From 77f317aceb488eb2ddffbe418e480f6678becc70 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Fri, 5 Aug 2005 07:42:20 -0700 Subject: [PATCH] --- yaml --- r: 5667 b: refs/heads/master c: 107207aa8576963861e9f0c66b439d233f02a97d h: refs/heads/master i: 5665: f13fa025c6a2d28d46d69d2544d0ba3bd8d73b4d 5663: 73bc119881382b0340b5f419fe473b7fde9b1ecd v: v3 --- [refs] | 2 +- trunk/Documentation/kprobes.txt | 588 ++++++++++++++++++ trunk/Documentation/usb/usbmon.txt | 2 +- .../video4linux/bttv/Insmod-options | 3 + trunk/arch/alpha/kernel/pci.c | 16 + trunk/arch/arm/kernel/bios32.c | 17 + trunk/arch/arm/mach-sa1100/jornada720.c | 1 + trunk/arch/arm/mm/fault.c | 6 +- trunk/arch/arm/oprofile/backtrace.c | 2 +- trunk/arch/arm26/mm/fault.c | 17 +- trunk/arch/cris/mm/fault.c | 6 +- trunk/arch/frv/mm/fault.c | 6 +- trunk/arch/i386/Kconfig | 3 +- trunk/arch/m68k/mm/fault.c | 6 +- trunk/arch/parisc/mm/fault.c | 12 +- trunk/arch/ppc/kernel/pci.c | 15 + trunk/arch/ppc64/kernel/head.S | 2 +- trunk/arch/ppc64/kernel/machine_kexec.c | 12 +- trunk/arch/ppc64/kernel/mpic.c | 4 +- trunk/arch/ppc64/kernel/mpic.h | 2 +- trunk/arch/ppc64/kernel/pci.c | 20 + trunk/arch/ppc64/kernel/xics.c | 31 +- trunk/arch/sh64/mm/fault.c | 6 +- trunk/arch/sparc64/kernel/pci.c | 6 + trunk/arch/x86_64/ia32/ptrace32.c | 8 +- trunk/arch/x86_64/mm/fault.c | 6 +- trunk/drivers/acpi/dispatcher/dswload.c | 6 - trunk/drivers/acpi/osl.c | 6 +- trunk/drivers/acpi/pci_link.c | 7 + trunk/drivers/char/rtc.c | 7 +- trunk/drivers/fc4/fc.c | 2 +- trunk/drivers/ide/ide-probe.c | 16 +- trunk/drivers/infiniband/include/ib_cm.h | 3 +- .../drivers/infiniband/ulp/ipoib/ipoib_main.c | 5 +- trunk/drivers/md/bitmap.c | 75 ++- trunk/drivers/md/dm-raid1.c | 2 +- trunk/drivers/md/md.c | 4 +- trunk/drivers/md/raid1.c | 29 +- trunk/drivers/media/video/bttv-cards.c | 8 +- trunk/drivers/media/video/bttv-driver.c | 28 +- trunk/drivers/pci/pci.c | 59 +- trunk/drivers/pci/setup-res.c | 2 +- trunk/drivers/pcmcia/yenta_socket.c | 15 +- trunk/drivers/scsi/aic7xxx/aic7xxx_osm.c | 24 +- trunk/drivers/scsi/ibmvscsi/srp.h | 2 +- trunk/drivers/scsi/ips.c | 8 +- trunk/drivers/scsi/ips.h | 39 +- trunk/drivers/scsi/st.c | 8 +- trunk/drivers/usb/host/ehci-dbg.c | 2 +- trunk/drivers/usb/host/ehci-q.c | 5 +- trunk/drivers/usb/host/ehci-sched.c | 13 +- trunk/drivers/usb/host/ehci.h | 5 + trunk/drivers/usb/host/isp116x-hcd.c | 4 +- trunk/drivers/usb/mon/Kconfig | 9 +- trunk/drivers/usb/mon/Makefile | 1 + trunk/fs/Kconfig | 11 +- trunk/fs/namei.c | 5 +- trunk/include/asm-alpha/pci.h | 3 + trunk/include/asm-arm/pci.h | 4 + trunk/include/asm-generic/pci.h | 8 + trunk/include/asm-parisc/pci.h | 4 + trunk/include/asm-ppc/pci.h | 4 + trunk/include/asm-ppc64/machdep.h | 2 +- trunk/include/asm-ppc64/pci.h | 4 + trunk/include/asm-ppc64/xics.h | 2 +- trunk/include/linux/fsnotify.h | 4 +- trunk/include/linux/pci.h | 3 + trunk/include/linux/raid/bitmap.h | 1 + trunk/kernel/exit.c | 4 +- trunk/kernel/posix-timers.c | 1 - trunk/kernel/sys.c | 2 - trunk/mm/mmap.c | 6 +- trunk/mm/mremap.c | 2 +- trunk/mm/nommu.c | 6 +- trunk/net/ipv4/tcp_output.c | 86 ++- trunk/security/keys/keyctl.c | 11 +- trunk/security/keys/keyring.c | 6 +- trunk/security/keys/process_keys.c | 2 +- trunk/security/keys/request_key.c | 2 +- 79 files changed, 1097 insertions(+), 279 deletions(-) create mode 100644 trunk/Documentation/kprobes.txt diff --git a/[refs] b/[refs] index 8de80bca7bbd..d9dfaf5e713c 100644 --- a/[refs] +++ b/[refs] @@ -1,2 +1,2 @@ --- -refs/heads/master: 3873658be7b3896e88648664e480a44d12083ad8 +refs/heads/master: 107207aa8576963861e9f0c66b439d233f02a97d diff --git a/trunk/Documentation/kprobes.txt b/trunk/Documentation/kprobes.txt new file mode 100644 index 000000000000..0541fe1de704 --- /dev/null +++ b/trunk/Documentation/kprobes.txt @@ -0,0 +1,588 @@ +Title : Kernel Probes (Kprobes) +Authors : Jim Keniston + : Prasanna S Panchamukhi + +CONTENTS + +1. Concepts: Kprobes, Jprobes, Return Probes +2. Architectures Supported +3. Configuring Kprobes +4. API Reference +5. Kprobes Features and Limitations +6. Probe Overhead +7. TODO +8. Kprobes Example +9. Jprobes Example +10. Kretprobes Example + +1. Concepts: Kprobes, Jprobes, Return Probes + +Kprobes enables you to dynamically break into any kernel routine and +collect debugging and performance information non-disruptively. You +can trap at almost any kernel code address, specifying a handler +routine to be invoked when the breakpoint is hit. + +There are currently three types of probes: kprobes, jprobes, and +kretprobes (also called return probes). A kprobe can be inserted +on virtually any instruction in the kernel. A jprobe is inserted at +the entry to a kernel function, and provides convenient access to the +function's arguments. A return probe fires when a specified function +returns. + +In the typical case, Kprobes-based instrumentation is packaged as +a kernel module. The module's init function installs ("registers") +one or more probes, and the exit function unregisters them. A +registration function such as register_kprobe() specifies where +the probe is to be inserted and what handler is to be called when +the probe is hit. + +The next three subsections explain how the different types of +probes work. They explain certain things that you'll need to +know in order to make the best use of Kprobes -- e.g., the +difference between a pre_handler and a post_handler, and how +to use the maxactive and nmissed fields of a kretprobe. But +if you're in a hurry to start using Kprobes, you can skip ahead +to section 2. + +1.1 How Does a Kprobe Work? + +When a kprobe is registered, Kprobes makes a copy of the probed +instruction and replaces the first byte(s) of the probed instruction +with a breakpoint instruction (e.g., int3 on i386 and x86_64). + +When a CPU hits the breakpoint instruction, a trap occurs, the CPU's +registers are saved, and control passes to Kprobes via the +notifier_call_chain mechanism. Kprobes executes the "pre_handler" +associated with the kprobe, passing the handler the addresses of the +kprobe struct and the saved registers. + +Next, Kprobes single-steps its copy of the probed instruction. +(It would be simpler to single-step the actual instruction in place, +but then Kprobes would have to temporarily remove the breakpoint +instruction. This would open a small time window when another CPU +could sail right past the probepoint.) + +After the instruction is single-stepped, Kprobes executes the +"post_handler," if any, that is associated with the kprobe. +Execution then continues with the instruction following the probepoint. + +1.2 How Does a Jprobe Work? + +A jprobe is implemented using a kprobe that is placed on a function's +entry point. It employs a simple mirroring principle to allow +seamless access to the probed function's arguments. The jprobe +handler routine should have the same signature (arg list and return +type) as the function being probed, and must always end by calling +the Kprobes function jprobe_return(). + +Here's how it works. When the probe is hit, Kprobes makes a copy of +the saved registers and a generous portion of the stack (see below). +Kprobes then points the saved instruction pointer at the jprobe's +handler routine, and returns from the trap. As a result, control +passes to the handler, which is presented with the same register and +stack contents as the probed function. When it is done, the handler +calls jprobe_return(), which traps again to restore the original stack +contents and processor state and switch to the probed function. + +By convention, the callee owns its arguments, so gcc may produce code +that unexpectedly modifies that portion of the stack. This is why +Kprobes saves a copy of the stack and restores it after the jprobe +handler has run. Up to MAX_STACK_SIZE bytes are copied -- e.g., +64 bytes on i386. + +Note that the probed function's args may be passed on the stack +or in registers (e.g., for x86_64 or for an i386 fastcall function). +The jprobe will work in either case, so long as the handler's +prototype matches that of the probed function. + +1.3 How Does a Return Probe Work? + +When you call register_kretprobe(), Kprobes establishes a kprobe at +the entry to the function. When the probed function is called and this +probe is hit, Kprobes saves a copy of the return address, and replaces +the return address with the address of a "trampoline." The trampoline +is an arbitrary piece of code -- typically just a nop instruction. +At boot time, Kprobes registers a kprobe at the trampoline. + +When the probed function executes its return instruction, control +passes to the trampoline and that probe is hit. Kprobes' trampoline +handler calls the user-specified handler associated with the kretprobe, +then sets the saved instruction pointer to the saved return address, +and that's where execution resumes upon return from the trap. + +While the probed function is executing, its return address is +stored in an object of type kretprobe_instance. Before calling +register_kretprobe(), the user sets the maxactive field of the +kretprobe struct to specify how many instances of the specified +function can be probed simultaneously. register_kretprobe() +pre-allocates the indicated number of kretprobe_instance objects. + +For example, if the function is non-recursive and is called with a +spinlock held, maxactive = 1 should be enough. If the function is +non-recursive and can never relinquish the CPU (e.g., via a semaphore +or preemption), NR_CPUS should be enough. If maxactive <= 0, it is +set to a default value. If CONFIG_PREEMPT is enabled, the default +is max(10, 2*NR_CPUS). Otherwise, the default is NR_CPUS. + +It's not a disaster if you set maxactive too low; you'll just miss +some probes. In the kretprobe struct, the nmissed field is set to +zero when the return probe is registered, and is incremented every +time the probed function is entered but there is no kretprobe_instance +object available for establishing the return probe. + +2. Architectures Supported + +Kprobes, jprobes, and return probes are implemented on the following +architectures: + +- i386 +- x86_64 (AMD-64, E64MT) +- ppc64 +- ia64 (Support for probes on certain instruction types is still in progress.) +- sparc64 (Return probes not yet implemented.) + +3. Configuring Kprobes + +When configuring the kernel using make menuconfig/xconfig/oldconfig, +ensure that CONFIG_KPROBES is set to "y". Under "Kernel hacking", +look for "Kprobes". You may have to enable "Kernel debugging" +(CONFIG_DEBUG_KERNEL) before you can enable Kprobes. + +You may also want to ensure that CONFIG_KALLSYMS and perhaps even +CONFIG_KALLSYMS_ALL are set to "y", since kallsyms_lookup_name() +is a handy, version-independent way to find a function's address. + +If you need to insert a probe in the middle of a function, you may find +it useful to "Compile the kernel with debug info" (CONFIG_DEBUG_INFO), +so you can use "objdump -d -l vmlinux" to see the source-to-object +code mapping. + +4. API Reference + +The Kprobes API includes a "register" function and an "unregister" +function for each type of probe. Here are terse, mini-man-page +specifications for these functions and the associated probe handlers +that you'll write. See the latter half of this document for examples. + +4.1 register_kprobe + +#include +int register_kprobe(struct kprobe *kp); + +Sets a breakpoint at the address kp->addr. When the breakpoint is +hit, Kprobes calls kp->pre_handler. After the probed instruction +is single-stepped, Kprobe calls kp->post_handler. If a fault +occurs during execution of kp->pre_handler or kp->post_handler, +or during single-stepping of the probed instruction, Kprobes calls +kp->fault_handler. Any or all handlers can be NULL. + +register_kprobe() returns 0 on success, or a negative errno otherwise. + +User's pre-handler (kp->pre_handler): +#include +#include +int pre_handler(struct kprobe *p, struct pt_regs *regs); + +Called with p pointing to the kprobe associated with the breakpoint, +and regs pointing to the struct containing the registers saved when +the breakpoint was hit. Return 0 here unless you're a Kprobes geek. + +User's post-handler (kp->post_handler): +#include +#include +void post_handler(struct kprobe *p, struct pt_regs *regs, + unsigned long flags); + +p and regs are as described for the pre_handler. flags always seems +to be zero. + +User's fault-handler (kp->fault_handler): +#include +#include +int fault_handler(struct kprobe *p, struct pt_regs *regs, int trapnr); + +p and regs are as described for the pre_handler. trapnr is the +architecture-specific trap number associated with the fault (e.g., +on i386, 13 for a general protection fault or 14 for a page fault). +Returns 1 if it successfully handled the exception. + +4.2 register_jprobe + +#include +int register_jprobe(struct jprobe *jp) + +Sets a breakpoint at the address jp->kp.addr, which must be the address +of the first instruction of a function. When the breakpoint is hit, +Kprobes runs the handler whose address is jp->entry. + +The handler should have the same arg list and return type as the probed +function; and just before it returns, it must call jprobe_return(). +(The handler never actually returns, since jprobe_return() returns +control to Kprobes.) If the probed function is declared asmlinkage, +fastcall, or anything else that affects how args are passed, the +handler's declaration must match. + +register_jprobe() returns 0 on success, or a negative errno otherwise. + +4.3 register_kretprobe + +#include +int register_kretprobe(struct kretprobe *rp); + +Establishes a return probe for the function whose address is +rp->kp.addr. When that function returns, Kprobes calls rp->handler. +You must set rp->maxactive appropriately before you call +register_kretprobe(); see "How Does a Return Probe Work?" for details. + +register_kretprobe() returns 0 on success, or a negative errno +otherwise. + +User's return-probe handler (rp->handler): +#include +#include +int kretprobe_handler(struct kretprobe_instance *ri, struct pt_regs *regs); + +regs is as described for kprobe.pre_handler. ri points to the +kretprobe_instance object, of which the following fields may be +of interest: +- ret_addr: the return address +- rp: points to the corresponding kretprobe object +- task: points to the corresponding task struct +The handler's return value is currently ignored. + +4.4 unregister_*probe + +#include +void unregister_kprobe(struct kprobe *kp); +void unregister_jprobe(struct jprobe *jp); +void unregister_kretprobe(struct kretprobe *rp); + +Removes the specified probe. The unregister function can be called +at any time after the probe has been registered. + +5. Kprobes Features and Limitations + +As of Linux v2.6.12, Kprobes allows multiple probes at the same +address. Currently, however, there cannot be multiple jprobes on +the same function at the same time. + +In general, you can install a probe anywhere in the kernel. +In particular, you can probe interrupt handlers. Known exceptions +are discussed in this section. + +For obvious reasons, it's a bad idea to install a probe in +the code that implements Kprobes (mostly kernel/kprobes.c and +arch/*/kernel/kprobes.c). A patch in the v2.6.13 timeframe instructs +Kprobes to reject such requests. + +If you install a probe in an inline-able function, Kprobes makes +no attempt to chase down all inline instances of the function and +install probes there. gcc may inline a function without being asked, +so keep this in mind if you're not seeing the probe hits you expect. + +A probe handler can modify the environment of the probed function +-- e.g., by modifying kernel data structures, or by modifying the +contents of the pt_regs struct (which are restored to the registers +upon return from the breakpoint). So Kprobes can be used, for example, +to install a bug fix or to inject faults for testing. Kprobes, of +course, has no way to distinguish the deliberately injected faults +from the accidental ones. Don't drink and probe. + +Kprobes makes no attempt to prevent probe handlers from stepping on +each other -- e.g., probing printk() and then calling printk() from a +probe handler. As of Linux v2.6.12, if a probe handler hits a probe, +that second probe's handlers won't be run in that instance. + +In Linux v2.6.12 and previous versions, Kprobes' data structures are +protected by a single lock that is held during probe registration and +unregistration and while handlers are run. Thus, no two handlers +can run simultaneously. To improve scalability on SMP systems, +this restriction will probably be removed soon, in which case +multiple handlers (or multiple instances of the same handler) may +run concurrently on different CPUs. Code your handlers accordingly. + +Kprobes does not use semaphores or allocate memory except during +registration and unregistration. + +Probe handlers are run with preemption disabled. Depending on the +architecture, handlers may also run with interrupts disabled. In any +case, your handler should not yield the CPU (e.g., by attempting to +acquire a semaphore). + +Since a return probe is implemented by replacing the return +address with the trampoline's address, stack backtraces and calls +to __builtin_return_address() will typically yield the trampoline's +address instead of the real return address for kretprobed functions. +(As far as we can tell, __builtin_return_address() is used only +for instrumentation and error reporting.) + +If the number of times a function is called does not match the +number of times it returns, registering a return probe on that +function may produce undesirable results. We have the do_exit() +and do_execve() cases covered. do_fork() is not an issue. We're +unaware of other specific cases where this could be a problem. + +6. Probe Overhead + +On a typical CPU in use in 2005, a kprobe hit takes 0.5 to 1.0 +microseconds to process. Specifically, a benchmark that hits the same +probepoint repeatedly, firing a simple handler each time, reports 1-2 +million hits per second, depending on the architecture. A jprobe or +return-probe hit typically takes 50-75% longer than a kprobe hit. +When you have a return probe set on a function, adding a kprobe at +the entry to that function adds essentially no overhead. + +Here are sample overhead figures (in usec) for different architectures. +k = kprobe; j = jprobe; r = return probe; kr = kprobe + return probe +on same function; jr = jprobe + return probe on same function + +i386: Intel Pentium M, 1495 MHz, 2957.31 bogomips +k = 0.57 usec; j = 1.00; r = 0.92; kr = 0.99; jr = 1.40 + +x86_64: AMD Opteron 246, 1994 MHz, 3971.48 bogomips +k = 0.49 usec; j = 0.76; r = 0.80; kr = 0.82; jr = 1.07 + +ppc64: POWER5 (gr), 1656 MHz (SMT disabled, 1 virtual CPU per physical CPU) +k = 0.77 usec; j = 1.31; r = 1.26; kr = 1.45; jr = 1.99 + +7. TODO + +a. SystemTap (http://sourceware.org/systemtap): Work in progress +to provide a simplified programming interface for probe-based +instrumentation. +b. Improved SMP scalability: Currently, work is in progress to handle +multiple kprobes in parallel. +c. Kernel return probes for sparc64. +d. Support for other architectures. +e. User-space probes. + +8. Kprobes Example + +Here's a sample kernel module showing the use of kprobes to dump a +stack trace and selected i386 registers when do_fork() is called. +----- cut here ----- +/*kprobe_example.c*/ +#include +#include +#include +#include +#include + +/*For each probe you need to allocate a kprobe structure*/ +static struct kprobe kp; + +/*kprobe pre_handler: called just before the probed instruction is executed*/ +int handler_pre(struct kprobe *p, struct pt_regs *regs) +{ + printk("pre_handler: p->addr=0x%p, eip=%lx, eflags=0x%lx\n", + p->addr, regs->eip, regs->eflags); + dump_stack(); + return 0; +} + +/*kprobe post_handler: called after the probed instruction is executed*/ +void handler_post(struct kprobe *p, struct pt_regs *regs, unsigned long flags) +{ + printk("post_handler: p->addr=0x%p, eflags=0x%lx\n", + p->addr, regs->eflags); +} + +/* fault_handler: this is called if an exception is generated for any + * instruction within the pre- or post-handler, or when Kprobes + * single-steps the probed instruction. + */ +int handler_fault(struct kprobe *p, struct pt_regs *regs, int trapnr) +{ + printk("fault_handler: p->addr=0x%p, trap #%dn", + p->addr, trapnr); + /* Return 0 because we don't handle the fault. */ + return 0; +} + +int init_module(void) +{ + int ret; + kp.pre_handler = handler_pre; + kp.post_handler = handler_post; + kp.fault_handler = handler_fault; + kp.addr = (kprobe_opcode_t*) kallsyms_lookup_name("do_fork"); + /* register the kprobe now */ + if (!kp.addr) { + printk("Couldn't find %s to plant kprobe\n", "do_fork"); + return -1; + } + if ((ret = register_kprobe(&kp) < 0)) { + printk("register_kprobe failed, returned %d\n", ret); + return -1; + } + printk("kprobe registered\n"); + return 0; +} + +void cleanup_module(void) +{ + unregister_kprobe(&kp); + printk("kprobe unregistered\n"); +} + +MODULE_LICENSE("GPL"); +----- cut here ----- + +You can build the kernel module, kprobe-example.ko, using the following +Makefile: +----- cut here ----- +obj-m := kprobe-example.o +KDIR := /lib/modules/$(shell uname -r)/build +PWD := $(shell pwd) +default: + $(MAKE) -C $(KDIR) SUBDIRS=$(PWD) modules +clean: + rm -f *.mod.c *.ko *.o +----- cut here ----- + +$ make +$ su - +... +# insmod kprobe-example.ko + +You will see the trace data in /var/log/messages and on the console +whenever do_fork() is invoked to create a new process. + +9. Jprobes Example + +Here's a sample kernel module showing the use of jprobes to dump +the arguments of do_fork(). +----- cut here ----- +/*jprobe-example.c */ +#include +#include +#include +#include +#include +#include + +/* + * Jumper probe for do_fork. + * Mirror principle enables access to arguments of the probed routine + * from the probe handler. + */ + +/* Proxy routine having the same arguments as actual do_fork() routine */ +long jdo_fork(unsigned long clone_flags, unsigned long stack_start, + struct pt_regs *regs, unsigned long stack_size, + int __user * parent_tidptr, int __user * child_tidptr) +{ + printk("jprobe: clone_flags=0x%lx, stack_size=0x%lx, regs=0x%p\n", + clone_flags, stack_size, regs); + /* Always end with a call to jprobe_return(). */ + jprobe_return(); + /*NOTREACHED*/ + return 0; +} + +static struct jprobe my_jprobe = { + .entry = (kprobe_opcode_t *) jdo_fork +}; + +int init_module(void) +{ + int ret; + my_jprobe.kp.addr = (kprobe_opcode_t *) kallsyms_lookup_name("do_fork"); + if (!my_jprobe.kp.addr) { + printk("Couldn't find %s to plant jprobe\n", "do_fork"); + return -1; + } + + if ((ret = register_jprobe(&my_jprobe)) <0) { + printk("register_jprobe failed, returned %d\n", ret); + return -1; + } + printk("Planted jprobe at %p, handler addr %p\n", + my_jprobe.kp.addr, my_jprobe.entry); + return 0; +} + +void cleanup_module(void) +{ + unregister_jprobe(&my_jprobe); + printk("jprobe unregistered\n"); +} + +MODULE_LICENSE("GPL"); +----- cut here ----- + +Build and insert the kernel module as shown in the above kprobe +example. You will see the trace data in /var/log/messages and on +the console whenever do_fork() is invoked to create a new process. +(Some messages may be suppressed if syslogd is configured to +eliminate duplicate messages.) + +10. Kretprobes Example + +Here's a sample kernel module showing the use of return probes to +report failed calls to sys_open(). +----- cut here ----- +/*kretprobe-example.c*/ +#include +#include +#include +#include + +static const char *probed_func = "sys_open"; + +/* Return-probe handler: If the probed function fails, log the return value. */ +static int ret_handler(struct kretprobe_instance *ri, struct pt_regs *regs) +{ + // Substitute the appropriate register name for your architecture -- + // e.g., regs->rax for x86_64, regs->gpr[3] for ppc64. + int retval = (int) regs->eax; + if (retval < 0) { + printk("%s returns %d\n", probed_func, retval); + } + return 0; +} + +static struct kretprobe my_kretprobe = { + .handler = ret_handler, + /* Probe up to 20 instances concurrently. */ + .maxactive = 20 +}; + +int init_module(void) +{ + int ret; + my_kretprobe.kp.addr = + (kprobe_opcode_t *) kallsyms_lookup_name(probed_func); + if (!my_kretprobe.kp.addr) { + printk("Couldn't find %s to plant return probe\n", probed_func); + return -1; + } + if ((ret = register_kretprobe(&my_kretprobe)) < 0) { + printk("register_kretprobe failed, returned %d\n", ret); + return -1; + } + printk("Planted return probe at %p\n", my_kretprobe.kp.addr); + return 0; +} + +void cleanup_module(void) +{ + unregister_kretprobe(&my_kretprobe); + printk("kretprobe unregistered\n"); + /* nmissed > 0 suggests that maxactive was set too low. */ + printk("Missed probing %d instances of %s\n", + my_kretprobe.nmissed, probed_func); +} + +MODULE_LICENSE("GPL"); +----- cut here ----- + +Build and insert the kernel module as shown in the above kprobe +example. You will see the trace data in /var/log/messages and on the +console whenever sys_open() returns a negative value. (Some messages +may be suppressed if syslogd is configured to eliminate duplicate +messages.) + +For additional information on Kprobes, refer to the following URLs: +http://www-106.ibm.com/developerworks/library/l-kprobes.html?ca=dgr-lnxw42Kprobe +http://www.redhat.com/magazine/005mar05/features/kprobes/ diff --git a/trunk/Documentation/usb/usbmon.txt b/trunk/Documentation/usb/usbmon.txt index f1896ee3bb2a..63cb7edd177e 100644 --- a/trunk/Documentation/usb/usbmon.txt +++ b/trunk/Documentation/usb/usbmon.txt @@ -102,7 +102,7 @@ Here is the list of words, from left to right: - URB Status. This field makes no sense for submissions, but is present to help scripts with parsing. In error case, it contains the error code. In case of a setup packet, it contains a Setup Tag. If scripts read a number - in this field, the proceed to read Data Length. Otherwise, they read + in this field, they proceed to read Data Length. Otherwise, they read the setup packet before reading the Data Length. - Setup packet, if present, consists of 5 words: one of each for bmRequestType, bRequest, wValue, wIndex, wLength, as specified by the USB Specification 2.0. diff --git a/trunk/Documentation/video4linux/bttv/Insmod-options b/trunk/Documentation/video4linux/bttv/Insmod-options index 7bb5a50b0779..fc94ff235ffa 100644 --- a/trunk/Documentation/video4linux/bttv/Insmod-options +++ b/trunk/Documentation/video4linux/bttv/Insmod-options @@ -44,6 +44,9 @@ bttv.o push used by bttv. bttv will disable overlay by default on this hardware to avoid crashes. With this insmod option you can override this. + no_overlay=1 Disable overlay. It should be used by broken + hardware that doesn't support PCI2PCI direct + transfers. automute=0/1 Automatically mutes the sound if there is no TV signal, on by default. You might try to disable this if you have bad input signal diff --git a/trunk/arch/alpha/kernel/pci.c b/trunk/arch/alpha/kernel/pci.c index 1f36bbd0ed5d..2a8b364c822e 100644 --- a/trunk/arch/alpha/kernel/pci.c +++ b/trunk/arch/alpha/kernel/pci.c @@ -350,8 +350,24 @@ pcibios_resource_to_bus(struct pci_dev *dev, struct pci_bus_region *region, region->end = res->end - offset; } +void pcibios_bus_to_resource(struct pci_dev *dev, struct resource *res, + struct pci_bus_region *region) +{ + struct pci_controller *hose = (struct pci_controller *)dev->sysdata; + unsigned long offset = 0; + + if (res->flags & IORESOURCE_IO) + offset = hose->io_space->start; + else if (res->flags & IORESOURCE_MEM) + offset = hose->mem_space->start; + + res->start = region->start + offset; + res->end = region->end + offset; +} + #ifdef CONFIG_HOTPLUG EXPORT_SYMBOL(pcibios_resource_to_bus); +EXPORT_SYMBOL(pcibios_bus_to_resource); #endif int diff --git a/trunk/arch/arm/kernel/bios32.c b/trunk/arch/arm/kernel/bios32.c index ad26e98f1e62..c4923fac8dff 100644 --- a/trunk/arch/arm/kernel/bios32.c +++ b/trunk/arch/arm/kernel/bios32.c @@ -447,9 +447,26 @@ pcibios_resource_to_bus(struct pci_dev *dev, struct pci_bus_region *region, region->end = res->end - offset; } +void __devinit +pcibios_bus_to_resource(struct pci_dev *dev, struct resource *res, + struct pci_bus_region *region) +{ + struct pci_sys_data *root = dev->sysdata; + unsigned long offset = 0; + + if (res->flags & IORESOURCE_IO) + offset = root->io_offset; + if (res->flags & IORESOURCE_MEM) + offset = root->mem_offset; + + res->start = region->start + offset; + res->end = region->end + offset; +} + #ifdef CONFIG_HOTPLUG EXPORT_SYMBOL(pcibios_fixup_bus); EXPORT_SYMBOL(pcibios_resource_to_bus); +EXPORT_SYMBOL(pcibios_bus_to_resource); #endif /* diff --git a/trunk/arch/arm/mach-sa1100/jornada720.c b/trunk/arch/arm/mach-sa1100/jornada720.c index eee3cbc5ec4f..2f497112c96a 100644 --- a/trunk/arch/arm/mach-sa1100/jornada720.c +++ b/trunk/arch/arm/mach-sa1100/jornada720.c @@ -97,6 +97,7 @@ static void __init jornada720_map_io(void) } MACHINE_START(JORNADA720, "HP Jornada 720") + /* Maintainer: Michael Gernoth */ .phys_ram = 0xc0000000, .phys_io = 0x80000000, .io_pg_offst = ((0xf8000000) >> 18) & 0xfffc, diff --git a/trunk/arch/arm/mm/fault.c b/trunk/arch/arm/mm/fault.c index 65bfe84b6d67..0b6c4db44e08 100644 --- a/trunk/arch/arm/mm/fault.c +++ b/trunk/arch/arm/mm/fault.c @@ -238,9 +238,9 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs) up_read(&mm->mmap_sem); /* - * Handle the "normal" case first + * Handle the "normal" case first - VM_FAULT_MAJOR / VM_FAULT_MINOR */ - if (fault > 0) + if (fault >= VM_FAULT_MINOR) return 0; /* @@ -261,7 +261,7 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs) do_exit(SIGKILL); return 0; - case 0: + case VM_FAULT_SIGBUS: /* * We had some memory, but were unable to * successfully fix up this page fault. diff --git a/trunk/arch/arm/oprofile/backtrace.c b/trunk/arch/arm/oprofile/backtrace.c index ec58d3e2eb8b..df35c452a8bf 100644 --- a/trunk/arch/arm/oprofile/backtrace.c +++ b/trunk/arch/arm/oprofile/backtrace.c @@ -115,7 +115,7 @@ static int valid_kernel_stack(struct frame_tail *tail, struct pt_regs *regs) return (tailaddr > stack) && (tailaddr < stack_base); } -void arm_backtrace(struct pt_regs const *regs, unsigned int depth) +void arm_backtrace(struct pt_regs * const regs, unsigned int depth) { struct frame_tail *tail; unsigned long last_address = 0; diff --git a/trunk/arch/arm26/mm/fault.c b/trunk/arch/arm26/mm/fault.c index dacca8bb7744..bd6f2db608b7 100644 --- a/trunk/arch/arm26/mm/fault.c +++ b/trunk/arch/arm26/mm/fault.c @@ -176,12 +176,12 @@ __do_page_fault(struct mm_struct *mm, unsigned long addr, unsigned int fsr, * Handle the "normal" cases first - successful and sigbus */ switch (fault) { - case 2: + case VM_FAULT_MAJOR: tsk->maj_flt++; return fault; - case 1: + case VM_FAULT_MINOR: tsk->min_flt++; - case 0: + case VM_FAULT_SIGBUS: return fault; } @@ -226,14 +226,11 @@ int do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs) /* * Handle the "normal" case first */ - if (fault > 0) + switch (fault) { + case VM_FAULT_MINOR: + case VM_FAULT_MAJOR: return 0; - - /* - * We had some memory, but were unable to - * successfully fix up this page fault. - */ - if (fault == 0){ + case VM_FAULT_SIGBUS: goto do_sigbus; } diff --git a/trunk/arch/cris/mm/fault.c b/trunk/arch/cris/mm/fault.c index fe1cc36b5aca..934c51078cce 100644 --- a/trunk/arch/cris/mm/fault.c +++ b/trunk/arch/cris/mm/fault.c @@ -284,13 +284,13 @@ do_page_fault(unsigned long address, struct pt_regs *regs, */ switch (handle_mm_fault(mm, vma, address, writeaccess & 1)) { - case 1: + case VM_FAULT_MINOR: tsk->min_flt++; break; - case 2: + case VM_FAULT_MAJOR: tsk->maj_flt++; break; - case 0: + case VM_FAULT_SIGBUS: goto do_sigbus; default: goto out_of_memory; diff --git a/trunk/arch/frv/mm/fault.c b/trunk/arch/frv/mm/fault.c index 41d02ac48233..8b3eb50c5105 100644 --- a/trunk/arch/frv/mm/fault.c +++ b/trunk/arch/frv/mm/fault.c @@ -163,13 +163,13 @@ asmlinkage void do_page_fault(int datammu, unsigned long esr0, unsigned long ear * the fault. */ switch (handle_mm_fault(mm, vma, ear0, write)) { - case 1: + case VM_FAULT_MINOR: current->min_flt++; break; - case 2: + case VM_FAULT_MAJOR: current->maj_flt++; break; - case 0: + case VM_FAULT_SIGBUS: goto do_sigbus; default: goto out_of_memory; diff --git a/trunk/arch/i386/Kconfig b/trunk/arch/i386/Kconfig index a801d9d48606..619d843ba231 100644 --- a/trunk/arch/i386/Kconfig +++ b/trunk/arch/i386/Kconfig @@ -454,8 +454,9 @@ config HPET_TIMER Choose N to continue using the legacy 8254 timer. config HPET_EMULATE_RTC - bool "Provide RTC interrupt" + bool depends on HPET_TIMER && RTC=y + default y config SMP bool "Symmetric multi-processing support" diff --git a/trunk/arch/m68k/mm/fault.c b/trunk/arch/m68k/mm/fault.c index ac48b6d2aff6..aec15270d334 100644 --- a/trunk/arch/m68k/mm/fault.c +++ b/trunk/arch/m68k/mm/fault.c @@ -160,13 +160,13 @@ int do_page_fault(struct pt_regs *regs, unsigned long address, printk("handle_mm_fault returns %d\n",fault); #endif switch (fault) { - case 1: + case VM_FAULT_MINOR: current->min_flt++; break; - case 2: + case VM_FAULT_MAJOR: current->maj_flt++; break; - case 0: + case VM_FAULT_SIGBUS: goto bus_err; default: goto out_of_memory; diff --git a/trunk/arch/parisc/mm/fault.c b/trunk/arch/parisc/mm/fault.c index eaa701479f5f..0ad945d4c0a4 100644 --- a/trunk/arch/parisc/mm/fault.c +++ b/trunk/arch/parisc/mm/fault.c @@ -178,17 +178,17 @@ void do_page_fault(struct pt_regs *regs, unsigned long code, */ switch (handle_mm_fault(mm, vma, address, (acc_type & VM_WRITE) != 0)) { - case 1: + case VM_FAULT_MINOR: ++current->min_flt; break; - case 2: + case VM_FAULT_MAJOR: ++current->maj_flt; break; - case 0: + case VM_FAULT_SIGBUS: /* - * We ran out of memory, or some other thing happened - * to us that made us unable to handle the page fault - * gracefully. + * We hit a hared mapping outside of the file, or some + * other thing happened to us that made us unable to + * handle the page fault gracefully. */ goto bad_area; default: diff --git a/trunk/arch/ppc/kernel/pci.c b/trunk/arch/ppc/kernel/pci.c index 70cfb6ffd877..7b3586a3bf30 100644 --- a/trunk/arch/ppc/kernel/pci.c +++ b/trunk/arch/ppc/kernel/pci.c @@ -160,6 +160,21 @@ void pcibios_resource_to_bus(struct pci_dev *dev, struct pci_bus_region *region, } EXPORT_SYMBOL(pcibios_resource_to_bus); +void pcibios_bus_to_resource(struct pci_dev *dev, struct resource *res, + struct pci_bus_region *region) +{ + unsigned long offset = 0; + struct pci_controller *hose = dev->sysdata; + + if (hose && res->flags & IORESOURCE_IO) + offset = (unsigned long)hose->io_base_virt - isa_io_base; + else if (hose && res->flags & IORESOURCE_MEM) + offset = hose->pci_mem_offset; + res->start = region->start + offset; + res->end = region->end + offset; +} +EXPORT_SYMBOL(pcibios_bus_to_resource); + /* * We need to avoid collisions with `mirrored' VGA ports * and other strange ISA hardware, so we always want the diff --git a/trunk/arch/ppc64/kernel/head.S b/trunk/arch/ppc64/kernel/head.S index 74fc3bc68604..784f56d4684c 100644 --- a/trunk/arch/ppc64/kernel/head.S +++ b/trunk/arch/ppc64/kernel/head.S @@ -2071,7 +2071,7 @@ _GLOBAL(hmt_start_secondary) blr #endif -#if defined(CONFIG_SMP) && !defined(CONFIG_PPC_ISERIES) +#if defined(CONFIG_KEXEC) || (defined(CONFIG_SMP) && !defined(CONFIG_PPC_ISERIES)) _GLOBAL(smp_release_cpus) /* All secondary cpus are spinning on a common * spinloop, release them all now so they can start diff --git a/trunk/arch/ppc64/kernel/machine_kexec.c b/trunk/arch/ppc64/kernel/machine_kexec.c index fdb2fc649d72..4775f12a013c 100644 --- a/trunk/arch/ppc64/kernel/machine_kexec.c +++ b/trunk/arch/ppc64/kernel/machine_kexec.c @@ -185,7 +185,7 @@ void kexec_copy_flush(struct kimage *image) void kexec_smp_down(void *arg) { if (ppc_md.cpu_irq_down) - ppc_md.cpu_irq_down(); + ppc_md.cpu_irq_down(1); local_irq_disable(); kexec_smp_wait(); @@ -232,7 +232,7 @@ static void kexec_prepare_cpus(void) /* after we tell the others to go down */ if (ppc_md.cpu_irq_down) - ppc_md.cpu_irq_down(); + ppc_md.cpu_irq_down(0); put_cpu(); @@ -243,15 +243,19 @@ static void kexec_prepare_cpus(void) static void kexec_prepare_cpus(void) { + extern void smp_release_cpus(void); /* * move the secondarys to us so that we can copy * the new kernel 0-0x100 safely * * do this if kexec in setup.c ? + * + * We need to release the cpus if we are ever going from an + * UP to an SMP kernel. */ - smp_relase_cpus(); + smp_release_cpus(); if (ppc_md.cpu_irq_down) - ppc_md.cpu_irq_down(); + ppc_md.cpu_irq_down(0); local_irq_disable(); } diff --git a/trunk/arch/ppc64/kernel/mpic.c b/trunk/arch/ppc64/kernel/mpic.c index e8fbab1df37f..cc262a05ddb4 100644 --- a/trunk/arch/ppc64/kernel/mpic.c +++ b/trunk/arch/ppc64/kernel/mpic.c @@ -794,10 +794,10 @@ void mpic_setup_this_cpu(void) /* * XXX: someone who knows mpic should check this. - * do we need to eoi the ipi here (see xics comments)? + * do we need to eoi the ipi including for kexec cpu here (see xics comments)? * or can we reset the mpic in the new kernel? */ -void mpic_teardown_this_cpu(void) +void mpic_teardown_this_cpu(int secondary) { struct mpic *mpic = mpic_primary; unsigned long flags; diff --git a/trunk/arch/ppc64/kernel/mpic.h b/trunk/arch/ppc64/kernel/mpic.h index 99fbbc9a084c..ca78a7f10528 100644 --- a/trunk/arch/ppc64/kernel/mpic.h +++ b/trunk/arch/ppc64/kernel/mpic.h @@ -256,7 +256,7 @@ extern unsigned int mpic_irq_get_priority(unsigned int irq); extern void mpic_setup_this_cpu(void); /* Clean up for kexec (or cpu offline or ...) */ -extern void mpic_teardown_this_cpu(void); +extern void mpic_teardown_this_cpu(int secondary); /* Request IPIs on primary mpic */ extern void mpic_request_ipis(void); diff --git a/trunk/arch/ppc64/kernel/pci.c b/trunk/arch/ppc64/kernel/pci.c index ae6f579d3fa0..d0d55c7908ef 100644 --- a/trunk/arch/ppc64/kernel/pci.c +++ b/trunk/arch/ppc64/kernel/pci.c @@ -108,8 +108,28 @@ void pcibios_resource_to_bus(struct pci_dev *dev, struct pci_bus_region *region region->end = res->end - offset; } +void pcibios_bus_to_resource(struct pci_dev *dev, struct resource *res, + struct pci_bus_region *region) +{ + unsigned long offset = 0; + struct pci_controller *hose = pci_bus_to_host(dev->bus); + + if (!hose) + return; + + if (res->flags & IORESOURCE_IO) + offset = (unsigned long)hose->io_base_virt - pci_io_base; + + if (res->flags & IORESOURCE_MEM) + offset = hose->pci_mem_offset; + + res->start = region->start + offset; + res->end = region->end + offset; +} + #ifdef CONFIG_HOTPLUG EXPORT_SYMBOL(pcibios_resource_to_bus); +EXPORT_SYMBOL(pcibios_bus_to_resource); #endif /* diff --git a/trunk/arch/ppc64/kernel/xics.c b/trunk/arch/ppc64/kernel/xics.c index 677c4450984a..d9dc6f28d050 100644 --- a/trunk/arch/ppc64/kernel/xics.c +++ b/trunk/arch/ppc64/kernel/xics.c @@ -647,29 +647,30 @@ static void xics_set_affinity(unsigned int virq, cpumask_t cpumask) } } -void xics_teardown_cpu(void) +void xics_teardown_cpu(int secondary) { int cpu = smp_processor_id(); - int status; ops->cppr_info(cpu, 0x00); iosync(); /* - * we need to EOI the IPI if we got here from kexec down IPI - * - * xics doesn't care if we duplicate an EOI as long as we - * don't EOI and raise priority. - * - * probably need to check all the other interrupts too - * should we be flagging idle loop instead? - * or creating some task to be scheduled? + * Some machines need to have at least one cpu in the GIQ, + * so leave the master cpu in the group. */ - ops->xirr_info_set(cpu, XICS_IPI); - - status = rtas_set_indicator(GLOBAL_INTERRUPT_QUEUE, - (1UL << interrupt_server_size) - 1 - default_distrib_server, 0); - WARN_ON(status != 0); + if (secondary) { + /* + * we need to EOI the IPI if we got here from kexec down IPI + * + * probably need to check all the other interrupts too + * should we be flagging idle loop instead? + * or creating some task to be scheduled? + */ + ops->xirr_info_set(cpu, XICS_IPI); + rtas_set_indicator(GLOBAL_INTERRUPT_QUEUE, + (1UL << interrupt_server_size) - 1 - + default_distrib_server, 0); + } } #ifdef CONFIG_HOTPLUG_CPU diff --git a/trunk/arch/sh64/mm/fault.c b/trunk/arch/sh64/mm/fault.c index a24932881dbb..f08d0eaf6497 100644 --- a/trunk/arch/sh64/mm/fault.c +++ b/trunk/arch/sh64/mm/fault.c @@ -223,13 +223,13 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long writeaccess, */ survive: switch (handle_mm_fault(mm, vma, address, writeaccess)) { - case 1: + case VM_FAULT_MINOR: tsk->min_flt++; break; - case 2: + case VM_FAULT_MAJOR: tsk->maj_flt++; break; - case 0: + case VM_FAULT_SIGBUS: goto do_sigbus; default: goto out_of_memory; diff --git a/trunk/arch/sparc64/kernel/pci.c b/trunk/arch/sparc64/kernel/pci.c index bba140d98b1b..914e125d3971 100644 --- a/trunk/arch/sparc64/kernel/pci.c +++ b/trunk/arch/sparc64/kernel/pci.c @@ -413,6 +413,12 @@ static int pci_assign_bus_resource(const struct pci_bus *bus, return -EBUSY; } +void pci_update_resource(struct pci_dev *dev, struct resource *res, int resno) +{ + /* Not implemented for sparc64... */ + BUG(); +} + int pci_assign_resource(struct pci_dev *pdev, int resource) { struct pcidev_cookie *pcp = pdev->sysdata; diff --git a/trunk/arch/x86_64/ia32/ptrace32.c b/trunk/arch/x86_64/ia32/ptrace32.c index b98b6d2462f6..2a925e2af390 100644 --- a/trunk/arch/x86_64/ia32/ptrace32.c +++ b/trunk/arch/x86_64/ia32/ptrace32.c @@ -43,11 +43,11 @@ static int putreg32(struct task_struct *child, unsigned regno, u32 val) switch (regno) { case offsetof(struct user32, regs.fs): if (val && (val & 3) != 3) return -EIO; - child->thread.fs = val & 0xffff; + child->thread.fsindex = val & 0xffff; break; case offsetof(struct user32, regs.gs): if (val && (val & 3) != 3) return -EIO; - child->thread.gs = val & 0xffff; + child->thread.gsindex = val & 0xffff; break; case offsetof(struct user32, regs.ds): if (val && (val & 3) != 3) return -EIO; @@ -138,10 +138,10 @@ static int getreg32(struct task_struct *child, unsigned regno, u32 *val) switch (regno) { case offsetof(struct user32, regs.fs): - *val = child->thread.fs; + *val = child->thread.fsindex; break; case offsetof(struct user32, regs.gs): - *val = child->thread.gs; + *val = child->thread.gsindex; break; case offsetof(struct user32, regs.ds): *val = child->thread.ds; diff --git a/trunk/arch/x86_64/mm/fault.c b/trunk/arch/x86_64/mm/fault.c index 13792721037e..493819e543a5 100644 --- a/trunk/arch/x86_64/mm/fault.c +++ b/trunk/arch/x86_64/mm/fault.c @@ -439,13 +439,13 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long error_code) * the fault. */ switch (handle_mm_fault(mm, vma, address, write)) { - case 1: + case VM_FAULT_MINOR: tsk->min_flt++; break; - case 2: + case VM_FAULT_MAJOR: tsk->maj_flt++; break; - case 0: + case VM_FAULT_SIGBUS: goto do_sigbus; default: goto out_of_memory; diff --git a/trunk/drivers/acpi/dispatcher/dswload.c b/trunk/drivers/acpi/dispatcher/dswload.c index 1ac197ccfc80..d11620018421 100644 --- a/trunk/drivers/acpi/dispatcher/dswload.c +++ b/trunk/drivers/acpi/dispatcher/dswload.c @@ -491,12 +491,6 @@ acpi_ds_load2_begin_op ( if ((!(walk_state->op_info->flags & AML_NSOPCODE) && (walk_state->opcode != AML_INT_NAMEPATH_OP)) || (!(walk_state->op_info->flags & AML_NAMED))) { - if ((walk_state->op_info->class == AML_CLASS_EXECUTE) || - (walk_state->op_info->class == AML_CLASS_CONTROL)) { - ACPI_REPORT_WARNING (( - "Encountered executable code at module level, [%s]\n", - acpi_ps_get_opcode_name (walk_state->opcode))); - } return_ACPI_STATUS (AE_OK); } diff --git a/trunk/drivers/acpi/osl.c b/trunk/drivers/acpi/osl.c index bdd9f37f8101..7289da3c4db6 100644 --- a/trunk/drivers/acpi/osl.c +++ b/trunk/drivers/acpi/osl.c @@ -145,10 +145,14 @@ acpi_os_vprintf(const char *fmt, va_list args) #endif } +extern int acpi_in_resume; void * acpi_os_allocate(acpi_size size) { - return kmalloc(size, GFP_KERNEL); + if (acpi_in_resume) + return kmalloc(size, GFP_ATOMIC); + else + return kmalloc(size, GFP_KERNEL); } void diff --git a/trunk/drivers/acpi/pci_link.c b/trunk/drivers/acpi/pci_link.c index 65cea07abbc3..834c2ceff1aa 100644 --- a/trunk/drivers/acpi/pci_link.c +++ b/trunk/drivers/acpi/pci_link.c @@ -798,6 +798,11 @@ acpi_pci_link_resume( return_VALUE(0); } +/* + * FIXME: this is a workaround to avoid nasty warning. It will be removed + * after every device calls pci_disable_device in .resume. + */ +int acpi_in_resume; static int irqrouter_resume( struct sys_device *dev) @@ -807,6 +812,7 @@ irqrouter_resume( ACPI_FUNCTION_TRACE("irqrouter_resume"); + acpi_in_resume = 1; list_for_each(node, &acpi_link.entries) { link = list_entry(node, struct acpi_pci_link, node); if (!link) { @@ -816,6 +822,7 @@ irqrouter_resume( } acpi_pci_link_resume(link); } + acpi_in_resume = 0; return_VALUE(0); } diff --git a/trunk/drivers/char/rtc.c b/trunk/drivers/char/rtc.c index d8f9e94ae475..cd4fe8b1709f 100644 --- a/trunk/drivers/char/rtc.c +++ b/trunk/drivers/char/rtc.c @@ -1209,6 +1209,7 @@ static int rtc_proc_open(struct inode *inode, struct file *file) void rtc_get_rtc_time(struct rtc_time *rtc_tm) { + unsigned long uip_watchdog = jiffies; unsigned char ctrl; #ifdef CONFIG_MACH_DECSTATION unsigned int real_year; @@ -1224,8 +1225,10 @@ void rtc_get_rtc_time(struct rtc_time *rtc_tm) * Once the read clears, read the RTC time (again via ioctl). Easy. */ - if (rtc_is_updating() != 0) - msleep(20); + while (rtc_is_updating() != 0 && jiffies - uip_watchdog < 2*HZ/100) { + barrier(); + cpu_relax(); + } /* * Only the values that we read from the RTC are set. We leave diff --git a/trunk/drivers/fc4/fc.c b/trunk/drivers/fc4/fc.c index 5d961f5e0ca0..e4710d1d1f9d 100644 --- a/trunk/drivers/fc4/fc.c +++ b/trunk/drivers/fc4/fc.c @@ -1004,8 +1004,8 @@ int fcp_scsi_dev_reset(Scsi_Cmnd *SCpnt) return FAILED; } fc->rst_pkt->eh_state = SCSI_STATE_UNUSED; - return SUCCESS; #endif + return SUCCESS; } static int __fcp_scsi_host_reset(Scsi_Cmnd *SCpnt) diff --git a/trunk/drivers/ide/ide-probe.c b/trunk/drivers/ide/ide-probe.c index 7df85af75371..94daf40ae323 100644 --- a/trunk/drivers/ide/ide-probe.c +++ b/trunk/drivers/ide/ide-probe.c @@ -960,6 +960,15 @@ static void save_match(ide_hwif_t *hwif, ide_hwif_t *new, ide_hwif_t **match) } #endif /* MAX_HWIFS > 1 */ +static inline int hwif_to_node(ide_hwif_t *hwif) +{ + if (hwif->pci_dev) + return pcibus_to_node(hwif->pci_dev->bus); + else + /* Add ways to determine the node of other busses here */ + return -1; +} + /* * init request queue */ @@ -978,8 +987,7 @@ static int ide_init_queue(ide_drive_t *drive) * do not. */ - q = blk_init_queue_node(do_ide_request, &ide_lock, - pcibus_to_node(drive->hwif->pci_dev->bus)); + q = blk_init_queue_node(do_ide_request, &ide_lock, hwif_to_node(hwif)); if (!q) return 1; @@ -1048,6 +1056,8 @@ static int init_irq (ide_hwif_t *hwif) BUG_ON(in_interrupt()); BUG_ON(irqs_disabled()); + BUG_ON(hwif == NULL); + down(&ide_cfg_sem); hwif->hwgroup = NULL; #if MAX_HWIFS > 1 @@ -1097,7 +1107,7 @@ static int init_irq (ide_hwif_t *hwif) spin_unlock_irq(&ide_lock); } else { hwgroup = kmalloc_node(sizeof(ide_hwgroup_t), GFP_KERNEL, - pcibus_to_node(hwif->drives[0].hwif->pci_dev->bus)); + hwif_to_node(hwif->drives[0].hwif)); if (!hwgroup) goto out_up; diff --git a/trunk/drivers/infiniband/include/ib_cm.h b/trunk/drivers/infiniband/include/ib_cm.h index e5d74a730a70..da650115e79a 100644 --- a/trunk/drivers/infiniband/include/ib_cm.h +++ b/trunk/drivers/infiniband/include/ib_cm.h @@ -169,7 +169,8 @@ enum ib_cm_rej_reason { IB_CM_REJ_INVALID_ALT_TRAFFIC_CLASS = __constant_htons(21), IB_CM_REJ_INVALID_ALT_HOP_LIMIT = __constant_htons(22), IB_CM_REJ_INVALID_ALT_PACKET_RATE = __constant_htons(23), - IB_CM_REJ_PORT_REDIRECT = __constant_htons(24), + IB_CM_REJ_PORT_CM_REDIRECT = __constant_htons(24), + IB_CM_REJ_PORT_REDIRECT = __constant_htons(25), IB_CM_REJ_INVALID_MTU = __constant_htons(26), IB_CM_REJ_INSUFFICIENT_RESP_RESOURCES = __constant_htons(27), IB_CM_REJ_CONSUMER_DEFINED = __constant_htons(28), diff --git a/trunk/drivers/infiniband/ulp/ipoib/ipoib_main.c b/trunk/drivers/infiniband/ulp/ipoib/ipoib_main.c index 6f60abbaebd5..fa00816a3cf7 100644 --- a/trunk/drivers/infiniband/ulp/ipoib/ipoib_main.c +++ b/trunk/drivers/infiniband/ulp/ipoib/ipoib_main.c @@ -600,9 +600,10 @@ static int ipoib_start_xmit(struct sk_buff *skb, struct net_device *dev) ipoib_mcast_send(dev, (union ib_gid *) (phdr->hwaddr + 4), skb); } else { - /* unicast GID -- should be ARP reply */ + /* unicast GID -- should be ARP or RARP reply */ - if (be16_to_cpup((u16 *) skb->data) != ETH_P_ARP) { + if ((be16_to_cpup((__be16 *) skb->data) != ETH_P_ARP) && + (be16_to_cpup((__be16 *) skb->data) != ETH_P_RARP)) { ipoib_warn(priv, "Unicast, no %s: type %04x, QPN %06x " IPOIB_GID_FMT "\n", skb->dst ? "neigh" : "dst", diff --git a/trunk/drivers/md/bitmap.c b/trunk/drivers/md/bitmap.c index 70bca955e0de..41df4cda66e2 100644 --- a/trunk/drivers/md/bitmap.c +++ b/trunk/drivers/md/bitmap.c @@ -818,8 +818,7 @@ int bitmap_unplug(struct bitmap *bitmap) return 0; } -static void bitmap_set_memory_bits(struct bitmap *bitmap, sector_t offset, - unsigned long sectors, int in_sync); +static void bitmap_set_memory_bits(struct bitmap *bitmap, sector_t offset); /* * bitmap_init_from_disk -- called at bitmap_create time to initialize * the in-memory bitmap from the on-disk bitmap -- also, sets up the * memory mapping of the bitmap file @@ -828,7 +827,7 @@ static void bitmap_set_memory_bits(struct bitmap *bitmap, sector_t offset, * previously kicked from the array, we mark all the bits as * 1's in order to cause a full resync. */ -static int bitmap_init_from_disk(struct bitmap *bitmap, int in_sync) +static int bitmap_init_from_disk(struct bitmap *bitmap) { unsigned long i, chunks, index, oldindex, bit; struct page *page = NULL, *oldpage = NULL; @@ -929,8 +928,7 @@ static int bitmap_init_from_disk(struct bitmap *bitmap, int in_sync) } if (test_bit(bit, page_address(page))) { /* if the disk bit is set, set the memory bit */ - bitmap_set_memory_bits(bitmap, - i << CHUNK_BLOCK_SHIFT(bitmap), 1, in_sync); + bitmap_set_memory_bits(bitmap, i << CHUNK_BLOCK_SHIFT(bitmap)); bit_cnt++; } } @@ -1426,35 +1424,53 @@ void bitmap_close_sync(struct bitmap *bitmap) } } -static void bitmap_set_memory_bits(struct bitmap *bitmap, sector_t offset, - unsigned long sectors, int in_sync) +static void bitmap_set_memory_bits(struct bitmap *bitmap, sector_t offset) { /* For each chunk covered by any of these sectors, set the - * counter to 1 and set resync_needed unless in_sync. They should all + * counter to 1 and set resync_needed. They should all * be 0 at this point */ - while (sectors) { - int secs; - bitmap_counter_t *bmc; - spin_lock_irq(&bitmap->lock); - bmc = bitmap_get_counter(bitmap, offset, &secs, 1); - if (!bmc) { - spin_unlock_irq(&bitmap->lock); - return; - } - if (! *bmc) { - struct page *page; - *bmc = 1 | (in_sync? 0 : NEEDED_MASK); - bitmap_count_page(bitmap, offset, 1); - page = filemap_get_page(bitmap, offset >> CHUNK_BLOCK_SHIFT(bitmap)); - set_page_attr(bitmap, page, BITMAP_PAGE_CLEAN); - } + + int secs; + bitmap_counter_t *bmc; + spin_lock_irq(&bitmap->lock); + bmc = bitmap_get_counter(bitmap, offset, &secs, 1); + if (!bmc) { spin_unlock_irq(&bitmap->lock); - if (sectors > secs) - sectors -= secs; - else - sectors = 0; + return; + } + if (! *bmc) { + struct page *page; + *bmc = 1 | NEEDED_MASK; + bitmap_count_page(bitmap, offset, 1); + page = filemap_get_page(bitmap, offset >> CHUNK_BLOCK_SHIFT(bitmap)); + set_page_attr(bitmap, page, BITMAP_PAGE_CLEAN); } + spin_unlock_irq(&bitmap->lock); + +} + +/* + * flush out any pending updates + */ +void bitmap_flush(mddev_t *mddev) +{ + struct bitmap *bitmap = mddev->bitmap; + int sleep; + + if (!bitmap) /* there was no bitmap */ + return; + + /* run the daemon_work three time to ensure everything is flushed + * that can be + */ + sleep = bitmap->daemon_sleep; + bitmap->daemon_sleep = 0; + bitmap_daemon_work(bitmap); + bitmap_daemon_work(bitmap); + bitmap_daemon_work(bitmap); + bitmap->daemon_sleep = sleep; + bitmap_update_sb(bitmap); } /* @@ -1565,7 +1581,8 @@ int bitmap_create(mddev_t *mddev) /* now that we have some pages available, initialize the in-memory * bitmap from the on-disk bitmap */ - err = bitmap_init_from_disk(bitmap, mddev->recovery_cp == MaxSector); + err = bitmap_init_from_disk(bitmap); + if (err) return err; diff --git a/trunk/drivers/md/dm-raid1.c b/trunk/drivers/md/dm-raid1.c index 12031c9d3f1e..b08df8b9b2ca 100644 --- a/trunk/drivers/md/dm-raid1.c +++ b/trunk/drivers/md/dm-raid1.c @@ -1230,7 +1230,7 @@ static int __init dm_mirror_init(void) if (r) return r; - _kmirrord_wq = create_workqueue("kmirrord"); + _kmirrord_wq = create_singlethread_workqueue("kmirrord"); if (!_kmirrord_wq) { DMERR("couldn't start kmirrord"); dm_dirty_log_exit(); diff --git a/trunk/drivers/md/md.c b/trunk/drivers/md/md.c index 6580e0fa4a47..480f658db6f2 100644 --- a/trunk/drivers/md/md.c +++ b/trunk/drivers/md/md.c @@ -1798,6 +1798,8 @@ static int do_md_stop(mddev_t * mddev, int ro) goto out; mddev->ro = 1; } else { + bitmap_flush(mddev); + wait_event(mddev->sb_wait, atomic_read(&mddev->pending_writes)==0); if (mddev->ro) set_disk_ro(disk, 0); blk_queue_make_request(mddev->queue, md_fail_request); @@ -3484,7 +3486,6 @@ static void md_do_sync(mddev_t *mddev) goto skip; } ITERATE_MDDEV(mddev2,tmp) { - printk("."); if (mddev2 == mddev) continue; if (mddev2->curr_resync && @@ -4007,3 +4008,4 @@ EXPORT_SYMBOL(md_wakeup_thread); EXPORT_SYMBOL(md_print_devices); EXPORT_SYMBOL(md_check_recovery); MODULE_LICENSE("GPL"); +MODULE_ALIAS("md"); diff --git a/trunk/drivers/md/raid1.c b/trunk/drivers/md/raid1.c index d3a64a04a6d8..51d9645ed09c 100644 --- a/trunk/drivers/md/raid1.c +++ b/trunk/drivers/md/raid1.c @@ -893,7 +893,6 @@ static int end_sync_read(struct bio *bio, unsigned int bytes_done, int error) if (!uptodate) { md_error(r1_bio->mddev, conf->mirrors[r1_bio->read_disk].rdev); - set_bit(R1BIO_Degraded, &r1_bio->state); } else set_bit(R1BIO_Uptodate, &r1_bio->state); rdev_dec_pending(conf->mirrors[r1_bio->read_disk].rdev, conf->mddev); @@ -918,10 +917,9 @@ static int end_sync_write(struct bio *bio, unsigned int bytes_done, int error) mirror = i; break; } - if (!uptodate) { + if (!uptodate) md_error(mddev, conf->mirrors[mirror].rdev); - set_bit(R1BIO_Degraded, &r1_bio->state); - } + update_head_pos(mirror, r1_bio); if (atomic_dec_and_test(&r1_bio->remaining)) { @@ -1109,6 +1107,7 @@ static sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *skipped, i int i; int write_targets = 0; int sync_blocks; + int still_degraded = 0; if (!conf->r1buf_pool) { @@ -1137,7 +1136,10 @@ static sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *skipped, i return 0; } - if (!bitmap_start_sync(mddev->bitmap, sector_nr, &sync_blocks, mddev->degraded) && + /* before building a request, check if we can skip these blocks.. + * This call the bitmap_start_sync doesn't actually record anything + */ + if (!bitmap_start_sync(mddev->bitmap, sector_nr, &sync_blocks, 1) && !conf->fullsync) { /* We can skip this block, and probably several more */ *skipped = 1; @@ -1203,24 +1205,23 @@ static sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *skipped, i if (i == disk) { bio->bi_rw = READ; bio->bi_end_io = end_sync_read; - } else if (conf->mirrors[i].rdev && - !conf->mirrors[i].rdev->faulty && - (!conf->mirrors[i].rdev->in_sync || - sector_nr + RESYNC_SECTORS > mddev->recovery_cp)) { + } else if (conf->mirrors[i].rdev == NULL || + conf->mirrors[i].rdev->faulty) { + still_degraded = 1; + continue; + } else if (!conf->mirrors[i].rdev->in_sync || + sector_nr + RESYNC_SECTORS > mddev->recovery_cp) { bio->bi_rw = WRITE; bio->bi_end_io = end_sync_write; write_targets ++; } else + /* no need to read or write here */ continue; bio->bi_sector = sector_nr + conf->mirrors[i].rdev->data_offset; bio->bi_bdev = conf->mirrors[i].rdev->bdev; bio->bi_private = r1_bio; } - if (write_targets + 1 < conf->raid_disks) - /* array degraded, can't clear bitmap */ - set_bit(R1BIO_Degraded, &r1_bio->state); - if (write_targets == 0) { /* There is nowhere to write, so all non-sync * drives must be failed - so we are finished @@ -1243,7 +1244,7 @@ static sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *skipped, i break; if (sync_blocks == 0) { if (!bitmap_start_sync(mddev->bitmap, sector_nr, - &sync_blocks, mddev->degraded) && + &sync_blocks, still_degraded) && !conf->fullsync) break; if (sync_blocks < (PAGE_SIZE>>9)) diff --git a/trunk/drivers/media/video/bttv-cards.c b/trunk/drivers/media/video/bttv-cards.c index 6c52fd0bb7df..a97b9b958ed6 100644 --- a/trunk/drivers/media/video/bttv-cards.c +++ b/trunk/drivers/media/video/bttv-cards.c @@ -95,7 +95,7 @@ static int __devinit pvr_boot(struct bttv *btv); static unsigned int triton1=0; static unsigned int vsfx=0; static unsigned int latency = UNSET; -static unsigned int no_overlay=-1; +int no_overlay=-1; static unsigned int card[BTTV_MAX] = { [ 0 ... (BTTV_MAX-1) ] = UNSET }; static unsigned int pll[BTTV_MAX] = { [ 0 ... (BTTV_MAX-1) ] = UNSET }; @@ -4296,9 +4296,11 @@ void __devinit bttv_check_chipset(void) printk(KERN_INFO "bttv: Host bridge needs VSFX enabled.\n"); if (pcipci_fail) { printk(KERN_WARNING "bttv: BT848 and your chipset may not work together.\n"); - if (UNSET == no_overlay) { - printk(KERN_WARNING "bttv: going to disable overlay.\n"); + if (!no_overlay) { + printk(KERN_WARNING "bttv: overlay will be disabled.\n"); no_overlay = 1; + } else { + printk(KERN_WARNING "bttv: overlay forced. Use this option at your own risk.\n"); } } if (UNSET != latency) diff --git a/trunk/drivers/media/video/bttv-driver.c b/trunk/drivers/media/video/bttv-driver.c index 67f331eeeb19..eee9322ce21b 100644 --- a/trunk/drivers/media/video/bttv-driver.c +++ b/trunk/drivers/media/video/bttv-driver.c @@ -1,5 +1,5 @@ /* - $Id: bttv-driver.c,v 1.45 2005/07/20 19:43:24 mkrufky Exp $ + $Id: bttv-driver.c,v 1.52 2005/08/04 00:55:16 mchehab Exp $ bttv - Bt848 frame grabber driver @@ -80,6 +80,7 @@ static unsigned int irq_iswitch = 0; static unsigned int uv_ratio = 50; static unsigned int full_luma_range = 0; static unsigned int coring = 0; +extern int no_overlay; /* API features (turn on/off stuff for testing) */ static unsigned int v4l2 = 1; @@ -2151,6 +2152,10 @@ static int bttv_s_fmt(struct bttv_fh *fh, struct bttv *btv, return 0; } case V4L2_BUF_TYPE_VIDEO_OVERLAY: + if (no_overlay > 0) { + printk ("V4L2_BUF_TYPE_VIDEO_OVERLAY: no_overlay\n"); + return -EINVAL; + } return setup_window(fh, btv, &f->fmt.win, 1); case V4L2_BUF_TYPE_VBI_CAPTURE: retval = bttv_switch_type(fh,f->type); @@ -2224,9 +2229,11 @@ static int bttv_do_ioctl(struct inode *inode, struct file *file, /* others */ cap->type = VID_TYPE_CAPTURE| VID_TYPE_TUNER| - VID_TYPE_OVERLAY| VID_TYPE_CLIPPING| VID_TYPE_SCALES; + if (no_overlay <= 0) + cap->type |= VID_TYPE_OVERLAY; + cap->maxwidth = bttv_tvnorms[btv->tvnorm].swidth; cap->maxheight = bttv_tvnorms[btv->tvnorm].sheight; cap->minwidth = 48; @@ -2302,6 +2309,11 @@ static int bttv_do_ioctl(struct inode *inode, struct file *file, struct video_window *win = arg; struct v4l2_window w2; + if (no_overlay > 0) { + printk ("VIDIOCSWIN: no_overlay\n"); + return -EINVAL; + } + w2.field = V4L2_FIELD_ANY; w2.w.left = win->x; w2.w.top = win->y; @@ -2577,10 +2589,12 @@ static int bttv_do_ioctl(struct inode *inode, struct file *file, cap->version = BTTV_VERSION_CODE; cap->capabilities = V4L2_CAP_VIDEO_CAPTURE | - V4L2_CAP_VIDEO_OVERLAY | V4L2_CAP_VBI_CAPTURE | V4L2_CAP_READWRITE | V4L2_CAP_STREAMING; + if (no_overlay <= 0) + cap->capabilities |= V4L2_CAP_VIDEO_OVERLAY; + if (bttv_tvcards[btv->c.type].tuner != UNSET && bttv_tvcards[btv->c.type].tuner != TUNER_ABSENT) cap->capabilities |= V4L2_CAP_TUNER; @@ -3076,7 +3090,7 @@ static struct file_operations bttv_fops = static struct video_device bttv_video_template = { .name = "UNSET", - .type = VID_TYPE_CAPTURE|VID_TYPE_TUNER|VID_TYPE_OVERLAY| + .type = VID_TYPE_CAPTURE|VID_TYPE_TUNER| VID_TYPE_CLIPPING|VID_TYPE_SCALES, .hardware = VID_HARDWARE_BT848, .fops = &bttv_fops, @@ -3756,6 +3770,12 @@ static void bttv_unregister_video(struct bttv *btv) /* register video4linux devices */ static int __devinit bttv_register_video(struct bttv *btv) { + if (no_overlay <= 0) { + bttv_video_template.type |= VID_TYPE_OVERLAY; + } else { + printk("bttv: Overlay support disabled.\n"); + } + /* video */ btv->video_dev = vdev_init(btv, &bttv_video_template, "video"); if (NULL == btv->video_dev) diff --git a/trunk/drivers/pci/pci.c b/trunk/drivers/pci/pci.c index 1b34fc56067e..65ea7d25f691 100644 --- a/trunk/drivers/pci/pci.c +++ b/trunk/drivers/pci/pci.c @@ -221,6 +221,37 @@ pci_find_parent_resource(const struct pci_dev *dev, struct resource *res) return best; } +/** + * pci_restore_bars - restore a devices BAR values (e.g. after wake-up) + * @dev: PCI device to have its BARs restored + * + * Restore the BAR values for a given device, so as to make it + * accessible by its driver. + */ +void +pci_restore_bars(struct pci_dev *dev) +{ + int i, numres; + + switch (dev->hdr_type) { + case PCI_HEADER_TYPE_NORMAL: + numres = 6; + break; + case PCI_HEADER_TYPE_BRIDGE: + numres = 2; + break; + case PCI_HEADER_TYPE_CARDBUS: + numres = 1; + break; + default: + /* Should never get here, but just in case... */ + return; + } + + for (i = 0; i < numres; i ++) + pci_update_resource(dev, &dev->resource[i], i); +} + /** * pci_set_power_state - Set the power state of a PCI device * @dev: PCI device to be suspended @@ -239,7 +270,7 @@ int (*platform_pci_set_power_state)(struct pci_dev *dev, pci_power_t t); int pci_set_power_state(struct pci_dev *dev, pci_power_t state) { - int pm; + int pm, need_restore = 0; u16 pmcsr, pmc; /* bound the state we're entering */ @@ -278,14 +309,17 @@ pci_set_power_state(struct pci_dev *dev, pci_power_t state) return -EIO; } + pci_read_config_word(dev, pm + PCI_PM_CTRL, &pmcsr); + /* If we're in D3, force entire word to 0. * This doesn't affect PME_Status, disables PME_En, and * sets PowerState to 0. */ - if (dev->current_state >= PCI_D3hot) + if (dev->current_state >= PCI_D3hot) { + if (!(pmcsr & PCI_PM_CTRL_NO_SOFT_RESET)) + need_restore = 1; pmcsr = 0; - else { - pci_read_config_word(dev, pm + PCI_PM_CTRL, &pmcsr); + } else { pmcsr &= ~PCI_PM_CTRL_STATE_MASK; pmcsr |= state; } @@ -308,6 +342,22 @@ pci_set_power_state(struct pci_dev *dev, pci_power_t state) platform_pci_set_power_state(dev, state); dev->current_state = state; + + /* According to section 5.4.1 of the "PCI BUS POWER MANAGEMENT + * INTERFACE SPECIFICATION, REV. 1.2", a device transitioning + * from D3hot to D0 _may_ perform an internal reset, thereby + * going to "D0 Uninitialized" rather than "D0 Initialized". + * For example, at least some versions of the 3c905B and the + * 3c556B exhibit this behaviour. + * + * At least some laptop BIOSen (e.g. the Thinkpad T21) leave + * devices in a D3hot state at boot. Consequently, we need to + * restore at least the BARs so that the device will be + * accessible to its driver. + */ + if (need_restore) + pci_restore_bars(dev); + return 0; } @@ -805,6 +855,7 @@ struct pci_dev *isa_bridge; EXPORT_SYMBOL(isa_bridge); #endif +EXPORT_SYMBOL_GPL(pci_restore_bars); EXPORT_SYMBOL(pci_enable_device_bars); EXPORT_SYMBOL(pci_enable_device); EXPORT_SYMBOL(pci_disable_device); diff --git a/trunk/drivers/pci/setup-res.c b/trunk/drivers/pci/setup-res.c index 1ca21d2ba11c..878fd0a65c02 100644 --- a/trunk/drivers/pci/setup-res.c +++ b/trunk/drivers/pci/setup-res.c @@ -26,7 +26,7 @@ #include "pci.h" -static void +void pci_update_resource(struct pci_dev *dev, struct resource *res, int resno) { struct pci_bus_region region; diff --git a/trunk/drivers/pcmcia/yenta_socket.c b/trunk/drivers/pcmcia/yenta_socket.c index 91e7457d5b04..62fd705203fb 100644 --- a/trunk/drivers/pcmcia/yenta_socket.c +++ b/trunk/drivers/pcmcia/yenta_socket.c @@ -605,9 +605,8 @@ static int yenta_search_res(struct yenta_socket *socket, struct resource *res, static void yenta_allocate_res(struct yenta_socket *socket, int nr, unsigned type, int addr_start, int addr_end) { - struct pci_bus *bus; struct resource *root, *res; - u32 start, end; + struct pci_bus_region region; unsigned mask; res = socket->dev->resource + PCI_BRIDGE_RESOURCES + nr; @@ -620,15 +619,13 @@ static void yenta_allocate_res(struct yenta_socket *socket, int nr, unsigned typ if (type & IORESOURCE_IO) mask = ~3; - bus = socket->dev->subordinate; - res->name = bus->name; + res->name = socket->dev->subordinate->name; res->flags = type; - start = config_readl(socket, addr_start) & mask; - end = config_readl(socket, addr_end) | ~mask; - if (start && end > start && !override_bios) { - res->start = start; - res->end = end; + region.start = config_readl(socket, addr_start) & mask; + region.end = config_readl(socket, addr_end) | ~mask; + if (region.start && region.end > region.start && !override_bios) { + pcibios_bus_to_resource(socket->dev, res, ®ion); root = pci_find_parent_resource(socket->dev, res); if (root && (request_resource(root, res) == 0)) return; diff --git a/trunk/drivers/scsi/aic7xxx/aic7xxx_osm.c b/trunk/drivers/scsi/aic7xxx/aic7xxx_osm.c index 116d0f51ca2c..687f19e9cf03 100644 --- a/trunk/drivers/scsi/aic7xxx/aic7xxx_osm.c +++ b/trunk/drivers/scsi/aic7xxx/aic7xxx_osm.c @@ -1264,14 +1264,12 @@ ahc_platform_set_tags(struct ahc_softc *ahc, struct ahc_devinfo *devinfo, } switch ((dev->flags & (AHC_DEV_Q_BASIC|AHC_DEV_Q_TAGGED))) { case AHC_DEV_Q_BASIC: - scsi_adjust_queue_depth(sdev, - MSG_SIMPLE_TASK, - dev->openings + dev->active); + scsi_set_tag_type(sdev, MSG_SIMPLE_TAG); + scsi_activate_tcq(sdev, dev->openings + dev->active); break; case AHC_DEV_Q_TAGGED: - scsi_adjust_queue_depth(sdev, - MSG_ORDERED_TASK, - dev->openings + dev->active); + scsi_set_tag_type(sdev, MSG_ORDERED_TAG); + scsi_activate_tcq(sdev, dev->openings + dev->active); break; default: /* @@ -1280,9 +1278,7 @@ ahc_platform_set_tags(struct ahc_softc *ahc, struct ahc_devinfo *devinfo, * serially on the controller/device. This should * remove some latency. */ - scsi_adjust_queue_depth(sdev, - /*NON-TAGGED*/0, - /*queue depth*/2); + scsi_deactivate_tcq(sdev, 2); break; } } @@ -1635,9 +1631,9 @@ ahc_send_async(struct ahc_softc *ahc, char channel, spi_period(starget) = tinfo->curr.period; spi_width(starget) = tinfo->curr.width; spi_offset(starget) = tinfo->curr.offset; - spi_dt(starget) = tinfo->curr.ppr_options & MSG_EXT_PPR_DT_REQ; - spi_qas(starget) = tinfo->curr.ppr_options & MSG_EXT_PPR_QAS_REQ; - spi_iu(starget) = tinfo->curr.ppr_options & MSG_EXT_PPR_IU_REQ; + spi_dt(starget) = tinfo->curr.ppr_options & MSG_EXT_PPR_DT_REQ ? 1 : 0; + spi_qas(starget) = tinfo->curr.ppr_options & MSG_EXT_PPR_QAS_REQ ? 1 : 0; + spi_iu(starget) = tinfo->curr.ppr_options & MSG_EXT_PPR_IU_REQ ? 1 : 0; spi_display_xfer_agreement(starget); break; } @@ -2429,12 +2425,14 @@ static void ahc_linux_set_dt(struct scsi_target *starget, int dt) unsigned int ppr_options = tinfo->goal.ppr_options & ~MSG_EXT_PPR_DT_REQ; unsigned int period = tinfo->goal.period; + unsigned int width = tinfo->goal.width; unsigned long flags; struct ahc_syncrate *syncrate; if (dt) { - period = 9; /* 12.5ns is the only period valid for DT */ ppr_options |= MSG_EXT_PPR_DT_REQ; + if (!width) + ahc_linux_set_width(starget, 1); } else if (period == 9) period = 10; /* if resetting DT, period must be >= 25ns */ diff --git a/trunk/drivers/scsi/ibmvscsi/srp.h b/trunk/drivers/scsi/ibmvscsi/srp.h index 2ae5154fd89c..7d8e4c4accb9 100644 --- a/trunk/drivers/scsi/ibmvscsi/srp.h +++ b/trunk/drivers/scsi/ibmvscsi/srp.h @@ -35,7 +35,7 @@ enum srp_types { SRP_LOGIN_REQ_TYPE = 0x00, SRP_LOGIN_RSP_TYPE = 0xC0, - SRP_LOGIN_REJ_TYPE = 0x80, + SRP_LOGIN_REJ_TYPE = 0xC2, SRP_I_LOGOUT_TYPE = 0x03, SRP_T_LOGOUT_TYPE = 0x80, SRP_TSK_MGMT_TYPE = 0x01, diff --git a/trunk/drivers/scsi/ips.c b/trunk/drivers/scsi/ips.c index 6dfcb4fbccdd..4cdd891781b1 100644 --- a/trunk/drivers/scsi/ips.c +++ b/trunk/drivers/scsi/ips.c @@ -133,10 +133,12 @@ /* 6.10.00 - Remove 1G Addressing Limitations */ /* 6.11.xx - Get VersionInfo buffer off the stack ! DDTS 60401 */ /* 6.11.xx - Make Logical Drive Info structure safe for DMA DDTS 60639 */ -/* 7.10.xx - Add highmem_io flag in SCSI Templete for 2.4 kernels */ +/* 7.10.18 - Add highmem_io flag in SCSI Templete for 2.4 kernels */ /* - Fix path/name for scsi_hosts.h include for 2.6 kernels */ /* - Fix sort order of 7k */ /* - Remove 3 unused "inline" functions */ +/* 7.12.xx - Use STATIC functions whereever possible */ +/* - Clean up deprecated MODULE_PARM calls */ /*****************************************************************************/ /* @@ -207,8 +209,8 @@ module_param(ips, charp, 0); /* * DRIVER_VER */ -#define IPS_VERSION_HIGH "7.10" -#define IPS_VERSION_LOW ".18 " +#define IPS_VERSION_HIGH "7.12" +#define IPS_VERSION_LOW ".02 " #if !defined(__i386__) && !defined(__ia64__) && !defined(__x86_64__) #warning "This driver has only been tested on the x86/ia64/x86_64 platforms" diff --git a/trunk/drivers/scsi/ips.h b/trunk/drivers/scsi/ips.h index 480e06f4d6ae..505e967013de 100644 --- a/trunk/drivers/scsi/ips.h +++ b/trunk/drivers/scsi/ips.h @@ -87,15 +87,14 @@ #define scsi_set_pci_device(sh,dev) (0) #endif - #if LINUX_VERSION_CODE < KERNEL_VERSION(2,5,0) - - #ifndef irqreturn_t - typedef void irqreturn_t; - #endif - + #ifndef IRQ_NONE + typedef void irqreturn_t; #define IRQ_NONE #define IRQ_HANDLED #define IRQ_RETVAL(x) + #endif + + #if LINUX_VERSION_CODE < KERNEL_VERSION(2,5,0) #define IPS_REGISTER_HOSTS(SHT) scsi_register_module(MODULE_SCSI_HA,SHT) #define IPS_UNREGISTER_HOSTS(SHT) scsi_unregister_module(MODULE_SCSI_HA,SHT) #define IPS_ADD_HOST(shost,device) @@ -123,6 +122,10 @@ #ifndef min #define min(x,y) ((x) < (y) ? x : y) #endif + + #ifndef __iomem /* For clean compiles in earlier kernels without __iomem annotations */ + #define __iomem + #endif #define pci_dma_hi32(a) ((a >> 16) >> 16) #define pci_dma_lo32(a) (a & 0xffffffff) @@ -1206,13 +1209,13 @@ typedef struct { #define IPS_VER_MAJOR 7 #define IPS_VER_MAJOR_STRING "7" -#define IPS_VER_MINOR 10 -#define IPS_VER_MINOR_STRING "10" -#define IPS_VER_BUILD 18 -#define IPS_VER_BUILD_STRING "18" -#define IPS_VER_STRING "7.10.18" +#define IPS_VER_MINOR 12 +#define IPS_VER_MINOR_STRING "12" +#define IPS_VER_BUILD 02 +#define IPS_VER_BUILD_STRING "02" +#define IPS_VER_STRING "7.12.02" #define IPS_RELEASE_ID 0x00020000 -#define IPS_BUILD_IDENT 731 +#define IPS_BUILD_IDENT 761 #define IPS_LEGALCOPYRIGHT_STRING "(C) Copyright IBM Corp. 1994, 2002. All Rights Reserved." #define IPS_ADAPTECCOPYRIGHT_STRING "(c) Copyright Adaptec, Inc. 2002 to 2004. All Rights Reserved." #define IPS_DELLCOPYRIGHT_STRING "(c) Copyright Dell 2004. All Rights Reserved." @@ -1223,12 +1226,12 @@ typedef struct { #define IPS_VER_SERVERAID2 "2.88.13" #define IPS_VER_NAVAJO "2.88.13" #define IPS_VER_SERVERAID3 "6.10.24" -#define IPS_VER_SERVERAID4H "7.10.11" -#define IPS_VER_SERVERAID4MLx "7.10.18" -#define IPS_VER_SARASOTA "7.10.18" -#define IPS_VER_MARCO "7.10.18" -#define IPS_VER_SEBRING "7.10.18" -#define IPS_VER_KEYWEST "7.10.18" +#define IPS_VER_SERVERAID4H "7.12.02" +#define IPS_VER_SERVERAID4MLx "7.12.02" +#define IPS_VER_SARASOTA "7.12.02" +#define IPS_VER_MARCO "7.12.02" +#define IPS_VER_SEBRING "7.12.02" +#define IPS_VER_KEYWEST "7.12.02" /* Compatability IDs for various adapters */ #define IPS_COMPAT_UNKNOWN "" diff --git a/trunk/drivers/scsi/st.c b/trunk/drivers/scsi/st.c index 0291a8fb654d..0a7839db5752 100644 --- a/trunk/drivers/scsi/st.c +++ b/trunk/drivers/scsi/st.c @@ -4149,12 +4149,10 @@ static int __init init_st(void) do_create_driverfs_files(); return 0; } - if (st_sysfs_class) - class_destroy(st_sysfs_class); unregister_chrdev_region(MKDEV(SCSI_TAPE_MAJOR, 0), - ST_MAX_TAPE_ENTRIES); } + class_destroy(st_sysfs_class); printk(KERN_ERR "Unable to get major %d for SCSI tapes\n", SCSI_TAPE_MAJOR); return 1; @@ -4162,13 +4160,11 @@ static int __init init_st(void) static void __exit exit_st(void) { - if (st_sysfs_class) - class_destroy(st_sysfs_class); - st_sysfs_class = NULL; do_remove_driverfs_files(); scsi_unregister_driver(&st_template.gendrv); unregister_chrdev_region(MKDEV(SCSI_TAPE_MAJOR, 0), ST_MAX_TAPE_ENTRIES); + class_destroy(st_sysfs_class); kfree(scsi_tapes); printk(KERN_INFO "st: Unloaded.\n"); } diff --git a/trunk/drivers/usb/host/ehci-dbg.c b/trunk/drivers/usb/host/ehci-dbg.c index 50cb01831075..b01efb6b36f6 100644 --- a/trunk/drivers/usb/host/ehci-dbg.c +++ b/trunk/drivers/usb/host/ehci-dbg.c @@ -527,7 +527,7 @@ show_periodic (struct class_device *class_dev, char *buf) p.qh->period, le32_to_cpup (&p.qh->hw_info2) /* uframe masks */ - & 0xffff, + & (QH_CMASK | QH_SMASK), p.qh); size -= temp; next += temp; diff --git a/trunk/drivers/usb/host/ehci-q.c b/trunk/drivers/usb/host/ehci-q.c index 4f97a4ad1ed3..20df01a79b2e 100644 --- a/trunk/drivers/usb/host/ehci-q.c +++ b/trunk/drivers/usb/host/ehci-q.c @@ -222,7 +222,7 @@ __acquires(ehci->lock) struct ehci_qh *qh = (struct ehci_qh *) urb->hcpriv; /* S-mask in a QH means it's an interrupt urb */ - if ((qh->hw_info2 & __constant_cpu_to_le32 (0x00ff)) != 0) { + if ((qh->hw_info2 & __constant_cpu_to_le32 (QH_SMASK)) != 0) { /* ... update hc-wide periodic stats (for usbfs) */ ehci_to_hcd(ehci)->self.bandwidth_int_reqs--; @@ -428,7 +428,8 @@ qh_completions (struct ehci_hcd *ehci, struct ehci_qh *qh, struct pt_regs *regs) /* should be rare for periodic transfers, * except maybe high bandwidth ... */ - if (qh->period) { + if ((__constant_cpu_to_le32 (QH_SMASK) + & qh->hw_info2) != 0) { intr_deschedule (ehci, qh); (void) qh_schedule (ehci, qh); } else diff --git a/trunk/drivers/usb/host/ehci-sched.c b/trunk/drivers/usb/host/ehci-sched.c index 9af4f64532a9..b56f25864ed6 100644 --- a/trunk/drivers/usb/host/ehci-sched.c +++ b/trunk/drivers/usb/host/ehci-sched.c @@ -301,7 +301,7 @@ static int qh_link_periodic (struct ehci_hcd *ehci, struct ehci_qh *qh) dev_dbg (&qh->dev->dev, "link qh%d-%04x/%p start %d [%d/%d us]\n", - period, le32_to_cpup (&qh->hw_info2) & 0xffff, + period, le32_to_cpup (&qh->hw_info2) & (QH_CMASK | QH_SMASK), qh, qh->start, qh->usecs, qh->c_usecs); /* high bandwidth, or otherwise every microframe */ @@ -385,7 +385,8 @@ static void qh_unlink_periodic (struct ehci_hcd *ehci, struct ehci_qh *qh) dev_dbg (&qh->dev->dev, "unlink qh%d-%04x/%p start %d [%d/%d us]\n", - qh->period, le32_to_cpup (&qh->hw_info2) & 0xffff, + qh->period, + le32_to_cpup (&qh->hw_info2) & (QH_CMASK | QH_SMASK), qh, qh->start, qh->usecs, qh->c_usecs); /* qh->qh_next still "live" to HC */ @@ -411,7 +412,7 @@ static void intr_deschedule (struct ehci_hcd *ehci, struct ehci_qh *qh) * active high speed queues may need bigger delays... */ if (list_empty (&qh->qtd_list) - || (__constant_cpu_to_le32 (0x0ff << 8) + || (__constant_cpu_to_le32 (QH_CMASK) & qh->hw_info2) != 0) wait = 2; else @@ -533,7 +534,7 @@ static int qh_schedule (struct ehci_hcd *ehci, struct ehci_qh *qh) /* reuse the previous schedule slots, if we can */ if (frame < qh->period) { - uframe = ffs (le32_to_cpup (&qh->hw_info2) & 0x00ff); + uframe = ffs (le32_to_cpup (&qh->hw_info2) & QH_SMASK); status = check_intr_schedule (ehci, frame, --uframe, qh, &c_mask); } else { @@ -569,10 +570,10 @@ static int qh_schedule (struct ehci_hcd *ehci, struct ehci_qh *qh) qh->start = frame; /* reset S-frame and (maybe) C-frame masks */ - qh->hw_info2 &= __constant_cpu_to_le32 (~0xffff); + qh->hw_info2 &= __constant_cpu_to_le32(~(QH_CMASK | QH_SMASK)); qh->hw_info2 |= qh->period ? cpu_to_le32 (1 << uframe) - : __constant_cpu_to_le32 (0xff); + : __constant_cpu_to_le32 (QH_SMASK); qh->hw_info2 |= c_mask; } else ehci_dbg (ehci, "reused qh %p schedule\n", qh); diff --git a/trunk/drivers/usb/host/ehci.h b/trunk/drivers/usb/host/ehci.h index 4df498231752..a7542157534c 100644 --- a/trunk/drivers/usb/host/ehci.h +++ b/trunk/drivers/usb/host/ehci.h @@ -385,6 +385,11 @@ struct ehci_qh { __le32 hw_info1; /* see EHCI 3.6.2 */ #define QH_HEAD 0x00008000 __le32 hw_info2; /* see EHCI 3.6.2 */ +#define QH_SMASK 0x000000ff +#define QH_CMASK 0x0000ff00 +#define QH_HUBADDR 0x007f0000 +#define QH_HUBPORT 0x3f800000 +#define QH_MULT 0xc0000000 __le32 hw_current; /* qtd list - see EHCI 3.6.4 */ /* qtd overlay (hardware parts of a struct ehci_qtd) */ diff --git a/trunk/drivers/usb/host/isp116x-hcd.c b/trunk/drivers/usb/host/isp116x-hcd.c index 50b1970fe6b6..76cb496c5836 100644 --- a/trunk/drivers/usb/host/isp116x-hcd.c +++ b/trunk/drivers/usb/host/isp116x-hcd.c @@ -229,9 +229,11 @@ static void preproc_atl_queue(struct isp116x *isp116x) struct isp116x_ep *ep; struct urb *urb; struct ptd *ptd; - u16 toggle = 0, dir = PTD_DIR_SETUP, len; + u16 len; for (ep = isp116x->atl_active; ep; ep = ep->active) { + u16 toggle = 0, dir = PTD_DIR_SETUP; + BUG_ON(list_empty(&ep->hep->urb_list)); urb = container_of(ep->hep->urb_list.next, struct urb, urb_list); diff --git a/trunk/drivers/usb/mon/Kconfig b/trunk/drivers/usb/mon/Kconfig index 777642e26b9a..deb9ddffa402 100644 --- a/trunk/drivers/usb/mon/Kconfig +++ b/trunk/drivers/usb/mon/Kconfig @@ -9,9 +9,8 @@ config USB_MON help If you say Y here, a component which captures the USB traffic between peripheral-specific drivers and HC drivers will be built. - The USB_MON is similar in spirit and may be compatible with Dave - Harding's USBMon. + For more information, see . - This is somewhat experimental at this time, but it should be safe, - as long as you aren't using modular USB and try to remove this - module. + This is somewhat experimental at this time, but it should be safe. + + If unsure, say Y. diff --git a/trunk/drivers/usb/mon/Makefile b/trunk/drivers/usb/mon/Makefile index f18d10ce91f9..b0015b8a1d1f 100644 --- a/trunk/drivers/usb/mon/Makefile +++ b/trunk/drivers/usb/mon/Makefile @@ -4,4 +4,5 @@ usbmon-objs := mon_main.o mon_stat.o mon_text.o +# This does not use CONFIG_USB_MON because we want this to use a tristate. obj-$(CONFIG_USB) += usbmon.o diff --git a/trunk/fs/Kconfig b/trunk/fs/Kconfig index 5d0c4be43dba..e54be7058359 100644 --- a/trunk/fs/Kconfig +++ b/trunk/fs/Kconfig @@ -363,12 +363,15 @@ config INOTIFY bool "Inotify file change notification support" default y ---help--- - Say Y here to enable inotify support and the /dev/inotify character - device. Inotify is a file change notification system and a + Say Y here to enable inotify support and the associated system + calls. Inotify is a file change notification system and a replacement for dnotify. Inotify fixes numerous shortcomings in dnotify and introduces several new features. It allows monitoring - of both files and directories via a single open fd. Multiple file - events are supported. + of both files and directories via a single open fd. Other features + include multiple file events, one-shot support, and unmount + notification. + + For more information, see Documentation/filesystems/inotify.txt If unsure, say Y. diff --git a/trunk/fs/namei.c b/trunk/fs/namei.c index 4a27eb798118..32accb6a672f 100644 --- a/trunk/fs/namei.c +++ b/trunk/fs/namei.c @@ -1801,8 +1801,8 @@ int vfs_rmdir(struct inode *dir, struct dentry *dentry) } up(&dentry->d_inode->i_sem); if (!error) { - fsnotify_rmdir(dentry, dentry->d_inode, dir); d_delete(dentry); + fsnotify_rmdir(dentry, dentry->d_inode, dir); } dput(dentry); @@ -1874,8 +1874,9 @@ int vfs_unlink(struct inode *dir, struct dentry *dentry) /* We don't d_delete() NFS sillyrenamed files--they still exist. */ if (!error && !(dentry->d_flags & DCACHE_NFSFS_RENAMED)) { - fsnotify_unlink(dentry, dir); + struct inode *inode = dentry->d_inode; d_delete(dentry); + fsnotify_unlink(dentry, inode, dir); } return error; diff --git a/trunk/include/asm-alpha/pci.h b/trunk/include/asm-alpha/pci.h index 28957697e59c..f681e675b823 100644 --- a/trunk/include/asm-alpha/pci.h +++ b/trunk/include/asm-alpha/pci.h @@ -251,6 +251,9 @@ static inline int pci_get_legacy_ide_irq(struct pci_dev *dev, int channel) extern void pcibios_resource_to_bus(struct pci_dev *, struct pci_bus_region *, struct resource *); +extern void pcibios_bus_to_resource(struct pci_dev *dev, struct resource *res, + struct pci_bus_region *region); + #define pci_domain_nr(bus) ((struct pci_controller *)(bus)->sysdata)->index static inline int pci_proc_domain(struct pci_bus *bus) diff --git a/trunk/include/asm-arm/pci.h b/trunk/include/asm-arm/pci.h index b28f1c95dd62..38ea5899a580 100644 --- a/trunk/include/asm-arm/pci.h +++ b/trunk/include/asm-arm/pci.h @@ -60,6 +60,10 @@ extern void pcibios_resource_to_bus(struct pci_dev *dev, struct pci_bus_region *region, struct resource *res); +extern void +pcibios_bus_to_resource(struct pci_dev *dev, struct resource *res, + struct pci_bus_region *region); + static inline void pcibios_add_platform_entries(struct pci_dev *dev) { } diff --git a/trunk/include/asm-generic/pci.h b/trunk/include/asm-generic/pci.h index 9d4cc47bde39..ee1d8b5d8168 100644 --- a/trunk/include/asm-generic/pci.h +++ b/trunk/include/asm-generic/pci.h @@ -22,6 +22,14 @@ pcibios_resource_to_bus(struct pci_dev *dev, struct pci_bus_region *region, region->end = res->end; } +static inline void +pcibios_bus_to_resource(struct pci_dev *dev, struct resource *res, + struct pci_bus_region *region) +{ + res->start = region->start; + res->end = region->end; +} + #define pcibios_scan_all_fns(a, b) 0 #ifndef HAVE_ARCH_PCI_GET_LEGACY_IDE_IRQ diff --git a/trunk/include/asm-parisc/pci.h b/trunk/include/asm-parisc/pci.h index ee741c150176..98d79a3d54fa 100644 --- a/trunk/include/asm-parisc/pci.h +++ b/trunk/include/asm-parisc/pci.h @@ -253,6 +253,10 @@ extern void pcibios_resource_to_bus(struct pci_dev *dev, struct pci_bus_region *region, struct resource *res); +extern void +pcibios_bus_to_resource(struct pci_dev *dev, struct resource *res, + struct pci_bus_region *region); + static inline void pcibios_add_platform_entries(struct pci_dev *dev) { } diff --git a/trunk/include/asm-ppc/pci.h b/trunk/include/asm-ppc/pci.h index a13d55870e62..a811e440c978 100644 --- a/trunk/include/asm-ppc/pci.h +++ b/trunk/include/asm-ppc/pci.h @@ -105,6 +105,10 @@ extern void pcibios_resource_to_bus(struct pci_dev *dev, struct pci_bus_region *region, struct resource *res); +extern void +pcibios_bus_to_resource(struct pci_dev *dev, struct resource *res, + struct pci_bus_region *region); + extern void pcibios_add_platform_entries(struct pci_dev *dev); struct file; diff --git a/trunk/include/asm-ppc64/machdep.h b/trunk/include/asm-ppc64/machdep.h index f0c1d2d92672..f0ef06375947 100644 --- a/trunk/include/asm-ppc64/machdep.h +++ b/trunk/include/asm-ppc64/machdep.h @@ -84,7 +84,7 @@ struct machdep_calls { void (*init_IRQ)(void); int (*get_irq)(struct pt_regs *); - void (*cpu_irq_down)(void); + void (*cpu_irq_down)(int secondary); /* PCI stuff */ void (*pcibios_fixup)(void); diff --git a/trunk/include/asm-ppc64/pci.h b/trunk/include/asm-ppc64/pci.h index faa772223075..4d057452f59b 100644 --- a/trunk/include/asm-ppc64/pci.h +++ b/trunk/include/asm-ppc64/pci.h @@ -134,6 +134,10 @@ extern void pcibios_resource_to_bus(struct pci_dev *dev, struct pci_bus_region *region, struct resource *res); +extern void +pcibios_bus_to_resource(struct pci_dev *dev, struct resource *res, + struct pci_bus_region *region); + extern int unmap_bus_range(struct pci_bus *bus); diff --git a/trunk/include/asm-ppc64/xics.h b/trunk/include/asm-ppc64/xics.h index 0c45e14e26ca..1092af55d707 100644 --- a/trunk/include/asm-ppc64/xics.h +++ b/trunk/include/asm-ppc64/xics.h @@ -17,7 +17,7 @@ void xics_init_IRQ(void); int xics_get_irq(struct pt_regs *); void xics_setup_cpu(void); -void xics_teardown_cpu(void); +void xics_teardown_cpu(int secondary); void xics_cause_IPI(int cpu); void xics_request_IPIs(void); void xics_migrate_irqs_away(void); diff --git a/trunk/include/linux/fsnotify.h b/trunk/include/linux/fsnotify.h index e96a4306ab3b..1cb4935348d8 100644 --- a/trunk/include/linux/fsnotify.h +++ b/trunk/include/linux/fsnotify.h @@ -46,10 +46,8 @@ static inline void fsnotify_move(struct inode *old_dir, struct inode *new_dir, /* * fsnotify_unlink - file was unlinked */ -static inline void fsnotify_unlink(struct dentry *dentry, struct inode *dir) +static inline void fsnotify_unlink(struct dentry *dentry, struct inode *inode, struct inode *dir) { - struct inode *inode = dentry->d_inode; - inode_dir_notify(dir, DN_DELETE); inotify_inode_queue_event(dir, IN_DELETE, 0, dentry->d_name.name); inotify_inode_queue_event(inode, IN_DELETE_SELF, 0, NULL); diff --git a/trunk/include/linux/pci.h b/trunk/include/linux/pci.h index 8621cf42b46f..98bdd95fcee9 100644 --- a/trunk/include/linux/pci.h +++ b/trunk/include/linux/pci.h @@ -225,6 +225,7 @@ #define PCI_PM_CAP_PME_D3cold 0x8000 /* PME# from D3 (cold) */ #define PCI_PM_CTRL 4 /* PM control and status register */ #define PCI_PM_CTRL_STATE_MASK 0x0003 /* Current power state (D0 to D3) */ +#define PCI_PM_CTRL_NO_SOFT_RESET 0x0004 /* No reset for D3hot->D0 */ #define PCI_PM_CTRL_PME_ENABLE 0x0100 /* PME pin enable */ #define PCI_PM_CTRL_DATA_SEL_MASK 0x1e00 /* Data select (??) */ #define PCI_PM_CTRL_DATA_SCALE_MASK 0x6000 /* Data scale (??) */ @@ -816,7 +817,9 @@ int pci_set_mwi(struct pci_dev *dev); void pci_clear_mwi(struct pci_dev *dev); int pci_set_dma_mask(struct pci_dev *dev, u64 mask); int pci_set_consistent_dma_mask(struct pci_dev *dev, u64 mask); +void pci_update_resource(struct pci_dev *dev, struct resource *res, int resno); int pci_assign_resource(struct pci_dev *dev, int i); +void pci_restore_bars(struct pci_dev *dev); /* ROM control related routines */ void __iomem *pci_map_rom(struct pci_dev *pdev, size_t *size); diff --git a/trunk/include/linux/raid/bitmap.h b/trunk/include/linux/raid/bitmap.h index 6213e976eade..4bf1659f8aa8 100644 --- a/trunk/include/linux/raid/bitmap.h +++ b/trunk/include/linux/raid/bitmap.h @@ -248,6 +248,7 @@ struct bitmap { /* these are used only by md/bitmap */ int bitmap_create(mddev_t *mddev); +void bitmap_flush(mddev_t *mddev); void bitmap_destroy(mddev_t *mddev); int bitmap_active(struct bitmap *bitmap); diff --git a/trunk/kernel/exit.c b/trunk/kernel/exit.c index 9d1b10ed0135..5b0fb9f09f21 100644 --- a/trunk/kernel/exit.c +++ b/trunk/kernel/exit.c @@ -829,8 +829,10 @@ fastcall NORET_TYPE void do_exit(long code) acct_update_integrals(tsk); update_mem_hiwater(tsk); group_dead = atomic_dec_and_test(&tsk->signal->live); - if (group_dead) + if (group_dead) { + del_timer_sync(&tsk->signal->real_timer); acct_process(code); + } exit_mm(tsk); exit_sem(tsk); diff --git a/trunk/kernel/posix-timers.c b/trunk/kernel/posix-timers.c index 10b2ad749d14..38798a2ff994 100644 --- a/trunk/kernel/posix-timers.c +++ b/trunk/kernel/posix-timers.c @@ -1166,7 +1166,6 @@ void exit_itimers(struct signal_struct *sig) tmr = list_entry(sig->posix_timers.next, struct k_itimer, list); itimer_delete(tmr); } - del_timer_sync(&sig->real_timer); } /* diff --git a/trunk/kernel/sys.c b/trunk/kernel/sys.c index 000e81ad2c1d..0bcaed6560ac 100644 --- a/trunk/kernel/sys.c +++ b/trunk/kernel/sys.c @@ -404,7 +404,6 @@ void kernel_halt(void) { notifier_call_chain(&reboot_notifier_list, SYS_HALT, NULL); system_state = SYSTEM_HALT; - device_suspend(PMSG_SUSPEND); device_shutdown(); printk(KERN_EMERG "System halted.\n"); machine_halt(); @@ -415,7 +414,6 @@ void kernel_power_off(void) { notifier_call_chain(&reboot_notifier_list, SYS_POWER_OFF, NULL); system_state = SYSTEM_POWER_OFF; - device_suspend(PMSG_SUSPEND); device_shutdown(); printk(KERN_EMERG "Power down.\n"); machine_power_off(); diff --git a/trunk/mm/mmap.c b/trunk/mm/mmap.c index da3fa90a0aae..404319477e71 100644 --- a/trunk/mm/mmap.c +++ b/trunk/mm/mmap.c @@ -143,7 +143,11 @@ int __vm_enough_memory(long pages, int cap_sys_admin) leave 3% of the size of this process for other processes */ allowed -= current->mm->total_vm / 32; - if (atomic_read(&vm_committed_space) < allowed) + /* + * cast `allowed' as a signed long because vm_committed_space + * sometimes has a negative value + */ + if (atomic_read(&vm_committed_space) < (long)allowed) return 0; vm_unacct_memory(pages); diff --git a/trunk/mm/mremap.c b/trunk/mm/mremap.c index ec7238a78f36..fc45dc9a617b 100644 --- a/trunk/mm/mremap.c +++ b/trunk/mm/mremap.c @@ -229,6 +229,7 @@ static unsigned long move_vma(struct vm_area_struct *vma, * since do_munmap() will decrement it by old_len == new_len */ mm->total_vm += new_len >> PAGE_SHIFT; + __vm_stat_account(mm, vma->vm_flags, vma->vm_file, new_len>>PAGE_SHIFT); if (do_munmap(mm, old_addr, old_len) < 0) { /* OOM: unable to split vma, just get accounts right */ @@ -243,7 +244,6 @@ static unsigned long move_vma(struct vm_area_struct *vma, vma->vm_next->vm_flags |= VM_ACCOUNT; } - __vm_stat_account(mm, vma->vm_flags, vma->vm_file, new_len>>PAGE_SHIFT); if (vm_flags & VM_LOCKED) { mm->locked_vm += new_len >> PAGE_SHIFT; if (new_len > old_len) diff --git a/trunk/mm/nommu.c b/trunk/mm/nommu.c index ce74452c02d9..fd4e8df0f02d 100644 --- a/trunk/mm/nommu.c +++ b/trunk/mm/nommu.c @@ -1167,7 +1167,11 @@ int __vm_enough_memory(long pages, int cap_sys_admin) leave 3% of the size of this process for other processes */ allowed -= current->mm->total_vm / 32; - if (atomic_read(&vm_committed_space) < allowed) + /* + * cast `allowed' as a signed long because vm_committed_space + * sometimes has a negative value + */ + if (atomic_read(&vm_committed_space) < (long)allowed) return 0; vm_unacct_memory(pages); diff --git a/trunk/net/ipv4/tcp_output.c b/trunk/net/ipv4/tcp_output.c index e3f8ea1bfa9c..7d076f0db100 100644 --- a/trunk/net/ipv4/tcp_output.c +++ b/trunk/net/ipv4/tcp_output.c @@ -403,11 +403,9 @@ static void tcp_queue_skb(struct sock *sk, struct sk_buff *skb) sk->sk_send_head = skb; } -static void tcp_set_skb_tso_segs(struct sock *sk, struct sk_buff *skb) +static void tcp_set_skb_tso_segs(struct sock *sk, struct sk_buff *skb, unsigned int mss_now) { - struct tcp_sock *tp = tcp_sk(sk); - - if (skb->len <= tp->mss_cache || + if (skb->len <= mss_now || !(sk->sk_route_caps & NETIF_F_TSO)) { /* Avoid the costly divide in the normal * non-TSO case. @@ -417,10 +415,10 @@ static void tcp_set_skb_tso_segs(struct sock *sk, struct sk_buff *skb) } else { unsigned int factor; - factor = skb->len + (tp->mss_cache - 1); - factor /= tp->mss_cache; + factor = skb->len + (mss_now - 1); + factor /= mss_now; skb_shinfo(skb)->tso_segs = factor; - skb_shinfo(skb)->tso_size = tp->mss_cache; + skb_shinfo(skb)->tso_size = mss_now; } } @@ -429,7 +427,7 @@ static void tcp_set_skb_tso_segs(struct sock *sk, struct sk_buff *skb) * packet to the list. This won't be called frequently, I hope. * Remember, these are still headerless SKBs at this point. */ -static int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len) +static int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len, unsigned int mss_now) { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *buff; @@ -492,8 +490,8 @@ static int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len) } /* Fix up tso_factor for both original and new SKB. */ - tcp_set_skb_tso_segs(sk, skb); - tcp_set_skb_tso_segs(sk, buff); + tcp_set_skb_tso_segs(sk, skb, mss_now); + tcp_set_skb_tso_segs(sk, buff, mss_now); if (TCP_SKB_CB(skb)->sacked & TCPCB_LOST) { tp->lost_out += tcp_skb_pcount(skb); @@ -569,7 +567,7 @@ int tcp_trim_head(struct sock *sk, struct sk_buff *skb, u32 len) * factor and mss. */ if (tcp_skb_pcount(skb) > 1) - tcp_set_skb_tso_segs(sk, skb); + tcp_set_skb_tso_segs(sk, skb, tcp_current_mss(sk, 1)); return 0; } @@ -734,12 +732,14 @@ static inline unsigned int tcp_cwnd_test(struct tcp_sock *tp, struct sk_buff *sk /* This must be invoked the first time we consider transmitting * SKB onto the wire. */ -static inline int tcp_init_tso_segs(struct sock *sk, struct sk_buff *skb) +static inline int tcp_init_tso_segs(struct sock *sk, struct sk_buff *skb, unsigned int mss_now) { int tso_segs = tcp_skb_pcount(skb); - if (!tso_segs) { - tcp_set_skb_tso_segs(sk, skb); + if (!tso_segs || + (tso_segs > 1 && + skb_shinfo(skb)->tso_size != mss_now)) { + tcp_set_skb_tso_segs(sk, skb, mss_now); tso_segs = tcp_skb_pcount(skb); } return tso_segs; @@ -817,7 +817,7 @@ static unsigned int tcp_snd_test(struct sock *sk, struct sk_buff *skb, struct tcp_sock *tp = tcp_sk(sk); unsigned int cwnd_quota; - tcp_init_tso_segs(sk, skb); + tcp_init_tso_segs(sk, skb, cur_mss); if (!tcp_nagle_test(tp, skb, cur_mss, nonagle)) return 0; @@ -854,7 +854,7 @@ int tcp_may_send_now(struct sock *sk, struct tcp_sock *tp) * know that all the data is in scatter-gather pages, and that the * packet has never been sent out before (and thus is not cloned). */ -static int tso_fragment(struct sock *sk, struct sk_buff *skb, unsigned int len) +static int tso_fragment(struct sock *sk, struct sk_buff *skb, unsigned int len, unsigned int mss_now) { struct sk_buff *buff; int nlen = skb->len - len; @@ -887,8 +887,8 @@ static int tso_fragment(struct sock *sk, struct sk_buff *skb, unsigned int len) skb_split(skb, buff, len); /* Fix up tso_factor for both original and new SKB. */ - tcp_set_skb_tso_segs(sk, skb); - tcp_set_skb_tso_segs(sk, buff); + tcp_set_skb_tso_segs(sk, skb, mss_now); + tcp_set_skb_tso_segs(sk, buff, mss_now); /* Link BUFF into the send queue. */ skb_header_release(buff); @@ -972,19 +972,18 @@ static int tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle) if (unlikely(sk->sk_state == TCP_CLOSE)) return 0; - skb = sk->sk_send_head; - if (unlikely(!skb)) - return 0; - - tso_segs = tcp_init_tso_segs(sk, skb); - cwnd_quota = tcp_cwnd_test(tp, skb); - if (unlikely(!cwnd_quota)) - goto out; - sent_pkts = 0; - while (likely(tcp_snd_wnd_test(tp, skb, mss_now))) { + while ((skb = sk->sk_send_head)) { + tso_segs = tcp_init_tso_segs(sk, skb, mss_now); BUG_ON(!tso_segs); + cwnd_quota = tcp_cwnd_test(tp, skb); + if (!cwnd_quota) + break; + + if (unlikely(!tcp_snd_wnd_test(tp, skb, mss_now))) + break; + if (tso_segs == 1) { if (unlikely(!tcp_nagle_test(tp, skb, mss_now, (tcp_skb_is_last(sk, skb) ? @@ -1006,11 +1005,11 @@ static int tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle) limit = skb->len - trim; } if (skb->len > limit) { - if (tso_fragment(sk, skb, limit)) + if (tso_fragment(sk, skb, limit, mss_now)) break; } } else if (unlikely(skb->len > mss_now)) { - if (unlikely(tcp_fragment(sk, skb, mss_now))) + if (unlikely(tcp_fragment(sk, skb, mss_now, mss_now))) break; } @@ -1026,27 +1025,12 @@ static int tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle) tcp_minshall_update(tp, mss_now, skb); sent_pkts++; - - /* Do not optimize this to use tso_segs. If we chopped up - * the packet above, tso_segs will no longer be valid. - */ - cwnd_quota -= tcp_skb_pcount(skb); - - BUG_ON(cwnd_quota < 0); - if (!cwnd_quota) - break; - - skb = sk->sk_send_head; - if (!skb) - break; - tso_segs = tcp_init_tso_segs(sk, skb); } if (likely(sent_pkts)) { tcp_cwnd_validate(sk, tp); return 0; } -out: return !tp->packets_out && sk->sk_send_head; } @@ -1076,7 +1060,7 @@ void tcp_push_one(struct sock *sk, unsigned int mss_now) BUG_ON(!skb || skb->len < mss_now); - tso_segs = tcp_init_tso_segs(sk, skb); + tso_segs = tcp_init_tso_segs(sk, skb, mss_now); cwnd_quota = tcp_snd_test(sk, skb, mss_now, TCP_NAGLE_PUSH); if (likely(cwnd_quota)) { @@ -1093,11 +1077,11 @@ void tcp_push_one(struct sock *sk, unsigned int mss_now) limit = skb->len - trim; } if (skb->len > limit) { - if (unlikely(tso_fragment(sk, skb, limit))) + if (unlikely(tso_fragment(sk, skb, limit, mss_now))) return; } } else if (unlikely(skb->len > mss_now)) { - if (unlikely(tcp_fragment(sk, skb, mss_now))) + if (unlikely(tcp_fragment(sk, skb, mss_now, mss_now))) return; } @@ -1388,7 +1372,7 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb) int old_factor = tcp_skb_pcount(skb); int new_factor; - if (tcp_fragment(sk, skb, cur_mss)) + if (tcp_fragment(sk, skb, cur_mss, cur_mss)) return -ENOMEM; /* We'll try again later. */ /* New SKB created, account for it. */ @@ -1991,7 +1975,7 @@ int tcp_write_wakeup(struct sock *sk) skb->len > mss) { seg_size = min(seg_size, mss); TCP_SKB_CB(skb)->flags |= TCPCB_FLAG_PSH; - if (tcp_fragment(sk, skb, seg_size)) + if (tcp_fragment(sk, skb, seg_size, mss)) return -1; /* SWS override triggered forced fragmentation. * Disable TSO, the connection is too sick. */ @@ -2000,7 +1984,7 @@ int tcp_write_wakeup(struct sock *sk) sk->sk_route_caps &= ~NETIF_F_TSO; } } else if (!tcp_skb_pcount(skb)) - tcp_set_skb_tso_segs(sk, skb); + tcp_set_skb_tso_segs(sk, skb, mss); TCP_SKB_CB(skb)->flags |= TCPCB_FLAG_PSH; TCP_SKB_CB(skb)->when = tcp_time_stamp; diff --git a/trunk/security/keys/keyctl.c b/trunk/security/keys/keyctl.c index fea262860ea0..a6516a64b297 100644 --- a/trunk/security/keys/keyctl.c +++ b/trunk/security/keys/keyctl.c @@ -49,9 +49,6 @@ asmlinkage long sys_add_key(const char __user *_type, goto error; type[31] = '\0'; - if (!type[0]) - goto error; - ret = -EPERM; if (type[0] == '.') goto error; @@ -144,6 +141,10 @@ asmlinkage long sys_request_key(const char __user *_type, goto error; type[31] = '\0'; + ret = -EPERM; + if (type[0] == '.') + goto error; + /* pull the description into kernel space */ ret = -EFAULT; dlen = strnlen_user(_description, PAGE_SIZE - 1); @@ -362,7 +363,7 @@ long keyctl_revoke_key(key_serial_t id) key_put(key); error: - return 0; + return ret; } /* end keyctl_revoke_key() */ @@ -685,6 +686,8 @@ long keyctl_read_key(key_serial_t keyid, char __user *buffer, size_t buflen) goto can_read_key2; ret = PTR_ERR(skey); + if (ret == -EAGAIN) + ret = -EACCES; goto error2; } diff --git a/trunk/security/keys/keyring.c b/trunk/security/keys/keyring.c index a1f6bac647a1..9c208c756df8 100644 --- a/trunk/security/keys/keyring.c +++ b/trunk/security/keys/keyring.c @@ -201,7 +201,11 @@ static void keyring_destroy(struct key *keyring) if (keyring->description) { write_lock(&keyring_name_lock); - list_del(&keyring->type_data.link); + + if (keyring->type_data.link.next != NULL && + !list_empty(&keyring->type_data.link)) + list_del(&keyring->type_data.link); + write_unlock(&keyring_name_lock); } diff --git a/trunk/security/keys/process_keys.c b/trunk/security/keys/process_keys.c index 9b0369c5a223..c089f78fb94e 100644 --- a/trunk/security/keys/process_keys.c +++ b/trunk/security/keys/process_keys.c @@ -678,7 +678,7 @@ long join_session_keyring(const char *name) keyring = keyring_alloc(name, tsk->uid, tsk->gid, 0, NULL); if (IS_ERR(keyring)) { ret = PTR_ERR(keyring); - goto error; + goto error2; } } else if (IS_ERR(keyring)) { diff --git a/trunk/security/keys/request_key.c b/trunk/security/keys/request_key.c index dfcd983af1fd..90c1506d007c 100644 --- a/trunk/security/keys/request_key.c +++ b/trunk/security/keys/request_key.c @@ -405,7 +405,7 @@ struct key *request_key_and_link(struct key_type *type, key_user_put(user); /* link the new key into the appropriate keyring */ - if (!PTR_ERR(key)) + if (!IS_ERR(key)) request_key_link(key, dest_keyring); }