Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/sparc

Pull sparc updates from David Miller:

 1) Support multiple huge page sizes, from Nitin Gupta.

 2) Improve boot time on large memory configurations, from Pavel
    Tatashin.

 3) Make BRK handling more consistent and documented, from Vijay Kumar.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/sparc:
  sparc64: Fix build error in flush_tsb_user_page
  sparc64: memblock resizes are not handled properly
  sparc64: use latency groups to improve add_node_ranges speed
  sparc64: Add 64K page size support
  sparc64: Multi-page size support
  Documentation/sparc: Steps for sending break on sunhv console
  sparc64: Send break twice from console to return to boot prom
  sparc64: Migrate hvcons irq to panicked cpu
  sparc64: Set cpu state to offline when stopped
  sunvdc: Add support for setting physical sector size
  sparc64: fix for user probes in high memory
  sparc: topology_64.h: Fix condition for including cpudata.h
  sparc32: mm: srmmu: add __ro_after_init to sparc32_cachetlb_ops structures

Documentation/sparc/console.txt

+Steps for sending 'break' on sunhv console:
+===========================================
+
+On Baremetal:
+   1. press   Esc + 'B'
+
+On LDOM:
+   1. press    Ctrl + ']'
+   2. telnet> send  break

arch/sparc/include/asm/page_64.h

@@ -17,7 +17,8 @@
 
 #define HPAGE_SHIFT		23
 #define REAL_HPAGE_SHIFT	22
-
+#define HPAGE_256MB_SHIFT	28
+#define HPAGE_64K_SHIFT		16
 #define REAL_HPAGE_SIZE		(_AC(1,UL) << REAL_HPAGE_SHIFT)
 
 #if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
@@ -26,6 +27,7 @@
 #define HUGETLB_PAGE_ORDER	(HPAGE_SHIFT - PAGE_SHIFT)
 #define HAVE_ARCH_HUGETLB_UNMAPPED_AREA
 #define REAL_HPAGE_PER_HPAGE	(_AC(1,UL) << (HPAGE_SHIFT - REAL_HPAGE_SHIFT))
+#define HUGE_MAX_HSTATE		3
 #endif
 
 #ifndef __ASSEMBLY__

arch/sparc/include/asm/pgtable_64.h

@@ -375,7 +375,10 @@ static inline pgprot_t pgprot_noncached(pgprot_t prot)
 #define pgprot_noncached pgprot_noncached
 
 #if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
-static inline unsigned long __pte_huge_mask(void)
+extern pte_t arch_make_huge_pte(pte_t entry, struct vm_area_struct *vma,
+				struct page *page, int writable);
+#define arch_make_huge_pte arch_make_huge_pte
+static inline unsigned long __pte_default_huge_mask(void)
 {
 	unsigned long mask;
 
@@ -395,12 +398,14 @@ static inline unsigned long __pte_huge_mask(void)
 
 static inline pte_t pte_mkhuge(pte_t pte)
 {
-	return __pte(pte_val(pte) | _PAGE_PMD_HUGE | __pte_huge_mask());
+	return __pte(pte_val(pte) | __pte_default_huge_mask());
 }
 
-static inline bool is_hugetlb_pte(pte_t pte)
+static inline bool is_default_hugetlb_pte(pte_t pte)
 {
-	return !!(pte_val(pte) & __pte_huge_mask());
+	unsigned long mask = __pte_default_huge_mask();
+
+	return (pte_val(pte) & mask) == mask;
 }
 
 static inline bool is_hugetlb_pmd(pmd_t pmd)
@@ -875,10 +880,12 @@ static inline unsigned long pud_pfn(pud_t pud)
 
 /* Actual page table PTE updates.  */
 void tlb_batch_add(struct mm_struct *mm, unsigned long vaddr,
-		   pte_t *ptep, pte_t orig, int fullmm);
+		   pte_t *ptep, pte_t orig, int fullmm,
+		   unsigned int hugepage_shift);
 
 static void maybe_tlb_batch_add(struct mm_struct *mm, unsigned long vaddr,
-				pte_t *ptep, pte_t orig, int fullmm)
+				pte_t *ptep, pte_t orig, int fullmm,
+				unsigned int hugepage_shift)
 {
 	/* It is more efficient to let flush_tlb_kernel_range()
 	 * handle init_mm tlb flushes.
@@ -887,7 +894,7 @@ static void maybe_tlb_batch_add(struct mm_struct *mm, unsigned long vaddr,
 	 *             and SUN4V pte layout, so this inline test is fine.
 	 */
 	if (likely(mm != &init_mm) && pte_accessible(mm, orig))
-		tlb_batch_add(mm, vaddr, ptep, orig, fullmm);
+		tlb_batch_add(mm, vaddr, ptep, orig, fullmm, hugepage_shift);
 }
 
 #define __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR
@@ -906,7 +913,7 @@ static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr,
 	pte_t orig = *ptep;
 
 	*ptep = pte;
-	maybe_tlb_batch_add(mm, addr, ptep, orig, fullmm);
+	maybe_tlb_batch_add(mm, addr, ptep, orig, fullmm, PAGE_SHIFT);
 }
 
 #define set_pte_at(mm,addr,ptep,pte)	\

arch/sparc/include/asm/setup.h

@@ -59,8 +59,11 @@ extern atomic_t dcpage_flushes;
 extern atomic_t dcpage_flushes_xcall;
 
 extern int sysctl_tsb_ratio;
-#endif
 
+#ifdef CONFIG_SERIAL_SUNHV
+void sunhv_migrate_hvcons_irq(int cpu);
+#endif
+#endif
 void sun_do_break(void);
 extern int stop_a_enabled;
 extern int scons_pwroff;

arch/sparc/include/asm/tlbflush_64.h

@@ -8,7 +8,7 @@
 #define TLB_BATCH_NR	192
 
 struct tlb_batch {
-	bool huge;
+	unsigned int hugepage_shift;
 	struct mm_struct *mm;
 	unsigned long tlb_nr;
 	unsigned long active;
@@ -17,7 +17,8 @@ struct tlb_batch {
 
 void flush_tsb_kernel_range(unsigned long start, unsigned long end);
 void flush_tsb_user(struct tlb_batch *tb);
-void flush_tsb_user_page(struct mm_struct *mm, unsigned long vaddr, bool huge);
+void flush_tsb_user_page(struct mm_struct *mm, unsigned long vaddr,
+			 unsigned int hugepage_shift);
 
 /* TLB flush operations. */
 

arch/sparc/include/asm/topology_64.h

@@ -4,7 +4,6 @@
 #ifdef CONFIG_NUMA
 
 #include <asm/mmzone.h>
-#include <asm/cpudata.h>
 
 static inline int cpu_to_node(int cpu)
 {
@@ -42,6 +41,9 @@ int __node_distance(int, int);
 #endif /* !(CONFIG_NUMA) */
 
 #ifdef CONFIG_SMP
+
+#include <asm/cpudata.h>
+
 #define topology_physical_package_id(cpu)	(cpu_data(cpu).proc_id)
 #define topology_core_id(cpu)			(cpu_data(cpu).core_id)
 #define topology_core_cpumask(cpu)		(&cpu_core_sib_map[cpu])

arch/sparc/include/asm/uprobes.h

@@ -42,8 +42,8 @@ struct arch_uprobe {
 };
 
 struct arch_uprobe_task {
-	u32 saved_tpc;
-	u32 saved_tnpc;
+	u64 saved_tpc;
+	u64 saved_tnpc;
 };
 
 struct task_struct;

arch/sparc/kernel/smp_64.c

@@ -1443,6 +1443,7 @@ void __irq_entry smp_receive_signal_client(int irq, struct pt_regs *regs)
 
 static void stop_this_cpu(void *dummy)
 {
+	set_cpu_online(smp_processor_id(), false);
 	prom_stopself();
 }
 
@@ -1451,9 +1452,15 @@ void smp_send_stop(void)
 	int cpu;
 
 	if (tlb_type == hypervisor) {
+		int this_cpu = smp_processor_id();
+#ifdef CONFIG_SERIAL_SUNHV
+		sunhv_migrate_hvcons_irq(this_cpu);
+#endif
 		for_each_online_cpu(cpu) {
-			if (cpu == smp_processor_id())
+			if (cpu == this_cpu)
 				continue;
+
+			set_cpu_online(cpu, false);
 #ifdef CONFIG_SUN_LDOMS
 			if (ldom_domaining_enabled) {
 				unsigned long hv_err;

arch/sparc/kernel/tsb.S

@@ -117,26 +117,11 @@ tsb_miss_page_table_walk_sun4v_fastpath:
 	/* Valid PTE is now in %g5.  */
 
 #if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
-661:	sethi		%uhi(_PAGE_SZALL_4U), %g7
+	sethi		%uhi(_PAGE_PMD_HUGE), %g7
 	sllx		%g7, 32, %g7
-	.section	.sun4v_2insn_patch, "ax"
-	.word		661b
-	mov		_PAGE_SZALL_4V, %g7
-	nop
-	.previous
-
-	and		%g5, %g7, %g2
-
-661:	sethi		%uhi(_PAGE_SZHUGE_4U), %g7
-	sllx		%g7, 32, %g7
-	.section	.sun4v_2insn_patch, "ax"
-	.word		661b
-	mov		_PAGE_SZHUGE_4V, %g7
-	nop
-	.previous
 
-	cmp		%g2, %g7
-	bne,pt		%xcc, 60f
+	andcc		%g5, %g7, %g0
+	be,pt		%xcc, 60f
 	 nop
 
 	/* It is a huge page, use huge page TSB entry address we

arch/sparc/mm/hugetlbpage.c

@@ -28,6 +28,7 @@ static unsigned long hugetlb_get_unmapped_area_bottomup(struct file *filp,
 							unsigned long pgoff,
 							unsigned long flags)
 {
+	struct hstate *h = hstate_file(filp);
 	unsigned long task_size = TASK_SIZE;
 	struct vm_unmapped_area_info info;
 
@@ -38,7 +39,7 @@ static unsigned long hugetlb_get_unmapped_area_bottomup(struct file *filp,
 	info.length = len;
 	info.low_limit = TASK_UNMAPPED_BASE;
 	info.high_limit = min(task_size, VA_EXCLUDE_START);
-	info.align_mask = PAGE_MASK & ~HPAGE_MASK;
+	info.align_mask = PAGE_MASK & ~huge_page_mask(h);
 	info.align_offset = 0;
 	addr = vm_unmapped_area(&info);
 
@@ -58,6 +59,7 @@ hugetlb_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 				  const unsigned long pgoff,
 				  const unsigned long flags)
 {
+	struct hstate *h = hstate_file(filp);
 	struct mm_struct *mm = current->mm;
 	unsigned long addr = addr0;
 	struct vm_unmapped_area_info info;
@@ -69,7 +71,7 @@ hugetlb_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 	info.length = len;
 	info.low_limit = PAGE_SIZE;
 	info.high_limit = mm->mmap_base;
-	info.align_mask = PAGE_MASK & ~HPAGE_MASK;
+	info.align_mask = PAGE_MASK & ~huge_page_mask(h);
 	info.align_offset = 0;
 	addr = vm_unmapped_area(&info);
 
@@ -94,6 +96,7 @@ unsigned long
 hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
 		unsigned long len, unsigned long pgoff, unsigned long flags)
 {
+	struct hstate *h = hstate_file(file);
 	struct mm_struct *mm = current->mm;
 	struct vm_area_struct *vma;
 	unsigned long task_size = TASK_SIZE;
@@ -101,7 +104,7 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
 	if (test_thread_flag(TIF_32BIT))
 		task_size = STACK_TOP32;
 
-	if (len & ~HPAGE_MASK)
+	if (len & ~huge_page_mask(h))
 		return -EINVAL;
 	if (len > task_size)
 		return -ENOMEM;
@@ -113,7 +116,7 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
 	}
 
 	if (addr) {
-		addr = ALIGN(addr, HPAGE_SIZE);
+		addr = ALIGN(addr, huge_page_size(h));
 		vma = find_vma(mm, addr);
 		if (task_size - len >= addr &&
 		    (!vma || addr + len <= vma->vm_start))
@@ -127,17 +130,141 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
 				pgoff, flags);
 }
 
+static pte_t sun4u_hugepage_shift_to_tte(pte_t entry, unsigned int shift)
+{
+	return entry;
+}
+
+static pte_t sun4v_hugepage_shift_to_tte(pte_t entry, unsigned int shift)
+{
+	unsigned long hugepage_size = _PAGE_SZ4MB_4V;
+
+	pte_val(entry) = pte_val(entry) & ~_PAGE_SZALL_4V;
+
+	switch (shift) {
+	case HPAGE_256MB_SHIFT:
+		hugepage_size = _PAGE_SZ256MB_4V;
+		pte_val(entry) |= _PAGE_PMD_HUGE;
+		break;
+	case HPAGE_SHIFT:
+		pte_val(entry) |= _PAGE_PMD_HUGE;
+		break;
+	case HPAGE_64K_SHIFT:
+		hugepage_size = _PAGE_SZ64K_4V;
+		break;
+	default:
+		WARN_ONCE(1, "unsupported hugepage shift=%u\n", shift);
+	}
+
+	pte_val(entry) = pte_val(entry) | hugepage_size;
+	return entry;
+}
+
+static pte_t hugepage_shift_to_tte(pte_t entry, unsigned int shift)
+{
+	if (tlb_type == hypervisor)
+		return sun4v_hugepage_shift_to_tte(entry, shift);
+	else
+		return sun4u_hugepage_shift_to_tte(entry, shift);
+}
+
+pte_t arch_make_huge_pte(pte_t entry, struct vm_area_struct *vma,
+			 struct page *page, int writeable)
+{
+	unsigned int shift = huge_page_shift(hstate_vma(vma));
+
+	return hugepage_shift_to_tte(entry, shift);
+}
+
+static unsigned int sun4v_huge_tte_to_shift(pte_t entry)
+{
+	unsigned long tte_szbits = pte_val(entry) & _PAGE_SZALL_4V;
+	unsigned int shift;
+
+	switch (tte_szbits) {
+	case _PAGE_SZ256MB_4V:
+		shift = HPAGE_256MB_SHIFT;
+		break;
+	case _PAGE_SZ4MB_4V:
+		shift = REAL_HPAGE_SHIFT;
+		break;
+	case _PAGE_SZ64K_4V:
+		shift = HPAGE_64K_SHIFT;
+		break;
+	default:
+		shift = PAGE_SHIFT;
+		break;
+	}
+	return shift;
+}
+
+static unsigned int sun4u_huge_tte_to_shift(pte_t entry)
+{
+	unsigned long tte_szbits = pte_val(entry) & _PAGE_SZALL_4U;
+	unsigned int shift;
+
+	switch (tte_szbits) {
+	case _PAGE_SZ256MB_4U:
+		shift = HPAGE_256MB_SHIFT;
+		break;
+	case _PAGE_SZ4MB_4U:
+		shift = REAL_HPAGE_SHIFT;
+		break;
+	case _PAGE_SZ64K_4U:
+		shift = HPAGE_64K_SHIFT;
+		break;
+	default:
+		shift = PAGE_SHIFT;
+		break;
+	}
+	return shift;
+}
+
+static unsigned int huge_tte_to_shift(pte_t entry)
+{
+	unsigned long shift;
+
+	if (tlb_type == hypervisor)
+		shift = sun4v_huge_tte_to_shift(entry);
+	else
+		shift = sun4u_huge_tte_to_shift(entry);
+
+	if (shift == PAGE_SHIFT)
+		WARN_ONCE(1, "tto_to_shift: invalid hugepage tte=0x%lx\n",
+			  pte_val(entry));
+
+	return shift;
+}
+
+static unsigned long huge_tte_to_size(pte_t pte)
+{
+	unsigned long size = 1UL << huge_tte_to_shift(pte);
+
+	if (size == REAL_HPAGE_SIZE)
+		size = HPAGE_SIZE;
+	return size;
+}
+
 pte_t *huge_pte_alloc(struct mm_struct *mm,
 			unsigned long addr, unsigned long sz)
 {
 	pgd_t *pgd;
 	pud_t *pud;
+	pmd_t *pmd;
 	pte_t *pte = NULL;
 
 	pgd = pgd_offset(mm, addr);
 	pud = pud_alloc(mm, pgd, addr);
-	if (pud)
-		pte = (pte_t *)pmd_alloc(mm, pud, addr);
+	if (pud) {
+		pmd = pmd_alloc(mm, pud, addr);
+		if (!pmd)
+			return NULL;
+
+		if (sz == PMD_SHIFT)
+			pte = (pte_t *)pmd;
+		else
+			pte = pte_alloc_map(mm, pmd, addr);
+	}
 
 	return pte;
 }
@@ -146,49 +273,83 @@ pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
 {
 	pgd_t *pgd;
 	pud_t *pud;
+	pmd_t *pmd;
 	pte_t *pte = NULL;
 
 	pgd = pgd_offset(mm, addr);
 	if (!pgd_none(*pgd)) {
 		pud = pud_offset(pgd, addr);
-		if (!pud_none(*pud))
-			pte = (pte_t *)pmd_offset(pud, addr);
+		if (!pud_none(*pud)) {
+			pmd = pmd_offset(pud, addr);
+			if (!pmd_none(*pmd)) {
+				if (is_hugetlb_pmd(*pmd))
+					pte = (pte_t *)pmd;
+				else
+					pte = pte_offset_map(pmd, addr);
+			}
+		}
 	}
+
 	return pte;
 }
 
 void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 		     pte_t *ptep, pte_t entry)
 {
+	unsigned int i, nptes, orig_shift, shift;
+	unsigned long size;
 	pte_t orig;
 
+	size = huge_tte_to_size(entry);
+	shift = size >= HPAGE_SIZE ? PMD_SHIFT : PAGE_SHIFT;
+	nptes = size >> shift;
+
 	if (!pte_present(*ptep) && pte_present(entry))
-		mm->context.hugetlb_pte_count++;
+		mm->context.hugetlb_pte_count += nptes;
 
-	addr &= HPAGE_MASK;
+	addr &= ~(size - 1);
 	orig = *ptep;
-	*ptep = entry;
+	orig_shift = pte_none(orig) ? PAGE_SHIFT : huge_tte_to_shift(orig);
+
+	for (i = 0; i < nptes; i++)
+		ptep[i] = __pte(pte_val(entry) + (i << shift));
 
-	/* Issue TLB flush at REAL_HPAGE_SIZE boundaries */
-	maybe_tlb_batch_add(mm, addr, ptep, orig, 0);
-	maybe_tlb_batch_add(mm, addr + REAL_HPAGE_SIZE, ptep, orig, 0);
+	maybe_tlb_batch_add(mm, addr, ptep, orig, 0, orig_shift);
+	/* An HPAGE_SIZE'ed page is composed of two REAL_HPAGE_SIZE'ed pages */
+	if (size == HPAGE_SIZE)
+		maybe_tlb_batch_add(mm, addr + REAL_HPAGE_SIZE, ptep, orig, 0,
+				    orig_shift);
 }
 
 pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
 			      pte_t *ptep)
 {
+	unsigned int i, nptes, hugepage_shift;
+	unsigned long size;
 	pte_t entry;
 
 	entry = *ptep;
+	size = huge_tte_to_size(entry);
+	if (size >= HPAGE_SIZE)
+		nptes = size >> PMD_SHIFT;
+	else
+		nptes = size >> PAGE_SHIFT;
+
+	hugepage_shift = pte_none(entry) ? PAGE_SHIFT :
+		huge_tte_to_shift(entry);
+
 	if (pte_present(entry))
-		mm->context.hugetlb_pte_count--;
+		mm->context.hugetlb_pte_count -= nptes;
 
-	addr &= HPAGE_MASK;
-	*ptep = __pte(0UL);
+	addr &= ~(size - 1);
+	for (i = 0; i < nptes; i++)
+		ptep[i] = __pte(0UL);
 
-	/* Issue TLB flush at REAL_HPAGE_SIZE boundaries */
-	maybe_tlb_batch_add(mm, addr, ptep, entry, 0);
-	maybe_tlb_batch_add(mm, addr + REAL_HPAGE_SIZE, ptep, entry, 0);
+	maybe_tlb_batch_add(mm, addr, ptep, entry, 0, hugepage_shift);
+	/* An HPAGE_SIZE'ed page is composed of two REAL_HPAGE_SIZE'ed pages */
+	if (size == HPAGE_SIZE)
+		maybe_tlb_batch_add(mm, addr + REAL_HPAGE_SIZE, ptep, entry, 0,
+				    hugepage_shift);
 
 	return entry;
 }

arch/sparc/mm/init_64.c

@@ -324,6 +324,50 @@ static void __update_mmu_tsb_insert(struct mm_struct *mm, unsigned long tsb_inde
 	tsb_insert(tsb, tag, tte);
 }
 
+#ifdef CONFIG_HUGETLB_PAGE
+static int __init setup_hugepagesz(char *string)
+{
+	unsigned long long hugepage_size;
+	unsigned int hugepage_shift;
+	unsigned short hv_pgsz_idx;
+	unsigned int hv_pgsz_mask;
+	int rc = 0;
+
+	hugepage_size = memparse(string, &string);
+	hugepage_shift = ilog2(hugepage_size);
+
+	switch (hugepage_shift) {
+	case HPAGE_256MB_SHIFT:
+		hv_pgsz_mask = HV_PGSZ_MASK_256MB;
+		hv_pgsz_idx = HV_PGSZ_IDX_256MB;
+		break;
+	case HPAGE_SHIFT:
+		hv_pgsz_mask = HV_PGSZ_MASK_4MB;
+		hv_pgsz_idx = HV_PGSZ_IDX_4MB;
+		break;
+	case HPAGE_64K_SHIFT:
+		hv_pgsz_mask = HV_PGSZ_MASK_64K;
+		hv_pgsz_idx = HV_PGSZ_IDX_64K;
+		break;
+	default:
+		hv_pgsz_mask = 0;
+	}
+
+	if ((hv_pgsz_mask & cpu_pgsz_mask) == 0U) {
+		pr_warn("hugepagesz=%llu not supported by MMU.\n",
+			hugepage_size);
+		goto out;
+	}
+
+	hugetlb_add_hstate(hugepage_shift - PAGE_SHIFT);
+	rc = 1;
+
+out:
+	return rc;
+}
+__setup("hugepagesz=", setup_hugepagesz);
+#endif	/* CONFIG_HUGETLB_PAGE */
+
 void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t *ptep)
 {
 	struct mm_struct *mm;
@@ -347,7 +391,7 @@ void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t *
 
 #if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
 	if ((mm->context.hugetlb_pte_count || mm->context.thp_pte_count) &&
-	    is_hugetlb_pte(pte)) {
+	    is_hugetlb_pmd(__pmd(pte_val(pte)))) {
 		/* We are fabricating 8MB pages using 4MB real hw pages.  */
 		pte_val(pte) |= (address & (1UL << REAL_HPAGE_SHIFT));
 		__update_mmu_tsb_insert(mm, MM_TSB_HUGE, REAL_HPAGE_SHIFT,
@@ -785,13 +829,23 @@ static void __init find_ramdisk(unsigned long phys_base)
 
 struct node_mem_mask {
 	unsigned long mask;
-	unsigned long val;
+	unsigned long match;
 };
 static struct node_mem_mask node_masks[MAX_NUMNODES];
 static int num_node_masks;
 
 #ifdef CONFIG_NEED_MULTIPLE_NODES
 
+struct mdesc_mlgroup {
+	u64	node;
+	u64	latency;
+	u64	match;
+	u64	mask;
+};
+
+static struct mdesc_mlgroup *mlgroups;
+static int num_mlgroups;
+
 int numa_cpu_lookup_table[NR_CPUS];
 cpumask_t numa_cpumask_lookup_table[MAX_NUMNODES];
 
@@ -802,78 +856,129 @@ struct mdesc_mblock {
 };
 static struct mdesc_mblock *mblocks;
 static int num_mblocks;
-static int find_numa_node_for_addr(unsigned long pa,
-				   struct node_mem_mask *pnode_mask);
 
-static unsigned long __init ra_to_pa(unsigned long addr)
+static struct mdesc_mblock * __init addr_to_mblock(unsigned long addr)
 {
+	struct mdesc_mblock *m = NULL;
 	int i;
 
 	for (i = 0; i < num_mblocks; i++) {
-		struct mdesc_mblock *m = &mblocks[i];
+		m = &mblocks[i];
 
 		if (addr >= m->base &&
 		    addr < (m->base + m->size)) {
-			addr += m->offset;
 			break;
 		}
 	}
-	return addr;
+
+	return m;
 }
 
-static int __init find_node(unsigned long addr)
+static u64 __init memblock_nid_range_sun4u(u64 start, u64 end, int *nid)
 {
-	static bool search_mdesc = true;
-	static struct node_mem_mask last_mem_mask = { ~0UL, ~0UL };
-	static int last_index;
-	int i;
+	int prev_nid, new_nid;
 
-	addr = ra_to_pa(addr);
-	for (i = 0; i < num_node_masks; i++) {
-		struct node_mem_mask *p = &node_masks[i];
+	prev_nid = -1;
+	for ( ; start < end; start += PAGE_SIZE) {
+		for (new_nid = 0; new_nid < num_node_masks; new_nid++) {
+			struct node_mem_mask *p = &node_masks[new_nid];
 
-		if ((addr & p->mask) == p->val)
-			return i;
-	}
-	/* The following condition has been observed on LDOM guests because
-	 * node_masks only contains the best latency mask and value.
-	 * LDOM guest's mdesc can contain a single latency group to
-	 * cover multiple address range. Print warning message only if the
-	 * address cannot be found in node_masks nor mdesc.
-	 */
-	if ((search_mdesc) &&
-	    ((addr & last_mem_mask.mask) != last_mem_mask.val)) {
-		/* find the available node in the mdesc */
-		last_index = find_numa_node_for_addr(addr, &last_mem_mask);
-		numadbg("find_node: latency group for address 0x%lx is %d\n",
-			addr, last_index);
-		if ((last_index < 0) || (last_index >= num_node_masks)) {
-			/* WARN_ONCE() and use default group 0 */
-			WARN_ONCE(1, "find_node: A physical address doesn't match a NUMA node rule. Some physical memory will be owned by node 0.");
-			search_mdesc = false;
-			last_index = 0;
+			if ((start & p->mask) == p->match) {
+				if (prev_nid == -1)
+					prev_nid = new_nid;
+				break;
+			}
 		}
+
+		if (new_nid == num_node_masks) {
+			prev_nid = 0;
+			WARN_ONCE(1, "addr[%Lx] doesn't match a NUMA node rule. Some memory will be owned by node 0.",
+				  start);
+			break;
+		}
+
+		if (prev_nid != new_nid)
+			break;
 	}
+	*nid = prev_nid;
 
-	return last_index;
+	return start > end ? end : start;
 }
 
 static u64 __init memblock_nid_range(u64 start, u64 end, int *nid)
 {
-	*nid = find_node(start);
-	start += PAGE_SIZE;
-	while (start < end) {
-		int n = find_node(start);
+	u64 ret_end, pa_start, m_mask, m_match, m_end;
+	struct mdesc_mblock *mblock;
+	int _nid, i;
+
+	if (tlb_type != hypervisor)
+		return memblock_nid_range_sun4u(start, end, nid);
+
+	mblock = addr_to_mblock(start);
+	if (!mblock) {
+		WARN_ONCE(1, "memblock_nid_range: Can't find mblock addr[%Lx]",
+			  start);
+
+		_nid = 0;
+		ret_end = end;
+		goto done;
+	}
+
+	pa_start = start + mblock->offset;
+	m_match = 0;
+	m_mask = 0;
+
+	for (_nid = 0; _nid < num_node_masks; _nid++) {
+		struct node_mem_mask *const m = &node_masks[_nid];
 
-		if (n != *nid)
+		if ((pa_start & m->mask) == m->match) {
+			m_match = m->match;
+			m_mask = m->mask;
 			break;
-		start += PAGE_SIZE;
+		}
 	}
 
-	if (start > end)
-		start = end;
+	if (num_node_masks == _nid) {
+		/* We could not find NUMA group, so default to 0, but lets
+		 * search for latency group, so we could calculate the correct
+		 * end address that we return
+		 */
+		_nid = 0;
+
+		for (i = 0; i < num_mlgroups; i++) {
+			struct mdesc_mlgroup *const m = &mlgroups[i];
+
+			if ((pa_start & m->mask) == m->match) {
+				m_match = m->match;
+				m_mask = m->mask;
+				break;
+			}
+		}
+
+		if (i == num_mlgroups) {
+			WARN_ONCE(1, "memblock_nid_range: Can't find latency group addr[%Lx]",
+				  start);
+
+			ret_end = end;
+			goto done;
+		}
+	}
 
-	return start;
+	/*
+	 * Each latency group has match and mask, and each memory block has an
+	 * offset.  An address belongs to a latency group if its address matches
+	 * the following formula: ((addr + offset) & mask) == match
+	 * It is, however, slow to check every single page if it matches a
+	 * particular latency group. As optimization we calculate end value by
+	 * using bit arithmetics.
+	 */
+	m_end = m_match + (1ul << __ffs(m_mask)) - mblock->offset;
+	m_end += pa_start & ~((1ul << fls64(m_mask)) - 1);
+	ret_end = m_end > end ? end : m_end;
+
+done:
+	*nid = _nid;
+	return ret_end;
 }
 #endif
 
@@ -914,7 +1019,8 @@ static void init_node_masks_nonnuma(void)
 
 	numadbg("Initializing tables for non-numa.\n");
 
-	node_masks[0].mask = node_masks[0].val = 0;
+	node_masks[0].mask = 0;
+	node_masks[0].match = 0;
 	num_node_masks = 1;
 
 #ifdef CONFIG_NEED_MULTIPLE_NODES
@@ -932,15 +1038,6 @@ EXPORT_SYMBOL(numa_cpu_lookup_table);
 EXPORT_SYMBOL(numa_cpumask_lookup_table);
 EXPORT_SYMBOL(node_data);
 
-struct mdesc_mlgroup {
-	u64	node;
-	u64	latency;
-	u64	match;
-	u64	mask;
-};
-static struct mdesc_mlgroup *mlgroups;
-static int num_mlgroups;
-
 static int scan_pio_for_cfg_handle(struct mdesc_handle *md, u64 pio,
 				   u32 cfg_handle)
 {
@@ -1029,6 +1126,10 @@ int of_node_to_nid(struct device_node *dp)
 static void __init add_node_ranges(void)
 {
 	struct memblock_region *reg;
+	unsigned long prev_max;
+
+memblock_resized:
+	prev_max = memblock.memory.max;
 
 	for_each_memblock(memory, reg) {
 		unsigned long size = reg->size;
@@ -1048,6 +1149,8 @@ static void __init add_node_ranges(void)
 
 			memblock_set_node(start, this_end - start,
 					  &memblock.memory, nid);
+			if (memblock.memory.max != prev_max)
+				goto memblock_resized;
 			start = this_end;
 		}
 	}
@@ -1182,41 +1285,6 @@ int __node_distance(int from, int to)
 	return numa_latency[from][to];
 }
 
-static int find_numa_node_for_addr(unsigned long pa,
-				   struct node_mem_mask *pnode_mask)
-{
-	struct mdesc_handle *md = mdesc_grab();
-	u64 node, arc;
-	int i = 0;
-
-	node = mdesc_node_by_name(md, MDESC_NODE_NULL, "latency-groups");
-	if (node == MDESC_NODE_NULL)
-		goto out;
-
-	mdesc_for_each_node_by_name(md, node, "group") {
-		mdesc_for_each_arc(arc, md, node, MDESC_ARC_TYPE_FWD) {
-			u64 target = mdesc_arc_target(md, arc);
-			struct mdesc_mlgroup *m = find_mlgroup(target);
-
-			if (!m)
-				continue;
-			if ((pa & m->mask) == m->match) {
-				if (pnode_mask) {
-					pnode_mask->mask = m->mask;
-					pnode_mask->val = m->match;
-				}
-				mdesc_release(md);
-				return i;
-			}
-		}
-		i++;
-	}
-
-out:
-	mdesc_release(md);
-	return -1;
-}
-
 static int __init find_best_numa_node_for_mlgroup(struct mdesc_mlgroup *grp)
 {
 	int i;
@@ -1224,7 +1292,7 @@ static int __init find_best_numa_node_for_mlgroup(struct mdesc_mlgroup *grp)
 	for (i = 0; i < MAX_NUMNODES; i++) {
 		struct node_mem_mask *n = &node_masks[i];
 
-		if ((grp->mask == n->mask) && (grp->match == n->val))
+		if ((grp->mask == n->mask) && (grp->match == n->match))
 			break;
 	}
 	return i;
@@ -1279,10 +1347,10 @@ static int __init numa_attach_mlgroup(struct mdesc_handle *md, u64 grp,
 	n = &node_masks[num_node_masks++];
 
 	n->mask = candidate->mask;
-	n->val = candidate->match;
+	n->match = candidate->match;
 
-	numadbg("NUMA NODE[%d]: mask[%lx] val[%lx] (latency[%llx])\n",
-		index, n->mask, n->val, candidate->latency);
+	numadbg("NUMA NODE[%d]: mask[%lx] match[%lx] (latency[%llx])\n",
+		index, n->mask, n->match, candidate->latency);
 
 	return 0;
 }
@@ -1379,7 +1447,7 @@ static int __init numa_parse_jbus(void)
 		numa_cpu_lookup_table[cpu] = index;
 		cpumask_copy(&numa_cpumask_lookup_table[index], cpumask_of(cpu));
 		node_masks[index].mask = ~((1UL << 36UL) - 1UL);
-		node_masks[index].val = cpu << 36UL;
+		node_masks[index].match = cpu << 36UL;
 
 		index++;
 	}

arch/sparc/mm/srmmu.c

@@ -1444,7 +1444,7 @@ static void poke_viking(void)
 	srmmu_set_mmureg(mreg);
 }
 
-static struct sparc32_cachetlb_ops viking_ops = {
+static struct sparc32_cachetlb_ops viking_ops __ro_after_init = {
 	.cache_all	= viking_flush_cache_all,
 	.cache_mm	= viking_flush_cache_mm,
 	.cache_page	= viking_flush_cache_page,
@@ -1475,7 +1475,7 @@ static struct sparc32_cachetlb_ops viking_ops = {
  * flushes going at once will require SMP locking anyways so there's
  * no real value in trying any harder than this.
  */
-static struct sparc32_cachetlb_ops viking_sun4d_smp_ops = {
+static struct sparc32_cachetlb_ops viking_sun4d_smp_ops __ro_after_init = {
 	.cache_all	= viking_flush_cache_all,
 	.cache_mm	= viking_flush_cache_mm,
 	.cache_page	= viking_flush_cache_page,
@@ -1759,7 +1759,7 @@ static void smp_flush_sig_insns(struct mm_struct *mm, unsigned long insn_addr)
 	local_ops->sig_insns(mm, insn_addr);
 }
 
-static struct sparc32_cachetlb_ops smp_cachetlb_ops = {
+static struct sparc32_cachetlb_ops smp_cachetlb_ops __ro_after_init = {
 	.cache_all	= smp_flush_cache_all,
 	.cache_mm	= smp_flush_cache_mm,
 	.cache_page	= smp_flush_cache_page,

arch/sparc/mm/tlb.c

@@ -67,7 +67,7 @@ void arch_leave_lazy_mmu_mode(void)
 }
 
 static void tlb_batch_add_one(struct mm_struct *mm, unsigned long vaddr,
-			      bool exec, bool huge)
+			      bool exec, unsigned int hugepage_shift)
 {
 	struct tlb_batch *tb = &get_cpu_var(tlb_batch);
 	unsigned long nr;
@@ -84,19 +84,19 @@ static void tlb_batch_add_one(struct mm_struct *mm, unsigned long vaddr,
 	}
 
 	if (!tb->active) {
-		flush_tsb_user_page(mm, vaddr, huge);
+		flush_tsb_user_page(mm, vaddr, hugepage_shift);
 		global_flush_tlb_page(mm, vaddr);
 		goto out;
 	}
 
 	if (nr == 0) {
 		tb->mm = mm;
-		tb->huge = huge;
+		tb->hugepage_shift = hugepage_shift;
 	}
 
-	if (tb->huge != huge) {
+	if (tb->hugepage_shift != hugepage_shift) {
 		flush_tlb_pending();
-		tb->huge = huge;
+		tb->hugepage_shift = hugepage_shift;
 		nr = 0;
 	}
 
@@ -110,10 +110,9 @@ static void tlb_batch_add_one(struct mm_struct *mm, unsigned long vaddr,
 }
 
 void tlb_batch_add(struct mm_struct *mm, unsigned long vaddr,
-		   pte_t *ptep, pte_t orig, int fullmm)
+		   pte_t *ptep, pte_t orig, int fullmm,
+		   unsigned int hugepage_shift)
 {
-	bool huge = is_hugetlb_pte(orig);
-
 	if (tlb_type != hypervisor &&
 	    pte_dirty(orig)) {
 		unsigned long paddr, pfn = pte_pfn(orig);
@@ -139,7 +138,7 @@ void tlb_batch_add(struct mm_struct *mm, unsigned long vaddr,
 
 no_cache_flush:
 	if (!fullmm)
-		tlb_batch_add_one(mm, vaddr, pte_exec(orig), huge);
+		tlb_batch_add_one(mm, vaddr, pte_exec(orig), hugepage_shift);
 }
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE

arch/sparc/mm/tsb.c

@@ -86,6 +86,33 @@ static void __flush_tsb_one(struct tlb_batch *tb, unsigned long hash_shift,
 		__flush_tsb_one_entry(tsb, tb->vaddrs[i], hash_shift, nentries);
 }
 
+#if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
+static void __flush_huge_tsb_one_entry(unsigned long tsb, unsigned long v,
+				       unsigned long hash_shift,
+				       unsigned long nentries,
+				       unsigned int hugepage_shift)
+{
+	unsigned int hpage_entries;
+	unsigned int i;
+
+	hpage_entries = 1 << (hugepage_shift - hash_shift);
+	for (i = 0; i < hpage_entries; i++)
+		__flush_tsb_one_entry(tsb, v + (i << hash_shift), hash_shift,
+				      nentries);
+}
+
+static void __flush_huge_tsb_one(struct tlb_batch *tb, unsigned long hash_shift,
+				 unsigned long tsb, unsigned long nentries,
+				 unsigned int hugepage_shift)
+{
+	unsigned long i;
+
+	for (i = 0; i < tb->tlb_nr; i++)
+		__flush_huge_tsb_one_entry(tsb, tb->vaddrs[i], hash_shift,
+					   nentries, hugepage_shift);
+}
+#endif
+
 void flush_tsb_user(struct tlb_batch *tb)
 {
 	struct mm_struct *mm = tb->mm;
@@ -93,45 +120,61 @@ void flush_tsb_user(struct tlb_batch *tb)
 
 	spin_lock_irqsave(&mm->context.lock, flags);
 
-	if (!tb->huge) {
+	if (tb->hugepage_shift < HPAGE_SHIFT) {
 		base = (unsigned long) mm->context.tsb_block[MM_TSB_BASE].tsb;
 		nentries = mm->context.tsb_block[MM_TSB_BASE].tsb_nentries;
 		if (tlb_type == cheetah_plus || tlb_type == hypervisor)
 			base = __pa(base);
-		__flush_tsb_one(tb, PAGE_SHIFT, base, nentries);
+		if (tb->hugepage_shift == PAGE_SHIFT)
+			__flush_tsb_one(tb, PAGE_SHIFT, base, nentries);
+#if defined(CONFIG_HUGETLB_PAGE)
+		else
+			__flush_huge_tsb_one(tb, PAGE_SHIFT, base, nentries,
+					     tb->hugepage_shift);
+#endif
 	}
 #if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
-	if (tb->huge && mm->context.tsb_block[MM_TSB_HUGE].tsb) {
+	else if (mm->context.tsb_block[MM_TSB_HUGE].tsb) {
 		base = (unsigned long) mm->context.tsb_block[MM_TSB_HUGE].tsb;
 		nentries = mm->context.tsb_block[MM_TSB_HUGE].tsb_nentries;
 		if (tlb_type == cheetah_plus || tlb_type == hypervisor)
 			base = __pa(base);
-		__flush_tsb_one(tb, REAL_HPAGE_SHIFT, base, nentries);
+		__flush_huge_tsb_one(tb, REAL_HPAGE_SHIFT, base, nentries,
+				     tb->hugepage_shift);
 	}
 #endif
 	spin_unlock_irqrestore(&mm->context.lock, flags);
 }
 
-void flush_tsb_user_page(struct mm_struct *mm, unsigned long vaddr, bool huge)
+void flush_tsb_user_page(struct mm_struct *mm, unsigned long vaddr,
+			 unsigned int hugepage_shift)
 {
 	unsigned long nentries, base, flags;
 
 	spin_lock_irqsave(&mm->context.lock, flags);
 
-	if (!huge) {
+	if (hugepage_shift < HPAGE_SHIFT) {
 		base = (unsigned long) mm->context.tsb_block[MM_TSB_BASE].tsb;
 		nentries = mm->context.tsb_block[MM_TSB_BASE].tsb_nentries;
 		if (tlb_type == cheetah_plus || tlb_type == hypervisor)
 			base = __pa(base);
-		__flush_tsb_one_entry(base, vaddr, PAGE_SHIFT, nentries);
+		if (hugepage_shift == PAGE_SHIFT)
+			__flush_tsb_one_entry(base, vaddr, PAGE_SHIFT,
+					      nentries);
+#if defined(CONFIG_HUGETLB_PAGE)
+		else
+			__flush_huge_tsb_one_entry(base, vaddr, PAGE_SHIFT,
+						   nentries, hugepage_shift);
+#endif
 	}
 #if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
-	if (huge && mm->context.tsb_block[MM_TSB_HUGE].tsb) {
+	else if (mm->context.tsb_block[MM_TSB_HUGE].tsb) {
 		base = (unsigned long) mm->context.tsb_block[MM_TSB_HUGE].tsb;
 		nentries = mm->context.tsb_block[MM_TSB_HUGE].tsb_nentries;
 		if (tlb_type == cheetah_plus || tlb_type == hypervisor)
 			base = __pa(base);
-		__flush_tsb_one_entry(base, vaddr, REAL_HPAGE_SHIFT, nentries);
+		__flush_huge_tsb_one_entry(base, vaddr, REAL_HPAGE_SHIFT,
+					   nentries, hugepage_shift);
 	}
 #endif
 	spin_unlock_irqrestore(&mm->context.lock, flags);

drivers/block/sunvdc.c

@@ -34,6 +34,7 @@ MODULE_LICENSE("GPL");
 MODULE_VERSION(DRV_MODULE_VERSION);
 
 #define VDC_TX_RING_SIZE	512
+#define VDC_DEFAULT_BLK_SIZE	512
 
 #define WAITING_FOR_LINK_UP	0x01
 #define WAITING_FOR_TX_SPACE	0x02
@@ -73,6 +74,7 @@ struct vdc_port {
 	u32			vdisk_size;
 	u8			vdisk_type;
 	u8			vdisk_mtype;
+	u32			vdisk_phys_blksz;
 
 	char			disk_name[32];
 };
@@ -88,6 +90,7 @@ static inline struct vdc_port *to_vdc_port(struct vio_driver_state *vio)
 
 /* Ordered from largest major to lowest */
 static struct vio_version vdc_versions[] = {
+	{ .major = 1, .minor = 2 },
 	{ .major = 1, .minor = 1 },
 	{ .major = 1, .minor = 0 },
 };
@@ -271,6 +274,11 @@ static int vdc_handle_attr(struct vio_driver_state *vio, void *arg)
 		if (pkt->max_xfer_size < port->max_xfer_size)
 			port->max_xfer_size = pkt->max_xfer_size;
 		port->vdisk_block_size = pkt->vdisk_block_size;
+
+		port->vdisk_phys_blksz = VDC_DEFAULT_BLK_SIZE;
+		if (vdc_version_supported(port, 1, 2))
+			port->vdisk_phys_blksz = pkt->phys_block_size;
+
 		return 0;
 	} else {
 		printk(KERN_ERR PFX "%s: Attribute NACK\n", vio->name);
@@ -754,6 +762,12 @@ static int probe_disk(struct vdc_port *port)
 	if (err)
 		return err;
 
+	/* Using version 1.2 means vdisk_phys_blksz should be set unless the
+	 * disk is reserved by another system.
+	 */
+	if (vdc_version_supported(port, 1, 2) && !port->vdisk_phys_blksz)
+		return -ENODEV;
+
 	if (vdc_version_supported(port, 1, 1)) {
 		/* vdisk_size should be set during the handshake, if it wasn't
 		 * then the underlying disk is reserved by another system
@@ -829,6 +843,8 @@ static int probe_disk(struct vdc_port *port)
 		}
 	}
 
+	blk_queue_physical_block_size(q, port->vdisk_phys_blksz);
+
 	pr_info(PFX "%s: %u sectors (%u MB) protocol %d.%d\n",
 	       g->disk_name,
 	       port->vdisk_size, (port->vdisk_size >> (20 - 9)),
@@ -910,7 +926,7 @@ static int vdc_port_probe(struct vio_dev *vdev, const struct vio_device_id *id)
 	if (err)
 		goto err_out_free_port;
 
-	port->vdisk_block_size = 512;
+	port->vdisk_block_size = VDC_DEFAULT_BLK_SIZE;
 	port->max_xfer_size = ((128 * 1024) / port->vdisk_block_size);
 	port->ring_cookies = ((port->max_xfer_size *
 			       port->vdisk_block_size) / PAGE_SIZE) + 2;

drivers/tty/serial/sunhv.c

@@ -116,7 +116,7 @@ static int receive_chars_getchar(struct uart_port *port)
 
 static int receive_chars_read(struct uart_port *port)
 {
-	int saw_console_brk = 0;
+	static int saw_console_brk;
 	int limit = 10000;
 
 	while (limit-- > 0) {
@@ -128,6 +128,9 @@ static int receive_chars_read(struct uart_port *port)
 			bytes_read = 0;
 
 			if (stat == CON_BREAK) {
+				if (saw_console_brk)
+					sun_do_break();
+
 				if (uart_handle_break(port))
 					continue;
 				saw_console_brk = 1;
@@ -151,6 +154,7 @@ static int receive_chars_read(struct uart_port *port)
 		if (port->sysrq != 0 &&  *con_read_page) {
 			for (i = 0; i < bytes_read; i++)
 				uart_handle_sysrq_char(port, con_read_page[i]);
+			saw_console_brk = 0;
 		}
 
 		if (port->state == NULL)
@@ -398,6 +402,12 @@ static struct uart_driver sunhv_reg = {
 
 static struct uart_port *sunhv_port;
 
+void sunhv_migrate_hvcons_irq(int cpu)
+{
+	/* Migrate hvcons irq to param cpu */
+	irq_force_affinity(sunhv_port->irq, cpumask_of(cpu));
+}
+
 /* Copy 's' into the con_write_page, decoding "\n" into
  * "\r\n" along the way.  We have to return two lengths
  * because the caller needs to know how much to advance

kernel/panic.c

@@ -273,7 +273,8 @@ void panic(const char *fmt, ...)
 		extern int stop_a_enabled;
 		/* Make sure the user can actually press Stop-A (L1-A) */
 		stop_a_enabled = 1;
-		pr_emerg("Press Stop-A (L1-A) to return to the boot prom\n");
+		pr_emerg("Press Stop-A (L1-A) from sun keyboard or send break\n"
+			 "twice on console to return to the boot prom\n");
 	}
 #endif
 #if defined(CONFIG_S390)