Merge commit 'v2.6.39-rc7' into sched/core

81 files changed, 1319 insertions, 561 deletions

diff --git a/arch/arm/configs/at91x40_defconfig b/arch/arm/configs/at91x40_defconfig
new file mode 100644
index 0000000..c55e921
--- /dev/null
+++ b/arch/arm/configs/at91x40_defconfig
@@ -0,0 +1,48 @@
+CONFIG_EXPERIMENTAL=y
+CONFIG_LOG_BUF_SHIFT=14
+CONFIG_EMBEDDED=y
+# CONFIG_HOTPLUG is not set
+# CONFIG_ELF_CORE is not set
+# CONFIG_FUTEX is not set
+# CONFIG_TIMERFD is not set
+# CONFIG_VM_EVENT_COUNTERS is not set
+# CONFIG_COMPAT_BRK is not set
+CONFIG_SLAB=y
+# CONFIG_LBDAF is not set
+# CONFIG_BLK_DEV_BSG is not set
+# CONFIG_IOSCHED_DEADLINE is not set
+# CONFIG_IOSCHED_CFQ is not set
+# CONFIG_MMU is not set
+CONFIG_ARCH_AT91=y
+CONFIG_ARCH_AT91X40=y
+CONFIG_MACH_AT91EB01=y
+CONFIG_AT91_EARLY_USART0=y
+CONFIG_CPU_ARM7TDMI=y
+CONFIG_SET_MEM_PARAM=y
+CONFIG_DRAM_BASE=0x01000000
+CONFIG_DRAM_SIZE=0x00400000
+CONFIG_FLASH_MEM_BASE=0x01400000
+CONFIG_PROCESSOR_ID=0x14000040
+CONFIG_ZBOOT_ROM_TEXT=0x0
+CONFIG_ZBOOT_ROM_BSS=0x0
+CONFIG_BINFMT_FLAT=y
+# CONFIG_SUSPEND is not set
+# CONFIG_FW_LOADER is not set
+CONFIG_MTD=y
+CONFIG_MTD_PARTITIONS=y
+CONFIG_MTD_CHAR=y
+CONFIG_MTD_BLOCK=y
+CONFIG_MTD_RAM=y
+CONFIG_MTD_ROM=y
+CONFIG_BLK_DEV_RAM=y
+# CONFIG_INPUT is not set
+# CONFIG_SERIO is not set
+# CONFIG_VT is not set
+# CONFIG_DEVKMEM is not set
+# CONFIG_HW_RANDOM is not set
+# CONFIG_HWMON is not set
+# CONFIG_USB_SUPPORT is not set
+CONFIG_EXT2_FS=y
+# CONFIG_DNOTIFY is not set
+CONFIG_ROMFS_FS=y
+# CONFIG_ENABLE_MUST_CHECK is not set
diff --git a/arch/arm/include/asm/cputype.h b/arch/arm/include/asm/cputype.h
index ed5bc9e..cd4458f 100644
--- a/arch/arm/include/asm/cputype.h
+++ b/arch/arm/include/asm/cputype.h
@@ -2,6 +2,7 @@
 #define __ASM_ARM_CPUTYPE_H
 
 #include <linux/stringify.h>
+#include <linux/kernel.h>
 
 #define CPUID_ID	0
 #define CPUID_CACHETYPE	1
diff --git a/arch/arm/include/asm/kprobes.h b/arch/arm/include/asm/kprobes.h
index bb8a19b..e46bdd0 100644
--- a/arch/arm/include/asm/kprobes.h
+++ b/arch/arm/include/asm/kprobes.h
@@ -39,10 +39,13 @@ typedef u32 kprobe_opcode_t;
 struct kprobe;
 typedef void (kprobe_insn_handler_t)(struct kprobe *, struct pt_regs *);
 
+typedef unsigned long (kprobe_check_cc)(unsigned long);
+
 /* Architecture specific copy of original instruction. */
 struct arch_specific_insn {
 	kprobe_opcode_t		*insn;
 	kprobe_insn_handler_t	*insn_handler;
+	kprobe_check_cc		*insn_check_cc;
 };
 
 struct prev_kprobe {
diff --git a/arch/arm/include/asm/unistd.h b/arch/arm/include/asm/unistd.h
index c891eb7..87dbe3e 100644
--- a/arch/arm/include/asm/unistd.h
+++ b/arch/arm/include/asm/unistd.h
@@ -396,6 +396,10 @@
 #define __NR_fanotify_init		(__NR_SYSCALL_BASE+367)
 #define __NR_fanotify_mark		(__NR_SYSCALL_BASE+368)
 #define __NR_prlimit64			(__NR_SYSCALL_BASE+369)
+#define __NR_name_to_handle_at		(__NR_SYSCALL_BASE+370)
+#define __NR_open_by_handle_at		(__NR_SYSCALL_BASE+371)
+#define __NR_clock_adjtime		(__NR_SYSCALL_BASE+372)
+#define __NR_syncfs			(__NR_SYSCALL_BASE+373)
 
 /*
  * The following SWIs are ARM private.
diff --git a/arch/arm/kernel/calls.S b/arch/arm/kernel/calls.S
index 5c26ecc..7fbf28c 100644
--- a/arch/arm/kernel/calls.S
+++ b/arch/arm/kernel/calls.S
@@ -379,6 +379,10 @@
 		CALL(sys_fanotify_init)
 		CALL(sys_fanotify_mark)
 		CALL(sys_prlimit64)
+/* 370 */	CALL(sys_name_to_handle_at)
+		CALL(sys_open_by_handle_at)
+		CALL(sys_clock_adjtime)
+		CALL(sys_syncfs)
 #ifndef syscalls_counted
 .equ syscalls_padding, ((NR_syscalls + 3) & ~3) - NR_syscalls
 #define syscalls_counted
diff --git a/arch/arm/kernel/kprobes-decode.c b/arch/arm/kernel/kprobes-decode.c
index 2389131..15eeff6 100644
--- a/arch/arm/kernel/kprobes-decode.c
+++ b/arch/arm/kernel/kprobes-decode.c
@@ -34,9 +34,6 @@
  *
  *   *) If the PC is written to by the instruction, the
  *      instruction must be fully simulated in software.
- *      If it is a conditional instruction, the handler
- *      will use insn[0] to copy its condition code to
- *	set r0 to 1 and insn[1] to "mov pc, lr" to return.
  *
  *   *) Otherwise, a modified form of the instruction is
  *      directly executed.  Its handler calls the
@@ -68,13 +65,17 @@
 
 #define branch_displacement(insn) sign_extend(((insn) & 0xffffff) << 2, 25)
 
+#define is_r15(insn, bitpos) (((insn) & (0xf << bitpos)) == (0xf << bitpos))
+
+/*
+ * Test if load/store instructions writeback the address register.
+ * if P (bit 24) == 0 or W (bit 21) == 1
+ */
+#define is_writeback(insn) ((insn ^ 0x01000000) & 0x01200000)
+
 #define PSR_fs	(PSR_f|PSR_s)
 
 #define KPROBE_RETURN_INSTRUCTION	0xe1a0f00e	/* mov pc, lr */
-#define SET_R0_TRUE_INSTRUCTION		0xe3a00001	/* mov	r0, #1 */
-
-#define	truecc_insn(insn)	(((insn) & 0xf0000000) | \
-				 (SET_R0_TRUE_INSTRUCTION & 0x0fffffff))
 
 typedef long (insn_0arg_fn_t)(void);
 typedef long (insn_1arg_fn_t)(long);
@@ -419,14 +420,10 @@ insnslot_llret_4arg_rwflags(long r0, long r1, long r2, long r3, long *cpsr,
 
 static void __kprobes simulate_bbl(struct kprobe *p, struct pt_regs *regs)
 {
-	insn_1arg_fn_t *i_fn = (insn_1arg_fn_t *)&p->ainsn.insn[0];
 	kprobe_opcode_t insn = p->opcode;
 	long iaddr = (long)p->addr;
 	int disp  = branch_displacement(insn);
 
-	if (!insnslot_1arg_rflags(0, regs->ARM_cpsr, i_fn))
-		return;
-
 	if (insn & (1 << 24))
 		regs->ARM_lr = iaddr + 4;
 
@@ -446,14 +443,10 @@ static void __kprobes simulate_blx1(struct kprobe *p, struct pt_regs *regs)
 
 static void __kprobes simulate_blx2bx(struct kprobe *p, struct pt_regs *regs)
 {
-	insn_1arg_fn_t *i_fn = (insn_1arg_fn_t *)&p->ainsn.insn[0];
 	kprobe_opcode_t insn = p->opcode;
 	int rm = insn & 0xf;
 	long rmv = regs->uregs[rm];
 
-	if (!insnslot_1arg_rflags(0, regs->ARM_cpsr, i_fn))
-		return;
-
 	if (insn & (1 << 5))
 		regs->ARM_lr = (long)p->addr + 4;
 
@@ -463,9 +456,16 @@ static void __kprobes simulate_blx2bx(struct kprobe *p, struct pt_regs *regs)
 		regs->ARM_cpsr |= PSR_T_BIT;
 }
 
+static void __kprobes simulate_mrs(struct kprobe *p, struct pt_regs *regs)
+{
+	kprobe_opcode_t insn = p->opcode;
+	int rd = (insn >> 12) & 0xf;
+	unsigned long mask = 0xf8ff03df; /* Mask out execution state */
+	regs->uregs[rd] = regs->ARM_cpsr & mask;
+}
+
 static void __kprobes simulate_ldm1stm1(struct kprobe *p, struct pt_regs *regs)
 {
-	insn_1arg_fn_t *i_fn = (insn_1arg_fn_t *)&p->ainsn.insn[0];
 	kprobe_opcode_t insn = p->opcode;
 	int rn = (insn >> 16) & 0xf;
 	int lbit = insn & (1 << 20);
@@ -476,9 +476,6 @@ static void __kprobes simulate_ldm1stm1(struct kprobe *p, struct pt_regs *regs)
 	int reg_bit_vector;
 	int reg_count;
 
-	if (!insnslot_1arg_rflags(0, regs->ARM_cpsr, i_fn))
-		return;
-
 	reg_count = 0;
 	reg_bit_vector = insn & 0xffff;
 	while (reg_bit_vector) {
@@ -510,11 +507,6 @@ static void __kprobes simulate_ldm1stm1(struct kprobe *p, struct pt_regs *regs)
 
 static void __kprobes simulate_stm1_pc(struct kprobe *p, struct pt_regs *regs)
 {
-	insn_1arg_fn_t *i_fn = (insn_1arg_fn_t *)&p->ainsn.insn[0];
-
-	if (!insnslot_1arg_rflags(0, regs->ARM_cpsr, i_fn))
-		return;
-
 	regs->ARM_pc = (long)p->addr + str_pc_offset;
 	simulate_ldm1stm1(p, regs);
 	regs->ARM_pc = (long)p->addr + 4;
@@ -525,24 +517,16 @@ static void __kprobes simulate_mov_ipsp(struct kprobe *p, struct pt_regs *regs)
 	regs->uregs[12] = regs->uregs[13];
 }
 
-static void __kprobes emulate_ldcstc(struct kprobe *p, struct pt_regs *regs)
-{
-	insn_1arg_fn_t *i_fn = (insn_1arg_fn_t *)&p->ainsn.insn[0];
-	kprobe_opcode_t insn = p->opcode;
-	int rn = (insn >> 16) & 0xf;
-	long rnv = regs->uregs[rn];
-
-	/* Save Rn in case of writeback. */
-	regs->uregs[rn] = insnslot_1arg_rflags(rnv, regs->ARM_cpsr, i_fn);
-}
-
 static void __kprobes emulate_ldrd(struct kprobe *p, struct pt_regs *regs)
 {
 	insn_2arg_fn_t *i_fn = (insn_2arg_fn_t *)&p->ainsn.insn[0];
 	kprobe_opcode_t insn = p->opcode;
+	long ppc = (long)p->addr + 8;
 	int rd = (insn >> 12) & 0xf;
 	int rn = (insn >> 16) & 0xf;
 	int rm = insn & 0xf;  /* rm may be invalid, don't care. */
+	long rmv = (rm == 15) ? ppc : regs->uregs[rm];
+	long rnv = (rn == 15) ? ppc : regs->uregs[rn];
 
 	/* Not following the C calling convention here, so need asm(). */
 	__asm__ __volatile__ (
@@ -554,29 +538,36 @@ static void __kprobes emulate_ldrd(struct kprobe *p, struct pt_regs *regs)
 		"str	r0, %[rn]	\n\t"	/* in case of writeback */
 		"str	r2, %[rd0]	\n\t"
 		"str	r3, %[rd1]	\n\t"
-		: [rn]  "+m" (regs->uregs[rn]),
+		: [rn]  "+m" (rnv),
 		  [rd0] "=m" (regs->uregs[rd]),
 		  [rd1] "=m" (regs->uregs[rd+1])
-		: [rm]   "m" (regs->uregs[rm]),
+		: [rm]   "m" (rmv),
 		  [cpsr] "r" (regs->ARM_cpsr),
 		  [i_fn] "r" (i_fn)
 		: "r0", "r1", "r2", "r3", "lr", "cc"
 	);
+	if (is_writeback(insn))
+		regs->uregs[rn] = rnv;
 }
 
 static void __kprobes emulate_strd(struct kprobe *p, struct pt_regs *regs)
 {
 	insn_4arg_fn_t *i_fn = (insn_4arg_fn_t *)&p->ainsn.insn[0];
 	kprobe_opcode_t insn = p->opcode;
+	long ppc = (long)p->addr + 8;
 	int rd = (insn >> 12) & 0xf;
 	int rn = (insn >> 16) & 0xf;
 	int rm  = insn & 0xf;
-	long rnv = regs->uregs[rn];
-	long rmv = regs->uregs[rm];  /* rm/rmv may be invalid, don't care. */
+	long rnv = (rn == 15) ? ppc : regs->uregs[rn];
+	/* rm/rmv may be invalid, don't care. */
+	long rmv = (rm == 15) ? ppc : regs->uregs[rm];
+	long rnv_wb;
 
-	regs->uregs[rn] = insnslot_4arg_rflags(rnv, rmv, regs->uregs[rd],
+	rnv_wb = insnslot_4arg_rflags(rnv, rmv, regs->uregs[rd],
 					       regs->uregs[rd+1],
 					       regs->ARM_cpsr, i_fn);
+	if (is_writeback(insn))
+		regs->uregs[rn] = rnv_wb;
 }
 
 static void __kprobes emulate_ldr(struct kprobe *p, struct pt_regs *regs)
@@ -630,31 +621,6 @@ static void __kprobes emulate_str(struct kprobe *p, struct pt_regs *regs)
 		regs->uregs[rn] = rnv_wb;  /* Save Rn in case of writeback. */
 }
 
-static void __kprobes emulate_mrrc(struct kprobe *p, struct pt_regs *regs)
-{
-	insn_llret_0arg_fn_t *i_fn = (insn_llret_0arg_fn_t *)&p->ainsn.insn[0];
-	kprobe_opcode_t insn = p->opcode;
-	union reg_pair fnr;
-	int rd = (insn >> 12) & 0xf;
-	int rn = (insn >> 16) & 0xf;
-
-	fnr.dr = insnslot_llret_0arg_rflags(regs->ARM_cpsr, i_fn);
-	regs->uregs[rn] = fnr.r0;
-	regs->uregs[rd] = fnr.r1;
-}
-
-static void __kprobes emulate_mcrr(struct kprobe *p, struct pt_regs *regs)
-{
-	insn_2arg_fn_t *i_fn = (insn_2arg_fn_t *)&p->ainsn.insn[0];
-	kprobe_opcode_t insn = p->opcode;
-	int rd = (insn >> 12) & 0xf;
-	int rn = (insn >> 16) & 0xf;
-	long rnv = regs->uregs[rn];
-	long rdv = regs->uregs[rd];
-
-	insnslot_2arg_rflags(rnv, rdv, regs->ARM_cpsr, i_fn);
-}
-
 static void __kprobes emulate_sat(struct kprobe *p, struct pt_regs *regs)
 {
 	insn_1arg_fn_t *i_fn = (insn_1arg_fn_t *)&p->ainsn.insn[0];
@@ -688,32 +654,32 @@ static void __kprobes emulate_none(struct kprobe *p, struct pt_regs *regs)
 	insnslot_0arg_rflags(regs->ARM_cpsr, i_fn);
 }
 
-static void __kprobes emulate_rd12(struct kprobe *p, struct pt_regs *regs)
+static void __kprobes emulate_nop(struct kprobe *p, struct pt_regs *regs)
 {
-	insn_0arg_fn_t *i_fn = (insn_0arg_fn_t *)&p->ainsn.insn[0];
-	kprobe_opcode_t insn = p->opcode;
-	int rd = (insn >> 12) & 0xf;
-
-	regs->uregs[rd] = insnslot_0arg_rflags(regs->ARM_cpsr, i_fn);
 }
 
-static void __kprobes emulate_ird12(struct kprobe *p, struct pt_regs *regs)
+static void __kprobes
+emulate_rd12_modify(struct kprobe *p, struct pt_regs *regs)
 {
 	insn_1arg_fn_t *i_fn = (insn_1arg_fn_t *)&p->ainsn.insn[0];
 	kprobe_opcode_t insn = p->opcode;
-	int ird = (insn >> 12) & 0xf;
+	int rd = (insn >> 12) & 0xf;
+	long rdv = regs->uregs[rd];
 
-	insnslot_1arg_rflags(regs->uregs[ird], regs->ARM_cpsr, i_fn);
+	regs->uregs[rd] = insnslot_1arg_rflags(rdv, regs->ARM_cpsr, i_fn);
 }
 
-static void __kprobes emulate_rn16(struct kprobe *p, struct pt_regs *regs)
+static void __kprobes
+emulate_rd12rn0_modify(struct kprobe *p, struct pt_regs *regs)
 {
-	insn_1arg_fn_t *i_fn = (insn_1arg_fn_t *)&p->ainsn.insn[0];
+	insn_2arg_fn_t *i_fn = (insn_2arg_fn_t *)&p->ainsn.insn[0];
 	kprobe_opcode_t insn = p->opcode;
-	int rn = (insn >> 16) & 0xf;
+	int rd = (insn >> 12) & 0xf;
+	int rn = insn & 0xf;
+	long rdv = regs->uregs[rd];
 	long rnv = regs->uregs[rn];
 
-	insnslot_1arg_rflags(rnv, regs->ARM_cpsr, i_fn);
+	regs->uregs[rd] = insnslot_2arg_rflags(rdv, rnv, regs->ARM_cpsr, i_fn);
 }
 
 static void __kprobes emulate_rd12rm0(struct kprobe *p, struct pt_regs *regs)
@@ -819,6 +785,17 @@ emulate_alu_imm_rwflags(struct kprobe *p, struct pt_regs *regs)
 }
 
 static void __kprobes
+emulate_alu_tests_imm(struct kprobe *p, struct pt_regs *regs)
+{
+	insn_1arg_fn_t *i_fn = (insn_1arg_fn_t *)&p->ainsn.insn[0];
+	kprobe_opcode_t insn = p->opcode;
+	int rn = (insn >> 16) & 0xf;
+	long rnv = (rn == 15) ? (long)p->addr + 8 : regs->uregs[rn];
+
+	insnslot_1arg_rwflags(rnv, &regs->ARM_cpsr, i_fn);
+}
+
+static void __kprobes
 emulate_alu_rflags(struct kprobe *p, struct pt_regs *regs)
 {
 	insn_3arg_fn_t *i_fn = (insn_3arg_fn_t *)&p->ainsn.insn[0];
@@ -854,14 +831,34 @@ emulate_alu_rwflags(struct kprobe *p, struct pt_regs *regs)
 		insnslot_3arg_rwflags(rnv, rmv, rsv, &regs->ARM_cpsr, i_fn);
 }
 
+static void __kprobes
+emulate_alu_tests(struct kprobe *p, struct pt_regs *regs)
+{
+	insn_3arg_fn_t *i_fn = (insn_3arg_fn_t *)&p->ainsn.insn[0];
+	kprobe_opcode_t insn = p->opcode;
+	long ppc = (long)p->addr + 8;
+	int rn = (insn >> 16) & 0xf;
+	int rs = (insn >> 8) & 0xf;	/* rs/rsv may be invalid, don't care. */
+	int rm = insn & 0xf;
+	long rnv = (rn == 15) ? ppc : regs->uregs[rn];
+	long rmv = (rm == 15) ? ppc : regs->uregs[rm];
+	long rsv = regs->uregs[rs];
+
+	insnslot_3arg_rwflags(rnv, rmv, rsv, &regs->ARM_cpsr, i_fn);
+}
+
 static enum kprobe_insn __kprobes
 prep_emulate_ldr_str(kprobe_opcode_t insn, struct arch_specific_insn *asi)
 {
-	int ibit = (insn & (1 << 26)) ? 25 : 22;
+	int not_imm = (insn & (1 << 26)) ? (insn & (1 << 25))
+					 : (~insn & (1 << 22));
+
+	if (is_writeback(insn) && is_r15(insn, 16))
+		return INSN_REJECTED;	/* Writeback to PC */
 
 	insn &= 0xfff00fff;
 	insn |= 0x00001000;	/* Rn = r0, Rd = r1 */
-	if (insn & (1 << ibit)) {
+	if (not_imm) {
 		insn &= ~0xf;
 		insn |= 2;	/* Rm = r2 */
 	}
@@ -871,20 +868,40 @@ prep_emulate_ldr_str(kprobe_opcode_t insn, struct arch_specific_insn *asi)
 }
 
 static enum kprobe_insn __kprobes
-prep_emulate_rd12rm0(kprobe_opcode_t insn, struct arch_specific_insn *asi)
+prep_emulate_rd12_modify(kprobe_opcode_t insn, struct arch_specific_insn *asi)
 {
-	insn &= 0xffff0ff0;	/* Rd = r0, Rm = r0 */
+	if (is_r15(insn, 12))
+		return INSN_REJECTED;	/* Rd is PC */
+
+	insn &= 0xffff0fff;	/* Rd = r0 */
 	asi->insn[0] = insn;
-	asi->insn_handler = emulate_rd12rm0;
+	asi->insn_handler = emulate_rd12_modify;
 	return INSN_GOOD;
 }
 
 static enum kprobe_insn __kprobes
-prep_emulate_rd12(kprobe_opcode_t insn, struct arch_specific_insn *asi)
+prep_emulate_rd12rn0_modify(kprobe_opcode_t insn,
+			    struct arch_specific_insn *asi)
 {
-	insn &= 0xffff0fff;	/* Rd = r0 */
+	if (is_r15(insn, 12))
+		return INSN_REJECTED;	/* Rd is PC */
+
+	insn &= 0xffff0ff0;	/* Rd = r0 */
+	insn |= 0x00000001;	/* Rn = r1 */
+	asi->insn[0] = insn;
+	asi->insn_handler = emulate_rd12rn0_modify;
+	return INSN_GOOD;
+}
+
+static enum kprobe_insn __kprobes
+prep_emulate_rd12rm0(kprobe_opcode_t insn, struct arch_specific_insn *asi)
+{
+	if (is_r15(insn, 12))
+		return INSN_REJECTED;	/* Rd is PC */
+
+	insn &= 0xffff0ff0;	/* Rd = r0, Rm = r0 */
 	asi->insn[0] = insn;
-	asi->insn_handler = emulate_rd12;
+	asi->insn_handler = emulate_rd12rm0;
 	return INSN_GOOD;
 }
 
@@ -892,6 +909,9 @@ static enum kprobe_insn __kprobes
 prep_emulate_rd12rn16rm0_wflags(kprobe_opcode_t insn,
 				struct arch_specific_insn *asi)
 {
+	if (is_r15(insn, 12))
+		return INSN_REJECTED;	/* Rd is PC */
+
 	insn &= 0xfff00ff0;	/* Rd = r0, Rn = r0 */
 	insn |= 0x00000001;	/* Rm = r1 */
 	asi->insn[0] = insn;
@@ -903,6 +923,9 @@ static enum kprobe_insn __kprobes
 prep_emulate_rd16rs8rm0_wflags(kprobe_opcode_t insn,
 			       struct arch_specific_insn *asi)
 {
+	if (is_r15(insn, 16))
+		return INSN_REJECTED;	/* Rd is PC */
+
 	insn &= 0xfff0f0f0;	/* Rd = r0, Rs = r0 */
 	insn |= 0x00000001;	/* Rm = r1          */
 	asi->insn[0] = insn;
@@ -914,6 +937,9 @@ static enum kprobe_insn __kprobes
 prep_emulate_rd16rn12rs8rm0_wflags(kprobe_opcode_t insn,
 				   struct arch_specific_insn *asi)
 {
+	if (is_r15(insn, 16))
+		return INSN_REJECTED;	/* Rd is PC */
+
 	insn &= 0xfff000f0;	/* Rd = r0, Rn = r0 */
 	insn |= 0x00000102;	/* Rs = r1, Rm = r2 */
 	asi->insn[0] = insn;
@@ -925,6 +951,9 @@ static enum kprobe_insn __kprobes
 prep_emulate_rdhi16rdlo12rs8rm0_wflags(kprobe_opcode_t insn,
 				       struct arch_specific_insn *asi)
 {
+	if (is_r15(insn, 16) || is_r15(insn, 12))
+		return INSN_REJECTED;	/* RdHi or RdLo is PC */
+
 	insn &= 0xfff000f0;	/* RdHi = r0, RdLo = r1 */
 	insn |= 0x00001203;	/* Rs = r2, Rm = r3 */
 	asi->insn[0] = insn;
@@ -945,20 +974,13 @@ prep_emulate_rdhi16rdlo12rs8rm0_wflags(kprobe_opcode_t insn,
 static enum kprobe_insn __kprobes
 space_1111(kprobe_opcode_t insn, struct arch_specific_insn *asi)
 {
-	/* CPS mmod == 1 : 1111 0001 0000 xx10 xxxx xxxx xx0x xxxx */
-	/* RFE           : 1111 100x x0x1 xxxx xxxx 1010 xxxx xxxx */
-	/* SRS           : 1111 100x x1x0 1101 xxxx 0101 xxxx xxxx */
-	if ((insn & 0xfff30020) == 0xf1020000 ||
-	    (insn & 0xfe500f00) == 0xf8100a00 ||
-	    (insn & 0xfe5f0f00) == 0xf84d0500)
-		return INSN_REJECTED;
-
-	/* PLD : 1111 01x1 x101 xxxx xxxx xxxx xxxx xxxx : */
-	if ((insn & 0xfd700000) == 0xf4500000) {
-		insn &= 0xfff0ffff;	/* Rn = r0 */
-		asi->insn[0] = insn;
-		asi->insn_handler = emulate_rn16;
-		return INSN_GOOD;
+	/* memory hint : 1111 0100 x001 xxxx xxxx xxxx xxxx xxxx : */
+	/* PLDI        : 1111 0100 x101 xxxx xxxx xxxx xxxx xxxx : */
+	/* PLDW        : 1111 0101 x001 xxxx xxxx xxxx xxxx xxxx : */
+	/* PLD         : 1111 0101 x101 xxxx xxxx xxxx xxxx xxxx : */
+	if ((insn & 0xfe300000) == 0xf4100000) {
+		asi->insn_handler = emulate_nop;
+		return INSN_GOOD_NO_SLOT;
 	}
 
 	/* BLX(1) : 1111 101x xxxx xxxx xxxx xxxx xxxx xxxx : */
@@ -967,41 +989,22 @@ space_1111(kprobe_opcode_t insn, struct arch_specific_insn *asi)
 		return INSN_GOOD_NO_SLOT;
 	}
 
-	/* SETEND : 1111 0001 0000 0001 xxxx xxxx 0000 xxxx */
-	/* CDP2   : 1111 1110 xxxx xxxx xxxx xxxx xxx0 xxxx */
-	if ((insn & 0xffff00f0) == 0xf1010000 ||
-	    (insn & 0xff000010) == 0xfe000000) {
-		asi->insn[0] = insn;
-		asi->insn_handler = emulate_none;
-		return INSN_GOOD;
-	}
+	/* CPS   : 1111 0001 0000 xxx0 xxxx xxxx xx0x xxxx */
+	/* SETEND: 1111 0001 0000 0001 xxxx xxxx 0000 xxxx */
 
+	/* SRS   : 1111 100x x1x0 xxxx xxxx xxxx xxxx xxxx */
+	/* RFE   : 1111 100x x0x1 xxxx xxxx xxxx xxxx xxxx */
+
+	/* Coprocessor instructions... */
 	/* MCRR2 : 1111 1100 0100 xxxx xxxx xxxx xxxx xxxx : (Rd != Rn) */
 	/* MRRC2 : 1111 1100 0101 xxxx xxxx xxxx xxxx xxxx : (Rd != Rn) */
-	if ((insn & 0xffe00000) == 0xfc400000) {
-		insn &= 0xfff00fff;	/* Rn = r0 */
-		insn |= 0x00001000;	/* Rd = r1 */
-		asi->insn[0] = insn;
-		asi->insn_handler =
-			(insn & (1 << 20)) ? emulate_mrrc : emulate_mcrr;
-		return INSN_GOOD;
-	}
+	/* LDC2  : 1111 110x xxx1 xxxx xxxx xxxx xxxx xxxx */
+	/* STC2  : 1111 110x xxx0 xxxx xxxx xxxx xxxx xxxx */
+	/* CDP2  : 1111 1110 xxxx xxxx xxxx xxxx xxx0 xxxx */
+	/* MCR2  : 1111 1110 xxx0 xxxx xxxx xxxx xxx1 xxxx */
+	/* MRC2  : 1111 1110 xxx1 xxxx xxxx xxxx xxx1 xxxx */
 
-	/* LDC2 : 1111 110x xxx1 xxxx xxxx xxxx xxxx xxxx */
-	/* STC2 : 1111 110x xxx0 xxxx xxxx xxxx xxxx xxxx */
-	if ((insn & 0xfe000000) == 0xfc000000) {
-		insn &= 0xfff0ffff;      /* Rn = r0 */
-		asi->insn[0] = insn;
-		asi->insn_handler = emulate_ldcstc;
-		return INSN_GOOD;
-	}
-
-	/* MCR2 : 1111 1110 xxx0 xxxx xxxx xxxx xxx1 xxxx */
-	/* MRC2 : 1111 1110 xxx1 xxxx xxxx xxxx xxx1 xxxx */
-	insn &= 0xffff0fff;	/* Rd = r0 */
-	asi->insn[0]      = insn;
-	asi->insn_handler = (insn & (1 << 20)) ? emulate_rd12 : emulate_ird12;
-	return INSN_GOOD;
+	return INSN_REJECTED;
 }
 
 static enum kprobe_insn __kprobes
@@ -1010,19 +1013,18 @@ space_cccc_000x(kprobe_opcode_t insn, struct arch_specific_insn *asi)
 	/* cccc 0001 0xx0 xxxx xxxx xxxx xxxx xxx0 xxxx */
 	if ((insn & 0x0f900010) == 0x01000000) {
 
-		/* BXJ  : cccc 0001 0010 xxxx xxxx xxxx 0010 xxxx */
-		/* MSR  : cccc 0001 0x10 xxxx xxxx xxxx 0000 xxxx */
-		if ((insn & 0x0ff000f0) == 0x01200020 ||
-		    (insn & 0x0fb000f0) == 0x01200000)
-			return INSN_REJECTED;
-
-		/* MRS : cccc 0001 0x00 xxxx xxxx xxxx 0000 xxxx */
-		if ((insn & 0x0fb00010) == 0x01000000)
-			return prep_emulate_rd12(insn, asi);
+		/* MRS cpsr : cccc 0001 0000 xxxx xxxx xxxx 0000 xxxx */
+		if ((insn & 0x0ff000f0) == 0x01000000) {
+			if (is_r15(insn, 12))
+				return INSN_REJECTED;	/* Rd is PC */
+			asi->insn_handler = simulate_mrs;
+			return INSN_GOOD_NO_SLOT;
+		}
 
 		/* SMLALxy : cccc 0001 0100 xxxx xxxx xxxx 1xx0 xxxx */
 		if ((insn & 0x0ff00090) == 0x01400080)
-			return prep_emulate_rdhi16rdlo12rs8rm0_wflags(insn, asi);
+			return prep_emulate_rdhi16rdlo12rs8rm0_wflags(insn,
+									asi);
 
 		/* SMULWy : cccc 0001 0010 xxxx xxxx xxxx 1x10 xxxx */
 		/* SMULxy : cccc 0001 0110 xxxx xxxx xxxx 1xx0 xxxx */
@@ -1031,24 +1033,29 @@ space_cccc_000x(kprobe_opcode_t insn, struct arch_specific_insn *asi)
 			return prep_emulate_rd16rs8rm0_wflags(insn, asi);
 
 		/* SMLAxy : cccc 0001 0000 xxxx xxxx xxxx 1xx0 xxxx : Q */
-		/* SMLAWy : cccc 0001 0010 xxxx xxxx xxxx 0x00 xxxx : Q */
-		return prep_emulate_rd16rn12rs8rm0_wflags(insn, asi);
+		/* SMLAWy : cccc 0001 0010 xxxx xxxx xxxx 1x00 xxxx : Q */
+		if ((insn & 0x0ff00090) == 0x01000080 ||
+		    (insn & 0x0ff000b0) == 0x01200080)
+			return prep_emulate_rd16rn12rs8rm0_wflags(insn, asi);
+
+		/* BXJ      : cccc 0001 0010 xxxx xxxx xxxx 0010 xxxx */
+		/* MSR      : cccc 0001 0x10 xxxx xxxx xxxx 0000 xxxx */
+		/* MRS spsr : cccc 0001 0100 xxxx xxxx xxxx 0000 xxxx */
 
+		/* Other instruction encodings aren't yet defined */
+		return INSN_REJECTED;
 	}
 
 	/* cccc 0001 0xx0 xxxx xxxx xxxx xxxx 0xx1 xxxx */
 	else if ((insn & 0x0f900090) == 0x01000010) {
 
-		/* BKPT : 1110 0001 0010 xxxx xxxx xxxx 0111 xxxx */
-		if ((insn & 0xfff000f0) == 0xe1200070)
-			return INSN_REJECTED;
-
 		/* BLX(2) : cccc 0001 0010 xxxx xxxx xxxx 0011 xxxx */
 		/* BX     : cccc 0001 0010 xxxx xxxx xxxx 0001 xxxx */
 		if ((insn & 0x0ff000d0) == 0x01200010) {
-			asi->insn[0] = truecc_insn(insn);
+			if ((insn & 0x0ff000ff) == 0x0120003f)
+				return INSN_REJECTED; /* BLX pc */
 			asi->insn_handler = simulate_blx2bx;
-			return INSN_GOOD;
+			return INSN_GOOD_NO_SLOT;
 		}
 
 		/* CLZ : cccc 0001 0110 xxxx xxxx xxxx 0001 xxxx */
@@ -1059,17 +1066,27 @@ space_cccc_000x(kprobe_opcode_t insn, struct arch_specific_insn *asi)
 		/* QSUB    : cccc 0001 0010 xxxx xxxx xxxx 0101 xxxx :Q */
 		/* QDADD   : cccc 0001 0100 xxxx xxxx xxxx 0101 xxxx :Q */
 		/* QDSUB   : cccc 0001 0110 xxxx xxxx xxxx 0101 xxxx :Q */
-		return prep_emulate_rd12rn16rm0_wflags(insn, asi);
+		if ((insn & 0x0f9000f0) == 0x01000050)
+			return prep_emulate_rd12rn16rm0_wflags(insn, asi);
+
+		/* BKPT : 1110 0001 0010 xxxx xxxx xxxx 0111 xxxx */
+		/* SMC  : cccc 0001 0110 xxxx xxxx xxxx 0111 xxxx */
+
+		/* Other instruction encodings aren't yet defined */
+		return INSN_REJECTED;
 	}
 
 	/* cccc 0000 xxxx xxxx xxxx xxxx xxxx 1001 xxxx */
-	else if ((insn & 0x0f000090) == 0x00000090) {
+	else if ((insn & 0x0f0000f0) == 0x00000090) {
 
 		/* MUL    : cccc 0000 0000 xxxx xxxx xxxx 1001 xxxx :   */
 		/* MULS   : cccc 0000 0001 xxxx xxxx xxxx 1001 xxxx :cc */
 		/* MLA    : cccc 0000 0010 xxxx xxxx xxxx 1001 xxxx :   */
 		/* MLAS   : cccc 0000 0011 xxxx xxxx xxxx 1001 xxxx :cc */
 		/* UMAAL  : cccc 0000 0100 xxxx xxxx xxxx 1001 xxxx :   */
+		/* undef  : cccc 0000 0101 xxxx xxxx xxxx 1001 xxxx :   */
+		/* MLS    : cccc 0000 0110 xxxx xxxx xxxx 1001 xxxx :   */
+		/* undef  : cccc 0000 0111 xxxx xxxx xxxx 1001 xxxx :   */
 		/* UMULL  : cccc 0000 1000 xxxx xxxx xxxx 1001 xxxx :   */
 		/* UMULLS : cccc 0000 1001 xxxx xxxx xxxx 1001 xxxx :cc */
 		/* UMLAL  : cccc 0000 1010 xxxx xxxx xxxx 1001 xxxx :   */
@@ -1078,13 +1095,15 @@ space_cccc_000x(kprobe_opcode_t insn, struct arch_specific_insn *asi)
 		/* SMULLS : cccc 0000 1101 xxxx xxxx xxxx 1001 xxxx :cc */
 		/* SMLAL  : cccc 0000 1110 xxxx xxxx xxxx 1001 xxxx :   */
 		/* SMLALS : cccc 0000 1111 xxxx xxxx xxxx 1001 xxxx :cc */
-		if ((insn & 0x0fe000f0) == 0x00000090) {
-		       return prep_emulate_rd16rs8rm0_wflags(insn, asi);
-		} else if  ((insn & 0x0fe000f0) == 0x00200090) {
-		       return prep_emulate_rd16rn12rs8rm0_wflags(insn, asi);
-		} else {
-		       return prep_emulate_rdhi16rdlo12rs8rm0_wflags(insn, asi);
-		}
+		if ((insn & 0x00d00000) == 0x00500000)
+			return INSN_REJECTED;
+		else if ((insn & 0x00e00000) == 0x00000000)
+			return prep_emulate_rd16rs8rm0_wflags(insn, asi);
+		else if ((insn & 0x00a00000) == 0x00200000)
+			return prep_emulate_rd16rn12rs8rm0_wflags(insn, asi);
+		else
+			return prep_emulate_rdhi16rdlo12rs8rm0_wflags(insn,
+									asi);
 	}
 
 	/* cccc 000x xxxx xxxx xxxx xxxx xxxx 1xx1 xxxx */
@@ -1092,23 +1111,45 @@ space_cccc_000x(kprobe_opcode_t insn, struct arch_specific_insn *asi)
 
 		/* SWP   : cccc 0001 0000 xxxx xxxx xxxx 1001 xxxx */
 		/* SWPB  : cccc 0001 0100 xxxx xxxx xxxx 1001 xxxx */
-		/* LDRD  : cccc 000x xxx0 xxxx xxxx xxxx 1101 xxxx */
-		/* STRD  : cccc 000x xxx0 xxxx xxxx xxxx 1111 xxxx */
+		/* ???   : cccc 0001 0x01 xxxx xxxx xxxx 1001 xxxx */
+		/* ???   : cccc 0001 0x10 xxxx xxxx xxxx 1001 xxxx */
+		/* ???   : cccc 0001 0x11 xxxx xxxx xxxx 1001 xxxx */
 		/* STREX : cccc 0001 1000 xxxx xxxx xxxx 1001 xxxx */
 		/* LDREX : cccc 0001 1001 xxxx xxxx xxxx 1001 xxxx */
+		/* STREXD: cccc 0001 1010 xxxx xxxx xxxx 1001 xxxx */
+		/* LDREXD: cccc 0001 1011 xxxx xxxx xxxx 1001 xxxx */
+		/* STREXB: cccc 0001 1100 xxxx xxxx xxxx 1001 xxxx */
+		/* LDREXB: cccc 0001 1101 xxxx xxxx xxxx 1001 xxxx */
+		/* STREXH: cccc 0001 1110 xxxx xxxx xxxx 1001 xxxx */
+		/* LDREXH: cccc 0001 1111 xxxx xxxx xxxx 1001 xxxx */
+
+		/* LDRD  : cccc 000x xxx0 xxxx xxxx xxxx 1101 xxxx */
+		/* STRD  : cccc 000x xxx0 xxxx xxxx xxxx 1111 xxxx */
 		/* LDRH  : cccc 000x xxx1 xxxx xxxx xxxx 1011 xxxx */
 		/* STRH  : cccc 000x xxx0 xxxx xxxx xxxx 1011 xxxx */
 		/* LDRSB : cccc 000x xxx1 xxxx xxxx xxxx 1101 xxxx */
 		/* LDRSH : cccc 000x xxx1 xxxx xxxx xxxx 1111 xxxx */
-		if ((insn & 0x0fb000f0) == 0x01000090) {
-			/* SWP/SWPB */
-			return prep_emulate_rd12rn16rm0_wflags(insn, asi);
+		if ((insn & 0x0f0000f0) == 0x01000090) {
+			if ((insn & 0x0fb000f0) == 0x01000090) {
+				/* SWP/SWPB */
+				return prep_emulate_rd12rn16rm0_wflags(insn,
+									asi);
+			} else {
+				/* STREX/LDREX variants and unallocaed space */
+				return INSN_REJECTED;
+			}
+
 		} else if ((insn & 0x0e1000d0) == 0x00000d0) {
 			/* STRD/LDRD */
+			if ((insn & 0x0000e000) == 0x0000e000)
+				return INSN_REJECTED;	/* Rd is LR or PC */
+			if (is_writeback(insn) && is_r15(insn, 16))
+				return INSN_REJECTED;	/* Writeback to PC */
+
 			insn &= 0xfff00fff;
 			insn |= 0x00002000;	/* Rn = r0, Rd = r2 */
-			if (insn & (1 << 22)) {
-				/* I bit */
+			if (!(insn & (1 << 22))) {
+				/* Register index */
 				insn &= ~0xf;
 				insn |= 1;	/* Rm = r1 */
 			}
@@ -1118,6 +1159,9 @@ space_cccc_000x(kprobe_opcode_t insn, struct arch_specific_insn *asi)
 			return INSN_GOOD;
 		}
 
+		/* LDRH/STRH/LDRSB/LDRSH */
+		if (is_r15(insn, 12))
+			return INSN_REJECTED;	/* Rd is PC */
 		return prep_emulate_ldr_str(insn, asi);
 	}
 
@@ -1125,7 +1169,7 @@ space_cccc_000x(kprobe_opcode_t insn, struct arch_specific_insn *asi)
 
 	/*
 	 * ALU op with S bit and Rd == 15 :
-	 * 	cccc 000x xxx1 xxxx 1111 xxxx xxxx xxxx
+	 *	cccc 000x xxx1 xxxx 1111 xxxx xxxx xxxx
 	 */
 	if ((insn & 0x0e10f000) == 0x0010f000)
 		return INSN_REJECTED;
@@ -1154,22 +1198,61 @@ space_cccc_000x(kprobe_opcode_t insn, struct arch_specific_insn *asi)
 		insn |= 0x00000200;     /* Rs = r2 */
 	}
 	asi->insn[0] = insn;
-	asi->insn_handler = (insn & (1 << 20)) ?  /* S-bit */
+
+	if ((insn & 0x0f900000) == 0x01100000) {
+		/*
+		 * TST : cccc 0001 0001 xxxx xxxx xxxx xxxx xxxx
+		 * TEQ : cccc 0001 0011 xxxx xxxx xxxx xxxx xxxx
+		 * CMP : cccc 0001 0101 xxxx xxxx xxxx xxxx xxxx
+		 * CMN : cccc 0001 0111 xxxx xxxx xxxx xxxx xxxx
+		 */
+		asi->insn_handler = emulate_alu_tests;
+	} else {
+		/* ALU ops which write to Rd */
+		asi->insn_handler = (insn & (1 << 20)) ?  /* S-bit */
 				emulate_alu_rwflags : emulate_alu_rflags;
+	}
 	return INSN_GOOD;
 }
 
 static enum kprobe_insn __kprobes
 space_cccc_001x(kprobe_opcode_t insn, struct arch_specific_insn *asi)
 {
+	/* MOVW  : cccc 0011 0000 xxxx xxxx xxxx xxxx xxxx */
+	/* MOVT  : cccc 0011 0100 xxxx xxxx xxxx xxxx xxxx */
+	if ((insn & 0x0fb00000) == 0x03000000)
+		return prep_emulate_rd12_modify(insn, asi);
+
+	/* hints : cccc 0011 0010 0000 xxxx xxxx xxxx xxxx */
+	if ((insn & 0x0fff0000) == 0x03200000) {
+		unsigned op2 = insn & 0x000000ff;
+		if (op2 == 0x01 || op2 == 0x04) {
+			/* YIELD : cccc 0011 0010 0000 xxxx xxxx 0000 0001 */
+			/* SEV   : cccc 0011 0010 0000 xxxx xxxx 0000 0100 */
+			asi->insn[0] = insn;
+			asi->insn_handler = emulate_none;
+			return INSN_GOOD;
+		} else if (op2 <= 0x03) {
+			/* NOP   : cccc 0011 0010 0000 xxxx xxxx 0000 0000 */
+			/* WFE   : cccc 0011 0010 0000 xxxx xxxx 0000 0010 */
+			/* WFI   : cccc 0011 0010 0000 xxxx xxxx 0000 0011 */
+			/*
+			 * We make WFE and WFI true NOPs to avoid stalls due
+			 * to missing events whilst processing the probe.
+			 */
+			asi->insn_handler = emulate_nop;
+			return INSN_GOOD_NO_SLOT;
+		}
+		/* For DBG and unallocated hints it's safest to reject them */
+		return INSN_REJECTED;
+	}
+
 	/*
 	 * MSR   : cccc 0011 0x10 xxxx xxxx xxxx xxxx xxxx
-	 * Undef : cccc 0011 0100 xxxx xxxx xxxx xxxx xxxx
 	 * ALU op with S bit and Rd == 15 :
 	 *	   cccc 001x xxx1 xxxx 1111 xxxx xxxx xxxx
 	 */
 	if ((insn & 0x0fb00000) == 0x03200000 ||	/* MSR */
-	    (insn & 0x0ff00000) == 0x03400000 ||	/* Undef */
 	    (insn & 0x0e10f000) == 0x0210f000)		/* ALU s-bit, R15  */
 		return INSN_REJECTED;
 
@@ -1180,10 +1263,22 @@ space_cccc_001x(kprobe_opcode_t insn, struct arch_specific_insn *asi)
 	 * *S (bit 20) updates condition codes
 	 * ADC/SBC/RSC reads the C flag
 	 */
-	insn &= 0xffff0fff;	/* Rd = r0 */
+	insn &= 0xfff00fff;	/* Rn = r0 and Rd = r0 */
 	asi->insn[0] = insn;
-	asi->insn_handler = (insn & (1 << 20)) ?  /* S-bit */
+
+	if ((insn & 0x0f900000) == 0x03100000) {
+		/*
+		 * TST : cccc 0011 0001 xxxx xxxx xxxx xxxx xxxx
+		 * TEQ : cccc 0011 0011 xxxx xxxx xxxx xxxx xxxx
+		 * CMP : cccc 0011 0101 xxxx xxxx xxxx xxxx xxxx
+		 * CMN : cccc 0011 0111 xxxx xxxx xxxx xxxx xxxx
+		 */
+		asi->insn_handler = emulate_alu_tests_imm;
+	} else {
+		/* ALU ops which write to Rd */
+		asi->insn_handler = (insn & (1 << 20)) ?  /* S-bit */
 			emulate_alu_imm_rwflags : emulate_alu_imm_rflags;
+	}
 	return INSN_GOOD;
 }
 
@@ -1192,6 +1287,8 @@ space_cccc_0110__1(kprobe_opcode_t insn, struct arch_specific_insn *asi)
 {
 	/* SEL : cccc 0110 1000 xxxx xxxx xxxx 1011 xxxx GE: !!! */
 	if ((insn & 0x0ff000f0) == 0x068000b0) {
+		if (is_r15(insn, 12))
+			return INSN_REJECTED;	/* Rd is PC */
 		insn &= 0xfff00ff0;	/* Rd = r0, Rn = r0 */
 		insn |= 0x00000001;	/* Rm = r1 */
 		asi->insn[0] = insn;
@@ -1205,6 +1302,8 @@ space_cccc_0110__1(kprobe_opcode_t insn, struct arch_specific_insn *asi)
 	/* USAT16 : cccc 0110 1110 xxxx xxxx xxxx 0011 xxxx :Q */
 	if ((insn & 0x0fa00030) == 0x06a00010 ||
 	    (insn & 0x0fb000f0) == 0x06a00030) {
+		if (is_r15(insn, 12))
+			return INSN_REJECTED;	/* Rd is PC */
 		insn &= 0xffff0ff0;	/* Rd = r0, Rm = r0 */
 		asi->insn[0] = insn;
 		asi->insn_handler = emulate_sat;
@@ -1213,57 +1312,101 @@ space_cccc_0110__1(kprobe_opcode_t insn, struct arch_specific_insn *asi)
 
 	/* REV    : cccc 0110 1011 xxxx xxxx xxxx 0011 xxxx */
 	/* REV16  : cccc 0110 1011 xxxx xxxx xxxx 1011 xxxx */
+	/* RBIT   : cccc 0110 1111 xxxx xxxx xxxx 0011 xxxx */
 	/* REVSH  : cccc 0110 1111 xxxx xxxx xxxx 1011 xxxx */
 	if ((insn & 0x0ff00070) == 0x06b00030 ||
-	    (insn & 0x0ff000f0) == 0x06f000b0)
+	    (insn & 0x0ff00070) == 0x06f00030)
 		return prep_emulate_rd12rm0(insn, asi);
 
+	/* ???       : cccc 0110 0000 xxxx xxxx xxxx xxx1 xxxx :   */
 	/* SADD16    : cccc 0110 0001 xxxx xxxx xxxx 0001 xxxx :GE */
 	/* SADDSUBX  : cccc 0110 0001 xxxx xxxx xxxx 0011 xxxx :GE */
 	/* SSUBADDX  : cccc 0110 0001 xxxx xxxx xxxx 0101 xxxx :GE */
 	/* SSUB16    : cccc 0110 0001 xxxx xxxx xxxx 0111 xxxx :GE */
 	/* SADD8     : cccc 0110 0001 xxxx xxxx xxxx 1001 xxxx :GE */
+	/* ???       : cccc 0110 0001 xxxx xxxx xxxx 1011 xxxx :   */
+	/* ???       : cccc 0110 0001 xxxx xxxx xxxx 1101 xxxx :   */
 	/* SSUB8     : cccc 0110 0001 xxxx xxxx xxxx 1111 xxxx :GE */
 	/* QADD16    : cccc 0110 0010 xxxx xxxx xxxx 0001 xxxx :   */
 	/* QADDSUBX  : cccc 0110 0010 xxxx xxxx xxxx 0011 xxxx :   */
 	/* QSUBADDX  : cccc 0110 0010 xxxx xxxx xxxx 0101 xxxx :   */
 	/* QSUB16    : cccc 0110 0010 xxxx xxxx xxxx 0111 xxxx :   */
 	/* QADD8     : cccc 0110 0010 xxxx xxxx xxxx 1001 xxxx :   */
+	/* ???       : cccc 0110 0010 xxxx xxxx xxxx 1011 xxxx :   */
+	/* ???       : cccc 0110 0010 xxxx xxxx xxxx 1101 xxxx :   */
 	/* QSUB8     : cccc 0110 0010 xxxx xxxx xxxx 1111 xxxx :   */
 	/* SHADD16   : cccc 0110 0011 xxxx xxxx xxxx 0001 xxxx :   */
 	/* SHADDSUBX : cccc 0110 0011 xxxx xxxx xxxx 0011 xxxx :   */
 	/* SHSUBADDX : cccc 0110 0011 xxxx xxxx xxxx 0101 xxxx :   */
 	/* SHSUB16   : cccc 0110 0011 xxxx xxxx xxxx 0111 xxxx :   */
 	/* SHADD8    : cccc 0110 0011 xxxx xxxx xxxx 1001 xxxx :   */
+	/* ???       : cccc 0110 0011 xxxx xxxx xxxx 1011 xxxx :   */
+	/* ???       : cccc 0110 0011 xxxx xxxx xxxx 1101 xxxx :   */
 	/* SHSUB8    : cccc 0110 0011 xxxx xxxx xxxx 1111 xxxx :   */
+	/* ???       : cccc 0110 0100 xxxx xxxx xxxx xxx1 xxxx :   */
 	/* UADD16    : cccc 0110 0101 xxxx xxxx xxxx 0001 xxxx :GE */
 	/* UADDSUBX  : cccc 0110 0101 xxxx xxxx xxxx 0011 xxxx :GE */
 	/* USUBADDX  : cccc 0110 0101 xxxx xxxx xxxx 0101 xxxx :GE */
 	/* USUB16    : cccc 0110 0101 xxxx xxxx xxxx 0111 xxxx :GE */
 	/* UADD8     : cccc 0110 0101 xxxx xxxx xxxx 1001 xxxx :GE */
+	/* ???       : cccc 0110 0101 xxxx xxxx xxxx 1011 xxxx :   */
+	/* ???       : cccc 0110 0101 xxxx xxxx xxxx 1101 xxxx :   */
 	/* USUB8     : cccc 0110 0101 xxxx xxxx xxxx 1111 xxxx :GE */
 	/* UQADD16   : cccc 0110 0110 xxxx xxxx xxxx 0001 xxxx :   */
 	/* UQADDSUBX : cccc 0110 0110 xxxx xxxx xxxx 0011 xxxx :   */
 	/* UQSUBADDX : cccc 0110 0110 xxxx xxxx xxxx 0101 xxxx :   */
 	/* UQSUB16   : cccc 0110 0110 xxxx xxxx xxxx 0111 xxxx :   */
 	/* UQADD8    : cccc 0110 0110 xxxx xxxx xxxx 1001 xxxx :   */
+	/* ???       : cccc 0110 0110 xxxx xxxx xxxx 1011 xxxx :   */
+	/* ???       : cccc 0110 0110 xxxx xxxx xxxx 1101 xxxx :   */
 	/* UQSUB8    : cccc 0110 0110 xxxx xxxx xxxx 1111 xxxx :   */
 	/* UHADD16   : cccc 0110 0111 xxxx xxxx xxxx 0001 xxxx :   */
 	/* UHADDSUBX : cccc 0110 0111 xxxx xxxx xxxx 0011 xxxx :   */
 	/* UHSUBADDX : cccc 0110 0111 xxxx xxxx xxxx 0101 xxxx :   */
 	/* UHSUB16   : cccc 0110 0111 xxxx xxxx xxxx 0111 xxxx :   */
 	/* UHADD8    : cccc 0110 0111 xxxx xxxx xxxx 1001 xxxx :   */
+	/* ???       : cccc 0110 0111 xxxx xxxx xxxx 1011 xxxx :   */
+	/* ???       : cccc 0110 0111 xxxx xxxx xxxx 1101 xxxx :   */
 	/* UHSUB8    : cccc 0110 0111 xxxx xxxx xxxx 1111 xxxx :   */
+	if ((insn & 0x0f800010) == 0x06000010) {
+		if ((insn & 0x00300000) == 0x00000000 ||
+		    (insn & 0x000000e0) == 0x000000a0 ||
+		    (insn & 0x000000e0) == 0x000000c0)
+			return INSN_REJECTED;	/* Unallocated space */
+		return prep_emulate_rd12rn16rm0_wflags(insn, asi);
+	}
+
 	/* PKHBT     : cccc 0110 1000 xxxx xxxx xxxx x001 xxxx :   */
 	/* PKHTB     : cccc 0110 1000 xxxx xxxx xxxx x101 xxxx :   */
+	if ((insn & 0x0ff00030) == 0x06800010)
+		return prep_emulate_rd12rn16rm0_wflags(insn, asi);
+
 	/* SXTAB16   : cccc 0110 1000 xxxx xxxx xxxx 0111 xxxx :   */
-	/* SXTB      : cccc 0110 1010 xxxx xxxx xxxx 0111 xxxx :   */
+	/* SXTB16    : cccc 0110 1000 1111 xxxx xxxx 0111 xxxx :   */
+	/* ???       : cccc 0110 1001 xxxx xxxx xxxx 0111 xxxx :   */
 	/* SXTAB     : cccc 0110 1010 xxxx xxxx xxxx 0111 xxxx :   */
+	/* SXTB      : cccc 0110 1010 1111 xxxx xxxx 0111 xxxx :   */
 	/* SXTAH     : cccc 0110 1011 xxxx xxxx xxxx 0111 xxxx :   */
+	/* SXTH      : cccc 0110 1011 1111 xxxx xxxx 0111 xxxx :   */
 	/* UXTAB16   : cccc 0110 1100 xxxx xxxx xxxx 0111 xxxx :   */
+	/* UXTB16    : cccc 0110 1100 1111 xxxx xxxx 0111 xxxx :   */
+	/* ???       : cccc 0110 1101 xxxx xxxx xxxx 0111 xxxx :   */
 	/* UXTAB     : cccc 0110 1110 xxxx xxxx xxxx 0111 xxxx :   */
+	/* UXTB      : cccc 0110 1110 1111 xxxx xxxx 0111 xxxx :   */
 	/* UXTAH     : cccc 0110 1111 xxxx xxxx xxxx 0111 xxxx :   */
-	return prep_emulate_rd12rn16rm0_wflags(insn, asi);
+	/* UXTH      : cccc 0110 1111 1111 xxxx xxxx 0111 xxxx :   */
+	if ((insn & 0x0f8000f0) == 0x06800070) {
+		if ((insn & 0x00300000) == 0x00100000)
+			return INSN_REJECTED;	/* Unallocated space */
+
+		if ((insn & 0x000f0000) == 0x000f0000)
+			return prep_emulate_rd12rm0(insn, asi);
+		else
+			return prep_emulate_rd12rn16rm0_wflags(insn, asi);
+	}
+
+	/* Other instruction encodings aren't yet defined */
+	return INSN_REJECTED;
 }
 
 static enum kprobe_insn __kprobes
@@ -1273,29 +1416,49 @@ space_cccc_0111__1(kprobe_opcode_t insn, struct arch_specific_insn *asi)
 	if ((insn & 0x0ff000f0) == 0x03f000f0)
 		return INSN_REJECTED;
 
-	/* USADA8 : cccc 0111 1000 xxxx xxxx xxxx 0001 xxxx */
-	/* USAD8  : cccc 0111 1000 xxxx 1111 xxxx 0001 xxxx */
-	if ((insn & 0x0ff000f0) == 0x07800010)
-		 return prep_emulate_rd16rn12rs8rm0_wflags(insn, asi);
-
 	/* SMLALD : cccc 0111 0100 xxxx xxxx xxxx 00x1 xxxx */
 	/* SMLSLD : cccc 0111 0100 xxxx xxxx xxxx 01x1 xxxx */
 	if ((insn & 0x0ff00090) == 0x07400010)
 		return prep_emulate_rdhi16rdlo12rs8rm0_wflags(insn, asi);
 
 	/* SMLAD  : cccc 0111 0000 xxxx xxxx xxxx 00x1 xxxx :Q */
+	/* SMUAD  : cccc 0111 0000 xxxx 1111 xxxx 00x1 xxxx :Q */
 	/* SMLSD  : cccc 0111 0000 xxxx xxxx xxxx 01x1 xxxx :Q */
+	/* SMUSD  : cccc 0111 0000 xxxx 1111 xxxx 01x1 xxxx :  */
 	/* SMMLA  : cccc 0111 0101 xxxx xxxx xxxx 00x1 xxxx :  */
-	/* SMMLS  : cccc 0111 0101 xxxx xxxx xxxx 11x1 xxxx :  */
+	/* SMMUL  : cccc 0111 0101 xxxx 1111 xxxx 00x1 xxxx :  */
+	/* USADA8 : cccc 0111 1000 xxxx xxxx xxxx 0001 xxxx :  */
+	/* USAD8  : cccc 0111 1000 xxxx 1111 xxxx 0001 xxxx :  */
 	if ((insn & 0x0ff00090) == 0x07000010 ||
 	    (insn & 0x0ff000d0) == 0x07500010 ||
-	    (insn & 0x0ff000d0) == 0x075000d0)
+	    (insn & 0x0ff000f0) == 0x07800010) {
+
+		if ((insn & 0x0000f000) == 0x0000f000)
+			return prep_emulate_rd16rs8rm0_wflags(insn, asi);
+		else
+			return prep_emulate_rd16rn12rs8rm0_wflags(insn, asi);
+	}
+
+	/* SMMLS  : cccc 0111 0101 xxxx xxxx xxxx 11x1 xxxx :  */
+	if ((insn & 0x0ff000d0) == 0x075000d0)
 		return prep_emulate_rd16rn12rs8rm0_wflags(insn, asi);
 
-	/* SMUSD  : cccc 0111 0000 xxxx xxxx xxxx 01x1 xxxx :  */
-	/* SMUAD  : cccc 0111 0000 xxxx 1111 xxxx 00x1 xxxx :Q */
-	/* SMMUL  : cccc 0111 0101 xxxx 1111 xxxx 00x1 xxxx :  */
-	return prep_emulate_rd16rs8rm0_wflags(insn, asi);
+	/* SBFX   : cccc 0111 101x xxxx xxxx xxxx x101 xxxx :  */
+	/* UBFX   : cccc 0111 111x xxxx xxxx xxxx x101 xxxx :  */
+	if ((insn & 0x0fa00070) == 0x07a00050)
+		return prep_emulate_rd12rm0(insn, asi);
+
+	/* BFI    : cccc 0111 110x xxxx xxxx xxxx x001 xxxx :  */
+	/* BFC    : cccc 0111 110x xxxx xxxx xxxx x001 1111 :  */
+	if ((insn & 0x0fe00070) == 0x07c00010) {
+
+		if ((insn & 0x0000000f) == 0x0000000f)
+			return prep_emulate_rd12_modify(insn, asi);
+		else
+			return prep_emulate_rd12rn0_modify(insn, asi);
+	}
+
+	return INSN_REJECTED;
 }
 
 static enum kprobe_insn __kprobes
@@ -1309,6 +1472,10 @@ space_cccc_01xx(kprobe_opcode_t insn, struct arch_specific_insn *asi)
 	/* STRB  : cccc 01xx x1x0 xxxx xxxx xxxx xxxx xxxx */
 	/* STRBT : cccc 01x0 x110 xxxx xxxx xxxx xxxx xxxx */
 	/* STRT  : cccc 01x0 x010 xxxx xxxx xxxx xxxx xxxx */
+
+	if ((insn & 0x00500000) == 0x00500000 && is_r15(insn, 12))
+		return INSN_REJECTED;	/* LDRB into PC */
+
 	return prep_emulate_ldr_str(insn, asi);
 }
 
@@ -1323,10 +1490,9 @@ space_cccc_100x(kprobe_opcode_t insn, struct arch_specific_insn *asi)
 
 	/* LDM(1) : cccc 100x x0x1 xxxx xxxx xxxx xxxx xxxx */
 	/* STM(1) : cccc 100x x0x0 xxxx xxxx xxxx xxxx xxxx */
-	asi->insn[0] = truecc_insn(insn);
 	asi->insn_handler = ((insn & 0x108000) == 0x008000) ? /* STM & R15 */
 				simulate_stm1_pc : simulate_ldm1stm1;
-	return INSN_GOOD;
+	return INSN_GOOD_NO_SLOT;
 }
 
 static enum kprobe_insn __kprobes
@@ -1334,58 +1500,117 @@ space_cccc_101x(kprobe_opcode_t insn, struct arch_specific_insn *asi)
 {
 	/* B  : cccc 1010 xxxx xxxx xxxx xxxx xxxx xxxx */
 	/* BL : cccc 1011 xxxx xxxx xxxx xxxx xxxx xxxx */
-	asi->insn[0] = truecc_insn(insn);
 	asi->insn_handler = simulate_bbl;
-	return INSN_GOOD;
+	return INSN_GOOD_NO_SLOT;
 }
 
 static enum kprobe_insn __kprobes
-space_cccc_1100_010x(kprobe_opcode_t insn, struct arch_specific_insn *asi)
+space_cccc_11xx(kprobe_opcode_t insn, struct arch_specific_insn *asi)
 {
+	/* Coprocessor instructions... */
 	/* MCRR : cccc 1100 0100 xxxx xxxx xxxx xxxx xxxx : (Rd!=Rn) */
 	/* MRRC : cccc 1100 0101 xxxx xxxx xxxx xxxx xxxx : (Rd!=Rn) */
-	insn &= 0xfff00fff;
-	insn |= 0x00001000;	/* Rn = r0, Rd = r1 */
-	asi->insn[0] = insn;
-	asi->insn_handler = (insn & (1 << 20)) ? emulate_mrrc : emulate_mcrr;
-	return INSN_GOOD;
+	/* LDC  : cccc 110x xxx1 xxxx xxxx xxxx xxxx xxxx */
+	/* STC  : cccc 110x xxx0 xxxx xxxx xxxx xxxx xxxx */
+	/* CDP  : cccc 1110 xxxx xxxx xxxx xxxx xxx0 xxxx */
+	/* MCR  : cccc 1110 xxx0 xxxx xxxx xxxx xxx1 xxxx */
+	/* MRC  : cccc 1110 xxx1 xxxx xxxx xxxx xxx1 xxxx */
+
+	/* SVC  : cccc 1111 xxxx xxxx xxxx xxxx xxxx xxxx */
+
+	return INSN_REJECTED;
 }
 
-static enum kprobe_insn __kprobes
-space_cccc_110x(kprobe_opcode_t insn, struct arch_specific_insn *asi)
+static unsigned long __kprobes __check_eq(unsigned long cpsr)
 {
-	/* LDC : cccc 110x xxx1 xxxx xxxx xxxx xxxx xxxx */
-	/* STC : cccc 110x xxx0 xxxx xxxx xxxx xxxx xxxx */
-	insn &= 0xfff0ffff;	/* Rn = r0 */
-	asi->insn[0] = insn;
-	asi->insn_handler = emulate_ldcstc;
-	return INSN_GOOD;
+	return cpsr & PSR_Z_BIT;
 }
 
-static enum kprobe_insn __kprobes
-space_cccc_111x(kprobe_opcode_t insn, struct arch_specific_insn *asi)
+static unsigned long __kprobes __check_ne(unsigned long cpsr)
 {
-	/* BKPT : 1110 0001 0010 xxxx xxxx xxxx 0111 xxxx */
-	/* SWI  : cccc 1111 xxxx xxxx xxxx xxxx xxxx xxxx */
-	if ((insn & 0xfff000f0) == 0xe1200070 ||
-	    (insn & 0x0f000000) == 0x0f000000)
-		return INSN_REJECTED;
+	return (~cpsr) & PSR_Z_BIT;
+}
 
-	/* CDP : cccc 1110 xxxx xxxx xxxx xxxx xxx0 xxxx */
-	if ((insn & 0x0f000010) == 0x0e000000) {
-		asi->insn[0] = insn;
-		asi->insn_handler = emulate_none;
-		return INSN_GOOD;
-	}
+static unsigned long __kprobes __check_cs(unsigned long cpsr)
+{
+	return cpsr & PSR_C_BIT;
+}
 
-	/* MCR : cccc 1110 xxx0 xxxx xxxx xxxx xxx1 xxxx */
-	/* MRC : cccc 1110 xxx1 xxxx xxxx xxxx xxx1 xxxx */
-	insn &= 0xffff0fff;	/* Rd = r0 */
-	asi->insn[0] = insn;
-	asi->insn_handler = (insn & (1 << 20)) ? emulate_rd12 : emulate_ird12;
-	return INSN_GOOD;
+static unsigned long __kprobes __check_cc(unsigned long cpsr)
+{
+	return (~cpsr) & PSR_C_BIT;
+}
+
+static unsigned long __kprobes __check_mi(unsigned long cpsr)
+{
+	return cpsr & PSR_N_BIT;
+}
+
+static unsigned long __kprobes __check_pl(unsigned long cpsr)
+{
+	return (~cpsr) & PSR_N_BIT;
+}
+
+static unsigned long __kprobes __check_vs(unsigned long cpsr)
+{
+	return cpsr & PSR_V_BIT;
+}
+
+static unsigned long __kprobes __check_vc(unsigned long cpsr)
+{
+	return (~cpsr) & PSR_V_BIT;
+}
+
+static unsigned long __kprobes __check_hi(unsigned long cpsr)
+{
+	cpsr &= ~(cpsr >> 1); /* PSR_C_BIT &= ~PSR_Z_BIT */
+	return cpsr & PSR_C_BIT;
 }
 
+static unsigned long __kprobes __check_ls(unsigned long cpsr)
+{
+	cpsr &= ~(cpsr >> 1); /* PSR_C_BIT &= ~PSR_Z_BIT */
+	return (~cpsr) & PSR_C_BIT;
+}
+
+static unsigned long __kprobes __check_ge(unsigned long cpsr)
+{
+	cpsr ^= (cpsr << 3); /* PSR_N_BIT ^= PSR_V_BIT */
+	return (~cpsr) & PSR_N_BIT;
+}
+
+static unsigned long __kprobes __check_lt(unsigned long cpsr)
+{
+	cpsr ^= (cpsr << 3); /* PSR_N_BIT ^= PSR_V_BIT */
+	return cpsr & PSR_N_BIT;
+}
+
+static unsigned long __kprobes __check_gt(unsigned long cpsr)
+{
+	unsigned long temp = cpsr ^ (cpsr << 3); /* PSR_N_BIT ^= PSR_V_BIT */
+	temp |= (cpsr << 1);			 /* PSR_N_BIT |= PSR_Z_BIT */
+	return (~temp) & PSR_N_BIT;
+}
+
+static unsigned long __kprobes __check_le(unsigned long cpsr)
+{
+	unsigned long temp = cpsr ^ (cpsr << 3); /* PSR_N_BIT ^= PSR_V_BIT */
+	temp |= (cpsr << 1);			 /* PSR_N_BIT |= PSR_Z_BIT */
+	return temp & PSR_N_BIT;
+}
+
+static unsigned long __kprobes __check_al(unsigned long cpsr)
+{
+	return true;
+}
+
+static kprobe_check_cc * const condition_checks[16] = {
+	&__check_eq, &__check_ne, &__check_cs, &__check_cc,
+	&__check_mi, &__check_pl, &__check_vs, &__check_vc,
+	&__check_hi, &__check_ls, &__check_ge, &__check_lt,
+	&__check_gt, &__check_le, &__check_al, &__check_al
+};
+
 /* Return:
  *   INSN_REJECTED     If instruction is one not allowed to kprobe,
  *   INSN_GOOD         If instruction is supported and uses instruction slot,
@@ -1401,133 +1626,45 @@ space_cccc_111x(kprobe_opcode_t insn, struct arch_specific_insn *asi)
 enum kprobe_insn __kprobes
 arm_kprobe_decode_insn(kprobe_opcode_t insn, struct arch_specific_insn *asi)
 {
+	asi->insn_check_cc = condition_checks[insn>>28];
 	asi->insn[1] = KPROBE_RETURN_INSTRUCTION;
 
-	if ((insn & 0xf0000000) == 0xf0000000) {
+	if ((insn & 0xf0000000) == 0xf0000000)
 
 		return space_1111(insn, asi);
 
-	} else if ((insn & 0x0e000000) == 0x00000000) {
+	else if ((insn & 0x0e000000) == 0x00000000)
 
 		return space_cccc_000x(insn, asi);
 
-	} else if ((insn & 0x0e000000) == 0x02000000) {
+	else if ((insn & 0x0e000000) == 0x02000000)
 
 		return space_cccc_001x(insn, asi);
 
-	} else if ((insn & 0x0f000010) == 0x06000010) {
+	else if ((insn & 0x0f000010) == 0x06000010)
 
 		return space_cccc_0110__1(insn, asi);
 
-	} else if ((insn & 0x0f000010) == 0x07000010) {
+	else if ((insn & 0x0f000010) == 0x07000010)
 
 		return space_cccc_0111__1(insn, asi);
 
-	} else if ((insn & 0x0c000000) == 0x04000000) {
+	else if ((insn & 0x0c000000) == 0x04000000)
 
 		return space_cccc_01xx(insn, asi);
 
-	} else if ((insn & 0x0e000000) == 0x08000000) {
+	else if ((insn & 0x0e000000) == 0x08000000)
 
 		return space_cccc_100x(insn, asi);
 
-	} else if ((insn & 0x0e000000) == 0x0a000000) {
+	else if ((insn & 0x0e000000) == 0x0a000000)
 
 		return space_cccc_101x(insn, asi);
 
-	} else if ((insn & 0x0fe00000) == 0x0c400000) {
-
-		return space_cccc_1100_010x(insn, asi);
-
-	} else if ((insn & 0x0e000000) == 0x0c000000) {
-
-		return space_cccc_110x(insn, asi);
-
-	}
-
-	return space_cccc_111x(insn, asi);
+	return space_cccc_11xx(insn, asi);
 }
 
 void __init arm_kprobe_decode_init(void)
 {
 	find_str_pc_offset();
 }
-
-
-/*
- * All ARM instructions listed below.
- *
- * Instructions and their general purpose registers are given.
- * If a particular register may not use R15, it is prefixed with a "!".
- * If marked with a "*" means the value returned by reading R15
- * is implementation defined.
- *
- * ADC/ADD/AND/BIC/CMN/CMP/EOR/MOV/MVN/ORR/RSB/RSC/SBC/SUB/TEQ
- *     TST: Rd, Rn, Rm, !Rs
- * BX: Rm
- * BLX(2): !Rm
- * BX: Rm (R15 legal, but discouraged)
- * BXJ: !Rm,
- * CLZ: !Rd, !Rm
- * CPY: Rd, Rm
- * LDC/2,STC/2 immediate offset & unindex: Rn
- * LDC/2,STC/2 immediate pre/post-indexed: !Rn
- * LDM(1/3): !Rn, register_list
- * LDM(2): !Rn, !register_list
- * LDR,STR,PLD immediate offset: Rd, Rn
- * LDR,STR,PLD register offset: Rd, Rn, !Rm
- * LDR,STR,PLD scaled register offset: Rd, !Rn, !Rm
- * LDR,STR immediate pre/post-indexed: Rd, !Rn
- * LDR,STR register pre/post-indexed: Rd, !Rn, !Rm
- * LDR,STR scaled register pre/post-indexed: Rd, !Rn, !Rm
- * LDRB,STRB immediate offset: !Rd, Rn
- * LDRB,STRB register offset: !Rd, Rn, !Rm
- * LDRB,STRB scaled register offset: !Rd, !Rn, !Rm
- * LDRB,STRB immediate pre/post-indexed: !Rd, !Rn
- * LDRB,STRB register pre/post-indexed: !Rd, !Rn, !Rm
- * LDRB,STRB scaled register pre/post-indexed: !Rd, !Rn, !Rm
- * LDRT,LDRBT,STRBT immediate pre/post-indexed: !Rd, !Rn
- * LDRT,LDRBT,STRBT register pre/post-indexed: !Rd, !Rn, !Rm
- * LDRT,LDRBT,STRBT scaled register pre/post-indexed: !Rd, !Rn, !Rm
- * LDRH/SH/SB/D,STRH/SH/SB/D immediate offset: !Rd, Rn
- * LDRH/SH/SB/D,STRH/SH/SB/D register offset: !Rd, Rn, !Rm
- * LDRH/SH/SB/D,STRH/SH/SB/D immediate pre/post-indexed: !Rd, !Rn
- * LDRH/SH/SB/D,STRH/SH/SB/D register pre/post-indexed: !Rd, !Rn, !Rm
- * LDREX: !Rd, !Rn
- * MCR/2: !Rd
- * MCRR/2,MRRC/2: !Rd, !Rn
- * MLA: !Rd, !Rn, !Rm, !Rs
- * MOV: Rd
- * MRC/2: !Rd (if Rd==15, only changes cond codes, not the register)
- * MRS,MSR: !Rd
- * MUL: !Rd, !Rm, !Rs
- * PKH{BT,TB}: !Rd, !Rn, !Rm
- * QDADD,[U]QADD/16/8/SUBX: !Rd, !Rm, !Rn
- * QDSUB,[U]QSUB/16/8/ADDX: !Rd, !Rm, !Rn
- * REV/16/SH: !Rd, !Rm
- * RFE: !Rn
- * {S,U}[H]ADD{16,8,SUBX},{S,U}[H]SUB{16,8,ADDX}: !Rd, !Rn, !Rm
- * SEL: !Rd, !Rn, !Rm
- * SMLA<x><y>,SMLA{D,W<y>},SMLSD,SMML{A,S}: !Rd, !Rn, !Rm, !Rs
- * SMLAL<x><y>,SMLA{D,LD},SMLSLD,SMMULL,SMULW<y>: !RdHi, !RdLo, !Rm, !Rs
- * SMMUL,SMUAD,SMUL<x><y>,SMUSD: !Rd, !Rm, !Rs
- * SSAT/16: !Rd, !Rm
- * STM(1/2): !Rn, register_list* (R15 in reg list not recommended)
- * STRT immediate pre/post-indexed: Rd*, !Rn
- * STRT register pre/post-indexed: Rd*, !Rn, !Rm
- * STRT scaled register pre/post-indexed: Rd*, !Rn, !Rm
- * STREX: !Rd, !Rn, !Rm
- * SWP/B: !Rd, !Rn, !Rm
- * {S,U}XTA{B,B16,H}: !Rd, !Rn, !Rm
- * {S,U}XT{B,B16,H}: !Rd, !Rm
- * UM{AA,LA,UL}L: !RdHi, !RdLo, !Rm, !Rs
- * USA{D8,A8,T,T16}: !Rd, !Rm, !Rs
- *
- * May transfer control by writing R15 (possible mode changes or alternate
- * mode accesses marked by "*"):
- * ALU op (* with s-bit), B, BL, BKPT, BLX(1/2), BX, BXJ, CPS*, CPY,
- * LDM(1), LDM(2/3)*, LDR, MOV, RFE*, SWI*
- *
- * Instructions that do not take general registers, nor transfer control:
- * CDP/2, SETEND, SRS*
- */
diff --git a/arch/arm/kernel/kprobes.c b/arch/arm/kernel/kprobes.c
index 2ba7deb..1656c87 100644
--- a/arch/arm/kernel/kprobes.c
+++ b/arch/arm/kernel/kprobes.c
@@ -134,7 +134,8 @@ static void __kprobes singlestep(struct kprobe *p, struct pt_regs *regs,
 				 struct kprobe_ctlblk *kcb)
 {
 	regs->ARM_pc += 4;
-	p->ainsn.insn_handler(p, regs);
+	if (p->ainsn.insn_check_cc(regs->ARM_cpsr))
+		p->ainsn.insn_handler(p, regs);
 }
 
 /*
diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c
index 979da39..139e3c8 100644
--- a/arch/arm/kernel/perf_event.c
+++ b/arch/arm/kernel/perf_event.c
@@ -746,7 +746,8 @@ perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
 
 	tail = (struct frame_tail __user *)regs->ARM_fp - 1;
 
-	while (tail && !((unsigned long)tail & 0x3))
+	while ((entry->nr < PERF_MAX_STACK_DEPTH) &&
+	       tail && !((unsigned long)tail & 0x3))
 		tail = user_backtrace(tail, entry);
 }
 
diff --git a/arch/arm/kernel/ptrace.c b/arch/arm/kernel/ptrace.c
index 2bf27f3..8182f45 100644
--- a/arch/arm/kernel/ptrace.c
+++ b/arch/arm/kernel/ptrace.c
@@ -767,12 +767,20 @@ long arch_ptrace(struct task_struct *child, long request,
 
 #ifdef CONFIG_HAVE_HW_BREAKPOINT
 		case PTRACE_GETHBPREGS:
+			if (ptrace_get_breakpoints(child) < 0)
+				return -ESRCH;
+
 			ret = ptrace_gethbpregs(child, addr,
 						(unsigned long __user *)data);
+			ptrace_put_breakpoints(child);
 			break;
 		case PTRACE_SETHBPREGS:
+			if (ptrace_get_breakpoints(child) < 0)
+				return -ESRCH;
+
 			ret = ptrace_sethbpregs(child, addr,
 						(unsigned long __user *)data);
+			ptrace_put_breakpoints(child);
 			break;
 #endif
 
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index 7a561eb..007a0a9 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -479,7 +479,7 @@ static void broadcast_timer_set_mode(enum clock_event_mode mode,
 {
 }
 
-static void broadcast_timer_setup(struct clock_event_device *evt)
+static void __cpuinit broadcast_timer_setup(struct clock_event_device *evt)
 {
 	evt->name	= "dummy_timer";
 	evt->features	= CLOCK_EVT_FEAT_ONESHOT |
diff --git a/arch/arm/kernel/sys_oabi-compat.c b/arch/arm/kernel/sys_oabi-compat.c
index 4ad8da1..af0aaeb 100644
--- a/arch/arm/kernel/sys_oabi-compat.c
+++ b/arch/arm/kernel/sys_oabi-compat.c
@@ -311,7 +311,7 @@ asmlinkage long sys_oabi_semtimedop(int semid,
 	long err;
 	int i;
 
-	if (nsops < 1)
+	if (nsops < 1 || nsops > SEMOPM)
 		return -EINVAL;
 	sops = kmalloc(sizeof(*sops) * nsops, GFP_KERNEL);
 	if (!sops)
diff --git a/arch/arm/mach-at91/Kconfig b/arch/arm/mach-at91/Kconfig
index 1939023..2d299bf 100644
--- a/arch/arm/mach-at91/Kconfig
+++ b/arch/arm/mach-at91/Kconfig
@@ -83,6 +83,7 @@ config ARCH_AT91CAP9
 	select CPU_ARM926T
 	select GENERIC_CLOCKEVENTS
 	select HAVE_FB_ATMEL
+	select HAVE_NET_MACB
 
 config ARCH_AT572D940HF
 	bool "AT572D940HF"
diff --git a/arch/arm/mach-at91/board-eb01.c b/arch/arm/mach-at91/board-eb01.c
index 1f9d3cb..d8df59a 100644
--- a/arch/arm/mach-at91/board-eb01.c
+++ b/arch/arm/mach-at91/board-eb01.c
@@ -30,6 +30,11 @@
 #include <mach/board.h>
 #include "generic.h"
 
+static void __init at91eb01_init_irq(void)
+{
+	at91x40_init_interrupts(NULL);
+}
+
 static void __init at91eb01_map_io(void)
 {
 	at91x40_initialize(40000000);
@@ -38,7 +43,7 @@ static void __init at91eb01_map_io(void)
 MACHINE_START(AT91EB01, "Atmel AT91 EB01")
 	/* Maintainer: Greg Ungerer <gerg@snapgear.com> */
 	.timer		= &at91x40_timer,
-	.init_irq	= at91x40_init_interrupts,
+	.init_irq	= at91eb01_init_irq,
 	.map_io		= at91eb01_map_io,
 MACHINE_END
 
diff --git a/arch/arm/mach-at91/include/mach/cpu.h b/arch/arm/mach-at91/include/mach/cpu.h
index 3bef931..0700f21 100644
--- a/arch/arm/mach-at91/include/mach/cpu.h
+++ b/arch/arm/mach-at91/include/mach/cpu.h
@@ -27,6 +27,7 @@
 #define ARCH_ID_AT91SAM9G45	0x819b05a0
 #define ARCH_ID_AT91SAM9G45MRL	0x819b05a2	/* aka 9G45-ES2 & non ES lots */
 #define ARCH_ID_AT91SAM9G45ES	0x819b05a1	/* 9G45-ES (Engineering Sample) */
+#define ARCH_ID_AT91SAM9X5	0x819a05a0
 #define ARCH_ID_AT91CAP9	0x039A03A0
 
 #define ARCH_ID_AT91SAM9XE128	0x329973a0
@@ -55,6 +56,12 @@ static inline unsigned long at91_cpu_fully_identify(void)
 #define ARCH_EXID_AT91SAM9G46	0x00000003
 #define ARCH_EXID_AT91SAM9G45	0x00000004
 
+#define ARCH_EXID_AT91SAM9G15	0x00000000
+#define ARCH_EXID_AT91SAM9G35	0x00000001
+#define ARCH_EXID_AT91SAM9X35	0x00000002
+#define ARCH_EXID_AT91SAM9G25	0x00000003
+#define ARCH_EXID_AT91SAM9X25	0x00000004
+
 static inline unsigned long at91_exid_identify(void)
 {
 	return at91_sys_read(AT91_DBGU_EXID);
@@ -143,6 +150,27 @@ static inline unsigned long at91cap9_rev_identify(void)
 #define cpu_is_at91sam9m11()	(0)
 #endif
 
+#ifdef CONFIG_ARCH_AT91SAM9X5
+#define cpu_is_at91sam9x5()	(at91_cpu_identify() == ARCH_ID_AT91SAM9X5)
+#define cpu_is_at91sam9g15()	(cpu_is_at91sam9x5() && \
+				(at91_exid_identify() == ARCH_EXID_AT91SAM9G15))
+#define cpu_is_at91sam9g35()	(cpu_is_at91sam9x5() && \
+				(at91_exid_identify() == ARCH_EXID_AT91SAM9G35))
+#define cpu_is_at91sam9x35()	(cpu_is_at91sam9x5() && \
+				(at91_exid_identify() == ARCH_EXID_AT91SAM9X35))
+#define cpu_is_at91sam9g25()	(cpu_is_at91sam9x5() && \
+				(at91_exid_identify() == ARCH_EXID_AT91SAM9G25))
+#define cpu_is_at91sam9x25()	(cpu_is_at91sam9x5() && \
+				(at91_exid_identify() == ARCH_EXID_AT91SAM9X25))
+#else
+#define cpu_is_at91sam9x5()	(0)
+#define cpu_is_at91sam9g15()	(0)
+#define cpu_is_at91sam9g35()	(0)
+#define cpu_is_at91sam9x35()	(0)
+#define cpu_is_at91sam9g25()	(0)
+#define cpu_is_at91sam9x25()	(0)
+#endif
+
 #ifdef CONFIG_ARCH_AT91CAP9
 #define cpu_is_at91cap9()	(at91_cpu_identify() == ARCH_ID_AT91CAP9)
 #define cpu_is_at91cap9_revB()	(at91cap9_rev_identify() == ARCH_REVISION_CAP9_B)
diff --git a/arch/arm/mach-davinci/Kconfig b/arch/arm/mach-davinci/Kconfig
index 32f1479..c0deaca 100644
--- a/arch/arm/mach-davinci/Kconfig
+++ b/arch/arm/mach-davinci/Kconfig
@@ -63,6 +63,7 @@ config MACH_DAVINCI_EVM
 	depends on ARCH_DAVINCI_DM644x
 	select MISC_DEVICES
 	select EEPROM_AT24
+	select I2C
 	help
 	  Configure this option to specify the whether the board used
 	  for development is a DM644x EVM
@@ -72,6 +73,7 @@ config MACH_SFFSDR
 	depends on ARCH_DAVINCI_DM644x
 	select MISC_DEVICES
 	select EEPROM_AT24
+	select I2C
 	help
 	  Say Y here to select the Lyrtech Small Form Factor
 	  Software Defined Radio (SFFSDR) board.
@@ -105,6 +107,7 @@ config MACH_DAVINCI_DM6467_EVM
 	select MACH_DAVINCI_DM6467TEVM
 	select MISC_DEVICES
 	select EEPROM_AT24
+	select I2C
 	help
 	  Configure this option to specify the whether the board used
 	  for development is a DM6467 EVM
@@ -118,6 +121,7 @@ config MACH_DAVINCI_DM365_EVM
 	depends on ARCH_DAVINCI_DM365
 	select MISC_DEVICES
 	select EEPROM_AT24
+	select I2C
 	help
 	  Configure this option to specify whether the board used
 	  for development is a DM365 EVM
@@ -129,6 +133,7 @@ config MACH_DAVINCI_DA830_EVM
 	select GPIO_PCF857X
 	select MISC_DEVICES
 	select EEPROM_AT24
+	select I2C
 	help
 	  Say Y here to select the TI DA830/OMAP-L137/AM17x Evaluation Module.
 
@@ -205,6 +210,7 @@ config MACH_MITYOMAPL138
 	depends on ARCH_DAVINCI_DA850
 	select MISC_DEVICES
 	select EEPROM_AT24
+	select I2C
 	help
 	  Say Y here to select the Critical Link MityDSP-L138/MityARM-1808
 	  System on Module.  Information on this SoM may be found at
diff --git a/arch/arm/mach-davinci/board-mityomapl138.c b/arch/arm/mach-davinci/board-mityomapl138.c
index 2aa79c5..606a6f2 100644
--- a/arch/arm/mach-davinci/board-mityomapl138.c
+++ b/arch/arm/mach-davinci/board-mityomapl138.c
@@ -29,7 +29,7 @@
 #include <mach/mux.h>
 #include <mach/spi.h>
 
-#define MITYOMAPL138_PHY_ID		"0:03"
+#define MITYOMAPL138_PHY_ID		""
 
 #define FACTORY_CONFIG_MAGIC	0x012C0138
 #define FACTORY_CONFIG_VERSION	0x00010001
@@ -414,7 +414,7 @@ static struct resource mityomapl138_nandflash_resource[] = {
 
 static struct platform_device mityomapl138_nandflash_device = {
 	.name		= "davinci_nand",
-	.id		= 0,
+	.id		= 1,
 	.dev		= {
 		.platform_data	= &mityomapl138_nandflash_data,
 	},
diff --git a/arch/arm/mach-davinci/devices-da8xx.c b/arch/arm/mach-davinci/devices-da8xx.c
index 625d4b6..58a02dc 100644
--- a/arch/arm/mach-davinci/devices-da8xx.c
+++ b/arch/arm/mach-davinci/devices-da8xx.c
@@ -39,7 +39,8 @@
 #define DA8XX_GPIO_BASE			0x01e26000
 #define DA8XX_I2C1_BASE			0x01e28000
 #define DA8XX_SPI0_BASE			0x01c41000
-#define DA8XX_SPI1_BASE			0x01f0e000
+#define DA830_SPI1_BASE			0x01e12000
+#define DA850_SPI1_BASE			0x01f0e000
 
 #define DA8XX_EMAC_CTRL_REG_OFFSET	0x3000
 #define DA8XX_EMAC_MOD_REG_OFFSET	0x2000
@@ -762,8 +763,8 @@ static struct resource da8xx_spi0_resources[] = {
 
 static struct resource da8xx_spi1_resources[] = {
 	[0] = {
-		.start	= DA8XX_SPI1_BASE,
-		.end	= DA8XX_SPI1_BASE + SZ_4K - 1,
+		.start	= DA830_SPI1_BASE,
+		.end	= DA830_SPI1_BASE + SZ_4K - 1,
 		.flags	= IORESOURCE_MEM,
 	},
 	[1] = {
@@ -832,5 +833,10 @@ int __init da8xx_register_spi(int instance, struct spi_board_info *info,
 
 	da8xx_spi_pdata[instance].num_chipselect = len;
 
+	if (instance == 1 && cpu_is_davinci_da850()) {
+		da8xx_spi1_resources[0].start = DA850_SPI1_BASE;
+		da8xx_spi1_resources[0].end = DA850_SPI1_BASE + SZ_4K - 1;
+	}
+
 	return platform_device_register(&da8xx_spi_device[instance]);
 }
diff --git a/arch/arm/mach-davinci/dm355.c b/arch/arm/mach-davinci/dm355.c
index f680122..a3a94e9 100644
--- a/arch/arm/mach-davinci/dm355.c
+++ b/arch/arm/mach-davinci/dm355.c
@@ -314,7 +314,7 @@ static struct clk timer2_clk = {
 	.name = "timer2",
 	.parent = &pll1_aux_clk,
 	.lpsc = DAVINCI_LPSC_TIMER2,
-	.usecount = 1,              /* REVISIT: why can't' this be disabled? */
+	.usecount = 1,              /* REVISIT: why can't this be disabled? */
 };
 
 static struct clk timer3_clk = {
diff --git a/arch/arm/mach-davinci/dm644x.c b/arch/arm/mach-davinci/dm644x.c
index 5f8a654..4c82c27 100644
--- a/arch/arm/mach-davinci/dm644x.c
+++ b/arch/arm/mach-davinci/dm644x.c
@@ -274,7 +274,7 @@ static struct clk timer2_clk = {
 	.name = "timer2",
 	.parent = &pll1_aux_clk,
 	.lpsc = DAVINCI_LPSC_TIMER2,
-	.usecount = 1,              /* REVISIT: why can't' this be disabled? */
+	.usecount = 1,              /* REVISIT: why can't this be disabled? */
 };
 
 static struct clk_lookup dm644x_clks[] = {
diff --git a/arch/arm/mach-davinci/include/mach/debug-macro.S b/arch/arm/mach-davinci/include/mach/debug-macro.S
index 9f1befc..f8b7ea4 100644
--- a/arch/arm/mach-davinci/include/mach/debug-macro.S
+++ b/arch/arm/mach-davinci/include/mach/debug-macro.S
@@ -24,6 +24,9 @@
 
 #define UART_SHIFT	2
 
+#define davinci_uart_v2p(x)	((x) - PAGE_OFFSET + PLAT_PHYS_OFFSET)
+#define davinci_uart_p2v(x)	((x) - PLAT_PHYS_OFFSET + PAGE_OFFSET)
+
 		.pushsection .data
 davinci_uart_phys:	.word	0
 davinci_uart_virt:	.word	0
@@ -34,7 +37,7 @@ davinci_uart_virt:	.word	0
 		/* Use davinci_uart_phys/virt if already configured */
 10:		mrc	p15, 0, \rp, c1, c0
 		tst	\rp, #1			@ MMU enabled?
-		ldreq	\rp, =__virt_to_phys(davinci_uart_phys)
+		ldreq	\rp, =davinci_uart_v2p(davinci_uart_phys)
 		ldrne	\rp, =davinci_uart_phys
 		add	\rv, \rp, #4		@ davinci_uart_virt
 		ldr	\rp, [\rp, #0]
@@ -48,18 +51,18 @@ davinci_uart_virt:	.word	0
 		tst	\rp, #1			@ MMU enabled?
 
 		/* Copy uart phys address from decompressor uart info */
-		ldreq	\rv, =__virt_to_phys(davinci_uart_phys)
+		ldreq	\rv, =davinci_uart_v2p(davinci_uart_phys)
 		ldrne	\rv, =davinci_uart_phys
 		ldreq	\rp, =DAVINCI_UART_INFO
-		ldrne	\rp, =__phys_to_virt(DAVINCI_UART_INFO)
+		ldrne	\rp, =davinci_uart_p2v(DAVINCI_UART_INFO)
 		ldr	\rp, [\rp, #0]
 		str	\rp, [\rv]
 
 		/* Copy uart virt address from decompressor uart info */
-		ldreq	\rv, =__virt_to_phys(davinci_uart_virt)
+		ldreq	\rv, =davinci_uart_v2p(davinci_uart_virt)
 		ldrne	\rv, =davinci_uart_virt
 		ldreq	\rp, =DAVINCI_UART_INFO
-		ldrne	\rp, =__phys_to_virt(DAVINCI_UART_INFO)
+		ldrne	\rp, =davinci_uart_p2v(DAVINCI_UART_INFO)
 		ldr	\rp, [\rp, #4]
 		str	\rp, [\rv]
 
diff --git a/arch/arm/mach-davinci/include/mach/serial.h b/arch/arm/mach-davinci/include/mach/serial.h
index 8051110..c9e6ce1 100644
--- a/arch/arm/mach-davinci/include/mach/serial.h
+++ b/arch/arm/mach-davinci/include/mach/serial.h
@@ -22,7 +22,7 @@
  *
  * This area sits just below the page tables (see arch/arm/kernel/head.S).
  */
-#define DAVINCI_UART_INFO	(PHYS_OFFSET + 0x3ff8)
+#define DAVINCI_UART_INFO	(PLAT_PHYS_OFFSET + 0x3ff8)
 
 #define DAVINCI_UART0_BASE	(IO_PHYS + 0x20000)
 #define DAVINCI_UART1_BASE	(IO_PHYS + 0x20400)
diff --git a/arch/arm/mach-mx3/mach-vpr200.c b/arch/arm/mach-mx3/mach-vpr200.c
index 2cf390f..47a69cb 100644
--- a/arch/arm/mach-mx3/mach-vpr200.c
+++ b/arch/arm/mach-mx3/mach-vpr200.c
@@ -257,11 +257,16 @@ static const struct fsl_usb2_platform_data otg_device_pdata __initconst = {
 	.workaround	= FLS_USB2_WORKAROUND_ENGCM09152,
 };
 
+static int vpr200_usbh_init(struct platform_device *pdev)
+{
+	return mx35_initialize_usb_hw(pdev->id,
+			MXC_EHCI_INTERFACE_SINGLE_UNI | MXC_EHCI_INTERNAL_PHY);
+}
+
 /* USB HOST config */
 static const struct mxc_usbh_platform_data usb_host_pdata __initconst = {
-	.portsc		= MXC_EHCI_MODE_SERIAL,
-	.flags		= MXC_EHCI_INTERFACE_SINGLE_UNI |
-			  MXC_EHCI_INTERNAL_PHY,
+	.init = vpr200_usbh_init,
+	.portsc = MXC_EHCI_MODE_SERIAL,
 };
 
 static struct platform_device *devices[] __initdata = {
diff --git a/arch/arm/mach-mx5/board-mx53_loco.c b/arch/arm/mach-mx5/board-mx53_loco.c
index 10a1bea..6206b11 100644
--- a/arch/arm/mach-mx5/board-mx53_loco.c
+++ b/arch/arm/mach-mx5/board-mx53_loco.c
@@ -193,7 +193,7 @@ static iomux_v3_cfg_t mx53_loco_pads[] = {
 	.wakeup		= wake,					\
 }
 
-static const struct gpio_keys_button loco_buttons[] __initconst = {
+static struct gpio_keys_button loco_buttons[] = {
 	GPIO_BUTTON(MX53_LOCO_POWER, KEY_POWER, 1, "power", 0),
 	GPIO_BUTTON(MX53_LOCO_UI1, KEY_VOLUMEUP, 1, "volume-up", 0),
 	GPIO_BUTTON(MX53_LOCO_UI2, KEY_VOLUMEDOWN, 1, "volume-down", 0),
diff --git a/arch/arm/mach-mxs/clock-mx28.c b/arch/arm/mach-mxs/clock-mx28.c
index 1ad97fe..5dcc59d 100644
--- a/arch/arm/mach-mxs/clock-mx28.c
+++ b/arch/arm/mach-mxs/clock-mx28.c
@@ -295,11 +295,11 @@ static int name##_set_rate(struct clk *clk, unsigned long rate)		\
 	unsigned long diff, parent_rate, calc_rate;			\
 	int i;								\
 									\
-	parent_rate = clk_get_rate(clk->parent);			\
 	div_max = BM_CLKCTRL_##dr##_DIV >> BP_CLKCTRL_##dr##_DIV;	\
 	bm_busy = BM_CLKCTRL_##dr##_BUSY;				\
 									\
 	if (clk->parent == &ref_xtal_clk) {				\
+		parent_rate = clk_get_rate(clk->parent);		\
 		div = DIV_ROUND_UP(parent_rate, rate);			\
 		if (clk == &cpu_clk) {					\
 			div_max = BM_CLKCTRL_CPU_DIV_XTAL >>		\
@@ -309,6 +309,11 @@ static int name##_set_rate(struct clk *clk, unsigned long rate)		\
 		if (div == 0 || div > div_max)				\
 			return -EINVAL;					\
 	} else {							\
+		/*							\
+		 * hack alert: this block modifies clk->parent, too,	\
+		 * so the base to use it the grand parent.		\
+		 */							\
+		parent_rate = clk_get_rate(clk->parent->parent);	\
 		rate >>= PARENT_RATE_SHIFT;				\
 		parent_rate >>= PARENT_RATE_SHIFT;			\
 		diff = parent_rate;					\
diff --git a/arch/arm/mach-omap2/Makefile b/arch/arm/mach-omap2/Makefile
index a45cd64..512b152 100644
--- a/arch/arm/mach-omap2/Makefile
+++ b/arch/arm/mach-omap2/Makefile
@@ -68,7 +68,7 @@ obj-$(CONFIG_OMAP_SMARTREFLEX)          += sr_device.o smartreflex.o
 obj-$(CONFIG_OMAP_SMARTREFLEX_CLASS3)	+= smartreflex-class3.o
 
 AFLAGS_sleep24xx.o			:=-Wa,-march=armv6
-AFLAGS_sleep34xx.o			:=-Wa,-march=armv7-a
+AFLAGS_sleep34xx.o			:=-Wa,-march=armv7-a$(plus_sec)
 
 ifeq ($(CONFIG_PM_VERBOSE),y)
 CFLAGS_pm_bus.o				+= -DDEBUG
diff --git a/arch/arm/mach-omap2/board-rx51.c b/arch/arm/mach-omap2/board-rx51.c
index e964895..f8ba20a 100644
--- a/arch/arm/mach-omap2/board-rx51.c
+++ b/arch/arm/mach-omap2/board-rx51.c
@@ -141,14 +141,19 @@ static void __init rx51_init(void)
 static void __init rx51_map_io(void)
 {
 	omap2_set_globals_3xxx();
-	rx51_video_mem_init();
 	omap34xx_map_common_io();
 }
 
+static void __init rx51_reserve(void)
+{
+	rx51_video_mem_init();
+	omap_reserve();
+}
+
 MACHINE_START(NOKIA_RX51, "Nokia RX-51 board")
 	/* Maintainer: Lauri Leukkunen <lauri.leukkunen@nokia.com> */
 	.boot_params	= 0x80000100,
-	.reserve	= omap_reserve,
+	.reserve	= rx51_reserve,
 	.map_io		= rx51_map_io,
 	.init_early	= rx51_init_early,
 	.init_irq	= omap_init_irq,
diff --git a/arch/arm/mach-omap2/clock44xx_data.c b/arch/arm/mach-omap2/clock44xx_data.c
index 276992d..8c96567 100644
--- a/arch/arm/mach-omap2/clock44xx_data.c
+++ b/arch/arm/mach-omap2/clock44xx_data.c
@@ -3116,14 +3116,9 @@ static struct omap_clk omap44xx_clks[] = {
 	CLK(NULL,	"dsp_fck",			&dsp_fck,	CK_443X),
 	CLK("omapdss_dss",	"sys_clk",			&dss_sys_clk,	CK_443X),
 	CLK("omapdss_dss",	"tv_clk",			&dss_tv_clk,	CK_443X),
-	CLK("omapdss_dss",	"dss_clk",			&dss_dss_clk,	CK_443X),
 	CLK("omapdss_dss",	"video_clk",			&dss_48mhz_clk,	CK_443X),
-	CLK("omapdss_dss",	"fck",				&dss_fck,	CK_443X),
-	/*
-	 * On OMAP4, DSS ick is a dummy clock; this is needed for compatibility
-	 * with OMAP2/3.
-	 */
-	CLK("omapdss_dss",	"ick",				&dummy_ck,	CK_443X),
+	CLK("omapdss_dss",	"fck",				&dss_dss_clk,	CK_443X),
+	CLK("omapdss_dss",	"ick",				&dss_fck,	CK_443X),
 	CLK(NULL,	"efuse_ctrl_cust_fck",		&efuse_ctrl_cust_fck,	CK_443X),
 	CLK(NULL,	"emif1_fck",			&emif1_fck,	CK_443X),
 	CLK(NULL,	"emif2_fck",			&emif2_fck,	CK_443X),
diff --git a/arch/arm/mach-omap2/cm2xxx_3xxx.c b/arch/arm/mach-omap2/cm2xxx_3xxx.c
index 9d0dec8..38830d8 100644
--- a/arch/arm/mach-omap2/cm2xxx_3xxx.c
+++ b/arch/arm/mach-omap2/cm2xxx_3xxx.c
@@ -247,6 +247,7 @@ struct omap3_cm_regs {
 	u32 per_cm_clksel;
 	u32 emu_cm_clksel;
 	u32 emu_cm_clkstctrl;
+	u32 pll_cm_autoidle;
 	u32 pll_cm_autoidle2;
 	u32 pll_cm_clksel4;
 	u32 pll_cm_clksel5;
@@ -319,6 +320,15 @@ void omap3_cm_save_context(void)
 		omap2_cm_read_mod_reg(OMAP3430_EMU_MOD, CM_CLKSEL1);
 	cm_context.emu_cm_clkstctrl =
 		omap2_cm_read_mod_reg(OMAP3430_EMU_MOD, OMAP2_CM_CLKSTCTRL);
+	/*
+	 * As per erratum i671, ROM code does not respect the PER DPLL
+	 * programming scheme if CM_AUTOIDLE_PLL.AUTO_PERIPH_DPLL == 1.
+	 * In this case, even though this register has been saved in
+	 * scratchpad contents, we need to restore AUTO_PERIPH_DPLL
+	 * by ourselves. So, we need to save it anyway.
+	 */
+	cm_context.pll_cm_autoidle =
+		omap2_cm_read_mod_reg(PLL_MOD, CM_AUTOIDLE);
 	cm_context.pll_cm_autoidle2 =
 		omap2_cm_read_mod_reg(PLL_MOD, CM_AUTOIDLE2);
 	cm_context.pll_cm_clksel4 =
@@ -441,6 +451,13 @@ void omap3_cm_restore_context(void)
 			       CM_CLKSEL1);
 	omap2_cm_write_mod_reg(cm_context.emu_cm_clkstctrl, OMAP3430_EMU_MOD,
 			       OMAP2_CM_CLKSTCTRL);
+	/*
+	 * As per erratum i671, ROM code does not respect the PER DPLL
+	 * programming scheme if CM_AUTOIDLE_PLL.AUTO_PERIPH_DPLL == 1.
+	 * In this case, we need to restore AUTO_PERIPH_DPLL by ourselves.
+	 */
+	omap2_cm_write_mod_reg(cm_context.pll_cm_autoidle, PLL_MOD,
+			       CM_AUTOIDLE);
 	omap2_cm_write_mod_reg(cm_context.pll_cm_autoidle2, PLL_MOD,
 			       CM_AUTOIDLE2);
 	omap2_cm_write_mod_reg(cm_context.pll_cm_clksel4, PLL_MOD,
diff --git a/arch/arm/mach-omap2/control.c b/arch/arm/mach-omap2/control.c
index 6952794..da53ba3 100644
--- a/arch/arm/mach-omap2/control.c
+++ b/arch/arm/mach-omap2/control.c
@@ -316,8 +316,14 @@ void omap3_save_scratchpad_contents(void)
 			omap2_cm_read_mod_reg(WKUP_MOD, CM_CLKSEL);
 	prcm_block_contents.cm_clken_pll =
 			omap2_cm_read_mod_reg(PLL_MOD, CM_CLKEN);
+	/*
+	 * As per erratum i671, ROM code does not respect the PER DPLL
+	 * programming scheme if CM_AUTOIDLE_PLL..AUTO_PERIPH_DPLL == 1.
+	 * Then,  in anycase, clear these bits to avoid extra latencies.
+	 */
 	prcm_block_contents.cm_autoidle_pll =
-			omap2_cm_read_mod_reg(PLL_MOD, OMAP3430_CM_AUTOIDLE_PLL);
+			omap2_cm_read_mod_reg(PLL_MOD, CM_AUTOIDLE) &
+			~OMAP3430_AUTO_PERIPH_DPLL_MASK;
 	prcm_block_contents.cm_clksel1_pll =
 			omap2_cm_read_mod_reg(PLL_MOD, OMAP3430_CM_CLKSEL1_PLL);
 	prcm_block_contents.cm_clksel2_pll =
diff --git a/arch/arm/mach-omap2/omap_hwmod_2420_data.c b/arch/arm/mach-omap2/omap_hwmod_2420_data.c
index 8eb3ce1..c4d0ae87 100644
--- a/arch/arm/mach-omap2/omap_hwmod_2420_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_2420_data.c
@@ -1639,6 +1639,7 @@ static struct omap_hwmod_ocp_if *omap2420_gpio1_slaves[] = {
 
 static struct omap_hwmod omap2420_gpio1_hwmod = {
 	.name		= "gpio1",
+	.flags		= HWMOD_CONTROL_OPT_CLKS_IN_RESET,
 	.mpu_irqs	= omap242x_gpio1_irqs,
 	.mpu_irqs_cnt	= ARRAY_SIZE(omap242x_gpio1_irqs),
 	.main_clk	= "gpios_fck",
@@ -1669,6 +1670,7 @@ static struct omap_hwmod_ocp_if *omap2420_gpio2_slaves[] = {
 
 static struct omap_hwmod omap2420_gpio2_hwmod = {
 	.name		= "gpio2",
+	.flags		= HWMOD_CONTROL_OPT_CLKS_IN_RESET,
 	.mpu_irqs	= omap242x_gpio2_irqs,
 	.mpu_irqs_cnt	= ARRAY_SIZE(omap242x_gpio2_irqs),
 	.main_clk	= "gpios_fck",
@@ -1699,6 +1701,7 @@ static struct omap_hwmod_ocp_if *omap2420_gpio3_slaves[] = {
 
 static struct omap_hwmod omap2420_gpio3_hwmod = {
 	.name		= "gpio3",
+	.flags		= HWMOD_CONTROL_OPT_CLKS_IN_RESET,
 	.mpu_irqs	= omap242x_gpio3_irqs,
 	.mpu_irqs_cnt	= ARRAY_SIZE(omap242x_gpio3_irqs),
 	.main_clk	= "gpios_fck",
@@ -1729,6 +1732,7 @@ static struct omap_hwmod_ocp_if *omap2420_gpio4_slaves[] = {
 
 static struct omap_hwmod omap2420_gpio4_hwmod = {
 	.name		= "gpio4",
+	.flags		= HWMOD_CONTROL_OPT_CLKS_IN_RESET,
 	.mpu_irqs	= omap242x_gpio4_irqs,
 	.mpu_irqs_cnt	= ARRAY_SIZE(omap242x_gpio4_irqs),
 	.main_clk	= "gpios_fck",
@@ -1782,7 +1786,7 @@ static struct omap_hwmod_irq_info omap2420_dma_system_irqs[] = {
 static struct omap_hwmod_addr_space omap2420_dma_system_addrs[] = {
 	{
 		.pa_start	= 0x48056000,
-		.pa_end		= 0x4a0560ff,
+		.pa_end		= 0x48056fff,
 		.flags		= ADDR_TYPE_RT
 	},
 };
diff --git a/arch/arm/mach-omap2/omap_hwmod_2430_data.c b/arch/arm/mach-omap2/omap_hwmod_2430_data.c
index e6e3810..9682dd5 100644
--- a/arch/arm/mach-omap2/omap_hwmod_2430_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_2430_data.c
@@ -1742,6 +1742,7 @@ static struct omap_hwmod_ocp_if *omap2430_gpio1_slaves[] = {
 
 static struct omap_hwmod omap2430_gpio1_hwmod = {
 	.name		= "gpio1",
+	.flags		= HWMOD_CONTROL_OPT_CLKS_IN_RESET,
 	.mpu_irqs	= omap243x_gpio1_irqs,
 	.mpu_irqs_cnt	= ARRAY_SIZE(omap243x_gpio1_irqs),
 	.main_clk	= "gpios_fck",
@@ -1772,6 +1773,7 @@ static struct omap_hwmod_ocp_if *omap2430_gpio2_slaves[] = {
 
 static struct omap_hwmod omap2430_gpio2_hwmod = {
 	.name		= "gpio2",
+	.flags		= HWMOD_CONTROL_OPT_CLKS_IN_RESET,
 	.mpu_irqs	= omap243x_gpio2_irqs,
 	.mpu_irqs_cnt	= ARRAY_SIZE(omap243x_gpio2_irqs),
 	.main_clk	= "gpios_fck",
@@ -1802,6 +1804,7 @@ static struct omap_hwmod_ocp_if *omap2430_gpio3_slaves[] = {
 
 static struct omap_hwmod omap2430_gpio3_hwmod = {
 	.name		= "gpio3",
+	.flags		= HWMOD_CONTROL_OPT_CLKS_IN_RESET,
 	.mpu_irqs	= omap243x_gpio3_irqs,
 	.mpu_irqs_cnt	= ARRAY_SIZE(omap243x_gpio3_irqs),
 	.main_clk	= "gpios_fck",
@@ -1832,6 +1835,7 @@ static struct omap_hwmod_ocp_if *omap2430_gpio4_slaves[] = {
 
 static struct omap_hwmod omap2430_gpio4_hwmod = {
 	.name		= "gpio4",
+	.flags		= HWMOD_CONTROL_OPT_CLKS_IN_RESET,
 	.mpu_irqs	= omap243x_gpio4_irqs,
 	.mpu_irqs_cnt	= ARRAY_SIZE(omap243x_gpio4_irqs),
 	.main_clk	= "gpios_fck",
@@ -1862,6 +1866,7 @@ static struct omap_hwmod_ocp_if *omap2430_gpio5_slaves[] = {
 
 static struct omap_hwmod omap2430_gpio5_hwmod = {
 	.name		= "gpio5",
+	.flags		= HWMOD_CONTROL_OPT_CLKS_IN_RESET,
 	.mpu_irqs	= omap243x_gpio5_irqs,
 	.mpu_irqs_cnt	= ARRAY_SIZE(omap243x_gpio5_irqs),
 	.main_clk	= "gpio5_fck",
@@ -1915,7 +1920,7 @@ static struct omap_hwmod_irq_info omap2430_dma_system_irqs[] = {
 static struct omap_hwmod_addr_space omap2430_dma_system_addrs[] = {
 	{
 		.pa_start	= 0x48056000,
-		.pa_end		= 0x4a0560ff,
+		.pa_end		= 0x48056fff,
 		.flags		= ADDR_TYPE_RT
 	},
 };
diff --git a/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c b/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
index b98e2dfc..909a84d 100644
--- a/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
@@ -2141,6 +2141,7 @@ static struct omap_hwmod_ocp_if *omap3xxx_gpio1_slaves[] = {
 
 static struct omap_hwmod omap3xxx_gpio1_hwmod = {
 	.name		= "gpio1",
+	.flags		= HWMOD_CONTROL_OPT_CLKS_IN_RESET,
 	.mpu_irqs	= omap3xxx_gpio1_irqs,
 	.mpu_irqs_cnt	= ARRAY_SIZE(omap3xxx_gpio1_irqs),
 	.main_clk	= "gpio1_ick",
@@ -2177,6 +2178,7 @@ static struct omap_hwmod_ocp_if *omap3xxx_gpio2_slaves[] = {
 
 static struct omap_hwmod omap3xxx_gpio2_hwmod = {
 	.name		= "gpio2",
+	.flags		= HWMOD_CONTROL_OPT_CLKS_IN_RESET,
 	.mpu_irqs	= omap3xxx_gpio2_irqs,
 	.mpu_irqs_cnt	= ARRAY_SIZE(omap3xxx_gpio2_irqs),
 	.main_clk	= "gpio2_ick",
@@ -2213,6 +2215,7 @@ static struct omap_hwmod_ocp_if *omap3xxx_gpio3_slaves[] = {
 
 static struct omap_hwmod omap3xxx_gpio3_hwmod = {
 	.name		= "gpio3",
+	.flags		= HWMOD_CONTROL_OPT_CLKS_IN_RESET,
 	.mpu_irqs	= omap3xxx_gpio3_irqs,
 	.mpu_irqs_cnt	= ARRAY_SIZE(omap3xxx_gpio3_irqs),
 	.main_clk	= "gpio3_ick",
@@ -2249,6 +2252,7 @@ static struct omap_hwmod_ocp_if *omap3xxx_gpio4_slaves[] = {
 
 static struct omap_hwmod omap3xxx_gpio4_hwmod = {
 	.name		= "gpio4",
+	.flags		= HWMOD_CONTROL_OPT_CLKS_IN_RESET,
 	.mpu_irqs	= omap3xxx_gpio4_irqs,
 	.mpu_irqs_cnt	= ARRAY_SIZE(omap3xxx_gpio4_irqs),
 	.main_clk	= "gpio4_ick",
@@ -2285,6 +2289,7 @@ static struct omap_hwmod_ocp_if *omap3xxx_gpio5_slaves[] = {
 
 static struct omap_hwmod omap3xxx_gpio5_hwmod = {
 	.name		= "gpio5",
+	.flags		= HWMOD_CONTROL_OPT_CLKS_IN_RESET,
 	.mpu_irqs	= omap3xxx_gpio5_irqs,
 	.mpu_irqs_cnt	= ARRAY_SIZE(omap3xxx_gpio5_irqs),
 	.main_clk	= "gpio5_ick",
@@ -2321,6 +2326,7 @@ static struct omap_hwmod_ocp_if *omap3xxx_gpio6_slaves[] = {
 
 static struct omap_hwmod omap3xxx_gpio6_hwmod = {
 	.name		= "gpio6",
+	.flags		= HWMOD_CONTROL_OPT_CLKS_IN_RESET,
 	.mpu_irqs	= omap3xxx_gpio6_irqs,
 	.mpu_irqs_cnt	= ARRAY_SIZE(omap3xxx_gpio6_irqs),
 	.main_clk	= "gpio6_ick",
@@ -2386,7 +2392,7 @@ static struct omap_hwmod_irq_info omap3xxx_dma_system_irqs[] = {
 static struct omap_hwmod_addr_space omap3xxx_dma_system_addrs[] = {
 	{
 		.pa_start	= 0x48056000,
-		.pa_end		= 0x4a0560ff,
+		.pa_end		= 0x48056fff,
 		.flags		= ADDR_TYPE_RT
 	},
 };
diff --git a/arch/arm/mach-omap2/omap_hwmod_44xx_data.c b/arch/arm/mach-omap2/omap_hwmod_44xx_data.c
index 3e88dd3..abc548a 100644
--- a/arch/arm/mach-omap2/omap_hwmod_44xx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_44xx_data.c
@@ -885,7 +885,7 @@ static struct omap_hwmod_ocp_if *omap44xx_dma_system_masters[] = {
 static struct omap_hwmod_addr_space omap44xx_dma_system_addrs[] = {
 	{
 		.pa_start	= 0x4a056000,
-		.pa_end		= 0x4a0560ff,
+		.pa_end		= 0x4a056fff,
 		.flags		= ADDR_TYPE_RT
 	},
 };
diff --git a/arch/arm/mach-omap2/omap_l3_smx.c b/arch/arm/mach-omap2/omap_l3_smx.c
index 5f2da756..4321e79 100644
--- a/arch/arm/mach-omap2/omap_l3_smx.c
+++ b/arch/arm/mach-omap2/omap_l3_smx.c
@@ -196,11 +196,11 @@ static irqreturn_t omap3_l3_app_irq(int irq, void *_l3)
 		/* No timeout error for debug sources */
 	}
 
-	base = ((l3->rt) + (*(omap3_l3_bases[int_type] + err_source)));
-
 	/* identify the error source */
 	for (err_source = 0; !(status & (1 << err_source)); err_source++)
 									;
+
+	base = l3->rt + *(omap3_l3_bases[int_type] + err_source);
 	error = omap3_l3_readll(base, L3_ERROR_LOG);
 
 	if (error) {
diff --git a/arch/arm/mach-omap2/pm.c b/arch/arm/mach-omap2/pm.c
index 30af335..49486f5 100644
--- a/arch/arm/mach-omap2/pm.c
+++ b/arch/arm/mach-omap2/pm.c
@@ -89,6 +89,7 @@ static void omap2_init_processor_devices(void)
 	if (cpu_is_omap44xx()) {
 		_init_omap_device("l3_main_1", &l3_dev);
 		_init_omap_device("dsp", &dsp_dev);
+		_init_omap_device("iva", &iva_dev);
 	} else {
 		_init_omap_device("l3_main", &l3_dev);
 	}
diff --git a/arch/arm/mach-omap2/voltage.c b/arch/arm/mach-omap2/voltage.c
index 6fb5209..0c1552d 100644
--- a/arch/arm/mach-omap2/voltage.c
+++ b/arch/arm/mach-omap2/voltage.c
@@ -114,7 +114,6 @@ static int __init _config_common_vdd_data(struct omap_vdd_info *vdd)
 	sys_clk_speed /= 1000;
 
 	/* Generic voltage parameters */
-	vdd->curr_volt = 1200000;
 	vdd->volt_scale = vp_forceupdate_scale_voltage;
 	vdd->vp_enabled = false;
 
diff --git a/arch/arm/mach-pxa/hx4700.c b/arch/arm/mach-pxa/hx4700.c
index 6de0ad0..9cdcca5 100644
--- a/arch/arm/mach-pxa/hx4700.c
+++ b/arch/arm/mach-pxa/hx4700.c
@@ -711,7 +711,7 @@ static struct regulator_consumer_supply bq24022_consumers[] = {
 static struct regulator_init_data bq24022_init_data = {
 	.constraints = {
 		.max_uA         = 500000,
-		.valid_ops_mask = REGULATOR_CHANGE_CURRENT,
+		.valid_ops_mask = REGULATOR_CHANGE_CURRENT|REGULATOR_CHANGE_STATUS,
 	},
 	.num_consumer_supplies  = ARRAY_SIZE(bq24022_consumers),
 	.consumer_supplies      = bq24022_consumers,
diff --git a/arch/arm/mach-pxa/magician.c b/arch/arm/mach-pxa/magician.c
index a72993d..9984ef7 100644
--- a/arch/arm/mach-pxa/magician.c
+++ b/arch/arm/mach-pxa/magician.c
@@ -599,7 +599,7 @@ static struct regulator_consumer_supply bq24022_consumers[] = {
 static struct regulator_init_data bq24022_init_data = {
 	.constraints = {
 		.max_uA         = 500000,
-		.valid_ops_mask = REGULATOR_CHANGE_CURRENT,
+		.valid_ops_mask = REGULATOR_CHANGE_CURRENT | REGULATOR_CHANGE_STATUS,
 	},
 	.num_consumer_supplies  = ARRAY_SIZE(bq24022_consumers),
 	.consumer_supplies      = bq24022_consumers,
diff --git a/arch/arm/mach-s3c2440/mach-gta02.c b/arch/arm/mach-s3c2440/mach-gta02.c
index 0db2411..7166620 100644
--- a/arch/arm/mach-s3c2440/mach-gta02.c
+++ b/arch/arm/mach-s3c2440/mach-gta02.c
@@ -409,6 +409,10 @@ struct platform_device s3c24xx_pwm_device = {
 	.num_resources	= 0,
 };
 
+static struct platform_device gta02_dfbmcs320_device = {
+	.name = "dfbmcs320",
+};
+
 static struct i2c_board_info gta02_i2c_devs[] __initdata = {
 	{
 		I2C_BOARD_INFO("pcf50633", 0x73),
@@ -523,6 +527,7 @@ static struct platform_device *gta02_devices[] __initdata = {
 	&s3c_device_iis,
 	&samsung_asoc_dma,
 	&s3c_device_i2c0,
+	&gta02_dfbmcs320_device,
 	&gta02_buttons_device,
 	&s3c_device_adc,
 	&s3c_device_ts,
diff --git a/arch/arm/mach-ux500/board-mop500.c b/arch/arm/mach-ux500/board-mop500.c
index af91374..6e1907fa 100644
--- a/arch/arm/mach-ux500/board-mop500.c
+++ b/arch/arm/mach-ux500/board-mop500.c
@@ -178,16 +178,15 @@ static struct i2c_board_info __initdata mop500_i2c0_devices[] = {
 		.irq		= NOMADIK_GPIO_TO_IRQ(217),
 		.platform_data  = &mop500_tc35892_data,
 	},
-};
-
-/* I2C0 devices only available prior to HREFv60 */
-static struct i2c_board_info __initdata mop500_i2c0_old_devices[] = {
+	/* I2C0 devices only available prior to HREFv60 */
 	{
 		I2C_BOARD_INFO("tps61052", 0x33),
 		.platform_data  = &mop500_tps61052_data,
 	},
 };
 
+#define NUM_PRE_V60_I2C0_DEVICES 1
+
 static struct i2c_board_info __initdata mop500_i2c2_devices[] = {
 	{
 		/* lp5521 LED driver, 1st device */
@@ -425,6 +424,8 @@ static void __init mop500_uart_init(void)
 
 static void __init mop500_init_machine(void)
 {
+	int i2c0_devs;
+
 	/*
 	 * The HREFv60 board removed a GPIO expander and routed
 	 * all these GPIO pins to the internal GPIO controller
@@ -448,11 +449,11 @@ static void __init mop500_init_machine(void)
 
 	platform_device_register(&ab8500_device);
 
-	i2c_register_board_info(0, mop500_i2c0_devices,
-				ARRAY_SIZE(mop500_i2c0_devices));
-	if (!machine_is_hrefv60())
-		i2c_register_board_info(0, mop500_i2c0_old_devices,
-					ARRAY_SIZE(mop500_i2c0_old_devices));
+	i2c0_devs = ARRAY_SIZE(mop500_i2c0_devices);
+	if (machine_is_hrefv60())
+		i2c0_devs -= NUM_PRE_V60_I2C0_DEVICES;
+
+	i2c_register_board_info(0, mop500_i2c0_devices, i2c0_devs);
 	i2c_register_board_info(2, mop500_i2c2_devices,
 				ARRAY_SIZE(mop500_i2c2_devices));
 }
diff --git a/arch/arm/mm/proc-xscale.S b/arch/arm/mm/proc-xscale.S
index ce233bc..42af976 100644
--- a/arch/arm/mm/proc-xscale.S
+++ b/arch/arm/mm/proc-xscale.S
@@ -395,7 +395,7 @@ ENTRY(xscale_dma_a0_map_area)
 	teq	r2, #DMA_TO_DEVICE
 	beq	xscale_dma_clean_range
 	b	xscale_dma_flush_range
-ENDPROC(xscsale_dma_a0_map_area)
+ENDPROC(xscale_dma_a0_map_area)
 
 /*
  *	dma_unmap_area(start, size, dir)
diff --git a/arch/arm/plat-mxc/gpio.c b/arch/arm/plat-mxc/gpio.c
index 7a10724..6cd6d7f 100644
--- a/arch/arm/plat-mxc/gpio.c
+++ b/arch/arm/plat-mxc/gpio.c
@@ -295,6 +295,12 @@ static int mxc_gpio_direction_output(struct gpio_chip *chip,
 	return 0;
 }
 
+/*
+ * This lock class tells lockdep that GPIO irqs are in a different
+ * category than their parents, so it won't report false recursion.
+ */
+static struct lock_class_key gpio_lock_class;
+
 int __init mxc_gpio_init(struct mxc_gpio_port *port, int cnt)
 {
 	int i, j;
@@ -311,6 +317,7 @@ int __init mxc_gpio_init(struct mxc_gpio_port *port, int cnt)
 		__raw_writel(~0, port[i].base + GPIO_ISR);
 		for (j = port[i].virtual_irq_start;
 			j < port[i].virtual_irq_start + 32; j++) {
+			irq_set_lockdep_class(j, &gpio_lock_class);
 			irq_set_chip_and_handler(j, &gpio_irq_chip,
 						 handle_level_irq);
 			set_irq_flags(j, IRQF_VALID);
diff --git a/arch/arm/plat-mxc/ssi-fiq.S b/arch/arm/plat-mxc/ssi-fiq.S
index 4ddce56..8397a2d 100644
--- a/arch/arm/plat-mxc/ssi-fiq.S
+++ b/arch/arm/plat-mxc/ssi-fiq.S
@@ -124,6 +124,8 @@ imx_ssi_fiq_start:
 1:
 		@ return from FIQ
 		subs	pc, lr, #4
+
+		.align
 imx_ssi_fiq_base:
 		.word 0x0
 imx_ssi_fiq_rx_buffer:
diff --git a/arch/m68k/mm/motorola.c b/arch/m68k/mm/motorola.c
index 02b7a03..8b3db1c 100644
--- a/arch/m68k/mm/motorola.c
+++ b/arch/m68k/mm/motorola.c
@@ -300,6 +300,8 @@ void __init paging_init(void)
 		zones_size[ZONE_DMA] = m68k_memory[i].size >> PAGE_SHIFT;
 		free_area_init_node(i, zones_size,
 				    m68k_memory[i].addr >> PAGE_SHIFT, NULL);
+		if (node_present_pages(i))
+			node_set_state(i, N_NORMAL_MEMORY);
 	}
 }
 
diff --git a/arch/parisc/mm/init.c b/arch/parisc/mm/init.c
index b7ed8d7..b1d1262 100644
--- a/arch/parisc/mm/init.c
+++ b/arch/parisc/mm/init.c
@@ -266,8 +266,10 @@ static void __init setup_bootmem(void)
 	}
 	memset(pfnnid_map, 0xff, sizeof(pfnnid_map));
 
-	for (i = 0; i < npmem_ranges; i++)
+	for (i = 0; i < npmem_ranges; i++) {
+		node_set_state(i, N_NORMAL_MEMORY);
 		node_set_online(i);
+	}
 #endif
 
 	/*
diff --git a/arch/powerpc/include/asm/8xx_immap.h b/arch/powerpc/include/asm/8xx_immap.h
index 6b6dc20..bdf0563 100644
--- a/arch/powerpc/include/asm/8xx_immap.h
+++ b/arch/powerpc/include/asm/8xx_immap.h
@@ -393,8 +393,8 @@ typedef struct fec {
 	uint	fec_addr_low;		/* lower 32 bits of station address	*/
 	ushort	fec_addr_high;		/* upper 16 bits of station address	*/
 	ushort	res1;			/* reserved				*/
-	uint	fec_hash_table_high;	/* upper 32-bits of hash table		*/
-	uint	fec_hash_table_low;	/* lower 32-bits of hash table		*/
+	uint	fec_grp_hash_table_high;	/* upper 32-bits of hash table		*/
+	uint	fec_grp_hash_table_low;	/* lower 32-bits of hash table		*/
 	uint	fec_r_des_start;	/* beginning of Rx descriptor ring	*/
 	uint	fec_x_des_start;	/* beginning of Tx descriptor ring	*/
 	uint	fec_r_buff_size;	/* Rx buffer size			*/
diff --git a/arch/powerpc/include/asm/uninorth.h b/arch/powerpc/include/asm/uninorth.h
index ae9c899..d12b11d 100644
--- a/arch/powerpc/include/asm/uninorth.h
+++ b/arch/powerpc/include/asm/uninorth.h
@@ -60,7 +60,7 @@
  *
  * Obviously, the GART is not cache coherent and so any change to it
  * must be flushed to memory (or maybe just make the GART space non
- * cachable). AGP memory itself does't seem to be cache coherent neither.
+ * cachable). AGP memory itself doesn't seem to be cache coherent neither.
  *
  * In order to invalidate the GART (which is probably necessary to inval
  * the bridge internal TLBs), the following sequence has to be written,
diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c
index 55613e3..a6ae1cf 100644
--- a/arch/powerpc/kernel/ptrace.c
+++ b/arch/powerpc/kernel/ptrace.c
@@ -933,12 +933,16 @@ int ptrace_set_debugreg(struct task_struct *task, unsigned long addr,
 	if (data && !(data & DABR_TRANSLATION))
 		return -EIO;
 #ifdef CONFIG_HAVE_HW_BREAKPOINT
+	if (ptrace_get_breakpoints(task) < 0)
+		return -ESRCH;
+
 	bp = thread->ptrace_bps[0];
 	if ((!data) || !(data & (DABR_DATA_WRITE | DABR_DATA_READ))) {
 		if (bp) {
 			unregister_hw_breakpoint(bp);
 			thread->ptrace_bps[0] = NULL;
 		}
+		ptrace_put_breakpoints(task);
 		return 0;
 	}
 	if (bp) {
@@ -948,9 +952,12 @@ int ptrace_set_debugreg(struct task_struct *task, unsigned long addr,
 					(DABR_DATA_WRITE | DABR_DATA_READ),
 							&attr.bp_type);
 		ret =  modify_user_hw_breakpoint(bp, &attr);
-		if (ret)
+		if (ret) {
+			ptrace_put_breakpoints(task);
 			return ret;
+		}
 		thread->ptrace_bps[0] = bp;
+		ptrace_put_breakpoints(task);
 		thread->dabr = data;
 		return 0;
 	}
@@ -965,9 +972,12 @@ int ptrace_set_debugreg(struct task_struct *task, unsigned long addr,
 							ptrace_triggered, task);
 	if (IS_ERR(bp)) {
 		thread->ptrace_bps[0] = NULL;
+		ptrace_put_breakpoints(task);
 		return PTR_ERR(bp);
 	}
 
+	ptrace_put_breakpoints(task);
+
 #endif /* CONFIG_HAVE_HW_BREAKPOINT */
 
 	/* Move contents to the DABR register */
diff --git a/arch/s390/crypto/prng.c b/arch/s390/crypto/prng.c
index 975e3ab..8b16c47 100644
--- a/arch/s390/crypto/prng.c
+++ b/arch/s390/crypto/prng.c
@@ -76,7 +76,7 @@ static void prng_seed(int nbytes)
 
 	/* Add the entropy */
 	while (nbytes >= 8) {
-		*((__u64 *)parm_block) ^= *((__u64 *)buf+i*8);
+		*((__u64 *)parm_block) ^= *((__u64 *)(buf+i));
 		prng_add_entropy();
 		i += 8;
 		nbytes -= 8;
diff --git a/arch/s390/kvm/sie64a.S b/arch/s390/kvm/sie64a.S
index 7e9d30d..ab0e041 100644
--- a/arch/s390/kvm/sie64a.S
+++ b/arch/s390/kvm/sie64a.S
@@ -48,10 +48,10 @@ sie_irq_handler:
 	tm	__TI_flags+7(%r2),_TIF_EXIT_SIE
 	jz	0f
 	larl	%r2,sie_exit			# work pending, leave sie
-	stg	%r2,__LC_RETURN_PSW+8
+	stg	%r2,SPI_PSW+8(0,%r15)
 	br	%r14
 0:	larl	%r2,sie_reenter			# re-enter with guest id
-	stg	%r2,__LC_RETURN_PSW+8
+	stg	%r2,SPI_PSW+8(0,%r15)
 1:	br	%r14
 
 /*
diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
index 9217e33..ab98813 100644
--- a/arch/s390/mm/fault.c
+++ b/arch/s390/mm/fault.c
@@ -543,7 +543,6 @@ static void pfault_interrupt(unsigned int ext_int_code,
 	struct task_struct *tsk;
 	__u16 subcode;
 
-	kstat_cpu(smp_processor_id()).irqs[EXTINT_PFL]++;
 	/*
 	 * Get the external interruption subcode & pfault
 	 * initial/completion signal bit. VM stores this 
@@ -553,14 +552,15 @@ static void pfault_interrupt(unsigned int ext_int_code,
 	subcode = ext_int_code >> 16;
 	if ((subcode & 0xff00) != __SUBCODE_MASK)
 		return;
+	kstat_cpu(smp_processor_id()).irqs[EXTINT_PFL]++;
 
 	/*
 	 * Get the token (= address of the task structure of the affected task).
 	 */
 #ifdef CONFIG_64BIT
-	tsk = *(struct task_struct **) param64;
+	tsk = (struct task_struct *) param64;
 #else
-	tsk = *(struct task_struct **) param32;
+	tsk = (struct task_struct *) param32;
 #endif
 
 	if (subcode & 0x0080) {
diff --git a/arch/s390/mm/pageattr.c b/arch/s390/mm/pageattr.c
index 122ffbd..0607e4b 100644
--- a/arch/s390/mm/pageattr.c
+++ b/arch/s390/mm/pageattr.c
@@ -24,12 +24,13 @@ static void change_page_attr(unsigned long addr, int numpages,
 			WARN_ON_ONCE(1);
 			continue;
 		}
-		ptep = pte_offset_kernel(pmdp, addr + i * PAGE_SIZE);
+		ptep = pte_offset_kernel(pmdp, addr);
 
 		pte = *ptep;
 		pte = set(pte);
-		ptep_invalidate(&init_mm, addr + i * PAGE_SIZE, ptep);
+		ptep_invalidate(&init_mm, addr, ptep);
 		*ptep = pte;
+		addr += PAGE_SIZE;
 	}
 }
 
diff --git a/arch/sh/kernel/ptrace_32.c b/arch/sh/kernel/ptrace_32.c
index 2130ca6..3d7b209 100644
--- a/arch/sh/kernel/ptrace_32.c
+++ b/arch/sh/kernel/ptrace_32.c
@@ -117,7 +117,11 @@ void user_enable_single_step(struct task_struct *child)
 
 	set_tsk_thread_flag(child, TIF_SINGLESTEP);
 
+	if (ptrace_get_breakpoints(child) < 0)
+		return;
+
 	set_single_step(child, pc);
+	ptrace_put_breakpoints(child);
 }
 
 void user_disable_single_step(struct task_struct *child)
diff --git a/arch/um/Kconfig.um b/arch/um/Kconfig.um
index 90a438a..b5e675e 100644
--- a/arch/um/Kconfig.um
+++ b/arch/um/Kconfig.um
@@ -47,7 +47,7 @@ config HOSTFS
 
 config HPPFS
 	tristate "HoneyPot ProcFS (EXPERIMENTAL)"
-	depends on EXPERIMENTAL
+	depends on EXPERIMENTAL && PROC_FS
 	help
 	  hppfs (HoneyPot ProcFS) is a filesystem which allows UML /proc
 	  entries to be overridden, removed, or fabricated from the host.
diff --git a/arch/um/include/asm/thread_info.h b/arch/um/include/asm/thread_info.h
index e2cf786bd..5bd1bad 100644
--- a/arch/um/include/asm/thread_info.h
+++ b/arch/um/include/asm/thread_info.h
@@ -49,7 +49,10 @@ static inline struct thread_info *current_thread_info(void)
 {
 	struct thread_info *ti;
 	unsigned long mask = THREAD_SIZE - 1;
-	ti = (struct thread_info *) (((unsigned long) &ti) & ~mask);
+	void *p;
+
+	asm volatile ("" : "=r" (p) : "0" (&ti));
+	ti = (struct thread_info *) (((unsigned long)p) & ~mask);
 	return ti;
 }
 
diff --git a/arch/um/sys-i386/Makefile b/arch/um/sys-i386/Makefile
index 804b28d..b1da91c 100644
--- a/arch/um/sys-i386/Makefile
+++ b/arch/um/sys-i386/Makefile
@@ -4,7 +4,7 @@
 
 obj-y = bug.o bugs.o checksum.o delay.o fault.o ksyms.o ldt.o ptrace.o \
 	ptrace_user.o setjmp.o signal.o stub.o stub_segv.o syscalls.o sysrq.o \
-	sys_call_table.o tls.o
+	sys_call_table.o tls.o atomic64_cx8_32.o
 
 obj-$(CONFIG_BINFMT_ELF) += elfcore.o
 
diff --git a/arch/um/sys-i386/atomic64_cx8_32.S b/arch/um/sys-i386/atomic64_cx8_32.S
new file mode 100644
index 0000000..1e901d3
--- /dev/null
+++ b/arch/um/sys-i386/atomic64_cx8_32.S
@@ -0,0 +1,225 @@
+/*
+ * atomic64_t for 586+
+ *
+ * Copied from arch/x86/lib/atomic64_cx8_32.S
+ *
+ * Copyright © 2010  Luca Barbieri
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ */
+
+#include <linux/linkage.h>
+#include <asm/alternative-asm.h>
+#include <asm/dwarf2.h>
+
+.macro SAVE reg
+	pushl_cfi %\reg
+	CFI_REL_OFFSET \reg, 0
+.endm
+
+.macro RESTORE reg
+	popl_cfi %\reg
+	CFI_RESTORE \reg
+.endm
+
+.macro read64 reg
+	movl %ebx, %eax
+	movl %ecx, %edx
+/* we need LOCK_PREFIX since otherwise cmpxchg8b always does the write */
+	LOCK_PREFIX
+	cmpxchg8b (\reg)
+.endm
+
+ENTRY(atomic64_read_cx8)
+	CFI_STARTPROC
+
+	read64 %ecx
+	ret
+	CFI_ENDPROC
+ENDPROC(atomic64_read_cx8)
+
+ENTRY(atomic64_set_cx8)
+	CFI_STARTPROC
+
+1:
+/* we don't need LOCK_PREFIX since aligned 64-bit writes
+ * are atomic on 586 and newer */
+	cmpxchg8b (%esi)
+	jne 1b
+
+	ret
+	CFI_ENDPROC
+ENDPROC(atomic64_set_cx8)
+
+ENTRY(atomic64_xchg_cx8)
+	CFI_STARTPROC
+
+	movl %ebx, %eax
+	movl %ecx, %edx
+1:
+	LOCK_PREFIX
+	cmpxchg8b (%esi)
+	jne 1b
+
+	ret
+	CFI_ENDPROC
+ENDPROC(atomic64_xchg_cx8)
+
+.macro addsub_return func ins insc
+ENTRY(atomic64_\func\()_return_cx8)
+	CFI_STARTPROC
+	SAVE ebp
+	SAVE ebx
+	SAVE esi
+	SAVE edi
+
+	movl %eax, %esi
+	movl %edx, %edi
+	movl %ecx, %ebp
+
+	read64 %ebp
+1:
+	movl %eax, %ebx
+	movl %edx, %ecx
+	\ins\()l %esi, %ebx
+	\insc\()l %edi, %ecx
+	LOCK_PREFIX
+	cmpxchg8b (%ebp)
+	jne 1b
+
+10:
+	movl %ebx, %eax
+	movl %ecx, %edx
+	RESTORE edi
+	RESTORE esi
+	RESTORE ebx
+	RESTORE ebp
+	ret
+	CFI_ENDPROC
+ENDPROC(atomic64_\func\()_return_cx8)
+.endm
+
+addsub_return add add adc
+addsub_return sub sub sbb
+
+.macro incdec_return func ins insc
+ENTRY(atomic64_\func\()_return_cx8)
+	CFI_STARTPROC
+	SAVE ebx
+
+	read64 %esi
+1:
+	movl %eax, %ebx
+	movl %edx, %ecx
+	\ins\()l $1, %ebx
+	\insc\()l $0, %ecx
+	LOCK_PREFIX
+	cmpxchg8b (%esi)
+	jne 1b
+
+10:
+	movl %ebx, %eax
+	movl %ecx, %edx
+	RESTORE ebx
+	ret
+	CFI_ENDPROC
+ENDPROC(atomic64_\func\()_return_cx8)
+.endm
+
+incdec_return inc add adc
+incdec_return dec sub sbb
+
+ENTRY(atomic64_dec_if_positive_cx8)
+	CFI_STARTPROC
+	SAVE ebx
+
+	read64 %esi
+1:
+	movl %eax, %ebx
+	movl %edx, %ecx
+	subl $1, %ebx
+	sbb $0, %ecx
+	js 2f
+	LOCK_PREFIX
+	cmpxchg8b (%esi)
+	jne 1b
+
+2:
+	movl %ebx, %eax
+	movl %ecx, %edx
+	RESTORE ebx
+	ret
+	CFI_ENDPROC
+ENDPROC(atomic64_dec_if_positive_cx8)
+
+ENTRY(atomic64_add_unless_cx8)
+	CFI_STARTPROC
+	SAVE ebp
+	SAVE ebx
+/* these just push these two parameters on the stack */
+	SAVE edi
+	SAVE esi
+
+	movl %ecx, %ebp
+	movl %eax, %esi
+	movl %edx, %edi
+
+	read64 %ebp
+1:
+	cmpl %eax, 0(%esp)
+	je 4f
+2:
+	movl %eax, %ebx
+	movl %edx, %ecx
+	addl %esi, %ebx
+	adcl %edi, %ecx
+	LOCK_PREFIX
+	cmpxchg8b (%ebp)
+	jne 1b
+
+	movl $1, %eax
+3:
+	addl $8, %esp
+	CFI_ADJUST_CFA_OFFSET -8
+	RESTORE ebx
+	RESTORE ebp
+	ret
+4:
+	cmpl %edx, 4(%esp)
+	jne 2b
+	xorl %eax, %eax
+	jmp 3b
+	CFI_ENDPROC
+ENDPROC(atomic64_add_unless_cx8)
+
+ENTRY(atomic64_inc_not_zero_cx8)
+	CFI_STARTPROC
+	SAVE ebx
+
+	read64 %esi
+1:
+	testl %eax, %eax
+	je 4f
+2:
+	movl %eax, %ebx
+	movl %edx, %ecx
+	addl $1, %ebx
+	adcl $0, %ecx
+	LOCK_PREFIX
+	cmpxchg8b (%esi)
+	jne 1b
+
+	movl $1, %eax
+3:
+	RESTORE ebx
+	ret
+4:
+	testl %edx, %edx
+	jne 2b
+	jmp 3b
+	CFI_ENDPROC
+ENDPROC(atomic64_inc_not_zero_cx8)
diff --git a/arch/x86/boot/memory.c b/arch/x86/boot/memory.c
index cae3feb..db75d07 100644
--- a/arch/x86/boot/memory.c
+++ b/arch/x86/boot/memory.c
@@ -91,7 +91,7 @@ static int detect_memory_e801(void)
 	if (oreg.ax > 15*1024) {
 		return -1;	/* Bogus! */
 	} else if (oreg.ax == 15*1024) {
-		boot_params.alt_mem_k = (oreg.dx << 6) + oreg.ax;
+		boot_params.alt_mem_k = (oreg.bx << 6) + oreg.ax;
 	} else {
 		/*
 		 * This ignores memory above 16MB if we have a memory
diff --git a/arch/x86/include/asm/gart.h b/arch/x86/include/asm/gart.h
index 43085bf..156cd5d 100644
--- a/arch/x86/include/asm/gart.h
+++ b/arch/x86/include/asm/gart.h
@@ -66,7 +66,7 @@ static inline void gart_set_size_and_enable(struct pci_dev *dev, u32 order)
 	 * Don't enable translation but enable GART IO and CPU accesses.
 	 * Also, set DISTLBWALKPRB since GART tables memory is UC.
 	 */
-	ctl = DISTLBWALKPRB | order << 1;
+	ctl = order << 1;
 
 	pci_write_config_dword(dev, AMD64_GARTAPERTURECTL, ctl);
 }
@@ -75,17 +75,17 @@ static inline void enable_gart_translation(struct pci_dev *dev, u64 addr)
 {
 	u32 tmp, ctl;
 
-        /* address of the mappings table */
-        addr >>= 12;
-        tmp = (u32) addr<<4;
-        tmp &= ~0xf;
-        pci_write_config_dword(dev, AMD64_GARTTABLEBASE, tmp);
-
-        /* Enable GART translation for this hammer. */
-        pci_read_config_dword(dev, AMD64_GARTAPERTURECTL, &ctl);
-        ctl |= GARTEN;
-        ctl &= ~(DISGARTCPU | DISGARTIO);
-        pci_write_config_dword(dev, AMD64_GARTAPERTURECTL, ctl);
+	/* address of the mappings table */
+	addr >>= 12;
+	tmp = (u32) addr<<4;
+	tmp &= ~0xf;
+	pci_write_config_dword(dev, AMD64_GARTTABLEBASE, tmp);
+
+	/* Enable GART translation for this hammer. */
+	pci_read_config_dword(dev, AMD64_GARTAPERTURECTL, &ctl);
+	ctl |= GARTEN | DISTLBWALKPRB;
+	ctl &= ~(DISGARTCPU | DISGARTIO);
+	pci_write_config_dword(dev, AMD64_GARTAPERTURECTL, ctl);
 }
 
 static inline int aperture_valid(u64 aper_base, u32 aper_size, u32 min_size)
diff --git a/arch/x86/include/asm/io_apic.h b/arch/x86/include/asm/io_apic.h
index c4bd267..a97a240 100644
--- a/arch/x86/include/asm/io_apic.h
+++ b/arch/x86/include/asm/io_apic.h
@@ -150,7 +150,7 @@ void setup_IO_APIC_irq_extra(u32 gsi);
 extern void ioapic_and_gsi_init(void);
 extern void ioapic_insert_resources(void);
 
-int io_apic_setup_irq_pin(unsigned int irq, int node, struct io_apic_irq_attr *attr);
+int io_apic_setup_irq_pin_once(unsigned int irq, int node, struct io_apic_irq_attr *attr);
 
 extern struct IO_APIC_route_entry **alloc_ioapic_entries(void);
 extern void free_ioapic_entries(struct IO_APIC_route_entry **ioapic_entries);
diff --git a/arch/x86/include/asm/numa.h b/arch/x86/include/asm/numa.h
index 3d4dab4..a50fc9f 100644
--- a/arch/x86/include/asm/numa.h
+++ b/arch/x86/include/asm/numa.h
@@ -51,7 +51,7 @@ static inline void numa_remove_cpu(int cpu)		{ }
 #endif	/* CONFIG_NUMA */
 
 #ifdef CONFIG_DEBUG_PER_CPU_MAPS
-struct cpumask __cpuinit *debug_cpumask_set_cpu(int cpu, int enable);
+void debug_cpumask_set_cpu(int cpu, int node, bool enable);
 #endif
 
 #endif	/* _ASM_X86_NUMA_H */
diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c
index 86d1ad4..73fb469 100644
--- a/arch/x86/kernel/aperture_64.c
+++ b/arch/x86/kernel/aperture_64.c
@@ -499,7 +499,7 @@ out:
 		 * Don't enable translation yet but enable GART IO and CPU
 		 * accesses and set DISTLBWALKPRB since GART table memory is UC.
 		 */
-		u32 ctl = DISTLBWALKPRB | aper_order << 1;
+		u32 ctl = aper_order << 1;
 
 		bus = amd_nb_bus_dev_ranges[i].bus;
 		dev_base = amd_nb_bus_dev_ranges[i].dev_base;
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 68df09b..45fd33d 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -128,8 +128,8 @@ static int __init parse_noapic(char *str)
 }
 early_param("noapic", parse_noapic);
 
-static int io_apic_setup_irq_pin_once(unsigned int irq, int node,
-				      struct io_apic_irq_attr *attr);
+static int io_apic_setup_irq_pin(unsigned int irq, int node,
+				 struct io_apic_irq_attr *attr);
 
 /* Will be called in mpparse/acpi/sfi codes for saving IRQ info */
 void mp_save_irq(struct mpc_intsrc *m)
@@ -3570,7 +3570,7 @@ int arch_setup_ht_irq(unsigned int irq, struct pci_dev *dev)
 }
 #endif /* CONFIG_HT_IRQ */
 
-int
+static int
 io_apic_setup_irq_pin(unsigned int irq, int node, struct io_apic_irq_attr *attr)
 {
 	struct irq_cfg *cfg = alloc_irq_and_cfg_at(irq, node);
@@ -3585,8 +3585,8 @@ io_apic_setup_irq_pin(unsigned int irq, int node, struct io_apic_irq_attr *attr)
 	return ret;
 }
 
-static int io_apic_setup_irq_pin_once(unsigned int irq, int node,
-				      struct io_apic_irq_attr *attr)
+int io_apic_setup_irq_pin_once(unsigned int irq, int node,
+			       struct io_apic_irq_attr *attr)
 {
 	unsigned int id = attr->ioapic, pin = attr->ioapic_pin;
 	int ret;
diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c
index 0b4be43..adee12e 100644
--- a/arch/x86/kernel/apm_32.c
+++ b/arch/x86/kernel/apm_32.c
@@ -228,6 +228,7 @@
 #include <linux/kthread.h>
 #include <linux/jiffies.h>
 #include <linux/acpi.h>
+#include <linux/syscore_ops.h>
 
 #include <asm/system.h>
 #include <asm/uaccess.h>
@@ -1238,6 +1239,7 @@ static int suspend(int vetoable)
 
 	local_irq_disable();
 	sysdev_suspend(PMSG_SUSPEND);
+	syscore_suspend();
 
 	local_irq_enable();
 
@@ -1255,6 +1257,7 @@ static int suspend(int vetoable)
 		apm_error("suspend", err);
 	err = (err == APM_SUCCESS) ? 0 : -EIO;
 
+	syscore_resume();
 	sysdev_resume();
 	local_irq_enable();
 
@@ -1280,6 +1283,7 @@ static void standby(void)
 
 	local_irq_disable();
 	sysdev_suspend(PMSG_SUSPEND);
+	syscore_suspend();
 	local_irq_enable();
 
 	err = set_system_power_state(APM_STATE_STANDBY);
@@ -1287,6 +1291,7 @@ static void standby(void)
 		apm_error("standby", err);
 
 	local_irq_disable();
+	syscore_resume();
 	sysdev_resume();
 	local_irq_enable();
 
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 3532d3b..bb9eb29 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -698,7 +698,7 @@ cpu_dev_register(amd_cpu_dev);
  */
 
 const int amd_erratum_400[] =
-	AMD_OSVW_ERRATUM(1, AMD_MODEL_RANGE(0xf, 0x41, 0x2, 0xff, 0xf),
+	AMD_OSVW_ERRATUM(1, AMD_MODEL_RANGE(0x0f, 0x4, 0x2, 0xff, 0xf),
 			    AMD_MODEL_RANGE(0x10, 0x2, 0x1, 0xff, 0xf));
 EXPORT_SYMBOL_GPL(amd_erratum_400);
 
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index eed3673a..e638689 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -586,8 +586,12 @@ static int x86_setup_perfctr(struct perf_event *event)
 			return -EOPNOTSUPP;
 	}
 
+	/*
+	 * Do not allow config1 (extended registers) to propagate,
+	 * there's no sane user-space generalization yet:
+	 */
 	if (attr->type == PERF_TYPE_RAW)
-		return x86_pmu_extra_regs(event->attr.config, event);
+		return 0;
 
 	if (attr->type == PERF_TYPE_HW_CACHE)
 		return set_ext_hw_attr(hwc, event);
@@ -609,8 +613,8 @@ static int x86_setup_perfctr(struct perf_event *event)
 	/*
 	 * Branch tracing:
 	 */
-	if ((attr->config == PERF_COUNT_HW_BRANCH_INSTRUCTIONS) &&
-	    (hwc->sample_period == 1)) {
+	if (attr->config == PERF_COUNT_HW_BRANCH_INSTRUCTIONS &&
+	    !attr->freq && hwc->sample_period == 1) {
 		/* BTS is not supported by this architecture. */
 		if (!x86_pmu.bts_active)
 			return -EOPNOTSUPP;
@@ -1284,6 +1288,16 @@ static int x86_pmu_handle_irq(struct pt_regs *regs)
 
 	cpuc = &__get_cpu_var(cpu_hw_events);
 
+	/*
+	 * Some chipsets need to unmask the LVTPC in a particular spot
+	 * inside the nmi handler.  As a result, the unmasking was pushed
+	 * into all the nmi handlers.
+	 *
+	 * This generic handler doesn't seem to have any issues where the
+	 * unmasking occurs so it was left at the top.
+	 */
+	apic_write(APIC_LVTPC, APIC_DM_NMI);
+
 	for (idx = 0; idx < x86_pmu.num_counters; idx++) {
 		if (!test_bit(idx, cpuc->active_mask)) {
 			/*
@@ -1370,8 +1384,6 @@ perf_event_nmi_handler(struct notifier_block *self,
 		return NOTIFY_DONE;
 	}
 
-	apic_write(APIC_LVTPC, APIC_DM_NMI);
-
 	handled = x86_pmu.handle_irq(args->regs);
 	if (!handled)
 		return NOTIFY_DONE;
diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c
index 461f62b..cf4e369 100644
--- a/arch/x86/kernel/cpu/perf_event_amd.c
+++ b/arch/x86/kernel/cpu/perf_event_amd.c
@@ -8,7 +8,7 @@ static __initconst const u64 amd_hw_cache_event_ids
  [ C(L1D) ] = {
 	[ C(OP_READ) ] = {
 		[ C(RESULT_ACCESS) ] = 0x0040, /* Data Cache Accesses        */
-		[ C(RESULT_MISS)   ] = 0x0041, /* Data Cache Misses          */
+		[ C(RESULT_MISS)   ] = 0x0141, /* Data Cache Misses          */
 	},
 	[ C(OP_WRITE) ] = {
 		[ C(RESULT_ACCESS) ] = 0x0142, /* Data Cache Refills :system */
@@ -427,7 +427,9 @@ static __initconst const struct x86_pmu amd_pmu = {
  *
  * Exceptions:
  *
+ * 0x000	FP	PERF_CTL[3], PERF_CTL[5:3] (*)
  * 0x003	FP	PERF_CTL[3]
+ * 0x004	FP	PERF_CTL[3], PERF_CTL[5:3] (*)
  * 0x00B	FP	PERF_CTL[3]
  * 0x00D	FP	PERF_CTL[3]
  * 0x023	DE	PERF_CTL[2:0]
@@ -448,6 +450,8 @@ static __initconst const struct x86_pmu amd_pmu = {
  * 0x0DF	LS	PERF_CTL[5:0]
  * 0x1D6	EX	PERF_CTL[5:0]
  * 0x1D8	EX	PERF_CTL[5:0]
+ *
+ * (*) depending on the umask all FPU counters may be used
  */
 
 static struct event_constraint amd_f15_PMC0  = EVENT_CONSTRAINT(0, 0x01, 0);
@@ -460,18 +464,28 @@ static struct event_constraint amd_f15_PMC53 = EVENT_CONSTRAINT(0, 0x38, 0);
 static struct event_constraint *
 amd_get_event_constraints_f15h(struct cpu_hw_events *cpuc, struct perf_event *event)
 {
-	unsigned int event_code = amd_get_event_code(&event->hw);
+	struct hw_perf_event *hwc = &event->hw;
+	unsigned int event_code = amd_get_event_code(hwc);
 
 	switch (event_code & AMD_EVENT_TYPE_MASK) {
 	case AMD_EVENT_FP:
 		switch (event_code) {
+		case 0x000:
+			if (!(hwc->config & 0x0000F000ULL))
+				break;
+			if (!(hwc->config & 0x00000F00ULL))
+				break;
+			return &amd_f15_PMC3;
+		case 0x004:
+			if (hweight_long(hwc->config & ARCH_PERFMON_EVENTSEL_UMASK) <= 1)
+				break;
+			return &amd_f15_PMC3;
 		case 0x003:
 		case 0x00B:
 		case 0x00D:
 			return &amd_f15_PMC3;
-		default:
-			return &amd_f15_PMC53;
 		}
+		return &amd_f15_PMC53;
 	case AMD_EVENT_LS:
 	case AMD_EVENT_DC:
 	case AMD_EVENT_EX_LS:
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 8fc2b2c..447a28d 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -25,7 +25,7 @@ struct intel_percore {
 /*
  * Intel PerfMon, used on Core and later.
  */
-static const u64 intel_perfmon_event_map[] =
+static u64 intel_perfmon_event_map[PERF_COUNT_HW_MAX] __read_mostly =
 {
   [PERF_COUNT_HW_CPU_CYCLES]		= 0x003c,
   [PERF_COUNT_HW_INSTRUCTIONS]		= 0x00c0,
@@ -184,26 +184,23 @@ static __initconst const u64 snb_hw_cache_event_ids
 	},
  },
  [ C(LL  ) ] = {
-	/*
-	 * TBD: Need Off-core Response Performance Monitoring support
-	 */
 	[ C(OP_READ) ] = {
-		/* OFFCORE_RESPONSE_0.ANY_DATA.LOCAL_CACHE */
+		/* OFFCORE_RESPONSE.ANY_DATA.LOCAL_CACHE */
 		[ C(RESULT_ACCESS) ] = 0x01b7,
-		/* OFFCORE_RESPONSE_1.ANY_DATA.ANY_LLC_MISS */
-		[ C(RESULT_MISS)   ] = 0x01bb,
+		/* OFFCORE_RESPONSE.ANY_DATA.ANY_LLC_MISS */
+		[ C(RESULT_MISS)   ] = 0x01b7,
 	},
 	[ C(OP_WRITE) ] = {
-		/* OFFCORE_RESPONSE_0.ANY_RFO.LOCAL_CACHE */
+		/* OFFCORE_RESPONSE.ANY_RFO.LOCAL_CACHE */
 		[ C(RESULT_ACCESS) ] = 0x01b7,
-		/* OFFCORE_RESPONSE_1.ANY_RFO.ANY_LLC_MISS */
-		[ C(RESULT_MISS)   ] = 0x01bb,
+		/* OFFCORE_RESPONSE.ANY_RFO.ANY_LLC_MISS */
+		[ C(RESULT_MISS)   ] = 0x01b7,
 	},
 	[ C(OP_PREFETCH) ] = {
-		/* OFFCORE_RESPONSE_0.PREFETCH.LOCAL_CACHE */
+		/* OFFCORE_RESPONSE.PREFETCH.LOCAL_CACHE */
 		[ C(RESULT_ACCESS) ] = 0x01b7,
-		/* OFFCORE_RESPONSE_1.PREFETCH.ANY_LLC_MISS */
-		[ C(RESULT_MISS)   ] = 0x01bb,
+		/* OFFCORE_RESPONSE.PREFETCH.ANY_LLC_MISS */
+		[ C(RESULT_MISS)   ] = 0x01b7,
 	},
  },
  [ C(DTLB) ] = {
@@ -285,26 +282,26 @@ static __initconst const u64 westmere_hw_cache_event_ids
  },
  [ C(LL  ) ] = {
 	[ C(OP_READ) ] = {
-		/* OFFCORE_RESPONSE_0.ANY_DATA.LOCAL_CACHE */
+		/* OFFCORE_RESPONSE.ANY_DATA.LOCAL_CACHE */
 		[ C(RESULT_ACCESS) ] = 0x01b7,
-		/* OFFCORE_RESPONSE_1.ANY_DATA.ANY_LLC_MISS */
-		[ C(RESULT_MISS)   ] = 0x01bb,
+		/* OFFCORE_RESPONSE.ANY_DATA.ANY_LLC_MISS */
+		[ C(RESULT_MISS)   ] = 0x01b7,
 	},
 	/*
 	 * Use RFO, not WRITEBACK, because a write miss would typically occur
 	 * on RFO.
 	 */
 	[ C(OP_WRITE) ] = {
-		/* OFFCORE_RESPONSE_1.ANY_RFO.LOCAL_CACHE */
-		[ C(RESULT_ACCESS) ] = 0x01bb,
-		/* OFFCORE_RESPONSE_0.ANY_RFO.ANY_LLC_MISS */
+		/* OFFCORE_RESPONSE.ANY_RFO.LOCAL_CACHE */
+		[ C(RESULT_ACCESS) ] = 0x01b7,
+		/* OFFCORE_RESPONSE.ANY_RFO.ANY_LLC_MISS */
 		[ C(RESULT_MISS)   ] = 0x01b7,
 	},
 	[ C(OP_PREFETCH) ] = {
-		/* OFFCORE_RESPONSE_0.PREFETCH.LOCAL_CACHE */
+		/* OFFCORE_RESPONSE.PREFETCH.LOCAL_CACHE */
 		[ C(RESULT_ACCESS) ] = 0x01b7,
-		/* OFFCORE_RESPONSE_1.PREFETCH.ANY_LLC_MISS */
-		[ C(RESULT_MISS)   ] = 0x01bb,
+		/* OFFCORE_RESPONSE.PREFETCH.ANY_LLC_MISS */
+		[ C(RESULT_MISS)   ] = 0x01b7,
 	},
  },
  [ C(DTLB) ] = {
@@ -352,16 +349,36 @@ static __initconst const u64 westmere_hw_cache_event_ids
 };
 
 /*
- * OFFCORE_RESPONSE MSR bits (subset), See IA32 SDM Vol 3 30.6.1.3
+ * Nehalem/Westmere MSR_OFFCORE_RESPONSE bits;
+ * See IA32 SDM Vol 3B 30.6.1.3
  */
 
-#define DMND_DATA_RD     (1 << 0)
-#define DMND_RFO         (1 << 1)
-#define DMND_WB          (1 << 3)
-#define PF_DATA_RD       (1 << 4)
-#define PF_DATA_RFO      (1 << 5)
-#define RESP_UNCORE_HIT  (1 << 8)
-#define RESP_MISS        (0xf600) /* non uncore hit */
+#define NHM_DMND_DATA_RD	(1 << 0)
+#define NHM_DMND_RFO		(1 << 1)
+#define NHM_DMND_IFETCH		(1 << 2)
+#define NHM_DMND_WB		(1 << 3)
+#define NHM_PF_DATA_RD		(1 << 4)
+#define NHM_PF_DATA_RFO		(1 << 5)
+#define NHM_PF_IFETCH		(1 << 6)
+#define NHM_OFFCORE_OTHER	(1 << 7)
+#define NHM_UNCORE_HIT		(1 << 8)
+#define NHM_OTHER_CORE_HIT_SNP	(1 << 9)
+#define NHM_OTHER_CORE_HITM	(1 << 10)
+        			/* reserved */
+#define NHM_REMOTE_CACHE_FWD	(1 << 12)
+#define NHM_REMOTE_DRAM		(1 << 13)
+#define NHM_LOCAL_DRAM		(1 << 14)
+#define NHM_NON_DRAM		(1 << 15)
+
+#define NHM_ALL_DRAM		(NHM_REMOTE_DRAM|NHM_LOCAL_DRAM)
+
+#define NHM_DMND_READ		(NHM_DMND_DATA_RD)
+#define NHM_DMND_WRITE		(NHM_DMND_RFO|NHM_DMND_WB)
+#define NHM_DMND_PREFETCH	(NHM_PF_DATA_RD|NHM_PF_DATA_RFO)
+
+#define NHM_L3_HIT	(NHM_UNCORE_HIT|NHM_OTHER_CORE_HIT_SNP|NHM_OTHER_CORE_HITM)
+#define NHM_L3_MISS	(NHM_NON_DRAM|NHM_ALL_DRAM|NHM_REMOTE_CACHE_FWD)
+#define NHM_L3_ACCESS	(NHM_L3_HIT|NHM_L3_MISS)
 
 static __initconst const u64 nehalem_hw_cache_extra_regs
 				[PERF_COUNT_HW_CACHE_MAX]
@@ -370,16 +387,16 @@ static __initconst const u64 nehalem_hw_cache_extra_regs
 {
  [ C(LL  ) ] = {
 	[ C(OP_READ) ] = {
-		[ C(RESULT_ACCESS) ] = DMND_DATA_RD|RESP_UNCORE_HIT,
-		[ C(RESULT_MISS)   ] = DMND_DATA_RD|RESP_MISS,
+		[ C(RESULT_ACCESS) ] = NHM_DMND_READ|NHM_L3_ACCESS,
+		[ C(RESULT_MISS)   ] = NHM_DMND_READ|NHM_L3_MISS,
 	},
 	[ C(OP_WRITE) ] = {
-		[ C(RESULT_ACCESS) ] = DMND_RFO|DMND_WB|RESP_UNCORE_HIT,
-		[ C(RESULT_MISS)   ] = DMND_RFO|DMND_WB|RESP_MISS,
+		[ C(RESULT_ACCESS) ] = NHM_DMND_WRITE|NHM_L3_ACCESS,
+		[ C(RESULT_MISS)   ] = NHM_DMND_WRITE|NHM_L3_MISS,
 	},
 	[ C(OP_PREFETCH) ] = {
-		[ C(RESULT_ACCESS) ] = PF_DATA_RD|PF_DATA_RFO|RESP_UNCORE_HIT,
-		[ C(RESULT_MISS)   ] = PF_DATA_RD|PF_DATA_RFO|RESP_MISS,
+		[ C(RESULT_ACCESS) ] = NHM_DMND_PREFETCH|NHM_L3_ACCESS,
+		[ C(RESULT_MISS)   ] = NHM_DMND_PREFETCH|NHM_L3_MISS,
 	},
  }
 };
@@ -391,12 +408,12 @@ static __initconst const u64 nehalem_hw_cache_event_ids
 {
  [ C(L1D) ] = {
 	[ C(OP_READ) ] = {
-		[ C(RESULT_ACCESS) ] = 0x0f40, /* L1D_CACHE_LD.MESI            */
-		[ C(RESULT_MISS)   ] = 0x0140, /* L1D_CACHE_LD.I_STATE         */
+		[ C(RESULT_ACCESS) ] = 0x010b, /* MEM_INST_RETIRED.LOADS       */
+		[ C(RESULT_MISS)   ] = 0x0151, /* L1D.REPL                     */
 	},
 	[ C(OP_WRITE) ] = {
-		[ C(RESULT_ACCESS) ] = 0x0f41, /* L1D_CACHE_ST.MESI            */
-		[ C(RESULT_MISS)   ] = 0x0141, /* L1D_CACHE_ST.I_STATE         */
+		[ C(RESULT_ACCESS) ] = 0x020b, /* MEM_INST_RETURED.STORES      */
+		[ C(RESULT_MISS)   ] = 0x0251, /* L1D.M_REPL                   */
 	},
 	[ C(OP_PREFETCH) ] = {
 		[ C(RESULT_ACCESS) ] = 0x014e, /* L1D_PREFETCH.REQUESTS        */
@@ -933,6 +950,16 @@ static int intel_pmu_handle_irq(struct pt_regs *regs)
 
 	cpuc = &__get_cpu_var(cpu_hw_events);
 
+	/*
+	 * Some chipsets need to unmask the LVTPC in a particular spot
+	 * inside the nmi handler.  As a result, the unmasking was pushed
+	 * into all the nmi handlers.
+	 *
+	 * This handler doesn't seem to have any issues with the unmasking
+	 * so it was left at the top.
+	 */
+	apic_write(APIC_LVTPC, APIC_DM_NMI);
+
 	intel_pmu_disable_all();
 	handled = intel_pmu_drain_bts_buffer();
 	status = intel_pmu_get_status();
@@ -998,6 +1025,9 @@ intel_bts_constraints(struct perf_event *event)
 	struct hw_perf_event *hwc = &event->hw;
 	unsigned int hw_event, bts_event;
 
+	if (event->attr.freq)
+		return NULL;
+
 	hw_event = hwc->config & INTEL_ARCH_EVENT_MASK;
 	bts_event = x86_pmu.event_map(PERF_COUNT_HW_BRANCH_INSTRUCTIONS);
 
@@ -1305,7 +1335,7 @@ static void intel_clovertown_quirks(void)
 	 * AJ106 could possibly be worked around by not allowing LBR
 	 *       usage from PEBS, including the fixup.
 	 * AJ68  could possibly be worked around by always programming
-	 * 	 a pebs_event_reset[0] value and coping with the lost events.
+	 *	 a pebs_event_reset[0] value and coping with the lost events.
 	 *
 	 * But taken together it might just make sense to not enable PEBS on
 	 * these chips.
@@ -1409,6 +1439,18 @@ static __init int intel_pmu_init(void)
 		x86_pmu.percore_constraints = intel_nehalem_percore_constraints;
 		x86_pmu.enable_all = intel_pmu_nhm_enable_all;
 		x86_pmu.extra_regs = intel_nehalem_extra_regs;
+
+		if (ebx & 0x40) {
+			/*
+			 * Erratum AAJ80 detected, we work it around by using
+			 * the BR_MISP_EXEC.ANY event. This will over-count
+			 * branch-misses, but it's still much better than the
+			 * architectural event which is often completely bogus:
+			 */
+			intel_perfmon_event_map[PERF_COUNT_HW_BRANCH_MISSES] = 0x7f89;
+
+			pr_cont("erratum AAJ80 worked around, ");
+		}
 		pr_cont("Nehalem events, ");
 		break;
 
@@ -1425,6 +1467,7 @@ static __init int intel_pmu_init(void)
 
 	case 37: /* 32 nm nehalem, "Clarkdale" */
 	case 44: /* 32 nm nehalem, "Gulftown" */
+	case 47: /* 32 nm Xeon E7 */
 		memcpy(hw_cache_event_ids, westmere_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
 		memcpy(hw_cache_extra_regs, nehalem_hw_cache_extra_regs,
diff --git a/arch/x86/kernel/cpu/perf_event_p4.c b/arch/x86/kernel/cpu/perf_event_p4.c
index c2520e1..e93fcd5 100644
--- a/arch/x86/kernel/cpu/perf_event_p4.c
+++ b/arch/x86/kernel/cpu/perf_event_p4.c
@@ -947,14 +947,23 @@ static int p4_pmu_handle_irq(struct pt_regs *regs)
 		if (!x86_perf_event_set_period(event))
 			continue;
 		if (perf_event_overflow(event, 1, &data, regs))
-			p4_pmu_disable_event(event);
+			x86_pmu_stop(event, 0);
 	}
 
-	if (handled) {
-		/* p4 quirk: unmask it again */
-		apic_write(APIC_LVTPC, apic_read(APIC_LVTPC) & ~APIC_LVT_MASKED);
+	if (handled)
 		inc_irq_stat(apic_perf_irqs);
-	}
+
+	/*
+	 * When dealing with the unmasking of the LVTPC on P4 perf hw, it has
+	 * been observed that the OVF bit flag has to be cleared first _before_
+	 * the LVTPC can be unmasked.
+	 *
+	 * The reason is the NMI line will continue to be asserted while the OVF
+	 * bit is set.  This causes a second NMI to generate if the LVTPC is
+	 * unmasked before the OVF bit is cleared, leading to unknown NMI
+	 * messages.
+	 */
+	apic_write(APIC_LVTPC, APIC_DM_NMI);
 
 	return handled;
 }
diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c
index 706a9fb..e90f084 100644
--- a/arch/x86/kernel/devicetree.c
+++ b/arch/x86/kernel/devicetree.c
@@ -391,7 +391,7 @@ static int ioapic_xlate(struct irq_domain *id, const u32 *intspec, u32 intsize,
 
 	set_io_apic_irq_attr(&attr, idx, line, it->trigger, it->polarity);
 
-	return io_apic_setup_irq_pin(*out_hwirq, cpu_to_node(0), &attr);
+	return io_apic_setup_irq_pin_once(*out_hwirq, cpu_to_node(0), &attr);
 }
 
 static void __init ioapic_add_ofnode(struct device_node *np)
diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c
index 82ada01..b117efd 100644
--- a/arch/x86/kernel/pci-gart_64.c
+++ b/arch/x86/kernel/pci-gart_64.c
@@ -81,6 +81,9 @@ static u32 gart_unmapped_entry;
 #define AGPEXTERN
 #endif
 
+/* GART can only remap to physical addresses < 1TB */
+#define GART_MAX_PHYS_ADDR	(1ULL << 40)
+
 /* backdoor interface to AGP driver */
 AGPEXTERN int agp_memory_reserved;
 AGPEXTERN __u32 *agp_gatt_table;
@@ -212,9 +215,13 @@ static dma_addr_t dma_map_area(struct device *dev, dma_addr_t phys_mem,
 				size_t size, int dir, unsigned long align_mask)
 {
 	unsigned long npages = iommu_num_pages(phys_mem, size, PAGE_SIZE);
-	unsigned long iommu_page = alloc_iommu(dev, npages, align_mask);
+	unsigned long iommu_page;
 	int i;
 
+	if (unlikely(phys_mem + size > GART_MAX_PHYS_ADDR))
+		return bad_dma_addr;
+
+	iommu_page = alloc_iommu(dev, npages, align_mask);
 	if (iommu_page == -1) {
 		if (!nonforced_iommu(dev, phys_mem, size))
 			return phys_mem;
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index 45892dc..f65e5b5 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -608,6 +608,9 @@ static int ptrace_write_dr7(struct task_struct *tsk, unsigned long data)
 	unsigned len, type;
 	struct perf_event *bp;
 
+	if (ptrace_get_breakpoints(tsk) < 0)
+		return -ESRCH;
+
 	data &= ~DR_CONTROL_RESERVED;
 	old_dr7 = ptrace_get_dr7(thread->ptrace_bps);
 restore:
@@ -655,6 +658,9 @@ restore:
 		}
 		goto restore;
 	}
+
+	ptrace_put_breakpoints(tsk);
+
 	return ((orig_ret < 0) ? orig_ret : rc);
 }
 
@@ -668,10 +674,17 @@ static unsigned long ptrace_get_debugreg(struct task_struct *tsk, int n)
 
 	if (n < HBP_NUM) {
 		struct perf_event *bp;
+
+		if (ptrace_get_breakpoints(tsk) < 0)
+			return -ESRCH;
+
 		bp = thread->ptrace_bps[n];
 		if (!bp)
-			return 0;
-		val = bp->hw.info.address;
+			val = 0;
+		else
+			val = bp->hw.info.address;
+
+		ptrace_put_breakpoints(tsk);
 	} else if (n == 6) {
 		val = thread->debugreg6;
 	 } else if (n == 7) {
@@ -686,6 +699,10 @@ static int ptrace_set_breakpoint_addr(struct task_struct *tsk, int nr,
 	struct perf_event *bp;
 	struct thread_struct *t = &tsk->thread;
 	struct perf_event_attr attr;
+	int err = 0;
+
+	if (ptrace_get_breakpoints(tsk) < 0)
+		return -ESRCH;
 
 	if (!t->ptrace_bps[nr]) {
 		ptrace_breakpoint_init(&attr);
@@ -709,24 +726,23 @@ static int ptrace_set_breakpoint_addr(struct task_struct *tsk, int nr,
 		 * writing for the user. And anyway this is the previous
 		 * behaviour.
 		 */
-		if (IS_ERR(bp))
-			return PTR_ERR(bp);
+		if (IS_ERR(bp)) {
+			err = PTR_ERR(bp);
+			goto put;
+		}
 
 		t->ptrace_bps[nr] = bp;
 	} else {
-		int err;
-
 		bp = t->ptrace_bps[nr];
 
 		attr = bp->attr;
 		attr.bp_addr = addr;
 		err = modify_user_hw_breakpoint(bp, &attr);
-		if (err)
-			return err;
 	}
 
-
-	return 0;
+put:
+	ptrace_put_breakpoints(tsk);
+	return err;
 }
 
 /*
diff --git a/arch/x86/kernel/reboot_32.S b/arch/x86/kernel/reboot_32.S
index 29092b3..1d5c46d 100644
--- a/arch/x86/kernel/reboot_32.S
+++ b/arch/x86/kernel/reboot_32.S
@@ -21,26 +21,26 @@ r_base = .
 	/* Get our own relocated address */
 	call	1f
 1:	popl	%ebx
-	subl	$1b, %ebx
+	subl	$(1b - r_base), %ebx
 
 	/* Compute the equivalent real-mode segment */
 	movl	%ebx, %ecx
 	shrl	$4, %ecx
 	
 	/* Patch post-real-mode segment jump */
-	movw	dispatch_table(%ebx,%eax,2),%ax
-	movw	%ax, 101f(%ebx)
-	movw	%cx, 102f(%ebx)
+	movw	(dispatch_table - r_base)(%ebx,%eax,2),%ax
+	movw	%ax, (101f - r_base)(%ebx)
+	movw	%cx, (102f - r_base)(%ebx)
 
 	/* Set up the IDT for real mode. */
-	lidtl	machine_real_restart_idt(%ebx)
+	lidtl	(machine_real_restart_idt - r_base)(%ebx)
 
 	/*
 	 * Set up a GDT from which we can load segment descriptors for real
 	 * mode.  The GDT is not used in real mode; it is just needed here to
 	 * prepare the descriptors.
 	 */
-	lgdtl	machine_real_restart_gdt(%ebx)
+	lgdtl	(machine_real_restart_gdt - r_base)(%ebx)
 
 	/*
 	 * Load the data segment registers with 16-bit compatible values
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 8ed8908..c2871d3 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -312,26 +312,6 @@ void __cpuinit smp_store_cpu_info(int id)
 		identify_secondary_cpu(c);
 }
 
-static void __cpuinit check_cpu_siblings_on_same_node(int cpu1, int cpu2)
-{
-	int node1 = early_cpu_to_node(cpu1);
-	int node2 = early_cpu_to_node(cpu2);
-
-	/*
-	 * Our CPU scheduler assumes all logical cpus in the same physical cpu
-	 * share the same node. But, buggy ACPI or NUMA emulation might assign
-	 * them to different node. Fix it.
-	 */
-	if (node1 != node2) {
-		pr_warning("CPU %d in node %d and CPU %d in node %d are in the same physical CPU. forcing same node %d\n",
-			   cpu1, node1, cpu2, node2, node2);
-
-		numa_remove_cpu(cpu1);
-		numa_set_node(cpu1, node2);
-		numa_add_cpu(cpu1);
-	}
-}
-
 static void __cpuinit link_thread_siblings(int cpu1, int cpu2)
 {
 	cpumask_set_cpu(cpu1, cpu_sibling_mask(cpu2));
@@ -340,7 +320,6 @@ static void __cpuinit link_thread_siblings(int cpu1, int cpu2)
 	cpumask_set_cpu(cpu2, cpu_core_mask(cpu1));
 	cpumask_set_cpu(cpu1, cpu_llc_shared_mask(cpu2));
 	cpumask_set_cpu(cpu2, cpu_llc_shared_mask(cpu1));
-	check_cpu_siblings_on_same_node(cpu1, cpu2);
 }
 
 
@@ -382,12 +361,10 @@ void __cpuinit set_cpu_sibling_map(int cpu)
 		    per_cpu(cpu_llc_id, cpu) == per_cpu(cpu_llc_id, i)) {
 			cpumask_set_cpu(i, cpu_llc_shared_mask(cpu));
 			cpumask_set_cpu(cpu, cpu_llc_shared_mask(i));
-			check_cpu_siblings_on_same_node(cpu, i);
 		}
 		if (c->phys_proc_id == cpu_data(i).phys_proc_id) {
 			cpumask_set_cpu(i, cpu_core_mask(cpu));
 			cpumask_set_cpu(cpu, cpu_core_mask(i));
-			check_cpu_siblings_on_same_node(cpu, i);
 			/*
 			 *  Does this new cpu bringup a new core?
 			 */
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index 9559d36..745258d 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -213,53 +213,48 @@ int early_cpu_to_node(int cpu)
 	return per_cpu(x86_cpu_to_node_map, cpu);
 }
 
-struct cpumask __cpuinit *debug_cpumask_set_cpu(int cpu, int enable)
+void debug_cpumask_set_cpu(int cpu, int node, bool enable)
 {
-	int node = early_cpu_to_node(cpu);
 	struct cpumask *mask;
 	char buf[64];
 
 	if (node == NUMA_NO_NODE) {
 		/* early_cpu_to_node() already emits a warning and trace */
-		return NULL;
+		return;
 	}
 	mask = node_to_cpumask_map[node];
 	if (!mask) {
 		pr_err("node_to_cpumask_map[%i] NULL\n", node);
 		dump_stack();
-		return NULL;
+		return;
 	}
 
+	if (enable)
+		cpumask_set_cpu(cpu, mask);
+	else
+		cpumask_clear_cpu(cpu, mask);
+
 	cpulist_scnprintf(buf, sizeof(buf), mask);
 	printk(KERN_DEBUG "%s cpu %d node %d: mask now %s\n",
 		enable ? "numa_add_cpu" : "numa_remove_cpu",
 		cpu, node, buf);
-	return mask;
+	return;
 }
 
 # ifndef CONFIG_NUMA_EMU
-static void __cpuinit numa_set_cpumask(int cpu, int enable)
+static void __cpuinit numa_set_cpumask(int cpu, bool enable)
 {
-	struct cpumask *mask;
-
-	mask = debug_cpumask_set_cpu(cpu, enable);
-	if (!mask)
-		return;
-
-	if (enable)
-		cpumask_set_cpu(cpu, mask);
-	else
-		cpumask_clear_cpu(cpu, mask);
+	debug_cpumask_set_cpu(cpu, early_cpu_to_node(cpu), enable);
 }
 
 void __cpuinit numa_add_cpu(int cpu)
 {
-	numa_set_cpumask(cpu, 1);
+	numa_set_cpumask(cpu, true);
 }
 
 void __cpuinit numa_remove_cpu(int cpu)
 {
-	numa_set_cpumask(cpu, 0);
+	numa_set_cpumask(cpu, false);
 }
 # endif	/* !CONFIG_NUMA_EMU */
 
diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c
index e8c00cc..85b52fc 100644
--- a/arch/x86/mm/numa_64.c
+++ b/arch/x86/mm/numa_64.c
@@ -306,7 +306,7 @@ int __init numa_cleanup_meminfo(struct numa_meminfo *mi)
 		bi->end = min(bi->end, high);
 
 		/* and there's no empty block */
-		if (bi->start == bi->end) {
+		if (bi->start >= bi->end) {
 			numa_remove_memblk_from(i--, mi);
 			continue;
 		}
diff --git a/arch/x86/mm/numa_emulation.c b/arch/x86/mm/numa_emulation.c
index ad091e4..de84cc1 100644
--- a/arch/x86/mm/numa_emulation.c
+++ b/arch/x86/mm/numa_emulation.c
@@ -454,10 +454,9 @@ void __cpuinit numa_remove_cpu(int cpu)
 		cpumask_clear_cpu(cpu, node_to_cpumask_map[i]);
 }
 #else	/* !CONFIG_DEBUG_PER_CPU_MAPS */
-static void __cpuinit numa_set_cpumask(int cpu, int enable)
+static void __cpuinit numa_set_cpumask(int cpu, bool enable)
 {
-	struct cpumask *mask;
-	int nid, physnid, i;
+	int nid, physnid;
 
 	nid = early_cpu_to_node(cpu);
 	if (nid == NUMA_NO_NODE) {
@@ -467,28 +466,21 @@ static void __cpuinit numa_set_cpumask(int cpu, int enable)
 
 	physnid = emu_nid_to_phys[nid];
 
-	for_each_online_node(i) {
+	for_each_online_node(nid) {
 		if (emu_nid_to_phys[nid] != physnid)
 			continue;
 
-		mask = debug_cpumask_set_cpu(cpu, enable);
-		if (!mask)
-			return;
-
-		if (enable)
-			cpumask_set_cpu(cpu, mask);
-		else
-			cpumask_clear_cpu(cpu, mask);
+		debug_cpumask_set_cpu(cpu, nid, enable);
 	}
 }
 
 void __cpuinit numa_add_cpu(int cpu)
 {
-	numa_set_cpumask(cpu, 1);
+	numa_set_cpumask(cpu, true);
 }
 
 void __cpuinit numa_remove_cpu(int cpu)
 {
-	numa_set_cpumask(cpu, 0);
+	numa_set_cpumask(cpu, false);
 }
 #endif	/* !CONFIG_DEBUG_PER_CPU_MAPS */
diff --git a/arch/x86/platform/ce4100/falconfalls.dts b/arch/x86/platform/ce4100/falconfalls.dts
index 2d6d226..e70be38 100644
--- a/arch/x86/platform/ce4100/falconfalls.dts
+++ b/arch/x86/platform/ce4100/falconfalls.dts
@@ -347,7 +347,7 @@
 						   "pciclass0c03";
 
 					reg = <0x16800 0x0 0x0 0x0 0x0>;
-					interrupts = <22 3>;
+					interrupts = <22 1>;
 				};
 
 				usb@d,1 {
@@ -357,7 +357,7 @@
 						   "pciclass0c03";
 
 					reg = <0x16900 0x0 0x0 0x0 0x0>;
-					interrupts = <22 3>;
+					interrupts = <22 1>;
 				};
 
 				sata@e,0 {
@@ -367,7 +367,7 @@
 						   "pciclass0106";
 
 					reg = <0x17000 0x0 0x0 0x0 0x0>;
-					interrupts = <23 3>;
+					interrupts = <23 1>;
 				};
 
 				flash@f,0 {
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index a991b57..55c965b 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -1463,6 +1463,119 @@ static int xen_pgd_alloc(struct mm_struct *mm)
 	return ret;
 }
 
+#ifdef CONFIG_X86_64
+static __initdata u64 __last_pgt_set_rw = 0;
+static __initdata u64 __pgt_buf_start = 0;
+static __initdata u64 __pgt_buf_end = 0;
+static __initdata u64 __pgt_buf_top = 0;
+/*
+ * As a consequence of the commit:
+ * 
+ * commit 4b239f458c229de044d6905c2b0f9fe16ed9e01e
+ * Author: Yinghai Lu <yinghai@kernel.org>
+ * Date:   Fri Dec 17 16:58:28 2010 -0800
+ * 
+ *     x86-64, mm: Put early page table high
+ * 
+ * at some point init_memory_mapping is going to reach the pagetable pages
+ * area and map those pages too (mapping them as normal memory that falls
+ * in the range of addresses passed to init_memory_mapping as argument).
+ * Some of those pages are already pagetable pages (they are in the range
+ * pgt_buf_start-pgt_buf_end) therefore they are going to be mapped RO and
+ * everything is fine.
+ * Some of these pages are not pagetable pages yet (they fall in the range
+ * pgt_buf_end-pgt_buf_top; for example the page at pgt_buf_end) so they
+ * are going to be mapped RW.  When these pages become pagetable pages and
+ * are hooked into the pagetable, xen will find that the guest has already
+ * a RW mapping of them somewhere and fail the operation.
+ * The reason Xen requires pagetables to be RO is that the hypervisor needs
+ * to verify that the pagetables are valid before using them. The validation
+ * operations are called "pinning".
+ * 
+ * In order to fix the issue we mark all the pages in the entire range
+ * pgt_buf_start-pgt_buf_top as RO, however when the pagetable allocation
+ * is completed only the range pgt_buf_start-pgt_buf_end is reserved by
+ * init_memory_mapping. Hence the kernel is going to crash as soon as one
+ * of the pages in the range pgt_buf_end-pgt_buf_top is reused (b/c those
+ * ranges are RO).
+ * 
+ * For this reason, 'mark_rw_past_pgt' is introduced which is called _after_
+ * the init_memory_mapping has completed (in a perfect world we would
+ * call this function from init_memory_mapping, but lets ignore that).
+ * 
+ * Because we are called _after_ init_memory_mapping the pgt_buf_[start,
+ * end,top] have all changed to new values (b/c init_memory_mapping
+ * is called and setting up another new page-table). Hence, the first time
+ * we enter this function, we save away the pgt_buf_start value and update
+ * the pgt_buf_[end,top].
+ * 
+ * When we detect that the "old" pgt_buf_start through pgt_buf_end
+ * PFNs have been reserved (so memblock_x86_reserve_range has been called),
+ * we immediately set out to RW the "old" pgt_buf_end through pgt_buf_top.
+ * 
+ * And then we update those "old" pgt_buf_[end|top] with the new ones
+ * so that we can redo this on the next pagetable.
+ */
+static __init void mark_rw_past_pgt(void) {
+
+	if (pgt_buf_end > pgt_buf_start) {
+		u64 addr, size;
+
+		/* Save it away. */
+		if (!__pgt_buf_start) {
+			__pgt_buf_start = pgt_buf_start;
+			__pgt_buf_end = pgt_buf_end;
+			__pgt_buf_top = pgt_buf_top;
+			return;
+		}
+		/* If we get the range that starts at __pgt_buf_end that means
+		 * the range is reserved, and that in 'init_memory_mapping'
+		 * the 'memblock_x86_reserve_range' has been called with the
+		 * outdated __pgt_buf_start, __pgt_buf_end (the "new"
+		 * pgt_buf_[start|end|top] refer now to a new pagetable.
+		 * Note: we are called _after_ the pgt_buf_[..] have been
+		 * updated.*/
+
+		addr = memblock_x86_find_in_range_size(PFN_PHYS(__pgt_buf_start),
+						       &size, PAGE_SIZE);
+
+		/* Still not reserved, meaning 'memblock_x86_reserve_range'
+		 * hasn't been called yet. Update the _end and _top.*/
+		if (addr == PFN_PHYS(__pgt_buf_start)) {
+			__pgt_buf_end = pgt_buf_end;
+			__pgt_buf_top = pgt_buf_top;
+			return;
+		}
+
+		/* OK, the area is reserved, meaning it is time for us to
+		 * set RW for the old end->top PFNs. */
+
+		/* ..unless we had already done this. */
+		if (__pgt_buf_end == __last_pgt_set_rw)
+			return;
+
+		addr = PFN_PHYS(__pgt_buf_end);
+		
+		/* set as RW the rest */
+		printk(KERN_DEBUG "xen: setting RW the range %llx - %llx\n",
+			PFN_PHYS(__pgt_buf_end), PFN_PHYS(__pgt_buf_top));
+		
+		while (addr < PFN_PHYS(__pgt_buf_top)) {
+			make_lowmem_page_readwrite(__va(addr));
+			addr += PAGE_SIZE;
+		}
+		/* And update everything so that we are ready for the next
+		 * pagetable (the one created for regions past 4GB) */
+		__last_pgt_set_rw = __pgt_buf_end;
+		__pgt_buf_start = pgt_buf_start;
+		__pgt_buf_end = pgt_buf_end;
+		__pgt_buf_top = pgt_buf_top;
+	}
+	return;
+}
+#else
+static __init void mark_rw_past_pgt(void) { }
+#endif
 static void xen_pgd_free(struct mm_struct *mm, pgd_t *pgd)
 {
 #ifdef CONFIG_X86_64
@@ -1473,30 +1586,43 @@ static void xen_pgd_free(struct mm_struct *mm, pgd_t *pgd)
 #endif
 }
 
+#ifdef CONFIG_X86_32
 static __init pte_t mask_rw_pte(pte_t *ptep, pte_t pte)
 {
-	unsigned long pfn = pte_pfn(pte);
-
-#ifdef CONFIG_X86_32
 	/* If there's an existing pte, then don't allow _PAGE_RW to be set */
 	if (pte_val_ma(*ptep) & _PAGE_PRESENT)
 		pte = __pte_ma(((pte_val_ma(*ptep) & _PAGE_RW) | ~_PAGE_RW) &
 			       pte_val_ma(pte));
-#endif
+
+	return pte;
+}
+#else /* CONFIG_X86_64 */
+static __init pte_t mask_rw_pte(pte_t *ptep, pte_t pte)
+{
+	unsigned long pfn = pte_pfn(pte);
 
 	/*
+	 * A bit of optimization. We do not need to call the workaround
+	 * when xen_set_pte_init is called with a PTE with 0 as PFN.
+	 * That is b/c the pagetable at that point are just being populated
+	 * with empty values and we can save some cycles by not calling
+	 * the 'memblock' code.*/
+	if (pfn)
+		mark_rw_past_pgt();
+	/*
 	 * If the new pfn is within the range of the newly allocated
 	 * kernel pagetable, and it isn't being mapped into an
 	 * early_ioremap fixmap slot as a freshly allocated page, make sure
 	 * it is RO.
 	 */
 	if (((!is_early_ioremap_ptep(ptep) &&
-			pfn >= pgt_buf_start && pfn < pgt_buf_end)) ||
+			pfn >= pgt_buf_start && pfn < pgt_buf_top)) ||
 			(is_early_ioremap_ptep(ptep) && pfn != (pgt_buf_end - 1)))
 		pte = pte_wrprotect(pte);
 
 	return pte;
 }
+#endif /* CONFIG_X86_64 */
 
 /* Init-time set_pte while constructing initial pagetables, which
    doesn't allow RO pagetable pages to be remapped RW */
@@ -1992,6 +2118,8 @@ __init void xen_ident_map_ISA(void)
 
 static __init void xen_post_allocator_init(void)
 {
+	mark_rw_past_pgt();
+
 #ifdef CONFIG_XEN_DEBUG
 	pv_mmu_ops.make_pte = PV_CALLEE_SAVE(xen_make_pte_debug);
 #endif
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index fa0269a..90bac0a 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -227,7 +227,7 @@ char * __init xen_memory_setup(void)
 
 	memcpy(map_raw, map, sizeof(map));
 	e820.nr_map = 0;
-	xen_extra_mem_start = mem_end;
+	xen_extra_mem_start = max((1ULL << 32), mem_end);
 	for (i = 0; i < memmap.nr_entries; i++) {
 		unsigned long long end;
 
diff --git a/arch/xtensa/kernel/irq.c b/arch/xtensa/kernel/irq.c
index d77089d..4340ee0 100644
--- a/arch/xtensa/kernel/irq.c
+++ b/arch/xtensa/kernel/irq.c
@@ -64,47 +64,41 @@ asmlinkage void do_IRQ(int irq, struct pt_regs *regs)
 
 int arch_show_interrupts(struct seq_file *p, int prec)
 {
-	int j;
-
-	seq_printf(p, "%*s: ", prec, "NMI");
-	for_each_online_cpu(j)
-		seq_printf(p, "%10u ", nmi_count(j));
-	seq_putc(p, '\n');
 	seq_printf(p, "%*s: ", prec, "ERR");
 	seq_printf(p, "%10u\n", atomic_read(&irq_err_count));
 	return 0;
 }
 
-static void xtensa_irq_mask(struct irq_chip *d)
+static void xtensa_irq_mask(struct irq_data *d)
 {
 	cached_irq_mask &= ~(1 << d->irq);
 	set_sr (cached_irq_mask, INTENABLE);
 }
 
-static void xtensa_irq_unmask(struct irq_chip *d)
+static void xtensa_irq_unmask(struct irq_data *d)
 {
 	cached_irq_mask |= 1 << d->irq;
 	set_sr (cached_irq_mask, INTENABLE);
 }
 
-static void xtensa_irq_enable(struct irq_chip *d)
+static void xtensa_irq_enable(struct irq_data *d)
 {
 	variant_irq_enable(d->irq);
 	xtensa_irq_unmask(d->irq);
 }
 
-static void xtensa_irq_disable(struct irq_chip *d)
+static void xtensa_irq_disable(struct irq_data *d)
 {
 	xtensa_irq_mask(d->irq);
 	variant_irq_disable(d->irq);
 }
 
-static void xtensa_irq_ack(struct irq_chip *d)
+static void xtensa_irq_ack(struct irq_data *d)
 {
 	set_sr(1 << d->irq, INTCLEAR);
 }
 
-static int xtensa_irq_retrigger(struct irq_chip *d)
+static int xtensa_irq_retrigger(struct irq_data *d)
 {
 	set_sr (1 << d->irq, INTSET);
 	return 1;