diff options
| author | Ingo Molnar <mingo@elte.hu> | 2011-04-18 14:53:18 +0200 |
|---|---|---|
| committer | Ingo Molnar <mingo@elte.hu> | 2011-04-18 14:53:33 +0200 |
| commit | 6ddafdaab3f809b110ada253d2f2d4910ebd3ac5 (patch) | |
| tree | 366bb7513511a05b6e11ab89bfe3b2dbd1d62a03 | |
| parent | 3905c54f2bd2c6f937f87307987ca072eabc3e7b (diff) | |
| parent | bd8e7dded88a3e1c085c333f19ff31387616f71a (diff) | |
Merge branch 'sched/locking' into sched/core
Merge reason: the rq locking changes are stable,
propagate them into the .40 queue.
Signed-off-by: Ingo Molnar <mingo@elte.hu>
216 files changed, 2080 insertions, 2462 deletions
diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt index 274b32d12532..492e81df2968 100644 --- a/Documentation/feature-removal-schedule.txt +++ b/Documentation/feature-removal-schedule.txt @@ -387,26 +387,6 @@ Who: Tejun Heo <tj@kernel.org> ---------------------------- -What: Support for lcd_switch and display_get in asus-laptop driver -When: March 2010 -Why: These two features use non-standard interfaces. There are the - only features that really need multiple path to guess what's - the right method name on a specific laptop. - - Removing them will allow to remove a lot of code an significantly - clean the drivers. - - This will affect the backlight code which won't be able to know - if the backlight is on or off. The platform display file will also be - write only (like the one in eeepc-laptop). - - This should'nt affect a lot of user because they usually know - when their display is on or off. - -Who: Corentin Chary <corentin.chary@gmail.com> - ----------------------------- - What: sysfs-class-rfkill state file When: Feb 2014 Files: net/rfkill/core.c diff --git a/MAINTAINERS b/MAINTAINERS index 6b4b9cdec370..649600cb8ec9 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -6916,6 +6916,13 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/mjg59/platform-drivers-x86. S: Maintained F: drivers/platform/x86 +XEN NETWORK BACKEND DRIVER +M: Ian Campbell <ian.campbell@citrix.com> +L: xen-devel@lists.xensource.com (moderated for non-subscribers) +L: netdev@vger.kernel.org +S: Supported +F: drivers/net/xen-netback/* + XEN PCI SUBSYSTEM M: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> L: xen-devel@lists.xensource.com (moderated for non-subscribers) @@ -1,7 +1,7 @@ VERSION = 2 PATCHLEVEL = 6 SUBLEVEL = 39 -EXTRAVERSION = -rc2 +EXTRAVERSION = -rc3 NAME = Flesh-Eating Bats with Fangs # *DOCUMENTATION* diff --git a/arch/alpha/kernel/smp.c b/arch/alpha/kernel/smp.c index 42aa078a5e4d..5a621c6d22ab 100644 --- a/arch/alpha/kernel/smp.c +++ b/arch/alpha/kernel/smp.c @@ -585,8 +585,7 @@ handle_ipi(struct pt_regs *regs) switch (which) { case IPI_RESCHEDULE: - /* Reschedule callback. Everything to be done - is done by the interrupt return path. */ + scheduler_ipi(); break; case IPI_CALL_FUNC: diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c index 8fe05ad932e4..7a561eb731ea 100644 --- a/arch/arm/kernel/smp.c +++ b/arch/arm/kernel/smp.c @@ -560,10 +560,7 @@ asmlinkage void __exception_irq_entry do_IPI(int ipinr, struct pt_regs *regs) break; case IPI_RESCHEDULE: - /* - * nothing more to do - eveything is - * done on the interrupt return path - */ + scheduler_ipi(); break; case IPI_CALL_FUNC: diff --git a/arch/avr32/include/asm/setup.h b/arch/avr32/include/asm/setup.h index ff5b7cf6be4d..160543dbec7e 100644 --- a/arch/avr32/include/asm/setup.h +++ b/arch/avr32/include/asm/setup.h @@ -94,6 +94,13 @@ struct tag_ethernet { #define ETH_INVALID_PHY 0xff +/* board information */ +#define ATAG_BOARDINFO 0x54410008 + +struct tag_boardinfo { + u32 board_number; +}; + struct tag { struct tag_header hdr; union { @@ -102,6 +109,7 @@ struct tag { struct tag_cmdline cmdline; struct tag_clock clock; struct tag_ethernet ethernet; + struct tag_boardinfo boardinfo; } u; }; @@ -128,6 +136,7 @@ extern struct tag *bootloader_tags; extern resource_size_t fbmem_start; extern resource_size_t fbmem_size; +extern u32 board_number; void setup_processor(void); diff --git a/arch/avr32/kernel/setup.c b/arch/avr32/kernel/setup.c index 5c7083916c33..bb0974cce4ac 100644 --- a/arch/avr32/kernel/setup.c +++ b/arch/avr32/kernel/setup.c @@ -391,6 +391,21 @@ static int __init parse_tag_clock(struct tag *tag) __tagtable(ATAG_CLOCK, parse_tag_clock); /* + * The board_number correspond to the bd->bi_board_number in U-Boot. This + * parameter is only available during initialisation and can be used in some + * kind of board identification. + */ +u32 __initdata board_number; + +static int __init parse_tag_boardinfo(struct tag *tag) +{ + board_number = tag->u.boardinfo.board_number; + + return 0; +} +__tagtable(ATAG_BOARDINFO, parse_tag_boardinfo); + +/* * Scan the tag table for this tag, and call its parse function. The * tag table is built by the linker from all the __tagtable * declarations. diff --git a/arch/avr32/kernel/traps.c b/arch/avr32/kernel/traps.c index b91b2044af9c..7aa25756412f 100644 --- a/arch/avr32/kernel/traps.c +++ b/arch/avr32/kernel/traps.c @@ -95,28 +95,6 @@ void _exception(long signr, struct pt_regs *regs, int code, info.si_code = code; info.si_addr = (void __user *)addr; force_sig_info(signr, &info, current); - - /* - * Init gets no signals that it doesn't have a handler for. - * That's all very well, but if it has caused a synchronous - * exception and we ignore the resulting signal, it will just - * generate the same exception over and over again and we get - * nowhere. Better to kill it and let the kernel panic. - */ - if (is_global_init(current)) { - __sighandler_t handler; - - spin_lock_irq(¤t->sighand->siglock); - handler = current->sighand->action[signr-1].sa.sa_handler; - spin_unlock_irq(¤t->sighand->siglock); - if (handler == SIG_DFL) { - /* init has generated a synchronous exception - and it doesn't have a handler for the signal */ - printk(KERN_CRIT "init has generated signal %ld " - "but has no handler for it\n", signr); - do_exit(signr); - } - } } asmlinkage void do_nmi(unsigned long ecr, struct pt_regs *regs) diff --git a/arch/avr32/mach-at32ap/clock.c b/arch/avr32/mach-at32ap/clock.c index 442f08c5e641..86925fd6ea5b 100644 --- a/arch/avr32/mach-at32ap/clock.c +++ b/arch/avr32/mach-at32ap/clock.c @@ -35,22 +35,30 @@ void at32_clk_register(struct clk *clk) spin_unlock(&clk_list_lock); } -struct clk *clk_get(struct device *dev, const char *id) +static struct clk *__clk_get(struct device *dev, const char *id) { struct clk *clk; - spin_lock(&clk_list_lock); - list_for_each_entry(clk, &at32_clock_list, list) { if (clk->dev == dev && strcmp(id, clk->name) == 0) { - spin_unlock(&clk_list_lock); return clk; } } - spin_unlock(&clk_list_lock); return ERR_PTR(-ENOENT); } + +struct clk *clk_get(struct device *dev, const char *id) +{ + struct clk *clk; + + spin_lock(&clk_list_lock); + clk = __clk_get(dev, id); + spin_unlock(&clk_list_lock); + + return clk; +} + EXPORT_SYMBOL(clk_get); void clk_put(struct clk *clk) @@ -257,15 +265,15 @@ static int clk_show(struct seq_file *s, void *unused) spin_lock(&clk_list_lock); /* show clock tree as derived from the three oscillators */ - clk = clk_get(NULL, "osc32k"); + clk = __clk_get(NULL, "osc32k"); dump_clock(clk, &r); clk_put(clk); - clk = clk_get(NULL, "osc0"); + clk = __clk_get(NULL, "osc0"); dump_clock(clk, &r); clk_put(clk); - clk = clk_get(NULL, "osc1"); + clk = __clk_get(NULL, "osc1"); dump_clock(clk, &r); clk_put(clk); diff --git a/arch/avr32/mach-at32ap/extint.c b/arch/avr32/mach-at32ap/extint.c index 47ba4b9b6db1..fbc2aeaebddb 100644 --- a/arch/avr32/mach-at32ap/extint.c +++ b/arch/avr32/mach-at32ap/extint.c @@ -61,34 +61,34 @@ struct eic { static struct eic *nmi_eic; static bool nmi_enabled; -static void eic_ack_irq(struct irq_chip *d) +static void eic_ack_irq(struct irq_data *d) { - struct eic *eic = irq_data_get_irq_chip_data(data); + struct eic *eic = irq_data_get_irq_chip_data(d); eic_writel(eic, ICR, 1 << (d->irq - eic->first_irq)); } -static void eic_mask_irq(struct irq_chip *d) +static void eic_mask_irq(struct irq_data *d) { - struct eic *eic = irq_data_get_irq_chip_data(data); + struct eic *eic = irq_data_get_irq_chip_data(d); eic_writel(eic, IDR, 1 << (d->irq - eic->first_irq)); } -static void eic_mask_ack_irq(struct irq_chip *d) +static void eic_mask_ack_irq(struct irq_data *d) { - struct eic *eic = irq_data_get_irq_chip_data(data); + struct eic *eic = irq_data_get_irq_chip_data(d); eic_writel(eic, ICR, 1 << (d->irq - eic->first_irq)); eic_writel(eic, IDR, 1 << (d->irq - eic->first_irq)); } -static void eic_unmask_irq(struct irq_chip *d) +static void eic_unmask_irq(struct irq_data *d) { - struct eic *eic = irq_data_get_irq_chip_data(data); + struct eic *eic = irq_data_get_irq_chip_data(d); eic_writel(eic, IER, 1 << (d->irq - eic->first_irq)); } -static int eic_set_irq_type(struct irq_chip *d, unsigned int flow_type) +static int eic_set_irq_type(struct irq_data *d, unsigned int flow_type) { - struct eic *eic = irq_data_get_irq_chip_data(data); + struct eic *eic = irq_data_get_irq_chip_data(d); unsigned int irq = d->irq; unsigned int i = irq - eic->first_irq; u32 mode, edge, level; @@ -191,7 +191,7 @@ static int __init eic_probe(struct platform_device *pdev) regs = platform_get_resource(pdev, IORESOURCE_MEM, 0); int_irq = platform_get_irq(pdev, 0); - if (!regs || !int_irq) { + if (!regs || (int)int_irq <= 0) { dev_dbg(&pdev->dev, "missing regs and/or irq resource\n"); return -ENXIO; } diff --git a/arch/avr32/mach-at32ap/pio.c b/arch/avr32/mach-at32ap/pio.c index f308e1ddc629..2e0aa853a4bc 100644 --- a/arch/avr32/mach-at32ap/pio.c +++ b/arch/avr32/mach-at32ap/pio.c @@ -257,7 +257,7 @@ static void gpio_irq_mask(struct irq_data *d) pio_writel(pio, IDR, 1 << (gpio & 0x1f)); } -static void gpio_irq_unmask(struct irq_data *d)) +static void gpio_irq_unmask(struct irq_data *d) { unsigned gpio = irq_to_gpio(d->irq); struct pio_device *pio = &pio_dev[gpio >> 5]; diff --git a/arch/avr32/mach-at32ap/pm-at32ap700x.S b/arch/avr32/mach-at32ap/pm-at32ap700x.S index 17503b0ed6c9..f868f4ce761b 100644 --- a/arch/avr32/mach-at32ap/pm-at32ap700x.S +++ b/arch/avr32/mach-at32ap/pm-at32ap700x.S @@ -53,7 +53,7 @@ cpu_enter_idle: st.w r8[TI_flags], r9 unmask_interrupts sleep CPU_SLEEP_IDLE - .size cpu_idle_sleep, . - cpu_idle_sleep + .size cpu_enter_idle, . - cpu_enter_idle /* * Common return path for PM functions that don't run from diff --git a/arch/blackfin/mach-common/smp.c b/arch/blackfin/mach-common/smp.c index 6e17a265c4d3..326bb86f4d29 100644 --- a/arch/blackfin/mach-common/smp.c +++ b/arch/blackfin/mach-common/smp.c @@ -164,6 +164,9 @@ static irqreturn_t ipi_handler_int1(int irq, void *dev_instance) while (msg_queue->count) { msg = &msg_queue->ipi_message[msg_queue->head]; switch (msg->type) { + case BFIN_IPI_RESCHEDULE: + scheduler_ipi(); + break; case BFIN_IPI_CALL_FUNC: spin_unlock_irqrestore(&msg_queue->lock, flags); ipi_call_function(cpu, msg); diff --git a/arch/cris/arch-v32/kernel/smp.c b/arch/cris/arch-v32/kernel/smp.c index 4c9e3e1ba5d1..66cc75657e2f 100644 --- a/arch/cris/arch-v32/kernel/smp.c +++ b/arch/cris/arch-v32/kernel/smp.c @@ -342,15 +342,18 @@ irqreturn_t crisv32_ipi_interrupt(int irq, void *dev_id) ipi = REG_RD(intr_vect, irq_regs[smp_processor_id()], rw_ipi); + if (ipi.vector & IPI_SCHEDULE) { + scheduler_ipi(); + } if (ipi.vector & IPI_CALL) { - func(info); + func(info); } if (ipi.vector & IPI_FLUSH_TLB) { - if (flush_mm == FLUSH_ALL) - __flush_tlb_all(); - else if (flush_vma == FLUSH_ALL) + if (flush_mm == FLUSH_ALL) + __flush_tlb_all(); + else if (flush_vma == FLUSH_ALL) __flush_tlb_mm(flush_mm); - else + else __flush_tlb_page(flush_vma, flush_addr); } diff --git a/arch/ia64/kernel/irq_ia64.c b/arch/ia64/kernel/irq_ia64.c index 5b704740f160..782c3a357f24 100644 --- a/arch/ia64/kernel/irq_ia64.c +++ b/arch/ia64/kernel/irq_ia64.c @@ -31,6 +31,7 @@ #include <linux/irq.h> #include <linux/ratelimit.h> #include <linux/acpi.h> +#include <linux/sched.h> #include <asm/delay.h> #include <asm/intrinsics.h> @@ -496,6 +497,7 @@ ia64_handle_irq (ia64_vector vector, struct pt_regs *regs) smp_local_flush_tlb(); kstat_incr_irqs_this_cpu(irq, desc); } else if (unlikely(IS_RESCHEDULE(vector))) { + scheduler_ipi(); kstat_incr_irqs_this_cpu(irq, desc); } else { ia64_setreg(_IA64_REG_CR_TPR, vector); diff --git a/arch/ia64/xen/irq_xen.c b/arch/ia64/xen/irq_xen.c index 108bb858acf2..b279e142c633 100644 --- a/arch/ia64/xen/irq_xen.c +++ b/arch/ia64/xen/irq_xen.c @@ -92,6 +92,8 @@ static unsigned short saved_irq_cnt; static int xen_slab_ready; #ifdef CONFIG_SMP +#include <linux/sched.h> + /* Dummy stub. Though we may check XEN_RESCHEDULE_VECTOR before __do_IRQ, * it ends up to issue several memory accesses upon percpu data and * thus adds unnecessary traffic to other paths. @@ -99,7 +101,13 @@ static int xen_slab_ready; static irqreturn_t xen_dummy_handler(int irq, void *dev_id) { + return IRQ_HANDLED; +} +static irqreturn_t +xen_resched_handler(int irq, void *dev_id) +{ + scheduler_ipi(); return IRQ_HANDLED; } @@ -110,7 +118,7 @@ static struct irqaction xen_ipi_irqaction = { }; static struct irqaction xen_resched_irqaction = { - .handler = xen_dummy_handler, + .handler = xen_resched_handler, .flags = IRQF_DISABLED, .name = "resched" }; diff --git a/arch/m32r/kernel/smp.c b/arch/m32r/kernel/smp.c index 31cef20b2996..fc10b39893d4 100644 --- a/arch/m32r/kernel/smp.c +++ b/arch/m32r/kernel/smp.c @@ -122,8 +122,6 @@ void smp_send_reschedule(int cpu_id) * * Description: This routine executes on CPU which received * 'RESCHEDULE_IPI'. - * Rescheduling is processed at the exit of interrupt - * operation. * * Born on Date: 2002.02.05 * @@ -138,7 +136,7 @@ void smp_send_reschedule(int cpu_id) *==========================================================================*/ void smp_reschedule_interrupt(void) { - /* nothing to do */ + scheduler_ipi(); } /*==========================================================================* diff --git a/arch/m68k/include/asm/unistd.h b/arch/m68k/include/asm/unistd.h index 26d851d385bb..29e17907d9f2 100644 --- a/arch/m68k/include/asm/unistd.h +++ b/arch/m68k/include/asm/unistd.h @@ -343,10 +343,14 @@ #define __NR_fanotify_init 337 #define __NR_fanotify_mark 338 #define __NR_prlimit64 339 +#define __NR_name_to_handle_at 340 +#define __NR_open_by_handle_at 341 +#define __NR_clock_adjtime 342 +#define __NR_syncfs 343 #ifdef __KERNEL__ -#define NR_syscalls 340 +#define NR_syscalls 344 #define __ARCH_WANT_IPC_PARSE_VERSION #define __ARCH_WANT_OLD_READDIR diff --git a/arch/m68k/kernel/entry_mm.S b/arch/m68k/kernel/entry_mm.S index 1559dea36e55..1359ee659574 100644 --- a/arch/m68k/kernel/entry_mm.S +++ b/arch/m68k/kernel/entry_mm.S @@ -750,4 +750,8 @@ sys_call_table: .long sys_fanotify_init .long sys_fanotify_mark .long sys_prlimit64 + .long sys_name_to_handle_at /* 340 */ + .long sys_open_by_handle_at + .long sys_clock_adjtime + .long sys_syncfs diff --git a/arch/m68k/kernel/syscalltable.S b/arch/m68k/kernel/syscalltable.S index 79b1ed198c07..9b8393d8adb8 100644 --- a/arch/m68k/kernel/syscalltable.S +++ b/arch/m68k/kernel/syscalltable.S @@ -358,6 +358,10 @@ ENTRY(sys_call_table) .long sys_fanotify_init .long sys_fanotify_mark .long sys_prlimit64 + .long sys_name_to_handle_at /* 340 */ + .long sys_open_by_handle_at + .long sys_clock_adjtime + .long sys_syncfs .rept NR_syscalls-(.-sys_call_table)/4 .long sys_ni_syscall diff --git a/arch/mips/cavium-octeon/smp.c b/arch/mips/cavium-octeon/smp.c index ba78b21cc8d0..76923eeb58b9 100644 --- a/arch/mips/cavium-octeon/smp.c +++ b/arch/mips/cavium-octeon/smp.c @@ -44,6 +44,8 @@ static irqreturn_t mailbox_interrupt(int irq, void *dev_id) if (action & SMP_CALL_FUNCTION) smp_call_function_interrupt(); + if (action & SMP_RESCHEDULE_YOURSELF) + scheduler_ipi(); /* Check if we've been told to flush the icache */ if (action & SMP_ICACHE_FLUSH) diff --git a/arch/mips/kernel/smtc.c b/arch/mips/kernel/smtc.c index 5a88cc4ccd5a..cedac4633741 100644 --- a/arch/mips/kernel/smtc.c +++ b/arch/mips/kernel/smtc.c @@ -929,7 +929,7 @@ static void post_direct_ipi(int cpu, struct smtc_ipi *pipi) static void ipi_resched_interrupt(void) { - /* Return from interrupt should be enough to cause scheduler check */ + scheduler_ipi(); } static void ipi_call_interrupt(void) diff --git a/arch/mips/mti-malta/malta-int.c b/arch/mips/mti-malta/malta-int.c index 9027061f0ead..7d93e6fbfa5a 100644 --- a/arch/mips/mti-malta/malta-int.c +++ b/arch/mips/mti-malta/malta-int.c @@ -309,6 +309,8 @@ static void ipi_call_dispatch(void) static irqreturn_t ipi_resched_interrupt(int irq, void *dev_id) { + scheduler_ipi(); + return IRQ_HANDLED; } diff --git a/arch/mips/pmc-sierra/yosemite/smp.c b/arch/mips/pmc-sierra/yosemite/smp.c index efc9e889b349..2608752898c0 100644 --- a/arch/mips/pmc-sierra/yosemite/smp.c +++ b/arch/mips/pmc-sierra/yosemite/smp.c @@ -55,6 +55,8 @@ void titan_mailbox_irq(void) if (status & 0x2) smp_call_function_interrupt(); + if (status & 0x4) + scheduler_ipi(); break; case 1: @@ -63,6 +65,8 @@ void titan_mailbox_irq(void) if (status & 0x2) smp_call_function_interrupt(); + if (status & 0x4) + scheduler_ipi(); break; } } diff --git a/arch/mips/sgi-ip27/ip27-irq.c b/arch/mips/sgi-ip27/ip27-irq.c index 0a04603d577c..b18b04e48577 100644 --- a/arch/mips/sgi-ip27/ip27-irq.c +++ b/arch/mips/sgi-ip27/ip27-irq.c @@ -147,8 +147,10 @@ static void ip27_do_irq_mask0(void) #ifdef CONFIG_SMP if (pend0 & (1UL << CPU_RESCHED_A_IRQ)) { LOCAL_HUB_CLR_INTR(CPU_RESCHED_A_IRQ); + scheduler_ipi(); } else if (pend0 & (1UL << CPU_RESCHED_B_IRQ)) { LOCAL_HUB_CLR_INTR(CPU_RESCHED_B_IRQ); + scheduler_ipi(); } else if (pend0 & (1UL << CPU_CALL_A_IRQ)) { LOCAL_HUB_CLR_INTR(CPU_CALL_A_IRQ); smp_call_function_interrupt(); diff --git a/arch/mips/sibyte/bcm1480/smp.c b/arch/mips/sibyte/bcm1480/smp.c index 47b347c992ea..d667875be564 100644 --- a/arch/mips/sibyte/bcm1480/smp.c +++ b/arch/mips/sibyte/bcm1480/smp.c @@ -20,6 +20,7 @@ #include <linux/delay.h> #include <linux/smp.h> #include <linux/kernel_stat.h> +#include <linux/sched.h> #include <asm/mmu_context.h> #include <asm/io.h> @@ -189,10 +190,8 @@ void bcm1480_mailbox_interrupt(void) /* Clear the mailbox to clear the interrupt */ __raw_writeq(((u64)action)<<48, mailbox_0_clear_regs[cpu]); - /* - * Nothing to do for SMP_RESCHEDULE_YOURSELF; returning from the - * interrupt will do the reschedule for us - */ + if (action & SMP_RESCHEDULE_YOURSELF) + scheduler_ipi(); if (action & SMP_CALL_FUNCTION) smp_call_function_interrupt(); diff --git a/arch/mips/sibyte/sb1250/smp.c b/arch/mips/sibyte/sb1250/smp.c index c00a5cb1128d..38e7f6bd7922 100644 --- a/arch/mips/sibyte/sb1250/smp.c +++ b/arch/mips/sibyte/sb1250/smp.c @@ -21,6 +21,7 @@ #include <linux/interrupt.h> #include <linux/smp.h> #include <linux/kernel_stat.h> +#include <linux/sched.h> #include <asm/mmu_context.h> #include <asm/io.h> @@ -177,10 +178,8 @@ void sb1250_mailbox_interrupt(void) /* Clear the mailbox to clear the interrupt */ ____raw_writeq(((u64)action) << 48, mailbox_clear_regs[cpu]); - /* - * Nothing to do for SMP_RESCHEDULE_YOURSELF; returning from the - * interrupt will do the reschedule for us - */ + if (action & SMP_RESCHEDULE_YOURSELF) + scheduler_ipi(); if (action & SMP_CALL_FUNCTION) smp_call_function_interrupt(); diff --git a/arch/mn10300/kernel/smp.c b/arch/mn10300/kernel/smp.c index 226c826a2194..83fb27912231 100644 --- a/arch/mn10300/kernel/smp.c +++ b/arch/mn10300/kernel/smp.c @@ -494,14 +494,11 @@ void smp_send_stop(void) * @irq: The interrupt number. * @dev_id: The device ID. * - * We need do nothing here, since the scheduling will be effected on our way - * back through entry.S. - * * Returns IRQ_HANDLED to indicate we handled the interrupt successfully. */ static irqreturn_t smp_reschedule_interrupt(int irq, void *dev_id) { - /* do nothing */ + scheduler_ipi(); return IRQ_HANDLED; } diff --git a/arch/parisc/kernel/smp.c b/arch/parisc/kernel/smp.c index 69d63d354ef0..828305f19cff 100644 --- a/arch/parisc/kernel/smp.c +++ b/arch/parisc/kernel/smp.c @@ -155,10 +155,7 @@ ipi_interrupt(int irq, void *dev_id) case IPI_RESCHEDULE: smp_debug(100, KERN_DEBUG "CPU%d IPI_RESCHEDULE\n", this_cpu); - /* - * Reschedule callback. Everything to be - * done is done by the interrupt return path. - */ + scheduler_ipi(); break; case IPI_CALL_FUNC: diff --git a/arch/powerpc/kernel/ibmebus.c b/arch/powerpc/kernel/ibmebus.c index c00d4ca1ee15..28581f1ad2c0 100644 --- a/arch/powerpc/kernel/ibmebus.c +++ b/arch/powerpc/kernel/ibmebus.c @@ -527,7 +527,7 @@ static int ibmebus_bus_pm_resume_noirq(struct device *dev) #endif /* !CONFIG_SUSPEND */ -#ifdef CONFIG_HIBERNATION +#ifdef CONFIG_HIBERNATE_CALLBACKS static int ibmebus_bus_pm_freeze(struct device *dev) { @@ -665,7 +665,7 @@ static int ibmebus_bus_pm_restore_noirq(struct device *dev) return ret; } -#else /* !CONFIG_HIBERNATION */ +#else /* !CONFIG_HIBERNATE_CALLBACKS */ #define ibmebus_bus_pm_freeze NULL #define ibmebus_bus_pm_thaw NULL @@ -676,7 +676,7 @@ static int ibmebus_bus_pm_restore_noirq(struct device *dev) #define ibmebus_bus_pm_poweroff_noirq NULL #define ibmebus_bus_pm_restore_noirq NULL -#endif /* !CONFIG_HIBERNATION */ +#endif /* !CONFIG_HIBERNATE_CALLBACKS */ static struct dev_pm_ops ibmebus_bus_dev_pm_ops = { .prepare = ibmebus_bus_pm_prepare, diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index cbdbb14be4b0..9f9c204bef69 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -116,7 +116,7 @@ void smp_message_recv(int msg) generic_smp_call_function_interrupt(); break; case PPC_MSG_RESCHEDULE: - /* we notice need_resched on exit */ + scheduler_ipi(); break; case PPC_MSG_CALL_FUNC_SINGLE: generic_smp_call_function_single_interrupt(); @@ -146,7 +146,7 @@ static irqreturn_t call_function_action(int irq, void *data) static irqreturn_t reschedule_action(int irq, void *data) { - /* we just need the return path side effect of checking need_resched */ + scheduler_ipi(); return IRQ_HANDLED; } diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c index 63a97db83f96..63c7d9ff220d 100644 --- a/arch/s390/kernel/smp.c +++ b/arch/s390/kernel/smp.c @@ -165,12 +165,12 @@ static void do_ext_call_interrupt(unsigned int ext_int_code, kstat_cpu(smp_processor_id()).irqs[EXTINT_IPI]++; /* * handle bit signal external calls - * - * For the ec_schedule signal we have to do nothing. All the work - * is done automatically when we return from the interrupt. */ bits = xchg(&S390_lowcore.ext_call_fast, 0); + if (test_bit(ec_schedule, &bits)) + scheduler_ipi(); + if (test_bit(ec_call_function, &bits)) generic_smp_call_function_interrupt(); diff --git a/arch/sh/kernel/smp.c b/arch/sh/kernel/smp.c index 509b36b45115..6207561ea34a 100644 --- a/arch/sh/kernel/smp.c +++ b/arch/sh/kernel/smp.c @@ -20,6 +20,7 @@ #include <linux/module.h> #include <linux/cpu.h> #include <linux/interrupt.h> +#include <linux/sched.h> #include <asm/atomic.h> #include <asm/processor.h> #include <asm/system.h> @@ -323,6 +324,7 @@ void smp_message_recv(unsigned int msg) generic_smp_call_function_interrupt(); break; case SMP_MSG_RESCHEDULE: + scheduler_ipi(); break; case SMP_MSG_FUNCTION_SINGLE: generic_smp_call_function_single_interrupt(); diff --git a/arch/sparc/kernel/smp_32.c b/arch/sparc/kernel/smp_32.c index 91c10fb70858..f95690c167b6 100644 --- a/arch/sparc/kernel/smp_32.c +++ b/arch/sparc/kernel/smp_32.c @@ -125,7 +125,9 @@ struct linux_prom_registers smp_penguin_ctable __cpuinitdata = { 0 }; void smp_send_reschedule(int cpu) { - /* See sparc64 */ + /* + * XXX missing reschedule IPI, see scheduler_ipi() + */ } void smp_send_stop(void) diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c index 3e94a8c23238..9478da7fdb3e 100644 --- a/arch/sparc/kernel/smp_64.c +++ b/arch/sparc/kernel/smp_64.c @@ -1368,6 +1368,7 @@ void smp_send_reschedule(int cpu) void __irq_entry smp_receive_signal_client(int irq, struct pt_regs *regs) { clear_softint(1 << irq); + scheduler_ipi(); } /* This is a nop because we capture all other cpus diff --git a/arch/tile/kernel/smp.c b/arch/tile/kernel/smp.c index a4293102ef81..c52224d5ed45 100644 --- a/arch/tile/kernel/smp.c +++ b/arch/tile/kernel/smp.c @@ -189,12 +189,8 @@ void flush_icache_range(unsigned long start, unsigned long end) /* Called when smp_send_reschedule() triggers IRQ_RESCHEDULE. */ static irqreturn_t handle_reschedule_ipi(int irq, void *token) { - /* - * Nothing to do here; when we return from interrupt, the - * rescheduling will occur there. But do bump the interrupt - * profiler count in the meantime. - */ __get_cpu_var(irq_stat).irq_resched_count++; + scheduler_ipi(); return IRQ_HANDLED; } diff --git a/arch/um/kernel/smp.c b/arch/um/kernel/smp.c index 106bf27e2a9a..eefb107d2d73 100644 --- a/arch/um/kernel/smp.c +++ b/arch/um/kernel/smp.c @@ -173,7 +173,7 @@ void IPI_handler(int cpu) break; case 'R': - set_tsk_need_resched(current); + scheduler_ipi(); break; case 'S': diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c index 513deac7228d..013e7eba83bb 100644 --- a/arch/x86/kernel/smp.c +++ b/arch/x86/kernel/smp.c @@ -194,14 +194,13 @@ static void native_stop_other_cpus(int wait) } /* - * Reschedule call back. Nothing to do, - * all the work is done automatically when - * we return from the interrupt. + * Reschedule call back. */ void smp_reschedule_interrupt(struct pt_regs *regs) { ack_APIC_irq(); inc_irq_stat(irq_resched_count); + scheduler_ipi(); /* * KVM uses this interrupt to force a cpu out of guest mode */ diff --git a/arch/x86/xen/Kconfig b/arch/x86/xen/Kconfig index 1c7121ba18ff..5cc821cb2e09 100644 --- a/arch/x86/xen/Kconfig +++ b/arch/x86/xen/Kconfig @@ -39,6 +39,7 @@ config XEN_MAX_DOMAIN_MEMORY config XEN_SAVE_RESTORE bool depends on XEN + select HIBERNATE_CALLBACKS default y config XEN_DEBUG_FS diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 49dbd78ec3cb..e3c6a06cf725 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -238,6 +238,7 @@ static void xen_cpuid(unsigned int *ax, unsigned int *bx, static __init void xen_init_cpuid_mask(void) { unsigned int ax, bx, cx, dx; + unsigned int xsave_mask; cpuid_leaf1_edx_mask = ~((1 << X86_FEATURE_MCE) | /* disable MCE */ @@ -249,24 +250,16 @@ static __init void xen_init_cpuid_mask(void) cpuid_leaf1_edx_mask &= ~((1 << X86_FEATURE_APIC) | /* disable local APIC */ (1 << X86_FEATURE_ACPI)); /* disable ACPI */ - ax = 1; - cx = 0; xen_cpuid(&ax, &bx, &cx, &dx); - /* cpuid claims we support xsave; try enabling it to see what happens */ - if (cx & (1 << (X86_FEATURE_XSAVE % 32))) { - unsigned long cr4; - - set_in_cr4(X86_CR4_OSXSAVE); - - cr4 = read_cr4(); + xsave_mask = + (1 << (X86_FEATURE_XSAVE % 32)) | + (1 << (X86_FEATURE_OSXSAVE % 32)); - if ((cr4 & X86_CR4_OSXSAVE) == 0) - cpuid_leaf1_ecx_mask &= ~(1 << (X86_FEATURE_XSAVE % 32)); - - clear_in_cr4(X86_CR4_OSXSAVE); - } + /* Xen will set CR4.OSXSAVE if supported and not disabled by force */ + if ((cx & xsave_mask) != xsave_mask) + cpuid_leaf1_ecx_mask &= ~xsave_mask; /* disable XSAVE & OSXSAVE */ } static void xen_set_debugreg(int reg, unsigned long val) diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index c82df6c9c0f0..a991b57f91fe 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -565,13 +565,13 @@ pte_t xen_make_pte_debug(pteval_t pte) if (io_page && (xen_initial_domain() || addr >= ISA_END_ADDRESS)) { other_addr = pfn_to_mfn(addr >> PAGE_SHIFT) << PAGE_SHIFT; - WARN(addr != other_addr, + WARN_ONCE(addr != other_addr, "0x%lx is using VM_IO, but it is 0x%lx!\n", (unsigned long)addr, (unsigned long)other_addr); } else { pteval_t iomap_set = (_pte.pte & PTE_FLAGS_MASK) & _PAGE_IOMAP; other_addr = (_pte.pte & PTE_PFN_MASK); - WARN((addr == other_addr) && (!io_page) && (!iomap_set), + WARN_ONCE((addr == other_addr) && (!io_page) && (!iomap_set), "0x%lx is missing VM_IO (and wasn't fixed)!\n", (unsigned long)addr); } diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c index 30612441ed99..762b46ab14d5 100644 --- a/arch/x86/xen/smp.c +++ b/arch/x86/xen/smp.c @@ -46,13 +46,12 @@ static irqreturn_t xen_call_function_interrupt(int irq, void *dev_id); static irqreturn_t xen_call_function_single_interrupt(int irq, void *dev_id); /* - * Reschedule call back. Nothing to do, - * all the work is done automatically when - * we return from the interrupt. + * Reschedule call back. */ static irqreturn_t xen_reschedule_interrupt(int irq, void *dev_id) { inc_irq_stat(irq_resched_count); + scheduler_ipi(); return IRQ_HANDLED; } diff --git a/drivers/amba/bus.c b/drivers/amba/bus.c index 821040503154..7025593a58c8 100644 --- a/drivers/amba/bus.c +++ b/drivers/amba/bus.c @@ -214,7 +214,7 @@ static int amba_pm_resume_noirq(struct device *dev) #endif /* !CONFIG_SUSPEND */ -#ifdef CONFIG_HIBERNATION +#ifdef CONFIG_HIBERNATE_CALLBACKS static int amba_pm_freeze(struct device *dev) { @@ -352,7 +352,7 @@ static int amba_pm_restore_noirq(struct device *dev) return ret; } -#else /* !CONFIG_HIBERNATION */ +#else /* !CONFIG_HIBERNATE_CALLBACKS */ #define amba_pm_freeze NULL #define amba_pm_thaw NULL @@ -363,7 +363,7 @@ static int amba_pm_restore_noirq(struct device *dev) #define amba_pm_poweroff_noirq NULL #define amba_pm_restore_noirq NULL -#endif /* !CONFIG_HIBERNATION */ +#endif /* !CONFIG_HIBERNATE_CALLBACKS */ #ifdef CONFIG_PM diff --git a/drivers/base/platform.c b/drivers/base/platform.c index f051cfff18af..9e0e4fc24c46 100644 --- a/drivers/base/platform.c +++ b/drivers/base/platform.c @@ -149,6 +149,7 @@ static void platform_device_release(struct device *dev) of_device_node_put(&pa->pdev.dev); kfree(pa->pdev.dev.platform_data); + kfree(pa->pdev.mfd_cell); kfree(pa->pdev.resource); kfree(pa); } @@ -771,7 +772,7 @@ int __weak platform_pm_resume_noirq(struct device *dev) #endif /* !CONFIG_SUSPEND */ -#ifdef CONFIG_HIBERNATION +#ifdef CONFIG_HIBERNATE_CALLBACKS static int platform_pm_freeze(struct device *dev) { @@ -909,7 +910,7 @@ static int platform_pm_restore_noirq(struct device *dev) return ret; } -#else /* !CONFIG_HIBERNATION */ +#else /* !CONFIG_HIBERNATE_CALLBACKS */ #define platform_pm_freeze NULL #define platform_pm_thaw NULL @@ -920,7 +921,7 @@ static int platform_pm_restore_noirq(struct device *dev) #define platform_pm_poweroff_noirq NULL #define platform_pm_restore_noirq NULL -#endif /* !CONFIG_HIBERNATION */ +#endif /* !CONFIG_HIBERNATE_CALLBACKS */ #ifdef CONFIG_PM_RUNTIME diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c index 052dc53eef38..fbc5b6e7c591 100644 --- a/drivers/base/power/main.c +++ b/drivers/base/power/main.c @@ -233,7 +233,7 @@ static int pm_op(struct device *dev, } break; #endif /* CONFIG_SUSPEND */ -#ifdef CONFIG_HIBERNATION +#ifdef CONFIG_HIBERNATE_CALLBACKS case PM_EVENT_FREEZE: case PM_EVENT_QUIESCE: if (ops->freeze) { @@ -260,7 +260,7 @@ static int pm_op(struct device *dev, suspend_report_result(ops->restore, error); } break; -#endif /* CONFIG_HIBERNATION */ +#endif /* CONFIG_HIBERNATE_CALLBACKS */ default: error = -EINVAL; } @@ -308,7 +308,7 @@ static int pm_noirq_op(struct device *dev, } break; #endif /* CONFIG_SUSPEND */ -#ifdef CONFIG_HIBERNATION +#ifdef CONFIG_HIBERNATE_CALLBACKS case PM_EVENT_FREEZE: case PM_EVENT_QUIESCE: if (ops->freeze_noirq) { @@ -335,7 +335,7 @@ static int pm_noirq_op(struct device *dev, suspend_report_result(ops->restore_noirq, error); } break; -#endif /* CONFIG_HIBERNATION */ +#endif /* CONFIG_HIBERNATE_CALLBACKS */ default: error = -EINVAL; } diff --git a/drivers/dma/fsldma.c b/drivers/dma/fsldma.c index 6b396759e7f5..8a781540590c 100644 --- a/drivers/dma/fsldma.c +++ b/drivers/dma/fsldma.c @@ -1448,7 +1448,7 @@ static const struct of_device_id fsldma_of_ids[] = { {} }; -static struct of_platform_driver fsldma_of_driver = { +static struct platform_driver fsldma_of_driver = { .driver = { .name = "fsl-elo-dma", .owner = THIS_MODULE, diff --git a/drivers/gpio/ml_ioh_gpio.c b/drivers/gpio/ml_ioh_gpio.c index 7f6f01a4b145..0a775f7987c2 100644 --- a/drivers/gpio/ml_ioh_gpio.c +++ b/drivers/gpio/ml_ioh_gpio.c @@ -116,6 +116,7 @@ static int ioh_gpio_direction_output(struct gpio_chip *gpio, unsigned nr, reg_val |= (1 << nr); else reg_val &= ~(1 << nr); + iowrite32(reg_val, &chip->reg->regs[chip->ch].po); mutex_unlock(&chip->lock); diff --git a/drivers/gpio/pca953x.c b/drivers/gpio/pca953x.c index 583e92592073..7630ab7b9bec 100644 --- a/drivers/gpio/pca953x.c +++ b/drivers/gpio/pca953x.c @@ -558,7 +558,7 @@ static int __devinit pca953x_probe(struct i2c_client *client, ret = gpiochip_add(&chip->gpio_chip); if (ret) - goto out_failed; + goto out_failed_irq; if (pdata->setup) { ret = pdata->setup(client, chip->gpio_chip.base, @@ -570,8 +570,9 @@ static int __devinit pca953x_probe(struct i2c_client *client, i2c_set_clientdata(client, chip); return 0; -out_failed: +out_failed_irq: pca953x_irq_teardown(chip); +out_failed: kfree(chip->dyn_pdata); kfree(chip); return ret; diff --git a/drivers/gpio/pch_gpio.c b/drivers/gpio/pch_gpio.c index 2c6af8705103..f970a5f3585e 100644 --- a/drivers/gpio/pch_gpio.c +++ b/drivers/gpio/pch_gpio.c @@ -105,6 +105,7 @@ static int pch_gpio_direction_output(struct gpio_chip *gpio, unsigned nr, reg_val |= (1 << nr); else reg_val &= ~(1 << nr); + iowrite32(reg_val, &chip->reg->po); mutex_unlock(&chip->lock); diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig index a6feb78c404c..c58f691ec3ce 100644 --- a/drivers/gpu/drm/Kconfig +++ b/drivers/gpu/drm/Kconfig @@ -96,6 +96,7 @@ config DRM_I915 # i915 depends on ACPI_VIDEO when ACPI is enabled # but for select to work, need to select ACPI_VIDEO's dependencies, ick select BACKLIGHT_CLASS_DEVICE if ACPI + select VIDEO_OUTPUT_CONTROL if ACPI select INPUT if ACPI select ACPI_VIDEO if ACPI select ACPI_BUTTON if ACPI diff --git a/drivers/gpu/drm/nouveau/nouveau_bios.c b/drivers/gpu/drm/nouveau/nouveau_bios.c index 8314a49b6b9a..90aef64b76f2 100644 --- a/drivers/gpu/drm/nouveau/nouveau_bios.c +++ b/drivers/gpu/drm/nouveau/nouveau_bios.c @@ -269,7 +269,7 @@ struct init_tbl_entry { int (*handler)(struct nvbios *, uint16_t, struct init_exec *); }; -static int parse_init_table(struct nvbios *, unsigned int, struct init_exec *); +static int parse_init_table(struct nvbios *, uint16_t, struct init_exec *); #define MACRO_INDEX_SIZE 2 #define MACRO_SIZE 8 @@ -2011,6 +2011,27 @@ init_sub_direct(struct nvbios *bios, uint16_t offset, struct init_exec *iexec) } static int +init_jump(struct nvbios *bios, uint16_t offset, struct init_exec *iexec) +{ + /* + * INIT_JUMP opcode: 0x5C ('\') + * + * offset (8 bit): opcode + * offset + 1 (16 bit): offset (in bios) + * + * Continue execution of init table from 'offset' + */ + + uint16_t jmp_offset = ROM16(bios->data[offset + 1]); + + if (!iexec->execute) + return 3; + + BIOSLOG(bios, "0x%04X: Jump to 0x%04X\n", offset, jmp_offset); + return jmp_offset - offset; +} + +static int init_i2c_if(struct nvbios *bios, uint16_t offset, struct init_exec *iexec) { /* @@ -3659,6 +3680,7 @@ static struct init_tbl_entry itbl_entry[] = { { "INIT_ZM_REG_SEQUENCE" , 0x58, init_zm_reg_sequence }, /* INIT_INDIRECT_REG (0x5A, 7, 0, 0) removed due to no example of use */ { "INIT_SUB_DIRECT" , 0x5B, init_sub_direct }, + { "INIT_JUMP" , 0x5C, init_jump }, { "INIT_I2C_IF" , 0x5E, init_i2c_if }, { "INIT_COPY_NV_REG" , 0x5F, init_copy_nv_reg }, { "INIT_ZM_INDEX_IO" , 0x62, init_zm_index_io }, @@ -3700,8 +3722,7 @@ static struct init_tbl_entry itbl_entry[] = { #define MAX_TABLE_OPS 1000 static int -parse_init_table(struct nvbios *bios, unsigned int offset, - struct init_exec *iexec) +parse_init_table(struct nvbios *bios, uint16_t offset, struct init_exec *iexec) { /* * Parses all commands in an init table. @@ -6333,6 +6354,32 @@ apply_dcb_encoder_quirks(struct drm_device *dev, int idx, u32 *conn, u32 *conf) } } + /* XFX GT-240X-YA + * + * So many things wrong here, replace the entire encoder table.. + */ + if (nv_match_device(dev, 0x0ca3, 0x1682, 0x3003)) { + if (idx == 0) { + *conn = 0x02001300; /* VGA, connector 1 */ + *conf = 0x00000028; + } else + if (idx == 1) { + *conn = 0x01010312; /* DVI, connector 0 */ + *conf = 0x00020030; + } else + if (idx == 2) { + *conn = 0x01010310; /* VGA, connector 0 */ + *conf = 0x00000028; + } else + if (idx == 3) { + *conn = 0x02022362; /* HDMI, connector 2 */ + *conf = 0x00020010; + } else { + *conn = 0x0000000e; /* EOL */ + *conf = 0x00000000; + } + } + return true; } diff --git a/drivers/gpu/drm/nouveau/nouveau_drv.h b/drivers/gpu/drm/nouveau/nouveau_drv.h index 57e5302503db..856d56a98d1e 100644 --- a/drivers/gpu/drm/nouveau/nouveau_drv.h +++ b/drivers/gpu/drm/nouveau/nouveau_drv.h @@ -1190,7 +1190,7 @@ extern int nv50_graph_load_context(struct nouveau_channel *); extern int nv50_graph_unload_context(struct drm_device *); extern int nv50_grctx_init(struct nouveau_grctx *); extern void nv50_graph_tlb_flush(struct drm_device *dev); -extern void nv86_graph_tlb_flush(struct drm_device *dev); +extern void nv84_graph_tlb_flush(struct drm_device *dev); extern struct nouveau_enum nv50_data_error_names[]; /* nvc0_graph.c */ diff --git a/drivers/gpu/drm/nouveau/nouveau_mem.c b/drivers/gpu/drm/nouveau/nouveau_mem.c index 2683377f4131..78f467fe30be 100644 --- a/drivers/gpu/drm/nouveau/nouveau_mem.c +++ b/drivers/gpu/drm/nouveau/nouveau_mem.c @@ -552,6 +552,7 @@ nouveau_mem_timing_init(struct drm_device *dev) u8 tRC; /* Byte 9 */ u8 tUNK_10, tUNK_11, tUNK_12, tUNK_13, tUNK_14; u8 tUNK_18, tUNK_19, tUNK_20, tUNK_21; + u8 magic_number = 0; /* Yeah... sorry*/ u8 *mem = NULL, *entry; int i, recordlen, entries; @@ -596,6 +597,12 @@ nouveau_mem_timing_init(struct drm_device *dev) if (!memtimings->timing) return; + /* Get "some number" from the timing reg for NV_40 + * Used in calculations later */ + if(dev_priv->card_type == NV_40) { + magic_number = (nv_rd32(dev,0x100228) & 0x0f000000) >> 24; + } + entry = mem + mem[1]; for (i = 0; i < entries; i++, entry += recordlen) { struct nouveau_pm_memtiming *timing = &pm->memtimings.timing[i]; @@ -635,36 +642,51 @@ nouveau_mem_timing_init(struct drm_device *dev) /* XXX: I don't trust the -1's and +1's... they must come * from somewhere! */ - timing->reg_100224 = ((tUNK_0 + tUNK_19 + 1) << 24 | + timing->reg_100224 = (tUNK_0 + tUNK_19 + 1 + magic_number) << 24 | tUNK_18 << 16 | - (tUNK_1 + tUNK_19 + 1) << 8 | - (tUNK_2 - 1)); + (tUNK_1 + tUNK_19 + 1 + magic_number) << 8; + if(dev_priv->chipset == 0xa8) { + timing->reg_100224 |= (tUNK_2 - 1); + } else { + timing->reg_100224 |= (tUNK_2 + 2 - magic_number); + } timing->reg_100228 = (tUNK_12 << 16 | tUNK_11 << 8 | tUNK_10); - if(recordlen > 19) { - timing->reg_100228 += (tUNK_19 - 1) << 24; - }/* I cannot back-up this else-statement right now - else { - timing->reg_100228 += tUNK_12 << 24; - }*/ - - /* XXX: reg_10022c */ - timing->reg_10022c = tUNK_2 - 1; - - timing->reg_100230 = (tUNK_20 << 24 | tUNK_21 << 16 | - tUNK_13 << 8 | tUNK_13); - - /* XXX: +6? */ - timing->reg_100234 = (tRAS << 24 | (tUNK_19 + 6) << 8 | tRC); - timing->reg_100234 += max(tUNK_10,tUNK_11) << 16; - - /* XXX; reg_100238, reg_10023c - * reg: 0x00?????? - * reg_10023c: - * 0 for pre-NV50 cards - * 0x????0202 for NV50+ cards (empirical evidence) */ - if(dev_priv->card_type >= NV_50) { + if(dev_priv->chipset >= 0xa3 && dev_priv->chipset < 0xaa) { + timing->reg_100228 |= (tUNK_19 - 1) << 24; + } + + if(dev_priv->card_type == NV_40) { + /* NV40: don't know what the rest of the regs are.. + * And don't need to know either */ + timing->reg_100228 |= 0x20200000 | magic_number << 24; + } else if(dev_priv->card_type >= NV_50) { + /* XXX: reg_10022c */ + timing->reg_10022c = tUNK_2 - 1; + + timing->reg_100230 = (tUNK_20 << 24 | tUNK_21 << 16 | + tUNK_13 << 8 | tUNK_13); + + timing->reg_100234 = (tRAS << 24 | tRC); + timing->reg_100234 += max(tUNK_10,tUNK_11) << 16; + + if(dev_priv->chipset < 0xa3) { + timing->reg_100234 |= (tUNK_2 + 2) << 8; + } else { + /* XXX: +6? */ + timing->reg_100234 |= (tUNK_19 + 6) << 8; + } + + /* XXX; reg_100238, reg_10023c + * reg_100238: 0x00?????? + * reg_10023c: 0x!!??0202 for NV50+ cards (empirical evidence) */ timing->reg_10023c = 0x202; + if(dev_priv->chipset < 0xa3) { + timing->reg_10023c |= 0x4000000 | (tUNK_2 - 1) << 16; + } else { + /* currently unknown + * 10023c seen as 06xxxxxx, 0bxxxxxx or 0fxxxxxx */ + } } NV_DEBUG(dev, "Entry %d: 220: %08x %08x %08x %08x\n", i, @@ -675,7 +697,7 @@ nouveau_mem_timing_init(struct drm_device *dev) timing->reg_100238, timing->reg_10023c); } - memtimings->nr_timing = entries; + memtimings->nr_timing = entries; memtimings->supported = true; } diff --git a/drivers/gpu/drm/nouveau/nouveau_perf.c b/drivers/gpu/drm/nouveau/nouveau_perf.c index ac62a1b8c4fc..670e3cb697ec 100644 --- a/drivers/gpu/drm/nouveau/nouveau_perf.c +++ b/drivers/gpu/drm/nouveau/nouveau_perf.c @@ -134,7 +134,7 @@ nouveau_perf_init(struct drm_device *dev) case 0x13: case 0x15: perflvl->fanspeed = entry[55]; - perflvl->voltage = entry[56]; + perflvl->voltage = (recordlen > 56) ? entry[56] : 0; perflvl->core = ROM32(entry[1]) * 10; perflvl->memory = ROM32(entry[5]) * 20; break; diff --git a/drivers/gpu/drm/nouveau/nouveau_state.c b/drivers/gpu/drm/nouveau/nouveau_state.c index 5bb2859001e2..6e2b1a6caa2d 100644 --- a/drivers/gpu/drm/nouveau/nouveau_state.c +++ b/drivers/gpu/drm/nouveau/nouveau_state.c @@ -376,15 +376,11 @@ static int nouveau_init_engine_ptrs(struct drm_device *dev) engine->graph.destroy_context = nv50_graph_destroy_context; engine->graph.load_context = nv50_graph_load_context; engine->graph.unload_context = nv50_graph_unload_context; - if (dev_priv->chipset != 0x86) + if (dev_priv->chipset == 0x50 || + dev_priv->chipset == 0xac) engine->graph.tlb_flush = nv50_graph_tlb_flush; - else { - /* from what i can see nvidia do this on every - * pre-NVA3 board except NVAC, but, we've only - * ever seen problems on NV86 - */ - engine->graph.tlb_flush = nv86_graph_tlb_flush; - } + else + engine->graph.tlb_flush = nv84_graph_tlb_flush; engine->fifo.channels = 128; engine->fifo.init = nv50_fifo_init; engine->fifo.takedown = nv50_fifo_takedown; diff --git a/drivers/gpu/drm/nouveau/nv04_dfp.c b/drivers/gpu/drm/nouveau/nv04_dfp.c index c82db37d9f41..12098bf839c4 100644 --- a/drivers/gpu/drm/nouveau/nv04_dfp.c +++ b/drivers/gpu/drm/nouveau/nv04_dfp.c @@ -581,12 +581,13 @@ static void nv04_dfp_restore(struct drm_encoder *encoder) int head = nv_encoder->restore.head; if (nv_encoder->dcb->type == OUTPUT_LVDS) { - struct drm_display_mode *native_mode = nouveau_encoder_connector_get(nv_encoder)->native_mode; - if (native_mode) - call_lvds_script(dev, nv_encoder->dcb, head, LVDS_PANEL_ON, - native_mode->clock); - else - NV_ERROR(dev, "Not restoring LVDS without native mode\n"); + struct nouveau_connector *connector = + nouveau_encoder_connector_get(nv_encoder); + + if (connector && connector->native_mode) + call_lvds_script(dev, nv_encoder->dcb, head, + LVDS_PANEL_ON, + connector->native_mode->clock); } else if (nv_encoder->dcb->type == OUTPUT_TMDS) { int clock = nouveau_hw_pllvals_to_clk diff --git a/drivers/gpu/drm/nouveau/nv50_crtc.c b/drivers/gpu/drm/nouveau/nv50_crtc.c index 2b9984027f41..a19ccaa025b3 100644 --- a/drivers/gpu/drm/nouveau/nv50_crtc.c +++ b/drivers/gpu/drm/nouveau/nv50_crtc.c @@ -469,9 +469,6 @@ nv50_crtc_wait_complete(struct drm_crtc *crtc) start = ptimer->read(dev); do { - nv_wr32(dev, 0x61002c, 0x370); - nv_wr32(dev, 0x000140, 1); - if (nv_ro32(disp->ntfy, 0x000)) return 0; } while (ptimer->read(dev) - start < 2000000000ULL); diff --git a/drivers/gpu/drm/nouveau/nv50_evo.c b/drivers/gpu/drm/nouveau/nv50_evo.c index a2cfaa691e9b..c8e83c1a4de8 100644 --- a/drivers/gpu/drm/nouveau/nv50_evo.c +++ b/drivers/gpu/drm/nouveau/nv50_evo.c @@ -186,6 +186,7 @@ nv50_evo_channel_init(struct nouveau_channel *evo) nv_mask(dev, 0x610028, 0x00000000, 0x00010001 << id); evo->dma.max = (4096/4) - 2; + evo->dma.max &= ~7; evo->dma.put = 0; evo->dma.cur = evo->dma.put; evo->dma.free = evo->dma.max - evo->dma.cur; diff --git a/drivers/gpu/drm/nouveau/nv50_graph.c b/drivers/gpu/drm/nouveau/nv50_graph.c index 8675b00caf18..b02a5b1e7d37 100644 --- a/drivers/gpu/drm/nouveau/nv50_graph.c +++ b/drivers/gpu/drm/nouveau/nv50_graph.c @@ -503,7 +503,7 @@ nv50_graph_tlb_flush(struct drm_device *dev) } void -nv86_graph_tlb_flush(struct drm_device *dev) +nv84_graph_tlb_flush(struct drm_device *dev) { struct drm_nouveau_private *dev_priv = dev->dev_private; struct nouveau_timer_engine *ptimer = &dev_priv->engine.timer; diff --git a/drivers/gpu/drm/nouveau/nvc0_vm.c b/drivers/gpu/drm/nouveau/nvc0_vm.c index 69af0ba7edd3..a0a2a0277f73 100644 --- a/drivers/gpu/drm/nouveau/nvc0_vm.c +++ b/drivers/gpu/drm/nouveau/nvc0_vm.c @@ -104,20 +104,26 @@ nvc0_vm_flush(struct nouveau_vm *vm) struct nouveau_instmem_engine *pinstmem = &dev_priv->engine.instmem; struct drm_device *dev = vm->dev; struct nouveau_vm_pgd *vpgd; - u32 r100c80, engine; + u32 engine = (dev_priv->chan_vm == vm) ? 1 : 5; pinstmem->flush(vm->dev); - if (vm == dev_priv->chan_vm) - engine = 1; - else - engine = 5; - + spin_lock(&dev_priv->ramin_lock); list_for_each_entry(vpgd, &vm->pgd_list, head) { - r100c80 = nv_rd32(dev, 0x100c80); + /* looks like maybe a "free flush slots" counter, the + * faster you write to 0x100cbc to more it decreases + */ + if (!nv_wait_ne(dev, 0x100c80, 0x00ff0000, 0x00000000)) { + NV_ERROR(dev, "vm timeout 0: 0x%08x %d\n", + nv_rd32(dev, 0x100c80), engine); + } nv_wr32(dev, 0x100cb8, vpgd->obj->vinst >> 8); nv_wr32(dev, 0x100cbc, 0x80000000 | engine); - if (!nv_wait(dev, 0x100c80, 0xffffffff, r100c80)) - NV_ERROR(dev, "vm flush timeout eng %d\n", engine); + /* wait for flush to be queued? */ + if (!nv_wait(dev, 0x100c80, 0x00008000, 0x00008000)) { + NV_ERROR(dev, "vm timeout 1: 0x%08x %d\n", + nv_rd32(dev, 0x100c80), engine); + } } + spin_unlock(&dev_priv->ramin_lock); } diff --git a/drivers/gpu/drm/radeon/atom.c b/drivers/gpu/drm/radeon/atom.c index 258fa5e7a2d9..d71d375149f8 100644 --- a/drivers/gpu/drm/radeon/atom.c +++ b/drivers/gpu/drm/radeon/atom.c @@ -32,6 +32,7 @@ #include "atom.h" #include "atom-names.h" #include "atom-bits.h" +#include "radeon.h" #define ATOM_COND_ABOVE 0 #define ATOM_COND_ABOVEOREQUAL 1 @@ -101,7 +102,9 @@ static void debug_print_spaces(int n) static uint32_t atom_iio_execute(struct atom_context *ctx, int base, uint32_t index, uint32_t data) { + struct radeon_device *rdev = ctx->card->dev->dev_private; uint32_t temp = 0xCDCDCDCD; + while (1) switch (CU8(base)) { case ATOM_IIO_NOP: @@ -112,7 +115,8 @@ static uint32_t atom_iio_execute(struct atom_context *ctx, int base, base += 3; break; case ATOM_IIO_WRITE: - (void)ctx->card->ioreg_read(ctx->card, CU16(base + 1)); + if (rdev->family == CHIP_RV515) + (void)ctx->card->ioreg_read(ctx->card, CU16(base + 1)); ctx->card->ioreg_write(ctx->card, CU16(base + 1), temp); base += 3; break; diff --git a/drivers/gpu/drm/radeon/atombios_crtc.c b/drivers/gpu/drm/radeon/atombios_crtc.c index b41ec59c7100..9d516a8c4dfa 100644 --- a/drivers/gpu/drm/radeon/atombios_crtc.c +++ b/drivers/gpu/drm/radeon/atombios_crtc.c @@ -531,6 +531,12 @@ static u32 atombios_adjust_pll(struct drm_crtc *crtc, pll->flags |= RADEON_PLL_PREFER_HIGH_FB_DIV; else pll->flags |= RADEON_PLL_PREFER_LOW_REF_DIV; + + if ((rdev->family == CHIP_R600) || + (rdev->family == CHIP_RV610) || + (rdev->family == CHIP_RV630) || + (rdev->family == CHIP_RV670)) + pll->flags |= RADEON_PLL_PREFER_MINM_OVER_MAXP; } else { pll->flags |= RADEON_PLL_LEGACY; diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c index 0b0cc74c08c0..3453910ee0f3 100644 --- a/drivers/gpu/drm/radeon/evergreen.c +++ b/drivers/gpu/drm/radeon/evergreen.c @@ -120,11 +120,16 @@ void evergreen_pm_misc(struct radeon_device *rdev) struct radeon_power_state *ps = &rdev->pm.power_state[req_ps_idx]; struct radeon_voltage *voltage = &ps->clock_info[req_cm_idx].voltage; - if ((voltage->type == VOLTAGE_SW) && voltage->voltage) { - if (voltage->voltage != rdev->pm.current_vddc) { - radeon_atom_set_voltage(rdev, voltage->voltage); + if (voltage->type == VOLTAGE_SW) { + if (voltage->voltage && (voltage->voltage != rdev->pm.current_vddc)) { + radeon_atom_set_voltage(rdev, voltage->voltage, SET_VOLTAGE_TYPE_ASIC_VDDC); rdev->pm.current_vddc = voltage->voltage; - DRM_DEBUG("Setting: v: %d\n", voltage->voltage); + DRM_DEBUG("Setting: vddc: %d\n", voltage->voltage); + } + if (voltage->vddci && (voltage->vddci != rdev->pm.current_vddci)) { + radeon_atom_set_voltage(rdev, voltage->vddci, SET_VOLTAGE_TYPE_ASIC_VDDCI); + rdev->pm.current_vddci = voltage->vddci; + DRM_DEBUG("Setting: vddci: %d\n", voltage->vddci); } } } @@ -3036,9 +3041,6 @@ int evergreen_init(struct radeon_device *rdev) { int r; - r = radeon_dummy_page_init(rdev); - if (r) - return r; /* This don't do much */ r = radeon_gem_init(rdev); if (r) @@ -3150,7 +3152,6 @@ void evergreen_fini(struct radeon_device *rdev) radeon_atombios_fini(rdev); kfree(rdev->bios); rdev->bios = NULL; - radeon_dummy_page_fini(rdev); } static void evergreen_pcie_gen2_enable(struct radeon_device *rdev) diff --git a/drivers/gpu/drm/radeon/r600.c b/drivers/gpu/drm/radeon/r600.c index be271c42de4d..15d58292677a 100644 --- a/drivers/gpu/drm/radeon/r600.c +++ b/drivers/gpu/drm/radeon/r600.c @@ -587,7 +587,7 @@ void r600_pm_misc(struct radeon_device *rdev) if ((voltage->type == VOLTAGE_SW) && voltage->voltage) { if (voltage->voltage != rdev->pm.current_vddc) { - radeon_atom_set_voltage(rdev, voltage->voltage); + radeon_atom_set_voltage(rdev, voltage->voltage, SET_VOLTAGE_TYPE_ASIC_VDDC); rdev->pm.current_vddc = voltage->voltage; DRM_DEBUG_DRIVER("Setting: v: %d\n", voltage->voltage); } @@ -2509,9 +2509,6 @@ int r600_init(struct radeon_device *rdev) { int r; - r = radeon_dummy_page_init(rdev); - if (r) - return r; if (r600_debugfs_mc_info_init(rdev)) { DRM_ERROR("Failed to register debugfs file for mc !\n"); } @@ -2625,7 +2622,6 @@ void r600_fini(struct radeon_device *rdev) radeon_atombios_fini(rdev); kfree(rdev->bios); rdev->bios = NULL; - radeon_dummy_page_fini(rdev); } diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h index 93f536594c73..ba643b576054 100644 --- a/drivers/gpu/drm/radeon/radeon.h +++ b/drivers/gpu/drm/radeon/radeon.h @@ -177,7 +177,7 @@ void radeon_pm_suspend(struct radeon_device *rdev); void radeon_pm_resume(struct radeon_device *rdev); void radeon_combios_get_power_modes(struct radeon_device *rdev); void radeon_atombios_get_power_modes(struct radeon_device *rdev); -void radeon_atom_set_voltage(struct radeon_device *rdev, u16 level); +void radeon_atom_set_voltage(struct radeon_device *rdev, u16 voltage_level, u8 voltage_type); void rs690_pm_info(struct radeon_device *rdev); extern int rv6xx_get_temp(struct radeon_device *rdev); extern int rv770_get_temp(struct radeon_device *rdev); @@ -767,7 +767,9 @@ struct radeon_voltage { u8 vddci_id; /* index into vddci voltage table */ bool vddci_enabled; /* r6xx+ sw */ - u32 voltage; + u16 voltage; + /* evergreen+ vddci */ + u16 vddci; }; /* clock mode flags */ @@ -835,10 +837,12 @@ struct radeon_pm { int default_power_state_index; u32 current_sclk; u32 current_mclk; - u32 current_vddc; + u16 current_vddc; + u16 current_vddci; u32 default_sclk; u32 default_mclk; - u32 default_vddc; + u16 default_vddc; + u16 default_vddci; struct radeon_i2c_chan *i2c_bus; /* selected pm method */ enum radeon_pm_method pm_method; diff --git a/drivers/gpu/drm/radeon/radeon_asic.c b/drivers/gpu/drm/radeon/radeon_asic.c index eb888ee5f674..ca576191d058 100644 --- a/drivers/gpu/drm/radeon/radeon_asic.c +++ b/drivers/gpu/drm/radeon/radeon_asic.c @@ -94,7 +94,7 @@ static void radeon_register_accessor_init(struct radeon_device *rdev) rdev->mc_rreg = &rs600_mc_rreg; rdev->mc_wreg = &rs600_mc_wreg; } - if ((rdev->family >= CHIP_R600) && (rdev->family <= CHIP_HEMLOCK)) { + if (rdev->family >= CHIP_R600) { rdev->pciep_rreg = &r600_pciep_rreg; rdev->pciep_wreg = &r600_pciep_wreg; } diff --git a/drivers/gpu/drm/radeon/radeon_atombios.c b/drivers/gpu/drm/radeon/radeon_atombios.c index 99768d9d91da..f5d12fb103fa 100644 --- a/drivers/gpu/drm/radeon/radeon_atombios.c +++ b/drivers/gpu/drm/radeon/radeon_atombios.c @@ -2176,24 +2176,27 @@ static void radeon_atombios_add_pplib_thermal_controller(struct radeon_device *r } } -static u16 radeon_atombios_get_default_vddc(struct radeon_device *rdev) +static void radeon_atombios_get_default_voltages(struct radeon_device *rdev, + u16 *vddc, u16 *vddci) { struct radeon_mode_info *mode_info = &rdev->mode_info; int index = GetIndexIntoMasterTable(DATA, FirmwareInfo); u8 frev, crev; u16 data_offset; union firmware_info *firmware_info; - u16 vddc = 0; + + *vddc = 0; + *vddci = 0; if (atom_parse_data_header(mode_info->atom_context, index, NULL, &frev, &crev, &data_offset)) { firmware_info = (union firmware_info *)(mode_info->atom_context->bios + data_offset); - vddc = le16_to_cpu(firmware_info->info_14.usBootUpVDDCVoltage); + *vddc = le16_to_cpu(firmware_info->info_14.usBootUpVDDCVoltage); + if ((frev == 2) && (crev >= 2)) + *vddci = le16_to_cpu(firmware_info->info_22.usBootUpVDDCIVoltage); } - - return vddc; } static void radeon_atombios_parse_pplib_non_clock_info(struct radeon_device *rdev, @@ -2203,7 +2206,9 @@ static void radeon_atombios_parse_pplib_non_clock_info(struct radeon_device *rde int j; u32 misc = le32_to_cpu(non_clock_info->ulCapsAndSettings); u32 misc2 = le16_to_cpu(non_clock_info->usClassification); - u16 vddc = radeon_atombios_get_default_vddc(rdev); + u16 vddc, vddci; + + radeon_atombios_get_default_voltages(rdev, &vddc, &vddci); rdev->pm.power_state[state_index].misc = misc; rdev->pm.power_state[state_index].misc2 = misc2; @@ -2244,6 +2249,7 @@ static void radeon_atombios_parse_pplib_non_clock_info(struct radeon_device *rde rdev->pm.default_sclk = rdev->pm.power_state[state_index].clock_info[0].sclk; rdev->pm.default_mclk = rdev->pm.power_state[state_index].clock_info[0].mclk; rdev->pm.default_vddc = rdev->pm.power_state[state_index].clock_info[0].voltage.voltage; + rdev->pm.default_vddci = rdev->pm.power_state[state_index].clock_info[0].voltage.vddci; } else { /* patch the table values with the default slck/mclk from firmware info */ for (j = 0; j < mode_index; j++) { @@ -2286,6 +2292,8 @@ static bool radeon_atombios_parse_pplib_clock_info(struct radeon_device *rdev, VOLTAGE_SW; rdev->pm.power_state[state_index].clock_info[mode_index].voltage.voltage = le16_to_cpu(clock_info->evergreen.usVDDC); + rdev->pm.power_state[state_index].clock_info[mode_index].voltage.vddci = + le16_to_cpu(clock_info->evergreen.usVDDCI); } else { sclk = le16_to_cpu(clock_info->r600.usEngineClockLow); sclk |= clock_info->r600.ucEngineClockHigh << 16; @@ -2577,25 +2585,25 @@ union set_voltage { struct _SET_VOLTAGE_PARAMETERS_V2 v2; }; -void radeon_atom_set_voltage(struct radeon_device *rdev, u16 level) +void radeon_atom_set_voltage(struct radeon_device *rdev, u16 voltage_level, u8 voltage_type) { union set_voltage args; int index = GetIndexIntoMasterTable(COMMAND, SetVoltage); - u8 frev, crev, volt_index = level; + u8 frev, crev, volt_index = voltage_level; if (!atom_parse_cmd_header(rdev->mode_info.atom_context, index, &frev, &crev)) return; switch (crev) { case 1: - args.v1.ucVoltageType = SET_VOLTAGE_TYPE_ASIC_VDDC; + args.v1.ucVoltageType = voltage_type; args.v1.ucVoltageMode = SET_ASIC_VOLTAGE_MODE_ALL_SOURCE; args.v1.ucVoltageIndex = volt_index; break; case 2: - args.v2.ucVoltageType = SET_VOLTAGE_TYPE_ASIC_VDDC; + args.v2.ucVoltageType = voltage_type; args.v2.ucVoltageMode = SET_ASIC_VOLTAGE_MODE_SET_VOLTAGE; - args.v2.usVoltageLevel = cpu_to_le16(level); + args.v2.usVoltageLevel = cpu_to_le16(voltage_level); break; default: DRM_ERROR("Unknown table version %d, %d\n", frev, crev); diff --git a/drivers/gpu/drm/radeon/radeon_fence.c b/drivers/gpu/drm/radeon/radeon_fence.c index 9e59868d354e..bbcd1dd7bac0 100644 --- a/drivers/gpu/drm/radeon/radeon_fence.c +++ b/drivers/gpu/drm/radeon/radeon_fence.c @@ -79,7 +79,7 @@ static bool radeon_fence_poll_locked(struct radeon_device *rdev) scratch_index = R600_WB_EVENT_OFFSET + rdev->fence_drv.scratch_reg - rdev->scratch.reg_base; else scratch_index = RADEON_WB_SCRATCH_OFFSET + rdev->fence_drv.scratch_reg - rdev->scratch.reg_base; - seq = rdev->wb.wb[scratch_index/4]; + seq = le32_to_cpu(rdev->wb.wb[scratch_index/4]); } else seq = RREG32(rdev->fence_drv.scratch_reg); if (seq != rdev->fence_drv.last_seq) { diff --git a/drivers/gpu/drm/radeon/radeon_gart.c b/drivers/gpu/drm/radeon/radeon_gart.c index f0534ef2f331..8a955bbdb608 100644 --- a/drivers/gpu/drm/radeon/radeon_gart.c +++ b/drivers/gpu/drm/radeon/radeon_gart.c @@ -285,4 +285,6 @@ void radeon_gart_fini(struct radeon_device *rdev) rdev->gart.pages = NULL; rdev->gart.pages_addr = NULL; rdev->gart.ttm_alloced = NULL; + + radeon_dummy_page_fini(rdev); } diff --git a/drivers/gpu/drm/radeon/radeon_i2c.c b/drivers/gpu/drm/radeon/radeon_i2c.c index ded2a45bc95c..ccbabf734a61 100644 --- a/drivers/gpu/drm/radeon/radeon_i2c.c +++ b/drivers/gpu/drm/radeon/radeon_i2c.c @@ -1062,7 +1062,7 @@ void radeon_i2c_get_byte(struct radeon_i2c_chan *i2c_bus, *val = in_buf[0]; DRM_DEBUG("val = 0x%02x\n", *val); } else { - DRM_ERROR("i2c 0x%02x 0x%02x read failed\n", + DRM_DEBUG("i2c 0x%02x 0x%02x read failed\n", addr, *val); } } @@ -1084,7 +1084,7 @@ void radeon_i2c_put_byte(struct radeon_i2c_chan *i2c_bus, out_buf[1] = val; if (i2c_transfer(&i2c_bus->adapter, &msg, 1) != 1) - DRM_ERROR("i2c 0x%02x 0x%02x write failed\n", + DRM_DEBUG("i2c 0x%02x 0x%02x write failed\n", addr, val); } diff --git a/drivers/gpu/drm/radeon/radeon_legacy_encoders.c b/drivers/gpu/drm/radeon/radeon_legacy_encoders.c index 5b54268ed6b2..2f46e0c8df53 100644 --- a/drivers/gpu/drm/radeon/radeon_legacy_encoders.c +++ b/drivers/gpu/drm/radeon/radeon_legacy_encoders.c @@ -269,7 +269,7 @@ static const struct drm_encoder_helper_funcs radeon_legacy_lvds_helper_funcs = { .disable = radeon_legacy_encoder_disable, }; -#ifdef CONFIG_BACKLIGHT_CLASS_DEVICE +#if defined(CONFIG_BACKLIGHT_CLASS_DEVICE) || defined(CONFIG_BACKLIGHT_CLASS_DEVICE_MODULE) #define MAX_RADEON_LEVEL 0xFF diff --git a/drivers/gpu/drm/radeon/radeon_pm.c b/drivers/gpu/drm/radeon/radeon_pm.c index 08de669e025a..86eda1ea94df 100644 --- a/drivers/gpu/drm/radeon/radeon_pm.c +++ b/drivers/gpu/drm/radeon/radeon_pm.c @@ -23,6 +23,7 @@ #include "drmP.h" #include "radeon.h" #include "avivod.h" +#include "atom.h" #ifdef CONFIG_ACPI #include <linux/acpi.h> #endif @@ -535,7 +536,11 @@ void radeon_pm_resume(struct radeon_device *rdev) /* set up the default clocks if the MC ucode is loaded */ if (ASIC_IS_DCE5(rdev) && rdev->mc_fw) { if (rdev->pm.default_vddc) - radeon_atom_set_voltage(rdev, rdev->pm.default_vddc); + radeon_atom_set_voltage(rdev, rdev->pm.default_vddc, + SET_VOLTAGE_TYPE_ASIC_VDDC); + if (rdev->pm.default_vddci) + radeon_atom_set_voltage(rdev, rdev->pm.default_vddci, + SET_VOLTAGE_TYPE_ASIC_VDDCI); if (rdev->pm.default_sclk) radeon_set_engine_clock(rdev, rdev->pm.default_sclk); if (rdev->pm.default_mclk) @@ -548,6 +553,7 @@ void radeon_pm_resume(struct radeon_device *rdev) rdev->pm.current_sclk = rdev->pm.default_sclk; rdev->pm.current_mclk = rdev->pm.default_mclk; rdev->pm.current_vddc = rdev->pm.power_state[rdev->pm.default_power_state_index].clock_info[0].voltage.voltage; + rdev->pm.current_vddci = rdev->pm.power_state[rdev->pm.default_power_state_index].clock_info[0].voltage.vddci; if (rdev->pm.pm_method == PM_METHOD_DYNPM && rdev->pm.dynpm_state == DYNPM_STATE_SUSPENDED) { rdev->pm.dynpm_state = DYNPM_STATE_ACTIVE; @@ -585,7 +591,8 @@ int radeon_pm_init(struct radeon_device *rdev) /* set up the default clocks if the MC ucode is loaded */ if (ASIC_IS_DCE5(rdev) && rdev->mc_fw) { if (rdev->pm.default_vddc) - radeon_atom_set_voltage(rdev, rdev->pm.default_vddc); + radeon_atom_set_voltage(rdev, rdev->pm.default_vddc, + SET_VOLTAGE_TYPE_ASIC_VDDC); if (rdev->pm.default_sclk) radeon_set_engine_clock(rdev, rdev->pm.default_sclk); if (rdev->pm.default_mclk) diff --git a/drivers/gpu/drm/radeon/radeon_ring.c b/drivers/gpu/drm/radeon/radeon_ring.c index bbc9cd823334..c6776e48fdde 100644 --- a/drivers/gpu/drm/radeon/radeon_ring.c +++ b/drivers/gpu/drm/radeon/radeon_ring.c @@ -248,7 +248,7 @@ void radeon_ib_pool_fini(struct radeon_device *rdev) void radeon_ring_free_size(struct radeon_device *rdev) { if (rdev->wb.enabled) - rdev->cp.rptr = rdev->wb.wb[RADEON_WB_CP_RPTR_OFFSET/4]; + rdev->cp.rptr = le32_to_cpu(rdev->wb.wb[RADEON_WB_CP_RPTR_OFFSET/4]); else { if (rdev->family >= CHIP_R600) rdev->cp.rptr = RREG32(R600_CP_RB_RPTR); diff --git a/drivers/gpu/drm/radeon/rs600.c b/drivers/gpu/drm/radeon/rs600.c index 876cebc4b8ba..6e3b11e5abbe 100644 --- a/drivers/gpu/drm/radeon/rs600.c +++ b/drivers/gpu/drm/radeon/rs600.c @@ -114,7 +114,7 @@ void rs600_pm_misc(struct radeon_device *rdev) udelay(voltage->delay); } } else if (voltage->type == VOLTAGE_VDDC) - radeon_atom_set_voltage(rdev, voltage->vddc_id); + radeon_atom_set_voltage(rdev, voltage->vddc_id, SET_VOLTAGE_TYPE_ASIC_VDDC); dyn_pwrmgt_sclk_length = RREG32_PLL(DYN_PWRMGT_SCLK_LENGTH); dyn_pwrmgt_sclk_length &= ~REDUCED_POWER_SCLK_HILEN(0xf); diff --git a/drivers/gpu/drm/radeon/rv770.c b/drivers/gpu/drm/radeon/rv770.c index b974ac7df8df..ef8a5babe9f7 100644 --- a/drivers/gpu/drm/radeon/rv770.c +++ b/drivers/gpu/drm/radeon/rv770.c @@ -106,7 +106,7 @@ void rv770_pm_misc(struct radeon_device *rdev) if ((voltage->type == VOLTAGE_SW) && voltage->voltage) { if (voltage->voltage != rdev->pm.current_vddc) { - radeon_atom_set_voltage(rdev, voltage->voltage); + radeon_atom_set_voltage(rdev, voltage->voltage, SET_VOLTAGE_TYPE_ASIC_VDDC); rdev->pm.current_vddc = voltage->voltage; DRM_DEBUG("Setting: v: %d\n", voltage->voltage); } @@ -1255,9 +1255,6 @@ int rv770_init(struct radeon_device *rdev) { int r; - r = radeon_dummy_page_init(rdev); - if (r) - return r; /* This don't do much */ r = radeon_gem_init(rdev); if (r) @@ -1372,7 +1369,6 @@ void rv770_fini(struct radeon_device *rdev) radeon_atombios_fini(rdev); kfree(rdev->bios); rdev->bios = NULL; - radeon_dummy_page_fini(rdev); } static void rv770_pcie_gen2_enable(struct radeon_device *rdev) diff --git a/drivers/gpu/drm/ttm/ttm_page_alloc.c b/drivers/gpu/drm/ttm/ttm_page_alloc.c index 737a2a2e46a5..9d9d92945f8c 100644 --- a/drivers/gpu/drm/ttm/ttm_page_alloc.c +++ b/drivers/gpu/drm/ttm/ttm_page_alloc.c @@ -683,22 +683,14 @@ int ttm_get_pages(struct list_head *pages, int flags, gfp_flags |= GFP_HIGHUSER; for (r = 0; r < count; ++r) { - if ((flags & TTM_PAGE_FLAG_DMA32) && dma_address) { - void *addr; - addr = dma_alloc_coherent(NULL, PAGE_SIZE, - &dma_address[r], - gfp_flags); - if (addr == NULL) - return -ENOMEM; - p = virt_to_page(addr); - } else - p = alloc_page(gfp_flags); + p = alloc_page(gfp_flags); if (!p) { printk(KERN_ERR TTM_PFX "Unable to allocate page."); return -ENOMEM; } + list_add(&p->lru, pages); } return 0; @@ -746,24 +738,12 @@ void ttm_put_pages(struct list_head *pages, unsigned page_count, int flags, unsigned long irq_flags; struct ttm_page_pool *pool = ttm_get_pool(flags, cstate); struct page *p, *tmp; - unsigned r; if (pool == NULL) { /* No pool for this memory type so free the pages */ - r = page_count-1; list_for_each_entry_safe(p, tmp, pages, lru) { - if ((flags & TTM_PAGE_FLAG_DMA32) && dma_address) { - void *addr = page_address(p); - WARN_ON(!addr || !dma_address[r]); - if (addr) - dma_free_coherent(NULL, PAGE_SIZE, - addr, - dma_address[r]); - dma_address[r] = 0; - } else - __free_page(p); - r--; + __free_page(p); } /* Make the pages list empty */ INIT_LIST_HEAD(pages); diff --git a/drivers/gpu/stub/Kconfig b/drivers/gpu/stub/Kconfig index 70e60a4bb678..419917955bf6 100644 --- a/drivers/gpu/stub/Kconfig +++ b/drivers/gpu/stub/Kconfig @@ -5,6 +5,7 @@ config STUB_POULSBO # Poulsbo stub depends on ACPI_VIDEO when ACPI is enabled # but for select to work, need to select ACPI_VIDEO's dependencies, ick select BACKLIGHT_CLASS_DEVICE if ACPI + select VIDEO_OUTPUT_CONTROL if ACPI select INPUT if ACPI select ACPI_VIDEO if ACPI select THERMAL if ACPI diff --git a/drivers/mfd/mfd-core.c b/drivers/mfd/mfd-core.c index d01574d98870..f4c8c844b913 100644 --- a/drivers/mfd/mfd-core.c +++ b/drivers/mfd/mfd-core.c @@ -55,6 +55,19 @@ int mfd_cell_disable(struct platform_device *pdev) } EXPORT_SYMBOL(mfd_cell_disable); +static int mfd_platform_add_cell(struct platform_device *pdev, + const struct mfd_cell *cell) +{ + if (!cell) + return 0; + + pdev->mfd_cell = kmemdup(cell, sizeof(*cell), GFP_KERNEL); + if (!pdev->mfd_cell) + return -ENOMEM; + + return 0; +} + static int mfd_add_device(struct device *parent, int id, const struct mfd_cell *cell, struct resource *mem_base, @@ -75,7 +88,7 @@ static int mfd_add_device(struct device *parent, int id, pdev->dev.parent = parent; - ret = platform_device_add_data(pdev, cell, sizeof(*cell)); + ret = mfd_platform_add_cell(pdev, cell); if (ret) goto fail_res; @@ -123,7 +136,6 @@ static int mfd_add_device(struct device *parent, int id, return 0; -/* platform_device_del(pdev); */ fail_res: kfree(res); fail_device: diff --git a/drivers/net/benet/be.h b/drivers/net/benet/be.h index f803c58b941d..66823eded7a3 100644 --- a/drivers/net/benet/be.h +++ b/drivers/net/benet/be.h @@ -154,7 +154,7 @@ struct be_eq_obj { u16 min_eqd; /* in usecs */ u16 max_eqd; /* in usecs */ u16 cur_eqd; /* in usecs */ - u8 msix_vec_idx; + u8 eq_idx; struct napi_struct napi; }; @@ -291,7 +291,7 @@ struct be_adapter { u32 num_rx_qs; u32 big_page_size; /* Compounded page size shared by rx wrbs */ - u8 msix_vec_next_idx; + u8 eq_next_idx; struct be_drv_stats drv_stats; struct vlan_group *vlan_grp; diff --git a/drivers/net/benet/be_main.c b/drivers/net/benet/be_main.c index 9a54c8b24ff9..7cb5a114c733 100644 --- a/drivers/net/benet/be_main.c +++ b/drivers/net/benet/be_main.c @@ -1497,7 +1497,7 @@ static int be_tx_queues_create(struct be_adapter *adapter) if (be_cmd_eq_create(adapter, eq, adapter->tx_eq.cur_eqd)) goto tx_eq_free; - adapter->tx_eq.msix_vec_idx = adapter->msix_vec_next_idx++; + adapter->tx_eq.eq_idx = adapter->eq_next_idx++; /* Alloc TX eth compl queue */ @@ -1590,7 +1590,7 @@ static int be_rx_queues_create(struct be_adapter *adapter) if (rc) goto err; - rxo->rx_eq.msix_vec_idx = adapter->msix_vec_next_idx++; + rxo->rx_eq.eq_idx = adapter->eq_next_idx++; /* CQ */ cq = &rxo->cq; @@ -1666,11 +1666,11 @@ static irqreturn_t be_intx(int irq, void *dev) if (!isr) return IRQ_NONE; - if ((1 << adapter->tx_eq.msix_vec_idx & isr)) + if ((1 << adapter->tx_eq.eq_idx & isr)) event_handle(adapter, &adapter->tx_eq); for_all_rx_queues(adapter, rxo, i) { - if ((1 << rxo->rx_eq.msix_vec_idx & isr)) + if ((1 << rxo->rx_eq.eq_idx & isr)) event_handle(adapter, &rxo->rx_eq); } } @@ -1951,7 +1951,7 @@ static void be_sriov_disable(struct be_adapter *adapter) static inline int be_msix_vec_get(struct be_adapter *adapter, struct be_eq_obj *eq_obj) { - return adapter->msix_entries[eq_obj->msix_vec_idx].vector; + return adapter->msix_entries[eq_obj->eq_idx].vector; } static int be_request_irq(struct be_adapter *adapter, @@ -2345,6 +2345,7 @@ static int be_clear(struct be_adapter *adapter) be_mcc_queues_destroy(adapter); be_rx_queues_destroy(adapter); be_tx_queues_destroy(adapter); + adapter->eq_next_idx = 0; if (be_physfn(adapter) && adapter->sriov_enabled) for (vf = 0; vf < num_vfs; vf++) @@ -3141,12 +3142,14 @@ static int be_resume(struct pci_dev *pdev) static void be_shutdown(struct pci_dev *pdev) { struct be_adapter *adapter = pci_get_drvdata(pdev); - struct net_device *netdev = adapter->netdev; - if (netif_running(netdev)) + if (!adapter) + return; + + if (netif_running(adapter->netdev)) cancel_delayed_work_sync(&adapter->work); - netif_device_detach(netdev); + netif_device_detach(adapter->netdev); be_cmd_reset_function(adapter); diff --git a/drivers/net/bna/bfa_ioc.c b/drivers/net/bna/bfa_ioc.c index 34933cb9569f..e3de0b8625cd 100644 --- a/drivers/net/bna/bfa_ioc.c +++ b/drivers/net/bna/bfa_ioc.c @@ -2219,13 +2219,9 @@ bfa_nw_ioc_get_mac(struct bfa_ioc *ioc) static void bfa_ioc_recover(struct bfa_ioc *ioc) { - u16 bdf; - - bdf = (ioc->pcidev.pci_slot << 8 | ioc->pcidev.pci_func << 3 | - ioc->pcidev.device_id); - - pr_crit("Firmware heartbeat failure at %d", bdf); - BUG_ON(1); + pr_crit("Heart Beat of IOC has failed\n"); + bfa_ioc_stats(ioc, ioc_hbfails); + bfa_fsm_send_event(ioc, IOC_E_HBFAIL); } static void diff --git a/drivers/net/can/mcp251x.c b/drivers/net/can/mcp251x.c index 7513c4523ac4..330140ee266d 100644 --- a/drivers/net/can/mcp251x.c +++ b/drivers/net/can/mcp251x.c @@ -931,7 +931,8 @@ static int mcp251x_open(struct net_device *net) priv->tx_len = 0; ret = request_threaded_irq(spi->irq, NULL, mcp251x_can_ist, - IRQF_TRIGGER_FALLING, DEVICE_NAME, priv); + pdata->irq_flags ? pdata->irq_flags : IRQF_TRIGGER_FALLING, + DEVICE_NAME, priv); if (ret) { dev_err(&spi->dev, "failed to acquire irq %d\n", spi->irq); if (pdata->transceiver_enable) diff --git a/drivers/net/mlx4/en_rx.c b/drivers/net/mlx4/en_rx.c index cfd50bc49169..62dd21b06df4 100644 --- a/drivers/net/mlx4/en_rx.c +++ b/drivers/net/mlx4/en_rx.c @@ -345,6 +345,8 @@ int mlx4_en_activate_rx_rings(struct mlx4_en_priv *priv) err = mlx4_en_init_allocator(priv, ring); if (err) { en_err(priv, "Failed initializing ring allocator\n"); + if (ring->stride <= TXBB_SIZE) + ring->buf -= TXBB_SIZE; ring_ind--; goto err_allocator; } @@ -369,6 +371,8 @@ err_buffers: ring_ind = priv->rx_ring_num - 1; err_allocator: while (ring_ind >= 0) { + if (priv->rx_ring[ring_ind].stride <= TXBB_SIZE) + priv->rx_ring[ring_ind].buf -= TXBB_SIZE; mlx4_en_destroy_allocator(priv, &priv->rx_ring[ring_ind]); ring_ind--; } diff --git a/drivers/net/mlx4/main.c b/drivers/net/mlx4/main.c index 62fa7eec5f0c..3814fc9b1145 100644 --- a/drivers/net/mlx4/main.c +++ b/drivers/net/mlx4/main.c @@ -944,6 +944,10 @@ static int mlx4_setup_hca(struct mlx4_dev *dev) } for (port = 1; port <= dev->caps.num_ports; port++) { + enum mlx4_port_type port_type = 0; + mlx4_SENSE_PORT(dev, port, &port_type); + if (port_type) + dev->caps.port_type[port] = port_type; ib_port_default_caps = 0; err = mlx4_get_port_ib_caps(dev, port, &ib_port_default_caps); if (err) @@ -958,6 +962,7 @@ static int mlx4_setup_hca(struct mlx4_dev *dev) goto err_mcg_table_free; } } + mlx4_set_port_mask(dev); return 0; diff --git a/drivers/net/mlx4/mlx4.h b/drivers/net/mlx4/mlx4.h index c1e0e5f1bcdb..dd7d745fbab4 100644 --- a/drivers/net/mlx4/mlx4.h +++ b/drivers/net/mlx4/mlx4.h @@ -431,6 +431,8 @@ void mlx4_srq_event(struct mlx4_dev *dev, u32 srqn, int event_type); void mlx4_handle_catas_err(struct mlx4_dev *dev); +int mlx4_SENSE_PORT(struct mlx4_dev *dev, int port, + enum mlx4_port_type *type); void mlx4_do_sense_ports(struct mlx4_dev *dev, enum mlx4_port_type *stype, enum mlx4_port_type *defaults); diff --git a/drivers/net/mlx4/sense.c b/drivers/net/mlx4/sense.c index 015fbe785c13..e2337a7411d9 100644 --- a/drivers/net/mlx4/sense.c +++ b/drivers/net/mlx4/sense.c @@ -38,8 +38,8 @@ #include "mlx4.h" -static int mlx4_SENSE_PORT(struct mlx4_dev *dev, int port, - enum mlx4_port_type *type) +int mlx4_SENSE_PORT(struct mlx4_dev *dev, int port, + enum mlx4_port_type *type) { u64 out_param; int err = 0; diff --git a/drivers/net/pppoe.c b/drivers/net/pppoe.c index 693aaef4e3ce..718879b35b7d 100644 --- a/drivers/net/pppoe.c +++ b/drivers/net/pppoe.c @@ -317,7 +317,7 @@ static void pppoe_flush_dev(struct net_device *dev) lock_sock(sk); if (po->pppoe_dev == dev && - sk->sk_state & (PPPOX_CONNECTED | PPPOX_BOUND)) { + sk->sk_state & (PPPOX_CONNECTED | PPPOX_BOUND | PPPOX_ZOMBIE)) { pppox_unbind_sock(sk); sk->sk_state = PPPOX_ZOMBIE; sk->sk_state_change(sk); diff --git a/drivers/net/smsc911x.c b/drivers/net/smsc911x.c index c498b720b532..4b42ecc63dcf 100644 --- a/drivers/net/smsc911x.c +++ b/drivers/net/smsc911x.c @@ -1818,6 +1818,7 @@ static int __devinit smsc911x_init(struct net_device *dev) SMSC_TRACE(PROBE, "PHY will be autodetected."); spin_lock_init(&pdata->dev_lock); + spin_lock_init(&pdata->mac_lock); if (pdata->ioaddr == 0) { SMSC_WARNING(PROBE, "pdata->ioaddr: 0x00000000"); @@ -1895,8 +1896,11 @@ static int __devinit smsc911x_init(struct net_device *dev) /* workaround for platforms without an eeprom, where the mac address * is stored elsewhere and set by the bootloader. This saves the * mac address before resetting the device */ - if (pdata->config.flags & SMSC911X_SAVE_MAC_ADDRESS) + if (pdata->config.flags & SMSC911X_SAVE_MAC_ADDRESS) { + spin_lock_irq(&pdata->mac_lock); smsc911x_read_mac_address(dev); + spin_unlock_irq(&pdata->mac_lock); + } /* Reset the LAN911x */ if (smsc911x_soft_reset(pdata)) @@ -2059,8 +2063,6 @@ static int __devinit smsc911x_drv_probe(struct platform_device *pdev) SMSC_TRACE(PROBE, "Network interface: \"%s\"", dev->name); } - spin_lock_init(&pdata->mac_lock); - retval = smsc911x_mii_init(pdev, dev); if (retval) { SMSC_WARNING(PROBE, diff --git a/drivers/net/usb/smsc95xx.c b/drivers/net/usb/smsc95xx.c index 727874d9deb6..47a6c870b51f 100644 --- a/drivers/net/usb/smsc95xx.c +++ b/drivers/net/usb/smsc95xx.c @@ -1313,6 +1313,21 @@ static const struct usb_device_id products[] = { USB_DEVICE(0x0424, 0x9909), .driver_info = (unsigned long) &smsc95xx_info, }, + { + /* SMSC LAN9530 USB Ethernet Device */ + USB_DEVICE(0x0424, 0x9530), + .driver_info = (unsigned long) &smsc95xx_info, + }, + { + /* SMSC LAN9730 USB Ethernet Device */ + USB_DEVICE(0x0424, 0x9730), + .driver_info = (unsigned long) &smsc95xx_info, + }, + { + /* SMSC LAN89530 USB Ethernet Device */ + USB_DEVICE(0x0424, 0x9E08), + .driver_info = (unsigned long) &smsc95xx_info, + }, { }, /* END */ }; MODULE_DEVICE_TABLE(usb, products); diff --git a/drivers/net/wireless/ath/ath9k/hw.c b/drivers/net/wireless/ath/ath9k/hw.c index 338b07502f1a..1ec9bcd6b281 100644 --- a/drivers/net/wireless/ath/ath9k/hw.c +++ b/drivers/net/wireless/ath/ath9k/hw.c @@ -2546,6 +2546,7 @@ static struct { { AR_SREV_VERSION_9287, "9287" }, { AR_SREV_VERSION_9271, "9271" }, { AR_SREV_VERSION_9300, "9300" }, + { AR_SREV_VERSION_9485, "9485" }, }; /* For devices with external radios */ diff --git a/drivers/net/wireless/b43/dma.c b/drivers/net/wireless/b43/dma.c index 3d5566e7af0a..ff0f5ba14b2c 100644 --- a/drivers/net/wireless/b43/dma.c +++ b/drivers/net/wireless/b43/dma.c @@ -1536,7 +1536,7 @@ static void dma_rx(struct b43_dmaring *ring, int *slot) dmaaddr = meta->dmaaddr; goto drop_recycle_buffer; } - if (unlikely(len > ring->rx_buffersize)) { + if (unlikely(len + ring->frameoffset > ring->rx_buffersize)) { /* The data did not fit into one descriptor buffer * and is split over multiple buffers. * This should never happen, as we try to allocate buffers diff --git a/drivers/net/wireless/b43/dma.h b/drivers/net/wireless/b43/dma.h index a01c2100f166..e8a80a1251bf 100644 --- a/drivers/net/wireless/b43/dma.h +++ b/drivers/net/wireless/b43/dma.h @@ -163,7 +163,7 @@ struct b43_dmadesc_generic { /* DMA engine tuning knobs */ #define B43_TXRING_SLOTS 256 #define B43_RXRING_SLOTS 64 -#define B43_DMA0_RX_BUFFERSIZE IEEE80211_MAX_FRAME_LEN +#define B43_DMA0_RX_BUFFERSIZE (B43_DMA0_RX_FRAMEOFFSET + IEEE80211_MAX_FRAME_LEN) /* Pointer poison */ #define B43_DMA_PTR_POISON ((void *)ERR_PTR(-ENOMEM)) diff --git a/drivers/net/wireless/iwlwifi/iwl-eeprom.h b/drivers/net/wireless/iwlwifi/iwl-eeprom.h index 98aa8af01192..20b66469d68f 100644 --- a/drivers/net/wireless/iwlwifi/iwl-eeprom.h +++ b/drivers/net/wireless/iwlwifi/iwl-eeprom.h @@ -241,7 +241,7 @@ struct iwl_eeprom_enhanced_txpwr { /* 6x00 Specific */ #define EEPROM_6000_TX_POWER_VERSION (4) -#define EEPROM_6000_EEPROM_VERSION (0x434) +#define EEPROM_6000_EEPROM_VERSION (0x423) /* 6x50 Specific */ #define EEPROM_6050_TX_POWER_VERSION (4) diff --git a/drivers/net/wireless/p54/p54usb.c b/drivers/net/wireless/p54/p54usb.c index 9b344a921e74..e18358725b69 100644 --- a/drivers/net/wireless/p54/p54usb.c +++ b/drivers/net/wireless/p54/p54usb.c @@ -56,6 +56,7 @@ static struct usb_device_id p54u_table[] __devinitdata = { {USB_DEVICE(0x0846, 0x4210)}, /* Netgear WG121 the second ? */ {USB_DEVICE(0x0846, 0x4220)}, /* Netgear WG111 */ {USB_DEVICE(0x09aa, 0x1000)}, /* Spinnaker Proto board */ + {USB_DEVICE(0x0bf8, 0x1007)}, /* Fujitsu E-5400 USB */ {USB_DEVICE(0x0cde, 0x0006)}, /* Medion 40900, Roper Europe */ {USB_DEVICE(0x0db0, 0x6826)}, /* MSI UB54G (MS-6826) */ {USB_DEVICE(0x107b, 0x55f2)}, /* Gateway WGU-210 (Gemtek) */ @@ -68,6 +69,7 @@ static struct usb_device_id p54u_table[] __devinitdata = { {USB_DEVICE(0x1915, 0x2235)}, /* Linksys WUSB54G Portable OEM */ {USB_DEVICE(0x2001, 0x3701)}, /* DLink DWL-G120 Spinnaker */ {USB_DEVICE(0x2001, 0x3703)}, /* DLink DWL-G122 */ + {USB_DEVICE(0x2001, 0x3762)}, /* Conceptronic C54U */ {USB_DEVICE(0x5041, 0x2234)}, /* Linksys WUSB54G */ {USB_DEVICE(0x5041, 0x2235)}, /* Linksys WUSB54G Portable */ diff --git a/drivers/net/wireless/rt2x00/rt2x00dev.c b/drivers/net/wireless/rt2x00/rt2x00dev.c index 9de9dbe94399..84eb6ad36377 100644 --- a/drivers/net/wireless/rt2x00/rt2x00dev.c +++ b/drivers/net/wireless/rt2x00/rt2x00dev.c @@ -1062,8 +1062,10 @@ void rt2x00lib_remove_dev(struct rt2x00_dev *rt2x00dev) * Stop all work. */ cancel_work_sync(&rt2x00dev->intf_work); - cancel_work_sync(&rt2x00dev->rxdone_work); - cancel_work_sync(&rt2x00dev->txdone_work); + if (rt2x00_is_usb(rt2x00dev)) { + cancel_work_sync(&rt2x00dev->rxdone_work); + cancel_work_sync(&rt2x00dev->txdone_work); + } destroy_workqueue(rt2x00dev->workqueue); /* diff --git a/drivers/net/wireless/rtlwifi/efuse.c b/drivers/net/wireless/rtlwifi/efuse.c index f74a8701c67d..590f14f45a89 100644 --- a/drivers/net/wireless/rtlwifi/efuse.c +++ b/drivers/net/wireless/rtlwifi/efuse.c @@ -685,7 +685,7 @@ static int efuse_pg_packet_read(struct ieee80211_hw *hw, u8 offset, u8 *data) u8 efuse_data, word_cnts = 0; u16 efuse_addr = 0; - u8 hworden; + u8 hworden = 0; u8 tmpdata[8]; if (data == NULL) diff --git a/drivers/net/wireless/rtlwifi/rtl8192c/fw_common.c b/drivers/net/wireless/rtlwifi/rtl8192c/fw_common.c index 5ef91374b230..28a6ce3bc239 100644 --- a/drivers/net/wireless/rtlwifi/rtl8192c/fw_common.c +++ b/drivers/net/wireless/rtlwifi/rtl8192c/fw_common.c @@ -303,7 +303,7 @@ static void _rtl92c_fill_h2c_command(struct ieee80211_hw *hw, u16 box_reg, box_extreg; u8 u1b_tmp; bool isfw_read = false; - u8 buf_index; + u8 buf_index = 0; bool bwrite_sucess = false; u8 wait_h2c_limmit = 100; u8 wait_writeh2c_limmit = 100; diff --git a/drivers/net/wireless/rtlwifi/usb.c b/drivers/net/wireless/rtlwifi/usb.c index a4b2613d6a8c..f5d85735d642 100644 --- a/drivers/net/wireless/rtlwifi/usb.c +++ b/drivers/net/wireless/rtlwifi/usb.c @@ -246,7 +246,7 @@ static void _rtl_usb_io_handler_init(struct device *dev, static void _rtl_usb_io_handler_release(struct ieee80211_hw *hw) { - struct rtl_priv *rtlpriv = rtl_priv(hw); + struct rtl_priv __maybe_unused *rtlpriv = rtl_priv(hw); mutex_destroy(&rtlpriv->io.bb_mutex); } diff --git a/drivers/net/wireless/wl12xx/sdio.c b/drivers/net/wireless/wl12xx/sdio.c index 5b9dbeafec06..b1c7d031c391 100644 --- a/drivers/net/wireless/wl12xx/sdio.c +++ b/drivers/net/wireless/wl12xx/sdio.c @@ -340,7 +340,7 @@ module_init(wl1271_init); module_exit(wl1271_exit); MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Luciano Coelho <luciano.coelho@nokia.com>"); +MODULE_AUTHOR("Luciano Coelho <coelho@ti.com>"); MODULE_AUTHOR("Juuso Oikarinen <juuso.oikarinen@nokia.com>"); MODULE_FIRMWARE(WL1271_FW_NAME); MODULE_FIRMWARE(WL1271_AP_FW_NAME); diff --git a/drivers/net/wireless/wl12xx/spi.c b/drivers/net/wireless/wl12xx/spi.c index 18cf01719ae0..ffc745b17f4d 100644 --- a/drivers/net/wireless/wl12xx/spi.c +++ b/drivers/net/wireless/wl12xx/spi.c @@ -487,7 +487,7 @@ module_init(wl1271_init); module_exit(wl1271_exit); MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Luciano Coelho <luciano.coelho@nokia.com>"); +MODULE_AUTHOR("Luciano Coelho <coelho@ti.com>"); MODULE_AUTHOR("Juuso Oikarinen <juuso.oikarinen@nokia.com>"); MODULE_FIRMWARE(WL1271_FW_NAME); MODULE_FIRMWARE(WL1271_AP_FW_NAME); diff --git a/drivers/net/wireless/wl12xx/testmode.c b/drivers/net/wireless/wl12xx/testmode.c index e64403b6896d..6ec06a4a4c6d 100644 --- a/drivers/net/wireless/wl12xx/testmode.c +++ b/drivers/net/wireless/wl12xx/testmode.c @@ -204,7 +204,10 @@ static int wl1271_tm_cmd_nvs_push(struct wl1271 *wl, struct nlattr *tb[]) kfree(wl->nvs); - wl->nvs = kzalloc(sizeof(struct wl1271_nvs_file), GFP_KERNEL); + if (len != sizeof(struct wl1271_nvs_file)) + return -EINVAL; + + wl->nvs = kzalloc(len, GFP_KERNEL); if (!wl->nvs) { wl1271_error("could not allocate memory for the nvs file"); ret = -ENOMEM; diff --git a/drivers/net/wireless/zd1211rw/zd_usb.c b/drivers/net/wireless/zd1211rw/zd_usb.c index 58236e6d0921..ab607bbd6291 100644 --- a/drivers/net/wireless/zd1211rw/zd_usb.c +++ b/drivers/net/wireless/zd1211rw/zd_usb.c @@ -643,7 +643,7 @@ static void rx_urb_complete(struct urb *urb) usb = urb->context; rx = &usb->rx; - zd_usb_reset_rx_idle_timer(usb); + tasklet_schedule(&rx->reset_timer_tasklet); if (length%rx->usb_packet_size > rx->usb_packet_size-4) { /* If there is an old first fragment, we don't care. */ @@ -812,6 +812,7 @@ void zd_usb_disable_rx(struct zd_usb *usb) __zd_usb_disable_rx(usb); mutex_unlock(&rx->setup_mutex); + tasklet_kill(&rx->reset_timer_tasklet); cancel_delayed_work_sync(&rx->idle_work); } @@ -1106,6 +1107,13 @@ static void zd_rx_idle_timer_handler(struct work_struct *work) zd_usb_reset_rx(usb); } +static void zd_usb_reset_rx_idle_timer_tasklet(unsigned long param) +{ + struct zd_usb *usb = (struct zd_usb *)param; + + zd_usb_reset_rx_idle_timer(usb); +} + void zd_usb_reset_rx_idle_timer(struct zd_usb *usb) { struct zd_usb_rx *rx = &usb->rx; @@ -1127,6 +1135,7 @@ static inline void init_usb_interrupt(struct zd_usb *usb) static inline void init_usb_rx(struct zd_usb *usb) { struct zd_usb_rx *rx = &usb->rx; + spin_lock_init(&rx->lock); mutex_init(&rx->setup_mutex); if (interface_to_usbdev(usb->intf)->speed == USB_SPEED_HIGH) { @@ -1136,11 +1145,14 @@ static inline void init_usb_rx(struct zd_usb *usb) } ZD_ASSERT(rx->fragment_length == 0); INIT_DELAYED_WORK(&rx->idle_work, zd_rx_idle_timer_handler); + rx->reset_timer_tasklet.func = zd_usb_reset_rx_idle_timer_tasklet; + rx->reset_timer_tasklet.data = (unsigned long)usb; } static inline void init_usb_tx(struct zd_usb *usb) { struct zd_usb_tx *tx = &usb->tx; + spin_lock_init(&tx->lock); atomic_set(&tx->enabled, 0); tx->stopped = 0; @@ -1671,6 +1683,10 @@ static void iowrite16v_urb_complete(struct urb *urb) if (urb->status && !usb->cmd_error) usb->cmd_error = urb->status; + + if (!usb->cmd_error && + urb->actual_length != urb->transfer_buffer_length) + usb->cmd_error = -EIO; } static int zd_submit_waiting_urb(struct zd_usb *usb, bool last) @@ -1805,7 +1821,7 @@ int zd_usb_iowrite16v_async(struct zd_usb *usb, const struct zd_ioreq16 *ioreqs, usb_fill_int_urb(urb, udev, usb_sndintpipe(udev, EP_REGS_OUT), req, req_len, iowrite16v_urb_complete, usb, ep->desc.bInterval); - urb->transfer_flags |= URB_FREE_BUFFER | URB_SHORT_NOT_OK; + urb->transfer_flags |= URB_FREE_BUFFER; /* Submit previous URB */ r = zd_submit_waiting_urb(usb, false); diff --git a/drivers/net/wireless/zd1211rw/zd_usb.h b/drivers/net/wireless/zd1211rw/zd_usb.h index b3df2c8116cc..325d0f989257 100644 --- a/drivers/net/wireless/zd1211rw/zd_usb.h +++ b/drivers/net/wireless/zd1211rw/zd_usb.h @@ -183,6 +183,7 @@ struct zd_usb_rx { spinlock_t lock; struct mutex setup_mutex; struct delayed_work idle_work; + struct tasklet_struct reset_timer_tasklet; u8 fragment[2 * USB_MAX_RX_SIZE]; unsigned int fragment_length; unsigned int usb_packet_size; diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c index d86ea8b01137..135df164a4c1 100644 --- a/drivers/pci/pci-driver.c +++ b/drivers/pci/pci-driver.c @@ -781,7 +781,7 @@ static int pci_pm_resume(struct device *dev) #endif /* !CONFIG_SUSPEND */ -#ifdef CONFIG_HIBERNATION +#ifdef CONFIG_HIBERNATE_CALLBACKS static int pci_pm_freeze(struct device *dev) { @@ -970,7 +970,7 @@ static int pci_pm_restore(struct device *dev) return error; } -#else /* !CONFIG_HIBERNATION */ +#else /* !CONFIG_HIBERNATE_CALLBACKS */ #define pci_pm_freeze NULL #define pci_pm_freeze_noirq NULL @@ -981,7 +981,7 @@ static int pci_pm_restore(struct device *dev) #define pci_pm_restore NULL #define pci_pm_restore_noirq NULL -#endif /* !CONFIG_HIBERNATION */ +#endif /* !CONFIG_HIBERNATE_CALLBACKS */ #ifdef CONFIG_PM_RUNTIME diff --git a/drivers/pci/setup-bus.c b/drivers/pci/setup-bus.c index 89d0a6a88df7..ebf51ad1b714 100644 --- a/drivers/pci/setup-bus.c +++ b/drivers/pci/setup-bus.c @@ -676,10 +676,10 @@ static int pbus_size_mem(struct pci_bus *bus, unsigned long mask, min_align = align1 >> 1; align += aligns[order]; } - size0 = calculate_memsize(size, min_size, 0, resource_size(b_res), align); + size0 = calculate_memsize(size, min_size, 0, resource_size(b_res), min_align); size1 = !add_size ? size : calculate_memsize(size, min_size+add_size, 0, - resource_size(b_res), align); + resource_size(b_res), min_align); if (!size0 && !size1) { if (b_res->start || b_res->end) dev_info(&bus->self->dev, "disabling bridge window " diff --git a/drivers/platform/x86/Kconfig b/drivers/platform/x86/Kconfig index 2ee442c2a5db..0485e394712a 100644 --- a/drivers/platform/x86/Kconfig +++ b/drivers/platform/x86/Kconfig @@ -187,7 +187,8 @@ config MSI_LAPTOP depends on ACPI depends on BACKLIGHT_CLASS_DEVICE depends on RFKILL - depends on SERIO_I8042 + depends on INPUT && SERIO_I8042 + select INPUT_SPARSEKMAP ---help--- This is a driver for laptops built by MSI (MICRO-STAR INTERNATIONAL): diff --git a/drivers/platform/x86/acer-wmi.c b/drivers/platform/x86/acer-wmi.c index 5ea6c3477d17..ac4e7f83ce6c 100644 --- a/drivers/platform/x86/acer-wmi.c +++ b/drivers/platform/x86/acer-wmi.c @@ -89,7 +89,7 @@ MODULE_LICENSE("GPL"); #define ACERWMID_EVENT_GUID "676AA15E-6A47-4D9F-A2CC-1E6D18D14026" MODULE_ALIAS("wmi:67C3371D-95A3-4C37-BB61-DD47B491DAAB"); -MODULE_ALIAS("wmi:6AF4F258-B401-42Fd-BE91-3D4AC2D7C0D3"); +MODULE_ALIAS("wmi:6AF4F258-B401-42FD-BE91-3D4AC2D7C0D3"); MODULE_ALIAS("wmi:676AA15E-6A47-4D9F-A2CC-1E6D18D14026"); enum acer_wmi_event_ids { diff --git a/drivers/platform/x86/asus-wmi.c b/drivers/platform/x86/asus-wmi.c index efc776cb0c66..832a3fd7c1c8 100644 --- a/drivers/platform/x86/asus-wmi.c +++ b/drivers/platform/x86/asus-wmi.c @@ -201,8 +201,8 @@ static int asus_wmi_input_init(struct asus_wmi *asus) if (!asus->inputdev) return -ENOMEM; - asus->inputdev->name = asus->driver->input_phys; - asus->inputdev->phys = asus->driver->input_name; + asus->inputdev->name = asus->driver->input_name; + asus->inputdev->phys = asus->driver->input_phys; asus->inputdev->id.bustype = BUS_HOST; asus->inputdev->dev.parent = &asus->platform_device->dev; diff --git a/drivers/platform/x86/eeepc-wmi.c b/drivers/platform/x86/eeepc-wmi.c index 0ddc434fb93b..649dcadd8ea3 100644 --- a/drivers/platform/x86/eeepc-wmi.c +++ b/drivers/platform/x86/eeepc-wmi.c @@ -67,9 +67,11 @@ static const struct key_entry eeepc_wmi_keymap[] = { { KE_KEY, 0x82, { KEY_CAMERA } }, { KE_KEY, 0x83, { KEY_CAMERA_ZOOMIN } }, { KE_KEY, 0x88, { KEY_WLAN } }, + { KE_KEY, 0xbd, { KEY_CAMERA } }, { KE_KEY, 0xcc, { KEY_SWITCHVIDEOMODE } }, { KE_KEY, 0xe0, { KEY_PROG1 } }, /* Task Manager */ { KE_KEY, 0xe1, { KEY_F14 } }, /* Change Resolution */ + { KE_KEY, 0xe8, { KEY_SCREENLOCK } }, { KE_KEY, 0xe9, { KEY_BRIGHTNESS_ZERO } }, { KE_KEY, 0xeb, { KEY_CAMERA_ZOOMOUT } }, { KE_KEY, 0xec, { KEY_CAMERA_UP } }, diff --git a/drivers/platform/x86/intel_pmic_gpio.c b/drivers/platform/x86/intel_pmic_gpio.c index d653104b59cb..464bb3fc4d88 100644 --- a/drivers/platform/x86/intel_pmic_gpio.c +++ b/drivers/platform/x86/intel_pmic_gpio.c @@ -74,6 +74,19 @@ struct pmic_gpio { u32 trigger_type; }; +static void pmic_program_irqtype(int gpio, int type) +{ + if (type & IRQ_TYPE_EDGE_RISING) + intel_scu_ipc_update_register(GPIO0 + gpio, 0x20, 0x20); + else + intel_scu_ipc_update_register(GPIO0 + gpio, 0x00, 0x20); + + if (type & IRQ_TYPE_EDGE_FALLING) + intel_scu_ipc_update_register(GPIO0 + gpio, 0x10, 0x10); + else + intel_scu_ipc_update_register(GPIO0 + gpio, 0x00, 0x10); +}; + static int pmic_gpio_direction_input(struct gpio_chip *chip, unsigned offset) { if (offset > 8) { @@ -166,16 +179,38 @@ static int pmic_gpio_to_irq(struct gpio_chip *chip, unsigned offset) return pg->irq_base + offset; } +static void pmic_bus_lock(struct irq_data *data) +{ + struct pmic_gpio *pg = irq_data_get_irq_chip_data(data); + + mutex_lock(&pg->buslock); +} + +static void pmic_bus_sync_unlock(struct irq_data *data) +{ + struct pmic_gpio *pg = irq_data_get_irq_chip_data(data); + + if (pg->update_type) { + unsigned int gpio = pg->update_type & ~GPIO_UPDATE_TYPE; + + pmic_program_irqtype(gpio, pg->trigger_type); + pg->update_type = 0; + } + mutex_unlock(&pg->buslock); +} + /* the gpiointr register is read-clear, so just do nothing. */ static void pmic_irq_unmask(struct irq_data *data) { } static void pmic_irq_mask(struct irq_data *data) { } static struct irq_chip pmic_irqchip = { - .name = "PMIC-GPIO", - .irq_mask = pmic_irq_mask, - .irq_unmask = pmic_irq_unmask, - .irq_set_type = pmic_irq_type, + .name = "PMIC-GPIO", + .irq_mask = pmic_irq_mask, + .irq_unmask = pmic_irq_unmask, + .irq_set_type = pmic_irq_type, + .irq_bus_lock = pmic_bus_lock, + .irq_bus_sync_unlock = pmic_bus_sync_unlock, }; static irqreturn_t pmic_irq_handler(int irq, void *data) diff --git a/drivers/platform/x86/samsung-laptop.c b/drivers/platform/x86/samsung-laptop.c index de434c6dc2d6..d347116d150e 100644 --- a/drivers/platform/x86/samsung-laptop.c +++ b/drivers/platform/x86/samsung-laptop.c @@ -571,6 +571,16 @@ static struct dmi_system_id __initdata samsung_dmi_table[] = { .callback = dmi_check_cb, }, { + .ident = "R410 Plus", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, + "SAMSUNG ELECTRONICS CO., LTD."), + DMI_MATCH(DMI_PRODUCT_NAME, "R410P"), + DMI_MATCH(DMI_BOARD_NAME, "R460"), + }, + .callback = dmi_check_cb, + }, + { .ident = "R518", .matches = { DMI_MATCH(DMI_SYS_VENDOR, @@ -591,12 +601,12 @@ static struct dmi_system_id __initdata samsung_dmi_table[] = { .callback = dmi_check_cb, }, { - .ident = "N150/N210/N220", + .ident = "N150/N210/N220/N230", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "SAMSUNG ELECTRONICS CO., LTD."), - DMI_MATCH(DMI_PRODUCT_NAME, "N150/N210/N220"), - DMI_MATCH(DMI_BOARD_NAME, "N150/N210/N220"), + DMI_MATCH(DMI_PRODUCT_NAME, "N150/N210/N220/N230"), + DMI_MATCH(DMI_BOARD_NAME, "N150/N210/N220/N230"), }, .callback = dmi_check_cb, }, @@ -771,6 +781,7 @@ static int __init samsung_init(void) /* create a backlight device to talk to this one */ memset(&props, 0, sizeof(struct backlight_properties)); + props.type = BACKLIGHT_PLATFORM; props.max_brightness = sabi_config->max_brightness; backlight_device = backlight_device_register("samsung", &sdev->dev, NULL, &backlight_ops, diff --git a/drivers/platform/x86/sony-laptop.c b/drivers/platform/x86/sony-laptop.c index e642f5f29504..8f709aec4da0 100644 --- a/drivers/platform/x86/sony-laptop.c +++ b/drivers/platform/x86/sony-laptop.c @@ -138,6 +138,8 @@ MODULE_PARM_DESC(kbd_backlight_timeout, "1 for 30 seconds, 2 for 60 seconds and 3 to disable timeout " "(default: 0)"); +static void sony_nc_kbd_backlight_resume(void); + enum sony_nc_rfkill { SONY_WIFI, SONY_BLUETOOTH, @@ -771,11 +773,6 @@ static int sony_nc_handles_setup(struct platform_device *pd) if (!handles) return -ENOMEM; - sysfs_attr_init(&handles->devattr.attr); - handles->devattr.attr.name = "handles"; - handles->devattr.attr.mode = S_IRUGO; - handles->devattr.show = sony_nc_handles_show; - for (i = 0; i < ARRAY_SIZE(handles->cap); i++) { if (!acpi_callsetfunc(sony_nc_acpi_handle, "SN00", i + 0x20, &result)) { @@ -785,11 +782,18 @@ static int sony_nc_handles_setup(struct platform_device *pd) } } - /* allow reading capabilities via sysfs */ - if (device_create_file(&pd->dev, &handles->devattr)) { - kfree(handles); - handles = NULL; - return -1; + if (debug) { + sysfs_attr_init(&handles->devattr.attr); + handles->devattr.attr.name = "handles"; + handles->devattr.attr.mode = S_IRUGO; + handles->devattr.show = sony_nc_handles_show; + + /* allow reading capabilities via sysfs */ + if (device_create_file(&pd->dev, &handles->devattr)) { + kfree(handles); + handles = NULL; + return -1; + } } return 0; @@ -798,7 +802,8 @@ static int sony_nc_handles_setup(struct platform_device *pd) static int sony_nc_handles_cleanup(struct platform_device *pd) { if (handles) { - device_remove_file(&pd->dev, &handles->devattr); + if (debug) + device_remove_file(&pd->dev, &handles->devattr); kfree(handles); handles = NULL; } @@ -808,6 +813,11 @@ static int sony_nc_handles_cleanup(struct platform_device *pd) static int sony_find_snc_handle(int handle) { int i; + + /* not initialized yet, return early */ + if (!handles) + return -1; + for (i = 0; i < 0x10; i++) { if (handles->cap[i] == handle) { dprintk("found handle 0x%.4x (offset: 0x%.2x)\n", @@ -1168,6 +1178,9 @@ static int sony_nc_resume(struct acpi_device *device) /* re-read rfkill state */ sony_nc_rfkill_update(); + /* restore kbd backlight states */ + sony_nc_kbd_backlight_resume(); + return 0; } @@ -1355,6 +1368,7 @@ out_no_enum: #define KBDBL_HANDLER 0x137 #define KBDBL_PRESENT 0xB00 #define SET_MODE 0xC00 +#define SET_STATE 0xD00 #define SET_TIMEOUT 0xE00 struct kbd_backlight { @@ -1377,6 +1391,10 @@ static ssize_t __sony_nc_kbd_backlight_mode_set(u8 value) (value << 0x10) | SET_MODE, &result)) return -EIO; + /* Try to turn the light on/off immediately */ + sony_call_snc_handle(KBDBL_HANDLER, (value << 0x10) | SET_STATE, + &result); + kbdbl_handle->mode = value; return 0; @@ -1458,7 +1476,7 @@ static int sony_nc_kbd_backlight_setup(struct platform_device *pd) { int result; - if (sony_call_snc_handle(0x137, KBDBL_PRESENT, &result)) + if (sony_call_snc_handle(KBDBL_HANDLER, KBDBL_PRESENT, &result)) return 0; if (!(result & 0x02)) return 0; @@ -1501,13 +1519,36 @@ outkzalloc: static int sony_nc_kbd_backlight_cleanup(struct platform_device *pd) { if (kbdbl_handle) { + int result; + device_remove_file(&pd->dev, &kbdbl_handle->mode_attr); device_remove_file(&pd->dev, &kbdbl_handle->timeout_attr); + + /* restore the default hw behaviour */ + sony_call_snc_handle(KBDBL_HANDLER, 0x1000 | SET_MODE, &result); + sony_call_snc_handle(KBDBL_HANDLER, SET_TIMEOUT, &result); + kfree(kbdbl_handle); } return 0; } +static void sony_nc_kbd_backlight_resume(void) +{ + int ignore = 0; + + if (!kbdbl_handle) + return; + + if (kbdbl_handle->mode == 0) + sony_call_snc_handle(KBDBL_HANDLER, SET_MODE, &ignore); + + if (kbdbl_handle->timeout != 0) + sony_call_snc_handle(KBDBL_HANDLER, + (kbdbl_handle->timeout << 0x10) | SET_TIMEOUT, + &ignore); +} + static void sony_nc_backlight_setup(void) { acpi_handle unused; diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c index a08561f5349e..efb3b6b9bcdb 100644 --- a/drivers/platform/x86/thinkpad_acpi.c +++ b/drivers/platform/x86/thinkpad_acpi.c @@ -8618,8 +8618,7 @@ static bool __pure __init tpacpi_is_valid_fw_id(const char* const s, tpacpi_is_fw_digit(s[1]) && s[2] == t && s[3] == 'T' && tpacpi_is_fw_digit(s[4]) && - tpacpi_is_fw_digit(s[5]) && - s[6] == 'W' && s[7] == 'W'; + tpacpi_is_fw_digit(s[5]); } /* returns 0 - probe ok, or < 0 - probe error. diff --git a/drivers/spi/amba-pl022.c b/drivers/spi/amba-pl022.c index 5825370bad25..08de58e7f59f 100644 --- a/drivers/spi/amba-pl022.c +++ b/drivers/spi/amba-pl022.c @@ -1555,7 +1555,7 @@ static int stop_queue(struct pl022 *pl022) * A wait_queue on the pl022->busy could be used, but then the common * execution path (pump_messages) would be required to call wake_up or * friends on every SPI message. Do this instead */ - while (!list_empty(&pl022->queue) && pl022->busy && limit--) { + while ((!list_empty(&pl022->queue) || pl022->busy) && limit--) { spin_unlock_irqrestore(&pl022->queue_lock, flags); msleep(10); spin_lock_irqsave(&pl022->queue_lock, flags); diff --git a/drivers/spi/dw_spi.c b/drivers/spi/dw_spi.c index b1a4b9f503ae..871e337c917f 100644 --- a/drivers/spi/dw_spi.c +++ b/drivers/spi/dw_spi.c @@ -821,7 +821,7 @@ static int stop_queue(struct dw_spi *dws) spin_lock_irqsave(&dws->lock, flags); dws->run = QUEUE_STOPPED; - while (!list_empty(&dws->queue) && dws->busy && limit--) { + while ((!list_empty(&dws->queue) || dws->busy) && limit--) { spin_unlock_irqrestore(&dws->lock, flags); msleep(10); spin_lock_irqsave(&dws->lock, flags); diff --git a/drivers/spi/pxa2xx_spi.c b/drivers/spi/pxa2xx_spi.c index 9c74aad6be93..dc25bee8d33f 100644 --- a/drivers/spi/pxa2xx_spi.c +++ b/drivers/spi/pxa2xx_spi.c @@ -1493,7 +1493,7 @@ static int stop_queue(struct driver_data *drv_data) * execution path (pump_messages) would be required to call wake_up or * friends on every SPI message. Do this instead */ drv_data->run = QUEUE_STOPPED; - while (!list_empty(&drv_data->queue) && drv_data->busy && limit--) { + while ((!list_empty(&drv_data->queue) || drv_data->busy) && limit--) { spin_unlock_irqrestore(&drv_data->lock, flags); msleep(10); spin_lock_irqsave(&drv_data->lock, flags); diff --git a/drivers/spi/spi_bfin5xx.c b/drivers/spi/spi_bfin5xx.c index bdb7289a1d22..f706dba165cf 100644 --- a/drivers/spi/spi_bfin5xx.c +++ b/drivers/spi/spi_bfin5xx.c @@ -1284,7 +1284,7 @@ static inline int bfin_spi_stop_queue(struct bfin_spi_master_data *drv_data) * friends on every SPI message. Do this instead */ drv_data->running = false; - while (!list_empty(&drv_data->queue) && drv_data->busy && limit--) { + while ((!list_empty(&drv_data->queue) || drv_data->busy) && limit--) { spin_unlock_irqrestore(&drv_data->lock, flags); msleep(10); spin_lock_irqsave(&drv_data->lock, flags); diff --git a/drivers/staging/Kconfig b/drivers/staging/Kconfig index dca4a0bb6ca9..e3786f161bc3 100644 --- a/drivers/staging/Kconfig +++ b/drivers/staging/Kconfig @@ -131,8 +131,6 @@ source "drivers/staging/wlags49_h2/Kconfig" source "drivers/staging/wlags49_h25/Kconfig" -source "drivers/staging/samsung-laptop/Kconfig" - source "drivers/staging/sm7xx/Kconfig" source "drivers/staging/dt3155v4l/Kconfig" diff --git a/drivers/staging/Makefile b/drivers/staging/Makefile index eb93012b6f59..f0d5c5315612 100644 --- a/drivers/staging/Makefile +++ b/drivers/staging/Makefile @@ -48,7 +48,6 @@ obj-$(CONFIG_XVMALLOC) += zram/ obj-$(CONFIG_ZCACHE) += zcache/ obj-$(CONFIG_WLAGS49_H2) += wlags49_h2/ obj-$(CONFIG_WLAGS49_H25) += wlags49_h25/ -obj-$(CONFIG_SAMSUNG_LAPTOP) += samsung-laptop/ obj-$(CONFIG_FB_SM7XX) += sm7xx/ obj-$(CONFIG_VIDEO_DT3155) += dt3155v4l/ obj-$(CONFIG_CRYSTALHD) += crystalhd/ diff --git a/drivers/staging/samsung-laptop/Kconfig b/drivers/staging/samsung-laptop/Kconfig deleted file mode 100644 index f27c60864c26..000000000000 --- a/drivers/staging/samsung-laptop/Kconfig +++ /dev/null @@ -1,10 +0,0 @@ -config SAMSUNG_LAPTOP - tristate "Samsung Laptop driver" - default n - depends on RFKILL && BACKLIGHT_CLASS_DEVICE && X86 - help - This module implements a driver for the N128 Samsung Laptop - providing control over the Wireless LED and the LCD backlight - - To compile this driver as a module, choose - M here: the module will be called samsung-laptop. diff --git a/drivers/staging/samsung-laptop/Makefile b/drivers/staging/samsung-laptop/Makefile deleted file mode 100644 index 3c6f42045211..000000000000 --- a/drivers/staging/samsung-laptop/Makefile +++ /dev/null @@ -1 +0,0 @@ -obj-$(CONFIG_SAMSUNG_LAPTOP) += samsung-laptop.o diff --git a/drivers/staging/samsung-laptop/TODO b/drivers/staging/samsung-laptop/TODO deleted file mode 100644 index f7a6d589916e..000000000000 --- a/drivers/staging/samsung-laptop/TODO +++ /dev/null @@ -1,5 +0,0 @@ -TODO: - - review from other developers - - figure out ACPI video issues - -Please send patches to Greg Kroah-Hartman <gregkh@suse.de> diff --git a/drivers/staging/samsung-laptop/samsung-laptop.c b/drivers/staging/samsung-laptop/samsung-laptop.c deleted file mode 100644 index 25294462b8b6..000000000000 --- a/drivers/staging/samsung-laptop/samsung-laptop.c +++ /dev/null @@ -1,843 +0,0 @@ -/* - * Samsung Laptop driver - * - * Copyright (C) 2009,2011 Greg Kroah-Hartman (gregkh@suse.de) - * Copyright (C) 2009,2011 Novell Inc. - * - * 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. - * - */ -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt - -#include <linux/kernel.h> -#include <linux/init.h> -#include <linux/module.h> -#include <linux/delay.h> -#include <linux/pci.h> -#include <linux/backlight.h> -#include <linux/fb.h> -#include <linux/dmi.h> -#include <linux/platform_device.h> -#include <linux/rfkill.h> - -/* - * This driver is needed because a number of Samsung laptops do not hook - * their control settings through ACPI. So we have to poke around in the - * BIOS to do things like brightness values, and "special" key controls. - */ - -/* - * We have 0 - 8 as valid brightness levels. The specs say that level 0 should - * be reserved by the BIOS (which really doesn't make much sense), we tell - * userspace that the value is 0 - 7 and then just tell the hardware 1 - 8 - */ -#define MAX_BRIGHT 0x07 - - -#define SABI_IFACE_MAIN 0x00 -#define SABI_IFACE_SUB 0x02 -#define SABI_IFACE_COMPLETE 0x04 -#define SABI_IFACE_DATA 0x05 - -/* Structure to get data back to the calling function */ -struct sabi_retval { - u8 retval[20]; -}; - -struct sabi_header_offsets { - u8 port; - u8 re_mem; - u8 iface_func; - u8 en_mem; - u8 data_offset; - u8 data_segment; -}; - -struct sabi_commands { - /* - * Brightness is 0 - 8, as described above. - * Value 0 is for the BIOS to use - */ - u8 get_brightness; - u8 set_brightness; - - /* - * first byte: - * 0x00 - wireless is off - * 0x01 - wireless is on - * second byte: - * 0x02 - 3G is off - * 0x03 - 3G is on - * TODO, verify 3G is correct, that doesn't seem right... - */ - u8 get_wireless_button; - u8 set_wireless_button; - - /* 0 is off, 1 is on */ - u8 get_backlight; - u8 set_backlight; - - /* - * 0x80 or 0x00 - no action - * 0x81 - recovery key pressed - */ - u8 get_recovery_mode; - u8 set_recovery_mode; - - /* - * on seclinux: 0 is low, 1 is high, - * on swsmi: 0 is normal, 1 is silent, 2 is turbo - */ - u8 get_performance_level; - u8 set_performance_level; - - /* - * Tell the BIOS that Linux is running on this machine. - * 81 is on, 80 is off - */ - u8 set_linux; -}; - -struct sabi_performance_level { - const char *name; - u8 value; -}; - -struct sabi_config { - const char *test_string; - u16 main_function; - const struct sabi_header_offsets header_offsets; - const struct sabi_commands commands; - const struct sabi_performance_level performance_levels[4]; - u8 min_brightness; - u8 max_brightness; -}; - -static const struct sabi_config sabi_configs[] = { - { - .test_string = "SECLINUX", - - .main_function = 0x4c49, - - .header_offsets = { - .port = 0x00, - .re_mem = 0x02, - .iface_func = 0x03, - .en_mem = 0x04, - .data_offset = 0x05, - .data_segment = 0x07, - }, - - .commands = { - .get_brightness = 0x00, - .set_brightness = 0x01, - - .get_wireless_button = 0x02, - .set_wireless_button = 0x03, - - .get_backlight = 0x04, - .set_backlight = 0x05, - - .get_recovery_mode = 0x06, - .set_recovery_mode = 0x07, - - .get_performance_level = 0x08, - .set_performance_level = 0x09, - - .set_linux = 0x0a, - }, - - .performance_levels = { - { - .name = "silent", - .value = 0, - }, - { - .name = "normal", - .value = 1, - }, - { }, - }, - .min_brightness = 1, - .max_brightness = 8, - }, - { - .test_string = "SwSmi@", - - .main_function = 0x5843, - - .header_offsets = { - .port = 0x00, - .re_mem = 0x04, - .iface_func = 0x02, - .en_mem = 0x03, - .data_offset = 0x05, - .data_segment = 0x07, - }, - - .commands = { - .get_brightness = 0x10, - .set_brightness = 0x11, - - .get_wireless_button = 0x12, - .set_wireless_button = 0x13, - - .get_backlight = 0x2d, - .set_backlight = 0x2e, - - .get_recovery_mode = 0xff, - .set_recovery_mode = 0xff, - - .get_performance_level = 0x31, - .set_performance_level = 0x32, - - .set_linux = 0xff, - }, - - .performance_levels = { - { - .name = "normal", - .value = 0, - }, - { - .name = "silent", - .value = 1, - }, - { - .name = "overclock", - .value = 2, - }, - { }, - }, - .min_brightness = 0, - .max_brightness = 8, - }, - { }, -}; - -static const struct sabi_config *sabi_config; - -static void __iomem *sabi; -static void __iomem *sabi_iface; -static void __iomem *f0000_segment; -static struct backlight_device *backlight_device; -static struct mutex sabi_mutex; -static struct platform_device *sdev; -static struct rfkill *rfk; - -static int force; -module_param(force, bool, 0); -MODULE_PARM_DESC(force, - "Disable the DMI check and forces the driver to be loaded"); - -static int debug; -module_param(debug, bool, S_IRUGO | S_IWUSR); -MODULE_PARM_DESC(debug, "Debug enabled or not"); - -static int sabi_get_command(u8 command, struct sabi_retval *sretval) -{ - int retval = 0; - u16 port = readw(sabi + sabi_config->header_offsets.port); - u8 complete, iface_data; - - mutex_lock(&sabi_mutex); - - /* enable memory to be able to write to it */ - outb(readb(sabi + sabi_config->header_offsets.en_mem), port); - - /* write out the command */ - writew(sabi_config->main_function, sabi_iface + SABI_IFACE_MAIN); - writew(command, sabi_iface + SABI_IFACE_SUB); - writeb(0, sabi_iface + SABI_IFACE_COMPLETE); - outb(readb(sabi + sabi_config->header_offsets.iface_func), port); - - /* write protect memory to make it safe */ - outb(readb(sabi + sabi_config->header_offsets.re_mem), port); - - /* see if the command actually succeeded */ - complete = readb(sabi_iface + SABI_IFACE_COMPLETE); - iface_data = readb(sabi_iface + SABI_IFACE_DATA); - if (complete != 0xaa || iface_data == 0xff) { - pr_warn("SABI get command 0x%02x failed with completion flag 0x%02x and data 0x%02x\n", - command, complete, iface_data); - retval = -EINVAL; - goto exit; - } - /* - * Save off the data into a structure so the caller use it. - * Right now we only want the first 4 bytes, - * There are commands that need more, but not for the ones we - * currently care about. - */ - sretval->retval[0] = readb(sabi_iface + SABI_IFACE_DATA); - sretval->retval[1] = readb(sabi_iface + SABI_IFACE_DATA + 1); - sretval->retval[2] = readb(sabi_iface + SABI_IFACE_DATA + 2); - sretval->retval[3] = readb(sabi_iface + SABI_IFACE_DATA + 3); - -exit: - mutex_unlock(&sabi_mutex); - return retval; - -} - -static int sabi_set_command(u8 command, u8 data) -{ - int retval = 0; - u16 port = readw(sabi + sabi_config->header_offsets.port); - u8 complete, iface_data; - - mutex_lock(&sabi_mutex); - - /* enable memory to be able to write to it */ - outb(readb(sabi + sabi_config->header_offsets.en_mem), port); - - /* write out the command */ - writew(sabi_config->main_function, sabi_iface + SABI_IFACE_MAIN); - writew(command, sabi_iface + SABI_IFACE_SUB); - writeb(0, sabi_iface + SABI_IFACE_COMPLETE); - writeb(data, sabi_iface + SABI_IFACE_DATA); - outb(readb(sabi + sabi_config->header_offsets.iface_func), port); - - /* write protect memory to make it safe */ - outb(readb(sabi + sabi_config->header_offsets.re_mem), port); - - /* see if the command actually succeeded */ - complete = readb(sabi_iface + SABI_IFACE_COMPLETE); - iface_data = readb(sabi_iface + SABI_IFACE_DATA); - if (complete != 0xaa || iface_data == 0xff) { - pr_warn("SABI set command 0x%02x failed with completion flag 0x%02x and data 0x%02x\n", - command, complete, iface_data); - retval = -EINVAL; - } - - mutex_unlock(&sabi_mutex); - return retval; -} - -static void test_backlight(void) -{ - struct sabi_retval sretval; - - sabi_get_command(sabi_config->commands.get_backlight, &sretval); - printk(KERN_DEBUG "backlight = 0x%02x\n", sretval.retval[0]); - - sabi_set_command(sabi_config->commands.set_backlight, 0); - printk(KERN_DEBUG "backlight should be off\n"); - - sabi_get_command(sabi_config->commands.get_backlight, &sretval); - printk(KERN_DEBUG "backlight = 0x%02x\n", sretval.retval[0]); - - msleep(1000); - - sabi_set_command(sabi_config->commands.set_backlight, 1); - printk(KERN_DEBUG "backlight should be on\n"); - - sabi_get_command(sabi_config->commands.get_backlight, &sretval); - printk(KERN_DEBUG "backlight = 0x%02x\n", sretval.retval[0]); -} - -static void test_wireless(void) -{ - struct sabi_retval sretval; - - sabi_get_command(sabi_config->commands.get_wireless_button, &sretval); - printk(KERN_DEBUG "wireless led = 0x%02x\n", sretval.retval[0]); - - sabi_set_command(sabi_config->commands.set_wireless_button, 0); - printk(KERN_DEBUG "wireless led should be off\n"); - - sabi_get_command(sabi_config->commands.get_wireless_button, &sretval); - printk(KERN_DEBUG "wireless led = 0x%02x\n", sretval.retval[0]); - - msleep(1000); - - sabi_set_command(sabi_config->commands.set_wireless_button, 1); - printk(KERN_DEBUG "wireless led should be on\n"); - - sabi_get_command(sabi_config->commands.get_wireless_button, &sretval); - printk(KERN_DEBUG "wireless led = 0x%02x\n", sretval.retval[0]); -} - -static u8 read_brightness(void) -{ - struct sabi_retval sretval; - int user_brightness = 0; - int retval; - - retval = sabi_get_command(sabi_config->commands.get_brightness, - &sretval); - if (!retval) { - user_brightness = sretval.retval[0]; - if (user_brightness != 0) - user_brightness -= sabi_config->min_brightness; - } - return user_brightness; -} - -static void set_brightness(u8 user_brightness) -{ - u8 user_level = user_brightness - sabi_config->min_brightness; - - sabi_set_command(sabi_config->commands.set_brightness, user_level); -} - -static int get_brightness(struct backlight_device *bd) -{ - return (int)read_brightness(); -} - -static int update_status(struct backlight_device *bd) -{ - set_brightness(bd->props.brightness); - - if (bd->props.power == FB_BLANK_UNBLANK) - sabi_set_command(sabi_config->commands.set_backlight, 1); - else - sabi_set_command(sabi_config->commands.set_backlight, 0); - return 0; -} - -static const struct backlight_ops backlight_ops = { - .get_brightness = get_brightness, - .update_status = update_status, -}; - -static int rfkill_set(void *data, bool blocked) -{ - /* Do something with blocked...*/ - /* - * blocked == false is on - * blocked == true is off - */ - if (blocked) - sabi_set_command(sabi_config->commands.set_wireless_button, 0); - else - sabi_set_command(sabi_config->commands.set_wireless_button, 1); - - return 0; -} - -static struct rfkill_ops rfkill_ops = { - .set_block = rfkill_set, -}; - -static int init_wireless(struct platform_device *sdev) -{ - int retval; - - rfk = rfkill_alloc("samsung-wifi", &sdev->dev, RFKILL_TYPE_WLAN, - &rfkill_ops, NULL); - if (!rfk) - return -ENOMEM; - - retval = rfkill_register(rfk); - if (retval) { - rfkill_destroy(rfk); - return -ENODEV; - } - - return 0; -} - -static void destroy_wireless(void) -{ - rfkill_unregister(rfk); - rfkill_destroy(rfk); -} - -static ssize_t get_performance_level(struct device *dev, - struct device_attribute *attr, char *buf) -{ - struct sabi_retval sretval; - int retval; - int i; - - /* Read the state */ - retval = sabi_get_command(sabi_config->commands.get_performance_level, - &sretval); - if (retval) - return retval; - - /* The logic is backwards, yeah, lots of fun... */ - for (i = 0; sabi_config->performance_levels[i].name; ++i) { - if (sretval.retval[0] == sabi_config->performance_levels[i].value) - return sprintf(buf, "%s\n", sabi_config->performance_levels[i].name); - } - return sprintf(buf, "%s\n", "unknown"); -} - -static ssize_t set_performance_level(struct device *dev, - struct device_attribute *attr, const char *buf, - size_t count) -{ - if (count >= 1) { - int i; - for (i = 0; sabi_config->performance_levels[i].name; ++i) { - const struct sabi_performance_level *level = - &sabi_config->performance_levels[i]; - if (!strncasecmp(level->name, buf, strlen(level->name))) { - sabi_set_command(sabi_config->commands.set_performance_level, - level->value); - break; - } - } - if (!sabi_config->performance_levels[i].name) - return -EINVAL; - } - return count; -} -static DEVICE_ATTR(performance_level, S_IWUSR | S_IRUGO, - get_performance_level, set_performance_level); - - -static int __init dmi_check_cb(const struct dmi_system_id *id) -{ - pr_info("found laptop model '%s'\n", - id->ident); - return 0; -} - -static struct dmi_system_id __initdata samsung_dmi_table[] = { - { - .ident = "N128", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, - "SAMSUNG ELECTRONICS CO., LTD."), - DMI_MATCH(DMI_PRODUCT_NAME, "N128"), - DMI_MATCH(DMI_BOARD_NAME, "N128"), - }, - .callback = dmi_check_cb, - }, - { - .ident = "N130", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, - "SAMSUNG ELECTRONICS CO., LTD."), - DMI_MATCH(DMI_PRODUCT_NAME, "N130"), - DMI_MATCH(DMI_BOARD_NAME, "N130"), - }, - .callback = dmi_check_cb, - }, - { - .ident = "X125", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, - "SAMSUNG ELECTRONICS CO., LTD."), - DMI_MATCH(DMI_PRODUCT_NAME, "X125"), - DMI_MATCH(DMI_BOARD_NAME, "X125"), - }, - .callback = dmi_check_cb, - }, - { - .ident = "X120/X170", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, - "SAMSUNG ELECTRONICS CO., LTD."), - DMI_MATCH(DMI_PRODUCT_NAME, "X120/X170"), - DMI_MATCH(DMI_BOARD_NAME, "X120/X170"), - }, - .callback = dmi_check_cb, - }, - { - .ident = "NC10", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, - "SAMSUNG ELECTRONICS CO., LTD."), - DMI_MATCH(DMI_PRODUCT_NAME, "NC10"), - DMI_MATCH(DMI_BOARD_NAME, "NC10"), - }, - .callback = dmi_check_cb, - }, - { - .ident = "NP-Q45", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, - "SAMSUNG ELECTRONICS CO., LTD."), - DMI_MATCH(DMI_PRODUCT_NAME, "SQ45S70S"), - DMI_MATCH(DMI_BOARD_NAME, "SQ45S70S"), - }, - .callback = dmi_check_cb, - }, - { - .ident = "X360", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, - "SAMSUNG ELECTRONICS CO., LTD."), - DMI_MATCH(DMI_PRODUCT_NAME, "X360"), - DMI_MATCH(DMI_BOARD_NAME, "X360"), - }, - .callback = dmi_check_cb, - }, - { - .ident = "R410 Plus", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, - "SAMSUNG ELECTRONICS CO., LTD."), - DMI_MATCH(DMI_PRODUCT_NAME, "R410P"), - DMI_MATCH(DMI_BOARD_NAME, "R460"), - }, - .callback = dmi_check_cb, - }, - { - .ident = "R518", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, - "SAMSUNG ELECTRONICS CO., LTD."), - DMI_MATCH(DMI_PRODUCT_NAME, "R518"), - DMI_MATCH(DMI_BOARD_NAME, "R518"), - }, - .callback = dmi_check_cb, - }, - { - .ident = "R519/R719", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, - "SAMSUNG ELECTRONICS CO., LTD."), - DMI_MATCH(DMI_PRODUCT_NAME, "R519/R719"), - DMI_MATCH(DMI_BOARD_NAME, "R519/R719"), - }, - .callback = dmi_check_cb, - }, - { - .ident = "N150/N210/N220/N230", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, - "SAMSUNG ELECTRONICS CO., LTD."), - DMI_MATCH(DMI_PRODUCT_NAME, "N150/N210/N220/N230"), - DMI_MATCH(DMI_BOARD_NAME, "N150/N210/N220/N230"), - }, - .callback = dmi_check_cb, - }, - { - .ident = "N150P/N210P/N220P", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, - "SAMSUNG ELECTRONICS CO., LTD."), - DMI_MATCH(DMI_PRODUCT_NAME, "N150P/N210P/N220P"), - DMI_MATCH(DMI_BOARD_NAME, "N150P/N210P/N220P"), - }, - .callback = dmi_check_cb, - }, - { - .ident = "R530/R730", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "SAMSUNG ELECTRONICS CO., LTD."), - DMI_MATCH(DMI_PRODUCT_NAME, "R530/R730"), - DMI_MATCH(DMI_BOARD_NAME, "R530/R730"), - }, - .callback = dmi_check_cb, - }, - { - .ident = "NF110/NF210/NF310", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "SAMSUNG ELECTRONICS CO., LTD."), - DMI_MATCH(DMI_PRODUCT_NAME, "NF110/NF210/NF310"), - DMI_MATCH(DMI_BOARD_NAME, "NF110/NF210/NF310"), - }, - .callback = dmi_check_cb, - }, - { - .ident = "N145P/N250P/N260P", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "SAMSUNG ELECTRONICS CO., LTD."), - DMI_MATCH(DMI_PRODUCT_NAME, "N145P/N250P/N260P"), - DMI_MATCH(DMI_BOARD_NAME, "N145P/N250P/N260P"), - }, - .callback = dmi_check_cb, - }, - { - .ident = "R70/R71", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, - "SAMSUNG ELECTRONICS CO., LTD."), - DMI_MATCH(DMI_PRODUCT_NAME, "R70/R71"), - DMI_MATCH(DMI_BOARD_NAME, "R70/R71"), - }, - .callback = dmi_check_cb, - }, - { - .ident = "P460", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "SAMSUNG ELECTRONICS CO., LTD."), - DMI_MATCH(DMI_PRODUCT_NAME, "P460"), - DMI_MATCH(DMI_BOARD_NAME, "P460"), - }, - .callback = dmi_check_cb, - }, - { }, -}; -MODULE_DEVICE_TABLE(dmi, samsung_dmi_table); - -static int find_signature(void __iomem *memcheck, const char *testStr) -{ - int i = 0; - int loca; - - for (loca = 0; loca < 0xffff; loca++) { - char temp = readb(memcheck + loca); - - if (temp == testStr[i]) { - if (i == strlen(testStr)-1) - break; - ++i; - } else { - i = 0; - } - } - return loca; -} - -static int __init samsung_init(void) -{ - struct backlight_properties props; - struct sabi_retval sretval; - unsigned int ifaceP; - int i; - int loca; - int retval; - - mutex_init(&sabi_mutex); - - if (!force && !dmi_check_system(samsung_dmi_table)) - return -ENODEV; - - f0000_segment = ioremap_nocache(0xf0000, 0xffff); - if (!f0000_segment) { - pr_err("Can't map the segment at 0xf0000\n"); - return -EINVAL; - } - - /* Try to find one of the signatures in memory to find the header */ - for (i = 0; sabi_configs[i].test_string != 0; ++i) { - sabi_config = &sabi_configs[i]; - loca = find_signature(f0000_segment, sabi_config->test_string); - if (loca != 0xffff) - break; - } - - if (loca == 0xffff) { - pr_err("This computer does not support SABI\n"); - goto error_no_signature; - } - - /* point to the SMI port Number */ - loca += 1; - sabi = (f0000_segment + loca); - - if (debug) { - printk(KERN_DEBUG "This computer supports SABI==%x\n", - loca + 0xf0000 - 6); - printk(KERN_DEBUG "SABI header:\n"); - printk(KERN_DEBUG " SMI Port Number = 0x%04x\n", - readw(sabi + sabi_config->header_offsets.port)); - printk(KERN_DEBUG " SMI Interface Function = 0x%02x\n", - readb(sabi + sabi_config->header_offsets.iface_func)); - printk(KERN_DEBUG " SMI enable memory buffer = 0x%02x\n", - readb(sabi + sabi_config->header_offsets.en_mem)); - printk(KERN_DEBUG " SMI restore memory buffer = 0x%02x\n", - readb(sabi + sabi_config->header_offsets.re_mem)); - printk(KERN_DEBUG " SABI data offset = 0x%04x\n", - readw(sabi + sabi_config->header_offsets.data_offset)); - printk(KERN_DEBUG " SABI data segment = 0x%04x\n", - readw(sabi + sabi_config->header_offsets.data_segment)); - } - - /* Get a pointer to the SABI Interface */ - ifaceP = (readw(sabi + sabi_config->header_offsets.data_segment) & 0x0ffff) << 4; - ifaceP += readw(sabi + sabi_config->header_offsets.data_offset) & 0x0ffff; - sabi_iface = ioremap_nocache(ifaceP, 16); - if (!sabi_iface) { - pr_err("Can't remap %x\n", ifaceP); - goto exit; - } - if (debug) { - printk(KERN_DEBUG "ifaceP = 0x%08x\n", ifaceP); - printk(KERN_DEBUG "sabi_iface = %p\n", sabi_iface); - - test_backlight(); - test_wireless(); - - retval = sabi_get_command(sabi_config->commands.get_brightness, - &sretval); - printk(KERN_DEBUG "brightness = 0x%02x\n", sretval.retval[0]); - } - - /* Turn on "Linux" mode in the BIOS */ - if (sabi_config->commands.set_linux != 0xff) { - retval = sabi_set_command(sabi_config->commands.set_linux, - 0x81); - if (retval) { - pr_warn("Linux mode was not set!\n"); - goto error_no_platform; - } - } - - /* knock up a platform device to hang stuff off of */ - sdev = platform_device_register_simple("samsung", -1, NULL, 0); - if (IS_ERR(sdev)) - goto error_no_platform; - - /* create a backlight device to talk to this one */ - memset(&props, 0, sizeof(struct backlight_properties)); - props.type = BACKLIGHT_PLATFORM; - props.max_brightness = sabi_config->max_brightness; - backlight_device = backlight_device_register("samsung", &sdev->dev, - NULL, &backlight_ops, - &props); - if (IS_ERR(backlight_device)) - goto error_no_backlight; - - backlight_device->props.brightness = read_brightness(); - backlight_device->props.power = FB_BLANK_UNBLANK; - backlight_update_status(backlight_device); - - retval = init_wireless(sdev); - if (retval) - goto error_no_rfk; - - retval = device_create_file(&sdev->dev, &dev_attr_performance_level); - if (retval) - goto error_file_create; - -exit: - return 0; - -error_file_create: - destroy_wireless(); - -error_no_rfk: - backlight_device_unregister(backlight_device); - -error_no_backlight: - platform_device_unregister(sdev); - -error_no_platform: - iounmap(sabi_iface); - -error_no_signature: - iounmap(f0000_segment); - return -EINVAL; -} - -static void __exit samsung_exit(void) -{ - /* Turn off "Linux" mode in the BIOS */ - if (sabi_config->commands.set_linux != 0xff) - sabi_set_command(sabi_config->commands.set_linux, 0x80); - - device_remove_file(&sdev->dev, &dev_attr_performance_level); - backlight_device_unregister(backlight_device); - destroy_wireless(); - iounmap(sabi_iface); - iounmap(f0000_segment); - platform_device_unregister(sdev); -} - -module_init(samsung_init); -module_exit(samsung_exit); - -MODULE_AUTHOR("Greg Kroah-Hartman <gregkh@suse.de>"); -MODULE_DESCRIPTION("Samsung Backlight driver"); -MODULE_LICENSE("GPL"); diff --git a/drivers/xen/events.c b/drivers/xen/events.c index 42d6c930cc87..33167b43ac7e 100644 --- a/drivers/xen/events.c +++ b/drivers/xen/events.c @@ -912,8 +912,7 @@ int bind_evtchn_to_irqhandler(unsigned int evtchn, unsigned long irqflags, const char *devname, void *dev_id) { - unsigned int irq; - int retval; + int irq, retval; irq = bind_evtchn_to_irq(evtchn); if (irq < 0) @@ -955,8 +954,7 @@ int bind_virq_to_irqhandler(unsigned int virq, unsigned int cpu, irq_handler_t handler, unsigned long irqflags, const char *devname, void *dev_id) { - unsigned int irq; - int retval; + int irq, retval; irq = bind_virq_to_irq(virq, cpu); if (irq < 0) diff --git a/drivers/xen/manage.c b/drivers/xen/manage.c index 95143dd6904d..1ac94125bf93 100644 --- a/drivers/xen/manage.c +++ b/drivers/xen/manage.c @@ -61,7 +61,7 @@ static void xen_post_suspend(int cancelled) xen_mm_unpin_all(); } -#ifdef CONFIG_HIBERNATION +#ifdef CONFIG_HIBERNATE_CALLBACKS static int xen_suspend(void *data) { struct suspend_info *si = data; @@ -173,7 +173,7 @@ out: #endif shutting_down = SHUTDOWN_INVALID; } -#endif /* CONFIG_HIBERNATION */ +#endif /* CONFIG_HIBERNATE_CALLBACKS */ struct shutdown_handler { const char *command; @@ -202,7 +202,7 @@ static void shutdown_handler(struct xenbus_watch *watch, { "poweroff", do_poweroff }, { "halt", do_poweroff }, { "reboot", do_reboot }, -#ifdef CONFIG_HIBERNATION +#ifdef CONFIG_HIBERNATE_CALLBACKS { "suspend", do_suspend }, #endif {NULL, NULL}, diff --git a/fs/cifs/README b/fs/cifs/README index fe1683590828..74ab165fc646 100644 --- a/fs/cifs/README +++ b/fs/cifs/README @@ -685,22 +685,6 @@ LinuxExtensionsEnabled If set to one then the client will attempt to support and want to map the uid and gid fields to values supplied at mount (rather than the actual values, then set this to zero. (default 1) -Experimental When set to 1 used to enable certain experimental - features (currently enables multipage writes - when signing is enabled, the multipage write - performance enhancement was disabled when - signing turned on in case buffer was modified - just before it was sent, also this flag will - be used to use the new experimental directory change - notification code). When set to 2 enables - an additional experimental feature, "raw ntlmssp" - session establishment support (which allows - specifying "sec=ntlmssp" on mount). The Linux cifs - module will use ntlmv2 authentication encapsulated - in "raw ntlmssp" (not using SPNEGO) when - "sec=ntlmssp" is specified on mount. - This support also requires building cifs with - the CONFIG_CIFS_EXPERIMENTAL configuration flag. These experimental features and tracing can be enabled by changing flags in /proc/fs/cifs (after the cifs module has been installed or built into the diff --git a/fs/cifs/cache.c b/fs/cifs/cache.c index e654dfd092c3..53d57a3fe427 100644 --- a/fs/cifs/cache.c +++ b/fs/cifs/cache.c @@ -50,7 +50,7 @@ void cifs_fscache_unregister(void) */ struct cifs_server_key { uint16_t family; /* address family */ - uint16_t port; /* IP port */ + __be16 port; /* IP port */ union { struct in_addr ipv4_addr; struct in6_addr ipv6_addr; diff --git a/fs/cifs/cifs_debug.c b/fs/cifs/cifs_debug.c index 65829d32128c..30d01bc90855 100644 --- a/fs/cifs/cifs_debug.c +++ b/fs/cifs/cifs_debug.c @@ -423,7 +423,6 @@ static const struct file_operations cifs_lookup_cache_proc_fops; static const struct file_operations traceSMB_proc_fops; static const struct file_operations cifs_multiuser_mount_proc_fops; static const struct file_operations cifs_security_flags_proc_fops; -static const struct file_operations cifs_experimental_proc_fops; static const struct file_operations cifs_linux_ext_proc_fops; void @@ -441,8 +440,6 @@ cifs_proc_init(void) proc_create("cifsFYI", 0, proc_fs_cifs, &cifsFYI_proc_fops); proc_create("traceSMB", 0, proc_fs_cifs, &traceSMB_proc_fops); proc_create("OplockEnabled", 0, proc_fs_cifs, &cifs_oplock_proc_fops); - proc_create("Experimental", 0, proc_fs_cifs, - &cifs_experimental_proc_fops); proc_create("LinuxExtensionsEnabled", 0, proc_fs_cifs, &cifs_linux_ext_proc_fops); proc_create("MultiuserMount", 0, proc_fs_cifs, @@ -469,7 +466,6 @@ cifs_proc_clean(void) remove_proc_entry("OplockEnabled", proc_fs_cifs); remove_proc_entry("SecurityFlags", proc_fs_cifs); remove_proc_entry("LinuxExtensionsEnabled", proc_fs_cifs); - remove_proc_entry("Experimental", proc_fs_cifs); remove_proc_entry("LookupCacheEnabled", proc_fs_cifs); remove_proc_entry("fs/cifs", NULL); } @@ -550,45 +546,6 @@ static const struct file_operations cifs_oplock_proc_fops = { .write = cifs_oplock_proc_write, }; -static int cifs_experimental_proc_show(struct seq_file *m, void *v) -{ - seq_printf(m, "%d\n", experimEnabled); - return 0; -} - -static int cifs_experimental_proc_open(struct inode *inode, struct file *file) -{ - return single_open(file, cifs_experimental_proc_show, NULL); -} - -static ssize_t cifs_experimental_proc_write(struct file *file, - const char __user *buffer, size_t count, loff_t *ppos) -{ - char c; - int rc; - - rc = get_user(c, buffer); - if (rc) - return rc; - if (c == '0' || c == 'n' || c == 'N') - experimEnabled = 0; - else if (c == '1' || c == 'y' || c == 'Y') - experimEnabled = 1; - else if (c == '2') - experimEnabled = 2; - - return count; -} - -static const struct file_operations cifs_experimental_proc_fops = { - .owner = THIS_MODULE, - .open = cifs_experimental_proc_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, - .write = cifs_experimental_proc_write, -}; - static int cifs_linux_ext_proc_show(struct seq_file *m, void *v) { seq_printf(m, "%d\n", linuxExtEnabled); diff --git a/fs/cifs/cifs_spnego.c b/fs/cifs/cifs_spnego.c index 4dfba8283165..33d221394aca 100644 --- a/fs/cifs/cifs_spnego.c +++ b/fs/cifs/cifs_spnego.c @@ -113,7 +113,7 @@ cifs_get_spnego_key(struct cifsSesInfo *sesInfo) MAX_MECH_STR_LEN + UID_KEY_LEN + (sizeof(uid_t) * 2) + CREDUID_KEY_LEN + (sizeof(uid_t) * 2) + - USER_KEY_LEN + strlen(sesInfo->userName) + + USER_KEY_LEN + strlen(sesInfo->user_name) + PID_KEY_LEN + (sizeof(pid_t) * 2) + 1; spnego_key = ERR_PTR(-ENOMEM); @@ -153,7 +153,7 @@ cifs_get_spnego_key(struct cifsSesInfo *sesInfo) sprintf(dp, ";creduid=0x%x", sesInfo->cred_uid); dp = description + strlen(description); - sprintf(dp, ";user=%s", sesInfo->userName); + sprintf(dp, ";user=%s", sesInfo->user_name); dp = description + strlen(description); sprintf(dp, ";pid=0x%x", current->pid); diff --git a/fs/cifs/cifs_unicode.c b/fs/cifs/cifs_unicode.c index fc0fd4fde306..23d43cde4306 100644 --- a/fs/cifs/cifs_unicode.c +++ b/fs/cifs/cifs_unicode.c @@ -90,7 +90,7 @@ cifs_mapchar(char *target, const __u16 src_char, const struct nls_table *cp, case UNI_COLON: *target = ':'; break; - case UNI_ASTERIK: + case UNI_ASTERISK: *target = '*'; break; case UNI_QUESTION: @@ -264,40 +264,40 @@ cifs_strndup_from_ucs(const char *src, const int maxlen, const bool is_unicode, * names are little endian 16 bit Unicode on the wire */ int -cifsConvertToUCS(__le16 *target, const char *source, int maxlen, +cifsConvertToUCS(__le16 *target, const char *source, int srclen, const struct nls_table *cp, int mapChars) { int i, j, charlen; - int len_remaining = maxlen; char src_char; - __u16 temp; + __le16 dst_char; + wchar_t tmp; if (!mapChars) return cifs_strtoUCS(target, source, PATH_MAX, cp); - for (i = 0, j = 0; i < maxlen; j++) { + for (i = 0, j = 0; i < srclen; j++) { src_char = source[i]; switch (src_char) { case 0: - put_unaligned_le16(0, &target[j]); + put_unaligned(0, &target[j]); goto ctoUCS_out; case ':': - temp = UNI_COLON; + dst_char = cpu_to_le16(UNI_COLON); break; case '*': - temp = UNI_ASTERIK; + dst_char = cpu_to_le16(UNI_ASTERISK); break; case '?': - temp = UNI_QUESTION; + dst_char = cpu_to_le16(UNI_QUESTION); break; case '<': - temp = UNI_LESSTHAN; + dst_char = cpu_to_le16(UNI_LESSTHAN); break; case '>': - temp = UNI_GRTRTHAN; + dst_char = cpu_to_le16(UNI_GRTRTHAN); break; case '|': - temp = UNI_PIPE; + dst_char = cpu_to_le16(UNI_PIPE); break; /* * FIXME: We can not handle remapping backslash (UNI_SLASH) @@ -305,17 +305,17 @@ cifsConvertToUCS(__le16 *target, const char *source, int maxlen, * as they use backslash as separator. */ default: - charlen = cp->char2uni(source+i, len_remaining, - &temp); + charlen = cp->char2uni(source + i, srclen - i, &tmp); + dst_char = cpu_to_le16(tmp); + /* * if no match, use question mark, which at least in * some cases serves as wild card */ if (charlen < 1) { - temp = 0x003f; + dst_char = cpu_to_le16(0x003f); charlen = 1; } - len_remaining -= charlen; /* * character may take more than one byte in the source * string, but will take exactly two bytes in the @@ -324,9 +324,8 @@ cifsConvertToUCS(__le16 *target, const char *source, int maxlen, i += charlen; continue; } - put_unaligned_le16(temp, &target[j]); + put_unaligned(dst_char, &target[j]); i++; /* move to next char in source string */ - len_remaining--; } ctoUCS_out: diff --git a/fs/cifs/cifs_unicode.h b/fs/cifs/cifs_unicode.h index 7fe6b52df507..644dd882a560 100644 --- a/fs/cifs/cifs_unicode.h +++ b/fs/cifs/cifs_unicode.h @@ -44,7 +44,7 @@ * reserved symbols (along with \ and /), otherwise illegal to store * in filenames in NTFS */ -#define UNI_ASTERIK (__u16) ('*' + 0xF000) +#define UNI_ASTERISK (__u16) ('*' + 0xF000) #define UNI_QUESTION (__u16) ('?' + 0xF000) #define UNI_COLON (__u16) (':' + 0xF000) #define UNI_GRTRTHAN (__u16) ('>' + 0xF000) diff --git a/fs/cifs/cifsencrypt.c b/fs/cifs/cifsencrypt.c index a51585f9852b..d1a016be73ba 100644 --- a/fs/cifs/cifsencrypt.c +++ b/fs/cifs/cifsencrypt.c @@ -30,12 +30,13 @@ #include <linux/ctype.h> #include <linux/random.h> -/* Calculate and return the CIFS signature based on the mac key and SMB PDU */ -/* the 16 byte signature must be allocated by the caller */ -/* Note we only use the 1st eight bytes */ -/* Note that the smb header signature field on input contains the - sequence number before this function is called */ - +/* + * Calculate and return the CIFS signature based on the mac key and SMB PDU. + * The 16 byte signature must be allocated by the caller. Note we only use the + * 1st eight bytes and that the smb header signature field on input contains + * the sequence number before this function is called. Also, this function + * should be called with the server->srv_mutex held. + */ static int cifs_calculate_signature(const struct smb_hdr *cifs_pdu, struct TCP_Server_Info *server, char *signature) { @@ -209,8 +210,10 @@ int cifs_verify_signature(struct smb_hdr *cifs_pdu, cpu_to_le32(expected_sequence_number); cifs_pdu->Signature.Sequence.Reserved = 0; + mutex_lock(&server->srv_mutex); rc = cifs_calculate_signature(cifs_pdu, server, what_we_think_sig_should_be); + mutex_unlock(&server->srv_mutex); if (rc) return rc; @@ -469,15 +472,15 @@ static int calc_ntlmv2_hash(struct cifsSesInfo *ses, char *ntlmv2_hash, return rc; } - /* convert ses->userName to unicode and uppercase */ - len = strlen(ses->userName); + /* convert ses->user_name to unicode and uppercase */ + len = strlen(ses->user_name); user = kmalloc(2 + (len * 2), GFP_KERNEL); if (user == NULL) { cERROR(1, "calc_ntlmv2_hash: user mem alloc failure\n"); rc = -ENOMEM; goto calc_exit_2; } - len = cifs_strtoUCS((__le16 *)user, ses->userName, len, nls_cp); + len = cifs_strtoUCS((__le16 *)user, ses->user_name, len, nls_cp); UniStrupr(user); crypto_shash_update(&ses->server->secmech.sdeschmacmd5->shash, diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index f2970136d17d..5c412b33cd7c 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -53,7 +53,6 @@ int cifsFYI = 0; int cifsERROR = 1; int traceSMB = 0; unsigned int oplockEnabled = 1; -unsigned int experimEnabled = 0; unsigned int linuxExtEnabled = 1; unsigned int lookupCacheEnabled = 1; unsigned int multiuser_mount = 0; @@ -127,6 +126,7 @@ cifs_read_super(struct super_block *sb, void *data, kfree(cifs_sb); return rc; } + cifs_sb->bdi.ra_pages = default_backing_dev_info.ra_pages; #ifdef CONFIG_CIFS_DFS_UPCALL /* copy mount params to sb for use in submounts */ @@ -409,8 +409,8 @@ cifs_show_options(struct seq_file *s, struct vfsmount *m) if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MULTIUSER) seq_printf(s, ",multiuser"); - else if (tcon->ses->userName) - seq_printf(s, ",username=%s", tcon->ses->userName); + else if (tcon->ses->user_name) + seq_printf(s, ",username=%s", tcon->ses->user_name); if (tcon->ses->domainName) seq_printf(s, ",domain=%s", tcon->ses->domainName); diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index 17afb0fbcaed..a5d1106fcbde 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -37,10 +37,9 @@ #define MAX_TREE_SIZE (2 + MAX_SERVER_SIZE + 1 + MAX_SHARE_SIZE + 1) #define MAX_SERVER_SIZE 15 -#define MAX_SHARE_SIZE 64 /* used to be 20, this should still be enough */ -#define MAX_USERNAME_SIZE 32 /* 32 is to allow for 15 char names + null - termination then *2 for unicode versions */ -#define MAX_PASSWORD_SIZE 512 /* max for windows seems to be 256 wide chars */ +#define MAX_SHARE_SIZE 80 +#define MAX_USERNAME_SIZE 256 /* reasonable maximum for current servers */ +#define MAX_PASSWORD_SIZE 512 /* max for windows seems to be 256 wide chars */ #define CIFS_MIN_RCV_POOL 4 @@ -92,7 +91,8 @@ enum statusEnum { CifsNew = 0, CifsGood, CifsExiting, - CifsNeedReconnect + CifsNeedReconnect, + CifsNeedNegotiate }; enum securityEnum { @@ -274,7 +274,7 @@ struct cifsSesInfo { int capabilities; char serverName[SERVER_NAME_LEN_WITH_NULL * 2]; /* BB make bigger for TCP names - will ipv6 and sctp addresses fit? */ - char userName[MAX_USERNAME_SIZE + 1]; + char *user_name; char *domainName; char *password; struct session_key auth_key; @@ -817,7 +817,6 @@ GLOBAL_EXTERN unsigned int multiuser_mount; /* if enabled allows new sessions have the uid/password or Kerberos credential or equivalent for current user */ GLOBAL_EXTERN unsigned int oplockEnabled; -GLOBAL_EXTERN unsigned int experimEnabled; GLOBAL_EXTERN unsigned int lookupCacheEnabled; GLOBAL_EXTERN unsigned int global_secflags; /* if on, session setup sent with more secure ntlmssp2 challenge/resp */ diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c index 2644a5d6cc67..df959bae6728 100644 --- a/fs/cifs/cifssmb.c +++ b/fs/cifs/cifssmb.c @@ -142,9 +142,9 @@ cifs_reconnect_tcon(struct cifsTconInfo *tcon, int smb_command) */ while (server->tcpStatus == CifsNeedReconnect) { wait_event_interruptible_timeout(server->response_q, - (server->tcpStatus == CifsGood), 10 * HZ); + (server->tcpStatus != CifsNeedReconnect), 10 * HZ); - /* is TCP session is reestablished now ?*/ + /* are we still trying to reconnect? */ if (server->tcpStatus != CifsNeedReconnect) break; @@ -729,7 +729,7 @@ CIFSSMBEcho(struct TCP_Server_Info *server) return rc; /* set up echo request */ - smb->hdr.Tid = cpu_to_le16(0xffff); + smb->hdr.Tid = 0xffff; smb->hdr.WordCount = 1; put_unaligned_le16(1, &smb->EchoCount); put_bcc_le(1, &smb->hdr); @@ -1884,10 +1884,10 @@ CIFSSMBPosixLock(const int xid, struct cifsTconInfo *tcon, __constant_cpu_to_le16(CIFS_WRLCK)) pLockData->fl_type = F_WRLCK; - pLockData->fl_start = parm_data->start; - pLockData->fl_end = parm_data->start + - parm_data->length - 1; - pLockData->fl_pid = parm_data->pid; + pLockData->fl_start = le64_to_cpu(parm_data->start); + pLockData->fl_end = pLockData->fl_start + + le64_to_cpu(parm_data->length) - 1; + pLockData->fl_pid = le32_to_cpu(parm_data->pid); } } diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 6e2b2addfc78..db9d55b507d0 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -199,8 +199,7 @@ cifs_reconnect(struct TCP_Server_Info *server) } spin_unlock(&GlobalMid_Lock); - while ((server->tcpStatus != CifsExiting) && - (server->tcpStatus != CifsGood)) { + while (server->tcpStatus == CifsNeedReconnect) { try_to_freeze(); /* we should try only the port we connected to before */ @@ -212,7 +211,7 @@ cifs_reconnect(struct TCP_Server_Info *server) atomic_inc(&tcpSesReconnectCount); spin_lock(&GlobalMid_Lock); if (server->tcpStatus != CifsExiting) - server->tcpStatus = CifsGood; + server->tcpStatus = CifsNeedNegotiate; spin_unlock(&GlobalMid_Lock); } } @@ -248,24 +247,24 @@ static int check2ndT2(struct smb_hdr *pSMB, unsigned int maxBufSize) total_data_size = get_unaligned_le16(&pSMBt->t2_rsp.TotalDataCount); data_in_this_rsp = get_unaligned_le16(&pSMBt->t2_rsp.DataCount); - remaining = total_data_size - data_in_this_rsp; - - if (remaining == 0) + if (total_data_size == data_in_this_rsp) return 0; - else if (remaining < 0) { + else if (total_data_size < data_in_this_rsp) { cFYI(1, "total data %d smaller than data in frame %d", total_data_size, data_in_this_rsp); return -EINVAL; - } else { - cFYI(1, "missing %d bytes from transact2, check next response", - remaining); - if (total_data_size > maxBufSize) { - cERROR(1, "TotalDataSize %d is over maximum buffer %d", - total_data_size, maxBufSize); - return -EINVAL; - } - return remaining; } + + remaining = total_data_size - data_in_this_rsp; + + cFYI(1, "missing %d bytes from transact2, check next response", + remaining); + if (total_data_size > maxBufSize) { + cERROR(1, "TotalDataSize %d is over maximum buffer %d", + total_data_size, maxBufSize); + return -EINVAL; + } + return remaining; } static int coalesce_t2(struct smb_hdr *psecond, struct smb_hdr *pTargetSMB) @@ -421,7 +420,7 @@ cifs_demultiplex_thread(struct TCP_Server_Info *server) pdu_length = 4; /* enough to get RFC1001 header */ incomplete_rcv: - if (echo_retries > 0 && + if (echo_retries > 0 && server->tcpStatus == CifsGood && time_after(jiffies, server->lstrp + (echo_retries * SMB_ECHO_INTERVAL))) { cERROR(1, "Server %s has not responded in %d seconds. " @@ -881,7 +880,8 @@ cifs_parse_mount_options(char *options, const char *devname, /* null user, ie anonymous, authentication */ vol->nullauth = 1; } - if (strnlen(value, 200) < 200) { + if (strnlen(value, MAX_USERNAME_SIZE) < + MAX_USERNAME_SIZE) { vol->username = value; } else { printk(KERN_WARNING "CIFS: username too long\n"); @@ -1472,7 +1472,7 @@ srcip_matches(struct sockaddr *srcaddr, struct sockaddr *rhs) static bool match_port(struct TCP_Server_Info *server, struct sockaddr *addr) { - unsigned short int port, *sport; + __be16 port, *sport; switch (addr->sa_family) { case AF_INET: @@ -1765,6 +1765,7 @@ cifs_get_tcp_session(struct smb_vol *volume_info) module_put(THIS_MODULE); goto out_err_crypto_release; } + tcp_ses->tcpStatus = CifsNeedNegotiate; /* thread spawned, put it on the list */ spin_lock(&cifs_tcp_ses_lock); @@ -1808,7 +1809,9 @@ cifs_find_smb_ses(struct TCP_Server_Info *server, struct smb_vol *vol) break; default: /* anything else takes username/password */ - if (strncmp(ses->userName, vol->username, + if (ses->user_name == NULL) + continue; + if (strncmp(ses->user_name, vol->username, MAX_USERNAME_SIZE)) continue; if (strlen(vol->username) != 0 && @@ -1851,6 +1854,8 @@ cifs_put_smb_ses(struct cifsSesInfo *ses) cifs_put_tcp_session(server); } +static bool warned_on_ntlm; /* globals init to false automatically */ + static struct cifsSesInfo * cifs_get_smb_ses(struct TCP_Server_Info *server, struct smb_vol *volume_info) { @@ -1906,9 +1911,11 @@ cifs_get_smb_ses(struct TCP_Server_Info *server, struct smb_vol *volume_info) else sprintf(ses->serverName, "%pI4", &addr->sin_addr); - if (volume_info->username) - strncpy(ses->userName, volume_info->username, - MAX_USERNAME_SIZE); + if (volume_info->username) { + ses->user_name = kstrdup(volume_info->username, GFP_KERNEL); + if (!ses->user_name) + goto get_ses_fail; + } /* volume_info->password freed at unmount */ if (volume_info->password) { @@ -1923,6 +1930,15 @@ cifs_get_smb_ses(struct TCP_Server_Info *server, struct smb_vol *volume_info) } ses->cred_uid = volume_info->cred_uid; ses->linux_uid = volume_info->linux_uid; + + /* ntlmv2 is much stronger than ntlm security, and has been broadly + supported for many years, time to update default security mechanism */ + if ((volume_info->secFlg == 0) && warned_on_ntlm == false) { + warned_on_ntlm = true; + cERROR(1, "default security mechanism requested. The default " + "security mechanism will be upgraded from ntlm to " + "ntlmv2 in kernel release 2.6.41"); + } ses->overrideSecFlg = volume_info->secFlg; mutex_lock(&ses->session_mutex); @@ -2276,7 +2292,7 @@ static int generic_ip_connect(struct TCP_Server_Info *server) { int rc = 0; - unsigned short int sport; + __be16 sport; int slen, sfamily; struct socket *socket = server->ssocket; struct sockaddr *saddr; @@ -2361,7 +2377,7 @@ generic_ip_connect(struct TCP_Server_Info *server) static int ip_connect(struct TCP_Server_Info *server) { - unsigned short int *sport; + __be16 *sport; struct sockaddr_in6 *addr6 = (struct sockaddr_in6 *)&server->dstaddr; struct sockaddr_in *addr = (struct sockaddr_in *)&server->dstaddr; @@ -2826,7 +2842,7 @@ try_mount_again: remote_path_check: /* check if a whole path (including prepath) is not remote */ - if (!rc && cifs_sb->prepathlen && tcon) { + if (!rc && tcon) { /* build_path_to_root works only when we have a valid tcon */ full_path = cifs_build_path_to_root(cifs_sb, tcon); if (full_path == NULL) { diff --git a/fs/cifs/file.c b/fs/cifs/file.c index c27d236738fc..faf59529e847 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -575,8 +575,10 @@ reopen_error_exit: int cifs_close(struct inode *inode, struct file *file) { - cifsFileInfo_put(file->private_data); - file->private_data = NULL; + if (file->private_data != NULL) { + cifsFileInfo_put(file->private_data); + file->private_data = NULL; + } /* return code from the ->release op is always ignored */ return 0; @@ -970,6 +972,9 @@ static ssize_t cifs_write(struct cifsFileInfo *open_file, total_written += bytes_written) { rc = -EAGAIN; while (rc == -EAGAIN) { + struct kvec iov[2]; + unsigned int len; + if (open_file->invalidHandle) { /* we could deadlock if we called filemap_fdatawait from here so tell @@ -979,31 +984,14 @@ static ssize_t cifs_write(struct cifsFileInfo *open_file, if (rc != 0) break; } - if (experimEnabled || (pTcon->ses->server && - ((pTcon->ses->server->secMode & - (SECMODE_SIGN_REQUIRED | SECMODE_SIGN_ENABLED)) - == 0))) { - struct kvec iov[2]; - unsigned int len; - - len = min((size_t)cifs_sb->wsize, - write_size - total_written); - /* iov[0] is reserved for smb header */ - iov[1].iov_base = (char *)write_data + - total_written; - iov[1].iov_len = len; - rc = CIFSSMBWrite2(xid, pTcon, - open_file->netfid, len, - *poffset, &bytes_written, - iov, 1, 0); - } else - rc = CIFSSMBWrite(xid, pTcon, - open_file->netfid, - min_t(const int, cifs_sb->wsize, - write_size - total_written), - *poffset, &bytes_written, - write_data + total_written, - NULL, 0); + + len = min((size_t)cifs_sb->wsize, + write_size - total_written); + /* iov[0] is reserved for smb header */ + iov[1].iov_base = (char *)write_data + total_written; + iov[1].iov_len = len; + rc = CIFSSMBWrite2(xid, pTcon, open_file->netfid, len, + *poffset, &bytes_written, iov, 1, 0); } if (rc || (bytes_written == 0)) { if (total_written) @@ -1240,12 +1228,6 @@ static int cifs_writepages(struct address_space *mapping, } tcon = tlink_tcon(open_file->tlink); - if (!experimEnabled && tcon->ses->server->secMode & - (SECMODE_SIGN_REQUIRED | SECMODE_SIGN_ENABLED)) { - cifsFileInfo_put(open_file); - kfree(iov); - return generic_writepages(mapping, wbc); - } cifsFileInfo_put(open_file); xid = GetXid(); @@ -1980,6 +1962,24 @@ static ssize_t cifs_read(struct file *file, char *read_data, size_t read_size, return total_read; } +/* + * If the page is mmap'ed into a process' page tables, then we need to make + * sure that it doesn't change while being written back. + */ +static int +cifs_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) +{ + struct page *page = vmf->page; + + lock_page(page); + return VM_FAULT_LOCKED; +} + +static struct vm_operations_struct cifs_file_vm_ops = { + .fault = filemap_fault, + .page_mkwrite = cifs_page_mkwrite, +}; + int cifs_file_strict_mmap(struct file *file, struct vm_area_struct *vma) { int rc, xid; @@ -1991,6 +1991,8 @@ int cifs_file_strict_mmap(struct file *file, struct vm_area_struct *vma) cifs_invalidate_mapping(inode); rc = generic_file_mmap(file, vma); + if (rc == 0) + vma->vm_ops = &cifs_file_vm_ops; FreeXid(xid); return rc; } @@ -2007,6 +2009,8 @@ int cifs_file_mmap(struct file *file, struct vm_area_struct *vma) return rc; } rc = generic_file_mmap(file, vma); + if (rc == 0) + vma->vm_ops = &cifs_file_vm_ops; FreeXid(xid); return rc; } diff --git a/fs/cifs/link.c b/fs/cifs/link.c index e8804d373404..ce417a9764a3 100644 --- a/fs/cifs/link.c +++ b/fs/cifs/link.c @@ -239,7 +239,7 @@ CIFSQueryMFSymLink(const int xid, struct cifsTconInfo *tcon, if (rc != 0) return rc; - if (file_info.EndOfFile != CIFS_MF_SYMLINK_FILE_SIZE) { + if (file_info.EndOfFile != cpu_to_le64(CIFS_MF_SYMLINK_FILE_SIZE)) { CIFSSMBClose(xid, tcon, netfid); /* it's not a symlink */ return -EINVAL; @@ -316,7 +316,7 @@ CIFSCheckMFSymlink(struct cifs_fattr *fattr, if (rc != 0) goto out; - if (file_info.EndOfFile != CIFS_MF_SYMLINK_FILE_SIZE) { + if (file_info.EndOfFile != cpu_to_le64(CIFS_MF_SYMLINK_FILE_SIZE)) { CIFSSMBClose(xid, pTcon, netfid); /* it's not a symlink */ goto out; diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c index 2a930a752a78..0c684ae4c071 100644 --- a/fs/cifs/misc.c +++ b/fs/cifs/misc.c @@ -100,6 +100,7 @@ sesInfoFree(struct cifsSesInfo *buf_to_free) memset(buf_to_free->password, 0, strlen(buf_to_free->password)); kfree(buf_to_free->password); } + kfree(buf_to_free->user_name); kfree(buf_to_free->domainName); kfree(buf_to_free); } @@ -520,7 +521,7 @@ is_valid_oplock_break(struct smb_hdr *buf, struct TCP_Server_Info *srv) (struct smb_com_transaction_change_notify_rsp *)buf; struct file_notify_information *pnotify; __u32 data_offset = 0; - if (pSMBr->ByteCount > sizeof(struct file_notify_information)) { + if (get_bcc_le(buf) > sizeof(struct file_notify_information)) { data_offset = le32_to_cpu(pSMBr->DataOffset); pnotify = (struct file_notify_information *) diff --git a/fs/cifs/sess.c b/fs/cifs/sess.c index 16765703131b..f6728eb6f4b9 100644 --- a/fs/cifs/sess.c +++ b/fs/cifs/sess.c @@ -219,12 +219,12 @@ static void unicode_ssetup_strings(char **pbcc_area, struct cifsSesInfo *ses, bcc_ptr++; } */ /* copy user */ - if (ses->userName == NULL) { + if (ses->user_name == NULL) { /* null user mount */ *bcc_ptr = 0; *(bcc_ptr+1) = 0; } else { - bytes_ret = cifs_strtoUCS((__le16 *) bcc_ptr, ses->userName, + bytes_ret = cifs_strtoUCS((__le16 *) bcc_ptr, ses->user_name, MAX_USERNAME_SIZE, nls_cp); } bcc_ptr += 2 * bytes_ret; @@ -244,12 +244,11 @@ static void ascii_ssetup_strings(char **pbcc_area, struct cifsSesInfo *ses, /* copy user */ /* BB what about null user mounts - check that we do this BB */ /* copy user */ - if (ses->userName == NULL) { - /* BB what about null user mounts - check that we do this BB */ - } else { - strncpy(bcc_ptr, ses->userName, MAX_USERNAME_SIZE); - } - bcc_ptr += strnlen(ses->userName, MAX_USERNAME_SIZE); + if (ses->user_name != NULL) + strncpy(bcc_ptr, ses->user_name, MAX_USERNAME_SIZE); + /* else null user mount */ + + bcc_ptr += strnlen(ses->user_name, MAX_USERNAME_SIZE); *bcc_ptr = 0; bcc_ptr++; /* account for null termination */ @@ -405,8 +404,8 @@ static int decode_ntlmssp_challenge(char *bcc_ptr, int blob_len, /* BB spec says that if AvId field of MsvAvTimestamp is populated then we must set the MIC field of the AUTHENTICATE_MESSAGE */ ses->ntlmssp->server_flags = le32_to_cpu(pblob->NegotiateFlags); - tioffset = cpu_to_le16(pblob->TargetInfoArray.BufferOffset); - tilen = cpu_to_le16(pblob->TargetInfoArray.Length); + tioffset = le32_to_cpu(pblob->TargetInfoArray.BufferOffset); + tilen = le16_to_cpu(pblob->TargetInfoArray.Length); if (tilen) { ses->auth_key.response = kmalloc(tilen, GFP_KERNEL); if (!ses->auth_key.response) { @@ -523,14 +522,14 @@ static int build_ntlmssp_auth_blob(unsigned char *pbuffer, tmp += len; } - if (ses->userName == NULL) { + if (ses->user_name == NULL) { sec_blob->UserName.BufferOffset = cpu_to_le32(tmp - pbuffer); sec_blob->UserName.Length = 0; sec_blob->UserName.MaximumLength = 0; tmp += 2; } else { int len; - len = cifs_strtoUCS((__le16 *)tmp, ses->userName, + len = cifs_strtoUCS((__le16 *)tmp, ses->user_name, MAX_USERNAME_SIZE, nls_cp); len *= 2; /* unicode is 2 bytes each */ sec_blob->UserName.BufferOffset = cpu_to_le32(tmp - pbuffer); diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h index e25e99bf7ee1..d0f53538a57f 100644 --- a/fs/ext4/ext4_jbd2.h +++ b/fs/ext4/ext4_jbd2.h @@ -86,8 +86,8 @@ #ifdef CONFIG_QUOTA /* Amount of blocks needed for quota update - we know that the structure was - * allocated so we need to update only inode+data */ -#define EXT4_QUOTA_TRANS_BLOCKS(sb) (test_opt(sb, QUOTA) ? 2 : 0) + * allocated so we need to update only data block */ +#define EXT4_QUOTA_TRANS_BLOCKS(sb) (test_opt(sb, QUOTA) ? 1 : 0) /* Amount of blocks needed for quota insert/delete - we do some block writes * but inode, sb and group updates are done only once */ #define EXT4_QUOTA_INIT_BLOCKS(sb) (test_opt(sb, QUOTA) ? (DQUOT_INIT_ALLOC*\ diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c index 4673bc05274f..e9473cbe80df 100644 --- a/fs/ext4/fsync.c +++ b/fs/ext4/fsync.c @@ -125,9 +125,11 @@ extern int ext4_flush_completed_IO(struct inode *inode) * the parent directory's parent as well, and so on recursively, if * they are also freshly created. */ -static void ext4_sync_parent(struct inode *inode) +static int ext4_sync_parent(struct inode *inode) { + struct writeback_control wbc; struct dentry *dentry = NULL; + int ret = 0; while (inode && ext4_test_inode_state(inode, EXT4_STATE_NEWENTRY)) { ext4_clear_inode_state(inode, EXT4_STATE_NEWENTRY); @@ -136,8 +138,17 @@ static void ext4_sync_parent(struct inode *inode) if (!dentry || !dentry->d_parent || !dentry->d_parent->d_inode) break; inode = dentry->d_parent->d_inode; - sync_mapping_buffers(inode->i_mapping); + ret = sync_mapping_buffers(inode->i_mapping); + if (ret) + break; + memset(&wbc, 0, sizeof(wbc)); + wbc.sync_mode = WB_SYNC_ALL; + wbc.nr_to_write = 0; /* only write out the inode */ + ret = sync_inode(inode, &wbc); + if (ret) + break; } + return ret; } /* @@ -176,7 +187,7 @@ int ext4_sync_file(struct file *file, int datasync) if (!journal) { ret = generic_file_fsync(file, datasync); if (!ret && !list_empty(&inode->i_dentry)) - ext4_sync_parent(inode); + ret = ext4_sync_parent(inode); goto out; } diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index ad8e303c0d29..f2fa5e8a582c 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -2502,6 +2502,7 @@ static int ext4_da_get_block_prep(struct inode *inode, sector_t iblock, * for partial write. */ set_buffer_new(bh); + set_buffer_mapped(bh); } return 0; } @@ -4429,8 +4430,8 @@ void ext4_truncate(struct inode *inode) Indirect chain[4]; Indirect *partial; __le32 nr = 0; - int n; - ext4_lblk_t last_block; + int n = 0; + ext4_lblk_t last_block, max_block; unsigned blocksize = inode->i_sb->s_blocksize; trace_ext4_truncate_enter(inode); @@ -4455,14 +4456,18 @@ void ext4_truncate(struct inode *inode) last_block = (inode->i_size + blocksize-1) >> EXT4_BLOCK_SIZE_BITS(inode->i_sb); + max_block = (EXT4_SB(inode->i_sb)->s_bitmap_maxbytes + blocksize-1) + >> EXT4_BLOCK_SIZE_BITS(inode->i_sb); if (inode->i_size & (blocksize - 1)) if (ext4_block_truncate_page(handle, mapping, inode->i_size)) goto out_stop; - n = ext4_block_to_path(inode, last_block, offsets, NULL); - if (n == 0) - goto out_stop; /* error */ + if (last_block != max_block) { + n = ext4_block_to_path(inode, last_block, offsets, NULL); + if (n == 0) + goto out_stop; /* error */ + } /* * OK. This truncate is going to happen. We add the inode to the @@ -4493,7 +4498,13 @@ void ext4_truncate(struct inode *inode) */ ei->i_disksize = inode->i_size; - if (n == 1) { /* direct blocks */ + if (last_block == max_block) { + /* + * It is unnecessary to free any data blocks if last_block is + * equal to the indirect block limit. + */ + goto out_unlock; + } else if (n == 1) { /* direct blocks */ ext4_free_data(handle, inode, NULL, i_data+offsets[0], i_data + EXT4_NDIR_BLOCKS); goto do_indirects; @@ -4553,6 +4564,7 @@ do_indirects: ; } +out_unlock: up_write(&ei->i_data_sem); inode->i_mtime = inode->i_ctime = ext4_current_time(inode); ext4_mark_inode_dirty(handle, inode); @@ -5398,13 +5410,12 @@ static int ext4_indirect_trans_blocks(struct inode *inode, int nrblocks, /* if nrblocks are contiguous */ if (chunk) { /* - * With N contiguous data blocks, it need at most - * N/EXT4_ADDR_PER_BLOCK(inode->i_sb) indirect blocks - * 2 dindirect blocks - * 1 tindirect block + * With N contiguous data blocks, we need at most + * N/EXT4_ADDR_PER_BLOCK(inode->i_sb) + 1 indirect blocks, + * 2 dindirect blocks, and 1 tindirect block */ - indirects = nrblocks / EXT4_ADDR_PER_BLOCK(inode->i_sb); - return indirects + 3; + return DIV_ROUND_UP(nrblocks, + EXT4_ADDR_PER_BLOCK(inode->i_sb)) + 4; } /* * if nrblocks are not contiguous, worse case, each block touch diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 056474b7b8e0..8553dfb310af 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -242,27 +242,44 @@ static void ext4_put_nojournal(handle_t *handle) * journal_end calls result in the superblock being marked dirty, so * that sync() will call the filesystem's write_super callback if * appropriate. + * + * To avoid j_barrier hold in userspace when a user calls freeze(), + * ext4 prevents a new handle from being started by s_frozen, which + * is in an upper layer. */ handle_t *ext4_journal_start_sb(struct super_block *sb, int nblocks) { journal_t *journal; + handle_t *handle; if (sb->s_flags & MS_RDONLY) return ERR_PTR(-EROFS); - vfs_check_frozen(sb, SB_FREEZE_TRANS); - /* Special case here: if the journal has aborted behind our - * backs (eg. EIO in the commit thread), then we still need to - * take the FS itself readonly cleanly. */ journal = EXT4_SB(sb)->s_journal; - if (journal) { - if (is_journal_aborted(journal)) { - ext4_abort(sb, "Detected aborted journal"); - return ERR_PTR(-EROFS); - } - return jbd2_journal_start(journal, nblocks); + handle = ext4_journal_current_handle(); + + /* + * If a handle has been started, it should be allowed to + * finish, otherwise deadlock could happen between freeze + * and others(e.g. truncate) due to the restart of the + * journal handle if the filesystem is forzen and active + * handles are not stopped. + */ + if (!handle) + vfs_check_frozen(sb, SB_FREEZE_TRANS); + + if (!journal) + return ext4_get_nojournal(); + /* + * Special case here: if the journal has aborted behind our + * backs (eg. EIO in the commit thread), then we still need to + * take the FS itself readonly cleanly. + */ + if (is_journal_aborted(journal)) { + ext4_abort(sb, "Detected aborted journal"); + return ERR_PTR(-EROFS); } - return ext4_get_nojournal(); + return jbd2_journal_start(journal, nblocks); } /* @@ -2975,6 +2992,12 @@ static int ext4_register_li_request(struct super_block *sb, mutex_unlock(&ext4_li_info->li_list_mtx); sbi->s_li_request = elr; + /* + * set elr to NULL here since it has been inserted to + * the request_list and the removal and free of it is + * handled by ext4_clear_request_list from now on. + */ + elr = NULL; if (!(ext4_li_info->li_state & EXT4_LAZYINIT_RUNNING)) { ret = ext4_run_lazyinit_thread(); @@ -3385,6 +3408,10 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) get_random_bytes(&sbi->s_next_generation, sizeof(u32)); spin_lock_init(&sbi->s_next_gen_lock); + init_timer(&sbi->s_err_report); + sbi->s_err_report.function = print_daily_error_info; + sbi->s_err_report.data = (unsigned long) sb; + err = percpu_counter_init(&sbi->s_freeblocks_counter, ext4_count_free_blocks(sb)); if (!err) { @@ -3646,9 +3673,6 @@ no_journal: "Opts: %s%s%s", descr, sbi->s_es->s_mount_opts, *sbi->s_es->s_mount_opts ? "; " : "", orig_data); - init_timer(&sbi->s_err_report); - sbi->s_err_report.function = print_daily_error_info; - sbi->s_err_report.data = (unsigned long) sb; if (es->s_error_count) mod_timer(&sbi->s_err_report, jiffies + 300*HZ); /* 5 minutes */ @@ -3672,6 +3696,7 @@ failed_mount_wq: sbi->s_journal = NULL; } failed_mount3: + del_timer(&sbi->s_err_report); if (sbi->s_flex_groups) { if (is_vmalloc_addr(sbi->s_flex_groups)) vfree(sbi->s_flex_groups); @@ -4138,6 +4163,11 @@ static int ext4_sync_fs(struct super_block *sb, int wait) /* * LVM calls this function before a (read-only) snapshot is created. This * gives us a chance to flush the journal completely and mark the fs clean. + * + * Note that only this function cannot bring a filesystem to be in a clean + * state independently, because ext4 prevents a new handle from being started + * by @sb->s_frozen, which stays in an upper layer. It thus needs help from + * the upper layer. */ static int ext4_freeze(struct super_block *sb) { @@ -4614,11 +4644,24 @@ static int ext4_quota_on(struct super_block *sb, int type, int format_id, static int ext4_quota_off(struct super_block *sb, int type) { + struct inode *inode = sb_dqopt(sb)->files[type]; + handle_t *handle; + /* Force all delayed allocation blocks to be allocated. * Caller already holds s_umount sem */ if (test_opt(sb, DELALLOC)) sync_filesystem(sb); + /* Update modification times of quota files when userspace can + * start looking at them */ + handle = ext4_journal_start(inode, 1); + if (IS_ERR(handle)) + goto out; + inode->i_mtime = inode->i_ctime = CURRENT_TIME; + ext4_mark_inode_dirty(handle, inode); + ext4_journal_stop(handle); + +out: return dquot_quota_off(sb, type); } @@ -4714,9 +4757,8 @@ out: if (inode->i_size < off + len) { i_size_write(inode, off + len); EXT4_I(inode)->i_disksize = inode->i_size; + ext4_mark_inode_dirty(handle, inode); } - inode->i_mtime = inode->i_ctime = CURRENT_TIME; - ext4_mark_inode_dirty(handle, inode); mutex_unlock(&inode->i_mutex); return len; } diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c index 20af62f4304b..6e28000a4b21 100644 --- a/fs/jbd2/commit.c +++ b/fs/jbd2/commit.c @@ -105,6 +105,8 @@ static int journal_submit_commit_record(journal_t *journal, int ret; struct timespec now = current_kernel_time(); + *cbh = NULL; + if (is_journal_aborted(journal)) return 0; @@ -806,7 +808,7 @@ wait_for_iobuf: if (err) __jbd2_journal_abort_hard(journal); } - if (!err && !is_journal_aborted(journal)) + if (cbh) err = journal_wait_on_commit_record(journal, cbh); if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT) && diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index aba8ebaec25c..e0ec3db1c395 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -2413,10 +2413,12 @@ const char *jbd2_dev_to_name(dev_t device) new_dev = kmalloc(sizeof(struct devname_cache), GFP_KERNEL); if (!new_dev) return "NODEV-ALLOCFAILURE"; /* Something non-NULL */ + bd = bdget(device); spin_lock(&devname_cache_lock); if (devcache[i]) { if (devcache[i]->device == device) { kfree(new_dev); + bdput(bd); ret = devcache[i]->devname; spin_unlock(&devname_cache_lock); return ret; @@ -2425,7 +2427,6 @@ const char *jbd2_dev_to_name(dev_t device) } devcache[i] = new_dev; devcache[i]->device = device; - bd = bdget(device); if (bd) { bdevname(bd, devcache[i]->devname); bdput(bd); diff --git a/fs/namespace.c b/fs/namespace.c index 7dba2ed03429..d99bcf59e4c2 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -1030,18 +1030,6 @@ const struct seq_operations mounts_op = { .show = show_vfsmnt }; -static int uuid_is_nil(u8 *uuid) -{ - int i; - u8 *cp = (u8 *)uuid; - - for (i = 0; i < 16; i++) { - if (*cp++) - return 0; - } - return 1; -} - static int show_mountinfo(struct seq_file *m, void *v) { struct proc_mounts *p = m->private; @@ -1085,10 +1073,6 @@ static int show_mountinfo(struct seq_file *m, void *v) if (IS_MNT_UNBINDABLE(mnt)) seq_puts(m, " unbindable"); - if (!uuid_is_nil(mnt->mnt_sb->s_uuid)) - /* print the uuid */ - seq_printf(m, " uuid:%pU", mnt->mnt_sb->s_uuid); - /* Filesystem specific data */ seq_puts(m, " - "); show_type(m, sb); diff --git a/fs/nfs/write.c b/fs/nfs/write.c index af0c6279a4a7..e4cbc11a74ab 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -542,11 +542,15 @@ nfs_scan_commit(struct inode *inode, struct list_head *dst, pgoff_t idx_start, u if (!nfs_need_commit(nfsi)) return 0; + spin_lock(&inode->i_lock); ret = nfs_scan_list(nfsi, dst, idx_start, npages, NFS_PAGE_TAG_COMMIT); if (ret > 0) nfsi->ncommit -= ret; + spin_unlock(&inode->i_lock); + if (nfs_need_commit(NFS_I(inode))) __mark_inode_dirty(inode, I_DIRTY_DATASYNC); + return ret; } #else @@ -1483,9 +1487,7 @@ int nfs_commit_inode(struct inode *inode, int how) res = nfs_commit_set_lock(NFS_I(inode), may_wait); if (res <= 0) goto out_mark_dirty; - spin_lock(&inode->i_lock); res = nfs_scan_commit(inode, &head, 0, 0); - spin_unlock(&inode->i_lock); if (res) { int error; diff --git a/fs/nfsd/lockd.c b/fs/nfsd/lockd.c index 0c6d81670137..7c831a2731fa 100644 --- a/fs/nfsd/lockd.c +++ b/fs/nfsd/lockd.c @@ -38,7 +38,6 @@ nlm_fopen(struct svc_rqst *rqstp, struct nfs_fh *f, struct file **filp) exp_readlock(); nfserr = nfsd_open(rqstp, &fh, S_IFREG, NFSD_MAY_LOCK, filp); fh_put(&fh); - rqstp->rq_client = NULL; exp_readunlock(); /* We return nlm error codes as nlm doesn't know * about nfsd, but nfsd does know about nlm.. diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 4b36ec3eb8ea..aa309aa93fe8 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -397,10 +397,13 @@ static void unhash_generic_stateid(struct nfs4_stateid *stp) static void free_generic_stateid(struct nfs4_stateid *stp) { - int oflag = nfs4_access_bmap_to_omode(stp); + int oflag; - nfs4_file_put_access(stp->st_file, oflag); - put_nfs4_file(stp->st_file); + if (stp->st_access_bmap) { + oflag = nfs4_access_bmap_to_omode(stp); + nfs4_file_put_access(stp->st_file, oflag); + put_nfs4_file(stp->st_file); + } kmem_cache_free(stateid_slab, stp); } diff --git a/fs/xfs/linux-2.6/xfs_buf.c b/fs/xfs/linux-2.6/xfs_buf.c index 5ea402023ebd..9ef9ed2cfe2e 100644 --- a/fs/xfs/linux-2.6/xfs_buf.c +++ b/fs/xfs/linux-2.6/xfs_buf.c @@ -293,7 +293,6 @@ xfs_buf_allocate_memory( size_t nbytes, offset; gfp_t gfp_mask = xb_to_gfp(flags); unsigned short page_count, i; - pgoff_t first; xfs_off_t end; int error; @@ -333,7 +332,6 @@ use_alloc_page: return error; offset = bp->b_offset; - first = bp->b_file_offset >> PAGE_SHIFT; bp->b_flags |= _XBF_PAGES; for (i = 0; i < bp->b_page_count; i++) { @@ -657,8 +655,6 @@ xfs_buf_readahead( xfs_off_t ioff, size_t isize) { - struct backing_dev_info *bdi; - if (bdi_read_congested(target->bt_bdi)) return; @@ -919,8 +915,6 @@ xfs_buf_lock( if (atomic_read(&bp->b_pin_count) && (bp->b_flags & XBF_STALE)) xfs_log_force(bp->b_target->bt_mount, 0); - if (atomic_read(&bp->b_io_remaining)) - blk_flush_plug(current); down(&bp->b_sema); XB_SET_OWNER(bp); @@ -1309,8 +1303,6 @@ xfs_buf_iowait( { trace_xfs_buf_iowait(bp, _RET_IP_); - if (atomic_read(&bp->b_io_remaining)) - blk_flush_plug(current); wait_for_completion(&bp->b_iowait); trace_xfs_buf_iowait_done(bp, _RET_IP_); @@ -1747,8 +1739,8 @@ xfsbufd( do { long age = xfs_buf_age_centisecs * msecs_to_jiffies(10); long tout = xfs_buf_timer_centisecs * msecs_to_jiffies(10); - int count = 0; struct list_head tmp; + struct blk_plug plug; if (unlikely(freezing(current))) { set_bit(XBT_FORCE_SLEEP, &target->bt_flags); @@ -1764,16 +1756,15 @@ xfsbufd( xfs_buf_delwri_split(target, &tmp, age); list_sort(NULL, &tmp, xfs_buf_cmp); + + blk_start_plug(&plug); while (!list_empty(&tmp)) { struct xfs_buf *bp; bp = list_first_entry(&tmp, struct xfs_buf, b_list); list_del_init(&bp->b_list); xfs_bdstrat_cb(bp); - count++; } - if (count) - blk_flush_plug(current); - + blk_finish_plug(&plug); } while (!kthread_should_stop()); return 0; @@ -1793,6 +1784,7 @@ xfs_flush_buftarg( int pincount = 0; LIST_HEAD(tmp_list); LIST_HEAD(wait_list); + struct blk_plug plug; xfs_buf_runall_queues(xfsconvertd_workqueue); xfs_buf_runall_queues(xfsdatad_workqueue); @@ -1807,6 +1799,8 @@ xfs_flush_buftarg( * we do that after issuing all the IO. */ list_sort(NULL, &tmp_list, xfs_buf_cmp); + + blk_start_plug(&plug); while (!list_empty(&tmp_list)) { bp = list_first_entry(&tmp_list, struct xfs_buf, b_list); ASSERT(target == bp->b_target); @@ -1817,10 +1811,10 @@ xfs_flush_buftarg( } xfs_bdstrat_cb(bp); } + blk_finish_plug(&plug); if (wait) { - /* Expedite and wait for IO to complete. */ - blk_flush_plug(current); + /* Wait for IO to complete. */ while (!list_empty(&wait_list)) { bp = list_first_entry(&wait_list, struct xfs_buf, b_list); diff --git a/fs/xfs/linux-2.6/xfs_message.c b/fs/xfs/linux-2.6/xfs_message.c index 508e06fd7d1e..3ca795609113 100644 --- a/fs/xfs/linux-2.6/xfs_message.c +++ b/fs/xfs/linux-2.6/xfs_message.c @@ -28,53 +28,47 @@ /* * XFS logging functions */ -static int +static void __xfs_printk( const char *level, const struct xfs_mount *mp, struct va_format *vaf) { if (mp && mp->m_fsname) - return printk("%sXFS (%s): %pV\n", level, mp->m_fsname, vaf); - return printk("%sXFS: %pV\n", level, vaf); + printk("%sXFS (%s): %pV\n", level, mp->m_fsname, vaf); + printk("%sXFS: %pV\n", level, vaf); } -int xfs_printk( +void xfs_printk( const char *level, const struct xfs_mount *mp, const char *fmt, ...) { struct va_format vaf; va_list args; - int r; va_start(args, fmt); vaf.fmt = fmt; vaf.va = &args; - r = __xfs_printk(level, mp, &vaf); + __xfs_printk(level, mp, &vaf); va_end(args); - - return r; } #define define_xfs_printk_level(func, kern_level) \ -int func(const struct xfs_mount *mp, const char *fmt, ...) \ +void func(const struct xfs_mount *mp, const char *fmt, ...) \ { \ struct va_format vaf; \ va_list args; \ - int r; \ \ va_start(args, fmt); \ \ vaf.fmt = fmt; \ vaf.va = &args; \ \ - r = __xfs_printk(kern_level, mp, &vaf); \ + __xfs_printk(kern_level, mp, &vaf); \ va_end(args); \ - \ - return r; \ } \ define_xfs_printk_level(xfs_emerg, KERN_EMERG); @@ -88,7 +82,7 @@ define_xfs_printk_level(xfs_info, KERN_INFO); define_xfs_printk_level(xfs_debug, KERN_DEBUG); #endif -int +void xfs_alert_tag( const struct xfs_mount *mp, int panic_tag, @@ -97,7 +91,6 @@ xfs_alert_tag( struct va_format vaf; va_list args; int do_panic = 0; - int r; if (xfs_panic_mask && (xfs_panic_mask & panic_tag)) { xfs_printk(KERN_ALERT, mp, @@ -110,12 +103,10 @@ xfs_alert_tag( vaf.fmt = fmt; vaf.va = &args; - r = __xfs_printk(KERN_ALERT, mp, &vaf); + __xfs_printk(KERN_ALERT, mp, &vaf); va_end(args); BUG_ON(do_panic); - - return r; } void diff --git a/fs/xfs/linux-2.6/xfs_message.h b/fs/xfs/linux-2.6/xfs_message.h index e77ffa16745b..f1b3fc1b6c4e 100644 --- a/fs/xfs/linux-2.6/xfs_message.h +++ b/fs/xfs/linux-2.6/xfs_message.h @@ -3,32 +3,34 @@ struct xfs_mount; -extern int xfs_printk(const char *level, const struct xfs_mount *mp, +extern void xfs_printk(const char *level, const struct xfs_mount *mp, const char *fmt, ...) __attribute__ ((format (printf, 3, 4))); -extern int xfs_emerg(const struct xfs_mount *mp, const char *fmt, ...) +extern void xfs_emerg(const struct xfs_mount *mp, const char *fmt, ...) __attribute__ ((format (printf, 2, 3))); -extern int xfs_alert(const struct xfs_mount *mp, const char *fmt, ...) +extern void xfs_alert(const struct xfs_mount *mp, const char *fmt, ...) __attribute__ ((format (printf, 2, 3))); -extern int xfs_alert_tag(const struct xfs_mount *mp, int tag, +extern void xfs_alert_tag(const struct xfs_mount *mp, int tag, const char *fmt, ...) __attribute__ ((format (printf, 3, 4))); -extern int xfs_crit(const struct xfs_mount *mp, const char *fmt, ...) +extern void xfs_crit(const struct xfs_mount *mp, const char *fmt, ...) __attribute__ ((format (printf, 2, 3))); -extern int xfs_err(const struct xfs_mount *mp, const char *fmt, ...) +extern void xfs_err(const struct xfs_mount *mp, const char *fmt, ...) __attribute__ ((format (printf, 2, 3))); -extern int xfs_warn(const struct xfs_mount *mp, const char *fmt, ...) +extern void xfs_warn(const struct xfs_mount *mp, const char *fmt, ...) __attribute__ ((format (printf, 2, 3))); -extern int xfs_notice(const struct xfs_mount *mp, const char *fmt, ...) +extern void xfs_notice(const struct xfs_mount *mp, const char *fmt, ...) __attribute__ ((format (printf, 2, 3))); -extern int xfs_info(const struct xfs_mount *mp, const char *fmt, ...) +extern void xfs_info(const struct xfs_mount *mp, const char *fmt, ...) __attribute__ ((format (printf, 2, 3))); #ifdef DEBUG -extern int xfs_debug(const struct xfs_mount *mp, const char *fmt, ...) +extern void xfs_debug(const struct xfs_mount *mp, const char *fmt, ...) __attribute__ ((format (printf, 2, 3))); #else -#define xfs_debug(mp, fmt, ...) (0) +static inline void xfs_debug(const struct xfs_mount *mp, const char *fmt, ...) +{ +} #endif extern void assfail(char *expr, char *f, int l); diff --git a/fs/xfs/linux-2.6/xfs_super.c b/fs/xfs/linux-2.6/xfs_super.c index 1ba5c451da36..b38e58d02299 100644 --- a/fs/xfs/linux-2.6/xfs_super.c +++ b/fs/xfs/linux-2.6/xfs_super.c @@ -816,75 +816,6 @@ xfs_setup_devices( return 0; } -/* - * XFS AIL push thread support - */ -void -xfsaild_wakeup( - struct xfs_ail *ailp, - xfs_lsn_t threshold_lsn) -{ - /* only ever move the target forwards */ - if (XFS_LSN_CMP(threshold_lsn, ailp->xa_target) > 0) { - ailp->xa_target = threshold_lsn; - wake_up_process(ailp->xa_task); - } -} - -STATIC int -xfsaild( - void *data) -{ - struct xfs_ail *ailp = data; - xfs_lsn_t last_pushed_lsn = 0; - long tout = 0; /* milliseconds */ - - while (!kthread_should_stop()) { - /* - * for short sleeps indicating congestion, don't allow us to - * get woken early. Otherwise all we do is bang on the AIL lock - * without making progress. - */ - if (tout && tout <= 20) - __set_current_state(TASK_KILLABLE); - else - __set_current_state(TASK_INTERRUPTIBLE); - schedule_timeout(tout ? - msecs_to_jiffies(tout) : MAX_SCHEDULE_TIMEOUT); - - /* swsusp */ - try_to_freeze(); - - ASSERT(ailp->xa_mount->m_log); - if (XFS_FORCED_SHUTDOWN(ailp->xa_mount)) - continue; - - tout = xfsaild_push(ailp, &last_pushed_lsn); - } - - return 0; -} /* xfsaild */ - -int -xfsaild_start( - struct xfs_ail *ailp) -{ - ailp->xa_target = 0; - ailp->xa_task = kthread_run(xfsaild, ailp, "xfsaild/%s", - ailp->xa_mount->m_fsname); - if (IS_ERR(ailp->xa_task)) - return -PTR_ERR(ailp->xa_task); - return 0; -} - -void -xfsaild_stop( - struct xfs_ail *ailp) -{ - kthread_stop(ailp->xa_task); -} - - /* Catch misguided souls that try to use this interface on XFS */ STATIC struct inode * xfs_fs_alloc_inode( @@ -1191,22 +1122,12 @@ xfs_fs_sync_fs( return -error; if (laptop_mode) { - int prev_sync_seq = mp->m_sync_seq; - /* * The disk must be active because we're syncing. * We schedule xfssyncd now (now that the disk is * active) instead of later (when it might not be). */ - wake_up_process(mp->m_sync_task); - /* - * We have to wait for the sync iteration to complete. - * If we don't, the disk activity caused by the sync - * will come after the sync is completed, and that - * triggers another sync from laptop mode. - */ - wait_event(mp->m_wait_single_sync_task, - mp->m_sync_seq != prev_sync_seq); + flush_delayed_work_sync(&mp->m_sync_work); } return 0; @@ -1490,9 +1411,6 @@ xfs_fs_fill_super( spin_lock_init(&mp->m_sb_lock); mutex_init(&mp->m_growlock); atomic_set(&mp->m_active_trans, 0); - INIT_LIST_HEAD(&mp->m_sync_list); - spin_lock_init(&mp->m_sync_lock); - init_waitqueue_head(&mp->m_wait_single_sync_task); mp->m_super = sb; sb->s_fs_info = mp; @@ -1799,6 +1717,38 @@ xfs_destroy_zones(void) } STATIC int __init +xfs_init_workqueues(void) +{ + /* + * max_active is set to 8 to give enough concurency to allow + * multiple work operations on each CPU to run. This allows multiple + * filesystems to be running sync work concurrently, and scales with + * the number of CPUs in the system. + */ + xfs_syncd_wq = alloc_workqueue("xfssyncd", WQ_CPU_INTENSIVE, 8); + if (!xfs_syncd_wq) + goto out; + + xfs_ail_wq = alloc_workqueue("xfsail", WQ_CPU_INTENSIVE, 8); + if (!xfs_ail_wq) + goto out_destroy_syncd; + + return 0; + +out_destroy_syncd: + destroy_workqueue(xfs_syncd_wq); +out: + return -ENOMEM; +} + +STATIC void +xfs_destroy_workqueues(void) +{ + destroy_workqueue(xfs_ail_wq); + destroy_workqueue(xfs_syncd_wq); +} + +STATIC int __init init_xfs_fs(void) { int error; @@ -1813,10 +1763,14 @@ init_xfs_fs(void) if (error) goto out; - error = xfs_mru_cache_init(); + error = xfs_init_workqueues(); if (error) goto out_destroy_zones; + error = xfs_mru_cache_init(); + if (error) + goto out_destroy_wq; + error = xfs_filestream_init(); if (error) goto out_mru_cache_uninit; @@ -1833,6 +1787,10 @@ init_xfs_fs(void) if (error) goto out_cleanup_procfs; + error = xfs_init_workqueues(); + if (error) + goto out_sysctl_unregister; + vfs_initquota(); error = register_filesystem(&xfs_fs_type); @@ -1850,6 +1808,8 @@ init_xfs_fs(void) xfs_filestream_uninit(); out_mru_cache_uninit: xfs_mru_cache_uninit(); + out_destroy_wq: + xfs_destroy_workqueues(); out_destroy_zones: xfs_destroy_zones(); out: @@ -1866,6 +1826,7 @@ exit_xfs_fs(void) xfs_buf_terminate(); xfs_filestream_uninit(); xfs_mru_cache_uninit(); + xfs_destroy_workqueues(); xfs_destroy_zones(); } diff --git a/fs/xfs/linux-2.6/xfs_sync.c b/fs/xfs/linux-2.6/xfs_sync.c index 9cf35a688f53..e4f9c1b0836c 100644 --- a/fs/xfs/linux-2.6/xfs_sync.c +++ b/fs/xfs/linux-2.6/xfs_sync.c @@ -22,6 +22,7 @@ #include "xfs_log.h" #include "xfs_inum.h" #include "xfs_trans.h" +#include "xfs_trans_priv.h" #include "xfs_sb.h" #include "xfs_ag.h" #include "xfs_mount.h" @@ -39,6 +40,8 @@ #include <linux/kthread.h> #include <linux/freezer.h> +struct workqueue_struct *xfs_syncd_wq; /* sync workqueue */ + /* * The inode lookup is done in batches to keep the amount of lock traffic and * radix tree lookups to a minimum. The batch size is a trade off between @@ -431,62 +434,12 @@ xfs_quiesce_attr( xfs_unmountfs_writesb(mp); } -/* - * Enqueue a work item to be picked up by the vfs xfssyncd thread. - * Doing this has two advantages: - * - It saves on stack space, which is tight in certain situations - * - It can be used (with care) as a mechanism to avoid deadlocks. - * Flushing while allocating in a full filesystem requires both. - */ -STATIC void -xfs_syncd_queue_work( - struct xfs_mount *mp, - void *data, - void (*syncer)(struct xfs_mount *, void *), - struct completion *completion) -{ - struct xfs_sync_work *work; - - work = kmem_alloc(sizeof(struct xfs_sync_work), KM_SLEEP); - INIT_LIST_HEAD(&work->w_list); - work->w_syncer = syncer; - work->w_data = data; - work->w_mount = mp; - work->w_completion = completion; - spin_lock(&mp->m_sync_lock); - list_add_tail(&work->w_list, &mp->m_sync_list); - spin_unlock(&mp->m_sync_lock); - wake_up_process(mp->m_sync_task); -} - -/* - * Flush delayed allocate data, attempting to free up reserved space - * from existing allocations. At this point a new allocation attempt - * has failed with ENOSPC and we are in the process of scratching our - * heads, looking about for more room... - */ -STATIC void -xfs_flush_inodes_work( - struct xfs_mount *mp, - void *arg) -{ - struct inode *inode = arg; - xfs_sync_data(mp, SYNC_TRYLOCK); - xfs_sync_data(mp, SYNC_TRYLOCK | SYNC_WAIT); - iput(inode); -} - -void -xfs_flush_inodes( - xfs_inode_t *ip) +static void +xfs_syncd_queue_sync( + struct xfs_mount *mp) { - struct inode *inode = VFS_I(ip); - DECLARE_COMPLETION_ONSTACK(completion); - - igrab(inode); - xfs_syncd_queue_work(ip->i_mount, inode, xfs_flush_inodes_work, &completion); - wait_for_completion(&completion); - xfs_log_force(ip->i_mount, XFS_LOG_SYNC); + queue_delayed_work(xfs_syncd_wq, &mp->m_sync_work, + msecs_to_jiffies(xfs_syncd_centisecs * 10)); } /* @@ -496,9 +449,10 @@ xfs_flush_inodes( */ STATIC void xfs_sync_worker( - struct xfs_mount *mp, - void *unused) + struct work_struct *work) { + struct xfs_mount *mp = container_of(to_delayed_work(work), + struct xfs_mount, m_sync_work); int error; if (!(mp->m_flags & XFS_MOUNT_RDONLY)) { @@ -508,73 +462,106 @@ xfs_sync_worker( error = xfs_fs_log_dummy(mp); else xfs_log_force(mp, 0); - xfs_reclaim_inodes(mp, 0); error = xfs_qm_sync(mp, SYNC_TRYLOCK); + + /* start pushing all the metadata that is currently dirty */ + xfs_ail_push_all(mp->m_ail); } - mp->m_sync_seq++; - wake_up(&mp->m_wait_single_sync_task); + + /* queue us up again */ + xfs_syncd_queue_sync(mp); } -STATIC int -xfssyncd( - void *arg) +/* + * Queue a new inode reclaim pass if there are reclaimable inodes and there + * isn't a reclaim pass already in progress. By default it runs every 5s based + * on the xfs syncd work default of 30s. Perhaps this should have it's own + * tunable, but that can be done if this method proves to be ineffective or too + * aggressive. + */ +static void +xfs_syncd_queue_reclaim( + struct xfs_mount *mp) { - struct xfs_mount *mp = arg; - long timeleft; - xfs_sync_work_t *work, *n; - LIST_HEAD (tmp); - - set_freezable(); - timeleft = xfs_syncd_centisecs * msecs_to_jiffies(10); - for (;;) { - if (list_empty(&mp->m_sync_list)) - timeleft = schedule_timeout_interruptible(timeleft); - /* swsusp */ - try_to_freeze(); - if (kthread_should_stop() && list_empty(&mp->m_sync_list)) - break; - spin_lock(&mp->m_sync_lock); - /* - * We can get woken by laptop mode, to do a sync - - * that's the (only!) case where the list would be - * empty with time remaining. - */ - if (!timeleft || list_empty(&mp->m_sync_list)) { - if (!timeleft) - timeleft = xfs_syncd_centisecs * - msecs_to_jiffies(10); - INIT_LIST_HEAD(&mp->m_sync_work.w_list); - list_add_tail(&mp->m_sync_work.w_list, - &mp->m_sync_list); - } - list_splice_init(&mp->m_sync_list, &tmp); - spin_unlock(&mp->m_sync_lock); + /* + * We can have inodes enter reclaim after we've shut down the syncd + * workqueue during unmount, so don't allow reclaim work to be queued + * during unmount. + */ + if (!(mp->m_super->s_flags & MS_ACTIVE)) + return; - list_for_each_entry_safe(work, n, &tmp, w_list) { - (*work->w_syncer)(mp, work->w_data); - list_del(&work->w_list); - if (work == &mp->m_sync_work) - continue; - if (work->w_completion) - complete(work->w_completion); - kmem_free(work); - } + rcu_read_lock(); + if (radix_tree_tagged(&mp->m_perag_tree, XFS_ICI_RECLAIM_TAG)) { + queue_delayed_work(xfs_syncd_wq, &mp->m_reclaim_work, + msecs_to_jiffies(xfs_syncd_centisecs / 6 * 10)); } + rcu_read_unlock(); +} - return 0; +/* + * This is a fast pass over the inode cache to try to get reclaim moving on as + * many inodes as possible in a short period of time. It kicks itself every few + * seconds, as well as being kicked by the inode cache shrinker when memory + * goes low. It scans as quickly as possible avoiding locked inodes or those + * already being flushed, and once done schedules a future pass. + */ +STATIC void +xfs_reclaim_worker( + struct work_struct *work) +{ + struct xfs_mount *mp = container_of(to_delayed_work(work), + struct xfs_mount, m_reclaim_work); + + xfs_reclaim_inodes(mp, SYNC_TRYLOCK); + xfs_syncd_queue_reclaim(mp); +} + +/* + * Flush delayed allocate data, attempting to free up reserved space + * from existing allocations. At this point a new allocation attempt + * has failed with ENOSPC and we are in the process of scratching our + * heads, looking about for more room. + * + * Queue a new data flush if there isn't one already in progress and + * wait for completion of the flush. This means that we only ever have one + * inode flush in progress no matter how many ENOSPC events are occurring and + * so will prevent the system from bogging down due to every concurrent + * ENOSPC event scanning all the active inodes in the system for writeback. + */ +void +xfs_flush_inodes( + struct xfs_inode *ip) +{ + struct xfs_mount *mp = ip->i_mount; + + queue_work(xfs_syncd_wq, &mp->m_flush_work); + flush_work_sync(&mp->m_flush_work); +} + +STATIC void +xfs_flush_worker( + struct work_struct *work) +{ + struct xfs_mount *mp = container_of(work, + struct xfs_mount, m_flush_work); + + xfs_sync_data(mp, SYNC_TRYLOCK); + xfs_sync_data(mp, SYNC_TRYLOCK | SYNC_WAIT); } int xfs_syncd_init( struct xfs_mount *mp) { - mp->m_sync_work.w_syncer = xfs_sync_worker; - mp->m_sync_work.w_mount = mp; - mp->m_sync_work.w_completion = NULL; - mp->m_sync_task = kthread_run(xfssyncd, mp, "xfssyncd/%s", mp->m_fsname); - if (IS_ERR(mp->m_sync_task)) - return -PTR_ERR(mp->m_sync_task); + INIT_WORK(&mp->m_flush_work, xfs_flush_worker); + INIT_DELAYED_WORK(&mp->m_sync_work, xfs_sync_worker); + INIT_DELAYED_WORK(&mp->m_reclaim_work, xfs_reclaim_worker); + + xfs_syncd_queue_sync(mp); + xfs_syncd_queue_reclaim(mp); + return 0; } @@ -582,7 +569,9 @@ void xfs_syncd_stop( struct xfs_mount *mp) { - kthread_stop(mp->m_sync_task); + cancel_delayed_work_sync(&mp->m_sync_work); + cancel_delayed_work_sync(&mp->m_reclaim_work); + cancel_work_sync(&mp->m_flush_work); } void @@ -601,6 +590,10 @@ __xfs_inode_set_reclaim_tag( XFS_INO_TO_AGNO(ip->i_mount, ip->i_ino), XFS_ICI_RECLAIM_TAG); spin_unlock(&ip->i_mount->m_perag_lock); + + /* schedule periodic background inode reclaim */ + xfs_syncd_queue_reclaim(ip->i_mount); + trace_xfs_perag_set_reclaim(ip->i_mount, pag->pag_agno, -1, _RET_IP_); } @@ -1017,7 +1010,13 @@ xfs_reclaim_inodes( } /* - * Shrinker infrastructure. + * Inode cache shrinker. + * + * When called we make sure that there is a background (fast) inode reclaim in + * progress, while we will throttle the speed of reclaim via doiing synchronous + * reclaim of inodes. That means if we come across dirty inodes, we wait for + * them to be cleaned, which we hope will not be very long due to the + * background walker having already kicked the IO off on those dirty inodes. */ static int xfs_reclaim_inode_shrink( @@ -1032,10 +1031,15 @@ xfs_reclaim_inode_shrink( mp = container_of(shrink, struct xfs_mount, m_inode_shrink); if (nr_to_scan) { + /* kick background reclaimer and push the AIL */ + xfs_syncd_queue_reclaim(mp); + xfs_ail_push_all(mp->m_ail); + if (!(gfp_mask & __GFP_FS)) return -1; - xfs_reclaim_inodes_ag(mp, SYNC_TRYLOCK, &nr_to_scan); + xfs_reclaim_inodes_ag(mp, SYNC_TRYLOCK | SYNC_WAIT, + &nr_to_scan); /* terminate if we don't exhaust the scan */ if (nr_to_scan > 0) return -1; diff --git a/fs/xfs/linux-2.6/xfs_sync.h b/fs/xfs/linux-2.6/xfs_sync.h index 32ba6628290c..e3a6ad27415f 100644 --- a/fs/xfs/linux-2.6/xfs_sync.h +++ b/fs/xfs/linux-2.6/xfs_sync.h @@ -32,6 +32,8 @@ typedef struct xfs_sync_work { #define SYNC_WAIT 0x0001 /* wait for i/o to complete */ #define SYNC_TRYLOCK 0x0002 /* only try to lock inodes */ +extern struct workqueue_struct *xfs_syncd_wq; /* sync workqueue */ + int xfs_syncd_init(struct xfs_mount *mp); void xfs_syncd_stop(struct xfs_mount *mp); diff --git a/fs/xfs/quota/xfs_qm.c b/fs/xfs/quota/xfs_qm.c index 254ee062bd7d..69228aa8605a 100644 --- a/fs/xfs/quota/xfs_qm.c +++ b/fs/xfs/quota/xfs_qm.c @@ -461,12 +461,10 @@ xfs_qm_dqflush_all( struct xfs_quotainfo *q = mp->m_quotainfo; int recl; struct xfs_dquot *dqp; - int niters; int error; if (!q) return 0; - niters = 0; again: mutex_lock(&q->qi_dqlist_lock); list_for_each_entry(dqp, &q->qi_dqlist, q_mplist) { @@ -1314,14 +1312,9 @@ xfs_qm_dqiter_bufs( { xfs_buf_t *bp; int error; - int notcommitted; - int incr; int type; ASSERT(blkcnt > 0); - notcommitted = 0; - incr = (blkcnt > XFS_QM_MAX_DQCLUSTER_LOGSZ) ? - XFS_QM_MAX_DQCLUSTER_LOGSZ : blkcnt; type = flags & XFS_QMOPT_UQUOTA ? XFS_DQ_USER : (flags & XFS_QMOPT_PQUOTA ? XFS_DQ_PROJ : XFS_DQ_GROUP); error = 0; diff --git a/fs/xfs/quota/xfs_qm.h b/fs/xfs/quota/xfs_qm.h index c9446f1c726d..567b29b9f1b3 100644 --- a/fs/xfs/quota/xfs_qm.h +++ b/fs/xfs/quota/xfs_qm.h @@ -65,11 +65,6 @@ extern kmem_zone_t *qm_dqtrxzone; * block in the dquot/xqm code. */ #define XFS_DQUOT_CLUSTER_SIZE_FSB (xfs_filblks_t)1 -/* - * When doing a quotacheck, we log dquot clusters of this many FSBs at most - * in a single transaction. We don't want to ask for too huge a log reservation. - */ -#define XFS_QM_MAX_DQCLUSTER_LOGSZ 3 typedef xfs_dqhash_t xfs_dqlist_t; diff --git a/fs/xfs/quota/xfs_qm_syscalls.c b/fs/xfs/quota/xfs_qm_syscalls.c index 0d62a07b7fd8..2dadb15d5ca9 100644 --- a/fs/xfs/quota/xfs_qm_syscalls.c +++ b/fs/xfs/quota/xfs_qm_syscalls.c @@ -313,14 +313,12 @@ xfs_qm_scall_quotaon( { int error; uint qf; - uint accflags; __int64_t sbflags; flags &= (XFS_ALL_QUOTA_ACCT | XFS_ALL_QUOTA_ENFD); /* * Switching on quota accounting must be done at mount time. */ - accflags = flags & XFS_ALL_QUOTA_ACCT; flags &= ~(XFS_ALL_QUOTA_ACCT); sbflags = 0; diff --git a/fs/xfs/xfs_alloc.c b/fs/xfs/xfs_alloc.c index 4bc3c649aee4..27d64d752eab 100644 --- a/fs/xfs/xfs_alloc.c +++ b/fs/xfs/xfs_alloc.c @@ -2395,17 +2395,33 @@ xfs_free_extent( memset(&args, 0, sizeof(xfs_alloc_arg_t)); args.tp = tp; args.mp = tp->t_mountp; + + /* + * validate that the block number is legal - the enables us to detect + * and handle a silent filesystem corruption rather than crashing. + */ args.agno = XFS_FSB_TO_AGNO(args.mp, bno); - ASSERT(args.agno < args.mp->m_sb.sb_agcount); + if (args.agno >= args.mp->m_sb.sb_agcount) + return EFSCORRUPTED; + args.agbno = XFS_FSB_TO_AGBNO(args.mp, bno); + if (args.agbno >= args.mp->m_sb.sb_agblocks) + return EFSCORRUPTED; + args.pag = xfs_perag_get(args.mp, args.agno); - if ((error = xfs_alloc_fix_freelist(&args, XFS_ALLOC_FLAG_FREEING))) + ASSERT(args.pag); + + error = xfs_alloc_fix_freelist(&args, XFS_ALLOC_FLAG_FREEING); + if (error) goto error0; -#ifdef DEBUG - ASSERT(args.agbp != NULL); - ASSERT((args.agbno + len) <= - be32_to_cpu(XFS_BUF_TO_AGF(args.agbp)->agf_length)); -#endif + + /* validate the extent size is legal now we have the agf locked */ + if (args.agbno + len > + be32_to_cpu(XFS_BUF_TO_AGF(args.agbp)->agf_length)) { + error = EFSCORRUPTED; + goto error0; + } + error = xfs_free_ag_extent(tp, args.agbp, args.agno, args.agbno, len, 0); error0: xfs_perag_put(args.pag); diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c index 46cc40131d4a..576fdfe81d60 100644 --- a/fs/xfs/xfs_inode_item.c +++ b/fs/xfs/xfs_inode_item.c @@ -198,6 +198,41 @@ xfs_inode_item_size( } /* + * xfs_inode_item_format_extents - convert in-core extents to on-disk form + * + * For either the data or attr fork in extent format, we need to endian convert + * the in-core extent as we place them into the on-disk inode. In this case, we + * need to do this conversion before we write the extents into the log. Because + * we don't have the disk inode to write into here, we allocate a buffer and + * format the extents into it via xfs_iextents_copy(). We free the buffer in + * the unlock routine after the copy for the log has been made. + * + * In the case of the data fork, the in-core and on-disk fork sizes can be + * different due to delayed allocation extents. We only log on-disk extents + * here, so always use the physical fork size to determine the size of the + * buffer we need to allocate. + */ +STATIC void +xfs_inode_item_format_extents( + struct xfs_inode *ip, + struct xfs_log_iovec *vecp, + int whichfork, + int type) +{ + xfs_bmbt_rec_t *ext_buffer; + + ext_buffer = kmem_alloc(XFS_IFORK_SIZE(ip, whichfork), KM_SLEEP); + if (whichfork == XFS_DATA_FORK) + ip->i_itemp->ili_extents_buf = ext_buffer; + else + ip->i_itemp->ili_aextents_buf = ext_buffer; + + vecp->i_addr = ext_buffer; + vecp->i_len = xfs_iextents_copy(ip, ext_buffer, whichfork); + vecp->i_type = type; +} + +/* * This is called to fill in the vector of log iovecs for the * given inode log item. It fills the first item with an inode * log format structure, the second with the on-disk inode structure, @@ -213,7 +248,6 @@ xfs_inode_item_format( struct xfs_inode *ip = iip->ili_inode; uint nvecs; size_t data_bytes; - xfs_bmbt_rec_t *ext_buffer; xfs_mount_t *mp; vecp->i_addr = &iip->ili_format; @@ -320,22 +354,8 @@ xfs_inode_item_format( } else #endif { - /* - * There are delayed allocation extents - * in the inode, or we need to convert - * the extents to on disk format. - * Use xfs_iextents_copy() - * to copy only the real extents into - * a separate buffer. We'll free the - * buffer in the unlock routine. - */ - ext_buffer = kmem_alloc(ip->i_df.if_bytes, - KM_SLEEP); - iip->ili_extents_buf = ext_buffer; - vecp->i_addr = ext_buffer; - vecp->i_len = xfs_iextents_copy(ip, ext_buffer, - XFS_DATA_FORK); - vecp->i_type = XLOG_REG_TYPE_IEXT; + xfs_inode_item_format_extents(ip, vecp, + XFS_DATA_FORK, XLOG_REG_TYPE_IEXT); } ASSERT(vecp->i_len <= ip->i_df.if_bytes); iip->ili_format.ilf_dsize = vecp->i_len; @@ -445,19 +465,12 @@ xfs_inode_item_format( */ vecp->i_addr = ip->i_afp->if_u1.if_extents; vecp->i_len = ip->i_afp->if_bytes; + vecp->i_type = XLOG_REG_TYPE_IATTR_EXT; #else ASSERT(iip->ili_aextents_buf == NULL); - /* - * Need to endian flip before logging - */ - ext_buffer = kmem_alloc(ip->i_afp->if_bytes, - KM_SLEEP); - iip->ili_aextents_buf = ext_buffer; - vecp->i_addr = ext_buffer; - vecp->i_len = xfs_iextents_copy(ip, ext_buffer, - XFS_ATTR_FORK); + xfs_inode_item_format_extents(ip, vecp, + XFS_ATTR_FORK, XLOG_REG_TYPE_IATTR_EXT); #endif - vecp->i_type = XLOG_REG_TYPE_IATTR_EXT; iip->ili_format.ilf_asize = vecp->i_len; vecp++; nvecs++; diff --git a/fs/xfs/xfs_itable.c b/fs/xfs/xfs_itable.c index dc1882adaf54..751e94fe1f77 100644 --- a/fs/xfs/xfs_itable.c +++ b/fs/xfs/xfs_itable.c @@ -204,7 +204,6 @@ xfs_bulkstat( xfs_agi_t *agi; /* agi header data */ xfs_agino_t agino; /* inode # in allocation group */ xfs_agnumber_t agno; /* allocation group number */ - xfs_daddr_t bno; /* inode cluster start daddr */ int chunkidx; /* current index into inode chunk */ int clustidx; /* current index into inode cluster */ xfs_btree_cur_t *cur; /* btree cursor for ialloc btree */ @@ -463,7 +462,6 @@ xfs_bulkstat( mp->m_sb.sb_inopblog); } ino = XFS_AGINO_TO_INO(mp, agno, agino); - bno = XFS_AGB_TO_DADDR(mp, agno, agbno); /* * Skip if this inode is free. */ diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c index 25efa9b8a602..b612ce4520ae 100644 --- a/fs/xfs/xfs_log.c +++ b/fs/xfs/xfs_log.c @@ -761,7 +761,7 @@ xfs_log_need_covered(xfs_mount_t *mp) break; case XLOG_STATE_COVER_NEED: case XLOG_STATE_COVER_NEED2: - if (!xfs_trans_ail_tail(log->l_ailp) && + if (!xfs_ail_min_lsn(log->l_ailp) && xlog_iclogs_empty(log)) { if (log->l_covered_state == XLOG_STATE_COVER_NEED) log->l_covered_state = XLOG_STATE_COVER_DONE; @@ -801,7 +801,7 @@ xlog_assign_tail_lsn( xfs_lsn_t tail_lsn; struct log *log = mp->m_log; - tail_lsn = xfs_trans_ail_tail(mp->m_ail); + tail_lsn = xfs_ail_min_lsn(mp->m_ail); if (!tail_lsn) tail_lsn = atomic64_read(&log->l_last_sync_lsn); @@ -1239,7 +1239,7 @@ xlog_grant_push_ail( * the filesystem is shutting down. */ if (!XLOG_FORCED_SHUTDOWN(log)) - xfs_trans_ail_push(log->l_ailp, threshold_lsn); + xfs_ail_push(log->l_ailp, threshold_lsn); } /* @@ -3407,6 +3407,17 @@ xlog_verify_dest_ptr( xfs_emerg(log->l_mp, "%s: invalid ptr", __func__); } +/* + * Check to make sure the grant write head didn't just over lap the tail. If + * the cycles are the same, we can't be overlapping. Otherwise, make sure that + * the cycles differ by exactly one and check the byte count. + * + * This check is run unlocked, so can give false positives. Rather than assert + * on failures, use a warn-once flag and a panic tag to allow the admin to + * determine if they want to panic the machine when such an error occurs. For + * debug kernels this will have the same effect as using an assert but, unlinke + * an assert, it can be turned off at runtime. + */ STATIC void xlog_verify_grant_tail( struct log *log) @@ -3414,17 +3425,22 @@ xlog_verify_grant_tail( int tail_cycle, tail_blocks; int cycle, space; - /* - * Check to make sure the grant write head didn't just over lap the - * tail. If the cycles are the same, we can't be overlapping. - * Otherwise, make sure that the cycles differ by exactly one and - * check the byte count. - */ xlog_crack_grant_head(&log->l_grant_write_head, &cycle, &space); xlog_crack_atomic_lsn(&log->l_tail_lsn, &tail_cycle, &tail_blocks); if (tail_cycle != cycle) { - ASSERT(cycle - 1 == tail_cycle); - ASSERT(space <= BBTOB(tail_blocks)); + if (cycle - 1 != tail_cycle && + !(log->l_flags & XLOG_TAIL_WARN)) { + xfs_alert_tag(log->l_mp, XFS_PTAG_LOGRES, + "%s: cycle - 1 != tail_cycle", __func__); + log->l_flags |= XLOG_TAIL_WARN; + } + + if (space > BBTOB(tail_blocks) && + !(log->l_flags & XLOG_TAIL_WARN)) { + xfs_alert_tag(log->l_mp, XFS_PTAG_LOGRES, + "%s: space > BBTOB(tail_blocks)", __func__); + log->l_flags |= XLOG_TAIL_WARN; + } } } diff --git a/fs/xfs/xfs_log_priv.h b/fs/xfs/xfs_log_priv.h index ffae692c9832..5864850e9e34 100644 --- a/fs/xfs/xfs_log_priv.h +++ b/fs/xfs/xfs_log_priv.h @@ -144,6 +144,7 @@ static inline uint xlog_get_client_id(__be32 i) #define XLOG_RECOVERY_NEEDED 0x4 /* log was recovered */ #define XLOG_IO_ERROR 0x8 /* log hit an I/O error, and being shutdown */ +#define XLOG_TAIL_WARN 0x10 /* log tail verify warning issued */ #ifdef __KERNEL__ /* diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h index a62e8971539d..19af0ab0d0c6 100644 --- a/fs/xfs/xfs_mount.h +++ b/fs/xfs/xfs_mount.h @@ -203,12 +203,9 @@ typedef struct xfs_mount { struct mutex m_icsb_mutex; /* balancer sync lock */ #endif struct xfs_mru_cache *m_filestream; /* per-mount filestream data */ - struct task_struct *m_sync_task; /* generalised sync thread */ - xfs_sync_work_t m_sync_work; /* work item for VFS_SYNC */ - struct list_head m_sync_list; /* sync thread work item list */ - spinlock_t m_sync_lock; /* work item list lock */ - int m_sync_seq; /* sync thread generation no. */ - wait_queue_head_t m_wait_single_sync_task; + struct delayed_work m_sync_work; /* background sync work */ + struct delayed_work m_reclaim_work; /* background inode reclaim */ + struct work_struct m_flush_work; /* background inode flush */ __int64_t m_update_flags; /* sb flags we need to update on the next remount,rw */ struct shrinker m_inode_shrink; /* inode reclaim shrinker */ diff --git a/fs/xfs/xfs_trans_ail.c b/fs/xfs/xfs_trans_ail.c index 12aff9584e29..acdb92f14d51 100644 --- a/fs/xfs/xfs_trans_ail.c +++ b/fs/xfs/xfs_trans_ail.c @@ -28,74 +28,138 @@ #include "xfs_trans_priv.h" #include "xfs_error.h" -STATIC void xfs_ail_splice(struct xfs_ail *, struct list_head *, xfs_lsn_t); -STATIC void xfs_ail_delete(struct xfs_ail *, xfs_log_item_t *); -STATIC xfs_log_item_t * xfs_ail_min(struct xfs_ail *); -STATIC xfs_log_item_t * xfs_ail_next(struct xfs_ail *, xfs_log_item_t *); +struct workqueue_struct *xfs_ail_wq; /* AIL workqueue */ #ifdef DEBUG -STATIC void xfs_ail_check(struct xfs_ail *, xfs_log_item_t *); -#else +/* + * Check that the list is sorted as it should be. + */ +STATIC void +xfs_ail_check( + struct xfs_ail *ailp, + xfs_log_item_t *lip) +{ + xfs_log_item_t *prev_lip; + + if (list_empty(&ailp->xa_ail)) + return; + + /* + * Check the next and previous entries are valid. + */ + ASSERT((lip->li_flags & XFS_LI_IN_AIL) != 0); + prev_lip = list_entry(lip->li_ail.prev, xfs_log_item_t, li_ail); + if (&prev_lip->li_ail != &ailp->xa_ail) + ASSERT(XFS_LSN_CMP(prev_lip->li_lsn, lip->li_lsn) <= 0); + + prev_lip = list_entry(lip->li_ail.next, xfs_log_item_t, li_ail); + if (&prev_lip->li_ail != &ailp->xa_ail) + ASSERT(XFS_LSN_CMP(prev_lip->li_lsn, lip->li_lsn) >= 0); + + +#ifdef XFS_TRANS_DEBUG + /* + * Walk the list checking lsn ordering, and that every entry has the + * XFS_LI_IN_AIL flag set. This is really expensive, so only do it + * when specifically debugging the transaction subsystem. + */ + prev_lip = list_entry(&ailp->xa_ail, xfs_log_item_t, li_ail); + list_for_each_entry(lip, &ailp->xa_ail, li_ail) { + if (&prev_lip->li_ail != &ailp->xa_ail) + ASSERT(XFS_LSN_CMP(prev_lip->li_lsn, lip->li_lsn) <= 0); + ASSERT((lip->li_flags & XFS_LI_IN_AIL) != 0); + prev_lip = lip; + } +#endif /* XFS_TRANS_DEBUG */ +} +#else /* !DEBUG */ #define xfs_ail_check(a,l) #endif /* DEBUG */ +/* + * Return a pointer to the first item in the AIL. If the AIL is empty, then + * return NULL. + */ +static xfs_log_item_t * +xfs_ail_min( + struct xfs_ail *ailp) +{ + if (list_empty(&ailp->xa_ail)) + return NULL; + + return list_first_entry(&ailp->xa_ail, xfs_log_item_t, li_ail); +} + + /* + * Return a pointer to the last item in the AIL. If the AIL is empty, then + * return NULL. + */ +static xfs_log_item_t * +xfs_ail_max( + struct xfs_ail *ailp) +{ + if (list_empty(&ailp->xa_ail)) + return NULL; + + return list_entry(ailp->xa_ail.prev, xfs_log_item_t, li_ail); +} + +/* + * Return a pointer to the item which follows the given item in the AIL. If + * the given item is the last item in the list, then return NULL. + */ +static xfs_log_item_t * +xfs_ail_next( + struct xfs_ail *ailp, + xfs_log_item_t *lip) +{ + if (lip->li_ail.next == &ailp->xa_ail) + return NULL; + + return list_first_entry(&lip->li_ail, xfs_log_item_t, li_ail); +} /* - * This is called by the log manager code to determine the LSN - * of the tail of the log. This is exactly the LSN of the first - * item in the AIL. If the AIL is empty, then this function - * returns 0. + * This is called by the log manager code to determine the LSN of the tail of + * the log. This is exactly the LSN of the first item in the AIL. If the AIL + * is empty, then this function returns 0. * - * We need the AIL lock in order to get a coherent read of the - * lsn of the last item in the AIL. + * We need the AIL lock in order to get a coherent read of the lsn of the last + * item in the AIL. */ xfs_lsn_t -xfs_trans_ail_tail( +xfs_ail_min_lsn( struct xfs_ail *ailp) { - xfs_lsn_t lsn; + xfs_lsn_t lsn = 0; xfs_log_item_t *lip; spin_lock(&ailp->xa_lock); lip = xfs_ail_min(ailp); - if (lip == NULL) { - lsn = (xfs_lsn_t)0; - } else { + if (lip) lsn = lip->li_lsn; - } spin_unlock(&ailp->xa_lock); return lsn; } /* - * xfs_trans_push_ail - * - * This routine is called to move the tail of the AIL forward. It does this by - * trying to flush items in the AIL whose lsns are below the given - * threshold_lsn. - * - * the push is run asynchronously in a separate thread, so we return the tail - * of the log right now instead of the tail after the push. This means we will - * either continue right away, or we will sleep waiting on the async thread to - * do its work. - * - * We do this unlocked - we only need to know whether there is anything in the - * AIL at the time we are called. We don't need to access the contents of - * any of the objects, so the lock is not needed. + * Return the maximum lsn held in the AIL, or zero if the AIL is empty. */ -void -xfs_trans_ail_push( - struct xfs_ail *ailp, - xfs_lsn_t threshold_lsn) +static xfs_lsn_t +xfs_ail_max_lsn( + struct xfs_ail *ailp) { - xfs_log_item_t *lip; + xfs_lsn_t lsn = 0; + xfs_log_item_t *lip; - lip = xfs_ail_min(ailp); - if (lip && !XFS_FORCED_SHUTDOWN(ailp->xa_mount)) { - if (XFS_LSN_CMP(threshold_lsn, ailp->xa_target) > 0) - xfsaild_wakeup(ailp, threshold_lsn); - } + spin_lock(&ailp->xa_lock); + lip = xfs_ail_max(ailp); + if (lip) + lsn = lip->li_lsn; + spin_unlock(&ailp->xa_lock); + + return lsn; } /* @@ -236,16 +300,57 @@ out: } /* - * xfsaild_push does the work of pushing on the AIL. Returning a timeout of - * zero indicates that the caller should sleep until woken. + * splice the log item list into the AIL at the given LSN. */ -long -xfsaild_push( - struct xfs_ail *ailp, - xfs_lsn_t *last_lsn) +static void +xfs_ail_splice( + struct xfs_ail *ailp, + struct list_head *list, + xfs_lsn_t lsn) { - long tout = 0; - xfs_lsn_t last_pushed_lsn = *last_lsn; + xfs_log_item_t *next_lip; + + /* If the list is empty, just insert the item. */ + if (list_empty(&ailp->xa_ail)) { + list_splice(list, &ailp->xa_ail); + return; + } + + list_for_each_entry_reverse(next_lip, &ailp->xa_ail, li_ail) { + if (XFS_LSN_CMP(next_lip->li_lsn, lsn) <= 0) + break; + } + + ASSERT(&next_lip->li_ail == &ailp->xa_ail || + XFS_LSN_CMP(next_lip->li_lsn, lsn) <= 0); + + list_splice_init(list, &next_lip->li_ail); +} + +/* + * Delete the given item from the AIL. Return a pointer to the item. + */ +static void +xfs_ail_delete( + struct xfs_ail *ailp, + xfs_log_item_t *lip) +{ + xfs_ail_check(ailp, lip); + list_del(&lip->li_ail); + xfs_trans_ail_cursor_clear(ailp, lip); +} + +/* + * xfs_ail_worker does the work of pushing on the AIL. It will requeue itself + * to run at a later time if there is more work to do to complete the push. + */ +STATIC void +xfs_ail_worker( + struct work_struct *work) +{ + struct xfs_ail *ailp = container_of(to_delayed_work(work), + struct xfs_ail, xa_work); + long tout; xfs_lsn_t target = ailp->xa_target; xfs_lsn_t lsn; xfs_log_item_t *lip; @@ -256,15 +361,15 @@ xfsaild_push( spin_lock(&ailp->xa_lock); xfs_trans_ail_cursor_init(ailp, cur); - lip = xfs_trans_ail_cursor_first(ailp, cur, *last_lsn); + lip = xfs_trans_ail_cursor_first(ailp, cur, ailp->xa_last_pushed_lsn); if (!lip || XFS_FORCED_SHUTDOWN(mp)) { /* * AIL is empty or our push has reached the end. */ xfs_trans_ail_cursor_done(ailp, cur); spin_unlock(&ailp->xa_lock); - *last_lsn = 0; - return tout; + ailp->xa_last_pushed_lsn = 0; + return; } XFS_STATS_INC(xs_push_ail); @@ -301,13 +406,13 @@ xfsaild_push( case XFS_ITEM_SUCCESS: XFS_STATS_INC(xs_push_ail_success); IOP_PUSH(lip); - last_pushed_lsn = lsn; + ailp->xa_last_pushed_lsn = lsn; break; case XFS_ITEM_PUSHBUF: XFS_STATS_INC(xs_push_ail_pushbuf); IOP_PUSHBUF(lip); - last_pushed_lsn = lsn; + ailp->xa_last_pushed_lsn = lsn; push_xfsbufd = 1; break; @@ -319,7 +424,7 @@ xfsaild_push( case XFS_ITEM_LOCKED: XFS_STATS_INC(xs_push_ail_locked); - last_pushed_lsn = lsn; + ailp->xa_last_pushed_lsn = lsn; stuck++; break; @@ -374,9 +479,23 @@ xfsaild_push( wake_up_process(mp->m_ddev_targp->bt_task); } + /* assume we have more work to do in a short while */ + tout = 10; if (!count) { /* We're past our target or empty, so idle */ - last_pushed_lsn = 0; + ailp->xa_last_pushed_lsn = 0; + + /* + * Check for an updated push target before clearing the + * XFS_AIL_PUSHING_BIT. If the target changed, we've got more + * work to do. Wait a bit longer before starting that work. + */ + smp_rmb(); + if (ailp->xa_target == target) { + clear_bit(XFS_AIL_PUSHING_BIT, &ailp->xa_flags); + return; + } + tout = 50; } else if (XFS_LSN_CMP(lsn, target) >= 0) { /* * We reached the target so wait a bit longer for I/O to @@ -384,7 +503,7 @@ xfsaild_push( * start the next scan from the start of the AIL. */ tout = 50; - last_pushed_lsn = 0; + ailp->xa_last_pushed_lsn = 0; } else if ((stuck * 100) / count > 90) { /* * Either there is a lot of contention on the AIL or we @@ -396,14 +515,61 @@ xfsaild_push( * continuing from where we were. */ tout = 20; - } else { - /* more to do, but wait a short while before continuing */ - tout = 10; } - *last_lsn = last_pushed_lsn; - return tout; + + /* There is more to do, requeue us. */ + queue_delayed_work(xfs_syncd_wq, &ailp->xa_work, + msecs_to_jiffies(tout)); +} + +/* + * This routine is called to move the tail of the AIL forward. It does this by + * trying to flush items in the AIL whose lsns are below the given + * threshold_lsn. + * + * The push is run asynchronously in a workqueue, which means the caller needs + * to handle waiting on the async flush for space to become available. + * We don't want to interrupt any push that is in progress, hence we only queue + * work if we set the pushing bit approriately. + * + * We do this unlocked - we only need to know whether there is anything in the + * AIL at the time we are called. We don't need to access the contents of + * any of the objects, so the lock is not needed. + */ +void +xfs_ail_push( + struct xfs_ail *ailp, + xfs_lsn_t threshold_lsn) +{ + xfs_log_item_t *lip; + + lip = xfs_ail_min(ailp); + if (!lip || XFS_FORCED_SHUTDOWN(ailp->xa_mount) || + XFS_LSN_CMP(threshold_lsn, ailp->xa_target) <= 0) + return; + + /* + * Ensure that the new target is noticed in push code before it clears + * the XFS_AIL_PUSHING_BIT. + */ + smp_wmb(); + ailp->xa_target = threshold_lsn; + if (!test_and_set_bit(XFS_AIL_PUSHING_BIT, &ailp->xa_flags)) + queue_delayed_work(xfs_syncd_wq, &ailp->xa_work, 0); } +/* + * Push out all items in the AIL immediately + */ +void +xfs_ail_push_all( + struct xfs_ail *ailp) +{ + xfs_lsn_t threshold_lsn = xfs_ail_max_lsn(ailp); + + if (threshold_lsn) + xfs_ail_push(ailp, threshold_lsn); +} /* * This is to be called when an item is unlocked that may have @@ -615,7 +781,6 @@ xfs_trans_ail_init( xfs_mount_t *mp) { struct xfs_ail *ailp; - int error; ailp = kmem_zalloc(sizeof(struct xfs_ail), KM_MAYFAIL); if (!ailp) @@ -624,15 +789,9 @@ xfs_trans_ail_init( ailp->xa_mount = mp; INIT_LIST_HEAD(&ailp->xa_ail); spin_lock_init(&ailp->xa_lock); - error = xfsaild_start(ailp); - if (error) - goto out_free_ailp; + INIT_DELAYED_WORK(&ailp->xa_work, xfs_ail_worker); mp->m_ail = ailp; return 0; - -out_free_ailp: - kmem_free(ailp); - return error; } void @@ -641,124 +800,6 @@ xfs_trans_ail_destroy( { struct xfs_ail *ailp = mp->m_ail; - xfsaild_stop(ailp); + cancel_delayed_work_sync(&ailp->xa_work); kmem_free(ailp); } - -/* - * splice the log item list into the AIL at the given LSN. - */ -STATIC void -xfs_ail_splice( - struct xfs_ail *ailp, - struct list_head *list, - xfs_lsn_t lsn) -{ - xfs_log_item_t *next_lip; - - /* - * If the list is empty, just insert the item. - */ - if (list_empty(&ailp->xa_ail)) { - list_splice(list, &ailp->xa_ail); - return; - } - - list_for_each_entry_reverse(next_lip, &ailp->xa_ail, li_ail) { - if (XFS_LSN_CMP(next_lip->li_lsn, lsn) <= 0) - break; - } - - ASSERT((&next_lip->li_ail == &ailp->xa_ail) || - (XFS_LSN_CMP(next_lip->li_lsn, lsn) <= 0)); - - list_splice_init(list, &next_lip->li_ail); - return; -} - -/* - * Delete the given item from the AIL. Return a pointer to the item. - */ -STATIC void -xfs_ail_delete( - struct xfs_ail *ailp, - xfs_log_item_t *lip) -{ - xfs_ail_check(ailp, lip); - list_del(&lip->li_ail); - xfs_trans_ail_cursor_clear(ailp, lip); -} - -/* - * Return a pointer to the first item in the AIL. - * If the AIL is empty, then return NULL. - */ -STATIC xfs_log_item_t * -xfs_ail_min( - struct xfs_ail *ailp) -{ - if (list_empty(&ailp->xa_ail)) - return NULL; - - return list_first_entry(&ailp->xa_ail, xfs_log_item_t, li_ail); -} - -/* - * Return a pointer to the item which follows - * the given item in the AIL. If the given item - * is the last item in the list, then return NULL. - */ -STATIC xfs_log_item_t * -xfs_ail_next( - struct xfs_ail *ailp, - xfs_log_item_t *lip) -{ - if (lip->li_ail.next == &ailp->xa_ail) - return NULL; - - return list_first_entry(&lip->li_ail, xfs_log_item_t, li_ail); -} - -#ifdef DEBUG -/* - * Check that the list is sorted as it should be. - */ -STATIC void -xfs_ail_check( - struct xfs_ail *ailp, - xfs_log_item_t *lip) -{ - xfs_log_item_t *prev_lip; - - if (list_empty(&ailp->xa_ail)) - return; - - /* - * Check the next and previous entries are valid. - */ - ASSERT((lip->li_flags & XFS_LI_IN_AIL) != 0); - prev_lip = list_entry(lip->li_ail.prev, xfs_log_item_t, li_ail); - if (&prev_lip->li_ail != &ailp->xa_ail) - ASSERT(XFS_LSN_CMP(prev_lip->li_lsn, lip->li_lsn) <= 0); - - prev_lip = list_entry(lip->li_ail.next, xfs_log_item_t, li_ail); - if (&prev_lip->li_ail != &ailp->xa_ail) - ASSERT(XFS_LSN_CMP(prev_lip->li_lsn, lip->li_lsn) >= 0); - - -#ifdef XFS_TRANS_DEBUG - /* - * Walk the list checking lsn ordering, and that every entry has the - * XFS_LI_IN_AIL flag set. This is really expensive, so only do it - * when specifically debugging the transaction subsystem. - */ - prev_lip = list_entry(&ailp->xa_ail, xfs_log_item_t, li_ail); - list_for_each_entry(lip, &ailp->xa_ail, li_ail) { - if (&prev_lip->li_ail != &ailp->xa_ail) - ASSERT(XFS_LSN_CMP(prev_lip->li_lsn, lip->li_lsn) <= 0); - ASSERT((lip->li_flags & XFS_LI_IN_AIL) != 0); - prev_lip = lip; - } -#endif /* XFS_TRANS_DEBUG */ -} -#endif /* DEBUG */ diff --git a/fs/xfs/xfs_trans_priv.h b/fs/xfs/xfs_trans_priv.h index 35162c238fa3..6b164e9e9a1f 100644 --- a/fs/xfs/xfs_trans_priv.h +++ b/fs/xfs/xfs_trans_priv.h @@ -65,16 +65,22 @@ struct xfs_ail_cursor { struct xfs_ail { struct xfs_mount *xa_mount; struct list_head xa_ail; - uint xa_gen; - struct task_struct *xa_task; xfs_lsn_t xa_target; struct xfs_ail_cursor xa_cursors; spinlock_t xa_lock; + struct delayed_work xa_work; + xfs_lsn_t xa_last_pushed_lsn; + unsigned long xa_flags; }; +#define XFS_AIL_PUSHING_BIT 0 + /* * From xfs_trans_ail.c */ + +extern struct workqueue_struct *xfs_ail_wq; /* AIL workqueue */ + void xfs_trans_ail_update_bulk(struct xfs_ail *ailp, struct xfs_log_item **log_items, int nr_items, xfs_lsn_t lsn) __releases(ailp->xa_lock); @@ -98,12 +104,13 @@ xfs_trans_ail_delete( xfs_trans_ail_delete_bulk(ailp, &lip, 1); } -void xfs_trans_ail_push(struct xfs_ail *, xfs_lsn_t); +void xfs_ail_push(struct xfs_ail *, xfs_lsn_t); +void xfs_ail_push_all(struct xfs_ail *); +xfs_lsn_t xfs_ail_min_lsn(struct xfs_ail *ailp); + void xfs_trans_unlocked_item(struct xfs_ail *, xfs_log_item_t *); -xfs_lsn_t xfs_trans_ail_tail(struct xfs_ail *ailp); - struct xfs_log_item *xfs_trans_ail_cursor_first(struct xfs_ail *ailp, struct xfs_ail_cursor *cur, xfs_lsn_t lsn); @@ -112,11 +119,6 @@ struct xfs_log_item *xfs_trans_ail_cursor_next(struct xfs_ail *ailp, void xfs_trans_ail_cursor_done(struct xfs_ail *ailp, struct xfs_ail_cursor *cur); -long xfsaild_push(struct xfs_ail *, xfs_lsn_t *); -void xfsaild_wakeup(struct xfs_ail *, xfs_lsn_t); -int xfsaild_start(struct xfs_ail *); -void xfsaild_stop(struct xfs_ail *); - #if BITS_PER_LONG != 64 static inline void xfs_trans_ail_copy_lsn( diff --git a/include/linux/can/platform/mcp251x.h b/include/linux/can/platform/mcp251x.h index 8e20540043f5..089fe43211a4 100644 --- a/include/linux/can/platform/mcp251x.h +++ b/include/linux/can/platform/mcp251x.h @@ -12,6 +12,7 @@ /** * struct mcp251x_platform_data - MCP251X SPI CAN controller platform data * @oscillator_frequency: - oscillator frequency in Hz + * @irq_flags: - IRQF configuration flags * @board_specific_setup: - called before probing the chip (power,reset) * @transceiver_enable: - called to power on/off the transceiver * @power_enable: - called to power on/off the mcp *and* the @@ -24,6 +25,7 @@ struct mcp251x_platform_data { unsigned long oscillator_frequency; + unsigned long irq_flags; int (*board_specific_setup)(struct spi_device *spi); int (*transceiver_enable)(int enable); int (*power_enable) (int enable); diff --git a/include/linux/mfd/core.h b/include/linux/mfd/core.h index ad1b19aa6508..aef23309a742 100644 --- a/include/linux/mfd/core.h +++ b/include/linux/mfd/core.h @@ -86,16 +86,25 @@ extern int mfd_clone_cell(const char *cell, const char **clones, */ static inline const struct mfd_cell *mfd_get_cell(struct platform_device *pdev) { - return pdev->dev.platform_data; + return pdev->mfd_cell; } /* * Given a platform device that's been created by mfd_add_devices(), fetch * the .mfd_data entry from the mfd_cell that created it. + * Otherwise just return the platform_data pointer. + * This maintains compatibility with platform drivers whose devices aren't + * created by the mfd layer, and expect platform_data to contain what would've + * otherwise been in mfd_data. */ static inline void *mfd_get_data(struct platform_device *pdev) { - return mfd_get_cell(pdev)->mfd_data; + const struct mfd_cell *cell = mfd_get_cell(pdev); + + if (cell) + return cell->mfd_data; + else + return pdev->dev.platform_data; } extern int mfd_add_devices(struct device *parent, int id, diff --git a/include/linux/mutex.h b/include/linux/mutex.h index 94b48bd40dd7..c75471db576e 100644 --- a/include/linux/mutex.h +++ b/include/linux/mutex.h @@ -51,7 +51,7 @@ struct mutex { spinlock_t wait_lock; struct list_head wait_list; #if defined(CONFIG_DEBUG_MUTEXES) || defined(CONFIG_SMP) - struct thread_info *owner; + struct task_struct *owner; #endif #ifdef CONFIG_DEBUG_MUTEXES const char *name; diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index eeec00abb664..7fa95df60146 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -270,7 +270,8 @@ struct nf_afinfo { unsigned int dataoff, unsigned int len, u_int8_t protocol); - int (*route)(struct dst_entry **dst, struct flowi *fl); + int (*route)(struct net *net, struct dst_entry **dst, + struct flowi *fl, bool strict); void (*saveroute)(const struct sk_buff *skb, struct nf_queue_entry *entry); int (*reroute)(struct sk_buff *skb, diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index ec333d83f3b4..5a262e3ae715 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -293,7 +293,7 @@ struct ip_set { /* Lock protecting the set data */ rwlock_t lock; /* References to the set */ - atomic_t ref; + u32 ref; /* The core set type */ struct ip_set_type *type; /* The type variant doing the real job */ diff --git a/include/linux/netfilter/ipset/ip_set_ahash.h b/include/linux/netfilter/ipset/ip_set_ahash.h index ec9d9bea1e37..a0196ac79051 100644 --- a/include/linux/netfilter/ipset/ip_set_ahash.h +++ b/include/linux/netfilter/ipset/ip_set_ahash.h @@ -515,8 +515,7 @@ type_pf_head(struct ip_set *set, struct sk_buff *skb) if (h->netmask != HOST_MASK) NLA_PUT_U8(skb, IPSET_ATTR_NETMASK, h->netmask); #endif - NLA_PUT_NET32(skb, IPSET_ATTR_REFERENCES, - htonl(atomic_read(&set->ref) - 1)); + NLA_PUT_NET32(skb, IPSET_ATTR_REFERENCES, htonl(set->ref - 1)); NLA_PUT_NET32(skb, IPSET_ATTR_MEMSIZE, htonl(memsize)); if (with_timeout(h->timeout)) NLA_PUT_NET32(skb, IPSET_ATTR_TIMEOUT, htonl(h->timeout)); diff --git a/include/linux/platform_device.h b/include/linux/platform_device.h index d96db9825708..744942c95fec 100644 --- a/include/linux/platform_device.h +++ b/include/linux/platform_device.h @@ -14,6 +14,8 @@ #include <linux/device.h> #include <linux/mod_devicetable.h> +struct mfd_cell; + struct platform_device { const char * name; int id; @@ -23,6 +25,9 @@ struct platform_device { const struct platform_device_id *id_entry; + /* MFD cell pointer */ + struct mfd_cell *mfd_cell; + /* arch specific additions */ struct pdev_archdata archdata; }; diff --git a/include/linux/sched.h b/include/linux/sched.h index e43e5b0ab0b5..d9ca3aa511ff 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -360,7 +360,7 @@ extern signed long schedule_timeout_interruptible(signed long timeout); extern signed long schedule_timeout_killable(signed long timeout); extern signed long schedule_timeout_uninterruptible(signed long timeout); asmlinkage void schedule(void); -extern int mutex_spin_on_owner(struct mutex *lock, struct thread_info *owner); +extern int mutex_spin_on_owner(struct mutex *lock, struct task_struct *owner); struct nsproxy; struct user_namespace; @@ -1038,8 +1038,12 @@ struct sched_domain; #define WF_FORK 0x02 /* child wakeup after fork */ #define ENQUEUE_WAKEUP 1 -#define ENQUEUE_WAKING 2 -#define ENQUEUE_HEAD 4 +#define ENQUEUE_HEAD 2 +#ifdef CONFIG_SMP +#define ENQUEUE_WAKING 4 /* sched_class::task_waking was called */ +#else +#define ENQUEUE_WAKING 0 +#endif #define DEQUEUE_SLEEP 1 @@ -1057,12 +1061,11 @@ struct sched_class { void (*put_prev_task) (struct rq *rq, struct task_struct *p); #ifdef CONFIG_SMP - int (*select_task_rq)(struct rq *rq, struct task_struct *p, - int sd_flag, int flags); + int (*select_task_rq)(struct task_struct *p, int sd_flag, int flags); void (*pre_schedule) (struct rq *this_rq, struct task_struct *task); void (*post_schedule) (struct rq *this_rq); - void (*task_waking) (struct rq *this_rq, struct task_struct *task); + void (*task_waking) (struct task_struct *task); void (*task_woken) (struct rq *this_rq, struct task_struct *task); void (*set_cpus_allowed)(struct task_struct *p, @@ -1190,10 +1193,10 @@ struct task_struct { int lock_depth; /* BKL lock depth */ #ifdef CONFIG_SMP -#ifdef __ARCH_WANT_UNLOCKED_CTXSW - int oncpu; -#endif + struct task_struct *wake_entry; + int on_cpu; #endif + int on_rq; int prio, static_prio, normal_prio; unsigned int rt_priority; @@ -1261,6 +1264,7 @@ struct task_struct { /* Revert to default priority/policy when forking */ unsigned sched_reset_on_fork:1; + unsigned sched_contributes_to_load:1; pid_t pid; pid_t tgid; @@ -2179,8 +2183,10 @@ extern void set_task_comm(struct task_struct *tsk, char *from); extern char *get_task_comm(char *to, struct task_struct *tsk); #ifdef CONFIG_SMP +void scheduler_ipi(void); extern unsigned long wait_task_inactive(struct task_struct *, long match_state); #else +static inline void scheduler_ipi(void) { } static inline unsigned long wait_task_inactive(struct task_struct *p, long match_state) { diff --git a/include/linux/suspend.h b/include/linux/suspend.h index 5a89e3612875..083ffea7ba18 100644 --- a/include/linux/suspend.h +++ b/include/linux/suspend.h @@ -249,6 +249,8 @@ extern void hibernation_set_ops(const struct platform_hibernation_ops *ops); extern int hibernate(void); extern bool system_entering_hibernation(void); #else /* CONFIG_HIBERNATION */ +static inline void register_nosave_region(unsigned long b, unsigned long e) {} +static inline void register_nosave_region_late(unsigned long b, unsigned long e) {} static inline int swsusp_page_is_forbidden(struct page *p) { return 0; } static inline void swsusp_set_page_free(struct page *p) {} static inline void swsusp_unset_page_free(struct page *p) {} @@ -297,14 +299,7 @@ static inline bool pm_wakeup_pending(void) { return false; } extern struct mutex pm_mutex; -#ifndef CONFIG_HIBERNATION -static inline void register_nosave_region(unsigned long b, unsigned long e) -{ -} -static inline void register_nosave_region_late(unsigned long b, unsigned long e) -{ -} - +#ifndef CONFIG_HIBERNATE_CALLBACKS static inline void lock_system_sleep(void) {} static inline void unlock_system_sleep(void) {} diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 814b434db749..d516f00c8e0f 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -52,7 +52,7 @@ static inline struct net *skb_net(const struct sk_buff *skb) */ if (likely(skb->dev && skb->dev->nd_net)) return dev_net(skb->dev); - if (skb_dst(skb)->dev) + if (skb_dst(skb) && skb_dst(skb)->dev) return dev_net(skb_dst(skb)->dev); WARN(skb->sk, "Maybe skb_sknet should be used in %s() at line:%d\n", __func__, __LINE__); diff --git a/include/net/mac80211.h b/include/net/mac80211.h index cb13239fe8e3..025d4cc7bbf8 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -1753,8 +1753,19 @@ enum ieee80211_ampdu_mlme_action { * that TX/RX_STOP can pass NULL for this parameter. * The @buf_size parameter is only valid when the action is set to * %IEEE80211_AMPDU_TX_OPERATIONAL and indicates the peer's reorder - * buffer size (number of subframes) for this session -- aggregates - * containing more subframes than this may not be transmitted to the peer. + * buffer size (number of subframes) for this session -- the driver + * may neither send aggregates containing more subframes than this + * nor send aggregates in a way that lost frames would exceed the + * buffer size. If just limiting the aggregate size, this would be + * possible with a buf_size of 8: + * - TX: 1.....7 + * - RX: 2....7 (lost frame #1) + * - TX: 8..1... + * which is invalid since #1 was now re-transmitted well past the + * buffer size of 8. Correct ways to retransmit #1 would be: + * - TX: 1 or 18 or 81 + * Even "189" would be wrong since 1 could be lost again. + * * Returns a negative error code on failure. * The callback can sleep. * diff --git a/include/net/route.h b/include/net/route.h index f88429cad52a..8fce0621cad1 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -64,6 +64,7 @@ struct rtable { __be32 rt_dst; /* Path destination */ __be32 rt_src; /* Path source */ + int rt_route_iif; int rt_iif; int rt_oif; __u32 rt_mark; @@ -80,12 +81,12 @@ struct rtable { static inline bool rt_is_input_route(struct rtable *rt) { - return rt->rt_iif != 0; + return rt->rt_route_iif != 0; } static inline bool rt_is_output_route(struct rtable *rt) { - return rt->rt_iif == 0; + return rt->rt_route_iif == 0; } struct ip_rt_acct { diff --git a/init/Kconfig b/init/Kconfig index 56240e724d9a..32745bfe059e 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -827,6 +827,11 @@ config SCHED_AUTOGROUP desktop applications. Task group autogeneration is currently based upon task session. +config SCHED_TTWU_QUEUE + bool + depends on !SPARC32 + default y + config MM_OWNER bool diff --git a/kernel/mutex-debug.c b/kernel/mutex-debug.c index ec815a960b5d..73da83aff418 100644 --- a/kernel/mutex-debug.c +++ b/kernel/mutex-debug.c @@ -75,7 +75,7 @@ void debug_mutex_unlock(struct mutex *lock) return; DEBUG_LOCKS_WARN_ON(lock->magic != lock); - DEBUG_LOCKS_WARN_ON(lock->owner != current_thread_info()); + DEBUG_LOCKS_WARN_ON(lock->owner != current); DEBUG_LOCKS_WARN_ON(!lock->wait_list.prev && !lock->wait_list.next); mutex_clear_owner(lock); } diff --git a/kernel/mutex-debug.h b/kernel/mutex-debug.h index 57d527a16f9d..0799fd3e4cfa 100644 --- a/kernel/mutex-debug.h +++ b/kernel/mutex-debug.h @@ -29,7 +29,7 @@ extern void debug_mutex_init(struct mutex *lock, const char *name, static inline void mutex_set_owner(struct mutex *lock) { - lock->owner = current_thread_info(); + lock->owner = current; } static inline void mutex_clear_owner(struct mutex *lock) diff --git a/kernel/mutex.c b/kernel/mutex.c index c4195fa98900..fe4706cb0c5b 100644 --- a/kernel/mutex.c +++ b/kernel/mutex.c @@ -160,7 +160,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, */ for (;;) { - struct thread_info *owner; + struct task_struct *owner; /* * If we own the BKL, then don't spin. The owner of diff --git a/kernel/mutex.h b/kernel/mutex.h index 67578ca48f94..4115fbf83b12 100644 --- a/kernel/mutex.h +++ b/kernel/mutex.h @@ -19,7 +19,7 @@ #ifdef CONFIG_SMP static inline void mutex_set_owner(struct mutex *lock) { - lock->owner = current_thread_info(); + lock->owner = current; } static inline void mutex_clear_owner(struct mutex *lock) diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig index 4603f08dc47b..6de9a8fc3417 100644 --- a/kernel/power/Kconfig +++ b/kernel/power/Kconfig @@ -18,9 +18,13 @@ config SUSPEND_FREEZER Turning OFF this setting is NOT recommended! If in doubt, say Y. +config HIBERNATE_CALLBACKS + bool + config HIBERNATION bool "Hibernation (aka 'suspend to disk')" depends on SWAP && ARCH_HIBERNATION_POSSIBLE + select HIBERNATE_CALLBACKS select LZO_COMPRESS select LZO_DECOMPRESS ---help--- @@ -85,7 +89,7 @@ config PM_STD_PARTITION config PM_SLEEP def_bool y - depends on SUSPEND || HIBERNATION || XEN_SAVE_RESTORE + depends on SUSPEND || HIBERNATE_CALLBACKS config PM_SLEEP_SMP def_bool y diff --git a/kernel/sched.c b/kernel/sched.c index 506cb8147c70..0cfe0310ed5d 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -312,6 +312,9 @@ struct cfs_rq { u64 exec_clock; u64 min_vruntime; +#ifndef CONFIG_64BIT + u64 min_vruntime_copy; +#endif struct rb_root tasks_timeline; struct rb_node *rb_leftmost; @@ -554,6 +557,10 @@ struct rq { unsigned int ttwu_count; unsigned int ttwu_local; #endif + +#ifdef CONFIG_SMP + struct task_struct *wake_list; +#endif }; static DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues); @@ -597,7 +604,7 @@ static inline int cpu_of(struct rq *rq) * Return the group to which this tasks belongs. * * We use task_subsys_state_check() and extend the RCU verification - * with lockdep_is_held(&task_rq(p)->lock) because cpu_cgroup_attach() + * with lockdep_is_held(&p->pi_lock) because cpu_cgroup_attach() * holds that lock for each task it moves into the cgroup. Therefore * by holding that lock, we pin the task to the current cgroup. */ @@ -607,7 +614,7 @@ static inline struct task_group *task_group(struct task_struct *p) struct cgroup_subsys_state *css; css = task_subsys_state_check(p, cpu_cgroup_subsys_id, - lockdep_is_held(&task_rq(p)->lock)); + lockdep_is_held(&p->pi_lock)); tg = container_of(css, struct task_group, css); return autogroup_task_group(p, tg); @@ -839,18 +846,39 @@ static inline int task_current(struct rq *rq, struct task_struct *p) return rq->curr == p; } -#ifndef __ARCH_WANT_UNLOCKED_CTXSW static inline int task_running(struct rq *rq, struct task_struct *p) { +#ifdef CONFIG_SMP + return p->on_cpu; +#else return task_current(rq, p); +#endif } +#ifndef __ARCH_WANT_UNLOCKED_CTXSW static inline void prepare_lock_switch(struct rq *rq, struct task_struct *next) { +#ifdef CONFIG_SMP + /* + * We can optimise this out completely for !SMP, because the + * SMP rebalancing from interrupt is the only thing that cares + * here. + */ + next->on_cpu = 1; +#endif } static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev) { +#ifdef CONFIG_SMP + /* + * After ->on_cpu is cleared, the task can be moved to a different CPU. + * We must ensure this doesn't happen until the switch is completely + * finished. + */ + smp_wmb(); + prev->on_cpu = 0; +#endif #ifdef CONFIG_DEBUG_SPINLOCK /* this is a valid case when another task releases the spinlock */ rq->lock.owner = current; @@ -866,15 +894,6 @@ static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev) } #else /* __ARCH_WANT_UNLOCKED_CTXSW */ -static inline int task_running(struct rq *rq, struct task_struct *p) -{ -#ifdef CONFIG_SMP - return p->oncpu; -#else - return task_current(rq, p); -#endif -} - static inline void prepare_lock_switch(struct rq *rq, struct task_struct *next) { #ifdef CONFIG_SMP @@ -883,7 +902,7 @@ static inline void prepare_lock_switch(struct rq *rq, struct task_struct *next) * SMP rebalancing from interrupt is the only thing that cares * here. */ - next->oncpu = 1; + next->on_cpu = 1; #endif #ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW raw_spin_unlock_irq(&rq->lock); @@ -896,12 +915,12 @@ static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev) { #ifdef CONFIG_SMP /* - * After ->oncpu is cleared, the task can be moved to a different CPU. + * After ->on_cpu is cleared, the task can be moved to a different CPU. * We must ensure this doesn't happen until the switch is completely * finished. */ smp_wmb(); - prev->oncpu = 0; + prev->on_cpu = 0; #endif #ifndef __ARCH_WANT_INTERRUPTS_ON_CTXSW local_irq_enable(); @@ -910,23 +929,15 @@ static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev) #endif /* __ARCH_WANT_UNLOCKED_CTXSW */ /* - * Check whether the task is waking, we use this to synchronize ->cpus_allowed - * against ttwu(). - */ -static inline int task_is_waking(struct task_struct *p) -{ - return unlikely(p->state == TASK_WAKING); -} - -/* - * __task_rq_lock - lock the runqueue a given task resides on. - * Must be called interrupts disabled. + * __task_rq_lock - lock the rq @p resides on. */ static inline struct rq *__task_rq_lock(struct task_struct *p) __acquires(rq->lock) { struct rq *rq; + lockdep_assert_held(&p->pi_lock); + for (;;) { rq = task_rq(p); raw_spin_lock(&rq->lock); @@ -937,22 +948,22 @@ static inline struct rq *__task_rq_lock(struct task_struct *p) } /* - * task_rq_lock - lock the runqueue a given task resides on and disable - * interrupts. Note the ordering: we can safely lookup the task_rq without - * explicitly disabling preemption. + * task_rq_lock - lock p->pi_lock and lock the rq @p resides on. */ static struct rq *task_rq_lock(struct task_struct *p, unsigned long *flags) + __acquires(p->pi_lock) __acquires(rq->lock) { struct rq *rq; for (;;) { - local_irq_save(*flags); + raw_spin_lock_irqsave(&p->pi_lock, *flags); rq = task_rq(p); raw_spin_lock(&rq->lock); if (likely(rq == task_rq(p))) return rq; - raw_spin_unlock_irqrestore(&rq->lock, *flags); + raw_spin_unlock(&rq->lock); + raw_spin_unlock_irqrestore(&p->pi_lock, *flags); } } @@ -962,10 +973,13 @@ static void __task_rq_unlock(struct rq *rq) raw_spin_unlock(&rq->lock); } -static inline void task_rq_unlock(struct rq *rq, unsigned long *flags) +static inline void +task_rq_unlock(struct rq *rq, struct task_struct *p, unsigned long *flags) __releases(rq->lock) + __releases(p->pi_lock) { - raw_spin_unlock_irqrestore(&rq->lock, *flags); + raw_spin_unlock(&rq->lock); + raw_spin_unlock_irqrestore(&p->pi_lock, *flags); } /* @@ -1774,7 +1788,6 @@ static void enqueue_task(struct rq *rq, struct task_struct *p, int flags) update_rq_clock(rq); sched_info_queued(p); p->sched_class->enqueue_task(rq, p, flags); - p->se.on_rq = 1; } static void dequeue_task(struct rq *rq, struct task_struct *p, int flags) @@ -1782,7 +1795,6 @@ static void dequeue_task(struct rq *rq, struct task_struct *p, int flags) update_rq_clock(rq); sched_info_dequeued(p); p->sched_class->dequeue_task(rq, p, flags); - p->se.on_rq = 0; } /* @@ -2117,7 +2129,7 @@ static void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags) * A queue event has occurred, and we're going to schedule. In * this case, we can save a useless back to back clock update. */ - if (rq->curr->se.on_rq && test_tsk_need_resched(rq->curr)) + if (rq->curr->on_rq && test_tsk_need_resched(rq->curr)) rq->skip_clock_update = 1; } @@ -2163,6 +2175,11 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu) */ WARN_ON_ONCE(p->state != TASK_RUNNING && p->state != TASK_WAKING && !(task_thread_info(p)->preempt_count & PREEMPT_ACTIVE)); + +#ifdef CONFIG_LOCKDEP + WARN_ON_ONCE(debug_locks && !(lockdep_is_held(&p->pi_lock) || + lockdep_is_held(&task_rq(p)->lock))); +#endif #endif trace_sched_migrate_task(p, new_cpu); @@ -2183,19 +2200,6 @@ struct migration_arg { static int migration_cpu_stop(void *data); /* - * The task's runqueue lock must be held. - * Returns true if you have to wait for migration thread. - */ -static bool migrate_task(struct task_struct *p, struct rq *rq) -{ - /* - * If the task is not on a runqueue (and not running), then - * the next wake-up will properly place the task. - */ - return p->se.on_rq || task_running(rq, p); -} - -/* * wait_task_inactive - wait for a thread to unschedule. * * If @match_state is nonzero, it's the @p->state value just checked and @@ -2252,11 +2256,11 @@ unsigned long wait_task_inactive(struct task_struct *p, long match_state) rq = task_rq_lock(p, &flags); trace_sched_wait_task(p); running = task_running(rq, p); - on_rq = p->se.on_rq; + on_rq = p->on_rq; ncsw = 0; if (!match_state || p->state == match_state) ncsw = p->nvcsw | LONG_MIN; /* sets MSB */ - task_rq_unlock(rq, &flags); + task_rq_unlock(rq, p, &flags); /* * If it changed from the expected state, bail out now. @@ -2331,7 +2335,7 @@ EXPORT_SYMBOL_GPL(kick_process); #ifdef CONFIG_SMP /* - * ->cpus_allowed is protected by either TASK_WAKING or rq->lock held. + * ->cpus_allowed is protected by both rq->lock and p->pi_lock */ static int select_fallback_rq(int cpu, struct task_struct *p) { @@ -2364,12 +2368,12 @@ static int select_fallback_rq(int cpu, struct task_struct *p) } /* - * The caller (fork, wakeup) owns TASK_WAKING, ->cpus_allowed is stable. + * The caller (fork, wakeup) owns p->pi_lock, ->cpus_allowed is stable. */ static inline -int select_task_rq(struct rq *rq, struct task_struct *p, int sd_flags, int wake_flags) +int select_task_rq(struct task_struct *p, int sd_flags, int wake_flags) { - int cpu = p->sched_class->select_task_rq(rq, p, sd_flags, wake_flags); + int cpu = p->sched_class->select_task_rq(p, sd_flags, wake_flags); /* * In order not to call set_task_cpu() on a blocking task we need @@ -2395,27 +2399,60 @@ static void update_avg(u64 *avg, u64 sample) } #endif -static inline void ttwu_activate(struct task_struct *p, struct rq *rq, - bool is_sync, bool is_migrate, bool is_local, - unsigned long en_flags) +static void +ttwu_stat(struct task_struct *p, int cpu, int wake_flags) { +#ifdef CONFIG_SCHEDSTATS + struct rq *rq = this_rq(); + +#ifdef CONFIG_SMP + int this_cpu = smp_processor_id(); + + if (cpu == this_cpu) { + schedstat_inc(rq, ttwu_local); + schedstat_inc(p, se.statistics.nr_wakeups_local); + } else { + struct sched_domain *sd; + + schedstat_inc(p, se.statistics.nr_wakeups_remote); + for_each_domain(this_cpu, sd) { + if (cpumask_test_cpu(cpu, sched_domain_span(sd))) { + schedstat_inc(sd, ttwu_wake_remote); + break; + } + } + } +#endif /* CONFIG_SMP */ + + schedstat_inc(rq, ttwu_count); schedstat_inc(p, se.statistics.nr_wakeups); - if (is_sync) + + if (wake_flags & WF_SYNC) schedstat_inc(p, se.statistics.nr_wakeups_sync); - if (is_migrate) + + if (cpu != task_cpu(p)) schedstat_inc(p, se.statistics.nr_wakeups_migrate); - if (is_local) - schedstat_inc(p, se.statistics.nr_wakeups_local); - else - schedstat_inc(p, se.statistics.nr_wakeups_remote); +#endif /* CONFIG_SCHEDSTATS */ +} + +static void ttwu_activate(struct rq *rq, struct task_struct *p, int en_flags) +{ activate_task(rq, p, en_flags); + p->on_rq = 1; + + /* if a worker is waking up, notify workqueue */ + if (p->flags & PF_WQ_WORKER) + wq_worker_waking_up(p, cpu_of(rq)); } -static inline void ttwu_post_activation(struct task_struct *p, struct rq *rq, - int wake_flags, bool success) +/* + * Mark the task runnable and perform wakeup-preemption. + */ +static void +ttwu_do_wakeup(struct rq *rq, struct task_struct *p, int wake_flags) { - trace_sched_wakeup(p, success); + trace_sched_wakeup(p, true); check_preempt_curr(rq, p, wake_flags); p->state = TASK_RUNNING; @@ -2434,9 +2471,99 @@ static inline void ttwu_post_activation(struct task_struct *p, struct rq *rq, rq->idle_stamp = 0; } #endif - /* if a worker is waking up, notify workqueue */ - if ((p->flags & PF_WQ_WORKER) && success) - wq_worker_waking_up(p, cpu_of(rq)); +} + +static void +ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags) +{ +#ifdef CONFIG_SMP + if (p->sched_contributes_to_load) + rq->nr_uninterruptible--; +#endif + + ttwu_activate(rq, p, ENQUEUE_WAKEUP | ENQUEUE_WAKING); + ttwu_do_wakeup(rq, p, wake_flags); +} + +/* + * Called in case the task @p isn't fully descheduled from its runqueue, + * in this case we must do a remote wakeup. Its a 'light' wakeup though, + * since all we need to do is flip p->state to TASK_RUNNING, since + * the task is still ->on_rq. + */ +static int ttwu_remote(struct task_struct *p, int wake_flags) +{ + struct rq *rq; + int ret = 0; + + rq = __task_rq_lock(p); + if (p->on_rq) { + ttwu_do_wakeup(rq, p, wake_flags); + ret = 1; + } + __task_rq_unlock(rq); + + return ret; +} + +#ifdef CONFIG_SMP +static void sched_ttwu_pending(void) +{ + struct rq *rq = this_rq(); + struct task_struct *list = xchg(&rq->wake_list, NULL); + + if (!list) + return; + + raw_spin_lock(&rq->lock); + + while (list) { + struct task_struct *p = list; + list = list->wake_entry; + ttwu_do_activate(rq, p, 0); + } + + raw_spin_unlock(&rq->lock); +} + +void scheduler_ipi(void) +{ + sched_ttwu_pending(); +} + +static void ttwu_queue_remote(struct task_struct *p, int cpu) +{ + struct rq *rq = cpu_rq(cpu); + struct task_struct *next = rq->wake_list; + + for (;;) { + struct task_struct *old = next; + + p->wake_entry = next; + next = cmpxchg(&rq->wake_list, old, p); + if (next == old) + break; + } + + if (!next) + smp_send_reschedule(cpu); +} +#endif + +static void ttwu_queue(struct task_struct *p, int cpu) +{ + struct rq *rq = cpu_rq(cpu); + +#if defined(CONFIG_SMP) && defined(CONFIG_SCHED_TTWU_QUEUE) + if (sched_feat(TTWU_QUEUE) && cpu != smp_processor_id()) { + ttwu_queue_remote(p, cpu); + return; + } +#endif + + raw_spin_lock(&rq->lock); + ttwu_do_activate(rq, p, 0); + raw_spin_unlock(&rq->lock); } /** @@ -2454,92 +2581,64 @@ static inline void ttwu_post_activation(struct task_struct *p, struct rq *rq, * Returns %true if @p was woken up, %false if it was already running * or @state didn't match @p's state. */ -static int try_to_wake_up(struct task_struct *p, unsigned int state, - int wake_flags) +static int +try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) { - int cpu, orig_cpu, this_cpu, success = 0; unsigned long flags; - unsigned long en_flags = ENQUEUE_WAKEUP; - struct rq *rq; - - this_cpu = get_cpu(); + int cpu, success = 0; smp_wmb(); - rq = task_rq_lock(p, &flags); + raw_spin_lock_irqsave(&p->pi_lock, flags); if (!(p->state & state)) goto out; - if (p->se.on_rq) - goto out_running; - + success = 1; /* we're going to change ->state */ cpu = task_cpu(p); - orig_cpu = cpu; -#ifdef CONFIG_SMP - if (unlikely(task_running(rq, p))) - goto out_activate; + if (p->on_rq && ttwu_remote(p, wake_flags)) + goto stat; +#ifdef CONFIG_SMP /* - * In order to handle concurrent wakeups and release the rq->lock - * we put the task in TASK_WAKING state. - * - * First fix up the nr_uninterruptible count: + * If the owning (remote) cpu is still in the middle of schedule() with + * this task as prev, wait until its done referencing the task. */ - if (task_contributes_to_load(p)) { - if (likely(cpu_online(orig_cpu))) - rq->nr_uninterruptible--; - else - this_rq()->nr_uninterruptible--; - } - p->state = TASK_WAKING; - - if (p->sched_class->task_waking) { - p->sched_class->task_waking(rq, p); - en_flags |= ENQUEUE_WAKING; + while (p->on_cpu) { +#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW + /* + * If called from interrupt context we could have landed in the + * middle of schedule(), in this case we should take care not + * to spin on ->on_cpu if p is current, since that would + * deadlock. + */ + if (p == current) { + ttwu_queue(p, cpu); + goto stat; + } +#endif + cpu_relax(); } - - cpu = select_task_rq(rq, p, SD_BALANCE_WAKE, wake_flags); - if (cpu != orig_cpu) - set_task_cpu(p, cpu); - __task_rq_unlock(rq); - - rq = cpu_rq(cpu); - raw_spin_lock(&rq->lock); - /* - * We migrated the task without holding either rq->lock, however - * since the task is not on the task list itself, nobody else - * will try and migrate the task, hence the rq should match the - * cpu we just moved it to. + * Pairs with the smp_wmb() in finish_lock_switch(). */ - WARN_ON(task_cpu(p) != cpu); - WARN_ON(p->state != TASK_WAKING); + smp_rmb(); -#ifdef CONFIG_SCHEDSTATS - schedstat_inc(rq, ttwu_count); - if (cpu == this_cpu) - schedstat_inc(rq, ttwu_local); - else { - struct sched_domain *sd; - for_each_domain(this_cpu, sd) { - if (cpumask_test_cpu(cpu, sched_domain_span(sd))) { - schedstat_inc(sd, ttwu_wake_remote); - break; - } - } - } -#endif /* CONFIG_SCHEDSTATS */ + p->sched_contributes_to_load = !!task_contributes_to_load(p); + p->state = TASK_WAKING; -out_activate: + if (p->sched_class->task_waking) + p->sched_class->task_waking(p); + + cpu = select_task_rq(p, SD_BALANCE_WAKE, wake_flags); + if (task_cpu(p) != cpu) + set_task_cpu(p, cpu); #endif /* CONFIG_SMP */ - ttwu_activate(p, rq, wake_flags & WF_SYNC, orig_cpu != cpu, - cpu == this_cpu, en_flags); - success = 1; -out_running: - ttwu_post_activation(p, rq, wake_flags, success); + + ttwu_queue(p, cpu); +stat: + ttwu_stat(p, cpu, wake_flags); out: - task_rq_unlock(rq, &flags); - put_cpu(); + raw_spin_unlock_irqrestore(&p->pi_lock, flags); return success; } @@ -2548,31 +2647,34 @@ out: * try_to_wake_up_local - try to wake up a local task with rq lock held * @p: the thread to be awakened * - * Put @p on the run-queue if it's not already there. The caller must + * Put @p on the run-queue if it's not already there. The caller must * ensure that this_rq() is locked, @p is bound to this_rq() and not - * the current task. this_rq() stays locked over invocation. + * the current task. */ static void try_to_wake_up_local(struct task_struct *p) { struct rq *rq = task_rq(p); - bool success = false; BUG_ON(rq != this_rq()); BUG_ON(p == current); lockdep_assert_held(&rq->lock); + if (!raw_spin_trylock(&p->pi_lock)) { + raw_spin_unlock(&rq->lock); + raw_spin_lock(&p->pi_lock); + raw_spin_lock(&rq->lock); + } + if (!(p->state & TASK_NORMAL)) - return; + goto out; - if (!p->se.on_rq) { - if (likely(!task_running(rq, p))) { - schedstat_inc(rq, ttwu_count); - schedstat_inc(rq, ttwu_local); - } - ttwu_activate(p, rq, false, false, true, ENQUEUE_WAKEUP); - success = true; - } - ttwu_post_activation(p, rq, 0, success); + if (!p->on_rq) + ttwu_activate(rq, p, ENQUEUE_WAKEUP); + + ttwu_do_wakeup(rq, p, 0); + ttwu_stat(p, smp_processor_id(), 0); +out: + raw_spin_unlock(&p->pi_lock); } /** @@ -2605,19 +2707,21 @@ int wake_up_state(struct task_struct *p, unsigned int state) */ static void __sched_fork(struct task_struct *p) { + p->on_rq = 0; + + p->se.on_rq = 0; p->se.exec_start = 0; p->se.sum_exec_runtime = 0; p->se.prev_sum_exec_runtime = 0; p->se.nr_migrations = 0; p->se.vruntime = 0; + INIT_LIST_HEAD(&p->se.group_node); #ifdef CONFIG_SCHEDSTATS memset(&p->se.statistics, 0, sizeof(p->se.statistics)); #endif INIT_LIST_HEAD(&p->rt.run_list); - p->se.on_rq = 0; - INIT_LIST_HEAD(&p->se.group_node); #ifdef CONFIG_PREEMPT_NOTIFIERS INIT_HLIST_HEAD(&p->preempt_notifiers); @@ -2629,6 +2733,7 @@ static void __sched_fork(struct task_struct *p) */ void sched_fork(struct task_struct *p, int clone_flags) { + unsigned long flags; int cpu = get_cpu(); __sched_fork(p); @@ -2679,16 +2784,16 @@ void sched_fork(struct task_struct *p, int clone_flags) * * Silence PROVE_RCU. */ - rcu_read_lock(); + raw_spin_lock_irqsave(&p->pi_lock, flags); set_task_cpu(p, cpu); - rcu_read_unlock(); + raw_spin_unlock_irqrestore(&p->pi_lock, flags); #if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT) if (likely(sched_info_on())) memset(&p->sched_info, 0, sizeof(p->sched_info)); #endif -#if defined(CONFIG_SMP) && defined(__ARCH_WANT_UNLOCKED_CTXSW) - p->oncpu = 0; +#if defined(CONFIG_SMP) + p->on_cpu = 0; #endif #ifdef CONFIG_PREEMPT /* Want to start with kernel preemption disabled. */ @@ -2712,37 +2817,27 @@ void wake_up_new_task(struct task_struct *p, unsigned long clone_flags) { unsigned long flags; struct rq *rq; - int cpu __maybe_unused = get_cpu(); + raw_spin_lock_irqsave(&p->pi_lock, flags); #ifdef CONFIG_SMP - rq = task_rq_lock(p, &flags); - p->state = TASK_WAKING; - /* * Fork balancing, do it here and not earlier because: * - cpus_allowed can change in the fork path * - any previously selected cpu might disappear through hotplug - * - * We set TASK_WAKING so that select_task_rq() can drop rq->lock - * without people poking at ->cpus_allowed. */ - cpu = select_task_rq(rq, p, SD_BALANCE_FORK, 0); - set_task_cpu(p, cpu); - - p->state = TASK_RUNNING; - task_rq_unlock(rq, &flags); + set_task_cpu(p, select_task_rq(p, SD_BALANCE_FORK, 0)); #endif - rq = task_rq_lock(p, &flags); + rq = __task_rq_lock(p); activate_task(rq, p, 0); - trace_sched_wakeup_new(p, 1); + p->on_rq = 1; + trace_sched_wakeup_new(p, true); check_preempt_curr(rq, p, WF_FORK); #ifdef CONFIG_SMP if (p->sched_class->task_woken) p->sched_class->task_woken(rq, p); #endif - task_rq_unlock(rq, &flags); - put_cpu(); + task_rq_unlock(rq, p, &flags); } #ifdef CONFIG_PREEMPT_NOTIFIERS @@ -3451,27 +3546,22 @@ void sched_exec(void) { struct task_struct *p = current; unsigned long flags; - struct rq *rq; int dest_cpu; - rq = task_rq_lock(p, &flags); - dest_cpu = p->sched_class->select_task_rq(rq, p, SD_BALANCE_EXEC, 0); + raw_spin_lock_irqsave(&p->pi_lock, flags); + dest_cpu = p->sched_class->select_task_rq(p, SD_BALANCE_EXEC, 0); if (dest_cpu == smp_processor_id()) goto unlock; - /* - * select_task_rq() can race against ->cpus_allowed - */ - if (cpumask_test_cpu(dest_cpu, &p->cpus_allowed) && - likely(cpu_active(dest_cpu)) && migrate_task(p, rq)) { + if (likely(cpu_active(dest_cpu))) { struct migration_arg arg = { p, dest_cpu }; - task_rq_unlock(rq, &flags); - stop_one_cpu(cpu_of(rq), migration_cpu_stop, &arg); + raw_spin_unlock_irqrestore(&p->pi_lock, flags); + stop_one_cpu(task_cpu(p), migration_cpu_stop, &arg); return; } unlock: - task_rq_unlock(rq, &flags); + raw_spin_unlock_irqrestore(&p->pi_lock, flags); } #endif @@ -3508,7 +3598,7 @@ unsigned long long task_delta_exec(struct task_struct *p) rq = task_rq_lock(p, &flags); ns = do_task_delta_exec(p, rq); - task_rq_unlock(rq, &flags); + task_rq_unlock(rq, p, &flags); return ns; } @@ -3526,7 +3616,7 @@ unsigned long long task_sched_runtime(struct task_struct *p) rq = task_rq_lock(p, &flags); ns = p->se.sum_exec_runtime + do_task_delta_exec(p, rq); - task_rq_unlock(rq, &flags); + task_rq_unlock(rq, p, &flags); return ns; } @@ -3550,7 +3640,7 @@ unsigned long long thread_group_sched_runtime(struct task_struct *p) rq = task_rq_lock(p, &flags); thread_group_cputime(p, &totals); ns = totals.sum_exec_runtime + do_task_delta_exec(p, rq); - task_rq_unlock(rq, &flags); + task_rq_unlock(rq, p, &flags); return ns; } @@ -4036,7 +4126,7 @@ static inline void schedule_debug(struct task_struct *prev) static void put_prev_task(struct rq *rq, struct task_struct *prev) { - if (prev->se.on_rq) + if (prev->on_rq) update_rq_clock(rq); prev->sched_class->put_prev_task(rq, prev); } @@ -4098,11 +4188,13 @@ need_resched: if (unlikely(signal_pending_state(prev->state, prev))) { prev->state = TASK_RUNNING; } else { + deactivate_task(rq, prev, DEQUEUE_SLEEP); + prev->on_rq = 0; + /* - * If a worker is going to sleep, notify and - * ask workqueue whether it wants to wake up a - * task to maintain concurrency. If so, wake - * up the task. + * If a worker went to sleep, notify and ask workqueue + * whether it wants to wake up a task to maintain + * concurrency. */ if (prev->flags & PF_WQ_WORKER) { struct task_struct *to_wakeup; @@ -4111,21 +4203,20 @@ need_resched: if (to_wakeup) try_to_wake_up_local(to_wakeup); } - deactivate_task(rq, prev, DEQUEUE_SLEEP); + + /* + * If we are going to sleep and we have plugged IO + * queued, make sure to submit it to avoid deadlocks. + */ + if (blk_needs_flush_plug(prev)) { + raw_spin_unlock(&rq->lock); + blk_flush_plug(prev); + raw_spin_lock(&rq->lock); + } } switch_count = &prev->nvcsw; } - /* - * If we are going to sleep and we have plugged IO queued, make - * sure to submit it to avoid deadlocks. - */ - if (prev->state != TASK_RUNNING && blk_needs_flush_plug(prev)) { - raw_spin_unlock(&rq->lock); - blk_flush_plug(prev); - raw_spin_lock(&rq->lock); - } - pre_schedule(rq, prev); if (unlikely(!rq->nr_running)) @@ -4162,70 +4253,53 @@ need_resched: EXPORT_SYMBOL(schedule); #ifdef CONFIG_MUTEX_SPIN_ON_OWNER -/* - * Look out! "owner" is an entirely speculative pointer - * access and not reliable. - */ -int mutex_spin_on_owner(struct mutex *lock, struct thread_info *owner) -{ - unsigned int cpu; - struct rq *rq; - if (!sched_feat(OWNER_SPIN)) - return 0; +static inline bool owner_running(struct mutex *lock, struct task_struct *owner) +{ + bool ret = false; -#ifdef CONFIG_DEBUG_PAGEALLOC - /* - * Need to access the cpu field knowing that - * DEBUG_PAGEALLOC could have unmapped it if - * the mutex owner just released it and exited. - */ - if (probe_kernel_address(&owner->cpu, cpu)) - return 0; -#else - cpu = owner->cpu; -#endif + rcu_read_lock(); + if (lock->owner != owner) + goto fail; /* - * Even if the access succeeded (likely case), - * the cpu field may no longer be valid. + * Ensure we emit the owner->on_cpu, dereference _after_ checking + * lock->owner still matches owner, if that fails, owner might + * point to free()d memory, if it still matches, the rcu_read_lock() + * ensures the memory stays valid. */ - if (cpu >= nr_cpumask_bits) - return 0; + barrier(); - /* - * We need to validate that we can do a - * get_cpu() and that we have the percpu area. - */ - if (!cpu_online(cpu)) - return 0; + ret = owner->on_cpu; +fail: + rcu_read_unlock(); - rq = cpu_rq(cpu); + return ret; +} - for (;;) { - /* - * Owner changed, break to re-assess state. - */ - if (lock->owner != owner) { - /* - * If the lock has switched to a different owner, - * we likely have heavy contention. Return 0 to quit - * optimistic spinning and not contend further: - */ - if (lock->owner) - return 0; - break; - } +/* + * Look out! "owner" is an entirely speculative pointer + * access and not reliable. + */ +int mutex_spin_on_owner(struct mutex *lock, struct task_struct *owner) +{ + if (!sched_feat(OWNER_SPIN)) + return 0; - /* - * Is that owner really running on that cpu? - */ - if (task_thread_info(rq->curr) != owner || need_resched()) + while (owner_running(lock, owner)) { + if (need_resched()) return 0; arch_mutex_cpu_relax(); } + /* + * If the owner changed to another task there is likely + * heavy contention, stop spinning. + */ + if (lock->owner) + return 0; + return 1; } #endif @@ -4685,19 +4759,18 @@ EXPORT_SYMBOL(sleep_on_timeout); */ void rt_mutex_setprio(struct task_struct *p, int prio) { - unsigned long flags; int oldprio, on_rq, running; struct rq *rq; const struct sched_class *prev_class; BUG_ON(prio < 0 || prio > MAX_PRIO); - rq = task_rq_lock(p, &flags); + rq = __task_rq_lock(p); trace_sched_pi_setprio(p, prio); oldprio = p->prio; prev_class = p->sched_class; - on_rq = p->se.on_rq; + on_rq = p->on_rq; running = task_current(rq, p); if (on_rq) dequeue_task(rq, p, 0); @@ -4717,7 +4790,7 @@ void rt_mutex_setprio(struct task_struct *p, int prio) enqueue_task(rq, p, oldprio < prio ? ENQUEUE_HEAD : 0); check_class_changed(rq, p, prev_class, oldprio); - task_rq_unlock(rq, &flags); + __task_rq_unlock(rq); } #endif @@ -4745,7 +4818,7 @@ void set_user_nice(struct task_struct *p, long nice) p->static_prio = NICE_TO_PRIO(nice); goto out_unlock; } - on_rq = p->se.on_rq; + on_rq = p->on_rq; if (on_rq) dequeue_task(rq, p, 0); @@ -4765,7 +4838,7 @@ void set_user_nice(struct task_struct *p, long nice) resched_task(rq->curr); } out_unlock: - task_rq_unlock(rq, &flags); + task_rq_unlock(rq, p, &flags); } EXPORT_SYMBOL(set_user_nice); @@ -4879,8 +4952,6 @@ static struct task_struct *find_process_by_pid(pid_t pid) static void __setscheduler(struct rq *rq, struct task_struct *p, int policy, int prio) { - BUG_ON(p->se.on_rq); - p->policy = policy; p->rt_priority = prio; p->normal_prio = normal_prio(p); @@ -4995,20 +5066,17 @@ recheck: /* * make sure no PI-waiters arrive (or leave) while we are * changing the priority of the task: - */ - raw_spin_lock_irqsave(&p->pi_lock, flags); - /* + * * To be able to change p->policy safely, the appropriate * runqueue lock must be held. */ - rq = __task_rq_lock(p); + rq = task_rq_lock(p, &flags); /* * Changing the policy of the stop threads its a very bad idea */ if (p == rq->stop) { - __task_rq_unlock(rq); - raw_spin_unlock_irqrestore(&p->pi_lock, flags); + task_rq_unlock(rq, p, &flags); return -EINVAL; } @@ -5032,8 +5100,7 @@ recheck: if (rt_bandwidth_enabled() && rt_policy(policy) && task_group(p)->rt_bandwidth.rt_runtime == 0 && !task_group_is_autogroup(task_group(p))) { - __task_rq_unlock(rq); - raw_spin_unlock_irqrestore(&p->pi_lock, flags); + task_rq_unlock(rq, p, &flags); return -EPERM; } } @@ -5042,11 +5109,10 @@ recheck: /* recheck policy now with rq lock held */ if (unlikely(oldpolicy != -1 && oldpolicy != p->policy)) { policy = oldpolicy = -1; - __task_rq_unlock(rq); - raw_spin_unlock_irqrestore(&p->pi_lock, flags); + task_rq_unlock(rq, p, &flags); goto recheck; } - on_rq = p->se.on_rq; + on_rq = p->on_rq; running = task_current(rq, p); if (on_rq) deactivate_task(rq, p, 0); @@ -5065,8 +5131,7 @@ recheck: activate_task(rq, p, 0); check_class_changed(rq, p, prev_class, oldprio); - __task_rq_unlock(rq); - raw_spin_unlock_irqrestore(&p->pi_lock, flags); + task_rq_unlock(rq, p, &flags); rt_mutex_adjust_pi(p); @@ -5317,7 +5382,6 @@ long sched_getaffinity(pid_t pid, struct cpumask *mask) { struct task_struct *p; unsigned long flags; - struct rq *rq; int retval; get_online_cpus(); @@ -5332,9 +5396,9 @@ long sched_getaffinity(pid_t pid, struct cpumask *mask) if (retval) goto out_unlock; - rq = task_rq_lock(p, &flags); + raw_spin_lock_irqsave(&p->pi_lock, flags); cpumask_and(mask, &p->cpus_allowed, cpu_online_mask); - task_rq_unlock(rq, &flags); + raw_spin_unlock_irqrestore(&p->pi_lock, flags); out_unlock: rcu_read_unlock(); @@ -5659,7 +5723,7 @@ SYSCALL_DEFINE2(sched_rr_get_interval, pid_t, pid, rq = task_rq_lock(p, &flags); time_slice = p->sched_class->get_rr_interval(rq, p); - task_rq_unlock(rq, &flags); + task_rq_unlock(rq, p, &flags); rcu_read_unlock(); jiffies_to_timespec(time_slice, &t); @@ -5777,8 +5841,8 @@ void __cpuinit init_idle(struct task_struct *idle, int cpu) rcu_read_unlock(); rq->curr = rq->idle = idle; -#if defined(CONFIG_SMP) && defined(__ARCH_WANT_UNLOCKED_CTXSW) - idle->oncpu = 1; +#if defined(CONFIG_SMP) + idle->on_cpu = 1; #endif raw_spin_unlock_irqrestore(&rq->lock, flags); @@ -5882,18 +5946,7 @@ int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask) unsigned int dest_cpu; int ret = 0; - /* - * Serialize against TASK_WAKING so that ttwu() and wunt() can - * drop the rq->lock and still rely on ->cpus_allowed. - */ -again: - while (task_is_waking(p)) - cpu_relax(); rq = task_rq_lock(p, &flags); - if (task_is_waking(p)) { - task_rq_unlock(rq, &flags); - goto again; - } if (!cpumask_intersects(new_mask, cpu_active_mask)) { ret = -EINVAL; @@ -5918,16 +5971,16 @@ again: goto out; dest_cpu = cpumask_any_and(cpu_active_mask, new_mask); - if (migrate_task(p, rq)) { + if (p->on_rq) { struct migration_arg arg = { p, dest_cpu }; /* Need help from migration thread: drop lock and wait. */ - task_rq_unlock(rq, &flags); + task_rq_unlock(rq, p, &flags); stop_one_cpu(cpu_of(rq), migration_cpu_stop, &arg); tlb_migrate_finish(p->mm); return 0; } out: - task_rq_unlock(rq, &flags); + task_rq_unlock(rq, p, &flags); return ret; } @@ -5955,6 +6008,7 @@ static int __migrate_task(struct task_struct *p, int src_cpu, int dest_cpu) rq_src = cpu_rq(src_cpu); rq_dest = cpu_rq(dest_cpu); + raw_spin_lock(&p->pi_lock); double_rq_lock(rq_src, rq_dest); /* Already moved. */ if (task_cpu(p) != src_cpu) @@ -5967,7 +6021,7 @@ static int __migrate_task(struct task_struct *p, int src_cpu, int dest_cpu) * If we're not on a rq, the next wake-up will ensure we're * placed properly. */ - if (p->se.on_rq) { + if (p->on_rq) { deactivate_task(rq_src, p, 0); set_task_cpu(p, dest_cpu); activate_task(rq_dest, p, 0); @@ -5977,6 +6031,7 @@ done: ret = 1; fail: double_rq_unlock(rq_src, rq_dest); + raw_spin_unlock(&p->pi_lock); return ret; } @@ -6317,6 +6372,7 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu) #ifdef CONFIG_HOTPLUG_CPU case CPU_DYING: + sched_ttwu_pending(); /* Update our root-domain */ raw_spin_lock_irqsave(&rq->lock, flags); if (rq->rd) { @@ -7961,7 +8017,7 @@ static void normalize_task(struct rq *rq, struct task_struct *p) int old_prio = p->prio; int on_rq; - on_rq = p->se.on_rq; + on_rq = p->on_rq; if (on_rq) deactivate_task(rq, p, 0); __setscheduler(rq, p, SCHED_NORMAL, 0); @@ -8304,7 +8360,7 @@ void sched_move_task(struct task_struct *tsk) rq = task_rq_lock(tsk, &flags); running = task_current(rq, tsk); - on_rq = tsk->se.on_rq; + on_rq = tsk->on_rq; if (on_rq) dequeue_task(rq, tsk, 0); @@ -8323,7 +8379,7 @@ void sched_move_task(struct task_struct *tsk) if (on_rq) enqueue_task(rq, tsk, 0); - task_rq_unlock(rq, &flags); + task_rq_unlock(rq, tsk, &flags); } #endif /* CONFIG_CGROUP_SCHED */ diff --git a/kernel/sched_debug.c b/kernel/sched_debug.c index 7bacd83a4158..3669bec6e130 100644 --- a/kernel/sched_debug.c +++ b/kernel/sched_debug.c @@ -152,7 +152,7 @@ static void print_rq(struct seq_file *m, struct rq *rq, int rq_cpu) read_lock_irqsave(&tasklist_lock, flags); do_each_thread(g, p) { - if (!p->se.on_rq || task_cpu(p) != rq_cpu) + if (!p->on_rq || task_cpu(p) != rq_cpu) continue; print_task(m, rq, p); diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index 9c5679cfe3b0..87445931a179 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -358,6 +358,10 @@ static void update_min_vruntime(struct cfs_rq *cfs_rq) } cfs_rq->min_vruntime = max_vruntime(cfs_rq->min_vruntime, vruntime); +#ifndef CONFIG_64BIT + smp_wmb(); + cfs_rq->min_vruntime_copy = cfs_rq->min_vruntime; +#endif } /* @@ -1372,12 +1376,25 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags) #ifdef CONFIG_SMP -static void task_waking_fair(struct rq *rq, struct task_struct *p) +static void task_waking_fair(struct task_struct *p) { struct sched_entity *se = &p->se; struct cfs_rq *cfs_rq = cfs_rq_of(se); + u64 min_vruntime; - se->vruntime -= cfs_rq->min_vruntime; +#ifndef CONFIG_64BIT + u64 min_vruntime_copy; + + do { + min_vruntime_copy = cfs_rq->min_vruntime_copy; + smp_rmb(); + min_vruntime = cfs_rq->min_vruntime; + } while (min_vruntime != min_vruntime_copy); +#else + min_vruntime = cfs_rq->min_vruntime; +#endif + + se->vruntime -= min_vruntime; } #ifdef CONFIG_FAIR_GROUP_SCHED @@ -1659,7 +1676,7 @@ static int select_idle_sibling(struct task_struct *p, int target) * preempt must be disabled. */ static int -select_task_rq_fair(struct rq *rq, struct task_struct *p, int sd_flag, int wake_flags) +select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flags) { struct sched_domain *tmp, *affine_sd = NULL, *sd = NULL; int cpu = smp_processor_id(); diff --git a/kernel/sched_features.h b/kernel/sched_features.h index 68e69acc29b9..be40f7371ee1 100644 --- a/kernel/sched_features.h +++ b/kernel/sched_features.h @@ -64,3 +64,9 @@ SCHED_FEAT(OWNER_SPIN, 1) * Decrement CPU power based on irq activity */ SCHED_FEAT(NONIRQ_POWER, 1) + +/* + * Queue remote wakeups on the target CPU and process them + * using the scheduler IPI. Reduces rq->lock contention/bounces. + */ +SCHED_FEAT(TTWU_QUEUE, 1) diff --git a/kernel/sched_idletask.c b/kernel/sched_idletask.c index a776a6396427..0a51882534ea 100644 --- a/kernel/sched_idletask.c +++ b/kernel/sched_idletask.c @@ -7,7 +7,7 @@ #ifdef CONFIG_SMP static int -select_task_rq_idle(struct rq *rq, struct task_struct *p, int sd_flag, int flags) +select_task_rq_idle(struct task_struct *p, int sd_flag, int flags) { return task_cpu(p); /* IDLE tasks as never migrated */ } diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c index e7cebdc65f82..19ecb3127379 100644 --- a/kernel/sched_rt.c +++ b/kernel/sched_rt.c @@ -977,13 +977,23 @@ static void yield_task_rt(struct rq *rq) static int find_lowest_rq(struct task_struct *task); static int -select_task_rq_rt(struct rq *rq, struct task_struct *p, int sd_flag, int flags) +select_task_rq_rt(struct task_struct *p, int sd_flag, int flags) { + struct task_struct *curr; + struct rq *rq; + int cpu; + if (sd_flag != SD_BALANCE_WAKE) return smp_processor_id(); + cpu = task_cpu(p); + rq = cpu_rq(cpu); + + rcu_read_lock(); + curr = ACCESS_ONCE(rq->curr); /* unlocked access */ + /* - * If the current task is an RT task, then + * If the current task on @p's runqueue is an RT task, then * try to see if we can wake this RT task up on another * runqueue. Otherwise simply start this RT task * on its current runqueue. @@ -997,21 +1007,25 @@ select_task_rq_rt(struct rq *rq, struct task_struct *p, int sd_flag, int flags) * lock? * * For equal prio tasks, we just let the scheduler sort it out. + * + * Otherwise, just let it ride on the affined RQ and the + * post-schedule router will push the preempted task away + * + * This test is optimistic, if we get it wrong the load-balancer + * will have to sort it out. */ - if (unlikely(rt_task(rq->curr)) && - (rq->curr->rt.nr_cpus_allowed < 2 || - rq->curr->prio < p->prio) && + if (curr && unlikely(rt_task(curr)) && + (curr->rt.nr_cpus_allowed < 2 || + curr->prio < p->prio) && (p->rt.nr_cpus_allowed > 1)) { - int cpu = find_lowest_rq(p); + int target = find_lowest_rq(p); - return (cpu == -1) ? task_cpu(p) : cpu; + if (target != -1) + cpu = target; } + rcu_read_unlock(); - /* - * Otherwise, just let it ride on the affined RQ and the - * post-schedule router will push the preempted task away - */ - return task_cpu(p); + return cpu; } static void check_preempt_equal_prio(struct rq *rq, struct task_struct *p) @@ -1136,7 +1150,7 @@ static void put_prev_task_rt(struct rq *rq, struct task_struct *p) * The previous task needs to be made eligible for pushing * if it is still active */ - if (p->se.on_rq && p->rt.nr_cpus_allowed > 1) + if (on_rt_rq(&p->rt) && p->rt.nr_cpus_allowed > 1) enqueue_pushable_task(rq, p); } @@ -1287,7 +1301,7 @@ static struct rq *find_lock_lowest_rq(struct task_struct *task, struct rq *rq) !cpumask_test_cpu(lowest_rq->cpu, &task->cpus_allowed) || task_running(rq, task) || - !task->se.on_rq)) { + !task->on_rq)) { raw_spin_unlock(&lowest_rq->lock); lowest_rq = NULL; @@ -1321,7 +1335,7 @@ static struct task_struct *pick_next_pushable_task(struct rq *rq) BUG_ON(task_current(rq, p)); BUG_ON(p->rt.nr_cpus_allowed <= 1); - BUG_ON(!p->se.on_rq); + BUG_ON(!p->on_rq); BUG_ON(!rt_task(p)); return p; @@ -1467,7 +1481,7 @@ static int pull_rt_task(struct rq *this_rq) */ if (p && (p->prio < this_rq->rt.highest_prio.curr)) { WARN_ON(p == src_rq->curr); - WARN_ON(!p->se.on_rq); + WARN_ON(!p->on_rq); /* * There's a chance that p is higher in priority @@ -1538,7 +1552,7 @@ static void set_cpus_allowed_rt(struct task_struct *p, * Update the migration status of the RQ if we have an RT task * which is running AND changing its weight value. */ - if (p->se.on_rq && (weight != p->rt.nr_cpus_allowed)) { + if (p->on_rq && (weight != p->rt.nr_cpus_allowed)) { struct rq *rq = task_rq(p); if (!task_current(rq, p)) { @@ -1608,7 +1622,7 @@ static void switched_from_rt(struct rq *rq, struct task_struct *p) * we may need to handle the pulling of RT tasks * now. */ - if (p->se.on_rq && !rq->rt.rt_nr_running) + if (p->on_rq && !rq->rt.rt_nr_running) pull_rt_task(rq); } @@ -1638,7 +1652,7 @@ static void switched_to_rt(struct rq *rq, struct task_struct *p) * If that current running task is also an RT task * then see if we can move to another run queue. */ - if (p->se.on_rq && rq->curr != p) { + if (p->on_rq && rq->curr != p) { #ifdef CONFIG_SMP if (rq->rt.overloaded && push_rt_task(rq) && /* Don't resched if we changed runqueues */ @@ -1657,7 +1671,7 @@ static void switched_to_rt(struct rq *rq, struct task_struct *p) static void prio_changed_rt(struct rq *rq, struct task_struct *p, int oldprio) { - if (!p->se.on_rq) + if (!p->on_rq) return; if (rq->curr == p) { diff --git a/kernel/sched_stoptask.c b/kernel/sched_stoptask.c index 1ba2bd40fdac..6f437632afab 100644 --- a/kernel/sched_stoptask.c +++ b/kernel/sched_stoptask.c @@ -9,8 +9,7 @@ #ifdef CONFIG_SMP static int -select_task_rq_stop(struct rq *rq, struct task_struct *p, - int sd_flag, int flags) +select_task_rq_stop(struct task_struct *p, int sd_flag, int flags) { return task_cpu(p); /* stop tasks as never migrate */ } @@ -26,7 +25,7 @@ static struct task_struct *pick_next_task_stop(struct rq *rq) { struct task_struct *stop = rq->stop; - if (stop && stop->se.on_rq) + if (stop && stop->on_rq) return stop; return NULL; diff --git a/mm/memory.c b/mm/memory.c index 9da8cab1b1b0..b623a249918c 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1410,6 +1410,13 @@ no_page_table: return page; } +static inline int stack_guard_page(struct vm_area_struct *vma, unsigned long addr) +{ + return (vma->vm_flags & VM_GROWSDOWN) && + (vma->vm_start == addr) && + !vma_stack_continue(vma->vm_prev, addr); +} + /** * __get_user_pages() - pin user pages in memory * @tsk: task_struct of target task @@ -1488,7 +1495,6 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, vma = find_extend_vma(mm, start); if (!vma && in_gate_area(mm, start)) { unsigned long pg = start & PAGE_MASK; - struct vm_area_struct *gate_vma = get_gate_vma(mm); pgd_t *pgd; pud_t *pud; pmd_t *pmd; @@ -1513,10 +1519,11 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, pte_unmap(pte); return i ? : -EFAULT; } + vma = get_gate_vma(mm); if (pages) { struct page *page; - page = vm_normal_page(gate_vma, start, *pte); + page = vm_normal_page(vma, start, *pte); if (!page) { if (!(gup_flags & FOLL_DUMP) && is_zero_pfn(pte_pfn(*pte))) @@ -1530,12 +1537,7 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, get_page(page); } pte_unmap(pte); - if (vmas) - vmas[i] = gate_vma; - i++; - start += PAGE_SIZE; - nr_pages--; - continue; + goto next_page; } if (!vma || @@ -1549,6 +1551,13 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, continue; } + /* + * If we don't actually want the page itself, + * and it's the stack guard page, just skip it. + */ + if (!pages && stack_guard_page(vma, start)) + goto next_page; + do { struct page *page; unsigned int foll_flags = gup_flags; @@ -1631,6 +1640,7 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, flush_anon_page(vma, page, start); flush_dcache_page(page); } +next_page: if (vmas) vmas[i] = vma; i++; diff --git a/mm/mlock.c b/mm/mlock.c index 2689a08c79af..6b55e3efe0df 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -135,13 +135,6 @@ void munlock_vma_page(struct page *page) } } -static inline int stack_guard_page(struct vm_area_struct *vma, unsigned long addr) -{ - return (vma->vm_flags & VM_GROWSDOWN) && - (vma->vm_start == addr) && - !vma_stack_continue(vma->vm_prev, addr); -} - /** * __mlock_vma_pages_range() - mlock a range of pages in the vma. * @vma: target vma @@ -188,12 +181,6 @@ static long __mlock_vma_pages_range(struct vm_area_struct *vma, if (vma->vm_flags & VM_LOCKED) gup_flags |= FOLL_MLOCK; - /* We don't try to access the guard page of a stack vma */ - if (stack_guard_page(vma, start)) { - addr += PAGE_SIZE; - nr_pages--; - } - return __get_user_pages(current, mm, addr, nr_pages, gup_flags, NULL, NULL, nonblocking); } diff --git a/mm/mmap.c b/mm/mmap.c index 2ec8eb5a9cdd..8c05e5b43b69 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -1814,11 +1814,14 @@ static int expand_downwards(struct vm_area_struct *vma, size = vma->vm_end - address; grow = (vma->vm_start - address) >> PAGE_SHIFT; - error = acct_stack_growth(vma, size, grow); - if (!error) { - vma->vm_start = address; - vma->vm_pgoff -= grow; - perf_event_mmap(vma); + error = -ENOMEM; + if (grow <= vma->vm_pgoff) { + error = acct_stack_growth(vma, size, grow); + if (!error) { + vma->vm_start = address; + vma->vm_pgoff -= grow; + perf_event_mmap(vma); + } } } vma_unlock_anon_vma(vma); diff --git a/net/dsa/mv88e6131.c b/net/dsa/mv88e6131.c index d951f93644bf..3da418894efc 100644 --- a/net/dsa/mv88e6131.c +++ b/net/dsa/mv88e6131.c @@ -14,6 +14,13 @@ #include "dsa_priv.h" #include "mv88e6xxx.h" +/* + * Switch product IDs + */ +#define ID_6085 0x04a0 +#define ID_6095 0x0950 +#define ID_6131 0x1060 + static char *mv88e6131_probe(struct mii_bus *bus, int sw_addr) { int ret; @@ -21,9 +28,11 @@ static char *mv88e6131_probe(struct mii_bus *bus, int sw_addr) ret = __mv88e6xxx_reg_read(bus, sw_addr, REG_PORT(0), 0x03); if (ret >= 0) { ret &= 0xfff0; - if (ret == 0x0950) + if (ret == ID_6085) + return "Marvell 88E6085"; + if (ret == ID_6095) return "Marvell 88E6095/88E6095F"; - if (ret == 0x1060) + if (ret == ID_6131) return "Marvell 88E6131"; } @@ -164,6 +173,7 @@ static int mv88e6131_setup_global(struct dsa_switch *ds) static int mv88e6131_setup_port(struct dsa_switch *ds, int p) { + struct mv88e6xxx_priv_state *ps = (void *)(ds + 1); int addr = REG_PORT(p); u16 val; @@ -171,10 +181,13 @@ static int mv88e6131_setup_port(struct dsa_switch *ds, int p) * MAC Forcing register: don't force link, speed, duplex * or flow control state to any particular values on physical * ports, but force the CPU port and all DSA ports to 1000 Mb/s - * full duplex. + * (100 Mb/s on 6085) full duplex. */ if (dsa_is_cpu_port(ds, p) || ds->dsa_port_mask & (1 << p)) - REG_WRITE(addr, 0x01, 0x003e); + if (ps->id == ID_6085) + REG_WRITE(addr, 0x01, 0x003d); /* 100 Mb/s */ + else + REG_WRITE(addr, 0x01, 0x003e); /* 1000 Mb/s */ else REG_WRITE(addr, 0x01, 0x0003); @@ -286,6 +299,8 @@ static int mv88e6131_setup(struct dsa_switch *ds) mv88e6xxx_ppu_state_init(ds); mutex_init(&ps->stats_mutex); + ps->id = REG_READ(REG_PORT(0), 0x03) & 0xfff0; + ret = mv88e6131_switch_reset(ds); if (ret < 0) return ret; diff --git a/net/dsa/mv88e6xxx.h b/net/dsa/mv88e6xxx.h index eb0e0aaa9f1b..61156ca26a0d 100644 --- a/net/dsa/mv88e6xxx.h +++ b/net/dsa/mv88e6xxx.h @@ -39,6 +39,8 @@ struct mv88e6xxx_priv_state { * Hold this mutex over snapshot + dump sequences. */ struct mutex stats_mutex; + + int id; /* switch product id */ }; struct mv88e6xxx_hw_stat { diff --git a/net/ipv4/netfilter.c b/net/ipv4/netfilter.c index f3c0b549b8e1..4614babdc45f 100644 --- a/net/ipv4/netfilter.c +++ b/net/ipv4/netfilter.c @@ -221,9 +221,10 @@ static __sum16 nf_ip_checksum_partial(struct sk_buff *skb, unsigned int hook, return csum; } -static int nf_ip_route(struct dst_entry **dst, struct flowi *fl) +static int nf_ip_route(struct net *net, struct dst_entry **dst, + struct flowi *fl, bool strict __always_unused) { - struct rtable *rt = ip_route_output_key(&init_net, &fl->u.ip4); + struct rtable *rt = ip_route_output_key(net, &fl->u.ip4); if (IS_ERR(rt)) return PTR_ERR(rt); *dst = &rt->dst; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index ea107515c53e..c1acf69858fd 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1891,6 +1891,7 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr, #ifdef CONFIG_IP_ROUTE_CLASSID rth->dst.tclassid = itag; #endif + rth->rt_route_iif = dev->ifindex; rth->rt_iif = dev->ifindex; rth->dst.dev = init_net.loopback_dev; dev_hold(rth->dst.dev); @@ -2026,6 +2027,7 @@ static int __mkroute_input(struct sk_buff *skb, rth->rt_key_src = saddr; rth->rt_src = saddr; rth->rt_gateway = daddr; + rth->rt_route_iif = in_dev->dev->ifindex; rth->rt_iif = in_dev->dev->ifindex; rth->dst.dev = (out_dev)->dev; dev_hold(rth->dst.dev); @@ -2202,6 +2204,7 @@ local_input: #ifdef CONFIG_IP_ROUTE_CLASSID rth->dst.tclassid = itag; #endif + rth->rt_route_iif = dev->ifindex; rth->rt_iif = dev->ifindex; rth->dst.dev = net->loopback_dev; dev_hold(rth->dst.dev); @@ -2401,7 +2404,8 @@ static struct rtable *__mkroute_output(const struct fib_result *res, rth->rt_mark = oldflp4->flowi4_mark; rth->rt_dst = fl4->daddr; rth->rt_src = fl4->saddr; - rth->rt_iif = 0; + rth->rt_route_iif = 0; + rth->rt_iif = oldflp4->flowi4_oif ? : dev_out->ifindex; /* get references to the devices that are to be hold by the routing cache entry */ rth->dst.dev = dev_out; @@ -2716,6 +2720,7 @@ struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_or rt->rt_key_dst = ort->rt_key_dst; rt->rt_key_src = ort->rt_key_src; rt->rt_tos = ort->rt_tos; + rt->rt_route_iif = ort->rt_route_iif; rt->rt_iif = ort->rt_iif; rt->rt_oif = ort->rt_oif; rt->rt_mark = ort->rt_mark; @@ -2725,7 +2730,6 @@ struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_or rt->rt_type = ort->rt_type; rt->rt_dst = ort->rt_dst; rt->rt_src = ort->rt_src; - rt->rt_iif = ort->rt_iif; rt->rt_gateway = ort->rt_gateway; rt->rt_spec_dst = ort->rt_spec_dst; rt->peer = ort->peer; diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index 13e0e7f659ff..d20a05e970d8 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -74,6 +74,7 @@ static int xfrm4_fill_dst(struct xfrm_dst *xdst, struct net_device *dev, rt->rt_key_dst = fl4->daddr; rt->rt_key_src = fl4->saddr; rt->rt_tos = fl4->flowi4_tos; + rt->rt_route_iif = fl4->flowi4_iif; rt->rt_iif = fl4->flowi4_iif; rt->rt_oif = fl4->flowi4_oif; rt->rt_mark = fl4->flowi4_mark; diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c index 39aaca2b4fd2..28bc1f644b7b 100644 --- a/net/ipv6/netfilter.c +++ b/net/ipv6/netfilter.c @@ -90,9 +90,18 @@ static int nf_ip6_reroute(struct sk_buff *skb, return 0; } -static int nf_ip6_route(struct dst_entry **dst, struct flowi *fl) +static int nf_ip6_route(struct net *net, struct dst_entry **dst, + struct flowi *fl, bool strict) { - *dst = ip6_route_output(&init_net, NULL, &fl->u.ip6); + static const struct ipv6_pinfo fake_pinfo; + static const struct inet_sock fake_sk = { + /* makes ip6_route_output set RT6_LOOKUP_F_IFACE: */ + .sk.sk_bound_dev_if = 1, + .pinet6 = (struct ipv6_pinfo *) &fake_pinfo, + }; + const void *sk = strict ? &fake_sk : NULL; + + *dst = ip6_route_output(net, sk, &fl->u.ip6); return (*dst)->error; } diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 56fa12538d45..4f49e5dd41bb 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1622,6 +1622,7 @@ static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) opt_skb = skb_clone(skb, GFP_ATOMIC); if (sk->sk_state == TCP_ESTABLISHED) { /* Fast path */ + sock_rps_save_rxhash(sk, skb->rxhash); if (tcp_rcv_established(sk, skb, tcp_hdr(skb), skb->len)) goto reset; if (opt_skb) @@ -1649,7 +1650,8 @@ static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) __kfree_skb(opt_skb); return 0; } - } + } else + sock_rps_save_rxhash(sk, skb->rxhash); if (tcp_rcv_state_process(sk, skb, tcp_hdr(skb), skb->len)) goto reset; diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index d7037c006e13..15c37746845e 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -505,6 +505,9 @@ int udpv6_queue_rcv_skb(struct sock * sk, struct sk_buff *skb) int rc; int is_udplite = IS_UDPLITE(sk); + if (!ipv6_addr_any(&inet6_sk(sk)->daddr)) + sock_rps_save_rxhash(sk, skb->rxhash); + if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb)) goto drop; diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 9d192d665ff5..c5d4530d8284 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -2541,7 +2541,6 @@ static void ieee80211_rx_handlers(struct ieee80211_rx_data *rx) * same TID from the same station */ rx->skb = skb; - rx->flags = 0; CALL_RXH(ieee80211_rx_h_decrypt) CALL_RXH(ieee80211_rx_h_check_more_data) @@ -2612,6 +2611,7 @@ void ieee80211_release_reorder_timeout(struct sta_info *sta, int tid) .sdata = sta->sdata, .local = sta->local, .queue = tid, + .flags = 0, }; struct tid_ampdu_rx *tid_agg_rx; diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index c3f988aa1152..32bff6d86cb2 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -652,7 +652,6 @@ comment "Xtables matches" config NETFILTER_XT_MATCH_ADDRTYPE tristate '"addrtype" address type match support' depends on NETFILTER_ADVANCED - depends on (IPV6 || IPV6=n) ---help--- This option allows you to match what routing thinks of an address, eg. UNICAST, LOCAL, BROADCAST, ... diff --git a/net/netfilter/ipset/ip_set_bitmap_ip.c b/net/netfilter/ipset/ip_set_bitmap_ip.c index bca96990218d..a113ff066928 100644 --- a/net/netfilter/ipset/ip_set_bitmap_ip.c +++ b/net/netfilter/ipset/ip_set_bitmap_ip.c @@ -338,8 +338,7 @@ bitmap_ip_head(struct ip_set *set, struct sk_buff *skb) NLA_PUT_IPADDR4(skb, IPSET_ATTR_IP_TO, htonl(map->last_ip)); if (map->netmask != 32) NLA_PUT_U8(skb, IPSET_ATTR_NETMASK, map->netmask); - NLA_PUT_NET32(skb, IPSET_ATTR_REFERENCES, - htonl(atomic_read(&set->ref) - 1)); + NLA_PUT_NET32(skb, IPSET_ATTR_REFERENCES, htonl(set->ref - 1)); NLA_PUT_NET32(skb, IPSET_ATTR_MEMSIZE, htonl(sizeof(*map) + map->memsize)); if (with_timeout(map->timeout)) diff --git a/net/netfilter/ipset/ip_set_bitmap_ipmac.c b/net/netfilter/ipset/ip_set_bitmap_ipmac.c index 5e790172deff..00a33242e90c 100644 --- a/net/netfilter/ipset/ip_set_bitmap_ipmac.c +++ b/net/netfilter/ipset/ip_set_bitmap_ipmac.c @@ -434,8 +434,7 @@ bitmap_ipmac_head(struct ip_set *set, struct sk_buff *skb) goto nla_put_failure; NLA_PUT_IPADDR4(skb, IPSET_ATTR_IP, htonl(map->first_ip)); NLA_PUT_IPADDR4(skb, IPSET_ATTR_IP_TO, htonl(map->last_ip)); - NLA_PUT_NET32(skb, IPSET_ATTR_REFERENCES, - htonl(atomic_read(&set->ref) - 1)); + NLA_PUT_NET32(skb, IPSET_ATTR_REFERENCES, htonl(set->ref - 1)); NLA_PUT_NET32(skb, IPSET_ATTR_MEMSIZE, htonl(sizeof(*map) + (map->last_ip - map->first_ip + 1) * map->dsize)); diff --git a/net/netfilter/ipset/ip_set_bitmap_port.c b/net/netfilter/ipset/ip_set_bitmap_port.c index 165f09b1a9cb..6b38eb8f6ed8 100644 --- a/net/netfilter/ipset/ip_set_bitmap_port.c +++ b/net/netfilter/ipset/ip_set_bitmap_port.c @@ -320,8 +320,7 @@ bitmap_port_head(struct ip_set *set, struct sk_buff *skb) goto nla_put_failure; NLA_PUT_NET16(skb, IPSET_ATTR_PORT, htons(map->first_port)); NLA_PUT_NET16(skb, IPSET_ATTR_PORT_TO, htons(map->last_port)); - NLA_PUT_NET32(skb, IPSET_ATTR_REFERENCES, - htonl(atomic_read(&set->ref) - 1)); + NLA_PUT_NET32(skb, IPSET_ATTR_REFERENCES, htonl(set->ref - 1)); NLA_PUT_NET32(skb, IPSET_ATTR_MEMSIZE, htonl(sizeof(*map) + map->memsize)); if (with_timeout(map->timeout)) diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index 253326e8d990..9152e69a162d 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -26,6 +26,7 @@ static LIST_HEAD(ip_set_type_list); /* all registered set types */ static DEFINE_MUTEX(ip_set_type_mutex); /* protects ip_set_type_list */ +static DEFINE_RWLOCK(ip_set_ref_lock); /* protects the set refs */ static struct ip_set **ip_set_list; /* all individual sets */ static ip_set_id_t ip_set_max = CONFIG_IP_SET_MAX; /* max number of sets */ @@ -301,13 +302,18 @@ EXPORT_SYMBOL_GPL(ip_set_get_ipaddr6); static inline void __ip_set_get(ip_set_id_t index) { - atomic_inc(&ip_set_list[index]->ref); + write_lock_bh(&ip_set_ref_lock); + ip_set_list[index]->ref++; + write_unlock_bh(&ip_set_ref_lock); } static inline void __ip_set_put(ip_set_id_t index) { - atomic_dec(&ip_set_list[index]->ref); + write_lock_bh(&ip_set_ref_lock); + BUG_ON(ip_set_list[index]->ref == 0); + ip_set_list[index]->ref--; + write_unlock_bh(&ip_set_ref_lock); } /* @@ -324,7 +330,7 @@ ip_set_test(ip_set_id_t index, const struct sk_buff *skb, struct ip_set *set = ip_set_list[index]; int ret = 0; - BUG_ON(set == NULL || atomic_read(&set->ref) == 0); + BUG_ON(set == NULL); pr_debug("set %s, index %u\n", set->name, index); if (dim < set->type->dimension || @@ -356,7 +362,7 @@ ip_set_add(ip_set_id_t index, const struct sk_buff *skb, struct ip_set *set = ip_set_list[index]; int ret; - BUG_ON(set == NULL || atomic_read(&set->ref) == 0); + BUG_ON(set == NULL); pr_debug("set %s, index %u\n", set->name, index); if (dim < set->type->dimension || @@ -378,7 +384,7 @@ ip_set_del(ip_set_id_t index, const struct sk_buff *skb, struct ip_set *set = ip_set_list[index]; int ret = 0; - BUG_ON(set == NULL || atomic_read(&set->ref) == 0); + BUG_ON(set == NULL); pr_debug("set %s, index %u\n", set->name, index); if (dim < set->type->dimension || @@ -397,7 +403,6 @@ EXPORT_SYMBOL_GPL(ip_set_del); * Find set by name, reference it once. The reference makes sure the * thing pointed to, does not go away under our feet. * - * The nfnl mutex must already be activated. */ ip_set_id_t ip_set_get_byname(const char *name, struct ip_set **set) @@ -423,15 +428,12 @@ EXPORT_SYMBOL_GPL(ip_set_get_byname); * reference count by 1. The caller shall not assume the index * to be valid, after calling this function. * - * The nfnl mutex must already be activated. */ void ip_set_put_byindex(ip_set_id_t index) { - if (ip_set_list[index] != NULL) { - BUG_ON(atomic_read(&ip_set_list[index]->ref) == 0); + if (ip_set_list[index] != NULL) __ip_set_put(index); - } } EXPORT_SYMBOL_GPL(ip_set_put_byindex); @@ -441,7 +443,6 @@ EXPORT_SYMBOL_GPL(ip_set_put_byindex); * can't be destroyed. The set cannot be renamed due to * the referencing either. * - * The nfnl mutex must already be activated. */ const char * ip_set_name_byindex(ip_set_id_t index) @@ -449,7 +450,7 @@ ip_set_name_byindex(ip_set_id_t index) const struct ip_set *set = ip_set_list[index]; BUG_ON(set == NULL); - BUG_ON(atomic_read(&set->ref) == 0); + BUG_ON(set->ref == 0); /* Referenced, so it's safe */ return set->name; @@ -515,10 +516,7 @@ void ip_set_nfnl_put(ip_set_id_t index) { nfnl_lock(); - if (ip_set_list[index] != NULL) { - BUG_ON(atomic_read(&ip_set_list[index]->ref) == 0); - __ip_set_put(index); - } + ip_set_put_byindex(index); nfnl_unlock(); } EXPORT_SYMBOL_GPL(ip_set_nfnl_put); @@ -526,7 +524,7 @@ EXPORT_SYMBOL_GPL(ip_set_nfnl_put); /* * Communication protocol with userspace over netlink. * - * We already locked by nfnl_lock. + * The commands are serialized by the nfnl mutex. */ static inline bool @@ -657,7 +655,6 @@ ip_set_create(struct sock *ctnl, struct sk_buff *skb, return -ENOMEM; rwlock_init(&set->lock); strlcpy(set->name, name, IPSET_MAXNAMELEN); - atomic_set(&set->ref, 0); set->family = family; /* @@ -690,8 +687,8 @@ ip_set_create(struct sock *ctnl, struct sk_buff *skb, /* * Here, we have a valid, constructed set and we are protected - * by nfnl_lock. Find the first free index in ip_set_list and - * check clashing. + * by the nfnl mutex. Find the first free index in ip_set_list + * and check clashing. */ if ((ret = find_free_id(set->name, &index, &clash)) != 0) { /* If this is the same set and requested, ignore error */ @@ -751,31 +748,51 @@ ip_set_destroy(struct sock *ctnl, struct sk_buff *skb, const struct nlattr * const attr[]) { ip_set_id_t i; + int ret = 0; if (unlikely(protocol_failed(attr))) return -IPSET_ERR_PROTOCOL; - /* References are protected by the nfnl mutex */ + /* Commands are serialized and references are + * protected by the ip_set_ref_lock. + * External systems (i.e. xt_set) must call + * ip_set_put|get_nfnl_* functions, that way we + * can safely check references here. + * + * list:set timer can only decrement the reference + * counter, so if it's already zero, we can proceed + * without holding the lock. + */ + read_lock_bh(&ip_set_ref_lock); if (!attr[IPSET_ATTR_SETNAME]) { for (i = 0; i < ip_set_max; i++) { - if (ip_set_list[i] != NULL && - (atomic_read(&ip_set_list[i]->ref))) - return -IPSET_ERR_BUSY; + if (ip_set_list[i] != NULL && ip_set_list[i]->ref) { + ret = IPSET_ERR_BUSY; + goto out; + } } + read_unlock_bh(&ip_set_ref_lock); for (i = 0; i < ip_set_max; i++) { if (ip_set_list[i] != NULL) ip_set_destroy_set(i); } } else { i = find_set_id(nla_data(attr[IPSET_ATTR_SETNAME])); - if (i == IPSET_INVALID_ID) - return -ENOENT; - else if (atomic_read(&ip_set_list[i]->ref)) - return -IPSET_ERR_BUSY; + if (i == IPSET_INVALID_ID) { + ret = -ENOENT; + goto out; + } else if (ip_set_list[i]->ref) { + ret = -IPSET_ERR_BUSY; + goto out; + } + read_unlock_bh(&ip_set_ref_lock); ip_set_destroy_set(i); } return 0; +out: + read_unlock_bh(&ip_set_ref_lock); + return ret; } /* Flush sets */ @@ -834,6 +851,7 @@ ip_set_rename(struct sock *ctnl, struct sk_buff *skb, struct ip_set *set; const char *name2; ip_set_id_t i; + int ret = 0; if (unlikely(protocol_failed(attr) || attr[IPSET_ATTR_SETNAME] == NULL || @@ -843,25 +861,33 @@ ip_set_rename(struct sock *ctnl, struct sk_buff *skb, set = find_set(nla_data(attr[IPSET_ATTR_SETNAME])); if (set == NULL) return -ENOENT; - if (atomic_read(&set->ref) != 0) - return -IPSET_ERR_REFERENCED; + + read_lock_bh(&ip_set_ref_lock); + if (set->ref != 0) { + ret = -IPSET_ERR_REFERENCED; + goto out; + } name2 = nla_data(attr[IPSET_ATTR_SETNAME2]); for (i = 0; i < ip_set_max; i++) { if (ip_set_list[i] != NULL && - STREQ(ip_set_list[i]->name, name2)) - return -IPSET_ERR_EXIST_SETNAME2; + STREQ(ip_set_list[i]->name, name2)) { + ret = -IPSET_ERR_EXIST_SETNAME2; + goto out; + } } strncpy(set->name, name2, IPSET_MAXNAMELEN); - return 0; +out: + read_unlock_bh(&ip_set_ref_lock); + return ret; } /* Swap two sets so that name/index points to the other. * References and set names are also swapped. * - * We are protected by the nfnl mutex and references are - * manipulated only by holding the mutex. The kernel interfaces + * The commands are serialized by the nfnl mutex and references are + * protected by the ip_set_ref_lock. The kernel interfaces * do not hold the mutex but the pointer settings are atomic * so the ip_set_list always contains valid pointers to the sets. */ @@ -874,7 +900,6 @@ ip_set_swap(struct sock *ctnl, struct sk_buff *skb, struct ip_set *from, *to; ip_set_id_t from_id, to_id; char from_name[IPSET_MAXNAMELEN]; - u32 from_ref; if (unlikely(protocol_failed(attr) || attr[IPSET_ATTR_SETNAME] == NULL || @@ -899,17 +924,15 @@ ip_set_swap(struct sock *ctnl, struct sk_buff *skb, from->type->family == to->type->family)) return -IPSET_ERR_TYPE_MISMATCH; - /* No magic here: ref munging protected by the nfnl_lock */ strncpy(from_name, from->name, IPSET_MAXNAMELEN); - from_ref = atomic_read(&from->ref); - strncpy(from->name, to->name, IPSET_MAXNAMELEN); - atomic_set(&from->ref, atomic_read(&to->ref)); strncpy(to->name, from_name, IPSET_MAXNAMELEN); - atomic_set(&to->ref, from_ref); + write_lock_bh(&ip_set_ref_lock); + swap(from->ref, to->ref); ip_set_list[from_id] = to; ip_set_list[to_id] = from; + write_unlock_bh(&ip_set_ref_lock); return 0; } @@ -926,7 +949,7 @@ ip_set_dump_done(struct netlink_callback *cb) { if (cb->args[2]) { pr_debug("release set %s\n", ip_set_list[cb->args[1]]->name); - __ip_set_put((ip_set_id_t) cb->args[1]); + ip_set_put_byindex((ip_set_id_t) cb->args[1]); } return 0; } @@ -1068,7 +1091,7 @@ release_refcount: /* If there was an error or set is done, release set */ if (ret || !cb->args[2]) { pr_debug("release set %s\n", ip_set_list[index]->name); - __ip_set_put(index); + ip_set_put_byindex(index); } /* If we dump all sets, continue with dumping last ones */ diff --git a/net/netfilter/ipset/ip_set_list_set.c b/net/netfilter/ipset/ip_set_list_set.c index a47c32982f06..e9159e99fc4b 100644 --- a/net/netfilter/ipset/ip_set_list_set.c +++ b/net/netfilter/ipset/ip_set_list_set.c @@ -43,14 +43,19 @@ struct list_set { static inline struct set_elem * list_set_elem(const struct list_set *map, u32 id) { - return (struct set_elem *)((char *)map->members + id * map->dsize); + return (struct set_elem *)((void *)map->members + id * map->dsize); +} + +static inline struct set_telem * +list_set_telem(const struct list_set *map, u32 id) +{ + return (struct set_telem *)((void *)map->members + id * map->dsize); } static inline bool list_set_timeout(const struct list_set *map, u32 id) { - const struct set_telem *elem = - (const struct set_telem *) list_set_elem(map, id); + const struct set_telem *elem = list_set_telem(map, id); return ip_set_timeout_test(elem->timeout); } @@ -58,19 +63,11 @@ list_set_timeout(const struct list_set *map, u32 id) static inline bool list_set_expired(const struct list_set *map, u32 id) { - const struct set_telem *elem = - (const struct set_telem *) list_set_elem(map, id); + const struct set_telem *elem = list_set_telem(map, id); return ip_set_timeout_expired(elem->timeout); } -static inline int -list_set_exist(const struct set_telem *elem) -{ - return elem->id != IPSET_INVALID_ID && - !ip_set_timeout_expired(elem->timeout); -} - /* Set list without and with timeout */ static int @@ -146,11 +143,11 @@ list_elem_tadd(struct list_set *map, u32 i, ip_set_id_t id, struct set_telem *e; for (; i < map->size; i++) { - e = (struct set_telem *)list_set_elem(map, i); + e = list_set_telem(map, i); swap(e->id, id); + swap(e->timeout, timeout); if (e->id == IPSET_INVALID_ID) break; - swap(e->timeout, timeout); } } @@ -164,7 +161,7 @@ list_set_add(struct list_set *map, u32 i, ip_set_id_t id, /* Last element replaced: e.g. add new,before,last */ ip_set_put_byindex(e->id); if (with_timeout(map->timeout)) - list_elem_tadd(map, i, id, timeout); + list_elem_tadd(map, i, id, ip_set_timeout_set(timeout)); else list_elem_add(map, i, id); @@ -172,11 +169,11 @@ list_set_add(struct list_set *map, u32 i, ip_set_id_t id, } static int -list_set_del(struct list_set *map, ip_set_id_t id, u32 i) +list_set_del(struct list_set *map, u32 i) { struct set_elem *a = list_set_elem(map, i), *b; - ip_set_put_byindex(id); + ip_set_put_byindex(a->id); for (; i < map->size - 1; i++) { b = list_set_elem(map, i + 1); @@ -308,11 +305,11 @@ list_set_uadt(struct ip_set *set, struct nlattr *tb[], (before == 0 || (before > 0 && next_id_eq(map, i, refid)))) - ret = list_set_del(map, id, i); + ret = list_set_del(map, i); else if (before < 0 && elem->id == refid && next_id_eq(map, i, id)) - ret = list_set_del(map, id, i + 1); + ret = list_set_del(map, i + 1); } break; default: @@ -369,8 +366,7 @@ list_set_head(struct ip_set *set, struct sk_buff *skb) NLA_PUT_NET32(skb, IPSET_ATTR_SIZE, htonl(map->size)); if (with_timeout(map->timeout)) NLA_PUT_NET32(skb, IPSET_ATTR_TIMEOUT, htonl(map->timeout)); - NLA_PUT_NET32(skb, IPSET_ATTR_REFERENCES, - htonl(atomic_read(&set->ref) - 1)); + NLA_PUT_NET32(skb, IPSET_ATTR_REFERENCES, htonl(set->ref - 1)); NLA_PUT_NET32(skb, IPSET_ATTR_MEMSIZE, htonl(sizeof(*map) + map->size * map->dsize)); ipset_nest_end(skb, nested); @@ -461,16 +457,13 @@ list_set_gc(unsigned long ul_set) struct set_telem *e; u32 i; - /* We run parallel with other readers (test element) - * but adding/deleting new entries is locked out */ - read_lock_bh(&set->lock); - for (i = map->size - 1; i >= 0; i--) { - e = (struct set_telem *) list_set_elem(map, i); - if (e->id != IPSET_INVALID_ID && - list_set_expired(map, i)) - list_set_del(map, e->id, i); + write_lock_bh(&set->lock); + for (i = 0; i < map->size; i++) { + e = list_set_telem(map, i); + if (e->id != IPSET_INVALID_ID && list_set_expired(map, i)) + list_set_del(map, i); } - read_unlock_bh(&set->lock); + write_unlock_bh(&set->lock); map->gc.expires = jiffies + IPSET_GC_PERIOD(map->timeout) * HZ; add_timer(&map->gc); diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 33733c8872e7..ae47090bf45f 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -3120,7 +3120,7 @@ nla_put_failure: static int ip_vs_genl_dump_daemons(struct sk_buff *skb, struct netlink_callback *cb) { - struct net *net = skb_net(skb); + struct net *net = skb_sknet(skb); struct netns_ipvs *ipvs = net_ipvs(net); mutex_lock(&__ip_vs_mutex); diff --git a/net/netfilter/nf_conntrack_h323_asn1.c b/net/netfilter/nf_conntrack_h323_asn1.c index 867882313e49..bcd5ed6b7130 100644 --- a/net/netfilter/nf_conntrack_h323_asn1.c +++ b/net/netfilter/nf_conntrack_h323_asn1.c @@ -631,7 +631,7 @@ static int decode_seqof(bitstr_t *bs, const struct field_t *f, CHECK_BOUND(bs, 2); count = *bs->cur++; count <<= 8; - count = *bs->cur++; + count += *bs->cur++; break; case SEMI: BYTE_ALIGN(bs); diff --git a/net/netfilter/nf_conntrack_h323_main.c b/net/netfilter/nf_conntrack_h323_main.c index 533a183e6661..18b2ce5c8ced 100644 --- a/net/netfilter/nf_conntrack_h323_main.c +++ b/net/netfilter/nf_conntrack_h323_main.c @@ -731,10 +731,10 @@ static int callforward_do_filter(const union nf_inet_addr *src, memset(&fl2, 0, sizeof(fl2)); fl2.daddr = dst->ip; - if (!afinfo->route((struct dst_entry **)&rt1, - flowi4_to_flowi(&fl1))) { - if (!afinfo->route((struct dst_entry **)&rt2, - flowi4_to_flowi(&fl2))) { + if (!afinfo->route(&init_net, (struct dst_entry **)&rt1, + flowi4_to_flowi(&fl1), false)) { + if (!afinfo->route(&init_net, (struct dst_entry **)&rt2, + flowi4_to_flowi(&fl2), false)) { if (rt1->rt_gateway == rt2->rt_gateway && rt1->dst.dev == rt2->dst.dev) ret = 1; @@ -755,10 +755,10 @@ static int callforward_do_filter(const union nf_inet_addr *src, memset(&fl2, 0, sizeof(fl2)); ipv6_addr_copy(&fl2.daddr, &dst->in6); - if (!afinfo->route((struct dst_entry **)&rt1, - flowi6_to_flowi(&fl1))) { - if (!afinfo->route((struct dst_entry **)&rt2, - flowi6_to_flowi(&fl2))) { + if (!afinfo->route(&init_net, (struct dst_entry **)&rt1, + flowi6_to_flowi(&fl1), false)) { + if (!afinfo->route(&init_net, (struct dst_entry **)&rt2, + flowi6_to_flowi(&fl2), false)) { if (!memcmp(&rt1->rt6i_gateway, &rt2->rt6i_gateway, sizeof(rt1->rt6i_gateway)) && rt1->dst.dev == rt2->dst.dev) diff --git a/net/netfilter/xt_TCPMSS.c b/net/netfilter/xt_TCPMSS.c index 6e6b46cb1db9..9e63b43faeed 100644 --- a/net/netfilter/xt_TCPMSS.c +++ b/net/netfilter/xt_TCPMSS.c @@ -166,7 +166,7 @@ static u_int32_t tcpmss_reverse_mtu(const struct sk_buff *skb, rcu_read_lock(); ai = nf_get_afinfo(family); if (ai != NULL) - ai->route((struct dst_entry **)&rt, &fl); + ai->route(&init_net, (struct dst_entry **)&rt, &fl, false); rcu_read_unlock(); if (rt != NULL) { diff --git a/net/netfilter/xt_addrtype.c b/net/netfilter/xt_addrtype.c index 2220b85e9519..b77d383cec78 100644 --- a/net/netfilter/xt_addrtype.c +++ b/net/netfilter/xt_addrtype.c @@ -32,11 +32,32 @@ MODULE_ALIAS("ipt_addrtype"); MODULE_ALIAS("ip6t_addrtype"); #if defined(CONFIG_IP6_NF_IPTABLES) || defined(CONFIG_IP6_NF_IPTABLES_MODULE) -static u32 xt_addrtype_rt6_to_type(const struct rt6_info *rt) +static u32 match_lookup_rt6(struct net *net, const struct net_device *dev, + const struct in6_addr *addr) { + const struct nf_afinfo *afinfo; + struct flowi6 flow; + struct rt6_info *rt; u32 ret; + int route_err; - if (!rt) + memset(&flow, 0, sizeof(flow)); + ipv6_addr_copy(&flow.daddr, addr); + if (dev) + flow.flowi6_oif = dev->ifindex; + + rcu_read_lock(); + + afinfo = nf_get_afinfo(NFPROTO_IPV6); + if (afinfo != NULL) + route_err = afinfo->route(net, (struct dst_entry **)&rt, + flowi6_to_flowi(&flow), !!dev); + else + route_err = 1; + + rcu_read_unlock(); + + if (route_err) return XT_ADDRTYPE_UNREACHABLE; if (rt->rt6i_flags & RTF_REJECT) @@ -48,6 +69,9 @@ static u32 xt_addrtype_rt6_to_type(const struct rt6_info *rt) ret |= XT_ADDRTYPE_LOCAL; if (rt->rt6i_flags & RTF_ANYCAST) ret |= XT_ADDRTYPE_ANYCAST; + + + dst_release(&rt->dst); return ret; } @@ -65,18 +89,8 @@ static bool match_type6(struct net *net, const struct net_device *dev, return false; if ((XT_ADDRTYPE_LOCAL | XT_ADDRTYPE_ANYCAST | - XT_ADDRTYPE_UNREACHABLE) & mask) { - struct rt6_info *rt; - u32 type; - int ifindex = dev ? dev->ifindex : 0; - - rt = rt6_lookup(net, addr, NULL, ifindex, !!dev); - - type = xt_addrtype_rt6_to_type(rt); - - dst_release(&rt->dst); - return !!(mask & type); - } + XT_ADDRTYPE_UNREACHABLE) & mask) + return !!(mask & match_lookup_rt6(net, dev, addr)); return true; } diff --git a/net/netfilter/xt_conntrack.c b/net/netfilter/xt_conntrack.c index 2c0086a4751e..481a86fdc409 100644 --- a/net/netfilter/xt_conntrack.c +++ b/net/netfilter/xt_conntrack.c @@ -195,7 +195,7 @@ conntrack_mt(const struct sk_buff *skb, struct xt_action_param *par, return info->match_flags & XT_CONNTRACK_STATE; if ((info->match_flags & XT_CONNTRACK_DIRECTION) && (CTINFO2DIR(ctinfo) == IP_CT_DIR_ORIGINAL) ^ - !!(info->invert_flags & XT_CONNTRACK_DIRECTION)) + !(info->invert_flags & XT_CONNTRACK_DIRECTION)) return false; if (info->match_flags & XT_CONNTRACK_ORIGSRC) |