3.0.41-stable review

@@ -18,8 +18,8 @@
 #include <asm/system.h>
 
 
-#define ATOMIC_INIT(i)		((atomic_t) { (i) })
-#define ATOMIC64_INIT(i)	((atomic64_t) { (i) })
+#define ATOMIC_INIT(i)		{ (i) }
+#define ATOMIC64_INIT(i)	{ (i) }
 
 #define atomic_read(v)		(*(volatile int *)&(v)->counter)
 #define atomic64_read(v)	(*(volatile long *)&(v)->counter)

@@ -284,7 +284,7 @@ mspec_mmap(struct file *file, struct vm_
 	vdata->flags = flags;
 	vdata->type = type;
 	spin_lock_init(&vdata->lock);
-	vdata->refcnt = ATOMIC_INIT(1);
+	atomic_set(&vdata->refcnt, 1);
 	vma->vm_private_data = vdata;
 
 	vma->vm_flags |= (VM_IO | VM_RESERVED | VM_PFNMAP | VM_DONTEXPAND);

@@ -193,7 +193,7 @@ static int rpcb_create_local_unix(void)
 	if (IS_ERR(clnt)) {
 		dprintk("RPC:       failed to create AF_LOCAL rpcbind "
 				"client (errno %ld).\n", PTR_ERR(clnt));
-		result = -PTR_ERR(clnt);
+		result = PTR_ERR(clnt);
 		goto out;
 	}
 

@@ -242,7 +242,7 @@ static int rpcb_create_local_net(void)
 	if (IS_ERR(clnt)) {
 		dprintk("RPC:       failed to create local rpcbind "
 				"client (errno %ld).\n", PTR_ERR(clnt));
-		result = -PTR_ERR(clnt);
+		result = PTR_ERR(clnt);
 		goto out;
 	}
 

@@ -182,7 +182,7 @@ static int nilfs_ioctl_change_cpmode(str
 	if (copy_from_user(&cpmode, argp, sizeof(cpmode)))
 		goto out;
 
-	down_read(&inode->i_sb->s_umount);
+	mutex_lock(&nilfs->ns_snapshot_mount_mutex);
 
 	nilfs_transaction_begin(inode->i_sb, &ti, 0);
 	ret = nilfs_cpfile_change_cpmode(

@@ -192,7 +192,7 @@ static int nilfs_ioctl_change_cpmode(str
 	else
 		nilfs_transaction_commit(inode->i_sb); /* never fails */
 
-	up_read(&inode->i_sb->s_umount);
+	mutex_unlock(&nilfs->ns_snapshot_mount_mutex);
 out:
 	mnt_drop_write(filp->f_path.mnt);
 	return ret;

@@ -951,6 +951,8 @@ static int nilfs_attach_snapshot(struct
 	struct nilfs_root *root;
 	int ret;
 
+	mutex_lock(&nilfs->ns_snapshot_mount_mutex);
+
 	down_read(&nilfs->ns_segctor_sem);
 	ret = nilfs_cpfile_is_snapshot(nilfs->ns_cpfile, cno);
 	up_read(&nilfs->ns_segctor_sem);

@@ -975,6 +977,7 @@ static int nilfs_attach_snapshot(struct
 	ret = nilfs_get_root_dentry(s, root, root_dentry);
 	nilfs_put_root(root);
  out:
+	mutex_unlock(&nilfs->ns_snapshot_mount_mutex);
 	return ret;
 }
 

@@ -76,6 +76,7 @@ struct the_nilfs *alloc_nilfs(struct blo
 	nilfs->ns_bdev = bdev;
 	atomic_set(&nilfs->ns_ndirtyblks, 0);
 	init_rwsem(&nilfs->ns_sem);
+	mutex_init(&nilfs->ns_snapshot_mount_mutex);
 	INIT_LIST_HEAD(&nilfs->ns_dirty_files);
 	INIT_LIST_HEAD(&nilfs->ns_gc_inodes);
 	spin_lock_init(&nilfs->ns_inode_lock);

@@ -47,6 +47,7 @@ enum {
  * @ns_flags: flags
  * @ns_bdev: block device
  * @ns_sem: semaphore for shared states
+ * @ns_snapshot_mount_mutex: mutex to protect snapshot mounts
  * @ns_sbh: buffer heads of on-disk super blocks
  * @ns_sbp: pointers to super block data
  * @ns_sbwtime: previous write time of super block

@@ -99,6 +100,7 @@ struct the_nilfs {
 
 	struct block_device    *ns_bdev;
 	struct rw_semaphore	ns_sem;
+	struct mutex		ns_snapshot_mount_mutex;
 
 	/*
 	 * used for

@@ -95,7 +95,7 @@ efi_setup_pcdp_console(char *cmdline)
 	if (efi.hcdp == EFI_INVALID_TABLE_ADDR)
 		return -ENODEV;
 
-	pcdp = ioremap(efi.hcdp, 4096);
+	pcdp = early_ioremap(efi.hcdp, 4096);
 	printk(KERN_INFO "PCDP: v%d at 0x%lx\n", pcdp->rev, efi.hcdp);
 
 	if (strstr(cmdline, "console=hcdp")) {

@@ -131,6 +131,6 @@ efi_setup_pcdp_console(char *cmdline)
 	}
 
 out:
-	iounmap(pcdp);
+	early_iounmap(pcdp, 4096);
 	return rc;
 }

@@ -1334,8 +1334,8 @@ static int soft_offline_huge_page(struct
 	/* Keep page count to indicate a given hugepage is isolated. */
 
 	list_add(&hpage->lru, &pagelist);
-	ret = migrate_huge_pages(&pagelist, new_page, MPOL_MF_MOVE_ALL, 0,
-				true);
+	ret = migrate_huge_pages(&pagelist, new_page, MPOL_MF_MOVE_ALL, false,
+				MIGRATE_SYNC);
 	if (ret) {
 		struct page *page1, *page2;
 		list_for_each_entry_safe(page1, page2, &pagelist, lru)

@@ -1464,7 +1464,7 @@ int soft_offline_page(struct page *page,
 					    page_is_file_cache(page));
 		list_add(&page->lru, &pagelist);
 		ret = migrate_pages(&pagelist, new_page, MPOL_MF_MOVE_ALL,
-							0, MIGRATE_SYNC);
+							false, MIGRATE_SYNC);
 		if (ret) {
 			putback_lru_pages(&pagelist);
 			pr_info("soft offline: %#lx: migration failed %d, type %lx\n",

@@ -7,121 +7,10 @@
  */
 #ifndef _ASM_MUTEX_H
 #define _ASM_MUTEX_H
-
-#if __LINUX_ARM_ARCH__ < 6
-/* On pre-ARMv6 hardware the swp based implementation is the most efficient. */
-# include <asm-generic/mutex-xchg.h>
-#else
-
 /*
- * Attempting to lock a mutex on ARMv6+ can be done with a bastardized
- * atomic decrement (it is not a reliable atomic decrement but it satisfies
- * the defined semantics for our purpose, while being smaller and faster
- * than a real atomic decrement or atomic swap.  The idea is to attempt
- * decrementing the lock value only once.  If once decremented it isn't zero,
- * or if its store-back fails due to a dispute on the exclusive store, we
- * simply bail out immediately through the slow path where the lock will be
- * reattempted until it succeeds.
+ * On pre-ARMv6 hardware this results in a swp-based implementation,
+ * which is the most efficient. For ARMv6+, we emit a pair of exclusive
+ * accesses instead.
  */
-static inline void
-__mutex_fastpath_lock(atomic_t *count, void (*fail_fn)(atomic_t *))
-{
-	int __ex_flag, __res;
-
-	__asm__ (
-
-		"ldrex	%0, [%2]	\n\t"
-		"sub	%0, %0, #1	\n\t"
-		"strex	%1, %0, [%2]	"
-
-		: "=&r" (__res), "=&r" (__ex_flag)
-		: "r" (&(count)->counter)
-		: "cc","memory" );
-
-	__res |= __ex_flag;
-	if (unlikely(__res != 0))
-		fail_fn(count);
-}
-
-static inline int
-__mutex_fastpath_lock_retval(atomic_t *count, int (*fail_fn)(atomic_t *))
-{
-	int __ex_flag, __res;
-
-	__asm__ (
-
-		"ldrex	%0, [%2]	\n\t"
-		"sub	%0, %0, #1	\n\t"
-		"strex	%1, %0, [%2]	"
-
-		: "=&r" (__res), "=&r" (__ex_flag)
-		: "r" (&(count)->counter)
-		: "cc","memory" );
-
-	__res |= __ex_flag;
-	if (unlikely(__res != 0))
-		__res = fail_fn(count);
-	return __res;
-}
-
-/*
- * Same trick is used for the unlock fast path. However the original value,
- * rather than the result, is used to test for success in order to have
- * better generated assembly.
- */
-static inline void
-__mutex_fastpath_unlock(atomic_t *count, void (*fail_fn)(atomic_t *))
-{
-	int __ex_flag, __res, __orig;
-
-	__asm__ (
-
-		"ldrex	%0, [%3]	\n\t"
-		"add	%1, %0, #1	\n\t"
-		"strex	%2, %1, [%3]	"
-
-		: "=&r" (__orig), "=&r" (__res), "=&r" (__ex_flag)
-		: "r" (&(count)->counter)
-		: "cc","memory" );
-
-	__orig |= __ex_flag;
-	if (unlikely(__orig != 0))
-		fail_fn(count);
-}
-
-/*
- * If the unlock was done on a contended lock, or if the unlock simply fails
- * then the mutex remains locked.
- */
-#define __mutex_slowpath_needs_to_unlock()	1
-
-/*
- * For __mutex_fastpath_trylock we use another construct which could be
- * described as a "single value cmpxchg".
- *
- * This provides the needed trylock semantics like cmpxchg would, but it is
- * lighter and less generic than a true cmpxchg implementation.
- */
-static inline int
-__mutex_fastpath_trylock(atomic_t *count, int (*fail_fn)(atomic_t *))
-{
-	int __ex_flag, __res, __orig;
-
-	__asm__ (
-
-		"1: ldrex	%0, [%3]	\n\t"
-		"subs		%1, %0, #1	\n\t"
-		"strexeq	%2, %1, [%3]	\n\t"
-		"movlt		%0, #0		\n\t"
-		"cmpeq		%2, #0		\n\t"
-		"bgt		1b		"
-
-		: "=&r" (__orig), "=&r" (__res), "=&r" (__ex_flag)
-		: "r" (&count->counter)
-		: "cc", "memory" );
-
-	return __orig;
-}
-
-#endif
+#include <asm-generic/mutex-xchg.h>
 #endif

@@ -412,6 +412,12 @@ static int vfp_pm_suspend(void)
 
 		/* disable, just in case */
 		fmxr(FPEXC, fmrx(FPEXC) & ~FPEXC_EN);
+	} else if (vfp_current_hw_state[ti->cpu]) {
+#ifndef CONFIG_SMP
+		fmxr(FPEXC, fpexc | FPEXC_EN);
+		vfp_save_state(vfp_current_hw_state[ti->cpu], fpexc);
+		fmxr(FPEXC, fpexc);
+#endif
 	}
 
 	/* clear any information we had about last context state */

@@ -215,7 +215,9 @@ static inline void vivt_flush_cache_mm(s
 static inline void
 vivt_flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned long end)
 {
-	if (cpumask_test_cpu(smp_processor_id(), mm_cpumask(vma->vm_mm)))
+	struct mm_struct *mm = vma->vm_mm;
+
+	if (!mm || cpumask_test_cpu(smp_processor_id(), mm_cpumask(mm)))
 		__cpuc_flush_user_range(start & PAGE_MASK, PAGE_ALIGN(end),
 					vma->vm_flags);
 }

@@ -223,7 +225,9 @@ vivt_flush_cache_range(struct vm_area_st
 static inline void
 vivt_flush_cache_page(struct vm_area_struct *vma, unsigned long user_addr, unsigned long pfn)
 {
-	if (cpumask_test_cpu(smp_processor_id(), mm_cpumask(vma->vm_mm))) {
+	struct mm_struct *mm = vma->vm_mm;
+
+	if (!mm || cpumask_test_cpu(smp_processor_id(), mm_cpumask(mm))) {
 		unsigned long addr = user_addr & PAGE_MASK;
 		__cpuc_flush_user_range(addr, addr + PAGE_SIZE, vma->vm_flags);
 	}

@@ -3089,7 +3089,6 @@ static const struct snd_pci_quirk cxt506
 	SND_PCI_QUIRK(0x1028, 0x02d8, "Dell Vostro", CXT5066_DELL_VOSTRO),
 	SND_PCI_QUIRK(0x1028, 0x02f5, "Dell Vostro 320", CXT5066_IDEAPAD),
 	SND_PCI_QUIRK(0x1028, 0x0401, "Dell Vostro 1014", CXT5066_DELL_VOSTRO),
-	SND_PCI_QUIRK(0x1028, 0x0402, "Dell Vostro", CXT5066_DELL_VOSTRO),
 	SND_PCI_QUIRK(0x1028, 0x0408, "Dell Inspiron One 19T", CXT5066_IDEAPAD),
 	SND_PCI_QUIRK(0x1028, 0x050f, "Dell Inspiron", CXT5066_IDEAPAD),
 	SND_PCI_QUIRK(0x1028, 0x0510, "Dell Vostro", CXT5066_IDEAPAD),

@@ -33,6 +33,24 @@
 void __mmu_notifier_release(struct mm_struct *mm)
 {
 	struct mmu_notifier *mn;
+	struct hlist_node *n;
+
+	/*
+	 * RCU here will block mmu_notifier_unregister until
+	 * ->release returns.
+	 */
+	rcu_read_lock();
+	hlist_for_each_entry_rcu(mn, n, &mm->mmu_notifier_mm->list, hlist)
+		/*
+		 * if ->release runs before mmu_notifier_unregister it
+		 * must be handled as it's the only way for the driver
+		 * to flush all existing sptes and stop the driver
+		 * from establishing any more sptes before all the
+		 * pages in the mm are freed.
+		 */
+		if (mn->ops->release)
+			mn->ops->release(mn, mm);
+	rcu_read_unlock();
 
 	spin_lock(&mm->mmu_notifier_mm->lock);
 	while (unlikely(!hlist_empty(&mm->mmu_notifier_mm->list))) {

@@ -46,23 +64,6 @@ void __mmu_notifier_release(struct mm_st
 		 * mmu_notifier_unregister to return.
 		 */
 		hlist_del_init_rcu(&mn->hlist);
-		/*
-		 * RCU here will block mmu_notifier_unregister until
-		 * ->release returns.
-		 */
-		rcu_read_lock();
-		spin_unlock(&mm->mmu_notifier_mm->lock);
-		/*
-		 * if ->release runs before mmu_notifier_unregister it
-		 * must be handled as it's the only way for the driver
-		 * to flush all existing sptes and stop the driver
-		 * from establishing any more sptes before all the
-		 * pages in the mm are freed.
-		 */
-		if (mn->ops->release)
-			mn->ops->release(mn, mm);
-		rcu_read_unlock();
-		spin_lock(&mm->mmu_notifier_mm->lock);
 	}
 	spin_unlock(&mm->mmu_notifier_mm->lock);
 

@@ -284,16 +285,13 @@ void mmu_notifier_unregister(struct mmu_
 {
 	BUG_ON(atomic_read(&mm->mm_count) <= 0);
 
-	spin_lock(&mm->mmu_notifier_mm->lock);
 	if (!hlist_unhashed(&mn->hlist)) {
-		hlist_del_rcu(&mn->hlist);
-
 		/*
 		 * RCU here will force exit_mmap to wait ->release to finish
 		 * before freeing the pages.
 		 */
 		rcu_read_lock();
-		spin_unlock(&mm->mmu_notifier_mm->lock);
+
 		/*
 		 * exit_mmap will block in mmu_notifier_release to
 		 * guarantee ->release is called before freeing the

@@ -302,8 +300,11 @@ void mmu_notifier_unregister(struct mmu_
 		if (mn->ops->release)
 			mn->ops->release(mn, mm);
 		rcu_read_unlock();
-	} else
+
+		spin_lock(&mm->mmu_notifier_mm->lock);
+		hlist_del_rcu(&mn->hlist);
 		spin_unlock(&mm->mmu_notifier_mm->lock);
+	}
 
 	/*
 	 * Wait any running method to finish, of course including

@@ -490,6 +490,7 @@ void ieee80211_stop_mesh(struct ieee8021
 
 	del_timer_sync(&sdata->u.mesh.housekeeping_timer);
 	del_timer_sync(&sdata->u.mesh.mesh_path_root_timer);
+	del_timer_sync(&sdata->u.mesh.mesh_path_timer);
 	/*
 	 * If the timer fired while we waited for it, it will have
 	 * requeued the work. Now the work will be running again

@@ -220,7 +220,7 @@ void __init arch_init_ideal_nops(void)
 			ideal_nops = intel_nops;
 #endif
 		}
-
+		break;
 	default:
 #ifdef CONFIG_X86_64
 		ideal_nops = k8_nops;

@@ -932,7 +932,21 @@ static ssize_t extract_entropy_user(stru
  */
 void get_random_bytes(void *buf, int nbytes)
 {
-	extract_entropy(&nonblocking_pool, buf, nbytes, 0, 0);
+	char *p = buf;
+
+	while (nbytes) {
+		unsigned long v;
+		int chunk = min(nbytes, (int)sizeof(unsigned long));
+
+		if (!arch_get_random_long(&v))
+			break;
+
+		memcpy(buf, &v, chunk);
+		p += chunk;
+		nbytes -= chunk;
+	}
+
+	extract_entropy(&nonblocking_pool, p, nbytes, 0, 0);
 }
 EXPORT_SYMBOL(get_random_bytes);
 

@@ -1318,9 +1332,14 @@ late_initcall(random_int_secret_init);
 DEFINE_PER_CPU(__u32 [MD5_DIGEST_WORDS], get_random_int_hash);
 unsigned int get_random_int(void)
 {
-	__u32 *hash = get_cpu_var(get_random_int_hash);
+	__u32 *hash;
 	unsigned int ret;
 
+	if (arch_get_random_int(&ret))
+		return ret;
+
+	hash = get_cpu_var(get_random_int_hash);
+
 	hash[0] += current->pid + jiffies + get_cycles();
 	md5_transform(hash, random_int_secret);
 	ret = hash[0];

@@ -91,6 +91,19 @@ static inline void prandom32_seed(struct
 	state->s3 = __seed(i, 15);
 }
 
+#ifdef CONFIG_ARCH_RANDOM
+# include <asm/archrandom.h>
+#else
+static inline int arch_get_random_long(unsigned long *v)
+{
+	return 0;
+}
+static inline int arch_get_random_int(unsigned int *v)
+{
+	return 0;
+}
+#endif
+
 #endif /* __KERNEL___ */
 
 #endif /* _LINUX_RANDOM_H */

@@ -941,7 +941,7 @@ void get_random_bytes(void *buf, int nby
 		if (!arch_get_random_long(&v))
 			break;
 
-		memcpy(buf, &v, chunk);
+		memcpy(p, &v, chunk);
 		p += chunk;
 		nbytes -= chunk;
 	}

@@ -624,8 +624,8 @@ static struct timer_rand_state input_tim
 static void add_timer_randomness(struct timer_rand_state *state, unsigned num)
 {
 	struct {
-		cycles_t cycles;
 		long jiffies;
+		unsigned cycles;
 		unsigned num;
 	} sample;
 	long delta, delta2, delta3;

@@ -637,7 +637,11 @@ static void add_timer_randomness(struct
 		goto out;
 
 	sample.jiffies = jiffies;
-	sample.cycles = get_cycles();
+
+	/* Use arch random value, fall back to cycles */
+	if (!arch_get_random_int(&sample.cycles))
+		sample.cycles = get_cycles();
+
 	sample.num = num;
 	mix_pool_bytes(&input_pool, &sample, sizeof(sample));
 

@@ -965,6 +965,7 @@ EXPORT_SYMBOL(get_random_bytes);
  */
 static void init_std_data(struct entropy_store *r)
 {
+	int i;
 	ktime_t now;
 	unsigned long flags;
 

@@ -974,6 +975,11 @@ static void init_std_data(struct entropy
 
 	now = ktime_get_real();
 	mix_pool_bytes(r, &now, sizeof(now));
+	for (i = r->poolinfo->poolwords; i; i--) {
+		if (!arch_get_random_long(&flags))
+			break;
+		mix_pool_bytes(r, &flags, sizeof(flags));
+	}
 	mix_pool_bytes(r, utsname(), sizeof(*(utsname())));
 }
 

@@ -975,7 +975,7 @@ static void init_std_data(struct entropy
 
 	now = ktime_get_real();
 	mix_pool_bytes(r, &now, sizeof(now));
-	for (i = r->poolinfo->poolwords; i; i--) {
+	for (i = r->poolinfo->POOLBYTES; i > 0; i -= sizeof flags) {
 		if (!arch_get_random_long(&flags))
 			break;
 		mix_pool_bytes(r, &flags, sizeof(flags));

@@ -1260,10 +1260,15 @@ static int proc_do_uuid(ctl_table *table
 	uuid = table->data;
 	if (!uuid) {
 		uuid = tmp_uuid;
-		uuid[8] = 0;
-	}
-	if (uuid[8] == 0)
 		generate_random_uuid(uuid);
+	} else {
+		static DEFINE_SPINLOCK(bootid_spinlock);
+
+		spin_lock(&bootid_spinlock);
+		if (!uuid[8])
+			generate_random_uuid(uuid);
+		spin_unlock(&bootid_spinlock);
+	}
 
 	sprintf(buf, "%pU", uuid);
 

@@ -127,19 +127,15 @@
  *
  * 	void add_input_randomness(unsigned int type, unsigned int code,
  *                                unsigned int value);
- * 	void add_interrupt_randomness(int irq);
+ *	void add_interrupt_randomness(int irq, int irq_flags);
  * 	void add_disk_randomness(struct gendisk *disk);
  *
  * add_input_randomness() uses the input layer interrupt timing, as well as
  * the event type information from the hardware.
  *
- * add_interrupt_randomness() uses the inter-interrupt timing as random
- * inputs to the entropy pool.  Note that not all interrupts are good
- * sources of randomness!  For example, the timer interrupts is not a
- * good choice, because the periodicity of the interrupts is too
- * regular, and hence predictable to an attacker.  Network Interface
- * Controller interrupts are a better measure, since the timing of the
- * NIC interrupts are more unpredictable.
+ * add_interrupt_randomness() uses the interrupt timing as random
+ * inputs to the entropy pool. Using the cycle counters and the irq source
+ * as inputs, it feeds the randomness roughly once a second.
  *
  * add_disk_randomness() uses what amounts to the seek time of block
  * layer request events, on a per-disk_devt basis, as input to the

@@ -248,6 +244,7 @@
 #include <linux/percpu.h>
 #include <linux/cryptohash.h>
 #include <linux/fips.h>
+#include <linux/ptrace.h>
 
 #ifdef CONFIG_GENERIC_HARDIRQS
 # include <linux/irq.h>

@@ -256,6 +253,7 @@
 #include <asm/processor.h>
 #include <asm/uaccess.h>
 #include <asm/irq.h>
+#include <asm/irq_regs.h>
 #include <asm/io.h>
 
 /*

@@ -421,7 +419,9 @@ struct entropy_store {
 	spinlock_t lock;
 	unsigned add_ptr;
 	int entropy_count;
+	int entropy_total;
 	int input_rotate;
+	unsigned int initialized:1;
 	__u8 last_data[EXTRACT_SIZE];
 };
 

@@ -454,6 +454,10 @@ static struct entropy_store nonblocking_
 	.pool = nonblocking_pool_data
 };
 
+static __u32 const twist_table[8] = {
+	0x00000000, 0x3b6e20c8, 0x76dc4190, 0x4db26158,
+	0xedb88320, 0xd6d6a3e8, 0x9b64c2b0, 0xa00ae278 };
+
 /*
  * This function adds bytes into the entropy "pool".  It does not
  * update the entropy estimate.  The caller should call

@@ -467,9 +471,6 @@ static struct entropy_store nonblocking_
 static void mix_pool_bytes_extract(struct entropy_store *r, const void *in,
 				   int nbytes, __u8 out[64])
 {
-	static __u32 const twist_table[8] = {
-		0x00000000, 0x3b6e20c8, 0x76dc4190, 0x4db26158,
-		0xedb88320, 0xd6d6a3e8, 0x9b64c2b0, 0xa00ae278 };
 	unsigned long i, j, tap1, tap2, tap3, tap4, tap5;
 	int input_rotate;
 	int wordmask = r->poolinfo->poolwords - 1;

@@ -528,6 +529,36 @@ static void mix_pool_bytes(struct entrop
        mix_pool_bytes_extract(r, in, bytes, NULL);
 }
 
+struct fast_pool {
+	__u32		pool[4];
+	unsigned long	last;
+	unsigned short	count;
+	unsigned char	rotate;
+	unsigned char	last_timer_intr;
+};
+
+/*
+ * This is a fast mixing routine used by the interrupt randomness
+ * collector.  It's hardcoded for an 128 bit pool and assumes that any
+ * locks that might be needed are taken by the caller.
+ */
+static void fast_mix(struct fast_pool *f, const void *in, int nbytes)
+{
+	const char	*bytes = in;
+	__u32		w;
+	unsigned	i = f->count;
+	unsigned	input_rotate = f->rotate;
+
+	while (nbytes--) {
+		w = rol32(*bytes++, input_rotate & 31) ^ f->pool[i & 3] ^
+			f->pool[(i + 1) & 3];
+		f->pool[i & 3] = (w >> 3) ^ twist_table[w & 7];
+		input_rotate += (i++ & 3) ? 7 : 14;
+	}
+	f->count = i;
+	f->rotate = input_rotate;
+}
+
 /*
  * Credit (or debit) the entropy store with n bits of entropy
  */

@@ -551,6 +582,12 @@ static void credit_entropy_bits(struct e
 		entropy_count = r->poolinfo->POOLBITS;
 	r->entropy_count = entropy_count;
 
+	if (!r->initialized && nbits > 0) {
+		r->entropy_total += nbits;
+		if (r->entropy_total > 128)
+			r->initialized = 1;
+	}
+
 	/* should we wake readers? */
 	if (r == &input_pool && entropy_count >= random_read_wakeup_thresh) {
 		wake_up_interruptible(&random_read_wait);

@@ -700,17 +737,48 @@ void add_input_randomness(unsigned int t
 }
 EXPORT_SYMBOL_GPL(add_input_randomness);
 
-void add_interrupt_randomness(int irq)
+static DEFINE_PER_CPU(struct fast_pool, irq_randomness);
+
+void add_interrupt_randomness(int irq, int irq_flags)
 {
-	struct timer_rand_state *state;
+	struct entropy_store	*r;
+	struct fast_pool	*fast_pool = &__get_cpu_var(irq_randomness);
+	struct pt_regs		*regs = get_irq_regs();
+	unsigned long		now = jiffies;
+	__u32			input[4], cycles = get_cycles();
+
+	input[0] = cycles ^ jiffies;
+	input[1] = irq;
+	if (regs) {
+		__u64 ip = instruction_pointer(regs);
+		input[2] = ip;
+		input[3] = ip >> 32;
+	}
 
-	state = get_timer_rand_state(irq);
+	fast_mix(fast_pool, input, sizeof(input));
 
-	if (state == NULL)
+	if ((fast_pool->count & 1023) &&
+	    !time_after(now, fast_pool->last + HZ))
 		return;
 
-	DEBUG_ENT("irq event %d\n", irq);
-	add_timer_randomness(state, 0x100 + irq);
+	fast_pool->last = now;
+
+	r = nonblocking_pool.initialized ? &input_pool : &nonblocking_pool;
+	mix_pool_bytes(r, &fast_pool->pool, sizeof(fast_pool->pool));
+	/*
+	 * If we don't have a valid cycle counter, and we see
+	 * back-to-back timer interrupts, then skip giving credit for
+	 * any entropy.
+	 */
+	if (cycles == 0) {
+		if (irq_flags & __IRQF_TIMER) {
+			if (fast_pool->last_timer_intr)
+				return;
+			fast_pool->last_timer_intr = 1;
+		} else
+			fast_pool->last_timer_intr = 0;
+	}
+	credit_entropy_bits(r, 1);
 }
 
 #ifdef CONFIG_BLOCK

@@ -971,6 +1039,7 @@ static void init_std_data(struct entropy
 
 	spin_lock_irqsave(&r->lock, flags);
 	r->entropy_count = 0;
+	r->entropy_total = 0;
 	spin_unlock_irqrestore(&r->lock, flags);
 
 	now = ktime_get_real();

@@ -408,8 +408,6 @@ static irqreturn_t ab3100_irq_handler(in
 	u32 fatevent;
 	int err;
 
-	add_interrupt_randomness(irq);
-
 	err = ab3100_get_register_page_interruptible(ab3100, AB3100_EVENTA1,
 				       event_regs, 3);
 	if (err)

@@ -52,7 +52,7 @@ extern void rand_initialize_irq(int irq)
 
 extern void add_input_randomness(unsigned int type, unsigned int code,
 				 unsigned int value);
-extern void add_interrupt_randomness(int irq);
+extern void add_interrupt_randomness(int irq, int irq_flags);
 
 extern void get_random_bytes(void *buf, int nbytes);
 void generate_random_uuid(unsigned char uuid_out[16]);

@@ -117,7 +117,7 @@ irqreturn_t
 handle_irq_event_percpu(struct irq_desc *desc, struct irqaction *action)
 {
 	irqreturn_t retval = IRQ_NONE;
-	unsigned int random = 0, irq = desc->irq_data.irq;
+	unsigned int flags = 0, irq = desc->irq_data.irq;
 
 	do {
 		irqreturn_t res;

@@ -145,7 +145,7 @@ handle_irq_event_percpu(struct irq_desc
 
 			/* Fall through to add to randomness */
 		case IRQ_HANDLED:
-			random |= action->flags;
+			flags |= action->flags;
 			break;
 
 		default:

@@ -156,8 +156,7 @@ handle_irq_event_percpu(struct irq_desc
 		action = action->next;
 	} while (action);
 
-	if (random & IRQF_SAMPLE_RANDOM)
-		add_interrupt_randomness(irq);
+	add_interrupt_randomness(irq, flags);
 
 	if (!noirqdebug)
 		note_interrupt(irq, desc, retval);

@@ -418,9 +418,9 @@ struct entropy_store {
 	/* read-write data: */
 	spinlock_t lock;
 	unsigned add_ptr;
+	unsigned input_rotate;
 	int entropy_count;
 	int entropy_total;
-	int input_rotate;
 	unsigned int initialized:1;
 	__u8 last_data[EXTRACT_SIZE];
 };

@@ -468,26 +468,24 @@ static __u32 const twist_table[8] = {
  * it's cheap to do so and helps slightly in the expected case where
  * the entropy is concentrated in the low-order bits.
  */
-static void mix_pool_bytes_extract(struct entropy_store *r, const void *in,
-				   int nbytes, __u8 out[64])
+static void __mix_pool_bytes(struct entropy_store *r, const void *in,
+			     int nbytes, __u8 out[64])
 {
 	unsigned long i, j, tap1, tap2, tap3, tap4, tap5;
 	int input_rotate;
 	int wordmask = r->poolinfo->poolwords - 1;
 	const char *bytes = in;
 	__u32 w;
-	unsigned long flags;
 
-	/* Taps are constant, so we can load them without holding r->lock.  */
 	tap1 = r->poolinfo->tap1;
 	tap2 = r->poolinfo->tap2;
 	tap3 = r->poolinfo->tap3;
 	tap4 = r->poolinfo->tap4;
 	tap5 = r->poolinfo->tap5;
 
-	spin_lock_irqsave(&r->lock, flags);
-	input_rotate = r->input_rotate;
-	i = r->add_ptr;
+	smp_rmb();
+	input_rotate = ACCESS_ONCE(r->input_rotate);
+	i = ACCESS_ONCE(r->add_ptr);
 
 	/* mix one byte at a time to simplify size handling and churn faster */
 	while (nbytes--) {

@@ -514,19 +512,23 @@ static void mix_pool_bytes_extract(struc
 		input_rotate += i ? 7 : 14;
 	}
 
-	r->input_rotate = input_rotate;
-	r->add_ptr = i;
+	ACCESS_ONCE(r->input_rotate) = input_rotate;
+	ACCESS_ONCE(r->add_ptr) = i;
+	smp_wmb();
 
 	if (out)
 		for (j = 0; j < 16; j++)
 			((__u32 *)out)[j] = r->pool[(i - j) & wordmask];
-
-	spin_unlock_irqrestore(&r->lock, flags);
 }
 
-static void mix_pool_bytes(struct entropy_store *r, const void *in, int bytes)
+static void mix_pool_bytes(struct entropy_store *r, const void *in,
+			     int nbytes, __u8 out[64])
 {
-       mix_pool_bytes_extract(r, in, bytes, NULL);
+	unsigned long flags;
+
+	spin_lock_irqsave(&r->lock, flags);
+	__mix_pool_bytes(r, in, nbytes, out);
+	spin_unlock_irqrestore(&r->lock, flags);
 }
 
 struct fast_pool {

@@ -564,23 +566,22 @@ static void fast_mix(struct fast_pool *f
  */
 static void credit_entropy_bits(struct entropy_store *r, int nbits)
 {
-	unsigned long flags;
-	int entropy_count;
+	int entropy_count, orig;
 
 	if (!nbits)
 		return;
 
-	spin_lock_irqsave(&r->lock, flags);
-
 	DEBUG_ENT("added %d entropy credits to %s\n", nbits, r->name);
-	entropy_count = r->entropy_count;
+retry:
+	entropy_count = orig = ACCESS_ONCE(r->entropy_count);
 	entropy_count += nbits;
 	if (entropy_count < 0) {
 		DEBUG_ENT("negative entropy/overflow\n");
 		entropy_count = 0;
 	} else if (entropy_count > r->poolinfo->POOLBITS)
 		entropy_count = r->poolinfo->POOLBITS;
-	r->entropy_count = entropy_count;
+	if (cmpxchg(&r->entropy_count, orig, entropy_count) != orig)
+		goto retry;
 
 	if (!r->initialized && nbits > 0) {
 		r->entropy_total += nbits;

@@ -593,7 +594,6 @@ static void credit_entropy_bits(struct e
 		wake_up_interruptible(&random_read_wait);
 		kill_fasync(&fasync, SIGIO, POLL_IN);
 	}
-	spin_unlock_irqrestore(&r->lock, flags);
 }
 
 /*********************************************************************

@@ -680,7 +680,7 @@ static void add_timer_randomness(struct
 		sample.cycles = get_cycles();
 
 	sample.num = num;
-	mix_pool_bytes(&input_pool, &sample, sizeof(sample));
+	mix_pool_bytes(&input_pool, &sample, sizeof(sample), NULL);
 
 	/*
 	 * Calculate number of bits of randomness we probably added.

@@ -764,7 +764,7 @@ void add_interrupt_randomness(int irq, i
 	fast_pool->last = now;
 
 	r = nonblocking_pool.initialized ? &input_pool : &nonblocking_pool;
-	mix_pool_bytes(r, &fast_pool->pool, sizeof(fast_pool->pool));
+	__mix_pool_bytes(r, &fast_pool->pool, sizeof(fast_pool->pool), NULL);
 	/*
 	 * If we don't have a valid cycle counter, and we see
 	 * back-to-back timer interrupts, then skip giving credit for

@@ -829,7 +829,7 @@ static void xfer_secondary_pool(struct e
 
 		bytes = extract_entropy(r->pull, tmp, bytes,
 					random_read_wakeup_thresh / 8, rsvd);
-		mix_pool_bytes(r, tmp, bytes);
+		mix_pool_bytes(r, tmp, bytes, NULL);
 		credit_entropy_bits(r, bytes*8);
 	}
 }

@@ -890,9 +890,11 @@ static void extract_buf(struct entropy_s
 	int i;
 	__u32 hash[5], workspace[SHA_WORKSPACE_WORDS];
 	__u8 extract[64];
+	unsigned long flags;
 
 	/* Generate a hash across the pool, 16 words (512 bits) at a time */
 	sha_init(hash);
+	spin_lock_irqsave(&r->lock, flags);
 	for (i = 0; i < r->poolinfo->poolwords; i += 16)
 		sha_transform(hash, (__u8 *)(r->pool + i), workspace);
 

@@ -905,7 +907,8 @@ static void extract_buf(struct entropy_s
 	 * brute-forcing the feedback as hard as brute-forcing the
 	 * hash.
 	 */
-	mix_pool_bytes_extract(r, hash, sizeof(hash), extract);
+	__mix_pool_bytes(r, hash, sizeof(hash), extract);
+	spin_unlock_irqrestore(&r->lock, flags);
 
 	/*
 	 * To avoid duplicates, we atomically extract a portion of the

@@ -928,11 +931,10 @@ static void extract_buf(struct entropy_s
 }
 
 static ssize_t extract_entropy(struct entropy_store *r, void *buf,
-			       size_t nbytes, int min, int reserved)
+				 size_t nbytes, int min, int reserved)
 {
 	ssize_t ret = 0, i;
 	__u8 tmp[EXTRACT_SIZE];
-	unsigned long flags;
 
 	xfer_secondary_pool(r, nbytes);
 	nbytes = account(r, nbytes, min, reserved);

@@ -941,6 +943,8 @@ static ssize_t extract_entropy(struct en
 		extract_buf(r, tmp);
 
 		if (fips_enabled) {
+			unsigned long flags;
+
 			spin_lock_irqsave(&r->lock, flags);
 			if (!memcmp(tmp, r->last_data, EXTRACT_SIZE))
 				panic("Hardware RNG duplicated output!\n");

@@ -1034,22 +1038,18 @@ EXPORT_SYMBOL(get_random_bytes);
 static void init_std_data(struct entropy_store *r)
 {
 	int i;
-	ktime_t now;
-	unsigned long flags;
+	ktime_t now = ktime_get_real();
+	unsigned long rv;
 
-	spin_lock_irqsave(&r->lock, flags);
 	r->entropy_count = 0;
 	r->entropy_total = 0;
-	spin_unlock_irqrestore(&r->lock, flags);
-
-	now = ktime_get_real();
-	mix_pool_bytes(r, &now, sizeof(now));
-	for (i = r->poolinfo->POOLBYTES; i > 0; i -= sizeof flags) {
-		if (!arch_get_random_long(&flags))
+	mix_pool_bytes(r, &now, sizeof(now), NULL);
+	for (i = r->poolinfo->POOLBYTES; i > 0; i -= sizeof(rv)) {
+		if (!arch_get_random_long(&rv))
 			break;
-		mix_pool_bytes(r, &flags, sizeof(flags));
+		mix_pool_bytes(r, &rv, sizeof(rv), NULL);
 	}
-	mix_pool_bytes(r, utsname(), sizeof(*(utsname())));
+	mix_pool_bytes(r, utsname(), sizeof(*(utsname())), NULL);
 }
 
 static int rand_initialize(void)

@@ -1186,7 +1186,7 @@ write_pool(struct entropy_store *r, cons
 		count -= bytes;
 		p += bytes;
 
-		mix_pool_bytes(r, buf, bytes);
+		mix_pool_bytes(r, buf, bytes, NULL);
 		cond_resched();
 	}
 

@@ -125,11 +125,20 @@
  * The current exported interfaces for gathering environmental noise
  * from the devices are:
  *
+ *	void add_device_randomness(const void *buf, unsigned int size);
  * 	void add_input_randomness(unsigned int type, unsigned int code,
  *                                unsigned int value);
  *	void add_interrupt_randomness(int irq, int irq_flags);
  * 	void add_disk_randomness(struct gendisk *disk);
  *
+ * add_device_randomness() is for adding data to the random pool that
+ * is likely to differ between two devices (or possibly even per boot).
+ * This would be things like MAC addresses or serial numbers, or the
+ * read-out of the RTC. This does *not* add any actual entropy to the
+ * pool, but it initializes the pool to different values for devices
+ * that might otherwise be identical and have very little entropy
+ * available to them (particularly common in the embedded world).
+ *
  * add_input_randomness() uses the input layer interrupt timing, as well as
  * the event type information from the hardware.
  *

@@ -646,6 +655,25 @@ static void set_timer_rand_state(unsigne
 }
 #endif
 
+/*
+ * Add device- or boot-specific data to the input and nonblocking
+ * pools to help initialize them to unique values.
+ *
+ * None of this adds any entropy, it is meant to avoid the
+ * problem of the nonblocking pool having similar initial state
+ * across largely identical devices.
+ */
+void add_device_randomness(const void *buf, unsigned int size)
+{
+	unsigned long time = get_cycles() ^ jiffies;
+
+	mix_pool_bytes(&input_pool, buf, size, NULL);
+	mix_pool_bytes(&input_pool, &time, sizeof(time), NULL);
+	mix_pool_bytes(&nonblocking_pool, buf, size, NULL);
+	mix_pool_bytes(&nonblocking_pool, &time, sizeof(time), NULL);
+}
+EXPORT_SYMBOL(add_device_randomness);
+
 static struct timer_rand_state input_timer_state;
 
 /*

@@ -50,6 +50,7 @@ struct rnd_state {
 
 extern void rand_initialize_irq(int irq);
 
+extern void add_device_randomness(const void *, unsigned int);
 extern void add_input_randomness(unsigned int type, unsigned int code,
 				 unsigned int value);
 extern void add_interrupt_randomness(int irq, int irq_flags);

@@ -24,6 +24,7 @@
 #include <linux/kthread.h>
 #include <linux/mutex.h>
 #include <linux/freezer.h>
+#include <linux/random.h>
 
 #include <asm/uaccess.h>
 #include <asm/byteorder.h>

@@ -1902,6 +1903,14 @@ int usb_new_device(struct usb_device *ud
 	/* Tell the world! */
 	announce_device(udev);
 
+	if (udev->serial)
+		add_device_randomness(udev->serial, strlen(udev->serial));
+	if (udev->product)
+		add_device_randomness(udev->product, strlen(udev->product));
+	if (udev->manufacturer)
+		add_device_randomness(udev->manufacturer,
+				      strlen(udev->manufacturer));
+
 	device_enable_async_suspend(&udev->dev);
 	/* Register the device.  The device driver is responsible
 	 * for configuring the device and invoking the add-device

@@ -1163,6 +1163,7 @@ static int __dev_open(struct net_device
 		net_dmaengine_get();
 		dev_set_rx_mode(dev);
 		dev_activate(dev);
+		add_device_randomness(dev->dev_addr, dev->addr_len);
 	}
 
 	return ret;

@@ -4730,6 +4731,7 @@ int dev_set_mac_address(struct net_devic
 	err = ops->ndo_set_mac_address(dev, sa);
 	if (!err)
 		call_netdevice_notifiers(NETDEV_CHANGEADDR, dev);
+	add_device_randomness(dev->dev_addr, dev->addr_len);
 	return err;
 }
 EXPORT_SYMBOL(dev_set_mac_address);

@@ -5507,6 +5509,7 @@ int register_netdevice(struct net_device
 	dev_init_scheduler(dev);
 	dev_hold(dev);
 	list_netdevice(dev);
+	add_device_randomness(dev->dev_addr, dev->addr_len);
 
 	/* Notify protocols, that a new device appeared. */
 	ret = call_netdevice_notifiers(NETDEV_REGISTER, dev);

@@ -1304,6 +1304,7 @@ static int do_setlink(struct net_device
 			goto errout;
 		send_addr_notify = 1;
 		modified = 1;
+		add_device_randomness(dev->dev_addr, dev->addr_len);
 	}
 
 	if (tb[IFLA_MTU]) {

@@ -254,6 +254,7 @@
 #include <linux/cryptohash.h>
 #include <linux/fips.h>
 #include <linux/ptrace.h>
+#include <linux/kmemcheck.h>
 
 #ifdef CONFIG_GENERIC_HARDIRQS
 # include <linux/irq.h>

@@ -702,11 +703,7 @@ static void add_timer_randomness(struct
 		goto out;
 
 	sample.jiffies = jiffies;
-
-	/* Use arch random value, fall back to cycles */
-	if (!arch_get_random_int(&sample.cycles))
-		sample.cycles = get_cycles();
-
+	sample.cycles = get_cycles();
 	sample.num = num;
 	mix_pool_bytes(&input_pool, &sample, sizeof(sample), NULL);
 

@@ -838,7 +835,11 @@ static ssize_t extract_entropy(struct en
  */
 static void xfer_secondary_pool(struct entropy_store *r, size_t nbytes)
 {
-	__u32 tmp[OUTPUT_POOL_WORDS];
+	union {
+		__u32	tmp[OUTPUT_POOL_WORDS];
+		long	hwrand[4];
+	} u;
+	int	i;
 
 	if (r->pull && r->entropy_count < nbytes * 8 &&
 	    r->entropy_count < r->poolinfo->POOLBITS) {

@@ -849,17 +850,23 @@ static void xfer_secondary_pool(struct e
 		/* pull at least as many as BYTES as wakeup BITS */
 		bytes = max_t(int, bytes, random_read_wakeup_thresh / 8);
 		/* but never more than the buffer size */
-		bytes = min_t(int, bytes, sizeof(tmp));
+		bytes = min_t(int, bytes, sizeof(u.tmp));
 
 		DEBUG_ENT("going to reseed %s with %d bits "
 			  "(%d of %d requested)\n",
 			  r->name, bytes * 8, nbytes * 8, r->entropy_count);
 
-		bytes = extract_entropy(r->pull, tmp, bytes,
+		bytes = extract_entropy(r->pull, u.tmp, bytes,
 					random_read_wakeup_thresh / 8, rsvd);
-		mix_pool_bytes(r, tmp, bytes, NULL);
+		mix_pool_bytes(r, u.tmp, bytes, NULL);
 		credit_entropy_bits(r, bytes*8);
 	}
+	kmemcheck_mark_initialized(&u.hwrand, sizeof(u.hwrand));
+	for (i = 0; i < 4; i++)
+		if (arch_get_random_long(&u.hwrand[i]))
+			break;
+	if (i)
+		mix_pool_bytes(r, &u.hwrand, sizeof(u.hwrand), 0);
 }
 
 /*

@@ -1038,11 +1038,28 @@ static ssize_t extract_entropy_user(stru
 
 /*
  * This function is the exported kernel interface.  It returns some
- * number of good random numbers, suitable for seeding TCP sequence
- * numbers, etc.
+ * number of good random numbers, suitable for key generation, seeding
+ * TCP sequence numbers, etc.  It does not use the hw random number
+ * generator, if available; use get_random_bytes_arch() for that.
  */
 void get_random_bytes(void *buf, int nbytes)
 {
+	extract_entropy(&nonblocking_pool, buf, nbytes, 0, 0);
+}
+EXPORT_SYMBOL(get_random_bytes);
+
+/*
+ * This function will use the architecture-specific hardware random
+ * number generator if it is available.  The arch-specific hw RNG will
+ * almost certainly be faster than what we can do in software, but it
+ * is impossible to verify that it is implemented securely (as
+ * opposed, to, say, the AES encryption of a sequence number using a
+ * key known by the NSA).  So it's useful if we need the speed, but
+ * only if we're willing to trust the hardware manufacturer not to
+ * have put in a back door.
+ */
+void get_random_bytes_arch(void *buf, int nbytes)
+{
 	char *p = buf;
 
 	while (nbytes) {

@@ -1057,9 +1074,11 @@ void get_random_bytes(void *buf, int nby
 		nbytes -= chunk;
 	}
 
-	extract_entropy(&nonblocking_pool, p, nbytes, 0, 0);
+	if (nbytes)
+		extract_entropy(&nonblocking_pool, p, nbytes, 0, 0);
 }
-EXPORT_SYMBOL(get_random_bytes);
+EXPORT_SYMBOL(get_random_bytes_arch);
+
 
 /*
  * init_std_data - initialize pool with system data

@@ -56,6 +56,7 @@ extern void add_input_randomness(unsigne
 extern void add_interrupt_randomness(int irq, int irq_flags);
 
 extern void get_random_bytes(void *buf, int nbytes);
+extern void get_random_bytes_arch(void *buf, int nbytes);
 void generate_random_uuid(unsigned char uuid_out[16]);
 
 #ifndef MODULE

@@ -266,6 +266,9 @@
 #include <asm/irq_regs.h>
 #include <asm/io.h>
 
+#define CREATE_TRACE_POINTS
+#include <trace/events/random.h>
+
 /*
  * Configuration information
  */

@@ -478,8 +481,8 @@ static __u32 const twist_table[8] = {
  * it's cheap to do so and helps slightly in the expected case where
  * the entropy is concentrated in the low-order bits.
  */
-static void __mix_pool_bytes(struct entropy_store *r, const void *in,
-			     int nbytes, __u8 out[64])
+static void _mix_pool_bytes(struct entropy_store *r, const void *in,
+			    int nbytes, __u8 out[64])
 {
 	unsigned long i, j, tap1, tap2, tap3, tap4, tap5;
 	int input_rotate;

@@ -531,13 +534,21 @@ static void __mix_pool_bytes(struct entr
 			((__u32 *)out)[j] = r->pool[(i - j) & wordmask];
 }
 
-static void mix_pool_bytes(struct entropy_store *r, const void *in,
+static void __mix_pool_bytes(struct entropy_store *r, const void *in,
 			     int nbytes, __u8 out[64])
 {
+	trace_mix_pool_bytes_nolock(r->name, nbytes, _RET_IP_);
+	_mix_pool_bytes(r, in, nbytes, out);
+}
+
+static void mix_pool_bytes(struct entropy_store *r, const void *in,
+			   int nbytes, __u8 out[64])
+{
 	unsigned long flags;
 
+	trace_mix_pool_bytes(r->name, nbytes, _RET_IP_);
 	spin_lock_irqsave(&r->lock, flags);
-	__mix_pool_bytes(r, in, nbytes, out);
+	_mix_pool_bytes(r, in, nbytes, out);
 	spin_unlock_irqrestore(&r->lock, flags);
 }
 

@@ -585,6 +596,7 @@ static void credit_entropy_bits(struct e
 retry:
 	entropy_count = orig = ACCESS_ONCE(r->entropy_count);
 	entropy_count += nbits;
+
 	if (entropy_count < 0) {
 		DEBUG_ENT("negative entropy/overflow\n");
 		entropy_count = 0;

@@ -599,6 +611,9 @@ retry:
 			r->initialized = 1;
 	}
 
+	trace_credit_entropy_bits(r->name, nbits, entropy_count,
+				  r->entropy_total, _RET_IP_);
+
 	/* should we wake readers? */
 	if (r == &input_pool && entropy_count >= random_read_wakeup_thresh) {
 		wake_up_interruptible(&random_read_wait);

@@ -971,6 +986,7 @@ static ssize_t extract_entropy(struct en
 	ssize_t ret = 0, i;
 	__u8 tmp[EXTRACT_SIZE];
 
+	trace_extract_entropy(r->name, nbytes, r->entropy_count, _RET_IP_);
 	xfer_secondary_pool(r, nbytes);
 	nbytes = account(r, nbytes, min, reserved);
 

@@ -1005,6 +1021,7 @@ static ssize_t extract_entropy_user(stru
 	ssize_t ret = 0, i;
 	__u8 tmp[EXTRACT_SIZE];
 
+	trace_extract_entropy_user(r->name, nbytes, r->entropy_count, _RET_IP_);
 	xfer_secondary_pool(r, nbytes);
 	nbytes = account(r, nbytes, 0, 0);
 

@@ -1062,6 +1079,7 @@ void get_random_bytes_arch(void *buf, in
 {
 	char *p = buf;
 
+	trace_get_random_bytes(nbytes, _RET_IP_);
 	while (nbytes) {
 		unsigned long v;
 		int chunk = min(nbytes, (int)sizeof(unsigned long));

134 lines not on this page · raw message

@@ -24,7 +24,7 @@
 #include <linux/mfd/wm831x/core.h>
 #include <linux/delay.h>
 #include <linux/platform_device.h>
-
+#include <linux/random.h>
 
 /*
  * R16416 (0x4020) - RTC Write Counter

@@ -96,6 +96,26 @@ struct wm831x_rtc {
 	unsigned int alarm_enabled:1;
 };
 
+static void wm831x_rtc_add_randomness(struct wm831x *wm831x)
+{
+	int ret;
+	u16 reg;
+
+	/*
+	 * The write counter contains a pseudo-random number which is
+	 * regenerated every time we set the RTC so it should be a
+	 * useful per-system source of entropy.
+	 */
+	ret = wm831x_reg_read(wm831x, WM831X_RTC_WRITE_COUNTER);
+	if (ret >= 0) {
+		reg = ret;
+		add_device_randomness(&reg, sizeof(reg));
+	} else {
+		dev_warn(wm831x->dev, "Failed to read RTC write counter: %d\n",
+			 ret);
+	}
+}
+
 /*
  * Read current time and date in RTC
  */

@@ -449,6 +469,8 @@ static int wm831x_rtc_probe(struct platf
 			alm_irq, ret);
 	}
 
+	wm831x_rtc_add_randomness(wm831x);
+
 	return 0;
 
 err:

@@ -18,6 +18,7 @@
 #include <linux/bcd.h>
 #include <linux/delay.h>
 #include <linux/mfd/core.h>
+#include <linux/random.h>
 
 #include <linux/mfd/wm831x/core.h>
 #include <linux/mfd/wm831x/otp.h>

@@ -66,6 +67,7 @@ static DEVICE_ATTR(unique_id, 0444, wm83
 
 int wm831x_otp_init(struct wm831x *wm831x)
 {
+	char uuid[WM831X_UNIQUE_ID_LEN];
 	int ret;
 
 	ret = device_create_file(wm831x->dev, &dev_attr_unique_id);

@@ -73,6 +75,12 @@ int wm831x_otp_init(struct wm831x *wm831
 		dev_err(wm831x->dev, "Unique ID attribute not created: %d\n",
 			ret);
 
+	ret = wm831x_unique_id_read(wm831x, uuid);
+	if (ret == 0)
+		add_device_randomness(uuid, sizeof(uuid));
+	else
+		dev_err(wm831x->dev, "Failed to read UUID: %d\n", ret);
+
 	return ret;
 }
 

@@ -23,7 +23,6 @@
 #include <linux/ioport.h>
 #include <linux/kernel_stat.h>
 #include <linux/ptrace.h>
-#include <linux/random.h>	/* for rand_initialize_irq() */
 #include <linux/signal.h>
 #include <linux/smp.h>
 #include <linux/threads.h>

67 lines not on this page · raw message

@@ -936,9 +936,6 @@ static int __devinit ab3100_probe(struct
 
 	err = request_threaded_irq(client->irq, NULL, ab3100_irq_handler,
 				IRQF_ONESHOT, "ab3100-core", ab3100);
-	/* This real unpredictable IRQ is of course sampled for entropy */
-	rand_initialize_irq(client->irq);
-
 	if (err)
 		goto exit_no_irq;
 

@@ -1309,8 +1309,6 @@ static int __init ab3550_probe(struct i2
 
 	err = request_threaded_irq(client->irq, NULL, ab3550_irq_handler,
 		IRQF_ONESHOT, "ab3550-core", ab);
-	/* This real unpredictable IRQ is of course sampled for entropy */
-	rand_initialize_irq(client->irq);
 
 	if (err)
 		goto exit_no_irq;

@@ -38,7 +38,6 @@ struct timer_rand_state;
  */
 struct irq_desc {
 	struct irq_data		irq_data;
-	struct timer_rand_state *timer_rand_state;
 	unsigned int __percpu	*kstat_irqs;
 	irq_flow_handler_t	handle_irq;
 #ifdef CONFIG_IRQ_PREFLOW_FASTEOI

@@ -48,8 +48,6 @@ struct rnd_state {
 
 #ifdef __KERNEL__
 
-extern void rand_initialize_irq(int irq);
-
 extern void add_device_randomness(const void *, unsigned int);
 extern void add_input_randomness(unsigned int type, unsigned int code,
 				 unsigned int value);

@@ -886,22 +886,6 @@ __setup_irq(unsigned int irq, struct irq
 
 	if (desc->irq_data.chip == &no_irq_chip)
 		return -ENOSYS;
-	/*
-	 * Some drivers like serial.c use request_irq() heavily,
-	 * so we have to be careful not to interfere with a
-	 * running system.
-	 */
-	if (new->flags & IRQF_SAMPLE_RANDOM) {
-		/*
-		 * This function might sleep, we want to call it first,
-		 * outside of the atomic block.
-		 * Yes, this might clear the entropy pool if the wrong
-		 * driver is attempted to be loaded, without actually
-		 * installing a new handler, but is this really a problem,
-		 * only the sysadmin is able to do this.
-		 */
-		rand_initialize_irq(irq);
-	}
 
 	/*
 	 * Check whether the interrupt nests into another interrupt

@@ -1325,7 +1309,6 @@ EXPORT_SYMBOL(free_irq);
  *	Flags:
  *
  *	IRQF_SHARED		Interrupt is shared
- *	IRQF_SAMPLE_RANDOM	The interrupt can be used for entropy
  *	IRQF_TRIGGER_*		Specify active edge(s) or level
  *
  */

@@ -1087,6 +1087,16 @@ static void init_std_data(struct entropy
 	mix_pool_bytes(r, utsname(), sizeof(*(utsname())), NULL);
 }
 
+/*
+ * Note that setup_arch() may call add_device_randomness()
+ * long before we get here. This allows seeding of the pools
+ * with some platform dependent data very early in the boot
+ * process. But it limits our options here. We must use
+ * statically allocated structures that already have all
+ * initializations complete at compile time. We should also
+ * take care not to overwrite the precious per platform data
+ * we were given.
+ */
 static int rand_initialize(void)
 {
 	init_std_data(&input_pool);

@@ -6,6 +6,7 @@
 #include <linux/dmi.h>
 #include <linux/efi.h>
 #include <linux/bootmem.h>
+#include <linux/random.h>
 #include <asm/dmi.h>
 
 /*

@@ -111,6 +112,8 @@ static int __init dmi_walk_early(void (*
 
 	dmi_table(buf, dmi_len, dmi_num, decode, NULL);
 
+	add_device_randomness(buf, dmi_len);
+
 	dmi_iounmap(buf, dmi_len);
 	return 0;
 }

@@ -277,6 +277,8 @@
 #define SEC_XFER_SIZE 512
 #define EXTRACT_SIZE 10
 
+#define LONGS(x) (((x) + sizeof(unsigned long) - 1)/sizeof(unsigned long))
+
 /*
  * The minimum number of bits of entropy before we wake up a read on
  * /dev/random.  Should be enough to do a significant reseed.

@@ -813,11 +815,7 @@ static ssize_t extract_entropy(struct en
  */
 static void xfer_secondary_pool(struct entropy_store *r, size_t nbytes)
 {
-	union {
-		__u32	tmp[OUTPUT_POOL_WORDS];
-		long	hwrand[4];
-	} u;
-	int	i;
+	__u32	tmp[OUTPUT_POOL_WORDS];
 
 	if (r->pull && r->entropy_count < nbytes * 8 &&
 	    r->entropy_count < r->poolinfo->POOLBITS) {

@@ -828,23 +826,17 @@ static void xfer_secondary_pool(struct e
 		/* pull at least as many as BYTES as wakeup BITS */
 		bytes = max_t(int, bytes, random_read_wakeup_thresh / 8);
 		/* but never more than the buffer size */
-		bytes = min_t(int, bytes, sizeof(u.tmp));
+		bytes = min_t(int, bytes, sizeof(tmp));
 
 		DEBUG_ENT("going to reseed %s with %d bits "
 			  "(%d of %d requested)\n",
 			  r->name, bytes * 8, nbytes * 8, r->entropy_count);
 
-		bytes = extract_entropy(r->pull, u.tmp, bytes,
+		bytes = extract_entropy(r->pull, tmp, bytes,
 					random_read_wakeup_thresh / 8, rsvd);
-		mix_pool_bytes(r, u.tmp, bytes, NULL);
+		mix_pool_bytes(r, tmp, bytes, NULL);
 		credit_entropy_bits(r, bytes*8);
 	}
-	kmemcheck_mark_initialized(&u.hwrand, sizeof(u.hwrand));
-	for (i = 0; i < 4; i++)
-		if (arch_get_random_long(&u.hwrand[i]))
-			break;
-	if (i)
-		mix_pool_bytes(r, &u.hwrand, sizeof(u.hwrand), 0);
 }
 
 /*

@@ -901,15 +893,19 @@ static size_t account(struct entropy_sto
 static void extract_buf(struct entropy_store *r, __u8 *out)
 {
 	int i;
-	__u32 hash[5], workspace[SHA_WORKSPACE_WORDS];
+	union {
+		__u32 w[5];
+		unsigned long l[LONGS(EXTRACT_SIZE)];
+	} hash;
+	__u32 workspace[SHA_WORKSPACE_WORDS];
 	__u8 extract[64];
 	unsigned long flags;
 
 	/* Generate a hash across the pool, 16 words (512 bits) at a time */
-	sha_init(hash);
+	sha_init(hash.w);
 	spin_lock_irqsave(&r->lock, flags);
 	for (i = 0; i < r->poolinfo->poolwords; i += 16)
-		sha_transform(hash, (__u8 *)(r->pool + i), workspace);
+		sha_transform(hash.w, (__u8 *)(r->pool + i), workspace);
 
 	/*
 	 * We mix the hash back into the pool to prevent backtracking

@@ -920,14 +916,14 @@ static void extract_buf(struct entropy_s
 	 * brute-forcing the feedback as hard as brute-forcing the
 	 * hash.
 	 */
-	__mix_pool_bytes(r, hash, sizeof(hash), extract);
+	__mix_pool_bytes(r, hash.w, sizeof(hash.w), extract);
 	spin_unlock_irqrestore(&r->lock, flags);
 
 	/*
 	 * To avoid duplicates, we atomically extract a portion of the
 	 * pool while mixing, and hash one final time.
 	 */
-	sha_transform(hash, extract, workspace);
+	sha_transform(hash.w, extract, workspace);
 	memset(extract, 0, sizeof(extract));
 	memset(workspace, 0, sizeof(workspace));
 

@@ -936,11 +932,23 @@ static void extract_buf(struct entropy_s
 	 * pattern, we fold it in half. Thus, we always feed back
 	 * twice as much data as we output.
 	 */
-	hash[0] ^= hash[3];
-	hash[1] ^= hash[4];
-	hash[2] ^= rol32(hash[2], 16);
-	memcpy(out, hash, EXTRACT_SIZE);
-	memset(hash, 0, sizeof(hash));
+	hash.w[0] ^= hash.w[3];
+	hash.w[1] ^= hash.w[4];
+	hash.w[2] ^= rol32(hash.w[2], 16);
+
+	/*
+	 * If we have a architectural hardware random number
+	 * generator, mix that in, too.
+	 */
+	for (i = 0; i < LONGS(EXTRACT_SIZE); i++) {
+		unsigned long v;
+		if (!arch_get_random_long(&v))
+			break;
+		hash.l[i] ^= v;
+	}
+
+	memcpy(out, &hash, EXTRACT_SIZE);
+	memset(&hash, 0, sizeof(hash));
 }
 
 static ssize_t extract_entropy(struct entropy_store *r, void *buf,

@@ -298,12 +298,11 @@ static ssize_t reload_store(struct sys_d
 {
 	unsigned long val;
 	int cpu = dev->id;
-	int ret = 0;
-	char *end;
+	ssize_t ret = 0;
 
-	val = simple_strtoul(buf, &end, 0);
-	if (end == buf)
-		return -EINVAL;
+	ret = kstrtoul(buf, 0, &val);
+	if (ret)
+		return ret;
 
 	if (val == 1) {
 		get_online_cpus();

@@ -297,19 +297,31 @@ static ssize_t reload_store(struct sys_d
 			    const char *buf, size_t size)
 {
 	unsigned long val;
-	int cpu = dev->id;
-	ssize_t ret = 0;
+	int cpu;
+	ssize_t ret = 0, tmp_ret;
+
+	/* allow reload only from the BSP */
+	if (boot_cpu_data.cpu_index != dev->id)
+		return -EINVAL;
 
 	ret = kstrtoul(buf, 0, &val);
 	if (ret)
 		return ret;
 
-	if (val == 1) {
-		get_online_cpus();
-		if (cpu_online(cpu))
-			ret = reload_for_cpu(cpu);
-		put_online_cpus();
+	if (val != 1)
+		return size;
+
+	get_online_cpus();
+	for_each_online_cpu(cpu) {
+		tmp_ret = reload_for_cpu(cpu);
+		if (tmp_ret != 0)
+			pr_warn("Error reloading microcode on CPU %d\n", cpu);
+
+		/* save retval of the first encountered reload error */
+		if (!ret)
+			ret = tmp_ret;
 	}
+	put_online_cpus();
 
 	if (!ret)
 		ret = size;

index bb3ee36..f7c89e2 100644
@@ -99,7 +99,6 @@ struct cpuinfo_x86 {
 	u16			apicid;
 	u16			initial_apicid;
 	u16			x86_clflush_size;
-#ifdef CONFIG_SMP
 	/* number of cores as seen by the OS: */
 	u16			booted_cores;
 	/* Physical processor id: */

@@ -110,7 +109,6 @@ struct cpuinfo_x86 {
 	u8			compute_unit_id;
 	/* Index into per_cpu list: */
 	u16			cpu_index;
-#endif
 	u32			microcode;
 } __attribute__((__aligned__(SMP_CACHE_BYTES)));
 

index bae1efe..be16854 100644
@@ -154,16 +154,14 @@ int amd_get_subcaches(int cpu)
 {
 	struct pci_dev *link = node_to_amd_nb(amd_get_nb_id(cpu))->link;
 	unsigned int mask;
-	int cuid = 0;
+	int cuid;
 
 	if (!amd_nb_has_feature(AMD_NB_L3_PARTITIONING))
 		return 0;
 
 	pci_read_config_dword(link, 0x1d4, &mask);
 
-#ifdef CONFIG_SMP
 	cuid = cpu_data(cpu).compute_unit_id;
-#endif
 	return (mask >> (4 * cuid)) & 0xf;
 }
 

@@ -172,7 +170,7 @@ int amd_set_subcaches(int cpu, int mask)
 	static unsigned int reset, ban;
 	struct amd_northbridge *nb = node_to_amd_nb(amd_get_nb_id(cpu));
 	unsigned int reg;
-	int cuid = 0;
+	int cuid;
 
 	if (!amd_nb_has_feature(AMD_NB_L3_PARTITIONING) || mask > 0xf)
 		return -EINVAL;

@@ -190,9 +188,7 @@ int amd_set_subcaches(int cpu, int mask)
 		pci_write_config_dword(nb->misc, 0x1b8, reg & ~0x180000);
 	}
 
-#ifdef CONFIG_SMP
 	cuid = cpu_data(cpu).compute_unit_id;
-#endif
 	mask <<= 4 * cuid;
 	mask |= (0xf ^ (1 << cuid)) << 26;
 

index 3524e1f..ff8557e 100644
@@ -148,7 +148,6 @@ static void __cpuinit init_amd_k6(struct cpuinfo_x86 *c)
 
 static void __cpuinit amd_k7_smp_check(struct cpuinfo_x86 *c)
 {
-#ifdef CONFIG_SMP
 	/* calling is from identify_secondary_cpu() ? */
 	if (!c->cpu_index)
 		return;

@@ -192,7 +191,6 @@ static void __cpuinit amd_k7_smp_check(struct cpuinfo_x86 *c)
 
 valid_k7:
 	;
-#endif
 }
 
 static void __cpuinit init_amd_k7(struct cpuinfo_x86 *c)

index aa003b1..ca93cc7 100644
@@ -676,9 +676,7 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
 	if (this_cpu->c_early_init)
 		this_cpu->c_early_init(c);
 
-#ifdef CONFIG_SMP
 	c->cpu_index = 0;
-#endif
 	filter_cpuid_features(c, false);
 
 	setup_smep(c);

@@ -764,10 +762,7 @@ static void __cpuinit generic_identify(struct cpuinfo_x86 *c)
 		c->apicid = c->initial_apicid;
 # endif
 #endif
-
-#ifdef CONFIG_X86_HT
 		c->phys_proc_id = c->initial_apicid;
-#endif
 	}
 
 	setup_smep(c);

index 5231312..3e6ff6c 100644
@@ -181,7 +181,6 @@ static void __cpuinit trap_init_f00f_bug(void)
 
 static void __cpuinit intel_smp_check(struct cpuinfo_x86 *c)
 {
-#ifdef CONFIG_SMP
 	/* calling is from identify_secondary_cpu() ? */
 	if (!c->cpu_index)
 		return;

@@ -198,7 +197,6 @@ static void __cpuinit intel_smp_check(struct cpuinfo_x86 *c)
 		WARN_ONCE(1, "WARNING: SMP operation may be unreliable"
 				    "with B stepping processors.\n");
 	}
-#endif
 }
 
 static void __cpuinit intel_workarounds(struct cpuinfo_x86 *c)

index b0f1271..3b67877 100644
@@ -119,9 +119,7 @@ void mce_setup(struct mce *m)
 	m->time = get_seconds();
 	m->cpuvendor = boot_cpu_data.x86_vendor;
 	m->cpuid = cpuid_eax(1);
-#ifdef CONFIG_SMP
 	m->socketid = cpu_data(m->extcpu).phys_proc_id;
-#endif
 	m->apicid = cpu_data(m->extcpu).initial_apicid;
 	rdmsrl(MSR_IA32_MCG_CAP, m->mcgcap);
 }

index 445a61c..d4444be 100644
@@ -65,11 +65,9 @@ struct threshold_bank {
 };
 static DEFINE_PER_CPU(struct threshold_bank * [NR_BANKS], threshold_banks);
 
-#ifdef CONFIG_SMP
 static unsigned char shared_bank[NR_BANKS] = {
 	0, 0, 0, 0, 1
 };
-#endif
 
 static DEFINE_PER_CPU(unsigned char, bank_map);	/* see which banks are on */
 

@@ -227,10 +225,9 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c)
 
 			if (!block)
 				per_cpu(bank_map, cpu) |= (1 << bank);
-#ifdef CONFIG_SMP
+
 			if (shared_bank[bank] && c->cpu_core_id)
 				break;
-#endif
 
 			memset(&b, 0, sizeof(b));
 			b.cpu			= cpu;

index 14b2314..8022c66 100644
@@ -64,12 +64,10 @@ static void show_cpuinfo_misc(struct seq_file *m, struct cpuinfo_x86 *c)
 static int show_cpuinfo(struct seq_file *m, void *v)
 {
 	struct cpuinfo_x86 *c = v;
-	unsigned int cpu = 0;
+	unsigned int cpu;
 	int i;
 
-#ifdef CONFIG_SMP
 	cpu = c->cpu_index;
-#endif
 	seq_printf(m, "processor\t: %u\n"
 		   "vendor_id\t: %s\n"
 		   "cpu family\t: %d\n"

index 18a1293..0db57b5 100644
@@ -1609,11 +1609,9 @@ static int sbridge_mce_check_error(struct notifier_block *nb, unsigned long val,
 		mce->cpuvendor, mce->cpuid, mce->time,
 		mce->socketid, mce->apicid);
 
-#ifdef CONFIG_SMP
 	/* Only handle if it is the right mc controller */
 	if (cpu_data(mce->cpu).phys_proc_id != pvt->sbridge_dev->mc)
 		return NOTIFY_DONE;
-#endif
 
 	smp_rmb();
 	if ((pvt->mce_out + 1) % MCE_LOG_LEN == pvt->mce_in) {

index 0790c98..19b4412 100644
@@ -57,16 +57,15 @@ MODULE_PARM_DESC(tjmax, "TjMax value in degrees Celsius");
 #define TOTAL_ATTRS		(MAX_CORE_ATTRS + 1)
 #define MAX_CORE_DATA		(NUM_REAL_CORES + BASE_SYSFS_ATTR_NO)
 
-#ifdef CONFIG_SMP
 #define TO_PHYS_ID(cpu)		cpu_data(cpu).phys_proc_id
 #define TO_CORE_ID(cpu)		cpu_data(cpu).cpu_core_id
+#define TO_ATTR_NO(cpu)		(TO_CORE_ID(cpu) + BASE_SYSFS_ATTR_NO)
+
+#ifdef CONFIG_SMP
 #define for_each_sibling(i, cpu)	for_each_cpu(i, cpu_sibling_mask(cpu))
 #else
-#define TO_PHYS_ID(cpu)		(cpu)
-#define TO_CORE_ID(cpu)		(cpu)
 #define for_each_sibling(i, cpu)	for (i = 0; false; )
 #endif
-#define TO_ATTR_NO(cpu)		(TO_CORE_ID(cpu) + BASE_SYSFS_ATTR_NO)
 
 /*
  * Per-Core Temperature Data

@@ -2301,6 +2301,22 @@ void unmap_hugepage_range(struct vm_area
 {
 	mutex_lock(&vma->vm_file->f_mapping->i_mmap_mutex);
 	__unmap_hugepage_range(vma, start, end, ref_page);
+	/*
+	 * Clear this flag so that x86's huge_pmd_share page_table_shareable
+	 * test will fail on a vma being torn down, and not grab a page table
+	 * on its way out.  We're lucky that the flag has such an appropriate
+	 * name, and can in fact be safely cleared here. We could clear it
+	 * before the __unmap_hugepage_range above, but all that's necessary
+	 * is to clear it before releasing the i_mmap_mutex below.
+	 *
+	 * This works because in the contexts this is called, the VMA is
+	 * going to be destroyed. It is not vunerable to madvise(DONTNEED)
+	 * because madvise is not supported on hugetlbfs. The same applies
+	 * for direct IO. unmap_hugepage_range() is only being called just
+	 * before free_pgtables() so clearing VM_MAYSHARE will not cause
+	 * surprises later.
+	 */
+	vma->vm_flags &= ~VM_MAYSHARE;
 	mutex_unlock(&vma->vm_file->f_mapping->i_mmap_mutex);
 }
 

@@ -2853,9 +2869,14 @@ void hugetlb_change_protection(struct vm
 		}
 	}
 	spin_unlock(&mm->page_table_lock);
-	mutex_unlock(&vma->vm_file->f_mapping->i_mmap_mutex);
-
+	/*
+	 * Must flush TLB before releasing i_mmap_mutex: x86's huge_pmd_unshare
+	 * may have cleared our pud entry and done put_page on the page table:
+	 * once we release i_mmap_mutex, another task can do the final put_page
+	 * and that page table be reused and filled with junk.
+	 */
 	flush_tlb_range(vma, start, end);
+	mutex_unlock(&vma->vm_file->f_mapping->i_mmap_mutex);
 }
 
 int hugetlb_reserve_pages(struct inode *inode,

@@ -202,7 +202,7 @@ static void pcap_isr_work(struct work_st
 		}
 		local_irq_enable();
 		ezx_pcap_write(pcap, PCAP_REG_MSR, pcap->msr);
-	} while (gpio_get_value(irq_to_gpio(pcap->spi->irq)));
+	} while (gpio_get_value(pdata->gpio));
 }
 
 static void pcap_irq_handler(unsigned int irq, struct irq_desc *desc)

@@ -16,6 +16,7 @@ struct pcap_subdev {
 struct pcap_platform_data {
 	unsigned int irq_base;
 	unsigned int config;
+	int gpio;
 	void (*init) (void *);	/* board specific init */
 	int num_subdevs;
 	struct pcap_subdev *subdevs;

@@ -959,6 +959,11 @@ static int cfg80211_netdev_notifier_call
 		 */
 		synchronize_rcu();
 		INIT_LIST_HEAD(&wdev->list);
+		/*
+		 * Ensure that all events have been processed and
+		 * freed.
+		 */
+		cfg80211_process_wdev_events(wdev);
 		break;
 	case NETDEV_PRE_UP:
 		if (!(wdev->wiphy->interface_modes & BIT(wdev->iftype)))

@@ -426,6 +426,7 @@ int cfg80211_change_iface(struct cfg8021
 			  struct net_device *dev, enum nl80211_iftype ntype,
 			  u32 *flags, struct vif_params *params);
 void cfg80211_process_rdev_events(struct cfg80211_registered_device *rdev);
+void cfg80211_process_wdev_events(struct wireless_dev *wdev);
 
 int cfg80211_can_change_interface(struct cfg80211_registered_device *rdev,
 				  struct wireless_dev *wdev,

@@ -719,7 +719,7 @@ void cfg80211_upload_connect_keys(struct
 	wdev->connect_keys = NULL;
 }
 
-static void cfg80211_process_wdev_events(struct wireless_dev *wdev)
+void cfg80211_process_wdev_events(struct wireless_dev *wdev)
 {
 	struct cfg80211_event *ev;
 	unsigned long flags;

@@ -975,6 +975,9 @@ int cfg80211_can_change_interface(struct
 	}
 	mutex_unlock(&rdev->devlist_mtx);
 
+	if (total == 1)
+		return 0;
+
 	for (i = 0; i < rdev->wiphy.n_iface_combinations; i++) {
 		const struct ieee80211_iface_combination *c;
 		struct ieee80211_iface_limit *limits;

@@ -1602,10 +1602,8 @@ static s32 e1000_check_for_serdes_link_8
 			 * auto-negotiation in the TXCW register and disable
 			 * forced link in the Device Control register in an
 			 * attempt to auto-negotiate with our link partner.
-			 * If the partner code word is null, stop forcing
-			 * and restart auto negotiation.
 			 */
-			if ((rxcw & E1000_RXCW_C) || !(rxcw & E1000_RXCW_CW))  {
+			if (rxcw & E1000_RXCW_C) {
 				/* Enable autoneg, and unforce link up */
 				ew32(TXCW, mac->txcw);
 				ew32(CTRL, (ctrl & ~E1000_CTRL_SLU));