lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  yescrypt  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  linux-hardening  linux-cve-announce  PHC 
Open Source and information security mailing list archives
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <20140814040337.GB7150@kroah.com>
Date:	Thu, 14 Aug 2014 12:03:37 +0800
From:	Greg KH <gregkh@...uxfoundation.org>
To:	linux-kernel@...r.kernel.org,
	Andrew Morton <akpm@...ux-foundation.org>,
	torvalds@...ux-foundation.org, stable@...r.kernel.org
Cc:	lwn@....net, Jiri Slaby <jslaby@...e.cz>
Subject: Re: Linux 3.14.17


diff --git a/Makefile b/Makefile
index 8b22e24a2d8e..12aac0325888 100644
--- a/Makefile
+++ b/Makefile
@@ -1,6 +1,6 @@
 VERSION = 3
 PATCHLEVEL = 14
-SUBLEVEL = 16
+SUBLEVEL = 17
 EXTRAVERSION =
 NAME = Remembering Coco
 
diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h
index 0f9e94537eee..1a49ffdf9da9 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)
@@ -71,6 +73,23 @@
 
 #include <linux/sched.h>
 
+extern unsigned long sparc64_valid_addr_bitmap[];
+
+/* Needs to be defined here and not in linux/mm.h, as it is arch dependent */
+static inline bool __kern_addr_valid(unsigned long paddr)
+{
+	if ((paddr >> MAX_PHYS_ADDRESS_BITS) != 0UL)
+		return false;
+	return test_bit(paddr >> ILOG2_4MB, sparc64_valid_addr_bitmap);
+}
+
+static inline bool kern_addr_valid(unsigned long addr)
+{
+	unsigned long paddr = __pa(addr);
+
+	return __kern_addr_valid(paddr);
+}
+
 /* Entries per page directory level. */
 #define PTRS_PER_PTE	(1UL << (PAGE_SHIFT-3))
 #define PTRS_PER_PMD	(1UL << PMD_BITS)
@@ -79,9 +98,12 @@
 /* Kernel has a separate 44bit address space. */
 #define FIRST_USER_ADDRESS	0
 
-#define pte_ERROR(e)	__builtin_trap()
-#define pmd_ERROR(e)	__builtin_trap()
-#define pgd_ERROR(e)	__builtin_trap()
+#define pmd_ERROR(e)							\
+	pr_err("%s:%d: bad pmd %p(%016lx) seen at (%pS)\n",		\
+	       __FILE__, __LINE__, &(e), pmd_val(e), __builtin_return_address(0))
+#define pgd_ERROR(e)							\
+	pr_err("%s:%d: bad pgd %p(%016lx) seen at (%pS)\n",		\
+	       __FILE__, __LINE__, &(e), pgd_val(e), __builtin_return_address(0))
 
 #endif /* !(__ASSEMBLY__) */
 
@@ -258,8 +280,8 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t prot)
 {
 	unsigned long mask, tmp;
 
-	/* SUN4U: 0x600307ffffffecb8 (negated == 0x9ffcf80000001347)
-	 * SUN4V: 0x30ffffffffffee17 (negated == 0xcf000000000011e8)
+	/* SUN4U: 0x630107ffffffec38 (negated == 0x9cfef800000013c7)
+	 * SUN4V: 0x33ffffffffffee07 (negated == 0xcc000000000011f8)
 	 *
 	 * Even if we use negation tricks the result is still a 6
 	 * instruction sequence, so don't try to play fancy and just
@@ -289,10 +311,10 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t prot)
 	"	.previous\n"
 	: "=r" (mask), "=r" (tmp)
 	: "i" (_PAGE_PADDR_4U | _PAGE_MODIFIED_4U | _PAGE_ACCESSED_4U |
-	       _PAGE_CP_4U | _PAGE_CV_4U | _PAGE_E_4U | _PAGE_PRESENT_4U |
+	       _PAGE_CP_4U | _PAGE_CV_4U | _PAGE_E_4U |
 	       _PAGE_SPECIAL | _PAGE_PMD_HUGE | _PAGE_SZALL_4U),
 	  "i" (_PAGE_PADDR_4V | _PAGE_MODIFIED_4V | _PAGE_ACCESSED_4V |
-	       _PAGE_CP_4V | _PAGE_CV_4V | _PAGE_E_4V | _PAGE_PRESENT_4V |
+	       _PAGE_CP_4V | _PAGE_CV_4V | _PAGE_E_4V |
 	       _PAGE_SPECIAL | _PAGE_PMD_HUGE | _PAGE_SZALL_4V));
 
 	return __pte((pte_val(pte) & mask) | (pgprot_val(prot) & ~mask));
@@ -633,7 +655,7 @@ static inline unsigned long pmd_large(pmd_t pmd)
 {
 	pte_t pte = __pte(pmd_val(pmd));
 
-	return (pte_val(pte) & _PAGE_PMD_HUGE) && pte_present(pte);
+	return pte_val(pte) & _PAGE_PMD_HUGE;
 }
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
@@ -719,20 +741,6 @@ static inline pmd_t pmd_mkwrite(pmd_t pmd)
 	return __pmd(pte_val(pte));
 }
 
-static inline pmd_t pmd_mknotpresent(pmd_t pmd)
-{
-	unsigned long mask;
-
-	if (tlb_type == hypervisor)
-		mask = _PAGE_PRESENT_4V;
-	else
-		mask = _PAGE_PRESENT_4U;
-
-	pmd_val(pmd) &= ~mask;
-
-	return pmd;
-}
-
 static inline pmd_t pmd_mksplitting(pmd_t pmd)
 {
 	pte_t pte = __pte(pmd_val(pmd));
@@ -757,6 +765,20 @@ static inline int pmd_present(pmd_t pmd)
 
 #define pmd_none(pmd)			(!pmd_val(pmd))
 
+/* pmd_bad() is only called on non-trans-huge PMDs.  Our encoding is
+ * very simple, it's just the physical address.  PTE tables are of
+ * size PAGE_SIZE so make sure the sub-PAGE_SIZE bits are clear and
+ * the top bits outside of the range of any physical address size we
+ * support are clear as well.  We also validate the physical itself.
+ */
+#define pmd_bad(pmd)			((pmd_val(pmd) & ~PAGE_MASK) || \
+					 !__kern_addr_valid(pmd_val(pmd)))
+
+#define pud_none(pud)			(!pud_val(pud))
+
+#define pud_bad(pud)			((pud_val(pud) & ~PAGE_MASK) || \
+					 !__kern_addr_valid(pud_val(pud)))
+
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 extern void set_pmd_at(struct mm_struct *mm, unsigned long addr,
 		       pmd_t *pmdp, pmd_t pmd);
@@ -790,10 +812,7 @@ static inline unsigned long __pmd_page(pmd_t pmd)
 #define pud_page_vaddr(pud)		\
 	((unsigned long) __va(pud_val(pud)))
 #define pud_page(pud) 			virt_to_page((void *)pud_page_vaddr(pud))
-#define pmd_bad(pmd)			(0)
 #define pmd_clear(pmdp)			(pmd_val(*(pmdp)) = 0UL)
-#define pud_none(pud)			(!pud_val(pud))
-#define pud_bad(pud)			(0)
 #define pud_present(pud)		(pud_val(pud) != 0U)
 #define pud_clear(pudp)			(pud_val(*(pudp)) = 0UL)
 
@@ -893,6 +912,10 @@ extern void update_mmu_cache(struct vm_area_struct *, unsigned long, pte_t *);
 extern void update_mmu_cache_pmd(struct vm_area_struct *vma, unsigned long addr,
 				 pmd_t *pmd);
 
+#define __HAVE_ARCH_PMDP_INVALIDATE
+extern void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
+			    pmd_t *pmdp);
+
 #define __HAVE_ARCH_PGTABLE_DEPOSIT
 extern void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
 				       pgtable_t pgtable);
@@ -919,18 +942,6 @@ extern unsigned long pte_file(pte_t);
 extern pte_t pgoff_to_pte(unsigned long);
 #define PTE_FILE_MAX_BITS	(64UL - PAGE_SHIFT - 1UL)
 
-extern unsigned long sparc64_valid_addr_bitmap[];
-
-/* Needs to be defined here and not in linux/mm.h, as it is arch dependent */
-static inline bool kern_addr_valid(unsigned long addr)
-{
-	unsigned long paddr = __pa(addr);
-
-	if ((paddr >> 41UL) != 0UL)
-		return false;
-	return test_bit(paddr >> 22, sparc64_valid_addr_bitmap);
-}
-
 extern int page_in_phys_avail(unsigned long paddr);
 
 /*
diff --git a/arch/sparc/include/asm/tlbflush_64.h b/arch/sparc/include/asm/tlbflush_64.h
index 3c3c89f52643..7f9bab26a499 100644
--- a/arch/sparc/include/asm/tlbflush_64.h
+++ b/arch/sparc/include/asm/tlbflush_64.h
@@ -34,6 +34,8 @@ 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);
@@ -48,11 +50,6 @@ 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);
@@ -63,11 +60,6 @@ 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/include/asm/tsb.h b/arch/sparc/include/asm/tsb.h
index 2230f80d9fe3..90916f955cac 100644
--- a/arch/sparc/include/asm/tsb.h
+++ b/arch/sparc/include/asm/tsb.h
@@ -171,7 +171,8 @@ extern struct tsb_phys_patch_entry __tsb_phys_patch, __tsb_phys_patch_end;
 	andcc		REG1, REG2, %g0;		\
 	be,pt		%xcc, 700f;			\
 	 sethi		%hi(4 * 1024 * 1024), REG2;	\
-	andn		REG1, REG2, REG1;		\
+	brgez,pn	REG1, FAIL_LABEL;		\
+	 andn		REG1, REG2, REG1;		\
 	and		VADDR, REG2, REG2;		\
 	brlz,pt		REG1, PTE_LABEL;		\
 	 or		REG1, REG2, REG1;		\
diff --git a/arch/sparc/kernel/head_64.S b/arch/sparc/kernel/head_64.S
index 26b706a1867d..452f04fe8da6 100644
--- a/arch/sparc/kernel/head_64.S
+++ b/arch/sparc/kernel/head_64.S
@@ -282,8 +282,8 @@ sun4v_chip_type:
 	stx	%l2, [%l4 + 0x0]
 	ldx	[%sp + 2047 + 128 + 0x50], %l3	! physaddr low
 	/* 4MB align */
-	srlx	%l3, 22, %l3
-	sllx	%l3, 22, %l3
+	srlx	%l3, ILOG2_4MB, %l3
+	sllx	%l3, ILOG2_4MB, %l3
 	stx	%l3, [%l4 + 0x8]
 
 	/* Leave service as-is, "call-method" */
diff --git a/arch/sparc/kernel/ktlb.S b/arch/sparc/kernel/ktlb.S
index 542e96ac4d39..605d49204580 100644
--- a/arch/sparc/kernel/ktlb.S
+++ b/arch/sparc/kernel/ktlb.S
@@ -277,7 +277,7 @@ kvmap_dtlb_load:
 #ifdef CONFIG_SPARSEMEM_VMEMMAP
 kvmap_vmemmap:
 	sub		%g4, %g5, %g5
-	srlx		%g5, 22, %g5
+	srlx		%g5, ILOG2_4MB, %g5
 	sethi		%hi(vmemmap_table), %g1
 	sllx		%g5, 3, %g5
 	or		%g1, %lo(vmemmap_table), %g1
diff --git a/arch/sparc/kernel/ldc.c b/arch/sparc/kernel/ldc.c
index e01d75d40329..66dacd56bb10 100644
--- a/arch/sparc/kernel/ldc.c
+++ b/arch/sparc/kernel/ldc.c
@@ -1336,7 +1336,7 @@ 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 b085311dcd0e..8416d7fadcce 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 f7c72b6efc27..d066eb18650c 100644
--- a/arch/sparc/kernel/sys32.S
+++ b/arch/sparc/kernel/sys32.S
@@ -44,7 +44,7 @@ SIGN1(sys32_timer_settime, compat_sys_timer_settime, %o1)
 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)
-SIGN3(sys32_futex, compat_sys_futex, %o1, %o2, %o5)
+SIGN1(sys32_futex, compat_sys_futex, %o1)
 SIGN1(sys32_recvfrom, compat_sys_recvfrom, %o0)
 SIGN1(sys32_recvmsg, compat_sys_recvmsg, %o0)
 SIGN1(sys32_sendmsg, compat_sys_sendmsg, %o0)
diff --git a/arch/sparc/kernel/unaligned_64.c b/arch/sparc/kernel/unaligned_64.c
index 3c1a7cb31579..35ab8b60d256 100644
--- a/arch/sparc/kernel/unaligned_64.c
+++ b/arch/sparc/kernel/unaligned_64.c
@@ -166,17 +166,23 @@ 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 2c20ad63ddbf..30eee6e8a81b 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 aa4d55b0bdf0..5ce8f2f64604 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 69bb818fdd79..4ced3fc66130 100644
--- a/arch/sparc/mm/fault_64.c
+++ b/arch/sparc/mm/fault_64.c
@@ -96,38 +96,51 @@ 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;
+	if (pud_none(*pudp) || unlikely(pud_bad(*pudp)))
+		goto out;
 
 	/* 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))
-		goto out;
+	local_irq_disable();
+
+	pmdp = pmd_offset(pudp, tpc);
+	if (pmd_none(*pmdp) || unlikely(pmd_bad(*pmdp)))
+		goto out_irq_enable;
 
-	pa  = (pte_pfn(pte) << PAGE_SHIFT);
-	pa += (tpc & ~PAGE_MASK);
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	if (pmd_trans_huge(*pmdp)) {
+		if (pmd_trans_splitting(*pmdp))
+			goto out_irq_enable;
 
-	/* 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));
+		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;
 }
 
@@ -153,7 +166,8 @@ show_signal_msg(struct pt_regs *regs, int sig, int code,
 }
 
 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;
@@ -161,10 +175,18 @@ 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;
 
@@ -239,7 +261,7 @@ 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;
 	}
 
@@ -259,18 +281,6 @@ 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)
 {
 	enum ctx_state prev_state = exception_enter();
@@ -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) {
@@ -525,7 +533,7 @@ 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/gup.c b/arch/sparc/mm/gup.c
index c4d3da68b800..1aed0432c64b 100644
--- a/arch/sparc/mm/gup.c
+++ b/arch/sparc/mm/gup.c
@@ -73,7 +73,7 @@ static int gup_huge_pmd(pmd_t *pmdp, pmd_t pmd, unsigned long addr,
 	struct page *head, *page, *tail;
 	int refs;
 
-	if (!pmd_large(pmd))
+	if (!(pmd_val(pmd) & _PAGE_VALID))
 		return 0;
 
 	if (write && !pmd_write(pmd))
diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c
index eafbc65c9c47..96862241b342 100644
--- a/arch/sparc/mm/init_64.c
+++ b/arch/sparc/mm/init_64.c
@@ -350,6 +350,10 @@ void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t *
 
 	mm = vma->vm_mm;
 
+	/* Don't insert a non-valid PTE into the TSB, we'll deadlock.  */
+	if (!pte_accessible(mm, pte))
+		return;
+
 	spin_lock_irqsave(&mm->context.lock, flags);
 
 #if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
@@ -588,7 +592,7 @@ static void __init remap_kernel(void)
 	int i, tlb_ent = sparc64_highest_locked_tlbent();
 
 	tte_vaddr = (unsigned long) KERNBASE;
-	phys_page = (prom_boot_mapping_phys_low >> 22UL) << 22UL;
+	phys_page = (prom_boot_mapping_phys_low >> ILOG2_4MB) << ILOG2_4MB;
 	tte_data = kern_large_tte(phys_page);
 
 	kern_locked_tte_data = tte_data;
@@ -1881,7 +1885,7 @@ void __init paging_init(void)
 
 	BUILD_BUG_ON(NR_CPUS > 4096);
 
-	kern_base = (prom_boot_mapping_phys_low >> 22UL) << 22UL;
+	kern_base = (prom_boot_mapping_phys_low >> ILOG2_4MB) << ILOG2_4MB;
 	kern_size = (unsigned long)&_end - (unsigned long)KERNBASE;
 
 	/* Invalidate both kernel TSBs.  */
@@ -1937,7 +1941,7 @@ void __init paging_init(void)
 	shift = kern_base + PAGE_OFFSET - ((unsigned long)KERNBASE);
 
 	real_end = (unsigned long)_end;
-	num_kernel_image_mappings = DIV_ROUND_UP(real_end - KERNBASE, 1 << 22);
+	num_kernel_image_mappings = DIV_ROUND_UP(real_end - KERNBASE, 1 << ILOG2_4MB);
 	printk("Kernel: Using %d locked TLB entries for main kernel image.\n",
 	       num_kernel_image_mappings);
 
@@ -2094,7 +2098,7 @@ static void __init setup_valid_addr_bitmap_from_pavail(unsigned long *bitmap)
 
 				if (new_start <= old_start &&
 				    new_end >= (old_start + PAGE_SIZE)) {
-					set_bit(old_start >> 22, bitmap);
+					set_bit(old_start >> ILOG2_4MB, bitmap);
 					goto do_next_page;
 				}
 			}
@@ -2143,7 +2147,7 @@ void __init mem_init(void)
 	addr = PAGE_OFFSET + kern_base;
 	last = PAGE_ALIGN(kern_size) + addr;
 	while (addr < last) {
-		set_bit(__pa(addr) >> 22, sparc64_valid_addr_bitmap);
+		set_bit(__pa(addr) >> ILOG2_4MB, sparc64_valid_addr_bitmap);
 		addr += PAGE_SIZE;
 	}
 
@@ -2267,7 +2271,7 @@ int __meminit vmemmap_populate(unsigned long vstart, unsigned long vend,
 		void *block;
 
 		if (!(*vmem_pp & _PAGE_VALID)) {
-			block = vmemmap_alloc_block(1UL << 22, node);
+			block = vmemmap_alloc_block(1UL << ILOG2_4MB, node);
 			if (!block)
 				return -ENOMEM;
 
@@ -2614,6 +2618,10 @@ void update_mmu_cache_pmd(struct vm_area_struct *vma, unsigned long addr,
 
 	pte = pmd_val(entry);
 
+	/* Don't insert a non-valid PMD into the TSB, we'll deadlock.  */
+	if (!(pte & _PAGE_VALID))
+		return;
+
 	/* We are fabricating 8MB pages using 4MB real hw pages.  */
 	pte |= (addr & (1UL << REAL_HPAGE_SHIFT));
 
@@ -2694,3 +2702,26 @@ void hugetlb_setup(struct pt_regs *regs)
 	}
 }
 #endif
+
+#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/tlb.c b/arch/sparc/mm/tlb.c
index b12cb5e72812..b89aba217e3b 100644
--- a/arch/sparc/mm/tlb.c
+++ b/arch/sparc/mm/tlb.c
@@ -134,7 +134,7 @@ no_cache_flush:
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 static void tlb_batch_pmd_scan(struct mm_struct *mm, unsigned long vaddr,
-			       pmd_t pmd, bool exec)
+			       pmd_t pmd)
 {
 	unsigned long end;
 	pte_t *pte;
@@ -142,8 +142,11 @@ static void tlb_batch_pmd_scan(struct mm_struct *mm, unsigned long vaddr,
 	pte = pte_offset_map(&pmd, vaddr);
 	end = vaddr + HPAGE_SIZE;
 	while (vaddr < end) {
-		if (pte_val(*pte) & _PAGE_VALID)
+		if (pte_val(*pte) & _PAGE_VALID) {
+			bool exec = pte_exec(*pte);
+
 			tlb_batch_add_one(mm, vaddr, exec);
+		}
 		pte++;
 		vaddr += PAGE_SIZE;
 	}
@@ -177,19 +180,30 @@ void set_pmd_at(struct mm_struct *mm, unsigned long addr,
 	}
 
 	if (!pmd_none(orig)) {
-		pte_t orig_pte = __pte(pmd_val(orig));
-		bool exec = pte_exec(orig_pte);
-
 		addr &= HPAGE_MASK;
 		if (pmd_trans_huge(orig)) {
+			pte_t orig_pte = __pte(pmd_val(orig));
+			bool exec = pte_exec(orig_pte);
+
 			tlb_batch_add_one(mm, addr, exec);
 			tlb_batch_add_one(mm, addr + REAL_HPAGE_SIZE, exec);
 		} else {
-			tlb_batch_pmd_scan(mm, addr, orig, exec);
+			tlb_batch_pmd_scan(mm, addr, orig);
 		}
 	}
 }
 
+void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
+		     pmd_t *pmdp)
+{
+	pmd_t entry = *pmdp;
+
+	pmd_val(entry) &= ~_PAGE_VALID;
+
+	set_pmd_at(vma->vm_mm, address, pmdp, entry);
+	flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
+}
+
 void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
 				pgtable_t pgtable)
 {
diff --git a/arch/sparc/mm/tsb.c b/arch/sparc/mm/tsb.c
index f5d506fdddad..fe19b81acc09 100644
--- a/arch/sparc/mm/tsb.c
+++ b/arch/sparc/mm/tsb.c
@@ -133,7 +133,19 @@ 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/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
index 391f29ef6d2e..1fbeaa9dd202 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
@@ -337,6 +337,7 @@ struct sw_tx_bd {
 	u8		flags;
 /* Set on the first BD descriptor when there is a split BD */
 #define BNX2X_TSO_SPLIT_BD		(1<<0)
+#define BNX2X_HAS_SECOND_PBD		(1<<1)
 };
 
 struct sw_rx_page {
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
index 5ed512473b12..afa4a1f63270 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
@@ -223,6 +223,12 @@ static u16 bnx2x_free_tx_pkt(struct bnx2x *bp, struct bnx2x_fp_txdata *txdata,
 	--nbd;
 	bd_idx = TX_BD(NEXT_TX_IDX(bd_idx));
 
+	if (tx_buf->flags & BNX2X_HAS_SECOND_PBD) {
+		/* Skip second parse bd... */
+		--nbd;
+		bd_idx = TX_BD(NEXT_TX_IDX(bd_idx));
+	}
+
 	/* TSO headers+data bds share a common mapping. See bnx2x_tx_split() */
 	if (tx_buf->flags & BNX2X_TSO_SPLIT_BD) {
 		tx_data_bd = &txdata->tx_desc_ring[bd_idx].reg_bd;
@@ -3868,6 +3874,9 @@ netdev_tx_t bnx2x_start_xmit(struct sk_buff *skb, struct net_device *dev)
 			/* set encapsulation flag in start BD */
 			SET_FLAG(tx_start_bd->general_data,
 				 ETH_TX_START_BD_TUNNEL_EXIST, 1);
+
+			tx_buf->flags |= BNX2X_HAS_SECOND_PBD;
+
 			nbd++;
 		} else if (xmit_type & XMIT_CSUM) {
 			/* Set PBD in checksum offload case w/o encapsulation */
diff --git a/drivers/net/ethernet/brocade/bna/bnad.c b/drivers/net/ethernet/brocade/bna/bnad.c
index 4ad1187e82fb..669eeb4eb247 100644
--- a/drivers/net/ethernet/brocade/bna/bnad.c
+++ b/drivers/net/ethernet/brocade/bna/bnad.c
@@ -600,9 +600,9 @@ bnad_cq_process(struct bnad *bnad, struct bna_ccb *ccb, int budget)
 	prefetch(bnad->netdev);
 
 	cq = ccb->sw_q;
-	cmpl = &cq[ccb->producer_index];
 
 	while (packets < budget) {
+		cmpl = &cq[ccb->producer_index];
 		if (!cmpl->valid)
 			break;
 		/* The 'valid' field is set by the adapter, only after writing
diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index 5adecc5f52b7..7f1abb7c18f2 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -548,6 +548,7 @@ static int macvlan_init(struct net_device *dev)
 				  (lowerdev->state & MACVLAN_STATE_MASK);
 	dev->features 		= lowerdev->features & MACVLAN_FEATURES;
 	dev->features		|= ALWAYS_ON_FEATURES;
+	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/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 365375408904..25f74191a788 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -353,7 +353,7 @@ int phy_device_register(struct phy_device *phydev)
 	phydev->bus->phy_map[phydev->addr] = phydev;
 
 	/* Run all of the fixups for this PHY */
-	err = phy_init_hw(phydev);
+	err = phy_scan_fixups(phydev);
 	if (err) {
 		pr_err("PHY %d failed to initialize\n", phydev->addr);
 		goto out;
diff --git a/drivers/net/ppp/pptp.c b/drivers/net/ppp/pptp.c
index 01805319e1e0..1aff970be33e 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 160e7510aca6..0787b9756165 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 c7763e482eb2..812b5f0361b6 100644
--- a/drivers/sbus/char/bbc_i2c.c
+++ b/drivers/sbus/char/bbc_i2c.c
@@ -300,13 +300,18 @@ static struct bbc_i2c_bus * attach_one_i2c(struct platform_device *op, int index
 	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/tty/serial/sunsab.c b/drivers/tty/serial/sunsab.c
index 80a58eca785b..e8f77606561b 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/fs/xfs/xfs_log.h b/fs/xfs/xfs_log.h
index b0f4ef77fa70..bf9781e9fd92 100644
--- a/fs/xfs/xfs_log.h
+++ b/fs/xfs/xfs_log.h
@@ -24,7 +24,8 @@ struct xfs_log_vec {
 	struct xfs_log_iovec	*lv_iovecp;	/* iovec array */
 	struct xfs_log_item	*lv_item;	/* owner */
 	char			*lv_buf;	/* formatted buffer */
-	int			lv_buf_len;	/* size of formatted buffer */
+	int			lv_bytes;	/* accounted space in buffer */
+	int			lv_buf_len;	/* aligned size of buffer */
 	int			lv_size;	/* size of allocated lv */
 };
 
@@ -52,15 +53,21 @@ xlog_prepare_iovec(struct xfs_log_vec *lv, struct xfs_log_iovec **vecp,
 	return vec->i_addr;
 }
 
+/*
+ * We need to make sure the next buffer is naturally aligned for the biggest
+ * basic data type we put into it.  We already accounted for this padding when
+ * sizing the buffer.
+ *
+ * However, this padding does not get written into the log, and hence we have to
+ * track the space used by the log vectors separately to prevent log space hangs
+ * due to inaccurate accounting (i.e. a leak) of the used log space through the
+ * CIL context ticket.
+ */
 static inline void
 xlog_finish_iovec(struct xfs_log_vec *lv, struct xfs_log_iovec *vec, int len)
 {
-	/*
-	 * We need to make sure the next buffer is naturally aligned for the
-	 * biggest basic data type we put into it.  We already accounted for
-	 * this when sizing the buffer.
-	 */
 	lv->lv_buf_len += round_up(len, sizeof(uint64_t));
+	lv->lv_bytes += len;
 	vec->i_len = len;
 }
 
diff --git a/fs/xfs/xfs_log_cil.c b/fs/xfs/xfs_log_cil.c
index 4ef6fdbced78..bcfbaae4702c 100644
--- a/fs/xfs/xfs_log_cil.c
+++ b/fs/xfs/xfs_log_cil.c
@@ -97,7 +97,7 @@ xfs_cil_prepare_item(
 {
 	/* Account for the new LV being passed in */
 	if (lv->lv_buf_len != XFS_LOG_VEC_ORDERED) {
-		*diff_len += lv->lv_buf_len;
+		*diff_len += lv->lv_bytes;
 		*diff_iovecs += lv->lv_niovecs;
 	}
 
@@ -111,7 +111,7 @@ xfs_cil_prepare_item(
 	else if (old_lv != lv) {
 		ASSERT(lv->lv_buf_len != XFS_LOG_VEC_ORDERED);
 
-		*diff_len -= old_lv->lv_buf_len;
+		*diff_len -= old_lv->lv_bytes;
 		*diff_iovecs -= old_lv->lv_niovecs;
 		kmem_free(old_lv);
 	}
@@ -239,7 +239,7 @@ xlog_cil_insert_format_items(
 			 * that the space reservation accounting is correct.
 			 */
 			*diff_iovecs -= lv->lv_niovecs;
-			*diff_len -= lv->lv_buf_len;
+			*diff_len -= lv->lv_bytes;
 		} else {
 			/* allocate new data chunk */
 			lv = kmem_zalloc(buf_size, KM_SLEEP|KM_NOFS);
@@ -259,6 +259,7 @@ xlog_cil_insert_format_items(
 
 		/* The allocated data region lies beyond the iovec region */
 		lv->lv_buf_len = 0;
+		lv->lv_bytes = 0;
 		lv->lv_buf = (char *)lv + buf_size - nbytes;
 		ASSERT(IS_ALIGNED((unsigned long)lv->lv_buf, sizeof(uint64_t)));
 
diff --git a/include/net/inetpeer.h b/include/net/inetpeer.h
index 058271bde27a..823ec7bb9c67 100644
--- a/include/net/inetpeer.h
+++ b/include/net/inetpeer.h
@@ -41,14 +41,13 @@ struct inet_peer {
 		struct rcu_head     gc_rcu;
 	};
 	/*
-	 * Once inet_peer is queued for deletion (refcnt == -1), following fields
-	 * are not available: rid, ip_id_count
+	 * Once inet_peer is queued for deletion (refcnt == -1), following field
+	 * is not available: rid
 	 * 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 */
 		};
 		struct rcu_head         rcu;
 		struct inet_peer	*gc_next;
@@ -165,7 +164,7 @@ bool inet_peer_xrlim_allow(struct inet_peer *peer, int timeout);
 void inetpeer_invalidate_tree(struct inet_peer_base *);
 
 /*
- * 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)
@@ -173,13 +172,4 @@ 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 23be0fd37937..937f19681426 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -297,9 +297,10 @@ static inline unsigned int ip_skb_dst_mtu(const struct sk_buff *skb)
 	}
 }
 
-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);
 
@@ -309,24 +310,20 @@ 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/ip_tunnels.h b/include/net/ip_tunnels.h
index e77c10405d51..7b9ec5837496 100644
--- a/include/net/ip_tunnels.h
+++ b/include/net/ip_tunnels.h
@@ -40,6 +40,7 @@ struct ip_tunnel_prl_entry {
 
 struct ip_tunnel_dst {
 	struct dst_entry __rcu 		*dst;
+	__be32				 saddr;
 };
 
 struct ip_tunnel {
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 4f541f11ce63..9ac65781d44b 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -660,8 +660,6 @@ static inline int ipv6_addr_diff(const struct in6_addr *a1, const struct in6_add
 	return __ipv6_addr_diff(a1, a2, sizeof(struct in6_addr));
 }
 
-void ipv6_select_ident(struct frag_hdr *fhdr, struct rt6_info *rt);
-
 int ip6_dst_hoplimit(struct dst_entry *dst);
 
 /*
diff --git a/include/net/secure_seq.h b/include/net/secure_seq.h
index f257486f17be..3f36d45b714a 100644
--- a/include/net/secure_seq.h
+++ b/include/net/secure_seq.h
@@ -3,8 +3,6 @@
 
 #include <linux/types.h>
 
-__u32 secure_ip_id(__be32 daddr);
-__u32 secure_ipv6_id(const __be32 daddr[4]);
 u32 secure_ipv4_port_ephemeral(__be32 saddr, __be32 daddr, __be16 dport);
 u32 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr,
 			       __be16 dport);
diff --git a/net/batman-adv/fragmentation.c b/net/batman-adv/fragmentation.c
index cc1cfd60c094..c46387a46535 100644
--- a/net/batman-adv/fragmentation.c
+++ b/net/batman-adv/fragmentation.c
@@ -128,6 +128,7 @@ static bool batadv_frag_insert_packet(struct batadv_orig_node *orig_node,
 {
 	struct batadv_frag_table_entry *chain;
 	struct batadv_frag_list_entry *frag_entry_new = NULL, *frag_entry_curr;
+	struct batadv_frag_list_entry *frag_entry_last = NULL;
 	struct batadv_frag_packet *frag_packet;
 	uint8_t bucket;
 	uint16_t seqno, hdr_size = sizeof(struct batadv_frag_packet);
@@ -180,11 +181,14 @@ static bool batadv_frag_insert_packet(struct batadv_orig_node *orig_node,
 			ret = true;
 			goto out;
 		}
+
+		/* store current entry because it could be the last in list */
+		frag_entry_last = frag_entry_curr;
 	}
 
-	/* Reached the end of the list, so insert after 'frag_entry_curr'. */
-	if (likely(frag_entry_curr)) {
-		hlist_add_after(&frag_entry_curr->list, &frag_entry_new->list);
+	/* Reached the end of the list, so insert after 'frag_entry_last'. */
+	if (likely(frag_entry_last)) {
+		hlist_add_after(&frag_entry_last->list, &frag_entry_new->list);
 		chain->size += skb->len - hdr_size;
 		chain->timestamp = jiffies;
 		ret = true;
diff --git a/net/compat.c b/net/compat.c
index f50161fb812e..cbc1a2a26587 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 b61869429f4c..26dc0062652f 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);
@@ -107,6 +107,10 @@ EXPORT_SYMBOL(memcpy_toiovecend);
 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 897da56f3aff..ba71212f0251 100644
--- a/net/core/secure_seq.c
+++ b/net/core/secure_seq.c
@@ -85,31 +85,6 @@ EXPORT_SYMBOL(secure_ipv6_port_ephemeral);
 #endif
 
 #ifdef CONFIG_INET
-__u32 secure_ip_id(__be32 daddr)
-{
-	u32 hash[MD5_DIGEST_WORDS];
-
-	net_secret_init();
-	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];
-
-	net_secret_init();
-	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 7f2e1fce706e..8f6391bbf509 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -2968,9 +2968,9 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb,
 		tail = nskb;
 
 		__copy_skb_header(nskb, head_skb);
-		nskb->mac_len = head_skb->mac_len;
 
 		skb_headers_offset_update(nskb, skb_headroom(nskb) - headroom);
+		skb_reset_mac_len(nskb);
 
 		skb_copy_from_linear_data_offset(head_skb, -tnl_hlen,
 						 nskb->data - tnl_hlen,
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index 9db3b877fcaf..0ffcd4d64e0a 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -369,7 +369,7 @@ 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;
@@ -714,7 +714,7 @@ 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 48f424465112..bf2cb4a4714b 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;
@@ -497,10 +483,6 @@ 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->metrics[RTAX_LOCK-1] = INETPEER_METRICS_NEW;
 		p->rate_tokens = 0;
 		/* 60*HZ is arbitrary, but chosen enough high so that the first
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 73c6b63bba74..ed88d781248f 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -148,7 +148,7 @@ 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;
@@ -386,8 +386,7 @@ 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;
@@ -1338,7 +1337,7 @@ struct sk_buff *__ip_make_skb(struct sock *sk,
 	iph->ttl = ttl;
 	iph->protocol = sk->sk_protocol;
 	ip_copy_addrs(iph, fl4);
-	ip_select_ident(skb, &rt->dst, sk);
+	ip_select_ident(skb, sk);
 
 	if (opt) {
 		iph->ihl += opt->optlen>>2;
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 62cd9e0ae35b..0a4af0920af3 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -69,23 +69,25 @@ static unsigned int ip_tunnel_hash(__be32 key, __be32 remote)
 }
 
 static void __tunnel_dst_set(struct ip_tunnel_dst *idst,
-			     struct dst_entry *dst)
+			     struct dst_entry *dst, __be32 saddr)
 {
 	struct dst_entry *old_dst;
 
 	dst_clone(dst);
 	old_dst = xchg((__force struct dst_entry **)&idst->dst, dst);
 	dst_release(old_dst);
+	idst->saddr = saddr;
 }
 
-static void tunnel_dst_set(struct ip_tunnel *t, struct dst_entry *dst)
+static void tunnel_dst_set(struct ip_tunnel *t,
+			   struct dst_entry *dst, __be32 saddr)
 {
-	__tunnel_dst_set(this_cpu_ptr(t->dst_cache), dst);
+	__tunnel_dst_set(this_cpu_ptr(t->dst_cache), dst, saddr);
 }
 
 static void tunnel_dst_reset(struct ip_tunnel *t)
 {
-	tunnel_dst_set(t, NULL);
+	tunnel_dst_set(t, NULL, 0);
 }
 
 void ip_tunnel_dst_reset_all(struct ip_tunnel *t)
@@ -93,20 +95,25 @@ void ip_tunnel_dst_reset_all(struct ip_tunnel *t)
 	int i;
 
 	for_each_possible_cpu(i)
-		__tunnel_dst_set(per_cpu_ptr(t->dst_cache, i), NULL);
+		__tunnel_dst_set(per_cpu_ptr(t->dst_cache, i), NULL, 0);
 }
 EXPORT_SYMBOL(ip_tunnel_dst_reset_all);
 
-static struct rtable *tunnel_rtable_get(struct ip_tunnel *t, u32 cookie)
+static struct rtable *tunnel_rtable_get(struct ip_tunnel *t,
+					u32 cookie, __be32 *saddr)
 {
+	struct ip_tunnel_dst *idst;
 	struct dst_entry *dst;
 
 	rcu_read_lock();
-	dst = rcu_dereference(this_cpu_ptr(t->dst_cache)->dst);
+	idst = this_cpu_ptr(t->dst_cache);
+	dst = rcu_dereference(idst->dst);
 	if (dst && !atomic_inc_not_zero(&dst->__refcnt))
 		dst = NULL;
 	if (dst) {
-		if (dst->obsolete && dst->ops->check(dst, cookie) == NULL) {
+		if (!dst->obsolete || dst->ops->check(dst, cookie)) {
+			*saddr = idst->saddr;
+		} else {
 			tunnel_dst_reset(t);
 			dst_release(dst);
 			dst = NULL;
@@ -362,7 +369,7 @@ static int ip_tunnel_bind_dev(struct net_device *dev)
 
 		if (!IS_ERR(rt)) {
 			tdev = rt->dst.dev;
-			tunnel_dst_set(tunnel, &rt->dst);
+			tunnel_dst_set(tunnel, &rt->dst, fl4.saddr);
 			ip_rt_put(rt);
 		}
 		if (dev->type != ARPHRD_ETHER)
@@ -606,7 +613,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 	init_tunnel_flow(&fl4, protocol, dst, tnl_params->saddr,
 			 tunnel->parms.o_key, RT_TOS(tos), tunnel->parms.link);
 
-	rt = connected ? tunnel_rtable_get(tunnel, 0) : NULL;
+	rt = connected ? tunnel_rtable_get(tunnel, 0, &fl4.saddr) : NULL;
 
 	if (!rt) {
 		rt = ip_route_output_key(tunnel->net, &fl4);
@@ -616,7 +623,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 			goto tx_error;
 		}
 		if (connected)
-			tunnel_dst_set(tunnel, &rt->dst);
+			tunnel_dst_set(tunnel, &rt->dst, fl4.saddr);
 	}
 
 	if (rt->dst.dev == dev) {
diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c
index 8d69626f2206..65b664d30fa1 100644
--- a/net/ipv4/ip_tunnel_core.c
+++ b/net/ipv4/ip_tunnel_core.c
@@ -74,7 +74,7 @@ int iptunnel_xmit(struct rtable *rt, struct sk_buff *skb,
 	iph->daddr	=	dst;
 	iph->saddr	=	src;
 	iph->ttl	=	ttl;
-	__ip_select_ident(iph, &rt->dst, (skb_shinfo(skb)->gso_segs ?: 1) - 1);
+	__ip_select_ident(iph, skb_shinfo(skb)->gso_segs ?: 1);
 
 	err = ip_local_out(skb);
 	if (unlikely(net_xmit_eval(err)))
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 28863570dd60..1149fc2290e2 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -1663,7 +1663,7 @@ 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 c04518f4850a..11c8d81fdc59 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -389,7 +389,7 @@ 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 031553f8a306..ca5a01ed8ed6 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -89,6 +89,7 @@
 #include <linux/rcupdate.h>
 #include <linux/times.h>
 #include <linux/slab.h>
+#include <linux/jhash.h>
 #include <net/dst.h>
 #include <net/net_namespace.h>
 #include <net/protocol.h>
@@ -462,39 +463,45 @@ static struct neighbour *ipv4_neigh_lookup(const struct dst_entry *dst,
 	return neigh_create(&arp_tbl, pkey, dev);
 }
 
-/*
- * 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)
+		delta = prandom_u32_max(now - old);
 
-	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 net *net = dev_net(dst->dev);
-	struct inet_peer *peer;
+	static u32 ip_idents_hashrnd __read_mostly;
+	u32 hash, id;
 
-	peer = inet_getpeer_v4(net->ipv4.peers, iph->daddr, 1);
-	if (peer) {
-		iph->id = htons(inet_getid(peer, more));
-		inet_putpeer(peer);
-		return;
-	}
+	net_get_random_once(&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);
 
@@ -2718,6 +2725,12 @@ 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");
+
+	prandom_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 06cae62bf208..6b1a5fd60598 100644
--- a/net/ipv4/tcp_vegas.c
+++ b/net/ipv4/tcp_vegas.c
@@ -219,7 +219,8 @@ static void tcp_vegas_cong_avoid(struct sock *sk, u32 ack, u32 acked,
 			 * 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 326475a94865..603ad498e18a 100644
--- a/net/ipv4/tcp_veno.c
+++ b/net/ipv4/tcp_veno.c
@@ -145,7 +145,7 @@ static void tcp_veno_cong_avoid(struct sock *sk, u32 ack, u32 acked,
 
 		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 31b18152528f..1f564a1487a3 100644
--- a/net/ipv4/xfrm4_mode_tunnel.c
+++ b/net/ipv4/xfrm4_mode_tunnel.c
@@ -117,12 +117,12 @@ 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/ip6_output.c b/net/ipv6/ip6_output.c
index a62b610307ec..073e5a6fc631 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -537,6 +537,20 @@ static void ip6_copy_metadata(struct sk_buff *to, struct sk_buff *from)
 	skb_copy_secmark(to, from);
 }
 
+static void ipv6_select_ident(struct frag_hdr *fhdr, struct rt6_info *rt)
+{
+	static u32 ip6_idents_hashrnd __read_mostly;
+	u32 hash, id;
+
+	net_get_random_once(&ip6_idents_hashrnd, sizeof(ip6_idents_hashrnd));
+
+	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 *))
 {
 	struct sk_buff *frag;
diff --git a/net/ipv6/output_core.c b/net/ipv6/output_core.c
index b31a01263185..798eb0f79078 100644
--- a/net/ipv6/output_core.c
+++ b/net/ipv6/output_core.c
@@ -7,29 +7,6 @@
 #include <net/ip6_fib.h>
 #include <net/addrconf.h>
 
-void ipv6_select_ident(struct frag_hdr *fhdr, struct rt6_info *rt)
-{
-	static atomic_t ipv6_fragmentation_id;
-	int ident;
-
-#if IS_ENABLED(CONFIG_IPV6)
-	if (rt && !(rt->dst.flags & DST_NOPEER)) {
-		struct inet_peer *peer;
-		struct net *net;
-
-		net = dev_net(rt->dst.dev);
-		peer = inet_getpeer_v6(net->ipv6.peers, &rt->rt6i_dst.addr, 1);
-		if (peer) {
-			fhdr->identification = htonl(inet_getid(peer, 0));
-			inet_putpeer(peer);
-			return;
-		}
-	}
-#endif
-	ident = atomic_inc_return(&ipv6_fragmentation_id);
-	fhdr->identification = htonl(ident);
-}
-EXPORT_SYMBOL(ipv6_select_ident);
 
 int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr)
 {
diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c
index c47444e4cf8c..7f0e1cf2d7e8 100644
--- a/net/netfilter/ipvs/ip_vs_xmit.c
+++ b/net/netfilter/ipvs/ip_vs_xmit.c
@@ -883,7 +883,7 @@ 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 a4d570126f5d..5d97d8fe4be7 100644
--- a/net/sctp/associola.c
+++ b/net/sctp/associola.c
@@ -1151,6 +1151,7 @@ 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 0f4d15fc2627..8267b06c3646 100644
--- a/net/sctp/output.c
+++ b/net/sctp/output.c
@@ -599,7 +599,7 @@ out:
 	return err;
 no_route:
 	kfree_skb(nskb);
-	IP_INC_STATS_BH(sock_net(asoc->base.sk), IPSTATS_MIB_OUTNOROUTES);
+	IP_INC_STATS(sock_net(asoc->base.sk), IPSTATS_MIB_OUTNOROUTES);
 
 	/* FIXME: Returning the 'err' will effect all the associations
 	 * associated with a socket, although only one of the paths of the
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index b10d04fa3933..3bea4ddc699d 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -176,9 +176,7 @@ static int verify_newsa_info(struct xfrm_usersa_info *p,
 		    attrs[XFRMA_ALG_AEAD]	||
 		    attrs[XFRMA_ALG_CRYPT]	||
 		    attrs[XFRMA_ALG_COMP]	||
-		    attrs[XFRMA_TFCPAD]		||
-		    (ntohl(p->id.spi) >= 0x10000))
-
+		    attrs[XFRMA_TFCPAD])
 			goto out;
 		break;
 
@@ -206,7 +204,8 @@ static int verify_newsa_info(struct xfrm_usersa_info *p,
 		    attrs[XFRMA_ALG_AUTH]	||
 		    attrs[XFRMA_ALG_AUTH_TRUNC]	||
 		    attrs[XFRMA_ALG_CRYPT]	||
-		    attrs[XFRMA_TFCPAD])
+		    attrs[XFRMA_TFCPAD]		||
+		    (ntohl(p->id.spi) >= 0x10000))
 			goto out;
 		break;
 
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

Powered by blists - more mailing lists