20 files changed, 343 insertions, 216 deletions

diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index 54f4fb994e9..ad35f66c69e 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -31,6 +31,7 @@
 #include <linux/kdebug.h>
 #include <linux/perf_event.h>
 #include <linux/magic.h>
+#include <linux/ratelimit.h>
 
 #include <asm/firmware.h>
 #include <asm/page.h>
@@ -346,11 +347,10 @@ bad_area_nosemaphore:
 		return 0;
 	}
 
-	if (is_exec && (error_code & DSISR_PROTFAULT)
-	    && printk_ratelimit())
-		printk(KERN_CRIT "kernel tried to execute NX-protected"
-		       " page (%lx) - exploit attempt? (uid: %d)\n",
-		       address, current_uid());
+	if (is_exec && (error_code & DSISR_PROTFAULT))
+		printk_ratelimited(KERN_CRIT "kernel tried to execute NX-protected"
+				   " page (%lx) - exploit attempt? (uid: %d)\n",
+				   address, current_uid());
 
 	return SIGSEGV;
 
diff --git a/arch/powerpc/mm/hash_low_64.S b/arch/powerpc/mm/hash_low_64.S
index 5b7dd4ea02b..a242b5d7cbe 100644
--- a/arch/powerpc/mm/hash_low_64.S
+++ b/arch/powerpc/mm/hash_low_64.S
@@ -118,7 +118,7 @@ _GLOBAL(__hash_page_4K)
 BEGIN_FTR_SECTION
 	cmpdi	r9,0			/* check segment size */
 	bne	3f
-END_FTR_SECTION_IFSET(CPU_FTR_1T_SEGMENT)
+END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT)
 	/* Calc va and put it in r29 */
 	rldicr	r29,r5,28,63-28
 	rldicl	r3,r3,0,36
@@ -401,7 +401,7 @@ _GLOBAL(__hash_page_4K)
 BEGIN_FTR_SECTION
 	cmpdi	r9,0			/* check segment size */
 	bne	3f
-END_FTR_SECTION_IFSET(CPU_FTR_1T_SEGMENT)
+END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT)
 	/* Calc va and put it in r29 */
 	rldicr	r29,r5,28,63-28		/* r29 = (vsid << 28) */
 	rldicl	r3,r3,0,36		/* r3 = (ea & 0x0fffffff) */
@@ -715,7 +715,7 @@ BEGIN_FTR_SECTION
 	andi.	r0,r31,_PAGE_NO_CACHE
 	/* If so, bail out and refault as a 4k page */
 	bne-	ht64_bail_ok
-END_FTR_SECTION_IFCLR(CPU_FTR_CI_LARGE_PAGE)
+END_MMU_FTR_SECTION_IFCLR(MMU_FTR_CI_LARGE_PAGE)
 	/* Prepare new PTE value (turn access RW into DIRTY, then
 	 * add BUSY and ACCESSED)
 	 */
@@ -736,7 +736,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_CI_LARGE_PAGE)
 BEGIN_FTR_SECTION
 	cmpdi	r9,0			/* check segment size */
 	bne	3f
-END_FTR_SECTION_IFSET(CPU_FTR_1T_SEGMENT)
+END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT)
 	/* Calc va and put it in r29 */
 	rldicr	r29,r5,28,63-28
 	rldicl	r3,r3,0,36
diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c
index 784a400e078..dfd764896db 100644
--- a/arch/powerpc/mm/hash_native_64.c
+++ b/arch/powerpc/mm/hash_native_64.c
@@ -50,9 +50,8 @@ static inline void __tlbie(unsigned long va, int psize, int ssize)
 	case MMU_PAGE_4K:
 		va &= ~0xffful;
 		va |= ssize << 8;
-		asm volatile(ASM_MMU_FTR_IFCLR("tlbie %0,0", PPC_TLBIE(%1,%0),
-					       %2)
-			     : : "r" (va), "r"(0), "i" (MMU_FTR_TLBIE_206)
+		asm volatile(ASM_FTR_IFCLR("tlbie %0,0", PPC_TLBIE(%1,%0), %2)
+			     : : "r" (va), "r"(0), "i" (CPU_FTR_HVMODE_206)
 			     : "memory");
 		break;
 	default:
@@ -61,9 +60,8 @@ static inline void __tlbie(unsigned long va, int psize, int ssize)
 		va |= penc << 12;
 		va |= ssize << 8;
 		va |= 1; /* L */
-		asm volatile(ASM_MMU_FTR_IFCLR("tlbie %0,1", PPC_TLBIE(%1,%0),
-					       %2)
-			     : : "r" (va), "r"(0), "i" (MMU_FTR_TLBIE_206)
+		asm volatile(ASM_FTR_IFCLR("tlbie %0,1", PPC_TLBIE(%1,%0), %2)
+			     : : "r" (va), "r"(0), "i" (CPU_FTR_HVMODE_206)
 			     : "memory");
 		break;
 	}
@@ -98,8 +96,8 @@ static inline void __tlbiel(unsigned long va, int psize, int ssize)
 
 static inline void tlbie(unsigned long va, int psize, int ssize, int local)
 {
-	unsigned int use_local = local && cpu_has_feature(CPU_FTR_TLBIEL);
-	int lock_tlbie = !cpu_has_feature(CPU_FTR_LOCKLESS_TLBIE);
+	unsigned int use_local = local && mmu_has_feature(MMU_FTR_TLBIEL);
+	int lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE);
 
 	if (use_local)
 		use_local = mmu_psize_defs[psize].tlbiel;
@@ -503,7 +501,7 @@ static void native_flush_hash_range(unsigned long number, int local)
 		} pte_iterate_hashed_end();
 	}
 
-	if (cpu_has_feature(CPU_FTR_TLBIEL) &&
+	if (mmu_has_feature(MMU_FTR_TLBIEL) &&
 	    mmu_psize_defs[psize].tlbiel && local) {
 		asm volatile("ptesync":::"memory");
 		for (i = 0; i < number; i++) {
@@ -517,7 +515,7 @@ static void native_flush_hash_range(unsigned long number, int local)
 		}
 		asm volatile("ptesync":::"memory");
 	} else {
-		int lock_tlbie = !cpu_has_feature(CPU_FTR_LOCKLESS_TLBIE);
+		int lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE);
 
 		if (lock_tlbie)
 			raw_spin_lock(&native_tlbie_lock);
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index 58a022d0f46..26b2872b3d0 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -53,6 +53,7 @@
 #include <asm/sections.h>
 #include <asm/spu.h>
 #include <asm/udbg.h>
+#include <asm/code-patching.h>
 
 #ifdef DEBUG
 #define DBG(fmt...) udbg_printf(fmt)
@@ -258,11 +259,11 @@ static int __init htab_dt_scan_seg_sizes(unsigned long node,
 	for (; size >= 4; size -= 4, ++prop) {
 		if (prop[0] == 40) {
 			DBG("1T segment support detected\n");
-			cur_cpu_spec->cpu_features |= CPU_FTR_1T_SEGMENT;
+			cur_cpu_spec->mmu_features |= MMU_FTR_1T_SEGMENT;
 			return 1;
 		}
 	}
-	cur_cpu_spec->cpu_features &= ~CPU_FTR_NO_SLBIE_B;
+	cur_cpu_spec->mmu_features &= ~MMU_FTR_NO_SLBIE_B;
 	return 0;
 }
 
@@ -288,7 +289,7 @@ static int __init htab_dt_scan_page_sizes(unsigned long node,
 	if (prop != NULL) {
 		DBG("Page sizes from device-tree:\n");
 		size /= 4;
-		cur_cpu_spec->cpu_features &= ~(CPU_FTR_16M_PAGE);
+		cur_cpu_spec->mmu_features &= ~(MMU_FTR_16M_PAGE);
 		while(size > 0) {
 			unsigned int shift = prop[0];
 			unsigned int slbenc = prop[1];
@@ -316,7 +317,7 @@ static int __init htab_dt_scan_page_sizes(unsigned long node,
 				break;
 			case 0x18:
 				idx = MMU_PAGE_16M;
-				cur_cpu_spec->cpu_features |= CPU_FTR_16M_PAGE;
+				cur_cpu_spec->mmu_features |= MMU_FTR_16M_PAGE;
 				break;
 			case 0x22:
 				idx = MMU_PAGE_16G;
@@ -411,7 +412,7 @@ static void __init htab_init_page_sizes(void)
 	 * Not in the device-tree, let's fallback on known size
 	 * list for 16M capable GP & GR
 	 */
-	if (cpu_has_feature(CPU_FTR_16M_PAGE))
+	if (mmu_has_feature(MMU_FTR_16M_PAGE))
 		memcpy(mmu_psize_defs, mmu_psize_defaults_gp,
 		       sizeof(mmu_psize_defaults_gp));
  found:
@@ -441,7 +442,7 @@ static void __init htab_init_page_sizes(void)
 		mmu_vmalloc_psize = MMU_PAGE_64K;
 		if (mmu_linear_psize == MMU_PAGE_4K)
 			mmu_linear_psize = MMU_PAGE_64K;
-		if (cpu_has_feature(CPU_FTR_CI_LARGE_PAGE)) {
+		if (mmu_has_feature(MMU_FTR_CI_LARGE_PAGE)) {
 			/*
 			 * Don't use 64k pages for ioremap on pSeries, since
 			 * that would stop us accessing the HEA ethernet.
@@ -547,15 +548,7 @@ int remove_section_mapping(unsigned long start, unsigned long end)
 }
 #endif /* CONFIG_MEMORY_HOTPLUG */
 
-static inline void make_bl(unsigned int *insn_addr, void *func)
-{
-	unsigned long funcp = *((unsigned long *)func);
-	int offset = funcp - (unsigned long)insn_addr;
-
-	*insn_addr = (unsigned int)(0x48000001 | (offset & 0x03fffffc));
-	flush_icache_range((unsigned long)insn_addr, 4+
-			   (unsigned long)insn_addr);
-}
+#define FUNCTION_TEXT(A)	((*(unsigned long *)(A)))
 
 static void __init htab_finish_init(void)
 {
@@ -570,16 +563,33 @@ static void __init htab_finish_init(void)
 	extern unsigned int *ht64_call_hpte_remove;
 	extern unsigned int *ht64_call_hpte_updatepp;
 
-	make_bl(ht64_call_hpte_insert1, ppc_md.hpte_insert);
-	make_bl(ht64_call_hpte_insert2, ppc_md.hpte_insert);
-	make_bl(ht64_call_hpte_remove, ppc_md.hpte_remove);
-	make_bl(ht64_call_hpte_updatepp, ppc_md.hpte_updatepp);
+	patch_branch(ht64_call_hpte_insert1,
+		FUNCTION_TEXT(ppc_md.hpte_insert),
+		BRANCH_SET_LINK);
+	patch_branch(ht64_call_hpte_insert2,
+		FUNCTION_TEXT(ppc_md.hpte_insert),
+		BRANCH_SET_LINK);
+	patch_branch(ht64_call_hpte_remove,
+		FUNCTION_TEXT(ppc_md.hpte_remove),
+		BRANCH_SET_LINK);
+	patch_branch(ht64_call_hpte_updatepp,
+		FUNCTION_TEXT(ppc_md.hpte_updatepp),
+		BRANCH_SET_LINK);
+
 #endif /* CONFIG_PPC_HAS_HASH_64K */
 
-	make_bl(htab_call_hpte_insert1, ppc_md.hpte_insert);
-	make_bl(htab_call_hpte_insert2, ppc_md.hpte_insert);
-	make_bl(htab_call_hpte_remove, ppc_md.hpte_remove);
-	make_bl(htab_call_hpte_updatepp, ppc_md.hpte_updatepp);
+	patch_branch(htab_call_hpte_insert1,
+		FUNCTION_TEXT(ppc_md.hpte_insert),
+		BRANCH_SET_LINK);
+	patch_branch(htab_call_hpte_insert2,
+		FUNCTION_TEXT(ppc_md.hpte_insert),
+		BRANCH_SET_LINK);
+	patch_branch(htab_call_hpte_remove,
+		FUNCTION_TEXT(ppc_md.hpte_remove),
+		BRANCH_SET_LINK);
+	patch_branch(htab_call_hpte_updatepp,
+		FUNCTION_TEXT(ppc_md.hpte_updatepp),
+		BRANCH_SET_LINK);
 }
 
 static void __init htab_initialize(void)
@@ -598,7 +608,7 @@ static void __init htab_initialize(void)
 	/* Initialize page sizes */
 	htab_init_page_sizes();
 
-	if (cpu_has_feature(CPU_FTR_1T_SEGMENT)) {
+	if (mmu_has_feature(MMU_FTR_1T_SEGMENT)) {
 		mmu_kernel_ssize = MMU_SEGSIZE_1T;
 		mmu_highuser_ssize = MMU_SEGSIZE_1T;
 		printk(KERN_INFO "Using 1TB segments\n");
@@ -739,7 +749,7 @@ void __init early_init_mmu(void)
 
 	/* Initialize stab / SLB management except on iSeries
 	 */
-	if (cpu_has_feature(CPU_FTR_SLB))
+	if (mmu_has_feature(MMU_FTR_SLB))
 		slb_initialize();
 	else if (!firmware_has_feature(FW_FEATURE_ISERIES))
 		stab_initialize(get_paca()->stab_real);
@@ -756,7 +766,7 @@ void __cpuinit early_init_mmu_secondary(void)
 	 * in real mode on pSeries and we want a virtual address on
 	 * iSeries anyway
 	 */
-	if (cpu_has_feature(CPU_FTR_SLB))
+	if (mmu_has_feature(MMU_FTR_SLB))
 		slb_initialize();
 	else
 		stab_initialize(get_paca()->stab_addr);
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index 9bb249c3046..0b9a5c1901b 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -529,7 +529,7 @@ static int __init hugetlbpage_init(void)
 {
 	int psize;
 
-	if (!cpu_has_feature(CPU_FTR_16M_PAGE))
+	if (!mmu_has_feature(MMU_FTR_16M_PAGE))
 		return -ENODEV;
 
 	for (psize = 0; psize < MMU_PAGE_COUNT; ++psize) {
diff --git a/arch/powerpc/mm/init_32.c b/arch/powerpc/mm/init_32.c
index d65b591e555..5de0f254dbb 100644
--- a/arch/powerpc/mm/init_32.c
+++ b/arch/powerpc/mm/init_32.c
@@ -223,21 +223,6 @@ void free_initmem(void)
 #undef FREESEC
 }
 
-#ifdef CONFIG_BLK_DEV_INITRD
-void free_initrd_mem(unsigned long start, unsigned long end)
-{
-	if (start < end)
-		printk ("Freeing initrd memory: %ldk freed\n", (end - start) >> 10);
-	for (; start < end; start += PAGE_SIZE) {
-		ClearPageReserved(virt_to_page(start));
-		init_page_count(virt_to_page(start));
-		free_page(start);
-		totalram_pages++;
-	}
-}
-#endif
-
-
 #ifdef CONFIG_8xx /* No 8xx specific .c file to put that in ... */
 void setup_initial_memory_limit(phys_addr_t first_memblock_base,
 				phys_addr_t first_memblock_size)
diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c
index 6374b2196a1..f6dbb4c20e6 100644
--- a/arch/powerpc/mm/init_64.c
+++ b/arch/powerpc/mm/init_64.c
@@ -99,20 +99,6 @@ void free_initmem(void)
 		((unsigned long)__init_end - (unsigned long)__init_begin) >> 10);
 }
 
-#ifdef CONFIG_BLK_DEV_INITRD
-void free_initrd_mem(unsigned long start, unsigned long end)
-{
-	if (start < end)
-		printk ("Freeing initrd memory: %ldk freed\n", (end - start) >> 10);
-	for (; start < end; start += PAGE_SIZE) {
-		ClearPageReserved(virt_to_page(start));
-		init_page_count(virt_to_page(start));
-		free_page(start);
-		totalram_pages++;
-	}
-}
-#endif
-
 static void pgd_ctor(void *addr)
 {
 	memset(addr, 0, PGD_TABLE_SIZE);
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index 57e545b84bf..29d4dde65c4 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -382,6 +382,25 @@ void __init mem_init(void)
 	mem_init_done = 1;
 }
 
+#ifdef CONFIG_BLK_DEV_INITRD
+void __init free_initrd_mem(unsigned long start, unsigned long end)
+{
+	if (start >= end)
+		return;
+
+	start = _ALIGN_DOWN(start, PAGE_SIZE);
+	end = _ALIGN_UP(end, PAGE_SIZE);
+	pr_info("Freeing initrd memory: %ldk freed\n", (end - start) >> 10);
+
+	for (; start < end; start += PAGE_SIZE) {
+		ClearPageReserved(virt_to_page(start));
+		init_page_count(virt_to_page(start));
+		free_page(start);
+		totalram_pages++;
+	}
+}
+#endif
+
 /*
  * This is called when a page has been modified by the kernel.
  * It just marks the page as not i-cache clean.  We do the i-cache
diff --git a/arch/powerpc/mm/mmu_context_hash64.c b/arch/powerpc/mm/mmu_context_hash64.c
index 2535828aa84..3bafc3deca6 100644
--- a/arch/powerpc/mm/mmu_context_hash64.c
+++ b/arch/powerpc/mm/mmu_context_hash64.c
@@ -20,9 +20,205 @@
 #include <linux/idr.h>
 #include <linux/module.h>
 #include <linux/gfp.h>
+#include <linux/slab.h>
 
 #include <asm/mmu_context.h>
 
+#ifdef CONFIG_PPC_ICSWX
+/*
+ * The processor and its L2 cache cause the icswx instruction to
+ * generate a COP_REQ transaction on PowerBus. The transaction has
+ * no address, and the processor does not perform an MMU access
+ * to authenticate the transaction. The command portion of the
+ * PowerBus COP_REQ transaction includes the LPAR_ID (LPID) and
+ * the coprocessor Process ID (PID), which the coprocessor compares
+ * to the authorized LPID and PID held in the coprocessor, to determine
+ * if the process is authorized to generate the transaction.
+ * The data of the COP_REQ transaction is 128-byte or less and is
+ * placed in cacheable memory on a 128-byte cache line boundary.
+ *
+ * The task to use a coprocessor should use use_cop() to allocate
+ * a coprocessor PID before executing icswx instruction. use_cop()
+ * also enables the coprocessor context switching. Drop_cop() is
+ * used to free the coprocessor PID.
+ *
+ * Example:
+ * Host Fabric Interface (HFI) is a PowerPC network coprocessor.
+ * Each HFI have multiple windows. Each HFI window serves as a
+ * network device sending to and receiving from HFI network.
+ * HFI immediate send function uses icswx instruction. The immediate
+ * send function allows small (single cache-line) packets be sent
+ * without using the regular HFI send FIFO and doorbell, which are
+ * much slower than immediate send.
+ *
+ * For each task intending to use HFI immediate send, the HFI driver
+ * calls use_cop() to obtain a coprocessor PID for the task.
+ * The HFI driver then allocate a free HFI window and save the
+ * coprocessor PID to the HFI window to allow the task to use the
+ * HFI window.
+ *
+ * The HFI driver repeatedly creates immediate send packets and
+ * issues icswx instruction to send data through the HFI window.
+ * The HFI compares the coprocessor PID in the CPU PID register
+ * to the PID held in the HFI window to determine if the transaction
+ * is allowed.
+ *
+ * When the task to release the HFI window, the HFI driver calls
+ * drop_cop() to release the coprocessor PID.
+ */
+
+#define COP_PID_NONE 0
+#define COP_PID_MIN (COP_PID_NONE + 1)
+#define COP_PID_MAX (0xFFFF)
+
+static DEFINE_SPINLOCK(mmu_context_acop_lock);
+static DEFINE_IDA(cop_ida);
+
+void switch_cop(struct mm_struct *next)
+{
+	mtspr(SPRN_PID, next->context.cop_pid);
+	mtspr(SPRN_ACOP, next->context.acop);
+}
+
+static int new_cop_pid(struct ida *ida, int min_id, int max_id,
+		       spinlock_t *lock)
+{
+	int index;
+	int err;
+
+again:
+	if (!ida_pre_get(ida, GFP_KERNEL))
+		return -ENOMEM;
+
+	spin_lock(lock);
+	err = ida_get_new_above(ida, min_id, &index);
+	spin_unlock(lock);
+
+	if (err == -EAGAIN)
+		goto again;
+	else if (err)
+		return err;
+
+	if (index > max_id) {
+		spin_lock(lock);
+		ida_remove(ida, index);
+		spin_unlock(lock);
+		return -ENOMEM;
+	}
+
+	return index;
+}
+
+static void sync_cop(void *arg)
+{
+	struct mm_struct *mm = arg;
+
+	if (mm == current->active_mm)
+		switch_cop(current->active_mm);
+}
+
+/**
+ * Start using a coprocessor.
+ * @acop: mask of coprocessor to be used.
+ * @mm: The mm the coprocessor to associate with. Most likely current mm.
+ *
+ * Return a positive PID if successful. Negative errno otherwise.
+ * The returned PID will be fed to the coprocessor to determine if an
+ * icswx transaction is authenticated.
+ */
+int use_cop(unsigned long acop, struct mm_struct *mm)
+{
+	int ret;
+
+	if (!cpu_has_feature(CPU_FTR_ICSWX))
+		return -ENODEV;
+
+	if (!mm || !acop)
+		return -EINVAL;
+
+	/* We need to make sure mm_users doesn't change */
+	down_read(&mm->mmap_sem);
+	spin_lock(mm->context.cop_lockp);
+
+	if (mm->context.cop_pid == COP_PID_NONE) {
+		ret = new_cop_pid(&cop_ida, COP_PID_MIN, COP_PID_MAX,
+				  &mmu_context_acop_lock);
+		if (ret < 0)
+			goto out;
+
+		mm->context.cop_pid = ret;
+	}
+	mm->context.acop |= acop;
+
+	sync_cop(mm);
+
+	/*
+	 * If this is a threaded process then there might be other threads
+	 * running. We need to send an IPI to force them to pick up any
+	 * change in PID and ACOP.
+	 */
+	if (atomic_read(&mm->mm_users) > 1)
+		smp_call_function(sync_cop, mm, 1);
+
+	ret = mm->context.cop_pid;
+
+out:
+	spin_unlock(mm->context.cop_lockp);
+	up_read(&mm->mmap_sem);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(use_cop);
+
+/**
+ * Stop using a coprocessor.
+ * @acop: mask of coprocessor to be stopped.
+ * @mm: The mm the coprocessor associated with.
+ */
+void drop_cop(unsigned long acop, struct mm_struct *mm)
+{
+	int free_pid = COP_PID_NONE;
+
+	if (!cpu_has_feature(CPU_FTR_ICSWX))
+		return;
+
+	if (WARN_ON_ONCE(!mm))
+		return;
+
+	/* We need to make sure mm_users doesn't change */
+	down_read(&mm->mmap_sem);
+	spin_lock(mm->context.cop_lockp);
+
+	mm->context.acop &= ~acop;
+
+	if ((!mm->context.acop) && (mm->context.cop_pid != COP_PID_NONE)) {
+		free_pid = mm->context.cop_pid;
+		mm->context.cop_pid = COP_PID_NONE;
+	}
+
+	sync_cop(mm);
+
+	/*
+	 * If this is a threaded process then there might be other threads
+	 * running. We need to send an IPI to force them to pick up any
+	 * change in PID and ACOP.
+	 */
+	if (atomic_read(&mm->mm_users) > 1)
+		smp_call_function(sync_cop, mm, 1);
+
+	if (free_pid != COP_PID_NONE) {
+		spin_lock(&mmu_context_acop_lock);
+		ida_remove(&cop_ida, free_pid);
+		spin_unlock(&mmu_context_acop_lock);
+	}
+
+	spin_unlock(mm->context.cop_lockp);
+	up_read(&mm->mmap_sem);
+}
+EXPORT_SYMBOL_GPL(drop_cop);
+
+#endif /* CONFIG_PPC_ICSWX */
+
 static DEFINE_SPINLOCK(mmu_context_lock);
 static DEFINE_IDA(mmu_context_ida);
 
@@ -31,7 +227,6 @@ static DEFINE_IDA(mmu_context_ida);
  * Each segment contains 2^28 bytes.  Each context maps 2^44 bytes,
  * so we can support 2^19-1 contexts (19 == 35 + 28 - 44).
  */
-#define NO_CONTEXT	0
 #define MAX_CONTEXT	((1UL << 19) - 1)
 
 int __init_new_context(void)
@@ -79,6 +274,16 @@ int init_new_context(struct task_struct *tsk, struct mm_struct *mm)
 		slice_set_user_psize(mm, mmu_virtual_psize);
 	subpage_prot_init_new_context(mm);
 	mm->context.id = index;
+#ifdef CONFIG_PPC_ICSWX
+	mm->context.cop_lockp = kmalloc(sizeof(spinlock_t), GFP_KERNEL);
+	if (!mm->context.cop_lockp) {
+		__destroy_context(index);
+		subpage_prot_free(mm);
+		mm->context.id = MMU_NO_CONTEXT;
+		return -ENOMEM;
+	}
+	spin_lock_init(mm->context.cop_lockp);
+#endif /* CONFIG_PPC_ICSWX */
 
 	return 0;
 }
@@ -93,7 +298,12 @@ EXPORT_SYMBOL_GPL(__destroy_context);
 
 void destroy_context(struct mm_struct *mm)
 {
+#ifdef CONFIG_PPC_ICSWX
+	drop_cop(mm->context.acop, mm);
+	kfree(mm->context.cop_lockp);
+	mm->context.cop_lockp = NULL;
+#endif /* CONFIG_PPC_ICSWX */
 	__destroy_context(mm->context.id);
 	subpage_prot_free(mm);
-	mm->context.id = NO_CONTEXT;
+	mm->context.id = MMU_NO_CONTEXT;
 }
diff --git a/arch/powerpc/mm/mmu_context_nohash.c b/arch/powerpc/mm/mmu_context_nohash.c
index c0aab52da3a..336807de550 100644
--- a/arch/powerpc/mm/mmu_context_nohash.c
+++ b/arch/powerpc/mm/mmu_context_nohash.c
@@ -338,12 +338,14 @@ static int __cpuinit mmu_context_cpu_notify(struct notifier_block *self,
 		return NOTIFY_OK;
 
 	switch (action) {
-	case CPU_ONLINE:
-	case CPU_ONLINE_FROZEN:
+	case CPU_UP_PREPARE:
+	case CPU_UP_PREPARE_FROZEN:
 		pr_devel("MMU: Allocating stale context map for CPU %d\n", cpu);
 		stale_map[cpu] = kzalloc(CTX_MAP_SIZE, GFP_KERNEL);
 		break;
 #ifdef CONFIG_HOTPLUG_CPU
+	case CPU_UP_CANCELED:
+	case CPU_UP_CANCELED_FROZEN:
 	case CPU_DEAD:
 	case CPU_DEAD_FROZEN:
 		pr_devel("MMU: Freeing stale context map for CPU %d\n", cpu);
@@ -407,7 +409,17 @@ void __init mmu_context_init(void)
 	} else if (mmu_has_feature(MMU_FTR_TYPE_47x)) {
 		first_context = 1;
 		last_context = 65535;
-	} else {
+	} else
+#ifdef CONFIG_PPC_BOOK3E_MMU
+	if (mmu_has_feature(MMU_FTR_TYPE_3E)) {
+		u32 mmucfg = mfspr(SPRN_MMUCFG);
+		u32 pid_bits = (mmucfg & MMUCFG_PIDSIZE_MASK)
+				>> MMUCFG_PIDSIZE_SHIFT;
+		first_context = 1;
+		last_context = (1UL << (pid_bits + 1)) - 1;
+	} else
+#endif
+	{
 		first_context = 1;
 		last_context = 255;
 	}
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index 5ec1dad2a19..2164006fe17 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -311,14 +311,13 @@ EXPORT_SYMBOL_GPL(of_node_to_nid);
 static int __init find_min_common_depth(void)
 {
 	int depth;
-	struct device_node *rtas_root;
 	struct device_node *chosen;
+	struct device_node *root;
 	const char *vec5;
 
-	rtas_root = of_find_node_by_path("/rtas");
-
-	if (!rtas_root)
-		return -1;
+	root = of_find_node_by_path("/rtas");
+	if (!root)
+		root = of_find_node_by_path("/");
 
 	/*
 	 * This property is a set of 32-bit integers, each representing
@@ -332,7 +331,7 @@ static int __init find_min_common_depth(void)
 	 * NUMA boundary and the following are progressively less significant
 	 * boundaries. There can be more than one level of NUMA.
 	 */
-	distance_ref_points = of_get_property(rtas_root,
+	distance_ref_points = of_get_property(root,
 					"ibm,associativity-reference-points",
 					&distance_ref_points_depth);
 
@@ -376,11 +375,11 @@ static int __init find_min_common_depth(void)
 		distance_ref_points_depth = MAX_DISTANCE_REF_POINTS;
 	}
 
-	of_node_put(rtas_root);
+	of_node_put(root);
 	return depth;
 
 err:
-	of_node_put(rtas_root);
+	of_node_put(root);
 	return -1;
 }
 
@@ -1453,7 +1452,7 @@ int arch_update_cpu_topology(void)
 	unsigned int associativity[VPHN_ASSOC_BUFSIZE] = {0};
 	struct sys_device *sysdev;
 
-	for_each_cpu_mask(cpu, cpu_associativity_changes_mask) {
+	for_each_cpu(cpu,&cpu_associativity_changes_mask) {
 		vphn_get_associativity(cpu, associativity);
 		nid = associativity_to_nid(associativity);
 
diff --git a/arch/powerpc/mm/pgtable.c b/arch/powerpc/mm/pgtable.c
index 6a3997f98df..af40c8768a7 100644
--- a/arch/powerpc/mm/pgtable.c
+++ b/arch/powerpc/mm/pgtable.c
@@ -33,110 +33,6 @@
 
 #include "mmu_decl.h"
 
-DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);
-
-#ifdef CONFIG_SMP
-
-/*
- * Handle batching of page table freeing on SMP. Page tables are
- * queued up and send to be freed later by RCU in order to avoid
- * freeing a page table page that is being walked without locks
- */
-
-static DEFINE_PER_CPU(struct pte_freelist_batch *, pte_freelist_cur);
-static unsigned long pte_freelist_forced_free;
-
-struct pte_freelist_batch
-{
-	struct rcu_head	rcu;
-	unsigned int	index;
-	unsigned long	tables[0];
-};
-
-#define PTE_FREELIST_SIZE \
-	((PAGE_SIZE - sizeof(struct pte_freelist_batch)) \
-	  / sizeof(unsigned long))
-
-static void pte_free_smp_sync(void *arg)
-{
-	/* Do nothing, just ensure we sync with all CPUs */
-}
-
-/* This is only called when we are critically out of memory
- * (and fail to get a page in pte_free_tlb).
- */
-static void pgtable_free_now(void *table, unsigned shift)
-{
-	pte_freelist_forced_free++;
-
-	smp_call_function(pte_free_smp_sync, NULL, 1);
-
-	pgtable_free(table, shift);
-}
-
-static void pte_free_rcu_callback(struct rcu_head *head)
-{
-	struct pte_freelist_batch *batch =
-		container_of(head, struct pte_freelist_batch, rcu);
-	unsigned int i;
-
-	for (i = 0; i < batch->index; i++) {
-		void *table = (void *)(batch->tables[i] & ~MAX_PGTABLE_INDEX_SIZE);
-		unsigned shift = batch->tables[i] & MAX_PGTABLE_INDEX_SIZE;
-
-		pgtable_free(table, shift);
-	}
-
-	free_page((unsigned long)batch);
-}
-
-static void pte_free_submit(struct pte_freelist_batch *batch)
-{
-	call_rcu_sched(&batch->rcu, pte_free_rcu_callback);
-}
-
-void pgtable_free_tlb(struct mmu_gather *tlb, void *table, unsigned shift)
-{
-	/* This is safe since tlb_gather_mmu has disabled preemption */
-	struct pte_freelist_batch **batchp = &__get_cpu_var(pte_freelist_cur);
-	unsigned long pgf;
-
-	if (atomic_read(&tlb->mm->mm_users) < 2 ||
-	    cpumask_equal(mm_cpumask(tlb->mm), cpumask_of(smp_processor_id()))){
-		pgtable_free(table, shift);
-		return;
-	}
-
-	if (*batchp == NULL) {
-		*batchp = (struct pte_freelist_batch *)__get_free_page(GFP_ATOMIC);
-		if (*batchp == NULL) {
-			pgtable_free_now(table, shift);
-			return;
-		}
-		(*batchp)->index = 0;
-	}
-	BUG_ON(shift > MAX_PGTABLE_INDEX_SIZE);
-	pgf = (unsigned long)table | shift;
-	(*batchp)->tables[(*batchp)->index++] = pgf;
-	if ((*batchp)->index == PTE_FREELIST_SIZE) {
-		pte_free_submit(*batchp);
-		*batchp = NULL;
-	}
-}
-
-void pte_free_finish(void)
-{
-	/* This is safe since tlb_gather_mmu has disabled preemption */
-	struct pte_freelist_batch **batchp = &__get_cpu_var(pte_freelist_cur);
-
-	if (*batchp == NULL)
-		return;
-	pte_free_submit(*batchp);
-	*batchp = NULL;
-}
-
-#endif /* CONFIG_SMP */
-
 static inline int is_exec_fault(void)
 {
 	return current->thread.regs && TRAP(current->thread.regs) == 0x400;
diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c
index 8dc41c0157f..51f87956f8f 100644
--- a/arch/powerpc/mm/pgtable_32.c
+++ b/arch/powerpc/mm/pgtable_32.c
@@ -133,7 +133,15 @@ ioremap(phys_addr_t addr, unsigned long size)
 EXPORT_SYMBOL(ioremap);
 
 void __iomem *
-ioremap_flags(phys_addr_t addr, unsigned long size, unsigned long flags)
+ioremap_wc(phys_addr_t addr, unsigned long size)
+{
+	return __ioremap_caller(addr, size, _PAGE_NO_CACHE,
+				__builtin_return_address(0));
+}
+EXPORT_SYMBOL(ioremap_wc);
+
+void __iomem *
+ioremap_prot(phys_addr_t addr, unsigned long size, unsigned long flags)
 {
 	/* writeable implies dirty for kernel addresses */
 	if (flags & _PAGE_RW)
@@ -152,7 +160,7 @@ ioremap_flags(phys_addr_t addr, unsigned long size, unsigned long flags)
 
 	return __ioremap_caller(addr, size, flags, __builtin_return_address(0));
 }
-EXPORT_SYMBOL(ioremap_flags);
+EXPORT_SYMBOL(ioremap_prot);
 
 void __iomem *
 __ioremap(phys_addr_t addr, unsigned long size, unsigned long flags)
diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c
index 88927a05cdc..6e595f6496d 100644
--- a/arch/powerpc/mm/pgtable_64.c
+++ b/arch/powerpc/mm/pgtable_64.c
@@ -255,7 +255,17 @@ void __iomem * ioremap(phys_addr_t addr, unsigned long size)
 	return __ioremap_caller(addr, size, flags, caller);
 }
 
-void __iomem * ioremap_flags(phys_addr_t addr, unsigned long size,
+void __iomem * ioremap_wc(phys_addr_t addr, unsigned long size)
+{
+	unsigned long flags = _PAGE_NO_CACHE;
+	void *caller = __builtin_return_address(0);
+
+	if (ppc_md.ioremap)
+		return ppc_md.ioremap(addr, size, flags, caller);
+	return __ioremap_caller(addr, size, flags, caller);
+}
+
+void __iomem * ioremap_prot(phys_addr_t addr, unsigned long size,
 			     unsigned long flags)
 {
 	void *caller = __builtin_return_address(0);
@@ -311,7 +321,8 @@ void iounmap(volatile void __iomem *token)
 }
 
 EXPORT_SYMBOL(ioremap);
-EXPORT_SYMBOL(ioremap_flags);
+EXPORT_SYMBOL(ioremap_wc);
+EXPORT_SYMBOL(ioremap_prot);
 EXPORT_SYMBOL(__ioremap);
 EXPORT_SYMBOL(__ioremap_at);
 EXPORT_SYMBOL(iounmap);
diff --git a/arch/powerpc/mm/slb.c b/arch/powerpc/mm/slb.c
index 1d98ecc8eec..e22276cb67a 100644
--- a/arch/powerpc/mm/slb.c
+++ b/arch/powerpc/mm/slb.c
@@ -24,6 +24,7 @@
 #include <asm/firmware.h>
 #include <linux/compiler.h>
 #include <asm/udbg.h>
+#include <asm/code-patching.h>
 
 
 extern void slb_allocate_realmode(unsigned long ea);
@@ -166,7 +167,7 @@ static inline int esids_match(unsigned long addr1, unsigned long addr2)
 	int esid_1t_count;
 
 	/* System is not 1T segment size capable. */
-	if (!cpu_has_feature(CPU_FTR_1T_SEGMENT))
+	if (!mmu_has_feature(MMU_FTR_1T_SEGMENT))
 		return (GET_ESID(addr1) == GET_ESID(addr2));
 
 	esid_1t_count = (((addr1 >> SID_SHIFT_1T) != 0) +
@@ -201,7 +202,7 @@ void switch_slb(struct task_struct *tsk, struct mm_struct *mm)
 	 */
 	hard_irq_disable();
 	offset = get_paca()->slb_cache_ptr;
-	if (!cpu_has_feature(CPU_FTR_NO_SLBIE_B) &&
+	if (!mmu_has_feature(MMU_FTR_NO_SLBIE_B) &&
 	    offset <= SLB_CACHE_ENTRIES) {
 		int i;
 		asm volatile("isync" : : : "memory");
@@ -249,9 +250,8 @@ void switch_slb(struct task_struct *tsk, struct mm_struct *mm)
 static inline void patch_slb_encoding(unsigned int *insn_addr,
 				      unsigned int immed)
 {
-	*insn_addr = (*insn_addr & 0xffff0000) | immed;
-	flush_icache_range((unsigned long)insn_addr, 4+
-			   (unsigned long)insn_addr);
+	int insn = (*insn_addr & 0xffff0000) | immed;
+	patch_instruction(insn_addr, insn);
 }
 
 void slb_set_size(u16 size)
diff --git a/arch/powerpc/mm/slb_low.S b/arch/powerpc/mm/slb_low.S
index 95ce3558169..ef653dc95b6 100644
--- a/arch/powerpc/mm/slb_low.S
+++ b/arch/powerpc/mm/slb_low.S
@@ -58,7 +58,7 @@ _GLOBAL(slb_miss_kernel_load_linear)
 	li	r11,0
 BEGIN_FTR_SECTION
 	b	slb_finish_load
-END_FTR_SECTION_IFCLR(CPU_FTR_1T_SEGMENT)
+END_MMU_FTR_SECTION_IFCLR(MMU_FTR_1T_SEGMENT)
 	b	slb_finish_load_1T
 
 1:
@@ -87,7 +87,7 @@ _GLOBAL(slb_miss_kernel_load_vmemmap)
 6:
 BEGIN_FTR_SECTION
 	b	slb_finish_load
-END_FTR_SECTION_IFCLR(CPU_FTR_1T_SEGMENT)
+END_MMU_FTR_SECTION_IFCLR(MMU_FTR_1T_SEGMENT)
 	b	slb_finish_load_1T
 
 0:	/* user address: proto-VSID = context << 15 | ESID. First check
@@ -138,11 +138,11 @@ END_FTR_SECTION_IFCLR(CPU_FTR_1T_SEGMENT)
 	ld	r9,PACACONTEXTID(r13)
 BEGIN_FTR_SECTION
 	cmpldi	r10,0x1000
-END_FTR_SECTION_IFSET(CPU_FTR_1T_SEGMENT)
+END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT)
 	rldimi	r10,r9,USER_ESID_BITS,0
 BEGIN_FTR_SECTION
 	bge	slb_finish_load_1T
-END_FTR_SECTION_IFSET(CPU_FTR_1T_SEGMENT)
+END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT)
 	b	slb_finish_load
 
 8:	/* invalid EA */
diff --git a/arch/powerpc/mm/stab.c b/arch/powerpc/mm/stab.c
index 446a01842a7..41e31642a86 100644
--- a/arch/powerpc/mm/stab.c
+++ b/arch/powerpc/mm/stab.c
@@ -243,7 +243,7 @@ void __init stabs_alloc(void)
 {
 	int cpu;
 
-	if (cpu_has_feature(CPU_FTR_SLB))
+	if (mmu_has_feature(MMU_FTR_SLB))
 		return;
 
 	for_each_possible_cpu(cpu) {
diff --git a/arch/powerpc/mm/tlb_hash32.c b/arch/powerpc/mm/tlb_hash32.c
index 690566b66e8..27b863c1494 100644
--- a/arch/powerpc/mm/tlb_hash32.c
+++ b/arch/powerpc/mm/tlb_hash32.c
@@ -71,9 +71,6 @@ void tlb_flush(struct mmu_gather *tlb)
 		 */
 		_tlbia();
 	}
-
-	/* Push out batch of freed page tables */
-	pte_free_finish();
 }
 
 /*
diff --git a/arch/powerpc/mm/tlb_hash64.c b/arch/powerpc/mm/tlb_hash64.c
index c14d09f614f..31f18207970 100644
--- a/arch/powerpc/mm/tlb_hash64.c
+++ b/arch/powerpc/mm/tlb_hash64.c
@@ -155,7 +155,7 @@ void __flush_tlb_pending(struct ppc64_tlb_batch *batch)
 
 void tlb_flush(struct mmu_gather *tlb)
 {
-	struct ppc64_tlb_batch *tlbbatch = &__get_cpu_var(ppc64_tlb_batch);
+	struct ppc64_tlb_batch *tlbbatch = &get_cpu_var(ppc64_tlb_batch);
 
 	/* If there's a TLB batch pending, then we must flush it because the
 	 * pages are going to be freed and we really don't want to have a CPU
@@ -164,8 +164,7 @@ void tlb_flush(struct mmu_gather *tlb)
 	if (tlbbatch->index)
 		__flush_tlb_pending(tlbbatch);
 
-	/* Push out batch of freed page tables */
-	pte_free_finish();
+	put_cpu_var(ppc64_tlb_batch);
 }
 
 /**
diff --git a/arch/powerpc/mm/tlb_nohash.c b/arch/powerpc/mm/tlb_nohash.c
index 2a030d89bbc..0bdad3aecc6 100644
--- a/arch/powerpc/mm/tlb_nohash.c
+++ b/arch/powerpc/mm/tlb_nohash.c
@@ -299,9 +299,6 @@ EXPORT_SYMBOL(flush_tlb_range);
 void tlb_flush(struct mmu_gather *tlb)
 {
 	flush_tlb_mm(tlb->mm);
-
-	/* Push out batch of freed page tables */
-	pte_free_finish();
 }
 
 /*