F: drivers/block/brd.c
RANDOM NUMBER DRIVER
- M: Matt Mackall <mpm@selenic.com>
+ M: Theodore Ts'o" <tytso@mit.edu>
S: Maintained
F: drivers/char/random.c
F: Documentation/filesystems/ufs.txt
F: fs/ufs/
+UHID USERSPACE HID IO DRIVER:
+M: David Herrmann <dh.herrmann@googlemail.com>
+L: linux-input@vger.kernel.org
+S: Maintained
+F: drivers/hid/uhid.c
+F: include/linux/uhid.h
+
ULTRA-WIDEBAND (UWB) SUBSYSTEM:
L: linux-usb@vger.kernel.org
S: Orphan
This workaround defines cpu_relax() as smp_mb(), preventing correctly
written polling loops from denying visibility of updates to memory.
+ config ARM_ERRATA_764369
+ bool "ARM errata: Data cache line maintenance operation by MVA may not succeed"
+ depends on CPU_V7 && SMP
+ help
+ This option enables the workaround for erratum 764369
+ affecting Cortex-A9 MPCore with two or more processors (all
+ current revisions). Under certain timing circumstances, a data
+ cache line maintenance operation by MVA targeting an Inner
+ Shareable memory region may fail to proceed up to either the
+ Point of Coherency or to the Point of Unification of the
+ system. This workaround adds a DSB instruction before the
+ relevant cache maintenance functions and sets a specific bit
+ in the diagnostic control register of the SCU.
+
+ config PL310_ERRATA_769419
+ bool "PL310 errata: no automatic Store Buffer drain"
+ depends on CACHE_L2X0
+ help
+ On revisions of the PL310 prior to r3p2, the Store Buffer does
+ not automatically drain. This can cause normal, non-cacheable
+ writes to be retained when the memory system is idle, leading
+ to suboptimal I/O performance for drivers using coherent DMA.
+ This option adds a write barrier to the cpu_idle loop so that,
+ on systems with an outer cache, the store buffer is drained
+ explicitly.
+
+ config ARM_ERRATA_775420
+ bool "ARM errata: A data cache maintenance operation which aborts, might lead to deadlock"
+ depends on CPU_V7
+ help
+ This option enables the workaround for the 775420 Cortex-A9 (r2p2,
+ r2p6,r2p8,r2p10,r3p0) erratum. In case a date cache maintenance
+ operation aborts with MMU exception, it might cause the processor
+ to deadlock. This workaround puts DSB before executing ISB if
+ an abort may occur on cache maintenance.
+
endmenu
source "arch/arm/common/Kconfig"
source "drivers/pcmcia/Kconfig"
- config ARM_ERRATA_764369
- bool "ARM errata: Data cache line maintenance operation by MVA may not succeed"
- depends on CPU_V7 && SMP
- help
- This option enables the workaround for erratum 764369
- affecting Cortex-A9 MPCore with two or more processors (all
- current revisions). Under certain timing circumstances, a data
- cache line maintenance operation by MVA targeting an Inner
- Shareable memory region may fail to proceed up to either the
- Point of Coherency or to the Point of Unification of the
- system. This workaround adds a DSB instruction before the
- relevant cache maintenance functions and sets a specific bit
- in the diagnostic control register of the SCU.
-
- config PL310_ERRATA_769419
- bool "PL310 errata: no automatic Store Buffer drain"
- depends on CACHE_L2X0
- help
- On revisions of the PL310 prior to r3p2, the Store Buffer does
- not automatically drain. This can cause normal, non-cacheable
- writes to be retained when the memory system is idle, leading
- to suboptimal I/O performance for drivers using coherent DMA.
- This option adds a write barrier to the cpu_idle loop so that,
- on systems with an outer cache, the store buffer is drained
- explicitly.
-
endmenu
menu "Kernel Features"
This was deprecated in 2001 and announced to live on for 5 years.
Some old boot loaders still use this way.
+config ARM_FLUSH_CONSOLE_ON_RESTART
+ bool "Force flush the console on restart"
+ help
+ If the console is locked while the system is rebooted, the messages
+ in the temporary logbuffer would not have propogated to all the
+ console drivers. This option forces the console lock to be
+ released if it failed to be acquired, which will cause all the
+ pending messages to be flushed.
+
endmenu
menu "Boot options"
config CPU_FREQ_IMX
tristate "CPUfreq driver for i.MX CPUs"
depends on ARCH_MXC && CPU_FREQ
+ select CPU_FREQ_TABLE
help
This enables the CPUfreq driver for i.MX CPUs.
mcrne p15, 0, r0, c8, c7, 0 @ flush I,D TLBs
#endif
mrc p15, 0, r0, c1, c0, 0 @ read control reg
+ bic r0, r0, #1 << 28 @ clear SCTLR.TRE
orr r0, r0, #0x5000 @ I-cache enable, RR cache replacement
orr r0, r0, #0x003c @ write buffer
#ifdef CONFIG_MMU
@ b __arm6_mmu_cache_off
@ b __armv3_mmu_cache_flush
+#if !defined(CONFIG_CPU_V7)
+ /* This collides with some V7 IDs, preventing correct detection */
.word 0x00000000 @ old ARM ID
.word 0x0000f000
mov pc, lr
THUMB( nop )
mov pc, lr
THUMB( nop )
+#endif
.word 0x41007000 @ ARM7/710
.word 0xfff8fe00
IPI_CALL_FUNC,
IPI_CALL_FUNC_SINGLE,
IPI_CPU_STOP,
+ IPI_CPU_BACKTRACE,
};
int __cpuinit __cpu_up(unsigned int cpu)
asmlinkage void __cpuinit secondary_start_kernel(void)
{
struct mm_struct *mm = &init_mm;
- unsigned int cpu = smp_processor_id();
+ unsigned int cpu;
- printk("CPU%u: Booted secondary processor\n", cpu);
+ /*
+ * The identity mapping is uncached (strongly ordered), so
+ * switch away from it before attempting any exclusive accesses.
+ */
+ cpu_switch_mm(mm->pgd, mm);
+ enter_lazy_tlb(mm, current);
+ local_flush_tlb_all();
/*
* All kernel threads share the same mm context; grab a
* reference and switch to it.
*/
+ cpu = smp_processor_id();
atomic_inc(&mm->mm_count);
current->active_mm = mm;
cpumask_set_cpu(cpu, mm_cpumask(mm));
- cpu_switch_mm(mm->pgd, mm);
- enter_lazy_tlb(mm, current);
- local_flush_tlb_all();
+
+ printk("CPU%u: Booted secondary processor\n", cpu);
cpu_init();
preempt_disable();
*/
platform_secondary_init(cpu);
- /*
- * Enable local interrupts.
- */
notify_cpu_starting(cpu);
- local_irq_enable();
- local_fiq_enable();
-
- /*
- * Setup the percpu timer for this CPU.
- */
- percpu_timer_setup();
calibrate_delay();
* before we continue.
*/
set_cpu_online(cpu, true);
+
+ /*
+ * Setup the percpu timer for this CPU.
+ */
+ percpu_timer_setup();
+
while (!cpu_active(cpu))
cpu_relax();
+ /*
+ * cpu_active bit is set, so it's safe to enable interrupts
+ * now.
+ */
+ local_irq_enable();
+ local_fiq_enable();
+
/*
* OK, it's off to the idle thread for us
*/
S(IPI_CALL_FUNC, "Function call interrupts"),
S(IPI_CALL_FUNC_SINGLE, "Single function call interrupts"),
S(IPI_CPU_STOP, "CPU stop interrupts"),
+ S(IPI_CPU_BACKTRACE, "CPU backtrace"),
};
void show_ipi_list(struct seq_file *p, int prec)
static void ipi_timer(void)
{
struct clock_event_device *evt = &__get_cpu_var(percpu_clockevent);
- irq_enter();
evt->event_handler(evt);
- irq_exit();
}
#ifdef CONFIG_LOCAL_TIMERS
if (local_timer_ack()) {
__inc_irq_stat(cpu, local_timer_irqs);
+ irq_enter();
ipi_timer();
+ irq_exit();
}
set_irq_regs(old_regs);
cpu_relax();
}
+static cpumask_t backtrace_mask;
+static DEFINE_RAW_SPINLOCK(backtrace_lock);
+
+/* "in progress" flag of arch_trigger_all_cpu_backtrace */
+static unsigned long backtrace_flag;
+
+void smp_send_all_cpu_backtrace(void)
+{
+ unsigned int this_cpu = smp_processor_id();
+ int i;
+
+ if (test_and_set_bit(0, &backtrace_flag))
+ /*
+ * If there is already a trigger_all_cpu_backtrace() in progress
+ * (backtrace_flag == 1), don't output double cpu dump infos.
+ */
+ return;
+
+ cpumask_copy(&backtrace_mask, cpu_online_mask);
+ cpu_clear(this_cpu, backtrace_mask);
+
+ pr_info("Backtrace for cpu %d (current):\n", this_cpu);
+ dump_stack();
+
+ pr_info("\nsending IPI to all other CPUs:\n");
+ smp_cross_call(&backtrace_mask, IPI_CPU_BACKTRACE);
+
+ /* Wait for up to 10 seconds for all other CPUs to do the backtrace */
+ for (i = 0; i < 10 * 1000; i++) {
+ if (cpumask_empty(&backtrace_mask))
+ break;
+ mdelay(1);
+ }
+
+ clear_bit(0, &backtrace_flag);
+ smp_mb__after_clear_bit();
+}
+
+/*
+ * ipi_cpu_backtrace - handle IPI from smp_send_all_cpu_backtrace()
+ */
+static void ipi_cpu_backtrace(unsigned int cpu, struct pt_regs *regs)
+{
+ if (cpu_isset(cpu, backtrace_mask)) {
+ raw_spin_lock(&backtrace_lock);
+ pr_warning("IPI backtrace for cpu %d\n", cpu);
+ show_regs(regs);
+ raw_spin_unlock(&backtrace_lock);
+ cpu_clear(cpu, backtrace_mask);
+ }
+}
+
/*
* Main handler for inter-processor interrupts
*/
switch (ipinr) {
case IPI_TIMER:
+ irq_enter();
ipi_timer();
+ irq_exit();
break;
case IPI_RESCHEDULE:
break;
case IPI_CALL_FUNC:
+ irq_enter();
generic_smp_call_function_interrupt();
+ irq_exit();
break;
case IPI_CALL_FUNC_SINGLE:
+ irq_enter();
generic_smp_call_function_single_interrupt();
+ irq_exit();
break;
case IPI_CPU_STOP:
+ irq_enter();
ipi_cpu_stop(cpu);
+ irq_exit();
break;
+ case IPI_CPU_BACKTRACE:
+ ipi_cpu_backtrace(cpu, regs);
+ break;
+
default:
printk(KERN_CRIT "CPU%u: Unknown IPI message 0x%x\n",
cpu, ipinr);
struct hd_struct *part;
char name_buf[BDEVNAME_SIZE];
char devt_buf[BDEVT_SIZE];
- u8 uuid[PARTITION_META_INFO_UUIDLTH * 2 + 1];
+ char uuid_buf[PARTITION_META_INFO_UUIDLTH * 2 + 5];
/*
* Don't show empty devices or things that have been
while ((part = disk_part_iter_next(&piter))) {
bool is_part0 = part == &disk->part0;
- uuid[0] = 0;
+ uuid_buf[0] = '\0';
if (part->info)
- part_unpack_uuid(part->info->uuid, uuid);
+ snprintf(uuid_buf, sizeof(uuid_buf), "%pU",
+ part->info->uuid);
printk("%s%s %10llu %s %s", is_part0 ? "" : " ",
bdevt_str(part_devt(part), devt_buf),
(unsigned long long)part->nr_sects >> 1,
- disk_name(disk, part->partno, name_buf), uuid);
+ disk_name(disk, part->partno, name_buf),
+ uuid_buf);
if (is_part0) {
if (disk->driverfs_dev != NULL &&
disk->driverfs_dev->driver != NULL)
blk_put_queue(disk->queue);
kfree(disk);
}
+
+static int disk_uevent(struct device *dev, struct kobj_uevent_env *env)
+{
+ struct gendisk *disk = dev_to_disk(dev);
+ struct disk_part_iter piter;
+ struct hd_struct *part;
+ int cnt = 0;
+
+ disk_part_iter_init(&piter, disk, 0);
+ while((part = disk_part_iter_next(&piter)))
+ cnt++;
+ disk_part_iter_exit(&piter);
+ add_uevent_var(env, "NPARTS=%u", cnt);
+ return 0;
+}
+
struct class block_class = {
.name = "block",
};
.groups = disk_attr_groups,
.release = disk_release,
.devnode = block_devnode,
+ .uevent = disk_uevent,
};
#ifdef CONFIG_PROC_FS
goto repeat;
}
- dev->power.deferred_resume = false;
if (dev->power.no_callbacks)
goto no_callback; /* Assume success. */
wake_up_all(&dev->power.wait_queue);
if (dev->power.deferred_resume) {
+ dev->power.deferred_resume = false;
rpm_resume(dev, 0);
retval = -EAGAIN;
goto out;
|| dev->parent->power.runtime_status == RPM_ACTIVE) {
atomic_inc(&dev->parent->power.child_count);
spin_unlock(&dev->parent->power.lock);
+ retval = 1;
goto no_callback; /* Assume success. */
}
spin_unlock(&dev->parent->power.lock);
}
wake_up_all(&dev->power.wait_queue);
- if (!retval)
+ if (retval >= 0)
rpm_idle(dev, RPM_ASYNC);
out:
unsigned long flags;
int retval;
+ might_sleep_if(!(rpmflags & RPM_ASYNC));
+
if (rpmflags & RPM_GET_PUT) {
if (!atomic_dec_and_test(&dev->power.usage_count))
return 0;
unsigned long flags;
int retval;
+ might_sleep_if(!(rpmflags & RPM_ASYNC) && !dev->power.irq_safe);
+
if (rpmflags & RPM_GET_PUT) {
if (!atomic_dec_and_test(&dev->power.usage_count))
return 0;
unsigned long flags;
int retval;
+ might_sleep_if(!(rpmflags & RPM_ASYNC) && !dev->power.irq_safe);
+
if (rpmflags & RPM_GET_PUT)
atomic_inc(&dev->power.usage_count);
*/
void __pm_runtime_disable(struct device *dev, bool check_resume)
{
+ might_sleep();
spin_lock_irq(&dev->power.lock);
if (dev->power.disable_depth > 0) {
{
int old_delay, old_use;
+ might_sleep();
+
spin_lock_irq(&dev->power.lock);
old_delay = dev->power.autosuspend_delay;
old_use = dev->power.use_autosuspend;
goto out;
}
+ if (status[13] & UHS_SDR50_BUS_SPEED)
+ card->sw_caps.hs_max_dtr = 50000000;
+
if (card->scr.sda_spec3) {
card->sw_caps.sd3_bus_mode = status[13];
}
card->sw_caps.sd3_curr_limit = status[7];
- } else {
- if (status[13] & 0x02)
- card->sw_caps.hs_max_dtr = 50000000;
}
out:
bool reinit)
{
int err;
+#ifdef CONFIG_MMC_PARANOID_SD_INIT
+ int retries;
+#endif
if (!reinit) {
/*
/*
* Fetch switch information from card.
*/
+#ifdef CONFIG_MMC_PARANOID_SD_INIT
+ for (retries = 1; retries <= 3; retries++) {
+ err = mmc_read_switch(card);
+ if (!err) {
+ if (retries > 1) {
+ printk(KERN_WARNING
+ "%s: recovered\n",
+ mmc_hostname(host));
+ }
+ break;
+ } else {
+ printk(KERN_WARNING
+ "%s: read switch failed (attempt %d)\n",
+ mmc_hostname(host), retries);
+ }
+ }
+#else
err = mmc_read_switch(card);
+#endif
+
if (err)
return err;
}
*/
static void mmc_sd_detect(struct mmc_host *host)
{
- int err;
+ int err = 0;
+#ifdef CONFIG_MMC_PARANOID_SD_INIT
+ int retries = 5;
+#endif
BUG_ON(!host);
BUG_ON(!host->card);
-
+
mmc_claim_host(host);
/*
* Just check if our card has been removed.
*/
+#ifdef CONFIG_MMC_PARANOID_SD_INIT
+ while(retries) {
+ err = mmc_send_status(host->card, NULL);
+ if (err) {
+ retries--;
+ udelay(5);
+ continue;
+ }
+ break;
+ }
+ if (!retries) {
+ printk(KERN_ERR "%s(%s): Unable to re-detect card (%d)\n",
+ __func__, mmc_hostname(host), err);
+ }
+#else
err = mmc_send_status(host->card, NULL);
-
+#endif
mmc_release_host(host);
if (err) {
static int mmc_sd_resume(struct mmc_host *host)
{
int err;
+#ifdef CONFIG_MMC_PARANOID_SD_INIT
+ int retries;
+#endif
BUG_ON(!host);
BUG_ON(!host->card);
mmc_claim_host(host);
+#ifdef CONFIG_MMC_PARANOID_SD_INIT
+ retries = 5;
+ while (retries) {
+ err = mmc_sd_init_card(host, host->ocr, host->card);
+
+ if (err) {
+ printk(KERN_ERR "%s: Re-init card rc = %d (retries = %d)\n",
+ mmc_hostname(host), err, retries);
+ mdelay(5);
+ retries--;
+ continue;
+ }
+ break;
+ }
+#else
err = mmc_sd_init_card(host, host->ocr, host->card);
+#endif
mmc_release_host(host);
return err;
{
int err;
u32 ocr;
+#ifdef CONFIG_MMC_PARANOID_SD_INIT
+ int retries;
+#endif
BUG_ON(!host);
WARN_ON(!host->claimed);
/*
* Detect and init the card.
*/
+#ifdef CONFIG_MMC_PARANOID_SD_INIT
+ retries = 5;
+ while (retries) {
+ err = mmc_sd_init_card(host, host->ocr, NULL);
+ if (err) {
+ retries--;
+ continue;
+ }
+ break;
+ }
+
+ if (!retries) {
+ printk(KERN_ERR "%s: mmc_sd_init_card() failure (err = %d)\n",
+ mmc_hostname(host), err);
+ goto err;
+ }
+#else
err = mmc_sd_init_card(host, host->ocr, NULL);
if (err)
goto err;
+#endif
mmc_release_host(host);
err = mmc_add_card(host->card);
#include "sdio_ops.h"
#include "sdio_cis.h"
+#ifdef CONFIG_MMC_EMBEDDED_SDIO
+#include <linux/mmc/sdio_ids.h>
+#endif
+
static int sdio_read_fbr(struct sdio_func *func)
{
int ret;
goto finish;
}
- /*
- * Read the common registers.
- */
- err = sdio_read_cccr(card);
- if (err)
- goto remove;
+#ifdef CONFIG_MMC_EMBEDDED_SDIO
+ if (host->embedded_sdio_data.cccr)
+ memcpy(&card->cccr, host->embedded_sdio_data.cccr, sizeof(struct sdio_cccr));
+ else {
+#endif
+ /*
+ * Read the common registers.
+ */
+ err = sdio_read_cccr(card);
+ if (err)
+ goto remove;
+#ifdef CONFIG_MMC_EMBEDDED_SDIO
+ }
+#endif
- /*
- * Read the common CIS tuples.
- */
- err = sdio_read_common_cis(card);
- if (err)
- goto remove;
+#ifdef CONFIG_MMC_EMBEDDED_SDIO
+ if (host->embedded_sdio_data.cis)
+ memcpy(&card->cis, host->embedded_sdio_data.cis, sizeof(struct sdio_cis));
+ else {
+#endif
+ /*
+ * Read the common CIS tuples.
+ */
+ err = sdio_read_common_cis(card);
+ if (err)
+ goto remove;
+#ifdef CONFIG_MMC_EMBEDDED_SDIO
+ }
+#endif
if (oldcard) {
int same = (card->cis.vendor == oldcard->cis.vendor &&
}
if (!err && host->sdio_irqs)
- mmc_signal_sdio_irq(host);
+ wake_up_process(host->sdio_irq_thread);
mmc_release_host(host);
/*
funcs = (ocr & 0x70000000) >> 28;
card->sdio_funcs = 0;
+#ifdef CONFIG_MMC_EMBEDDED_SDIO
+ if (host->embedded_sdio_data.funcs)
+ card->sdio_funcs = funcs = host->embedded_sdio_data.num_funcs;
+#endif
+
/*
* Initialize (but don't add) all present functions.
*/
for (i = 0; i < funcs; i++, card->sdio_funcs++) {
- err = sdio_init_func(host->card, i + 1);
- if (err)
- goto remove;
-
+#ifdef CONFIG_MMC_EMBEDDED_SDIO
+ if (host->embedded_sdio_data.funcs) {
+ struct sdio_func *tmp;
+
+ tmp = sdio_alloc_func(host->card);
+ if (IS_ERR(tmp))
+ goto remove;
+ tmp->num = (i + 1);
+ card->sdio_func[i] = tmp;
+ tmp->class = host->embedded_sdio_data.funcs[i].f_class;
+ tmp->max_blksize = host->embedded_sdio_data.funcs[i].f_maxblksize;
+ tmp->vendor = card->cis.vendor;
+ tmp->device = card->cis.device;
+ } else {
+#endif
+ err = sdio_init_func(host->card, i + 1);
+ if (err)
+ goto remove;
+#ifdef CONFIG_MMC_EMBEDDED_SDIO
+ }
+#endif
/*
* Enable Runtime PM for this func (if supported)
*/
return err;
}
+int sdio_reset_comm(struct mmc_card *card)
+{
+ struct mmc_host *host = card->host;
+ u32 ocr;
+ int err;
+
+ printk("%s():\n", __func__);
+ mmc_claim_host(host);
+
+ mmc_go_idle(host);
+
+ mmc_set_clock(host, host->f_min);
+
+ err = mmc_send_io_op_cond(host, 0, &ocr);
+ if (err)
+ goto err;
+
+ host->ocr = mmc_select_voltage(host, ocr);
+ if (!host->ocr) {
+ err = -EINVAL;
+ goto err;
+ }
+
+ err = mmc_send_io_op_cond(host, host->ocr, &ocr);
+ if (err)
+ goto err;
+
+ if (mmc_host_is_spi(host)) {
+ err = mmc_spi_set_crc(host, use_spi_crc);
+ if (err)
+ goto err;
+ }
+
+ if (!mmc_host_is_spi(host)) {
+ err = mmc_send_relative_addr(host, &card->rca);
+ if (err)
+ goto err;
+ mmc_set_bus_mode(host, MMC_BUSMODE_PUSHPULL);
+ }
+ if (!mmc_host_is_spi(host)) {
+ err = mmc_select_card(card);
+ if (err)
+ goto err;
+ }
+
+ /*
+ * Switch to high-speed (if supported).
+ */
+ err = sdio_enable_hs(card);
+ if (err > 0)
+ mmc_sd_go_highspeed(card);
+ else if (err)
+ goto err;
+
+ /*
+ * Change to the card's maximum speed.
+ */
+ mmc_set_clock(host, mmc_sdio_get_max_clock(card));
+
+ err = sdio_enable_4bit_bus(card);
+ if (err > 0)
+ mmc_set_bus_width(host, MMC_BUS_WIDTH_4);
+ else if (err)
+ goto err;
+
+ mmc_release_host(host);
+ return 0;
+err:
+ printk("%s: Error resetting SDIO communications (%d)\n",
+ mmc_hostname(host), err);
+ mmc_release_host(host);
+ return err;
+}
+EXPORT_SYMBOL(sdio_reset_comm);
u16 clk = 0;
unsigned long timeout;
- if (clock == host->clock)
+ if (clock && clock == host->clock)
return;
if (host->ops->set_clock) {
mmc_card_is_removable(mmc))
mmc->caps |= MMC_CAP_NEEDS_POLL;
- /* UHS-I mode(s) supported by the host controller. */
- if (host->version >= SDHCI_SPEC_300)
+ /* Any UHS-I mode in caps implies SDR12 and SDR25 support. */
+ if (caps[1] & (SDHCI_SUPPORT_SDR104 | SDHCI_SUPPORT_SDR50 |
+ SDHCI_SUPPORT_DDR50))
mmc->caps |= MMC_CAP_UHS_SDR12 | MMC_CAP_UHS_SDR25;
/* SDR104 supports also implies SDR50 support */
source "drivers/net/stmmac/Kconfig"
config PCH_GBE
- tristate "Intel EG20T PCH / OKI SEMICONDUCTOR ML7223 IOH GbE"
+ tristate "Intel EG20T PCH/OKI SEMICONDUCTOR IOH(ML7223/ML7831) GbE"
depends on PCI
select MII
---help---
This driver enables Gigabit Ethernet function.
This driver also can be used for OKI SEMICONDUCTOR IOH(Input/
- Output Hub), ML7223.
- ML7223 IOH is for MP(Media Phone) use.
- ML7223 is companion chip for Intel Atom E6xx series.
- ML7223 is completely compatible for Intel EG20T PCH.
+ Output Hub), ML7223/ML7831.
+ ML7223 IOH is for MP(Media Phone) use. ML7831 IOH is for general
+ purpose use.
+ ML7223/ML7831 is companion chip for Intel Atom E6xx series.
+ ML7223/ML7831 is completely compatible for Intel EG20T PCH.
endif # NETDEV_1000
used by ISPs and enterprises to tunnel PPP traffic over UDP
tunnels. L2TP is replacing PPTP for VPN uses.
+config PPPOLAC
+ tristate "PPP on L2TP Access Concentrator"
+ depends on PPP && INET
+ help
+ L2TP (RFC 2661) is a tunneling protocol widely used in virtual private
+ networks. This driver handles L2TP data packets between a UDP socket
+ and a PPP channel, but only permits one session per socket. Thus it is
+ fairly simple and suited for clients.
+
+config PPPOPNS
+ tristate "PPP on PPTP Network Server"
+ depends on PPP && INET
+ help
+ PPTP (RFC 2637) is a tunneling protocol widely used in virtual private
+ networks. This driver handles PPTP data packets between a RAW socket
+ and a PPP channel. It is fairly simple and easy to use.
+
config SLIP
tristate "SLIP (serial line) support"
---help---
int vnet_hdr_sz;
int ret;
- if (cmd == TUNSETIFF || _IOC_TYPE(cmd) == 0x89)
+#ifdef CONFIG_ANDROID_PARANOID_NETWORK
+ if (cmd != TUNGETIFF && !capable(CAP_NET_ADMIN)) {
+ return -EPERM;
+ }
+#endif
+
+ if (cmd == TUNSETIFF || _IOC_TYPE(cmd) == 0x89) {
if (copy_from_user(&ifr, argp, ifreq_len))
return -EFAULT;
-
+ } else {
+ memset(&ifr, 0, sizeof(ifr));
+ }
if (cmd == TUNGETFEATURES) {
/* Currently this just means: "what IFF flags are valid?".
* This is needed because we never checked for invalid flags on
struct uart_state *state = tty->driver_data;
struct uart_port *port = state->uart_port;
+ if (port->ops->wake_peer)
+ port->ops->wake_peer(port);
+
if (!uart_circ_empty(&state->xmit) && state->xmit.buf &&
!tty->stopped && !tty->hw_stopped)
port->ops->start_tx(port);
tty_unregister_driver(p);
put_tty_driver(p);
kfree(drv->state);
+ drv->state = NULL;
drv->tty_driver = NULL;
}
* Returns negative errno, or zero on success
*/
int gether_setup(struct usb_gadget *g, u8 ethaddr[ETH_ALEN])
+{
+ return gether_setup_name(g, ethaddr, "usb");
+}
+
+/**
+ * gether_setup_name - initialize one ethernet-over-usb link
+ * @g: gadget to associated with these links
+ * @ethaddr: NULL, or a buffer in which the ethernet address of the
+ * host side of the link is recorded
+ * @netname: name for network device (for example, "usb")
+ * Context: may sleep
+ *
+ * This sets up the single network link that may be exported by a
+ * gadget driver using this framework. The link layer addresses are
+ * set up using module parameters.
+ *
+ * Returns negative errno, or zero on success
+ */
+int gether_setup_name(struct usb_gadget *g, u8 ethaddr[ETH_ALEN],
+ const char *netname)
{
struct eth_dev *dev;
struct net_device *net;
/* network device setup */
dev->net = net;
- strcpy(net->name, "usb%d");
+ snprintf(net->name, sizeof(net->name), "%s%%d", netname);
if (get_ether_addr(dev_addr, net->dev_addr))
dev_warn(&g->dev,
SET_ETHTOOL_OPS(net, &ops);
- /* two kinds of host-initiated state changes:
- * - iff DATA transfer is active, carrier is "on"
- * - tx queueing enabled if open *and* carrier is "on"
- */
- netif_carrier_off(net);
-
dev->gadget = g;
SET_NETDEV_DEV(net, &g->dev);
SET_NETDEV_DEVTYPE(net, &gadget_type);
INFO(dev, "HOST MAC %pM\n", dev->host_mac);
the_dev = dev;
+
+ /* two kinds of host-initiated state changes:
+ * - iff DATA transfer is active, carrier is "on"
+ * - tx queueing enabled if open *and* carrier is "on"
+ */
+ netif_carrier_off(net);
}
return status;
struct eth_dev *dev = link->ioport;
struct usb_request *req;
- WARN_ON(!dev);
if (!dev)
return;
else {
qtd = list_entry (qh->qtd_list.next,
struct ehci_qtd, qtd_list);
- /* first qtd may already be partially processed */
- if (cpu_to_hc32(ehci, qtd->qtd_dma) == qh->hw->hw_current)
+ /*
+ * first qtd may already be partially processed.
+ * If we come here during unlink, the QH overlay region
+ * might have reference to the just unlinked qtd. The
+ * qtd is updated in qh_completions(). Update the QH
+ * overlay here.
+ */
+ if (cpu_to_hc32(ehci, qtd->qtd_dma) == qh->hw->hw_current) {
+ qh->hw->hw_qtd_next = qtd->hw_next;
qtd = NULL;
+ }
}
if (qtd)
head->qh_next.qh = qh;
head->hw->hw_next = dma;
+ /*
+ * flush qh descriptor into memory immediately,
+ * see comments in qh_append_tds.
+ * */
+ ehci_sync_mem();
+
qh_get(qh);
qh->xacterrs = 0;
qh->qh_state = QH_STATE_LINKED;
wmb ();
dummy->hw_token = token;
+ /*
+ * Writing to dma coherent buffer on ARM may
+ * be delayed to reach memory, so HC may not see
+ * hw_token of dummy qtd in time, which can cause
+ * the qtd transaction to be executed very late,
+ * and degrade performance a lot. ehci_sync_mem
+ * is added to flush 'token' immediatelly into
+ * memory, so that ehci can execute the transaction
+ * ASAP.
+ * */
+ ehci_sync_mem();
+
urb->hcpriv = qh_get (qh);
}
}
#include <linux/pipe_fs_i.h>
#include <linux/swap.h>
#include <linux/splice.h>
+#include <linux/freezer.h>
MODULE_ALIAS_MISCDEV(FUSE_MINOR);
MODULE_ALIAS("devname:fuse");
* Wait it out.
*/
spin_unlock(&fc->lock);
- wait_event(req->waitq, req->state == FUSE_REQ_FINISHED);
+
+ while (req->state != FUSE_REQ_FINISHED)
+ wait_event_freezable(req->waitq,
+ req->state == FUSE_REQ_FINISHED);
spin_lock(&fc->lock);
if (!req->aborted)
req->pages[req->num_pages] = page;
req->num_pages++;
+ offset = 0;
num -= this_num;
total_len += this_num;
index++;
/* migration should happen before other stuff but after perf */
CPU_PRI_PERF = 20,
CPU_PRI_MIGRATION = 10,
- /* prepare workqueues for other notifiers */
- CPU_PRI_WORKQUEUE = 5,
+ /* bring up workqueues before normal notifiers and down after */
+ CPU_PRI_WORKQUEUE_UP = 5,
+ CPU_PRI_WORKQUEUE_DOWN = -5,
};
#ifdef CONFIG_SMP
static inline void enable_nonboot_cpus(void) {}
#endif /* !CONFIG_PM_SLEEP_SMP */
+#define IDLE_START 1
+#define IDLE_END 2
+
+void idle_notifier_register(struct notifier_block *n);
+void idle_notifier_unregister(struct notifier_block *n);
+void idle_notifier_call_chain(unsigned long val);
+
#endif /* _LINUX_CPU_H_ */
#include <linux/leds.h>
#include <linux/sched.h>
+#include <linux/wakelock.h>
#include <linux/mmc/core.h>
#include <linux/mmc/pm.h>
int claim_cnt; /* "claim" nesting count */
struct delayed_work detect;
+ struct wake_lock detect_wake_lock;
const struct mmc_bus_ops *bus_ops; /* current bus driver */
unsigned int bus_refs; /* reference counter */
+ unsigned int bus_resume_flags;
+#define MMC_BUSRESUME_MANUAL_RESUME (1 << 0)
+#define MMC_BUSRESUME_NEEDS_RESUME (1 << 1)
+
unsigned int sdio_irqs;
struct task_struct *sdio_irq_thread;
+ bool sdio_irq_pending;
atomic_t sdio_irq_thread_abort;
mmc_pm_flag_t pm_flags; /* requested pm features */
struct dentry *debugfs_root;
+#ifdef CONFIG_MMC_EMBEDDED_SDIO
+ struct {
+ struct sdio_cis *cis;
+ struct sdio_cccr *cccr;
+ struct sdio_embedded_func *funcs;
+ int num_funcs;
+ } embedded_sdio_data;
+#endif
+
unsigned long private[0] ____cacheline_aligned;
};
extern void mmc_remove_host(struct mmc_host *);
extern void mmc_free_host(struct mmc_host *);
+#ifdef CONFIG_MMC_EMBEDDED_SDIO
+extern void mmc_set_embedded_sdio_data(struct mmc_host *host,
+ struct sdio_cis *cis,
+ struct sdio_cccr *cccr,
+ struct sdio_embedded_func *funcs,
+ int num_funcs);
+#endif
+
static inline void *mmc_priv(struct mmc_host *host)
{
return (void *)host->private;
#define mmc_dev(x) ((x)->parent)
#define mmc_classdev(x) (&(x)->class_dev)
#define mmc_hostname(x) (dev_name(&(x)->class_dev))
+#define mmc_bus_needs_resume(host) ((host)->bus_resume_flags & MMC_BUSRESUME_NEEDS_RESUME)
+#define mmc_bus_manual_resume(host) ((host)->bus_resume_flags & MMC_BUSRESUME_MANUAL_RESUME)
+
+static inline void mmc_set_bus_resume_policy(struct mmc_host *host, int manual)
+{
+ if (manual)
+ host->bus_resume_flags |= MMC_BUSRESUME_MANUAL_RESUME;
+ else
+ host->bus_resume_flags &= ~MMC_BUSRESUME_MANUAL_RESUME;
+}
+
+extern int mmc_resume_bus(struct mmc_host *host);
extern int mmc_suspend_host(struct mmc_host *);
extern int mmc_resume_host(struct mmc_host *);
static inline void mmc_signal_sdio_irq(struct mmc_host *host)
{
host->ops->enable_sdio_irq(host, 0);
+ host->sdio_irq_pending = true;
wake_up_process(host->sdio_irq_thread);
}
const struct sched_class *sched_class;
struct sched_entity se;
struct sched_rt_entity rt;
+ #ifdef CONFIG_CGROUP_SCHED
+ struct task_group *sched_task_group;
+ #endif
#ifdef CONFIG_PREEMPT_NOTIFIERS
/* list of struct preempt_notifier: */
#endif
#ifdef CONFIG_CPUSETS
nodemask_t mems_allowed; /* Protected by alloc_lock */
- int mems_allowed_change_disable;
+ seqcount_t mems_allowed_seq; /* Seqence no to catch updates */
int cpuset_mem_spread_rotor;
int cpuset_slab_spread_rotor;
#endif
extern void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st);
extern void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *st);
+extern int task_free_register(struct notifier_block *n);
+extern int task_free_unregister(struct notifier_block *n);
+
/*
* Per process flags
*/
extern long sched_group_rt_period(struct task_group *tg);
extern int sched_rt_can_attach(struct task_group *tg, struct task_struct *tsk);
#endif
- #endif
+ #endif /* CONFIG_CGROUP_SCHED */
extern int task_can_switch_user(struct user_struct *up,
struct task_struct *tsk);
static DECLARE_WORK(release_agent_work, cgroup_release_agent);
static void check_for_release(struct cgroup *cgrp);
+/*
+ * A queue for waiters to do rmdir() cgroup. A tasks will sleep when
+ * cgroup->count == 0 && list_empty(&cgroup->children) && subsys has some
+ * reference to css->refcnt. In general, this refcnt is expected to goes down
+ * to zero, soon.
+ *
+ * CGRP_WAIT_ON_RMDIR flag is set under cgroup's inode->i_mutex;
+ */
+DECLARE_WAIT_QUEUE_HEAD(cgroup_rmdir_waitq);
+
+static void cgroup_wakeup_rmdir_waiter(struct cgroup *cgrp)
+{
+ if (unlikely(test_and_clear_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags)))
+ wake_up_all(&cgroup_rmdir_waitq);
+}
+
+void cgroup_exclude_rmdir(struct cgroup_subsys_state *css)
+{
+ css_get(css);
+}
+
+void cgroup_release_and_wakeup_rmdir(struct cgroup_subsys_state *css)
+{
+ cgroup_wakeup_rmdir_waiter(css->cgroup);
+ css_put(css);
+}
+
/* Link structure for associating css_set objects with cgroups */
struct cg_cgroup_link {
/*
return &css_set_table[index];
}
-/* We don't maintain the lists running through each css_set to its
- * task until after the first call to cgroup_iter_start(). This
- * reduces the fork()/exit() overhead for people who have cgroups
- * compiled into their kernel but not actually in use */
-static int use_task_css_set_links __read_mostly;
-
-static void __put_css_set(struct css_set *cg, int taskexit)
+static void free_css_set_work(struct work_struct *work)
{
+ struct css_set *cg = container_of(work, struct css_set, work);
struct cg_cgroup_link *link;
struct cg_cgroup_link *saved_link;
- /*
- * Ensure that the refcount doesn't hit zero while any readers
- * can see it. Similar to atomic_dec_and_lock(), but for an
- * rwlock
- */
- if (atomic_add_unless(&cg->refcount, -1, 1))
- return;
- write_lock(&css_set_lock);
- if (!atomic_dec_and_test(&cg->refcount)) {
- write_unlock(&css_set_lock);
- return;
- }
-
- /* This css_set is dead. unlink it and release cgroup refcounts */
- hlist_del(&cg->hlist);
- css_set_count--;
+ write_lock(&css_set_lock);
list_for_each_entry_safe(link, saved_link, &cg->cg_links,
cg_link_list) {
struct cgroup *cgrp = link->cgrp;
list_del(&link->cg_link_list);
list_del(&link->cgrp_link_list);
- if (atomic_dec_and_test(&cgrp->count) &&
- notify_on_release(cgrp)) {
- if (taskexit)
- set_bit(CGRP_RELEASABLE, &cgrp->flags);
+ if (atomic_dec_and_test(&cgrp->count)) {
check_for_release(cgrp);
+ cgroup_wakeup_rmdir_waiter(cgrp);
}
-
kfree(link);
}
-
write_unlock(&css_set_lock);
- kfree_rcu(cg, rcu_head);
+
+ kfree(cg);
}
+static void free_css_set_rcu(struct rcu_head *obj)
+{
+ struct css_set *cg = container_of(obj, struct css_set, rcu_head);
+
+ INIT_WORK(&cg->work, free_css_set_work);
+ schedule_work(&cg->work);
+}
+
+/* We don't maintain the lists running through each css_set to its
+ * task until after the first call to cgroup_iter_start(). This
+ * reduces the fork()/exit() overhead for people who have cgroups
+ * compiled into their kernel but not actually in use */
+static int use_task_css_set_links __read_mostly;
+
/*
* refcounted get/put for css_set objects
*/
atomic_inc(&cg->refcount);
}
-static inline void put_css_set(struct css_set *cg)
+static void put_css_set(struct css_set *cg)
{
- __put_css_set(cg, 0);
-}
+ /*
+ * Ensure that the refcount doesn't hit zero while any readers
+ * can see it. Similar to atomic_dec_and_lock(), but for an
+ * rwlock
+ */
+ if (atomic_add_unless(&cg->refcount, -1, 1))
+ return;
+ write_lock(&css_set_lock);
+ if (!atomic_dec_and_test(&cg->refcount)) {
+ write_unlock(&css_set_lock);
+ return;
+ }
-static inline void put_css_set_taskexit(struct css_set *cg)
-{
- __put_css_set(cg, 1);
+ hlist_del(&cg->hlist);
+ css_set_count--;
+
+ write_unlock(&css_set_lock);
+ call_rcu(&cg->rcu_head, free_css_set_rcu);
}
/*
* cgroup_attach_task(), which overwrites one tasks cgroup pointer with
* another. It does so using cgroup_mutex, however there are
* several performance critical places that need to reference
- * task->cgroup without the expense of grabbing a system global
+ * task->cgroups without the expense of grabbing a system global
* mutex. Therefore except as noted below, when dereferencing or, as
- * in cgroup_attach_task(), modifying a task'ss cgroup pointer we use
+ * in cgroup_attach_task(), modifying a task's cgroups pointer we use
* task_lock(), which acts on a spinlock (task->alloc_lock) already in
* the task_struct routinely used for such matters.
*
remove_dir(dentry);
}
-/*
- * A queue for waiters to do rmdir() cgroup. A tasks will sleep when
- * cgroup->count == 0 && list_empty(&cgroup->children) && subsys has some
- * reference to css->refcnt. In general, this refcnt is expected to goes down
- * to zero, soon.
- *
- * CGRP_WAIT_ON_RMDIR flag is set under cgroup's inode->i_mutex;
- */
-DECLARE_WAIT_QUEUE_HEAD(cgroup_rmdir_waitq);
-
-static void cgroup_wakeup_rmdir_waiter(struct cgroup *cgrp)
-{
- if (unlikely(test_and_clear_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags)))
- wake_up_all(&cgroup_rmdir_waitq);
-}
-
-void cgroup_exclude_rmdir(struct cgroup_subsys_state *css)
-{
- css_get(css);
-}
-
-void cgroup_release_and_wakeup_rmdir(struct cgroup_subsys_state *css)
-{
- cgroup_wakeup_rmdir_waiter(css->cgroup);
- css_put(css);
-}
-
/*
* Call with cgroup_mutex held. Drops reference counts on modules, including
* any duplicate ones that parse_cgroupfs_options took. If this function
* trading it for newcg is protected by cgroup_mutex, we're safe to drop
* it here; it will be freed under RCU.
*/
- put_css_set(oldcg);
-
set_bit(CGRP_RELEASABLE, &oldcgrp->flags);
+ put_css_set(oldcg);
return 0;
}
struct cgroup_subsys *ss, *failed_ss = NULL;
struct cgroup *oldcgrp;
struct cgroupfs_root *root = cgrp->root;
+ struct css_set *cg;
/* Nothing to do if the task is already in that cgroup */
oldcgrp = task_cgroup_from_root(tsk, root);
}
}
+ task_lock(tsk);
+ cg = tsk->cgroups;
+ get_css_set(cg);
+ task_unlock(tsk);
+
retval = cgroup_task_migrate(cgrp, oldcgrp, tsk, false);
if (retval)
goto out;
if (ss->attach)
ss->attach(ss, cgrp, oldcgrp, tsk);
}
-
- synchronize_rcu();
+ set_bit(CGRP_RELEASABLE, &cgrp->flags);
+ /* put_css_set will not destroy cg until after an RCU grace period */
+ put_css_set(cg);
/*
* wake up rmdir() waiter. the rmdir should fail since the cgroup
return retval;
}
+static int cgroup_allow_attach(struct cgroup *cgrp, struct task_struct *tsk)
+{
+ struct cgroup_subsys *ss;
+ int ret;
+
+ for_each_subsys(cgrp->root, ss) {
+ if (ss->allow_attach) {
+ ret = ss->allow_attach(cgrp, tsk);
+ if (ret)
+ return ret;
+ } else {
+ return -EACCES;
+ }
+ }
+
+ return 0;
+}
+
/*
* Find the task_struct of the task to attach by vpid and pass it along to the
* function to attach either it or all tasks in its threadgroup. Will take
if (cred->euid &&
cred->euid != tcred->uid &&
cred->euid != tcred->suid) {
- rcu_read_unlock();
- cgroup_unlock();
- return -EACCES;
+ /*
+ * if the default permission check fails, give each
+ * cgroup a chance to extend the permission check
+ */
+ ret = cgroup_allow_attach(cgrp, tsk);
+ if (ret) {
+ rcu_read_unlock();
+ cgroup_unlock();
+ return ret;
+ }
}
get_task_struct(tsk);
rcu_read_unlock();
if (err < 0)
goto err_remove;
+ set_bit(CGRP_RELEASABLE, &parent->flags);
+
/* The cgroup directory was pre-locked for us */
BUG_ON(!mutex_is_locked(&cgrp->dentry->d_inode->i_mutex));
return !failed;
}
+/* checks if all of the css_sets attached to a cgroup have a refcount of 0.
+ * Must be called with css_set_lock held */
+static int cgroup_css_sets_empty(struct cgroup *cgrp)
+{
+ struct cg_cgroup_link *link;
+
+ list_for_each_entry(link, &cgrp->css_sets, cgrp_link_list) {
+ struct css_set *cg = link->cg;
+ if (atomic_read(&cg->refcount) > 0)
+ return 0;
+ }
+
+ return 1;
+}
+
static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry)
{
struct cgroup *cgrp = dentry->d_fsdata;
/* the vfs holds both inode->i_mutex already */
again:
mutex_lock(&cgroup_mutex);
- if (atomic_read(&cgrp->count) != 0) {
+ if (!cgroup_css_sets_empty(cgrp)) {
mutex_unlock(&cgroup_mutex);
return -EBUSY;
}
mutex_lock(&cgroup_mutex);
parent = cgrp->parent;
- if (atomic_read(&cgrp->count) || !list_empty(&cgrp->children)) {
+ if (!cgroup_css_sets_empty(cgrp) || !list_empty(&cgrp->children)) {
clear_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags);
mutex_unlock(&cgroup_mutex);
return -EBUSY;
cgroup_d_remove_dir(d);
dput(d);
- set_bit(CGRP_RELEASABLE, &parent->flags);
check_for_release(parent);
/*
task_unlock(tsk);
if (cg)
- put_css_set_taskexit(cg);
+ put_css_set(cg);
}
/**
}
}
+/* Caller must verify that the css is not for root cgroup */
+void __css_get(struct cgroup_subsys_state *css, int count)
+{
+ atomic_add(count, &css->refcnt);
+ set_bit(CGRP_RELEASABLE, &css->cgroup->flags);
+}
+EXPORT_SYMBOL_GPL(__css_get);
+
/* Caller must verify that the css is not for root cgroup */
void __css_put(struct cgroup_subsys_state *css, int count)
{
rcu_read_lock();
val = atomic_sub_return(count, &css->refcnt);
if (val == 1) {
- if (notify_on_release(cgrp)) {
- set_bit(CGRP_RELEASABLE, &cgrp->flags);
- check_for_release(cgrp);
- }
+ check_for_release(cgrp);
cgroup_wakeup_rmdir_waiter(cgrp);
}
rcu_read_unlock();
#include <linux/audit.h>
#include <linux/memcontrol.h>
#include <linux/ftrace.h>
+ #include <linux/proc_fs.h>
#include <linux/profile.h>
#include <linux/rmap.h>
#include <linux/ksm.h>
/* SLAB cache for mm_struct structures (tsk->mm) */
static struct kmem_cache *mm_cachep;
+/* Notifier list called when a task struct is freed */
+static ATOMIC_NOTIFIER_HEAD(task_free_notifier);
+
static void account_kernel_stack(struct thread_info *ti, int account)
{
struct zone *zone = page_zone(virt_to_page(ti));
free_signal_struct(sig);
}
+int task_free_register(struct notifier_block *n)
+{
+ return atomic_notifier_chain_register(&task_free_notifier, n);
+}
+EXPORT_SYMBOL(task_free_register);
+
+int task_free_unregister(struct notifier_block *n)
+{
+ return atomic_notifier_chain_unregister(&task_free_notifier, n);
+}
+EXPORT_SYMBOL(task_free_unregister);
+
void __put_task_struct(struct task_struct *tsk)
{
WARN_ON(!tsk->exit_state);
delayacct_tsk_free(tsk);
put_signal_struct(tsk->signal);
+ atomic_notifier_call_chain(&task_free_notifier, 0, tsk);
if (!profile_handoff_task(tsk))
free_task(tsk);
}
#ifdef CONFIG_CGROUPS
init_rwsem(&sig->threadgroup_fork_lock);
#endif
+ #ifdef CONFIG_CPUSETS
+ seqcount_init(&tsk->mems_allowed_seq);
+ #endif
sig->oom_adj = current->signal->oom_adj;
sig->oom_score_adj = current->signal->oom_score_adj;
{
raw_spin_lock_init(&p->pi_lock);
#ifdef CONFIG_RT_MUTEXES
- plist_head_init_raw(&p->pi_waiters, &p->pi_lock);
+ plist_head_init(&p->pi_waiters);
p->pi_blocked_on = NULL;
#endif
}
if (p->io_context)
exit_io_context(p);
bad_fork_cleanup_namespaces:
+ if (unlikely(clone_flags & CLONE_NEWPID))
+ pid_ns_release_proc(p->nsproxy->pid_ns);
exit_task_namespaces(p);
bad_fork_cleanup_mm:
if (p->mm) {
* @uaddr2: the pi futex we will take prior to returning to user-space
*
* The caller will wait on uaddr and will be requeued by futex_requeue() to
- * uaddr2 which must be PI aware. Normal wakeup will wake on uaddr2 and
- * complete the acquisition of the rt_mutex prior to returning to userspace.
- * This ensures the rt_mutex maintains an owner when it has waiters; without
- * one, the pi logic wouldn't know which task to boost/deboost, if there was a
- * need to.
+ * uaddr2 which must be PI aware and unique from uaddr. Normal wakeup will wake
+ * on uaddr2 and complete the acquisition of the rt_mutex prior to returning to
+ * userspace. This ensures the rt_mutex maintains an owner when it has waiters;
+ * without one, the pi logic would not know which task to boost/deboost, if
+ * there was a need to.
*
* We call schedule in futex_wait_queue_me() when we enqueue and return there
* via the following:
struct futex_q q = futex_q_init;
int res, ret;
+ if (uaddr == uaddr2)
+ return -EINVAL;
+
if (!bitset)
return -EINVAL;
* signal. futex_unlock_pi() will not destroy the lock_ptr nor
* the pi_state.
*/
- WARN_ON(!&q.pi_state);
+ WARN_ON(!q.pi_state);
pi_mutex = &q.pi_state->pi_mutex;
ret = rt_mutex_finish_proxy_lock(pi_mutex, to, &rt_waiter, 1);
debug_rt_mutex_free_waiter(&rt_waiter);
* fault, unlock the rt_mutex and return the fault to userspace.
*/
if (ret == -EFAULT) {
- if (rt_mutex_owner(pi_mutex) == current)
+ if (pi_mutex && rt_mutex_owner(pi_mutex) == current)
rt_mutex_unlock(pi_mutex);
} else if (ret == -EINTR) {
/*
futex_cmpxchg_enabled = 1;
for (i = 0; i < ARRAY_SIZE(futex_queues); i++) {
- plist_head_init(&futex_queues[i].chain, &futex_queues[i].lock);
+ plist_head_init(&futex_queues[i].chain);
spin_lock_init(&futex_queues[i].lock);
}
#include <linux/slab.h>
#include <linux/suspend.h>
#include <linux/syscore_ops.h>
+ #include <linux/ftrace.h>
#include <trace/events/power.h>
#include "power.h"
const char *const pm_states[PM_SUSPEND_MAX] = {
+#ifdef CONFIG_EARLYSUSPEND
+ [PM_SUSPEND_ON] = "on",
+#endif
[PM_SUSPEND_STANDBY] = "standby",
[PM_SUSPEND_MEM] = "mem",
};
goto Close;
}
suspend_console();
+ ftrace_stop();
suspend_test_start();
error = dpm_suspend_start(PMSG_SUSPEND);
if (error) {
suspend_test_start();
dpm_resume_end(PMSG_RESUME);
suspend_test_finish("resume devices");
+ ftrace_start();
resume_console();
Close:
if (suspend_ops->end)
#include <linux/ctype.h>
#include <linux/ftrace.h>
#include <linux/slab.h>
+#include <linux/cpuacct.h>
#include <asm/tlb.h>
#include <asm/irq_regs.h>
/*
* Return the group to which this tasks belongs.
*
- * We use task_subsys_state_check() and extend the RCU verification with
- * pi->lock and rq->lock because cpu_cgroup_attach() holds those locks for each
- * task it moves into the cgroup. Therefore by holding either of those locks,
- * we pin the task to the current cgroup.
+ * We cannot use task_subsys_state() and friends because the cgroup
+ * subsystem changes that value before the cgroup_subsys::attach() method
+ * is called, therefore we cannot pin it and might observe the wrong value.
+ *
+ * The same is true for autogroup's p->signal->autogroup->tg, the autogroup
+ * core changes this before calling sched_move_task().
+ *
+ * Instead we use a 'copy' which is updated from sched_move_task() while
+ * holding both task_struct::pi_lock and rq::lock.
*/
static inline struct task_group *task_group(struct task_struct *p)
{
- struct task_group *tg;
- struct cgroup_subsys_state *css;
-
- css = task_subsys_state_check(p, cpu_cgroup_subsys_id,
- lockdep_is_held(&p->pi_lock) ||
- lockdep_is_held(&task_rq(p)->lock));
- tg = container_of(css, struct task_group, css);
-
- return autogroup_task_group(p, tg);
+ return p->sched_task_group;
}
/* Change a task's cfs_rq and parent entity if it moves across CPUs/groups */
* a task's CPU. ->pi_lock for waking tasks, rq->lock for runnable tasks.
*
* sched_move_task() holds both and thus holding either pins the cgroup,
- * see set_task_rq().
+ * see task_group().
*
* Furthermore, all task_rq users should acquire both locks, see
* task_rq_lock().
static int __init setup_relax_domain_level(char *str)
{
- unsigned long val;
-
- val = simple_strtoul(str, NULL, 0);
- if (val < sched_domain_level_max)
- default_relax_domain_level = val;
+ if (kstrtoint(str, 0, &default_relax_domain_level))
+ pr_warn("Unable to set relax_domain_level\n");
return 1;
}
if (!sd)
return child;
- set_domain_attribute(sd, attr);
cpumask_and(sched_domain_span(sd), cpu_map, tl->mask(cpu));
if (child) {
sd->level = child->level + 1;
child->parent = sd;
}
sd->child = child;
+ set_domain_attribute(sd, attr);
return sd;
}
}
#endif /* CONFIG_SCHED_MC || CONFIG_SCHED_SMT */
+ static int num_cpus_frozen; /* used to mark begin/end of suspend/resume */
+
/*
* Update cpusets according to cpu_active mask. If cpusets are
* disabled, cpuset_update_active_cpus() becomes a simple wrapper
* around partition_sched_domains().
+ *
+ * If we come here as part of a suspend/resume, don't touch cpusets because we
+ * want to restore it back to its original state upon resume anyway.
*/
static int cpuset_cpu_active(struct notifier_block *nfb, unsigned long action,
void *hcpu)
{
- switch (action & ~CPU_TASKS_FROZEN) {
+ switch (action) {
+ case CPU_ONLINE_FROZEN:
+ case CPU_DOWN_FAILED_FROZEN:
+
+ /*
+ * num_cpus_frozen tracks how many CPUs are involved in suspend
+ * resume sequence. As long as this is not the last online
+ * operation in the resume sequence, just build a single sched
+ * domain, ignoring cpusets.
+ */
+ num_cpus_frozen--;
+ if (likely(num_cpus_frozen)) {
+ partition_sched_domains(1, NULL, NULL);
+ break;
+ }
+
+ /*
+ * This is the last CPU online operation. So fall through and
+ * restore the original sched domains by considering the
+ * cpuset configurations.
+ */
+
case CPU_ONLINE:
case CPU_DOWN_FAILED:
cpuset_update_active_cpus();
- return NOTIFY_OK;
+ break;
default:
return NOTIFY_DONE;
}
+ return NOTIFY_OK;
}
static int cpuset_cpu_inactive(struct notifier_block *nfb, unsigned long action,
void *hcpu)
{
- switch (action & ~CPU_TASKS_FROZEN) {
+ switch (action) {
case CPU_DOWN_PREPARE:
cpuset_update_active_cpus();
- return NOTIFY_OK;
+ break;
+ case CPU_DOWN_PREPARE_FROZEN:
+ num_cpus_frozen++;
+ partition_sched_domains(1, NULL, NULL);
+ break;
default:
return NOTIFY_DONE;
}
+ return NOTIFY_OK;
}
static int update_runtime(struct notifier_block *nfb,
#ifdef CONFIG_SMP
rt_rq->rt_nr_migratory = 0;
rt_rq->overloaded = 0;
- plist_head_init_raw(&rt_rq->pushable_tasks, &rq->lock);
+ plist_head_init(&rt_rq->pushable_tasks);
#endif
rt_rq->rt_time = 0;
#endif
#ifdef CONFIG_RT_MUTEXES
- plist_head_init_raw(&init_task.pi_waiters, &init_task.pi_lock);
+ plist_head_init(&init_task.pi_waiters);
#endif
/*
return (nested == preempt_offset);
}
+static int __might_sleep_init_called;
+int __init __might_sleep_init(void)
+{
+ __might_sleep_init_called = 1;
+ return 0;
+}
+early_initcall(__might_sleep_init);
+
void __might_sleep(const char *file, int line, int preempt_offset)
{
#ifdef in_atomic
static unsigned long prev_jiffy; /* ratelimiting */
if ((preempt_count_equals(preempt_offset) && !irqs_disabled()) ||
- system_state != SYSTEM_RUNNING || oops_in_progress)
+ oops_in_progress)
+ return;
+ if (system_state != SYSTEM_RUNNING &&
+ (!__might_sleep_init_called || system_state != SYSTEM_BOOTING))
return;
if (time_before(jiffies, prev_jiffy + HZ) && prev_jiffy)
return;
*/
void sched_move_task(struct task_struct *tsk)
{
+ struct task_group *tg;
int on_rq, running;
unsigned long flags;
struct rq *rq;
if (unlikely(running))
tsk->sched_class->put_prev_task(rq, tsk);
+ tg = container_of(task_subsys_state_check(tsk, cpu_cgroup_subsys_id,
+ lockdep_is_held(&tsk->sighand->siglock)),
+ struct task_group, css);
+ tg = autogroup_task_group(tsk, tg);
+ tsk->sched_task_group = tg;
+
#ifdef CONFIG_FAIR_GROUP_SCHED
if (tsk->sched_class->task_move_group)
tsk->sched_class->task_move_group(tsk, on_rq);
sched_destroy_group(tg);
}
+static int
+cpu_cgroup_allow_attach(struct cgroup *cgrp, struct task_struct *tsk)
+{
+ const struct cred *cred = current_cred(), *tcred;
+
+ tcred = __task_cred(tsk);
+
+ if ((current != tsk) && !capable(CAP_SYS_NICE) &&
+ cred->euid != tcred->uid && cred->euid != tcred->suid)
+ return -EACCES;
+
+ return 0;
+}
+
static int
cpu_cgroup_can_attach_task(struct cgroup *cgrp, struct task_struct *tsk)
{
.name = "cpu",
.create = cpu_cgroup_create,
.destroy = cpu_cgroup_destroy,
+ .allow_attach = cpu_cgroup_allow_attach,
.can_attach_task = cpu_cgroup_can_attach_task,
.attach_task = cpu_cgroup_attach_task,
.exit = cpu_cgroup_exit,
u64 __percpu *cpuusage;
struct percpu_counter cpustat[CPUACCT_STAT_NSTATS];
struct cpuacct *parent;
+ struct cpuacct_charge_calls *cpufreq_fn;
+ void *cpuacct_data;
};
+static struct cpuacct *cpuacct_root;
+
+/* Default calls for cpufreq accounting */
+static struct cpuacct_charge_calls *cpuacct_cpufreq;
+int cpuacct_register_cpufreq(struct cpuacct_charge_calls *fn)
+{
+ cpuacct_cpufreq = fn;
+
+ /*
+ * Root node is created before platform can register callbacks,
+ * initalize here.
+ */
+ if (cpuacct_root && fn) {
+ cpuacct_root->cpufreq_fn = fn;
+ if (fn->init)
+ fn->init(&cpuacct_root->cpuacct_data);
+ }
+ return 0;
+}
+
struct cgroup_subsys cpuacct_subsys;
/* return cpu accounting group corresponding to this container */
if (percpu_counter_init(&ca->cpustat[i], 0))
goto out_free_counters;
+ ca->cpufreq_fn = cpuacct_cpufreq;
+
+ /* If available, have platform code initalize cpu frequency table */
+ if (ca->cpufreq_fn && ca->cpufreq_fn->init)
+ ca->cpufreq_fn->init(&ca->cpuacct_data);
+
if (cgrp->parent)
ca->parent = cgroup_ca(cgrp->parent);
+ else
+ cpuacct_root = ca;
return &ca->css;
return 0;
}
+static int cpuacct_cpufreq_show(struct cgroup *cgrp, struct cftype *cft,
+ struct cgroup_map_cb *cb)
+{
+ struct cpuacct *ca = cgroup_ca(cgrp);
+ if (ca->cpufreq_fn && ca->cpufreq_fn->cpufreq_show)
+ ca->cpufreq_fn->cpufreq_show(ca->cpuacct_data, cb);
+
+ return 0;
+}
+
+/* return total cpu power usage (milliWatt second) of a group */
+static u64 cpuacct_powerusage_read(struct cgroup *cgrp, struct cftype *cft)
+{
+ int i;
+ struct cpuacct *ca = cgroup_ca(cgrp);
+ u64 totalpower = 0;
+
+ if (ca->cpufreq_fn && ca->cpufreq_fn->power_usage)
+ for_each_present_cpu(i) {
+ totalpower += ca->cpufreq_fn->power_usage(
+ ca->cpuacct_data);
+ }
+
+ return totalpower;
+}
+
static struct cftype files[] = {
{
.name = "usage",
.name = "stat",
.read_map = cpuacct_stats_show,
},
+ {
+ .name = "cpufreq",
+ .read_map = cpuacct_cpufreq_show,
+ },
+ {
+ .name = "power",
+ .read_u64 = cpuacct_powerusage_read
+ },
};
static int cpuacct_populate(struct cgroup_subsys *ss, struct cgroup *cgrp)
for (; ca; ca = ca->parent) {
u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu);
*cpuusage += cputime;
+
+ /* Call back into platform code to account for CPU speeds */
+ if (ca->cpufreq_fn && ca->cpufreq_fn->charge)
+ ca->cpufreq_fn->charge(ca->cpuacct_data, cputime, cpu);
}
rcu_read_unlock();
static struct timespec wall_to_monotonic __attribute__ ((aligned (16)));
static struct timespec total_sleep_time;
+ /* Offset clock monotonic -> clock realtime */
+ static ktime_t offs_real;
+
+ /* Offset clock monotonic -> clock boottime */
+ static ktime_t offs_boot;
+
/*
* The raw monotonic time for the CLOCK_MONOTONIC_RAW posix clock.
*/
static struct timespec raw_time;
- /* flag for if timekeeping is suspended */
- int __read_mostly timekeeping_suspended;
+ /* must hold write on xtime_lock */
+ static void update_rt_offset(void)
+ {
+ struct timespec tmp, *wtm = &wall_to_monotonic;
+
+ set_normalized_timespec(&tmp, -wtm->tv_sec, -wtm->tv_nsec);
+ offs_real = timespec_to_ktime(tmp);
+ }
- /* must hold xtime_lock */
- void timekeeping_leap_insert(int leapsecond)
+ /* must hold write on xtime_lock */
+ static void timekeeping_update(bool clearntp)
{
- xtime.tv_sec += leapsecond;
- wall_to_monotonic.tv_sec -= leapsecond;
- update_vsyscall(&xtime, &wall_to_monotonic, timekeeper.clock,
- timekeeper.mult);
+ if (clearntp) {
+ timekeeper.ntp_error = 0;
+ ntp_clear();
+ }
+ update_rt_offset();
+ update_vsyscall(&xtime, &wall_to_monotonic,
+ timekeeper.clock, timekeeper.mult);
}
+
+
+ /* flag for if timekeeping is suspended */
+ int __read_mostly timekeeping_suspended;
+
/**
* timekeeping_forward_now - update clock to the current time
*
struct timespec ts_delta;
unsigned long flags;
- if ((unsigned long)tv->tv_nsec >= NSEC_PER_SEC)
+ if (!timespec_valid_strict(tv))
return -EINVAL;
write_seqlock_irqsave(&xtime_lock, flags);
xtime = *tv;
- timekeeper.ntp_error = 0;
- ntp_clear();
-
- update_vsyscall(&xtime, &wall_to_monotonic, timekeeper.clock,
- timekeeper.mult);
+ timekeeping_update(true);
write_sequnlock_irqrestore(&xtime_lock, flags);
int timekeeping_inject_offset(struct timespec *ts)
{
unsigned long flags;
+ struct timespec tmp;
+ int ret = 0;
if ((unsigned long)ts->tv_nsec >= NSEC_PER_SEC)
return -EINVAL;
timekeeping_forward_now();
+ tmp = timespec_add(xtime, *ts);
+ if (!timespec_valid_strict(&tmp)) {
+ ret = -EINVAL;
+ goto error;
+ }
+
xtime = timespec_add(xtime, *ts);
wall_to_monotonic = timespec_sub(wall_to_monotonic, *ts);
- timekeeper.ntp_error = 0;
- ntp_clear();
-
- update_vsyscall(&xtime, &wall_to_monotonic, timekeeper.clock,
- timekeeper.mult);
+ error: /* even if we error out, we forwarded the time, so call update */
+ timekeeping_update(true);
write_sequnlock_irqrestore(&xtime_lock, flags);
/* signal hrtimers about time change */
clock_was_set();
- return 0;
+ return ret;
}
EXPORT_SYMBOL(timekeeping_inject_offset);
struct timespec now, boot;
read_persistent_clock(&now);
+ if (!timespec_valid_strict(&now)) {
+ pr_warn("WARNING: Persistent clock returned invalid value!\n"
+ " Check your CMOS/BIOS settings.\n");
+ now.tv_sec = 0;
+ now.tv_nsec = 0;
+ }
+
read_boot_clock(&boot);
+ if (!timespec_valid_strict(&boot)) {
+ pr_warn("WARNING: Boot clock returned invalid value!\n"
+ " Check your CMOS/BIOS settings.\n");
+ boot.tv_sec = 0;
+ boot.tv_nsec = 0;
+ }
write_seqlock_irqsave(&xtime_lock, flags);
}
set_normalized_timespec(&wall_to_monotonic,
-boot.tv_sec, -boot.tv_nsec);
+ update_rt_offset();
total_sleep_time.tv_sec = 0;
total_sleep_time.tv_nsec = 0;
write_sequnlock_irqrestore(&xtime_lock, flags);
/* time in seconds when suspend began */
static struct timespec timekeeping_suspend_time;
+ static void update_sleep_time(struct timespec t)
+ {
+ total_sleep_time = t;
+ offs_boot = timespec_to_ktime(t);
+ }
+
/**
* __timekeeping_inject_sleeptime - Internal function to add sleep interval
* @delta: pointer to a timespec delta value
*/
static void __timekeeping_inject_sleeptime(struct timespec *delta)
{
- if (!timespec_valid(delta)) {
+ if (!timespec_valid_strict(delta)) {
printk(KERN_WARNING "__timekeeping_inject_sleeptime: Invalid "
"sleep delta value!\n");
return;
xtime = timespec_add(xtime, *delta);
wall_to_monotonic = timespec_sub(wall_to_monotonic, *delta);
- total_sleep_time = timespec_add(total_sleep_time, *delta);
+ update_sleep_time(timespec_add(total_sleep_time, *delta));
}
__timekeeping_inject_sleeptime(delta);
- timekeeper.ntp_error = 0;
- ntp_clear();
- update_vsyscall(&xtime, &wall_to_monotonic, timekeeper.clock,
- timekeeper.mult);
+ timekeeping_update(true);
write_sequnlock_irqrestore(&xtime_lock, flags);
timekeeper.clock->cycle_last = timekeeper.clock->read(timekeeper.clock);
timekeeper.ntp_error = 0;
timekeeping_suspended = 0;
+ timekeeping_update(false);
write_sequnlock_irqrestore(&xtime_lock, flags);
touch_softlockup_watchdog();
timekeeper.xtime_nsec += timekeeper.xtime_interval << shift;
while (timekeeper.xtime_nsec >= nsecps) {
+ int leap;
timekeeper.xtime_nsec -= nsecps;
xtime.tv_sec++;
- second_overflow();
+ leap = second_overflow(xtime.tv_sec);
+ xtime.tv_sec += leap;
+ wall_to_monotonic.tv_sec -= leap;
+ if (leap)
+ clock_was_set_delayed();
}
/* Accumulate raw time */
#else
offset = (clock->read(clock) - clock->cycle_last) & clock->mask;
#endif
+ /* Check if there's really nothing to do */
+ if (offset < timekeeper.cycle_interval)
+ return;
+
timekeeper.xtime_nsec = (s64)xtime.tv_nsec << timekeeper.shift;
/*
* xtime.tv_nsec isn't larger then NSEC_PER_SEC
*/
if (unlikely(xtime.tv_nsec >= NSEC_PER_SEC)) {
+ int leap;
xtime.tv_nsec -= NSEC_PER_SEC;
xtime.tv_sec++;
- second_overflow();
+ leap = second_overflow(xtime.tv_sec);
+ xtime.tv_sec += leap;
+ wall_to_monotonic.tv_sec -= leap;
+ if (leap)
+ clock_was_set_delayed();
}
- /* check to see if there is a new clocksource to use */
- update_vsyscall(&xtime, &wall_to_monotonic, timekeeper.clock,
- timekeeper.mult);
+ timekeeping_update(false);
}
/**
} while (read_seqretry(&xtime_lock, seq));
set_normalized_timespec(ts, ts->tv_sec + tomono.tv_sec + sleep.tv_sec,
- ts->tv_nsec + tomono.tv_nsec + sleep.tv_nsec + nsecs);
+ (s64)ts->tv_nsec + tomono.tv_nsec + sleep.tv_nsec + nsecs);
}
EXPORT_SYMBOL_GPL(get_monotonic_boottime);
} while (read_seqretry(&xtime_lock, seq));
}
+ #ifdef CONFIG_HIGH_RES_TIMERS
+ /**
+ * ktime_get_update_offsets - hrtimer helper
+ * @real: pointer to storage for monotonic -> realtime offset
+ * @_boot: pointer to storage for monotonic -> boottime offset
+ *
+ * Returns current monotonic time and updates the offsets
+ * Called from hrtimer_interupt() or retrigger_next_event()
+ */
+ ktime_t ktime_get_update_offsets(ktime_t *real, ktime_t *boot)
+ {
+ ktime_t now;
+ unsigned int seq;
+ u64 secs, nsecs;
+
+ do {
+ seq = read_seqbegin(&xtime_lock);
+
+ secs = xtime.tv_sec;
+ nsecs = xtime.tv_nsec;
+ nsecs += timekeeping_get_ns();
+ /* If arch requires, add in gettimeoffset() */
+ nsecs += arch_gettimeoffset();
+
+ *real = offs_real;
+ *boot = offs_boot;
+ } while (read_seqretry(&xtime_lock, seq));
+
+ now = ktime_add_ns(ktime_set(secs, 0), nsecs);
+ now = ktime_sub(now, *real);
+ return now;
+ }
+ #endif
+
/**
* ktime_get_monotonic_offset() - get wall_to_monotonic in ktime_t format
*/
saved_gfp_mask = gfp_allowed_mask;
gfp_allowed_mask &= ~GFP_IOFS;
}
+
+static bool pm_suspending(void)
+{
+ if ((gfp_allowed_mask & GFP_IOFS) == GFP_IOFS)
+ return false;
+ return true;
+}
+
+#else
+
+static bool pm_suspending(void)
+{
+ return false;
+}
#endif /* CONFIG_PM_SLEEP */
#ifdef CONFIG_HUGETLB_PAGE_SIZE_VARIABLE
};
int min_free_kbytes = 1024;
+int min_free_order_shift = 1;
static unsigned long __meminitdata nr_kernel_pages;
static unsigned long __meminitdata nr_all_pages;
combined_idx = buddy_idx & page_idx;
higher_page = page + (combined_idx - page_idx);
buddy_idx = __find_buddy_index(combined_idx, order + 1);
- higher_buddy = page + (buddy_idx - combined_idx);
+ higher_buddy = higher_page + (buddy_idx - combined_idx);
if (page_is_buddy(higher_page, higher_buddy, order + 1)) {
list_add_tail(&page->lru,
&zone->free_area[order].free_list[migratetype]);
free_pages -= z->free_area[o].nr_free << o;
/* Require fewer higher order pages to be free */
- min >>= 1;
+ min >>= min_free_order_shift;
if (free_pages <= min)
return false;
__alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
struct zonelist *zonelist, enum zone_type high_zoneidx,
nodemask_t *nodemask, int alloc_flags, struct zone *preferred_zone,
- int migratetype, unsigned long *did_some_progress,
- bool sync_migration)
+ int migratetype, bool sync_migration,
+ bool *deferred_compaction,
+ unsigned long *did_some_progress)
{
struct page *page;
- if (!order || compaction_deferred(preferred_zone))
+ if (!order)
return NULL;
+ if (compaction_deferred(preferred_zone)) {
+ *deferred_compaction = true;
+ return NULL;
+ }
+
current->flags |= PF_MEMALLOC;
*did_some_progress = try_to_compact_pages(zonelist, order, gfp_mask,
nodemask, sync_migration);
* but not enough to satisfy watermarks.
*/
count_vm_event(COMPACTFAIL);
- defer_compaction(preferred_zone);
+
+ /*
+ * As async compaction considers a subset of pageblocks, only
+ * defer if the failure was a sync compaction failure.
+ */
+ if (sync_migration)
+ defer_compaction(preferred_zone);
cond_resched();
}
__alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
struct zonelist *zonelist, enum zone_type high_zoneidx,
nodemask_t *nodemask, int alloc_flags, struct zone *preferred_zone,
- int migratetype, unsigned long *did_some_progress,
- bool sync_migration)
+ int migratetype, bool sync_migration,
+ bool *deferred_compaction,
+ unsigned long *did_some_progress)
{
return NULL;
}
unsigned long pages_reclaimed = 0;
unsigned long did_some_progress;
bool sync_migration = false;
+ bool deferred_compaction = false;
/*
* In the slowpath, we sanity check order to avoid ever trying to
zonelist, high_zoneidx,
nodemask,
alloc_flags, preferred_zone,
- migratetype, &did_some_progress,
- sync_migration);
+ migratetype, sync_migration,
+ &deferred_compaction,
+ &did_some_progress);
if (page)
goto got_pg;
sync_migration = true;
+ /*
+ * If compaction is deferred for high-order allocations, it is because
+ * sync compaction recently failed. In this is the case and the caller
+ * has requested the system not be heavily disrupted, fail the
+ * allocation now instead of entering direct reclaim
+ */
+ if (deferred_compaction && (gfp_mask & __GFP_NO_KSWAPD))
+ goto nopage;
+
/* Try direct reclaim and then allocating */
page = __alloc_pages_direct_reclaim(gfp_mask, order,
zonelist, high_zoneidx,
goto restart;
}
+
+ /*
+ * Suspend converts GFP_KERNEL to __GFP_WAIT which can
+ * prevent reclaim making forward progress without
+ * invoking OOM. Bail if we are suspending
+ */
+ if (pm_suspending())
+ goto nopage;
}
/* Check if we should retry the allocation */
zonelist, high_zoneidx,
nodemask,
alloc_flags, preferred_zone,
- migratetype, &did_some_progress,
- sync_migration);
+ migratetype, sync_migration,
+ &deferred_compaction,
+ &did_some_progress);
if (page)
goto got_pg;
}
{
enum zone_type high_zoneidx = gfp_zone(gfp_mask);
struct zone *preferred_zone;
- struct page *page;
+ struct page *page = NULL;
int migratetype = allocflags_to_migratetype(gfp_mask);
+ unsigned int cpuset_mems_cookie;
gfp_mask &= gfp_allowed_mask;
if (unlikely(!zonelist->_zonerefs->zone))
return NULL;
- get_mems_allowed();
+ retry_cpuset:
+ cpuset_mems_cookie = get_mems_allowed();
+
/* The preferred zone is used for statistics later */
first_zones_zonelist(zonelist, high_zoneidx,
nodemask ? : &cpuset_current_mems_allowed,
&preferred_zone);
- if (!preferred_zone) {
- put_mems_allowed();
- return NULL;
- }
+ if (!preferred_zone)
+ goto out;
/* First allocation attempt */
page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, nodemask, order,
page = __alloc_pages_slowpath(gfp_mask, order,
zonelist, high_zoneidx, nodemask,
preferred_zone, migratetype);
- put_mems_allowed();
trace_mm_page_alloc(page, order, gfp_mask, migratetype);
+
+ out:
+ /*
+ * When updating a task's mems_allowed, it is possible to race with
+ * parallel threads in such a way that an allocation can fail while
+ * the mask is being updated. If a page allocation is about to fail,
+ * check if the cpuset changed during allocation and if so, retry.
+ */
+ if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page))
+ goto retry_cpuset;
+
return page;
}
EXPORT_SYMBOL(__alloc_pages_nodemask);
bool skip_free_areas_node(unsigned int flags, int nid)
{
bool ret = false;
+ unsigned int cpuset_mems_cookie;
if (!(flags & SHOW_MEM_FILTER_NODES))
goto out;
- get_mems_allowed();
- ret = !node_isset(nid, cpuset_current_mems_allowed);
- put_mems_allowed();
+ do {
+ cpuset_mems_cookie = get_mems_allowed();
+ ret = !node_isset(nid, cpuset_current_mems_allowed);
+ } while (!put_mems_allowed(cpuset_mems_cookie));
out:
return ret;
}
if (page_to_nid(page) != zone_to_nid(zone))
continue;
- /* Blocks with reserved pages will never free, skip them. */
- block_end_pfn = min(pfn + pageblock_nr_pages, end_pfn);
- if (pageblock_is_reserved(pfn, block_end_pfn))
- continue;
-
block_migratetype = get_pageblock_migratetype(page);
- /* If this block is reserved, account for it */
- if (reserve > 0 && block_migratetype == MIGRATE_RESERVE) {
- reserve--;
- continue;
- }
+ /* Only test what is necessary when the reserves are not met */
+ if (reserve > 0) {
+ /*
+ * Blocks with reserved pages will never free, skip
+ * them.
+ */
+ block_end_pfn = min(pfn + pageblock_nr_pages, end_pfn);
+ if (pageblock_is_reserved(pfn, block_end_pfn))
+ continue;
- /* Suitable for reserving if this block is movable */
- if (reserve > 0 && block_migratetype == MIGRATE_MOVABLE) {
- set_pageblock_migratetype(page, MIGRATE_RESERVE);
- move_freepages_block(zone, page, MIGRATE_RESERVE);
- reserve--;
- continue;
+ /* If this block is reserved, account for it */
+ if (block_migratetype == MIGRATE_RESERVE) {
+ reserve--;
+ continue;
+ }
+
+ /* Suitable for reserving if this block is movable */
+ if (block_migratetype == MIGRATE_MOVABLE) {
+ set_pageblock_migratetype(page,
+ MIGRATE_RESERVE);
+ move_freepages_block(zone, page,
+ MIGRATE_RESERVE);
+ reserve--;
+ continue;
+ }
}
/*
{
struct inode *inode;
struct dentry *dentry = NULL;
- u64 inum = fid->raw[2];
- inum = (inum << 32) | fid->raw[1];
+ u64 inum;
if (fh_len < 3)
return NULL;
+ inum = fid->raw[2];
+ inum = (inum << 32) | fid->raw[1];
+
inode = ilookup5(sb, (unsigned long)(inum + fid->raw[0]),
shmem_match, fid->raw);
if (inode) {
}
EXPORT_SYMBOL_GPL(shmem_file_setup);
+void shmem_set_file(struct vm_area_struct *vma, struct file *file)
+{
+ if (vma->vm_file)
+ fput(vma->vm_file);
+ vma->vm_file = file;
+ vma->vm_ops = &shmem_vm_ops;
+ vma->vm_flags |= VM_CAN_NONLINEAR;
+}
+
/**
* shmem_zero_setup - setup a shared anonymous mapping
* @vma: the vma to be mmapped is prepared by do_mmap_pgoff
if (IS_ERR(file))
return PTR_ERR(file);
- if (vma->vm_file)
- fput(vma->vm_file);
- vma->vm_file = file;
- vma->vm_ops = &shmem_vm_ops;
- vma->vm_flags |= VM_CAN_NONLINEAR;
+ shmem_set_file(vma, file);
return 0;
}
return 0;
}
-struct bdaddr_list *hci_blacklist_lookup(struct hci_dev *hdev, bdaddr_t *bdaddr)
-{
- struct list_head *p;
-
- list_for_each(p, &hdev->blacklist) {
- struct bdaddr_list *b;
-
- b = list_entry(p, struct bdaddr_list, list);
-
- if (bacmp(bdaddr, &b->bdaddr) == 0)
- return b;
- }
-
- return NULL;
-}
-
-static int hci_blacklist_add(struct hci_dev *hdev, void __user *arg)
+static int hci_sock_blacklist_add(struct hci_dev *hdev, void __user *arg)
{
bdaddr_t bdaddr;
- struct bdaddr_list *entry;
if (copy_from_user(&bdaddr, arg, sizeof(bdaddr)))
return -EFAULT;
- if (bacmp(&bdaddr, BDADDR_ANY) == 0)
- return -EBADF;
-
- if (hci_blacklist_lookup(hdev, &bdaddr))
- return -EEXIST;
-
- entry = kzalloc(sizeof(struct bdaddr_list), GFP_KERNEL);
- if (!entry)
- return -ENOMEM;
-
- bacpy(&entry->bdaddr, &bdaddr);
-
- list_add(&entry->list, &hdev->blacklist);
-
- return 0;
+ return hci_blacklist_add(hdev, &bdaddr);
}
-int hci_blacklist_clear(struct hci_dev *hdev)
-{
- struct list_head *p, *n;
-
- list_for_each_safe(p, n, &hdev->blacklist) {
- struct bdaddr_list *b;
-
- b = list_entry(p, struct bdaddr_list, list);
-
- list_del(p);
- kfree(b);
- }
-
- return 0;
-}
-
-static int hci_blacklist_del(struct hci_dev *hdev, void __user *arg)
+static int hci_sock_blacklist_del(struct hci_dev *hdev, void __user *arg)
{
bdaddr_t bdaddr;
- struct bdaddr_list *entry;
if (copy_from_user(&bdaddr, arg, sizeof(bdaddr)))
return -EFAULT;
- if (bacmp(&bdaddr, BDADDR_ANY) == 0)
- return hci_blacklist_clear(hdev);
-
- entry = hci_blacklist_lookup(hdev, &bdaddr);
- if (!entry)
- return -ENOENT;
-
- list_del(&entry->list);
- kfree(entry);
-
- return 0;
+ return hci_blacklist_del(hdev, &bdaddr);
}
/* Ioctls that require bound socket */
case HCIBLOCKADDR:
if (!capable(CAP_NET_ADMIN))
return -EACCES;
- return hci_blacklist_add(hdev, (void __user *) arg);
+ return hci_sock_blacklist_add(hdev, (void __user *) arg);
case HCIUNBLOCKADDR:
if (!capable(CAP_NET_ADMIN))
return -EACCES;
- return hci_blacklist_del(hdev, (void __user *) arg);
+ return hci_sock_blacklist_del(hdev, (void __user *) arg);
default:
if (hdev->ioctl)
*addr_len = sizeof(*haddr);
haddr->hci_family = AF_BLUETOOTH;
haddr->hci_dev = hdev->id;
+ haddr->hci_channel= 0;
release_sock(sk);
return 0;
{
struct hci_filter *f = &hci_pi(sk)->filter;
+ memset(&uf, 0, sizeof(uf));
uf.type_mask = f->type_mask;
uf.opcode = f->opcode;
uf.event_mask[0] = *((u32 *) f->event_mask + 0);
#include <net/bluetooth/bluetooth.h>
#include <net/bluetooth/hci_core.h>
#include <net/bluetooth/l2cap.h>
+#include <net/bluetooth/smp.h>
static const struct proto_ops l2cap_sock_ops;
-
-/* ---- L2CAP timers ---- */
-static void l2cap_sock_timeout(unsigned long arg)
-{
- struct sock *sk = (struct sock *) arg;
- int reason;
-
- BT_DBG("sock %p state %d", sk, sk->sk_state);
-
- bh_lock_sock(sk);
-
- if (sock_owned_by_user(sk)) {
- /* sk is owned by user. Try again later */
- l2cap_sock_set_timer(sk, HZ / 5);
- bh_unlock_sock(sk);
- sock_put(sk);
- return;
- }
-
- if (sk->sk_state == BT_CONNECTED || sk->sk_state == BT_CONFIG)
- reason = ECONNREFUSED;
- else if (sk->sk_state == BT_CONNECT &&
- l2cap_pi(sk)->chan->sec_level != BT_SECURITY_SDP)
- reason = ECONNREFUSED;
- else
- reason = ETIMEDOUT;
-
- __l2cap_sock_close(sk, reason);
-
- bh_unlock_sock(sk);
-
- l2cap_sock_kill(sk);
- sock_put(sk);
-}
-
-void l2cap_sock_set_timer(struct sock *sk, long timeout)
-{
- BT_DBG("sk %p state %d timeout %ld", sk, sk->sk_state, timeout);
- sk_reset_timer(sk, &sk->sk_timer, jiffies + timeout);
-}
-
-void l2cap_sock_clear_timer(struct sock *sk)
-{
- BT_DBG("sock %p state %d", sk, sk->sk_state);
- sk_stop_timer(sk, &sk->sk_timer);
-}
+static void l2cap_sock_init(struct sock *sk, struct sock *parent);
+static struct sock *l2cap_sock_alloc(struct net *net, struct socket *sock, int proto, gfp_t prio);
static int l2cap_sock_bind(struct socket *sock, struct sockaddr *addr, int alen)
{
chan->sec_level = BT_SECURITY_SDP;
bacpy(&bt_sk(sk)->src, &la.l2_bdaddr);
+
+ chan->state = BT_BOUND;
sk->sk_state = BT_BOUND;
done:
lock_sock(sk);
- if ((sk->sk_type == SOCK_SEQPACKET || sk->sk_type == SOCK_STREAM)
+ if (chan->chan_type == L2CAP_CHAN_CONN_ORIENTED
&& !(la.l2_psm || la.l2_cid)) {
err = -EINVAL;
goto done;
}
/* PSM must be odd and lsb of upper byte must be 0 */
- if ((__le16_to_cpu(la.l2_psm) & 0x0101) != 0x0001 &&
- sk->sk_type != SOCK_RAW && !la.l2_cid) {
+ if ((__le16_to_cpu(la.l2_psm) & 0x0101) != 0x0001 && !la.l2_cid &&
+ chan->chan_type != L2CAP_CHAN_RAW) {
err = -EINVAL;
goto done;
}
sk->sk_max_ack_backlog = backlog;
sk->sk_ack_backlog = 0;
+
+ chan->state = BT_LISTEN;
sk->sk_state = BT_LISTEN;
done:
lock_sock_nested(sk, SINGLE_DEPTH_NESTING);
- if (sk->sk_state != BT_LISTEN) {
- err = -EBADFD;
- goto done;
- }
-
timeo = sock_rcvtimeo(sk, flags & O_NONBLOCK);
BT_DBG("sk %p timeo %ld", sk, timeo);
/* Wait for an incoming connection. (wake-one). */
add_wait_queue_exclusive(sk_sleep(sk), &wait);
- while (!(nsk = bt_accept_dequeue(sk, newsock))) {
+ while (1) {
set_current_state(TASK_INTERRUPTIBLE);
- if (!timeo) {
- err = -EAGAIN;
+
+ if (sk->sk_state != BT_LISTEN) {
+ err = -EBADFD;
break;
}
- release_sock(sk);
- timeo = schedule_timeout(timeo);
- lock_sock_nested(sk, SINGLE_DEPTH_NESTING);
+ nsk = bt_accept_dequeue(sk, newsock);
+ if (nsk)
+ break;
- if (sk->sk_state != BT_LISTEN) {
- err = -EBADFD;
+ if (!timeo) {
+ err = -EAGAIN;
break;
}
err = sock_intr_errno(timeo);
break;
}
+
+ release_sock(sk);
+ timeo = schedule_timeout(timeo);
+ lock_sock_nested(sk, SINGLE_DEPTH_NESTING);
}
- set_current_state(TASK_RUNNING);
+ __set_current_state(TASK_RUNNING);
remove_wait_queue(sk_sleep(sk), &wait);
if (err)
BT_DBG("sock %p, sk %p", sock, sk);
+ memset(la, 0, sizeof(struct sockaddr_l2));
addr->sa_family = AF_BLUETOOTH;
*len = sizeof(struct sockaddr_l2);
struct sock *sk = sock->sk;
struct l2cap_chan *chan = l2cap_pi(sk)->chan;
struct bt_security sec;
+ struct bt_power pwr;
int len, err = 0;
BT_DBG("sk %p", sk);
switch (optname) {
case BT_SECURITY:
- if (sk->sk_type != SOCK_SEQPACKET && sk->sk_type != SOCK_STREAM
- && sk->sk_type != SOCK_RAW) {
+ if (chan->chan_type != L2CAP_CHAN_CONN_ORIENTED &&
+ chan->chan_type != L2CAP_CHAN_RAW) {
err = -EINVAL;
break;
}
+ memset(&sec, 0, sizeof(sec));
sec.level = chan->sec_level;
+ if (sk->sk_state == BT_CONNECTED)
+ sec.key_size = chan->conn->hcon->enc_key_size;
+
len = min_t(unsigned int, len, sizeof(sec));
if (copy_to_user(optval, (char *) &sec, len))
err = -EFAULT;
break;
+ case BT_POWER:
+ if (sk->sk_type != SOCK_SEQPACKET && sk->sk_type != SOCK_STREAM
+ && sk->sk_type != SOCK_RAW) {
+ err = -EINVAL;
+ break;
+ }
+
+ pwr.force_active = chan->force_active;
+
+ len = min_t(unsigned int, len, sizeof(pwr));
+ if (copy_to_user(optval, (char *) &pwr, len))
+ err = -EFAULT;
+
+ break;
+
default:
err = -ENOPROTOOPT;
break;
chan->mode = opts.mode;
switch (chan->mode) {
case L2CAP_MODE_BASIC:
- chan->conf_state &= ~L2CAP_CONF_STATE2_DEVICE;
+ clear_bit(CONF_STATE2_DEVICE, &chan->conf_state);
break;
case L2CAP_MODE_ERTM:
case L2CAP_MODE_STREAMING:
struct sock *sk = sock->sk;
struct l2cap_chan *chan = l2cap_pi(sk)->chan;
struct bt_security sec;
+ struct bt_power pwr;
+ struct l2cap_conn *conn;
int len, err = 0;
u32 opt;
switch (optname) {
case BT_SECURITY:
- if (sk->sk_type != SOCK_SEQPACKET && sk->sk_type != SOCK_STREAM
- && sk->sk_type != SOCK_RAW) {
+ if (chan->chan_type != L2CAP_CHAN_CONN_ORIENTED &&
+ chan->chan_type != L2CAP_CHAN_RAW) {
err = -EINVAL;
break;
}
}
chan->sec_level = sec.level;
+
+ conn = chan->conn;
+ if (conn && chan->scid == L2CAP_CID_LE_DATA) {
+ if (!conn->hcon->out) {
+ err = -EINVAL;
+ break;
+ }
+
+ if (smp_conn_security(conn, sec.level))
+ break;
+
+ err = 0;
+ sk->sk_state = BT_CONFIG;
+ }
break;
case BT_DEFER_SETUP:
chan->flushable = opt;
break;
+ case BT_POWER:
+ if (chan->chan_type != L2CAP_CHAN_CONN_ORIENTED &&
+ chan->chan_type != L2CAP_CHAN_RAW) {
+ err = -EINVAL;
+ break;
+ }
+
+ pwr.force_active = BT_POWER_FORCE_ACTIVE_ON;
+
+ len = min_t(unsigned int, sizeof(pwr), optlen);
+ if (copy_from_user((char *) &pwr, optval, len)) {
+ err = -EFAULT;
+ break;
+ }
+ chan->force_active = pwr.force_active;
+ break;
+
default:
err = -ENOPROTOOPT;
break;
{
struct sock *sk = sock->sk;
struct l2cap_chan *chan = l2cap_pi(sk)->chan;
- struct sk_buff *skb;
- u16 control;
int err;
BT_DBG("sock %p, sk %p", sock, sk);
lock_sock(sk);
if (sk->sk_state != BT_CONNECTED) {
- err = -ENOTCONN;
- goto done;
- }
-
- /* Connectionless channel */
- if (sk->sk_type == SOCK_DGRAM) {
- skb = l2cap_create_connless_pdu(chan, msg, len);
- if (IS_ERR(skb)) {
- err = PTR_ERR(skb);
- } else {
- l2cap_do_send(chan, skb);
- err = len;
- }
- goto done;
+ release_sock(sk);
+ return -ENOTCONN;
}
- switch (chan->mode) {
- case L2CAP_MODE_BASIC:
- /* Check outgoing MTU */
- if (len > chan->omtu) {
- err = -EMSGSIZE;
- goto done;
- }
-
- /* Create a basic PDU */
- skb = l2cap_create_basic_pdu(chan, msg, len);
- if (IS_ERR(skb)) {
- err = PTR_ERR(skb);
- goto done;
- }
-
- l2cap_do_send(chan, skb);
- err = len;
- break;
-
- case L2CAP_MODE_ERTM:
- case L2CAP_MODE_STREAMING:
- /* Entire SDU fits into one PDU */
- if (len <= chan->remote_mps) {
- control = L2CAP_SDU_UNSEGMENTED;
- skb = l2cap_create_iframe_pdu(chan, msg, len, control,
- 0);
- if (IS_ERR(skb)) {
- err = PTR_ERR(skb);
- goto done;
- }
- __skb_queue_tail(&chan->tx_q, skb);
-
- if (chan->tx_send_head == NULL)
- chan->tx_send_head = skb;
-
- } else {
- /* Segment SDU into multiples PDUs */
- err = l2cap_sar_segment_sdu(chan, msg, len);
- if (err < 0)
- goto done;
- }
-
- if (chan->mode == L2CAP_MODE_STREAMING) {
- l2cap_streaming_send(chan);
- err = len;
- break;
- }
-
- if ((chan->conn_state & L2CAP_CONN_REMOTE_BUSY) &&
- (chan->conn_state & L2CAP_CONN_WAIT_F)) {
- err = len;
- break;
- }
- err = l2cap_ertm_send(chan);
-
- if (err >= 0)
- err = len;
- break;
-
- default:
- BT_DBG("bad state %1.1x", chan->mode);
- err = -EBADFD;
- }
+ err = l2cap_chan_send(chan, msg, len);
-done:
release_sock(sk);
return err;
}
static int l2cap_sock_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, size_t len, int flags)
{
struct sock *sk = sock->sk;
+ struct l2cap_pinfo *pi = l2cap_pi(sk);
+ int err;
lock_sock(sk);
if (sk->sk_state == BT_CONNECT2 && bt_sk(sk)->defer_setup) {
sk->sk_state = BT_CONFIG;
- __l2cap_connect_rsp_defer(l2cap_pi(sk)->chan);
+ __l2cap_connect_rsp_defer(pi->chan);
release_sock(sk);
return 0;
}
release_sock(sk);
if (sock->type == SOCK_STREAM)
- return bt_sock_stream_recvmsg(iocb, sock, msg, len, flags);
+ err = bt_sock_stream_recvmsg(iocb, sock, msg, len, flags);
+ else
+ err = bt_sock_recvmsg(iocb, sock, msg, len, flags);
+
+ if (pi->chan->mode != L2CAP_MODE_ERTM)
+ return err;
+
+ /* Attempt to put pending rx data in the socket buffer */
+
+ lock_sock(sk);
+
+ if (!test_bit(CONN_LOCAL_BUSY, &pi->chan->conn_state))
+ goto done;
+
+ if (pi->rx_busy_skb) {
+ if (!sock_queue_rcv_skb(sk, pi->rx_busy_skb))
+ pi->rx_busy_skb = NULL;
+ else
+ goto done;
+ }
- return bt_sock_recvmsg(iocb, sock, msg, len, flags);
+ /* Restore data flow when half of the receive buffer is
+ * available. This avoids resending large numbers of
+ * frames.
+ */
+ if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf >> 1)
+ l2cap_chan_busy(pi->chan, 0);
+
+done:
+ release_sock(sk);
+ return err;
}
/* Kill socket (only if zapped and orphan)
* Must be called on unlocked socket.
*/
-void l2cap_sock_kill(struct sock *sk)
+static void l2cap_sock_kill(struct sock *sk)
{
if (!sock_flag(sk, SOCK_ZAPPED) || sk->sk_socket)
return;
sock_put(sk);
}
-/* Must be called on unlocked socket. */
-static void l2cap_sock_close(struct sock *sk)
-{
- l2cap_sock_clear_timer(sk);
- lock_sock(sk);
- __l2cap_sock_close(sk, ECONNRESET);
- release_sock(sk);
- l2cap_sock_kill(sk);
-}
-
-static void l2cap_sock_cleanup_listen(struct sock *parent)
-{
- struct sock *sk;
-
- BT_DBG("parent %p", parent);
-
- /* Close not yet accepted channels */
- while ((sk = bt_accept_dequeue(parent, NULL)))
- l2cap_sock_close(sk);
-
- parent->sk_state = BT_CLOSED;
- sock_set_flag(parent, SOCK_ZAPPED);
-}
-
-void __l2cap_sock_close(struct sock *sk, int reason)
-{
- struct l2cap_chan *chan = l2cap_pi(sk)->chan;
- struct l2cap_conn *conn = chan->conn;
-
- BT_DBG("sk %p state %d socket %p", sk, sk->sk_state, sk->sk_socket);
-
- switch (sk->sk_state) {
- case BT_LISTEN:
- l2cap_sock_cleanup_listen(sk);
- break;
-
- case BT_CONNECTED:
- case BT_CONFIG:
- if ((sk->sk_type == SOCK_SEQPACKET ||
- sk->sk_type == SOCK_STREAM) &&
- conn->hcon->type == ACL_LINK) {
- l2cap_sock_set_timer(sk, sk->sk_sndtimeo);
- l2cap_send_disconn_req(conn, chan, reason);
- } else
- l2cap_chan_del(chan, reason);
- break;
-
- case BT_CONNECT2:
- if ((sk->sk_type == SOCK_SEQPACKET ||
- sk->sk_type == SOCK_STREAM) &&
- conn->hcon->type == ACL_LINK) {
- struct l2cap_conn_rsp rsp;
- __u16 result;
-
- if (bt_sk(sk)->defer_setup)
- result = L2CAP_CR_SEC_BLOCK;
- else
- result = L2CAP_CR_BAD_PSM;
-
- rsp.scid = cpu_to_le16(chan->dcid);
- rsp.dcid = cpu_to_le16(chan->scid);
- rsp.result = cpu_to_le16(result);
- rsp.status = cpu_to_le16(L2CAP_CS_NO_INFO);
- l2cap_send_cmd(conn, chan->ident, L2CAP_CONN_RSP,
- sizeof(rsp), &rsp);
- }
-
- l2cap_chan_del(chan, reason);
- break;
-
- case BT_CONNECT:
- case BT_DISCONN:
- l2cap_chan_del(chan, reason);
- break;
-
- default:
- sock_set_flag(sk, SOCK_ZAPPED);
- break;
- }
-}
-
static int l2cap_sock_shutdown(struct socket *sock, int how)
{
struct sock *sk = sock->sk;
err = __l2cap_wait_ack(sk);
sk->sk_shutdown = SHUTDOWN_MASK;
- l2cap_sock_clear_timer(sk);
- __l2cap_sock_close(sk, 0);
+ l2cap_chan_close(chan, 0);
if (sock_flag(sk, SOCK_LINGER) && sk->sk_lingertime)
err = bt_sock_wait_state(sk, BT_CLOSED,
return err;
}
+static struct l2cap_chan *l2cap_sock_new_connection_cb(void *data)
+{
+ struct sock *sk, *parent = data;
+
+ sk = l2cap_sock_alloc(sock_net(parent), NULL, BTPROTO_L2CAP,
+ GFP_ATOMIC);
+ if (!sk)
+ return NULL;
+
+ l2cap_sock_init(sk, parent);
+
+ return l2cap_pi(sk)->chan;
+}
+
+static int l2cap_sock_recv_cb(void *data, struct sk_buff *skb)
+{
+ int err;
+ struct sock *sk = data;
+ struct l2cap_pinfo *pi = l2cap_pi(sk);
+
+ if (pi->rx_busy_skb)
+ return -ENOMEM;
+
+ err = sock_queue_rcv_skb(sk, skb);
+
+ /* For ERTM, handle one skb that doesn't fit into the recv
+ * buffer. This is important to do because the data frames
+ * have already been acked, so the skb cannot be discarded.
+ *
+ * Notify the l2cap core that the buffer is full, so the
+ * LOCAL_BUSY state is entered and no more frames are
+ * acked and reassembled until there is buffer space
+ * available.
+ */
+ if (err < 0 && pi->chan->mode == L2CAP_MODE_ERTM) {
+ pi->rx_busy_skb = skb;
+ l2cap_chan_busy(pi->chan, 1);
+ err = 0;
+ }
+
+ return err;
+}
+
+static void l2cap_sock_close_cb(void *data)
+{
+ struct sock *sk = data;
+
+ l2cap_sock_kill(sk);
+}
+
+static void l2cap_sock_state_change_cb(void *data, int state)
+{
+ struct sock *sk = data;
+
+ sk->sk_state = state;
+}
+
+static struct l2cap_ops l2cap_chan_ops = {
+ .name = "L2CAP Socket Interface",
+ .new_connection = l2cap_sock_new_connection_cb,
+ .recv = l2cap_sock_recv_cb,
+ .close = l2cap_sock_close_cb,
+ .state_change = l2cap_sock_state_change_cb,
+};
+
static void l2cap_sock_destruct(struct sock *sk)
{
BT_DBG("sk %p", sk);
+ if (l2cap_pi(sk)->rx_busy_skb) {
+ kfree_skb(l2cap_pi(sk)->rx_busy_skb);
+ l2cap_pi(sk)->rx_busy_skb = NULL;
+ }
+
skb_queue_purge(&sk->sk_receive_queue);
skb_queue_purge(&sk->sk_write_queue);
}
-void l2cap_sock_init(struct sock *sk, struct sock *parent)
+static void l2cap_sock_init(struct sock *sk, struct sock *parent)
{
struct l2cap_pinfo *pi = l2cap_pi(sk);
struct l2cap_chan *chan = pi->chan;
sk->sk_type = parent->sk_type;
bt_sk(sk)->defer_setup = bt_sk(parent)->defer_setup;
+ chan->chan_type = pchan->chan_type;
chan->imtu = pchan->imtu;
chan->omtu = pchan->omtu;
chan->conf_state = pchan->conf_state;
chan->role_switch = pchan->role_switch;
chan->force_reliable = pchan->force_reliable;
chan->flushable = pchan->flushable;
+ chan->force_active = pchan->force_active;
} else {
+
+ switch (sk->sk_type) {
+ case SOCK_RAW:
+ chan->chan_type = L2CAP_CHAN_RAW;
+ break;
+ case SOCK_DGRAM:
+ chan->chan_type = L2CAP_CHAN_CONN_LESS;
+ break;
+ case SOCK_SEQPACKET:
+ case SOCK_STREAM:
+ chan->chan_type = L2CAP_CHAN_CONN_ORIENTED;
+ break;
+ }
+
chan->imtu = L2CAP_DEFAULT_MTU;
chan->omtu = 0;
if (!disable_ertm && sk->sk_type == SOCK_STREAM) {
chan->mode = L2CAP_MODE_ERTM;
- chan->conf_state |= L2CAP_CONF_STATE2_DEVICE;
+ set_bit(CONF_STATE2_DEVICE, &chan->conf_state);
} else {
chan->mode = L2CAP_MODE_BASIC;
}
chan->role_switch = 0;
chan->force_reliable = 0;
chan->flushable = BT_FLUSHABLE_OFF;
+ chan->force_active = BT_POWER_FORCE_ACTIVE_ON;
+
}
/* Default config options */
chan->flush_to = L2CAP_DEFAULT_FLUSH_TO;
+
+ chan->data = sk;
+ chan->ops = &l2cap_chan_ops;
}
static struct proto l2cap_proto = {
.obj_size = sizeof(struct l2cap_pinfo)
};
-struct sock *l2cap_sock_alloc(struct net *net, struct socket *sock, int proto, gfp_t prio)
+static struct sock *l2cap_sock_alloc(struct net *net, struct socket *sock, int proto, gfp_t prio)
{
struct sock *sk;
+ struct l2cap_chan *chan;
sk = sk_alloc(net, PF_BLUETOOTH, prio, &l2cap_proto);
if (!sk)
INIT_LIST_HEAD(&bt_sk(sk)->accept_q);
sk->sk_destruct = l2cap_sock_destruct;
- sk->sk_sndtimeo = msecs_to_jiffies(L2CAP_CONN_TIMEOUT);
+ sk->sk_sndtimeo = L2CAP_CONN_TIMEOUT;
sock_reset_flag(sk, SOCK_ZAPPED);
sk->sk_protocol = proto;
sk->sk_state = BT_OPEN;
- setup_timer(&sk->sk_timer, l2cap_sock_timeout, (unsigned long) sk);
+ chan = l2cap_chan_create(sk);
+ if (!chan) {
+ l2cap_sock_kill(sk);
+ return NULL;
+ }
+
+ l2cap_pi(sk)->chan = chan;
return sk;
}
int kern)
{
struct sock *sk;
- struct l2cap_chan *chan;
BT_DBG("sock %p", sock);
if (!sk)
return -ENOMEM;
- chan = l2cap_chan_create(sk);
- if (!chan) {
- l2cap_sock_kill(sk);
- return -ENOMEM;
- }
-
- l2cap_pi(sk)->chan = chan;
-
l2cap_sock_init(sk, NULL);
return 0;
}
lock_sock(sk);
- if (sk->sk_state != BT_LISTEN) {
- err = -EBADFD;
- goto done;
- }
-
if (sk->sk_type != SOCK_STREAM) {
err = -EINVAL;
goto done;
/* Wait for an incoming connection. (wake-one). */
add_wait_queue_exclusive(sk_sleep(sk), &wait);
- while (!(nsk = bt_accept_dequeue(sk, newsock))) {
+ while (1) {
set_current_state(TASK_INTERRUPTIBLE);
- if (!timeo) {
- err = -EAGAIN;
+
+ if (sk->sk_state != BT_LISTEN) {
+ err = -EBADFD;
break;
}
- release_sock(sk);
- timeo = schedule_timeout(timeo);
- lock_sock(sk);
+ nsk = bt_accept_dequeue(sk, newsock);
+ if (nsk)
+ break;
- if (sk->sk_state != BT_LISTEN) {
- err = -EBADFD;
+ if (!timeo) {
+ err = -EAGAIN;
break;
}
err = sock_intr_errno(timeo);
break;
}
+
+ release_sock(sk);
+ timeo = schedule_timeout(timeo);
+ lock_sock(sk);
}
- set_current_state(TASK_RUNNING);
+ __set_current_state(TASK_RUNNING);
remove_wait_queue(sk_sleep(sk), &wait);
if (err)
BT_DBG("sock %p, sk %p", sock, sk);
+ memset(sa, 0, sizeof(*sa));
sa->rc_family = AF_BLUETOOTH;
sa->rc_channel = rfcomm_pi(sk)->channel;
if (peer)
{
struct sock *sk = sock->sk;
struct bt_security sec;
- int len, err = 0;
+ int err = 0;
+ size_t len;
u32 opt;
BT_DBG("sk %p", sk);
static int rfcomm_sock_getsockopt_old(struct socket *sock, int optname, char __user *optval, int __user *optlen)
{
struct sock *sk = sock->sk;
- struct sock *l2cap_sk;
struct rfcomm_conninfo cinfo;
struct l2cap_conn *conn = l2cap_pi(sk)->chan->conn;
int len, err = 0;
break;
}
- l2cap_sk = rfcomm_pi(sk)->dlc->session->sock->sk;
memset(&cinfo, 0, sizeof(cinfo));
cinfo.hci_handle = conn->hcon->handle;
#include <linux/crypto.h>
#include <linux/time.h>
#include <linux/slab.h>
+#include <linux/uid_stat.h>
#include <net/icmp.h>
#include <net/tcp.h>
#include <net/xfrm.h>
#include <net/ip.h>
+#include <net/ip6_route.h>
+#include <net/ipv6.h>
+#include <net/transp_v6.h>
#include <net/netdma.h>
#include <net/sock.h>
old_size_goal + mss_now > xmit_size_goal)) {
xmit_size_goal = old_size_goal;
} else {
- tp->xmit_size_goal_segs = xmit_size_goal / mss_now;
+ tp->xmit_size_goal_segs =
+ min_t(u16, xmit_size_goal / mss_now,
+ sk->sk_gso_max_segs);
xmit_size_goal = tp->xmit_size_goal_segs * mss_now;
}
}
wait_for_sndbuf:
set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
wait_for_memory:
- if (copied)
- tcp_push(sk, flags & ~MSG_MORE, mss_now, TCP_NAGLE_PUSH);
+ tcp_push(sk, flags & ~MSG_MORE, mss_now, TCP_NAGLE_PUSH);
if ((err = sk_stream_wait_memory(sk, &timeo)) != 0)
goto do_error;
if (copied)
tcp_push(sk, flags, mss_now, tp->nonagle);
release_sock(sk);
+
+ if (copied > 0)
+ uid_stat_tcp_snd(current_uid(), copied);
return copied;
do_fault:
tcp_rcv_space_adjust(sk);
/* Clean up data we have read: This will do ACK frames. */
- if (copied > 0)
+ if (copied > 0) {
tcp_cleanup_rbuf(sk, copied);
+ uid_stat_tcp_rcv(current_uid(), copied);
+ }
+
return copied;
}
EXPORT_SYMBOL(tcp_read_sock);
}
#ifdef CONFIG_NET_DMA
- if (tp->ucopy.dma_chan)
- dma_async_memcpy_issue_pending(tp->ucopy.dma_chan);
+ if (tp->ucopy.dma_chan) {
+ if (tp->rcv_wnd == 0 &&
+ !skb_queue_empty(&sk->sk_async_wait_queue)) {
+ tcp_service_net_dma(sk, true);
+ tcp_cleanup_rbuf(sk, copied);
+ } else
+ dma_async_memcpy_issue_pending(tp->ucopy.dma_chan);
+ }
#endif
if (copied >= target) {
/* Do not sleep, just process backlog. */
tcp_cleanup_rbuf(sk, copied);
release_sock(sk);
+
+ if (copied > 0)
+ uid_stat_tcp_rcv(current_uid(), copied);
return copied;
out:
recv_urg:
err = tcp_recv_urg(sk, msg, len, flags);
+ if (err > 0)
+ uid_stat_tcp_rcv(current_uid(), err);
goto out;
}
EXPORT_SYMBOL(tcp_recvmsg);
/* Cap the max timeout in ms TCP will retry/retrans
* before giving up and aborting (ETIMEDOUT) a connection.
*/
- icsk->icsk_user_timeout = msecs_to_jiffies(val);
+ if (val < 0)
+ err = -EINVAL;
+ else
+ icsk->icsk_user_timeout = msecs_to_jiffies(val);
break;
default:
err = -ENOPROTOOPT;
{
struct sk_buff *skb = NULL;
unsigned long limit;
- int i, max_share, cnt;
+ int i, max_rshare, max_wshare, cnt;
unsigned long jiffy = jiffies;
BUILD_BUG_ON(sizeof(struct tcp_skb_cb) > sizeof(skb->cb));
/* Set per-socket limits to no more than 1/128 the pressure threshold */
limit = ((unsigned long)sysctl_tcp_mem[1]) << (PAGE_SHIFT - 7);
- max_share = min(4UL*1024*1024, limit);
+ max_wshare = min(4UL*1024*1024, limit);
+ max_rshare = min(6UL*1024*1024, limit);
sysctl_tcp_wmem[0] = SK_MEM_QUANTUM;
sysctl_tcp_wmem[1] = 16*1024;
- sysctl_tcp_wmem[2] = max(64*1024, max_share);
+ sysctl_tcp_wmem[2] = max(64*1024, max_wshare);
sysctl_tcp_rmem[0] = SK_MEM_QUANTUM;
sysctl_tcp_rmem[1] = 87380;
- sysctl_tcp_rmem[2] = max(87380, max_share);
+ sysctl_tcp_rmem[2] = max(87380, max_rshare);
printk(KERN_INFO "TCP: Hash tables configured "
"(established %u bind %u)\n",
tcp_secret_retiring = &tcp_secret_two;
tcp_secret_secondary = &tcp_secret_two;
}
+
+static int tcp_is_local(struct net *net, __be32 addr) {
+ struct rtable *rt;
+ struct flowi4 fl4 = { .daddr = addr };
+ rt = ip_route_output_key(net, &fl4);
+ if (IS_ERR_OR_NULL(rt))
+ return 0;
+ return rt->dst.dev && (rt->dst.dev->flags & IFF_LOOPBACK);
+}
+
+#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+static int tcp_is_local6(struct net *net, struct in6_addr *addr) {
+ struct rt6_info *rt6 = rt6_lookup(net, addr, addr, 0, 0);
+ return rt6 && rt6->rt6i_dev && (rt6->rt6i_dev->flags & IFF_LOOPBACK);
+}
+#endif
+
+/*
+ * tcp_nuke_addr - destroy all sockets on the given local address
+ * if local address is the unspecified address (0.0.0.0 or ::), destroy all
+ * sockets with local addresses that are not configured.
+ */
+int tcp_nuke_addr(struct net *net, struct sockaddr *addr)
+{
+ int family = addr->sa_family;
+ unsigned int bucket;
+
+ struct in_addr *in;
+#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+ struct in6_addr *in6;
+#endif
+ if (family == AF_INET) {
+ in = &((struct sockaddr_in *)addr)->sin_addr;
+#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+ } else if (family == AF_INET6) {
+ in6 = &((struct sockaddr_in6 *)addr)->sin6_addr;
+#endif
+ } else {
+ return -EAFNOSUPPORT;
+ }
+
+ for (bucket = 0; bucket < tcp_hashinfo.ehash_mask; bucket++) {
+ struct hlist_nulls_node *node;
+ struct sock *sk;
+ spinlock_t *lock = inet_ehash_lockp(&tcp_hashinfo, bucket);
+
+restart:
+ spin_lock_bh(lock);
+ sk_nulls_for_each(sk, node, &tcp_hashinfo.ehash[bucket].chain) {
+ struct inet_sock *inet = inet_sk(sk);
+
+ if (sysctl_ip_dynaddr && sk->sk_state == TCP_SYN_SENT)
+ continue;
+ if (sock_flag(sk, SOCK_DEAD))
+ continue;
+
+ if (family == AF_INET) {
+ __be32 s4 = inet->inet_rcv_saddr;
+ if (s4 == LOOPBACK4_IPV6)
+ continue;
+
+ if (in->s_addr != s4 &&
+ !(in->s_addr == INADDR_ANY &&
+ !tcp_is_local(net, s4)))
+ continue;
+ }
+
+#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+ if (family == AF_INET6) {
+ struct in6_addr *s6;
+ if (!inet->pinet6)
+ continue;
+
+ s6 = &inet->pinet6->rcv_saddr;
+ if (ipv6_addr_type(s6) == IPV6_ADDR_MAPPED)
+ continue;
+
+ if (!ipv6_addr_equal(in6, s6) &&
+ !(ipv6_addr_equal(in6, &in6addr_any) &&
+ !tcp_is_local6(net, s6)))
+ continue;
+ }
+#endif
+
+ sock_hold(sk);
+ spin_unlock_bh(lock);
+
+ local_bh_disable();
+ bh_lock_sock(sk);
+ sk->sk_err = ETIMEDOUT;
+ sk->sk_error_report(sk);
+
+ tcp_done(sk);
+ bh_unlock_sock(sk);
+ local_bh_enable();
+ sock_put(sk);
+
+ goto restart;
+ }
+ spin_unlock_bh(lock);
+ }
+
+ return 0;
+}
struct net_device *dev;
struct inet6_dev *idev;
- rcu_read_lock();
- for_each_netdev_rcu(net, dev) {
+ for_each_netdev(net, dev) {
idev = __in6_dev_get(dev);
if (idev) {
int changed = (!idev->cnf.forwarding) ^ (!newf);
dev_forward_change(idev);
}
}
- rcu_read_unlock();
}
static int addrconf_fixup_forwarding(struct ctl_table *table, int *p, int old)
{
struct inet6_dev *idev = ifp->idev;
struct in6_addr addr, *tmpaddr;
- unsigned long tmp_prefered_lft, tmp_valid_lft, tmp_cstamp, tmp_tstamp, age;
+ unsigned long tmp_prefered_lft, tmp_valid_lft, tmp_tstamp, age;
unsigned long regen_advance;
int tmp_plen;
int ret = 0;
int max_addresses;
u32 addr_flags;
+ unsigned long now = jiffies;
write_lock(&idev->lock);
if (ift) {
goto out;
}
memcpy(&addr.s6_addr[8], idev->rndid, 8);
- age = (jiffies - ifp->tstamp) / HZ;
+ age = (now - ifp->tstamp) / HZ;
tmp_valid_lft = min_t(__u32,
ifp->valid_lft,
idev->cnf.temp_valid_lft + age);
idev->cnf.max_desync_factor);
tmp_plen = ifp->prefix_len;
max_addresses = idev->cnf.max_addresses;
- tmp_cstamp = ifp->cstamp;
tmp_tstamp = ifp->tstamp;
spin_unlock_bh(&ifp->lock);
ift->ifpub = ifp;
ift->valid_lft = tmp_valid_lft;
ift->prefered_lft = tmp_prefered_lft;
- ift->cstamp = tmp_cstamp;
+ ift->cstamp = now;
ift->tstamp = tmp_tstamp;
spin_unlock_bh(&ift->lock);
#ifdef CONFIG_IPV6_PRIVACY
read_lock_bh(&in6_dev->lock);
/* update all temporary addresses in the list */
- list_for_each_entry(ift, &in6_dev->tempaddr_list, tmp_list) {
- /*
- * When adjusting the lifetimes of an existing
- * temporary address, only lower the lifetimes.
- * Implementations must not increase the
- * lifetimes of an existing temporary address
- * when processing a Prefix Information Option.
- */
+ list_for_each_entry(ift, &in6_dev->tempaddr_list,
+ tmp_list) {
+ int age, max_valid, max_prefered;
+
if (ifp != ift->ifpub)
continue;
+ /*
+ * RFC 4941 section 3.3:
+ * If a received option will extend the lifetime
+ * of a public address, the lifetimes of
+ * temporary addresses should be extended,
+ * subject to the overall constraint that no
+ * temporary addresses should ever remain
+ * "valid" or "preferred" for a time longer than
+ * (TEMP_VALID_LIFETIME) or
+ * (TEMP_PREFERRED_LIFETIME - DESYNC_FACTOR),
+ * respectively.
+ */
+ age = (now - ift->cstamp) / HZ;
+ max_valid = in6_dev->cnf.temp_valid_lft - age;
+ if (max_valid < 0)
+ max_valid = 0;
+
+ max_prefered = in6_dev->cnf.temp_prefered_lft -
+ in6_dev->cnf.max_desync_factor -
+ age;
+ if (max_prefered < 0)
+ max_prefered = 0;
+
+ if (valid_lft > max_valid)
+ valid_lft = max_valid;
+
+ if (prefered_lft > max_prefered)
+ prefered_lft = max_prefered;
+
spin_lock(&ift->lock);
flags = ift->flags;
- if (ift->valid_lft > valid_lft &&
- ift->valid_lft - valid_lft > (jiffies - ift->tstamp) / HZ)
- ift->valid_lft = valid_lft + (jiffies - ift->tstamp) / HZ;
- if (ift->prefered_lft > prefered_lft &&
- ift->prefered_lft - prefered_lft > (jiffies - ift->tstamp) / HZ)
- ift->prefered_lft = prefered_lft + (jiffies - ift->tstamp) / HZ;
+ ift->valid_lft = valid_lft;
+ ift->prefered_lft = prefered_lft;
+ ift->tstamp = now;
+ if (prefered_lft > 0)
+ ift->flags &= ~IFA_F_DEPRECATED;
+
spin_unlock(&ift->lock);
if (!(flags&IFA_F_TENTATIVE))
ipv6_ifa_notify(0, ift);
if ((create || list_empty(&in6_dev->tempaddr_list)) && in6_dev->cnf.use_tempaddr > 0) {
/*
- * When a new public address is created as described in [ADDRCONF],
- * also create a new temporary address. Also create a temporary
- * address if it's enabled but no temporary address currently exists.
+ * When a new public address is created as
+ * described in [ADDRCONF], also create a new
+ * temporary address. Also create a temporary
+ * address if it's enabled but no temporary
+ * address currently exists.
*/
read_unlock_bh(&in6_dev->lock);
ipv6_create_tempaddr(ifp, NULL);
{
struct rt6_info *rt = dst_alloc(ops, dev, 0, 0, flags);
- memset(&rt->rt6i_table, 0, sizeof(*rt) - sizeof(struct dst_entry));
+ if (rt != NULL)
+ memset(&rt->rt6i_table, 0,
+ sizeof(*rt) - sizeof(struct dst_entry));
return rt;
}
struct fib6_table *table;
struct net *net = dev_net(rt->rt6i_dev);
- if (rt == net->ipv6.ip6_null_entry)
- return -ENOENT;
+ if (rt == net->ipv6.ip6_null_entry) {
+ err = -ENOENT;
+ goto out;
+ }
table = rt->rt6i_table;
write_lock_bh(&table->tb6_lock);
-
err = fib6_del(rt, info);
- dst_release(&rt->dst);
-
write_unlock_bh(&table->tb6_lock);
+ out:
+ dst_release(&rt->dst);
return err;
}
net->ipv6.sysctl.ip6_rt_mtu_expires = 10*60*HZ;
net->ipv6.sysctl.ip6_rt_min_advmss = IPV6_MIN_MTU - 20 - 40;
- #ifdef CONFIG_PROC_FS
- proc_net_fops_create(net, "ipv6_route", 0, &ipv6_route_proc_fops);
- proc_net_fops_create(net, "rt6_stats", S_IRUGO, &rt6_stats_seq_fops);
- #endif
net->ipv6.ip6_rt_gc_expire = 30*HZ;
ret = 0;
static void __net_exit ip6_route_net_exit(struct net *net)
{
- #ifdef CONFIG_PROC_FS
- proc_net_remove(net, "ipv6_route");
- proc_net_remove(net, "rt6_stats");
- #endif
kfree(net->ipv6.ip6_null_entry);
#ifdef CONFIG_IPV6_MULTIPLE_TABLES
kfree(net->ipv6.ip6_prohibit_entry);
dst_entries_destroy(&net->ipv6.ip6_dst_ops);
}
+ static int __net_init ip6_route_net_init_late(struct net *net)
+ {
+ #ifdef CONFIG_PROC_FS
+ proc_net_fops_create(net, "ipv6_route", 0, &ipv6_route_proc_fops);
+ proc_net_fops_create(net, "rt6_stats", S_IRUGO, &rt6_stats_seq_fops);
+ #endif
+ return 0;
+ }
+
+ static void __net_exit ip6_route_net_exit_late(struct net *net)
+ {
+ #ifdef CONFIG_PROC_FS
+ proc_net_remove(net, "ipv6_route");
+ proc_net_remove(net, "rt6_stats");
+ #endif
+ }
+
static struct pernet_operations ip6_route_net_ops = {
.init = ip6_route_net_init,
.exit = ip6_route_net_exit,
};
+ static struct pernet_operations ip6_route_net_late_ops = {
+ .init = ip6_route_net_init_late,
+ .exit = ip6_route_net_exit_late,
+ };
+
static struct notifier_block ip6_route_dev_notifier = {
.notifier_call = ip6_route_dev_notify,
.priority = 0,
if (ret)
goto xfrm6_init;
+ ret = register_pernet_subsys(&ip6_route_net_late_ops);
+ if (ret)
+ goto fib6_rules_init;
+
ret = -ENOBUFS;
if (__rtnl_register(PF_INET6, RTM_NEWROUTE, inet6_rtm_newroute, NULL) ||
__rtnl_register(PF_INET6, RTM_DELROUTE, inet6_rtm_delroute, NULL) ||
__rtnl_register(PF_INET6, RTM_GETROUTE, inet6_rtm_getroute, NULL))
- goto fib6_rules_init;
+ goto out_register_late_subsys;
ret = register_netdevice_notifier(&ip6_route_dev_notifier);
if (ret)
- goto fib6_rules_init;
+ goto out_register_late_subsys;
out:
return ret;
+ out_register_late_subsys:
+ unregister_pernet_subsys(&ip6_route_net_late_ops);
fib6_rules_init:
fib6_rules_cleanup();
xfrm6_init:
void ip6_route_cleanup(void)
{
unregister_netdevice_notifier(&ip6_route_dev_notifier);
+ unregister_pernet_subsys(&ip6_route_net_late_ops);
fib6_rules_cleanup();
xfrm6_fini();
fib6_gc_cleanup();
int i;
u16 ifmodes = wiphy->interface_modes;
+ if (WARN_ON((wiphy->wowlan.flags & WIPHY_WOWLAN_GTK_REKEY_FAILURE) &&
+ !(wiphy->wowlan.flags & WIPHY_WOWLAN_SUPPORTS_GTK_REKEY)))
+ return -EINVAL;
+
+ if (WARN_ON(wiphy->ap_sme_capa &&
+ !(wiphy->flags & WIPHY_FLAG_HAVE_AP_SME)))
+ return -EINVAL;
+
if (WARN_ON(wiphy->addresses && !wiphy->n_addresses))
return -EINVAL;
*/
synchronize_rcu();
INIT_LIST_HEAD(&wdev->list);
+ /*
+ * Ensure that all events have been processed and
+ * freed.
+ */
+ cfg80211_process_wdev_events(wdev);
break;
case NETDEV_PRE_UP:
if (!(wdev->wiphy->interface_modes & BIT(wdev->iftype)))
int opencount; /* also protected by devlist_mtx */
wait_queue_head_t dev_wait;
+ u32 ap_beacons_nlpid;
+
/* BSSes/scanning */
spinlock_t bss_lock;
struct list_head bss_list;
struct net_device *dev, enum nl80211_iftype ntype,
u32 *flags, struct vif_params *params);
void cfg80211_process_rdev_events(struct cfg80211_registered_device *rdev);
+ void cfg80211_process_wdev_events(struct wireless_dev *wdev);
int cfg80211_can_change_interface(struct cfg80211_registered_device *rdev,
struct wireless_dev *wdev,
struct reg_regdb_search_request *request;
const struct ieee80211_regdomain *curdom, *regdom;
int i, r;
+ bool set_reg = false;
+
+ mutex_lock(&cfg80211_mutex);
mutex_lock(®_regdb_search_mutex);
while (!list_empty(®_regdb_search_list)) {
r = reg_copy_regd(®dom, curdom);
if (r)
break;
- mutex_lock(&cfg80211_mutex);
- set_regdom(regdom);
- mutex_unlock(&cfg80211_mutex);
+ set_reg = true;
break;
}
}
kfree(request);
}
mutex_unlock(®_regdb_search_mutex);
+
+ if (set_reg)
+ set_regdom(regdom);
+
+ mutex_unlock(&cfg80211_mutex);
}
static DECLARE_WORK(reg_regdb_work, reg_regdb_search);
schedule_work(®_regdb_work);
}
+
+ /* Feel free to add any other sanity checks here */
+ static void reg_regdb_size_check(void)
+ {
+ /* We should ideally BUILD_BUG_ON() but then random builds would fail */
+ WARN_ONCE(!reg_regdb_size, "db.txt is empty, you should update it...");
+ }
#else
+ static inline void reg_regdb_size_check(void) {}
static inline void reg_regdb_query(const char *alpha2) {}
#endif /* CONFIG_CFG80211_INTERNAL_REGDB */
spin_unlock(®_requests_lock);
if (last_request->initiator == NL80211_REGDOM_SET_BY_USER)
- cancel_delayed_work_sync(®_timeout);
+ cancel_delayed_work(®_timeout);
if (need_more_processing)
schedule_work(®_work);
static void restore_regulatory_settings(bool reset_user)
{
char alpha2[2];
+ char world_alpha2[2];
struct reg_beacon *reg_beacon, *btmp;
struct regulatory_request *reg_request, *tmp;
LIST_HEAD(tmp_reg_req_list);
/* First restore to the basic regulatory settings */
cfg80211_regdomain = cfg80211_world_regdom;
+ world_alpha2[0] = cfg80211_regdomain->alpha2[0];
+ world_alpha2[1] = cfg80211_regdomain->alpha2[1];
mutex_unlock(®_mutex);
mutex_unlock(&cfg80211_mutex);
- regulatory_hint_core(cfg80211_regdomain->alpha2);
+ regulatory_hint_core(world_alpha2);
/*
* This restores the ieee80211_regdom module parameter
spin_lock_init(®_requests_lock);
spin_lock_init(®_pending_beacons_lock);
+ reg_regdb_size_check();
+
cfg80211_regdomain = cfg80211_world_regdom;
user_alpha2[0] = '9';
BUG();
}
xdst = dst_alloc(dst_ops, NULL, 0, 0, 0);
- memset(&xdst->u.rt6.rt6i_table, 0, sizeof(*xdst) - sizeof(struct dst_entry));
- xfrm_policy_put_afinfo(afinfo);
- if (likely(xdst))
+ if (likely(xdst)) {
+ memset(&xdst->u.rt6.rt6i_table, 0,
+ sizeof(*xdst) - sizeof(struct dst_entry));
xdst->flo.ops = &xfrm_bundle_fc_ops;
- else
+ } else
xdst = ERR_PTR(-ENOBUFS);
+ xfrm_policy_put_afinfo(afinfo);
+
return xdst;
}
if (!afinfo) {
dst_release(dst_orig);
- ret = ERR_PTR(-EINVAL);
+ return ERR_PTR(-EINVAL);
} else {
ret = afinfo->blackhole_route(net, dst_orig);
}
}
ok:
xfrm_pols_put(pols, drop_pols);
+ if (dst && dst->xfrm &&
+ dst->xfrm->props.mode == XFRM_MODE_TUNNEL)
+ dst->flags |= DST_XFRM_TUNNEL;
return dst;
nopol:
# Usage: cflags-y += $(call as-instr,instr,option1,option2)
as-instr = $(call try-run,\
- /bin/echo -e "$(1)" | $(CC) $(KBUILD_AFLAGS) -c -xassembler -o "$$TMP" -,$(2),$(3))
+ printf "%b\n" "$(1)" | $(CC) $(KBUILD_AFLAGS) -c -xassembler -o "$$TMP" -,$(2),$(3))
# cc-option
# Usage: cflags-y += $(call cc-option,-march=winchip-c6,-march=i586)
# >$< substitution to preserve $ when reloading .cmd file
# note: when using inline perl scripts [perl -e '...$$t=1;...']
# in $(cmd_xxx) double $$ your perl vars
- make-cmd = $(subst \#,\\\#,$(subst $$,$$$$,$(call escsq,$(cmd_$(1)))))
+ make-cmd = $(subst \\,\\\\,$(subst \#,\\\#,$(subst $$,$$$$,$(call escsq,$(cmd_$(1))))))
# Find any prerequisites that is newer than target or that does not exist.
# PHONY targets skipped in both cases.