-at-a-time.h>
+#endif
+
+#define SIPROUND \
+	do { \
+	v0 += v1; v1 = rol64(v1, 13); v1 ^= v0; v0 = rol64(v0, 32); \
+	v2 += v3; v3 = rol64(v3, 16); v3 ^= v2; \
+	v0 += v3; v3 = rol64(v3, 21); v3 ^= v0; \
+	v2 += v1; v1 = rol64(v1, 17); v1 ^= v2; v2 = rol64(v2, 32); \
+	} while (0)
+
+#define PREAMBLE(len) \
+	u64 v0 = 0x736f6d6570736575ULL; \
+	u64 v1 = 0x646f72616e646f6dULL; \
+	u64 v2 = 0x6c7967656e657261ULL; \
+	u64 v3 = 0x7465646279746573ULL; \
+	u64 b = ((u64)(len)) << 56; \
+	v3 ^= key->key[1]; \
+	v2 ^= key->key[0]; \
+	v1 ^= key->key[1]; \
+	v0 ^= key->key[0];
+
+#define POSTAMBLE \
+	v3 ^= b; \
+	SIPROUND; \
+	SIPROUND; \
+	v0 ^= b; \
+	v2 ^= 0xff; \
+	SIPROUND; \
+	SIPROUND; \
+	SIPROUND; \
+	SIPROUND; \
+	return (v0 ^ v1) ^ (v2 ^ v3);
+
+u64 __siphash_aligned(const void *data, size_t len, const siphash_key_t *key)
+{
+	const u8 *end = data + len - (len % sizeof(u64));
+	const u8 left = len & (sizeof(u64) - 1);
+	u64 m;
+	PREAMBLE(len)
+	for (; data != end; data += sizeof(u64)) {
+		m = le64_to_cpup(data);
+		v3 ^= m;
+		SIPROUND;
+		SIPROUND;
+		v0 ^= m;
+	}
+#if defined(CONFIG_DCACHE_WORD_ACCESS) && BITS_PER_LONG == 64
+	if (left)
+		b |= le64_to_cpu((__force __le64)(load_unaligned_zeropad(data) &
+						  bytemask_from_count(left)));
+#else
+	switch (left) {
+	case 7: b |= ((u64)end[6]) << 48;
+	case 6: b |= ((u64)end[5]) << 40;
+	case 5: b |= ((u64)end[4]) << 32;
+	case 4: b |= le32_to_cpup(data); break;
+	case 3: b |= ((u64)end[2]) << 16;
+	case 2: b |= le16_to_cpup(data); break;
+	case 1: b |= end[0];
+	}
+#endif
+	POSTAMBLE
+}
+EXPORT_SYMBOL(__siphash_aligned);
+
+#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
+u64 __siphash_unaligned(const void *data, size_t len, const siphash_key_t *key)
+{
+	const u8 *end = data + len - (len % sizeof(u64));
+	const u8 left = len & (sizeof(u64) - 1);
+	u64 m;
+	PREAMBLE(len)
+	for (; data != end; data += sizeof(u64)) {
+		m = get_unaligned_le64(data);
+		v3 ^= m;
+		SIPROUND;
+		SIPROUND;
+		v0 ^= m;
+	}
+#if defined(CONFIG_DCACHE_WORD_ACCESS) && BITS_PER_LONG == 64
+	if (left)
+		b |= le64_to_cpu((__force __le64)(load_unaligned_zeropad(data) &
+						  bytemask_from_count(left)));
+#else
+	switch (left) {
+	case 7: b |= ((u64)end[6]) << 48;
+	case 6: b |= ((u64)end[5]) << 40;
+	case 5: b |= ((u64)end[4]) << 32;
+	case 4: b |= get_unaligned_le32(end); break;
+	case 3: b |= ((u64)end[2]) << 16;
+	case 2: b |= get_unaligned_le16(end); break;
+	case 1: b |= end[0];
+	}
+#endif
+	POSTAMBLE
+}
+EXPORT_SYMBOL(__siphash_unaligned);
+#endif
+
+/**
+ * siphash_1u64 - compute 64-bit siphash PRF value of a u64
+ * @first: first u64
+ * @key: the siphash key
+ */
+u64 siphash_1u64(const u64 first, const siphash_key_t *key)
+{
+	PREAMBLE(8)
+	v3 ^= first;
+	SIPROUND;
+	SIPROUND;
+	v0 ^= first;
+	POSTAMBLE
+}
+EXPORT_SYMBOL(siphash_1u64);
+
+/**
+ * siphash_2u64 - compute 64-bit siphash PRF value of 2 u64
+ * @first: first u64
+ * @second: second u64
+ * @key: the siphash key
+ */
+u64 siphash_2u64(const u64 first, const u64 second, const siphash_key_t *key)
+{
+	PREAMBLE(16)
+	v3 ^= first;
+	SIPROUND;
+	SIPROUND;
+	v0 ^= first;
+	v3 ^= second;
+	SIPROUND;
+	SIPROUND;
+	v0 ^= second;
+	POSTAMBLE
+}
+EXPORT_SYMBOL(siphash_2u64);
+
+/**
+ * siphash_3u64 - compute 64-bit siphash PRF value of 3 u64
+ * @first: first u64
+ * @second: second u64
+ * @third: third u64
+ * @key: the siphash key
+ */
+u64 siphash_3u64(const u64 first, const u64 second, const u64 third,
+		 const siphash_key_t *key)
+{
+	PREAMBLE(24)
+	v3 ^= first;
+	SIPROUND;
+	SIPROUND;
+	v0 ^= first;
+	v3 ^= second;
+	SIPROUND;
+	SIPROUND;
+	v0 ^= second;
+	v3 ^= third;
+	SIPROUND;
+	SIPROUND;
+	v0 ^= third;
+	POSTAMBLE
+}
+EXPORT_SYMBOL(siphash_3u64);
+
+/**
+ * siphash_4u64 - compute 64-bit siphash PRF value of 4 u64
+ * @first: first u64
+ * @second: second u64
+ * @third: third u64
+ * @forth: forth u64
+ * @key: the siphash key
+ */
+u64 siphash_4u64(const u64 first, const u64 second, const u64 third,
+		 const u64 forth, const siphash_key_t *key)
+{
+	PREAMBLE(32)
+	v3 ^= first;
+	SIPROUND;
+	SIPROUND;
+	v0 ^= first;
+	v3 ^= second;
+	SIPROUND;
+	SIPROUND;
+	v0 ^= second;
+	v3 ^= third;
+	SIPROUND;
+	SIPROUND;
+	v0 ^= third;
+	v3 ^= forth;
+	SIPROUND;
+	SIPROUND;
+	v0 ^= forth;
+	POSTAMBLE
+}
+EXPORT_SYMBOL(siphash_4u64);
+
+u64 siphash_1u32(const u32 first, const siphash_key_t *key)
+{
+	PREAMBLE(4)
+	b |= first;
+	POSTAMBLE
+}
+EXPORT_SYMBOL(siphash_1u32);
+
+u64 siphash_3u32(const u32 first, const u32 second, const u32 third,
+		 const siphash_key_t *key)
+{
+	u64 combined = (u64)second << 32 | first;
+	PREAMBLE(12)
+	v3 ^= combined;
+	SIPROUND;
+	SIPROUND;
+	v0 ^= combined;
+	b |= third;
+	POSTAMBLE
+}
+EXPORT_SYMBOL(siphash_3u32);
+
+#if BITS_PER_LONG == 64
+/* Note that on 64-bit, we make HalfSipHash1-3 actually be SipHash1-3, for
+ * performance reasons. On 32-bit, below, we actually implement HalfSipHash1-3.
+ */
+
+#define HSIPROUND SIPROUND
+#define HPREAMBLE(len) PREAMBLE(len)
+#define HPOSTAMBLE \
+	v3 ^= b; \
+	HSIPROUND; \
+	v0 ^= b; \
+	v2 ^= 0xff; \
+	HSIPROUND; \
+	HSIPROUND; \
+	HSIPROUND; \
+	return (v0 ^ v1) ^ (v2 ^ v3);
+
+u32 __hsiphash_aligned(const void *data, size_t len, const hsiphash_key_t *key)
+{
+	const u8 *end = data + len - (len % sizeof(u64));
+	const u8 left = len & (sizeof(u64) - 1);
+	u64 m;
+	HPREAMBLE(len)
+	for (; data != end; data += sizeof(u64)) {
+		m = le64_to_cpup(data);
+		v3 ^= m;
+		HSIPROUND;
+		v0 ^= m;
+	}
+#if defined(CONFIG_DCACHE_WORD_ACCESS) && BITS_PER_LONG == 64
+	if (left)
+		b |= le64_to_cpu((__force __le64)(load_unaligned_zeropad(data) &
+						  bytemask_from_count(left)));
+#else
+	switch (left) {
+	case 7: b |= ((u64)end[6]) << 48;
+	case 6: b |= ((u64)end[5]) << 40;
+	case 5: b |= ((u64)end[4]) << 32;
+	case 4: b |= le32_to_cpup(data); break;
+	case 3: b |= ((u64)end[2]) << 16;
+	case 2: b |= le16_to_cpup(data); break;
+	case 1: b |= end[0];
+	}
+#endif
+	HPOSTAMBLE
+}
+EXPORT_SYMBOL(__hsiphash_aligned);
+
+#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
+u32 __hsiphash_unaligned(const void *data, size_t len,
+			 const hsiphash_key_t *key)
+{
+	const u8 *end = data + len - (len % sizeof(u64));
+	const u8 left = len & (sizeof(u64) - 1);
+	u64 m;
+	HPREAMBLE(len)
+	for (; data != end; data += sizeof(u64)) {
+		m = get_unaligned_le64(data);
+		v3 ^= m;
+		HSIPROUND;
+		v0 ^= m;
+	}
+#if defined(CONFIG_DCACHE_WORD_ACCESS) && BITS_PER_LONG == 64
+	if (left)
+		b |= le64_to_cpu((__force __le64)(load_unaligned_zeropad(data) &
+						  bytemask_from_count(left)));
+#else
+	switch (left) {
+	case 7: b |= ((u64)end[6]) << 48;
+	case 6: b |= ((u64)end[5]) << 40;
+	case 5: b |= ((u64)end[4]) << 32;
+	case 4: b |= get_unaligned_le32(end); break;
+	case 3: b |= ((u64)end[2]) << 16;
+	case 2: b |= get_unaligned_le16(end); break;
+	case 1: b |= end[0];
+	}
+#endif
+	HPOSTAMBLE
+}
+EXPORT_SYMBOL(__hsiphash_unaligned);
+#endif
+
+/**
+ * hsiphash_1u32 - compute 64-bit hsiphash PRF value of a u32
+ * @first: first u32
+ * @key: the hsiphash key
+ */
+u32 hsiphash_1u32(const u32 first, const hsiphash_key_t *key)
+{
+	HPREAMBLE(4)
+	b |= first;
+	HPOSTAMBLE
+}
+EXPORT_SYMBOL(hsiphash_1u32);
+
+/**
+ * hsiphash_2u32 - compute 32-bit hsiphash PRF value of 2 u32
+ * @first: first u32
+ * @second: second u32
+ * @key: the hsiphash key
+ */
+u32 hsiphash_2u32(const u32 first, const u32 second, const hsiphash_key_t *key)
+{
+	u64 combined = (u64)second << 32 | first;
+	HPREAMBLE(8)
+	v3 ^= combined;
+	HSIPROUND;
+	v0 ^= combined;
+	HPOSTAMBLE
+}
+EXPORT_SYMBOL(hsiphash_2u32);
+
+/**
+ * hsiphash_3u32 - compute 32-bit hsiphash PRF value of 3 u32
+ * @first: first u32
+ * @second: second u32
+ * @third: third u32
+ * @key: the hsiphash key
+ */
+u32 hsiphash_3u32(const u32 first, const u32 second, const u32 third,
+		  const hsiphash_key_t *key)
+{
+	u64 combined = (u64)second << 32 | first;
+	HPREAMBLE(12)
+	v3 ^= combined;
+	HSIPROUND;
+	v0 ^= combined;
+	b |= third;
+	HPOSTAMBLE
+}
+EXPORT_SYMBOL(hsiphash_3u32);
+
+/**
+ * hsiphash_4u32 - compute 32-bit hsiphash PRF value of 4 u32
+ * @first: first u32
+ * @second: second u32
+ * @third: third u32
+ * @forth: forth u32
+ * @key: the hsiphash key
+ */
+u32 hsiphash_4u32(const u32 first, const u32 second, const u32 third,
+		  const u32 forth, const hsiphash_key_t *key)
+{
+	u64 combined = (u64)second << 32 | first;
+	HPREAMBLE(16)
+	v3 ^= combined;
+	HSIPROUND;
+	v0 ^= combined;
+	combined = (u64)forth << 32 | third;
+	v3 ^= combined;
+	HSIPROUND;
+	v0 ^= combined;
+	HPOSTAMBLE
+}
+EXPORT_SYMBOL(hsiphash_4u32);
+#else
+#define HSIPROUND \
+	do { \
+	v0 += v1; v1 = rol32(v1, 5); v1 ^= v0; v0 = rol32(v0, 16); \
+	v2 += v3; v3 = rol32(v3, 8); v3 ^= v2; \
+	v0 += v3; v3 = rol32(v3, 7); v3 ^= v0; \
+	v2 += v1; v1 = rol32(v1, 13); v1 ^= v2; v2 = rol32(v2, 16); \
+	} while (0)
+
+#define HPREAMBLE(len) \
+	u32 v0 = 0; \
+	u32 v1 = 0; \
+	u32 v2 = 0x6c796765U; \
+	u32 v3 = 0x74656462U; \
+	u32 b = ((u32)(len)) << 24; \
+	v3 ^= key->key[1]; \
+	v2 ^= key->key[0]; \
+	v1 ^= key->key[1]; \
+	v0 ^= key->key[0];
+
+#define HPOSTAMBLE \
+	v3 ^= b; \
+	HSIPROUND; \
+	v0 ^= b; \
+	v2 ^= 0xff; \
+	HSIPROUND; \
+	HSIPROUND; \
+	HSIPROUND; \
+	return v1 ^ v3;
+
+u32 __hsiphash_aligned(const void *data, size_t len, const hsiphash_key_t *key)
+{
+	const u8 *end = data + len - (len % sizeof(u32));
+	const u8 left = len & (sizeof(u32) - 1);
+	u32 m;
+	HPREAMBLE(len)
+	for (; data != end; data += sizeof(u32)) {
+		m = le32_to_cpup(data);
+		v3 ^= m;
+		HSIPROUND;
+		v0 ^= m;
+	}
+	switch (left) {
+	case 3: b |= ((u32)end[2]) << 16;
+	case 2: b |= le16_to_cpup(data); break;
+	case 1: b |= end[0];
+	}
+	HPOSTAMBLE
+}
+EXPORT_SYMBOL(__hsiphash_aligned);
+
+#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
+u32 __hsiphash_unaligned(const void *data, size_t len,
+			 const hsiphash_key_t *key)
+{
+	const u8 *end = data + len - (len % sizeof(u32));
+	const u8 left = len & (sizeof(u32) - 1);
+	u32 m;
+	HPREAMBLE(len)
+	for (; data != end; data += sizeof(u32)) {
+		m = get_unaligned_le32(data);
+		v3 ^= m;
+		HSIPROUND;
+		v0 ^= m;
+	}
+	switch (left) {
+	case 3: b |= ((u32)end[2]) << 16;
+	case 2: b |= get_unaligned_le16(end); break;
+	case 1: b |= end[0];
+	}
+	HPOSTAMBLE
+}
+EXPORT_SYMBOL(__hsiphash_unaligned);
+#endif
+
+/**
+ * hsiphash_1u32 - compute 32-bit hsiphash PRF value of a u32
+ * @first: first u32
+ * @key: the hsiphash key
+ */
+u32 hsiphash_1u32(const u32 first, const hsiphash_key_t *key)
+{
+	HPREAMBLE(4)
+	v3 ^= first;
+	HSIPROUND;
+	v0 ^= first;
+	HPOSTAMBLE
+}
+EXPORT_SYMBOL(hsiphash_1u32);
+
+/**
+ * hsiphash_2u32 - compute 32-bit hsiphash PRF value of 2 u32
+ * @first: first u32
+ * @second: second u32
+ * @key: the hsiphash key
+ */
+u32 hsiphash_2u32(const u32 first, const u32 second, const hsiphash_key_t *key)
+{
+	HPREAMBLE(8)
+	v3 ^= first;
+	HSIPROUND;
+	v0 ^= first;
+	v3 ^= second;
+	HSIPROUND;
+	v0 ^= second;
+	HPOSTAMBLE
+}
+EXPORT_SYMBOL(hsiphash_2u32);
+
+/**
+ * hsiphash_3u32 - compute 32-bit hsiphash PRF value of 3 u32
+ * @first: first u32
+ * @second: second u32
+ * @third: third u32
+ * @key: the hsiphash key
+ */
+u32 hsiphash_3u32(const u32 first, const u32 second, const u32 third,
+		  const hsiphash_key_t *key)
+{
+	HPREAMBLE(12)
+	v3 ^= first;
+	HSIPROUND;
+	v0 ^= first;
+	v3 ^= second;
+	HSIPROUND;
+	v0 ^= second;
+	v3 ^= third;
+	HSIPROUND;
+	v0 ^= third;
+	HPOSTAMBLE
+}
+EXPORT_SYMBOL(hsiphash_3u32);
+
+/**
+ * hsiphash_4u32 - compute 32-bit hsiphash PRF value of 4 u32
+ * @first: first u32
+ * @second: second u32
+ * @third: third u32
+ * @forth: forth u32
+ * @key: the hsiphash key
+ */
+u32 hsiphash_4u32(const u32 first, const u32 second, const u32 third,
+		  const u32 forth, const hsiphash_key_t *key)
+{
+	HPREAMBLE(16)
+	v3 ^= first;
+	HSIPROUND;
+	v0 ^= first;
+	v3 ^= second;
+	HSIPROUND;
+	v0 ^= second;
+	v3 ^= third;
+	HSIPROUND;
+	v0 ^= third;
+	v3 ^= forth;
+	HSIPROUND;
+	v0 ^= forth;
+	HPOSTAMBLE
+}
+EXPORT_SYMBOL(hsiphash_4u32);
+#endif
diff --git a/lib/test_siphash.c b/lib/test_siphash.c
new file mode 100644
index 000000000000..a6d854d933bf
--- /dev/null
+++ b/lib/test_siphash.c
@@ -0,0 +1,223 @@
+/* Test cases for siphash.c
+ *
+ * Copyright (C) 2016 Jason A. Donenfeld <Jason@xxxxxxxxx>. All Rights Reserved.
+ *
+ * This file is provided under a dual BSD/GPLv2 license.
+ *
+ * SipHash: a fast short-input PRF
+ * https://131002.net/siphash/
+ *
+ * This implementation is specifically for SipHash2-4 for a secure PRF
+ * and HalfSipHash1-3/SipHash1-3 for an insecure PRF only suitable for
+ * hashtables.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/siphash.h>
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/errno.h>
+#include <linux/module.h>
+
+/* Test vectors taken from reference source available at:
+ *     https://github.com/veorq/SipHash
+ */
+
+static const siphash_key_t test_key_siphash =
+	{{ 0x0706050403020100ULL, 0x0f0e0d0c0b0a0908ULL }};
+
+static const u64 test_vectors_siphash[64] = {
+	0x726fdb47dd0e0e31ULL, 0x74f839c593dc67fdULL, 0x0d6c8009d9a94f5aULL,
+	0x85676696d7fb7e2dULL, 0xcf2794e0277187b7ULL, 0x18765564cd99a68dULL,
+	0xcbc9466e58fee3ceULL, 0xab0200f58b01d137ULL, 0x93f5f5799a932462ULL,
+	0x9e0082df0ba9e4b0ULL, 0x7a5dbbc594ddb9f3ULL, 0xf4b32f46226bada7ULL,
+	0x751e8fbc860ee5fbULL, 0x14ea5627c0843d90ULL, 0xf723ca908e7af2eeULL,
+	0xa129ca6149be45e5ULL, 0x3f2acc7f57c29bdbULL, 0x699ae9f52cbe4794ULL,
+	0x4bc1b3f0968dd39cULL, 0xbb6dc91da77961bdULL, 0xbed65cf21aa2ee98ULL,
+	0xd0f2cbb02e3b67c7ULL, 0x93536795e3a33e88ULL, 0xa80c038ccd5ccec8ULL,
+	0xb8ad50c6f649af94ULL, 0xbce192de8a85b8eaULL, 0x17d835b85bbb15f3ULL,
+	0x2f2e6163076bcfadULL, 0xde4daaaca71dc9a5ULL, 0xa6a2506687956571ULL,
+	0xad87a3535c49ef28ULL, 0x32d892fad841c342ULL, 0x7127512f72f27cceULL,
+	0xa7f32346f95978e3ULL, 0x12e0b01abb051238ULL, 0x15e034d40fa197aeULL,
+	0x314dffbe0815a3b4ULL, 0x027990f029623981ULL, 0xcadcd4e59ef40c4dULL,
+	0x9abfd8766a33735cULL, 0x0e3ea96b5304a7d0ULL, 0xad0c42d6fc585992ULL,
+	0x187306c89bc215a9ULL, 0xd4a60abcf3792b95ULL, 0xf935451de4f21df2ULL,
+	0xa9538f0419755787ULL, 0xdb9acddff56ca510ULL, 0xd06c98cd5c0975ebULL,
+	0xe612a3cb9ecba951ULL, 0xc766e62cfcadaf96ULL, 0xee64435a9752fe72ULL,
+	0xa192d576b245165aULL, 0x0a8787bf8ecb74b2ULL, 0x81b3e73d20b49b6fULL,
+	0x7fa8220ba3b2eceaULL, 0x245731c13ca42499ULL, 0xb78dbfaf3a8d83bdULL,
+	0xea1ad565322a1a0bULL, 0x60e61c23a3795013ULL, 0x6606d7e446282b93ULL,
+	0x6ca4ecb15c5f91e1ULL, 0x9f626da15c9625f3ULL, 0xe51b38608ef25f57ULL,
+	0x958a324ceb064572ULL
+};
+
+#if BITS_PER_LONG == 64
+static const hsiphash_key_t test_key_hsiphash =
+	{{ 0x0706050403020100ULL, 0x0f0e0d0c0b0a0908ULL }};
+
+static const u32 test_vectors_hsiphash[64] = {
+	0x050fc4dcU, 0x7d57ca93U, 0x4dc7d44dU,
+	0xe7ddf7fbU, 0x88d38328U, 0x49533b67U,
+	0xc59f22a7U, 0x9bb11140U, 0x8d299a8eU,
+	0x6c063de4U, 0x92ff097fU, 0xf94dc352U,
+	0x57b4d9a2U, 0x1229ffa7U, 0xc0f95d34U,
+	0x2a519956U, 0x7d908b66U, 0x63dbd80cU,
+	0xb473e63eU, 0x8d297d1cU, 0xa6cce040U,
+	0x2b45f844U, 0xa320872eU, 0xdae6c123U,
+	0x67349c8cU, 0x705b0979U, 0xca9913a5U,
+	0x4ade3b35U, 0xef6cd00dU, 0x4ab1e1f4U,
+	0x43c5e663U, 0x8c21d1bcU, 0x16a7b60dU,
+	0x7a8ff9bfU, 0x1f2a753eU, 0xbf186b91U,
+	0xada26206U, 0xa3c33057U, 0xae3a36a1U,
+	0x7b108392U, 0x99e41531U, 0x3f1ad944U,
+	0xc8138825U, 0xc28949a6U, 0xfaf8876bU,
+	0x9f042196U, 0x68b1d623U, 0x8b5114fdU,
+	0xdf074c46U, 0x12cc86b3U, 0x0a52098fU,
+	0x9d292f9aU, 0xa2f41f12U, 0x43a71ed0U,
+	0x73f0bce6U, 0x70a7e980U, 0x243c6d75U,
+	0xfdb71513U, 0xa67d8a08U, 0xb7e8f148U,
+	0xf7a644eeU, 0x0f1837f2U, 0x4b6694e0U,
+	0xb7bbb3a8U
+};
+#else
+static const hsiphash_key_t test_key_hsiphash =
+	{{ 0x03020100U, 0x07060504U }};
+
+static const u32 test_vectors_hsiphash[64] = {
+	0x5814c896U, 0xe7e864caU, 0xbc4b0e30U,
+	0x01539939U, 0x7e059ea6U, 0x88e3d89bU,
+	0xa0080b65U, 0x9d38d9d6U, 0x577999b1U,
+	0xc839caedU, 0xe4fa32cfU, 0x959246eeU,
+	0x6b28096cU, 0x66dd9cd6U, 0x16658a7cU,
+	0xd0257b04U, 0x8b31d501U, 0x2b1cd04bU,
+	0x06712339U, 0x522aca67U, 0x911bb605U,
+	0x90a65f0eU, 0xf826ef7bU, 0x62512debU,
+	0x57150ad7U, 0x5d473507U, 0x1ec47442U,
+	0xab64afd3U, 0x0a4100d0U, 0x6d2ce652U,
+	0x2331b6a3U, 0x08d8791aU, 0xbc6dda8dU,
+	0xe0f6c934U, 0xb0652033U, 0x9b9851ccU,
+	0x7c46fb7fU, 0x732ba8cbU, 0xf142997aU,
+	0xfcc9aa1bU, 0x05327eb2U, 0xe110131cU,
+	0xf9e5e7c0U, 0xa7d708a6U, 0x11795ab1U,
+	0x65671619U, 0x9f5fff91U, 0xd89c5267U,
+	0x007783ebU, 0x95766243U, 0xab639262U,
+	0x9c7e1390U, 0xc368dda6U, 0x38ddc455U,
+	0xfa13d379U, 0x979ea4e8U, 0x53ecd77eU,
+	0x2ee80657U, 0x33dbb66aU, 0xae3f0577U,
+	0x88b4c4ccU, 0x3e7f480bU, 0x74c1ebf8U,
+	0x87178304U
+};
+#endif
+
+static int __init siphash_test_init(void)
+{
+	u8 in[64] __aligned(SIPHASH_ALIGNMENT);
+	u8 in_unaligned[65] __aligned(SIPHASH_ALIGNMENT);
+	u8 i;
+	int ret = 0;
+
+	for (i = 0; i < 64; ++i) {
+		in[i] = i;
+		in_unaligned[i + 1] = i;
+		if (siphash(in, i, &test_key_siphash) !=
+						test_vectors_siphash[i]) {
+			pr_info("siphash self-test aligned %u: FAIL\n", i + 1);
+			ret = -EINVAL;
+		}
+		if (siphash(in_unaligned + 1, i, &test_key_siphash) !=
+						test_vectors_siphash[i]) {
+			pr_info("siphash self-test unaligned %u: FAIL\n", i + 1);
+			ret = -EINVAL;
+		}
+		if (hsiphash(in, i, &test_key_hsiphash) !=
+						test_vectors_hsiphash[i]) {
+			pr_info("hsiphash self-test aligned %u: FAIL\n", i + 1);
+			ret = -EINVAL;
+		}
+		if (hsiphash(in_unaligned + 1, i, &test_key_hsiphash) !=
+						test_vectors_hsiphash[i]) {
+			pr_info("hsiphash self-test unaligned %u: FAIL\n", i + 1);
+			ret = -EINVAL;
+		}
+	}
+	if (siphash_1u64(0x0706050403020100ULL, &test_key_siphash) !=
+						test_vectors_siphash[8]) {
+		pr_info("siphash self-test 1u64: FAIL\n");
+		ret = -EINVAL;
+	}
+	if (siphash_2u64(0x0706050403020100ULL, 0x0f0e0d0c0b0a0908ULL,
+			 &test_key_siphash) != test_vectors_siphash[16]) {
+		pr_info("siphash self-test 2u64: FAIL\n");
+		ret = -EINVAL;
+	}
+	if (siphash_3u64(0x0706050403020100ULL, 0x0f0e0d0c0b0a0908ULL,
+			 0x1716151413121110ULL, &test_key_siphash) !=
+						test_vectors_siphash[24]) {
+		pr_info("siphash self-test 3u64: FAIL\n");
+		ret = -EINVAL;
+	}
+	if (siphash_4u64(0x0706050403020100ULL, 0x0f0e0d0c0b0a0908ULL,
+			 0x1716151413121110ULL, 0x1f1e1d1c1b1a1918ULL,
+			 &test_key_siphash) != test_vectors_siphash[32]) {
+		pr_info("siphash self-test 4u64: FAIL\n");
+		ret = -EINVAL;
+	}
+	if (siphash_1u32(0x03020100U, &test_key_siphash) !=
+						test_vectors_siphash[4]) {
+		pr_info("siphash self-test 1u32: FAIL\n");
+		ret = -EINVAL;
+	}
+	if (siphash_2u32(0x03020100U, 0x07060504U, &test_key_siphash) !=
+						test_vectors_siphash[8]) {
+		pr_info("siphash self-test 2u32: FAIL\n");
+		ret = -EINVAL;
+	}
+	if (siphash_3u32(0x03020100U, 0x07060504U,
+			 0x0b0a0908U, &test_key_siphash) !=
+						test_vectors_siphash[12]) {
+		pr_info("siphash self-test 3u32: FAIL\n");
+		ret = -EINVAL;
+	}
+	if (siphash_4u32(0x03020100U, 0x07060504U,
+			 0x0b0a0908U, 0x0f0e0d0cU, &test_key_siphash) !=
+						test_vectors_siphash[16]) {
+		pr_info("siphash self-test 4u32: FAIL\n");
+		ret = -EINVAL;
+	}
+	if (hsiphash_1u32(0x03020100U, &test_key_hsiphash) !=
+						test_vectors_hsiphash[4]) {
+		pr_info("hsiphash self-test 1u32: FAIL\n");
+		ret = -EINVAL;
+	}
+	if (hsiphash_2u32(0x03020100U, 0x07060504U, &test_key_hsiphash) !=
+						test_vectors_hsiphash[8]) {
+		pr_info("hsiphash self-test 2u32: FAIL\n");
+		ret = -EINVAL;
+	}
+	if (hsiphash_3u32(0x03020100U, 0x07060504U,
+			  0x0b0a0908U, &test_key_hsiphash) !=
+						test_vectors_hsiphash[12]) {
+		pr_info("hsiphash self-test 3u32: FAIL\n");
+		ret = -EINVAL;
+	}
+	if (hsiphash_4u32(0x03020100U, 0x07060504U,
+			  0x0b0a0908U, 0x0f0e0d0cU, &test_key_hsiphash) !=
+						test_vectors_hsiphash[16]) {
+		pr_info("hsiphash self-test 4u32: FAIL\n");
+		ret = -EINVAL;
+	}
+	if (!ret)
+		pr_info("self-tests: pass\n");
+	return ret;
+}
+
+static void __exit siphash_test_exit(void)
+{
+}
+
+module_init(siphash_test_init);
+module_exit(siphash_test_exit);
+
+MODULE_AUTHOR("Jason A. Donenfeld <Jason@xxxxxxxxx>");
+MODULE_LICENSE("Dual BSD/GPL");
diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c
index 1a87cf78fadc..d9471e3ef216 100644
--- a/net/bridge/netfilter/ebtables.c
+++ b/net/bridge/netfilter/ebtables.c
@@ -2280,8 +2280,10 @@ static int compat_do_replace(struct net *net, void __user *user,
 	state.buf_kern_len = size64;
 
 	ret = compat_copy_entries(entries_tmp, tmp.entries_size, &state);
-	if (WARN_ON(ret < 0))
+	if (WARN_ON(ret < 0)) {
+		vfree(entries_tmp);
 		goto out_unlock;
+	}
 
 	vfree(entries_tmp);
 	tmp.entries_size = size64;
diff --git a/net/core/stream.c b/net/core/stream.c
index b96f7a79e544..3089b014bb53 100644
--- a/net/core/stream.c
+++ b/net/core/stream.c
@@ -119,7 +119,6 @@ int sk_stream_wait_memory(struct sock *sk, long *timeo_p)
 	int err = 0;
 	long vm_wait = 0;
 	long current_timeo = *timeo_p;
-	bool noblock = (*timeo_p ? false : true);
 	DEFINE_WAIT(wait);
 
 	if (sk_stream_memory_free(sk))
@@ -132,11 +131,8 @@ int sk_stream_wait_memory(struct sock *sk, long *timeo_p)
 
 		if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN))
 			goto do_error;
-		if (!*timeo_p) {
-			if (noblock)
-				set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
-			goto do_nonblock;
-		}
+		if (!*timeo_p)
+			goto do_eagain;
 		if (signal_pending(current))
 			goto do_interrupted;
 		sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk);
@@ -168,7 +164,13 @@ out:
 do_error:
 	err = -EPIPE;
 	goto out;
-do_nonblock:
+do_eagain:
+	/* Make sure that whenever EAGAIN is returned, EPOLLOUT event can
+	 * be generated later.
+	 * When TCP receives ACK packets that make room, tcp_check_space()
+	 * only calls tcp_new_space() if SOCK_NOSPACE is set.
+	 */
+	set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
 	err = -EAGAIN;
 	goto out;
 do_interrupted:
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index a58effba760a..3c605a788ba1 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -490,15 +490,17 @@ EXPORT_SYMBOL(ip_idents_reserve);
 
 void __ip_select_ident(struct net *net, struct iphdr *iph, int segs)
 {
-	static u32 ip_idents_hashrnd __read_mostly;
 	u32 hash, id;
 
-	net_get_random_once(&ip_idents_hashrnd, sizeof(ip_idents_hashrnd));
+	/* Note the following code is not safe, but this is okay. */
+	if (unlikely(siphash_key_is_zero(&net->ipv4.ip_id_key)))
+		get_random_bytes(&net->ipv4.ip_id_key,
+				 sizeof(net->ipv4.ip_id_key));
 
-	hash = jhash_3words((__force u32)iph->daddr,
+	hash = siphash_3u32((__force u32)iph->daddr,
 			    (__force u32)iph->saddr,
-			    iph->protocol ^ net_hash_mix(net),
-			    ip_idents_hashrnd);
+			    iph->protocol,
+			    &net->ipv4.ip_id_key);
 	id = ip_idents_reserve(hash, segs);
 	iph->id = htons(id);
 }
diff --git a/net/ipv6/output_core.c b/net/ipv6/output_core.c
index f99a04674419..6b896cc9604e 100644
--- a/net/ipv6/output_core.c
+++ b/net/ipv6/output_core.c
@@ -10,15 +10,25 @@
 #include <net/secure_seq.h>
 #include <linux/netfilter.h>
 
-static u32 __ipv6_select_ident(struct net *net, u32 hashrnd,
+static u32 __ipv6_select_ident(struct net *net,
 			       const struct in6_addr *dst,
 			       const struct in6_addr *src)
 {
+	const struct {
+		struct in6_addr dst;
+		struct in6_addr src;
+	} __aligned(SIPHASH_ALIGNMENT) combined = {
+		.dst = *dst,
+		.src = *src,
+	};
 	u32 hash, id;
 
-	hash = __ipv6_addr_jhash(dst, hashrnd);
-	hash = __ipv6_addr_jhash(src, hash);
-	hash ^= net_hash_mix(net);
+	/* Note the following code is not safe, but this is okay. */
+	if (unlikely(siphash_key_is_zero(&net->ipv4.ip_id_key)))
+		get_random_bytes(&net->ipv4.ip_id_key,
+				 sizeof(net->ipv4.ip_id_key));
+
+	hash = siphash(&combined, sizeof(combined), &net->ipv4.ip_id_key);
 
 	/* Treat id of 0 as unset and if we get 0 back from ip_idents_reserve,
 	 * set the hight order instead thus minimizing possible future
@@ -41,7 +51,6 @@ static u32 __ipv6_select_ident(struct net *net, u32 hashrnd,
  */
 void ipv6_proxy_select_ident(struct net *net, struct sk_buff *skb)
 {
-	static u32 ip6_proxy_idents_hashrnd __read_mostly;
 	struct in6_addr buf[2];
 	struct in6_addr *addrs;
 	u32 id;
@@ -53,11 +62,7 @@ void ipv6_proxy_select_ident(struct net *net, struct sk_buff *skb)
 	if (!addrs)
 		return;
 
-	net_get_random_once(&ip6_proxy_idents_hashrnd,
-			    sizeof(ip6_proxy_idents_hashrnd));
-
-	id = __ipv6_select_ident(net, ip6_proxy_idents_hashrnd,
-				 &addrs[1], &addrs[0]);
+	id = __ipv6_select_ident(net, &addrs[1], &addrs[0]);
 	skb_shinfo(skb)->ip6_frag_id = htonl(id);
 }
 EXPORT_SYMBOL_GPL(ipv6_proxy_select_ident);
@@ -66,12 +71,9 @@ __be32 ipv6_select_ident(struct net *net,
 			 const struct in6_addr *daddr,
 			 const struct in6_addr *saddr)
 {
-	static u32 ip6_idents_hashrnd __read_mostly;
 	u32 id;
 
-	net_get_random_once(&ip6_idents_hashrnd, sizeof(ip6_idents_hashrnd));
-
-	id = __ipv6_select_ident(net, ip6_idents_hashrnd, daddr, saddr);
+	id = __ipv6_select_ident(net, daddr, saddr);
 	return htonl(id);
 }
 EXPORT_SYMBOL(ipv6_select_ident);
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index 7349bf26ae7b..1999a7eaa692 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -1211,6 +1211,11 @@ static int ieee80211_add_station(struct wiphy *wiphy, struct net_device *dev,
 	if (is_multicast_ether_addr(mac))
 		return -EINVAL;
 
+	if (params->sta_flags_set & BIT(NL80211_STA_FLAG_TDLS_PEER) &&
+	    sdata->vif.type == NL80211_IFTYPE_STATION &&
+	    !sdata->u.mgd.associated)
+		return -EINVAL;
+
 	sta = sta_info_alloc(sdata, mac, GFP_KERNEL);
 	if (!sta)
 		return -ENOMEM;
@@ -1228,10 +1233,6 @@ static int ieee80211_add_station(struct wiphy *wiphy, struct net_device *dev,
 	if (params->sta_flags_set & BIT(NL80211_STA_FLAG_TDLS_PEER))
 		sta->sta.tdls = true;
 
-	if (sta->sta.tdls && sdata->vif.type == NL80211_IFTYPE_STATION &&
-	    !sdata->u.mgd.associated)
-		return -EINVAL;
-
 	err = sta_apply_parameters(local, sta, params);
 	if (err) {
 		sta_info_free(local, sta);
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 5f747089024f..de0aad12b91d 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -23,6 +23,7 @@
 #include <linux/slab.h>
 #include <linux/random.h>
 #include <linux/jhash.h>
+#include <linux/siphash.h>
 #include <linux/err.h>
 #include <linux/percpu.h>
 #include <linux/moduleparam.h>
@@ -234,6 +235,40 @@ nf_ct_invert_tuple(struct nf_conntrack_tuple *inverse,
 }
 EXPORT_SYMBOL_GPL(nf_ct_invert_tuple);
 
+/* Generate a almost-unique pseudo-id for a given conntrack.
+ *
+ * intentionally doesn't re-use any of the seeds used for hash
+ * table location, we assume id gets exposed to userspace.
+ *
+ * Following nf_conn items do not change throughout lifetime
+ * of the nf_conn:
+ *
+ * 1. nf_conn address
+ * 2. nf_conn->master address (normally NULL)
+ * 3. the associated net namespace
+ * 4. the original direction tuple
+ */
+u32 nf_ct_get_id(const struct nf_conn *ct)
+{
+	static __read_mostly siphash_key_t ct_id_seed;
+	unsigned long a, b, c, d;
+
+	net_get_random_once(&ct_id_seed, sizeof(ct_id_seed));
+
+	a = (unsigned long)ct;
+	b = (unsigned long)ct->master;
+	c = (unsigned long)nf_ct_net(ct);
+	d = (unsigned long)siphash(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple,
+				   sizeof(ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple),
+				   &ct_id_seed);
+#ifdef CONFIG_64BIT
+	return siphash_4u64((u64)a, (u64)b, (u64)c, (u64)d, &ct_id_seed);
+#else
+	return siphash_4u32((u32)a, (u32)b, (u32)c, (u32)d, &ct_id_seed);
+#endif
+}
+EXPORT_SYMBOL_GPL(nf_ct_get_id);
+
 static void
 clean_from_lists(struct nf_conn *ct)
 {
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index c68e020427ab..3a24c01cb909 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -29,6 +29,7 @@
 #include <linux/spinlock.h>
 #include <linux/interrupt.h>
 #include <linux/slab.h>
+#include <linux/siphash.h>
 
 #include <linux/netfilter.h>
 #include <net/netlink.h>
@@ -451,7 +452,9 @@ ctnetlink_dump_ct_seq_adj(struct sk_buff *skb, const struct nf_conn *ct)
 static inline int
 ctnetlink_dump_id(struct sk_buff *skb, const struct nf_conn *ct)
 {
-	if (nla_put_be32(skb, CTA_ID, htonl((unsigned long)ct)))
+	__be32 id = (__force __be32)nf_ct_get_id(ct);
+
+	if (nla_put_be32(skb, CTA_ID, id))
 		goto nla_put_failure;
 	return 0;
 
@@ -1159,8 +1162,9 @@ ctnetlink_del_conntrack(struct sock *ctnl, struct sk_buff *skb,
 	ct = nf_ct_tuplehash_to_ctrack(h);
 
 	if (cda[CTA_ID]) {
-		u_int32_t id = ntohl(nla_get_be32(cda[CTA_ID]));
-		if (id != (u32)(unsigned long)ct) {
+		__be32 id = nla_get_be32(cda[CTA_ID]);
+
+		if (id != (__force __be32)nf_ct_get_id(ct)) {
 			nf_ct_put(ct);
 			return -ENOENT;
 		}
@@ -2480,6 +2484,25 @@ nla_put_failure:
 
 static const union nf_inet_addr any_addr;
 
+static __be32 nf_expect_get_id(const struct nf_conntrack_expect *exp)
+{
+	static __read_mostly siphash_key_t exp_id_seed;
+	unsigned long a, b, c, d;
+
+	net_get_random_once(&exp_id_seed, sizeof(exp_id_seed));
+
+	a = (unsigned long)exp;
+	b = (unsigned long)exp->helper;
+	c = (unsigned long)exp->master;
+	d = (unsigned long)siphash(&exp->tuple, sizeof(exp->tuple), &exp_id_seed);
+
+#ifdef CONFIG_64BIT
+	return (__force __be32)siphash_4u64((u64)a, (u64)b, (u64)c, (u64)d, &exp_id_seed);
+#else
+	return (__force __be32)siphash_4u32((u32)a, (u32)b, (u32)c, (u32)d, &exp_id_seed);
+#endif
+}
+
 static int
 ctnetlink_exp_dump_expect(struct sk_buff *skb,
 			  const struct nf_conntrack_expect *exp)
@@ -2527,7 +2550,7 @@ ctnetlink_exp_dump_expect(struct sk_buff *skb,
 	}
 #endif
 	if (nla_put_be32(skb, CTA_EXPECT_TIMEOUT, htonl(timeout)) ||
-	    nla_put_be32(skb, CTA_EXPECT_ID, htonl((unsigned long)exp)) ||
+	    nla_put_be32(skb, CTA_EXPECT_ID, nf_expect_get_id(exp)) ||
 	    nla_put_be32(skb, CTA_EXPECT_FLAGS, htonl(exp->flags)) ||
 	    nla_put_be32(skb, CTA_EXPECT_CLASS, htonl(exp->class)))
 		goto nla_put_failure;
@@ -2824,7 +2847,8 @@ ctnetlink_get_expect(struct sock *ctnl, struct sk_buff *skb,
 
 	if (cda[CTA_EXPECT_ID]) {
 		__be32 id = nla_get_be32(cda[CTA_EXPECT_ID]);
-		if (ntohl(id) != (u32)(unsigned long)exp) {
+
+		if (id != nf_expect_get_id(exp)) {
 			nf_ct_expect_put(exp);
 			return -ENOENT;
 		}
diff --git a/net/wireless/reg.c b/net/wireless/reg.c
index 429abf421906..6a670a373e29 100644
--- a/net/wireless/reg.c
+++ b/net/wireless/reg.c
@@ -2234,7 +2234,7 @@ static void reg_process_pending_hints(void)
 
 	/* When last_request->processed becomes true this will be rescheduled */
 	if (lr && !lr->processed) {
-		reg_process_hint(lr);
+		pr_debug("Pending regulatory request, waiting for it to be processed...\n");
 		return;
 	}
 
diff --git a/sound/core/seq/seq_clientmgr.c b/sound/core/seq/seq_clientmgr.c
index 7fa0219c9758..331a2b00e53f 100644
--- a/sound/core/seq/seq_clientmgr.c
+++ b/sound/core/seq/seq_clientmgr.c
@@ -1906,8 +1906,7 @@ static int snd_seq_ioctl_get_client_pool(struct snd_seq_client *client,
 	if (cptr->type == USER_CLIENT) {
 		info.input_pool = cptr->data.user.fifo_pool_size;
 		info.input_free = info.input_pool;
-		if (cptr->data.user.fifo)
-			info.input_free = snd_seq_unused_cells(cptr->data.user.fifo->pool);
+		info.input_free = snd_seq_fifo_unused_cells(cptr->data.user.fifo);
 	} else {
 		info.input_pool = 0;
 		info.input_free = 0;
diff --git a/sound/core/seq/seq_fifo.c b/sound/core/seq/seq_fifo.c
index 9acbed1ac982..d9f5428ee995 100644
--- a/sound/core/seq/seq_fifo.c
+++ b/sound/core/seq/seq_fifo.c
@@ -278,3 +278,20 @@ int snd_seq_fifo_resize(struct snd_seq_fifo *f, int poolsize)
 
 	return 0;
 }
+
+/* get the number of unused cells safely */
+int snd_seq_fifo_unused_cells(struct snd_seq_fifo *f)
+{
+	unsigned long flags;
+	int cells;
+
+	if (!f)
+		return 0;
+
+	snd_use_lock_use(&f->use_lock);
+	spin_lock_irqsave(&f->lock, flags);
+	cells = snd_seq_unused_cells(f->pool);
+	spin_unlock_irqrestore(&f->lock, flags);
+	snd_use_lock_free(&f->use_lock);
+	return cells;
+}
diff --git a/sound/core/seq/seq_fifo.h b/sound/core/seq/seq_fifo.h
index 062c446e7867..5d38a0d7f0cd 100644
--- a/sound/core/seq/seq_fifo.h
+++ b/sound/core/seq/seq_fifo.h
@@ -68,5 +68,7 @@ int snd_seq_fifo_poll_wait(struct snd_seq_fifo *f, struct file *file, poll_table
 /* resize pool in fifo */
 int snd_seq_fifo_resize(struct snd_seq_fifo *f, int poolsize);
 
+/* get the number of unused cells safely */
+int snd_seq_fifo_unused_cells(struct snd_seq_fifo *f);
 
 #endif
diff --git a/sound/soc/davinci/davinci-mcasp.c b/sound/soc/davinci/davinci-mcasp.c
index 512ec25c9ead..2f7be6cee98e 100644
--- a/sound/soc/davinci/davinci-mcasp.c
+++ b/sound/soc/davinci/davinci-mcasp.c
@@ -1128,6 +1128,28 @@ static int davinci_mcasp_trigger(struct snd_pcm_substream *substream,
 	return ret;
 }
 
+static int davinci_mcasp_hw_rule_slot_width(struct snd_pcm_hw_params *params,
+					    struct snd_pcm_hw_rule *rule)
+{
+	struct davinci_mcasp_ruledata *rd = rule->private;
+	struct snd_mask *fmt = hw_param_mask(params, SNDRV_PCM_HW_PARAM_FORMAT);
+	struct snd_mask nfmt;
+	int i, slot_width;
+
+	snd_mask_none(&nfmt);
+	slot_width = rd->mcasp->slot_width;
+
+	for (i = 0; i <= SNDRV_PCM_FORMAT_LAST; i++) {
+		if (snd_mask_test(fmt, i)) {
+			if (snd_pcm_format_width(i) <= slot_width) {
+				snd_mask_set(&nfmt, i);
+			}
+		}
+	}
+
+	return snd_mask_refine(fmt, &nfmt);
+}
+
 static const unsigned int davinci_mcasp_dai_rates[] = {
 	8000, 11025, 16000, 22050, 32000, 44100, 48000, 64000,
 	88200, 96000, 176400, 192000,
@@ -1219,7 +1241,7 @@ static int davinci_mcasp_startup(struct snd_pcm_substream *substream,
 	struct davinci_mcasp_ruledata *ruledata =
 					&mcasp->ruledata[substream->stream];
 	u32 max_channels = 0;
-	int i, dir;
+	int i, dir, ret;
 	int tdm_slots = mcasp->tdm_slots;
 
 	if (mcasp->tdm_mask[substream->stream])
@@ -1244,6 +1266,7 @@ static int davinci_mcasp_startup(struct snd_pcm_substream *substream,
 			max_channels++;
 	}
 	ruledata->serializers = max_channels;
+	ruledata->mcasp = mcasp;
 	max_channels *= tdm_slots;
 	/*
 	 * If the already active stream has less channels than the calculated
@@ -1269,20 +1292,22 @@ static int davinci_mcasp_startup(struct snd_pcm_substream *substream,
 				   0, SNDRV_PCM_HW_PARAM_CHANNELS,
 				   &mcasp->chconstr[substream->stream]);
 
-	if (mcasp->slot_width)
-		snd_pcm_hw_constraint_minmax(substream->runtime,
-					     SNDRV_PCM_HW_PARAM_SAMPLE_BITS,
-					     8, mcasp->slot_width);
+	if (mcasp->slot_width) {
+		/* Only allow formats require <= slot_width bits on the bus */
+		ret = snd_pcm_hw_rule_add(substream->runtime, 0,
+					  SNDRV_PCM_HW_PARAM_FORMAT,
+					  davinci_mcasp_hw_rule_slot_width,
+					  ruledata,
+					  SNDRV_PCM_HW_PARAM_FORMAT, -1);
+		if (ret)
+			return ret;
+	}
 
 	/*
 	 * If we rely on implicit BCLK divider setting we should
 	 * set constraints based on what we can provide.
 	 */
 	if (mcasp->bclk_master && mcasp->bclk_div == 0 && mcasp->sysclk_freq) {
-		int ret;
-
-		ruledata->mcasp = mcasp;
-
 		ret = snd_pcm_hw_rule_add(substream->runtime, 0,
 					  SNDRV_PCM_HW_PARAM_RATE,
 					  davinci_mcasp_hw_rule_rate,
diff --git a/sound/usb/mixer.c b/sound/usb/mixer.c
index 1f7eb3816cd7..e24572fd6e30 100644
--- a/sound/usb/mixer.c
+++ b/sound/usb/mixer.c
@@ -81,6 +81,7 @@ struct mixer_build {
 	unsigned char *buffer;
 	unsigned int buflen;
 	DECLARE_BITMAP(unitbitmap, MAX_ID_ELEMS);
+	DECLARE_BITMAP(termbitmap, MAX_ID_ELEMS);
 	struct usb_audio_term oterm;
 	const struct usbmix_name_map *map;
 	const struct usbmix_selector_map *selector_map;
@@ -709,15 +710,24 @@ static int get_term_name(struct mixer_build *state, struct usb_audio_term *iterm
  * parse the source unit recursively until it reaches to a terminal
  * or a branched unit.
  */
-static int check_input_term(struct mixer_build *state, int id,
+static int __check_input_term(struct mixer_build *state, int id,
 			    struct usb_audio_term *term)
 {
 	int err;
 	void *p1;
+	unsigned char *hdr;
 
 	memset(term, 0, sizeof(*term));
-	while ((p1 = find_audio_control_unit(state, id)) != NULL) {
-		unsigned char *hdr = p1;
+	for (;;) {
+		/* a loop in the terminal chain? */
+		if (test_and_set_bit(id, state->termbitmap))
+			return -EINVAL;
+
+		p1 = find_audio_control_unit(state, id);
+		if (!p1)
+			break;
+
+		hdr = p1;
 		term->id = id;
 		switch (hdr[2]) {
 		case UAC_INPUT_TERMINAL:
@@ -732,7 +742,7 @@ static int check_input_term(struct mixer_build *state, int id,
 
 				/* call recursively to verify that the
 				 * referenced clock entity is valid */
-				err = check_input_term(state, d->bCSourceID, term);
+				err = __check_input_term(state, d->bCSourceID, term);
 				if (err < 0)
 					return err;
 
@@ -764,7 +774,7 @@ static int check_input_term(struct mixer_build *state, int id,
 		case UAC2_CLOCK_SELECTOR: {
 			struct uac_selector_unit_descriptor *d = p1;
 			/* call recursively to retrieve the channel info */
-			err = check_input_term(state, d->baSourceID[0], term);
+			err = __check_input_term(state, d->baSourceID[0], term);
 			if (err < 0)
 				return err;
 			term->type = d->bDescriptorSubtype << 16; /* virtual type */
@@ -811,6 +821,15 @@ static int check_input_term(struct mixer_build *state, int id,
 	return -ENODEV;
 }
 
+
+static int check_input_term(struct mixer_build *state, int id,
+			    struct usb_audio_term *term)
+{
+	memset(term, 0, sizeof(*term));
+	memset(state->termbitmap, 0, sizeof(state->termbitmap));
+	return __check_input_term(state, id, term);
+}
+
 /*
  * Feature Unit
  */
@@ -1628,6 +1647,7 @@ static int parse_audio_mixer_unit(struct mixer_build *state, int unitid,
 	int pin, ich, err;
 
 	if (desc->bLength < 11 || !(input_pins = desc->bNrInPins) ||
+	    desc->bLength < sizeof(*desc) + desc->bNrInPins ||
 	    !(num_outs = uac_mixer_unit_bNrChannels(desc))) {
 		usb_audio_err(state->chip,
 			      "invalid MIXER UNIT descriptor %d\n",
diff --git a/tools/hv/hv_kvp_daemon.c b/tools/hv/hv_kvp_daemon.c
index 177480066816..fffc7c418459 100644
--- a/tools/hv/hv_kvp_daemon.c
+++ b/tools/hv/hv_kvp_daemon.c
@@ -1379,6 +1379,8 @@ int main(int argc, char *argv[])
 			daemonize = 0;
 			break;
 		case 'h':
+			print_usage(argv);
+			exit(0);
 		default:
 			print_usage(argv);
 			exit(EXIT_FAILURE);
diff --git a/tools/hv/hv_vss_daemon.c b/tools/hv/hv_vss_daemon.c
index 5d51d6ff08e6..b5465f92ed50 100644
--- a/tools/hv/hv_vss_daemon.c
+++ b/tools/hv/hv_vss_daemon.c
@@ -164,6 +164,8 @@ int main(int argc, char *argv[])
 			daemonize = 0;
 			break;
 		case 'h':
+			print_usage(argv);
+			exit(0);
 		default:
 			print_usage(argv);
 			exit(EXIT_FAILURE);
diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c
index df41deed0320..3bfba81d1911 100644
--- a/tools/perf/bench/numa.c
+++ b/tools/perf/bench/numa.c
@@ -370,8 +370,10 @@ static u8 *alloc_data(ssize_t bytes0, int map_flags,
 
 	/* Allocate and initialize all memory on CPU#0: */
 	if (init_cpu0) {
-		orig_mask = bind_to_node(0);
-		bind_to_memnode(0);
+		int node = numa_node_of_cpu(0);
+
+		orig_mask = bind_to_node(node);
+		bind_to_memnode(node);
 	}
 
 	bytes = bytes0 + HPSIZE;
diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c
index 1a35ab044c11..54af2f2e2ee4 100644
--- a/tools/perf/tests/parse-events.c
+++ b/tools/perf/tests/parse-events.c
@@ -12,32 +12,6 @@
 #define PERF_TP_SAMPLE_TYPE (PERF_SAMPLE_RAW | PERF_SAMPLE_TIME | \
 			     PERF_SAMPLE_CPU | PERF_SAMPLE_PERIOD)
 
-#if defined(__s390x__)
-/* Return true if kvm module is available and loaded. Test this
- * and retun success when trace point kvm_s390_create_vm
- * exists. Otherwise this test always fails.
- */
-static bool kvm_s390_create_vm_valid(void)
-{
-	char *eventfile;
-	bool rc = false;
-
-	eventfile = get_events_file("kvm-s390");
-
-	if (eventfile) {
-		DIR *mydir = opendir(eventfile);
-
-		if (mydir) {
-			rc = true;
-			closedir(mydir);
-		}
-		put_events_file(eventfile);
-	}
-
-	return rc;
-}
-#endif
-
 static int test__checkevent_tracepoint(struct perf_evlist *evlist)
 {
 	struct perf_evsel *evsel = perf_evlist__first(evlist);
@@ -1587,7 +1561,6 @@ static struct evlist_test test__events[] = {
 	{
 		.name  = "kvm-s390:kvm_s390_create_vm",
 		.check = test__checkevent_tracepoint,
-		.valid = kvm_s390_create_vm_valid,
 		.id    = 100,
 	},
 #endif
diff --git a/tools/testing/selftests/kvm/config b/tools/testing/selftests/kvm/config
new file mode 100644
index 000000000000..63ed533f73d6
--- /dev/null
+++ b/tools/testing/selftests/kvm/config
@@ -0,0 +1,3 @@
+CONFIG_KVM=y
+CONFIG_KVM_INTEL=y
+CONFIG_KVM_AMD=y