Merge branch 'android-4.4@e76c0fa' into branch 'msm-4.4'

* refs/heads/tmp-e76c0fa
  Linux 4.4.72
  arm64: ensure extension of smp_store_release value
  arm64: armv8_deprecated: ensure extension of addr
  usercopy: Adjust tests to deal with SMAP/PAN
  RDMA/qib,hfi1: Fix MR reference count leak on write with immediate
  arm64: entry: improve data abort handling of tagged pointers
  arm64: hw_breakpoint: fix watchpoint matching for tagged pointers
  Make __xfs_xattr_put_listen preperly report errors.
  NFSv4: Don't perform cached access checks before we've OPENed the file
  NFS: Ensure we revalidate attributes before using execute_ok()
  mm: consider memblock reservations for deferred memory initialization sizing
  net: better skb->sender_cpu and skb->napi_id cohabitation
  serial: sh-sci: Fix panic when serial console and DMA are enabled
  tty: Drop krefs for interrupted tty lock
  drivers: char: mem: Fix wraparound check to allow mappings up to the end
  ASoC: Fix use-after-free at card unregistration
  ALSA: timer: Fix missing queue indices reset at SNDRV_TIMER_IOCTL_SELECT
  ALSA: timer: Fix race between read and ioctl
  drm/nouveau/tmr: fully separate alarm execution/pending lists
  drm/vmwgfx: Make sure backup_handle is always valid
  drm/vmwgfx: limit the number of mip levels in vmw_gb_surface_define_ioctl()
  drm/vmwgfx: Handle vmalloc() failure in vmw_local_fifo_reserve()
  perf/core: Drop kernel samples even though :u is specified
  powerpc/hotplug-mem: Fix missing endian conversion of aa_index
  powerpc/numa: Fix percpu allocations to be NUMA aware
  powerpc/eeh: Avoid use after free in eeh_handle_special_event()
  scsi: qla2xxx: don't disable a not previously enabled PCI device
  KVM: arm/arm64: Handle possible NULL stage2 pud when ageing pages
  btrfs: fix memory leak in update_space_info failure path
  btrfs: use correct types for page indices in btrfs_page_exists_in_range
  cxl: Fix error path on bad ioctl
  ufs_getfrag_block(): we only grab ->truncate_mutex on block creation path
  ufs_extend_tail(): fix the braino in calling conventions of ufs_new_fragments()
  ufs: set correct ->s_maxsize
  ufs: restore maintaining ->i_blocks
  fix ufs_isblockset()
  ufs: restore proper tail allocation
  fs: add i_blocksize()
  cpuset: consider dying css as offline
  Input: elantech - add Fujitsu Lifebook E546/E557 to force crc_enabled
  drm/msm: Expose our reservation object when exporting a dmabuf.
  target: Re-add check to reject control WRITEs with overflow data
  cpufreq: cpufreq_register_driver() should return -ENODEV if init fails
  stackprotector: Increase the per-task stack canary's random range from 32 bits to 64 bits on 64-bit platforms
  random: properly align get_random_int_hash
  drivers: char: random: add get_random_long()
  iio: proximity: as3935: fix AS3935_INT mask
  iio: light: ltr501 Fix interchanged als/ps register field
  staging/lustre/lov: remove set_fs() call from lov_getstripe()
  usb: chipidea: debug: check before accessing ci_role
  usb: chipidea: udc: fix NULL pointer dereference if udc_start failed
  usb: gadget: f_mass_storage: Serialize wake and sleep execution
  ext4: fix fdatasync(2) after extent manipulation operations
  ext4: keep existing extra fields when inode expands
  ext4: fix SEEK_HOLE
  xen-netfront: cast grant table reference first to type int
  xen-netfront: do not cast grant table reference to signed short
  xen/privcmd: Support correctly 64KB page granularity when mapping memory
  dmaengine: ep93xx: Always start from BASE0
  dmaengine: usb-dmac: Fix DMAOR AE bit definition
  KVM: async_pf: avoid async pf injection when in guest mode
  arm: KVM: Allow unaligned accesses at HYP
  KVM: cpuid: Fix read/write out-of-bounds vulnerability in cpuid emulation
  kvm: async_pf: fix rcu_irq_enter() with irqs enabled
  nfsd: Fix up the "supattr_exclcreat" attributes
  nfsd4: fix null dereference on replay
  drm/amdgpu/ci: disable mclk switching for high refresh rates (v2)
  crypto: gcm - wait for crypto op not signal safe
  KEYS: fix freeing uninitialized memory in key_update()
  KEYS: fix dereferencing NULL payload with nonzero length
  ptrace: Properly initialize ptracer_cred on fork
  serial: ifx6x60: fix use-after-free on module unload
  arch/sparc: support NR_CPUS = 4096
  sparc64: delete old wrap code
  sparc64: new context wrap
  sparc64: add per-cpu mm of secondary contexts
  sparc64: redefine first version
  sparc64: combine activate_mm and switch_mm
  sparc64: reset mm cpumask after wrap
  sparc: Machine description indices can vary
  sparc64: mm: fix copy_tsb to correctly copy huge page TSBs
  net: bridge: start hello timer only if device is up
  net: ethoc: enable NAPI before poll may be scheduled
  net: ping: do not abuse udp_poll()
  ipv6: Fix leak in ipv6_gso_segment().
  vxlan: fix use-after-free on deletion
  tcp: disallow cwnd undo when switching congestion control
  cxgb4: avoid enabling napi twice to the same queue
  ipv6: xfrm: Handle errors reported by xfrm6_find_1stfragopt()
  bnx2x: Fix Multi-Cos
  ANDROID: uid_sys_stats: check previous uid_entry before call find_or_register_uid
  ANDROID: sdcardfs: d_splice_alias can return error values

Change-Id: I829ebf1a9271dcf0462c537e7bfcbcfde322f336
Signed-off-by: Blagovest Kolenichev <bkolenichev@codeaurora.org>

14 files changed, 156 insertions, 112 deletions

diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index 3736be630113..894bcaed002e 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -183,9 +183,9 @@ config NR_CPUS
 	int "Maximum number of CPUs"
 	depends on SMP
 	range 2 32 if SPARC32
-	range 2 1024 if SPARC64
+	range 2 4096 if SPARC64
 	default 32 if SPARC32
-	default 64 if SPARC64
+	default 4096 if SPARC64
 
 source kernel/Kconfig.hz
 
diff --git a/arch/sparc/include/asm/mmu_64.h b/arch/sparc/include/asm/mmu_64.h
index f7de0dbc38af..83b36a5371ff 100644
--- a/arch/sparc/include/asm/mmu_64.h
+++ b/arch/sparc/include/asm/mmu_64.h
@@ -52,7 +52,7 @@
 #define CTX_NR_MASK		TAG_CONTEXT_BITS
 #define CTX_HW_MASK		(CTX_NR_MASK | CTX_PGSZ_MASK)
 
-#define CTX_FIRST_VERSION	((_AC(1,UL) << CTX_VERSION_SHIFT) + _AC(1,UL))
+#define CTX_FIRST_VERSION	BIT(CTX_VERSION_SHIFT)
 #define CTX_VALID(__ctx)	\
 	 (!(((__ctx.sparc64_ctx_val) ^ tlb_context_cache) & CTX_VERSION_MASK))
 #define CTX_HWBITS(__ctx)	((__ctx.sparc64_ctx_val) & CTX_HW_MASK)
diff --git a/arch/sparc/include/asm/mmu_context_64.h b/arch/sparc/include/asm/mmu_context_64.h
index b84be675e507..349dd23e2876 100644
--- a/arch/sparc/include/asm/mmu_context_64.h
+++ b/arch/sparc/include/asm/mmu_context_64.h
@@ -17,13 +17,8 @@ extern spinlock_t ctx_alloc_lock;
 extern unsigned long tlb_context_cache;
 extern unsigned long mmu_context_bmap[];
 
+DECLARE_PER_CPU(struct mm_struct *, per_cpu_secondary_mm);
 void get_new_mmu_context(struct mm_struct *mm);
-#ifdef CONFIG_SMP
-void smp_new_mmu_context_version(void);
-#else
-#define smp_new_mmu_context_version() do { } while (0)
-#endif
-
 int init_new_context(struct task_struct *tsk, struct mm_struct *mm);
 void destroy_context(struct mm_struct *mm);
 
@@ -74,8 +69,9 @@ void __flush_tlb_mm(unsigned long, unsigned long);
 static inline void switch_mm(struct mm_struct *old_mm, struct mm_struct *mm, struct task_struct *tsk)
 {
 	unsigned long ctx_valid, flags;
-	int cpu;
+	int cpu = smp_processor_id();
 
+	per_cpu(per_cpu_secondary_mm, cpu) = mm;
 	if (unlikely(mm == &init_mm))
 		return;
 
@@ -121,7 +117,6 @@ static inline void switch_mm(struct mm_struct *old_mm, struct mm_struct *mm, str
 	 * for the first time, we must flush that context out of the
 	 * local TLB.
 	 */
-	cpu = smp_processor_id();
 	if (!ctx_valid || !cpumask_test_cpu(cpu, mm_cpumask(mm))) {
 		cpumask_set_cpu(cpu, mm_cpumask(mm));
 		__flush_tlb_mm(CTX_HWBITS(mm->context),
@@ -131,26 +126,7 @@ static inline void switch_mm(struct mm_struct *old_mm, struct mm_struct *mm, str
 }
 
 #define deactivate_mm(tsk,mm)	do { } while (0)
-
-/* Activate a new MM instance for the current task. */
-static inline void activate_mm(struct mm_struct *active_mm, struct mm_struct *mm)
-{
-	unsigned long flags;
-	int cpu;
-
-	spin_lock_irqsave(&mm->context.lock, flags);
-	if (!CTX_VALID(mm->context))
-		get_new_mmu_context(mm);
-	cpu = smp_processor_id();
-	if (!cpumask_test_cpu(cpu, mm_cpumask(mm)))
-		cpumask_set_cpu(cpu, mm_cpumask(mm));
-
-	load_secondary_context(mm);
-	__flush_tlb_mm(CTX_HWBITS(mm->context), SECONDARY_CONTEXT);
-	tsb_context_switch(mm);
-	spin_unlock_irqrestore(&mm->context.lock, flags);
-}
-
+#define activate_mm(active_mm, mm) switch_mm(active_mm, mm, NULL)
 #endif /* !(__ASSEMBLY__) */
 
 #endif /* !(__SPARC64_MMU_CONTEXT_H) */
diff --git a/arch/sparc/include/asm/pil.h b/arch/sparc/include/asm/pil.h
index 266937030546..522b43db2ed3 100644
--- a/arch/sparc/include/asm/pil.h
+++ b/arch/sparc/include/asm/pil.h
@@ -20,7 +20,6 @@
 #define PIL_SMP_CALL_FUNC	1
 #define PIL_SMP_RECEIVE_SIGNAL	2
 #define PIL_SMP_CAPTURE		3
-#define PIL_SMP_CTX_NEW_VERSION	4
 #define PIL_DEVICE_IRQ		5
 #define PIL_SMP_CALL_FUNC_SNGL	6
 #define PIL_DEFERRED_PCR_WORK	7
diff --git a/arch/sparc/include/asm/vio.h b/arch/sparc/include/asm/vio.h
index 8174f6cdbbbb..9dca7a892978 100644
--- a/arch/sparc/include/asm/vio.h
+++ b/arch/sparc/include/asm/vio.h
@@ -327,6 +327,7 @@ struct vio_dev {
 	int			compat_len;
 
 	u64			dev_no;
+	u64			id;
 
 	unsigned long		channel_id;
 
diff --git a/arch/sparc/kernel/irq_64.c b/arch/sparc/kernel/irq_64.c
index e22416ce56ea..bfbde8c4ffb2 100644
--- a/arch/sparc/kernel/irq_64.c
+++ b/arch/sparc/kernel/irq_64.c
@@ -1034,17 +1034,26 @@ static void __init init_cpu_send_mondo_info(struct trap_per_cpu *tb)
 {
 #ifdef CONFIG_SMP
 	unsigned long page;
+	void *mondo, *p;
 
-	BUILD_BUG_ON((NR_CPUS * sizeof(u16)) > (PAGE_SIZE - 64));
+	BUILD_BUG_ON((NR_CPUS * sizeof(u16)) > PAGE_SIZE);
+
+	/* Make sure mondo block is 64byte aligned */
+	p = kzalloc(127, GFP_KERNEL);
+	if (!p) {
+		prom_printf("SUN4V: Error, cannot allocate mondo block.\n");
+		prom_halt();
+	}
+	mondo = (void *)(((unsigned long)p + 63) & ~0x3f);
+	tb->cpu_mondo_block_pa = __pa(mondo);
 
 	page = get_zeroed_page(GFP_KERNEL);
 	if (!page) {
-		prom_printf("SUN4V: Error, cannot allocate cpu mondo page.\n");
+		prom_printf("SUN4V: Error, cannot allocate cpu list page.\n");
 		prom_halt();
 	}
 
-	tb->cpu_mondo_block_pa = __pa(page);
-	tb->cpu_list_pa = __pa(page + 64);
+	tb->cpu_list_pa = __pa(page);
 #endif
 }
 
diff --git a/arch/sparc/kernel/kernel.h b/arch/sparc/kernel/kernel.h
index e7f652be9e61..44f32dd4477f 100644
--- a/arch/sparc/kernel/kernel.h
+++ b/arch/sparc/kernel/kernel.h
@@ -37,7 +37,6 @@ void handle_stdfmna(struct pt_regs *regs, unsigned long sfar, unsigned long sfsr
 /* smp_64.c */
 void __irq_entry smp_call_function_client(int irq, struct pt_regs *regs);
 void __irq_entry smp_call_function_single_client(int irq, struct pt_regs *regs);
-void __irq_entry smp_new_mmu_context_version_client(int irq, struct pt_regs *regs);
 void __irq_entry smp_penguin_jailcell(int irq, struct pt_regs *regs);
 void __irq_entry smp_receive_signal_client(int irq, struct pt_regs *regs);
 
diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c
index 19cd08d18672..95a9fa0d2195 100644
--- a/arch/sparc/kernel/smp_64.c
+++ b/arch/sparc/kernel/smp_64.c
@@ -959,37 +959,6 @@ void flush_dcache_page_all(struct mm_struct *mm, struct page *page)
 	preempt_enable();
 }
 
-void __irq_entry smp_new_mmu_context_version_client(int irq, struct pt_regs *regs)
-{
-	struct mm_struct *mm;
-	unsigned long flags;
-
-	clear_softint(1 << irq);
-
-	/* See if we need to allocate a new TLB context because
-	 * the version of the one we are using is now out of date.
-	 */
-	mm = current->active_mm;
-	if (unlikely(!mm || (mm == &init_mm)))
-		return;
-
-	spin_lock_irqsave(&mm->context.lock, flags);
-
-	if (unlikely(!CTX_VALID(mm->context)))
-		get_new_mmu_context(mm);
-
-	spin_unlock_irqrestore(&mm->context.lock, flags);
-
-	load_secondary_context(mm);
-	__flush_tlb_mm(CTX_HWBITS(mm->context),
-		       SECONDARY_CONTEXT);
-}
-
-void smp_new_mmu_context_version(void)
-{
-	smp_cross_call(&xcall_new_mmu_context_version, 0, 0, 0);
-}
-
 #ifdef CONFIG_KGDB
 void kgdb_roundup_cpus(unsigned long flags)
 {
diff --git a/arch/sparc/kernel/tsb.S b/arch/sparc/kernel/tsb.S
index d568c8207af7..395ec1800530 100644
--- a/arch/sparc/kernel/tsb.S
+++ b/arch/sparc/kernel/tsb.S
@@ -470,13 +470,16 @@ __tsb_context_switch:
 	.type	copy_tsb,#function
 copy_tsb:		/* %o0=old_tsb_base, %o1=old_tsb_size
 			 * %o2=new_tsb_base, %o3=new_tsb_size
+			 * %o4=page_size_shift
 			 */
 	sethi		%uhi(TSB_PASS_BITS), %g7
 	srlx		%o3, 4, %o3
-	add		%o0, %o1, %g1	/* end of old tsb */
+	add		%o0, %o1, %o1	/* end of old tsb */
 	sllx		%g7, 32, %g7
 	sub		%o3, 1, %o3	/* %o3 == new tsb hash mask */
 
+	mov		%o4, %g1	/* page_size_shift */
+
 661:	prefetcha	[%o0] ASI_N, #one_read
 	.section	.tsb_phys_patch, "ax"
 	.word		661b
@@ -501,9 +504,9 @@ copy_tsb:		/* %o0=old_tsb_base, %o1=old_tsb_size
 	/* This can definitely be computed faster... */
 	srlx		%o0, 4, %o5	/* Build index */
 	and		%o5, 511, %o5	/* Mask index */
-	sllx		%o5, PAGE_SHIFT, %o5 /* Put into vaddr position */
+	sllx		%o5, %g1, %o5	/* Put into vaddr position */
 	or		%o4, %o5, %o4	/* Full VADDR. */
-	srlx		%o4, PAGE_SHIFT, %o4 /* Shift down to create index */
+	srlx		%o4, %g1, %o4	/* Shift down to create index */
 	and		%o4, %o3, %o4	/* Mask with new_tsb_nents-1 */
 	sllx		%o4, 4, %o4	/* Shift back up into tsb ent offset */
 	TSB_STORE(%o2 + %o4, %g2)	/* Store TAG */
@@ -511,7 +514,7 @@ copy_tsb:		/* %o0=old_tsb_base, %o1=old_tsb_size
 	TSB_STORE(%o2 + %o4, %g3)	/* Store TTE */
 
 80:	add		%o0, 16, %o0
-	cmp		%o0, %g1
+	cmp		%o0, %o1
 	bne,pt		%xcc, 90b
 	 nop
 
diff --git a/arch/sparc/kernel/ttable_64.S b/arch/sparc/kernel/ttable_64.S
index c6dfdaa29e20..170ead662f2a 100644
--- a/arch/sparc/kernel/ttable_64.S
+++ b/arch/sparc/kernel/ttable_64.S
@@ -50,7 +50,7 @@ tl0_resv03e:	BTRAP(0x3e) BTRAP(0x3f) BTRAP(0x40)
 tl0_irq1:	TRAP_IRQ(smp_call_function_client, 1)
 tl0_irq2:	TRAP_IRQ(smp_receive_signal_client, 2)
 tl0_irq3:	TRAP_IRQ(smp_penguin_jailcell, 3)
-tl0_irq4:	TRAP_IRQ(smp_new_mmu_context_version_client, 4)
+tl0_irq4:       BTRAP(0x44)
 #else
 tl0_irq1:	BTRAP(0x41)
 tl0_irq2:	BTRAP(0x42)
diff --git a/arch/sparc/kernel/vio.c b/arch/sparc/kernel/vio.c
index cb5789c9f961..34824ca396f0 100644
--- a/arch/sparc/kernel/vio.c
+++ b/arch/sparc/kernel/vio.c
@@ -284,13 +284,16 @@ static struct vio_dev *vio_create_one(struct mdesc_handle *hp, u64 mp,
 	if (!id) {
 		dev_set_name(&vdev->dev, "%s", bus_id_name);
 		vdev->dev_no = ~(u64)0;
+		vdev->id = ~(u64)0;
 	} else if (!cfg_handle) {
 		dev_set_name(&vdev->dev, "%s-%llu", bus_id_name, *id);
 		vdev->dev_no = *id;
+		vdev->id = ~(u64)0;
 	} else {
 		dev_set_name(&vdev->dev, "%s-%llu-%llu", bus_id_name,
 			     *cfg_handle, *id);
 		vdev->dev_no = *cfg_handle;
+		vdev->id = *id;
 	}
 
 	vdev->dev.parent = parent;
@@ -333,27 +336,84 @@ static void vio_add(struct mdesc_handle *hp, u64 node)
 	(void) vio_create_one(hp, node, &root_vdev->dev);
 }
 
+struct vio_md_node_query {
+	const char *type;
+	u64 dev_no;
+	u64 id;
+};
+
 static int vio_md_node_match(struct device *dev, void *arg)
 {
+	struct vio_md_node_query *query = (struct vio_md_node_query *) arg;
 	struct vio_dev *vdev = to_vio_dev(dev);
 
-	if (vdev->mp == (u64) arg)
-		return 1;
+	if (vdev->dev_no != query->dev_no)
+		return 0;
+	if (vdev->id != query->id)
+		return 0;
+	if (strcmp(vdev->type, query->type))
+		return 0;
 
-	return 0;
+	return 1;
 }
 
 static void vio_remove(struct mdesc_handle *hp, u64 node)
 {
+	const char *type;
+	const u64 *id, *cfg_handle;
+	u64 a;
+	struct vio_md_node_query query;
 	struct device *dev;
 
-	dev = device_find_child(&root_vdev->dev, (void *) node,
+	type = mdesc_get_property(hp, node, "device-type", NULL);
+	if (!type) {
+		type = mdesc_get_property(hp, node, "name", NULL);
+		if (!type)
+			type = mdesc_node_name(hp, node);
+	}
+
+	query.type = type;
+
+	id = mdesc_get_property(hp, node, "id", NULL);
+	cfg_handle = NULL;
+	mdesc_for_each_arc(a, hp, node, MDESC_ARC_TYPE_BACK) {
+		u64 target;
+
+		target = mdesc_arc_target(hp, a);
+		cfg_handle = mdesc_get_property(hp, target,
+						"cfg-handle", NULL);
+		if (cfg_handle)
+			break;
+	}
+
+	if (!id) {
+		query.dev_no = ~(u64)0;
+		query.id = ~(u64)0;
+	} else if (!cfg_handle) {
+		query.dev_no = *id;
+		query.id = ~(u64)0;
+	} else {
+		query.dev_no = *cfg_handle;
+		query.id = *id;
+	}
+
+	dev = device_find_child(&root_vdev->dev, &query,
 				vio_md_node_match);
 	if (dev) {
 		printk(KERN_INFO "VIO: Removing device %s\n", dev_name(dev));
 
 		device_unregister(dev);
 		put_device(dev);
+	} else {
+		if (!id)
+			printk(KERN_ERR "VIO: Removed unknown %s node.\n",
+			       type);
+		else if (!cfg_handle)
+			printk(KERN_ERR "VIO: Removed unknown %s node %llu.\n",
+			       type, *id);
+		else
+			printk(KERN_ERR "VIO: Removed unknown %s node %llu-%llu.\n",
+			       type, *cfg_handle, *id);
 	}
 }
 
diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c
index 965655afdbb6..384aba109d7c 100644
--- a/arch/sparc/mm/init_64.c
+++ b/arch/sparc/mm/init_64.c
@@ -656,10 +656,58 @@ EXPORT_SYMBOL(__flush_dcache_range);
 
 /* get_new_mmu_context() uses "cache + 1".  */
 DEFINE_SPINLOCK(ctx_alloc_lock);
-unsigned long tlb_context_cache = CTX_FIRST_VERSION - 1;
+unsigned long tlb_context_cache = CTX_FIRST_VERSION;
 #define MAX_CTX_NR	(1UL << CTX_NR_BITS)
 #define CTX_BMAP_SLOTS	BITS_TO_LONGS(MAX_CTX_NR)
 DECLARE_BITMAP(mmu_context_bmap, MAX_CTX_NR);
+DEFINE_PER_CPU(struct mm_struct *, per_cpu_secondary_mm) = {0};
+
+static void mmu_context_wrap(void)
+{
+	unsigned long old_ver = tlb_context_cache & CTX_VERSION_MASK;
+	unsigned long new_ver, new_ctx, old_ctx;
+	struct mm_struct *mm;
+	int cpu;
+
+	bitmap_zero(mmu_context_bmap, 1 << CTX_NR_BITS);
+
+	/* Reserve kernel context */
+	set_bit(0, mmu_context_bmap);
+
+	new_ver = (tlb_context_cache & CTX_VERSION_MASK) + CTX_FIRST_VERSION;
+	if (unlikely(new_ver == 0))
+		new_ver = CTX_FIRST_VERSION;
+	tlb_context_cache = new_ver;
+
+	/*
+	 * Make sure that any new mm that are added into per_cpu_secondary_mm,
+	 * are going to go through get_new_mmu_context() path.
+	 */
+	mb();
+
+	/*
+	 * Updated versions to current on those CPUs that had valid secondary
+	 * contexts
+	 */
+	for_each_online_cpu(cpu) {
+		/*
+		 * If a new mm is stored after we took this mm from the array,
+		 * it will go into get_new_mmu_context() path, because we
+		 * already bumped the version in tlb_context_cache.
+		 */
+		mm = per_cpu(per_cpu_secondary_mm, cpu);
+
+		if (unlikely(!mm || mm == &init_mm))
+			continue;
+
+		old_ctx = mm->context.sparc64_ctx_val;
+		if (likely((old_ctx & CTX_VERSION_MASK) == old_ver)) {
+			new_ctx = (old_ctx & ~CTX_VERSION_MASK) | new_ver;
+			set_bit(new_ctx & CTX_NR_MASK, mmu_context_bmap);
+			mm->context.sparc64_ctx_val = new_ctx;
+		}
+	}
+}
 
 /* Caller does TLB context flushing on local CPU if necessary.
  * The caller also ensures that CTX_VALID(mm->context) is false.
@@ -675,48 +723,30 @@ void get_new_mmu_context(struct mm_struct *mm)
 {
 	unsigned long ctx, new_ctx;
 	unsigned long orig_pgsz_bits;
-	int new_version;
 
 	spin_lock(&ctx_alloc_lock);
+retry:
+	/* wrap might have happened, test again if our context became valid */
+	if (unlikely(CTX_VALID(mm->context)))
+		goto out;
 	orig_pgsz_bits = (mm->context.sparc64_ctx_val & CTX_PGSZ_MASK);
 	ctx = (tlb_context_cache + 1) & CTX_NR_MASK;
 	new_ctx = find_next_zero_bit(mmu_context_bmap, 1 << CTX_NR_BITS, ctx);
-	new_version = 0;
 	if (new_ctx >= (1 << CTX_NR_BITS)) {
 		new_ctx = find_next_zero_bit(mmu_context_bmap, ctx, 1);
 		if (new_ctx >= ctx) {
-			int i;
-			new_ctx = (tlb_context_cache & CTX_VERSION_MASK) +
-				CTX_FIRST_VERSION;
-			if (new_ctx == 1)
-				new_ctx = CTX_FIRST_VERSION;
-
-			/* Don't call memset, for 16 entries that's just
-			 * plain silly...
-			 */
-			mmu_context_bmap[0] = 3;
-			mmu_context_bmap[1] = 0;
-			mmu_context_bmap[2] = 0;
-			mmu_context_bmap[3] = 0;
-			for (i = 4; i < CTX_BMAP_SLOTS; i += 4) {
-				mmu_context_bmap[i + 0] = 0;
-				mmu_context_bmap[i + 1] = 0;
-				mmu_context_bmap[i + 2] = 0;
-				mmu_context_bmap[i + 3] = 0;
-			}
-			new_version = 1;
-			goto out;
+			mmu_context_wrap();
+			goto retry;
 		}
 	}
+	if (mm->context.sparc64_ctx_val)
+		cpumask_clear(mm_cpumask(mm));
 	mmu_context_bmap[new_ctx>>6] |= (1UL << (new_ctx & 63));
 	new_ctx |= (tlb_context_cache & CTX_VERSION_MASK);
-out:
 	tlb_context_cache = new_ctx;
 	mm->context.sparc64_ctx_val = new_ctx | orig_pgsz_bits;
+out:
 	spin_unlock(&ctx_alloc_lock);
-
-	if (unlikely(new_version))
-		smp_new_mmu_context_version();
 }
 
 static int numa_enabled = 1;
diff --git a/arch/sparc/mm/tsb.c b/arch/sparc/mm/tsb.c
index 9cdeca0fa955..266411291634 100644
--- a/arch/sparc/mm/tsb.c
+++ b/arch/sparc/mm/tsb.c
@@ -451,7 +451,8 @@ retry_tsb_alloc:
 		extern void copy_tsb(unsigned long old_tsb_base,
 				     unsigned long old_tsb_size,
 				     unsigned long new_tsb_base,
-				     unsigned long new_tsb_size);
+				     unsigned long new_tsb_size,
+				     unsigned long page_size_shift);
 		unsigned long old_tsb_base = (unsigned long) old_tsb;
 		unsigned long new_tsb_base = (unsigned long) new_tsb;
 
@@ -459,7 +460,9 @@ retry_tsb_alloc:
 			old_tsb_base = __pa(old_tsb_base);
 			new_tsb_base = __pa(new_tsb_base);
 		}
-		copy_tsb(old_tsb_base, old_size, new_tsb_base, new_size);
+		copy_tsb(old_tsb_base, old_size, new_tsb_base, new_size,
+			tsb_index == MM_TSB_BASE ?
+			PAGE_SHIFT : REAL_HPAGE_SHIFT);
 	}
 
 	mm->context.tsb_block[tsb_index].tsb = new_tsb;
diff --git a/arch/sparc/mm/ultra.S b/arch/sparc/mm/ultra.S
index 5d2fd6cd3189..fcf4d27a38fb 100644
--- a/arch/sparc/mm/ultra.S
+++ b/arch/sparc/mm/ultra.S
@@ -971,11 +971,6 @@ xcall_capture:
 	wr		%g0, (1 << PIL_SMP_CAPTURE), %set_softint
 	retry
 
-	.globl		xcall_new_mmu_context_version
-xcall_new_mmu_context_version:
-	wr		%g0, (1 << PIL_SMP_CTX_NEW_VERSION), %set_softint
-	retry
-
 #ifdef CONFIG_KGDB
 	.globl		xcall_kgdb_capture
 xcall_kgdb_capture: