diff --git a/Makefile b/Makefile index dd03fa5777a0..36f0913bd1d6 100644 --- a/Makefile +++ b/Makefile @@ -1,6 +1,6 @@ VERSION = 3 PATCHLEVEL = 4 -SUBLEVEL = 102 +SUBLEVEL = 103 EXTRAVERSION = NAME = Saber-toothed Squirrel diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h index 656de8bc0ed6..cd24caf1732d 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 f0d6a9700f4c..1a4bb971e06d 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 435e406fdec3..1beaf60a5f78 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 bb2886ac1df3..bbf7e955cb19 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 d97f3eb72e06..085c60fd4b6b 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 dae85bc2eda5..a3c3a5bcd126 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 0aed75653b50..e993fc8d7c66 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 1fe0429b6314..1387acafc62c 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 7f8238f4f954..7eb24bddf268 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 f4e84f3440dd..41530193e6d6 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/drivers/net/macvlan.c b/drivers/net/macvlan.c index c4bb95b051f3..6749acf6f3f4 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 8327cc596c34..9f047a04215e 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 542668292900..7179f72b11ea 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/tty/serial/sunsab.c b/drivers/tty/serial/sunsab.c index f0d93eb7e6ec..c9549aa135b2 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/net/inetpeer.h b/include/net/inetpeer.h index 2d643649f0f8..168d30dfe807 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 6d6b12f4753c..34d004892143 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -264,9 +264,10 @@ 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); @@ -276,24 +277,20 @@ 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 4dccfe3bf731..e8ee3bb1b1ca 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 fa7af9183dc9..117eaa578d0d 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -392,14 +392,19 @@ 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 c2e542b27a5a..b1c3d1c63c4e 100644 --- a/include/net/secure_seq.h +++ b/include/net/secure_seq.h @@ -3,8 +3,6 @@ #include -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/net/compat.c b/net/compat.c index 93f542335e19..2c774d889d39 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 7fd34a56aeb3..d1628b79286b 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 99b2596531bb..6ecbd58418b3 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 8de819475378..728f49babfe0 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 3f0bb3b3819d..782467708c10 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 d63a9268cff6..db1b6a73e0ff 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_output.c b/net/ipv4/ip_output.c index d6407b563fd8..7827436ae843 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 94cd1ef1e319..5ccef6e06dc5 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 48c6ebcb7fe0..c1b3970caa68 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 90bc88bbd2a4..fd6843371f2e 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1341,46 +1341,53 @@ 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); @@ -3009,7 +3016,6 @@ 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; @@ -3441,6 +3447,12 @@ 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 80fa2bfd7ede..c042e529a11e 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 ac43cd747bce..b4d1858be550 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 938553efbf8e..5531eb2a56a5 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/ip6_output.c b/net/ipv6/ip6_output.c index 6225b7cf12b9..2bf7916c816f 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -599,22 +599,19 @@ 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/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index ec78ab63dd46..559d307163b1 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 25b207b3ffe4..da54d2922f51 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 cf3e22c586a6..5bd9aa93139d 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