Index: linux-rt-rebase.q/Documentation/block/barrier.txt =================================================================== --- linux-rt-rebase.q.orig/Documentation/block/barrier.txt +++ linux-rt-rebase.q/Documentation/block/barrier.txt @@ -79,9 +79,9 @@ and how to prepare flush requests. Note used to indicate the whole sequence of performing barrier requests including draining and flushing. -typedef void (prepare_flush_fn)(request_queue_t *q, struct request *rq); +typedef void (prepare_flush_fn)(struct request_queue *q, struct request *rq); -int blk_queue_ordered(request_queue_t *q, unsigned ordered, +int blk_queue_ordered(struct request_queue *q, unsigned ordered, prepare_flush_fn *prepare_flush_fn); @q : the queue in question @@ -92,7 +92,7 @@ int blk_queue_ordered(request_queue_t *q For example, SCSI disk driver's prepare_flush_fn looks like the following. -static void sd_prepare_flush(request_queue_t *q, struct request *rq) +static void sd_prepare_flush(struct request_queue *q, struct request *rq) { memset(rq->cmd, 0, sizeof(rq->cmd)); rq->cmd_type = REQ_TYPE_BLOCK_PC; Index: linux-rt-rebase.q/Documentation/block/biodoc.txt =================================================================== --- linux-rt-rebase.q.orig/Documentation/block/biodoc.txt +++ linux-rt-rebase.q/Documentation/block/biodoc.txt @@ -740,12 +740,12 @@ Block now offers some simple generic fun queueing (typically known as tagged command queueing), ie manage more than one outstanding command on a queue at any given time. - blk_queue_init_tags(request_queue_t *q, int depth) + blk_queue_init_tags(struct request_queue *q, int depth) Initialize internal command tagging structures for a maximum depth of 'depth'. - blk_queue_free_tags((request_queue_t *q) + blk_queue_free_tags((struct request_queue *q) Teardown tag info associated with the queue. This will be done automatically by block if blk_queue_cleanup() is called on a queue @@ -754,7 +754,7 @@ one outstanding command on a queue at an The above are initialization and exit management, the main helpers during normal operations are: - blk_queue_start_tag(request_queue_t *q, struct request *rq) + blk_queue_start_tag(struct request_queue *q, struct request *rq) Start tagged operation for this request. A free tag number between 0 and 'depth' is assigned to the request (rq->tag holds this number), @@ -762,7 +762,7 @@ normal operations are: for this queue is already achieved (or if the tag wasn't started for some other reason), 1 is returned. Otherwise 0 is returned. - blk_queue_end_tag(request_queue_t *q, struct request *rq) + blk_queue_end_tag(struct request_queue *q, struct request *rq) End tagged operation on this request. 'rq' is removed from the internal book keeping structures. @@ -781,7 +781,7 @@ queue. For instance, on IDE any tagged r the hardware and software block queue and enable the driver to sanely restart all the outstanding requests. There's a third helper to do that: - blk_queue_invalidate_tags(request_queue_t *q) + blk_queue_invalidate_tags(struct request_queue *q) Clear the internal block tag queue and re-add all the pending requests to the request queue. The driver will receive them again on the Index: linux-rt-rebase.q/Documentation/block/request.txt =================================================================== --- linux-rt-rebase.q.orig/Documentation/block/request.txt +++ linux-rt-rebase.q/Documentation/block/request.txt @@ -83,6 +83,6 @@ struct bio *bio DBI First bio in reque struct bio *biotail DBI Last bio in request -request_queue_t *q DB Request queue this request belongs to +struct request_queue *q DB Request queue this request belongs to struct request_list *rl B Request list this request came from Index: linux-rt-rebase.q/Documentation/cpuidle/core.txt =================================================================== --- /dev/null +++ linux-rt-rebase.q/Documentation/cpuidle/core.txt @@ -0,0 +1,17 @@ + + Supporting multiple CPU idle levels in kernel + + cpuidle + +General Information: + +Various CPUs today support multiple idle levels that are differentiated +by varying exit latencies and power consumption during idle. +cpuidle is a generic in-kernel infrastructure that separates +idle policy (governor) from idle mechanism (driver) and provides a +standardized infrastructure to support independent development of +governors and drivers. + +cpuidle resides under drivers/cpuidle. + + Index: linux-rt-rebase.q/Documentation/cpuidle/driver.txt =================================================================== --- /dev/null +++ linux-rt-rebase.q/Documentation/cpuidle/driver.txt @@ -0,0 +1,29 @@ + + + Supporting multiple CPU idle levels in kernel + + cpuidle drivers + + + + +cpuidle driver hooks into the cpuidle infrastructure and does the +architecture/platform dependent part of CPU idle states. Driver +provides the platform idle state detection capability and also +has mechanisms in place to support actusl entry-exit into a CPU idle state. + +cpuidle driver supports capability detection for a platform using the +init and exit routines. They will be called for each online CPU, with a +percpu cpuidle_driver object and driver should fill in cpuidle_states +inside cpuidle_driver depending on the CPU capability. + +Driver can handle dynamic state changes (like battery<->AC), by calling +force_redetect interface. + +It is possible to have more than one driver registered at the same time and +user can switch between drivers using /sysfs interface (when enabled). + +Interfaces: +int cpuidle_register_driver(struct cpuidle_driver *drv); +void cpuidle_unregister_driver(struct cpuidle_driver *drv); +int cpuidle_force_redetect(struct cpuidle_device *dev); Index: linux-rt-rebase.q/Documentation/cpuidle/governor.txt =================================================================== --- /dev/null +++ linux-rt-rebase.q/Documentation/cpuidle/governor.txt @@ -0,0 +1,28 @@ + + + + Supporting multiple CPU idle levels in kernel + + cpuidle governors + + + + +cpuidle governor is policy routine that decides what idle state to enter at +any given time. cpuidle core uses different callbacks to governor while +handling idle entry. +* select_state() callback where governor can determine next idle state to enter +* prepare_idle() callback is called before entering an idle state +* scan() callback is called after a driver forces redetection of the states + +More than one governor can be registered at the same time and +user can switch between drivers using /sysfs interface (when supported). + +More than one governor part is supported for developers to easily experiment +with different governors. By default, most optimal governor based on your +kernel configuration and platform will be selected by cpuidle. + +Interfaces: +int cpuidle_register_governor(struct cpuidle_governor *gov); +void cpuidle_unregister_governor(struct cpuidle_governor *gov); + Index: linux-rt-rebase.q/Documentation/cpuidle/sysfs.txt =================================================================== --- /dev/null +++ linux-rt-rebase.q/Documentation/cpuidle/sysfs.txt @@ -0,0 +1,35 @@ + + + Supporting multiple CPU idle levels in kernel + + cpuidle sysfs + +System global cpuidle related information and tunables are under +/sys/devices/system/cpu/cpuidle + +The current interfaces in this directory has self-explanatory names: +* current_driver_ro +* current_governor_ro + +With cpuidle_sysfs_switch boot option (meant for developer testing) +following objects are visible instead. +* available_drivers +* available_governors +* current_driver +* current_governor +In this case user can switch the driver, governor at run time by writing +onto current_driver and current_governor. + + +Per logical CPU specific cpuidle information are under +/sys/devices/system/cpu/cpuX/cpuidle +for each online cpu X + +Under this percpu directory, there is a directory for each idle state supported +by the driver, which in turn has +* latency : Latency to exit out of this idle state (in microseconds) +* power : Power consumed while in this idle state (in milliwatts) +* time : Total time spent in this idle state (in microseconds) +* usage : Number of times this state was entered (count) + + Index: linux-rt-rebase.q/Documentation/gpio.txt =================================================================== --- linux-rt-rebase.q.orig/Documentation/gpio.txt +++ linux-rt-rebase.q/Documentation/gpio.txt @@ -148,7 +148,7 @@ pin ... that won't always match the spec issues including wire-OR and output latencies. The get/set calls have no error returns because "invalid GPIO" should have -been reported earlier in gpio_set_direction(). However, note that not all +been reported earlier from gpio_direction_*(). However, note that not all platforms can read the value of output pins; those that can't should always return zero. Also, using these calls for GPIOs that can't safely be accessed without sleeping (see below) is an error. @@ -239,7 +239,7 @@ map between them using calls like: Those return either the corresponding number in the other namespace, or else a negative errno code if the mapping can't be done. (For example, some GPIOs can't used as IRQs.) It is an unchecked error to use a GPIO -number that hasn't been marked as an input using gpio_set_direction(), or +number that wasn't set up as an input using gpio_direction_input(), or to use an IRQ number that didn't originally come from gpio_to_irq(). These two mapping calls are expected to cost on the order of a single Index: linux-rt-rebase.q/Documentation/iostats.txt =================================================================== --- linux-rt-rebase.q.orig/Documentation/iostats.txt +++ linux-rt-rebase.q/Documentation/iostats.txt @@ -79,7 +79,7 @@ Field 8 -- # of milliseconds spent writ measured from __make_request() to end_that_request_last()). Field 9 -- # of I/Os currently in progress The only field that should go to zero. Incremented as requests are - given to appropriate request_queue_t and decremented as they finish. + given to appropriate struct request_queue and decremented as they finish. Field 10 -- # of milliseconds spent doing I/Os This field is increases so long as field 9 is nonzero. Field 11 -- weighted # of milliseconds spent doing I/Os Index: linux-rt-rebase.q/Documentation/lguest/Makefile =================================================================== --- linux-rt-rebase.q.orig/Documentation/lguest/Makefile +++ linux-rt-rebase.q/Documentation/lguest/Makefile @@ -11,8 +11,7 @@ endif include $(KBUILD_OUTPUT)/.config LGUEST_GUEST_TOP := ($(CONFIG_PAGE_OFFSET) - 0x08000000) -CFLAGS:=-Wall -Wmissing-declarations -Wmissing-prototypes -O3 \ - -static -DLGUEST_GUEST_TOP="$(LGUEST_GUEST_TOP)" -Wl,-T,lguest.lds +CFLAGS:=-Wall -Wmissing-declarations -Wmissing-prototypes -O3 -Wl,-T,lguest.lds LDLIBS:=-lz all: lguest.lds lguest Index: linux-rt-rebase.q/Documentation/lguest/lguest.c =================================================================== --- linux-rt-rebase.q.orig/Documentation/lguest/lguest.c +++ linux-rt-rebase.q/Documentation/lguest/lguest.c @@ -47,12 +47,14 @@ static bool verbose; #define verbose(args...) \ do { if (verbose) printf(args); } while(0) static int waker_fd; +static u32 top; struct device_list { fd_set infds; int max_infd; + struct lguest_device_desc *descs; struct device *dev; struct device **lastdev; }; @@ -324,8 +326,7 @@ static void concat(char *dst, char *args static int tell_kernel(u32 pgdir, u32 start, u32 page_offset) { u32 args[] = { LHREQ_INITIALIZE, - LGUEST_GUEST_TOP/getpagesize(), /* Just below us */ - pgdir, start, page_offset }; + top/getpagesize(), pgdir, start, page_offset }; int fd; fd = open_or_die("/dev/lguest", O_RDWR); @@ -382,7 +383,7 @@ static int setup_waker(int lguest_fd, st static void *_check_pointer(unsigned long addr, unsigned int size, unsigned int line) { - if (addr >= LGUEST_GUEST_TOP || addr + size >= LGUEST_GUEST_TOP) + if (addr >= top || addr + size >= top) errx(1, "%s:%i: Invalid address %li", __FILE__, line, addr); return (void *)addr; } @@ -629,24 +630,26 @@ static void handle_input(int fd, struct } } -static struct lguest_device_desc *new_dev_desc(u16 type, u16 features, - u16 num_pages) +static struct lguest_device_desc * +new_dev_desc(struct lguest_device_desc *descs, + u16 type, u16 features, u16 num_pages) { - static unsigned long top = LGUEST_GUEST_TOP; - struct lguest_device_desc *desc; + unsigned int i; - desc = malloc(sizeof(*desc)); - desc->type = type; - desc->num_pages = num_pages; - desc->features = features; - desc->status = 0; - if (num_pages) { - top -= num_pages*getpagesize(); - map_zeroed_pages(top, num_pages); - desc->pfn = top / getpagesize(); - } else - desc->pfn = 0; - return desc; + for (i = 0; i < LGUEST_MAX_DEVICES; i++) { + if (!descs[i].type) { + descs[i].type = type; + descs[i].features = features; + descs[i].num_pages = num_pages; + if (num_pages) { + map_zeroed_pages(top, num_pages); + descs[i].pfn = top/getpagesize(); + top += num_pages*getpagesize(); + } + return &descs[i]; + } + } + errx(1, "too many devices"); } static struct device *new_device(struct device_list *devices, @@ -669,7 +672,7 @@ static struct device *new_device(struct dev->fd = fd; if (handle_input) set_fd(dev->fd, devices); - dev->desc = new_dev_desc(type, features, num_pages); + dev->desc = new_dev_desc(devices->descs, type, features, num_pages); dev->mem = (void *)(dev->desc->pfn * getpagesize()); dev->handle_input = handle_input; dev->watch_key = (unsigned long)dev->mem + watch_off; @@ -866,30 +869,6 @@ static void setup_tun_net(const char *ar verbose("attached to bridge: %s\n", br_name); } -/* Now we know how much memory we have, we copy in device descriptors */ -static void map_device_descriptors(struct device_list *devs, unsigned long mem) -{ - struct device *i; - unsigned int num; - struct lguest_device_desc *descs; - - /* Device descriptor array sits just above top of normal memory */ - descs = map_zeroed_pages(mem, 1); - - for (i = devs->dev, num = 0; i; i = i->next, num++) { - if (num == LGUEST_MAX_DEVICES) - errx(1, "too many devices"); - verbose("Device %i: %s\n", num, - i->desc->type == LGUEST_DEVICE_T_NET ? "net" - : i->desc->type == LGUEST_DEVICE_T_CONSOLE ? "console" - : i->desc->type == LGUEST_DEVICE_T_BLOCK ? "block" - : "unknown"); - descs[num] = *i->desc; - free(i->desc); - i->desc = &descs[num]; - } -} - static void __attribute__((noreturn)) run_guest(int lguest_fd, struct device_list *device_list) { @@ -934,8 +913,8 @@ static void usage(void) int main(int argc, char *argv[]) { - unsigned long mem, pgdir, start, page_offset, initrd_size = 0; - int c, lguest_fd; + unsigned long mem = 0, pgdir, start, page_offset, initrd_size = 0; + int i, c, lguest_fd; struct device_list device_list; void *boot = (void *)0; const char *initrd_name = NULL; @@ -945,6 +924,15 @@ int main(int argc, char *argv[]) device_list.lastdev = &device_list.dev; FD_ZERO(&device_list.infds); + /* We need to know how much memory so we can allocate devices. */ + for (i = 1; i < argc; i++) { + if (argv[i][0] != '-') { + mem = top = atoi(argv[i]) * 1024 * 1024; + device_list.descs = map_zeroed_pages(top, 1); + top += getpagesize(); + break; + } + } while ((c = getopt_long(argc, argv, "v", opts, NULL)) != EOF) { switch (c) { case 'v': @@ -974,16 +962,12 @@ int main(int argc, char *argv[]) setup_console(&device_list); /* First we map /dev/zero over all of guest-physical memory. */ - mem = atoi(argv[optind]) * 1024 * 1024; map_zeroed_pages(0, mem / getpagesize()); /* Now we load the kernel */ start = load_kernel(open_or_die(argv[optind+1], O_RDONLY), &page_offset); - /* Write the device descriptors into memory. */ - map_device_descriptors(&device_list, mem); - /* Map the initrd image if requested */ if (initrd_name) { initrd_size = load_initrd(initrd_name, mem); Index: linux-rt-rebase.q/Documentation/stable_api_nonsense.txt =================================================================== --- linux-rt-rebase.q.orig/Documentation/stable_api_nonsense.txt +++ linux-rt-rebase.q/Documentation/stable_api_nonsense.txt @@ -62,6 +62,9 @@ consider the following facts about the L - different structures can contain different fields - Some functions may not be implemented at all, (i.e. some locks compile away to nothing for non-SMP builds.) + - Parameter passing of variables from function to function can be + done in different ways (the CONFIG_REGPARM option controls + this.) - Memory within the kernel can be aligned in different ways, depending on the build options. - Linux runs on a wide range of different processor architectures. Index: linux-rt-rebase.q/Makefile =================================================================== --- linux-rt-rebase.q.orig/Makefile +++ linux-rt-rebase.q/Makefile @@ -1,7 +1,7 @@ VERSION = 2 PATCHLEVEL = 6 SUBLEVEL = 23 -EXTRAVERSION =-rc1 +EXTRAVERSION =-rc1-rt6 NAME = Holy Dancing Manatees, Batman! # *DOCUMENTATION* @@ -299,7 +299,7 @@ CHECKFLAGS := -D__linux__ -Dlinux -D MODFLAGS = -DMODULE CFLAGS_MODULE = $(MODFLAGS) AFLAGS_MODULE = $(MODFLAGS) -LDFLAGS_MODULE = -r +LDFLAGS_MODULE = CFLAGS_KERNEL = AFLAGS_KERNEL = @@ -491,10 +491,15 @@ endif include $(srctree)/arch/$(ARCH)/Makefile -ifdef CONFIG_FRAME_POINTER -CFLAGS += -fno-omit-frame-pointer -fno-optimize-sibling-calls + +ifdef CONFIG_MCOUNT +CFLAGS += -pg -fno-omit-frame-pointer -fno-optimize-sibling-calls else -CFLAGS += -fomit-frame-pointer + ifdef CONFIG_FRAME_POINTER + CFLAGS += -fno-omit-frame-pointer -fno-optimize-sibling-calls + else + CFLAGS += -fomit-frame-pointer + endif endif ifdef CONFIG_DEBUG_INFO Index: linux-rt-rebase.q/arch/arm/Kconfig =================================================================== --- linux-rt-rebase.q.orig/arch/arm/Kconfig +++ linux-rt-rebase.q/arch/arm/Kconfig @@ -33,6 +33,10 @@ config GENERIC_CLOCKEVENTS bool default n +config STACKTRACE_SUPPORT + bool + default y + config MMU bool default y @@ -608,18 +612,7 @@ config LOCAL_TIMERS accounting to be spread across the timer interval, preventing a "thundering herd" at every timer tick. -config PREEMPT - bool "Preemptible Kernel (EXPERIMENTAL)" - depends on EXPERIMENTAL - help - This option reduces the latency of the kernel when reacting to - real-time or interactive events by allowing a low priority process to - be preempted even if it is in kernel mode executing a system call. - This allows applications to run more reliably even when the system is - under load. - - Say Y here if you are building a kernel for a desktop, embedded - or real-time system. Say N if you are unsure. +source kernel/Kconfig.preempt config NO_IDLE_HZ bool "Dynamic tick timer" Index: linux-rt-rebase.q/arch/arm/boot/compressed/head.S =================================================================== --- linux-rt-rebase.q.orig/arch/arm/boot/compressed/head.S +++ linux-rt-rebase.q/arch/arm/boot/compressed/head.S @@ -928,6 +928,19 @@ memdump: mov r12, r0 #endif .ltorg +#ifdef CONFIG_MCOUNT +/* CONFIG_MCOUNT causes boot header to be built with -pg requiring this + * trampoline + */ + .text + .align 0 + .type mcount %function + .global mcount +mcount: + mov pc, lr @ just return +#endif + + reloc_end: .align Index: linux-rt-rebase.q/arch/arm/common/time-acorn.c =================================================================== --- linux-rt-rebase.q.orig/arch/arm/common/time-acorn.c +++ linux-rt-rebase.q/arch/arm/common/time-acorn.c @@ -77,7 +77,7 @@ ioc_timer_interrupt(int irq, void *dev_i static struct irqaction ioc_timer_irq = { .name = "timer", - .flags = IRQF_DISABLED, + .flags = IRQF_DISABLED | IRQF_NODELAY, .handler = ioc_timer_interrupt }; Index: linux-rt-rebase.q/arch/arm/kernel/dma.c =================================================================== --- linux-rt-rebase.q.orig/arch/arm/kernel/dma.c +++ linux-rt-rebase.q/arch/arm/kernel/dma.c @@ -20,7 +20,7 @@ #include -DEFINE_SPINLOCK(dma_spin_lock); +DEFINE_RAW_SPINLOCK(dma_spin_lock); EXPORT_SYMBOL(dma_spin_lock); static dma_t dma_chan[MAX_DMA_CHANNELS]; Index: linux-rt-rebase.q/arch/arm/kernel/entry-armv.S =================================================================== --- linux-rt-rebase.q.orig/arch/arm/kernel/entry-armv.S +++ linux-rt-rebase.q/arch/arm/kernel/entry-armv.S @@ -204,7 +204,7 @@ __irq_svc: irq_handler #ifdef CONFIG_PREEMPT ldr r0, [tsk, #TI_FLAGS] @ get flags - tst r0, #_TIF_NEED_RESCHED + tst r0, #_TIF_NEED_RESCHED | _TIF_NEED_RESCHED_DELAYED blne svc_preempt preempt_return: ldr r0, [tsk, #TI_PREEMPT] @ read preempt value @@ -235,7 +235,7 @@ svc_preempt: str r7, [tsk, #TI_PREEMPT] @ expects preempt_count == 0 1: bl preempt_schedule_irq @ irq en/disable is done inside ldr r0, [tsk, #TI_FLAGS] @ get new tasks TI_FLAGS - tst r0, #_TIF_NEED_RESCHED + tst r0, #_TIF_NEED_RESCHED | _TIF_NEED_RESCHED_DELAYED beq preempt_return @ go again b 1b #endif Index: linux-rt-rebase.q/arch/arm/kernel/entry-common.S =================================================================== --- linux-rt-rebase.q.orig/arch/arm/kernel/entry-common.S +++ linux-rt-rebase.q/arch/arm/kernel/entry-common.S @@ -3,6 +3,8 @@ * * Copyright (C) 2000 Russell King * + * FUNCTION_TRACE/mcount support (C) 2005 Timesys john.cooper@timesys.com + * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as * published by the Free Software Foundation. @@ -44,7 +46,7 @@ ret_fast_syscall: fast_work_pending: str r0, [sp, #S_R0+S_OFF]! @ returned r0 work_pending: - tst r1, #_TIF_NEED_RESCHED + tst r1, #_TIF_NEED_RESCHED | _TIF_NEED_RESCHED_DELAYED bne work_resched tst r1, #_TIF_NOTIFY_RESUME | _TIF_SIGPENDING beq no_work_pending @@ -54,7 +56,8 @@ work_pending: b ret_slow_syscall @ Check work again work_resched: - bl schedule + bl __schedule + /* * "slow" syscall return path. "why" tells us if this was a real syscall. */ @@ -394,6 +397,112 @@ ENTRY(sys_oabi_call_table) #include "calls.S" #undef ABI #undef OBSOLETE +#endif + +#ifdef CONFIG_FRAME_POINTER + +#ifdef CONFIG_MCOUNT +/* + * At the point where we are in mcount() we maintain the + * frame of the prologue code and keep the call to mcount() + * out of the stack frame list: + + saved pc <---\ caller of instrumented routine + saved lr | + ip/prev_sp | + fp -----^ | + : | + | + -> saved pc | instrumented routine + | saved lr | + | ip/prev_sp | + | fp ---------/ + | : + | + | mcount + | saved pc + | saved lr + | ip/prev sp + -- fp + r3 + r2 + r1 + sp-> r0 + : + */ + + .text + .align 0 + .type mcount %function + .global mcount + +/* gcc -pg generated FUNCTION_PROLOGUE references mcount() + * and has already created the stack frame invocation for + * the routine we have been called to instrument. We create + * a complete frame nevertheless, as we want to use the same + * call to mcount() from c code. + */ +mcount: + + ldr ip, =mcount_enabled @ leave early, if disabled + ldr ip, [ip] + cmp ip, #0 + moveq pc, lr + + mov ip, sp + stmdb sp!, {r0 - r3, fp, ip, lr, pc} @ create stack frame + + ldr r1, [fp, #-4] @ get lr (the return address + @ of the caller of the + @ instrumented function) + mov r0, lr @ get lr - (the return address + @ of the instrumented function) + + sub fp, ip, #4 @ point fp at this frame + + bl __trace +1: + ldmdb fp, {r0 - r3, fp, sp, pc} @ pop entry frame and return + +#endif + +/* ARM replacement for unsupported gcc __builtin_return_address(n) + * where 0 < n. n == 0 is supported here as well. + * + * Walk up the stack frame until the desired frame is found or a NULL + * fp is encountered, return NULL in the latter case. + * + * Note: it is possible under code optimization for the stack invocation + * of an ancestor function (level N) to be removed before calling a + * descendant function (level N+1). No easy means is available to deduce + * this scenario with the result being [for example] caller_addr(0) when + * called from level N+1 returning level N-1 rather than the expected + * level N. This optimization issue appears isolated to the case of + * a call to a level N+1 routine made at the tail end of a level N + * routine -- the level N frame is deleted and a simple branch is made + * to the level N+1 routine. + */ + + .text + .align 0 + .type arm_return_addr %function + .global arm_return_addr + +arm_return_addr: + mov ip, r0 + mov r0, fp +3: + cmp r0, #0 + beq 1f @ frame list hit end, bail + cmp ip, #0 + beq 2f @ reached desired frame + ldr r0, [r0, #-12] @ else continue, get next fp + sub ip, ip, #1 + b 3b +2: + ldr r0, [r0, #-4] @ get target return address +1: + mov pc, lr #endif Index: linux-rt-rebase.q/arch/arm/kernel/fiq.c =================================================================== --- linux-rt-rebase.q.orig/arch/arm/kernel/fiq.c +++ linux-rt-rebase.q/arch/arm/kernel/fiq.c @@ -89,7 +89,7 @@ void set_fiq_handler(void *start, unsign * disable irqs for the duration. Note - these functions are almost * entirely coded in assembly. */ -void __attribute__((naked)) set_fiq_regs(struct pt_regs *regs) +void notrace __attribute__((naked)) set_fiq_regs(struct pt_regs *regs) { register unsigned long tmp; asm volatile ( @@ -107,7 +107,7 @@ void __attribute__((naked)) set_fiq_regs : "r" (®s->ARM_r8), "I" (PSR_I_BIT | PSR_F_BIT | FIQ_MODE)); } -void __attribute__((naked)) get_fiq_regs(struct pt_regs *regs) +void notrace __attribute__((naked)) get_fiq_regs(struct pt_regs *regs) { register unsigned long tmp; asm volatile ( Index: linux-rt-rebase.q/arch/arm/kernel/irq.c =================================================================== --- linux-rt-rebase.q.orig/arch/arm/kernel/irq.c +++ linux-rt-rebase.q/arch/arm/kernel/irq.c @@ -100,7 +100,7 @@ unlock: /* Handle bad interrupts */ static struct irq_desc bad_irq_desc = { .handle_irq = handle_bad_irq, - .lock = SPIN_LOCK_UNLOCKED + .lock = RAW_SPIN_LOCK_UNLOCKED(bad_irq_desc.lock) }; /* @@ -108,11 +108,13 @@ static struct irq_desc bad_irq_desc = { * come via this function. Instead, they should provide their * own 'handler' */ -asmlinkage void __exception asm_do_IRQ(unsigned int irq, struct pt_regs *regs) +asmlinkage void __exception notrace asm_do_IRQ(unsigned int irq, struct pt_regs *regs) { struct pt_regs *old_regs = set_irq_regs(regs); struct irq_desc *desc = irq_desc + irq; + trace_special(instruction_pointer(regs), irq, 0); + /* * Some hardware gives randomly wrong interrupts. Rather * than crashing, do something sensible. Index: linux-rt-rebase.q/arch/arm/kernel/process.c =================================================================== --- linux-rt-rebase.q.orig/arch/arm/kernel/process.c +++ linux-rt-rebase.q/arch/arm/kernel/process.c @@ -134,7 +134,7 @@ static void default_idle(void) cpu_relax(); else { local_irq_disable(); - if (!need_resched()) { + if (!need_resched() && !need_resched_delayed()) { timer_dyn_reprogram(); arch_idle(); } @@ -166,13 +166,17 @@ void cpu_idle(void) idle = default_idle; leds_event(led_idle_start); tick_nohz_stop_sched_tick(); - while (!need_resched()) + while (!need_resched() && !need_resched_delayed()) idle(); leds_event(led_idle_end); + local_irq_disable(); + trace_preempt_exit_idle(); tick_nohz_restart_sched_tick(); - preempt_enable_no_resched(); - schedule(); + __preempt_enable_no_resched(); + __schedule(); preempt_disable(); + trace_preempt_enter_idle(); + local_irq_enable(); } } Index: linux-rt-rebase.q/arch/arm/kernel/semaphore.c =================================================================== --- linux-rt-rebase.q.orig/arch/arm/kernel/semaphore.c +++ linux-rt-rebase.q/arch/arm/kernel/semaphore.c @@ -49,14 +49,16 @@ * we cannot lose wakeup events. */ -void __up(struct semaphore *sem) +fastcall void __attribute_used__ __compat_up(struct compat_semaphore *sem) { wake_up(&sem->wait); } +EXPORT_SYMBOL(__compat_up); + static DEFINE_SPINLOCK(semaphore_lock); -void __sched __down(struct semaphore * sem) +fastcall void __attribute_used__ __sched __compat_down(struct compat_semaphore * sem) { struct task_struct *tsk = current; DECLARE_WAITQUEUE(wait, tsk); @@ -89,7 +91,9 @@ void __sched __down(struct semaphore * s wake_up(&sem->wait); } -int __sched __down_interruptible(struct semaphore * sem) +EXPORT_SYMBOL(__compat_down); + +fastcall int __attribute_used__ __sched __compat_down_interruptible(struct compat_semaphore * sem) { int retval = 0; struct task_struct *tsk = current; @@ -140,6 +144,8 @@ int __sched __down_interruptible(struct return retval; } +EXPORT_SYMBOL(__compat_down_interruptible); + /* * Trylock failed - make sure we correct for * having decremented the count. @@ -148,7 +154,7 @@ int __sched __down_interruptible(struct * single "cmpxchg" without failure cases, * but then it wouldn't work on a 386. */ -int __down_trylock(struct semaphore * sem) +fastcall int __attribute_used__ __sched __compat_down_trylock(struct compat_semaphore * sem) { int sleepers; unsigned long flags; @@ -168,6 +174,15 @@ int __down_trylock(struct semaphore * se return 1; } +EXPORT_SYMBOL(__compat_down_trylock); + +fastcall int __sched compat_sem_is_locked(struct compat_semaphore *sem) +{ + return (int) atomic_read(&sem->count) < 0; +} + +EXPORT_SYMBOL(compat_sem_is_locked); + /* * The semaphore operations have a special calling sequence that * allow us to do a simpler in-line version of them. These routines @@ -185,7 +200,7 @@ asm(" .section .sched.text,\"ax\",%progb __down_failed: \n\ stmfd sp!, {r0 - r4, lr} \n\ mov r0, ip \n\ - bl __down \n\ + bl __compat_down \n\ ldmfd sp!, {r0 - r4, pc} \n\ \n\ .align 5 \n\ @@ -193,7 +208,7 @@ __down_failed: \n\ __down_interruptible_failed: \n\ stmfd sp!, {r0 - r4, lr} \n\ mov r0, ip \n\ - bl __down_interruptible \n\ + bl __compat_down_interruptible \n\ mov ip, r0 \n\ ldmfd sp!, {r0 - r4, pc} \n\ \n\ @@ -202,7 +217,7 @@ __down_interruptible_failed: \n\ __down_trylock_failed: \n\ stmfd sp!, {r0 - r4, lr} \n\ mov r0, ip \n\ - bl __down_trylock \n\ + bl __compat_down_trylock \n\ mov ip, r0 \n\ ldmfd sp!, {r0 - r4, pc} \n\ \n\ @@ -211,7 +226,7 @@ __down_trylock_failed: \n\ __up_wakeup: \n\ stmfd sp!, {r0 - r4, lr} \n\ mov r0, ip \n\ - bl __up \n\ + bl __compat_up \n\ ldmfd sp!, {r0 - r4, pc} \n\ "); Index: linux-rt-rebase.q/arch/arm/kernel/signal.c =================================================================== --- linux-rt-rebase.q.orig/arch/arm/kernel/signal.c +++ linux-rt-rebase.q/arch/arm/kernel/signal.c @@ -623,6 +623,14 @@ static int do_signal(sigset_t *oldset, s siginfo_t info; int signr; +#ifdef CONFIG_PREEMPT_RT + /* + * Fully-preemptible kernel does not need interrupts disabled: + */ + local_irq_enable(); + preempt_check_resched(); +#endif + /* * We want the common case to go fast, which * is why we may in certain cases get here from Index: linux-rt-rebase.q/arch/arm/kernel/smp.c =================================================================== --- linux-rt-rebase.q.orig/arch/arm/kernel/smp.c +++ linux-rt-rebase.q/arch/arm/kernel/smp.c @@ -521,7 +521,7 @@ static void ipi_call_function(unsigned i cpu_clear(cpu, data->unfinished); } -static DEFINE_SPINLOCK(stop_lock); +static DEFINE_RAW_SPINLOCK(stop_lock); /* * ipi_cpu_stop - handle IPI from smp_send_stop() Index: linux-rt-rebase.q/arch/arm/kernel/time.c =================================================================== --- linux-rt-rebase.q.orig/arch/arm/kernel/time.c +++ linux-rt-rebase.q/arch/arm/kernel/time.c @@ -236,6 +236,13 @@ static inline void do_leds(void) #define do_leds() #endif +void arch_tick_leds(void) +{ +#ifdef CONFIG_LEDS_TIMER + do_leds(); +#endif +} + #ifndef CONFIG_GENERIC_TIME void do_gettimeofday(struct timeval *tv) { Index: linux-rt-rebase.q/arch/arm/kernel/traps.c =================================================================== --- linux-rt-rebase.q.orig/arch/arm/kernel/traps.c +++ linux-rt-rebase.q/arch/arm/kernel/traps.c @@ -233,7 +233,7 @@ static void __die(const char *str, int e } } -DEFINE_SPINLOCK(die_lock); +DEFINE_RAW_SPINLOCK(die_lock); /* * This function is protected against re-entrancy. @@ -276,7 +276,7 @@ void arm_notify_die(const char *str, str } static LIST_HEAD(undef_hook); -static DEFINE_SPINLOCK(undef_lock); +static DEFINE_RAW_SPINLOCK(undef_lock); void register_undef_hook(struct undef_hook *hook) { @@ -355,6 +355,7 @@ asmlinkage void do_unexp_fiq (struct pt_ #ifndef CONFIG_IGNORE_FIQ printk("Hmm. Unexpected FIQ received, but trying to continue\n"); printk("You may have a hardware problem...\n"); + print_traces(current); #endif } Index: linux-rt-rebase.q/arch/arm/lib/Makefile =================================================================== --- linux-rt-rebase.q.orig/arch/arm/lib/Makefile +++ linux-rt-rebase.q/arch/arm/lib/Makefile @@ -41,6 +41,7 @@ lib-$(CONFIG_ARCH_RPC) += ecard.o io-ac lib-$(CONFIG_ARCH_CLPS7500) += io-acorn.o lib-$(CONFIG_ARCH_L7200) += io-acorn.o lib-$(CONFIG_ARCH_SHARK) += io-shark.o +lib-$(CONFIG_STACKTRACE) += stacktrace.o $(obj)/csumpartialcopy.o: $(obj)/csumpartialcopygeneric.S $(obj)/csumpartialcopyuser.o: $(obj)/csumpartialcopygeneric.S Index: linux-rt-rebase.q/arch/arm/lib/stacktrace.c =================================================================== --- /dev/null +++ linux-rt-rebase.q/arch/arm/lib/stacktrace.c @@ -0,0 +1,7 @@ +#include +#include + +void save_stack_trace(struct stack_trace *trace) +{ +} + Index: linux-rt-rebase.q/arch/arm/mach-ep93xx/core.c =================================================================== --- linux-rt-rebase.q.orig/arch/arm/mach-ep93xx/core.c +++ linux-rt-rebase.q/arch/arm/mach-ep93xx/core.c @@ -32,6 +32,8 @@ #include #include #include +#include +#include #include #include @@ -50,7 +52,6 @@ #include - /************************************************************************* * Static I/O mappings that are needed for all EP93xx platforms *************************************************************************/ @@ -93,59 +94,125 @@ void __init ep93xx_map_io(void) * to use this timer for something else. We also use timer 4 for keeping * track of lost jiffies. */ -static unsigned int last_jiffy_time; - -#define TIMER4_TICKS_PER_JIFFY ((CLOCK_TICK_RATE + (HZ/2)) / HZ) +static struct clock_event_device clockevent_ep93xx; static int ep93xx_timer_interrupt(int irq, void *dev_id) { - write_seqlock(&xtime_lock); + __raw_writel(EP93XX_TC_CLEAR, EP93XX_TIMER1_CLEAR); - __raw_writel(1, EP93XX_TIMER1_CLEAR); - while ((signed long) - (__raw_readl(EP93XX_TIMER4_VALUE_LOW) - last_jiffy_time) - >= TIMER4_TICKS_PER_JIFFY) { - last_jiffy_time += TIMER4_TICKS_PER_JIFFY; - timer_tick(); - } - - write_sequnlock(&xtime_lock); + clockevent_ep93xx.event_handler(&clockevent_ep93xx); return IRQ_HANDLED; } +static int ep93xx_set_next_event(unsigned long evt, + struct clock_event_device *unused) +{ + u32 tmode = __raw_readl(EP93XX_TIMER1_CONTROL); + + /* stop timer */ + __raw_writel(tmode & ~EP93XX_TC123_ENABLE, EP93XX_TIMER1_CONTROL); + /* program timer */ + __raw_writel(evt, EP93XX_TIMER1_LOAD); + /* start timer */ + __raw_writel(tmode | EP93XX_TC123_ENABLE, EP93XX_TIMER1_CONTROL); + + return 0; +} + +static void ep93xx_set_mode(enum clock_event_mode mode, + struct clock_event_device *evt) +{ + u32 tmode = EP93XX_TC123_SEL_508KHZ; + + /* Disable timer */ + __raw_writel(tmode, EP93XX_TIMER1_CONTROL); + + switch(mode) { + case CLOCK_EVT_MODE_PERIODIC: + /* Set timer period */ + __raw_writel((508469 / HZ) - 1, EP93XX_TIMER1_LOAD); + tmode |= EP93XX_TC123_PERIODIC; + + case CLOCK_EVT_MODE_ONESHOT: + tmode |= EP93XX_TC123_ENABLE; + __raw_writel(tmode, EP93XX_TIMER1_CONTROL); + break; + + case CLOCK_EVT_MODE_SHUTDOWN: + case CLOCK_EVT_MODE_UNUSED: + case CLOCK_EVT_MODE_RESUME: + return; + } +} + +static struct clock_event_device clockevent_ep93xx = { + .name = "ep93xx-timer1", + .features = CLOCK_EVT_FEAT_ONESHOT | CLOCK_EVT_FEAT_PERIODIC, + .shift = 32, + .set_mode = ep93xx_set_mode, + .set_next_event = ep93xx_set_next_event, +}; + + static struct irqaction ep93xx_timer_irq = { .name = "ep93xx timer", .flags = IRQF_DISABLED | IRQF_TIMER | IRQF_IRQPOLL, .handler = ep93xx_timer_interrupt, }; -static void __init ep93xx_timer_init(void) +static void __init ep93xx_clockevent_init(void) { - /* Enable periodic HZ timer. */ - __raw_writel(0x48, EP93XX_TIMER1_CONTROL); - __raw_writel((508469 / HZ) - 1, EP93XX_TIMER1_LOAD); - __raw_writel(0xc8, EP93XX_TIMER1_CONTROL); + setup_irq(IRQ_EP93XX_TIMER1, &ep93xx_timer_irq); - /* Enable lost jiffy timer. */ - __raw_writel(0x100, EP93XX_TIMER4_VALUE_HIGH); + clockevent_ep93xx.mult = div_sc(508469, NSEC_PER_SEC, + clockevent_ep93xx.shift); + clockevent_ep93xx.max_delta_ns = + clockevent_delta2ns(0xfffffffe, &clockevent_ep93xx); + clockevent_ep93xx.min_delta_ns = + clockevent_delta2ns(0xf, &clockevent_ep93xx); + clockevent_ep93xx.cpumask = cpumask_of_cpu(0); + clockevents_register_device(&clockevent_ep93xx); +} - setup_irq(IRQ_EP93XX_TIMER1, &ep93xx_timer_irq); +/* + * timer4 is a 40 Bit timer, separated in a 32bit and a 8 bit + * register, EP93XX_TIMER4_VALUE_LOW stores 32 bit word. The + * controlregister is in EP93XX_TIMER4_VALUE_HIGH + */ + +cycle_t ep93xx_get_cycles(void) +{ + return __raw_readl(EP93XX_TIMER4_VALUE_LOW); } -static unsigned long ep93xx_gettimeoffset(void) +static struct clocksource clocksource_ep93xx = { + .name = "ep93xx_timer4", + .rating = 200, + .read = ep93xx_get_cycles, + .mask = 0xFFFFFFFF, + .shift = 20, + .flags = CLOCK_SOURCE_IS_CONTINUOUS, +}; + +static void __init ep93xx_clocksource_init(void) { - int offset; + /* Reset time-stamp counter */ + __raw_writel(0x100, EP93XX_TIMER4_VALUE_HIGH); - offset = __raw_readl(EP93XX_TIMER4_VALUE_LOW) - last_jiffy_time; + clocksource_ep93xx.mult = + clocksource_hz2mult(983040, clocksource_ep93xx.shift); + clocksource_register(&clocksource_ep93xx); +} - /* Calculate (1000000 / 983040) * offset. */ - return offset + (53 * offset / 3072); +static void __init ep93xx_timer_init(void) +{ + ep93xx_clocksource_init(); + ep93xx_clockevent_init(); } struct sys_timer ep93xx_timer = { - .init = ep93xx_timer_init, - .offset = ep93xx_gettimeoffset, + .init = ep93xx_timer_init, }; @@ -497,7 +564,6 @@ static struct platform_device ep93xx_ohc .resource = ep93xx_ohci_resources, }; - void __init ep93xx_init_devices(void) { unsigned int v; Index: linux-rt-rebase.q/arch/arm/mach-footbridge/netwinder-hw.c =================================================================== --- linux-rt-rebase.q.orig/arch/arm/mach-footbridge/netwinder-hw.c +++ linux-rt-rebase.q/arch/arm/mach-footbridge/netwinder-hw.c @@ -67,7 +67,7 @@ static inline void wb977_ww(int reg, int /* * This is a lock for accessing ports GP1_IO_BASE and GP2_IO_BASE */ -DEFINE_SPINLOCK(gpio_lock); +DEFINE_RAW_SPINLOCK(gpio_lock); static unsigned int current_gpio_op; static unsigned int current_gpio_io; Index: linux-rt-rebase.q/arch/arm/mach-footbridge/netwinder-leds.c =================================================================== --- linux-rt-rebase.q.orig/arch/arm/mach-footbridge/netwinder-leds.c +++ linux-rt-rebase.q/arch/arm/mach-footbridge/netwinder-leds.c @@ -32,7 +32,7 @@ static char led_state; static char hw_led_state; static DEFINE_SPINLOCK(leds_lock); -extern spinlock_t gpio_lock; +extern raw_spinlock_t gpio_lock; static void netwinder_leds_event(led_event_t evt) { Index: linux-rt-rebase.q/arch/arm/mach-integrator/core.c =================================================================== --- linux-rt-rebase.q.orig/arch/arm/mach-integrator/core.c +++ linux-rt-rebase.q/arch/arm/mach-integrator/core.c @@ -164,7 +164,7 @@ static struct amba_pl010_data integrator #define CM_CTRL IO_ADDRESS(INTEGRATOR_HDR_BASE) + INTEGRATOR_HDR_CTRL_OFFSET -static DEFINE_SPINLOCK(cm_lock); +static DEFINE_RAW_SPINLOCK(cm_lock); /** * cm_control - update the CM_CTRL register. Index: linux-rt-rebase.q/arch/arm/mach-integrator/pci_v3.c =================================================================== --- linux-rt-rebase.q.orig/arch/arm/mach-integrator/pci_v3.c +++ linux-rt-rebase.q/arch/arm/mach-integrator/pci_v3.c @@ -162,7 +162,7 @@ * 7:2 register number * */ -static DEFINE_SPINLOCK(v3_lock); +static DEFINE_RAW_SPINLOCK(v3_lock); #define PCI_BUS_NONMEM_START 0x00000000 #define PCI_BUS_NONMEM_SIZE SZ_256M Index: linux-rt-rebase.q/arch/arm/mach-ixp4xx/common-pci.c =================================================================== --- linux-rt-rebase.q.orig/arch/arm/mach-ixp4xx/common-pci.c +++ linux-rt-rebase.q/arch/arm/mach-ixp4xx/common-pci.c @@ -53,7 +53,7 @@ unsigned long ixp4xx_pci_reg_base = 0; * these transactions are atomic or we will end up * with corrupt data on the bus or in a driver. */ -static DEFINE_SPINLOCK(ixp4xx_pci_lock); +static DEFINE_RAW_SPINLOCK(ixp4xx_pci_lock); /* * Read from PCI config space Index: linux-rt-rebase.q/arch/arm/mach-sa1100/badge4.c =================================================================== --- linux-rt-rebase.q.orig/arch/arm/mach-sa1100/badge4.c +++ linux-rt-rebase.q/arch/arm/mach-sa1100/badge4.c @@ -240,15 +240,22 @@ void badge4_set_5V(unsigned subsystem, i /* detect on->off and off->on transitions */ if ((!old_5V_bitmap) && (badge4_5V_bitmap)) { /* was off, now on */ - printk(KERN_INFO "%s: enabling 5V supply rail\n", __FUNCTION__); GPSR = BADGE4_GPIO_PCMEN5V; } else if ((old_5V_bitmap) && (!badge4_5V_bitmap)) { /* was on, now off */ - printk(KERN_INFO "%s: disabling 5V supply rail\n", __FUNCTION__); GPCR = BADGE4_GPIO_PCMEN5V; } local_irq_restore(flags); + + /* detect on->off and off->on transitions */ + if ((!old_5V_bitmap) && (badge4_5V_bitmap)) { + /* was off, now on */ + printk(KERN_INFO "%s: enabling 5V supply rail\n", __FUNCTION__); + } else if ((old_5V_bitmap) && (!badge4_5V_bitmap)) { + /* was on, now off */ + printk(KERN_INFO "%s: disabling 5V supply rail\n", __FUNCTION__); + } } EXPORT_SYMBOL(badge4_set_5V); Index: linux-rt-rebase.q/arch/arm/mach-shark/leds.c =================================================================== --- linux-rt-rebase.q.orig/arch/arm/mach-shark/leds.c +++ linux-rt-rebase.q/arch/arm/mach-shark/leds.c @@ -32,7 +32,7 @@ static char led_state; static short hw_led_state; static short saved_state; -static DEFINE_SPINLOCK(leds_lock); +static DEFINE_RAW_SPINLOCK(leds_lock); short sequoia_read(int addr) { outw(addr,0x24); Index: linux-rt-rebase.q/arch/arm/mm/consistent.c =================================================================== --- linux-rt-rebase.q.orig/arch/arm/mm/consistent.c +++ linux-rt-rebase.q/arch/arm/mm/consistent.c @@ -40,7 +40,7 @@ * These are the page tables (2MB each) covering uncached, DMA consistent allocations */ static pte_t *consistent_pte[NUM_CONSISTENT_PTES]; -static DEFINE_SPINLOCK(consistent_lock); +static DEFINE_RAW_SPINLOCK(consistent_lock); /* * VM region handling support. Index: linux-rt-rebase.q/arch/arm/mm/copypage-v4mc.c =================================================================== --- linux-rt-rebase.q.orig/arch/arm/mm/copypage-v4mc.c +++ linux-rt-rebase.q/arch/arm/mm/copypage-v4mc.c @@ -30,7 +30,7 @@ #define minicache_pgprot __pgprot(L_PTE_PRESENT | L_PTE_YOUNG | \ L_PTE_CACHEABLE) -static DEFINE_SPINLOCK(minicache_lock); +static DEFINE_RAW_SPINLOCK(minicache_lock); /* * ARMv4 mini-dcache optimised copy_user_page @@ -44,7 +44,7 @@ static DEFINE_SPINLOCK(minicache_lock); * instruction. If your processor does not supply this, you have to write your * own copy_user_page that does the right thing. */ -static void __attribute__((naked)) +static void notrace __attribute__((naked)) mc_copy_user_page(void *from, void *to) { asm volatile( @@ -88,7 +88,7 @@ void v4_mc_copy_user_page(void *kto, con /* * ARMv4 optimised clear_user_page */ -void __attribute__((naked)) +void notrace __attribute__((naked)) v4_mc_clear_user_page(void *kaddr, unsigned long vaddr) { asm volatile( Index: linux-rt-rebase.q/arch/arm/mm/copypage-v6.c =================================================================== --- linux-rt-rebase.q.orig/arch/arm/mm/copypage-v6.c +++ linux-rt-rebase.q/arch/arm/mm/copypage-v6.c @@ -26,7 +26,7 @@ #define from_address (0xffff8000) #define to_address (0xffffc000) -static DEFINE_SPINLOCK(v6_lock); +static DEFINE_RAW_SPINLOCK(v6_lock); /* * Copy the user page. No aliasing to deal with so we can just Index: linux-rt-rebase.q/arch/arm/mm/copypage-xscale.c =================================================================== --- linux-rt-rebase.q.orig/arch/arm/mm/copypage-xscale.c +++ linux-rt-rebase.q/arch/arm/mm/copypage-xscale.c @@ -32,7 +32,7 @@ #define minicache_pgprot __pgprot(L_PTE_PRESENT | L_PTE_YOUNG | \ L_PTE_CACHEABLE) -static DEFINE_SPINLOCK(minicache_lock); +static DEFINE_RAW_SPINLOCK(minicache_lock); /* * XScale mini-dcache optimised copy_user_page @@ -42,7 +42,7 @@ static DEFINE_SPINLOCK(minicache_lock); * Dcache aliasing issue. The writes will be forwarded to the write buffer, * and merged as appropriate. */ -static void __attribute__((naked)) +static void notrace __attribute__((naked)) mc_copy_user_page(void *from, void *to) { /* @@ -110,7 +110,7 @@ void xscale_mc_copy_user_page(void *kto, /* * XScale optimised clear_user_page */ -void __attribute__((naked)) +void notrace __attribute__((naked)) xscale_mc_clear_user_page(void *kaddr, unsigned long vaddr) { asm volatile( Index: linux-rt-rebase.q/arch/arm/mm/fault.c =================================================================== --- linux-rt-rebase.q.orig/arch/arm/mm/fault.c +++ linux-rt-rebase.q/arch/arm/mm/fault.c @@ -215,7 +215,7 @@ out: return fault; } -static int +static notrace int do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs) { struct task_struct *tsk; @@ -229,7 +229,7 @@ do_page_fault(unsigned long addr, unsign * If we're in an interrupt or have no user * context, we must not take the fault.. */ - if (in_atomic() || !mm) + if (in_atomic() || !mm || current->pagefault_disabled) goto no_context; /* @@ -311,7 +311,7 @@ no_context: * interrupt or a critical region, and should only copy the information * from the master page table, nothing more. */ -static int +static notrace int do_translation_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs) { @@ -354,7 +354,7 @@ bad_area: * Some section permission faults need to be handled gracefully. * They can happen due to a __{get,put}_user during an oops. */ -static int +static notrace int do_sect_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs) { do_bad_area(addr, fsr, regs); @@ -364,7 +364,7 @@ do_sect_fault(unsigned long addr, unsign /* * This abort handler always returns "fault". */ -static int +static notrace int do_bad(unsigned long addr, unsigned int fsr, struct pt_regs *regs) { return 1; @@ -419,7 +419,7 @@ static struct fsr_info { { do_bad, SIGBUS, 0, "unknown 31" } }; -void __init +void __init notrace hook_fault_code(int nr, int (*fn)(unsigned long, unsigned int, struct pt_regs *), int sig, const char *name) { @@ -433,7 +433,7 @@ hook_fault_code(int nr, int (*fn)(unsign /* * Dispatch a data abort to the relevant handler. */ -asmlinkage void __exception +asmlinkage void __exception notrace do_DataAbort(unsigned long addr, unsigned int fsr, struct pt_regs *regs) { const struct fsr_info *inf = fsr_info + (fsr & 15) + ((fsr & (1 << 10)) >> 6); @@ -452,7 +452,7 @@ do_DataAbort(unsigned long addr, unsigne arm_notify_die("", regs, &info, fsr, 0); } -asmlinkage void __exception +asmlinkage void __exception notrace do_PrefetchAbort(unsigned long addr, struct pt_regs *regs) { do_translation_fault(addr, 0, regs); Index: linux-rt-rebase.q/arch/arm/mm/mmu.c =================================================================== --- linux-rt-rebase.q.orig/arch/arm/mm/mmu.c +++ linux-rt-rebase.q/arch/arm/mm/mmu.c @@ -25,7 +25,7 @@ #include "mm.h" -DEFINE_PER_CPU(struct mmu_gather, mmu_gathers); +DEFINE_PER_CPU_LOCKED(struct mmu_gather, mmu_gathers); extern void _stext, _etext, __data_start, _end; extern pgd_t swapper_pg_dir[PTRS_PER_PGD]; Index: linux-rt-rebase.q/arch/arm/oprofile/op_model_xscale.c =================================================================== --- linux-rt-rebase.q.orig/arch/arm/oprofile/op_model_xscale.c +++ linux-rt-rebase.q/arch/arm/oprofile/op_model_xscale.c @@ -381,8 +381,9 @@ static int xscale_pmu_start(void) { int ret; u32 pmnc = read_pmnc(); + int irq_flags = IRQF_DISABLED | IRQF_NODELAY; - ret = request_irq(XSCALE_PMU_IRQ, xscale_pmu_interrupt, IRQF_DISABLED, + ret = request_irq(XSCALE_PMU_IRQ, xscale_pmu_interrupt, irq_flags, "XScale PMU", (void *)results); if (ret < 0) { Index: linux-rt-rebase.q/arch/arm/plat-omap/mailbox.c =================================================================== --- linux-rt-rebase.q.orig/arch/arm/plat-omap/mailbox.c +++ linux-rt-rebase.q/arch/arm/plat-omap/mailbox.c @@ -161,11 +161,11 @@ static void mbox_rx_work(struct work_str /* * Mailbox interrupt handler */ -static void mbox_txq_fn(request_queue_t * q) +static void mbox_txq_fn(struct request_queue * q) { } -static void mbox_rxq_fn(request_queue_t * q) +static void mbox_rxq_fn(struct request_queue * q) { } @@ -180,7 +180,7 @@ static void __mbox_rx_interrupt(struct o { struct request *rq; mbox_msg_t msg; - request_queue_t *q = mbox->rxq->queue; + struct request_queue *q = mbox->rxq->queue; disable_mbox_irq(mbox, IRQ_RX); @@ -297,7 +297,7 @@ static struct omap_mbox_queue *mbox_queu request_fn_proc * proc, void (*work) (struct work_struct *)) { - request_queue_t *q; + struct request_queue *q; struct omap_mbox_queue *mq; mq = kzalloc(sizeof(struct omap_mbox_queue), GFP_KERNEL); Index: linux-rt-rebase.q/arch/i386/Kconfig =================================================================== --- linux-rt-rebase.q.orig/arch/i386/Kconfig +++ linux-rt-rebase.q/arch/i386/Kconfig @@ -35,6 +35,10 @@ config GENERIC_CLOCKEVENTS_BROADCAST default y depends on X86_LOCAL_APIC +config NONIRQ_WAKEUP + bool + default y + config LOCKDEP_SUPPORT bool default y @@ -776,6 +780,14 @@ config BOOT_IOREMAP depends on (((X86_SUMMIT || X86_GENERICARCH) && NUMA) || (X86 && EFI)) default y +# +# function tracing might turn this off: +# +config REGPARM + bool + depends on !MCOUNT + default y + config SECCOMP bool "Enable seccomp to safely compute untrusted bytecode" depends on PROC_FS @@ -1066,6 +1078,8 @@ endif # APM source "arch/i386/kernel/cpu/cpufreq/Kconfig" +source "drivers/cpuidle/Kconfig" + endmenu menu "Bus options (PCI, PCMCIA, EISA, MCA, ISA)" @@ -1270,6 +1284,10 @@ config GENERIC_PENDING_IRQ depends on GENERIC_HARDIRQS && SMP default y +config HARDIRQS_SW_RESEND + bool + default y + config X86_SMP bool depends on SMP && !X86_VOYAGER Index: linux-rt-rebase.q/arch/i386/Kconfig.cpu =================================================================== --- linux-rt-rebase.q.orig/arch/i386/Kconfig.cpu +++ linux-rt-rebase.q/arch/i386/Kconfig.cpu @@ -247,12 +247,16 @@ config X86_XADD config RWSEM_GENERIC_SPINLOCK bool - depends on !X86_XADD + depends on !X86_XADD || PREEMPT_RT + default y + +config ASM_SEMAPHORES + bool default y config RWSEM_XCHGADD_ALGORITHM bool - depends on X86_XADD + depends on X86_XADD && !RWSEM_GENERIC_SPINLOCK default y config ARCH_HAS_ILOG2_U32 Index: linux-rt-rebase.q/arch/i386/Kconfig.debug =================================================================== --- linux-rt-rebase.q.orig/arch/i386/Kconfig.debug +++ linux-rt-rebase.q/arch/i386/Kconfig.debug @@ -49,6 +49,7 @@ config DEBUG_PAGEALLOC config DEBUG_RODATA bool "Write protect kernel read-only data structures" depends on DEBUG_KERNEL + default y help Mark the kernel read-only data as write-protected in the pagetables, in order to catch accidental (and incorrect) writes to such const @@ -59,6 +60,7 @@ config DEBUG_RODATA config 4KSTACKS bool "Use 4Kb for kernel stacks instead of 8Kb" depends on DEBUG_KERNEL + default y help If you say Y here the kernel will use a 4Kb stacksize for the kernel stack attached to each process/thread. This facilitates Index: linux-rt-rebase.q/arch/i386/Makefile =================================================================== --- linux-rt-rebase.q.orig/arch/i386/Makefile +++ linux-rt-rebase.q/arch/i386/Makefile @@ -31,7 +31,7 @@ LDFLAGS_vmlinux := --emit-relocs endif CHECKFLAGS += -D__i386__ -CFLAGS += -pipe -msoft-float -mregparm=3 -freg-struct-return +CFLAGS += -pipe -msoft-float -freg-struct-return # prevent gcc from keeping the stack 16 byte aligned CFLAGS += $(call cc-option,-mpreferred-stack-boundary=2) @@ -39,6 +39,8 @@ CFLAGS += $(call cc-option,-mpreferred-s # CPU-specific tuning. Anything which can be shared with UML should go here. include $(srctree)/arch/i386/Makefile.cpu +cflags-$(CONFIG_REGPARM) += -mregparm=3 + # temporary until string.h is fixed cflags-y += -ffreestanding Index: linux-rt-rebase.q/arch/i386/boot/apm.c =================================================================== --- linux-rt-rebase.q.orig/arch/i386/boot/apm.c +++ linux-rt-rebase.q/arch/i386/boot/apm.c @@ -40,14 +40,15 @@ int query_apm_bios(void) if (bx != 0x504d) /* "PM" signature */ return -1; - if (cx & 0x02) /* 32 bits supported? */ + if (!(cx & 0x02)) /* 32 bits supported? */ return -1; /* Disconnect first, just in case */ ax = 0x5304; + bx = 0; asm volatile("pushl %%ebp ; int $0x15 ; popl %%ebp" - : "+a" (ax) - : : "ebx", "ecx", "edx", "esi", "edi"); + : "+a" (ax), "+b" (bx) + : : "ecx", "edx", "esi", "edi"); /* Paranoia */ ebx = esi = 0; Index: linux-rt-rebase.q/arch/i386/boot/compressed/Makefile =================================================================== --- linux-rt-rebase.q.orig/arch/i386/boot/compressed/Makefile +++ linux-rt-rebase.q/arch/i386/boot/compressed/Makefile @@ -11,7 +11,7 @@ EXTRA_AFLAGS := -traditional LDFLAGS_vmlinux := -T hostprogs-y := relocs -CFLAGS := -m32 -D__KERNEL__ $(LINUX_INCLUDE) -O2 \ +CFLAGS := -m32 -D__KERNEL__ $(LINUX_INCLUDE) -Iinclude -O2 \ -fno-strict-aliasing -fPIC \ $(call cc-option,-ffreestanding) \ $(call cc-option,-fno-stack-protector) Index: linux-rt-rebase.q/arch/i386/boot/main.c =================================================================== --- linux-rt-rebase.q.orig/arch/i386/boot/main.c +++ linux-rt-rebase.q/arch/i386/boot/main.c @@ -73,15 +73,15 @@ static void keyboard_set_repeat(void) } /* - * Get Intel SpeedStep IST information. + * Get Intel SpeedStep (IST) information. */ -static void query_speedstep_ist(void) +static void query_ist(void) { asm("int $0x15" - : "=a" (boot_params.speedstep_info[0]), - "=b" (boot_params.speedstep_info[1]), - "=c" (boot_params.speedstep_info[2]), - "=d" (boot_params.speedstep_info[3]) + : "=a" (boot_params.ist_info.signature), + "=b" (boot_params.ist_info.command), + "=c" (boot_params.ist_info.event), + "=d" (boot_params.ist_info.perf_level) : "a" (0x0000e980), /* IST Support */ "d" (0x47534943)); /* Request value */ } @@ -144,8 +144,8 @@ void main(void) query_voyager(); #endif - /* Query SpeedStep IST information */ - query_speedstep_ist(); + /* Query Intel SpeedStep (IST) information */ + query_ist(); /* Query APM information */ #if defined(CONFIG_APM) || defined(CONFIG_APM_MODULE) Index: linux-rt-rebase.q/arch/i386/kernel/Makefile =================================================================== --- linux-rt-rebase.q.orig/arch/i386/kernel/Makefile +++ linux-rt-rebase.q/arch/i386/kernel/Makefile @@ -21,6 +21,7 @@ obj-$(CONFIG_APM) += apm.o obj-$(CONFIG_X86_SMP) += smp.o smpboot.o tsc_sync.o obj-$(CONFIG_SMP) += smpcommon.o obj-$(CONFIG_X86_TRAMPOLINE) += trampoline.o +obj-$(CONFIG_MCOUNT) += mcount-wrapper.o obj-$(CONFIG_X86_MPPARSE) += mpparse.o obj-$(CONFIG_X86_LOCAL_APIC) += apic.o nmi.o obj-$(CONFIG_X86_IO_APIC) += io_apic.o Index: linux-rt-rebase.q/arch/i386/kernel/acpi/Makefile =================================================================== --- linux-rt-rebase.q.orig/arch/i386/kernel/acpi/Makefile +++ linux-rt-rebase.q/arch/i386/kernel/acpi/Makefile @@ -2,7 +2,7 @@ obj-$(CONFIG_ACPI) += boot.o ifneq ($(CONFIG_PCI),) obj-$(CONFIG_X86_IO_APIC) += earlyquirk.o endif -obj-$(CONFIG_ACPI_SLEEP) += sleep.o wakeup.o +obj-$(CONFIG_ACPI) += sleep.o wakeup.o ifneq ($(CONFIG_ACPI_PROCESSOR),) obj-y += cstate.o processor.o Index: linux-rt-rebase.q/arch/i386/kernel/apic.c =================================================================== --- linux-rt-rebase.q.orig/arch/i386/kernel/apic.c +++ linux-rt-rebase.q/arch/i386/kernel/apic.c @@ -579,10 +579,12 @@ static void local_apic_timer_interrupt(v * interrupt as well. Thus we cannot inline the local irq ... ] */ -void fastcall smp_apic_timer_interrupt(struct pt_regs *regs) +void fastcall notrace smp_apic_timer_interrupt(struct pt_regs *regs) { struct pt_regs *old_regs = set_irq_regs(regs); + trace_special(regs->eip, 1, 0); + /* * NOTE! We'd better ACK the irq immediately, * because timer handling can be slow. @@ -1309,6 +1311,7 @@ void smp_error_interrupt(struct pt_regs */ printk (KERN_DEBUG "APIC error on CPU%d: %02lx(%02lx)\n", smp_processor_id(), v , v1); + dump_stack(); irq_exit(); } Index: linux-rt-rebase.q/arch/i386/kernel/apm.c =================================================================== --- linux-rt-rebase.q.orig/arch/i386/kernel/apm.c +++ linux-rt-rebase.q/arch/i386/kernel/apm.c @@ -783,7 +783,7 @@ static int apm_do_idle(void) */ smp_mb(); } - if (!need_resched()) { + if (!need_resched() && !need_resched_delayed()) { idled = 1; ret = apm_bios_call_simple(APM_FUNC_IDLE, 0, 0, &eax); } Index: linux-rt-rebase.q/arch/i386/kernel/cpu/mtrr/generic.c =================================================================== --- linux-rt-rebase.q.orig/arch/i386/kernel/cpu/mtrr/generic.c +++ linux-rt-rebase.q/arch/i386/kernel/cpu/mtrr/generic.c @@ -330,7 +330,7 @@ static unsigned long set_mtrr_state(void static unsigned long cr4 = 0; -static DEFINE_SPINLOCK(set_atomicity_lock); +static DEFINE_RAW_SPINLOCK(set_atomicity_lock); /* * Since we are disabling the cache don't allow any interrupts - they Index: linux-rt-rebase.q/arch/i386/kernel/crash.c =================================================================== --- linux-rt-rebase.q.orig/arch/i386/kernel/crash.c +++ linux-rt-rebase.q/arch/i386/kernel/crash.c @@ -70,14 +70,6 @@ static int crash_nmi_callback(struct not return 1; } -static void smp_send_nmi_allbutself(void) -{ - cpumask_t mask = cpu_online_map; - cpu_clear(safe_smp_processor_id(), mask); - if (!cpus_empty(mask)) - send_IPI_mask(mask, NMI_VECTOR); -} - static struct notifier_block crash_nmi_nb = { .notifier_call = crash_nmi_callback, }; Index: linux-rt-rebase.q/arch/i386/kernel/entry.S =================================================================== --- linux-rt-rebase.q.orig/arch/i386/kernel/entry.S +++ linux-rt-rebase.q/arch/i386/kernel/entry.S @@ -264,14 +264,18 @@ END(ret_from_exception) #ifdef CONFIG_PREEMPT ENTRY(resume_kernel) DISABLE_INTERRUPTS(CLBR_ANY) + cmpl $0, kernel_preemption + jz restore_nocheck cmpl $0,TI_preempt_count(%ebp) # non-zero preempt_count ? jnz restore_nocheck need_resched: movl TI_flags(%ebp), %ecx # need_resched set ? testb $_TIF_NEED_RESCHED, %cl - jz restore_all + jz restore_nocheck testl $IF_MASK,PT_EFLAGS(%esp) # interrupts off (exception path) ? - jz restore_all + jz restore_nocheck + DISABLE_INTERRUPTS(CLBR_ANY) + call preempt_schedule_irq jmp need_resched END(resume_kernel) @@ -329,6 +333,11 @@ sysenter_past_esp: pushl %eax CFI_ADJUST_CFA_OFFSET 4 SAVE_ALL +#ifdef CONFIG_EVENT_TRACE + pushl %edx; pushl %ecx; pushl %ebx; pushl %eax + call sys_call + popl %eax; popl %ebx; popl %ecx; popl %edx +#endif GET_THREAD_INFO(%ebp) /* Note, _TIF_SECCOMP is bit number 8, and so it needs testw and not testb */ @@ -343,6 +352,11 @@ sysenter_past_esp: movl TI_flags(%ebp), %ecx testw $_TIF_ALLWORK_MASK, %cx jne syscall_exit_work +#ifdef CONFIG_EVENT_TRACE + pushl %eax + call sys_ret + popl %eax +#endif /* if something modifies registers it must also disable sysexit */ movl PT_EIP(%esp), %edx movl PT_OLDESP(%esp), %ecx @@ -366,6 +380,11 @@ ENTRY(system_call) pushl %eax # save orig_eax CFI_ADJUST_CFA_OFFSET 4 SAVE_ALL +#ifdef CONFIG_EVENT_TRACE + pushl %edx; pushl %ecx; pushl %ebx; pushl %eax + call sys_call + popl %eax; popl %ebx; popl %ecx; popl %edx +#endif GET_THREAD_INFO(%ebp) # system call tracing in operation / emulation /* Note, _TIF_SECCOMP is bit number 8, and so it needs testw and not testb */ @@ -463,19 +482,19 @@ ENDPROC(system_call) ALIGN RING0_PTREGS_FRAME # can't unwind into user space anyway work_pending: - testb $_TIF_NEED_RESCHED, %cl + testl $(_TIF_NEED_RESCHED|_TIF_NEED_RESCHED_DELAYED), %ecx jz work_notifysig work_resched: - call schedule - DISABLE_INTERRUPTS(CLBR_ANY) # make sure we don't miss an interrupt + DISABLE_INTERRUPTS(CLBR_ANY) + call __schedule + # make sure we don't miss an interrupt # setting need_resched or sigpending # between sampling and the iret - TRACE_IRQS_OFF movl TI_flags(%ebp), %ecx andl $_TIF_WORK_MASK, %ecx # is there any work to be done other # than syscall tracing? jz restore_all - testb $_TIF_NEED_RESCHED, %cl + testl $(_TIF_NEED_RESCHED|_TIF_NEED_RESCHED_DELAYED), %ecx jnz work_resched work_notifysig: # deal with pending signals and Index: linux-rt-rebase.q/arch/i386/kernel/head.S =================================================================== --- linux-rt-rebase.q.orig/arch/i386/kernel/head.S +++ linux-rt-rebase.q/arch/i386/kernel/head.S @@ -492,6 +492,7 @@ ignore_int: call printk #endif addl $(5*4),%esp + call dump_stack popl %ds popl %es popl %edx Index: linux-rt-rebase.q/arch/i386/kernel/hpet.c =================================================================== --- linux-rt-rebase.q.orig/arch/i386/kernel/hpet.c +++ linux-rt-rebase.q/arch/i386/kernel/hpet.c @@ -1,5 +1,6 @@ #include #include +#include #include #include #include @@ -7,11 +8,11 @@ #include #include +#include #include +#include #include -extern struct clock_event_device *global_clock_event; - #define HPET_MASK CLOCKSOURCE_MASK(32) #define HPET_SHIFT 22 @@ -22,9 +23,9 @@ extern struct clock_event_device *global * HPET address is set in acpi/boot.c, when an ACPI entry exists */ unsigned long hpet_address; -static void __iomem * hpet_virt_address; +static void __iomem *hpet_virt_address; -static inline unsigned long hpet_readl(unsigned long a) +unsigned long hpet_readl(unsigned long a) { return readl(hpet_virt_address + a); } @@ -34,6 +35,36 @@ static inline void hpet_writel(unsigned writel(d, hpet_virt_address + a); } +#ifdef CONFIG_X86_64 + +#include + +static inline void hpet_set_mapping(void) +{ + set_fixmap_nocache(FIX_HPET_BASE, hpet_address); + __set_fixmap(VSYSCALL_HPET, hpet_address, PAGE_KERNEL_VSYSCALL_NOCACHE); + hpet_virt_address = (void __iomem *)fix_to_virt(FIX_HPET_BASE); +} + +static inline void hpet_clear_mapping(void) +{ + hpet_virt_address = NULL; +} + +#else + +static inline void hpet_set_mapping(void) +{ + hpet_virt_address = ioremap_nocache(hpet_address, HPET_MMAP_SIZE); +} + +static inline void hpet_clear_mapping(void) +{ + iounmap(hpet_virt_address); + hpet_virt_address = NULL; +} +#endif + /* * HPET command line enable / disable */ @@ -49,6 +80,13 @@ static int __init hpet_setup(char* str) } __setup("hpet=", hpet_setup); +static int __init disable_hpet(char *str) +{ + boot_hpet_disable = 1; + return 1; +} +__setup("nohpet", disable_hpet); + static inline int is_hpet_capable(void) { return (!boot_hpet_disable && hpet_address); @@ -83,7 +121,7 @@ static void hpet_reserve_platform_timers memset(&hd, 0, sizeof (hd)); hd.hd_phys_address = hpet_address; - hd.hd_address = hpet_virt_address; + hd.hd_address = hpet; hd.hd_nirqs = nrtimers; hd.hd_flags = HPET_DATA_PLATFORM; hpet_reserve_timer(&hd, 0); @@ -111,9 +149,9 @@ static void hpet_reserve_platform_timers */ static unsigned long hpet_period; -static void hpet_set_mode(enum clock_event_mode mode, +static void hpet_legacy_set_mode(enum clock_event_mode mode, struct clock_event_device *evt); -static int hpet_next_event(unsigned long delta, +static int hpet_legacy_next_event(unsigned long delta, struct clock_event_device *evt); /* @@ -122,10 +160,11 @@ static int hpet_next_event(unsigned long static struct clock_event_device hpet_clockevent = { .name = "hpet", .features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT, - .set_mode = hpet_set_mode, - .set_next_event = hpet_next_event, + .set_mode = hpet_legacy_set_mode, + .set_next_event = hpet_legacy_next_event, .shift = 32, .irq = 0, + .rating = 50, }; static void hpet_start_counter(void) @@ -140,7 +179,18 @@ static void hpet_start_counter(void) hpet_writel(cfg, HPET_CFG); } -static void hpet_enable_int(void) +static void hpet_resume_device(void) +{ + force_hpet_resume(); +} + +static void hpet_restart_counter(void) +{ + hpet_resume_device(); + hpet_start_counter(); +} + +static void hpet_enable_legacy_int(void) { unsigned long cfg = hpet_readl(HPET_CFG); @@ -149,7 +199,39 @@ static void hpet_enable_int(void) hpet_legacy_int_enabled = 1; } -static void hpet_set_mode(enum clock_event_mode mode, +static void hpet_legacy_clockevent_register(void) +{ + uint64_t hpet_freq; + + /* Start HPET legacy interrupts */ + hpet_enable_legacy_int(); + + /* + * The period is a femto seconds value. We need to calculate the + * scaled math multiplication factor for nanosecond to hpet tick + * conversion. + */ + hpet_freq = 1000000000000000ULL; + do_div(hpet_freq, hpet_period); + hpet_clockevent.mult = div_sc((unsigned long) hpet_freq, + NSEC_PER_SEC, 32); + /* Calculate the min / max delta */ + hpet_clockevent.max_delta_ns = clockevent_delta2ns(0x7FFFFFFF, + &hpet_clockevent); + hpet_clockevent.min_delta_ns = clockevent_delta2ns(0x30, + &hpet_clockevent); + + /* + * Start hpet with the boot cpu mask and make it + * global after the IO_APIC has been initialized. + */ + hpet_clockevent.cpumask = cpumask_of_cpu(smp_processor_id()); + clockevents_register_device(&hpet_clockevent); + global_clock_event = &hpet_clockevent; + printk(KERN_DEBUG "hpet clockevent registered\n"); +} + +static void hpet_legacy_set_mode(enum clock_event_mode mode, struct clock_event_device *evt) { unsigned long cfg, cmp, now; @@ -190,12 +272,12 @@ static void hpet_set_mode(enum clock_eve break; case CLOCK_EVT_MODE_RESUME: - hpet_enable_int(); + hpet_enable_legacy_int(); break; } } -static int hpet_next_event(unsigned long delta, +static int hpet_legacy_next_event(unsigned long delta, struct clock_event_device *evt) { unsigned long cnt; @@ -210,11 +292,18 @@ static int hpet_next_event(unsigned long /* * Clock source related code */ -static cycle_t read_hpet(void) +static cycle_t notrace read_hpet(void) { return (cycle_t)hpet_readl(HPET_COUNTER); } +#ifdef CONFIG_X86_64 +static cycle_t __vsyscall_fn vread_hpet(void) +{ + return readl((const void __iomem *)fix_to_virt(VSYSCALL_HPET) + 0xf0); +} +#endif + static struct clocksource clocksource_hpet = { .name = "hpet", .rating = 250, @@ -222,61 +311,17 @@ static struct clocksource clocksource_hp .mask = HPET_MASK, .shift = HPET_SHIFT, .flags = CLOCK_SOURCE_IS_CONTINUOUS, - .resume = hpet_start_counter, + .resume = hpet_restart_counter, +#ifdef CONFIG_X86_64 + .vread = vread_hpet, +#endif }; -/* - * Try to setup the HPET timer - */ -int __init hpet_enable(void) +static int hpet_clocksource_register(void) { - unsigned long id; - uint64_t hpet_freq; u64 tmp, start, now; cycle_t t1; - if (!is_hpet_capable()) - return 0; - - hpet_virt_address = ioremap_nocache(hpet_address, HPET_MMAP_SIZE); - - /* - * Read the period and check for a sane value: - */ - hpet_period = hpet_readl(HPET_PERIOD); - if (hpet_period < HPET_MIN_PERIOD || hpet_period > HPET_MAX_PERIOD) - goto out_nohpet; - - /* - * The period is a femto seconds value. We need to calculate the - * scaled math multiplication factor for nanosecond to hpet tick - * conversion. - */ - hpet_freq = 1000000000000000ULL; - do_div(hpet_freq, hpet_period); - hpet_clockevent.mult = div_sc((unsigned long) hpet_freq, - NSEC_PER_SEC, 32); - /* Calculate the min / max delta */ - hpet_clockevent.max_delta_ns = clockevent_delta2ns(0x7FFFFFFF, - &hpet_clockevent); - hpet_clockevent.min_delta_ns = clockevent_delta2ns(0x30, - &hpet_clockevent); - - /* - * Read the HPET ID register to retrieve the IRQ routing - * information and the number of channels - */ - id = hpet_readl(HPET_ID); - -#ifdef CONFIG_HPET_EMULATE_RTC - /* - * The legacy routing mode needs at least two channels, tick timer - * and the rtc emulation channel. - */ - if (!(id & HPET_ID_NUMBER)) - goto out_nohpet; -#endif - /* Start the counter */ hpet_start_counter(); @@ -298,7 +343,7 @@ int __init hpet_enable(void) if (t1 == read_hpet()) { printk(KERN_WARNING "HPET counter not counting. HPET disabled\n"); - goto out_nohpet; + return -ENODEV; } /* Initialize and register HPET clocksource @@ -319,27 +364,84 @@ int __init hpet_enable(void) clocksource_register(&clocksource_hpet); + return 0; +} + +/* + * Try to setup the HPET timer + */ +int __init hpet_enable(void) +{ + unsigned long id; + + if (!is_hpet_capable()) + return 0; + + hpet_set_mapping(); + + /* + * Read the period and check for a sane value: + */ + hpet_period = hpet_readl(HPET_PERIOD); + if (hpet_period < HPET_MIN_PERIOD || hpet_period > HPET_MAX_PERIOD) + goto out_nohpet; + + /* + * Read the HPET ID register to retrieve the IRQ routing + * information and the number of channels + */ + id = hpet_readl(HPET_ID); + +#ifdef CONFIG_HPET_EMULATE_RTC + /* + * The legacy routing mode needs at least two channels, tick timer + * and the rtc emulation channel. + */ + if (!(id & HPET_ID_NUMBER)) + goto out_nohpet; +#endif + + if (hpet_clocksource_register()) + goto out_nohpet; + if (id & HPET_ID_LEGSUP) { - hpet_enable_int(); - hpet_reserve_platform_timers(id); - /* - * Start hpet with the boot cpu mask and make it - * global after the IO_APIC has been initialized. - */ - hpet_clockevent.cpumask = cpumask_of_cpu(smp_processor_id()); - clockevents_register_device(&hpet_clockevent); - global_clock_event = &hpet_clockevent; + hpet_legacy_clockevent_register(); return 1; } return 0; out_nohpet: - iounmap(hpet_virt_address); - hpet_virt_address = NULL; + hpet_clear_mapping(); boot_hpet_disable = 1; return 0; } +/* + * Needs to be late, as the reserve_timer code calls kalloc ! + * + * Not a problem on i386 as hpet_enable is called from late_time_init, + * but on x86_64 it is necessary ! + */ +static __init int hpet_late_init(void) +{ + if (boot_hpet_disable) + return -ENODEV; + + if (!hpet_address) { + if (!force_hpet_address) + return -ENODEV; + + hpet_address = force_hpet_address; + hpet_enable(); + if (!hpet_virt_address) + return -ENODEV; + } + + hpet_reserve_platform_timers(hpet_readl(HPET_ID)); + + return 0; +} +fs_initcall(hpet_late_init); #ifdef CONFIG_HPET_EMULATE_RTC Index: linux-rt-rebase.q/arch/i386/kernel/i386_ksyms.c =================================================================== --- linux-rt-rebase.q.orig/arch/i386/kernel/i386_ksyms.c +++ linux-rt-rebase.q/arch/i386/kernel/i386_ksyms.c @@ -2,10 +2,12 @@ #include #include -EXPORT_SYMBOL(__down_failed); -EXPORT_SYMBOL(__down_failed_interruptible); -EXPORT_SYMBOL(__down_failed_trylock); -EXPORT_SYMBOL(__up_wakeup); +#ifdef CONFIG_ASM_SEMAPHORES +EXPORT_SYMBOL(__compat_down_failed); +EXPORT_SYMBOL(__compat_down_failed_interruptible); +EXPORT_SYMBOL(__compat_down_failed_trylock); +EXPORT_SYMBOL(__compat_up_wakeup); +#endif /* Networking helper routines. */ EXPORT_SYMBOL(csum_partial_copy_generic); @@ -20,7 +22,7 @@ EXPORT_SYMBOL(__put_user_8); EXPORT_SYMBOL(strstr); -#ifdef CONFIG_SMP +#if defined(CONFIG_SMP) && defined(CONFIG_ASM_SEMAPHORES) extern void FASTCALL( __write_lock_failed(rwlock_t *rw)); extern void FASTCALL( __read_lock_failed(rwlock_t *rw)); EXPORT_SYMBOL(__write_lock_failed); Index: linux-rt-rebase.q/arch/i386/kernel/i8253.c =================================================================== --- linux-rt-rebase.q.orig/arch/i386/kernel/i8253.c +++ linux-rt-rebase.q/arch/i386/kernel/i8253.c @@ -13,9 +13,8 @@ #include #include #include -#include -DEFINE_SPINLOCK(i8253_lock); +DEFINE_RAW_SPINLOCK(i8253_lock); EXPORT_SYMBOL(i8253_lock); /* @@ -120,6 +119,7 @@ void __init setup_pit_timer(void) global_clock_event = &pit_clockevent; } +#ifndef CONFIG_X86_64 /* * Since the PIT overflows every tick, its not very useful * to just read by itself. So use jiffies to emulate a free @@ -204,3 +204,5 @@ static int __init init_pit_clocksource(v return clocksource_register(&clocksource_pit); } arch_initcall(init_pit_clocksource); + +#endif Index: linux-rt-rebase.q/arch/i386/kernel/i8259.c =================================================================== --- linux-rt-rebase.q.orig/arch/i386/kernel/i8259.c +++ linux-rt-rebase.q/arch/i386/kernel/i8259.c @@ -34,7 +34,7 @@ */ static int i8259A_auto_eoi; -DEFINE_SPINLOCK(i8259A_lock); +DEFINE_RAW_SPINLOCK(i8259A_lock); static void mask_and_ack_8259A(unsigned int); static struct irq_chip i8259A_chip = { @@ -170,6 +170,8 @@ static void mask_and_ack_8259A(unsigned */ if (cached_irq_mask & irqmask) goto spurious_8259A_irq; + if (irq & 8) + outb(0x60+(irq&7),PIC_SLAVE_CMD); /* 'Specific EOI' to slave */ cached_irq_mask |= irqmask; handle_real_irq: @@ -297,10 +299,10 @@ void init_8259A(int auto_eoi) outb_p(0x11, PIC_MASTER_CMD); /* ICW1: select 8259A-1 init */ outb_p(0x20 + 0, PIC_MASTER_IMR); /* ICW2: 8259A-1 IR0-7 mapped to 0x20-0x27 */ outb_p(1U << PIC_CASCADE_IR, PIC_MASTER_IMR); /* 8259A-1 (the master) has a slave on IR2 */ - if (auto_eoi) /* master does Auto EOI */ - outb_p(MASTER_ICW4_DEFAULT | PIC_ICW4_AEOI, PIC_MASTER_IMR); - else /* master expects normal EOI */ + if (!auto_eoi) /* master expects normal EOI */ outb_p(MASTER_ICW4_DEFAULT, PIC_MASTER_IMR); + else /* master does Auto EOI */ + outb_p(MASTER_ICW4_DEFAULT | PIC_ICW4_AEOI, PIC_MASTER_IMR); outb_p(0x11, PIC_SLAVE_CMD); /* ICW1: select 8259A-2 init */ outb_p(0x20 + 8, PIC_SLAVE_IMR); /* ICW2: 8259A-2 IR0-7 mapped to 0x28-0x2f */ @@ -350,7 +352,7 @@ static irqreturn_t math_error_irq(int cp * New motherboards sometimes make IRQ 13 be a PCI interrupt, * so allow interrupt sharing. */ -static struct irqaction fpu_irq = { math_error_irq, 0, CPU_MASK_NONE, "fpu", NULL, NULL }; +static struct irqaction fpu_irq = { math_error_irq, IRQF_NODELAY, CPU_MASK_NONE, "fpu", NULL, NULL }; void __init init_ISA_irqs (void) { Index: linux-rt-rebase.q/arch/i386/kernel/io_apic.c =================================================================== --- linux-rt-rebase.q.orig/arch/i386/kernel/io_apic.c +++ linux-rt-rebase.q/arch/i386/kernel/io_apic.c @@ -56,8 +56,8 @@ atomic_t irq_mis_count; /* Where if anywhere is the i8259 connect in external int mode */ static struct { int pin, apic; } ioapic_i8259 = { -1, -1 }; -static DEFINE_SPINLOCK(ioapic_lock); -static DEFINE_SPINLOCK(vector_lock); +static DEFINE_RAW_SPINLOCK(ioapic_lock); +static DEFINE_RAW_SPINLOCK(vector_lock); int timer_over_8254 __initdata = 1; @@ -261,14 +261,14 @@ static void __unmask_IO_APIC_irq (unsign __modify_IO_APIC_irq(irq, 0, 0x00010000); } -/* mask = 1, trigger = 0 */ -static void __mask_and_edge_IO_APIC_irq (unsigned int irq) +/* trigger = 0 (edge mode) */ +static void __pcix_mask_IO_APIC_irq (unsigned int irq) { - __modify_IO_APIC_irq(irq, 0x00010000, 0x00008000); + __modify_IO_APIC_irq(irq, 0, 0x00008000); } -/* mask = 0, trigger = 1 */ -static void __unmask_and_level_IO_APIC_irq (unsigned int irq) +/* mask = 0, trigger = 1 (level mode) */ +static void __pcix_unmask_IO_APIC_irq (unsigned int irq) { __modify_IO_APIC_irq(irq, 0x00008000, 0x00010000); } @@ -291,6 +291,24 @@ static void unmask_IO_APIC_irq (unsigned spin_unlock_irqrestore(&ioapic_lock, flags); } +static void pcix_mask_IO_APIC_irq (unsigned int irq) +{ + unsigned long flags; + + spin_lock_irqsave(&ioapic_lock, flags); + __pcix_mask_IO_APIC_irq(irq); + spin_unlock_irqrestore(&ioapic_lock, flags); +} + +static void pcix_unmask_IO_APIC_irq (unsigned int irq) +{ + unsigned long flags; + + spin_lock_irqsave(&ioapic_lock, flags); + __pcix_unmask_IO_APIC_irq(irq); + spin_unlock_irqrestore(&ioapic_lock, flags); +} + static void clear_IO_APIC_pin(unsigned int apic, unsigned int pin) { struct IO_APIC_route_entry entry; @@ -1247,21 +1265,27 @@ static int assign_irq_vector(int irq) return vector; } + static struct irq_chip ioapic_chip; +static struct irq_chip pcix_ioapic_chip; #define IOAPIC_AUTO -1 #define IOAPIC_EDGE 0 #define IOAPIC_LEVEL 1 -static void ioapic_register_intr(int irq, int vector, unsigned long trigger) +static void ioapic_register_intr(int irq, int vector, unsigned long trigger, + int pcix) { + struct irq_chip *chip = pcix ? &pcix_ioapic_chip : &ioapic_chip; + if ((trigger == IOAPIC_AUTO && IO_APIC_irq_trigger(irq)) || trigger == IOAPIC_LEVEL) - set_irq_chip_and_handler_name(irq, &ioapic_chip, - handle_fasteoi_irq, "fasteoi"); + set_irq_chip_and_handler_name(irq, chip, handle_fasteoi_irq, + pcix ? "pcix-fasteoi" : "fasteoi"); else - set_irq_chip_and_handler_name(irq, &ioapic_chip, - handle_edge_irq, "edge"); + set_irq_chip_and_handler_name(irq, chip, handle_edge_irq, + pcix ? "pcix-edge" : "edge"); + set_intr_gate(vector, interrupt[irq]); } @@ -1325,7 +1349,8 @@ static void __init setup_IO_APIC_irqs(vo if (IO_APIC_IRQ(irq)) { vector = assign_irq_vector(irq); entry.vector = vector; - ioapic_register_intr(irq, vector, IOAPIC_AUTO); + ioapic_register_intr(irq, vector, IOAPIC_AUTO, + apic > 0); if (!apic && (irq < 16)) disable_8259A_irq(irq); @@ -1496,7 +1521,7 @@ void __init print_IO_APIC(void) return; } -#if 0 +#if 1 static void print_APIC_bitfield (int base) { @@ -1900,7 +1925,7 @@ static int __init timer_irq_works(void) * might have cached one ExtINT interrupt. Finally, at * least one tick may be lost due to delays. */ - if (jiffies - t1 > 4) + if (jiffies - t1 > 4 && jiffies - t1 < 16) return 1; return 0; @@ -1989,8 +2014,10 @@ static void ack_ioapic_quirk_irq(unsigne if (!(v & (1 << (i & 0x1f)))) { atomic_inc(&irq_mis_count); spin_lock(&ioapic_lock); - __mask_and_edge_IO_APIC_irq(irq); - __unmask_and_level_IO_APIC_irq(irq); + /* mask = 1, trigger = 0 */ + __modify_IO_APIC_irq(irq, 0x00010000, 0x00008000); + /* mask = 0, trigger = 1 */ + __modify_IO_APIC_irq(irq, 0x00008000, 0x00010000); spin_unlock(&ioapic_lock); } } @@ -2015,6 +2042,18 @@ static struct irq_chip ioapic_chip __rea .retrigger = ioapic_retrigger_irq, }; +static struct irq_chip pcix_ioapic_chip __read_mostly = { + .name = "IO-APIC", + .startup = startup_ioapic_irq, + .mask = pcix_mask_IO_APIC_irq, + .unmask = pcix_unmask_IO_APIC_irq, + .ack = ack_ioapic_irq, + .eoi = ack_ioapic_irq, +#ifdef CONFIG_SMP + .set_affinity = set_ioapic_affinity_irq, +#endif + .retrigger = ioapic_retrigger_irq, +}; static inline void init_IO_APIC_traps(void) { @@ -2815,7 +2854,7 @@ int io_apic_set_pci_routing (int ioapic, mp_ioapics[ioapic].mpc_apicid, pin, entry.vector, irq, edge_level, active_high_low); - ioapic_register_intr(irq, entry.vector, edge_level); + ioapic_register_intr(irq, entry.vector, edge_level, ioapic > 0); if (!ioapic && (irq < 16)) disable_8259A_irq(irq); Index: linux-rt-rebase.q/arch/i386/kernel/irq.c =================================================================== --- linux-rt-rebase.q.orig/arch/i386/kernel/irq.c +++ linux-rt-rebase.q/arch/i386/kernel/irq.c @@ -68,7 +68,7 @@ static union irq_ctx *softirq_ctx[NR_CPU * SMP cross-CPU interrupts have their own specific * handlers). */ -fastcall unsigned int do_IRQ(struct pt_regs *regs) +fastcall notrace unsigned int do_IRQ(struct pt_regs *regs) { struct pt_regs *old_regs; /* high bit used in ret_from_ code */ @@ -79,6 +79,10 @@ fastcall unsigned int do_IRQ(struct pt_r u32 *isp; #endif +#ifdef CONFIG_X86_LOCAL_APIC + irq_show_regs_callback(smp_processor_id(), regs); +#endif + if (unlikely((unsigned)irq >= NR_IRQS)) { printk(KERN_EMERG "%s: cannot handle IRQ %d\n", __FUNCTION__, irq); @@ -87,6 +91,11 @@ fastcall unsigned int do_IRQ(struct pt_r old_regs = set_irq_regs(regs); irq_enter(); +#ifdef CONFIG_EVENT_TRACE + if (irq == trace_user_trigger_irq) + user_trace_start(); +#endif + trace_special(regs->eip, irq, 0); #ifdef CONFIG_DEBUG_STACKOVERFLOW /* Debugging check for stack overflow: is there less than 1KB free? */ { @@ -95,7 +104,7 @@ fastcall unsigned int do_IRQ(struct pt_r __asm__ __volatile__("andl %%esp,%0" : "=r" (esp) : "0" (THREAD_SIZE - 1)); if (unlikely(esp < (sizeof(struct thread_info) + STACK_WARN))) { - printk("do_IRQ: stack overflow: %ld\n", + printk("BUG: do_IRQ: stack overflow: %ld\n", esp - sizeof(struct thread_info)); dump_stack(); } Index: linux-rt-rebase.q/arch/i386/kernel/kprobes.c =================================================================== --- linux-rt-rebase.q.orig/arch/i386/kernel/kprobes.c +++ linux-rt-rebase.q/arch/i386/kernel/kprobes.c @@ -326,7 +326,7 @@ ss_probe: /* Boost up -- we can execute copied instructions directly */ reset_current_kprobe(); regs->eip = (unsigned long)p->ainsn.insn; - preempt_enable_no_resched(); + preempt_enable(); return 1; } #endif @@ -335,7 +335,7 @@ ss_probe: return 1; no_kprobe: - preempt_enable_no_resched(); + preempt_enable(); return ret; } @@ -566,7 +566,7 @@ static int __kprobes post_kprobe_handler } reset_current_kprobe(); out: - preempt_enable_no_resched(); + preempt_enable(); /* * if somebody else is singlestepping across a probe point, eflags @@ -600,7 +600,7 @@ static int __kprobes kprobe_fault_handle restore_previous_kprobe(kcb); else reset_current_kprobe(); - preempt_enable_no_resched(); + preempt_enable(); break; case KPROBE_HIT_ACTIVE: case KPROBE_HIT_SSDONE: @@ -662,12 +662,11 @@ int __kprobes kprobe_exceptions_notify(s break; case DIE_GPF: case DIE_PAGE_FAULT: + // TODO: do this better on PREEMPT_RT /* kprobe_running() needs smp_processor_id() */ - preempt_disable(); - if (kprobe_running() && + if (per_cpu(current_kprobe, raw_smp_processor_id()) && kprobe_fault_handler(args->regs, args->trapnr)) ret = NOTIFY_STOP; - preempt_enable(); break; default: break; @@ -734,7 +733,7 @@ int __kprobes longjmp_break_handler(stru *regs = kcb->jprobe_saved_regs; memcpy((kprobe_opcode_t *) stack_addr, kcb->jprobes_stack, MIN_STACK_SIZE(stack_addr)); - preempt_enable_no_resched(); + preempt_enable(); return 1; } return 0; Index: linux-rt-rebase.q/arch/i386/kernel/mcount-wrapper.S =================================================================== --- /dev/null +++ linux-rt-rebase.q/arch/i386/kernel/mcount-wrapper.S @@ -0,0 +1,27 @@ +/* + * linux/arch/i386/mcount-wrapper.S + * + * Copyright (C) 2004 Ingo Molnar + */ + +.globl mcount +mcount: + + cmpl $0, mcount_enabled + jz out + + push %ebp + mov %esp, %ebp + pushl %eax + pushl %ecx + pushl %edx + + call __mcount + + popl %edx + popl %ecx + popl %eax + popl %ebp +out: + ret + Index: linux-rt-rebase.q/arch/i386/kernel/microcode.c =================================================================== --- linux-rt-rebase.q.orig/arch/i386/kernel/microcode.c +++ linux-rt-rebase.q/arch/i386/kernel/microcode.c @@ -116,7 +116,7 @@ MODULE_LICENSE("GPL"); #define exttable_size(et) ((et)->count * EXT_SIGNATURE_SIZE + EXT_HEADER_SIZE) /* serialize access to the physical write to MSR 0x79 */ -static DEFINE_SPINLOCK(microcode_update_lock); +static DEFINE_RAW_SPINLOCK(microcode_update_lock); /* no concurrent ->write()s are allowed on /dev/cpu/microcode */ static DEFINE_MUTEX(microcode_mutex); Index: linux-rt-rebase.q/arch/i386/kernel/nmi.c =================================================================== --- linux-rt-rebase.q.orig/arch/i386/kernel/nmi.c +++ linux-rt-rebase.q/arch/i386/kernel/nmi.c @@ -28,6 +28,8 @@ #include #include +#include + #include "mach_traps.h" int unknown_nmi_panic; @@ -44,7 +46,7 @@ static cpumask_t backtrace_mask = CPU_MA atomic_t nmi_active = ATOMIC_INIT(0); /* oprofile uses this */ unsigned int nmi_watchdog = NMI_DEFAULT; -static unsigned int nmi_hz = HZ; +static unsigned int nmi_hz = 1000; static DEFINE_PER_CPU(short, wd_enabled); @@ -60,7 +62,12 @@ static int endflag __initdata = 0; */ static __init void nmi_cpu_busy(void *data) { + /* + * avoid a warning, on PREEMPT_RT this wont run in hardirq context: + */ +#ifndef CONFIG_PREEMPT_RT local_irq_enable_in_hardirq(); +#endif /* Intentionally don't use cpu_relax here. This is to make sure that the performance counter really ticks, even if there is a simulator or similar that catches the @@ -95,7 +102,7 @@ static int __init check_nmi_watchdog(voi for_each_possible_cpu(cpu) prev_nmi_count[cpu] = per_cpu(irq_stat, cpu).__nmi_count; local_irq_enable(); - mdelay((20*1000)/nmi_hz); // wait 20 ticks + mdelay((100*1000)/nmi_hz); /* wait 100 ticks */ for_each_possible_cpu(cpu) { #ifdef CONFIG_SMP @@ -319,9 +326,48 @@ EXPORT_SYMBOL(touch_nmi_watchdog); extern void die_nmi(struct pt_regs *, const char *msg); -__kprobes int nmi_watchdog_tick(struct pt_regs * regs, unsigned reason) +int nmi_show_regs[NR_CPUS]; + +void nmi_show_all_regs(void) +{ + int i; + + if (system_state == SYSTEM_BOOTING) + return; + + printk(KERN_WARNING "nmi_show_all_regs(): start on CPU#%d.\n", + raw_smp_processor_id()); + dump_stack(); + + for_each_online_cpu(i) + nmi_show_regs[i] = 1; + + smp_send_nmi_allbutself(); + + for_each_online_cpu(i) { + while (nmi_show_regs[i] == 1) + barrier(); + } +} + +static DEFINE_RAW_SPINLOCK(nmi_print_lock); + +notrace void irq_show_regs_callback(int cpu, struct pt_regs *regs) { + if (!nmi_show_regs[cpu]) + return; + + nmi_show_regs[cpu] = 0; + spin_lock(&nmi_print_lock); + printk(KERN_WARNING "NMI show regs on CPU#%d:\n", cpu); + printk(KERN_WARNING "apic_timer_irqs: %d\n", + per_cpu(irq_stat, cpu).apic_timer_irqs); + show_regs(regs); + spin_unlock(&nmi_print_lock); +} +notrace __kprobes int nmi_watchdog_tick(struct pt_regs *regs, unsigned reason) +{ /* * Since current_thread_info()-> is always on the stack, and we * always switch the stack NMI-atomically, it's safe to use @@ -332,6 +378,8 @@ __kprobes int nmi_watchdog_tick(struct p int cpu = smp_processor_id(); int rc=0; + __profile_tick(CPU_PROFILING, regs); + /* check for other users first */ if (notify_die(DIE_NMI, "nmi", regs, reason, 2, SIGINT) == NOTIFY_STOP) { @@ -344,7 +392,7 @@ __kprobes int nmi_watchdog_tick(struct p spin_lock(&lock); printk("NMI backtrace for cpu %d\n", cpu); - dump_stack(); + show_regs(regs); spin_unlock(&lock); cpu_clear(cpu, backtrace_mask); } @@ -355,6 +403,9 @@ __kprobes int nmi_watchdog_tick(struct p */ sum = per_cpu(irq_stat, cpu).apic_timer_irqs + kstat_cpu(cpu).irqs[0]; + irq_show_regs_callback(cpu, regs); + + /* if the apic timer isn't firing, this cpu isn't doing much */ /* if the none of the timers isn't firing, this cpu isn't doing much */ if (!touched && last_irq_sums[cpu] == sum) { /* @@ -362,11 +413,29 @@ __kprobes int nmi_watchdog_tick(struct p * wait a few IRQs (5 seconds) before doing the oops ... */ alert_counter[cpu]++; - if (alert_counter[cpu] == 5*nmi_hz) - /* - * die_nmi will return ONLY if NOTIFY_STOP happens.. - */ - die_nmi(regs, "BUG: NMI Watchdog detected LOCKUP"); + if (alert_counter[cpu] && !(alert_counter[cpu] % (5*nmi_hz))) { + int i; + + spin_lock(&nmi_print_lock); + printk(KERN_WARNING "NMI watchdog detected lockup on " + "CPU#%d (%d/%d)\n", cpu, alert_counter[cpu], + 5*nmi_hz); + show_regs(regs); + spin_unlock(&nmi_print_lock); + + for_each_online_cpu(i) { + if (i == cpu) + continue; + nmi_show_regs[i] = 1; + while (nmi_show_regs[i] == 1) + cpu_relax(); + } + printk(KERN_WARNING "NMI watchdog running again ...\n"); + for_each_online_cpu(i) + alert_counter[i] = 0; + + } + } else { last_irq_sums[cpu] = sum; alert_counter[cpu] = 0; @@ -464,5 +533,15 @@ void __trigger_all_cpu_backtrace(void) } } +void smp_send_nmi_allbutself(void) +{ +#ifdef CONFIG_SMP + cpumask_t mask = cpu_online_map; + cpu_clear(safe_smp_processor_id(), mask); + if (!cpus_empty(mask)) + send_IPI_mask(mask, NMI_VECTOR); +#endif +} + EXPORT_SYMBOL(nmi_active); EXPORT_SYMBOL(nmi_watchdog); Index: linux-rt-rebase.q/arch/i386/kernel/paravirt.c =================================================================== --- linux-rt-rebase.q.orig/arch/i386/kernel/paravirt.c +++ linux-rt-rebase.q/arch/i386/kernel/paravirt.c @@ -208,7 +208,7 @@ void init_IRQ(void) paravirt_ops.init_IRQ(); } -static void native_flush_tlb(void) +static fastcall void native_flush_tlb(void) { __native_flush_tlb(); } @@ -217,12 +217,12 @@ static void native_flush_tlb(void) * Global pages have to be flushed a bit differently. Not a real * performance problem because this does not happen often. */ -static void native_flush_tlb_global(void) +static fastcall void native_flush_tlb_global(void) { __native_flush_tlb_global(); } -static void native_flush_tlb_single(unsigned long addr) +static fastcall void native_flush_tlb_single(unsigned long addr) { __native_flush_tlb_single(addr); } @@ -273,6 +273,16 @@ int paravirt_disable_iospace(void) return ret; } +#ifdef CONFIG_HIGHPTE +/* + * kmap_atomic() might be an inline or a macro: + */ +static void *kmap_atomic_func(struct page *page, enum km_type idx) +{ + return kmap_atomic(page, idx); +} +#endif + struct paravirt_ops paravirt_ops = { .name = "bare hardware", .paravirt_enabled = 0, @@ -361,7 +371,7 @@ struct paravirt_ops paravirt_ops = { .pte_update_defer = paravirt_nop, #ifdef CONFIG_HIGHPTE - .kmap_atomic_pte = kmap_atomic, + .kmap_atomic_pte = kmap_atomic_func, #endif #ifdef CONFIG_X86_PAE Index: linux-rt-rebase.q/arch/i386/kernel/process.c =================================================================== --- linux-rt-rebase.q.orig/arch/i386/kernel/process.c +++ linux-rt-rebase.q/arch/i386/kernel/process.c @@ -115,7 +115,7 @@ void default_idle(void) smp_mb(); local_irq_disable(); - if (!need_resched()) + if (!need_resched() && !need_resched_delayed()) safe_halt(); /* enables interrupts racelessly */ else local_irq_enable(); @@ -136,7 +136,9 @@ EXPORT_SYMBOL(default_idle); */ static void poll_idle (void) { - cpu_relax(); + do { + cpu_relax(); + } while (!need_resched() && !need_resched_delayed()); } #ifdef CONFIG_HOTPLUG_CPU @@ -179,14 +181,13 @@ void cpu_idle(void) /* endless idle loop with no priority at all */ while (1) { - tick_nohz_stop_sched_tick(); - while (!need_resched()) { + while (!need_resched() && !need_resched_delayed()) { void (*idle)(void); if (__get_cpu_var(cpu_idle_state)) __get_cpu_var(cpu_idle_state) = 0; - check_pgt_cache(); + tick_nohz_stop_sched_tick(); rmb(); idle = pm_idle; @@ -199,10 +200,14 @@ void cpu_idle(void) __get_cpu_var(irq_stat).idle_timestamp = jiffies; idle(); } + local_irq_disable(); + trace_preempt_exit_idle(); tick_nohz_restart_sched_tick(); - preempt_enable_no_resched(); - schedule(); + __preempt_enable_no_resched(); + __schedule(); preempt_disable(); + trace_preempt_enter_idle(); + local_irq_enable(); } } @@ -248,10 +253,10 @@ EXPORT_SYMBOL_GPL(cpu_idle_wait); */ void mwait_idle_with_hints(unsigned long eax, unsigned long ecx) { - if (!need_resched()) { + if (!need_resched() && !need_resched_delayed()) { __monitor((void *)¤t_thread_info()->flags, 0, 0); smp_mb(); - if (!need_resched()) + if (!need_resched() && !need_resched_delayed()) __mwait(eax, ecx); } } @@ -380,15 +385,23 @@ void exit_thread(void) if (unlikely(test_thread_flag(TIF_IO_BITMAP))) { struct task_struct *tsk = current; struct thread_struct *t = &tsk->thread; - int cpu = get_cpu(); - struct tss_struct *tss = &per_cpu(init_tss, cpu); + void *io_bitmap_ptr = t->io_bitmap_ptr; + int cpu; + struct tss_struct *tss; - kfree(t->io_bitmap_ptr); + /* + * On PREEMPT_RT we must not call kfree() with + * preemption disabled, so we first zap the pointer: + */ t->io_bitmap_ptr = NULL; + kfree(io_bitmap_ptr); + clear_thread_flag(TIF_IO_BITMAP); /* * Careful, clear this in the TSS too: */ + cpu = get_cpu(); + tss = &per_cpu(init_tss, cpu); memset(tss->io_bitmap, 0xff, tss->io_bitmap_max); t->io_bitmap_max = 0; tss->io_bitmap_owner = NULL; Index: linux-rt-rebase.q/arch/i386/kernel/quirks.c =================================================================== --- linux-rt-rebase.q.orig/arch/i386/kernel/quirks.c +++ linux-rt-rebase.q/arch/i386/kernel/quirks.c @@ -4,6 +4,8 @@ #include #include +#include + #if defined(CONFIG_X86_IO_APIC) && defined(CONFIG_SMP) && defined(CONFIG_PCI) static void __devinit quirk_intel_irqbalance(struct pci_dev *dev) @@ -47,3 +49,280 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_IN DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_E7525_MCH, quirk_intel_irqbalance); DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_E7520_MCH, quirk_intel_irqbalance); #endif + +#if defined(CONFIG_HPET_TIMER) +unsigned long force_hpet_address; + +static enum { + NONE_FORCE_HPET_RESUME, + OLD_ICH_FORCE_HPET_RESUME, + ICH_FORCE_HPET_RESUME, + VT8237_FORCE_HPET_RESUME +} force_hpet_resume_type; + +static void __iomem *rcba_base; + +static void ich_force_hpet_resume(void) +{ + u32 val; + + if (!force_hpet_address) + return; + + if (rcba_base == NULL) + BUG(); + + /* read the Function Disable register, dword mode only */ + val = readl(rcba_base + 0x3404); + if (!(val & 0x80)) { + /* HPET disabled in HPTC. Trying to enable */ + writel(val | 0x80, rcba_base + 0x3404); + } + + val = readl(rcba_base + 0x3404); + if (!(val & 0x80)) + BUG(); + else + printk(KERN_DEBUG "Force enabled HPET at resume\n"); + + return; +} + +static void ich_force_enable_hpet(struct pci_dev *dev) +{ + u32 val; + u32 uninitialized_var(rcba); + int err = 0; + + if (hpet_address || force_hpet_address) + return; + + pci_read_config_dword(dev, 0xF0, &rcba); + rcba &= 0xFFFFC000; + if (rcba == 0) { + printk(KERN_DEBUG "RCBA disabled. Cannot force enable HPET\n"); + return; + } + + /* use bits 31:14, 16 kB aligned */ + rcba_base = ioremap_nocache(rcba, 0x4000); + if (rcba_base == NULL) { + printk(KERN_DEBUG "ioremap failed. Cannot force enable HPET\n"); + return; + } + + /* read the Function Disable register, dword mode only */ + val = readl(rcba_base + 0x3404); + + if (val & 0x80) { + /* HPET is enabled in HPTC. Just not reported by BIOS */ + val = val & 0x3; + force_hpet_address = 0xFED00000 | (val << 12); + printk(KERN_DEBUG "Force enabled HPET at base address 0x%lx\n", + force_hpet_address); + iounmap(rcba_base); + return; + } + + /* HPET disabled in HPTC. Trying to enable */ + writel(val | 0x80, rcba_base + 0x3404); + + val = readl(rcba_base + 0x3404); + if (!(val & 0x80)) { + err = 1; + } else { + val = val & 0x3; + force_hpet_address = 0xFED00000 | (val << 12); + } + + if (err) { + force_hpet_address = 0; + iounmap(rcba_base); + printk(KERN_DEBUG "Failed to force enable HPET\n"); + } else { + force_hpet_resume_type = ICH_FORCE_HPET_RESUME; + printk(KERN_DEBUG "Force enabled HPET at base address 0x%lx\n", + force_hpet_address); + } +} + +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ESB2_0, + ich_force_enable_hpet); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ICH6_1, + ich_force_enable_hpet); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ICH7_0, + ich_force_enable_hpet); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ICH7_1, + ich_force_enable_hpet); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ICH7_31, + ich_force_enable_hpet); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ICH8_1, + ich_force_enable_hpet); + + +static struct pci_dev *cached_dev; + +static void old_ich_force_hpet_resume(void) +{ + u32 val; + u32 uninitialized_var(gen_cntl); + + if (!force_hpet_address || !cached_dev) + return; + + pci_read_config_dword(cached_dev, 0xD0, &gen_cntl); + gen_cntl &= (~(0x7 << 15)); + gen_cntl |= (0x4 << 15); + + pci_write_config_dword(cached_dev, 0xD0, gen_cntl); + pci_read_config_dword(cached_dev, 0xD0, &gen_cntl); + val = gen_cntl >> 15; + val &= 0x7; + if (val == 0x4) + printk(KERN_DEBUG "Force enabled HPET at resume\n"); + else + BUG(); +} + +static void old_ich_force_enable_hpet(struct pci_dev *dev) +{ + u32 val; + u32 uninitialized_var(gen_cntl); + + if (hpet_address || force_hpet_address) + return; + + pci_read_config_dword(dev, 0xD0, &gen_cntl); + /* + * Bit 17 is HPET enable bit. + * Bit 16:15 control the HPET base address. + */ + val = gen_cntl >> 15; + val &= 0x7; + if (val & 0x4) { + val &= 0x3; + force_hpet_address = 0xFED00000 | (val << 12); + printk(KERN_DEBUG "HPET at base address 0x%lx\n", + force_hpet_address); + return; + } + + /* + * HPET is disabled. Trying enabling at FED00000 and check + * whether it sticks + */ + gen_cntl &= (~(0x7 << 15)); + gen_cntl |= (0x4 << 15); + pci_write_config_dword(dev, 0xD0, gen_cntl); + + pci_read_config_dword(dev, 0xD0, &gen_cntl); + + val = gen_cntl >> 15; + val &= 0x7; + if (val & 0x4) { + /* HPET is enabled in HPTC. Just not reported by BIOS */ + val &= 0x3; + force_hpet_address = 0xFED00000 | (val << 12); + printk(KERN_DEBUG "Force enabled HPET at base address 0x%lx\n", + force_hpet_address); + cached_dev = dev; + force_hpet_resume_type = OLD_ICH_FORCE_HPET_RESUME; + return; + } + + printk(KERN_DEBUG "Failed to force enable HPET\n"); +} + +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82801CA_0, + old_ich_force_enable_hpet); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82801CA_12, + old_ich_force_enable_hpet); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82801DB_0, + old_ich_force_enable_hpet); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82801DB_12, + old_ich_force_enable_hpet); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82801EB_0, + old_ich_force_enable_hpet); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82801EB_12, + old_ich_force_enable_hpet); + + +static void vt8237_force_hpet_resume(void) +{ + u32 val; + + if (!force_hpet_address || !cached_dev) + return; + + val = 0xfed00000 | 0x80; + pci_write_config_dword(cached_dev, 0x68, val); + + pci_read_config_dword(cached_dev, 0x68, &val); + if (val & 0x80) + printk(KERN_DEBUG "Force enabled HPET at resume\n"); + else + BUG(); +} + +static void vt8237_force_enable_hpet(struct pci_dev *dev) +{ + u32 val; + + if (hpet_address || force_hpet_address) + return; + + pci_read_config_dword(dev, 0x68, &val); + /* + * Bit 7 is HPET enable bit. + * Bit 31:10 is HPET base address (contrary to what datasheet claims) + */ + if (val & 0x80) { + force_hpet_address = (val & ~0x3ff); + printk(KERN_DEBUG "HPET at base address 0x%lx\n", + force_hpet_address); + return; + } + + /* + * HPET is disabled. Trying enabling at FED00000 and check + * whether it sticks + */ + val = 0xfed00000 | 0x80; + pci_write_config_dword(dev, 0x68, val); + + pci_read_config_dword(dev, 0x68, &val); + if (val & 0x80) { + force_hpet_address = (val & ~0x3ff); + printk(KERN_DEBUG "Force enabled HPET at base address 0x%lx\n", + force_hpet_address); + cached_dev = dev; + force_hpet_resume_type = VT8237_FORCE_HPET_RESUME; + return; + } + + printk(KERN_DEBUG "Failed to force enable HPET\n"); +} + +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_VIA, PCI_DEVICE_ID_VIA_8235, + vt8237_force_enable_hpet); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_VIA, PCI_DEVICE_ID_VIA_8237, + vt8237_force_enable_hpet); + +void force_hpet_resume(void) +{ + switch (force_hpet_resume_type) { + case ICH_FORCE_HPET_RESUME: + return ich_force_hpet_resume(); + + case OLD_ICH_FORCE_HPET_RESUME: + return old_ich_force_hpet_resume(); + + case VT8237_FORCE_HPET_RESUME: + return vt8237_force_hpet_resume(); + + default: + break; + } +} + +#endif Index: linux-rt-rebase.q/arch/i386/kernel/setup.c =================================================================== --- linux-rt-rebase.q.orig/arch/i386/kernel/setup.c +++ linux-rt-rebase.q/arch/i386/kernel/setup.c @@ -422,7 +422,7 @@ void __init setup_bootmem_allocator(void */ reserve_bootmem(PAGE_SIZE, PAGE_SIZE); #endif -#ifdef CONFIG_ACPI_SLEEP +#ifdef CONFIG_ACPI /* * Reserve low memory region for sleep support. */ Index: linux-rt-rebase.q/arch/i386/kernel/signal.c =================================================================== --- linux-rt-rebase.q.orig/arch/i386/kernel/signal.c +++ linux-rt-rebase.q/arch/i386/kernel/signal.c @@ -540,6 +540,13 @@ handle_signal(unsigned long sig, siginfo } } +#ifdef CONFIG_PREEMPT_RT + /* + * Fully-preemptible kernel does not need interrupts disabled: + */ + local_irq_enable(); + preempt_check_resched(); +#endif /* * If TF is set due to a debugger (PT_DTRACE), clear the TF flag so * that register information in the sigcontext is correct. @@ -580,6 +587,13 @@ static void fastcall do_signal(struct pt struct k_sigaction ka; sigset_t *oldset; +#ifdef CONFIG_PREEMPT_RT + /* + * Fully-preemptible kernel does not need interrupts disabled: + */ + local_irq_enable(); + preempt_check_resched(); +#endif /* * We want the common case to go fast, which * is why we may in certain cases get here from Index: linux-rt-rebase.q/arch/i386/kernel/smp.c =================================================================== --- linux-rt-rebase.q.orig/arch/i386/kernel/smp.c +++ linux-rt-rebase.q/arch/i386/kernel/smp.c @@ -18,6 +18,7 @@ #include #include #include +#include #include #include @@ -247,7 +248,7 @@ void send_IPI_mask_sequence(cpumask_t ma static cpumask_t flush_cpumask; static struct mm_struct * flush_mm; static unsigned long flush_va; -static DEFINE_SPINLOCK(tlbstate_lock); +static DEFINE_RAW_SPINLOCK(tlbstate_lock); /* * We cannot call mmdrop() because we are in interrupt context, @@ -344,8 +345,9 @@ out: put_cpu_no_resched(); } -void native_flush_tlb_others(const cpumask_t *cpumaskp, struct mm_struct *mm, - unsigned long va) +void fastcall +native_flush_tlb_others(const cpumask_t *cpumaskp, struct mm_struct *mm, + unsigned long va) { cpumask_t cpumask = *cpumaskp; @@ -470,15 +472,34 @@ void flush_tlb_all(void) */ static void native_smp_send_reschedule(int cpu) { + trace_special(cpu, 0, 0); WARN_ON(cpu_is_offline(cpu)); send_IPI_mask(cpumask_of_cpu(cpu), RESCHEDULE_VECTOR); } /* + * this function sends a 'reschedule' IPI to all other CPUs. + * This is used when RT tasks are starving and other CPUs + * might be able to run them: + */ +void smp_send_reschedule_allbutself(void) +{ + send_IPI_allbutself(RESCHEDULE_VECTOR); +} + +void smp_send_reschedule_allbutself_cpumask(cpumask_t mask) +{ + cpu_clear(smp_processor_id(), mask); + cpus_and(mask, mask, cpu_online_map); + if (!cpus_empty(mask)) + send_IPI_mask(mask, RESCHEDULE_VECTOR); +} + +/* * Structure and data for smp_call_function(). This is designed to minimise * static memory requirements. It also looks cleaner. */ -static DEFINE_SPINLOCK(call_lock); +static DEFINE_RAW_SPINLOCK(call_lock); struct call_data_struct { void (*func) (void *info); @@ -633,13 +654,14 @@ static void native_smp_send_stop(void) } /* - * Reschedule call back. Nothing to do, - * all the work is done automatically when - * we return from the interrupt. + * Reschedule call back. Trigger a reschedule pass so that + * RT-overload balancing can pass tasks around. */ -fastcall void smp_reschedule_interrupt(struct pt_regs *regs) +fastcall notrace void smp_reschedule_interrupt(struct pt_regs *regs) { + trace_special(regs->eip, 0, 0); ack_APIC_irq(); + set_tsk_need_resched(current); } fastcall void smp_call_function_interrupt(struct pt_regs *regs) Index: linux-rt-rebase.q/arch/i386/kernel/time.c =================================================================== --- linux-rt-rebase.q.orig/arch/i386/kernel/time.c +++ linux-rt-rebase.q/arch/i386/kernel/time.c @@ -124,7 +124,7 @@ static int set_rtc_mmss(unsigned long no int timer_ack; -unsigned long profile_pc(struct pt_regs *regs) +unsigned long notrace profile_pc(struct pt_regs *regs) { unsigned long pc = instruction_pointer(regs); Index: linux-rt-rebase.q/arch/i386/kernel/traps.c =================================================================== --- linux-rt-rebase.q.orig/arch/i386/kernel/traps.c +++ linux-rt-rebase.q/arch/i386/kernel/traps.c @@ -227,6 +227,7 @@ show_trace_log_lvl(struct task_struct *t { dump_trace(task, regs, stack, &print_trace_ops, log_lvl); printk("%s =======================\n", log_lvl); + print_traces(task); } void show_trace(struct task_struct *task, struct pt_regs *regs, @@ -256,8 +257,15 @@ static void show_stack_log_lvl(struct ta printk("\n%s ", log_lvl); printk("%08lx ", *stack++); } + + pause_on_oops_head(); + printk("\n%sCall Trace:\n", log_lvl); show_trace_log_lvl(task, regs, esp, log_lvl); + + pause_on_oops_tail(); + + debug_show_held_locks(task); } void show_stack(struct task_struct *task, unsigned long *esp) @@ -278,6 +286,12 @@ void dump_stack(void) EXPORT_SYMBOL(dump_stack); +#if defined(CONFIG_DEBUG_STACKOVERFLOW) && defined(CONFIG_EVENT_TRACE) +extern unsigned long worst_stack_left; +#else +# define worst_stack_left -1L +#endif + void show_registers(struct pt_regs *regs) { int i; @@ -306,8 +320,12 @@ void show_registers(struct pt_regs *regs regs->eax, regs->ebx, regs->ecx, regs->edx); printk(KERN_EMERG "esi: %08lx edi: %08lx ebp: %08lx esp: %08lx\n", regs->esi, regs->edi, regs->ebp, esp); - printk(KERN_EMERG "ds: %04x es: %04x fs: %04x gs: %04x ss: %04x\n", - regs->xds & 0xffff, regs->xes & 0xffff, regs->xfs & 0xffff, gs, ss); + + printk(KERN_EMERG "ds: %04x es: %04x fs: %04x gs: %04x ss: %04x " + " preempt:%08x\n", + regs->xds & 0xffff, regs->xes & 0xffff, regs->xfs & 0xffff, gs, + ss, preempt_count()); + printk(KERN_EMERG "Process %.*s (pid: %d, ti=%p task=%p task.ti=%p)", TASK_COMM_LEN, current->comm, current->pid, current_thread_info(), current, task_thread_info(current)); @@ -367,11 +385,11 @@ int is_valid_bugaddr(unsigned long eip) void die(const char * str, struct pt_regs * regs, long err) { static struct { - spinlock_t lock; + raw_spinlock_t lock; u32 lock_owner; int lock_owner_depth; } die = { - .lock = __SPIN_LOCK_UNLOCKED(die.lock), + .lock = RAW_SPIN_LOCK_UNLOCKED(die.lock), .lock_owner = -1, .lock_owner_depth = 0 }; @@ -478,6 +496,11 @@ static void __kprobes do_trap(int trapnr if (!user_mode(regs)) goto kernel_trap; +#ifdef CONFIG_PREEMPT_RT + local_irq_enable(); + preempt_check_resched(); +#endif + trap_signal: { /* * We want error_code and trap_no set for userspace faults and @@ -734,10 +757,11 @@ void __kprobes die_nmi(struct pt_regs *r crash_kexec(regs); } + nmi_exit(); do_exit(SIGSEGV); } -static __kprobes void default_do_nmi(struct pt_regs * regs) +static notrace __kprobes void default_do_nmi(struct pt_regs * regs) { unsigned char reason = 0; @@ -777,11 +801,12 @@ static __kprobes void default_do_nmi(str static int ignore_nmis; -fastcall __kprobes void do_nmi(struct pt_regs * regs, long error_code) +fastcall notrace __kprobes void do_nmi(struct pt_regs * regs, long error_code) { int cpu; nmi_enter(); + nmi_trace((unsigned long)do_nmi, regs->eip, regs->eflags); cpu = smp_processor_id(); Index: linux-rt-rebase.q/arch/i386/kernel/tsc.c =================================================================== --- linux-rt-rebase.q.orig/arch/i386/kernel/tsc.c +++ linux-rt-rebase.q/arch/i386/kernel/tsc.c @@ -270,7 +270,7 @@ core_initcall(cpufreq_tsc); static unsigned long current_tsc_khz = 0; -static cycle_t read_tsc(void) +static notrace cycle_t read_tsc(void) { cycle_t ret; Index: linux-rt-rebase.q/arch/i386/kernel/vm86.c =================================================================== --- linux-rt-rebase.q.orig/arch/i386/kernel/vm86.c +++ linux-rt-rebase.q/arch/i386/kernel/vm86.c @@ -137,6 +137,7 @@ struct pt_regs * fastcall save_v86_state local_irq_enable(); if (!current->thread.vm86_info) { + local_irq_disable(); printk("no vm86_info: BAD\n"); do_exit(SIGSEGV); } Index: linux-rt-rebase.q/arch/i386/lib/delay.c =================================================================== --- linux-rt-rebase.q.orig/arch/i386/lib/delay.c +++ linux-rt-rebase.q/arch/i386/lib/delay.c @@ -23,7 +23,7 @@ #endif /* simple loop based delay: */ -static void delay_loop(unsigned long loops) +static notrace void delay_loop(unsigned long loops) { int d0; @@ -38,7 +38,7 @@ static void delay_loop(unsigned long loo } /* TSC based delay: */ -static void delay_tsc(unsigned long loops) +static notrace void delay_tsc(unsigned long loops) { unsigned long bclock, now; @@ -69,7 +69,7 @@ int read_current_timer(unsigned long *ti return -1; } -void __delay(unsigned long loops) +void notrace __delay(unsigned long loops) { delay_fn(loops); } Index: linux-rt-rebase.q/arch/i386/lib/semaphore.S =================================================================== --- linux-rt-rebase.q.orig/arch/i386/lib/semaphore.S +++ linux-rt-rebase.q/arch/i386/lib/semaphore.S @@ -30,7 +30,7 @@ * value or just clobbered.. */ .section .sched.text -ENTRY(__down_failed) +ENTRY(__compat_down_failed) CFI_STARTPROC FRAME pushl %edx @@ -39,7 +39,7 @@ ENTRY(__down_failed) pushl %ecx CFI_ADJUST_CFA_OFFSET 4 CFI_REL_OFFSET ecx,0 - call __down + call __compat_down popl %ecx CFI_ADJUST_CFA_OFFSET -4 CFI_RESTORE ecx @@ -49,9 +49,9 @@ ENTRY(__down_failed) ENDFRAME ret CFI_ENDPROC - END(__down_failed) + END(__compat_down_failed) -ENTRY(__down_failed_interruptible) +ENTRY(__compat_down_failed_interruptible) CFI_STARTPROC FRAME pushl %edx @@ -60,7 +60,7 @@ ENTRY(__down_failed_interruptible) pushl %ecx CFI_ADJUST_CFA_OFFSET 4 CFI_REL_OFFSET ecx,0 - call __down_interruptible + call __compat_down_interruptible popl %ecx CFI_ADJUST_CFA_OFFSET -4 CFI_RESTORE ecx @@ -70,9 +70,9 @@ ENTRY(__down_failed_interruptible) ENDFRAME ret CFI_ENDPROC - END(__down_failed_interruptible) + END(__compat_down_failed_interruptible) -ENTRY(__down_failed_trylock) +ENTRY(__compat_down_failed_trylock) CFI_STARTPROC FRAME pushl %edx @@ -81,7 +81,7 @@ ENTRY(__down_failed_trylock) pushl %ecx CFI_ADJUST_CFA_OFFSET 4 CFI_REL_OFFSET ecx,0 - call __down_trylock + call __compat_down_trylock popl %ecx CFI_ADJUST_CFA_OFFSET -4 CFI_RESTORE ecx @@ -91,9 +91,9 @@ ENTRY(__down_failed_trylock) ENDFRAME ret CFI_ENDPROC - END(__down_failed_trylock) + END(__compat_down_failed_trylock) -ENTRY(__up_wakeup) +ENTRY(__compat_up_wakeup) CFI_STARTPROC FRAME pushl %edx @@ -102,7 +102,7 @@ ENTRY(__up_wakeup) pushl %ecx CFI_ADJUST_CFA_OFFSET 4 CFI_REL_OFFSET ecx,0 - call __up + call __compat_up popl %ecx CFI_ADJUST_CFA_OFFSET -4 CFI_RESTORE ecx @@ -112,7 +112,7 @@ ENTRY(__up_wakeup) ENDFRAME ret CFI_ENDPROC - END(__up_wakeup) + END(__compat_up_wakeup) /* * rw spinlock fallbacks Index: linux-rt-rebase.q/arch/i386/mach-default/setup.c =================================================================== --- linux-rt-rebase.q.orig/arch/i386/mach-default/setup.c +++ linux-rt-rebase.q/arch/i386/mach-default/setup.c @@ -35,7 +35,7 @@ void __init pre_intr_init_hook(void) /* * IRQ2 is cascade interrupt to second interrupt controller */ -static struct irqaction irq2 = { no_action, 0, CPU_MASK_NONE, "cascade", NULL, NULL}; +static struct irqaction irq2 = { no_action, IRQF_NODELAY, CPU_MASK_NONE, "cascade", NULL, NULL}; /** * intr_init_hook - post gate setup interrupt initialisation @@ -81,7 +81,7 @@ void __init trap_init_hook(void) static struct irqaction irq0 = { .handler = timer_interrupt, - .flags = IRQF_DISABLED | IRQF_NOBALANCING | IRQF_IRQPOLL, + .flags = IRQF_DISABLED | IRQF_NOBALANCING | IRQF_IRQPOLL | IRQF_NODELAY, .mask = CPU_MASK_NONE, .name = "timer" }; Index: linux-rt-rebase.q/arch/i386/mach-visws/visws_apic.c =================================================================== --- linux-rt-rebase.q.orig/arch/i386/mach-visws/visws_apic.c +++ linux-rt-rebase.q/arch/i386/mach-visws/visws_apic.c @@ -257,11 +257,13 @@ out_unlock: static struct irqaction master_action = { .handler = piix4_master_intr, .name = "PIIX4-8259", + .flags = IRQF_NODELAY, }; static struct irqaction cascade_action = { .handler = no_action, .name = "cascade", + .flags = IRQF_NODELAY, }; Index: linux-rt-rebase.q/arch/i386/mach-voyager/setup.c =================================================================== --- linux-rt-rebase.q.orig/arch/i386/mach-voyager/setup.c +++ linux-rt-rebase.q/arch/i386/mach-voyager/setup.c @@ -18,7 +18,7 @@ void __init pre_intr_init_hook(void) /* * IRQ2 is cascade interrupt to second interrupt controller */ -static struct irqaction irq2 = { no_action, 0, CPU_MASK_NONE, "cascade", NULL, NULL}; +static struct irqaction irq2 = { no_action, IRQF_NODELAY, CPU_MASK_NONE, "cascade", NULL, NULL}; void __init intr_init_hook(void) { @@ -42,7 +42,7 @@ void __init trap_init_hook(void) static struct irqaction irq0 = { .handler = timer_interrupt, - .flags = IRQF_DISABLED | IRQF_NOBALANCING | IRQF_IRQPOLL, + .flags = IRQF_DISABLED | IRQF_NOBALANCING | IRQF_IRQPOLL | IRQF_NODELAY, .mask = CPU_MASK_NONE, .name = "timer" }; Index: linux-rt-rebase.q/arch/i386/mm/fault.c =================================================================== --- linux-rt-rebase.q.orig/arch/i386/mm/fault.c +++ linux-rt-rebase.q/arch/i386/mm/fault.c @@ -297,8 +297,8 @@ int show_unhandled_signals = 1; * bit 3 == 1 means use of reserved bit detected * bit 4 == 1 means fault was an instruction fetch */ -fastcall void __kprobes do_page_fault(struct pt_regs *regs, - unsigned long error_code) +fastcall notrace void __kprobes do_page_fault(struct pt_regs *regs, + unsigned long error_code) { struct task_struct *tsk; struct mm_struct *mm; @@ -309,6 +309,7 @@ fastcall void __kprobes do_page_fault(st /* get the address */ address = read_cr2(); + trace_special(regs->eip, error_code, address); tsk = current; @@ -353,7 +354,7 @@ fastcall void __kprobes do_page_fault(st * If we're in an interrupt, have no user context or are running in an * atomic region then we must not take the fault.. */ - if (in_atomic() || !mm) + if (in_atomic() || !mm || current->pagefault_disabled) goto bad_area_nosemaphore; /* When running in the kernel we expect faults to occur only to @@ -497,6 +498,9 @@ bad_area_nosemaphore: nr = (address - idt_descr.address) >> 3; if (nr == 6) { + stop_trace(); + user_trace_stop(); + zap_rt_locks(); do_invalid_op(regs, 0); return; } Index: linux-rt-rebase.q/arch/i386/mm/highmem.c =================================================================== --- linux-rt-rebase.q.orig/arch/i386/mm/highmem.c +++ linux-rt-rebase.q/arch/i386/mm/highmem.c @@ -3,9 +3,9 @@ void *kmap(struct page *page) { - might_sleep(); if (!PageHighMem(page)) return page_address(page); + might_sleep(); return kmap_high(page); } @@ -18,6 +18,26 @@ void kunmap(struct page *page) kunmap_high(page); } +void kunmap_virt(void *ptr) +{ + struct page *page; + + if ((unsigned long)ptr < PKMAP_ADDR(0)) + return; + page = pte_page(pkmap_page_table[PKMAP_NR((unsigned long)ptr)]); + kunmap(page); +} + +struct page *kmap_to_page(void *ptr) +{ + struct page *page; + + if ((unsigned long)ptr < PKMAP_ADDR(0)) + return virt_to_page(ptr); + page = pte_page(pkmap_page_table[PKMAP_NR((unsigned long)ptr)]); + return page; +} + /* * kmap_atomic/kunmap_atomic is significantly faster than kmap/kunmap because * no global lock is needed and because the kmap code must perform a global TLB @@ -26,16 +46,16 @@ void kunmap(struct page *page) * However when holding an atomic kmap is is not legal to sleep, so atomic * kmaps are appropriate for short, tight code paths only. */ -void *kmap_atomic_prot(struct page *page, enum km_type type, pgprot_t prot) +void *__kmap_atomic_prot(struct page *page, enum km_type type, pgprot_t prot) { enum fixed_addresses idx; unsigned long vaddr; - /* even !CONFIG_PREEMPT needs this, for in_atomic in do_page_fault */ + preempt_disable(); pagefault_disable(); idx = type + KM_TYPE_NR*smp_processor_id(); - BUG_ON(!pte_none(*(kmap_pte-idx))); + WARN_ON_ONCE(!pte_none(*(kmap_pte-idx))); if (!PageHighMem(page)) return page_address(page); @@ -47,12 +67,12 @@ void *kmap_atomic_prot(struct page *page return (void*) vaddr; } -void *kmap_atomic(struct page *page, enum km_type type) +void *__kmap_atomic(struct page *page, enum km_type type) { return kmap_atomic_prot(page, type, kmap_prot); } -void kunmap_atomic(void *kvaddr, enum km_type type) +void __kunmap_atomic(void *kvaddr, enum km_type type) { unsigned long vaddr = (unsigned long) kvaddr & PAGE_MASK; enum fixed_addresses idx = type + KM_TYPE_NR*smp_processor_id(); @@ -74,16 +94,18 @@ void kunmap_atomic(void *kvaddr, enum km arch_flush_lazy_mmu_mode(); pagefault_enable(); + preempt_enable(); } /* This is the same as kmap_atomic() but can map memory that doesn't * have a struct page associated with it. */ -void *kmap_atomic_pfn(unsigned long pfn, enum km_type type) +void *__kmap_atomic_pfn(unsigned long pfn, enum km_type type) { enum fixed_addresses idx; unsigned long vaddr; + preempt_disable(); pagefault_disable(); idx = type + KM_TYPE_NR*smp_processor_id(); @@ -94,7 +116,7 @@ void *kmap_atomic_pfn(unsigned long pfn, return (void*) vaddr; } -struct page *kmap_atomic_to_page(void *ptr) +struct page *__kmap_atomic_to_page(void *ptr) { unsigned long idx, vaddr = (unsigned long)ptr; pte_t *pte; @@ -109,6 +131,7 @@ struct page *kmap_atomic_to_page(void *p EXPORT_SYMBOL(kmap); EXPORT_SYMBOL(kunmap); -EXPORT_SYMBOL(kmap_atomic); -EXPORT_SYMBOL(kunmap_atomic); -EXPORT_SYMBOL(kmap_atomic_to_page); +EXPORT_SYMBOL(kunmap_virt); +EXPORT_SYMBOL(__kmap_atomic); +EXPORT_SYMBOL(__kunmap_atomic); +EXPORT_SYMBOL(__kmap_atomic_to_page); Index: linux-rt-rebase.q/arch/i386/mm/init.c =================================================================== --- linux-rt-rebase.q.orig/arch/i386/mm/init.c +++ linux-rt-rebase.q/arch/i386/mm/init.c @@ -47,7 +47,7 @@ unsigned int __VMALLOC_RESERVE = 128 << 20; -DEFINE_PER_CPU(struct mmu_gather, mmu_gathers); +DEFINE_PER_CPU_LOCKED(struct mmu_gather, mmu_gathers); unsigned long highstart_pfn, highend_pfn; static int noinline do_test_wp_bit(void); @@ -193,7 +193,7 @@ static inline int page_kills_ppro(unsign return 0; } -int page_is_ram(unsigned long pagenr) +int notrace page_is_ram(unsigned long pagenr) { int i; unsigned long addr, end; @@ -432,7 +432,7 @@ static void __init pagetable_init (void) paravirt_pagetable_setup_done(pgd_base); } -#if defined(CONFIG_SOFTWARE_SUSPEND) || defined(CONFIG_ACPI_SLEEP) +#if defined(CONFIG_SOFTWARE_SUSPEND) || defined(CONFIG_ACPI) /* * Swap suspend & friends need this for resume because things like the intel-agp * driver might have split up a kernel 4MB mapping. Index: linux-rt-rebase.q/arch/i386/mm/pgtable.c =================================================================== --- linux-rt-rebase.q.orig/arch/i386/mm/pgtable.c +++ linux-rt-rebase.q/arch/i386/mm/pgtable.c @@ -208,7 +208,7 @@ void pmd_ctor(void *pmd, struct kmem_cac * vmalloc faults work because attached pagetables are never freed. * -- wli */ -DEFINE_SPINLOCK(pgd_lock); +DEFINE_RAW_SPINLOCK(pgd_lock); struct page *pgd_list; static inline void pgd_list_add(pgd_t *pgd) Index: linux-rt-rebase.q/arch/i386/oprofile/Kconfig =================================================================== --- linux-rt-rebase.q.orig/arch/i386/oprofile/Kconfig +++ linux-rt-rebase.q/arch/i386/oprofile/Kconfig @@ -15,3 +15,6 @@ config OPROFILE If unsure, say N. +config PROFILE_NMI + bool + default y Index: linux-rt-rebase.q/arch/i386/pci/Makefile =================================================================== --- linux-rt-rebase.q.orig/arch/i386/pci/Makefile +++ linux-rt-rebase.q/arch/i386/pci/Makefile @@ -4,8 +4,9 @@ obj-$(CONFIG_PCI_BIOS) += pcbios.o obj-$(CONFIG_PCI_MMCONFIG) += mmconfig.o direct.o mmconfig-shared.o obj-$(CONFIG_PCI_DIRECT) += direct.o +obj-$(CONFIG_ACPI) += acpi.o + pci-y := fixup.o -pci-$(CONFIG_ACPI) += acpi.o pci-y += legacy.o irq.o pci-$(CONFIG_X86_VISWS) := visws.o fixup.o Index: linux-rt-rebase.q/arch/i386/pci/common.c =================================================================== --- linux-rt-rebase.q.orig/arch/i386/pci/common.c +++ linux-rt-rebase.q/arch/i386/pci/common.c @@ -52,7 +52,7 @@ int pcibios_scanned; * This interrupt-safe spinlock protects all accesses to PCI * configuration space. */ -DEFINE_SPINLOCK(pci_config_lock); +DEFINE_RAW_SPINLOCK(pci_config_lock); /* * Several buggy motherboards address only 16 devices and mirror Index: linux-rt-rebase.q/arch/i386/pci/direct.c =================================================================== --- linux-rt-rebase.q.orig/arch/i386/pci/direct.c +++ linux-rt-rebase.q/arch/i386/pci/direct.c @@ -220,16 +220,23 @@ static int __init pci_check_type1(void) unsigned int tmp; int works = 0; - local_irq_save(flags); + spin_lock_irqsave(&pci_config_lock, flags); outb(0x01, 0xCFB); tmp = inl(0xCF8); outl(0x80000000, 0xCF8); - if (inl(0xCF8) == 0x80000000 && pci_sanity_check(&pci_direct_conf1)) { - works = 1; + + if (inl(0xCF8) == 0x80000000) { + spin_unlock_irqrestore(&pci_config_lock, flags); + + if (pci_sanity_check(&pci_direct_conf1)) + works = 1; + + spin_lock_irqsave(&pci_config_lock, flags); } outl(tmp, 0xCF8); - local_irq_restore(flags); + + spin_unlock_irqrestore(&pci_config_lock, flags); return works; } @@ -239,17 +246,19 @@ static int __init pci_check_type2(void) unsigned long flags; int works = 0; - local_irq_save(flags); + spin_lock_irqsave(&pci_config_lock, flags); outb(0x00, 0xCFB); outb(0x00, 0xCF8); outb(0x00, 0xCFA); - if (inb(0xCF8) == 0x00 && inb(0xCFA) == 0x00 && - pci_sanity_check(&pci_direct_conf2)) { - works = 1; - } - local_irq_restore(flags); + if (inb(0xCF8) == 0x00 && inb(0xCFA) == 0x00) { + spin_unlock_irqrestore(&pci_config_lock, flags); + + if (pci_sanity_check(&pci_direct_conf2)) + works = 1; + } else + spin_unlock_irqrestore(&pci_config_lock, flags); return works; } Index: linux-rt-rebase.q/arch/i386/pci/pci.h =================================================================== --- linux-rt-rebase.q.orig/arch/i386/pci/pci.h +++ linux-rt-rebase.q/arch/i386/pci/pci.h @@ -78,7 +78,7 @@ struct irq_routing_table { extern unsigned int pcibios_irq_mask; extern int pcibios_scanned; -extern spinlock_t pci_config_lock; +extern raw_spinlock_t pci_config_lock; extern int (*pcibios_enable_irq)(struct pci_dev *dev); extern void (*pcibios_disable_irq)(struct pci_dev *dev); Index: linux-rt-rebase.q/arch/ia64/Kconfig =================================================================== --- linux-rt-rebase.q.orig/arch/ia64/Kconfig +++ linux-rt-rebase.q/arch/ia64/Kconfig @@ -44,6 +44,7 @@ config SWIOTLB config RWSEM_XCHGADD_ALGORITHM bool + depends on !PREEMPT_RT default y config ARCH_HAS_ILOG2_U32 @@ -275,6 +276,69 @@ config SMP If you don't know what to do here, say N. + +config GENERIC_TIME + bool + default y + +config HIGH_RES_TIMERS + bool "High-Resolution Timers" + help + + POSIX timers are available by default. This option enables + high-resolution POSIX timers. With this option the resolution + is at least 1 microsecond. High resolution is not free. If + enabled this option will add a small overhead each time a + timer expires that is not on a 1/HZ tick boundary. If no such + timers are used the overhead is nil. + + This option enables two additional POSIX CLOCKS, + CLOCK_REALTIME_HR and CLOCK_MONOTONIC_HR. Note that this + option does not change the resolution of CLOCK_REALTIME or + CLOCK_MONOTONIC which remain at 1/HZ resolution. + +config HIGH_RES_RESOLUTION + int "High-Resolution-Timer resolution (nanoseconds)" + depends on HIGH_RES_TIMERS + default 1000 + help + + This sets the resolution of timers accessed with + CLOCK_REALTIME_HR and CLOCK_MONOTONIC_HR. Too + fine a resolution (small a number) will usually not + be observable due to normal system latencies. For an + 800 MHZ processor about 10,000 is the recommended maximum + (smallest number). If you don't need that sort of resolution, + higher numbers may generate less overhead. + +choice + prompt "Clock source" + depends on HIGH_RES_TIMERS + default HIGH_RES_TIMER_ITC + help + This option allows you to choose the hardware source in charge + of generating high precision interruptions on your system. + On IA-64 these are: + + + ITC Interval Time Counter 1/CPU clock + HPET High Precision Event Timer ~ (XXX:have to check the spec) + + The ITC timer is available on all the ia64 computers because + it is integrated directly into the processor. However it may not + give correct results on MP machines with processors running + at different clock rates. In this case you may want to use + the HPET if available on your machine. + + +config HIGH_RES_TIMER_ITC + bool "Interval Time Counter/ITC" + +config HIGH_RES_TIMER_HPET + bool "High Precision Event Timer/HPET" + +endchoice + config NR_CPUS int "Maximum number of CPUs (2-1024)" range 2 1024 @@ -327,17 +391,15 @@ config FORCE_CPEI_RETARGET This option it useful to enable this feature on older BIOS's as well. You can also enable this by using boot command line option force_cpei=1. -config PREEMPT - bool "Preemptible Kernel" - help - This option reduces the latency of the kernel when reacting to - real-time or interactive events by allowing a low priority process to - be preempted even if it is in kernel mode executing a system call. - This allows applications to run more reliably even when the system is - under load. +source "kernel/Kconfig.preempt" - Say Y here if you are building a kernel for a desktop, embedded - or real-time system. Say N if you are unsure. +config RWSEM_GENERIC_SPINLOCK + bool + depends on PREEMPT_RT + default y + +config PREEMPT + def_bool y if (PREEMPT_RT || PREEMPT_SOFTIRQS || PREEMPT_HARDIRQS || PREEMPT_VOLUNTARY || PREEMPT_DESKTOP) source "mm/Kconfig" Index: linux-rt-rebase.q/arch/ia64/ia32/ia32_support.c =================================================================== --- linux-rt-rebase.q.orig/arch/ia64/ia32/ia32_support.c +++ linux-rt-rebase.q/arch/ia64/ia32/ia32_support.c @@ -249,11 +249,11 @@ ia32_init (void) #if PAGE_SHIFT > IA32_PAGE_SHIFT { - extern struct kmem_cache *partial_page_cachep; + extern struct kmem_cache *ia64_partial_page_cachep; - partial_page_cachep = kmem_cache_create("partial_page_cache", - sizeof(struct partial_page), - 0, SLAB_PANIC, NULL); + ia64_partial_page_cachep = kmem_cache_create("ia64_partial_page_cache", + sizeof(struct ia64_partial_page), + 0, SLAB_PANIC, NULL); } #endif return 0; Index: linux-rt-rebase.q/arch/ia64/ia32/ia32priv.h =================================================================== --- linux-rt-rebase.q.orig/arch/ia64/ia32/ia32priv.h +++ linux-rt-rebase.q/arch/ia64/ia32/ia32priv.h @@ -25,8 +25,8 @@ * partially mapped pages provide precise accounting of which 4k sub pages * are mapped and which ones are not, thereby improving IA-32 compatibility. */ -struct partial_page { - struct partial_page *next; /* linked list, sorted by address */ +struct ia64_partial_page { + struct ia64_partial_page *next; /* linked list, sorted by address */ struct rb_node pp_rb; /* 64K is the largest "normal" page supported by ia64 ABI. So 4K*64 * should suffice.*/ @@ -34,17 +34,17 @@ struct partial_page { unsigned int base; }; -struct partial_page_list { - struct partial_page *pp_head; /* list head, points to the lowest +struct ia64_partial_page_list { + struct ia64_partial_page *pp_head; /* list head, points to the lowest * addressed partial page */ struct rb_root ppl_rb; - struct partial_page *pp_hint; /* pp_hint->next is the last + struct ia64_partial_page *pp_hint; /* pp_hint->next is the last * accessed partial page */ atomic_t pp_count; /* reference count */ }; #if PAGE_SHIFT > IA32_PAGE_SHIFT -struct partial_page_list* ia32_init_pp_list (void); +struct ia64_partial_page_list* ia32_init_pp_list (void); #else # define ia32_init_pp_list() 0 #endif Index: linux-rt-rebase.q/arch/ia64/ia32/sys_ia32.c =================================================================== --- linux-rt-rebase.q.orig/arch/ia64/ia32/sys_ia32.c +++ linux-rt-rebase.q/arch/ia64/ia32/sys_ia32.c @@ -253,17 +253,17 @@ mmap_subpage (struct file *file, unsigne return ret; } -/* SLAB cache for partial_page structures */ -struct kmem_cache *partial_page_cachep; +/* SLAB cache for ia64_partial_page structures */ +struct kmem_cache *ia64_partial_page_cachep; /* - * init partial_page_list. + * init ia64_partial_page_list. * return 0 means kmalloc fail. */ -struct partial_page_list* +struct ia64_partial_page_list* ia32_init_pp_list(void) { - struct partial_page_list *p; + struct ia64_partial_page_list *p; if ((p = kmalloc(sizeof(*p), GFP_KERNEL)) == NULL) return p; @@ -280,12 +280,12 @@ ia32_init_pp_list(void) * Else, return 0 and provide @pprev, @rb_link, @rb_parent to * be used by later __ia32_insert_pp(). */ -static struct partial_page * -__ia32_find_pp(struct partial_page_list *ppl, unsigned int start, - struct partial_page **pprev, struct rb_node ***rb_link, +static struct ia64_partial_page * +__ia32_find_pp(struct ia64_partial_page_list *ppl, unsigned int start, + struct ia64_partial_page **pprev, struct rb_node ***rb_link, struct rb_node **rb_parent) { - struct partial_page *pp; + struct ia64_partial_page *pp; struct rb_node **__rb_link, *__rb_parent, *rb_prev; pp = ppl->pp_hint; @@ -297,7 +297,7 @@ __ia32_find_pp(struct partial_page_list while (*__rb_link) { __rb_parent = *__rb_link; - pp = rb_entry(__rb_parent, struct partial_page, pp_rb); + pp = rb_entry(__rb_parent, struct ia64_partial_page, pp_rb); if (pp->base == start) { ppl->pp_hint = pp; @@ -314,7 +314,7 @@ __ia32_find_pp(struct partial_page_list *rb_parent = __rb_parent; *pprev = NULL; if (rb_prev) - *pprev = rb_entry(rb_prev, struct partial_page, pp_rb); + *pprev = rb_entry(rb_prev, struct ia64_partial_page, pp_rb); return NULL; } @@ -322,9 +322,9 @@ __ia32_find_pp(struct partial_page_list * insert @pp into @ppl. */ static void -__ia32_insert_pp(struct partial_page_list *ppl, struct partial_page *pp, - struct partial_page *prev, struct rb_node **rb_link, - struct rb_node *rb_parent) +__ia32_insert_pp(struct ia64_partial_page_list *ppl, + struct ia64_partial_page *pp, struct ia64_partial_page *prev, + struct rb_node **rb_link, struct rb_node *rb_parent) { /* link list */ if (prev) { @@ -334,7 +334,7 @@ __ia32_insert_pp(struct partial_page_lis ppl->pp_head = pp; if (rb_parent) pp->next = rb_entry(rb_parent, - struct partial_page, pp_rb); + struct ia64_partial_page, pp_rb); else pp->next = NULL; } @@ -350,8 +350,8 @@ __ia32_insert_pp(struct partial_page_lis * delete @pp from partial page list @ppl. */ static void -__ia32_delete_pp(struct partial_page_list *ppl, struct partial_page *pp, - struct partial_page *prev) +__ia32_delete_pp(struct ia64_partial_page_list *ppl, + struct ia64_partial_page *pp, struct ia64_partial_page *prev) { if (prev) { prev->next = pp->next; @@ -363,15 +363,15 @@ __ia32_delete_pp(struct partial_page_lis ppl->pp_hint = pp->next; } rb_erase(&pp->pp_rb, &ppl->ppl_rb); - kmem_cache_free(partial_page_cachep, pp); + kmem_cache_free(ia64_partial_page_cachep, pp); } -static struct partial_page * -__pp_prev(struct partial_page *pp) +static struct ia64_partial_page * +__pp_prev(struct ia64_partial_page *pp) { struct rb_node *prev = rb_prev(&pp->pp_rb); if (prev) - return rb_entry(prev, struct partial_page, pp_rb); + return rb_entry(prev, struct ia64_partial_page, pp_rb); else return NULL; } @@ -383,7 +383,7 @@ __pp_prev(struct partial_page *pp) static void __ia32_delete_pp_range(unsigned int start, unsigned int end) { - struct partial_page *pp, *prev; + struct ia64_partial_page *pp, *prev; struct rb_node **rb_link, *rb_parent; if (start >= end) @@ -401,7 +401,7 @@ __ia32_delete_pp_range(unsigned int star } while (pp && pp->base < end) { - struct partial_page *tmp = pp->next; + struct ia64_partial_page *tmp = pp->next; __ia32_delete_pp(current->thread.ppl, pp, prev); pp = tmp; } @@ -414,7 +414,7 @@ __ia32_delete_pp_range(unsigned int star static int __ia32_set_pp(unsigned int start, unsigned int end, int flags) { - struct partial_page *pp, *prev; + struct ia64_partial_page *pp, *prev; struct rb_node ** rb_link, *rb_parent; unsigned int pstart, start_bit, end_bit, i; @@ -450,8 +450,8 @@ __ia32_set_pp(unsigned int start, unsign return 0; } - /* new a partial_page */ - pp = kmem_cache_alloc(partial_page_cachep, GFP_KERNEL); + /* new a ia64_partial_page */ + pp = kmem_cache_alloc(ia64_partial_page_cachep, GFP_KERNEL); if (!pp) return -ENOMEM; pp->base = pstart; @@ -504,7 +504,7 @@ ia32_set_pp(unsigned int start, unsigned static int __ia32_unset_pp(unsigned int start, unsigned int end) { - struct partial_page *pp, *prev; + struct ia64_partial_page *pp, *prev; struct rb_node ** rb_link, *rb_parent; unsigned int pstart, start_bit, end_bit, i; struct vm_area_struct *vma; @@ -532,8 +532,8 @@ __ia32_unset_pp(unsigned int start, unsi return -ENOMEM; } - /* new a partial_page */ - pp = kmem_cache_alloc(partial_page_cachep, GFP_KERNEL); + /* new a ia64_partial_page */ + pp = kmem_cache_alloc(ia64_partial_page_cachep, GFP_KERNEL); if (!pp) return -ENOMEM; pp->base = pstart; @@ -605,7 +605,7 @@ ia32_unset_pp(unsigned int *startp, unsi static int __ia32_compare_pp(unsigned int start, unsigned int end) { - struct partial_page *pp, *prev; + struct ia64_partial_page *pp, *prev; struct rb_node ** rb_link, *rb_parent; unsigned int pstart, start_bit, end_bit, size; unsigned int first_bit, next_zero_bit; /* the first range in bitmap */ @@ -682,13 +682,13 @@ ia32_compare_pp(unsigned int *startp, un } static void -__ia32_drop_pp_list(struct partial_page_list *ppl) +__ia32_drop_pp_list(struct ia64_partial_page_list *ppl) { - struct partial_page *pp = ppl->pp_head; + struct ia64_partial_page *pp = ppl->pp_head; while (pp) { - struct partial_page *next = pp->next; - kmem_cache_free(partial_page_cachep, pp); + struct ia64_partial_page *next = pp->next; + kmem_cache_free(ia64_partial_page_cachep, pp); pp = next; } @@ -696,9 +696,9 @@ __ia32_drop_pp_list(struct partial_page_ } void -ia32_drop_partial_page_list(struct task_struct *task) +ia32_drop_ia64_partial_page_list(struct task_struct *task) { - struct partial_page_list* ppl = task->thread.ppl; + struct ia64_partial_page_list* ppl = task->thread.ppl; if (ppl && atomic_dec_and_test(&ppl->pp_count)) __ia32_drop_pp_list(ppl); @@ -708,9 +708,9 @@ ia32_drop_partial_page_list(struct task_ * Copy current->thread.ppl to ppl (already initialized). */ static int -__ia32_copy_pp_list(struct partial_page_list *ppl) +__ia32_copy_pp_list(struct ia64_partial_page_list *ppl) { - struct partial_page *pp, *tmp, *prev; + struct ia64_partial_page *pp, *tmp, *prev; struct rb_node **rb_link, *rb_parent; ppl->pp_head = NULL; @@ -721,7 +721,7 @@ __ia32_copy_pp_list(struct partial_page_ prev = NULL; for (pp = current->thread.ppl->pp_head; pp; pp = pp->next) { - tmp = kmem_cache_alloc(partial_page_cachep, GFP_KERNEL); + tmp = kmem_cache_alloc(ia64_partial_page_cachep, GFP_KERNEL); if (!tmp) return -ENOMEM; *tmp = *pp; @@ -734,7 +734,8 @@ __ia32_copy_pp_list(struct partial_page_ } int -ia32_copy_partial_page_list(struct task_struct *p, unsigned long clone_flags) +ia32_copy_ia64_partial_page_list(struct task_struct *p, + unsigned long clone_flags) { int retval = 0; Index: linux-rt-rebase.q/arch/ia64/kernel/acpi.c =================================================================== --- linux-rt-rebase.q.orig/arch/ia64/kernel/acpi.c +++ linux-rt-rebase.q/arch/ia64/kernel/acpi.c @@ -67,6 +67,8 @@ EXPORT_SYMBOL(pm_power_off); unsigned int acpi_cpei_override; unsigned int acpi_cpei_phys_cpuid; +unsigned long acpi_wakeup_address = 0; + const char __init * acpi_get_sysname(void) { @@ -986,4 +988,21 @@ int acpi_unregister_ioapic(acpi_handle h EXPORT_SYMBOL(acpi_unregister_ioapic); +/* + * acpi_save_state_mem() - save kernel state + * + * TBD when when IA64 starts to support suspend... + */ +int acpi_save_state_mem(void) { return 0; } + +/* + * acpi_restore_state() + */ +void acpi_restore_state_mem(void) {} + +/* + * do_suspend_lowlevel() + */ +void do_suspend_lowlevel(void) {} + #endif /* CONFIG_ACPI */ Index: linux-rt-rebase.q/arch/ia64/kernel/asm-offsets.c =================================================================== --- linux-rt-rebase.q.orig/arch/ia64/kernel/asm-offsets.c +++ linux-rt-rebase.q/arch/ia64/kernel/asm-offsets.c @@ -257,6 +257,7 @@ void foo(void) offsetof (struct pal_min_state_area_s, pmsa_xip)); BLANK(); +#ifdef CONFIG_TIME_INTERPOLATION /* used by fsys_gettimeofday in arch/ia64/kernel/fsys.S */ DEFINE(IA64_GTOD_LOCK_OFFSET, offsetof (struct fsyscall_gtod_data_t, lock)); @@ -278,4 +279,5 @@ void foo(void) offsetof (struct itc_jitter_data_t, itc_jitter)); DEFINE(IA64_ITC_LASTCYCLE_OFFSET, offsetof (struct itc_jitter_data_t, itc_lastcycle)); +#endif } Index: linux-rt-rebase.q/arch/ia64/kernel/entry.S =================================================================== --- linux-rt-rebase.q.orig/arch/ia64/kernel/entry.S +++ linux-rt-rebase.q/arch/ia64/kernel/entry.S @@ -1098,23 +1098,24 @@ skip_rbs_switch: st8 [r2]=r8 st8 [r3]=r10 .work_pending: - tbit.z p6,p0=r31,TIF_NEED_RESCHED // current_thread_info()->need_resched==0? + tbit.nz p6,p0=r31,TIF_NEED_RESCHED // current_thread_info()->need_resched==0? +(p6) br.cond.sptk.few .needresched + tbit.z p6,p0=r31,TIF_NEED_RESCHED_DELAYED // current_thread_info()->need_resched_delayed==0? (p6) br.cond.sptk.few .notify -#ifdef CONFIG_PREEMPT -(pKStk) dep r21=-1,r0,PREEMPT_ACTIVE_BIT,1 + +.needresched: + +(pKStk) br.cond.sptk.many .fromkernel ;; -(pKStk) st4 [r20]=r21 ssm psr.i // enable interrupts -#endif br.call.spnt.many rp=schedule -.ret9: cmp.eq p6,p0=r0,r0 // p6 <- 1 - rsm psr.i // disable interrupts - ;; -#ifdef CONFIG_PREEMPT -(pKStk) adds r20=TI_PRE_COUNT+IA64_TASK_SIZE,r13 +.ret9a: rsm psr.i // disable interrupts ;; -(pKStk) st4 [r20]=r0 // preempt_count() <- 0 -#endif + br.cond.sptk.many .endpreemptdep +.fromkernel: + br.call.spnt.many rp=preempt_schedule_irq +.ret9b: rsm psr.i // disable interrupts +.endpreemptdep: (pLvSys)br.cond.sptk.few .work_pending_syscall_end br.cond.sptk.many .work_processed_kernel // re-check Index: linux-rt-rebase.q/arch/ia64/kernel/fsys.S =================================================================== --- linux-rt-rebase.q.orig/arch/ia64/kernel/fsys.S +++ linux-rt-rebase.q/arch/ia64/kernel/fsys.S @@ -26,6 +26,7 @@ #include "entry.h" +#ifdef CONFIG_TIME_INTERPOLATION /* * See Documentation/ia64/fsys.txt for details on fsyscalls. * @@ -349,6 +350,26 @@ ENTRY(fsys_clock_gettime) br.many .gettime END(fsys_clock_gettime) + +#else // !CONFIG_TIME_INTERPOLATION + +# define fsys_gettimeofday 0 +# define fsys_clock_gettime 0 + +.fail_einval: + mov r8 = EINVAL + mov r10 = -1 + FSYS_RETURN + +.fail_efault: + mov r8 = EFAULT + mov r10 = -1 + FSYS_RETURN + +#endif + + + /* * long fsys_rt_sigprocmask (int how, sigset_t *set, sigset_t *oset, size_t sigsetsize). */ Index: linux-rt-rebase.q/arch/ia64/kernel/head.S =================================================================== --- linux-rt-rebase.q.orig/arch/ia64/kernel/head.S +++ linux-rt-rebase.q/arch/ia64/kernel/head.S @@ -178,7 +178,7 @@ swapper_pg_dir: halt_msg: stringz "Halting kernel\n" - .text + .section .text.head,"ax" .global start_ap @@ -392,6 +392,8 @@ self: hint @pause br.sptk.many self // endless loop END(_start) + .text + GLOBAL_ENTRY(ia64_save_debug_regs) alloc r16=ar.pfs,1,0,0,0 mov r20=ar.lc // preserve ar.lc Index: linux-rt-rebase.q/arch/ia64/kernel/iosapic.c =================================================================== --- linux-rt-rebase.q.orig/arch/ia64/kernel/iosapic.c +++ linux-rt-rebase.q/arch/ia64/kernel/iosapic.c @@ -111,7 +111,7 @@ (PAGE_SIZE / sizeof(struct iosapic_rte_info)) #define RTE_PREALLOCATED (1) -static DEFINE_SPINLOCK(iosapic_lock); +static DEFINE_RAW_SPINLOCK(iosapic_lock); /* * These tables map IA-64 vectors to the IOSAPIC pin that generates this @@ -403,6 +403,34 @@ iosapic_startup_level_irq (unsigned int return 0; } +/* + * In the preemptible case mask the IRQ first then handle it and ack it. + */ +#ifdef CONFIG_PREEMPT_HARDIRQS + +static void +iosapic_ack_level_irq (unsigned int irq) +{ + ia64_vector vec = irq_to_vector(irq); + struct iosapic_rte_info *rte; + + move_irq(irq); + mask_irq(irq); + list_for_each_entry(rte, &iosapic_intr_info[vec].rtes, rte_list) + iosapic_eoi(rte->addr, vec); +} + +static void +iosapic_end_level_irq (unsigned int irq) +{ + if (!(irq_desc[irq].status & IRQ_INPROGRESS)) + unmask_irq(irq); +} + +#else /* !CONFIG_PREEMPT_HARDIRQS */ + +#define iosapic_ack_level_irq nop + static void iosapic_end_level_irq (unsigned int irq) { @@ -424,10 +452,12 @@ iosapic_end_level_irq (unsigned int irq) } } + +#endif + #define iosapic_shutdown_level_irq mask_irq #define iosapic_enable_level_irq unmask_irq #define iosapic_disable_level_irq mask_irq -#define iosapic_ack_level_irq nop struct irq_chip irq_type_iosapic_level = { .name = "IO-SAPIC-level", Index: linux-rt-rebase.q/arch/ia64/kernel/irq_ia64.c =================================================================== --- linux-rt-rebase.q.orig/arch/ia64/kernel/irq_ia64.c +++ linux-rt-rebase.q/arch/ia64/kernel/irq_ia64.c @@ -85,8 +85,8 @@ DEFINE_PER_CPU(int[IA64_NUM_VECTORS], ve [0 ... IA64_NUM_VECTORS - 1] = IA64_SPURIOUS_INT_VECTOR }; -static cpumask_t vector_table[IA64_MAX_DEVICE_VECTORS] = { - [0 ... IA64_MAX_DEVICE_VECTORS - 1] = CPU_MASK_NONE +static cpumask_t vector_table[IA64_NUM_VECTORS] = { + [0 ... IA64_NUM_VECTORS - 1] = CPU_MASK_NONE }; static int irq_status[NR_IRQS] = { @@ -123,17 +123,18 @@ static inline int find_unassigned_irq(vo static inline int find_unassigned_vector(cpumask_t domain) { cpumask_t mask; - int pos; + int pos, vector; cpus_and(mask, domain, cpu_online_map); if (cpus_empty(mask)) return -EINVAL; for (pos = 0; pos < IA64_NUM_DEVICE_VECTORS; pos++) { - cpus_and(mask, domain, vector_table[pos]); + vector = IA64_FIRST_DEVICE_VECTOR + pos; + cpus_and(mask, domain, vector_table[vector]); if (!cpus_empty(mask)) continue; - return IA64_FIRST_DEVICE_VECTOR + pos; + return vector; } return -ENOSPC; } @@ -141,7 +142,7 @@ static inline int find_unassigned_vector static int __bind_irq_vector(int irq, int vector, cpumask_t domain) { cpumask_t mask; - int cpu, pos; + int cpu; struct irq_cfg *cfg = &irq_cfg[irq]; cpus_and(mask, domain, cpu_online_map); @@ -156,8 +157,7 @@ static int __bind_irq_vector(int irq, in cfg->vector = vector; cfg->domain = domain; irq_status[irq] = IRQ_USED; - pos = vector - IA64_FIRST_DEVICE_VECTOR; - cpus_or(vector_table[pos], vector_table[pos], domain); + cpus_or(vector_table[vector], vector_table[vector], domain); return 0; } @@ -174,7 +174,7 @@ int bind_irq_vector(int irq, int vector, static void __clear_irq_vector(int irq) { - int vector, cpu, pos; + int vector, cpu; cpumask_t mask; cpumask_t domain; struct irq_cfg *cfg = &irq_cfg[irq]; @@ -189,8 +189,7 @@ static void __clear_irq_vector(int irq) cfg->vector = IRQ_VECTOR_UNASSIGNED; cfg->domain = CPU_MASK_NONE; irq_status[irq] = IRQ_UNUSED; - pos = vector - IA64_FIRST_DEVICE_VECTOR; - cpus_andnot(vector_table[pos], vector_table[pos], domain); + cpus_andnot(vector_table[vector], vector_table[vector], domain); } static void clear_irq_vector(int irq) @@ -212,9 +211,6 @@ assign_irq_vector (int irq) vector = -ENOSPC; spin_lock_irqsave(&vector_lock, flags); - if (irq < 0) { - goto out; - } for_each_online_cpu(cpu) { domain = vector_allocation_domain(cpu); vector = find_unassigned_vector(domain); @@ -223,6 +219,8 @@ assign_irq_vector (int irq) } if (vector < 0) goto out; + if (irq == AUTO_ASSIGN) + irq = vector; BUG_ON(__bind_irq_vector(irq, vector, domain)); out: spin_unlock_irqrestore(&vector_lock, flags); Index: linux-rt-rebase.q/arch/ia64/kernel/machvec.c =================================================================== --- linux-rt-rebase.q.orig/arch/ia64/kernel/machvec.c +++ linux-rt-rebase.q/arch/ia64/kernel/machvec.c @@ -13,14 +13,6 @@ struct ia64_machine_vector ia64_mv; EXPORT_SYMBOL(ia64_mv); -static __initdata const char *mvec_name; -static __init int setup_mvec(char *s) -{ - mvec_name = s; - return 0; -} -early_param("machvec", setup_mvec); - static struct ia64_machine_vector * __init lookup_machvec (const char *name) { @@ -41,7 +33,7 @@ machvec_init (const char *name) struct ia64_machine_vector *mv; if (!name) - name = mvec_name ? mvec_name : acpi_get_sysname(); + name = acpi_get_sysname(); mv = lookup_machvec(name); if (!mv) panic("generic kernel failed to find machine vector for" @@ -51,6 +43,23 @@ machvec_init (const char *name) printk(KERN_INFO "booting generic kernel on platform %s\n", name); } +void __init +machvec_init_from_cmdline(const char *cmdline) +{ + char str[64]; + const char *start; + char *end; + + if (! (start = strstr(cmdline, "machvec=")) ) + return machvec_init(NULL); + + strlcpy(str, start + strlen("machvec="), sizeof(str)); + if ( (end = strchr(str, ' ')) ) + *end = '\0'; + + return machvec_init(str); +} + #endif /* CONFIG_IA64_GENERIC */ void Index: linux-rt-rebase.q/arch/ia64/kernel/mca.c =================================================================== --- linux-rt-rebase.q.orig/arch/ia64/kernel/mca.c +++ linux-rt-rebase.q/arch/ia64/kernel/mca.c @@ -322,7 +322,7 @@ ia64_mca_spin(const char *func) typedef struct ia64_state_log_s { - spinlock_t isl_lock; + raw_spinlock_t isl_lock; int isl_index; unsigned long isl_count; ia64_err_rec_t *isl_log[IA64_MAX_LOGS]; /* need space to store header + error log */ Index: linux-rt-rebase.q/arch/ia64/kernel/perfmon.c =================================================================== --- linux-rt-rebase.q.orig/arch/ia64/kernel/perfmon.c +++ linux-rt-rebase.q/arch/ia64/kernel/perfmon.c @@ -280,7 +280,7 @@ typedef struct { */ typedef struct pfm_context { - spinlock_t ctx_lock; /* context protection */ + raw_spinlock_t ctx_lock; /* context protection */ pfm_context_flags_t ctx_flags; /* bitmask of flags (block reason incl.) */ unsigned int ctx_state; /* state: active/inactive (no bitfield) */ @@ -369,7 +369,7 @@ typedef struct pfm_context { * mostly used to synchronize between system wide and per-process */ typedef struct { - spinlock_t pfs_lock; /* lock the structure */ + raw_spinlock_t pfs_lock; /* lock the structure */ unsigned int pfs_task_sessions; /* number of per task sessions */ unsigned int pfs_sys_sessions; /* number of per system wide sessions */ @@ -510,7 +510,7 @@ static pfm_intr_handler_desc_t *pfm_alt static struct proc_dir_entry *perfmon_dir; static pfm_uuid_t pfm_null_uuid = {0,}; -static spinlock_t pfm_buffer_fmt_lock; +static raw_spinlock_t pfm_buffer_fmt_lock; static LIST_HEAD(pfm_buffer_fmt_list); static pmu_config_t *pmu_conf; Index: linux-rt-rebase.q/arch/ia64/kernel/process.c =================================================================== --- linux-rt-rebase.q.orig/arch/ia64/kernel/process.c +++ linux-rt-rebase.q/arch/ia64/kernel/process.c @@ -94,6 +94,9 @@ show_stack (struct task_struct *task, un void dump_stack (void) { + if (irqs_disabled()) { + printk("Uh oh.. entering dump_stack() with irqs disabled.\n"); + } show_stack(NULL, NULL); } @@ -197,7 +200,7 @@ void default_idle (void) { local_irq_enable(); - while (!need_resched()) { + while (!need_resched() && !need_resched_delayed()) { if (can_do_pal_halt) safe_halt(); else @@ -281,7 +284,7 @@ cpu_idle (void) current_thread_info()->status |= TS_POLLING; } - if (!need_resched()) { + if (!need_resched() && !need_resched_delayed()) { void (*idle)(void); #ifdef CONFIG_SMP min_xtp(); @@ -303,10 +306,11 @@ cpu_idle (void) normal_xtp(); #endif } - preempt_enable_no_resched(); - schedule(); + __preempt_enable_no_resched(); + __schedule(); + preempt_disable(); - check_pgt_cache(); + if (cpu_is_offline(cpu)) play_dead(); } @@ -499,7 +503,8 @@ copy_thread (int nr, unsigned long clone /* Copy partially mapped page list */ if (!retval) - retval = ia32_copy_partial_page_list(p, clone_flags); + retval = ia32_copy_ia64_partial_page_list(p, + clone_flags); } #endif @@ -728,7 +733,7 @@ flush_thread (void) ia64_drop_fpu(current); #ifdef CONFIG_IA32_SUPPORT if (IS_IA32_PROCESS(task_pt_regs(current))) { - ia32_drop_partial_page_list(current); + ia32_drop_ia64_partial_page_list(current); current->thread.task_size = IA32_PAGE_OFFSET; set_fs(USER_DS); } @@ -754,7 +759,7 @@ exit_thread (void) pfm_release_debug_registers(current); #endif if (IS_IA32_PROCESS(task_pt_regs(current))) - ia32_drop_partial_page_list(current); + ia32_drop_ia64_partial_page_list(current); } unsigned long Index: linux-rt-rebase.q/arch/ia64/kernel/sal.c =================================================================== --- linux-rt-rebase.q.orig/arch/ia64/kernel/sal.c +++ linux-rt-rebase.q/arch/ia64/kernel/sal.c @@ -18,7 +18,7 @@ #include #include - __cacheline_aligned DEFINE_SPINLOCK(sal_lock); + __cacheline_aligned DEFINE_RAW_SPINLOCK(sal_lock); unsigned long sal_platform_features; unsigned short sal_revision; Index: linux-rt-rebase.q/arch/ia64/kernel/salinfo.c =================================================================== --- linux-rt-rebase.q.orig/arch/ia64/kernel/salinfo.c +++ linux-rt-rebase.q/arch/ia64/kernel/salinfo.c @@ -140,7 +140,7 @@ enum salinfo_state { struct salinfo_data { cpumask_t cpu_event; /* which cpus have outstanding events */ - struct semaphore mutex; + struct compat_semaphore mutex; u8 *log_buffer; u64 log_size; u8 *oemdata; /* decoded oem data */ @@ -156,8 +156,8 @@ struct salinfo_data { static struct salinfo_data salinfo_data[ARRAY_SIZE(salinfo_log_name)]; -static DEFINE_SPINLOCK(data_lock); -static DEFINE_SPINLOCK(data_saved_lock); +static DEFINE_RAW_SPINLOCK(data_lock); +static DEFINE_RAW_SPINLOCK(data_saved_lock); /** salinfo_platform_oemdata - optional callback to decode oemdata from an error * record. Index: linux-rt-rebase.q/arch/ia64/kernel/semaphore.c =================================================================== --- linux-rt-rebase.q.orig/arch/ia64/kernel/semaphore.c +++ linux-rt-rebase.q/arch/ia64/kernel/semaphore.c @@ -40,12 +40,12 @@ */ void -__up (struct semaphore *sem) +__up (struct compat_semaphore *sem) { wake_up(&sem->wait); } -void __sched __down (struct semaphore *sem) +void __sched __down (struct compat_semaphore *sem) { struct task_struct *tsk = current; DECLARE_WAITQUEUE(wait, tsk); @@ -82,7 +82,7 @@ void __sched __down (struct semaphore *s tsk->state = TASK_RUNNING; } -int __sched __down_interruptible (struct semaphore * sem) +int __sched __down_interruptible (struct compat_semaphore * sem) { int retval = 0; struct task_struct *tsk = current; @@ -142,7 +142,7 @@ int __sched __down_interruptible (struct * count. */ int -__down_trylock (struct semaphore *sem) +__down_trylock (struct compat_semaphore *sem) { unsigned long flags; int sleepers; Index: linux-rt-rebase.q/arch/ia64/kernel/setup.c =================================================================== --- linux-rt-rebase.q.orig/arch/ia64/kernel/setup.c +++ linux-rt-rebase.q/arch/ia64/kernel/setup.c @@ -491,12 +491,17 @@ setup_arch (char **cmdline_p) efi_init(); io_port_init(); - parse_early_param(); - #ifdef CONFIG_IA64_GENERIC - machvec_init(NULL); + /* machvec needs to be parsed from the command line + * before parse_early_param() is called to ensure + * that ia64_mv is initialised before any command line + * settings may cause console setup to occur + */ + machvec_init_from_cmdline(*cmdline_p); #endif + parse_early_param(); + if (early_console_setup(*cmdline_p) == 0) mark_bsp_online(); Index: linux-rt-rebase.q/arch/ia64/kernel/signal.c =================================================================== --- linux-rt-rebase.q.orig/arch/ia64/kernel/signal.c +++ linux-rt-rebase.q/arch/ia64/kernel/signal.c @@ -446,6 +446,14 @@ ia64_do_signal (struct sigscratch *scr, long errno = scr->pt.r8; # define ERR_CODE(c) (IS_IA32_PROCESS(&scr->pt) ? -(c) : (c)) +#ifdef CONFIG_PREEMPT_RT + /* + * Fully-preemptible kernel does not need interrupts disabled: + */ + local_irq_enable(); + preempt_check_resched(); +#endif + /* * In the ia64_leave_kernel code path, we want the common case to go fast, which * is why we may in certain cases get here from kernel mode. Just return without Index: linux-rt-rebase.q/arch/ia64/kernel/smp.c =================================================================== --- linux-rt-rebase.q.orig/arch/ia64/kernel/smp.c +++ linux-rt-rebase.q/arch/ia64/kernel/smp.c @@ -261,6 +261,22 @@ smp_send_reschedule (int cpu) } /* + * this function sends a 'reschedule' IPI to all other CPUs. + * This is used when RT tasks are starving and other CPUs + * might be able to run them: + */ +void smp_send_reschedule_allbutself(void) +{ + unsigned int cpu; + + for_each_online_cpu(cpu) { + if (cpu != smp_processor_id()) + platform_send_ipi(cpu, IA64_IPI_RESCHEDULE, + IA64_IPI_DM_INT, 0); + } +} + +/* * Called with preemption disabled. */ static void @@ -468,7 +484,7 @@ smp_send_stop (void) send_IPI_allbutself(IPI_CPU_STOP); } -int __init +int setup_profiling_timer (unsigned int multiplier) { return -EINVAL; Index: linux-rt-rebase.q/arch/ia64/kernel/smpboot.c =================================================================== --- linux-rt-rebase.q.orig/arch/ia64/kernel/smpboot.c +++ linux-rt-rebase.q/arch/ia64/kernel/smpboot.c @@ -370,6 +370,8 @@ smp_setup_percpu_timer (void) { } +extern void register_itc_clockevent(void); + static void __cpuinit smp_callin (void) { @@ -448,6 +450,7 @@ smp_callin (void) #ifdef CONFIG_IA32_SUPPORT ia32_gdt_init(); #endif + register_itc_clockevent(); /* * Allow the master to continue. @@ -487,7 +490,7 @@ struct create_idle { int cpu; }; -void +void __cpuinit do_fork_idle(struct work_struct *work) { struct create_idle *c_idle = @@ -497,7 +500,7 @@ do_fork_idle(struct work_struct *work) complete(&c_idle->done); } -static int __devinit +static int __cpuinit do_boot_cpu (int sapicid, int cpu) { int timeout; @@ -808,7 +811,7 @@ set_cpu_sibling_map(int cpu) } } -int __devinit +int __cpuinit __cpu_up (unsigned int cpu) { int ret; Index: linux-rt-rebase.q/arch/ia64/kernel/time.c =================================================================== --- linux-rt-rebase.q.orig/arch/ia64/kernel/time.c +++ linux-rt-rebase.q/arch/ia64/kernel/time.c @@ -70,6 +70,7 @@ timer_interrupt (int irq, void *dev_id) platform_timer_interrupt(irq, dev_id); +#if 0 new_itm = local_cpu_data->itm_next; if (!time_after(ia64_get_itc(), new_itm)) @@ -77,29 +78,48 @@ timer_interrupt (int irq, void *dev_id) ia64_get_itc(), new_itm); profile_tick(CPU_PROFILING); +#endif + + if (time_after(ia64_get_itc(), local_cpu_data->itm_tick_next)) { - while (1) { - update_process_times(user_mode(get_irq_regs())); + unsigned long new_tick_itm; + new_tick_itm = local_cpu_data->itm_tick_next; - new_itm += local_cpu_data->itm_delta; + profile_tick(CPU_PROFILING, get_irq_regs()); - if (smp_processor_id() == time_keeper_id) { - /* - * Here we are in the timer irq handler. We have irqs locally - * disabled, but we don't know if the timer_bh is running on - * another CPU. We need to avoid to SMP race by acquiring the - * xtime_lock. - */ - write_seqlock(&xtime_lock); - do_timer(1); - local_cpu_data->itm_next = new_itm; - write_sequnlock(&xtime_lock); - } else - local_cpu_data->itm_next = new_itm; + while (1) { + update_process_times(user_mode(get_irq_regs())); + + new_tick_itm += local_cpu_data->itm_tick_delta; + + if (smp_processor_id() == time_keeper_id) { + /* + * Here we are in the timer irq handler. We have irqs locally + * disabled, but we don't know if the timer_bh is running on + * another CPU. We need to avoid to SMP race by acquiring the + * xtime_lock. + */ + write_seqlock(&xtime_lock); + do_timer(get_irq_regs()); + local_cpu_data->itm_tick_next = new_tick_itm; + write_sequnlock(&xtime_lock); + } else + local_cpu_data->itm_tick_next = new_tick_itm; + + if (time_after(new_tick_itm, ia64_get_itc())) + break; + } + } - if (time_after(new_itm, ia64_get_itc())) - break; + if (time_after(ia64_get_itc(), local_cpu_data->itm_timer_next)) { + if (itc_clockevent.event_handler) + itc_clockevent.event_handler(get_irq_regs()); + // FIXME, really, please + new_itm = local_cpu_data->itm_tick_next; + + if (time_after(new_itm, local_cpu_data->itm_timer_next)) + new_itm = local_cpu_data->itm_timer_next; /* * Allow IPIs to interrupt the timer loop. */ @@ -117,8 +137,8 @@ timer_interrupt (int irq, void *dev_id) * too fast (with the potentially devastating effect * of losing monotony of time). */ - while (!time_after(new_itm, ia64_get_itc() + local_cpu_data->itm_delta/2)) - new_itm += local_cpu_data->itm_delta; + while (!time_after(new_itm, ia64_get_itc() + local_cpu_data->itm_tick_delta/2)) + new_itm += local_cpu_data->itm_tick_delta; ia64_set_itm(new_itm); /* double check, in case we got hit by a (slow) PMI: */ } while (time_after_eq(ia64_get_itc(), new_itm)); @@ -137,7 +157,7 @@ ia64_cpu_local_tick (void) /* arrange for the cycle counter to generate a timer interrupt: */ ia64_set_itv(IA64_TIMER_VECTOR); - delta = local_cpu_data->itm_delta; + delta = local_cpu_data->itm_tick_delta; /* * Stagger the timer tick for each CPU so they don't occur all at (almost) the * same time: @@ -146,8 +166,8 @@ ia64_cpu_local_tick (void) unsigned long hi = 1UL << ia64_fls(cpu); shift = (2*(cpu - hi) + 1) * delta/hi/2; } - local_cpu_data->itm_next = ia64_get_itc() + delta + shift; - ia64_set_itm(local_cpu_data->itm_next); + local_cpu_data->itm_tick_next = ia64_get_itc() + delta + shift; + ia64_set_itm(local_cpu_data->itm_tick_next); } static int nojitter; @@ -205,7 +225,7 @@ ia64_init_itm (void) itc_freq = (platform_base_freq*itc_ratio.num)/itc_ratio.den; - local_cpu_data->itm_delta = (itc_freq + HZ/2) / HZ; + local_cpu_data->itm_tick_delta = (itc_freq + HZ/2) / HZ; printk(KERN_DEBUG "CPU %d: base freq=%lu.%03luMHz, ITC ratio=%u/%u, " "ITC freq=%lu.%03luMHz", smp_processor_id(), platform_base_freq / 1000000, (platform_base_freq / 1000) % 1000, @@ -225,6 +245,7 @@ ia64_init_itm (void) local_cpu_data->nsec_per_cyc = ((NSEC_PER_SEC<mfh = 1; } - preempt_enable_no_resched(); + __preempt_enable_no_resched(); } static inline int Index: linux-rt-rebase.q/arch/ia64/kernel/unwind.c =================================================================== --- linux-rt-rebase.q.orig/arch/ia64/kernel/unwind.c +++ linux-rt-rebase.q/arch/ia64/kernel/unwind.c @@ -82,7 +82,7 @@ typedef unsigned long unw_word; typedef unsigned char unw_hash_index_t; static struct { - spinlock_t lock; /* spinlock for unwind data */ + raw_spinlock_t lock; /* spinlock for unwind data */ /* list of unwind tables (one per load-module) */ struct unw_table *tables; @@ -146,7 +146,7 @@ static struct { # endif } unw = { .tables = &unw.kernel_table, - .lock = __SPIN_LOCK_UNLOCKED(unw.lock), + .lock = RAW_SPIN_LOCK_UNLOCKED(unw.lock), .save_order = { UNW_REG_RP, UNW_REG_PFS, UNW_REG_PSP, UNW_REG_PR, UNW_REG_UNAT, UNW_REG_LC, UNW_REG_FPSR, UNW_REG_PRI_UNAT_GR Index: linux-rt-rebase.q/arch/ia64/kernel/unwind_i.h =================================================================== --- linux-rt-rebase.q.orig/arch/ia64/kernel/unwind_i.h +++ linux-rt-rebase.q/arch/ia64/kernel/unwind_i.h @@ -154,7 +154,7 @@ struct unw_script { unsigned long ip; /* ip this script is for */ unsigned long pr_mask; /* mask of predicates script depends on */ unsigned long pr_val; /* predicate values this script is for */ - rwlock_t lock; + raw_rwlock_t lock; unsigned int flags; /* see UNW_FLAG_* in unwind.h */ unsigned short lru_chain; /* used for least-recently-used chain */ unsigned short coll_chain; /* used for hash collisions */ Index: linux-rt-rebase.q/arch/ia64/kernel/vmlinux.lds.S =================================================================== --- linux-rt-rebase.q.orig/arch/ia64/kernel/vmlinux.lds.S +++ linux-rt-rebase.q/arch/ia64/kernel/vmlinux.lds.S @@ -50,6 +50,8 @@ SECTIONS KPROBES_TEXT *(.gnu.linkonce.t*) } + .text.head : AT(ADDR(.text.head) - LOAD_OFFSET) + { *(.text.head) } .text2 : AT(ADDR(.text2) - LOAD_OFFSET) { *(.text2) } #ifdef CONFIG_SMP Index: linux-rt-rebase.q/arch/ia64/mm/init.c =================================================================== --- linux-rt-rebase.q.orig/arch/ia64/mm/init.c +++ linux-rt-rebase.q/arch/ia64/mm/init.c @@ -37,7 +37,7 @@ #include #include -DEFINE_PER_CPU(struct mmu_gather, mmu_gathers); +DEFINE_PER_CPU_LOCKED(struct mmu_gather, mmu_gathers); extern void ia64_tlb_init (void); Index: linux-rt-rebase.q/arch/ia64/mm/tlb.c =================================================================== --- linux-rt-rebase.q.orig/arch/ia64/mm/tlb.c +++ linux-rt-rebase.q/arch/ia64/mm/tlb.c @@ -32,7 +32,7 @@ static struct { } purge; struct ia64_ctx ia64_ctx = { - .lock = __SPIN_LOCK_UNLOCKED(ia64_ctx.lock), + .lock = RAW_SPIN_LOCK_UNLOCKED(ia64_ctx.lock), .next = 1, .max_ctx = ~0U }; Index: linux-rt-rebase.q/arch/ia64/pci/pci.c =================================================================== --- linux-rt-rebase.q.orig/arch/ia64/pci/pci.c +++ linux-rt-rebase.q/arch/ia64/pci/pci.c @@ -581,7 +581,7 @@ pcibios_align_resource (void *data, stru /* * PCI BIOS setup, always defaults to SAL interface */ -char * __init +char * __devinit pcibios_setup (char *str) { return str; Index: linux-rt-rebase.q/arch/m68knommu/Kconfig =================================================================== --- linux-rt-rebase.q.orig/arch/m68knommu/Kconfig +++ linux-rt-rebase.q/arch/m68knommu/Kconfig @@ -216,6 +216,18 @@ config XCOPILOT_BUGS help Support the bugs of Xcopilot. +config UC5272 + bool 'Arcturus Networks uC5272 dimm board support' + depends on M5272 + help + Support for the Arcturus Networks uC5272 dimm board. + +config UC5282 + bool "Arcturus Networks uC5282 board support" + depends on M528x + help + Support for the Arcturus Networks uC5282 dimm board. + config UCSIMM bool "uCsimm module support" depends on M68EZ328 @@ -342,6 +354,18 @@ config SOM5282EM depends on M528x help Support for the EMAC.Inc SOM5282EM module. + +config WILDFIRE + bool "Intec Automation Inc. WildFire board support" + depends on M528x + help + Support for the Intec Automation Inc. WildFire. + +config WILDFIREMOD + bool "Intec Automation Inc. WildFire module support" + depends on M528x + help + Support for the Intec Automation Inc. WildFire module. config ARN5307 bool "Arnewsh 5307 board support" Index: linux-rt-rebase.q/arch/m68knommu/Makefile =================================================================== --- linux-rt-rebase.q.orig/arch/m68knommu/Makefile +++ linux-rt-rebase.q/arch/m68knommu/Makefile @@ -26,6 +26,8 @@ platform-$(CONFIG_M5407) := 5407 PLATFORM := $(platform-y) board-$(CONFIG_PILOT) := pilot +board-$(CONFIG_UC5272) := UC5272 +board-$(CONFIG_UC5282) := UC5282 board-$(CONFIG_UCSIMM) := ucsimm board-$(CONFIG_UCDIMM) := ucdimm board-$(CONFIG_UCQUICC) := uCquicc Index: linux-rt-rebase.q/arch/m68knommu/kernel/dma.c =================================================================== --- linux-rt-rebase.q.orig/arch/m68knommu/kernel/dma.c +++ linux-rt-rebase.q/arch/m68knommu/kernel/dma.c @@ -8,6 +8,7 @@ #include #include #include +#include #include void *dma_alloc_coherent(struct device *dev, size_t size, Index: linux-rt-rebase.q/arch/m68knommu/kernel/setup.c =================================================================== --- linux-rt-rebase.q.orig/arch/m68knommu/kernel/setup.c +++ linux-rt-rebase.q/arch/m68knommu/kernel/setup.c @@ -132,6 +132,11 @@ void setup_arch(char **cmdline_p) config_BSP(&command_line[0], sizeof(command_line)); +#if defined(CONFIG_BOOTPARAM) + strncpy(&command_line[0], CONFIG_BOOTPARAM_STRING, sizeof(command_line)); + command_line[sizeof(command_line) - 1] = 0; +#endif + printk(KERN_INFO "\x0F\r\n\nuClinux/" CPU "\n"); #ifdef CONFIG_UCDIMM Index: linux-rt-rebase.q/arch/m68knommu/platform/5206/config.c =================================================================== --- linux-rt-rebase.q.orig/arch/m68knommu/platform/5206/config.c +++ linux-rt-rebase.q/arch/m68knommu/platform/5206/config.c @@ -98,14 +98,6 @@ int mcf_timerirqpending(int timer) void config_BSP(char *commandp, int size) { mcf_setimr(MCFSIM_IMR_MASKALL); - -#if defined(CONFIG_BOOTPARAM) - strncpy(commandp, CONFIG_BOOTPARAM_STRING, size); - commandp[size-1] = 0; -#else - memset(commandp, 0, size); -#endif - mach_sched_init = coldfire_timer_init; mach_tick = coldfire_tick; mach_gettimeoffset = coldfire_timer_offset; Index: linux-rt-rebase.q/arch/m68knommu/platform/5206e/config.c =================================================================== --- linux-rt-rebase.q.orig/arch/m68knommu/platform/5206e/config.c +++ linux-rt-rebase.q/arch/m68knommu/platform/5206e/config.c @@ -98,15 +98,10 @@ void config_BSP(char *commandp, int size { mcf_setimr(MCFSIM_IMR_MASKALL); -#if defined(CONFIG_BOOTPARAM) - strncpy(commandp, CONFIG_BOOTPARAM_STRING, size); - commandp[size-1] = 0; -#elif defined(CONFIG_NETtel) +#if defined(CONFIG_NETtel) /* Copy command line from FLASH to local buffer... */ memcpy(commandp, (char *) 0xf0004000, size); commandp[size-1] = 0; -#else - memset(commandp, 0, size); #endif /* CONFIG_NETtel */ mach_sched_init = coldfire_timer_init; Index: linux-rt-rebase.q/arch/m68knommu/platform/520x/config.c =================================================================== --- linux-rt-rebase.q.orig/arch/m68knommu/platform/520x/config.c +++ linux-rt-rebase.q/arch/m68knommu/platform/520x/config.c @@ -48,13 +48,6 @@ void mcf_autovector(unsigned int vec) void config_BSP(char *commandp, int size) { -#ifdef CONFIG_BOOTPARAM - strncpy(commandp, CONFIG_BOOTPARAM_STRING, size); - commandp[size-1] = 0; -#else - memset(commandp, 0, size); -#endif - mach_sched_init = coldfire_pit_init; mach_tick = coldfire_pit_tick; mach_gettimeoffset = coldfire_pit_offset; Index: linux-rt-rebase.q/arch/m68knommu/platform/523x/config.c =================================================================== --- linux-rt-rebase.q.orig/arch/m68knommu/platform/523x/config.c +++ linux-rt-rebase.q/arch/m68knommu/platform/523x/config.c @@ -63,14 +63,6 @@ void mcf_autovector(unsigned int vec) void config_BSP(char *commandp, int size) { mcf_disableall(); - -#ifdef CONFIG_BOOTPARAM - strncpy(commandp, CONFIG_BOOTPARAM_STRING, size); - commandp[size-1] = 0; -#else - memset(commandp, 0, size); -#endif - mach_sched_init = coldfire_pit_init; mach_tick = coldfire_pit_tick; mach_gettimeoffset = coldfire_pit_offset; Index: linux-rt-rebase.q/arch/m68knommu/platform/5249/config.c =================================================================== --- linux-rt-rebase.q.orig/arch/m68knommu/platform/5249/config.c +++ linux-rt-rebase.q/arch/m68knommu/platform/5249/config.c @@ -96,14 +96,6 @@ int mcf_timerirqpending(int timer) void config_BSP(char *commandp, int size) { mcf_setimr(MCFSIM_IMR_MASKALL); - -#if defined(CONFIG_BOOTPARAM) - strncpy(commandp, CONFIG_BOOTPARAM_STRING, size); - commandp[size-1] = 0; -#else - memset(commandp, 0, size); -#endif - mach_sched_init = coldfire_timer_init; mach_tick = coldfire_tick; mach_gettimeoffset = coldfire_timer_offset; Index: linux-rt-rebase.q/arch/m68knommu/platform/5272/config.c =================================================================== --- linux-rt-rebase.q.orig/arch/m68knommu/platform/5272/config.c +++ linux-rt-rebase.q/arch/m68knommu/platform/5272/config.c @@ -113,10 +113,7 @@ void config_BSP(char *commandp, int size mcf_disableall(); -#if defined(CONFIG_BOOTPARAM) - strncpy(commandp, CONFIG_BOOTPARAM_STRING, size); - commandp[size-1] = 0; -#elif defined(CONFIG_NETtel) || defined(CONFIG_SCALES) +#if defined(CONFIG_NETtel) || defined(CONFIG_SCALES) /* Copy command line from FLASH to local buffer... */ memcpy(commandp, (char *) 0xf0004000, size); commandp[size-1] = 0; @@ -128,8 +125,6 @@ void config_BSP(char *commandp, int size /* Copy command line from FLASH to local buffer... */ memcpy(commandp, (char *) 0xf0010000, size); commandp[size-1] = 0; -#else - memset(commandp, 0, size); #endif mcf_timervector = 69; Index: linux-rt-rebase.q/arch/m68knommu/platform/527x/config.c =================================================================== --- linux-rt-rebase.q.orig/arch/m68knommu/platform/527x/config.c +++ linux-rt-rebase.q/arch/m68knommu/platform/527x/config.c @@ -63,14 +63,6 @@ void mcf_autovector(unsigned int vec) void config_BSP(char *commandp, int size) { mcf_disableall(); - -#ifdef CONFIG_BOOTPARAM - strncpy(commandp, CONFIG_BOOTPARAM_STRING, size); - commandp[size-1] = 0; -#else - memset(commandp, 0, size); -#endif - mach_sched_init = coldfire_pit_init; mach_tick = coldfire_pit_tick; mach_gettimeoffset = coldfire_pit_offset; Index: linux-rt-rebase.q/arch/m68knommu/platform/528x/config.c =================================================================== --- linux-rt-rebase.q.orig/arch/m68knommu/platform/528x/config.c +++ linux-rt-rebase.q/arch/m68knommu/platform/528x/config.c @@ -63,14 +63,6 @@ void mcf_autovector(unsigned int vec) void config_BSP(char *commandp, int size) { mcf_disableall(); - -#ifdef CONFIG_BOOTPARAM - strncpy(commandp, CONFIG_BOOTPARAM_STRING, size); - commandp[size-1] = 0; -#else - memset(commandp, 0, size); -#endif - mach_sched_init = coldfire_pit_init; mach_tick = coldfire_pit_tick; mach_gettimeoffset = coldfire_pit_offset; Index: linux-rt-rebase.q/arch/m68knommu/platform/5307/config.c =================================================================== --- linux-rt-rebase.q.orig/arch/m68knommu/platform/5307/config.c +++ linux-rt-rebase.q/arch/m68knommu/platform/5307/config.c @@ -111,10 +111,7 @@ void config_BSP(char *commandp, int size { mcf_setimr(MCFSIM_IMR_MASKALL); -#if defined(CONFIG_BOOTPARAM) - strncpy(commandp, CONFIG_BOOTPARAM_STRING, size); - commandp[size-1] = 0; -#elif defined(CONFIG_NETtel) || defined(CONFIG_eLIA) || \ +#if defined(CONFIG_NETtel) || defined(CONFIG_eLIA) || \ defined(CONFIG_DISKtel) || defined(CONFIG_SECUREEDGEMP3) || \ defined(CONFIG_CLEOPATRA) /* Copy command line from FLASH to local buffer... */ @@ -124,8 +121,6 @@ void config_BSP(char *commandp, int size mcf_timervector = 30; mcf_profilevector = 31; mcf_timerlevel = 6; -#else - memset(commandp, 0, size); #endif mach_sched_init = coldfire_timer_init; Index: linux-rt-rebase.q/arch/m68knommu/platform/5307/entry.S =================================================================== --- linux-rt-rebase.q.orig/arch/m68knommu/platform/5307/entry.S +++ linux-rt-rebase.q/arch/m68knommu/platform/5307/entry.S @@ -213,16 +213,12 @@ ENTRY(ret_from_interrupt) * Beware - when entering resume, prev (the current task) is * in a0, next (the new task) is in a1,so don't change these * registers until their contents are no longer needed. + * This is always called in supervisor mode, so don't bother to save + * and restore sr; user's process sr is actually in the stack. */ ENTRY(resume) movel %a0, %d1 /* get prev thread in d1 */ - movew %sr,%d0 /* save thread status reg */ - movew %d0,%a0@(TASK_THREAD+THREAD_SR) - - oril #0x700,%d0 /* disable interrupts */ - move %d0,%sr - movel sw_usp,%d0 /* save usp */ movel %d0,%a0@(TASK_THREAD+THREAD_USP) @@ -233,7 +229,4 @@ ENTRY(resume) movel %a1@(TASK_THREAD+THREAD_USP),%a0 /* restore thread user stack */ movel %a0, sw_usp - - movew %a1@(TASK_THREAD+THREAD_SR),%d0 /* restore thread status reg */ - movew %d0, %sr rts Index: linux-rt-rebase.q/arch/m68knommu/platform/532x/config.c =================================================================== --- linux-rt-rebase.q.orig/arch/m68knommu/platform/532x/config.c +++ linux-rt-rebase.q/arch/m68knommu/platform/532x/config.c @@ -92,10 +92,7 @@ void config_BSP(char *commandp, int size { mcf_setimr(MCFSIM_IMR_MASKALL); -#if defined(CONFIG_BOOTPARAM) - strncpy(commandp, CONFIG_BOOTPARAM_STRING, size); - commandp[size-1] = 0; -#else +#if !defined(CONFIG_BOOTPARAM) /* Copy command line from FLASH to local buffer... */ memcpy(commandp, (char *) 0x4000, 4); if(strncmp(commandp, "kcl ", 4) == 0){ Index: linux-rt-rebase.q/arch/m68knommu/platform/5407/config.c =================================================================== --- linux-rt-rebase.q.orig/arch/m68knommu/platform/5407/config.c +++ linux-rt-rebase.q/arch/m68knommu/platform/5407/config.c @@ -102,13 +102,6 @@ void config_BSP(char *commandp, int size { mcf_setimr(MCFSIM_IMR_MASKALL); -#if defined(CONFIG_BOOTPARAM) - strncpy(commandp, CONFIG_BOOTPARAM_STRING, size); - commandp[size-1] = 0; -#else - memset(commandp, 0, size); -#endif - #if defined(CONFIG_CLEOPATRA) /* Different timer setup - to prevent device clash */ mcf_timervector = 30; Index: linux-rt-rebase.q/arch/m68knommu/platform/68VZ328/config.c =================================================================== --- linux-rt-rebase.q.orig/arch/m68knommu/platform/68VZ328/config.c +++ linux-rt-rebase.q/arch/m68knommu/platform/68VZ328/config.c @@ -191,13 +191,6 @@ void config_BSP(char *command, int size) { printk(KERN_INFO "68VZ328 DragonBallVZ support (c) 2001 Lineo, Inc.\n"); -#if defined(CONFIG_BOOTPARAM) - strncpy(command, CONFIG_BOOTPARAM_STRING, size); - command[size-1] = 0; -#else - memset(command, 0, size); -#endif - init_hardware(command, size); mach_sched_init = (void *) m68328_timer_init; Index: linux-rt-rebase.q/arch/mips/Kconfig =================================================================== --- linux-rt-rebase.q.orig/arch/mips/Kconfig +++ linux-rt-rebase.q/arch/mips/Kconfig @@ -251,6 +251,7 @@ config MIPS_SIM config MOMENCO_OCELOT bool "Momentum Ocelot board" select DMA_NONCOHERENT + select NO_SPINLOCK select HW_HAS_PCI select IRQ_CPU select IRQ_CPU_RM7K @@ -647,6 +648,7 @@ source "arch/mips/philips/pnx8550/common endmenu + config RWSEM_GENERIC_SPINLOCK bool default y @@ -654,6 +656,10 @@ config RWSEM_GENERIC_SPINLOCK config RWSEM_XCHGADD_ALGORITHM bool +config ASM_SEMAPHORES + bool + default y + config ARCH_HAS_ILOG2_U32 bool default n @@ -715,6 +721,9 @@ config DMA_NONCOHERENT config DMA_NEED_PCI_MAP_STATE bool +config NO_SPINLOCK + bool + config EARLY_PRINTK bool "Early printk" if EMBEDDED && DEBUG_KERNEL depends on SYS_HAS_EARLY_PRINTK @@ -1787,12 +1796,17 @@ config SECCOMP If unsure, say Y. Only embedded should say N here. -endmenu - -config RWSEM_GENERIC_SPINLOCK +config GENERIC_TIME bool default y +source "kernel/time/Kconfig" + +config CPU_SPEED + int "CPU speed used for clocksource/clockevent calculations" + default 600 +endmenu + config LOCKDEP_SUPPORT bool default y Index: linux-rt-rebase.q/arch/mips/Makefile =================================================================== --- linux-rt-rebase.q.orig/arch/mips/Makefile +++ linux-rt-rebase.q/arch/mips/Makefile @@ -328,7 +328,7 @@ load-$(CONFIG_MIPS_SEAD) += 0xffffffff80 # MIPS SIM # core-$(CONFIG_MIPS_SIM) += arch/mips/mipssim/ -cflags-$(CONFIG_MIPS_SIM) += -Iinclude/asm-mips/mach-sim +cflags-$(CONFIG_MIPS_SIM) += -Iinclude/asm-mips/mach-mipssim load-$(CONFIG_MIPS_SIM) += 0x80100000 # Index: linux-rt-rebase.q/arch/mips/arc/console.c =================================================================== --- linux-rt-rebase.q.orig/arch/mips/arc/console.c +++ /dev/null @@ -1,31 +0,0 @@ -/* - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. - * - * Copyright (C) 1996 David S. Miller (dm@sgi.com) - * Compability with board caches, Ulf Carlsson - */ -#include -#include -#include - -/* - * IP22 boardcache is not compatible with board caches. Thus we disable it - * during romvec action. Since r4xx0.c is always compiled and linked with your - * kernel, this shouldn't cause any harm regardless what MIPS processor you - * have. - * - * The ARC write and read functions seem to interfere with the serial lines - * in some way. You should be careful with them. - */ - -void prom_putchar(char c) -{ - ULONG cnt; - CHAR it = c; - - bc_disable(); - ArcWrite(1, &it, 1, &cnt); - bc_enable(); -} Index: linux-rt-rebase.q/arch/mips/jazz/io.c =================================================================== --- linux-rt-rebase.q.orig/arch/mips/jazz/io.c +++ /dev/null @@ -1,135 +0,0 @@ -/* - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. - * - * Low level I/O functions for Jazz family machines. - * - * Copyright (C) 1997 by Ralf Baechle. - */ -#include -#include -#include -#include -#include - -/* - * Map an 16mb segment of the EISA address space to 0xe3000000; - */ -static inline void map_eisa_address(unsigned long address) -{ - /* XXX */ - /* We've got an wired entry in the TLB. We just need to modify it. - fast and clean. But since we want to get rid of wired entries - things are a little bit more complicated ... */ -} - -static unsigned char jazz_readb(unsigned long addr) -{ - unsigned char res; - - map_eisa_address(addr); - addr &= 0xffffff; - res = *(volatile unsigned char *) (JAZZ_EISA_BASE + addr); - - return res; -} - -static unsigned short jazz_readw(unsigned long addr) -{ - unsigned short res; - - map_eisa_address(addr); - addr &= 0xffffff; - res = *(volatile unsigned char *) (JAZZ_EISA_BASE + addr); - - return res; -} - -static unsigned int jazz_readl(unsigned long addr) -{ - unsigned int res; - - map_eisa_address(addr); - addr &= 0xffffff; - res = *(volatile unsigned char *) (JAZZ_EISA_BASE + addr); - - return res; -} - -static void jazz_writeb(unsigned char val, unsigned long addr) -{ - map_eisa_address(addr); - addr &= 0xffffff; - *(volatile unsigned char *) (JAZZ_EISA_BASE + addr) = val; -} - -static void jazz_writew(unsigned short val, unsigned long addr) -{ - map_eisa_address(addr); - addr &= 0xffffff; - *(volatile unsigned char *) (JAZZ_EISA_BASE + addr) = val; -} - -static void jazz_writel(unsigned int val, unsigned long addr) -{ - map_eisa_address(addr); - addr &= 0xffffff; - *(volatile unsigned char *) (JAZZ_EISA_BASE + addr) = val; -} - -static void jazz_memset_io(unsigned long addr, int val, unsigned long len) -{ - unsigned long waddr; - - waddr = JAZZ_EISA_BASE | (addr & 0xffffff); - while(len) { - unsigned long fraglen; - - fraglen = (~addr + 1) & 0xffffff; - fraglen = (fraglen < len) ? fraglen : len; - map_eisa_address(addr); - memset((char *)waddr, val, fraglen); - addr += fraglen; - waddr = waddr + fraglen - 0x1000000; - len -= fraglen; - } -} - -static void jazz_memcpy_fromio(unsigned long to, unsigned long from, unsigned long len) -{ - unsigned long waddr; - - waddr = JAZZ_EISA_BASE | (from & 0xffffff); - while(len) { - unsigned long fraglen; - - fraglen = (~from + 1) & 0xffffff; - fraglen = (fraglen < len) ? fraglen : len; - map_eisa_address(from); - memcpy((void *)to, (void *)waddr, fraglen); - to += fraglen; - from += fraglen; - waddr = waddr + fraglen - 0x1000000; - len -= fraglen; - } -} - -static void jazz_memcpy_toio(unsigned long to, unsigned long from, unsigned long len) -{ - unsigned long waddr; - - waddr = JAZZ_EISA_BASE | (to & 0xffffff); - while(len) { - unsigned long fraglen; - - fraglen = (~to + 1) & 0xffffff; - fraglen = (fraglen < len) ? fraglen : len; - map_eisa_address(to); - memcpy((char *)to + JAZZ_EISA_BASE, (void *)from, fraglen); - to += fraglen; - from += fraglen; - waddr = waddr + fraglen - 0x1000000; - len -= fraglen; - } -} Index: linux-rt-rebase.q/arch/mips/jazz/reset.c =================================================================== --- linux-rt-rebase.q.orig/arch/mips/jazz/reset.c +++ linux-rt-rebase.q/arch/mips/jazz/reset.c @@ -6,10 +6,6 @@ */ #include #include -#include -#include -#include -#include #define KBD_STAT_IBF 0x02 /* Keyboard input buffer full */ @@ -58,12 +54,3 @@ void jazz_machine_restart(char *command) jazz_write_output (0x00); } } - -void jazz_machine_halt(void) -{ -} - -void jazz_machine_power_off(void) -{ - /* Jazz machines don't have a software power switch */ -} Index: linux-rt-rebase.q/arch/mips/jazz/setup.c =================================================================== --- linux-rt-rebase.q.orig/arch/mips/jazz/setup.c +++ linux-rt-rebase.q/arch/mips/jazz/setup.c @@ -34,8 +34,6 @@ extern asmlinkage void jazz_handle_int(void); extern void jazz_machine_restart(char *command); -extern void jazz_machine_halt(void); -extern void jazz_machine_power_off(void); void __init plat_timer_setup(struct irqaction *irq) { @@ -95,8 +93,6 @@ void __init plat_mem_setup(void) /* The RTC is outside the port address space */ _machine_restart = jazz_machine_restart; - _machine_halt = jazz_machine_halt; - pm_power_off = jazz_machine_power_off; screen_info = (struct screen_info) { 0, 0, /* orig-x, orig-y */ Index: linux-rt-rebase.q/arch/mips/jmr3927/rbhma3100/setup.c =================================================================== --- linux-rt-rebase.q.orig/arch/mips/jmr3927/rbhma3100/setup.c +++ linux-rt-rebase.q/arch/mips/jmr3927/rbhma3100/setup.c @@ -434,7 +434,7 @@ EXPORT_SYMBOL(__swizzle_addr_b); static int __init jmr3927_rtc_init(void) { - struct resource res = { + static struct resource __initdata res = { .start = JMR3927_IOC_NVRAMB_ADDR - IO_BASE, .end = JMR3927_IOC_NVRAMB_ADDR - IO_BASE + 0x800 - 1, .flags = IORESOURCE_MEM, Index: linux-rt-rebase.q/arch/mips/kernel/Makefile =================================================================== --- linux-rt-rebase.q.orig/arch/mips/kernel/Makefile +++ linux-rt-rebase.q/arch/mips/kernel/Makefile @@ -5,7 +5,7 @@ extra-y := head.o init_task.o vmlinux.lds obj-y += cpu-probe.o branch.o entry.o genex.o irq.o process.o \ - ptrace.o reset.o semaphore.o setup.o signal.o syscall.o \ + ptrace.o reset.o setup.o signal.o syscall.o \ time.o topology.o traps.o unaligned.o binfmt_irix-objs := irixelf.o irixinv.o irixioctl.o irixsig.o \ @@ -17,6 +17,8 @@ obj-$(CONFIG_MODULES) += mips_ksyms.o m obj-$(CONFIG_CPU_LOONGSON2) += r4k_fpu.o r4k_switch.o obj-$(CONFIG_CPU_MIPS32) += r4k_fpu.o r4k_switch.o obj-$(CONFIG_CPU_MIPS64) += r4k_fpu.o r4k_switch.o +obj-$(CONFIG_ASM_SEMAPHORES) += semaphore.o + obj-$(CONFIG_CPU_R3000) += r2300_fpu.o r2300_switch.o obj-$(CONFIG_CPU_R4000) += r4k_fpu.o r4k_switch.o obj-$(CONFIG_CPU_R4300) += r4k_fpu.o r4k_switch.o Index: linux-rt-rebase.q/arch/mips/kernel/asm-offsets.c =================================================================== --- linux-rt-rebase.q.orig/arch/mips/kernel/asm-offsets.c +++ linux-rt-rebase.q/arch/mips/kernel/asm-offsets.c @@ -10,9 +10,11 @@ */ #include #include +#include #include #include #include +#include #include #include Index: linux-rt-rebase.q/arch/mips/kernel/entry.S =================================================================== --- linux-rt-rebase.q.orig/arch/mips/kernel/entry.S +++ linux-rt-rebase.q/arch/mips/kernel/entry.S @@ -30,7 +30,7 @@ .align 5 #ifndef CONFIG_PREEMPT FEXPORT(ret_from_exception) - local_irq_disable # preempt stop + raw_local_irq_disable # preempt stop b __ret_from_irq #endif FEXPORT(ret_from_irq) @@ -41,7 +41,7 @@ FEXPORT(__ret_from_irq) beqz t0, resume_kernel resume_userspace: - local_irq_disable # make sure we dont miss an + raw_local_irq_disable # make sure we dont miss an # interrupt setting need_resched # between sampling and return LONG_L a2, TI_FLAGS($28) # current->work @@ -51,7 +51,9 @@ resume_userspace: #ifdef CONFIG_PREEMPT resume_kernel: - local_irq_disable + raw_local_irq_disable + lw t0, kernel_preemption + beqz t0, restore_all lw t0, TI_PRE_COUNT($28) bnez t0, restore_all need_resched: @@ -61,7 +63,9 @@ need_resched: LONG_L t0, PT_STATUS(sp) # Interrupts off? andi t0, 1 beqz t0, restore_all + raw_local_irq_disable jal preempt_schedule_irq + sw zero, TI_PRE_COUNT($28) b need_resched #endif @@ -69,7 +73,7 @@ FEXPORT(ret_from_fork) jal schedule_tail # a0 = struct task_struct *prev FEXPORT(syscall_exit) - local_irq_disable # make sure need_resched and + raw_local_irq_disable # make sure need_resched and # signals dont change between # sampling and return LONG_L a2, TI_FLAGS($28) # current->work @@ -142,19 +146,21 @@ FEXPORT(restore_partial) # restore part .set at work_pending: - andi t0, a2, _TIF_NEED_RESCHED # a2 is preloaded with TI_FLAGS + # a2 is preloaded with TI_FLAGS + andi t0, a2, (_TIF_NEED_RESCHED|_TIF_NEED_RESCHED_DELAYED) beqz t0, work_notifysig work_resched: + raw_local_irq_enable t0 jal schedule - local_irq_disable # make sure need_resched and + raw_local_irq_disable # make sure need_resched and # signals dont change between # sampling and return LONG_L a2, TI_FLAGS($28) andi t0, a2, _TIF_WORK_MASK # is there any work to be done # other than syscall tracing? beqz t0, restore_all - andi t0, a2, _TIF_NEED_RESCHED + andi t0, a2, (_TIF_NEED_RESCHED|_TIF_NEED_RESCHED_DELAYED) bnez t0, work_resched work_notifysig: # deal with pending signals and @@ -170,7 +176,7 @@ syscall_exit_work: li t0, _TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT and t0, a2 # a2 is preloaded with TI_FLAGS beqz t0, work_pending # trace bit set? - local_irq_enable # could let do_syscall_trace() + raw_local_irq_enable # could let do_syscall_trace() # call schedule() instead move a0, sp li a1, 1 Index: linux-rt-rebase.q/arch/mips/kernel/gdb-stub.c =================================================================== --- linux-rt-rebase.q.orig/arch/mips/kernel/gdb-stub.c +++ linux-rt-rebase.q/arch/mips/kernel/gdb-stub.c @@ -1099,12 +1099,12 @@ void adel(void) * malloc is needed by gdb client in "call func()", even a private one * will make gdb happy */ -static void * __attribute_used__ malloc(size_t size) +static void __used *malloc(size_t size) { return kmalloc(size, GFP_ATOMIC); } -static void __attribute_used__ free (void *where) +static void __used free(void *where) { kfree(where); } Index: linux-rt-rebase.q/arch/mips/kernel/head.S =================================================================== --- linux-rt-rebase.q.orig/arch/mips/kernel/head.S +++ linux-rt-rebase.q/arch/mips/kernel/head.S @@ -141,7 +141,7 @@ EXPORT(stext) # used for profiling EXPORT(_stext) -#ifdef CONFIG_BOOT_RAW +#ifndef CONFIG_BOOT_RAW /* * Give us a fighting chance of running if execution beings at the * kernel load address. This is needed because this platform does Index: linux-rt-rebase.q/arch/mips/kernel/i8259.c =================================================================== --- linux-rt-rebase.q.orig/arch/mips/kernel/i8259.c +++ linux-rt-rebase.q/arch/mips/kernel/i8259.c @@ -29,9 +29,9 @@ */ static int i8259A_auto_eoi = -1; -DEFINE_SPINLOCK(i8259A_lock); /* some platforms call this... */ void mask_and_ack_8259A(unsigned int); +DEFINE_RAW_SPINLOCK(i8259A_lock); static struct irq_chip i8259A_chip = { .name = "XT-PIC", Index: linux-rt-rebase.q/arch/mips/kernel/linux32.c =================================================================== --- linux-rt-rebase.q.orig/arch/mips/kernel/linux32.c +++ linux-rt-rebase.q/arch/mips/kernel/linux32.c @@ -567,7 +567,7 @@ asmlinkage long sys32_fadvise64_64(int f } save_static_function(sys32_clone); -__attribute_used__ noinline static int +static int noinline __used _sys32_clone(nabi_no_regargs struct pt_regs regs) { unsigned long clone_flags; Index: linux-rt-rebase.q/arch/mips/kernel/module.c =================================================================== --- linux-rt-rebase.q.orig/arch/mips/kernel/module.c +++ linux-rt-rebase.q/arch/mips/kernel/module.c @@ -40,7 +40,7 @@ struct mips_hi16 { static struct mips_hi16 *mips_hi16_list; static LIST_HEAD(dbe_list); -static DEFINE_SPINLOCK(dbe_lock); +static DEFINE_RAW_SPINLOCK(dbe_lock); void *module_alloc(unsigned long size) { Index: linux-rt-rebase.q/arch/mips/kernel/process.c =================================================================== --- linux-rt-rebase.q.orig/arch/mips/kernel/process.c +++ linux-rt-rebase.q/arch/mips/kernel/process.c @@ -52,7 +52,7 @@ void __noreturn cpu_idle(void) { /* endless idle loop with no priority at all */ while (1) { - while (!need_resched()) { + while (!need_resched() && !need_resched_delayed()) { #ifdef CONFIG_SMTC_IDLE_HOOK_DEBUG extern void smtc_idle_loop_hook(void); @@ -61,9 +61,11 @@ void __noreturn cpu_idle(void) if (cpu_wait) (*cpu_wait)(); } - preempt_enable_no_resched(); - schedule(); + local_irq_disable(); + __preempt_enable_no_resched(); + __schedule(); preempt_disable(); + local_irq_enable(); } } Index: linux-rt-rebase.q/arch/mips/kernel/rtlx.c =================================================================== --- linux-rt-rebase.q.orig/arch/mips/kernel/rtlx.c +++ linux-rt-rebase.q/arch/mips/kernel/rtlx.c @@ -85,7 +85,7 @@ static irqreturn_t rtlx_interrupt(int ir return IRQ_HANDLED; } -static __attribute_used__ void dump_rtlx(void) +static void __used dump_rtlx(void) { int i; Index: linux-rt-rebase.q/arch/mips/kernel/scall32-o32.S =================================================================== --- linux-rt-rebase.q.orig/arch/mips/kernel/scall32-o32.S +++ linux-rt-rebase.q/arch/mips/kernel/scall32-o32.S @@ -73,7 +73,7 @@ stack_done: 1: sw v0, PT_R2(sp) # result o32_syscall_exit: - local_irq_disable # make sure need_resched and + raw_local_irq_disable # make sure need_resched and # signals dont change between # sampling and return lw a2, TI_FLAGS($28) # current->work Index: linux-rt-rebase.q/arch/mips/kernel/scall64-64.S =================================================================== --- linux-rt-rebase.q.orig/arch/mips/kernel/scall64-64.S +++ linux-rt-rebase.q/arch/mips/kernel/scall64-64.S @@ -72,7 +72,7 @@ NESTED(handle_sys64, PT_SIZE, sp) 1: sd v0, PT_R2(sp) # result n64_syscall_exit: - local_irq_disable # make sure need_resched and + raw_local_irq_disable # make sure need_resched and # signals dont change between # sampling and return LONG_L a2, TI_FLAGS($28) # current->work Index: linux-rt-rebase.q/arch/mips/kernel/scall64-n32.S =================================================================== --- linux-rt-rebase.q.orig/arch/mips/kernel/scall64-n32.S +++ linux-rt-rebase.q/arch/mips/kernel/scall64-n32.S @@ -69,7 +69,7 @@ NESTED(handle_sysn32, PT_SIZE, sp) sd v0, PT_R0(sp) # set flag for syscall restarting 1: sd v0, PT_R2(sp) # result - local_irq_disable # make sure need_resched and + raw_local_irq_disable # make sure need_resched and # signals dont change between # sampling and return LONG_L a2, TI_FLAGS($28) # current->work Index: linux-rt-rebase.q/arch/mips/kernel/scall64-o32.S =================================================================== --- linux-rt-rebase.q.orig/arch/mips/kernel/scall64-o32.S +++ linux-rt-rebase.q/arch/mips/kernel/scall64-o32.S @@ -98,7 +98,7 @@ NESTED(handle_sys, PT_SIZE, sp) 1: sd v0, PT_R2(sp) # result o32_syscall_exit: - local_irq_disable # make need_resched and + raw_local_irq_disable # make need_resched and # signals dont change between # sampling and return LONG_L a2, TI_FLAGS($28) Index: linux-rt-rebase.q/arch/mips/kernel/semaphore.c =================================================================== --- linux-rt-rebase.q.orig/arch/mips/kernel/semaphore.c +++ linux-rt-rebase.q/arch/mips/kernel/semaphore.c @@ -36,7 +36,7 @@ * sem->count and sem->waking atomic. Scalability isn't an issue because * this lock is used on UP only so it's just an empty variable. */ -static inline int __sem_update_count(struct semaphore *sem, int incr) +static inline int __sem_update_count(struct compat_semaphore *sem, int incr) { int old_count, tmp; @@ -67,7 +67,7 @@ static inline int __sem_update_count(str : "=&r" (old_count), "=&r" (tmp), "=m" (sem->count) : "r" (incr), "m" (sem->count)); } else { - static DEFINE_SPINLOCK(semaphore_lock); + static DEFINE_RAW_SPINLOCK(semaphore_lock); unsigned long flags; spin_lock_irqsave(&semaphore_lock, flags); @@ -80,7 +80,7 @@ static inline int __sem_update_count(str return old_count; } -void __up(struct semaphore *sem) +void __compat_up(struct compat_semaphore *sem) { /* * Note that we incremented count in up() before we came here, @@ -94,7 +94,7 @@ void __up(struct semaphore *sem) wake_up(&sem->wait); } -EXPORT_SYMBOL(__up); +EXPORT_SYMBOL(__compat_up); /* * Note that when we come in to __down or __down_interruptible, @@ -104,7 +104,7 @@ EXPORT_SYMBOL(__up); * Thus it is only when we decrement count from some value > 0 * that we have actually got the semaphore. */ -void __sched __down(struct semaphore *sem) +void __sched __compat_down(struct compat_semaphore *sem) { struct task_struct *tsk = current; DECLARE_WAITQUEUE(wait, tsk); @@ -133,9 +133,9 @@ void __sched __down(struct semaphore *se wake_up(&sem->wait); } -EXPORT_SYMBOL(__down); +EXPORT_SYMBOL(__compat_down); -int __sched __down_interruptible(struct semaphore * sem) +int __sched __compat_down_interruptible(struct compat_semaphore * sem) { int retval = 0; struct task_struct *tsk = current; @@ -165,4 +165,10 @@ int __sched __down_interruptible(struct return retval; } -EXPORT_SYMBOL(__down_interruptible); +EXPORT_SYMBOL(__compat_down_interruptible); + +int fastcall compat_sem_is_locked(struct compat_semaphore *sem) +{ + return (int) atomic_read(&sem->count) < 0; +} +EXPORT_SYMBOL(compat_sem_is_locked); Index: linux-rt-rebase.q/arch/mips/kernel/signal.c =================================================================== --- linux-rt-rebase.q.orig/arch/mips/kernel/signal.c +++ linux-rt-rebase.q/arch/mips/kernel/signal.c @@ -629,6 +629,10 @@ static void do_signal(struct pt_regs *re siginfo_t info; int signr; +#ifdef CONFIG_PREEMPT_RT + local_irq_enable(); + preempt_check_resched(); +#endif /* * We want the common case to go fast, which is why we may in certain * cases get here from kernel mode. Just return without doing anything Index: linux-rt-rebase.q/arch/mips/kernel/signal32.c =================================================================== --- linux-rt-rebase.q.orig/arch/mips/kernel/signal32.c +++ linux-rt-rebase.q/arch/mips/kernel/signal32.c @@ -656,6 +656,10 @@ static int setup_rt_frame_32(struct k_si if (err) goto give_sigsegv; +#ifdef CONFIG_PREEMPT_RT + local_irq_enable(); + preempt_check_resched(); +#endif /* * Arguments to signal handler: * Index: linux-rt-rebase.q/arch/mips/kernel/smp.c =================================================================== --- linux-rt-rebase.q.orig/arch/mips/kernel/smp.c +++ linux-rt-rebase.q/arch/mips/kernel/smp.c @@ -88,7 +88,22 @@ asmlinkage __cpuinit void start_secondar cpu_idle(); } -DEFINE_SPINLOCK(smp_call_lock); +DEFINE_RAW_SPINLOCK(smp_call_lock); + +/* + * this function sends a 'reschedule' IPI to all other CPUs. + * This is used when RT tasks are starving and other CPUs + * might be able to run them. + */ +void smp_send_reschedule_allbutself(void) +{ + int cpu = smp_processor_id(); + int i; + + for (i = 0; i < NR_CPUS; i++) + if (cpu_online(i) && i != cpu) + core_send_ipi(i, SMP_RESCHEDULE_YOURSELF); +} struct call_data_struct *call_data; @@ -275,6 +290,8 @@ int setup_profiling_timer(unsigned int m return 0; } +static DEFINE_RAW_SPINLOCK(tlbstate_lock); + static void flush_tlb_all_ipi(void *info) { local_flush_tlb_all(); @@ -332,6 +349,7 @@ static inline void smp_on_each_tlb(void void flush_tlb_mm(struct mm_struct *mm) { preempt_disable(); + spin_lock(&tlbstate_lock); if ((atomic_read(&mm->mm_users) != 1) || (current->mm != mm)) { smp_on_other_tlbs(flush_tlb_mm_ipi, (void *)mm); @@ -341,6 +359,7 @@ void flush_tlb_mm(struct mm_struct *mm) if (smp_processor_id() != i) cpu_context(i, mm) = 0; } + spin_unlock(&tlbstate_lock); local_flush_tlb_mm(mm); preempt_enable(); @@ -364,6 +383,8 @@ void flush_tlb_range(struct vm_area_stru struct mm_struct *mm = vma->vm_mm; preempt_disable(); + spin_lock(&tlbstate_lock); + if ((atomic_read(&mm->mm_users) != 1) || (current->mm != mm)) { struct flush_tlb_data fd; @@ -377,6 +398,7 @@ void flush_tlb_range(struct vm_area_stru if (smp_processor_id() != i) cpu_context(i, mm) = 0; } + spin_unlock(&tlbstate_lock); local_flush_tlb_range(vma, start, end); preempt_enable(); } @@ -407,6 +429,8 @@ static void flush_tlb_page_ipi(void *inf void flush_tlb_page(struct vm_area_struct *vma, unsigned long page) { preempt_disable(); + spin_lock(&tlbstate_lock); + if ((atomic_read(&vma->vm_mm->mm_users) != 1) || (current->mm != vma->vm_mm)) { struct flush_tlb_data fd; @@ -419,6 +443,7 @@ void flush_tlb_page(struct vm_area_struc if (smp_processor_id() != i) cpu_context(i, vma->vm_mm) = 0; } + spin_unlock(&tlbstate_lock); local_flush_tlb_page(vma, page); preempt_enable(); } Index: linux-rt-rebase.q/arch/mips/kernel/syscall.c =================================================================== --- linux-rt-rebase.q.orig/arch/mips/kernel/syscall.c +++ linux-rt-rebase.q/arch/mips/kernel/syscall.c @@ -167,14 +167,14 @@ sys_mmap2(unsigned long addr, unsigned l } save_static_function(sys_fork); -__attribute_used__ noinline static int +static int __used noinline _sys_fork(nabi_no_regargs struct pt_regs regs) { return do_fork(SIGCHLD, regs.regs[29], ®s, 0, NULL, NULL); } save_static_function(sys_clone); -__attribute_used__ noinline static int +static int __used noinline _sys_clone(nabi_no_regargs struct pt_regs regs) { unsigned long clone_flags; Index: linux-rt-rebase.q/arch/mips/kernel/time.c =================================================================== --- linux-rt-rebase.q.orig/arch/mips/kernel/time.c +++ linux-rt-rebase.q/arch/mips/kernel/time.c @@ -10,6 +10,11 @@ * under the terms of the GNU General Public License as published by the * Free Software Foundation; either version 2 of the License, or (at your * option) any later version. + * + * This implementation of High Res Timers uses two timers. One is the system + * timer. The second is used for the high res timers. The high res timers + * require the CPU to have count/compare registers. The mips_set_next_event() + * function schedules the next high res timer interrupt. */ #include #include @@ -23,6 +28,7 @@ #include #include #include +#include #include #include @@ -47,7 +53,27 @@ /* * forward reference */ -DEFINE_SPINLOCK(rtc_lock); +DEFINE_RAW_SPINLOCK(rtc_lock); + +/* any missed timer interrupts */ +int missed_timer_count; + +#ifdef CONFIG_HIGH_RES_TIMERS +static void mips_set_next_event(unsigned long evt); +static void mips_set_mode(int mode, void *priv); + +static struct clock_event lapic_clockevent = { + .name = "mips clockevent interface", + .capabilities = CLOCK_CAP_NEXTEVT | CLOCK_CAP_PROFILE | + CLOCK_HAS_IRQHANDLER +#ifdef CONFIG_SMP + | CLOCK_CAP_UPDATE +#endif + , + .shift = 32, + .set_next_event = mips_set_next_event, +}; +#endif /* * By default we provide the null RTC ops @@ -56,6 +82,129 @@ static unsigned long null_rtc_get_time(v { return mktime(2000, 1, 1, 0, 0, 0); } +#ifdef CONFIG_SMP +/* + * We have to synchronize the master CPU with all the slave CPUs + */ +static atomic_t cpus_started; +static atomic_t cpus_ready; +static atomic_t cpus_count; +/* + * Master processor inits + */ +static void sync_cpus_init(int v) +{ + atomic_set(&cpus_count, 0); + mb(); + atomic_set(&cpus_started, v); + mb(); + atomic_set(&cpus_ready, v); + mb(); +} + +/* + * Called by the master processor + */ +static void sync_cpus_master(int v) +{ + atomic_set(&cpus_count, 0); + mb(); + atomic_set(&cpus_started, v); + mb(); + /* Wait here till all other CPUs are now ready */ + while (atomic_read(&cpus_count) != (num_online_cpus() -1) ) + mb(); + atomic_set(&cpus_ready, v); + mb(); +} +/* + * Called by the slave processors + */ +static void sync_cpus_slave(int v) +{ + /* Check if the master has been through this */ + while (atomic_read(&cpus_started) != v) + mb(); + atomic_inc(&cpus_count); + mb(); + while (atomic_read(&cpus_ready) != v) + mb(); +} +/* + * Called by the slave CPUs when done syncing the count register + * with the master processor + */ +static void sync_cpus_slave_exit(int v) +{ + while (atomic_read(&cpus_started) != v) + mb(); + atomic_inc(&cpus_count); + mb(); +} + +#define LOOPS 100 +static u32 c0_count[NR_CPUS]; /* Count register per CPU */ +static u32 c[NR_CPUS][LOOPS + 1]; /* Count register per CPU per loop for syncing */ + +/* + * Slave processors execute this via IPI + */ +static void sync_c0_count_slave(void *info) +{ + int cpus = 1, loop, prev_count = 0, cpu = smp_processor_id(); + unsigned long flags; + u32 diff_count; /* CPU count registers are 32-bit */ + local_irq_save(flags); + + for(loop = 0; loop <= LOOPS; loop++) { + /* Sync with the Master processor */ + sync_cpus_slave(cpus++); + c[cpu][loop] = c0_count[cpu] = read_c0_count(); + mb(); + sync_cpus_slave(cpus++); + diff_count = c0_count[0] - c0_count[cpu]; + diff_count += prev_count; + diff_count += read_c0_count(); + write_c0_count(diff_count); + prev_count = (prev_count >> 1) + + ((int)(c0_count[0] - c0_count[cpu]) >> 1); + } + + /* Slave processor is done syncing count register with Master */ + sync_cpus_slave_exit(cpus++); + printk("SMP: Slave processor %d done syncing count \n", cpu); + local_irq_restore(flags); +} + +/* + * Master kicks off the syncing process + */ +void sync_c0_count_master(void) +{ + int cpus = 0, loop, cpu = smp_processor_id(); + unsigned long flags; + + printk("SMP: Starting to sync the c0 count register ... \n"); + sync_cpus_init(cpus++); + + /* Kick off the slave processors to also start the syncing process */ + smp_call_function(sync_c0_count_slave, NULL, 0, 0); + local_irq_save(flags); + + for (loop = 0; loop <= LOOPS; loop++) { + /* Wait for all the CPUs here */ + sync_cpus_master(cpus++); + c[cpu][loop] = c0_count[cpu] = read_c0_count(); + mb(); + /* Do syncing once more */ + sync_cpus_master(cpus++); + } + sync_cpus_master(cpus++); + local_irq_restore(flags); + + printk("SMP: Syncing process completed accross CPUs ... \n"); +} +#endif /* CONFIG_SMP */ static int null_rtc_set_time(unsigned long sec) { @@ -66,19 +215,30 @@ unsigned long (*rtc_mips_get_time)(void) int (*rtc_mips_set_time)(unsigned long) = null_rtc_set_time; int (*rtc_mips_set_mmss)(unsigned long); - /* how many counter cycles in a jiffy */ static unsigned long cycles_per_jiffy __read_mostly; +static unsigned long hrt_cycles_per_jiffy __read_mostly; + + /* expirelo is the count value for next CPU timer interrupt */ static unsigned int expirelo; - /* * Null timer ack for systems not needing one (e.g. i8254). */ static void null_timer_ack(void) { /* nothing */ } +#ifdef CONFIG_HIGH_RES_TIMERS +/* + * Set the next event + */ +static void mips_set_next_event(unsigned long evt) +{ + write_c0_compare(read_c0_count() + evt); +} +#endif + /* * Null high precision timer functions for systems lacking one. */ @@ -95,13 +255,13 @@ static void c0_timer_ack(void) unsigned int count; /* Ack this timer interrupt and set the next one. */ - expirelo += cycles_per_jiffy; + expirelo += hrt_cycles_per_jiffy; write_c0_compare(expirelo); - /* Check to see if we have missed any timer interrupts. */ - while (((count = read_c0_count()) - expirelo) < 0x7fffffff) { - /* missed_timer_count++; */ - expirelo = count + cycles_per_jiffy; + count = read_c0_count(); + if ((count - expirelo) < 0x7fffffff) { + /* missed_timer_count++; */ + expirelo = count + hrt_cycles_per_jiffy; write_c0_compare(expirelo); } } @@ -127,6 +287,29 @@ void (*mips_timer_ack)(void); /* last time when xtime and rtc are sync'ed up */ static long last_rtc_update; +unsigned long read_persistent_clock(void) +{ + unsigned long sec; + sec = rtc_mips_get_time(); + return sec; +} + +void sync_persistent_clock(struct timespec ts) +{ + if (ntp_synced() && + xtime.tv_sec > last_rtc_update + 660 && + (xtime.tv_nsec / 1000) >= 500000 - ((unsigned) TICK_SIZE) / 2 && + (xtime.tv_nsec / 1000) <= 500000 + ((unsigned) TICK_SIZE) / 2) { + if (rtc_mips_set_mmss(xtime.tv_sec) == 0) { + last_rtc_update = xtime.tv_sec; + } + else { + /* do it again in 60 s */ + last_rtc_update = xtime.tv_sec - 600; + } + } +} + /* * local_timer_interrupt() does profiling and process accounting * on a per-CPU basis. @@ -160,7 +343,7 @@ irqreturn_t timer_interrupt(int irq, voi /* * If we have an externally synchronized Linux clock, then update - * CMOS clock accordingly every ~11 minutes. rtc_mips_set_time() has to be + * CMOS clock accordingly every ~11 minutes. rtc_set_time() has to be * called as close as possible to 500 ms before the new second starts. */ if (ntp_synced() && @@ -228,6 +411,15 @@ static inline int handle_perf_irq (int r !r2; } +#ifdef CONFIG_HIGH_RES_TIMERS +void event_timer_handler(struct pt_regs *regs) +{ + c0_timer_ack(); + if (lapic_clockevent.event_handler) + lapic_clockevent.event_handler(regs,NULL); +} +#endif + asmlinkage void ll_timer_interrupt(int irq) { int r2 = cpu_has_mips_r2; @@ -235,6 +427,16 @@ asmlinkage void ll_timer_interrupt(int i irq_enter(); kstat_this_cpu.irqs[irq]++; + +#ifdef CONFIG_HIGH_RES_TIMERS + /* + * Run the event handler + */ + if (!r2 || (read_c0_cause() & (1 << 26))) + if (lapic_clockevent.event_handler) + lapic_clockevent.event_handler(regs,NULL); +#endif + if (handle_perf_irq(r2)) goto out; @@ -267,7 +469,7 @@ asmlinkage void ll_local_timer_interrupt * b) (optional) calibrate and set the mips_hpt_frequency * (only needed if you intended to use cpu counter as timer interrupt * source) - * 2) setup xtime based on rtc_mips_get_time(). + * 2) setup xtime based on rtc_get_time(). * 3) calculate a couple of cached variables for later usage * 4) plat_timer_setup() - * a) (optional) over-write any choices made above by time_init(). @@ -281,7 +483,7 @@ unsigned int mips_hpt_frequency; static struct irqaction timer_irqaction = { .handler = timer_interrupt, - .flags = IRQF_DISABLED | IRQF_PERCPU, + .flags = IRQF_DISABLED | IRQF_PERCPU | IRQF_NODELAY, .name = "timer", }; @@ -358,6 +560,9 @@ static void __init init_mips_clocksource void __init time_init(void) { +#ifdef CONFIG_HIGH_RES_TIMERS + u64 temp; +#endif if (board_time_init) board_time_init(); @@ -401,6 +606,12 @@ void __init time_init(void) if (!mips_hpt_frequency) mips_hpt_frequency = calibrate_hpt(); +#ifdef CONFIG_HIGH_RES_TIMERS + hrt_cycles_per_jiffy = ( (CONFIG_CPU_SPEED * 1000000) + HZ / 2) / HZ; +#else + hrt_cycles_per_jiffy = cycles_per_jiffy; +#endif + /* Report the high precision timer rate for a reference. */ printk("Using %u.%03u MHz high precision timer.\n", ((mips_hpt_frequency + 500) / 1000) / 1000, Index: linux-rt-rebase.q/arch/mips/kernel/traps.c =================================================================== --- linux-rt-rebase.q.orig/arch/mips/kernel/traps.c +++ linux-rt-rebase.q/arch/mips/kernel/traps.c @@ -309,7 +309,7 @@ void show_registers(struct pt_regs *regs printk("\n"); } -static DEFINE_SPINLOCK(die_lock); +static DEFINE_RAW_SPINLOCK(die_lock); void __noreturn die(const char * str, struct pt_regs * regs) { Index: linux-rt-rebase.q/arch/mips/kernel/vpe.c =================================================================== --- linux-rt-rebase.q.orig/arch/mips/kernel/vpe.c +++ linux-rt-rebase.q/arch/mips/kernel/vpe.c @@ -154,7 +154,6 @@ struct { }; static void release_progmem(void *ptr); -/* static __attribute_used__ void dump_vpe(struct vpe * v); */ extern void save_gp_address(unsigned int secbase, unsigned int rel); /* get the vpe associated with this minor */ @@ -1024,7 +1023,7 @@ static int vpe_elfload(struct vpe * v) return 0; } -__attribute_used__ void dump_vpe(struct vpe * v) +void __used dump_vpe(struct vpe * v) { struct tc *t; Index: linux-rt-rebase.q/arch/mips/mm/c-sb1.c =================================================================== --- linux-rt-rebase.q.orig/arch/mips/mm/c-sb1.c +++ linux-rt-rebase.q/arch/mips/mm/c-sb1.c @@ -272,7 +272,7 @@ void sb1_flush_cache_data_page(unsigned /* * Invalidate all caches on this CPU */ -static void __attribute_used__ local_sb1___flush_cache_all(void) +static void __used local_sb1___flush_cache_all(void) { __sb1_writeback_inv_dcache_all(); __sb1_flush_icache_all(); Index: linux-rt-rebase.q/arch/mips/mm/fault.c =================================================================== --- linux-rt-rebase.q.orig/arch/mips/mm/fault.c +++ linux-rt-rebase.q/arch/mips/mm/fault.c @@ -69,7 +69,7 @@ asmlinkage void do_page_fault(struct pt_ * If we're in an interrupt or have no user * context, we must not take the fault.. */ - if (in_atomic() || !mm) + if (in_atomic() || !mm || current->pagefault_disabled) goto bad_area_nosemaphore; down_read(&mm->mmap_sem); Index: linux-rt-rebase.q/arch/mips/mm/highmem.c =================================================================== --- linux-rt-rebase.q.orig/arch/mips/mm/highmem.c +++ linux-rt-rebase.q/arch/mips/mm/highmem.c @@ -38,7 +38,7 @@ void *__kmap_atomic(struct page *page, e enum fixed_addresses idx; unsigned long vaddr; - /* even !CONFIG_PREEMPT needs this, for in_atomic in do_page_fault */ + preempt_disable(); pagefault_disable(); if (!PageHighMem(page)) return page_address(page); @@ -63,6 +63,7 @@ void __kunmap_atomic(void *kvaddr, enum if (vaddr < FIXADDR_START) { // FIXME pagefault_enable(); + preempt_enable(); return; } @@ -78,6 +79,7 @@ void __kunmap_atomic(void *kvaddr, enum #endif pagefault_enable(); + preempt_enable(); } /* @@ -89,6 +91,7 @@ void *kmap_atomic_pfn(unsigned long pfn, enum fixed_addresses idx; unsigned long vaddr; + preempt_disable(); pagefault_disable(); idx = type + KM_TYPE_NR*smp_processor_id(); Index: linux-rt-rebase.q/arch/mips/mm/init.c =================================================================== --- linux-rt-rebase.q.orig/arch/mips/mm/init.c +++ linux-rt-rebase.q/arch/mips/mm/init.c @@ -59,7 +59,7 @@ #endif /* CONFIG_MIPS_MT_SMTC */ -DEFINE_PER_CPU(struct mmu_gather, mmu_gathers); +DEFINE_PER_CPU_LOCKED(struct mmu_gather, mmu_gathers); /* * We have up to 8 empty zeroed pages so we can map one of the right colour @@ -484,7 +484,7 @@ void free_initrd_mem(unsigned long start } #endif -void free_initmem(void) +void __init_refok free_initmem(void) { prom_free_prom_memory(); free_init_pages("unused kernel memory", Index: linux-rt-rebase.q/arch/mips/sibyte/cfe/smp.c =================================================================== --- linux-rt-rebase.q.orig/arch/mips/sibyte/cfe/smp.c +++ linux-rt-rebase.q/arch/mips/sibyte/cfe/smp.c @@ -107,4 +107,8 @@ void prom_smp_finish(void) */ void prom_cpus_done(void) { +#ifdef CONFIG_HIGH_RES_TIMERS + extern void sync_c0_count_master(void); + sync_c0_count_master(); +#endif } Index: linux-rt-rebase.q/arch/mips/sibyte/sb1250/irq.c =================================================================== --- linux-rt-rebase.q.orig/arch/mips/sibyte/sb1250/irq.c +++ linux-rt-rebase.q/arch/mips/sibyte/sb1250/irq.c @@ -81,7 +81,7 @@ static struct irq_chip sb1250_irq_type = /* Store the CPU id (not the logical number) */ int sb1250_irq_owner[SB1250_NR_IRQS]; -DEFINE_SPINLOCK(sb1250_imr_lock); +DEFINE_RAW_SPINLOCK(sb1250_imr_lock); void sb1250_mask_irq(int cpu, int irq) { @@ -242,7 +242,7 @@ static irqreturn_t sb1250_dummy_handler static struct irqaction sb1250_dummy_action = { .handler = sb1250_dummy_handler, - .flags = 0, + .flags = IRQF_NODELAY, .mask = CPU_MASK_NONE, .name = "sb1250-private", .next = NULL, @@ -352,6 +352,10 @@ void __init arch_init_irq(void) #ifdef CONFIG_KGDB imask |= STATUSF_IP6; #endif + +#ifdef CONFIG_HIGH_RES_TIMERS + imask |= STATUSF_IP7; +#endif /* Enable necessary IPs, disable the rest */ change_c0_status(ST0_IM, imask); @@ -429,6 +433,10 @@ asmlinkage void plat_irq_dispatch(void) else #endif +#ifdef CONFIG_HIGH_RES_TIMERS + if (pending & CAUSEF_IP7) + event_timer_handler(regs); +#endif if (pending & CAUSEF_IP4) sb1250_timer_interrupt(); Index: linux-rt-rebase.q/arch/mips/sibyte/sb1250/smp.c =================================================================== --- linux-rt-rebase.q.orig/arch/mips/sibyte/sb1250/smp.c +++ linux-rt-rebase.q/arch/mips/sibyte/sb1250/smp.c @@ -59,7 +59,7 @@ void sb1250_smp_finish(void) { extern void sb1250_time_init(void); sb1250_time_init(); - local_irq_enable(); + raw_local_irq_enable(); } /* Index: linux-rt-rebase.q/arch/mips/sibyte/swarm/setup.c =================================================================== --- linux-rt-rebase.q.orig/arch/mips/sibyte/swarm/setup.c +++ linux-rt-rebase.q/arch/mips/sibyte/swarm/setup.c @@ -131,6 +131,12 @@ void __init plat_mem_setup(void) rtc_mips_set_time = m41t81_set_time; } +#ifdef CONFIG_HIGH_RES_TIMERS + /* + * set the mips_hpt_frequency here + */ + mips_hpt_frequency = CONFIG_CPU_SPEED * 1000000; +#endif printk("This kernel optimized for " #ifdef CONFIG_SIMULATION "simulation" Index: linux-rt-rebase.q/arch/mips/sni/sniprom.c =================================================================== --- linux-rt-rebase.q.orig/arch/mips/sni/sniprom.c +++ linux-rt-rebase.q/arch/mips/sni/sniprom.c @@ -19,6 +19,7 @@ #include #include #include +#include #include /* special SNI prom calls */ @@ -71,7 +72,7 @@ const char *get_system_type(void) #define SNI_IDPROM_SIZE 0x1000 #ifdef DEBUG -static void sni_idprom_dump(void) +static void __init sni_idprom_dump(void) { int i; @@ -88,7 +89,7 @@ static void sni_idprom_dump(void) } #endif -static void sni_mem_init(void ) +static void __init sni_mem_init(void ) { int i, memsize; struct membank { Index: linux-rt-rebase.q/arch/mips/tx4927/toshiba_rbtx4927/toshiba_rbtx4927_setup.c =================================================================== --- linux-rt-rebase.q.orig/arch/mips/tx4927/toshiba_rbtx4927/toshiba_rbtx4927_setup.c +++ linux-rt-rebase.q/arch/mips/tx4927/toshiba_rbtx4927/toshiba_rbtx4927_setup.c @@ -1020,7 +1020,7 @@ void __init toshiba_rbtx4927_timer_setup static int __init toshiba_rbtx4927_rtc_init(void) { - struct resource res = { + static struct resource __initdata res = { .start = 0x1c010000, .end = 0x1c010000 + 0x800 - 1, .flags = IORESOURCE_MEM, Index: linux-rt-rebase.q/arch/powerpc/Kconfig =================================================================== --- linux-rt-rebase.q.orig/arch/powerpc/Kconfig +++ linux-rt-rebase.q/arch/powerpc/Kconfig @@ -21,18 +21,15 @@ config MMU bool default y -config GENERIC_HARDIRQS +config GENERIC_TIME bool default y -config IRQ_PER_CPU +config GENERIC_HARDIRQS bool default y -config RWSEM_GENERIC_SPINLOCK - bool - -config RWSEM_XCHGADD_ALGORITHM +config IRQ_PER_CPU bool default y @@ -157,7 +154,30 @@ config HIGHMEM depends on PPC32 source kernel/Kconfig.hz + +config GENERIC_CLOCKEVENTS + bool "Clock event devices support" + default n + help + Enable support for the clock event devices necessary for the + high-resolution timers and the tickless system support. + NOTE: This is not compatible with the deterministic time accounting + option on PPC64. + +source kernel/time/Kconfig source kernel/Kconfig.preempt + +config RWSEM_GENERIC_SPINLOCK + bool + default y + +config ASM_SEMAPHORES + bool + default y + +config RWSEM_XCHGADD_ALGORITHM + bool + source "fs/Kconfig.binfmt" # We optimistically allocate largepages from the VM, so make the limit @@ -165,7 +185,7 @@ source "fs/Kconfig.binfmt" # max order + 1 config FORCE_MAX_ZONEORDER int - depends on PPC64 + depends on PPC64 && !GENERIC_CLOCKEVENTS default "9" if PPC_64K_PAGES default "13" @@ -411,11 +431,6 @@ config PPC_INDIRECT_PCI default y if 40x || 44x default n -config PPC_INDIRECT_PCI_BE - bool - depends PPC_INDIRECT_PCI - default n - config EISA bool @@ -425,6 +440,10 @@ config SBUS config FSL_SOC bool +config FSL_PCI + bool + select PPC_INDIRECT_PCI + # Yes MCA RS/6000s exist but Linux-PPC does not currently support any config MCA bool Index: linux-rt-rebase.q/arch/powerpc/Kconfig.debug =================================================================== --- linux-rt-rebase.q.orig/arch/powerpc/Kconfig.debug +++ linux-rt-rebase.q/arch/powerpc/Kconfig.debug @@ -2,6 +2,10 @@ menu "Kernel hacking" source "lib/Kconfig.debug" +config TRACE_IRQFLAGS_SUPPORT + bool + default y + config DEBUG_STACKOVERFLOW bool "Check for stack overflows" depends on DEBUG_KERNEL Index: linux-rt-rebase.q/arch/powerpc/boot/dts/mpc8313erdb.dts =================================================================== --- linux-rt-rebase.q.orig/arch/powerpc/boot/dts/mpc8313erdb.dts +++ linux-rt-rebase.q/arch/powerpc/boot/dts/mpc8313erdb.dts @@ -178,7 +178,7 @@ #size-cells = <2>; #address-cells = <3>; reg = <8500 100>; - compatible = "83xx"; + compatible = "fsl,mpc8349-pci"; device_type = "pci"; }; Index: linux-rt-rebase.q/arch/powerpc/boot/dts/mpc832x_mds.dts =================================================================== --- linux-rt-rebase.q.orig/arch/powerpc/boot/dts/mpc832x_mds.dts +++ linux-rt-rebase.q/arch/powerpc/boot/dts/mpc832x_mds.dts @@ -154,7 +154,7 @@ #size-cells = <2>; #address-cells = <3>; reg = <8500 100>; - compatible = "83xx"; + compatible = "fsl,mpc8349-pci"; device_type = "pci"; }; Index: linux-rt-rebase.q/arch/powerpc/boot/dts/mpc832x_rdb.dts =================================================================== --- linux-rt-rebase.q.orig/arch/powerpc/boot/dts/mpc832x_rdb.dts +++ linux-rt-rebase.q/arch/powerpc/boot/dts/mpc832x_rdb.dts @@ -123,7 +123,7 @@ #size-cells = <2>; #address-cells = <3>; reg = <8500 100>; - compatible = "83xx"; + compatible = "fsl,mpc8349-pci"; device_type = "pci"; }; Index: linux-rt-rebase.q/arch/powerpc/boot/dts/mpc8349emitx.dts =================================================================== --- linux-rt-rebase.q.orig/arch/powerpc/boot/dts/mpc8349emitx.dts +++ linux-rt-rebase.q/arch/powerpc/boot/dts/mpc8349emitx.dts @@ -197,7 +197,7 @@ #size-cells = <2>; #address-cells = <3>; reg = <8500 100>; - compatible = "83xx"; + compatible = "fsl,mpc8349-pci"; device_type = "pci"; }; @@ -222,7 +222,7 @@ #size-cells = <2>; #address-cells = <3>; reg = <8600 100>; - compatible = "83xx"; + compatible = "fsl,mpc8349-pci"; device_type = "pci"; }; Index: linux-rt-rebase.q/arch/powerpc/boot/dts/mpc8349emitxgp.dts =================================================================== --- linux-rt-rebase.q.orig/arch/powerpc/boot/dts/mpc8349emitxgp.dts +++ linux-rt-rebase.q/arch/powerpc/boot/dts/mpc8349emitxgp.dts @@ -154,7 +154,7 @@ #size-cells = <2>; #address-cells = <3>; reg = <8600 100>; - compatible = "83xx"; + compatible = "fsl,mpc8349-pci"; device_type = "pci"; }; Index: linux-rt-rebase.q/arch/powerpc/boot/dts/mpc834x_mds.dts =================================================================== --- linux-rt-rebase.q.orig/arch/powerpc/boot/dts/mpc834x_mds.dts +++ linux-rt-rebase.q/arch/powerpc/boot/dts/mpc834x_mds.dts @@ -241,7 +241,7 @@ #size-cells = <2>; #address-cells = <3>; reg = <8500 100>; - compatible = "83xx"; + compatible = "fsl,mpc8349-pci"; device_type = "pci"; }; @@ -301,7 +301,7 @@ #size-cells = <2>; #address-cells = <3>; reg = <8600 100>; - compatible = "83xx"; + compatible = "fsl,mpc8349-pci"; device_type = "pci"; }; Index: linux-rt-rebase.q/arch/powerpc/boot/dts/mpc836x_mds.dts =================================================================== --- linux-rt-rebase.q.orig/arch/powerpc/boot/dts/mpc836x_mds.dts +++ linux-rt-rebase.q/arch/powerpc/boot/dts/mpc836x_mds.dts @@ -169,7 +169,7 @@ #size-cells = <2>; #address-cells = <3>; reg = <8500 100>; - compatible = "83xx"; + compatible = "fsl,mpc8349-pci"; device_type = "pci"; }; Index: linux-rt-rebase.q/arch/powerpc/boot/dts/mpc8540ads.dts =================================================================== --- linux-rt-rebase.q.orig/arch/powerpc/boot/dts/mpc8540ads.dts +++ linux-rt-rebase.q/arch/powerpc/boot/dts/mpc8540ads.dts @@ -258,7 +258,7 @@ #size-cells = <2>; #address-cells = <3>; reg = <8000 1000>; - compatible = "85xx"; + compatible = "fsl,mpc8540-pcix", "fsl,mpc8540-pci"; device_type = "pci"; }; Index: linux-rt-rebase.q/arch/powerpc/boot/dts/mpc8541cds.dts =================================================================== --- linux-rt-rebase.q.orig/arch/powerpc/boot/dts/mpc8541cds.dts +++ linux-rt-rebase.q/arch/powerpc/boot/dts/mpc8541cds.dts @@ -193,7 +193,7 @@ #size-cells = <2>; #address-cells = <3>; reg = <8000 1000>; - compatible = "85xx"; + compatible = "fsl,mpc8540-pci"; device_type = "pci"; i8259@19000 { @@ -230,7 +230,7 @@ #size-cells = <2>; #address-cells = <3>; reg = <9000 1000>; - compatible = "85xx"; + compatible = "fsl,mpc8540-pci"; device_type = "pci"; }; Index: linux-rt-rebase.q/arch/powerpc/boot/dts/mpc8544ds.dts =================================================================== --- linux-rt-rebase.q.orig/arch/powerpc/boot/dts/mpc8544ds.dts +++ linux-rt-rebase.q/arch/powerpc/boot/dts/mpc8544ds.dts @@ -137,6 +137,217 @@ interrupt-parent = <&mpic>; }; + pci@8000 { + compatible = "fsl,mpc8540-pci"; + device_type = "pci"; + interrupt-map-mask = ; + interrupt-map = < + + /* IDSEL 0x11 J17 Slot 1 */ + 8800 0 0 1 &mpic 2 1 + 8800 0 0 2 &mpic 3 1 + 8800 0 0 3 &mpic 4 1 + 8800 0 0 4 &mpic 1 1 + + /* IDSEL 0x12 J16 Slot 2 */ + + 9000 0 0 1 &mpic 3 1 + 9000 0 0 2 &mpic 4 1 + 9000 0 0 3 &mpic 2 1 + 9000 0 0 4 &mpic 1 1>; + + interrupt-parent = <&mpic>; + interrupts = <18 2>; + bus-range = <0 ff>; + ranges = <02000000 0 80000000 80000000 0 10000000 + 01000000 0 00000000 e2000000 0 00800000>; + clock-frequency = <3f940aa>; + #interrupt-cells = <1>; + #size-cells = <2>; + #address-cells = <3>; + reg = <8000 1000>; + }; + + pcie@9000 { + compatible = "fsl,mpc8548-pcie"; + device_type = "pci"; + #interrupt-cells = <1>; + #size-cells = <2>; + #address-cells = <3>; + reg = <9000 1000>; + bus-range = <0 ff>; + ranges = <02000000 0 90000000 90000000 0 10000000 + 01000000 0 00000000 e3000000 0 00800000>; + clock-frequency = <1fca055>; + interrupt-parent = <&mpic>; + interrupts = <1a 2>; + interrupt-map-mask = ; + interrupt-map = < + /* IDSEL 0x0 */ + 0000 0 0 1 &mpic 4 1 + 0000 0 0 2 &mpic 5 1 + 0000 0 0 3 &mpic 6 1 + 0000 0 0 4 &mpic 7 1 + >; + }; + + pcie@a000 { + compatible = "fsl,mpc8548-pcie"; + device_type = "pci"; + #interrupt-cells = <1>; + #size-cells = <2>; + #address-cells = <3>; + reg = ; + bus-range = <0 ff>; + ranges = <02000000 0 a0000000 a0000000 0 10000000 + 01000000 0 00000000 e2800000 0 00800000>; + clock-frequency = <1fca055>; + interrupt-parent = <&mpic>; + interrupts = <19 2>; + interrupt-map-mask = ; + interrupt-map = < + /* IDSEL 0x0 */ + 0000 0 0 1 &mpic 0 1 + 0000 0 0 2 &mpic 1 1 + 0000 0 0 3 &mpic 2 1 + 0000 0 0 4 &mpic 3 1 + >; + }; + + pcie@b000 { + compatible = "fsl,mpc8548-pcie"; + device_type = "pci"; + #interrupt-cells = <1>; + #size-cells = <2>; + #address-cells = <3>; + reg = ; + bus-range = <0 ff>; + ranges = <02000000 0 b0000000 b0000000 0 10000000 + 01000000 0 00000000 e3800000 0 00800000>; + clock-frequency = <1fca055>; + interrupt-parent = <&mpic>; + interrupts = <1b 2>; + interrupt-map-mask = ; + interrupt-map = < + + // IDSEL 0x1a + d000 0 0 1 &i8259 6 2 + d000 0 0 2 &i8259 3 2 + d000 0 0 3 &i8259 4 2 + d000 0 0 4 &i8259 5 2 + + // IDSEL 0x1b + d800 0 0 1 &i8259 5 2 + d800 0 0 2 &i8259 0 0 + d800 0 0 3 &i8259 0 0 + d800 0 0 4 &i8259 0 0 + + // IDSEL 0x1c USB + e000 0 0 1 &i8259 9 2 + e000 0 0 2 &i8259 a 2 + e000 0 0 3 &i8259 c 2 + e000 0 0 4 &i8259 7 2 + + // IDSEL 0x1d Audio + e800 0 0 1 &i8259 9 2 + e800 0 0 2 &i8259 a 2 + e800 0 0 3 &i8259 b 2 + e800 0 0 4 &i8259 0 0 + + // IDSEL 0x1e Legacy + f000 0 0 1 &i8259 c 2 + f000 0 0 2 &i8259 0 0 + f000 0 0 3 &i8259 0 0 + f000 0 0 4 &i8259 0 0 + + // IDSEL 0x1f IDE/SATA + f800 0 0 1 &i8259 6 2 + f800 0 0 2 &i8259 0 0 + f800 0 0 3 &i8259 0 0 + f800 0 0 4 &i8259 0 0 + >; + uli1575@0 { + reg = <0 0 0 0 0>; + #size-cells = <2>; + #address-cells = <3>; + ranges = <02000000 0 b0000000 + 02000000 0 b0000000 + 0 10000000 + 01000000 0 00000000 + 01000000 0 00000000 + 0 00080000>; + + pci_bridge@0 { + reg = <0 0 0 0 0>; + #size-cells = <2>; + #address-cells = <3>; + ranges = <02000000 0 b0000000 + 02000000 0 b0000000 + 0 20000000 + 01000000 0 00000000 + 01000000 0 00000000 + 0 00100000>; + + isa@1e { + device_type = "isa"; + #interrupt-cells = <2>; + #size-cells = <1>; + #address-cells = <2>; + reg = ; + ranges = <1 0 01000000 0 0 + 00001000>; + interrupt-parent = <&i8259>; + + i8259: interrupt-controller@20 { + reg = <1 20 2 + 1 a0 2 + 1 4d0 2>; + clock-frequency = <0>; + interrupt-controller; + device_type = "interrupt-controller"; + #address-cells = <0>; + #interrupt-cells = <2>; + built-in; + compatible = "chrp,iic"; + interrupts = <9 2>; + interrupt-parent = + <&mpic>; + }; + + i8042@60 { + #size-cells = <0>; + #address-cells = <1>; + reg = <1 60 1 1 64 1>; + interrupts = <1 3 c 3>; + interrupt-parent = + <&i8259>; + + keyboard@0 { + reg = <0>; + compatible = "pnpPNP,303"; + }; + + mouse@1 { + reg = <1>; + compatible = "pnpPNP,f03"; + }; + }; + + rtc@70 { + compatible = + "pnpPNP,b00"; + reg = <1 70 2>; + }; + + gpio@400 { + reg = <1 400 80>; + }; + }; + }; + }; + + }; + mpic: pic@40000 { clock-frequency = <0>; interrupt-controller; Index: linux-rt-rebase.q/arch/powerpc/boot/dts/mpc8548cds.dts =================================================================== --- linux-rt-rebase.q.orig/arch/powerpc/boot/dts/mpc8548cds.dts +++ linux-rt-rebase.q/arch/powerpc/boot/dts/mpc8548cds.dts @@ -1,5 +1,5 @@ /* - * MPC8555 CDS Device Tree Source + * MPC8548 CDS Device Tree Source * * Copyright 2006 Freescale Semiconductor Inc. * @@ -44,8 +44,14 @@ #size-cells = <1>; #interrupt-cells = <2>; device_type = "soc"; - ranges = <0 e0000000 00100000>; - reg = ; // CCSRBAR 1M + ranges = <00001000 e0001000 000ff000 + 80000000 80000000 10000000 + e2000000 e2000000 00800000 + 90000000 90000000 10000000 + e2800000 e2800000 00800000 + a0000000 a0000000 20000000 + e3000000 e3000000 01000000>; + reg = ; // CCSRBAR bus-frequency = <0>; memory-controller@2000 { @@ -162,8 +168,8 @@ serial@4500 { device_type = "serial"; compatible = "ns16550"; - reg = <4500 100>; // reg base, size - clock-frequency = <0>; // should we fill in in uboot? + reg = <4500 100>; // reg base, size + clock-frequency = <0>; // should we fill in in uboot? interrupts = <2a 2>; interrupt-parent = <&mpic>; }; @@ -172,7 +178,7 @@ device_type = "serial"; compatible = "ns16550"; reg = <4600 100>; // reg base, size - clock-frequency = <0>; // should we fill in in uboot? + clock-frequency = <0>; // should we fill in in uboot? interrupts = <2a 2>; interrupt-parent = <&mpic>; }; @@ -183,77 +189,154 @@ fsl,has-rstcr; }; - pci1: pci@8000 { - interrupt-map-mask = <1f800 0 0 7>; + pci@8000 { + interrupt-map-mask = ; interrupt-map = < + /* IDSEL 0x4 (PCIX Slot 2) */ + 02000 0 0 1 &mpic 0 1 + 02000 0 0 2 &mpic 1 1 + 02000 0 0 3 &mpic 2 1 + 02000 0 0 4 &mpic 3 1 + + /* IDSEL 0x5 (PCIX Slot 3) */ + 02800 0 0 1 &mpic 1 1 + 02800 0 0 2 &mpic 2 1 + 02800 0 0 3 &mpic 3 1 + 02800 0 0 4 &mpic 0 1 + + /* IDSEL 0x6 (PCIX Slot 4) */ + 03000 0 0 1 &mpic 2 1 + 03000 0 0 2 &mpic 3 1 + 03000 0 0 3 &mpic 0 1 + 03000 0 0 4 &mpic 1 1 + + /* IDSEL 0x8 (PCIX Slot 5) */ + 04000 0 0 1 &mpic 0 1 + 04000 0 0 2 &mpic 1 1 + 04000 0 0 3 &mpic 2 1 + 04000 0 0 4 &mpic 3 1 + + /* IDSEL 0xC (Tsi310 bridge) */ + 06000 0 0 1 &mpic 0 1 + 06000 0 0 2 &mpic 1 1 + 06000 0 0 3 &mpic 2 1 + 06000 0 0 4 &mpic 3 1 + + /* IDSEL 0x14 (Slot 2) */ + 0a000 0 0 1 &mpic 0 1 + 0a000 0 0 2 &mpic 1 1 + 0a000 0 0 3 &mpic 2 1 + 0a000 0 0 4 &mpic 3 1 + + /* IDSEL 0x15 (Slot 3) */ + 0a800 0 0 1 &mpic 1 1 + 0a800 0 0 2 &mpic 2 1 + 0a800 0 0 3 &mpic 3 1 + 0a800 0 0 4 &mpic 0 1 + + /* IDSEL 0x16 (Slot 4) */ + 0b000 0 0 1 &mpic 2 1 + 0b000 0 0 2 &mpic 3 1 + 0b000 0 0 3 &mpic 0 1 + 0b000 0 0 4 &mpic 1 1 + + /* IDSEL 0x18 (Slot 5) */ + 0c000 0 0 1 &mpic 0 1 + 0c000 0 0 2 &mpic 1 1 + 0c000 0 0 3 &mpic 2 1 + 0c000 0 0 4 &mpic 3 1 + + /* IDSEL 0x1C (Tsi310 bridge PCI primary) */ + 0E000 0 0 1 &mpic 0 1 + 0E000 0 0 2 &mpic 1 1 + 0E000 0 0 3 &mpic 2 1 + 0E000 0 0 4 &mpic 3 1>; - /* IDSEL 0x10 */ - 08000 0 0 1 &mpic 0 1 - 08000 0 0 2 &mpic 1 1 - 08000 0 0 3 &mpic 2 1 - 08000 0 0 4 &mpic 3 1 - - /* IDSEL 0x11 */ - 08800 0 0 1 &mpic 0 1 - 08800 0 0 2 &mpic 1 1 - 08800 0 0 3 &mpic 2 1 - 08800 0 0 4 &mpic 3 1 - - /* IDSEL 0x12 (Slot 1) */ - 09000 0 0 1 &mpic 0 1 - 09000 0 0 2 &mpic 1 1 - 09000 0 0 3 &mpic 2 1 - 09000 0 0 4 &mpic 3 1 - - /* IDSEL 0x13 (Slot 2) */ - 09800 0 0 1 &mpic 1 1 - 09800 0 0 2 &mpic 2 1 - 09800 0 0 3 &mpic 3 1 - 09800 0 0 4 &mpic 0 1 - - /* IDSEL 0x14 (Slot 3) */ - 0a000 0 0 1 &mpic 2 1 - 0a000 0 0 2 &mpic 3 1 - 0a000 0 0 3 &mpic 0 1 - 0a000 0 0 4 &mpic 1 1 - - /* IDSEL 0x15 (Slot 4) */ - 0a800 0 0 1 &mpic 3 1 - 0a800 0 0 2 &mpic 0 1 - 0a800 0 0 3 &mpic 1 1 - 0a800 0 0 4 &mpic 2 1 - - /* Bus 1 (Tundra Bridge) */ - /* IDSEL 0x12 (ISA bridge) */ - 19000 0 0 1 &mpic 0 1 - 19000 0 0 2 &mpic 1 1 - 19000 0 0 3 &mpic 2 1 - 19000 0 0 4 &mpic 3 1>; interrupt-parent = <&mpic>; interrupts = <18 2>; bus-range = <0 0>; - ranges = <02000000 0 80000000 80000000 0 20000000 - 01000000 0 00000000 e2000000 0 00100000>; + ranges = <02000000 0 80000000 80000000 0 10000000 + 01000000 0 00000000 e2000000 0 00800000>; clock-frequency = <3f940aa>; #interrupt-cells = <1>; #size-cells = <2>; #address-cells = <3>; reg = <8000 1000>; - compatible = "85xx"; + compatible = "fsl,mpc8540-pcix", "fsl,mpc8540-pci"; device_type = "pci"; - i8259@19000 { - clock-frequency = <0>; - interrupt-controller; - device_type = "interrupt-controller"; - reg = <19000 0 0 0 1>; - #address-cells = <0>; - #interrupt-cells = <2>; - built-in; - compatible = "chrp,iic"; - big-endian; - interrupts = <1>; - interrupt-parent = <&pci1>; + pci_bridge@1c { + interrupt-map-mask = ; + interrupt-map = < + + /* IDSEL 0x00 (PrPMC Site) */ + 0000 0 0 1 &mpic 0 1 + 0000 0 0 2 &mpic 1 1 + 0000 0 0 3 &mpic 2 1 + 0000 0 0 4 &mpic 3 1 + + /* IDSEL 0x04 (VIA chip) */ + 2000 0 0 1 &mpic 0 1 + 2000 0 0 2 &mpic 1 1 + 2000 0 0 3 &mpic 2 1 + 2000 0 0 4 &mpic 3 1 + + /* IDSEL 0x05 (8139) */ + 2800 0 0 1 &mpic 1 1 + + /* IDSEL 0x06 (Slot 6) */ + 3000 0 0 1 &mpic 2 1 + 3000 0 0 2 &mpic 3 1 + 3000 0 0 3 &mpic 0 1 + 3000 0 0 4 &mpic 1 1 + + /* IDESL 0x07 (Slot 7) */ + 3800 0 0 1 &mpic 3 1 + 3800 0 0 2 &mpic 0 1 + 3800 0 0 3 &mpic 1 1 + 3800 0 0 4 &mpic 2 1>; + + reg = ; + #interrupt-cells = <1>; + #size-cells = <2>; + #address-cells = <3>; + ranges = <02000000 0 80000000 + 02000000 0 80000000 + 0 20000000 + 01000000 0 00000000 + 01000000 0 00000000 + 0 00080000>; + clock-frequency = <1fca055>; + + isa@4 { + device_type = "isa"; + #interrupt-cells = <2>; + #size-cells = <1>; + #address-cells = <2>; + reg = <2000 0 0 0 0>; + ranges = <1 0 01000000 0 0 00001000>; + interrupt-parent = <&i8259>; + + i8259: interrupt-controller@20 { + clock-frequency = <0>; + interrupt-controller; + device_type = "interrupt-controller"; + reg = <1 20 2 + 1 a0 2 + 1 4d0 2>; + #address-cells = <0>; + #interrupt-cells = <2>; + built-in; + compatible = "chrp,iic"; + interrupts = <0 1>; + interrupt-parent = <&mpic>; + }; + + rtc@70 { + compatible = "pnpPNP,b00"; + reg = <1 70 2>; + }; + }; }; }; @@ -263,20 +346,45 @@ /* IDSEL 0x15 */ a800 0 0 1 &mpic b 1 - a800 0 0 2 &mpic b 1 - a800 0 0 3 &mpic b 1 - a800 0 0 4 &mpic b 1>; + a800 0 0 2 &mpic 1 1 + a800 0 0 3 &mpic 2 1 + a800 0 0 4 &mpic 3 1>; + interrupt-parent = <&mpic>; interrupts = <19 2>; bus-range = <0 0>; - ranges = <02000000 0 a0000000 a0000000 0 20000000 - 01000000 0 00000000 e3000000 0 00100000>; + ranges = <02000000 0 90000000 90000000 0 10000000 + 01000000 0 00000000 e2800000 0 00800000>; clock-frequency = <3f940aa>; #interrupt-cells = <1>; #size-cells = <2>; #address-cells = <3>; reg = <9000 1000>; - compatible = "85xx"; + compatible = "fsl,mpc8540-pci"; + device_type = "pci"; + }; + /* PCI Express */ + pcie@a000 { + interrupt-map-mask = ; + interrupt-map = < + + /* IDSEL 0x0 (PEX) */ + 00000 0 0 1 &mpic 0 1 + 00000 0 0 2 &mpic 1 1 + 00000 0 0 3 &mpic 2 1 + 00000 0 0 4 &mpic 3 1>; + + interrupt-parent = <&mpic>; + interrupts = <1a 2>; + bus-range = <0 ff>; + ranges = <02000000 0 a0000000 a0000000 0 20000000 + 01000000 0 00000000 e3000000 0 08000000>; + clock-frequency = <1fca055>; + #interrupt-cells = <1>; + #size-cells = <2>; + #address-cells = <3>; + reg = ; + compatible = "fsl,mpc8548-pcie"; device_type = "pci"; }; Index: linux-rt-rebase.q/arch/powerpc/boot/dts/mpc8555cds.dts =================================================================== --- linux-rt-rebase.q.orig/arch/powerpc/boot/dts/mpc8555cds.dts +++ linux-rt-rebase.q/arch/powerpc/boot/dts/mpc8555cds.dts @@ -193,7 +193,7 @@ #size-cells = <2>; #address-cells = <3>; reg = <8000 1000>; - compatible = "85xx"; + compatible = "fsl,mpc8540-pci"; device_type = "pci"; i8259@19000 { @@ -230,7 +230,7 @@ #size-cells = <2>; #address-cells = <3>; reg = <9000 1000>; - compatible = "85xx"; + compatible = "fsl,mpc8540-pci"; device_type = "pci"; }; Index: linux-rt-rebase.q/arch/powerpc/boot/dts/mpc8560ads.dts =================================================================== --- linux-rt-rebase.q.orig/arch/powerpc/boot/dts/mpc8560ads.dts +++ linux-rt-rebase.q/arch/powerpc/boot/dts/mpc8560ads.dts @@ -136,7 +136,7 @@ #interrupt-cells = <1>; #size-cells = <2>; #address-cells = <3>; - compatible = "85xx"; + compatible = "fsl,mpc8540-pcix", "fsl,mpc8540-pci"; device_type = "pci"; reg = <8000 1000>; clock-frequency = <3f940aa>; Index: linux-rt-rebase.q/arch/powerpc/boot/dts/mpc8568mds.dts =================================================================== --- linux-rt-rebase.q.orig/arch/powerpc/boot/dts/mpc8568mds.dts +++ linux-rt-rebase.q/arch/powerpc/boot/dts/mpc8568mds.dts @@ -170,6 +170,60 @@ interrupt-parent = <&mpic>; }; + pci@8000 { + interrupt-map-mask = ; + interrupt-map = < + /* IDSEL 0x12 AD18 */ + 9000 0 0 1 &mpic 5 1 + 9000 0 0 2 &mpic 6 1 + 9000 0 0 3 &mpic 7 1 + 9000 0 0 4 &mpic 4 1 + + /* IDSEL 0x13 AD19 */ + 9800 0 0 1 &mpic 6 1 + 9800 0 0 2 &mpic 7 1 + 9800 0 0 3 &mpic 4 1 + 9800 0 0 4 &mpic 5 1>; + + interrupt-parent = <&mpic>; + interrupts = <18 2>; + bus-range = <0 ff>; + ranges = <02000000 0 80000000 80000000 0 20000000 + 01000000 0 00000000 e2000000 0 00800000>; + clock-frequency = <3f940aa>; + #interrupt-cells = <1>; + #size-cells = <2>; + #address-cells = <3>; + reg = <8000 1000>; + compatible = "fsl,mpc8540-pci"; + device_type = "pci"; + }; + + /* PCI Express */ + pcie@a000 { + interrupt-map-mask = ; + interrupt-map = < + + /* IDSEL 0x0 (PEX) */ + 00000 0 0 1 &mpic 0 1 + 00000 0 0 2 &mpic 1 1 + 00000 0 0 3 &mpic 2 1 + 00000 0 0 4 &mpic 3 1>; + + interrupt-parent = <&mpic>; + interrupts = <1a 2>; + bus-range = <0 ff>; + ranges = <02000000 0 a0000000 a0000000 0 20000000 + 01000000 0 00000000 e3000000 0 08000000>; + clock-frequency = <1fca055>; + #interrupt-cells = <1>; + #size-cells = <2>; + #address-cells = <3>; + reg = ; + compatible = "fsl,mpc8548-pcie"; + device_type = "pci"; + }; + serial@4600 { device_type = "serial"; compatible = "ns16550"; Index: linux-rt-rebase.q/arch/powerpc/boot/dts/mpc8641_hpcn.dts =================================================================== --- linux-rt-rebase.q.orig/arch/powerpc/boot/dts/mpc8641_hpcn.dts +++ linux-rt-rebase.q/arch/powerpc/boot/dts/mpc8641_hpcn.dts @@ -211,8 +211,8 @@ interrupt-parent = <&mpic>; }; - pci@8000 { - compatible = "86xx"; + pcie@8000 { + compatible = "fsl,mpc8641-pcie"; device_type = "pci"; #interrupt-cells = <1>; #size-cells = <2>; @@ -399,8 +399,8 @@ }; - pci@9000 { - compatible = "86xx"; + pcie@9000 { + compatible = "fsl,mpc8641-pcie"; device_type = "pci"; #interrupt-cells = <1>; #size-cells = <2>; Index: linux-rt-rebase.q/arch/powerpc/configs/mpc8544_ds_defconfig =================================================================== --- linux-rt-rebase.q.orig/arch/powerpc/configs/mpc8544_ds_defconfig +++ linux-rt-rebase.q/arch/powerpc/configs/mpc8544_ds_defconfig @@ -1,9 +1,26 @@ # # Automatically generated make config: don't edit -# Linux kernel version: 2.6.22-rc7 -# Sun Jul 1 23:56:58 2007 +# Linux kernel version: 2.6.22 +# Fri Jul 20 14:09:13 2007 # # CONFIG_PPC64 is not set + +# +# Processor support +# +# CONFIG_6xx is not set +CONFIG_PPC_85xx=y +# CONFIG_PPC_8xx is not set +# CONFIG_40x is not set +# CONFIG_44x is not set +# CONFIG_E200 is not set +CONFIG_85xx=y +CONFIG_E500=y +CONFIG_BOOKE=y +CONFIG_FSL_BOOKE=y +# CONFIG_PHYS_64BIT is not set +# CONFIG_SPE is not set +# CONFIG_PPC_MM_SLICES is not set CONFIG_PPC32=y CONFIG_PPC_MERGE=y CONFIG_MMU=y @@ -14,6 +31,7 @@ CONFIG_ARCH_HAS_ILOG2_U32=y CONFIG_GENERIC_HWEIGHT=y CONFIG_GENERIC_CALIBRATE_DELAY=y CONFIG_GENERIC_FIND_NEXT_BIT=y +# CONFIG_ARCH_NO_VIRT_TO_BUS is not set CONFIG_PPC=y CONFIG_EARLY_PRINTK=y CONFIG_GENERIC_NVRAM=y @@ -25,28 +43,8 @@ CONFIG_PPC_UDBG_16550=y CONFIG_AUDIT_ARCH=y CONFIG_GENERIC_BUG=y CONFIG_DEFAULT_UIMAGE=y - -# -# Processor support -# -# CONFIG_CLASSIC32 is not set -# CONFIG_PPC_82xx is not set -# CONFIG_PPC_83xx is not set -CONFIG_PPC_85xx=y -# CONFIG_PPC_86xx is not set -# CONFIG_PPC_8xx is not set -# CONFIG_40x is not set -# CONFIG_44x is not set -# CONFIG_E200 is not set -CONFIG_85xx=y -CONFIG_E500=y # CONFIG_PPC_DCR_NATIVE is not set # CONFIG_PPC_DCR_MMIO is not set -CONFIG_BOOKE=y -CONFIG_FSL_BOOKE=y -# CONFIG_PHYS_64BIT is not set -# CONFIG_SPE is not set -# CONFIG_PPC_MM_SLICES is not set CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config" # @@ -63,13 +61,12 @@ CONFIG_LOCALVERSION="" CONFIG_LOCALVERSION_AUTO=y CONFIG_SWAP=y CONFIG_SYSVIPC=y -CONFIG_IPC_NS=y CONFIG_SYSVIPC_SYSCTL=y CONFIG_POSIX_MQUEUE=y CONFIG_BSD_PROCESS_ACCT=y # CONFIG_BSD_PROCESS_ACCT_V3 is not set # CONFIG_TASKSTATS is not set -# CONFIG_UTS_NS is not set +# CONFIG_USER_NS is not set CONFIG_AUDIT=y # CONFIG_AUDITSYSCALL is not set CONFIG_IKCONFIG=y @@ -86,7 +83,7 @@ CONFIG_SYSCTL_SYSCALL=y CONFIG_KALLSYMS=y CONFIG_KALLSYMS_ALL=y # CONFIG_KALLSYMS_EXTRA_PASS is not set -# CONFIG_HOTPLUG is not set +CONFIG_HOTPLUG=y CONFIG_PRINTK=y CONFIG_BUG=y CONFIG_ELF_CORE=y @@ -105,24 +102,17 @@ CONFIG_SLAB=y CONFIG_RT_MUTEXES=y # CONFIG_TINY_SHMEM is not set CONFIG_BASE_SMALL=0 - -# -# Loadable module support -# CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y CONFIG_MODULE_FORCE_UNLOAD=y CONFIG_MODVERSIONS=y # CONFIG_MODULE_SRCVERSION_ALL is not set CONFIG_KMOD=y - -# -# Block layer -# CONFIG_BLOCK=y CONFIG_LBD=y # CONFIG_BLK_DEV_IO_TRACE is not set # CONFIG_LSF is not set +# CONFIG_BLK_DEV_BSG is not set # # IO Schedulers @@ -153,7 +143,7 @@ CONFIG_MPC8544_DS=y CONFIG_MPC85xx=y CONFIG_MPIC=y # CONFIG_MPIC_WEIRD is not set -# CONFIG_PPC_I8259 is not set +CONFIG_PPC_I8259=y # CONFIG_PPC_RTAS is not set # CONFIG_MMIO_NVRAM is not set # CONFIG_PPC_MPC106 is not set @@ -191,6 +181,8 @@ CONFIG_FLAT_NODE_MEM_MAP=y CONFIG_SPLIT_PTLOCK_CPUS=4 # CONFIG_RESOURCES_64BIT is not set CONFIG_ZONE_DMA_FLAG=1 +CONFIG_BOUNCE=y +CONFIG_VIRT_TO_BUS=y CONFIG_PROC_DEVICETREE=y CONFIG_CMDLINE_BOOL=y CONFIG_CMDLINE="root=/dev/sda3 rw console=ttyS0,115200" @@ -205,15 +197,21 @@ CONFIG_ISA_DMA_API=y # CONFIG_ZONE_DMA=y CONFIG_PPC_INDIRECT_PCI=y -CONFIG_PPC_INDIRECT_PCI_BE=y CONFIG_FSL_SOC=y -# CONFIG_PCI is not set -# CONFIG_PCI_DOMAINS is not set -# CONFIG_ARCH_SUPPORTS_MSI is not set +CONFIG_FSL_PCI=y +CONFIG_PCI=y +CONFIG_PCI_DOMAINS=y +CONFIG_PCI_SYSCALL=y +# CONFIG_PCIEPORTBUS is not set +CONFIG_ARCH_SUPPORTS_MSI=y +# CONFIG_PCI_MSI is not set +# CONFIG_PCI_DEBUG is not set # # PCCARD (PCMCIA/CardBus) support # +# CONFIG_PCCARD is not set +# CONFIG_HOTPLUG_PCI is not set # # Advanced setup @@ -254,7 +252,6 @@ CONFIG_ASK_IP_FIB_HASH=y CONFIG_IP_FIB_HASH=y CONFIG_IP_MULTIPLE_TABLES=y CONFIG_IP_ROUTE_MULTIPATH=y -# CONFIG_IP_ROUTE_MULTIPATH_CACHED is not set CONFIG_IP_ROUTE_VERBOSE=y CONFIG_IP_PNP=y CONFIG_IP_PNP_DHCP=y @@ -330,6 +327,7 @@ CONFIG_FIB_RULES=y # CONFIG_MAC80211 is not set # CONFIG_IEEE80211 is not set # CONFIG_RFKILL is not set +# CONFIG_NET_9P is not set # # Device Drivers @@ -340,45 +338,35 @@ CONFIG_FIB_RULES=y # CONFIG_STANDALONE=y CONFIG_PREVENT_FIRMWARE_BUILD=y +# CONFIG_FW_LOADER is not set # CONFIG_DEBUG_DRIVER is not set # CONFIG_DEBUG_DEVRES is not set # CONFIG_SYS_HYPERVISOR is not set - -# -# Connector - unified userspace <-> kernelspace linker -# # CONFIG_CONNECTOR is not set # CONFIG_MTD is not set - -# -# Parallel port support -# # CONFIG_PARPORT is not set - -# -# Plug and Play support -# -# CONFIG_PNPACPI is not set - -# -# Block devices -# +CONFIG_BLK_DEV=y # CONFIG_BLK_DEV_FD is not set +# CONFIG_BLK_CPQ_DA is not set +# CONFIG_BLK_CPQ_CISS_DA is not set +# CONFIG_BLK_DEV_DAC960 is not set +# CONFIG_BLK_DEV_UMEM is not set # CONFIG_BLK_DEV_COW_COMMON is not set CONFIG_BLK_DEV_LOOP=y # CONFIG_BLK_DEV_CRYPTOLOOP is not set CONFIG_BLK_DEV_NBD=y +# CONFIG_BLK_DEV_SX8 is not set CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_RAM_COUNT=2 CONFIG_BLK_DEV_RAM_SIZE=16384 CONFIG_BLK_DEV_RAM_BLOCKSIZE=1024 # CONFIG_CDROM_PKTCDVD is not set # CONFIG_ATA_OVER_ETH is not set - -# -# Misc devices -# -# CONFIG_BLINK is not set +CONFIG_MISC_DEVICES=y +# CONFIG_PHANTOM is not set +# CONFIG_EEPROM_93CX6 is not set +# CONFIG_SGI_IOC4 is not set +# CONFIG_TIFM_CORE is not set # CONFIG_IDE is not set # @@ -386,6 +374,7 @@ CONFIG_BLK_DEV_RAM_BLOCKSIZE=1024 # # CONFIG_RAID_ATTRS is not set CONFIG_SCSI=y +CONFIG_SCSI_DMA=y # CONFIG_SCSI_TGT is not set # CONFIG_SCSI_NETLINK is not set CONFIG_SCSI_PROC_FS=y @@ -422,25 +411,120 @@ CONFIG_SCSI_WAIT_SCAN=m # SCSI low-level drivers # # CONFIG_ISCSI_TCP is not set +# CONFIG_BLK_DEV_3W_XXXX_RAID is not set +# CONFIG_SCSI_3W_9XXX is not set +# CONFIG_SCSI_ACARD is not set +# CONFIG_SCSI_AACRAID is not set +# CONFIG_SCSI_AIC7XXX is not set +# CONFIG_SCSI_AIC7XXX_OLD is not set +# CONFIG_SCSI_AIC79XX is not set +# CONFIG_SCSI_AIC94XX is not set +# CONFIG_SCSI_DPT_I2O is not set +# CONFIG_SCSI_ARCMSR is not set +# CONFIG_MEGARAID_NEWGEN is not set +# CONFIG_MEGARAID_LEGACY is not set +# CONFIG_MEGARAID_SAS is not set +# CONFIG_SCSI_HPTIOP is not set +# CONFIG_SCSI_BUSLOGIC is not set +# CONFIG_SCSI_DMX3191D is not set +# CONFIG_SCSI_EATA is not set +# CONFIG_SCSI_FUTURE_DOMAIN is not set +# CONFIG_SCSI_GDTH is not set +# CONFIG_SCSI_IPS is not set +# CONFIG_SCSI_INITIO is not set +# CONFIG_SCSI_INIA100 is not set +# CONFIG_SCSI_STEX is not set +# CONFIG_SCSI_SYM53C8XX_2 is not set +# CONFIG_SCSI_IPR is not set +# CONFIG_SCSI_QLOGIC_1280 is not set +# CONFIG_SCSI_QLA_FC is not set +# CONFIG_SCSI_QLA_ISCSI is not set +# CONFIG_SCSI_LPFC is not set +# CONFIG_SCSI_DC395x is not set +# CONFIG_SCSI_DC390T is not set +# CONFIG_SCSI_NSP32 is not set # CONFIG_SCSI_DEBUG is not set +# CONFIG_SCSI_SRP is not set CONFIG_ATA=y # CONFIG_ATA_NONSTANDARD is not set +# CONFIG_SATA_AHCI is not set +# CONFIG_SATA_SVW is not set +# CONFIG_ATA_PIIX is not set +# CONFIG_SATA_MV is not set +# CONFIG_SATA_NV is not set +# CONFIG_PDC_ADMA is not set +# CONFIG_SATA_QSTOR is not set +# CONFIG_SATA_PROMISE is not set +# CONFIG_SATA_SX4 is not set +# CONFIG_SATA_SIL is not set +# CONFIG_SATA_SIL24 is not set +# CONFIG_SATA_SIS is not set +# CONFIG_SATA_ULI is not set +# CONFIG_SATA_VIA is not set +# CONFIG_SATA_VITESSE is not set +# CONFIG_SATA_INIC162X is not set +# CONFIG_PATA_ALI is not set +# CONFIG_PATA_AMD is not set +# CONFIG_PATA_ARTOP is not set +# CONFIG_PATA_ATIIXP is not set +# CONFIG_PATA_CMD640_PCI is not set +# CONFIG_PATA_CMD64X is not set +# CONFIG_PATA_CS5520 is not set +# CONFIG_PATA_CS5530 is not set +# CONFIG_PATA_CYPRESS is not set +# CONFIG_PATA_EFAR is not set +# CONFIG_ATA_GENERIC is not set +# CONFIG_PATA_HPT366 is not set +# CONFIG_PATA_HPT37X is not set +# CONFIG_PATA_HPT3X2N is not set +# CONFIG_PATA_HPT3X3 is not set +# CONFIG_PATA_IT821X is not set +# CONFIG_PATA_IT8213 is not set +# CONFIG_PATA_JMICRON is not set +# CONFIG_PATA_TRIFLEX is not set +# CONFIG_PATA_MARVELL is not set +# CONFIG_PATA_MPIIX is not set +# CONFIG_PATA_OLDPIIX is not set +# CONFIG_PATA_NETCELL is not set +# CONFIG_PATA_NS87410 is not set +# CONFIG_PATA_OPTI is not set +# CONFIG_PATA_OPTIDMA is not set +# CONFIG_PATA_PDC_OLD is not set +# CONFIG_PATA_RADISYS is not set +# CONFIG_PATA_RZ1000 is not set +# CONFIG_PATA_SC1200 is not set +# CONFIG_PATA_SERVERWORKS is not set +# CONFIG_PATA_PDC2027X is not set +# CONFIG_PATA_SIL680 is not set +# CONFIG_PATA_SIS is not set +# CONFIG_PATA_VIA is not set +# CONFIG_PATA_WINBOND is not set # CONFIG_PATA_PLATFORM is not set +# CONFIG_MD is not set # -# Multi-device support (RAID and LVM) +# Fusion MPT device support # -# CONFIG_MD is not set -# CONFIG_MACINTOSH_DRIVERS is not set +# CONFIG_FUSION is not set +# CONFIG_FUSION_SPI is not set +# CONFIG_FUSION_FC is not set +# CONFIG_FUSION_SAS is not set # -# Network device support +# IEEE 1394 (FireWire) support # +# CONFIG_FIREWIRE is not set +# CONFIG_IEEE1394 is not set +# CONFIG_I2O is not set +# CONFIG_MACINTOSH_DRIVERS is not set CONFIG_NETDEVICES=y +# CONFIG_NETDEVICES_MULTIQUEUE is not set # CONFIG_DUMMY is not set # CONFIG_BONDING is not set +# CONFIG_MACVLAN is not set # CONFIG_EQUALIZER is not set # CONFIG_TUN is not set +# CONFIG_ARCNET is not set CONFIG_PHYLIB=y # @@ -454,17 +538,44 @@ CONFIG_PHYLIB=y CONFIG_VITESSE_PHY=y # CONFIG_SMSC_PHY is not set # CONFIG_BROADCOM_PHY is not set +# CONFIG_ICPLUS_PHY is not set # CONFIG_FIXED_PHY is not set - -# -# Ethernet (10 or 100Mbit) -# CONFIG_NET_ETHERNET=y CONFIG_MII=y +# CONFIG_HAPPYMEAL is not set +# CONFIG_SUNGEM is not set +# CONFIG_CASSINI is not set +# CONFIG_NET_VENDOR_3COM is not set +# CONFIG_NET_TULIP is not set +# CONFIG_HP100 is not set +# CONFIG_NET_PCI is not set CONFIG_NETDEV_1000=y +# CONFIG_ACENIC is not set +# CONFIG_DL2K is not set +# CONFIG_E1000 is not set +# CONFIG_NS83820 is not set +# CONFIG_HAMACHI is not set +# CONFIG_YELLOWFIN is not set +# CONFIG_R8169 is not set +# CONFIG_SIS190 is not set +# CONFIG_SKGE is not set +# CONFIG_SKY2 is not set +# CONFIG_VIA_VELOCITY is not set +# CONFIG_TIGON3 is not set +# CONFIG_BNX2 is not set CONFIG_GIANFAR=y CONFIG_GFAR_NAPI=y +# CONFIG_QLA3XXX is not set +# CONFIG_ATL1 is not set CONFIG_NETDEV_10000=y +# CONFIG_CHELSIO_T1 is not set +# CONFIG_CHELSIO_T3 is not set +# CONFIG_IXGB is not set +# CONFIG_S2IO is not set +# CONFIG_MYRI10GE is not set +# CONFIG_NETXEN_NIC is not set +# CONFIG_MLX4_CORE is not set +# CONFIG_TR is not set # # Wireless LAN @@ -472,21 +583,16 @@ CONFIG_NETDEV_10000=y # CONFIG_WLAN_PRE80211 is not set # CONFIG_WLAN_80211 is not set # CONFIG_WAN is not set +# CONFIG_FDDI is not set +# CONFIG_HIPPI is not set # CONFIG_PPP is not set # CONFIG_SLIP is not set +# CONFIG_NET_FC is not set # CONFIG_SHAPER is not set # CONFIG_NETCONSOLE is not set # CONFIG_NETPOLL is not set # CONFIG_NET_POLL_CONTROLLER is not set - -# -# ISDN subsystem -# # CONFIG_ISDN is not set - -# -# Telephony Support -# # CONFIG_PHONE is not set # @@ -521,6 +627,7 @@ CONFIG_INPUT=y CONFIG_SERIO=y CONFIG_SERIO_I8042=y CONFIG_SERIO_SERPORT=y +# CONFIG_SERIO_PCIPS2 is not set CONFIG_SERIO_LIBPS2=y # CONFIG_SERIO_RAW is not set # CONFIG_GAMEPORT is not set @@ -539,6 +646,7 @@ CONFIG_HW_CONSOLE=y # CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y +CONFIG_SERIAL_8250_PCI=y CONFIG_SERIAL_8250_NR_UARTS=4 CONFIG_SERIAL_8250_RUNTIME_UARTS=4 # CONFIG_SERIAL_8250_EXTENDED is not set @@ -550,14 +658,11 @@ CONFIG_SERIAL_8250_SHARE_IRQ=y # CONFIG_SERIAL_UARTLITE is not set CONFIG_SERIAL_CORE=y CONFIG_SERIAL_CORE_CONSOLE=y +# CONFIG_SERIAL_JSM is not set # CONFIG_SERIAL_OF_PLATFORM is not set CONFIG_UNIX98_PTYS=y CONFIG_LEGACY_PTYS=y CONFIG_LEGACY_PTY_COUNT=256 - -# -# IPMI -# # CONFIG_IPMI_HANDLER is not set # CONFIG_WATCHDOG is not set # CONFIG_HW_RANDOM is not set @@ -565,12 +670,12 @@ CONFIG_NVRAM=y CONFIG_GEN_RTC=y CONFIG_GEN_RTC_X=y # CONFIG_R3964 is not set +# CONFIG_APPLICOM is not set +# CONFIG_AGP is not set +# CONFIG_DRM is not set # CONFIG_RAW_DRIVER is not set - -# -# TPM devices -# # CONFIG_TCG_TPM is not set +CONFIG_DEVPORT=y # CONFIG_I2C is not set # @@ -578,11 +683,8 @@ CONFIG_GEN_RTC_X=y # # CONFIG_SPI is not set # CONFIG_SPI_MASTER is not set - -# -# Dallas's 1-wire bus -# # CONFIG_W1 is not set +# CONFIG_POWER_SUPPLY is not set # CONFIG_HWMON is not set # @@ -655,19 +757,14 @@ CONFIG_DUMMY_CONSOLE=y # Sound # # CONFIG_SOUND is not set - -# -# HID Devices -# +CONFIG_HID_SUPPORT=y CONFIG_HID=y # CONFIG_HID_DEBUG is not set - -# -# USB support -# -# CONFIG_USB_ARCH_HAS_HCD is not set -# CONFIG_USB_ARCH_HAS_OHCI is not set -# CONFIG_USB_ARCH_HAS_EHCI is not set +CONFIG_USB_SUPPORT=y +CONFIG_USB_ARCH_HAS_HCD=y +CONFIG_USB_ARCH_HAS_OHCI=y +CONFIG_USB_ARCH_HAS_EHCI=y +# CONFIG_USB is not set # # NOTE: USB_STORAGE enables SCSI, and 'SCSI disk support' @@ -691,14 +788,7 @@ CONFIG_HID=y # # LED Triggers # - -# -# InfiniBand support -# - -# -# EDAC - error detection and reporting (RAS) (EXPERIMENTAL) -# +# CONFIG_INFINIBAND is not set # # Real Time Clock @@ -719,19 +809,13 @@ CONFIG_RTC_INTF_DEV=y # CONFIG_RTC_DRV_TEST is not set # -# I2C RTC drivers -# - -# -# SPI RTC drivers -# - -# # Platform RTC drivers # +# CONFIG_RTC_DRV_CMOS is not set # CONFIG_RTC_DRV_DS1553 is not set # CONFIG_RTC_DRV_DS1742 is not set # CONFIG_RTC_DRV_M48T86 is not set +# CONFIG_RTC_DRV_M48T59 is not set # CONFIG_RTC_DRV_V3020 is not set # @@ -752,6 +836,11 @@ CONFIG_RTC_INTF_DEV=y # # +# Userspace I/O +# +# CONFIG_UIO is not set + +# # File systems # CONFIG_EXT2_FS=y @@ -859,7 +948,6 @@ CONFIG_RPCSEC_GSS_KRB5=y # CONFIG_NCP_FS is not set # CONFIG_CODA_FS is not set # CONFIG_AFS_FS is not set -# CONFIG_9P_FS is not set # # Partition Types @@ -941,6 +1029,7 @@ CONFIG_BITREVERSE=y # CONFIG_CRC16 is not set # CONFIG_CRC_ITU_T is not set CONFIG_CRC32=y +# CONFIG_CRC7 is not set CONFIG_LIBCRC32C=m CONFIG_ZLIB_INFLATE=y CONFIG_PLIST=y @@ -965,6 +1054,7 @@ CONFIG_ENABLE_MUST_CHECK=y CONFIG_DEBUG_KERNEL=y # CONFIG_DEBUG_SHIRQ is not set CONFIG_DETECT_SOFTLOCKUP=y +CONFIG_SCHED_DEBUG=y # CONFIG_SCHEDSTATS is not set # CONFIG_TIMER_STATS is not set # CONFIG_DEBUG_SLAB is not set @@ -996,10 +1086,6 @@ CONFIG_FORCED_INLINING=y # # CONFIG_KEYS is not set # CONFIG_SECURITY is not set - -# -# Cryptographic options -# CONFIG_CRYPTO=y CONFIG_CRYPTO_ALGAPI=y CONFIG_CRYPTO_BLKCIPHER=y @@ -1038,7 +1124,4 @@ CONFIG_CRYPTO_DES=y # CONFIG_CRYPTO_CRC32C is not set # CONFIG_CRYPTO_CAMELLIA is not set # CONFIG_CRYPTO_TEST is not set - -# -# Hardware crypto devices -# +CONFIG_CRYPTO_HW=y Index: linux-rt-rebase.q/arch/powerpc/configs/mpc8568mds_defconfig =================================================================== --- linux-rt-rebase.q.orig/arch/powerpc/configs/mpc8568mds_defconfig +++ linux-rt-rebase.q/arch/powerpc/configs/mpc8568mds_defconfig @@ -1,9 +1,26 @@ # # Automatically generated make config: don't edit -# Linux kernel version: 2.6.22-rc7 -# Sun Jul 1 23:56:59 2007 +# Linux kernel version: 2.6.22 +# Fri Jul 20 13:55:04 2007 # # CONFIG_PPC64 is not set + +# +# Processor support +# +# CONFIG_6xx is not set +CONFIG_PPC_85xx=y +# CONFIG_PPC_8xx is not set +# CONFIG_40x is not set +# CONFIG_44x is not set +# CONFIG_E200 is not set +CONFIG_85xx=y +CONFIG_E500=y +CONFIG_BOOKE=y +CONFIG_FSL_BOOKE=y +# CONFIG_PHYS_64BIT is not set +CONFIG_SPE=y +# CONFIG_PPC_MM_SLICES is not set CONFIG_PPC32=y CONFIG_PPC_MERGE=y CONFIG_MMU=y @@ -14,6 +31,7 @@ CONFIG_ARCH_HAS_ILOG2_U32=y CONFIG_GENERIC_HWEIGHT=y CONFIG_GENERIC_CALIBRATE_DELAY=y CONFIG_GENERIC_FIND_NEXT_BIT=y +# CONFIG_ARCH_NO_VIRT_TO_BUS is not set CONFIG_PPC=y CONFIG_EARLY_PRINTK=y CONFIG_GENERIC_NVRAM=y @@ -25,28 +43,8 @@ CONFIG_PPC_UDBG_16550=y CONFIG_AUDIT_ARCH=y CONFIG_GENERIC_BUG=y CONFIG_DEFAULT_UIMAGE=y - -# -# Processor support -# -# CONFIG_CLASSIC32 is not set -# CONFIG_PPC_82xx is not set -# CONFIG_PPC_83xx is not set -CONFIG_PPC_85xx=y -# CONFIG_PPC_86xx is not set -# CONFIG_PPC_8xx is not set -# CONFIG_40x is not set -# CONFIG_44x is not set -# CONFIG_E200 is not set -CONFIG_85xx=y -CONFIG_E500=y # CONFIG_PPC_DCR_NATIVE is not set # CONFIG_PPC_DCR_MMIO is not set -CONFIG_BOOKE=y -CONFIG_FSL_BOOKE=y -# CONFIG_PHYS_64BIT is not set -CONFIG_SPE=y -# CONFIG_PPC_MM_SLICES is not set CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config" # @@ -63,12 +61,11 @@ CONFIG_LOCALVERSION="" CONFIG_LOCALVERSION_AUTO=y CONFIG_SWAP=y CONFIG_SYSVIPC=y -# CONFIG_IPC_NS is not set CONFIG_SYSVIPC_SYSCTL=y # CONFIG_POSIX_MQUEUE is not set # CONFIG_BSD_PROCESS_ACCT is not set # CONFIG_TASKSTATS is not set -# CONFIG_UTS_NS is not set +# CONFIG_USER_NS is not set # CONFIG_AUDIT is not set # CONFIG_IKCONFIG is not set CONFIG_LOG_BUF_SHIFT=14 @@ -100,24 +97,17 @@ CONFIG_SLAB=y CONFIG_RT_MUTEXES=y # CONFIG_TINY_SHMEM is not set CONFIG_BASE_SMALL=0 - -# -# Loadable module support -# CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y # CONFIG_MODULE_FORCE_UNLOAD is not set # CONFIG_MODVERSIONS is not set # CONFIG_MODULE_SRCVERSION_ALL is not set # CONFIG_KMOD is not set - -# -# Block layer -# CONFIG_BLOCK=y # CONFIG_LBD is not set # CONFIG_BLK_DEV_IO_TRACE is not set # CONFIG_LSF is not set +# CONFIG_BLK_DEV_BSG is not set # # IO Schedulers @@ -186,6 +176,8 @@ CONFIG_FLAT_NODE_MEM_MAP=y CONFIG_SPLIT_PTLOCK_CPUS=4 # CONFIG_RESOURCES_64BIT is not set CONFIG_ZONE_DMA_FLAG=1 +CONFIG_BOUNCE=y +CONFIG_VIRT_TO_BUS=y CONFIG_PROC_DEVICETREE=y # CONFIG_CMDLINE_BOOL is not set # CONFIG_PM is not set @@ -201,14 +193,20 @@ CONFIG_ZONE_DMA=y CONFIG_PPC_INDIRECT_PCI=y CONFIG_PPC_INDIRECT_PCI_BE=y CONFIG_FSL_SOC=y -# CONFIG_PCI is not set -# CONFIG_PCI_DOMAINS is not set -# CONFIG_ARCH_SUPPORTS_MSI is not set +CONFIG_FSL_PCI=y +CONFIG_PCI=y +CONFIG_PCI_DOMAINS=y +CONFIG_PCI_SYSCALL=y +# CONFIG_PCIEPORTBUS is not set +CONFIG_ARCH_SUPPORTS_MSI=y +# CONFIG_PCI_MSI is not set +# CONFIG_PCI_DEBUG is not set # # PCCARD (PCMCIA/CardBus) support # # CONFIG_PCCARD is not set +# CONFIG_HOTPLUG_PCI is not set # # Advanced setup @@ -309,6 +307,7 @@ CONFIG_DEFAULT_TCP_CONG="cubic" # CONFIG_MAC80211 is not set # CONFIG_IEEE80211 is not set # CONFIG_RFKILL is not set +# CONFIG_NET_9P is not set # # Device Drivers @@ -323,42 +322,31 @@ CONFIG_PREVENT_FIRMWARE_BUILD=y # CONFIG_DEBUG_DRIVER is not set # CONFIG_DEBUG_DEVRES is not set # CONFIG_SYS_HYPERVISOR is not set - -# -# Connector - unified userspace <-> kernelspace linker -# # CONFIG_CONNECTOR is not set # CONFIG_MTD is not set - -# -# Parallel port support -# # CONFIG_PARPORT is not set - -# -# Plug and Play support -# -# CONFIG_PNPACPI is not set - -# -# Block devices -# +CONFIG_BLK_DEV=y # CONFIG_BLK_DEV_FD is not set +# CONFIG_BLK_CPQ_DA is not set +# CONFIG_BLK_CPQ_CISS_DA is not set +# CONFIG_BLK_DEV_DAC960 is not set +# CONFIG_BLK_DEV_UMEM is not set # CONFIG_BLK_DEV_COW_COMMON is not set CONFIG_BLK_DEV_LOOP=y # CONFIG_BLK_DEV_CRYPTOLOOP is not set # CONFIG_BLK_DEV_NBD is not set +# CONFIG_BLK_DEV_SX8 is not set CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_RAM_COUNT=16 CONFIG_BLK_DEV_RAM_SIZE=32768 CONFIG_BLK_DEV_RAM_BLOCKSIZE=1024 # CONFIG_CDROM_PKTCDVD is not set # CONFIG_ATA_OVER_ETH is not set - -# -# Misc devices -# -# CONFIG_BLINK is not set +CONFIG_MISC_DEVICES=y +# CONFIG_PHANTOM is not set +# CONFIG_EEPROM_93CX6 is not set +# CONFIG_SGI_IOC4 is not set +# CONFIG_TIFM_CORE is not set # CONFIG_IDE is not set # @@ -366,6 +354,7 @@ CONFIG_BLK_DEV_RAM_BLOCKSIZE=1024 # # CONFIG_RAID_ATTRS is not set CONFIG_SCSI=y +CONFIG_SCSI_DMA=y # CONFIG_SCSI_TGT is not set # CONFIG_SCSI_NETLINK is not set CONFIG_SCSI_PROC_FS=y @@ -402,23 +391,65 @@ CONFIG_SCSI_WAIT_SCAN=m # SCSI low-level drivers # # CONFIG_ISCSI_TCP is not set +# CONFIG_BLK_DEV_3W_XXXX_RAID is not set +# CONFIG_SCSI_3W_9XXX is not set +# CONFIG_SCSI_ACARD is not set +# CONFIG_SCSI_AACRAID is not set +# CONFIG_SCSI_AIC7XXX is not set +# CONFIG_SCSI_AIC7XXX_OLD is not set +# CONFIG_SCSI_AIC79XX is not set +# CONFIG_SCSI_AIC94XX is not set +# CONFIG_SCSI_DPT_I2O is not set +# CONFIG_SCSI_ARCMSR is not set +# CONFIG_MEGARAID_NEWGEN is not set +# CONFIG_MEGARAID_LEGACY is not set +# CONFIG_MEGARAID_SAS is not set +# CONFIG_SCSI_HPTIOP is not set +# CONFIG_SCSI_BUSLOGIC is not set +# CONFIG_SCSI_DMX3191D is not set +# CONFIG_SCSI_EATA is not set +# CONFIG_SCSI_FUTURE_DOMAIN is not set +# CONFIG_SCSI_GDTH is not set +# CONFIG_SCSI_IPS is not set +# CONFIG_SCSI_INITIO is not set +# CONFIG_SCSI_INIA100 is not set +# CONFIG_SCSI_STEX is not set +# CONFIG_SCSI_SYM53C8XX_2 is not set +# CONFIG_SCSI_QLOGIC_1280 is not set +# CONFIG_SCSI_QLA_FC is not set +# CONFIG_SCSI_QLA_ISCSI is not set +# CONFIG_SCSI_LPFC is not set +# CONFIG_SCSI_DC395x is not set +# CONFIG_SCSI_DC390T is not set +# CONFIG_SCSI_NSP32 is not set # CONFIG_SCSI_DEBUG is not set +# CONFIG_SCSI_SRP is not set # CONFIG_ATA is not set +# CONFIG_MD is not set # -# Multi-device support (RAID and LVM) +# Fusion MPT device support # -# CONFIG_MD is not set -# CONFIG_MACINTOSH_DRIVERS is not set +# CONFIG_FUSION is not set +# CONFIG_FUSION_SPI is not set +# CONFIG_FUSION_FC is not set +# CONFIG_FUSION_SAS is not set # -# Network device support +# IEEE 1394 (FireWire) support # +# CONFIG_FIREWIRE is not set +# CONFIG_IEEE1394 is not set +# CONFIG_I2O is not set +# CONFIG_MACINTOSH_DRIVERS is not set CONFIG_NETDEVICES=y +# CONFIG_NETDEVICES_MULTIQUEUE is not set # CONFIG_DUMMY is not set # CONFIG_BONDING is not set +# CONFIG_MACVLAN is not set # CONFIG_EQUALIZER is not set # CONFIG_TUN is not set +# CONFIG_ARCNET is not set CONFIG_PHYLIB=y # @@ -432,17 +463,44 @@ CONFIG_MARVELL_PHY=y # CONFIG_VITESSE_PHY is not set # CONFIG_SMSC_PHY is not set # CONFIG_BROADCOM_PHY is not set +# CONFIG_ICPLUS_PHY is not set # CONFIG_FIXED_PHY is not set - -# -# Ethernet (10 or 100Mbit) -# CONFIG_NET_ETHERNET=y CONFIG_MII=y +# CONFIG_HAPPYMEAL is not set +# CONFIG_SUNGEM is not set +# CONFIG_CASSINI is not set +# CONFIG_NET_VENDOR_3COM is not set +# CONFIG_NET_TULIP is not set +# CONFIG_HP100 is not set +# CONFIG_NET_PCI is not set CONFIG_NETDEV_1000=y +# CONFIG_ACENIC is not set +# CONFIG_DL2K is not set +# CONFIG_E1000 is not set +# CONFIG_NS83820 is not set +# CONFIG_HAMACHI is not set +# CONFIG_YELLOWFIN is not set +# CONFIG_R8169 is not set +# CONFIG_SIS190 is not set +# CONFIG_SKGE is not set +# CONFIG_SKY2 is not set +# CONFIG_VIA_VELOCITY is not set +# CONFIG_TIGON3 is not set +# CONFIG_BNX2 is not set CONFIG_GIANFAR=y CONFIG_GFAR_NAPI=y +# CONFIG_QLA3XXX is not set +# CONFIG_ATL1 is not set CONFIG_NETDEV_10000=y +# CONFIG_CHELSIO_T1 is not set +# CONFIG_CHELSIO_T3 is not set +# CONFIG_IXGB is not set +# CONFIG_S2IO is not set +# CONFIG_MYRI10GE is not set +# CONFIG_NETXEN_NIC is not set +# CONFIG_MLX4_CORE is not set +# CONFIG_TR is not set # # Wireless LAN @@ -450,21 +508,16 @@ CONFIG_NETDEV_10000=y # CONFIG_WLAN_PRE80211 is not set # CONFIG_WLAN_80211 is not set # CONFIG_WAN is not set +# CONFIG_FDDI is not set +# CONFIG_HIPPI is not set # CONFIG_PPP is not set # CONFIG_SLIP is not set +# CONFIG_NET_FC is not set # CONFIG_SHAPER is not set # CONFIG_NETCONSOLE is not set # CONFIG_NETPOLL is not set # CONFIG_NET_POLL_CONTROLLER is not set - -# -# ISDN subsystem -# # CONFIG_ISDN is not set - -# -# Telephony Support -# # CONFIG_PHONE is not set # @@ -510,6 +563,7 @@ CONFIG_INPUT=y # CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y +CONFIG_SERIAL_8250_PCI=y CONFIG_SERIAL_8250_NR_UARTS=4 CONFIG_SERIAL_8250_RUNTIME_UARTS=4 # CONFIG_SERIAL_8250_EXTENDED is not set @@ -521,14 +575,11 @@ CONFIG_SERIAL_8250_SHARE_IRQ=y # CONFIG_SERIAL_UARTLITE is not set CONFIG_SERIAL_CORE=y CONFIG_SERIAL_CORE_CONSOLE=y +# CONFIG_SERIAL_JSM is not set # CONFIG_SERIAL_OF_PLATFORM is not set CONFIG_UNIX98_PTYS=y CONFIG_LEGACY_PTYS=y CONFIG_LEGACY_PTY_COUNT=256 - -# -# IPMI -# # CONFIG_IPMI_HANDLER is not set CONFIG_WATCHDOG=y # CONFIG_WATCHDOG_NOWAYOUT is not set @@ -538,17 +589,23 @@ CONFIG_WATCHDOG=y # # CONFIG_SOFT_WATCHDOG is not set # CONFIG_BOOKE_WDT is not set + +# +# PCI-based Watchdog Cards +# +# CONFIG_PCIPCWATCHDOG is not set +# CONFIG_WDTPCI is not set CONFIG_HW_RANDOM=y # CONFIG_NVRAM is not set CONFIG_GEN_RTC=y # CONFIG_GEN_RTC_X is not set # CONFIG_R3964 is not set +# CONFIG_APPLICOM is not set +# CONFIG_AGP is not set +# CONFIG_DRM is not set # CONFIG_RAW_DRIVER is not set - -# -# TPM devices -# # CONFIG_TCG_TPM is not set +CONFIG_DEVPORT=y CONFIG_I2C=y CONFIG_I2C_BOARDINFO=y CONFIG_I2C_CHARDEV=y @@ -563,23 +620,43 @@ CONFIG_I2C_CHARDEV=y # # I2C Hardware Bus support # +# CONFIG_I2C_ALI1535 is not set +# CONFIG_I2C_ALI1563 is not set +# CONFIG_I2C_ALI15X3 is not set +# CONFIG_I2C_AMD756 is not set +# CONFIG_I2C_AMD8111 is not set +# CONFIG_I2C_I801 is not set +# CONFIG_I2C_I810 is not set +# CONFIG_I2C_PIIX4 is not set CONFIG_I2C_MPC=y +# CONFIG_I2C_NFORCE2 is not set # CONFIG_I2C_OCORES is not set # CONFIG_I2C_PARPORT_LIGHT is not set +# CONFIG_I2C_PROSAVAGE is not set +# CONFIG_I2C_SAVAGE4 is not set # CONFIG_I2C_SIMTEC is not set +# CONFIG_I2C_SIS5595 is not set +# CONFIG_I2C_SIS630 is not set +# CONFIG_I2C_SIS96X is not set +# CONFIG_I2C_TAOS_EVM is not set # CONFIG_I2C_STUB is not set +# CONFIG_I2C_VIA is not set +# CONFIG_I2C_VIAPRO is not set +# CONFIG_I2C_VOODOO3 is not set # # Miscellaneous I2C Chip support # # CONFIG_SENSORS_DS1337 is not set # CONFIG_SENSORS_DS1374 is not set +# CONFIG_DS1682 is not set # CONFIG_SENSORS_EEPROM is not set # CONFIG_SENSORS_PCF8574 is not set # CONFIG_SENSORS_PCA9539 is not set # CONFIG_SENSORS_PCF8591 is not set # CONFIG_SENSORS_M41T00 is not set # CONFIG_SENSORS_MAX6875 is not set +# CONFIG_SENSORS_TSL2550 is not set # CONFIG_I2C_DEBUG_CORE is not set # CONFIG_I2C_DEBUG_ALGO is not set # CONFIG_I2C_DEBUG_BUS is not set @@ -590,11 +667,8 @@ CONFIG_I2C_MPC=y # # CONFIG_SPI is not set # CONFIG_SPI_MASTER is not set - -# -# Dallas's 1-wire bus -# # CONFIG_W1 is not set +# CONFIG_POWER_SUPPLY is not set CONFIG_HWMON=y # CONFIG_HWMON_VID is not set # CONFIG_SENSORS_ABITUGURU is not set @@ -628,10 +702,13 @@ CONFIG_HWMON=y # CONFIG_SENSORS_MAX6650 is not set # CONFIG_SENSORS_PC87360 is not set # CONFIG_SENSORS_PC87427 is not set +# CONFIG_SENSORS_SIS5595 is not set # CONFIG_SENSORS_SMSC47M1 is not set # CONFIG_SENSORS_SMSC47M192 is not set # CONFIG_SENSORS_SMSC47B397 is not set +# CONFIG_SENSORS_VIA686A is not set # CONFIG_SENSORS_VT1211 is not set +# CONFIG_SENSORS_VT8231 is not set # CONFIG_SENSORS_W83781D is not set # CONFIG_SENSORS_W83791D is not set # CONFIG_SENSORS_W83792D is not set @@ -670,19 +747,14 @@ CONFIG_DAB=y # Sound # # CONFIG_SOUND is not set - -# -# HID Devices -# +CONFIG_HID_SUPPORT=y CONFIG_HID=y # CONFIG_HID_DEBUG is not set - -# -# USB support -# -# CONFIG_USB_ARCH_HAS_HCD is not set -# CONFIG_USB_ARCH_HAS_OHCI is not set -# CONFIG_USB_ARCH_HAS_EHCI is not set +CONFIG_USB_SUPPORT=y +CONFIG_USB_ARCH_HAS_HCD=y +CONFIG_USB_ARCH_HAS_OHCI=y +CONFIG_USB_ARCH_HAS_EHCI=y +# CONFIG_USB is not set # # NOTE: USB_STORAGE enables SCSI, and 'SCSI disk support' @@ -706,14 +778,7 @@ CONFIG_HID=y # # LED Triggers # - -# -# InfiniBand support -# - -# -# EDAC - error detection and reporting (RAS) (EXPERIMENTAL) -# +# CONFIG_INFINIBAND is not set # # Real Time Clock @@ -734,6 +799,11 @@ CONFIG_HID=y # # +# Userspace I/O +# +# CONFIG_UIO is not set + +# # File systems # CONFIG_EXT2_FS=y @@ -829,7 +899,6 @@ CONFIG_RPCSEC_GSS_KRB5=y # CONFIG_NCP_FS is not set # CONFIG_CODA_FS is not set # CONFIG_AFS_FS is not set -# CONFIG_9P_FS is not set # # Partition Types @@ -868,6 +937,7 @@ CONFIG_BITREVERSE=y # CONFIG_CRC16 is not set # CONFIG_CRC_ITU_T is not set CONFIG_CRC32=y +# CONFIG_CRC7 is not set # CONFIG_LIBCRC32C is not set CONFIG_PLIST=y CONFIG_HAS_IOMEM=y @@ -892,6 +962,7 @@ CONFIG_ENABLE_MUST_CHECK=y CONFIG_DEBUG_KERNEL=y # CONFIG_DEBUG_SHIRQ is not set CONFIG_DETECT_SOFTLOCKUP=y +CONFIG_SCHED_DEBUG=y # CONFIG_SCHEDSTATS is not set # CONFIG_TIMER_STATS is not set # CONFIG_DEBUG_SLAB is not set @@ -915,7 +986,7 @@ CONFIG_FORCED_INLINING=y CONFIG_DEBUGGER=y # CONFIG_XMON is not set # CONFIG_BDI_SWITCH is not set -CONFIG_BOOTX_TEXT=y +# CONFIG_BOOTX_TEXT is not set CONFIG_PPC_EARLY_DEBUG=y # CONFIG_PPC_EARLY_DEBUG_LPAR is not set # CONFIG_PPC_EARLY_DEBUG_G5 is not set @@ -932,10 +1003,6 @@ CONFIG_PPC_EARLY_DEBUG=y # # CONFIG_KEYS is not set # CONFIG_SECURITY is not set - -# -# Cryptographic options -# CONFIG_CRYPTO=y CONFIG_CRYPTO_ALGAPI=y CONFIG_CRYPTO_BLKCIPHER=y @@ -973,7 +1040,4 @@ CONFIG_CRYPTO_DES=y # CONFIG_CRYPTO_CRC32C is not set # CONFIG_CRYPTO_CAMELLIA is not set # CONFIG_CRYPTO_TEST is not set - -# -# Hardware crypto devices -# +CONFIG_CRYPTO_HW=y Index: linux-rt-rebase.q/arch/powerpc/kernel/Makefile =================================================================== --- linux-rt-rebase.q.orig/arch/powerpc/kernel/Makefile +++ linux-rt-rebase.q/arch/powerpc/kernel/Makefile @@ -10,11 +10,12 @@ CFLAGS_prom_init.o += -fPIC CFLAGS_btext.o += -fPIC endif -obj-y := semaphore.o cputable.o ptrace.o syscalls.o \ +obj-y := cputable.o ptrace.o syscalls.o \ irq.o align.o signal_32.o pmc.o vdso.o \ init_task.o process.o systbl.o idle.o \ signal.o obj-y += vdso32/ +obj-$(CONFIG_ASM_SEMAPHORES) += semaphore.o obj-$(CONFIG_PPC64) += setup_64.o binfmt_elf32.o sys_ppc32.o \ signal_64.o ptrace32.o \ paca.o cpu_setup_ppc970.o \ Index: linux-rt-rebase.q/arch/powerpc/kernel/asm-offsets.c =================================================================== --- linux-rt-rebase.q.orig/arch/powerpc/kernel/asm-offsets.c +++ linux-rt-rebase.q/arch/powerpc/kernel/asm-offsets.c @@ -273,16 +273,7 @@ int main(void) #endif /* ! CONFIG_PPC64 */ /* datapage offsets for use by vdso */ - DEFINE(CFG_TB_ORIG_STAMP, offsetof(struct vdso_data, tb_orig_stamp)); - DEFINE(CFG_TB_TICKS_PER_SEC, offsetof(struct vdso_data, tb_ticks_per_sec)); - DEFINE(CFG_TB_TO_XS, offsetof(struct vdso_data, tb_to_xs)); - DEFINE(CFG_STAMP_XSEC, offsetof(struct vdso_data, stamp_xsec)); - DEFINE(CFG_TB_UPDATE_COUNT, offsetof(struct vdso_data, tb_update_count)); - DEFINE(CFG_TZ_MINUTEWEST, offsetof(struct vdso_data, tz_minuteswest)); - DEFINE(CFG_TZ_DSTTIME, offsetof(struct vdso_data, tz_dsttime)); DEFINE(CFG_SYSCALL_MAP32, offsetof(struct vdso_data, syscall_map_32)); - DEFINE(WTOM_CLOCK_SEC, offsetof(struct vdso_data, wtom_clock_sec)); - DEFINE(WTOM_CLOCK_NSEC, offsetof(struct vdso_data, wtom_clock_nsec)); #ifdef CONFIG_PPC64 DEFINE(CFG_SYSCALL_MAP64, offsetof(struct vdso_data, syscall_map_64)); DEFINE(TVAL64_TV_SEC, offsetof(struct timeval, tv_sec)); @@ -303,12 +294,6 @@ int main(void) DEFINE(TZONE_TZ_MINWEST, offsetof(struct timezone, tz_minuteswest)); DEFINE(TZONE_TZ_DSTTIME, offsetof(struct timezone, tz_dsttime)); - /* Other bits used by the vdso */ - DEFINE(CLOCK_REALTIME, CLOCK_REALTIME); - DEFINE(CLOCK_MONOTONIC, CLOCK_MONOTONIC); - DEFINE(NSEC_PER_SEC, NSEC_PER_SEC); - DEFINE(CLOCK_REALTIME_RES, TICK_NSEC); - #ifdef CONFIG_BUG DEFINE(BUG_ENTRY_SIZE, sizeof(struct bug_entry)); #endif Index: linux-rt-rebase.q/arch/powerpc/kernel/entry_32.S =================================================================== --- linux-rt-rebase.q.orig/arch/powerpc/kernel/entry_32.S +++ linux-rt-rebase.q/arch/powerpc/kernel/entry_32.S @@ -641,7 +641,7 @@ user_exc_return: /* r10 contains MSR_KE /* Check current_thread_info()->flags */ rlwinm r9,r1,0,0,(31-THREAD_SHIFT) lwz r9,TI_FLAGS(r9) - andi. r0,r9,(_TIF_SIGPENDING|_TIF_RESTORE_SIGMASK|_TIF_NEED_RESCHED) + andi. r0,r9,(_TIF_SIGPENDING|_TIF_RESTORE_SIGMASK|_TIF_NEED_RESCHED|_TIF_NEED_RESCHED_DELAYED) bne do_work restore_user: @@ -863,7 +863,7 @@ global_dbcr0: #endif /* !(CONFIG_4xx || CONFIG_BOOKE) */ do_work: /* r10 contains MSR_KERNEL here */ - andi. r0,r9,_TIF_NEED_RESCHED + andi. r0,r9,(_TIF_NEED_RESCHED|_TIF_NEED_RESCHED_DELAYED) beq do_user_signal do_resched: /* r10 contains MSR_KERNEL here */ @@ -877,7 +877,7 @@ recheck: MTMSRD(r10) /* disable interrupts */ rlwinm r9,r1,0,0,(31-THREAD_SHIFT) lwz r9,TI_FLAGS(r9) - andi. r0,r9,_TIF_NEED_RESCHED + andi. r0,r9,(_TIF_NEED_RESCHED|_TIF_NEED_RESCHED_DELAYED) bne- do_resched andi. r0,r9,_TIF_SIGPENDING|_TIF_RESTORE_SIGMASK beq restore_user @@ -989,3 +989,85 @@ machine_check_in_rtas: /* XXX load up BATs and panic */ #endif /* CONFIG_PPC_RTAS */ + +#ifdef CONFIG_MCOUNT +/* + * mcount() is not the same as _mcount(). The callers of mcount() have a + * normal context. The callers of _mcount() do not have a stack frame and + * have not saved the "caller saves" registers. + */ +_GLOBAL(mcount) + stwu r1,-16(r1) + mflr r3 + lis r5,mcount_enabled@ha + lwz r5,mcount_enabled@l(r5) + stw r3,20(r1) + cmpwi r5,0 + beq 1f + /* r3 contains lr (eip), put parent lr (parent_eip) in r4 */ + lwz r4,16(r1) + lwz r4,4(r4) + bl __trace +1: + lwz r0,20(r1) + mtlr r0 + addi r1,r1,16 + blr + +/* + * The -pg flag, which is specified in the case of CONFIG_MCOUNT, causes the + * C compiler to add a call to _mcount() at the start of each function + * preamble, before the stack frame is created. An example of this preamble + * code is: + * + * mflr r0 + * lis r12,-16354 + * stw r0,4(r1) + * addi r0,r12,-19652 + * bl 0xc00034c8 <_mcount> + * mflr r0 + * stwu r1,-16(r1) + */ +_GLOBAL(_mcount) +#define M_STK_SIZE 48 + /* Would not expect to need to save cr, but glibc version of */ + /* _mcount() does, so cautiously saving it here too. */ + stwu r1,-M_STK_SIZE(r1) + stw r3, 12(r1) + stw r4, 16(r1) + stw r5, 20(r1) + stw r6, 24(r1) + mflr r3 /* will use as first arg to __trace() */ + mfcr r4 + lis r5,mcount_enabled@ha + lwz r5,mcount_enabled@l(r5) + cmpwi r5,0 + stw r3, 44(r1) /* lr */ + stw r4, 8(r1) /* cr */ + stw r7, 28(r1) + stw r8, 32(r1) + stw r9, 36(r1) + stw r10,40(r1) + beq 1f + /* r3 contains lr (eip), put parent lr (parent_eip) in r4 */ + lwz r4,M_STK_SIZE+4(r1) + bl __trace +1: + lwz r8, 8(r1) /* cr */ + lwz r9, 44(r1) /* lr */ + lwz r3, 12(r1) + lwz r4, 16(r1) + lwz r5, 20(r1) + mtcrf 0xff,r8 + mtctr r9 + lwz r0, 52(r1) + lwz r6, 24(r1) + lwz r7, 28(r1) + lwz r8, 32(r1) + lwz r9, 36(r1) + lwz r10,40(r1) + addi r1,r1,M_STK_SIZE + mtlr r0 + bctr + +#endif /* CONFIG_MCOUNT */ Index: linux-rt-rebase.q/arch/powerpc/kernel/entry_64.S =================================================================== --- linux-rt-rebase.q.orig/arch/powerpc/kernel/entry_64.S +++ linux-rt-rebase.q/arch/powerpc/kernel/entry_64.S @@ -449,7 +449,8 @@ _GLOBAL(ret_from_except_lite) #ifdef CONFIG_PREEMPT clrrdi r9,r1,THREAD_SHIFT /* current_thread_info() */ - li r0,_TIF_NEED_RESCHED /* bits to check */ + li r0,(_TIF_NEED_RESCHED|_TIF_NEED_RESCHED_DELAYED) + /* bits to check */ ld r3,_MSR(r1) ld r4,TI_FLAGS(r9) /* Move MSR_PR bit in r3 to _TIF_SIGPENDING position in r0 */ @@ -572,17 +573,22 @@ do_work: rotldi r10,r10,16 mtmsrd r10,1 ld r4,TI_FLAGS(r9) - andi. r0,r4,_TIF_NEED_RESCHED + andi. r0,r4,(_TIF_NEED_RESCHED|_TIF_NEED_RESCHED_DELAYED) bne 1b b restore user_work: #endif + /* here we are preempting the current task */ + li r0,1 + stb r0,PACASOFTIRQEN(r13) + stb r0,PACAHARDIRQEN(r13) + /* Enable interrupts */ ori r10,r10,MSR_EE mtmsrd r10,1 - andi. r0,r4,_TIF_NEED_RESCHED + andi. r0,r4,(_TIF_NEED_RESCHED|_TIF_NEED_RESCHED_DELAYED) beq 1f bl .schedule b .ret_from_except_lite @@ -826,3 +832,63 @@ _GLOBAL(enter_prom) ld r0,16(r1) mtlr r0 blr + +#ifdef CONFIG_MCOUNT +/* + * code almost taken from entry_32.S + */ +#define MCOUNT_FRAME_SIZE 32 +_GLOBAL(mcount) + stdu r1,-MCOUNT_FRAME_SIZE(r1) + mflr r3 + + LOAD_REG_ADDR(r5,mcount_enabled) + lwz r5,0(r5) + std r3,MCOUNT_FRAME_SIZE+16(r1) + cmpwi r5,0 + beq 1f + + /* r3 contains lr (eip), put parent lr (parent_eip) in r4 */ + ld r4,MCOUNT_FRAME_SIZE(r1) + ld r4,16(r4) + bl .__trace + nop +1: + ld r0,MCOUNT_FRAME_SIZE+16(r1) + mtlr r0 + addi r1,r1,MCOUNT_FRAME_SIZE + blr + +/* + * Based on glibc-2.4/sysdeps/powerpc/powerpc64/ppc-mcount.S + * + * We don't need to save the parameter-passing registers as gcc takes + * care of that for us. Thus this function looks fairly normal. + * In fact, the generic code would work for us. + */ +_GLOBAL(_mcount) + /* return if we're in real mode. */ + mfmsr r3 + andi. r0,r3,MSR_IR|MSR_DR /* see if relocation is on? */ + beqlr /* if not, do nothing. */ + /* we're in translation mode. keep going. */ + mflr r3 + ld r11,0(r1) /* load back chain ptr */ + stdu r1,-STACK_FRAME_OVERHEAD(r1) + std r3,STACK_FRAME_OVERHEAD+16(r1) + ld r4,16(r11) /* LR in back chain */ + LOAD_REG_ADDR(r5,mcount_enabled) + lwz r5,0(r5) + cmpwi r5,0 /* see if mcount_enabled? */ + beq 1f /* if disabled, then skip */ + + /* r3 contains lr (eip), put parent lr (parent_eip) in r4 */ + bl .__trace + nop +1: + ld r0,STACK_FRAME_OVERHEAD+16(r1) /* restore saved LR */ + mtlr r0 + addi r1,r1,STACK_FRAME_OVERHEAD + blr + +#endif /* CONFIG_MCOUNT */ Index: linux-rt-rebase.q/arch/powerpc/kernel/head_64.S =================================================================== --- linux-rt-rebase.q.orig/arch/powerpc/kernel/head_64.S +++ linux-rt-rebase.q/arch/powerpc/kernel/head_64.S @@ -1391,7 +1391,7 @@ END_FW_FTR_SECTION_IFCLR(FW_FEATURE_ISER * handles any interrupts pending at this point. */ ld r3,SOFTE(r1) - bl .local_irq_restore + bl .raw_local_irq_restore b 11f /* Here we have a page fault that hash_page can't handle. */ Index: linux-rt-rebase.q/arch/powerpc/kernel/idle.c =================================================================== --- linux-rt-rebase.q.orig/arch/powerpc/kernel/idle.c +++ linux-rt-rebase.q/arch/powerpc/kernel/idle.c @@ -24,6 +24,7 @@ #include #include #include +#include #include #include @@ -59,7 +60,9 @@ void cpu_idle(void) set_thread_flag(TIF_POLLING_NRFLAG); while (1) { - while (!need_resched() && !cpu_should_die()) { + tick_nohz_stop_sched_tick(); + while (!need_resched() && !need_resched_delayed() && + !cpu_should_die()) { ppc64_runlatch_off(); if (ppc_md.power_save) { @@ -72,7 +75,9 @@ void cpu_idle(void) local_irq_disable(); /* check again after disabling irqs */ - if (!need_resched() && !cpu_should_die()) + if (!need_resched() && + !need_resched_delayed() && + !cpu_should_die()) ppc_md.power_save(); local_irq_enable(); @@ -92,7 +97,10 @@ void cpu_idle(void) ppc64_runlatch_on(); if (cpu_should_die()) cpu_die(); - preempt_enable_no_resched(); + + tick_nohz_restart_sched_tick(); + + __preempt_enable_no_resched(); schedule(); preempt_disable(); } Index: linux-rt-rebase.q/arch/powerpc/kernel/irq.c =================================================================== --- linux-rt-rebase.q.orig/arch/powerpc/kernel/irq.c +++ linux-rt-rebase.q/arch/powerpc/kernel/irq.c @@ -93,8 +93,6 @@ extern atomic_t ipi_sent; #endif #ifdef CONFIG_PPC64 -EXPORT_SYMBOL(irq_desc); - int distribute_irqs = 1; static inline unsigned long get_hard_enabled(void) @@ -113,7 +111,7 @@ static inline void set_soft_enabled(unsi : : "r" (enable), "i" (offsetof(struct paca_struct, soft_enabled))); } -void local_irq_restore(unsigned long en) +void notrace raw_local_irq_restore(unsigned long en) { /* * get_paca()->soft_enabled = en; @@ -405,7 +403,7 @@ EXPORT_SYMBOL(do_softirq); #ifdef CONFIG_PPC_MERGE static LIST_HEAD(irq_hosts); -static DEFINE_SPINLOCK(irq_big_lock); +static DEFINE_RAW_SPINLOCK(irq_big_lock); static DEFINE_PER_CPU(unsigned int, irq_radix_reader); static unsigned int irq_radix_writer; struct irq_map_entry irq_map[NR_IRQS]; Index: linux-rt-rebase.q/arch/powerpc/kernel/pci_32.c =================================================================== --- linux-rt-rebase.q.orig/arch/powerpc/kernel/pci_32.c +++ linux-rt-rebase.q/arch/powerpc/kernel/pci_32.c @@ -415,15 +415,13 @@ probe_resource(struct pci_bus *parent, s return 0; } -static void __init -update_bridge_base(struct pci_bus *bus, int i) +void __init +update_bridge_resource(struct pci_dev *dev, struct resource *res) { - struct resource *res = bus->resource[i]; u8 io_base_lo, io_limit_lo; u16 mem_base, mem_limit; u16 cmd; unsigned long start, end, off; - struct pci_dev *dev = bus->self; struct pci_controller *hose = dev->sysdata; if (!hose) { @@ -467,12 +465,20 @@ update_bridge_base(struct pci_bus *bus, pci_write_config_word(dev, PCI_PREF_MEMORY_LIMIT, mem_limit); } else { - DBG(KERN_ERR "PCI: ugh, bridge %s res %d has flags=%lx\n", - pci_name(dev), i, res->flags); + DBG(KERN_ERR "PCI: ugh, bridge %s res has flags=%lx\n", + pci_name(dev), res->flags); } pci_write_config_word(dev, PCI_COMMAND, cmd); } +static void __init +update_bridge_base(struct pci_bus *bus, int i) +{ + struct resource *res = bus->resource[i]; + struct pci_dev *dev = bus->self; + update_bridge_resource(dev, res); +} + static inline void alloc_resource(struct pci_dev *dev, int idx) { struct resource *pr, *r = &dev->resource[idx]; @@ -1468,3 +1474,10 @@ EARLY_PCI_OP(read, dword, u32 *) EARLY_PCI_OP(write, byte, u8) EARLY_PCI_OP(write, word, u16) EARLY_PCI_OP(write, dword, u32) + +extern int pci_bus_find_capability (struct pci_bus *bus, unsigned int devfn, int cap); +int early_find_capability(struct pci_controller *hose, int bus, int devfn, + int cap) +{ + return pci_bus_find_capability(fake_pci_bus(hose, bus), devfn, cap); +} Index: linux-rt-rebase.q/arch/powerpc/kernel/pmc.c =================================================================== --- linux-rt-rebase.q.orig/arch/powerpc/kernel/pmc.c +++ linux-rt-rebase.q/arch/powerpc/kernel/pmc.c @@ -37,7 +37,7 @@ static void dummy_perf(struct pt_regs *r } -static DEFINE_SPINLOCK(pmc_owner_lock); +static DEFINE_RAW_SPINLOCK(pmc_owner_lock); static void *pmc_owner_caller; /* mostly for debugging */ perf_irq_t perf_irq = dummy_perf; Index: linux-rt-rebase.q/arch/powerpc/kernel/ppc_ksyms.c =================================================================== --- linux-rt-rebase.q.orig/arch/powerpc/kernel/ppc_ksyms.c +++ linux-rt-rebase.q/arch/powerpc/kernel/ppc_ksyms.c @@ -16,7 +16,6 @@ #include #include -#include #include #include #include @@ -50,7 +49,7 @@ #endif #ifdef CONFIG_PPC64 -EXPORT_SYMBOL(local_irq_restore); +EXPORT_SYMBOL(raw_local_irq_restore); #endif #ifdef CONFIG_PPC32 @@ -170,7 +169,6 @@ EXPORT_SYMBOL(screen_info); #ifdef CONFIG_PPC32 EXPORT_SYMBOL(timer_interrupt); -EXPORT_SYMBOL(irq_desc); EXPORT_SYMBOL(tb_ticks_per_jiffy); EXPORT_SYMBOL(console_drivers); EXPORT_SYMBOL(cacheable_memcpy); Index: linux-rt-rebase.q/arch/powerpc/kernel/rtas.c =================================================================== --- linux-rt-rebase.q.orig/arch/powerpc/kernel/rtas.c +++ linux-rt-rebase.q/arch/powerpc/kernel/rtas.c @@ -36,7 +36,7 @@ #include struct rtas_t rtas = { - .lock = SPIN_LOCK_UNLOCKED + .lock = RAW_SPIN_LOCK_UNLOCKED(lock) }; EXPORT_SYMBOL(rtas); Index: linux-rt-rebase.q/arch/powerpc/kernel/semaphore.c =================================================================== --- linux-rt-rebase.q.orig/arch/powerpc/kernel/semaphore.c +++ linux-rt-rebase.q/arch/powerpc/kernel/semaphore.c @@ -31,7 +31,7 @@ * sem->count = tmp; * return old_count; */ -static inline int __sem_update_count(struct semaphore *sem, int incr) +static inline int __sem_update_count(struct compat_semaphore *sem, int incr) { int old_count, tmp; @@ -50,7 +50,7 @@ static inline int __sem_update_count(str return old_count; } -void __up(struct semaphore *sem) +void __compat_up(struct compat_semaphore *sem) { /* * Note that we incremented count in up() before we came here, @@ -63,7 +63,7 @@ void __up(struct semaphore *sem) __sem_update_count(sem, 1); wake_up(&sem->wait); } -EXPORT_SYMBOL(__up); +EXPORT_SYMBOL(__compat_up); /* * Note that when we come in to __down or __down_interruptible, @@ -73,7 +73,7 @@ EXPORT_SYMBOL(__up); * Thus it is only when we decrement count from some value > 0 * that we have actually got the semaphore. */ -void __sched __down(struct semaphore *sem) +void __sched __compat_down(struct compat_semaphore *sem) { struct task_struct *tsk = current; DECLARE_WAITQUEUE(wait, tsk); @@ -101,9 +101,9 @@ void __sched __down(struct semaphore *se */ wake_up(&sem->wait); } -EXPORT_SYMBOL(__down); +EXPORT_SYMBOL(__compat_down); -int __sched __down_interruptible(struct semaphore * sem) +int __sched __compat_down_interruptible(struct compat_semaphore *sem) { int retval = 0; struct task_struct *tsk = current; @@ -132,4 +132,10 @@ int __sched __down_interruptible(struct wake_up(&sem->wait); return retval; } -EXPORT_SYMBOL(__down_interruptible); +EXPORT_SYMBOL(__compat_down_interruptible); + +int compat_sem_is_locked(struct compat_semaphore *sem) +{ + return (int) atomic_read(&sem->count) < 0; +} +EXPORT_SYMBOL(compat_sem_is_locked); Index: linux-rt-rebase.q/arch/powerpc/kernel/setup_64.c =================================================================== --- linux-rt-rebase.q.orig/arch/powerpc/kernel/setup_64.c +++ linux-rt-rebase.q/arch/powerpc/kernel/setup_64.c @@ -605,3 +605,22 @@ struct ppc_pci_io ppc_pci_io; EXPORT_SYMBOL(ppc_pci_io); #endif /* CONFIG_PPC_INDIRECT_IO */ +#ifdef CONFIG_STACKTRACE +#include +void notrace save_stack_trace(struct stack_trace *trace, + struct task_struct *task) +{ +} +#endif /* CONFIG_STACKTRACE */ + +#ifdef CONFIG_EARLY_PRINTK +void notrace early_printk(const char *fmt, ...) +{ + BUG(); +} +#endif /* CONFIG_EARLY_PRINTK */ + +#ifdef CONFIG_MCOUNT +extern void _mcount(void); +EXPORT_SYMBOL(_mcount); +#endif /* CONFIG_MCOUNT */ Index: linux-rt-rebase.q/arch/powerpc/kernel/smp.c =================================================================== --- linux-rt-rebase.q.orig/arch/powerpc/kernel/smp.c +++ linux-rt-rebase.q/arch/powerpc/kernel/smp.c @@ -126,6 +126,16 @@ void smp_send_reschedule(int cpu) smp_ops->message_pass(cpu, PPC_MSG_RESCHEDULE); } +/* + * this function sends a 'reschedule' IPI to all other CPUs. + * This is used when RT tasks are starving and other CPUs + * might be able to run them: + */ +void smp_send_reschedule_allbutself(void) +{ + smp_ops->message_pass(MSG_ALL_BUT_SELF, PPC_MSG_RESCHEDULE); +} + #ifdef CONFIG_DEBUGGER void smp_send_debugger_break(int cpu) { @@ -162,7 +172,7 @@ void smp_send_stop(void) * static memory requirements. It also looks cleaner. * Stolen from the i386 version. */ -static __cacheline_aligned_in_smp DEFINE_SPINLOCK(call_lock); +static __cacheline_aligned_in_smp DEFINE_RAW_SPINLOCK(call_lock); static struct call_data_struct { void (*func) (void *info); @@ -336,8 +346,6 @@ void smp_call_function_interrupt(void) } } -extern struct gettimeofday_struct do_gtod; - struct thread_info *current_set[NR_CPUS]; DECLARE_PER_CPU(unsigned int, pvr); Index: linux-rt-rebase.q/arch/powerpc/kernel/time.c =================================================================== --- linux-rt-rebase.q.orig/arch/powerpc/kernel/time.c +++ linux-rt-rebase.q/arch/powerpc/kernel/time.c @@ -52,6 +52,7 @@ #include #include #include +#include #include #include @@ -116,8 +117,6 @@ static u64 tb_to_ns_scale __read_mostly; static unsigned tb_to_ns_shift __read_mostly; static unsigned long boot_tb __read_mostly; -struct gettimeofday_struct do_gtod; - extern struct timezone sys_tz; static long timezone_offset; @@ -128,6 +127,86 @@ unsigned long ppc_tb_freq; static u64 tb_last_jiffy __cacheline_aligned_in_smp; static DEFINE_PER_CPU(u64, last_jiffy); +#ifdef CONFIG_GENERIC_CLOCKEVENTS + +#if defined(CONFIG_40x) || defined(CONFIG_BOOKE) +#define DECREMENTER_MAX 0xffffffff +#else +#define DECREMENTER_MAX 0x7fffffff /* setting MSB triggers an interrupt */ +#endif + +static int decrementer_set_next_event(unsigned long evt, + struct clock_event_device *dev) +{ +#if defined(CONFIG_40x) + mtspr(SPRN_PIT, evt); /* 40x has a hidden PIT auto-reload register */ +#elif defined(CONFIG_BOOKE) + mtspr(SPRN_DECAR, evt); /* Book E has separate auto-reload register */ + set_dec(evt); +#else + set_dec(evt - 1); /* Classic decrementer interrupts at -1 */ +#endif + return 0; +} + +static void decrementer_set_mode(enum clock_event_mode mode, + struct clock_event_device *dev) +{ +#if defined(CONFIG_40x) || defined(CONFIG_BOOKE) + u32 tcr = mfspr(SPRN_TCR); + + tcr |= TCR_DIE; + switch (mode) { + case CLOCK_EVT_MODE_PERIODIC: + tcr |= TCR_ARE; + break; + case CLOCK_EVT_MODE_ONESHOT: + tcr &= ~TCR_ARE; + break; + case CLOCK_EVT_MODE_UNUSED: + case CLOCK_EVT_MODE_SHUTDOWN: + tcr &= ~TCR_DIE; + break; + case CLOCK_EVT_MODE_RESUME: + break; + } + mtspr(SPRN_TCR, tcr); + + if (mode == CLOCK_EVT_MODE_PERIODIC) + decrementer_set_next_event(tb_ticks_per_jiffy, dev); +#endif +} + +static struct clock_event_device decrementer_clockevent = { + .name = "decrementer", +#if defined(CONFIG_40x) || defined(CONFIG_BOOKE) + .features = CLOCK_EVT_FEAT_ONESHOT | CLOCK_EVT_FEAT_PERIODIC, +#else + .features = CLOCK_EVT_FEAT_ONESHOT, +#endif + .shift = 32, + .rating = 200, + .irq = -1, + .set_next_event = decrementer_set_next_event, + .set_mode = decrementer_set_mode, +}; + +static DEFINE_PER_CPU(struct clock_event_device, decrementers); + +static void register_decrementer(void) +{ + int cpu = smp_processor_id(); + struct clock_event_device *decrementer = &per_cpu(decrementers, cpu); + + memcpy(decrementer, &decrementer_clockevent, sizeof(*decrementer)); + + decrementer->cpumask = cpumask_of_cpu(cpu); + + clockevents_register_device(decrementer); +} + +#endif /* CONFIG_GENERIC_CLOCKEVENTS */ + #ifdef CONFIG_VIRT_CPU_ACCOUNTING /* * Factors for converting from cputime_t (timebase ticks) to @@ -319,6 +398,9 @@ void snapshot_timebase(void) { __get_cpu_var(last_jiffy) = get_tb(); snapshot_purr(); +#ifdef CONFIG_GENERIC_CLOCKEVENTS + register_decrementer(); +#endif } void __delay(unsigned long loops) @@ -382,160 +464,6 @@ static __inline__ void timer_check_rtc(v } } -/* - * This version of gettimeofday has microsecond resolution. - */ -static inline void __do_gettimeofday(struct timeval *tv) -{ - unsigned long sec, usec; - u64 tb_ticks, xsec; - struct gettimeofday_vars *temp_varp; - u64 temp_tb_to_xs, temp_stamp_xsec; - - /* - * These calculations are faster (gets rid of divides) - * if done in units of 1/2^20 rather than microseconds. - * The conversion to microseconds at the end is done - * without a divide (and in fact, without a multiply) - */ - temp_varp = do_gtod.varp; - - /* Sampling the time base must be done after loading - * do_gtod.varp in order to avoid racing with update_gtod. - */ - data_barrier(temp_varp); - tb_ticks = get_tb() - temp_varp->tb_orig_stamp; - temp_tb_to_xs = temp_varp->tb_to_xs; - temp_stamp_xsec = temp_varp->stamp_xsec; - xsec = temp_stamp_xsec + mulhdu(tb_ticks, temp_tb_to_xs); - sec = xsec / XSEC_PER_SEC; - usec = (unsigned long)xsec & (XSEC_PER_SEC - 1); - usec = SCALE_XSEC(usec, 1000000); - - tv->tv_sec = sec; - tv->tv_usec = usec; -} - -void do_gettimeofday(struct timeval *tv) -{ - if (__USE_RTC()) { - /* do this the old way */ - unsigned long flags, seq; - unsigned int sec, nsec, usec; - - do { - seq = read_seqbegin_irqsave(&xtime_lock, flags); - sec = xtime.tv_sec; - nsec = xtime.tv_nsec + tb_ticks_since(tb_last_jiffy); - } while (read_seqretry_irqrestore(&xtime_lock, seq, flags)); - usec = nsec / 1000; - while (usec >= 1000000) { - usec -= 1000000; - ++sec; - } - tv->tv_sec = sec; - tv->tv_usec = usec; - return; - } - __do_gettimeofday(tv); -} - -EXPORT_SYMBOL(do_gettimeofday); - -/* - * There are two copies of tb_to_xs and stamp_xsec so that no - * lock is needed to access and use these values in - * do_gettimeofday. We alternate the copies and as long as a - * reasonable time elapses between changes, there will never - * be inconsistent values. ntpd has a minimum of one minute - * between updates. - */ -static inline void update_gtod(u64 new_tb_stamp, u64 new_stamp_xsec, - u64 new_tb_to_xs) -{ - unsigned temp_idx; - struct gettimeofday_vars *temp_varp; - - temp_idx = (do_gtod.var_idx == 0); - temp_varp = &do_gtod.vars[temp_idx]; - - temp_varp->tb_to_xs = new_tb_to_xs; - temp_varp->tb_orig_stamp = new_tb_stamp; - temp_varp->stamp_xsec = new_stamp_xsec; - smp_mb(); - do_gtod.varp = temp_varp; - do_gtod.var_idx = temp_idx; - - /* - * tb_update_count is used to allow the userspace gettimeofday code - * to assure itself that it sees a consistent view of the tb_to_xs and - * stamp_xsec variables. It reads the tb_update_count, then reads - * tb_to_xs and stamp_xsec and then reads tb_update_count again. If - * the two values of tb_update_count match and are even then the - * tb_to_xs and stamp_xsec values are consistent. If not, then it - * loops back and reads them again until this criteria is met. - * We expect the caller to have done the first increment of - * vdso_data->tb_update_count already. - */ - vdso_data->tb_orig_stamp = new_tb_stamp; - vdso_data->stamp_xsec = new_stamp_xsec; - vdso_data->tb_to_xs = new_tb_to_xs; - vdso_data->wtom_clock_sec = wall_to_monotonic.tv_sec; - vdso_data->wtom_clock_nsec = wall_to_monotonic.tv_nsec; - smp_wmb(); - ++(vdso_data->tb_update_count); -} - -/* - * When the timebase - tb_orig_stamp gets too big, we do a manipulation - * between tb_orig_stamp and stamp_xsec. The goal here is to keep the - * difference tb - tb_orig_stamp small enough to always fit inside a - * 32 bits number. This is a requirement of our fast 32 bits userland - * implementation in the vdso. If we "miss" a call to this function - * (interrupt latency, CPU locked in a spinlock, ...) and we end up - * with a too big difference, then the vdso will fallback to calling - * the syscall - */ -static __inline__ void timer_recalc_offset(u64 cur_tb) -{ - unsigned long offset; - u64 new_stamp_xsec; - u64 tlen, t2x; - u64 tb, xsec_old, xsec_new; - struct gettimeofday_vars *varp; - - if (__USE_RTC()) - return; - tlen = current_tick_length(); - offset = cur_tb - do_gtod.varp->tb_orig_stamp; - if (tlen == last_tick_len && offset < 0x80000000u) - return; - if (tlen != last_tick_len) { - t2x = mulhdu(tlen << TICKLEN_SHIFT, ticklen_to_xs); - last_tick_len = tlen; - } else - t2x = do_gtod.varp->tb_to_xs; - new_stamp_xsec = (u64) xtime.tv_nsec * XSEC_PER_SEC; - do_div(new_stamp_xsec, 1000000000); - new_stamp_xsec += (u64) xtime.tv_sec * XSEC_PER_SEC; - - ++vdso_data->tb_update_count; - smp_mb(); - - /* - * Make sure time doesn't go backwards for userspace gettimeofday. - */ - tb = get_tb(); - varp = do_gtod.varp; - xsec_old = mulhdu(tb - varp->tb_orig_stamp, varp->tb_to_xs) - + varp->stamp_xsec; - xsec_new = mulhdu(tb - cur_tb, t2x) + new_stamp_xsec; - if (xsec_new < xsec_old) - new_stamp_xsec += xsec_old - xsec_new; - - update_gtod(cur_tb, new_stamp_xsec, t2x); -} - #ifdef CONFIG_SMP unsigned long profile_pc(struct pt_regs *regs) { @@ -590,11 +518,7 @@ static int __init iSeries_tb_recal(void) tb_ticks_per_sec = new_tb_ticks_per_sec; calc_cputime_factors(); div128_by_32( XSEC_PER_SEC, 0, tb_ticks_per_sec, &divres ); - do_gtod.tb_ticks_per_sec = tb_ticks_per_sec; tb_to_xs = divres.result_low; - do_gtod.varp->tb_to_xs = tb_to_xs; - vdso_data->tb_ticks_per_sec = tb_ticks_per_sec; - vdso_data->tb_to_xs = tb_to_xs; } else { printk( "Titan recalibrate: FAILED (difference > 4 percent)\n" @@ -649,7 +573,27 @@ void timer_interrupt(struct pt_regs * re old_regs = set_irq_regs(regs); irq_enter(); +#ifdef CONFIG_GENERIC_CLOCKEVENTS +#if !defined(CONFIG_40x) && !defined(CONFIG_BOOKE) + /* + * We must write a positive value to the decrementer to clear + * the interrupt on POWER4+ compatible CPUs. + */ + set_dec(DECREMENTER_MAX); +#endif + /* + * We can't disable the decrementer, so in the period between + * CPU being marked offline and calling stop-self, it's taking + * timer interrupts... + */ + if (!cpu_is_offline(cpu)) { + struct clock_event_device *dev = &per_cpu(decrementers, cpu); + + dev->event_handler(dev); + } +#else profile_tick(CPU_PROFILING); +#endif calculate_steal_time(); #ifdef CONFIG_PPC_ISERIES @@ -665,6 +609,7 @@ void timer_interrupt(struct pt_regs * re if (__USE_RTC() && per_cpu(last_jiffy, cpu) >= 1000000000) per_cpu(last_jiffy, cpu) -= 1000000000; +#ifndef CONFIG_GENERIC_CLOCKEVENTS /* * We cannot disable the decrementer, so in the period * between this cpu's being marked offline in cpu_online_map @@ -674,6 +619,7 @@ void timer_interrupt(struct pt_regs * re */ if (!cpu_is_offline(cpu)) account_process_time(regs); +#endif /* * No need to check whether cpu is offline here; boot_cpuid @@ -686,15 +632,19 @@ void timer_interrupt(struct pt_regs * re tb_next_jiffy = tb_last_jiffy + tb_ticks_per_jiffy; if (per_cpu(last_jiffy, cpu) >= tb_next_jiffy) { tb_last_jiffy = tb_next_jiffy; +#ifndef CONFIG_GENERIC_CLOCKEVENTS do_timer(1); - timer_recalc_offset(tb_last_jiffy); +#endif + /*timer_recalc_offset(tb_last_jiffy);*/ timer_check_rtc(); } write_sequnlock(&xtime_lock); } - + +#ifndef CONFIG_GENERIC_CLOCKEVENTS next_dec = tb_ticks_per_jiffy - ticks; set_dec(next_dec); +#endif #ifdef CONFIG_PPC_ISERIES if (firmware_has_feature(FW_FEATURE_ISERIES) && hvlpevent_is_pending()) @@ -760,71 +710,6 @@ unsigned long long sched_clock(void) return mulhdu(get_tb() - boot_tb, tb_to_ns_scale) << tb_to_ns_shift; } -int do_settimeofday(struct timespec *tv) -{ - time_t wtm_sec, new_sec = tv->tv_sec; - long wtm_nsec, new_nsec = tv->tv_nsec; - unsigned long flags; - u64 new_xsec; - unsigned long tb_delta; - - if ((unsigned long)tv->tv_nsec >= NSEC_PER_SEC) - return -EINVAL; - - write_seqlock_irqsave(&xtime_lock, flags); - - /* - * Updating the RTC is not the job of this code. If the time is - * stepped under NTP, the RTC will be updated after STA_UNSYNC - * is cleared. Tools like clock/hwclock either copy the RTC - * to the system time, in which case there is no point in writing - * to the RTC again, or write to the RTC but then they don't call - * settimeofday to perform this operation. - */ - - /* Make userspace gettimeofday spin until we're done. */ - ++vdso_data->tb_update_count; - smp_mb(); - - /* - * Subtract off the number of nanoseconds since the - * beginning of the last tick. - */ - tb_delta = tb_ticks_since(tb_last_jiffy); - tb_delta = mulhdu(tb_delta, do_gtod.varp->tb_to_xs); /* in xsec */ - new_nsec -= SCALE_XSEC(tb_delta, 1000000000); - - wtm_sec = wall_to_monotonic.tv_sec + (xtime.tv_sec - new_sec); - wtm_nsec = wall_to_monotonic.tv_nsec + (xtime.tv_nsec - new_nsec); - - set_normalized_timespec(&xtime, new_sec, new_nsec); - set_normalized_timespec(&wall_to_monotonic, wtm_sec, wtm_nsec); - - /* In case of a large backwards jump in time with NTP, we want the - * clock to be updated as soon as the PLL is again in lock. - */ - last_rtc_update = new_sec - 658; - - ntp_clear(); - - new_xsec = xtime.tv_nsec; - if (new_xsec != 0) { - new_xsec *= XSEC_PER_SEC; - do_div(new_xsec, NSEC_PER_SEC); - } - new_xsec += (u64)xtime.tv_sec * XSEC_PER_SEC; - update_gtod(tb_last_jiffy, new_xsec, do_gtod.varp->tb_to_xs); - - vdso_data->tz_minuteswest = sys_tz.tz_minuteswest; - vdso_data->tz_dsttime = sys_tz.tz_dsttime; - - write_sequnlock_irqrestore(&xtime_lock, flags); - clock_was_set(); - return 0; -} - -EXPORT_SYMBOL(do_settimeofday); - static int __init get_freq(char *name, int cells, unsigned long *val) { struct device_node *cpu; @@ -880,31 +765,46 @@ void __init generic_calibrate_decr(void) #endif } -unsigned long get_boot_time(void) +unsigned long read_persistent_clock(void) { - struct rtc_time tm; + unsigned long time = 0; + static int first = 1; + + if (first && ppc_md.time_init) { + timezone_offset = ppc_md.time_init(); + + /* If platform provided a timezone (pmac), we correct the time */ + if (timezone_offset) { + sys_tz.tz_minuteswest = -timezone_offset / 60; + sys_tz.tz_dsttime = 0; + } + } if (ppc_md.get_boot_time) - return ppc_md.get_boot_time(); - if (!ppc_md.get_rtc_time) - return 0; - ppc_md.get_rtc_time(&tm); - return mktime(tm.tm_year+1900, tm.tm_mon+1, tm.tm_mday, - tm.tm_hour, tm.tm_min, tm.tm_sec); + time = ppc_md.get_boot_time(); + else if (ppc_md.get_rtc_time) { + struct rtc_time tm; + + ppc_md.get_rtc_time(&tm); + time = mktime(tm.tm_year+1900, tm.tm_mon+1, tm.tm_mday, + tm.tm_hour, tm.tm_min, tm.tm_sec); + } + time -= timezone_offset; + + if (first) { + last_rtc_update = time; + first = 0; + } + return time; } /* This function is only called on the boot processor */ void __init time_init(void) { - unsigned long flags; - unsigned long tm = 0; struct div_result res; u64 scale, x; unsigned shift; - if (ppc_md.time_init != NULL) - timezone_offset = ppc_md.time_init(); - if (__USE_RTC()) { /* 601 processor: dec counts down by 128 every 128ns */ ppc_tb_freq = 1000000000; @@ -979,46 +879,21 @@ void __init time_init(void) /* Save the current timebase to pretty up CONFIG_PRINTK_TIME */ boot_tb = get_tb(); - tm = get_boot_time(); - - write_seqlock_irqsave(&xtime_lock, flags); - - /* If platform provided a timezone (pmac), we correct the time */ - if (timezone_offset) { - sys_tz.tz_minuteswest = -timezone_offset / 60; - sys_tz.tz_dsttime = 0; - tm -= timezone_offset; - } - - xtime.tv_sec = tm; - xtime.tv_nsec = 0; - do_gtod.varp = &do_gtod.vars[0]; - do_gtod.var_idx = 0; - do_gtod.varp->tb_orig_stamp = tb_last_jiffy; - __get_cpu_var(last_jiffy) = tb_last_jiffy; - do_gtod.varp->stamp_xsec = (u64) xtime.tv_sec * XSEC_PER_SEC; - do_gtod.tb_ticks_per_sec = tb_ticks_per_sec; - do_gtod.varp->tb_to_xs = tb_to_xs; - do_gtod.tb_to_us = tb_to_us; - - vdso_data->tb_orig_stamp = tb_last_jiffy; - vdso_data->tb_update_count = 0; - vdso_data->tb_ticks_per_sec = tb_ticks_per_sec; - vdso_data->stamp_xsec = (u64) xtime.tv_sec * XSEC_PER_SEC; - vdso_data->tb_to_xs = tb_to_xs; - - time_freq = 0; - - last_rtc_update = xtime.tv_sec; - set_normalized_timespec(&wall_to_monotonic, - -xtime.tv_sec, -xtime.tv_nsec); - write_sequnlock_irqrestore(&xtime_lock, flags); +#ifdef CONFIG_GENERIC_CLOCKEVENTS + decrementer_clockevent.mult = div_sc(ppc_tb_freq, NSEC_PER_SEC, + decrementer_clockevent.shift); + decrementer_clockevent.max_delta_ns = + clockevent_delta2ns(DECREMENTER_MAX, &decrementer_clockevent); + decrementer_clockevent.min_delta_ns = + clockevent_delta2ns(0xf, &decrementer_clockevent); + register_decrementer(); +#else /* Not exact, but the timer interrupt takes care of this */ set_dec(tb_ticks_per_jiffy); +#endif } - #define FEBRUARY 2 #define STARTOFTIME 1970 #define SECDAY 86400L @@ -1163,3 +1038,39 @@ void div128_by_32(u64 dividend_high, u64 dr->result_low = ((u64)y << 32) + z; } + +/* PowerPC clocksource code */ + +#include + +static cycle_t notrace timebase_read(void) +{ + return (cycle_t)get_tb(); +} + +struct clocksource clocksource_timebase = { + .name = "timebase", + .rating = 200, + .read = timebase_read, + .mask = (cycle_t)-1, + .mult = 0, + .shift = 22, + .flags = CLOCK_SOURCE_IS_CONTINUOUS, +}; + + +/* XXX - this should be calculated or properly externed! */ +static int __init init_timebase_clocksource(void) +{ + if (__USE_RTC()) + return -ENODEV; + +#ifdef CONFIG_PPC64 + clocksource_timebase.shift = tb_ticks_per_jiffy / 1000000; +#endif + clocksource_timebase.mult = clocksource_hz2mult(tb_ticks_per_sec, + clocksource_timebase.shift); + return clocksource_register(&clocksource_timebase); +} + +module_init(init_timebase_clocksource); Index: linux-rt-rebase.q/arch/powerpc/kernel/traps.c =================================================================== --- linux-rt-rebase.q.orig/arch/powerpc/kernel/traps.c +++ linux-rt-rebase.q/arch/powerpc/kernel/traps.c @@ -97,11 +97,11 @@ static inline void pmac_backlight_unblan int die(const char *str, struct pt_regs *regs, long err) { static struct { - spinlock_t lock; + raw_spinlock_t lock; u32 lock_owner; int lock_owner_depth; } die = { - .lock = __SPIN_LOCK_UNLOCKED(die.lock), + .lock = _RAW_SPIN_LOCK_UNLOCKED(die.lock), .lock_owner = -1, .lock_owner_depth = 0 }; @@ -178,6 +178,11 @@ void _exception(int signr, struct pt_reg return; } +#ifdef CONFIG_PREEMPT_RT + local_irq_enable(); + preempt_check_resched(); +#endif + memset(&info, 0, sizeof(info)); info.si_signo = signr; info.si_code = code; Index: linux-rt-rebase.q/arch/powerpc/kernel/vdso32/Makefile =================================================================== --- linux-rt-rebase.q.orig/arch/powerpc/kernel/vdso32/Makefile +++ linux-rt-rebase.q/arch/powerpc/kernel/vdso32/Makefile @@ -1,7 +1,7 @@ # List of files in the vdso, has to be asm only for now -obj-vdso32 = sigtramp.o gettimeofday.o datapage.o cacheflush.o note.o +obj-vdso32 = sigtramp.o datapage.o cacheflush.o note.o # Build rules Index: linux-rt-rebase.q/arch/powerpc/kernel/vdso32/datapage.S =================================================================== --- linux-rt-rebase.q.orig/arch/powerpc/kernel/vdso32/datapage.S +++ linux-rt-rebase.q/arch/powerpc/kernel/vdso32/datapage.S @@ -65,21 +65,3 @@ V_FUNCTION_BEGIN(__kernel_get_syscall_ma blr .cfi_endproc V_FUNCTION_END(__kernel_get_syscall_map) - -/* - * void unsigned long long __kernel_get_tbfreq(void); - * - * returns the timebase frequency in HZ - */ -V_FUNCTION_BEGIN(__kernel_get_tbfreq) - .cfi_startproc - mflr r12 - .cfi_register lr,r12 - bl __get_datapage@local - lwz r4,(CFG_TB_TICKS_PER_SEC + 4)(r3) - lwz r3,CFG_TB_TICKS_PER_SEC(r3) - mtlr r12 - crclr cr0*4+so - blr - .cfi_endproc -V_FUNCTION_END(__kernel_get_tbfreq) Index: linux-rt-rebase.q/arch/powerpc/kernel/vdso32/gettimeofday.S =================================================================== --- linux-rt-rebase.q.orig/arch/powerpc/kernel/vdso32/gettimeofday.S +++ /dev/null @@ -1,324 +0,0 @@ -/* - * Userland implementation of gettimeofday() for 32 bits processes in a - * ppc64 kernel for use in the vDSO - * - * Copyright (C) 2004 Benjamin Herrenschmuidt (benh@kernel.crashing.org, - * IBM Corp. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - */ -#include -#include -#include -#include -#include - - .text -/* - * Exact prototype of gettimeofday - * - * int __kernel_gettimeofday(struct timeval *tv, struct timezone *tz); - * - */ -V_FUNCTION_BEGIN(__kernel_gettimeofday) - .cfi_startproc - mflr r12 - .cfi_register lr,r12 - - mr r10,r3 /* r10 saves tv */ - mr r11,r4 /* r11 saves tz */ - bl __get_datapage@local /* get data page */ - mr r9, r3 /* datapage ptr in r9 */ - cmplwi r10,0 /* check if tv is NULL */ - beq 3f - bl __do_get_xsec@local /* get xsec from tb & kernel */ - bne- 2f /* out of line -> do syscall */ - - /* seconds are xsec >> 20 */ - rlwinm r5,r4,12,20,31 - rlwimi r5,r3,12,0,19 - stw r5,TVAL32_TV_SEC(r10) - - /* get remaining xsec and convert to usec. we scale - * up remaining xsec by 12 bits and get the top 32 bits - * of the multiplication - */ - rlwinm r5,r4,12,0,19 - lis r6,1000000@h - ori r6,r6,1000000@l - mulhwu r5,r5,r6 - stw r5,TVAL32_TV_USEC(r10) - -3: cmplwi r11,0 /* check if tz is NULL */ - beq 1f - lwz r4,CFG_TZ_MINUTEWEST(r9)/* fill tz */ - lwz r5,CFG_TZ_DSTTIME(r9) - stw r4,TZONE_TZ_MINWEST(r11) - stw r5,TZONE_TZ_DSTTIME(r11) - -1: mtlr r12 - crclr cr0*4+so - li r3,0 - blr - -2: - mtlr r12 - mr r3,r10 - mr r4,r11 - li r0,__NR_gettimeofday - sc - blr - .cfi_endproc -V_FUNCTION_END(__kernel_gettimeofday) - -/* - * Exact prototype of clock_gettime() - * - * int __kernel_clock_gettime(clockid_t clock_id, struct timespec *tp); - * - */ -V_FUNCTION_BEGIN(__kernel_clock_gettime) - .cfi_startproc - /* Check for supported clock IDs */ - cmpli cr0,r3,CLOCK_REALTIME - cmpli cr1,r3,CLOCK_MONOTONIC - cror cr0*4+eq,cr0*4+eq,cr1*4+eq - bne cr0,99f - - mflr r12 /* r12 saves lr */ - .cfi_register lr,r12 - mr r10,r3 /* r10 saves id */ - mr r11,r4 /* r11 saves tp */ - bl __get_datapage@local /* get data page */ - mr r9,r3 /* datapage ptr in r9 */ - beq cr1,50f /* if monotonic -> jump there */ - - /* - * CLOCK_REALTIME - */ - - bl __do_get_xsec@local /* get xsec from tb & kernel */ - bne- 98f /* out of line -> do syscall */ - - /* seconds are xsec >> 20 */ - rlwinm r5,r4,12,20,31 - rlwimi r5,r3,12,0,19 - stw r5,TSPC32_TV_SEC(r11) - - /* get remaining xsec and convert to nsec. we scale - * up remaining xsec by 12 bits and get the top 32 bits - * of the multiplication, then we multiply by 1000 - */ - rlwinm r5,r4,12,0,19 - lis r6,1000000@h - ori r6,r6,1000000@l - mulhwu r5,r5,r6 - mulli r5,r5,1000 - stw r5,TSPC32_TV_NSEC(r11) - mtlr r12 - crclr cr0*4+so - li r3,0 - blr - - /* - * CLOCK_MONOTONIC - */ - -50: bl __do_get_xsec@local /* get xsec from tb & kernel */ - bne- 98f /* out of line -> do syscall */ - - /* seconds are xsec >> 20 */ - rlwinm r6,r4,12,20,31 - rlwimi r6,r3,12,0,19 - - /* get remaining xsec and convert to nsec. we scale - * up remaining xsec by 12 bits and get the top 32 bits - * of the multiplication, then we multiply by 1000 - */ - rlwinm r7,r4,12,0,19 - lis r5,1000000@h - ori r5,r5,1000000@l - mulhwu r7,r7,r5 - mulli r7,r7,1000 - - /* now we must fixup using wall to monotonic. We need to snapshot - * that value and do the counter trick again. Fortunately, we still - * have the counter value in r8 that was returned by __do_get_xsec. - * At this point, r6,r7 contain our sec/nsec values, r3,r4 and r5 - * can be used - */ - - lwz r3,WTOM_CLOCK_SEC(r9) - lwz r4,WTOM_CLOCK_NSEC(r9) - - /* We now have our result in r3,r4. We create a fake dependency - * on that result and re-check the counter - */ - or r5,r4,r3 - xor r0,r5,r5 - add r9,r9,r0 -#ifdef CONFIG_PPC64 - lwz r0,(CFG_TB_UPDATE_COUNT+4)(r9) -#else - lwz r0,(CFG_TB_UPDATE_COUNT)(r9) -#endif - cmpl cr0,r8,r0 /* check if updated */ - bne- 50b - - /* Calculate and store result. Note that this mimmics the C code, - * which may cause funny results if nsec goes negative... is that - * possible at all ? - */ - add r3,r3,r6 - add r4,r4,r7 - lis r5,NSEC_PER_SEC@h - ori r5,r5,NSEC_PER_SEC@l - cmpl cr0,r4,r5 - cmpli cr1,r4,0 - blt 1f - subf r4,r5,r4 - addi r3,r3,1 -1: bge cr1,1f - addi r3,r3,-1 - add r4,r4,r5 -1: stw r3,TSPC32_TV_SEC(r11) - stw r4,TSPC32_TV_NSEC(r11) - - mtlr r12 - crclr cr0*4+so - li r3,0 - blr - - /* - * syscall fallback - */ -98: - mtlr r12 - mr r3,r10 - mr r4,r11 -99: - li r0,__NR_clock_gettime - sc - blr - .cfi_endproc -V_FUNCTION_END(__kernel_clock_gettime) - - -/* - * Exact prototype of clock_getres() - * - * int __kernel_clock_getres(clockid_t clock_id, struct timespec *res); - * - */ -V_FUNCTION_BEGIN(__kernel_clock_getres) - .cfi_startproc - /* Check for supported clock IDs */ - cmpwi cr0,r3,CLOCK_REALTIME - cmpwi cr1,r3,CLOCK_MONOTONIC - cror cr0*4+eq,cr0*4+eq,cr1*4+eq - bne cr0,99f - - li r3,0 - cmpli cr0,r4,0 - crclr cr0*4+so - beqlr - lis r5,CLOCK_REALTIME_RES@h - ori r5,r5,CLOCK_REALTIME_RES@l - stw r3,TSPC32_TV_SEC(r4) - stw r5,TSPC32_TV_NSEC(r4) - blr - - /* - * syscall fallback - */ -99: - li r0,__NR_clock_getres - sc - blr - .cfi_endproc -V_FUNCTION_END(__kernel_clock_getres) - - -/* - * This is the core of gettimeofday() & friends, it returns the xsec - * value in r3 & r4 and expects the datapage ptr (non clobbered) - * in r9. clobbers r0,r4,r5,r6,r7,r8. - * When returning, r8 contains the counter value that can be reused - * by the monotonic clock implementation - */ -__do_get_xsec: - .cfi_startproc - /* Check for update count & load values. We use the low - * order 32 bits of the update count - */ -#ifdef CONFIG_PPC64 -1: lwz r8,(CFG_TB_UPDATE_COUNT+4)(r9) -#else -1: lwz r8,(CFG_TB_UPDATE_COUNT)(r9) -#endif - andi. r0,r8,1 /* pending update ? loop */ - bne- 1b - xor r0,r8,r8 /* create dependency */ - add r9,r9,r0 - - /* Load orig stamp (offset to TB) */ - lwz r5,CFG_TB_ORIG_STAMP(r9) - lwz r6,(CFG_TB_ORIG_STAMP+4)(r9) - - /* Get a stable TB value */ -2: mftbu r3 - mftbl r4 - mftbu r0 - cmpl cr0,r3,r0 - bne- 2b - - /* Substract tb orig stamp. If the high part is non-zero, we jump to - * the slow path which call the syscall. - * If it's ok, then we have our 32 bits tb_ticks value in r7 - */ - subfc r7,r6,r4 - subfe. r0,r5,r3 - bne- 3f - - /* Load scale factor & do multiplication */ - lwz r5,CFG_TB_TO_XS(r9) /* load values */ - lwz r6,(CFG_TB_TO_XS+4)(r9) - mulhwu r4,r7,r5 - mulhwu r6,r7,r6 - mullw r0,r7,r5 - addc r6,r6,r0 - - /* At this point, we have the scaled xsec value in r4 + XER:CA - * we load & add the stamp since epoch - */ - lwz r5,CFG_STAMP_XSEC(r9) - lwz r6,(CFG_STAMP_XSEC+4)(r9) - adde r4,r4,r6 - addze r3,r5 - - /* We now have our result in r3,r4. We create a fake dependency - * on that result and re-check the counter - */ - or r6,r4,r3 - xor r0,r6,r6 - add r9,r9,r0 -#ifdef CONFIG_PPC64 - lwz r0,(CFG_TB_UPDATE_COUNT+4)(r9) -#else - lwz r0,(CFG_TB_UPDATE_COUNT)(r9) -#endif - cmpl cr0,r8,r0 /* check if updated */ - bne- 1b - - /* Warning ! The caller expects CR:EQ to be set to indicate a - * successful calculation (so it won't fallback to the syscall - * method). We have overriden that CR bit in the counter check, - * but fortunately, the loop exit condition _is_ CR:EQ set, so - * we can exit safely here. If you change this code, be careful - * of that side effect. - */ -3: blr - .cfi_endproc Index: linux-rt-rebase.q/arch/powerpc/kernel/vdso32/vdso32.lds.S =================================================================== --- linux-rt-rebase.q.orig/arch/powerpc/kernel/vdso32/vdso32.lds.S +++ linux-rt-rebase.q/arch/powerpc/kernel/vdso32/vdso32.lds.S @@ -117,10 +117,6 @@ VERSION global: __kernel_datapage_offset; /* Has to be there for the kernel to find */ __kernel_get_syscall_map; - __kernel_gettimeofday; - __kernel_clock_gettime; - __kernel_clock_getres; - __kernel_get_tbfreq; __kernel_sync_dicache; __kernel_sync_dicache_p5; __kernel_sigtramp32; Index: linux-rt-rebase.q/arch/powerpc/kernel/vdso64/Makefile =================================================================== --- linux-rt-rebase.q.orig/arch/powerpc/kernel/vdso64/Makefile +++ linux-rt-rebase.q/arch/powerpc/kernel/vdso64/Makefile @@ -1,6 +1,6 @@ # List of files in the vdso, has to be asm only for now -obj-vdso64 = sigtramp.o gettimeofday.o datapage.o cacheflush.o note.o +obj-vdso64 = sigtramp.o datapage.o cacheflush.o note.o # Build rules Index: linux-rt-rebase.q/arch/powerpc/kernel/vdso64/datapage.S =================================================================== --- linux-rt-rebase.q.orig/arch/powerpc/kernel/vdso64/datapage.S +++ linux-rt-rebase.q/arch/powerpc/kernel/vdso64/datapage.S @@ -65,21 +65,3 @@ V_FUNCTION_BEGIN(__kernel_get_syscall_ma blr .cfi_endproc V_FUNCTION_END(__kernel_get_syscall_map) - - -/* - * void unsigned long __kernel_get_tbfreq(void); - * - * returns the timebase frequency in HZ - */ -V_FUNCTION_BEGIN(__kernel_get_tbfreq) - .cfi_startproc - mflr r12 - .cfi_register lr,r12 - bl V_LOCAL_FUNC(__get_datapage) - ld r3,CFG_TB_TICKS_PER_SEC(r3) - mtlr r12 - crclr cr0*4+so - blr - .cfi_endproc -V_FUNCTION_END(__kernel_get_tbfreq) Index: linux-rt-rebase.q/arch/powerpc/kernel/vdso64/gettimeofday.S =================================================================== --- linux-rt-rebase.q.orig/arch/powerpc/kernel/vdso64/gettimeofday.S +++ /dev/null @@ -1,255 +0,0 @@ -/* - * Userland implementation of gettimeofday() for 64 bits processes in a - * ppc64 kernel for use in the vDSO - * - * Copyright (C) 2004 Benjamin Herrenschmuidt (benh@kernel.crashing.org), - * IBM Corp. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - */ -#include -#include -#include -#include -#include - - .text -/* - * Exact prototype of gettimeofday - * - * int __kernel_gettimeofday(struct timeval *tv, struct timezone *tz); - * - */ -V_FUNCTION_BEGIN(__kernel_gettimeofday) - .cfi_startproc - mflr r12 - .cfi_register lr,r12 - - mr r11,r3 /* r11 holds tv */ - mr r10,r4 /* r10 holds tz */ - bl V_LOCAL_FUNC(__get_datapage) /* get data page */ - cmpldi r11,0 /* check if tv is NULL */ - beq 2f - bl V_LOCAL_FUNC(__do_get_xsec) /* get xsec from tb & kernel */ - lis r7,15 /* r7 = 1000000 = USEC_PER_SEC */ - ori r7,r7,16960 - rldicl r5,r4,44,20 /* r5 = sec = xsec / XSEC_PER_SEC */ - rldicr r6,r5,20,43 /* r6 = sec * XSEC_PER_SEC */ - std r5,TVAL64_TV_SEC(r11) /* store sec in tv */ - subf r0,r6,r4 /* r0 = xsec = (xsec - r6) */ - mulld r0,r0,r7 /* usec = (xsec * USEC_PER_SEC) / - * XSEC_PER_SEC - */ - rldicl r0,r0,44,20 - std r0,TVAL64_TV_USEC(r11) /* store usec in tv */ -2: cmpldi r10,0 /* check if tz is NULL */ - beq 1f - lwz r4,CFG_TZ_MINUTEWEST(r3)/* fill tz */ - lwz r5,CFG_TZ_DSTTIME(r3) - stw r4,TZONE_TZ_MINWEST(r10) - stw r5,TZONE_TZ_DSTTIME(r10) -1: mtlr r12 - crclr cr0*4+so - li r3,0 /* always success */ - blr - .cfi_endproc -V_FUNCTION_END(__kernel_gettimeofday) - - -/* - * Exact prototype of clock_gettime() - * - * int __kernel_clock_gettime(clockid_t clock_id, struct timespec *tp); - * - */ -V_FUNCTION_BEGIN(__kernel_clock_gettime) - .cfi_startproc - /* Check for supported clock IDs */ - cmpwi cr0,r3,CLOCK_REALTIME - cmpwi cr1,r3,CLOCK_MONOTONIC - cror cr0*4+eq,cr0*4+eq,cr1*4+eq - bne cr0,99f - - mflr r12 /* r12 saves lr */ - .cfi_register lr,r12 - mr r10,r3 /* r10 saves id */ - mr r11,r4 /* r11 saves tp */ - bl V_LOCAL_FUNC(__get_datapage) /* get data page */ - beq cr1,50f /* if monotonic -> jump there */ - - /* - * CLOCK_REALTIME - */ - - bl V_LOCAL_FUNC(__do_get_xsec) /* get xsec from tb & kernel */ - - lis r7,15 /* r7 = 1000000 = USEC_PER_SEC */ - ori r7,r7,16960 - rldicl r5,r4,44,20 /* r5 = sec = xsec / XSEC_PER_SEC */ - rldicr r6,r5,20,43 /* r6 = sec * XSEC_PER_SEC */ - std r5,TSPC64_TV_SEC(r11) /* store sec in tv */ - subf r0,r6,r4 /* r0 = xsec = (xsec - r6) */ - mulld r0,r0,r7 /* usec = (xsec * USEC_PER_SEC) / - * XSEC_PER_SEC - */ - rldicl r0,r0,44,20 - mulli r0,r0,1000 /* nsec = usec * 1000 */ - std r0,TSPC64_TV_NSEC(r11) /* store nsec in tp */ - - mtlr r12 - crclr cr0*4+so - li r3,0 - blr - - /* - * CLOCK_MONOTONIC - */ - -50: bl V_LOCAL_FUNC(__do_get_xsec) /* get xsec from tb & kernel */ - - lis r7,15 /* r7 = 1000000 = USEC_PER_SEC */ - ori r7,r7,16960 - rldicl r5,r4,44,20 /* r5 = sec = xsec / XSEC_PER_SEC */ - rldicr r6,r5,20,43 /* r6 = sec * XSEC_PER_SEC */ - subf r0,r6,r4 /* r0 = xsec = (xsec - r6) */ - mulld r0,r0,r7 /* usec = (xsec * USEC_PER_SEC) / - * XSEC_PER_SEC - */ - rldicl r6,r0,44,20 - mulli r6,r6,1000 /* nsec = usec * 1000 */ - - /* now we must fixup using wall to monotonic. We need to snapshot - * that value and do the counter trick again. Fortunately, we still - * have the counter value in r8 that was returned by __do_get_xsec. - * At this point, r5,r6 contain our sec/nsec values. - * can be used - */ - - lwa r4,WTOM_CLOCK_SEC(r3) - lwa r7,WTOM_CLOCK_NSEC(r3) - - /* We now have our result in r4,r7. We create a fake dependency - * on that result and re-check the counter - */ - or r9,r4,r7 - xor r0,r9,r9 - add r3,r3,r0 - ld r0,CFG_TB_UPDATE_COUNT(r3) - cmpld cr0,r0,r8 /* check if updated */ - bne- 50b - - /* Calculate and store result. Note that this mimmics the C code, - * which may cause funny results if nsec goes negative... is that - * possible at all ? - */ - add r4,r4,r5 - add r7,r7,r6 - lis r9,NSEC_PER_SEC@h - ori r9,r9,NSEC_PER_SEC@l - cmpl cr0,r7,r9 - cmpli cr1,r7,0 - blt 1f - subf r7,r9,r7 - addi r4,r4,1 -1: bge cr1,1f - addi r4,r4,-1 - add r7,r7,r9 -1: std r4,TSPC64_TV_SEC(r11) - std r7,TSPC64_TV_NSEC(r11) - - mtlr r12 - crclr cr0*4+so - li r3,0 - blr - - /* - * syscall fallback - */ -98: - mtlr r12 - mr r3,r10 - mr r4,r11 -99: - li r0,__NR_clock_gettime - sc - blr - .cfi_endproc -V_FUNCTION_END(__kernel_clock_gettime) - - -/* - * Exact prototype of clock_getres() - * - * int __kernel_clock_getres(clockid_t clock_id, struct timespec *res); - * - */ -V_FUNCTION_BEGIN(__kernel_clock_getres) - .cfi_startproc - /* Check for supported clock IDs */ - cmpwi cr0,r3,CLOCK_REALTIME - cmpwi cr1,r3,CLOCK_MONOTONIC - cror cr0*4+eq,cr0*4+eq,cr1*4+eq - bne cr0,99f - - li r3,0 - cmpli cr0,r4,0 - crclr cr0*4+so - beqlr - lis r5,CLOCK_REALTIME_RES@h - ori r5,r5,CLOCK_REALTIME_RES@l - std r3,TSPC64_TV_SEC(r4) - std r5,TSPC64_TV_NSEC(r4) - blr - - /* - * syscall fallback - */ -99: - li r0,__NR_clock_getres - sc - blr - .cfi_endproc -V_FUNCTION_END(__kernel_clock_getres) - - -/* - * This is the core of gettimeofday(), it returns the xsec - * value in r4 and expects the datapage ptr (non clobbered) - * in r3. clobbers r0,r4,r5,r6,r7,r8 - * When returning, r8 contains the counter value that can be reused - */ -V_FUNCTION_BEGIN(__do_get_xsec) - .cfi_startproc - /* check for update count & load values */ -1: ld r8,CFG_TB_UPDATE_COUNT(r3) - andi. r0,r8,1 /* pending update ? loop */ - bne- 1b - xor r0,r8,r8 /* create dependency */ - add r3,r3,r0 - - /* Get TB & offset it. We use the MFTB macro which will generate - * workaround code for Cell. - */ - MFTB(r7) - ld r9,CFG_TB_ORIG_STAMP(r3) - subf r7,r9,r7 - - /* Scale result */ - ld r5,CFG_TB_TO_XS(r3) - mulhdu r7,r7,r5 - - /* Add stamp since epoch */ - ld r6,CFG_STAMP_XSEC(r3) - add r4,r6,r7 - - xor r0,r4,r4 - add r3,r3,r0 - ld r0,CFG_TB_UPDATE_COUNT(r3) - cmpld cr0,r0,r8 /* check if updated */ - bne- 1b - blr - .cfi_endproc -V_FUNCTION_END(__do_get_xsec) Index: linux-rt-rebase.q/arch/powerpc/kernel/vdso64/vdso64.lds.S =================================================================== --- linux-rt-rebase.q.orig/arch/powerpc/kernel/vdso64/vdso64.lds.S +++ linux-rt-rebase.q/arch/powerpc/kernel/vdso64/vdso64.lds.S @@ -115,10 +115,6 @@ VERSION global: __kernel_datapage_offset; /* Has to be there for the kernel to find */ __kernel_get_syscall_map; - __kernel_gettimeofday; - __kernel_clock_gettime; - __kernel_clock_getres; - __kernel_get_tbfreq; __kernel_sync_dicache; __kernel_sync_dicache_p5; __kernel_sigtramp_rt64; Index: linux-rt-rebase.q/arch/powerpc/lib/locks.c =================================================================== --- linux-rt-rebase.q.orig/arch/powerpc/lib/locks.c +++ linux-rt-rebase.q/arch/powerpc/lib/locks.c @@ -25,7 +25,7 @@ #include #include -void __spin_yield(raw_spinlock_t *lock) +void __spin_yield(__raw_spinlock_t *lock) { unsigned int lock_value, holder_cpu, yield_count; @@ -82,7 +82,7 @@ void __rw_yield(raw_rwlock_t *rw) } #endif -void __raw_spin_unlock_wait(raw_spinlock_t *lock) +void __raw_spin_unlock_wait(__raw_spinlock_t *lock) { while (lock->slock) { HMT_low(); Index: linux-rt-rebase.q/arch/powerpc/mm/fault.c =================================================================== --- linux-rt-rebase.q.orig/arch/powerpc/mm/fault.c +++ linux-rt-rebase.q/arch/powerpc/mm/fault.c @@ -184,7 +184,7 @@ int __kprobes do_page_fault(struct pt_re } #endif /* !(CONFIG_4xx || CONFIG_BOOKE)*/ - if (in_atomic() || mm == NULL) { + if (in_atomic() || mm == NULL || current->pagefault_disabled) { if (!user_mode(regs)) return SIGSEGV; /* in_atomic() in user mode is really bad, Index: linux-rt-rebase.q/arch/powerpc/mm/hash_native_64.c =================================================================== --- linux-rt-rebase.q.orig/arch/powerpc/mm/hash_native_64.c +++ linux-rt-rebase.q/arch/powerpc/mm/hash_native_64.c @@ -36,7 +36,7 @@ #define HPTE_LOCK_BIT 3 -static DEFINE_SPINLOCK(native_tlbie_lock); +static DEFINE_RAW_SPINLOCK(native_tlbie_lock); static inline void __tlbie(unsigned long va, unsigned int psize) { Index: linux-rt-rebase.q/arch/powerpc/mm/init_32.c =================================================================== --- linux-rt-rebase.q.orig/arch/powerpc/mm/init_32.c +++ linux-rt-rebase.q/arch/powerpc/mm/init_32.c @@ -55,7 +55,7 @@ #endif #define MAX_LOW_MEM CONFIG_LOWMEM_SIZE -DEFINE_PER_CPU(struct mmu_gather, mmu_gathers); +DEFINE_PER_CPU_LOCKED(struct mmu_gather, mmu_gathers); unsigned long total_memory; unsigned long total_lowmem; Index: linux-rt-rebase.q/arch/powerpc/mm/tlb_64.c =================================================================== --- linux-rt-rebase.q.orig/arch/powerpc/mm/tlb_64.c +++ linux-rt-rebase.q/arch/powerpc/mm/tlb_64.c @@ -30,13 +30,14 @@ #include #include #include +#include DEFINE_PER_CPU(struct ppc64_tlb_batch, ppc64_tlb_batch); /* This is declared as we are using the more or less generic * include/asm-powerpc/tlb.h file -- tgall */ -DEFINE_PER_CPU(struct mmu_gather, mmu_gathers); +DEFINE_PER_CPU_LOCKED(struct mmu_gather, mmu_gathers); DEFINE_PER_CPU(struct pte_freelist_batch *, pte_freelist_cur); unsigned long pte_freelist_forced_free; @@ -93,8 +94,11 @@ static void pte_free_submit(struct pte_f void pgtable_free_tlb(struct mmu_gather *tlb, pgtable_free_t pgf) { - /* This is safe since tlb_gather_mmu has disabled preemption */ - cpumask_t local_cpumask = cpumask_of_cpu(smp_processor_id()); + /* + * This is safe since tlb_gather_mmu has disabled preemption. + * tlb->cpu is set by tlb_gather_mmu as well. + */ + cpumask_t local_cpumask = cpumask_of_cpu(tlb->cpu); struct pte_freelist_batch **batchp = &__get_cpu_var(pte_freelist_cur); if (atomic_read(&tlb->mm->mm_users) < 2 || @@ -200,6 +204,18 @@ void hpte_need_flush(struct mm_struct *m batch->pte[i] = rpte; batch->vaddr[i] = vaddr; batch->index = ++i; + +#ifdef CONFIG_PREEMPT_RT + /* + * Since flushing tlb needs expensive hypervisor call(s) on celleb, + * always flush it on RT to reduce scheduling latency. + */ + if (machine_is(celleb)) { + flush_tlb_pending(); + return; + } +#endif /* CONFIG_PREEMPT_RT */ + if (i >= PPC64_TLB_BATCH_NR) __flush_tlb_pending(batch); } Index: linux-rt-rebase.q/arch/powerpc/platforms/82xx/mpc82xx_ads.c =================================================================== --- linux-rt-rebase.q.orig/arch/powerpc/platforms/82xx/mpc82xx_ads.c +++ linux-rt-rebase.q/arch/powerpc/platforms/82xx/mpc82xx_ads.c @@ -553,7 +553,8 @@ static void __init mpc82xx_add_bridge(st setup_indirect_pci(hose, r.start + offsetof(pci_cpm2_t, pci_cfg_addr), - r.start + offsetof(pci_cpm2_t, pci_cfg_data)); + r.start + offsetof(pci_cpm2_t, pci_cfg_data), + 0); pci_process_bridge_OF_ranges(hose, np, 1); } Index: linux-rt-rebase.q/arch/powerpc/platforms/83xx/pci.c =================================================================== --- linux-rt-rebase.q.orig/arch/powerpc/platforms/83xx/pci.c +++ linux-rt-rebase.q/arch/powerpc/platforms/83xx/pci.c @@ -74,11 +74,11 @@ int __init mpc83xx_add_bridge(struct dev */ /* PCI 1 */ if ((rsrc.start & 0xfffff) == 0x8500) { - setup_indirect_pci(hose, immr + 0x8300, immr + 0x8304); + setup_indirect_pci(hose, immr + 0x8300, immr + 0x8304, 0); } /* PCI 2 */ if ((rsrc.start & 0xfffff) == 0x8600) { - setup_indirect_pci(hose, immr + 0x8380, immr + 0x8384); + setup_indirect_pci(hose, immr + 0x8380, immr + 0x8384, 0); primary = 0; } Index: linux-rt-rebase.q/arch/powerpc/platforms/85xx/Kconfig =================================================================== --- linux-rt-rebase.q.orig/arch/powerpc/platforms/85xx/Kconfig +++ linux-rt-rebase.q/arch/powerpc/platforms/85xx/Kconfig @@ -18,6 +18,7 @@ config MPC8560_ADS config MPC85xx_CDS bool "Freescale MPC85xx CDS" select DEFAULT_UIMAGE + select PPC_I8259 help This option enables support for the MPC85xx CDS board @@ -30,6 +31,7 @@ config MPC85xx_MDS config MPC8544_DS bool "Freescale MPC8544 DS" + select PPC_I8259 select DEFAULT_UIMAGE help This option enables support for the MPC8544 DS board @@ -50,9 +52,9 @@ config MPC8560 config MPC85xx bool select PPC_UDBG_16550 - select PPC_INDIRECT_PCI - select PPC_INDIRECT_PCI_BE + select PPC_INDIRECT_PCI if PCI select MPIC + select FSL_PCI if PCI select SERIAL_8250_SHARE_IRQ if SERIAL_8250 default y if MPC8540_ADS || MPC85xx_CDS || MPC8560_ADS \ || MPC85xx_MDS || MPC8544_DS Index: linux-rt-rebase.q/arch/powerpc/platforms/85xx/Makefile =================================================================== --- linux-rt-rebase.q.orig/arch/powerpc/platforms/85xx/Makefile +++ linux-rt-rebase.q/arch/powerpc/platforms/85xx/Makefile @@ -1,7 +1,7 @@ # # Makefile for the PowerPC 85xx linux kernel. # -obj-$(CONFIG_PPC_85xx) += misc.o pci.o +obj-$(CONFIG_PPC_85xx) += misc.o obj-$(CONFIG_MPC8540_ADS) += mpc85xx_ads.o obj-$(CONFIG_MPC8560_ADS) += mpc85xx_ads.o obj-$(CONFIG_MPC85xx_CDS) += mpc85xx_cds.o Index: linux-rt-rebase.q/arch/powerpc/platforms/85xx/mpc8544_ds.c =================================================================== --- linux-rt-rebase.q.orig/arch/powerpc/platforms/85xx/mpc8544_ds.c +++ linux-rt-rebase.q/arch/powerpc/platforms/85xx/mpc8544_ds.c @@ -2,6 +2,8 @@ * MPC8544 DS Board Setup * * Author Xianghua Xiao (x.xiao@freescale.com) + * Roy Zang + * - Add PCI/PCI Exprees support * Copyright 2007 Freescale Semiconductor Inc. * * This program is free software; you can redistribute it and/or modify it @@ -12,13 +14,16 @@ #include #include +#include #include #include #include +#include #include #include #include +#include #include #include #include @@ -27,6 +32,7 @@ #include #include +#include #include "mpc85xx.h" #undef DEBUG @@ -37,6 +43,17 @@ #define DBG(fmt, args...) #endif +#ifdef CONFIG_PPC_I8259 +static void mpc8544_8259_cascade(unsigned int irq, struct irq_desc *desc) +{ + unsigned int cascade_irq = i8259_irq(); + + if (cascade_irq != NO_IRQ) { + generic_handle_irq(cascade_irq); + } + desc->chip->eoi(irq); +} +#endif /* CONFIG_PPC_I8259 */ void __init mpc8544_ds_pic_init(void) { @@ -96,19 +113,240 @@ void __init mpc8544_ds_pic_init(void) #endif /* CONFIG_PPC_I8259 */ } +#ifdef CONFIG_PCI +enum pirq { PIRQA = 8, PIRQB, PIRQC, PIRQD, PIRQE, PIRQF, PIRQG, PIRQH }; + +/* + * Value in table -- IRQ number + */ +const unsigned char uli1575_irq_route_table[16] = { + 0, /* 0: Reserved */ + 0x8, + 0, /* 2: Reserved */ + 0x2, + 0x4, + 0x5, + 0x7, + 0x6, + 0, /* 8: Reserved */ + 0x1, + 0x3, + 0x9, + 0xb, + 0, /* 13: Reserved */ + 0xd, + 0xf, +}; + +static int __devinit +get_pci_irq_from_of(struct pci_controller *hose, int slot, int pin) +{ + struct of_irq oirq; + u32 laddr[3]; + struct device_node *hosenode = hose ? hose->arch_data : NULL; + + if (!hosenode) + return -EINVAL; + + laddr[0] = (hose->first_busno << 16) | (PCI_DEVFN(slot, 0) << 8); + laddr[1] = laddr[2] = 0; + of_irq_map_raw(hosenode, &pin, 1, laddr, &oirq); + DBG("mpc8544_ds: pci irq addr %x, slot %d, pin %d, irq %d\n", + laddr[0], slot, pin, oirq.specifier[0]); + return oirq.specifier[0]; +} + +/*8259*/ +static void __devinit quirk_uli1575(struct pci_dev *dev) +{ + unsigned short temp; + struct pci_controller *hose = pci_bus_to_host(dev->bus); + unsigned char irq2pin[16]; + unsigned long pirq_map_word = 0; + u32 irq; + int i; + + /* + * ULI1575 interrupts route setup + */ + memset(irq2pin, 0, 16); /* Initialize default value 0 */ + + irq2pin[6]=PIRQA+3; /* enabled mapping for IRQ6 to PIRQD, used by SATA */ + + /* + * PIRQE -> PIRQF mapping set manually + * + * IRQ pin IRQ# + * PIRQE ---- 9 + * PIRQF ---- 10 + * PIRQG ---- 11 + * PIRQH ---- 12 + */ + for (i = 0; i < 4; i++) + irq2pin[i + 9] = PIRQE + i; + + /* Set IRQ-PIRQ Mapping to ULI1575 */ + for (i = 0; i < 16; i++) + if (irq2pin[i]) + pirq_map_word |= (uli1575_irq_route_table[i] & 0xf) + << ((irq2pin[i] - PIRQA) * 4); + + pirq_map_word |= 1<<26; /* disable INTx in EP mode*/ + + /* ULI1575 IRQ mapping conf register default value is 0xb9317542 */ + DBG("Setup ULI1575 IRQ mapping configuration register value = 0x%x\n", + (int)pirq_map_word); + pci_write_config_dword(dev, 0x48, pirq_map_word); + +#define ULI1575_SET_DEV_IRQ(slot, pin, reg) \ + do { \ + int irq; \ + irq = get_pci_irq_from_of(hose, slot, pin); \ + if (irq > 0 && irq < 16) \ + pci_write_config_byte(dev, reg, irq2pin[irq]); \ + else \ + printk(KERN_WARNING "ULI1575 device" \ + "(slot %d, pin %d) irq %d is invalid.\n", \ + slot, pin, irq); \ + } while(0) + + /* USB 1.1 OHCI controller 1, slot 28, pin 1 */ + ULI1575_SET_DEV_IRQ(28, 1, 0x86); + + /* USB 1.1 OHCI controller 2, slot 28, pin 2 */ + ULI1575_SET_DEV_IRQ(28, 2, 0x87); + + /* USB 1.1 OHCI controller 3, slot 28, pin 3 */ + ULI1575_SET_DEV_IRQ(28, 3, 0x88); + + /* USB 2.0 controller, slot 28, pin 4 */ + irq = get_pci_irq_from_of(hose, 28, 4); + if (irq >= 0 && irq <= 15) + pci_write_config_dword(dev, 0x74, uli1575_irq_route_table[irq]); + + /* Audio controller, slot 29, pin 1 */ + ULI1575_SET_DEV_IRQ(29, 1, 0x8a); + + /* Modem controller, slot 29, pin 2 */ + ULI1575_SET_DEV_IRQ(29, 2, 0x8b); + + /* HD audio controller, slot 29, pin 3 */ + ULI1575_SET_DEV_IRQ(29, 3, 0x8c); + + /* SMB interrupt: slot 30, pin 1 */ + ULI1575_SET_DEV_IRQ(30, 1, 0x8e); + + /* PMU ACPI SCI interrupt: slot 30, pin 2 */ + ULI1575_SET_DEV_IRQ(30, 2, 0x8f); + + /* Serial ATA interrupt: slot 31, pin 1 */ + ULI1575_SET_DEV_IRQ(31, 1, 0x8d); + + /* Primary PATA IDE IRQ: 14 + * Secondary PATA IDE IRQ: 15 + */ + pci_write_config_byte(dev, 0x44, 0x30 | uli1575_irq_route_table[14]); + pci_write_config_byte(dev, 0x75, uli1575_irq_route_table[15]); + + /* Set IRQ14 and IRQ15 to legacy IRQs */ + pci_read_config_word(dev, 0x46, &temp); + temp |= 0xc000; + pci_write_config_word(dev, 0x46, temp); + + /* Set i8259 interrupt trigger + * IRQ 3: Level + * IRQ 4: Level + * IRQ 5: Level + * IRQ 6: Level + * IRQ 7: Level + * IRQ 9: Level + * IRQ 10: Level + * IRQ 11: Level + * IRQ 12: Level + * IRQ 14: Edge + * IRQ 15: Edge + */ + outb(0xfa, 0x4d0); + outb(0x1e, 0x4d1); + +#undef ULI1575_SET_DEV_IRQ +} + +/* SATA */ +static void __devinit quirk_uli5288(struct pci_dev *dev) +{ + unsigned char c; + + pci_read_config_byte(dev, 0x83, &c); + c |= 0x80; /* read/write lock */ + pci_write_config_byte(dev, 0x83, c); + + pci_write_config_byte(dev, 0x09, 0x01); /* Base class code: storage */ + pci_write_config_byte(dev, 0x0a, 0x06); /* IDE disk */ + + pci_read_config_byte(dev, 0x83, &c); + c &= 0x7f; + pci_write_config_byte(dev, 0x83, c); + + pci_read_config_byte(dev, 0x84, &c); + c |= 0x01; /* emulated PATA mode enabled */ + pci_write_config_byte(dev, 0x84, c); +} + +/* PATA */ +static void __devinit quirk_uli5229(struct pci_dev *dev) +{ + unsigned short temp; + pci_write_config_word(dev, 0x04, 0x0405); /* MEM IO MSI */ + pci_read_config_word(dev, 0x4a, &temp); + temp |= 0x1000; /* Enable Native IRQ 14/15 */ + pci_write_config_word(dev, 0x4a, temp); +} + +/*Bridge*/ +static void __devinit early_uli5249(struct pci_dev *dev) +{ + unsigned char temp; + pci_write_config_word(dev, 0x04, 0x0007); /* mem access */ + pci_read_config_byte(dev, 0x7c, &temp); + pci_write_config_byte(dev, 0x7c, 0x80); /* R/W lock control */ + pci_write_config_byte(dev, 0x09, 0x01); /* set as pci-pci bridge */ + pci_write_config_byte(dev, 0x7c, temp); /* restore pci bus debug control */ + dev->class |= 0x1; +} + +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AL, 0x1575, quirk_uli1575); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AL, 0x5288, quirk_uli5288); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AL, 0x5229, quirk_uli5229); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_AL, 0x5249, early_uli5249); +#endif /* CONFIG_PCI */ /* * Setup the architecture */ static void __init mpc8544_ds_setup_arch(void) { +#ifdef CONFIG_PCI + struct device_node *np; +#endif + if (ppc_md.progress) ppc_md.progress("mpc8544_ds_setup_arch()", 0); +#ifdef CONFIG_PCI + for (np = NULL; (np = of_find_node_by_type(np, "pci")) != NULL;) { + struct resource rsrc; + of_address_to_resource(np, 0, &rsrc); + if ((rsrc.start & 0xfffff) == 0xb000) + fsl_add_bridge(np, 1); + else + fsl_add_bridge(np, 0); + } +#endif + printk("MPC8544 DS board from Freescale Semiconductor\n"); } - /* * Called very early, device-tree isn't unflattened */ @@ -124,6 +362,7 @@ define_machine(mpc8544_ds) { .probe = mpc8544_ds_probe, .setup_arch = mpc8544_ds_setup_arch, .init_IRQ = mpc8544_ds_pic_init, + .pcibios_fixup_bus = fsl_pcibios_fixup_bus, .get_irq = mpic_get_irq, .restart = mpc85xx_restart, .calibrate_decr = generic_calibrate_decr, Index: linux-rt-rebase.q/arch/powerpc/platforms/85xx/mpc85xx.h =================================================================== --- linux-rt-rebase.q.orig/arch/powerpc/platforms/85xx/mpc85xx.h +++ linux-rt-rebase.q/arch/powerpc/platforms/85xx/mpc85xx.h @@ -15,4 +15,3 @@ */ extern void mpc85xx_restart(char *); -extern int mpc85xx_add_bridge(struct device_node *dev); Index: linux-rt-rebase.q/arch/powerpc/platforms/85xx/mpc85xx_ads.c =================================================================== --- linux-rt-rebase.q.orig/arch/powerpc/platforms/85xx/mpc85xx_ads.c +++ linux-rt-rebase.q/arch/powerpc/platforms/85xx/mpc85xx_ads.c @@ -29,6 +29,7 @@ #include #include +#include #include "mpc85xx.h" #ifdef CONFIG_CPM2 @@ -217,7 +218,7 @@ static void __init mpc85xx_ads_setup_arc #ifdef CONFIG_PCI for (np = NULL; (np = of_find_node_by_type(np, "pci")) != NULL;) - mpc85xx_add_bridge(np); + fsl_add_bridge(np, 1); ppc_md.pci_exclude_device = mpc85xx_exclude_device; #endif } Index: linux-rt-rebase.q/arch/powerpc/platforms/85xx/mpc85xx_cds.c =================================================================== --- linux-rt-rebase.q.orig/arch/powerpc/platforms/85xx/mpc85xx_cds.c +++ linux-rt-rebase.q/arch/powerpc/platforms/85xx/mpc85xx_cds.c @@ -24,6 +24,7 @@ #include #include #include +#include #include #include @@ -45,6 +46,7 @@ #include #include +#include #include "mpc85xx.h" static int cds_pci_slot = 2; @@ -58,8 +60,6 @@ static volatile u8 *cadmus; static int mpc85xx_exclude_device(struct pci_controller *hose, u_char bus, u_char devfn) { - if ((bus == hose->first_busno) && PCI_SLOT(devfn) == 0) - return PCIBIOS_DEVICE_NOT_FOUND; /* We explicitly do not go past the Tundra 320 Bridge */ if ((bus == 1) && (PCI_SLOT(devfn) == ARCADIA_2ND_BRIDGE_IDSEL)) return PCIBIOS_DEVICE_NOT_FOUND; @@ -69,6 +69,37 @@ static int mpc85xx_exclude_device(struct return PCIBIOS_SUCCESSFUL; } +static void mpc85xx_cds_restart(char *cmd) +{ + struct pci_dev *dev; + u_char tmp; + + if ((dev = pci_get_device(PCI_VENDOR_ID_VIA, PCI_DEVICE_ID_VIA_82C686, + NULL))) { + + /* Use the VIA Super Southbridge to force a PCI reset */ + pci_read_config_byte(dev, 0x47, &tmp); + pci_write_config_byte(dev, 0x47, tmp | 1); + + /* Flush the outbound PCI write queues */ + pci_read_config_byte(dev, 0x47, &tmp); + + /* + * At this point, the harware reset should have triggered. + * However, if it doesn't work for some mysterious reason, + * just fall through to the default reset below. + */ + + pci_dev_put(dev); + } + + /* + * If we can't find the VIA chip (maybe the P2P bridge is disabled) + * or the VIA chip reset didn't work, just use the default reset. + */ + mpc85xx_restart(NULL); +} + static void __init mpc85xx_cds_pci_irq_fixup(struct pci_dev *dev) { u_char c; @@ -98,7 +129,7 @@ static void __init mpc85xx_cds_pci_irq_f /* There are two USB controllers. * Identify them by functon number */ - if (PCI_FUNC(dev->devfn)) + if (PCI_FUNC(dev->devfn) == 3) dev->irq = 11; else dev->irq = 10; @@ -109,17 +140,41 @@ static void __init mpc85xx_cds_pci_irq_f } } +static void __devinit skip_fake_bridge(struct pci_dev *dev) +{ + /* Make it an error to skip the fake bridge + * in pci_setup_device() in probe.c */ + dev->hdr_type = 0x7f; +} +DECLARE_PCI_FIXUP_EARLY(0x1957, 0x3fff, skip_fake_bridge); +DECLARE_PCI_FIXUP_EARLY(0x3fff, 0x1957, skip_fake_bridge); +DECLARE_PCI_FIXUP_EARLY(0xff3f, 0x5719, skip_fake_bridge); + #ifdef CONFIG_PPC_I8259 -#warning The i8259 PIC support is currently broken -static void mpc85xx_8259_cascade(unsigned int irq, struct irq_desc *desc) +static void mpc85xx_8259_cascade_handler(unsigned int irq, + struct irq_desc *desc) { unsigned int cascade_irq = i8259_irq(); if (cascade_irq != NO_IRQ) + /* handle an interrupt from the 8259 */ generic_handle_irq(cascade_irq); - desc->chip->eoi(irq); + /* check for any interrupts from the shared IRQ line */ + handle_fasteoi_irq(irq, desc); +} + +static irqreturn_t mpc85xx_8259_cascade_action(int irq, void *dev_id) +{ + return IRQ_HANDLED; } + +static struct irqaction mpc85xxcds_8259_irqaction = { + .handler = mpc85xx_8259_cascade_action, + .flags = IRQF_SHARED, + .mask = CPU_MASK_NONE, + .name = "8259 cascade", +}; #endif /* PPC_I8259 */ #endif /* CONFIG_PCI */ @@ -128,10 +183,6 @@ static void __init mpc85xx_cds_pic_init( struct mpic *mpic; struct resource r; struct device_node *np = NULL; -#ifdef CONFIG_PPC_I8259 - struct device_node *cascade_node = NULL; - int cascade_irq; -#endif np = of_find_node_by_type(np, "open-pic"); @@ -155,8 +206,19 @@ static void __init mpc85xx_cds_pic_init( of_node_put(np); mpic_init(mpic); +} + +#if defined(CONFIG_PPC_I8259) && defined(CONFIG_PCI) +static int mpc85xx_cds_8259_attach(void) +{ + int ret; + struct device_node *np = NULL; + struct device_node *cascade_node = NULL; + int cascade_irq; + + if (!machine_is(mpc85xx_cds)) + return 0; -#ifdef CONFIG_PPC_I8259 /* Initialize the i8259 controller */ for_each_node_by_type(np, "interrupt-controller") if (of_device_is_compatible(np, "chrp,iic")) { @@ -166,22 +228,39 @@ static void __init mpc85xx_cds_pic_init( if (cascade_node == NULL) { printk(KERN_DEBUG "Could not find i8259 PIC\n"); - return; + return -ENODEV; } cascade_irq = irq_of_parse_and_map(cascade_node, 0); if (cascade_irq == NO_IRQ) { printk(KERN_ERR "Failed to map cascade interrupt\n"); - return; + return -ENXIO; } i8259_init(cascade_node, 0); of_node_put(cascade_node); - set_irq_chained_handler(cascade_irq, mpc85xx_8259_cascade); -#endif /* CONFIG_PPC_I8259 */ + /* + * Hook the interrupt to make sure desc->action is never NULL. + * This is required to ensure that the interrupt does not get + * disabled when the last user of the shared IRQ line frees their + * interrupt. + */ + if ((ret = setup_irq(cascade_irq, &mpc85xxcds_8259_irqaction))) { + printk(KERN_ERR "Failed to setup cascade interrupt\n"); + return ret; + } + + /* Success. Connect our low-level cascade handler. */ + set_irq_handler(cascade_irq, mpc85xx_8259_cascade_handler); + + return 0; } +device_initcall(mpc85xx_cds_8259_attach); + +#endif /* CONFIG_PPC_I8259 */ + /* * Setup the architecture */ @@ -218,9 +297,14 @@ static void __init mpc85xx_cds_setup_arc } #ifdef CONFIG_PCI - for (np = NULL; (np = of_find_node_by_type(np, "pci")) != NULL;) - mpc85xx_add_bridge(np); - + for (np = NULL; (np = of_find_node_by_type(np, "pci")) != NULL;) { + struct resource rsrc; + of_address_to_resource(np, 0, &rsrc); + if ((rsrc.start & 0xfffff) == 0x8000) + fsl_add_bridge(np, 1); + else + fsl_add_bridge(np, 0); + } ppc_md.pci_irq_fixup = mpc85xx_cds_pci_irq_fixup; ppc_md.pci_exclude_device = mpc85xx_exclude_device; #endif @@ -265,7 +349,12 @@ define_machine(mpc85xx_cds) { .init_IRQ = mpc85xx_cds_pic_init, .show_cpuinfo = mpc85xx_cds_show_cpuinfo, .get_irq = mpic_get_irq, +#ifdef CONFIG_PCI + .restart = mpc85xx_cds_restart, +#else .restart = mpc85xx_restart, +#endif .calibrate_decr = generic_calibrate_decr, .progress = udbg_progress, + .pcibios_fixup_bus = fsl_pcibios_fixup_bus, }; Index: linux-rt-rebase.q/arch/powerpc/platforms/85xx/mpc85xx_mds.c =================================================================== --- linux-rt-rebase.q.orig/arch/powerpc/platforms/85xx/mpc85xx_mds.c +++ linux-rt-rebase.q/arch/powerpc/platforms/85xx/mpc85xx_mds.c @@ -46,6 +46,7 @@ #include #include #include +#include #include #include #include @@ -94,9 +95,8 @@ static void __init mpc85xx_mds_setup_arc } #ifdef CONFIG_PCI - for (np = NULL; (np = of_find_node_by_type(np, "pci")) != NULL;) { - mpc85xx_add_bridge(np); - } + for (np = NULL; (np = of_find_node_by_type(np, "pci")) != NULL;) + fsl_add_bridge(np, 1); of_node_put(np); #endif @@ -208,4 +208,5 @@ define_machine(mpc85xx_mds) { .restart = mpc85xx_restart, .calibrate_decr = generic_calibrate_decr, .progress = udbg_progress, + .pcibios_fixup_bus = fsl_pcibios_fixup_bus, }; Index: linux-rt-rebase.q/arch/powerpc/platforms/85xx/pci.c =================================================================== --- linux-rt-rebase.q.orig/arch/powerpc/platforms/85xx/pci.c +++ /dev/null @@ -1,91 +0,0 @@ -/* - * FSL SoC setup code - * - * Maintained by Kumar Gala (see MAINTAINERS for contact information) - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License as published by the - * Free Software Foundation; either version 2 of the License, or (at your - * option) any later version. - */ - -#include -#include -#include -#include -#include -#include -#include -#include - -#include -#include -#include -#include -#include -#include - -#undef DEBUG - -#ifdef DEBUG -#define DBG(x...) printk(x) -#else -#define DBG(x...) -#endif - -#ifdef CONFIG_PCI -int __init mpc85xx_add_bridge(struct device_node *dev) -{ - int len; - struct pci_controller *hose; - struct resource rsrc; - const int *bus_range; - int primary = 1, has_address = 0; - phys_addr_t immr = get_immrbase(); - - DBG("Adding PCI host bridge %s\n", dev->full_name); - - /* Fetch host bridge registers address */ - has_address = (of_address_to_resource(dev, 0, &rsrc) == 0); - - /* Get bus range if any */ - bus_range = of_get_property(dev, "bus-range", &len); - if (bus_range == NULL || len < 2 * sizeof(int)) { - printk(KERN_WARNING "Can't get bus-range for %s, assume" - " bus 0\n", dev->full_name); - } - - pci_assign_all_buses = 1; - hose = pcibios_alloc_controller(dev); - if (!hose) - return -ENOMEM; - - hose->first_busno = bus_range ? bus_range[0] : 0; - hose->last_busno = bus_range ? bus_range[1] : 0xff; - - /* PCI 1 */ - if ((rsrc.start & 0xfffff) == 0x8000) { - setup_indirect_pci(hose, immr + 0x8000, immr + 0x8004); - } - /* PCI 2 */ - if ((rsrc.start & 0xfffff) == 0x9000) { - setup_indirect_pci(hose, immr + 0x9000, immr + 0x9004); - primary = 0; - } - - printk(KERN_INFO "Found MPC85xx PCI host bridge at 0x%016llx. " - "Firmware bus number: %d->%d\n", - (unsigned long long)rsrc.start, hose->first_busno, - hose->last_busno); - - DBG(" ->Hose at 0x%p, cfg_addr=0x%p,cfg_data=0x%p\n", - hose, hose->cfg_addr, hose->cfg_data); - - /* Interpret the "ranges" property */ - /* This also maps the I/O region and sets isa_io/mem_base */ - pci_process_bridge_OF_ranges(hose, dev, primary); - - return 0; -} - -#endif Index: linux-rt-rebase.q/arch/powerpc/platforms/86xx/Kconfig =================================================================== --- linux-rt-rebase.q.orig/arch/powerpc/platforms/86xx/Kconfig +++ linux-rt-rebase.q/arch/powerpc/platforms/86xx/Kconfig @@ -14,8 +14,7 @@ endchoice config MPC8641 bool - select PPC_INDIRECT_PCI - select PPC_INDIRECT_PCI_BE + select FSL_PCI if PCI select PPC_UDBG_16550 select MPIC default y if MPC8641_HPCN Index: linux-rt-rebase.q/arch/powerpc/platforms/86xx/Makefile =================================================================== --- linux-rt-rebase.q.orig/arch/powerpc/platforms/86xx/Makefile +++ linux-rt-rebase.q/arch/powerpc/platforms/86xx/Makefile @@ -4,4 +4,3 @@ obj-$(CONFIG_SMP) += mpc86xx_smp.o obj-$(CONFIG_MPC8641_HPCN) += mpc86xx_hpcn.o -obj-$(CONFIG_PCI) += pci.o Index: linux-rt-rebase.q/arch/powerpc/platforms/86xx/mpc86xx.h =================================================================== --- linux-rt-rebase.q.orig/arch/powerpc/platforms/86xx/mpc86xx.h +++ linux-rt-rebase.q/arch/powerpc/platforms/86xx/mpc86xx.h @@ -15,11 +15,6 @@ * mpc86xx_* files. Mostly for use by mpc86xx_setup(). */ -extern int mpc86xx_add_bridge(struct device_node *dev); - -extern int mpc86xx_exclude_device(struct pci_controller *hose, - u_char bus, u_char devfn); - extern void __init mpc86xx_smp_init(void); #endif /* __MPC86XX_H__ */ Index: linux-rt-rebase.q/arch/powerpc/platforms/86xx/mpc86xx_hpcn.c =================================================================== --- linux-rt-rebase.q.orig/arch/powerpc/platforms/86xx/mpc86xx_hpcn.c +++ linux-rt-rebase.q/arch/powerpc/platforms/86xx/mpc86xx_hpcn.c @@ -31,6 +31,7 @@ #include +#include #include #include "mpc86xx.h" @@ -344,8 +345,14 @@ mpc86xx_hpcn_setup_arch(void) } #ifdef CONFIG_PCI - for (np = NULL; (np = of_find_node_by_type(np, "pci")) != NULL;) - mpc86xx_add_bridge(np); + for (np = NULL; (np = of_find_node_by_type(np, "pci")) != NULL;) { + struct resource rsrc; + of_address_to_resource(np, 0, &rsrc); + if ((rsrc.start & 0xfffff) == 0x8000) + fsl_add_bridge(np, 1); + else + fsl_add_bridge(np, 0); + } #endif printk("MPC86xx HPCN board from Freescale Semiconductor\n"); @@ -424,7 +431,6 @@ mpc86xx_time_init(void) return 0; } - define_machine(mpc86xx_hpcn) { .name = "MPC86xx HPCN", .probe = mpc86xx_hpcn_probe, @@ -436,4 +442,5 @@ define_machine(mpc86xx_hpcn) { .time_init = mpc86xx_time_init, .calibrate_decr = generic_calibrate_decr, .progress = udbg_progress, + .pcibios_fixup_bus = fsl_pcibios_fixup_bus, }; Index: linux-rt-rebase.q/arch/powerpc/platforms/86xx/pci.c =================================================================== --- linux-rt-rebase.q.orig/arch/powerpc/platforms/86xx/pci.c +++ /dev/null @@ -1,238 +0,0 @@ -/* - * MPC86XX pci setup code - * - * Recode: ZHANG WEI - * Initial author: Xianghua Xiao - * - * Copyright 2006 Freescale Semiconductor Inc. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License as published by the - * Free Software Foundation; either version 2 of the License, or (at your - * option) any later version. - */ - -#include -#include -#include -#include -#include - -#include -#include -#include -#include -#include -#include -#include - -#include "mpc86xx.h" - -#undef DEBUG - -#ifdef DEBUG -#define DBG(fmt, args...) printk(KERN_ERR "%s: " fmt, __FUNCTION__, ## args) -#else -#define DBG(fmt, args...) -#endif - -struct pcie_outbound_window_regs { - uint pexotar; /* 0x.0 - PCI Express outbound translation address register */ - uint pexotear; /* 0x.4 - PCI Express outbound translation extended address register */ - uint pexowbar; /* 0x.8 - PCI Express outbound window base address register */ - char res1[4]; - uint pexowar; /* 0x.10 - PCI Express outbound window attributes register */ - char res2[12]; -}; - -struct pcie_inbound_window_regs { - uint pexitar; /* 0x.0 - PCI Express inbound translation address register */ - char res1[4]; - uint pexiwbar; /* 0x.8 - PCI Express inbound window base address register */ - uint pexiwbear; /* 0x.c - PCI Express inbound window base extended address register */ - uint pexiwar; /* 0x.10 - PCI Express inbound window attributes register */ - char res2[12]; -}; - -static void __init setup_pcie_atmu(struct pci_controller *hose, struct resource *rsrc) -{ - volatile struct ccsr_pex *pcie; - volatile struct pcie_outbound_window_regs *pcieow; - volatile struct pcie_inbound_window_regs *pcieiw; - int i = 0; - - DBG("PCIE memory map start 0x%x, size 0x%x\n", rsrc->start, - rsrc->end - rsrc->start + 1); - pcie = ioremap(rsrc->start, rsrc->end - rsrc->start + 1); - - /* Disable all windows (except pexowar0 since its ignored) */ - pcie->pexowar1 = 0; - pcie->pexowar2 = 0; - pcie->pexowar3 = 0; - pcie->pexowar4 = 0; - pcie->pexiwar1 = 0; - pcie->pexiwar2 = 0; - pcie->pexiwar3 = 0; - - pcieow = (struct pcie_outbound_window_regs *)&pcie->pexotar1; - pcieiw = (struct pcie_inbound_window_regs *)&pcie->pexitar1; - - /* Setup outbound MEM window */ - for(i = 0; i < 3; i++) - if (hose->mem_resources[i].flags & IORESOURCE_MEM){ - DBG("PCIE MEM resource start 0x%08x, size 0x%08x.\n", - hose->mem_resources[i].start, - hose->mem_resources[i].end - - hose->mem_resources[i].start + 1); - pcieow->pexotar = (hose->mem_resources[i].start) >> 12 - & 0x000fffff; - pcieow->pexotear = 0; - pcieow->pexowbar = (hose->mem_resources[i].start) >> 12 - & 0x000fffff; - /* Enable, Mem R/W */ - pcieow->pexowar = 0x80044000 | - (__ilog2(hose->mem_resources[i].end - - hose->mem_resources[i].start + 1) - - 1); - pcieow++; - } - - /* Setup outbound IO window */ - if (hose->io_resource.flags & IORESOURCE_IO){ - DBG("PCIE IO resource start 0x%08x, size 0x%08x, phy base 0x%08x.\n", - hose->io_resource.start, - hose->io_resource.end - hose->io_resource.start + 1, - hose->io_base_phys); - pcieow->pexotar = (hose->io_resource.start) >> 12 & 0x000fffff; - pcieow->pexotear = 0; - pcieow->pexowbar = (hose->io_base_phys) >> 12 & 0x000fffff; - /* Enable, IO R/W */ - pcieow->pexowar = 0x80088000 | (__ilog2(hose->io_resource.end - - hose->io_resource.start + 1) - 1); - } - - /* Setup 2G inbound Memory Window @ 0 */ - pcieiw->pexitar = 0x00000000; - pcieiw->pexiwbar = 0x00000000; - /* Enable, Prefetch, Local Mem, Snoop R/W, 2G */ - pcieiw->pexiwar = 0xa0f5501e; -} - -static void __init -mpc86xx_setup_pcie(struct pci_controller *hose, u32 pcie_offset, u32 pcie_size) -{ - u16 cmd; - - DBG("PCIE host controller register offset 0x%08x, size 0x%08x.\n", - pcie_offset, pcie_size); - - early_read_config_word(hose, 0, 0, PCI_COMMAND, &cmd); - cmd |= PCI_COMMAND_SERR | PCI_COMMAND_MASTER | PCI_COMMAND_MEMORY - | PCI_COMMAND_IO; - early_write_config_word(hose, 0, 0, PCI_COMMAND, cmd); - - early_write_config_byte(hose, 0, 0, PCI_LATENCY_TIMER, 0x80); -} - -static void __devinit quirk_fsl_pcie_transparent(struct pci_dev *dev) -{ - struct resource *res; - int i, res_idx = PCI_BRIDGE_RESOURCES; - struct pci_controller *hose; - - /* - * Make the bridge be transparent. - */ - dev->transparent = 1; - - hose = pci_bus_to_host(dev->bus); - if (!hose) { - printk(KERN_ERR "Can't find hose for bus %d\n", - dev->bus->number); - return; - } - - if (hose->io_resource.flags) { - res = &dev->resource[res_idx++]; - res->start = hose->io_resource.start; - res->end = hose->io_resource.end; - res->flags = hose->io_resource.flags; - } - - for (i = 0; i < 3; i++) { - res = &dev->resource[res_idx + i]; - res->start = hose->mem_resources[i].start; - res->end = hose->mem_resources[i].end; - res->flags = hose->mem_resources[i].flags; - } -} - - -DECLARE_PCI_FIXUP_EARLY(0x1957, 0x7010, quirk_fsl_pcie_transparent); -DECLARE_PCI_FIXUP_EARLY(0x1957, 0x7011, quirk_fsl_pcie_transparent); - -#define PCIE_LTSSM 0x404 /* PCIe Link Training and Status */ -#define PCIE_LTSSM_L0 0x16 /* L0 state */ - -int __init mpc86xx_add_bridge(struct device_node *dev) -{ - int len; - struct pci_controller *hose; - struct resource rsrc; - const int *bus_range; - int has_address = 0; - int primary = 0; - u16 val; - - DBG("Adding PCIE host bridge %s\n", dev->full_name); - - /* Fetch host bridge registers address */ - has_address = (of_address_to_resource(dev, 0, &rsrc) == 0); - - /* Get bus range if any */ - bus_range = of_get_property(dev, "bus-range", &len); - if (bus_range == NULL || len < 2 * sizeof(int)) - printk(KERN_WARNING "Can't get bus-range for %s, assume" - " bus 0\n", dev->full_name); - - pci_assign_all_buses = 1; - hose = pcibios_alloc_controller(dev); - if (!hose) - return -ENOMEM; - - hose->indirect_type = PPC_INDIRECT_TYPE_EXT_REG | - PPC_INDIRECT_TYPE_SURPRESS_PRIMARY_BUS; - - hose->first_busno = bus_range ? bus_range[0] : 0x0; - hose->last_busno = bus_range ? bus_range[1] : 0xff; - - setup_indirect_pci(hose, rsrc.start, rsrc.start + 0x4); - - /* Probe the hose link training status */ - early_read_config_word(hose, 0, 0, PCIE_LTSSM, &val); - if (val < PCIE_LTSSM_L0) - return -ENXIO; - - /* Setup the PCIE host controller. */ - mpc86xx_setup_pcie(hose, rsrc.start, rsrc.end - rsrc.start + 1); - - if ((rsrc.start & 0xfffff) == 0x8000) - primary = 1; - - printk(KERN_INFO "Found MPC86xx PCIE host bridge at 0x%08lx. " - "Firmware bus number: %d->%d\n", - (unsigned long) rsrc.start, - hose->first_busno, hose->last_busno); - - DBG(" ->Hose at 0x%p, cfg_addr=0x%p,cfg_data=0x%p\n", - hose, hose->cfg_addr, hose->cfg_data); - - /* Interpret the "ranges" property */ - /* This also maps the I/O region and sets isa_io/mem_base */ - pci_process_bridge_OF_ranges(hose, dev, primary); - - /* Setup PEX window registers */ - setup_pcie_atmu(hose, &rsrc); - - return 0; -} Index: linux-rt-rebase.q/arch/powerpc/platforms/cell/smp.c =================================================================== --- linux-rt-rebase.q.orig/arch/powerpc/platforms/cell/smp.c +++ linux-rt-rebase.q/arch/powerpc/platforms/cell/smp.c @@ -133,7 +133,7 @@ static void __devinit smp_iic_setup_cpu( iic_setup_cpu(); } -static DEFINE_SPINLOCK(timebase_lock); +static DEFINE_RAW_SPINLOCK(timebase_lock); static unsigned long timebase = 0; static void __devinit cell_give_timebase(void) Index: linux-rt-rebase.q/arch/powerpc/platforms/cell/spufs/spufs.h =================================================================== --- linux-rt-rebase.q.orig/arch/powerpc/platforms/cell/spufs/spufs.h +++ linux-rt-rebase.q/arch/powerpc/platforms/cell/spufs/spufs.h @@ -40,13 +40,10 @@ enum { struct spu_context_ops; struct spu_gang; -enum { - SPU_SCHED_WAS_ACTIVE, /* was active upon spu_acquire_saved() */ -}; - /* ctx->sched_flags */ enum { SPU_SCHED_NOTIFY_ACTIVE, + SPU_SCHED_WAS_ACTIVE, /* was active upon spu_acquire_saved() */ }; struct spu_context { Index: linux-rt-rebase.q/arch/powerpc/platforms/celleb/htab.c =================================================================== --- linux-rt-rebase.q.orig/arch/powerpc/platforms/celleb/htab.c +++ linux-rt-rebase.q/arch/powerpc/platforms/celleb/htab.c @@ -40,7 +40,7 @@ #define DBG_LOW(fmt...) do { } while(0) #endif -static DEFINE_SPINLOCK(beat_htab_lock); +static DEFINE_RAW_SPINLOCK(beat_htab_lock); static inline unsigned int beat_read_mask(unsigned hpte_group) { Index: linux-rt-rebase.q/arch/powerpc/platforms/celleb/interrupt.c =================================================================== --- linux-rt-rebase.q.orig/arch/powerpc/platforms/celleb/interrupt.c +++ linux-rt-rebase.q/arch/powerpc/platforms/celleb/interrupt.c @@ -29,8 +29,12 @@ #include "interrupt.h" #include "beat_wrapper.h" +#ifdef CONFIG_PREEMPT_HARDIRQS +extern int hardirq_preemption; +#endif /* CONFIG_PREEMPT_HARDIRQS */ + #define MAX_IRQS NR_IRQS -static DEFINE_SPINLOCK(beatic_irq_mask_lock); +static DEFINE_RAW_SPINLOCK(beatic_irq_mask_lock); static uint64_t beatic_irq_mask_enable[(MAX_IRQS+255)/64]; static uint64_t beatic_irq_mask_ack[(MAX_IRQS+255)/64]; @@ -71,12 +75,35 @@ static void beatic_mask_irq(unsigned int spin_unlock_irqrestore(&beatic_irq_mask_lock, flags); } +static void __beatic_eoi_irq(unsigned int irq_plug) +{ + s64 err; + + if ((err = beat_downcount_of_interrupt(irq_plug)) != 0) { + if ((err & 0xFFFFFFFF) != 0xFFFFFFF5) /* -11: wrong state */ + panic("Failed to downcount IRQ! Error = %16lx", err); + + printk(KERN_ERR "IRQ over-downcounted, plug %d\n", irq_plug); + } +} + static void beatic_unmask_irq(unsigned int irq_plug) { unsigned long flags; +#ifdef CONFIG_PREEMPT_HARDIRQS + if (hardirq_preemption) + __beatic_eoi_irq(irq_plug); +#endif /* CONFIG_PREEMPT_HARDIRQS */ + spin_lock_irqsave(&beatic_irq_mask_lock, flags); beatic_irq_mask_enable[irq_plug/64] |= 1UL << (63 - (irq_plug%64)); + +#ifdef CONFIG_PREEMPT_HARDIRQS + if (hardirq_preemption) + beatic_irq_mask_ack[irq_plug/64] |= 1UL << (63 - (irq_plug%64)); +#endif /* CONFIG_PREEMPT_HARDIRQS */ + beatic_update_irq_mask(irq_plug); spin_unlock_irqrestore(&beatic_irq_mask_lock, flags); } @@ -93,15 +120,15 @@ static void beatic_ack_irq(unsigned int static void beatic_end_irq(unsigned int irq_plug) { - s64 err; unsigned long flags; - if ((err = beat_downcount_of_interrupt(irq_plug)) != 0) { - if ((err & 0xFFFFFFFF) != 0xFFFFFFF5) /* -11: wrong state */ - panic("Failed to downcount IRQ! Error = %16lx", err); +#ifdef CONFIG_PREEMPT_HARDIRQS + if (hardirq_preemption) + return; +#endif /* CONFIG_PREEMPT_HARDIRQS */ + + __beatic_eoi_irq(irq_plug); - printk(KERN_ERR "IRQ over-downcounted, plug %d\n", irq_plug); - } spin_lock_irqsave(&beatic_irq_mask_lock, flags); beatic_irq_mask_ack[irq_plug/64] |= 1UL << (63 - (irq_plug%64)); beatic_update_irq_mask(irq_plug); Index: linux-rt-rebase.q/arch/powerpc/platforms/chrp/pci.c =================================================================== --- linux-rt-rebase.q.orig/arch/powerpc/platforms/chrp/pci.c +++ linux-rt-rebase.q/arch/powerpc/platforms/chrp/pci.c @@ -181,7 +181,7 @@ setup_python(struct pci_controller *hose } iounmap(reg); - setup_indirect_pci(hose, r.start + 0xf8000, r.start + 0xf8010); + setup_indirect_pci(hose, r.start + 0xf8000, r.start + 0xf8010, 0); } /* Marvell Discovery II based Pegasos 2 */ @@ -277,13 +277,14 @@ chrp_find_bridges(void) hose->cfg_data = p; gg2_pci_config_base = p; } else if (is_pegasos == 1) { - setup_indirect_pci(hose, 0xfec00cf8, 0xfee00cfc); + setup_indirect_pci(hose, 0xfec00cf8, 0xfee00cfc, 0); } else if (is_pegasos == 2) { setup_peg2(hose, dev); } else if (!strncmp(model, "IBM,CPC710", 10)) { setup_indirect_pci(hose, r.start + 0x000f8000, - r.start + 0x000f8010); + r.start + 0x000f8010, + 0); if (index == 0) { dma = of_get_property(dev, "system-dma-base", &len); Index: linux-rt-rebase.q/arch/powerpc/platforms/chrp/smp.c =================================================================== --- linux-rt-rebase.q.orig/arch/powerpc/platforms/chrp/smp.c +++ linux-rt-rebase.q/arch/powerpc/platforms/chrp/smp.c @@ -44,7 +44,7 @@ static void __devinit smp_chrp_setup_cpu mpic_setup_this_cpu(); } -static DEFINE_SPINLOCK(timebase_lock); +static DEFINE_RAW_SPINLOCK(timebase_lock); static unsigned int timebase_upper = 0, timebase_lower = 0; void __devinit smp_chrp_give_timebase(void) Index: linux-rt-rebase.q/arch/powerpc/platforms/chrp/time.c =================================================================== --- linux-rt-rebase.q.orig/arch/powerpc/platforms/chrp/time.c +++ linux-rt-rebase.q/arch/powerpc/platforms/chrp/time.c @@ -27,7 +27,7 @@ #include #include -extern spinlock_t rtc_lock; +extern raw_spinlock_t rtc_lock; static int nvram_as1 = NVRAM_AS1; static int nvram_as0 = NVRAM_AS0; Index: linux-rt-rebase.q/arch/powerpc/platforms/embedded6xx/linkstation.c =================================================================== --- linux-rt-rebase.q.orig/arch/powerpc/platforms/embedded6xx/linkstation.c +++ linux-rt-rebase.q/arch/powerpc/platforms/embedded6xx/linkstation.c @@ -73,7 +73,7 @@ static int __init linkstation_add_bridge return -ENOMEM; hose->first_busno = bus_range ? bus_range[0] : 0; hose->last_busno = bus_range ? bus_range[1] : 0xff; - setup_indirect_pci(hose, 0xfec00000, 0xfee00000); + setup_indirect_pci(hose, 0xfec00000, 0xfee00000, 0); /* Interpret the "ranges" property */ /* This also maps the I/O region and sets isa_io/mem_base */ Index: linux-rt-rebase.q/arch/powerpc/platforms/iseries/setup.c =================================================================== --- linux-rt-rebase.q.orig/arch/powerpc/platforms/iseries/setup.c +++ linux-rt-rebase.q/arch/powerpc/platforms/iseries/setup.c @@ -562,12 +562,14 @@ static void yield_shared_processor(void) static void iseries_shared_idle(void) { while (1) { - while (!need_resched() && !hvlpevent_is_pending()) { + while (!need_resched() && !need_resched_delayed() + && !hvlpevent_is_pending()) { local_irq_disable(); ppc64_runlatch_off(); /* Recheck with irqs off */ - if (!need_resched() && !hvlpevent_is_pending()) + if (!need_resched() && !need_resched_delayed() + && !hvlpevent_is_pending()) yield_shared_processor(); HMT_medium(); Index: linux-rt-rebase.q/arch/powerpc/platforms/powermac/feature.c =================================================================== --- linux-rt-rebase.q.orig/arch/powerpc/platforms/powermac/feature.c +++ linux-rt-rebase.q/arch/powerpc/platforms/powermac/feature.c @@ -59,7 +59,7 @@ extern struct device_node *k2_skiplist[2 * We use a single global lock to protect accesses. Each driver has * to take care of its own locking */ -DEFINE_SPINLOCK(feature_lock); +DEFINE_RAW_SPINLOCK(feature_lock); #define LOCK(flags) spin_lock_irqsave(&feature_lock, flags); #define UNLOCK(flags) spin_unlock_irqrestore(&feature_lock, flags); Index: linux-rt-rebase.q/arch/powerpc/platforms/powermac/nvram.c =================================================================== --- linux-rt-rebase.q.orig/arch/powerpc/platforms/powermac/nvram.c +++ linux-rt-rebase.q/arch/powerpc/platforms/powermac/nvram.c @@ -80,7 +80,7 @@ static int is_core_99; static int core99_bank = 0; static int nvram_partitions[3]; // XXX Turn that into a sem -static DEFINE_SPINLOCK(nv_lock); +static DEFINE_RAW_SPINLOCK(nv_lock); static int (*core99_write_bank)(int bank, u8* datas); static int (*core99_erase_bank)(int bank); Index: linux-rt-rebase.q/arch/powerpc/platforms/powermac/pic.c =================================================================== --- linux-rt-rebase.q.orig/arch/powerpc/platforms/powermac/pic.c +++ linux-rt-rebase.q/arch/powerpc/platforms/powermac/pic.c @@ -63,7 +63,7 @@ static int max_irqs; static int max_real_irqs; static u32 level_mask[4]; -static DEFINE_SPINLOCK(pmac_pic_lock); +static DEFINE_RAW_SPINLOCK(pmac_pic_lock); #define NR_MASK_WORDS ((NR_IRQS + 31) / 32) static unsigned long ppc_lost_interrupts[NR_MASK_WORDS]; Index: linux-rt-rebase.q/arch/powerpc/platforms/pseries/setup.c =================================================================== --- linux-rt-rebase.q.orig/arch/powerpc/platforms/pseries/setup.c +++ linux-rt-rebase.q/arch/powerpc/platforms/pseries/setup.c @@ -418,7 +418,8 @@ static void pseries_dedicated_idle_sleep set_thread_flag(TIF_POLLING_NRFLAG); while (get_tb() < start_snooze) { - if (need_resched() || cpu_is_offline(cpu)) + if (need_resched() || need_resched_delayed() || + cpu_is_offline(cpu)) goto out; ppc64_runlatch_off(); HMT_low(); @@ -429,7 +430,8 @@ static void pseries_dedicated_idle_sleep clear_thread_flag(TIF_POLLING_NRFLAG); smp_mb(); local_irq_disable(); - if (need_resched() || cpu_is_offline(cpu)) + if (need_resched() || need_resched_delayed() || + cpu_is_offline(cpu)) goto out; } Index: linux-rt-rebase.q/arch/powerpc/platforms/pseries/smp.c =================================================================== --- linux-rt-rebase.q.orig/arch/powerpc/platforms/pseries/smp.c +++ linux-rt-rebase.q/arch/powerpc/platforms/pseries/smp.c @@ -154,7 +154,7 @@ static void __devinit smp_xics_setup_cpu } #endif /* CONFIG_XICS */ -static DEFINE_SPINLOCK(timebase_lock); +static DEFINE_RAW_SPINLOCK(timebase_lock); static unsigned long timebase = 0; static void __devinit pSeries_give_timebase(void) Index: linux-rt-rebase.q/arch/powerpc/sysdev/Makefile =================================================================== --- linux-rt-rebase.q.orig/arch/powerpc/sysdev/Makefile +++ linux-rt-rebase.q/arch/powerpc/sysdev/Makefile @@ -12,6 +12,7 @@ obj-$(CONFIG_PPC_PMI) += pmi.o obj-$(CONFIG_U3_DART) += dart_iommu.o obj-$(CONFIG_MMIO_NVRAM) += mmio_nvram.o obj-$(CONFIG_FSL_SOC) += fsl_soc.o +obj-$(CONFIG_FSL_PCI) += fsl_pci.o obj-$(CONFIG_TSI108_BRIDGE) += tsi108_pci.o tsi108_dev.o obj-$(CONFIG_QUICC_ENGINE) += qe_lib/ mv64x60-$(CONFIG_PCI) += mv64x60_pci.o Index: linux-rt-rebase.q/arch/powerpc/sysdev/fsl_pci.c =================================================================== --- /dev/null +++ linux-rt-rebase.q/arch/powerpc/sysdev/fsl_pci.c @@ -0,0 +1,257 @@ +/* + * MPC85xx/86xx PCI/PCIE support routing. + * + * Copyright 2007 Freescale Semiconductor, Inc + * + * Initial author: Xianghua Xiao + * Recode: ZHANG WEI + * Rewrite the routing for Frescale PCI and PCI Express + * Roy Zang + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + */ +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include +#include + +/* atmu setup for fsl pci/pcie controller */ +void __init setup_pci_atmu(struct pci_controller *hose, struct resource *rsrc) +{ + struct ccsr_pci __iomem *pci; + int i; + + pr_debug("PCI memory map start 0x%x, size 0x%x\n", rsrc->start, + rsrc->end - rsrc->start + 1); + pci = ioremap(rsrc->start, rsrc->end - rsrc->start + 1); + + /* Disable all windows (except powar0 since its ignored) */ + for(i = 1; i < 5; i++) + out_be32(&pci->pow[i].powar, 0); + for(i = 0; i < 3; i++) + out_be32(&pci->piw[i].piwar, 0); + + /* Setup outbound MEM window */ + for(i = 0; i < 3; i++) + if (hose->mem_resources[i].flags & IORESOURCE_MEM){ + pr_debug("PCI MEM resource start 0x%08x, size 0x%08x.\n", + hose->mem_resources[i].start, + hose->mem_resources[i].end + - hose->mem_resources[i].start + 1); + out_be32(&pci->pow[i+1].potar, + (hose->mem_resources[i].start >> 12) + & 0x000fffff); + out_be32(&pci->pow[i+1].potear, 0); + out_be32(&pci->pow[i+1].powbar, + (hose->mem_resources[i].start >> 12) + & 0x000fffff); + /* Enable, Mem R/W */ + out_be32(&pci->pow[i+1].powar, 0x80044000 + | (__ilog2(hose->mem_resources[i].end + - hose->mem_resources[i].start + 1) - 1)); + } + + /* Setup outbound IO window */ + if (hose->io_resource.flags & IORESOURCE_IO){ + pr_debug("PCI IO resource start 0x%08x, size 0x%08x, phy base 0x%08x.\n", + hose->io_resource.start, + hose->io_resource.end - hose->io_resource.start + 1, + hose->io_base_phys); + out_be32(&pci->pow[i+1].potar, (hose->io_resource.start >> 12) + & 0x000fffff); + out_be32(&pci->pow[i+1].potear, 0); + out_be32(&pci->pow[i+1].powbar, (hose->io_base_phys >> 12) + & 0x000fffff); + /* Enable, IO R/W */ + out_be32(&pci->pow[i+1].powar, 0x80088000 + | (__ilog2(hose->io_resource.end + - hose->io_resource.start + 1) - 1)); + } + + /* Setup 2G inbound Memory Window @ 1 */ + out_be32(&pci->piw[2].pitar, 0x00000000); + out_be32(&pci->piw[2].piwbar,0x00000000); + out_be32(&pci->piw[2].piwar, PIWAR_2G); +} + +void __init setup_pci_cmd(struct pci_controller *hose) +{ + u16 cmd; + int cap_x; + + early_read_config_word(hose, 0, 0, PCI_COMMAND, &cmd); + cmd |= PCI_COMMAND_SERR | PCI_COMMAND_MASTER | PCI_COMMAND_MEMORY + | PCI_COMMAND_IO; + early_write_config_word(hose, 0, 0, PCI_COMMAND, cmd); + + cap_x = early_find_capability(hose, 0, 0, PCI_CAP_ID_PCIX); + if (cap_x) { + int pci_x_cmd = cap_x + PCI_X_CMD; + cmd = PCI_X_CMD_MAX_SPLIT | PCI_X_CMD_MAX_READ + | PCI_X_CMD_ERO | PCI_X_CMD_DPERR_E; + early_write_config_word(hose, 0, 0, pci_x_cmd, cmd); + } else { + early_write_config_byte(hose, 0, 0, PCI_LATENCY_TIMER, 0x80); + } +} + +static void __devinit quirk_fsl_pcie_transparent(struct pci_dev *dev) +{ + struct resource *res; + int i, res_idx = PCI_BRIDGE_RESOURCES; + struct pci_controller *hose; + + /* if we aren't a PCIe don't bother */ + if (!pci_find_capability(dev, PCI_CAP_ID_EXP)) + return ; + + /* + * Make the bridge be transparent. + */ + dev->transparent = 1; + + hose = pci_bus_to_host(dev->bus); + if (!hose) { + printk(KERN_ERR "Can't find hose for bus %d\n", + dev->bus->number); + return; + } + + /* Clear out any of the virtual P2P bridge registers */ + pci_write_config_word(dev, PCI_IO_BASE_UPPER16, 0); + pci_write_config_word(dev, PCI_IO_LIMIT_UPPER16, 0); + pci_write_config_byte(dev, PCI_IO_BASE, 0x10); + pci_write_config_byte(dev, PCI_IO_LIMIT, 0); + pci_write_config_word(dev, PCI_MEMORY_BASE, 0x10); + pci_write_config_word(dev, PCI_MEMORY_LIMIT, 0); + pci_write_config_word(dev, PCI_PREF_BASE_UPPER32, 0x0); + pci_write_config_word(dev, PCI_PREF_LIMIT_UPPER32, 0x0); + pci_write_config_word(dev, PCI_PREF_MEMORY_BASE, 0x10); + pci_write_config_word(dev, PCI_PREF_MEMORY_LIMIT, 0); + + if (hose->io_resource.flags) { + res = &dev->resource[res_idx++]; + res->start = hose->io_resource.start; + res->end = hose->io_resource.end; + res->flags = hose->io_resource.flags; + update_bridge_resource(dev, res); + } + + for (i = 0; i < 3; i++) { + res = &dev->resource[res_idx + i]; + res->start = hose->mem_resources[i].start; + res->end = hose->mem_resources[i].end; + res->flags = hose->mem_resources[i].flags; + update_bridge_resource(dev, res); + } +} + +int __init fsl_pcie_check_link(struct pci_controller *hose) +{ + u16 val; + early_read_config_word(hose, 0, 0, PCIE_LTSSM, &val); + if (val < PCIE_LTSSM_L0) + return 1; + return 0; +} + +void fsl_pcibios_fixup_bus(struct pci_bus *bus) +{ + struct pci_controller *hose = (struct pci_controller *) bus->sysdata; + int i; + + /* deal with bogus pci_bus when we don't have anything connected on PCIe */ + if (hose->indirect_type & PPC_INDIRECT_TYPE_NO_PCIE_LINK) { + if (bus->parent) { + for (i = 0; i < 4; ++i) + bus->resource[i] = bus->parent->resource[i]; + } + } +} + +int __init fsl_add_bridge(struct device_node *dev, int is_primary) +{ + int len; + struct pci_controller *hose; + struct resource rsrc; + const int *bus_range; + + pr_debug("Adding PCI host bridge %s\n", dev->full_name); + + /* Fetch host bridge registers address */ + if (of_address_to_resource(dev, 0, &rsrc)) { + printk(KERN_WARNING "Can't get pci register base!"); + return -ENOMEM; + } + + /* Get bus range if any */ + bus_range = of_get_property(dev, "bus-range", &len); + if (bus_range == NULL || len < 2 * sizeof(int)) + printk(KERN_WARNING "Can't get bus-range for %s, assume" + " bus 0\n", dev->full_name); + + pci_assign_all_buses = 1; + hose = pcibios_alloc_controller(dev); + if (!hose) + return -ENOMEM; + + hose->first_busno = bus_range ? bus_range[0] : 0x0; + hose->last_busno = bus_range ? bus_range[1] : 0xff; + + setup_indirect_pci(hose, rsrc.start, rsrc.start + 0x4, + PPC_INDIRECT_TYPE_BIG_ENDIAN); + setup_pci_cmd(hose); + + /* check PCI express link status */ + if (early_find_capability(hose, 0, 0, PCI_CAP_ID_EXP)) { + hose->indirect_type = PPC_INDIRECT_TYPE_EXT_REG | + PPC_INDIRECT_TYPE_SURPRESS_PRIMARY_BUS; + if (fsl_pcie_check_link(hose)) + hose->indirect_type |= PPC_INDIRECT_TYPE_NO_PCIE_LINK; + } + + printk(KERN_INFO "Found FSL PCI host bridge at 0x%016llx." + "Firmware bus number: %d->%d\n", + (unsigned long long)rsrc.start, hose->first_busno, + hose->last_busno); + + pr_debug(" ->Hose at 0x%p, cfg_addr=0x%p,cfg_data=0x%p\n", + hose, hose->cfg_addr, hose->cfg_data); + + /* Interpret the "ranges" property */ + /* This also maps the I/O region and sets isa_io/mem_base */ + pci_process_bridge_OF_ranges(hose, dev, is_primary); + + /* Setup PEX window registers */ + setup_pci_atmu(hose, &rsrc); + + return 0; +} + +DECLARE_PCI_FIXUP_EARLY(0x1957, PCI_DEVICE_ID_MPC8548E, quirk_fsl_pcie_transparent); +DECLARE_PCI_FIXUP_EARLY(0x1957, PCI_DEVICE_ID_MPC8548, quirk_fsl_pcie_transparent); +DECLARE_PCI_FIXUP_EARLY(0x1957, PCI_DEVICE_ID_MPC8543E, quirk_fsl_pcie_transparent); +DECLARE_PCI_FIXUP_EARLY(0x1957, PCI_DEVICE_ID_MPC8543, quirk_fsl_pcie_transparent); +DECLARE_PCI_FIXUP_EARLY(0x1957, PCI_DEVICE_ID_MPC8547E, quirk_fsl_pcie_transparent); +DECLARE_PCI_FIXUP_EARLY(0x1957, PCI_DEVICE_ID_MPC8545E, quirk_fsl_pcie_transparent); +DECLARE_PCI_FIXUP_EARLY(0x1957, PCI_DEVICE_ID_MPC8545, quirk_fsl_pcie_transparent); +DECLARE_PCI_FIXUP_EARLY(0x1957, PCI_DEVICE_ID_MPC8568E, quirk_fsl_pcie_transparent); +DECLARE_PCI_FIXUP_EARLY(0x1957, PCI_DEVICE_ID_MPC8568, quirk_fsl_pcie_transparent); +DECLARE_PCI_FIXUP_EARLY(0x1957, PCI_DEVICE_ID_MPC8567E, quirk_fsl_pcie_transparent); +DECLARE_PCI_FIXUP_EARLY(0x1957, PCI_DEVICE_ID_MPC8567, quirk_fsl_pcie_transparent); +DECLARE_PCI_FIXUP_EARLY(0x1957, PCI_DEVICE_ID_MPC8544E, quirk_fsl_pcie_transparent); +DECLARE_PCI_FIXUP_EARLY(0x1957, PCI_DEVICE_ID_MPC8544, quirk_fsl_pcie_transparent); +DECLARE_PCI_FIXUP_EARLY(0x1957, PCI_DEVICE_ID_MPC8641, quirk_fsl_pcie_transparent); +DECLARE_PCI_FIXUP_EARLY(0x1957, PCI_DEVICE_ID_MPC8641D, quirk_fsl_pcie_transparent); Index: linux-rt-rebase.q/arch/powerpc/sysdev/fsl_pci.h =================================================================== --- /dev/null +++ linux-rt-rebase.q/arch/powerpc/sysdev/fsl_pci.h @@ -0,0 +1,88 @@ +/* + * MPC85xx/86xx PCI Express structure define + * + * Copyright 2007 Freescale Semiconductor, Inc + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + * + */ + +#ifdef __KERNEL__ +#ifndef __POWERPC_FSL_PCI_H +#define __POWERPC_FSL_PCI_H + +#define PCIE_LTSSM 0x0404 /* PCIE Link Training and Status */ +#define PCIE_LTSSM_L0 0x16 /* L0 state */ +#define PIWAR_2G 0xa0f5501e /* Enable, Prefetch, Local Mem, Snoop R/W, 2G */ + +/* PCI/PCI Express outbound window reg */ +struct pci_outbound_window_regs { + __be32 potar; /* 0x.0 - Outbound translation address register */ + __be32 potear; /* 0x.4 - Outbound translation extended address register */ + __be32 powbar; /* 0x.8 - Outbound window base address register */ + u8 res1[4]; + __be32 powar; /* 0x.10 - Outbound window attributes register */ + u8 res2[12]; +}; + +/* PCI/PCI Express inbound window reg */ +struct pci_inbound_window_regs { + __be32 pitar; /* 0x.0 - Inbound translation address register */ + u8 res1[4]; + __be32 piwbar; /* 0x.8 - Inbound window base address register */ + __be32 piwbear; /* 0x.c - Inbound window base extended address register */ + __be32 piwar; /* 0x.10 - Inbound window attributes register */ + u8 res2[12]; +}; + +/* PCI/PCI Express IO block registers for 85xx/86xx */ +struct ccsr_pci { + __be32 config_addr; /* 0x.000 - PCI/PCIE Configuration Address Register */ + __be32 config_data; /* 0x.004 - PCI/PCIE Configuration Data Register */ + __be32 int_ack; /* 0x.008 - PCI Interrupt Acknowledge Register */ + __be32 pex_otb_cpl_tor; /* 0x.00c - PCIE Outbound completion timeout register */ + __be32 pex_conf_tor; /* 0x.010 - PCIE configuration timeout register */ + u8 res2[12]; + __be32 pex_pme_mes_dr; /* 0x.020 - PCIE PME and message detect register */ + __be32 pex_pme_mes_disr; /* 0x.024 - PCIE PME and message disable register */ + __be32 pex_pme_mes_ier; /* 0x.028 - PCIE PME and message interrupt enable register */ + __be32 pex_pmcr; /* 0x.02c - PCIE power management command register */ + u8 res3[3024]; + +/* PCI/PCI Express outbound window 0-4 + * Window 0 is the default window and is the only window enabled upon reset. + * The default outbound register set is used when a transaction misses + * in all of the other outbound windows. + */ + struct pci_outbound_window_regs pow[5]; + + u8 res14[256]; + +/* PCI/PCI Express inbound window 3-1 + * inbound window 1 supports only a 32-bit base address and does not + * define an inbound window base extended address register. + */ + struct pci_inbound_window_regs piw[3]; + + __be32 pex_err_dr; /* 0x.e00 - PCI/PCIE error detect register */ + u8 res21[4]; + __be32 pex_err_en; /* 0x.e08 - PCI/PCIE error interrupt enable register */ + u8 res22[4]; + __be32 pex_err_disr; /* 0x.e10 - PCI/PCIE error disable register */ + u8 res23[12]; + __be32 pex_err_cap_stat; /* 0x.e20 - PCI/PCIE error capture status register */ + u8 res24[4]; + __be32 pex_err_cap_r0; /* 0x.e28 - PCIE error capture register 0 */ + __be32 pex_err_cap_r1; /* 0x.e2c - PCIE error capture register 0 */ + __be32 pex_err_cap_r2; /* 0x.e30 - PCIE error capture register 0 */ + __be32 pex_err_cap_r3; /* 0x.e34 - PCIE error capture register 0 */ +}; + +extern int fsl_add_bridge(struct device_node *dev, int is_primary); +extern void fsl_pcibios_fixup_bus(struct pci_bus *bus); + +#endif /* __POWERPC_FSL_PCI_H */ +#endif /* __KERNEL__ */ Index: linux-rt-rebase.q/arch/powerpc/sysdev/fsl_pcie.h =================================================================== --- linux-rt-rebase.q.orig/arch/powerpc/sysdev/fsl_pcie.h +++ /dev/null @@ -1,94 +0,0 @@ -/* - * MPC85xx/86xx PCI Express structure define - * - * Copyright 2007 Freescale Semiconductor, Inc - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License as published by the - * Free Software Foundation; either version 2 of the License, or (at your - * option) any later version. - * - */ - -#ifdef __KERNEL__ -#ifndef __POWERPC_FSL_PCIE_H -#define __POWERPC_FSL_PCIE_H - -/* PCIE Express IO block registers in 85xx/86xx */ - -struct ccsr_pex { - __be32 __iomem pex_config_addr; /* 0x.000 - PCI Express Configuration Address Register */ - __be32 __iomem pex_config_data; /* 0x.004 - PCI Express Configuration Data Register */ - u8 __iomem res1[4]; - __be32 __iomem pex_otb_cpl_tor; /* 0x.00c - PCI Express Outbound completion timeout register */ - __be32 __iomem pex_conf_tor; /* 0x.010 - PCI Express configuration timeout register */ - u8 __iomem res2[12]; - __be32 __iomem pex_pme_mes_dr; /* 0x.020 - PCI Express PME and message detect register */ - __be32 __iomem pex_pme_mes_disr; /* 0x.024 - PCI Express PME and message disable register */ - __be32 __iomem pex_pme_mes_ier; /* 0x.028 - PCI Express PME and message interrupt enable register */ - __be32 __iomem pex_pmcr; /* 0x.02c - PCI Express power management command register */ - u8 __iomem res3[3024]; - __be32 __iomem pexotar0; /* 0x.c00 - PCI Express outbound translation address register 0 */ - __be32 __iomem pexotear0; /* 0x.c04 - PCI Express outbound translation extended address register 0*/ - u8 __iomem res4[8]; - __be32 __iomem pexowar0; /* 0x.c10 - PCI Express outbound window attributes register 0*/ - u8 __iomem res5[12]; - __be32 __iomem pexotar1; /* 0x.c20 - PCI Express outbound translation address register 1 */ - __be32 __iomem pexotear1; /* 0x.c24 - PCI Express outbound translation extended address register 1*/ - __be32 __iomem pexowbar1; /* 0x.c28 - PCI Express outbound window base address register 1*/ - u8 __iomem res6[4]; - __be32 __iomem pexowar1; /* 0x.c30 - PCI Express outbound window attributes register 1*/ - u8 __iomem res7[12]; - __be32 __iomem pexotar2; /* 0x.c40 - PCI Express outbound translation address register 2 */ - __be32 __iomem pexotear2; /* 0x.c44 - PCI Express outbound translation extended address register 2*/ - __be32 __iomem pexowbar2; /* 0x.c48 - PCI Express outbound window base address register 2*/ - u8 __iomem res8[4]; - __be32 __iomem pexowar2; /* 0x.c50 - PCI Express outbound window attributes register 2*/ - u8 __iomem res9[12]; - __be32 __iomem pexotar3; /* 0x.c60 - PCI Express outbound translation address register 3 */ - __be32 __iomem pexotear3; /* 0x.c64 - PCI Express outbound translation extended address register 3*/ - __be32 __iomem pexowbar3; /* 0x.c68 - PCI Express outbound window base address register 3*/ - u8 __iomem res10[4]; - __be32 __iomem pexowar3; /* 0x.c70 - PCI Express outbound window attributes register 3*/ - u8 __iomem res11[12]; - __be32 __iomem pexotar4; /* 0x.c80 - PCI Express outbound translation address register 4 */ - __be32 __iomem pexotear4; /* 0x.c84 - PCI Express outbound translation extended address register 4*/ - __be32 __iomem pexowbar4; /* 0x.c88 - PCI Express outbound window base address register 4*/ - u8 __iomem res12[4]; - __be32 __iomem pexowar4; /* 0x.c90 - PCI Express outbound window attributes register 4*/ - u8 __iomem res13[12]; - u8 __iomem res14[256]; - __be32 __iomem pexitar3; /* 0x.da0 - PCI Express inbound translation address register 3 */ - u8 __iomem res15[4]; - __be32 __iomem pexiwbar3; /* 0x.da8 - PCI Express inbound window base address register 3 */ - __be32 __iomem pexiwbear3; /* 0x.dac - PCI Express inbound window base extended address register 3 */ - __be32 __iomem pexiwar3; /* 0x.db0 - PCI Express inbound window attributes register 3 */ - u8 __iomem res16[12]; - __be32 __iomem pexitar2; /* 0x.dc0 - PCI Express inbound translation address register 2 */ - u8 __iomem res17[4]; - __be32 __iomem pexiwbar2; /* 0x.dc8 - PCI Express inbound window base address register 2 */ - __be32 __iomem pexiwbear2; /* 0x.dcc - PCI Express inbound window base extended address register 2 */ - __be32 __iomem pexiwar2; /* 0x.dd0 - PCI Express inbound window attributes register 2 */ - u8 __iomem res18[12]; - __be32 __iomem pexitar1; /* 0x.de0 - PCI Express inbound translation address register 2 */ - u8 __iomem res19[4]; - __be32 __iomem pexiwbar1; /* 0x.de8 - PCI Express inbound window base address register 2 */ - __be32 __iomem pexiwbear1; /* 0x.dec - PCI Express inbound window base extended address register 2 */ - __be32 __iomem pexiwar1; /* 0x.df0 - PCI Express inbound window attributes register 2 */ - u8 __iomem res20[12]; - __be32 __iomem pex_err_dr; /* 0x.e00 - PCI Express error detect register */ - u8 __iomem res21[4]; - __be32 __iomem pex_err_en; /* 0x.e08 - PCI Express error interrupt enable register */ - u8 __iomem res22[4]; - __be32 __iomem pex_err_disr; /* 0x.e10 - PCI Express error disable register */ - u8 __iomem res23[12]; - __be32 __iomem pex_err_cap_stat; /* 0x.e20 - PCI Express error capture status register */ - u8 __iomem res24[4]; - __be32 __iomem pex_err_cap_r0; /* 0x.e28 - PCI Express error capture register 0 */ - __be32 __iomem pex_err_cap_r1; /* 0x.e2c - PCI Express error capture register 0 */ - __be32 __iomem pex_err_cap_r2; /* 0x.e30 - PCI Express error capture register 0 */ - __be32 __iomem pex_err_cap_r3; /* 0x.e34 - PCI Express error capture register 0 */ -}; - -#endif /* __POWERPC_FSL_PCIE_H */ -#endif /* __KERNEL__ */ Index: linux-rt-rebase.q/arch/powerpc/sysdev/grackle.c =================================================================== --- linux-rt-rebase.q.orig/arch/powerpc/sysdev/grackle.c +++ linux-rt-rebase.q/arch/powerpc/sysdev/grackle.c @@ -55,7 +55,7 @@ static inline void grackle_set_loop_snoo void __init setup_grackle(struct pci_controller *hose) { - setup_indirect_pci(hose, 0xfec00000, 0xfee00000); + setup_indirect_pci(hose, 0xfec00000, 0xfee00000, 0); if (machine_is_compatible("PowerMac1,1")) pci_assign_all_buses = 1; if (machine_is_compatible("AAPL,PowerBook1998")) Index: linux-rt-rebase.q/arch/powerpc/sysdev/i8259.c =================================================================== --- linux-rt-rebase.q.orig/arch/powerpc/sysdev/i8259.c +++ linux-rt-rebase.q/arch/powerpc/sysdev/i8259.c @@ -23,7 +23,7 @@ static unsigned char cached_8259[2] = { #define cached_A1 (cached_8259[0]) #define cached_21 (cached_8259[1]) -static DEFINE_SPINLOCK(i8259_lock); +static DEFINE_RAW_SPINLOCK(i8259_lock); static struct device_node *i8259_node; static struct irq_host *i8259_host; Index: linux-rt-rebase.q/arch/powerpc/sysdev/indirect_pci.c =================================================================== --- linux-rt-rebase.q.orig/arch/powerpc/sysdev/indirect_pci.c +++ linux-rt-rebase.q/arch/powerpc/sysdev/indirect_pci.c @@ -20,12 +20,6 @@ #include #include -#ifdef CONFIG_PPC_INDIRECT_PCI_BE -#define PCI_CFG_OUT out_be32 -#else -#define PCI_CFG_OUT out_le32 -#endif - static int indirect_read_config(struct pci_bus *bus, unsigned int devfn, int offset, int len, u32 *val) @@ -35,10 +29,17 @@ indirect_read_config(struct pci_bus *bus u8 cfg_type = 0; u32 bus_no, reg; + if (hose->indirect_type & PPC_INDIRECT_TYPE_NO_PCIE_LINK) { + if (bus->number != hose->first_busno) + return PCIBIOS_DEVICE_NOT_FOUND; + if (devfn != 0) + return PCIBIOS_DEVICE_NOT_FOUND; + } + if (ppc_md.pci_exclude_device) if (ppc_md.pci_exclude_device(hose, bus->number, devfn)) return PCIBIOS_DEVICE_NOT_FOUND; - + if (hose->indirect_type & PPC_INDIRECT_TYPE_SET_CFG_TYPE) if (bus->number != hose->first_busno) cfg_type = 1; @@ -51,9 +52,12 @@ indirect_read_config(struct pci_bus *bus else reg = offset & 0xfc; - PCI_CFG_OUT(hose->cfg_addr, - (0x80000000 | (bus_no << 16) - | (devfn << 8) | reg | cfg_type)); + if (hose->indirect_type & PPC_INDIRECT_TYPE_BIG_ENDIAN) + out_be32(hose->cfg_addr, (0x80000000 | (bus_no << 16) | + (devfn << 8) | reg | cfg_type)); + else + out_le32(hose->cfg_addr, (0x80000000 | (bus_no << 16) | + (devfn << 8) | reg | cfg_type)); /* * Note: the caller has already checked that offset is @@ -83,6 +87,13 @@ indirect_write_config(struct pci_bus *bu u8 cfg_type = 0; u32 bus_no, reg; + if (hose->indirect_type & PPC_INDIRECT_TYPE_NO_PCIE_LINK) { + if (bus->number != hose->first_busno) + return PCIBIOS_DEVICE_NOT_FOUND; + if (devfn != 0) + return PCIBIOS_DEVICE_NOT_FOUND; + } + if (ppc_md.pci_exclude_device) if (ppc_md.pci_exclude_device(hose, bus->number, devfn)) return PCIBIOS_DEVICE_NOT_FOUND; @@ -99,9 +110,12 @@ indirect_write_config(struct pci_bus *bu else reg = offset & 0xfc; - PCI_CFG_OUT(hose->cfg_addr, - (0x80000000 | (bus_no << 16) - | (devfn << 8) | reg | cfg_type)); + if (hose->indirect_type & PPC_INDIRECT_TYPE_BIG_ENDIAN) + out_be32(hose->cfg_addr, (0x80000000 | (bus_no << 16) | + (devfn << 8) | reg | cfg_type)); + else + out_le32(hose->cfg_addr, (0x80000000 | (bus_no << 16) | + (devfn << 8) | reg | cfg_type)); /* surpress setting of PCI_PRIMARY_BUS */ if (hose->indirect_type & PPC_INDIRECT_TYPE_SURPRESS_PRIMARY_BUS) @@ -135,24 +149,15 @@ static struct pci_ops indirect_pci_ops = }; void __init -setup_indirect_pci_nomap(struct pci_controller* hose, void __iomem * cfg_addr, - void __iomem * cfg_data) -{ - hose->cfg_addr = cfg_addr; - hose->cfg_data = cfg_data; - hose->ops = &indirect_pci_ops; -} - -void __init -setup_indirect_pci(struct pci_controller* hose, u32 cfg_addr, u32 cfg_data) +setup_indirect_pci(struct pci_controller* hose, u32 cfg_addr, u32 cfg_data, u32 flags) { unsigned long base = cfg_addr & PAGE_MASK; - void __iomem *mbase, *addr, *data; + void __iomem *mbase; mbase = ioremap(base, PAGE_SIZE); - addr = mbase + (cfg_addr & ~PAGE_MASK); + hose->cfg_addr = mbase + (cfg_addr & ~PAGE_MASK); if ((cfg_data & PAGE_MASK) != base) mbase = ioremap(cfg_data & PAGE_MASK, PAGE_SIZE); - data = mbase + (cfg_data & ~PAGE_MASK); - setup_indirect_pci_nomap(hose, addr, data); + hose->cfg_data = mbase + (cfg_data & ~PAGE_MASK); + hose->ops = &indirect_pci_ops; } Index: linux-rt-rebase.q/arch/powerpc/sysdev/ipic.c =================================================================== --- linux-rt-rebase.q.orig/arch/powerpc/sysdev/ipic.c +++ linux-rt-rebase.q/arch/powerpc/sysdev/ipic.c @@ -30,7 +30,7 @@ #include "ipic.h" static struct ipic * primary_ipic; -static DEFINE_SPINLOCK(ipic_lock); +static DEFINE_RAW_SPINLOCK(ipic_lock); static struct ipic_info ipic_info[] = { [9] = { Index: linux-rt-rebase.q/arch/powerpc/sysdev/mpic.c =================================================================== --- linux-rt-rebase.q.orig/arch/powerpc/sysdev/mpic.c +++ linux-rt-rebase.q/arch/powerpc/sysdev/mpic.c @@ -46,7 +46,7 @@ static struct mpic *mpics; static struct mpic *mpic_primary; -static DEFINE_SPINLOCK(mpic_lock); +static DEFINE_RAW_SPINLOCK(mpic_lock); #ifdef CONFIG_PPC32 /* XXX for now */ #ifdef CONFIG_IRQ_ALL_CPUS Index: linux-rt-rebase.q/arch/powerpc/sysdev/mv64x60_pci.c =================================================================== --- linux-rt-rebase.q.orig/arch/powerpc/sysdev/mv64x60_pci.c +++ linux-rt-rebase.q/arch/powerpc/sysdev/mv64x60_pci.c @@ -144,7 +144,7 @@ static int __init mv64x60_add_bridge(str hose->first_busno = bus_range ? bus_range[0] : 0; hose->last_busno = bus_range ? bus_range[1] : 0xff; - setup_indirect_pci(hose, rsrc.start, rsrc.start + 4); + setup_indirect_pci(hose, rsrc.start, rsrc.start + 4, 0); hose->self_busno = hose->first_busno; printk(KERN_INFO "Found MV64x60 PCI host bridge at 0x%016llx. " Index: linux-rt-rebase.q/arch/powerpc/xmon/xmon.c =================================================================== --- linux-rt-rebase.q.orig/arch/powerpc/xmon/xmon.c +++ linux-rt-rebase.q/arch/powerpc/xmon/xmon.c @@ -340,6 +340,7 @@ static int xmon_core(struct pt_regs *reg unsigned long timeout; #endif + preempt_disable(); local_irq_save(flags); bp = in_breakpoint_table(regs->nip, &offset); @@ -516,6 +517,7 @@ static int xmon_core(struct pt_regs *reg insert_cpu_bpts(); local_irq_restore(flags); + preempt_enable(); return cmd != 'X' && cmd != EOF; } @@ -2129,7 +2131,7 @@ print_address(unsigned long addr) static unsigned long mdest; /* destination address */ static unsigned long msrc; /* source address */ static unsigned long mval; /* byte value to set memory to */ -static unsigned long mcount; /* # bytes to affect */ +static unsigned long xmon_mcount; /* # bytes to affect */ static unsigned long mdiffs; /* max # differences to print */ void @@ -2141,19 +2143,20 @@ memops(int cmd) scanhex((void *)(cmd == 's'? &mval: &msrc)); if( termch != '\n' ) termch = 0; - scanhex((void *)&mcount); + scanhex((void *)&xmon_mcount); switch( cmd ){ case 'm': - memmove((void *)mdest, (void *)msrc, mcount); + memmove((void *)mdest, (void *)msrc, xmon_mcount); break; case 's': - memset((void *)mdest, mval, mcount); + memset((void *)mdest, mval, xmon_mcount); break; case 'd': if( termch != '\n' ) termch = 0; scanhex((void *)&mdiffs); - memdiffs((unsigned char *)mdest, (unsigned char *)msrc, mcount, mdiffs); + memdiffs((unsigned char *)mdest, (unsigned char *)msrc, + xmon_mcount, mdiffs); break; } } Index: linux-rt-rebase.q/arch/ppc/8260_io/enet.c =================================================================== --- linux-rt-rebase.q.orig/arch/ppc/8260_io/enet.c +++ linux-rt-rebase.q/arch/ppc/8260_io/enet.c @@ -115,7 +115,7 @@ struct scc_enet_private { scc_t *sccp; struct net_device_stats stats; uint tx_full; - spinlock_t lock; + raw_spinlock_t lock; }; static int scc_enet_open(struct net_device *dev); Index: linux-rt-rebase.q/arch/ppc/8260_io/fcc_enet.c =================================================================== --- linux-rt-rebase.q.orig/arch/ppc/8260_io/fcc_enet.c +++ linux-rt-rebase.q/arch/ppc/8260_io/fcc_enet.c @@ -375,7 +375,7 @@ struct fcc_enet_private { volatile fcc_enet_t *ep; struct net_device_stats stats; uint tx_free; - spinlock_t lock; + raw_spinlock_t lock; #ifdef CONFIG_USE_MDIO uint phy_id; Index: linux-rt-rebase.q/arch/ppc/8xx_io/commproc.c =================================================================== --- linux-rt-rebase.q.orig/arch/ppc/8xx_io/commproc.c +++ linux-rt-rebase.q/arch/ppc/8xx_io/commproc.c @@ -370,7 +370,7 @@ cpm_setbrg(uint brg, uint rate) /* * dpalloc / dpfree bits. */ -static spinlock_t cpm_dpmem_lock; +static raw_spinlock_t cpm_dpmem_lock; /* * 16 blocks should be enough to satisfy all requests * until the memory subsystem goes up... Index: linux-rt-rebase.q/arch/ppc/8xx_io/enet.c =================================================================== --- linux-rt-rebase.q.orig/arch/ppc/8xx_io/enet.c +++ linux-rt-rebase.q/arch/ppc/8xx_io/enet.c @@ -142,7 +142,7 @@ struct scc_enet_private { unsigned char *rx_vaddr[RX_RING_SIZE]; struct net_device_stats stats; uint tx_full; - spinlock_t lock; + raw_spinlock_t lock; }; static int scc_enet_open(struct net_device *dev); Index: linux-rt-rebase.q/arch/ppc/8xx_io/fec.c =================================================================== --- linux-rt-rebase.q.orig/arch/ppc/8xx_io/fec.c +++ linux-rt-rebase.q/arch/ppc/8xx_io/fec.c @@ -164,7 +164,7 @@ struct fec_enet_private { struct net_device_stats stats; uint tx_full; - spinlock_t lock; + raw_spinlock_t lock; #ifdef CONFIG_USE_MDIO uint phy_id; Index: linux-rt-rebase.q/arch/ppc/Kconfig =================================================================== --- linux-rt-rebase.q.orig/arch/ppc/Kconfig +++ linux-rt-rebase.q/arch/ppc/Kconfig @@ -12,13 +12,6 @@ config GENERIC_HARDIRQS bool default y -config RWSEM_GENERIC_SPINLOCK - bool - -config RWSEM_XCHGADD_ALGORITHM - bool - default y - config ARCH_HAS_ILOG2_U32 bool default y @@ -988,6 +981,18 @@ config ARCH_POPULATES_NODE_MAP source kernel/Kconfig.hz source kernel/Kconfig.preempt + +config RWSEM_GENERIC_SPINLOCK + bool + default y + +config ASM_SEMAPHORES + bool + default y + +config RWSEM_XCHGADD_ALGORITHM + bool + source "mm/Kconfig" source "fs/Kconfig.binfmt" Index: linux-rt-rebase.q/arch/ppc/boot/Makefile =================================================================== --- linux-rt-rebase.q.orig/arch/ppc/boot/Makefile +++ linux-rt-rebase.q/arch/ppc/boot/Makefile @@ -14,6 +14,15 @@ # CFLAGS += -fno-builtin -D__BOOTER__ -Iarch/$(ARCH)/boot/include + +ifdef CONFIG_MCOUNT +# do not trace the boot loader +nullstring := +space := $(nullstring) # end of the line +pg_flag = $(nullstring) -pg # end of the line +CFLAGS := $(subst ${pg_flag},${space},${CFLAGS}) +endif + HOSTCFLAGS += -Iarch/$(ARCH)/boot/include BOOT_TARGETS = zImage zImage.initrd znetboot znetboot.initrd Index: linux-rt-rebase.q/arch/ppc/kernel/entry.S =================================================================== --- linux-rt-rebase.q.orig/arch/ppc/kernel/entry.S +++ linux-rt-rebase.q/arch/ppc/kernel/entry.S @@ -863,7 +863,7 @@ global_dbcr0: #endif /* !(CONFIG_4xx || CONFIG_BOOKE) */ do_work: /* r10 contains MSR_KERNEL here */ - andi. r0,r9,_TIF_NEED_RESCHED + andi. r0,r9,(_TIF_NEED_RESCHED|_TIF_NEED_RESCHED_DELAYED) beq do_user_signal do_resched: /* r10 contains MSR_KERNEL here */ @@ -877,7 +877,7 @@ recheck: MTMSRD(r10) /* disable interrupts */ rlwinm r9,r1,0,0,18 lwz r9,TI_FLAGS(r9) - andi. r0,r9,_TIF_NEED_RESCHED + andi. r0,r9,(_TIF_NEED_RESCHED|_TIF_NEED_RESCHED_DELAYED) bne- do_resched andi. r0,r9,_TIF_SIGPENDING beq restore_user Index: linux-rt-rebase.q/arch/ppc/kernel/semaphore.c =================================================================== --- linux-rt-rebase.q.orig/arch/ppc/kernel/semaphore.c +++ linux-rt-rebase.q/arch/ppc/kernel/semaphore.c @@ -29,7 +29,7 @@ * sem->count = tmp; * return old_count; */ -static inline int __sem_update_count(struct semaphore *sem, int incr) +static inline int __sem_update_count(struct compat_semaphore *sem, int incr) { int old_count, tmp; @@ -48,7 +48,7 @@ static inline int __sem_update_count(str return old_count; } -void __up(struct semaphore *sem) +void __compat_up(struct compat_semaphore *sem) { /* * Note that we incremented count in up() before we came here, @@ -70,7 +70,7 @@ void __up(struct semaphore *sem) * Thus it is only when we decrement count from some value > 0 * that we have actually got the semaphore. */ -void __sched __down(struct semaphore *sem) +void __sched __compat_down(struct compat_semaphore *sem) { struct task_struct *tsk = current; DECLARE_WAITQUEUE(wait, tsk); @@ -100,7 +100,7 @@ void __sched __down(struct semaphore *se wake_up(&sem->wait); } -int __sched __down_interruptible(struct semaphore * sem) +int __sched __compat_down_interruptible(struct compat_semaphore * sem) { int retval = 0; struct task_struct *tsk = current; @@ -129,3 +129,8 @@ int __sched __down_interruptible(struct wake_up(&sem->wait); return retval; } + +int compat_sem_is_locked(struct compat_semaphore *sem) +{ + return (int) atomic_read(&sem->count) < 0; +} Index: linux-rt-rebase.q/arch/ppc/kernel/smp.c =================================================================== --- linux-rt-rebase.q.orig/arch/ppc/kernel/smp.c +++ linux-rt-rebase.q/arch/ppc/kernel/smp.c @@ -136,6 +136,16 @@ void smp_send_reschedule(int cpu) smp_message_pass(cpu, PPC_MSG_RESCHEDULE); } +/* + * this function sends a 'reschedule' IPI to all other CPUs. + * This is used when RT tasks are starving and other CPUs + * might be able to run them: + */ +void smp_send_reschedule_allbutself(void) +{ + smp_message_pass(MSG_ALL_BUT_SELF, PPC_MSG_RESCHEDULE, 0, 0); +} + #ifdef CONFIG_XMON void smp_send_xmon_break(int cpu) { @@ -160,7 +170,7 @@ void smp_send_stop(void) * static memory requirements. It also looks cleaner. * Stolen from the i386 version. */ -static DEFINE_SPINLOCK(call_lock); +static DEFINE_RAW_SPINLOCK(call_lock); static struct call_data_struct { void (*func) (void *info); Index: linux-rt-rebase.q/arch/ppc/kernel/traps.c =================================================================== --- linux-rt-rebase.q.orig/arch/ppc/kernel/traps.c +++ linux-rt-rebase.q/arch/ppc/kernel/traps.c @@ -72,7 +72,7 @@ void (*debugger_fault_handler)(struct pt * Trap & Exception support */ -DEFINE_SPINLOCK(die_lock); +DEFINE_RAW_SPINLOCK(die_lock); int die(const char * str, struct pt_regs * fp, long err) { @@ -108,6 +108,10 @@ void _exception(int signr, struct pt_reg debugger(regs); die("Exception in kernel mode", regs, signr); } +#ifdef CONFIG_PREEMPT_RT + local_irq_enable(); + preempt_check_resched(); +#endif info.si_signo = signr; info.si_errno = 0; info.si_code = code; Index: linux-rt-rebase.q/arch/ppc/lib/locks.c =================================================================== --- linux-rt-rebase.q.orig/arch/ppc/lib/locks.c +++ linux-rt-rebase.q/arch/ppc/lib/locks.c @@ -42,7 +42,7 @@ static inline unsigned long __spin_trylo return ret; } -void _raw_spin_lock(spinlock_t *lock) +void __raw_spin_lock(raw_spinlock_t *lock) { int cpu = smp_processor_id(); unsigned int stuck = INIT_STUCK; @@ -62,9 +62,9 @@ void _raw_spin_lock(spinlock_t *lock) lock->owner_pc = (unsigned long)__builtin_return_address(0); lock->owner_cpu = cpu; } -EXPORT_SYMBOL(_raw_spin_lock); +EXPORT_SYMBOL(__raw_spin_lock); -int _raw_spin_trylock(spinlock_t *lock) +int __raw_spin_trylock(raw_spinlock_t *lock) { if (__spin_trylock(&lock->lock)) return 0; @@ -72,9 +72,9 @@ int _raw_spin_trylock(spinlock_t *lock) lock->owner_pc = (unsigned long)__builtin_return_address(0); return 1; } -EXPORT_SYMBOL(_raw_spin_trylock); +EXPORT_SYMBOL(__raw_spin_trylock); -void _raw_spin_unlock(spinlock_t *lp) +void __raw_spin_unlock(raw_spinlock_t *lp) { if ( !lp->lock ) printk("_spin_unlock(%p): no lock cpu %d curr PC %p %s/%d\n", @@ -88,13 +88,13 @@ void _raw_spin_unlock(spinlock_t *lp) wmb(); lp->lock = 0; } -EXPORT_SYMBOL(_raw_spin_unlock); +EXPORT_SYMBOL(__raw_spin_unlock); /* * For rwlocks, zero is unlocked, -1 is write-locked, * positive is read-locked. */ -static __inline__ int __read_trylock(rwlock_t *rw) +static __inline__ int __read_trylock(raw_rwlock_t *rw) { signed int tmp; @@ -114,13 +114,13 @@ static __inline__ int __read_trylock(rwl return tmp; } -int _raw_read_trylock(rwlock_t *rw) +int __raw_read_trylock(raw_rwlock_t *rw) { return __read_trylock(rw) > 0; } -EXPORT_SYMBOL(_raw_read_trylock); +EXPORT_SYMBOL(__raw_read_trylock); -void _raw_read_lock(rwlock_t *rw) +void __raw_read_lock(rwlock_t *rw) { unsigned int stuck; @@ -135,9 +135,9 @@ void _raw_read_lock(rwlock_t *rw) } } } -EXPORT_SYMBOL(_raw_read_lock); +EXPORT_SYMBOL(__raw_read_lock); -void _raw_read_unlock(rwlock_t *rw) +void __raw_read_unlock(raw_rwlock_t *rw) { if ( rw->lock == 0 ) printk("_read_unlock(): %s/%d (nip %08lX) lock %d\n", @@ -146,9 +146,9 @@ void _raw_read_unlock(rwlock_t *rw) wmb(); atomic_dec((atomic_t *) &(rw)->lock); } -EXPORT_SYMBOL(_raw_read_unlock); +EXPORT_SYMBOL(__raw_read_unlock); -void _raw_write_lock(rwlock_t *rw) +void __raw_write_lock(raw_rwlock_t *rw) { unsigned int stuck; @@ -164,18 +164,18 @@ void _raw_write_lock(rwlock_t *rw) } wmb(); } -EXPORT_SYMBOL(_raw_write_lock); +EXPORT_SYMBOL(__raw_write_lock); -int _raw_write_trylock(rwlock_t *rw) +int __raw_write_trylock(raw_rwlock_t *rw) { if (cmpxchg(&rw->lock, 0, -1) != 0) return 0; wmb(); return 1; } -EXPORT_SYMBOL(_raw_write_trylock); +EXPORT_SYMBOL(__raw_write_trylock); -void _raw_write_unlock(rwlock_t *rw) +void __raw_write_unlock(raw_rwlock_t *rw) { if (rw->lock >= 0) printk("_write_lock(): %s/%d (nip %08lX) lock %d\n", @@ -184,6 +184,6 @@ void _raw_write_unlock(rwlock_t *rw) wmb(); rw->lock = 0; } -EXPORT_SYMBOL(_raw_write_unlock); +EXPORT_SYMBOL(__raw_write_unlock); #endif Index: linux-rt-rebase.q/arch/ppc/mm/init.c =================================================================== --- linux-rt-rebase.q.orig/arch/ppc/mm/init.c +++ linux-rt-rebase.q/arch/ppc/mm/init.c @@ -55,7 +55,7 @@ #endif #define MAX_LOW_MEM CONFIG_LOWMEM_SIZE -DEFINE_PER_CPU(struct mmu_gather, mmu_gathers); +DEFINE_PER_CPU_LOCKED(struct mmu_gather, mmu_gathers); unsigned long total_memory; unsigned long total_lowmem; Index: linux-rt-rebase.q/arch/ppc/platforms/hdpu.c =================================================================== --- linux-rt-rebase.q.orig/arch/ppc/platforms/hdpu.c +++ linux-rt-rebase.q/arch/ppc/platforms/hdpu.c @@ -55,7 +55,7 @@ static void parse_bootinfo(unsigned long static void hdpu_set_l1pe(void); static void hdpu_cpustate_set(unsigned char new_state); #ifdef CONFIG_SMP -static DEFINE_SPINLOCK(timebase_lock); +static DEFINE_RAW_SPINLOCK(timebase_lock); static unsigned int timebase_upper = 0, timebase_lower = 0; extern int smp_tb_synchronized; Index: linux-rt-rebase.q/arch/ppc/platforms/sbc82xx.c =================================================================== --- linux-rt-rebase.q.orig/arch/ppc/platforms/sbc82xx.c +++ linux-rt-rebase.q/arch/ppc/platforms/sbc82xx.c @@ -65,7 +65,7 @@ static void sbc82xx_time_init(void) static volatile char *sbc82xx_i8259_map; static char sbc82xx_i8259_mask = 0xff; -static DEFINE_SPINLOCK(sbc82xx_i8259_lock); +static DEFINE_RAW_SPINLOCK(sbc82xx_i8259_lock); static void sbc82xx_i8259_mask_and_ack_irq(unsigned int irq_nr) { Index: linux-rt-rebase.q/arch/ppc/syslib/cpm2_common.c =================================================================== --- linux-rt-rebase.q.orig/arch/ppc/syslib/cpm2_common.c +++ linux-rt-rebase.q/arch/ppc/syslib/cpm2_common.c @@ -114,7 +114,7 @@ cpm2_fastbrg(uint brg, uint rate, int di /* * dpalloc / dpfree bits. */ -static spinlock_t cpm_dpmem_lock; +static raw_spinlock_t cpm_dpmem_lock; /* 16 blocks should be enough to satisfy all requests * until the memory subsystem goes up... */ static rh_block_t cpm_boot_dpmem_rh_block[16]; Index: linux-rt-rebase.q/arch/ppc/syslib/ocp.c =================================================================== --- linux-rt-rebase.q.orig/arch/ppc/syslib/ocp.c +++ linux-rt-rebase.q/arch/ppc/syslib/ocp.c @@ -44,11 +44,11 @@ #include #include #include +#include #include #include #include -#include #include //#define DBG(x) printk x Index: linux-rt-rebase.q/arch/ppc/syslib/open_pic.c =================================================================== --- linux-rt-rebase.q.orig/arch/ppc/syslib/open_pic.c +++ linux-rt-rebase.q/arch/ppc/syslib/open_pic.c @@ -526,7 +526,7 @@ void openpic_reset_processor_phys(u_int } #if defined(CONFIG_SMP) || defined(CONFIG_PM) -static DEFINE_SPINLOCK(openpic_setup_lock); +static DEFINE_RAW_SPINLOCK(openpic_setup_lock); #endif #ifdef CONFIG_SMP Index: linux-rt-rebase.q/arch/ppc/syslib/open_pic2.c =================================================================== --- linux-rt-rebase.q.orig/arch/ppc/syslib/open_pic2.c +++ linux-rt-rebase.q/arch/ppc/syslib/open_pic2.c @@ -380,7 +380,7 @@ static void openpic2_set_spurious(u_int vec); } -static DEFINE_SPINLOCK(openpic2_setup_lock); +static DEFINE_RAW_SPINLOCK(openpic2_setup_lock); /* * Initialize a timer interrupt (and disable it) Index: linux-rt-rebase.q/arch/sh/kernel/cpu/clock.c =================================================================== --- linux-rt-rebase.q.orig/arch/sh/kernel/cpu/clock.c +++ linux-rt-rebase.q/arch/sh/kernel/cpu/clock.c @@ -28,7 +28,7 @@ #include static LIST_HEAD(clock_list); -static DEFINE_SPINLOCK(clock_lock); +static DEFINE_RAW_SPINLOCK(clock_lock); static DEFINE_MUTEX(clock_list_sem); /* Index: linux-rt-rebase.q/arch/sh/kernel/cpu/sh4/sq.c =================================================================== --- linux-rt-rebase.q.orig/arch/sh/kernel/cpu/sh4/sq.c +++ linux-rt-rebase.q/arch/sh/kernel/cpu/sh4/sq.c @@ -37,7 +37,7 @@ struct sq_mapping { }; static struct sq_mapping *sq_mapping_list; -static DEFINE_SPINLOCK(sq_mapping_lock); +static DEFINE_RAW_SPINLOCK(sq_mapping_lock); static struct kmem_cache *sq_cache; static unsigned long *sq_bitmap; Index: linux-rt-rebase.q/arch/sh/kernel/entry-common.S =================================================================== --- linux-rt-rebase.q.orig/arch/sh/kernel/entry-common.S +++ linux-rt-rebase.q/arch/sh/kernel/entry-common.S @@ -157,7 +157,7 @@ ENTRY(resume_userspace) mov.l @(TI_FLAGS,r8), r0 ! current_thread_info->flags tst #_TIF_WORK_MASK, r0 bt/s __restore_all - tst #_TIF_NEED_RESCHED, r0 + tst #_TIF_NEED_RESCHED|_TIF_NEED_RESCHED_DELAYED, r0 .align 2 work_pending: @@ -209,10 +209,10 @@ work_resched: tst #_TIF_WORK_MASK, r0 bt __restore_all bra work_pending - tst #_TIF_NEED_RESCHED, r0 + tst #_TIF_NEED_RESCHED | _TIF_NEED_RESCHED_DELAYED, r0 .align 2 -1: .long schedule +1: .long __schedule 2: .long do_notify_resume 3: .long restore_all #ifdef CONFIG_TRACE_IRQFLAGS @@ -226,7 +226,7 @@ syscall_exit_work: ! r8: current_thread_info tst #_TIF_SYSCALL_TRACE | _TIF_SINGLESTEP, r0 bt/s work_pending - tst #_TIF_NEED_RESCHED, r0 + tst #_TIF_NEED_RESCHED| _TIF_NEED_RESCHED_DELAYED, r0 #ifdef CONFIG_TRACE_IRQFLAGS mov.l 5f, r0 jsr @r0 Index: linux-rt-rebase.q/arch/sh/kernel/irq.c =================================================================== --- linux-rt-rebase.q.orig/arch/sh/kernel/irq.c +++ linux-rt-rebase.q/arch/sh/kernel/irq.c @@ -82,7 +82,7 @@ static union irq_ctx *hardirq_ctx[NR_CPU static union irq_ctx *softirq_ctx[NR_CPUS] __read_mostly; #endif -asmlinkage int do_IRQ(unsigned int irq, struct pt_regs *regs) +asmlinkage notrace int do_IRQ(unsigned int irq, struct pt_regs *regs) { struct pt_regs *old_regs = set_irq_regs(regs); #ifdef CONFIG_4KSTACKS Index: linux-rt-rebase.q/arch/sh/kernel/process.c =================================================================== --- linux-rt-rebase.q.orig/arch/sh/kernel/process.c +++ linux-rt-rebase.q/arch/sh/kernel/process.c @@ -63,7 +63,7 @@ void default_idle(void) clear_thread_flag(TIF_POLLING_NRFLAG); smp_mb__after_clear_bit(); set_bl_bit(); - while (!need_resched()) + while (!need_resched() && !need_resched_delayed()) cpu_sleep(); clear_bl_bit(); set_thread_flag(TIF_POLLING_NRFLAG); @@ -84,13 +84,15 @@ void cpu_idle(void) idle = default_idle; tick_nohz_stop_sched_tick(); - while (!need_resched()) + while (!need_resched() && !need_resched_delayed()) idle(); tick_nohz_restart_sched_tick(); - preempt_enable_no_resched(); - schedule(); + local_irq_disable(); + __preempt_enable_no_resched(); + __schedule(); preempt_disable(); + local_irq_enable(); check_pgt_cache(); } } Index: linux-rt-rebase.q/arch/sh/kernel/semaphore.c =================================================================== --- linux-rt-rebase.q.orig/arch/sh/kernel/semaphore.c +++ linux-rt-rebase.q/arch/sh/kernel/semaphore.c @@ -46,7 +46,7 @@ DEFINE_SPINLOCK(semaphore_wake_lock); * critical part is the inline stuff in * where we want to avoid any extra jumps and calls. */ -void __up(struct semaphore *sem) +void __attribute_used__ __compat_up(struct compat_semaphore *sem) { wake_one_more(sem); wake_up(&sem->wait); @@ -104,7 +104,7 @@ void __up(struct semaphore *sem) tsk->state = TASK_RUNNING; \ remove_wait_queue(&sem->wait, &wait); -void __sched __down(struct semaphore * sem) +void __attribute_used__ __sched __compat_down(struct compat_semaphore * sem) { DOWN_VAR DOWN_HEAD(TASK_UNINTERRUPTIBLE) @@ -114,7 +114,7 @@ void __sched __down(struct semaphore * s DOWN_TAIL(TASK_UNINTERRUPTIBLE) } -int __sched __down_interruptible(struct semaphore * sem) +int __attribute_used__ __sched __compat_down_interruptible(struct compat_semaphore * sem) { int ret = 0; DOWN_VAR @@ -133,7 +133,13 @@ int __sched __down_interruptible(struct return ret; } -int __down_trylock(struct semaphore * sem) +int __attribute_used__ __compat_down_trylock(struct compat_semaphore * sem) { return waking_non_zero_trylock(sem); } + +fastcall int __sched compat_sem_is_locked(struct compat_semaphore *sem) +{ + return (int) atomic_read(&sem->count) < 0; +} + Index: linux-rt-rebase.q/arch/sh/kernel/sh_ksyms.c =================================================================== --- linux-rt-rebase.q.orig/arch/sh/kernel/sh_ksyms.c +++ linux-rt-rebase.q/arch/sh/kernel/sh_ksyms.c @@ -26,7 +26,6 @@ EXPORT_SYMBOL(sh_mv); /* platform dependent support */ EXPORT_SYMBOL(dump_fpu); EXPORT_SYMBOL(kernel_thread); -EXPORT_SYMBOL(irq_desc); EXPORT_SYMBOL(no_irq_type); EXPORT_SYMBOL(strlen); @@ -50,9 +49,9 @@ EXPORT_SYMBOL(get_vm_area); #endif /* semaphore exports */ -EXPORT_SYMBOL(__up); -EXPORT_SYMBOL(__down); -EXPORT_SYMBOL(__down_interruptible); +EXPORT_SYMBOL(__compat_up); +EXPORT_SYMBOL(__compat_down); +EXPORT_SYMBOL(__compat_down_interruptible); EXPORT_SYMBOL(__udelay); EXPORT_SYMBOL(__ndelay); @@ -141,7 +140,7 @@ EXPORT_SYMBOL(__flush_purge_region); EXPORT_SYMBOL(clear_user_page); #endif -EXPORT_SYMBOL(__down_trylock); +EXPORT_SYMBOL(__compat_down_trylock); #ifdef CONFIG_SMP EXPORT_SYMBOL(synchronize_irq); Index: linux-rt-rebase.q/arch/sh/kernel/signal.c =================================================================== --- linux-rt-rebase.q.orig/arch/sh/kernel/signal.c +++ linux-rt-rebase.q/arch/sh/kernel/signal.c @@ -566,6 +566,13 @@ static void do_signal(struct pt_regs *re struct k_sigaction ka; sigset_t *oldset; +#ifdef CONFIG_PREEMPT_RT + /* + * Fully-preemptible kernel does not need interrupts disabled: + */ + raw_local_irq_enable(); + preempt_check_resched(); +#endif /* * We want the common case to go fast, which * is why we may in certain cases get here from Index: linux-rt-rebase.q/arch/sh/kernel/time.c =================================================================== --- linux-rt-rebase.q.orig/arch/sh/kernel/time.c +++ linux-rt-rebase.q/arch/sh/kernel/time.c @@ -24,7 +24,7 @@ struct sys_timer *sys_timer; /* Move this somewhere more sensible.. */ -DEFINE_SPINLOCK(rtc_lock); +DEFINE_RAW_SPINLOCK(rtc_lock); EXPORT_SYMBOL(rtc_lock); /* Dummy RTC ops */ Index: linux-rt-rebase.q/arch/sh/kernel/traps.c =================================================================== --- linux-rt-rebase.q.orig/arch/sh/kernel/traps.c +++ linux-rt-rebase.q/arch/sh/kernel/traps.c @@ -77,7 +77,7 @@ static void dump_mem(const char *str, un } } -static DEFINE_SPINLOCK(die_lock); +static DEFINE_RAW_SPINLOCK(die_lock); void die(const char * str, struct pt_regs * regs, long err) { Index: linux-rt-rebase.q/arch/sh/mm/cache-sh4.c =================================================================== --- linux-rt-rebase.q.orig/arch/sh/mm/cache-sh4.c +++ linux-rt-rebase.q/arch/sh/mm/cache-sh4.c @@ -203,7 +203,7 @@ void flush_cache_sigtramp(unsigned long index = CACHE_IC_ADDRESS_ARRAY | (v & current_cpu_data.icache.entry_mask); - local_irq_save(flags); + raw_local_irq_save(flags); jump_to_P2(); for (i = 0; i < current_cpu_data.icache.ways; @@ -212,7 +212,7 @@ void flush_cache_sigtramp(unsigned long back_to_P1(); wmb(); - local_irq_restore(flags); + raw_local_irq_restore(flags); } static inline void flush_cache_4096(unsigned long start, @@ -228,10 +228,10 @@ static inline void flush_cache_4096(unsi (start < CACHE_OC_ADDRESS_ARRAY)) exec_offset = 0x20000000; - local_irq_save(flags); + raw_local_irq_save(flags); __flush_cache_4096(start | SH_CACHE_ASSOC, P1SEGADDR(phys), exec_offset); - local_irq_restore(flags); + raw_local_irq_restore(flags); } /* @@ -259,7 +259,7 @@ static inline void flush_icache_all(void { unsigned long flags, ccr; - local_irq_save(flags); + raw_local_irq_save(flags); jump_to_P2(); /* Flush I-cache */ @@ -273,7 +273,7 @@ static inline void flush_icache_all(void */ back_to_P1(); - local_irq_restore(flags); + raw_local_irq_restore(flags); } void flush_dcache_all(void) Index: linux-rt-rebase.q/arch/sh/mm/init.c =================================================================== --- linux-rt-rebase.q.orig/arch/sh/mm/init.c +++ linux-rt-rebase.q/arch/sh/mm/init.c @@ -21,7 +21,7 @@ #include #include -DEFINE_PER_CPU(struct mmu_gather, mmu_gathers); +DEFINE_PER_CPU_LOCKED(struct mmu_gather, mmu_gathers); pgd_t swapper_pg_dir[PTRS_PER_PGD]; void (*copy_page)(void *from, void *to); Index: linux-rt-rebase.q/arch/sh/mm/pg-sh4.c =================================================================== --- linux-rt-rebase.q.orig/arch/sh/mm/pg-sh4.c +++ linux-rt-rebase.q/arch/sh/mm/pg-sh4.c @@ -39,9 +39,9 @@ void clear_user_page(void *to, unsigned entry = pfn_pte(phys_addr >> PAGE_SHIFT, PAGE_KERNEL); mutex_lock(&p3map_mutex[(address & CACHE_ALIAS)>>12]); set_pte(pte, entry); - local_irq_save(flags); + raw_local_irq_save(flags); flush_tlb_one(get_asid(), p3_addr); - local_irq_restore(flags); + raw_local_irq_restore(flags); update_mmu_cache(NULL, p3_addr, entry); __clear_user_page((void *)p3_addr, to); pte_clear(&init_mm, p3_addr, pte); @@ -75,9 +75,9 @@ void copy_user_page(void *to, void *from entry = pfn_pte(phys_addr >> PAGE_SHIFT, PAGE_KERNEL); mutex_lock(&p3map_mutex[(address & CACHE_ALIAS)>>12]); set_pte(pte, entry); - local_irq_save(flags); + raw_local_irq_save(flags); flush_tlb_one(get_asid(), p3_addr); - local_irq_restore(flags); + raw_local_irq_restore(flags); update_mmu_cache(NULL, p3_addr, entry); __copy_user_page((void *)p3_addr, from, to); pte_clear(&init_mm, p3_addr, pte); Index: linux-rt-rebase.q/arch/sh/mm/tlb-flush.c =================================================================== --- linux-rt-rebase.q.orig/arch/sh/mm/tlb-flush.c +++ linux-rt-rebase.q/arch/sh/mm/tlb-flush.c @@ -24,7 +24,7 @@ void local_flush_tlb_page(struct vm_area asid = cpu_asid(cpu, vma->vm_mm); page &= PAGE_MASK; - local_irq_save(flags); + raw_local_irq_save(flags); if (vma->vm_mm != current->mm) { saved_asid = get_asid(); set_asid(asid); @@ -32,7 +32,7 @@ void local_flush_tlb_page(struct vm_area local_flush_tlb_one(asid, page); if (saved_asid != MMU_NO_ASID) set_asid(saved_asid); - local_irq_restore(flags); + raw_local_irq_restore(flags); } } @@ -46,7 +46,7 @@ void local_flush_tlb_range(struct vm_are unsigned long flags; int size; - local_irq_save(flags); + raw_local_irq_save(flags); size = (end - start + (PAGE_SIZE - 1)) >> PAGE_SHIFT; if (size > (MMU_NTLB_ENTRIES/4)) { /* Too many TLB to flush */ cpu_context(cpu, mm) = NO_CONTEXT; @@ -71,7 +71,7 @@ void local_flush_tlb_range(struct vm_are if (saved_asid != MMU_NO_ASID) set_asid(saved_asid); } - local_irq_restore(flags); + raw_local_irq_restore(flags); } } @@ -81,7 +81,7 @@ void local_flush_tlb_kernel_range(unsign unsigned long flags; int size; - local_irq_save(flags); + raw_local_irq_save(flags); size = (end - start + (PAGE_SIZE - 1)) >> PAGE_SHIFT; if (size > (MMU_NTLB_ENTRIES/4)) { /* Too many TLB to flush */ local_flush_tlb_all(); @@ -100,7 +100,7 @@ void local_flush_tlb_kernel_range(unsign } set_asid(saved_asid); } - local_irq_restore(flags); + raw_local_irq_restore(flags); } void local_flush_tlb_mm(struct mm_struct *mm) @@ -112,11 +112,11 @@ void local_flush_tlb_mm(struct mm_struct if (cpu_context(cpu, mm) != NO_CONTEXT) { unsigned long flags; - local_irq_save(flags); + raw_local_irq_save(flags); cpu_context(cpu, mm) = NO_CONTEXT; if (mm == current->mm) activate_context(mm, cpu); - local_irq_restore(flags); + raw_local_irq_restore(flags); } } @@ -131,10 +131,10 @@ void local_flush_tlb_all(void) * TF-bit for SH-3, TI-bit for SH-4. * It's same position, bit #2. */ - local_irq_save(flags); + raw_local_irq_save(flags); status = ctrl_inl(MMUCR); status |= 0x04; ctrl_outl(status, MMUCR); ctrl_barrier(); - local_irq_restore(flags); + raw_local_irq_restore(flags); } Index: linux-rt-rebase.q/arch/sh/mm/tlb-sh4.c =================================================================== --- linux-rt-rebase.q.orig/arch/sh/mm/tlb-sh4.c +++ linux-rt-rebase.q/arch/sh/mm/tlb-sh4.c @@ -51,7 +51,7 @@ void update_mmu_cache(struct vm_area_str } } - local_irq_save(flags); + raw_local_irq_save(flags); /* Set PTEH register */ vpn = (address & MMU_VPN_MASK) | get_asid(); @@ -74,7 +74,7 @@ void update_mmu_cache(struct vm_area_str /* Load the TLB */ asm volatile("ldtlb": /* no output */ : /* no input */ : "memory"); - local_irq_restore(flags); + raw_local_irq_restore(flags); } void local_flush_tlb_one(unsigned long asid, unsigned long page) Index: linux-rt-rebase.q/arch/sh64/lib/dbg.c =================================================================== --- linux-rt-rebase.q.orig/arch/sh64/lib/dbg.c +++ linux-rt-rebase.q/arch/sh64/lib/dbg.c @@ -424,6 +424,6 @@ void print_page(struct page *page) printk(" page[%p] -> index 0x%lx, count 0x%x, flags 0x%lx\n", page, page->index, page_count(page), page->flags); printk(" address_space = %p, pages =%ld\n", page->mapping, - page->mapping->nrpages); + mapping_nrpages(page->mapping)); } Index: linux-rt-rebase.q/arch/sparc/defconfig =================================================================== --- linux-rt-rebase.q.orig/arch/sparc/defconfig +++ linux-rt-rebase.q/arch/sparc/defconfig @@ -600,7 +600,7 @@ CONFIG_LEGACY_PTY_COUNT=256 # CONFIG_IPMI_HANDLER is not set # CONFIG_WATCHDOG is not set CONFIG_HW_RANDOM=m -CONFIG_RTC=m +CONFIG_JS_RTC=m # CONFIG_R3964 is not set # CONFIG_APPLICOM is not set # CONFIG_DRM is not set Index: linux-rt-rebase.q/arch/sparc/kernel/sparc_ksyms.c =================================================================== --- linux-rt-rebase.q.orig/arch/sparc/kernel/sparc_ksyms.c +++ linux-rt-rebase.q/arch/sparc/kernel/sparc_ksyms.c @@ -161,6 +161,8 @@ EXPORT_SYMBOL(BTFIXUP_CALL(mmu_get_scsi_ EXPORT_SYMBOL(BTFIXUP_CALL(mmu_release_scsi_sgl)); EXPORT_SYMBOL(BTFIXUP_CALL(mmu_release_scsi_one)); +EXPORT_SYMBOL(BTFIXUP_CALL(pgprot_noncached)); + #ifdef CONFIG_SBUS EXPORT_SYMBOL(sbus_root); EXPORT_SYMBOL(dma_chain); @@ -260,6 +262,7 @@ EXPORT_SYMBOL(__memmove); /* Moving data to/from userspace. */ EXPORT_SYMBOL(__copy_user); EXPORT_SYMBOL(__strncpy_from_user); +EXPORT_SYMBOL(__strnlen_user); /* Networking helper routines. */ EXPORT_SYMBOL(__csum_partial_copy_sparc_generic); Index: linux-rt-rebase.q/arch/sparc/kernel/vmlinux.lds.S =================================================================== --- linux-rt-rebase.q.orig/arch/sparc/kernel/vmlinux.lds.S +++ linux-rt-rebase.q/arch/sparc/kernel/vmlinux.lds.S @@ -35,6 +35,8 @@ SECTIONS __ex_table : { *(__ex_table) } __stop___ex_table = .; + NOTES + . = ALIGN(4096); __init_begin = .; _sinittext = .; Index: linux-rt-rebase.q/arch/sparc/lib/memset.S =================================================================== --- linux-rt-rebase.q.orig/arch/sparc/lib/memset.S +++ linux-rt-rebase.q/arch/sparc/lib/memset.S @@ -162,7 +162,7 @@ __bzero: 8: add %o0, 1, %o0 subcc %o1, 1, %o1 - bne,a 8b + bne 8b EX(stb %g3, [%o0 - 1], add %o1, 1) 0: retl Index: linux-rt-rebase.q/arch/sparc/mm/highmem.c =================================================================== --- linux-rt-rebase.q.orig/arch/sparc/mm/highmem.c +++ linux-rt-rebase.q/arch/sparc/mm/highmem.c @@ -34,7 +34,7 @@ void *kmap_atomic(struct page *page, enu unsigned long idx; unsigned long vaddr; - /* even !CONFIG_PREEMPT needs this, for in_atomic in do_page_fault */ + preempt_disable(); pagefault_disable(); if (!PageHighMem(page)) return page_address(page); @@ -71,6 +71,7 @@ void kunmap_atomic(void *kvaddr, enum km if (vaddr < FIXADDR_START) { // FIXME pagefault_enable(); + preempt_enable(); return; } @@ -97,6 +98,7 @@ void kunmap_atomic(void *kvaddr, enum km #endif pagefault_enable(); + preempt_enable(); } /* We may be fed a pagetable here by ptep_to_xxx and others. */ Index: linux-rt-rebase.q/arch/sparc/prom/printf.c =================================================================== --- linux-rt-rebase.q.orig/arch/sparc/prom/printf.c +++ linux-rt-rebase.q/arch/sparc/prom/printf.c @@ -13,6 +13,7 @@ */ #include +#include #include #include @@ -44,3 +45,4 @@ prom_printf(char *fmt, ...) prom_write(ppbuf, i); } +EXPORT_SYMBOL(prom_printf); Index: linux-rt-rebase.q/arch/sparc64/defconfig =================================================================== --- linux-rt-rebase.q.orig/arch/sparc64/defconfig +++ linux-rt-rebase.q/arch/sparc64/defconfig @@ -1,11 +1,12 @@ # # Automatically generated make config: don't edit -# Linux kernel version: 2.6.22 -# Thu Jul 19 21:30:37 2007 +# Linux kernel version: 2.6.23-rc1 +# Sun Jul 22 19:24:37 2007 # CONFIG_SPARC=y CONFIG_SPARC64=y CONFIG_GENERIC_TIME=y +CONFIG_GENERIC_CMOS_UPDATE=y CONFIG_GENERIC_CLOCKEVENTS=y CONFIG_64BIT=y CONFIG_MMU=y @@ -17,6 +18,7 @@ CONFIG_ARCH_MAY_HAVE_PC_FDC=y # CONFIG_ARCH_HAS_ILOG2_U64 is not set CONFIG_AUDIT_ARCH=y CONFIG_ARCH_NO_VIRT_TO_BUS=y +CONFIG_OF=y CONFIG_SPARC64_PAGE_SIZE_8KB=y # CONFIG_SPARC64_PAGE_SIZE_64KB is not set # CONFIG_SPARC64_PAGE_SIZE_512KB is not set @@ -314,6 +316,7 @@ CONFIG_FW_LOADER=y # CONFIG_SYS_HYPERVISOR is not set CONFIG_CONNECTOR=m # CONFIG_MTD is not set +CONFIG_OF_DEVICE=y # CONFIG_PARPORT is not set CONFIG_BLK_DEV=y # CONFIG_BLK_DEV_FD is not set @@ -433,10 +436,7 @@ CONFIG_SCSI_FC_ATTRS=y CONFIG_SCSI_ISCSI_ATTRS=m # CONFIG_SCSI_SAS_ATTRS is not set # CONFIG_SCSI_SAS_LIBSAS is not set - -# -# SCSI low-level drivers -# +CONFIG_SCSI_LOWLEVEL=y CONFIG_ISCSI_TCP=m # CONFIG_BLK_DEV_3W_XXXX_RAID is not set # CONFIG_SCSI_3W_9XXX is not set @@ -701,7 +701,6 @@ CONFIG_UNIX98_PTYS=y # CONFIG_IPMI_HANDLER is not set # CONFIG_WATCHDOG is not set # CONFIG_HW_RANDOM is not set -CONFIG_RTC=y # CONFIG_R3964 is not set # CONFIG_APPLICOM is not set # CONFIG_DRM is not set @@ -844,6 +843,7 @@ CONFIG_HWMON=y # # CONFIG_DISPLAY_SUPPORT is not set # CONFIG_VGASTATE is not set +# CONFIG_VIDEO_OUTPUT_CONTROL is not set CONFIG_FB=y # CONFIG_FIRMWARE_EDID is not set CONFIG_FB_DDC=y @@ -937,7 +937,6 @@ CONFIG_SND_MIXER_OSS=m CONFIG_SND_PCM_OSS=m CONFIG_SND_PCM_OSS_PLUGINS=y CONFIG_SND_SEQUENCER_OSS=y -# CONFIG_SND_RTCTIMER is not set # CONFIG_SND_DYNAMIC_MINORS is not set CONFIG_SND_SUPPORT_OLD_API=y CONFIG_SND_VERBOSE_PROCFS=y @@ -1034,6 +1033,10 @@ CONFIG_SND_SUN_CS4231=m # CONFIG_SND_SOC is not set # +# SoC Audio support for SuperH +# + +# # Open Sound System # # CONFIG_SOUND_PRIME is not set @@ -1157,19 +1160,7 @@ CONFIG_USB_STORAGE=m # # CONFIG_USB_GADGET is not set # CONFIG_MMC is not set - -# -# LED devices -# # CONFIG_NEW_LEDS is not set - -# -# LED drivers -# - -# -# LED Triggers -# # CONFIG_INFINIBAND is not set # @@ -1199,7 +1190,6 @@ CONFIG_USB_STORAGE=m # Misc Linux/SPARC drivers # CONFIG_SUN_OPENPROMIO=m -CONFIG_SUN_MOSTEK_RTC=y # CONFIG_OBP_FLASH is not set # CONFIG_SUN_BPP is not set # CONFIG_BBC_I2C is not set Index: linux-rt-rebase.q/arch/sparc64/kernel/head.S =================================================================== --- linux-rt-rebase.q.orig/arch/sparc64/kernel/head.S +++ linux-rt-rebase.q/arch/sparc64/kernel/head.S @@ -1,15 +1,15 @@ -/* $Id: head.S,v 1.87 2002/02/09 19:49:31 davem Exp $ - * head.S: Initial boot code for the Sparc64 port of Linux. +/* head.S: Initial boot code for the Sparc64 port of Linux. * - * Copyright (C) 1996,1997 David S. Miller (davem@caip.rutgers.edu) + * Copyright (C) 1996, 1997, 2007 David S. Miller (davem@davemloft.net) * Copyright (C) 1996 David Sitsky (David.Sitsky@anu.edu.au) - * Copyright (C) 1997,1998 Jakub Jelinek (jj@sunsite.mff.cuni.cz) + * Copyright (C) 1997, 1998 Jakub Jelinek (jj@sunsite.mff.cuni.cz) * Copyright (C) 1997 Miguel de Icaza (miguel@nuclecu.unam.mx) */ #include #include #include +#include #include #include #include @@ -374,6 +374,7 @@ jump_to_sun4u_init: jmpl %g2 + %g0, %g0 nop + .section .text.init.refok sun4u_init: BRANCH_IF_SUN4V(g1, sun4v_init) @@ -529,6 +530,8 @@ tlb_fixup_done: nop /* Not reached... */ + .previous + /* This is meant to allow the sharing of this code between * boot processor invocation (via setup_tba() below) and * secondary processor startup (via trampoline.S). The Index: linux-rt-rebase.q/arch/sparc64/kernel/vmlinux.lds.S =================================================================== --- linux-rt-rebase.q.orig/arch/sparc64/kernel/vmlinux.lds.S +++ linux-rt-rebase.q/arch/sparc64/kernel/vmlinux.lds.S @@ -45,6 +45,8 @@ SECTIONS __ex_table : { *(__ex_table) } __stop___ex_table = .; + NOTES + . = ALIGN(PAGE_SIZE); __init_begin = .; .init.text : { Index: linux-rt-rebase.q/arch/um/drivers/mconsole_kern.c =================================================================== --- linux-rt-rebase.q.orig/arch/um/drivers/mconsole_kern.c +++ linux-rt-rebase.q/arch/um/drivers/mconsole_kern.c @@ -499,7 +499,7 @@ static struct mc_device mem_mc = { .remove = mem_remove, }; -static int mem_mc_init(void) +static int __init mem_mc_init(void) { if(can_drop_memory()) mconsole_register_dev(&mem_mc); @@ -798,7 +798,7 @@ void mconsole_stack(struct mc_request *r */ static char *notify_socket = NULL; -static int mconsole_init(void) +static int __init mconsole_init(void) { /* long to avoid size mismatch warnings from gcc */ long sock; Index: linux-rt-rebase.q/arch/um/drivers/net_kern.c =================================================================== --- linux-rt-rebase.q.orig/arch/um/drivers/net_kern.c +++ linux-rt-rebase.q/arch/um/drivers/net_kern.c @@ -623,7 +623,7 @@ static int eth_setup_common(char *str, i return found; } -static int eth_setup(char *str) +static int __init eth_setup(char *str) { struct eth_init *new; char *error; Index: linux-rt-rebase.q/arch/um/drivers/ubd_kern.c =================================================================== --- linux-rt-rebase.q.orig/arch/um/drivers/ubd_kern.c +++ linux-rt-rebase.q/arch/um/drivers/ubd_kern.c @@ -469,7 +469,7 @@ __uml_help(fakehd, " Change the ubd device name to \"hd\".\n\n" ); -static void do_ubd_request(request_queue_t * q); +static void do_ubd_request(struct request_queue * q); /* Only changed by ubd_init, which is an initcall. */ int thread_fd = -1; @@ -1081,7 +1081,7 @@ static void prepare_request(struct reque } /* Called with dev->lock held */ -static void do_ubd_request(request_queue_t *q) +static void do_ubd_request(struct request_queue *q) { struct io_thread_req *io_req; struct request *req; Index: linux-rt-rebase.q/arch/um/kernel/mem.c =================================================================== --- linux-rt-rebase.q.orig/arch/um/kernel/mem.c +++ linux-rt-rebase.q/arch/um/kernel/mem.c @@ -62,7 +62,7 @@ static void setup_highmem(unsigned long } #endif -void mem_init(void) +void __init mem_init(void) { /* clear the zero-page */ memset((void *) empty_zero_page, 0, PAGE_SIZE); Index: linux-rt-rebase.q/arch/um/kernel/physmem.c =================================================================== --- linux-rt-rebase.q.orig/arch/um/kernel/physmem.c +++ linux-rt-rebase.q/arch/um/kernel/physmem.c @@ -28,7 +28,8 @@ unsigned long high_physmem; extern unsigned long long physmem_size; -int init_maps(unsigned long physmem, unsigned long iomem, unsigned long highmem) +int __init init_maps(unsigned long physmem, unsigned long iomem, + unsigned long highmem) { struct page *p, *map; unsigned long phys_len, phys_pages, highmem_len, highmem_pages; @@ -47,13 +48,7 @@ int init_maps(unsigned long physmem, uns total_pages = phys_pages + iomem_pages + highmem_pages; total_len = phys_len + iomem_len + highmem_len; - if(kmalloc_ok){ - map = kmalloc(total_len, GFP_KERNEL); - if(map == NULL) - map = vmalloc(total_len); - } - else map = alloc_bootmem_low_pages(total_len); - + map = alloc_bootmem_low_pages(total_len); if(map == NULL) return -ENOMEM; @@ -98,8 +93,8 @@ void map_memory(unsigned long virt, unsi extern int __syscall_stub_start; -void setup_physmem(unsigned long start, unsigned long reserve_end, - unsigned long len, unsigned long long highmem) +void __init setup_physmem(unsigned long start, unsigned long reserve_end, + unsigned long len, unsigned long long highmem) { unsigned long reserve = reserve_end - start; int pfn = PFN_UP(__pa(reserve_end)); Index: linux-rt-rebase.q/arch/um/kernel/skas/process.c =================================================================== --- linux-rt-rebase.q.orig/arch/um/kernel/skas/process.c +++ linux-rt-rebase.q/arch/um/kernel/skas/process.c @@ -145,7 +145,7 @@ void init_idle_skas(void) extern void start_kernel(void); -static int start_kernel_proc(void *unused) +static int __init start_kernel_proc(void *unused) { int pid; @@ -165,7 +165,7 @@ extern int userspace_pid[]; extern char cpu0_irqstack[]; -int start_uml_skas(void) +int __init start_uml_skas(void) { stack_protections((unsigned long) &cpu0_irqstack); set_sigstack(cpu0_irqstack, THREAD_SIZE); Index: linux-rt-rebase.q/arch/um/os-Linux/aio.c =================================================================== --- linux-rt-rebase.q.orig/arch/um/os-Linux/aio.c +++ linux-rt-rebase.q/arch/um/os-Linux/aio.c @@ -14,6 +14,7 @@ #include "init.h" #include "user.h" #include "mode.h" +#include "kern_constants.h" struct aio_thread_req { enum aio_type type; @@ -65,47 +66,33 @@ static long io_getevents(aio_context_t c static int do_aio(aio_context_t ctx, enum aio_type type, int fd, char *buf, int len, unsigned long long offset, struct aio_context *aio) { - struct iocb iocb, *iocbp = &iocb; + struct iocb *iocbp = & ((struct iocb) { + .aio_data = (unsigned long) aio, + .aio_fildes = fd, + .aio_buf = (unsigned long) buf, + .aio_nbytes = len, + .aio_offset = offset + }); char c; - int err; - - iocb = ((struct iocb) { .aio_data = (unsigned long) aio, - .aio_reqprio = 0, - .aio_fildes = fd, - .aio_buf = (unsigned long) buf, - .aio_nbytes = len, - .aio_offset = offset, - .aio_reserved1 = 0, - .aio_reserved2 = 0, - .aio_reserved3 = 0 }); - switch(type){ + switch (type) { case AIO_READ: - iocb.aio_lio_opcode = IOCB_CMD_PREAD; - err = io_submit(ctx, 1, &iocbp); + iocbp->aio_lio_opcode = IOCB_CMD_PREAD; break; case AIO_WRITE: - iocb.aio_lio_opcode = IOCB_CMD_PWRITE; - err = io_submit(ctx, 1, &iocbp); + iocbp->aio_lio_opcode = IOCB_CMD_PWRITE; break; case AIO_MMAP: - iocb.aio_lio_opcode = IOCB_CMD_PREAD; - iocb.aio_buf = (unsigned long) &c; - iocb.aio_nbytes = sizeof(c); - err = io_submit(ctx, 1, &iocbp); + iocbp->aio_lio_opcode = IOCB_CMD_PREAD; + iocbp->aio_buf = (unsigned long) &c; + iocbp->aio_nbytes = sizeof(c); break; default: - printk("Bogus op in do_aio - %d\n", type); - err = -EINVAL; - break; + printk(UM_KERN_ERR "Bogus op in do_aio - %d\n", type); + return -EINVAL; } - if(err > 0) - err = 0; - else - err = -errno; - - return err; + return (io_submit(ctx, 1, &iocbp) > 0) ? 0 : -errno; } /* Initialized in an initcall and unchanged thereafter */ Index: linux-rt-rebase.q/arch/um/os-Linux/process.c =================================================================== --- linux-rt-rebase.q.orig/arch/um/os-Linux/process.c +++ linux-rt-rebase.q/arch/um/os-Linux/process.c @@ -194,7 +194,7 @@ int os_unmap_memory(void *addr, int len) #define MADV_REMOVE KERNEL_MADV_REMOVE #endif -int __init os_drop_memory(void *addr, int length) +int os_drop_memory(void *addr, int length) { int err; Index: linux-rt-rebase.q/arch/um/os-Linux/user_syms.c =================================================================== --- linux-rt-rebase.q.orig/arch/um/os-Linux/user_syms.c +++ linux-rt-rebase.q/arch/um/os-Linux/user_syms.c @@ -19,10 +19,7 @@ extern void *memmove(void *, const void extern void *memset(void *, int, size_t); extern int printf(const char *, ...); -/* If they're not defined, the export is included in lib/string.c.*/ -#ifdef __HAVE_ARCH_STRLEN -EXPORT_SYMBOL(strlen); -#endif +/* If it's not defined, the export is included in lib/string.c.*/ #ifdef __HAVE_ARCH_STRSTR EXPORT_SYMBOL(strstr); #endif Index: linux-rt-rebase.q/arch/um/sys-i386/Makefile =================================================================== --- linux-rt-rebase.q.orig/arch/um/sys-i386/Makefile +++ linux-rt-rebase.q/arch/um/sys-i386/Makefile @@ -4,7 +4,7 @@ obj-y = bug.o bugs.o checksum.o delay.o obj-$(CONFIG_MODE_SKAS) += stub.o stub_segv.o -subarch-obj-y = lib/bitops.o lib/semaphore.o +subarch-obj-y = lib/bitops.o lib/semaphore.o lib/string.o subarch-obj-$(CONFIG_HIGHMEM) += mm/highmem.o subarch-obj-$(CONFIG_MODULES) += kernel/module.o Index: linux-rt-rebase.q/arch/x86_64/Kconfig =================================================================== --- linux-rt-rebase.q.orig/arch/x86_64/Kconfig +++ linux-rt-rebase.q/arch/x86_64/Kconfig @@ -28,6 +28,18 @@ config GENERIC_TIME bool default y +config GENERIC_CLOCKEVENTS + bool + default y + +config GENERIC_CLOCKEVENTS_BROADCAST + bool + default y + +config NONIRQ_WAKEUP + bool + default y + config GENERIC_TIME_VSYSCALL bool default y @@ -74,13 +86,6 @@ config ISA config SBUS bool -config RWSEM_GENERIC_SPINLOCK - bool - default y - -config RWSEM_XCHGADD_ALGORITHM - bool - config GENERIC_HWEIGHT bool default y @@ -138,6 +143,8 @@ source "init/Kconfig" menu "Processor type and features" +source "kernel/time/Kconfig" + choice prompt "Subarchitecture Type" default X86_PC @@ -355,6 +362,14 @@ config NUMA If the system is EM64T, you should say N unless your system is EM64T NUMA. +config RWSEM_GENERIC_SPINLOCK + bool + default y + +config RWSEM_XCHGADD_ALGORITHM + depends on !RWSEM_GENERIC_SPINLOCK && !PREEMPT_RT + bool + config K8_NUMA bool "Old style AMD Opteron NUMA detection" depends on NUMA && PCI @@ -706,6 +721,10 @@ config GENERIC_PENDING_IRQ depends on GENERIC_HARDIRQS && SMP default y +config HARDIRQS_SW_RESEND + bool + default y + menu "Power management options" source kernel/power/Kconfig @@ -714,6 +733,8 @@ source "drivers/acpi/Kconfig" source "arch/x86_64/kernel/cpufreq/Kconfig" +source "drivers/cpuidle/Kconfig" + endmenu menu "Bus options (PCI etc.)" Index: linux-rt-rebase.q/arch/x86_64/ia32/ia32entry.S =================================================================== --- linux-rt-rebase.q.orig/arch/x86_64/ia32/ia32entry.S +++ linux-rt-rebase.q/arch/x86_64/ia32/ia32entry.S @@ -120,7 +120,9 @@ sysenter_do_call: cmpl $(IA32_NR_syscalls-1),%eax ja ia32_badsys IA32_ARG_FIXUP 1 + TRACE_SYS_IA32_CALL call *ia32_sys_call_table(,%rax,8) + TRACE_SYS_RET movq %rax,RAX-ARGOFFSET(%rsp) GET_THREAD_INFO(%r10) cli @@ -229,7 +231,9 @@ cstar_do_call: cmpl $IA32_NR_syscalls-1,%eax ja ia32_badsys IA32_ARG_FIXUP 1 + TRACE_SYS_IA32_CALL call *ia32_sys_call_table(,%rax,8) + TRACE_SYS_RET movq %rax,RAX-ARGOFFSET(%rsp) GET_THREAD_INFO(%r10) cli @@ -323,8 +327,10 @@ ia32_do_syscall: cmpl $(IA32_NR_syscalls-1),%eax ja ia32_badsys IA32_ARG_FIXUP + TRACE_SYS_IA32_CALL call *ia32_sys_call_table(,%rax,8) # xxx: rip relative ia32_sysret: + TRACE_SYS_RET movq %rax,RAX-ARGOFFSET(%rsp) jmp int_ret_from_sys_call @@ -395,7 +401,7 @@ END(ia32_ptregs_common) .section .rodata,"a" .align 8 -ia32_sys_call_table: +ENTRY(ia32_sys_call_table) .quad sys_restart_syscall .quad sys_exit .quad stub32_fork @@ -721,4 +727,7 @@ ia32_sys_call_table: .quad compat_sys_timerfd .quad sys_eventfd .quad sys32_fallocate +#ifdef CONFIG_EVENT_TRACE + .globl ia32_syscall_end +#endif ia32_syscall_end: Index: linux-rt-rebase.q/arch/x86_64/kernel/Makefile =================================================================== --- linux-rt-rebase.q.orig/arch/x86_64/kernel/Makefile +++ linux-rt-rebase.q/arch/x86_64/kernel/Makefile @@ -9,7 +9,7 @@ obj-y := process.o signal.o entry.o trap x8664_ksyms.o i387.o syscall.o vsyscall.o \ setup64.o bootflag.o e820.o reboot.o quirks.o i8237.o \ pci-dma.o pci-nommu.o alternative.o hpet.o tsc.o bugs.o \ - perfctr-watchdog.o + perfctr-watchdog.o i8253.o obj-$(CONFIG_STACKTRACE) += stacktrace.o obj-$(CONFIG_X86_MCE) += mce.o therm_throt.o @@ -49,6 +49,8 @@ obj-y += pcspeaker.o CFLAGS_vsyscall.o := $(PROFILING) -g0 +i8253-y += ../../i386/kernel/i8253.o +hpet-y += ../../i386/kernel/hpet.o therm_throt-y += ../../i386/kernel/cpu/mcheck/therm_throt.o bootflag-y += ../../i386/kernel/bootflag.o legacy_serial-y += ../../i386/kernel/legacy_serial.o Index: linux-rt-rebase.q/arch/x86_64/kernel/acpi/Makefile =================================================================== --- linux-rt-rebase.q.orig/arch/x86_64/kernel/acpi/Makefile +++ linux-rt-rebase.q/arch/x86_64/kernel/acpi/Makefile @@ -1,6 +1,6 @@ obj-y := boot.o boot-y := ../../../i386/kernel/acpi/boot.o -obj-$(CONFIG_ACPI_SLEEP) += sleep.o wakeup.o +obj-y += sleep.o wakeup.o ifneq ($(CONFIG_ACPI_PROCESSOR),) obj-y += processor.o Index: linux-rt-rebase.q/arch/x86_64/kernel/acpi/sleep.c =================================================================== --- linux-rt-rebase.q.orig/arch/x86_64/kernel/acpi/sleep.c +++ linux-rt-rebase.q/arch/x86_64/kernel/acpi/sleep.c @@ -51,8 +51,6 @@ Low-Level Sleep Support -------------------------------------------------------------------------- */ -#ifdef CONFIG_ACPI_SLEEP - /* address in low memory of the wakeup routine. */ unsigned long acpi_wakeup_address = 0; unsigned long acpi_realmode_flags; @@ -117,8 +115,6 @@ static int __init acpi_sleep_setup(char __setup("acpi_sleep=", acpi_sleep_setup); -#endif /*CONFIG_ACPI_SLEEP */ - void acpi_pci_link_exit(void) { } Index: linux-rt-rebase.q/arch/x86_64/kernel/apic.c =================================================================== --- linux-rt-rebase.q.orig/arch/x86_64/kernel/apic.c +++ linux-rt-rebase.q/arch/x86_64/kernel/apic.c @@ -25,6 +25,7 @@ #include #include #include +#include #include #include @@ -39,12 +40,10 @@ #include #include -int apic_mapped; int apic_verbosity; -int apic_runs_main_timer; -int apic_calibrate_pmtmr __initdata; - -int disable_apic_timer __initdata; +static int apic_mapped; +static int apic_calibrate_pmtmr __initdata; +static int disable_apic_timer __initdata; /* Local APIC timer works in C2? */ int local_apic_timer_c2_ok; @@ -56,14 +55,78 @@ static struct resource lapic_resource = .flags = IORESOURCE_MEM | IORESOURCE_BUSY, }; +static unsigned int calibration_result; + +static int lapic_next_event(unsigned long delta, + struct clock_event_device *evt); +static void lapic_timer_setup(enum clock_event_mode mode, + struct clock_event_device *evt); + +static void lapic_timer_broadcast(cpumask_t mask); + +static void __setup_APIC_LVTT(unsigned int clocks, int oneshot, int irqen); + +static struct clock_event_device lapic_clockevent = { + .name = "lapic", + .features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT + | CLOCK_EVT_FEAT_C3STOP | CLOCK_EVT_FEAT_DUMMY, + .shift = 32, + .set_mode = lapic_timer_setup, + .set_next_event = lapic_next_event, + .broadcast = lapic_timer_broadcast, + .rating = 100, + .irq = -1, +}; +static DEFINE_PER_CPU(struct clock_event_device, lapic_events); + +static int lapic_next_event(unsigned long delta, + struct clock_event_device *evt) +{ + apic_write(APIC_TMICT, delta); + return 0; +} + +static void lapic_timer_setup(enum clock_event_mode mode, + struct clock_event_device *evt) +{ + unsigned long flags; + unsigned int v; + + /* Lapic used as dummy for broadcast ? */ + if (evt->features & CLOCK_EVT_FEAT_DUMMY) + return; + + local_irq_save(flags); + + switch (mode) { + case CLOCK_EVT_MODE_PERIODIC: + case CLOCK_EVT_MODE_ONESHOT: + __setup_APIC_LVTT(calibration_result, + mode != CLOCK_EVT_MODE_PERIODIC, 1); + break; + case CLOCK_EVT_MODE_UNUSED: + case CLOCK_EVT_MODE_SHUTDOWN: + v = apic_read(APIC_LVTT); + v |= (APIC_LVT_MASKED | LOCAL_TIMER_VECTOR); + apic_write(APIC_LVTT, v); + break; + case CLOCK_EVT_MODE_RESUME: + /* Nothing to do here */ + break; + } + + local_irq_restore(flags); +} + /* - * cpu_mask that denotes the CPUs that needs timer interrupt coming in as - * IPIs in place of local APIC timers + * Local APIC timer broadcast function */ -static cpumask_t timer_interrupt_broadcast_ipi_mask; - -/* Using APIC to generate smp_local_timer_interrupt? */ -int using_apic_timer __read_mostly = 0; +static void lapic_timer_broadcast(cpumask_t mask) +{ +#ifdef CONFIG_SMP + send_IPI_mask(mask, LOCAL_TIMER_VECTOR); +#endif +} static void apic_pm_activate(void); @@ -454,7 +517,6 @@ void __cpuinit setup_local_APIC (void) oldvalue, value); } - nmi_watchdog_default(); setup_apic_nmi_watchdog(NULL); apic_pm_activate(); } @@ -758,16 +820,14 @@ void __init init_apic_mappings(void) * P5 APIC double write bug. */ -#define APIC_DIVISOR 16 - -static void __setup_APIC_LVTT(unsigned int clocks) +static void __setup_APIC_LVTT(unsigned int clocks, int oneshot, int irqen) { unsigned int lvtt_value, tmp_value; - int cpu = smp_processor_id(); - lvtt_value = APIC_LVT_TIMER_PERIODIC | LOCAL_TIMER_VECTOR; - - if (cpu_isset(cpu, timer_interrupt_broadcast_ipi_mask)) + lvtt_value = LOCAL_TIMER_VECTOR; + if (!oneshot) + lvtt_value |= APIC_LVT_TIMER_PERIODIC; + if (!irqen) lvtt_value |= APIC_LVT_MASKED; apic_write(APIC_LVTT, lvtt_value); @@ -780,46 +840,18 @@ static void __setup_APIC_LVTT(unsigned i & ~(APIC_TDR_DIV_1 | APIC_TDR_DIV_TMBASE)) | APIC_TDR_DIV_16); - apic_write(APIC_TMICT, clocks/APIC_DIVISOR); + if (!oneshot) + apic_write(APIC_TMICT, clocks); } -static void setup_APIC_timer(unsigned int clocks) +static void setup_APIC_timer(void) { - unsigned long flags; + struct clock_event_device *levt = &__get_cpu_var(lapic_events); - local_irq_save(flags); + memcpy(levt, &lapic_clockevent, sizeof(*levt)); + levt->cpumask = cpumask_of_cpu(smp_processor_id()); - /* wait for irq slice */ - if (hpet_address && hpet_use_timer) { - int trigger = hpet_readl(HPET_T0_CMP); - while (hpet_readl(HPET_COUNTER) >= trigger) - /* do nothing */ ; - while (hpet_readl(HPET_COUNTER) < trigger) - /* do nothing */ ; - } else { - int c1, c2; - outb_p(0x00, 0x43); - c2 = inb_p(0x40); - c2 |= inb_p(0x40) << 8; - do { - c1 = c2; - outb_p(0x00, 0x43); - c2 = inb_p(0x40); - c2 |= inb_p(0x40) << 8; - } while (c2 - c1 < 300); - } - __setup_APIC_LVTT(clocks); - /* Turn off PIT interrupt if we use APIC timer as main timer. - Only works with the PM timer right now - TBD fix it for HPET too. */ - if ((pmtmr_ioport != 0) && - smp_processor_id() == boot_cpu_id && - apic_runs_main_timer == 1 && - !cpu_isset(boot_cpu_id, timer_interrupt_broadcast_ipi_mask)) { - stop_timer_interrupt(); - apic_runs_main_timer++; - } - local_irq_restore(flags); + clockevents_register_device(levt); } /* @@ -837,17 +869,22 @@ static void setup_APIC_timer(unsigned in #define TICK_COUNT 100000000 -static int __init calibrate_APIC_clock(void) +static void __init calibrate_APIC_clock(void) { unsigned apic, apic_start; unsigned long tsc, tsc_start; int result; + + local_irq_disable(); + /* * Put whatever arbitrary (but long enough) timeout * value into the APIC clock, we just want to get the * counter running for calibration. + * + * No interrupt enable ! */ - __setup_APIC_LVTT(4000000000); + __setup_APIC_LVTT(250000000, 0, 0); apic_start = apic_read(APIC_TMCCT); #ifdef CONFIG_X86_PM_TIMER @@ -869,123 +906,62 @@ static int __init calibrate_APIC_clock(v result = (apic_start - apic) * 1000L * tsc_khz / (tsc - tsc_start); } - printk("result %d\n", result); + local_irq_enable(); + + printk(KERN_DEBUG "APIC timer calibration result %d\n", result); printk(KERN_INFO "Detected %d.%03d MHz APIC timer.\n", result / 1000 / 1000, result / 1000 % 1000); - return result * APIC_DIVISOR / HZ; -} + /* Calculate the scaled math multiplication factor */ + lapic_clockevent.mult = div_sc(result, NSEC_PER_SEC, 32); + lapic_clockevent.max_delta_ns = + clockevent_delta2ns(0x7FFFFF, &lapic_clockevent); + lapic_clockevent.min_delta_ns = + clockevent_delta2ns(0xF, &lapic_clockevent); -static unsigned int calibration_result; + calibration_result = result / HZ; +} void __init setup_boot_APIC_clock (void) { + /* + * The local apic timer can be disabled via the kernel commandline. + * Register the lapic timer as a dummy clock event source on SMP + * systems, so the broadcast mechanism is used. On UP systems simply + * ignore it. + */ if (disable_apic_timer) { printk(KERN_INFO "Disabling APIC timer\n"); + /* No broadcast on UP ! */ + if (num_possible_cpus() > 1) + setup_APIC_timer(); return; } printk(KERN_INFO "Using local APIC timer interrupts.\n"); - using_apic_timer = 1; - - local_irq_disable(); + calibrate_APIC_clock(); - calibration_result = calibrate_APIC_clock(); /* - * Now set up the timer for real. + * If nmi_watchdog is set to IO_APIC, we need the + * PIT/HPET going. Otherwise register lapic as a dummy + * device. */ - setup_APIC_timer(calibration_result); + if (nmi_watchdog != NMI_IO_APIC) + lapic_clockevent.features &= ~CLOCK_EVT_FEAT_DUMMY; + else + printk(KERN_WARNING "APIC timer registered as dummy," + " due to nmi_watchdog=1!\n"); - local_irq_enable(); + setup_APIC_timer(); } void __cpuinit setup_secondary_APIC_clock(void) { - local_irq_disable(); /* FIXME: Do we need this? --RR */ - setup_APIC_timer(calibration_result); - local_irq_enable(); + setup_APIC_timer(); } -void disable_APIC_timer(void) -{ - if (using_apic_timer) { - unsigned long v; - - v = apic_read(APIC_LVTT); - /* - * When an illegal vector value (0-15) is written to an LVT - * entry and delivery mode is Fixed, the APIC may signal an - * illegal vector error, with out regard to whether the mask - * bit is set or whether an interrupt is actually seen on input. - * - * Boot sequence might call this function when the LVTT has - * '0' vector value. So make sure vector field is set to - * valid value. - */ - v |= (APIC_LVT_MASKED | LOCAL_TIMER_VECTOR); - apic_write(APIC_LVTT, v); - } -} - -void enable_APIC_timer(void) -{ - int cpu = smp_processor_id(); - - if (using_apic_timer && - !cpu_isset(cpu, timer_interrupt_broadcast_ipi_mask)) { - unsigned long v; - - v = apic_read(APIC_LVTT); - apic_write(APIC_LVTT, v & ~APIC_LVT_MASKED); - } -} - -void switch_APIC_timer_to_ipi(void *cpumask) -{ - cpumask_t mask = *(cpumask_t *)cpumask; - int cpu = smp_processor_id(); - - if (cpu_isset(cpu, mask) && - !cpu_isset(cpu, timer_interrupt_broadcast_ipi_mask)) { - disable_APIC_timer(); - cpu_set(cpu, timer_interrupt_broadcast_ipi_mask); - } -} -EXPORT_SYMBOL(switch_APIC_timer_to_ipi); - -void smp_send_timer_broadcast_ipi(void) -{ - int cpu = smp_processor_id(); - cpumask_t mask; - - cpus_and(mask, cpu_online_map, timer_interrupt_broadcast_ipi_mask); - - if (cpu_isset(cpu, mask)) { - cpu_clear(cpu, mask); - add_pda(apic_timer_irqs, 1); - smp_local_timer_interrupt(); - } - - if (!cpus_empty(mask)) { - send_IPI_mask(mask, LOCAL_TIMER_VECTOR); - } -} - -void switch_ipi_to_APIC_timer(void *cpumask) -{ - cpumask_t mask = *(cpumask_t *)cpumask; - int cpu = smp_processor_id(); - - if (cpu_isset(cpu, mask) && - cpu_isset(cpu, timer_interrupt_broadcast_ipi_mask)) { - cpu_clear(cpu, timer_interrupt_broadcast_ipi_mask); - enable_APIC_timer(); - } -} -EXPORT_SYMBOL(switch_ipi_to_APIC_timer); - int setup_profiling_timer(unsigned int multiplier) { return -EINVAL; @@ -999,8 +975,6 @@ void setup_APIC_extended_lvt(unsigned ch apic_write(reg, v); } -#undef APIC_DIVISOR - /* * Local timer interrupt handler. It does both profiling and * process statistics/rescheduling. @@ -1013,22 +987,34 @@ void setup_APIC_extended_lvt(unsigned ch void smp_local_timer_interrupt(void) { - profile_tick(CPU_PROFILING); -#ifdef CONFIG_SMP - update_process_times(user_mode(get_irq_regs())); -#endif - if (apic_runs_main_timer > 1 && smp_processor_id() == boot_cpu_id) - main_timer_handler(); + int cpu = smp_processor_id(); + struct clock_event_device *evt = &per_cpu(lapic_events, cpu); + /* - * We take the 'long' return path, and there every subsystem - * grabs the appropriate locks (kernel lock/ irq lock). - * - * We might want to decouple profiling from the 'long path', - * and do the profiling totally in assembly. + * Normally we should not be here till LAPIC has been initialized but + * in some cases like kdump, its possible that there is a pending LAPIC + * timer interrupt from previous kernel's context and is delivered in + * new kernel the moment interrupts are enabled. * - * Currently this isn't too much of an issue (performance wise), - * we can take more than 100K local irqs per second on a 100 MHz P5. + * Interrupts are enabled early and LAPIC is setup much later, hence + * its possible that when we get here evt->event_handler is NULL. + * Check for event_handler being NULL and discard the interrupt as + * spurious. + */ + if (!evt->event_handler) { + printk(KERN_WARNING + "Spurious LAPIC timer interrupt on cpu %d\n", cpu); + /* Switch it off */ + lapic_timer_setup(CLOCK_EVT_MODE_SHUTDOWN, evt); + return; + } + + /* + * the NMI deadlock-detector uses this. */ + add_pda(apic_timer_irqs, 1); + + evt->event_handler(evt); } /* @@ -1044,11 +1030,6 @@ void smp_apic_timer_interrupt(struct pt_ struct pt_regs *old_regs = set_irq_regs(regs); /* - * the NMI deadlock-detector uses this. - */ - add_pda(apic_timer_irqs, 1); - - /* * NOTE! We'd better ACK the irq immediately, * because timer handling can be slow. */ @@ -1128,7 +1109,6 @@ asmlinkage void smp_spurious_interrupt(v v = apic_read(APIC_ISR + ((SPURIOUS_APIC_VECTOR & ~0x1f) >> 1)); if (v & (1 << (SPURIOUS_APIC_VECTOR & 0x1f))) ack_APIC_irq(); - irq_exit(); } @@ -1227,29 +1207,13 @@ static __init int setup_noapictimer(char disable_apic_timer = 1; return 1; } - -static __init int setup_apicmaintimer(char *str) -{ - apic_runs_main_timer = 1; - nohpet = 1; - return 1; -} -__setup("apicmaintimer", setup_apicmaintimer); - -static __init int setup_noapicmaintimer(char *str) -{ - apic_runs_main_timer = -1; - return 1; -} -__setup("noapicmaintimer", setup_noapicmaintimer); +__setup("noapictimer", setup_noapictimer); static __init int setup_apicpmtimer(char *s) { apic_calibrate_pmtmr = 1; notsc_setup(NULL); - return setup_apicmaintimer(NULL); + return 0; } __setup("apicpmtimer", setup_apicpmtimer); -__setup("noapictimer", setup_noapictimer); - Index: linux-rt-rebase.q/arch/x86_64/kernel/crash.c =================================================================== --- linux-rt-rebase.q.orig/arch/x86_64/kernel/crash.c +++ linux-rt-rebase.q/arch/x86_64/kernel/crash.c @@ -62,11 +62,6 @@ static int crash_nmi_callback(struct not return 1; } -static void smp_send_nmi_allbutself(void) -{ - send_IPI_allbutself(NMI_VECTOR); -} - /* * This code is a best effort heuristic to get the * other cpus to stop executing. So races with Index: linux-rt-rebase.q/arch/x86_64/kernel/early_printk.c =================================================================== --- linux-rt-rebase.q.orig/arch/x86_64/kernel/early_printk.c +++ linux-rt-rebase.q/arch/x86_64/kernel/early_printk.c @@ -203,7 +203,7 @@ static int early_console_initialized = 0 void early_printk(const char *fmt, ...) { - char buf[512]; + static char buf[512]; int n; va_list ap; Index: linux-rt-rebase.q/arch/x86_64/kernel/entry.S =================================================================== --- linux-rt-rebase.q.orig/arch/x86_64/kernel/entry.S +++ linux-rt-rebase.q/arch/x86_64/kernel/entry.S @@ -53,6 +53,47 @@ .code64 +#ifdef CONFIG_EVENT_TRACE + +ENTRY(mcount) + cmpl $0, mcount_enabled + jz out + + push %rbp + mov %rsp,%rbp + + push %r11 + push %r10 + push %r9 + push %r8 + push %rdi + push %rsi + push %rdx + push %rcx + push %rax + + mov 0x0(%rbp),%rax + mov 0x8(%rbp),%rdi + mov 0x8(%rax),%rsi + + call __trace + + pop %rax + pop %rcx + pop %rdx + pop %rsi + pop %rdi + pop %r8 + pop %r9 + pop %r10 + pop %r11 + + pop %rbp +out: + ret + +#endif + #ifndef CONFIG_PREEMPT #define retint_kernel retint_restore_args #endif @@ -234,7 +275,9 @@ ENTRY(system_call) cmpq $__NR_syscall_max,%rax ja badsys movq %r10,%rcx + TRACE_SYS_CALL call *sys_call_table(,%rax,8) # XXX: rip relative + TRACE_SYS_RET movq %rax,RAX-ARGOFFSET(%rsp) /* * Syscall return path ending with SYSRET (fast path) @@ -267,8 +310,8 @@ sysret_check: /* Handle reschedules */ /* edx: work, edi: workmask */ sysret_careful: - bt $TIF_NEED_RESCHED,%edx - jnc sysret_signal + testl $(_TIF_NEED_RESCHED|_TIF_NEED_RESCHED_DELAYED),%edx + jz sysret_signal TRACE_IRQS_ON sti pushq %rdi @@ -291,7 +334,7 @@ sysret_signal: leaq -ARGOFFSET(%rsp),%rdi # &pt_regs -> arg1 xorl %esi,%esi # oldset -> arg2 call ptregscall_common -1: movl $_TIF_NEED_RESCHED,%edi +1: movl $(_TIF_NEED_RESCHED|_TIF_NEED_RESCHED_DELAYED),%edi /* Use IRET because user could have changed frame. This works because ptregscall_common has called FIXUP_TOP_OF_STACK. */ cli @@ -316,7 +359,9 @@ tracesys: cmova %rcx,%rax ja 1f movq %r10,%rcx /* fixup for C */ + TRACE_SYS_CALL call *sys_call_table(,%rax,8) + TRACE_SYS_RET 1: movq %rax,RAX-ARGOFFSET(%rsp) /* Use IRET because user could have changed frame */ @@ -344,8 +389,8 @@ int_with_check: /* First do a reschedule test. */ /* edx: work, edi: workmask */ int_careful: - bt $TIF_NEED_RESCHED,%edx - jnc int_very_careful + testl $(_TIF_NEED_RESCHED|_TIF_NEED_RESCHED_DELAYED),%edx + jz int_very_careful TRACE_IRQS_ON sti pushq %rdi @@ -380,7 +425,7 @@ int_signal: movq %rsp,%rdi # &ptregs -> arg1 xorl %esi,%esi # oldset -> arg2 call do_notify_resume -1: movl $_TIF_NEED_RESCHED,%edi +1: movl $(_TIF_NEED_RESCHED|_TIF_NEED_RESCHED_DELAYED),%edi int_restore_rest: RESTORE_REST cli @@ -584,8 +629,8 @@ bad_iret: /* edi: workmask, edx: work */ retint_careful: CFI_RESTORE_STATE - bt $TIF_NEED_RESCHED,%edx - jnc retint_signal + testl $(_TIF_NEED_RESCHED|_TIF_NEED_RESCHED_DELAYED),%edx + jz retint_signal TRACE_IRQS_ON sti pushq %rdi @@ -611,7 +656,7 @@ retint_signal: RESTORE_REST cli TRACE_IRQS_OFF - movl $_TIF_NEED_RESCHED,%edi + movl $(_TIF_NEED_RESCHED|_TIF_NEED_RESCHED_DELAYED),%edi GET_THREAD_INFO(%rcx) jmp retint_check Index: linux-rt-rebase.q/arch/x86_64/kernel/head.S =================================================================== --- linux-rt-rebase.q.orig/arch/x86_64/kernel/head.S +++ linux-rt-rebase.q/arch/x86_64/kernel/head.S @@ -120,7 +120,7 @@ ident_complete: addq %rbp, trampoline_level4_pgt + 0(%rip) addq %rbp, trampoline_level4_pgt + (511*8)(%rip) #endif -#ifdef CONFIG_ACPI_SLEEP +#ifdef CONFIG_ACPI addq %rbp, wakeup_level4_pgt + 0(%rip) addq %rbp, wakeup_level4_pgt + (511*8)(%rip) #endif Index: linux-rt-rebase.q/arch/x86_64/kernel/head64.c =================================================================== --- linux-rt-rebase.q.orig/arch/x86_64/kernel/head64.c +++ linux-rt-rebase.q/arch/x86_64/kernel/head64.c @@ -10,6 +10,7 @@ #include #include #include +#include #include #include @@ -25,7 +26,11 @@ static void __init zap_identity_mappings { pgd_t *pgd = pgd_offset_k(0UL); pgd_clear(pgd); - __flush_tlb(); + /* + * preempt_disable/enable does not work this early in the + * bootup yet: + */ + write_cr3(read_cr3()); } /* Don't add a printk in there. printk relies on the PDA which is not initialized @@ -58,7 +63,7 @@ static void __init copy_bootdata(char *r memcpy(boot_command_line, command_line, COMMAND_LINE_SIZE); } -void __init x86_64_start_kernel(char * real_mode_data) +void __init notrace x86_64_start_kernel(char * real_mode_data) { int i; Index: linux-rt-rebase.q/arch/x86_64/kernel/hpet.c =================================================================== --- linux-rt-rebase.q.orig/arch/x86_64/kernel/hpet.c +++ /dev/null @@ -1,493 +0,0 @@ -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#define HPET_MASK 0xFFFFFFFF -#define HPET_SHIFT 22 - -/* FSEC = 10^-15 NSEC = 10^-9 */ -#define FSEC_PER_NSEC 1000000 - -int nohpet __initdata; - -unsigned long hpet_address; -unsigned long hpet_period; /* fsecs / HPET clock */ -unsigned long hpet_tick; /* HPET clocks / interrupt */ - -int hpet_use_timer; /* Use counter of hpet for time keeping, - * otherwise PIT - */ - -#ifdef CONFIG_HPET -static __init int late_hpet_init(void) -{ - struct hpet_data hd; - unsigned int ntimer; - - if (!hpet_address) - return 0; - - memset(&hd, 0, sizeof(hd)); - - ntimer = hpet_readl(HPET_ID); - ntimer = (ntimer & HPET_ID_NUMBER) >> HPET_ID_NUMBER_SHIFT; - ntimer++; - - /* - * Register with driver. - * Timer0 and Timer1 is used by platform. - */ - hd.hd_phys_address = hpet_address; - hd.hd_address = (void __iomem *)fix_to_virt(FIX_HPET_BASE); - hd.hd_nirqs = ntimer; - hd.hd_flags = HPET_DATA_PLATFORM; - hpet_reserve_timer(&hd, 0); -#ifdef CONFIG_HPET_EMULATE_RTC - hpet_reserve_timer(&hd, 1); -#endif - hd.hd_irq[0] = HPET_LEGACY_8254; - hd.hd_irq[1] = HPET_LEGACY_RTC; - if (ntimer > 2) { - struct hpet *hpet; - struct hpet_timer *timer; - int i; - - hpet = (struct hpet *) fix_to_virt(FIX_HPET_BASE); - timer = &hpet->hpet_timers[2]; - for (i = 2; i < ntimer; timer++, i++) - hd.hd_irq[i] = (timer->hpet_config & - Tn_INT_ROUTE_CNF_MASK) >> - Tn_INT_ROUTE_CNF_SHIFT; - - } - - hpet_alloc(&hd); - return 0; -} -fs_initcall(late_hpet_init); -#endif - -int hpet_timer_stop_set_go(unsigned long tick) -{ - unsigned int cfg; - -/* - * Stop the timers and reset the main counter. - */ - - cfg = hpet_readl(HPET_CFG); - cfg &= ~(HPET_CFG_ENABLE | HPET_CFG_LEGACY); - hpet_writel(cfg, HPET_CFG); - hpet_writel(0, HPET_COUNTER); - hpet_writel(0, HPET_COUNTER + 4); - -/* - * Set up timer 0, as periodic with first interrupt to happen at hpet_tick, - * and period also hpet_tick. - */ - if (hpet_use_timer) { - hpet_writel(HPET_TN_ENABLE | HPET_TN_PERIODIC | HPET_TN_SETVAL | - HPET_TN_32BIT, HPET_T0_CFG); - hpet_writel(hpet_tick, HPET_T0_CMP); /* next interrupt */ - hpet_writel(hpet_tick, HPET_T0_CMP); /* period */ - cfg |= HPET_CFG_LEGACY; - } -/* - * Go! - */ - - cfg |= HPET_CFG_ENABLE; - hpet_writel(cfg, HPET_CFG); - - return 0; -} - -static cycle_t read_hpet(void) -{ - return (cycle_t)hpet_readl(HPET_COUNTER); -} - -static cycle_t __vsyscall_fn vread_hpet(void) -{ - return readl((void __iomem *)fix_to_virt(VSYSCALL_HPET) + 0xf0); -} - -struct clocksource clocksource_hpet = { - .name = "hpet", - .rating = 250, - .read = read_hpet, - .mask = (cycle_t)HPET_MASK, - .mult = 0, /* set below */ - .shift = HPET_SHIFT, - .flags = CLOCK_SOURCE_IS_CONTINUOUS, - .vread = vread_hpet, -}; - -int __init hpet_arch_init(void) -{ - unsigned int id; - u64 tmp; - - if (!hpet_address) - return -1; - set_fixmap_nocache(FIX_HPET_BASE, hpet_address); - __set_fixmap(VSYSCALL_HPET, hpet_address, PAGE_KERNEL_VSYSCALL_NOCACHE); - -/* - * Read the period, compute tick and quotient. - */ - - id = hpet_readl(HPET_ID); - - if (!(id & HPET_ID_VENDOR) || !(id & HPET_ID_NUMBER)) - return -1; - - hpet_period = hpet_readl(HPET_PERIOD); - if (hpet_period < 100000 || hpet_period > 100000000) - return -1; - - hpet_tick = (FSEC_PER_TICK + hpet_period / 2) / hpet_period; - - hpet_use_timer = (id & HPET_ID_LEGSUP); - - /* - * hpet period is in femto seconds per cycle - * so we need to convert this to ns/cyc units - * aproximated by mult/2^shift - * - * fsec/cyc * 1nsec/1000000fsec = nsec/cyc = mult/2^shift - * fsec/cyc * 1ns/1000000fsec * 2^shift = mult - * fsec/cyc * 2^shift * 1nsec/1000000fsec = mult - * (fsec/cyc << shift)/1000000 = mult - * (hpet_period << shift)/FSEC_PER_NSEC = mult - */ - tmp = (u64)hpet_period << HPET_SHIFT; - do_div(tmp, FSEC_PER_NSEC); - clocksource_hpet.mult = (u32)tmp; - clocksource_register(&clocksource_hpet); - - return hpet_timer_stop_set_go(hpet_tick); -} - -int hpet_reenable(void) -{ - return hpet_timer_stop_set_go(hpet_tick); -} - -/* - * calibrate_tsc() calibrates the processor TSC in a very simple way, comparing - * it to the HPET timer of known frequency. - */ - -#define TICK_COUNT 100000000 -#define SMI_THRESHOLD 50000 -#define MAX_TRIES 5 - -/* - * Some platforms take periodic SMI interrupts with 5ms duration. Make sure none - * occurs between the reads of the hpet & TSC. - */ -static void __init read_hpet_tsc(int *hpet, int *tsc) -{ - int tsc1, tsc2, hpet1, i; - - for (i = 0; i < MAX_TRIES; i++) { - tsc1 = get_cycles_sync(); - hpet1 = hpet_readl(HPET_COUNTER); - tsc2 = get_cycles_sync(); - if ((tsc2 - tsc1) < SMI_THRESHOLD) - break; - } - *hpet = hpet1; - *tsc = tsc2; -} - -unsigned int __init hpet_calibrate_tsc(void) -{ - int tsc_start, hpet_start; - int tsc_now, hpet_now; - unsigned long flags; - - local_irq_save(flags); - - read_hpet_tsc(&hpet_start, &tsc_start); - - do { - local_irq_disable(); - read_hpet_tsc(&hpet_now, &tsc_now); - local_irq_restore(flags); - } while ((tsc_now - tsc_start) < TICK_COUNT && - (hpet_now - hpet_start) < TICK_COUNT); - - return (tsc_now - tsc_start) * 1000000000L - / ((hpet_now - hpet_start) * hpet_period / 1000); -} - -#ifdef CONFIG_HPET_EMULATE_RTC -/* HPET in LegacyReplacement Mode eats up RTC interrupt line. When, HPET - * is enabled, we support RTC interrupt functionality in software. - * RTC has 3 kinds of interrupts: - * 1) Update Interrupt - generate an interrupt, every sec, when RTC clock - * is updated - * 2) Alarm Interrupt - generate an interrupt at a specific time of day - * 3) Periodic Interrupt - generate periodic interrupt, with frequencies - * 2Hz-8192Hz (2Hz-64Hz for non-root user) (all freqs in powers of 2) - * (1) and (2) above are implemented using polling at a frequency of - * 64 Hz. The exact frequency is a tradeoff between accuracy and interrupt - * overhead. (DEFAULT_RTC_INT_FREQ) - * For (3), we use interrupts at 64Hz or user specified periodic - * frequency, whichever is higher. - */ -#include - -#define DEFAULT_RTC_INT_FREQ 64 -#define RTC_NUM_INTS 1 - -static unsigned long UIE_on; -static unsigned long prev_update_sec; - -static unsigned long AIE_on; -static struct rtc_time alarm_time; - -static unsigned long PIE_on; -static unsigned long PIE_freq = DEFAULT_RTC_INT_FREQ; -static unsigned long PIE_count; - -static unsigned long hpet_rtc_int_freq; /* RTC interrupt frequency */ -static unsigned int hpet_t1_cmp; /* cached comparator register */ - -int is_hpet_enabled(void) -{ - return hpet_address != 0; -} - -/* - * Timer 1 for RTC, we do not use periodic interrupt feature, - * even if HPET supports periodic interrupts on Timer 1. - * The reason being, to set up a periodic interrupt in HPET, we need to - * stop the main counter. And if we do that everytime someone diables/enables - * RTC, we will have adverse effect on main kernel timer running on Timer 0. - * So, for the time being, simulate the periodic interrupt in software. - * - * hpet_rtc_timer_init() is called for the first time and during subsequent - * interuppts reinit happens through hpet_rtc_timer_reinit(). - */ -int hpet_rtc_timer_init(void) -{ - unsigned int cfg, cnt; - unsigned long flags; - - if (!is_hpet_enabled()) - return 0; - /* - * Set the counter 1 and enable the interrupts. - */ - if (PIE_on && (PIE_freq > DEFAULT_RTC_INT_FREQ)) - hpet_rtc_int_freq = PIE_freq; - else - hpet_rtc_int_freq = DEFAULT_RTC_INT_FREQ; - - local_irq_save(flags); - - cnt = hpet_readl(HPET_COUNTER); - cnt += ((hpet_tick*HZ)/hpet_rtc_int_freq); - hpet_writel(cnt, HPET_T1_CMP); - hpet_t1_cmp = cnt; - - cfg = hpet_readl(HPET_T1_CFG); - cfg &= ~HPET_TN_PERIODIC; - cfg |= HPET_TN_ENABLE | HPET_TN_32BIT; - hpet_writel(cfg, HPET_T1_CFG); - - local_irq_restore(flags); - - return 1; -} - -static void hpet_rtc_timer_reinit(void) -{ - unsigned int cfg, cnt, ticks_per_int, lost_ints; - - if (unlikely(!(PIE_on | AIE_on | UIE_on))) { - cfg = hpet_readl(HPET_T1_CFG); - cfg &= ~HPET_TN_ENABLE; - hpet_writel(cfg, HPET_T1_CFG); - return; - } - - if (PIE_on && (PIE_freq > DEFAULT_RTC_INT_FREQ)) - hpet_rtc_int_freq = PIE_freq; - else - hpet_rtc_int_freq = DEFAULT_RTC_INT_FREQ; - - /* It is more accurate to use the comparator value than current count.*/ - ticks_per_int = hpet_tick * HZ / hpet_rtc_int_freq; - hpet_t1_cmp += ticks_per_int; - hpet_writel(hpet_t1_cmp, HPET_T1_CMP); - - /* - * If the interrupt handler was delayed too long, the write above tries - * to schedule the next interrupt in the past and the hardware would - * not interrupt until the counter had wrapped around. - * So we have to check that the comparator wasn't set to a past time. - */ - cnt = hpet_readl(HPET_COUNTER); - if (unlikely((int)(cnt - hpet_t1_cmp) > 0)) { - lost_ints = (cnt - hpet_t1_cmp) / ticks_per_int + 1; - /* Make sure that, even with the time needed to execute - * this code, the next scheduled interrupt has been moved - * back to the future: */ - lost_ints++; - - hpet_t1_cmp += lost_ints * ticks_per_int; - hpet_writel(hpet_t1_cmp, HPET_T1_CMP); - - if (PIE_on) - PIE_count += lost_ints; - - if (printk_ratelimit()) - printk(KERN_WARNING "rtc: lost some interrupts at %ldHz.\n", - hpet_rtc_int_freq); - } -} - -/* - * The functions below are called from rtc driver. - * Return 0 if HPET is not being used. - * Otherwise do the necessary changes and return 1. - */ -int hpet_mask_rtc_irq_bit(unsigned long bit_mask) -{ - if (!is_hpet_enabled()) - return 0; - - if (bit_mask & RTC_UIE) - UIE_on = 0; - if (bit_mask & RTC_PIE) - PIE_on = 0; - if (bit_mask & RTC_AIE) - AIE_on = 0; - - return 1; -} - -int hpet_set_rtc_irq_bit(unsigned long bit_mask) -{ - int timer_init_reqd = 0; - - if (!is_hpet_enabled()) - return 0; - - if (!(PIE_on | AIE_on | UIE_on)) - timer_init_reqd = 1; - - if (bit_mask & RTC_UIE) { - UIE_on = 1; - } - if (bit_mask & RTC_PIE) { - PIE_on = 1; - PIE_count = 0; - } - if (bit_mask & RTC_AIE) { - AIE_on = 1; - } - - if (timer_init_reqd) - hpet_rtc_timer_init(); - - return 1; -} - -int hpet_set_alarm_time(unsigned char hrs, unsigned char min, unsigned char sec) -{ - if (!is_hpet_enabled()) - return 0; - - alarm_time.tm_hour = hrs; - alarm_time.tm_min = min; - alarm_time.tm_sec = sec; - - return 1; -} - -int hpet_set_periodic_freq(unsigned long freq) -{ - if (!is_hpet_enabled()) - return 0; - - PIE_freq = freq; - PIE_count = 0; - - return 1; -} - -int hpet_rtc_dropped_irq(void) -{ - if (!is_hpet_enabled()) - return 0; - - return 1; -} - -irqreturn_t hpet_rtc_interrupt(int irq, void *dev_id) -{ - struct rtc_time curr_time; - unsigned long rtc_int_flag = 0; - int call_rtc_interrupt = 0; - - hpet_rtc_timer_reinit(); - - if (UIE_on | AIE_on) { - rtc_get_rtc_time(&curr_time); - } - if (UIE_on) { - if (curr_time.tm_sec != prev_update_sec) { - /* Set update int info, call real rtc int routine */ - call_rtc_interrupt = 1; - rtc_int_flag = RTC_UF; - prev_update_sec = curr_time.tm_sec; - } - } - if (PIE_on) { - PIE_count++; - if (PIE_count >= hpet_rtc_int_freq/PIE_freq) { - /* Set periodic int info, call real rtc int routine */ - call_rtc_interrupt = 1; - rtc_int_flag |= RTC_PF; - PIE_count = 0; - } - } - if (AIE_on) { - if ((curr_time.tm_sec == alarm_time.tm_sec) && - (curr_time.tm_min == alarm_time.tm_min) && - (curr_time.tm_hour == alarm_time.tm_hour)) { - /* Set alarm int info, call real rtc int routine */ - call_rtc_interrupt = 1; - rtc_int_flag |= RTC_AF; - } - } - if (call_rtc_interrupt) { - rtc_int_flag |= (RTC_IRQF | (RTC_NUM_INTS << 8)); - rtc_interrupt(rtc_int_flag, dev_id); - } - return IRQ_HANDLED; -} -#endif - -static int __init nohpet_setup(char *s) -{ - nohpet = 1; - return 1; -} - -__setup("nohpet", nohpet_setup); Index: linux-rt-rebase.q/arch/x86_64/kernel/i8259.c =================================================================== --- linux-rt-rebase.q.orig/arch/x86_64/kernel/i8259.c +++ linux-rt-rebase.q/arch/x86_64/kernel/i8259.c @@ -96,8 +96,8 @@ static void (*interrupt[NR_VECTORS - FIR */ static int i8259A_auto_eoi; -DEFINE_SPINLOCK(i8259A_lock); static void mask_and_ack_8259A(unsigned int); +DEFINE_RAW_SPINLOCK(i8259A_lock); static struct irq_chip i8259A_chip = { .name = "XT-PIC", @@ -395,7 +395,8 @@ device_initcall(i8259A_init_sysfs); * IRQ2 is cascade interrupt to second interrupt controller */ -static struct irqaction irq2 = { no_action, 0, CPU_MASK_NONE, "cascade", NULL, NULL}; +static struct irqaction irq2 = { no_action, IRQF_NODELAY, CPU_MASK_NONE, "cascade", NULL, NULL}; + DEFINE_PER_CPU(vector_irq_t, vector_irq) = { [0 ... IRQ0_VECTOR - 1] = -1, [IRQ0_VECTOR] = 0, @@ -444,46 +445,6 @@ void __init init_ISA_irqs (void) } } -static void setup_timer_hardware(void) -{ - outb_p(0x34,0x43); /* binary, mode 2, LSB/MSB, ch 0 */ - udelay(10); - outb_p(LATCH & 0xff , 0x40); /* LSB */ - udelay(10); - outb(LATCH >> 8 , 0x40); /* MSB */ -} - -static int timer_resume(struct sys_device *dev) -{ - setup_timer_hardware(); - return 0; -} - -void i8254_timer_resume(void) -{ - setup_timer_hardware(); -} - -static struct sysdev_class timer_sysclass = { - set_kset_name("timer_pit"), - .resume = timer_resume, -}; - -static struct sys_device device_timer = { - .id = 0, - .cls = &timer_sysclass, -}; - -static int __init init_timer_sysfs(void) -{ - int error = sysdev_class_register(&timer_sysclass); - if (!error) - error = sysdev_register(&device_timer); - return error; -} - -device_initcall(init_timer_sysfs); - void __init init_IRQ(void) { int i; @@ -533,12 +494,6 @@ void __init init_IRQ(void) set_intr_gate(SPURIOUS_APIC_VECTOR, spurious_interrupt); set_intr_gate(ERROR_APIC_VECTOR, error_interrupt); - /* - * Set the clock to HZ Hz, we already have a valid - * vector now: - */ - setup_timer_hardware(); - if (!acpi_ioapic) setup_irq(2, &irq2); } Index: linux-rt-rebase.q/arch/x86_64/kernel/io_apic.c =================================================================== --- linux-rt-rebase.q.orig/arch/x86_64/kernel/io_apic.c +++ linux-rt-rebase.q/arch/x86_64/kernel/io_apic.c @@ -90,8 +90,8 @@ int timer_over_8254 __initdata = 1; /* Where if anywhere is the i8259 connect in external int mode */ static struct { int pin, apic; } ioapic_i8259 = { -1, -1 }; -static DEFINE_SPINLOCK(ioapic_lock); -DEFINE_SPINLOCK(vector_lock); +static DEFINE_RAW_SPINLOCK(ioapic_lock); +DEFINE_RAW_SPINLOCK(vector_lock); /* * # of IRQ routing registers @@ -204,6 +204,9 @@ static inline void io_apic_sync(unsigned reg ACTION; \ io_apic_modify(entry->apic, reg); \ FINAL; \ + /* Force POST flush by reading: */ \ + reg = io_apic_read(entry->apic, 0x10 + R + pin*2); \ + \ if (!entry->next) \ break; \ entry = irq_2_pin + entry->next; \ @@ -348,10 +351,11 @@ static void add_pin_to_irq(unsigned int static void name##_IO_APIC_irq (unsigned int irq) \ __DO_ACTION(R, ACTION, FINAL) -DO_ACTION( __mask, 0, |= 0x00010000, io_apic_sync(entry->apic) ) - /* mask = 1 */ -DO_ACTION( __unmask, 0, &= 0xfffeffff, ) - /* mask = 0 */ +DO_ACTION( __mask, 0, |= 0x00010000, ) /* mask = 1 */ +DO_ACTION( __unmask, 0, &= 0xfffeffff, ) /* mask = 0 */ + +DO_ACTION( __pcix_mask, 0, &= 0xffff7fff, ) /* edge */ +DO_ACTION( __pcix_unmask, 0, = (reg & 0xfffeffff) | 0x00008000, ) /* level */ static void mask_IO_APIC_irq (unsigned int irq) { @@ -370,6 +374,23 @@ static void unmask_IO_APIC_irq (unsigned __unmask_IO_APIC_irq(irq); spin_unlock_irqrestore(&ioapic_lock, flags); } +static void pcix_mask_IO_APIC_irq (unsigned int irq) +{ + unsigned long flags; + + spin_lock_irqsave(&ioapic_lock, flags); + __pcix_mask_IO_APIC_irq(irq); + spin_unlock_irqrestore(&ioapic_lock, flags); +} + +static void pcix_unmask_IO_APIC_irq (unsigned int irq) +{ + unsigned long flags; + + spin_lock_irqsave(&ioapic_lock, flags); + __pcix_unmask_IO_APIC_irq(irq); + spin_unlock_irqrestore(&ioapic_lock, flags); +} static void clear_IO_APIC_pin(unsigned int apic, unsigned int pin) { @@ -797,15 +818,18 @@ void __setup_vector_irq(int cpu) static struct irq_chip ioapic_chip; +static struct irq_chip pcix_ioapic_chip; -static void ioapic_register_intr(int irq, unsigned long trigger) +static void ioapic_register_intr(int irq, unsigned long trigger, int pcix) { + struct irq_chip *chip = pcix ? &pcix_ioapic_chip : &ioapic_chip; + if (trigger) - set_irq_chip_and_handler_name(irq, &ioapic_chip, - handle_fasteoi_irq, "fasteoi"); + set_irq_chip_and_handler_name(irq, chip, handle_fasteoi_irq, + pcix ? "pcix-fasteoi" : "fasteoi"); else - set_irq_chip_and_handler_name(irq, &ioapic_chip, - handle_edge_irq, "edge"); + set_irq_chip_and_handler_name(irq, chip, handle_edge_irq, + pcix ? "pcix-edge" : "edge"); } static void setup_IO_APIC_irq(int apic, int pin, unsigned int irq, @@ -849,7 +873,7 @@ static void setup_IO_APIC_irq(int apic, if (trigger) entry.mask = 1; - ioapic_register_intr(irq, trigger); + ioapic_register_intr(irq, trigger, apic > 0); if (irq < 16) disable_8259A_irq(irq); @@ -1431,7 +1455,8 @@ static void ack_apic_level(unsigned int irq_complete_move(irq); #if defined(CONFIG_GENERIC_PENDING_IRQ) || defined(CONFIG_IRQBALANCE) /* If we are moving the irq we need to mask it */ - if (unlikely(irq_desc[irq].status & IRQ_MOVE_PENDING)) { + if (unlikely(irq_desc[irq].status & IRQ_MOVE_PENDING) && + !(irq_desc[irq].status & IRQ_INPROGRESS)) { do_unmask_irq = 1; mask_IO_APIC_irq(irq); } @@ -1478,14 +1503,27 @@ static void ack_apic_level(unsigned int } static struct irq_chip ioapic_chip __read_mostly = { - .name = "IO-APIC", - .startup = startup_ioapic_irq, - .mask = mask_IO_APIC_irq, - .unmask = unmask_IO_APIC_irq, - .ack = ack_apic_edge, - .eoi = ack_apic_level, + .name = "IO-APIC", + .startup = startup_ioapic_irq, + .mask = mask_IO_APIC_irq, + .unmask = unmask_IO_APIC_irq, + .ack = ack_apic_edge, + .eoi = ack_apic_level, +#ifdef CONFIG_SMP + .set_affinity = set_ioapic_affinity_irq, +#endif + .retrigger = ioapic_retrigger_irq, +}; + +static struct irq_chip pcix_ioapic_chip __read_mostly = { + .name = "IO-APIC", + .startup = startup_ioapic_irq, + .mask = pcix_mask_IO_APIC_irq, + .unmask = pcix_unmask_IO_APIC_irq, + .ack = ack_apic_edge, + .eoi = ack_apic_level, #ifdef CONFIG_SMP - .set_affinity = set_ioapic_affinity_irq, + .set_affinity = set_ioapic_affinity_irq, #endif .retrigger = ioapic_retrigger_irq, }; @@ -1682,7 +1720,6 @@ static inline void check_timer(void) */ unmask_IO_APIC_irq(0); if (!no_timer_check && timer_irq_works()) { - nmi_watchdog_default(); if (nmi_watchdog == NMI_IO_APIC) { disable_8259A_irq(0); setup_nmi(); @@ -1708,7 +1745,6 @@ static inline void check_timer(void) setup_ExtINT_IRQ0_pin(apic2, pin2, cfg->vector); if (timer_irq_works()) { apic_printk(APIC_VERBOSE," works.\n"); - nmi_watchdog_default(); if (nmi_watchdog == NMI_IO_APIC) { setup_nmi(); } Index: linux-rt-rebase.q/arch/x86_64/kernel/irq.c =================================================================== --- linux-rt-rebase.q.orig/arch/x86_64/kernel/irq.c +++ linux-rt-rebase.q/arch/x86_64/kernel/irq.c @@ -111,10 +111,18 @@ asmlinkage unsigned int do_IRQ(struct pt unsigned vector = ~regs->orig_rax; unsigned irq; + irq_show_regs_callback(smp_processor_id(), regs); + exit_idle(); irq_enter(); irq = __get_cpu_var(vector_irq)[vector]; +#ifdef CONFIG_EVENT_TRACE + if (irq == trace_user_trigger_irq) + user_trace_start(); +#endif + trace_special(regs->rip, irq, 0); + #ifdef CONFIG_DEBUG_STACKOVERFLOW stack_overflow_check(regs); #endif Index: linux-rt-rebase.q/arch/x86_64/kernel/kprobes.c =================================================================== --- linux-rt-rebase.q.orig/arch/x86_64/kernel/kprobes.c +++ linux-rt-rebase.q/arch/x86_64/kernel/kprobes.c @@ -654,11 +654,9 @@ int __kprobes kprobe_exceptions_notify(s case DIE_GPF: case DIE_PAGE_FAULT: /* kprobe_running() needs smp_processor_id() */ - preempt_disable(); - if (kprobe_running() && + if (per_cpu(current_kprobe, raw_smp_processor_id()) && kprobe_fault_handler(args->regs, args->trapnr)) ret = NOTIFY_STOP; - preempt_enable(); break; default: break; Index: linux-rt-rebase.q/arch/x86_64/kernel/nmi.c =================================================================== --- linux-rt-rebase.q.orig/arch/x86_64/kernel/nmi.c +++ linux-rt-rebase.q/arch/x86_64/kernel/nmi.c @@ -22,11 +22,13 @@ #include #include #include +#include #include #include #include #include +#include int unknown_nmi_panic; int nmi_watchdog_enabled; @@ -44,7 +46,7 @@ atomic_t nmi_active = ATOMIC_INIT(0); / int panic_on_timeout; unsigned int nmi_watchdog = NMI_DEFAULT; -static unsigned int nmi_hz = HZ; +static unsigned int nmi_hz = 1000; static DEFINE_PER_CPU(short, wd_enabled); @@ -52,7 +54,7 @@ static DEFINE_PER_CPU(short, wd_enabled) static int unknown_nmi_panic_callback(struct pt_regs *regs, int cpu); /* Run after command line and cpu_init init, but before all other checks */ -void nmi_watchdog_default(void) +static inline void nmi_watchdog_default(void) { if (nmi_watchdog != NMI_DEFAULT) return; @@ -68,7 +70,9 @@ static int endflag __initdata = 0; */ static __init void nmi_cpu_busy(void *data) { +#ifndef CONFIG_PREEMPT_RT local_irq_enable_in_hardirq(); +#endif /* Intentionally don't use cpu_relax here. This is to make sure that the performance counter really ticks, even if there is a simulator or similar that catches the @@ -302,7 +306,7 @@ void touch_nmi_watchdog(void) unsigned cpu; /* - * Tell other CPUs to reset their alert counters. We cannot + * Tell other CPUs to reset their alert counters. We cannot * do it ourselves because the alert count increase is not * atomic. */ @@ -312,16 +316,54 @@ void touch_nmi_watchdog(void) } } - touch_softlockup_watchdog(); + touch_softlockup_watchdog(); +} + +int nmi_show_regs[NR_CPUS]; + +void nmi_show_all_regs(void) +{ + int i; + + if (system_state == SYSTEM_BOOTING) + return; + + smp_send_nmi_allbutself(); + + for_each_online_cpu(i) + nmi_show_regs[i] = 1; + + for_each_online_cpu(i) { + while (nmi_show_regs[i] == 1) + barrier(); + } +} + +static DEFINE_RAW_SPINLOCK(nmi_print_lock); + +notrace void irq_show_regs_callback(int cpu, struct pt_regs *regs) +{ + if (!nmi_show_regs[cpu]) + return; + + nmi_show_regs[cpu] = 0; + spin_lock(&nmi_print_lock); + printk(KERN_WARNING "NMI show regs on CPU#%d:\n", cpu); + printk(KERN_WARNING "apic_timer_irqs: %d\n", read_pda(apic_timer_irqs)); + show_regs(regs); + spin_unlock(&nmi_print_lock); } -int __kprobes nmi_watchdog_tick(struct pt_regs * regs, unsigned reason) +int notrace __kprobes nmi_watchdog_tick(struct pt_regs * regs, unsigned reason) { int sum; int touched = 0; int cpu = smp_processor_id(); int rc = 0; + irq_show_regs_callback(cpu, regs); + __profile_tick(CPU_PROFILING, regs); + /* check for other users first */ if (notify_die(DIE_NMI, "nmi", regs, reason, 2, SIGINT) == NOTIFY_STOP) { @@ -330,6 +372,7 @@ int __kprobes nmi_watchdog_tick(struct p } sum = read_pda(apic_timer_irqs); + if (__get_cpu_var(nmi_touch)) { __get_cpu_var(nmi_touch) = 0; touched = 1; @@ -358,9 +401,20 @@ int __kprobes nmi_watchdog_tick(struct p * wait a few IRQs (5 seconds) before doing the oops ... */ local_inc(&__get_cpu_var(alert_counter)); - if (local_read(&__get_cpu_var(alert_counter)) == 5*nmi_hz) + if (local_read(&__get_cpu_var(alert_counter)) == 5*nmi_hz) { + int i; + + for_each_online_cpu(i) { + if (i == cpu) + continue; + nmi_show_regs[i] = 1; + while (nmi_show_regs[i] == 1) + cpu_relax(); + } + die_nmi("NMI Watchdog detected LOCKUP on CPU %d\n", regs, panic_on_timeout); + } } else { __get_cpu_var(last_irq_sum) = sum; local_set(&__get_cpu_var(alert_counter), 0); @@ -478,6 +532,13 @@ void __trigger_all_cpu_backtrace(void) } } +void smp_send_nmi_allbutself(void) +{ +#ifdef CONFIG_SMP + send_IPI_allbutself(NMI_VECTOR); +#endif +} + EXPORT_SYMBOL(nmi_active); EXPORT_SYMBOL(nmi_watchdog); EXPORT_SYMBOL(touch_nmi_watchdog); Index: linux-rt-rebase.q/arch/x86_64/kernel/process.c =================================================================== --- linux-rt-rebase.q.orig/arch/x86_64/kernel/process.c +++ linux-rt-rebase.q/arch/x86_64/kernel/process.c @@ -37,6 +37,7 @@ #include #include #include +#include #include #include @@ -115,7 +116,7 @@ static void default_idle(void) */ smp_mb(); local_irq_disable(); - if (!need_resched()) { + if (!need_resched() && !need_resched_delayed()) { /* Enables interrupts one instruction before HLT. x86 special cases this so there is no race. */ safe_halt(); @@ -201,13 +202,14 @@ void cpu_idle (void) current_thread_info()->status |= TS_POLLING; /* endless idle loop with no priority at all */ while (1) { - while (!need_resched()) { + while (!need_resched() && !need_resched_delayed()) { void (*idle)(void); if (__get_cpu_var(cpu_idle_state)) __get_cpu_var(cpu_idle_state) = 0; - check_pgt_cache(); + tick_nohz_stop_sched_tick(); + rmb(); idle = pm_idle; if (!idle) @@ -228,9 +230,14 @@ void cpu_idle (void) __exit_idle(); } - preempt_enable_no_resched(); - schedule(); + tick_nohz_restart_sched_tick(); + local_irq_disable(); + trace_preempt_exit_idle(); + __preempt_enable_no_resched(); + __schedule(); preempt_disable(); + trace_preempt_enter_idle(); + local_irq_enable(); } } @@ -246,10 +253,10 @@ void cpu_idle (void) */ void mwait_idle_with_hints(unsigned long eax, unsigned long ecx) { - if (!need_resched()) { + if (!need_resched() && !need_resched_delayed()) { __monitor((void *)¤t_thread_info()->flags, 0, 0); smp_mb(); - if (!need_resched()) + if (!need_resched() && !need_resched_delayed()) __mwait(eax, ecx); } } @@ -257,12 +264,13 @@ void mwait_idle_with_hints(unsigned long /* Default MONITOR/MWAIT with no hints, used for default C1 state */ static void mwait_idle(void) { - if (!need_resched()) { + if (!need_resched() && !need_resched_delayed()) { __monitor((void *)¤t_thread_info()->flags, 0, 0); smp_mb(); - if (!need_resched()) + if (!need_resched() && !need_resched_delayed()) { + trace_hardirqs_on(); __sti_mwait(0, 0); - else + } else local_irq_enable(); } else { local_irq_enable(); @@ -378,7 +386,7 @@ void exit_thread(void) struct thread_struct *t = &me->thread; if (me->thread.io_bitmap_ptr) { - struct tss_struct *tss = &per_cpu(init_tss, get_cpu()); + struct tss_struct *tss; kfree(t->io_bitmap_ptr); t->io_bitmap_ptr = NULL; @@ -386,6 +394,7 @@ void exit_thread(void) /* * Careful, clear this in the TSS too: */ + tss = &per_cpu(init_tss, get_cpu()); memset(tss->io_bitmap, 0xff, t->io_bitmap_max); t->io_bitmap_max = 0; put_cpu(); Index: linux-rt-rebase.q/arch/x86_64/kernel/setup.c =================================================================== --- linux-rt-rebase.q.orig/arch/x86_64/kernel/setup.c +++ linux-rt-rebase.q/arch/x86_64/kernel/setup.c @@ -333,7 +333,7 @@ void __init setup_arch(char **cmdline_p) reserve_bootmem_generic(SMP_TRAMPOLINE_BASE, 2*PAGE_SIZE); #endif -#ifdef CONFIG_ACPI_SLEEP +#ifdef CONFIG_ACPI /* * Reserve low memory region for sleep support. */ Index: linux-rt-rebase.q/arch/x86_64/kernel/setup64.c =================================================================== --- linux-rt-rebase.q.orig/arch/x86_64/kernel/setup64.c +++ linux-rt-rebase.q/arch/x86_64/kernel/setup64.c @@ -114,7 +114,7 @@ void __init setup_per_cpu_areas(void) } } -void pda_init(int cpu) +void notrace pda_init(int cpu) { struct x8664_pda *pda = cpu_pda(cpu); @@ -191,7 +191,7 @@ unsigned long kernel_eflags; * 'CPU state barrier', nothing should get across. * A lot of state is already set up in PDA init. */ -void __cpuinit cpu_init (void) +void __cpuinit notrace cpu_init (void) { int cpu = stack_smp_processor_id(); struct tss_struct *t = &per_cpu(init_tss, cpu); Index: linux-rt-rebase.q/arch/x86_64/kernel/signal.c =================================================================== --- linux-rt-rebase.q.orig/arch/x86_64/kernel/signal.c +++ linux-rt-rebase.q/arch/x86_64/kernel/signal.c @@ -396,6 +396,13 @@ static void do_signal(struct pt_regs *re int signr; sigset_t *oldset; +#ifdef CONFIG_PREEMPT_RT + /* + * Fully-preemptible kernel does not need interrupts disabled: + */ + local_irq_enable(); + preempt_check_resched(); +#endif /* * We want the common case to go fast, which * is why we may in certain cases get here from Index: linux-rt-rebase.q/arch/x86_64/kernel/smp.c =================================================================== --- linux-rt-rebase.q.orig/arch/x86_64/kernel/smp.c +++ linux-rt-rebase.q/arch/x86_64/kernel/smp.c @@ -15,6 +15,7 @@ #include #include #include +#include #include #include #include @@ -56,7 +57,7 @@ union smp_flush_state { struct mm_struct *flush_mm; unsigned long flush_va; #define FLUSH_ALL -1ULL - spinlock_t tlbstate_lock; + raw_spinlock_t tlbstate_lock; }; char pad[SMP_CACHE_BYTES]; } ____cacheline_aligned; @@ -241,7 +242,6 @@ void flush_tlb_mm (struct mm_struct * mm } if (!cpus_empty(cpu_mask)) flush_tlb_others(cpu_mask, mm, FLUSH_ALL); - check_pgt_cache(); preempt_enable(); } EXPORT_SYMBOL(flush_tlb_mm); @@ -295,10 +295,28 @@ void smp_send_reschedule(int cpu) } /* + * this function sends a 'reschedule' IPI to all other CPUs. + * This is used when RT tasks are starving and other CPUs + * might be able to run them: + */ +void smp_send_reschedule_allbutself(void) +{ + send_IPI_allbutself(RESCHEDULE_VECTOR); +} + +void smp_send_reschedule_allbutself_cpumask(cpumask_t mask) +{ + cpu_clear(smp_processor_id(), mask); + cpus_and(mask, mask, cpu_online_map); + if (!cpus_empty(mask)) + send_IPI_mask(mask, RESCHEDULE_VECTOR); +} + +/* * Structure and data for smp_call_function(). This is designed to minimise * static memory requirements. It also looks cleaner. */ -static DEFINE_SPINLOCK(call_lock); +static DEFINE_RAW_SPINLOCK(call_lock); struct call_data_struct { void (*func) (void *info); Index: linux-rt-rebase.q/arch/x86_64/kernel/smpboot.c =================================================================== --- linux-rt-rebase.q.orig/arch/x86_64/kernel/smpboot.c +++ linux-rt-rebase.q/arch/x86_64/kernel/smpboot.c @@ -223,8 +223,6 @@ void __cpuinit smp_callin(void) local_irq_disable(); Dprintk("Stack at about %p\n",&cpuid); - disable_APIC_timer(); - /* * Save our processor parameters */ @@ -318,7 +316,7 @@ static inline void set_cpu_sibling_map(i /* * Setup code on secondary processor (after comming out of the trampoline) */ -void __cpuinit start_secondary(void) +void __cpuinit notrace start_secondary(void) { /* * Dont put anything before smp_callin(), SMP @@ -333,8 +331,8 @@ void __cpuinit start_secondary(void) barrier(); /* - * Check TSC sync first: - */ + * Check TSC sync first: + */ check_tsc_sync_target(); Dprintk("cpu %d: setting up apic clock\n", smp_processor_id()); @@ -348,8 +346,6 @@ void __cpuinit start_secondary(void) enable_8259A_irq(0); } - enable_APIC_timer(); - /* * The sibling maps must be set before turing the online map on for * this cpu @@ -854,7 +850,6 @@ static int __init smp_sanity_check(unsig */ void __init smp_prepare_cpus(unsigned int max_cpus) { - nmi_watchdog_default(); current_cpu_data = boot_cpu_data; current_thread_info()->cpu = 0; /* needed? */ set_cpu_sibling_map(0); Index: linux-rt-rebase.q/arch/x86_64/kernel/time.c =================================================================== --- linux-rt-rebase.q.orig/arch/x86_64/kernel/time.c +++ linux-rt-rebase.q/arch/x86_64/kernel/time.c @@ -28,11 +28,12 @@ #include #include #include +#include + #ifdef CONFIG_ACPI #include /* for PM timer frequency */ #include #endif -#include #include #include #include @@ -47,12 +48,8 @@ #include #include -static char *timename = NULL; - DEFINE_SPINLOCK(rtc_lock); EXPORT_SYMBOL(rtc_lock); -DEFINE_SPINLOCK(i8253_lock); -EXPORT_SYMBOL(i8253_lock); volatile unsigned long __jiffies __section_jiffies = INITIAL_JIFFIES; @@ -153,45 +150,10 @@ int update_persistent_clock(struct times return set_rtc_mmss(now.tv_sec); } -void main_timer_handler(void) +static irqreturn_t timer_event_interrupt(int irq, void *dev_id) { -/* - * Here we are in the timer irq handler. We have irqs locally disabled (so we - * don't need spin_lock_irqsave()) but we don't know if the timer_bh is running - * on the other CPU, so we need a lock. We also need to lock the vsyscall - * variables, because both do_timer() and us change them -arca+vojtech - */ - - write_seqlock(&xtime_lock); - -/* - * Do the timer stuff. - */ - - do_timer(1); -#ifndef CONFIG_SMP - update_process_times(user_mode(get_irq_regs())); -#endif - -/* - * In the SMP case we use the local APIC timer interrupt to do the profiling, - * except when we simulate SMP mode on a uniprocessor system, in that case we - * have to call the local interrupt handler. - */ - - if (!using_apic_timer) - smp_local_timer_interrupt(); + global_clock_event->event_handler(global_clock_event); - write_sequnlock(&xtime_lock); -} - -static irqreturn_t timer_interrupt(int irq, void *dev_id) -{ - if (apic_runs_main_timer > 1) - return IRQ_HANDLED; - main_timer_handler(); - if (using_apic_timer) - smp_send_timer_broadcast_ipi(); return IRQ_HANDLED; } @@ -292,97 +254,22 @@ static unsigned int __init tsc_calibrate return pmc_now * tsc_khz / (tsc_now - tsc_start); } -/* - * pit_calibrate_tsc() uses the speaker output (channel 2) of - * the PIT. This is better than using the timer interrupt output, - * because we can read the value of the speaker with just one inb(), - * where we need three i/o operations for the interrupt channel. - * We count how many ticks the TSC does in 50 ms. - */ - -static unsigned int __init pit_calibrate_tsc(void) -{ - unsigned long start, end; - unsigned long flags; - - spin_lock_irqsave(&i8253_lock, flags); - - outb((inb(0x61) & ~0x02) | 0x01, 0x61); - - outb(0xb0, 0x43); - outb((PIT_TICK_RATE / (1000 / 50)) & 0xff, 0x42); - outb((PIT_TICK_RATE / (1000 / 50)) >> 8, 0x42); - start = get_cycles_sync(); - while ((inb(0x61) & 0x20) == 0); - end = get_cycles_sync(); - - spin_unlock_irqrestore(&i8253_lock, flags); - - return (end - start) / 50; -} - -#define PIT_MODE 0x43 -#define PIT_CH0 0x40 - -static void __pit_init(int val, u8 mode) -{ - unsigned long flags; - - spin_lock_irqsave(&i8253_lock, flags); - outb_p(mode, PIT_MODE); - outb_p(val & 0xff, PIT_CH0); /* LSB */ - outb_p(val >> 8, PIT_CH0); /* MSB */ - spin_unlock_irqrestore(&i8253_lock, flags); -} - -void __init pit_init(void) -{ - __pit_init(LATCH, 0x34); /* binary, mode 2, LSB/MSB, ch 0 */ -} - -void pit_stop_interrupt(void) -{ - __pit_init(0, 0x30); /* mode 0 */ -} - -void stop_timer_interrupt(void) -{ - char *name; - if (hpet_address) { - name = "HPET"; - hpet_timer_stop_set_go(0); - } else { - name = "PIT"; - pit_stop_interrupt(); - } - printk(KERN_INFO "timer: %s interrupt stopped.\n", name); -} - static struct irqaction irq0 = { - .handler = timer_interrupt, - .flags = IRQF_DISABLED | IRQF_IRQPOLL, + .handler = timer_event_interrupt, + .flags = IRQF_DISABLED | IRQF_IRQPOLL | IRQF_NOBALANCING | + IRQF_NODELAY, .mask = CPU_MASK_NONE, .name = "timer" }; void __init time_init(void) { - if (nohpet) - hpet_address = 0; + if (!hpet_enable()) + setup_pit_timer(); - if (hpet_arch_init()) - hpet_address = 0; + setup_irq(0, &irq0); - if (hpet_use_timer) { - /* set tick_nsec to use the proper rate for HPET */ - tick_nsec = TICK_NSEC_HPET; - tsc_khz = hpet_calibrate_tsc(); - timename = "HPET"; - } else { - pit_init(); - tsc_khz = pit_calibrate_tsc(); - timename = "PIT"; - } + tsc_calibrate(); cpu_khz = tsc_khz; if (cpu_has(&boot_cpu_data, X86_FEATURE_CONSTANT_TSC) && @@ -402,46 +289,4 @@ void __init time_init(void) printk(KERN_INFO "time.c: Detected %d.%03d MHz processor.\n", cpu_khz / 1000, cpu_khz % 1000); init_tsc_clocksource(); - - setup_irq(0, &irq0); -} - -/* - * sysfs support for the timer. - */ - -static int timer_suspend(struct sys_device *dev, pm_message_t state) -{ - return 0; -} - -static int timer_resume(struct sys_device *dev) -{ - if (hpet_address) - hpet_reenable(); - else - i8254_timer_resume(); - return 0; } - -static struct sysdev_class timer_sysclass = { - .resume = timer_resume, - .suspend = timer_suspend, - set_kset_name("timer"), -}; - -/* XXX this sysfs stuff should probably go elsewhere later -john */ -static struct sys_device device_timer = { - .id = 0, - .cls = &timer_sysclass, -}; - -static int time_init_device(void) -{ - int error = sysdev_class_register(&timer_sysclass); - if (!error) - error = sysdev_register(&device_timer); - return error; -} - -device_initcall(time_init_device); Index: linux-rt-rebase.q/arch/x86_64/kernel/traps.c =================================================================== --- linux-rt-rebase.q.orig/arch/x86_64/kernel/traps.c +++ linux-rt-rebase.q/arch/x86_64/kernel/traps.c @@ -219,7 +219,7 @@ void dump_trace(struct task_struct *tsk, unsigned long *stack, struct stacktrace_ops *ops, void *data) { - const unsigned cpu = get_cpu(); + const unsigned cpu = raw_smp_processor_id(); unsigned long *irqstack_end = (unsigned long*)cpu_pda(cpu)->irqstackptr; unsigned used = 0; struct thread_info *tinfo; @@ -310,7 +310,6 @@ void dump_trace(struct task_struct *tsk, tinfo = task_thread_info(tsk); HANDLE_STACK (valid_stack_ptr(tinfo, stack)); #undef HANDLE_STACK - put_cpu(); } EXPORT_SYMBOL(dump_trace); @@ -348,9 +347,13 @@ static struct stacktrace_ops print_trace void show_trace(struct task_struct *tsk, struct pt_regs *regs, unsigned long *stack) { + pause_on_oops_head(); printk("\nCall Trace:\n"); dump_trace(tsk, regs, stack, &print_trace_ops, NULL); printk("\n"); + pause_on_oops_tail(); + debug_show_held_locks(tsk); + print_traces(tsk); } static void @@ -358,7 +361,7 @@ _show_stack(struct task_struct *tsk, str { unsigned long *stack; int i; - const int cpu = smp_processor_id(); + const int cpu = raw_smp_processor_id(); unsigned long *irqstack_end = (unsigned long *) (cpu_pda(cpu)->irqstackptr); unsigned long *irqstack = (unsigned long *) (cpu_pda(cpu)->irqstackptr - IRQSTACKSIZE); Index: linux-rt-rebase.q/arch/x86_64/kernel/tsc.c =================================================================== --- linux-rt-rebase.q.orig/arch/x86_64/kernel/tsc.c +++ linux-rt-rebase.q/arch/x86_64/kernel/tsc.c @@ -6,7 +6,9 @@ #include #include #include +#include +#include #include static int notsc __initdata = 0; @@ -118,7 +120,93 @@ core_initcall(cpufreq_tsc); #endif -static int tsc_unstable = 0; +#define MAX_RETRIES 5 +#define SMI_TRESHOLD 50000 + +/* + * Read TSC and the reference counters. Take care of SMI disturbance + */ +static unsigned long __init tsc_read_refs(unsigned long *pm, + unsigned long *hpet) +{ + unsigned long t1, t2; + int i; + + for (i = 0; i < MAX_RETRIES; i++) { + t1 = get_cycles_sync(); + if (hpet) + *hpet = hpet_readl(HPET_COUNTER) & 0xFFFFFFFF; + else + *pm = acpi_pm_read_early(); + t2 = get_cycles_sync(); + if ((t2 - t1) < SMI_TRESHOLD) + return t2; + } + return ULONG_MAX; +} + +/** + * tsc_calibrate - calibrate the tsc on boot + */ +void __init tsc_calibrate(void) +{ + unsigned long flags, tsc1, tsc2, tr1, tr2, pm1, pm2, hpet1, hpet2; + int hpet = is_hpet_enabled(); + + local_irq_save(flags); + + tsc1 = tsc_read_refs(&pm1, hpet ? &hpet1 : NULL); + + outb((inb(0x61) & ~0x02) | 0x01, 0x61); + + outb(0xb0, 0x43); + outb((CLOCK_TICK_RATE / (1000 / 50)) & 0xff, 0x42); + outb((CLOCK_TICK_RATE / (1000 / 50)) >> 8, 0x42); + tr1 = get_cycles_sync(); + while ((inb(0x61) & 0x20) == 0); + tr2 = get_cycles_sync(); + + tsc2 = tsc_read_refs(&pm2, hpet ? &hpet2 : NULL); + + local_irq_restore(flags); + + /* + * Preset the result with the raw and inaccurate PIT + * calibration value + */ + tsc_khz = (tr2 - tr1) / 50; + + /* hpet or pmtimer available ? */ + if (!hpet && !pm1 && !pm2) { + printk(KERN_INFO "TSC calibrated against PIT\n"); + return; + } + + /* Check, whether the sampling was disturbed by an SMI */ + if (tsc1 == ULONG_MAX || tsc2 == ULONG_MAX) { + printk(KERN_WARNING "TSC calibration disturbed by SMI, " + "using PIT calibration result\n"); + return; + } + + tsc2 = (tsc2 - tsc1) * 1000000L; + + if (hpet) { + printk(KERN_INFO "TSC calibrated against HPET\n"); + if (hpet2 < hpet1) + hpet2 += 0x100000000; + hpet2 -= hpet1; + tsc1 = (hpet2 * hpet_readl(HPET_PERIOD)) / 1000000; + } else { + printk(KERN_INFO "TSC calibrated against PM_TIMER\n"); + if (pm2 < pm1) + pm2 += ACPI_PM_OVRRUN; + pm2 -= pm1; + tsc1 = (pm2 * 1000000000) / PMTMR_TICKS_PER_SEC; + } + + tsc_khz = tsc2 / tsc1; +} /* * Make an educated guess if the TSC is trustworthy and synchronized @@ -159,13 +247,13 @@ __setup("notsc", notsc_setup); /* clock source code: */ -static cycle_t read_tsc(void) +static notrace cycle_t read_tsc(void) { cycle_t ret = (cycle_t)get_cycles_sync(); return ret; } -static cycle_t __vsyscall_fn vread_tsc(void) +static notrace cycle_t __vsyscall_fn vread_tsc(void) { cycle_t ret = (cycle_t)get_cycles_sync(); return ret; Index: linux-rt-rebase.q/arch/x86_64/kernel/tsc_sync.c =================================================================== --- linux-rt-rebase.q.orig/arch/x86_64/kernel/tsc_sync.c +++ linux-rt-rebase.q/arch/x86_64/kernel/tsc_sync.c @@ -33,7 +33,7 @@ static __cpuinitdata atomic_t stop_count * we want to have the fastest, inlined, non-debug version * of a critical section, to be able to prove TSC time-warps: */ -static __cpuinitdata raw_spinlock_t sync_lock = __RAW_SPIN_LOCK_UNLOCKED; +static __cpuinitdata __raw_spinlock_t sync_lock = __RAW_SPIN_LOCK_UNLOCKED; static __cpuinitdata cycles_t last_tsc; static __cpuinitdata cycles_t max_warp; static __cpuinitdata int nr_warps; @@ -97,6 +97,7 @@ static __cpuinit void check_tsc_warp(voi */ void __cpuinit check_tsc_sync_source(int cpu) { + unsigned long flags; int cpus = 2; /* @@ -117,8 +118,11 @@ void __cpuinit check_tsc_sync_source(int /* * Wait for the target to arrive: */ + local_save_flags(flags); + local_irq_enable(); while (atomic_read(&start_count) != cpus-1) cpu_relax(); + local_irq_restore(flags); /* * Trigger the target to continue into the measurement too: */ Index: linux-rt-rebase.q/arch/x86_64/kernel/vsyscall.c =================================================================== --- linux-rt-rebase.q.orig/arch/x86_64/kernel/vsyscall.c +++ linux-rt-rebase.q/arch/x86_64/kernel/vsyscall.c @@ -44,7 +44,7 @@ #include #include -#define __vsyscall(nr) __attribute__ ((unused,__section__(".vsyscall_" #nr))) +#define __vsyscall(nr) __attribute__ ((unused,__section__(".vsyscall_" #nr))) notrace #define __syscall_clobber "r11","rcx","memory" #define __pa_vsymbol(x) \ ({unsigned long v; \ @@ -62,7 +62,7 @@ int __vgetcpu_mode __section_vgetcpu_mod struct vsyscall_gtod_data __vsyscall_gtod_data __section_vsyscall_gtod_data = { - .lock = SEQLOCK_UNLOCKED, + .lock = __RAW_SEQLOCK_UNLOCKED(__vsyscall_gtod_data.lock), .sysctl_enabled = 1, }; @@ -77,6 +77,7 @@ void update_vsyscall(struct timespec *wa vsyscall_gtod_data.clock.mask = clock->mask; vsyscall_gtod_data.clock.mult = clock->mult; vsyscall_gtod_data.clock.shift = clock->shift; + vsyscall_gtod_data.clock.cycle_accumulated = clock->cycle_accumulated; vsyscall_gtod_data.wall_time_sec = wall_time->tv_sec; vsyscall_gtod_data.wall_time_nsec = wall_time->tv_nsec; vsyscall_gtod_data.sys_tz = sys_tz; @@ -114,10 +115,29 @@ static __always_inline long time_syscall static __always_inline void do_vgettimeofday(struct timeval * tv) { - cycle_t now, base, mask, cycle_delta; + cycle_t now, base, accumulated, mask, cycle_delta; unsigned seq; unsigned long mult, shift, nsec; cycle_t (*vread)(void); + + if (likely(__vsyscall_gtod_data.sysctl_enabled == 2)) { + struct timeval tmp; + + do { + barrier(); + tv->tv_sec = __vsyscall_gtod_data.wall_time_sec; + tv->tv_usec = __vsyscall_gtod_data.wall_time_nsec; + barrier(); + tmp.tv_sec = __vsyscall_gtod_data.wall_time_sec; + tmp.tv_usec = __vsyscall_gtod_data.wall_time_nsec; + + } while (tmp.tv_usec != tv->tv_usec || + tmp.tv_sec != tv->tv_sec); + + tv->tv_usec /= NSEC_PER_USEC; + return; + } + do { seq = read_seqbegin(&__vsyscall_gtod_data.lock); @@ -128,6 +148,7 @@ static __always_inline void do_vgettimeo } now = vread(); base = __vsyscall_gtod_data.clock.cycle_last; + accumulated = __vsyscall_gtod_data.clock.cycle_accumulated; mask = __vsyscall_gtod_data.clock.mask; mult = __vsyscall_gtod_data.clock.mult; shift = __vsyscall_gtod_data.clock.shift; @@ -138,6 +159,7 @@ static __always_inline void do_vgettimeo /* calculate interval: */ cycle_delta = (now - base) & mask; + cycle_delta += accumulated; /* convert to nsecs: */ nsec += (cycle_delta * mult) >> shift; Index: linux-rt-rebase.q/arch/x86_64/kernel/x8664_ksyms.c =================================================================== --- linux-rt-rebase.q.orig/arch/x86_64/kernel/x8664_ksyms.c +++ linux-rt-rebase.q/arch/x86_64/kernel/x8664_ksyms.c @@ -11,10 +11,12 @@ EXPORT_SYMBOL(kernel_thread); -EXPORT_SYMBOL(__down_failed); -EXPORT_SYMBOL(__down_failed_interruptible); -EXPORT_SYMBOL(__down_failed_trylock); -EXPORT_SYMBOL(__up_wakeup); +#ifdef CONFIG_RWSEM_GENERIC_SPINLOCK +EXPORT_SYMBOL(__compat_down_failed); +EXPORT_SYMBOL(__compat_down_failed_interruptible); +EXPORT_SYMBOL(__compat_down_failed_trylock); +EXPORT_SYMBOL(__compat_up_wakeup); +#endif EXPORT_SYMBOL(__get_user_1); EXPORT_SYMBOL(__get_user_2); Index: linux-rt-rebase.q/arch/x86_64/lib/thunk.S =================================================================== --- linux-rt-rebase.q.orig/arch/x86_64/lib/thunk.S +++ linux-rt-rebase.q/arch/x86_64/lib/thunk.S @@ -40,15 +40,31 @@ thunk rwsem_wake_thunk,rwsem_wake thunk rwsem_downgrade_thunk,rwsem_downgrade_wake #endif - - thunk __down_failed,__down - thunk_retrax __down_failed_interruptible,__down_interruptible - thunk_retrax __down_failed_trylock,__down_trylock - thunk __up_wakeup,__up + +#ifdef CONFIG_RWSEM_GENERIC_SPINLOCK + thunk __compat_down_failed,__compat_down + thunk_retrax __compat_down_failed_interruptible,__compat_down_interruptible + thunk_retrax __compat_down_failed_trylock,__compat_down_trylock + thunk __compat_up_wakeup,__compat_up +#endif #ifdef CONFIG_TRACE_IRQFLAGS - thunk trace_hardirqs_on_thunk,trace_hardirqs_on - thunk trace_hardirqs_off_thunk,trace_hardirqs_off + /* put return address in rdi (arg1) */ + .macro thunk_ra name,func + .globl \name +\name: + CFI_STARTPROC + SAVE_ARGS + /* SAVE_ARGS pushs 9 elements */ + /* the next element would be the rip */ + movq 9*8(%rsp), %rdi + call \func + jmp restore + CFI_ENDPROC + .endm + + thunk_ra trace_hardirqs_on_thunk,trace_hardirqs_on_caller + thunk_ra trace_hardirqs_off_thunk,trace_hardirqs_off_caller #endif /* SAVE_ARGS below is used only for the .cfi directives it contains. */ Index: linux-rt-rebase.q/arch/x86_64/mm/fault.c =================================================================== --- linux-rt-rebase.q.orig/arch/x86_64/mm/fault.c +++ linux-rt-rebase.q/arch/x86_64/mm/fault.c @@ -371,7 +371,7 @@ asmlinkage void __kprobes do_page_fault( * If we're in an interrupt or have no user * context, we must not take the fault.. */ - if (unlikely(in_atomic() || !mm)) + if (unlikely(in_atomic() || !mm || current->pagefault_disabled)) goto bad_area_nosemaphore; again: Index: linux-rt-rebase.q/arch/x86_64/mm/init.c =================================================================== --- linux-rt-rebase.q.orig/arch/x86_64/mm/init.c +++ linux-rt-rebase.q/arch/x86_64/mm/init.c @@ -53,7 +53,7 @@ EXPORT_SYMBOL(dma_ops); static unsigned long dma_reserve __initdata; -DEFINE_PER_CPU(struct mmu_gather, mmu_gathers); +DEFINE_PER_CPU_LOCKED(struct mmu_gather, mmu_gathers); /* * NOTE: pagetable_init alloc all the fixmap pagetables contiguous on the Index: linux-rt-rebase.q/block/as-iosched.c =================================================================== --- linux-rt-rebase.q.orig/block/as-iosched.c +++ linux-rt-rebase.q/block/as-iosched.c @@ -796,7 +796,7 @@ static void update_write_batch(struct as * as_completed_request is to be called when a request has completed and * returned something to the requesting process, be it an error or data. */ -static void as_completed_request(request_queue_t *q, struct request *rq) +static void as_completed_request(struct request_queue *q, struct request *rq) { struct as_data *ad = q->elevator->elevator_data; @@ -853,7 +853,8 @@ out: * reference unless it replaces the request at somepart of the elevator * (ie. the dispatch queue) */ -static void as_remove_queued_request(request_queue_t *q, struct request *rq) +static void as_remove_queued_request(struct request_queue *q, + struct request *rq) { const int data_dir = rq_is_sync(rq); struct as_data *ad = q->elevator->elevator_data; @@ -978,7 +979,7 @@ static void as_move_to_dispatch(struct a * read/write expire, batch expire, etc, and moves it to the dispatch * queue. Returns 1 if a request was found, 0 otherwise. */ -static int as_dispatch_request(request_queue_t *q, int force) +static int as_dispatch_request(struct request_queue *q, int force) { struct as_data *ad = q->elevator->elevator_data; const int reads = !list_empty(&ad->fifo_list[REQ_SYNC]); @@ -1139,7 +1140,7 @@ fifo_expired: /* * add rq to rbtree and fifo */ -static void as_add_request(request_queue_t *q, struct request *rq) +static void as_add_request(struct request_queue *q, struct request *rq) { struct as_data *ad = q->elevator->elevator_data; int data_dir; @@ -1167,7 +1168,7 @@ static void as_add_request(request_queue RQ_SET_STATE(rq, AS_RQ_QUEUED); } -static void as_activate_request(request_queue_t *q, struct request *rq) +static void as_activate_request(struct request_queue *q, struct request *rq) { WARN_ON(RQ_STATE(rq) != AS_RQ_DISPATCHED); RQ_SET_STATE(rq, AS_RQ_REMOVED); @@ -1175,7 +1176,7 @@ static void as_activate_request(request_ atomic_dec(&RQ_IOC(rq)->aic->nr_dispatched); } -static void as_deactivate_request(request_queue_t *q, struct request *rq) +static void as_deactivate_request(struct request_queue *q, struct request *rq) { WARN_ON(RQ_STATE(rq) != AS_RQ_REMOVED); RQ_SET_STATE(rq, AS_RQ_DISPATCHED); @@ -1189,7 +1190,7 @@ static void as_deactivate_request(reques * is not empty - it is used in the block layer to check for plugging and * merging opportunities */ -static int as_queue_empty(request_queue_t *q) +static int as_queue_empty(struct request_queue *q) { struct as_data *ad = q->elevator->elevator_data; @@ -1198,7 +1199,7 @@ static int as_queue_empty(request_queue_ } static int -as_merge(request_queue_t *q, struct request **req, struct bio *bio) +as_merge(struct request_queue *q, struct request **req, struct bio *bio) { struct as_data *ad = q->elevator->elevator_data; sector_t rb_key = bio->bi_sector + bio_sectors(bio); @@ -1216,7 +1217,8 @@ as_merge(request_queue_t *q, struct requ return ELEVATOR_NO_MERGE; } -static void as_merged_request(request_queue_t *q, struct request *req, int type) +static void as_merged_request(struct request_queue *q, struct request *req, + int type) { struct as_data *ad = q->elevator->elevator_data; @@ -1234,7 +1236,7 @@ static void as_merged_request(request_qu } } -static void as_merged_requests(request_queue_t *q, struct request *req, +static void as_merged_requests(struct request_queue *q, struct request *req, struct request *next) { /* @@ -1285,7 +1287,7 @@ static void as_work_handler(struct work_ spin_unlock_irqrestore(q->queue_lock, flags); } -static int as_may_queue(request_queue_t *q, int rw) +static int as_may_queue(struct request_queue *q, int rw) { int ret = ELV_MQUEUE_MAY; struct as_data *ad = q->elevator->elevator_data; @@ -1318,7 +1320,7 @@ static void as_exit_queue(elevator_t *e) /* * initialize elevator private data (as_data). */ -static void *as_init_queue(request_queue_t *q) +static void *as_init_queue(struct request_queue *q) { struct as_data *ad; Index: linux-rt-rebase.q/block/blktrace.c =================================================================== --- linux-rt-rebase.q.orig/block/blktrace.c +++ linux-rt-rebase.q/block/blktrace.c @@ -231,7 +231,7 @@ static void blk_trace_cleanup(struct blk kfree(bt); } -static int blk_trace_remove(request_queue_t *q) +static int blk_trace_remove(struct request_queue *q) { struct blk_trace *bt; @@ -312,7 +312,7 @@ static struct rchan_callbacks blk_relay_ /* * Setup everything required to start tracing */ -static int blk_trace_setup(request_queue_t *q, struct block_device *bdev, +static int blk_trace_setup(struct request_queue *q, struct block_device *bdev, char __user *arg) { struct blk_user_trace_setup buts; @@ -401,7 +401,7 @@ err: return ret; } -static int blk_trace_startstop(request_queue_t *q, int start) +static int blk_trace_startstop(struct request_queue *q, int start) { struct blk_trace *bt; int ret; @@ -444,7 +444,7 @@ static int blk_trace_startstop(request_q **/ int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg) { - request_queue_t *q; + struct request_queue *q; int ret, start = 0; q = bdev_get_queue(bdev); @@ -479,7 +479,7 @@ int blk_trace_ioctl(struct block_device * @q: the request queue associated with the device * **/ -void blk_trace_shutdown(request_queue_t *q) +void blk_trace_shutdown(struct request_queue *q) { if (q->blk_trace) { blk_trace_startstop(q, 0); Index: linux-rt-rebase.q/block/bsg.c =================================================================== --- linux-rt-rebase.q.orig/block/bsg.c +++ linux-rt-rebase.q/block/bsg.c @@ -37,7 +37,7 @@ #define BSG_VERSION "0.4" struct bsg_device { - request_queue_t *queue; + struct request_queue *queue; spinlock_t lock; struct list_head busy_list; struct list_head done_list; @@ -180,7 +180,7 @@ unlock: return ret; } -static int blk_fill_sgv4_hdr_rq(request_queue_t *q, struct request *rq, +static int blk_fill_sgv4_hdr_rq(struct request_queue *q, struct request *rq, struct sg_io_v4 *hdr, int has_write_perm) { memset(rq->cmd, 0, BLK_MAX_CDB); /* ATAPI hates garbage after CDB */ @@ -214,7 +214,7 @@ static int blk_fill_sgv4_hdr_rq(request_ * Check if sg_io_v4 from user is allowed and valid */ static int -bsg_validate_sgv4_hdr(request_queue_t *q, struct sg_io_v4 *hdr, int *rw) +bsg_validate_sgv4_hdr(struct request_queue *q, struct sg_io_v4 *hdr, int *rw) { int ret = 0; @@ -250,7 +250,7 @@ bsg_validate_sgv4_hdr(request_queue_t *q static struct request * bsg_map_hdr(struct bsg_device *bd, struct sg_io_v4 *hdr) { - request_queue_t *q = bd->queue; + struct request_queue *q = bd->queue; struct request *rq, *next_rq = NULL; int ret, rw; unsigned int dxfer_len; @@ -345,7 +345,7 @@ static void bsg_rq_end_io(struct request * do final setup of a 'bc' and submit the matching 'rq' to the block * layer for io */ -static void bsg_add_command(struct bsg_device *bd, request_queue_t *q, +static void bsg_add_command(struct bsg_device *bd, struct request_queue *q, struct bsg_command *bc, struct request *rq) { rq->sense = bc->sense; @@ -611,7 +611,7 @@ static int __bsg_write(struct bsg_device bc = NULL; ret = 0; while (nr_commands) { - request_queue_t *q = bd->queue; + struct request_queue *q = bd->queue; bc = bsg_alloc_command(bd); if (IS_ERR(bc)) { Index: linux-rt-rebase.q/block/cfq-iosched.c =================================================================== --- linux-rt-rebase.q.orig/block/cfq-iosched.c +++ linux-rt-rebase.q/block/cfq-iosched.c @@ -71,7 +71,7 @@ struct cfq_rb_root { * Per block device queue structure */ struct cfq_data { - request_queue_t *queue; + struct request_queue *queue; /* * rr list of queues with requests and the count of them @@ -197,7 +197,7 @@ CFQ_CFQQ_FNS(slice_new); CFQ_CFQQ_FNS(sync); #undef CFQ_CFQQ_FNS -static void cfq_dispatch_insert(request_queue_t *, struct request *); +static void cfq_dispatch_insert(struct request_queue *, struct request *); static struct cfq_queue *cfq_get_queue(struct cfq_data *, int, struct task_struct *, gfp_t); static struct cfq_io_context *cfq_cic_rb_lookup(struct cfq_data *, @@ -237,7 +237,7 @@ static inline void cfq_schedule_dispatch kblockd_schedule_work(&cfqd->unplug_work); } -static int cfq_queue_empty(request_queue_t *q) +static int cfq_queue_empty(struct request_queue *q) { struct cfq_data *cfqd = q->elevator->elevator_data; @@ -623,7 +623,7 @@ cfq_find_rq_fmerge(struct cfq_data *cfqd return NULL; } -static void cfq_activate_request(request_queue_t *q, struct request *rq) +static void cfq_activate_request(struct request_queue *q, struct request *rq) { struct cfq_data *cfqd = q->elevator->elevator_data; @@ -641,7 +641,7 @@ static void cfq_activate_request(request cfqd->last_position = rq->hard_sector + rq->hard_nr_sectors; } -static void cfq_deactivate_request(request_queue_t *q, struct request *rq) +static void cfq_deactivate_request(struct request_queue *q, struct request *rq) { struct cfq_data *cfqd = q->elevator->elevator_data; @@ -665,7 +665,8 @@ static void cfq_remove_request(struct re } } -static int cfq_merge(request_queue_t *q, struct request **req, struct bio *bio) +static int cfq_merge(struct request_queue *q, struct request **req, + struct bio *bio) { struct cfq_data *cfqd = q->elevator->elevator_data; struct request *__rq; @@ -679,7 +680,7 @@ static int cfq_merge(request_queue_t *q, return ELEVATOR_NO_MERGE; } -static void cfq_merged_request(request_queue_t *q, struct request *req, +static void cfq_merged_request(struct request_queue *q, struct request *req, int type) { if (type == ELEVATOR_FRONT_MERGE) { @@ -690,7 +691,7 @@ static void cfq_merged_request(request_q } static void -cfq_merged_requests(request_queue_t *q, struct request *rq, +cfq_merged_requests(struct request_queue *q, struct request *rq, struct request *next) { /* @@ -703,7 +704,7 @@ cfq_merged_requests(request_queue_t *q, cfq_remove_request(next); } -static int cfq_allow_merge(request_queue_t *q, struct request *rq, +static int cfq_allow_merge(struct request_queue *q, struct request *rq, struct bio *bio) { struct cfq_data *cfqd = q->elevator->elevator_data; @@ -913,7 +914,7 @@ static void cfq_arm_slice_timer(struct c /* * Move request from internal lists to the request queue dispatch list. */ -static void cfq_dispatch_insert(request_queue_t *q, struct request *rq) +static void cfq_dispatch_insert(struct request_queue *q, struct request *rq) { struct cfq_data *cfqd = q->elevator->elevator_data; struct cfq_queue *cfqq = RQ_CFQQ(rq); @@ -1093,7 +1094,7 @@ static int cfq_forced_dispatch(struct cf return dispatched; } -static int cfq_dispatch_requests(request_queue_t *q, int force) +static int cfq_dispatch_requests(struct request_queue *q, int force) { struct cfq_data *cfqd = q->elevator->elevator_data; struct cfq_queue *cfqq; @@ -1214,7 +1215,7 @@ static void cfq_exit_single_io_context(s struct cfq_data *cfqd = cic->key; if (cfqd) { - request_queue_t *q = cfqd->queue; + struct request_queue *q = cfqd->queue; spin_lock_irq(q->queue_lock); __cfq_exit_single_io_context(cfqd, cic); @@ -1775,7 +1776,7 @@ cfq_rq_enqueued(struct cfq_data *cfqd, s } } -static void cfq_insert_request(request_queue_t *q, struct request *rq) +static void cfq_insert_request(struct request_queue *q, struct request *rq) { struct cfq_data *cfqd = q->elevator->elevator_data; struct cfq_queue *cfqq = RQ_CFQQ(rq); @@ -1789,7 +1790,7 @@ static void cfq_insert_request(request_q cfq_rq_enqueued(cfqd, cfqq, rq); } -static void cfq_completed_request(request_queue_t *q, struct request *rq) +static void cfq_completed_request(struct request_queue *q, struct request *rq) { struct cfq_queue *cfqq = RQ_CFQQ(rq); struct cfq_data *cfqd = cfqq->cfqd; @@ -1868,7 +1869,7 @@ static inline int __cfq_may_queue(struct return ELV_MQUEUE_MAY; } -static int cfq_may_queue(request_queue_t *q, int rw) +static int cfq_may_queue(struct request_queue *q, int rw) { struct cfq_data *cfqd = q->elevator->elevator_data; struct task_struct *tsk = current; @@ -1922,7 +1923,7 @@ static void cfq_put_request(struct reque * Allocate cfq data structures associated with this request. */ static int -cfq_set_request(request_queue_t *q, struct request *rq, gfp_t gfp_mask) +cfq_set_request(struct request_queue *q, struct request *rq, gfp_t gfp_mask) { struct cfq_data *cfqd = q->elevator->elevator_data; struct task_struct *tsk = current; @@ -1974,7 +1975,7 @@ static void cfq_kick_queue(struct work_s { struct cfq_data *cfqd = container_of(work, struct cfq_data, unplug_work); - request_queue_t *q = cfqd->queue; + struct request_queue *q = cfqd->queue; unsigned long flags; spin_lock_irqsave(q->queue_lock, flags); @@ -2072,7 +2073,7 @@ static void cfq_put_async_queues(struct static void cfq_exit_queue(elevator_t *e) { struct cfq_data *cfqd = e->elevator_data; - request_queue_t *q = cfqd->queue; + struct request_queue *q = cfqd->queue; cfq_shutdown_timer_wq(cfqd); @@ -2098,7 +2099,7 @@ static void cfq_exit_queue(elevator_t *e kfree(cfqd); } -static void *cfq_init_queue(request_queue_t *q) +static void *cfq_init_queue(struct request_queue *q) { struct cfq_data *cfqd; Index: linux-rt-rebase.q/block/deadline-iosched.c =================================================================== --- linux-rt-rebase.q.orig/block/deadline-iosched.c +++ linux-rt-rebase.q/block/deadline-iosched.c @@ -106,7 +106,7 @@ deadline_add_request(struct request_queu /* * remove rq from rbtree and fifo. */ -static void deadline_remove_request(request_queue_t *q, struct request *rq) +static void deadline_remove_request(struct request_queue *q, struct request *rq) { struct deadline_data *dd = q->elevator->elevator_data; @@ -115,7 +115,7 @@ static void deadline_remove_request(requ } static int -deadline_merge(request_queue_t *q, struct request **req, struct bio *bio) +deadline_merge(struct request_queue *q, struct request **req, struct bio *bio) { struct deadline_data *dd = q->elevator->elevator_data; struct request *__rq; @@ -144,8 +144,8 @@ out: return ret; } -static void deadline_merged_request(request_queue_t *q, struct request *req, - int type) +static void deadline_merged_request(struct request_queue *q, + struct request *req, int type) { struct deadline_data *dd = q->elevator->elevator_data; @@ -159,7 +159,7 @@ static void deadline_merged_request(requ } static void -deadline_merged_requests(request_queue_t *q, struct request *req, +deadline_merged_requests(struct request_queue *q, struct request *req, struct request *next) { /* @@ -185,7 +185,7 @@ deadline_merged_requests(request_queue_t static inline void deadline_move_to_dispatch(struct deadline_data *dd, struct request *rq) { - request_queue_t *q = rq->q; + struct request_queue *q = rq->q; deadline_remove_request(q, rq); elv_dispatch_add_tail(q, rq); @@ -236,7 +236,7 @@ static inline int deadline_check_fifo(st * deadline_dispatch_requests selects the best request according to * read/write expire, fifo_batch, etc */ -static int deadline_dispatch_requests(request_queue_t *q, int force) +static int deadline_dispatch_requests(struct request_queue *q, int force) { struct deadline_data *dd = q->elevator->elevator_data; const int reads = !list_empty(&dd->fifo_list[READ]); @@ -335,7 +335,7 @@ dispatch_request: return 1; } -static int deadline_queue_empty(request_queue_t *q) +static int deadline_queue_empty(struct request_queue *q) { struct deadline_data *dd = q->elevator->elevator_data; @@ -356,7 +356,7 @@ static void deadline_exit_queue(elevator /* * initialize elevator private data (deadline_data). */ -static void *deadline_init_queue(request_queue_t *q) +static void *deadline_init_queue(struct request_queue *q) { struct deadline_data *dd; Index: linux-rt-rebase.q/block/elevator.c =================================================================== --- linux-rt-rebase.q.orig/block/elevator.c +++ linux-rt-rebase.q/block/elevator.c @@ -56,7 +56,7 @@ static const int elv_hash_shift = 6; */ static int elv_iosched_allow_merge(struct request *rq, struct bio *bio) { - request_queue_t *q = rq->q; + struct request_queue *q = rq->q; elevator_t *e = q->elevator; if (e->ops->elevator_allow_merge_fn) @@ -141,12 +141,13 @@ static struct elevator_type *elevator_ge return e; } -static void *elevator_init_queue(request_queue_t *q, struct elevator_queue *eq) +static void *elevator_init_queue(struct request_queue *q, + struct elevator_queue *eq) { return eq->ops->elevator_init_fn(q); } -static void elevator_attach(request_queue_t *q, struct elevator_queue *eq, +static void elevator_attach(struct request_queue *q, struct elevator_queue *eq, void *data) { q->elevator = eq; @@ -172,7 +173,8 @@ __setup("elevator=", elevator_setup); static struct kobj_type elv_ktype; -static elevator_t *elevator_alloc(request_queue_t *q, struct elevator_type *e) +static elevator_t *elevator_alloc(struct request_queue *q, + struct elevator_type *e) { elevator_t *eq; int i; @@ -212,7 +214,7 @@ static void elevator_release(struct kobj kfree(e); } -int elevator_init(request_queue_t *q, char *name) +int elevator_init(struct request_queue *q, char *name) { struct elevator_type *e = NULL; struct elevator_queue *eq; @@ -264,7 +266,7 @@ void elevator_exit(elevator_t *e) EXPORT_SYMBOL(elevator_exit); -static void elv_activate_rq(request_queue_t *q, struct request *rq) +static void elv_activate_rq(struct request_queue *q, struct request *rq) { elevator_t *e = q->elevator; @@ -272,7 +274,7 @@ static void elv_activate_rq(request_queu e->ops->elevator_activate_req_fn(q, rq); } -static void elv_deactivate_rq(request_queue_t *q, struct request *rq) +static void elv_deactivate_rq(struct request_queue *q, struct request *rq) { elevator_t *e = q->elevator; @@ -285,13 +287,13 @@ static inline void __elv_rqhash_del(stru hlist_del_init(&rq->hash); } -static void elv_rqhash_del(request_queue_t *q, struct request *rq) +static void elv_rqhash_del(struct request_queue *q, struct request *rq) { if (ELV_ON_HASH(rq)) __elv_rqhash_del(rq); } -static void elv_rqhash_add(request_queue_t *q, struct request *rq) +static void elv_rqhash_add(struct request_queue *q, struct request *rq) { elevator_t *e = q->elevator; @@ -299,13 +301,13 @@ static void elv_rqhash_add(request_queue hlist_add_head(&rq->hash, &e->hash[ELV_HASH_FN(rq_hash_key(rq))]); } -static void elv_rqhash_reposition(request_queue_t *q, struct request *rq) +static void elv_rqhash_reposition(struct request_queue *q, struct request *rq) { __elv_rqhash_del(rq); elv_rqhash_add(q, rq); } -static struct request *elv_rqhash_find(request_queue_t *q, sector_t offset) +static struct request *elv_rqhash_find(struct request_queue *q, sector_t offset) { elevator_t *e = q->elevator; struct hlist_head *hash_list = &e->hash[ELV_HASH_FN(offset)]; @@ -391,7 +393,7 @@ EXPORT_SYMBOL(elv_rb_find); * entry. rq is sort insted into the dispatch queue. To be used by * specific elevators. */ -void elv_dispatch_sort(request_queue_t *q, struct request *rq) +void elv_dispatch_sort(struct request_queue *q, struct request *rq) { sector_t boundary; struct list_head *entry; @@ -449,7 +451,7 @@ void elv_dispatch_add_tail(struct reques EXPORT_SYMBOL(elv_dispatch_add_tail); -int elv_merge(request_queue_t *q, struct request **req, struct bio *bio) +int elv_merge(struct request_queue *q, struct request **req, struct bio *bio) { elevator_t *e = q->elevator; struct request *__rq; @@ -481,7 +483,7 @@ int elv_merge(request_queue_t *q, struct return ELEVATOR_NO_MERGE; } -void elv_merged_request(request_queue_t *q, struct request *rq, int type) +void elv_merged_request(struct request_queue *q, struct request *rq, int type) { elevator_t *e = q->elevator; @@ -494,7 +496,7 @@ void elv_merged_request(request_queue_t q->last_merge = rq; } -void elv_merge_requests(request_queue_t *q, struct request *rq, +void elv_merge_requests(struct request_queue *q, struct request *rq, struct request *next) { elevator_t *e = q->elevator; @@ -509,7 +511,7 @@ void elv_merge_requests(request_queue_t q->last_merge = rq; } -void elv_requeue_request(request_queue_t *q, struct request *rq) +void elv_requeue_request(struct request_queue *q, struct request *rq) { /* * it already went through dequeue, we need to decrement the @@ -526,7 +528,7 @@ void elv_requeue_request(request_queue_t elv_insert(q, rq, ELEVATOR_INSERT_REQUEUE); } -static void elv_drain_elevator(request_queue_t *q) +static void elv_drain_elevator(struct request_queue *q) { static int printed; while (q->elevator->ops->elevator_dispatch_fn(q, 1)) @@ -540,7 +542,7 @@ static void elv_drain_elevator(request_q } } -void elv_insert(request_queue_t *q, struct request *rq, int where) +void elv_insert(struct request_queue *q, struct request *rq, int where) { struct list_head *pos; unsigned ordseq; @@ -638,7 +640,7 @@ void elv_insert(request_queue_t *q, stru } } -void __elv_add_request(request_queue_t *q, struct request *rq, int where, +void __elv_add_request(struct request_queue *q, struct request *rq, int where, int plug) { if (q->ordcolor) @@ -676,7 +678,7 @@ void __elv_add_request(request_queue_t * EXPORT_SYMBOL(__elv_add_request); -void elv_add_request(request_queue_t *q, struct request *rq, int where, +void elv_add_request(struct request_queue *q, struct request *rq, int where, int plug) { unsigned long flags; @@ -688,7 +690,7 @@ void elv_add_request(request_queue_t *q, EXPORT_SYMBOL(elv_add_request); -static inline struct request *__elv_next_request(request_queue_t *q) +static inline struct request *__elv_next_request(struct request_queue *q) { struct request *rq; @@ -704,7 +706,7 @@ static inline struct request *__elv_next } } -struct request *elv_next_request(request_queue_t *q) +struct request *elv_next_request(struct request_queue *q) { struct request *rq; int ret; @@ -770,7 +772,7 @@ struct request *elv_next_request(request EXPORT_SYMBOL(elv_next_request); -void elv_dequeue_request(request_queue_t *q, struct request *rq) +void elv_dequeue_request(struct request_queue *q, struct request *rq) { BUG_ON(list_empty(&rq->queuelist)); BUG_ON(ELV_ON_HASH(rq)); @@ -788,7 +790,7 @@ void elv_dequeue_request(request_queue_t EXPORT_SYMBOL(elv_dequeue_request); -int elv_queue_empty(request_queue_t *q) +int elv_queue_empty(struct request_queue *q) { elevator_t *e = q->elevator; @@ -803,7 +805,7 @@ int elv_queue_empty(request_queue_t *q) EXPORT_SYMBOL(elv_queue_empty); -struct request *elv_latter_request(request_queue_t *q, struct request *rq) +struct request *elv_latter_request(struct request_queue *q, struct request *rq) { elevator_t *e = q->elevator; @@ -812,7 +814,7 @@ struct request *elv_latter_request(reque return NULL; } -struct request *elv_former_request(request_queue_t *q, struct request *rq) +struct request *elv_former_request(struct request_queue *q, struct request *rq) { elevator_t *e = q->elevator; @@ -821,7 +823,7 @@ struct request *elv_former_request(reque return NULL; } -int elv_set_request(request_queue_t *q, struct request *rq, gfp_t gfp_mask) +int elv_set_request(struct request_queue *q, struct request *rq, gfp_t gfp_mask) { elevator_t *e = q->elevator; @@ -832,7 +834,7 @@ int elv_set_request(request_queue_t *q, return 0; } -void elv_put_request(request_queue_t *q, struct request *rq) +void elv_put_request(struct request_queue *q, struct request *rq) { elevator_t *e = q->elevator; @@ -840,7 +842,7 @@ void elv_put_request(request_queue_t *q, e->ops->elevator_put_req_fn(rq); } -int elv_may_queue(request_queue_t *q, int rw) +int elv_may_queue(struct request_queue *q, int rw) { elevator_t *e = q->elevator; @@ -850,7 +852,7 @@ int elv_may_queue(request_queue_t *q, in return ELV_MQUEUE_MAY; } -void elv_completed_request(request_queue_t *q, struct request *rq) +void elv_completed_request(struct request_queue *q, struct request *rq) { elevator_t *e = q->elevator; @@ -1006,7 +1008,7 @@ EXPORT_SYMBOL_GPL(elv_unregister); * need for the new one. this way we have a chance of going back to the old * one, if the new one fails init for some reason. */ -static int elevator_switch(request_queue_t *q, struct elevator_type *new_e) +static int elevator_switch(struct request_queue *q, struct elevator_type *new_e) { elevator_t *old_elevator, *e; void *data; @@ -1078,7 +1080,8 @@ fail_register: return 0; } -ssize_t elv_iosched_store(request_queue_t *q, const char *name, size_t count) +ssize_t elv_iosched_store(struct request_queue *q, const char *name, + size_t count) { char elevator_name[ELV_NAME_MAX]; size_t len; @@ -1107,7 +1110,7 @@ ssize_t elv_iosched_store(request_queue_ return count; } -ssize_t elv_iosched_show(request_queue_t *q, char *name) +ssize_t elv_iosched_show(struct request_queue *q, char *name) { elevator_t *e = q->elevator; struct elevator_type *elv = e->elevator_type; @@ -1127,7 +1130,8 @@ ssize_t elv_iosched_show(request_queue_t return len; } -struct request *elv_rb_former_request(request_queue_t *q, struct request *rq) +struct request *elv_rb_former_request(struct request_queue *q, + struct request *rq) { struct rb_node *rbprev = rb_prev(&rq->rb_node); @@ -1139,7 +1143,8 @@ struct request *elv_rb_former_request(re EXPORT_SYMBOL(elv_rb_former_request); -struct request *elv_rb_latter_request(request_queue_t *q, struct request *rq) +struct request *elv_rb_latter_request(struct request_queue *q, + struct request *rq) { struct rb_node *rbnext = rb_next(&rq->rb_node); Index: linux-rt-rebase.q/block/ll_rw_blk.c =================================================================== --- linux-rt-rebase.q.orig/block/ll_rw_blk.c +++ linux-rt-rebase.q/block/ll_rw_blk.c @@ -40,7 +40,7 @@ static void blk_unplug_work(struct work_ static void blk_unplug_timeout(unsigned long data); static void drive_stat_acct(struct request *rq, int nr_sectors, int new_io); static void init_request_from_bio(struct request *req, struct bio *bio); -static int __make_request(request_queue_t *q, struct bio *bio); +static int __make_request(struct request_queue *q, struct bio *bio); static struct io_context *current_io_context(gfp_t gfp_flags, int node); /* @@ -121,7 +121,7 @@ static void blk_queue_congestion_thresho struct backing_dev_info *blk_get_backing_dev_info(struct block_device *bdev) { struct backing_dev_info *ret = NULL; - request_queue_t *q = bdev_get_queue(bdev); + struct request_queue *q = bdev_get_queue(bdev); if (q) ret = &q->backing_dev_info; @@ -140,7 +140,7 @@ EXPORT_SYMBOL(blk_get_backing_dev_info); * cdb from the request data for instance. * */ -void blk_queue_prep_rq(request_queue_t *q, prep_rq_fn *pfn) +void blk_queue_prep_rq(struct request_queue *q, prep_rq_fn *pfn) { q->prep_rq_fn = pfn; } @@ -163,14 +163,14 @@ EXPORT_SYMBOL(blk_queue_prep_rq); * no merge_bvec_fn is defined for a queue, and only the fixed limits are * honored. */ -void blk_queue_merge_bvec(request_queue_t *q, merge_bvec_fn *mbfn) +void blk_queue_merge_bvec(struct request_queue *q, merge_bvec_fn *mbfn) { q->merge_bvec_fn = mbfn; } EXPORT_SYMBOL(blk_queue_merge_bvec); -void blk_queue_softirq_done(request_queue_t *q, softirq_done_fn *fn) +void blk_queue_softirq_done(struct request_queue *q, softirq_done_fn *fn) { q->softirq_done_fn = fn; } @@ -199,7 +199,7 @@ EXPORT_SYMBOL(blk_queue_softirq_done); * __bio_kmap_atomic() to get a temporary kernel mapping, or by calling * blk_queue_bounce() to create a buffer in normal memory. **/ -void blk_queue_make_request(request_queue_t * q, make_request_fn * mfn) +void blk_queue_make_request(struct request_queue * q, make_request_fn * mfn) { /* * set defaults @@ -235,7 +235,7 @@ void blk_queue_make_request(request_queu EXPORT_SYMBOL(blk_queue_make_request); -static void rq_init(request_queue_t *q, struct request *rq) +static void rq_init(struct request_queue *q, struct request *rq) { INIT_LIST_HEAD(&rq->queuelist); INIT_LIST_HEAD(&rq->donelist); @@ -272,7 +272,7 @@ static void rq_init(request_queue_t *q, * feature should call this function and indicate so. * **/ -int blk_queue_ordered(request_queue_t *q, unsigned ordered, +int blk_queue_ordered(struct request_queue *q, unsigned ordered, prepare_flush_fn *prepare_flush_fn) { if (ordered & (QUEUE_ORDERED_PREFLUSH | QUEUE_ORDERED_POSTFLUSH) && @@ -311,7 +311,7 @@ EXPORT_SYMBOL(blk_queue_ordered); * to the block layer by defining it through this call. * **/ -void blk_queue_issue_flush_fn(request_queue_t *q, issue_flush_fn *iff) +void blk_queue_issue_flush_fn(struct request_queue *q, issue_flush_fn *iff) { q->issue_flush_fn = iff; } @@ -321,7 +321,7 @@ EXPORT_SYMBOL(blk_queue_issue_flush_fn); /* * Cache flushing for ordered writes handling */ -inline unsigned blk_ordered_cur_seq(request_queue_t *q) +inline unsigned blk_ordered_cur_seq(struct request_queue *q) { if (!q->ordseq) return 0; @@ -330,7 +330,7 @@ inline unsigned blk_ordered_cur_seq(requ unsigned blk_ordered_req_seq(struct request *rq) { - request_queue_t *q = rq->q; + struct request_queue *q = rq->q; BUG_ON(q->ordseq == 0); @@ -357,7 +357,7 @@ unsigned blk_ordered_req_seq(struct requ return QUEUE_ORDSEQ_DONE; } -void blk_ordered_complete_seq(request_queue_t *q, unsigned seq, int error) +void blk_ordered_complete_seq(struct request_queue *q, unsigned seq, int error) { struct request *rq; int uptodate; @@ -401,7 +401,7 @@ static void post_flush_end_io(struct req blk_ordered_complete_seq(rq->q, QUEUE_ORDSEQ_POSTFLUSH, error); } -static void queue_flush(request_queue_t *q, unsigned which) +static void queue_flush(struct request_queue *q, unsigned which) { struct request *rq; rq_end_io_fn *end_io; @@ -425,7 +425,7 @@ static void queue_flush(request_queue_t elv_insert(q, rq, ELEVATOR_INSERT_FRONT); } -static inline struct request *start_ordered(request_queue_t *q, +static inline struct request *start_ordered(struct request_queue *q, struct request *rq) { q->bi_size = 0; @@ -476,7 +476,7 @@ static inline struct request *start_orde return rq; } -int blk_do_ordered(request_queue_t *q, struct request **rqp) +int blk_do_ordered(struct request_queue *q, struct request **rqp) { struct request *rq = *rqp; int is_barrier = blk_fs_request(rq) && blk_barrier_rq(rq); @@ -527,7 +527,7 @@ int blk_do_ordered(request_queue_t *q, s static int flush_dry_bio_endio(struct bio *bio, unsigned int bytes, int error) { - request_queue_t *q = bio->bi_private; + struct request_queue *q = bio->bi_private; /* * This is dry run, restore bio_sector and size. We'll finish @@ -551,7 +551,7 @@ static int flush_dry_bio_endio(struct bi static int ordered_bio_endio(struct request *rq, struct bio *bio, unsigned int nbytes, int error) { - request_queue_t *q = rq->q; + struct request_queue *q = rq->q; bio_end_io_t *endio; void *private; @@ -588,7 +588,7 @@ static int ordered_bio_endio(struct requ * blk_queue_bounce_limit to have lower memory pages allocated as bounce * buffers for doing I/O to pages residing above @page. **/ -void blk_queue_bounce_limit(request_queue_t *q, u64 dma_addr) +void blk_queue_bounce_limit(struct request_queue *q, u64 dma_addr) { unsigned long bounce_pfn = dma_addr >> PAGE_SHIFT; int dma = 0; @@ -624,7 +624,7 @@ EXPORT_SYMBOL(blk_queue_bounce_limit); * Enables a low level driver to set an upper limit on the size of * received requests. **/ -void blk_queue_max_sectors(request_queue_t *q, unsigned int max_sectors) +void blk_queue_max_sectors(struct request_queue *q, unsigned int max_sectors) { if ((max_sectors << 9) < PAGE_CACHE_SIZE) { max_sectors = 1 << (PAGE_CACHE_SHIFT - 9); @@ -651,7 +651,8 @@ EXPORT_SYMBOL(blk_queue_max_sectors); * physical data segments in a request. This would be the largest sized * scatter list the driver could handle. **/ -void blk_queue_max_phys_segments(request_queue_t *q, unsigned short max_segments) +void blk_queue_max_phys_segments(struct request_queue *q, + unsigned short max_segments) { if (!max_segments) { max_segments = 1; @@ -674,7 +675,8 @@ EXPORT_SYMBOL(blk_queue_max_phys_segment * address/length pairs the host adapter can actually give as once * to the device. **/ -void blk_queue_max_hw_segments(request_queue_t *q, unsigned short max_segments) +void blk_queue_max_hw_segments(struct request_queue *q, + unsigned short max_segments) { if (!max_segments) { max_segments = 1; @@ -695,7 +697,7 @@ EXPORT_SYMBOL(blk_queue_max_hw_segments) * Enables a low level driver to set an upper limit on the size of a * coalesced segment **/ -void blk_queue_max_segment_size(request_queue_t *q, unsigned int max_size) +void blk_queue_max_segment_size(struct request_queue *q, unsigned int max_size) { if (max_size < PAGE_CACHE_SIZE) { max_size = PAGE_CACHE_SIZE; @@ -718,7 +720,7 @@ EXPORT_SYMBOL(blk_queue_max_segment_size * even internal read-modify-write operations). Usually the default * of 512 covers most hardware. **/ -void blk_queue_hardsect_size(request_queue_t *q, unsigned short size) +void blk_queue_hardsect_size(struct request_queue *q, unsigned short size) { q->hardsect_size = size; } @@ -735,7 +737,7 @@ EXPORT_SYMBOL(blk_queue_hardsect_size); * @t: the stacking driver (top) * @b: the underlying device (bottom) **/ -void blk_queue_stack_limits(request_queue_t *t, request_queue_t *b) +void blk_queue_stack_limits(struct request_queue *t, struct request_queue *b) { /* zero is "infinity" */ t->max_sectors = min_not_zero(t->max_sectors,b->max_sectors); @@ -756,7 +758,7 @@ EXPORT_SYMBOL(blk_queue_stack_limits); * @q: the request queue for the device * @mask: the memory boundary mask **/ -void blk_queue_segment_boundary(request_queue_t *q, unsigned long mask) +void blk_queue_segment_boundary(struct request_queue *q, unsigned long mask) { if (mask < PAGE_CACHE_SIZE - 1) { mask = PAGE_CACHE_SIZE - 1; @@ -778,7 +780,7 @@ EXPORT_SYMBOL(blk_queue_segment_boundary * this is used when buiding direct io requests for the queue. * **/ -void blk_queue_dma_alignment(request_queue_t *q, int mask) +void blk_queue_dma_alignment(struct request_queue *q, int mask) { q->dma_alignment = mask; } @@ -796,7 +798,7 @@ EXPORT_SYMBOL(blk_queue_dma_alignment); * * no locks need be held. **/ -struct request *blk_queue_find_tag(request_queue_t *q, int tag) +struct request *blk_queue_find_tag(struct request_queue *q, int tag) { return blk_map_queue_find_tag(q->queue_tags, tag); } @@ -840,7 +842,7 @@ static int __blk_free_tags(struct blk_qu * blk_cleanup_queue() will take care of calling this function, if tagging * has been used. So there's no need to call this directly. **/ -static void __blk_queue_free_tags(request_queue_t *q) +static void __blk_queue_free_tags(struct request_queue *q) { struct blk_queue_tag *bqt = q->queue_tags; @@ -877,7 +879,7 @@ EXPORT_SYMBOL(blk_free_tags); * This is used to disabled tagged queuing to a device, yet leave * queue in function. **/ -void blk_queue_free_tags(request_queue_t *q) +void blk_queue_free_tags(struct request_queue *q) { clear_bit(QUEUE_FLAG_QUEUED, &q->queue_flags); } @@ -885,7 +887,7 @@ void blk_queue_free_tags(request_queue_t EXPORT_SYMBOL(blk_queue_free_tags); static int -init_tag_map(request_queue_t *q, struct blk_queue_tag *tags, int depth) +init_tag_map(struct request_queue *q, struct blk_queue_tag *tags, int depth) { struct request **tag_index; unsigned long *tag_map; @@ -955,7 +957,7 @@ EXPORT_SYMBOL(blk_init_tags); * @depth: the maximum queue depth supported * @tags: the tag to use **/ -int blk_queue_init_tags(request_queue_t *q, int depth, +int blk_queue_init_tags(struct request_queue *q, int depth, struct blk_queue_tag *tags) { int rc; @@ -996,7 +998,7 @@ EXPORT_SYMBOL(blk_queue_init_tags); * Notes: * Must be called with the queue lock held. **/ -int blk_queue_resize_tags(request_queue_t *q, int new_depth) +int blk_queue_resize_tags(struct request_queue *q, int new_depth) { struct blk_queue_tag *bqt = q->queue_tags; struct request **tag_index; @@ -1059,7 +1061,7 @@ EXPORT_SYMBOL(blk_queue_resize_tags); * Notes: * queue lock must be held. **/ -void blk_queue_end_tag(request_queue_t *q, struct request *rq) +void blk_queue_end_tag(struct request_queue *q, struct request *rq) { struct blk_queue_tag *bqt = q->queue_tags; int tag = rq->tag; @@ -1111,7 +1113,7 @@ EXPORT_SYMBOL(blk_queue_end_tag); * Notes: * queue lock must be held. **/ -int blk_queue_start_tag(request_queue_t *q, struct request *rq) +int blk_queue_start_tag(struct request_queue *q, struct request *rq) { struct blk_queue_tag *bqt = q->queue_tags; int tag; @@ -1158,7 +1160,7 @@ EXPORT_SYMBOL(blk_queue_start_tag); * Notes: * queue lock must be held. **/ -void blk_queue_invalidate_tags(request_queue_t *q) +void blk_queue_invalidate_tags(struct request_queue *q) { struct blk_queue_tag *bqt = q->queue_tags; struct list_head *tmp, *n; @@ -1205,7 +1207,7 @@ void blk_dump_rq_flags(struct request *r EXPORT_SYMBOL(blk_dump_rq_flags); -void blk_recount_segments(request_queue_t *q, struct bio *bio) +void blk_recount_segments(struct request_queue *q, struct bio *bio) { struct bio_vec *bv, *bvprv = NULL; int i, nr_phys_segs, nr_hw_segs, seg_size, hw_seg_size, cluster; @@ -1267,7 +1269,7 @@ new_hw_segment: } EXPORT_SYMBOL(blk_recount_segments); -static int blk_phys_contig_segment(request_queue_t *q, struct bio *bio, +static int blk_phys_contig_segment(struct request_queue *q, struct bio *bio, struct bio *nxt) { if (!(q->queue_flags & (1 << QUEUE_FLAG_CLUSTER))) @@ -1288,7 +1290,7 @@ static int blk_phys_contig_segment(reque return 0; } -static int blk_hw_contig_segment(request_queue_t *q, struct bio *bio, +static int blk_hw_contig_segment(struct request_queue *q, struct bio *bio, struct bio *nxt) { if (unlikely(!bio_flagged(bio, BIO_SEG_VALID))) @@ -1308,7 +1310,8 @@ static int blk_hw_contig_segment(request * map a request to scatterlist, return number of sg entries setup. Caller * must make sure sg can hold rq->nr_phys_segments entries */ -int blk_rq_map_sg(request_queue_t *q, struct request *rq, struct scatterlist *sg) +int blk_rq_map_sg(struct request_queue *q, struct request *rq, + struct scatterlist *sg) { struct bio_vec *bvec, *bvprv; struct bio *bio; @@ -1361,7 +1364,7 @@ EXPORT_SYMBOL(blk_rq_map_sg); * specific ones if so desired */ -static inline int ll_new_mergeable(request_queue_t *q, +static inline int ll_new_mergeable(struct request_queue *q, struct request *req, struct bio *bio) { @@ -1382,7 +1385,7 @@ static inline int ll_new_mergeable(reque return 1; } -static inline int ll_new_hw_segment(request_queue_t *q, +static inline int ll_new_hw_segment(struct request_queue *q, struct request *req, struct bio *bio) { @@ -1406,7 +1409,7 @@ static inline int ll_new_hw_segment(requ return 1; } -int ll_back_merge_fn(request_queue_t *q, struct request *req, struct bio *bio) +int ll_back_merge_fn(struct request_queue *q, struct request *req, struct bio *bio) { unsigned short max_sectors; int len; @@ -1444,7 +1447,7 @@ int ll_back_merge_fn(request_queue_t *q, } EXPORT_SYMBOL(ll_back_merge_fn); -static int ll_front_merge_fn(request_queue_t *q, struct request *req, +static int ll_front_merge_fn(struct request_queue *q, struct request *req, struct bio *bio) { unsigned short max_sectors; @@ -1483,7 +1486,7 @@ static int ll_front_merge_fn(request_que return ll_new_hw_segment(q, req, bio); } -static int ll_merge_requests_fn(request_queue_t *q, struct request *req, +static int ll_merge_requests_fn(struct request_queue *q, struct request *req, struct request *next) { int total_phys_segments; @@ -1539,9 +1542,9 @@ static int ll_merge_requests_fn(request_ * This is called with interrupts off and no requests on the queue and * with the queue lock held. */ -void blk_plug_device(request_queue_t *q) +void blk_plug_device(struct request_queue *q) { - WARN_ON(!irqs_disabled()); + WARN_ON_NONRT(!irqs_disabled()); /* * don't plug a stopped queue, it must be paired with blk_start_queue() @@ -1562,9 +1565,9 @@ EXPORT_SYMBOL(blk_plug_device); * remove the queue from the plugged list, if present. called with * queue lock held and interrupts disabled. */ -int blk_remove_plug(request_queue_t *q) +int blk_remove_plug(struct request_queue *q) { - WARN_ON(!irqs_disabled()); + WARN_ON_NONRT(!irqs_disabled()); if (!test_and_clear_bit(QUEUE_FLAG_PLUGGED, &q->queue_flags)) return 0; @@ -1578,7 +1581,7 @@ EXPORT_SYMBOL(blk_remove_plug); /* * remove the plug and let it rip.. */ -void __generic_unplug_device(request_queue_t *q) +void __generic_unplug_device(struct request_queue *q) { if (unlikely(blk_queue_stopped(q))) return; @@ -1592,7 +1595,7 @@ EXPORT_SYMBOL(__generic_unplug_device); /** * generic_unplug_device - fire a request queue - * @q: The &request_queue_t in question + * @q: The &struct request_queue in question * * Description: * Linux uses plugging to build bigger requests queues before letting @@ -1601,7 +1604,7 @@ EXPORT_SYMBOL(__generic_unplug_device); * gets unplugged, the request_fn defined for the queue is invoked and * transfers started. **/ -void generic_unplug_device(request_queue_t *q) +void generic_unplug_device(struct request_queue *q) { spin_lock_irq(q->queue_lock); __generic_unplug_device(q); @@ -1612,7 +1615,7 @@ EXPORT_SYMBOL(generic_unplug_device); static void blk_backing_dev_unplug(struct backing_dev_info *bdi, struct page *page) { - request_queue_t *q = bdi->unplug_io_data; + struct request_queue *q = bdi->unplug_io_data; /* * devices don't necessarily have an ->unplug_fn defined @@ -1627,7 +1630,8 @@ static void blk_backing_dev_unplug(struc static void blk_unplug_work(struct work_struct *work) { - request_queue_t *q = container_of(work, request_queue_t, unplug_work); + struct request_queue *q = + container_of(work, struct request_queue, unplug_work); blk_add_trace_pdu_int(q, BLK_TA_UNPLUG_IO, NULL, q->rq.count[READ] + q->rq.count[WRITE]); @@ -1637,7 +1641,7 @@ static void blk_unplug_work(struct work_ static void blk_unplug_timeout(unsigned long data) { - request_queue_t *q = (request_queue_t *)data; + struct request_queue *q = (struct request_queue *)data; blk_add_trace_pdu_int(q, BLK_TA_UNPLUG_TIMER, NULL, q->rq.count[READ] + q->rq.count[WRITE]); @@ -1647,16 +1651,16 @@ static void blk_unplug_timeout(unsigned /** * blk_start_queue - restart a previously stopped queue - * @q: The &request_queue_t in question + * @q: The &struct request_queue in question * * Description: * blk_start_queue() will clear the stop flag on the queue, and call * the request_fn for the queue if it was in a stopped state when * entered. Also see blk_stop_queue(). Queue lock must be held. **/ -void blk_start_queue(request_queue_t *q) +void blk_start_queue(struct request_queue *q) { - WARN_ON(!irqs_disabled()); + WARN_ON_NONRT(!irqs_disabled()); clear_bit(QUEUE_FLAG_STOPPED, &q->queue_flags); @@ -1677,7 +1681,7 @@ EXPORT_SYMBOL(blk_start_queue); /** * blk_stop_queue - stop a queue - * @q: The &request_queue_t in question + * @q: The &struct request_queue in question * * Description: * The Linux block layer assumes that a block driver will consume all @@ -1689,7 +1693,7 @@ EXPORT_SYMBOL(blk_start_queue); * the driver has signalled it's ready to go again. This happens by calling * blk_start_queue() to restart queue operations. Queue lock must be held. **/ -void blk_stop_queue(request_queue_t *q) +void blk_stop_queue(struct request_queue *q) { blk_remove_plug(q); set_bit(QUEUE_FLAG_STOPPED, &q->queue_flags); @@ -1746,7 +1750,7 @@ void blk_run_queue(struct request_queue EXPORT_SYMBOL(blk_run_queue); /** - * blk_cleanup_queue: - release a &request_queue_t when it is no longer needed + * blk_cleanup_queue: - release a &struct request_queue when it is no longer needed * @kobj: the kobj belonging of the request queue to be released * * Description: @@ -1762,7 +1766,8 @@ EXPORT_SYMBOL(blk_run_queue); **/ static void blk_release_queue(struct kobject *kobj) { - request_queue_t *q = container_of(kobj, struct request_queue, kobj); + struct request_queue *q = + container_of(kobj, struct request_queue, kobj); struct request_list *rl = &q->rq; blk_sync_queue(q); @@ -1778,13 +1783,13 @@ static void blk_release_queue(struct kob kmem_cache_free(requestq_cachep, q); } -void blk_put_queue(request_queue_t *q) +void blk_put_queue(struct request_queue *q) { kobject_put(&q->kobj); } EXPORT_SYMBOL(blk_put_queue); -void blk_cleanup_queue(request_queue_t * q) +void blk_cleanup_queue(struct request_queue * q) { mutex_lock(&q->sysfs_lock); set_bit(QUEUE_FLAG_DEAD, &q->queue_flags); @@ -1798,7 +1803,7 @@ void blk_cleanup_queue(request_queue_t * EXPORT_SYMBOL(blk_cleanup_queue); -static int blk_init_free_list(request_queue_t *q) +static int blk_init_free_list(struct request_queue *q) { struct request_list *rl = &q->rq; @@ -1817,7 +1822,7 @@ static int blk_init_free_list(request_qu return 0; } -request_queue_t *blk_alloc_queue(gfp_t gfp_mask) +struct request_queue *blk_alloc_queue(gfp_t gfp_mask) { return blk_alloc_queue_node(gfp_mask, -1); } @@ -1825,9 +1830,9 @@ EXPORT_SYMBOL(blk_alloc_queue); static struct kobj_type queue_ktype; -request_queue_t *blk_alloc_queue_node(gfp_t gfp_mask, int node_id) +struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id) { - request_queue_t *q; + struct request_queue *q; q = kmem_cache_alloc_node(requestq_cachep, gfp_mask | __GFP_ZERO, node_id); @@ -1882,16 +1887,16 @@ EXPORT_SYMBOL(blk_alloc_queue_node); * when the block device is deactivated (such as at module unload). **/ -request_queue_t *blk_init_queue(request_fn_proc *rfn, spinlock_t *lock) +struct request_queue *blk_init_queue(request_fn_proc *rfn, spinlock_t *lock) { return blk_init_queue_node(rfn, lock, -1); } EXPORT_SYMBOL(blk_init_queue); -request_queue_t * +struct request_queue * blk_init_queue_node(request_fn_proc *rfn, spinlock_t *lock, int node_id) { - request_queue_t *q = blk_alloc_queue_node(GFP_KERNEL, node_id); + struct request_queue *q = blk_alloc_queue_node(GFP_KERNEL, node_id); if (!q) return NULL; @@ -1940,7 +1945,7 @@ blk_init_queue_node(request_fn_proc *rfn } EXPORT_SYMBOL(blk_init_queue_node); -int blk_get_queue(request_queue_t *q) +int blk_get_queue(struct request_queue *q) { if (likely(!test_bit(QUEUE_FLAG_DEAD, &q->queue_flags))) { kobject_get(&q->kobj); @@ -1952,7 +1957,7 @@ int blk_get_queue(request_queue_t *q) EXPORT_SYMBOL(blk_get_queue); -static inline void blk_free_request(request_queue_t *q, struct request *rq) +static inline void blk_free_request(struct request_queue *q, struct request *rq) { if (rq->cmd_flags & REQ_ELVPRIV) elv_put_request(q, rq); @@ -1960,7 +1965,7 @@ static inline void blk_free_request(requ } static struct request * -blk_alloc_request(request_queue_t *q, int rw, int priv, gfp_t gfp_mask) +blk_alloc_request(struct request_queue *q, int rw, int priv, gfp_t gfp_mask) { struct request *rq = mempool_alloc(q->rq.rq_pool, gfp_mask); @@ -1988,7 +1993,7 @@ blk_alloc_request(request_queue_t *q, in * ioc_batching returns true if the ioc is a valid batching request and * should be given priority access to a request. */ -static inline int ioc_batching(request_queue_t *q, struct io_context *ioc) +static inline int ioc_batching(struct request_queue *q, struct io_context *ioc) { if (!ioc) return 0; @@ -2009,7 +2014,7 @@ static inline int ioc_batching(request_q * is the behaviour we want though - once it gets a wakeup it should be given * a nice run. */ -static void ioc_set_batching(request_queue_t *q, struct io_context *ioc) +static void ioc_set_batching(struct request_queue *q, struct io_context *ioc) { if (!ioc || ioc_batching(q, ioc)) return; @@ -2018,7 +2023,7 @@ static void ioc_set_batching(request_que ioc->last_waited = jiffies; } -static void __freed_request(request_queue_t *q, int rw) +static void __freed_request(struct request_queue *q, int rw) { struct request_list *rl = &q->rq; @@ -2037,7 +2042,7 @@ static void __freed_request(request_queu * A request has just been released. Account for it, update the full and * congestion status, wake up any waiters. Called under q->queue_lock. */ -static void freed_request(request_queue_t *q, int rw, int priv) +static void freed_request(struct request_queue *q, int rw, int priv) { struct request_list *rl = &q->rq; @@ -2057,7 +2062,7 @@ static void freed_request(request_queue_ * Returns NULL on failure, with queue_lock held. * Returns !NULL on success, with queue_lock *not held*. */ -static struct request *get_request(request_queue_t *q, int rw_flags, +static struct request *get_request(struct request_queue *q, int rw_flags, struct bio *bio, gfp_t gfp_mask) { struct request *rq = NULL; @@ -2162,7 +2167,7 @@ out: * * Called with q->queue_lock held, and returns with it unlocked. */ -static struct request *get_request_wait(request_queue_t *q, int rw_flags, +static struct request *get_request_wait(struct request_queue *q, int rw_flags, struct bio *bio) { const int rw = rw_flags & 0x01; @@ -2204,7 +2209,7 @@ static struct request *get_request_wait( return rq; } -struct request *blk_get_request(request_queue_t *q, int rw, gfp_t gfp_mask) +struct request *blk_get_request(struct request_queue *q, int rw, gfp_t gfp_mask) { struct request *rq; @@ -2234,7 +2239,7 @@ EXPORT_SYMBOL(blk_get_request); * * The queue lock must be held with interrupts disabled. */ -void blk_start_queueing(request_queue_t *q) +void blk_start_queueing(struct request_queue *q) { if (!blk_queue_plugged(q)) q->request_fn(q); @@ -2253,7 +2258,7 @@ EXPORT_SYMBOL(blk_start_queueing); * more, when that condition happens we need to put the request back * on the queue. Must be called with queue lock held. */ -void blk_requeue_request(request_queue_t *q, struct request *rq) +void blk_requeue_request(struct request_queue *q, struct request *rq) { blk_add_trace_rq(q, rq, BLK_TA_REQUEUE); @@ -2284,7 +2289,7 @@ EXPORT_SYMBOL(blk_requeue_request); * of the queue for things like a QUEUE_FULL message from a device, or a * host that is unable to accept a particular command. */ -void blk_insert_request(request_queue_t *q, struct request *rq, +void blk_insert_request(struct request_queue *q, struct request *rq, int at_head, void *data) { int where = at_head ? ELEVATOR_INSERT_FRONT : ELEVATOR_INSERT_BACK; @@ -2330,7 +2335,7 @@ static int __blk_rq_unmap_user(struct bi return ret; } -static int __blk_rq_map_user(request_queue_t *q, struct request *rq, +static int __blk_rq_map_user(struct request_queue *q, struct request *rq, void __user *ubuf, unsigned int len) { unsigned long uaddr; @@ -2403,8 +2408,8 @@ unmap_bio: * original bio must be passed back in to blk_rq_unmap_user() for proper * unmapping. */ -int blk_rq_map_user(request_queue_t *q, struct request *rq, void __user *ubuf, - unsigned long len) +int blk_rq_map_user(struct request_queue *q, struct request *rq, + void __user *ubuf, unsigned long len) { unsigned long bytes_read = 0; struct bio *bio = NULL; @@ -2470,7 +2475,7 @@ EXPORT_SYMBOL(blk_rq_map_user); * original bio must be passed back in to blk_rq_unmap_user() for proper * unmapping. */ -int blk_rq_map_user_iov(request_queue_t *q, struct request *rq, +int blk_rq_map_user_iov(struct request_queue *q, struct request *rq, struct sg_iovec *iov, int iov_count, unsigned int len) { struct bio *bio; @@ -2540,7 +2545,7 @@ EXPORT_SYMBOL(blk_rq_unmap_user); * @len: length of user data * @gfp_mask: memory allocation flags */ -int blk_rq_map_kern(request_queue_t *q, struct request *rq, void *kbuf, +int blk_rq_map_kern(struct request_queue *q, struct request *rq, void *kbuf, unsigned int len, gfp_t gfp_mask) { struct bio *bio; @@ -2577,7 +2582,7 @@ EXPORT_SYMBOL(blk_rq_map_kern); * Insert a fully prepared request at the back of the io scheduler queue * for execution. Don't wait for completion. */ -void blk_execute_rq_nowait(request_queue_t *q, struct gendisk *bd_disk, +void blk_execute_rq_nowait(struct request_queue *q, struct gendisk *bd_disk, struct request *rq, int at_head, rq_end_io_fn *done) { @@ -2605,7 +2610,7 @@ EXPORT_SYMBOL_GPL(blk_execute_rq_nowait) * Insert a fully prepared request at the back of the io scheduler queue * for execution and wait for completion. */ -int blk_execute_rq(request_queue_t *q, struct gendisk *bd_disk, +int blk_execute_rq(struct request_queue *q, struct gendisk *bd_disk, struct request *rq, int at_head) { DECLARE_COMPLETION_ONSTACK(wait); @@ -2648,7 +2653,7 @@ EXPORT_SYMBOL(blk_execute_rq); */ int blkdev_issue_flush(struct block_device *bdev, sector_t *error_sector) { - request_queue_t *q; + struct request_queue *q; if (bdev->bd_disk == NULL) return -ENXIO; @@ -2684,7 +2689,7 @@ static void drive_stat_acct(struct reque * queue lock is held and interrupts disabled, as we muck with the * request queue list. */ -static inline void add_request(request_queue_t * q, struct request * req) +static inline void add_request(struct request_queue * q, struct request * req) { drive_stat_acct(req, req->nr_sectors, 1); @@ -2730,7 +2735,7 @@ EXPORT_SYMBOL_GPL(disk_round_stats); /* * queue lock must be held */ -void __blk_put_request(request_queue_t *q, struct request *req) +void __blk_put_request(struct request_queue *q, struct request *req) { if (unlikely(!q)) return; @@ -2760,7 +2765,7 @@ EXPORT_SYMBOL_GPL(__blk_put_request); void blk_put_request(struct request *req) { unsigned long flags; - request_queue_t *q = req->q; + struct request_queue *q = req->q; /* * Gee, IDE calls in w/ NULL q. Fix IDE and remove the @@ -2798,7 +2803,7 @@ EXPORT_SYMBOL(blk_end_sync_rq); /* * Has to be called with the request spinlock acquired */ -static int attempt_merge(request_queue_t *q, struct request *req, +static int attempt_merge(struct request_queue *q, struct request *req, struct request *next) { if (!rq_mergeable(req) || !rq_mergeable(next)) @@ -2851,7 +2856,8 @@ static int attempt_merge(request_queue_t return 1; } -static inline int attempt_back_merge(request_queue_t *q, struct request *rq) +static inline int attempt_back_merge(struct request_queue *q, + struct request *rq) { struct request *next = elv_latter_request(q, rq); @@ -2861,7 +2867,8 @@ static inline int attempt_back_merge(req return 0; } -static inline int attempt_front_merge(request_queue_t *q, struct request *rq) +static inline int attempt_front_merge(struct request_queue *q, + struct request *rq) { struct request *prev = elv_former_request(q, rq); @@ -2905,7 +2912,7 @@ static void init_request_from_bio(struct req->start_time = jiffies; } -static int __make_request(request_queue_t *q, struct bio *bio) +static int __make_request(struct request_queue *q, struct bio *bio) { struct request *req; int el_ret, nr_sectors, barrier, err; @@ -3119,7 +3126,7 @@ static inline int should_fail_request(st */ static inline void __generic_make_request(struct bio *bio) { - request_queue_t *q; + struct request_queue *q; sector_t maxsector; sector_t old_sector; int ret, nr_sectors = bio_sectors(bio); @@ -3312,7 +3319,7 @@ static void blk_recalc_rq_segments(struc struct bio *bio, *prevbio = NULL; int nr_phys_segs, nr_hw_segs; unsigned int phys_size, hw_size; - request_queue_t *q = rq->q; + struct request_queue *q = rq->q; if (!rq->bio) return; @@ -3658,7 +3665,8 @@ void end_request(struct request *req, in EXPORT_SYMBOL(end_request); -void blk_rq_bio_prep(request_queue_t *q, struct request *rq, struct bio *bio) +void blk_rq_bio_prep(struct request_queue *q, struct request *rq, + struct bio *bio) { /* first two bits are identical in rq->cmd_flags and bio->bi_rw */ rq->cmd_flags |= (bio->bi_rw & 3); @@ -3701,7 +3709,7 @@ int __init blk_dev_init(void) sizeof(struct request), 0, SLAB_PANIC, NULL); requestq_cachep = kmem_cache_create("blkdev_queue", - sizeof(request_queue_t), 0, SLAB_PANIC, NULL); + sizeof(struct request_queue), 0, SLAB_PANIC, NULL); iocontext_cachep = kmem_cache_create("blkdev_ioc", sizeof(struct io_context), 0, SLAB_PANIC, NULL); @@ -4021,7 +4029,8 @@ static ssize_t queue_attr_show(struct kobject *kobj, struct attribute *attr, char *page) { struct queue_sysfs_entry *entry = to_queue(attr); - request_queue_t *q = container_of(kobj, struct request_queue, kobj); + struct request_queue *q = + container_of(kobj, struct request_queue, kobj); ssize_t res; if (!entry->show) @@ -4041,7 +4050,7 @@ queue_attr_store(struct kobject *kobj, s const char *page, size_t length) { struct queue_sysfs_entry *entry = to_queue(attr); - request_queue_t *q = container_of(kobj, struct request_queue, kobj); + struct request_queue *q = container_of(kobj, struct request_queue, kobj); ssize_t res; @@ -4072,7 +4081,7 @@ int blk_register_queue(struct gendisk *d { int ret; - request_queue_t *q = disk->queue; + struct request_queue *q = disk->queue; if (!q || !q->request_fn) return -ENXIO; @@ -4097,7 +4106,7 @@ int blk_register_queue(struct gendisk *d void blk_unregister_queue(struct gendisk *disk) { - request_queue_t *q = disk->queue; + struct request_queue *q = disk->queue; if (q && q->request_fn) { elv_unregister_queue(q); Index: linux-rt-rebase.q/block/noop-iosched.c =================================================================== --- linux-rt-rebase.q.orig/block/noop-iosched.c +++ linux-rt-rebase.q/block/noop-iosched.c @@ -11,13 +11,13 @@ struct noop_data { struct list_head queue; }; -static void noop_merged_requests(request_queue_t *q, struct request *rq, +static void noop_merged_requests(struct request_queue *q, struct request *rq, struct request *next) { list_del_init(&next->queuelist); } -static int noop_dispatch(request_queue_t *q, int force) +static int noop_dispatch(struct request_queue *q, int force) { struct noop_data *nd = q->elevator->elevator_data; @@ -31,14 +31,14 @@ static int noop_dispatch(request_queue_t return 0; } -static void noop_add_request(request_queue_t *q, struct request *rq) +static void noop_add_request(struct request_queue *q, struct request *rq) { struct noop_data *nd = q->elevator->elevator_data; list_add_tail(&rq->queuelist, &nd->queue); } -static int noop_queue_empty(request_queue_t *q) +static int noop_queue_empty(struct request_queue *q) { struct noop_data *nd = q->elevator->elevator_data; @@ -46,7 +46,7 @@ static int noop_queue_empty(request_queu } static struct request * -noop_former_request(request_queue_t *q, struct request *rq) +noop_former_request(struct request_queue *q, struct request *rq) { struct noop_data *nd = q->elevator->elevator_data; @@ -56,7 +56,7 @@ noop_former_request(request_queue_t *q, } static struct request * -noop_latter_request(request_queue_t *q, struct request *rq) +noop_latter_request(struct request_queue *q, struct request *rq) { struct noop_data *nd = q->elevator->elevator_data; @@ -65,7 +65,7 @@ noop_latter_request(request_queue_t *q, return list_entry(rq->queuelist.next, struct request, queuelist); } -static void *noop_init_queue(request_queue_t *q) +static void *noop_init_queue(struct request_queue *q) { struct noop_data *nd; Index: linux-rt-rebase.q/block/scsi_ioctl.c =================================================================== --- linux-rt-rebase.q.orig/block/scsi_ioctl.c +++ linux-rt-rebase.q/block/scsi_ioctl.c @@ -49,22 +49,22 @@ static int sg_get_version(int __user *p) return put_user(sg_version_num, p); } -static int scsi_get_idlun(request_queue_t *q, int __user *p) +static int scsi_get_idlun(struct request_queue *q, int __user *p) { return put_user(0, p); } -static int scsi_get_bus(request_queue_t *q, int __user *p) +static int scsi_get_bus(struct request_queue *q, int __user *p) { return put_user(0, p); } -static int sg_get_timeout(request_queue_t *q) +static int sg_get_timeout(struct request_queue *q) { return q->sg_timeout / (HZ / USER_HZ); } -static int sg_set_timeout(request_queue_t *q, int __user *p) +static int sg_set_timeout(struct request_queue *q, int __user *p) { int timeout, err = get_user(timeout, p); @@ -74,14 +74,14 @@ static int sg_set_timeout(request_queue_ return err; } -static int sg_get_reserved_size(request_queue_t *q, int __user *p) +static int sg_get_reserved_size(struct request_queue *q, int __user *p) { unsigned val = min(q->sg_reserved_size, q->max_sectors << 9); return put_user(val, p); } -static int sg_set_reserved_size(request_queue_t *q, int __user *p) +static int sg_set_reserved_size(struct request_queue *q, int __user *p) { int size, err = get_user(size, p); @@ -101,7 +101,7 @@ static int sg_set_reserved_size(request_ * will always return that we are ATAPI even for a real SCSI drive, I'm not * so sure this is worth doing anything about (why would you care??) */ -static int sg_emulated_host(request_queue_t *q, int __user *p) +static int sg_emulated_host(struct request_queue *q, int __user *p) { return put_user(1, p); } @@ -214,7 +214,7 @@ int blk_verify_command(unsigned char *cm } EXPORT_SYMBOL_GPL(blk_verify_command); -static int blk_fill_sghdr_rq(request_queue_t *q, struct request *rq, +static int blk_fill_sghdr_rq(struct request_queue *q, struct request *rq, struct sg_io_hdr *hdr, int has_write_perm) { memset(rq->cmd, 0, BLK_MAX_CDB); /* ATAPI hates garbage after CDB */ @@ -286,7 +286,7 @@ static int blk_complete_sghdr_rq(struct return r; } -static int sg_io(struct file *file, request_queue_t *q, +static int sg_io(struct file *file, struct request_queue *q, struct gendisk *bd_disk, struct sg_io_hdr *hdr) { unsigned long start_time; @@ -519,7 +519,8 @@ error: EXPORT_SYMBOL_GPL(sg_scsi_ioctl); /* Send basic block requests */ -static int __blk_send_generic(request_queue_t *q, struct gendisk *bd_disk, int cmd, int data) +static int __blk_send_generic(struct request_queue *q, struct gendisk *bd_disk, + int cmd, int data) { struct request *rq; int err; @@ -539,7 +540,8 @@ static int __blk_send_generic(request_qu return err; } -static inline int blk_send_start_stop(request_queue_t *q, struct gendisk *bd_disk, int data) +static inline int blk_send_start_stop(struct request_queue *q, + struct gendisk *bd_disk, int data) { return __blk_send_generic(q, bd_disk, GPCMD_START_STOP_UNIT, data); } Index: linux-rt-rebase.q/drivers/Makefile =================================================================== --- linux-rt-rebase.q.orig/drivers/Makefile +++ linux-rt-rebase.q/drivers/Makefile @@ -75,6 +75,7 @@ obj-$(CONFIG_MCA) += mca/ obj-$(CONFIG_EISA) += eisa/ obj-$(CONFIG_LGUEST_GUEST) += lguest/ obj-$(CONFIG_CPU_FREQ) += cpufreq/ +obj-$(CONFIG_CPU_IDLE) += cpuidle/ obj-$(CONFIG_MMC) += mmc/ obj-$(CONFIG_NEW_LEDS) += leds/ obj-$(CONFIG_INFINIBAND) += infiniband/ Index: linux-rt-rebase.q/drivers/acorn/block/fd1772.c =================================================================== --- linux-rt-rebase.q.orig/drivers/acorn/block/fd1772.c +++ linux-rt-rebase.q/drivers/acorn/block/fd1772.c @@ -372,7 +372,7 @@ static int fd_test_drive_present(int dri static void config_types(void); static int floppy_open(struct inode *inode, struct file *filp); static int floppy_release(struct inode *inode, struct file *filp); -static void do_fd_request(request_queue_t *); +static void do_fd_request(struct request_queue *); /************************* End of Prototypes **************************/ @@ -1271,7 +1271,7 @@ static void fd1772_checkint(void) } } -static void do_fd_request(request_queue_t* q) +static void do_fd_request(struct request_queue* q) { unsigned long flags; Index: linux-rt-rebase.q/drivers/acorn/block/mfmhd.c =================================================================== --- linux-rt-rebase.q.orig/drivers/acorn/block/mfmhd.c +++ linux-rt-rebase.q/drivers/acorn/block/mfmhd.c @@ -924,7 +924,7 @@ static void mfm_request(void) DBG("mfm_request: Dropping out bottom\n"); } -static void do_mfm_request(request_queue_t *q) +static void do_mfm_request(struct request_queue *q) { DBG("do_mfm_request: about to mfm_request\n"); mfm_request(); Index: linux-rt-rebase.q/drivers/acpi/Kconfig =================================================================== --- linux-rt-rebase.q.orig/drivers/acpi/Kconfig +++ linux-rt-rebase.q/drivers/acpi/Kconfig @@ -11,6 +11,9 @@ menuconfig ACPI depends on PCI depends on PM select PNP + # for sleep + select HOTPLUG_CPU if X86 && SMP + select SUSPEND_SMP if X86 && SMP default y ---help--- Advanced Configuration and Power Interface (ACPI) support for @@ -42,51 +45,26 @@ menuconfig ACPI if ACPI -config ACPI_SLEEP - bool "Sleep States" - depends on X86 && (!SMP || SUSPEND_SMP) - default y +config ACPI_PROCFS + bool "Deprecated /proc/acpi files" + depends on PROC_FS ---help--- - This option adds support for ACPI suspend states. - - With this option, you will be able to put the system "to sleep". - Sleep states are low power states for the system and devices. All - of the system operating state is saved to either memory or disk - (depending on the state), to allow the system to resume operation - quickly at your request. - - Although this option sounds really nifty, barely any of the device - drivers have been converted to the new driver model and hence few - have proper power management support. - - This option is not recommended for anyone except those doing driver - power management development. - -config ACPI_SLEEP_PROC_FS - bool - depends on ACPI_SLEEP && PROC_FS - default y + For backwards compatibility, this option allows + depricated /proc/acpi/ files to exist, even when + they have been replaced by functions in /sys. + The deprecated files (and their replacements) include: + + /proc/acpi/sleep (/sys/power/state) + /proc/acpi/info (/sys/modules/acpi/parameters/acpica_version) + /proc/acpi/dsdt (/sys/firmware/acpi/tables/DSDT) + /proc/acpi/fadt (/sys/firmware/acpi/tables/FACP) + /proc/acpi/debug_layer (/sys/module/acpi/parameters/debug_layer) + /proc/acpi/debug_level (/sys/module/acpi/parameters/debug_level) -config ACPI_SLEEP_PROC_SLEEP - bool "/proc/acpi/sleep (deprecated)" - depends on ACPI_SLEEP_PROC_FS - default n - ---help--- - Create /proc/acpi/sleep - Deprecated by /sys/power/state + This option has no effect on /proc/acpi/ files + and functions which do not yet exist in /sys. -config ACPI_PROCFS - bool "Procfs interface (deprecated)" - default y - ---help--- - The Procfs interface for ACPI is made optional for backward compatibility. - As the same functions are duplicated in the sysfs interface - and this proc interface will be removed some time later, - it's marked as deprecated. - ( /proc/acpi/debug_layer && debug_level are deprecated by - /sys/module/acpi/parameters/debug_layer && debug_level. - /proc/acpi/info is deprecated by - /sys/module/acpi/parameters/acpica_version ) + Say N to delete /proc/acpi/ files that have moved to /sys/ config ACPI_AC tristate "AC Adapter" Index: linux-rt-rebase.q/drivers/acpi/ac.c =================================================================== --- linux-rt-rebase.q.orig/drivers/acpi/ac.c +++ linux-rt-rebase.q/drivers/acpi/ac.c @@ -34,7 +34,6 @@ #define ACPI_AC_COMPONENT 0x00020000 #define ACPI_AC_CLASS "ac_adapter" -#define ACPI_AC_HID "ACPI0003" #define ACPI_AC_DEVICE_NAME "AC Adapter" #define ACPI_AC_FILE_STATE "state" #define ACPI_AC_NOTIFY_STATUS 0x80 @@ -56,10 +55,16 @@ static int acpi_ac_add(struct acpi_devic static int acpi_ac_remove(struct acpi_device *device, int type); static int acpi_ac_open_fs(struct inode *inode, struct file *file); +const static struct acpi_device_id ac_device_ids[] = { + {"ACPI0003", 0}, + {"", 0}, +}; +MODULE_DEVICE_TABLE(acpi, ac_device_ids); + static struct acpi_driver acpi_ac_driver = { .name = "ac", .class = ACPI_AC_CLASS, - .ids = ACPI_AC_HID, + .ids = ac_device_ids, .ops = { .add = acpi_ac_add, .remove = acpi_ac_remove, Index: linux-rt-rebase.q/drivers/acpi/acpi_memhotplug.c =================================================================== --- linux-rt-rebase.q.orig/drivers/acpi/acpi_memhotplug.c +++ linux-rt-rebase.q/drivers/acpi/acpi_memhotplug.c @@ -53,10 +53,16 @@ static int acpi_memory_device_add(struct static int acpi_memory_device_remove(struct acpi_device *device, int type); static int acpi_memory_device_start(struct acpi_device *device); +static const struct acpi_device_id memory_device_ids[] = { + {ACPI_MEMORY_DEVICE_HID, 0}, + {"", 0}, +}; +MODULE_DEVICE_TABLE(acpi, memory_device_ids); + static struct acpi_driver acpi_memory_device_driver = { .name = "acpi_memhotplug", .class = ACPI_MEMORY_DEVICE_CLASS, - .ids = ACPI_MEMORY_DEVICE_HID, + .ids = memory_device_ids, .ops = { .add = acpi_memory_device_add, .remove = acpi_memory_device_remove, Index: linux-rt-rebase.q/drivers/acpi/asus_acpi.c =================================================================== --- linux-rt-rebase.q.orig/drivers/acpi/asus_acpi.c +++ linux-rt-rebase.q/drivers/acpi/asus_acpi.c @@ -56,7 +56,6 @@ #define ACPI_HOTK_NAME "Asus Laptop ACPI Extras Driver" #define ACPI_HOTK_CLASS "hotkey" #define ACPI_HOTK_DEVICE_NAME "Hotkey" -#define ACPI_HOTK_HID "ATK0100" /* * Some events we use, same for all Asus @@ -426,14 +425,20 @@ static struct acpi_table_header *asus_in static struct asus_hotk *hotk; /* - * The hotkey driver declaration + * The hotkey driver and autoloading declaration */ static int asus_hotk_add(struct acpi_device *device); static int asus_hotk_remove(struct acpi_device *device, int type); +static const struct acpi_device_id asus_device_ids[] = { + {"ATK0100", 0}, + {"", 0}, +}; +MODULE_DEVICE_TABLE(acpi, asus_device_ids); + static struct acpi_driver asus_hotk_driver = { .name = "asus_acpi", .class = ACPI_HOTK_CLASS, - .ids = ACPI_HOTK_HID, + .ids = asus_device_ids, .ops = { .add = asus_hotk_add, .remove = asus_hotk_remove, Index: linux-rt-rebase.q/drivers/acpi/battery.c =================================================================== --- linux-rt-rebase.q.orig/drivers/acpi/battery.c +++ linux-rt-rebase.q/drivers/acpi/battery.c @@ -41,7 +41,6 @@ #define ACPI_BATTERY_COMPONENT 0x00040000 #define ACPI_BATTERY_CLASS "battery" -#define ACPI_BATTERY_HID "PNP0C0A" #define ACPI_BATTERY_DEVICE_NAME "Battery" #define ACPI_BATTERY_NOTIFY_STATUS 0x80 #define ACPI_BATTERY_NOTIFY_INFO 0x81 @@ -74,10 +73,16 @@ static int acpi_battery_add(struct acpi_ static int acpi_battery_remove(struct acpi_device *device, int type); static int acpi_battery_resume(struct acpi_device *device); +static const struct acpi_device_id battery_device_ids[] = { + {"PNP0C0A", 0}, + {"", 0}, +}; +MODULE_DEVICE_TABLE(acpi, battery_device_ids); + static struct acpi_driver acpi_battery_driver = { .name = "battery", .class = ACPI_BATTERY_CLASS, - .ids = ACPI_BATTERY_HID, + .ids = battery_device_ids, .ops = { .add = acpi_battery_add, .resume = acpi_battery_resume, Index: linux-rt-rebase.q/drivers/acpi/button.c =================================================================== --- linux-rt-rebase.q.orig/drivers/acpi/button.c +++ linux-rt-rebase.q/drivers/acpi/button.c @@ -66,6 +66,16 @@ MODULE_AUTHOR("Paul Diefenbaugh"); MODULE_DESCRIPTION("ACPI Button Driver"); MODULE_LICENSE("GPL"); +static const struct acpi_device_id button_device_ids[] = { + {ACPI_BUTTON_HID_LID, 0}, + {ACPI_BUTTON_HID_SLEEP, 0}, + {ACPI_BUTTON_HID_SLEEPF, 0}, + {ACPI_BUTTON_HID_POWER, 0}, + {ACPI_BUTTON_HID_POWERF, 0}, + {"", 0}, +}; +MODULE_DEVICE_TABLE(acpi, button_device_ids); + static int acpi_button_add(struct acpi_device *device); static int acpi_button_remove(struct acpi_device *device, int type); static int acpi_button_info_open_fs(struct inode *inode, struct file *file); @@ -74,7 +84,7 @@ static int acpi_button_state_open_fs(str static struct acpi_driver acpi_button_driver = { .name = "button", .class = ACPI_BUTTON_CLASS, - .ids = "button_power,button_sleep,PNP0C0D,PNP0C0C,PNP0C0E", + .ids = button_device_ids, .ops = { .add = acpi_button_add, .remove = acpi_button_remove, Index: linux-rt-rebase.q/drivers/acpi/container.c =================================================================== --- linux-rt-rebase.q.orig/drivers/acpi/container.c +++ linux-rt-rebase.q/drivers/acpi/container.c @@ -52,10 +52,18 @@ MODULE_LICENSE("GPL"); static int acpi_container_add(struct acpi_device *device); static int acpi_container_remove(struct acpi_device *device, int type); +static const struct acpi_device_id container_device_ids[] = { + {"ACPI0004", 0}, + {"PNP0A05", 0}, + {"PNP0A06", 0}, + {"", 0}, +}; +MODULE_DEVICE_TABLE(acpi, container_device_ids); + static struct acpi_driver acpi_container_driver = { .name = "container", .class = ACPI_CONTAINER_CLASS, - .ids = "ACPI0004,PNP0A05,PNP0A06", + .ids = container_device_ids, .ops = { .add = acpi_container_add, .remove = acpi_container_remove, Index: linux-rt-rebase.q/drivers/acpi/ec.c =================================================================== --- linux-rt-rebase.q.orig/drivers/acpi/ec.c +++ linux-rt-rebase.q/drivers/acpi/ec.c @@ -41,7 +41,6 @@ #include #define ACPI_EC_CLASS "embedded_controller" -#define ACPI_EC_HID "PNP0C09" #define ACPI_EC_DEVICE_NAME "Embedded Controller" #define ACPI_EC_FILE_INFO "info" @@ -82,10 +81,15 @@ static int acpi_ec_start(struct acpi_dev static int acpi_ec_stop(struct acpi_device *device, int type); static int acpi_ec_add(struct acpi_device *device); +static const struct acpi_device_id ec_device_ids[] = { + {"PNP0C09", 0}, + {"", 0}, +}; + static struct acpi_driver acpi_ec_driver = { .name = "ec", .class = ACPI_EC_CLASS, - .ids = ACPI_EC_HID, + .ids = ec_device_ids, .ops = { .add = acpi_ec_add, .remove = acpi_ec_remove, @@ -479,7 +483,19 @@ static u32 acpi_ec_gpe_handler(void *dat atomic_inc(&ec->event_count); if (acpi_ec_mode == EC_INTR) { +#if 0 wake_up(&ec->wait); +#else + // hack ... + if (waitqueue_active(&ec->wait)) { + struct task_struct *task; + + task = list_entry(ec->wait.task_list.next, + wait_queue_t, task_list)->private; + if (task) + wake_up_process(task); + } +#endif } value = acpi_ec_read_status(ec); Index: linux-rt-rebase.q/drivers/acpi/events/evrgnini.c =================================================================== --- linux-rt-rebase.q.orig/drivers/acpi/events/evrgnini.c +++ linux-rt-rebase.q/drivers/acpi/events/evrgnini.c @@ -378,7 +378,7 @@ static u8 acpi_ev_match_pci_root_bridge( static u8 acpi_ev_is_pci_root_bridge(struct acpi_namespace_node *node) { acpi_status status; - struct acpi_device_id hid; + struct acpica_device_id hid; struct acpi_compatible_id_list *cid; acpi_native_uint i; Index: linux-rt-rebase.q/drivers/acpi/fan.c =================================================================== --- linux-rt-rebase.q.orig/drivers/acpi/fan.c +++ linux-rt-rebase.q/drivers/acpi/fan.c @@ -50,10 +50,16 @@ static int acpi_fan_remove(struct acpi_d static int acpi_fan_suspend(struct acpi_device *device, pm_message_t state); static int acpi_fan_resume(struct acpi_device *device); +static const struct acpi_device_id fan_device_ids[] = { + {"PNP0C0B", 0}, + {"", 0}, +}; +MODULE_DEVICE_TABLE(acpi, fan_device_ids); + static struct acpi_driver acpi_fan_driver = { .name = "fan", .class = ACPI_FAN_CLASS, - .ids = "PNP0C0B", + .ids = fan_device_ids, .ops = { .add = acpi_fan_add, .remove = acpi_fan_remove, Index: linux-rt-rebase.q/drivers/acpi/hardware/hwregs.c =================================================================== --- linux-rt-rebase.q.orig/drivers/acpi/hardware/hwregs.c +++ linux-rt-rebase.q/drivers/acpi/hardware/hwregs.c @@ -73,7 +73,7 @@ acpi_status acpi_hw_clear_acpi_status(vo ACPI_BITMASK_ALL_FIXED_STATUS, (u16) acpi_gbl_FADT.xpm1a_event_block.address)); - lock_flags = acpi_os_acquire_lock(acpi_gbl_hardware_lock); + spin_lock_irqsave(acpi_gbl_hardware_lock, lock_flags); status = acpi_hw_register_write(ACPI_MTX_DO_NOT_LOCK, ACPI_REGISTER_PM1_STATUS, @@ -98,7 +98,7 @@ acpi_status acpi_hw_clear_acpi_status(vo status = acpi_ev_walk_gpe_list(acpi_hw_clear_gpe_block); unlock_and_exit: - acpi_os_release_lock(acpi_gbl_hardware_lock, lock_flags); + spin_unlock_irqrestore(acpi_gbl_hardware_lock, lock_flags); return_ACPI_STATUS(status); } @@ -331,7 +331,7 @@ acpi_status acpi_set_register(u32 regist return_ACPI_STATUS(AE_BAD_PARAMETER); } - lock_flags = acpi_os_acquire_lock(acpi_gbl_hardware_lock); + spin_lock_irqsave(acpi_gbl_hardware_lock, lock_flags); /* Always do a register read first so we can insert the new bits */ @@ -441,7 +441,7 @@ acpi_status acpi_set_register(u32 regist unlock_and_exit: - acpi_os_release_lock(acpi_gbl_hardware_lock, lock_flags); + spin_unlock_irqrestore(acpi_gbl_hardware_lock, lock_flags); /* Normalize the value that was read */ @@ -481,7 +481,7 @@ acpi_hw_register_read(u8 use_lock, u32 r ACPI_FUNCTION_TRACE(hw_register_read); if (ACPI_MTX_LOCK == use_lock) { - lock_flags = acpi_os_acquire_lock(acpi_gbl_hardware_lock); + spin_lock_irqsave(acpi_gbl_hardware_lock, lock_flags); } switch (register_id) { @@ -560,7 +560,7 @@ acpi_hw_register_read(u8 use_lock, u32 r unlock_and_exit: if (ACPI_MTX_LOCK == use_lock) { - acpi_os_release_lock(acpi_gbl_hardware_lock, lock_flags); + spin_unlock_irqrestore(acpi_gbl_hardware_lock, lock_flags); } if (ACPI_SUCCESS(status)) { @@ -606,7 +606,7 @@ acpi_status acpi_hw_register_write(u8 us ACPI_FUNCTION_TRACE(hw_register_write); if (ACPI_MTX_LOCK == use_lock) { - lock_flags = acpi_os_acquire_lock(acpi_gbl_hardware_lock); + spin_lock_irqsave(acpi_gbl_hardware_lock, lock_flags); } switch (register_id) { @@ -730,7 +730,7 @@ acpi_status acpi_hw_register_write(u8 us unlock_and_exit: if (ACPI_MTX_LOCK == use_lock) { - acpi_os_release_lock(acpi_gbl_hardware_lock, lock_flags); + spin_unlock_irqrestore(acpi_gbl_hardware_lock, lock_flags); } return_ACPI_STATUS(status); Index: linux-rt-rebase.q/drivers/acpi/namespace/nsxfeval.c =================================================================== --- linux-rt-rebase.q.orig/drivers/acpi/namespace/nsxfeval.c +++ linux-rt-rebase.q/drivers/acpi/namespace/nsxfeval.c @@ -440,7 +440,7 @@ acpi_ns_get_device_callback(acpi_handle acpi_status status; struct acpi_namespace_node *node; u32 flags; - struct acpi_device_id hid; + struct acpica_device_id hid; struct acpi_compatible_id_list *cid; acpi_native_uint i; Index: linux-rt-rebase.q/drivers/acpi/osl.c =================================================================== --- linux-rt-rebase.q.orig/drivers/acpi/osl.c +++ linux-rt-rebase.q/drivers/acpi/osl.c @@ -739,13 +739,13 @@ void acpi_os_delete_lock(acpi_spinlock h acpi_status acpi_os_create_semaphore(u32 max_units, u32 initial_units, acpi_handle * handle) { - struct semaphore *sem = NULL; + struct compat_semaphore *sem = NULL; - sem = acpi_os_allocate(sizeof(struct semaphore)); + sem = acpi_os_allocate(sizeof(struct compat_semaphore)); if (!sem) return AE_NO_MEMORY; - memset(sem, 0, sizeof(struct semaphore)); + memset(sem, 0, sizeof(struct compat_semaphore)); sema_init(sem, initial_units); @@ -768,7 +768,7 @@ EXPORT_SYMBOL(acpi_os_create_semaphore); acpi_status acpi_os_delete_semaphore(acpi_handle handle) { - struct semaphore *sem = (struct semaphore *)handle; + struct compat_semaphore *sem = (struct compat_semaphore *)handle; if (!sem) @@ -796,7 +796,7 @@ EXPORT_SYMBOL(acpi_os_delete_semaphore); acpi_status acpi_os_wait_semaphore(acpi_handle handle, u32 units, u16 timeout) { acpi_status status = AE_OK; - struct semaphore *sem = (struct semaphore *)handle; + struct compat_semaphore *sem = (struct compat_semaphore *)handle; int ret = 0; @@ -883,7 +883,7 @@ EXPORT_SYMBOL(acpi_os_wait_semaphore); */ acpi_status acpi_os_signal_semaphore(acpi_handle handle, u32 units) { - struct semaphore *sem = (struct semaphore *)handle; + struct compat_semaphore *sem = (struct compat_semaphore *)handle; if (!sem || (units < 1)) @@ -1050,6 +1050,17 @@ unsigned int max_cstate = ACPI_PROCESSOR EXPORT_SYMBOL(max_cstate); +void (*acpi_do_set_cstate_limit)(void); +EXPORT_SYMBOL(acpi_do_set_cstate_limit); + +void acpi_set_cstate_limit(unsigned int new_limit) +{ + max_cstate = new_limit; + if (acpi_do_set_cstate_limit) + acpi_do_set_cstate_limit(); +} +EXPORT_SYMBOL(acpi_set_cstate_limit); + /* * Acquire a spinlock. * Index: linux-rt-rebase.q/drivers/acpi/pci_link.c =================================================================== --- linux-rt-rebase.q.orig/drivers/acpi/pci_link.c +++ linux-rt-rebase.q/drivers/acpi/pci_link.c @@ -46,7 +46,6 @@ #define _COMPONENT ACPI_PCI_COMPONENT ACPI_MODULE_NAME("pci_link"); #define ACPI_PCI_LINK_CLASS "pci_irq_routing" -#define ACPI_PCI_LINK_HID "PNP0C0F" #define ACPI_PCI_LINK_DEVICE_NAME "PCI Interrupt Link" #define ACPI_PCI_LINK_FILE_INFO "info" #define ACPI_PCI_LINK_FILE_STATUS "state" @@ -54,10 +53,16 @@ ACPI_MODULE_NAME("pci_link"); static int acpi_pci_link_add(struct acpi_device *device); static int acpi_pci_link_remove(struct acpi_device *device, int type); +static struct acpi_device_id link_device_ids[] = { + {"PNP0C0F", 0}, + {"", 0}, +}; +MODULE_DEVICE_TABLE(acpi, link_device_ids); + static struct acpi_driver acpi_pci_link_driver = { .name = "pci_link", .class = ACPI_PCI_LINK_CLASS, - .ids = ACPI_PCI_LINK_HID, + .ids = link_device_ids, .ops = { .add = acpi_pci_link_add, .remove = acpi_pci_link_remove, Index: linux-rt-rebase.q/drivers/acpi/pci_root.c =================================================================== --- linux-rt-rebase.q.orig/drivers/acpi/pci_root.c +++ linux-rt-rebase.q/drivers/acpi/pci_root.c @@ -38,16 +38,21 @@ #define _COMPONENT ACPI_PCI_COMPONENT ACPI_MODULE_NAME("pci_root"); #define ACPI_PCI_ROOT_CLASS "pci_bridge" -#define ACPI_PCI_ROOT_HID "PNP0A03" #define ACPI_PCI_ROOT_DEVICE_NAME "PCI Root Bridge" static int acpi_pci_root_add(struct acpi_device *device); static int acpi_pci_root_remove(struct acpi_device *device, int type); static int acpi_pci_root_start(struct acpi_device *device); +static struct acpi_device_id root_device_ids[] = { + {"PNP0A03", 0}, + {"", 0}, +}; +MODULE_DEVICE_TABLE(acpi, root_device_ids); + static struct acpi_driver acpi_pci_root_driver = { .name = "pci_root", .class = ACPI_PCI_ROOT_CLASS, - .ids = ACPI_PCI_ROOT_HID, + .ids = root_device_ids, .ops = { .add = acpi_pci_root_add, .remove = acpi_pci_root_remove, Index: linux-rt-rebase.q/drivers/acpi/power.c =================================================================== --- linux-rt-rebase.q.orig/drivers/acpi/power.c +++ linux-rt-rebase.q/drivers/acpi/power.c @@ -59,10 +59,16 @@ static int acpi_power_remove(struct acpi static int acpi_power_resume(struct acpi_device *device); static int acpi_power_open_fs(struct inode *inode, struct file *file); +static struct acpi_device_id power_device_ids[] = { + {ACPI_POWER_HID, 0}, + {"", 0}, +}; +MODULE_DEVICE_TABLE(acpi, power_device_ids); + static struct acpi_driver acpi_power_driver = { .name = "power", .class = ACPI_POWER_CLASS, - .ids = ACPI_POWER_HID, + .ids = power_device_ids, .ops = { .add = acpi_power_add, .remove = acpi_power_remove, Index: linux-rt-rebase.q/drivers/acpi/processor_core.c =================================================================== --- linux-rt-rebase.q.orig/drivers/acpi/processor_core.c +++ linux-rt-rebase.q/drivers/acpi/processor_core.c @@ -44,6 +44,7 @@ #include #include #include +#include #include #include @@ -88,10 +89,16 @@ static int acpi_processor_handle_eject(s extern int acpi_processor_tstate_has_changed(struct acpi_processor *pr); +static const struct acpi_device_id processor_device_ids[] = { + {ACPI_PROCESSOR_HID, 0}, + {"", 0}, +}; +MODULE_DEVICE_TABLE(acpi, processor_device_ids); + static struct acpi_driver acpi_processor_driver = { .name = "processor", .class = ACPI_PROCESSOR_CLASS, - .ids = ACPI_PROCESSOR_HID, + .ids = processor_device_ids, .ops = { .add = acpi_processor_add, .remove = acpi_processor_remove, @@ -1025,11 +1032,15 @@ static int __init acpi_processor_init(vo acpi_processor_ppc_init(); + cpuidle_register_driver(&acpi_idle_driver); + acpi_do_set_cstate_limit = acpi_max_cstate_changed; return 0; } static void __exit acpi_processor_exit(void) { + acpi_do_set_cstate_limit = NULL; + cpuidle_unregister_driver(&acpi_idle_driver); acpi_processor_ppc_exit(); Index: linux-rt-rebase.q/drivers/acpi/processor_idle.c =================================================================== --- linux-rt-rebase.q.orig/drivers/acpi/processor_idle.c +++ linux-rt-rebase.q/drivers/acpi/processor_idle.c @@ -40,6 +40,7 @@ #include /* need_resched() */ #include #include +#include /* * Include the apic definitions for x86 to have the APIC timer related defines @@ -62,25 +63,34 @@ #define _COMPONENT ACPI_PROCESSOR_COMPONENT ACPI_MODULE_NAME("processor_idle"); #define ACPI_PROCESSOR_FILE_POWER "power" -#define US_TO_PM_TIMER_TICKS(t) ((t * (PM_TIMER_FREQUENCY/1000)) / 1000) -#define C2_OVERHEAD 4 /* 1us (3.579 ticks per us) */ -#define C3_OVERHEAD 4 /* 1us (3.579 ticks per us) */ -static void (*pm_idle_save) (void) __read_mostly; -module_param(max_cstate, uint, 0644); +#define PM_TIMER_TICKS_TO_US(p) (((p) * 1000)/(PM_TIMER_FREQUENCY/1000)) +#define C2_OVERHEAD 1 /* 1us */ +#define C3_OVERHEAD 1 /* 1us */ + +void acpi_max_cstate_changed(void) +{ + /* Driver will reset devices' max cstate limit */ + cpuidle_force_redetect_devices(&acpi_idle_driver); +} + +static int change_max_cstate(const char *val, struct kernel_param *kp) +{ + int max; + + max = simple_strtol(val, NULL, 0); + if (!max) + return -EINVAL; + max_cstate = max; + if (acpi_do_set_cstate_limit) + acpi_do_set_cstate_limit(); + return 0; +} + +module_param_call(max_cstate, change_max_cstate, param_get_uint, &max_cstate, 0644); static unsigned int nocst __read_mostly; module_param(nocst, uint, 0000); -/* - * bm_history -- bit-mask with a bit per jiffy of bus-master activity - * 1000 HZ: 0xFFFFFFFF: 32 jiffies = 32ms - * 800 HZ: 0xFFFFFFFF: 32 jiffies = 40ms - * 100 HZ: 0x0000000F: 4 jiffies = 40ms - * reduce history for more aggressive entry into C3 - */ -static unsigned int bm_history __read_mostly = - (HZ >= 800 ? 0xFFFFFFFF : ((1U << (HZ / 25)) - 1)); -module_param(bm_history, uint, 0644); /* -------------------------------------------------------------------------- Power Management -------------------------------------------------------------------------- */ @@ -166,88 +176,6 @@ static struct dmi_system_id __cpuinitdat {}, }; -static inline u32 ticks_elapsed(u32 t1, u32 t2) -{ - if (t2 >= t1) - return (t2 - t1); - else if (!(acpi_gbl_FADT.flags & ACPI_FADT_32BIT_TIMER)) - return (((0x00FFFFFF - t1) + t2) & 0x00FFFFFF); - else - return ((0xFFFFFFFF - t1) + t2); -} - -static void -acpi_processor_power_activate(struct acpi_processor *pr, - struct acpi_processor_cx *new) -{ - struct acpi_processor_cx *old; - - if (!pr || !new) - return; - - old = pr->power.state; - - if (old) - old->promotion.count = 0; - new->demotion.count = 0; - - /* Cleanup from old state. */ - if (old) { - switch (old->type) { - case ACPI_STATE_C3: - /* Disable bus master reload */ - if (new->type != ACPI_STATE_C3 && pr->flags.bm_check) - acpi_set_register(ACPI_BITREG_BUS_MASTER_RLD, 0); - break; - } - } - - /* Prepare to use new state. */ - switch (new->type) { - case ACPI_STATE_C3: - /* Enable bus master reload */ - if (old->type != ACPI_STATE_C3 && pr->flags.bm_check) - acpi_set_register(ACPI_BITREG_BUS_MASTER_RLD, 1); - break; - } - - pr->power.state = new; - - return; -} - -static void acpi_safe_halt(void) -{ - current_thread_info()->status &= ~TS_POLLING; - /* - * TS_POLLING-cleared state must be visible before we - * test NEED_RESCHED: - */ - smp_mb(); - if (!need_resched()) - safe_halt(); - current_thread_info()->status |= TS_POLLING; -} - -static atomic_t c3_cpu_count; - -/* Common C-state entry for C2, C3, .. */ -static void acpi_cstate_enter(struct acpi_processor_cx *cstate) -{ - if (cstate->space_id == ACPI_CSTATE_FFH) { - /* Call into architectural FFH based C-state */ - acpi_processor_ffh_cstate_enter(cstate); - } else { - int unused; - /* IO port based C-state */ - inb(cstate->address); - /* Dummy wait op - must do something useless after P_LVL2 read - because chipsets cannot guarantee that STPCLK# signal - gets asserted in time to freeze execution properly. */ - unused = inl(acpi_gbl_FADT.xpm_timer_block.address); - } -} - #ifdef ARCH_APICTIMER_STOPS_ON_C3 /* @@ -275,21 +203,12 @@ static void acpi_timer_check_state(int s static void acpi_propagate_timer_broadcast(struct acpi_processor *pr) { -#ifdef CONFIG_GENERIC_CLOCKEVENTS unsigned long reason; reason = pr->power.timer_broadcast_on_state < INT_MAX ? CLOCK_EVT_NOTIFY_BROADCAST_ON : CLOCK_EVT_NOTIFY_BROADCAST_OFF; clockevents_notify(reason, &pr->id); -#else - cpumask_t mask = cpumask_of_cpu(pr->id); - - if (pr->power.timer_broadcast_on_state < INT_MAX) - on_each_cpu(switch_APIC_timer_to_ipi, &mask, 1, 1); - else - on_each_cpu(switch_ipi_to_APIC_timer, &mask, 1, 1); -#endif } /* Power(C) State timer broadcast control */ @@ -297,8 +216,6 @@ static void acpi_state_timer_broadcast(s struct acpi_processor_cx *cx, int broadcast) { -#ifdef CONFIG_GENERIC_CLOCKEVENTS - int state = cx - pr->power.states; if (state >= pr->power.timer_broadcast_on_state) { @@ -308,7 +225,6 @@ static void acpi_state_timer_broadcast(s CLOCK_EVT_NOTIFY_BROADCAST_EXIT; clockevents_notify(reason, &pr->id); } -#endif } #else @@ -324,387 +240,6 @@ static void acpi_state_timer_broadcast(s #endif -static void acpi_processor_idle(void) -{ - struct acpi_processor *pr = NULL; - struct acpi_processor_cx *cx = NULL; - struct acpi_processor_cx *next_state = NULL; - int sleep_ticks = 0; - u32 t1, t2 = 0; - - /* - * Interrupts must be disabled during bus mastering calculations and - * for C2/C3 transitions. - */ - local_irq_disable(); - - pr = processors[smp_processor_id()]; - if (!pr) { - local_irq_enable(); - return; - } - - /* - * Check whether we truly need to go idle, or should - * reschedule: - */ - if (unlikely(need_resched())) { - local_irq_enable(); - return; - } - - cx = pr->power.state; - if (!cx) { - if (pm_idle_save) - pm_idle_save(); - else - acpi_safe_halt(); - return; - } - - /* - * Check BM Activity - * ----------------- - * Check for bus mastering activity (if required), record, and check - * for demotion. - */ - if (pr->flags.bm_check) { - u32 bm_status = 0; - unsigned long diff = jiffies - pr->power.bm_check_timestamp; - - if (diff > 31) - diff = 31; - - pr->power.bm_activity <<= diff; - - acpi_get_register(ACPI_BITREG_BUS_MASTER_STATUS, &bm_status); - if (bm_status) { - pr->power.bm_activity |= 0x1; - acpi_set_register(ACPI_BITREG_BUS_MASTER_STATUS, 1); - } - /* - * PIIX4 Erratum #18: Note that BM_STS doesn't always reflect - * the true state of bus mastering activity; forcing us to - * manually check the BMIDEA bit of each IDE channel. - */ - else if (errata.piix4.bmisx) { - if ((inb_p(errata.piix4.bmisx + 0x02) & 0x01) - || (inb_p(errata.piix4.bmisx + 0x0A) & 0x01)) - pr->power.bm_activity |= 0x1; - } - - pr->power.bm_check_timestamp = jiffies; - - /* - * If bus mastering is or was active this jiffy, demote - * to avoid a faulty transition. Note that the processor - * won't enter a low-power state during this call (to this - * function) but should upon the next. - * - * TBD: A better policy might be to fallback to the demotion - * state (use it for this quantum only) istead of - * demoting -- and rely on duration as our sole demotion - * qualification. This may, however, introduce DMA - * issues (e.g. floppy DMA transfer overrun/underrun). - */ - if ((pr->power.bm_activity & 0x1) && - cx->demotion.threshold.bm) { - local_irq_enable(); - next_state = cx->demotion.state; - goto end; - } - } - -#ifdef CONFIG_HOTPLUG_CPU - /* - * Check for P_LVL2_UP flag before entering C2 and above on - * an SMP system. We do it here instead of doing it at _CST/P_LVL - * detection phase, to work cleanly with logical CPU hotplug. - */ - if ((cx->type != ACPI_STATE_C1) && (num_online_cpus() > 1) && - !pr->flags.has_cst && !(acpi_gbl_FADT.flags & ACPI_FADT_C2_MP_SUPPORTED)) - cx = &pr->power.states[ACPI_STATE_C1]; -#endif - - /* - * Sleep: - * ------ - * Invoke the current Cx state to put the processor to sleep. - */ - if (cx->type == ACPI_STATE_C2 || cx->type == ACPI_STATE_C3) { - current_thread_info()->status &= ~TS_POLLING; - /* - * TS_POLLING-cleared state must be visible before we - * test NEED_RESCHED: - */ - smp_mb(); - if (need_resched()) { - current_thread_info()->status |= TS_POLLING; - local_irq_enable(); - return; - } - } - - switch (cx->type) { - - case ACPI_STATE_C1: - /* - * Invoke C1. - * Use the appropriate idle routine, the one that would - * be used without acpi C-states. - */ - if (pm_idle_save) - pm_idle_save(); - else - acpi_safe_halt(); - - /* - * TBD: Can't get time duration while in C1, as resumes - * go to an ISR rather than here. Need to instrument - * base interrupt handler. - */ - sleep_ticks = 0xFFFFFFFF; - break; - - case ACPI_STATE_C2: - /* Get start time (ticks) */ - t1 = inl(acpi_gbl_FADT.xpm_timer_block.address); - /* Invoke C2 */ - acpi_state_timer_broadcast(pr, cx, 1); - acpi_cstate_enter(cx); - /* Get end time (ticks) */ - t2 = inl(acpi_gbl_FADT.xpm_timer_block.address); - -#if defined (CONFIG_GENERIC_TIME) && defined (CONFIG_X86_TSC) - /* TSC halts in C2, so notify users */ - mark_tsc_unstable("possible TSC halt in C2"); -#endif - /* Re-enable interrupts */ - local_irq_enable(); - current_thread_info()->status |= TS_POLLING; - /* Compute time (ticks) that we were actually asleep */ - sleep_ticks = - ticks_elapsed(t1, t2) - cx->latency_ticks - C2_OVERHEAD; - acpi_state_timer_broadcast(pr, cx, 0); - break; - - case ACPI_STATE_C3: - - /* - * disable bus master - * bm_check implies we need ARB_DIS - * !bm_check implies we need cache flush - * bm_control implies whether we can do ARB_DIS - * - * That leaves a case where bm_check is set and bm_control is - * not set. In that case we cannot do much, we enter C3 - * without doing anything. - */ - if (pr->flags.bm_check && pr->flags.bm_control) { - if (atomic_inc_return(&c3_cpu_count) == - num_online_cpus()) { - /* - * All CPUs are trying to go to C3 - * Disable bus master arbitration - */ - acpi_set_register(ACPI_BITREG_ARB_DISABLE, 1); - } - } else if (!pr->flags.bm_check) { - /* SMP with no shared cache... Invalidate cache */ - ACPI_FLUSH_CPU_CACHE(); - } - - /* Get start time (ticks) */ - t1 = inl(acpi_gbl_FADT.xpm_timer_block.address); - /* Invoke C3 */ - acpi_state_timer_broadcast(pr, cx, 1); - acpi_cstate_enter(cx); - /* Get end time (ticks) */ - t2 = inl(acpi_gbl_FADT.xpm_timer_block.address); - if (pr->flags.bm_check && pr->flags.bm_control) { - /* Enable bus master arbitration */ - atomic_dec(&c3_cpu_count); - acpi_set_register(ACPI_BITREG_ARB_DISABLE, 0); - } - -#if defined (CONFIG_GENERIC_TIME) && defined (CONFIG_X86_TSC) - /* TSC halts in C3, so notify users */ - mark_tsc_unstable("TSC halts in C3"); -#endif - /* Re-enable interrupts */ - local_irq_enable(); - current_thread_info()->status |= TS_POLLING; - /* Compute time (ticks) that we were actually asleep */ - sleep_ticks = - ticks_elapsed(t1, t2) - cx->latency_ticks - C3_OVERHEAD; - acpi_state_timer_broadcast(pr, cx, 0); - break; - - default: - local_irq_enable(); - return; - } - cx->usage++; - if ((cx->type != ACPI_STATE_C1) && (sleep_ticks > 0)) - cx->time += sleep_ticks; - - next_state = pr->power.state; - -#ifdef CONFIG_HOTPLUG_CPU - /* Don't do promotion/demotion */ - if ((cx->type == ACPI_STATE_C1) && (num_online_cpus() > 1) && - !pr->flags.has_cst && !(acpi_gbl_FADT.flags & ACPI_FADT_C2_MP_SUPPORTED)) { - next_state = cx; - goto end; - } -#endif - - /* - * Promotion? - * ---------- - * Track the number of longs (time asleep is greater than threshold) - * and promote when the count threshold is reached. Note that bus - * mastering activity may prevent promotions. - * Do not promote above max_cstate. - */ - if (cx->promotion.state && - ((cx->promotion.state - pr->power.states) <= max_cstate)) { - if (sleep_ticks > cx->promotion.threshold.ticks && - cx->promotion.state->latency <= system_latency_constraint()) { - cx->promotion.count++; - cx->demotion.count = 0; - if (cx->promotion.count >= - cx->promotion.threshold.count) { - if (pr->flags.bm_check) { - if (! - (pr->power.bm_activity & cx-> - promotion.threshold.bm)) { - next_state = - cx->promotion.state; - goto end; - } - } else { - next_state = cx->promotion.state; - goto end; - } - } - } - } - - /* - * Demotion? - * --------- - * Track the number of shorts (time asleep is less than time threshold) - * and demote when the usage threshold is reached. - */ - if (cx->demotion.state) { - if (sleep_ticks < cx->demotion.threshold.ticks) { - cx->demotion.count++; - cx->promotion.count = 0; - if (cx->demotion.count >= cx->demotion.threshold.count) { - next_state = cx->demotion.state; - goto end; - } - } - } - - end: - /* - * Demote if current state exceeds max_cstate - * or if the latency of the current state is unacceptable - */ - if ((pr->power.state - pr->power.states) > max_cstate || - pr->power.state->latency > system_latency_constraint()) { - if (cx->demotion.state) - next_state = cx->demotion.state; - } - - /* - * New Cx State? - * ------------- - * If we're going to start using a new Cx state we must clean up - * from the previous and prepare to use the new. - */ - if (next_state != pr->power.state) - acpi_processor_power_activate(pr, next_state); -} - -static int acpi_processor_set_power_policy(struct acpi_processor *pr) -{ - unsigned int i; - unsigned int state_is_set = 0; - struct acpi_processor_cx *lower = NULL; - struct acpi_processor_cx *higher = NULL; - struct acpi_processor_cx *cx; - - - if (!pr) - return -EINVAL; - - /* - * This function sets the default Cx state policy (OS idle handler). - * Our scheme is to promote quickly to C2 but more conservatively - * to C3. We're favoring C2 for its characteristics of low latency - * (quick response), good power savings, and ability to allow bus - * mastering activity. Note that the Cx state policy is completely - * customizable and can be altered dynamically. - */ - - /* startup state */ - for (i = 1; i < ACPI_PROCESSOR_MAX_POWER; i++) { - cx = &pr->power.states[i]; - if (!cx->valid) - continue; - - if (!state_is_set) - pr->power.state = cx; - state_is_set++; - break; - } - - if (!state_is_set) - return -ENODEV; - - /* demotion */ - for (i = 1; i < ACPI_PROCESSOR_MAX_POWER; i++) { - cx = &pr->power.states[i]; - if (!cx->valid) - continue; - - if (lower) { - cx->demotion.state = lower; - cx->demotion.threshold.ticks = cx->latency_ticks; - cx->demotion.threshold.count = 1; - if (cx->type == ACPI_STATE_C3) - cx->demotion.threshold.bm = bm_history; - } - - lower = cx; - } - - /* promotion */ - for (i = (ACPI_PROCESSOR_MAX_POWER - 1); i > 0; i--) { - cx = &pr->power.states[i]; - if (!cx->valid) - continue; - - if (higher) { - cx->promotion.state = higher; - cx->promotion.threshold.ticks = cx->latency_ticks; - if (cx->type >= ACPI_STATE_C2) - cx->promotion.threshold.count = 4; - else - cx->promotion.threshold.count = 10; - if (higher->type == ACPI_STATE_C3) - cx->promotion.threshold.bm = bm_history; - } - - higher = cx; - } - - return 0; -} - static int acpi_processor_get_power_info_fadt(struct acpi_processor *pr) { @@ -922,7 +457,7 @@ static void acpi_processor_power_verify_ * Normalize the C2 latency to expidite policy */ cx->valid = 1; - cx->latency_ticks = US_TO_PM_TIMER_TICKS(cx->latency); + cx->latency_ticks = cx->latency; return; } @@ -996,7 +531,7 @@ static void acpi_processor_power_verify_ * use this in our C3 policy */ cx->valid = 1; - cx->latency_ticks = US_TO_PM_TIMER_TICKS(cx->latency); + cx->latency_ticks = cx->latency; return; } @@ -1062,18 +597,6 @@ static int acpi_processor_get_power_info pr->power.count = acpi_processor_power_verify(pr); /* - * Set Default Policy - * ------------------ - * Now that we know which states are supported, set the default - * policy. Note that this policy can be changed dynamically - * (e.g. encourage deeper sleeps to conserve battery life when - * not on AC). - */ - result = acpi_processor_set_power_policy(pr); - if (result) - return result; - - /* * if one state of type C2 or C3 is available, mark this * CPU as being "idle manageable" */ @@ -1090,9 +613,6 @@ static int acpi_processor_get_power_info int acpi_processor_cst_has_changed(struct acpi_processor *pr) { - int result = 0; - - if (!pr) return -EINVAL; @@ -1103,16 +623,9 @@ int acpi_processor_cst_has_changed(struc if (!pr->flags.power_setup_done) return -ENODEV; - /* Fall back to the default idle loop */ - pm_idle = pm_idle_save; - synchronize_sched(); /* Relies on interrupts forcing exit from idle. */ - - pr->flags.power = 0; - result = acpi_processor_get_power_info(pr); - if ((pr->flags.power == 1) && (pr->flags.power_setup_done)) - pm_idle = acpi_processor_idle; - - return result; + acpi_processor_get_power_info(pr); + return cpuidle_force_redetect(per_cpu(cpuidle_devices, pr->id), + &acpi_idle_driver); } /* proc interface */ @@ -1198,30 +711,6 @@ static const struct file_operations acpi .release = single_release, }; -#ifdef CONFIG_SMP -static void smp_callback(void *v) -{ - /* we already woke the CPU up, nothing more to do */ -} - -/* - * This function gets called when a part of the kernel has a new latency - * requirement. This means we need to get all processors out of their C-state, - * and then recalculate a new suitable C-state. Just do a cross-cpu IPI; that - * wakes them all right up. - */ -static int acpi_processor_latency_notify(struct notifier_block *b, - unsigned long l, void *v) -{ - smp_call_function(smp_callback, NULL, 0, 1); - return NOTIFY_OK; -} - -static struct notifier_block acpi_processor_latency_notifier = { - .notifier_call = acpi_processor_latency_notify, -}; -#endif - int __cpuinit acpi_processor_power_init(struct acpi_processor *pr, struct acpi_device *device) { @@ -1238,9 +727,6 @@ int __cpuinit acpi_processor_power_init( "ACPI: processor limited to max C-state %d\n", max_cstate); first_run++; -#ifdef CONFIG_SMP - register_latency_notifier(&acpi_processor_latency_notifier); -#endif } if (!pr) @@ -1257,6 +743,7 @@ int __cpuinit acpi_processor_power_init( acpi_processor_get_power_info(pr); + /* * Install the idle handler if processor power management is supported. * Note that we use previously set idle handler will be used on @@ -1269,11 +756,6 @@ int __cpuinit acpi_processor_power_init( printk(" C%d[C%d]", i, pr->power.states[i].type); printk(")\n"); - - if (pr->id == 0) { - pm_idle_save = pm_idle; - pm_idle = acpi_processor_idle; - } } /* 'power' [R] */ @@ -1301,21 +783,357 @@ int acpi_processor_power_exit(struct acp if (acpi_device_dir(device)) remove_proc_entry(ACPI_PROCESSOR_FILE_POWER, acpi_device_dir(device)); + return 0; +} - /* Unregister the idle handler when processor #0 is removed. */ - if (pr->id == 0) { - pm_idle = pm_idle_save; +/** + * ticks_elapsed - a helper function that determines how many ticks (in US) + * have elapsed between two PM Timer timestamps + * @t1: the start time + * @t2: the end time + */ +static inline u32 ticks_elapsed_in_us(u32 t1, u32 t2) +{ + if (t2 >= t1) + return PM_TIMER_TICKS_TO_US(t2 - t1); + else if (!(acpi_gbl_FADT.flags & ACPI_FADT_32BIT_TIMER)) + return PM_TIMER_TICKS_TO_US(((0x00FFFFFF - t1) + t2) & 0x00FFFFFF); + else + return PM_TIMER_TICKS_TO_US((0xFFFFFFFF - t1) + t2); +} - /* - * We are about to unload the current idle thread pm callback - * (pm_idle), Wait for all processors to update cached/local - * copies of pm_idle before proceeding. - */ - cpu_idle_wait(); -#ifdef CONFIG_SMP - unregister_latency_notifier(&acpi_processor_latency_notifier); +static inline u32 ticks_elapsed(u32 t1, u32 t2) +{ + if (t2 >= t1) + return (t2 - t1); + else if (!(acpi_gbl_FADT.flags & ACPI_FADT_32BIT_TIMER)) + return (((0x00FFFFFF - t1) + t2) & 0x00FFFFFF); + else + return ((0xFFFFFFFF - t1) + t2); +} + +/** + * acpi_idle_update_bm_rld - updates the BM_RLD bit depending on target state + * @pr: the processor + * @target: the new target state + */ +static inline void acpi_idle_update_bm_rld(struct acpi_processor *pr, + struct acpi_processor_cx *target) +{ + if (pr->flags.bm_rld_set && target->type != ACPI_STATE_C3) { + acpi_set_register(ACPI_BITREG_BUS_MASTER_RLD, 0); + pr->flags.bm_rld_set = 0; + } + + if (!pr->flags.bm_rld_set && target->type == ACPI_STATE_C3) { + acpi_set_register(ACPI_BITREG_BUS_MASTER_RLD, 1); + pr->flags.bm_rld_set = 1; + } +} + +/** + * acpi_idle_do_entry - a helper function that does C2 and C3 type entry + * @cx: cstate data + */ +static inline void acpi_idle_do_entry(struct acpi_processor_cx *cx) +{ + /* + * We have irqs disabled here, so stop latency tracing + * at this point and restart it after we return: + */ + stop_critical_timing(); + + if (cx->space_id == ACPI_CSTATE_FFH) { + /* Call into architectural FFH based C-state */ + acpi_processor_ffh_cstate_enter(cx); + } else { + int unused; + /* IO port based C-state */ + inb(cx->address); + /* Dummy wait op - must do something useless after P_LVL2 read + because chipsets cannot guarantee that STPCLK# signal + gets asserted in time to freeze execution properly. */ + unused = inl(acpi_gbl_FADT.xpm_timer_block.address); + } + + touch_critical_timing(); +} + +/** + * acpi_idle_enter_c1 - enters an ACPI C1 state-type + * @dev: the target CPU + * @state: the state data + * + * This is equivalent to the HALT instruction. + */ +static int acpi_idle_enter_c1(struct cpuidle_device *dev, + struct cpuidle_state *state) +{ + struct acpi_processor *pr; + struct acpi_processor_cx *cx = cpuidle_get_statedata(state); + pr = processors[smp_processor_id()]; + + if (unlikely(!pr)) + return 0; + + if (pr->flags.bm_check) + acpi_idle_update_bm_rld(pr, cx); + + current_thread_info()->status &= ~TS_POLLING; + /* + * TS_POLLING-cleared state must be visible before we test + * NEED_RESCHED: + */ + smp_mb(); + if (!need_resched() || !need_resched_delayed()) + safe_halt(); + current_thread_info()->status |= TS_POLLING; + + cx->usage++; + + return 0; +} + +/** + * acpi_idle_enter_c2 - enters an ACPI C2 state-type + * @dev: the target CPU + * @state: the state data + */ +static int acpi_idle_enter_c2(struct cpuidle_device *dev, + struct cpuidle_state *state) +{ + struct acpi_processor *pr; + struct acpi_processor_cx *cx = cpuidle_get_statedata(state); + u32 t1, t2; + pr = processors[smp_processor_id()]; + + if (unlikely(!pr)) + return 0; + + if (pr->flags.bm_check) + acpi_idle_update_bm_rld(pr, cx); + + local_irq_disable(); + current_thread_info()->status &= ~TS_POLLING; + /* + * TS_POLLING-cleared state must be visible before we test + * NEED_RESCHED: + */ + smp_mb(); + + if (unlikely(need_resched() || need_resched_delayed())) { + current_thread_info()->status |= TS_POLLING; + local_irq_enable(); + return 0; + } + + t1 = inl(acpi_gbl_FADT.xpm_timer_block.address); + acpi_state_timer_broadcast(pr, cx, 1); + acpi_idle_do_entry(cx); + t2 = inl(acpi_gbl_FADT.xpm_timer_block.address); + +#if defined(CONFIG_GENERIC_TIME) && defined(CONFIG_X86) + /* TSC halts in C2, so notify users */ + mark_tsc_unstable("possible TSC halt in C2"); #endif + + local_irq_enable(); + current_thread_info()->status |= TS_POLLING; + + cx->usage++; + + acpi_state_timer_broadcast(pr, cx, 0); + cx->time += ticks_elapsed(t1, t2); + return ticks_elapsed_in_us(t1, t2); +} + +static int c3_cpu_count; +static DEFINE_RAW_SPINLOCK(c3_lock); + +/** + * acpi_idle_enter_c3 - enters an ACPI C3 state-type + * @dev: the target CPU + * @state: the state data + * + * Similar to C2 entry, except special bus master handling is needed. + */ +static int acpi_idle_enter_c3(struct cpuidle_device *dev, + struct cpuidle_state *state) +{ + struct acpi_processor *pr; + struct acpi_processor_cx *cx = cpuidle_get_statedata(state); + u32 t1, t2; + pr = processors[smp_processor_id()]; + + if (unlikely(!pr)) + return 0; + + if (pr->flags.bm_check) + acpi_idle_update_bm_rld(pr, cx); + + local_irq_disable(); + current_thread_info()->status &= ~TS_POLLING; + /* + * TS_POLLING-cleared state must be visible before we test + * NEED_RESCHED: + */ + smp_mb(); + + if (unlikely(need_resched() || need_resched_delayed())) { + current_thread_info()->status |= TS_POLLING; + local_irq_enable(); + return 0; + } + + /* + * Must be done before busmaster disable as we might need to + * access HPET ! + */ + acpi_state_timer_broadcast(pr, cx, 1); + + /* disable bus master */ + if (pr->flags.bm_check) { + spin_lock(&c3_lock); + c3_cpu_count++; + if (c3_cpu_count == num_online_cpus()) { + /* + * All CPUs are trying to go to C3 + * Disable bus master arbitration + */ + acpi_set_register(ACPI_BITREG_ARB_DISABLE, 1); + } + spin_unlock(&c3_lock); + } else { + /* SMP with no shared cache... Invalidate cache */ + ACPI_FLUSH_CPU_CACHE(); + } + + /* Get start time (ticks) */ + t1 = inl(acpi_gbl_FADT.xpm_timer_block.address); + acpi_idle_do_entry(cx); + t2 = inl(acpi_gbl_FADT.xpm_timer_block.address); + + if (pr->flags.bm_check) { + spin_lock(&c3_lock); + /* Enable bus master arbitration */ + if (c3_cpu_count == num_online_cpus()) + acpi_set_register(ACPI_BITREG_ARB_DISABLE, 0); + c3_cpu_count--; + spin_unlock(&c3_lock); } +#if defined(CONFIG_GENERIC_TIME) && defined(CONFIG_X86) + /* TSC halts in C3, so notify users */ + mark_tsc_unstable("TSC halts in C3"); +#endif + + local_irq_enable(); + current_thread_info()->status |= TS_POLLING; + + cx->usage++; + + acpi_state_timer_broadcast(pr, cx, 0); + cx->time += ticks_elapsed(t1, t2); + return ticks_elapsed_in_us(t1, t2); +} + +/** + * acpi_idle_bm_check - checks if bus master activity was detected + */ +static int acpi_idle_bm_check(void) +{ + u32 bm_status = 0; + + acpi_get_register(ACPI_BITREG_BUS_MASTER_STATUS, &bm_status); + if (bm_status) + acpi_set_register(ACPI_BITREG_BUS_MASTER_STATUS, 1); + /* + * PIIX4 Erratum #18: Note that BM_STS doesn't always reflect + * the true state of bus mastering activity; forcing us to + * manually check the BMIDEA bit of each IDE channel. + */ + else if (errata.piix4.bmisx) { + if ((inb_p(errata.piix4.bmisx + 0x02) & 0x01) + || (inb_p(errata.piix4.bmisx + 0x0A) & 0x01)) + bm_status = 1; + } + return bm_status; +} + +/** + * acpi_idle_init - attaches the driver to a CPU + * @dev: the CPU + */ +static int acpi_idle_init(struct cpuidle_device *dev) +{ + int cpu = dev->cpu; + int i, count = 0; + struct acpi_processor_cx *cx; + struct cpuidle_state *state; + + struct acpi_processor *pr = processors[cpu]; + + if (!pr->flags.power_setup_done) + return -EINVAL; + + if (pr->flags.power == 0) { + return -EINVAL; + } + + for (i = 1; i < ACPI_PROCESSOR_MAX_POWER && i <= max_cstate; i++) { + cx = &pr->power.states[i]; + state = &dev->states[count]; + + if (!cx->valid) + continue; + +#ifdef CONFIG_HOTPLUG_CPU + if ((cx->type != ACPI_STATE_C1) && (num_online_cpus() > 1) && + !pr->flags.has_cst && + !(acpi_gbl_FADT.flags & ACPI_FADT_C2_MP_SUPPORTED)) + continue; +#endif + cpuidle_set_statedata(state, cx); + + state->exit_latency = cx->latency; + state->target_residency = cx->latency * 6; + state->power_usage = cx->power; + + state->flags = 0; + switch (cx->type) { + case ACPI_STATE_C1: + state->flags |= CPUIDLE_FLAG_SHALLOW; + state->enter = acpi_idle_enter_c1; + break; + + case ACPI_STATE_C2: + state->flags |= CPUIDLE_FLAG_BALANCED; + state->flags |= CPUIDLE_FLAG_TIME_VALID; + state->enter = acpi_idle_enter_c2; + break; + + case ACPI_STATE_C3: + state->flags |= CPUIDLE_FLAG_DEEP; + state->flags |= CPUIDLE_FLAG_TIME_VALID; + state->flags |= CPUIDLE_FLAG_CHECK_BM; + state->enter = acpi_idle_enter_c3; + break; + } + + count++; + } + + if (!count) + return -EINVAL; + + dev->state_count = count; return 0; } + +struct cpuidle_driver acpi_idle_driver = { + .name = "acpi_idle", + .init = acpi_idle_init, + .redetect = acpi_idle_init, + .bm_check = acpi_idle_bm_check, + .owner = THIS_MODULE, +}; Index: linux-rt-rebase.q/drivers/acpi/processor_throttling.c =================================================================== --- linux-rt-rebase.q.orig/drivers/acpi/processor_throttling.c +++ linux-rt-rebase.q/drivers/acpi/processor_throttling.c @@ -47,6 +47,9 @@ ACPI_MODULE_NAME("processor_throttling") static int acpi_processor_get_throttling(struct acpi_processor *pr); int acpi_processor_set_throttling(struct acpi_processor *pr, int state); +/* + * _TPC - Throttling Present Capabilities + */ static int acpi_processor_get_platform_limit(struct acpi_processor *pr) { acpi_status status = 0; @@ -55,8 +58,10 @@ static int acpi_processor_get_platform_l if (!pr) return -EINVAL; status = acpi_evaluate_integer(pr->handle, "_TPC", NULL, &tpc); - if (ACPI_FAILURE(status) && status != AE_NOT_FOUND) { - ACPI_EXCEPTION((AE_INFO, status, "Evaluating _TPC")); + if (ACPI_FAILURE(status)) { + if (status != AE_NOT_FOUND) { + ACPI_EXCEPTION((AE_INFO, status, "Evaluating _TPC")); + } return -ENODEV; } pr->throttling_platform_limit = (int)tpc; @@ -68,9 +73,9 @@ int acpi_processor_tstate_has_changed(st return acpi_processor_get_platform_limit(pr); } -/* -------------------------------------------------------------------------- - _PTC, _TSS, _TSD support - -------------------------------------------------------------------------- */ +/* + * _PTC - Processor Throttling Control (and status) register location + */ static int acpi_processor_get_throttling_control(struct acpi_processor *pr) { int result = 0; @@ -81,7 +86,9 @@ static int acpi_processor_get_throttling status = acpi_evaluate_object(pr->handle, "_PTC", NULL, &buffer); if (ACPI_FAILURE(status)) { - ACPI_EXCEPTION((AE_INFO, status, "Evaluating _PTC")); + if (status != AE_NOT_FOUND) { + ACPI_EXCEPTION((AE_INFO, status, "Evaluating _PTC")); + } return -ENODEV; } @@ -132,6 +139,10 @@ static int acpi_processor_get_throttling return result; } + +/* + * _TSS - Throttling Supported States + */ static int acpi_processor_get_throttling_states(struct acpi_processor *pr) { int result = 0; @@ -144,7 +155,9 @@ static int acpi_processor_get_throttling status = acpi_evaluate_object(pr->handle, "_TSS", NULL, &buffer); if (ACPI_FAILURE(status)) { - ACPI_EXCEPTION((AE_INFO, status, "Evaluating _TSS")); + if (status != AE_NOT_FOUND) { + ACPI_EXCEPTION((AE_INFO, status, "Evaluating _TSS")); + } return -ENODEV; } @@ -201,6 +214,10 @@ static int acpi_processor_get_throttling return result; } + +/* + * _TSD - T-State Dependencies + */ static int acpi_processor_get_tsd(struct acpi_processor *pr) { int result = 0; @@ -213,6 +230,9 @@ static int acpi_processor_get_tsd(struct status = acpi_evaluate_object(pr->handle, "_TSD", NULL, &buffer); if (ACPI_FAILURE(status)) { + if (status != AE_NOT_FOUND) { + ACPI_EXCEPTION((AE_INFO, status, "Evaluating _TSD")); + } return -ENODEV; } @@ -525,9 +545,6 @@ int acpi_processor_get_throttling_info(s int result = 0; int step = 0; int i = 0; - int no_ptc = 0; - int no_tss = 0; - int no_tsd = 0; ACPI_DEBUG_PRINT((ACPI_DB_INFO, "pblk_address[0x%08x] duty_offset[%d] duty_width[%d]\n", @@ -538,12 +555,14 @@ int acpi_processor_get_throttling_info(s if (!pr) return -EINVAL; - /* TBD: Support ACPI 2.0 objects */ - no_ptc = acpi_processor_get_throttling_control(pr); - no_tss = acpi_processor_get_throttling_states(pr); - no_tsd = acpi_processor_get_tsd(pr); - - if (no_ptc || no_tss) { + /* + * Evaluate _PTC, _TSS and _TPC + * They must all be present or none of them can be used. + */ + if (acpi_processor_get_throttling_control(pr) || + acpi_processor_get_throttling_states(pr) || + acpi_processor_get_platform_limit(pr)) + { pr->throttling.acpi_processor_get_throttling = &acpi_processor_get_throttling_fadt; pr->throttling.acpi_processor_set_throttling = @@ -555,6 +574,8 @@ int acpi_processor_get_throttling_info(s &acpi_processor_set_throttling_ptc; } + acpi_processor_get_tsd(pr); + if (!pr->throttling.address) { ACPI_DEBUG_PRINT((ACPI_DB_INFO, "No throttling register\n")); return 0; @@ -658,18 +679,20 @@ static int acpi_processor_throttling_seq pr->throttling.state_count - 1); seq_puts(seq, "states:\n"); - if (acpi_processor_get_throttling == acpi_processor_get_throttling_fadt) + if (pr->throttling.acpi_processor_get_throttling == + acpi_processor_get_throttling_fadt) { for (i = 0; i < pr->throttling.state_count; i++) seq_printf(seq, " %cT%d: %02d%%\n", (i == pr->throttling.state ? '*' : ' '), i, (pr->throttling.states[i].performance ? pr-> throttling.states[i].performance / 10 : 0)); - else + } else { for (i = 0; i < pr->throttling.state_count; i++) seq_printf(seq, " %cT%d: %02d%%\n", (i == pr->throttling.state ? '*' : ' '), i, (int)pr->throttling.states_tss[i]. freqpercentage); + } end: return 0; Index: linux-rt-rebase.q/drivers/acpi/sbs.c =================================================================== --- linux-rt-rebase.q.orig/drivers/acpi/sbs.c +++ linux-rt-rebase.q/drivers/acpi/sbs.c @@ -38,7 +38,6 @@ #define ACPI_SBS_CLASS "sbs" #define ACPI_AC_CLASS "ac_adapter" #define ACPI_BATTERY_CLASS "battery" -#define ACPI_SBS_HID "ACPI0002" #define ACPI_SBS_DEVICE_NAME "Smart Battery System" #define ACPI_SBS_FILE_INFO "info" #define ACPI_SBS_FILE_STATE "state" @@ -124,10 +123,17 @@ static int acpi_sbs_add(struct acpi_devi static int acpi_sbs_remove(struct acpi_device *device, int type); static int acpi_sbs_resume(struct acpi_device *device); +static const struct acpi_device_id sbs_device_ids[] = { + {"ACPI0001", 0}, + {"ACPI0005", 0}, + {"", 0}, +}; +MODULE_DEVICE_TABLE(acpi, sbs_device_ids); + static struct acpi_driver acpi_sbs_driver = { .name = "sbs", .class = ACPI_SBS_CLASS, - .ids = "ACPI0001,ACPI0005", + .ids = sbs_device_ids, .ops = { .add = acpi_sbs_add, .remove = acpi_sbs_remove, Index: linux-rt-rebase.q/drivers/acpi/scan.c =================================================================== --- linux-rt-rebase.q.orig/drivers/acpi/scan.c +++ linux-rt-rebase.q/drivers/acpi/scan.c @@ -16,7 +16,7 @@ ACPI_MODULE_NAME("scan"); extern struct acpi_device *acpi_root; #define ACPI_BUS_CLASS "system_bus" -#define ACPI_BUS_HID "ACPI_BUS" +#define ACPI_BUS_HID "LNXSYBUS" #define ACPI_BUS_DEVICE_NAME "System Bus" static LIST_HEAD(acpi_device_list); @@ -29,6 +29,62 @@ struct acpi_device_bus_id{ unsigned int instance_no; struct list_head node; }; + +/* + * Creates hid/cid(s) string needed for modalias and uevent + * e.g. on a device with hid:IBM0001 and cid:ACPI0001 you get: + * char *modalias: "acpi:IBM0001:ACPI0001" +*/ +int create_modalias(struct acpi_device *acpi_dev, char *modalias, int size){ + + int len; + + if (!acpi_dev->flags.hardware_id) + return -ENODEV; + + len = snprintf(modalias, size, "acpi:%s:", + acpi_dev->pnp.hardware_id); + if (len < 0 || len >= size) + return -EINVAL; + size -= len; + + if (acpi_dev->flags.compatible_ids) { + struct acpi_compatible_id_list *cid_list; + int i; + int count; + + cid_list = acpi_dev->pnp.cid_list; + for (i = 0; i < cid_list->count; i++) { + count = snprintf(&modalias[len], size, "%s:", + cid_list->id[i].value); + if (count < 0 || count >= size) { + printk(KERN_ERR "acpi: %s cid[%i] exceeds event buffer size", + acpi_dev->pnp.device_name, i); + break; + } + len += count; + size -= count; + } + } + + modalias[len] = '\0'; + return len; +} + +static ssize_t +acpi_device_modalias_show(struct device *dev, struct device_attribute *attr, char *buf) { + struct acpi_device *acpi_dev = to_acpi_device(dev); + int len; + + /* Device has no HID and no CID or string is >1024 */ + len = create_modalias(acpi_dev, buf, 1024); + if (len <= 0) + return 0; + buf[len++] = '\n'; + return len; +} +static DEVICE_ATTR(modalias, 0444, acpi_device_modalias_show, NULL); + static int acpi_eject_operation(acpi_handle handle, int lockable) { struct acpi_object_list arg_list; @@ -154,6 +210,12 @@ static int acpi_device_setup_files(struc goto end; } + if (dev->flags.hardware_id || dev->flags.compatible_ids){ + result = device_create_file(&dev->dev, &dev_attr_modalias); + if(result) + goto end; + } + /* * If device has _EJ0, 'eject' file is created that is used to trigger * hot-removal function from userland. @@ -178,6 +240,9 @@ static void acpi_device_remove_files(str if (ACPI_SUCCESS(status)) device_remove_file(&dev->dev, &dev_attr_eject); + if (dev->flags.hardware_id || dev->flags.compatible_ids) + device_remove_file(&dev->dev, &dev_attr_modalias); + if(dev->flags.hardware_id) device_remove_file(&dev->dev, &dev_attr_hid); if(dev->handle) @@ -186,6 +251,37 @@ static void acpi_device_remove_files(str /* -------------------------------------------------------------------------- ACPI Bus operations -------------------------------------------------------------------------- */ + +int acpi_match_device_ids(struct acpi_device *device, + const struct acpi_device_id *ids) +{ + const struct acpi_device_id *id; + + if (device->flags.hardware_id) { + for (id = ids; id->id[0]; id++) { + if (!strcmp((char*)id->id, device->pnp.hardware_id)) + return 0; + } + } + + if (device->flags.compatible_ids) { + struct acpi_compatible_id_list *cid_list = device->pnp.cid_list; + int i; + + for (id = ids; id->id[0]; id++) { + /* compare multiple _CID entries against driver ids */ + for (i = 0; i < cid_list->count; i++) { + if (!strcmp((char*)id->id, + cid_list->id[i].value)) + return 0; + } + } + } + + return -ENOENT; +} +EXPORT_SYMBOL(acpi_match_device_ids); + static void acpi_device_release(struct device *dev) { struct acpi_device *acpi_dev = to_acpi_device(dev); @@ -219,37 +315,19 @@ static int acpi_bus_match(struct device struct acpi_device *acpi_dev = to_acpi_device(dev); struct acpi_driver *acpi_drv = to_acpi_driver(drv); - return !acpi_match_ids(acpi_dev, acpi_drv->ids); + return !acpi_match_device_ids(acpi_dev, acpi_drv->ids); } static int acpi_device_uevent(struct device *dev, char **envp, int num_envp, - char *buffer, int buffer_size) + char *buffer, int buffer_size) { struct acpi_device *acpi_dev = to_acpi_device(dev); - int i = 0, length = 0, ret = 0; - - if (acpi_dev->flags.hardware_id) - ret = add_uevent_var(envp, num_envp, &i, - buffer, buffer_size, &length, - "HWID=%s", acpi_dev->pnp.hardware_id); - if (ret) - return -ENOMEM; - if (acpi_dev->flags.compatible_ids) { - int j; - struct acpi_compatible_id_list *cid_list; - cid_list = acpi_dev->pnp.cid_list; - - for (j = 0; j < cid_list->count; j++) { - ret = add_uevent_var(envp, num_envp, &i, buffer, - buffer_size, &length, "COMPTID=%s", - cid_list->id[j].value); - if (ret) - return -ENOMEM; - } + strcpy(buffer, "MODALIAS="); + if (create_modalias(acpi_dev, buffer + 9, buffer_size - 9) > 0) { + envp[0] = buffer; + envp[1] = NULL; } - - envp[i] = NULL; return 0; } @@ -543,25 +621,6 @@ void acpi_bus_data_handler(acpi_handle h return; } -int acpi_match_ids(struct acpi_device *device, char *ids) -{ - if (device->flags.hardware_id) - if (strstr(ids, device->pnp.hardware_id)) - return 0; - - if (device->flags.compatible_ids) { - struct acpi_compatible_id_list *cid_list = device->pnp.cid_list; - int i; - - /* compare multiple _CID entries against driver ids */ - for (i = 0; i < cid_list->count; i++) { - if (strstr(ids, cid_list->id[i].value)) - return 0; - } - } - return -ENOENT; -} - static int acpi_bus_get_perf_flags(struct acpi_device *device) { device->performance.state = ACPI_STATE_UNKNOWN; @@ -624,6 +683,13 @@ static int acpi_bus_get_wakeup_device_fl struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL }; union acpi_object *package = NULL; + struct acpi_device_id button_device_ids[] = { + {"PNP0C0D", 0}, + {"PNP0C0C", 0}, + {"PNP0C0E", 0}, + {"", 0}, + }; + /* _PRW */ status = acpi_evaluate_object(device->handle, "_PRW", NULL, &buffer); @@ -643,7 +709,7 @@ static int acpi_bus_get_wakeup_device_fl device->wakeup.flags.valid = 1; /* Power button, Lid switch always enable wakeup */ - if (!acpi_match_ids(device, "PNP0C0D,PNP0C0C,PNP0C0E")) + if (!acpi_match_device_ids(device, button_device_ids)) device->wakeup.flags.run_wake = 1; end: Index: linux-rt-rebase.q/drivers/acpi/sleep/Makefile =================================================================== --- linux-rt-rebase.q.orig/drivers/acpi/sleep/Makefile +++ linux-rt-rebase.q/drivers/acpi/sleep/Makefile @@ -1,5 +1,5 @@ obj-y := poweroff.o wakeup.o -obj-$(CONFIG_ACPI_SLEEP) += main.o -obj-$(CONFIG_ACPI_SLEEP_PROC_FS) += proc.o +obj-y += main.o +obj-$(CONFIG_X86) += proc.o EXTRA_CFLAGS += $(ACPI_CFLAGS) Index: linux-rt-rebase.q/drivers/acpi/sleep/main.c =================================================================== --- linux-rt-rebase.q.orig/drivers/acpi/sleep/main.c +++ linux-rt-rebase.q/drivers/acpi/sleep/main.c @@ -34,35 +34,55 @@ static u32 acpi_suspend_states[] = { static int init_8259A_after_S1; +extern int acpi_sleep_prepare(u32 acpi_state); +extern void acpi_power_off(void); + +static u32 acpi_target_sleep_state = ACPI_STATE_S0; + +/** + * acpi_pm_set_target - Set the target system sleep state to the state + * associated with given @pm_state, if supported. + */ + +static int acpi_pm_set_target(suspend_state_t pm_state) +{ + u32 acpi_state = acpi_suspend_states[pm_state]; + int error = 0; + + if (sleep_states[acpi_state]) { + acpi_target_sleep_state = acpi_state; + } else { + printk(KERN_ERR "ACPI does not support this state: %d\n", + pm_state); + error = -ENOSYS; + } + return error; +} + /** * acpi_pm_prepare - Do preliminary suspend work. - * @pm_state: suspend state we're entering. + * @pm_state: ignored * - * Make sure we support the state. If we do, and we need it, set the - * firmware waking vector and do arch-specific nastiness to get the - * wakeup code to the waking vector. + * If necessary, set the firmware waking vector and do arch-specific + * nastiness to get the wakeup code to the waking vector. */ -extern int acpi_sleep_prepare(u32 acpi_state); -extern void acpi_power_off(void); - static int acpi_pm_prepare(suspend_state_t pm_state) { - u32 acpi_state = acpi_suspend_states[pm_state]; + int error = acpi_sleep_prepare(acpi_target_sleep_state); - if (!sleep_states[acpi_state]) { - printk("acpi_pm_prepare does not support %d \n", pm_state); - return -EPERM; - } - return acpi_sleep_prepare(acpi_state); + if (error) + acpi_target_sleep_state = ACPI_STATE_S0; + + return error; } /** * acpi_pm_enter - Actually enter a sleep state. - * @pm_state: State we're entering. + * @pm_state: ignored * - * Flush caches and go to sleep. For STR or STD, we have to call - * arch-specific assembly, which in turn call acpi_enter_sleep_state(). + * Flush caches and go to sleep. For STR we have to call arch-specific + * assembly, which in turn call acpi_enter_sleep_state(). * It's unfortunate, but it works. Please fix if you're feeling frisky. */ @@ -70,31 +90,31 @@ static int acpi_pm_enter(suspend_state_t { acpi_status status = AE_OK; unsigned long flags = 0; - u32 acpi_state = acpi_suspend_states[pm_state]; + u32 acpi_state = acpi_target_sleep_state; ACPI_FLUSH_CPU_CACHE(); /* Do arch specific saving of state. */ - if (pm_state > PM_SUSPEND_STANDBY) { + if (acpi_state == ACPI_STATE_S3) { int error = acpi_save_state_mem(); - if (error) + + if (error) { + acpi_target_sleep_state = ACPI_STATE_S0; return error; + } } local_irq_save(flags); acpi_enable_wakeup_device(acpi_state); - switch (pm_state) { - case PM_SUSPEND_STANDBY: + switch (acpi_state) { + case ACPI_STATE_S1: barrier(); status = acpi_enter_sleep_state(acpi_state); break; - case PM_SUSPEND_MEM: + case ACPI_STATE_S3: do_suspend_lowlevel(); break; - - default: - return -EINVAL; } /* ACPI 3.0 specs (P62) says that it's the responsabilty @@ -107,12 +127,8 @@ static int acpi_pm_enter(suspend_state_t local_irq_restore(flags); printk(KERN_DEBUG "Back to C!\n"); - /* restore processor state - * We should only be here if we're coming back from STR or STD. - * And, in the case of the latter, the memory image should have already - * been loaded from disk. - */ - if (pm_state > PM_SUSPEND_STANDBY) + /* restore processor state */ + if (acpi_state == ACPI_STATE_S3) acpi_restore_state_mem(); return ACPI_SUCCESS(status) ? 0 : -EFAULT; @@ -120,7 +136,7 @@ static int acpi_pm_enter(suspend_state_t /** * acpi_pm_finish - Finish up suspend sequence. - * @pm_state: State we're coming out of. + * @pm_state: ignored * * This is called after we wake back up (or if entering the sleep state * failed). @@ -128,7 +144,7 @@ static int acpi_pm_enter(suspend_state_t static int acpi_pm_finish(suspend_state_t pm_state) { - u32 acpi_state = acpi_suspend_states[pm_state]; + u32 acpi_state = acpi_target_sleep_state; acpi_leave_sleep_state(acpi_state); acpi_disable_wakeup_device(acpi_state); @@ -136,10 +152,14 @@ static int acpi_pm_finish(suspend_state_ /* reset firmware waking vector */ acpi_set_firmware_waking_vector((acpi_physical_address) 0); + acpi_target_sleep_state = ACPI_STATE_S0; + +#ifdef CONFIG_X86 if (init_8259A_after_S1) { printk("Broken toshiba laptop -> kicking interrupts\n"); init_8259A(0); } +#endif return 0; } @@ -176,6 +196,7 @@ static int acpi_pm_state_valid(suspend_s static struct pm_ops acpi_pm_ops = { .valid = acpi_pm_state_valid, + .set_target = acpi_pm_set_target, .prepare = acpi_pm_prepare, .enter = acpi_pm_enter, .finish = acpi_pm_finish, @@ -235,6 +256,81 @@ static struct hibernation_ops acpi_hiber }; #endif /* CONFIG_SOFTWARE_SUSPEND */ +/** + * acpi_pm_device_sleep_state - return preferred power state of ACPI device + * in the system sleep state given by %acpi_target_sleep_state + * @dev: device to examine + * @wake: if set, the device should be able to wake up the system + * @d_min_p: used to store the upper limit of allowed states range + * Return value: preferred power state of the device on success, -ENODEV on + * failure (ie. if there's no 'struct acpi_device' for @dev) + * + * Find the lowest power (highest number) ACPI device power state that + * device @dev can be in while the system is in the sleep state represented + * by %acpi_target_sleep_state. If @wake is nonzero, the device should be + * able to wake up the system from this sleep state. If @d_min_p is set, + * the highest power (lowest number) device power state of @dev allowed + * in this system sleep state is stored at the location pointed to by it. + * + * The caller must ensure that @dev is valid before using this function. + * The caller is also responsible for figuring out if the device is + * supposed to be able to wake up the system and passing this information + * via @wake. + */ + +int acpi_pm_device_sleep_state(struct device *dev, int wake, int *d_min_p) +{ + acpi_handle handle = DEVICE_ACPI_HANDLE(dev); + struct acpi_device *adev; + char acpi_method[] = "_SxD"; + unsigned long d_min, d_max; + + if (!handle || ACPI_FAILURE(acpi_bus_get_device(handle, &adev))) { + printk(KERN_ERR "ACPI handle has no context!\n"); + return -ENODEV; + } + + acpi_method[2] = '0' + acpi_target_sleep_state; + /* + * If the sleep state is S0, we will return D3, but if the device has + * _S0W, we will use the value from _S0W + */ + d_min = ACPI_STATE_D0; + d_max = ACPI_STATE_D3; + + /* + * If present, _SxD methods return the minimum D-state (highest power + * state) we can use for the corresponding S-states. Otherwise, the + * minimum D-state is D0 (ACPI 3.x). + * + * NOTE: We rely on acpi_evaluate_integer() not clobbering the integer + * provided -- that's our fault recovery, we ignore retval. + */ + if (acpi_target_sleep_state > ACPI_STATE_S0) + acpi_evaluate_integer(handle, acpi_method, NULL, &d_min); + + /* + * If _PRW says we can wake up the system from the target sleep state, + * the D-state returned by _SxD is sufficient for that (we assume a + * wakeup-aware driver if wake is set). Still, if _SxW exists + * (ACPI 3.x), it should return the maximum (lowest power) D-state that + * can wake the system. _S0W may be valid, too. + */ + if (acpi_target_sleep_state == ACPI_STATE_S0 || + (wake && adev->wakeup.state.enabled && + adev->wakeup.sleep_state <= acpi_target_sleep_state)) { + acpi_method[3] = 'W'; + acpi_evaluate_integer(handle, acpi_method, NULL, &d_max); + /* Sanity check */ + if (d_max < d_min) + d_min = d_max; + } + + if (d_min_p) + *d_min_p = d_min; + return d_max; +} + /* * Toshiba fails to preserve interrupts over S1, reinitialization * of 8259 is needed after S1 resume. Index: linux-rt-rebase.q/drivers/acpi/sleep/poweroff.c =================================================================== --- linux-rt-rebase.q.orig/drivers/acpi/sleep/poweroff.c +++ linux-rt-rebase.q/drivers/acpi/sleep/poweroff.c @@ -18,7 +18,6 @@ int acpi_sleep_prepare(u32 acpi_state) { -#ifdef CONFIG_ACPI_SLEEP /* do we have a wakeup address for S2 and S3? */ if (acpi_state == ACPI_STATE_S3) { if (!acpi_wakeup_address) { @@ -31,7 +30,6 @@ int acpi_sleep_prepare(u32 acpi_state) } ACPI_FLUSH_CPU_CACHE(); acpi_enable_wakeup_device_prep(acpi_state); -#endif acpi_gpe_sleep_prepare(acpi_state); acpi_enter_sleep_state_prep(acpi_state); return 0; Index: linux-rt-rebase.q/drivers/acpi/sleep/proc.c =================================================================== --- linux-rt-rebase.q.orig/drivers/acpi/sleep/proc.c +++ linux-rt-rebase.q/drivers/acpi/sleep/proc.c @@ -14,8 +14,16 @@ #include "sleep.h" #define _COMPONENT ACPI_SYSTEM_COMPONENT + +/* + * this file provides support for: + * /proc/acpi/sleep + * /proc/acpi/alarm + * /proc/acpi/wakeup + */ + ACPI_MODULE_NAME("sleep") -#ifdef CONFIG_ACPI_SLEEP_PROC_SLEEP +#ifdef CONFIG_ACPI_PROCFS static int acpi_system_sleep_seq_show(struct seq_file *seq, void *offset) { int i; @@ -68,7 +76,7 @@ acpi_system_write_sleep(struct file *fil Done: return error ? error : count; } -#endif /* CONFIG_ACPI_SLEEP_PROC_SLEEP */ +#endif /* CONFIG_ACPI_PROCFS */ #if defined(CONFIG_RTC_DRV_CMOS) || defined(CONFIG_RTC_DRV_CMOS_MODULE) /* use /sys/class/rtc/rtcX/wakealarm instead; it's not ACPI-specific */ @@ -463,7 +471,7 @@ static const struct file_operations acpi .release = single_release, }; -#ifdef CONFIG_ACPI_SLEEP_PROC_SLEEP +#ifdef CONFIG_ACPI_PROCFS static const struct file_operations acpi_system_sleep_fops = { .open = acpi_system_sleep_open_fs, .read = seq_read, @@ -471,7 +479,7 @@ static const struct file_operations acpi .llseek = seq_lseek, .release = single_release, }; -#endif /* CONFIG_ACPI_SLEEP_PROC_SLEEP */ +#endif /* CONFIG_ACPI_PROCFS */ #ifdef HAVE_ACPI_LEGACY_ALARM static const struct file_operations acpi_system_alarm_fops = { @@ -498,14 +506,14 @@ static int __init acpi_sleep_proc_init(v if (acpi_disabled) return 0; -#ifdef CONFIG_ACPI_SLEEP_PROC_SLEEP +#ifdef CONFIG_ACPI_PROCFS /* 'sleep' [R/W] */ entry = create_proc_entry("sleep", S_IFREG | S_IRUGO | S_IWUSR, acpi_root_dir); if (entry) entry->proc_fops = &acpi_system_sleep_fops; -#endif +#endif /* CONFIG_ACPI_PROCFS */ #ifdef HAVE_ACPI_LEGACY_ALARM /* 'alarm' [R/W] */ Index: linux-rt-rebase.q/drivers/acpi/sleep/wakeup.c =================================================================== --- linux-rt-rebase.q.orig/drivers/acpi/sleep/wakeup.c +++ linux-rt-rebase.q/drivers/acpi/sleep/wakeup.c @@ -17,7 +17,6 @@ ACPI_MODULE_NAME("wakeup_devices") extern struct list_head acpi_wakeup_device_list; extern spinlock_t acpi_device_lock; -#ifdef CONFIG_ACPI_SLEEP /** * acpi_enable_wakeup_device_prep - prepare wakeup devices * @sleep_state: ACPI state @@ -180,7 +179,6 @@ static int __init acpi_wakeup_device_ini } late_initcall(acpi_wakeup_device_init); -#endif /* * Disable all wakeup GPEs before entering requested sleep state. Index: linux-rt-rebase.q/drivers/acpi/thermal.c =================================================================== --- linux-rt-rebase.q.orig/drivers/acpi/thermal.c +++ linux-rt-rebase.q/drivers/acpi/thermal.c @@ -92,10 +92,16 @@ static int acpi_thermal_polling_open_fs( static ssize_t acpi_thermal_write_polling(struct file *, const char __user *, size_t, loff_t *); +static const struct acpi_device_id thermal_device_ids[] = { + {ACPI_THERMAL_HID, 0}, + {"", 0}, +}; +MODULE_DEVICE_TABLE(acpi, thermal_device_ids); + static struct acpi_driver acpi_thermal_driver = { .name = "thermal", .class = ACPI_THERMAL_CLASS, - .ids = ACPI_THERMAL_HID, + .ids = thermal_device_ids, .ops = { .add = acpi_thermal_add, .remove = acpi_thermal_remove, Index: linux-rt-rebase.q/drivers/acpi/utilities/uteval.c =================================================================== --- linux-rt-rebase.q.orig/drivers/acpi/utilities/uteval.c +++ linux-rt-rebase.q/drivers/acpi/utilities/uteval.c @@ -407,7 +407,7 @@ acpi_ut_copy_id_string(char *destination acpi_status acpi_ut_execute_HID(struct acpi_namespace_node *device_node, - struct acpi_device_id *hid) + struct acpica_device_id *hid) { union acpi_operand_object *obj_desc; acpi_status status; @@ -609,7 +609,7 @@ acpi_ut_execute_CID(struct acpi_namespac acpi_status acpi_ut_execute_UID(struct acpi_namespace_node *device_node, - struct acpi_device_id *uid) + struct acpica_device_id *uid) { union acpi_operand_object *obj_desc; acpi_status status; Index: linux-rt-rebase.q/drivers/acpi/utilities/utmutex.c =================================================================== --- linux-rt-rebase.q.orig/drivers/acpi/utilities/utmutex.c +++ linux-rt-rebase.q/drivers/acpi/utilities/utmutex.c @@ -116,7 +116,7 @@ void acpi_ut_mutex_terminate(void) /* Delete the spinlocks */ acpi_os_delete_lock(acpi_gbl_gpe_lock); - acpi_os_delete_lock(acpi_gbl_hardware_lock); +// acpi_os_delete_lock(acpi_gbl_hardware_lock); return_VOID; } Index: linux-rt-rebase.q/drivers/acpi/video.c =================================================================== --- linux-rt-rebase.q.orig/drivers/acpi/video.c +++ linux-rt-rebase.q/drivers/acpi/video.c @@ -74,10 +74,16 @@ MODULE_LICENSE("GPL"); static int acpi_video_bus_add(struct acpi_device *device); static int acpi_video_bus_remove(struct acpi_device *device, int type); +static const struct acpi_device_id video_device_ids[] = { + {ACPI_VIDEO_HID, 0}, + {"", 0}, +}; +MODULE_DEVICE_TABLE(acpi, video_device_ids); + static struct acpi_driver acpi_video_bus = { .name = "video", .class = ACPI_VIDEO_CLASS, - .ids = ACPI_VIDEO_HID, + .ids = video_device_ids, .ops = { .add = acpi_video_bus_add, .remove = acpi_video_bus_remove, Index: linux-rt-rebase.q/drivers/ata/ata_piix.c =================================================================== --- linux-rt-rebase.q.orig/drivers/ata/ata_piix.c +++ linux-rt-rebase.q/drivers/ata/ata_piix.c @@ -91,6 +91,7 @@ #include #include #include +#include #define DRV_NAME "ata_piix" #define DRV_VERSION "2.11" @@ -140,6 +141,9 @@ enum { RV = -3, /* reserved */ PIIX_AHCI_DEVICE = 6, + + /* host->flags bits */ + PIIX_HOST_BROKEN_SUSPEND = (1 << 24), }; struct piix_map_db { @@ -159,6 +163,10 @@ static void piix_set_piomode (struct ata static void piix_set_dmamode (struct ata_port *ap, struct ata_device *adev); static void ich_set_dmamode (struct ata_port *ap, struct ata_device *adev); static int ich_pata_cable_detect(struct ata_port *ap); +#ifdef CONFIG_PM +static int piix_pci_device_suspend(struct pci_dev *pdev, pm_message_t mesg); +static int piix_pci_device_resume(struct pci_dev *pdev); +#endif static unsigned int in_module_init = 1; @@ -255,8 +263,8 @@ static struct pci_driver piix_pci_driver .probe = piix_init_one, .remove = ata_pci_remove_one, #ifdef CONFIG_PM - .suspend = ata_pci_device_suspend, - .resume = ata_pci_device_resume, + .suspend = piix_pci_device_suspend, + .resume = piix_pci_device_resume, #endif }; @@ -881,6 +889,107 @@ static void ich_set_dmamode (struct ata_ do_pata_set_dmamode(ap, adev, 1); } +#ifdef CONFIG_PM +static struct dmi_system_id piix_broken_suspend_dmi_table[] = { + { + .ident = "TECRA M5", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "TOSHIBA"), + DMI_MATCH(DMI_PRODUCT_NAME, "TECRA M5"), + }, + }, + { + .ident = "Satellite U200", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "TOSHIBA"), + DMI_MATCH(DMI_PRODUCT_NAME, "Satellite U200"), + }, + }, + { + .ident = "Satellite U205", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "TOSHIBA"), + DMI_MATCH(DMI_PRODUCT_NAME, "Satellite U205"), + }, + }, + { + .ident = "Portege M500", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "TOSHIBA"), + DMI_MATCH(DMI_PRODUCT_NAME, "PORTEGE M500"), + }, + }, + { } +}; + +static int piix_pci_device_suspend(struct pci_dev *pdev, pm_message_t mesg) +{ + struct ata_host *host = dev_get_drvdata(&pdev->dev); + unsigned long flags; + int rc = 0; + + rc = ata_host_suspend(host, mesg); + if (rc) + return rc; + + /* Some braindamaged ACPI suspend implementations expect the + * controller to be awake on entry; otherwise, it burns cpu + * cycles and power trying to do something to the sleeping + * beauty. + */ + if (dmi_check_system(piix_broken_suspend_dmi_table) && + mesg.event == PM_EVENT_SUSPEND) { + pci_save_state(pdev); + + /* mark its power state as "unknown", since we don't + * know if e.g. the BIOS will change its device state + * when we suspend. + */ + if (pdev->current_state == PCI_D0) + pdev->current_state = PCI_UNKNOWN; + + /* tell resume that it's waking up from broken suspend */ + spin_lock_irqsave(&host->lock, flags); + host->flags |= PIIX_HOST_BROKEN_SUSPEND; + spin_unlock_irqrestore(&host->lock, flags); + } else + ata_pci_device_do_suspend(pdev, mesg); + + return 0; +} + +static int piix_pci_device_resume(struct pci_dev *pdev) +{ + struct ata_host *host = dev_get_drvdata(&pdev->dev); + unsigned long flags; + int rc; + + if (host->flags & PIIX_HOST_BROKEN_SUSPEND) { + spin_lock_irqsave(&host->lock, flags); + host->flags &= ~PIIX_HOST_BROKEN_SUSPEND; + spin_unlock_irqrestore(&host->lock, flags); + + pci_set_power_state(pdev, PCI_D0); + pci_restore_state(pdev); + + /* PCI device wasn't disabled during suspend. Use + * __pci_reenable_device() to avoid affecting the + * enable count. + */ + rc = __pci_reenable_device(pdev); + if (rc) + dev_printk(KERN_ERR, &pdev->dev, "failed to enable " + "device after resume (%d)\n", rc); + } else + rc = ata_pci_device_do_resume(pdev); + + if (rc == 0) + ata_host_resume(host); + + return rc; +} +#endif + #define AHCI_PCI_BAR 5 #define AHCI_GLOBAL_CTL 0x04 #define AHCI_ENABLE (1 << 31) Index: linux-rt-rebase.q/drivers/ata/libata-scsi.c =================================================================== --- linux-rt-rebase.q.orig/drivers/ata/libata-scsi.c +++ linux-rt-rebase.q/drivers/ata/libata-scsi.c @@ -768,7 +768,7 @@ static void ata_scsi_dev_config(struct s * Decrement max hw segments accordingly. */ if (dev->class == ATA_DEV_ATAPI) { - request_queue_t *q = sdev->request_queue; + struct request_queue *q = sdev->request_queue; blk_queue_max_hw_segments(q, q->max_hw_segments - 1); } Index: linux-rt-rebase.q/drivers/ata/pata_ali.c =================================================================== --- linux-rt-rebase.q.orig/drivers/ata/pata_ali.c +++ linux-rt-rebase.q/drivers/ata/pata_ali.c @@ -45,7 +45,7 @@ static struct dmi_system_id cable_dmi_ta .ident = "HP Pavilion N5430", .matches = { DMI_MATCH(DMI_BOARD_VENDOR, "Hewlett-Packard"), - DMI_MATCH(DMI_BOARD_NAME, "OmniBook N32N-736"), + DMI_MATCH(DMI_BOARD_VERSION, "OmniBook N32N-736"), }, }, { } Index: linux-rt-rebase.q/drivers/ata/pata_hpt37x.c =================================================================== --- linux-rt-rebase.q.orig/drivers/ata/pata_hpt37x.c +++ linux-rt-rebase.q/drivers/ata/pata_hpt37x.c @@ -26,7 +26,7 @@ #include #define DRV_NAME "pata_hpt37x" -#define DRV_VERSION "0.6.6" +#define DRV_VERSION "0.6.7" struct hpt_clock { u8 xfer_speed; @@ -1103,17 +1103,17 @@ static int hpt37x_init_one(struct pci_de /* Select the DPLL clock. */ pci_write_config_byte(dev, 0x5b, 0x21); - pci_write_config_dword(dev, 0x5C, (f_high << 16) | f_low); + pci_write_config_dword(dev, 0x5C, (f_high << 16) | f_low | 0x100); for(adjust = 0; adjust < 8; adjust++) { if (hpt37x_calibrate_dpll(dev)) break; /* See if it'll settle at a fractionally different clock */ - if ((adjust & 3) == 3) { - f_low --; - f_high ++; - } - pci_write_config_dword(dev, 0x5C, (f_high << 16) | f_low); + if (adjust & 1) + f_low -= adjust >> 1; + else + f_high += adjust >> 1; + pci_write_config_dword(dev, 0x5C, (f_high << 16) | f_low | 0x100); } if (adjust == 8) { printk(KERN_WARNING "hpt37x: DPLL did not stabilize.\n"); Index: linux-rt-rebase.q/drivers/base/power/resume.c =================================================================== --- linux-rt-rebase.q.orig/drivers/base/power/resume.c +++ linux-rt-rebase.q/drivers/base/power/resume.c @@ -9,6 +9,7 @@ */ #include +#include #include #include "../base.h" #include "power.h" Index: linux-rt-rebase.q/drivers/block/amiflop.c =================================================================== --- linux-rt-rebase.q.orig/drivers/block/amiflop.c +++ linux-rt-rebase.q/drivers/block/amiflop.c @@ -1422,7 +1422,7 @@ static void redo_fd_request(void) goto repeat; } -static void do_fd_request(request_queue_t * q) +static void do_fd_request(struct request_queue * q) { redo_fd_request(); } Index: linux-rt-rebase.q/drivers/block/aoe/aoe.h =================================================================== --- linux-rt-rebase.q.orig/drivers/block/aoe/aoe.h +++ linux-rt-rebase.q/drivers/block/aoe/aoe.h @@ -138,7 +138,7 @@ struct aoedev { u16 maxbcnt; struct work_struct work;/* disk create work struct */ struct gendisk *gd; - request_queue_t blkq; + struct request_queue blkq; struct hd_geometry geo; sector_t ssize; struct timer_list timer; Index: linux-rt-rebase.q/drivers/block/aoe/aoeblk.c =================================================================== --- linux-rt-rebase.q.orig/drivers/block/aoe/aoeblk.c +++ linux-rt-rebase.q/drivers/block/aoe/aoeblk.c @@ -125,7 +125,7 @@ aoeblk_release(struct inode *inode, stru } static int -aoeblk_make_request(request_queue_t *q, struct bio *bio) +aoeblk_make_request(struct request_queue *q, struct bio *bio) { struct aoedev *d; struct buf *buf; Index: linux-rt-rebase.q/drivers/block/ataflop.c =================================================================== --- linux-rt-rebase.q.orig/drivers/block/ataflop.c +++ linux-rt-rebase.q/drivers/block/ataflop.c @@ -1466,7 +1466,7 @@ repeat: } -void do_fd_request(request_queue_t * q) +void do_fd_request(struct request_queue * q) { unsigned long flags; Index: linux-rt-rebase.q/drivers/block/cciss.c =================================================================== --- linux-rt-rebase.q.orig/drivers/block/cciss.c +++ linux-rt-rebase.q/drivers/block/cciss.c @@ -139,7 +139,7 @@ static struct board_type products[] = { static ctlr_info_t *hba[MAX_CTLR]; -static void do_cciss_request(request_queue_t *q); +static void do_cciss_request(struct request_queue *q); static irqreturn_t do_cciss_intr(int irq, void *dev_id); static int cciss_open(struct inode *inode, struct file *filep); static int cciss_release(struct inode *inode, struct file *filep); @@ -1584,7 +1584,7 @@ static int deregister_disk(struct gendis */ if (h->gendisk[0] != disk) { if (disk) { - request_queue_t *q = disk->queue; + struct request_queue *q = disk->queue; if (disk->flags & GENHD_FL_UP) del_gendisk(disk); if (q) { @@ -2511,7 +2511,7 @@ after_error_processing: /* * Get a request and submit it to the controller. */ -static void do_cciss_request(request_queue_t *q) +static void do_cciss_request(struct request_queue *q) { ctlr_info_t *h = q->queuedata; CommandList_struct *c; @@ -3380,7 +3380,7 @@ static int __devinit cciss_init_one(stru do { drive_info_struct *drv = &(hba[i]->drv[j]); struct gendisk *disk = hba[i]->gendisk[j]; - request_queue_t *q; + struct request_queue *q; /* Check if the disk was allocated already */ if (!disk){ @@ -3523,7 +3523,7 @@ static void __devexit cciss_remove_one(s for (j = 0; j < CISS_MAX_LUN; j++) { struct gendisk *disk = hba[i]->gendisk[j]; if (disk) { - request_queue_t *q = disk->queue; + struct request_queue *q = disk->queue; if (disk->flags & GENHD_FL_UP) del_gendisk(disk); Index: linux-rt-rebase.q/drivers/block/cpqarray.c =================================================================== --- linux-rt-rebase.q.orig/drivers/block/cpqarray.c +++ linux-rt-rebase.q/drivers/block/cpqarray.c @@ -161,7 +161,7 @@ static int ida_ioctl(struct inode *inode static int ida_getgeo(struct block_device *bdev, struct hd_geometry *geo); static int ida_ctlr_ioctl(ctlr_info_t *h, int dsk, ida_ioctl_t *io); -static void do_ida_request(request_queue_t *q); +static void do_ida_request(struct request_queue *q); static void start_io(ctlr_info_t *h); static inline void addQ(cmdlist_t **Qptr, cmdlist_t *c); @@ -391,7 +391,7 @@ static void __devexit cpqarray_remove_on /* pdev is NULL for eisa */ static int __init cpqarray_register_ctlr( int i, struct pci_dev *pdev) { - request_queue_t *q; + struct request_queue *q; int j; /* @@ -886,7 +886,7 @@ static inline cmdlist_t *removeQ(cmdlist * are in here (either via the dummy do_ida_request functions or by being * called from the interrupt handler */ -static void do_ida_request(request_queue_t *q) +static void do_ida_request(struct request_queue *q) { ctlr_info_t *h = q->queuedata; cmdlist_t *c; Index: linux-rt-rebase.q/drivers/block/floppy.c =================================================================== --- linux-rt-rebase.q.orig/drivers/block/floppy.c +++ linux-rt-rebase.q/drivers/block/floppy.c @@ -251,7 +251,7 @@ static int irqdma_allocated; static struct request *current_req; static struct request_queue *floppy_queue; -static void do_fd_request(request_queue_t * q); +static void do_fd_request(struct request_queue * q); #ifndef fd_get_dma_residue #define fd_get_dma_residue() get_dma_residue(FLOPPY_DMA) @@ -2981,7 +2981,7 @@ static void process_fd_request(void) schedule_bh(redo_fd_request); } -static void do_fd_request(request_queue_t * q) +static void do_fd_request(struct request_queue * q) { if (max_buffer_sectors == 0) { printk("VFS: do_fd_request called on non-open device\n"); @@ -4157,6 +4157,28 @@ static void floppy_device_release(struct complete(&device_release); } +static int floppy_suspend(struct platform_device *dev, pm_message_t state) +{ + floppy_release_irq_and_dma(); + + return 0; +} + +static int floppy_resume(struct platform_device *dev) +{ + floppy_grab_irq_and_dma(); + + return 0; +} + +static struct platform_driver floppy_driver = { + .suspend = floppy_suspend, + .resume = floppy_resume, + .driver = { + .name = "floppy", + }, +}; + static struct platform_device floppy_device[N_DRIVE]; static struct kobject *floppy_find(dev_t dev, int *part, void *data) @@ -4205,10 +4227,14 @@ static int __init floppy_init(void) if (err) goto out_put_disk; + err = platform_driver_register(&floppy_driver); + if (err) + goto out_unreg_blkdev; + floppy_queue = blk_init_queue(do_fd_request, &floppy_lock); if (!floppy_queue) { err = -ENOMEM; - goto out_unreg_blkdev; + goto out_unreg_driver; } blk_queue_max_sectors(floppy_queue, 64); @@ -4357,6 +4383,8 @@ out_flush_work: out_unreg_region: blk_unregister_region(MKDEV(FLOPPY_MAJOR, 0), 256); blk_cleanup_queue(floppy_queue); +out_unreg_driver: + platform_driver_unregister(&floppy_driver); out_unreg_blkdev: unregister_blkdev(FLOPPY_MAJOR, "fd"); out_put_disk: @@ -4548,6 +4576,7 @@ void cleanup_module(void) init_completion(&device_release); blk_unregister_region(MKDEV(FLOPPY_MAJOR, 0), 256); unregister_blkdev(FLOPPY_MAJOR, "fd"); + platform_driver_unregister(&floppy_driver); for (drive = 0; drive < N_DRIVE; drive++) { del_timer_sync(&motor_off_timer[drive]); Index: linux-rt-rebase.q/drivers/block/lguest_blk.c =================================================================== --- linux-rt-rebase.q.orig/drivers/block/lguest_blk.c +++ linux-rt-rebase.q/drivers/block/lguest_blk.c @@ -137,7 +137,7 @@ static void do_read(struct blockdev *bd, lguest_send_dma(bd->phys_addr, &ping); } -static void do_lgb_request(request_queue_t *q) +static void do_lgb_request(struct request_queue *q) { struct blockdev *bd; struct request *req; Index: linux-rt-rebase.q/drivers/block/loop.c =================================================================== --- linux-rt-rebase.q.orig/drivers/block/loop.c +++ linux-rt-rebase.q/drivers/block/loop.c @@ -529,7 +529,7 @@ static struct bio *loop_get_bio(struct l return bio; } -static int loop_make_request(request_queue_t *q, struct bio *old_bio) +static int loop_make_request(struct request_queue *q, struct bio *old_bio) { struct loop_device *lo = q->queuedata; int rw = bio_rw(old_bio); @@ -558,7 +558,7 @@ out: /* * kick off io on the underlying address space */ -static void loop_unplug(request_queue_t *q) +static void loop_unplug(struct request_queue *q) { struct loop_device *lo = q->queuedata; Index: linux-rt-rebase.q/drivers/block/nbd.c =================================================================== --- linux-rt-rebase.q.orig/drivers/block/nbd.c +++ linux-rt-rebase.q/drivers/block/nbd.c @@ -100,7 +100,7 @@ static const char *nbdcmd_to_ascii(int c static void nbd_end_request(struct request *req) { int uptodate = (req->errors == 0) ? 1 : 0; - request_queue_t *q = req->q; + struct request_queue *q = req->q; unsigned long flags; dprintk(DBG_BLKDEV, "%s: request %p: %s\n", req->rq_disk->disk_name, @@ -410,7 +410,7 @@ static void nbd_clear_que(struct nbd_dev * { printk( "Warning: Ignoring result!\n"); nbd_end_request( req ); } */ -static void do_nbd_request(request_queue_t * q) +static void do_nbd_request(struct request_queue * q) { struct request *req; Index: linux-rt-rebase.q/drivers/block/paride/pcd.c =================================================================== --- linux-rt-rebase.q.orig/drivers/block/paride/pcd.c +++ linux-rt-rebase.q/drivers/block/paride/pcd.c @@ -183,7 +183,7 @@ static int pcd_packet(struct cdrom_devic static int pcd_detect(void); static void pcd_probe_capabilities(void); static void do_pcd_read_drq(void); -static void do_pcd_request(request_queue_t * q); +static void do_pcd_request(struct request_queue * q); static void do_pcd_read(void); struct pcd_unit { @@ -713,7 +713,7 @@ static int pcd_detect(void) /* I/O request processing */ static struct request_queue *pcd_queue; -static void do_pcd_request(request_queue_t * q) +static void do_pcd_request(struct request_queue * q) { if (pcd_busy) return; Index: linux-rt-rebase.q/drivers/block/paride/pd.c =================================================================== --- linux-rt-rebase.q.orig/drivers/block/paride/pd.c +++ linux-rt-rebase.q/drivers/block/paride/pd.c @@ -698,7 +698,7 @@ static enum action pd_identify(struct pd /* end of io request engine */ -static void do_pd_request(request_queue_t * q) +static void do_pd_request(struct request_queue * q) { if (pd_req) return; Index: linux-rt-rebase.q/drivers/block/paride/pf.c =================================================================== --- linux-rt-rebase.q.orig/drivers/block/paride/pf.c +++ linux-rt-rebase.q/drivers/block/paride/pf.c @@ -202,7 +202,7 @@ module_param_array(drive3, int, NULL, 0) #define ATAPI_WRITE_10 0x2a static int pf_open(struct inode *inode, struct file *file); -static void do_pf_request(request_queue_t * q); +static void do_pf_request(struct request_queue * q); static int pf_ioctl(struct inode *inode, struct file *file, unsigned int cmd, unsigned long arg); static int pf_getgeo(struct block_device *bdev, struct hd_geometry *geo); @@ -760,7 +760,7 @@ static void pf_end_request(int uptodate) } } -static void do_pf_request(request_queue_t * q) +static void do_pf_request(struct request_queue * q) { if (pf_busy) return; Index: linux-rt-rebase.q/drivers/block/paride/pseudo.h =================================================================== --- linux-rt-rebase.q.orig/drivers/block/paride/pseudo.h +++ linux-rt-rebase.q/drivers/block/paride/pseudo.h @@ -43,7 +43,7 @@ static unsigned long ps_timeout; static int ps_tq_active = 0; static int ps_nice = 0; -static DEFINE_SPINLOCK(ps_spinlock __attribute__((unused))); +static __attribute__((unused)) DEFINE_SPINLOCK(ps_spinlock); static DECLARE_DELAYED_WORK(ps_tq, ps_tq_int); Index: linux-rt-rebase.q/drivers/block/pktcdvd.c =================================================================== --- linux-rt-rebase.q.orig/drivers/block/pktcdvd.c +++ linux-rt-rebase.q/drivers/block/pktcdvd.c @@ -752,7 +752,7 @@ static inline struct bio *pkt_get_list_f */ static int pkt_generic_packet(struct pktcdvd_device *pd, struct packet_command *cgc) { - request_queue_t *q = bdev_get_queue(pd->bdev); + struct request_queue *q = bdev_get_queue(pd->bdev); struct request *rq; int ret = 0; @@ -979,7 +979,7 @@ static void pkt_iosched_process_queue(st * Special care is needed if the underlying block device has a small * max_phys_segments value. */ -static int pkt_set_segment_merging(struct pktcdvd_device *pd, request_queue_t *q) +static int pkt_set_segment_merging(struct pktcdvd_device *pd, struct request_queue *q) { if ((pd->settings.size << 9) / CD_FRAMESIZE <= q->max_phys_segments) { /* @@ -2314,7 +2314,7 @@ static int pkt_open_dev(struct pktcdvd_d { int ret; long lba; - request_queue_t *q; + struct request_queue *q; /* * We need to re-open the cdrom device without O_NONBLOCK to be able @@ -2477,7 +2477,7 @@ static int pkt_end_io_read_cloned(struct return 0; } -static int pkt_make_request(request_queue_t *q, struct bio *bio) +static int pkt_make_request(struct request_queue *q, struct bio *bio) { struct pktcdvd_device *pd; char b[BDEVNAME_SIZE]; @@ -2626,7 +2626,7 @@ end_io: -static int pkt_merge_bvec(request_queue_t *q, struct bio *bio, struct bio_vec *bvec) +static int pkt_merge_bvec(struct request_queue *q, struct bio *bio, struct bio_vec *bvec) { struct pktcdvd_device *pd = q->queuedata; sector_t zone = ZONE(bio->bi_sector, pd); @@ -2647,7 +2647,7 @@ static int pkt_merge_bvec(request_queue_ static void pkt_init_queue(struct pktcdvd_device *pd) { - request_queue_t *q = pd->disk->queue; + struct request_queue *q = pd->disk->queue; blk_queue_make_request(q, pkt_make_request); blk_queue_hardsect_size(q, CD_FRAMESIZE); Index: linux-rt-rebase.q/drivers/block/ps2esdi.c =================================================================== --- linux-rt-rebase.q.orig/drivers/block/ps2esdi.c +++ linux-rt-rebase.q/drivers/block/ps2esdi.c @@ -64,7 +64,7 @@ static void reset_ctrl(void); static int ps2esdi_geninit(void); -static void do_ps2esdi_request(request_queue_t * q); +static void do_ps2esdi_request(struct request_queue * q); static void ps2esdi_readwrite(int cmd, struct request *req); @@ -473,7 +473,7 @@ static void __init ps2esdi_get_device_cf } /* strategy routine that handles most of the IO requests */ -static void do_ps2esdi_request(request_queue_t * q) +static void do_ps2esdi_request(struct request_queue * q) { struct request *req; /* since, this routine is called with interrupts cleared - they Index: linux-rt-rebase.q/drivers/block/ps3disk.c =================================================================== --- linux-rt-rebase.q.orig/drivers/block/ps3disk.c +++ linux-rt-rebase.q/drivers/block/ps3disk.c @@ -190,7 +190,7 @@ static int ps3disk_submit_flush_request( } static void ps3disk_do_request(struct ps3_storage_device *dev, - request_queue_t *q) + struct request_queue *q) { struct request *req; @@ -211,7 +211,7 @@ static void ps3disk_do_request(struct ps } } -static void ps3disk_request(request_queue_t *q) +static void ps3disk_request(struct request_queue *q) { struct ps3_storage_device *dev = q->queuedata; struct ps3disk_private *priv = dev->sbd.core.driver_data; @@ -404,7 +404,7 @@ static int ps3disk_identify(struct ps3_s return 0; } -static void ps3disk_prepare_flush(request_queue_t *q, struct request *req) +static void ps3disk_prepare_flush(struct request_queue *q, struct request *req) { struct ps3_storage_device *dev = q->queuedata; @@ -414,7 +414,7 @@ static void ps3disk_prepare_flush(reques req->cmd_type = REQ_TYPE_FLUSH; } -static int ps3disk_issue_flush(request_queue_t *q, struct gendisk *gendisk, +static int ps3disk_issue_flush(struct request_queue *q, struct gendisk *gendisk, sector_t *sector) { struct ps3_storage_device *dev = q->queuedata; Index: linux-rt-rebase.q/drivers/block/rd.c =================================================================== --- linux-rt-rebase.q.orig/drivers/block/rd.c +++ linux-rt-rebase.q/drivers/block/rd.c @@ -264,7 +264,7 @@ static int rd_blkdev_pagecache_IO(int rw * 19-JAN-1998 Richard Gooch Added devfs support * */ -static int rd_make_request(request_queue_t *q, struct bio *bio) +static int rd_make_request(struct request_queue *q, struct bio *bio) { struct block_device *bdev = bio->bi_bdev; struct address_space * mapping = bdev->bd_inode->i_mapping; Index: linux-rt-rebase.q/drivers/block/sunvdc.c =================================================================== --- linux-rt-rebase.q.orig/drivers/block/sunvdc.c +++ linux-rt-rebase.q/drivers/block/sunvdc.c @@ -444,7 +444,7 @@ out: return err; } -static void do_vdc_request(request_queue_t *q) +static void do_vdc_request(struct request_queue *q) { while (1) { struct request *req = elv_next_request(q); Index: linux-rt-rebase.q/drivers/block/swim3.c =================================================================== --- linux-rt-rebase.q.orig/drivers/block/swim3.c +++ linux-rt-rebase.q/drivers/block/swim3.c @@ -225,7 +225,7 @@ static unsigned short write_postamble[] static void swim3_select(struct floppy_state *fs, int sel); static void swim3_action(struct floppy_state *fs, int action); static int swim3_readbit(struct floppy_state *fs, int bit); -static void do_fd_request(request_queue_t * q); +static void do_fd_request(struct request_queue * q); static void start_request(struct floppy_state *fs); static void set_timeout(struct floppy_state *fs, int nticks, void (*proc)(unsigned long)); @@ -290,7 +290,7 @@ static int swim3_readbit(struct floppy_s return (stat & DATA) == 0; } -static void do_fd_request(request_queue_t * q) +static void do_fd_request(struct request_queue * q) { int i; for(i=0;iwait_q_prod % CARM_MAX_WAIT_Q; @@ -768,7 +768,7 @@ static inline void carm_push_q (struct c BUG_ON(host->wait_q_prod == host->wait_q_cons); /* overrun */ } -static inline request_queue_t *carm_pop_q(struct carm_host *host) +static inline struct request_queue *carm_pop_q(struct carm_host *host) { unsigned int idx; @@ -783,7 +783,7 @@ static inline request_queue_t *carm_pop_ static inline void carm_round_robin(struct carm_host *host) { - request_queue_t *q = carm_pop_q(host); + struct request_queue *q = carm_pop_q(host); if (q) { blk_start_queue(q); VPRINTK("STARTED QUEUE %p\n", q); @@ -802,7 +802,7 @@ static inline void carm_end_rq(struct ca } } -static void carm_oob_rq_fn(request_queue_t *q) +static void carm_oob_rq_fn(struct request_queue *q) { struct carm_host *host = q->queuedata; struct carm_request *crq; @@ -833,7 +833,7 @@ static void carm_oob_rq_fn(request_queue } } -static void carm_rq_fn(request_queue_t *q) +static void carm_rq_fn(struct request_queue *q) { struct carm_port *port = q->queuedata; struct carm_host *host = port->host; @@ -1494,7 +1494,7 @@ static int carm_init_disks(struct carm_h for (i = 0; i < CARM_MAX_PORTS; i++) { struct gendisk *disk; - request_queue_t *q; + struct request_queue *q; struct carm_port *port; port = &host->port[i]; @@ -1538,7 +1538,7 @@ static void carm_free_disks(struct carm_ for (i = 0; i < CARM_MAX_PORTS; i++) { struct gendisk *disk = host->port[i].disk; if (disk) { - request_queue_t *q = disk->queue; + struct request_queue *q = disk->queue; if (disk->flags & GENHD_FL_UP) del_gendisk(disk); @@ -1571,7 +1571,7 @@ static int carm_init_one (struct pci_dev struct carm_host *host; unsigned int pci_dac; int rc; - request_queue_t *q; + struct request_queue *q; unsigned int i; if (!printed_version++) Index: linux-rt-rebase.q/drivers/block/ub.c =================================================================== --- linux-rt-rebase.q.orig/drivers/block/ub.c +++ linux-rt-rebase.q/drivers/block/ub.c @@ -503,7 +503,7 @@ static void ub_cleanup(struct ub_dev *sc { struct list_head *p; struct ub_lun *lun; - request_queue_t *q; + struct request_queue *q; while (!list_empty(&sc->luns)) { p = sc->luns.next; @@ -619,7 +619,7 @@ static struct ub_scsi_cmd *ub_cmdq_pop(s * The request function is our main entry point */ -static void ub_request_fn(request_queue_t *q) +static void ub_request_fn(struct request_queue *q) { struct ub_lun *lun = q->queuedata; struct request *rq; @@ -2273,7 +2273,7 @@ err_core: static int ub_probe_lun(struct ub_dev *sc, int lnum) { struct ub_lun *lun; - request_queue_t *q; + struct request_queue *q; struct gendisk *disk; int rc; Index: linux-rt-rebase.q/drivers/block/umem.c =================================================================== --- linux-rt-rebase.q.orig/drivers/block/umem.c +++ linux-rt-rebase.q/drivers/block/umem.c @@ -114,7 +114,7 @@ struct cardinfo { */ struct bio *bio, *currentbio, **biotail; - request_queue_t *queue; + struct request_queue *queue; struct mm_page { dma_addr_t page_dma; @@ -357,7 +357,7 @@ static inline void reset_page(struct mm_ page->biotail = & page->bio; } -static void mm_unplug_device(request_queue_t *q) +static void mm_unplug_device(struct request_queue *q) { struct cardinfo *card = q->queuedata; unsigned long flags; @@ -541,7 +541,7 @@ static void process_page(unsigned long d -- mm_make_request ----------------------------------------------------------------------------------- */ -static int mm_make_request(request_queue_t *q, struct bio *bio) +static int mm_make_request(struct request_queue *q, struct bio *bio) { struct cardinfo *card = q->queuedata; pr_debug("mm_make_request %llu %u\n", Index: linux-rt-rebase.q/drivers/block/viodasd.c =================================================================== --- linux-rt-rebase.q.orig/drivers/block/viodasd.c +++ linux-rt-rebase.q/drivers/block/viodasd.c @@ -400,7 +400,7 @@ error_ret: /* * This is the external request processing routine */ -static void do_viodasd_request(request_queue_t *q) +static void do_viodasd_request(struct request_queue *q) { struct request *req; Index: linux-rt-rebase.q/drivers/block/xd.c =================================================================== --- linux-rt-rebase.q.orig/drivers/block/xd.c +++ linux-rt-rebase.q/drivers/block/xd.c @@ -298,7 +298,7 @@ static u_char __init xd_detect (u_char * } /* do_xd_request: handle an incoming request */ -static void do_xd_request (request_queue_t * q) +static void do_xd_request (struct request_queue * q) { struct request *req; Index: linux-rt-rebase.q/drivers/block/xd.h =================================================================== --- linux-rt-rebase.q.orig/drivers/block/xd.h +++ linux-rt-rebase.q/drivers/block/xd.h @@ -104,7 +104,7 @@ static int xd_manual_geo_init (char *com static u_char xd_detect (u_char *controller, unsigned int *address); static u_char xd_initdrives (void (*init_drive)(u_char drive)); -static void do_xd_request (request_queue_t * q); +static void do_xd_request (struct request_queue * q); static int xd_ioctl (struct inode *inode,struct file *file,unsigned int cmd,unsigned long arg); static int xd_readwrite (u_char operation,XD_INFO *disk,char *buffer,u_int block,u_int count); static void xd_recalibrate (u_char drive); Index: linux-rt-rebase.q/drivers/block/xen-blkfront.c =================================================================== --- linux-rt-rebase.q.orig/drivers/block/xen-blkfront.c +++ linux-rt-rebase.q/drivers/block/xen-blkfront.c @@ -241,7 +241,7 @@ static inline void flush_requests(struct * do_blkif_request * read a block; request is in a request queue */ -static void do_blkif_request(request_queue_t *rq) +static void do_blkif_request(struct request_queue *rq) { struct blkfront_info *info = NULL; struct request *req; @@ -287,7 +287,7 @@ wait: static int xlvbd_init_blk_queue(struct gendisk *gd, u16 sector_size) { - request_queue_t *rq; + struct request_queue *rq; rq = blk_init_queue(do_blkif_request, &blkif_io_lock); if (rq == NULL) Index: linux-rt-rebase.q/drivers/block/xsysace.c =================================================================== --- linux-rt-rebase.q.orig/drivers/block/xsysace.c +++ linux-rt-rebase.q/drivers/block/xsysace.c @@ -458,7 +458,7 @@ static inline void ace_fsm_yieldirq(stru } /* Get the next read/write request; ending requests that we don't handle */ -struct request *ace_get_next_request(request_queue_t * q) +struct request *ace_get_next_request(struct request_queue * q) { struct request *req; @@ -825,7 +825,7 @@ static irqreturn_t ace_interrupt(int irq /* --------------------------------------------------------------------- * Block ops */ -static void ace_request(request_queue_t * q) +static void ace_request(struct request_queue * q) { struct request *req; struct ace_device *ace; Index: linux-rt-rebase.q/drivers/block/z2ram.c =================================================================== --- linux-rt-rebase.q.orig/drivers/block/z2ram.c +++ linux-rt-rebase.q/drivers/block/z2ram.c @@ -67,7 +67,7 @@ static DEFINE_SPINLOCK(z2ram_lock); static struct block_device_operations z2_fops; static struct gendisk *z2ram_gendisk; -static void do_z2_request(request_queue_t *q) +static void do_z2_request(struct request_queue *q) { struct request *req; while ((req = elv_next_request(q)) != NULL) { Index: linux-rt-rebase.q/drivers/cdrom/cdrom.c =================================================================== --- linux-rt-rebase.q.orig/drivers/cdrom/cdrom.c +++ linux-rt-rebase.q/drivers/cdrom/cdrom.c @@ -2094,7 +2094,7 @@ out: static int cdrom_read_cdda_bpc(struct cdrom_device_info *cdi, __u8 __user *ubuf, int lba, int nframes) { - request_queue_t *q = cdi->disk->queue; + struct request_queue *q = cdi->disk->queue; struct request *rq; struct bio *bio; unsigned int len; Index: linux-rt-rebase.q/drivers/cdrom/viocd.c =================================================================== --- linux-rt-rebase.q.orig/drivers/cdrom/viocd.c +++ linux-rt-rebase.q/drivers/cdrom/viocd.c @@ -398,7 +398,7 @@ static void viocd_end_request(struct req static int rwreq; -static void do_viocd_request(request_queue_t *q) +static void do_viocd_request(struct request_queue *q) { struct request *req; Index: linux-rt-rebase.q/drivers/char/Kconfig =================================================================== --- linux-rt-rebase.q.orig/drivers/char/Kconfig +++ linux-rt-rebase.q/drivers/char/Kconfig @@ -726,7 +726,7 @@ config NVRAM config RTC tristate "Enhanced Real Time Clock Support" - depends on !PPC && !PARISC && !IA64 && !M68K && !SPARC64 && (!SPARC32 || PCI) && !FRV && !ARM && !SUPERH && !S390 + depends on !PPC && !PARISC && !IA64 && !M68K && !SPARC && !FRV && !ARM && !SUPERH && !S390 ---help--- If you say Y here and create a character special file /dev/rtc with major number 10 and minor number 135 using mknod ("man mknod"), you @@ -750,6 +750,68 @@ config RTC To compile this driver as a module, choose M here: the module will be called rtc. +config JS_RTC + tristate "Enhanced Real Time Clock Support" + depends on SPARC32 && PCI + ---help--- + If you say Y here and create a character special file /dev/rtc with + major number 10 and minor number 135 using mknod ("man mknod"), you + will get access to the real time clock (or hardware clock) built + into your computer. + + Every PC has such a clock built in. It can be used to generate + signals from as low as 1Hz up to 8192Hz, and can also be used + as a 24 hour alarm. It reports status information via the file + /proc/driver/rtc and its behaviour is set by various ioctls on + /dev/rtc. + + If you think you have a use for such a device (such as periodic data + sampling), then say Y here, and read + for details. + + To compile this driver as a module, choose M here: the + module will be called js-rtc. + +config RTC_HISTOGRAM + bool "Real Time Clock Histogram Support" + default n + depends on RTC + ---help--- + If you say Y here then the kernel will track the delivery and + wakeup latency of /dev/rtc using tasks and will report a + histogram to the kernel log when the application closes /dev/rtc. + +config BLOCKER + tristate "Priority Inheritance Debugging (Blocker) Device Support" + depends on X86 + default y + ---help--- + If you say Y here then a device will be created that the userspace + pi_test suite uses to test and measure kernel locking primitives. + +config LPPTEST + tristate "Parallel Port Based Latency Measurement Device" + depends on !PARPORT && X86 + default y + ---help--- + If you say Y here then a device will be created that the userspace + testlpp utility uses to measure IRQ latencies of a target system + from an independent measurement system. + + NOTE: this code assumes x86 PCs and that the parallel port is + bidirectional and is on IRQ 7. + + to use the device, both the target and the source system needs to + run a kernel with CONFIG_LPPTEST enabled. To measure latencies, + use the scripts/testlpp utility in your kernel source directory, + and run it (as root) on the source system - it will start printing + out the latencies it took to get a response from the target system: + + Latency of response: 12.2 usecs (121265 cycles) + + then generate various workloads on the target system to see how + (worst-case-) latencies are impacted. + config SGI_DS1286 tristate "SGI DS1286 RTC support" depends on SGI_IP22 @@ -1033,6 +1095,24 @@ config TELCLOCK /sys/devices/platform/telco_clock, with a number of files for controlling the behavior of this hardware. +config RMEM + tristate "Access to physical memory via /dev/rmem" + default m + help + The /dev/mem device only allows mmap() memory available to + I/O mapped memory; it does not allow access to "real" + physical memory. The /dev/rmem device is a hack which does + allow access to physical memory. We use this instead of + patching /dev/mem because we don't expect this functionality + to ever be accepted into mainline. + +config ALLOC_RTSJ_MEM + tristate "RTSJ-specific hack to reserve memory" + default m + help + The RTSJ TCK conformance test requires reserving some physical + memory for testing /dev/rmem. + config DEVPORT bool depends on !M68K Index: linux-rt-rebase.q/drivers/char/Makefile =================================================================== --- linux-rt-rebase.q.orig/drivers/char/Makefile +++ linux-rt-rebase.q/drivers/char/Makefile @@ -97,6 +97,10 @@ obj-$(CONFIG_GPIO_VR41XX) += vr41xx_giu. obj-$(CONFIG_GPIO_TB0219) += tb0219.o obj-$(CONFIG_TELCLOCK) += tlclk.o +obj-$(CONFIG_BLOCKER) += blocker.o +obj-$(CONFIG_LPPTEST) += lpptest.o +obj-$(CONFIG_RMEM) += rmem.o + obj-$(CONFIG_WATCHDOG) += watchdog/ obj-$(CONFIG_MWAVE) += mwave/ obj-$(CONFIG_AGP) += agp/ @@ -109,6 +113,11 @@ obj-$(CONFIG_TCG_TPM) += tpm/ obj-$(CONFIG_PS3_FLASH) += ps3flash.o +obj-$(CONFIG_JS_RTC) += js-rtc.o +js-rtc-y = rtc.o + +obj-$(CONFIG_ALLOC_RTSJ_MEM) += alloc_rtsj_mem.o + # Files generated that shall be removed upon make clean clean-files := consolemap_deftbl.c defkeymap.c Index: linux-rt-rebase.q/drivers/char/alloc_rtsj_mem.c =================================================================== --- /dev/null +++ linux-rt-rebase.q/drivers/char/alloc_rtsj_mem.c @@ -0,0 +1,88 @@ +/* + * alloc_rtsj_mem.c -- Hack to allocate some memory + * + * Copyright (C) 2005 by Theodore Ts'o + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * + */ + +#include +#include +#include +#include +#include +#include + +#include + +MODULE_AUTHOR("Theodore Tso"); +MODULE_DESCRIPTION("RTSJ alloc memory"); +MODULE_LICENSE("GPL"); + +static void *mem = 0; +int size = 0, addr = 0; + +module_param(size, int, 0444); +module_param(addr, int, 0444); + +static void __exit shutdown_module(void) +{ + kfree(mem); +} + +#ifndef MODULE +void __init alloc_rtsj_mem_early_setup(void) +{ + if (size > PAGE_SIZE*2) { + mem = alloc_bootmem(size); + if (mem) { + printk(KERN_INFO "alloc_rtsj_mem: got %d bytes " + "using alloc_bootmem\n", size); + } else { + printk(KERN_INFO "alloc_rtsj_mem: failed to " + "get %d bytes from alloc_bootmem\n", size); + } + } +} +#endif + +static int __init startup_module(void) +{ + static char test_string[] = "The BOFH: Servicing users the way the " + "military\n\tservices targets for 15 years.\n"; + + if (!size) + return 0; + + if (!mem) { + mem = kmalloc(size, GFP_KERNEL); + if (mem) { + printk(KERN_INFO "alloc_rtsj_mem: got %d bytes " + "using kmalloc\n", size); + } else { + printk(KERN_ERR "alloc_rtsj_mem: failed to get " + "%d bytes using kmalloc\n", size); + return -ENOMEM; + } + } + memcpy(mem, test_string, min(sizeof(test_string), (size_t) size)); + addr = virt_to_phys(mem); + return 0; +} + +module_init(startup_module); +module_exit(shutdown_module); + Index: linux-rt-rebase.q/drivers/char/blocker.c =================================================================== --- /dev/null +++ linux-rt-rebase.q/drivers/char/blocker.c @@ -0,0 +1,109 @@ +/* + * priority inheritance testing device + */ + +#include +#include +#include +#include + +#define BLOCKER_MINOR 221 + +#define BLOCK_IOCTL 4245 +#define BLOCK_SET_DEPTH 4246 + +#define BLOCKER_MAX_LOCK_DEPTH 10 + +void loop(int loops) +{ + int i; + + for (i = 0; i < loops; i++) + get_cycles(); +} + +static spinlock_t blocker_lock[BLOCKER_MAX_LOCK_DEPTH]; + +static unsigned int lock_depth = 1; + +void do_the_lock_and_loop(unsigned int args) +{ + int i, max; + + if (rt_task(current)) + max = lock_depth; + else if (lock_depth > 1) + max = (current->pid % lock_depth) + 1; + else + max = 1; + + /* Always lock from the top down */ + for (i = max-1; i >= 0; i--) + spin_lock(&blocker_lock[i]); + loop(args); + for (i = 0; i < max; i++) + spin_unlock(&blocker_lock[i]); +} + +static int blocker_open(struct inode *in, struct file *file) +{ + printk(KERN_INFO "blocker_open called\n"); + + return 0; +} + +static long blocker_ioctl(struct file *file, + unsigned int cmd, unsigned long args) +{ + switch(cmd) { + case BLOCK_IOCTL: + do_the_lock_and_loop(args); + return 0; + case BLOCK_SET_DEPTH: + if (args >= BLOCKER_MAX_LOCK_DEPTH) + return -EINVAL; + lock_depth = args; + return 0; + default: + return -EINVAL; + } +} + +static struct file_operations blocker_fops = { + .owner = THIS_MODULE, + .llseek = no_llseek, + .unlocked_ioctl = blocker_ioctl, + .open = blocker_open, +}; + +static struct miscdevice blocker_dev = +{ + BLOCKER_MINOR, + "blocker", + &blocker_fops +}; + +static int __init blocker_init(void) +{ + int i; + + if (misc_register(&blocker_dev)) + return -ENODEV; + + for (i = 0; i < BLOCKER_MAX_LOCK_DEPTH; i++) + spin_lock_init(blocker_lock + i); + + return 0; +} + +void __exit blocker_exit(void) +{ + printk(KERN_INFO "blocker device uninstalled\n"); + misc_deregister(&blocker_dev); +} + +module_init(blocker_init); +module_exit(blocker_exit); + +MODULE_LICENSE("GPL"); + Index: linux-rt-rebase.q/drivers/char/hpet.c =================================================================== --- linux-rt-rebase.q.orig/drivers/char/hpet.c +++ linux-rt-rebase.q/drivers/char/hpet.c @@ -1007,9 +1007,15 @@ static int hpet_acpi_remove(struct acpi_ return -EINVAL; } +static const struct acpi_device_id hpet_device_ids[] = { + {"PNP0103", 0}, + {"", 0}, +}; +MODULE_DEVICE_TABLE(acpi, hpet_device_ids); + static struct acpi_driver hpet_acpi_driver = { .name = "hpet", - .ids = "PNP0103", + .ids = hpet_device_ids, .ops = { .add = hpet_acpi_add, .remove = hpet_acpi_remove, Index: linux-rt-rebase.q/drivers/char/lpptest.c =================================================================== --- /dev/null +++ linux-rt-rebase.q/drivers/char/lpptest.c @@ -0,0 +1,178 @@ +/* + * /dev/lpptest device: test IRQ handling latencies over parallel port + * + * Copyright (C) 2005 Thomas Gleixner, Ingo Molnar + * + * licensed under the GPL + * + * You need to have CONFIG_PARPORT disabled for this device, it is a + * completely self-contained device that assumes sole ownership of the + * parallel port. + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +/* + * API wrappers so that the code can be shared with the -rt tree: + */ +#ifndef local_irq_disable +# define local_irq_disable local_irq_disable +# define local_irq_enable local_irq_enable +#endif + +#ifndef IRQ_NODELAY +# define IRQ_NODELAY 0 +# define IRQF_NODELAY 0 +#endif + +/* + * Driver: + */ +#define LPPTEST_CHAR_MAJOR 245 +#define LPPTEST_DEVICE_NAME "lpptest" + +#define LPPTEST_IRQ 7 + +#define LPPTEST_TEST _IOR (LPPTEST_CHAR_MAJOR, 1, unsigned long long) +#define LPPTEST_DISABLE _IOR (LPPTEST_CHAR_MAJOR, 2, unsigned long long) +#define LPPTEST_ENABLE _IOR (LPPTEST_CHAR_MAJOR, 3, unsigned long long) + +static char dev_id[] = "lpptest"; + +#define INIT_PORT() outb(0x04, 0x37a) +#define ENABLE_IRQ() outb(0x10, 0x37a) +#define DISABLE_IRQ() outb(0, 0x37a) + +static unsigned char out = 0x5a; + +/** + * Interrupt handler. Flip a bit in the reply. + */ +static int lpptest_irq (int irq, void *dev_id) +{ + out ^= 0xff; + outb(out, 0x378); + + return IRQ_HANDLED; +} + +static cycles_t test_response(void) +{ + cycles_t now, end; + unsigned char in; + int timeout = 0; + + local_irq_disable(); + in = inb(0x379); + inb(0x378); + outb(0x08, 0x378); + now = get_cycles(); + while(1) { + if (inb(0x379) != in) + break; + if (timeout++ > 1000000) { + outb(0x00, 0x378); + local_irq_enable(); + + return 0; + } + } + end = get_cycles(); + outb(0x00, 0x378); + local_irq_enable(); + + return end - now; +} + +static int lpptest_open(struct inode *inode, struct file *file) +{ + return 0; +} + +static int lpptest_close(struct inode *inode, struct file *file) +{ + return 0; +} + +int lpptest_ioctl(struct inode *inode, struct file *file, unsigned int ioctl_num, unsigned long ioctl_param) +{ + int retval = 0; + + switch (ioctl_num) { + + case LPPTEST_DISABLE: + DISABLE_IRQ(); + break; + + case LPPTEST_ENABLE: + ENABLE_IRQ(); + break; + + case LPPTEST_TEST: { + + cycles_t diff = test_response(); + if (copy_to_user((void *)ioctl_param, (void*) &diff, sizeof(diff))) + goto errcpy; + break; + } + default: retval = -EINVAL; + } + + return retval; + + errcpy: + return -EFAULT; +} + +static struct file_operations lpptest_dev_fops = { + .ioctl = lpptest_ioctl, + .open = lpptest_open, + .release = lpptest_close, +}; + +static int __init lpptest_init (void) +{ + if (register_chrdev(LPPTEST_CHAR_MAJOR, LPPTEST_DEVICE_NAME, &lpptest_dev_fops)) + { + printk(KERN_NOTICE "Can't allocate major number %d for lpptest.\n", + LPPTEST_CHAR_MAJOR); + return -EAGAIN; + } + + if (request_irq (LPPTEST_IRQ, lpptest_irq, 0, "lpptest", dev_id)) { + printk (KERN_WARNING "lpptest: irq %d in use. Unload parport module!\n", LPPTEST_IRQ); + unregister_chrdev(LPPTEST_CHAR_MAJOR, LPPTEST_DEVICE_NAME); + return -EAGAIN; + } + irq_desc[LPPTEST_IRQ].status |= IRQ_NODELAY; + irq_desc[LPPTEST_IRQ].action->flags |= IRQF_NODELAY | IRQF_DISABLED; + + INIT_PORT(); + ENABLE_IRQ(); + + return 0; +} +module_init (lpptest_init); + +static void __exit lpptest_exit (void) +{ + DISABLE_IRQ(); + + free_irq(LPPTEST_IRQ, dev_id); + unregister_chrdev(LPPTEST_CHAR_MAJOR, LPPTEST_DEVICE_NAME); +} +module_exit (lpptest_exit); + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("lpp test module"); + Index: linux-rt-rebase.q/drivers/char/random.c =================================================================== --- linux-rt-rebase.q.orig/drivers/char/random.c +++ linux-rt-rebase.q/drivers/char/random.c @@ -580,8 +580,11 @@ static void add_timer_randomness(struct preempt_disable(); /* if over the trickle threshold, use only 1 in 4096 samples */ if (input_pool.entropy_count > trickle_thresh && - (__get_cpu_var(trickle_count)++ & 0xfff)) - goto out; + (__get_cpu_var(trickle_count)++ & 0xfff)) { + preempt_enable(); + return; + } + preempt_enable(); sample.jiffies = jiffies; sample.cycles = get_cycles(); @@ -626,9 +629,6 @@ static void add_timer_randomness(struct if(input_pool.entropy_count >= random_read_wakeup_thresh) wake_up_interruptible(&random_read_wait); - -out: - preempt_enable(); } void add_input_randomness(unsigned int type, unsigned int code, Index: linux-rt-rebase.q/drivers/char/rmem.c =================================================================== --- /dev/null +++ linux-rt-rebase.q/drivers/char/rmem.c @@ -0,0 +1,134 @@ +/* + * Rmem - REALLY simple memory mapping demonstration. + * + * Copyright (C) 2005 by Theodore Ts'o + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * + */ + +#include +#include +#include + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +static int rmem_major = 0; +module_param(rmem_major, int, 0444); + +static struct class *rmem_class; + +MODULE_AUTHOR("Theodore Ts'o"); +MODULE_LICENSE("GPL"); + +struct page *rmem_vma_nopage(struct vm_area_struct *vma, + unsigned long address, int *type) +{ + struct page *pageptr; + unsigned long offset = vma->vm_pgoff << PAGE_SHIFT; + unsigned long physaddr = address - vma->vm_start + offset; + unsigned long pageframe = physaddr >> PAGE_SHIFT; + + if (!pfn_valid(pageframe)) + return NOPAGE_SIGBUS; + pageptr = pfn_to_page(pageframe); + get_page(pageptr); + if (type) + *type = VM_FAULT_MINOR; + return pageptr; +} + +static struct vm_operations_struct rmem_nopage_vm_ops = { + .nopage = rmem_vma_nopage, +}; + +static int rmem_nopage_mmap(struct file *filp, struct vm_area_struct *vma) +{ + unsigned long offset = vma->vm_pgoff << PAGE_SHIFT; + + if (offset >= __pa(high_memory) || (filp->f_flags & O_SYNC)) + vma->vm_flags |= VM_IO; + vma->vm_flags |= VM_RESERVED; + vma->vm_ops = &rmem_nopage_vm_ops; +#ifdef TAINT_USER + add_taint(TAINT_USER); +#endif + return 0; +} + +static struct file_operations rmem_nopage_ops = { + .owner = THIS_MODULE, + .mmap = rmem_nopage_mmap, +}; + +static struct cdev rmem_cdev = { + .kobj = {.name = "rmem", }, + .owner = THIS_MODULE, +}; + +static int __init rmem_init(void) +{ + int result; + dev_t dev = MKDEV(rmem_major, 0); + + /* Figure out our device number. */ + if (rmem_major) + result = register_chrdev_region(dev, 1, "rmem"); + else { + result = alloc_chrdev_region(&dev, 0, 1, "rmem"); + rmem_major = MAJOR(dev); + } + if (result < 0) { + printk(KERN_WARNING "rmem: unable to get major %d\n", rmem_major); + return result; + } + if (rmem_major == 0) + rmem_major = result; + + cdev_init(&rmem_cdev, &rmem_nopage_ops); + result = cdev_add(&rmem_cdev, dev, 1); + if (result) { + printk (KERN_NOTICE "Error %d adding /dev/rmem", result); + kobject_put(&rmem_cdev.kobj); + unregister_chrdev_region(dev, 1); + return 1; + } + + rmem_class = class_create(THIS_MODULE, "rmem"); + class_device_create(rmem_class, NULL, dev, NULL, "rmem"); + + return 0; +} + + +static void __exit rmem_cleanup(void) +{ + cdev_del(&rmem_cdev); + unregister_chrdev_region(MKDEV(rmem_major, 0), 1); + class_destroy(rmem_class); +} + + +module_init(rmem_init); +module_exit(rmem_cleanup); Index: linux-rt-rebase.q/drivers/char/rtc.c =================================================================== --- linux-rt-rebase.q.orig/drivers/char/rtc.c +++ linux-rt-rebase.q/drivers/char/rtc.c @@ -90,10 +90,35 @@ #include #include +#ifdef CONFIG_MIPS +# include +#endif static unsigned long rtc_port; static int rtc_irq = PCI_IRQ_NONE; #endif +#ifdef CONFIG_RTC_HISTOGRAM + +static cycles_t last_interrupt_time; + +#include + +#define CPU_MHZ (cpu_khz / 1000) + +#define HISTSIZE 10000 +static int histogram[HISTSIZE]; + +static int rtc_state; + +enum rtc_states { + S_STARTUP, /* First round - let the application start */ + S_IDLE, /* Waiting for an interrupt */ + S_WAITING_FOR_READ, /* Signal delivered. waiting for rtc_read() */ + S_READ_MISSED, /* Signal delivered, read() deadline missed */ +}; + +#endif + #ifdef CONFIG_HPET_RTC_IRQ #undef RTC_IRQ #endif @@ -222,7 +247,146 @@ static inline unsigned char rtc_is_updat return uip; } +#ifndef RTC_IRQ +# undef CONFIG_RTC_HISTOGRAM +#endif + +static inline void rtc_open_event(void) +{ +#ifdef CONFIG_RTC_HISTOGRAM + int i; + + last_interrupt_time = 0; + rtc_state = S_STARTUP; + rtc_irq_data = 0; + + for (i = 0; i < HISTSIZE; i++) + histogram[i] = 0; +#endif +} + +static inline void rtc_wake_event(void) +{ +#ifndef CONFIG_RTC_HISTOGRAM + kill_fasync (&rtc_async_queue, SIGIO, POLL_IN); +#else + if (!(rtc_status & RTC_IS_OPEN)) + return; + + switch (rtc_state) { + /* Startup */ + case S_STARTUP: + kill_fasync (&rtc_async_queue, SIGIO, POLL_IN); + break; + /* Waiting for an interrupt */ + case S_IDLE: + kill_fasync (&rtc_async_queue, SIGIO, POLL_IN); + last_interrupt_time = get_cycles(); + rtc_state = S_WAITING_FOR_READ; + break; + + /* Signal has been delivered. waiting for rtc_read() */ + case S_WAITING_FOR_READ: + /* + * Well foo. The usermode application didn't + * schedule and read in time. + */ + last_interrupt_time = get_cycles(); + rtc_state = S_READ_MISSED; + printk("Read missed before next interrupt\n"); + break; + /* Signal has been delivered, read() deadline was missed */ + case S_READ_MISSED: + /* + * Not much we can do here. We're waiting for the usermode + * application to read the rtc + */ + last_interrupt_time = get_cycles(); + break; + } +#endif +} + +static inline void rtc_read_event(void) +{ +#ifdef CONFIG_RTC_HISTOGRAM + cycles_t now = get_cycles(); + + switch (rtc_state) { + /* Startup */ + case S_STARTUP: + rtc_state = S_IDLE; + break; + + /* Waiting for an interrupt */ + case S_IDLE: + printk("bug in rtc_read(): called in state S_IDLE!\n"); + break; + case S_WAITING_FOR_READ: /* + * Signal has been delivered. + * waiting for rtc_read() + */ + /* + * Well done + */ + case S_READ_MISSED: /* + * Signal has been delivered, read() + * deadline was missed + */ + /* + * So, you finally got here. + */ + if (!last_interrupt_time) + printk("bug in rtc_read(): last_interrupt_time = 0\n"); + rtc_state = S_IDLE; + { + cycles_t latency = now - last_interrupt_time; + unsigned long delta; /* Microseconds */ + + delta = latency; + delta /= CPU_MHZ; + + if (delta > 1000 * 1000) { + printk("rtc: eek\n"); + } else { + unsigned long slot = delta; + if (slot >= HISTSIZE) + slot = HISTSIZE - 1; + histogram[slot]++; + if (delta > 2000) + printk("wow! That was a " + "%ld millisec bump\n", + delta / 1000); + } + } + rtc_state = S_IDLE; + break; + } +#endif +} + +static inline void rtc_close_event(void) +{ +#ifdef CONFIG_RTC_HISTOGRAM + int i = 0; + unsigned long total = 0; + + for (i = 0; i < HISTSIZE; i++) + total += histogram[i]; + if (!total) + return; + + printk("\nrtc latency histogram of {%s/%d, %lu samples}:\n", + current->comm, current->pid, total); + for (i = 0; i < HISTSIZE; i++) { + if (histogram[i]) + printk("%d %d\n", i, histogram[i]); + } +#endif +} + #ifdef RTC_IRQ + /* * A very tiny interrupt handler. It runs with IRQF_DISABLED set, * but there is possibility of conflicting with the set_rtc_mmss() @@ -266,9 +430,9 @@ irqreturn_t rtc_interrupt(int irq, void if (rtc_callback) rtc_callback->func(rtc_callback->private_data); spin_unlock(&rtc_task_lock); - wake_up_interruptible(&rtc_wait); - kill_fasync (&rtc_async_queue, SIGIO, POLL_IN); + rtc_wake_event(); + wake_up_interruptible(&rtc_wait); return IRQ_HANDLED; } @@ -378,6 +542,8 @@ static ssize_t rtc_read(struct file *fil schedule(); } while (1); + rtc_read_event(); + if (count == sizeof(unsigned int)) retval = put_user(data, (unsigned int __user *)buf) ?: sizeof(int); else @@ -610,6 +776,11 @@ static int rtc_do_ioctl(unsigned int cmd save_freq_select = CMOS_READ(RTC_FREQ_SELECT); CMOS_WRITE((save_freq_select|RTC_DIV_RESET2), RTC_FREQ_SELECT); + /* + * Make CMOS date writes nonpreemptible even on PREEMPT_RT. + * There's a limit to everything! =B-) + */ + preempt_disable(); #ifdef CONFIG_MACH_DECSTATION CMOS_WRITE(real_yrs, RTC_DEC_YEAR); #endif @@ -619,6 +790,7 @@ static int rtc_do_ioctl(unsigned int cmd CMOS_WRITE(hrs, RTC_HOURS); CMOS_WRITE(min, RTC_MINUTES); CMOS_WRITE(sec, RTC_SECONDS); + preempt_enable(); CMOS_WRITE(save_control, RTC_CONTROL); CMOS_WRITE(save_freq_select, RTC_FREQ_SELECT); @@ -717,6 +889,7 @@ static int rtc_open(struct inode *inode, if(rtc_status & RTC_IS_OPEN) goto out_busy; + rtc_open_event(); rtc_status |= RTC_IS_OPEN; rtc_irq_data = 0; @@ -772,6 +945,7 @@ no_irq: rtc_irq_data = 0; rtc_status &= ~RTC_IS_OPEN; spin_unlock_irq (&rtc_lock); + rtc_close_event(); return 0; } @@ -1141,8 +1315,10 @@ static void rtc_dropped_irq(unsigned lon spin_unlock_irq(&rtc_lock); +#ifndef CONFIG_PREEMPT_RT if (printk_ratelimit()) printk(KERN_WARNING "rtc: lost some interrupts at %ldHz.\n", freq); +#endif /* Now we have new data */ wake_up_interruptible(&rtc_wait); Index: linux-rt-rebase.q/drivers/char/sysrq.c =================================================================== --- linux-rt-rebase.q.orig/drivers/char/sysrq.c +++ linux-rt-rebase.q/drivers/char/sysrq.c @@ -208,6 +208,22 @@ static struct sysrq_key_op sysrq_showreg .enable_mask = SYSRQ_ENABLE_DUMP, }; +#if defined(__i386__) || defined(__x86_64__) + +static void sysrq_handle_showallregs(int key, struct tty_struct *tty) +{ + nmi_show_all_regs(); +} + +static struct sysrq_key_op sysrq_showallregs_op = { + .handler = sysrq_handle_showallregs, + .help_msg = "showalLcpupc", + .action_msg = "Show Regs On All CPUs", +}; +#else +#define sysrq_showallregs_op (*(struct sysrq_key_op *)0) +#endif + static void sysrq_handle_showstate(int key, struct tty_struct *tty) { show_state(); @@ -340,7 +356,7 @@ static struct sysrq_key_op *sysrq_key_ta &sysrq_kill_op, /* i */ NULL, /* j */ &sysrq_SAK_op, /* k */ - NULL, /* l */ + &sysrq_showallregs_op, /* l */ &sysrq_showmem_op, /* m */ &sysrq_unrt_op, /* n */ /* o: This will often be registered as 'Off' at init time */ Index: linux-rt-rebase.q/drivers/char/tty_io.c =================================================================== --- linux-rt-rebase.q.orig/drivers/char/tty_io.c +++ linux-rt-rebase.q/drivers/char/tty_io.c @@ -257,6 +257,7 @@ static int check_tty_count(struct tty_st printk(KERN_WARNING "Warning: dev (%s) tty->count(%d) " "!= #fd's(%d) in %s\n", tty->name, tty->count, count, routine); + dump_stack(); return count; } #endif @@ -3648,10 +3649,14 @@ void tty_flip_buffer_push(struct tty_str tty->buf.tail->commit = tty->buf.tail->used; spin_unlock_irqrestore(&tty->buf.lock, flags); +#ifndef CONFIG_PREEMPT_RT if (tty->low_latency) flush_to_ldisc(&tty->buf.work.work); else schedule_delayed_work(&tty->buf.work, 1); +#else + flush_to_ldisc(&tty->buf.work.work); +#endif } EXPORT_SYMBOL(tty_flip_buffer_push); Index: linux-rt-rebase.q/drivers/clocksource/acpi_pm.c =================================================================== --- linux-rt-rebase.q.orig/drivers/clocksource/acpi_pm.c +++ linux-rt-rebase.q/drivers/clocksource/acpi_pm.c @@ -30,13 +30,13 @@ */ u32 pmtmr_ioport __read_mostly; -static inline u32 read_pmtmr(void) +static notrace inline u32 read_pmtmr(void) { /* mask the output to 24 bits */ return inl(pmtmr_ioport) & ACPI_PM_MASK; } -u32 acpi_pm_read_verified(void) +u32 notrace acpi_pm_read_verified(void) { u32 v1 = 0, v2 = 0, v3 = 0; @@ -56,12 +56,12 @@ u32 acpi_pm_read_verified(void) return v2; } -static cycle_t acpi_pm_read_slow(void) +static notrace cycle_t acpi_pm_read_slow(void) { return (cycle_t)acpi_pm_read_verified(); } -static cycle_t acpi_pm_read(void) +static notrace cycle_t acpi_pm_read(void) { return (cycle_t)read_pmtmr(); } Index: linux-rt-rebase.q/drivers/cpuidle/Kconfig =================================================================== --- /dev/null +++ linux-rt-rebase.q/drivers/cpuidle/Kconfig @@ -0,0 +1,39 @@ +menu "CPU idle PM support" + +config CPU_IDLE + bool "CPU idle PM support" + help + CPU idle is a generic framework for supporting software-controlled + idle processor power management. It includes modular cross-platform + governors that can be swapped during runtime. + + If you're using a mobile platform that supports CPU idle PM (e.g. + an ACPI-capable notebook), you should say Y here. + +if CPU_IDLE + +comment "Governors" + +config CPU_IDLE_GOV_LADDER + tristate "'ladder' governor" + depends on CPU_IDLE + default y + help + This cpuidle governor promotes and demotes through the supported idle + states using residency time and bus master activity as metrics. This + algorithm was originally introduced in the old ACPI processor driver. + +config CPU_IDLE_GOV_MENU + tristate "'menu' governor" + depends on CPU_IDLE && NO_HZ + default y + help + This cpuidle governor evaluates all available states and chooses the + deepest state that meets all of the following constraints: BM activity, + expected time until next timer interrupt, and last break event time + delta. It is designed to minimize power consumption. Currently + dynticks is required. + +endif # CPU_IDLE + +endmenu Index: linux-rt-rebase.q/drivers/cpuidle/Makefile =================================================================== --- /dev/null +++ linux-rt-rebase.q/drivers/cpuidle/Makefile @@ -0,0 +1,5 @@ +# +# Makefile for cpuidle. +# + +obj-y += cpuidle.o driver.o governor.o sysfs.o governors/ Index: linux-rt-rebase.q/drivers/cpuidle/cpuidle.c =================================================================== --- /dev/null +++ linux-rt-rebase.q/drivers/cpuidle/cpuidle.c @@ -0,0 +1,306 @@ +/* + * cpuidle.c - core cpuidle infrastructure + * + * (C) 2006-2007 Venkatesh Pallipadi + * Shaohua Li + * Adam Belay + * + * This code is licenced under the GPL. + */ + +#include +#include +#include +#include +#include +#include +#include + +#include "cpuidle.h" + +DEFINE_PER_CPU(struct cpuidle_device *, cpuidle_devices); +EXPORT_PER_CPU_SYMBOL_GPL(cpuidle_devices); + +DEFINE_MUTEX(cpuidle_lock); +LIST_HEAD(cpuidle_detected_devices); +static void (*pm_idle_old)(void); + +/** + * cpuidle_idle_call - the main idle loop + * + * NOTE: no locks or semaphores should be used here + */ +static void cpuidle_idle_call(void) +{ + struct cpuidle_device *dev = __get_cpu_var(cpuidle_devices); + struct cpuidle_state *target_state; + int next_state; + + /* check if the device is ready */ + if (!dev || dev->status != CPUIDLE_STATUS_DOIDLE) { + if (pm_idle_old) + pm_idle_old(); + else + local_irq_enable(); + return; + } + + /* ask the governor for the next state */ + next_state = cpuidle_curr_governor->select(dev); + if (need_resched()) + return; + target_state = &dev->states[next_state]; + + /* enter the state and update stats */ + dev->last_residency = target_state->enter(dev, target_state); + dev->last_state = target_state; + target_state->time += dev->last_residency; + target_state->usage++; + + /* give the governor an opportunity to reflect on the outcome */ + if (cpuidle_curr_governor->reflect) + cpuidle_curr_governor->reflect(dev); +} + +/** + * cpuidle_install_idle_handler - installs the cpuidle idle loop handler + */ +void cpuidle_install_idle_handler(void) +{ + if (pm_idle != cpuidle_idle_call) { + /* Make sure all changes finished before we switch to new idle */ + smp_wmb(); + pm_idle = cpuidle_idle_call; + } +} + +/** + * cpuidle_uninstall_idle_handler - uninstalls the cpuidle idle loop handler + */ +void cpuidle_uninstall_idle_handler(void) +{ + if (pm_idle != pm_idle_old) { + pm_idle = pm_idle_old; + cpu_idle_wait(); + } +} + +/** + * cpuidle_rescan_device - prepares for a new state configuration + * @dev: the target device + * + * Must be called with cpuidle_lock aquired. + */ +void cpuidle_rescan_device(struct cpuidle_device *dev) +{ + int i; + + if (cpuidle_curr_governor->scan) + cpuidle_curr_governor->scan(dev); + + for (i = 0; i < dev->state_count; i++) { + dev->states[i].usage = 0; + dev->states[i].time = 0; + } +} + +/** + * cpuidle_add_device - attaches the driver to a CPU instance + * @sys_dev: the system device (driver model CPU representation) + */ +static int cpuidle_add_device(struct sys_device *sys_dev) +{ + int cpu = sys_dev->id; + struct cpuidle_device *dev; + + dev = per_cpu(cpuidle_devices, cpu); + + mutex_lock(&cpuidle_lock); + if (cpu_is_offline(cpu)) { + mutex_unlock(&cpuidle_lock); + return 0; + } + + if (!dev) { + dev = kzalloc(sizeof(struct cpuidle_device), GFP_KERNEL); + if (!dev) { + mutex_unlock(&cpuidle_lock); + return -ENOMEM; + } + init_completion(&dev->kobj_unregister); + per_cpu(cpuidle_devices, cpu) = dev; + } + dev->cpu = cpu; + + if (dev->status & CPUIDLE_STATUS_DETECTED) { + mutex_unlock(&cpuidle_lock); + return 0; + } + + cpuidle_add_sysfs(sys_dev); + + if (cpuidle_curr_driver) { + if (cpuidle_attach_driver(dev)) + goto err_ret; + } + + if (cpuidle_curr_governor) { + if (cpuidle_attach_governor(dev)) { + cpuidle_detach_driver(dev); + goto err_ret; + } + } + + if (cpuidle_device_can_idle(dev)) + cpuidle_install_idle_handler(); + + list_add(&dev->device_list, &cpuidle_detected_devices); + dev->status |= CPUIDLE_STATUS_DETECTED; + +err_ret: + mutex_unlock(&cpuidle_lock); + + return 0; +} + +/** + * __cpuidle_remove_device - detaches the driver from a CPU instance + * @sys_dev: the system device (driver model CPU representation) + * + * Must be called with cpuidle_lock aquired. + */ +static int __cpuidle_remove_device(struct sys_device *sys_dev) +{ + struct cpuidle_device *dev; + + dev = per_cpu(cpuidle_devices, sys_dev->id); + + if (!(dev->status & CPUIDLE_STATUS_DETECTED)) { + return 0; + } + dev->status &= ~CPUIDLE_STATUS_DETECTED; + /* NOTE: we don't wait because the cpu is already offline */ + if (cpuidle_curr_governor) + cpuidle_detach_governor(dev); + if (cpuidle_curr_driver) + cpuidle_detach_driver(dev); + cpuidle_remove_sysfs(sys_dev); + list_del(&dev->device_list); + wait_for_completion(&dev->kobj_unregister); + per_cpu(cpuidle_devices, sys_dev->id) = NULL; + kfree(dev); + + return 0; +} + +/** + * cpuidle_remove_device - detaches the driver from a CPU instance + * @sys_dev: the system device (driver model CPU representation) + */ +static int cpuidle_remove_device(struct sys_device *sys_dev) +{ + int ret; + mutex_lock(&cpuidle_lock); + ret = __cpuidle_remove_device(sys_dev); + mutex_unlock(&cpuidle_lock); + + return ret; +} + +static struct sysdev_driver cpuidle_sysdev_driver = { + .add = cpuidle_add_device, + .remove = cpuidle_remove_device, +}; + +static int cpuidle_cpu_callback(struct notifier_block *nfb, + unsigned long action, void *hcpu) +{ + struct sys_device *sys_dev; + + sys_dev = get_cpu_sysdev((unsigned long)hcpu); + + switch (action) { + case CPU_ONLINE: + cpuidle_add_device(sys_dev); + break; + case CPU_DOWN_PREPARE: + mutex_lock(&cpuidle_lock); + break; + case CPU_DEAD: + __cpuidle_remove_device(sys_dev); + mutex_unlock(&cpuidle_lock); + break; + case CPU_DOWN_FAILED: + mutex_unlock(&cpuidle_lock); + break; + } + + return NOTIFY_OK; +} + +static struct notifier_block __cpuinitdata cpuidle_cpu_notifier = +{ + .notifier_call = cpuidle_cpu_callback, +}; + +#ifdef CONFIG_SMP + +static void smp_callback(void *v) +{ + /* we already woke the CPU up, nothing more to do */ +} + +/* + * This function gets called when a part of the kernel has a new latency + * requirement. This means we need to get all processors out of their C-state, + * and then recalculate a new suitable C-state. Just do a cross-cpu IPI; that + * wakes them all right up. + */ +static int cpuidle_latency_notify(struct notifier_block *b, + unsigned long l, void *v) +{ + smp_call_function(smp_callback, NULL, 0, 1); + return NOTIFY_OK; +} + +static struct notifier_block cpuidle_latency_notifier = { + .notifier_call = cpuidle_latency_notify, +}; + +#define latency_notifier_init(x) do { register_latency_notifier(x); } while (0) + +#else /* CONFIG_SMP */ + +#define latency_notifier_init(x) do { } while (0) + +#endif /* CONFIG_SMP */ + +/** + * cpuidle_init - core initializer + */ +static int __init cpuidle_init(void) +{ + int ret; + + pm_idle_old = pm_idle; + + ret = cpuidle_add_class_sysfs(&cpu_sysdev_class); + if (ret) + return ret; + + register_hotcpu_notifier(&cpuidle_cpu_notifier); + + ret = sysdev_driver_register(&cpu_sysdev_class, &cpuidle_sysdev_driver); + + if (ret) { + cpuidle_remove_class_sysfs(&cpu_sysdev_class); + printk(KERN_ERR "cpuidle: failed to initialize\n"); + return ret; + } + + latency_notifier_init(&cpuidle_latency_notifier); + + return 0; +} + +core_initcall(cpuidle_init); Index: linux-rt-rebase.q/drivers/cpuidle/cpuidle.h =================================================================== --- /dev/null +++ linux-rt-rebase.q/drivers/cpuidle/cpuidle.h @@ -0,0 +1,50 @@ +/* + * cpuidle.h - The internal header file + */ + +#ifndef __DRIVER_CPUIDLE_H +#define __DRIVER_CPUIDLE_H + +#include + +/* For internal use only */ +extern struct cpuidle_governor *cpuidle_curr_governor; +extern struct cpuidle_driver *cpuidle_curr_driver; +extern struct list_head cpuidle_drivers; +extern struct list_head cpuidle_governors; +extern struct list_head cpuidle_detected_devices; +extern struct mutex cpuidle_lock; + +/* idle loop */ +extern void cpuidle_install_idle_handler(void); +extern void cpuidle_uninstall_idle_handler(void); +extern void cpuidle_rescan_device(struct cpuidle_device *dev); + +/* drivers */ +extern int cpuidle_attach_driver(struct cpuidle_device *dev); +extern void cpuidle_detach_driver(struct cpuidle_device *dev); +extern int cpuidle_switch_driver(struct cpuidle_driver *drv); + +/* governors */ +extern int cpuidle_attach_governor(struct cpuidle_device *dev); +extern void cpuidle_detach_governor(struct cpuidle_device *dev); +extern int cpuidle_switch_governor(struct cpuidle_governor *gov); + +/* sysfs */ +extern int cpuidle_add_class_sysfs(struct sysdev_class *cls); +extern void cpuidle_remove_class_sysfs(struct sysdev_class *cls); +extern int cpuidle_add_driver_sysfs(struct cpuidle_device *device); +extern void cpuidle_remove_driver_sysfs(struct cpuidle_device *device); +extern int cpuidle_add_sysfs(struct sys_device *sysdev); +extern void cpuidle_remove_sysfs(struct sys_device *sysdev); + +/** + * cpuidle_device_can_idle - determines if a CPU can utilize the idle loop + * @dev: the target CPU + */ +static inline int cpuidle_device_can_idle(struct cpuidle_device *dev) +{ + return (dev->status == CPUIDLE_STATUS_DOIDLE); +} + +#endif /* __DRIVER_CPUIDLE_H */ Index: linux-rt-rebase.q/drivers/cpuidle/driver.c =================================================================== --- /dev/null +++ linux-rt-rebase.q/drivers/cpuidle/driver.c @@ -0,0 +1,276 @@ +/* + * driver.c - driver support + * + * (C) 2006-2007 Venkatesh Pallipadi + * Shaohua Li + * Adam Belay + * + * This code is licenced under the GPL. + */ + +#include +#include +#include + +#include "cpuidle.h" + +LIST_HEAD(cpuidle_drivers); +struct cpuidle_driver *cpuidle_curr_driver; + + +/** + * cpuidle_attach_driver - attaches a driver to a CPU + * @dev: the target CPU + * + * Must be called with cpuidle_lock aquired. + */ +int cpuidle_attach_driver(struct cpuidle_device *dev) +{ + int ret; + + if (dev->status & CPUIDLE_STATUS_DRIVER_ATTACHED) + return -EIO; + + if (!try_module_get(cpuidle_curr_driver->owner)) + return -EINVAL; + + ret = cpuidle_curr_driver->init(dev); + if (ret) { + module_put(cpuidle_curr_driver->owner); + printk(KERN_INFO "cpuidle: driver %s failed to attach to " + "cpu %d\n", cpuidle_curr_driver->name, dev->cpu); + } else { + if (dev->status & CPUIDLE_STATUS_GOVERNOR_ATTACHED) + cpuidle_rescan_device(dev); + smp_wmb(); + dev->status |= CPUIDLE_STATUS_DRIVER_ATTACHED; + cpuidle_add_driver_sysfs(dev); + } + + return ret; +} + +/** + * cpuidle_detach_govenor - detaches a driver from a CPU + * @dev: the target CPU + * + * Must be called with cpuidle_lock aquired. + */ +void cpuidle_detach_driver(struct cpuidle_device *dev) +{ + if (dev->status & CPUIDLE_STATUS_DRIVER_ATTACHED) { + cpuidle_remove_driver_sysfs(dev); + dev->status &= ~CPUIDLE_STATUS_DRIVER_ATTACHED; + if (cpuidle_curr_driver->exit) + cpuidle_curr_driver->exit(dev); + module_put(cpuidle_curr_driver->owner); + } +} + +/** + * __cpuidle_find_driver - finds a driver of the specified name + * @str: the name + * + * Must be called with cpuidle_lock aquired. + */ +static struct cpuidle_driver * __cpuidle_find_driver(const char *str) +{ + struct cpuidle_driver *drv; + + list_for_each_entry(drv, &cpuidle_drivers, driver_list) + if (!strnicmp(str, drv->name, CPUIDLE_NAME_LEN)) + return drv; + + return NULL; +} + +/** + * cpuidle_switch_driver - changes the driver + * @drv: the new target driver + * + * NOTE: "drv" can be NULL to specify disabled + * Must be called with cpuidle_lock aquired. + */ +int cpuidle_switch_driver(struct cpuidle_driver *drv) +{ + struct cpuidle_device *dev; + + if (drv == cpuidle_curr_driver) + return -EINVAL; + + cpuidle_uninstall_idle_handler(); + + if (cpuidle_curr_driver) + list_for_each_entry(dev, &cpuidle_detected_devices, device_list) + cpuidle_detach_driver(dev); + + cpuidle_curr_driver = drv; + + if (drv) { + int ret = 1; + list_for_each_entry(dev, &cpuidle_detected_devices, device_list) + if (cpuidle_attach_driver(dev) == 0) + ret = 0; + + /* If attach on all devices fail, switch to NULL driver */ + if (ret) + cpuidle_curr_driver = NULL; + + if (cpuidle_curr_driver && cpuidle_curr_governor) { + printk(KERN_INFO "cpuidle: using driver %s\n", + drv->name); + cpuidle_install_idle_handler(); + } + } + + return 0; +} + +/** + * cpuidle_register_driver - registers a driver + * @drv: the driver + */ +int cpuidle_register_driver(struct cpuidle_driver *drv) +{ + int ret = -EEXIST; + + if (!drv || !drv->init) + return -EINVAL; + + mutex_lock(&cpuidle_lock); + if (__cpuidle_find_driver(drv->name) == NULL) { + ret = 0; + list_add_tail(&drv->driver_list, &cpuidle_drivers); + if (!cpuidle_curr_driver) + cpuidle_switch_driver(drv); + } + mutex_unlock(&cpuidle_lock); + + return ret; +} + +EXPORT_SYMBOL_GPL(cpuidle_register_driver); + +/** + * cpuidle_unregister_driver - unregisters a driver + * @drv: the driver + */ +void cpuidle_unregister_driver(struct cpuidle_driver *drv) +{ + if (!drv) + return; + + mutex_lock(&cpuidle_lock); + if (drv == cpuidle_curr_driver) + cpuidle_switch_driver(NULL); + list_del(&drv->driver_list); + mutex_unlock(&cpuidle_lock); +} + +EXPORT_SYMBOL_GPL(cpuidle_unregister_driver); + +static void __cpuidle_force_redetect(struct cpuidle_device *dev) +{ + cpuidle_remove_driver_sysfs(dev); + cpuidle_curr_driver->redetect(dev); + cpuidle_add_driver_sysfs(dev); +} + +/** + * cpuidle_force_redetect - redetects the idle states of a CPU + * + * @dev: the CPU to redetect + * @drv: the target driver + * + * Generally, the driver will call this when the supported states set has + * changed. (e.g. as the result of an ACPI transition to battery power) + */ +int cpuidle_force_redetect(struct cpuidle_device *dev, + struct cpuidle_driver *drv) +{ + int uninstalled = 0; + + mutex_lock(&cpuidle_lock); + + if (drv != cpuidle_curr_driver) { + mutex_unlock(&cpuidle_lock); + return 0; + } + + if (!(dev->status & CPUIDLE_STATUS_DRIVER_ATTACHED) || + !cpuidle_curr_driver->redetect) { + mutex_unlock(&cpuidle_lock); + return -EIO; + } + + if (cpuidle_device_can_idle(dev)) { + uninstalled = 1; + cpuidle_uninstall_idle_handler(); + } + + __cpuidle_force_redetect(dev); + + if (cpuidle_device_can_idle(dev)) { + cpuidle_rescan_device(dev); + cpuidle_install_idle_handler(); + } + + /* other devices are still ok */ + if (uninstalled) + cpuidle_install_idle_handler(); + + mutex_unlock(&cpuidle_lock); + + return 0; +} + +EXPORT_SYMBOL_GPL(cpuidle_force_redetect); + +/** + * cpuidle_force_redetect_devices - redetects the idle states of all CPUs + * + * @drv: the target driver + * + * Generally, the driver will call this when the supported states set has + * changed. (e.g. as the result of an ACPI transition to battery power) + */ +int cpuidle_force_redetect_devices(struct cpuidle_driver *drv) +{ + struct cpuidle_device *dev; + int ret = 0; + + mutex_lock(&cpuidle_lock); + + if (drv != cpuidle_curr_driver) + goto out; + + if (!cpuidle_curr_driver->redetect) { + ret = -EIO; + goto out; + } + + cpuidle_uninstall_idle_handler(); + + list_for_each_entry(dev, &cpuidle_detected_devices, device_list) + __cpuidle_force_redetect(dev); + + cpuidle_install_idle_handler(); +out: + mutex_unlock(&cpuidle_lock); + return ret; +} + +EXPORT_SYMBOL_GPL(cpuidle_force_redetect_devices); + +/** + * cpuidle_get_bm_activity - determines if BM activity has occured + */ +int cpuidle_get_bm_activity(void) +{ + if (cpuidle_curr_driver->bm_check) + return cpuidle_curr_driver->bm_check(); + else + return 0; +} +EXPORT_SYMBOL_GPL(cpuidle_get_bm_activity); + Index: linux-rt-rebase.q/drivers/cpuidle/governor.c =================================================================== --- /dev/null +++ linux-rt-rebase.q/drivers/cpuidle/governor.c @@ -0,0 +1,187 @@ +/* + * governor.c - governor support + * + * (C) 2006-2007 Venkatesh Pallipadi + * Shaohua Li + * Adam Belay + * + * This code is licenced under the GPL. + */ + +#include +#include +#include + +#include "cpuidle.h" + +LIST_HEAD(cpuidle_governors); +struct cpuidle_governor *cpuidle_curr_governor; + + +/** + * cpuidle_attach_governor - attaches a governor to a CPU + * @dev: the target CPU + * + * Must be called with cpuidle_lock aquired. + */ +int cpuidle_attach_governor(struct cpuidle_device *dev) +{ + int ret = 0; + + if(dev->status & CPUIDLE_STATUS_GOVERNOR_ATTACHED) + return -EIO; + + if (!try_module_get(cpuidle_curr_governor->owner)) + return -EINVAL; + + if (cpuidle_curr_governor->init) + ret = cpuidle_curr_governor->init(dev); + if (ret) { + module_put(cpuidle_curr_governor->owner); + printk(KERN_ERR "cpuidle: governor %s failed to attach to cpu %d\n", + cpuidle_curr_governor->name, dev->cpu); + } else { + if (dev->status & CPUIDLE_STATUS_DRIVER_ATTACHED) + cpuidle_rescan_device(dev); + smp_wmb(); + dev->status |= CPUIDLE_STATUS_GOVERNOR_ATTACHED; + } + + return ret; +} + +/** + * cpuidle_detach_govenor - detaches a governor from a CPU + * @dev: the target CPU + * + * Must be called with cpuidle_lock aquired. + */ +void cpuidle_detach_governor(struct cpuidle_device *dev) +{ + if (dev->status & CPUIDLE_STATUS_GOVERNOR_ATTACHED) { + dev->status &= ~CPUIDLE_STATUS_GOVERNOR_ATTACHED; + if (cpuidle_curr_governor->exit) + cpuidle_curr_governor->exit(dev); + module_put(cpuidle_curr_governor->owner); + } +} + +/** + * __cpuidle_find_governor - finds a governor of the specified name + * @str: the name + * + * Must be called with cpuidle_lock aquired. + */ +static struct cpuidle_governor * __cpuidle_find_governor(const char *str) +{ + struct cpuidle_governor *gov; + + list_for_each_entry(gov, &cpuidle_governors, governor_list) + if (!strnicmp(str, gov->name, CPUIDLE_NAME_LEN)) + return gov; + + return NULL; +} + +/** + * cpuidle_switch_governor - changes the governor + * @gov: the new target governor + * + * NOTE: "gov" can be NULL to specify disabled + * Must be called with cpuidle_lock aquired. + */ +int cpuidle_switch_governor(struct cpuidle_governor *gov) +{ + struct cpuidle_device *dev; + + if (gov == cpuidle_curr_governor) + return -EINVAL; + + cpuidle_uninstall_idle_handler(); + + if (cpuidle_curr_governor) + list_for_each_entry(dev, &cpuidle_detected_devices, device_list) + cpuidle_detach_governor(dev); + + cpuidle_curr_governor = gov; + + if (gov) { + list_for_each_entry(dev, &cpuidle_detected_devices, device_list) + cpuidle_attach_governor(dev); + if (cpuidle_curr_driver) + cpuidle_install_idle_handler(); + printk(KERN_INFO "cpuidle: using governor %s\n", gov->name); + } + + return 0; +} + +/** + * cpuidle_register_governor - registers a governor + * @gov: the governor + */ +int cpuidle_register_governor(struct cpuidle_governor *gov) +{ + int ret = -EEXIST; + + if (!gov || !gov->select) + return -EINVAL; + + mutex_lock(&cpuidle_lock); + if (__cpuidle_find_governor(gov->name) == NULL) { + ret = 0; + list_add_tail(&gov->governor_list, &cpuidle_governors); + if (!cpuidle_curr_governor || + cpuidle_curr_governor->rating < gov->rating) + cpuidle_switch_governor(gov); + } + mutex_unlock(&cpuidle_lock); + + return ret; +} + +EXPORT_SYMBOL_GPL(cpuidle_register_governor); + +/** + * cpuidle_replace_governor - find a replacement governor + * @exclude_rating: the rating that will be skipped while looking for + * new governor. + */ +static struct cpuidle_governor *cpuidle_replace_governor(int exclude_rating) +{ + struct cpuidle_governor *gov; + struct cpuidle_governor *ret_gov = NULL; + unsigned int max_rating = 0; + + list_for_each_entry(gov, &cpuidle_governors, governor_list) { + if (gov->rating == exclude_rating) + continue; + if (gov->rating > max_rating) { + max_rating = gov->rating; + ret_gov = gov; + } + } + + return ret_gov; +} + +/** + * cpuidle_unregister_governor - unregisters a governor + * @gov: the governor + */ +void cpuidle_unregister_governor(struct cpuidle_governor *gov) +{ + if (!gov) + return; + + mutex_lock(&cpuidle_lock); + if (gov == cpuidle_curr_governor) { + struct cpuidle_governor *new_gov; + new_gov = cpuidle_replace_governor(gov->rating); + cpuidle_switch_governor(new_gov); + } + list_del(&gov->governor_list); + mutex_unlock(&cpuidle_lock); +} + +EXPORT_SYMBOL_GPL(cpuidle_unregister_governor); Index: linux-rt-rebase.q/drivers/cpuidle/governors/Makefile =================================================================== --- /dev/null +++ linux-rt-rebase.q/drivers/cpuidle/governors/Makefile @@ -0,0 +1,6 @@ +# +# Makefile for cpuidle governors. +# + +obj-$(CONFIG_CPU_IDLE_GOV_LADDER) += ladder.o +obj-$(CONFIG_CPU_IDLE_GOV_MENU) += menu.o Index: linux-rt-rebase.q/drivers/cpuidle/governors/ladder.c =================================================================== --- /dev/null +++ linux-rt-rebase.q/drivers/cpuidle/governors/ladder.c @@ -0,0 +1,228 @@ +/* + * ladder.c - the residency ladder algorithm + * + * Copyright (C) 2001, 2002 Andy Grover + * Copyright (C) 2001, 2002 Paul Diefenbaugh + * Copyright (C) 2004, 2005 Dominik Brodowski + * + * (C) 2006-2007 Venkatesh Pallipadi + * Shaohua Li + * Adam Belay + * + * This code is licenced under the GPL. + */ + +#include +#include +#include +#include +#include + +#include +#include + +#define PROMOTION_COUNT 4 +#define DEMOTION_COUNT 1 + +/* + * bm_history -- bit-mask with a bit per jiffy of bus-master activity + * 1000 HZ: 0xFFFFFFFF: 32 jiffies = 32ms + * 800 HZ: 0xFFFFFFFF: 32 jiffies = 40ms + * 100 HZ: 0x0000000F: 4 jiffies = 40ms + * reduce history for more aggressive entry into C3 + */ +static unsigned int bm_history __read_mostly = + (HZ >= 800 ? 0xFFFFFFFF : ((1U << (HZ / 25)) - 1)); +module_param(bm_history, uint, 0644); + +struct ladder_device_state { + struct { + u32 promotion_count; + u32 demotion_count; + u32 promotion_time; + u32 demotion_time; + u32 bm; + } threshold; + struct { + int promotion_count; + int demotion_count; + } stats; +}; + +struct ladder_device { + struct ladder_device_state states[CPUIDLE_STATE_MAX]; + unsigned int bm_check:1; + unsigned long bm_check_timestamp; + unsigned long bm_activity; /* FIXME: bm activity should be global */ + int last_state_idx; +}; + +/** + * ladder_do_selection - prepares private data for a state change + * @ldev: the ladder device + * @old_idx: the current state index + * @new_idx: the new target state index + */ +static inline void ladder_do_selection(struct ladder_device *ldev, + int old_idx, int new_idx) +{ + ldev->states[old_idx].stats.promotion_count = 0; + ldev->states[old_idx].stats.demotion_count = 0; + ldev->last_state_idx = new_idx; +} + +/** + * ladder_select_state - selects the next state to enter + * @dev: the CPU + */ +static int ladder_select_state(struct cpuidle_device *dev) +{ + struct ladder_device *ldev = dev->governor_data; + struct ladder_device_state *last_state; + int last_residency, last_idx = ldev->last_state_idx; + + if (unlikely(!ldev)) + return 0; + + last_state = &ldev->states[last_idx]; + + /* demote if within BM threshold */ + if (ldev->bm_check) { + unsigned long diff; + + diff = jiffies - ldev->bm_check_timestamp; + if (diff > 31) + diff = 31; + + ldev->bm_activity <<= diff; + if (cpuidle_get_bm_activity()) + ldev->bm_activity |= ((1 << diff) - 1); + + ldev->bm_check_timestamp = jiffies; + if ((last_idx > 0) && + (last_state->threshold.bm & ldev->bm_activity)) { + ladder_do_selection(ldev, last_idx, last_idx - 1); + return last_idx - 1; + } + } + + if (dev->states[last_idx].flags & CPUIDLE_FLAG_TIME_VALID) + last_residency = cpuidle_get_last_residency(dev) - dev->states[last_idx].exit_latency; + else + last_residency = last_state->threshold.promotion_time + 1; + + /* consider promotion */ + if (last_idx < dev->state_count - 1 && + last_residency > last_state->threshold.promotion_time && + dev->states[last_idx + 1].exit_latency <= system_latency_constraint()) { + last_state->stats.promotion_count++; + last_state->stats.demotion_count = 0; + if (last_state->stats.promotion_count >= last_state->threshold.promotion_count) { + ladder_do_selection(ldev, last_idx, last_idx + 1); + return last_idx + 1; + } + } + + /* consider demotion */ + if (last_idx > 0 && + last_residency < last_state->threshold.demotion_time) { + last_state->stats.demotion_count++; + last_state->stats.promotion_count = 0; + if (last_state->stats.demotion_count >= last_state->threshold.demotion_count) { + ladder_do_selection(ldev, last_idx, last_idx - 1); + return last_idx - 1; + } + } + + /* otherwise remain at the current state */ + return last_idx; +} + +/** + * ladder_scan_device - scans a CPU's states and does setup + * @dev: the CPU + */ +static void ladder_scan_device(struct cpuidle_device *dev) +{ + int i, bm_check = 0; + struct ladder_device *ldev = dev->governor_data; + struct ladder_device_state *lstate; + struct cpuidle_state *state; + + ldev->last_state_idx = 0; + ldev->bm_check_timestamp = 0; + ldev->bm_activity = 0; + + for (i = 0; i < dev->state_count; i++) { + state = &dev->states[i]; + lstate = &ldev->states[i]; + + lstate->stats.promotion_count = 0; + lstate->stats.demotion_count = 0; + + lstate->threshold.promotion_count = PROMOTION_COUNT; + lstate->threshold.demotion_count = DEMOTION_COUNT; + + if (i < dev->state_count - 1) + lstate->threshold.promotion_time = state->exit_latency; + if (i > 0) + lstate->threshold.demotion_time = state->exit_latency; + if (state->flags & CPUIDLE_FLAG_CHECK_BM) { + lstate->threshold.bm = bm_history; + bm_check = 1; + } else + lstate->threshold.bm = 0; + } + + ldev->bm_check = bm_check; +} + +/** + * ladder_init_device - initializes a CPU-instance + * @dev: the CPU + */ +static int ladder_init_device(struct cpuidle_device *dev) +{ + dev->governor_data = kmalloc(sizeof(struct ladder_device), GFP_KERNEL); + + return !dev->governor_data; +} + +/** + * ladder_exit_device - exits a CPU-instance + * @dev: the CPU + */ +static void ladder_exit_device(struct cpuidle_device *dev) +{ + kfree(dev->governor_data); +} + +static struct cpuidle_governor ladder_governor = { + .name = "ladder", + .rating = 10, + .init = ladder_init_device, + .exit = ladder_exit_device, + .scan = ladder_scan_device, + .select = ladder_select_state, + .owner = THIS_MODULE, +}; + +/** + * init_ladder - initializes the governor + */ +static int __init init_ladder(void) +{ + return cpuidle_register_governor(&ladder_governor); +} + +/** + * exit_ladder - exits the governor + */ +static void __exit exit_ladder(void) +{ + cpuidle_unregister_governor(&ladder_governor); +} + +MODULE_LICENSE("GPL"); +module_init(init_ladder); +module_exit(exit_ladder); Index: linux-rt-rebase.q/drivers/cpuidle/governors/menu.c =================================================================== --- /dev/null +++ linux-rt-rebase.q/drivers/cpuidle/governors/menu.c @@ -0,0 +1,181 @@ +/* + * menu.c - the menu idle governor + * + * Copyright (C) 2006-2007 Adam Belay + * + * This code is licenced under the GPL. + */ + +#include +#include +#include +#include +#include +#include +#include + +#define BM_HOLDOFF 20000 /* 20 ms */ +#define DEMOTION_THRESHOLD 5 +#define DEMOTION_TIMEOUT_MULTIPLIER 1000 + +struct menu_device { + int last_state_idx; + + int deepest_break_state; + struct timespec break_expire_time_ts; + int break_last_cnt; + + int deepest_bm_state; + int bm_elapsed_us; + int bm_holdoff_us; +}; + +static DEFINE_PER_CPU(struct menu_device, menu_devices); + +/** + * menu_select - selects the next idle state to enter + * @dev: the CPU + */ +static int menu_select(struct cpuidle_device *dev) +{ + struct menu_device *data = &__get_cpu_var(menu_devices); + int i, expected_us, max_state = dev->state_count; + + /* discard BM history because it is sticky */ + cpuidle_get_bm_activity(); + + /* determine the expected residency time */ + expected_us = (s32) ktime_to_ns(tick_nohz_get_sleep_length()) / 1000; + + /* determine the maximum state compatible with current BM status */ + if (cpuidle_get_bm_activity()) + data->bm_elapsed_us = 0; + if (data->bm_elapsed_us <= data->bm_holdoff_us) + max_state = data->deepest_bm_state + 1; + + /* determine the maximum state compatible with recent idle breaks */ + if (data->deepest_break_state >= 0) { + struct timespec now; + ktime_get_ts(&now); + if (timespec_compare(&data->break_expire_time_ts, &now) > 0) { + max_state = min(max_state, + data->deepest_break_state + 1); + } else { + data->deepest_break_state = -1; + } + } + + /* find the deepest idle state that satisfies our constraints */ + for (i = 1; i < max_state; i++) { + struct cpuidle_state *s = &dev->states[i]; + + if (s->target_residency > expected_us) + break; + + if (s->exit_latency > system_latency_constraint()) + break; + } + + if (data->last_state_idx != i - 1) + data->break_last_cnt = 0; + + data->last_state_idx = i - 1; + return i - 1; +} + +/** + * menu_reflect - attempts to guess what happened after entry + * @dev: the CPU + * + * NOTE: it's important to be fast here because this operation will add to + * the overall exit latency. + */ +static void menu_reflect(struct cpuidle_device *dev) +{ + struct menu_device *data = &__get_cpu_var(menu_devices); + int last_idx = data->last_state_idx; + int measured_us = cpuidle_get_last_residency(dev); + struct cpuidle_state *target = &dev->states[last_idx]; + + /* + * Ugh, this idle state doesn't support residency measurements, so we + * are basically lost in the dark. As a compromise, assume we slept + * for one full standard timer tick. However, be aware that this + * could potentially result in a suboptimal state transition. + */ + if (!(target->flags & CPUIDLE_FLAG_TIME_VALID)) + measured_us = USEC_PER_SEC / HZ; + + data->bm_elapsed_us += measured_us; + + if (data->last_state_idx == 0) + return; + + /* + * Did something other than the timer interrupt + * cause an early break event? + */ + if (unlikely(measured_us < target->target_residency)) { + if (data->break_last_cnt > DEMOTION_THRESHOLD) { + data->deepest_break_state = data->last_state_idx - 1; + ktime_get_ts(&data->break_expire_time_ts); + timespec_add_ns(&data->break_expire_time_ts, + target->target_residency * + DEMOTION_TIMEOUT_MULTIPLIER); + } else { + data->break_last_cnt++; + } + } else { + if (data->break_last_cnt > 0) + data->break_last_cnt--; + } +} + +/** + * menu_scan_device - scans a CPU's states and does setup + * @dev: the CPU + */ +static void menu_scan_device(struct cpuidle_device *dev) +{ + struct menu_device *data = &per_cpu(menu_devices, dev->cpu); + int i; + + data->last_state_idx = 0; + data->bm_elapsed_us = 0; + data->bm_holdoff_us = BM_HOLDOFF; + data->deepest_break_state = -1; + + for (i = 1; i < dev->state_count; i++) + if (dev->states[i].flags & CPUIDLE_FLAG_CHECK_BM) + break; + data->deepest_bm_state = i - 1; +} + +static struct cpuidle_governor menu_governor = { + .name = "menu", + .rating = 20, + .scan = menu_scan_device, + .select = menu_select, + .reflect = menu_reflect, + .owner = THIS_MODULE, +}; + +/** + * init_menu - initializes the governor + */ +static int __init init_menu(void) +{ + return cpuidle_register_governor(&menu_governor); +} + +/** + * exit_menu - exits the governor + */ +static void __exit exit_menu(void) +{ + cpuidle_unregister_governor(&menu_governor); +} + +MODULE_LICENSE("GPL"); +module_init(init_menu); +module_exit(exit_menu); Index: linux-rt-rebase.q/drivers/cpuidle/sysfs.c =================================================================== --- /dev/null +++ linux-rt-rebase.q/drivers/cpuidle/sysfs.c @@ -0,0 +1,393 @@ +/* + * sysfs.c - sysfs support + * + * (C) 2006-2007 Shaohua Li + * + * This code is licenced under the GPL. + */ + +#include +#include +#include +#include + +#include "cpuidle.h" + +static unsigned int sysfs_switch; +static int __init cpuidle_sysfs_setup(char *unused) +{ + sysfs_switch = 1; + return 1; +} +__setup("cpuidle_sysfs_switch", cpuidle_sysfs_setup); + +static ssize_t show_available_drivers(struct sys_device *dev, char *buf) +{ + ssize_t i = 0; + struct cpuidle_driver *tmp; + + mutex_lock(&cpuidle_lock); + list_for_each_entry(tmp, &cpuidle_drivers, driver_list) { + if (i >= (ssize_t)((PAGE_SIZE/sizeof(char)) - CPUIDLE_NAME_LEN - 2)) + goto out; + i += scnprintf(&buf[i], CPUIDLE_NAME_LEN, "%s ", tmp->name); + } +out: + i+= sprintf(&buf[i], "\n"); + mutex_unlock(&cpuidle_lock); + return i; +} + +static ssize_t show_available_governors(struct sys_device *dev, char *buf) +{ + ssize_t i = 0; + struct cpuidle_governor *tmp; + + mutex_lock(&cpuidle_lock); + list_for_each_entry(tmp, &cpuidle_governors, governor_list) { + if (i >= (ssize_t)((PAGE_SIZE/sizeof(char)) - CPUIDLE_NAME_LEN - 2)) + goto out; + i += scnprintf(&buf[i], CPUIDLE_NAME_LEN, "%s ", tmp->name); + } + if (list_empty(&cpuidle_governors)) + i+= sprintf(&buf[i], "no governors"); +out: + i+= sprintf(&buf[i], "\n"); + mutex_unlock(&cpuidle_lock); + return i; +} + +static ssize_t show_current_driver(struct sys_device *dev, char *buf) +{ + ssize_t ret; + + mutex_lock(&cpuidle_lock); + ret = sprintf(buf, "%s\n", cpuidle_curr_driver->name); + mutex_unlock(&cpuidle_lock); + return ret; +} + +static ssize_t store_current_driver(struct sys_device *dev, + const char *buf, size_t count) +{ + char str[CPUIDLE_NAME_LEN]; + int len = count; + struct cpuidle_driver *tmp, *found = NULL; + + if (len > CPUIDLE_NAME_LEN) + len = CPUIDLE_NAME_LEN; + + if (sscanf(buf, "%s", str) != 1) + return -EINVAL; + + mutex_lock(&cpuidle_lock); + list_for_each_entry(tmp, &cpuidle_drivers, driver_list) { + if (strncmp(tmp->name, str, CPUIDLE_NAME_LEN) == 0) { + found = tmp; + break; + } + } + if (found) + cpuidle_switch_driver(found); + mutex_unlock(&cpuidle_lock); + + return count; +} + +static ssize_t show_current_governor(struct sys_device *dev, char *buf) +{ + ssize_t i; + + mutex_lock(&cpuidle_lock); + if (cpuidle_curr_governor) + i = sprintf(buf, "%s\n", cpuidle_curr_governor->name); + else + i = sprintf(buf, "no governor\n"); + mutex_unlock(&cpuidle_lock); + + return i; +} + +static ssize_t store_current_governor(struct sys_device *dev, + const char *buf, size_t count) +{ + char str[CPUIDLE_NAME_LEN]; + int len = count; + struct cpuidle_governor *tmp, *found = NULL; + + if (len > CPUIDLE_NAME_LEN) + len = CPUIDLE_NAME_LEN; + + if (sscanf(buf, "%s", str) != 1) + return -EINVAL; + + mutex_lock(&cpuidle_lock); + list_for_each_entry(tmp, &cpuidle_governors, governor_list) { + if (strncmp(tmp->name, str, CPUIDLE_NAME_LEN) == 0) { + found = tmp; + break; + } + } + if (found) + cpuidle_switch_governor(found); + mutex_unlock(&cpuidle_lock); + + return count; +} + +static SYSDEV_ATTR(current_driver_ro, 0444, show_current_driver, NULL); +static SYSDEV_ATTR(current_governor_ro, 0444, show_current_governor, NULL); + +static struct attribute *cpuclass_default_attrs[] = { + &attr_current_driver_ro.attr, + &attr_current_governor_ro.attr, + NULL +}; + +static SYSDEV_ATTR(available_drivers, 0444, show_available_drivers, NULL); +static SYSDEV_ATTR(available_governors, 0444, show_available_governors, NULL); +static SYSDEV_ATTR(current_driver, 0644, show_current_driver, + store_current_driver); +static SYSDEV_ATTR(current_governor, 0644, show_current_governor, + store_current_governor); + +static struct attribute *cpuclass_switch_attrs[] = { + &attr_available_drivers.attr, + &attr_available_governors.attr, + &attr_current_driver.attr, + &attr_current_governor.attr, + NULL +}; + +static struct attribute_group cpuclass_attr_group = { + .attrs = cpuclass_default_attrs, + .name = "cpuidle", +}; + +/** + * cpuidle_add_class_sysfs - add CPU global sysfs attributes + */ +int cpuidle_add_class_sysfs(struct sysdev_class *cls) +{ + if (sysfs_switch) + cpuclass_attr_group.attrs = cpuclass_switch_attrs; + + return sysfs_create_group(&cls->kset.kobj, &cpuclass_attr_group); +} + +/** + * cpuidle_remove_class_sysfs - remove CPU global sysfs attributes + */ +void cpuidle_remove_class_sysfs(struct sysdev_class *cls) +{ + sysfs_remove_group(&cls->kset.kobj, &cpuclass_attr_group); +} + +struct cpuidle_attr { + struct attribute attr; + ssize_t (*show)(struct cpuidle_device *, char *); + ssize_t (*store)(struct cpuidle_device *, const char *, size_t count); +}; + +#define define_one_ro(_name, show) \ + static struct cpuidle_attr attr_##_name = __ATTR(_name, 0444, show, NULL) +#define define_one_rw(_name, show, store) \ + static struct cpuidle_attr attr_##_name = __ATTR(_name, 0644, show, store) + +#define kobj_to_cpuidledev(k) container_of(k, struct cpuidle_device, kobj) +#define attr_to_cpuidleattr(a) container_of(a, struct cpuidle_attr, attr) +static ssize_t cpuidle_show(struct kobject * kobj, struct attribute * attr ,char * buf) +{ + int ret = -EIO; + struct cpuidle_device *dev = kobj_to_cpuidledev(kobj); + struct cpuidle_attr * cattr = attr_to_cpuidleattr(attr); + + if (cattr->show) { + mutex_lock(&cpuidle_lock); + ret = cattr->show(dev, buf); + mutex_unlock(&cpuidle_lock); + } + return ret; +} + +static ssize_t cpuidle_store(struct kobject * kobj, struct attribute * attr, + const char * buf, size_t count) +{ + int ret = -EIO; + struct cpuidle_device *dev = kobj_to_cpuidledev(kobj); + struct cpuidle_attr * cattr = attr_to_cpuidleattr(attr); + + if (cattr->store) { + mutex_lock(&cpuidle_lock); + ret = cattr->store(dev, buf, count); + mutex_unlock(&cpuidle_lock); + } + return ret; +} + +static struct sysfs_ops cpuidle_sysfs_ops = { + .show = cpuidle_show, + .store = cpuidle_store, +}; + +static void cpuidle_sysfs_release(struct kobject *kobj) +{ + struct cpuidle_device *dev = kobj_to_cpuidledev(kobj); + + complete(&dev->kobj_unregister); +} + +static struct kobj_type ktype_cpuidle = { + .sysfs_ops = &cpuidle_sysfs_ops, + .release = cpuidle_sysfs_release, +}; + +struct cpuidle_state_attr { + struct attribute attr; + ssize_t (*show)(struct cpuidle_state *, char *); + ssize_t (*store)(struct cpuidle_state *, const char *, size_t); +}; + +#define define_one_state_ro(_name, show) \ +static struct cpuidle_state_attr attr_##_name = __ATTR(_name, 0444, show, NULL) + +#define define_show_state_function(_name) \ +static ssize_t show_state_##_name(struct cpuidle_state *state, char *buf) \ +{ \ + return sprintf(buf, "%d\n", state->_name);\ +} + +define_show_state_function(exit_latency) +define_show_state_function(power_usage) +define_show_state_function(usage) +define_show_state_function(time) +define_one_state_ro(latency, show_state_exit_latency); +define_one_state_ro(power, show_state_power_usage); +define_one_state_ro(usage, show_state_usage); +define_one_state_ro(time, show_state_time); + +static struct attribute *cpuidle_state_default_attrs[] = { + &attr_latency.attr, + &attr_power.attr, + &attr_usage.attr, + &attr_time.attr, + NULL +}; + +#define kobj_to_state_obj(k) container_of(k, struct cpuidle_state_kobj, kobj) +#define kobj_to_state(k) (kobj_to_state_obj(k)->state) +#define attr_to_stateattr(a) container_of(a, struct cpuidle_state_attr, attr) +static ssize_t cpuidle_state_show(struct kobject * kobj, + struct attribute * attr ,char * buf) +{ + int ret = -EIO; + struct cpuidle_state *state = kobj_to_state(kobj); + struct cpuidle_state_attr * cattr = attr_to_stateattr(attr); + + if (cattr->show) + ret = cattr->show(state, buf); + + return ret; +} + +static struct sysfs_ops cpuidle_state_sysfs_ops = { + .show = cpuidle_state_show, +}; + +static void cpuidle_state_sysfs_release(struct kobject *kobj) +{ + struct cpuidle_state_kobj *state_obj = kobj_to_state_obj(kobj); + + complete(&state_obj->kobj_unregister); +} + +static struct kobj_type ktype_state_cpuidle = { + .sysfs_ops = &cpuidle_state_sysfs_ops, + .default_attrs = cpuidle_state_default_attrs, + .release = cpuidle_state_sysfs_release, +}; + +static void inline cpuidle_free_state_kobj(struct cpuidle_device *device, int i) +{ + kobject_unregister(&device->kobjs[i]->kobj); + wait_for_completion(&device->kobjs[i]->kobj_unregister); + kfree(device->kobjs[i]); + device->kobjs[i] = NULL; +} + +/** + * cpuidle_add_driver_sysfs - adds driver-specific sysfs attributes + * @device: the target device + */ +int cpuidle_add_driver_sysfs(struct cpuidle_device *device) +{ + int i, ret = -ENOMEM; + struct cpuidle_state_kobj *kobj; + + /* state statistics */ + for (i = 0; i < device->state_count; i++) { + kobj = kzalloc(sizeof(struct cpuidle_state_kobj), GFP_KERNEL); + if (!kobj) + goto error_state; + kobj->state = &device->states[i]; + init_completion(&kobj->kobj_unregister); + + kobj->kobj.parent = &device->kobj; + kobj->kobj.ktype = &ktype_state_cpuidle; + kobject_set_name(&kobj->kobj, "state%d", i); + ret = kobject_register(&kobj->kobj); + if (ret) { + kfree(kobj); + goto error_state; + } + device->kobjs[i] = kobj; + } + + return 0; + +error_state: + for (i = i - 1; i >= 0; i--) + cpuidle_free_state_kobj(device, i); + return ret; +} + +/** + * cpuidle_remove_driver_sysfs - removes driver-specific sysfs attributes + * @device: the target device + */ +void cpuidle_remove_driver_sysfs(struct cpuidle_device *device) +{ + int i; + + for (i = 0; i < device->state_count; i++) + cpuidle_free_state_kobj(device, i); +} + +/** + * cpuidle_add_sysfs - creates a sysfs instance for the target device + * @sysdev: the target device + */ +int cpuidle_add_sysfs(struct sys_device *sysdev) +{ + int cpu = sysdev->id; + struct cpuidle_device *dev; + + dev = per_cpu(cpuidle_devices, cpu); + dev->kobj.parent = &sysdev->kobj; + dev->kobj.ktype = &ktype_cpuidle; + kobject_set_name(&dev->kobj, "%s", "cpuidle"); + return kobject_register(&dev->kobj); +} + +/** + * cpuidle_remove_sysfs - deletes a sysfs instance on the target device + * @sysdev: the target device + */ +void cpuidle_remove_sysfs(struct sys_device *sysdev) +{ + int cpu = sysdev->id; + struct cpuidle_device *dev; + + dev = per_cpu(cpuidle_devices, cpu); + kobject_unregister(&dev->kobj); +} Index: linux-rt-rebase.q/drivers/ide/ide-cd.c =================================================================== --- linux-rt-rebase.q.orig/drivers/ide/ide-cd.c +++ linux-rt-rebase.q/drivers/ide/ide-cd.c @@ -3071,7 +3071,7 @@ static inline void ide_cdrom_add_setting /* * standard prep_rq_fn that builds 10 byte cmds */ -static int ide_cdrom_prep_fs(request_queue_t *q, struct request *rq) +static int ide_cdrom_prep_fs(struct request_queue *q, struct request *rq) { int hard_sect = queue_hardsect_size(q); long block = (long)rq->hard_sector / (hard_sect >> 9); @@ -3137,7 +3137,7 @@ static int ide_cdrom_prep_pc(struct requ return BLKPREP_OK; } -static int ide_cdrom_prep_fn(request_queue_t *q, struct request *rq) +static int ide_cdrom_prep_fn(struct request_queue *q, struct request *rq) { if (blk_fs_request(rq)) return ide_cdrom_prep_fs(q, rq); Index: linux-rt-rebase.q/drivers/ide/ide-disk.c =================================================================== --- linux-rt-rebase.q.orig/drivers/ide/ide-disk.c +++ linux-rt-rebase.q/drivers/ide/ide-disk.c @@ -679,7 +679,7 @@ static ide_proc_entry_t idedisk_proc[] = }; #endif /* CONFIG_IDE_PROC_FS */ -static void idedisk_prepare_flush(request_queue_t *q, struct request *rq) +static void idedisk_prepare_flush(struct request_queue *q, struct request *rq) { ide_drive_t *drive = q->queuedata; @@ -697,7 +697,7 @@ static void idedisk_prepare_flush(reques rq->buffer = rq->cmd; } -static int idedisk_issue_flush(request_queue_t *q, struct gendisk *disk, +static int idedisk_issue_flush(struct request_queue *q, struct gendisk *disk, sector_t *error_sector) { ide_drive_t *drive = q->queuedata; Index: linux-rt-rebase.q/drivers/ide/ide-floppy.c =================================================================== --- linux-rt-rebase.q.orig/drivers/ide/ide-floppy.c +++ linux-rt-rebase.q/drivers/ide/ide-floppy.c @@ -1672,9 +1672,9 @@ static int idefloppy_get_format_progress atapi_status_t status; unsigned long flags; - local_irq_save(flags); + local_irq_save_nort(flags); status.all = HWIF(drive)->INB(IDE_STATUS_REG); - local_irq_restore(flags); + local_irq_restore_nort(flags); progress_indication = !status.b.dsc ? 0 : 0x10000; } Index: linux-rt-rebase.q/drivers/ide/ide-io.c =================================================================== --- linux-rt-rebase.q.orig/drivers/ide/ide-io.c +++ linux-rt-rebase.q/drivers/ide/ide-io.c @@ -1199,7 +1199,7 @@ static void ide_do_request (ide_hwgroup_ ide_get_lock(ide_intr, hwgroup); /* caller must own ide_lock */ - BUG_ON(!irqs_disabled()); + BUG_ON_NONRT(!irqs_disabled()); while (!hwgroup->busy) { hwgroup->busy = 1; @@ -1327,7 +1327,7 @@ static void ide_do_request (ide_hwgroup_ /* * Passes the stuff to ide_do_request */ -void do_ide_request(request_queue_t *q) +void do_ide_request(struct request_queue *q) { ide_drive_t *drive = q->queuedata; @@ -1467,7 +1467,7 @@ void ide_timer_expiry (unsigned long dat #endif /* DISABLE_IRQ_NOSYNC */ /* local CPU only, * as if we were handling an interrupt */ - local_irq_disable(); + local_irq_disable_nort(); if (hwgroup->polling) { startstop = handler(drive); } else if (drive_is_ready(drive)) { Index: linux-rt-rebase.q/drivers/ide/ide-iops.c =================================================================== --- linux-rt-rebase.q.orig/drivers/ide/ide-iops.c +++ linux-rt-rebase.q/drivers/ide/ide-iops.c @@ -220,10 +220,10 @@ static void ata_input_data(ide_drive_t * if (io_32bit) { if (io_32bit & 2) { unsigned long flags; - local_irq_save(flags); + local_irq_save_nort(flags); ata_vlb_sync(drive, IDE_NSECTOR_REG); hwif->INSL(IDE_DATA_REG, buffer, wcount); - local_irq_restore(flags); + local_irq_restore_nort(flags); } else hwif->INSL(IDE_DATA_REG, buffer, wcount); } else { @@ -242,10 +242,10 @@ static void ata_output_data(ide_drive_t if (io_32bit) { if (io_32bit & 2) { unsigned long flags; - local_irq_save(flags); + local_irq_save_nort(flags); ata_vlb_sync(drive, IDE_NSECTOR_REG); hwif->OUTSL(IDE_DATA_REG, buffer, wcount); - local_irq_restore(flags); + local_irq_restore_nort(flags); } else hwif->OUTSL(IDE_DATA_REG, buffer, wcount); } else { @@ -540,12 +540,12 @@ int ide_wait_stat (ide_startstop_t *star if (!(stat & BUSY_STAT)) break; - local_irq_restore(flags); + local_irq_restore_nort(flags); *startstop = ide_error(drive, "status timeout", stat); return 1; } } - local_irq_restore(flags); + local_irq_restore_nort(flags); } /* * Allow status to settle, then read it again. @@ -720,17 +720,15 @@ int ide_driveid_update (ide_drive_t *dri printk("%s: CHECK for good STATUS\n", drive->name); return 0; } - local_irq_save(flags); - SELECT_MASK(drive, 0); id = kmalloc(SECTOR_WORDS*4, GFP_ATOMIC); - if (!id) { - local_irq_restore(flags); + if (!id) return 0; - } + local_irq_save_nort(flags); + SELECT_MASK(drive, 0); ata_input_data(drive, id, SECTOR_WORDS); (void) hwif->INB(IDE_STATUS_REG); /* clear drive IRQ */ - local_irq_enable(); - local_irq_restore(flags); + local_irq_enable_nort(); + local_irq_restore_nort(flags); ide_fix_driveid(id); if (id) { drive->id->dma_ultra = id->dma_ultra; @@ -810,7 +808,7 @@ int ide_config_drive_speed (ide_drive_t if (time_after(jiffies, timeout)) break; } - local_irq_restore(flags); + local_irq_restore_nort(flags); } /* Index: linux-rt-rebase.q/drivers/ide/ide-lib.c =================================================================== --- linux-rt-rebase.q.orig/drivers/ide/ide-lib.c +++ linux-rt-rebase.q/drivers/ide/ide-lib.c @@ -388,15 +388,16 @@ int ide_set_xfer_rate(ide_drive_t *drive static void ide_dump_opcode(ide_drive_t *drive) { + unsigned long flags; struct request *rq; u8 opcode = 0; int found = 0; - spin_lock(&ide_lock); + spin_lock_irqsave(&ide_lock, flags); rq = NULL; if (HWGROUP(drive)) rq = HWGROUP(drive)->rq; - spin_unlock(&ide_lock); + spin_unlock_irqrestore(&ide_lock, flags); if (!rq) return; if (rq->cmd_type == REQ_TYPE_ATA_CMD || @@ -425,10 +426,8 @@ static void ide_dump_opcode(ide_drive_t static u8 ide_dump_ata_status(ide_drive_t *drive, const char *msg, u8 stat) { ide_hwif_t *hwif = HWIF(drive); - unsigned long flags; u8 err = 0; - local_irq_save(flags); printk("%s: %s: status=0x%02x { ", drive->name, msg, stat); if (stat & BUSY_STAT) printk("Busy "); @@ -488,7 +487,7 @@ static u8 ide_dump_ata_status(ide_drive_ printk("\n"); } ide_dump_opcode(drive); - local_irq_restore(flags); + return err; } @@ -503,14 +502,11 @@ static u8 ide_dump_ata_status(ide_drive_ static u8 ide_dump_atapi_status(ide_drive_t *drive, const char *msg, u8 stat) { - unsigned long flags; - atapi_status_t status; atapi_error_t error; status.all = stat; error.all = 0; - local_irq_save(flags); printk("%s: %s: status=0x%02x { ", drive->name, msg, stat); if (status.b.bsy) printk("Busy "); @@ -536,7 +532,7 @@ static u8 ide_dump_atapi_status(ide_driv printk("}\n"); } ide_dump_opcode(drive); - local_irq_restore(flags); + return error.all; } Index: linux-rt-rebase.q/drivers/ide/ide-probe.c =================================================================== --- linux-rt-rebase.q.orig/drivers/ide/ide-probe.c +++ linux-rt-rebase.q/drivers/ide/ide-probe.c @@ -141,7 +141,7 @@ static inline void do_identify (ide_driv hwif->ata_input_data(drive, id, SECTOR_WORDS); drive->id_read = 1; - local_irq_enable(); + local_irq_enable_nort(); ide_fix_driveid(id); #if defined (CONFIG_SCSI_EATA_PIO) || defined (CONFIG_SCSI_EATA) @@ -323,14 +323,14 @@ static int actual_try_to_identify (ide_d unsigned long flags; /* local CPU only; some systems need this */ - local_irq_save(flags); + local_irq_save_nort(flags); /* drive returned ID */ do_identify(drive, cmd); /* drive responded with ID */ rc = 0; /* clear drive IRQ */ (void) hwif->INB(IDE_STATUS_REG); - local_irq_restore(flags); + local_irq_restore_nort(flags); } else { /* drive refused ID */ rc = 2; @@ -807,7 +807,7 @@ static void probe_hwif(ide_hwif_t *hwif, } while ((stat & BUSY_STAT) && time_after(timeout, jiffies)); } - local_irq_restore(flags); + local_irq_restore_nort(flags); /* * Use cached IRQ number. It might be (and is...) changed by probe * code above @@ -945,7 +945,7 @@ static void save_match(ide_hwif_t *hwif, */ static int ide_init_queue(ide_drive_t *drive) { - request_queue_t *q; + struct request_queue *q; ide_hwif_t *hwif = HWIF(drive); int max_sectors = 256; int max_sg_entries = PRD_ENTRIES; Index: linux-rt-rebase.q/drivers/ide/ide-taskfile.c =================================================================== --- linux-rt-rebase.q.orig/drivers/ide/ide-taskfile.c +++ linux-rt-rebase.q/drivers/ide/ide-taskfile.c @@ -278,7 +278,7 @@ static void ide_pio_sector(ide_drive_t * offset %= PAGE_SIZE; #ifdef CONFIG_HIGHMEM - local_irq_save(flags); + local_irq_save_nort(flags); #endif buf = kmap_atomic(page, KM_BIO_SRC_IRQ) + offset; @@ -298,7 +298,7 @@ static void ide_pio_sector(ide_drive_t * kunmap_atomic(buf, KM_BIO_SRC_IRQ); #ifdef CONFIG_HIGHMEM - local_irq_restore(flags); + local_irq_restore_nort(flags); #endif } @@ -464,7 +464,7 @@ ide_startstop_t pre_task_out_intr (ide_d } if (!drive->unmask) - local_irq_disable(); + local_irq_disable_nort(); ide_set_handler(drive, &task_out_intr, WAIT_WORSTCASE, NULL); ide_pio_datablock(drive, rq, 1); Index: linux-rt-rebase.q/drivers/ide/legacy/hd.c =================================================================== --- linux-rt-rebase.q.orig/drivers/ide/legacy/hd.c +++ linux-rt-rebase.q/drivers/ide/legacy/hd.c @@ -652,7 +652,7 @@ repeat: } } -static void do_hd_request (request_queue_t * q) +static void do_hd_request (struct request_queue * q) { disable_irq(HD_IRQ); hd_request(); Index: linux-rt-rebase.q/drivers/ide/pci/alim15x3.c =================================================================== --- linux-rt-rebase.q.orig/drivers/ide/pci/alim15x3.c +++ linux-rt-rebase.q/drivers/ide/pci/alim15x3.c @@ -326,7 +326,7 @@ static u8 ali15x3_tune_pio (ide_drive_t if (r_clc >= 16) r_clc = 0; } - local_irq_save(flags); + local_irq_save_nort(flags); /* * PIO mode => ATA FIFO on, ATAPI FIFO off @@ -348,7 +348,7 @@ static u8 ali15x3_tune_pio (ide_drive_t pci_write_config_byte(dev, port, s_clc); pci_write_config_byte(dev, port+drive->select.b.unit+2, (a_clc << 4) | r_clc); - local_irq_restore(flags); + local_irq_restore_nort(flags); /* * setup active rec @@ -519,7 +519,7 @@ static unsigned int __devinit init_chips } #endif /* defined(DISPLAY_ALI_TIMINGS) && defined(CONFIG_IDE_PROC_FS) */ - local_irq_save(flags); + local_irq_save_nort(flags); if (m5229_revision < 0xC2) { /* @@ -580,7 +580,7 @@ static unsigned int __devinit init_chips out: pci_dev_put(north); pci_dev_put(isa_dev); - local_irq_restore(flags); + local_irq_restore_nort(flags); return 0; } @@ -630,7 +630,7 @@ static u8 __devinit ata66_ali15x3(ide_hw unsigned long flags; u8 cbl = ATA_CBL_PATA40, tmpbyte; - local_irq_save(flags); + local_irq_save_nort(flags); if (m5229_revision >= 0xC2) { /* @@ -679,7 +679,7 @@ static u8 __devinit ata66_ali15x3(ide_hw pci_write_config_byte(dev, 0x53, tmpbyte); - local_irq_restore(flags); + local_irq_restore_nort(flags); return cbl; } Index: linux-rt-rebase.q/drivers/ide/pci/cs5530.c =================================================================== --- linux-rt-rebase.q.orig/drivers/ide/pci/cs5530.c +++ linux-rt-rebase.q/drivers/ide/pci/cs5530.c @@ -227,8 +227,8 @@ static unsigned int __devinit init_chips goto out; } - spin_lock_irqsave(&ide_lock, flags); - /* all CPUs (there should only be one CPU with this chipset) */ + /* Local CPU. ide_lock is acquired in do_ide_setup_pci_device. */ + local_irq_save(flags); /* * Enable BusMaster and MemoryWriteAndInvalidate for the cs5530: @@ -280,7 +280,7 @@ static unsigned int __devinit init_chips pci_write_config_byte(master_0, 0x42, 0x00); pci_write_config_byte(master_0, 0x43, 0xc1); - spin_unlock_irqrestore(&ide_lock, flags); + local_irq_restore(flags); out: pci_dev_put(master_0); Index: linux-rt-rebase.q/drivers/ide/pci/hpt366.c =================================================================== --- linux-rt-rebase.q.orig/drivers/ide/pci/hpt366.c +++ linux-rt-rebase.q/drivers/ide/pci/hpt366.c @@ -1351,7 +1351,7 @@ static void __devinit init_dma_hpt366(id dma_old = hwif->INB(dmabase + 2); - local_irq_save(flags); + local_irq_save_nort(flags); dma_new = dma_old; pci_read_config_byte(dev, hwif->channel ? 0x4b : 0x43, &masterdma); @@ -1362,7 +1362,7 @@ static void __devinit init_dma_hpt366(id if (dma_new != dma_old) hwif->OUTB(dma_new, dmabase + 2); - local_irq_restore(flags); + local_irq_restore_nort(flags); ide_setup_dma(hwif, dmabase, 8); } Index: linux-rt-rebase.q/drivers/input/ff-memless.c =================================================================== --- linux-rt-rebase.q.orig/drivers/input/ff-memless.c +++ linux-rt-rebase.q/drivers/input/ff-memless.c @@ -28,6 +28,7 @@ #include #include #include +#include #include #include Index: linux-rt-rebase.q/drivers/input/gameport/gameport.c =================================================================== --- linux-rt-rebase.q.orig/drivers/input/gameport/gameport.c +++ linux-rt-rebase.q/drivers/input/gameport/gameport.c @@ -21,6 +21,7 @@ #include #include #include +#include #include /* HZ */ #include #include @@ -102,12 +103,12 @@ static int gameport_measure_speed(struct tx = 1 << 30; for(i = 0; i < 50; i++) { - local_irq_save(flags); + local_irq_save_nort(flags); GET_TIME(t1); for (t = 0; t < 50; t++) gameport_read(gameport); GET_TIME(t2); GET_TIME(t3); - local_irq_restore(flags); + local_irq_restore_nort(flags); udelay(i * 10); if ((t = DELTA(t2,t1) - DELTA(t3,t2)) < tx) tx = t; } @@ -126,11 +127,11 @@ static int gameport_measure_speed(struct tx = 1 << 30; for(i = 0; i < 50; i++) { - local_irq_save(flags); + local_irq_save_nort(flags); rdtscl(t1); for (t = 0; t < 50; t++) gameport_read(gameport); rdtscl(t2); - local_irq_restore(flags); + local_irq_restore_nort(flags); udelay(i * 10); if (t2 - t1 < tx) tx = t2 - t1; } Index: linux-rt-rebase.q/drivers/input/keyboard/atkbd.c =================================================================== --- linux-rt-rebase.q.orig/drivers/input/keyboard/atkbd.c +++ linux-rt-rebase.q/drivers/input/keyboard/atkbd.c @@ -1396,9 +1396,23 @@ static ssize_t atkbd_show_err_count(stru return sprintf(buf, "%lu\n", atkbd->err_count); } +static int __read_mostly noatkbd; + +static int __init noatkbd_setup(char *str) +{ + noatkbd = 1; + printk(KERN_INFO "debug: not setting up AT keyboard.\n"); + + return 1; +} + +__setup("noatkbd", noatkbd_setup); static int __init atkbd_init(void) { + if (noatkbd) + return 0; + return serio_register_driver(&atkbd_drv); } Index: linux-rt-rebase.q/drivers/input/misc/atlas_btns.c =================================================================== --- linux-rt-rebase.q.orig/drivers/input/misc/atlas_btns.c +++ linux-rt-rebase.q/drivers/input/misc/atlas_btns.c @@ -31,7 +31,6 @@ #define ACPI_ATLAS_NAME "Atlas ACPI" #define ACPI_ATLAS_CLASS "Atlas" -#define ACPI_ATLAS_BUTTON_HID "ASIM0000" static struct input_dev *input_dev; @@ -130,10 +129,16 @@ static int atlas_acpi_button_remove(stru return status; } +static const struct acpi_device_id atlas_device_ids[] = { + {"ASIM0000", 0}, + {"", 0}, +}; +MODULE_DEVICE_TABLE(acpi, atlas_device_ids); + static struct acpi_driver atlas_acpi_driver = { .name = ACPI_ATLAS_NAME, .class = ACPI_ATLAS_CLASS, - .ids = ACPI_ATLAS_BUTTON_HID, + .ids = atlas_device_ids, .ops = { .add = atlas_acpi_button_add, .remove = atlas_acpi_button_remove, Index: linux-rt-rebase.q/drivers/input/mouse/psmouse-base.c =================================================================== --- linux-rt-rebase.q.orig/drivers/input/mouse/psmouse-base.c +++ linux-rt-rebase.q/drivers/input/mouse/psmouse-base.c @@ -1594,10 +1594,25 @@ static int psmouse_get_maxproto(char *bu return sprintf(buffer, "%s\n", psmouse_protocol_by_type(type)->name); } +static int __read_mostly nopsmouse; + +static int __init nopsmouse_setup(char *str) +{ + nopsmouse = 1; + printk(KERN_INFO "debug: not setting up psmouse.\n"); + + return 1; +} + +__setup("nopsmouse", nopsmouse_setup); + static int __init psmouse_init(void) { int err; + if (nopsmouse) + return 0; + kpsmoused_wq = create_singlethread_workqueue("kpsmoused"); if (!kpsmoused_wq) { printk(KERN_ERR "psmouse: failed to create kpsmoused workqueue\n"); Index: linux-rt-rebase.q/drivers/kvm/kvm_main.c =================================================================== --- linux-rt-rebase.q.orig/drivers/kvm/kvm_main.c +++ linux-rt-rebase.q/drivers/kvm/kvm_main.c @@ -297,9 +297,6 @@ static struct kvm *kvm_create_vm(void) kvm_io_bus_init(&kvm->pio_bus); spin_lock_init(&kvm->lock); INIT_LIST_HEAD(&kvm->active_mmu_pages); - spin_lock(&kvm_lock); - list_add(&kvm->vm_list, &vm_list); - spin_unlock(&kvm_lock); kvm_io_bus_init(&kvm->mmio_bus); for (i = 0; i < KVM_MAX_VCPUS; ++i) { struct kvm_vcpu *vcpu = &kvm->vcpus[i]; @@ -309,6 +306,9 @@ static struct kvm *kvm_create_vm(void) vcpu->kvm = kvm; vcpu->mmu.root_hpa = INVALID_PAGE; } + spin_lock(&kvm_lock); + list_add(&kvm->vm_list, &vm_list); + spin_unlock(&kvm_lock); return kvm; } @@ -1070,18 +1070,16 @@ static int emulator_write_phys(struct kv return 0; mark_page_dirty(vcpu->kvm, gpa >> PAGE_SHIFT); virt = kmap_atomic(page, KM_USER0); - if (memcmp(virt + offset_in_page(gpa), val, bytes)) { - kvm_mmu_pte_write(vcpu, gpa, virt + offset, val, bytes); - memcpy(virt + offset_in_page(gpa), val, bytes); - } + kvm_mmu_pte_write(vcpu, gpa, virt + offset, val, bytes); + memcpy(virt + offset_in_page(gpa), val, bytes); kunmap_atomic(virt, KM_USER0); return 1; } -static int emulator_write_emulated(unsigned long addr, - const void *val, - unsigned int bytes, - struct x86_emulate_ctxt *ctxt) +static int emulator_write_emulated_onepage(unsigned long addr, + const void *val, + unsigned int bytes, + struct x86_emulate_ctxt *ctxt) { struct kvm_vcpu *vcpu = ctxt->vcpu; struct kvm_io_device *mmio_dev; @@ -1113,6 +1111,26 @@ static int emulator_write_emulated(unsig return X86EMUL_CONTINUE; } +static int emulator_write_emulated(unsigned long addr, + const void *val, + unsigned int bytes, + struct x86_emulate_ctxt *ctxt) +{ + /* Crossing a page boundary? */ + if (((addr + bytes - 1) ^ addr) & PAGE_MASK) { + int rc, now; + + now = -addr & ~PAGE_MASK; + rc = emulator_write_emulated_onepage(addr, val, now, ctxt); + if (rc != X86EMUL_CONTINUE) + return rc; + addr += now; + val += now; + bytes -= now; + } + return emulator_write_emulated_onepage(addr, val, bytes, ctxt); +} + static int emulator_cmpxchg_emulated(unsigned long addr, const void *old, const void *new, @@ -2414,9 +2432,9 @@ static void cpuid_fix_nx_cap(struct kvm_ break; } } - if (entry && (entry->edx & EFER_NX) && !(efer & EFER_NX)) { + if (entry && (entry->edx & (1 << 20)) && !(efer & EFER_NX)) { entry->edx &= ~(1 << 20); - printk(KERN_INFO ": guest NX capability removed\n"); + printk(KERN_INFO "kvm: guest NX capability removed\n"); } } @@ -2884,7 +2902,7 @@ static int kvm_reboot(struct notifier_bl * in vmx root mode. */ printk(KERN_INFO "kvm: exiting hardware virtualization\n"); - on_each_cpu(hardware_disable, NULL, 0, 1); + schedule_on_each_cpu(hardware_disable, NULL, 0, 1); } return NOTIFY_OK; } @@ -3107,7 +3125,7 @@ int kvm_init_arch(struct kvm_arch_ops *o if (r < 0) goto out; - on_each_cpu(hardware_enable, NULL, 0, 1); + schedule_on_each_cpu(hardware_enable, NULL, 0, 1); r = register_cpu_notifier(&kvm_cpu_notifier); if (r) goto out_free_1; @@ -3139,7 +3157,7 @@ out_free_2: unregister_reboot_notifier(&kvm_reboot_notifier); unregister_cpu_notifier(&kvm_cpu_notifier); out_free_1: - on_each_cpu(hardware_disable, NULL, 0, 1); + schedule_on_each_cpu(hardware_disable, NULL, 0, 1); kvm_arch_ops->hardware_unsetup(); out: kvm_arch_ops = NULL; @@ -3153,7 +3171,7 @@ void kvm_exit_arch(void) sysdev_class_unregister(&kvm_sysdev_class); unregister_reboot_notifier(&kvm_reboot_notifier); unregister_cpu_notifier(&kvm_cpu_notifier); - on_each_cpu(hardware_disable, NULL, 0, 1); + schedule_on_each_cpu(hardware_disable, NULL, 0, 1); kvm_arch_ops->hardware_unsetup(); kvm_arch_ops = NULL; } Index: linux-rt-rebase.q/drivers/kvm/svm.c =================================================================== --- linux-rt-rebase.q.orig/drivers/kvm/svm.c +++ linux-rt-rebase.q/drivers/kvm/svm.c @@ -613,9 +613,17 @@ static void svm_free_vcpu(struct kvm_vcp static void svm_vcpu_load(struct kvm_vcpu *vcpu) { - int cpu, i; + int cpu = raw_smp_processor_id(), i; + cpumask_t this_mask = cpumask_of_cpu(cpu); + + /* + * Keep the context preemptible, but do not migrate + * away to another CPU. TODO: make sure this persists. + * Save/restore original mask. + */ + if (unlikely(!cpus_equal(current->cpus_allowed, this_mask))) + set_cpus_allowed(current, cpumask_of_cpu(cpu)); - cpu = get_cpu(); if (unlikely(cpu != vcpu->cpu)) { u64 tsc_this, delta; @@ -641,7 +649,6 @@ static void svm_vcpu_put(struct kvm_vcpu wrmsrl(host_save_user_msrs[i], vcpu->svm->host_user_msrs[i]); rdtscll(vcpu->host_tsc); - put_cpu(); } static void svm_vcpu_decache(struct kvm_vcpu *vcpu) Index: linux-rt-rebase.q/drivers/kvm/vmx.c =================================================================== --- linux-rt-rebase.q.orig/drivers/kvm/vmx.c +++ linux-rt-rebase.q/drivers/kvm/vmx.c @@ -366,6 +366,8 @@ static void vmx_load_host_state(struct k reload_tss(); } + preempt_enable(); + save_msrs(vcpu->guest_msrs, vcpu->save_nmsrs); load_msrs(vcpu->host_msrs, vcpu->save_nmsrs); if (msr_efer_need_save_restore(vcpu)) @@ -379,10 +381,17 @@ static void vmx_load_host_state(struct k static void vmx_vcpu_load(struct kvm_vcpu *vcpu) { u64 phys_addr = __pa(vcpu->vmcs); - int cpu; u64 tsc_this, delta; + int cpu = raw_smp_processor_id(); + cpumask_t this_mask = cpumask_of_cpu(cpu); - cpu = get_cpu(); + /* + * Keep the context preemptible, but do not migrate + * away to another CPU. TODO: make sure this persists. + * Save/restore original mask. + */ + if (unlikely(!cpus_equal(current->cpus_allowed, this_mask))) + set_cpus_allowed(current, cpumask_of_cpu(cpu)); if (vcpu->cpu != cpu) vcpu_clear(vcpu); @@ -428,7 +437,6 @@ static void vmx_vcpu_put(struct kvm_vcpu { vmx_load_host_state(vcpu); kvm_put_guest_fpu(vcpu); - put_cpu(); } static void vmx_fpu_activate(struct kvm_vcpu *vcpu) @@ -2022,6 +2030,7 @@ again: if (test_and_clear_bit(KVM_TLB_FLUSH, &vcpu->requests)) vmx_flush_tlb(vcpu); + preempt_disable(); asm ( /* Store host registers */ #ifdef CONFIG_X86_64 Index: linux-rt-rebase.q/drivers/kvm/x86_emulate.c =================================================================== --- linux-rt-rebase.q.orig/drivers/kvm/x86_emulate.c +++ linux-rt-rebase.q/drivers/kvm/x86_emulate.c @@ -1178,6 +1178,8 @@ pop_instruction: twobyte_insn: switch (b) { case 0x01: /* lgdt, lidt, lmsw */ + /* Disable writeback. */ + no_wb = 1; switch (modrm_reg) { u16 size; unsigned long address; Index: linux-rt-rebase.q/drivers/macintosh/adb.c =================================================================== --- linux-rt-rebase.q.orig/drivers/macintosh/adb.c +++ linux-rt-rebase.q/drivers/macintosh/adb.c @@ -250,6 +250,8 @@ adb_probe_task(void *x) { strcpy(current->comm, "kadbprobe"); + down(&adb_probe_mutex); + printk(KERN_INFO "adb: starting probe task...\n"); do_adb_reset_bus(); printk(KERN_INFO "adb: finished probe task...\n"); @@ -276,7 +278,9 @@ adb_reset_bus(void) return 0; } - down(&adb_probe_mutex); + if (adb_got_sleep) + return 0; + schedule_work(&adb_reset_work); return 0; } @@ -339,9 +343,8 @@ adb_notify_sleep(struct pmu_sleep_notifi { switch (when) { case PBOOK_SLEEP_REQUEST: + /* Signal to discontiue probing */ adb_got_sleep = 1; - /* We need to get a lock on the probe thread */ - down(&adb_probe_mutex); /* Stop autopoll */ if (adb_controller->autopoll) adb_controller->autopoll(0); @@ -350,7 +353,6 @@ adb_notify_sleep(struct pmu_sleep_notifi break; case PBOOK_WAKE: adb_got_sleep = 0; - up(&adb_probe_mutex); adb_reset_bus(); break; } Index: linux-rt-rebase.q/drivers/md/dm-table.c =================================================================== --- linux-rt-rebase.q.orig/drivers/md/dm-table.c +++ linux-rt-rebase.q/drivers/md/dm-table.c @@ -526,7 +526,7 @@ static int __table_get_device(struct dm_ void dm_set_device_limits(struct dm_target *ti, struct block_device *bdev) { - request_queue_t *q = bdev_get_queue(bdev); + struct request_queue *q = bdev_get_queue(bdev); struct io_restrictions *rs = &ti->limits; /* @@ -979,7 +979,7 @@ int dm_table_any_congested(struct dm_tab devices = dm_table_get_devices(t); for (d = devices->next; d != devices; d = d->next) { struct dm_dev *dd = list_entry(d, struct dm_dev, list); - request_queue_t *q = bdev_get_queue(dd->bdev); + struct request_queue *q = bdev_get_queue(dd->bdev); r |= bdi_congested(&q->backing_dev_info, bdi_bits); } @@ -992,7 +992,7 @@ void dm_table_unplug_all(struct dm_table for (d = devices->next; d != devices; d = d->next) { struct dm_dev *dd = list_entry(d, struct dm_dev, list); - request_queue_t *q = bdev_get_queue(dd->bdev); + struct request_queue *q = bdev_get_queue(dd->bdev); if (q->unplug_fn) q->unplug_fn(q); @@ -1011,7 +1011,7 @@ int dm_table_flush_all(struct dm_table * for (d = devices->next; d != devices; d = d->next) { struct dm_dev *dd = list_entry(d, struct dm_dev, list); - request_queue_t *q = bdev_get_queue(dd->bdev); + struct request_queue *q = bdev_get_queue(dd->bdev); int err; if (!q->issue_flush_fn) Index: linux-rt-rebase.q/drivers/md/dm.c =================================================================== --- linux-rt-rebase.q.orig/drivers/md/dm.c +++ linux-rt-rebase.q/drivers/md/dm.c @@ -80,7 +80,7 @@ struct mapped_device { unsigned long flags; - request_queue_t *queue; + struct request_queue *queue; struct gendisk *disk; char name[16]; @@ -792,7 +792,7 @@ static void __split_bio(struct mapped_de * The request function that just remaps the bio built up by * dm_merge_bvec. */ -static int dm_request(request_queue_t *q, struct bio *bio) +static int dm_request(struct request_queue *q, struct bio *bio) { int r; int rw = bio_data_dir(bio); @@ -844,7 +844,7 @@ static int dm_request(request_queue_t *q return 0; } -static int dm_flush_all(request_queue_t *q, struct gendisk *disk, +static int dm_flush_all(struct request_queue *q, struct gendisk *disk, sector_t *error_sector) { struct mapped_device *md = q->queuedata; @@ -859,7 +859,7 @@ static int dm_flush_all(request_queue_t return ret; } -static void dm_unplug_all(request_queue_t *q) +static void dm_unplug_all(struct request_queue *q) { struct mapped_device *md = q->queuedata; struct dm_table *map = dm_get_table(md); @@ -1110,7 +1110,7 @@ static void __set_size(struct mapped_dev static int __bind(struct mapped_device *md, struct dm_table *t) { - request_queue_t *q = md->queue; + struct request_queue *q = md->queue; sector_t size; size = dm_table_get_size(t); Index: linux-rt-rebase.q/drivers/md/faulty.c =================================================================== --- linux-rt-rebase.q.orig/drivers/md/faulty.c +++ linux-rt-rebase.q/drivers/md/faulty.c @@ -167,7 +167,7 @@ static void add_sector(conf_t *conf, sec conf->nfaults = n+1; } -static int make_request(request_queue_t *q, struct bio *bio) +static int make_request(struct request_queue *q, struct bio *bio) { mddev_t *mddev = q->queuedata; conf_t *conf = (conf_t*)mddev->private; Index: linux-rt-rebase.q/drivers/md/linear.c =================================================================== --- linux-rt-rebase.q.orig/drivers/md/linear.c +++ linux-rt-rebase.q/drivers/md/linear.c @@ -55,7 +55,7 @@ static inline dev_info_t *which_dev(mdde * * Return amount of bytes we can take at this offset */ -static int linear_mergeable_bvec(request_queue_t *q, struct bio *bio, struct bio_vec *biovec) +static int linear_mergeable_bvec(struct request_queue *q, struct bio *bio, struct bio_vec *biovec) { mddev_t *mddev = q->queuedata; dev_info_t *dev0; @@ -79,20 +79,20 @@ static int linear_mergeable_bvec(request return maxsectors << 9; } -static void linear_unplug(request_queue_t *q) +static void linear_unplug(struct request_queue *q) { mddev_t *mddev = q->queuedata; linear_conf_t *conf = mddev_to_conf(mddev); int i; for (i=0; i < mddev->raid_disks; i++) { - request_queue_t *r_queue = bdev_get_queue(conf->disks[i].rdev->bdev); + struct request_queue *r_queue = bdev_get_queue(conf->disks[i].rdev->bdev); if (r_queue->unplug_fn) r_queue->unplug_fn(r_queue); } } -static int linear_issue_flush(request_queue_t *q, struct gendisk *disk, +static int linear_issue_flush(struct request_queue *q, struct gendisk *disk, sector_t *error_sector) { mddev_t *mddev = q->queuedata; @@ -101,7 +101,7 @@ static int linear_issue_flush(request_qu for (i=0; i < mddev->raid_disks && ret == 0; i++) { struct block_device *bdev = conf->disks[i].rdev->bdev; - request_queue_t *r_queue = bdev_get_queue(bdev); + struct request_queue *r_queue = bdev_get_queue(bdev); if (!r_queue->issue_flush_fn) ret = -EOPNOTSUPP; @@ -118,7 +118,7 @@ static int linear_congested(void *data, int i, ret = 0; for (i = 0; i < mddev->raid_disks && !ret ; i++) { - request_queue_t *q = bdev_get_queue(conf->disks[i].rdev->bdev); + struct request_queue *q = bdev_get_queue(conf->disks[i].rdev->bdev); ret |= bdi_congested(&q->backing_dev_info, bits); } return ret; @@ -330,7 +330,7 @@ static int linear_stop (mddev_t *mddev) return 0; } -static int linear_make_request (request_queue_t *q, struct bio *bio) +static int linear_make_request (struct request_queue *q, struct bio *bio) { const int rw = bio_data_dir(bio); mddev_t *mddev = q->queuedata; Index: linux-rt-rebase.q/drivers/md/md.c =================================================================== --- linux-rt-rebase.q.orig/drivers/md/md.c +++ linux-rt-rebase.q/drivers/md/md.c @@ -211,7 +211,7 @@ static DEFINE_SPINLOCK(all_mddevs_lock); ) -static int md_fail_request (request_queue_t *q, struct bio *bio) +static int md_fail_request (struct request_queue *q, struct bio *bio) { bio_io_error(bio, bio->bi_size); return 0; Index: linux-rt-rebase.q/drivers/md/multipath.c =================================================================== --- linux-rt-rebase.q.orig/drivers/md/multipath.c +++ linux-rt-rebase.q/drivers/md/multipath.c @@ -125,7 +125,7 @@ static void unplug_slaves(mddev_t *mddev mdk_rdev_t *rdev = rcu_dereference(conf->multipaths[i].rdev); if (rdev && !test_bit(Faulty, &rdev->flags) && atomic_read(&rdev->nr_pending)) { - request_queue_t *r_queue = bdev_get_queue(rdev->bdev); + struct request_queue *r_queue = bdev_get_queue(rdev->bdev); atomic_inc(&rdev->nr_pending); rcu_read_unlock(); @@ -140,13 +140,13 @@ static void unplug_slaves(mddev_t *mddev rcu_read_unlock(); } -static void multipath_unplug(request_queue_t *q) +static void multipath_unplug(struct request_queue *q) { unplug_slaves(q->queuedata); } -static int multipath_make_request (request_queue_t *q, struct bio * bio) +static int multipath_make_request (struct request_queue *q, struct bio * bio) { mddev_t *mddev = q->queuedata; multipath_conf_t *conf = mddev_to_conf(mddev); @@ -199,7 +199,7 @@ static void multipath_status (struct seq seq_printf (seq, "]"); } -static int multipath_issue_flush(request_queue_t *q, struct gendisk *disk, +static int multipath_issue_flush(struct request_queue *q, struct gendisk *disk, sector_t *error_sector) { mddev_t *mddev = q->queuedata; @@ -211,7 +211,7 @@ static int multipath_issue_flush(request mdk_rdev_t *rdev = rcu_dereference(conf->multipaths[i].rdev); if (rdev && !test_bit(Faulty, &rdev->flags)) { struct block_device *bdev = rdev->bdev; - request_queue_t *r_queue = bdev_get_queue(bdev); + struct request_queue *r_queue = bdev_get_queue(bdev); if (!r_queue->issue_flush_fn) ret = -EOPNOTSUPP; @@ -238,7 +238,7 @@ static int multipath_congested(void *dat for (i = 0; i < mddev->raid_disks ; i++) { mdk_rdev_t *rdev = rcu_dereference(conf->multipaths[i].rdev); if (rdev && !test_bit(Faulty, &rdev->flags)) { - request_queue_t *q = bdev_get_queue(rdev->bdev); + struct request_queue *q = bdev_get_queue(rdev->bdev); ret |= bdi_congested(&q->backing_dev_info, bits); /* Just like multipath_map, we just check the Index: linux-rt-rebase.q/drivers/md/raid0.c =================================================================== --- linux-rt-rebase.q.orig/drivers/md/raid0.c +++ linux-rt-rebase.q/drivers/md/raid0.c @@ -25,7 +25,7 @@ #define MD_DRIVER #define MD_PERSONALITY -static void raid0_unplug(request_queue_t *q) +static void raid0_unplug(struct request_queue *q) { mddev_t *mddev = q->queuedata; raid0_conf_t *conf = mddev_to_conf(mddev); @@ -33,14 +33,14 @@ static void raid0_unplug(request_queue_t int i; for (i=0; iraid_disks; i++) { - request_queue_t *r_queue = bdev_get_queue(devlist[i]->bdev); + struct request_queue *r_queue = bdev_get_queue(devlist[i]->bdev); if (r_queue->unplug_fn) r_queue->unplug_fn(r_queue); } } -static int raid0_issue_flush(request_queue_t *q, struct gendisk *disk, +static int raid0_issue_flush(struct request_queue *q, struct gendisk *disk, sector_t *error_sector) { mddev_t *mddev = q->queuedata; @@ -50,7 +50,7 @@ static int raid0_issue_flush(request_que for (i=0; iraid_disks && ret == 0; i++) { struct block_device *bdev = devlist[i]->bdev; - request_queue_t *r_queue = bdev_get_queue(bdev); + struct request_queue *r_queue = bdev_get_queue(bdev); if (!r_queue->issue_flush_fn) ret = -EOPNOTSUPP; @@ -68,7 +68,7 @@ static int raid0_congested(void *data, i int i, ret = 0; for (i = 0; i < mddev->raid_disks && !ret ; i++) { - request_queue_t *q = bdev_get_queue(devlist[i]->bdev); + struct request_queue *q = bdev_get_queue(devlist[i]->bdev); ret |= bdi_congested(&q->backing_dev_info, bits); } @@ -268,7 +268,7 @@ static int create_strip_zones (mddev_t * * * Return amount of bytes we can accept at this offset */ -static int raid0_mergeable_bvec(request_queue_t *q, struct bio *bio, struct bio_vec *biovec) +static int raid0_mergeable_bvec(struct request_queue *q, struct bio *bio, struct bio_vec *biovec) { mddev_t *mddev = q->queuedata; sector_t sector = bio->bi_sector + get_start_sect(bio->bi_bdev); @@ -408,7 +408,7 @@ static int raid0_stop (mddev_t *mddev) return 0; } -static int raid0_make_request (request_queue_t *q, struct bio *bio) +static int raid0_make_request (struct request_queue *q, struct bio *bio) { mddev_t *mddev = q->queuedata; unsigned int sect_in_chunk, chunksize_bits, chunk_size, chunk_sects; Index: linux-rt-rebase.q/drivers/md/raid1.c =================================================================== --- linux-rt-rebase.q.orig/drivers/md/raid1.c +++ linux-rt-rebase.q/drivers/md/raid1.c @@ -552,7 +552,7 @@ static void unplug_slaves(mddev_t *mddev for (i=0; iraid_disks; i++) { mdk_rdev_t *rdev = rcu_dereference(conf->mirrors[i].rdev); if (rdev && !test_bit(Faulty, &rdev->flags) && atomic_read(&rdev->nr_pending)) { - request_queue_t *r_queue = bdev_get_queue(rdev->bdev); + struct request_queue *r_queue = bdev_get_queue(rdev->bdev); atomic_inc(&rdev->nr_pending); rcu_read_unlock(); @@ -567,7 +567,7 @@ static void unplug_slaves(mddev_t *mddev rcu_read_unlock(); } -static void raid1_unplug(request_queue_t *q) +static void raid1_unplug(struct request_queue *q) { mddev_t *mddev = q->queuedata; @@ -575,7 +575,7 @@ static void raid1_unplug(request_queue_t md_wakeup_thread(mddev->thread); } -static int raid1_issue_flush(request_queue_t *q, struct gendisk *disk, +static int raid1_issue_flush(struct request_queue *q, struct gendisk *disk, sector_t *error_sector) { mddev_t *mddev = q->queuedata; @@ -587,7 +587,7 @@ static int raid1_issue_flush(request_que mdk_rdev_t *rdev = rcu_dereference(conf->mirrors[i].rdev); if (rdev && !test_bit(Faulty, &rdev->flags)) { struct block_device *bdev = rdev->bdev; - request_queue_t *r_queue = bdev_get_queue(bdev); + struct request_queue *r_queue = bdev_get_queue(bdev); if (!r_queue->issue_flush_fn) ret = -EOPNOTSUPP; @@ -615,7 +615,7 @@ static int raid1_congested(void *data, i for (i = 0; i < mddev->raid_disks; i++) { mdk_rdev_t *rdev = rcu_dereference(conf->mirrors[i].rdev); if (rdev && !test_bit(Faulty, &rdev->flags)) { - request_queue_t *q = bdev_get_queue(rdev->bdev); + struct request_queue *q = bdev_get_queue(rdev->bdev); /* Note the '|| 1' - when read_balance prefers * non-congested targets, it can be removed @@ -765,7 +765,7 @@ do_sync_io: return NULL; } -static int make_request(request_queue_t *q, struct bio * bio) +static int make_request(struct request_queue *q, struct bio * bio) { mddev_t *mddev = q->queuedata; conf_t *conf = mddev_to_conf(mddev); Index: linux-rt-rebase.q/drivers/md/raid10.c =================================================================== --- linux-rt-rebase.q.orig/drivers/md/raid10.c +++ linux-rt-rebase.q/drivers/md/raid10.c @@ -453,7 +453,7 @@ static sector_t raid10_find_virt(conf_t * If near_copies == raid_disk, there are no striping issues, * but in that case, the function isn't called at all. */ -static int raid10_mergeable_bvec(request_queue_t *q, struct bio *bio, +static int raid10_mergeable_bvec(struct request_queue *q, struct bio *bio, struct bio_vec *bio_vec) { mddev_t *mddev = q->queuedata; @@ -595,7 +595,7 @@ static void unplug_slaves(mddev_t *mddev for (i=0; iraid_disks; i++) { mdk_rdev_t *rdev = rcu_dereference(conf->mirrors[i].rdev); if (rdev && !test_bit(Faulty, &rdev->flags) && atomic_read(&rdev->nr_pending)) { - request_queue_t *r_queue = bdev_get_queue(rdev->bdev); + struct request_queue *r_queue = bdev_get_queue(rdev->bdev); atomic_inc(&rdev->nr_pending); rcu_read_unlock(); @@ -610,7 +610,7 @@ static void unplug_slaves(mddev_t *mddev rcu_read_unlock(); } -static void raid10_unplug(request_queue_t *q) +static void raid10_unplug(struct request_queue *q) { mddev_t *mddev = q->queuedata; @@ -618,7 +618,7 @@ static void raid10_unplug(request_queue_ md_wakeup_thread(mddev->thread); } -static int raid10_issue_flush(request_queue_t *q, struct gendisk *disk, +static int raid10_issue_flush(struct request_queue *q, struct gendisk *disk, sector_t *error_sector) { mddev_t *mddev = q->queuedata; @@ -630,7 +630,7 @@ static int raid10_issue_flush(request_qu mdk_rdev_t *rdev = rcu_dereference(conf->mirrors[i].rdev); if (rdev && !test_bit(Faulty, &rdev->flags)) { struct block_device *bdev = rdev->bdev; - request_queue_t *r_queue = bdev_get_queue(bdev); + struct request_queue *r_queue = bdev_get_queue(bdev); if (!r_queue->issue_flush_fn) ret = -EOPNOTSUPP; @@ -658,7 +658,7 @@ static int raid10_congested(void *data, for (i = 0; i < mddev->raid_disks && ret == 0; i++) { mdk_rdev_t *rdev = rcu_dereference(conf->mirrors[i].rdev); if (rdev && !test_bit(Faulty, &rdev->flags)) { - request_queue_t *q = bdev_get_queue(rdev->bdev); + struct request_queue *q = bdev_get_queue(rdev->bdev); ret |= bdi_congested(&q->backing_dev_info, bits); } @@ -772,7 +772,7 @@ static void unfreeze_array(conf_t *conf) spin_unlock_irq(&conf->resync_lock); } -static int make_request(request_queue_t *q, struct bio * bio) +static int make_request(struct request_queue *q, struct bio * bio) { mddev_t *mddev = q->queuedata; conf_t *conf = mddev_to_conf(mddev); Index: linux-rt-rebase.q/drivers/md/raid5.c =================================================================== --- linux-rt-rebase.q.orig/drivers/md/raid5.c +++ linux-rt-rebase.q/drivers/md/raid5.c @@ -289,7 +289,7 @@ static struct stripe_head *__find_stripe } static void unplug_slaves(mddev_t *mddev); -static void raid5_unplug_device(request_queue_t *q); +static void raid5_unplug_device(struct request_queue *q); static struct stripe_head *get_active_stripe(raid5_conf_t *conf, sector_t sector, int disks, int pd_idx, int noblock) @@ -3182,7 +3182,7 @@ static void unplug_slaves(mddev_t *mddev for (i=0; iraid_disks; i++) { mdk_rdev_t *rdev = rcu_dereference(conf->disks[i].rdev); if (rdev && !test_bit(Faulty, &rdev->flags) && atomic_read(&rdev->nr_pending)) { - request_queue_t *r_queue = bdev_get_queue(rdev->bdev); + struct request_queue *r_queue = bdev_get_queue(rdev->bdev); atomic_inc(&rdev->nr_pending); rcu_read_unlock(); @@ -3197,7 +3197,7 @@ static void unplug_slaves(mddev_t *mddev rcu_read_unlock(); } -static void raid5_unplug_device(request_queue_t *q) +static void raid5_unplug_device(struct request_queue *q) { mddev_t *mddev = q->queuedata; raid5_conf_t *conf = mddev_to_conf(mddev); @@ -3216,7 +3216,7 @@ static void raid5_unplug_device(request_ unplug_slaves(mddev); } -static int raid5_issue_flush(request_queue_t *q, struct gendisk *disk, +static int raid5_issue_flush(struct request_queue *q, struct gendisk *disk, sector_t *error_sector) { mddev_t *mddev = q->queuedata; @@ -3228,7 +3228,7 @@ static int raid5_issue_flush(request_que mdk_rdev_t *rdev = rcu_dereference(conf->disks[i].rdev); if (rdev && !test_bit(Faulty, &rdev->flags)) { struct block_device *bdev = rdev->bdev; - request_queue_t *r_queue = bdev_get_queue(bdev); + struct request_queue *r_queue = bdev_get_queue(bdev); if (!r_queue->issue_flush_fn) ret = -EOPNOTSUPP; @@ -3267,7 +3267,7 @@ static int raid5_congested(void *data, i /* We want read requests to align with chunks where possible, * but write requests don't need to. */ -static int raid5_mergeable_bvec(request_queue_t *q, struct bio *bio, struct bio_vec *biovec) +static int raid5_mergeable_bvec(struct request_queue *q, struct bio *bio, struct bio_vec *biovec) { mddev_t *mddev = q->queuedata; sector_t sector = bio->bi_sector + get_start_sect(bio->bi_bdev); @@ -3377,7 +3377,7 @@ static int raid5_align_endio(struct bio static int bio_fits_rdev(struct bio *bi) { - request_queue_t *q = bdev_get_queue(bi->bi_bdev); + struct request_queue *q = bdev_get_queue(bi->bi_bdev); if ((bi->bi_size>>9) > q->max_sectors) return 0; @@ -3396,7 +3396,7 @@ static int bio_fits_rdev(struct bio *bi) } -static int chunk_aligned_read(request_queue_t *q, struct bio * raid_bio) +static int chunk_aligned_read(struct request_queue *q, struct bio * raid_bio) { mddev_t *mddev = q->queuedata; raid5_conf_t *conf = mddev_to_conf(mddev); @@ -3466,7 +3466,7 @@ static int chunk_aligned_read(request_qu } -static int make_request(request_queue_t *q, struct bio * bi) +static int make_request(struct request_queue *q, struct bio * bi) { mddev_t *mddev = q->queuedata; raid5_conf_t *conf = mddev_to_conf(mddev); Index: linux-rt-rebase.q/drivers/media/dvb/dvb-core/dvb_frontend.c =================================================================== --- linux-rt-rebase.q.orig/drivers/media/dvb/dvb-core/dvb_frontend.c +++ linux-rt-rebase.q/drivers/media/dvb/dvb-core/dvb_frontend.c @@ -98,7 +98,7 @@ struct dvb_frontend_private { struct dvb_device *dvbdev; struct dvb_frontend_parameters parameters; struct dvb_fe_events events; - struct semaphore sem; + struct compat_semaphore sem; struct list_head list_head; wait_queue_head_t wait_queue; struct task_struct *thread; Index: linux-rt-rebase.q/drivers/media/dvb/dvb-core/dvb_frontend.h =================================================================== --- linux-rt-rebase.q.orig/drivers/media/dvb/dvb-core/dvb_frontend.h +++ linux-rt-rebase.q/drivers/media/dvb/dvb-core/dvb_frontend.h @@ -142,7 +142,7 @@ struct dvb_fe_events { int eventr; int overflow; wait_queue_head_t wait_queue; - struct semaphore sem; + struct compat_semaphore sem; }; struct dvb_frontend { Index: linux-rt-rebase.q/drivers/message/i2o/i2o_block.c =================================================================== --- linux-rt-rebase.q.orig/drivers/message/i2o/i2o_block.c +++ linux-rt-rebase.q/drivers/message/i2o/i2o_block.c @@ -159,7 +159,7 @@ static int i2o_block_device_flush(struct * Returns 0 on success or negative error code on failure. */ -static int i2o_block_issue_flush(request_queue_t * queue, struct gendisk *disk, +static int i2o_block_issue_flush(struct request_queue * queue, struct gendisk *disk, sector_t * error_sector) { struct i2o_block_device *i2o_blk_dev = queue->queuedata; @@ -445,7 +445,7 @@ static void i2o_block_end_request(struct { struct i2o_block_request *ireq = req->special; struct i2o_block_device *dev = ireq->i2o_blk_dev; - request_queue_t *q = req->q; + struct request_queue *q = req->q; unsigned long flags; if (end_that_request_chunk(req, uptodate, nr_bytes)) { Index: linux-rt-rebase.q/drivers/misc/asus-laptop.c =================================================================== --- linux-rt-rebase.q.orig/drivers/misc/asus-laptop.c +++ linux-rt-rebase.q/drivers/misc/asus-laptop.c @@ -53,7 +53,6 @@ #define ASUS_HOTK_NAME "Asus Laptop Support" #define ASUS_HOTK_CLASS "hotkey" #define ASUS_HOTK_DEVICE_NAME "Hotkey" -#define ASUS_HOTK_HID "ATK0100" #define ASUS_HOTK_FILE "asus-laptop" #define ASUS_HOTK_PREFIX "\\_SB.ATKD." @@ -197,12 +196,18 @@ static struct asus_hotk *hotk; /* * The hotkey driver declaration */ +static const struct acpi_device_id asus_device_ids[] = { + {"ATK0100", 0}, + {"", 0}, +}; +MODULE_DEVICE_TABLE(acpi, asus_device_ids); + static int asus_hotk_add(struct acpi_device *device); static int asus_hotk_remove(struct acpi_device *device, int type); static struct acpi_driver asus_hotk_driver = { .name = ASUS_HOTK_NAME, .class = ASUS_HOTK_CLASS, - .ids = ASUS_HOTK_HID, + .ids = asus_device_ids, .ops = { .add = asus_hotk_add, .remove = asus_hotk_remove, @@ -1067,19 +1072,16 @@ static void asus_backlight_exit(void) } #define ASUS_LED_UNREGISTER(object) \ - if(object##_led.class_dev \ - && !IS_ERR(object##_led.class_dev)) \ - led_classdev_unregister(&object##_led) + led_classdev_unregister(&object##_led) static void asus_led_exit(void) { + destroy_workqueue(led_workqueue); ASUS_LED_UNREGISTER(mled); ASUS_LED_UNREGISTER(tled); ASUS_LED_UNREGISTER(pled); ASUS_LED_UNREGISTER(rled); ASUS_LED_UNREGISTER(gled); - - destroy_workqueue(led_workqueue); } static void __exit asus_laptop_exit(void) @@ -1135,29 +1137,42 @@ static int asus_led_init(struct device * rv = ASUS_LED_REGISTER(mled, dev); if (rv) - return rv; + goto out; rv = ASUS_LED_REGISTER(tled, dev); if (rv) - return rv; + goto out1; rv = ASUS_LED_REGISTER(rled, dev); if (rv) - return rv; + goto out2; rv = ASUS_LED_REGISTER(pled, dev); if (rv) - return rv; + goto out3; rv = ASUS_LED_REGISTER(gled, dev); if (rv) - return rv; + goto out4; led_workqueue = create_singlethread_workqueue("led_workqueue"); if (!led_workqueue) - return -ENOMEM; + goto out5; return 0; +out5: + rv = -ENOMEM; + ASUS_LED_UNREGISTER(gled); +out4: + ASUS_LED_UNREGISTER(pled); +out3: + ASUS_LED_UNREGISTER(rled); +out2: + ASUS_LED_UNREGISTER(tled); +out1: + ASUS_LED_UNREGISTER(mled); +out: + return rv; } static int __init asus_laptop_init(void) Index: linux-rt-rebase.q/drivers/misc/sony-laptop.c =================================================================== --- linux-rt-rebase.q.orig/drivers/misc/sony-laptop.c +++ linux-rt-rebase.q/drivers/misc/sony-laptop.c @@ -1124,10 +1124,22 @@ static int sony_nc_remove(struct acpi_de return 0; } +static const struct acpi_device_id sony_device_ids[] = { + {SONY_NC_HID, 0}, + {SONY_PIC_HID, 0}, + {"", 0}, +}; +MODULE_DEVICE_TABLE(acpi, sony_device_ids); + +static const struct acpi_device_id sony_nc_device_ids[] = { + {SONY_NC_HID, 0}, + {"", 0}, +}; + static struct acpi_driver sony_nc_driver = { .name = SONY_NC_DRIVER_NAME, .class = SONY_NC_CLASS, - .ids = SONY_NC_HID, + .ids = sony_nc_device_ids, .owner = THIS_MODULE, .ops = { .add = sony_nc_add, @@ -2470,10 +2482,15 @@ static int sony_pic_resume(struct acpi_d return 0; } +static const struct acpi_device_id sony_pic_device_ids[] = { + {SONY_PIC_HID, 0}, + {"", 0}, +}; + static struct acpi_driver sony_pic_driver = { .name = SONY_PIC_DRIVER_NAME, .class = SONY_PIC_CLASS, - .ids = SONY_PIC_HID, + .ids = sony_pic_device_ids, .owner = THIS_MODULE, .ops = { .add = sony_pic_add, Index: linux-rt-rebase.q/drivers/misc/thinkpad_acpi.c =================================================================== --- linux-rt-rebase.q.orig/drivers/misc/thinkpad_acpi.c +++ linux-rt-rebase.q/drivers/misc/thinkpad_acpi.c @@ -411,12 +411,13 @@ static int __init register_tpacpi_subdri sprintf(ibm->acpi->driver->name, "%s_%s", IBM_NAME, ibm->name); ibm->acpi->driver->ids = ibm->acpi->hid; + ibm->acpi->driver->ops.add = &tpacpi_device_add; rc = acpi_bus_register_driver(ibm->acpi->driver); if (rc < 0) { printk(IBM_ERR "acpi_bus_register_driver(%s) failed: %d\n", - ibm->acpi->hid, rc); + ibm->name, rc); kfree(ibm->acpi->driver); ibm->acpi->driver = NULL; } else if (!rc) @@ -1316,8 +1317,13 @@ errexit: return res; } +static const struct acpi_device_id ibm_htk_device_ids[] = { + {IBM_HKEY_HID, 0}, + {"", 0}, +}; + static struct tp_acpi_drv_struct ibm_hotkey_acpidriver = { - .hid = IBM_HKEY_HID, + .hid = ibm_htk_device_ids, .notify = hotkey_notify, .handle = &hkey_handle, .type = ACPI_DEVICE_NOTIFY, @@ -2080,6 +2086,11 @@ IBM_HANDLE(dock, root, "\\_SB.GDCK", /* /* don't list other alternatives as we install a notify handler on the 570 */ IBM_HANDLE(pci, root, "\\_SB.PCI"); /* 570 */ +static const struct acpi_device_id ibm_pci_device_ids[] = { + {PCI_ROOT_HID_STRING, 0}, + {"", 0}, +}; + static struct tp_acpi_drv_struct ibm_dock_acpidriver[2] = { { .notify = dock_notify, @@ -2090,7 +2101,7 @@ static struct tp_acpi_drv_struct ibm_doc /* THIS ONE MUST NEVER BE USED FOR DRIVER AUTOLOADING. * We just use it to get notifications of dock hotplug * in very old thinkpads */ - .hid = PCI_ROOT_HID_STRING, + .hid = ibm_pci_device_ids, .notify = dock_notify, .handle = &pci_handle, .type = ACPI_SYSTEM_NOTIFY, @@ -2149,7 +2160,8 @@ static int __init dock_init2(struct ibm_ static void dock_notify(struct ibm_struct *ibm, u32 event) { int docked = dock_docked(); - int pci = ibm->acpi->hid && strstr(ibm->acpi->hid, PCI_ROOT_HID_STRING); + int pci = ibm->acpi->hid && ibm->acpi->device && + acpi_match_device_ids(ibm->acpi->device, ibm_pci_device_ids); if (event == 1 && !pci) /* 570 */ acpi_bus_generate_event(ibm->acpi->device, event, 1); /* button */ Index: linux-rt-rebase.q/drivers/misc/thinkpad_acpi.h =================================================================== --- linux-rt-rebase.q.orig/drivers/misc/thinkpad_acpi.h +++ linux-rt-rebase.q/drivers/misc/thinkpad_acpi.h @@ -193,7 +193,7 @@ static void thinkpad_acpi_module_exit(vo struct ibm_struct; struct tp_acpi_drv_struct { - char *hid; + const struct acpi_device_id *hid; struct acpi_driver *driver; void (*notify) (struct ibm_struct *, u32); Index: linux-rt-rebase.q/drivers/mmc/card/queue.c =================================================================== --- linux-rt-rebase.q.orig/drivers/mmc/card/queue.c +++ linux-rt-rebase.q/drivers/mmc/card/queue.c @@ -83,7 +83,7 @@ static int mmc_queue_thread(void *d) * on any queue on this host, and attempt to issue it. This may * not be the queue we were asked to process. */ -static void mmc_request(request_queue_t *q) +static void mmc_request(struct request_queue *q) { struct mmc_queue *mq = q->queuedata; struct request *req; @@ -211,7 +211,7 @@ int mmc_init_queue(struct mmc_queue *mq, void mmc_cleanup_queue(struct mmc_queue *mq) { - request_queue_t *q = mq->queue; + struct request_queue *q = mq->queue; unsigned long flags; /* Mark that we should start throwing out stragglers */ @@ -252,7 +252,7 @@ EXPORT_SYMBOL(mmc_cleanup_queue); */ void mmc_queue_suspend(struct mmc_queue *mq) { - request_queue_t *q = mq->queue; + struct request_queue *q = mq->queue; unsigned long flags; if (!(mq->flags & MMC_QUEUE_SUSPENDED)) { @@ -272,7 +272,7 @@ void mmc_queue_suspend(struct mmc_queue */ void mmc_queue_resume(struct mmc_queue *mq) { - request_queue_t *q = mq->queue; + struct request_queue *q = mq->queue; unsigned long flags; if (mq->flags & MMC_QUEUE_SUSPENDED) { Index: linux-rt-rebase.q/drivers/net/3c527.c =================================================================== --- linux-rt-rebase.q.orig/drivers/net/3c527.c +++ linux-rt-rebase.q/drivers/net/3c527.c @@ -182,7 +182,7 @@ struct mc32_local u16 rx_ring_tail; /* index to rx de-queue end */ - struct semaphore cmd_mutex; /* Serialises issuing of execute commands */ + struct compat_semaphore cmd_mutex; /* Serialises issuing of execute commands */ struct completion execution_cmd; /* Card has completed an execute command */ struct completion xceiver_cmd; /* Card has completed a tx or rx command */ }; Index: linux-rt-rebase.q/drivers/net/3c59x.c =================================================================== --- linux-rt-rebase.q.orig/drivers/net/3c59x.c +++ linux-rt-rebase.q/drivers/net/3c59x.c @@ -792,9 +792,9 @@ static void poll_vortex(struct net_devic { struct vortex_private *vp = netdev_priv(dev); unsigned long flags; - local_irq_save(flags); + local_irq_save_nort(flags); (vp->full_bus_master_rx ? boomerang_interrupt:vortex_interrupt)(dev->irq,dev); - local_irq_restore(flags); + local_irq_restore_nort(flags); } #endif @@ -1728,6 +1728,7 @@ vortex_timer(unsigned long data) int next_tick = 60*HZ; int ok = 0; int media_status, old_window; + unsigned long flags; if (vortex_debug > 2) { printk(KERN_DEBUG "%s: Media selection timer tick happened, %s.\n", @@ -1735,7 +1736,7 @@ vortex_timer(unsigned long data) printk(KERN_DEBUG "dev->watchdog_timeo=%d\n", dev->watchdog_timeo); } - disable_irq_lockdep(dev->irq); + spin_lock_irqsave(&vp->lock, flags); old_window = ioread16(ioaddr + EL3_CMD) >> 13; EL3WINDOW(4); media_status = ioread16(ioaddr + Wn4_Media); @@ -1758,9 +1759,7 @@ vortex_timer(unsigned long data) case XCVR_MII: case XCVR_NWAY: { ok = 1; - spin_lock_bh(&vp->lock); vortex_check_media(dev, 0); - spin_unlock_bh(&vp->lock); } break; default: /* Other media types handled by Tx timeouts. */ @@ -1816,7 +1815,7 @@ leave_media_alone: dev->name, media_tbl[dev->if_port].name); EL3WINDOW(old_window); - enable_irq_lockdep(dev->irq); + spin_unlock_irqrestore(&vp->lock, flags); mod_timer(&vp->timer, RUN_AT(next_tick)); if (vp->deferred) iowrite16(FakeIntr, ioaddr + EL3_CMD); @@ -1849,13 +1848,17 @@ static void vortex_tx_timeout(struct net /* * Block interrupts because vortex_interrupt does a bare spin_lock() */ +#ifndef CONFIG_PREEMPT_RT unsigned long flags; local_irq_save(flags); +#endif if (vp->full_bus_master_tx) boomerang_interrupt(dev->irq, dev); else vortex_interrupt(dev->irq, dev); +#ifndef CONFIG_PREEMPT_RT local_irq_restore(flags); +#endif } } Index: linux-rt-rebase.q/drivers/net/8139too.c =================================================================== --- linux-rt-rebase.q.orig/drivers/net/8139too.c +++ linux-rt-rebase.q/drivers/net/8139too.c @@ -2128,10 +2128,10 @@ static int rtl8139_poll(struct net_devic * Order is important since data can get interrupted * again when we think we are done. */ - local_irq_save(flags); + local_irq_save_nort(flags); RTL_W16_F(IntrMask, rtl8139_intr_mask); __netif_rx_complete(dev); - local_irq_restore(flags); + local_irq_restore_nort(flags); } spin_unlock(&tp->rx_lock); @@ -2211,7 +2211,11 @@ static irqreturn_t rtl8139_interrupt (in */ static void rtl8139_poll_controller(struct net_device *dev) { - disable_irq(dev->irq); + /* + * use _nosync() variant - might be used by netconsole + * from atomic contexts: + */ + disable_irq_nosync(dev->irq); rtl8139_interrupt(dev->irq, dev); enable_irq(dev->irq); } Index: linux-rt-rebase.q/drivers/net/82596.c =================================================================== --- linux-rt-rebase.q.orig/drivers/net/82596.c +++ linux-rt-rebase.q/drivers/net/82596.c @@ -57,6 +57,7 @@ #include #include #include +#include static char version[] __initdata = "82596.c $Revision: 1.5 $\n"; Index: linux-rt-rebase.q/drivers/net/Makefile =================================================================== --- linux-rt-rebase.q.orig/drivers/net/Makefile +++ linux-rt-rebase.q/drivers/net/Makefile @@ -18,7 +18,7 @@ gianfar_driver-objs := gianfar.o \ gianfar_sysfs.o obj-$(CONFIG_UCC_GETH) += ucc_geth_driver.o -ucc_geth_driver-objs := ucc_geth.o ucc_geth_mii.o +ucc_geth_driver-objs := ucc_geth.o ucc_geth_mii.o ucc_geth_ethtool.o # # link order important here Index: linux-rt-rebase.q/drivers/net/acenic.c =================================================================== --- linux-rt-rebase.q.orig/drivers/net/acenic.c +++ linux-rt-rebase.q/drivers/net/acenic.c @@ -3128,12 +3128,6 @@ static int __devinit read_eeprom_byte(st int result = 0; short i; - if (!dev) { - printk(KERN_ERR "No device!\n"); - result = -ENODEV; - goto out; - } - /* * Don't take interrupts on this CPU will bit banging * the %#%#@$ I2C device Index: linux-rt-rebase.q/drivers/net/atl1/atl1_hw.h =================================================================== --- linux-rt-rebase.q.orig/drivers/net/atl1/atl1_hw.h +++ linux-rt-rebase.q/drivers/net/atl1/atl1_hw.h @@ -680,11 +680,6 @@ void atl1_check_options(struct atl1_adap #define AUTONEG_ADVERTISE_10_100_ALL 0x000F /* All 10/100 speeds */ #define AUTONEG_ADVERTISE_10_ALL 0x0003 /* 10Mbps Full & Half speeds */ -/* The size (in bytes) of a ethernet packet */ -#define ENET_HEADER_SIZE 14 -#define MAXIMUM_ETHERNET_FRAME_SIZE 1518 /* with FCS */ -#define MINIMUM_ETHERNET_FRAME_SIZE 64 /* with FCS */ -#define ETHERNET_FCS_SIZE 4 #define MAX_JUMBO_FRAME_SIZE 0x2800 #define PHY_AUTO_NEG_TIME 45 /* 4.5 Seconds */ @@ -929,8 +924,8 @@ enum atl1_dma_req_block { atl1_dma_req_128 = 0, atl1_dma_req_256 = 1, atl1_dma_req_512 = 2, - atl1_dam_req_1024 = 3, - atl1_dam_req_2048 = 4, + atl1_dma_req_1024 = 3, + atl1_dma_req_2048 = 4, atl1_dma_req_4096 = 5 }; Index: linux-rt-rebase.q/drivers/net/atl1/atl1_main.c =================================================================== --- linux-rt-rebase.q.orig/drivers/net/atl1/atl1_main.c +++ linux-rt-rebase.q/drivers/net/atl1/atl1_main.c @@ -59,6 +59,7 @@ #include #include #include +#include #include #include #include @@ -120,8 +121,8 @@ static int __devinit atl1_sw_init(struct struct atl1_hw *hw = &adapter->hw; struct net_device *netdev = adapter->netdev; - hw->max_frame_size = netdev->mtu + ENET_HEADER_SIZE + ETHERNET_FCS_SIZE; - hw->min_frame_size = MINIMUM_ETHERNET_FRAME_SIZE; + hw->max_frame_size = netdev->mtu + ETH_HLEN + ETH_FCS_LEN; + hw->min_frame_size = ETH_ZLEN + ETH_FCS_LEN; adapter->wol = 0; adapter->rx_buffer_len = (hw->max_frame_size + 7) & ~7; @@ -314,7 +315,7 @@ err_nomem: return -ENOMEM; } -void atl1_init_ring_ptrs(struct atl1_adapter *adapter) +static void atl1_init_ring_ptrs(struct atl1_adapter *adapter) { struct atl1_tpd_ring *tpd_ring = &adapter->tpd_ring; struct atl1_rfd_ring *rfd_ring = &adapter->rfd_ring; @@ -688,9 +689,9 @@ static int atl1_change_mtu(struct net_de { struct atl1_adapter *adapter = netdev_priv(netdev); int old_mtu = netdev->mtu; - int max_frame = new_mtu + ENET_HEADER_SIZE + ETHERNET_FCS_SIZE; + int max_frame = new_mtu + ETH_HLEN + ETH_FCS_LEN; - if ((max_frame < MINIMUM_ETHERNET_FRAME_SIZE) || + if ((max_frame < ETH_ZLEN + ETH_FCS_LEN) || (max_frame > MAX_JUMBO_FRAME_SIZE)) { dev_warn(&adapter->pdev->dev, "invalid MTU setting\n"); return -EINVAL; @@ -908,8 +909,8 @@ static u32 atl1_configure(struct atl1_ad /* config DMA Engine */ value = ((((u32) hw->dmar_block) & DMA_CTRL_DMAR_BURST_LEN_MASK) << DMA_CTRL_DMAR_BURST_LEN_SHIFT) | - ((((u32) hw->dmaw_block) & DMA_CTRL_DMAR_BURST_LEN_MASK) - << DMA_CTRL_DMAR_BURST_LEN_SHIFT) | DMA_CTRL_DMAR_EN | + ((((u32) hw->dmaw_block) & DMA_CTRL_DMAW_BURST_LEN_MASK) + << DMA_CTRL_DMAW_BURST_LEN_SHIFT) | DMA_CTRL_DMAR_EN | DMA_CTRL_DMAW_EN; value |= (u32) hw->dma_ord; if (atl1_rcb_128 == hw->rcb_value) @@ -917,7 +918,10 @@ static u32 atl1_configure(struct atl1_ad iowrite32(value, hw->hw_addr + REG_DMA_CTRL); /* config CMB / SMB */ - value = hw->cmb_rrd | ((u32) hw->cmb_tpd << 16); + value = (hw->cmb_tpd > adapter->tpd_ring.count) ? + hw->cmb_tpd : adapter->tpd_ring.count; + value <<= 16; + value |= hw->cmb_rrd; iowrite32(value, hw->hw_addr + REG_CMB_WRITE_TH); value = hw->cmb_rx_timer | ((u32) hw->cmb_tx_timer << 16); iowrite32(value, hw->hw_addr + REG_CMB_WRITE_TIMER); @@ -1334,7 +1338,7 @@ rrd_ok: skb = buffer_info->skb; length = le16_to_cpu(rrd->xsz.xsum_sz.pkt_size); - skb_put(skb, length - ETHERNET_FCS_SIZE); + skb_put(skb, length - ETH_FCS_LEN); /* Receive Checksum Offload */ atl1_rx_checksum(adapter, rrd, skb); @@ -1422,7 +1426,7 @@ static void atl1_intr_tx(struct atl1_ada netif_wake_queue(adapter->netdev); } -static u16 tpd_avail(struct atl1_tpd_ring *tpd_ring) +static u16 atl1_tpd_avail(struct atl1_tpd_ring *tpd_ring) { u16 next_to_clean = atomic_read(&tpd_ring->next_to_clean); u16 next_to_use = atomic_read(&tpd_ring->next_to_use); @@ -1453,7 +1457,7 @@ static int atl1_tso(struct atl1_adapter tcp_hdr(skb)->check = ~csum_tcpudp_magic(iph->saddr, iph->daddr, 0, IPPROTO_TCP, 0); ipofst = skb_network_offset(skb); - if (ipofst != ENET_HEADER_SIZE) /* 802.3 frame */ + if (ipofst != ETH_HLEN) /* 802.3 frame */ tso->tsopl |= 1 << TSO_PARAM_ETHTYPE_SHIFT; tso->tsopl |= (iph->ihl & @@ -1708,7 +1712,7 @@ static int atl1_xmit_frame(struct sk_buf return NETDEV_TX_LOCKED; } - if (tpd_avail(&adapter->tpd_ring) < count) { + if (atl1_tpd_avail(&adapter->tpd_ring) < count) { /* not enough descriptors */ netif_stop_queue(netdev); spin_unlock_irqrestore(&adapter->lock, flags); Index: linux-rt-rebase.q/drivers/net/defxx.c =================================================================== --- linux-rt-rebase.q.orig/drivers/net/defxx.c +++ linux-rt-rebase.q/drivers/net/defxx.c @@ -200,6 +200,7 @@ /* Include files */ #include +#include #include #include #include @@ -240,8 +241,6 @@ static char version[] __devinitdata = */ #define NEW_SKB_SIZE (PI_RCV_DATA_K_SIZE_MAX+128) -#define __unused __attribute__ ((unused)) - #ifdef CONFIG_PCI #define DFX_BUS_PCI(dev) (dev->bus == &pci_bus_type) #else @@ -375,7 +374,7 @@ static inline void dfx_outl(DFX_board_t static void dfx_port_write_long(DFX_board_t *bp, int offset, u32 data) { - struct device __unused *bdev = bp->bus_dev; + struct device __maybe_unused *bdev = bp->bus_dev; int dfx_bus_tc = DFX_BUS_TC(bdev); int dfx_use_mmio = DFX_MMIO || dfx_bus_tc; @@ -399,7 +398,7 @@ static inline void dfx_inl(DFX_board_t * static void dfx_port_read_long(DFX_board_t *bp, int offset, u32 *data) { - struct device __unused *bdev = bp->bus_dev; + struct device __maybe_unused *bdev = bp->bus_dev; int dfx_bus_tc = DFX_BUS_TC(bdev); int dfx_use_mmio = DFX_MMIO || dfx_bus_tc; @@ -866,7 +865,7 @@ static void __devinit dfx_bus_uninit(str static void __devinit dfx_bus_config_check(DFX_board_t *bp) { - struct device __unused *bdev = bp->bus_dev; + struct device __maybe_unused *bdev = bp->bus_dev; int dfx_bus_eisa = DFX_BUS_EISA(bdev); int status; /* return code from adapter port control call */ u32 host_data; /* LW data returned from port control call */ @@ -3624,8 +3623,8 @@ static void __devexit dfx_unregister(str } -static int __devinit __unused dfx_dev_register(struct device *); -static int __devexit __unused dfx_dev_unregister(struct device *); +static int __devinit __maybe_unused dfx_dev_register(struct device *); +static int __devexit __maybe_unused dfx_dev_unregister(struct device *); #ifdef CONFIG_PCI static int __devinit dfx_pci_register(struct pci_dev *, @@ -3699,7 +3698,7 @@ static struct tc_driver dfx_tc_driver = }; #endif /* CONFIG_TC */ -static int __devinit __unused dfx_dev_register(struct device *dev) +static int __devinit __maybe_unused dfx_dev_register(struct device *dev) { int status; @@ -3709,7 +3708,7 @@ static int __devinit __unused dfx_dev_re return status; } -static int __devexit __unused dfx_dev_unregister(struct device *dev) +static int __devexit __maybe_unused dfx_dev_unregister(struct device *dev) { put_device(dev); dfx_unregister(dev); Index: linux-rt-rebase.q/drivers/net/ehea/ehea.h =================================================================== --- linux-rt-rebase.q.orig/drivers/net/ehea/ehea.h +++ linux-rt-rebase.q/drivers/net/ehea/ehea.h @@ -39,7 +39,7 @@ #include #define DRV_NAME "ehea" -#define DRV_VERSION "EHEA_0071" +#define DRV_VERSION "EHEA_0072" /* eHEA capability flags */ #define DLPAR_PORT_ADD_REM 1 Index: linux-rt-rebase.q/drivers/net/ehea/ehea_main.c =================================================================== --- linux-rt-rebase.q.orig/drivers/net/ehea/ehea_main.c +++ linux-rt-rebase.q/drivers/net/ehea/ehea_main.c @@ -589,6 +589,23 @@ static int ehea_poll(struct net_device * return 1; } +#ifdef CONFIG_NET_POLL_CONTROLLER +static void ehea_netpoll(struct net_device *dev) +{ + struct ehea_port *port = netdev_priv(dev); + + netif_rx_schedule(port->port_res[0].d_netdev); +} +#endif + +static int ehea_poll_firstqueue(struct net_device *dev, int *budget) +{ + struct ehea_port *port = netdev_priv(dev); + struct net_device *d_dev = port->port_res[0].d_netdev; + + return ehea_poll(d_dev, budget); +} + static irqreturn_t ehea_recv_irq_handler(int irq, void *param) { struct ehea_port_res *pr = param; @@ -2626,7 +2643,10 @@ struct ehea_port *ehea_setup_single_port memcpy(dev->dev_addr, &port->mac_addr, ETH_ALEN); dev->open = ehea_open; - dev->poll = ehea_poll; + dev->poll = ehea_poll_firstqueue; +#ifdef CONFIG_NET_POLL_CONTROLLER + dev->poll_controller = ehea_netpoll; +#endif dev->weight = 64; dev->stop = ehea_stop; dev->hard_start_xmit = ehea_start_xmit; Index: linux-rt-rebase.q/drivers/net/forcedeth.c =================================================================== --- linux-rt-rebase.q.orig/drivers/net/forcedeth.c +++ linux-rt-rebase.q/drivers/net/forcedeth.c @@ -5546,6 +5546,22 @@ static struct pci_device_id pci_tbl[] = PCI_DEVICE(PCI_VENDOR_ID_NVIDIA, PCI_DEVICE_ID_NVIDIA_NVENET_27), .driver_data = DEV_NEED_TIMERIRQ|DEV_NEED_LINKTIMER|DEV_HAS_HIGH_DMA|DEV_HAS_POWER_CNTRL|DEV_HAS_MSI|DEV_HAS_PAUSEFRAME_TX|DEV_HAS_STATISTICS_V2|DEV_HAS_TEST_EXTENDED|DEV_HAS_MGMT_UNIT, }, + { /* MCP73 Ethernet Controller */ + PCI_DEVICE(PCI_VENDOR_ID_NVIDIA, PCI_DEVICE_ID_NVIDIA_NVENET_28), + .driver_data = DEV_NEED_TIMERIRQ|DEV_NEED_LINKTIMER|DEV_HAS_HIGH_DMA|DEV_HAS_POWER_CNTRL|DEV_HAS_MSI|DEV_HAS_PAUSEFRAME_TX|DEV_HAS_STATISTICS_V2|DEV_HAS_TEST_EXTENDED|DEV_HAS_MGMT_UNIT, + }, + { /* MCP73 Ethernet Controller */ + PCI_DEVICE(PCI_VENDOR_ID_NVIDIA, PCI_DEVICE_ID_NVIDIA_NVENET_29), + .driver_data = DEV_NEED_TIMERIRQ|DEV_NEED_LINKTIMER|DEV_HAS_HIGH_DMA|DEV_HAS_POWER_CNTRL|DEV_HAS_MSI|DEV_HAS_PAUSEFRAME_TX|DEV_HAS_STATISTICS_V2|DEV_HAS_TEST_EXTENDED|DEV_HAS_MGMT_UNIT, + }, + { /* MCP73 Ethernet Controller */ + PCI_DEVICE(PCI_VENDOR_ID_NVIDIA, PCI_DEVICE_ID_NVIDIA_NVENET_30), + .driver_data = DEV_NEED_TIMERIRQ|DEV_NEED_LINKTIMER|DEV_HAS_HIGH_DMA|DEV_HAS_POWER_CNTRL|DEV_HAS_MSI|DEV_HAS_PAUSEFRAME_TX|DEV_HAS_STATISTICS_V2|DEV_HAS_TEST_EXTENDED|DEV_HAS_MGMT_UNIT, + }, + { /* MCP73 Ethernet Controller */ + PCI_DEVICE(PCI_VENDOR_ID_NVIDIA, PCI_DEVICE_ID_NVIDIA_NVENET_31), + .driver_data = DEV_NEED_TIMERIRQ|DEV_NEED_LINKTIMER|DEV_HAS_HIGH_DMA|DEV_HAS_POWER_CNTRL|DEV_HAS_MSI|DEV_HAS_PAUSEFRAME_TX|DEV_HAS_STATISTICS_V2|DEV_HAS_TEST_EXTENDED|DEV_HAS_MGMT_UNIT, + }, {0,}, }; Index: linux-rt-rebase.q/drivers/net/hamradio/6pack.c =================================================================== --- linux-rt-rebase.q.orig/drivers/net/hamradio/6pack.c +++ linux-rt-rebase.q/drivers/net/hamradio/6pack.c @@ -123,7 +123,7 @@ struct sixpack { struct timer_list tx_t; struct timer_list resync_t; atomic_t refcnt; - struct semaphore dead_sem; + struct compat_semaphore dead_sem; spinlock_t lock; }; Index: linux-rt-rebase.q/drivers/net/hamradio/mkiss.c =================================================================== --- linux-rt-rebase.q.orig/drivers/net/hamradio/mkiss.c +++ linux-rt-rebase.q/drivers/net/hamradio/mkiss.c @@ -84,7 +84,7 @@ struct mkiss { #define CRC_MODE_SMACK_TEST 4 atomic_t refcnt; - struct semaphore dead_sem; + struct compat_semaphore dead_sem; }; /*---------------------------------------------------------------------------*/ Index: linux-rt-rebase.q/drivers/net/ibm_emac/ibm_emac_core.c =================================================================== --- linux-rt-rebase.q.orig/drivers/net/ibm_emac/ibm_emac_core.c +++ linux-rt-rebase.q/drivers/net/ibm_emac/ibm_emac_core.c @@ -1059,6 +1059,8 @@ static inline int emac_xmit_finish(struc ++dev->stats.tx_packets; dev->stats.tx_bytes += len; + spin_unlock(&dev->tx_lock); + return 0; } @@ -1072,6 +1074,7 @@ static int emac_start_xmit(struct sk_buf u16 ctrl = EMAC_TX_CTRL_GFCS | EMAC_TX_CTRL_GP | MAL_TX_CTRL_READY | MAL_TX_CTRL_LAST | emac_tx_csum(dev, skb); + spin_lock(&dev->tx_lock); slot = dev->tx_slot++; if (dev->tx_slot == NUM_TX_BUFF) { dev->tx_slot = 0; @@ -1134,6 +1137,8 @@ static int emac_start_xmit_sg(struct sk_ if (likely(!nr_frags && len <= MAL_MAX_TX_SIZE)) return emac_start_xmit(skb, ndev); + spin_lock(&dev->tx_lock); + len -= skb->data_len; /* Note, this is only an *estimation*, we can still run out of empty @@ -1202,6 +1207,7 @@ static int emac_start_xmit_sg(struct sk_ stop_queue: netif_stop_queue(ndev); DBG2("%d: stopped TX queue" NL, dev->def->index); + spin_unlock(&dev->tx_lock); return 1; } #else @@ -1241,6 +1247,7 @@ static void emac_poll_tx(void *param) DBG2("%d: poll_tx, %d %d" NL, dev->def->index, dev->tx_cnt, dev->ack_slot); + spin_lock(&dev->tx_lock); if (dev->tx_cnt) { u16 ctrl; int slot = dev->ack_slot, n = 0; @@ -1250,6 +1257,7 @@ static void emac_poll_tx(void *param) struct sk_buff *skb = dev->tx_skb[slot]; ++n; + spin_unlock(&dev->tx_lock); if (skb) { dev_kfree_skb(skb); dev->tx_skb[slot] = NULL; @@ -1259,6 +1267,7 @@ static void emac_poll_tx(void *param) if (unlikely(EMAC_IS_BAD_TX(ctrl))) emac_parse_tx_error(dev, ctrl); + spin_lock(&dev->tx_lock); if (--dev->tx_cnt) goto again; } @@ -1271,6 +1280,7 @@ static void emac_poll_tx(void *param) DBG2("%d: tx %d pkts" NL, dev->def->index, n); } } + spin_unlock(&dev->tx_lock); } static inline void emac_recycle_rx_skb(struct ocp_enet_private *dev, int slot, @@ -1963,6 +1973,7 @@ static int __init emac_probe(struct ocp_ dev->ldev = &ocpdev->dev; dev->def = ocpdev->def; SET_MODULE_OWNER(ndev); + spin_lock_init(&dev->tx_lock); /* Find MAL device we are connected to */ maldev = Index: linux-rt-rebase.q/drivers/net/ibm_emac/ibm_emac_core.h =================================================================== --- linux-rt-rebase.q.orig/drivers/net/ibm_emac/ibm_emac_core.h +++ linux-rt-rebase.q/drivers/net/ibm_emac/ibm_emac_core.h @@ -193,6 +193,8 @@ struct ocp_enet_private { struct ibm_emac_error_stats estats; struct net_device_stats nstats; + spinlock_t tx_lock; + struct device* ldev; }; Index: linux-rt-rebase.q/drivers/net/loopback.c =================================================================== --- linux-rt-rebase.q.orig/drivers/net/loopback.c +++ linux-rt-rebase.q/drivers/net/loopback.c @@ -154,12 +154,12 @@ static int loopback_xmit(struct sk_buff #endif dev->last_rx = jiffies; - /* it's OK to use __get_cpu_var() because BHs are off */ - lb_stats = &__get_cpu_var(pcpu_lstats); + lb_stats = &per_cpu(pcpu_lstats, get_cpu()); lb_stats->bytes += skb->len; lb_stats->packets++; + put_cpu(); - netif_rx(skb); + netif_rx_ni(skb); return 0; } Index: linux-rt-rebase.q/drivers/net/netconsole.c =================================================================== --- linux-rt-rebase.q.orig/drivers/net/netconsole.c +++ linux-rt-rebase.q/drivers/net/netconsole.c @@ -68,21 +68,16 @@ static int configured = 0; static void write_msg(struct console *con, const char *msg, unsigned int len) { int frag, left; - unsigned long flags; if (!np.dev) return; - local_irq_save(flags); - - for(left = len; left; ) { + for (left = len; left; ) { frag = min(left, MAX_PRINT_CHUNK); netpoll_send_udp(&np, msg, frag); msg += frag; left -= frag; } - - local_irq_restore(flags); } static struct console netconsole = { Index: linux-rt-rebase.q/drivers/net/netxen/netxen_nic.h =================================================================== --- linux-rt-rebase.q.orig/drivers/net/netxen/netxen_nic.h +++ linux-rt-rebase.q/drivers/net/netxen/netxen_nic.h @@ -1179,8 +1179,7 @@ dma_watchdog_shutdown_poll_result(struct NETXEN_CAM_RAM(NETXEN_CAM_RAM_DMA_WATCHDOG_CTRL), &ctrl, 4)) printk(KERN_ERR "failed to read dma watchdog status\n"); - return ((netxen_get_dma_watchdog_enabled(ctrl) == 0) && - (netxen_get_dma_watchdog_disabled(ctrl) == 0)); + return (netxen_get_dma_watchdog_enabled(ctrl) == 0); } static inline int Index: linux-rt-rebase.q/drivers/net/netxen/netxen_nic_main.c =================================================================== --- linux-rt-rebase.q.orig/drivers/net/netxen/netxen_nic_main.c +++ linux-rt-rebase.q/drivers/net/netxen/netxen_nic_main.c @@ -46,7 +46,7 @@ MODULE_DESCRIPTION("NetXen Multi port (1 MODULE_LICENSE("GPL"); MODULE_VERSION(NETXEN_NIC_LINUX_VERSIONID); -char netxen_nic_driver_name[] = "netxen-nic"; +char netxen_nic_driver_name[] = "netxen_nic"; static char netxen_nic_driver_string[] = "NetXen Network Driver version " NETXEN_NIC_LINUX_VERSIONID; @@ -640,6 +640,10 @@ netxen_nic_probe(struct pci_dev *pdev, c NETXEN_CRB_NORMALIZE(adapter, NETXEN_ROMUSB_GLB_PEGTUNE_DONE)); /* Handshake with the card before we register the devices. */ + writel(0, NETXEN_CRB_NORMALIZE(adapter, CRB_CMDPEG_STATE)); + netxen_pinit_from_rom(adapter, 0); + msleep(1); + netxen_load_firmware(adapter); netxen_phantom_init(adapter, NETXEN_NIC_PEG_TUNE); } @@ -782,19 +786,18 @@ static void __devexit netxen_nic_remove( if (adapter->portnum == 0) { if (init_firmware_done) { - dma_watchdog_shutdown_request(adapter); - msleep(100); i = 100; - while ((dma_watchdog_shutdown_poll_result(adapter) != 1) && i) { - printk(KERN_INFO "dma_watchdog_shutdown_poll still in progress\n"); + do { + if (dma_watchdog_shutdown_request(adapter) == 1) + break; msleep(100); - i--; - } - - if (i == 0) { - printk(KERN_ERR "dma_watchdog_shutdown_request failed\n"); - return; - } + if (dma_watchdog_shutdown_poll_result(adapter) == 1) + break; + } while (--i); + + if (i == 0) + printk(KERN_ERR "%s: dma_watchdog_shutdown failed\n", + netdev->name); /* clear the register for future unloads/loads */ writel(0, NETXEN_CRB_NORMALIZE(adapter, NETXEN_CAM_RAM(0x1fc))); @@ -803,11 +806,9 @@ static void __devexit netxen_nic_remove( /* leave the hw in the same state as reboot */ writel(0, NETXEN_CRB_NORMALIZE(adapter, CRB_CMDPEG_STATE)); - if (netxen_pinit_from_rom(adapter, 0)) - return; + netxen_pinit_from_rom(adapter, 0); msleep(1); - if (netxen_load_firmware(adapter)) - return; + netxen_load_firmware(adapter); netxen_phantom_init(adapter, NETXEN_NIC_PEG_TUNE); } @@ -816,22 +817,21 @@ static void __devexit netxen_nic_remove( printk(KERN_INFO "State: 0x%0x\n", readl(NETXEN_CRB_NORMALIZE(adapter, CRB_CMDPEG_STATE))); - dma_watchdog_shutdown_request(adapter); - msleep(100); i = 100; - while ((dma_watchdog_shutdown_poll_result(adapter) != 1) && i) { - printk(KERN_INFO "dma_watchdog_shutdown_poll still in progress\n"); + do { + if (dma_watchdog_shutdown_request(adapter) == 1) + break; msleep(100); - i--; - } + if (dma_watchdog_shutdown_poll_result(adapter) == 1) + break; + } while (--i); if (i) { netxen_free_adapter_offload(adapter); } else { - printk(KERN_ERR "failed to dma shutdown\n"); - return; + printk(KERN_ERR "%s: dma_watchdog_shutdown failed\n", + netdev->name); } - } iounmap(adapter->ahw.db_base); Index: linux-rt-rebase.q/drivers/net/phy/vitesse.c =================================================================== --- linux-rt-rebase.q.orig/drivers/net/phy/vitesse.c +++ linux-rt-rebase.q/drivers/net/phy/vitesse.c @@ -109,7 +109,7 @@ static int vsc824x_config_intr(struct ph */ err = phy_read(phydev, MII_VSC8244_ISTAT); - if (err) + if (err < 0) return err; err = phy_write(phydev, MII_VSC8244_IMASK, 0); Index: linux-rt-rebase.q/drivers/net/plip.c =================================================================== --- linux-rt-rebase.q.orig/drivers/net/plip.c +++ linux-rt-rebase.q/drivers/net/plip.c @@ -228,7 +228,10 @@ struct net_local { struct hh_cache *hh); spinlock_t lock; atomic_t kill_timer; - struct semaphore killed_timer_sem; + /* + * PREEMPT_RT: this isnt a mutex, it should be struct completion. + */ + struct compat_semaphore killed_timer_sem; }; static inline void enable_parport_interrupts (struct net_device *dev) Index: linux-rt-rebase.q/drivers/net/ppp_async.c =================================================================== --- linux-rt-rebase.q.orig/drivers/net/ppp_async.c +++ linux-rt-rebase.q/drivers/net/ppp_async.c @@ -67,7 +67,7 @@ struct asyncppp { struct tasklet_struct tsk; atomic_t refcnt; - struct semaphore dead_sem; + struct compat_semaphore dead_sem; struct ppp_channel chan; /* interface to generic ppp layer */ unsigned char obuf[OBUFSIZE]; }; Index: linux-rt-rebase.q/drivers/net/ppp_synctty.c =================================================================== --- linux-rt-rebase.q.orig/drivers/net/ppp_synctty.c +++ linux-rt-rebase.q/drivers/net/ppp_synctty.c @@ -70,7 +70,7 @@ struct syncppp { struct tasklet_struct tsk; atomic_t refcnt; - struct semaphore dead_sem; + struct compat_semaphore dead_sem; struct ppp_channel chan; /* interface to generic ppp layer */ }; Index: linux-rt-rebase.q/drivers/net/ps3_gelic_net.c =================================================================== --- linux-rt-rebase.q.orig/drivers/net/ps3_gelic_net.c +++ linux-rt-rebase.q/drivers/net/ps3_gelic_net.c @@ -290,7 +290,8 @@ static void gelic_net_release_rx_chain(s descr->buf_addr = 0; dev_kfree_skb_any(descr->skb); descr->skb = NULL; - descr->dmac_cmd_status = GELIC_NET_DESCR_NOT_IN_USE; + gelic_net_set_descr_status(descr, + GELIC_NET_DESCR_NOT_IN_USE); } descr = descr->next; } while (descr != card->rx_chain.head); @@ -374,7 +375,7 @@ static void gelic_net_release_tx_descr(s descr->skb = NULL; /* set descr status */ - descr->dmac_cmd_status = GELIC_NET_DMAC_CMDSTAT_NOT_IN_USE; + gelic_net_set_descr_status(descr, GELIC_NET_DESCR_NOT_IN_USE); } /** @@ -403,26 +404,29 @@ static void gelic_net_release_tx_chain(s "%s: forcing end of tx descriptor " \ "with status %x\n", __func__, status); - card->netdev_stats.tx_dropped++; + card->netdev->stats.tx_dropped++; break; case GELIC_NET_DESCR_COMPLETE: - card->netdev_stats.tx_packets++; - card->netdev_stats.tx_bytes += - tx_chain->tail->skb->len; + if (tx_chain->tail->skb) { + card->netdev->stats.tx_packets++; + card->netdev->stats.tx_bytes += + tx_chain->tail->skb->len; + } break; case GELIC_NET_DESCR_CARDOWNED: /* pending tx request */ default: /* any other value (== GELIC_NET_DESCR_NOT_IN_USE) */ - goto out; + if (!stop) + goto out; } gelic_net_release_tx_descr(card, tx_chain->tail); - release = 1; + release ++; } out: - if (!stop && release) + if (!stop && (2 < release)) netif_wake_queue(card->netdev); } @@ -659,19 +663,21 @@ static int gelic_net_prepare_tx_descr_v( { dma_addr_t buf[2]; unsigned int vlan_len; + struct gelic_net_descr *sec_descr = descr->next; if (skb->len < GELIC_NET_VLAN_POS) return -EINVAL; - memcpy(&descr->vlan, skb->data, GELIC_NET_VLAN_POS); + vlan_len = GELIC_NET_VLAN_POS; + memcpy(&descr->vlan, skb->data, vlan_len); if (card->vlan_index != -1) { + /* internal vlan tag used */ descr->vlan.h_vlan_proto = htons(ETH_P_8021Q); /* vlan 0x8100*/ descr->vlan.h_vlan_TCI = htons(card->vlan_id[card->vlan_index]); - vlan_len = GELIC_NET_VLAN_POS + VLAN_HLEN; /* VLAN_HLEN=4 */ - } else - vlan_len = GELIC_NET_VLAN_POS; /* no vlan tag */ + vlan_len += VLAN_HLEN; /* added for above two lines */ + } - /* first descr */ + /* map data area */ buf[0] = dma_map_single(ctodev(card), &descr->vlan, vlan_len, DMA_TO_DEVICE); @@ -682,20 +688,6 @@ static int gelic_net_prepare_tx_descr_v( return -ENOMEM; } - descr->buf_addr = buf[0]; - descr->buf_size = vlan_len; - descr->skb = skb; /* not used */ - descr->data_status = 0; - gelic_net_set_txdescr_cmdstat(descr, skb, 1); /* not the frame end */ - - /* second descr */ - card->tx_chain.head = card->tx_chain.head->next; - descr->next_descr_addr = descr->next->bus_addr; - descr = descr->next; - if (gelic_net_get_descr_status(descr) != GELIC_NET_DESCR_NOT_IN_USE) - /* XXX will be removed */ - dev_err(ctodev(card), "descr is not free!\n"); - buf[1] = dma_map_single(ctodev(card), skb->data + GELIC_NET_VLAN_POS, skb->len - GELIC_NET_VLAN_POS, DMA_TO_DEVICE); @@ -710,13 +702,24 @@ static int gelic_net_prepare_tx_descr_v( return -ENOMEM; } - descr->buf_addr = buf[1]; - descr->buf_size = skb->len - GELIC_NET_VLAN_POS; - descr->skb = skb; + /* first descr */ + descr->buf_addr = buf[0]; + descr->buf_size = vlan_len; + descr->skb = NULL; /* not used */ descr->data_status = 0; - descr->next_descr_addr = 0; /* terminate hw descr */ - gelic_net_set_txdescr_cmdstat(descr, skb, 0); + descr->next_descr_addr = descr->next->bus_addr; + gelic_net_set_txdescr_cmdstat(descr, skb, 1); /* not the frame end */ + + /* second descr */ + sec_descr->buf_addr = buf[1]; + sec_descr->buf_size = skb->len - GELIC_NET_VLAN_POS; + sec_descr->skb = skb; + sec_descr->data_status = 0; + sec_descr->next_descr_addr = 0; /* terminate hw descr */ + gelic_net_set_txdescr_cmdstat(sec_descr, skb, 0); + /* bump free descriptor pointer */ + card->tx_chain.head = sec_descr->next; return 0; } @@ -729,7 +732,7 @@ static int gelic_net_prepare_tx_descr_v( static int gelic_net_kick_txdma(struct gelic_net_card *card, struct gelic_net_descr *descr) { - int status = -ENXIO; + int status = 0; int count = 10; if (card->tx_dma_progress) @@ -763,47 +766,62 @@ static int gelic_net_kick_txdma(struct g static int gelic_net_xmit(struct sk_buff *skb, struct net_device *netdev) { struct gelic_net_card *card = netdev_priv(netdev); - struct gelic_net_descr *descr = NULL; + struct gelic_net_descr *descr; int result; unsigned long flags; spin_lock_irqsave(&card->tx_dma_lock, flags); gelic_net_release_tx_chain(card, 0); - if (!skb) - goto kick; + descr = gelic_net_get_next_tx_descr(card); if (!descr) { + /* + * no more descriptors free + */ netif_stop_queue(netdev); spin_unlock_irqrestore(&card->tx_dma_lock, flags); return NETDEV_TX_BUSY; } - result = gelic_net_prepare_tx_descr_v(card, descr, skb); - - if (result) - goto error; - card->tx_chain.head = card->tx_chain.head->next; - - if (descr->prev) - descr->prev->next_descr_addr = descr->bus_addr; -kick: + result = gelic_net_prepare_tx_descr_v(card, descr, skb); + if (result) { + /* + * DMA map failed. As chanses are that failure + * would continue, just release skb and return + */ + card->netdev->stats.tx_dropped++; + dev_kfree_skb_any(skb); + spin_unlock_irqrestore(&card->tx_dma_lock, flags); + return NETDEV_TX_OK; + } + /* + * link this prepared descriptor to previous one + * to achieve high performance + */ + descr->prev->next_descr_addr = descr->bus_addr; /* * as hardware descriptor is modified in the above lines, * ensure that the hardware sees it */ wmb(); - if (gelic_net_kick_txdma(card, card->tx_chain.tail)) - goto error; + if (gelic_net_kick_txdma(card, descr)) { + /* + * kick failed. + * release descriptors which were just prepared + */ + card->netdev->stats.tx_dropped++; + gelic_net_release_tx_descr(card, descr); + gelic_net_release_tx_descr(card, descr->next); + card->tx_chain.tail = descr->next->next; + dev_info(ctodev(card), "%s: kick failure\n", __func__); + } else { + /* OK, DMA started/reserved */ + netdev->trans_start = jiffies; + } - netdev->trans_start = jiffies; spin_unlock_irqrestore(&card->tx_dma_lock, flags); return NETDEV_TX_OK; - -error: - card->netdev_stats.tx_dropped++; - spin_unlock_irqrestore(&card->tx_dma_lock, flags); - return NETDEV_TX_LOCKED; } /** @@ -854,8 +872,8 @@ static void gelic_net_pass_skb_up(struct skb->ip_summed = CHECKSUM_NONE; /* update netdevice statistics */ - card->netdev_stats.rx_packets++; - card->netdev_stats.rx_bytes += skb->len; + card->netdev->stats.rx_packets++; + card->netdev->stats.rx_bytes += skb->len; /* pass skb up to stack */ netif_receive_skb(skb); @@ -895,38 +913,67 @@ static int gelic_net_decode_one_descr(st (status == GELIC_NET_DESCR_FORCE_END)) { dev_info(ctodev(card), "dropping RX descriptor with state %x\n", status); - card->netdev_stats.rx_dropped++; + card->netdev->stats.rx_dropped++; goto refill; } - if ((status != GELIC_NET_DESCR_COMPLETE) && - (status != GELIC_NET_DESCR_FRAME_END)) { + if (status == GELIC_NET_DESCR_BUFFER_FULL) { + /* + * Buffer full would occur if and only if + * the frame length was longer than the size of this + * descriptor's buffer. If the frame length was equal + * to or shorter than buffer'size, FRAME_END condition + * would occur. + * Anyway this frame was longer than the MTU, + * just drop it. + */ + dev_info(ctodev(card), "overlength frame\n"); + goto refill; + } + /* + * descriptoers any other than FRAME_END here should + * be treated as error. + */ + if (status != GELIC_NET_DESCR_FRAME_END) { dev_dbg(ctodev(card), "RX descriptor with state %x\n", status); goto refill; } /* ok, we've got a packet in descr */ - gelic_net_pass_skb_up(descr, card); /* 1: skb_up sccess */ - + gelic_net_pass_skb_up(descr, card); refill: - descr->next_descr_addr = 0; /* unlink the descr */ + /* + * So that always DMAC can see the end + * of the descriptor chain to avoid + * from unwanted DMAC overrun. + */ + descr->next_descr_addr = 0; /* change the descriptor state: */ gelic_net_set_descr_status(descr, GELIC_NET_DESCR_NOT_IN_USE); - /* refill one desc - * FIXME: this can fail, but for now, just leave this - * descriptor without skb + /* + * this call can fail, but for now, just leave this + * decriptor without skb */ gelic_net_prepare_rx_descr(card, descr); + chain->head = descr; chain->tail = descr->next; + + /* + * Set this descriptor the end of the chain. + */ descr->prev->next_descr_addr = descr->bus_addr; + /* + * If dmac chain was met, DMAC stopped. + * thus re-enable it + */ if (dmac_chain_ended) { - gelic_net_enable_rxdmac(card); - dev_dbg(ctodev(card), "reenable rx dma\n"); + card->rx_dma_restart_required = 1; + dev_dbg(ctodev(card), "reenable rx dma scheduled\n"); } return 1; @@ -968,20 +1015,6 @@ static int gelic_net_poll(struct net_dev } else return 1; } - -/** - * gelic_net_get_stats - get interface statistics - * @netdev: interface device structure - * - * returns the interface statistics residing in the gelic_net_card struct - */ -static struct net_device_stats *gelic_net_get_stats(struct net_device *netdev) -{ - struct gelic_net_card *card = netdev_priv(netdev); - - return &card->netdev_stats; -} - /** * gelic_net_change_mtu - changes the MTU of an interface * @netdev: interface device structure @@ -1016,6 +1049,11 @@ static irqreturn_t gelic_net_interrupt(i if (!status) return IRQ_NONE; + if (card->rx_dma_restart_required) { + card->rx_dma_restart_required = 0; + gelic_net_enable_rxdmac(card); + } + if (status & GELIC_NET_RXINT) { gelic_net_rx_irq_off(card); netif_rx_schedule(netdev); @@ -1024,9 +1062,10 @@ static irqreturn_t gelic_net_interrupt(i if (status & GELIC_NET_TXINT) { spin_lock_irqsave(&card->tx_dma_lock, flags); card->tx_dma_progress = 0; + gelic_net_release_tx_chain(card, 0); + /* kick outstanding tx descriptor if any */ + gelic_net_kick_txdma(card, card->tx_chain.tail); spin_unlock_irqrestore(&card->tx_dma_lock, flags); - /* start pending DMA */ - gelic_net_xmit(NULL, netdev); } return IRQ_HANDLED; } @@ -1068,7 +1107,7 @@ static int gelic_net_open_device(struct } result = request_irq(card->netdev->irq, gelic_net_interrupt, - IRQF_DISABLED, "gelic network", card->netdev); + IRQF_DISABLED, card->netdev->name, card->netdev); if (result) { dev_info(ctodev(card), "%s:%d: request_irq failed (%d)\n", @@ -1107,7 +1146,7 @@ static int gelic_net_open(struct net_dev card->descr, GELIC_NET_TX_DESCRIPTORS)) goto alloc_tx_failed; if (gelic_net_init_chain(card, &card->rx_chain, - card->descr + GELIC_NET_RX_DESCRIPTORS, + card->descr + GELIC_NET_TX_DESCRIPTORS, GELIC_NET_RX_DESCRIPTORS)) goto alloc_rx_failed; @@ -1129,7 +1168,6 @@ static int gelic_net_open(struct net_dev netif_start_queue(netdev); netif_carrier_on(netdev); - netif_poll_enable(netdev); return 0; @@ -1141,7 +1179,6 @@ alloc_tx_failed: return -ENOMEM; } -#ifdef GELIC_NET_ETHTOOL static void gelic_net_get_drvinfo (struct net_device *netdev, struct ethtool_drvinfo *info) { @@ -1261,7 +1298,6 @@ static struct ethtool_ops gelic_net_etht .get_rx_csum = gelic_net_get_rx_csum, .set_rx_csum = gelic_net_set_rx_csum, }; -#endif /** * gelic_net_tx_timeout_task - task scheduled by the watchdog timeout @@ -1320,7 +1356,6 @@ static void gelic_net_setup_netdev_ops(s netdev->open = &gelic_net_open; netdev->stop = &gelic_net_stop; netdev->hard_start_xmit = &gelic_net_xmit; - netdev->get_stats = &gelic_net_get_stats; netdev->set_multicast_list = &gelic_net_set_multi; netdev->change_mtu = &gelic_net_change_mtu; /* tx watchdog */ @@ -1329,9 +1364,7 @@ static void gelic_net_setup_netdev_ops(s /* NAPI */ netdev->poll = &gelic_net_poll; netdev->weight = GELIC_NET_NAPI_WEIGHT; -#ifdef GELIC_NET_ETHTOOL netdev->ethtool_ops = &gelic_net_ethtool_ops; -#endif } /** Index: linux-rt-rebase.q/drivers/net/ps3_gelic_net.h =================================================================== --- linux-rt-rebase.q.orig/drivers/net/ps3_gelic_net.h +++ linux-rt-rebase.q/drivers/net/ps3_gelic_net.h @@ -28,21 +28,12 @@ #ifndef _GELIC_NET_H #define _GELIC_NET_H -#define GELIC_NET_DRV_NAME "Gelic Network Driver" -#define GELIC_NET_DRV_VERSION "1.0" - -#define GELIC_NET_ETHTOOL /* use ethtool */ - -/* ioctl */ -#define GELIC_NET_GET_MODE (SIOCDEVPRIVATE + 0) -#define GELIC_NET_SET_MODE (SIOCDEVPRIVATE + 1) - /* descriptors */ #define GELIC_NET_RX_DESCRIPTORS 128 /* num of descriptors */ #define GELIC_NET_TX_DESCRIPTORS 128 /* num of descriptors */ -#define GELIC_NET_MAX_MTU 2308 -#define GELIC_NET_MIN_MTU 64 +#define GELIC_NET_MAX_MTU VLAN_ETH_FRAME_LEN +#define GELIC_NET_MIN_MTU VLAN_ETH_ZLEN #define GELIC_NET_RXBUF_ALIGN 128 #define GELIC_NET_RX_CSUM_DEFAULT 1 /* hw chksum */ #define GELIC_NET_WATCHDOG_TIMEOUT 5*HZ @@ -90,7 +81,8 @@ enum gelic_net_int1_status { */ #define GELIC_NET_RXVLNPKT 0x00200000 /* VLAN packet */ /* bit 20..16 reserved */ -#define GELIC_NET_RXRECNUM 0x0000ff00 /* reception receipt number */ +#define GELIC_NET_RXRRECNUM 0x0000ff00 /* reception receipt number */ +#define GELIC_NET_RXRRECNUM_SHIFT 8 /* bit 7..0 reserved */ #define GELIC_NET_TXDESC_TAIL 0 @@ -133,19 +125,19 @@ enum gelic_net_int1_status { * interrupt status */ #define GELIC_NET_DMAC_CMDSTAT_CHAIN_END 0x00000002 /* RXDCEIS:DMA stopped */ -#define GELIC_NET_DMAC_CMDSTAT_NOT_IN_USE 0xb0000000 #define GELIC_NET_DESCR_IND_PROC_SHIFT 28 #define GELIC_NET_DESCR_IND_PROC_MASKO 0x0fffffff enum gelic_net_descr_status { - GELIC_NET_DESCR_COMPLETE = 0x00, /* used in rx and tx */ + GELIC_NET_DESCR_COMPLETE = 0x00, /* used in tx */ + GELIC_NET_DESCR_BUFFER_FULL = 0x00, /* used in rx */ GELIC_NET_DESCR_RESPONSE_ERROR = 0x01, /* used in rx and tx */ GELIC_NET_DESCR_PROTECTION_ERROR = 0x02, /* used in rx and tx */ GELIC_NET_DESCR_FRAME_END = 0x04, /* used in rx */ GELIC_NET_DESCR_FORCE_END = 0x05, /* used in rx and tx */ GELIC_NET_DESCR_CARDOWNED = 0x0a, /* used in rx and tx */ - GELIC_NET_DESCR_NOT_IN_USE /* any other value */ + GELIC_NET_DESCR_NOT_IN_USE = 0x0b /* any other value */ }; /* for lv1_net_control */ #define GELIC_NET_GET_MAC_ADDRESS 0x0000000000000001 @@ -216,10 +208,10 @@ struct gelic_net_card { struct gelic_net_descr_chain tx_chain; struct gelic_net_descr_chain rx_chain; + int rx_dma_restart_required; /* gurad dmac descriptor chain*/ spinlock_t chain_lock; - struct net_device_stats netdev_stats; int rx_csum; /* guard tx_dma_progress */ spinlock_t tx_dma_lock; Index: linux-rt-rebase.q/drivers/net/sungem.c =================================================================== --- linux-rt-rebase.q.orig/drivers/net/sungem.c +++ linux-rt-rebase.q/drivers/net/sungem.c @@ -1034,10 +1034,8 @@ static int gem_start_xmit(struct sk_buff (csum_stuff_off << 21)); } - local_irq_save(flags); - if (!spin_trylock(&gp->tx_lock)) { + if (!spin_trylock_irqsave(&gp->tx_lock, flags)) { /* Tell upper layer to requeue */ - local_irq_restore(flags); return NETDEV_TX_LOCKED; } /* We raced with gem_do_stop() */ Index: linux-rt-rebase.q/drivers/net/tulip/tulip_core.c =================================================================== --- linux-rt-rebase.q.orig/drivers/net/tulip/tulip_core.c +++ linux-rt-rebase.q/drivers/net/tulip/tulip_core.c @@ -1798,6 +1798,7 @@ static void __devexit tulip_remove_one ( pci_iounmap(pdev, tp->base_addr); free_netdev (dev); pci_release_regions (pdev); + pci_disable_device (pdev); pci_set_drvdata (pdev, NULL); /* pci_power_off (pdev, -1); */ Index: linux-rt-rebase.q/drivers/net/ucc_geth.c =================================================================== --- linux-rt-rebase.q.orig/drivers/net/ucc_geth.c +++ linux-rt-rebase.q/drivers/net/ucc_geth.c @@ -43,10 +43,6 @@ #undef DEBUG -#define DRV_DESC "QE UCC Gigabit Ethernet Controller" -#define DRV_NAME "ucc_geth" -#define DRV_VERSION "1.1" - #define ugeth_printk(level, format, arg...) \ printk(level format "\n", ## arg) @@ -64,9 +60,19 @@ #else #define ugeth_vdbg(fmt, args...) do { } while (0) #endif /* UGETH_VERBOSE_DEBUG */ +#define UGETH_MSG_DEFAULT (NETIF_MSG_IFUP << 1 ) - 1 +void uec_set_ethtool_ops(struct net_device *netdev); + static DEFINE_SPINLOCK(ugeth_lock); +static struct { + u32 msg_enable; +} debug = { -1 }; + +module_param_named(debug, debug.msg_enable, int, 0); +MODULE_PARM_DESC(debug, "Debug verbosity level (0=none, ..., 0xffff=all)"); + static struct ucc_geth_info ugeth_primary_info = { .uf_info = { .bd_mem_part = MEM_PART_SYSTEM, @@ -104,6 +110,7 @@ static struct ucc_geth_info ugeth_primar .maxRetransmission = 0xf, .collisionWindow = 0x37, .receiveFlowControl = 1, + .transmitFlowControl = 1, .maxGroupAddrInHash = 4, .maxIndAddrInHash = 4, .prel = 7, @@ -139,7 +146,9 @@ static struct ucc_geth_info ugeth_primar .numStationAddresses = UCC_GETH_NUM_OF_STATION_ADDRESSES_1, .largestexternallookupkeysize = QE_FLTR_LARGEST_EXTERNAL_TABLE_LOOKUP_KEY_SIZE_NONE, - .statisticsMode = UCC_GETH_STATISTICS_GATHERING_MODE_NONE, + .statisticsMode = UCC_GETH_STATISTICS_GATHERING_MODE_HARDWARE | + UCC_GETH_STATISTICS_GATHERING_MODE_FIRMWARE_TX | + UCC_GETH_STATISTICS_GATHERING_MODE_FIRMWARE_RX, .vlanOperationTagged = UCC_GETH_VLAN_OPERATION_TAGGED_NOP, .vlanOperationNonTagged = UCC_GETH_VLAN_OPERATION_NON_TAGGED_NOP, .rxQoSMode = UCC_GETH_QOS_MODE_DEFAULT, @@ -281,7 +290,8 @@ static int fill_init_enet_entries(struct for (i = 0; i < num_entries; i++) { if ((snum = qe_get_snum()) < 0) { - ugeth_err("fill_init_enet_entries: Can not get SNUM."); + if (netif_msg_ifup(ugeth)) + ugeth_err("fill_init_enet_entries: Can not get SNUM."); return snum; } if ((i == 0) && skip_page_for_first_entry) @@ -291,8 +301,8 @@ static int fill_init_enet_entries(struct init_enet_offset = qe_muram_alloc(thread_size, thread_alignment); if (IS_ERR_VALUE(init_enet_offset)) { - ugeth_err - ("fill_init_enet_entries: Can not allocate DPRAM memory."); + if (netif_msg_ifup(ugeth)) + ugeth_err("fill_init_enet_entries: Can not allocate DPRAM memory."); qe_put_snum((u8) snum); return -ENOMEM; } @@ -1200,7 +1210,7 @@ static int init_inter_frame_gap_params(u return 0; } -static int init_flow_control_params(u32 automatic_flow_control_mode, +int init_flow_control_params(u32 automatic_flow_control_mode, int rx_flow_control_enable, int tx_flow_control_enable, u16 pause_period, @@ -1486,9 +1496,9 @@ static int adjust_enet_interface(struct ret_val = init_preamble_length(ug_info->prel, &ug_regs->maccfg2); if (ret_val != 0) { - ugeth_err - ("%s: Preamble length must be between 3 and 7 inclusive.", - __FUNCTION__); + if (netif_msg_probe(ugeth)) + ugeth_err("%s: Preamble length must be between 3 and 7 inclusive.", + __FUNCTION__); return ret_val; } @@ -1726,7 +1736,8 @@ static int ugeth_enable(struct ucc_geth_ /* check if the UCC number is in range. */ if (ugeth->ug_info->uf_info.ucc_num >= UCC_MAX_NUM) { - ugeth_err("%s: ucc_num out of range.", __FUNCTION__); + if (netif_msg_probe(ugeth)) + ugeth_err("%s: ucc_num out of range.", __FUNCTION__); return -EINVAL; } @@ -1754,7 +1765,8 @@ static int ugeth_disable(struct ucc_geth /* check if the UCC number is in range. */ if (ugeth->ug_info->uf_info.ucc_num >= UCC_MAX_NUM) { - ugeth_err("%s: ucc_num out of range.", __FUNCTION__); + if (netif_msg_probe(ugeth)) + ugeth_err("%s: ucc_num out of range.", __FUNCTION__); return -EINVAL; } @@ -2306,7 +2318,9 @@ static int ucc_struct_init(struct ucc_ge if (!((uf_info->bd_mem_part == MEM_PART_SYSTEM) || (uf_info->bd_mem_part == MEM_PART_MURAM))) { - ugeth_err("%s: Bad memory partition value.", __FUNCTION__); + if (netif_msg_probe(ugeth)) + ugeth_err("%s: Bad memory partition value.", + __FUNCTION__); return -EINVAL; } @@ -2315,9 +2329,10 @@ static int ucc_struct_init(struct ucc_ge if ((ug_info->bdRingLenRx[i] < UCC_GETH_RX_BD_RING_SIZE_MIN) || (ug_info->bdRingLenRx[i] % UCC_GETH_RX_BD_RING_SIZE_ALIGNMENT)) { - ugeth_err - ("%s: Rx BD ring length must be multiple of 4," - " no smaller than 8.", __FUNCTION__); + if (netif_msg_probe(ugeth)) + ugeth_err + ("%s: Rx BD ring length must be multiple of 4, no smaller than 8.", + __FUNCTION__); return -EINVAL; } } @@ -2325,9 +2340,10 @@ static int ucc_struct_init(struct ucc_ge /* Tx BD lengths */ for (i = 0; i < ug_info->numQueuesTx; i++) { if (ug_info->bdRingLenTx[i] < UCC_GETH_TX_BD_RING_SIZE_MIN) { - ugeth_err - ("%s: Tx BD ring length must be no smaller than 2.", - __FUNCTION__); + if (netif_msg_probe(ugeth)) + ugeth_err + ("%s: Tx BD ring length must be no smaller than 2.", + __FUNCTION__); return -EINVAL; } } @@ -2335,31 +2351,35 @@ static int ucc_struct_init(struct ucc_ge /* mrblr */ if ((uf_info->max_rx_buf_length == 0) || (uf_info->max_rx_buf_length % UCC_GETH_MRBLR_ALIGNMENT)) { - ugeth_err - ("%s: max_rx_buf_length must be non-zero multiple of 128.", - __FUNCTION__); + if (netif_msg_probe(ugeth)) + ugeth_err + ("%s: max_rx_buf_length must be non-zero multiple of 128.", + __FUNCTION__); return -EINVAL; } /* num Tx queues */ if (ug_info->numQueuesTx > NUM_TX_QUEUES) { - ugeth_err("%s: number of tx queues too large.", __FUNCTION__); + if (netif_msg_probe(ugeth)) + ugeth_err("%s: number of tx queues too large.", __FUNCTION__); return -EINVAL; } /* num Rx queues */ if (ug_info->numQueuesRx > NUM_RX_QUEUES) { - ugeth_err("%s: number of rx queues too large.", __FUNCTION__); + if (netif_msg_probe(ugeth)) + ugeth_err("%s: number of rx queues too large.", __FUNCTION__); return -EINVAL; } /* l2qt */ for (i = 0; i < UCC_GETH_VLAN_PRIORITY_MAX; i++) { if (ug_info->l2qt[i] >= ug_info->numQueuesRx) { - ugeth_err - ("%s: VLAN priority table entry must not be" - " larger than number of Rx queues.", - __FUNCTION__); + if (netif_msg_probe(ugeth)) + ugeth_err + ("%s: VLAN priority table entry must not be" + " larger than number of Rx queues.", + __FUNCTION__); return -EINVAL; } } @@ -2367,26 +2387,29 @@ static int ucc_struct_init(struct ucc_ge /* l3qt */ for (i = 0; i < UCC_GETH_IP_PRIORITY_MAX; i++) { if (ug_info->l3qt[i] >= ug_info->numQueuesRx) { - ugeth_err - ("%s: IP priority table entry must not be" - " larger than number of Rx queues.", - __FUNCTION__); + if (netif_msg_probe(ugeth)) + ugeth_err + ("%s: IP priority table entry must not be" + " larger than number of Rx queues.", + __FUNCTION__); return -EINVAL; } } if (ug_info->cam && !ug_info->ecamptr) { - ugeth_err("%s: If cam mode is chosen, must supply cam ptr.", - __FUNCTION__); + if (netif_msg_probe(ugeth)) + ugeth_err("%s: If cam mode is chosen, must supply cam ptr.", + __FUNCTION__); return -EINVAL; } if ((ug_info->numStationAddresses != UCC_GETH_NUM_OF_STATION_ADDRESSES_1) && ug_info->rxExtendedFiltering) { - ugeth_err("%s: Number of station addresses greater than 1 " - "not allowed in extended parsing mode.", - __FUNCTION__); + if (netif_msg_probe(ugeth)) + ugeth_err("%s: Number of station addresses greater than 1 " + "not allowed in extended parsing mode.", + __FUNCTION__); return -EINVAL; } @@ -2399,7 +2422,8 @@ static int ucc_struct_init(struct ucc_ge uf_info->uccm_mask |= (UCCE_TXBF_SINGLE_MASK << i); /* Initialize the general fast UCC block. */ if (ucc_fast_init(uf_info, &ugeth->uccf)) { - ugeth_err("%s: Failed to init uccf.", __FUNCTION__); + if (netif_msg_probe(ugeth)) + ugeth_err("%s: Failed to init uccf.", __FUNCTION__); ucc_geth_memclean(ugeth); return -ENOMEM; } @@ -2452,7 +2476,9 @@ static int ucc_geth_startup(struct ucc_g numThreadsRxNumerical = 8; break; default: - ugeth_err("%s: Bad number of Rx threads value.", __FUNCTION__); + if (netif_msg_ifup(ugeth)) + ugeth_err("%s: Bad number of Rx threads value.", + __FUNCTION__); ucc_geth_memclean(ugeth); return -EINVAL; break; @@ -2475,7 +2501,9 @@ static int ucc_geth_startup(struct ucc_g numThreadsTxNumerical = 8; break; default: - ugeth_err("%s: Bad number of Tx threads value.", __FUNCTION__); + if (netif_msg_ifup(ugeth)) + ugeth_err("%s: Bad number of Tx threads value.", + __FUNCTION__); ucc_geth_memclean(ugeth); return -EINVAL; break; @@ -2507,7 +2535,7 @@ static int ucc_geth_startup(struct ucc_g /* For more details see the hardware spec. */ init_flow_control_params(ug_info->aufc, ug_info->receiveFlowControl, - 1, + ug_info->transmitFlowControl, ug_info->pausePeriod, ug_info->extensionField, &uf_regs->upsmr, @@ -2527,8 +2555,9 @@ static int ucc_geth_startup(struct ucc_g ug_info->backToBackInterFrameGap, &ug_regs->ipgifg); if (ret_val != 0) { - ugeth_err("%s: IPGIFG initialization parameter too large.", - __FUNCTION__); + if (netif_msg_ifup(ugeth)) + ugeth_err("%s: IPGIFG initialization parameter too large.", + __FUNCTION__); ucc_geth_memclean(ugeth); return ret_val; } @@ -2544,7 +2573,8 @@ static int ucc_geth_startup(struct ucc_g ug_info->collisionWindow, &ug_regs->hafdup); if (ret_val != 0) { - ugeth_err("%s: Half Duplex initialization parameter too large.", + if (netif_msg_ifup(ugeth)) + ugeth_err("%s: Half Duplex initialization parameter too large.", __FUNCTION__); ucc_geth_memclean(ugeth); return ret_val; @@ -2597,9 +2627,10 @@ static int ucc_geth_startup(struct ucc_g tx_bd_ring_offset[j]); } if (!ugeth->p_tx_bd_ring[j]) { - ugeth_err - ("%s: Can not allocate memory for Tx bd rings.", - __FUNCTION__); + if (netif_msg_ifup(ugeth)) + ugeth_err + ("%s: Can not allocate memory for Tx bd rings.", + __FUNCTION__); ucc_geth_memclean(ugeth); return -ENOMEM; } @@ -2632,9 +2663,10 @@ static int ucc_geth_startup(struct ucc_g rx_bd_ring_offset[j]); } if (!ugeth->p_rx_bd_ring[j]) { - ugeth_err - ("%s: Can not allocate memory for Rx bd rings.", - __FUNCTION__); + if (netif_msg_ifup(ugeth)) + ugeth_err + ("%s: Can not allocate memory for Rx bd rings.", + __FUNCTION__); ucc_geth_memclean(ugeth); return -ENOMEM; } @@ -2648,8 +2680,9 @@ static int ucc_geth_startup(struct ucc_g GFP_KERNEL); if (ugeth->tx_skbuff[j] == NULL) { - ugeth_err("%s: Could not allocate tx_skbuff", - __FUNCTION__); + if (netif_msg_ifup(ugeth)) + ugeth_err("%s: Could not allocate tx_skbuff", + __FUNCTION__); ucc_geth_memclean(ugeth); return -ENOMEM; } @@ -2679,8 +2712,9 @@ static int ucc_geth_startup(struct ucc_g GFP_KERNEL); if (ugeth->rx_skbuff[j] == NULL) { - ugeth_err("%s: Could not allocate rx_skbuff", - __FUNCTION__); + if (netif_msg_ifup(ugeth)) + ugeth_err("%s: Could not allocate rx_skbuff", + __FUNCTION__); ucc_geth_memclean(ugeth); return -ENOMEM; } @@ -2711,9 +2745,10 @@ static int ucc_geth_startup(struct ucc_g qe_muram_alloc(sizeof(struct ucc_geth_tx_global_pram), UCC_GETH_TX_GLOBAL_PRAM_ALIGNMENT); if (IS_ERR_VALUE(ugeth->tx_glbl_pram_offset)) { - ugeth_err - ("%s: Can not allocate DPRAM memory for p_tx_glbl_pram.", - __FUNCTION__); + if (netif_msg_ifup(ugeth)) + ugeth_err + ("%s: Can not allocate DPRAM memory for p_tx_glbl_pram.", + __FUNCTION__); ucc_geth_memclean(ugeth); return -ENOMEM; } @@ -2733,9 +2768,10 @@ static int ucc_geth_startup(struct ucc_g 32 * (numThreadsTxNumerical == 1), UCC_GETH_THREAD_DATA_ALIGNMENT); if (IS_ERR_VALUE(ugeth->thread_dat_tx_offset)) { - ugeth_err - ("%s: Can not allocate DPRAM memory for p_thread_data_tx.", - __FUNCTION__); + if (netif_msg_ifup(ugeth)) + ugeth_err + ("%s: Can not allocate DPRAM memory for p_thread_data_tx.", + __FUNCTION__); ucc_geth_memclean(ugeth); return -ENOMEM; } @@ -2761,9 +2797,10 @@ static int ucc_geth_startup(struct ucc_g sizeof(struct ucc_geth_send_queue_qd), UCC_GETH_SEND_QUEUE_QUEUE_DESCRIPTOR_ALIGNMENT); if (IS_ERR_VALUE(ugeth->send_q_mem_reg_offset)) { - ugeth_err - ("%s: Can not allocate DPRAM memory for p_send_q_mem_reg.", - __FUNCTION__); + if (netif_msg_ifup(ugeth)) + ugeth_err + ("%s: Can not allocate DPRAM memory for p_send_q_mem_reg.", + __FUNCTION__); ucc_geth_memclean(ugeth); return -ENOMEM; } @@ -2804,9 +2841,10 @@ static int ucc_geth_startup(struct ucc_g qe_muram_alloc(sizeof(struct ucc_geth_scheduler), UCC_GETH_SCHEDULER_ALIGNMENT); if (IS_ERR_VALUE(ugeth->scheduler_offset)) { - ugeth_err - ("%s: Can not allocate DPRAM memory for p_scheduler.", - __FUNCTION__); + if (netif_msg_ifup(ugeth)) + ugeth_err + ("%s: Can not allocate DPRAM memory for p_scheduler.", + __FUNCTION__); ucc_geth_memclean(ugeth); return -ENOMEM; } @@ -2852,9 +2890,11 @@ static int ucc_geth_startup(struct ucc_g (struct ucc_geth_tx_firmware_statistics_pram), UCC_GETH_TX_STATISTICS_ALIGNMENT); if (IS_ERR_VALUE(ugeth->tx_fw_statistics_pram_offset)) { - ugeth_err - ("%s: Can not allocate DPRAM memory for" - " p_tx_fw_statistics_pram.", __FUNCTION__); + if (netif_msg_ifup(ugeth)) + ugeth_err + ("%s: Can not allocate DPRAM memory for" + " p_tx_fw_statistics_pram.", + __FUNCTION__); ucc_geth_memclean(ugeth); return -ENOMEM; } @@ -2891,9 +2931,10 @@ static int ucc_geth_startup(struct ucc_g qe_muram_alloc(sizeof(struct ucc_geth_rx_global_pram), UCC_GETH_RX_GLOBAL_PRAM_ALIGNMENT); if (IS_ERR_VALUE(ugeth->rx_glbl_pram_offset)) { - ugeth_err - ("%s: Can not allocate DPRAM memory for p_rx_glbl_pram.", - __FUNCTION__); + if (netif_msg_ifup(ugeth)) + ugeth_err + ("%s: Can not allocate DPRAM memory for p_rx_glbl_pram.", + __FUNCTION__); ucc_geth_memclean(ugeth); return -ENOMEM; } @@ -2912,9 +2953,10 @@ static int ucc_geth_startup(struct ucc_g sizeof(struct ucc_geth_thread_data_rx), UCC_GETH_THREAD_DATA_ALIGNMENT); if (IS_ERR_VALUE(ugeth->thread_dat_rx_offset)) { - ugeth_err - ("%s: Can not allocate DPRAM memory for p_thread_data_rx.", - __FUNCTION__); + if (netif_msg_ifup(ugeth)) + ugeth_err + ("%s: Can not allocate DPRAM memory for p_thread_data_rx.", + __FUNCTION__); ucc_geth_memclean(ugeth); return -ENOMEM; } @@ -2935,9 +2977,10 @@ static int ucc_geth_startup(struct ucc_g (struct ucc_geth_rx_firmware_statistics_pram), UCC_GETH_RX_STATISTICS_ALIGNMENT); if (IS_ERR_VALUE(ugeth->rx_fw_statistics_pram_offset)) { - ugeth_err - ("%s: Can not allocate DPRAM memory for" - " p_rx_fw_statistics_pram.", __FUNCTION__); + if (netif_msg_ifup(ugeth)) + ugeth_err + ("%s: Can not allocate DPRAM memory for" + " p_rx_fw_statistics_pram.", __FUNCTION__); ucc_geth_memclean(ugeth); return -ENOMEM; } @@ -2957,9 +3000,10 @@ static int ucc_geth_startup(struct ucc_g sizeof(struct ucc_geth_rx_interrupt_coalescing_entry) + 4, UCC_GETH_RX_INTERRUPT_COALESCING_ALIGNMENT); if (IS_ERR_VALUE(ugeth->rx_irq_coalescing_tbl_offset)) { - ugeth_err - ("%s: Can not allocate DPRAM memory for" - " p_rx_irq_coalescing_tbl.", __FUNCTION__); + if (netif_msg_ifup(ugeth)) + ugeth_err + ("%s: Can not allocate DPRAM memory for" + " p_rx_irq_coalescing_tbl.", __FUNCTION__); ucc_geth_memclean(ugeth); return -ENOMEM; } @@ -3025,9 +3069,10 @@ static int ucc_geth_startup(struct ucc_g sizeof(struct ucc_geth_rx_prefetched_bds)), UCC_GETH_RX_BD_QUEUES_ALIGNMENT); if (IS_ERR_VALUE(ugeth->rx_bd_qs_tbl_offset)) { - ugeth_err - ("%s: Can not allocate DPRAM memory for p_rx_bd_qs_tbl.", - __FUNCTION__); + if (netif_msg_ifup(ugeth)) + ugeth_err + ("%s: Can not allocate DPRAM memory for p_rx_bd_qs_tbl.", + __FUNCTION__); ucc_geth_memclean(ugeth); return -ENOMEM; } @@ -3102,8 +3147,9 @@ static int ucc_geth_startup(struct ucc_g /* initialize extended filtering */ if (ug_info->rxExtendedFiltering) { if (!ug_info->extendedFilteringChainPointer) { - ugeth_err("%s: Null Extended Filtering Chain Pointer.", - __FUNCTION__); + if (netif_msg_ifup(ugeth)) + ugeth_err("%s: Null Extended Filtering Chain Pointer.", + __FUNCTION__); ucc_geth_memclean(ugeth); return -EINVAL; } @@ -3114,9 +3160,10 @@ static int ucc_geth_startup(struct ucc_g qe_muram_alloc(sizeof(struct ucc_geth_exf_global_pram), UCC_GETH_RX_EXTENDED_FILTERING_GLOBAL_PARAMETERS_ALIGNMENT); if (IS_ERR_VALUE(ugeth->exf_glbl_param_offset)) { - ugeth_err - ("%s: Can not allocate DPRAM memory for" - " p_exf_glbl_param.", __FUNCTION__); + if (netif_msg_ifup(ugeth)) + ugeth_err + ("%s: Can not allocate DPRAM memory for" + " p_exf_glbl_param.", __FUNCTION__); ucc_geth_memclean(ugeth); return -ENOMEM; } @@ -3161,9 +3208,10 @@ static int ucc_geth_startup(struct ucc_g */ if (!(ugeth->p_init_enet_param_shadow = kmalloc(sizeof(struct ucc_geth_init_pram), GFP_KERNEL))) { - ugeth_err - ("%s: Can not allocate memory for" - " p_UccInitEnetParamShadows.", __FUNCTION__); + if (netif_msg_ifup(ugeth)) + ugeth_err + ("%s: Can not allocate memory for" + " p_UccInitEnetParamShadows.", __FUNCTION__); ucc_geth_memclean(ugeth); return -ENOMEM; } @@ -3196,8 +3244,9 @@ static int ucc_geth_startup(struct ucc_g QE_FLTR_LARGEST_EXTERNAL_TABLE_LOOKUP_KEY_SIZE_8_BYTES) && (ug_info->largestexternallookupkeysize != QE_FLTR_LARGEST_EXTERNAL_TABLE_LOOKUP_KEY_SIZE_16_BYTES)) { - ugeth_err("%s: Invalid largest External Lookup Key Size.", - __FUNCTION__); + if (netif_msg_ifup(ugeth)) + ugeth_err("%s: Invalid largest External Lookup Key Size.", + __FUNCTION__); ucc_geth_memclean(ugeth); return -EINVAL; } @@ -3222,8 +3271,9 @@ static int ucc_geth_startup(struct ucc_g /* Rx needs one extra for terminator */ , size, UCC_GETH_THREAD_RX_PRAM_ALIGNMENT, ug_info->riscRx, 1)) != 0) { - ugeth_err("%s: Can not fill p_init_enet_param_shadow.", - __FUNCTION__); + if (netif_msg_ifup(ugeth)) + ugeth_err("%s: Can not fill p_init_enet_param_shadow.", + __FUNCTION__); ucc_geth_memclean(ugeth); return ret_val; } @@ -3237,8 +3287,9 @@ static int ucc_geth_startup(struct ucc_g sizeof(struct ucc_geth_thread_tx_pram), UCC_GETH_THREAD_TX_PRAM_ALIGNMENT, ug_info->riscTx, 0)) != 0) { - ugeth_err("%s: Can not fill p_init_enet_param_shadow.", - __FUNCTION__); + if (netif_msg_ifup(ugeth)) + ugeth_err("%s: Can not fill p_init_enet_param_shadow.", + __FUNCTION__); ucc_geth_memclean(ugeth); return ret_val; } @@ -3246,8 +3297,9 @@ static int ucc_geth_startup(struct ucc_g /* Load Rx bds with buffers */ for (i = 0; i < ug_info->numQueuesRx; i++) { if ((ret_val = rx_bd_buffer_set(ugeth, (u8) i)) != 0) { - ugeth_err("%s: Can not fill Rx bds with buffers.", - __FUNCTION__); + if (netif_msg_ifup(ugeth)) + ugeth_err("%s: Can not fill Rx bds with buffers.", + __FUNCTION__); ucc_geth_memclean(ugeth); return ret_val; } @@ -3256,9 +3308,10 @@ static int ucc_geth_startup(struct ucc_g /* Allocate InitEnet command parameter structure */ init_enet_pram_offset = qe_muram_alloc(sizeof(struct ucc_geth_init_pram), 4); if (IS_ERR_VALUE(init_enet_pram_offset)) { - ugeth_err - ("%s: Can not allocate DPRAM memory for p_init_enet_pram.", - __FUNCTION__); + if (netif_msg_ifup(ugeth)) + ugeth_err + ("%s: Can not allocate DPRAM memory for p_init_enet_pram.", + __FUNCTION__); ucc_geth_memclean(ugeth); return -ENOMEM; } @@ -3428,8 +3481,9 @@ static int ucc_geth_rx(struct ucc_geth_p if (!skb || (!(bd_status & (R_F | R_L))) || (bd_status & R_ERRORS_FATAL)) { - ugeth_vdbg("%s, %d: ERROR!!! skb - 0x%08x", - __FUNCTION__, __LINE__, (u32) skb); + if (netif_msg_rx_err(ugeth)) + ugeth_err("%s, %d: ERROR!!! skb - 0x%08x", + __FUNCTION__, __LINE__, (u32) skb); if (skb) dev_kfree_skb_any(skb); @@ -3458,7 +3512,8 @@ static int ucc_geth_rx(struct ucc_geth_p skb = get_new_skb(ugeth, bd); if (!skb) { - ugeth_warn("%s: No Rx Data Buffer", __FUNCTION__); + if (netif_msg_rx_err(ugeth)) + ugeth_warn("%s: No Rx Data Buffer", __FUNCTION__); ugeth->stats.rx_dropped++; break; } @@ -3649,28 +3704,32 @@ static int ucc_geth_open(struct net_devi /* Test station address */ if (dev->dev_addr[0] & ENET_GROUP_ADDR) { - ugeth_err("%s: Multicast address used for station address" - " - is this what you wanted?", __FUNCTION__); + if (netif_msg_ifup(ugeth)) + ugeth_err("%s: Multicast address used for station address" + " - is this what you wanted?", __FUNCTION__); return -EINVAL; } err = ucc_struct_init(ugeth); if (err) { - ugeth_err("%s: Cannot configure internal struct, aborting.", dev->name); + if (netif_msg_ifup(ugeth)) + ugeth_err("%s: Cannot configure internal struct, aborting.", dev->name); return err; } err = ucc_geth_startup(ugeth); if (err) { - ugeth_err("%s: Cannot configure net device, aborting.", - dev->name); + if (netif_msg_ifup(ugeth)) + ugeth_err("%s: Cannot configure net device, aborting.", + dev->name); return err; } err = adjust_enet_interface(ugeth); if (err) { - ugeth_err("%s: Cannot configure net device, aborting.", - dev->name); + if (netif_msg_ifup(ugeth)) + ugeth_err("%s: Cannot configure net device, aborting.", + dev->name); return err; } @@ -3687,7 +3746,8 @@ static int ucc_geth_open(struct net_devi err = init_phy(dev); if (err) { - ugeth_err("%s: Cannot initialize PHY, aborting.", dev->name); + if (netif_msg_ifup(ugeth)) + ugeth_err("%s: Cannot initialize PHY, aborting.", dev->name); return err; } @@ -3697,15 +3757,17 @@ static int ucc_geth_open(struct net_devi request_irq(ugeth->ug_info->uf_info.irq, ucc_geth_irq_handler, 0, "UCC Geth", dev); if (err) { - ugeth_err("%s: Cannot get IRQ for net device, aborting.", - dev->name); + if (netif_msg_ifup(ugeth)) + ugeth_err("%s: Cannot get IRQ for net device, aborting.", + dev->name); ucc_geth_stop(ugeth); return err; } err = ugeth_enable(ugeth, COMM_DIR_RX_AND_TX); if (err) { - ugeth_err("%s: Cannot enable net device, aborting.", dev->name); + if (netif_msg_ifup(ugeth)) + ugeth_err("%s: Cannot enable net device, aborting.", dev->name); ucc_geth_stop(ugeth); return err; } @@ -3732,8 +3794,6 @@ static int ucc_geth_close(struct net_dev return 0; } -const struct ethtool_ops ucc_geth_ethtool_ops = { }; - static phy_interface_t to_phy_interface(const char *phy_connection_type) { if (strcasecmp(phy_connection_type, "mii") == 0) @@ -3790,6 +3850,13 @@ static int ucc_geth_probe(struct of_devi return -ENODEV; ug_info = &ugeth_info[ucc_num]; + if (ug_info == NULL) { + if (netif_msg_probe(&debug)) + ugeth_err("%s: [%d] Missing additional data!", + __FUNCTION__, ucc_num); + return -ENODEV; + } + ug_info->uf_info.ucc_num = ucc_num; prop = of_get_property(np, "rx-clock", NULL); @@ -3868,15 +3935,10 @@ static int ucc_geth_probe(struct of_devi ug_info->mdio_bus = res.start; - printk(KERN_INFO "ucc_geth: UCC%1d at 0x%8x (irq = %d) \n", - ug_info->uf_info.ucc_num + 1, ug_info->uf_info.regs, - ug_info->uf_info.irq); - - if (ug_info == NULL) { - ugeth_err("%s: [%d] Missing additional data!", __FUNCTION__, - ucc_num); - return -ENODEV; - } + if (netif_msg_probe(&debug)) + printk(KERN_INFO "ucc_geth: UCC%1d at 0x%8x (irq = %d) \n", + ug_info->uf_info.ucc_num + 1, ug_info->uf_info.regs, + ug_info->uf_info.irq); /* Create an ethernet device instance */ dev = alloc_etherdev(sizeof(*ugeth)); @@ -3896,6 +3958,7 @@ static int ucc_geth_probe(struct of_devi SET_NETDEV_DEV(dev, device); /* Fill in the dev structure */ + uec_set_ethtool_ops(dev); dev->open = ucc_geth_open; dev->hard_start_xmit = ucc_geth_start_xmit; dev->tx_timeout = ucc_geth_timeout; @@ -3909,16 +3972,16 @@ static int ucc_geth_probe(struct of_devi // dev->change_mtu = ucc_geth_change_mtu; dev->mtu = 1500; dev->set_multicast_list = ucc_geth_set_multi; - dev->ethtool_ops = &ucc_geth_ethtool_ops; - ugeth->msg_enable = (NETIF_MSG_IFUP << 1 ) - 1; + ugeth->msg_enable = netif_msg_init(debug.msg_enable, UGETH_MSG_DEFAULT); ugeth->phy_interface = phy_interface; ugeth->max_speed = max_speed; err = register_netdev(dev); if (err) { - ugeth_err("%s: Cannot register net device, aborting.", - dev->name); + if (netif_msg_probe(ugeth)) + ugeth_err("%s: Cannot register net device, aborting.", + dev->name); free_netdev(dev); return err; } @@ -3972,7 +4035,8 @@ static int __init ucc_geth_init(void) if (ret) return ret; - printk(KERN_INFO "ucc_geth: " DRV_DESC "\n"); + if (netif_msg_drv(&debug)) + printk(KERN_INFO "ucc_geth: " DRV_DESC "\n"); for (i = 0; i < 8; i++) memcpy(&(ugeth_info[i]), &ugeth_primary_info, sizeof(ugeth_primary_info)); Index: linux-rt-rebase.q/drivers/net/ucc_geth.h =================================================================== --- linux-rt-rebase.q.orig/drivers/net/ucc_geth.h +++ linux-rt-rebase.q/drivers/net/ucc_geth.h @@ -30,6 +30,10 @@ #include "ucc_geth_mii.h" +#define DRV_DESC "QE UCC Gigabit Ethernet Controller" +#define DRV_NAME "ucc_geth" +#define DRV_VERSION "1.1" + #define NUM_TX_QUEUES 8 #define NUM_RX_QUEUES 8 #define NUM_BDS_IN_PREFETCHED_BDS 4 @@ -896,6 +900,7 @@ struct ucc_geth_hardware_statistics { #define UCC_GETH_TX_VTAG_TABLE_ENTRY_MAX 8 #define UCC_GETH_RX_BD_RING_SIZE_MIN 8 #define UCC_GETH_TX_BD_RING_SIZE_MIN 2 +#define UCC_GETH_BD_RING_SIZE_MAX 0xffff #define UCC_GETH_SIZE_OF_BD QE_SIZEOF_BD @@ -1135,6 +1140,7 @@ struct ucc_geth_info { int bro; int ecm; int receiveFlowControl; + int transmitFlowControl; u8 maxGroupAddrInHash; u8 maxIndAddrInHash; u8 prel; Index: linux-rt-rebase.q/drivers/net/ucc_geth_ethtool.c =================================================================== --- /dev/null +++ linux-rt-rebase.q/drivers/net/ucc_geth_ethtool.c @@ -0,0 +1,388 @@ +/* + * Copyright (c) 2007 Freescale Semiconductor, Inc. All rights reserved. + * + * Description: QE UCC Gigabit Ethernet Ethtool API Set + * + * Author: Li Yang + * + * Limitation: + * Can only get/set setttings of the first queue. + * Need to re-open the interface manually after changing some paramters. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include + +#include "ucc_geth.h" +#include "ucc_geth_mii.h" + +static char hw_stat_gstrings[][ETH_GSTRING_LEN] = { + "tx-64-frames", + "tx-65-127-frames", + "tx-128-255-frames", + "rx-64-frames", + "rx-65-127-frames", + "rx-128-255-frames", + "tx-bytes-ok", + "tx-pause-frames", + "tx-multicast-frames", + "tx-broadcast-frames", + "rx-frames", + "rx-bytes-ok", + "rx-bytes-all", + "rx-multicast-frames", + "rx-broadcast-frames", + "stats-counter-carry", + "stats-counter-mask", + "rx-dropped-frames", +}; + +static char tx_fw_stat_gstrings[][ETH_GSTRING_LEN] = { + "tx-single-collision", + "tx-multiple-collision", + "tx-late-collsion", + "tx-aborted-frames", + "tx-lost-frames", + "tx-carrier-sense-errors", + "tx-frames-ok", + "tx-excessive-differ-frames", + "tx-256-511-frames", + "tx-1024-1518-frames", + "tx-jumbo-frames", +}; + +static char rx_fw_stat_gstrings[][ETH_GSTRING_LEN] = { + "rx-crc-errors", + "rx-alignment-errors", + "rx-in-range-length-errors", + "rx-out-of-range-length-errors", + "rx-too-long-frames", + "rx-runt", + "rx-very-long-event", + "rx-symbol-errors", + "rx-busy-drop-frames", + "reserved", + "reserved", + "rx-mismatch-drop-frames", + "rx-small-than-64", + "rx-256-511-frames", + "rx-512-1023-frames", + "rx-1024-1518-frames", + "rx-jumbo-frames", + "rx-mac-error-loss", + "rx-pause-frames", + "reserved", + "rx-vlan-removed", + "rx-vlan-replaced", + "rx-vlan-inserted", + "rx-ip-checksum-errors", +}; + +#define UEC_HW_STATS_LEN ARRAY_SIZE(hw_stat_gstrings) +#define UEC_TX_FW_STATS_LEN ARRAY_SIZE(tx_fw_stat_gstrings) +#define UEC_RX_FW_STATS_LEN ARRAY_SIZE(rx_fw_stat_gstrings) + +extern int init_flow_control_params(u32 automatic_flow_control_mode, + int rx_flow_control_enable, + int tx_flow_control_enable, u16 pause_period, + u16 extension_field, volatile u32 *upsmr_register, + volatile u32 *uempr_register, volatile u32 *maccfg1_register); + +static int +uec_get_settings(struct net_device *netdev, struct ethtool_cmd *ecmd) +{ + struct ucc_geth_private *ugeth = netdev_priv(netdev); + struct phy_device *phydev = ugeth->phydev; + struct ucc_geth_info *ug_info = ugeth->ug_info; + + if (!phydev) + return -ENODEV; + + ecmd->maxtxpkt = 1; + ecmd->maxrxpkt = ug_info->interruptcoalescingmaxvalue[0]; + + return phy_ethtool_gset(phydev, ecmd); +} + +static int +uec_set_settings(struct net_device *netdev, struct ethtool_cmd *ecmd) +{ + struct ucc_geth_private *ugeth = netdev_priv(netdev); + struct phy_device *phydev = ugeth->phydev; + + if (!phydev) + return -ENODEV; + + return phy_ethtool_sset(phydev, ecmd); +} + +static void +uec_get_pauseparam(struct net_device *netdev, + struct ethtool_pauseparam *pause) +{ + struct ucc_geth_private *ugeth = netdev_priv(netdev); + + pause->autoneg = ugeth->phydev->autoneg; + + if (ugeth->ug_info->receiveFlowControl) + pause->rx_pause = 1; + if (ugeth->ug_info->transmitFlowControl) + pause->tx_pause = 1; +} + +static int +uec_set_pauseparam(struct net_device *netdev, + struct ethtool_pauseparam *pause) +{ + struct ucc_geth_private *ugeth = netdev_priv(netdev); + int ret = 0; + + ugeth->ug_info->receiveFlowControl = pause->rx_pause; + ugeth->ug_info->transmitFlowControl = pause->tx_pause; + + if (ugeth->phydev->autoneg) { + if (netif_running(netdev)) { + /* FIXME: automatically restart */ + printk(KERN_INFO + "Please re-open the interface.\n"); + } + } else { + struct ucc_geth_info *ug_info = ugeth->ug_info; + + ret = init_flow_control_params(ug_info->aufc, + ug_info->receiveFlowControl, + ug_info->transmitFlowControl, + ug_info->pausePeriod, + ug_info->extensionField, + &ugeth->uccf->uf_regs->upsmr, + &ugeth->ug_regs->uempr, + &ugeth->ug_regs->maccfg1); + } + + return ret; +} + +static uint32_t +uec_get_msglevel(struct net_device *netdev) +{ + struct ucc_geth_private *ugeth = netdev_priv(netdev); + return ugeth->msg_enable; +} + +static void +uec_set_msglevel(struct net_device *netdev, uint32_t data) +{ + struct ucc_geth_private *ugeth = netdev_priv(netdev); + ugeth->msg_enable = data; +} + +static int +uec_get_regs_len(struct net_device *netdev) +{ + return sizeof(struct ucc_geth); +} + +static void +uec_get_regs(struct net_device *netdev, + struct ethtool_regs *regs, void *p) +{ + int i; + struct ucc_geth_private *ugeth = netdev_priv(netdev); + u32 __iomem *ug_regs = (u32 __iomem *)ugeth->ug_regs; + u32 *buff = p; + + for (i = 0; i < sizeof(struct ucc_geth) / sizeof(u32); i++) + buff[i] = in_be32(&ug_regs[i]); +} + +static void +uec_get_ringparam(struct net_device *netdev, + struct ethtool_ringparam *ring) +{ + struct ucc_geth_private *ugeth = netdev_priv(netdev); + struct ucc_geth_info *ug_info = ugeth->ug_info; + int queue = 0; + + ring->rx_max_pending = UCC_GETH_BD_RING_SIZE_MAX; + ring->rx_mini_max_pending = UCC_GETH_BD_RING_SIZE_MAX; + ring->rx_jumbo_max_pending = UCC_GETH_BD_RING_SIZE_MAX; + ring->tx_max_pending = UCC_GETH_BD_RING_SIZE_MAX; + + ring->rx_pending = ug_info->bdRingLenRx[queue]; + ring->rx_mini_pending = ug_info->bdRingLenRx[queue]; + ring->rx_jumbo_pending = ug_info->bdRingLenRx[queue]; + ring->tx_pending = ug_info->bdRingLenTx[queue]; +} + +static int +uec_set_ringparam(struct net_device *netdev, + struct ethtool_ringparam *ring) +{ + struct ucc_geth_private *ugeth = netdev_priv(netdev); + struct ucc_geth_info *ug_info = ugeth->ug_info; + int queue = 0, ret = 0; + + if (ring->rx_pending < UCC_GETH_RX_BD_RING_SIZE_MIN) { + printk("%s: RxBD ring size must be no smaller than %d.\n", + netdev->name, UCC_GETH_RX_BD_RING_SIZE_MIN); + return -EINVAL; + } + if (ring->rx_pending % UCC_GETH_RX_BD_RING_SIZE_ALIGNMENT) { + printk("%s: RxBD ring size must be multiple of %d.\n", + netdev->name, UCC_GETH_RX_BD_RING_SIZE_ALIGNMENT); + return -EINVAL; + } + if (ring->tx_pending < UCC_GETH_TX_BD_RING_SIZE_MIN) { + printk("%s: TxBD ring size must be no smaller than %d.\n", + netdev->name, UCC_GETH_TX_BD_RING_SIZE_MIN); + return -EINVAL; + } + + ug_info->bdRingLenRx[queue] = ring->rx_pending; + ug_info->bdRingLenTx[queue] = ring->tx_pending; + + if (netif_running(netdev)) { + /* FIXME: restart automatically */ + printk(KERN_INFO + "Please re-open the interface.\n"); + } + + return ret; +} + +static int uec_get_stats_count(struct net_device *netdev) +{ + struct ucc_geth_private *ugeth = netdev_priv(netdev); + u32 stats_mode = ugeth->ug_info->statisticsMode; + int len = 0; + + if (stats_mode & UCC_GETH_STATISTICS_GATHERING_MODE_HARDWARE) + len += UEC_HW_STATS_LEN; + if (stats_mode & UCC_GETH_STATISTICS_GATHERING_MODE_FIRMWARE_TX) + len += UEC_TX_FW_STATS_LEN; + if (stats_mode & UCC_GETH_STATISTICS_GATHERING_MODE_FIRMWARE_RX) + len += UEC_RX_FW_STATS_LEN; + + return len; +} + +static void uec_get_strings(struct net_device *netdev, u32 stringset, u8 *buf) +{ + struct ucc_geth_private *ugeth = netdev_priv(netdev); + u32 stats_mode = ugeth->ug_info->statisticsMode; + + if (stats_mode & UCC_GETH_STATISTICS_GATHERING_MODE_HARDWARE) { + memcpy(buf, hw_stat_gstrings, UEC_HW_STATS_LEN * + ETH_GSTRING_LEN); + buf += UEC_HW_STATS_LEN * ETH_GSTRING_LEN; + } + if (stats_mode & UCC_GETH_STATISTICS_GATHERING_MODE_FIRMWARE_TX) { + memcpy(buf, tx_fw_stat_gstrings, UEC_TX_FW_STATS_LEN * + ETH_GSTRING_LEN); + buf += UEC_TX_FW_STATS_LEN * ETH_GSTRING_LEN; + } + if (stats_mode & UCC_GETH_STATISTICS_GATHERING_MODE_FIRMWARE_RX) + memcpy(buf, tx_fw_stat_gstrings, UEC_RX_FW_STATS_LEN * + ETH_GSTRING_LEN); +} + +static void uec_get_ethtool_stats(struct net_device *netdev, + struct ethtool_stats *stats, uint64_t *data) +{ + struct ucc_geth_private *ugeth = netdev_priv(netdev); + u32 stats_mode = ugeth->ug_info->statisticsMode; + u32 __iomem *base; + int i, j = 0; + + if (stats_mode & UCC_GETH_STATISTICS_GATHERING_MODE_HARDWARE) { + base = (u32 __iomem *)&ugeth->ug_regs->tx64; + for (i = 0; i < UEC_HW_STATS_LEN; i++) + data[j++] = (u64)in_be32(&base[i]); + } + if (stats_mode & UCC_GETH_STATISTICS_GATHERING_MODE_FIRMWARE_TX) { + base = (u32 __iomem *)ugeth->p_tx_fw_statistics_pram; + for (i = 0; i < UEC_TX_FW_STATS_LEN; i++) + data[j++] = (u64)in_be32(&base[i]); + } + if (stats_mode & UCC_GETH_STATISTICS_GATHERING_MODE_FIRMWARE_RX) { + base = (u32 __iomem *)ugeth->p_rx_fw_statistics_pram; + for (i = 0; i < UEC_RX_FW_STATS_LEN; i++) + data[j++] = (u64)in_be32(&base[i]); + } +} + +static int uec_nway_reset(struct net_device *netdev) +{ + struct ucc_geth_private *ugeth = netdev_priv(netdev); + + return phy_start_aneg(ugeth->phydev); +} + +/* Report driver information */ +static void +uec_get_drvinfo(struct net_device *netdev, + struct ethtool_drvinfo *drvinfo) +{ + strncpy(drvinfo->driver, DRV_NAME, 32); + strncpy(drvinfo->version, DRV_VERSION, 32); + strncpy(drvinfo->fw_version, "N/A", 32); + strncpy(drvinfo->bus_info, "QUICC ENGINE", 32); + drvinfo->n_stats = uec_get_stats_count(netdev); + drvinfo->testinfo_len = 0; + drvinfo->eedump_len = 0; + drvinfo->regdump_len = uec_get_regs_len(netdev); +} + +static const struct ethtool_ops uec_ethtool_ops = { + .get_settings = uec_get_settings, + .set_settings = uec_set_settings, + .get_drvinfo = uec_get_drvinfo, + .get_regs_len = uec_get_regs_len, + .get_regs = uec_get_regs, + .get_msglevel = uec_get_msglevel, + .set_msglevel = uec_set_msglevel, + .nway_reset = uec_nway_reset, + .get_link = ethtool_op_get_link, + .get_ringparam = uec_get_ringparam, + .set_ringparam = uec_set_ringparam, + .get_pauseparam = uec_get_pauseparam, + .set_pauseparam = uec_set_pauseparam, + .get_sg = ethtool_op_get_sg, + .set_sg = ethtool_op_set_sg, + .get_tso = ethtool_op_get_tso, + .get_stats_count = uec_get_stats_count, + .get_strings = uec_get_strings, + .get_ethtool_stats = uec_get_ethtool_stats, + .get_perm_addr = ethtool_op_get_perm_addr, +}; + +void uec_set_ethtool_ops(struct net_device *netdev) +{ + SET_ETHTOOL_OPS(netdev, &uec_ethtool_ops); +} Index: linux-rt-rebase.q/drivers/net/ucc_geth_mii.c =================================================================== --- linux-rt-rebase.q.orig/drivers/net/ucc_geth_mii.c +++ linux-rt-rebase.q/drivers/net/ucc_geth_mii.c @@ -54,8 +54,8 @@ #define vdbg(format, arg...) do {} while(0) #endif -#define DRV_DESC "QE UCC Ethernet Controller MII Bus" -#define DRV_NAME "fsl-uec_mdio" +#define MII_DRV_DESC "QE UCC Ethernet Controller MII Bus" +#define MII_DRV_NAME "fsl-uec_mdio" /* Write value to the PHY for this device to the register at regnum, */ /* waiting until the write is done before it returns. All PHY */ @@ -261,7 +261,7 @@ static struct of_device_id uec_mdio_matc }; static struct of_platform_driver uec_mdio_driver = { - .name = DRV_NAME, + .name = MII_DRV_NAME, .probe = uec_mdio_probe, .remove = uec_mdio_remove, .match_table = uec_mdio_match, Index: linux-rt-rebase.q/drivers/net/usb/usbnet.c =================================================================== --- linux-rt-rebase.q.orig/drivers/net/usb/usbnet.c +++ linux-rt-rebase.q/drivers/net/usb/usbnet.c @@ -898,6 +898,8 @@ static void tx_complete (struct urb *urb urb->dev = NULL; entry->state = tx_done; + spin_lock_rt(&dev->txq.lock); + spin_unlock_rt(&dev->txq.lock); defer_bh(dev, skb, &dev->txq); } Index: linux-rt-rebase.q/drivers/oprofile/oprofilefs.c =================================================================== --- linux-rt-rebase.q.orig/drivers/oprofile/oprofilefs.c +++ linux-rt-rebase.q/drivers/oprofile/oprofilefs.c @@ -21,7 +21,7 @@ #define OPROFILEFS_MAGIC 0x6f70726f -DEFINE_SPINLOCK(oprofilefs_lock); +DEFINE_RAW_SPINLOCK(oprofilefs_lock); static struct inode * oprofilefs_get_inode(struct super_block * sb, int mode) { Index: linux-rt-rebase.q/drivers/pci/access.c =================================================================== --- linux-rt-rebase.q.orig/drivers/pci/access.c +++ linux-rt-rebase.q/drivers/pci/access.c @@ -11,7 +11,7 @@ * configuration space. */ -static DEFINE_SPINLOCK(pci_lock); +static DEFINE_RAW_SPINLOCK(pci_lock); /* * Wrappers for all PCI configuration access functions. They just check Index: linux-rt-rebase.q/drivers/pci/hotplug/cpqphp_ctrl.c =================================================================== --- linux-rt-rebase.q.orig/drivers/pci/hotplug/cpqphp_ctrl.c +++ linux-rt-rebase.q/drivers/pci/hotplug/cpqphp_ctrl.c @@ -45,8 +45,8 @@ static int configure_new_function(struct u8 behind_bridge, struct resource_lists *resources); static void interrupt_event_handler(struct controller *ctrl); -static struct semaphore event_semaphore; /* mutex for process loop (up if something to process) */ -static struct semaphore event_exit; /* guard ensure thread has exited before calling it quits */ +static struct compat_semaphore event_semaphore; /* mutex for process loop (up if something to process) */ +static struct compat_semaphore event_exit; /* guard ensure thread has exited before calling it quits */ static int event_finished; static unsigned long pushbutton_pending; /* = 0 */ @@ -1746,10 +1746,8 @@ static void pushbutton_helper_thread(uns static int event_thread(void* data) { struct controller *ctrl; - lock_kernel(); + daemonize("phpd_event"); - - unlock_kernel(); while (1) { dbg("!!!!event_thread sleeping\n"); Index: linux-rt-rebase.q/drivers/pci/hotplug/ibmphp_hpc.c =================================================================== --- linux-rt-rebase.q.orig/drivers/pci/hotplug/ibmphp_hpc.c +++ linux-rt-rebase.q/drivers/pci/hotplug/ibmphp_hpc.c @@ -106,7 +106,7 @@ static int tid_poll; static struct mutex sem_hpcaccess; // lock access to HPC static struct semaphore semOperations; // lock all operations and // access to data structures -static struct semaphore sem_exit; // make sure polling thread goes away +static struct compat_semaphore sem_exit; // make sure polling thread goes away //---------------------------------------------------------------------------- // local function prototypes //---------------------------------------------------------------------------- Index: linux-rt-rebase.q/drivers/pci/msi.c =================================================================== --- linux-rt-rebase.q.orig/drivers/pci/msi.c +++ linux-rt-rebase.q/drivers/pci/msi.c @@ -235,6 +235,10 @@ static void __pci_restore_msi_state(stru return; entry = get_irq_msi(dev->irq); + if (!entry) { + WARN_ON(1); + return; + } pos = entry->msi_attrib.pos; pci_intx(dev, 0); /* disable intx */ Index: linux-rt-rebase.q/drivers/pci/pci-acpi.c =================================================================== --- linux-rt-rebase.q.orig/drivers/pci/pci-acpi.c +++ linux-rt-rebase.q/drivers/pci/pci-acpi.c @@ -245,16 +245,33 @@ EXPORT_SYMBOL(pci_osc_control_set); * currently we simply return _SxD, if present. */ -static int acpi_pci_choose_state(struct pci_dev *pdev, pm_message_t state) +static pci_power_t acpi_pci_choose_state(struct pci_dev *pdev, + pm_message_t state) { - /* TBD */ + int acpi_state; - return -ENODEV; + acpi_state = acpi_pm_device_sleep_state(&pdev->dev, + device_may_wakeup(&pdev->dev), NULL); + if (acpi_state < 0) + return PCI_POWER_ERROR; + + switch (acpi_state) { + case ACPI_STATE_D0: + return PCI_D0; + case ACPI_STATE_D1: + return PCI_D1; + case ACPI_STATE_D2: + return PCI_D2; + case ACPI_STATE_D3: + return PCI_D3hot; + } + return PCI_POWER_ERROR; } static int acpi_pci_set_power_state(struct pci_dev *dev, pci_power_t state) { acpi_handle handle = DEVICE_ACPI_HANDLE(&dev->dev); + acpi_handle tmp; static int state_conv[] = { [0] = 0, [1] = 1, @@ -266,6 +283,9 @@ static int acpi_pci_set_power_state(stru if (!handle) return -ENODEV; + /* If the ACPI device has _EJ0, ignore the device */ + if (ACPI_SUCCESS(acpi_get_handle(handle, "_EJ0", &tmp))) + return 0; return acpi_bus_set_power(handle, acpi_state); } Index: linux-rt-rebase.q/drivers/pci/pci.c =================================================================== --- linux-rt-rebase.q.orig/drivers/pci/pci.c +++ linux-rt-rebase.q/drivers/pci/pci.c @@ -499,7 +499,7 @@ pci_set_power_state(struct pci_dev *dev, return 0; } -int (*platform_pci_choose_state)(struct pci_dev *dev, pm_message_t state); +pci_power_t (*platform_pci_choose_state)(struct pci_dev *dev, pm_message_t state); /** * pci_choose_state - Choose the power state of a PCI device @@ -513,15 +513,15 @@ int (*platform_pci_choose_state)(struct pci_power_t pci_choose_state(struct pci_dev *dev, pm_message_t state) { - int ret; + pci_power_t ret; if (!pci_find_capability(dev, PCI_CAP_ID_PM)) return PCI_D0; if (platform_pci_choose_state) { ret = platform_pci_choose_state(dev, state); - if (ret >= 0) - state.event = ret; + if (ret != PCI_POWER_ERROR) + return ret; } switch (state.event) { @@ -1604,6 +1604,7 @@ early_param("pci", pci_setup); device_initcall(pci_init); EXPORT_SYMBOL_GPL(pci_restore_bars); +EXPORT_SYMBOL(__pci_reenable_device); EXPORT_SYMBOL(pci_enable_device_bars); EXPORT_SYMBOL(pci_enable_device); EXPORT_SYMBOL(pcim_enable_device); Index: linux-rt-rebase.q/drivers/pci/pci.h =================================================================== --- linux-rt-rebase.q.orig/drivers/pci/pci.h +++ linux-rt-rebase.q/drivers/pci/pci.h @@ -1,6 +1,5 @@ /* Functions internal to the PCI core code */ -extern int __must_check __pci_reenable_device(struct pci_dev *); extern int pci_uevent(struct device *dev, char **envp, int num_envp, char *buffer, int buffer_size); extern int pci_create_sysfs_dev_files(struct pci_dev *pdev); @@ -13,7 +12,7 @@ extern int pci_bus_alloc_resource(struct resource_size_t, resource_size_t), void *alignf_data); /* Firmware callbacks */ -extern int (*platform_pci_choose_state)(struct pci_dev *dev, pm_message_t state); +extern pci_power_t (*platform_pci_choose_state)(struct pci_dev *dev, pm_message_t state); extern int (*platform_pci_set_power_state)(struct pci_dev *dev, pci_power_t state); extern int pci_user_read_config_byte(struct pci_dev *dev, int where, u8 *val); Index: linux-rt-rebase.q/drivers/pnp/driver.c =================================================================== --- linux-rt-rebase.q.orig/drivers/pnp/driver.c +++ linux-rt-rebase.q/drivers/pnp/driver.c @@ -167,6 +167,8 @@ static int pnp_bus_suspend(struct device return error; } + if (pnp_dev->protocol && pnp_dev->protocol->suspend) + pnp_dev->protocol->suspend(pnp_dev, state); return 0; } @@ -179,6 +181,9 @@ static int pnp_bus_resume(struct device if (!pnp_drv) return 0; + if (pnp_dev->protocol && pnp_dev->protocol->resume) + pnp_dev->protocol->resume(pnp_dev); + if (!(pnp_drv->flags & PNP_DRIVER_RES_DO_NOT_CHANGE)) { error = pnp_start_dev(pnp_dev); if (error) Index: linux-rt-rebase.q/drivers/pnp/pnpacpi/core.c =================================================================== --- linux-rt-rebase.q.orig/drivers/pnp/pnpacpi/core.c +++ linux-rt-rebase.q/drivers/pnp/pnpacpi/core.c @@ -21,7 +21,10 @@ #include #include +#include #include +#include + #include "pnpacpi.h" static int num = 0; @@ -33,15 +36,17 @@ static int num = 0; * have irqs (PIC, Timer) because we call acpi_register_gsi. * Finaly only devices that have a CRS method need to be in this list. */ -static char __initdata excluded_id_list[] = - "PNP0C09," /* EC */ - "PNP0C0F," /* Link device */ - "PNP0000," /* PIC */ - "PNP0100," /* Timer */ - ; +static __initdata struct acpi_device_id excluded_id_list[] ={ + {"PNP0C09", 0}, /* EC */ + {"PNP0C0F", 0}, /* Link device */ + {"PNP0000", 0}, /* PIC */ + {"PNP0100", 0}, /* Timer */ + {"", 0}, +}; + static inline int is_exclusive_device(struct acpi_device *dev) { - return (!acpi_match_ids(dev, excluded_id_list)); + return (!acpi_match_device_ids(dev, excluded_id_list)); } /* @@ -119,11 +124,25 @@ static int pnpacpi_disable_resources(str return ACPI_FAILURE(status) ? -ENODEV : 0; } +static int pnpacpi_suspend(struct pnp_dev *dev, pm_message_t state) +{ + return acpi_bus_set_power((acpi_handle)dev->data, + acpi_pm_device_sleep_state(&dev->dev, + device_may_wakeup(&dev->dev), NULL)); +} + +static int pnpacpi_resume(struct pnp_dev *dev) +{ + return acpi_bus_set_power((acpi_handle)dev->data, ACPI_STATE_D0); +} + static struct pnp_protocol pnpacpi_protocol = { .name = "Plug and Play ACPI", .get = pnpacpi_get_resources, .set = pnpacpi_set_resources, .disable = pnpacpi_disable_resources, + .suspend = pnpacpi_suspend, + .resume = pnpacpi_resume, }; static int __init pnpacpi_add_device(struct acpi_device *device) Index: linux-rt-rebase.q/drivers/rtc/class.c =================================================================== --- linux-rt-rebase.q.orig/drivers/rtc/class.c +++ linux-rt-rebase.q/drivers/rtc/class.c @@ -46,6 +46,7 @@ static int rtc_suspend(struct device *de { struct rtc_device *rtc = to_rtc_device(dev); struct rtc_time tm; + struct timespec ts = current_kernel_time(); if (strncmp(rtc->dev.bus_id, CONFIG_RTC_HCTOSYS_DEVICE, @@ -57,8 +58,8 @@ static int rtc_suspend(struct device *de /* RTC precision is 1 second; adjust delta for avg 1/2 sec err */ set_normalized_timespec(&delta, - xtime.tv_sec - oldtime, - xtime.tv_nsec - (NSEC_PER_SEC >> 1)); + ts.tv_sec - oldtime, + ts.tv_nsec - (NSEC_PER_SEC >> 1)); return 0; } Index: linux-rt-rebase.q/drivers/s390/block/dasd.c =================================================================== --- linux-rt-rebase.q.orig/drivers/s390/block/dasd.c +++ linux-rt-rebase.q/drivers/s390/block/dasd.c @@ -1187,7 +1187,7 @@ dasd_end_request_cb(struct dasd_ccw_req static void __dasd_process_blk_queue(struct dasd_device * device) { - request_queue_t *queue; + struct request_queue *queue; struct request *req; struct dasd_ccw_req *cqr; int nr_queued; @@ -1740,7 +1740,7 @@ dasd_cancel_req(struct dasd_ccw_req *cqr * Dasd request queue function. Called from ll_rw_blk.c */ static void -do_dasd_request(request_queue_t * queue) +do_dasd_request(struct request_queue * queue) { struct dasd_device *device; Index: linux-rt-rebase.q/drivers/s390/block/dasd_int.h =================================================================== --- linux-rt-rebase.q.orig/drivers/s390/block/dasd_int.h +++ linux-rt-rebase.q/drivers/s390/block/dasd_int.h @@ -293,7 +293,7 @@ struct dasd_uid { struct dasd_device { /* Block device stuff. */ struct gendisk *gdp; - request_queue_t *request_queue; + struct request_queue *request_queue; spinlock_t request_queue_lock; struct block_device *bdev; unsigned int devindex; Index: linux-rt-rebase.q/drivers/s390/block/dcssblk.c =================================================================== --- linux-rt-rebase.q.orig/drivers/s390/block/dcssblk.c +++ linux-rt-rebase.q/drivers/s390/block/dcssblk.c @@ -621,7 +621,7 @@ out: } static int -dcssblk_make_request(request_queue_t *q, struct bio *bio) +dcssblk_make_request(struct request_queue *q, struct bio *bio) { struct dcssblk_dev_info *dev_info; struct bio_vec *bvec; Index: linux-rt-rebase.q/drivers/s390/block/xpram.c =================================================================== --- linux-rt-rebase.q.orig/drivers/s390/block/xpram.c +++ linux-rt-rebase.q/drivers/s390/block/xpram.c @@ -191,7 +191,7 @@ static unsigned long __init xpram_highes /* * Block device make request function. */ -static int xpram_make_request(request_queue_t *q, struct bio *bio) +static int xpram_make_request(struct request_queue *q, struct bio *bio) { xpram_device_t *xdev = bio->bi_bdev->bd_disk->private_data; struct bio_vec *bvec; Index: linux-rt-rebase.q/drivers/s390/char/tape.h =================================================================== --- linux-rt-rebase.q.orig/drivers/s390/char/tape.h +++ linux-rt-rebase.q/drivers/s390/char/tape.h @@ -188,7 +188,7 @@ struct tape_blk_data { struct tape_device * device; /* Block device request queue. */ - request_queue_t * request_queue; + struct request_queue * request_queue; spinlock_t request_queue_lock; /* Task to move entries from block request to CCS request queue. */ Index: linux-rt-rebase.q/drivers/s390/char/tape_block.c =================================================================== --- linux-rt-rebase.q.orig/drivers/s390/char/tape_block.c +++ linux-rt-rebase.q/drivers/s390/char/tape_block.c @@ -147,7 +147,7 @@ static void tapeblock_requeue(struct work_struct *work) { struct tape_blk_data * blkdat; struct tape_device * device; - request_queue_t * queue; + struct request_queue * queue; int nr_queued; struct request * req; struct list_head * l; @@ -194,7 +194,7 @@ tapeblock_requeue(struct work_struct *wo * Tape request queue function. Called from ll_rw_blk.c */ static void -tapeblock_request_fn(request_queue_t *queue) +tapeblock_request_fn(struct request_queue *queue) { struct tape_device *device; Index: linux-rt-rebase.q/drivers/s390/net/ctcmain.c =================================================================== --- linux-rt-rebase.q.orig/drivers/s390/net/ctcmain.c +++ linux-rt-rebase.q/drivers/s390/net/ctcmain.c @@ -674,7 +674,7 @@ ch_action_txdone(fsm_instance * fi, int int first = 1; int i; unsigned long duration; - struct timespec done_stamp = xtime; + struct timespec done_stamp = current_kernel_time(); DBF_TEXT(trace, 4, __FUNCTION__); @@ -730,7 +730,7 @@ ch_action_txdone(fsm_instance * fi, int spin_unlock(&ch->collect_lock); ch->ccw[1].count = ch->trans_skb->len; fsm_addtimer(&ch->timer, CTC_TIMEOUT_5SEC, CH_EVENT_TIMER, ch); - ch->prof.send_stamp = xtime; + ch->prof.send_stamp = current_kernel_time(); rc = ccw_device_start(ch->cdev, &ch->ccw[0], (unsigned long) ch, 0xff, 0); ch->prof.doios_multi++; @@ -2281,7 +2281,7 @@ transmit_skb(struct channel *ch, struct fsm_newstate(ch->fsm, CH_STATE_TX); fsm_addtimer(&ch->timer, CTC_TIMEOUT_5SEC, CH_EVENT_TIMER, ch); spin_lock_irqsave(get_ccwdev_lock(ch->cdev), saveflags); - ch->prof.send_stamp = xtime; + ch->prof.send_stamp = current_kernel_time(); rc = ccw_device_start(ch->cdev, &ch->ccw[ccw_idx], (unsigned long) ch, 0xff, 0); spin_unlock_irqrestore(get_ccwdev_lock(ch->cdev), saveflags); Index: linux-rt-rebase.q/drivers/s390/net/netiucv.c =================================================================== --- linux-rt-rebase.q.orig/drivers/s390/net/netiucv.c +++ linux-rt-rebase.q/drivers/s390/net/netiucv.c @@ -753,7 +753,7 @@ static void conn_action_txdone(fsm_insta header.next = 0; memcpy(skb_put(conn->tx_buff, NETIUCV_HDRLEN), &header, NETIUCV_HDRLEN); - conn->prof.send_stamp = xtime; + conn->prof.send_stamp = current_kernel_time(); txmsg.class = 0; txmsg.tag = 0; rc = iucv_message_send(conn->path, &txmsg, 0, 0, @@ -1185,7 +1185,7 @@ static int netiucv_transmit_skb(struct i memcpy(skb_put(nskb, NETIUCV_HDRLEN), &header, NETIUCV_HDRLEN); fsm_newstate(conn->fsm, CONN_STATE_TX); - conn->prof.send_stamp = xtime; + conn->prof.send_stamp = current_kernel_time(); msg.tag = 1; msg.class = 0; Index: linux-rt-rebase.q/drivers/sbus/char/Kconfig =================================================================== --- linux-rt-rebase.q.orig/drivers/sbus/char/Kconfig +++ linux-rt-rebase.q/drivers/sbus/char/Kconfig @@ -15,6 +15,7 @@ config SUN_OPENPROMIO config SUN_MOSTEK_RTC tristate "Mostek real time clock support" + depends on SPARC32 help The Mostek RTC chip is used on all known Sun computers except some JavaStations. For a JavaStation you need to say Y both here Index: linux-rt-rebase.q/drivers/sbus/char/jsflash.c =================================================================== --- linux-rt-rebase.q.orig/drivers/sbus/char/jsflash.c +++ linux-rt-rebase.q/drivers/sbus/char/jsflash.c @@ -185,7 +185,7 @@ static void jsfd_read(char *buf, unsigne } } -static void jsfd_do_request(request_queue_t *q) +static void jsfd_do_request(struct request_queue *q) { struct request *req; Index: linux-rt-rebase.q/drivers/scsi/aacraid/aacraid.h =================================================================== --- linux-rt-rebase.q.orig/drivers/scsi/aacraid/aacraid.h +++ linux-rt-rebase.q/drivers/scsi/aacraid/aacraid.h @@ -715,7 +715,7 @@ struct aac_fib_context { u32 unique; // unique value representing this context ulong jiffies; // used for cleanup - dmb changed to ulong struct list_head next; // used to link context's into a linked list - struct semaphore wait_sem; // this is used to wait for the next fib to arrive. + struct compat_semaphore wait_sem; // this is used to wait for the next fib to arrive. int wait; // Set to true when thread is in WaitForSingleObject unsigned long count; // total number of FIBs on FibList struct list_head fib_list; // this holds fibs and their attachd hw_fibs @@ -785,7 +785,7 @@ struct fib { * This is the event the sendfib routine will wait on if the * caller did not pass one and this is synch io. */ - struct semaphore event_wait; + struct compat_semaphore event_wait; spinlock_t event_lock; u32 done; /* gets set to 1 when fib is complete */ Index: linux-rt-rebase.q/drivers/scsi/aacraid/linit.c =================================================================== --- linux-rt-rebase.q.orig/drivers/scsi/aacraid/linit.c +++ linux-rt-rebase.q/drivers/scsi/aacraid/linit.c @@ -636,6 +636,8 @@ static int aac_cfg_open(struct inode *in static int aac_cfg_ioctl(struct inode *inode, struct file *file, unsigned int cmd, unsigned long arg) { + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; return aac_do_ioctl(file->private_data, cmd, (void __user *)arg); } @@ -689,6 +691,8 @@ static int aac_compat_ioctl(struct scsi_ static long aac_compat_cfg_ioctl(struct file *file, unsigned cmd, unsigned long arg) { + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; return aac_compat_do_ioctl((struct aac_dev *)file->private_data, cmd, arg); } #endif Index: linux-rt-rebase.q/drivers/scsi/qla2xxx/qla_def.h =================================================================== --- linux-rt-rebase.q.orig/drivers/scsi/qla2xxx/qla_def.h +++ linux-rt-rebase.q/drivers/scsi/qla2xxx/qla_def.h @@ -2413,7 +2413,7 @@ typedef struct scsi_qla_host { struct semaphore mbx_cmd_sem; /* Serialialize mbx access */ struct semaphore vport_sem; /* Virtual port synchronization */ - struct semaphore mbx_intr_sem; /* Used for completion notification */ + struct compat_semaphore mbx_intr_sem; /* Used for completion notification */ uint32_t mbx_flags; #define MBX_IN_PROGRESS BIT_0 Index: linux-rt-rebase.q/drivers/scsi/scsi_lib.c =================================================================== --- linux-rt-rebase.q.orig/drivers/scsi/scsi_lib.c +++ linux-rt-rebase.q/drivers/scsi/scsi_lib.c @@ -654,7 +654,7 @@ void scsi_run_host_queues(struct Scsi_Ho static struct scsi_cmnd *scsi_end_request(struct scsi_cmnd *cmd, int uptodate, int bytes, int requeue) { - request_queue_t *q = cmd->device->request_queue; + struct request_queue *q = cmd->device->request_queue; struct request *req = cmd->request; unsigned long flags; @@ -818,7 +818,7 @@ void scsi_io_completion(struct scsi_cmnd { int result = cmd->result; int this_count = cmd->request_bufflen; - request_queue_t *q = cmd->device->request_queue; + struct request_queue *q = cmd->device->request_queue; struct request *req = cmd->request; int clear_errors = 1; struct scsi_sense_hdr sshdr; @@ -1038,7 +1038,7 @@ static int scsi_init_io(struct scsi_cmnd return BLKPREP_KILL; } -static int scsi_issue_flush_fn(request_queue_t *q, struct gendisk *disk, +static int scsi_issue_flush_fn(struct request_queue *q, struct gendisk *disk, sector_t *error_sector) { struct scsi_device *sdev = q->queuedata; @@ -1340,7 +1340,7 @@ static inline int scsi_host_queue_ready( /* * Kill a request for a dead device */ -static void scsi_kill_request(struct request *req, request_queue_t *q) +static void scsi_kill_request(struct request *req, struct request_queue *q) { struct scsi_cmnd *cmd = req->special; struct scsi_device *sdev = cmd->device; @@ -2119,7 +2119,7 @@ EXPORT_SYMBOL(scsi_target_resume); int scsi_internal_device_block(struct scsi_device *sdev) { - request_queue_t *q = sdev->request_queue; + struct request_queue *q = sdev->request_queue; unsigned long flags; int err = 0; @@ -2159,7 +2159,7 @@ EXPORT_SYMBOL_GPL(scsi_internal_device_b int scsi_internal_device_unblock(struct scsi_device *sdev) { - request_queue_t *q = sdev->request_queue; + struct request_queue *q = sdev->request_queue; int err; unsigned long flags; Index: linux-rt-rebase.q/drivers/scsi/sd.c =================================================================== --- linux-rt-rebase.q.orig/drivers/scsi/sd.c +++ linux-rt-rebase.q/drivers/scsi/sd.c @@ -814,7 +814,7 @@ static int sd_issue_flush(struct device return ret; } -static void sd_prepare_flush(request_queue_t *q, struct request *rq) +static void sd_prepare_flush(struct request_queue *q, struct request *rq) { memset(rq->cmd, 0, sizeof(rq->cmd)); rq->cmd_type = REQ_TYPE_BLOCK_PC; @@ -1285,7 +1285,7 @@ got_data: */ int hard_sector = sector_size; sector_t sz = (sdkp->capacity/2) * (hard_sector/256); - request_queue_t *queue = sdp->request_queue; + struct request_queue *queue = sdp->request_queue; sector_t mb = sz; blk_queue_hardsect_size(queue, hard_sector); Index: linux-rt-rebase.q/drivers/scsi/sr.c =================================================================== --- linux-rt-rebase.q.orig/drivers/scsi/sr.c +++ linux-rt-rebase.q/drivers/scsi/sr.c @@ -624,7 +624,7 @@ static void get_sectorsize(struct scsi_c unsigned char *buffer; int the_result, retries = 3; int sector_size; - request_queue_t *queue; + struct request_queue *queue; buffer = kmalloc(512, GFP_KERNEL | GFP_DMA); if (!buffer) Index: linux-rt-rebase.q/drivers/serial/68328serial.c =================================================================== --- linux-rt-rebase.q.orig/drivers/serial/68328serial.c +++ linux-rt-rebase.q/drivers/serial/68328serial.c @@ -33,7 +33,6 @@ #include #include #include -#include #include #include @@ -401,9 +400,9 @@ irqreturn_t rs_interrupt(int irq, void * return IRQ_HANDLED; } -static void do_softint(void *private) +static void do_softint(struct work_struct *work) { - struct m68k_serial *info = (struct m68k_serial *) private; + struct m68k_serial *info = container_of(work, struct m68k_serial, tqueue); struct tty_struct *tty; tty = info->tty; @@ -425,9 +424,9 @@ static void do_softint(void *private) * do_serial_hangup() -> tty->hangup() -> rs_hangup() * */ -static void do_serial_hangup(void *private) +static void do_serial_hangup(struct work_struct *work) { - struct m68k_serial *info = (struct m68k_serial *) private; + struct m68k_serial *info = container_of(work, struct m68k_serial, tqueue_hangup); struct tty_struct *tty; tty = info->tty; @@ -1324,59 +1323,6 @@ static void show_serial_version(void) printk("MC68328 serial driver version 1.00\n"); } -#ifdef CONFIG_PM_LEGACY -/* Serial Power management - * The console (currently fixed at line 0) is a special case for power - * management because the kernel is so chatty. The console will be - * explicitly disabled my our power manager as the last minute, so we won't - * mess with it here. - */ -static struct pm_dev *serial_pm[NR_PORTS]; - -static int serial_pm_callback(struct pm_dev *dev, pm_request_t request, void *data) -{ - struct m68k_serial *info = (struct m68k_serial *)dev->data; - - if(info == NULL) - return -1; - - /* special case for line 0 - pm restores it */ - if(info->line == 0) - return 0; - - switch (request) { - case PM_SUSPEND: - shutdown(info); - break; - - case PM_RESUME: - startup(info); - break; - } - return 0; -} - -void shutdown_console(void) -{ - struct m68k_serial *info = &m68k_soft[0]; - - /* HACK: wait a bit for any pending printk's to be dumped */ - { - int i = 10000; - while(i--); - } - - shutdown(info); -} - -void startup_console(void) -{ - struct m68k_serial *info = &m68k_soft[0]; - startup(info); -} -#endif /* CONFIG_PM_LEGACY */ - - static const struct tty_operations rs_ops = { .open = rs_open, .close = rs_close, @@ -1444,8 +1390,8 @@ rs68328_init(void) info->event = 0; info->count = 0; info->blocked_open = 0; - INIT_WORK(&info->tqueue, do_softint, info); - INIT_WORK(&info->tqueue_hangup, do_serial_hangup, info); + INIT_WORK(&info->tqueue, do_softint); + INIT_WORK(&info->tqueue_hangup, do_serial_hangup); init_waitqueue_head(&info->open_wait); init_waitqueue_head(&info->close_wait); info->line = i; @@ -1467,11 +1413,6 @@ rs68328_init(void) IRQ_FLG_STD, "M68328_UART", NULL)) panic("Unable to attach 68328 serial interrupt\n"); -#ifdef CONFIG_PM_LEGACY - serial_pm[i] = pm_register(PM_SYS_DEV, PM_SYS_COM, serial_pm_callback); - if (serial_pm[i]) - serial_pm[i]->data = info; -#endif } local_irq_restore(flags); return 0; Index: linux-rt-rebase.q/drivers/serial/8250.c =================================================================== --- linux-rt-rebase.q.orig/drivers/serial/8250.c +++ linux-rt-rebase.q/drivers/serial/8250.c @@ -1451,7 +1451,10 @@ static irqreturn_t serial8250_interrupt( { struct irq_info *i = dev_id; struct list_head *l, *end = NULL; - int pass_counter = 0, handled = 0; +#ifndef CONFIG_PREEMPT_RT + int pass_counter = 0; +#endif + int handled = 0; DEBUG_INTR("serial8250_interrupt(%d)...", irq); @@ -1489,12 +1492,18 @@ static irqreturn_t serial8250_interrupt( l = l->next; + /* + * On preempt-rt we can be preempted and run in our + * own thread. + */ +#ifndef CONFIG_PREEMPT_RT if (l == i->head && pass_counter++ > PASS_LIMIT) { /* If we hit this, we're dead. */ printk(KERN_ERR "serial8250: too much work for " "irq%d\n", irq); break; } +#endif } while (l != end); spin_unlock(&i->lock); @@ -2456,14 +2465,10 @@ serial8250_console_write(struct console touch_nmi_watchdog(); - local_irq_save(flags); - if (up->port.sysrq) { - /* serial8250_handle_port() already took the lock */ - locked = 0; - } else if (oops_in_progress) { - locked = spin_trylock(&up->port.lock); - } else - spin_lock(&up->port.lock); + if (up->port.sysrq || oops_in_progress) + locked = spin_trylock_irqsave(&up->port.lock, flags); + else + spin_lock_irqsave(&up->port.lock, flags); /* * First save the IER then disable the interrupts @@ -2485,8 +2490,7 @@ serial8250_console_write(struct console serial_out(up, UART_IER, ier); if (locked) - spin_unlock(&up->port.lock); - local_irq_restore(flags); + spin_unlock_irqrestore(&up->port.lock, flags); } static int __init serial8250_console_setup(struct console *co, char *options) @@ -2650,8 +2654,9 @@ static int __devinit serial8250_probe(st ret = serial8250_register_port(&port); if (ret < 0) { dev_err(&dev->dev, "unable to register port at index %d " - "(IO%lx MEM%lx IRQ%d): %d\n", i, - p->iobase, p->mapbase, p->irq, ret); + "(IO%lx MEM%llx IRQ%d): %d\n", i, + p->iobase, (unsigned long long)p->mapbase, + p->irq, ret); } } return 0; Index: linux-rt-rebase.q/drivers/serial/8250_early.c =================================================================== --- linux-rt-rebase.q.orig/drivers/serial/8250_early.c +++ linux-rt-rebase.q/drivers/serial/8250_early.c @@ -151,8 +151,9 @@ static int __init parse_options(struct e #else port->membase = ioremap(port->mapbase, 64); if (!port->membase) { - printk(KERN_ERR "%s: Couldn't ioremap 0x%lx\n", - __FUNCTION__, port->mapbase); + printk(KERN_ERR "%s: Couldn't ioremap 0x%llx\n", + __FUNCTION__, + (unsigned long long)port->mapbase); return -ENOMEM; } #endif @@ -175,9 +176,10 @@ static int __init parse_options(struct e device->baud); } - printk(KERN_INFO "Early serial console at %s 0x%lx (options '%s')\n", + printk(KERN_INFO "Early serial console at %s 0x%llx (options '%s')\n", mmio ? "MMIO" : "I/O port", - mmio ? port->mapbase : (unsigned long) port->iobase, + mmio ? (unsigned long long) port->mapbase + : (unsigned long long) port->iobase, device->options); return 0; } Index: linux-rt-rebase.q/drivers/serial/serial_core.c =================================================================== --- linux-rt-rebase.q.orig/drivers/serial/serial_core.c +++ linux-rt-rebase.q/drivers/serial/serial_core.c @@ -626,7 +626,7 @@ static int uart_get_info(struct uart_sta tmp.hub6 = port->hub6; tmp.io_type = port->iotype; tmp.iomem_reg_shift = port->regshift; - tmp.iomem_base = (void *)port->mapbase; + tmp.iomem_base = (void *)(unsigned long)port->mapbase; if (copy_to_user(retinfo, &tmp, sizeof(*retinfo))) return -EFAULT; @@ -1666,10 +1666,11 @@ static int uart_line_info(char *buf, str return 0; mmio = port->iotype >= UPIO_MEM; - ret = sprintf(buf, "%d: uart:%s %s%08lX irq:%d", + ret = sprintf(buf, "%d: uart:%s %s%08llX irq:%d", port->line, uart_type(port), mmio ? "mmio:0x" : "port:", - mmio ? port->mapbase : (unsigned long) port->iobase, + mmio ? (unsigned long long)port->mapbase + : (unsigned long long) port->iobase, port->irq); if (port->type == PORT_UNKNOWN) { @@ -2069,7 +2070,7 @@ uart_report_port(struct uart_driver *drv case UPIO_TSI: case UPIO_DWAPB: snprintf(address, sizeof(address), - "MMIO 0x%lx", port->mapbase); + "MMIO 0x%llx", (unsigned long long)port->mapbase); break; default: strlcpy(address, "*unknown*", sizeof(address)); Index: linux-rt-rebase.q/drivers/usb/core/devio.c =================================================================== --- linux-rt-rebase.q.orig/drivers/usb/core/devio.c +++ linux-rt-rebase.q/drivers/usb/core/devio.c @@ -308,10 +308,11 @@ static void async_completed(struct urb * struct async *as = urb->context; struct dev_state *ps = as->ps; struct siginfo sinfo; + unsigned long flags; - spin_lock(&ps->lock); - list_move_tail(&as->asynclist, &ps->async_completed); - spin_unlock(&ps->lock); + spin_lock_irqsave(&ps->lock, flags); + list_move_tail(&as->asynclist, &ps->async_completed); + spin_unlock_irqrestore(&ps->lock, flags); if (as->signr) { sinfo.si_signo = as->signr; sinfo.si_errno = as->urb->status; Index: linux-rt-rebase.q/drivers/usb/core/hcd.c =================================================================== --- linux-rt-rebase.q.orig/drivers/usb/core/hcd.c +++ linux-rt-rebase.q/drivers/usb/core/hcd.c @@ -523,13 +523,11 @@ error: } /* any errors get returned through the urb completion */ - local_irq_save (flags); - spin_lock (&urb->lock); + spin_lock_irqsave(&urb->lock, flags); if (urb->status == -EINPROGRESS) urb->status = status; - spin_unlock (&urb->lock); + spin_unlock_irqrestore(&urb->lock, flags); usb_hcd_giveback_urb (hcd, urb); - local_irq_restore (flags); return 0; } @@ -559,8 +557,7 @@ void usb_hcd_poll_rh_status(struct usb_h if (length > 0) { /* try to complete the status urb */ - local_irq_save (flags); - spin_lock(&hcd_root_hub_lock); + spin_lock_irqsave(&hcd_root_hub_lock, flags); urb = hcd->status_urb; if (urb) { spin_lock(&urb->lock); @@ -576,14 +573,13 @@ void usb_hcd_poll_rh_status(struct usb_h spin_unlock(&urb->lock); } else length = 0; - spin_unlock(&hcd_root_hub_lock); + spin_unlock_irqrestore(&hcd_root_hub_lock, flags); /* local irqs are always blocked in completions */ if (length > 0) usb_hcd_giveback_urb (hcd, urb); else hcd->poll_pending = 1; - local_irq_restore (flags); } /* The USB 2.0 spec says 256 ms. This is close enough and won't @@ -657,17 +653,15 @@ static int usb_rh_urb_dequeue (struct us } else { /* Status URB */ if (!hcd->uses_new_polling) del_timer (&hcd->rh_timer); - local_irq_save (flags); - spin_lock (&hcd_root_hub_lock); + spin_lock_irqsave(&hcd_root_hub_lock, flags); if (urb == hcd->status_urb) { hcd->status_urb = NULL; urb->hcpriv = NULL; } else urb = NULL; /* wasn't fully queued */ - spin_unlock (&hcd_root_hub_lock); + spin_unlock_irqrestore(&hcd_root_hub_lock, flags); if (urb) usb_hcd_giveback_urb (hcd, urb); - local_irq_restore (flags); } return 0; @@ -1200,13 +1194,13 @@ void usb_hcd_endpoint_disable (struct us { struct usb_hcd *hcd; struct urb *urb; + unsigned long flags; hcd = bus_to_hcd(udev->bus); - local_irq_disable (); /* ep is already gone from udev->ep_{in,out}[]; no more submits */ rescan: - spin_lock(&hcd_urb_list_lock); + spin_lock_irqsave(&hcd_urb_list_lock, flags); list_for_each_entry (urb, &ep->urb_list, urb_list) { int tmp; @@ -1243,8 +1237,7 @@ rescan: /* list contents may have changed */ goto rescan; } - spin_unlock(&hcd_urb_list_lock); - local_irq_enable (); + spin_unlock_irqrestore(&hcd_urb_list_lock, flags); /* synchronize with the hardware, so old configuration state * clears out immediately (and will be freed). Index: linux-rt-rebase.q/drivers/usb/core/message.c =================================================================== --- linux-rt-rebase.q.orig/drivers/usb/core/message.c +++ linux-rt-rebase.q/drivers/usb/core/message.c @@ -252,8 +252,9 @@ static void sg_complete (struct urb *urb { struct usb_sg_request *io = urb->context; int status = urb->status; + unsigned long flags; - spin_lock (&io->lock); + spin_lock_irqsave (&io->lock, flags); /* In 2.5 we require hcds' endpoint queues not to progress after fault * reports, until the completion callback (this!) returns. That lets @@ -287,7 +288,7 @@ static void sg_complete (struct urb *urb * unlink pending urbs so they won't rx/tx bad data. * careful: unlink can sometimes be synchronous... */ - spin_unlock (&io->lock); + spin_unlock_irqrestore (&io->lock, flags); for (i = 0, found = 0; i < io->entries; i++) { if (!io->urbs [i] || !io->urbs [i]->dev) continue; @@ -302,7 +303,7 @@ static void sg_complete (struct urb *urb } else if (urb == io->urbs [i]) found = 1; } - spin_lock (&io->lock); + spin_lock_irqsave (&io->lock, flags); } urb->dev = NULL; @@ -312,7 +313,7 @@ static void sg_complete (struct urb *urb if (!io->count) complete (&io->complete); - spin_unlock (&io->lock); + spin_unlock_irqrestore (&io->lock, flags); } @@ -587,7 +588,7 @@ void usb_sg_cancel (struct usb_sg_reques dev_warn (&io->dev->dev, "%s, unlink --> %d\n", __FUNCTION__, retval); } - spin_lock (&io->lock); + spin_lock_irqsave (&io->lock, flags); } spin_unlock_irqrestore (&io->lock, flags); } Index: linux-rt-rebase.q/drivers/usb/storage/usb.h =================================================================== --- linux-rt-rebase.q.orig/drivers/usb/storage/usb.h +++ linux-rt-rebase.q/drivers/usb/storage/usb.h @@ -147,7 +147,7 @@ struct us_data { struct task_struct *ctl_thread; /* the control thread */ /* mutual exclusion and synchronization structures */ - struct semaphore sema; /* to sleep thread on */ + struct compat_semaphore sema; /* to sleep thread on */ struct completion notify; /* thread begin/end */ wait_queue_head_t delay_wait; /* wait during scan, reset */ Index: linux-rt-rebase.q/drivers/video/Kconfig =================================================================== --- linux-rt-rebase.q.orig/drivers/video/Kconfig +++ linux-rt-rebase.q/drivers/video/Kconfig @@ -1571,7 +1571,14 @@ config FB_PM3 config FB_AU1100 bool "Au1100 LCD Driver" - depends on (FB = y) && EXPERIMENTAL && PCI && MIPS && MIPS_PB1100=y + depends on (FB = y) && MIPS && SOC_AU1100 + select FB_CFB_FILLRECT + select FB_CFB_COPYAREA + select FB_CFB_IMAGEBLIT + help + This is the framebuffer driver for the AMD Au1100 SOC. It can drive + various panels and CRTs by passing in kernel cmd line option + au1100fb:panel=. config FB_AU1200 bool "Au1200 LCD Driver" Index: linux-rt-rebase.q/drivers/video/console/fbcon.c =================================================================== --- linux-rt-rebase.q.orig/drivers/video/console/fbcon.c +++ linux-rt-rebase.q/drivers/video/console/fbcon.c @@ -1295,7 +1295,6 @@ static void fbcon_clear(struct vc_data * { struct fb_info *info = registered_fb[con2fb_map[vc->vc_num]]; struct fbcon_ops *ops = info->fbcon_par; - struct display *p = &fb_display[vc->vc_num]; u_int y_break; @@ -1324,10 +1323,11 @@ static void fbcon_putcs(struct vc_data * struct display *p = &fb_display[vc->vc_num]; struct fbcon_ops *ops = info->fbcon_par; - if (!fbcon_is_inactive(vc, info)) + if (!fbcon_is_inactive(vc, info)) { ops->putcs(vc, info, s, count, real_y(p, ypos), xpos, get_color(vc, info, scr_readw(s), 1), get_color(vc, info, scr_readw(s), 0)); + } } static void fbcon_putc(struct vc_data *vc, int c, int ypos, int xpos) @@ -3311,6 +3311,7 @@ static const struct consw fb_con = { .con_screen_pos = fbcon_screen_pos, .con_getxy = fbcon_getxy, .con_resize = fbcon_resize, + .con_preemptible = 1, }; static struct notifier_block fbcon_event_notifier = { Index: linux-rt-rebase.q/drivers/video/console/vgacon.c =================================================================== --- linux-rt-rebase.q.orig/drivers/video/console/vgacon.c +++ linux-rt-rebase.q/drivers/video/console/vgacon.c @@ -51,7 +51,7 @@ #include