Merge tag 'v3.4.103' into kk4.4

This is the 3.4.103 stable release

71 files changed, 695 insertions, 380 deletions

diff --git a/Documentation/x86/x86_64/mm.txt b/Documentation/x86/x86_64/mm.txt
index d6498e3cd71..f33a9369e35 100644
--- a/Documentation/x86/x86_64/mm.txt
+++ b/Documentation/x86/x86_64/mm.txt
@@ -12,6 +12,8 @@ ffffc90000000000 - ffffe8ffffffffff (=45 bits) vmalloc/ioremap space
 ffffe90000000000 - ffffe9ffffffffff (=40 bits) hole
 ffffea0000000000 - ffffeaffffffffff (=40 bits) virtual memory map (1TB)
 ... unused hole ...
+ffffff0000000000 - ffffff7fffffffff (=39 bits) %esp fixup stacks
+... unused hole ...
 ffffffff80000000 - ffffffffa0000000 (=512 MB)  kernel text mapping, from phys 0
 ffffffffa0000000 - fffffffffff00000 (=1536 MB) module mapping space
 
diff --git a/Makefile b/Makefile
index 9de394fcb7b..509f784d0a7 100644
--- a/Makefile
+++ b/Makefile
@@ -1,6 +1,6 @@
 VERSION = 3
 PATCHLEVEL = 4
-SUBLEVEL = 101
+SUBLEVEL = 103
 EXTRAVERSION =
 NAME = Saber-toothed Squirrel
 
diff --git a/arch/arm/mm/idmap.c b/arch/arm/mm/idmap.c
index ab88ed4f8e0..ef8f2df0254 100644
--- a/arch/arm/mm/idmap.c
+++ b/arch/arm/mm/idmap.c
@@ -22,6 +22,13 @@ static void idmap_add_pmd(pud_t *pud, unsigned long addr, unsigned long end,
 			pr_warning("Failed to allocate identity pmd.\n");
 			return;
 		}
+		/*
+		 * Copy the original PMD to ensure that the PMD entries for
+		 * the kernel image are preserved.
+		 */
+		if (!pud_none(*pud))
+			memcpy(pmd, pmd_offset(pud, 0),
+			       PTRS_PER_PMD * sizeof(pmd_t));
 		pud_populate(&init_mm, pud, pmd);
 		pmd += pmd_index(addr);
 	} else
diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h
index 656de8bc0ed..cd24caf1732 100644
--- a/arch/sparc/include/asm/pgtable_64.h
+++ b/arch/sparc/include/asm/pgtable_64.h
@@ -24,7 +24,8 @@
 
 /* The kernel image occupies 0x4000000 to 0x6000000 (4MB --> 96MB).
  * The page copy blockops can use 0x6000000 to 0x8000000.
- * The TSB is mapped in the 0x8000000 to 0xa000000 range.
+ * The 8K TSB is mapped in the 0x8000000 to 0x8400000 range.
+ * The 4M TSB is mapped in the 0x8400000 to 0x8800000 range.
  * The PROM resides in an area spanning 0xf0000000 to 0x100000000.
  * The vmalloc area spans 0x100000000 to 0x200000000.
  * Since modules need to be in the lowest 32-bits of the address space,
@@ -33,7 +34,8 @@
  * 0x400000000.
  */
 #define	TLBTEMP_BASE		_AC(0x0000000006000000,UL)
-#define	TSBMAP_BASE		_AC(0x0000000008000000,UL)
+#define	TSBMAP_8K_BASE		_AC(0x0000000008000000,UL)
+#define	TSBMAP_4M_BASE		_AC(0x0000000008400000,UL)
 #define MODULES_VADDR		_AC(0x0000000010000000,UL)
 #define MODULES_LEN		_AC(0x00000000e0000000,UL)
 #define MODULES_END		_AC(0x00000000f0000000,UL)
diff --git a/arch/sparc/include/asm/tlbflush_64.h b/arch/sparc/include/asm/tlbflush_64.h
index f0d6a9700f4..1a4bb971e06 100644
--- a/arch/sparc/include/asm/tlbflush_64.h
+++ b/arch/sparc/include/asm/tlbflush_64.h
@@ -35,6 +35,8 @@ static inline void flush_tlb_range(struct vm_area_struct *vma,
 {
 }
 
+void flush_tlb_kernel_range(unsigned long start, unsigned long end);
+
 #define __HAVE_ARCH_ENTER_LAZY_MMU_MODE
 
 extern void flush_tlb_pending(void);
@@ -49,11 +51,6 @@ extern void __flush_tlb_kernel_range(unsigned long start, unsigned long end);
 
 #ifndef CONFIG_SMP
 
-#define flush_tlb_kernel_range(start,end) \
-do {	flush_tsb_kernel_range(start,end); \
-	__flush_tlb_kernel_range(start,end); \
-} while (0)
-
 static inline void global_flush_tlb_page(struct mm_struct *mm, unsigned long vaddr)
 {
 	__flush_tlb_page(CTX_HWBITS(mm->context), vaddr);
@@ -64,11 +61,6 @@ static inline void global_flush_tlb_page(struct mm_struct *mm, unsigned long vad
 extern void smp_flush_tlb_kernel_range(unsigned long start, unsigned long end);
 extern void smp_flush_tlb_page(struct mm_struct *mm, unsigned long vaddr);
 
-#define flush_tlb_kernel_range(start, end) \
-do {	flush_tsb_kernel_range(start,end); \
-	smp_flush_tlb_kernel_range(start, end); \
-} while (0)
-
 #define global_flush_tlb_page(mm, vaddr) \
 	smp_flush_tlb_page(mm, vaddr)
 
diff --git a/arch/sparc/kernel/ldc.c b/arch/sparc/kernel/ldc.c
index 435e406fdec..1beaf60a5f7 100644
--- a/arch/sparc/kernel/ldc.c
+++ b/arch/sparc/kernel/ldc.c
@@ -1339,7 +1339,7 @@ int ldc_connect(struct ldc_channel *lp)
 	if (!(lp->flags & LDC_FLAG_ALLOCED_QUEUES) ||
 	    !(lp->flags & LDC_FLAG_REGISTERED_QUEUES) ||
 	    lp->hs_state != LDC_HS_OPEN)
-		err = -EINVAL;
+		err = ((lp->hs_state > LDC_HS_OPEN) ? 0 : -EINVAL);
 	else
 		err = start_handshake(lp);
 
diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c
index bb2886ac1df..bbf7e955cb1 100644
--- a/arch/sparc/kernel/smp_64.c
+++ b/arch/sparc/kernel/smp_64.c
@@ -151,7 +151,7 @@ void cpu_panic(void)
 #define NUM_ROUNDS	64	/* magic value */
 #define NUM_ITERS	5	/* likewise */
 
-static DEFINE_SPINLOCK(itc_sync_lock);
+static DEFINE_RAW_SPINLOCK(itc_sync_lock);
 static unsigned long go[SLAVE + 1];
 
 #define DEBUG_TICK_SYNC	0
@@ -259,7 +259,7 @@ static void smp_synchronize_one_tick(int cpu)
 	go[MASTER] = 0;
 	membar_safe("#StoreLoad");
 
-	spin_lock_irqsave(&itc_sync_lock, flags);
+	raw_spin_lock_irqsave(&itc_sync_lock, flags);
 	{
 		for (i = 0; i < NUM_ROUNDS*NUM_ITERS; i++) {
 			while (!go[MASTER])
@@ -270,7 +270,7 @@ static void smp_synchronize_one_tick(int cpu)
 			membar_safe("#StoreLoad");
 		}
 	}
-	spin_unlock_irqrestore(&itc_sync_lock, flags);
+	raw_spin_unlock_irqrestore(&itc_sync_lock, flags);
 }
 
 #if defined(CONFIG_SUN_LDOMS) && defined(CONFIG_HOTPLUG_CPU)
diff --git a/arch/sparc/kernel/sys32.S b/arch/sparc/kernel/sys32.S
index d97f3eb72e0..085c60fd4b6 100644
--- a/arch/sparc/kernel/sys32.S
+++ b/arch/sparc/kernel/sys32.S
@@ -87,7 +87,7 @@ SIGN1(sys32_io_submit, compat_sys_io_submit, %o1)
 SIGN1(sys32_mq_open, compat_sys_mq_open, %o1)
 SIGN1(sys32_select, compat_sys_select, %o0)
 SIGN1(sys32_mkdir, sys_mkdir, %o1)
-SIGN3(sys32_futex, compat_sys_futex, %o1, %o2, %o5)
+SIGN1(sys32_futex, compat_sys_futex, %o1)
 SIGN1(sys32_sysfs, compat_sys_sysfs, %o0)
 SIGN2(sys32_sendfile, compat_sys_sendfile, %o0, %o1)
 SIGN2(sys32_sendfile64, compat_sys_sendfile64, %o0, %o1)
diff --git a/arch/sparc/kernel/unaligned_64.c b/arch/sparc/kernel/unaligned_64.c
index dae85bc2eda..a3c3a5bcd12 100644
--- a/arch/sparc/kernel/unaligned_64.c
+++ b/arch/sparc/kernel/unaligned_64.c
@@ -156,17 +156,23 @@ static unsigned long *fetch_reg_addr(unsigned int reg, struct pt_regs *regs)
 unsigned long compute_effective_address(struct pt_regs *regs,
 					unsigned int insn, unsigned int rd)
 {
+	int from_kernel = (regs->tstate & TSTATE_PRIV) != 0;
 	unsigned int rs1 = (insn >> 14) & 0x1f;
 	unsigned int rs2 = insn & 0x1f;
-	int from_kernel = (regs->tstate & TSTATE_PRIV) != 0;
+	unsigned long addr;
 
 	if (insn & 0x2000) {
 		maybe_flush_windows(rs1, 0, rd, from_kernel);
-		return (fetch_reg(rs1, regs) + sign_extend_imm13(insn));
+		addr = (fetch_reg(rs1, regs) + sign_extend_imm13(insn));
 	} else {
 		maybe_flush_windows(rs1, rs2, rd, from_kernel);
-		return (fetch_reg(rs1, regs) + fetch_reg(rs2, regs));
+		addr = (fetch_reg(rs1, regs) + fetch_reg(rs2, regs));
 	}
+
+	if (!from_kernel && test_thread_flag(TIF_32BIT))
+		addr &= 0xffffffff;
+
+	return addr;
 }
 
 /* This is just to make gcc think die_if_kernel does return... */
diff --git a/arch/sparc/lib/NG2memcpy.S b/arch/sparc/lib/NG2memcpy.S
index 0aed75653b5..e993fc8d7c6 100644
--- a/arch/sparc/lib/NG2memcpy.S
+++ b/arch/sparc/lib/NG2memcpy.S
@@ -236,6 +236,7 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 	 */
 	VISEntryHalf
 
+	membar		#Sync
 	alignaddr	%o1, %g0, %g0
 
 	add		%o1, (64 - 1), %o4
diff --git a/arch/sparc/math-emu/math_32.c b/arch/sparc/math-emu/math_32.c
index aa4d55b0bdf..5ce8f2f6460 100644
--- a/arch/sparc/math-emu/math_32.c
+++ b/arch/sparc/math-emu/math_32.c
@@ -499,7 +499,7 @@ static int do_one_mathemu(u32 insn, unsigned long *pfsr, unsigned long *fregs)
 		case 0: fsr = *pfsr;
 			if (IR == -1) IR = 2;
 			/* fcc is always fcc0 */
-			fsr &= ~0xc00; fsr |= (IR << 10); break;
+			fsr &= ~0xc00; fsr |= (IR << 10);
 			*pfsr = fsr;
 			break;
 		case 1: rd->s = IR; break;
diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c
index 1fe0429b631..1387acafc62 100644
--- a/arch/sparc/mm/fault_64.c
+++ b/arch/sparc/mm/fault_64.c
@@ -95,38 +95,51 @@ static unsigned int get_user_insn(unsigned long tpc)
 	pte_t *ptep, pte;
 	unsigned long pa;
 	u32 insn = 0;
-	unsigned long pstate;
 
-	if (pgd_none(*pgdp))
-		goto outret;
+	if (pgd_none(*pgdp) || unlikely(pgd_bad(*pgdp)))
+		goto out;
 	pudp = pud_offset(pgdp, tpc);
-	if (pud_none(*pudp))
-		goto outret;
-	pmdp = pmd_offset(pudp, tpc);
-	if (pmd_none(*pmdp))
-		goto outret;
-
-	/* This disables preemption for us as well. */
-	__asm__ __volatile__("rdpr %%pstate, %0" : "=r" (pstate));
-	__asm__ __volatile__("wrpr %0, %1, %%pstate"
-				: : "r" (pstate), "i" (PSTATE_IE));
-	ptep = pte_offset_map(pmdp, tpc);
-	pte = *ptep;
-	if (!pte_present(pte))
+	if (pud_none(*pudp) || unlikely(pud_bad(*pudp)))
 		goto out;
 
-	pa  = (pte_pfn(pte) << PAGE_SHIFT);
-	pa += (tpc & ~PAGE_MASK);
-
-	/* Use phys bypass so we don't pollute dtlb/dcache. */
-	__asm__ __volatile__("lduwa [%1] %2, %0"
-			     : "=r" (insn)
-			     : "r" (pa), "i" (ASI_PHYS_USE_EC));
+	/* This disables preemption for us as well. */
+	local_irq_disable();
 
+	pmdp = pmd_offset(pudp, tpc);
+	if (pmd_none(*pmdp) || unlikely(pmd_bad(*pmdp)))
+		goto out_irq_enable;
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	if (pmd_trans_huge(*pmdp)) {
+		if (pmd_trans_splitting(*pmdp))
+			goto out_irq_enable;
+
+		pa  = pmd_pfn(*pmdp) << PAGE_SHIFT;
+		pa += tpc & ~HPAGE_MASK;
+
+		/* Use phys bypass so we don't pollute dtlb/dcache. */
+		__asm__ __volatile__("lduwa [%1] %2, %0"
+				     : "=r" (insn)
+				     : "r" (pa), "i" (ASI_PHYS_USE_EC));
+	} else
+#endif
+	{
+		ptep = pte_offset_map(pmdp, tpc);
+		pte = *ptep;
+		if (pte_present(pte)) {
+			pa  = (pte_pfn(pte) << PAGE_SHIFT);
+			pa += (tpc & ~PAGE_MASK);
+
+			/* Use phys bypass so we don't pollute dtlb/dcache. */
+			__asm__ __volatile__("lduwa [%1] %2, %0"
+					     : "=r" (insn)
+					     : "r" (pa), "i" (ASI_PHYS_USE_EC));
+		}
+		pte_unmap(ptep);
+	}
+out_irq_enable:
+	local_irq_enable();
 out:
-	pte_unmap(ptep);
-	__asm__ __volatile__("wrpr %0, 0x0, %%pstate" : : "r" (pstate));
-outret:
 	return insn;
 }
 
@@ -154,7 +167,8 @@ show_signal_msg(struct pt_regs *regs, int sig, int code,
 extern unsigned long compute_effective_address(struct pt_regs *, unsigned int, unsigned int);
 
 static void do_fault_siginfo(int code, int sig, struct pt_regs *regs,
-			     unsigned int insn, int fault_code)
+			     unsigned long fault_addr, unsigned int insn,
+			     int fault_code)
 {
 	unsigned long addr;
 	siginfo_t info;
@@ -162,10 +176,18 @@ static void do_fault_siginfo(int code, int sig, struct pt_regs *regs,
 	info.si_code = code;
 	info.si_signo = sig;
 	info.si_errno = 0;
-	if (fault_code & FAULT_CODE_ITLB)
+	if (fault_code & FAULT_CODE_ITLB) {
 		addr = regs->tpc;
-	else
-		addr = compute_effective_address(regs, insn, 0);
+	} else {
+		/* If we were able to probe the faulting instruction, use it
+		 * to compute a precise fault address.  Otherwise use the fault
+		 * time provided address which may only have page granularity.
+		 */
+		if (insn)
+			addr = compute_effective_address(regs, insn, 0);
+		else
+			addr = fault_addr;
+	}
 	info.si_addr = (void __user *) addr;
 	info.si_trapno = 0;
 
@@ -240,7 +262,7 @@ static void __kprobes do_kernel_fault(struct pt_regs *regs, int si_code,
 		/* The si_code was set to make clear whether
 		 * this was a SEGV_MAPERR or SEGV_ACCERR fault.
 		 */
-		do_fault_siginfo(si_code, SIGSEGV, regs, insn, fault_code);
+		do_fault_siginfo(si_code, SIGSEGV, regs, address, insn, fault_code);
 		return;
 	}
 
@@ -260,18 +282,6 @@ static void noinline __kprobes bogus_32bit_fault_tpc(struct pt_regs *regs)
 	show_regs(regs);
 }
 
-static void noinline __kprobes bogus_32bit_fault_address(struct pt_regs *regs,
-							 unsigned long addr)
-{
-	static int times;
-
-	if (times++ < 10)
-		printk(KERN_ERR "FAULT[%s:%d]: 32-bit process "
-		       "reports 64-bit fault address [%lx]\n",
-		       current->comm, current->pid, addr);
-	show_regs(regs);
-}
-
 asmlinkage void __kprobes do_sparc64_fault(struct pt_regs *regs)
 {
 	struct mm_struct *mm = current->mm;
@@ -300,10 +310,8 @@ asmlinkage void __kprobes do_sparc64_fault(struct pt_regs *regs)
 				goto intr_or_no_mm;
 			}
 		}
-		if (unlikely((address >> 32) != 0)) {
-			bogus_32bit_fault_address(regs, address);
+		if (unlikely((address >> 32) != 0))
 			goto intr_or_no_mm;
-		}
 	}
 
 	if (regs->tstate & TSTATE_PRIV) {
@@ -515,7 +523,7 @@ do_sigbus:
 	 * Send a sigbus, regardless of whether we were in kernel
 	 * or user mode.
 	 */
-	do_fault_siginfo(BUS_ADRERR, SIGBUS, regs, insn, fault_code);
+	do_fault_siginfo(BUS_ADRERR, SIGBUS, regs, address, insn, fault_code);
 
 	/* Kernel mode? Handle exceptions or die */
 	if (regs->tstate & TSTATE_PRIV)
diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c
index 7f8238f4f95..7eb24bddf26 100644
--- a/arch/sparc/mm/init_64.c
+++ b/arch/sparc/mm/init_64.c
@@ -308,6 +308,10 @@ void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t *
 	tsb_index = MM_TSB_BASE;
 	tsb_hash_shift = PAGE_SHIFT;
 
+	/* Don't insert a non-valid PTE into the TSB, we'll deadlock.  */
+	if (!(pte_val(pte) & _PAGE_VALID))
+		return;
+
 	spin_lock_irqsave(&mm->context.lock, flags);
 
 #ifdef CONFIG_HUGETLB_PAGE
@@ -2417,3 +2421,26 @@ void __flush_tlb_all(void)
 	__asm__ __volatile__("wrpr	%0, 0, %%pstate"
 			     : : "r" (pstate));
 }
+
+#ifdef CONFIG_SMP
+#define do_flush_tlb_kernel_range	smp_flush_tlb_kernel_range
+#else
+#define do_flush_tlb_kernel_range	__flush_tlb_kernel_range
+#endif
+
+void flush_tlb_kernel_range(unsigned long start, unsigned long end)
+{
+	if (start < HI_OBP_ADDRESS && end > LOW_OBP_ADDRESS) {
+		if (start < LOW_OBP_ADDRESS) {
+			flush_tsb_kernel_range(start, LOW_OBP_ADDRESS);
+			do_flush_tlb_kernel_range(start, LOW_OBP_ADDRESS);
+		}
+		if (end > HI_OBP_ADDRESS) {
+			flush_tsb_kernel_range(end, HI_OBP_ADDRESS);
+			do_flush_tlb_kernel_range(end, HI_OBP_ADDRESS);
+		}
+	} else {
+		flush_tsb_kernel_range(start, end);
+		do_flush_tlb_kernel_range(start, end);
+	}
+}
diff --git a/arch/sparc/mm/tsb.c b/arch/sparc/mm/tsb.c
index f4e84f3440d..41530193e6d 100644
--- a/arch/sparc/mm/tsb.c
+++ b/arch/sparc/mm/tsb.c
@@ -150,7 +150,19 @@ static void setup_tsb_params(struct mm_struct *mm, unsigned long tsb_idx, unsign
 	mm->context.tsb_block[tsb_idx].tsb_nentries =
 		tsb_bytes / sizeof(struct tsb);
 
-	base = TSBMAP_BASE;
+	switch (tsb_idx) {
+	case MM_TSB_BASE:
+		base = TSBMAP_8K_BASE;
+		break;
+#if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
+	case MM_TSB_HUGE:
+		base = TSBMAP_4M_BASE;
+		break;
+#endif
+	default:
+		BUG();
+	}
+
 	tte = pgprot_val(PAGE_KERNEL_LOCKED);
 	tsb_paddr = __pa(mm->context.tsb_block[tsb_idx].tsb);
 	BUG_ON(tsb_paddr & (tsb_bytes - 1UL));
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 7da62603c68..06d7f890717 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -916,10 +916,27 @@ config VM86
 	default y
 	depends on X86_32
 	---help---
-	  This option is required by programs like DOSEMU to run 16-bit legacy
-	  code on X86 processors. It also may be needed by software like
-	  XFree86 to initialize some video cards via BIOS. Disabling this
-	  option saves about 6k.
+	  This option is required by programs like DOSEMU to run
+	  16-bit real mode legacy code on x86 processors. It also may
+	  be needed by software like XFree86 to initialize some video
+	  cards via BIOS. Disabling this option saves about 6K.
+
+config X86_16BIT
+	bool "Enable support for 16-bit segments" if EXPERT
+	default y
+	---help---
+	  This option is required by programs like Wine to run 16-bit
+	  protected mode legacy code on x86 processors.  Disabling
+	  this option saves about 300 bytes on i386, or around 6K text
+	  plus 16K runtime memory on x86-64,
+
+config X86_ESPFIX32
+	def_bool y
+	depends on X86_16BIT && X86_32
+
+config X86_ESPFIX64
+	def_bool y
+	depends on X86_16BIT && X86_64
 
 config TOSHIBA
 	tristate "Toshiba Laptop support"
diff --git a/arch/x86/include/asm/espfix.h b/arch/x86/include/asm/espfix.h
new file mode 100644
index 00000000000..99efebb2f69
--- /dev/null
+++ b/arch/x86/include/asm/espfix.h
@@ -0,0 +1,16 @@
+#ifndef _ASM_X86_ESPFIX_H
+#define _ASM_X86_ESPFIX_H
+
+#ifdef CONFIG_X86_64
+
+#include <asm/percpu.h>
+
+DECLARE_PER_CPU_READ_MOSTLY(unsigned long, espfix_stack);
+DECLARE_PER_CPU_READ_MOSTLY(unsigned long, espfix_waddr);
+
+extern void init_espfix_bsp(void);
+extern void init_espfix_ap(void);
+
+#endif /* CONFIG_X86_64 */
+
+#endif /* _ASM_X86_ESPFIX_H */
diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h
index bba3cf88e62..0a8b519226b 100644
--- a/arch/x86/include/asm/irqflags.h
+++ b/arch/x86/include/asm/irqflags.h
@@ -129,7 +129,7 @@ static inline notrace unsigned long arch_local_irq_save(void)
 
 #define PARAVIRT_ADJUST_EXCEPTION_FRAME	/*  */
 
-#define INTERRUPT_RETURN	iretq
+#define INTERRUPT_RETURN	jmp native_iret
 #define USERGS_SYSRET64				\
 	swapgs;					\
 	sysretq;
diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h
index 766ea16fbbb..51817fae704 100644
--- a/arch/x86/include/asm/pgtable_64_types.h
+++ b/arch/x86/include/asm/pgtable_64_types.h
@@ -59,5 +59,7 @@ typedef struct { pteval_t pte; } pte_t;
 #define MODULES_VADDR    _AC(0xffffffffa0000000, UL)
 #define MODULES_END      _AC(0xffffffffff000000, UL)
 #define MODULES_LEN   (MODULES_END - MODULES_VADDR)
+#define ESPFIX_PGD_ENTRY _AC(-2, UL)
+#define ESPFIX_BASE_ADDR (ESPFIX_PGD_ENTRY << PGDIR_SHIFT)
 
 #endif /* _ASM_X86_PGTABLE_64_DEFS_H */
diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h
index d0f19f9fb84..16c7971457f 100644
--- a/arch/x86/include/asm/setup.h
+++ b/arch/x86/include/asm/setup.h
@@ -61,6 +61,8 @@ static inline void x86_ce4100_early_setup(void) { }
 
 #ifndef _SETUP
 
+#include <asm/espfix.h>
+
 /*
  * This is set up by the setup-routine at boot-time
  */
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 532d2e090e6..9f15a46e9cc 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -28,6 +28,7 @@ obj-$(CONFIG_X86_64)	+= sys_x86_64.o x8664_ksyms_64.o
 obj-y			+= syscall_$(BITS).o
 obj-$(CONFIG_X86_64)	+= vsyscall_64.o
 obj-$(CONFIG_X86_64)	+= vsyscall_emu_64.o
+obj-$(CONFIG_X86_ESPFIX64)	+= espfix_64.o
 obj-y			+= bootflag.o e820.o
 obj-y			+= pci-dma.o quirks.o topology.o kdebugfs.o
 obj-y			+= alternative.o i8253.o pci-nommu.o hw_breakpoint.o
diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index e36c5cf38fd..a0751249d3c 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -525,6 +525,7 @@ syscall_exit:
 restore_all:
 	TRACE_IRQS_IRET
 restore_all_notrace:
+#ifdef CONFIG_X86_ESPFIX32
 	movl PT_EFLAGS(%esp), %eax	# mix EFLAGS, SS and CS
 	# Warning: PT_OLDSS(%esp) contains the wrong/random values if we
 	# are returning to the kernel.
@@ -535,6 +536,7 @@ restore_all_notrace:
 	cmpl $((SEGMENT_LDT << 8) | USER_RPL), %eax
 	CFI_REMEMBER_STATE
 	je ldt_ss			# returning to user-space with LDT SS
+#endif
 restore_nocheck:
 	RESTORE_REGS 4			# skip orig_eax/error_code
 irq_return:
@@ -550,6 +552,7 @@ ENTRY(iret_exc)
 	.long irq_return,iret_exc
 .previous
 
+#ifdef CONFIG_X86_ESPFIX32
 	CFI_RESTORE_STATE
 ldt_ss:
 #ifdef CONFIG_PARAVIRT
@@ -593,6 +596,7 @@ ldt_ss:
 	lss (%esp), %esp		/* switch to espfix segment */
 	CFI_ADJUST_CFA_OFFSET -8
 	jmp restore_nocheck
+#endif
 	CFI_ENDPROC
 ENDPROC(system_call)
 
@@ -766,6 +770,7 @@ ENDPROC(ptregs_clone)
  * the high word of the segment base from the GDT and swiches to the
  * normal stack and adjusts ESP with the matching offset.
  */
+#ifdef CONFIG_X86_ESPFIX32
 	/* fixup the stack */
 	mov GDT_ESPFIX_SS + 4, %al /* bits 16..23 */
 	mov GDT_ESPFIX_SS + 7, %ah /* bits 24..31 */
@@ -775,8 +780,10 @@ ENDPROC(ptregs_clone)
 	pushl_cfi %eax
 	lss (%esp), %esp		/* switch to the normal stack segment */
 	CFI_ADJUST_CFA_OFFSET -8
+#endif
 .endm
 .macro UNWIND_ESPFIX_STACK
+#ifdef CONFIG_X86_ESPFIX32
 	movl %ss, %eax
 	/* see if on espfix stack */
 	cmpw $__ESPFIX_SS, %ax
@@ -787,6 +794,7 @@ ENDPROC(ptregs_clone)
 	/* switch to normal stack */
 	FIXUP_ESPFIX_STACK
 27:
+#endif
 .endm
 
 /*
@@ -1318,11 +1326,13 @@ END(debug)
  */
 ENTRY(nmi)
 	RING0_INT_FRAME
+#ifdef CONFIG_X86_ESPFIX32
 	pushl_cfi %eax
 	movl %ss, %eax
 	cmpw $__ESPFIX_SS, %ax
 	popl_cfi %eax
 	je nmi_espfix_stack
+#endif
 	cmpl $ia32_sysenter_target,(%esp)
 	je nmi_stack_fixup
 	pushl_cfi %eax
@@ -1362,6 +1372,7 @@ nmi_debug_stack_check:
 	FIX_STACK 24, nmi_stack_correct, 1
 	jmp nmi_stack_correct
 
+#ifdef CONFIG_X86_ESPFIX32
 nmi_espfix_stack:
 	/* We have a RING0_INT_FRAME here.
 	 *
@@ -1383,6 +1394,7 @@ nmi_espfix_stack:
 	lss 12+4(%esp), %esp		# back to espfix stack
 	CFI_ADJUST_CFA_OFFSET -24
 	jmp irq_return
+#endif
 	CFI_ENDPROC
 END(nmi)
 
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index bd6f59203b5..42b055e2469 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -55,6 +55,7 @@
 #include <asm/paravirt.h>
 #include <asm/ftrace.h>
 #include <asm/percpu.h>
+#include <asm/pgtable_types.h>
 #include <linux/err.h>
 
 /* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this.  */
@@ -901,17 +902,47 @@ restore_args:
 irq_return:
 	INTERRUPT_RETURN
 
-	.section __ex_table, "a"
-	.quad irq_return, bad_iret
-	.previous
-
-#ifdef CONFIG_PARAVIRT
 ENTRY(native_iret)
+	/*
+	 * Are we returning to a stack segment from the LDT?  Note: in
+	 * 64-bit mode SS:RSP on the exception stack is always valid.
+	 */
+#ifdef CONFIG_X86_ESPFIX64
+	testb $4,(SS-RIP)(%rsp)
+	jnz native_irq_return_ldt
+#endif
+
+native_irq_return_iret:
 	iretq
 
 	.section __ex_table,"a"
-	.quad native_iret, bad_iret
+	.quad native_irq_return_iret, bad_iret
 	.previous
+
+#ifdef CONFIG_X86_ESPFIX64
+native_irq_return_ldt:
+	pushq_cfi %rax
+	pushq_cfi %rdi
+	SWAPGS
+	movq PER_CPU_VAR(espfix_waddr),%rdi
+	movq %rax,(0*8)(%rdi)	/* RAX */
+	movq (2*8)(%rsp),%rax	/* RIP */
+	movq %rax,(1*8)(%rdi)
+	movq (3*8)(%rsp),%rax	/* CS */
+	movq %rax,(2*8)(%rdi)
+	movq (4*8)(%rsp),%rax	/* RFLAGS */
+	movq %rax,(3*8)(%rdi)
+	movq (6*8)(%rsp),%rax	/* SS */
+	movq %rax,(5*8)(%rdi)
+	movq (5*8)(%rsp),%rax	/* RSP */
+	movq %rax,(4*8)(%rdi)
+	andl $0xffff0000,%eax
+	popq_cfi %rdi
+	orq PER_CPU_VAR(espfix_stack),%rax
+	SWAPGS
+	movq %rax,%rsp
+	popq_cfi %rax
+	jmp native_irq_return_iret
 #endif
 
 	.section .fixup,"ax"
@@ -977,9 +1008,40 @@ ENTRY(retint_kernel)
 	call preempt_schedule_irq
 	jmp exit_intr
 #endif
-
 	CFI_ENDPROC
 END(common_interrupt)
+
+	/*
+	 * If IRET takes a fault on the espfix stack, then we
+	 * end up promoting it to a doublefault.  In that case,
+	 * modify the stack to make it look like we just entered
+	 * the #GP handler from user space, similar to bad_iret.
+	 */
+#ifdef CONFIG_X86_ESPFIX64
+	ALIGN
+__do_double_fault:
+	XCPT_FRAME 1 RDI+8
+	movq RSP(%rdi),%rax		/* Trap on the espfix stack? */
+	sarq $PGDIR_SHIFT,%rax
+	cmpl $ESPFIX_PGD_ENTRY,%eax
+	jne do_double_fault		/* No, just deliver the fault */
+	cmpl $__KERNEL_CS,CS(%rdi)
+	jne do_double_fault
+	movq RIP(%rdi),%rax
+	cmpq $native_irq_return_iret,%rax
+	jne do_double_fault		/* This shouldn't happen... */
+	movq PER_CPU_VAR(kernel_stack),%rax
+	subq $(6*8-KERNEL_STACK_OFFSET),%rax	/* Reset to original stack */
+	movq %rax,RSP(%rdi)
+	movq $0,(%rax)			/* Missing (lost) #GP error code */
+	movq $general_protection,RIP(%rdi)
+	retq
+	CFI_ENDPROC
+END(__do_double_fault)
+#else
+# define __do_double_fault do_double_fault
+#endif
+
 /*
  * End of kprobes section
  */
@@ -1155,7 +1217,7 @@ zeroentry overflow do_overflow
 zeroentry bounds do_bounds
 zeroentry invalid_op do_invalid_op
 zeroentry device_not_available do_device_not_available
-paranoiderrorentry double_fault do_double_fault
+paranoiderrorentry double_fault __do_double_fault
 zeroentry coprocessor_segment_overrun do_coprocessor_segment_overrun
 errorentry invalid_TSS do_invalid_TSS
 errorentry segment_not_present do_segment_not_present
@@ -1486,7 +1548,7 @@ error_sti:
  */
 error_kernelspace:
 	incl %ebx
-	leaq irq_return(%rip),%rcx
+	leaq native_irq_return_iret(%rip),%rcx
 	cmpq %rcx,RIP+8(%rsp)
 	je error_swapgs
 	movl %ecx,%eax	/* zero extend */
diff --git a/arch/x86/kernel/espfix_64.c b/arch/x86/kernel/espfix_64.c
new file mode 100644
index 00000000000..94d857fb103
--- /dev/null
+++ b/arch/x86/kernel/espfix_64.c
@@ -0,0 +1,208 @@
+/* ----------------------------------------------------------------------- *
+ *
+ *   Copyright 2014 Intel Corporation; author: H. Peter Anvin
+ *
+ *   This program is free software; you can redistribute it and/or modify it
+ *   under the terms and conditions of the GNU General Public License,
+ *   version 2, as published by the Free Software Foundation.
+ *
+ *   This program is distributed in the hope it will be useful, but WITHOUT
+ *   ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ *   FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ *   more details.
+ *
+ * ----------------------------------------------------------------------- */
+
+/*
+ * The IRET instruction, when returning to a 16-bit segment, only
+ * restores the bottom 16 bits of the user space stack pointer.  This
+ * causes some 16-bit software to break, but it also leaks kernel state
+ * to user space.
+ *
+ * This works around this by creating percpu "ministacks", each of which
+ * is mapped 2^16 times 64K apart.  When we detect that the return SS is
+ * on the LDT, we copy the IRET frame to the ministack and use the
+ * relevant alias to return to userspace.  The ministacks are mapped
+ * readonly, so if the IRET fault we promote #GP to #DF which is an IST
+ * vector and thus has its own stack; we then do the fixup in the #DF
+ * handler.
+ *
+ * This file sets up the ministacks and the related page tables.  The
+ * actual ministack invocation is in entry_64.S.
+ */
+
+#include <linux/init.h>
+#include <linux/init_task.h>
+#include <linux/kernel.h>
+#include <linux/percpu.h>
+#include <linux/gfp.h>
+#include <linux/random.h>
+#include <asm/pgtable.h>
+#include <asm/pgalloc.h>
+#include <asm/setup.h>
+#include <asm/espfix.h>
+
+/*
+ * Note: we only need 6*8 = 48 bytes for the espfix stack, but round
+ * it up to a cache line to avoid unnecessary sharing.
+ */
+#define ESPFIX_STACK_SIZE	(8*8UL)
+#define ESPFIX_STACKS_PER_PAGE	(PAGE_SIZE/ESPFIX_STACK_SIZE)
+
+/* There is address space for how many espfix pages? */
+#define ESPFIX_PAGE_SPACE	(1UL << (PGDIR_SHIFT-PAGE_SHIFT-16))
+
+#define ESPFIX_MAX_CPUS		(ESPFIX_STACKS_PER_PAGE * ESPFIX_PAGE_SPACE)
+#if CONFIG_NR_CPUS > ESPFIX_MAX_CPUS
+# error "Need more than one PGD for the ESPFIX hack"
+#endif
+
+#define PGALLOC_GFP (GFP_KERNEL | __GFP_NOTRACK | __GFP_REPEAT | __GFP_ZERO)
+
+/* This contains the *bottom* address of the espfix stack */
+DEFINE_PER_CPU_READ_MOSTLY(unsigned long, espfix_stack);
+DEFINE_PER_CPU_READ_MOSTLY(unsigned long, espfix_waddr);
+
+/* Initialization mutex - should this be a spinlock? */
+static DEFINE_MUTEX(espfix_init_mutex);
+
+/* Page allocation bitmap - each page serves ESPFIX_STACKS_PER_PAGE CPUs */
+#define ESPFIX_MAX_PAGES  DIV_ROUND_UP(CONFIG_NR_CPUS, ESPFIX_STACKS_PER_PAGE)
+static void *espfix_pages[ESPFIX_MAX_PAGES];
+
+static __page_aligned_bss pud_t espfix_pud_page[PTRS_PER_PUD]
+	__aligned(PAGE_SIZE);
+
+static unsigned int page_random, slot_random;
+
+/*
+ * This returns the bottom address of the espfix stack for a specific CPU.
+ * The math allows for a non-power-of-two ESPFIX_STACK_SIZE, in which case
+ * we have to account for some amount of padding at the end of each page.
+ */
+static inline unsigned long espfix_base_addr(unsigned int cpu)
+{
+	unsigned long page, slot;
+	unsigned long addr;
+
+	page = (cpu / ESPFIX_STACKS_PER_PAGE) ^ page_random;
+	slot = (cpu + slot_random) % ESPFIX_STACKS_PER_PAGE;
+	addr = (page << PAGE_SHIFT) + (slot * ESPFIX_STACK_SIZE);
+	addr = (addr & 0xffffUL) | ((addr & ~0xffffUL) << 16);
+	addr += ESPFIX_BASE_ADDR;
+	return addr;
+}
+
+#define PTE_STRIDE        (65536/PAGE_SIZE)
+#define ESPFIX_PTE_CLONES (PTRS_PER_PTE/PTE_STRIDE)
+#define ESPFIX_PMD_CLONES PTRS_PER_PMD
+#define ESPFIX_PUD_CLONES (65536/(ESPFIX_PTE_CLONES*ESPFIX_PMD_CLONES))
+
+#define PGTABLE_PROT	  ((_KERNPG_TABLE & ~_PAGE_RW) | _PAGE_NX)
+
+static void init_espfix_random(void)
+{
+	unsigned long rand;
+
+	/*
+	 * This is run before the entropy pools are initialized,
+	 * but this is hopefully better than nothing.
+	 */
+	if (!arch_get_random_long(&rand)) {
+		/* The constant is an arbitrary large prime */
+		rdtscll(rand);
+		rand *= 0xc345c6b72fd16123UL;
+	}
+
+	slot_random = rand % ESPFIX_STACKS_PER_PAGE;
+	page_random = (rand / ESPFIX_STACKS_PER_PAGE)
+		& (ESPFIX_PAGE_SPACE - 1);
+}
+
+void __init init_espfix_bsp(void)
+{
+	pgd_t *pgd_p;
+	pteval_t ptemask;
+
+	ptemask = __supported_pte_mask;
+
+	/* Install the espfix pud into the kernel page directory */
+	pgd_p = &init_level4_pgt[pgd_index(ESPFIX_BASE_ADDR)];
+	pgd_populate(&init_mm, pgd_p, (pud_t *)espfix_pud_page);
+
+	/* Randomize the locations */
+	init_espfix_random();
+
+	/* The rest is the same as for any other processor */
+	init_espfix_ap();
+}
+
+void init_espfix_ap(void)
+{
+	unsigned int cpu, page;
+	unsigned long addr;
+	pud_t pud, *pud_p;
+	pmd_t pmd, *pmd_p;
+	pte_t pte, *pte_p;
+	int n;
+	void *stack_page;
+	pteval_t ptemask;
+
+	/* We only have to do this once... */
+	if (likely(this_cpu_read(espfix_stack)))
+		return;		/* Already initialized */
+
+	cpu = smp_processor_id();
+	addr = espfix_base_addr(cpu);
+	page = cpu/ESPFIX_STACKS_PER_PAGE;
+
+	/* Did another CPU already set this up? */
+	stack_page = ACCESS_ONCE(espfix_pages[page]);
+	if (likely(stack_page))
+		goto done;
+
+	mutex_lock(&espfix_init_mutex);
+
+	/* Did we race on the lock? */
+	stack_page = ACCESS_ONCE(espfix_pages[page]);
+	if (stack_page)
+		goto unlock_done;
+
+	ptemask = __supported_pte_mask;
+
+	pud_p = &espfix_pud_page[pud_index(addr)];
+	pud = *pud_p;
+	if (!pud_present(pud)) {
+		pmd_p = (pmd_t *)__get_free_page(PGALLOC_GFP);
+		pud = __pud(__pa(pmd_p) | (PGTABLE_PROT & ptemask));
+		paravirt_alloc_pmd(&init_mm, __pa(pmd_p) >> PAGE_SHIFT);
+		for (n = 0; n < ESPFIX_PUD_CLONES; n++)
+			set_pud(&pud_p[n], pud);
+	}
+
+	pmd_p = pmd_offset(&pud, addr);
+	pmd = *pmd_p;
+	if (!pmd_present(pmd)) {
+		pte_p = (pte_t *)__get_free_page(PGALLOC_GFP);
+		pmd = __pmd(__pa(pte_p) | (PGTABLE_PROT & ptemask));
+		paravirt_alloc_pte(&init_mm, __pa(pte_p) >> PAGE_SHIFT);
+		for (n = 0; n < ESPFIX_PMD_CLONES; n++)
+			set_pmd(&pmd_p[n], pmd);
+	}
+
+	pte_p = pte_offset_kernel(&pmd, addr);
+	stack_page = (void *)__get_free_page(GFP_KERNEL);
+	pte = __pte(__pa(stack_page) | (__PAGE_KERNEL_RO & ptemask));
+	for (n = 0; n < ESPFIX_PTE_CLONES; n++)
+		set_pte(&pte_p[n*PTE_STRIDE], pte);
+
+	/* Job is done for this CPU and any CPU which shares this page */
+	ACCESS_ONCE(espfix_pages[page]) = stack_page;
+
+unlock_done:
+	mutex_unlock(&espfix_init_mutex);
+done:
+	this_cpu_write(espfix_stack, addr);
+	this_cpu_write(espfix_waddr, (unsigned long)stack_page
+		       + (addr & ~PAGE_MASK));
+}
diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c
index dcbbaa165bd..c37886d759c 100644
--- a/arch/x86/kernel/ldt.c
+++ b/arch/x86/kernel/ldt.c
@@ -20,8 +20,6 @@
 #include <asm/mmu_context.h>
 #include <asm/syscalls.h>
 
-int sysctl_ldt16 = 0;
-
 #ifdef CONFIG_SMP
 static void flush_ldt(void *current_mm)
 {
@@ -231,16 +229,10 @@ static int write_ldt(void __user *ptr, unsigned long bytecount, int oldmode)
 		}
 	}
 
-	/*
-	 * On x86-64 we do not support 16-bit segments due to
-	 * IRET leaking the high bits of the kernel stack address.
-	 */
-#ifdef CONFIG_X86_64
-	if (!ldt_info.seg_32bit && !sysctl_ldt16) {
+	if (!IS_ENABLED(CONFIG_X86_16BIT) && !ldt_info.seg_32bit) {
 		error = -EINVAL;
 		goto out_unlock;
 	}
-#endif
 
 	fill_ldt(&ldt, &ldt_info);
 	if (oldmode)
diff --git a/arch/x86/kernel/paravirt_patch_64.c b/arch/x86/kernel/paravirt_patch_64.c
index 3f08f34f93e..a1da6737ba5 100644
--- a/arch/x86/kernel/paravirt_patch_64.c
+++ b/arch/x86/kernel/paravirt_patch_64.c
@@ -6,7 +6,6 @@ DEF_NATIVE(pv_irq_ops, irq_disable, "cli");
 DEF_NATIVE(pv_irq_ops, irq_enable, "sti");
 DEF_NATIVE(pv_irq_ops, restore_fl, "pushq %rdi; popfq");
 DEF_NATIVE(pv_irq_ops, save_fl, "pushfq; popq %rax");
-DEF_NATIVE(pv_cpu_ops, iret, "iretq");
 DEF_NATIVE(pv_mmu_ops, read_cr2, "movq %cr2, %rax");
 DEF_NATIVE(pv_mmu_ops, read_cr3, "movq %cr3, %rax");
 DEF_NATIVE(pv_mmu_ops, write_cr3, "movq %rdi, %cr3");
@@ -50,7 +49,6 @@ unsigned native_patch(u8 type, u16 clobbers, void *ibuf,
 		PATCH_SITE(pv_irq_ops, save_fl);
 		PATCH_SITE(pv_irq_ops, irq_enable);
 		PATCH_SITE(pv_irq_ops, irq_disable);
-		PATCH_SITE(pv_cpu_ops, iret);
 		PATCH_SITE(pv_cpu_ops, irq_enable_sysexit);
 		PATCH_SITE(pv_cpu_ops, usergs_sysret32);
 		PATCH_SITE(pv_cpu_ops, usergs_sysret64);
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 849cdcf2e76..d28c59588ad 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -271,6 +271,13 @@ notrace static void __cpuinit start_secondary(void *unused)
 	check_tsc_sync_target();
 
 	/*
+	 * Enable the espfix hack for this CPU
+	 */
+#ifdef CONFIG_X86_ESPFIX64
+	init_espfix_ap();
+#endif
+
+	/*
 	 * We need to hold call_lock, so there is no inconsistency
 	 * between the time smp_call_function() determines number of
 	 * IPI recipients, and the time when the determination is made
diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c
index 0002a3a3308..e04e6775323 100644
--- a/arch/x86/mm/dump_pagetables.c
+++ b/arch/x86/mm/dump_pagetables.c
@@ -30,11 +30,13 @@ struct pg_state {
 	unsigned long start_address;
 	unsigned long current_address;
 	const struct addr_marker *marker;
+	unsigned long lines;
 };
 
 struct addr_marker {
 	unsigned long start_address;
 	const char *name;
+	unsigned long max_lines;
 };
 
 /* indices for address_markers; keep sync'd w/ address_markers below */
@@ -45,6 +47,7 @@ enum address_markers_idx {
 	LOW_KERNEL_NR,
 	VMALLOC_START_NR,
 	VMEMMAP_START_NR,
+	ESPFIX_START_NR,
 	HIGH_KERNEL_NR,
 	MODULES_VADDR_NR,
 	MODULES_END_NR,
@@ -67,6 +70,7 @@ static struct addr_marker address_markers[] = {
 	{ PAGE_OFFSET,		"Low Kernel Mapping" },
 	{ VMALLOC_START,        "vmalloc() Area" },
 	{ VMEMMAP_START,        "Vmemmap" },
+	{ ESPFIX_BASE_ADDR,	"ESPfix Area", 16 },
 	{ __START_KERNEL_map,   "High Kernel Mapping" },
 	{ MODULES_VADDR,        "Modules" },
 	{ MODULES_END,          "End Modules" },
@@ -163,7 +167,7 @@ static void note_page(struct seq_file *m, struct pg_state *st,
 		      pgprot_t new_prot, int level)
 {
 	pgprotval_t prot, cur;
-	static const char units[] = "KMGTPE";
+	static const char units[] = "BKMGTPE";
 
 	/*
 	 * If we have a "break" in the series, we need to flush the state that
@@ -178,6 +182,7 @@ static void note_page(struct seq_file *m, struct pg_state *st,
 		st->current_prot = new_prot;
 		st->level = level;
 		st->marker = address_markers;
+		st->lines = 0;
 		seq_printf(m, "---[ %s ]---\n", st->marker->name);
 	} else if (prot != cur || level != st->level ||
 		   st->current_address >= st->marker[1].start_address) {
@@ -188,17 +193,21 @@ static void note_page(struct seq_file *m, struct pg_state *st,
 		/*
 		 * Now print the actual finished series
 		 */
-		seq_printf(m, "0x%0*lx-0x%0*lx   ",
-			   width, st->start_address,
-			   width, st->current_address);
-
-		delta = (st->current_address - st->start_address) >> 10;
-		while (!(delta & 1023) && unit[1]) {
-			delta >>= 10;
-			unit++;
+		if (!st->marker->max_lines ||
+		    st->lines < st->marker->max_lines) {
+			seq_printf(m, "0x%0*lx-0x%0*lx   ",
+				   width, st->start_address,
+				   width, st->current_address);
+
+			delta = (st->current_address - st->start_address);
+			while (!(delta & 1023) && unit[1]) {
+				delta >>= 10;
+				unit++;
+			}
+			seq_printf(m, "%9lu%c ", delta, *unit);
+			printk_prot(m, st->current_prot, st->level);
 		}
-		seq_printf(m, "%9lu%c ", delta, *unit);
-		printk_prot(m, st->current_prot, st->level);
+		st->lines++;
 
 		/*
 		 * We print markers for special areas of address space,
@@ -206,7 +215,15 @@ static void note_page(struct seq_file *m, struct pg_state *st,
 		 * This helps in the interpretation.
 		 */
 		if (st->current_address >= st->marker[1].start_address) {
+			if (st->marker->max_lines &&
+			    st->lines > st->marker->max_lines) {
+				unsigned long nskip =
+					st->lines - st->marker->max_lines;
+				seq_printf(m, "... %lu entr%s skipped ... \n",
+					   nskip, nskip == 1 ? "y" : "ies");
+			}
 			st->marker++;
+			st->lines = 0;
 			seq_printf(m, "---[ %s ]---\n", st->marker->name);
 		}
 
diff --git a/arch/x86/vdso/vdso32-setup.c b/arch/x86/vdso/vdso32-setup.c
index c734408d55e..66e6d935982 100644
--- a/arch/x86/vdso/vdso32-setup.c
+++ b/arch/x86/vdso/vdso32-setup.c
@@ -41,7 +41,6 @@ enum {
 #ifdef CONFIG_X86_64
 #define vdso_enabled			sysctl_vsyscall32
 #define arch_setup_additional_pages	syscall32_setup_pages
-extern int sysctl_ldt16;
 #endif
 
 /*
@@ -381,13 +380,6 @@ static ctl_table abi_table2[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec
 	},
-	{
-		.procname	= "ldt16",
-		.data		= &sysctl_ldt16,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec
-	},
 	{}
 };
 
diff --git a/crypto/af_alg.c b/crypto/af_alg.c
index ac33d5f3077..bf948e13498 100644
--- a/crypto/af_alg.c
+++ b/crypto/af_alg.c
@@ -21,6 +21,7 @@
 #include <linux/module.h>
 #include <linux/net.h>
 #include <linux/rwsem.h>
+#include <linux/security.h>
 
 struct alg_type_list {
 	const struct af_alg_type *type;
@@ -243,6 +244,7 @@ int af_alg_accept(struct sock *sk, struct socket *newsock)
 
 	sock_init_data(newsock, sk2);
 	sock_graft(sk2, newsock);
+	security_sk_clone(sk, sk2);
 
 	err = type->accept(ask->private, sk2);
 	if (err) {
diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index c4bb95b051f..6749acf6f3f 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -455,6 +455,7 @@ static int macvlan_init(struct net_device *dev)
 				  (lowerdev->state & MACVLAN_STATE_MASK);
 	dev->features 		= lowerdev->features & MACVLAN_FEATURES;
 	dev->features		|= NETIF_F_LLTX;
+	dev->vlan_features	= lowerdev->vlan_features & MACVLAN_FEATURES;
 	dev->gso_max_size	= lowerdev->gso_max_size;
 	dev->iflink		= lowerdev->ifindex;
 	dev->hard_header_len	= lowerdev->hard_header_len;
diff --git a/drivers/net/ppp/pptp.c b/drivers/net/ppp/pptp.c
index 8327cc596c3..9f047a04215 100644
--- a/drivers/net/ppp/pptp.c
+++ b/drivers/net/ppp/pptp.c
@@ -281,7 +281,7 @@ static int pptp_xmit(struct ppp_channel *chan, struct sk_buff *skb)
 	nf_reset(skb);
 
 	skb->ip_summed = CHECKSUM_NONE;
-	ip_select_ident(skb, &rt->dst, NULL);
+	ip_select_ident(skb, NULL);
 	ip_send_check(iph);
 
 	ip_local_out(skb);
diff --git a/drivers/sbus/char/bbc_envctrl.c b/drivers/sbus/char/bbc_envctrl.c
index 160e7510aca..0787b975616 100644
--- a/drivers/sbus/char/bbc_envctrl.c
+++ b/drivers/sbus/char/bbc_envctrl.c
@@ -452,6 +452,9 @@ static void attach_one_temp(struct bbc_i2c_bus *bp, struct platform_device *op,
 	if (!tp)
 		return;
 
+	INIT_LIST_HEAD(&tp->bp_list);
+	INIT_LIST_HEAD(&tp->glob_list);
+
 	tp->client = bbc_i2c_attach(bp, op);
 	if (!tp->client) {
 		kfree(tp);
@@ -497,6 +500,9 @@ static void attach_one_fan(struct bbc_i2c_bus *bp, struct platform_device *op,
 	if (!fp)
 		return;
 
+	INIT_LIST_HEAD(&fp->bp_list);
+	INIT_LIST_HEAD(&fp->glob_list);
+
 	fp->client = bbc_i2c_attach(bp, op);
 	if (!fp->client) {
 		kfree(fp);
diff --git a/drivers/sbus/char/bbc_i2c.c b/drivers/sbus/char/bbc_i2c.c
index 54266829290..7179f72b11e 100644
--- a/drivers/sbus/char/bbc_i2c.c
+++ b/drivers/sbus/char/bbc_i2c.c
@@ -301,13 +301,18 @@ static struct bbc_i2c_bus * __init attach_one_i2c(struct platform_device *op, in
 	if (!bp)
 		return NULL;
 
+	INIT_LIST_HEAD(&bp->temps);
+	INIT_LIST_HEAD(&bp->fans);
+
 	bp->i2c_control_regs = of_ioremap(&op->resource[0], 0, 0x2, "bbc_i2c_regs");
 	if (!bp->i2c_control_regs)
 		goto fail;
 
-	bp->i2c_bussel_reg = of_ioremap(&op->resource[1], 0, 0x1, "bbc_i2c_bussel");
-	if (!bp->i2c_bussel_reg)
-		goto fail;
+	if (op->num_resources == 2) {
+		bp->i2c_bussel_reg = of_ioremap(&op->resource[1], 0, 0x1, "bbc_i2c_bussel");
+		if (!bp->i2c_bussel_reg)
+			goto fail;
+	}
 
 	bp->waiting = 0;
 	init_waitqueue_head(&bp->wq);
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 2bc036292d9..ac99b46dc4a 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -795,6 +795,14 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes)
 			scsi_next_command(cmd);
 			return;
 		}
+	} else if (blk_rq_bytes(req) == 0 && result && !sense_deferred) {
+		/*
+		 * Certain non BLOCK_PC requests are commands that don't
+		 * actually transfer anything (FLUSH), so cannot use
+		 * good_bytes != blk_rq_bytes(req) as the signal for an error.
+		 * This sets the error explicitly for the problem case.
+		 */
+		error = __scsi_error_from_host_byte(cmd, result);
 	}
 
 	/* no bidi support for !REQ_TYPE_BLOCK_PC yet */
diff --git a/drivers/tty/serial/sunsab.c b/drivers/tty/serial/sunsab.c
index f0d93eb7e6e..c9549aa135b 100644
--- a/drivers/tty/serial/sunsab.c
+++ b/drivers/tty/serial/sunsab.c
@@ -157,6 +157,15 @@ receive_chars(struct uart_sunsab_port *up,
 	    (up->port.line == up->port.cons->index))
 		saw_console_brk = 1;
 
+	if (count == 0) {
+		if (unlikely(stat->sreg.isr1 & SAB82532_ISR1_BRK)) {
+			stat->sreg.isr0 &= ~(SAB82532_ISR0_PERR |
+					     SAB82532_ISR0_FERR);
+			up->port.icount.brk++;
+			uart_handle_break(&up->port);
+		}
+	}
+
 	for (i = 0; i < count; i++) {
 		unsigned char ch = buf[i], flag;
 
diff --git a/include/linux/printk.h b/include/linux/printk.h
index 0525927f203..d633115489d 100644
--- a/include/linux/printk.h
+++ b/include/linux/printk.h
@@ -101,9 +101,9 @@ asmlinkage __printf(1, 2) __cold
 int printk(const char *fmt, ...);
 
 /*
- * Special printk facility for scheduler use only, _DO_NOT_USE_ !
+ * Special printk facility for scheduler/timekeeping use only, _DO_NOT_USE_ !
  */
-__printf(1, 2) __cold int printk_sched(const char *fmt, ...);
+__printf(1, 2) __cold int printk_deferred(const char *fmt, ...);
 
 /*
  * Please don't use printk_ratelimit(), because it shares ratelimiting state
@@ -133,7 +133,7 @@ int printk(const char *s, ...)
 	return 0;
 }
 static inline __printf(1, 2) __cold
-int printk_sched(const char *s, ...)
+int printk_deferred(const char *s, ...)
 {
 	return 0;
 }
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index e22df7a4f1a..4424db24396 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -2608,22 +2608,5 @@ static inline bool skb_is_recycleable(const struct sk_buff *skb, int skb_size)
 
 	return true;
 }
-
-/**
- * skb_gso_network_seglen - Return length of individual segments of a gso packet
- *
- * @skb: GSO skb
- *
- * skb_gso_network_seglen is used to determine the real size of the
- * individual segments, including Layer3 (IP, IPv6) and L4 headers (TCP/UDP).
- *
- * The MAC/L2 header is not accounted for.
- */
-static inline unsigned int skb_gso_network_seglen(const struct sk_buff *skb)
-{
-	unsigned int hdr_len = skb_transport_header(skb) -
-			       skb_network_header(skb);
-	return hdr_len + skb_gso_transport_seglen(skb);
-}
 #endif	/* __KERNEL__ */
 #endif	/* _LINUX_SKBUFF_H */
diff --git a/include/net/inetpeer.h b/include/net/inetpeer.h
index 2d643649f0f..168d30dfe80 100644
--- a/include/net/inetpeer.h
+++ b/include/net/inetpeer.h
@@ -46,13 +46,12 @@ struct inet_peer {
 	};
 	/*
 	 * Once inet_peer is queued for deletion (refcnt == -1), following fields
-	 * are not available: rid, ip_id_count, tcp_ts, tcp_ts_stamp
+	 * are not available: rid, tcp_ts, tcp_ts_stamp
 	 * We can share memory with rcu_head to help keep inet_peer small.
 	 */
 	union {
 		struct {
 			atomic_t			rid;		/* Frag reception counter */
-			atomic_t			ip_id_count;	/* IP ID for the next packet */
 			__u32				tcp_ts;
 			__u32				tcp_ts_stamp;
 		};
@@ -102,7 +101,7 @@ extern bool inet_peer_xrlim_allow(struct inet_peer *peer, int timeout);
 extern void inetpeer_invalidate_tree(int family);
 
 /*
- * temporary check to make sure we dont access rid, ip_id_count, tcp_ts,
+ * temporary check to make sure we dont access rid, tcp_ts,
  * tcp_ts_stamp if no refcount is taken on inet_peer
  */
 static inline void inet_peer_refcheck(const struct inet_peer *p)
@@ -110,13 +109,4 @@ static inline void inet_peer_refcheck(const struct inet_peer *p)
 	WARN_ON_ONCE(atomic_read(&p->refcnt) <= 0);
 }
 
-
-/* can be called with or without local BH being disabled */
-static inline int inet_getid(struct inet_peer *p, int more)
-{
-	more++;
-	inet_peer_refcheck(p);
-	return atomic_add_return(more, &p->ip_id_count) - more;
-}
-
 #endif /* _NET_INETPEER_H */
diff --git a/include/net/ip.h b/include/net/ip.h
index 3c9421362d8..dae582a487f 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -265,9 +265,10 @@ int ip_dont_fragment(struct sock *sk, struct dst_entry *dst)
 		 !(dst_metric_locked(dst, RTAX_MTU)));
 }
 
-extern void __ip_select_ident(struct iphdr *iph, struct dst_entry *dst, int more);
+u32 ip_idents_reserve(u32 hash, int segs);
+void __ip_select_ident(struct iphdr *iph, int segs);
 
-static inline void ip_select_ident(struct sk_buff *skb, struct dst_entry *dst, struct sock *sk)
+static inline void ip_select_ident_segs(struct sk_buff *skb, struct sock *sk, int segs)
 {
 	struct iphdr *iph = ip_hdr(skb);
 
@@ -277,24 +278,20 @@ static inline void ip_select_ident(struct sk_buff *skb, struct dst_entry *dst, s
 		 * does not change, they drop every other packet in
 		 * a TCP stream using header compression.
 		 */
-		iph->id = (sk && inet_sk(sk)->inet_daddr) ?
-					htons(inet_sk(sk)->inet_id++) : 0;
-	} else
-		__ip_select_ident(iph, dst, 0);
-}
-
-static inline void ip_select_ident_more(struct sk_buff *skb, struct dst_entry *dst, struct sock *sk, int more)
-{
-	struct iphdr *iph = ip_hdr(skb);
-
-	if ((iph->frag_off & htons(IP_DF)) && !skb->local_df) {
 		if (sk && inet_sk(sk)->inet_daddr) {
 			iph->id = htons(inet_sk(sk)->inet_id);
-			inet_sk(sk)->inet_id += 1 + more;
-		} else
+			inet_sk(sk)->inet_id += segs;
+		} else {
 			iph->id = 0;
-	} else
-		__ip_select_ident(iph, dst, more);
+		}
+	} else {
+		__ip_select_ident(iph, segs);
+	}
+}
+
+static inline void ip_select_ident(struct sk_buff *skb, struct sock *sk)
+{
+	ip_select_ident_segs(skb, sk, 1);
 }
 
 /*
diff --git a/include/net/ipip.h b/include/net/ipip.h
index 4dccfe3bf73..e8ee3bb1b1c 100644
--- a/include/net/ipip.h
+++ b/include/net/ipip.h
@@ -50,7 +50,7 @@ struct ip_tunnel_prl_entry {
 	int pkt_len = skb->len - skb_transport_offset(skb);		\
 									\
 	skb->ip_summed = CHECKSUM_NONE;					\
-	ip_select_ident(skb, &rt->dst, NULL);				\
+	ip_select_ident(skb, NULL);				\
 									\
 	err = ip_local_out(skb);					\
 	if (likely(net_xmit_eval(err) == 0)) {				\
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 8b80d56821f..5c40e777a65 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -412,14 +412,19 @@ void ip6_frag_init(struct inet_frag_queue *q, void *a);
 int ip6_frag_match(struct inet_frag_queue *q, void *a);
 
 /* more secured version of ipv6_addr_hash() */
-static inline u32 ipv6_addr_jhash(const struct in6_addr *a)
+static inline u32 __ipv6_addr_jhash(const struct in6_addr *a, const u32 initval)
 {
 	u32 v = (__force u32)a->s6_addr32[0] ^ (__force u32)a->s6_addr32[1];
 
 	return jhash_3words(v,
 			    (__force u32)a->s6_addr32[2],
 			    (__force u32)a->s6_addr32[3],
-			    ipv6_hash_secret);
+			    initval);
+}
+
+static inline u32 ipv6_addr_jhash(const struct in6_addr *a)
+{
+	return __ipv6_addr_jhash(a, ipv6_hash_secret);
 }
 
 static inline int ipv6_addr_any(const struct in6_addr *a)
diff --git a/include/net/secure_seq.h b/include/net/secure_seq.h
index c2e542b27a5..b1c3d1c63c4 100644
--- a/include/net/secure_seq.h
+++ b/include/net/secure_seq.h
@@ -3,8 +3,6 @@
 
 #include <linux/types.h>
 
-extern __u32 secure_ip_id(__be32 daddr);
-extern __u32 secure_ipv6_id(const __be32 daddr[4]);
 extern u32 secure_ipv4_port_ephemeral(__be32 saddr, __be32 daddr, __be16 dport);
 extern u32 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr,
 				      __be16 dport);
diff --git a/init/main.c b/init/main.c
index 71d4c644c3f..f91924bec87 100644
--- a/init/main.c
+++ b/init/main.c
@@ -607,6 +607,10 @@ asmlinkage void __init start_kernel(void)
 	if (efi_enabled(EFI_RUNTIME_SERVICES))
 		efi_enter_virtual_mode();
 #endif
+#ifdef CONFIG_X86_ESPFIX64
+	/* Should be run before the first non-init thread is created */
+	init_espfix_bsp();
+#endif
 	thread_info_cache_init();
 	cred_init();
 	fork_init(totalram_pages);
diff --git a/kernel/printk.c b/kernel/printk.c
index 47e427f54fc..cdbf762047d 100644
--- a/kernel/printk.c
+++ b/kernel/printk.c
@@ -1749,7 +1749,7 @@ late_initcall(printk_late_init);
 
 #if defined CONFIG_PRINTK
 
-int printk_sched(const char *fmt, ...)
+int printk_deferred(const char *fmt, ...)
 {
 	unsigned long flags;
 	va_list args;
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 44994800b33..c19a5c75643 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1313,7 +1313,7 @@ out:
 		 * leave kernel.
 		 */
 		if (p->mm && printk_ratelimit()) {
-			printk_sched("process %d (%s) no longer affine to cpu%d\n",
+			printk_deferred("process %d (%s) no longer affine to cpu%d\n",
 					task_pid_nr(p), p->comm, cpu);
 		}
 	}
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 2b013183571..526c77d1b65 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -884,7 +884,7 @@ static int sched_rt_runtime_exceeded(struct rt_rq *rt_rq)
 
 			if (!once) {
 				once = true;
-				printk_sched("sched: RT throttling activated\n");
+				printk_deferred("sched: RT throttling activated\n");
 			}
 		} else {
 			/*
diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c
index 0d37a6fd18a..4d7ee79ec46 100644
--- a/kernel/time/clockevents.c
+++ b/kernel/time/clockevents.c
@@ -143,7 +143,8 @@ static int clockevents_increase_min_delta(struct clock_event_device *dev)
 {
 	/* Nothing to do if we already reached the limit */
 	if (dev->min_delta_ns >= MIN_DELTA_LIMIT) {
-		printk(KERN_WARNING "CE: Reprogramming failure. Giving up\n");
+		printk_deferred(KERN_WARNING
+				"CE: Reprogramming failure. Giving up\n");
 		dev->next_event.tv64 = KTIME_MAX;
 		return -ETIME;
 	}
@@ -156,9 +157,10 @@ static int clockevents_increase_min_delta(struct clock_event_device *dev)
 	if (dev->min_delta_ns > MIN_DELTA_LIMIT)
 		dev->min_delta_ns = MIN_DELTA_LIMIT;
 
-	printk(KERN_WARNING "CE: %s increased min_delta_ns to %llu nsec\n",
-	       dev->name ? dev->name : "?",
-	       (unsigned long long) dev->min_delta_ns);
+	printk_deferred(KERN_WARNING
+			"CE: %s increased min_delta_ns to %llu nsec\n",
+			dev->name ? dev->name : "?",
+			(unsigned long long) dev->min_delta_ns);
 	return 0;
 }
 
diff --git a/lib/btree.c b/lib/btree.c
index 5cf9e74ec3f..53a773ecf57 100644
--- a/lib/btree.c
+++ b/lib/btree.c
@@ -198,6 +198,7 @@ EXPORT_SYMBOL_GPL(btree_init);
 
 void btree_destroy(struct btree_head *head)
 {
+	mempool_free(head->node, head->mempool);
 	mempool_destroy(head->mempool);
 	head->mempool = NULL;
 }
diff --git a/mm/mlock.c b/mm/mlock.c
index 029f234eb6d..39a36dbfbe5 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -78,6 +78,7 @@ void __clear_page_mlock(struct page *page)
  */
 void mlock_vma_page(struct page *page)
 {
+	/* Serialize with page migration */
 	BUG_ON(!PageLocked(page));
 
 	if (!TestSetPageMlocked(page)) {
@@ -105,6 +106,7 @@ void mlock_vma_page(struct page *page)
  */
 void munlock_vma_page(struct page *page)
 {
+	/* For try_to_munlock() and to serialize with page migration */
 	BUG_ON(!PageLocked(page));
 
 	if (TestClearPageMlocked(page)) {
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 50dd9a8a5bb..3c88ab1b16a 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2340,7 +2340,7 @@ static inline int
 gfp_to_alloc_flags(gfp_t gfp_mask)
 {
 	int alloc_flags = ALLOC_WMARK_MIN | ALLOC_CPUSET;
-	const gfp_t wait = gfp_mask & __GFP_WAIT;
+	const bool atomic = !(gfp_mask & (__GFP_WAIT | __GFP_NO_KSWAPD));
 
 	/* __GFP_HIGH is assumed to be the same as ALLOC_HIGH to save a branch. */
 	BUILD_BUG_ON(__GFP_HIGH != (__force gfp_t) ALLOC_HIGH);
@@ -2349,20 +2349,20 @@ gfp_to_alloc_flags(gfp_t gfp_mask)
 	 * The caller may dip into page reserves a bit more if the caller
 	 * cannot run direct reclaim, or if the caller has realtime scheduling
 	 * policy or is asking for __GFP_HIGH memory.  GFP_ATOMIC requests will
-	 * set both ALLOC_HARDER (!wait) and ALLOC_HIGH (__GFP_HIGH).
+	 * set both ALLOC_HARDER (atomic == true) and ALLOC_HIGH (__GFP_HIGH).
 	 */
 	alloc_flags |= (__force int) (gfp_mask & __GFP_HIGH);
 
-	if (!wait) {
+	if (atomic) {
 		/*
-		 * Not worth trying to allocate harder for
-		 * __GFP_NOMEMALLOC even if it can't schedule.
+		 * Not worth trying to allocate harder for __GFP_NOMEMALLOC even
+		 * if it can't schedule.
 		 */
-		if  (!(gfp_mask & __GFP_NOMEMALLOC))
+		if (!(gfp_mask & __GFP_NOMEMALLOC))
 			alloc_flags |= ALLOC_HARDER;
 		/*
-		 * Ignore cpuset if GFP_ATOMIC (!wait) rather than fail alloc.
-		 * See also cpuset_zone_allowed() comment in kernel/cpuset.c.
+		 * Ignore cpuset mems for GFP_ATOMIC rather than fail, see the
+		 * comment for __cpuset_node_allowed_softwall().
 		 */
 		alloc_flags &= ~ALLOC_CPUSET;
 	} else if (unlikely(rt_task(current)) && !in_interrupt())
diff --git a/mm/rmap.c b/mm/rmap.c
index 6dc46f345db..695eaff55d7 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1449,9 +1449,19 @@ static int try_to_unmap_cluster(unsigned long cursor, unsigned int *mapcount,
 		BUG_ON(!page || PageAnon(page));
 
 		if (locked_vma) {
-			mlock_vma_page(page);   /* no-op if already mlocked */
-			if (page == check_page)
+			if (page == check_page) {
+				/* we know we have check_page locked */
+				mlock_vma_page(page);
 				ret = SWAP_MLOCK;
+			} else if (trylock_page(page)) {
+				/*
+				 * If we can lock the page, perform mlock.
+				 * Otherwise leave the page alone, it will be
+				 * eventually encountered again later.
+				 */
+				mlock_vma_page(page);
+				unlock_page(page);
+			}
 			continue;	/* don't unmap */
 		}
 
diff --git a/net/compat.c b/net/compat.c
index 93f542335e1..2c774d889d3 100644
--- a/net/compat.c
+++ b/net/compat.c
@@ -85,7 +85,7 @@ int verify_compat_iovec(struct msghdr *kern_msg, struct iovec *kern_iov,
 {
 	int tot_len;
 
-	if (kern_msg->msg_namelen) {
+	if (kern_msg->msg_name && kern_msg->msg_namelen) {
 		if (mode == VERIFY_READ) {
 			int err = move_addr_to_kernel(kern_msg->msg_name,
 						      kern_msg->msg_namelen,
@@ -93,10 +93,11 @@ int verify_compat_iovec(struct msghdr *kern_msg, struct iovec *kern_iov,
 			if (err < 0)
 				return err;
 		}
-		if (kern_msg->msg_name)
-			kern_msg->msg_name = kern_address;
-	} else
+		kern_msg->msg_name = kern_address;
+	} else {
 		kern_msg->msg_name = NULL;
+		kern_msg->msg_namelen = 0;
+	}
 
 	tot_len = iov_from_user_compat_to_kern(kern_iov,
 					  (struct compat_iovec __user *)kern_msg->msg_iov,
diff --git a/net/core/iovec.c b/net/core/iovec.c
index 7fd34a56aeb..d1628b79286 100644
--- a/net/core/iovec.c
+++ b/net/core/iovec.c
@@ -39,7 +39,7 @@ int verify_iovec(struct msghdr *m, struct iovec *iov, struct sockaddr_storage *a
 {
 	int size, ct, err;
 
-	if (m->msg_namelen) {
+	if (m->msg_name && m->msg_namelen) {
 		if (mode == VERIFY_READ) {
 			void __user *namep;
 			namep = (void __user __force *) m->msg_name;
@@ -48,10 +48,10 @@ int verify_iovec(struct msghdr *m, struct iovec *iov, struct sockaddr_storage *a
 			if (err < 0)
 				return err;
 		}
-		if (m->msg_name)
-			m->msg_name = address;
+		m->msg_name = address;
 	} else {
 		m->msg_name = NULL;
+		m->msg_namelen = 0;
 	}
 
 	size = m->msg_iovlen * sizeof(struct iovec);
@@ -157,6 +157,10 @@ EXPORT_SYMBOL(memcpy_fromiovec);
 int memcpy_fromiovecend(unsigned char *kdata, const struct iovec *iov,
 			int offset, int len)
 {
+	/* No data? Done! */
+	if (len == 0)
+		return 0;
+
 	/* Skip over the finished iovecs */
 	while (offset >= iov->iov_len) {
 		offset -= iov->iov_len;
diff --git a/net/core/secure_seq.c b/net/core/secure_seq.c
index 99b2596531b..6ecbd58418b 100644
--- a/net/core/secure_seq.c
+++ b/net/core/secure_seq.c
@@ -79,29 +79,6 @@ u32 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr,
 #endif
 
 #ifdef CONFIG_INET
-__u32 secure_ip_id(__be32 daddr)
-{
-	u32 hash[MD5_DIGEST_WORDS];
-
-	hash[0] = (__force __u32) daddr;
-	hash[1] = net_secret[13];
-	hash[2] = net_secret[14];
-	hash[3] = net_secret[15];
-
-	md5_transform(hash, net_secret);
-
-	return hash[0];
-}
-
-__u32 secure_ipv6_id(const __be32 daddr[4])
-{
-	__u32 hash[4];
-
-	memcpy(hash, daddr, 16);
-	md5_transform(hash, net_secret);
-
-	return hash[0];
-}
 
 __u32 secure_tcp_sequence_number(__be32 saddr, __be32 daddr,
 				 __be16 sport, __be16 dport)
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 8de81947537..728f49babfe 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -2748,7 +2748,6 @@ struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features)
 		tail = nskb;
 
 		__copy_skb_header(nskb, skb);
-		nskb->mac_len = skb->mac_len;
 
 		/* nskb and skb might have different headroom */
 		if (nskb->ip_summed == CHECKSUM_PARTIAL)
@@ -2758,6 +2757,7 @@ struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features)
 		skb_set_network_header(nskb, skb->mac_len);
 		nskb->transport_header = (nskb->network_header +
 					  skb_network_header_len(skb));
+		skb_reset_mac_len(nskb);
 		skb_copy_from_linear_data(skb, nskb->data, doffset);
 
 		if (fskb != skb_shinfo(skb)->frag_list)
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index 3f0bb3b3819..782467708c1 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -343,7 +343,7 @@ static struct sk_buff *igmpv3_newpack(struct net_device *dev, int size)
 	pip->saddr    = fl4.saddr;
 	pip->protocol = IPPROTO_IGMP;
 	pip->tot_len  = 0;	/* filled in later */
-	ip_select_ident(skb, &rt->dst, NULL);
+	ip_select_ident(skb, NULL);
 	((u8*)&pip[1])[0] = IPOPT_RA;
 	((u8*)&pip[1])[1] = 4;
 	((u8*)&pip[1])[2] = 0;
@@ -687,7 +687,7 @@ static int igmp_send_report(struct in_device *in_dev, struct ip_mc_list *pmc,
 	iph->daddr    = dst;
 	iph->saddr    = fl4.saddr;
 	iph->protocol = IPPROTO_IGMP;
-	ip_select_ident(skb, &rt->dst, NULL);
+	ip_select_ident(skb, NULL);
 	((u8*)&iph[1])[0] = IPOPT_RA;
 	((u8*)&iph[1])[1] = 4;
 	((u8*)&iph[1])[2] = 0;
diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c
index d63a9268cff..db1b6a73e0f 100644
--- a/net/ipv4/inetpeer.c
+++ b/net/ipv4/inetpeer.c
@@ -26,20 +26,7 @@
  *  Theory of operations.
  *  We keep one entry for each peer IP address.  The nodes contains long-living
  *  information about the peer which doesn't depend on routes.
- *  At this moment this information consists only of ID field for the next
- *  outgoing IP packet.  This field is incremented with each packet as encoded
- *  in inet_getid() function (include/net/inetpeer.h).
- *  At the moment of writing this notes identifier of IP packets is generated
- *  to be unpredictable using this code only for packets subjected
- *  (actually or potentially) to defragmentation.  I.e. DF packets less than
- *  PMTU in size when local fragmentation is disabled use a constant ID and do
- *  not use this code (see ip_select_ident() in include/net/ip.h).
  *
- *  Route cache entries hold references to our nodes.
- *  New cache entries get references via lookup by destination IP address in
- *  the avl tree.  The reference is grabbed only when it's needed i.e. only
- *  when we try to output IP packet which needs an unpredictable ID (see
- *  __ip_select_ident() in net/ipv4/route.c).
  *  Nodes are removed only when reference counter goes to 0.
  *  When it's happened the node may be removed when a sufficient amount of
  *  time has been passed since its last use.  The less-recently-used entry can
@@ -62,7 +49,6 @@
  *		refcnt: atomically against modifications on other CPU;
  *		   usually under some other lock to prevent node disappearing
  *		daddr: unchangeable
- *		ip_id_count: atomic value (no lock needed)
  */
 
 static struct kmem_cache *peer_cachep __read_mostly;
@@ -488,10 +474,6 @@ relookup:
 		p->daddr = *daddr;
 		atomic_set(&p->refcnt, 1);
 		atomic_set(&p->rid, 0);
-		atomic_set(&p->ip_id_count,
-				(daddr->family == AF_INET) ?
-					secure_ip_id(daddr->addr.a4) :
-					secure_ipv6_id(daddr->addr.a6));
 		p->tcp_ts_stamp = 0;
 		p->metrics[RTAX_LOCK-1] = INETPEER_METRICS_NEW;
 		p->rate_tokens = 0;
diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c
index 7593f3a4603..29a07b6c716 100644
--- a/net/ipv4/ip_forward.c
+++ b/net/ipv4/ip_forward.c
@@ -39,68 +39,6 @@
 #include <net/route.h>
 #include <net/xfrm.h>
 
-static bool ip_may_fragment(const struct sk_buff *skb)
-{
-	return unlikely((ip_hdr(skb)->frag_off & htons(IP_DF)) == 0) ||
-		skb->local_df;
-}
-
-static bool ip_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu)
-{
-	if (skb->len <= mtu)
-		return false;
-
-	if (skb_is_gso(skb) && skb_gso_network_seglen(skb) <= mtu)
-		return false;
-
-	return true;
-}
-
-static bool ip_gso_exceeds_dst_mtu(const struct sk_buff *skb)
-{
-	unsigned int mtu;
-
-	if (skb->local_df || !skb_is_gso(skb))
-		return false;
-
-	mtu = dst_mtu(skb_dst(skb));
-
-	/* if seglen > mtu, do software segmentation for IP fragmentation on
-	 * output.  DF bit cannot be set since ip_forward would have sent
-	 * icmp error.
-	 */
-	return skb_gso_network_seglen(skb) > mtu;
-}
-
-/* called if GSO skb needs to be fragmented on forward */
-static int ip_forward_finish_gso(struct sk_buff *skb)
-{
-	struct sk_buff *segs;
-	int ret = 0;
-
-	segs = skb_gso_segment(skb, 0);
-	if (IS_ERR(segs)) {
-		kfree_skb(skb);
-		return -ENOMEM;
-	}
-
-	consume_skb(skb);
-
-	do {
-		struct sk_buff *nskb = segs->next;
-		int err;
-
-		segs->next = NULL;
-		err = dst_output(segs);
-
-		if (err && ret == 0)
-			ret = err;
-		segs = nskb;
-	} while (segs);
-
-	return ret;
-}
-
 static int ip_forward_finish(struct sk_buff *skb)
 {
 	struct ip_options * opt	= &(IPCB(skb)->opt);
@@ -110,9 +48,6 @@ static int ip_forward_finish(struct sk_buff *skb)
 	if (unlikely(opt->optlen))
 		ip_forward_options(skb);
 
-	if (ip_gso_exceeds_dst_mtu(skb))
-		return ip_forward_finish_gso(skb);
-
 	return dst_output(skb);
 }
 
@@ -152,7 +87,8 @@ int ip_forward(struct sk_buff *skb)
 	if (opt->is_strictroute && opt->nexthop != rt->rt_gateway)
 		goto sr_failed;
 
-	if (!ip_may_fragment(skb) && ip_exceeds_mtu(skb, dst_mtu(&rt->dst))) {
+	if (unlikely(skb->len > dst_mtu(&rt->dst) && !skb_is_gso(skb) &&
+		     (ip_hdr(skb)->frag_off & htons(IP_DF))) && !skb->local_df) {
 		IP_INC_STATS(dev_net(rt->dst.dev), IPSTATS_MIB_FRAGFAILS);
 		icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
 			  htonl(dst_mtu(&rt->dst)));
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index a9efca62749..683a1d29c54 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -161,7 +161,7 @@ int ip_build_and_send_pkt(struct sk_buff *skb, struct sock *sk,
 	iph->daddr    = (opt && opt->opt.srr ? opt->opt.faddr : daddr);
 	iph->saddr    = saddr;
 	iph->protocol = sk->sk_protocol;
-	ip_select_ident(skb, &rt->dst, sk);
+	ip_select_ident(skb, sk);
 
 	if (opt && opt->opt.optlen) {
 		iph->ihl += opt->opt.optlen>>2;
@@ -403,8 +403,7 @@ packet_routed:
 		ip_options_build(skb, &inet_opt->opt, inet->inet_daddr, rt, 0);
 	}
 
-	ip_select_ident_more(skb, &rt->dst, sk,
-			     (skb_shinfo(skb)->gso_segs ?: 1) - 1);
+	ip_select_ident_segs(skb, sk, skb_shinfo(skb)->gso_segs ?: 1);
 
 	skb->priority = sk->sk_priority;
 	skb->mark = sk->sk_mark;
@@ -1347,7 +1346,7 @@ struct sk_buff *__ip_make_skb(struct sock *sk,
 	iph->ihl = 5;
 	iph->tos = inet->tos;
 	iph->frag_off = df;
-	ip_select_ident(skb, &rt->dst, sk);
+	ip_select_ident(skb, sk);
 	iph->ttl = ttl;
 	iph->protocol = sk->sk_protocol;
 	ip_copy_addrs(iph, fl4);
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 94cd1ef1e31..5ccef6e06dc 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -1576,7 +1576,7 @@ static void ip_encap(struct sk_buff *skb, __be32 saddr, __be32 daddr)
 	iph->protocol	=	IPPROTO_IPIP;
 	iph->ihl	=	5;
 	iph->tot_len	=	htons(skb->len);
-	ip_select_ident(skb, skb_dst(skb), NULL);
+	ip_select_ident(skb, NULL);
 	ip_send_check(iph);
 
 	memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 6e213930612..d996cf8fe69 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -384,7 +384,7 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4,
 		iph->check   = 0;
 		iph->tot_len = htons(length);
 		if (!iph->id)
-			ip_select_ident(skb, &rt->dst, NULL);
+			ip_select_ident(skb, NULL);
 
 		iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl);
 	}
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 73373d76146..e2ae7e49605 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1342,46 +1342,53 @@ void rt_bind_peer(struct rtable *rt, __be32 daddr, int create)
 		rt->rt_peer_genid = rt_peer_genid();
 }
 
-/*
- * Peer allocation may fail only in serious out-of-memory conditions.  However
- * we still can generate some output.
- * Random ID selection looks a bit dangerous because we have no chances to
- * select ID being unique in a reasonable period of time.
- * But broken packet identifier may be better than no packet at all.
+#define IP_IDENTS_SZ 2048u
+struct ip_ident_bucket {
+	atomic_t	id;
+	u32		stamp32;
+};
+
+static struct ip_ident_bucket *ip_idents __read_mostly;
+
+/* In order to protect privacy, we add a perturbation to identifiers
+ * if one generator is seldom used. This makes hard for an attacker
+ * to infer how many packets were sent between two points in time.
  */
-static void ip_select_fb_ident(struct iphdr *iph)
+u32 ip_idents_reserve(u32 hash, int segs)
 {
-	static DEFINE_SPINLOCK(ip_fb_id_lock);
-	static u32 ip_fallback_id;
-	u32 salt;
+	struct ip_ident_bucket *bucket = ip_idents + hash % IP_IDENTS_SZ;
+	u32 old = ACCESS_ONCE(bucket->stamp32);
+	u32 now = (u32)jiffies;
+	u32 delta = 0;
+
+	if (old != now && cmpxchg(&bucket->stamp32, old, now) == old) {
+		u64 x = random32();
+
+		x *= (now - old);
+		delta = (u32)(x >> 32);
+	}
 
-	spin_lock_bh(&ip_fb_id_lock);
-	salt = secure_ip_id((__force __be32)ip_fallback_id ^ iph->daddr);
-	iph->id = htons(salt & 0xFFFF);
-	ip_fallback_id = salt;
-	spin_unlock_bh(&ip_fb_id_lock);
+	return atomic_add_return(segs + delta, &bucket->id) - segs;
 }
+EXPORT_SYMBOL(ip_idents_reserve);
 
-void __ip_select_ident(struct iphdr *iph, struct dst_entry *dst, int more)
+void __ip_select_ident(struct iphdr *iph, int segs)
 {
-	struct rtable *rt = (struct rtable *) dst;
-
-	if (rt && !(rt->dst.flags & DST_NOPEER)) {
-		if (rt->peer == NULL)
-			rt_bind_peer(rt, rt->rt_dst, 1);
+	static u32 ip_idents_hashrnd __read_mostly;
+	static bool hashrnd_initialized = false;
+	u32 hash, id;
 
-		/* If peer is attached to destination, it is never detached,
-		   so that we need not to grab a lock to dereference it.
-		 */
-		if (rt->peer) {
-			iph->id = htons(inet_getid(rt->peer, more));
-			return;
-		}
-	} else if (!rt)
-		printk(KERN_DEBUG "rt_bind_peer(0) @%p\n",
-		       __builtin_return_address(0));
+	if (unlikely(!hashrnd_initialized)) {
+		hashrnd_initialized = true;
+		get_random_bytes(&ip_idents_hashrnd, sizeof(ip_idents_hashrnd));
+	}
 
-	ip_select_fb_ident(iph);
+	hash = jhash_3words((__force u32)iph->daddr,
+			    (__force u32)iph->saddr,
+			    iph->protocol,
+			    ip_idents_hashrnd);
+	id = ip_idents_reserve(hash, segs);
+	iph->id = htons(id);
 }
 EXPORT_SYMBOL(__ip_select_ident);
 
@@ -3020,7 +3027,6 @@ static int rt_fill_info(struct net *net,
 	error = rt->dst.error;
 	if (peer) {
 		inet_peer_refcheck(rt->peer);
-		id = atomic_read(&peer->ip_id_count) & 0xffff;
 		if (peer->tcp_ts_stamp) {
 			ts = peer->tcp_ts;
 			tsage = get_seconds() - peer->tcp_ts_stamp;
@@ -3453,6 +3459,12 @@ int __init ip_rt_init(void)
 {
 	int rc = 0;
 
+	ip_idents = kmalloc(IP_IDENTS_SZ * sizeof(*ip_idents), GFP_KERNEL);
+	if (!ip_idents)
+		panic("IP: failed to allocate ip_idents\n");
+
+	get_random_bytes(ip_idents, IP_IDENTS_SZ * sizeof(*ip_idents));
+
 #ifdef CONFIG_IP_ROUTE_CLASSID
 	ip_rt_acct = __alloc_percpu(256 * sizeof(struct ip_rt_acct), __alignof__(struct ip_rt_acct));
 	if (!ip_rt_acct)
diff --git a/net/ipv4/tcp_vegas.c b/net/ipv4/tcp_vegas.c
index 80fa2bfd7ed..c042e529a11 100644
--- a/net/ipv4/tcp_vegas.c
+++ b/net/ipv4/tcp_vegas.c
@@ -218,7 +218,8 @@ static void tcp_vegas_cong_avoid(struct sock *sk, u32 ack, u32 in_flight)
 			 * This is:
 			 *     (actual rate in segments) * baseRTT
 			 */
-			target_cwnd = tp->snd_cwnd * vegas->baseRTT / rtt;
+			target_cwnd = (u64)tp->snd_cwnd * vegas->baseRTT;
+			do_div(target_cwnd, rtt);
 
 			/* Calculate the difference between the window we had,
 			 * and the window we would like to have. This quantity
diff --git a/net/ipv4/tcp_veno.c b/net/ipv4/tcp_veno.c
index ac43cd747bc..b4d1858be55 100644
--- a/net/ipv4/tcp_veno.c
+++ b/net/ipv4/tcp_veno.c
@@ -144,7 +144,7 @@ static void tcp_veno_cong_avoid(struct sock *sk, u32 ack, u32 in_flight)
 
 		rtt = veno->minrtt;
 
-		target_cwnd = (tp->snd_cwnd * veno->basertt);
+		target_cwnd = (u64)tp->snd_cwnd * veno->basertt;
 		target_cwnd <<= V_PARAM_SHIFT;
 		do_div(target_cwnd, rtt);
 
diff --git a/net/ipv4/xfrm4_mode_tunnel.c b/net/ipv4/xfrm4_mode_tunnel.c
index 938553efbf8..5531eb2a56a 100644
--- a/net/ipv4/xfrm4_mode_tunnel.c
+++ b/net/ipv4/xfrm4_mode_tunnel.c
@@ -54,12 +54,12 @@ static int xfrm4_mode_tunnel_output(struct xfrm_state *x, struct sk_buff *skb)
 
 	top_iph->frag_off = (flags & XFRM_STATE_NOPMTUDISC) ?
 		0 : (XFRM_MODE_SKB_CB(skb)->frag_off & htons(IP_DF));
-	ip_select_ident(skb, dst->child, NULL);
 
 	top_iph->ttl = ip4_dst_hoplimit(dst->child);
 
 	top_iph->saddr = x->props.saddr.a4;
 	top_iph->daddr = x->id.daddr.a4;
+	ip_select_ident(skb, NULL);
 
 	return 0;
 }
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index e82f4f0053e..ac4b0e33c98 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -2454,8 +2454,18 @@ static void init_loopback(struct net_device *dev)
 			if (sp_ifa->flags & (IFA_F_DADFAILED | IFA_F_TENTATIVE))
 				continue;
 
-			if (sp_ifa->rt)
-				continue;
+			if (sp_ifa->rt) {
+				/* This dst has been added to garbage list when
+				 * lo device down, release this obsolete dst and
+				 * reallocate a new router for ifa.
+				 */
+				if (sp_ifa->rt->dst.obsolete > 0) {
+					dst_release(&sp_ifa->rt->dst);
+					sp_ifa->rt = NULL;
+				} else {
+					continue;
+				}
+			}
 
 			sp_rt = addrconf_dst_alloc(idev, &sp_ifa->addr, 0);
 
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 2d474dc7aad..cbaf15ba83e 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -382,17 +382,6 @@ static inline int ip6_forward_finish(struct sk_buff *skb)
 	return dst_output(skb);
 }
 
-static bool ip6_pkt_too_big(const struct sk_buff *skb, unsigned int mtu)
-{
-	if (skb->len <= mtu || skb->local_df)
-		return false;
-
-	if (skb_is_gso(skb) && skb_gso_network_seglen(skb) <= mtu)
-		return false;
-
-	return true;
-}
-
 int ip6_forward(struct sk_buff *skb)
 {
 	struct dst_entry *dst = skb_dst(skb);
@@ -515,7 +504,7 @@ int ip6_forward(struct sk_buff *skb)
 	if (mtu < IPV6_MIN_MTU)
 		mtu = IPV6_MIN_MTU;
 
-	if (ip6_pkt_too_big(skb, mtu)) {
+	if (skb->len > mtu && !skb_is_gso(skb)) {
 		/* Again, force OUTPUT device used as source address */
 		skb->dev = dst->dev;
 		icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
@@ -611,22 +600,19 @@ int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr)
 
 void ipv6_select_ident(struct frag_hdr *fhdr, struct rt6_info *rt)
 {
-	static atomic_t ipv6_fragmentation_id;
-	int ident;
+	static u32 ip6_idents_hashrnd __read_mostly;
+	static bool hashrnd_initialized = false;
+	u32 hash, id;
 
-	if (rt && !(rt->dst.flags & DST_NOPEER)) {
-		struct inet_peer *peer;
-
-		if (!rt->rt6i_peer)
-			rt6_bind_peer(rt, 1);
-		peer = rt->rt6i_peer;
-		if (peer) {
-			fhdr->identification = htonl(inet_getid(peer, 0));
-			return;
-		}
+	if (unlikely(!hashrnd_initialized)) {
+		hashrnd_initialized = true;
+		get_random_bytes(&ip6_idents_hashrnd, sizeof(ip6_idents_hashrnd));
 	}
-	ident = atomic_inc_return(&ipv6_fragmentation_id);
-	fhdr->identification = htonl(ident);
+	hash = __ipv6_addr_jhash(&rt->rt6i_dst.addr, ip6_idents_hashrnd);
+	hash = __ipv6_addr_jhash(&rt->rt6i_src.addr, hash);
+
+	id = ip_idents_reserve(hash, 1);
+	fhdr->identification = htonl(id);
 }
 
 int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index 4e38a81e48e..82ed7dfb7b8 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -1351,7 +1351,7 @@ static int pppol2tp_setsockopt(struct socket *sock, int level, int optname,
 	int err;
 
 	if (level != SOL_PPPOL2TP)
-		return udp_prot.setsockopt(sk, level, optname, optval, optlen);
+		return -EINVAL;
 
 	if (optlen < sizeof(int))
 		return -EINVAL;
@@ -1477,7 +1477,7 @@ static int pppol2tp_getsockopt(struct socket *sock, int level,
 	struct pppol2tp_session *ps;
 
 	if (level != SOL_PPPOL2TP)
-		return udp_prot.getsockopt(sk, level, optname, optval, optlen);
+		return -EINVAL;
 
 	if (get_user(len, (int __user *) optlen))
 		return -EFAULT;
diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c
index ec78ab63dd4..559d307163b 100644
--- a/net/netfilter/ipvs/ip_vs_xmit.c
+++ b/net/netfilter/ipvs/ip_vs_xmit.c
@@ -853,7 +853,7 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 	iph->daddr		=	cp->daddr.ip;
 	iph->saddr		=	saddr;
 	iph->ttl		=	old_iph->ttl;
-	ip_select_ident(skb, &rt->dst, NULL);
+	ip_select_ident(skb, NULL);
 
 	/* Another hack: avoid icmp_send in ip_fragment */
 	skb->local_df = 1;
diff --git a/net/sctp/associola.c b/net/sctp/associola.c
index 25b207b3ffe..da54d2922f5 100644
--- a/net/sctp/associola.c
+++ b/net/sctp/associola.c
@@ -1188,6 +1188,7 @@ void sctp_assoc_update(struct sctp_association *asoc,
 	asoc->c = new->c;
 	asoc->peer.rwnd = new->peer.rwnd;
 	asoc->peer.sack_needed = new->peer.sack_needed;
+	asoc->peer.auth_capable = new->peer.auth_capable;
 	asoc->peer.i = new->peer.i;
 	sctp_tsnmap_init(&asoc->peer.tsn_map, SCTP_TSN_MAP_INITIAL,
 			 asoc->peer.i.initial_tsn, GFP_ATOMIC);
diff --git a/net/sctp/output.c b/net/sctp/output.c
index cf3e22c586a..5bd9aa93139 100644
--- a/net/sctp/output.c
+++ b/net/sctp/output.c
@@ -587,7 +587,7 @@ out:
 	return err;
 no_route:
 	kfree_skb(nskb);
-	IP_INC_STATS_BH(&init_net, IPSTATS_MIB_OUTNOROUTES);
+	IP_INC_STATS(&init_net, IPSTATS_MIB_OUTNOROUTES);
 
 	/* FIXME: Returning the 'err' will effect all the associations
 	 * associated with a socket, although only one of the paths of the