Merge branch 'rt/base' into rt/head

Documentation/filesystems/9p.txt

@@ -123,6 +123,9 @@ available from the same CVS repository.
 There are user and developer mailing lists available through the v9fs project
 on sourceforge (http://sourceforge.net/projects/v9fs).
 
+A stand-alone version of the module (which should build for any 2.6 kernel)
+is available via (http://github.com/ericvh/9p-sac/tree/master)
+
 News and other information is maintained on SWiK (http://swik.net/v9fs).
 
 Bug reports may be issued through the kernel.org bugzilla 

Makefile

 VERSION = 2
 PATCHLEVEL = 6
 SUBLEVEL = 31
-EXTRAVERSION = -rc7
+EXTRAVERSION = -rc8
 NAME = Man-Eating Seals of Antiquity
 
 # *DOCUMENTATION*

arch/m68k/amiga/config.c

@@ -574,10 +574,11 @@ static int a2000_hwclk(int op, struct rtc_time *t)
 
 	tod_2000.cntrl1 = TOD2000_CNTRL1_HOLD;
 
-	while ((tod_2000.cntrl1 & TOD2000_CNTRL1_BUSY) && cnt--) {
+	while ((tod_2000.cntrl1 & TOD2000_CNTRL1_BUSY) && cnt) {
 		tod_2000.cntrl1 &= ~TOD2000_CNTRL1_HOLD;
 		udelay(70);
 		tod_2000.cntrl1 |= TOD2000_CNTRL1_HOLD;
+		--cnt;
 	}
 
 	if (!cnt)
@@ -649,10 +650,11 @@ static int amiga_set_clock_mmss(unsigned long nowtime)
 
 		tod_2000.cntrl1 |= TOD2000_CNTRL1_HOLD;
 
-		while ((tod_2000.cntrl1 & TOD2000_CNTRL1_BUSY) && cnt--) {
+		while ((tod_2000.cntrl1 & TOD2000_CNTRL1_BUSY) && cnt) {
 			tod_2000.cntrl1 &= ~TOD2000_CNTRL1_HOLD;
 			udelay(70);
 			tod_2000.cntrl1 |= TOD2000_CNTRL1_HOLD;
+			--cnt;
 		}
 
 		if (!cnt)

arch/m68k/include/asm/motorola_pgalloc.h

@@ -36,12 +36,10 @@ static inline pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long addres
 		return NULL;
 
 	pte = kmap(page);
-	if (pte) {
-		__flush_page_to_ram(pte);
-		flush_tlb_kernel_page(pte);
-		nocache_page(pte);
-	}
-	kunmap(pte);
+	__flush_page_to_ram(pte);
+	flush_tlb_kernel_page(pte);
+	nocache_page(pte);
+	kunmap(page);
 	pgtable_page_ctor(page);
 	return page;
 }

arch/m68k/include/asm/pgtable_mm.h

@@ -135,8 +135,6 @@ static inline void update_mmu_cache(struct vm_area_struct *vma,
 #endif
 
 #ifndef __ASSEMBLY__
-#include <asm-generic/pgtable.h>
-
 /*
  * Macro to mark a page protection value as "uncacheable".
  */
@@ -154,6 +152,7 @@ static inline void update_mmu_cache(struct vm_area_struct *vma,
 	    ? (__pgprot((pgprot_val(prot) & _CACHEMASK040) | _PAGE_NOCACHE_S))	\
 	    : (prot)))
 
+#include <asm-generic/pgtable.h>
 #endif /* !__ASSEMBLY__ */
 
 /*

arch/m68k/include/asm/unistd.h

@@ -334,10 +334,12 @@
 #define __NR_inotify_init1	328
 #define __NR_preadv		329
 #define __NR_pwritev		330
+#define __NR_rt_tgsigqueueinfo	331
+#define __NR_perf_counter_open	332
 
 #ifdef __KERNEL__
 
-#define NR_syscalls		331
+#define NR_syscalls		333
 
 #define __ARCH_WANT_IPC_PARSE_VERSION
 #define __ARCH_WANT_OLD_READDIR

arch/m68k/kernel/entry.S

@@ -755,4 +755,6 @@ sys_call_table:
 	.long sys_inotify_init1
 	.long sys_preadv
 	.long sys_pwritev		/* 330 */
+	.long sys_rt_tgsigqueueinfo
+	.long sys_perf_counter_open
 

arch/m68knommu/kernel/syscalltable.S

@@ -349,6 +349,8 @@ ENTRY(sys_call_table)
 	.long sys_inotify_init1
 	.long sys_preadv
 	.long sys_pwritev		/* 330 */
+	.long sys_rt_tgsigqueueinfo
+	.long sys_perf_counter_open
 
 	.rept NR_syscalls-(.-sys_call_table)/4
 		.long sys_ni_syscall

arch/powerpc/platforms/ps3/time.c

@@ -21,6 +21,7 @@
 #include <linux/kernel.h>
 #include <linux/platform_device.h>
 
+#include <asm/firmware.h>
 #include <asm/rtc.h>
 #include <asm/lv1call.h>
 #include <asm/ps3.h>
@@ -84,6 +85,9 @@ static int __init ps3_rtc_init(void)
 {
 	struct platform_device *pdev;
 
+	if (!firmware_has_feature(FW_FEATURE_PS3_LV1))
+		return -ENODEV;
+
 	pdev = platform_device_register_simple("rtc-ps3", -1, NULL, 0);
 	if (IS_ERR(pdev))
 		return PTR_ERR(pdev);

drivers/acpi/processor_core.c

@@ -1151,6 +1151,9 @@ static int __init acpi_processor_init(void)
 {
 	int result = 0;
 
+	if (acpi_disabled)
+		return 0;
+
 	memset(&errata, 0, sizeof(errata));
 
 #ifdef CONFIG_SMP
@@ -1197,6 +1200,9 @@ out_proc:
 
 static void __exit acpi_processor_exit(void)
 {
+	if (acpi_disabled)
+		return;
+
 	acpi_processor_ppc_exit();
 
 	acpi_thermal_cpufreq_exit();

drivers/acpi/processor_thermal.c

@@ -66,7 +66,7 @@ static int acpi_processor_apply_limit(struct acpi_processor *pr)
 		if (pr->limit.thermal.tx > tx)
 			tx = pr->limit.thermal.tx;
 
-		result = acpi_processor_set_throttling(pr, tx);
+		result = acpi_processor_set_throttling(pr, tx, false);
 		if (result)
 			goto end;
 	}
@@ -421,12 +421,12 @@ processor_set_cur_state(struct thermal_cooling_device *cdev,
 
 	if (state <= max_pstate) {
 		if (pr->flags.throttling && pr->throttling.state)
-			result = acpi_processor_set_throttling(pr, 0);
+			result = acpi_processor_set_throttling(pr, 0, false);
 		cpufreq_set_cur_state(pr->id, state);
 	} else {
 		cpufreq_set_cur_state(pr->id, max_pstate);
 		result = acpi_processor_set_throttling(pr,
-				state - max_pstate);
+				state - max_pstate, false);
 	}
 	return result;
 }

drivers/acpi/processor_throttling.c

@@ -62,7 +62,8 @@ struct throttling_tstate {
 #define THROTTLING_POSTCHANGE      (2)
 
 static int acpi_processor_get_throttling(struct acpi_processor *pr);
-int acpi_processor_set_throttling(struct acpi_processor *pr, int state);
+int acpi_processor_set_throttling(struct acpi_processor *pr,
+						int state, bool force);
 
 static int acpi_processor_update_tsd_coord(void)
 {
@@ -361,7 +362,7 @@ int acpi_processor_tstate_has_changed(struct acpi_processor *pr)
 		 */
 		target_state = throttling_limit;
 	}
-	return acpi_processor_set_throttling(pr, target_state);
+	return acpi_processor_set_throttling(pr, target_state, false);
 }
 
 /*
@@ -839,10 +840,10 @@ static int acpi_processor_get_throttling_ptc(struct acpi_processor *pr)
 	if (ret >= 0) {
 		state = acpi_get_throttling_state(pr, value);
 		if (state == -1) {
-			ACPI_WARNING((AE_INFO,
-				"Invalid throttling state, reset"));
+			ACPI_DEBUG_PRINT((ACPI_DB_INFO,
+				"Invalid throttling state, reset\n"));
 			state = 0;
-			ret = acpi_processor_set_throttling(pr, state);
+			ret = acpi_processor_set_throttling(pr, state, true);
 			if (ret)
 				return ret;
 		}
@@ -915,7 +916,7 @@ static int acpi_processor_get_fadt_info(struct acpi_processor *pr)
 }
 
 static int acpi_processor_set_throttling_fadt(struct acpi_processor *pr,
-					      int state)
+					      int state, bool force)
 {
 	u32 value = 0;
 	u32 duty_mask = 0;
@@ -930,7 +931,7 @@ static int acpi_processor_set_throttling_fadt(struct acpi_processor *pr,
 	if (!pr->flags.throttling)
 		return -ENODEV;
 
-	if (state == pr->throttling.state)
+	if (!force && (state == pr->throttling.state))
 		return 0;
 
 	if (state < pr->throttling_platform_limit)
@@ -988,7 +989,7 @@ static int acpi_processor_set_throttling_fadt(struct acpi_processor *pr,
 }
 
 static int acpi_processor_set_throttling_ptc(struct acpi_processor *pr,
-					     int state)
+					     int state, bool force)
 {
 	int ret;
 	acpi_integer value;
@@ -1002,7 +1003,7 @@ static int acpi_processor_set_throttling_ptc(struct acpi_processor *pr,
 	if (!pr->flags.throttling)
 		return -ENODEV;
 
-	if (state == pr->throttling.state)
+	if (!force && (state == pr->throttling.state))
 		return 0;
 
 	if (state < pr->throttling_platform_limit)
@@ -1018,7 +1019,8 @@ static int acpi_processor_set_throttling_ptc(struct acpi_processor *pr,
 	return 0;
 }
 
-int acpi_processor_set_throttling(struct acpi_processor *pr, int state)
+int acpi_processor_set_throttling(struct acpi_processor *pr,
+						int state, bool force)
 {
 	cpumask_var_t saved_mask;
 	int ret = 0;
@@ -1070,7 +1072,7 @@ int acpi_processor_set_throttling(struct acpi_processor *pr, int state)
 		/* FIXME: use work_on_cpu() */
 		set_cpus_allowed_ptr(current, cpumask_of(pr->id));
 		ret = p_throttling->acpi_processor_set_throttling(pr,
-						t_state.target_state);
+						t_state.target_state, force);
 	} else {
 		/*
 		 * When the T-state coordination is SW_ALL or HW_ALL,
@@ -1103,7 +1105,7 @@ int acpi_processor_set_throttling(struct acpi_processor *pr, int state)
 			set_cpus_allowed_ptr(current, cpumask_of(i));
 			ret = match_pr->throttling.
 				acpi_processor_set_throttling(
-				match_pr, t_state.target_state);
+				match_pr, t_state.target_state, force);
 		}
 	}
 	/*
@@ -1201,7 +1203,7 @@ int acpi_processor_get_throttling_info(struct acpi_processor *pr)
 		ACPI_DEBUG_PRINT((ACPI_DB_INFO,
 				  "Disabling throttling (was T%d)\n",
 				  pr->throttling.state));
-		result = acpi_processor_set_throttling(pr, 0);
+		result = acpi_processor_set_throttling(pr, 0, false);
 		if (result)
 			goto end;
 	}
@@ -1307,7 +1309,7 @@ static ssize_t acpi_processor_write_throttling(struct file *file,
 	if (strcmp(tmpbuf, charp) != 0)
 		return -EINVAL;
 
-	result = acpi_processor_set_throttling(pr, state_val);
+	result = acpi_processor_set_throttling(pr, state_val, false);
 	if (result)
 		return result;
 

drivers/leds/ledtrig-gpio.c

@@ -117,6 +117,9 @@ static ssize_t gpio_trig_inverted_store(struct device *dev,
 
 	gpio_data->inverted = !!inverted;
 
+	/* After inverting, we need to update the LED. */
+	schedule_work(&gpio_data->work);
+
 	return n;
 }
 static DEVICE_ATTR(inverted, 0644, gpio_trig_inverted_show,
@@ -146,20 +149,26 @@ static ssize_t gpio_trig_gpio_store(struct device *dev,
 		return -EINVAL;
 	}
 
+	if (gpio_data->gpio == gpio)
+		return n;
+
 	if (!gpio) {
-		free_irq(gpio_to_irq(gpio_data->gpio), led);
+		if (gpio_data->gpio != 0)
+			free_irq(gpio_to_irq(gpio_data->gpio), led);
+		gpio_data->gpio = 0;
 		return n;
 	}
 
-	if (gpio_data->gpio > 0 && gpio_data->gpio != gpio)
-		free_irq(gpio_to_irq(gpio_data->gpio), led);
-
-	gpio_data->gpio = gpio;
 	ret = request_irq(gpio_to_irq(gpio), gpio_trig_irq,
 			IRQF_SHARED | IRQF_TRIGGER_RISING
 			| IRQF_TRIGGER_FALLING, "ledtrig-gpio", led);
-	if (ret)
+	if (ret) {
 		dev_err(dev, "request_irq failed with error %d\n", ret);
+	} else {
+		if (gpio_data->gpio != 0)
+			free_irq(gpio_to_irq(gpio_data->gpio), led);
+		gpio_data->gpio = gpio;
+	}
 
 	return ret ? ret : n;
 }
@@ -211,7 +220,8 @@ static void gpio_trig_deactivate(struct led_classdev *led)
 		device_remove_file(led->dev, &dev_attr_inverted);
 		device_remove_file(led->dev, &dev_attr_desired_brightness);
 		flush_work(&gpio_data->work);
-		free_irq(gpio_to_irq(gpio_data->gpio),led);
+		if (gpio_data->gpio != 0)
+			free_irq(gpio_to_irq(gpio_data->gpio), led);
 		kfree(gpio_data);
 	}
 }

drivers/macintosh/via-maciisi.c

@@ -288,7 +288,7 @@ static void maciisi_sync(struct adb_request *req)
 	}
 	/* This could be BAD... when the ADB controller doesn't respond
 	 * for this long, it's probably not coming back :-( */
-	if(count >= 50) /* Hopefully shouldn't happen */
+	if (count > 50) /* Hopefully shouldn't happen */
 		printk(KERN_ERR "maciisi_send_request: poll timed out!\n");
 }
 

drivers/net/smc91x.c

@@ -531,7 +531,7 @@ static inline void  smc_rcv(struct net_device *dev)
 		local_irq_restore(flags);				\
 	__ret;								\
 })
-#define smc_special_lock(lock, flags)		spin_lock_irq(lock, flags)
+#define smc_special_lock(lock, flags)		spin_lock_irqsave(lock, flags)
 #define smc_special_unlock(lock, flags) 	spin_unlock_irqrestore(lock, flags)
 #else
 #define smc_special_trylock(lock, flags)	(1)

drivers/net/virtio_net.c

@@ -70,6 +70,9 @@ struct virtnet_info
 	struct sk_buff_head recv;
 	struct sk_buff_head send;
 
+	/* Work struct for refilling if we run low on memory. */
+	struct delayed_work refill;
+
 	/* Chain pages by the private ptr. */
 	struct page *pages;
 };
@@ -273,19 +276,22 @@ drop:
 	dev_kfree_skb(skb);
 }
 
-static void try_fill_recv_maxbufs(struct virtnet_info *vi)
+static bool try_fill_recv_maxbufs(struct virtnet_info *vi, gfp_t gfp)
 {
 	struct sk_buff *skb;
 	struct scatterlist sg[2+MAX_SKB_FRAGS];
 	int num, err, i;
+	bool oom = false;
 
 	sg_init_table(sg, 2+MAX_SKB_FRAGS);
 	for (;;) {
 		struct virtio_net_hdr *hdr;
 
 		skb = netdev_alloc_skb(vi->dev, MAX_PACKET_LEN + NET_IP_ALIGN);
-		if (unlikely(!skb))
+		if (unlikely(!skb)) {
+			oom = true;
 			break;
+		}
 
 		skb_reserve(skb, NET_IP_ALIGN);
 		skb_put(skb, MAX_PACKET_LEN);
@@ -296,7 +302,7 @@ static void try_fill_recv_maxbufs(struct virtnet_info *vi)
 		if (vi->big_packets) {
 			for (i = 0; i < MAX_SKB_FRAGS; i++) {
 				skb_frag_t *f = &skb_shinfo(skb)->frags[i];
-				f->page = get_a_page(vi, GFP_ATOMIC);
+				f->page = get_a_page(vi, gfp);
 				if (!f->page)
 					break;
 
@@ -325,31 +331,35 @@ static void try_fill_recv_maxbufs(struct virtnet_info *vi)
 	if (unlikely(vi->num > vi->max))
 		vi->max = vi->num;
 	vi->rvq->vq_ops->kick(vi->rvq);
+	return !oom;
 }
 
-static void try_fill_recv(struct virtnet_info *vi)
+/* Returns false if we couldn't fill entirely (OOM). */
+static bool try_fill_recv(struct virtnet_info *vi, gfp_t gfp)
 {
 	struct sk_buff *skb;
 	struct scatterlist sg[1];
 	int err;
+	bool oom = false;
 
-	if (!vi->mergeable_rx_bufs) {
-		try_fill_recv_maxbufs(vi);
-		return;
-	}
+	if (!vi->mergeable_rx_bufs)
+		return try_fill_recv_maxbufs(vi, gfp);
 
 	for (;;) {
 		skb_frag_t *f;
 
 		skb = netdev_alloc_skb(vi->dev, GOOD_COPY_LEN + NET_IP_ALIGN);
-		if (unlikely(!skb))
+		if (unlikely(!skb)) {
+			oom = true;
 			break;
+		}
 
 		skb_reserve(skb, NET_IP_ALIGN);
 
 		f = &skb_shinfo(skb)->frags[0];
-		f->page = get_a_page(vi, GFP_ATOMIC);
+		f->page = get_a_page(vi, gfp);
 		if (!f->page) {
+			oom = true;
 			kfree_skb(skb);
 			break;
 		}
@@ -373,6 +383,7 @@ static void try_fill_recv(struct virtnet_info *vi)
 	if (unlikely(vi->num > vi->max))
 		vi->max = vi->num;
 	vi->rvq->vq_ops->kick(vi->rvq);
+	return !oom;
 }
 
 static void skb_recv_done(struct virtqueue *rvq)
@@ -385,6 +396,23 @@ static void skb_recv_done(struct virtqueue *rvq)
 	}
 }
 
+static void refill_work(struct work_struct *work)
+{
+	struct virtnet_info *vi;
+	bool still_empty;
+
+	vi = container_of(work, struct virtnet_info, refill.work);
+	napi_disable(&vi->napi);
+	try_fill_recv(vi, GFP_KERNEL);
+	still_empty = (vi->num == 0);
+	napi_enable(&vi->napi);
+
+	/* In theory, this can happen: if we don't get any buffers in
+	 * we will *never* try to fill again. */
+	if (still_empty)
+		schedule_delayed_work(&vi->refill, HZ/2);
+}
+
 static int virtnet_poll(struct napi_struct *napi, int budget)
 {
 	struct virtnet_info *vi = container_of(napi, struct virtnet_info, napi);
@@ -400,10 +428,10 @@ again:
 		received++;
 	}
 
-	/* FIXME: If we oom and completely run out of inbufs, we need
-	 * to start a timer trying to fill more. */
-	if (vi->num < vi->max / 2)
-		try_fill_recv(vi);
+	if (vi->num < vi->max / 2) {
+		if (!try_fill_recv(vi, GFP_ATOMIC))
+			schedule_delayed_work(&vi->refill, 0);
+	}
 
 	/* Out of packets? */
 	if (received < budget) {
@@ -893,6 +921,7 @@ static int virtnet_probe(struct virtio_device *vdev)
 	vi->vdev = vdev;
 	vdev->priv = vi;
 	vi->pages = NULL;
+	INIT_DELAYED_WORK(&vi->refill, refill_work);
 
 	/* If they give us a callback when all buffers are done, we don't need
 	 * the timer. */
@@ -941,7 +970,7 @@ static int virtnet_probe(struct virtio_device *vdev)
 	}
 
 	/* Last of all, set up some receive buffers. */
-	try_fill_recv(vi);
+	try_fill_recv(vi, GFP_KERNEL);
 
 	/* If we didn't even get one input buffer, we're useless. */
 	if (vi->num == 0) {
@@ -958,6 +987,7 @@ static int virtnet_probe(struct virtio_device *vdev)
 
 unregister:
 	unregister_netdev(dev);
+	cancel_delayed_work_sync(&vi->refill);
 free_vqs:
 	vdev->config->del_vqs(vdev);
 free:
@@ -986,6 +1016,7 @@ static void virtnet_remove(struct virtio_device *vdev)
 	BUG_ON(vi->num != 0);
 
 	unregister_netdev(vi->dev);
+	cancel_delayed_work_sync(&vi->refill);
 
 	vdev->config->del_vqs(vi->vdev);
 

drivers/platform/x86/wmi.c

@@ -270,7 +270,7 @@ u32 method_id, const struct acpi_buffer *in, struct acpi_buffer *out)
 	acpi_status status;
 	struct acpi_object_list input;
 	union acpi_object params[3];
-	char method[4] = "WM";
+	char method[5] = "WM";
 
 	if (!find_guid(guid_string, &wblock))
 		return AE_ERROR;
@@ -328,8 +328,8 @@ struct acpi_buffer *out)
 	acpi_status status, wc_status = AE_ERROR;
 	struct acpi_object_list input, wc_input;
 	union acpi_object wc_params[1], wq_params[1];
-	char method[4];
-	char wc_method[4] = "WC";
+	char method[5];
+	char wc_method[5] = "WC";
 
 	if (!guid_string || !out)
 		return AE_BAD_PARAMETER;
@@ -410,7 +410,7 @@ const struct acpi_buffer *in)
 	acpi_handle handle;
 	struct acpi_object_list input;
 	union acpi_object params[2];
-	char method[4] = "WS";
+	char method[5] = "WS";
 
 	if (!guid_string || !in)
 		return AE_BAD_DATA;

drivers/pps/pps.c

@@ -244,7 +244,7 @@ int pps_register_cdev(struct pps_device *pps)
 	}
 	pps->dev = device_create(pps_class, pps->info.dev, pps->devno, NULL,
 							"pps%d", pps->id);
-	if (err)
+	if (IS_ERR(pps->dev))
 		goto del_cdev;
 	dev_set_drvdata(pps->dev, pps);
 

drivers/thermal/thermal_sys.c

@@ -953,7 +953,12 @@ void thermal_zone_device_update(struct thermal_zone_device *tz)
 
 	mutex_lock(&tz->lock);
 
-	tz->ops->get_temp(tz, &temp);
+	if (tz->ops->get_temp(tz, &temp)) {
+		/* get_temp failed - retry it later */
+		printk(KERN_WARNING PREFIX "failed to read out thermal zone "
+		       "%d\n", tz->id);
+		goto leave;
+	}
 
 	for (count = 0; count < tz->trips; count++) {
 		tz->ops->get_trip_type(tz, count, &trip_type);
@@ -1005,6 +1010,8 @@ void thermal_zone_device_update(struct thermal_zone_device *tz)
 					    THERMAL_TRIPS_NONE);
 
 	tz->last_temperature = temp;
+
+      leave:
 	if (tz->passive)
 		thermal_zone_device_set_polling(tz, tz->passive_delay);
 	else if (tz->polling_delay)

drivers/video/xen-fbfront.c

@@ -454,6 +454,10 @@ static int __devinit xenfb_probe(struct xenbus_device *dev,
 
 	xenfb_init_shared_page(info, fb_info);
 
+	ret = xenfb_connect_backend(dev, info);
+	if (ret < 0)
+		goto error;
+
 	ret = register_framebuffer(fb_info);
 	if (ret) {
 		fb_deferred_io_cleanup(fb_info);
@@ -464,10 +468,6 @@ static int __devinit xenfb_probe(struct xenbus_device *dev,
 	}
 	info->fb_info = fb_info;
 
-	ret = xenfb_connect_backend(dev, info);
-	if (ret < 0)
-		goto error;
-
 	xenfb_make_preferred_console();
 	return 0;
 

fs/9p/v9fs.c

@@ -76,7 +76,7 @@ static const match_table_t tokens = {
  * Return 0 upon success, -ERRNO upon failure.
  */
 
-static int v9fs_parse_options(struct v9fs_session_info *v9ses)
+static int v9fs_parse_options(struct v9fs_session_info *v9ses, char *opts)
 {
 	char *options;
 	substring_t args[MAX_OPT_ARGS];
@@ -90,10 +90,10 @@ static int v9fs_parse_options(struct v9fs_session_info *v9ses)
 	v9ses->debug = 0;
 	v9ses->cache = 0;
 
-	if (!v9ses->options)
+	if (!opts)
 		return 0;
 
-	options = kstrdup(v9ses->options, GFP_KERNEL);
+	options = kstrdup(opts, GFP_KERNEL);
 	if (!options) {
 		P9_DPRINTK(P9_DEBUG_ERROR,
 			   "failed to allocate copy of option string\n");
@@ -206,24 +206,14 @@ struct p9_fid *v9fs_session_init(struct v9fs_session_info *v9ses,
 	v9ses->uid = ~0;
 	v9ses->dfltuid = V9FS_DEFUID;
 	v9ses->dfltgid = V9FS_DEFGID;
-	if (data) {
-		v9ses->options = kstrdup(data, GFP_KERNEL);
-		if (!v9ses->options) {
-			P9_DPRINTK(P9_DEBUG_ERROR,
-			   "failed to allocate copy of option string\n");
-			retval = -ENOMEM;
-			goto error;
-		}
-	}
 
-	rc = v9fs_parse_options(v9ses);
+	rc = v9fs_parse_options(v9ses, data);
 	if (rc < 0) {
 		retval = rc;
 		goto error;
 	}
 
-	v9ses->clnt = p9_client_create(dev_name, v9ses->options);
-
+	v9ses->clnt = p9_client_create(dev_name, data);
 	if (IS_ERR(v9ses->clnt)) {
 		retval = PTR_ERR(v9ses->clnt);
 		v9ses->clnt = NULL;
@@ -280,7 +270,6 @@ void v9fs_session_close(struct v9fs_session_info *v9ses)
 
 	__putname(v9ses->uname);
 	__putname(v9ses->aname);
-	kfree(v9ses->options);
 }
 
 /**

fs/9p/v9fs.h

@@ -85,7 +85,6 @@ struct v9fs_session_info {
 	unsigned int afid;
 	unsigned int cache;
 
-	char *options;		/* copy of mount options */
 	char *uname;		/* user name to mount as */
 	char *aname;		/* name of remote hierarchy being mounted */
 	unsigned int maxdata;	/* max data for client interface */

fs/9p/vfs_inode.c

@@ -171,7 +171,6 @@ int v9fs_uflags2omode(int uflags, int extended)
 
 /**
  * v9fs_blank_wstat - helper function to setup a 9P stat structure
- * @v9ses: 9P session info (for determining extended mode)
  * @wstat: structure to initialize
  *
  */
@@ -207,65 +206,72 @@ v9fs_blank_wstat(struct p9_wstat *wstat)
 
 struct inode *v9fs_get_inode(struct super_block *sb, int mode)
 {
+	int err;
 	struct inode *inode;
 	struct v9fs_session_info *v9ses = sb->s_fs_info;
 
 	P9_DPRINTK(P9_DEBUG_VFS, "super block: %p mode: %o\n", sb, mode);
 
 	inode = new_inode(sb);
-	if (inode) {
-		inode->i_mode = mode;
-		inode->i_uid = current_fsuid();
-		inode->i_gid = current_fsgid();
-		inode->i_blocks = 0;
-		inode->i_rdev = 0;
-		inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
-		inode->i_mapping->a_ops = &v9fs_addr_operations;
-
-		switch (mode & S_IFMT) {
-		case S_IFIFO:
-		case S_IFBLK:
-		case S_IFCHR:
-		case S_IFSOCK:
-			if (!v9fs_extended(v9ses)) {
-				P9_DPRINTK(P9_DEBUG_ERROR,
-				      "special files without extended mode\n");
-				return ERR_PTR(-EINVAL);
-			}
-			init_special_inode(inode, inode->i_mode,
-					   inode->i_rdev);
-			break;
-		case S_IFREG:
-			inode->i_op = &v9fs_file_inode_operations;
-			inode->i_fop = &v9fs_file_operations;
-			break;
-		case S_IFLNK:
-			if (!v9fs_extended(v9ses)) {
-				P9_DPRINTK(P9_DEBUG_ERROR,
-					"extended modes used w/o 9P2000.u\n");
-				return ERR_PTR(-EINVAL);
-			}
-			inode->i_op = &v9fs_symlink_inode_operations;
-			break;
-		case S_IFDIR:
-			inc_nlink(inode);
-			if (v9fs_extended(v9ses))
-				inode->i_op = &v9fs_dir_inode_operations_ext;
-			else
-				inode->i_op = &v9fs_dir_inode_operations;
-			inode->i_fop = &v9fs_dir_operations;
-			break;
-		default:
-			P9_DPRINTK(P9_DEBUG_ERROR,
-				"BAD mode 0x%x S_IFMT 0x%x\n",
-				mode, mode & S_IFMT);
-			return ERR_PTR(-EINVAL);
-		}
-	} else {
+	if (!inode) {
 		P9_EPRINTK(KERN_WARNING, "Problem allocating inode\n");
 		return ERR_PTR(-ENOMEM);
 	}
+
+	inode->i_mode = mode;
+	inode->i_uid = current_fsuid();
+	inode->i_gid = current_fsgid();
+	inode->i_blocks = 0;
+	inode->i_rdev = 0;
+	inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
+	inode->i_mapping->a_ops = &v9fs_addr_operations;
+
+	switch (mode & S_IFMT) {
+	case S_IFIFO:
+	case S_IFBLK:
+	case S_IFCHR:
+	case S_IFSOCK:
+		if (!v9fs_extended(v9ses)) {
+			P9_DPRINTK(P9_DEBUG_ERROR,
+				   "special files without extended mode\n");
+			err = -EINVAL;
+			goto error;
+		}
+		init_special_inode(inode, inode->i_mode, inode->i_rdev);
+		break;
+	case S_IFREG:
+		inode->i_op = &v9fs_file_inode_operations;
+		inode->i_fop = &v9fs_file_operations;
+		break;
+	case S_IFLNK:
+		if (!v9fs_extended(v9ses)) {
+			P9_DPRINTK(P9_DEBUG_ERROR,
+				   "extended modes used w/o 9P2000.u\n");
+			err = -EINVAL;
+			goto error;
+		}
+		inode->i_op = &v9fs_symlink_inode_operations;
+		break;
+	case S_IFDIR:
+		inc_nlink(inode);
+		if (v9fs_extended(v9ses))
+			inode->i_op = &v9fs_dir_inode_operations_ext;
+		else
+			inode->i_op = &v9fs_dir_inode_operations;
+		inode->i_fop = &v9fs_dir_operations;
+		break;
+	default:
+		P9_DPRINTK(P9_DEBUG_ERROR, "BAD mode 0x%x S_IFMT 0x%x\n",
+			   mode, mode & S_IFMT);
+		err = -EINVAL;
+		goto error;
+	}
+
 	return inode;
+
+error:
+	iput(inode);
+	return ERR_PTR(err);
 }
 
 /*
@@ -338,30 +344,25 @@ v9fs_inode_from_fid(struct v9fs_session_info *v9ses, struct p9_fid *fid,
 
 	ret = NULL;
 	st = p9_client_stat(fid);
-	if (IS_ERR(st)) {
-		err = PTR_ERR(st);
-		st = NULL;
-		goto error;
-	}
+	if (IS_ERR(st))
+		return ERR_CAST(st);
 
 	umode = p9mode2unixmode(v9ses, st->mode);
 	ret = v9fs_get_inode(sb, umode);
 	if (IS_ERR(ret)) {
 		err = PTR_ERR(ret);
-		ret = NULL;
 		goto error;
 	}
 
 	v9fs_stat2inode(st, ret, sb);
 	ret->i_ino = v9fs_qid2ino(&st->qid);
+	p9stat_free(st);
 	kfree(st);
 	return ret;
 
 error:
+	p9stat_free(st);
 	kfree(st);
-	if (ret)
-		iput(ret);
-
 	return ERR_PTR(err);
 }
 
@@ -403,9 +404,9 @@ v9fs_open_created(struct inode *inode, struct file *file)
  * @v9ses: session information
  * @dir: directory that dentry is being created in
  * @dentry:  dentry that is being created
+ * @extension: 9p2000.u extension string to support devices, etc.
  * @perm: create permissions
  * @mode: open mode
- * @extension: 9p2000.u extension string to support devices, etc.
  *
  */
 static struct p9_fid *
@@ -470,7 +471,10 @@ v9fs_create(struct v9fs_session_info *v9ses, struct inode *dir,
 		dentry->d_op = &v9fs_dentry_operations;
 
 	d_instantiate(dentry, inode);
-	v9fs_fid_add(dentry, fid);
+	err = v9fs_fid_add(dentry, fid);
+	if (err < 0)
+		goto error;
+
 	return ofid;
 
 error:

fs/9p/vfs_super.c

@@ -81,7 +81,7 @@ static int v9fs_set_super(struct super_block *s, void *data)
 
 static void
 v9fs_fill_super(struct super_block *sb, struct v9fs_session_info *v9ses,
-		int flags)
+		int flags, void *data)
 {
 	sb->s_maxbytes = MAX_LFS_FILESIZE;
 	sb->s_blocksize_bits = fls(v9ses->maxdata - 1);
@@ -91,6 +91,8 @@ v9fs_fill_super(struct super_block *sb, struct v9fs_session_info *v9ses,
 
 	sb->s_flags = flags | MS_ACTIVE | MS_SYNCHRONOUS | MS_DIRSYNC |
 	    MS_NOATIME;
+
+	save_mount_options(sb, data);
 }
 
 /**
@@ -113,14 +115,11 @@ static int v9fs_get_sb(struct file_system_type *fs_type, int flags,
 	struct v9fs_session_info *v9ses = NULL;
 	struct p9_wstat *st = NULL;
 	int mode = S_IRWXUGO | S_ISVTX;
-	uid_t uid = current_fsuid();
-	gid_t gid = current_fsgid();
 	struct p9_fid *fid;
 	int retval = 0;
 
 	P9_DPRINTK(P9_DEBUG_VFS, " \n");
 
-	st = NULL;
 	v9ses = kzalloc(sizeof(struct v9fs_session_info), GFP_KERNEL);
 	if (!v9ses)
 		return -ENOMEM;
@@ -142,7 +141,7 @@ static int v9fs_get_sb(struct file_system_type *fs_type, int flags,
 		retval = PTR_ERR(sb);
 		goto free_stat;
 	}
-	v9fs_fill_super(sb, v9ses, flags);
+	v9fs_fill_super(sb, v9ses, flags, data);
 
 	inode = v9fs_get_inode(sb, S_IFDIR | mode);
 	if (IS_ERR(inode)) {
@@ -150,9 +149,6 @@ static int v9fs_get_sb(struct file_system_type *fs_type, int flags,
 		goto release_sb;
 	}
 
-	inode->i_uid = uid;
-	inode->i_gid = gid;
-
 	root = d_alloc_root(inode);
 	if (!root) {
 		iput(inode);
@@ -173,10 +169,8 @@ P9_DPRINTK(P9_DEBUG_VFS, " simple set mount, return 0\n");
 	simple_set_mnt(mnt, sb);
 	return 0;
 
-release_sb:
-	deactivate_locked_super(sb);
-
 free_stat:
+	p9stat_free(st);
 	kfree(st);
 
 clunk_fid:
@@ -185,7 +179,12 @@ clunk_fid:
 close_session:
 	v9fs_session_close(v9ses);
 	kfree(v9ses);
+	return retval;
 
+release_sb:
+	p9stat_free(st);
+	kfree(st);
+	deactivate_locked_super(sb);
 	return retval;
 }
 
@@ -207,24 +206,10 @@ static void v9fs_kill_super(struct super_block *s)
 
 	v9fs_session_close(v9ses);
 	kfree(v9ses);
+	s->s_fs_info = NULL;
 	P9_DPRINTK(P9_DEBUG_VFS, "exiting kill_super\n");
 }
 
-/**
- * v9fs_show_options - Show mount options in /proc/mounts
- * @m: seq_file to write to
- * @mnt: mount descriptor
- *
- */
-
-static int v9fs_show_options(struct seq_file *m, struct vfsmount *mnt)
-{
-	struct v9fs_session_info *v9ses = mnt->mnt_sb->s_fs_info;
-
-	seq_printf(m, "%s", v9ses->options);
-	return 0;
-}
-
 static void
 v9fs_umount_begin(struct super_block *sb)
 {
@@ -237,7 +222,7 @@ v9fs_umount_begin(struct super_block *sb)
 static const struct super_operations v9fs_super_ops = {
 	.statfs = simple_statfs,
 	.clear_inode = v9fs_clear_inode,
-	.show_options = v9fs_show_options,
+	.show_options = generic_show_options,
 	.umount_begin = v9fs_umount_begin,
 };
 

fs/afs/file.c

@@ -134,9 +134,16 @@ static int afs_readpage(struct file *file, struct page *page)
 
 	inode = page->mapping->host;
 
-	ASSERT(file != NULL);
-	key = file->private_data;
-	ASSERT(key != NULL);
+	if (file) {
+		key = file->private_data;
+		ASSERT(key != NULL);
+	} else {
+		key = afs_request_key(AFS_FS_S(inode->i_sb)->volume->cell);
+		if (IS_ERR(key)) {
+			ret = PTR_ERR(key);
+			goto error_nokey;
+		}
+	}
 
 	_enter("{%x},{%lu},{%lu}", key_serial(key), inode->i_ino, page->index);
 
@@ -207,12 +214,17 @@ static int afs_readpage(struct file *file, struct page *page)
 		unlock_page(page);
 	}
 
+	if (!file)
+		key_put(key);
 	_leave(" = 0");
 	return 0;
 
 error:
 	SetPageError(page);
 	unlock_page(page);
+	if (!file)
+		key_put(key);
+error_nokey:
 	_leave(" = %d", ret);
 	return ret;
 }

fs/notify/inotify/inotify_fsnotify.c

@@ -105,16 +105,45 @@ static bool inotify_should_send_event(struct fsnotify_group *group, struct inode
 	return send;
 }
 
+/*
+ * This is NEVER supposed to be called.  Inotify marks should either have been
+ * removed from the idr when the watch was removed or in the
+ * fsnotify_destroy_mark_by_group() call when the inotify instance was being
+ * torn down.  This is only called if the idr is about to be freed but there
+ * are still marks in it.
+ */
 static int idr_callback(int id, void *p, void *data)
 {
-	BUG();
+	struct fsnotify_mark_entry *entry;
+	struct inotify_inode_mark_entry *ientry;
+	static bool warned = false;
+
+	if (warned)
+		return 0;
+
+	warned = false;
+	entry = p;
+	ientry = container_of(entry, struct inotify_inode_mark_entry, fsn_entry);
+
+	WARN(1, "inotify closing but id=%d for entry=%p in group=%p still in "
+		"idr.  Probably leaking memory\n", id, p, data);
+
+	/*
+	 * I'm taking the liberty of assuming that the mark in question is a
+	 * valid address and I'm dereferencing it.  This might help to figure
+	 * out why we got here and the panic is no worse than the original
+	 * BUG() that was here.
+	 */
+	if (entry)
+		printk(KERN_WARNING "entry->group=%p inode=%p wd=%d\n",
+			entry->group, entry->inode, ientry->wd);
 	return 0;
 }
 
 static void inotify_free_group_priv(struct fsnotify_group *group)
 {
 	/* ideally the idr is empty and we won't hit the BUG in teh callback */
-	idr_for_each(&group->inotify_data.idr, idr_callback, NULL);
+	idr_for_each(&group->inotify_data.idr, idr_callback, group);
 	idr_remove_all(&group->inotify_data.idr);
 	idr_destroy(&group->inotify_data.idr);
 }

fs/notify/inotify/inotify_user.c

@@ -47,9 +47,6 @@
 
 static struct vfsmount *inotify_mnt __read_mostly;
 
-/* this just sits here and wastes global memory.  used to just pad userspace messages with zeros */
-static struct inotify_event nul_inotify_event;
-
 /* these are configurable via /proc/sys/fs/inotify/ */
 static int inotify_max_user_instances __read_mostly;
 static int inotify_max_queued_events __read_mostly;
@@ -199,8 +196,10 @@ static ssize_t copy_event_to_user(struct fsnotify_group *group,
 		inotify_free_event_priv(fsn_priv);
 	}
 
-	/* round up event->name_len so it is a multiple of event_size */
-	name_len = roundup(event->name_len, event_size);
+	/* round up event->name_len so it is a multiple of event_size
+	 * plus an extra byte for the terminating '\0'.
+	 */
+	name_len = roundup(event->name_len + 1, event_size);
 	inotify_event.len = name_len;
 
 	inotify_event.mask = inotify_mask_to_arg(event->mask);
@@ -224,8 +223,8 @@ static ssize_t copy_event_to_user(struct fsnotify_group *group,
 			return -EFAULT;
 		buf += event->name_len;
 
-		/* fill userspace with 0's from nul_inotify_event */
-		if (copy_to_user(buf, &nul_inotify_event, len_to_zero))
+		/* fill userspace with 0's */
+		if (clear_user(buf, len_to_zero))
 			return -EFAULT;
 		buf += len_to_zero;
 		event_size += name_len;
@@ -364,20 +363,53 @@ static int inotify_find_inode(const char __user *dirname, struct path *path, uns
 	return error;
 }
 
+/*
+ * Remove the mark from the idr (if present) and drop the reference
+ * on the mark because it was in the idr.
+ */
 static void inotify_remove_from_idr(struct fsnotify_group *group,
 				    struct inotify_inode_mark_entry *ientry)
 {
 	struct idr *idr;
+	struct fsnotify_mark_entry *entry;
+	struct inotify_inode_mark_entry *found_ientry;
+	int wd;
 
 	spin_lock(&group->inotify_data.idr_lock);
 	idr = &group->inotify_data.idr;
-	idr_remove(idr, ientry->wd);
-	spin_unlock(&group->inotify_data.idr_lock);
+	wd = ientry->wd;
+
+	if (wd == -1)
+		goto out;
+
+	entry = idr_find(&group->inotify_data.idr, wd);
+	if (unlikely(!entry))
+		goto out;
+
+	found_ientry = container_of(entry, struct inotify_inode_mark_entry, fsn_entry);
+	if (unlikely(found_ientry != ientry)) {
+		/* We found an entry in the idr with the right wd, but it's
+		 * not the entry we were told to remove.  eparis seriously
+		 * fucked up somewhere. */
+		WARN_ON(1);
+		ientry->wd = -1;
+		goto out;
+	}
+
+	/* One ref for being in the idr, one ref held by the caller */
+	BUG_ON(atomic_read(&entry->refcnt) < 2);
+
+	idr_remove(idr, wd);
 	ientry->wd = -1;
+
+	/* removed from the idr, drop that ref */
+	fsnotify_put_mark(entry);
+out:
+	spin_unlock(&group->inotify_data.idr_lock);
 }
+
 /*
- * Send IN_IGNORED for this wd, remove this wd from the idr, and drop the
- * internal reference help on the mark because it is in the idr.
+ * Send IN_IGNORED for this wd, remove this wd from the idr.
  */
 void inotify_ignored_and_remove_idr(struct fsnotify_mark_entry *entry,
 				    struct fsnotify_group *group)
@@ -417,9 +449,6 @@ skip_send_ignore:
 	/* remove this entry from the idr */
 	inotify_remove_from_idr(group, ientry);
 
-	/* removed from idr, drop that reference */
-	fsnotify_put_mark(entry);
-
 	atomic_dec(&group->inotify_data.user->inotify_watches);
 }
 
@@ -431,80 +460,29 @@ static void inotify_free_mark(struct fsnotify_mark_entry *entry)
 	kmem_cache_free(inotify_inode_mark_cachep, ientry);
 }
 
-static int inotify_update_watch(struct fsnotify_group *group, struct inode *inode, u32 arg)
+static int inotify_update_existing_watch(struct fsnotify_group *group,
+					 struct inode *inode,
+					 u32 arg)
 {
-	struct fsnotify_mark_entry *entry = NULL;
+	struct fsnotify_mark_entry *entry;
 	struct inotify_inode_mark_entry *ientry;
-	struct inotify_inode_mark_entry *tmp_ientry;
-	int ret = 0;
-	int add = (arg & IN_MASK_ADD);
-	__u32 mask;
 	__u32 old_mask, new_mask;
+	__u32 mask;
+	int add = (arg & IN_MASK_ADD);
+	int ret;
 
 	/* don't allow invalid bits: we don't want flags set */
 	mask = inotify_arg_to_mask(arg);
 	if (unlikely(!mask))
 		return -EINVAL;
 
-	tmp_ientry = kmem_cache_alloc(inotify_inode_mark_cachep, GFP_KERNEL);
-	if (unlikely(!tmp_ientry))
-		return -ENOMEM;
-	/* we set the mask at the end after attaching it */
-	fsnotify_init_mark(&tmp_ientry->fsn_entry, inotify_free_mark);
-	tmp_ientry->wd = -1;
-
-find_entry:
 	spin_lock(&inode->i_lock);
 	entry = fsnotify_find_mark_entry(group, inode);
 	spin_unlock(&inode->i_lock);
-	if (entry) {
-		ientry = container_of(entry, struct inotify_inode_mark_entry, fsn_entry);
-	} else {
-		ret = -ENOSPC;
-		if (atomic_read(&group->inotify_data.user->inotify_watches) >= inotify_max_user_watches)
-			goto out_err;
-retry:
-		ret = -ENOMEM;
-		if (unlikely(!idr_pre_get(&group->inotify_data.idr, GFP_KERNEL)))
-			goto out_err;
-
-		spin_lock(&group->inotify_data.idr_lock);
-		ret = idr_get_new_above(&group->inotify_data.idr, &tmp_ientry->fsn_entry,
-					group->inotify_data.last_wd,
-					&tmp_ientry->wd);
-		spin_unlock(&group->inotify_data.idr_lock);
-		if (ret) {
-			if (ret == -EAGAIN)
-				goto retry;
-			goto out_err;
-		}
-
-		ret = fsnotify_add_mark(&tmp_ientry->fsn_entry, group, inode);
-		if (ret) {
-			inotify_remove_from_idr(group, tmp_ientry);
-			if (ret == -EEXIST)
-				goto find_entry;
-			goto out_err;
-		}
-
-		/* tmp_ientry has been added to the inode, so we are all set up.
-		 * now we just need to make sure tmp_ientry doesn't get freed and
-		 * we need to set up entry and ientry so the generic code can
-		 * do its thing. */
-		ientry = tmp_ientry;
-		entry = &ientry->fsn_entry;
-		tmp_ientry = NULL;
-
-		atomic_inc(&group->inotify_data.user->inotify_watches);
-
-		/* update the idr hint */
-		group->inotify_data.last_wd = ientry->wd;
-
-		/* we put the mark on the idr, take a reference */
-		fsnotify_get_mark(entry);
-	}
+	if (!entry)
+		return -ENOENT;
 
-	ret = ientry->wd;
+	ientry = container_of(entry, struct inotify_inode_mark_entry, fsn_entry);
 
 	spin_lock(&entry->lock);
 
@@ -536,18 +514,103 @@ retry:
 			fsnotify_recalc_group_mask(group);
 	}
 
-	/* this either matches fsnotify_find_mark_entry, or init_mark_entry
-	 * depending on which path we took... */
+	/* return the wd */
+	ret = ientry->wd;
+
+	/* match the get from fsnotify_find_mark_entry() */
 	fsnotify_put_mark(entry);
 
+	return ret;
+}
+
+static int inotify_new_watch(struct fsnotify_group *group,
+			     struct inode *inode,
+			     u32 arg)
+{
+	struct inotify_inode_mark_entry *tmp_ientry;
+	__u32 mask;
+	int ret;
+
+	/* don't allow invalid bits: we don't want flags set */
+	mask = inotify_arg_to_mask(arg);
+	if (unlikely(!mask))
+		return -EINVAL;
+
+	tmp_ientry = kmem_cache_alloc(inotify_inode_mark_cachep, GFP_KERNEL);
+	if (unlikely(!tmp_ientry))
+		return -ENOMEM;
+
+	fsnotify_init_mark(&tmp_ientry->fsn_entry, inotify_free_mark);
+	tmp_ientry->fsn_entry.mask = mask;
+	tmp_ientry->wd = -1;
+
+	ret = -ENOSPC;
+	if (atomic_read(&group->inotify_data.user->inotify_watches) >= inotify_max_user_watches)
+		goto out_err;
+retry:
+	ret = -ENOMEM;
+	if (unlikely(!idr_pre_get(&group->inotify_data.idr, GFP_KERNEL)))
+		goto out_err;
+
+	spin_lock(&group->inotify_data.idr_lock);
+	ret = idr_get_new_above(&group->inotify_data.idr, &tmp_ientry->fsn_entry,
+				group->inotify_data.last_wd,
+				&tmp_ientry->wd);
+	spin_unlock(&group->inotify_data.idr_lock);
+	if (ret) {
+		/* idr was out of memory allocate and try again */
+		if (ret == -EAGAIN)
+			goto retry;
+		goto out_err;
+	}
+
+	/* we put the mark on the idr, take a reference */
+	fsnotify_get_mark(&tmp_ientry->fsn_entry);
+
+	/* we are on the idr, now get on the inode */
+	ret = fsnotify_add_mark(&tmp_ientry->fsn_entry, group, inode);
+	if (ret) {
+		/* we failed to get on the inode, get off the idr */
+		inotify_remove_from_idr(group, tmp_ientry);
+		goto out_err;
+	}
+
+	/* update the idr hint, who cares about races, it's just a hint */
+	group->inotify_data.last_wd = tmp_ientry->wd;
+
+	/* increment the number of watches the user has */
+	atomic_inc(&group->inotify_data.user->inotify_watches);
+
+	/* return the watch descriptor for this new entry */
+	ret = tmp_ientry->wd;
+
+	/* match the ref from fsnotify_init_markentry() */
+	fsnotify_put_mark(&tmp_ientry->fsn_entry);
+
 out_err:
-	/* could be an error, could be that we found an existing mark */
-	if (tmp_ientry) {
-		/* on the idr but didn't make it on the inode */
-		if (tmp_ientry->wd != -1)
-			inotify_remove_from_idr(group, tmp_ientry);
+	if (ret < 0)
 		kmem_cache_free(inotify_inode_mark_cachep, tmp_ientry);
-	}
+
+	return ret;
+}
+
+static int inotify_update_watch(struct fsnotify_group *group, struct inode *inode, u32 arg)
+{
+	int ret = 0;
+
+retry:
+	/* try to update and existing watch with the new arg */
+	ret = inotify_update_existing_watch(group, inode, arg);
+	/* no mark present, try to add a new one */
+	if (ret == -ENOENT)
+		ret = inotify_new_watch(group, inode, arg);
+	/*
+	 * inotify_new_watch could race with another thread which did an
+	 * inotify_new_watch between the update_existing and the add watch
+	 * here, go back and try to update an existing mark again.
+	 */
+	if (ret == -EEXIST)
+		goto retry;
 
 	return ret;
 }

include/acpi/processor.h

@@ -174,7 +174,7 @@ struct acpi_processor_throttling {
 	cpumask_var_t shared_cpu_map;
 	int (*acpi_processor_get_throttling) (struct acpi_processor * pr);
 	int (*acpi_processor_set_throttling) (struct acpi_processor * pr,
-					      int state);
+					      int state, bool force);
 
 	u32 address;
 	u8 duty_offset;
@@ -321,7 +321,8 @@ static inline int acpi_processor_ppc_has_changed(struct acpi_processor *pr)
 /* in processor_throttling.c */
 int acpi_processor_tstate_has_changed(struct acpi_processor *pr);
 int acpi_processor_get_throttling_info(struct acpi_processor *pr);
-extern int acpi_processor_set_throttling(struct acpi_processor *pr, int state);
+extern int acpi_processor_set_throttling(struct acpi_processor *pr,
+					 int state, bool force);
 extern const struct file_operations acpi_processor_throttling_fops;
 extern void acpi_processor_throttling_init(void);
 /* in processor_idle.c */

include/linux/flex_array.h

@@ -21,7 +21,7 @@ struct flex_array {
 		struct {
 			int element_size;
 			int total_nr_elements;
-			struct flex_array_part *parts[0];
+			struct flex_array_part *parts[];
 		};
 		/*
 		 * This little trick makes sure that
@@ -36,12 +36,14 @@ struct flex_array {
 	.total_nr_elements = (total),	\
 } } }
 
-struct flex_array *flex_array_alloc(int element_size, int total, gfp_t flags);
-int flex_array_prealloc(struct flex_array *fa, int start, int end, gfp_t flags);
+struct flex_array *flex_array_alloc(int element_size, unsigned int total,
+		gfp_t flags);
+int flex_array_prealloc(struct flex_array *fa, unsigned int start,
+		unsigned int end, gfp_t flags);
 void flex_array_free(struct flex_array *fa);
 void flex_array_free_parts(struct flex_array *fa);
-int flex_array_put(struct flex_array *fa, int element_nr, void *src,
+int flex_array_put(struct flex_array *fa, unsigned int element_nr, void *src,
 		gfp_t flags);
-void *flex_array_get(struct flex_array *fa, int element_nr);
+void *flex_array_get(struct flex_array *fa, unsigned int element_nr);
 
 #endif /* _FLEX_ARRAY_H */

kernel/fork.c

@@ -846,11 +846,8 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
 {
 	struct signal_struct *sig;
 
-	if (clone_flags & CLONE_THREAD) {
-		atomic_inc(&current->signal->count);
-		atomic_inc(&current->signal->live);
+	if (clone_flags & CLONE_THREAD)
 		return 0;
-	}
 
 	sig = kmem_cache_alloc(signal_cachep, GFP_KERNEL);
 	tsk->signal = sig;
@@ -908,16 +905,6 @@ void __cleanup_signal(struct signal_struct *sig)
 	kmem_cache_free(signal_cachep, sig);
 }
 
-static void cleanup_signal(struct task_struct *tsk)
-{
-	struct signal_struct *sig = tsk->signal;
-
-	atomic_dec(&sig->live);
-
-	if (atomic_dec_and_test(&sig->count))
-		__cleanup_signal(sig);
-}
-
 static void copy_flags(unsigned long clone_flags, struct task_struct *p)
 {
 	unsigned long new_flags = p->flags;
@@ -1281,6 +1268,8 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	}
 
 	if (clone_flags & CLONE_THREAD) {
+		atomic_inc(&current->signal->count);
+		atomic_inc(&current->signal->live);
 		p->group_leader = current->group_leader;
 		list_add_tail_rcu(&p->thread_group, &p->group_leader->thread_group);
 	}
@@ -1326,7 +1315,8 @@ bad_fork_cleanup_mm:
 	if (p->mm)
 		mmput(p->mm);
 bad_fork_cleanup_signal:
-	cleanup_signal(p);
+	if (!(clone_flags & CLONE_THREAD))
+		__cleanup_signal(p->signal);
 bad_fork_cleanup_sighand:
 	__cleanup_sighand(p->sighand);
 bad_fork_cleanup_fs:

kernel/module.c

@@ -909,16 +909,18 @@ void __symbol_put(const char *symbol)
 }
 EXPORT_SYMBOL(__symbol_put);
 
+/* Note this assumes addr is a function, which it currently always is. */
 void symbol_put_addr(void *addr)
 {
 	struct module *modaddr;
+	unsigned long a = (unsigned long)dereference_function_descriptor(addr);
 
-	if (core_kernel_text((unsigned long)addr))
+	if (core_kernel_text(a))
 		return;
 
 	/* module_text_address is safe here: we're supposed to have reference
 	 * to module from symbol_get, so it can't go away. */
-	modaddr = __module_text_address((unsigned long)addr);
+	modaddr = __module_text_address(a);
 	BUG_ON(!modaddr);
 	module_put(modaddr);
 }
@@ -2353,7 +2355,8 @@ static noinline struct module *load_module(void __user *umod,
 	if (err < 0)
 		goto unlink;
 	add_sect_attrs(mod, hdr->e_shnum, secstrings, sechdrs);
-	add_notes_attrs(mod, hdr->e_shnum, secstrings, sechdrs);
+	if (mod->sect_attrs)
+		add_notes_attrs(mod, hdr->e_shnum, secstrings, sechdrs);
 
 	/* Get rid of temporary copy */
 	vfree(hdr);

lib/flex_array.c

@@ -99,7 +99,8 @@ static inline int elements_fit_in_base(struct flex_array *fa)
  * capacity in the base structure.  Also note that no effort is made
  * to efficiently pack objects across page boundaries.
  */
-struct flex_array *flex_array_alloc(int element_size, int total, gfp_t flags)
+struct flex_array *flex_array_alloc(int element_size, unsigned int total,
+					gfp_t flags)
 {
 	struct flex_array *ret;
 	int max_size = nr_base_part_ptrs() * __elements_per_part(element_size);
@@ -115,16 +116,14 @@ struct flex_array *flex_array_alloc(int element_size, int total, gfp_t flags)
 	return ret;
 }
 
-static int fa_element_to_part_nr(struct flex_array *fa, int element_nr)
+static int fa_element_to_part_nr(struct flex_array *fa,
+					unsigned int element_nr)
 {
 	return element_nr / __elements_per_part(fa->element_size);
 }
 
 /**
  * flex_array_free_parts - just free the second-level pages
- * @src:	address of data to copy into the array
- * @element_nr:	index of the position in which to insert
- * 		the new element.
  *
  * This is to be used in cases where the base 'struct flex_array'
  * has been statically allocated and should not be free.
@@ -146,14 +145,12 @@ void flex_array_free(struct flex_array *fa)
 	kfree(fa);
 }
 
-static int fa_index_inside_part(struct flex_array *fa, int element_nr)
+static unsigned int index_inside_part(struct flex_array *fa,
+					unsigned int element_nr)
 {
-	return element_nr % __elements_per_part(fa->element_size);
-}
+	unsigned int part_offset;
 
-static int index_inside_part(struct flex_array *fa, int element_nr)
-{
-	int part_offset = fa_index_inside_part(fa, element_nr);
+	part_offset = element_nr % __elements_per_part(fa->element_size);
 	return part_offset * fa->element_size;
 }
 
@@ -188,7 +185,8 @@ __fa_get_part(struct flex_array *fa, int part_nr, gfp_t flags)
  *
  * Locking must be provided by the caller.
  */
-int flex_array_put(struct flex_array *fa, int element_nr, void *src, gfp_t flags)
+int flex_array_put(struct flex_array *fa, unsigned int element_nr, void *src,
+			gfp_t flags)
 {
 	int part_nr = fa_element_to_part_nr(fa, element_nr);
 	struct flex_array_part *part;
@@ -198,10 +196,11 @@ int flex_array_put(struct flex_array *fa, int element_nr, void *src, gfp_t flags
 		return -ENOSPC;
 	if (elements_fit_in_base(fa))
 		part = (struct flex_array_part *)&fa->parts[0];
-	else
+	else {
 		part = __fa_get_part(fa, part_nr, flags);
-	if (!part)
-		return -ENOMEM;
+		if (!part)
+			return -ENOMEM;
+	}
 	dst = &part->elements[index_inside_part(fa, element_nr)];
 	memcpy(dst, src, fa->element_size);
 	return 0;
@@ -219,7 +218,8 @@ int flex_array_put(struct flex_array *fa, int element_nr, void *src, gfp_t flags
  *
  * Locking must be provided by the caller.
  */
-int flex_array_prealloc(struct flex_array *fa, int start, int end, gfp_t flags)
+int flex_array_prealloc(struct flex_array *fa, unsigned int start,
+			unsigned int end, gfp_t flags)
 {
 	int start_part;
 	int end_part;
@@ -250,18 +250,19 @@ int flex_array_prealloc(struct flex_array *fa, int start, int end, gfp_t flags)
  *
  * Locking must be provided by the caller.
  */
-void *flex_array_get(struct flex_array *fa, int element_nr)
+void *flex_array_get(struct flex_array *fa, unsigned int element_nr)
 {
 	int part_nr = fa_element_to_part_nr(fa, element_nr);
 	struct flex_array_part *part;
 
 	if (element_nr >= fa->total_nr_elements)
 		return NULL;
-	if (!fa->parts[part_nr])
-		return NULL;
 	if (elements_fit_in_base(fa))
 		part = (struct flex_array_part *)&fa->parts[0];
-	else
+	else {
 		part = fa->parts[part_nr];
+		if (!part)
+			return NULL;
+	}
 	return &part->elements[index_inside_part(fa, element_nr)];
 }

lib/lmb.c

@@ -429,7 +429,7 @@ u64 __init lmb_phys_mem_size(void)
 	return lmb.memory.size;
 }
 
-u64 __init lmb_end_of_DRAM(void)
+u64 lmb_end_of_DRAM(void)
 {
 	int idx = lmb.memory.cnt - 1;
 

mm/rmap.c

@@ -358,6 +358,7 @@ static int page_referenced_one(struct page *page,
 	 */
 	if (vma->vm_flags & VM_LOCKED) {
 		*mapcount = 1;	/* break early from loop */
+		*vm_flags |= VM_LOCKED;
 		goto out_unmap;
 	}
 

mm/vmscan.c

@@ -631,9 +631,14 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 
 		referenced = page_referenced(page, 1,
 						sc->mem_cgroup, &vm_flags);
-		/* In active use or really unfreeable?  Activate it. */
+		/*
+		 * In active use or really unfreeable?  Activate it.
+		 * If page which have PG_mlocked lost isoltation race,
+		 * try_to_unmap moves it to unevictable list
+		 */
 		if (sc->order <= PAGE_ALLOC_COSTLY_ORDER &&
-					referenced && page_mapping_inuse(page))
+					referenced && page_mapping_inuse(page)
+					&& !(vm_flags & VM_LOCKED))
 			goto activate_locked;
 
 		/*

net/9p/client.c

@@ -60,9 +60,9 @@ static struct p9_req_t *
 p9_client_rpc(struct p9_client *c, int8_t type, const char *fmt, ...);
 
 /**
- * v9fs_parse_options - parse mount options into session structure
- * @options: options string passed from mount
- * @v9ses: existing v9fs session information
+ * parse_options - parse mount options into client structure
+ * @opts: options string passed from mount
+ * @clnt: existing v9fs client information
  *
  * Return 0 upon success, -ERRNO upon failure
  */
@@ -232,7 +232,7 @@ EXPORT_SYMBOL(p9_tag_lookup);
 
 /**
  * p9_tag_init - setup tags structure and contents
- * @tags: tags structure from the client struct
+ * @c:  v9fs client struct
  *
  * This initializes the tags structure for each client instance.
  *
@@ -258,7 +258,7 @@ error:
 
 /**
  * p9_tag_cleanup - cleans up tags structure and reclaims resources
- * @tags: tags structure from the client struct
+ * @c:  v9fs client struct
  *
  * This frees resources associated with the tags structure
  *
@@ -411,14 +411,9 @@ static int p9_check_errors(struct p9_client *c, struct p9_req_t *req)
 		if (c->dotu)
 			err = -ecode;
 
-		if (!err) {
+		if (!err || !IS_ERR_VALUE(err))
 			err = p9_errstr2errno(ename, strlen(ename));
 
-			/* string match failed */
-			if (!err)
-				err = -ESERVERFAULT;
-		}
-
 		P9_DPRINTK(P9_DEBUG_9P, "<<< RERROR (%d) %s\n", -ecode, ename);
 
 		kfree(ename);
@@ -430,8 +425,8 @@ static int p9_check_errors(struct p9_client *c, struct p9_req_t *req)
 
 /**
  * p9_client_flush - flush (cancel) a request
- * c: client state
- * req: request to cancel
+ * @c: client state
+ * @oldreq: request to cancel
  *
  * This sents a flush for a particular requests and links
  * the flush request to the original request.  The current

net/9p/error.c

@@ -239,7 +239,7 @@ int p9_errstr2errno(char *errstr, int len)
 		errstr[len] = 0;
 		printk(KERN_ERR "%s: server reported unknown error %s\n",
 			__func__, errstr);
-		errno = 1;
+		errno = ESERVERFAULT;
 	}
 
 	return -errno;

net/9p/trans_fd.c

@@ -119,8 +119,8 @@ struct p9_poll_wait {
  * @wpos: write position for current frame
  * @wsize: amount of data to write for current frame
  * @wbuf: current write buffer
+ * @poll_pending_link: pending links to be polled per conn
  * @poll_wait: array of wait_q's for various worker threads
- * @poll_waddr: ????
  * @pt: poll state
  * @rq: current read work
  * @wq: current write work
@@ -700,9 +700,9 @@ static int p9_fd_cancel(struct p9_client *client, struct p9_req_t *req)
 }
 
 /**
- * parse_options - parse mount options into session structure
- * @options: options string passed from mount
- * @opts: transport-specific structure to parse options into
+ * parse_opts - parse mount options into p9_fd_opts structure
+ * @params: options string passed from mount
+ * @opts: fd transport-specific structure to parse options into
  *
  * Returns 0 upon success, -ERRNO upon failure
  */

net/9p/trans_rdma.c

@@ -67,14 +67,15 @@
  * @pd: Protection Domain pointer
  * @qp: Queue Pair pointer
  * @cq: Completion Queue pointer
+ * @dm_mr: DMA Memory Region pointer
  * @lkey: The local access only memory region key
  * @timeout: Number of uSecs to wait for connection management events
  * @sq_depth: The depth of the Send Queue
  * @sq_sem: Semaphore for the SQ
  * @rq_depth: The depth of the Receive Queue.
+ * @rq_count: Count of requests in the Receive Queue.
  * @addr: The remote peer's address
  * @req_lock: Protects the active request list
- * @send_wait: Wait list when the SQ fills up
  * @cm_done: Completion event for connection management tracking
  */
 struct p9_trans_rdma {
@@ -154,9 +155,9 @@ static match_table_t tokens = {
 };
 
 /**
- * parse_options - parse mount options into session structure
- * @options: options string passed from mount
- * @opts: transport-specific structure to parse options into
+ * parse_opts - parse mount options into rdma options structure
+ * @params: options string passed from mount
+ * @opts: rdma transport-specific structure to parse options into
  *
  * Returns 0 upon success, -ERRNO upon failure
  */

net/9p/trans_virtio.c

@@ -57,11 +57,9 @@ static int chan_index;
  * @initialized: whether the channel is initialized
  * @inuse: whether the channel is in use
  * @lock: protects multiple elements within this structure
+ * @client: client instance
  * @vdev: virtio dev associated with this channel
  * @vq: virtio queue associated with this channel
- * @tagpool: accounting for tag ids (and request slots)
- * @reqs: array of request slots
- * @max_tag: current number of request_slots allocated
  * @sg: scatter gather list which is used to pack a request (protected?)
  *
  * We keep all per-channel information in a structure.
@@ -92,7 +90,7 @@ static unsigned int rest_of_page(void *data)
 
 /**
  * p9_virtio_close - reclaim resources of a channel
- * @trans: transport state
+ * @client: client instance
  *
  * This reclaims a channel by freeing its resources and
  * reseting its inuse flag.
@@ -181,9 +179,8 @@ static int p9_virtio_cancel(struct p9_client *client, struct p9_req_t *req)
 
 /**
  * p9_virtio_request - issue a request
- * @t: transport state
- * @tc: &p9_fcall request to transmit
- * @rc: &p9_fcall to put reponse into
+ * @client: client instance issuing the request
+ * @req: request to be issued
  *
  */
 

net/ipv4/ip_output.c

@@ -813,6 +813,8 @@ int ip_append_data(struct sock *sk,
 			inet->cork.addr = ipc->addr;
 		}
 		rt = *rtp;
+		if (unlikely(!rt))
+			return -EFAULT;
 		/*
 		 * We steal reference to this route, caller should not release it
 		 */

security/integrity/ima/ima_main.c

@@ -262,6 +262,8 @@ void ima_counts_put(struct path *path, int mask)
 	else if (mask & (MAY_READ | MAY_EXEC))
 		iint->readcount--;
 	mutex_unlock(&iint->mutex);
+
+	kref_put(&iint->refcount, iint_free);
 }
 
 /*
@@ -291,6 +293,8 @@ void ima_counts_get(struct file *file)
 	if (file->f_mode & FMODE_WRITE)
 		iint->writecount++;
 	mutex_unlock(&iint->mutex);
+
+	kref_put(&iint->refcount, iint_free);
 }
 EXPORT_SYMBOL_GPL(ima_counts_get);