Re: Linux 2.6.25.18

From: Greg KH
Date: Wed Oct 08 2008 - 23:13:36 EST

diff --git a/Makefile b/Makefile
index cb23e66..5a92857 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
VERSION = 2
PATCHLEVEL = 6
SUBLEVEL = 25
-EXTRAVERSION = .17
+EXTRAVERSION = .18
NAME = Funky Weasel is Jiggy wit it

# *DOCUMENTATION*
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index 36652ea..bec6496 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -222,8 +222,8 @@ static void hpet_legacy_clockevent_register(void)
/* Calculate the min / max delta */
hpet_clockevent.max_delta_ns = clockevent_delta2ns(0x7FFFFFFF,
&hpet_clockevent);
- hpet_clockevent.min_delta_ns = clockevent_delta2ns(0x30,
- &hpet_clockevent);
+ /* 5 usec minimum reprogramming delta. */
+ hpet_clockevent.min_delta_ns = 5000;

/*
* Start hpet with the boot cpu mask and make it
@@ -282,15 +282,22 @@ static void hpet_legacy_set_mode(enum clock_event_mode mode,
}

static int hpet_legacy_next_event(unsigned long delta,
- struct clock_event_device *evt)
+ struct clock_event_device *evt)
{
- unsigned long cnt;
+ u32 cnt;

cnt = hpet_readl(HPET_COUNTER);
- cnt += delta;
+ cnt += (u32) delta;
hpet_writel(cnt, HPET_T0_CMP);

- return ((long)(hpet_readl(HPET_COUNTER) - cnt ) > 0) ? -ETIME : 0;
+ /*
+ * We need to read back the CMP register to make sure that
+ * what we wrote hit the chip before we compare it to the
+ * counter.
+ */
+ WARN_ON((u32)hpet_readl(HPET_T0_CMP) != cnt);
+
+ return (s32)((u32)hpet_readl(HPET_COUNTER) - cnt) >= 0 ? -ETIME : 0;
}

/*
diff --git a/arch/x86/kernel/io_delay.c b/arch/x86/kernel/io_delay.c
index 5921e5f..84ec3cd 100644
--- a/arch/x86/kernel/io_delay.c
+++ b/arch/x86/kernel/io_delay.c
@@ -92,6 +92,14 @@ static struct dmi_system_id __initdata io_delay_0xed_port_dmi_table[] = {
DMI_MATCH(DMI_BOARD_NAME, "30BF")
}
},
+ {
+ .callback = dmi_io_delay_0xed_port,
+ .ident = "Presario F700",
+ .matches = {
+ DMI_MATCH(DMI_BOARD_VENDOR, "Quanta"),
+ DMI_MATCH(DMI_BOARD_NAME, "30D3")
+ }
+ },
{ }
};

diff --git a/arch/x86/kernel/vmi_32.c b/arch/x86/kernel/vmi_32.c
index 12affe1..72f9826 100644
--- a/arch/x86/kernel/vmi_32.c
+++ b/arch/x86/kernel/vmi_32.c
@@ -234,7 +234,7 @@ static void vmi_write_ldt_entry(struct desc_struct *dt, int entry,
const void *desc)
{
u32 *ldt_entry = (u32 *)desc;
- vmi_ops.write_idt_entry(dt, entry, ldt_entry[0], ldt_entry[1]);
+ vmi_ops.write_ldt_entry(dt, entry, ldt_entry[0], ldt_entry[1]);
}

static void vmi_load_sp0(struct tss_struct *tss,
diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c
index 7222a18..a9b8796 100644
--- a/drivers/acpi/ec.c
+++ b/drivers/acpi/ec.c
@@ -228,6 +228,8 @@ static int acpi_ec_wait(struct acpi_ec *ec, enum ec_event event, int force_poll)
if (acpi_ec_check_status(ec, event))
goto end;
}
+ if (acpi_ec_check_status(ec,event))
+ return 0;
}
pr_err(PREFIX "acpi_ec_wait timeout,"
" status = %d, expect_event = %d\n",
diff --git a/drivers/acpi/processor_perflib.c b/drivers/acpi/processor_perflib.c
index 42fb635..87b9a17 100644
--- a/drivers/acpi/processor_perflib.c
+++ b/drivers/acpi/processor_perflib.c
@@ -70,7 +70,7 @@ static DEFINE_MUTEX(performance_mutex);
* 0 -> cpufreq low level drivers initialized -> consider _PPC values
* 1 -> ignore _PPC totally -> forced by user through boot param
*/
-static unsigned int ignore_ppc = -1;
+static int ignore_ppc = -1;
module_param(ignore_ppc, uint, 0644);
MODULE_PARM_DESC(ignore_ppc, "If the frequency of your machine gets wrongly" \
"limited by BIOS, this should help");
diff --git a/drivers/i2c/i2c-dev.c b/drivers/i2c/i2c-dev.c
index 393e679..342255b 100644
--- a/drivers/i2c/i2c-dev.c
+++ b/drivers/i2c/i2c-dev.c
@@ -574,8 +574,10 @@ static int __init i2c_dev_init(void)
goto out;

i2c_dev_class = class_create(THIS_MODULE, "i2c-dev");
- if (IS_ERR(i2c_dev_class))
+ if (IS_ERR(i2c_dev_class)) {
+ res = PTR_ERR(i2c_dev_class);
goto out_unreg_chrdev;
+ }

res = i2c_add_driver(&i2cdev_driver);
if (res)
diff --git a/drivers/mmc/card/block.c b/drivers/mmc/card/block.c
index 91ded3e..3318642 100644
--- a/drivers/mmc/card/block.c
+++ b/drivers/mmc/card/block.c
@@ -103,8 +103,10 @@ static int mmc_blk_open(struct inode *inode, struct file *filp)
check_disk_change(inode->i_bdev);
ret = 0;

- if ((filp->f_mode & FMODE_WRITE) && md->read_only)
+ if ((filp->f_mode & FMODE_WRITE) && md->read_only) {
+ mmc_blk_put(md);
ret = -EROFS;
+ }
}

return ret;
diff --git a/drivers/net/niu.c b/drivers/net/niu.c
index d11ba61..5fd6a65 100644
--- a/drivers/net/niu.c
+++ b/drivers/net/niu.c
@@ -5230,6 +5230,56 @@ static void niu_netif_start(struct niu *np)
niu_enable_interrupts(np, 1);
}

+static void niu_reset_buffers(struct niu *np)
+{
+ int i, j, k, err;
+
+ if (np->rx_rings) {
+ for (i = 0; i < np->num_rx_rings; i++) {
+ struct rx_ring_info *rp = &np->rx_rings[i];
+
+ for (j = 0, k = 0; j < MAX_RBR_RING_SIZE; j++) {
+ struct page *page;
+
+ page = rp->rxhash[j];
+ while (page) {
+ struct page *next =
+ (struct page *) page->mapping;
+ u64 base = page->index;
+ base = base >> RBR_DESCR_ADDR_SHIFT;
+ rp->rbr[k++] = cpu_to_le32(base);
+ page = next;
+ }
+ }
+ for (; k < MAX_RBR_RING_SIZE; k++) {
+ err = niu_rbr_add_page(np, rp, GFP_ATOMIC, k);
+ if (unlikely(err))
+ break;
+ }
+
+ rp->rbr_index = rp->rbr_table_size - 1;
+ rp->rcr_index = 0;
+ rp->rbr_pending = 0;
+ rp->rbr_refill_pending = 0;
+ }
+ }
+ if (np->tx_rings) {
+ for (i = 0; i < np->num_tx_rings; i++) {
+ struct tx_ring_info *rp = &np->tx_rings[i];
+
+ for (j = 0; j < MAX_TX_RING_SIZE; j++) {
+ if (rp->tx_buffs[j].skb)
+ (void) release_tx_packet(np, rp, j);
+ }
+
+ rp->pending = MAX_TX_RING_SIZE;
+ rp->prod = 0;
+ rp->cons = 0;
+ rp->wrap_bit = 0;
+ }
+ }
+}
+
static void niu_reset_task(struct work_struct *work)
{
struct niu *np = container_of(work, struct niu, reset_task);
@@ -5252,6 +5302,12 @@ static void niu_reset_task(struct work_struct *work)

niu_stop_hw(np);

+ spin_unlock_irqrestore(&np->lock, flags);
+
+ niu_reset_buffers(np);
+
+ spin_lock_irqsave(&np->lock, flags);
+
err = niu_init_hw(np);
if (!err) {
np->timer.expires = jiffies + HZ;
diff --git a/drivers/spi/pxa2xx_spi.c b/drivers/spi/pxa2xx_spi.c
index 147e26a..1dcc79f 100644
--- a/drivers/spi/pxa2xx_spi.c
+++ b/drivers/spi/pxa2xx_spi.c
@@ -48,9 +48,10 @@ MODULE_ALIAS("platform:pxa2xx-spi");

#define MAX_BUSES 3

-#define DMA_INT_MASK (DCSR_ENDINTR | DCSR_STARTINTR | DCSR_BUSERR)
-#define RESET_DMA_CHANNEL (DCSR_NODESC | DMA_INT_MASK)
-#define IS_DMA_ALIGNED(x) (((u32)(x)&0x07)==0)
+#define DMA_INT_MASK (DCSR_ENDINTR | DCSR_STARTINTR | DCSR_BUSERR)
+#define RESET_DMA_CHANNEL (DCSR_NODESC | DMA_INT_MASK)
+#define IS_DMA_ALIGNED(x) ((((u32)(x)) & 0x07) == 0)
+#define MAX_DMA_LEN 8191

/*
* for testing SSCR1 changes that require SSP restart, basically
@@ -142,7 +143,6 @@ struct driver_data {
size_t tx_map_len;
u8 n_bytes;
u32 dma_width;
- int cs_change;
int (*write)(struct driver_data *drv_data);
int (*read)(struct driver_data *drv_data);
irqreturn_t (*transfer_handler)(struct driver_data *drv_data);
@@ -404,8 +404,45 @@ static void giveback(struct driver_data *drv_data)
struct spi_transfer,
transfer_list);

+ /* Delay if requested before any change in chip select */
+ if (last_transfer->delay_usecs)
+ udelay(last_transfer->delay_usecs);
+
+ /* Drop chip select UNLESS cs_change is true or we are returning
+ * a message with an error, or next message is for another chip
+ */
if (!last_transfer->cs_change)
drv_data->cs_control(PXA2XX_CS_DEASSERT);
+ else {
+ struct spi_message *next_msg;
+
+ /* Holding of cs was hinted, but we need to make sure
+ * the next message is for the same chip. Don't waste
+ * time with the following tests unless this was hinted.
+ *
+ * We cannot postpone this until pump_messages, because
+ * after calling msg->complete (below) the driver that
+ * sent the current message could be unloaded, which
+ * could invalidate the cs_control() callback...
+ */
+
+ /* get a pointer to the next message, if any */
+ spin_lock_irqsave(&drv_data->lock, flags);
+ if (list_empty(&drv_data->queue))
+ next_msg = NULL;
+ else
+ next_msg = list_entry(drv_data->queue.next,
+ struct spi_message, queue);
+ spin_unlock_irqrestore(&drv_data->lock, flags);
+
+ /* see if the next and current messages point
+ * to the same chip
+ */
+ if (next_msg && next_msg->spi != msg->spi)
+ next_msg = NULL;
+ if (!next_msg || msg->state == ERROR_STATE)
+ drv_data->cs_control(PXA2XX_CS_DEASSERT);
+ }

msg->state = NULL;
if (msg->complete)
@@ -488,10 +525,9 @@ static void dma_transfer_complete(struct driver_data *drv_data)
msg->actual_length += drv_data->len -
(drv_data->rx_end - drv_data->rx);

- /* Release chip select if requested, transfer delays are
- * handled in pump_transfers */
- if (drv_data->cs_change)
- drv_data->cs_control(PXA2XX_CS_DEASSERT);
+ /* Transfer delays and chip select release are
+ * handled in pump_transfers or giveback
+ */

/* Move to next transfer */
msg->state = next_transfer(drv_data);
@@ -600,10 +636,9 @@ static void int_transfer_complete(struct driver_data *drv_data)
drv_data->cur_msg->actual_length += drv_data->len -
(drv_data->rx_end - drv_data->rx);

- /* Release chip select if requested, transfer delays are
- * handled in pump_transfers */
- if (drv_data->cs_change)
- drv_data->cs_control(PXA2XX_CS_DEASSERT);
+ /* Transfer delays and chip select release are
+ * handled in pump_transfers or giveback
+ */

/* Move to next transfer */
drv_data->cur_msg->state = next_transfer(drv_data);
@@ -837,23 +872,40 @@ static void pump_transfers(unsigned long data)
return;
}

- /* Delay if requested at end of transfer*/
+ /* Delay if requested at end of transfer before CS change */
if (message->state == RUNNING_STATE) {
previous = list_entry(transfer->transfer_list.prev,
struct spi_transfer,
transfer_list);
if (previous->delay_usecs)
udelay(previous->delay_usecs);
+
+ /* Drop chip select only if cs_change is requested */
+ if (previous->cs_change)
+ drv_data->cs_control(PXA2XX_CS_DEASSERT);
}

- /* Check transfer length */
- if (transfer->len > 8191)
- {
- dev_warn(&drv_data->pdev->dev, "pump_transfers: transfer "
- "length greater than 8191\n");
- message->status = -EINVAL;
- giveback(drv_data);
- return;
+ /* Check for transfers that need multiple DMA segments */
+ if (transfer->len > MAX_DMA_LEN && chip->enable_dma) {
+
+ /* reject already-mapped transfers; PIO won't always work */
+ if (message->is_dma_mapped
+ || transfer->rx_dma || transfer->tx_dma) {
+ dev_err(&drv_data->pdev->dev,
+ "pump_transfers: mapped transfer length "
+ "of %u is greater than %d\n",
+ transfer->len, MAX_DMA_LEN);
+ message->status = -EINVAL;
+ giveback(drv_data);
+ return;
+ }
+
+ /* warn ... we force this to PIO mode */
+ if (printk_ratelimit())
+ dev_warn(&message->spi->dev, "pump_transfers: "
+ "DMA disabled for transfer length %ld "
+ "greater than %d\n",
+ (long)drv_data->len, MAX_DMA_LEN);
}

/* Setup the transfer state based on the type of transfer */
@@ -875,7 +927,6 @@ static void pump_transfers(unsigned long data)
drv_data->len = transfer->len & DCMD_LENGTH;
drv_data->write = drv_data->tx ? chip->write : null_writer;
drv_data->read = drv_data->rx ? chip->read : null_reader;
- drv_data->cs_change = transfer->cs_change;

/* Change speed and bit per word on a per transfer */
cr0 = chip->cr0;
@@ -922,7 +973,7 @@ static void pump_transfers(unsigned long data)
&dma_thresh))
if (printk_ratelimit())
dev_warn(&message->spi->dev,
- "pump_transfer: "
+ "pump_transfers: "
"DMA burst size reduced to "
"match bits_per_word\n");
}
@@ -936,8 +987,23 @@ static void pump_transfers(unsigned long data)

message->state = RUNNING_STATE;

- /* Try to map dma buffer and do a dma transfer if successful */
- if ((drv_data->dma_mapped = map_dma_buffers(drv_data))) {
+ /* Try to map dma buffer and do a dma transfer if successful, but
+ * only if the length is non-zero and less than MAX_DMA_LEN.
+ *
+ * Zero-length non-descriptor DMA is illegal on PXA2xx; force use
+ * of PIO instead. Care is needed above because the transfer may
+ * have have been passed with buffers that are already dma mapped.
+ * A zero-length transfer in PIO mode will not try to write/read
+ * to/from the buffers
+ *
+ * REVISIT large transfers are exactly where we most want to be
+ * using DMA. If this happens much, split those transfers into
+ * multiple DMA segments rather than forcing PIO.
+ */
+ drv_data->dma_mapped = 0;
+ if (drv_data->len > 0 && drv_data->len <= MAX_DMA_LEN)
+ drv_data->dma_mapped = map_dma_buffers(drv_data);
+ if (drv_data->dma_mapped) {

/* Ensure we have the correct interrupt handler */
drv_data->transfer_handler = dma_transfer;
diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c
index 27533b3..ed7b123 100644
--- a/drivers/usb/core/hcd.c
+++ b/drivers/usb/core/hcd.c
@@ -1877,7 +1877,8 @@ int usb_add_hcd(struct usb_hcd *hcd,
* with IRQF_SHARED. As usb_hcd_irq() will always disable
* interrupts we can remove it here.
*/
- irqflags &= ~IRQF_DISABLED;
+ if (irqflags & IRQF_SHARED)
+ irqflags &= ~IRQF_DISABLED;

snprintf(hcd->irq_descr, sizeof(hcd->irq_descr), "%s:usb%d",
hcd->driver->description, hcd->self.busnum);
diff --git a/include/asm-generic/rtc.h b/include/asm-generic/rtc.h
index dd1bed8..85286fb 100644
--- a/include/asm-generic/rtc.h
+++ b/include/asm-generic/rtc.h
@@ -17,6 +17,7 @@
#include <linux/mc146818rtc.h>
#include <linux/rtc.h>
#include <linux/bcd.h>
+#include <linux/delay.h>

#define RTC_PIE 0x40 /* periodic interrupt enable */
#define RTC_AIE 0x20 /* alarm interrupt enable */
@@ -45,7 +46,6 @@ static inline unsigned char rtc_is_updating(void)

static inline unsigned int get_rtc_time(struct rtc_time *time)
{
- unsigned long uip_watchdog = jiffies;
unsigned char ctrl;
unsigned long flags;

@@ -55,19 +55,15 @@ static inline unsigned int get_rtc_time(struct rtc_time *time)

/*
* read RTC once any update in progress is done. The update
- * can take just over 2ms. We wait 10 to 20ms. There is no need to
+ * can take just over 2ms. We wait 20ms. There is no need to
* to poll-wait (up to 1s - eeccch) for the falling edge of RTC_UIP.
* If you need to know *exactly* when a second has started, enable
* periodic update complete interrupts, (via ioctl) and then
* immediately read /dev/rtc which will block until you get the IRQ.
* Once the read clears, read the RTC time (again via ioctl). Easy.
*/
-
- if (rtc_is_updating() != 0)
- while (jiffies - uip_watchdog < 2*HZ/100) {
- barrier();
- cpu_relax();
- }
+ if (rtc_is_updating())
+ mdelay(20);

/*
* Only the values that we read from the RTC are set. We leave
diff --git a/include/linux/clockchips.h b/include/linux/clockchips.h
index c33b0dc..ed3a5d4 100644
--- a/include/linux/clockchips.h
+++ b/include/linux/clockchips.h
@@ -127,6 +127,8 @@ extern int clockevents_register_notifier(struct notifier_block *nb);
extern int clockevents_program_event(struct clock_event_device *dev,
ktime_t expires, ktime_t now);

+extern void clockevents_handle_noop(struct clock_event_device *dev);
+
#ifdef CONFIG_GENERIC_CLOCKEVENTS
extern void clockevents_notify(unsigned long reason, void *arg);
#else
diff --git a/include/net/netlink.h b/include/net/netlink.h
index 112dcdf..5383fdf 100644
--- a/include/net/netlink.h
+++ b/include/net/netlink.h
@@ -704,7 +704,7 @@ static inline int nla_len(const struct nlattr *nla)
*/
static inline int nla_ok(const struct nlattr *nla, int remaining)
{
- return remaining >= sizeof(*nla) &&
+ return remaining >= (int) sizeof(*nla) &&
nla->nla_len >= sizeof(*nla) &&
nla->nla_len <= remaining;
}
diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c
index 3d1e3e1..1876b52 100644
--- a/kernel/time/clockevents.c
+++ b/kernel/time/clockevents.c
@@ -177,7 +177,7 @@ void clockevents_register_device(struct clock_event_device *dev)
/*
* Noop handler when we shut down an event device
*/
-static void clockevents_handle_noop(struct clock_event_device *dev)
+void clockevents_handle_noop(struct clock_event_device *dev)
{
}

@@ -199,7 +199,6 @@ void clockevents_exchange_device(struct clock_event_device *old,
* released list and do a notify add later.
*/
if (old) {
- old->event_handler = clockevents_handle_noop;
clockevents_set_mode(old, CLOCK_EVT_MODE_UNUSED);
list_del(&old->list);
list_add(&old->list, &clockevents_released);
diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index 5fd9b94..a1dac40 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -205,7 +205,7 @@ static void sync_cmos_clock(unsigned long dummy)
if (abs(now.tv_nsec - (NSEC_PER_SEC / 2)) <= tick_nsec / 2)
fail = update_persistent_clock(now);

- next.tv_nsec = (NSEC_PER_SEC / 2) - now.tv_nsec;
+ next.tv_nsec = (NSEC_PER_SEC / 2) - now.tv_nsec - (TICK_NSEC / 2);
if (next.tv_nsec <= 0)
next.tv_nsec += NSEC_PER_SEC;

diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index e1bd50c..0edd345 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -174,6 +174,8 @@ static void tick_do_periodic_broadcast(void)
*/
static void tick_handle_periodic_broadcast(struct clock_event_device *dev)
{
+ ktime_t next;
+
tick_do_periodic_broadcast();

/*
@@ -184,10 +186,13 @@ static void tick_handle_periodic_broadcast(struct clock_event_device *dev)

/*
* Setup the next period for devices, which do not have
- * periodic mode:
+ * periodic mode. We read dev->next_event first and add to it
+ * when the event alrady expired. clockevents_program_event()
+ * sets dev->next_event only when the event is really
+ * programmed to the device.
*/
- for (;;) {
- ktime_t next = ktime_add(dev->next_event, tick_period);
+ for (next = dev->next_event; ;) {
+ next = ktime_add(next, tick_period);

if (!clockevents_program_event(dev, next, ktime_get()))
return;
@@ -204,7 +209,7 @@ static void tick_do_broadcast_on_off(void *why)
struct clock_event_device *bc, *dev;
struct tick_device *td;
unsigned long flags, *reason = why;
- int cpu;
+ int cpu, bc_stopped;

spin_lock_irqsave(&tick_broadcast_lock, flags);

@@ -222,6 +227,8 @@ static void tick_do_broadcast_on_off(void *why)
if (!tick_device_is_functional(dev))
goto out;

+ bc_stopped = cpus_empty(tick_broadcast_mask);
+
switch (*reason) {
case CLOCK_EVT_NOTIFY_BROADCAST_ON:
case CLOCK_EVT_NOTIFY_BROADCAST_FORCE:
@@ -243,9 +250,10 @@ static void tick_do_broadcast_on_off(void *why)
break;
}

- if (cpus_empty(tick_broadcast_mask))
- clockevents_set_mode(bc, CLOCK_EVT_MODE_SHUTDOWN);
- else {
+ if (cpus_empty(tick_broadcast_mask)) {
+ if (!bc_stopped)
+ clockevents_set_mode(bc, CLOCK_EVT_MODE_SHUTDOWN);
+ } else if (bc_stopped) {
if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC)
tick_broadcast_start_periodic(bc);
else
@@ -362,16 +370,8 @@ cpumask_t *tick_get_broadcast_oneshot_mask(void)
static int tick_broadcast_set_event(ktime_t expires, int force)
{
struct clock_event_device *bc = tick_broadcast_device.evtdev;
- ktime_t now = ktime_get();
- int res;
-
- for(;;) {
- res = clockevents_program_event(bc, expires, now);
- if (!res || !force)
- return res;
- now = ktime_get();
- expires = ktime_add(now, ktime_set(0, bc->min_delta_ns));
- }
+
+ return tick_dev_program_event(bc, expires, force);
}

int tick_resume_broadcast_oneshot(struct clock_event_device *bc)
@@ -490,14 +490,52 @@ static void tick_broadcast_clear_oneshot(int cpu)
cpu_clear(cpu, tick_broadcast_oneshot_mask);
}

+static void tick_broadcast_init_next_event(cpumask_t *mask, ktime_t expires)
+{
+ struct tick_device *td;
+ int cpu;
+
+ for_each_cpu_mask(cpu, *mask) {
+ td = &per_cpu(tick_cpu_device, cpu);
+ if (td->evtdev)
+ td->evtdev->next_event = expires;
+ }
+}
+
/**
* tick_broadcast_setup_oneshot - setup the broadcast device
*/
void tick_broadcast_setup_oneshot(struct clock_event_device *bc)
{
- bc->event_handler = tick_handle_oneshot_broadcast;
- clockevents_set_mode(bc, CLOCK_EVT_MODE_ONESHOT);
- bc->next_event.tv64 = KTIME_MAX;
+ /* Set it up only once ! */
+ if (bc->event_handler != tick_handle_oneshot_broadcast) {
+ int was_periodic = bc->mode == CLOCK_EVT_MODE_PERIODIC;
+ int cpu = smp_processor_id();
+ cpumask_t mask;
+
+ bc->event_handler = tick_handle_oneshot_broadcast;
+ clockevents_set_mode(bc, CLOCK_EVT_MODE_ONESHOT);
+
+ /* Take the do_timer update */
+ tick_do_timer_cpu = cpu;
+
+ /*
+ * We must be careful here. There might be other CPUs
+ * waiting for periodic broadcast. We need to set the
+ * oneshot_mask bits for those and program the
+ * broadcast device to fire.
+ */
+ mask = tick_broadcast_mask;
+ cpu_clear(cpu, mask);
+ cpus_or(tick_broadcast_oneshot_mask,
+ tick_broadcast_oneshot_mask, mask);
+
+ if (was_periodic && !cpus_empty(mask)) {
+ tick_broadcast_init_next_event(&mask, tick_next_period);
+ tick_broadcast_set_event(tick_next_period, 1);
+ } else
+ bc->next_event.tv64 = KTIME_MAX;
+ }
}

/*
diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c
index 1bea399..d106d61 100644
--- a/kernel/time/tick-common.c
+++ b/kernel/time/tick-common.c
@@ -159,6 +159,7 @@ static void tick_setup_device(struct tick_device *td,
} else {
handler = td->evtdev->event_handler;
next_event = td->evtdev->next_event;
+ td->evtdev->event_handler = clockevents_handle_noop;
}

td->evtdev = newdev;
diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h
index f13f2b7..0ffc291 100644
--- a/kernel/time/tick-internal.h
+++ b/kernel/time/tick-internal.h
@@ -17,6 +17,8 @@ extern void tick_handle_periodic(struct clock_event_device *dev);
extern void tick_setup_oneshot(struct clock_event_device *newdev,
void (*handler)(struct clock_event_device *),
ktime_t nextevt);
+extern int tick_dev_program_event(struct clock_event_device *dev,
+ ktime_t expires, int force);
extern int tick_program_event(ktime_t expires, int force);
extern void tick_oneshot_notify(void);
extern int tick_switch_to_oneshot(void (*handler)(struct clock_event_device *));
diff --git a/kernel/time/tick-oneshot.c b/kernel/time/tick-oneshot.c
index 0258d31..0737da0 100644
--- a/kernel/time/tick-oneshot.c
+++ b/kernel/time/tick-oneshot.c
@@ -23,24 +23,56 @@
#include "tick-internal.h"

/**
- * tick_program_event
+ * tick_program_event internal worker function
*/
-int tick_program_event(ktime_t expires, int force)
+int tick_dev_program_event(struct clock_event_device *dev, ktime_t expires,
+ int force)
{
- struct clock_event_device *dev = __get_cpu_var(tick_cpu_device).evtdev;
ktime_t now = ktime_get();
+ int i;

- while (1) {
+ for (i = 0;;) {
int ret = clockevents_program_event(dev, expires, now);

if (!ret || !force)
return ret;
+
+ /*
+ * We tried 2 times to program the device with the given
+ * min_delta_ns. If that's not working then we double it
+ * and emit a warning.
+ */
+ if (++i > 2) {
+ /* Increase the min. delta and try again */
+ if (!dev->min_delta_ns)
+ dev->min_delta_ns = 5000;
+ else
+ dev->min_delta_ns += dev->min_delta_ns >> 1;
+
+ printk(KERN_WARNING
+ "CE: %s increasing min_delta_ns to %lu nsec\n",
+ dev->name ? dev->name : "?",
+ dev->min_delta_ns << 1);
+
+ i = 0;
+ }
+
now = ktime_get();
- expires = ktime_add(now, ktime_set(0, dev->min_delta_ns));
+ expires = ktime_add_ns(now, dev->min_delta_ns);
}
}

/**
+ * tick_program_event
+ */
+int tick_program_event(ktime_t expires, int force)
+{
+ struct clock_event_device *dev = __get_cpu_var(tick_cpu_device).evtdev;
+
+ return tick_dev_program_event(dev, expires, force);
+}
+
+/**
* tick_resume_onshot - resume oneshot mode
*/
void tick_resume_oneshot(void)
@@ -61,7 +93,7 @@ void tick_setup_oneshot(struct clock_event_device *newdev,
{
newdev->event_handler = handler;
clockevents_set_mode(newdev, CLOCK_EVT_MODE_ONESHOT);
- clockevents_program_event(newdev, next_event, ktime_get());
+ tick_dev_program_event(newdev, next_event, 1);
}

/**
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 9703c87..b924502 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -956,6 +956,27 @@ int udp_disconnect(struct sock *sk, int flags)
return 0;
}

+static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
+{
+ int is_udplite = IS_UDPLITE(sk);
+ int rc;
+
+ if ((rc = sock_queue_rcv_skb(sk, skb)) < 0) {
+ /* Note that an ENOMEM error is charged twice */
+ if (rc == -ENOMEM)
+ UDP_INC_STATS_BH(UDP_MIB_RCVBUFERRORS,
+ is_udplite);
+ goto drop;
+ }
+
+ return 0;
+
+drop:
+ UDP_INC_STATS_BH(UDP_MIB_INERRORS, is_udplite);
+ kfree_skb(skb);
+ return -1;
+}
+
/* returns:
* -1: error
* 0: success
@@ -1046,14 +1067,16 @@ int udp_queue_rcv_skb(struct sock * sk, struct sk_buff *skb)
goto drop;
}

- if ((rc = sock_queue_rcv_skb(sk,skb)) < 0) {
- /* Note that an ENOMEM error is charged twice */
- if (rc == -ENOMEM)
- UDP_INC_STATS_BH(UDP_MIB_RCVBUFERRORS, is_udplite);
- goto drop;
- }
+ rc = 0;

- return 0;
+ bh_lock_sock(sk);
+ if (!sock_owned_by_user(sk))
+ rc = __udp_queue_rcv_skb(sk, skb);
+ else
+ sk_add_backlog(sk, skb);
+ bh_unlock_sock(sk);
+
+ return rc;

drop:
UDP_INC_STATS_BH(UDP_MIB_INERRORS, is_udplite);
@@ -1091,15 +1114,7 @@ static int __udp4_lib_mcast_deliver(struct sk_buff *skb,
skb1 = skb_clone(skb, GFP_ATOMIC);

if (skb1) {
- int ret = 0;
-
- bh_lock_sock_nested(sk);
- if (!sock_owned_by_user(sk))
- ret = udp_queue_rcv_skb(sk, skb1);
- else
- sk_add_backlog(sk, skb1);
- bh_unlock_sock(sk);
-
+ int ret = udp_queue_rcv_skb(sk, skb1);
if (ret > 0)
/* we should probably re-process instead
* of dropping packets here. */
@@ -1192,13 +1207,7 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct hlist_head udptable[],
uh->dest, inet_iif(skb), udptable);

if (sk != NULL) {
- int ret = 0;
- bh_lock_sock_nested(sk);
- if (!sock_owned_by_user(sk))
- ret = udp_queue_rcv_skb(sk, skb);
- else
- sk_add_backlog(sk, skb);
- bh_unlock_sock(sk);
+ int ret = udp_queue_rcv_skb(sk, skb);
sock_put(sk);

/* a return value > 0 means to resubmit the input, but
@@ -1493,7 +1502,7 @@ struct proto udp_prot = {
.sendmsg = udp_sendmsg,
.recvmsg = udp_recvmsg,
.sendpage = udp_sendpage,
- .backlog_rcv = udp_queue_rcv_skb,
+ .backlog_rcv = __udp_queue_rcv_skb,
.hash = udp_lib_hash,
.unhash = udp_lib_unhash,
.get_port = udp_v4_get_port,
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index fb1c192..d650e10 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -930,39 +930,39 @@ static int ip6_dst_lookup_tail(struct sock *sk,
}

#ifdef CONFIG_IPV6_OPTIMISTIC_DAD
- /*
- * Here if the dst entry we've looked up
- * has a neighbour entry that is in the INCOMPLETE
- * state and the src address from the flow is
- * marked as OPTIMISTIC, we release the found
- * dst entry and replace it instead with the
- * dst entry of the nexthop router
- */
- if (!((*dst)->neighbour->nud_state & NUD_VALID)) {
- struct inet6_ifaddr *ifp;
- struct flowi fl_gw;
- int redirect;
-
- ifp = ipv6_get_ifaddr(&init_net, &fl->fl6_src,
- (*dst)->dev, 1);
-
- redirect = (ifp && ifp->flags & IFA_F_OPTIMISTIC);
- if (ifp)
- in6_ifa_put(ifp);
-
- if (redirect) {
- /*
- * We need to get the dst entry for the
- * default router instead
- */
- dst_release(*dst);
- memcpy(&fl_gw, fl, sizeof(struct flowi));
- memset(&fl_gw.fl6_dst, 0, sizeof(struct in6_addr));
- *dst = ip6_route_output(sk, &fl_gw);
- if ((err = (*dst)->error))
- goto out_err_release;
- }
+ /*
+ * Here if the dst entry we've looked up
+ * has a neighbour entry that is in the INCOMPLETE
+ * state and the src address from the flow is
+ * marked as OPTIMISTIC, we release the found
+ * dst entry and replace it instead with the
+ * dst entry of the nexthop router
+ */
+ if ((*dst)->neighbour && !((*dst)->neighbour->nud_state & NUD_VALID)) {
+ struct inet6_ifaddr *ifp;
+ struct flowi fl_gw;
+ int redirect;
+
+ ifp = ipv6_get_ifaddr(&init_net, &fl->fl6_src,
+ (*dst)->dev, 1);
+
+ redirect = (ifp && ifp->flags & IFA_F_OPTIMISTIC);
+ if (ifp)
+ in6_ifa_put(ifp);
+
+ if (redirect) {
+ /*
+ * We need to get the dst entry for the
+ * default router instead
+ */
+ dst_release(*dst);
+ memcpy(&fl_gw, fl, sizeof(struct flowi));
+ memset(&fl_gw.fl6_dst, 0, sizeof(struct in6_addr));
+ *dst = ip6_route_output(sk, &fl_gw);
+ if ((err = (*dst)->error))
+ goto out_err_release;
}
+ }
#endif

return 0;
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 53739de..4e36c57 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -373,7 +373,7 @@ static int __udp6_lib_mcast_deliver(struct sk_buff *skb, struct in6_addr *saddr,
uh->source, saddr, dif))) {
struct sk_buff *buff = skb_clone(skb, GFP_ATOMIC);
if (buff) {
- bh_lock_sock_nested(sk2);
+ bh_lock_sock(sk2);
if (!sock_owned_by_user(sk2))
udpv6_queue_rcv_skb(sk2, buff);
else
@@ -381,7 +381,7 @@ static int __udp6_lib_mcast_deliver(struct sk_buff *skb, struct in6_addr *saddr,
bh_unlock_sock(sk2);
}
}
- bh_lock_sock_nested(sk);
+ bh_lock_sock(sk);
if (!sock_owned_by_user(sk))
udpv6_queue_rcv_skb(sk, skb);
else
@@ -499,7 +499,7 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct hlist_head udptable[],

/* deliver */

- bh_lock_sock_nested(sk);
+ bh_lock_sock(sk);
if (!sock_owned_by_user(sk))
udpv6_queue_rcv_skb(sk, skb);
else
diff --git a/net/sctp/associola.c b/net/sctp/associola.c
index d29f792..1eefac2 100644
--- a/net/sctp/associola.c
+++ b/net/sctp/associola.c
@@ -588,11 +588,12 @@ struct sctp_transport *sctp_assoc_add_peer(struct sctp_association *asoc,
/* Check to see if this is a duplicate. */
peer = sctp_assoc_lookup_paddr(asoc, addr);
if (peer) {
+ /* An UNKNOWN state is only set on transports added by
+ * user in sctp_connectx() call. Such transports should be
+ * considered CONFIRMED per RFC 4960, Section 5.4.
+ */
if (peer->state == SCTP_UNKNOWN) {
- if (peer_state == SCTP_ACTIVE)
- peer->state = SCTP_ACTIVE;
- if (peer_state == SCTP_UNCONFIRMED)
- peer->state = SCTP_UNCONFIRMED;
+ peer->state = SCTP_ACTIVE;
}
return peer;
}
diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c
index 36ebb39..d024fd0 100644
--- a/net/sctp/sm_make_chunk.c
+++ b/net/sctp/sm_make_chunk.c
@@ -1886,11 +1886,13 @@ static void sctp_process_ext_param(struct sctp_association *asoc,
/* if the peer reports AUTH, assume that he
* supports AUTH.
*/
- asoc->peer.auth_capable = 1;
+ if (sctp_auth_enable)
+ asoc->peer.auth_capable = 1;
break;
case SCTP_CID_ASCONF:
case SCTP_CID_ASCONF_ACK:
- asoc->peer.asconf_capable = 1;
+ if (sctp_addip_enable)
+ asoc->peer.asconf_capable = 1;
break;
default:
break;
@@ -2319,12 +2321,10 @@ clean_up:
/* Release the transport structures. */
list_for_each_safe(pos, temp, &asoc->peer.transport_addr_list) {
transport = list_entry(pos, struct sctp_transport, transports);
- list_del_init(pos);
- sctp_transport_free(transport);
+ if (transport->state != SCTP_ACTIVE)
+ sctp_assoc_rm_peer(asoc, transport);
}

- asoc->peer.transport_count = 0;
-
nomem:
return 0;
}
@@ -2454,6 +2454,9 @@ static int sctp_process_param(struct sctp_association *asoc,
break;

case SCTP_PARAM_SET_PRIMARY:
+ if (!sctp_addip_enable)
+ goto fall_through;
+
addr_param = param.v + sizeof(sctp_addip_param_t);

af = sctp_get_af_specific(param_type2af(param.p->type));
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/