Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/percpu

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/percpu: (46 commits)
  powerpc64: convert to dynamic percpu allocator
  sparc64: use embedding percpu first chunk allocator
  percpu: kill lpage first chunk allocator
  x86,percpu: use embedding for 64bit NUMA and page for 32bit NUMA
  percpu: update embedding first chunk allocator to handle sparse units
  percpu: use group information to allocate vmap areas sparsely
  vmalloc: implement pcpu_get_vm_areas()
  vmalloc: separate out insert_vmalloc_vm()
  percpu: add chunk->base_addr
  percpu: add pcpu_unit_offsets[]
  percpu: introduce pcpu_alloc_info and pcpu_group_info
  percpu: move pcpu_lpage_build_unit_map() and pcpul_lpage_dump_cfg() upward
  percpu: add @align to pcpu_fc_alloc_fn_t
  percpu: make @dyn_size mandatory for pcpu_setup_first_chunk()
  percpu: drop @static_size from first chunk allocators
  percpu: generalize first chunk allocator selection
  percpu: build first chunk allocators selectively
  percpu: rename 4k first chunk allocator to page
  percpu: improve boot messages
  percpu: fix pcpu_reclaim() locking
  ...

Fix trivial conflict as by Tejun Heo in kernel/sched.c

3 files changed, 23 insertions, 119 deletions

diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index 2bd5c287538a..86b82348b97c 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -99,7 +99,7 @@ config AUDIT_ARCH
 config HAVE_SETUP_PER_CPU_AREA
 	def_bool y if SPARC64
 
-config HAVE_DYNAMIC_PER_CPU_AREA
+config NEED_PER_CPU_EMBED_FIRST_CHUNK
 	def_bool y if SPARC64
 
 config GENERIC_HARDIRQS_NO__DO_IRQ
diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c
index 3691907a43b4..ff68373ce6d6 100644
--- a/arch/sparc/kernel/smp_64.c
+++ b/arch/sparc/kernel/smp_64.c
@@ -1389,8 +1389,8 @@ void smp_send_stop(void)
  * RETURNS:
  * Pointer to the allocated area on success, NULL on failure.
  */
-static void * __init pcpu_alloc_bootmem(unsigned int cpu, unsigned long size,
-					unsigned long align)
+static void * __init pcpu_alloc_bootmem(unsigned int cpu, size_t size,
+					size_t align)
 {
 	const unsigned long goal = __pa(MAX_DMA_ADDRESS);
 #ifdef CONFIG_NEED_MULTIPLE_NODES
@@ -1415,127 +1415,35 @@ static void * __init pcpu_alloc_bootmem(unsigned int cpu, unsigned long size,
 #endif
 }
 
-static size_t pcpur_size __initdata;
-static void **pcpur_ptrs __initdata;
-
-static struct page * __init pcpur_get_page(unsigned int cpu, int pageno)
+static void __init pcpu_free_bootmem(void *ptr, size_t size)
 {
-	size_t off = (size_t)pageno << PAGE_SHIFT;
-
-	if (off >= pcpur_size)
-		return NULL;
-
-	return virt_to_page(pcpur_ptrs[cpu] + off);
+	free_bootmem(__pa(ptr), size);
 }
 
-#define PCPU_CHUNK_SIZE (4UL * 1024UL * 1024UL)
-
-static void __init pcpu_map_range(unsigned long start, unsigned long end,
-				  struct page *page)
+static int pcpu_cpu_distance(unsigned int from, unsigned int to)
 {
-	unsigned long pfn = page_to_pfn(page);
-	unsigned long pte_base;
-
-	BUG_ON((pfn<<PAGE_SHIFT)&(PCPU_CHUNK_SIZE - 1UL));
-
-	pte_base = (_PAGE_VALID | _PAGE_SZ4MB_4U |
-		    _PAGE_CP_4U | _PAGE_CV_4U |
-		    _PAGE_P_4U | _PAGE_W_4U);
-	if (tlb_type == hypervisor)
-		pte_base = (_PAGE_VALID | _PAGE_SZ4MB_4V |
-			    _PAGE_CP_4V | _PAGE_CV_4V |
-			    _PAGE_P_4V | _PAGE_W_4V);
-
-	while (start < end) {
-		pgd_t *pgd = pgd_offset_k(start);
-		unsigned long this_end;
-		pud_t *pud;
-		pmd_t *pmd;
-		pte_t *pte;
-
-		pud = pud_offset(pgd, start);
-		if (pud_none(*pud)) {
-			pmd_t *new;
-
-			new = __alloc_bootmem(PAGE_SIZE, PAGE_SIZE, PAGE_SIZE);
-			pud_populate(&init_mm, pud, new);
-		}
-
-		pmd = pmd_offset(pud, start);
-		if (!pmd_present(*pmd)) {
-			pte_t *new;
-
-			new = __alloc_bootmem(PAGE_SIZE, PAGE_SIZE, PAGE_SIZE);
-			pmd_populate_kernel(&init_mm, pmd, new);
-		}
-
-		pte = pte_offset_kernel(pmd, start);
-		this_end = (start + PMD_SIZE) & PMD_MASK;
-		if (this_end > end)
-			this_end = end;
-
-		while (start < this_end) {
-			unsigned long paddr = pfn << PAGE_SHIFT;
-
-			pte_val(*pte) = (paddr | pte_base);
-
-			start += PAGE_SIZE;
-			pte++;
-			pfn++;
-		}
-	}
+	if (cpu_to_node(from) == cpu_to_node(to))
+		return LOCAL_DISTANCE;
+	else
+		return REMOTE_DISTANCE;
 }
 
 void __init setup_per_cpu_areas(void)
 {
-	size_t dyn_size, static_size = __per_cpu_end - __per_cpu_start;
-	static struct vm_struct vm;
-	unsigned long delta, cpu;
-	size_t pcpu_unit_size;
-	size_t ptrs_size;
-
-	pcpur_size = PFN_ALIGN(static_size + PERCPU_MODULE_RESERVE +
-			       PERCPU_DYNAMIC_RESERVE);
-	dyn_size = pcpur_size - static_size - PERCPU_MODULE_RESERVE;
-
+	unsigned long delta;
+	unsigned int cpu;
+	int rc;
 
-	ptrs_size = PFN_ALIGN(nr_cpu_ids * sizeof(pcpur_ptrs[0]));
-	pcpur_ptrs = alloc_bootmem(ptrs_size);
-
-	for_each_possible_cpu(cpu) {
-		pcpur_ptrs[cpu] = pcpu_alloc_bootmem(cpu, PCPU_CHUNK_SIZE,
-						     PCPU_CHUNK_SIZE);
-
-		free_bootmem(__pa(pcpur_ptrs[cpu] + pcpur_size),
-			     PCPU_CHUNK_SIZE - pcpur_size);
-
-		memcpy(pcpur_ptrs[cpu], __per_cpu_load, static_size);
-	}
-
-	/* allocate address and map */
-	vm.flags = VM_ALLOC;
-	vm.size = nr_cpu_ids * PCPU_CHUNK_SIZE;
-	vm_area_register_early(&vm, PCPU_CHUNK_SIZE);
-
-	for_each_possible_cpu(cpu) {
-		unsigned long start = (unsigned long) vm.addr;
-		unsigned long end;
-
-		start += cpu * PCPU_CHUNK_SIZE;
-		end = start + PCPU_CHUNK_SIZE;
-		pcpu_map_range(start, end, virt_to_page(pcpur_ptrs[cpu]));
-	}
-
-	pcpu_unit_size = pcpu_setup_first_chunk(pcpur_get_page, static_size,
-						PERCPU_MODULE_RESERVE, dyn_size,
-						PCPU_CHUNK_SIZE, vm.addr, NULL);
-
-	free_bootmem(__pa(pcpur_ptrs), ptrs_size);
+	rc = pcpu_embed_first_chunk(PERCPU_MODULE_RESERVE,
+				    PERCPU_DYNAMIC_RESERVE, 4 << 20,
+				    pcpu_cpu_distance, pcpu_alloc_bootmem,
+				    pcpu_free_bootmem);
+	if (rc)
+		panic("failed to initialize first chunk (%d)", rc);
 
 	delta = (unsigned long)pcpu_base_addr - (unsigned long)__per_cpu_start;
-	for_each_possible_cpu(cpu) {
-		__per_cpu_offset(cpu) = delta + cpu * pcpu_unit_size;
-	}
+	for_each_possible_cpu(cpu)
+		__per_cpu_offset(cpu) = delta + pcpu_unit_offsets[cpu];
 
 	/* Setup %g5 for the boot cpu.  */
 	__local_per_cpu_offset = __per_cpu_offset(smp_processor_id());
diff --git a/arch/sparc/kernel/vmlinux.lds.S b/arch/sparc/kernel/vmlinux.lds.S
index fcbbd000ec08..866390feb683 100644
--- a/arch/sparc/kernel/vmlinux.lds.S
+++ b/arch/sparc/kernel/vmlinux.lds.S
@@ -171,12 +171,8 @@ SECTIONS
 	}
 	_end = . ;
 
-	/DISCARD/ : {
-		EXIT_TEXT
-		EXIT_DATA
-		*(.exitcall.exit)
-	}
-
 	STABS_DEBUG
 	DWARF_DEBUG
+
+	DISCARDS
 }