22 files changed, 336 insertions, 207 deletions

diff --git a/MAINTAINERS b/MAINTAINERS
index 5b422908d0f3..a0e3c3a47a51 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -485,8 +485,8 @@ S:	Maintained
 F:      drivers/input/mouse/bcm5974.c
 
 APPLE SMC DRIVER
-M:      Nicolas Boichat <nicolas@boichat.ch>
-L:      mactel-linux-devel@lists.sourceforge.net
+M:      Henrik Rydberg <rydberg@euromail.se>
+L:      lm-sensors@lm-sensors.org
 S:      Maintained
 F:      drivers/hwmon/applesmc.c
 
diff --git a/arch/m68k/include/asm/atomic_mm.h b/arch/m68k/include/asm/atomic_mm.h
index 88b7af20a996..d9d2ed647435 100644
--- a/arch/m68k/include/asm/atomic_mm.h
+++ b/arch/m68k/include/asm/atomic_mm.h
@@ -148,14 +148,18 @@ static inline int atomic_xchg(atomic_t *v, int new)
 static inline int atomic_sub_and_test(int i, atomic_t *v)
 {
         char c;
-        __asm__ __volatile__("subl %2,%1; seq %0" : "=d" (c), "+m" (*v): "g" (i));
+        __asm__ __volatile__("subl %2,%1; seq %0"
+                             : "=d" (c), "+m" (*v)
+                             : "id" (i));
         return c != 0;
 }
 
 static inline int atomic_add_negative(int i, atomic_t *v)
 {
         char c;
-        __asm__ __volatile__("addl %2,%1; smi %0" : "=d" (c), "+m" (*v): "g" (i));
+        __asm__ __volatile__("addl %2,%1; smi %0"
+                             : "=d" (c), "+m" (*v)
+                             : "id" (i));
         return c != 0;
 }
 
diff --git a/arch/m68k/include/asm/sigcontext.h b/arch/m68k/include/asm/sigcontext.h
index 1320eaa4cc2a..a29dd74a17cb 100644
--- a/arch/m68k/include/asm/sigcontext.h
+++ b/arch/m68k/include/asm/sigcontext.h
@@ -17,13 +17,11 @@ struct sigcontext {
 #ifndef __uClinux__
 # ifdef __mcoldfire__
         unsigned long  sc_fpregs[2][2]; /* room for two fp registers */
-        unsigned long  sc_fpcntl[3];
-        unsigned char  sc_fpstate[16+6*8];
 # else
         unsigned long  sc_fpregs[2*3];  /* room for two fp registers */
+# endif
         unsigned long  sc_fpcntl[3];
         unsigned char  sc_fpstate[216];
-# endif
 #endif
 };
 
diff --git a/arch/x86/include/asm/lguest_hcall.h b/arch/x86/include/asm/lguest_hcall.h
index ba0eed8aa1a6..b60f2924c413 100644
--- a/arch/x86/include/asm/lguest_hcall.h
+++ b/arch/x86/include/asm/lguest_hcall.h
@@ -28,22 +28,39 @@
 
 #ifndef __ASSEMBLY__
 #include <asm/hw_irq.h>
-#include <asm/kvm_para.h>
 
 /*G:030
  * But first, how does our Guest contact the Host to ask for privileged
  * operations?  There are two ways: the direct way is to make a "hypercall",
  * to make requests of the Host Itself.
  *
- * We use the KVM hypercall mechanism, though completely different hypercall
- * numbers. Seventeen hypercalls are available: the hypercall number is put in
- * the %eax register, and the arguments (when required) are placed in %ebx,
- * %ecx, %edx and %esi.  If a return value makes sense, it's returned in %eax.
+ * Our hypercall mechanism uses the highest unused trap code (traps 32 and
+ * above are used by real hardware interrupts).  Seventeen hypercalls are
+ * available: the hypercall number is put in the %eax register, and the
+ * arguments (when required) are placed in %ebx, %ecx, %edx and %esi.
+ * If a return value makes sense, it's returned in %eax.
  *
  * Grossly invalid calls result in Sudden Death at the hands of the vengeful
  * Host, rather than returning failure.  This reflects Winston Churchill's
  * definition of a gentleman: "someone who is only rude intentionally".
-:*/
+ */
+static inline unsigned long
+hcall(unsigned long call,
+      unsigned long arg1, unsigned long arg2, unsigned long arg3,
+      unsigned long arg4)
+{
+        /* "int" is the Intel instruction to trigger a trap. */
+        asm volatile("int $" __stringify(LGUEST_TRAP_ENTRY)
+                     /* The call in %eax (aka "a") might be overwritten */
+                     : "=a"(call)
+                       /* The arguments are in %eax, %ebx, %ecx, %edx & %esi */
+                     : "a"(call), "b"(arg1), "c"(arg2), "d"(arg3), "S"(arg4)
+                       /* "memory" means this might write somewhere in memory.
+                        * This isn't true for all calls, but it's safe to tell
+                        * gcc that it might happen so it doesn't get clever. */
+                     : "memory");
+        return call;
+}
 
 /* Can't use our min() macro here: needs to be a constant */
 #define LGUEST_IRQS (NR_IRQS < 32 ? NR_IRQS: 32)
diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c
index 7e59dc1d3fc2..2bdf628066bd 100644
--- a/arch/x86/lguest/boot.c
+++ b/arch/x86/lguest/boot.c
@@ -115,7 +115,7 @@ static void async_hcall(unsigned long call, unsigned long arg1,
         local_irq_save(flags);
         if (lguest_data.hcall_status[next_call] != 0xFF) {
                 /* Table full, so do normal hcall which will flush table. */
-                kvm_hypercall4(call, arg1, arg2, arg3, arg4);
+                hcall(call, arg1, arg2, arg3, arg4);
         } else {
                 lguest_data.hcalls[next_call].arg0 = call;
                 lguest_data.hcalls[next_call].arg1 = arg1;
@@ -145,46 +145,45 @@ static void async_hcall(unsigned long call, unsigned long arg1,
  * So, when we're in lazy mode, we call async_hcall() to store the call for
  * future processing:
  */
-static void lazy_hcall1(unsigned long call,
-                       unsigned long arg1)
+static void lazy_hcall1(unsigned long call, unsigned long arg1)
 {
         if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_NONE)
-                kvm_hypercall1(call, arg1);
+                hcall(call, arg1, 0, 0, 0);
         else
                 async_hcall(call, arg1, 0, 0, 0);
 }
 
 /* You can imagine what lazy_hcall2, 3 and 4 look like. :*/
 static void lazy_hcall2(unsigned long call,
-                       unsigned long arg1,
-                       unsigned long arg2)
+                        unsigned long arg1,
+                        unsigned long arg2)
 {
         if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_NONE)
-                kvm_hypercall2(call, arg1, arg2);
+                hcall(call, arg1, arg2, 0, 0);
         else
                 async_hcall(call, arg1, arg2, 0, 0);
 }
 
 static void lazy_hcall3(unsigned long call,
-                       unsigned long arg1,
-                       unsigned long arg2,
-                       unsigned long arg3)
+                        unsigned long arg1,
+                        unsigned long arg2,
+                        unsigned long arg3)
 {
         if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_NONE)
-                kvm_hypercall3(call, arg1, arg2, arg3);
+                hcall(call, arg1, arg2, arg3, 0);
         else
                 async_hcall(call, arg1, arg2, arg3, 0);
 }
 
 #ifdef CONFIG_X86_PAE
 static void lazy_hcall4(unsigned long call,
-                       unsigned long arg1,
-                       unsigned long arg2,
-                       unsigned long arg3,
-                       unsigned long arg4)
+                        unsigned long arg1,
+                        unsigned long arg2,
+                        unsigned long arg3,
+                        unsigned long arg4)
 {
         if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_NONE)
-                kvm_hypercall4(call, arg1, arg2, arg3, arg4);
+                hcall(call, arg1, arg2, arg3, arg4);
         else
                 async_hcall(call, arg1, arg2, arg3, arg4);
 }
@@ -196,13 +195,13 @@ static void lazy_hcall4(unsigned long call,
 :*/
 static void lguest_leave_lazy_mmu_mode(void)
 {
-        kvm_hypercall0(LHCALL_FLUSH_ASYNC);
+        hcall(LHCALL_FLUSH_ASYNC, 0, 0, 0, 0);
         paravirt_leave_lazy_mmu();
 }
 
 static void lguest_end_context_switch(struct task_struct *next)
 {
-        kvm_hypercall0(LHCALL_FLUSH_ASYNC);
+        hcall(LHCALL_FLUSH_ASYNC, 0, 0, 0, 0);
         paravirt_end_context_switch(next);
 }
 
@@ -286,7 +285,7 @@ static void lguest_write_idt_entry(gate_desc *dt,
         /* Keep the local copy up to date. */
         native_write_idt_entry(dt, entrynum, g);
         /* Tell Host about this new entry. */
-        kvm_hypercall3(LHCALL_LOAD_IDT_ENTRY, entrynum, desc[0], desc[1]);
+        hcall(LHCALL_LOAD_IDT_ENTRY, entrynum, desc[0], desc[1], 0);
 }
 
 /*
@@ -300,7 +299,7 @@ static void lguest_load_idt(const struct desc_ptr *desc)
         struct desc_struct *idt = (void *)desc->address;
 
         for (i = 0; i < (desc->size+1)/8; i++)
-                kvm_hypercall3(LHCALL_LOAD_IDT_ENTRY, i, idt[i].a, idt[i].b);
+                hcall(LHCALL_LOAD_IDT_ENTRY, i, idt[i].a, idt[i].b, 0);
 }
 
 /*
@@ -321,7 +320,7 @@ static void lguest_load_gdt(const struct desc_ptr *desc)
         struct desc_struct *gdt = (void *)desc->address;
 
         for (i = 0; i < (desc->size+1)/8; i++)
-                kvm_hypercall3(LHCALL_LOAD_GDT_ENTRY, i, gdt[i].a, gdt[i].b);
+                hcall(LHCALL_LOAD_GDT_ENTRY, i, gdt[i].a, gdt[i].b, 0);
 }
 
 /*
@@ -334,8 +333,8 @@ static void lguest_write_gdt_entry(struct desc_struct *dt, int entrynum,
 {
         native_write_gdt_entry(dt, entrynum, desc, type);
         /* Tell Host about this new entry. */
-        kvm_hypercall3(LHCALL_LOAD_GDT_ENTRY, entrynum,
-                       dt[entrynum].a, dt[entrynum].b);
+        hcall(LHCALL_LOAD_GDT_ENTRY, entrynum,
+              dt[entrynum].a, dt[entrynum].b, 0);
 }
 
 /*
@@ -931,7 +930,7 @@ static int lguest_clockevent_set_next_event(unsigned long delta,
         }
 
         /* Please wake us this far in the future. */
-        kvm_hypercall1(LHCALL_SET_CLOCKEVENT, delta);
+        hcall(LHCALL_SET_CLOCKEVENT, delta, 0, 0, 0);
         return 0;
 }
 
@@ -942,7 +941,7 @@ static void lguest_clockevent_set_mode(enum clock_event_mode mode,
         case CLOCK_EVT_MODE_UNUSED:
         case CLOCK_EVT_MODE_SHUTDOWN:
                 /* A 0 argument shuts the clock down. */
-                kvm_hypercall0(LHCALL_SET_CLOCKEVENT);
+                hcall(LHCALL_SET_CLOCKEVENT, 0, 0, 0, 0);
                 break;
         case CLOCK_EVT_MODE_ONESHOT:
                 /* This is what we expect. */
@@ -1100,7 +1099,7 @@ static void set_lguest_basic_apic_ops(void)
 /* STOP!  Until an interrupt comes in. */
 static void lguest_safe_halt(void)
 {
-        kvm_hypercall0(LHCALL_HALT);
+        hcall(LHCALL_HALT, 0, 0, 0, 0);
 }
 
 /*
@@ -1112,8 +1111,8 @@ static void lguest_safe_halt(void)
  */
 static void lguest_power_off(void)
 {
-        kvm_hypercall2(LHCALL_SHUTDOWN, __pa("Power down"),
-                                        LGUEST_SHUTDOWN_POWEROFF);
+        hcall(LHCALL_SHUTDOWN, __pa("Power down"),
+              LGUEST_SHUTDOWN_POWEROFF, 0, 0);
 }
 
 /*
@@ -1123,7 +1122,7 @@ static void lguest_power_off(void)
  */
 static int lguest_panic(struct notifier_block *nb, unsigned long l, void *p)
 {
-        kvm_hypercall2(LHCALL_SHUTDOWN, __pa(p), LGUEST_SHUTDOWN_POWEROFF);
+        hcall(LHCALL_SHUTDOWN, __pa(p), LGUEST_SHUTDOWN_POWEROFF, 0, 0);
         /* The hcall won't return, but to keep gcc happy, we're "done". */
         return NOTIFY_DONE;
 }
@@ -1162,7 +1161,7 @@ static __init int early_put_chars(u32 vtermno, const char *buf, int count)
                 len = sizeof(scratch) - 1;
         scratch[len] = '\0';
         memcpy(scratch, buf, len);
-        kvm_hypercall1(LHCALL_NOTIFY, __pa(scratch));
+        hcall(LHCALL_NOTIFY, __pa(scratch), 0, 0, 0);
 
         /* This routine returns the number of bytes actually written. */
         return len;
@@ -1174,7 +1173,7 @@ static __init int early_put_chars(u32 vtermno, const char *buf, int count)
  */
 static void lguest_restart(char *reason)
 {
-        kvm_hypercall2(LHCALL_SHUTDOWN, __pa(reason), LGUEST_SHUTDOWN_RESTART);
+        hcall(LHCALL_SHUTDOWN, __pa(reason), LGUEST_SHUTDOWN_RESTART, 0, 0);
 }
 
 /*G:050
diff --git a/arch/x86/lguest/i386_head.S b/arch/x86/lguest/i386_head.S
index 27eac0faee48..4f420c2f2d55 100644
--- a/arch/x86/lguest/i386_head.S
+++ b/arch/x86/lguest/i386_head.S
@@ -32,7 +32,7 @@ ENTRY(lguest_entry)
          */
         movl $LHCALL_LGUEST_INIT, %eax
         movl $lguest_data - __PAGE_OFFSET, %ebx
-        .byte 0x0f,0x01,0xc1 /* KVM_HYPERCALL */
+        int $LGUEST_TRAP_ENTRY
 
         /* Set up the initial stack so we can run C code. */
         movl $(init_thread_union+THREAD_SIZE),%esp
diff --git a/drivers/hwmon/applesmc.c b/drivers/hwmon/applesmc.c
index c1605b528e8f..0f28d91f29d8 100644
--- a/drivers/hwmon/applesmc.c
+++ b/drivers/hwmon/applesmc.c
@@ -142,6 +142,12 @@ static const char *temperature_sensors_sets[][41] = {
           "TM1S", "TM2P", "TM2S", "TM3S", "TM8P", "TM8S", "TM9P", "TM9S",
           "TN0C", "TN0D", "TN0H", "TS0C", "Tp0C", "Tp1C", "Tv0S", "Tv1S",
           NULL },
+/* Set 17: iMac 9,1 */
+        { "TA0P", "TC0D", "TC0H", "TC0P", "TG0D", "TG0H", "TH0P", "TL0P",
+          "TN0D", "TN0H", "TN0P", "TO0P", "Tm0P", "Tp0P", NULL },
+/* Set 18: MacBook Pro 2,2 */
+        { "TB0T", "TC0D", "TC0P", "TG0H", "TG0P", "TG0T", "TM0P", "TTF0",
+          "Th0H", "Th1H", "Tm0P", "Ts0P", NULL },
 };
 
 /* List of keys used to read/write fan speeds */
@@ -1350,6 +1356,10 @@ static __initdata struct dmi_match_data applesmc_dmi_data[] = {
         { .accelerometer = 1, .light = 1, .temperature_set = 15 },
 /* MacPro3,1: temperature set 16 */
         { .accelerometer = 0, .light = 0, .temperature_set = 16 },
+/* iMac 9,1: light sensor only, temperature set 17 */
+        { .accelerometer = 0, .light = 0, .temperature_set = 17 },
+/* MacBook Pro 2,2: accelerometer, backlight and temperature set 18 */
+        { .accelerometer = 1, .light = 1, .temperature_set = 18 },
 };
 
 /* Note that DMI_MATCH(...,"MacBook") will match "MacBookPro1,1".
@@ -1375,6 +1385,10 @@ static __initdata struct dmi_system_id applesmc_whitelist[] = {
           DMI_MATCH(DMI_BOARD_VENDOR, "Apple"),
           DMI_MATCH(DMI_PRODUCT_NAME, "MacBookPro3") },
                 &applesmc_dmi_data[9]},
+        { applesmc_dmi_match, "Apple MacBook Pro 2,2", {
+          DMI_MATCH(DMI_BOARD_VENDOR, "Apple Computer, Inc."),
+          DMI_MATCH(DMI_PRODUCT_NAME, "MacBookPro2,2") },
+                &applesmc_dmi_data[18]},
         { applesmc_dmi_match, "Apple MacBook Pro", {
           DMI_MATCH(DMI_BOARD_VENDOR,"Apple"),
           DMI_MATCH(DMI_PRODUCT_NAME,"MacBookPro") },
@@ -1415,6 +1429,10 @@ static __initdata struct dmi_system_id applesmc_whitelist[] = {
           DMI_MATCH(DMI_BOARD_VENDOR, "Apple"),
           DMI_MATCH(DMI_PRODUCT_NAME, "MacPro") },
                 &applesmc_dmi_data[4]},
+        { applesmc_dmi_match, "Apple iMac 9,1", {
+          DMI_MATCH(DMI_BOARD_VENDOR, "Apple Inc."),
+          DMI_MATCH(DMI_PRODUCT_NAME, "iMac9,1") },
+                &applesmc_dmi_data[17]},
         { applesmc_dmi_match, "Apple iMac 8", {
           DMI_MATCH(DMI_BOARD_VENDOR, "Apple"),
           DMI_MATCH(DMI_PRODUCT_NAME, "iMac8") },
diff --git a/drivers/hwmon/it87.c b/drivers/hwmon/it87.c
index 1002befd87d5..5be09c048c5f 100644
--- a/drivers/hwmon/it87.c
+++ b/drivers/hwmon/it87.c
@@ -539,14 +539,14 @@ static ssize_t set_sensor(struct device *dev, struct device_attribute *attr,
 
         struct it87_data *data = dev_get_drvdata(dev);
         long val;
+        u8 reg;
 
         if (strict_strtol(buf, 10, &val) < 0)
                 return -EINVAL;
 
-        mutex_lock(&data->update_lock);
-
-        data->sensor &= ~(1 << nr);
-        data->sensor &= ~(8 << nr);
+        reg = it87_read_value(data, IT87_REG_TEMP_ENABLE);
+        reg &= ~(1 << nr);
+        reg &= ~(8 << nr);
         if (val == 2) { /* backwards compatibility */
                 dev_warn(dev, "Sensor type 2 is deprecated, please use 4 "
                          "instead\n");
@@ -554,14 +554,16 @@ static ssize_t set_sensor(struct device *dev, struct device_attribute *attr,
         }
         /* 3 = thermal diode; 4 = thermistor; 0 = disabled */
         if (val == 3)
-                data->sensor |= 1 << nr;
+                reg |= 1 << nr;
         else if (val == 4)
-                data->sensor |= 8 << nr;
-        else if (val != 0) {
-                mutex_unlock(&data->update_lock);
+                reg |= 8 << nr;
+        else if (val != 0)
                 return -EINVAL;
-        }
+
+        mutex_lock(&data->update_lock);
+        data->sensor = reg;
         it87_write_value(data, IT87_REG_TEMP_ENABLE, data->sensor);
+        data->valid = 0;        /* Force cache refresh */
         mutex_unlock(&data->update_lock);
         return count;
 }
@@ -1841,14 +1843,10 @@ static void __devinit it87_init_device(struct platform_device *pdev)
                         it87_write_value(data, IT87_REG_TEMP_HIGH(i), 127);
         }
 
-        /* Check if temperature channels are reset manually or by some reason */
-        tmp = it87_read_value(data, IT87_REG_TEMP_ENABLE);
-        if ((tmp & 0x3f) == 0) {
-                /* Temp1,Temp3=thermistor; Temp2=thermal diode */
-                tmp = (tmp & 0xc0) | 0x2a;
-                it87_write_value(data, IT87_REG_TEMP_ENABLE, tmp);
-        }
-        data->sensor = tmp;
+        /* Temperature channels are not forcibly enabled, as they can be
+         * set to two different sensor types and we can't guess which one
+         * is correct for a given system. These channels can be enabled at
+         * run-time through the temp{1-3}_type sysfs accessors if needed. */
 
         /* Check if voltage monitors are reset manually or by some reason */
         tmp = it87_read_value(data, IT87_REG_VIN_ENABLE);
diff --git a/drivers/hwmon/sht15.c b/drivers/hwmon/sht15.c
index 6b2d8ae64fe1..a610e7880fb3 100644
--- a/drivers/hwmon/sht15.c
+++ b/drivers/hwmon/sht15.c
@@ -303,13 +303,13 @@ error_ret:
  **/
 static inline int sht15_calc_temp(struct sht15_data *data)
 {
-        int d1 = 0;
+        int d1 = temppoints[0].d1;
         int i;
 
-        for (i = 1; i < ARRAY_SIZE(temppoints); i++)
+        for (i = ARRAY_SIZE(temppoints) - 1; i > 0; i--)
                 /* Find pointer to interpolate */
                 if (data->supply_uV > temppoints[i - 1].vdd) {
-                        d1 = (data->supply_uV/1000 - temppoints[i - 1].vdd)
+                        d1 = (data->supply_uV - temppoints[i - 1].vdd)
                                 * (temppoints[i].d1 - temppoints[i - 1].d1)
                                 / (temppoints[i].vdd - temppoints[i - 1].vdd)
                                 + temppoints[i - 1].d1;
@@ -542,7 +542,12 @@ static int __devinit sht15_probe(struct platform_device *pdev)
 /* If a regulator is available, query what the supply voltage actually is!*/
         data->reg = regulator_get(data->dev, "vcc");
         if (!IS_ERR(data->reg)) {
-                data->supply_uV = regulator_get_voltage(data->reg);
+                int voltage;
+
+                voltage = regulator_get_voltage(data->reg);
+                if (voltage)
+                        data->supply_uV = voltage;
+
                 regulator_enable(data->reg);
                 /* setup a notifier block to update this if another device
                  *  causes the voltage to change */
diff --git a/drivers/lguest/lguest_device.c b/drivers/lguest/lguest_device.c
index 07090f379c63..69c84a1d88ea 100644
--- a/drivers/lguest/lguest_device.c
+++ b/drivers/lguest/lguest_device.c
@@ -178,7 +178,7 @@ static void set_status(struct virtio_device *vdev, u8 status)
 
         /* We set the status. */
         to_lgdev(vdev)->desc->status = status;
-        kvm_hypercall1(LHCALL_NOTIFY, (max_pfn << PAGE_SHIFT) + offset);
+        hcall(LHCALL_NOTIFY, (max_pfn << PAGE_SHIFT) + offset, 0, 0, 0);
 }
 
 static void lg_set_status(struct virtio_device *vdev, u8 status)
@@ -229,7 +229,7 @@ static void lg_notify(struct virtqueue *vq)
          */
         struct lguest_vq_info *lvq = vq->priv;
 
-        kvm_hypercall1(LHCALL_NOTIFY, lvq->config.pfn << PAGE_SHIFT);
+        hcall(LHCALL_NOTIFY, lvq->config.pfn << PAGE_SHIFT, 0, 0, 0);
 }
 
 /* An extern declaration inside a C file is bad form.  Don't do it. */
diff --git a/drivers/lguest/x86/core.c b/drivers/lguest/x86/core.c
index fb2b7ef7868e..b4eb675a807e 100644
--- a/drivers/lguest/x86/core.c
+++ b/drivers/lguest/x86/core.c
@@ -288,6 +288,18 @@ static int emulate_insn(struct lg_cpu *cpu)
         insn = lgread(cpu, physaddr, u8);
 
         /*
+         * Around 2.6.33, the kernel started using an emulation for the
+         * cmpxchg8b instruction in early boot on many configurations.  This
+         * code isn't paravirtualized, and it tries to disable interrupts.
+         * Ignore it, which will Mostly Work.
+         */
+        if (insn == 0xfa) {
+                /* "cli", or Clear Interrupt Enable instruction.  Skip it. */
+                cpu->regs->eip++;
+                return 1;
+        }
+
+        /*
          * 0x66 is an "operand prefix".  It means it's using the upper 16 bits
          * of the eax register.
          */
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index aa3cd7cc3e40..412593703d1e 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -337,16 +337,15 @@ out:
 /*
  * Get ref for the oldest snapc for an inode with dirty data... that is, the
  * only snap context we are allowed to write back.
- *
- * Caller holds i_lock.
  */
-static struct ceph_snap_context *__get_oldest_context(struct inode *inode,
-                                                      u64 *snap_size)
+static struct ceph_snap_context *get_oldest_context(struct inode *inode,
+                                                    u64 *snap_size)
 {
         struct ceph_inode_info *ci = ceph_inode(inode);
         struct ceph_snap_context *snapc = NULL;
         struct ceph_cap_snap *capsnap = NULL;
 
+        spin_lock(&inode->i_lock);
         list_for_each_entry(capsnap, &ci->i_cap_snaps, ci_item) {
                 dout(" cap_snap %p snapc %p has %d dirty pages\n", capsnap,
                      capsnap->context, capsnap->dirty_pages);
@@ -357,21 +356,11 @@ static struct ceph_snap_context *__get_oldest_context(struct inode *inode,
                         break;
                 }
         }
-        if (!snapc && ci->i_snap_realm) {
-                snapc = ceph_get_snap_context(ci->i_snap_realm->cached_context);
+        if (!snapc && ci->i_head_snapc) {
+                snapc = ceph_get_snap_context(ci->i_head_snapc);
                 dout(" head snapc %p has %d dirty pages\n",
                      snapc, ci->i_wrbuffer_ref_head);
         }
-        return snapc;
-}
-
-static struct ceph_snap_context *get_oldest_context(struct inode *inode,
-                                                    u64 *snap_size)
-{
-        struct ceph_snap_context *snapc = NULL;
-
-        spin_lock(&inode->i_lock);
-        snapc = __get_oldest_context(inode, snap_size);
         spin_unlock(&inode->i_lock);
         return snapc;
 }
@@ -392,7 +381,7 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc)
         int len = PAGE_CACHE_SIZE;
         loff_t i_size;
         int err = 0;
-        struct ceph_snap_context *snapc;
+        struct ceph_snap_context *snapc, *oldest;
         u64 snap_size = 0;
         long writeback_stat;
 
@@ -413,13 +402,16 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc)
                 dout("writepage %p page %p not dirty?\n", inode, page);
                 goto out;
         }
-        if (snapc != get_oldest_context(inode, &snap_size)) {
+        oldest = get_oldest_context(inode, &snap_size);
+        if (snapc->seq > oldest->seq) {
                 dout("writepage %p page %p snapc %p not writeable - noop\n",
                      inode, page, (void *)page->private);
                 /* we should only noop if called by kswapd */
                 WARN_ON((current->flags & PF_MEMALLOC) == 0);
+                ceph_put_snap_context(oldest);
                 goto out;
         }
+        ceph_put_snap_context(oldest);
 
         /* is this a partial page at end of file? */
         if (snap_size)
@@ -458,7 +450,7 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc)
         ClearPagePrivate(page);
         end_page_writeback(page);
         ceph_put_wrbuffer_cap_refs(ci, 1, snapc);
-        ceph_put_snap_context(snapc);
+        ceph_put_snap_context(snapc);  /* page's reference */
 out:
         return err;
 }
@@ -558,9 +550,9 @@ static void writepages_finish(struct ceph_osd_request *req,
                         dout("inode %p skipping page %p\n", inode, page);
                         wbc->pages_skipped++;
                 }
+                ceph_put_snap_context((void *)page->private);
                 page->private = 0;
                 ClearPagePrivate(page);
-                ceph_put_snap_context(snapc);
                 dout("unlocking %d %p\n", i, page);
                 end_page_writeback(page);
 
@@ -618,7 +610,7 @@ static int ceph_writepages_start(struct address_space *mapping,
         int range_whole = 0;
         int should_loop = 1;
         pgoff_t max_pages = 0, max_pages_ever = 0;
-        struct ceph_snap_context *snapc = NULL, *last_snapc = NULL;
+        struct ceph_snap_context *snapc = NULL, *last_snapc = NULL, *pgsnapc;
         struct pagevec pvec;
         int done = 0;
         int rc = 0;
@@ -770,9 +762,10 @@ get_more_pages:
                         }
 
                         /* only if matching snap context */
-                        if (snapc != (void *)page->private) {
-                                dout("page snapc %p != oldest %p\n",
-                                     (void *)page->private, snapc);
+                        pgsnapc = (void *)page->private;
+                        if (pgsnapc->seq > snapc->seq) {
+                                dout("page snapc %p %lld > oldest %p %lld\n",
+                                     pgsnapc, pgsnapc->seq, snapc, snapc->seq);
                                 unlock_page(page);
                                 if (!locked_pages)
                                         continue; /* keep looking for snap */
@@ -914,7 +907,10 @@ static int context_is_writeable_or_written(struct inode *inode,
                                            struct ceph_snap_context *snapc)
 {
         struct ceph_snap_context *oldest = get_oldest_context(inode, NULL);
-        return !oldest || snapc->seq <= oldest->seq;
+        int ret = !oldest || snapc->seq <= oldest->seq;
+
+        ceph_put_snap_context(oldest);
+        return ret;
 }
 
 /*
@@ -936,8 +932,8 @@ static int ceph_update_writeable_page(struct file *file,
         int pos_in_page = pos & ~PAGE_CACHE_MASK;
         int end_in_page = pos_in_page + len;
         loff_t i_size;
-        struct ceph_snap_context *snapc;
         int r;
+        struct ceph_snap_context *snapc, *oldest;
 
 retry_locked:
         /* writepages currently holds page lock, but if we change that later, */
@@ -947,23 +943,24 @@ retry_locked:
         BUG_ON(!ci->i_snap_realm);
         down_read(&mdsc->snap_rwsem);
         BUG_ON(!ci->i_snap_realm->cached_context);
-        if (page->private &&
-            (void *)page->private != ci->i_snap_realm->cached_context) {
+        snapc = (void *)page->private;
+        if (snapc && snapc != ci->i_head_snapc) {
                 /*
                  * this page is already dirty in another (older) snap
                  * context!  is it writeable now?
                  */
-                snapc = get_oldest_context(inode, NULL);
+                oldest = get_oldest_context(inode, NULL);
                 up_read(&mdsc->snap_rwsem);
 
-                if (snapc != (void *)page->private) {
+                if (snapc->seq > oldest->seq) {
+                        ceph_put_snap_context(oldest);
                         dout(" page %p snapc %p not current or oldest\n",
-                             page, (void *)page->private);
+                             page, snapc);
                         /*
                          * queue for writeback, and wait for snapc to
                          * be writeable or written
                          */
-                        snapc = ceph_get_snap_context((void *)page->private);
+                        snapc = ceph_get_snap_context(snapc);
                         unlock_page(page);
                         ceph_queue_writeback(inode);
                         r = wait_event_interruptible(ci->i_cap_wq,
@@ -973,6 +970,7 @@ retry_locked:
                                 return r;
                         return -EAGAIN;
                 }
+                ceph_put_snap_context(oldest);
 
                 /* yay, writeable, do it now (without dropping page lock) */
                 dout(" page %p snapc %p not current, but oldest\n",
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index 3710e077a857..aa2239fa9a3b 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -1205,6 +1205,12 @@ retry:
                 if (capsnap->dirty_pages || capsnap->writing)
                         continue;
 
+                /*
+                 * if cap writeback already occurred, we should have dropped
+                 * the capsnap in ceph_put_wrbuffer_cap_refs.
+                 */
+                BUG_ON(capsnap->dirty == 0);
+
                 /* pick mds, take s_mutex */
                 mds = __ceph_get_cap_mds(ci, &mseq);
                 if (session && session->s_mds != mds) {
@@ -2118,8 +2124,8 @@ void ceph_put_cap_refs(struct ceph_inode_info *ci, int had)
                 }
         spin_unlock(&inode->i_lock);
 
-        dout("put_cap_refs %p had %s %s\n", inode, ceph_cap_string(had),
-             last ? "last" : "");
+        dout("put_cap_refs %p had %s%s%s\n", inode, ceph_cap_string(had),
+             last ? " last" : "", put ? " put" : "");
 
         if (last && !flushsnaps)
                 ceph_check_caps(ci, 0, NULL);
@@ -2143,7 +2149,8 @@ void ceph_put_wrbuffer_cap_refs(struct ceph_inode_info *ci, int nr,
 {
         struct inode *inode = &ci->vfs_inode;
         int last = 0;
-        int last_snap = 0;
+        int complete_capsnap = 0;
+        int drop_capsnap = 0;
         int found = 0;
         struct ceph_cap_snap *capsnap = NULL;
 
@@ -2166,19 +2173,32 @@ void ceph_put_wrbuffer_cap_refs(struct ceph_inode_info *ci, int nr,
                 list_for_each_entry(capsnap, &ci->i_cap_snaps, ci_item) {
                         if (capsnap->context == snapc) {
                                 found = 1;
-                                capsnap->dirty_pages -= nr;
-                                last_snap = !capsnap->dirty_pages;
                                 break;
                         }
                 }
                 BUG_ON(!found);
+                capsnap->dirty_pages -= nr;
+                if (capsnap->dirty_pages == 0) {
+                        complete_capsnap = 1;
+                        if (capsnap->dirty == 0)
+                                /* cap writeback completed before we created
+                                 * the cap_snap; no FLUSHSNAP is needed */
+                                drop_capsnap = 1;
+                }
                 dout("put_wrbuffer_cap_refs on %p cap_snap %p "
-                     " snap %lld %d/%d -> %d/%d %s%s\n",
+                     " snap %lld %d/%d -> %d/%d %s%s%s\n",
                      inode, capsnap, capsnap->context->seq,
                      ci->i_wrbuffer_ref+nr, capsnap->dirty_pages + nr,
                      ci->i_wrbuffer_ref, capsnap->dirty_pages,
                      last ? " (wrbuffer last)" : "",
-                     last_snap ? " (capsnap last)" : "");
+                     complete_capsnap ? " (complete capsnap)" : "",
+                     drop_capsnap ? " (drop capsnap)" : "");
+                if (drop_capsnap) {
+                        ceph_put_snap_context(capsnap->context);
+                        list_del(&capsnap->ci_item);
+                        list_del(&capsnap->flushing_item);
+                        ceph_put_cap_snap(capsnap);
+                }
         }
 
         spin_unlock(&inode->i_lock);
@@ -2186,10 +2206,12 @@ void ceph_put_wrbuffer_cap_refs(struct ceph_inode_info *ci, int nr,
         if (last) {
                 ceph_check_caps(ci, CHECK_CAPS_AUTHONLY, NULL);
                 iput(inode);
-        } else if (last_snap) {
+        } else if (complete_capsnap) {
                 ceph_flush_snaps(ci);
                 wake_up(&ci->i_cap_wq);
         }
+        if (drop_capsnap)
+                iput(inode);
 }
 
 /*
@@ -2465,8 +2487,8 @@ static void handle_cap_flushsnap_ack(struct inode *inode, u64 flush_tid,
                                 break;
                         }
                         WARN_ON(capsnap->dirty_pages || capsnap->writing);
-                        dout(" removing cap_snap %p follows %lld\n",
-                             capsnap, follows);
+                        dout(" removing %p cap_snap %p follows %lld\n",
+                             inode, capsnap, follows);
                         ceph_put_snap_context(capsnap->context);
                         list_del(&capsnap->ci_item);
                         list_del(&capsnap->flushing_item);
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index 7261dc6c2ead..ea8ee2e526aa 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -171,11 +171,11 @@ more:
         spin_lock(&inode->i_lock);
         spin_lock(&dcache_lock);
 
+        last = dentry;
+
         if (err < 0)
                 goto out_unlock;
 
-        last = dentry;
-
         p = p->prev;
         filp->f_pos++;
 
@@ -312,7 +312,7 @@ more:
                 req->r_readdir_offset = fi->next_offset;
                 req->r_args.readdir.frag = cpu_to_le32(frag);
                 req->r_args.readdir.max_entries = cpu_to_le32(max_entries);
-                req->r_num_caps = max_entries;
+                req->r_num_caps = max_entries + 1;
                 err = ceph_mdsc_do_request(mdsc, NULL, req);
                 if (err < 0) {
                         ceph_mdsc_put_request(req);
@@ -489,6 +489,7 @@ struct dentry *ceph_finish_lookup(struct ceph_mds_request *req,
                 struct inode *inode = ceph_get_snapdir(parent);
                 dout("ENOENT on snapdir %p '%.*s', linking to snapdir %p\n",
                      dentry, dentry->d_name.len, dentry->d_name.name, inode);
+                BUG_ON(!d_unhashed(dentry));
                 d_add(dentry, inode);
                 err = 0;
         }
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index aca82d55cc53..26f883c275e8 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -886,6 +886,7 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req,
         struct inode *in = NULL;
         struct ceph_mds_reply_inode *ininfo;
         struct ceph_vino vino;
+        struct ceph_client *client = ceph_sb_to_client(sb);
         int i = 0;
         int err = 0;
 
@@ -949,7 +950,14 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req,
                         return err;
         }
 
-        if (rinfo->head->is_dentry && !req->r_aborted) {
+        /*
+         * ignore null lease/binding on snapdir ENOENT, or else we
+         * will have trouble splicing in the virtual snapdir later
+         */
+        if (rinfo->head->is_dentry && !req->r_aborted &&
+            (rinfo->head->is_target || strncmp(req->r_dentry->d_name.name,
+                                               client->mount_args->snapdir_name,
+                                               req->r_dentry->d_name.len))) {
                 /*
                  * lookup link rename   : null -> possibly existing inode
                  * mknod symlink mkdir  : null -> new inode
diff --git a/fs/ceph/messenger.c b/fs/ceph/messenger.c
index 8f1715ffbe4b..cdaaa131add3 100644
--- a/fs/ceph/messenger.c
+++ b/fs/ceph/messenger.c
@@ -30,6 +30,10 @@ static char tag_msg = CEPH_MSGR_TAG_MSG;
 static char tag_ack = CEPH_MSGR_TAG_ACK;
 static char tag_keepalive = CEPH_MSGR_TAG_KEEPALIVE;
 
+#ifdef CONFIG_LOCKDEP
+static struct lock_class_key socket_class;
+#endif
+
 
 static void queue_con(struct ceph_connection *con);
 static void con_work(struct work_struct *);
@@ -228,6 +232,10 @@ static struct socket *ceph_tcp_connect(struct ceph_connection *con)
         con->sock = sock;
         sock->sk->sk_allocation = GFP_NOFS;
 
+#ifdef CONFIG_LOCKDEP
+        lockdep_set_class(&sock->sk->sk_lock, &socket_class);
+#endif
+
         set_sock_callbacks(sock, con);
 
         dout("connect %s\n", pr_addr(&con->peer_addr.in_addr));
@@ -333,6 +341,7 @@ static void reset_connection(struct ceph_connection *con)
                 con->out_msg = NULL;
         }
         con->in_seq = 0;
+        con->in_seq_acked = 0;
 }
 
 /*
diff --git a/fs/ceph/osdmap.c b/fs/ceph/osdmap.c
index 21c6623c4b07..2e2c15eed82a 100644
--- a/fs/ceph/osdmap.c
+++ b/fs/ceph/osdmap.c
@@ -314,71 +314,6 @@ bad:
         return ERR_PTR(err);
 }
 
-
-/*
- * osd map
- */
-void ceph_osdmap_destroy(struct ceph_osdmap *map)
-{
-        dout("osdmap_destroy %p\n", map);
-        if (map->crush)
-                crush_destroy(map->crush);
-        while (!RB_EMPTY_ROOT(&map->pg_temp)) {
-                struct ceph_pg_mapping *pg =
-                        rb_entry(rb_first(&map->pg_temp),
-                                 struct ceph_pg_mapping, node);
-                rb_erase(&pg->node, &map->pg_temp);
-                kfree(pg);
-        }
-        while (!RB_EMPTY_ROOT(&map->pg_pools)) {
-                struct ceph_pg_pool_info *pi =
-                        rb_entry(rb_first(&map->pg_pools),
-                                 struct ceph_pg_pool_info, node);
-                rb_erase(&pi->node, &map->pg_pools);
-                kfree(pi);
-        }
-        kfree(map->osd_state);
-        kfree(map->osd_weight);
-        kfree(map->osd_addr);
-        kfree(map);
-}
-
-/*
- * adjust max osd value.  reallocate arrays.
- */
-static int osdmap_set_max_osd(struct ceph_osdmap *map, int max)
-{
-        u8 *state;
-        struct ceph_entity_addr *addr;
-        u32 *weight;
-
-        state = kcalloc(max, sizeof(*state), GFP_NOFS);
-        addr = kcalloc(max, sizeof(*addr), GFP_NOFS);
-        weight = kcalloc(max, sizeof(*weight), GFP_NOFS);
-        if (state == NULL || addr == NULL || weight == NULL) {
-                kfree(state);
-                kfree(addr);
-                kfree(weight);
-                return -ENOMEM;
-        }
-
-        /* copy old? */
-        if (map->osd_state) {
-                memcpy(state, map->osd_state, map->max_osd*sizeof(*state));
-                memcpy(addr, map->osd_addr, map->max_osd*sizeof(*addr));
-                memcpy(weight, map->osd_weight, map->max_osd*sizeof(*weight));
-                kfree(map->osd_state);
-                kfree(map->osd_addr);
-                kfree(map->osd_weight);
-        }
-
-        map->osd_state = state;
-        map->osd_weight = weight;
-        map->osd_addr = addr;
-        map->max_osd = max;
-        return 0;
-}
-
 /*
  * rbtree of pg_mapping for handling pg_temp (explicit mapping of pgid
  * to a set of osds)
@@ -482,6 +417,13 @@ static struct ceph_pg_pool_info *__lookup_pg_pool(struct rb_root *root, int id)
         return NULL;
 }
 
+static void __remove_pg_pool(struct rb_root *root, struct ceph_pg_pool_info *pi)
+{
+        rb_erase(&pi->node, root);
+        kfree(pi->name);
+        kfree(pi);
+}
+
 void __decode_pool(void **p, struct ceph_pg_pool_info *pi)
 {
         ceph_decode_copy(p, &pi->v, sizeof(pi->v));
@@ -490,6 +432,98 @@ void __decode_pool(void **p, struct ceph_pg_pool_info *pi)
         *p += le32_to_cpu(pi->v.num_removed_snap_intervals) * sizeof(u64) * 2;
 }
 
+static int __decode_pool_names(void **p, void *end, struct ceph_osdmap *map)
+{
+        struct ceph_pg_pool_info *pi;
+        u32 num, len, pool;
+
+        ceph_decode_32_safe(p, end, num, bad);
+        dout(" %d pool names\n", num);
+        while (num--) {
+                ceph_decode_32_safe(p, end, pool, bad);
+                ceph_decode_32_safe(p, end, len, bad);
+                dout("  pool %d len %d\n", pool, len);
+                pi = __lookup_pg_pool(&map->pg_pools, pool);
+                if (pi) {
+                        kfree(pi->name);
+                        pi->name = kmalloc(len + 1, GFP_NOFS);
+                        if (pi->name) {
+                                memcpy(pi->name, *p, len);
+                                pi->name[len] = '\0';
+                                dout("  name is %s\n", pi->name);
+                        }
+                }
+                *p += len;
+        }
+        return 0;
+
+bad:
+        return -EINVAL;
+}
+
+/*
+ * osd map
+ */
+void ceph_osdmap_destroy(struct ceph_osdmap *map)
+{
+        dout("osdmap_destroy %p\n", map);
+        if (map->crush)
+                crush_destroy(map->crush);
+        while (!RB_EMPTY_ROOT(&map->pg_temp)) {
+                struct ceph_pg_mapping *pg =
+                        rb_entry(rb_first(&map->pg_temp),
+                                 struct ceph_pg_mapping, node);
+                rb_erase(&pg->node, &map->pg_temp);
+                kfree(pg);
+        }
+        while (!RB_EMPTY_ROOT(&map->pg_pools)) {
+                struct ceph_pg_pool_info *pi =
+                        rb_entry(rb_first(&map->pg_pools),
+                                 struct ceph_pg_pool_info, node);
+                __remove_pg_pool(&map->pg_pools, pi);
+        }
+        kfree(map->osd_state);
+        kfree(map->osd_weight);
+        kfree(map->osd_addr);
+        kfree(map);
+}
+
+/*
+ * adjust max osd value.  reallocate arrays.
+ */
+static int osdmap_set_max_osd(struct ceph_osdmap *map, int max)
+{
+        u8 *state;
+        struct ceph_entity_addr *addr;
+        u32 *weight;
+
+        state = kcalloc(max, sizeof(*state), GFP_NOFS);
+        addr = kcalloc(max, sizeof(*addr), GFP_NOFS);
+        weight = kcalloc(max, sizeof(*weight), GFP_NOFS);
+        if (state == NULL || addr == NULL || weight == NULL) {
+                kfree(state);
+                kfree(addr);
+                kfree(weight);
+                return -ENOMEM;
+        }
+
+        /* copy old? */
+        if (map->osd_state) {
+                memcpy(state, map->osd_state, map->max_osd*sizeof(*state));
+                memcpy(addr, map->osd_addr, map->max_osd*sizeof(*addr));
+                memcpy(weight, map->osd_weight, map->max_osd*sizeof(*weight));
+                kfree(map->osd_state);
+                kfree(map->osd_addr);
+                kfree(map->osd_weight);
+        }
+
+        map->osd_state = state;
+        map->osd_weight = weight;
+        map->osd_addr = addr;
+        map->max_osd = max;
+        return 0;
+}
+
 /*
  * decode a full map.
  */
@@ -526,7 +560,7 @@ struct ceph_osdmap *osdmap_decode(void **p, void *end)
         ceph_decode_32_safe(p, end, max, bad);
         while (max--) {
                 ceph_decode_need(p, end, 4 + 1 + sizeof(pi->v), bad);
-                pi = kmalloc(sizeof(*pi), GFP_NOFS);
+                pi = kzalloc(sizeof(*pi), GFP_NOFS);
                 if (!pi)
                         goto bad;
                 pi->id = ceph_decode_32(p);
@@ -539,6 +573,10 @@ struct ceph_osdmap *osdmap_decode(void **p, void *end)
                 __decode_pool(p, pi);
                 __insert_pg_pool(&map->pg_pools, pi);
         }
+
+        if (version >= 5 && __decode_pool_names(p, end, map) < 0)
+                goto bad;
+
         ceph_decode_32_safe(p, end, map->pool_max, bad);
 
         ceph_decode_32_safe(p, end, map->flags, bad);
@@ -712,7 +750,7 @@ struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end,
                 }
                 pi = __lookup_pg_pool(&map->pg_pools, pool);
                 if (!pi) {
-                        pi = kmalloc(sizeof(*pi), GFP_NOFS);
+                        pi = kzalloc(sizeof(*pi), GFP_NOFS);
                         if (!pi) {
                                 err = -ENOMEM;
                                 goto bad;
@@ -722,6 +760,8 @@ struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end,
                 }
                 __decode_pool(p, pi);
         }
+        if (version >= 5 && __decode_pool_names(p, end, map) < 0)
+                goto bad;
 
         /* old_pool */
         ceph_decode_32_safe(p, end, len, bad);
@@ -730,10 +770,8 @@ struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end,
 
                 ceph_decode_32_safe(p, end, pool, bad);
                 pi = __lookup_pg_pool(&map->pg_pools, pool);
-                if (pi) {
-                        rb_erase(&pi->node, &map->pg_pools);
-                        kfree(pi);
-                }
+                if (pi)
+                        __remove_pg_pool(&map->pg_pools, pi);
         }
 
         /* new_up */
diff --git a/fs/ceph/osdmap.h b/fs/ceph/osdmap.h
index 1fb55afb2642..8bc9f1e4f562 100644
--- a/fs/ceph/osdmap.h
+++ b/fs/ceph/osdmap.h
@@ -23,6 +23,7 @@ struct ceph_pg_pool_info {
         int id;
         struct ceph_pg_pool v;
         int pg_num_mask, pgp_num_mask, lpg_num_mask, lpgp_num_mask;
+        char *name;
 };
 
 struct ceph_pg_mapping {
diff --git a/fs/ceph/rados.h b/fs/ceph/rados.h
index 26ac8b89a676..a1fc1d017b58 100644
--- a/fs/ceph/rados.h
+++ b/fs/ceph/rados.h
@@ -11,8 +11,10 @@
 /*
  * osdmap encoding versions
  */
-#define CEPH_OSDMAP_INC_VERSION 4
-#define CEPH_OSDMAP_VERSION     4
+#define CEPH_OSDMAP_INC_VERSION     5
+#define CEPH_OSDMAP_INC_VERSION_EXT 5
+#define CEPH_OSDMAP_VERSION         5
+#define CEPH_OSDMAP_VERSION_EXT     5
 
 /*
  * fs id
diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c
index e6f9bc57d472..2b881262ef67 100644
--- a/fs/ceph/snap.c
+++ b/fs/ceph/snap.c
@@ -431,8 +431,7 @@ static int dup_array(u64 **dst, __le64 *src, int num)
  * Caller must hold snap_rwsem for read (i.e., the realm topology won't
  * change).
  */
-void ceph_queue_cap_snap(struct ceph_inode_info *ci,
-                         struct ceph_snap_context *snapc)
+void ceph_queue_cap_snap(struct ceph_inode_info *ci)
 {
         struct inode *inode = &ci->vfs_inode;
         struct ceph_cap_snap *capsnap;
@@ -451,10 +450,11 @@ void ceph_queue_cap_snap(struct ceph_inode_info *ci,
                    as no new writes are allowed to start when pending, so any
                    writes in progress now were started before the previous
                    cap_snap.  lucky us. */
-                dout("queue_cap_snap %p snapc %p seq %llu used %d"
-                     " already pending\n", inode, snapc, snapc->seq, used);
+                dout("queue_cap_snap %p already pending\n", inode);
                 kfree(capsnap);
         } else if (ci->i_wrbuffer_ref_head || (used & CEPH_CAP_FILE_WR)) {
+                struct ceph_snap_context *snapc = ci->i_head_snapc;
+
                 igrab(inode);
 
                 atomic_set(&capsnap->nref, 1);
@@ -463,7 +463,6 @@ void ceph_queue_cap_snap(struct ceph_inode_info *ci,
                 INIT_LIST_HEAD(&capsnap->flushing_item);
 
                 capsnap->follows = snapc->seq - 1;
-                capsnap->context = ceph_get_snap_context(snapc);
                 capsnap->issued = __ceph_caps_issued(ci, NULL);
                 capsnap->dirty = __ceph_caps_dirty(ci);
 
@@ -480,7 +479,7 @@ void ceph_queue_cap_snap(struct ceph_inode_info *ci,
                    snapshot. */
                 capsnap->dirty_pages = ci->i_wrbuffer_ref_head;
                 ci->i_wrbuffer_ref_head = 0;
-                ceph_put_snap_context(ci->i_head_snapc);
+                capsnap->context = snapc;
                 ci->i_head_snapc = NULL;
                 list_add_tail(&capsnap->ci_item, &ci->i_cap_snaps);
 
@@ -522,15 +521,17 @@ int __ceph_finish_cap_snap(struct ceph_inode_info *ci,
         capsnap->ctime = inode->i_ctime;
         capsnap->time_warp_seq = ci->i_time_warp_seq;
         if (capsnap->dirty_pages) {
-                dout("finish_cap_snap %p cap_snap %p snapc %p %llu s=%llu "
+                dout("finish_cap_snap %p cap_snap %p snapc %p %llu %s s=%llu "
                      "still has %d dirty pages\n", inode, capsnap,
                      capsnap->context, capsnap->context->seq,
-                     capsnap->size, capsnap->dirty_pages);
+                     ceph_cap_string(capsnap->dirty), capsnap->size,
+                     capsnap->dirty_pages);
                 return 0;
         }
-        dout("finish_cap_snap %p cap_snap %p snapc %p %llu s=%llu clean\n",
+        dout("finish_cap_snap %p cap_snap %p snapc %p %llu %s s=%llu\n",
              inode, capsnap, capsnap->context,
-             capsnap->context->seq, capsnap->size);
+             capsnap->context->seq, ceph_cap_string(capsnap->dirty),
+             capsnap->size);
 
         spin_lock(&mdsc->snap_flush_lock);
         list_add_tail(&ci->i_snap_flush_item, &mdsc->snap_flush_list);
@@ -602,7 +603,7 @@ more:
                                 if (lastinode)
                                         iput(lastinode);
                                 lastinode = inode;
-                                ceph_queue_cap_snap(ci, realm->cached_context);
+                                ceph_queue_cap_snap(ci);
                                 spin_lock(&realm->inodes_with_caps_lock);
                         }
                         spin_unlock(&realm->inodes_with_caps_lock);
@@ -824,8 +825,7 @@ void ceph_handle_snap(struct ceph_mds_client *mdsc,
                         spin_unlock(&realm->inodes_with_caps_lock);
                         spin_unlock(&inode->i_lock);
 
-                        ceph_queue_cap_snap(ci,
-                                            ci->i_snap_realm->cached_context);
+                        ceph_queue_cap_snap(ci);
 
                         iput(inode);
                         continue;
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index ca702c67bc66..e30dfbb056c3 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -715,8 +715,7 @@ extern int ceph_update_snap_trace(struct ceph_mds_client *m,
 extern void ceph_handle_snap(struct ceph_mds_client *mdsc,
                              struct ceph_mds_session *session,
                              struct ceph_msg *msg);
-extern void ceph_queue_cap_snap(struct ceph_inode_info *ci,
-                                struct ceph_snap_context *snapc);
+extern void ceph_queue_cap_snap(struct ceph_inode_info *ci);
 extern int __ceph_finish_cap_snap(struct ceph_inode_info *ci,
                                   struct ceph_cap_snap *capsnap);
 extern void ceph_cleanup_empty_realms(struct ceph_mds_client *mdsc);
diff --git a/lib/vsprintf.c b/lib/vsprintf.c
index 24112e5a5780..7376b7c55ffe 100644
--- a/lib/vsprintf.c
+++ b/lib/vsprintf.c
@@ -408,12 +408,12 @@ enum format_type {
 };
 
 struct printf_spec {
-        u16     type;
-        s16     field_width;    /* width of output field */
+        u8      type;           /* format_type enum */
         u8      flags;          /* flags to number() */
-        u8      base;
-        s8      precision;      /* # of digits/chars */
-        u8      qualifier;
+        u8      base;           /* number base, 8, 10 or 16 only */
+        u8      qualifier;      /* number qualifier, one of 'hHlLtzZ' */
+        s16     field_width;    /* width of output field */
+        s16     precision;      /* # of digits/chars */
 };
 
 static char *number(char *buf, char *end, unsigned long long num,