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

9 files changed, 69 insertions, 369 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index a800b0faaad..e98e81a0497 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -150,7 +150,10 @@ config ARCH_HAS_CACHE_LINE_SIZE
 config HAVE_SETUP_PER_CPU_AREA
 	def_bool y
 
-config HAVE_DYNAMIC_PER_CPU_AREA
+config NEED_PER_CPU_EMBED_FIRST_CHUNK
+	def_bool y
+
+config NEED_PER_CPU_PAGE_FIRST_CHUNK
 	def_bool y
 
 config HAVE_CPUMASK_OF_CPU_MAP
diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index 04eacefcfd2..b65a36defeb 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -168,15 +168,6 @@ do {							\
 /* We can use this directly for local CPU (faster). */
 DECLARE_PER_CPU(unsigned long, this_cpu_off);
 
-#ifdef CONFIG_NEED_MULTIPLE_NODES
-void *pcpu_lpage_remapped(void *kaddr);
-#else
-static inline void *pcpu_lpage_remapped(void *kaddr)
-{
-	return NULL;
-}
-#endif
-
 #endif /* !__ASSEMBLY__ */
 
 #ifdef CONFIG_SMP
diff --git a/arch/x86/kernel/cpu/cpu_debug.c b/arch/x86/kernel/cpu/cpu_debug.c
index 6b2a52dd040..dca325c0399 100644
--- a/arch/x86/kernel/cpu/cpu_debug.c
+++ b/arch/x86/kernel/cpu/cpu_debug.c
@@ -30,8 +30,8 @@
 #include <asm/apic.h>
 #include <asm/desc.h>
 
-static DEFINE_PER_CPU(struct cpu_cpuX_base, cpu_arr[CPU_REG_ALL_BIT]);
-static DEFINE_PER_CPU(struct cpu_private *, priv_arr[MAX_CPU_FILES]);
+static DEFINE_PER_CPU(struct cpu_cpuX_base [CPU_REG_ALL_BIT], cpu_arr);
+static DEFINE_PER_CPU(struct cpu_private * [MAX_CPU_FILES], priv_arr);
 static DEFINE_PER_CPU(int, cpu_priv_count);
 
 static DEFINE_MUTEX(cpu_debug_lock);
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 9bfe9d2ea61..fdd51b55435 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -1101,7 +1101,7 @@ void mce_log_therm_throt_event(__u64 status)
  */
 static int check_interval = 5 * 60; /* 5 minutes */
 
-static DEFINE_PER_CPU(int, next_interval); /* in jiffies */
+static DEFINE_PER_CPU(int, mce_next_interval); /* in jiffies */
 static DEFINE_PER_CPU(struct timer_list, mce_timer);
 
 static void mcheck_timer(unsigned long data)
@@ -1120,7 +1120,7 @@ static void mcheck_timer(unsigned long data)
 	 * Alert userspace if needed.  If we logged an MCE, reduce the
 	 * polling interval, otherwise increase the polling interval.
 	 */
-	n = &__get_cpu_var(next_interval);
+	n = &__get_cpu_var(mce_next_interval);
 	if (mce_notify_irq())
 		*n = max(*n/2, HZ/100);
 	else
@@ -1335,7 +1335,7 @@ static void mce_cpu_features(struct cpuinfo_x86 *c)
 static void mce_init_timer(void)
 {
 	struct timer_list *t = &__get_cpu_var(mce_timer);
-	int *n = &__get_cpu_var(next_interval);
+	int *n = &__get_cpu_var(mce_next_interval);
 
 	if (mce_ignore_ce)
 		return;
@@ -1935,7 +1935,7 @@ mce_cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu)
 	case CPU_DOWN_FAILED:
 	case CPU_DOWN_FAILED_FROZEN:
 		t->expires = round_jiffies(jiffies +
-						__get_cpu_var(next_interval));
+					   __get_cpu_var(mce_next_interval));
 		add_timer_on(t, cpu);
 		smp_call_function_single(cpu, mce_reenable_cpu, &action, 1);
 		break;
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c
index 1fecba404fd..8cd5224943b 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c
@@ -69,7 +69,7 @@ struct threshold_bank {
 	struct threshold_block	*blocks;
 	cpumask_var_t		cpus;
 };
-static DEFINE_PER_CPU(struct threshold_bank *, threshold_banks[NR_BANKS]);
+static DEFINE_PER_CPU(struct threshold_bank * [NR_BANKS], threshold_banks);
 
 #ifdef CONFIG_SMP
 static unsigned char shared_bank[NR_BANKS] = {
diff --git a/arch/x86/kernel/cpu/perf_counter.c b/arch/x86/kernel/cpu/perf_counter.c
index f9cd0849bd4..2732e2c1e4d 100644
--- a/arch/x86/kernel/cpu/perf_counter.c
+++ b/arch/x86/kernel/cpu/perf_counter.c
@@ -1211,7 +1211,7 @@ amd_pmu_disable_counter(struct hw_perf_counter *hwc, int idx)
 	x86_pmu_disable_counter(hwc, idx);
 }
 
-static DEFINE_PER_CPU(u64, prev_left[X86_PMC_IDX_MAX]);
+static DEFINE_PER_CPU(u64 [X86_PMC_IDX_MAX], pmc_prev_left);
 
 /*
  * Set the next IRQ period, based on the hwc->period_left value.
@@ -1253,7 +1253,7 @@ x86_perf_counter_set_period(struct perf_counter *counter,
 	if (left > x86_pmu.max_period)
 		left = x86_pmu.max_period;
 
-	per_cpu(prev_left[idx], smp_processor_id()) = left;
+	per_cpu(pmc_prev_left[idx], smp_processor_id()) = left;
 
 	/*
 	 * The hw counter starts counting from this counter offset,
@@ -1470,7 +1470,7 @@ void perf_counter_print_debug(void)
 		rdmsrl(x86_pmu.eventsel + idx, pmc_ctrl);
 		rdmsrl(x86_pmu.perfctr  + idx, pmc_count);
 
-		prev_left = per_cpu(prev_left[idx], cpu);
+		prev_left = per_cpu(pmc_prev_left[idx], cpu);
 
 		pr_info("CPU#%d:   gen-PMC%d ctrl:  %016llx\n",
 			cpu, idx, pmc_ctrl);
@@ -2110,8 +2110,8 @@ void callchain_store(struct perf_callchain_entry *entry, u64 ip)
 		entry->ip[entry->nr++] = ip;
 }
 
-static DEFINE_PER_CPU(struct perf_callchain_entry, irq_entry);
-static DEFINE_PER_CPU(struct perf_callchain_entry, nmi_entry);
+static DEFINE_PER_CPU(struct perf_callchain_entry, pmc_irq_entry);
+static DEFINE_PER_CPU(struct perf_callchain_entry, pmc_nmi_entry);
 static DEFINE_PER_CPU(int, in_nmi_frame);
 
 
@@ -2264,9 +2264,9 @@ struct perf_callchain_entry *perf_callchain(struct pt_regs *regs)
 	struct perf_callchain_entry *entry;
 
 	if (in_nmi())
-		entry = &__get_cpu_var(nmi_entry);
+		entry = &__get_cpu_var(pmc_nmi_entry);
 	else
-		entry = &__get_cpu_var(irq_entry);
+		entry = &__get_cpu_var(pmc_irq_entry);
 
 	entry->nr = 0;
 
diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index 07d81916f21..d559af913e1 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -55,6 +55,7 @@ EXPORT_SYMBOL(__per_cpu_offset);
 #define PERCPU_FIRST_CHUNK_RESERVE	0
 #endif
 
+#ifdef CONFIG_X86_32
 /**
  * pcpu_need_numa - determine percpu allocation needs to consider NUMA
  *
@@ -83,6 +84,7 @@ static bool __init pcpu_need_numa(void)
 #endif
 	return false;
 }
+#endif
 
 /**
  * pcpu_alloc_bootmem - NUMA friendly alloc_bootmem wrapper for percpu
@@ -124,308 +126,35 @@ static void * __init pcpu_alloc_bootmem(unsigned int cpu, unsigned long size,
 }
 
 /*
- * Large page remap allocator
- *
- * This allocator uses PMD page as unit.  A PMD page is allocated for
- * each cpu and each is remapped into vmalloc area using PMD mapping.
- * As PMD page is quite large, only part of it is used for the first
- * chunk.  Unused part is returned to the bootmem allocator.
- *
- * So, the PMD pages are mapped twice - once to the physical mapping
- * and to the vmalloc area for the first percpu chunk.  The double
- * mapping does add one more PMD TLB entry pressure but still is much
- * better than only using 4k mappings while still being NUMA friendly.
+ * Helpers for first chunk memory allocation
  */
-#ifdef CONFIG_NEED_MULTIPLE_NODES
-struct pcpul_ent {
-	unsigned int	cpu;
-	void		*ptr;
-};
-
-static size_t pcpul_size;
-static struct pcpul_ent *pcpul_map;
-static struct vm_struct pcpul_vm;
-
-static struct page * __init pcpul_get_page(unsigned int cpu, int pageno)
+static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size, size_t align)
 {
-	size_t off = (size_t)pageno << PAGE_SHIFT;
-
-	if (off >= pcpul_size)
-		return NULL;
-
-	return virt_to_page(pcpul_map[cpu].ptr + off);
+	return pcpu_alloc_bootmem(cpu, size, align);
 }
 
-static ssize_t __init setup_pcpu_lpage(size_t static_size, bool chosen)
+static void __init pcpu_fc_free(void *ptr, size_t size)
 {
-	size_t map_size, dyn_size;
-	unsigned int cpu;
-	int i, j;
-	ssize_t ret;
-
-	if (!chosen) {
-		size_t vm_size = VMALLOC_END - VMALLOC_START;
-		size_t tot_size = nr_cpu_ids * PMD_SIZE;
-
-		/* on non-NUMA, embedding is better */
-		if (!pcpu_need_numa())
-			return -EINVAL;
-
-		/* don't consume more than 20% of vmalloc area */
-		if (tot_size > vm_size / 5) {
-			pr_info("PERCPU: too large chunk size %zuMB for "
-				"large page remap\n", tot_size >> 20);
-			return -EINVAL;
-		}
-	}
-
-	/* need PSE */
-	if (!cpu_has_pse) {
-		pr_warning("PERCPU: lpage allocator requires PSE\n");
-		return -EINVAL;
-	}
-
-	/*
-	 * Currently supports only single page.  Supporting multiple
-	 * pages won't be too difficult if it ever becomes necessary.
-	 */
-	pcpul_size = PFN_ALIGN(static_size + PERCPU_MODULE_RESERVE +
-			       PERCPU_DYNAMIC_RESERVE);
-	if (pcpul_size > PMD_SIZE) {
-		pr_warning("PERCPU: static data is larger than large page, "
-			   "can't use large page\n");
-		return -EINVAL;
-	}
-	dyn_size = pcpul_size - static_size - PERCPU_FIRST_CHUNK_RESERVE;
-
-	/* allocate pointer array and alloc large pages */
-	map_size = PFN_ALIGN(nr_cpu_ids * sizeof(pcpul_map[0]));
-	pcpul_map = alloc_bootmem(map_size);
-
-	for_each_possible_cpu(cpu) {
-		pcpul_map[cpu].cpu = cpu;
-		pcpul_map[cpu].ptr = pcpu_alloc_bootmem(cpu, PMD_SIZE,
-							PMD_SIZE);
-		if (!pcpul_map[cpu].ptr) {
-			pr_warning("PERCPU: failed to allocate large page "
-				   "for cpu%u\n", cpu);
-			goto enomem;
-		}
-
-		/*
-		 * Only use pcpul_size bytes and give back the rest.
-		 *
-		 * Ingo: The 2MB up-rounding bootmem is needed to make
-		 * sure the partial 2MB page is still fully RAM - it's
-		 * not well-specified to have a PAT-incompatible area
-		 * (unmapped RAM, device memory, etc.) in that hole.
-		 */
-		free_bootmem(__pa(pcpul_map[cpu].ptr + pcpul_size),
-			     PMD_SIZE - pcpul_size);
-
-		memcpy(pcpul_map[cpu].ptr, __per_cpu_load, static_size);
-	}
-
-	/* allocate address and map */
-	pcpul_vm.flags = VM_ALLOC;
-	pcpul_vm.size = nr_cpu_ids * PMD_SIZE;
-	vm_area_register_early(&pcpul_vm, PMD_SIZE);
-
-	for_each_possible_cpu(cpu) {
-		pmd_t *pmd, pmd_v;
-
-		pmd = populate_extra_pmd((unsigned long)pcpul_vm.addr +
-					 cpu * PMD_SIZE);
-		pmd_v = pfn_pmd(page_to_pfn(virt_to_page(pcpul_map[cpu].ptr)),
-				PAGE_KERNEL_LARGE);
-		set_pmd(pmd, pmd_v);
-	}
-
-	/* we're ready, commit */
-	pr_info("PERCPU: Remapped at %p with large pages, static data "
-		"%zu bytes\n", pcpul_vm.addr, static_size);
-
-	ret = pcpu_setup_first_chunk(pcpul_get_page, static_size,
-				     PERCPU_FIRST_CHUNK_RESERVE, dyn_size,
-				     PMD_SIZE, pcpul_vm.addr, NULL);
-
-	/* sort pcpul_map array for pcpu_lpage_remapped() */
-	for (i = 0; i < nr_cpu_ids - 1; i++)
-		for (j = i + 1; j < nr_cpu_ids; j++)
-			if (pcpul_map[i].ptr > pcpul_map[j].ptr) {
-				struct pcpul_ent tmp = pcpul_map[i];
-				pcpul_map[i] = pcpul_map[j];
-				pcpul_map[j] = tmp;
-			}
-
-	return ret;
-
-enomem:
-	for_each_possible_cpu(cpu)
-		if (pcpul_map[cpu].ptr)
-			free_bootmem(__pa(pcpul_map[cpu].ptr), pcpul_size);
-	free_bootmem(__pa(pcpul_map), map_size);
-	return -ENOMEM;
+	free_bootmem(__pa(ptr), size);
 }
 
-/**
- * pcpu_lpage_remapped - determine whether a kaddr is in pcpul recycled area
- * @kaddr: the kernel address in question
- *
- * Determine whether @kaddr falls in the pcpul recycled area.  This is
- * used by pageattr to detect VM aliases and break up the pcpu PMD
- * mapping such that the same physical page is not mapped under
- * different attributes.
- *
- * The recycled area is always at the tail of a partially used PMD
- * page.
- *
- * RETURNS:
- * Address of corresponding remapped pcpu address if match is found;
- * otherwise, NULL.
- */
-void *pcpu_lpage_remapped(void *kaddr)
+static int __init pcpu_cpu_distance(unsigned int from, unsigned int to)
 {
-	void *pmd_addr = (void *)((unsigned long)kaddr & PMD_MASK);
-	unsigned long offset = (unsigned long)kaddr & ~PMD_MASK;
-	int left = 0, right = nr_cpu_ids - 1;
-	int pos;
-
-	/* pcpul in use at all? */
-	if (!pcpul_map)
-		return NULL;
-
-	/* okay, perform binary search */
-	while (left <= right) {
-		pos = (left + right) / 2;
-
-		if (pcpul_map[pos].ptr < pmd_addr)
-			left = pos + 1;
-		else if (pcpul_map[pos].ptr > pmd_addr)
-			right = pos - 1;
-		else {
-			/* it shouldn't be in the area for the first chunk */
-			WARN_ON(offset < pcpul_size);
-
-			return pcpul_vm.addr +
-				pcpul_map[pos].cpu * PMD_SIZE + offset;
-		}
-	}
-
-	return NULL;
-}
+#ifdef CONFIG_NEED_MULTIPLE_NODES
+	if (early_cpu_to_node(from) == early_cpu_to_node(to))
+		return LOCAL_DISTANCE;
+	else
+		return REMOTE_DISTANCE;
 #else
-static ssize_t __init setup_pcpu_lpage(size_t static_size, bool chosen)
-{
-	return -EINVAL;
-}
+	return LOCAL_DISTANCE;
 #endif
-
-/*
- * Embedding allocator
- *
- * The first chunk is sized to just contain the static area plus
- * module and dynamic reserves and embedded into linear physical
- * mapping so that it can use PMD mapping without additional TLB
- * pressure.
- */
-static ssize_t __init setup_pcpu_embed(size_t static_size, bool chosen)
-{
-	size_t reserve = PERCPU_MODULE_RESERVE + PERCPU_DYNAMIC_RESERVE;
-
-	/*
-	 * If large page isn't supported, there's no benefit in doing
-	 * this.  Also, embedding allocation doesn't play well with
-	 * NUMA.
-	 */
-	if (!chosen && (!cpu_has_pse || pcpu_need_numa()))
-		return -EINVAL;
-
-	return pcpu_embed_first_chunk(static_size, PERCPU_FIRST_CHUNK_RESERVE,
-				      reserve - PERCPU_FIRST_CHUNK_RESERVE, -1);
 }
 
-/*
- * 4k page allocator
- *
- * This is the basic allocator.  Static percpu area is allocated
- * page-by-page and most of initialization is done by the generic
- * setup function.
- */
-static struct page **pcpu4k_pages __initdata;
-static int pcpu4k_nr_static_pages __initdata;
-
-static struct page * __init pcpu4k_get_page(unsigned int cpu, int pageno)
-{
-	if (pageno < pcpu4k_nr_static_pages)
-		return pcpu4k_pages[cpu * pcpu4k_nr_static_pages + pageno];
-	return NULL;
-}
-
-static void __init pcpu4k_populate_pte(unsigned long addr)
+static void __init pcpup_populate_pte(unsigned long addr)
 {
 	populate_extra_pte(addr);
 }
 
-static ssize_t __init setup_pcpu_4k(size_t static_size)
-{
-	size_t pages_size;
-	unsigned int cpu;
-	int i, j;
-	ssize_t ret;
-
-	pcpu4k_nr_static_pages = PFN_UP(static_size);
-
-	/* unaligned allocations can't be freed, round up to page size */
-	pages_size = PFN_ALIGN(pcpu4k_nr_static_pages * nr_cpu_ids
-			       * sizeof(pcpu4k_pages[0]));
-	pcpu4k_pages = alloc_bootmem(pages_size);
-
-	/* allocate and copy */
-	j = 0;
-	for_each_possible_cpu(cpu)
-		for (i = 0; i < pcpu4k_nr_static_pages; i++) {
-			void *ptr;
-
-			ptr = pcpu_alloc_bootmem(cpu, PAGE_SIZE, PAGE_SIZE);
-			if (!ptr) {
-				pr_warning("PERCPU: failed to allocate "
-					   "4k page for cpu%u\n", cpu);
-				goto enomem;
-			}
-
-			memcpy(ptr, __per_cpu_load + i * PAGE_SIZE, PAGE_SIZE);
-			pcpu4k_pages[j++] = virt_to_page(ptr);
-		}
-
-	/* we're ready, commit */
-	pr_info("PERCPU: Allocated %d 4k pages, static data %zu bytes\n",
-		pcpu4k_nr_static_pages, static_size);
-
-	ret = pcpu_setup_first_chunk(pcpu4k_get_page, static_size,
-				     PERCPU_FIRST_CHUNK_RESERVE, -1,
-				     -1, NULL, pcpu4k_populate_pte);
-	goto out_free_ar;
-
-enomem:
-	while (--j >= 0)
-		free_bootmem(__pa(page_address(pcpu4k_pages[j])), PAGE_SIZE);
-	ret = -ENOMEM;
-out_free_ar:
-	free_bootmem(__pa(pcpu4k_pages), pages_size);
-	return ret;
-}
-
-/* for explicit first chunk allocator selection */
-static char pcpu_chosen_alloc[16] __initdata;
-
-static int __init percpu_alloc_setup(char *str)
-{
-	strncpy(pcpu_chosen_alloc, str, sizeof(pcpu_chosen_alloc) - 1);
-	return 0;
-}
-early_param("percpu_alloc", percpu_alloc_setup);
-
 static inline void setup_percpu_segment(int cpu)
 {
 #ifdef CONFIG_X86_32
@@ -441,52 +170,49 @@ static inline void setup_percpu_segment(int cpu)
 
 void __init setup_per_cpu_areas(void)
 {
-	size_t static_size = __per_cpu_end - __per_cpu_start;
 	unsigned int cpu;
 	unsigned long delta;
-	size_t pcpu_unit_size;
-	ssize_t ret;
+	int rc;
 
 	pr_info("NR_CPUS:%d nr_cpumask_bits:%d nr_cpu_ids:%d nr_node_ids:%d\n",
 		NR_CPUS, nr_cpumask_bits, nr_cpu_ids, nr_node_ids);
 
 	/*
-	 * Allocate percpu area.  If PSE is supported, try to make use
-	 * of large page mappings.  Please read comments on top of
-	 * each allocator for details.
+	 * Allocate percpu area.  Embedding allocator is our favorite;
+	 * however, on NUMA configurations, it can result in very
+	 * sparse unit mapping and vmalloc area isn't spacious enough
+	 * on 32bit.  Use page in that case.
 	 */
-	ret = -EINVAL;
-	if (strlen(pcpu_chosen_alloc)) {
-		if (strcmp(pcpu_chosen_alloc, "4k")) {
-			if (!strcmp(pcpu_chosen_alloc, "lpage"))
-				ret = setup_pcpu_lpage(static_size, true);
-			else if (!strcmp(pcpu_chosen_alloc, "embed"))
-				ret = setup_pcpu_embed(static_size, true);
-			else
-				pr_warning("PERCPU: unknown allocator %s "
-					   "specified\n", pcpu_chosen_alloc);
-			if (ret < 0)
-				pr_warning("PERCPU: %s allocator failed (%zd), "
-					   "falling back to 4k\n",
-					   pcpu_chosen_alloc, ret);
-		}
-	} else {
-		ret = setup_pcpu_lpage(static_size, false);
-		if (ret < 0)
-			ret = setup_pcpu_embed(static_size, false);
+#ifdef CONFIG_X86_32
+	if (pcpu_chosen_fc == PCPU_FC_AUTO && pcpu_need_numa())
+		pcpu_chosen_fc = PCPU_FC_PAGE;
+#endif
+	rc = -EINVAL;
+	if (pcpu_chosen_fc != PCPU_FC_PAGE) {
+		const size_t atom_size = cpu_has_pse ? PMD_SIZE : PAGE_SIZE;
+		const size_t dyn_size = PERCPU_MODULE_RESERVE +
+			PERCPU_DYNAMIC_RESERVE - PERCPU_FIRST_CHUNK_RESERVE;
+
+		rc = pcpu_embed_first_chunk(PERCPU_FIRST_CHUNK_RESERVE,
+					    dyn_size, atom_size,
+					    pcpu_cpu_distance,
+					    pcpu_fc_alloc, pcpu_fc_free);
+		if (rc < 0)
+			pr_warning("PERCPU: %s allocator failed (%d), "
+				   "falling back to page size\n",
+				   pcpu_fc_names[pcpu_chosen_fc], rc);
 	}
-	if (ret < 0)
-		ret = setup_pcpu_4k(static_size);
-	if (ret < 0)
-		panic("cannot allocate static percpu area (%zu bytes, err=%zd)",
-		      static_size, ret);
-
-	pcpu_unit_size = ret;
+	if (rc < 0)
+		rc = pcpu_page_first_chunk(PERCPU_FIRST_CHUNK_RESERVE,
+					   pcpu_fc_alloc, pcpu_fc_free,
+					   pcpup_populate_pte);
+	if (rc < 0)
+		panic("cannot initialize percpu area (err=%d)", rc);
 
 	/* alrighty, percpu areas up and running */
 	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;
+		per_cpu_offset(cpu) = delta + pcpu_unit_offsets[cpu];
 		per_cpu(this_cpu_off, cpu) = per_cpu_offset(cpu);
 		per_cpu(cpu_number, cpu) = cpu;
 		setup_percpu_segment(cpu);
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 9fc178255c0..0ccb57d5ee3 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -348,15 +348,12 @@ SECTIONS
 		_end = .;
 	}
 
-	/* Sections to be discarded */
-	/DISCARD/ : {
-		*(.exitcall.exit)
-		*(.eh_frame)
-		*(.discard)
-	}
-
         STABS_DEBUG
         DWARF_DEBUG
+
+	/* Sections to be discarded */
+	DISCARDS
+	/DISCARD/ : { *(.eh_frame) }
 }
 
 
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index e245775ec85..24952fdc7e4 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -12,6 +12,7 @@
 #include <linux/seq_file.h>
 #include <linux/debugfs.h>
 #include <linux/pfn.h>
+#include <linux/percpu.h>
 
 #include <asm/e820.h>
 #include <asm/processor.h>
@@ -686,7 +687,7 @@ static int cpa_process_alias(struct cpa_data *cpa)
 {
 	struct cpa_data alias_cpa;
 	unsigned long laddr = (unsigned long)__va(cpa->pfn << PAGE_SHIFT);
-	unsigned long vaddr, remapped;
+	unsigned long vaddr;
 	int ret;
 
 	if (cpa->pfn >= max_pfn_mapped)
@@ -744,24 +745,6 @@ static int cpa_process_alias(struct cpa_data *cpa)
 	}
 #endif
 
-	/*
-	 * If the PMD page was partially used for per-cpu remapping,
-	 * the recycled area needs to be split and modified.  Because
-	 * the area is always proper subset of a PMD page
-	 * cpa->numpages is guaranteed to be 1 for these areas, so
-	 * there's no need to loop over and check for further remaps.
-	 */
-	remapped = (unsigned long)pcpu_lpage_remapped((void *)laddr);
-	if (remapped) {
-		WARN_ON(cpa->numpages > 1);
-		alias_cpa = *cpa;
-		alias_cpa.vaddr = &remapped;
-		alias_cpa.flags &= ~(CPA_PAGES_ARRAY | CPA_ARRAY);
-		ret = __change_page_attr_set_clr(&alias_cpa, 0);
-		if (ret)
-			return ret;
-	}
-
 	return 0;
 }