Merge branch 'for-tip' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/percpu into x86/urgent

29 files changed, 245 insertions, 110 deletions

diff --git a/arch/alpha/mm/fault.c b/arch/alpha/mm/fault.c
index 4829f96..00a31de 100644
--- a/arch/alpha/mm/fault.c
+++ b/arch/alpha/mm/fault.c
@@ -146,7 +146,7 @@ do_page_fault(unsigned long address, unsigned long mmcsr,
 	/* If for any reason at all we couldn't handle the fault,
 	   make sure we exit gracefully rather than endlessly redo
 	   the fault.  */
-	fault = handle_mm_fault(mm, vma, address, cause > 0);
+	fault = handle_mm_fault(mm, vma, address, cause > 0 ? FAULT_FLAG_WRITE : 0);
 	up_read(&mm->mmap_sem);
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c
index 0455557..6fdcbb7 100644
--- a/arch/arm/mm/fault.c
+++ b/arch/arm/mm/fault.c
@@ -208,7 +208,7 @@ good_area:
 	 * than endlessly redo the fault.
 	 */
 survive:
-	fault = handle_mm_fault(mm, vma, addr & PAGE_MASK, fsr & (1 << 11));
+	fault = handle_mm_fault(mm, vma, addr & PAGE_MASK, (fsr & (1 << 11)) ? FAULT_FLAG_WRITE : 0);
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
diff --git a/arch/avr32/mm/fault.c b/arch/avr32/mm/fault.c
index 62d4abb..b61d86d 100644
--- a/arch/avr32/mm/fault.c
+++ b/arch/avr32/mm/fault.c
@@ -133,7 +133,7 @@ good_area:
 	 * fault.
 	 */
 survive:
-	fault = handle_mm_fault(mm, vma, address, writeaccess);
+	fault = handle_mm_fault(mm, vma, address, writeaccess ? FAULT_FLAG_WRITE : 0);
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
diff --git a/arch/cris/mm/fault.c b/arch/cris/mm/fault.c
index c4c76db..f925115 100644
--- a/arch/cris/mm/fault.c
+++ b/arch/cris/mm/fault.c
@@ -163,7 +163,7 @@ do_page_fault(unsigned long address, struct pt_regs *regs,
 	 * the fault.
 	 */
 
-	fault = handle_mm_fault(mm, vma, address, writeaccess & 1);
+	fault = handle_mm_fault(mm, vma, address, (writeaccess & 1) ? FAULT_FLAG_WRITE : 0);
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
diff --git a/arch/frv/mm/fault.c b/arch/frv/mm/fault.c
index 05093d4..30f5d10 100644
--- a/arch/frv/mm/fault.c
+++ b/arch/frv/mm/fault.c
@@ -163,7 +163,7 @@ asmlinkage void do_page_fault(int datammu, unsigned long esr0, unsigned long ear
 	 * make sure we exit gracefully rather than endlessly redo
 	 * the fault.
 	 */
-	fault = handle_mm_fault(mm, vma, ear0, write);
+	fault = handle_mm_fault(mm, vma, ear0, write ? FAULT_FLAG_WRITE : 0);
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
diff --git a/arch/ia64/mm/fault.c b/arch/ia64/mm/fault.c
index 23088be..19261a9 100644
--- a/arch/ia64/mm/fault.c
+++ b/arch/ia64/mm/fault.c
@@ -154,7 +154,7 @@ ia64_do_page_fault (unsigned long address, unsigned long isr, struct pt_regs *re
 	 * sure we exit gracefully rather than endlessly redo the
 	 * fault.
 	 */
-	fault = handle_mm_fault(mm, vma, address, (mask & VM_WRITE) != 0);
+	fault = handle_mm_fault(mm, vma, address, (mask & VM_WRITE) ? FAULT_FLAG_WRITE : 0);
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		/*
 		 * We ran out of memory, or some other thing happened
diff --git a/arch/m32r/mm/fault.c b/arch/m32r/mm/fault.c
index 4a71df4..7274b47 100644
--- a/arch/m32r/mm/fault.c
+++ b/arch/m32r/mm/fault.c
@@ -196,7 +196,7 @@ survive:
 	 */
 	addr = (address & PAGE_MASK);
 	set_thread_fault_code(error_code);
-	fault = handle_mm_fault(mm, vma, addr, write);
+	fault = handle_mm_fault(mm, vma, addr, write ? FAULT_FLAG_WRITE : 0);
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
diff --git a/arch/m68k/mm/fault.c b/arch/m68k/mm/fault.c
index f493f03..d0e35cf 100644
--- a/arch/m68k/mm/fault.c
+++ b/arch/m68k/mm/fault.c
@@ -155,7 +155,7 @@ good_area:
 	 */
 
  survive:
-	fault = handle_mm_fault(mm, vma, address, write);
+	fault = handle_mm_fault(mm, vma, address, write ? FAULT_FLAG_WRITE : 0);
 #ifdef DEBUG
 	printk("handle_mm_fault returns %d\n",fault);
 #endif
diff --git a/arch/microblaze/mm/fault.c b/arch/microblaze/mm/fault.c
index 5e67cd1..956607a 100644
--- a/arch/microblaze/mm/fault.c
+++ b/arch/microblaze/mm/fault.c
@@ -232,7 +232,7 @@ good_area:
 	 * the fault.
 	 */
 survive:
-	fault = handle_mm_fault(mm, vma, address, is_write);
+	fault = handle_mm_fault(mm, vma, address, is_write ? FAULT_FLAG_WRITE : 0);
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
diff --git a/arch/mips/mm/fault.c b/arch/mips/mm/fault.c
index 55767ad..6751ce9 100644
--- a/arch/mips/mm/fault.c
+++ b/arch/mips/mm/fault.c
@@ -102,7 +102,7 @@ good_area:
 	 * make sure we exit gracefully rather than endlessly redo
 	 * the fault.
 	 */
-	fault = handle_mm_fault(mm, vma, address, write);
+	fault = handle_mm_fault(mm, vma, address, write ? FAULT_FLAG_WRITE : 0);
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
diff --git a/arch/mn10300/mm/fault.c b/arch/mn10300/mm/fault.c
index 33cf250..a62e1e1 100644
--- a/arch/mn10300/mm/fault.c
+++ b/arch/mn10300/mm/fault.c
@@ -258,7 +258,7 @@ good_area:
 	 * make sure we exit gracefully rather than endlessly redo
 	 * the fault.
 	 */
-	fault = handle_mm_fault(mm, vma, address, write);
+	fault = handle_mm_fault(mm, vma, address, write ? FAULT_FLAG_WRITE : 0);
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c
index 92c7fa4..bfb6dd6 100644
--- a/arch/parisc/mm/fault.c
+++ b/arch/parisc/mm/fault.c
@@ -202,7 +202,7 @@ good_area:
 	 * fault.
 	 */
 
-	fault = handle_mm_fault(mm, vma, address, (acc_type & VM_WRITE) != 0);
+	fault = handle_mm_fault(mm, vma, address, (acc_type & VM_WRITE) ? FAULT_FLAG_WRITE : 0);
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		/*
 		 * We hit a shared mapping outside of the file, or some
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index 5beffc8..830bef0 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -302,7 +302,7 @@ good_area:
 	 * the fault.
 	 */
  survive:
-	ret = handle_mm_fault(mm, vma, address, is_write);
+	ret = handle_mm_fault(mm, vma, address, is_write ? FAULT_FLAG_WRITE : 0);
 	if (unlikely(ret & VM_FAULT_ERROR)) {
 		if (ret & VM_FAULT_OOM)
 			goto out_of_memory;
diff --git a/arch/powerpc/platforms/cell/spu_fault.c b/arch/powerpc/platforms/cell/spu_fault.c
index 95d8dad..d06ba87 100644
--- a/arch/powerpc/platforms/cell/spu_fault.c
+++ b/arch/powerpc/platforms/cell/spu_fault.c
@@ -70,7 +70,7 @@ int spu_handle_mm_fault(struct mm_struct *mm, unsigned long ea,
 	}
 
 	ret = 0;
-	*flt = handle_mm_fault(mm, vma, ea, is_write);
+	*flt = handle_mm_fault(mm, vma, ea, is_write ? FAULT_FLAG_WRITE : 0);
 	if (unlikely(*flt & VM_FAULT_ERROR)) {
 		if (*flt & VM_FAULT_OOM) {
 			ret = -ENOMEM;
diff --git a/arch/s390/lib/uaccess_pt.c b/arch/s390/lib/uaccess_pt.c
index b0b84c3..cb5d59e 100644
--- a/arch/s390/lib/uaccess_pt.c
+++ b/arch/s390/lib/uaccess_pt.c
@@ -66,7 +66,7 @@ static int __handle_fault(struct mm_struct *mm, unsigned long address,
 	}
 
 survive:
-	fault = handle_mm_fault(mm, vma, address, write_access);
+	fault = handle_mm_fault(mm, vma, address, write_access ? FAULT_FLAG_WRITE : 0);
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
index 220a152..74eb26b 100644
--- a/arch/s390/mm/fault.c
+++ b/arch/s390/mm/fault.c
@@ -352,7 +352,7 @@ good_area:
 	 * make sure we exit gracefully rather than endlessly redo
 	 * the fault.
 	 */
-	fault = handle_mm_fault(mm, vma, address, write);
+	fault = handle_mm_fault(mm, vma, address, write ? FAULT_FLAG_WRITE : 0);
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM) {
 			up_read(&mm->mmap_sem);
diff --git a/arch/sh/mm/fault_32.c b/arch/sh/mm/fault_32.c
index 2c50f80..cc8ddbd 100644
--- a/arch/sh/mm/fault_32.c
+++ b/arch/sh/mm/fault_32.c
@@ -133,7 +133,7 @@ good_area:
 	 * the fault.
 	 */
 survive:
-	fault = handle_mm_fault(mm, vma, address, writeaccess);
+	fault = handle_mm_fault(mm, vma, address, writeaccess ? FAULT_FLAG_WRITE : 0);
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
diff --git a/arch/sh/mm/tlbflush_64.c b/arch/sh/mm/tlbflush_64.c
index 7876997..fcbb6e1 100644
--- a/arch/sh/mm/tlbflush_64.c
+++ b/arch/sh/mm/tlbflush_64.c
@@ -187,7 +187,7 @@ good_area:
 	 * the fault.
 	 */
 survive:
-	fault = handle_mm_fault(mm, vma, address, writeaccess);
+	fault = handle_mm_fault(mm, vma, address, writeaccess ? FAULT_FLAG_WRITE : 0);
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
diff --git a/arch/sparc/mm/fault_32.c b/arch/sparc/mm/fault_32.c
index 12e447f..a5e30c6 100644
--- a/arch/sparc/mm/fault_32.c
+++ b/arch/sparc/mm/fault_32.c
@@ -241,7 +241,7 @@ good_area:
 	 * make sure we exit gracefully rather than endlessly redo
 	 * the fault.
 	 */
-	fault = handle_mm_fault(mm, vma, address, write);
+	fault = handle_mm_fault(mm, vma, address, write ? FAULT_FLAG_WRITE : 0);
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
@@ -484,7 +484,7 @@ good_area:
 		if(!(vma->vm_flags & (VM_READ | VM_EXEC)))
 			goto bad_area;
 	}
-	switch (handle_mm_fault(mm, vma, address, write)) {
+	switch (handle_mm_fault(mm, vma, address, write ? FAULT_FLAG_WRITE : 0)) {
 	case VM_FAULT_SIGBUS:
 	case VM_FAULT_OOM:
 		goto do_sigbus;
diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c
index 4ab8993..e5620b2 100644
--- a/arch/sparc/mm/fault_64.c
+++ b/arch/sparc/mm/fault_64.c
@@ -398,7 +398,7 @@ good_area:
 			goto bad_area;
 	}
 
-	fault = handle_mm_fault(mm, vma, address, (fault_code & FAULT_CODE_WRITE));
+	fault = handle_mm_fault(mm, vma, address, (fault_code & FAULT_CODE_WRITE) ? FAULT_FLAG_WRITE : 0);
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
diff --git a/arch/um/kernel/trap.c b/arch/um/kernel/trap.c
index 7384d8a..637c650 100644
--- a/arch/um/kernel/trap.c
+++ b/arch/um/kernel/trap.c
@@ -65,7 +65,7 @@ good_area:
 	do {
 		int fault;
 
-		fault = handle_mm_fault(mm, vma, address, is_write);
+		fault = handle_mm_fault(mm, vma, address, is_write ? FAULT_FLAG_WRITE : 0);
 		if (unlikely(fault & VM_FAULT_ERROR)) {
 			if (fault & VM_FAULT_OOM) {
 				goto out_of_memory;
diff --git a/arch/x86/crypto/aesni-intel_asm.S b/arch/x86/crypto/aesni-intel_asm.S
index caba996..eb0566e 100644
--- a/arch/x86/crypto/aesni-intel_asm.S
+++ b/arch/x86/crypto/aesni-intel_asm.S
@@ -845,7 +845,7 @@ ENTRY(aesni_cbc_enc)
  */
 ENTRY(aesni_cbc_dec)
 	cmp $16, LEN
-	jb .Lcbc_dec_ret
+	jb .Lcbc_dec_just_ret
 	mov 480(KEYP), KLEN
 	add $240, KEYP
 	movups (IVP), IV
@@ -891,6 +891,7 @@ ENTRY(aesni_cbc_dec)
 	add $16, OUTP
 	cmp $16, LEN
 	jge .Lcbc_dec_loop1
-	movups IV, (IVP)
 .Lcbc_dec_ret:
+	movups IV, (IVP)
+.Lcbc_dec_just_ret:
 	ret
diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c
index 4e66339..c580c5e 100644
--- a/arch/x86/crypto/aesni-intel_glue.c
+++ b/arch/x86/crypto/aesni-intel_glue.c
@@ -198,6 +198,7 @@ static int ecb_encrypt(struct blkcipher_desc *desc,
 
 	blkcipher_walk_init(&walk, dst, src, nbytes);
 	err = blkcipher_walk_virt(desc, &walk);
+	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
 
 	kernel_fpu_begin();
 	while ((nbytes = walk.nbytes)) {
@@ -221,6 +222,7 @@ static int ecb_decrypt(struct blkcipher_desc *desc,
 
 	blkcipher_walk_init(&walk, dst, src, nbytes);
 	err = blkcipher_walk_virt(desc, &walk);
+	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
 
 	kernel_fpu_begin();
 	while ((nbytes = walk.nbytes)) {
@@ -266,6 +268,7 @@ static int cbc_encrypt(struct blkcipher_desc *desc,
 
 	blkcipher_walk_init(&walk, dst, src, nbytes);
 	err = blkcipher_walk_virt(desc, &walk);
+	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
 
 	kernel_fpu_begin();
 	while ((nbytes = walk.nbytes)) {
@@ -289,6 +292,7 @@ static int cbc_decrypt(struct blkcipher_desc *desc,
 
 	blkcipher_walk_init(&walk, dst, src, nbytes);
 	err = blkcipher_walk_virt(desc, &walk);
+	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
 
 	kernel_fpu_begin();
 	while ((nbytes = walk.nbytes)) {
diff --git a/arch/x86/crypto/fpu.c b/arch/x86/crypto/fpu.c
index 5f9781a..daef6cd 100644
--- a/arch/x86/crypto/fpu.c
+++ b/arch/x86/crypto/fpu.c
@@ -48,7 +48,7 @@ static int crypto_fpu_encrypt(struct blkcipher_desc *desc_in,
 	struct blkcipher_desc desc = {
 		.tfm = child,
 		.info = desc_in->info,
-		.flags = desc_in->flags,
+		.flags = desc_in->flags & ~CRYPTO_TFM_REQ_MAY_SLEEP,
 	};
 
 	kernel_fpu_begin();
@@ -67,7 +67,7 @@ static int crypto_fpu_decrypt(struct blkcipher_desc *desc_in,
 	struct blkcipher_desc desc = {
 		.tfm = child,
 		.info = desc_in->info,
-		.flags = desc_in->flags,
+		.flags = desc_in->flags & ~CRYPTO_TFM_REQ_MAY_SLEEP,
 	};
 
 	kernel_fpu_begin();
diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index 02ecb30..103f1dd 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -42,6 +42,7 @@
 
 #else /* ...!ASSEMBLY */
 
+#include <linux/kernel.h>
 #include <linux/stringify.h>
 
 #ifdef CONFIG_SMP
@@ -155,6 +156,15 @@ 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/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index 9c3f082..29a3eef 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -124,7 +124,7 @@ static void * __init pcpu_alloc_bootmem(unsigned int cpu, unsigned long size,
 }
 
 /*
- * Remap allocator
+ * 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.
@@ -137,105 +137,185 @@ static void * __init pcpu_alloc_bootmem(unsigned int cpu, unsigned long size,
  * better than only using 4k mappings while still being NUMA friendly.
  */
 #ifdef CONFIG_NEED_MULTIPLE_NODES
-static size_t pcpur_size __initdata;
-static void **pcpur_ptrs __initdata;
+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 pcpur_get_page(unsigned int cpu, int pageno)
+static struct page * __init pcpul_get_page(unsigned int cpu, int pageno)
 {
 	size_t off = (size_t)pageno << PAGE_SHIFT;
 
-	if (off >= pcpur_size)
+	if (off >= pcpul_size)
 		return NULL;
 
-	return virt_to_page(pcpur_ptrs[cpu] + off);
+	return virt_to_page(pcpul_map[cpu].ptr + off);
 }
 
-static ssize_t __init setup_pcpu_remap(size_t static_size)
+static ssize_t __init setup_pcpu_lpage(size_t static_size, bool chosen)
 {
-	static struct vm_struct vm;
-	size_t ptrs_size, dyn_size;
+	size_t map_size, dyn_size;
 	unsigned int cpu;
+	int i, j;
 	ssize_t ret;
 
-	/*
-	 * If large page isn't supported, there's no benefit in doing
-	 * this.  Also, on non-NUMA, embedding is better.
-	 *
-	 * NOTE: disabled for now.
-	 */
-	if (true || !cpu_has_pse || !pcpu_need_numa())
+	if (!chosen) {
+		size_t vm_size = VMALLOC_END - VMALLOC_START;
+		size_t tot_size = num_possible_cpus() * 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.
 	 */
-	pcpur_size = PFN_ALIGN(static_size + PERCPU_MODULE_RESERVE +
+	pcpul_size = PFN_ALIGN(static_size + PERCPU_MODULE_RESERVE +
 			       PERCPU_DYNAMIC_RESERVE);
-	if (pcpur_size > PMD_SIZE) {
+	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 = pcpur_size - static_size - PERCPU_FIRST_CHUNK_RESERVE;
+	dyn_size = pcpul_size - static_size - PERCPU_FIRST_CHUNK_RESERVE;
 
 	/* allocate pointer array and alloc large pages */
-	ptrs_size = PFN_ALIGN(num_possible_cpus() * sizeof(pcpur_ptrs[0]));
-	pcpur_ptrs = alloc_bootmem(ptrs_size);
+	map_size = PFN_ALIGN(num_possible_cpus() * sizeof(pcpul_map[0]));
+	pcpul_map = alloc_bootmem(map_size);
 
 	for_each_possible_cpu(cpu) {
-		pcpur_ptrs[cpu] = pcpu_alloc_bootmem(cpu, PMD_SIZE, PMD_SIZE);
-		if (!pcpur_ptrs[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 pcpur_size bytes and give back the rest.
+		 * 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(pcpur_ptrs[cpu] + pcpur_size),
-			     PMD_SIZE - pcpur_size);
+		free_bootmem(__pa(pcpul_map[cpu].ptr + pcpul_size),
+			     PMD_SIZE - pcpul_size);
 
-		memcpy(pcpur_ptrs[cpu], __per_cpu_load, static_size);
+		memcpy(pcpul_map[cpu].ptr, __per_cpu_load, static_size);
 	}
 
 	/* allocate address and map */
-	vm.flags = VM_ALLOC;
-	vm.size = num_possible_cpus() * PMD_SIZE;
-	vm_area_register_early(&vm, PMD_SIZE);
+	pcpul_vm.flags = VM_ALLOC;
+	pcpul_vm.size = num_possible_cpus() * PMD_SIZE;
+	vm_area_register_early(&pcpul_vm, PMD_SIZE);
 
 	for_each_possible_cpu(cpu) {
-		pmd_t *pmd;
+		pmd_t *pmd, pmd_v;
 
-		pmd = populate_extra_pmd((unsigned long)vm.addr
-					 + cpu * PMD_SIZE);
-		set_pmd(pmd, pfn_pmd(page_to_pfn(virt_to_page(pcpur_ptrs[cpu])),
-				     PAGE_KERNEL_LARGE));
+		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", vm.addr, static_size);
+		"%zu bytes\n", pcpul_vm.addr, static_size);
 
-	ret = pcpu_setup_first_chunk(pcpur_get_page, static_size,
+	ret = pcpu_setup_first_chunk(pcpul_get_page, static_size,
 				     PERCPU_FIRST_CHUNK_RESERVE, dyn_size,
-				     PMD_SIZE, vm.addr, NULL);
-	goto out_free_ar;
+				     PMD_SIZE, pcpul_vm.addr, NULL);
+
+	/* sort pcpul_map array for pcpu_lpage_remapped() */
+	for (i = 0; i < num_possible_cpus() - 1; i++)
+		for (j = i + 1; j < num_possible_cpus(); 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 (pcpur_ptrs[cpu])
-			free_bootmem(__pa(pcpur_ptrs[cpu]), PMD_SIZE);
-	ret = -ENOMEM;
-out_free_ar:
-	free_bootmem(__pa(pcpur_ptrs), ptrs_size);
-	return ret;
+		if (pcpul_map[cpu].ptr)
+			free_bootmem(__pa(pcpul_map[cpu].ptr), pcpul_size);
+	free_bootmem(__pa(pcpul_map), map_size);
+	return -ENOMEM;
+}
+
+/**
+ * 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)
+{
+	void *pmd_addr = (void *)((unsigned long)kaddr & PMD_MASK);
+	unsigned long offset = (unsigned long)kaddr & ~PMD_MASK;
+	int left = 0, right = num_possible_cpus() - 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;
 }
 #else
-static ssize_t __init setup_pcpu_remap(size_t static_size)
+static ssize_t __init setup_pcpu_lpage(size_t static_size, bool chosen)
 {
 	return -EINVAL;
 }
@@ -249,7 +329,7 @@ static ssize_t __init setup_pcpu_remap(size_t static_size)
  * mapping so that it can use PMD mapping without additional TLB
  * pressure.
  */
-static ssize_t __init setup_pcpu_embed(size_t static_size)
+static ssize_t __init setup_pcpu_embed(size_t static_size, bool chosen)
 {
 	size_t reserve = PERCPU_MODULE_RESERVE + PERCPU_DYNAMIC_RESERVE;
 
@@ -258,7 +338,7 @@ static ssize_t __init setup_pcpu_embed(size_t static_size)
 	 * this.  Also, embedding allocation doesn't play well with
 	 * NUMA.
 	 */
-	if (!cpu_has_pse || pcpu_need_numa())
+	if (!chosen && (!cpu_has_pse || pcpu_need_numa()))
 		return -EINVAL;
 
 	return pcpu_embed_first_chunk(static_size, PERCPU_FIRST_CHUNK_RESERVE,
@@ -308,8 +388,11 @@ static ssize_t __init setup_pcpu_4k(size_t static_size)
 			void *ptr;
 
 			ptr = pcpu_alloc_bootmem(cpu, PAGE_SIZE, PAGE_SIZE);
-			if (!ptr)
+			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);
@@ -333,6 +416,16 @@ out_free_ar:
 	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
@@ -346,11 +439,6 @@ static inline void setup_percpu_segment(int cpu)
 #endif
 }
 
-/*
- * Great future plan:
- * Declare PDA itself and support (irqstack,tss,pgd) as per cpu data.
- * Always point %gs to its beginning
- */
 void __init setup_per_cpu_areas(void)
 {
 	size_t static_size = __per_cpu_end - __per_cpu_start;
@@ -367,9 +455,26 @@ void __init setup_per_cpu_areas(void)
 	 * of large page mappings.  Please read comments on top of
 	 * each allocator for details.
 	 */
-	ret = setup_pcpu_remap(static_size);
-	if (ret < 0)
-		ret = setup_pcpu_embed(static_size);
+	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);
+	}
 	if (ret < 0)
 		ret = setup_pcpu_4k(static_size);
 	if (ret < 0)
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index c403526..78a5fff 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -1113,7 +1113,7 @@ good_area:
 	 * make sure we exit gracefully rather than endlessly redo
 	 * the fault:
 	 */
-	fault = handle_mm_fault(mm, vma, address, write);
+	fault = handle_mm_fault(mm, vma, address, write ? FAULT_FLAG_WRITE : 0);
 
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		mm_fault_error(regs, error_code, address, fault);
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index 3cfe9ce..1b734d7 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -11,6 +11,7 @@
 #include <linux/interrupt.h>
 #include <linux/seq_file.h>
 #include <linux/debugfs.h>
+#include <linux/pfn.h>
 
 #include <asm/e820.h>
 #include <asm/processor.h>
@@ -681,8 +682,9 @@ static int __change_page_attr_set_clr(struct cpa_data *cpa, int checkalias);
 static int cpa_process_alias(struct cpa_data *cpa)
 {
 	struct cpa_data alias_cpa;
-	int ret = 0;
-	unsigned long temp_cpa_vaddr, vaddr;
+	unsigned long laddr = (unsigned long)__va(cpa->pfn << PAGE_SHIFT);
+	unsigned long vaddr, remapped;
+	int ret;
 
 	if (cpa->pfn >= max_pfn_mapped)
 		return 0;
@@ -706,42 +708,55 @@ static int cpa_process_alias(struct cpa_data *cpa)
 		    PAGE_OFFSET + (max_pfn_mapped << PAGE_SHIFT)))) {
 
 		alias_cpa = *cpa;
-		temp_cpa_vaddr = (unsigned long) __va(cpa->pfn << PAGE_SHIFT);
-		alias_cpa.vaddr = &temp_cpa_vaddr;
+		alias_cpa.vaddr = &laddr;
 		alias_cpa.flags &= ~(CPA_PAGES_ARRAY | CPA_ARRAY);
 
-
 		ret = __change_page_attr_set_clr(&alias_cpa, 0);
+		if (ret)
+			return ret;
 	}
 
 #ifdef CONFIG_X86_64
-	if (ret)
-		return ret;
 	/*
-	 * No need to redo, when the primary call touched the high
-	 * mapping already:
-	 */
-	if (within(vaddr, (unsigned long) _text, _brk_end))
-		return 0;
-
-	/*
-	 * If the physical address is inside the kernel map, we need
+	 * If the primary call didn't touch the high mapping already
+	 * and the physical address is inside the kernel map, we need
 	 * to touch the high mapped kernel as well:
 	 */
-	if (!within(cpa->pfn, highmap_start_pfn(), highmap_end_pfn()))
-		return 0;
+	if (!within(vaddr, (unsigned long)_text, _brk_end) &&
+	    within(cpa->pfn, highmap_start_pfn(), highmap_end_pfn())) {
+		unsigned long temp_cpa_vaddr = (cpa->pfn << PAGE_SHIFT) +
+					       __START_KERNEL_map - phys_base;
+		alias_cpa = *cpa;
+		alias_cpa.vaddr = &temp_cpa_vaddr;
+		alias_cpa.flags &= ~(CPA_PAGES_ARRAY | CPA_ARRAY);
 
-	alias_cpa = *cpa;
-	temp_cpa_vaddr = (cpa->pfn << PAGE_SHIFT) + __START_KERNEL_map - phys_base;
-	alias_cpa.vaddr = &temp_cpa_vaddr;
-	alias_cpa.flags &= ~(CPA_PAGES_ARRAY | CPA_ARRAY);
+		/*
+		 * The high mapping range is imprecise, so ignore the
+		 * return value.
+		 */
+		__change_page_attr_set_clr(&alias_cpa, 0);
+	}
+#endif
 
 	/*
-	 * The high mapping range is imprecise, so ignore the return value.
+	 * 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.
 	 */
-	__change_page_attr_set_clr(&alias_cpa, 0);
-#endif
-	return ret;
+	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;
 }
 
 static int __change_page_attr_set_clr(struct cpa_data *cpa, int checkalias)
diff --git a/arch/xtensa/mm/fault.c b/arch/xtensa/mm/fault.c
index bdd860d..bc07333 100644
--- a/arch/xtensa/mm/fault.c
+++ b/arch/xtensa/mm/fault.c
@@ -106,7 +106,7 @@ good_area:
 	 * the fault.
 	 */
 survive:
-	fault = handle_mm_fault(mm, vma, address, is_write);
+	fault = handle_mm_fault(mm, vma, address, is_write ? FAULT_FLAG_WRITE : 0);
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;