Merge branches 'release', 'idle', 'redhat-bugzilla-436589', 'sbs' and 'video' into release
diff --git a/Documentation/i386/IO-APIC.txt b/Documentation/i386/IO-APIC.txt
index f951666..30b4c71 100644
--- a/Documentation/i386/IO-APIC.txt
+++ b/Documentation/i386/IO-APIC.txt
@@ -70,7 +70,7 @@
These INTA-D PCI IRQs are always 'local to the card', their real meaning
depends on which slot they are in. If you look at the daisy chaining diagram,
-a card in slot4, issuing INTA IRQ, it will end up as a signal on PIRQ2 of
+a card in slot4, issuing INTA IRQ, it will end up as a signal on PIRQ4 of
the PCI chipset. Most cards issue INTA, this creates optimal distribution
between the PIRQ lines. (distributing IRQ sources properly is not a
necessity, PCI IRQs can be shared at will, but it's a good for performance
diff --git a/MAINTAINERS b/MAINTAINERS
index 73883b8..2f70e5c 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -2322,6 +2322,8 @@
M: anil.s.keshavamurthy@intel.com
P: David S. Miller
M: davem@davemloft.net
+P: Masami Hiramatsu
+M: mhiramat@redhat.com
L: linux-kernel@vger.kernel.org
S: Maintained
diff --git a/arch/x86/kernel/cpu/cpufreq/speedstep-smi.c b/arch/x86/kernel/cpu/cpufreq/speedstep-smi.c
index f2b5a621d..8a85c93 100644
--- a/arch/x86/kernel/cpu/cpufreq/speedstep-smi.c
+++ b/arch/x86/kernel/cpu/cpufreq/speedstep-smi.c
@@ -63,7 +63,7 @@
*/
static int speedstep_smi_ownership (void)
{
- u32 command, result, magic;
+ u32 command, result, magic, dummy;
u32 function = GET_SPEEDSTEP_OWNER;
unsigned char magic_data[] = "Copyright (c) 1999 Intel Corporation";
@@ -73,8 +73,11 @@
dprintk("trying to obtain ownership with command %x at port %x\n", command, smi_port);
__asm__ __volatile__(
+ "push %%ebp\n"
"out %%al, (%%dx)\n"
- : "=D" (result)
+ "pop %%ebp\n"
+ : "=D" (result), "=a" (dummy), "=b" (dummy), "=c" (dummy), "=d" (dummy),
+ "=S" (dummy)
: "a" (command), "b" (function), "c" (0), "d" (smi_port),
"D" (0), "S" (magic)
: "memory"
@@ -96,7 +99,7 @@
*/
static int speedstep_smi_get_freqs (unsigned int *low, unsigned int *high)
{
- u32 command, result = 0, edi, high_mhz, low_mhz;
+ u32 command, result = 0, edi, high_mhz, low_mhz, dummy;
u32 state=0;
u32 function = GET_SPEEDSTEP_FREQS;
@@ -109,10 +112,12 @@
dprintk("trying to determine frequencies with command %x at port %x\n", command, smi_port);
- __asm__ __volatile__("movl $0, %%edi\n"
+ __asm__ __volatile__(
+ "push %%ebp\n"
"out %%al, (%%dx)\n"
- : "=a" (result), "=b" (high_mhz), "=c" (low_mhz), "=d" (state), "=D" (edi)
- : "a" (command), "b" (function), "c" (state), "d" (smi_port), "S" (0)
+ "pop %%ebp"
+ : "=a" (result), "=b" (high_mhz), "=c" (low_mhz), "=d" (state), "=D" (edi), "=S" (dummy)
+ : "a" (command), "b" (function), "c" (state), "d" (smi_port), "S" (0), "D" (0)
);
dprintk("result %x, low_freq %u, high_freq %u\n", result, low_mhz, high_mhz);
@@ -135,16 +140,18 @@
static int speedstep_get_state (void)
{
u32 function=GET_SPEEDSTEP_STATE;
- u32 result, state, edi, command;
+ u32 result, state, edi, command, dummy;
command = (smi_sig & 0xffffff00) | (smi_cmd & 0xff);
dprintk("trying to determine current setting with command %x at port %x\n", command, smi_port);
- __asm__ __volatile__("movl $0, %%edi\n"
+ __asm__ __volatile__(
+ "push %%ebp\n"
"out %%al, (%%dx)\n"
- : "=a" (result), "=b" (state), "=D" (edi)
- : "a" (command), "b" (function), "c" (0), "d" (smi_port), "S" (0)
+ "pop %%ebp\n"
+ : "=a" (result), "=b" (state), "=D" (edi), "=c" (dummy), "=d" (dummy), "=S" (dummy)
+ : "a" (command), "b" (function), "c" (0), "d" (smi_port), "S" (0), "D" (0)
);
dprintk("state is %x, result is %x\n", state, result);
@@ -160,7 +167,7 @@
*/
static void speedstep_set_state (unsigned int state)
{
- unsigned int result = 0, command, new_state;
+ unsigned int result = 0, command, new_state, dummy;
unsigned long flags;
unsigned int function=SET_SPEEDSTEP_STATE;
unsigned int retry = 0;
@@ -182,10 +189,12 @@
}
retry++;
__asm__ __volatile__(
- "movl $0, %%edi\n"
+ "push %%ebp\n"
"out %%al, (%%dx)\n"
- : "=b" (new_state), "=D" (result)
- : "a" (command), "b" (function), "c" (state), "d" (smi_port), "S" (0)
+ "pop %%ebp"
+ : "=b" (new_state), "=D" (result), "=c" (dummy), "=a" (dummy),
+ "=d" (dummy), "=S" (dummy)
+ : "a" (command), "b" (function), "c" (state), "d" (smi_port), "S" (0), "D" (0)
);
} while ((new_state != state) && (retry <= SMI_TRIES));
@@ -195,7 +204,7 @@
if (new_state == state) {
dprintk("change to %u MHz succeeded after %u tries with result %u\n", (speedstep_freqs[new_state].frequency / 1000), retry, result);
} else {
- printk(KERN_ERR "cpufreq: change failed with new_state %u and result %u\n", new_state, result);
+ printk(KERN_ERR "cpufreq: change to state %u failed with new_state %u and result %u\n", state, new_state, result);
}
return;
diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c
index 103d61a..3e18db4 100644
--- a/arch/x86/kernel/cpu/mtrr/generic.c
+++ b/arch/x86/kernel/cpu/mtrr/generic.c
@@ -176,12 +176,13 @@
}
/**
- * Checks and updates an fixed-range MTRR if it differs from the value it
- * should have. If K8 extentions are wanted, update the K8 SYSCFG MSR also.
- * see AMD publication no. 24593, chapter 7.8.1, page 233 for more information
- * \param msr MSR address of the MTTR which should be checked and updated
- * \param changed pointer which indicates whether the MTRR needed to be changed
- * \param msrwords pointer to the MSR values which the MSR should have
+ * set_fixed_range - checks & updates a fixed-range MTRR if it differs from the value it should have
+ * @msr: MSR address of the MTTR which should be checked and updated
+ * @changed: pointer which indicates whether the MTRR needed to be changed
+ * @msrwords: pointer to the MSR values which the MSR should have
+ *
+ * If K8 extentions are wanted, update the K8 SYSCFG MSR also.
+ * See AMD publication no. 24593, chapter 7.8.1, page 233 for more information.
*/
static void set_fixed_range(int msr, bool *changed, unsigned int *msrwords)
{
@@ -199,12 +200,15 @@
}
}
+/**
+ * generic_get_free_region - Get a free MTRR.
+ * @base: The starting (base) address of the region.
+ * @size: The size (in bytes) of the region.
+ * @replace_reg: mtrr index to be replaced; set to invalid value if none.
+ *
+ * Returns: The index of the region on success, else negative on error.
+ */
int generic_get_free_region(unsigned long base, unsigned long size, int replace_reg)
-/* [SUMMARY] Get a free MTRR.
- <base> The starting (base) address of the region.
- <size> The size (in bytes) of the region.
- [RETURNS] The index of the region on success, else -1 on error.
-*/
{
int i, max;
mtrr_type ltype;
@@ -249,8 +253,8 @@
}
/**
- * Checks and updates the fixed-range MTRRs if they differ from the saved set
- * \param frs pointer to fixed-range MTRR values, saved by get_fixed_ranges()
+ * set_fixed_ranges - checks & updates the fixed-range MTRRs if they differ from the saved set
+ * @frs: pointer to fixed-range MTRR values, saved by get_fixed_ranges()
*/
static int set_fixed_ranges(mtrr_type * frs)
{
@@ -294,13 +298,13 @@
static u32 deftype_lo, deftype_hi;
+/**
+ * set_mtrr_state - Set the MTRR state for this CPU.
+ *
+ * NOTE: The CPU must already be in a safe state for MTRR changes.
+ * RETURNS: 0 if no changes made, else a mask indicating what was changed.
+ */
static unsigned long set_mtrr_state(void)
-/* [SUMMARY] Set the MTRR state for this CPU.
- <state> The MTRR state information to read.
- <ctxt> Some relevant CPU context.
- [NOTE] The CPU must already be in a safe state for MTRR changes.
- [RETURNS] 0 if no changes made, else a mask indication what was changed.
-*/
{
unsigned int i;
unsigned long change_mask = 0;
diff --git a/arch/x86/kernel/io_delay.c b/arch/x86/kernel/io_delay.c
index c706a30..5921e5f 100644
--- a/arch/x86/kernel/io_delay.c
+++ b/arch/x86/kernel/io_delay.c
@@ -78,6 +78,14 @@
},
{
.callback = dmi_io_delay_0xed_port,
+ .ident = "HP Pavilion dv6000",
+ .matches = {
+ DMI_MATCH(DMI_BOARD_VENDOR, "Quanta"),
+ DMI_MATCH(DMI_BOARD_NAME, "30B8")
+ }
+ },
+ {
+ .callback = dmi_io_delay_0xed_port,
.ident = "HP Pavilion tx1000",
.matches = {
DMI_MATCH(DMI_BOARD_VENDOR, "Quanta"),
diff --git a/arch/x86/kernel/mfgpt_32.c b/arch/x86/kernel/mfgpt_32.c
index 027fc06..b402c0f 100644
--- a/arch/x86/kernel/mfgpt_32.c
+++ b/arch/x86/kernel/mfgpt_32.c
@@ -30,6 +30,7 @@
#include <linux/kernel.h>
#include <linux/interrupt.h>
+#include <linux/module.h>
#include <asm/geode.h>
static struct mfgpt_timer_t {
diff --git a/arch/x86/kernel/setup_32.c b/arch/x86/kernel/setup_32.c
index a1d7071..2b3e5d4 100644
--- a/arch/x86/kernel/setup_32.c
+++ b/arch/x86/kernel/setup_32.c
@@ -406,8 +406,6 @@
*/
min_low_pfn = PFN_UP(init_pg_tables_end);
- find_max_pfn();
-
max_low_pfn = find_max_low_pfn();
#ifdef CONFIG_HIGHMEM
@@ -764,12 +762,13 @@
if (efi_enabled)
efi_init();
- max_low_pfn = setup_memory();
-
/* update e820 for memory not covered by WB MTRRs */
+ find_max_pfn();
mtrr_bp_init();
if (mtrr_trim_uncached_memory(max_pfn))
- max_low_pfn = setup_memory();
+ find_max_pfn();
+
+ max_low_pfn = setup_memory();
#ifdef CONFIG_VMI
/*
diff --git a/arch/x86/kernel/setup_64.c b/arch/x86/kernel/setup_64.c
index 7637dc9..f4f7ecf 100644
--- a/arch/x86/kernel/setup_64.c
+++ b/arch/x86/kernel/setup_64.c
@@ -801,7 +801,7 @@
/* Don't do the funky fallback heuristics the AMD version employs
for now. */
node = apicid_to_node[apicid];
- if (node == NUMA_NO_NODE)
+ if (node == NUMA_NO_NODE || !node_online(node))
node = first_node(node_online_map);
numa_set_node(cpu, node);
diff --git a/arch/x86/mm/discontig_32.c b/arch/x86/mm/discontig_32.c
index c394ca0..8e25e06 100644
--- a/arch/x86/mm/discontig_32.c
+++ b/arch/x86/mm/discontig_32.c
@@ -324,7 +324,6 @@
* this space and use it to adjust the boundary between ZONE_NORMAL
* and ZONE_HIGHMEM.
*/
- find_max_pfn();
get_memcfg_numa();
kva_pages = calculate_numa_remap_pages();
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index 4afaba0..794895c 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -137,7 +137,11 @@
switch (mode) {
case IOR_MODE_UNCACHED:
default:
- prot = PAGE_KERNEL_NOCACHE;
+ /*
+ * FIXME: we will use UC MINUS for now, as video fb drivers
+ * depend on it. Upcoming ioremap_wc() will fix this behavior.
+ */
+ prot = PAGE_KERNEL_UC_MINUS;
break;
case IOR_MODE_CACHED:
prot = PAGE_KERNEL;
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index 14e48b5..7b79f6b 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -771,7 +771,7 @@
int set_memory_uc(unsigned long addr, int numpages)
{
return change_page_attr_set(addr, numpages,
- __pgprot(_PAGE_PCD | _PAGE_PWT));
+ __pgprot(_PAGE_PCD));
}
EXPORT_SYMBOL(set_memory_uc);
diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c
index e8e2d88..788da97 100644
--- a/drivers/acpi/processor_idle.c
+++ b/drivers/acpi/processor_idle.c
@@ -1487,7 +1487,6 @@
return 0;
}
- acpi_unlazy_tlb(smp_processor_id());
/*
* Must be done before busmaster disable as we might need to
* access HPET !
@@ -1577,6 +1576,8 @@
return 0;
}
+ acpi_unlazy_tlb(smp_processor_id());
+
/* Tell the scheduler that we are going deep-idle: */
sched_clock_idle_sleep_event();
/*
@@ -1692,7 +1693,9 @@
switch (cx->type) {
case ACPI_STATE_C1:
state->flags |= CPUIDLE_FLAG_SHALLOW;
- state->flags |= CPUIDLE_FLAG_TIME_VALID;
+ if (cx->entry_method == ACPI_CSTATE_FFH)
+ state->flags |= CPUIDLE_FLAG_TIME_VALID;
+
state->enter = acpi_idle_enter_c1;
dev->safe_state = state;
break;
diff --git a/drivers/acpi/sbshc.c b/drivers/acpi/sbshc.c
index a2cf300..bcf2c70 100644
--- a/drivers/acpi/sbshc.c
+++ b/drivers/acpi/sbshc.c
@@ -130,7 +130,6 @@
goto end;
}
smb_hc_write(hc, ACPI_SMB_COMMAND, command);
- smb_hc_write(hc, ACPI_SMB_COMMAND, command);
if (!(protocol & 0x01)) {
smb_hc_write(hc, ACPI_SMB_BLOCK_COUNT, length);
for (i = 0; i < length; ++i)
diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
index 57570ac..e6ce262 100644
--- a/drivers/acpi/scan.c
+++ b/drivers/acpi/scan.c
@@ -39,20 +39,26 @@
int size)
{
int len;
+ int count;
- if (!acpi_dev->flags.hardware_id)
+ if (!acpi_dev->flags.hardware_id && !acpi_dev->flags.compatible_ids)
return -ENODEV;
- len = snprintf(modalias, size, "acpi:%s:",
- acpi_dev->pnp.hardware_id);
- if (len < 0 || len >= size)
- return -EINVAL;
+ len = snprintf(modalias, size, "acpi:");
size -= len;
+ if (acpi_dev->flags.hardware_id) {
+ count = snprintf(&modalias[len], size, "%s:",
+ acpi_dev->pnp.hardware_id);
+ if (count < 0 || count >= size)
+ return -EINVAL;
+ len += count;
+ size -= count;
+ }
+
if (acpi_dev->flags.compatible_ids) {
struct acpi_compatible_id_list *cid_list;
int i;
- int count;
cid_list = acpi_dev->pnp.cid_list;
for (i = 0; i < cid_list->count; i++) {
diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c
index d73663a..fc555a9 100644
--- a/drivers/cpuidle/cpuidle.c
+++ b/drivers/cpuidle/cpuidle.c
@@ -67,7 +67,7 @@
/* enter the state and update stats */
dev->last_residency = target_state->enter(dev, target_state);
dev->last_state = target_state;
- target_state->time += dev->last_residency;
+ target_state->time += (unsigned long long)dev->last_residency;
target_state->usage++;
/* give the governor an opportunity to reflect on the outcome */
@@ -224,7 +224,7 @@
state->exit_latency = 0;
state->target_residency = 0;
state->power_usage = -1;
- state->flags = CPUIDLE_FLAG_POLL | CPUIDLE_FLAG_TIME_VALID;
+ state->flags = CPUIDLE_FLAG_POLL;
state->enter = poll_idle;
}
#else
diff --git a/drivers/cpuidle/sysfs.c b/drivers/cpuidle/sysfs.c
index 69102ca..e949618 100644
--- a/drivers/cpuidle/sysfs.c
+++ b/drivers/cpuidle/sysfs.c
@@ -218,6 +218,12 @@
return sprintf(buf, "%u\n", state->_name);\
}
+#define define_show_state_ull_function(_name) \
+static ssize_t show_state_##_name(struct cpuidle_state *state, char *buf) \
+{ \
+ return sprintf(buf, "%llu\n", state->_name);\
+}
+
#define define_show_state_str_function(_name) \
static ssize_t show_state_##_name(struct cpuidle_state *state, char *buf) \
{ \
@@ -228,8 +234,8 @@
define_show_state_function(exit_latency)
define_show_state_function(power_usage)
-define_show_state_function(usage)
-define_show_state_function(time)
+define_show_state_ull_function(usage)
+define_show_state_ull_function(time)
define_show_state_str_function(name)
define_show_state_str_function(desc)
diff --git a/drivers/pci/setup-bus.c b/drivers/pci/setup-bus.c
index 125e7b7..f7cb8e0 100644
--- a/drivers/pci/setup-bus.c
+++ b/drivers/pci/setup-bus.c
@@ -486,12 +486,7 @@
break;
case PCI_CLASS_BRIDGE_PCI:
- /* don't size subtractive decoding (transparent)
- * PCI-to-PCI bridges */
- if (bus->self->transparent)
- break;
pci_bridge_check_ranges(bus);
- /* fall through */
default:
pbus_size_io(bus);
/* If the bridge supports prefetchable range, size it
diff --git a/include/asm-x86/pgtable.h b/include/asm-x86/pgtable.h
index 174b877..9cf472a 100644
--- a/include/asm-x86/pgtable.h
+++ b/include/asm-x86/pgtable.h
@@ -85,6 +85,7 @@
#define __PAGE_KERNEL_RX (__PAGE_KERNEL_EXEC & ~_PAGE_RW)
#define __PAGE_KERNEL_EXEC_NOCACHE (__PAGE_KERNEL_EXEC | _PAGE_PCD | _PAGE_PWT)
#define __PAGE_KERNEL_NOCACHE (__PAGE_KERNEL | _PAGE_PCD | _PAGE_PWT)
+#define __PAGE_KERNEL_UC_MINUS (__PAGE_KERNEL | _PAGE_PCD)
#define __PAGE_KERNEL_VSYSCALL (__PAGE_KERNEL_RX | _PAGE_USER)
#define __PAGE_KERNEL_VSYSCALL_NOCACHE (__PAGE_KERNEL_VSYSCALL | _PAGE_PCD | _PAGE_PWT)
#define __PAGE_KERNEL_LARGE (__PAGE_KERNEL | _PAGE_PSE)
@@ -101,6 +102,7 @@
#define PAGE_KERNEL_EXEC MAKE_GLOBAL(__PAGE_KERNEL_EXEC)
#define PAGE_KERNEL_RX MAKE_GLOBAL(__PAGE_KERNEL_RX)
#define PAGE_KERNEL_NOCACHE MAKE_GLOBAL(__PAGE_KERNEL_NOCACHE)
+#define PAGE_KERNEL_UC_MINUS MAKE_GLOBAL(__PAGE_KERNEL_UC_MINUS)
#define PAGE_KERNEL_EXEC_NOCACHE MAKE_GLOBAL(__PAGE_KERNEL_EXEC_NOCACHE)
#define PAGE_KERNEL_LARGE MAKE_GLOBAL(__PAGE_KERNEL_LARGE)
#define PAGE_KERNEL_LARGE_EXEC MAKE_GLOBAL(__PAGE_KERNEL_LARGE_EXEC)
diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h
index 6b72a45..51e6b1e 100644
--- a/include/linux/cpuidle.h
+++ b/include/linux/cpuidle.h
@@ -38,8 +38,8 @@
unsigned int power_usage; /* in mW */
unsigned int target_residency; /* in US */
- unsigned int usage;
- unsigned int time; /* in US */
+ unsigned long long usage;
+ unsigned long long time; /* in US */
int (*enter) (struct cpuidle_device *dev,
struct cpuidle_state *state);
diff --git a/include/linux/sched.h b/include/linux/sched.h
index fed07d0..6a1e7af 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1541,6 +1541,12 @@
extern void sched_idle_next(void);
+#if defined(CONFIG_NO_HZ) && defined(CONFIG_SMP)
+extern void wake_up_idle_cpu(int cpu);
+#else
+static inline void wake_up_idle_cpu(int cpu) { }
+#endif
+
#ifdef CONFIG_SCHED_DEBUG
extern unsigned int sysctl_sched_latency;
extern unsigned int sysctl_sched_min_granularity;
diff --git a/kernel/relay.c b/kernel/relay.c
index 4c035a8..d6204a4 100644
--- a/kernel/relay.c
+++ b/kernel/relay.c
@@ -736,7 +736,7 @@
kref_get(&buf->kref);
filp->private_data = buf;
- return 0;
+ return nonseekable_open(inode, filp);
}
/**
@@ -1056,6 +1056,10 @@
.get = generic_pipe_buf_get,
};
+static void relay_page_release(struct splice_pipe_desc *spd, unsigned int i)
+{
+}
+
/*
* subbuf_splice_actor - splice up to one subbuf's worth of data
*/
@@ -1083,6 +1087,7 @@
.partial = partial,
.flags = flags,
.ops = &relay_pipe_buf_ops,
+ .spd_release = relay_page_release,
};
if (rbuf->subbufs_produced == rbuf->subbufs_consumed)
diff --git a/kernel/sched.c b/kernel/sched.c
index 28c73f0..8dcdec6f 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -1052,6 +1052,49 @@
resched_task(cpu_curr(cpu));
spin_unlock_irqrestore(&rq->lock, flags);
}
+
+#ifdef CONFIG_NO_HZ
+/*
+ * When add_timer_on() enqueues a timer into the timer wheel of an
+ * idle CPU then this timer might expire before the next timer event
+ * which is scheduled to wake up that CPU. In case of a completely
+ * idle system the next event might even be infinite time into the
+ * future. wake_up_idle_cpu() ensures that the CPU is woken up and
+ * leaves the inner idle loop so the newly added timer is taken into
+ * account when the CPU goes back to idle and evaluates the timer
+ * wheel for the next timer event.
+ */
+void wake_up_idle_cpu(int cpu)
+{
+ struct rq *rq = cpu_rq(cpu);
+
+ if (cpu == smp_processor_id())
+ return;
+
+ /*
+ * This is safe, as this function is called with the timer
+ * wheel base lock of (cpu) held. When the CPU is on the way
+ * to idle and has not yet set rq->curr to idle then it will
+ * be serialized on the timer wheel base lock and take the new
+ * timer into account automatically.
+ */
+ if (rq->curr != rq->idle)
+ return;
+
+ /*
+ * We can set TIF_RESCHED on the idle task of the other CPU
+ * lockless. The worst case is that the other CPU runs the
+ * idle task through an additional NOOP schedule()
+ */
+ set_tsk_thread_flag(rq->idle, TIF_NEED_RESCHED);
+
+ /* NEED_RESCHED must be visible before we test polling */
+ smp_mb();
+ if (!tsk_is_polling(rq->idle))
+ smp_send_reschedule(cpu);
+}
+#endif
+
#else
static void __resched_task(struct task_struct *p, int tif_bit)
{
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index 278534b..7f60097 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -174,7 +174,7 @@
if (watchdog)
del_timer(&watchdog_timer);
watchdog = cs;
- init_timer_deferrable(&watchdog_timer);
+ init_timer(&watchdog_timer);
watchdog_timer.function = clocksource_watchdog;
/* Reset watchdog cycles */
diff --git a/kernel/timer.c b/kernel/timer.c
index 99b00a2..b024106 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -451,10 +451,18 @@
spin_lock_irqsave(&base->lock, flags);
timer_set_base(timer, base);
internal_add_timer(base, timer);
+ /*
+ * Check whether the other CPU is idle and needs to be
+ * triggered to reevaluate the timer wheel when nohz is
+ * active. We are protected against the other CPU fiddling
+ * with the timer by holding the timer base lock. This also
+ * makes sure that a CPU on the way to idle can not evaluate
+ * the timer wheel.
+ */
+ wake_up_idle_cpu(cpu);
spin_unlock_irqrestore(&base->lock, flags);
}
-
/**
* mod_timer - modify a timer's timeout
* @timer: the timer to be modified
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 74c1b6b..51c9e2c 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -401,12 +401,20 @@
struct page *page;
unsigned long nr_pages;
+ /*
+ * We want to release as many surplus pages as possible, spread
+ * evenly across all nodes. Iterate across all nodes until we
+ * can no longer free unreserved surplus pages. This occurs when
+ * the nodes with surplus pages have no free pages.
+ */
+ unsigned long remaining_iterations = num_online_nodes();
+
/* Uncommit the reservation */
resv_huge_pages -= unused_resv_pages;
nr_pages = min(unused_resv_pages, surplus_huge_pages);
- while (nr_pages) {
+ while (remaining_iterations-- && nr_pages) {
nid = next_node(nid, node_online_map);
if (nid == MAX_NUMNODES)
nid = first_node(node_online_map);
@@ -424,6 +432,7 @@
surplus_huge_pages--;
surplus_huge_pages_node[nid]--;
nr_pages--;
+ remaining_iterations = num_online_nodes();
}
}
}
@@ -671,9 +680,11 @@
{
return sprintf(buf,
"Node %d HugePages_Total: %5u\n"
- "Node %d HugePages_Free: %5u\n",
+ "Node %d HugePages_Free: %5u\n"
+ "Node %d HugePages_Surp: %5u\n",
nid, nr_huge_pages_node[nid],
- nid, free_huge_pages_node[nid]);
+ nid, free_huge_pages_node[nid],
+ nid, surplus_huge_pages_node[nid]);
}
/* Return the number pages of memory we physically have, in PAGE_SIZE units. */
diff --git a/mm/slab.c b/mm/slab.c
index bb4070e..04b308c 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -1481,7 +1481,7 @@
list_add(&cache_cache.next, &cache_chain);
cache_cache.colour_off = cache_line_size();
cache_cache.array[smp_processor_id()] = &initarray_cache.cache;
- cache_cache.nodelists[node] = &initkmem_list3[CACHE_CACHE];
+ cache_cache.nodelists[node] = &initkmem_list3[CACHE_CACHE + node];
/*
* struct kmem_cache size depends on nr_node_ids, which
@@ -1602,7 +1602,7 @@
int nid;
for_each_online_node(nid) {
- init_list(&cache_cache, &initkmem_list3[CACHE_CACHE], nid);
+ init_list(&cache_cache, &initkmem_list3[CACHE_CACHE + nid], nid);
init_list(malloc_sizes[INDEX_AC].cs_cachep,
&initkmem_list3[SIZE_AC + nid], nid);
diff --git a/mm/slub.c b/mm/slub.c
index ca71d5b..b72bc98 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -2685,6 +2685,7 @@
}
EXPORT_SYMBOL(kfree);
+#if defined(SLUB_DEBUG) || defined(CONFIG_SLABINFO)
static unsigned long count_partial(struct kmem_cache_node *n)
{
unsigned long flags;
@@ -2697,6 +2698,7 @@
spin_unlock_irqrestore(&n->list_lock, flags);
return x;
}
+#endif
/*
* kmem_cache_shrink removes empty slabs from the partial lists and sorts
diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
index 9712716..c22d6b6 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
@@ -322,15 +322,6 @@
ctxt->direction = DMA_FROM_DEVICE;
clear_bit(RDMACTXT_F_READ_DONE, &ctxt->flags);
clear_bit(RDMACTXT_F_LAST_CTXT, &ctxt->flags);
- if ((ch+1)->rc_discrim == 0) {
- /*
- * Checked in sq_cq_reap to see if we need to
- * be enqueued
- */
- set_bit(RDMACTXT_F_LAST_CTXT, &ctxt->flags);
- ctxt->next = hdr_ctxt;
- hdr_ctxt->next = head;
- }
/* Prepare READ WR */
memset(&read_wr, 0, sizeof read_wr);
@@ -348,7 +339,17 @@
rdma_set_ctxt_sge(ctxt, &sge[ch_sge_ary[ch_no].start],
&sgl_offset,
read_wr.num_sge);
-
+ if (((ch+1)->rc_discrim == 0) &&
+ (read_wr.num_sge == ch_sge_ary[ch_no].count)) {
+ /*
+ * Mark the last RDMA_READ with a bit to
+ * indicate all RPC data has been fetched from
+ * the client and the RPC needs to be enqueued.
+ */
+ set_bit(RDMACTXT_F_LAST_CTXT, &ctxt->flags);
+ ctxt->next = hdr_ctxt;
+ hdr_ctxt->next = head;
+ }
/* Post the read */
err = svc_rdma_send(xprt, &read_wr);
if (err) {