Merge branch '4.7-fixes' into mips-for-linux-next

Documentation/x86/intel_mpx.txt

@@ -45,7 +45,7 @@ is how we expect the compiler, application and kernel to work together.
    MPX-instrumented.
 3) The kernel detects that the CPU has MPX, allows the new prctl() to
    succeed, and notes the location of the bounds directory. Userspace is
-   expected to keep the bounds directory at that locationWe note it
+   expected to keep the bounds directory at that location. We note it
    instead of reading it each time because the 'xsave' operation needed
    to access the bounds directory register is an expensive operation.
 4) If the application needs to spill bounds out of the 4 registers, it
@@ -167,7 +167,7 @@ If a #BR is generated due to a bounds violation caused by MPX.
 We need to decode MPX instructions to get violation address and
 set this address into extended struct siginfo.
 
-The _sigfault feild of struct siginfo is extended as follow:
+The _sigfault field of struct siginfo is extended as follow:
 
 87		/* SIGILL, SIGFPE, SIGSEGV, SIGBUS */
 88		struct {
@@ -240,5 +240,5 @@ them at the same bounds table.
 This is allowed architecturally.  See more information "Intel(R) Architecture
 Instruction Set Extensions Programming Reference" (9.3.4).
 
-However, if users did this, the kernel might be fooled in to unmaping an
+However, if users did this, the kernel might be fooled in to unmapping an
 in-use bounds table since it does not recognize sharing.

Documentation/x86/tlb.txt

@@ -5,7 +5,7 @@ memory, it has two choices:
     from areas other than the one we are trying to flush will be
     destroyed and must be refilled later, at some cost.
  2. Use the invlpg instruction to invalidate a single page at a
-    time.  This could potentialy cost many more instructions, but
+    time.  This could potentially cost many more instructions, but
     it is a much more precise operation, causing no collateral
     damage to other TLB entries.
 
@@ -19,7 +19,7 @@ Which method to do depends on a few things:
     work.
  3. The size of the TLB.  The larger the TLB, the more collateral
     damage we do with a full flush.  So, the larger the TLB, the
-    more attrative an individual flush looks.  Data and
+    more attractive an individual flush looks.  Data and
     instructions have separate TLBs, as do different page sizes.
  4. The microarchitecture.  The TLB has become a multi-level
     cache on modern CPUs, and the global flushes have become more

Documentation/x86/x86_64/machinecheck

@@ -36,7 +36,7 @@ between all CPUs.
 
 check_interval
 	How often to poll for corrected machine check errors, in seconds
-	(Note output is hexademical). Default 5 minutes.  When the poller
+	(Note output is hexadecimal). Default 5 minutes.  When the poller
 	finds MCEs it triggers an exponential speedup (poll more often) on
 	the polling interval.  When the poller stops finding MCEs, it
 	triggers an exponential backoff (poll less often) on the polling

Makefile

@@ -1,7 +1,7 @@
 VERSION = 4
 PATCHLEVEL = 7
 SUBLEVEL = 0
-EXTRAVERSION = -rc6
+EXTRAVERSION = -rc7
 NAME = Psychotic Stoned Sheep
 
 # *DOCUMENTATION*

arch/arm64/include/asm/cputype.h

@@ -80,12 +80,14 @@
 #define APM_CPU_PART_POTENZA		0x000
 
 #define CAVIUM_CPU_PART_THUNDERX	0x0A1
+#define CAVIUM_CPU_PART_THUNDERX_81XX	0x0A2
 
 #define BRCM_CPU_PART_VULCAN		0x516
 
 #define MIDR_CORTEX_A53 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A53)
 #define MIDR_CORTEX_A57 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A57)
 #define MIDR_THUNDERX	MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX)
+#define MIDR_THUNDERX_81XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_81XX)
 
 #ifndef __ASSEMBLY__
 

arch/arm64/include/asm/ptrace.h

@@ -117,6 +117,8 @@ struct pt_regs {
 	};
 	u64 orig_x0;
 	u64 syscallno;
+	u64 orig_addr_limit;
+	u64 unused;	// maintain 16 byte alignment
 };
 
 #define arch_has_single_step()	(1)

arch/arm64/kernel/asm-offsets.c

@@ -60,6 +60,7 @@ int main(void)
   DEFINE(S_PC,			offsetof(struct pt_regs, pc));
   DEFINE(S_ORIG_X0,		offsetof(struct pt_regs, orig_x0));
   DEFINE(S_SYSCALLNO,		offsetof(struct pt_regs, syscallno));
+  DEFINE(S_ORIG_ADDR_LIMIT,	offsetof(struct pt_regs, orig_addr_limit));
   DEFINE(S_FRAME_SIZE,		sizeof(struct pt_regs));
   BLANK();
   DEFINE(MM_CONTEXT_ID,		offsetof(struct mm_struct, context.id.counter));

arch/arm64/kernel/cpu_errata.c

@@ -98,6 +98,12 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 		MIDR_RANGE(MIDR_THUNDERX, 0x00,
 			   (1 << MIDR_VARIANT_SHIFT) | 1),
 	},
+	{
+	/* Cavium ThunderX, T81 pass 1.0 */
+		.desc = "Cavium erratum 27456",
+		.capability = ARM64_WORKAROUND_CAVIUM_27456,
+		MIDR_RANGE(MIDR_THUNDERX_81XX, 0x00, 0x00),
+	},
 #endif
 	{
 	}

arch/arm64/kernel/entry.S

@@ -28,6 +28,7 @@
 #include <asm/errno.h>
 #include <asm/esr.h>
 #include <asm/irq.h>
+#include <asm/memory.h>
 #include <asm/thread_info.h>
 #include <asm/unistd.h>
 
@@ -97,7 +98,14 @@
 	mov	x29, xzr			// fp pointed to user-space
 	.else
 	add	x21, sp, #S_FRAME_SIZE
-	.endif
+	get_thread_info tsk
+	/* Save the task's original addr_limit and set USER_DS (TASK_SIZE_64) */
+	ldr	x20, [tsk, #TI_ADDR_LIMIT]
+	str	x20, [sp, #S_ORIG_ADDR_LIMIT]
+	mov	x20, #TASK_SIZE_64
+	str	x20, [tsk, #TI_ADDR_LIMIT]
+	ALTERNATIVE(nop, SET_PSTATE_UAO(0), ARM64_HAS_UAO, CONFIG_ARM64_UAO)
+	.endif /* \el == 0 */
 	mrs	x22, elr_el1
 	mrs	x23, spsr_el1
 	stp	lr, x21, [sp, #S_LR]
@@ -128,6 +136,14 @@
 	.endm
 
 	.macro	kernel_exit, el
+	.if	\el != 0
+	/* Restore the task's original addr_limit. */
+	ldr	x20, [sp, #S_ORIG_ADDR_LIMIT]
+	str	x20, [tsk, #TI_ADDR_LIMIT]
+
+	/* No need to restore UAO, it will be restored from SPSR_EL1 */
+	.endif
+
 	ldp	x21, x22, [sp, #S_PC]		// load ELR, SPSR
 	.if	\el == 0
 	ct_user_enter
@@ -406,7 +422,6 @@ el1_irq:
 	bl	trace_hardirqs_off
 #endif
 
-	get_thread_info tsk
 	irq_handler
 
 #ifdef CONFIG_PREEMPT

arch/arm64/mm/fault.c

@@ -280,7 +280,8 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr,
 	}
 
 	if (permission_fault(esr) && (addr < USER_DS)) {
-		if (get_fs() == KERNEL_DS)
+		/* regs->orig_addr_limit may be 0 if we entered from EL0 */
+		if (regs->orig_addr_limit == KERNEL_DS)
 			die("Accessing user space memory with fs=KERNEL_DS", regs, esr);
 
 		if (!search_exception_tables(regs->pc))

arch/mips/cavium-octeon/octeon-irq.c

@@ -1260,7 +1260,7 @@ static int octeon_irq_gpio_map(struct irq_domain *d,
 
 	line = (hw + gpiod->base_hwirq) >> 6;
 	bit = (hw + gpiod->base_hwirq) & 63;
-	if (line > ARRAY_SIZE(octeon_irq_ciu_to_irq) ||
+	if (line >= ARRAY_SIZE(octeon_irq_ciu_to_irq) ||
 		octeon_irq_ciu_to_irq[line][bit] != 0)
 		return -EINVAL;
 

arch/mips/include/asm/msa.h

@@ -168,6 +168,7 @@ static inline unsigned int read_msa_##name(void)		\
 	unsigned int reg;					\
 	__asm__ __volatile__(					\
 	"	.set	push\n"					\
+	"	.set	fp=64\n"				\
 	"	.set	msa\n"					\
 	"	cfcmsa	%0, $" #cs "\n"				\
 	"	.set	pop\n"					\
@@ -179,6 +180,7 @@ static inline void write_msa_##name(unsigned int val)		\
 {								\
 	__asm__ __volatile__(					\
 	"	.set	push\n"					\
+	"	.set	fp=64\n"				\
 	"	.set	msa\n"					\
 	"	ctcmsa	$" #cs ", %0\n"				\
 	"	.set	pop\n"					\

arch/mips/kernel/cevt-r4k.c

@@ -276,12 +276,7 @@ int r4k_clockevent_init(void)
 				  CLOCK_EVT_FEAT_C3STOP |
 				  CLOCK_EVT_FEAT_PERCPU;
 
-	clockevent_set_clock(cd, mips_hpt_frequency);
-
-	/* Calculate the min / max delta */
-	cd->max_delta_ns	= clockevent_delta2ns(0x7fffffff, cd);
 	min_delta		= calculate_min_delta();
-	cd->min_delta_ns	= clockevent_delta2ns(min_delta, cd);
 
 	cd->rating		= 300;
 	cd->irq			= irq;
@@ -289,7 +284,7 @@ int r4k_clockevent_init(void)
 	cd->set_next_event	= mips_next_event;
 	cd->event_handler	= mips_event_handler;
 
-	clockevents_register_device(cd);
+	clockevents_config_and_register(cd, mips_hpt_frequency, min_delta, 0x7fffffff);
 
 	if (cp0_timer_irq_installed)
 		return 0;

arch/mips/kernel/csrc-r4k.c

@@ -23,7 +23,7 @@ static struct clocksource clocksource_mips = {
 	.flags		= CLOCK_SOURCE_IS_CONTINUOUS,
 };
 
-static u64 notrace r4k_read_sched_clock(void)
+static u64 __maybe_unused notrace r4k_read_sched_clock(void)
 {
 	return read_c0_count();
 }
@@ -82,7 +82,9 @@ int __init init_r4k_clocksource(void)
 
 	clocksource_register_hz(&clocksource_mips, mips_hpt_frequency);
 
+#ifndef CONFIG_CPU_FREQ
 	sched_clock_register(r4k_read_sched_clock, 32, mips_hpt_frequency);
+#endif
 
 	return 0;
 }

arch/mips/kernel/traps.c

@@ -704,6 +704,7 @@ asmlinkage void do_ov(struct pt_regs *regs)
 int process_fpemu_return(int sig, void __user *fault_addr, unsigned long fcr31)
 {
 	struct siginfo si = { 0 };
+	struct vm_area_struct *vma;
 
 	switch (sig) {
 	case 0:
@@ -744,7 +745,8 @@ int process_fpemu_return(int sig, void __user *fault_addr, unsigned long fcr31)
 		si.si_addr = fault_addr;
 		si.si_signo = sig;
 		down_read(&current->mm->mmap_sem);
-		if (find_vma(current->mm, (unsigned long)fault_addr))
+		vma = find_vma(current->mm, (unsigned long)fault_addr);
+		if (vma && (vma->vm_start <= (unsigned long)fault_addr))
 			si.si_code = SEGV_ACCERR;
 		else
 			si.si_code = SEGV_MAPERR;

arch/mips/lantiq/irq.c

@@ -344,7 +344,7 @@ static int icu_map(struct irq_domain *d, unsigned int irq, irq_hw_number_t hw)
 		if (hw == ltq_eiu_irq[i])
 			chip = &ltq_eiu_type;
 
-	irq_set_chip_and_handler(hw, chip, handle_level_irq);
+	irq_set_chip_and_handler(irq, chip, handle_level_irq);
 
 	return 0;
 }

arch/mips/loongson64/loongson-3/hpet.c

@@ -13,8 +13,8 @@
 #define SMBUS_PCI_REG64		0x64
 #define SMBUS_PCI_REGB4		0xb4
 
-#define HPET_MIN_CYCLES		64
-#define HPET_MIN_PROG_DELTA	(HPET_MIN_CYCLES + (HPET_MIN_CYCLES >> 1))
+#define HPET_MIN_CYCLES		16
+#define HPET_MIN_PROG_DELTA	(HPET_MIN_CYCLES * 12)
 
 static DEFINE_SPINLOCK(hpet_lock);
 DEFINE_PER_CPU(struct clock_event_device, hpet_clockevent_device);
@@ -157,14 +157,14 @@ static int hpet_tick_resume(struct clock_event_device *evt)
 static int hpet_next_event(unsigned long delta,
 		struct clock_event_device *evt)
 {
-	unsigned int cnt;
-	int res;
+	u32 cnt;
+	s32 res;
 
 	cnt = hpet_read(HPET_COUNTER);
-	cnt += delta;
+	cnt += (u32) delta;
 	hpet_write(HPET_T0_CMP, cnt);
 
-	res = (int)(cnt - hpet_read(HPET_COUNTER));
+	res = (s32)(cnt - hpet_read(HPET_COUNTER));
 
 	return res < HPET_MIN_CYCLES ? -ETIME : 0;
 }
@@ -230,7 +230,7 @@ void __init setup_hpet_timer(void)
 
 	cd = &per_cpu(hpet_clockevent_device, cpu);
 	cd->name = "hpet";
-	cd->rating = 320;
+	cd->rating = 100;
 	cd->features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT;
 	cd->set_state_shutdown = hpet_set_state_shutdown;
 	cd->set_state_periodic = hpet_set_state_periodic;

arch/mips/mm/sc-rm7k.c

@@ -161,7 +161,7 @@ static void rm7k_tc_disable(void)
 	local_irq_save(flags);
 	blast_rm7k_tcache();
 	clear_c0_config(RM7K_CONF_TE);
-	local_irq_save(flags);
+	local_irq_restore(flags);
 }
 
 static void rm7k_sc_disable(void)

arch/mips/net/bpf_jit.c

@@ -1199,7 +1199,7 @@ void bpf_jit_compile(struct bpf_prog *fp)
 
 	memset(&ctx, 0, sizeof(ctx));
 
-	ctx.offsets = kcalloc(fp->len, sizeof(*ctx.offsets), GFP_KERNEL);
+	ctx.offsets = kcalloc(fp->len + 1, sizeof(*ctx.offsets), GFP_KERNEL);
 	if (ctx.offsets == NULL)
 		return;
 

arch/x86/events/core.c

@@ -2319,7 +2319,7 @@ void
 perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs)
 {
 	struct stack_frame frame;
-	const void __user *fp;
+	const unsigned long __user *fp;
 
 	if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
 		/* TODO: We don't support guest os callchain now */
@@ -2332,7 +2332,7 @@ perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs
 	if (regs->flags & (X86_VM_MASK | PERF_EFLAGS_VM))
 		return;
 
-	fp = (void __user *)regs->bp;
+	fp = (unsigned long __user *)regs->bp;
 
 	perf_callchain_store(entry, regs->ip);
 
@@ -2345,16 +2345,17 @@ perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs
 	pagefault_disable();
 	while (entry->nr < entry->max_stack) {
 		unsigned long bytes;
+
 		frame.next_frame	     = NULL;
 		frame.return_address = 0;
 
-		if (!access_ok(VERIFY_READ, fp, 16))
+		if (!access_ok(VERIFY_READ, fp, sizeof(*fp) * 2))
 			break;
 
-		bytes = __copy_from_user_nmi(&frame.next_frame, fp, 8);
+		bytes = __copy_from_user_nmi(&frame.next_frame, fp, sizeof(*fp));
 		if (bytes != 0)
 			break;
-		bytes = __copy_from_user_nmi(&frame.return_address, fp+8, 8);
+		bytes = __copy_from_user_nmi(&frame.return_address, fp + 1, sizeof(*fp));
 		if (bytes != 0)
 			break;
 

arch/x86/events/intel/Makefile

@@ -1,8 +1,8 @@
 obj-$(CONFIG_CPU_SUP_INTEL)		+= core.o bts.o cqm.o
 obj-$(CONFIG_CPU_SUP_INTEL)		+= ds.o knc.o
 obj-$(CONFIG_CPU_SUP_INTEL)		+= lbr.o p4.o p6.o pt.o
-obj-$(CONFIG_PERF_EVENTS_INTEL_RAPL)	+= intel-rapl.o
-intel-rapl-objs				:= rapl.o
+obj-$(CONFIG_PERF_EVENTS_INTEL_RAPL)	+= intel-rapl-perf.o
+intel-rapl-perf-objs			:= rapl.o
 obj-$(CONFIG_PERF_EVENTS_INTEL_UNCORE)	+= intel-uncore.o
 intel-uncore-objs			:= uncore.o uncore_nhmex.o uncore_snb.o uncore_snbep.o
 obj-$(CONFIG_PERF_EVENTS_INTEL_CSTATE)	+= intel-cstate.o

arch/x86/events/intel/core.c

@@ -115,6 +115,10 @@ static struct event_constraint intel_snb_event_constraints[] __read_mostly =
 	INTEL_UEVENT_CONSTRAINT(0x04a3, 0xf), /* CYCLE_ACTIVITY.CYCLES_NO_DISPATCH */
 	INTEL_UEVENT_CONSTRAINT(0x02a3, 0x4), /* CYCLE_ACTIVITY.CYCLES_L1D_PENDING */
 
+	/*
+	 * When HT is off these events can only run on the bottom 4 counters
+	 * When HT is on, they are impacted by the HT bug and require EXCL access
+	 */
 	INTEL_EXCLEVT_CONSTRAINT(0xd0, 0xf), /* MEM_UOPS_RETIRED.* */
 	INTEL_EXCLEVT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */
 	INTEL_EXCLEVT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */
@@ -139,6 +143,10 @@ static struct event_constraint intel_ivb_event_constraints[] __read_mostly =
 	INTEL_UEVENT_CONSTRAINT(0x0ca3, 0x4), /* CYCLE_ACTIVITY.STALLS_L1D_PENDING */
 	INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PREC_DIST */
 
+	/*
+	 * When HT is off these events can only run on the bottom 4 counters
+	 * When HT is on, they are impacted by the HT bug and require EXCL access
+	 */
 	INTEL_EXCLEVT_CONSTRAINT(0xd0, 0xf), /* MEM_UOPS_RETIRED.* */
 	INTEL_EXCLEVT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */
 	INTEL_EXCLEVT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */
@@ -182,6 +190,16 @@ struct event_constraint intel_skl_event_constraints[] = {
 	FIXED_EVENT_CONSTRAINT(0x003c, 1),	/* CPU_CLK_UNHALTED.CORE */
 	FIXED_EVENT_CONSTRAINT(0x0300, 2),	/* CPU_CLK_UNHALTED.REF */
 	INTEL_UEVENT_CONSTRAINT(0x1c0, 0x2),	/* INST_RETIRED.PREC_DIST */
+
+	/*
+	 * when HT is off, these can only run on the bottom 4 counters
+	 */
+	INTEL_EVENT_CONSTRAINT(0xd0, 0xf),	/* MEM_INST_RETIRED.* */
+	INTEL_EVENT_CONSTRAINT(0xd1, 0xf),	/* MEM_LOAD_RETIRED.* */
+	INTEL_EVENT_CONSTRAINT(0xd2, 0xf),	/* MEM_LOAD_L3_HIT_RETIRED.* */
+	INTEL_EVENT_CONSTRAINT(0xcd, 0xf),	/* MEM_TRANS_RETIRED.* */
+	INTEL_EVENT_CONSTRAINT(0xc6, 0xf),	/* FRONTEND_RETIRED.* */
+
 	EVENT_CONSTRAINT_END
 };
 
@@ -250,6 +268,10 @@ static struct event_constraint intel_hsw_event_constraints[] = {
 	/* CYCLE_ACTIVITY.CYCLES_NO_EXECUTE */
 	INTEL_UEVENT_CONSTRAINT(0x04a3, 0xf),
 
+	/*
+	 * When HT is off these events can only run on the bottom 4 counters
+	 * When HT is on, they are impacted by the HT bug and require EXCL access
+	 */
 	INTEL_EXCLEVT_CONSTRAINT(0xd0, 0xf), /* MEM_UOPS_RETIRED.* */
 	INTEL_EXCLEVT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */
 	INTEL_EXCLEVT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */
@@ -264,6 +286,13 @@ struct event_constraint intel_bdw_event_constraints[] = {
 	FIXED_EVENT_CONSTRAINT(0x0300, 2),	/* CPU_CLK_UNHALTED.REF */
 	INTEL_UEVENT_CONSTRAINT(0x148, 0x4),	/* L1D_PEND_MISS.PENDING */
 	INTEL_UBIT_EVENT_CONSTRAINT(0x8a3, 0x4),	/* CYCLE_ACTIVITY.CYCLES_L1D_MISS */
+	/*
+	 * when HT is off, these can only run on the bottom 4 counters
+	 */
+	INTEL_EVENT_CONSTRAINT(0xd0, 0xf),	/* MEM_INST_RETIRED.* */
+	INTEL_EVENT_CONSTRAINT(0xd1, 0xf),	/* MEM_LOAD_RETIRED.* */
+	INTEL_EVENT_CONSTRAINT(0xd2, 0xf),	/* MEM_LOAD_L3_HIT_RETIRED.* */
+	INTEL_EVENT_CONSTRAINT(0xcd, 0xf),	/* MEM_TRANS_RETIRED.* */
 	EVENT_CONSTRAINT_END
 };
 

arch/x86/kernel/amd_nb.c

@@ -71,8 +71,8 @@ int amd_cache_northbridges(void)
 	while ((misc = next_northbridge(misc, amd_nb_misc_ids)) != NULL)
 		i++;
 
-	if (i == 0)
-		return 0;
+	if (!i)
+		return -ENODEV;
 
 	nb = kzalloc(i * sizeof(struct amd_northbridge), GFP_KERNEL);
 	if (!nb)

arch/x86/pci/acpi.c

@@ -396,6 +396,7 @@ int __init pci_acpi_init(void)
 		return -ENODEV;
 
 	printk(KERN_INFO "PCI: Using ACPI for IRQ routing\n");
+	acpi_irq_penalty_init();
 	pcibios_enable_irq = acpi_pci_irq_enable;
 	pcibios_disable_irq = acpi_pci_irq_disable;
 	x86_init.pci.init_irq = x86_init_noop;

arch/x86/power/hibernate_64.c

@@ -19,6 +19,7 @@
 #include <asm/mtrr.h>
 #include <asm/sections.h>
 #include <asm/suspend.h>
+#include <asm/tlbflush.h>
 
 /* Defined in hibernate_asm_64.S */
 extern asmlinkage __visible int restore_image(void);
@@ -28,6 +29,7 @@ extern asmlinkage __visible int restore_image(void);
  * kernel's text (this value is passed in the image header).
  */
 unsigned long restore_jump_address __visible;
+unsigned long jump_address_phys;
 
 /*
  * Value of the cr3 register from before the hibernation (this value is passed
@@ -37,7 +39,43 @@ unsigned long restore_cr3 __visible;
 
 pgd_t *temp_level4_pgt __visible;
 
-void *relocated_restore_code __visible;
+unsigned long relocated_restore_code __visible;
+
+static int set_up_temporary_text_mapping(void)
+{
+	pmd_t *pmd;
+	pud_t *pud;
+
+	/*
+	 * The new mapping only has to cover the page containing the image
+	 * kernel's entry point (jump_address_phys), because the switch over to
+	 * it is carried out by relocated code running from a page allocated
+	 * specifically for this purpose and covered by the identity mapping, so
+	 * the temporary kernel text mapping is only needed for the final jump.
+	 * Moreover, in that mapping the virtual address of the image kernel's
+	 * entry point must be the same as its virtual address in the image
+	 * kernel (restore_jump_address), so the image kernel's
+	 * restore_registers() code doesn't find itself in a different area of
+	 * the virtual address space after switching over to the original page
+	 * tables used by the image kernel.
+	 */
+	pud = (pud_t *)get_safe_page(GFP_ATOMIC);
+	if (!pud)
+		return -ENOMEM;
+
+	pmd = (pmd_t *)get_safe_page(GFP_ATOMIC);
+	if (!pmd)
+		return -ENOMEM;
+
+	set_pmd(pmd + pmd_index(restore_jump_address),
+		__pmd((jump_address_phys & PMD_MASK) | __PAGE_KERNEL_LARGE_EXEC));
+	set_pud(pud + pud_index(restore_jump_address),
+		__pud(__pa(pmd) | _KERNPG_TABLE));
+	set_pgd(temp_level4_pgt + pgd_index(restore_jump_address),
+		__pgd(__pa(pud) | _KERNPG_TABLE));
+
+	return 0;
+}
 
 static void *alloc_pgt_page(void *context)
 {
@@ -59,9 +97,10 @@ static int set_up_temporary_mappings(void)
 	if (!temp_level4_pgt)
 		return -ENOMEM;
 
-	/* It is safe to reuse the original kernel mapping */
-	set_pgd(temp_level4_pgt + pgd_index(__START_KERNEL_map),
-		init_level4_pgt[pgd_index(__START_KERNEL_map)]);
+	/* Prepare a temporary mapping for the kernel text */
+	result = set_up_temporary_text_mapping();
+	if (result)
+		return result;
 
 	/* Set up the direct mapping from scratch */
 	for (i = 0; i < nr_pfn_mapped; i++) {
@@ -78,19 +117,50 @@ static int set_up_temporary_mappings(void)
 	return 0;
 }
 
+static int relocate_restore_code(void)
+{
+	pgd_t *pgd;
+	pud_t *pud;
+
+	relocated_restore_code = get_safe_page(GFP_ATOMIC);
+	if (!relocated_restore_code)
+		return -ENOMEM;
+
+	memcpy((void *)relocated_restore_code, &core_restore_code, PAGE_SIZE);
+
+	/* Make the page containing the relocated code executable */
+	pgd = (pgd_t *)__va(read_cr3()) + pgd_index(relocated_restore_code);
+	pud = pud_offset(pgd, relocated_restore_code);
+	if (pud_large(*pud)) {
+		set_pud(pud, __pud(pud_val(*pud) & ~_PAGE_NX));
+	} else {
+		pmd_t *pmd = pmd_offset(pud, relocated_restore_code);
+
+		if (pmd_large(*pmd)) {
+			set_pmd(pmd, __pmd(pmd_val(*pmd) & ~_PAGE_NX));
+		} else {
+			pte_t *pte = pte_offset_kernel(pmd, relocated_restore_code);
+
+			set_pte(pte, __pte(pte_val(*pte) & ~_PAGE_NX));
+		}
+	}
+	__flush_tlb_all();
+
+	return 0;
+}
+
 int swsusp_arch_resume(void)
 {
 	int error;
 
 	/* We have got enough memory and from now on we cannot recover */
-	if ((error = set_up_temporary_mappings()))
+	error = set_up_temporary_mappings();
+	if (error)
 		return error;
 
-	relocated_restore_code = (void *)get_safe_page(GFP_ATOMIC);
-	if (!relocated_restore_code)
-		return -ENOMEM;
-	memcpy(relocated_restore_code, &core_restore_code,
-	       &restore_registers - &core_restore_code);
+	error = relocate_restore_code();
+	if (error)
+		return error;
 
 	restore_image();
 	return 0;
@@ -109,11 +179,12 @@ int pfn_is_nosave(unsigned long pfn)
 
 struct restore_data_record {
 	unsigned long jump_address;
+	unsigned long jump_address_phys;
 	unsigned long cr3;
 	unsigned long magic;
 };
 
-#define RESTORE_MAGIC	0x0123456789ABCDEFUL
+#define RESTORE_MAGIC	0x123456789ABCDEF0UL
 
 /**
  *	arch_hibernation_header_save - populate the architecture specific part
@@ -126,7 +197,8 @@ int arch_hibernation_header_save(void *addr, unsigned int max_size)
 
 	if (max_size < sizeof(struct restore_data_record))
 		return -EOVERFLOW;
-	rdr->jump_address = restore_jump_address;
+	rdr->jump_address = (unsigned long)&restore_registers;
+	rdr->jump_address_phys = __pa_symbol(&restore_registers);
 	rdr->cr3 = restore_cr3;
 	rdr->magic = RESTORE_MAGIC;
 	return 0;
@@ -142,6 +214,7 @@ int arch_hibernation_header_restore(void *addr)
 	struct restore_data_record *rdr = addr;
 
 	restore_jump_address = rdr->jump_address;
+	jump_address_phys = rdr->jump_address_phys;
 	restore_cr3 = rdr->cr3;
 	return (rdr->magic == RESTORE_MAGIC) ? 0 : -EINVAL;
 }

arch/x86/power/hibernate_asm_64.S

@@ -44,9 +44,6 @@ ENTRY(swsusp_arch_suspend)
 	pushfq
 	popq	pt_regs_flags(%rax)
 
-	/* save the address of restore_registers */
-	movq	$restore_registers, %rax
-	movq	%rax, restore_jump_address(%rip)
 	/* save cr3 */
 	movq	%cr3, %rax
 	movq	%rax, restore_cr3(%rip)
@@ -57,31 +54,34 @@ ENTRY(swsusp_arch_suspend)
 ENDPROC(swsusp_arch_suspend)
 
 ENTRY(restore_image)
-	/* switch to temporary page tables */
-	movq	$__PAGE_OFFSET, %rdx
-	movq	temp_level4_pgt(%rip), %rax
-	subq	%rdx, %rax
-	movq	%rax, %cr3
-	/* Flush TLB */
-	movq	mmu_cr4_features(%rip), %rax
-	movq	%rax, %rdx
-	andq	$~(X86_CR4_PGE), %rdx
-	movq	%rdx, %cr4;  # turn off PGE
-	movq	%cr3, %rcx;  # flush TLB
-	movq	%rcx, %cr3;
-	movq	%rax, %cr4;  # turn PGE back on
-
 	/* prepare to jump to the image kernel */
-	movq	restore_jump_address(%rip), %rax
-	movq	restore_cr3(%rip), %rbx
+	movq	restore_jump_address(%rip), %r8
+	movq	restore_cr3(%rip), %r9
+
+	/* prepare to switch to temporary page tables */
+	movq	temp_level4_pgt(%rip), %rax
+	movq	mmu_cr4_features(%rip), %rbx
 
 	/* prepare to copy image data to their original locations */
 	movq	restore_pblist(%rip), %rdx
+
+	/* jump to relocated restore code */
 	movq	relocated_restore_code(%rip), %rcx
 	jmpq	*%rcx
 
 	/* code below has been relocated to a safe page */
 ENTRY(core_restore_code)
+	/* switch to temporary page tables */
+	movq	$__PAGE_OFFSET, %rcx
+	subq	%rcx, %rax
+	movq	%rax, %cr3
+	/* flush TLB */
+	movq	%rbx, %rcx
+	andq	$~(X86_CR4_PGE), %rcx
+	movq	%rcx, %cr4;  # turn off PGE
+	movq	%cr3, %rcx;  # flush TLB
+	movq	%rcx, %cr3;
+	movq	%rbx, %cr4;  # turn PGE back on
 .Lloop:
 	testq	%rdx, %rdx
 	jz	.Ldone
@@ -96,24 +96,17 @@ ENTRY(core_restore_code)
 	/* progress to the next pbe */
 	movq	pbe_next(%rdx), %rdx
 	jmp	.Lloop
+
 .Ldone:
 	/* jump to the restore_registers address from the image header */
-	jmpq	*%rax
-	/*
-	 * NOTE: This assumes that the boot kernel's text mapping covers the
-	 * image kernel's page containing restore_registers and the address of
-	 * this page is the same as in the image kernel's text mapping (it
-	 * should always be true, because the text mapping is linear, starting
-	 * from 0, and is supposed to cover the entire kernel text for every
-	 * kernel).
-	 *
-	 * code below belongs to the image kernel
-	 */
+	jmpq	*%r8
 
+	 /* code below belongs to the image kernel */
+	.align PAGE_SIZE
 ENTRY(restore_registers)
 	FRAME_BEGIN
 	/* go back to the original page tables */
-	movq    %rbx, %cr3
+	movq    %r9, %cr3
 
 	/* Flush TLB, including "global" things (vmalloc) */
 	movq	mmu_cr4_features(%rip), %rax

block/ioprio.c

@@ -150,8 +150,10 @@ static int get_task_ioprio(struct task_struct *p)
 	if (ret)
 		goto out;
 	ret = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_NONE, IOPRIO_NORM);
+	task_lock(p);
 	if (p->io_context)
 		ret = p->io_context->ioprio;
+	task_unlock(p);
 out:
 	return ret;
 }

drivers/acpi/acpi_dbg.c

@@ -602,7 +602,7 @@ static int acpi_aml_read_user(char __user *buf, int len)
 	crc->tail = (crc->tail + n) & (ACPI_AML_BUF_SIZE - 1);
 	ret = n;
 out:
-	acpi_aml_unlock_fifo(ACPI_AML_OUT_USER, !ret);
+	acpi_aml_unlock_fifo(ACPI_AML_OUT_USER, ret >= 0);
 	return ret;
 }
 
@@ -672,7 +672,7 @@ static int acpi_aml_write_user(const char __user *buf, int len)
 	crc->head = (crc->head + n) & (ACPI_AML_BUF_SIZE - 1);
 	ret = n;
 out:
-	acpi_aml_unlock_fifo(ACPI_AML_IN_USER, !ret);
+	acpi_aml_unlock_fifo(ACPI_AML_IN_USER, ret >= 0);
 	return n;
 }
 

drivers/acpi/acpica/nsload.c

@@ -46,6 +46,7 @@
 #include "acnamesp.h"
 #include "acdispat.h"
 #include "actables.h"
+#include "acinterp.h"
 
 #define _COMPONENT          ACPI_NAMESPACE
 ACPI_MODULE_NAME("nsload")
@@ -78,6 +79,8 @@ acpi_ns_load_table(u32 table_index, struct acpi_namespace_node *node)
 
 	ACPI_FUNCTION_TRACE(ns_load_table);
 
+	acpi_ex_enter_interpreter();
+
 	/*
 	 * Parse the table and load the namespace with all named
 	 * objects found within. Control methods are NOT parsed
@@ -89,7 +92,7 @@ acpi_ns_load_table(u32 table_index, struct acpi_namespace_node *node)
 	 */
 	status = acpi_ut_acquire_mutex(ACPI_MTX_NAMESPACE);
 	if (ACPI_FAILURE(status)) {
-		return_ACPI_STATUS(status);
+		goto unlock_interp;
 	}
 
 	/* If table already loaded into namespace, just return */
@@ -130,6 +133,8 @@ acpi_ns_load_table(u32 table_index, struct acpi_namespace_node *node)
 
 unlock:
 	(void)acpi_ut_release_mutex(ACPI_MTX_NAMESPACE);
+unlock_interp:
+	(void)acpi_ex_exit_interpreter();
 
 	if (ACPI_FAILURE(status)) {
 		return_ACPI_STATUS(status);

drivers/acpi/acpica/nsparse.c

@@ -47,7 +47,6 @@
 #include "acparser.h"
 #include "acdispat.h"
 #include "actables.h"
-#include "acinterp.h"
 
 #define _COMPONENT          ACPI_NAMESPACE
 ACPI_MODULE_NAME("nsparse")
@@ -171,8 +170,6 @@ acpi_ns_parse_table(u32 table_index, struct acpi_namespace_node *start_node)
 
 	ACPI_FUNCTION_TRACE(ns_parse_table);
 
-	acpi_ex_enter_interpreter();
-
 	/*
 	 * AML Parse, pass 1
 	 *
@@ -188,7 +185,7 @@ acpi_ns_parse_table(u32 table_index, struct acpi_namespace_node *start_node)
 	status = acpi_ns_one_complete_parse(ACPI_IMODE_LOAD_PASS1,
 					    table_index, start_node);
 	if (ACPI_FAILURE(status)) {
-		goto error_exit;
+		return_ACPI_STATUS(status);
 	}
 
 	/*
@@ -204,10 +201,8 @@ acpi_ns_parse_table(u32 table_index, struct acpi_namespace_node *start_node)
 	status = acpi_ns_one_complete_parse(ACPI_IMODE_LOAD_PASS2,
 					    table_index, start_node);
 	if (ACPI_FAILURE(status)) {
-		goto error_exit;
+		return_ACPI_STATUS(status);
 	}
 
-error_exit:
-	acpi_ex_exit_interpreter();
 	return_ACPI_STATUS(status);
 }

drivers/acpi/pci_link.c

@@ -470,6 +470,7 @@ static int acpi_irq_pci_sharing_penalty(int irq)
 {
 	struct acpi_pci_link *link;
 	int penalty = 0;
+	int i;
 
 	list_for_each_entry(link, &acpi_link_list, list) {
 		/*
@@ -478,18 +479,14 @@ static int acpi_irq_pci_sharing_penalty(int irq)
 		 */
 		if (link->irq.active && link->irq.active == irq)
 			penalty += PIRQ_PENALTY_PCI_USING;
-		else {
-			int i;
-
-			/*
-			 * If a link is inactive, penalize the IRQs it
-			 * might use, but not as severely.
-			 */
-			for (i = 0; i < link->irq.possible_count; i++)
-				if (link->irq.possible[i] == irq)
-					penalty += PIRQ_PENALTY_PCI_POSSIBLE /
-						link->irq.possible_count;
-		}
+
+		/*
+		 * penalize the IRQs PCI might use, but not as severely.
+		 */
+		for (i = 0; i < link->irq.possible_count; i++)
+			if (link->irq.possible[i] == irq)
+				penalty += PIRQ_PENALTY_PCI_POSSIBLE /
+					link->irq.possible_count;
 	}
 
 	return penalty;
@@ -499,9 +496,6 @@ static int acpi_irq_get_penalty(int irq)
 {
 	int penalty = 0;
 
-	if (irq < ACPI_MAX_ISA_IRQS)
-		penalty += acpi_isa_irq_penalty[irq];
-
 	/*
 	* Penalize IRQ used by ACPI SCI. If ACPI SCI pin attributes conflict
 	* with PCI IRQ attributes, mark ACPI SCI as ISA_ALWAYS so it won't be
@@ -516,10 +510,49 @@ static int acpi_irq_get_penalty(int irq)
 			penalty += PIRQ_PENALTY_PCI_USING;
 	}
 
+	if (irq < ACPI_MAX_ISA_IRQS)
+		return penalty + acpi_isa_irq_penalty[irq];
+
 	penalty += acpi_irq_pci_sharing_penalty(irq);
 	return penalty;
 }
 
+int __init acpi_irq_penalty_init(void)
+{
+	struct acpi_pci_link *link;
+	int i;
+
+	/*
+	 * Update penalties to facilitate IRQ balancing.
+	 */
+	list_for_each_entry(link, &acpi_link_list, list) {
+
+		/*
+		 * reflect the possible and active irqs in the penalty table --
+		 * useful for breaking ties.
+		 */
+		if (link->irq.possible_count) {
+			int penalty =
+			    PIRQ_PENALTY_PCI_POSSIBLE /
+			    link->irq.possible_count;
+
+			for (i = 0; i < link->irq.possible_count; i++) {
+				if (link->irq.possible[i] < ACPI_MAX_ISA_IRQS)
+					acpi_isa_irq_penalty[link->irq.
+							 possible[i]] +=
+					    penalty;
+			}
+
+		} else if (link->irq.active &&
+				(link->irq.active < ACPI_MAX_ISA_IRQS)) {
+			acpi_isa_irq_penalty[link->irq.active] +=
+			    PIRQ_PENALTY_PCI_POSSIBLE;
+		}
+	}
+
+	return 0;
+}
+
 static int acpi_irq_balance = -1;	/* 0: static, 1: balance */
 
 static int acpi_pci_link_allocate(struct acpi_pci_link *link)

drivers/block/xen-blkfront.c

@@ -207,6 +207,9 @@ struct blkfront_info
 	struct blk_mq_tag_set tag_set;
 	struct blkfront_ring_info *rinfo;
 	unsigned int nr_rings;
+	/* Save uncomplete reqs and bios for migration. */
+	struct list_head requests;
+	struct bio_list bio_list;
 };
 
 static unsigned int nr_minors;
@@ -2002,69 +2005,22 @@ static int blkif_recover(struct blkfront_info *info)
 {
 	unsigned int i, r_index;
 	struct request *req, *n;
-	struct blk_shadow *copy;
 	int rc;
 	struct bio *bio, *cloned_bio;
-	struct bio_list bio_list, merge_bio;
 	unsigned int segs, offset;
 	int pending, size;
 	struct split_bio *split_bio;
-	struct list_head requests;
 
 	blkfront_gather_backend_features(info);
 	segs = info->max_indirect_segments ? : BLKIF_MAX_SEGMENTS_PER_REQUEST;
 	blk_queue_max_segments(info->rq, segs);
-	bio_list_init(&bio_list);
-	INIT_LIST_HEAD(&requests);
 
 	for (r_index = 0; r_index < info->nr_rings; r_index++) {
-		struct blkfront_ring_info *rinfo;
-
-		rinfo = &info->rinfo[r_index];
-		/* Stage 1: Make a safe copy of the shadow state. */
-		copy = kmemdup(rinfo->shadow, sizeof(rinfo->shadow),
-			       GFP_NOIO | __GFP_REPEAT | __GFP_HIGH);
-		if (!copy)
-			return -ENOMEM;
-
-		/* Stage 2: Set up free list. */
-		memset(&rinfo->shadow, 0, sizeof(rinfo->shadow));
-		for (i = 0; i < BLK_RING_SIZE(info); i++)
-			rinfo->shadow[i].req.u.rw.id = i+1;
-		rinfo->shadow_free = rinfo->ring.req_prod_pvt;
-		rinfo->shadow[BLK_RING_SIZE(info)-1].req.u.rw.id = 0x0fffffff;
+		struct blkfront_ring_info *rinfo = &info->rinfo[r_index];
 
 		rc = blkfront_setup_indirect(rinfo);
-		if (rc) {
-			kfree(copy);
+		if (rc)
 			return rc;
-		}
-
-		for (i = 0; i < BLK_RING_SIZE(info); i++) {
-			/* Not in use? */
-			if (!copy[i].request)
-				continue;
-
-			/*
-			 * Get the bios in the request so we can re-queue them.
-			 */
-			if (copy[i].request->cmd_flags &
-			    (REQ_FLUSH | REQ_FUA | REQ_DISCARD | REQ_SECURE)) {
-				/*
-				 * Flush operations don't contain bios, so
-				 * we need to requeue the whole request
-				 */
-				list_add(&copy[i].request->queuelist, &requests);
-				continue;
-			}
-			merge_bio.head = copy[i].request->bio;
-			merge_bio.tail = copy[i].request->biotail;
-			bio_list_merge(&bio_list, &merge_bio);
-			copy[i].request->bio = NULL;
-			blk_end_request_all(copy[i].request, 0);
-		}
-
-		kfree(copy);
 	}
 	xenbus_switch_state(info->xbdev, XenbusStateConnected);
 
@@ -2079,7 +2035,7 @@ static int blkif_recover(struct blkfront_info *info)
 		kick_pending_request_queues(rinfo);
 	}
 
-	list_for_each_entry_safe(req, n, &requests, queuelist) {
+	list_for_each_entry_safe(req, n, &info->requests, queuelist) {
 		/* Requeue pending requests (flush or discard) */
 		list_del_init(&req->queuelist);
 		BUG_ON(req->nr_phys_segments > segs);
@@ -2087,7 +2043,7 @@ static int blkif_recover(struct blkfront_info *info)
 	}
 	blk_mq_kick_requeue_list(info->rq);
 
-	while ((bio = bio_list_pop(&bio_list)) != NULL) {
+	while ((bio = bio_list_pop(&info->bio_list)) != NULL) {
 		/* Traverse the list of pending bios and re-queue them */
 		if (bio_segments(bio) > segs) {
 			/*
@@ -2133,9 +2089,42 @@ static int blkfront_resume(struct xenbus_device *dev)
 {
 	struct blkfront_info *info = dev_get_drvdata(&dev->dev);
 	int err = 0;
+	unsigned int i, j;
 
 	dev_dbg(&dev->dev, "blkfront_resume: %s\n", dev->nodename);
 
+	bio_list_init(&info->bio_list);
+	INIT_LIST_HEAD(&info->requests);
+	for (i = 0; i < info->nr_rings; i++) {
+		struct blkfront_ring_info *rinfo = &info->rinfo[i];
+		struct bio_list merge_bio;
+		struct blk_shadow *shadow = rinfo->shadow;
+
+		for (j = 0; j < BLK_RING_SIZE(info); j++) {
+			/* Not in use? */
+			if (!shadow[j].request)
+				continue;
+
+			/*
+			 * Get the bios in the request so we can re-queue them.
+			 */
+			if (shadow[j].request->cmd_flags &
+					(REQ_FLUSH | REQ_FUA | REQ_DISCARD | REQ_SECURE)) {
+				/*
+				 * Flush operations don't contain bios, so
+				 * we need to requeue the whole request
+				 */
+				list_add(&shadow[j].request->queuelist, &info->requests);
+				continue;
+			}
+			merge_bio.head = shadow[j].request->bio;
+			merge_bio.tail = shadow[j].request->biotail;
+			bio_list_merge(&info->bio_list, &merge_bio);
+			shadow[j].request->bio = NULL;
+			blk_mq_end_request(shadow[j].request, 0);
+		}
+	}
+
 	blkif_free(info, info->connected == BLKIF_STATE_CONNECTED);
 
 	err = negotiate_mq(info);

drivers/cpuidle/cpuidle.c

@@ -173,7 +173,7 @@ int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv,
 
 	struct cpuidle_state *target_state = &drv->states[index];
 	bool broadcast = !!(target_state->flags & CPUIDLE_FLAG_TIMER_STOP);
-	u64 time_start, time_end;
+	ktime_t time_start, time_end;
 	s64 diff;
 
 	/*
@@ -195,13 +195,13 @@ int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv,
 	sched_idle_set_state(target_state);
 
 	trace_cpu_idle_rcuidle(index, dev->cpu);
-	time_start = local_clock();
+	time_start = ns_to_ktime(local_clock());
 
 	stop_critical_timings();
 	entered_state = target_state->enter(dev, drv, index);
 	start_critical_timings();
 
-	time_end = local_clock();
+	time_end = ns_to_ktime(local_clock());
 	trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, dev->cpu);
 
 	/* The cpu is no longer idle or about to enter idle. */
@@ -217,11 +217,7 @@ int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv,
 	if (!cpuidle_state_is_coupled(drv, index))
 		local_irq_enable();
 
-	/*
-	 * local_clock() returns the time in nanosecond, let's shift
-	 * by 10 (divide by 1024) to have microsecond based time.
-	 */
-	diff = (time_end - time_start) >> 10;
+	diff = ktime_us_delta(time_end, time_start);
 	if (diff > INT_MAX)
 		diff = INT_MAX;
 

drivers/gpio/Kconfig

@@ -49,7 +49,7 @@ config GPIO_DEVRES
 
 config OF_GPIO
 	def_bool y
-	depends on OF || COMPILE_TEST
+	depends on OF
 
 config GPIO_ACPI
 	def_bool y

drivers/gpio/gpio-sch.c

@@ -61,9 +61,8 @@ static unsigned sch_gpio_bit(struct sch_gpio *sch, unsigned gpio)
 	return gpio % 8;
 }
 
-static int sch_gpio_reg_get(struct gpio_chip *gc, unsigned gpio, unsigned reg)
+static int sch_gpio_reg_get(struct sch_gpio *sch, unsigned gpio, unsigned reg)
 {
-	struct sch_gpio *sch = gpiochip_get_data(gc);
 	unsigned short offset, bit;
 	u8 reg_val;
 
@@ -75,10 +74,9 @@ static int sch_gpio_reg_get(struct gpio_chip *gc, unsigned gpio, unsigned reg)
 	return reg_val;
 }
 
-static void sch_gpio_reg_set(struct gpio_chip *gc, unsigned gpio, unsigned reg,
+static void sch_gpio_reg_set(struct sch_gpio *sch, unsigned gpio, unsigned reg,
 			     int val)
 {
-	struct sch_gpio *sch = gpiochip_get_data(gc);
 	unsigned short offset, bit;
 	u8 reg_val;
 
@@ -98,14 +96,15 @@ static int sch_gpio_direction_in(struct gpio_chip *gc, unsigned gpio_num)
 	struct sch_gpio *sch = gpiochip_get_data(gc);
 
 	spin_lock(&sch->lock);
-	sch_gpio_reg_set(gc, gpio_num, GIO, 1);
+	sch_gpio_reg_set(sch, gpio_num, GIO, 1);
 	spin_unlock(&sch->lock);
 	return 0;
 }
 
 static int sch_gpio_get(struct gpio_chip *gc, unsigned gpio_num)
 {
-	return sch_gpio_reg_get(gc, gpio_num, GLV);
+	struct sch_gpio *sch = gpiochip_get_data(gc);
+	return sch_gpio_reg_get(sch, gpio_num, GLV);
 }
 
 static void sch_gpio_set(struct gpio_chip *gc, unsigned gpio_num, int val)
@@ -113,7 +112,7 @@ static void sch_gpio_set(struct gpio_chip *gc, unsigned gpio_num, int val)
 	struct sch_gpio *sch = gpiochip_get_data(gc);
 
 	spin_lock(&sch->lock);
-	sch_gpio_reg_set(gc, gpio_num, GLV, val);
+	sch_gpio_reg_set(sch, gpio_num, GLV, val);
 	spin_unlock(&sch->lock);
 }
 
@@ -123,7 +122,7 @@ static int sch_gpio_direction_out(struct gpio_chip *gc, unsigned gpio_num,
 	struct sch_gpio *sch = gpiochip_get_data(gc);
 
 	spin_lock(&sch->lock);
-	sch_gpio_reg_set(gc, gpio_num, GIO, 0);
+	sch_gpio_reg_set(sch, gpio_num, GIO, 0);
 	spin_unlock(&sch->lock);
 
 	/*
@@ -182,13 +181,13 @@ static int sch_gpio_probe(struct platform_device *pdev)
 		 * GPIO7 is configured by the CMC as SLPIOVR
 		 * Enable GPIO[9:8] core powered gpios explicitly
 		 */
-		sch_gpio_reg_set(&sch->chip, 8, GEN, 1);
-		sch_gpio_reg_set(&sch->chip, 9, GEN, 1);
+		sch_gpio_reg_set(sch, 8, GEN, 1);
+		sch_gpio_reg_set(sch, 9, GEN, 1);
 		/*
 		 * SUS_GPIO[2:0] enabled by default
 		 * Enable SUS_GPIO3 resume powered gpio explicitly
 		 */
-		sch_gpio_reg_set(&sch->chip, 13, GEN, 1);
+		sch_gpio_reg_set(sch, 13, GEN, 1);
 		break;
 
 	case PCI_DEVICE_ID_INTEL_ITC_LPC:

drivers/gpio/gpiolib-legacy.c

@@ -28,6 +28,10 @@ int gpio_request_one(unsigned gpio, unsigned long flags, const char *label)
 	if (!desc && gpio_is_valid(gpio))
 		return -EPROBE_DEFER;
 
+	err = gpiod_request(desc, label);
+	if (err)
+		return err;
+
 	if (flags & GPIOF_OPEN_DRAIN)
 		set_bit(FLAG_OPEN_DRAIN, &desc->flags);
 
@@ -37,10 +41,6 @@ int gpio_request_one(unsigned gpio, unsigned long flags, const char *label)
 	if (flags & GPIOF_ACTIVE_LOW)
 		set_bit(FLAG_ACTIVE_LOW, &desc->flags);
 
-	err = gpiod_request(desc, label);
-	if (err)
-		return err;
-
 	if (flags & GPIOF_DIR_IN)
 		err = gpiod_direction_input(desc);
 	else

drivers/gpio/gpiolib.c

@@ -1352,14 +1352,6 @@ static int __gpiod_request(struct gpio_desc *desc, const char *label)
 		spin_lock_irqsave(&gpio_lock, flags);
 	}
 done:
-	if (status < 0) {
-		/* Clear flags that might have been set by the caller before
-		 * requesting the GPIO.
-		 */
-		clear_bit(FLAG_ACTIVE_LOW, &desc->flags);
-		clear_bit(FLAG_OPEN_DRAIN, &desc->flags);
-		clear_bit(FLAG_OPEN_SOURCE, &desc->flags);
-	}
 	spin_unlock_irqrestore(&gpio_lock, flags);
 	return status;
 }
@@ -2587,28 +2579,13 @@ struct gpio_desc *__must_check gpiod_get_optional(struct device *dev,
 }
 EXPORT_SYMBOL_GPL(gpiod_get_optional);
 
-/**
- * gpiod_parse_flags - helper function to parse GPIO lookup flags
- * @desc:	gpio to be setup
- * @lflags:	gpio_lookup_flags - returned from of_find_gpio() or
- *		of_get_gpio_hog()
- *
- * Set the GPIO descriptor flags based on the given GPIO lookup flags.
- */
-static void gpiod_parse_flags(struct gpio_desc *desc, unsigned long lflags)
-{
-	if (lflags & GPIO_ACTIVE_LOW)
-		set_bit(FLAG_ACTIVE_LOW, &desc->flags);
-	if (lflags & GPIO_OPEN_DRAIN)
-		set_bit(FLAG_OPEN_DRAIN, &desc->flags);
-	if (lflags & GPIO_OPEN_SOURCE)
-		set_bit(FLAG_OPEN_SOURCE, &desc->flags);
-}
 
 /**
  * gpiod_configure_flags - helper function to configure a given GPIO
  * @desc:	gpio whose value will be assigned
  * @con_id:	function within the GPIO consumer
+ * @lflags:	gpio_lookup_flags - returned from of_find_gpio() or
+ *		of_get_gpio_hog()
  * @dflags:	gpiod_flags - optional GPIO initialization flags
  *
  * Return 0 on success, -ENOENT if no GPIO has been assigned to the
@@ -2616,10 +2593,17 @@ static void gpiod_parse_flags(struct gpio_desc *desc, unsigned long lflags)
  * occurred while trying to acquire the GPIO.
  */
 static int gpiod_configure_flags(struct gpio_desc *desc, const char *con_id,
-				 enum gpiod_flags dflags)
+		unsigned long lflags, enum gpiod_flags dflags)
 {
 	int status;
 
+	if (lflags & GPIO_ACTIVE_LOW)
+		set_bit(FLAG_ACTIVE_LOW, &desc->flags);
+	if (lflags & GPIO_OPEN_DRAIN)
+		set_bit(FLAG_OPEN_DRAIN, &desc->flags);
+	if (lflags & GPIO_OPEN_SOURCE)
+		set_bit(FLAG_OPEN_SOURCE, &desc->flags);
+
 	/* No particular flag request, return here... */
 	if (!(dflags & GPIOD_FLAGS_BIT_DIR_SET)) {
 		pr_debug("no flags found for %s\n", con_id);
@@ -2686,13 +2670,11 @@ struct gpio_desc *__must_check gpiod_get_index(struct device *dev,
 		return desc;
 	}
 
-	gpiod_parse_flags(desc, lookupflags);
-
 	status = gpiod_request(desc, con_id);
 	if (status < 0)
 		return ERR_PTR(status);
 
-	status = gpiod_configure_flags(desc, con_id, flags);
+	status = gpiod_configure_flags(desc, con_id, lookupflags, flags);
 	if (status < 0) {
 		dev_dbg(dev, "setup of GPIO %s failed\n", con_id);
 		gpiod_put(desc);
@@ -2748,6 +2730,10 @@ struct gpio_desc *fwnode_get_named_gpiod(struct fwnode_handle *fwnode,
 	if (IS_ERR(desc))
 		return desc;
 
+	ret = gpiod_request(desc, NULL);
+	if (ret)
+		return ERR_PTR(ret);
+
 	if (active_low)
 		set_bit(FLAG_ACTIVE_LOW, &desc->flags);
 
@@ -2758,10 +2744,6 @@ struct gpio_desc *fwnode_get_named_gpiod(struct fwnode_handle *fwnode,
 			set_bit(FLAG_OPEN_SOURCE, &desc->flags);
 	}
 
-	ret = gpiod_request(desc, NULL);
-	if (ret)
-		return ERR_PTR(ret);
-
 	return desc;
 }
 EXPORT_SYMBOL_GPL(fwnode_get_named_gpiod);
@@ -2814,8 +2796,6 @@ int gpiod_hog(struct gpio_desc *desc, const char *name,
 	chip = gpiod_to_chip(desc);
 	hwnum = gpio_chip_hwgpio(desc);
 
-	gpiod_parse_flags(desc, lflags);
-
 	local_desc = gpiochip_request_own_desc(chip, hwnum, name);
 	if (IS_ERR(local_desc)) {
 		status = PTR_ERR(local_desc);
@@ -2824,7 +2804,7 @@ int gpiod_hog(struct gpio_desc *desc, const char *name,
 		return status;
 	}
 
-	status = gpiod_configure_flags(desc, name, dflags);
+	status = gpiod_configure_flags(desc, name, lflags, dflags);
 	if (status < 0) {
 		pr_err("setup of hog GPIO %s (chip %s, offset %d) failed, %d\n",
 		       name, chip->label, hwnum, status);

drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_hwmgr.c

@@ -98,7 +98,6 @@
 #define PCIE_BUS_CLK                10000
 #define TCLK                        (PCIE_BUS_CLK / 10)
 
-#define CEILING_UCHAR(double) ((double-(uint8_t)(double)) > 0 ? (uint8_t)(double+1) : (uint8_t)(double))
 
 static const uint16_t polaris10_clock_stretcher_lookup_table[2][4] =
 { {600, 1050, 3, 0}, {600, 1050, 6, 1} };
@@ -733,7 +732,7 @@ static int polaris10_populate_smc_mvdd_table(struct pp_hwmgr *hwmgr,
 			table->Smio[level] |=
 				data->mvdd_voltage_table.entries[level].smio_low;
 		}
-		table->SmioMask2 = data->vddci_voltage_table.mask_low;
+		table->SmioMask2 = data->mvdd_voltage_table.mask_low;
 
 		table->MvddLevelCount = (uint32_t) PP_HOST_TO_SMC_UL(count);
 	}
@@ -1807,27 +1806,25 @@ static int polaris10_populate_clock_stretcher_data_table(struct pp_hwmgr *hwmgr)
 
 	ro = efuse * (max -min)/255 + min;
 
-	/* Populate Sclk_CKS_masterEn0_7 and Sclk_voltageOffset
-	 * there is a little difference in calculating
-	 * volt_with_cks with windows */
+	/* Populate Sclk_CKS_masterEn0_7 and Sclk_voltageOffset */
 	for (i = 0; i < sclk_table->count; i++) {
 		data->smc_state_table.Sclk_CKS_masterEn0_7 |=
 				sclk_table->entries[i].cks_enable << i;
 		if (hwmgr->chip_id == CHIP_POLARIS10) {
-			volt_without_cks = (uint32_t)((2753594000 + (sclk_table->entries[i].clk/100) * 136418 -(ro - 70) * 1000000) / \
+			volt_without_cks = (uint32_t)((2753594000U + (sclk_table->entries[i].clk/100) * 136418 -(ro - 70) * 1000000) / \
 						(2424180 - (sclk_table->entries[i].clk/100) * 1132925/1000));
-			volt_with_cks = (uint32_t)((279720200 + sclk_table->entries[i].clk * 3232 - (ro - 65) * 100000000) / \
-					(252248000 - sclk_table->entries[i].clk/100 * 115764));
+			volt_with_cks = (uint32_t)((2797202000U + sclk_table->entries[i].clk/100 * 3232 - (ro - 65) * 1000000) / \
+					(2522480 - sclk_table->entries[i].clk/100 * 115764/100));
 		} else {
-			volt_without_cks = (uint32_t)((2416794800 + (sclk_table->entries[i].clk/100) * 1476925/10 -(ro - 50) * 1000000) / \
-						(2625416 - (sclk_table->entries[i].clk/100) * 12586807/10000));
-			volt_with_cks = (uint32_t)((2999656000 + sclk_table->entries[i].clk * 392803/100 - (ro - 44) * 1000000) / \
-					(3422454 - sclk_table->entries[i].clk/100 * 18886376/10000));
+			volt_without_cks = (uint32_t)((2416794800U + (sclk_table->entries[i].clk/100) * 1476925/10 -(ro - 50) * 1000000) / \
+						(2625416 - (sclk_table->entries[i].clk/100) * (12586807/10000)));
+			volt_with_cks = (uint32_t)((2999656000U - sclk_table->entries[i].clk/100 * 392803 - (ro - 44) * 1000000) / \
+					(3422454 - sclk_table->entries[i].clk/100 * (18886376/10000)));
 		}
 
 		if (volt_without_cks >= volt_with_cks)
-			volt_offset = (uint8_t)CEILING_UCHAR((volt_without_cks - volt_with_cks +
-					sclk_table->entries[i].cks_voffset) * 100 / 625);
+			volt_offset = (uint8_t)(((volt_without_cks - volt_with_cks +
+					sclk_table->entries[i].cks_voffset) * 100 + 624) / 625);
 
 		data->smc_state_table.Sclk_voltageOffset[i] = volt_offset;
 	}
@@ -2685,7 +2682,7 @@ static int polaris10_get_evv_voltages(struct pp_hwmgr *hwmgr)
 {
 	struct polaris10_hwmgr *data = (struct polaris10_hwmgr *)(hwmgr->backend);
 	uint16_t vv_id;
-	uint16_t vddc = 0;
+	uint32_t vddc = 0;
 	uint16_t i, j;
 	uint32_t sclk = 0;
 	struct phm_ppt_v1_information *table_info =
@@ -2716,8 +2713,9 @@ static int polaris10_get_evv_voltages(struct pp_hwmgr *hwmgr)
 						continue);
 
 
-			/* need to make sure vddc is less than 2v or else, it could burn the ASIC. */
-			PP_ASSERT_WITH_CODE((vddc < 2000 && vddc != 0),
+			/* need to make sure vddc is less than 2v or else, it could burn the ASIC.
+			 * real voltage level in unit of 0.01mv */
+			PP_ASSERT_WITH_CODE((vddc < 200000 && vddc != 0),
 					"Invalid VDDC value", result = -EINVAL;);
 
 			/* the voltage should not be zero nor equal to leakage ID */

drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.c

@@ -1256,7 +1256,7 @@ int atomctrl_set_ac_timing_ai(struct pp_hwmgr *hwmgr, uint32_t memory_clock,
 }
 
 int atomctrl_get_voltage_evv_on_sclk_ai(struct pp_hwmgr *hwmgr, uint8_t voltage_type,
-				uint32_t sclk, uint16_t virtual_voltage_Id, uint16_t *voltage)
+				uint32_t sclk, uint16_t virtual_voltage_Id, uint32_t *voltage)
 {
 
 	int result;
@@ -1274,7 +1274,7 @@ int atomctrl_get_voltage_evv_on_sclk_ai(struct pp_hwmgr *hwmgr, uint8_t voltage_
 	if (0 != result)
 		return result;
 
-	*voltage = get_voltage_info_param_space.usVoltageLevel;
+	*voltage = ((GET_EVV_VOLTAGE_INFO_OUTPUT_PARAMETER_V1_3 *)(&get_voltage_info_param_space))->ulVoltageLevel;
 
 	return result;
 }

drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.h

@@ -305,7 +305,7 @@ extern int atomctrl_get_engine_pll_dividers_ai(struct pp_hwmgr *hwmgr, uint32_t
 extern int atomctrl_set_ac_timing_ai(struct pp_hwmgr *hwmgr, uint32_t memory_clock,
 								uint8_t level);
 extern int atomctrl_get_voltage_evv_on_sclk_ai(struct pp_hwmgr *hwmgr, uint8_t voltage_type,
-				uint32_t sclk, uint16_t virtual_voltage_Id, uint16_t *voltage);
+				uint32_t sclk, uint16_t virtual_voltage_Id, uint32_t *voltage);
 extern int atomctrl_get_smc_sclk_range_table(struct pp_hwmgr *hwmgr, struct pp_atom_ctrl_sclk_range_table *table);
 
 extern int atomctrl_get_avfs_information(struct pp_hwmgr *hwmgr, struct pp_atom_ctrl__avfs_parameters *param);

drivers/gpu/drm/amd/powerplay/hwmgr/tonga_hwmgr.c

@@ -1302,7 +1302,7 @@ static int tonga_populate_smc_mvdd_table(struct pp_hwmgr *hwmgr,
 			table->Smio[count] |=
 				data->mvdd_voltage_table.entries[count].smio_low;
 		}
-		table->SmioMask2 = data->vddci_voltage_table.mask_low;
+		table->SmioMask2 = data->mvdd_voltage_table.mask_low;
 
 		CONVERT_FROM_HOST_TO_SMC_UL(table->MvddLevelCount);
 	}

drivers/gpu/drm/amd/powerplay/hwmgr/tonga_processpptables.c

@@ -302,7 +302,7 @@ static int init_dpm_2_parameters(
 			(((unsigned long)powerplay_table) + le16_to_cpu(powerplay_table->usPPMTableOffset));
 
 		if (0 != powerplay_table->usPPMTableOffset) {
-			if (1 == get_platform_power_management_table(hwmgr, atom_ppm_table)) {
+			if (get_platform_power_management_table(hwmgr, atom_ppm_table) == 0) {
 				phm_cap_set(hwmgr->platform_descriptor.platformCaps,
 					PHM_PlatformCaps_EnablePlatformPowerManagement);
 			}

drivers/gpu/drm/nouveau/nvkm/engine/disp/sorgf119.c

@@ -40,7 +40,8 @@ static int
 gf119_sor_dp_pattern(struct nvkm_output_dp *outp, int pattern)
 {
 	struct nvkm_device *device = outp->base.disp->engine.subdev.device;
-	nvkm_mask(device, 0x61c110, 0x0f0f0f0f, 0x01010101 * pattern);
+	const u32 soff = gf119_sor_soff(outp);
+	nvkm_mask(device, 0x61c110 + soff, 0x0f0f0f0f, 0x01010101 * pattern);
 	return 0;
 }
 

drivers/gpu/drm/sun4i/sun4i_crtc.c

@@ -65,6 +65,14 @@ static void sun4i_crtc_disable(struct drm_crtc *crtc)
 	DRM_DEBUG_DRIVER("Disabling the CRTC\n");
 
 	sun4i_tcon_disable(drv->tcon);
+
+	if (crtc->state->event && !crtc->state->active) {
+		spin_lock_irq(&crtc->dev->event_lock);
+		drm_crtc_send_vblank_event(crtc, crtc->state->event);
+		spin_unlock_irq(&crtc->dev->event_lock);
+
+		crtc->state->event = NULL;
+	}
 }
 
 static void sun4i_crtc_enable(struct drm_crtc *crtc)

drivers/gpu/drm/sun4i/sun4i_drv.c

@@ -92,7 +92,7 @@ static struct drm_driver sun4i_drv_driver = {
 	/* Frame Buffer Operations */
 
 	/* VBlank Operations */
-	.get_vblank_counter	= drm_vblank_count,
+	.get_vblank_counter	= drm_vblank_no_hw_counter,
 	.enable_vblank		= sun4i_drv_enable_vblank,
 	.disable_vblank		= sun4i_drv_disable_vblank,
 };
@@ -310,6 +310,7 @@ static int sun4i_drv_probe(struct platform_device *pdev)
 
 		count += sun4i_drv_add_endpoints(&pdev->dev, &match,
 						pipeline);
+		of_node_put(pipeline);
 
 		DRM_DEBUG_DRIVER("Queued %d outputs on pipeline %d\n",
 				 count, i);

drivers/iommu/amd_iommu_init.c

@@ -1568,13 +1568,23 @@ static int __init amd_iommu_init_pci(void)
 			break;
 	}
 
+	/*
+	 * Order is important here to make sure any unity map requirements are
+	 * fulfilled. The unity mappings are created and written to the device
+	 * table during the amd_iommu_init_api() call.
+	 *
+	 * After that we call init_device_table_dma() to make sure any
+	 * uninitialized DTE will block DMA, and in the end we flush the caches
+	 * of all IOMMUs to make sure the changes to the device table are
+	 * active.
+	 */
+	ret = amd_iommu_init_api();
+
 	init_device_table_dma();
 
 	for_each_iommu(iommu)
 		iommu_flush_all_caches(iommu);
 
-	ret = amd_iommu_init_api();
-
 	if (!ret)
 		print_iommu_info();
 

drivers/iommu/intel-iommu.c

@@ -4602,13 +4602,13 @@ static void free_all_cpu_cached_iovas(unsigned int cpu)
 	for (i = 0; i < g_num_of_iommus; i++) {
 		struct intel_iommu *iommu = g_iommus[i];
 		struct dmar_domain *domain;
-		u16 did;
+		int did;
 
 		if (!iommu)
 			continue;
 
 		for (did = 0; did < cap_ndoms(iommu->cap); did++) {
-			domain = get_iommu_domain(iommu, did);
+			domain = get_iommu_domain(iommu, (u16)did);
 
 			if (!domain)
 				continue;

drivers/irqchip/irq-mips-gic.c

@@ -718,7 +718,7 @@ static int gic_shared_irq_domain_map(struct irq_domain *d, unsigned int virq,
 
 	spin_lock_irqsave(&gic_lock, flags);
 	gic_map_to_pin(intr, gic_cpu_pin);
-	gic_map_to_vpe(intr, vpe);
+	gic_map_to_vpe(intr, mips_cm_vp_id(vpe));
 	for (i = 0; i < min(gic_vpes, NR_CPUS); i++)
 		clear_bit(intr, pcpu_masks[i].pcpu_mask);
 	set_bit(intr, pcpu_masks[vpe].pcpu_mask);
@@ -959,7 +959,7 @@ int gic_ipi_domain_match(struct irq_domain *d, struct device_node *node,
 	switch (bus_token) {
 	case DOMAIN_BUS_IPI:
 		is_ipi = d->bus_token == bus_token;
-		return to_of_node(d->fwnode) == node && is_ipi;
+		return (!node || to_of_node(d->fwnode) == node) && is_ipi;
 		break;
 	default:
 		return 0;

drivers/net/bonding/bond_3ad.c

@@ -101,11 +101,14 @@ enum ad_link_speed_type {
 #define MAC_ADDRESS_EQUAL(A, B)	\
 	ether_addr_equal_64bits((const u8 *)A, (const u8 *)B)
 
-static struct mac_addr null_mac_addr = { { 0, 0, 0, 0, 0, 0 } };
+static const u8 null_mac_addr[ETH_ALEN + 2] __long_aligned = {
+	0, 0, 0, 0, 0, 0
+};
 static u16 ad_ticks_per_sec;
 static const int ad_delta_in_ticks = (AD_TIMER_INTERVAL * HZ) / 1000;
 
-static const u8 lacpdu_mcast_addr[ETH_ALEN] = MULTICAST_LACPDU_ADDR;
+static const u8 lacpdu_mcast_addr[ETH_ALEN + 2] __long_aligned =
+	MULTICAST_LACPDU_ADDR;
 
 /* ================= main 802.3ad protocol functions ================== */
 static int ad_lacpdu_send(struct port *port);
@@ -1739,7 +1742,7 @@ static void ad_clear_agg(struct aggregator *aggregator)
 		aggregator->is_individual = false;
 		aggregator->actor_admin_aggregator_key = 0;
 		aggregator->actor_oper_aggregator_key = 0;
-		aggregator->partner_system = null_mac_addr;
+		eth_zero_addr(aggregator->partner_system.mac_addr_value);
 		aggregator->partner_system_priority = 0;
 		aggregator->partner_oper_aggregator_key = 0;
 		aggregator->receive_state = 0;
@@ -1761,7 +1764,7 @@ static void ad_initialize_agg(struct aggregator *aggregator)
 	if (aggregator) {
 		ad_clear_agg(aggregator);
 
-		aggregator->aggregator_mac_address = null_mac_addr;
+		eth_zero_addr(aggregator->aggregator_mac_address.mac_addr_value);
 		aggregator->aggregator_identifier = 0;
 		aggregator->slave = NULL;
 	}

drivers/net/bonding/bond_alb.c

@@ -42,13 +42,10 @@
 
 
 
-#ifndef __long_aligned
-#define __long_aligned __attribute__((aligned((sizeof(long)))))
-#endif
-static const u8 mac_bcast[ETH_ALEN] __long_aligned = {
+static const u8 mac_bcast[ETH_ALEN + 2] __long_aligned = {
 	0xff, 0xff, 0xff, 0xff, 0xff, 0xff
 };
-static const u8 mac_v6_allmcast[ETH_ALEN] __long_aligned = {
+static const u8 mac_v6_allmcast[ETH_ALEN + 2] __long_aligned = {
 	0x33, 0x33, 0x00, 0x00, 0x00, 0x01
 };
 static const int alb_delta_in_ticks = HZ / ALB_TIMER_TICKS_PER_SEC;

drivers/net/bonding/bond_main.c

@@ -1584,6 +1584,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
 	}
 
 	/* check for initial state */
+	new_slave->link = BOND_LINK_NOCHANGE;
 	if (bond->params.miimon) {
 		if (bond_check_dev_link(bond, slave_dev, 0) == BMSR_LSTATUS) {
 			if (bond->params.updelay) {

drivers/net/ethernet/broadcom/bcmsysport.c

@@ -392,7 +392,7 @@ static void bcm_sysport_get_stats(struct net_device *dev,
 		else
 			p = (char *)priv;
 		p += s->stat_offset;
-		data[i] = *(u32 *)p;
+		data[i] = *(unsigned long *)p;
 	}
 }
 

drivers/net/ethernet/chelsio/cxgb4/t4fw_version.h

@@ -36,8 +36,8 @@
 #define __T4FW_VERSION_H__
 
 #define T4FW_VERSION_MAJOR 0x01
-#define T4FW_VERSION_MINOR 0x0E
-#define T4FW_VERSION_MICRO 0x04
+#define T4FW_VERSION_MINOR 0x0F
+#define T4FW_VERSION_MICRO 0x25
 #define T4FW_VERSION_BUILD 0x00
 
 #define T4FW_MIN_VERSION_MAJOR 0x01
@@ -45,8 +45,8 @@
 #define T4FW_MIN_VERSION_MICRO 0x00
 
 #define T5FW_VERSION_MAJOR 0x01
-#define T5FW_VERSION_MINOR 0x0E
-#define T5FW_VERSION_MICRO 0x04
+#define T5FW_VERSION_MINOR 0x0F
+#define T5FW_VERSION_MICRO 0x25
 #define T5FW_VERSION_BUILD 0x00
 
 #define T5FW_MIN_VERSION_MAJOR 0x00
@@ -54,8 +54,8 @@
 #define T5FW_MIN_VERSION_MICRO 0x00
 
 #define T6FW_VERSION_MAJOR 0x01
-#define T6FW_VERSION_MINOR 0x0E
-#define T6FW_VERSION_MICRO 0x04
+#define T6FW_VERSION_MINOR 0x0F
+#define T6FW_VERSION_MICRO 0x25
 #define T6FW_VERSION_BUILD 0x00
 
 #define T6FW_MIN_VERSION_MAJOR 0x00

drivers/net/ethernet/intel/e1000e/netdev.c

@@ -154,16 +154,6 @@ void __ew32(struct e1000_hw *hw, unsigned long reg, u32 val)
 	writel(val, hw->hw_addr + reg);
 }
 
-static bool e1000e_vlan_used(struct e1000_adapter *adapter)
-{
-	u16 vid;
-
-	for_each_set_bit(vid, adapter->active_vlans, VLAN_N_VID)
-		return true;
-
-	return false;
-}
-
 /**
  * e1000_regdump - register printout routine
  * @hw: pointer to the HW structure
@@ -3453,8 +3443,7 @@ static void e1000e_set_rx_mode(struct net_device *netdev)
 
 	ew32(RCTL, rctl);
 
-	if (netdev->features & NETIF_F_HW_VLAN_CTAG_RX ||
-	    e1000e_vlan_used(adapter))
+	if (netdev->features & NETIF_F_HW_VLAN_CTAG_RX)
 		e1000e_vlan_strip_enable(adapter);
 	else
 		e1000e_vlan_strip_disable(adapter);
@@ -6926,6 +6915,14 @@ static netdev_features_t e1000_fix_features(struct net_device *netdev,
 	if ((hw->mac.type >= e1000_pch2lan) && (netdev->mtu > ETH_DATA_LEN))
 		features &= ~NETIF_F_RXFCS;
 
+	/* Since there is no support for separate Rx/Tx vlan accel
+	 * enable/disable make sure Tx flag is always in same state as Rx.
+	 */
+	if (features & NETIF_F_HW_VLAN_CTAG_RX)
+		features |= NETIF_F_HW_VLAN_CTAG_TX;
+	else
+		features &= ~NETIF_F_HW_VLAN_CTAG_TX;
+
 	return features;
 }
 

drivers/net/ethernet/intel/ixgbevf/mbx.c

@@ -85,7 +85,7 @@ static s32 ixgbevf_poll_for_ack(struct ixgbe_hw *hw)
 static s32 ixgbevf_read_posted_mbx(struct ixgbe_hw *hw, u32 *msg, u16 size)
 {
 	struct ixgbe_mbx_info *mbx = &hw->mbx;
-	s32 ret_val = -IXGBE_ERR_MBX;
+	s32 ret_val = IXGBE_ERR_MBX;
 
 	if (!mbx->ops.read)
 		goto out;
@@ -111,7 +111,7 @@ out:
 static s32 ixgbevf_write_posted_mbx(struct ixgbe_hw *hw, u32 *msg, u16 size)
 {
 	struct ixgbe_mbx_info *mbx = &hw->mbx;
-	s32 ret_val = -IXGBE_ERR_MBX;
+	s32 ret_val = IXGBE_ERR_MBX;
 
 	/* exit if either we can't write or there isn't a defined timeout */
 	if (!mbx->ops.write || !mbx->timeout)

drivers/net/ethernet/marvell/mvneta.c

@@ -3458,6 +3458,8 @@ static int mvneta_open(struct net_device *dev)
 	return 0;
 
 err_free_irq:
+	unregister_cpu_notifier(&pp->cpu_notifier);
+	on_each_cpu(mvneta_percpu_disable, pp, true);
 	free_percpu_irq(pp->dev->irq, pp->ports);
 err_cleanup_txqs:
 	mvneta_cleanup_txqs(pp);

drivers/net/ethernet/mellanox/mlx5/core/cmd.c

@@ -295,6 +295,12 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op,
 	case MLX5_CMD_OP_DESTROY_FLOW_GROUP:
 	case MLX5_CMD_OP_DELETE_FLOW_TABLE_ENTRY:
 	case MLX5_CMD_OP_DEALLOC_FLOW_COUNTER:
+	case MLX5_CMD_OP_2ERR_QP:
+	case MLX5_CMD_OP_2RST_QP:
+	case MLX5_CMD_OP_MODIFY_NIC_VPORT_CONTEXT:
+	case MLX5_CMD_OP_MODIFY_FLOW_TABLE:
+	case MLX5_CMD_OP_SET_FLOW_TABLE_ENTRY:
+	case MLX5_CMD_OP_SET_FLOW_TABLE_ROOT:
 		return MLX5_CMD_STAT_OK;
 
 	case MLX5_CMD_OP_QUERY_HCA_CAP:
@@ -321,8 +327,6 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op,
 	case MLX5_CMD_OP_RTR2RTS_QP:
 	case MLX5_CMD_OP_RTS2RTS_QP:
 	case MLX5_CMD_OP_SQERR2RTS_QP:
-	case MLX5_CMD_OP_2ERR_QP:
-	case MLX5_CMD_OP_2RST_QP:
 	case MLX5_CMD_OP_QUERY_QP:
 	case MLX5_CMD_OP_SQD_RTS_QP:
 	case MLX5_CMD_OP_INIT2INIT_QP:
@@ -342,7 +346,6 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op,
 	case MLX5_CMD_OP_QUERY_ESW_VPORT_CONTEXT:
 	case MLX5_CMD_OP_MODIFY_ESW_VPORT_CONTEXT:
 	case MLX5_CMD_OP_QUERY_NIC_VPORT_CONTEXT:
-	case MLX5_CMD_OP_MODIFY_NIC_VPORT_CONTEXT:
 	case MLX5_CMD_OP_QUERY_ROCE_ADDRESS:
 	case MLX5_CMD_OP_SET_ROCE_ADDRESS:
 	case MLX5_CMD_OP_QUERY_HCA_VPORT_CONTEXT:
@@ -390,11 +393,12 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op,
 	case MLX5_CMD_OP_CREATE_RQT:
 	case MLX5_CMD_OP_MODIFY_RQT:
 	case MLX5_CMD_OP_QUERY_RQT:
+
 	case MLX5_CMD_OP_CREATE_FLOW_TABLE:
 	case MLX5_CMD_OP_QUERY_FLOW_TABLE:
 	case MLX5_CMD_OP_CREATE_FLOW_GROUP:
 	case MLX5_CMD_OP_QUERY_FLOW_GROUP:
-	case MLX5_CMD_OP_SET_FLOW_TABLE_ENTRY:
+
 	case MLX5_CMD_OP_QUERY_FLOW_TABLE_ENTRY:
 	case MLX5_CMD_OP_ALLOC_FLOW_COUNTER:
 	case MLX5_CMD_OP_QUERY_FLOW_COUNTER:
@@ -602,11 +606,36 @@ static void dump_command(struct mlx5_core_dev *dev,
 		pr_debug("\n");
 }
 
+static u16 msg_to_opcode(struct mlx5_cmd_msg *in)
+{
+	struct mlx5_inbox_hdr *hdr = (struct mlx5_inbox_hdr *)(in->first.data);
+
+	return be16_to_cpu(hdr->opcode);
+}
+
+static void cb_timeout_handler(struct work_struct *work)
+{
+	struct delayed_work *dwork = container_of(work, struct delayed_work,
+						  work);
+	struct mlx5_cmd_work_ent *ent = container_of(dwork,
+						     struct mlx5_cmd_work_ent,
+						     cb_timeout_work);
+	struct mlx5_core_dev *dev = container_of(ent->cmd, struct mlx5_core_dev,
+						 cmd);
+
+	ent->ret = -ETIMEDOUT;
+	mlx5_core_warn(dev, "%s(0x%x) timeout. Will cause a leak of a command resource\n",
+		       mlx5_command_str(msg_to_opcode(ent->in)),
+		       msg_to_opcode(ent->in));
+	mlx5_cmd_comp_handler(dev, 1UL << ent->idx);
+}
+
 static void cmd_work_handler(struct work_struct *work)
 {
 	struct mlx5_cmd_work_ent *ent = container_of(work, struct mlx5_cmd_work_ent, work);
 	struct mlx5_cmd *cmd = ent->cmd;
 	struct mlx5_core_dev *dev = container_of(cmd, struct mlx5_core_dev, cmd);
+	unsigned long cb_timeout = msecs_to_jiffies(MLX5_CMD_TIMEOUT_MSEC);
 	struct mlx5_cmd_layout *lay;
 	struct semaphore *sem;
 	unsigned long flags;
@@ -647,6 +676,9 @@ static void cmd_work_handler(struct work_struct *work)
 	dump_command(dev, ent, 1);
 	ent->ts1 = ktime_get_ns();
 
+	if (ent->callback)
+		schedule_delayed_work(&ent->cb_timeout_work, cb_timeout);
+
 	/* ring doorbell after the descriptor is valid */
 	mlx5_core_dbg(dev, "writing 0x%x to command doorbell\n", 1 << ent->idx);
 	wmb();
@@ -691,13 +723,6 @@ static const char *deliv_status_to_str(u8 status)
 	}
 }
 
-static u16 msg_to_opcode(struct mlx5_cmd_msg *in)
-{
-	struct mlx5_inbox_hdr *hdr = (struct mlx5_inbox_hdr *)(in->first.data);
-
-	return be16_to_cpu(hdr->opcode);
-}
-
 static int wait_func(struct mlx5_core_dev *dev, struct mlx5_cmd_work_ent *ent)
 {
 	unsigned long timeout = msecs_to_jiffies(MLX5_CMD_TIMEOUT_MSEC);
@@ -706,13 +731,13 @@ static int wait_func(struct mlx5_core_dev *dev, struct mlx5_cmd_work_ent *ent)
 
 	if (cmd->mode == CMD_MODE_POLLING) {
 		wait_for_completion(&ent->done);
-		err = ent->ret;
-	} else {
-		if (!wait_for_completion_timeout(&ent->done, timeout))
-			err = -ETIMEDOUT;
-		else
-			err = 0;
+	} else if (!wait_for_completion_timeout(&ent->done, timeout)) {
+		ent->ret = -ETIMEDOUT;
+		mlx5_cmd_comp_handler(dev, 1UL << ent->idx);
 	}
+
+	err = ent->ret;
+
 	if (err == -ETIMEDOUT) {
 		mlx5_core_warn(dev, "%s(0x%x) timeout. Will cause a leak of a command resource\n",
 			       mlx5_command_str(msg_to_opcode(ent->in)),
@@ -761,6 +786,7 @@ static int mlx5_cmd_invoke(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *in,
 	if (!callback)
 		init_completion(&ent->done);
 
+	INIT_DELAYED_WORK(&ent->cb_timeout_work, cb_timeout_handler);
 	INIT_WORK(&ent->work, cmd_work_handler);
 	if (page_queue) {
 		cmd_work_handler(&ent->work);
@@ -770,28 +796,26 @@ static int mlx5_cmd_invoke(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *in,
 		goto out_free;
 	}
 
-	if (!callback) {
-		err = wait_func(dev, ent);
-		if (err == -ETIMEDOUT)
-			goto out;
-
-		ds = ent->ts2 - ent->ts1;
-		op = be16_to_cpu(((struct mlx5_inbox_hdr *)in->first.data)->opcode);
-		if (op < ARRAY_SIZE(cmd->stats)) {
-			stats = &cmd->stats[op];
-			spin_lock_irq(&stats->lock);
-			stats->sum += ds;
-			++stats->n;
-			spin_unlock_irq(&stats->lock);
-		}
-		mlx5_core_dbg_mask(dev, 1 << MLX5_CMD_TIME,
-				   "fw exec time for %s is %lld nsec\n",
-				   mlx5_command_str(op), ds);
-		*status = ent->status;
-		free_cmd(ent);
-	}
+	if (callback)
+		goto out;
 
-	return err;
+	err = wait_func(dev, ent);
+	if (err == -ETIMEDOUT)
+		goto out_free;
+
+	ds = ent->ts2 - ent->ts1;
+	op = be16_to_cpu(((struct mlx5_inbox_hdr *)in->first.data)->opcode);
+	if (op < ARRAY_SIZE(cmd->stats)) {
+		stats = &cmd->stats[op];
+		spin_lock_irq(&stats->lock);
+		stats->sum += ds;
+		++stats->n;
+		spin_unlock_irq(&stats->lock);
+	}
+	mlx5_core_dbg_mask(dev, 1 << MLX5_CMD_TIME,
+			   "fw exec time for %s is %lld nsec\n",
+			   mlx5_command_str(op), ds);
+	*status = ent->status;
 
 out_free:
 	free_cmd(ent);
@@ -1181,41 +1205,30 @@ err_dbg:
 	return err;
 }
 
-void mlx5_cmd_use_events(struct mlx5_core_dev *dev)
+static void mlx5_cmd_change_mod(struct mlx5_core_dev *dev, int mode)
 {
 	struct mlx5_cmd *cmd = &dev->cmd;
 	int i;
 
 	for (i = 0; i < cmd->max_reg_cmds; i++)
 		down(&cmd->sem);
-
 	down(&cmd->pages_sem);
 
-	flush_workqueue(cmd->wq);
-
-	cmd->mode = CMD_MODE_EVENTS;
+	cmd->mode = mode;
 
 	up(&cmd->pages_sem);
 	for (i = 0; i < cmd->max_reg_cmds; i++)
 		up(&cmd->sem);
 }
 
-void mlx5_cmd_use_polling(struct mlx5_core_dev *dev)
+void mlx5_cmd_use_events(struct mlx5_core_dev *dev)
 {
-	struct mlx5_cmd *cmd = &dev->cmd;
-	int i;
-
-	for (i = 0; i < cmd->max_reg_cmds; i++)
-		down(&cmd->sem);
-
-	down(&cmd->pages_sem);
-
-	flush_workqueue(cmd->wq);
-	cmd->mode = CMD_MODE_POLLING;
+	mlx5_cmd_change_mod(dev, CMD_MODE_EVENTS);
+}
 
-	up(&cmd->pages_sem);
-	for (i = 0; i < cmd->max_reg_cmds; i++)
-		up(&cmd->sem);
+void mlx5_cmd_use_polling(struct mlx5_core_dev *dev)
+{
+	mlx5_cmd_change_mod(dev, CMD_MODE_POLLING);
 }
 
 static void free_msg(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *msg)
@@ -1251,6 +1264,8 @@ void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec)
 			struct semaphore *sem;
 
 			ent = cmd->ent_arr[i];
+			if (ent->callback)
+				cancel_delayed_work(&ent->cb_timeout_work);
 			if (ent->page_queue)
 				sem = &cmd->pages_sem;
 			else

drivers/net/ethernet/mellanox/mlx5/core/en.h

@@ -145,7 +145,6 @@ struct mlx5e_umr_wqe {
 
 #ifdef CONFIG_MLX5_CORE_EN_DCB
 #define MLX5E_MAX_BW_ALLOC 100 /* Max percentage of BW allocation */
-#define MLX5E_MIN_BW_ALLOC 1   /* Min percentage of BW allocation */
 #endif
 
 struct mlx5e_params {
@@ -191,6 +190,7 @@ struct mlx5e_tstamp {
 enum {
 	MLX5E_RQ_STATE_POST_WQES_ENABLE,
 	MLX5E_RQ_STATE_UMR_WQE_IN_PROGRESS,
+	MLX5E_RQ_STATE_FLUSH_TIMEOUT,
 };
 
 struct mlx5e_cq {
@@ -220,6 +220,8 @@ typedef void (*mlx5e_fp_handle_rx_cqe)(struct mlx5e_rq *rq,
 typedef int (*mlx5e_fp_alloc_wqe)(struct mlx5e_rq *rq, struct mlx5e_rx_wqe *wqe,
 				  u16 ix);
 
+typedef void (*mlx5e_fp_dealloc_wqe)(struct mlx5e_rq *rq, u16 ix);
+
 struct mlx5e_dma_info {
 	struct page	*page;
 	dma_addr_t	addr;
@@ -241,6 +243,7 @@ struct mlx5e_rq {
 	struct mlx5e_cq        cq;
 	mlx5e_fp_handle_rx_cqe handle_rx_cqe;
 	mlx5e_fp_alloc_wqe     alloc_wqe;
+	mlx5e_fp_dealloc_wqe   dealloc_wqe;
 
 	unsigned long          state;
 	int                    ix;
@@ -305,6 +308,7 @@ struct mlx5e_sq_dma {
 enum {
 	MLX5E_SQ_STATE_WAKE_TXQ_ENABLE,
 	MLX5E_SQ_STATE_BF_ENABLE,
+	MLX5E_SQ_STATE_TX_TIMEOUT,
 };
 
 struct mlx5e_ico_wqe_info {
@@ -538,6 +542,7 @@ struct mlx5e_priv {
 	struct workqueue_struct    *wq;
 	struct work_struct         update_carrier_work;
 	struct work_struct         set_rx_mode_work;
+	struct work_struct         tx_timeout_work;
 	struct delayed_work        update_stats_work;
 
 	struct mlx5_core_dev      *mdev;
@@ -589,12 +594,16 @@ void mlx5e_cq_error_event(struct mlx5_core_cq *mcq, enum mlx5_event event);
 int mlx5e_napi_poll(struct napi_struct *napi, int budget);
 bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget);
 int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget);
+void mlx5e_free_tx_descs(struct mlx5e_sq *sq);
+void mlx5e_free_rx_descs(struct mlx5e_rq *rq);
 
 void mlx5e_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe);
 void mlx5e_handle_rx_cqe_mpwrq(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe);
 bool mlx5e_post_rx_wqes(struct mlx5e_rq *rq);
 int mlx5e_alloc_rx_wqe(struct mlx5e_rq *rq, struct mlx5e_rx_wqe *wqe, u16 ix);
 int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, struct mlx5e_rx_wqe *wqe, u16 ix);
+void mlx5e_dealloc_rx_wqe(struct mlx5e_rq *rq, u16 ix);
+void mlx5e_dealloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix);
 void mlx5e_post_rx_fragmented_mpwqe(struct mlx5e_rq *rq);
 void mlx5e_complete_rx_linear_mpwqe(struct mlx5e_rq *rq,
 				    struct mlx5_cqe64 *cqe,

drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c

@@ -96,7 +96,7 @@ static void mlx5e_build_tc_tx_bw(struct ieee_ets *ets, u8 *tc_tx_bw,
 			tc_tx_bw[i] = MLX5E_MAX_BW_ALLOC;
 			break;
 		case IEEE_8021QAZ_TSA_ETS:
-			tc_tx_bw[i] = ets->tc_tx_bw[i] ?: MLX5E_MIN_BW_ALLOC;
+			tc_tx_bw[i] = ets->tc_tx_bw[i];
 			break;
 		}
 	}
@@ -140,8 +140,12 @@ static int mlx5e_dbcnl_validate_ets(struct ieee_ets *ets)
 
 	/* Validate Bandwidth Sum */
 	for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) {
-		if (ets->tc_tsa[i] == IEEE_8021QAZ_TSA_ETS)
+		if (ets->tc_tsa[i] == IEEE_8021QAZ_TSA_ETS) {
+			if (!ets->tc_tx_bw[i])
+				return -EINVAL;
+
 			bw_sum += ets->tc_tx_bw[i];
+		}
 	}
 
 	if (bw_sum != 0 && bw_sum != 100)

drivers/net/ethernet/mellanox/mlx5/core/en_main.c

@@ -39,6 +39,13 @@
 #include "eswitch.h"
 #include "vxlan.h"
 
+enum {
+	MLX5_EN_QP_FLUSH_TIMEOUT_MS	= 5000,
+	MLX5_EN_QP_FLUSH_MSLEEP_QUANT	= 20,
+	MLX5_EN_QP_FLUSH_MAX_ITER	= MLX5_EN_QP_FLUSH_TIMEOUT_MS /
+					  MLX5_EN_QP_FLUSH_MSLEEP_QUANT,
+};
+
 struct mlx5e_rq_param {
 	u32                        rqc[MLX5_ST_SZ_DW(rqc)];
 	struct mlx5_wq_param       wq;
@@ -74,10 +81,13 @@ static void mlx5e_update_carrier(struct mlx5e_priv *priv)
 	port_state = mlx5_query_vport_state(mdev,
 		MLX5_QUERY_VPORT_STATE_IN_OP_MOD_VNIC_VPORT, 0);
 
-	if (port_state == VPORT_STATE_UP)
+	if (port_state == VPORT_STATE_UP) {
+		netdev_info(priv->netdev, "Link up\n");
 		netif_carrier_on(priv->netdev);
-	else
+	} else {
+		netdev_info(priv->netdev, "Link down\n");
 		netif_carrier_off(priv->netdev);
+	}
 }
 
 static void mlx5e_update_carrier_work(struct work_struct *work)
@@ -91,6 +101,26 @@ static void mlx5e_update_carrier_work(struct work_struct *work)
 	mutex_unlock(&priv->state_lock);
 }
 
+static void mlx5e_tx_timeout_work(struct work_struct *work)
+{
+	struct mlx5e_priv *priv = container_of(work, struct mlx5e_priv,
+					       tx_timeout_work);
+	int err;
+
+	rtnl_lock();
+	mutex_lock(&priv->state_lock);
+	if (!test_bit(MLX5E_STATE_OPENED, &priv->state))
+		goto unlock;
+	mlx5e_close_locked(priv->netdev);
+	err = mlx5e_open_locked(priv->netdev);
+	if (err)
+		netdev_err(priv->netdev, "mlx5e_open_locked failed recovering from a tx_timeout, err(%d).\n",
+			   err);
+unlock:
+	mutex_unlock(&priv->state_lock);
+	rtnl_unlock();
+}
+
 static void mlx5e_update_sw_counters(struct mlx5e_priv *priv)
 {
 	struct mlx5e_sw_stats *s = &priv->stats.sw;
@@ -305,6 +335,7 @@ static int mlx5e_create_rq(struct mlx5e_channel *c,
 		}
 		rq->handle_rx_cqe = mlx5e_handle_rx_cqe_mpwrq;
 		rq->alloc_wqe = mlx5e_alloc_rx_mpwqe;
+		rq->dealloc_wqe = mlx5e_dealloc_rx_mpwqe;
 
 		rq->mpwqe_stride_sz = BIT(priv->params.mpwqe_log_stride_sz);
 		rq->mpwqe_num_strides = BIT(priv->params.mpwqe_log_num_strides);
@@ -320,6 +351,7 @@ static int mlx5e_create_rq(struct mlx5e_channel *c,
 		}
 		rq->handle_rx_cqe = mlx5e_handle_rx_cqe;
 		rq->alloc_wqe = mlx5e_alloc_rx_wqe;
+		rq->dealloc_wqe = mlx5e_dealloc_rx_wqe;
 
 		rq->wqe_sz = (priv->params.lro_en) ?
 				priv->params.lro_wqe_sz :
@@ -525,17 +557,25 @@ err_destroy_rq:
 
 static void mlx5e_close_rq(struct mlx5e_rq *rq)
 {
+	int tout = 0;
+	int err;
+
 	clear_bit(MLX5E_RQ_STATE_POST_WQES_ENABLE, &rq->state);
 	napi_synchronize(&rq->channel->napi); /* prevent mlx5e_post_rx_wqes */
 
-	mlx5e_modify_rq_state(rq, MLX5_RQC_STATE_RDY, MLX5_RQC_STATE_ERR);
-	while (!mlx5_wq_ll_is_empty(&rq->wq))
-		msleep(20);
+	err = mlx5e_modify_rq_state(rq, MLX5_RQC_STATE_RDY, MLX5_RQC_STATE_ERR);
+	while (!mlx5_wq_ll_is_empty(&rq->wq) && !err &&
+	       tout++ < MLX5_EN_QP_FLUSH_MAX_ITER)
+		msleep(MLX5_EN_QP_FLUSH_MSLEEP_QUANT);
+
+	if (err || tout == MLX5_EN_QP_FLUSH_MAX_ITER)
+		set_bit(MLX5E_RQ_STATE_FLUSH_TIMEOUT, &rq->state);
 
 	/* avoid destroying rq before mlx5e_poll_rx_cq() is done with it */
 	napi_synchronize(&rq->channel->napi);
 
 	mlx5e_disable_rq(rq);
+	mlx5e_free_rx_descs(rq);
 	mlx5e_destroy_rq(rq);
 }
 
@@ -782,6 +822,9 @@ static inline void netif_tx_disable_queue(struct netdev_queue *txq)
 
 static void mlx5e_close_sq(struct mlx5e_sq *sq)
 {
+	int tout = 0;
+	int err;
+
 	if (sq->txq) {
 		clear_bit(MLX5E_SQ_STATE_WAKE_TXQ_ENABLE, &sq->state);
 		/* prevent netif_tx_wake_queue */
@@ -792,15 +835,24 @@ static void mlx5e_close_sq(struct mlx5e_sq *sq)
 		if (mlx5e_sq_has_room_for(sq, 1))
 			mlx5e_send_nop(sq, true);
 
-		mlx5e_modify_sq(sq, MLX5_SQC_STATE_RDY, MLX5_SQC_STATE_ERR);
+		err = mlx5e_modify_sq(sq, MLX5_SQC_STATE_RDY,
+				      MLX5_SQC_STATE_ERR);
+		if (err)
+			set_bit(MLX5E_SQ_STATE_TX_TIMEOUT, &sq->state);
 	}
 
-	while (sq->cc != sq->pc) /* wait till sq is empty */
-		msleep(20);
+	/* wait till sq is empty, unless a TX timeout occurred on this SQ */
+	while (sq->cc != sq->pc &&
+	       !test_bit(MLX5E_SQ_STATE_TX_TIMEOUT, &sq->state)) {
+		msleep(MLX5_EN_QP_FLUSH_MSLEEP_QUANT);
+		if (tout++ > MLX5_EN_QP_FLUSH_MAX_ITER)
+			set_bit(MLX5E_SQ_STATE_TX_TIMEOUT, &sq->state);
+	}
 
 	/* avoid destroying sq before mlx5e_poll_tx_cq() is done with it */
 	napi_synchronize(&sq->channel->napi);
 
+	mlx5e_free_tx_descs(sq);
 	mlx5e_disable_sq(sq);
 	mlx5e_destroy_sq(sq);
 }
@@ -1658,8 +1710,11 @@ static void mlx5e_netdev_set_tcs(struct net_device *netdev)
 
 	netdev_set_num_tc(netdev, ntc);
 
+	/* Map netdev TCs to offset 0
+	 * We have our own UP to TXQ mapping for QoS
+	 */
 	for (tc = 0; tc < ntc; tc++)
-		netdev_set_tc_queue(netdev, tc, nch, tc * nch);
+		netdev_set_tc_queue(netdev, tc, nch, 0);
 }
 
 int mlx5e_open_locked(struct net_device *netdev)
@@ -2590,6 +2645,29 @@ static netdev_features_t mlx5e_features_check(struct sk_buff *skb,
 	return features;
 }
 
+static void mlx5e_tx_timeout(struct net_device *dev)
+{
+	struct mlx5e_priv *priv = netdev_priv(dev);
+	bool sched_work = false;
+	int i;
+
+	netdev_err(dev, "TX timeout detected\n");
+
+	for (i = 0; i < priv->params.num_channels * priv->params.num_tc; i++) {
+		struct mlx5e_sq *sq = priv->txq_to_sq_map[i];
+
+		if (!netif_tx_queue_stopped(netdev_get_tx_queue(dev, i)))
+			continue;
+		sched_work = true;
+		set_bit(MLX5E_SQ_STATE_TX_TIMEOUT, &sq->state);
+		netdev_err(dev, "TX timeout on queue: %d, SQ: 0x%x, CQ: 0x%x, SQ Cons: 0x%x SQ Prod: 0x%x\n",
+			   i, sq->sqn, sq->cq.mcq.cqn, sq->cc, sq->pc);
+	}
+
+	if (sched_work && test_bit(MLX5E_STATE_OPENED, &priv->state))
+		schedule_work(&priv->tx_timeout_work);
+}
+
 static const struct net_device_ops mlx5e_netdev_ops_basic = {
 	.ndo_open                = mlx5e_open,
 	.ndo_stop                = mlx5e_close,
@@ -2607,6 +2685,7 @@ static const struct net_device_ops mlx5e_netdev_ops_basic = {
 #ifdef CONFIG_RFS_ACCEL
 	.ndo_rx_flow_steer	 = mlx5e_rx_flow_steer,
 #endif
+	.ndo_tx_timeout          = mlx5e_tx_timeout,
 };
 
 static const struct net_device_ops mlx5e_netdev_ops_sriov = {
@@ -2636,6 +2715,7 @@ static const struct net_device_ops mlx5e_netdev_ops_sriov = {
 	.ndo_get_vf_config       = mlx5e_get_vf_config,
 	.ndo_set_vf_link_state   = mlx5e_set_vf_link_state,
 	.ndo_get_vf_stats        = mlx5e_get_vf_stats,
+	.ndo_tx_timeout          = mlx5e_tx_timeout,
 };
 
 static int mlx5e_check_required_hca_cap(struct mlx5_core_dev *mdev)
@@ -2838,6 +2918,7 @@ static void mlx5e_build_netdev_priv(struct mlx5_core_dev *mdev,
 
 	INIT_WORK(&priv->update_carrier_work, mlx5e_update_carrier_work);
 	INIT_WORK(&priv->set_rx_mode_work, mlx5e_set_rx_mode_work);
+	INIT_WORK(&priv->tx_timeout_work, mlx5e_tx_timeout_work);
 	INIT_DELAYED_WORK(&priv->update_stats_work, mlx5e_update_stats_work);
 }
 

drivers/net/ethernet/mellanox/mlx5/core/en_rx.c

@@ -212,6 +212,20 @@ err_free_skb:
 	return -ENOMEM;
 }
 
+void mlx5e_dealloc_rx_wqe(struct mlx5e_rq *rq, u16 ix)
+{
+	struct sk_buff *skb = rq->skb[ix];
+
+	if (skb) {
+		rq->skb[ix] = NULL;
+		dma_unmap_single(rq->pdev,
+				 *((dma_addr_t *)skb->cb),
+				 rq->wqe_sz,
+				 DMA_FROM_DEVICE);
+		dev_kfree_skb(skb);
+	}
+}
+
 static inline int mlx5e_mpwqe_strides_per_page(struct mlx5e_rq *rq)
 {
 	return rq->mpwqe_num_strides >> MLX5_MPWRQ_WQE_PAGE_ORDER;
@@ -574,6 +588,30 @@ int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, struct mlx5e_rx_wqe *wqe, u16 ix)
 	return 0;
 }
 
+void mlx5e_dealloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
+{
+	struct mlx5e_mpw_info *wi = &rq->wqe_info[ix];
+
+	wi->free_wqe(rq, wi);
+}
+
+void mlx5e_free_rx_descs(struct mlx5e_rq *rq)
+{
+	struct mlx5_wq_ll *wq = &rq->wq;
+	struct mlx5e_rx_wqe *wqe;
+	__be16 wqe_ix_be;
+	u16 wqe_ix;
+
+	while (!mlx5_wq_ll_is_empty(wq)) {
+		wqe_ix_be = *wq->tail_next;
+		wqe_ix    = be16_to_cpu(wqe_ix_be);
+		wqe       = mlx5_wq_ll_get_wqe(&rq->wq, wqe_ix);
+		rq->dealloc_wqe(rq, wqe_ix);
+		mlx5_wq_ll_pop(&rq->wq, wqe_ix_be,
+			       &wqe->next.next_wqe_index);
+	}
+}
+
 #define RQ_CANNOT_POST(rq) \
 		(!test_bit(MLX5E_RQ_STATE_POST_WQES_ENABLE, &rq->state) || \
 		 test_bit(MLX5E_RQ_STATE_UMR_WQE_IN_PROGRESS, &rq->state))
@@ -878,6 +916,9 @@ int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget)
 	struct mlx5e_rq *rq = container_of(cq, struct mlx5e_rq, cq);
 	int work_done = 0;
 
+	if (unlikely(test_bit(MLX5E_RQ_STATE_FLUSH_TIMEOUT, &rq->state)))
+		return 0;
+
 	if (cq->decmprs_left)
 		work_done += mlx5e_decompress_cqes_cont(rq, cq, 0, budget);
 

drivers/net/ethernet/mellanox/mlx5/core/en_tx.c

@@ -110,8 +110,20 @@ u16 mlx5e_select_queue(struct net_device *dev, struct sk_buff *skb,
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
 	int channel_ix = fallback(dev, skb);
-	int up = (netdev_get_num_tc(dev) && skb_vlan_tag_present(skb)) ?
-		 skb->vlan_tci >> VLAN_PRIO_SHIFT : 0;
+	int up = 0;
+
+	if (!netdev_get_num_tc(dev))
+		return channel_ix;
+
+	if (skb_vlan_tag_present(skb))
+		up = skb->vlan_tci >> VLAN_PRIO_SHIFT;
+
+	/* channel_ix can be larger than num_channels since
+	 * dev->num_real_tx_queues = num_channels * num_tc
+	 */
+	if (channel_ix >= priv->params.num_channels)
+		channel_ix = reciprocal_scale(channel_ix,
+					      priv->params.num_channels);
 
 	return priv->channeltc_to_txq_map[channel_ix][up];
 }
@@ -123,7 +135,7 @@ static inline u16 mlx5e_get_inline_hdr_size(struct mlx5e_sq *sq,
 	 * headers and occur before the data gather.
 	 * Therefore these headers must be copied into the WQE
 	 */
-#define MLX5E_MIN_INLINE ETH_HLEN
+#define MLX5E_MIN_INLINE (ETH_HLEN + VLAN_HLEN)
 
 	if (bf) {
 		u16 ihs = skb_headlen(skb);
@@ -135,7 +147,7 @@ static inline u16 mlx5e_get_inline_hdr_size(struct mlx5e_sq *sq,
 			return skb_headlen(skb);
 	}
 
-	return MLX5E_MIN_INLINE;
+	return max(skb_network_offset(skb), MLX5E_MIN_INLINE);
 }
 
 static inline void mlx5e_tx_skb_pull_inline(unsigned char **skb_data,
@@ -341,6 +353,35 @@ netdev_tx_t mlx5e_xmit(struct sk_buff *skb, struct net_device *dev)
 	return mlx5e_sq_xmit(sq, skb);
 }
 
+void mlx5e_free_tx_descs(struct mlx5e_sq *sq)
+{
+	struct mlx5e_tx_wqe_info *wi;
+	struct sk_buff *skb;
+	u16 ci;
+	int i;
+
+	while (sq->cc != sq->pc) {
+		ci = sq->cc & sq->wq.sz_m1;
+		skb = sq->skb[ci];
+		wi = &sq->wqe_info[ci];
+
+		if (!skb) { /* nop */
+			sq->cc++;
+			continue;
+		}
+
+		for (i = 0; i < wi->num_dma; i++) {
+			struct mlx5e_sq_dma *dma =
+				mlx5e_dma_get(sq, sq->dma_fifo_cc++);
+
+			mlx5e_tx_dma_unmap(sq->pdev, dma);
+		}
+
+		dev_kfree_skb_any(skb);
+		sq->cc += wi->num_wqebbs;
+	}
+}
+
 bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget)
 {
 	struct mlx5e_sq *sq;
@@ -352,6 +393,9 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget)
 
 	sq = container_of(cq, struct mlx5e_sq, cq);
 
+	if (unlikely(test_bit(MLX5E_SQ_STATE_TX_TIMEOUT, &sq->state)))
+		return false;
+
 	npkts = 0;
 	nbytes = 0;
 

drivers/net/ethernet/mellanox/mlx5/core/health.c

@@ -108,15 +108,21 @@ static int in_fatal(struct mlx5_core_dev *dev)
 
 void mlx5_enter_error_state(struct mlx5_core_dev *dev)
 {
+	mutex_lock(&dev->intf_state_mutex);
 	if (dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR)
-		return;
+		goto unlock;
 
 	mlx5_core_err(dev, "start\n");
-	if (pci_channel_offline(dev->pdev) || in_fatal(dev))
+	if (pci_channel_offline(dev->pdev) || in_fatal(dev)) {
 		dev->state = MLX5_DEVICE_STATE_INTERNAL_ERROR;
+		trigger_cmd_completions(dev);
+	}
 
 	mlx5_core_event(dev, MLX5_DEV_EVENT_SYS_ERROR, 0);
 	mlx5_core_err(dev, "end\n");
+
+unlock:
+	mutex_unlock(&dev->intf_state_mutex);
 }
 
 static void mlx5_handle_bad_state(struct mlx5_core_dev *dev)
@@ -245,7 +251,6 @@ static void poll_health(unsigned long data)
 	u32 count;
 
 	if (dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR) {
-		trigger_cmd_completions(dev);
 		mod_timer(&health->timer, get_next_poll_jiffies());
 		return;
 	}

drivers/net/ethernet/mellanox/mlx5/core/main.c

@@ -1422,46 +1422,31 @@ void mlx5_disable_device(struct mlx5_core_dev *dev)
 	mlx5_pci_err_detected(dev->pdev, 0);
 }
 
-/* wait for the device to show vital signs. For now we check
- * that we can read the device ID and that the health buffer
- * shows a non zero value which is different than 0xffffffff
+/* wait for the device to show vital signs by waiting
+ * for the health counter to start counting.
  */
-static void wait_vital(struct pci_dev *pdev)
+static int wait_vital(struct pci_dev *pdev)
 {
 	struct mlx5_core_dev *dev = pci_get_drvdata(pdev);
 	struct mlx5_core_health *health = &dev->priv.health;
 	const int niter = 100;
+	u32 last_count = 0;
 	u32 count;
-	u16 did;
 	int i;
 
-	/* Wait for firmware to be ready after reset */
-	msleep(1000);
-	for (i = 0; i < niter; i++) {
-		if (pci_read_config_word(pdev, 2, &did)) {
-			dev_warn(&pdev->dev, "failed reading config word\n");
-			break;
-		}
-		if (did == pdev->device) {
-			dev_info(&pdev->dev, "device ID correctly read after %d iterations\n", i);
-			break;
-		}
-		msleep(50);
-	}
-	if (i == niter)
-		dev_warn(&pdev->dev, "%s-%d: could not read device ID\n", __func__, __LINE__);
-
 	for (i = 0; i < niter; i++) {
 		count = ioread32be(health->health_counter);
 		if (count && count != 0xffffffff) {
-			dev_info(&pdev->dev, "Counter value 0x%x after %d iterations\n", count, i);
-			break;
+			if (last_count && last_count != count) {
+				dev_info(&pdev->dev, "Counter value 0x%x after %d iterations\n", count, i);
+				return 0;
+			}
+			last_count = count;
 		}
 		msleep(50);
 	}
 
-	if (i == niter)
-		dev_warn(&pdev->dev, "%s-%d: could not read device ID\n", __func__, __LINE__);
+	return -ETIMEDOUT;
 }
 
 static void mlx5_pci_resume(struct pci_dev *pdev)
@@ -1473,7 +1458,11 @@ static void mlx5_pci_resume(struct pci_dev *pdev)
 	dev_info(&pdev->dev, "%s was called\n", __func__);
 
 	pci_save_state(pdev);
-	wait_vital(pdev);
+	err = wait_vital(pdev);
+	if (err) {
+		dev_err(&pdev->dev, "%s: wait_vital timed out\n", __func__);
+		return;
+	}
 
 	err = mlx5_load_one(dev, priv);
 	if (err)

drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c

@@ -345,7 +345,6 @@ retry:
 			       func_id, npages, err);
 		goto out_4k;
 	}
-	dev->priv.fw_pages += npages;
 
 	err = mlx5_cmd_status_to_err(&out.hdr);
 	if (err) {
@@ -373,6 +372,33 @@ out_free:
 	return err;
 }
 
+static int reclaim_pages_cmd(struct mlx5_core_dev *dev,
+			     struct mlx5_manage_pages_inbox *in, int in_size,
+			     struct mlx5_manage_pages_outbox *out, int out_size)
+{
+	struct fw_page *fwp;
+	struct rb_node *p;
+	u32 npages;
+	u32 i = 0;
+
+	if (dev->state != MLX5_DEVICE_STATE_INTERNAL_ERROR)
+		return mlx5_cmd_exec_check_status(dev, (u32 *)in, in_size,
+						  (u32 *)out, out_size);
+
+	npages = be32_to_cpu(in->num_entries);
+
+	p = rb_first(&dev->priv.page_root);
+	while (p && i < npages) {
+		fwp = rb_entry(p, struct fw_page, rb_node);
+		out->pas[i] = cpu_to_be64(fwp->addr);
+		p = rb_next(p);
+		i++;
+	}
+
+	out->num_entries = cpu_to_be32(i);
+	return 0;
+}
+
 static int reclaim_pages(struct mlx5_core_dev *dev, u32 func_id, int npages,
 			 int *nclaimed)
 {
@@ -398,15 +424,9 @@ static int reclaim_pages(struct mlx5_core_dev *dev, u32 func_id, int npages,
 	in.func_id = cpu_to_be16(func_id);
 	in.num_entries = cpu_to_be32(npages);
 	mlx5_core_dbg(dev, "npages %d, outlen %d\n", npages, outlen);
-	err = mlx5_cmd_exec(dev, &in, sizeof(in), out, outlen);
+	err = reclaim_pages_cmd(dev, &in, sizeof(in), out, outlen);
 	if (err) {
-		mlx5_core_err(dev, "failed reclaiming pages\n");
-		goto out_free;
-	}
-	dev->priv.fw_pages -= npages;
-
-	if (out->hdr.status) {
-		err = mlx5_cmd_status_to_err(&out->hdr);
+		mlx5_core_err(dev, "failed reclaiming pages: err %d\n", err);
 		goto out_free;
 	}
 
@@ -417,13 +437,15 @@ static int reclaim_pages(struct mlx5_core_dev *dev, u32 func_id, int npages,
 		err = -EINVAL;
 		goto out_free;
 	}
-	if (nclaimed)
-		*nclaimed = num_claimed;
 
 	for (i = 0; i < num_claimed; i++) {
 		addr = be64_to_cpu(out->pas[i]);
 		free_4k(dev, addr);
 	}
+
+	if (nclaimed)
+		*nclaimed = num_claimed;
+
 	dev->priv.fw_pages -= num_claimed;
 	if (func_id)
 		dev->priv.vfs_pages -= num_claimed;
@@ -514,14 +536,10 @@ int mlx5_reclaim_startup_pages(struct mlx5_core_dev *dev)
 		p = rb_first(&dev->priv.page_root);
 		if (p) {
 			fwp = rb_entry(p, struct fw_page, rb_node);
-			if (dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR) {
-				free_4k(dev, fwp->addr);
-				nclaimed = 1;
-			} else {
-				err = reclaim_pages(dev, fwp->func_id,
-						    optimal_reclaimed_pages(),
-						    &nclaimed);
-			}
+			err = reclaim_pages(dev, fwp->func_id,
+					    optimal_reclaimed_pages(),
+					    &nclaimed);
+
 			if (err) {
 				mlx5_core_warn(dev, "failed reclaiming pages (%d)\n",
 					       err);
@@ -536,6 +554,13 @@ int mlx5_reclaim_startup_pages(struct mlx5_core_dev *dev)
 		}
 	} while (p);
 
+	WARN(dev->priv.fw_pages,
+	     "FW pages counter is %d after reclaiming all pages\n",
+	     dev->priv.fw_pages);
+	WARN(dev->priv.vfs_pages,
+	     "VFs FW pages counter is %d after reclaiming all pages\n",
+	     dev->priv.vfs_pages);
+
 	return 0;
 }
 

drivers/net/ethernet/mellanox/mlx5/core/vport.c

@@ -513,7 +513,6 @@ int mlx5_modify_nic_vport_node_guid(struct mlx5_core_dev *mdev,
 {
 	int inlen = MLX5_ST_SZ_BYTES(modify_nic_vport_context_in);
 	void *nic_vport_context;
-	u8 *guid;
 	void *in;
 	int err;
 
@@ -535,8 +534,6 @@ int mlx5_modify_nic_vport_node_guid(struct mlx5_core_dev *mdev,
 
 	nic_vport_context = MLX5_ADDR_OF(modify_nic_vport_context_in,
 					 in, nic_vport_context);
-	guid = MLX5_ADDR_OF(nic_vport_context, nic_vport_context,
-			    node_guid);
 	MLX5_SET64(nic_vport_context, nic_vport_context, node_guid, node_guid);
 
 	err = mlx5_modify_nic_vport_context(mdev, in, inlen);

drivers/net/ethernet/microchip/enc28j60.c

@@ -1151,7 +1151,8 @@ static void enc28j60_irq_work_handler(struct work_struct *work)
 			enc28j60_phy_read(priv, PHIR);
 		}
 		/* TX complete handler */
-		if ((intflags & EIR_TXIF) != 0) {
+		if (((intflags & EIR_TXIF) != 0) &&
+		    ((intflags & EIR_TXERIF) == 0)) {
 			bool err = false;
 			loop++;
 			if (netif_msg_intr(priv))
@@ -1203,7 +1204,7 @@ static void enc28j60_irq_work_handler(struct work_struct *work)
 					enc28j60_tx_clear(ndev, true);
 			} else
 				enc28j60_tx_clear(ndev, true);
-			locked_reg_bfclr(priv, EIR, EIR_TXERIF);
+			locked_reg_bfclr(priv, EIR, EIR_TXERIF | EIR_TXIF);
 		}
 		/* RX Error handler */
 		if ((intflags & EIR_RXERIF) != 0) {
@@ -1238,6 +1239,8 @@ static void enc28j60_irq_work_handler(struct work_struct *work)
  */
 static void enc28j60_hw_tx(struct enc28j60_net *priv)
 {
+	BUG_ON(!priv->tx_skb);
+
 	if (netif_msg_tx_queued(priv))
 		printk(KERN_DEBUG DRV_NAME
 			": Tx Packet Len:%d\n", priv->tx_skb->len);

drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c

@@ -772,6 +772,8 @@ netdev_tx_t qlcnic_xmit_frame(struct sk_buff *skb, struct net_device *netdev)
 	tx_ring->tx_stats.tx_bytes += skb->len;
 	tx_ring->tx_stats.xmit_called++;
 
+	/* Ensure writes are complete before HW fetches Tx descriptors */
+	wmb();
 	qlcnic_update_cmd_producer(tx_ring);
 
 	return NETDEV_TX_OK;

drivers/net/ethernet/stmicro/stmmac/stmmac_main.c

@@ -2804,7 +2804,7 @@ static irqreturn_t stmmac_interrupt(int irq, void *dev_id)
 				priv->tx_path_in_lpi_mode = true;
 			if (status & CORE_IRQ_TX_PATH_EXIT_LPI_MODE)
 				priv->tx_path_in_lpi_mode = false;
-			if (status & CORE_IRQ_MTL_RX_OVERFLOW)
+			if (status & CORE_IRQ_MTL_RX_OVERFLOW && priv->hw->dma->set_rx_tail_ptr)
 				priv->hw->dma->set_rx_tail_ptr(priv->ioaddr,
 							priv->rx_tail_addr,
 							STMMAC_CHAN0);

drivers/net/geneve.c

@@ -1072,12 +1072,17 @@ static netdev_tx_t geneve_xmit(struct sk_buff *skb, struct net_device *dev)
 
 static int __geneve_change_mtu(struct net_device *dev, int new_mtu, bool strict)
 {
+	struct geneve_dev *geneve = netdev_priv(dev);
 	/* The max_mtu calculation does not take account of GENEVE
 	 * options, to avoid excluding potentially valid
 	 * configurations.
 	 */
-	int max_mtu = IP_MAX_MTU - GENEVE_BASE_HLEN - sizeof(struct iphdr)
-		- dev->hard_header_len;
+	int max_mtu = IP_MAX_MTU - GENEVE_BASE_HLEN - dev->hard_header_len;
+
+	if (geneve->remote.sa.sa_family == AF_INET6)
+		max_mtu -= sizeof(struct ipv6hdr);
+	else
+		max_mtu -= sizeof(struct iphdr);
 
 	if (new_mtu < 68)
 		return -EINVAL;

drivers/net/macsec.c

@@ -2640,6 +2640,7 @@ static netdev_tx_t macsec_start_xmit(struct sk_buff *skb,
 		u64_stats_update_begin(&secy_stats->syncp);
 		secy_stats->stats.OutPktsUntagged++;
 		u64_stats_update_end(&secy_stats->syncp);
+		skb->dev = macsec->real_dev;
 		len = skb->len;
 		ret = dev_queue_xmit(skb);
 		count_tx(dev, ret, len);

drivers/net/phy/dp83867.c

@@ -57,6 +57,7 @@
 
 /* PHY CTRL bits */
 #define DP83867_PHYCR_FIFO_DEPTH_SHIFT		14
+#define DP83867_PHYCR_FIFO_DEPTH_MASK		(3 << 14)
 
 /* RGMIIDCTL bits */
 #define DP83867_RGMII_TX_CLK_DELAY_SHIFT	4
@@ -133,8 +134,8 @@ static int dp83867_of_init(struct phy_device *phydev)
 static int dp83867_config_init(struct phy_device *phydev)
 {
 	struct dp83867_private *dp83867;
-	int ret;
-	u16 val, delay;
+	int ret, val;
+	u16 delay;
 
 	if (!phydev->priv) {
 		dp83867 = devm_kzalloc(&phydev->mdio.dev, sizeof(*dp83867),
@@ -151,8 +152,12 @@ static int dp83867_config_init(struct phy_device *phydev)
 	}
 
 	if (phy_interface_is_rgmii(phydev)) {
-		ret = phy_write(phydev, MII_DP83867_PHYCTRL,
-			(dp83867->fifo_depth << DP83867_PHYCR_FIFO_DEPTH_SHIFT));
+		val = phy_read(phydev, MII_DP83867_PHYCTRL);
+		if (val < 0)
+			return val;
+		val &= ~DP83867_PHYCR_FIFO_DEPTH_MASK;
+		val |= (dp83867->fifo_depth << DP83867_PHYCR_FIFO_DEPTH_SHIFT);
+		ret = phy_write(phydev, MII_DP83867_PHYCTRL, val);
 		if (ret)
 			return ret;
 	}

drivers/net/usb/cdc_ncm.c

@@ -854,6 +854,13 @@ int cdc_ncm_bind_common(struct usbnet *dev, struct usb_interface *intf, u8 data_
 	if (cdc_ncm_init(dev))
 		goto error2;
 
+	/* Some firmwares need a pause here or they will silently fail
+	 * to set up the interface properly.  This value was decided
+	 * empirically on a Sierra Wireless MC7455 running 02.08.02.00
+	 * firmware.
+	 */
+	usleep_range(10000, 20000);
+
 	/* configure data interface */
 	temp = usb_set_interface(dev->udev, iface_no, data_altsetting);
 	if (temp) {

drivers/net/usb/r8152.c

@@ -31,7 +31,7 @@
 #define NETNEXT_VERSION		"08"
 
 /* Information for net */
-#define NET_VERSION		"4"
+#define NET_VERSION		"5"
 
 #define DRIVER_VERSION		"v1." NETNEXT_VERSION "." NET_VERSION
 #define DRIVER_AUTHOR "Realtek linux nic maintainers <nic_swsd@realtek.com>"
@@ -624,6 +624,7 @@ struct r8152 {
 		int (*eee_get)(struct r8152 *, struct ethtool_eee *);
 		int (*eee_set)(struct r8152 *, struct ethtool_eee *);
 		bool (*in_nway)(struct r8152 *);
+		void (*autosuspend_en)(struct r8152 *tp, bool enable);
 	} rtl_ops;
 
 	int intr_interval;
@@ -2408,9 +2409,6 @@ static void rtl_runtime_suspend_enable(struct r8152 *tp, bool enable)
 	if (enable) {
 		u32 ocp_data;
 
-		r8153_u1u2en(tp, false);
-		r8153_u2p3en(tp, false);
-
 		__rtl_set_wol(tp, WAKE_ANY);
 
 		ocp_write_byte(tp, MCU_TYPE_PLA, PLA_CRWECR, CRWECR_CONFIG);
@@ -2421,7 +2419,28 @@ static void rtl_runtime_suspend_enable(struct r8152 *tp, bool enable)
 
 		ocp_write_byte(tp, MCU_TYPE_PLA, PLA_CRWECR, CRWECR_NORAML);
 	} else {
+		u32 ocp_data;
+
 		__rtl_set_wol(tp, tp->saved_wolopts);
+
+		ocp_write_byte(tp, MCU_TYPE_PLA, PLA_CRWECR, CRWECR_CONFIG);
+
+		ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_CONFIG34);
+		ocp_data &= ~LINK_OFF_WAKE_EN;
+		ocp_write_word(tp, MCU_TYPE_PLA, PLA_CONFIG34, ocp_data);
+
+		ocp_write_byte(tp, MCU_TYPE_PLA, PLA_CRWECR, CRWECR_NORAML);
+	}
+}
+
+static void rtl8153_runtime_enable(struct r8152 *tp, bool enable)
+{
+	rtl_runtime_suspend_enable(tp, enable);
+
+	if (enable) {
+		r8153_u1u2en(tp, false);
+		r8153_u2p3en(tp, false);
+	} else {
 		r8153_u2p3en(tp, true);
 		r8153_u1u2en(tp, true);
 	}
@@ -3512,7 +3531,7 @@ static int rtl8152_suspend(struct usb_interface *intf, pm_message_t message)
 		napi_disable(&tp->napi);
 		if (test_bit(SELECTIVE_SUSPEND, &tp->flags)) {
 			rtl_stop_rx(tp);
-			rtl_runtime_suspend_enable(tp, true);
+			tp->rtl_ops.autosuspend_en(tp, true);
 		} else {
 			cancel_delayed_work_sync(&tp->schedule);
 			tp->rtl_ops.down(tp);
@@ -3538,7 +3557,7 @@ static int rtl8152_resume(struct usb_interface *intf)
 
 	if (netif_running(tp->netdev) && tp->netdev->flags & IFF_UP) {
 		if (test_bit(SELECTIVE_SUSPEND, &tp->flags)) {
-			rtl_runtime_suspend_enable(tp, false);
+			tp->rtl_ops.autosuspend_en(tp, false);
 			clear_bit(SELECTIVE_SUSPEND, &tp->flags);
 			napi_disable(&tp->napi);
 			set_bit(WORK_ENABLE, &tp->flags);
@@ -3557,7 +3576,7 @@ static int rtl8152_resume(struct usb_interface *intf)
 		usb_submit_urb(tp->intr_urb, GFP_KERNEL);
 	} else if (test_bit(SELECTIVE_SUSPEND, &tp->flags)) {
 		if (tp->netdev->flags & IFF_UP)
-			rtl_runtime_suspend_enable(tp, false);
+			tp->rtl_ops.autosuspend_en(tp, false);
 		clear_bit(SELECTIVE_SUSPEND, &tp->flags);
 	}
 
@@ -4137,6 +4156,7 @@ static int rtl_ops_init(struct r8152 *tp)
 		ops->eee_get		= r8152_get_eee;
 		ops->eee_set		= r8152_set_eee;
 		ops->in_nway		= rtl8152_in_nway;
+		ops->autosuspend_en	= rtl_runtime_suspend_enable;
 		break;
 
 	case RTL_VER_03:
@@ -4152,6 +4172,7 @@ static int rtl_ops_init(struct r8152 *tp)
 		ops->eee_get		= r8153_get_eee;
 		ops->eee_set		= r8153_set_eee;
 		ops->in_nway		= rtl8153_in_nway;
+		ops->autosuspend_en	= rtl8153_runtime_enable;
 		break;
 
 	default:

drivers/net/usb/usbnet.c

@@ -395,8 +395,11 @@ int usbnet_change_mtu (struct net_device *net, int new_mtu)
 	dev->hard_mtu = net->mtu + net->hard_header_len;
 	if (dev->rx_urb_size == old_hard_mtu) {
 		dev->rx_urb_size = dev->hard_mtu;
-		if (dev->rx_urb_size > old_rx_urb_size)
+		if (dev->rx_urb_size > old_rx_urb_size) {
+			usbnet_pause_rx(dev);
 			usbnet_unlink_rx_urbs(dev);
+			usbnet_resume_rx(dev);
+		}
 	}
 
 	/* max qlen depend on hard_mtu and rx_urb_size */
@@ -1508,8 +1511,9 @@ static void usbnet_bh (unsigned long param)
 	} else if (netif_running (dev->net) &&
 		   netif_device_present (dev->net) &&
 		   netif_carrier_ok(dev->net) &&
-		   !timer_pending (&dev->delay) &&
-		   !test_bit (EVENT_RX_HALT, &dev->flags)) {
+		   !timer_pending(&dev->delay) &&
+		   !test_bit(EVENT_RX_PAUSED, &dev->flags) &&
+		   !test_bit(EVENT_RX_HALT, &dev->flags)) {
 		int	temp = dev->rxq.qlen;
 
 		if (temp < RX_QLEN(dev)) {

drivers/platform/chrome/cros_ec_dev.c

@@ -151,13 +151,19 @@ static long ec_device_ioctl_xcmd(struct cros_ec_dev *ec, void __user *arg)
 		goto exit;
 	}
 
+	if (u_cmd.outsize != s_cmd->outsize ||
+	    u_cmd.insize != s_cmd->insize) {
+		ret = -EINVAL;
+		goto exit;
+	}
+
 	s_cmd->command += ec->cmd_offset;
 	ret = cros_ec_cmd_xfer(ec->ec_dev, s_cmd);
 	/* Only copy data to userland if data was received. */
 	if (ret < 0)
 		goto exit;
 
-	if (copy_to_user(arg, s_cmd, sizeof(*s_cmd) + u_cmd.insize))
+	if (copy_to_user(arg, s_cmd, sizeof(*s_cmd) + s_cmd->insize))
 		ret = -EFAULT;
 exit:
 	kfree(s_cmd);

drivers/s390/net/qeth_l2_main.c

@@ -1051,6 +1051,7 @@ static void qeth_l2_remove_device(struct ccwgroup_device *cgdev)
 		qeth_l2_set_offline(cgdev);
 
 	if (card->dev) {
+		netif_napi_del(&card->napi);
 		unregister_netdev(card->dev);
 		card->dev = NULL;
 	}

drivers/s390/net/qeth_l3_main.c

@@ -3226,6 +3226,7 @@ static void qeth_l3_remove_device(struct ccwgroup_device *cgdev)
 		qeth_l3_set_offline(cgdev);
 
 	if (card->dev) {
+		netif_napi_del(&card->napi);
 		unregister_netdev(card->dev);
 		card->dev = NULL;
 	}

drivers/scsi/ipr.c

@@ -10093,6 +10093,7 @@ static int ipr_probe_ioa(struct pci_dev *pdev,
 		ioa_cfg->intr_flag = IPR_USE_MSI;
 	else {
 		ioa_cfg->intr_flag = IPR_USE_LSI;
+		ioa_cfg->clear_isr = 1;
 		ioa_cfg->nvectors = 1;
 		dev_info(&pdev->dev, "Cannot enable MSI.\n");
 	}

drivers/scsi/qla2xxx/qla_isr.c

@@ -2548,7 +2548,7 @@ void qla24xx_process_response_queue(struct scsi_qla_host *vha,
 	if (!vha->flags.online)
 		return;
 
-	if (rsp->msix->cpuid != smp_processor_id()) {
+	if (rsp->msix && rsp->msix->cpuid != smp_processor_id()) {
 		/* if kernel does not notify qla of IRQ's CPU change,
 		 * then set it here.
 		 */

drivers/scsi/scsi_devinfo.c

@@ -429,7 +429,7 @@ static struct scsi_dev_info_list *scsi_dev_info_list_find(const char *vendor,
 	 * here, and we don't know what device it is
 	 * trying to work with, leave it as-is.
 	 */
-	vmax = 8;	/* max length of vendor */
+	vmax = sizeof(devinfo->vendor);
 	vskip = vendor;
 	while (vmax > 0 && *vskip == ' ') {
 		vmax--;
@@ -439,7 +439,7 @@ static struct scsi_dev_info_list *scsi_dev_info_list_find(const char *vendor,
 	while (vmax > 0 && vskip[vmax - 1] == ' ')
 		--vmax;
 
-	mmax = 16;	/* max length of model */
+	mmax = sizeof(devinfo->model);
 	mskip = model;
 	while (mmax > 0 && *mskip == ' ') {
 		mmax--;
@@ -455,10 +455,12 @@ static struct scsi_dev_info_list *scsi_dev_info_list_find(const char *vendor,
 			 * Behave like the older version of get_device_flags.
 			 */
 			if (memcmp(devinfo->vendor, vskip, vmax) ||
-					devinfo->vendor[vmax])
+					(vmax < sizeof(devinfo->vendor) &&
+						devinfo->vendor[vmax]))
 				continue;
 			if (memcmp(devinfo->model, mskip, mmax) ||
-					devinfo->model[mmax])
+					(mmax < sizeof(devinfo->model) &&
+						devinfo->model[mmax]))
 				continue;
 			return devinfo;
 		} else {

drivers/xen/xen-acpi-processor.c

@@ -423,36 +423,7 @@ upload:
 
 	return 0;
 }
-static int __init check_prereq(void)
-{
-	struct cpuinfo_x86 *c = &cpu_data(0);
-
-	if (!xen_initial_domain())
-		return -ENODEV;
-
-	if (!acpi_gbl_FADT.smi_command)
-		return -ENODEV;
-
-	if (c->x86_vendor == X86_VENDOR_INTEL) {
-		if (!cpu_has(c, X86_FEATURE_EST))
-			return -ENODEV;
 
-		return 0;
-	}
-	if (c->x86_vendor == X86_VENDOR_AMD) {
-		/* Copied from powernow-k8.h, can't include ../cpufreq/powernow
-		 * as we get compile warnings for the static functions.
-		 */
-#define CPUID_FREQ_VOLT_CAPABILITIES    0x80000007
-#define USE_HW_PSTATE                   0x00000080
-		u32 eax, ebx, ecx, edx;
-		cpuid(CPUID_FREQ_VOLT_CAPABILITIES, &eax, &ebx, &ecx, &edx);
-		if ((edx & USE_HW_PSTATE) != USE_HW_PSTATE)
-			return -ENODEV;
-		return 0;
-	}
-	return -ENODEV;
-}
 /* acpi_perf_data is a pointer to percpu data. */
 static struct acpi_processor_performance __percpu *acpi_perf_data;
 
@@ -509,10 +480,10 @@ struct notifier_block xen_acpi_processor_resume_nb = {
 static int __init xen_acpi_processor_init(void)
 {
 	unsigned int i;
-	int rc = check_prereq();
+	int rc;
 
-	if (rc)
-		return rc;
+	if (!xen_initial_domain())
+		return -ENODEV;
 
 	nr_acpi_bits = get_max_acpi_id() + 1;
 	acpi_ids_done = kcalloc(BITS_TO_LONGS(nr_acpi_bits), sizeof(unsigned long), GFP_KERNEL);

drivers/xen/xenbus/xenbus_dev_frontend.c

@@ -316,11 +316,18 @@ static int xenbus_write_transaction(unsigned msg_type,
 			rc = -ENOMEM;
 			goto out;
 		}
+	} else {
+		list_for_each_entry(trans, &u->transactions, list)
+			if (trans->handle.id == u->u.msg.tx_id)
+				break;
+		if (&trans->list == &u->transactions)
+			return -ESRCH;
 	}
 
 	reply = xenbus_dev_request_and_reply(&u->u.msg);
 	if (IS_ERR(reply)) {
-		kfree(trans);
+		if (msg_type == XS_TRANSACTION_START)
+			kfree(trans);
 		rc = PTR_ERR(reply);
 		goto out;
 	}
@@ -333,12 +340,7 @@ static int xenbus_write_transaction(unsigned msg_type,
 			list_add(&trans->list, &u->transactions);
 		}
 	} else if (u->u.msg.type == XS_TRANSACTION_END) {
-		list_for_each_entry(trans, &u->transactions, list)
-			if (trans->handle.id == u->u.msg.tx_id)
-				break;
-		BUG_ON(&trans->list == &u->transactions);
 		list_del(&trans->list);
-
 		kfree(trans);
 	}
 

drivers/xen/xenbus/xenbus_xs.c

@@ -232,10 +232,10 @@ static void transaction_resume(void)
 void *xenbus_dev_request_and_reply(struct xsd_sockmsg *msg)
 {
 	void *ret;
-	struct xsd_sockmsg req_msg = *msg;
+	enum xsd_sockmsg_type type = msg->type;
 	int err;
 
-	if (req_msg.type == XS_TRANSACTION_START)
+	if (type == XS_TRANSACTION_START)
 		transaction_start();
 
 	mutex_lock(&xs_state.request_mutex);
@@ -249,12 +249,8 @@ void *xenbus_dev_request_and_reply(struct xsd_sockmsg *msg)
 
 	mutex_unlock(&xs_state.request_mutex);
 
-	if (IS_ERR(ret))
-		return ret;
-
 	if ((msg->type == XS_TRANSACTION_END) ||
-	    ((req_msg.type == XS_TRANSACTION_START) &&
-	     (msg->type == XS_ERROR)))
+	    ((type == XS_TRANSACTION_START) && (msg->type == XS_ERROR)))
 		transaction_end();
 
 	return ret;

fs/configfs/file.c

@@ -357,8 +357,6 @@ configfs_write_bin_file(struct file *file, const char __user *buf,
 
 	len = simple_write_to_buffer(buffer->bin_buffer,
 			buffer->bin_buffer_size, ppos, buf, count);
-	if (len > 0)
-		*ppos += len;
 out:
 	mutex_unlock(&buffer->mutex);
 	return len;

fs/ecryptfs/crypto.c

@@ -45,7 +45,7 @@
  * ecryptfs_to_hex
  * @dst: Buffer to take hex character representation of contents of
  *       src; must be at least of size (src_size * 2)
- * @src: Buffer to be converted to a hex string respresentation
+ * @src: Buffer to be converted to a hex string representation
  * @src_size: number of bytes to convert
  */
 void ecryptfs_to_hex(char *dst, char *src, size_t src_size)
@@ -60,7 +60,7 @@ void ecryptfs_to_hex(char *dst, char *src, size_t src_size)
  * ecryptfs_from_hex
  * @dst: Buffer to take the bytes from src hex; must be at least of
  *       size (src_size / 2)
- * @src: Buffer to be converted from a hex string respresentation to raw value
+ * @src: Buffer to be converted from a hex string representation to raw value
  * @dst_size: size of dst buffer, or number of hex characters pairs to convert
  */
 void ecryptfs_from_hex(char *dst, char *src, int dst_size)
@@ -953,7 +953,7 @@ struct ecryptfs_cipher_code_str_map_elem {
 };
 
 /* Add support for additional ciphers by adding elements here. The
- * cipher_code is whatever OpenPGP applicatoins use to identify the
+ * cipher_code is whatever OpenPGP applications use to identify the
  * ciphers. List in order of probability. */
 static struct ecryptfs_cipher_code_str_map_elem
 ecryptfs_cipher_code_str_map[] = {
@@ -1410,7 +1410,7 @@ int ecryptfs_read_and_validate_xattr_region(struct dentry *dentry,
  *
  * Common entry point for reading file metadata. From here, we could
  * retrieve the header information from the header region of the file,
- * the xattr region of the file, or some other repostory that is
+ * the xattr region of the file, or some other repository that is
  * stored separately from the file itself. The current implementation
  * supports retrieving the metadata information from the file contents
  * and from the xattr region.

fs/ecryptfs/file.c

@@ -169,9 +169,22 @@ out:
 	return rc;
 }
 
+static int ecryptfs_mmap(struct file *file, struct vm_area_struct *vma)
+{
+	struct file *lower_file = ecryptfs_file_to_lower(file);
+	/*
+	 * Don't allow mmap on top of file systems that don't support it
+	 * natively.  If FILESYSTEM_MAX_STACK_DEPTH > 2 or ecryptfs
+	 * allows recursive mounting, this will need to be extended.
+	 */
+	if (!lower_file->f_op->mmap)
+		return -ENODEV;
+	return generic_file_mmap(file, vma);
+}
+
 /**
  * ecryptfs_open
- * @inode: inode speciying file to open
+ * @inode: inode specifying file to open
  * @file: Structure to return filled in
  *
  * Opens the file specified by inode.
@@ -240,7 +253,7 @@ out:
 
 /**
  * ecryptfs_dir_open
- * @inode: inode speciying file to open
+ * @inode: inode specifying file to open
  * @file: Structure to return filled in
  *
  * Opens the file specified by inode.
@@ -403,7 +416,7 @@ const struct file_operations ecryptfs_main_fops = {
 #ifdef CONFIG_COMPAT
 	.compat_ioctl = ecryptfs_compat_ioctl,
 #endif
-	.mmap = generic_file_mmap,
+	.mmap = ecryptfs_mmap,
 	.open = ecryptfs_open,
 	.flush = ecryptfs_flush,
 	.release = ecryptfs_release,

fs/ecryptfs/kthread.c

@@ -25,7 +25,6 @@
 #include <linux/slab.h>
 #include <linux/wait.h>
 #include <linux/mount.h>
-#include <linux/file.h>
 #include "ecryptfs_kernel.h"
 
 struct ecryptfs_open_req {
@@ -148,7 +147,7 @@ int ecryptfs_privileged_open(struct file **lower_file,
 	flags |= IS_RDONLY(d_inode(lower_dentry)) ? O_RDONLY : O_RDWR;
 	(*lower_file) = dentry_open(&req.path, flags, cred);
 	if (!IS_ERR(*lower_file))
-		goto have_file;
+		goto out;
 	if ((flags & O_ACCMODE) == O_RDONLY) {
 		rc = PTR_ERR((*lower_file));
 		goto out;
@@ -166,16 +165,8 @@ int ecryptfs_privileged_open(struct file **lower_file,
 	mutex_unlock(&ecryptfs_kthread_ctl.mux);
 	wake_up(&ecryptfs_kthread_ctl.wait);
 	wait_for_completion(&req.done);
-	if (IS_ERR(*lower_file)) {
+	if (IS_ERR(*lower_file))
 		rc = PTR_ERR(*lower_file);
-		goto out;
-	}
-have_file:
-	if ((*lower_file)->f_op->mmap == NULL) {
-		fput(*lower_file);
-		*lower_file = NULL;
-		rc = -EMEDIUMTYPE;
-	}
 out:
 	return rc;
 }

fs/ecryptfs/main.c

@@ -738,8 +738,7 @@ static void ecryptfs_free_kmem_caches(void)
 		struct ecryptfs_cache_info *info;
 
 		info = &ecryptfs_cache_infos[i];
-		if (*(info->cache))
-			kmem_cache_destroy(*(info->cache));
+		kmem_cache_destroy(*(info->cache));
 	}
 }
 

fs/fs-writeback.c

@@ -483,9 +483,9 @@ static void inode_switch_wbs(struct inode *inode, int new_wb_id)
 		goto out_free;
 	}
 	inode->i_state |= I_WB_SWITCH;
+	__iget(inode);
 	spin_unlock(&inode->i_lock);
 
-	ihold(inode);
 	isw->inode = inode;
 
 	atomic_inc(&isw_nr_in_flight);

include/acpi/acpi_drivers.h

@@ -78,6 +78,7 @@
 
 /* ACPI PCI Interrupt Link (pci_link.c) */
 
+int acpi_irq_penalty_init(void);
 int acpi_pci_link_allocate_irq(acpi_handle handle, int index, int *triggering,
 			       int *polarity, char **name);
 int acpi_pci_link_free_irq(acpi_handle handle);

include/linux/mlx5/driver.h

@@ -629,6 +629,7 @@ struct mlx5_cmd_work_ent {
 	void		       *uout;
 	int			uout_size;
 	mlx5_cmd_cbk_t		callback;
+	struct delayed_work	cb_timeout_work;
 	void		       *context;
 	int			idx;
 	struct completion	done;

include/linux/skbuff.h

@@ -1062,6 +1062,7 @@ __skb_set_sw_hash(struct sk_buff *skb, __u32 hash, bool is_l4)
 }
 
 void __skb_get_hash(struct sk_buff *skb);
+u32 __skb_get_hash_symmetric(struct sk_buff *skb);
 u32 skb_get_poff(const struct sk_buff *skb);
 u32 __skb_get_poff(const struct sk_buff *skb, void *data,
 		   const struct flow_keys *keys, int hlen);
@@ -2869,6 +2870,25 @@ static inline void skb_postpush_rcsum(struct sk_buff *skb,
 		skb->csum = csum_partial(start, len, skb->csum);
 }
 
+/**
+ *	skb_push_rcsum - push skb and update receive checksum
+ *	@skb: buffer to update
+ *	@len: length of data pulled
+ *
+ *	This function performs an skb_push on the packet and updates
+ *	the CHECKSUM_COMPLETE checksum.  It should be used on
+ *	receive path processing instead of skb_push unless you know
+ *	that the checksum difference is zero (e.g., a valid IP header)
+ *	or you are setting ip_summed to CHECKSUM_NONE.
+ */
+static inline unsigned char *skb_push_rcsum(struct sk_buff *skb,
+					    unsigned int len)
+{
+	skb_push(skb, len);
+	skb_postpush_rcsum(skb, skb->data, len);
+	return skb->data;
+}
+
 /**
  *	pskb_trim_rcsum - trim received skb and update checksum
  *	@skb: buffer to trim

include/net/bonding.h

@@ -34,6 +34,9 @@
 
 #define BOND_DEFAULT_MIIMON	100
 
+#ifndef __long_aligned
+#define __long_aligned __attribute__((aligned((sizeof(long)))))
+#endif
 /*
  * Less bad way to call ioctl from within the kernel; this needs to be
  * done some other way to get the call out of interrupt context.
@@ -138,7 +141,9 @@ struct bond_params {
 	struct reciprocal_value reciprocal_packets_per_slave;
 	u16 ad_actor_sys_prio;
 	u16 ad_user_port_key;
-	u8 ad_actor_system[ETH_ALEN];
+
+	/* 2 bytes of padding : see ether_addr_equal_64bits() */
+	u8 ad_actor_system[ETH_ALEN + 2];
 };
 
 struct bond_parm_tbl {

include/net/ip.h

@@ -313,10 +313,9 @@ static inline unsigned int ip_dst_mtu_maybe_forward(const struct dst_entry *dst,
 	return min(dst->dev->mtu, IP_MAX_MTU);
 }
 
-static inline unsigned int ip_skb_dst_mtu(const struct sk_buff *skb)
+static inline unsigned int ip_skb_dst_mtu(struct sock *sk,
+					  const struct sk_buff *skb)
 {
-	struct sock *sk = skb->sk;
-
 	if (!sk || !sk_fullsock(sk) || ip_sk_use_pmtu(sk)) {
 		bool forwarding = IPCB(skb)->flags & IPSKB_FORWARDED;
 

init/Kconfig

@@ -1458,6 +1458,7 @@ config KALLSYMS_ALL
 
 config KALLSYMS_ABSOLUTE_PERCPU
 	bool
+	depends on KALLSYMS
 	default X86_64 && SMP
 
 config KALLSYMS_BASE_RELATIVE

kernel/events/core.c

@@ -1678,12 +1678,33 @@ static bool is_orphaned_event(struct perf_event *event)
 	return event->state == PERF_EVENT_STATE_DEAD;
 }
 
-static inline int pmu_filter_match(struct perf_event *event)
+static inline int __pmu_filter_match(struct perf_event *event)
 {
 	struct pmu *pmu = event->pmu;
 	return pmu->filter_match ? pmu->filter_match(event) : 1;
 }
 
+/*
+ * Check whether we should attempt to schedule an event group based on
+ * PMU-specific filtering. An event group can consist of HW and SW events,
+ * potentially with a SW leader, so we must check all the filters, to
+ * determine whether a group is schedulable:
+ */
+static inline int pmu_filter_match(struct perf_event *event)
+{
+	struct perf_event *child;
+
+	if (!__pmu_filter_match(event))
+		return 0;
+
+	list_for_each_entry(child, &event->sibling_list, group_entry) {
+		if (!__pmu_filter_match(child))
+			return 0;
+	}
+
+	return 1;
+}
+
 static inline int
 event_filter_match(struct perf_event *event)
 {

kernel/sched/fair.c

@@ -735,8 +735,6 @@ void post_init_entity_util_avg(struct sched_entity *se)
 	}
 }
 
-static inline unsigned long cfs_rq_runnable_load_avg(struct cfs_rq *cfs_rq);
-static inline unsigned long cfs_rq_load_avg(struct cfs_rq *cfs_rq);
 #else
 void init_entity_runnable_average(struct sched_entity *se)
 {
@@ -2499,28 +2497,22 @@ account_entity_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se)
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
 # ifdef CONFIG_SMP
-static inline long calc_tg_weight(struct task_group *tg, struct cfs_rq *cfs_rq)
+static long calc_cfs_shares(struct cfs_rq *cfs_rq, struct task_group *tg)
 {
-	long tg_weight;
+	long tg_weight, load, shares;
 
 	/*
-	 * Use this CPU's real-time load instead of the last load contribution
-	 * as the updating of the contribution is delayed, and we will use the
-	 * the real-time load to calc the share. See update_tg_load_avg().
+	 * This really should be: cfs_rq->avg.load_avg, but instead we use
+	 * cfs_rq->load.weight, which is its upper bound. This helps ramp up
+	 * the shares for small weight interactive tasks.
 	 */
-	tg_weight = atomic_long_read(&tg->load_avg);
-	tg_weight -= cfs_rq->tg_load_avg_contrib;
-	tg_weight += cfs_rq->load.weight;
+	load = scale_load_down(cfs_rq->load.weight);
 
-	return tg_weight;
-}
-
-static long calc_cfs_shares(struct cfs_rq *cfs_rq, struct task_group *tg)
-{
-	long tg_weight, load, shares;
+	tg_weight = atomic_long_read(&tg->load_avg);
 
-	tg_weight = calc_tg_weight(tg, cfs_rq);
-	load = cfs_rq->load.weight;
+	/* Ensure tg_weight >= load */
+	tg_weight -= cfs_rq->tg_load_avg_contrib;
+	tg_weight += load;
 
 	shares = (tg->shares * load);
 	if (tg_weight)
@@ -2539,6 +2531,7 @@ static inline long calc_cfs_shares(struct cfs_rq *cfs_rq, struct task_group *tg)
 	return tg->shares;
 }
 # endif /* CONFIG_SMP */
+
 static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se,
 			    unsigned long weight)
 {
@@ -4946,19 +4939,24 @@ static long effective_load(struct task_group *tg, int cpu, long wl, long wg)
 		return wl;
 
 	for_each_sched_entity(se) {
-		long w, W;
+		struct cfs_rq *cfs_rq = se->my_q;
+		long W, w = cfs_rq_load_avg(cfs_rq);
 
-		tg = se->my_q->tg;
+		tg = cfs_rq->tg;
 
 		/*
 		 * W = @wg + \Sum rw_j
 		 */
-		W = wg + calc_tg_weight(tg, se->my_q);
+		W = wg + atomic_long_read(&tg->load_avg);
+
+		/* Ensure \Sum rw_j >= rw_i */
+		W -= cfs_rq->tg_load_avg_contrib;
+		W += w;
 
 		/*
 		 * w = rw_i + @wl
 		 */
-		w = cfs_rq_load_avg(se->my_q) + wl;
+		w += wl;
 
 		/*
 		 * wl = S * s'_i; see (2)

mm/shmem.c

@@ -2225,9 +2225,11 @@ static long shmem_fallocate(struct file *file, int mode, loff_t offset,
 			error = shmem_getpage(inode, index, &page, SGP_FALLOC);
 		if (error) {
 			/* Remove the !PageUptodate pages we added */
-			shmem_undo_range(inode,
-				(loff_t)start << PAGE_SHIFT,
-				((loff_t)index << PAGE_SHIFT) - 1, true);
+			if (index > start) {
+				shmem_undo_range(inode,
+				    (loff_t)start << PAGE_SHIFT,
+				    ((loff_t)index << PAGE_SHIFT) - 1, true);
+			}
 			goto undone;
 		}
 

net/bridge/br_netfilter_hooks.c

@@ -700,7 +700,7 @@ static int
 br_nf_ip_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
 		  int (*output)(struct net *, struct sock *, struct sk_buff *))
 {
-	unsigned int mtu = ip_skb_dst_mtu(skb);
+	unsigned int mtu = ip_skb_dst_mtu(sk, skb);
 	struct iphdr *iph = ip_hdr(skb);
 
 	if (unlikely(((iph->frag_off & htons(IP_DF)) && !skb->ignore_df) ||