20 files changed, 221 insertions, 156 deletions

diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h
index 548da3aa0a30..d58fc4e4149c 100644
--- a/arch/powerpc/include/asm/exception-64s.h
+++ b/arch/powerpc/include/asm/exception-64s.h
@@ -288,13 +288,6 @@ label##_hv:								\
 /* Exception addition: Hard disable interrupts */
 #define DISABLE_INTS	SOFT_DISABLE_INTS(r10,r11)
 
-/* Exception addition: Keep interrupt state */
-#define ENABLE_INTS				\
-	ld	r11,PACAKMSR(r13);		\
-	ld	r12,_MSR(r1);			\
-	rlwimi	r11,r12,0,MSR_EE;		\
-	mtmsrd	r11,1
-
 #define ADD_NVGPRS				\
 	bl	.save_nvgprs
 
diff --git a/arch/powerpc/include/asm/irq.h b/arch/powerpc/include/asm/irq.h
index e648af92ced1..0e40843a1c6e 100644
--- a/arch/powerpc/include/asm/irq.h
+++ b/arch/powerpc/include/asm/irq.h
@@ -18,10 +18,6 @@
 #include <linux/atomic.h>
 
 
-/* Define a way to iterate across irqs. */
-#define for_each_irq(i) \
-	for ((i) = 0; (i) < NR_IRQS; ++(i))
-
 extern atomic_t ppc_n_lost_interrupts;
 
 /* This number is used when no interrupt has been assigned */
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index f8a7a1a1a9f4..ef2074c3e906 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -588,23 +588,19 @@ _GLOBAL(ret_from_except_lite)
 fast_exc_return_irq:
 restore:
 	/*
-	 * This is the main kernel exit path, we first check if we
-	 * have to change our interrupt state.
+	 * This is the main kernel exit path. First we check if we
+	 * are about to re-enable interrupts
 	 */
 	ld	r5,SOFTE(r1)
 	lbz	r6,PACASOFTIRQEN(r13)
-	cmpwi	cr1,r5,0
-	cmpw	cr0,r5,r6
-	beq	cr0,4f
+	cmpwi	cr0,r5,0
+	beq	restore_irq_off
 
-	/* We do, handle disable first, which is easy */
-	bne	cr1,3f;
- 	li	r0,0
-	stb	r0,PACASOFTIRQEN(r13);
-	TRACE_DISABLE_INTS
-	b	4f
+	/* We are enabling, were we already enabled ? Yes, just return */
+	cmpwi	cr0,r6,1
+	beq	cr0,do_restore
 
-3:	/*
+	/*
 	 * We are about to soft-enable interrupts (we are hard disabled
 	 * at this point). We check if there's anything that needs to
 	 * be replayed first.
@@ -626,7 +622,7 @@ restore_no_replay:
 	/*
 	 * Final return path. BookE is handled in a different file
 	 */
-4:
+do_restore:
 #ifdef CONFIG_PPC_BOOK3E
 	b	.exception_return_book3e
 #else
@@ -700,6 +696,25 @@ fast_exception_return:
 #endif /* CONFIG_PPC_BOOK3E */
 
 	/*
+	 * We are returning to a context with interrupts soft disabled.
+	 *
+	 * However, we may also about to hard enable, so we need to
+	 * make sure that in this case, we also clear PACA_IRQ_HARD_DIS
+	 * or that bit can get out of sync and bad things will happen
+	 */
+restore_irq_off:
+	ld	r3,_MSR(r1)
+	lbz	r7,PACAIRQHAPPENED(r13)
+	andi.	r0,r3,MSR_EE
+	beq	1f
+	rlwinm	r7,r7,0,~PACA_IRQ_HARD_DIS
+	stb	r7,PACAIRQHAPPENED(r13)
+1:	li	r0,0
+	stb	r0,PACASOFTIRQEN(r13);
+	TRACE_DISABLE_INTS
+	b	do_restore
+
+	/*
 	 * Something did happen, check if a re-emit is needed
 	 * (this also clears paca->irq_happened)
 	 */
@@ -748,6 +763,9 @@ restore_check_irq_replay:
 #endif /* CONFIG_PPC_BOOK3E */
 1:	b	.ret_from_except /* What else to do here ? */
  
+
+
+3:
 do_work:
 #ifdef CONFIG_PREEMPT
 	andi.	r0,r3,MSR_PR	/* Returning to user mode? */
@@ -767,16 +785,6 @@ do_work:
 	SOFT_DISABLE_INTS(r3,r4)
 1:	bl	.preempt_schedule_irq
 
-	/* Hard-disable interrupts again (and update PACA) */
-#ifdef CONFIG_PPC_BOOK3E
-	wrteei	0
-#else
-	ld	r10,PACAKMSR(r13) /* Get kernel MSR without EE */
-	mtmsrd	r10,1
-#endif /* CONFIG_PPC_BOOK3E */
-	li	r0,PACA_IRQ_HARD_DIS
-	stb	r0,PACAIRQHAPPENED(r13)
-
 	/* Re-test flags and eventually loop */
 	clrrdi	r9,r1,THREAD_SHIFT
 	ld	r4,TI_FLAGS(r9)
@@ -787,14 +795,6 @@ do_work:
 user_work:
 #endif /* CONFIG_PREEMPT */
 
-	/* Enable interrupts */
-#ifdef CONFIG_PPC_BOOK3E
-	wrteei	1
-#else
-	ori	r10,r10,MSR_EE
-	mtmsrd	r10,1
-#endif /* CONFIG_PPC_BOOK3E */
-
 	andi.	r0,r4,_TIF_NEED_RESCHED
 	beq	1f
 	bl	.restore_interrupts
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index cb705fdbb458..8f880bc77c56 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -768,8 +768,8 @@ alignment_common:
 	std	r3,_DAR(r1)
 	std	r4,_DSISR(r1)
 	bl	.save_nvgprs
+	DISABLE_INTS
 	addi	r3,r1,STACK_FRAME_OVERHEAD
-	ENABLE_INTS
 	bl	.alignment_exception
 	b	.ret_from_except
 
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 5ec1b2354ca6..641da9e868ce 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -229,6 +229,19 @@ notrace void arch_local_irq_restore(unsigned long en)
 	 */
 	if (unlikely(irq_happened != PACA_IRQ_HARD_DIS))
 		__hard_irq_disable();
+#ifdef CONFIG_TRACE_IRQFLAG
+	else {
+		/*
+		 * We should already be hard disabled here. We had bugs
+		 * where that wasn't the case so let's dbl check it and
+		 * warn if we are wrong. Only do that when IRQ tracing
+		 * is enabled as mfmsr() can be costly.
+		 */
+		if (WARN_ON(mfmsr() & MSR_EE))
+			__hard_irq_disable();
+	}
+#endif /* CONFIG_TRACE_IRQFLAG */
+
 	set_soft_enabled(0);
 
 	/*
@@ -260,11 +273,17 @@ EXPORT_SYMBOL(arch_local_irq_restore);
  * if they are currently disabled. This is typically called before
  * schedule() or do_signal() when returning to userspace. We do it
  * in C to avoid the burden of dealing with lockdep etc...
+ *
+ * NOTE: This is called with interrupts hard disabled but not marked
+ * as such in paca->irq_happened, so we need to resync this.
  */
 void restore_interrupts(void)
 {
-	if (irqs_disabled())
+	if (irqs_disabled()) {
+		local_paca->irq_happened |= PACA_IRQ_HARD_DIS;
 		local_irq_enable();
+	} else
+		__hard_irq_enable();
 }
 
 #endif /* CONFIG_PPC64 */
@@ -330,14 +349,10 @@ void migrate_irqs(void)
 
 	alloc_cpumask_var(&mask, GFP_KERNEL);
 
-	for_each_irq(irq) {
+	for_each_irq_desc(irq, desc) {
 		struct irq_data *data;
 		struct irq_chip *chip;
 
-		desc = irq_to_desc(irq);
-		if (!desc)
-			continue;
-
 		data = irq_desc_get_irq_data(desc);
 		if (irqd_is_per_cpu(data))
 			continue;
diff --git a/arch/powerpc/kernel/machine_kexec.c b/arch/powerpc/kernel/machine_kexec.c
index c957b1202bdc..5df777794403 100644
--- a/arch/powerpc/kernel/machine_kexec.c
+++ b/arch/powerpc/kernel/machine_kexec.c
@@ -23,14 +23,11 @@
 
 void machine_kexec_mask_interrupts(void) {
 	unsigned int i;
+	struct irq_desc *desc;
 
-	for_each_irq(i) {
-		struct irq_desc *desc = irq_to_desc(i);
+	for_each_irq_desc(i, desc) {
 		struct irq_chip *chip;
 
-		if (!desc)
-			continue;
-
 		chip = irq_desc_get_chip(desc);
 		if (!chip)
 			continue;
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index 6aa0c663e247..158972341a2d 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -248,7 +248,7 @@ void _exception(int signr, struct pt_regs *regs, int code, unsigned long addr)
 				   addr, regs->nip, regs->link, code);
 	}
 
-	if (!arch_irq_disabled_regs(regs))
+	if (arch_irqs_disabled() && !arch_irq_disabled_regs(regs))
 		local_irq_enable();
 
 	memset(&info, 0, sizeof(info));
@@ -1019,7 +1019,9 @@ void __kprobes program_check_exception(struct pt_regs *regs)
 		return;
 	}
 
-	local_irq_enable();
+	/* We restore the interrupt state now */
+	if (!arch_irq_disabled_regs(regs))
+		local_irq_enable();
 
 #ifdef CONFIG_MATH_EMULATION
 	/* (reason & REASON_ILLEGAL) would be the obvious thing here,
@@ -1069,6 +1071,10 @@ void alignment_exception(struct pt_regs *regs)
 {
 	int sig, code, fixed = 0;
 
+	/* We restore the interrupt state now */
+	if (!arch_irq_disabled_regs(regs))
+		local_irq_enable();
+
 	/* we don't implement logging of alignment exceptions */
 	if (!(current->thread.align_ctl & PR_UNALIGN_SIGBUS))
 		fixed = fix_alignment(regs);
diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c
index ddc485a529f2..c3beaeef3f60 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_hv.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c
@@ -258,6 +258,8 @@ static long kvmppc_get_guest_page(struct kvm *kvm, unsigned long gfn,
 			    !(memslot->userspace_addr & (s - 1))) {
 				start &= ~(s - 1);
 				pgsize = s;
+				get_page(hpage);
+				put_page(page);
 				page = hpage;
 			}
 		}
@@ -281,11 +283,8 @@ static long kvmppc_get_guest_page(struct kvm *kvm, unsigned long gfn,
 	err = 0;
 
  out:
-	if (got) {
-		if (PageHuge(page))
-			page = compound_head(page);
+	if (got)
 		put_page(page);
-	}
 	return err;
 
  up_err:
@@ -678,8 +677,15 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		SetPageDirty(page);
 
  out_put:
-	if (page)
-		put_page(page);
+	if (page) {
+		/*
+		 * We drop pages[0] here, not page because page might
+		 * have been set to the head page of a compound, but
+		 * we have to drop the reference on the correct tail
+		 * page to match the get inside gup()
+		 */
+		put_page(pages[0]);
+	}
 	return ret;
 
  out_unlock:
@@ -979,6 +985,7 @@ void *kvmppc_pin_guest_page(struct kvm *kvm, unsigned long gpa,
 			pa = *physp;
 		}
 		page = pfn_to_page(pa >> PAGE_SHIFT);
+		get_page(page);
 	} else {
 		hva = gfn_to_hva_memslot(memslot, gfn);
 		npages = get_user_pages_fast(hva, 1, 1, pages);
@@ -991,8 +998,6 @@ void *kvmppc_pin_guest_page(struct kvm *kvm, unsigned long gpa,
 		page = compound_head(page);
 		psize <<= compound_order(page);
 	}
-	if (!kvm->arch.using_mmu_notifiers)
-		get_page(page);
 	offset = gpa & (psize - 1);
 	if (nb_ret)
 		*nb_ret = psize - offset;
@@ -1003,7 +1008,6 @@ void kvmppc_unpin_guest_page(struct kvm *kvm, void *va)
 {
 	struct page *page = virt_to_page(va);
 
-	page = compound_head(page);
 	put_page(page);
 }
 
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 01294a5099dd..108d1f580177 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -1192,8 +1192,6 @@ static void unpin_slot(struct kvm *kvm, int slot_id)
 				continue;
 			pfn = physp[j] >> PAGE_SHIFT;
 			page = pfn_to_page(pfn);
-			if (PageHuge(page))
-				page = compound_head(page);
 			SetPageDirty(page);
 			put_page(page);
 		}
diff --git a/arch/powerpc/net/bpf_jit.h b/arch/powerpc/net/bpf_jit.h
index af1ab5e9a691..5c3cf2d04e41 100644
--- a/arch/powerpc/net/bpf_jit.h
+++ b/arch/powerpc/net/bpf_jit.h
@@ -48,7 +48,13 @@
 /*
  * Assembly helpers from arch/powerpc/net/bpf_jit.S:
  */
-extern u8 sk_load_word[], sk_load_half[], sk_load_byte[], sk_load_byte_msh[];
+#define DECLARE_LOAD_FUNC(func)	\
+	extern u8 func[], func##_negative_offset[], func##_positive_offset[]
+
+DECLARE_LOAD_FUNC(sk_load_word);
+DECLARE_LOAD_FUNC(sk_load_half);
+DECLARE_LOAD_FUNC(sk_load_byte);
+DECLARE_LOAD_FUNC(sk_load_byte_msh);
 
 #define FUNCTION_DESCR_SIZE	24
 
diff --git a/arch/powerpc/net/bpf_jit_64.S b/arch/powerpc/net/bpf_jit_64.S
index ff4506e85cce..55ba3855a97f 100644
--- a/arch/powerpc/net/bpf_jit_64.S
+++ b/arch/powerpc/net/bpf_jit_64.S
@@ -31,14 +31,13 @@
  * then branch directly to slow_path_XXX if required.  (In fact, could
  * load a spare GPR with the address of slow_path_generic and pass size
  * as an argument, making the call site a mtlr, li and bllr.)
- *
- * Technically, the "is addr < 0" check is unnecessary & slowing down
- * the ABS path, as it's statically checked on generation.
  */
 	.globl	sk_load_word
 sk_load_word:
 	cmpdi	r_addr, 0
-	blt	bpf_error
+	blt	bpf_slow_path_word_neg
+	.globl	sk_load_word_positive_offset
+sk_load_word_positive_offset:
 	/* Are we accessing past headlen? */
 	subi	r_scratch1, r_HL, 4
 	cmpd	r_scratch1, r_addr
@@ -51,7 +50,9 @@ sk_load_word:
 	.globl	sk_load_half
 sk_load_half:
 	cmpdi	r_addr, 0
-	blt	bpf_error
+	blt	bpf_slow_path_half_neg
+	.globl	sk_load_half_positive_offset
+sk_load_half_positive_offset:
 	subi	r_scratch1, r_HL, 2
 	cmpd	r_scratch1, r_addr
 	blt	bpf_slow_path_half
@@ -61,7 +62,9 @@ sk_load_half:
 	.globl	sk_load_byte
 sk_load_byte:
 	cmpdi	r_addr, 0
-	blt	bpf_error
+	blt	bpf_slow_path_byte_neg
+	.globl	sk_load_byte_positive_offset
+sk_load_byte_positive_offset:
 	cmpd	r_HL, r_addr
 	ble	bpf_slow_path_byte
 	lbzx	r_A, r_D, r_addr
@@ -69,22 +72,20 @@ sk_load_byte:
 
 /*
  * BPF_S_LDX_B_MSH: ldxb  4*([offset]&0xf)
- * r_addr is the offset value, already known positive
+ * r_addr is the offset value
  */
 	.globl sk_load_byte_msh
 sk_load_byte_msh:
+	cmpdi	r_addr, 0
+	blt	bpf_slow_path_byte_msh_neg
+	.globl sk_load_byte_msh_positive_offset
+sk_load_byte_msh_positive_offset:
 	cmpd	r_HL, r_addr
 	ble	bpf_slow_path_byte_msh
 	lbzx	r_X, r_D, r_addr
 	rlwinm	r_X, r_X, 2, 32-4-2, 31-2
 	blr
 
-bpf_error:
-	/* Entered with cr0 = lt */
-	li	r3, 0
-	/* Generated code will 'blt epilogue', returning 0. */
-	blr
-
 /* Call out to skb_copy_bits:
  * We'll need to back up our volatile regs first; we have
  * local variable space at r1+(BPF_PPC_STACK_BASIC).
@@ -136,3 +137,84 @@ bpf_slow_path_byte_msh:
 	lbz	r_X, BPF_PPC_STACK_BASIC+(2*8)(r1)
 	rlwinm	r_X, r_X, 2, 32-4-2, 31-2
 	blr
+
+/* Call out to bpf_internal_load_pointer_neg_helper:
+ * We'll need to back up our volatile regs first; we have
+ * local variable space at r1+(BPF_PPC_STACK_BASIC).
+ * Allocate a new stack frame here to remain ABI-compliant in
+ * stashing LR.
+ */
+#define sk_negative_common(SIZE)				\
+	mflr	r0;						\
+	std	r0, 16(r1);					\
+	/* R3 goes in parameter space of caller's frame */	\
+	std	r_skb, (BPF_PPC_STACKFRAME+48)(r1);		\
+	std	r_A, (BPF_PPC_STACK_BASIC+(0*8))(r1);		\
+	std	r_X, (BPF_PPC_STACK_BASIC+(1*8))(r1);		\
+	stdu	r1, -BPF_PPC_SLOWPATH_FRAME(r1);		\
+	/* R3 = r_skb, as passed */				\
+	mr	r4, r_addr;					\
+	li	r5, SIZE;					\
+	bl	bpf_internal_load_pointer_neg_helper;		\
+	/* R3 != 0 on success */				\
+	addi	r1, r1, BPF_PPC_SLOWPATH_FRAME;			\
+	ld	r0, 16(r1);					\
+	ld	r_A, (BPF_PPC_STACK_BASIC+(0*8))(r1);		\
+	ld	r_X, (BPF_PPC_STACK_BASIC+(1*8))(r1);		\
+	mtlr	r0;						\
+	cmpldi	r3, 0;						\
+	beq	bpf_error_slow;	/* cr0 = EQ */			\
+	mr	r_addr, r3;					\
+	ld	r_skb, (BPF_PPC_STACKFRAME+48)(r1);		\
+	/* Great success! */
+
+bpf_slow_path_word_neg:
+	lis     r_scratch1,-32	/* SKF_LL_OFF */
+	cmpd	r_addr, r_scratch1	/* addr < SKF_* */
+	blt	bpf_error	/* cr0 = LT */
+	.globl	sk_load_word_negative_offset
+sk_load_word_negative_offset:
+	sk_negative_common(4)
+	lwz	r_A, 0(r_addr)
+	blr
+
+bpf_slow_path_half_neg:
+	lis     r_scratch1,-32	/* SKF_LL_OFF */
+	cmpd	r_addr, r_scratch1	/* addr < SKF_* */
+	blt	bpf_error	/* cr0 = LT */
+	.globl	sk_load_half_negative_offset
+sk_load_half_negative_offset:
+	sk_negative_common(2)
+	lhz	r_A, 0(r_addr)
+	blr
+
+bpf_slow_path_byte_neg:
+	lis     r_scratch1,-32	/* SKF_LL_OFF */
+	cmpd	r_addr, r_scratch1	/* addr < SKF_* */
+	blt	bpf_error	/* cr0 = LT */
+	.globl	sk_load_byte_negative_offset
+sk_load_byte_negative_offset:
+	sk_negative_common(1)
+	lbz	r_A, 0(r_addr)
+	blr
+
+bpf_slow_path_byte_msh_neg:
+	lis     r_scratch1,-32	/* SKF_LL_OFF */
+	cmpd	r_addr, r_scratch1	/* addr < SKF_* */
+	blt	bpf_error	/* cr0 = LT */
+	.globl	sk_load_byte_msh_negative_offset
+sk_load_byte_msh_negative_offset:
+	sk_negative_common(1)
+	lbz	r_X, 0(r_addr)
+	rlwinm	r_X, r_X, 2, 32-4-2, 31-2
+	blr
+
+bpf_error_slow:
+	/* fabricate a cr0 = lt */
+	li	r_scratch1, -1
+	cmpdi	r_scratch1, 0
+bpf_error:
+	/* Entered with cr0 = lt */
+	li	r3, 0
+	/* Generated code will 'blt epilogue', returning 0. */
+	blr
diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c
index 73619d3aeb6c..2dc8b1484845 100644
--- a/arch/powerpc/net/bpf_jit_comp.c
+++ b/arch/powerpc/net/bpf_jit_comp.c
@@ -127,6 +127,9 @@ static void bpf_jit_build_epilogue(u32 *image, struct codegen_context *ctx)
 	PPC_BLR();
 }
 
+#define CHOOSE_LOAD_FUNC(K, func) \
+	((int)K < 0 ? ((int)K >= SKF_LL_OFF ? func##_negative_offset : func) : func##_positive_offset)
+
 /* Assemble the body code between the prologue & epilogue. */
 static int bpf_jit_build_body(struct sk_filter *fp, u32 *image,
 			      struct codegen_context *ctx,
@@ -391,21 +394,16 @@ static int bpf_jit_build_body(struct sk_filter *fp, u32 *image,
 
 			/*** Absolute loads from packet header/data ***/
 		case BPF_S_LD_W_ABS:
-			func = sk_load_word;
+			func = CHOOSE_LOAD_FUNC(K, sk_load_word);
 			goto common_load;
 		case BPF_S_LD_H_ABS:
-			func = sk_load_half;
+			func = CHOOSE_LOAD_FUNC(K, sk_load_half);
 			goto common_load;
 		case BPF_S_LD_B_ABS:
-			func = sk_load_byte;
+			func = CHOOSE_LOAD_FUNC(K, sk_load_byte);
 		common_load:
-			/*
-			 * Load from [K].  Reference with the (negative)
-			 * SKF_NET_OFF/SKF_LL_OFF offsets is unsupported.
-			 */
+			/* Load from [K]. */
 			ctx->seen |= SEEN_DATAREF;
-			if ((int)K < 0)
-				return -ENOTSUPP;
 			PPC_LI64(r_scratch1, func);
 			PPC_MTLR(r_scratch1);
 			PPC_LI32(r_addr, K);
@@ -429,7 +427,7 @@ static int bpf_jit_build_body(struct sk_filter *fp, u32 *image,
 		common_load_ind:
 			/*
 			 * Load from [X + K].  Negative offsets are tested for
-			 * in the helper functions, and result in a 'ret 0'.
+			 * in the helper functions.
 			 */
 			ctx->seen |= SEEN_DATAREF | SEEN_XREG;
 			PPC_LI64(r_scratch1, func);
@@ -443,13 +441,7 @@ static int bpf_jit_build_body(struct sk_filter *fp, u32 *image,
 			break;
 
 		case BPF_S_LDX_B_MSH:
-			/*
-			 * x86 version drops packet (RET 0) when K<0, whereas
-			 * interpreter does allow K<0 (__load_pointer, special
-			 * ancillary data).  common_load returns ENOTSUPP if K<0,
-			 * so we fall back to interpreter & filter works.
-			 */
-			func = sk_load_byte_msh;
+			func = CHOOSE_LOAD_FUNC(K, sk_load_byte_msh);
 			goto common_load;
 			break;
 
diff --git a/arch/powerpc/platforms/cell/axon_msi.c b/arch/powerpc/platforms/cell/axon_msi.c
index d09f3e8e6867..85825b5401e5 100644
--- a/arch/powerpc/platforms/cell/axon_msi.c
+++ b/arch/powerpc/platforms/cell/axon_msi.c
@@ -114,7 +114,7 @@ static void axon_msi_cascade(unsigned int irq, struct irq_desc *desc)
 		pr_devel("axon_msi: woff %x roff %x msi %x\n",
 			  write_offset, msic->read_offset, msi);
 
-		if (msi < NR_IRQS && irq_get_chip_data(msi) == msic) {
+		if (msi < nr_irqs && irq_get_chip_data(msi) == msic) {
 			generic_handle_irq(msi);
 			msic->fifo_virt[idx] = cpu_to_le32(0xffffffff);
 		} else {
@@ -276,9 +276,6 @@ static int axon_msi_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
 	if (rc)
 		return rc;
 
-	/* We rely on being able to stash a virq in a u16 */
-	BUILD_BUG_ON(NR_IRQS > 65536);
-
 	list_for_each_entry(entry, &dev->msi_list, list) {
 		virq = irq_create_direct_mapping(msic->irq_domain);
 		if (virq == NO_IRQ) {
@@ -392,7 +389,8 @@ static int axon_msi_probe(struct platform_device *device)
 	}
 	memset(msic->fifo_virt, 0xff, MSIC_FIFO_SIZE_BYTES);
 
-	msic->irq_domain = irq_domain_add_nomap(dn, 0, &msic_host_ops, msic);
+	/* We rely on being able to stash a virq in a u16, so limit irqs to < 65536 */
+	msic->irq_domain = irq_domain_add_nomap(dn, 65536, &msic_host_ops, msic);
 	if (!msic->irq_domain) {
 		printk(KERN_ERR "axon_msi: couldn't allocate irq_domain for %s\n",
 		       dn->full_name);
diff --git a/arch/powerpc/platforms/cell/beat_interrupt.c b/arch/powerpc/platforms/cell/beat_interrupt.c
index f9a48af335cb..8c6dc42ecf65 100644
--- a/arch/powerpc/platforms/cell/beat_interrupt.c
+++ b/arch/powerpc/platforms/cell/beat_interrupt.c
@@ -248,6 +248,6 @@ void beatic_deinit_IRQ(void)
 {
 	int	i;
 
-	for (i = 1; i < NR_IRQS; i++)
+	for (i = 1; i < nr_irqs; i++)
 		beat_destruct_irq_plug(i);
 }
diff --git a/arch/powerpc/platforms/powermac/pic.c b/arch/powerpc/platforms/powermac/pic.c
index 66ad93de1d55..c4e630576ff2 100644
--- a/arch/powerpc/platforms/powermac/pic.c
+++ b/arch/powerpc/platforms/powermac/pic.c
@@ -57,9 +57,9 @@ static int max_real_irqs;
 
 static DEFINE_RAW_SPINLOCK(pmac_pic_lock);
 
-#define NR_MASK_WORDS	((NR_IRQS + 31) / 32)
-static unsigned long ppc_lost_interrupts[NR_MASK_WORDS];
-static unsigned long ppc_cached_irq_mask[NR_MASK_WORDS];
+/* The max irq number this driver deals with is 128; see max_irqs */
+static DECLARE_BITMAP(ppc_lost_interrupts, 128);
+static DECLARE_BITMAP(ppc_cached_irq_mask, 128);
 static int pmac_irq_cascade = -1;
 static struct irq_domain *pmac_pic_host;
 
diff --git a/arch/powerpc/platforms/pseries/Kconfig b/arch/powerpc/platforms/pseries/Kconfig
index aadbe4f6d537..178a5f300bc9 100644
--- a/arch/powerpc/platforms/pseries/Kconfig
+++ b/arch/powerpc/platforms/pseries/Kconfig
@@ -30,9 +30,9 @@ config PPC_SPLPAR
 	  two or more partitions.
 
 config EEH
-	bool "PCI Extended Error Handling (EEH)" if EXPERT
+	bool
 	depends on PPC_PSERIES && PCI
-	default y if !EXPERT
+	default y
 
 config PSERIES_MSI
        bool
diff --git a/arch/powerpc/sysdev/cpm2_pic.c b/arch/powerpc/sysdev/cpm2_pic.c
index d3be961e2ae7..10386b676d87 100644
--- a/arch/powerpc/sysdev/cpm2_pic.c
+++ b/arch/powerpc/sysdev/cpm2_pic.c
@@ -51,8 +51,7 @@
 static intctl_cpm2_t __iomem *cpm2_intctl;
 
 static struct irq_domain *cpm2_pic_host;
-#define NR_MASK_WORDS   ((NR_IRQS + 31) / 32)
-static unsigned long ppc_cached_irq_mask[NR_MASK_WORDS];
+static unsigned long ppc_cached_irq_mask[2]; /* 2 32-bit registers */
 
 static const u_char irq_to_siureg[] = {
 	1, 1, 1, 1, 1, 1, 1, 1,
diff --git a/arch/powerpc/sysdev/mpc8xx_pic.c b/arch/powerpc/sysdev/mpc8xx_pic.c
index d5f5416be310..b724622c3a0b 100644
--- a/arch/powerpc/sysdev/mpc8xx_pic.c
+++ b/arch/powerpc/sysdev/mpc8xx_pic.c
@@ -18,69 +18,45 @@
 extern int cpm_get_irq(struct pt_regs *regs);
 
 static struct irq_domain *mpc8xx_pic_host;
-#define NR_MASK_WORDS   ((NR_IRQS + 31) / 32)
-static unsigned long ppc_cached_irq_mask[NR_MASK_WORDS];
+static unsigned long mpc8xx_cached_irq_mask;
 static sysconf8xx_t __iomem *siu_reg;
 
-int cpm_get_irq(struct pt_regs *regs);
+static inline unsigned long mpc8xx_irqd_to_bit(struct irq_data *d)
+{
+	return 0x80000000 >> irqd_to_hwirq(d);
+}
 
 static void mpc8xx_unmask_irq(struct irq_data *d)
 {
-	int	bit, word;
-	unsigned int irq_nr = (unsigned int)irqd_to_hwirq(d);
-
-	bit = irq_nr & 0x1f;
-	word = irq_nr >> 5;
-
-	ppc_cached_irq_mask[word] |= (1 << (31-bit));
-	out_be32(&siu_reg->sc_simask, ppc_cached_irq_mask[word]);
+	mpc8xx_cached_irq_mask |= mpc8xx_irqd_to_bit(d);
+	out_be32(&siu_reg->sc_simask, mpc8xx_cached_irq_mask);
 }
 
 static void mpc8xx_mask_irq(struct irq_data *d)
 {
-	int	bit, word;
-	unsigned int irq_nr = (unsigned int)irqd_to_hwirq(d);
-
-	bit = irq_nr & 0x1f;
-	word = irq_nr >> 5;
-
-	ppc_cached_irq_mask[word] &= ~(1 << (31-bit));
-	out_be32(&siu_reg->sc_simask, ppc_cached_irq_mask[word]);
+	mpc8xx_cached_irq_mask &= ~mpc8xx_irqd_to_bit(d);
+	out_be32(&siu_reg->sc_simask, mpc8xx_cached_irq_mask);
 }
 
 static void mpc8xx_ack(struct irq_data *d)
 {
-	int	bit;
-	unsigned int irq_nr = (unsigned int)irqd_to_hwirq(d);
-
-	bit = irq_nr & 0x1f;
-	out_be32(&siu_reg->sc_sipend, 1 << (31-bit));
+	out_be32(&siu_reg->sc_sipend, mpc8xx_irqd_to_bit(d));
 }
 
 static void mpc8xx_end_irq(struct irq_data *d)
 {
-	int bit, word;
-	unsigned int irq_nr = (unsigned int)irqd_to_hwirq(d);
-
-	bit = irq_nr & 0x1f;
-	word = irq_nr >> 5;
-
-	ppc_cached_irq_mask[word] |= (1 << (31-bit));
-	out_be32(&siu_reg->sc_simask, ppc_cached_irq_mask[word]);
+	mpc8xx_cached_irq_mask |= mpc8xx_irqd_to_bit(d);
+	out_be32(&siu_reg->sc_simask, mpc8xx_cached_irq_mask);
 }
 
 static int mpc8xx_set_irq_type(struct irq_data *d, unsigned int flow_type)
 {
-	if (flow_type & IRQ_TYPE_EDGE_FALLING) {
-		irq_hw_number_t hw = (unsigned int)irqd_to_hwirq(d);
+	/* only external IRQ senses are programmable */
+	if ((flow_type & IRQ_TYPE_EDGE_FALLING) && !(irqd_to_hwirq(d) & 1)) {
 		unsigned int siel = in_be32(&siu_reg->sc_siel);
-
-		/* only external IRQ senses are programmable */
-		if ((hw & 1) == 0) {
-			siel |= (0x80000000 >> hw);
-			out_be32(&siu_reg->sc_siel, siel);
-			__irq_set_handler_locked(d->irq, handle_edge_irq);
-		}
+		siel |= mpc8xx_irqd_to_bit(d);
+		out_be32(&siu_reg->sc_siel, siel);
+		__irq_set_handler_locked(d->irq, handle_edge_irq);
 	}
 	return 0;
 }
@@ -132,6 +108,9 @@ static int mpc8xx_pic_host_xlate(struct irq_domain *h, struct device_node *ct,
 		IRQ_TYPE_EDGE_FALLING,
 	};
 
+	if (intspec[0] > 0x1f)
+		return 0;
+
 	*out_hwirq = intspec[0];
 	if (intsize > 1 && intspec[1] < 4)
 		*out_flags = map_pic_senses[intspec[1]];
diff --git a/arch/powerpc/sysdev/scom.c b/arch/powerpc/sysdev/scom.c
index 49a3ece1c6b3..702256a1ca11 100644
--- a/arch/powerpc/sysdev/scom.c
+++ b/arch/powerpc/sysdev/scom.c
@@ -22,6 +22,7 @@
 #include <linux/debugfs.h>
 #include <linux/slab.h>
 #include <linux/export.h>
+#include <asm/debug.h>
 #include <asm/prom.h>
 #include <asm/scom.h>
 
diff --git a/arch/powerpc/sysdev/xics/xics-common.c b/arch/powerpc/sysdev/xics/xics-common.c
index ea5e204e3450..cd1d18db92c6 100644
--- a/arch/powerpc/sysdev/xics/xics-common.c
+++ b/arch/powerpc/sysdev/xics/xics-common.c
@@ -188,6 +188,7 @@ void xics_migrate_irqs_away(void)
 {
 	int cpu = smp_processor_id(), hw_cpu = hard_smp_processor_id();
 	unsigned int irq, virq;
+	struct irq_desc *desc;
 
 	/* If we used to be the default server, move to the new "boot_cpuid" */
 	if (hw_cpu == xics_default_server)
@@ -202,8 +203,7 @@ void xics_migrate_irqs_away(void)
 	/* Allow IPIs again... */
 	icp_ops->set_priority(DEFAULT_PRIORITY);
 
-	for_each_irq(virq) {
-		struct irq_desc *desc;
+	for_each_irq_desc(virq, desc) {
 		struct irq_chip *chip;
 		long server;
 		unsigned long flags;
@@ -212,9 +212,8 @@ void xics_migrate_irqs_away(void)
 		/* We can't set affinity on ISA interrupts */
 		if (virq < NUM_ISA_INTERRUPTS)
 			continue;
-		desc = irq_to_desc(virq);
 		/* We only need to migrate enabled IRQS */
-		if (!desc || !desc->action)
+		if (!desc->action)
 			continue;
 		if (desc->irq_data.domain != xics_host)
 			continue;