diff options
98 files changed, 1270 insertions, 667 deletions
diff --git a/Documentation/input/multi-touch-protocol.txt b/Documentation/input/multi-touch-protocol.txt index 8490480ce432..c0fc1c75fd88 100644 --- a/Documentation/input/multi-touch-protocol.txt +++ b/Documentation/input/multi-touch-protocol.txt @@ -68,6 +68,22 @@ like: SYN_MT_REPORT SYN_REPORT +Here is the sequence after lifting one of the fingers: + + ABS_MT_POSITION_X + ABS_MT_POSITION_Y + SYN_MT_REPORT + SYN_REPORT + +And here is the sequence after lifting the remaining finger: + + SYN_MT_REPORT + SYN_REPORT + +If the driver reports one of BTN_TOUCH or ABS_PRESSURE in addition to the +ABS_MT events, the last SYN_MT_REPORT event may be omitted. Otherwise, the +last SYN_REPORT will be dropped by the input core, resulting in no +zero-finger event reaching userland. Event Semantics --------------- @@ -217,11 +233,6 @@ where examples can be found. difference between the contact position and the approaching tool position could be used to derive tilt. [2] The list can of course be extended. -[3] The multi-touch X driver is currently in the prototyping stage. At the -time of writing (April 2009), the MT protocol is not yet merged, and the -prototype implements finger matching, basic mouse support and two-finger -scrolling. The project aims at improving the quality of current multi-touch -functionality available in the Synaptics X driver, and in addition -implement more advanced gestures. +[3] Multitouch X driver project: http://bitmath.org/code/multitouch/. [4] See the section on event computation. [5] See the section on finger tracking. diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index e4cbca58536c..e2202e93b148 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -320,11 +320,6 @@ and is between 256 and 4096 characters. It is defined in the file amd_iommu= [HW,X86-84] Pass parameters to the AMD IOMMU driver in the system. Possible values are: - isolate - enable device isolation (each device, as far - as possible, will get its own protection - domain) [default] - share - put every device behind one IOMMU into the - same protection domain fullflush - enable flushing of IO/TLB entries when they are unmapped. Otherwise they are flushed before they will be reused, which diff --git a/Documentation/networking/timestamping.txt b/Documentation/networking/timestamping.txt index 0e58b4539176..e8c8f4f06c67 100644 --- a/Documentation/networking/timestamping.txt +++ b/Documentation/networking/timestamping.txt @@ -41,11 +41,12 @@ SOF_TIMESTAMPING_SOFTWARE: return system time stamp generated in SOF_TIMESTAMPING_TX/RX determine how time stamps are generated. SOF_TIMESTAMPING_RAW/SYS determine how they are reported in the following control message: - struct scm_timestamping { - struct timespec systime; - struct timespec hwtimetrans; - struct timespec hwtimeraw; - }; + +struct scm_timestamping { + struct timespec systime; + struct timespec hwtimetrans; + struct timespec hwtimeraw; +}; recvmsg() can be used to get this control message for regular incoming packets. For send time stamps the outgoing packet is looped back to @@ -87,12 +88,13 @@ by the network device and will be empty without that support. SIOCSHWTSTAMP: Hardware time stamping must also be initialized for each device driver -that is expected to do hardware time stamping. The parameter is: +that is expected to do hardware time stamping. The parameter is defined in +/include/linux/net_tstamp.h as: struct hwtstamp_config { - int flags; /* no flags defined right now, must be zero */ - int tx_type; /* HWTSTAMP_TX_* */ - int rx_filter; /* HWTSTAMP_FILTER_* */ + int flags; /* no flags defined right now, must be zero */ + int tx_type; /* HWTSTAMP_TX_* */ + int rx_filter; /* HWTSTAMP_FILTER_* */ }; Desired behavior is passed into the kernel and to a specific device by @@ -139,42 +141,56 @@ enum { /* time stamp any incoming packet */ HWTSTAMP_FILTER_ALL, - /* return value: time stamp all packets requested plus some others */ - HWTSTAMP_FILTER_SOME, + /* return value: time stamp all packets requested plus some others */ + HWTSTAMP_FILTER_SOME, /* PTP v1, UDP, any kind of event packet */ HWTSTAMP_FILTER_PTP_V1_L4_EVENT, - ... + /* for the complete list of values, please check + * the include file /include/linux/net_tstamp.h + */ }; DEVICE IMPLEMENTATION A driver which supports hardware time stamping must support the -SIOCSHWTSTAMP ioctl. Time stamps for received packets must be stored -in the skb with skb_hwtstamp_set(). +SIOCSHWTSTAMP ioctl and update the supplied struct hwtstamp_config with +the actual values as described in the section on SIOCSHWTSTAMP. + +Time stamps for received packets must be stored in the skb. To get a pointer +to the shared time stamp structure of the skb call skb_hwtstamps(). Then +set the time stamps in the structure: + +struct skb_shared_hwtstamps { + /* hardware time stamp transformed into duration + * since arbitrary point in time + */ + ktime_t hwtstamp; + ktime_t syststamp; /* hwtstamp transformed to system time base */ +}; Time stamps for outgoing packets are to be generated as follows: -- In hard_start_xmit(), check if skb_hwtstamp_check_tx_hardware() - returns non-zero. If yes, then the driver is expected - to do hardware time stamping. +- In hard_start_xmit(), check if skb_tx(skb)->hardware is set no-zero. + If yes, then the driver is expected to do hardware time stamping. - If this is possible for the skb and requested, then declare - that the driver is doing the time stamping by calling - skb_hwtstamp_tx_in_progress(). A driver not supporting - hardware time stamping doesn't do that. A driver must never - touch sk_buff::tstamp! It is used to store how time stamping - for an outgoing packets is to be done. + that the driver is doing the time stamping by setting the field + skb_tx(skb)->in_progress non-zero. You might want to keep a pointer + to the associated skb for the next step and not free the skb. A driver + not supporting hardware time stamping doesn't do that. A driver must + never touch sk_buff::tstamp! It is used to store software generated + time stamps by the network subsystem. - As soon as the driver has sent the packet and/or obtained a hardware time stamp for it, it passes the time stamp back by calling skb_hwtstamp_tx() with the original skb, the raw - hardware time stamp and a handle to the device (necessary - to convert the hardware time stamp to system time). If obtaining - the hardware time stamp somehow fails, then the driver should - not fall back to software time stamping. The rationale is that - this would occur at a later time in the processing pipeline - than other software time stamping and therefore could lead - to unexpected deltas between time stamps. -- If the driver did not call skb_hwtstamp_tx_in_progress(), then + hardware time stamp. skb_hwtstamp_tx() clones the original skb and + adds the timestamps, therefore the original skb has to be freed now. + If obtaining the hardware time stamp somehow fails, then the driver + should not fall back to software time stamping. The rationale is that + this would occur at a later time in the processing pipeline than other + software time stamping and therefore could lead to unexpected deltas + between time stamps. +- If the driver did not call set skb_tx(skb)->in_progress, then dev_hard_start_xmit() checks whether software time stamping is wanted as fallback and potentially generates the time stamp. diff --git a/MAINTAINERS b/MAINTAINERS index 5b422908d0f3..a0e3c3a47a51 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -485,8 +485,8 @@ S: Maintained F: drivers/input/mouse/bcm5974.c APPLE SMC DRIVER -M: Nicolas Boichat <nicolas@boichat.ch> -L: mactel-linux-devel@lists.sourceforge.net +M: Henrik Rydberg <rydberg@euromail.se> +L: lm-sensors@lm-sensors.org S: Maintained F: drivers/hwmon/applesmc.c diff --git a/arch/m68k/include/asm/atomic_mm.h b/arch/m68k/include/asm/atomic_mm.h index 88b7af20a996..d9d2ed647435 100644 --- a/arch/m68k/include/asm/atomic_mm.h +++ b/arch/m68k/include/asm/atomic_mm.h @@ -148,14 +148,18 @@ static inline int atomic_xchg(atomic_t *v, int new) static inline int atomic_sub_and_test(int i, atomic_t *v) { char c; - __asm__ __volatile__("subl %2,%1; seq %0" : "=d" (c), "+m" (*v): "g" (i)); + __asm__ __volatile__("subl %2,%1; seq %0" + : "=d" (c), "+m" (*v) + : "id" (i)); return c != 0; } static inline int atomic_add_negative(int i, atomic_t *v) { char c; - __asm__ __volatile__("addl %2,%1; smi %0" : "=d" (c), "+m" (*v): "g" (i)); + __asm__ __volatile__("addl %2,%1; smi %0" + : "=d" (c), "+m" (*v) + : "id" (i)); return c != 0; } diff --git a/arch/m68k/include/asm/sigcontext.h b/arch/m68k/include/asm/sigcontext.h index 1320eaa4cc2a..a29dd74a17cb 100644 --- a/arch/m68k/include/asm/sigcontext.h +++ b/arch/m68k/include/asm/sigcontext.h @@ -17,13 +17,11 @@ struct sigcontext { #ifndef __uClinux__ # ifdef __mcoldfire__ unsigned long sc_fpregs[2][2]; /* room for two fp registers */ - unsigned long sc_fpcntl[3]; - unsigned char sc_fpstate[16+6*8]; # else unsigned long sc_fpregs[2*3]; /* room for two fp registers */ +# endif unsigned long sc_fpcntl[3]; unsigned char sc_fpstate[216]; -# endif #endif }; diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index 6db513674050..9908d477ccd9 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -37,6 +37,9 @@ config SPARC64 def_bool 64BIT select ARCH_SUPPORTS_MSI select HAVE_FUNCTION_TRACER + select HAVE_FUNCTION_GRAPH_TRACER + select HAVE_FUNCTION_GRAPH_FP_TEST + select HAVE_FUNCTION_TRACE_MCOUNT_TEST select HAVE_KRETPROBES select HAVE_KPROBES select HAVE_LMB diff --git a/arch/sparc/Kconfig.debug b/arch/sparc/Kconfig.debug index 9d3c889718ac..1b4a831565f9 100644 --- a/arch/sparc/Kconfig.debug +++ b/arch/sparc/Kconfig.debug @@ -19,13 +19,10 @@ config DEBUG_DCFLUSH bool "D-cache flush debugging" depends on SPARC64 && DEBUG_KERNEL -config STACK_DEBUG - bool "Stack Overflow Detection Support" - config MCOUNT bool depends on SPARC64 - depends on STACK_DEBUG || FUNCTION_TRACER + depends on FUNCTION_TRACER default y config FRAME_POINTER diff --git a/arch/sparc/include/asm/cpudata_64.h b/arch/sparc/include/asm/cpudata_64.h index 926397d345ff..050ef35b9dcf 100644 --- a/arch/sparc/include/asm/cpudata_64.h +++ b/arch/sparc/include/asm/cpudata_64.h @@ -17,7 +17,7 @@ typedef struct { unsigned int __nmi_count; unsigned long clock_tick; /* %tick's per second */ unsigned long __pad; - unsigned int __pad1; + unsigned int irq0_irqs; unsigned int __pad2; /* Dcache line 2, rarely used */ diff --git a/arch/sparc/include/asm/irqflags_64.h b/arch/sparc/include/asm/irqflags_64.h index 8b49bf920df3..bfa1ea45b4cd 100644 --- a/arch/sparc/include/asm/irqflags_64.h +++ b/arch/sparc/include/asm/irqflags_64.h @@ -76,9 +76,26 @@ static inline int raw_irqs_disabled(void) */ static inline unsigned long __raw_local_irq_save(void) { - unsigned long flags = __raw_local_save_flags(); - - raw_local_irq_disable(); + unsigned long flags, tmp; + + /* Disable interrupts to PIL_NORMAL_MAX unless we already + * are using PIL_NMI, in which case PIL_NMI is retained. + * + * The only values we ever program into the %pil are 0, + * PIL_NORMAL_MAX and PIL_NMI. + * + * Since PIL_NMI is the largest %pil value and all bits are + * set in it (0xf), it doesn't matter what PIL_NORMAL_MAX + * actually is. + */ + __asm__ __volatile__( + "rdpr %%pil, %0\n\t" + "or %0, %2, %1\n\t" + "wrpr %1, 0x0, %%pil" + : "=r" (flags), "=r" (tmp) + : "i" (PIL_NORMAL_MAX) + : "memory" + ); return flags; } diff --git a/arch/sparc/kernel/Makefile b/arch/sparc/kernel/Makefile index c6316142db4e..0c2dc1f24a9a 100644 --- a/arch/sparc/kernel/Makefile +++ b/arch/sparc/kernel/Makefile @@ -13,6 +13,14 @@ extra-y += init_task.o CPPFLAGS_vmlinux.lds := -Usparc -m$(BITS) extra-y += vmlinux.lds +ifdef CONFIG_FUNCTION_TRACER +# Do not profile debug and lowlevel utilities +CFLAGS_REMOVE_ftrace.o := -pg +CFLAGS_REMOVE_time_$(BITS).o := -pg +CFLAGS_REMOVE_perf_event.o := -pg +CFLAGS_REMOVE_pcr.o := -pg +endif + obj-$(CONFIG_SPARC32) += entry.o wof.o wuf.o obj-$(CONFIG_SPARC32) += etrap_32.o obj-$(CONFIG_SPARC32) += rtrap_32.o @@ -85,7 +93,7 @@ obj-$(CONFIG_KGDB) += kgdb_$(BITS).o obj-$(CONFIG_DYNAMIC_FTRACE) += ftrace.o -CFLAGS_REMOVE_ftrace.o := -pg +obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o obj-$(CONFIG_EARLYFB) += btext.o obj-$(CONFIG_STACKTRACE) += stacktrace.o diff --git a/arch/sparc/kernel/ftrace.c b/arch/sparc/kernel/ftrace.c index 9103a56b39e8..03ab022e51c5 100644 --- a/arch/sparc/kernel/ftrace.c +++ b/arch/sparc/kernel/ftrace.c @@ -13,7 +13,7 @@ static const u32 ftrace_nop = 0x01000000; static u32 ftrace_call_replace(unsigned long ip, unsigned long addr) { - static u32 call; + u32 call; s32 off; off = ((s32)addr - (s32)ip); @@ -91,3 +91,61 @@ int __init ftrace_dyn_arch_init(void *data) return 0; } #endif + +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + +#ifdef CONFIG_DYNAMIC_FTRACE +extern void ftrace_graph_call(void); + +int ftrace_enable_ftrace_graph_caller(void) +{ + unsigned long ip = (unsigned long)(&ftrace_graph_call); + u32 old, new; + + old = *(u32 *) &ftrace_graph_call; + new = ftrace_call_replace(ip, (unsigned long) &ftrace_graph_caller); + return ftrace_modify_code(ip, old, new); +} + +int ftrace_disable_ftrace_graph_caller(void) +{ + unsigned long ip = (unsigned long)(&ftrace_graph_call); + u32 old, new; + + old = *(u32 *) &ftrace_graph_call; + new = ftrace_call_replace(ip, (unsigned long) &ftrace_stub); + + return ftrace_modify_code(ip, old, new); +} + +#endif /* !CONFIG_DYNAMIC_FTRACE */ + +/* + * Hook the return address and push it in the stack of return addrs + * in current thread info. + */ +unsigned long prepare_ftrace_return(unsigned long parent, + unsigned long self_addr, + unsigned long frame_pointer) +{ + unsigned long return_hooker = (unsigned long) &return_to_handler; + struct ftrace_graph_ent trace; + + if (unlikely(atomic_read(¤t->tracing_graph_pause))) + return parent + 8UL; + + if (ftrace_push_return_trace(parent, self_addr, &trace.depth, + frame_pointer) == -EBUSY) + return parent + 8UL; + + trace.func = self_addr; + + /* Only trace if the calling function expects to */ + if (!ftrace_graph_entry(&trace)) { + current->curr_ret_stack--; + return parent + 8UL; + } + + return return_hooker; +} +#endif /* CONFIG_FUNCTION_GRAPH_TRACER */ diff --git a/arch/sparc/kernel/irq_64.c b/arch/sparc/kernel/irq_64.c index e1cbdb94d97b..454ce3a25273 100644 --- a/arch/sparc/kernel/irq_64.c +++ b/arch/sparc/kernel/irq_64.c @@ -20,6 +20,7 @@ #include <linux/delay.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> +#include <linux/ftrace.h> #include <linux/irq.h> #include <asm/ptrace.h> @@ -647,6 +648,14 @@ unsigned int sun4v_build_virq(u32 devhandle, unsigned int devino) bucket = kzalloc(sizeof(struct ino_bucket), GFP_ATOMIC); if (unlikely(!bucket)) return 0; + + /* The only reference we store to the IRQ bucket is + * by physical address which kmemleak can't see, tell + * it that this object explicitly is not a leak and + * should be scanned. + */ + kmemleak_not_leak(bucket); + __flush_dcache_range((unsigned long) bucket, ((unsigned long) bucket + sizeof(struct ino_bucket))); @@ -721,7 +730,7 @@ static __attribute__((always_inline)) void restore_hardirq_stack(void *orig_sp) __asm__ __volatile__("mov %0, %%sp" : : "r" (orig_sp)); } -void handler_irq(int irq, struct pt_regs *regs) +void __irq_entry handler_irq(int irq, struct pt_regs *regs) { unsigned long pstate, bucket_pa; struct pt_regs *old_regs; diff --git a/arch/sparc/kernel/kgdb_64.c b/arch/sparc/kernel/kgdb_64.c index f5a0fd490b59..0a2bd0f99fc1 100644 --- a/arch/sparc/kernel/kgdb_64.c +++ b/arch/sparc/kernel/kgdb_64.c @@ -5,6 +5,7 @@ #include <linux/kgdb.h> #include <linux/kdebug.h> +#include <linux/ftrace.h> #include <asm/kdebug.h> #include <asm/ptrace.h> @@ -108,7 +109,7 @@ void gdb_regs_to_pt_regs(unsigned long *gdb_regs, struct pt_regs *regs) } #ifdef CONFIG_SMP -void smp_kgdb_capture_client(int irq, struct pt_regs *regs) +void __irq_entry smp_kgdb_capture_client(int irq, struct pt_regs *regs) { unsigned long flags; diff --git a/arch/sparc/kernel/nmi.c b/arch/sparc/kernel/nmi.c index b287b62c7ea3..75a3d1a25356 100644 --- a/arch/sparc/kernel/nmi.c +++ b/arch/sparc/kernel/nmi.c @@ -92,7 +92,6 @@ static void die_nmi(const char *str, struct pt_regs *regs, int do_panic) notrace __kprobes void perfctr_irq(int irq, struct pt_regs *regs) { unsigned int sum, touched = 0; - int cpu = smp_processor_id(); clear_softint(1 << irq); @@ -106,7 +105,7 @@ notrace __kprobes void perfctr_irq(int irq, struct pt_regs *regs) else pcr_ops->write(PCR_PIC_PRIV); - sum = kstat_irqs_cpu(0, cpu); + sum = local_cpu_data().irq0_irqs; if (__get_cpu_var(nmi_touch)) { __get_cpu_var(nmi_touch) = 0; touched = 1; diff --git a/arch/sparc/kernel/pci_common.c b/arch/sparc/kernel/pci_common.c index b775658a927d..8a000583b5cf 100644 --- a/arch/sparc/kernel/pci_common.c +++ b/arch/sparc/kernel/pci_common.c @@ -371,14 +371,19 @@ static void pci_register_iommu_region(struct pci_pbm_info *pbm) struct resource *rp = kzalloc(sizeof(*rp), GFP_KERNEL); if (!rp) { - prom_printf("Cannot allocate IOMMU resource.\n"); - prom_halt(); + pr_info("%s: Cannot allocate IOMMU resource.\n", + pbm->name); + return; } rp->name = "IOMMU"; rp->start = pbm->mem_space.start + (unsigned long) vdma[0]; rp->end = rp->start + (unsigned long) vdma[1] - 1UL; rp->flags = IORESOURCE_BUSY; - request_resource(&pbm->mem_space, rp); + if (request_resource(&pbm->mem_space, rp)) { + pr_info("%s: Unable to request IOMMU resource.\n", + pbm->name); + kfree(rp); + } } } diff --git a/arch/sparc/kernel/pcr.c b/arch/sparc/kernel/pcr.c index 2d94e7a03af5..c4a6a50b4849 100644 --- a/arch/sparc/kernel/pcr.c +++ b/arch/sparc/kernel/pcr.c @@ -8,6 +8,7 @@ #include <linux/irq.h> #include <linux/perf_event.h> +#include <linux/ftrace.h> #include <asm/pil.h> #include <asm/pcr.h> @@ -34,7 +35,7 @@ unsigned int picl_shift; * Therefore in such situations we defer the work by signalling * a lower level cpu IRQ. */ -void deferred_pcr_work_irq(int irq, struct pt_regs *regs) +void __irq_entry deferred_pcr_work_irq(int irq, struct pt_regs *regs) { struct pt_regs *old_regs; diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c index 4c5334528109..b6a2b8f47040 100644 --- a/arch/sparc/kernel/smp_64.c +++ b/arch/sparc/kernel/smp_64.c @@ -22,6 +22,7 @@ #include <linux/profile.h> #include <linux/bootmem.h> #include <linux/vmalloc.h> +#include <linux/ftrace.h> #include <linux/cpu.h> #include <linux/slab.h> @@ -823,13 +824,13 @@ void arch_send_call_function_single_ipi(int cpu) &cpumask_of_cpu(cpu)); } -void smp_call_function_client(int irq, struct pt_regs *regs) +void __irq_entry smp_call_function_client(int irq, struct pt_regs *regs) { clear_softint(1 << irq); generic_smp_call_function_interrupt(); } -void smp_call_function_single_client(int irq, struct pt_regs *regs) +void __irq_entry smp_call_function_single_client(int irq, struct pt_regs *regs) { clear_softint(1 << irq); generic_smp_call_function_single_interrupt(); @@ -965,7 +966,7 @@ void flush_dcache_page_all(struct mm_struct *mm, struct page *page) put_cpu(); } -void smp_new_mmu_context_version_client(int irq, struct pt_regs *regs) +void __irq_entry smp_new_mmu_context_version_client(int irq, struct pt_regs *regs) { struct mm_struct *mm; unsigned long flags; @@ -1149,7 +1150,7 @@ void smp_release(void) */ extern void prom_world(int); -void smp_penguin_jailcell(int irq, struct pt_regs *regs) +void __irq_entry smp_penguin_jailcell(int irq, struct pt_regs *regs) { clear_softint(1 << irq); @@ -1365,7 +1366,7 @@ void smp_send_reschedule(int cpu) &cpumask_of_cpu(cpu)); } -void smp_receive_signal_client(int irq, struct pt_regs *regs) +void __irq_entry smp_receive_signal_client(int irq, struct pt_regs *regs) { clear_softint(1 << irq); } diff --git a/arch/sparc/kernel/time_64.c b/arch/sparc/kernel/time_64.c index 67e165102885..c7bbe6cf7b85 100644 --- a/arch/sparc/kernel/time_64.c +++ b/arch/sparc/kernel/time_64.c @@ -35,6 +35,7 @@ #include <linux/clocksource.h> #include <linux/of_device.h> #include <linux/platform_device.h> +#include <linux/ftrace.h> #include <asm/oplib.h> #include <asm/timer.h> @@ -717,7 +718,7 @@ static struct clock_event_device sparc64_clockevent = { }; static DEFINE_PER_CPU(struct clock_event_device, sparc64_events); -void timer_interrupt(int irq, struct pt_regs *regs) +void __irq_entry timer_interrupt(int irq, struct pt_regs *regs) { struct pt_regs *old_regs = set_irq_regs(regs); unsigned long tick_mask = tick_ops->softint_mask; @@ -728,6 +729,7 @@ void timer_interrupt(int irq, struct pt_regs *regs) irq_enter(); + local_cpu_data().irq0_irqs++; kstat_incr_irqs_this_cpu(0, irq_to_desc(0)); if (unlikely(!evt->event_handler)) { diff --git a/arch/sparc/kernel/traps_64.c b/arch/sparc/kernel/traps_64.c index 837dfc2390d6..9da57f032983 100644 --- a/arch/sparc/kernel/traps_64.c +++ b/arch/sparc/kernel/traps_64.c @@ -2203,27 +2203,6 @@ void dump_stack(void) EXPORT_SYMBOL(dump_stack); -static inline int is_kernel_stack(struct task_struct *task, - struct reg_window *rw) -{ - unsigned long rw_addr = (unsigned long) rw; - unsigned long thread_base, thread_end; - - if (rw_addr < PAGE_OFFSET) { - if (task != &init_task) - return 0; - } - - thread_base = (unsigned long) task_stack_page(task); - thread_end = thread_base + sizeof(union thread_union); - if (rw_addr >= thread_base && - rw_addr < thread_end && - !(rw_addr & 0x7UL)) - return 1; - - return 0; -} - static inline struct reg_window *kernel_stack_up(struct reg_window *rw) { unsigned long fp = rw->ins[6]; @@ -2252,6 +2231,7 @@ void die_if_kernel(char *str, struct pt_regs *regs) show_regs(regs); add_taint(TAINT_DIE); if (regs->tstate & TSTATE_PRIV) { + struct thread_info *tp = current_thread_info(); struct reg_window *rw = (struct reg_window *) (regs->u_regs[UREG_FP] + STACK_BIAS); @@ -2259,8 +2239,8 @@ void die_if_kernel(char *str, struct pt_regs *regs) * find some badly aligned kernel stack. */ while (rw && - count++ < 30&& - is_kernel_stack(current, rw)) { + count++ < 30 && + kstack_valid(tp, (unsigned long) rw)) { printk("Caller[%016lx]: %pS\n", rw->ins[7], (void *) rw->ins[7]); diff --git a/arch/sparc/kernel/vmlinux.lds.S b/arch/sparc/kernel/vmlinux.lds.S index 4e5992593967..0c1e6783657f 100644 --- a/arch/sparc/kernel/vmlinux.lds.S +++ b/arch/sparc/kernel/vmlinux.lds.S @@ -46,11 +46,16 @@ SECTIONS SCHED_TEXT LOCK_TEXT KPROBES_TEXT + IRQENTRY_TEXT *(.gnu.warning) } = 0 _etext = .; RO_DATA(PAGE_SIZE) + + /* Start of data section */ + _sdata = .; + .data1 : { *(.data1) } diff --git a/arch/sparc/lib/mcount.S b/arch/sparc/lib/mcount.S index 24b8b12deed2..3753e3c6e176 100644 --- a/arch/sparc/lib/mcount.S +++ b/arch/sparc/lib/mcount.S @@ -7,26 +7,11 @@ #include <linux/linkage.h> -#include <asm/ptrace.h> -#include <asm/thread_info.h> - /* * This is the main variant and is called by C code. GCC's -pg option * automatically instruments every C function with a call to this. */ -#ifdef CONFIG_STACK_DEBUG - -#define OVSTACKSIZE 4096 /* lets hope this is enough */ - - .data - .align 8 -panicstring: - .asciz "Stack overflow\n" - .align 8 -ovstack: - .skip OVSTACKSIZE -#endif .text .align 32 .globl _mcount @@ -35,84 +20,48 @@ ovstack: .type mcount,#function _mcount: mcount: -#ifdef CONFIG_STACK_DEBUG - /* - * Check whether %sp is dangerously low. - */ - ldub [%g6 + TI_FPDEPTH], %g1 - srl %g1, 1, %g3 - add %g3, 1, %g3 - sllx %g3, 8, %g3 ! each fpregs frame is 256b - add %g3, 192, %g3 - add %g6, %g3, %g3 ! where does task_struct+frame end? - sub %g3, STACK_BIAS, %g3 - cmp %sp, %g3 - bg,pt %xcc, 1f - nop - lduh [%g6 + TI_CPU], %g1 - sethi %hi(hardirq_stack), %g3 - or %g3, %lo(hardirq_stack), %g3 - sllx %g1, 3, %g1 - ldx [%g3 + %g1], %g7 - sub %g7, STACK_BIAS, %g7 - cmp %sp, %g7 - bleu,pt %xcc, 2f - sethi %hi(THREAD_SIZE), %g3 - add %g7, %g3, %g7 - cmp %sp, %g7 - blu,pn %xcc, 1f -2: sethi %hi(softirq_stack), %g3 - or %g3, %lo(softirq_stack), %g3 - ldx [%g3 + %g1], %g7 - sub %g7, STACK_BIAS, %g7 - cmp %sp, %g7 - bleu,pt %xcc, 3f - sethi %hi(THREAD_SIZE), %g3 - add %g7, %g3, %g7 - cmp %sp, %g7 - blu,pn %xcc, 1f - nop - /* If we are already on ovstack, don't hop onto it - * again, we are already trying to output the stack overflow - * message. - */ -3: sethi %hi(ovstack), %g7 ! cant move to panic stack fast enough - or %g7, %lo(ovstack), %g7 - add %g7, OVSTACKSIZE, %g3 - sub %g3, STACK_BIAS + 192, %g3 - sub %g7, STACK_BIAS, %g7 - cmp %sp, %g7 - blu,pn %xcc, 2f - cmp %sp, %g3 - bleu,pn %xcc, 1f - nop -2: mov %g3, %sp - sethi %hi(panicstring), %g3 - call prom_printf - or %g3, %lo(panicstring), %o0 - call prom_halt - nop -1: -#endif #ifdef CONFIG_FUNCTION_TRACER #ifdef CONFIG_DYNAMIC_FTRACE - mov %o7, %o0 - .globl mcount_call -mcount_call: - call ftrace_stub - mov %o0, %o7 + /* Do nothing, the retl/nop below is all we need. */ #else - sethi %hi(ftrace_trace_function), %g1 + sethi %hi(function_trace_stop), %g1 + lduw [%g1 + %lo(function_trace_stop)], %g2 + brnz,pn %g2, 2f + sethi %hi(ftrace_trace_function), %g1 sethi %hi(ftrace_stub), %g2 ldx [%g1 + %lo(ftrace_trace_function)], %g1 or %g2, %lo(ftrace_stub), %g2 cmp %g1, %g2 be,pn %icc, 1f - mov %i7, %o1 - jmpl %g1, %g0 - mov %o7, %o0 + mov %i7, %g3 + save %sp, -128, %sp + mov %g3, %o1 + jmpl %g1, %o7 + mov %i7, %o0 + ret + restore /* not reached */ 1: +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + sethi %hi(ftrace_graph_return), %g1 + ldx [%g1 + %lo(ftrace_graph_return)], %g3 + cmp %g2, %g3 + bne,pn %xcc, 5f + sethi %hi(ftrace_graph_entry_stub), %g2 + sethi %hi(ftrace_graph_entry), %g1 + or %g2, %lo(ftrace_graph_entry_stub), %g2 + ldx [%g1 + %lo(ftrace_graph_entry)], %g1 + cmp %g1, %g2 + be,pt %xcc, 2f + nop +5: mov %i7, %g2 + mov %fp, %g3 + save %sp, -128, %sp + mov %g2, %l0 + ba,pt %xcc, ftrace_graph_caller + mov %g3, %l1 +#endif +2: #endif #endif retl @@ -131,14 +80,50 @@ ftrace_stub: .globl ftrace_caller .type ftrace_caller,#function ftrace_caller: - mov %i7, %o1 - mov %o7, %o0 + sethi %hi(function_trace_stop), %g1 + mov %i7, %g2 + lduw [%g1 + %lo(function_trace_stop)], %g1 + brnz,pn %g1, ftrace_stub + mov %fp, %g3 + save %sp, -128, %sp + mov %g2, %o1 + mov %g2, %l0 + mov %g3, %l1 .globl ftrace_call ftrace_call: call ftrace_stub - mov %o0, %o7 - retl + mov %i7, %o0 +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + .globl ftrace_graph_call +ftrace_graph_call: + call ftrace_stub nop +#endif + ret + restore +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + .size ftrace_graph_call,.-ftrace_graph_call +#endif + .size ftrace_call,.-ftrace_call .size ftrace_caller,.-ftrace_caller #endif #endif + +#ifdef CONFIG_FUNCTION_GRAPH_TRACER +ENTRY(ftrace_graph_caller) + mov %l0, %o0 + mov %i7, %o1 + call prepare_ftrace_return + mov %l1, %o2 + ret + restore %o0, -8, %i7 +END(ftrace_graph_caller) + +ENTRY(return_to_handler) + save %sp, -128, %sp + call ftrace_return_to_handler + mov %fp, %o0 + jmpl %o0 + 8, %g0 + restore +END(return_to_handler) +#endif diff --git a/arch/x86/include/asm/amd_iommu_types.h b/arch/x86/include/asm/amd_iommu_types.h index ba19ad4c47d0..86a0ff0aeac7 100644 --- a/arch/x86/include/asm/amd_iommu_types.h +++ b/arch/x86/include/asm/amd_iommu_types.h @@ -21,6 +21,7 @@ #define _ASM_X86_AMD_IOMMU_TYPES_H #include <linux/types.h> +#include <linux/mutex.h> #include <linux/list.h> #include <linux/spinlock.h> @@ -140,6 +141,7 @@ /* constants to configure the command buffer */ #define CMD_BUFFER_SIZE 8192 +#define CMD_BUFFER_UNINITIALIZED 1 #define CMD_BUFFER_ENTRIES 512 #define MMIO_CMD_SIZE_SHIFT 56 #define MMIO_CMD_SIZE_512 (0x9ULL << MMIO_CMD_SIZE_SHIFT) @@ -237,6 +239,7 @@ struct protection_domain { struct list_head list; /* for list of all protection domains */ struct list_head dev_list; /* List of all devices in this domain */ spinlock_t lock; /* mostly used to lock the page table*/ + struct mutex api_lock; /* protect page tables in the iommu-api path */ u16 id; /* the domain id written to the device table */ int mode; /* paging mode (0-6 levels) */ u64 *pt_root; /* page table root pointer */ diff --git a/arch/x86/include/asm/lguest_hcall.h b/arch/x86/include/asm/lguest_hcall.h index ba0eed8aa1a6..b60f2924c413 100644 --- a/arch/x86/include/asm/lguest_hcall.h +++ b/arch/x86/include/asm/lguest_hcall.h @@ -28,22 +28,39 @@ #ifndef __ASSEMBLY__ #include <asm/hw_irq.h> -#include <asm/kvm_para.h> /*G:030 * But first, how does our Guest contact the Host to ask for privileged * operations? There are two ways: the direct way is to make a "hypercall", * to make requests of the Host Itself. * - * We use the KVM hypercall mechanism, though completely different hypercall - * numbers. Seventeen hypercalls are available: the hypercall number is put in - * the %eax register, and the arguments (when required) are placed in %ebx, - * %ecx, %edx and %esi. If a return value makes sense, it's returned in %eax. + * Our hypercall mechanism uses the highest unused trap code (traps 32 and + * above are used by real hardware interrupts). Seventeen hypercalls are + * available: the hypercall number is put in the %eax register, and the + * arguments (when required) are placed in %ebx, %ecx, %edx and %esi. + * If a return value makes sense, it's returned in %eax. * * Grossly invalid calls result in Sudden Death at the hands of the vengeful * Host, rather than returning failure. This reflects Winston Churchill's * definition of a gentleman: "someone who is only rude intentionally". -:*/ + */ +static inline unsigned long +hcall(unsigned long call, + unsigned long arg1, unsigned long arg2, unsigned long arg3, + unsigned long arg4) +{ + /* "int" is the Intel instruction to trigger a trap. */ + asm volatile("int $" __stringify(LGUEST_TRAP_ENTRY) + /* The call in %eax (aka "a") might be overwritten */ + : "=a"(call) + /* The arguments are in %eax, %ebx, %ecx, %edx & %esi */ + : "a"(call), "b"(arg1), "c"(arg2), "d"(arg3), "S"(arg4) + /* "memory" means this might write somewhere in memory. + * This isn't true for all calls, but it's safe to tell + * gcc that it might happen so it doesn't get clever. */ + : "memory"); + return call; +} /* Can't use our min() macro here: needs to be a constant */ #define LGUEST_IRQS (NR_IRQS < 32 ? NR_IRQS: 32) diff --git a/arch/x86/kernel/amd_iommu.c b/arch/x86/kernel/amd_iommu.c index f3dadb571d9b..f854d89b7edf 100644 --- a/arch/x86/kernel/amd_iommu.c +++ b/arch/x86/kernel/amd_iommu.c @@ -118,7 +118,7 @@ static bool check_device(struct device *dev) return false; /* No device or no PCI device */ - if (!dev || dev->bus != &pci_bus_type) + if (dev->bus != &pci_bus_type) return false; devid = get_device_id(dev); @@ -392,6 +392,7 @@ static int __iommu_queue_command(struct amd_iommu *iommu, struct iommu_cmd *cmd) u32 tail, head; u8 *target; + WARN_ON(iommu->cmd_buf_size & CMD_BUFFER_UNINITIALIZED); tail = readl(iommu->mmio_base + MMIO_CMD_TAIL_OFFSET); target = iommu->cmd_buf + tail; memcpy_toio(target, cmd, sizeof(*cmd)); @@ -2186,7 +2187,7 @@ static void prealloc_protection_domains(void) struct dma_ops_domain *dma_dom; u16 devid; - while ((dev = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, dev)) != NULL) { + for_each_pci_dev(dev) { /* Do we handle this device? */ if (!check_device(&dev->dev)) @@ -2298,7 +2299,7 @@ static void cleanup_domain(struct protection_domain *domain) list_for_each_entry_safe(dev_data, next, &domain->dev_list, list) { struct device *dev = dev_data->dev; - do_detach(dev); + __detach_device(dev); atomic_set(&dev_data->bind, 0); } @@ -2327,6 +2328,7 @@ static struct protection_domain *protection_domain_alloc(void) return NULL; spin_lock_init(&domain->lock); + mutex_init(&domain->api_lock); domain->id = domain_id_alloc(); if (!domain->id) goto out_err; @@ -2379,9 +2381,7 @@ static void amd_iommu_domain_destroy(struct iommu_domain *dom) free_pagetable(domain); - domain_id_free(domain->id); - - kfree(domain); + protection_domain_free(domain); dom->priv = NULL; } @@ -2456,6 +2456,8 @@ static int amd_iommu_map_range(struct iommu_domain *dom, iova &= PAGE_MASK; paddr &= PAGE_MASK; + mutex_lock(&domain->api_lock); + for (i = 0; i < npages; ++i) { ret = iommu_map_page(domain, iova, paddr, prot, PM_MAP_4k); if (ret) @@ -2465,6 +2467,8 @@ static int amd_iommu_map_range(struct iommu_domain *dom, paddr += PAGE_SIZE; } + mutex_unlock(&domain->api_lock); + return 0; } @@ -2477,12 +2481,16 @@ static void amd_iommu_unmap_range(struct iommu_domain *dom, iova &= PAGE_MASK; + mutex_lock(&domain->api_lock); + for (i = 0; i < npages; ++i) { iommu_unmap_page(domain, iova, PM_MAP_4k); iova += PAGE_SIZE; } iommu_flush_tlb_pde(domain); + + mutex_unlock(&domain->api_lock); } static phys_addr_t amd_iommu_iova_to_phys(struct iommu_domain *dom, diff --git a/arch/x86/kernel/amd_iommu_init.c b/arch/x86/kernel/amd_iommu_init.c index 42f5350b908f..6360abf993d4 100644 --- a/arch/x86/kernel/amd_iommu_init.c +++ b/arch/x86/kernel/amd_iommu_init.c @@ -138,9 +138,9 @@ int amd_iommus_present; bool amd_iommu_np_cache __read_mostly; /* - * Set to true if ACPI table parsing and hardware intialization went properly + * The ACPI table parsing functions set this variable on an error */ -static bool amd_iommu_initialized; +static int __initdata amd_iommu_init_err; /* * List of protection domains - used during resume @@ -391,9 +391,11 @@ static int __init find_last_devid_acpi(struct acpi_table_header *table) */ for (i = 0; i < table->length; ++i) checksum += p[i]; - if (checksum != 0) + if (checksum != 0) { /* ACPI table corrupt */ - return -ENODEV; + amd_iommu_init_err = -ENODEV; + return 0; + } p += IVRS_HEADER_LENGTH; @@ -436,7 +438,7 @@ static u8 * __init alloc_command_buffer(struct amd_iommu *iommu) if (cmd_buf == NULL) return NULL; - iommu->cmd_buf_size = CMD_BUFFER_SIZE; + iommu->cmd_buf_size = CMD_BUFFER_SIZE | CMD_BUFFER_UNINITIALIZED; return cmd_buf; } @@ -472,12 +474,13 @@ static void iommu_enable_command_buffer(struct amd_iommu *iommu) &entry, sizeof(entry)); amd_iommu_reset_cmd_buffer(iommu); + iommu->cmd_buf_size &= ~(CMD_BUFFER_UNINITIALIZED); } static void __init free_command_buffer(struct amd_iommu *iommu) { free_pages((unsigned long)iommu->cmd_buf, - get_order(iommu->cmd_buf_size)); + get_order(iommu->cmd_buf_size & ~(CMD_BUFFER_UNINITIALIZED))); } /* allocates the memory where the IOMMU will log its events to */ @@ -920,11 +923,16 @@ static int __init init_iommu_all(struct acpi_table_header *table) h->mmio_phys); iommu = kzalloc(sizeof(struct amd_iommu), GFP_KERNEL); - if (iommu == NULL) - return -ENOMEM; + if (iommu == NULL) { + amd_iommu_init_err = -ENOMEM; + return 0; + } + ret = init_iommu_one(iommu, h); - if (ret) - return ret; + if (ret) { + amd_iommu_init_err = ret; + return 0; + } break; default: break; @@ -934,8 +942,6 @@ static int __init init_iommu_all(struct acpi_table_header *table) } WARN_ON(p != end); - amd_iommu_initialized = true; - return 0; } @@ -1211,6 +1217,10 @@ static int __init amd_iommu_init(void) if (acpi_table_parse("IVRS", find_last_devid_acpi) != 0) return -ENODEV; + ret = amd_iommu_init_err; + if (ret) + goto out; + dev_table_size = tbl_size(DEV_TABLE_ENTRY_SIZE); alias_table_size = tbl_size(ALIAS_TABLE_ENTRY_SIZE); rlookup_table_size = tbl_size(RLOOKUP_TABLE_ENTRY_SIZE); @@ -1270,12 +1280,19 @@ static int __init amd_iommu_init(void) if (acpi_table_parse("IVRS", init_iommu_all) != 0) goto free; - if (!amd_iommu_initialized) + if (amd_iommu_init_err) { + ret = amd_iommu_init_err; goto free; + } if (acpi_table_parse("IVRS", init_memory_definitions) != 0) goto free; + if (amd_iommu_init_err) { + ret = amd_iommu_init_err; + goto free; + } + ret = sysdev_class_register(&amd_iommu_sysdev_class); if (ret) goto free; @@ -1288,6 +1305,8 @@ static int __init amd_iommu_init(void) if (ret) goto free; + enable_iommus(); + if (iommu_pass_through) ret = amd_iommu_init_passthrough(); else @@ -1300,8 +1319,6 @@ static int __init amd_iommu_init(void) amd_iommu_init_notifier(); - enable_iommus(); - if (iommu_pass_through) goto out; @@ -1315,6 +1332,7 @@ out: return ret; free: + disable_iommus(); amd_iommu_uninit_devices(); diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c index 3704997e8b25..b5d8b0bcf235 100644 --- a/arch/x86/kernel/aperture_64.c +++ b/arch/x86/kernel/aperture_64.c @@ -393,6 +393,7 @@ void __init gart_iommu_hole_init(void) for (i = 0; i < ARRAY_SIZE(bus_dev_ranges); i++) { int bus; int dev_base, dev_limit; + u32 ctl; bus = bus_dev_ranges[i].bus; dev_base = bus_dev_ranges[i].dev_base; @@ -406,7 +407,19 @@ void __init gart_iommu_hole_init(void) gart_iommu_aperture = 1; x86_init.iommu.iommu_init = gart_iommu_init; - aper_order = (read_pci_config(bus, slot, 3, AMD64_GARTAPERTURECTL) >> 1) & 7; + ctl = read_pci_config(bus, slot, 3, + AMD64_GARTAPERTURECTL); + + /* + * Before we do anything else disable the GART. It may + * still be enabled if we boot into a crash-kernel here. + * Reconfiguring the GART while it is enabled could have + * unknown side-effects. + */ + ctl &= ~GARTEN; + write_pci_config(bus, slot, 3, AMD64_GARTAPERTURECTL, ctl); + + aper_order = (ctl >> 1) & 7; aper_size = (32 * 1024 * 1024) << aper_order; aper_base = read_pci_config(bus, slot, 3, AMD64_GARTAPERTUREBASE) & 0x7fff; aper_base <<= 25; diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c index a4849c10a77e..ebd4c51d096a 100644 --- a/arch/x86/kernel/crash.c +++ b/arch/x86/kernel/crash.c @@ -27,7 +27,6 @@ #include <asm/cpu.h> #include <asm/reboot.h> #include <asm/virtext.h> -#include <asm/x86_init.h> #if defined(CONFIG_SMP) && defined(CONFIG_X86_LOCAL_APIC) @@ -103,10 +102,5 @@ void native_machine_crash_shutdown(struct pt_regs *regs) #ifdef CONFIG_HPET_TIMER hpet_disable(); #endif - -#ifdef CONFIG_X86_64 - x86_platform.iommu_shutdown(); -#endif - crash_save_cpu(regs, safe_smp_processor_id()); } diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c index 68cd24f9deae..0f7f130caa67 100644 --- a/arch/x86/kernel/pci-gart_64.c +++ b/arch/x86/kernel/pci-gart_64.c @@ -565,6 +565,9 @@ static void enable_gart_translations(void) enable_gart_translation(dev, __pa(agp_gatt_table)); } + + /* Flush the GART-TLB to remove stale entries */ + k8_flush_garts(); } /* diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c index 7e59dc1d3fc2..2bdf628066bd 100644 --- a/arch/x86/lguest/boot.c +++ b/arch/x86/lguest/boot.c @@ -115,7 +115,7 @@ static void async_hcall(unsigned long call, unsigned long arg1, local_irq_save(flags); if (lguest_data.hcall_status[next_call] != 0xFF) { /* Table full, so do normal hcall which will flush table. */ - kvm_hypercall4(call, arg1, arg2, arg3, arg4); + hcall(call, arg1, arg2, arg3, arg4); } else { lguest_data.hcalls[next_call].arg0 = call; lguest_data.hcalls[next_call].arg1 = arg1; @@ -145,46 +145,45 @@ static void async_hcall(unsigned long call, unsigned long arg1, * So, when we're in lazy mode, we call async_hcall() to store the call for * future processing: */ -static void lazy_hcall1(unsigned long call, - unsigned long arg1) +static void lazy_hcall1(unsigned long call, unsigned long arg1) { if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_NONE) - kvm_hypercall1(call, arg1); + hcall(call, arg1, 0, 0, 0); else async_hcall(call, arg1, 0, 0, 0); } /* You can imagine what lazy_hcall2, 3 and 4 look like. :*/ static void lazy_hcall2(unsigned long call, - unsigned long arg1, - unsigned long arg2) + unsigned long arg1, + unsigned long arg2) { if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_NONE) - kvm_hypercall2(call, arg1, arg2); + hcall(call, arg1, arg2, 0, 0); else async_hcall(call, arg1, arg2, 0, 0); } static void lazy_hcall3(unsigned long call, - unsigned long arg1, - unsigned long arg2, - unsigned long arg3) + unsigned long arg1, + unsigned long arg2, + unsigned long arg3) { if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_NONE) - kvm_hypercall3(call, arg1, arg2, arg3); + hcall(call, arg1, arg2, arg3, 0); else async_hcall(call, arg1, arg2, arg3, 0); } #ifdef CONFIG_X86_PAE static void lazy_hcall4(unsigned long call, - unsigned long arg1, - unsigned long arg2, - unsigned long arg3, - unsigned long arg4) + unsigned long arg1, + unsigned long arg2, + unsigned long arg3, + unsigned long arg4) { if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_NONE) - kvm_hypercall4(call, arg1, arg2, arg3, arg4); + hcall(call, arg1, arg2, arg3, arg4); else async_hcall(call, arg1, arg2, arg3, arg4); } @@ -196,13 +195,13 @@ static void lazy_hcall4(unsigned long call, :*/ static void lguest_leave_lazy_mmu_mode(void) { - kvm_hypercall0(LHCALL_FLUSH_ASYNC); + hcall(LHCALL_FLUSH_ASYNC, 0, 0, 0, 0); paravirt_leave_lazy_mmu(); } static void lguest_end_context_switch(struct task_struct *next) { - kvm_hypercall0(LHCALL_FLUSH_ASYNC); + hcall(LHCALL_FLUSH_ASYNC, 0, 0, 0, 0); paravirt_end_context_switch(next); } @@ -286,7 +285,7 @@ static void lguest_write_idt_entry(gate_desc *dt, /* Keep the local copy up to date. */ native_write_idt_entry(dt, entrynum, g); /* Tell Host about this new entry. */ - kvm_hypercall3(LHCALL_LOAD_IDT_ENTRY, entrynum, desc[0], desc[1]); + hcall(LHCALL_LOAD_IDT_ENTRY, entrynum, desc[0], desc[1], 0); } /* @@ -300,7 +299,7 @@ static void lguest_load_idt(const struct desc_ptr *desc) struct desc_struct *idt = (void *)desc->address; for (i = 0; i < (desc->size+1)/8; i++) - kvm_hypercall3(LHCALL_LOAD_IDT_ENTRY, i, idt[i].a, idt[i].b); + hcall(LHCALL_LOAD_IDT_ENTRY, i, idt[i].a, idt[i].b, 0); } /* @@ -321,7 +320,7 @@ static void lguest_load_gdt(const struct desc_ptr *desc) struct desc_struct *gdt = (void *)desc->address; for (i = 0; i < (desc->size+1)/8; i++) - kvm_hypercall3(LHCALL_LOAD_GDT_ENTRY, i, gdt[i].a, gdt[i].b); + hcall(LHCALL_LOAD_GDT_ENTRY, i, gdt[i].a, gdt[i].b, 0); } /* @@ -334,8 +333,8 @@ static void lguest_write_gdt_entry(struct desc_struct *dt, int entrynum, { native_write_gdt_entry(dt, entrynum, desc, type); /* Tell Host about this new entry. */ - kvm_hypercall3(LHCALL_LOAD_GDT_ENTRY, entrynum, - dt[entrynum].a, dt[entrynum].b); + hcall(LHCALL_LOAD_GDT_ENTRY, entrynum, + dt[entrynum].a, dt[entrynum].b, 0); } /* @@ -931,7 +930,7 @@ static int lguest_clockevent_set_next_event(unsigned long delta, } /* Please wake us this far in the future. */ - kvm_hypercall1(LHCALL_SET_CLOCKEVENT, delta); + hcall(LHCALL_SET_CLOCKEVENT, delta, 0, 0, 0); return 0; } @@ -942,7 +941,7 @@ static void lguest_clockevent_set_mode(enum clock_event_mode mode, case CLOCK_EVT_MODE_UNUSED: case CLOCK_EVT_MODE_SHUTDOWN: /* A 0 argument shuts the clock down. */ - kvm_hypercall0(LHCALL_SET_CLOCKEVENT); + hcall(LHCALL_SET_CLOCKEVENT, 0, 0, 0, 0); break; case CLOCK_EVT_MODE_ONESHOT: /* This is what we expect. */ @@ -1100,7 +1099,7 @@ static void set_lguest_basic_apic_ops(void) /* STOP! Until an interrupt comes in. */ static void lguest_safe_halt(void) { - kvm_hypercall0(LHCALL_HALT); + hcall(LHCALL_HALT, 0, 0, 0, 0); } /* @@ -1112,8 +1111,8 @@ static void lguest_safe_halt(void) */ static void lguest_power_off(void) { - kvm_hypercall2(LHCALL_SHUTDOWN, __pa("Power down"), - LGUEST_SHUTDOWN_POWEROFF); + hcall(LHCALL_SHUTDOWN, __pa("Power down"), + LGUEST_SHUTDOWN_POWEROFF, 0, 0); } /* @@ -1123,7 +1122,7 @@ static void lguest_power_off(void) */ static int lguest_panic(struct notifier_block *nb, unsigned long l, void *p) { - kvm_hypercall2(LHCALL_SHUTDOWN, __pa(p), LGUEST_SHUTDOWN_POWEROFF); + hcall(LHCALL_SHUTDOWN, __pa(p), LGUEST_SHUTDOWN_POWEROFF, 0, 0); /* The hcall won't return, but to keep gcc happy, we're "done". */ return NOTIFY_DONE; } @@ -1162,7 +1161,7 @@ static __init int early_put_chars(u32 vtermno, const char *buf, int count) len = sizeof(scratch) - 1; scratch[len] = '\0'; memcpy(scratch, buf, len); - kvm_hypercall1(LHCALL_NOTIFY, __pa(scratch)); + hcall(LHCALL_NOTIFY, __pa(scratch), 0, 0, 0); /* This routine returns the number of bytes actually written. */ return len; @@ -1174,7 +1173,7 @@ static __init int early_put_chars(u32 vtermno, const char *buf, int count) */ static void lguest_restart(char *reason) { - kvm_hypercall2(LHCALL_SHUTDOWN, __pa(reason), LGUEST_SHUTDOWN_RESTART); + hcall(LHCALL_SHUTDOWN, __pa(reason), LGUEST_SHUTDOWN_RESTART, 0, 0); } /*G:050 diff --git a/arch/x86/lguest/i386_head.S b/arch/x86/lguest/i386_head.S index 27eac0faee48..4f420c2f2d55 100644 --- a/arch/x86/lguest/i386_head.S +++ b/arch/x86/lguest/i386_head.S @@ -32,7 +32,7 @@ ENTRY(lguest_entry) */ movl $LHCALL_LGUEST_INIT, %eax movl $lguest_data - __PAGE_OFFSET, %ebx - .byte 0x0f,0x01,0xc1 /* KVM_HYPERCALL */ + int $LGUEST_TRAP_ENTRY /* Set up the initial stack so we can run C code. */ movl $(init_thread_union+THREAD_SIZE),%esp diff --git a/drivers/firewire/core-cdev.c b/drivers/firewire/core-cdev.c index 702dcc98c074..14a34d99eea2 100644 --- a/drivers/firewire/core-cdev.c +++ b/drivers/firewire/core-cdev.c @@ -960,6 +960,8 @@ static int ioctl_queue_iso(struct client *client, union ioctl_arg *arg) u.packet.header_length = GET_HEADER_LENGTH(control); if (ctx->type == FW_ISO_CONTEXT_TRANSMIT) { + if (u.packet.header_length % 4 != 0) + return -EINVAL; header_length = u.packet.header_length; } else { /* @@ -969,7 +971,8 @@ static int ioctl_queue_iso(struct client *client, union ioctl_arg *arg) if (ctx->header_size == 0) { if (u.packet.header_length > 0) return -EINVAL; - } else if (u.packet.header_length % ctx->header_size != 0) { + } else if (u.packet.header_length == 0 || + u.packet.header_length % ctx->header_size != 0) { return -EINVAL; } header_length = 0; @@ -1354,24 +1357,24 @@ static int dispatch_ioctl(struct client *client, return -ENODEV; if (_IOC_TYPE(cmd) != '#' || - _IOC_NR(cmd) >= ARRAY_SIZE(ioctl_handlers)) + _IOC_NR(cmd) >= ARRAY_SIZE(ioctl_handlers) || + _IOC_SIZE(cmd) > sizeof(buffer)) return -EINVAL; - if (_IOC_DIR(cmd) & _IOC_WRITE) { - if (_IOC_SIZE(cmd) > sizeof(buffer) || - copy_from_user(&buffer, arg, _IOC_SIZE(cmd))) + if (_IOC_DIR(cmd) == _IOC_READ) + memset(&buffer, 0, _IOC_SIZE(cmd)); + + if (_IOC_DIR(cmd) & _IOC_WRITE) + if (copy_from_user(&buffer, arg, _IOC_SIZE(cmd))) return -EFAULT; - } ret = ioctl_handlers[_IOC_NR(cmd)](client, &buffer); if (ret < 0) return ret; - if (_IOC_DIR(cmd) & _IOC_READ) { - if (_IOC_SIZE(cmd) > sizeof(buffer) || - copy_to_user(arg, &buffer, _IOC_SIZE(cmd))) + if (_IOC_DIR(cmd) & _IOC_READ) + if (copy_to_user(arg, &buffer, _IOC_SIZE(cmd))) return -EFAULT; - } return ret; } diff --git a/drivers/hwmon/applesmc.c b/drivers/hwmon/applesmc.c index c1605b528e8f..0f28d91f29d8 100644 --- a/drivers/hwmon/applesmc.c +++ b/drivers/hwmon/applesmc.c @@ -142,6 +142,12 @@ static const char *temperature_sensors_sets[][41] = { "TM1S", "TM2P", "TM2S", "TM3S", "TM8P", "TM8S", "TM9P", "TM9S", "TN0C", "TN0D", "TN0H", "TS0C", "Tp0C", "Tp1C", "Tv0S", "Tv1S", NULL }, +/* Set 17: iMac 9,1 */ + { "TA0P", "TC0D", "TC0H", "TC0P", "TG0D", "TG0H", "TH0P", "TL0P", + "TN0D", "TN0H", "TN0P", "TO0P", "Tm0P", "Tp0P", NULL }, +/* Set 18: MacBook Pro 2,2 */ + { "TB0T", "TC0D", "TC0P", "TG0H", "TG0P", "TG0T", "TM0P", "TTF0", + "Th0H", "Th1H", "Tm0P", "Ts0P", NULL }, }; /* List of keys used to read/write fan speeds */ @@ -1350,6 +1356,10 @@ static __initdata struct dmi_match_data applesmc_dmi_data[] = { { .accelerometer = 1, .light = 1, .temperature_set = 15 }, /* MacPro3,1: temperature set 16 */ { .accelerometer = 0, .light = 0, .temperature_set = 16 }, +/* iMac 9,1: light sensor only, temperature set 17 */ + { .accelerometer = 0, .light = 0, .temperature_set = 17 }, +/* MacBook Pro 2,2: accelerometer, backlight and temperature set 18 */ + { .accelerometer = 1, .light = 1, .temperature_set = 18 }, }; /* Note that DMI_MATCH(...,"MacBook") will match "MacBookPro1,1". @@ -1375,6 +1385,10 @@ static __initdata struct dmi_system_id applesmc_whitelist[] = { DMI_MATCH(DMI_BOARD_VENDOR, "Apple"), DMI_MATCH(DMI_PRODUCT_NAME, "MacBookPro3") }, &applesmc_dmi_data[9]}, + { applesmc_dmi_match, "Apple MacBook Pro 2,2", { + DMI_MATCH(DMI_BOARD_VENDOR, "Apple Computer, Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "MacBookPro2,2") }, + &applesmc_dmi_data[18]}, { applesmc_dmi_match, "Apple MacBook Pro", { DMI_MATCH(DMI_BOARD_VENDOR,"Apple"), DMI_MATCH(DMI_PRODUCT_NAME,"MacBookPro") }, @@ -1415,6 +1429,10 @@ static __initdata struct dmi_system_id applesmc_whitelist[] = { DMI_MATCH(DMI_BOARD_VENDOR, "Apple"), DMI_MATCH(DMI_PRODUCT_NAME, "MacPro") }, &applesmc_dmi_data[4]}, + { applesmc_dmi_match, "Apple iMac 9,1", { + DMI_MATCH(DMI_BOARD_VENDOR, "Apple Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "iMac9,1") }, + &applesmc_dmi_data[17]}, { applesmc_dmi_match, "Apple iMac 8", { DMI_MATCH(DMI_BOARD_VENDOR, "Apple"), DMI_MATCH(DMI_PRODUCT_NAME, "iMac8") }, diff --git a/drivers/hwmon/it87.c b/drivers/hwmon/it87.c index 1002befd87d5..5be09c048c5f 100644 --- a/drivers/hwmon/it87.c +++ b/drivers/hwmon/it87.c @@ -539,14 +539,14 @@ static ssize_t set_sensor(struct device *dev, struct device_attribute *attr, struct it87_data *data = dev_get_drvdata(dev); long val; + u8 reg; if (strict_strtol(buf, 10, &val) < 0) return -EINVAL; - mutex_lock(&data->update_lock); - - data->sensor &= ~(1 << nr); - data->sensor &= ~(8 << nr); + reg = it87_read_value(data, IT87_REG_TEMP_ENABLE); + reg &= ~(1 << nr); + reg &= ~(8 << nr); if (val == 2) { /* backwards compatibility */ dev_warn(dev, "Sensor type 2 is deprecated, please use 4 " "instead\n"); @@ -554,14 +554,16 @@ static ssize_t set_sensor(struct device *dev, struct device_attribute *attr, } /* 3 = thermal diode; 4 = thermistor; 0 = disabled */ if (val == 3) - data->sensor |= 1 << nr; + reg |= 1 << nr; else if (val == 4) - data->sensor |= 8 << nr; - else if (val != 0) { - mutex_unlock(&data->update_lock); + reg |= 8 << nr; + else if (val != 0) return -EINVAL; - } + + mutex_lock(&data->update_lock); + data->sensor = reg; it87_write_value(data, IT87_REG_TEMP_ENABLE, data->sensor); + data->valid = 0; /* Force cache refresh */ mutex_unlock(&data->update_lock); return count; } @@ -1841,14 +1843,10 @@ static void __devinit it87_init_device(struct platform_device *pdev) it87_write_value(data, IT87_REG_TEMP_HIGH(i), 127); } - /* Check if temperature channels are reset manually or by some reason */ - tmp = it87_read_value(data, IT87_REG_TEMP_ENABLE); - if ((tmp & 0x3f) == 0) { - /* Temp1,Temp3=thermistor; Temp2=thermal diode */ - tmp = (tmp & 0xc0) | 0x2a; - it87_write_value(data, IT87_REG_TEMP_ENABLE, tmp); - } - data->sensor = tmp; + /* Temperature channels are not forcibly enabled, as they can be + * set to two different sensor types and we can't guess which one + * is correct for a given system. These channels can be enabled at + * run-time through the temp{1-3}_type sysfs accessors if needed. */ /* Check if voltage monitors are reset manually or by some reason */ tmp = it87_read_value(data, IT87_REG_VIN_ENABLE); diff --git a/drivers/hwmon/sht15.c b/drivers/hwmon/sht15.c index 6b2d8ae64fe1..a610e7880fb3 100644 --- a/drivers/hwmon/sht15.c +++ b/drivers/hwmon/sht15.c @@ -303,13 +303,13 @@ error_ret: **/ static inline int sht15_calc_temp(struct sht15_data *data) { - int d1 = 0; + int d1 = temppoints[0].d1; int i; - for (i = 1; i < ARRAY_SIZE(temppoints); i++) + for (i = ARRAY_SIZE(temppoints) - 1; i > 0; i--) /* Find pointer to interpolate */ if (data->supply_uV > temppoints[i - 1].vdd) { - d1 = (data->supply_uV/1000 - temppoints[i - 1].vdd) + d1 = (data->supply_uV - temppoints[i - 1].vdd) * (temppoints[i].d1 - temppoints[i - 1].d1) / (temppoints[i].vdd - temppoints[i - 1].vdd) + temppoints[i - 1].d1; @@ -542,7 +542,12 @@ static int __devinit sht15_probe(struct platform_device *pdev) /* If a regulator is available, query what the supply voltage actually is!*/ data->reg = regulator_get(data->dev, "vcc"); if (!IS_ERR(data->reg)) { - data->supply_uV = regulator_get_voltage(data->reg); + int voltage; + + voltage = regulator_get_voltage(data->reg); + if (voltage) + data->supply_uV = voltage; + regulator_enable(data->reg); /* setup a notifier block to update this if another device * causes the voltage to change */ diff --git a/drivers/input/input.c b/drivers/input/input.c index afd4e2b7658c..9c79bd56b51a 100644 --- a/drivers/input/input.c +++ b/drivers/input/input.c @@ -660,7 +660,14 @@ static int input_default_setkeycode(struct input_dev *dev, int input_get_keycode(struct input_dev *dev, unsigned int scancode, unsigned int *keycode) { - return dev->getkeycode(dev, scancode, keycode); + unsigned long flags; + int retval; + + spin_lock_irqsave(&dev->event_lock, flags); + retval = dev->getkeycode(dev, scancode, keycode); + spin_unlock_irqrestore(&dev->event_lock, flags); + + return retval; } EXPORT_SYMBOL(input_get_keycode); diff --git a/drivers/input/keyboard/matrix_keypad.c b/drivers/input/keyboard/matrix_keypad.c index ffc25cfcef7a..b443e088fd3c 100644 --- a/drivers/input/keyboard/matrix_keypad.c +++ b/drivers/input/keyboard/matrix_keypad.c @@ -374,7 +374,9 @@ static int __devinit matrix_keypad_probe(struct platform_device *pdev) input_dev->name = pdev->name; input_dev->id.bustype = BUS_HOST; input_dev->dev.parent = &pdev->dev; - input_dev->evbit[0] = BIT_MASK(EV_KEY) | BIT_MASK(EV_REP); + input_dev->evbit[0] = BIT_MASK(EV_KEY); + if (!pdata->no_autorepeat) + input_dev->evbit[0] |= BIT_MASK(EV_REP); input_dev->open = matrix_keypad_start; input_dev->close = matrix_keypad_stop; diff --git a/drivers/input/mouse/alps.c b/drivers/input/mouse/alps.c index 99d58764ef03..0d22cb9ce42e 100644 --- a/drivers/input/mouse/alps.c +++ b/drivers/input/mouse/alps.c @@ -64,6 +64,7 @@ static const struct alps_model_info alps_model_data[] = { { { 0x62, 0x02, 0x14 }, 0xcf, 0xcf, ALPS_PASS | ALPS_DUALPOINT | ALPS_PS2_INTERLEAVED }, { { 0x73, 0x02, 0x50 }, 0xcf, 0xcf, ALPS_FOUR_BUTTONS }, /* Dell Vostro 1400 */ + { { 0x73, 0x02, 0x64 }, 0xf8, 0xf8, 0 }, /* HP Pavilion dm3 */ { { 0x52, 0x01, 0x14 }, 0xff, 0xff, ALPS_PASS | ALPS_DUALPOINT | ALPS_PS2_INTERLEAVED }, /* Toshiba Tecra A11-11L */ }; diff --git a/drivers/input/mouse/bcm5974.c b/drivers/input/mouse/bcm5974.c index 4f8fe0886b2a..b89879bd860f 100644 --- a/drivers/input/mouse/bcm5974.c +++ b/drivers/input/mouse/bcm5974.c @@ -803,7 +803,6 @@ static struct usb_driver bcm5974_driver = { .disconnect = bcm5974_disconnect, .suspend = bcm5974_suspend, .resume = bcm5974_resume, - .reset_resume = bcm5974_resume, .id_table = bcm5974_table, .supports_autosuspend = 1, }; diff --git a/drivers/input/serio/i8042.c b/drivers/input/serio/i8042.c index 577688b5b951..6440a8f55686 100644 --- a/drivers/input/serio/i8042.c +++ b/drivers/input/serio/i8042.c @@ -39,7 +39,7 @@ MODULE_PARM_DESC(noaux, "Do not probe or use AUX (mouse) port."); static bool i8042_nomux; module_param_named(nomux, i8042_nomux, bool, 0); -MODULE_PARM_DESC(nomux, "Do not check whether an active multiplexing conrtoller is present."); +MODULE_PARM_DESC(nomux, "Do not check whether an active multiplexing controller is present."); static bool i8042_unlock; module_param_named(unlock, i8042_unlock, bool, 0); diff --git a/drivers/input/sparse-keymap.c b/drivers/input/sparse-keymap.c index 82ae18d29685..014248344763 100644 --- a/drivers/input/sparse-keymap.c +++ b/drivers/input/sparse-keymap.c @@ -68,12 +68,14 @@ static int sparse_keymap_getkeycode(struct input_dev *dev, unsigned int scancode, unsigned int *keycode) { - const struct key_entry *key = - sparse_keymap_entry_from_scancode(dev, scancode); + const struct key_entry *key; - if (key && key->type == KE_KEY) { - *keycode = key->keycode; - return 0; + if (dev->keycode) { + key = sparse_keymap_entry_from_scancode(dev, scancode); + if (key && key->type == KE_KEY) { + *keycode = key->keycode; + return 0; + } } return -EINVAL; @@ -86,17 +88,16 @@ static int sparse_keymap_setkeycode(struct input_dev *dev, struct key_entry *key; int old_keycode; - if (keycode < 0 || keycode > KEY_MAX) - return -EINVAL; - - key = sparse_keymap_entry_from_scancode(dev, scancode); - if (key && key->type == KE_KEY) { - old_keycode = key->keycode; - key->keycode = keycode; - set_bit(keycode, dev->keybit); - if (!sparse_keymap_entry_from_keycode(dev, old_keycode)) - clear_bit(old_keycode, dev->keybit); - return 0; + if (dev->keycode) { + key = sparse_keymap_entry_from_scancode(dev, scancode); + if (key && key->type == KE_KEY) { + old_keycode = key->keycode; + key->keycode = keycode; + set_bit(keycode, dev->keybit); + if (!sparse_keymap_entry_from_keycode(dev, old_keycode)) + clear_bit(old_keycode, dev->keybit); + return 0; + } } return -EINVAL; @@ -164,7 +165,7 @@ int sparse_keymap_setup(struct input_dev *dev, return 0; err_out: - kfree(keymap); + kfree(map); return error; } @@ -176,14 +177,27 @@ EXPORT_SYMBOL(sparse_keymap_setup); * * This function is used to free memory allocated by sparse keymap * in an input device that was set up by sparse_keymap_setup(). + * NOTE: It is safe to cal this function while input device is + * still registered (however the drivers should care not to try to + * use freed keymap and thus have to shut off interrups/polling + * before freeing the keymap). */ void sparse_keymap_free(struct input_dev *dev) { + unsigned long flags; + + /* + * Take event lock to prevent racing with input_get_keycode() + * and input_set_keycode() if we are called while input device + * is still registered. + */ + spin_lock_irqsave(&dev->event_lock, flags); + kfree(dev->keycode); dev->keycode = NULL; dev->keycodemax = 0; - dev->getkeycode = NULL; - dev->setkeycode = NULL; + + spin_unlock_irqrestore(&dev->event_lock, flags); } EXPORT_SYMBOL(sparse_keymap_free); diff --git a/drivers/input/tablet/wacom_sys.c b/drivers/input/tablet/wacom_sys.c index 8b5d2873f0c4..f46502589e4e 100644 --- a/drivers/input/tablet/wacom_sys.c +++ b/drivers/input/tablet/wacom_sys.c @@ -673,13 +673,15 @@ static int wacom_resume(struct usb_interface *intf) int rv; mutex_lock(&wacom->lock); - if (wacom->open) { + + /* switch to wacom mode first */ + wacom_query_tablet_data(intf, features); + + if (wacom->open) rv = usb_submit_urb(wacom->irq, GFP_NOIO); - /* switch to wacom mode if needed */ - if (!wacom_retrieve_hid_descriptor(intf, features)) - wacom_query_tablet_data(intf, features); - } else + else rv = 0; + mutex_unlock(&wacom->lock); return rv; diff --git a/drivers/input/tablet/wacom_wac.c b/drivers/input/tablet/wacom_wac.c index b3ba3437a2eb..4a852d815c68 100644 --- a/drivers/input/tablet/wacom_wac.c +++ b/drivers/input/tablet/wacom_wac.c @@ -155,19 +155,19 @@ static int wacom_graphire_irq(struct wacom_wac *wacom, void *wcombo) { struct wacom_features *features = &wacom->features; unsigned char *data = wacom->data; - int x, y, prox; - int rw = 0; - int retval = 0; + int x, y, rw; + static int penData = 0; if (data[0] != WACOM_REPORT_PENABLED) { dbg("wacom_graphire_irq: received unknown report #%d", data[0]); - goto exit; + return 0; } - prox = data[1] & 0x80; - if (prox || wacom->id[0]) { - if (prox) { - switch ((data[1] >> 5) & 3) { + if (data[1] & 0x80) { + /* in prox and not a pad data */ + penData = 1; + + switch ((data[1] >> 5) & 3) { case 0: /* Pen */ wacom->tool[0] = BTN_TOOL_PEN; @@ -181,13 +181,23 @@ static int wacom_graphire_irq(struct wacom_wac *wacom, void *wcombo) case 2: /* Mouse with wheel */ wacom_report_key(wcombo, BTN_MIDDLE, data[1] & 0x04); + if (features->type == WACOM_G4 || features->type == WACOM_MO) { + rw = data[7] & 0x04 ? (data[7] & 0x03)-4 : (data[7] & 0x03); + wacom_report_rel(wcombo, REL_WHEEL, -rw); + } else + wacom_report_rel(wcombo, REL_WHEEL, -(signed char) data[6]); /* fall through */ case 3: /* Mouse without wheel */ wacom->tool[0] = BTN_TOOL_MOUSE; wacom->id[0] = CURSOR_DEVICE_ID; + wacom_report_key(wcombo, BTN_LEFT, data[1] & 0x01); + wacom_report_key(wcombo, BTN_RIGHT, data[1] & 0x02); + if (features->type == WACOM_G4 || features->type == WACOM_MO) + wacom_report_abs(wcombo, ABS_DISTANCE, data[6] & 0x3f); + else + wacom_report_abs(wcombo, ABS_DISTANCE, data[7] & 0x3f); break; - } } x = wacom_le16_to_cpu(&data[2]); y = wacom_le16_to_cpu(&data[4]); @@ -198,32 +208,36 @@ static int wacom_graphire_irq(struct wacom_wac *wacom, void *wcombo) wacom_report_key(wcombo, BTN_TOUCH, data[1] & 0x01); wacom_report_key(wcombo, BTN_STYLUS, data[1] & 0x02); wacom_report_key(wcombo, BTN_STYLUS2, data[1] & 0x04); - } else { - wacom_report_key(wcombo, BTN_LEFT, data[1] & 0x01); - wacom_report_key(wcombo, BTN_RIGHT, data[1] & 0x02); - if (features->type == WACOM_G4 || - features->type == WACOM_MO) { - wacom_report_abs(wcombo, ABS_DISTANCE, data[6] & 0x3f); - rw = (signed)(data[7] & 0x04) - (data[7] & 0x03); - } else { - wacom_report_abs(wcombo, ABS_DISTANCE, data[7] & 0x3f); - rw = -(signed)data[6]; - } - wacom_report_rel(wcombo, REL_WHEEL, rw); } - - if (!prox) - wacom->id[0] = 0; wacom_report_abs(wcombo, ABS_MISC, wacom->id[0]); /* report tool id */ - wacom_report_key(wcombo, wacom->tool[0], prox); - wacom_input_sync(wcombo); /* sync last event */ + wacom_report_key(wcombo, wacom->tool[0], 1); + } else if (wacom->id[0]) { + wacom_report_abs(wcombo, ABS_X, 0); + wacom_report_abs(wcombo, ABS_Y, 0); + if (wacom->tool[0] == BTN_TOOL_MOUSE) { + wacom_report_key(wcombo, BTN_LEFT, 0); + wacom_report_key(wcombo, BTN_RIGHT, 0); + wacom_report_abs(wcombo, ABS_DISTANCE, 0); + } else { + wacom_report_abs(wcombo, ABS_PRESSURE, 0); + wacom_report_key(wcombo, BTN_TOUCH, 0); + wacom_report_key(wcombo, BTN_STYLUS, 0); + wacom_report_key(wcombo, BTN_STYLUS2, 0); + } + wacom->id[0] = 0; + wacom_report_abs(wcombo, ABS_MISC, 0); /* reset tool id */ + wacom_report_key(wcombo, wacom->tool[0], 0); } /* send pad data */ switch (features->type) { case WACOM_G4: - prox = data[7] & 0xf8; - if (prox || wacom->id[1]) { + if (data[7] & 0xf8) { + if (penData) { + wacom_input_sync(wcombo); /* sync last event */ + if (!wacom->id[0]) + penData = 0; + } wacom->id[1] = PAD_DEVICE_ID; wacom_report_key(wcombo, BTN_0, (data[7] & 0x40)); wacom_report_key(wcombo, BTN_4, (data[7] & 0x80)); @@ -231,16 +245,29 @@ static int wacom_graphire_irq(struct wacom_wac *wacom, void *wcombo) wacom_report_rel(wcombo, REL_WHEEL, rw); wacom_report_key(wcombo, BTN_TOOL_FINGER, 0xf0); wacom_report_abs(wcombo, ABS_MISC, wacom->id[1]); - if (!prox) - wacom->id[1] = 0; - wacom_report_abs(wcombo, ABS_MISC, wacom->id[1]); + wacom_input_event(wcombo, EV_MSC, MSC_SERIAL, 0xf0); + } else if (wacom->id[1]) { + if (penData) { + wacom_input_sync(wcombo); /* sync last event */ + if (!wacom->id[0]) + penData = 0; + } + wacom->id[1] = 0; + wacom_report_key(wcombo, BTN_0, (data[7] & 0x40)); + wacom_report_key(wcombo, BTN_4, (data[7] & 0x80)); + wacom_report_rel(wcombo, REL_WHEEL, 0); + wacom_report_key(wcombo, BTN_TOOL_FINGER, 0); + wacom_report_abs(wcombo, ABS_MISC, 0); wacom_input_event(wcombo, EV_MSC, MSC_SERIAL, 0xf0); } - retval = 1; break; case WACOM_MO: - prox = (data[7] & 0xf8) || data[8]; - if (prox || wacom->id[1]) { + if ((data[7] & 0xf8) || (data[8] & 0xff)) { + if (penData) { + wacom_input_sync(wcombo); /* sync last event */ + if (!wacom->id[0]) + penData = 0; + } wacom->id[1] = PAD_DEVICE_ID; wacom_report_key(wcombo, BTN_0, (data[7] & 0x08)); wacom_report_key(wcombo, BTN_1, (data[7] & 0x20)); @@ -248,16 +275,27 @@ static int wacom_graphire_irq(struct wacom_wac *wacom, void *wcombo) wacom_report_key(wcombo, BTN_5, (data[7] & 0x40)); wacom_report_abs(wcombo, ABS_WHEEL, (data[8] & 0x7f)); wacom_report_key(wcombo, BTN_TOOL_FINGER, 0xf0); - if (!prox) - wacom->id[1] = 0; wacom_report_abs(wcombo, ABS_MISC, wacom->id[1]); wacom_input_event(wcombo, EV_MSC, MSC_SERIAL, 0xf0); + } else if (wacom->id[1]) { + if (penData) { + wacom_input_sync(wcombo); /* sync last event */ + if (!wacom->id[0]) + penData = 0; + } + wacom->id[1] = 0; + wacom_report_key(wcombo, BTN_0, (data[7] & 0x08)); + wacom_report_key(wcombo, BTN_1, (data[7] & 0x20)); + wacom_report_key(wcombo, BTN_4, (data[7] & 0x10)); + wacom_report_key(wcombo, BTN_5, (data[7] & 0x40)); + wacom_report_abs(wcombo, ABS_WHEEL, (data[8] & 0x7f)); + wacom_report_key(wcombo, BTN_TOOL_FINGER, 0); + wacom_report_abs(wcombo, ABS_MISC, 0); + wacom_input_event(wcombo, EV_MSC, MSC_SERIAL, 0xf0); } - retval = 1; break; } -exit: - return retval; + return 1; } static int wacom_intuos_inout(struct wacom_wac *wacom, void *wcombo) @@ -598,9 +636,9 @@ static int wacom_intuos_irq(struct wacom_wac *wacom, void *wcombo) static void wacom_tpc_finger_in(struct wacom_wac *wacom, void *wcombo, char *data, int idx) { wacom_report_abs(wcombo, ABS_X, - data[2 + idx * 2] | ((data[3 + idx * 2] & 0x7f) << 8)); + (data[2 + idx * 2] & 0xff) | ((data[3 + idx * 2] & 0x7f) << 8)); wacom_report_abs(wcombo, ABS_Y, - data[6 + idx * 2] | ((data[7 + idx * 2] & 0x7f) << 8)); + (data[6 + idx * 2] & 0xff) | ((data[7 + idx * 2] & 0x7f) << 8)); wacom_report_abs(wcombo, ABS_MISC, wacom->id[0]); wacom_report_key(wcombo, wacom->tool[idx], 1); if (idx) @@ -744,24 +782,31 @@ static int wacom_tpc_irq(struct wacom_wac *wacom, void *wcombo) touchInProx = 0; - if (!wacom->id[0]) { /* first in prox */ - /* Going into proximity select tool */ - wacom->tool[0] = (data[1] & 0x0c) ? BTN_TOOL_RUBBER : BTN_TOOL_PEN; - if (wacom->tool[0] == BTN_TOOL_PEN) - wacom->id[0] = STYLUS_DEVICE_ID; - else - wacom->id[0] = ERASER_DEVICE_ID; - } - wacom_report_key(wcombo, BTN_STYLUS, data[1] & 0x02); - wacom_report_key(wcombo, BTN_STYLUS2, data[1] & 0x10); - wacom_report_abs(wcombo, ABS_X, wacom_le16_to_cpu(&data[2])); - wacom_report_abs(wcombo, ABS_Y, wacom_le16_to_cpu(&data[4])); - pressure = ((data[7] & 0x01) << 8) | data[6]; - if (pressure < 0) - pressure = features->pressure_max + pressure + 1; - wacom_report_abs(wcombo, ABS_PRESSURE, pressure); - wacom_report_key(wcombo, BTN_TOUCH, data[1] & 0x05); - if (!prox) { /* out-prox */ + if (prox) { /* in prox */ + if (!wacom->id[0]) { + /* Going into proximity select tool */ + wacom->tool[0] = (data[1] & 0x0c) ? BTN_TOOL_RUBBER : BTN_TOOL_PEN; + if (wacom->tool[0] == BTN_TOOL_PEN) + wacom->id[0] = STYLUS_DEVICE_ID; + else + wacom->id[0] = ERASER_DEVICE_ID; + } + wacom_report_key(wcombo, BTN_STYLUS, data[1] & 0x02); + wacom_report_key(wcombo, BTN_STYLUS2, data[1] & 0x10); + wacom_report_abs(wcombo, ABS_X, wacom_le16_to_cpu(&data[2])); + wacom_report_abs(wcombo, ABS_Y, wacom_le16_to_cpu(&data[4])); + pressure = ((data[7] & 0x01) << 8) | data[6]; + if (pressure < 0) + pressure = features->pressure_max + pressure + 1; + wacom_report_abs(wcombo, ABS_PRESSURE, pressure); + wacom_report_key(wcombo, BTN_TOUCH, data[1] & 0x05); + } else { + wacom_report_abs(wcombo, ABS_X, 0); + wacom_report_abs(wcombo, ABS_Y, 0); + wacom_report_abs(wcombo, ABS_PRESSURE, 0); + wacom_report_key(wcombo, BTN_STYLUS, 0); + wacom_report_key(wcombo, BTN_STYLUS2, 0); + wacom_report_key(wcombo, BTN_TOUCH, 0); wacom->id[0] = 0; /* pen is out so touch can be enabled now */ touchInProx = 1; diff --git a/drivers/lguest/lguest_device.c b/drivers/lguest/lguest_device.c index 07090f379c63..69c84a1d88ea 100644 --- a/drivers/lguest/lguest_device.c +++ b/drivers/lguest/lguest_device.c @@ -178,7 +178,7 @@ static void set_status(struct virtio_device *vdev, u8 status) /* We set the status. */ to_lgdev(vdev)->desc->status = status; - kvm_hypercall1(LHCALL_NOTIFY, (max_pfn << PAGE_SHIFT) + offset); + hcall(LHCALL_NOTIFY, (max_pfn << PAGE_SHIFT) + offset, 0, 0, 0); } static void lg_set_status(struct virtio_device *vdev, u8 status) @@ -229,7 +229,7 @@ static void lg_notify(struct virtqueue *vq) */ struct lguest_vq_info *lvq = vq->priv; - kvm_hypercall1(LHCALL_NOTIFY, lvq->config.pfn << PAGE_SHIFT); + hcall(LHCALL_NOTIFY, lvq->config.pfn << PAGE_SHIFT, 0, 0, 0); } /* An extern declaration inside a C file is bad form. Don't do it. */ diff --git a/drivers/lguest/x86/core.c b/drivers/lguest/x86/core.c index fb2b7ef7868e..b4eb675a807e 100644 --- a/drivers/lguest/x86/core.c +++ b/drivers/lguest/x86/core.c @@ -288,6 +288,18 @@ static int emulate_insn(struct lg_cpu *cpu) insn = lgread(cpu, physaddr, u8); /* + * Around 2.6.33, the kernel started using an emulation for the + * cmpxchg8b instruction in early boot on many configurations. This + * code isn't paravirtualized, and it tries to disable interrupts. + * Ignore it, which will Mostly Work. + */ + if (insn == 0xfa) { + /* "cli", or Clear Interrupt Enable instruction. Skip it. */ + cpu->regs->eip++; + return 1; + } + + /* * 0x66 is an "operand prefix". It means it's using the upper 16 bits * of the eax register. */ diff --git a/drivers/net/cnic.c b/drivers/net/cnic.c index 9781942992e9..4b451a7c03e9 100644 --- a/drivers/net/cnic.c +++ b/drivers/net/cnic.c @@ -2334,13 +2334,13 @@ static int cnic_service_bnx2x(void *data, void *status_blk) struct cnic_local *cp = dev->cnic_priv; u16 prod = cp->kcq_prod_idx & MAX_KCQ_IDX; - prefetch(cp->status_blk.bnx2x); - prefetch(&cp->kcq[KCQ_PG(prod)][KCQ_IDX(prod)]); + if (likely(test_bit(CNIC_F_CNIC_UP, &dev->flags))) { + prefetch(cp->status_blk.bnx2x); + prefetch(&cp->kcq[KCQ_PG(prod)][KCQ_IDX(prod)]); - if (likely(test_bit(CNIC_F_CNIC_UP, &dev->flags))) tasklet_schedule(&cp->cnic_irq_task); - - cnic_chk_pkt_rings(cp); + cnic_chk_pkt_rings(cp); + } return 0; } diff --git a/drivers/net/e1000e/netdev.c b/drivers/net/e1000e/netdev.c index cfd09cea7214..73d43c53015a 100644 --- a/drivers/net/e1000e/netdev.c +++ b/drivers/net/e1000e/netdev.c @@ -661,6 +661,8 @@ static bool e1000_clean_tx_irq(struct e1000_adapter *adapter) i = 0; } + if (i == tx_ring->next_to_use) + break; eop = tx_ring->buffer_info[i].next_to_watch; eop_desc = E1000_TX_DESC(*tx_ring, eop); } diff --git a/drivers/net/igb/igb_ethtool.c b/drivers/net/igb/igb_ethtool.c index d313fae992da..743038490104 100644 --- a/drivers/net/igb/igb_ethtool.c +++ b/drivers/net/igb/igb_ethtool.c @@ -1814,6 +1814,7 @@ static int igb_wol_exclusion(struct igb_adapter *adapter, retval = 0; break; case E1000_DEV_ID_82576_QUAD_COPPER: + case E1000_DEV_ID_82576_QUAD_COPPER_ET2: /* quad port adapters only support WoL on port A */ if (!(adapter->flags & IGB_FLAG_QUAD_PORT_A)) { wol->supported = 0; diff --git a/drivers/net/igb/igb_main.c b/drivers/net/igb/igb_main.c index 9b3c51ab1758..c9baa2aa98cd 100644 --- a/drivers/net/igb/igb_main.c +++ b/drivers/net/igb/igb_main.c @@ -1612,6 +1612,7 @@ static int __devinit igb_probe(struct pci_dev *pdev, adapter->eeprom_wol = 0; break; case E1000_DEV_ID_82576_QUAD_COPPER: + case E1000_DEV_ID_82576_QUAD_COPPER_ET2: /* if quad port adapter, disable WoL on all but port A */ if (global_quad_port_a != 0) adapter->eeprom_wol = 0; diff --git a/drivers/net/myri10ge/myri10ge.c b/drivers/net/myri10ge/myri10ge.c index 471887742b02..ecde0876a785 100644 --- a/drivers/net/myri10ge/myri10ge.c +++ b/drivers/net/myri10ge/myri10ge.c @@ -1690,7 +1690,7 @@ myri10ge_set_pauseparam(struct net_device *netdev, if (pause->tx_pause != mgp->pause) return myri10ge_change_pause(mgp, pause->tx_pause); if (pause->rx_pause != mgp->pause) - return myri10ge_change_pause(mgp, pause->tx_pause); + return myri10ge_change_pause(mgp, pause->rx_pause); if (pause->autoneg != 0) return -EINVAL; return 0; diff --git a/drivers/net/pcmcia/smc91c92_cs.c b/drivers/net/pcmcia/smc91c92_cs.c index ff7eb9116b6a..fd9d6e34fda4 100644 --- a/drivers/net/pcmcia/smc91c92_cs.c +++ b/drivers/net/pcmcia/smc91c92_cs.c @@ -1608,9 +1608,12 @@ static void set_rx_mode(struct net_device *dev) { unsigned int ioaddr = dev->base_addr; struct smc_private *smc = netdev_priv(dev); - u_int multicast_table[ 2 ] = { 0, }; + unsigned char multicast_table[8]; unsigned long flags; u_short rx_cfg_setting; + int i; + + memset(multicast_table, 0, sizeof(multicast_table)); if (dev->flags & IFF_PROMISC) { rx_cfg_setting = RxStripCRC | RxEnable | RxPromisc | RxAllMulti; @@ -1622,10 +1625,6 @@ static void set_rx_mode(struct net_device *dev) netdev_for_each_mc_addr(mc_addr, dev) { u_int position = ether_crc(6, mc_addr->dmi_addr); -#ifndef final_version /* Verify multicast address. */ - if ((mc_addr->dmi_addr[0] & 1) == 0) - continue; -#endif multicast_table[position >> 29] |= 1 << ((position >> 26) & 7); } } @@ -1635,8 +1634,8 @@ static void set_rx_mode(struct net_device *dev) /* Load MC table and Rx setting into the chip without interrupts. */ spin_lock_irqsave(&smc->lock, flags); SMC_SELECT_BANK(3); - outl(multicast_table[0], ioaddr + MULTICAST0); - outl(multicast_table[1], ioaddr + MULTICAST4); + for (i = 0; i < 8; i++) + outb(multicast_table[i], ioaddr + MULTICAST0 + i); SMC_SELECT_BANK(0); outw(rx_cfg_setting, ioaddr + RCR); SMC_SELECT_BANK(2); diff --git a/drivers/net/qlcnic/qlcnic_hw.c b/drivers/net/qlcnic/qlcnic_hw.c index a6ef266a2fe2..e73ba455aa20 100644 --- a/drivers/net/qlcnic/qlcnic_hw.c +++ b/drivers/net/qlcnic/qlcnic_hw.c @@ -431,6 +431,9 @@ void qlcnic_set_multi(struct net_device *netdev) u8 bcast_addr[ETH_ALEN] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff }; u32 mode = VPORT_MISS_MODE_DROP; + if (adapter->is_up != QLCNIC_ADAPTER_UP_MAGIC) + return; + qlcnic_nic_add_mac(adapter, adapter->mac_addr); qlcnic_nic_add_mac(adapter, bcast_addr); diff --git a/drivers/net/r6040.c b/drivers/net/r6040.c index 43afdb6b25e6..0298d8c1dcb6 100644 --- a/drivers/net/r6040.c +++ b/drivers/net/r6040.c @@ -134,7 +134,7 @@ #define RX_DESC_SIZE (RX_DCNT * sizeof(struct r6040_descriptor)) #define TX_DESC_SIZE (TX_DCNT * sizeof(struct r6040_descriptor)) #define MBCR_DEFAULT 0x012A /* MAC Bus Control Register */ -#define MCAST_MAX 4 /* Max number multicast addresses to filter */ +#define MCAST_MAX 3 /* Max number multicast addresses to filter */ /* Descriptor status */ #define DSC_OWNER_MAC 0x8000 /* MAC is the owner of this descriptor */ @@ -982,9 +982,6 @@ static void r6040_multicast_list(struct net_device *dev) crc >>= 26; hash_table[crc >> 4] |= 1 << (15 - (crc & 0xf)); } - /* Write the index of the hash table */ - for (i = 0; i < 4; i++) - iowrite16(hash_table[i] << 14, ioaddr + MCR1); /* Fill the MAC hash tables with their values */ iowrite16(hash_table[0], ioaddr + MAR0); iowrite16(hash_table[1], ioaddr + MAR1); @@ -1000,9 +997,9 @@ static void r6040_multicast_list(struct net_device *dev) iowrite16(adrp[1], ioaddr + MID_1M + 8 * i); iowrite16(adrp[2], ioaddr + MID_1H + 8 * i); } else { - iowrite16(0xffff, ioaddr + MID_0L + 8 * i); - iowrite16(0xffff, ioaddr + MID_0M + 8 * i); - iowrite16(0xffff, ioaddr + MID_0H + 8 * i); + iowrite16(0xffff, ioaddr + MID_1L + 8 * i); + iowrite16(0xffff, ioaddr + MID_1M + 8 * i); + iowrite16(0xffff, ioaddr + MID_1H + 8 * i); } i++; } diff --git a/drivers/net/stmmac/stmmac_main.c b/drivers/net/stmmac/stmmac_main.c index a214a1627e8b..4111a85ec80e 100644 --- a/drivers/net/stmmac/stmmac_main.c +++ b/drivers/net/stmmac/stmmac_main.c @@ -1686,7 +1686,7 @@ static int stmmac_dvr_probe(struct platform_device *pdev) } pr_info("done!\n"); - if (!request_mem_region(res->start, (res->end - res->start), + if (!request_mem_region(res->start, resource_size(res), pdev->name)) { pr_err("%s: ERROR: memory allocation failed" "cannot get the I/O addr 0x%x\n", @@ -1695,9 +1695,9 @@ static int stmmac_dvr_probe(struct platform_device *pdev) goto out; } - addr = ioremap(res->start, (res->end - res->start)); + addr = ioremap(res->start, resource_size(res)); if (!addr) { - pr_err("%s: ERROR: memory mapping failed \n", __func__); + pr_err("%s: ERROR: memory mapping failed\n", __func__); ret = -ENOMEM; goto out; } @@ -1775,7 +1775,7 @@ static int stmmac_dvr_probe(struct platform_device *pdev) out: if (ret < 0) { platform_set_drvdata(pdev, NULL); - release_mem_region(res->start, (res->end - res->start)); + release_mem_region(res->start, resource_size(res)); if (addr != NULL) iounmap(addr); } @@ -1813,7 +1813,7 @@ static int stmmac_dvr_remove(struct platform_device *pdev) iounmap((void *)ndev->base_addr); res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - release_mem_region(res->start, (res->end - res->start)); + release_mem_region(res->start, resource_size(res)); free_netdev(ndev); diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 6fb783ce20b9..b0577dd1a42d 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -327,6 +327,7 @@ static int add_recvbuf_small(struct virtnet_info *vi, gfp_t gfp) struct scatterlist sg[2]; int err; + sg_init_table(sg, 2); skb = netdev_alloc_skb_ip_align(vi->dev, MAX_PACKET_LEN); if (unlikely(!skb)) return -ENOMEM; @@ -352,6 +353,7 @@ static int add_recvbuf_big(struct virtnet_info *vi, gfp_t gfp) char *p; int i, err, offset; + sg_init_table(sg, MAX_SKB_FRAGS + 2); /* page in sg[MAX_SKB_FRAGS + 1] is list tail */ for (i = MAX_SKB_FRAGS + 1; i > 1; --i) { first = get_a_page(vi, gfp); diff --git a/drivers/net/wireless/ath/ath9k/main.c b/drivers/net/wireless/ath/ath9k/main.c index 67ca4e5a6017..115e1aeedb59 100644 --- a/drivers/net/wireless/ath/ath9k/main.c +++ b/drivers/net/wireless/ath/ath9k/main.c @@ -1532,8 +1532,7 @@ static int ath9k_config(struct ieee80211_hw *hw, u32 changed) all_wiphys_idle = ath9k_all_wiphys_idle(sc); ath9k_set_wiphy_idle(aphy, idle); - if (!idle && all_wiphys_idle) - enable_radio = true; + enable_radio = (!idle && all_wiphys_idle); /* * After we unlock here its possible another wiphy diff --git a/drivers/net/wireless/iwlwifi/iwl-4965.c b/drivers/net/wireless/iwlwifi/iwl-4965.c index 83c52a682622..8972166386cb 100644 --- a/drivers/net/wireless/iwlwifi/iwl-4965.c +++ b/drivers/net/wireless/iwlwifi/iwl-4965.c @@ -2015,7 +2015,9 @@ static void iwl4965_rx_reply_tx(struct iwl_priv *priv, IWL_DEBUG_TX_REPLY(priv, "Retry scheduler reclaim scd_ssn " "%d index %d\n", scd_ssn , index); freed = iwl_tx_queue_reclaim(priv, txq_id, index); - iwl_free_tfds_in_queue(priv, sta_id, tid, freed); + if (qc) + iwl_free_tfds_in_queue(priv, sta_id, + tid, freed); if (priv->mac80211_registered && (iwl_queue_space(&txq->q) > txq->q.low_mark) && @@ -2041,14 +2043,17 @@ static void iwl4965_rx_reply_tx(struct iwl_priv *priv, tx_resp->failure_frame); freed = iwl_tx_queue_reclaim(priv, txq_id, index); - iwl_free_tfds_in_queue(priv, sta_id, tid, freed); + if (qc && likely(sta_id != IWL_INVALID_STATION)) + iwl_free_tfds_in_queue(priv, sta_id, tid, freed); + else if (sta_id == IWL_INVALID_STATION) + IWL_DEBUG_TX_REPLY(priv, "Station not known\n"); if (priv->mac80211_registered && (iwl_queue_space(&txq->q) > txq->q.low_mark)) iwl_wake_queue(priv, txq_id); } - - iwl_txq_check_empty(priv, sta_id, tid, txq_id); + if (qc && likely(sta_id != IWL_INVALID_STATION)) + iwl_txq_check_empty(priv, sta_id, tid, txq_id); if (iwl_check_bits(status, TX_ABORT_REQUIRED_MSK)) IWL_ERR(priv, "TODO: Implement Tx ABORT REQUIRED!!!\n"); diff --git a/drivers/net/wireless/iwlwifi/iwl-agn-rs.c b/drivers/net/wireless/iwlwifi/iwl-agn-rs.c index 35f819ac87a3..1460116d329f 100644 --- a/drivers/net/wireless/iwlwifi/iwl-agn-rs.c +++ b/drivers/net/wireless/iwlwifi/iwl-agn-rs.c @@ -346,6 +346,17 @@ static inline int get_num_of_ant_from_rate(u32 rate_n_flags) !!(rate_n_flags & RATE_MCS_ANT_C_MSK); } +/* + * Static function to get the expected throughput from an iwl_scale_tbl_info + * that wraps a NULL pointer check + */ +static s32 get_expected_tpt(struct iwl_scale_tbl_info *tbl, int rs_index) +{ + if (tbl->expected_tpt) + return tbl->expected_tpt[rs_index]; + return 0; +} + /** * rs_collect_tx_data - Update the success/failure sliding window * @@ -353,19 +364,21 @@ static inline int get_num_of_ant_from_rate(u32 rate_n_flags) * at this rate. window->data contains the bitmask of successful * packets. */ -static int rs_collect_tx_data(struct iwl_rate_scale_data *windows, - int scale_index, s32 tpt, int attempts, - int successes) +static int rs_collect_tx_data(struct iwl_scale_tbl_info *tbl, + int scale_index, int attempts, int successes) { struct iwl_rate_scale_data *window = NULL; static const u64 mask = (((u64)1) << (IWL_RATE_MAX_WINDOW - 1)); - s32 fail_count; + s32 fail_count, tpt; if (scale_index < 0 || scale_index >= IWL_RATE_COUNT) return -EINVAL; /* Select window for current tx bit rate */ - window = &(windows[scale_index]); + window = &(tbl->win[scale_index]); + + /* Get expected throughput */ + tpt = get_expected_tpt(tbl, scale_index); /* * Keep track of only the latest 62 tx frame attempts in this rate's @@ -739,16 +752,6 @@ static bool table_type_matches(struct iwl_scale_tbl_info *a, return (a->lq_type == b->lq_type) && (a->ant_type == b->ant_type) && (a->is_SGI == b->is_SGI); } -/* - * Static function to get the expected throughput from an iwl_scale_tbl_info - * that wraps a NULL pointer check - */ -static s32 get_expected_tpt(struct iwl_scale_tbl_info *tbl, int rs_index) -{ - if (tbl->expected_tpt) - return tbl->expected_tpt[rs_index]; - return 0; -} /* * mac80211 sends us Tx status @@ -765,12 +768,10 @@ static void rs_tx_status(void *priv_r, struct ieee80211_supported_band *sband, struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data; struct iwl_priv *priv = (struct iwl_priv *)priv_r; struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); - struct iwl_rate_scale_data *window = NULL; enum mac80211_rate_control_flags mac_flags; u32 tx_rate; struct iwl_scale_tbl_info tbl_type; - struct iwl_scale_tbl_info *curr_tbl, *other_tbl; - s32 tpt = 0; + struct iwl_scale_tbl_info *curr_tbl, *other_tbl, *tmp_tbl; IWL_DEBUG_RATE_LIMIT(priv, "get frame ack response, update rate scale window\n"); @@ -853,7 +854,6 @@ static void rs_tx_status(void *priv_r, struct ieee80211_supported_band *sband, IWL_DEBUG_RATE(priv, "Neither active nor search matches tx rate\n"); return; } - window = (struct iwl_rate_scale_data *)&(curr_tbl->win[0]); /* * Updating the frame history depends on whether packets were @@ -866,8 +866,7 @@ static void rs_tx_status(void *priv_r, struct ieee80211_supported_band *sband, tx_rate = le32_to_cpu(table->rs_table[0].rate_n_flags); rs_get_tbl_info_from_mcs(tx_rate, priv->band, &tbl_type, &rs_index); - tpt = get_expected_tpt(curr_tbl, rs_index); - rs_collect_tx_data(window, rs_index, tpt, + rs_collect_tx_data(curr_tbl, rs_index, info->status.ampdu_ack_len, info->status.ampdu_ack_map); @@ -897,19 +896,13 @@ static void rs_tx_status(void *priv_r, struct ieee80211_supported_band *sband, * table as active/search. */ if (table_type_matches(&tbl_type, curr_tbl)) - tpt = get_expected_tpt(curr_tbl, rs_index); + tmp_tbl = curr_tbl; else if (table_type_matches(&tbl_type, other_tbl)) - tpt = get_expected_tpt(other_tbl, rs_index); + tmp_tbl = other_tbl; else continue; - - /* Constants mean 1 transmission, 0 successes */ - if (i < retries) - rs_collect_tx_data(window, rs_index, tpt, 1, - 0); - else - rs_collect_tx_data(window, rs_index, tpt, 1, - legacy_success); + rs_collect_tx_data(tmp_tbl, rs_index, 1, + i < retries ? 0 : legacy_success); } /* Update success/fail counts if not searching for new mode */ diff --git a/drivers/net/wireless/iwlwifi/iwl-core.c b/drivers/net/wireless/iwlwifi/iwl-core.c index db050b811232..3352f7086632 100644 --- a/drivers/net/wireless/iwlwifi/iwl-core.c +++ b/drivers/net/wireless/iwlwifi/iwl-core.c @@ -308,10 +308,13 @@ int iwl_hw_nic_init(struct iwl_priv *priv) spin_unlock_irqrestore(&priv->lock, flags); - /* Allocate and init all Tx and Command queues */ - ret = iwl_txq_ctx_reset(priv); - if (ret) - return ret; + /* Allocate or reset and init all Tx and Command queues */ + if (!priv->txq) { + ret = iwl_txq_ctx_alloc(priv); + if (ret) + return ret; + } else + iwl_txq_ctx_reset(priv); set_bit(STATUS_INIT, &priv->status); diff --git a/drivers/net/wireless/iwlwifi/iwl-core.h b/drivers/net/wireless/iwlwifi/iwl-core.h index 4ef7739f9e8e..732590f5fe30 100644 --- a/drivers/net/wireless/iwlwifi/iwl-core.h +++ b/drivers/net/wireless/iwlwifi/iwl-core.h @@ -442,7 +442,8 @@ void iwl_rx_csa(struct iwl_priv *priv, struct iwl_rx_mem_buffer *rxb); /***************************************************** * TX ******************************************************/ -int iwl_txq_ctx_reset(struct iwl_priv *priv); +int iwl_txq_ctx_alloc(struct iwl_priv *priv); +void iwl_txq_ctx_reset(struct iwl_priv *priv); void iwl_hw_txq_free_tfd(struct iwl_priv *priv, struct iwl_tx_queue *txq); int iwl_hw_txq_attach_buf_to_tfd(struct iwl_priv *priv, struct iwl_tx_queue *txq, @@ -456,6 +457,8 @@ void iwl_free_tfds_in_queue(struct iwl_priv *priv, void iwl_txq_update_write_ptr(struct iwl_priv *priv, struct iwl_tx_queue *txq); int iwl_tx_queue_init(struct iwl_priv *priv, struct iwl_tx_queue *txq, int slots_num, u32 txq_id); +void iwl_tx_queue_reset(struct iwl_priv *priv, struct iwl_tx_queue *txq, + int slots_num, u32 txq_id); void iwl_tx_queue_free(struct iwl_priv *priv, int txq_id); int iwl_tx_agg_start(struct iwl_priv *priv, const u8 *ra, u16 tid, u16 *ssn); int iwl_tx_agg_stop(struct iwl_priv *priv , const u8 *ra, u16 tid); diff --git a/drivers/net/wireless/iwlwifi/iwl-tx.c b/drivers/net/wireless/iwlwifi/iwl-tx.c index f0b7e6cfbe4f..8dd0c036d547 100644 --- a/drivers/net/wireless/iwlwifi/iwl-tx.c +++ b/drivers/net/wireless/iwlwifi/iwl-tx.c @@ -194,10 +194,34 @@ void iwl_cmd_queue_free(struct iwl_priv *priv) struct iwl_queue *q = &txq->q; struct device *dev = &priv->pci_dev->dev; int i; + bool huge = false; if (q->n_bd == 0) return; + for (; q->read_ptr != q->write_ptr; + q->read_ptr = iwl_queue_inc_wrap(q->read_ptr, q->n_bd)) { + /* we have no way to tell if it is a huge cmd ATM */ + i = get_cmd_index(q, q->read_ptr, 0); + + if (txq->meta[i].flags & CMD_SIZE_HUGE) { + huge = true; + continue; + } + + pci_unmap_single(priv->pci_dev, + pci_unmap_addr(&txq->meta[i], mapping), + pci_unmap_len(&txq->meta[i], len), + PCI_DMA_BIDIRECTIONAL); + } + if (huge) { + i = q->n_window; + pci_unmap_single(priv->pci_dev, + pci_unmap_addr(&txq->meta[i], mapping), + pci_unmap_len(&txq->meta[i], len), + PCI_DMA_BIDIRECTIONAL); + } + /* De-alloc array of command/tx buffers */ for (i = 0; i <= TFD_CMD_SLOTS; i++) kfree(txq->cmd[i]); @@ -410,6 +434,26 @@ out_free_arrays: } EXPORT_SYMBOL(iwl_tx_queue_init); +void iwl_tx_queue_reset(struct iwl_priv *priv, struct iwl_tx_queue *txq, + int slots_num, u32 txq_id) +{ + int actual_slots = slots_num; + + if (txq_id == IWL_CMD_QUEUE_NUM) + actual_slots++; + + memset(txq->meta, 0, sizeof(struct iwl_cmd_meta) * actual_slots); + + txq->need_update = 0; + + /* Initialize queue's high/low-water marks, and head/tail indexes */ + iwl_queue_init(priv, &txq->q, TFD_QUEUE_SIZE_MAX, slots_num, txq_id); + + /* Tell device where to find queue */ + priv->cfg->ops->lib->txq_init(priv, txq); +} +EXPORT_SYMBOL(iwl_tx_queue_reset); + /** * iwl_hw_txq_ctx_free - Free TXQ Context * @@ -421,8 +465,7 @@ void iwl_hw_txq_ctx_free(struct iwl_priv *priv) /* Tx queues */ if (priv->txq) { - for (txq_id = 0; txq_id < priv->hw_params.max_txq_num; - txq_id++) + for (txq_id = 0; txq_id < priv->hw_params.max_txq_num; txq_id++) if (txq_id == IWL_CMD_QUEUE_NUM) iwl_cmd_queue_free(priv); else @@ -438,15 +481,15 @@ void iwl_hw_txq_ctx_free(struct iwl_priv *priv) EXPORT_SYMBOL(iwl_hw_txq_ctx_free); /** - * iwl_txq_ctx_reset - Reset TX queue context - * Destroys all DMA structures and initialize them again + * iwl_txq_ctx_alloc - allocate TX queue context + * Allocate all Tx DMA structures and initialize them * * @param priv * @return error code */ -int iwl_txq_ctx_reset(struct iwl_priv *priv) +int iwl_txq_ctx_alloc(struct iwl_priv *priv) { - int ret = 0; + int ret; int txq_id, slots_num; unsigned long flags; @@ -504,8 +547,31 @@ int iwl_txq_ctx_reset(struct iwl_priv *priv) return ret; } +void iwl_txq_ctx_reset(struct iwl_priv *priv) +{ + int txq_id, slots_num; + unsigned long flags; + + spin_lock_irqsave(&priv->lock, flags); + + /* Turn off all Tx DMA fifos */ + priv->cfg->ops->lib->txq_set_sched(priv, 0); + + /* Tell NIC where to find the "keep warm" buffer */ + iwl_write_direct32(priv, FH_KW_MEM_ADDR_REG, priv->kw.dma >> 4); + + spin_unlock_irqrestore(&priv->lock, flags); + + /* Alloc and init all Tx queues, including the command queue (#4) */ + for (txq_id = 0; txq_id < priv->hw_params.max_txq_num; txq_id++) { + slots_num = txq_id == IWL_CMD_QUEUE_NUM ? + TFD_CMD_SLOTS : TFD_TX_CMD_SLOTS; + iwl_tx_queue_reset(priv, &priv->txq[txq_id], slots_num, txq_id); + } +} + /** - * iwl_txq_ctx_stop - Stop all Tx DMA channels, free Tx queue memory + * iwl_txq_ctx_stop - Stop all Tx DMA channels */ void iwl_txq_ctx_stop(struct iwl_priv *priv) { @@ -525,9 +591,6 @@ void iwl_txq_ctx_stop(struct iwl_priv *priv) 1000); } spin_unlock_irqrestore(&priv->lock, flags); - - /* Deallocate memory for all Tx queues */ - iwl_hw_txq_ctx_free(priv); } EXPORT_SYMBOL(iwl_txq_ctx_stop); @@ -1050,6 +1113,14 @@ int iwl_enqueue_hcmd(struct iwl_priv *priv, struct iwl_host_cmd *cmd) spin_lock_irqsave(&priv->hcmd_lock, flags); + /* If this is a huge cmd, mark the huge flag also on the meta.flags + * of the _original_ cmd. This is used for DMA mapping clean up. + */ + if (cmd->flags & CMD_SIZE_HUGE) { + idx = get_cmd_index(q, q->write_ptr, 0); + txq->meta[idx].flags = CMD_SIZE_HUGE; + } + idx = get_cmd_index(q, q->write_ptr, cmd->flags & CMD_SIZE_HUGE); out_cmd = txq->cmd[idx]; out_meta = &txq->meta[idx]; @@ -1227,6 +1298,7 @@ void iwl_tx_cmd_complete(struct iwl_priv *priv, struct iwl_rx_mem_buffer *rxb) bool huge = !!(pkt->hdr.sequence & SEQ_HUGE_FRAME); struct iwl_device_cmd *cmd; struct iwl_cmd_meta *meta; + struct iwl_tx_queue *txq = &priv->txq[IWL_CMD_QUEUE_NUM]; /* If a Tx command is being handled and it isn't in the actual * command queue then there a command routing bug has been introduced @@ -1240,9 +1312,17 @@ void iwl_tx_cmd_complete(struct iwl_priv *priv, struct iwl_rx_mem_buffer *rxb) return; } - cmd_index = get_cmd_index(&priv->txq[IWL_CMD_QUEUE_NUM].q, index, huge); - cmd = priv->txq[IWL_CMD_QUEUE_NUM].cmd[cmd_index]; - meta = &priv->txq[IWL_CMD_QUEUE_NUM].meta[cmd_index]; + /* If this is a huge cmd, clear the huge flag on the meta.flags + * of the _original_ cmd. So that iwl_cmd_queue_free won't unmap + * the DMA buffer for the scan (huge) command. + */ + if (huge) { + cmd_index = get_cmd_index(&txq->q, index, 0); + txq->meta[cmd_index].flags = 0; + } + cmd_index = get_cmd_index(&txq->q, index, huge); + cmd = txq->cmd[cmd_index]; + meta = &txq->meta[cmd_index]; pci_unmap_single(priv->pci_dev, pci_unmap_addr(meta, mapping), @@ -1264,6 +1344,7 @@ void iwl_tx_cmd_complete(struct iwl_priv *priv, struct iwl_rx_mem_buffer *rxb) get_cmd_string(cmd->hdr.cmd)); wake_up_interruptible(&priv->wait_command_queue); } + meta->flags = 0; } EXPORT_SYMBOL(iwl_tx_cmd_complete); diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index 5be11c99e18f..e69d238c5af0 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -236,6 +236,10 @@ static int vq_memory_access_ok(void __user *log_base, struct vhost_memory *mem, int log_all) { int i; + + if (!mem) + return 0; + for (i = 0; i < mem->nregions; ++i) { struct vhost_memory_region *m = mem->regions + i; unsigned long a = m->userspace_addr; diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index aa3cd7cc3e40..412593703d1e 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -337,16 +337,15 @@ out: /* * Get ref for the oldest snapc for an inode with dirty data... that is, the * only snap context we are allowed to write back. - * - * Caller holds i_lock. */ -static struct ceph_snap_context *__get_oldest_context(struct inode *inode, - u64 *snap_size) +static struct ceph_snap_context *get_oldest_context(struct inode *inode, + u64 *snap_size) { struct ceph_inode_info *ci = ceph_inode(inode); struct ceph_snap_context *snapc = NULL; struct ceph_cap_snap *capsnap = NULL; + spin_lock(&inode->i_lock); list_for_each_entry(capsnap, &ci->i_cap_snaps, ci_item) { dout(" cap_snap %p snapc %p has %d dirty pages\n", capsnap, capsnap->context, capsnap->dirty_pages); @@ -357,21 +356,11 @@ static struct ceph_snap_context *__get_oldest_context(struct inode *inode, break; } } - if (!snapc && ci->i_snap_realm) { - snapc = ceph_get_snap_context(ci->i_snap_realm->cached_context); + if (!snapc && ci->i_head_snapc) { + snapc = ceph_get_snap_context(ci->i_head_snapc); dout(" head snapc %p has %d dirty pages\n", snapc, ci->i_wrbuffer_ref_head); } - return snapc; -} - -static struct ceph_snap_context *get_oldest_context(struct inode *inode, - u64 *snap_size) -{ - struct ceph_snap_context *snapc = NULL; - - spin_lock(&inode->i_lock); - snapc = __get_oldest_context(inode, snap_size); spin_unlock(&inode->i_lock); return snapc; } @@ -392,7 +381,7 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc) int len = PAGE_CACHE_SIZE; loff_t i_size; int err = 0; - struct ceph_snap_context *snapc; + struct ceph_snap_context *snapc, *oldest; u64 snap_size = 0; long writeback_stat; @@ -413,13 +402,16 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc) dout("writepage %p page %p not dirty?\n", inode, page); goto out; } - if (snapc != get_oldest_context(inode, &snap_size)) { + oldest = get_oldest_context(inode, &snap_size); + if (snapc->seq > oldest->seq) { dout("writepage %p page %p snapc %p not writeable - noop\n", inode, page, (void *)page->private); /* we should only noop if called by kswapd */ WARN_ON((current->flags & PF_MEMALLOC) == 0); + ceph_put_snap_context(oldest); goto out; } + ceph_put_snap_context(oldest); /* is this a partial page at end of file? */ if (snap_size) @@ -458,7 +450,7 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc) ClearPagePrivate(page); end_page_writeback(page); ceph_put_wrbuffer_cap_refs(ci, 1, snapc); - ceph_put_snap_context(snapc); + ceph_put_snap_context(snapc); /* page's reference */ out: return err; } @@ -558,9 +550,9 @@ static void writepages_finish(struct ceph_osd_request *req, dout("inode %p skipping page %p\n", inode, page); wbc->pages_skipped++; } + ceph_put_snap_context((void *)page->private); page->private = 0; ClearPagePrivate(page); - ceph_put_snap_context(snapc); dout("unlocking %d %p\n", i, page); end_page_writeback(page); @@ -618,7 +610,7 @@ static int ceph_writepages_start(struct address_space *mapping, int range_whole = 0; int should_loop = 1; pgoff_t max_pages = 0, max_pages_ever = 0; - struct ceph_snap_context *snapc = NULL, *last_snapc = NULL; + struct ceph_snap_context *snapc = NULL, *last_snapc = NULL, *pgsnapc; struct pagevec pvec; int done = 0; int rc = 0; @@ -770,9 +762,10 @@ get_more_pages: } /* only if matching snap context */ - if (snapc != (void *)page->private) { - dout("page snapc %p != oldest %p\n", - (void *)page->private, snapc); + pgsnapc = (void *)page->private; + if (pgsnapc->seq > snapc->seq) { + dout("page snapc %p %lld > oldest %p %lld\n", + pgsnapc, pgsnapc->seq, snapc, snapc->seq); unlock_page(page); if (!locked_pages) continue; /* keep looking for snap */ @@ -914,7 +907,10 @@ static int context_is_writeable_or_written(struct inode *inode, struct ceph_snap_context *snapc) { struct ceph_snap_context *oldest = get_oldest_context(inode, NULL); - return !oldest || snapc->seq <= oldest->seq; + int ret = !oldest || snapc->seq <= oldest->seq; + + ceph_put_snap_context(oldest); + return ret; } /* @@ -936,8 +932,8 @@ static int ceph_update_writeable_page(struct file *file, int pos_in_page = pos & ~PAGE_CACHE_MASK; int end_in_page = pos_in_page + len; loff_t i_size; - struct ceph_snap_context *snapc; int r; + struct ceph_snap_context *snapc, *oldest; retry_locked: /* writepages currently holds page lock, but if we change that later, */ @@ -947,23 +943,24 @@ retry_locked: BUG_ON(!ci->i_snap_realm); down_read(&mdsc->snap_rwsem); BUG_ON(!ci->i_snap_realm->cached_context); - if (page->private && - (void *)page->private != ci->i_snap_realm->cached_context) { + snapc = (void *)page->private; + if (snapc && snapc != ci->i_head_snapc) { /* * this page is already dirty in another (older) snap * context! is it writeable now? */ - snapc = get_oldest_context(inode, NULL); + oldest = get_oldest_context(inode, NULL); up_read(&mdsc->snap_rwsem); - if (snapc != (void *)page->private) { + if (snapc->seq > oldest->seq) { + ceph_put_snap_context(oldest); dout(" page %p snapc %p not current or oldest\n", - page, (void *)page->private); + page, snapc); /* * queue for writeback, and wait for snapc to * be writeable or written */ - snapc = ceph_get_snap_context((void *)page->private); + snapc = ceph_get_snap_context(snapc); unlock_page(page); ceph_queue_writeback(inode); r = wait_event_interruptible(ci->i_cap_wq, @@ -973,6 +970,7 @@ retry_locked: return r; return -EAGAIN; } + ceph_put_snap_context(oldest); /* yay, writeable, do it now (without dropping page lock) */ dout(" page %p snapc %p not current, but oldest\n", diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index 3710e077a857..aa2239fa9a3b 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -1205,6 +1205,12 @@ retry: if (capsnap->dirty_pages || capsnap->writing) continue; + /* + * if cap writeback already occurred, we should have dropped + * the capsnap in ceph_put_wrbuffer_cap_refs. + */ + BUG_ON(capsnap->dirty == 0); + /* pick mds, take s_mutex */ mds = __ceph_get_cap_mds(ci, &mseq); if (session && session->s_mds != mds) { @@ -2118,8 +2124,8 @@ void ceph_put_cap_refs(struct ceph_inode_info *ci, int had) } spin_unlock(&inode->i_lock); - dout("put_cap_refs %p had %s %s\n", inode, ceph_cap_string(had), - last ? "last" : ""); + dout("put_cap_refs %p had %s%s%s\n", inode, ceph_cap_string(had), + last ? " last" : "", put ? " put" : ""); if (last && !flushsnaps) ceph_check_caps(ci, 0, NULL); @@ -2143,7 +2149,8 @@ void ceph_put_wrbuffer_cap_refs(struct ceph_inode_info *ci, int nr, { struct inode *inode = &ci->vfs_inode; int last = 0; - int last_snap = 0; + int complete_capsnap = 0; + int drop_capsnap = 0; int found = 0; struct ceph_cap_snap *capsnap = NULL; @@ -2166,19 +2173,32 @@ void ceph_put_wrbuffer_cap_refs(struct ceph_inode_info *ci, int nr, list_for_each_entry(capsnap, &ci->i_cap_snaps, ci_item) { if (capsnap->context == snapc) { found = 1; - capsnap->dirty_pages -= nr; - last_snap = !capsnap->dirty_pages; break; } } BUG_ON(!found); + capsnap->dirty_pages -= nr; + if (capsnap->dirty_pages == 0) { + complete_capsnap = 1; + if (capsnap->dirty == 0) + /* cap writeback completed before we created + * the cap_snap; no FLUSHSNAP is needed */ + drop_capsnap = 1; + } dout("put_wrbuffer_cap_refs on %p cap_snap %p " - " snap %lld %d/%d -> %d/%d %s%s\n", + " snap %lld %d/%d -> %d/%d %s%s%s\n", inode, capsnap, capsnap->context->seq, ci->i_wrbuffer_ref+nr, capsnap->dirty_pages + nr, ci->i_wrbuffer_ref, capsnap->dirty_pages, last ? " (wrbuffer last)" : "", - last_snap ? " (capsnap last)" : ""); + complete_capsnap ? " (complete capsnap)" : "", + drop_capsnap ? " (drop capsnap)" : ""); + if (drop_capsnap) { + ceph_put_snap_context(capsnap->context); + list_del(&capsnap->ci_item); + list_del(&capsnap->flushing_item); + ceph_put_cap_snap(capsnap); + } } spin_unlock(&inode->i_lock); @@ -2186,10 +2206,12 @@ void ceph_put_wrbuffer_cap_refs(struct ceph_inode_info *ci, int nr, if (last) { ceph_check_caps(ci, CHECK_CAPS_AUTHONLY, NULL); iput(inode); - } else if (last_snap) { + } else if (complete_capsnap) { ceph_flush_snaps(ci); wake_up(&ci->i_cap_wq); } + if (drop_capsnap) + iput(inode); } /* @@ -2465,8 +2487,8 @@ static void handle_cap_flushsnap_ack(struct inode *inode, u64 flush_tid, break; } WARN_ON(capsnap->dirty_pages || capsnap->writing); - dout(" removing cap_snap %p follows %lld\n", - capsnap, follows); + dout(" removing %p cap_snap %p follows %lld\n", + inode, capsnap, follows); ceph_put_snap_context(capsnap->context); list_del(&capsnap->ci_item); list_del(&capsnap->flushing_item); diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c index 7261dc6c2ead..ea8ee2e526aa 100644 --- a/fs/ceph/dir.c +++ b/fs/ceph/dir.c @@ -171,11 +171,11 @@ more: spin_lock(&inode->i_lock); spin_lock(&dcache_lock); + last = dentry; + if (err < 0) goto out_unlock; - last = dentry; - p = p->prev; filp->f_pos++; @@ -312,7 +312,7 @@ more: req->r_readdir_offset = fi->next_offset; req->r_args.readdir.frag = cpu_to_le32(frag); req->r_args.readdir.max_entries = cpu_to_le32(max_entries); - req->r_num_caps = max_entries; + req->r_num_caps = max_entries + 1; err = ceph_mdsc_do_request(mdsc, NULL, req); if (err < 0) { ceph_mdsc_put_request(req); @@ -489,6 +489,7 @@ struct dentry *ceph_finish_lookup(struct ceph_mds_request *req, struct inode *inode = ceph_get_snapdir(parent); dout("ENOENT on snapdir %p '%.*s', linking to snapdir %p\n", dentry, dentry->d_name.len, dentry->d_name.name, inode); + BUG_ON(!d_unhashed(dentry)); d_add(dentry, inode); err = 0; } diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index aca82d55cc53..26f883c275e8 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -886,6 +886,7 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req, struct inode *in = NULL; struct ceph_mds_reply_inode *ininfo; struct ceph_vino vino; + struct ceph_client *client = ceph_sb_to_client(sb); int i = 0; int err = 0; @@ -949,7 +950,14 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req, return err; } - if (rinfo->head->is_dentry && !req->r_aborted) { + /* + * ignore null lease/binding on snapdir ENOENT, or else we + * will have trouble splicing in the virtual snapdir later + */ + if (rinfo->head->is_dentry && !req->r_aborted && + (rinfo->head->is_target || strncmp(req->r_dentry->d_name.name, + client->mount_args->snapdir_name, + req->r_dentry->d_name.len))) { /* * lookup link rename : null -> possibly existing inode * mknod symlink mkdir : null -> new inode diff --git a/fs/ceph/messenger.c b/fs/ceph/messenger.c index 8f1715ffbe4b..cdaaa131add3 100644 --- a/fs/ceph/messenger.c +++ b/fs/ceph/messenger.c @@ -30,6 +30,10 @@ static char tag_msg = CEPH_MSGR_TAG_MSG; static char tag_ack = CEPH_MSGR_TAG_ACK; static char tag_keepalive = CEPH_MSGR_TAG_KEEPALIVE; +#ifdef CONFIG_LOCKDEP +static struct lock_class_key socket_class; +#endif + static void queue_con(struct ceph_connection *con); static void con_work(struct work_struct *); @@ -228,6 +232,10 @@ static struct socket *ceph_tcp_connect(struct ceph_connection *con) con->sock = sock; sock->sk->sk_allocation = GFP_NOFS; +#ifdef CONFIG_LOCKDEP + lockdep_set_class(&sock->sk->sk_lock, &socket_class); +#endif + set_sock_callbacks(sock, con); dout("connect %s\n", pr_addr(&con->peer_addr.in_addr)); @@ -333,6 +341,7 @@ static void reset_connection(struct ceph_connection *con) con->out_msg = NULL; } con->in_seq = 0; + con->in_seq_acked = 0; } /* diff --git a/fs/ceph/osdmap.c b/fs/ceph/osdmap.c index 21c6623c4b07..2e2c15eed82a 100644 --- a/fs/ceph/osdmap.c +++ b/fs/ceph/osdmap.c @@ -314,71 +314,6 @@ bad: return ERR_PTR(err); } - -/* - * osd map - */ -void ceph_osdmap_destroy(struct ceph_osdmap *map) -{ - dout("osdmap_destroy %p\n", map); - if (map->crush) - crush_destroy(map->crush); - while (!RB_EMPTY_ROOT(&map->pg_temp)) { - struct ceph_pg_mapping *pg = - rb_entry(rb_first(&map->pg_temp), - struct ceph_pg_mapping, node); - rb_erase(&pg->node, &map->pg_temp); - kfree(pg); - } - while (!RB_EMPTY_ROOT(&map->pg_pools)) { - struct ceph_pg_pool_info *pi = - rb_entry(rb_first(&map->pg_pools), - struct ceph_pg_pool_info, node); - rb_erase(&pi->node, &map->pg_pools); - kfree(pi); - } - kfree(map->osd_state); - kfree(map->osd_weight); - kfree(map->osd_addr); - kfree(map); -} - -/* - * adjust max osd value. reallocate arrays. - */ -static int osdmap_set_max_osd(struct ceph_osdmap *map, int max) -{ - u8 *state; - struct ceph_entity_addr *addr; - u32 *weight; - - state = kcalloc(max, sizeof(*state), GFP_NOFS); - addr = kcalloc(max, sizeof(*addr), GFP_NOFS); - weight = kcalloc(max, sizeof(*weight), GFP_NOFS); - if (state == NULL || addr == NULL || weight == NULL) { - kfree(state); - kfree(addr); - kfree(weight); - return -ENOMEM; - } - - /* copy old? */ - if (map->osd_state) { - memcpy(state, map->osd_state, map->max_osd*sizeof(*state)); - memcpy(addr, map->osd_addr, map->max_osd*sizeof(*addr)); - memcpy(weight, map->osd_weight, map->max_osd*sizeof(*weight)); - kfree(map->osd_state); - kfree(map->osd_addr); - kfree(map->osd_weight); - } - - map->osd_state = state; - map->osd_weight = weight; - map->osd_addr = addr; - map->max_osd = max; - return 0; -} - /* * rbtree of pg_mapping for handling pg_temp (explicit mapping of pgid * to a set of osds) @@ -482,6 +417,13 @@ static struct ceph_pg_pool_info *__lookup_pg_pool(struct rb_root *root, int id) return NULL; } +static void __remove_pg_pool(struct rb_root *root, struct ceph_pg_pool_info *pi) +{ + rb_erase(&pi->node, root); + kfree(pi->name); + kfree(pi); +} + void __decode_pool(void **p, struct ceph_pg_pool_info *pi) { ceph_decode_copy(p, &pi->v, sizeof(pi->v)); @@ -490,6 +432,98 @@ void __decode_pool(void **p, struct ceph_pg_pool_info *pi) *p += le32_to_cpu(pi->v.num_removed_snap_intervals) * sizeof(u64) * 2; } +static int __decode_pool_names(void **p, void *end, struct ceph_osdmap *map) +{ + struct ceph_pg_pool_info *pi; + u32 num, len, pool; + + ceph_decode_32_safe(p, end, num, bad); + dout(" %d pool names\n", num); + while (num--) { + ceph_decode_32_safe(p, end, pool, bad); + ceph_decode_32_safe(p, end, len, bad); + dout(" pool %d len %d\n", pool, len); + pi = __lookup_pg_pool(&map->pg_pools, pool); + if (pi) { + kfree(pi->name); + pi->name = kmalloc(len + 1, GFP_NOFS); + if (pi->name) { + memcpy(pi->name, *p, len); + pi->name[len] = '\0'; + dout(" name is %s\n", pi->name); + } + } + *p += len; + } + return 0; + +bad: + return -EINVAL; +} + +/* + * osd map + */ +void ceph_osdmap_destroy(struct ceph_osdmap *map) +{ + dout("osdmap_destroy %p\n", map); + if (map->crush) + crush_destroy(map->crush); + while (!RB_EMPTY_ROOT(&map->pg_temp)) { + struct ceph_pg_mapping *pg = + rb_entry(rb_first(&map->pg_temp), + struct ceph_pg_mapping, node); + rb_erase(&pg->node, &map->pg_temp); + kfree(pg); + } + while (!RB_EMPTY_ROOT(&map->pg_pools)) { + struct ceph_pg_pool_info *pi = + rb_entry(rb_first(&map->pg_pools), + struct ceph_pg_pool_info, node); + __remove_pg_pool(&map->pg_pools, pi); + } + kfree(map->osd_state); + kfree(map->osd_weight); + kfree(map->osd_addr); + kfree(map); +} + +/* + * adjust max osd value. reallocate arrays. + */ +static int osdmap_set_max_osd(struct ceph_osdmap *map, int max) +{ + u8 *state; + struct ceph_entity_addr *addr; + u32 *weight; + + state = kcalloc(max, sizeof(*state), GFP_NOFS); + addr = kcalloc(max, sizeof(*addr), GFP_NOFS); + weight = kcalloc(max, sizeof(*weight), GFP_NOFS); + if (state == NULL || addr == NULL || weight == NULL) { + kfree(state); + kfree(addr); + kfree(weight); + return -ENOMEM; + } + + /* copy old? */ + if (map->osd_state) { + memcpy(state, map->osd_state, map->max_osd*sizeof(*state)); + memcpy(addr, map->osd_addr, map->max_osd*sizeof(*addr)); + memcpy(weight, map->osd_weight, map->max_osd*sizeof(*weight)); + kfree(map->osd_state); + kfree(map->osd_addr); + kfree(map->osd_weight); + } + + map->osd_state = state; + map->osd_weight = weight; + map->osd_addr = addr; + map->max_osd = max; + return 0; +} + /* * decode a full map. */ @@ -526,7 +560,7 @@ struct ceph_osdmap *osdmap_decode(void **p, void *end) ceph_decode_32_safe(p, end, max, bad); while (max--) { ceph_decode_need(p, end, 4 + 1 + sizeof(pi->v), bad); - pi = kmalloc(sizeof(*pi), GFP_NOFS); + pi = kzalloc(sizeof(*pi), GFP_NOFS); if (!pi) goto bad; pi->id = ceph_decode_32(p); @@ -539,6 +573,10 @@ struct ceph_osdmap *osdmap_decode(void **p, void *end) __decode_pool(p, pi); __insert_pg_pool(&map->pg_pools, pi); } + + if (version >= 5 && __decode_pool_names(p, end, map) < 0) + goto bad; + ceph_decode_32_safe(p, end, map->pool_max, bad); ceph_decode_32_safe(p, end, map->flags, bad); @@ -712,7 +750,7 @@ struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end, } pi = __lookup_pg_pool(&map->pg_pools, pool); if (!pi) { - pi = kmalloc(sizeof(*pi), GFP_NOFS); + pi = kzalloc(sizeof(*pi), GFP_NOFS); if (!pi) { err = -ENOMEM; goto bad; @@ -722,6 +760,8 @@ struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end, } __decode_pool(p, pi); } + if (version >= 5 && __decode_pool_names(p, end, map) < 0) + goto bad; /* old_pool */ ceph_decode_32_safe(p, end, len, bad); @@ -730,10 +770,8 @@ struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end, ceph_decode_32_safe(p, end, pool, bad); pi = __lookup_pg_pool(&map->pg_pools, pool); - if (pi) { - rb_erase(&pi->node, &map->pg_pools); - kfree(pi); - } + if (pi) + __remove_pg_pool(&map->pg_pools, pi); } /* new_up */ diff --git a/fs/ceph/osdmap.h b/fs/ceph/osdmap.h index 1fb55afb2642..8bc9f1e4f562 100644 --- a/fs/ceph/osdmap.h +++ b/fs/ceph/osdmap.h @@ -23,6 +23,7 @@ struct ceph_pg_pool_info { int id; struct ceph_pg_pool v; int pg_num_mask, pgp_num_mask, lpg_num_mask, lpgp_num_mask; + char *name; }; struct ceph_pg_mapping { diff --git a/fs/ceph/rados.h b/fs/ceph/rados.h index 26ac8b89a676..a1fc1d017b58 100644 --- a/fs/ceph/rados.h +++ b/fs/ceph/rados.h @@ -11,8 +11,10 @@ /* * osdmap encoding versions */ -#define CEPH_OSDMAP_INC_VERSION 4 -#define CEPH_OSDMAP_VERSION 4 +#define CEPH_OSDMAP_INC_VERSION 5 +#define CEPH_OSDMAP_INC_VERSION_EXT 5 +#define CEPH_OSDMAP_VERSION 5 +#define CEPH_OSDMAP_VERSION_EXT 5 /* * fs id diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c index e6f9bc57d472..2b881262ef67 100644 --- a/fs/ceph/snap.c +++ b/fs/ceph/snap.c @@ -431,8 +431,7 @@ static int dup_array(u64 **dst, __le64 *src, int num) * Caller must hold snap_rwsem for read (i.e., the realm topology won't * change). */ -void ceph_queue_cap_snap(struct ceph_inode_info *ci, - struct ceph_snap_context *snapc) +void ceph_queue_cap_snap(struct ceph_inode_info *ci) { struct inode *inode = &ci->vfs_inode; struct ceph_cap_snap *capsnap; @@ -451,10 +450,11 @@ void ceph_queue_cap_snap(struct ceph_inode_info *ci, as no new writes are allowed to start when pending, so any writes in progress now were started before the previous cap_snap. lucky us. */ - dout("queue_cap_snap %p snapc %p seq %llu used %d" - " already pending\n", inode, snapc, snapc->seq, used); + dout("queue_cap_snap %p already pending\n", inode); kfree(capsnap); } else if (ci->i_wrbuffer_ref_head || (used & CEPH_CAP_FILE_WR)) { + struct ceph_snap_context *snapc = ci->i_head_snapc; + igrab(inode); atomic_set(&capsnap->nref, 1); @@ -463,7 +463,6 @@ void ceph_queue_cap_snap(struct ceph_inode_info *ci, INIT_LIST_HEAD(&capsnap->flushing_item); capsnap->follows = snapc->seq - 1; - capsnap->context = ceph_get_snap_context(snapc); capsnap->issued = __ceph_caps_issued(ci, NULL); capsnap->dirty = __ceph_caps_dirty(ci); @@ -480,7 +479,7 @@ void ceph_queue_cap_snap(struct ceph_inode_info *ci, snapshot. */ capsnap->dirty_pages = ci->i_wrbuffer_ref_head; ci->i_wrbuffer_ref_head = 0; - ceph_put_snap_context(ci->i_head_snapc); + capsnap->context = snapc; ci->i_head_snapc = NULL; list_add_tail(&capsnap->ci_item, &ci->i_cap_snaps); @@ -522,15 +521,17 @@ int __ceph_finish_cap_snap(struct ceph_inode_info *ci, capsnap->ctime = inode->i_ctime; capsnap->time_warp_seq = ci->i_time_warp_seq; if (capsnap->dirty_pages) { - dout("finish_cap_snap %p cap_snap %p snapc %p %llu s=%llu " + dout("finish_cap_snap %p cap_snap %p snapc %p %llu %s s=%llu " "still has %d dirty pages\n", inode, capsnap, capsnap->context, capsnap->context->seq, - capsnap->size, capsnap->dirty_pages); + ceph_cap_string(capsnap->dirty), capsnap->size, + capsnap->dirty_pages); return 0; } - dout("finish_cap_snap %p cap_snap %p snapc %p %llu s=%llu clean\n", + dout("finish_cap_snap %p cap_snap %p snapc %p %llu %s s=%llu\n", inode, capsnap, capsnap->context, - capsnap->context->seq, capsnap->size); + capsnap->context->seq, ceph_cap_string(capsnap->dirty), + capsnap->size); spin_lock(&mdsc->snap_flush_lock); list_add_tail(&ci->i_snap_flush_item, &mdsc->snap_flush_list); @@ -602,7 +603,7 @@ more: if (lastinode) iput(lastinode); lastinode = inode; - ceph_queue_cap_snap(ci, realm->cached_context); + ceph_queue_cap_snap(ci); spin_lock(&realm->inodes_with_caps_lock); } spin_unlock(&realm->inodes_with_caps_lock); @@ -824,8 +825,7 @@ void ceph_handle_snap(struct ceph_mds_client *mdsc, spin_unlock(&realm->inodes_with_caps_lock); spin_unlock(&inode->i_lock); - ceph_queue_cap_snap(ci, - ci->i_snap_realm->cached_context); + ceph_queue_cap_snap(ci); iput(inode); continue; diff --git a/fs/ceph/super.h b/fs/ceph/super.h index ca702c67bc66..e30dfbb056c3 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -715,8 +715,7 @@ extern int ceph_update_snap_trace(struct ceph_mds_client *m, extern void ceph_handle_snap(struct ceph_mds_client *mdsc, struct ceph_mds_session *session, struct ceph_msg *msg); -extern void ceph_queue_cap_snap(struct ceph_inode_info *ci, - struct ceph_snap_context *snapc); +extern void ceph_queue_cap_snap(struct ceph_inode_info *ci); extern int __ceph_finish_cap_snap(struct ceph_inode_info *ci, struct ceph_cap_snap *capsnap); extern void ceph_cleanup_empty_realms(struct ceph_mds_client *mdsc); diff --git a/fs/nfs/client.c b/fs/nfs/client.c index 2a3d352c0bff..a8766c4ef2e0 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -1294,7 +1294,8 @@ static int nfs4_init_server(struct nfs_server *server, /* Initialise the client representation from the mount data */ server->flags = data->flags; - server->caps |= NFS_CAP_ATOMIC_OPEN|NFS_CAP_CHANGE_ATTR; + server->caps |= NFS_CAP_ATOMIC_OPEN|NFS_CAP_CHANGE_ATTR| + NFS_CAP_POSIX_LOCK; server->options = data->options; /* Get a client record */ diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index c6f2750648f4..be46f26c9a56 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -1025,12 +1025,12 @@ static struct dentry *nfs_atomic_lookup(struct inode *dir, struct dentry *dentry res = NULL; goto out; /* This turned out not to be a regular file */ + case -EISDIR: case -ENOTDIR: goto no_open; case -ELOOP: if (!(nd->intent.open.flags & O_NOFOLLOW)) goto no_open; - /* case -EISDIR: */ /* case -EINVAL: */ default: goto out; diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 737128f777f3..50a56edca0b5 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -623,10 +623,10 @@ struct nfs_open_context *nfs_find_open_context(struct inode *inode, struct rpc_c list_for_each_entry(pos, &nfsi->open_files, list) { if (cred != NULL && pos->cred != cred) continue; - if ((pos->mode & mode) == mode) { - ctx = get_nfs_open_context(pos); - break; - } + if ((pos->mode & (FMODE_READ|FMODE_WRITE)) != mode) + continue; + ctx = get_nfs_open_context(pos); + break; } spin_unlock(&inode->i_lock); return ctx; diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index fe0cd9eb1d4d..638067007c65 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -1523,6 +1523,8 @@ static int _nfs4_proc_open(struct nfs4_opendata *data) nfs_post_op_update_inode(dir, o_res->dir_attr); } else nfs_refresh_inode(dir, o_res->dir_attr); + if ((o_res->rflags & NFS4_OPEN_RESULT_LOCKTYPE_POSIX) == 0) + server->caps &= ~NFS_CAP_POSIX_LOCK; if(o_res->rflags & NFS4_OPEN_RESULT_CONFIRM) { status = _nfs4_proc_open_confirm(data); if (status != 0) @@ -1664,7 +1666,7 @@ static int _nfs4_do_open(struct inode *dir, struct path *path, fmode_t fmode, in status = PTR_ERR(state); if (IS_ERR(state)) goto err_opendata_put; - if ((opendata->o_res.rflags & NFS4_OPEN_RESULT_LOCKTYPE_POSIX) != 0) + if (server->caps & NFS_CAP_POSIX_LOCK) set_bit(NFS_STATE_POSIX_LOCKS, &state->flags); nfs4_opendata_put(opendata); nfs4_put_state_owner(sp); diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 53ff70e23993..de38d63aa920 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -201,6 +201,7 @@ static int nfs_set_page_writeback(struct page *page) struct inode *inode = page->mapping->host; struct nfs_server *nfss = NFS_SERVER(inode); + page_cache_get(page); if (atomic_long_inc_return(&nfss->writeback) > NFS_CONGESTION_ON_THRESH) { set_bdi_congested(&nfss->backing_dev_info, @@ -216,6 +217,7 @@ static void nfs_end_page_writeback(struct page *page) struct nfs_server *nfss = NFS_SERVER(inode); end_page_writeback(page); + page_cache_release(page); if (atomic_long_dec_return(&nfss->writeback) < NFS_CONGESTION_OFF_THRESH) clear_bdi_congested(&nfss->backing_dev_info, BLK_RW_ASYNC); } @@ -421,6 +423,7 @@ static void nfs_mark_request_dirty(struct nfs_page *req) { __set_page_dirty_nobuffers(req->wb_page); + __mark_inode_dirty(req->wb_page->mapping->host, I_DIRTY_DATASYNC); } #if defined(CONFIG_NFS_V3) || defined(CONFIG_NFS_V4) @@ -660,9 +663,11 @@ static int nfs_writepage_setup(struct nfs_open_context *ctx, struct page *page, req = nfs_setup_write_request(ctx, page, offset, count); if (IS_ERR(req)) return PTR_ERR(req); + nfs_mark_request_dirty(req); /* Update file length */ nfs_grow_file(page, offset, count); nfs_mark_uptodate(page, req->wb_pgbase, req->wb_bytes); + nfs_mark_request_dirty(req); nfs_clear_page_tag_locked(req); return 0; } @@ -739,8 +744,6 @@ int nfs_updatepage(struct file *file, struct page *page, status = nfs_writepage_setup(ctx, page, offset, count); if (status < 0) nfs_set_pageerror(page); - else - __set_page_dirty_nobuffers(page); dprintk("NFS: nfs_updatepage returns %d (isize %lld)\n", status, (long long)i_size_read(inode)); @@ -749,13 +752,12 @@ int nfs_updatepage(struct file *file, struct page *page, static void nfs_writepage_release(struct nfs_page *req) { + struct page *page = req->wb_page; - if (PageError(req->wb_page) || !nfs_reschedule_unstable_write(req)) { - nfs_end_page_writeback(req->wb_page); + if (PageError(req->wb_page) || !nfs_reschedule_unstable_write(req)) nfs_inode_remove_request(req); - } else - nfs_end_page_writeback(req->wb_page); nfs_clear_page_tag_locked(req); + nfs_end_page_writeback(page); } static int flush_task_priority(int how) @@ -779,7 +781,6 @@ static int nfs_write_rpcsetup(struct nfs_page *req, int how) { struct inode *inode = req->wb_context->path.dentry->d_inode; - int flags = (how & FLUSH_SYNC) ? 0 : RPC_TASK_ASYNC; int priority = flush_task_priority(how); struct rpc_task *task; struct rpc_message msg = { @@ -794,9 +795,10 @@ static int nfs_write_rpcsetup(struct nfs_page *req, .callback_ops = call_ops, .callback_data = data, .workqueue = nfsiod_workqueue, - .flags = flags, + .flags = RPC_TASK_ASYNC, .priority = priority, }; + int ret = 0; /* Set up the RPC argument and reply structs * NB: take care not to mess about with data->commit et al. */ @@ -835,10 +837,18 @@ static int nfs_write_rpcsetup(struct nfs_page *req, (unsigned long long)data->args.offset); task = rpc_run_task(&task_setup_data); - if (IS_ERR(task)) - return PTR_ERR(task); + if (IS_ERR(task)) { + ret = PTR_ERR(task); + goto out; + } + if (how & FLUSH_SYNC) { + ret = rpc_wait_for_completion_task(task); + if (ret == 0) + ret = task->tk_status; + } rpc_put_task(task); - return 0; +out: + return ret; } /* If a nfs_flush_* function fails, it should remove reqs from @head and @@ -847,9 +857,11 @@ static int nfs_write_rpcsetup(struct nfs_page *req, */ static void nfs_redirty_request(struct nfs_page *req) { + struct page *page = req->wb_page; + nfs_mark_request_dirty(req); - nfs_end_page_writeback(req->wb_page); nfs_clear_page_tag_locked(req); + nfs_end_page_writeback(page); } /* @@ -1084,16 +1096,15 @@ static void nfs_writeback_release_full(void *calldata) if (nfs_write_need_commit(data)) { memcpy(&req->wb_verf, &data->verf, sizeof(req->wb_verf)); nfs_mark_request_commit(req); - nfs_end_page_writeback(page); dprintk(" marked for commit\n"); goto next; } dprintk(" OK\n"); remove_request: - nfs_end_page_writeback(page); nfs_inode_remove_request(req); next: nfs_clear_page_tag_locked(req); + nfs_end_page_writeback(page); } nfs_writedata_release(calldata); } @@ -1207,7 +1218,6 @@ static int nfs_commit_rpcsetup(struct list_head *head, { struct nfs_page *first = nfs_list_entry(head->next); struct inode *inode = first->wb_context->path.dentry->d_inode; - int flags = (how & FLUSH_SYNC) ? 0 : RPC_TASK_ASYNC; int priority = flush_task_priority(how); struct rpc_task *task; struct rpc_message msg = { @@ -1222,7 +1232,7 @@ static int nfs_commit_rpcsetup(struct list_head *head, .callback_ops = &nfs_commit_ops, .callback_data = data, .workqueue = nfsiod_workqueue, - .flags = flags, + .flags = RPC_TASK_ASYNC, .priority = priority, }; @@ -1252,6 +1262,8 @@ static int nfs_commit_rpcsetup(struct list_head *head, task = rpc_run_task(&task_setup_data); if (IS_ERR(task)) return PTR_ERR(task); + if (how & FLUSH_SYNC) + rpc_wait_for_completion_task(task); rpc_put_task(task); return 0; } diff --git a/include/linux/firewire-cdev.h b/include/linux/firewire-cdev.h index 40b11013408e..81f3b14d5d76 100644 --- a/include/linux/firewire-cdev.h +++ b/include/linux/firewire-cdev.h @@ -1,21 +1,26 @@ /* * Char device interface. * - * Copyright (C) 2005-2006 Kristian Hoegsberg <krh@bitplanet.net> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software Foundation, - * Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * Copyright (C) 2005-2007 Kristian Hoegsberg <krh@bitplanet.net> + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice (including the next + * paragraph) shall be included in all copies or substantial portions of the + * Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * PRECISION INSIGHT AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM, DAMAGES OR + * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, + * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER + * DEALINGS IN THE SOFTWARE. */ #ifndef _LINUX_FIREWIRE_CDEV_H @@ -438,7 +443,7 @@ struct fw_cdev_remove_descriptor { * @type: %FW_CDEV_ISO_CONTEXT_TRANSMIT or %FW_CDEV_ISO_CONTEXT_RECEIVE * @header_size: Header size to strip for receive contexts * @channel: Channel to bind to - * @speed: Speed to transmit at + * @speed: Speed for transmit contexts * @closure: To be returned in &fw_cdev_event_iso_interrupt * @handle: Handle to context, written back by kernel * @@ -451,6 +456,9 @@ struct fw_cdev_remove_descriptor { * If a context was successfully created, the kernel writes back a handle to the * context, which must be passed in for subsequent operations on that context. * + * For receive contexts, @header_size must be at least 4 and must be a multiple + * of 4. + * * Note that the effect of a @header_size > 4 depends on * &fw_cdev_get_info.version, as documented at &fw_cdev_event_iso_interrupt. */ @@ -481,10 +489,34 @@ struct fw_cdev_create_iso_context { * * &struct fw_cdev_iso_packet is used to describe isochronous packet queues. * - * Use the FW_CDEV_ISO_ macros to fill in @control. The sy and tag fields are - * specified by IEEE 1394a and IEC 61883. - * - * FIXME - finish this documentation + * Use the FW_CDEV_ISO_ macros to fill in @control. + * + * For transmit packets, the header length must be a multiple of 4 and specifies + * the numbers of bytes in @header that will be prepended to the packet's + * payload; these bytes are copied into the kernel and will not be accessed + * after the ioctl has returned. The sy and tag fields are copied to the iso + * packet header (these fields are specified by IEEE 1394a and IEC 61883-1). + * The skip flag specifies that no packet is to be sent in a frame; when using + * this, all other fields except the interrupt flag must be zero. + * + * For receive packets, the header length must be a multiple of the context's + * header size; if the header length is larger than the context's header size, + * multiple packets are queued for this entry. The sy and tag fields are + * ignored. If the sync flag is set, the context drops all packets until + * a packet with a matching sy field is received (the sync value to wait for is + * specified in the &fw_cdev_start_iso structure). The payload length defines + * how many payload bytes can be received for one packet (in addition to payload + * quadlets that have been defined as headers and are stripped and returned in + * the &fw_cdev_event_iso_interrupt structure). If more bytes are received, the + * additional bytes are dropped. If less bytes are received, the remaining + * bytes in this part of the payload buffer will not be written to, not even by + * the next packet, i.e., packets received in consecutive frames will not + * necessarily be consecutive in memory. If an entry has queued multiple + * packets, the payload length is divided equally among them. + * + * When a packet with the interrupt flag set has been completed, the + * &fw_cdev_event_iso_interrupt event will be sent. An entry that has queued + * multiple receive packets is completed when its last packet is completed. */ struct fw_cdev_iso_packet { __u32 control; @@ -501,7 +533,7 @@ struct fw_cdev_iso_packet { * Queue a number of isochronous packets for reception or transmission. * This ioctl takes a pointer to an array of &fw_cdev_iso_packet structs, * which describe how to transmit from or receive into a contiguous region - * of a mmap()'ed payload buffer. As part of the packet descriptors, + * of a mmap()'ed payload buffer. As part of transmit packet descriptors, * a series of headers can be supplied, which will be prepended to the * payload during DMA. * @@ -620,8 +652,8 @@ struct fw_cdev_get_cycle_timer2 { * instead of allocated. * An %FW_CDEV_EVENT_ISO_RESOURCE_DEALLOCATED event concludes this operation. * - * To summarize, %FW_CDEV_IOC_DEALLOCATE_ISO_RESOURCE allocates iso resources - * for the lifetime of the fd or handle. + * To summarize, %FW_CDEV_IOC_ALLOCATE_ISO_RESOURCE allocates iso resources + * for the lifetime of the fd or @handle. * In contrast, %FW_CDEV_IOC_ALLOCATE_ISO_RESOURCE_ONCE allocates iso resources * for the duration of a bus generation. * diff --git a/include/linux/firewire-constants.h b/include/linux/firewire-constants.h index b316770a43fd..9c63f06e67f2 100644 --- a/include/linux/firewire-constants.h +++ b/include/linux/firewire-constants.h @@ -1,3 +1,28 @@ +/* + * IEEE 1394 constants. + * + * Copyright (C) 2005-2007 Kristian Hoegsberg <krh@bitplanet.net> + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice (including the next + * paragraph) shall be included in all copies or substantial portions of the + * Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * PRECISION INSIGHT AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM, DAMAGES OR + * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, + * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER + * DEALINGS IN THE SOFTWARE. + */ + #ifndef _LINUX_FIREWIRE_CONSTANTS_H #define _LINUX_FIREWIRE_CONSTANTS_H @@ -21,7 +46,7 @@ #define EXTCODE_WRAP_ADD 0x6 #define EXTCODE_VENDOR_DEPENDENT 0x7 -/* Juju specific tcodes */ +/* Linux firewire-core (Juju) specific tcodes */ #define TCODE_LOCK_MASK_SWAP (0x10 | EXTCODE_MASK_SWAP) #define TCODE_LOCK_COMPARE_SWAP (0x10 | EXTCODE_COMPARE_SWAP) #define TCODE_LOCK_FETCH_ADD (0x10 | EXTCODE_FETCH_ADD) @@ -36,7 +61,7 @@ #define RCODE_TYPE_ERROR 0x6 #define RCODE_ADDRESS_ERROR 0x7 -/* Juju specific rcodes */ +/* Linux firewire-core (Juju) specific rcodes */ #define RCODE_SEND_ERROR 0x10 #define RCODE_CANCELLED 0x11 #define RCODE_BUSY 0x12 diff --git a/include/linux/input/matrix_keypad.h b/include/linux/input/matrix_keypad.h index 3bd018baae20..c964cd7f436a 100644 --- a/include/linux/input/matrix_keypad.h +++ b/include/linux/input/matrix_keypad.h @@ -44,6 +44,7 @@ struct matrix_keymap_data { * @active_low: gpio polarity * @wakeup: controls whether the device should be set up as wakeup * source + * @no_autorepeat: disable key autorepeat * * This structure represents platform-specific data that use used by * matrix_keypad driver to perform proper initialization. @@ -64,6 +65,7 @@ struct matrix_keypad_platform_data { bool active_low; bool wakeup; + bool no_autorepeat; }; /** diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index 717a5e54eb1d..e82957acea56 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -176,6 +176,7 @@ struct nfs_server { #define NFS_CAP_ATIME (1U << 11) #define NFS_CAP_CTIME (1U << 12) #define NFS_CAP_MTIME (1U << 13) +#define NFS_CAP_POSIX_LOCK (1U << 14) /* maximum number of slots to use */ diff --git a/include/net/x25.h b/include/net/x25.h index 15ef9624ab75..468551ea4f1d 100644 --- a/include/net/x25.h +++ b/include/net/x25.h @@ -183,6 +183,10 @@ extern int sysctl_x25_clear_request_timeout; extern int sysctl_x25_ack_holdback_timeout; extern int sysctl_x25_forward; +extern int x25_parse_address_block(struct sk_buff *skb, + struct x25_address *called_addr, + struct x25_address *calling_addr); + extern int x25_addr_ntoa(unsigned char *, struct x25_address *, struct x25_address *); extern int x25_addr_aton(unsigned char *, struct x25_address *, diff --git a/kernel/power/user.c b/kernel/power/user.c index 4d2289626a84..a8c96212bc1b 100644 --- a/kernel/power/user.c +++ b/kernel/power/user.c @@ -420,7 +420,7 @@ static long snapshot_ioctl(struct file *filp, unsigned int cmd, * User space encodes device types as two-byte values, * so we need to recode them */ - swdev = old_decode_dev(swap_area.dev); + swdev = new_decode_dev(swap_area.dev); if (swdev) { offset = swap_area.offset; data->swap = swap_type_of(swdev, offset, NULL); diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index ff017108700d..935248bdbc47 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -356,7 +356,7 @@ config SLUB_STATS config DEBUG_KMEMLEAK bool "Kernel memory leak detector" depends on DEBUG_KERNEL && EXPERIMENTAL && !MEMORY_HOTPLUG && \ - (X86 || ARM || PPC || S390 || SUPERH || MICROBLAZE) + (X86 || ARM || PPC || S390 || SPARC64 || SUPERH || MICROBLAZE) select DEBUG_FS if SYSFS select STACKTRACE if STACKTRACE_SUPPORT diff --git a/lib/dma-debug.c b/lib/dma-debug.c index ba8b67039d13..01e64270e246 100644 --- a/lib/dma-debug.c +++ b/lib/dma-debug.c @@ -570,7 +570,7 @@ static ssize_t filter_write(struct file *file, const char __user *userbuf, * Now parse out the first token and use it as the name for the * driver to filter for. */ - for (i = 0; i < NAME_MAX_LEN; ++i) { + for (i = 0; i < NAME_MAX_LEN - 1; ++i) { current_driver_name[i] = buf[i]; if (isspace(buf[i]) || buf[i] == ' ' || buf[i] == 0) break; diff --git a/lib/vsprintf.c b/lib/vsprintf.c index 24112e5a5780..7376b7c55ffe 100644 --- a/lib/vsprintf.c +++ b/lib/vsprintf.c @@ -408,12 +408,12 @@ enum format_type { }; struct printf_spec { - u16 type; - s16 field_width; /* width of output field */ + u8 type; /* format_type enum */ u8 flags; /* flags to number() */ - u8 base; - s8 precision; /* # of digits/chars */ - u8 qualifier; + u8 base; /* number base, 8, 10 or 16 only */ + u8 qualifier; /* number qualifier, one of 'hHlLtzZ' */ + s16 field_width; /* width of output field */ + s16 precision; /* # of digits/chars */ }; static char *number(char *buf, char *end, unsigned long long num, diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 6980625537ca..f29ada827a6a 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -723,7 +723,7 @@ static int br_multicast_igmp3_report(struct net_bridge *br, if (!pskb_may_pull(skb, len)) return -EINVAL; - grec = (void *)(skb->data + len); + grec = (void *)(skb->data + len - sizeof(*grec)); group = grec->grec_mca; type = grec->grec_type; diff --git a/net/can/raw.c b/net/can/raw.c index 3a7dffb6519c..da99cf153b33 100644 --- a/net/can/raw.c +++ b/net/can/raw.c @@ -445,7 +445,7 @@ static int raw_setsockopt(struct socket *sock, int level, int optname, return -EFAULT; } } else if (count == 1) { - if (copy_from_user(&sfilter, optval, optlen)) + if (copy_from_user(&sfilter, optval, sizeof(sfilter))) return -EFAULT; } diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 954bbfb39dff..8fef859db35d 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -472,8 +472,8 @@ static struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr, if (hslot->count < hslot2->count) goto begin; - result = udp4_lib_lookup2(net, INADDR_ANY, sport, - daddr, hnum, dif, + result = udp4_lib_lookup2(net, saddr, sport, + INADDR_ANY, hnum, dif, hslot2, slot2); } rcu_read_unlock(); diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index c177aea88c0b..90824852f598 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -259,8 +259,8 @@ static struct sock *__udp6_lib_lookup(struct net *net, if (hslot->count < hslot2->count) goto begin; - result = udp6_lib_lookup2(net, &in6addr_any, sport, - daddr, hnum, dif, + result = udp6_lib_lookup2(net, saddr, sport, + &in6addr_any, hnum, dif, hslot2, slot2); } rcu_read_unlock(); diff --git a/net/mac80211/main.c b/net/mac80211/main.c index 06c33b68d8e5..b887e484ae04 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -225,11 +225,11 @@ void ieee80211_bss_info_change_notify(struct ieee80211_sub_if_data *sdata, switch (sdata->vif.type) { case NL80211_IFTYPE_AP: sdata->vif.bss_conf.enable_beacon = - !!rcu_dereference(sdata->u.ap.beacon); + !!sdata->u.ap.beacon; break; case NL80211_IFTYPE_ADHOC: sdata->vif.bss_conf.enable_beacon = - !!rcu_dereference(sdata->u.ibss.presp); + !!sdata->u.ibss.presp; break; case NL80211_IFTYPE_MESH_POINT: sdata->vif.bss_conf.enable_beacon = true; diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c index 58e3e3a61d99..859ee5f3d941 100644 --- a/net/mac80211/mesh.c +++ b/net/mac80211/mesh.c @@ -750,9 +750,6 @@ ieee80211_mesh_rx_mgmt(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb) switch (fc & IEEE80211_FCTL_STYPE) { case IEEE80211_STYPE_ACTION: - if (skb->len < IEEE80211_MIN_ACTION_SIZE) - return RX_DROP_MONITOR; - /* fall through */ case IEEE80211_STYPE_PROBE_RESP: case IEEE80211_STYPE_BEACON: skb_queue_tail(&ifmsh->skb_queue, skb); diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index f0accf622cd7..04ea07f0e78a 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -1974,6 +1974,11 @@ ieee80211_rx_h_action(struct ieee80211_rx_data *rx) goto handled; } break; + case MESH_PLINK_CATEGORY: + case MESH_PATH_SEL_CATEGORY: + if (ieee80211_vif_is_mesh(&sdata->vif)) + return ieee80211_mesh_rx_mgmt(sdata, rx->skb); + break; } /* diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index 56422d894351..fb12cec4d333 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -93,12 +93,18 @@ struct sta_info *sta_info_get(struct ieee80211_sub_if_data *sdata, struct ieee80211_local *local = sdata->local; struct sta_info *sta; - sta = rcu_dereference(local->sta_hash[STA_HASH(addr)]); + sta = rcu_dereference_check(local->sta_hash[STA_HASH(addr)], + rcu_read_lock_held() || + lockdep_is_held(&local->sta_lock) || + lockdep_is_held(&local->sta_mtx)); while (sta) { if (sta->sdata == sdata && memcmp(sta->sta.addr, addr, ETH_ALEN) == 0) break; - sta = rcu_dereference(sta->hnext); + sta = rcu_dereference_check(sta->hnext, + rcu_read_lock_held() || + lockdep_is_held(&local->sta_lock) || + lockdep_is_held(&local->sta_mtx)); } return sta; } @@ -113,13 +119,19 @@ struct sta_info *sta_info_get_bss(struct ieee80211_sub_if_data *sdata, struct ieee80211_local *local = sdata->local; struct sta_info *sta; - sta = rcu_dereference(local->sta_hash[STA_HASH(addr)]); + sta = rcu_dereference_check(local->sta_hash[STA_HASH(addr)], + rcu_read_lock_held() || + lockdep_is_held(&local->sta_lock) || + lockdep_is_held(&local->sta_mtx)); while (sta) { if ((sta->sdata == sdata || sta->sdata->bss == sdata->bss) && memcmp(sta->sta.addr, addr, ETH_ALEN) == 0) break; - sta = rcu_dereference(sta->hnext); + sta = rcu_dereference_check(sta->hnext, + rcu_read_lock_held() || + lockdep_is_held(&local->sta_lock) || + lockdep_is_held(&local->sta_mtx)); } return sta; } diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c index e56f711baccc..cbddd0cb83f1 100644 --- a/net/x25/af_x25.c +++ b/net/x25/af_x25.c @@ -83,6 +83,41 @@ struct compat_x25_subscrip_struct { }; #endif + +int x25_parse_address_block(struct sk_buff *skb, + struct x25_address *called_addr, + struct x25_address *calling_addr) +{ + unsigned char len; + int needed; + int rc; + + if (skb->len < 1) { + /* packet has no address block */ + rc = 0; + goto empty; + } + + len = *skb->data; + needed = 1 + (len >> 4) + (len & 0x0f); + + if (skb->len < needed) { + /* packet is too short to hold the addresses it claims + to hold */ + rc = -1; + goto empty; + } + + return x25_addr_ntoa(skb->data, called_addr, calling_addr); + +empty: + *called_addr->x25_addr = 0; + *calling_addr->x25_addr = 0; + + return rc; +} + + int x25_addr_ntoa(unsigned char *p, struct x25_address *called_addr, struct x25_address *calling_addr) { @@ -554,7 +589,8 @@ static int x25_create(struct net *net, struct socket *sock, int protocol, x25->facilities.winsize_out = X25_DEFAULT_WINDOW_SIZE; x25->facilities.pacsize_in = X25_DEFAULT_PACKET_SIZE; x25->facilities.pacsize_out = X25_DEFAULT_PACKET_SIZE; - x25->facilities.throughput = X25_DEFAULT_THROUGHPUT; + x25->facilities.throughput = 0; /* by default don't negotiate + throughput */ x25->facilities.reverse = X25_DEFAULT_REVERSE; x25->dte_facilities.calling_len = 0; x25->dte_facilities.called_len = 0; @@ -922,16 +958,26 @@ int x25_rx_call_request(struct sk_buff *skb, struct x25_neigh *nb, /* * Extract the X.25 addresses and convert them to ASCII strings, * and remove them. + * + * Address block is mandatory in call request packets */ - addr_len = x25_addr_ntoa(skb->data, &source_addr, &dest_addr); + addr_len = x25_parse_address_block(skb, &source_addr, &dest_addr); + if (addr_len <= 0) + goto out_clear_request; skb_pull(skb, addr_len); /* * Get the length of the facilities, skip past them for the moment * get the call user data because this is needed to determine * the correct listener + * + * Facilities length is mandatory in call request packets */ + if (skb->len < 1) + goto out_clear_request; len = skb->data[0] + 1; + if (skb->len < len) + goto out_clear_request; skb_pull(skb,len); /* @@ -1415,9 +1461,20 @@ static int x25_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) if (facilities.winsize_in < 1 || facilities.winsize_in > 127) break; - if (facilities.throughput < 0x03 || - facilities.throughput > 0xDD) - break; + if (facilities.throughput) { + int out = facilities.throughput & 0xf0; + int in = facilities.throughput & 0x0f; + if (!out) + facilities.throughput |= + X25_DEFAULT_THROUGHPUT << 4; + else if (out < 0x30 || out > 0xD0) + break; + if (!in) + facilities.throughput |= + X25_DEFAULT_THROUGHPUT; + else if (in < 0x03 || in > 0x0D) + break; + } if (facilities.reverse && (facilities.reverse & 0x81) != 0x81) break; diff --git a/net/x25/x25_facilities.c b/net/x25/x25_facilities.c index a21f6646eb3a..771bab00754b 100644 --- a/net/x25/x25_facilities.c +++ b/net/x25/x25_facilities.c @@ -35,7 +35,7 @@ int x25_parse_facilities(struct sk_buff *skb, struct x25_facilities *facilities, struct x25_dte_facilities *dte_facs, unsigned long *vc_fac_mask) { unsigned char *p = skb->data; - unsigned int len = *p++; + unsigned int len; *vc_fac_mask = 0; @@ -50,6 +50,14 @@ int x25_parse_facilities(struct sk_buff *skb, struct x25_facilities *facilities, memset(dte_facs->called_ae, '\0', sizeof(dte_facs->called_ae)); memset(dte_facs->calling_ae, '\0', sizeof(dte_facs->calling_ae)); + if (skb->len < 1) + return 0; + + len = *p++; + + if (len >= skb->len) + return -1; + while (len > 0) { switch (*p & X25_FAC_CLASS_MASK) { case X25_FAC_CLASS_A: @@ -247,6 +255,8 @@ int x25_negotiate_facilities(struct sk_buff *skb, struct sock *sk, memcpy(new, ours, sizeof(*new)); len = x25_parse_facilities(skb, &theirs, dte, &x25->vc_facil_mask); + if (len < 0) + return len; /* * They want reverse charging, we won't accept it. @@ -259,9 +269,18 @@ int x25_negotiate_facilities(struct sk_buff *skb, struct sock *sk, new->reverse = theirs.reverse; if (theirs.throughput) { - if (theirs.throughput < ours->throughput) { - SOCK_DEBUG(sk, "X.25: throughput negotiated down\n"); - new->throughput = theirs.throughput; + int theirs_in = theirs.throughput & 0x0f; + int theirs_out = theirs.throughput & 0xf0; + int ours_in = ours->throughput & 0x0f; + int ours_out = ours->throughput & 0xf0; + if (!ours_in || theirs_in < ours_in) { + SOCK_DEBUG(sk, "X.25: inbound throughput negotiated\n"); + new->throughput = (new->throughput & 0xf0) | theirs_in; + } + if (!ours_out || theirs_out < ours_out) { + SOCK_DEBUG(sk, + "X.25: outbound throughput negotiated\n"); + new->throughput = (new->throughput & 0x0f) | theirs_out; } } diff --git a/net/x25/x25_in.c b/net/x25/x25_in.c index a31b3b9e5966..372ac226e648 100644 --- a/net/x25/x25_in.c +++ b/net/x25/x25_in.c @@ -90,6 +90,7 @@ static int x25_queue_rx_frame(struct sock *sk, struct sk_buff *skb, int more) static int x25_state1_machine(struct sock *sk, struct sk_buff *skb, int frametype) { struct x25_address source_addr, dest_addr; + int len; switch (frametype) { case X25_CALL_ACCEPTED: { @@ -107,11 +108,17 @@ static int x25_state1_machine(struct sock *sk, struct sk_buff *skb, int frametyp * Parse the data in the frame. */ skb_pull(skb, X25_STD_MIN_LEN); - skb_pull(skb, x25_addr_ntoa(skb->data, &source_addr, &dest_addr)); - skb_pull(skb, - x25_parse_facilities(skb, &x25->facilities, + + len = x25_parse_address_block(skb, &source_addr, + &dest_addr); + if (len > 0) + skb_pull(skb, len); + + len = x25_parse_facilities(skb, &x25->facilities, &x25->dte_facilities, - &x25->vc_facil_mask)); + &x25->vc_facil_mask); + if (len > 0) + skb_pull(skb, len); /* * Copy any Call User Data. */ diff --git a/security/selinux/ss/avtab.h b/security/selinux/ss/avtab.h index 8da6a8428086..cd4f734e2749 100644 --- a/security/selinux/ss/avtab.h +++ b/security/selinux/ss/avtab.h @@ -82,7 +82,7 @@ struct avtab_node *avtab_search_node_next(struct avtab_node *node, int specified void avtab_cache_init(void); void avtab_cache_destroy(void); -#define MAX_AVTAB_HASH_BITS 13 +#define MAX_AVTAB_HASH_BITS 11 #define MAX_AVTAB_HASH_BUCKETS (1 << MAX_AVTAB_HASH_BITS) #define MAX_AVTAB_HASH_MASK (MAX_AVTAB_HASH_BUCKETS-1) #define MAX_AVTAB_SIZE MAX_AVTAB_HASH_BUCKETS |