22 files changed, 203 insertions, 266 deletions

diff --git a/arch/ia64/kernel/Makefile.gate b/arch/ia64/kernel/Makefile.gate
index 1d87f84069b..ab9b03a9adc 100644
--- a/arch/ia64/kernel/Makefile.gate
+++ b/arch/ia64/kernel/Makefile.gate
@@ -10,7 +10,7 @@ quiet_cmd_gate = GATE $@
       cmd_gate = $(CC) -nostdlib $(GATECFLAGS_$(@F)) -Wl,-T,$(filter-out FORCE,$^) -o $@
 
 GATECFLAGS_gate.so = -shared -s -Wl,-soname=linux-gate.so.1 \
-		     $(call ld-option, -Wl$(comma)--hash-style=sysv)
+		     $(call cc-ldoption, -Wl$(comma)--hash-style=sysv)
 $(obj)/gate.so: $(obj)/gate.lds $(obj)/gate.o FORCE
 	$(call if_changed,gate)
 
diff --git a/arch/ia64/kernel/crash.c b/arch/ia64/kernel/crash.c
index f065093f8e9..6631a9dfafd 100644
--- a/arch/ia64/kernel/crash.c
+++ b/arch/ia64/kernel/crash.c
@@ -23,6 +23,7 @@
 int kdump_status[NR_CPUS];
 static atomic_t kdump_cpu_frozen;
 atomic_t kdump_in_progress;
+static int kdump_freeze_monarch;
 static int kdump_on_init = 1;
 static int kdump_on_fatal_mca = 1;
 
@@ -108,10 +109,38 @@ machine_crash_shutdown(struct pt_regs *pt)
 	 */
 	kexec_disable_iosapic();
 #ifdef CONFIG_SMP
+	/*
+	 * If kdump_on_init is set and an INIT is asserted here, kdump will
+	 * be started again via INIT monarch.
+	 */
+	local_irq_disable();
+	ia64_set_psr_mc();	/* mask MCA/INIT */
+	if (atomic_inc_return(&kdump_in_progress) != 1)
+		unw_init_running(kdump_cpu_freeze, NULL);
+
+	/*
+	 * Now this cpu is ready for kdump.
+	 * Stop all others by IPI or INIT.  They could receive INIT from
+	 * outside and might be INIT monarch, but only thing they have to
+	 * do is falling into kdump_cpu_freeze().
+	 *
+	 * If an INIT is asserted here:
+	 * - All receivers might be slaves, since some of cpus could already
+	 *   be frozen and INIT might be masked on monarch.  In this case,
+	 *   all slaves will be frozen soon since kdump_in_progress will let
+	 *   them into DIE_INIT_SLAVE_LEAVE.
+	 * - One might be a monarch, but INIT rendezvous will fail since
+	 *   at least this cpu already have INIT masked so it never join
+	 *   to the rendezvous.  In this case, all slaves and monarch will
+	 *   be frozen soon with no wait since the INIT rendezvous is skipped
+	 *   by kdump_in_progress.
+	 */
 	kdump_smp_send_stop();
 	/* not all cpu response to IPI, send INIT to freeze them */
-	if (kdump_wait_cpu_freeze() && kdump_on_init) 	{
+	if (kdump_wait_cpu_freeze()) {
 		kdump_smp_send_init();
+		/* wait again, don't go ahead if possible */
+		kdump_wait_cpu_freeze();
 	}
 #endif
 }
@@ -129,17 +158,17 @@ void
 kdump_cpu_freeze(struct unw_frame_info *info, void *arg)
 {
 	int cpuid;
+
 	local_irq_disable();
 	cpuid = smp_processor_id();
 	crash_save_this_cpu();
 	current->thread.ksp = (__u64)info->sw - 16;
+
+	ia64_set_psr_mc();	/* mask MCA/INIT and stop reentrance */
+
 	atomic_inc(&kdump_cpu_frozen);
 	kdump_status[cpuid] = 1;
 	mb();
-#ifdef CONFIG_HOTPLUG_CPU
-	if (cpuid != 0)
-		ia64_jump_to_sal(&sal_boot_rendez_state[cpuid]);
-#endif
 	for (;;)
 		cpu_relax();
 }
@@ -150,6 +179,20 @@ kdump_init_notifier(struct notifier_block *self, unsigned long val, void *data)
 	struct ia64_mca_notify_die *nd;
 	struct die_args *args = data;
 
+	if (atomic_read(&kdump_in_progress)) {
+		switch (val) {
+		case DIE_INIT_MONARCH_LEAVE:
+			if (!kdump_freeze_monarch)
+				break;
+			/* fall through */
+		case DIE_INIT_SLAVE_LEAVE:
+		case DIE_INIT_MONARCH_ENTER:
+		case DIE_MCA_RENDZVOUS_LEAVE:
+			unw_init_running(kdump_cpu_freeze, NULL);
+			break;
+		}
+	}
+
 	if (!kdump_on_init && !kdump_on_fatal_mca)
 		return NOTIFY_DONE;
 
@@ -162,43 +205,31 @@ kdump_init_notifier(struct notifier_block *self, unsigned long val, void *data)
 	}
 
 	if (val != DIE_INIT_MONARCH_LEAVE &&
-	    val != DIE_INIT_SLAVE_LEAVE &&
 	    val != DIE_INIT_MONARCH_PROCESS &&
-	    val != DIE_MCA_RENDZVOUS_LEAVE &&
 	    val != DIE_MCA_MONARCH_LEAVE)
 		return NOTIFY_DONE;
 
 	nd = (struct ia64_mca_notify_die *)args->err;
-	/* Reason code 1 means machine check rendezvous*/
-	if ((val == DIE_INIT_MONARCH_LEAVE || val == DIE_INIT_SLAVE_LEAVE
-	    || val == DIE_INIT_MONARCH_PROCESS) && nd->sos->rv_rc == 1)
-		return NOTIFY_DONE;
 
 	switch (val) {
 	case DIE_INIT_MONARCH_PROCESS:
-		if (kdump_on_init) {
-			atomic_set(&kdump_in_progress, 1);
-			*(nd->monarch_cpu) = -1;
+		/* Reason code 1 means machine check rendezvous*/
+		if (kdump_on_init && (nd->sos->rv_rc != 1)) {
+			if (atomic_inc_return(&kdump_in_progress) != 1)
+				kdump_freeze_monarch = 1;
 		}
 		break;
 	case DIE_INIT_MONARCH_LEAVE:
-		if (kdump_on_init)
+		/* Reason code 1 means machine check rendezvous*/
+		if (kdump_on_init && (nd->sos->rv_rc != 1))
 			machine_kdump_on_init();
 		break;
-	case DIE_INIT_SLAVE_LEAVE:
-		if (atomic_read(&kdump_in_progress))
-			unw_init_running(kdump_cpu_freeze, NULL);
-		break;
-	case DIE_MCA_RENDZVOUS_LEAVE:
-		if (atomic_read(&kdump_in_progress))
-			unw_init_running(kdump_cpu_freeze, NULL);
-		break;
 	case DIE_MCA_MONARCH_LEAVE:
 		/* *(nd->data) indicate if MCA is recoverable */
 		if (kdump_on_fatal_mca && !(*(nd->data))) {
-			atomic_set(&kdump_in_progress, 1);
-			*(nd->monarch_cpu) = -1;
-			machine_kdump_on_init();
+			if (atomic_inc_return(&kdump_in_progress) == 1)
+				machine_kdump_on_init();
+			/* We got fatal MCA while kdump!? No way!! */
 		}
 		break;
 	}
diff --git a/arch/ia64/kernel/dma-mapping.c b/arch/ia64/kernel/dma-mapping.c
index 086a2aeb040..f2c1600da09 100644
--- a/arch/ia64/kernel/dma-mapping.c
+++ b/arch/ia64/kernel/dma-mapping.c
@@ -6,6 +6,16 @@ int iommu_detected __read_mostly;
 struct dma_map_ops *dma_ops;
 EXPORT_SYMBOL(dma_ops);
 
+#define PREALLOC_DMA_DEBUG_ENTRIES (1 << 16)
+
+static int __init dma_init(void)
+{
+	dma_debug_init(PREALLOC_DMA_DEBUG_ENTRIES);
+
+	return 0;
+}
+fs_initcall(dma_init);
+
 struct dma_map_ops *dma_get_ops(struct device *dev)
 {
 	return dma_ops;
diff --git a/arch/ia64/kernel/esi.c b/arch/ia64/kernel/esi.c
index ebf4e988e78..d5764a3d74a 100644
--- a/arch/ia64/kernel/esi.c
+++ b/arch/ia64/kernel/esi.c
@@ -65,7 +65,7 @@ static int __init esi_init (void)
 	}
 
 	if (!esi)
-		return -ENODEV;;
+		return -ENODEV;
 
 	systab = __va(esi);
 
diff --git a/arch/ia64/kernel/head.S b/arch/ia64/kernel/head.S
index 23f846de62d..696eff28a0c 100644
--- a/arch/ia64/kernel/head.S
+++ b/arch/ia64/kernel/head.S
@@ -167,7 +167,7 @@ RestRR:											\
 	mov _tmp2=((ia64_rid(IA64_REGION_ID_KERNEL, (num<<61)) << 8) | (pgsize << 2) | vhpt);; \
 	mov rr[_tmp1]=_tmp2
 
-	.section __special_page_section,"ax"
+	__PAGE_ALIGNED_DATA
 
 	.global empty_zero_page
 empty_zero_page:
@@ -181,7 +181,7 @@ swapper_pg_dir:
 halt_msg:
 	stringz "Halting kernel\n"
 
-	.section .text.head,"ax"
+	__REF
 
 	.global start_ap
 
@@ -1130,95 +1130,6 @@ SET_REG(b5);
 #endif /* CONFIG_IA64_BRL_EMU */
 
 #ifdef CONFIG_SMP
-	/*
-	 * This routine handles spinlock contention.  It uses a non-standard calling
-	 * convention to avoid converting leaf routines into interior routines.  Because
-	 * of this special convention, there are several restrictions:
-	 *
-	 * - do not use gp relative variables, this code is called from the kernel
-	 *   and from modules, r1 is undefined.
-	 * - do not use stacked registers, the caller owns them.
-	 * - do not use the scratch stack space, the caller owns it.
-	 * - do not use any registers other than the ones listed below
-	 *
-	 * Inputs:
-	 *   ar.pfs - saved CFM of caller
-	 *   ar.ccv - 0 (and available for use)
-	 *   r27    - flags from spin_lock_irqsave or 0.  Must be preserved.
-	 *   r28    - available for use.
-	 *   r29    - available for use.
-	 *   r30    - available for use.
-	 *   r31    - address of lock, available for use.
-	 *   b6     - return address
-	 *   p14    - available for use.
-	 *   p15    - used to track flag status.
-	 *
-	 * If you patch this code to use more registers, do not forget to update
-	 * the clobber lists for spin_lock() in arch/ia64/include/asm/spinlock.h.
-	 */
-
-#if (__GNUC__ == 3 && __GNUC_MINOR__ < 3)
-
-GLOBAL_ENTRY(ia64_spinlock_contention_pre3_4)
-	.prologue
-	.save ar.pfs, r0	// this code effectively has a zero frame size
-	.save rp, r28
-	.body
-	nop 0
-	tbit.nz p15,p0=r27,IA64_PSR_I_BIT
-	.restore sp		// pop existing prologue after next insn
-	mov b6 = r28
-	.prologue
-	.save ar.pfs, r0
-	.altrp b6
-	.body
-	;;
-(p15)	ssm psr.i		// reenable interrupts if they were on
-				// DavidM says that srlz.d is slow and is not required in this case
-.wait:
-	// exponential backoff, kdb, lockmeter etc. go in here
-	hint @pause
-	ld4 r30=[r31]		// don't use ld4.bias; if it's contended, we won't write the word
-	nop 0
-	;;
-	cmp4.ne p14,p0=r30,r0
-(p14)	br.cond.sptk.few .wait
-(p15)	rsm psr.i		// disable interrupts if we reenabled them
-	br.cond.sptk.few b6	// lock is now free, try to acquire
-	.global ia64_spinlock_contention_pre3_4_end	// for kernprof
-ia64_spinlock_contention_pre3_4_end:
-END(ia64_spinlock_contention_pre3_4)
-
-#else
-
-GLOBAL_ENTRY(ia64_spinlock_contention)
-	.prologue
-	.altrp b6
-	.body
-	tbit.nz p15,p0=r27,IA64_PSR_I_BIT
-	;;
-.wait:
-(p15)	ssm psr.i		// reenable interrupts if they were on
-				// DavidM says that srlz.d is slow and is not required in this case
-.wait2:
-	// exponential backoff, kdb, lockmeter etc. go in here
-	hint @pause
-	ld4 r30=[r31]		// don't use ld4.bias; if it's contended, we won't write the word
-	;;
-	cmp4.ne p14,p0=r30,r0
-	mov r30 = 1
-(p14)	br.cond.sptk.few .wait2
-(p15)	rsm psr.i		// disable interrupts if we reenabled them
-	;;
-	cmpxchg4.acq r30=[r31], r30, ar.ccv
-	;;
-	cmp4.ne p14,p0=r0,r30
-(p14)	br.cond.sptk.few .wait
-
-	br.ret.sptk.many b6	// lock is now taken
-END(ia64_spinlock_contention)
-
-#endif
 
 #ifdef CONFIG_HOTPLUG_CPU
 GLOBAL_ENTRY(ia64_jump_to_sal)
@@ -1242,7 +1153,7 @@ GLOBAL_ENTRY(ia64_jump_to_sal)
 	movl r16=SAL_PSR_BITS_TO_SET;;
 	mov cr.ipsr=r16
 	mov cr.ifs=r0;;
-	rfi;;
+	rfi;;			// note: this unmask MCA/INIT (psr.mc)
 1:
 	/*
 	 * Invalidate all TLB data/inst
diff --git a/arch/ia64/kernel/ia64_ksyms.c b/arch/ia64/kernel/ia64_ksyms.c
index 2d311864e35..14d39e30062 100644
--- a/arch/ia64/kernel/ia64_ksyms.c
+++ b/arch/ia64/kernel/ia64_ksyms.c
@@ -21,6 +21,7 @@ EXPORT_SYMBOL(csum_ipv6_magic);
 
 #include <asm/page.h>
 EXPORT_SYMBOL(clear_page);
+EXPORT_SYMBOL(copy_page);
 
 #ifdef CONFIG_VIRTUAL_MEM_MAP
 #include <linux/bootmem.h>
@@ -60,9 +61,6 @@ EXPORT_SYMBOL(__udivdi3);
 EXPORT_SYMBOL(__moddi3);
 EXPORT_SYMBOL(__umoddi3);
 
-#include <asm/page.h>
-EXPORT_SYMBOL(copy_page);
-
 #if defined(CONFIG_MD_RAID456) || defined(CONFIG_MD_RAID456_MODULE)
 extern void xor_ia64_2(void);
 extern void xor_ia64_3(void);
@@ -86,26 +84,6 @@ EXPORT_SYMBOL(ia64_save_scratch_fpregs);
 #include <asm/unwind.h>
 EXPORT_SYMBOL(unw_init_running);
 
-#ifdef ASM_SUPPORTED
-# ifdef CONFIG_SMP
-#  if (__GNUC__ == 3 && __GNUC_MINOR__ < 3)
-/*
- * This is not a normal routine and we don't want a function descriptor for it, so we use
- * a fake declaration here.
- */
-extern char ia64_spinlock_contention_pre3_4;
-EXPORT_SYMBOL(ia64_spinlock_contention_pre3_4);
-#  else
-/*
- * This is not a normal routine and we don't want a function descriptor for it, so we use
- * a fake declaration here.
- */
-extern char ia64_spinlock_contention;
-EXPORT_SYMBOL(ia64_spinlock_contention);
-#  endif
-# endif
-#endif
-
 #if defined(CONFIG_IA64_ESI) || defined(CONFIG_IA64_ESI_MODULE)
 extern void esi_call_phys (void);
 EXPORT_SYMBOL_GPL(esi_call_phys);
diff --git a/arch/ia64/kernel/init_task.c b/arch/ia64/kernel/init_task.c
index c475fc281be..e253ab8fcbc 100644
--- a/arch/ia64/kernel/init_task.c
+++ b/arch/ia64/kernel/init_task.c
@@ -33,7 +33,8 @@ union {
 		struct thread_info thread_info;
 	} s;
 	unsigned long stack[KERNEL_STACK_SIZE/sizeof (unsigned long)];
-} init_task_mem asm ("init_task") __attribute__((section(".data.init_task"))) = {{
+} init_task_mem asm ("init_task") __init_task_data =
+	{{
 	.task =		INIT_TASK(init_task_mem.s.task),
 	.thread_info =	INIT_THREAD_INFO(init_task_mem.s.task)
 }};
diff --git a/arch/ia64/kernel/iosapic.c b/arch/ia64/kernel/iosapic.c
index c48b03f2b61..dab4d393908 100644
--- a/arch/ia64/kernel/iosapic.c
+++ b/arch/ia64/kernel/iosapic.c
@@ -1072,6 +1072,10 @@ iosapic_init (unsigned long phys_addr, unsigned int gsi_base)
 	}
 
 	addr = ioremap(phys_addr, 0);
+	if (addr == NULL) {
+		spin_unlock_irqrestore(&iosapic_lock, flags);
+		return -ENOMEM;
+	}
 	ver = iosapic_version(addr);
 	if ((err = iosapic_check_gsi_range(gsi_base, ver))) {
 		iounmap(addr);
diff --git a/arch/ia64/kernel/machine_kexec.c b/arch/ia64/kernel/machine_kexec.c
index 0823de1f6eb..3d3aeef4694 100644
--- a/arch/ia64/kernel/machine_kexec.c
+++ b/arch/ia64/kernel/machine_kexec.c
@@ -24,6 +24,8 @@
 #include <asm/delay.h>
 #include <asm/meminit.h>
 #include <asm/processor.h>
+#include <asm/sal.h>
+#include <asm/mca.h>
 
 typedef NORET_TYPE void (*relocate_new_kernel_t)(
 					unsigned long indirection_page,
@@ -85,13 +87,26 @@ static void ia64_machine_kexec(struct unw_frame_info *info, void *arg)
 	void *pal_addr = efi_get_pal_addr();
 	unsigned long code_addr = (unsigned long)page_address(image->control_code_page);
 	int ii;
+	u64 fp, gp;
+	ia64_fptr_t *init_handler = (ia64_fptr_t *)ia64_os_init_on_kdump;
 
 	BUG_ON(!image);
 	if (image->type == KEXEC_TYPE_CRASH) {
 		crash_save_this_cpu();
 		current->thread.ksp = (__u64)info->sw - 16;
+
+		/* Register noop init handler */
+		fp = ia64_tpa(init_handler->fp);
+		gp = ia64_tpa(ia64_getreg(_IA64_REG_GP));
+		ia64_sal_set_vectors(SAL_VECTOR_OS_INIT, fp, gp, 0, fp, gp, 0);
+	} else {
+		/* Unregister init handlers of current kernel */
+		ia64_sal_set_vectors(SAL_VECTOR_OS_INIT, 0, 0, 0, 0, 0, 0);
 	}
 
+	/* Unregister mca handler - No more recovery on current kernel */
+	ia64_sal_set_vectors(SAL_VECTOR_OS_MCA, 0, 0, 0, 0, 0, 0);
+
 	/* Interrupts aren't acceptable while we reboot */
 	local_irq_disable();
 
diff --git a/arch/ia64/kernel/mca.c b/arch/ia64/kernel/mca.c
index 7b30d21c519..d2877a7bfe2 100644
--- a/arch/ia64/kernel/mca.c
+++ b/arch/ia64/kernel/mca.c
@@ -1682,14 +1682,25 @@ ia64_init_handler(struct pt_regs *regs, struct switch_stack *sw,
 
 	if (!sos->monarch) {
 		ia64_mc_info.imi_rendez_checkin[cpu] = IA64_MCA_RENDEZ_CHECKIN_INIT;
+
+#ifdef CONFIG_KEXEC
+		while (monarch_cpu == -1 && !atomic_read(&kdump_in_progress))
+			udelay(1000);
+#else
 		while (monarch_cpu == -1)
-		       cpu_relax();	/* spin until monarch enters */
+			cpu_relax();	/* spin until monarch enters */
+#endif
 
 		NOTIFY_INIT(DIE_INIT_SLAVE_ENTER, regs, (long)&nd, 1);
 		NOTIFY_INIT(DIE_INIT_SLAVE_PROCESS, regs, (long)&nd, 1);
 
+#ifdef CONFIG_KEXEC
+		while (monarch_cpu != -1 && !atomic_read(&kdump_in_progress))
+			udelay(1000);
+#else
 		while (monarch_cpu != -1)
-		       cpu_relax();	/* spin until monarch leaves */
+			cpu_relax();	/* spin until monarch leaves */
+#endif
 
 		NOTIFY_INIT(DIE_INIT_SLAVE_LEAVE, regs, (long)&nd, 1);
 
diff --git a/arch/ia64/kernel/mca_asm.S b/arch/ia64/kernel/mca_asm.S
index a06d46548ff..7461d2573d4 100644
--- a/arch/ia64/kernel/mca_asm.S
+++ b/arch/ia64/kernel/mca_asm.S
@@ -40,6 +40,7 @@
 
 	.global ia64_do_tlb_purge
 	.global ia64_os_mca_dispatch
+	.global ia64_os_init_on_kdump
 	.global ia64_os_init_dispatch_monarch
 	.global ia64_os_init_dispatch_slave
 
@@ -299,6 +300,25 @@ END(ia64_os_mca_virtual_begin)
 //StartMain////////////////////////////////////////////////////////////////////
 
 //
+// NOP init handler for kdump.  In panic situation, we may receive INIT
+// while kernel transition.  Since we initialize registers on leave from
+// current kernel, no longer monarch/slave handlers of current kernel in
+// virtual mode are called safely.
+// We can unregister these init handlers from SAL, however then the INIT
+// will result in warmboot by SAL and we cannot retrieve the crashdump.
+// Therefore register this NOP function to SAL, to prevent entering virtual
+// mode and resulting warmboot by SAL.
+//
+ia64_os_init_on_kdump:
+	mov		r8=r0		// IA64_INIT_RESUME
+	mov             r9=r10		// SAL_GP
+	mov		r22=r17		// *minstate
+	;;
+	mov		r10=r0		// return to same context
+	mov		b0=r12		// SAL_CHECK return address
+	br		b0
+
+//
 // SAL to OS entry point for INIT on all processors.  This has been defined for
 // registration purposes with SAL as a part of ia64_mca_init.  Monarch and
 // slave INIT have identical processing, except for the value of the
@@ -1073,3 +1093,30 @@ GLOBAL_ENTRY(ia64_get_rnat)
 	mov ar.rsc=3
 	br.ret.sptk.many rp
 END(ia64_get_rnat)
+
+
+// void ia64_set_psr_mc(void)
+//
+// Set psr.mc bit to mask MCA/INIT.
+GLOBAL_ENTRY(ia64_set_psr_mc)
+	rsm psr.i | psr.ic		// disable interrupts
+	;;
+	srlz.d
+	;;
+	mov r14 = psr			// get psr{36:35,31:0}
+	movl r15 = 1f
+	;;
+	dep r14 = -1, r14, PSR_MC, 1	// set psr.mc
+	;;
+	dep r14 = -1, r14, PSR_IC, 1	// set psr.ic
+	;;
+	dep r14 = -1, r14, PSR_BN, 1	// keep bank1 in use
+	;;
+	mov cr.ipsr = r14
+	mov cr.ifs = r0
+	mov cr.iip = r15
+	;;
+	rfi
+1:
+	br.ret.sptk.many rp
+END(ia64_set_psr_mc)
diff --git a/arch/ia64/kernel/pci-dma.c b/arch/ia64/kernel/pci-dma.c
index 05695962fe4..f6b1ff0aea7 100644
--- a/arch/ia64/kernel/pci-dma.c
+++ b/arch/ia64/kernel/pci-dma.c
@@ -69,11 +69,6 @@ iommu_dma_init(void)
 
 int iommu_dma_supported(struct device *dev, u64 mask)
 {
-	struct dma_map_ops *ops = platform_dma_get_ops(dev);
-
-	if (ops->dma_supported)
-		return ops->dma_supported(dev, mask);
-
 	/* Copied from i386. Doesn't make much sense, because it will
 	   only work for pci_alloc_coherent.
 	   The caller just has to use GFP_DMA in this case. */
diff --git a/arch/ia64/kernel/pci-swiotlb.c b/arch/ia64/kernel/pci-swiotlb.c
index 223abb13410..285aae8431c 100644
--- a/arch/ia64/kernel/pci-swiotlb.c
+++ b/arch/ia64/kernel/pci-swiotlb.c
@@ -46,7 +46,7 @@ void __init swiotlb_dma_init(void)
 
 void __init pci_swiotlb_init(void)
 {
-	if (!iommu_detected || iommu_pass_through) {
+	if (!iommu_detected) {
 #ifdef CONFIG_IA64_GENERIC
 		swiotlb = 1;
 		printk(KERN_INFO "PCI-DMA: Re-initialize machine vector.\n");
diff --git a/arch/ia64/kernel/perfmon.c b/arch/ia64/kernel/perfmon.c
index abce2468a40..f1782705b1f 100644
--- a/arch/ia64/kernel/perfmon.c
+++ b/arch/ia64/kernel/perfmon.c
@@ -5603,7 +5603,7 @@ pfm_interrupt_handler(int irq, void *arg)
  * /proc/perfmon interface, for debug only
  */
 
-#define PFM_PROC_SHOW_HEADER	((void *)nr_cpu_ids+1)
+#define PFM_PROC_SHOW_HEADER	((void *)(long)nr_cpu_ids+1)
 
 static void *
 pfm_proc_start(struct seq_file *m, loff_t *pos)
diff --git a/arch/ia64/kernel/process.c b/arch/ia64/kernel/process.c
index 5d7c0e5b9e7..9bcec9945c1 100644
--- a/arch/ia64/kernel/process.c
+++ b/arch/ia64/kernel/process.c
@@ -161,6 +161,13 @@ show_regs (struct pt_regs *regs)
 		show_stack(NULL, NULL);
 }
 
+/* local support for deprecated console_print */
+void
+console_print(const char *s)
+{
+	printk(KERN_EMERG "%s", s);
+}
+
 void
 do_notify_resume_user(sigset_t *unused, struct sigscratch *scr, long in_syscall)
 {
@@ -192,6 +199,8 @@ do_notify_resume_user(sigset_t *unused, struct sigscratch *scr, long in_syscall)
 	if (test_thread_flag(TIF_NOTIFY_RESUME)) {
 		clear_thread_flag(TIF_NOTIFY_RESUME);
 		tracehook_notify_resume(&scr->pt);
+		if (current->replacement_session_keyring)
+			key_replace_session_keyring();
 	}
 
 	/* copy user rbs to kernel rbs */
diff --git a/arch/ia64/kernel/ptrace.c b/arch/ia64/kernel/ptrace.c
index 92c9689b7d9..9daa87fdb01 100644
--- a/arch/ia64/kernel/ptrace.c
+++ b/arch/ia64/kernel/ptrace.c
@@ -15,7 +15,6 @@
 #include <linux/mm.h>
 #include <linux/errno.h>
 #include <linux/ptrace.h>
-#include <linux/smp_lock.h>
 #include <linux/user.h>
 #include <linux/security.h>
 #include <linux/audit.h>
diff --git a/arch/ia64/kernel/relocate_kernel.S b/arch/ia64/kernel/relocate_kernel.S
index 903babd22d6..32f6fc131fb 100644
--- a/arch/ia64/kernel/relocate_kernel.S
+++ b/arch/ia64/kernel/relocate_kernel.S
@@ -52,7 +52,7 @@ GLOBAL_ENTRY(relocate_new_kernel)
 	srlz.i
 	;;
 	mov ar.rnat=r18
-	rfi
+	rfi				// note: this unmask MCA/INIT (psr.mc)
 	;;
 1:
 	//physical mode code begin
diff --git a/arch/ia64/kernel/salinfo.c b/arch/ia64/kernel/salinfo.c
index 7053c55b764..e6676fca482 100644
--- a/arch/ia64/kernel/salinfo.c
+++ b/arch/ia64/kernel/salinfo.c
@@ -192,7 +192,7 @@ struct salinfo_platform_oemdata_parms {
 static void
 salinfo_work_to_do(struct salinfo_data *data)
 {
-	down_trylock(&data->mutex);
+	(void)(down_trylock(&data->mutex) ?: 0);
 	up(&data->mutex);
 }
 
diff --git a/arch/ia64/kernel/setup.c b/arch/ia64/kernel/setup.c
index 1b23ec126b6..1de86c96801 100644
--- a/arch/ia64/kernel/setup.c
+++ b/arch/ia64/kernel/setup.c
@@ -855,11 +855,17 @@ identify_cpu (struct cpuinfo_ia64 *c)
 	c->unimpl_pa_mask = ~((1L<<63) | ((1L << phys_addr_size) - 1));
 }
 
+/*
+ * In UP configuration, setup_per_cpu_areas() is defined in
+ * include/linux/percpu.h
+ */
+#ifdef CONFIG_SMP
 void __init
 setup_per_cpu_areas (void)
 {
 	/* start_kernel() requires this... */
 }
+#endif
 
 /*
  * Do the following calculations:
diff --git a/arch/ia64/kernel/smp.c b/arch/ia64/kernel/smp.c
index f0c521b0ba4..dabeefe2113 100644
--- a/arch/ia64/kernel/smp.c
+++ b/arch/ia64/kernel/smp.c
@@ -58,7 +58,8 @@ static struct local_tlb_flush_counts {
 	unsigned int count;
 } __attribute__((__aligned__(32))) local_tlb_flush_counts[NR_CPUS];
 
-static DEFINE_PER_CPU(unsigned short, shadow_flush_counts[NR_CPUS]) ____cacheline_aligned;
+static DEFINE_PER_CPU_SHARED_ALIGNED(unsigned short [NR_CPUS],
+				     shadow_flush_counts);
 
 #define IPI_CALL_FUNC		0
 #define IPI_CPU_STOP		1
@@ -301,7 +302,7 @@ smp_flush_tlb_mm (struct mm_struct *mm)
 		return;
 	}
 
-	smp_call_function_mask(mm->cpu_vm_mask,
+	smp_call_function_many(mm_cpumask(mm),
 		(void (*)(void *))local_finish_flush_tlb_mm, mm, 1);
 	local_irq_disable();
 	local_finish_flush_tlb_mm(mm);
diff --git a/arch/ia64/kernel/topology.c b/arch/ia64/kernel/topology.c
index bc80dff1df7..8f060352e12 100644
--- a/arch/ia64/kernel/topology.c
+++ b/arch/ia64/kernel/topology.c
@@ -372,6 +372,10 @@ static int __cpuinit cache_add_dev(struct sys_device * sys_dev)
 	retval = kobject_init_and_add(&all_cpu_cache_info[cpu].kobj,
 				      &cache_ktype_percpu_entry, &sys_dev->kobj,
 				      "%s", "cache");
+	if (unlikely(retval < 0)) {
+		cpu_cache_sysfs_exit(cpu);
+		return retval;
+	}
 
 	for (i = 0; i < all_cpu_cache_info[cpu].num_cache_leaves; i++) {
 		this_object = LEAF_KOBJECT_PTR(cpu,i);
@@ -385,7 +389,7 @@ static int __cpuinit cache_add_dev(struct sys_device * sys_dev)
 			}
 			kobject_put(&all_cpu_cache_info[cpu].kobj);
 			cpu_cache_sysfs_exit(cpu);
-			break;
+			return retval;
 		}
 		kobject_uevent(&(this_object->kobj), KOBJ_ADD);
 	}
diff --git a/arch/ia64/kernel/vmlinux.lds.S b/arch/ia64/kernel/vmlinux.lds.S
index 4a95e86b9ac..0a0c77b2c98 100644
--- a/arch/ia64/kernel/vmlinux.lds.S
+++ b/arch/ia64/kernel/vmlinux.lds.S
@@ -24,14 +24,14 @@ PHDRS {
 }
 SECTIONS
 {
-  /* Sections to be discarded */
+  /* unwind exit sections must be discarded before the rest of the
+     sections get included. */
   /DISCARD/ : {
-	EXIT_TEXT
-	EXIT_DATA
-	*(.exitcall.exit)
 	*(.IA_64.unwind.exit.text)
 	*(.IA_64.unwind_info.exit.text)
-	}
+	*(.comment)
+	*(.note)
+  }
 
   v = PAGE_OFFSET;	/* this symbol is here to make debugging easier... */
   phys_start = _start - LOAD_OFFSET;
@@ -51,8 +51,6 @@ SECTIONS
 	KPROBES_TEXT
 	*(.gnu.linkonce.t*)
     }
-  .text.head : AT(ADDR(.text.head) - LOAD_OFFSET)
-	{ *(.text.head) }
   .text2 : AT(ADDR(.text2) - LOAD_OFFSET)
 	{ *(.text2) }
 #ifdef CONFIG_SMP
@@ -66,14 +64,7 @@ SECTIONS
   NOTES :code :note		/* put .notes in text and mark in PT_NOTE  */
   code_continues : {} :code	/* switch back to regular program...  */
 
-  /* Exception table */
-  . = ALIGN(16);
-  __ex_table : AT(ADDR(__ex_table) - LOAD_OFFSET)
-	{
-	  __start___ex_table = .;
-	  *(__ex_table)
-	  __stop___ex_table = .;
-	}
+  EXCEPTION_TABLE(16)
 
   /* MCA table */
   . = ALIGN(16);
@@ -115,38 +106,9 @@ SECTIONS
 
   . = ALIGN(PAGE_SIZE);
   __init_begin = .;
-  .init.text : AT(ADDR(.init.text) - LOAD_OFFSET)
-	{
-	  _sinittext = .;
-	  INIT_TEXT
-	  _einittext = .;
-	}
 
-  .init.data : AT(ADDR(.init.data) - LOAD_OFFSET)
-	{ INIT_DATA }
-
-#ifdef CONFIG_BLK_DEV_INITRD
-  .init.ramfs : AT(ADDR(.init.ramfs) - LOAD_OFFSET)
-	{
-	  __initramfs_start = .;
-	  *(.init.ramfs)
-	  __initramfs_end = .;
-	}
-#endif
-
-   . = ALIGN(16);
-  .init.setup : AT(ADDR(.init.setup) - LOAD_OFFSET)
-        {
-	  __setup_start = .;
-	  *(.init.setup)
-	  __setup_end = .;
-	}
-  .initcall.init : AT(ADDR(.initcall.init) - LOAD_OFFSET)
-	{
-	  __initcall_start = .;
-	INITCALLS
-	  __initcall_end = .;
-	}
+  INIT_TEXT_SECTION(PAGE_SIZE)
+  INIT_DATA_SECTION(16)
 
   .data.patch.vtop : AT(ADDR(.data.patch.vtop) - LOAD_OFFSET)
 	{
@@ -204,24 +166,13 @@ SECTIONS
 	}
 #endif
 
-  . = ALIGN(8);
-   __con_initcall_start = .;
-  .con_initcall.init : AT(ADDR(.con_initcall.init) - LOAD_OFFSET)
-	{ *(.con_initcall.init) }
-  __con_initcall_end = .;
-  __security_initcall_start = .;
-  .security_initcall.init : AT(ADDR(.security_initcall.init) - LOAD_OFFSET)
-	{ *(.security_initcall.init) }
-  __security_initcall_end = .;
   . = ALIGN(PAGE_SIZE);
   __init_end = .;
 
-  /* The initial task and kernel stack */
-  .data.init_task : AT(ADDR(.data.init_task) - LOAD_OFFSET)
-	{ *(.data.init_task) }
-
   .data.page_aligned : AT(ADDR(.data.page_aligned) - LOAD_OFFSET)
-        { *(__special_page_section)
+        {
+	PAGE_ALIGNED_DATA(PAGE_SIZE)
+	  . = ALIGN(PAGE_SIZE);
 	  __start_gate_section = .;
 	  *(.data.gate)
 	  __stop_gate_section = .;
@@ -236,12 +187,6 @@ SECTIONS
   				 * kernel data
 				 */
 
-  .data.read_mostly : AT(ADDR(.data.read_mostly) - LOAD_OFFSET)
-        { *(.data.read_mostly) }
-
-  .data.cacheline_aligned : AT(ADDR(.data.cacheline_aligned) - LOAD_OFFSET)
-        { *(.data.cacheline_aligned) }
-
   /* Per-cpu data: */
   . = ALIGN(PERCPU_PAGE_SIZE);
   PERCPU_VADDR(PERCPU_ADDR, :percpu)
@@ -258,6 +203,9 @@ SECTIONS
 		__cpu0_per_cpu = .;
   . = . + PERCPU_PAGE_SIZE;	/* cpu0 per-cpu space */
 #endif
+		INIT_TASK_DATA(PAGE_SIZE)
+		CACHELINE_ALIGNED_DATA(SMP_CACHE_BYTES)
+		READ_MOSTLY_DATA(SMP_CACHE_BYTES)
 		DATA_DATA
 		*(.data1)
 		*(.gnu.linkonce.d*)
@@ -274,49 +222,16 @@ SECTIONS
   .sdata : AT(ADDR(.sdata) - LOAD_OFFSET)
 	{ *(.sdata) *(.sdata1) *(.srdata) }
   _edata  =  .;
-  __bss_start = .;
-  .sbss : AT(ADDR(.sbss) - LOAD_OFFSET)
-	{ *(.sbss) *(.scommon) }
-  .bss : AT(ADDR(.bss) - LOAD_OFFSET)
-	{ *(.bss) *(COMMON) }
-  __bss_stop = .;
+
+  BSS_SECTION(0, 0, 0)
 
   _end = .;
 
   code : { } :code
-  /* Stabs debugging sections.  */
-  .stab 0 : { *(.stab) }
-  .stabstr 0 : { *(.stabstr) }
-  .stab.excl 0 : { *(.stab.excl) }
-  .stab.exclstr 0 : { *(.stab.exclstr) }
-  .stab.index 0 : { *(.stab.index) }
-  .stab.indexstr 0 : { *(.stab.indexstr) }
-  /* DWARF debug sections.
-     Symbols in the DWARF debugging sections are relative to the beginning
-     of the section so we begin them at 0.  */
-  /* DWARF 1 */
-  .debug          0 : { *(.debug) }
-  .line           0 : { *(.line) }
-  /* GNU DWARF 1 extensions */
-  .debug_srcinfo  0 : { *(.debug_srcinfo) }
-  .debug_sfnames  0 : { *(.debug_sfnames) }
-  /* DWARF 1.1 and DWARF 2 */
-  .debug_aranges  0 : { *(.debug_aranges) }
-  .debug_pubnames 0 : { *(.debug_pubnames) }
-  /* DWARF 2 */
-  .debug_info     0 : { *(.debug_info) }
-  .debug_abbrev   0 : { *(.debug_abbrev) }
-  .debug_line     0 : { *(.debug_line) }
-  .debug_frame    0 : { *(.debug_frame) }
-  .debug_str      0 : { *(.debug_str) }
-  .debug_loc      0 : { *(.debug_loc) }
-  .debug_macinfo  0 : { *(.debug_macinfo) }
-  /* SGI/MIPS DWARF 2 extensions */
-  .debug_weaknames 0 : { *(.debug_weaknames) }
-  .debug_funcnames 0 : { *(.debug_funcnames) }
-  .debug_typenames 0 : { *(.debug_typenames) }
-  .debug_varnames  0 : { *(.debug_varnames) }
-  /* These must appear regardless of  .  */
-  /DISCARD/ : { *(.comment) }
-  /DISCARD/ : { *(.note) }
+
+  STABS_DEBUG
+  DWARF_DEBUG
+
+  /* Default discards */
+  DISCARDS
 }