Merge git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux into rmobile-fixes-for-linus

9 files changed, 376 insertions, 70 deletions

diff --git a/arch/x86/include/asm/cmpxchg.h b/arch/x86/include/asm/cmpxchg.h
index 0c9fa2745f1..b3b73326290 100644
--- a/arch/x86/include/asm/cmpxchg.h
+++ b/arch/x86/include/asm/cmpxchg.h
@@ -145,13 +145,13 @@ extern void __add_wrong_size(void)
 
 #ifdef __HAVE_ARCH_CMPXCHG
 #define cmpxchg(ptr, old, new)						\
-	__cmpxchg((ptr), (old), (new), sizeof(*ptr))
+	__cmpxchg(ptr, old, new, sizeof(*(ptr)))
 
 #define sync_cmpxchg(ptr, old, new)					\
-	__sync_cmpxchg((ptr), (old), (new), sizeof(*ptr))
+	__sync_cmpxchg(ptr, old, new, sizeof(*(ptr)))
 
 #define cmpxchg_local(ptr, old, new)					\
-	__cmpxchg_local((ptr), (old), (new), sizeof(*ptr))
+	__cmpxchg_local(ptr, old, new, sizeof(*(ptr)))
 #endif
 
 /*
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index 17c5d4bdee5..8d67d428b0f 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -159,6 +159,7 @@
 #define X86_FEATURE_WDT		(6*32+13) /* Watchdog timer */
 #define X86_FEATURE_LWP		(6*32+15) /* Light Weight Profiling */
 #define X86_FEATURE_FMA4	(6*32+16) /* 4 operands MAC instructions */
+#define X86_FEATURE_TCE		(6*32+17) /* translation cache extension */
 #define X86_FEATURE_NODEID_MSR	(6*32+19) /* NodeId MSR */
 #define X86_FEATURE_TBM		(6*32+21) /* trailing bit manipulations */
 #define X86_FEATURE_TOPOEXT	(6*32+22) /* topology extensions CPUID leafs */
diff --git a/arch/x86/include/asm/i387.h b/arch/x86/include/asm/i387.h
index 6919e936345..247904945d3 100644
--- a/arch/x86/include/asm/i387.h
+++ b/arch/x86/include/asm/i387.h
@@ -29,10 +29,11 @@ extern unsigned int sig_xstate_size;
 extern void fpu_init(void);
 extern void mxcsr_feature_mask_init(void);
 extern int init_fpu(struct task_struct *child);
-extern asmlinkage void math_state_restore(void);
-extern void __math_state_restore(void);
+extern void math_state_restore(void);
 extern int dump_fpu(struct pt_regs *, struct user_i387_struct *);
 
+DECLARE_PER_CPU(struct task_struct *, fpu_owner_task);
+
 extern user_regset_active_fn fpregs_active, xfpregs_active;
 extern user_regset_get_fn fpregs_get, xfpregs_get, fpregs_soft_get,
 				xstateregs_get;
@@ -212,19 +213,11 @@ static inline void fpu_fxsave(struct fpu *fpu)
 
 #endif	/* CONFIG_X86_64 */
 
-/* We need a safe address that is cheap to find and that is already
-   in L1 during context switch. The best choices are unfortunately
-   different for UP and SMP */
-#ifdef CONFIG_SMP
-#define safe_address (__per_cpu_offset[0])
-#else
-#define safe_address (__get_cpu_var(kernel_cpustat).cpustat[CPUTIME_USER])
-#endif
-
 /*
- * These must be called with preempt disabled
+ * These must be called with preempt disabled. Returns
+ * 'true' if the FPU state is still intact.
  */
-static inline void fpu_save_init(struct fpu *fpu)
+static inline int fpu_save_init(struct fpu *fpu)
 {
 	if (use_xsave()) {
 		fpu_xsave(fpu);
@@ -233,33 +226,33 @@ static inline void fpu_save_init(struct fpu *fpu)
 		 * xsave header may indicate the init state of the FP.
 		 */
 		if (!(fpu->state->xsave.xsave_hdr.xstate_bv & XSTATE_FP))
-			return;
+			return 1;
 	} else if (use_fxsr()) {
 		fpu_fxsave(fpu);
 	} else {
 		asm volatile("fnsave %[fx]; fwait"
 			     : [fx] "=m" (fpu->state->fsave));
-		return;
+		return 0;
 	}
 
-	if (unlikely(fpu->state->fxsave.swd & X87_FSW_ES))
+	/*
+	 * If exceptions are pending, we need to clear them so
+	 * that we don't randomly get exceptions later.
+	 *
+	 * FIXME! Is this perhaps only true for the old-style
+	 * irq13 case? Maybe we could leave the x87 state
+	 * intact otherwise?
+	 */
+	if (unlikely(fpu->state->fxsave.swd & X87_FSW_ES)) {
 		asm volatile("fnclex");
-
-	/* AMD K7/K8 CPUs don't save/restore FDP/FIP/FOP unless an exception
-	   is pending.  Clear the x87 state here by setting it to fixed
-	   values. safe_address is a random variable that should be in L1 */
-	alternative_input(
-		ASM_NOP8 ASM_NOP2,
-		"emms\n\t"	  	/* clear stack tags */
-		"fildl %P[addr]",	/* set F?P to defined value */
-		X86_FEATURE_FXSAVE_LEAK,
-		[addr] "m" (safe_address));
+		return 0;
+	}
+	return 1;
 }
 
-static inline void __save_init_fpu(struct task_struct *tsk)
+static inline int __save_init_fpu(struct task_struct *tsk)
 {
-	fpu_save_init(&tsk->thread.fpu);
-	task_thread_info(tsk)->status &= ~TS_USEDFPU;
+	return fpu_save_init(&tsk->thread.fpu);
 }
 
 static inline int fpu_fxrstor_checking(struct fpu *fpu)
@@ -277,44 +270,212 @@ static inline int fpu_restore_checking(struct fpu *fpu)
 
 static inline int restore_fpu_checking(struct task_struct *tsk)
 {
+	/* AMD K7/K8 CPUs don't save/restore FDP/FIP/FOP unless an exception
+	   is pending.  Clear the x87 state here by setting it to fixed
+	   values. "m" is a random variable that should be in L1 */
+	alternative_input(
+		ASM_NOP8 ASM_NOP2,
+		"emms\n\t"	  	/* clear stack tags */
+		"fildl %P[addr]",	/* set F?P to defined value */
+		X86_FEATURE_FXSAVE_LEAK,
+		[addr] "m" (tsk->thread.fpu.has_fpu));
+
 	return fpu_restore_checking(&tsk->thread.fpu);
 }
 
 /*
- * Signal frame handlers...
+ * Software FPU state helpers. Careful: these need to
+ * be preemption protection *and* they need to be
+ * properly paired with the CR0.TS changes!
  */
-extern int save_i387_xstate(void __user *buf);
-extern int restore_i387_xstate(void __user *buf);
+static inline int __thread_has_fpu(struct task_struct *tsk)
+{
+	return tsk->thread.fpu.has_fpu;
+}
 
-static inline void __unlazy_fpu(struct task_struct *tsk)
+/* Must be paired with an 'stts' after! */
+static inline void __thread_clear_has_fpu(struct task_struct *tsk)
 {
-	if (task_thread_info(tsk)->status & TS_USEDFPU) {
-		__save_init_fpu(tsk);
-		stts();
-	} else
-		tsk->fpu_counter = 0;
+	tsk->thread.fpu.has_fpu = 0;
+	percpu_write(fpu_owner_task, NULL);
+}
+
+/* Must be paired with a 'clts' before! */
+static inline void __thread_set_has_fpu(struct task_struct *tsk)
+{
+	tsk->thread.fpu.has_fpu = 1;
+	percpu_write(fpu_owner_task, tsk);
+}
+
+/*
+ * Encapsulate the CR0.TS handling together with the
+ * software flag.
+ *
+ * These generally need preemption protection to work,
+ * do try to avoid using these on their own.
+ */
+static inline void __thread_fpu_end(struct task_struct *tsk)
+{
+	__thread_clear_has_fpu(tsk);
+	stts();
+}
+
+static inline void __thread_fpu_begin(struct task_struct *tsk)
+{
+	clts();
+	__thread_set_has_fpu(tsk);
+}
+
+/*
+ * FPU state switching for scheduling.
+ *
+ * This is a two-stage process:
+ *
+ *  - switch_fpu_prepare() saves the old state and
+ *    sets the new state of the CR0.TS bit. This is
+ *    done within the context of the old process.
+ *
+ *  - switch_fpu_finish() restores the new state as
+ *    necessary.
+ */
+typedef struct { int preload; } fpu_switch_t;
+
+/*
+ * FIXME! We could do a totally lazy restore, but we need to
+ * add a per-cpu "this was the task that last touched the FPU
+ * on this CPU" variable, and the task needs to have a "I last
+ * touched the FPU on this CPU" and check them.
+ *
+ * We don't do that yet, so "fpu_lazy_restore()" always returns
+ * false, but some day..
+ */
+static inline int fpu_lazy_restore(struct task_struct *new, unsigned int cpu)
+{
+	return new == percpu_read_stable(fpu_owner_task) &&
+		cpu == new->thread.fpu.last_cpu;
+}
+
+static inline fpu_switch_t switch_fpu_prepare(struct task_struct *old, struct task_struct *new, int cpu)
+{
+	fpu_switch_t fpu;
+
+	fpu.preload = tsk_used_math(new) && new->fpu_counter > 5;
+	if (__thread_has_fpu(old)) {
+		if (!__save_init_fpu(old))
+			cpu = ~0;
+		old->thread.fpu.last_cpu = cpu;
+		old->thread.fpu.has_fpu = 0;	/* But leave fpu_owner_task! */
+
+		/* Don't change CR0.TS if we just switch! */
+		if (fpu.preload) {
+			new->fpu_counter++;
+			__thread_set_has_fpu(new);
+			prefetch(new->thread.fpu.state);
+		} else
+			stts();
+	} else {
+		old->fpu_counter = 0;
+		old->thread.fpu.last_cpu = ~0;
+		if (fpu.preload) {
+			new->fpu_counter++;
+			if (fpu_lazy_restore(new, cpu))
+				fpu.preload = 0;
+			else
+				prefetch(new->thread.fpu.state);
+			__thread_fpu_begin(new);
+		}
+	}
+	return fpu;
+}
+
+/*
+ * By the time this gets called, we've already cleared CR0.TS and
+ * given the process the FPU if we are going to preload the FPU
+ * state - all we need to do is to conditionally restore the register
+ * state itself.
+ */
+static inline void switch_fpu_finish(struct task_struct *new, fpu_switch_t fpu)
+{
+	if (fpu.preload) {
+		if (unlikely(restore_fpu_checking(new)))
+			__thread_fpu_end(new);
+	}
 }
 
+/*
+ * Signal frame handlers...
+ */
+extern int save_i387_xstate(void __user *buf);
+extern int restore_i387_xstate(void __user *buf);
+
 static inline void __clear_fpu(struct task_struct *tsk)
 {
-	if (task_thread_info(tsk)->status & TS_USEDFPU) {
+	if (__thread_has_fpu(tsk)) {
 		/* Ignore delayed exceptions from user space */
 		asm volatile("1: fwait\n"
 			     "2:\n"
 			     _ASM_EXTABLE(1b, 2b));
-		task_thread_info(tsk)->status &= ~TS_USEDFPU;
-		stts();
+		__thread_fpu_end(tsk);
 	}
 }
 
+/*
+ * Were we in an interrupt that interrupted kernel mode?
+ *
+ * We can do a kernel_fpu_begin/end() pair *ONLY* if that
+ * pair does nothing at all: the thread must not have fpu (so
+ * that we don't try to save the FPU state), and TS must
+ * be set (so that the clts/stts pair does nothing that is
+ * visible in the interrupted kernel thread).
+ */
+static inline bool interrupted_kernel_fpu_idle(void)
+{
+	return !__thread_has_fpu(current) &&
+		(read_cr0() & X86_CR0_TS);
+}
+
+/*
+ * Were we in user mode (or vm86 mode) when we were
+ * interrupted?
+ *
+ * Doing kernel_fpu_begin/end() is ok if we are running
+ * in an interrupt context from user mode - we'll just
+ * save the FPU state as required.
+ */
+static inline bool interrupted_user_mode(void)
+{
+	struct pt_regs *regs = get_irq_regs();
+	return regs && user_mode_vm(regs);
+}
+
+/*
+ * Can we use the FPU in kernel mode with the
+ * whole "kernel_fpu_begin/end()" sequence?
+ *
+ * It's always ok in process context (ie "not interrupt")
+ * but it is sometimes ok even from an irq.
+ */
+static inline bool irq_fpu_usable(void)
+{
+	return !in_interrupt() ||
+		interrupted_user_mode() ||
+		interrupted_kernel_fpu_idle();
+}
+
 static inline void kernel_fpu_begin(void)
 {
-	struct thread_info *me = current_thread_info();
+	struct task_struct *me = current;
+
+	WARN_ON_ONCE(!irq_fpu_usable());
 	preempt_disable();
-	if (me->status & TS_USEDFPU)
-		__save_init_fpu(me->task);
-	else
+	if (__thread_has_fpu(me)) {
+		__save_init_fpu(me);
+		__thread_clear_has_fpu(me);
+		/* We do 'stts()' in kernel_fpu_end() */
+	} else {
+		percpu_write(fpu_owner_task, NULL);
 		clts();
+	}
 }
 
 static inline void kernel_fpu_end(void)
@@ -323,14 +484,6 @@ static inline void kernel_fpu_end(void)
 	preempt_enable();
 }
 
-static inline bool irq_fpu_usable(void)
-{
-	struct pt_regs *regs;
-
-	return !in_interrupt() || !(regs = get_irq_regs()) || \
-		user_mode(regs) || (read_cr0() & X86_CR0_TS);
-}
-
 /*
  * Some instructions like VIA's padlock instructions generate a spurious
  * DNA fault but don't modify SSE registers. And these instructions
@@ -363,20 +516,64 @@ static inline void irq_ts_restore(int TS_state)
 }
 
 /*
+ * The question "does this thread have fpu access?"
+ * is slightly racy, since preemption could come in
+ * and revoke it immediately after the test.
+ *
+ * However, even in that very unlikely scenario,
+ * we can just assume we have FPU access - typically
+ * to save the FP state - we'll just take a #NM
+ * fault and get the FPU access back.
+ *
+ * The actual user_fpu_begin/end() functions
+ * need to be preemption-safe, though.
+ *
+ * NOTE! user_fpu_end() must be used only after you
+ * have saved the FP state, and user_fpu_begin() must
+ * be used only immediately before restoring it.
+ * These functions do not do any save/restore on
+ * their own.
+ */
+static inline int user_has_fpu(void)
+{
+	return __thread_has_fpu(current);
+}
+
+static inline void user_fpu_end(void)
+{
+	preempt_disable();
+	__thread_fpu_end(current);
+	preempt_enable();
+}
+
+static inline void user_fpu_begin(void)
+{
+	preempt_disable();
+	if (!user_has_fpu())
+		__thread_fpu_begin(current);
+	preempt_enable();
+}
+
+/*
  * These disable preemption on their own and are safe
  */
 static inline void save_init_fpu(struct task_struct *tsk)
 {
+	WARN_ON_ONCE(!__thread_has_fpu(tsk));
 	preempt_disable();
 	__save_init_fpu(tsk);
-	stts();
+	__thread_fpu_end(tsk);
 	preempt_enable();
 }
 
 static inline void unlazy_fpu(struct task_struct *tsk)
 {
 	preempt_disable();
-	__unlazy_fpu(tsk);
+	if (__thread_has_fpu(tsk)) {
+		__save_init_fpu(tsk);
+		__thread_fpu_end(tsk);
+	} else
+		tsk->fpu_counter = 0;
 	preempt_enable();
 }
 
diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h
index ab4092e3214..7b9cfc4878a 100644
--- a/arch/x86/include/asm/kvm_emulate.h
+++ b/arch/x86/include/asm/kvm_emulate.h
@@ -190,6 +190,9 @@ struct x86_emulate_ops {
 	int (*intercept)(struct x86_emulate_ctxt *ctxt,
 			 struct x86_instruction_info *info,
 			 enum x86_intercept_stage stage);
+
+	bool (*get_cpuid)(struct x86_emulate_ctxt *ctxt,
+			 u32 *eax, u32 *ebx, u32 *ecx, u32 *edx);
 };
 
 typedef u32 __attribute__((vector_size(16))) sse128_t;
@@ -298,6 +301,19 @@ struct x86_emulate_ctxt {
 #define X86EMUL_MODE_PROT     (X86EMUL_MODE_PROT16|X86EMUL_MODE_PROT32| \
 			       X86EMUL_MODE_PROT64)
 
+/* CPUID vendors */
+#define X86EMUL_CPUID_VENDOR_AuthenticAMD_ebx 0x68747541
+#define X86EMUL_CPUID_VENDOR_AuthenticAMD_ecx 0x444d4163
+#define X86EMUL_CPUID_VENDOR_AuthenticAMD_edx 0x69746e65
+
+#define X86EMUL_CPUID_VENDOR_AMDisbetterI_ebx 0x69444d41
+#define X86EMUL_CPUID_VENDOR_AMDisbetterI_ecx 0x21726574
+#define X86EMUL_CPUID_VENDOR_AMDisbetterI_edx 0x74656273
+
+#define X86EMUL_CPUID_VENDOR_GenuineIntel_ebx 0x756e6547
+#define X86EMUL_CPUID_VENDOR_GenuineIntel_ecx 0x6c65746e
+#define X86EMUL_CPUID_VENDOR_GenuineIntel_edx 0x49656e69
+
 enum x86_intercept_stage {
 	X86_ICTP_NONE = 0,   /* Allow zero-init to not match anything */
 	X86_ICPT_PRE_EXCEPT,
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index aa9088c2693..58545c97d07 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -374,6 +374,8 @@ union thread_xstate {
 };
 
 struct fpu {
+	unsigned int last_cpu;
+	unsigned int has_fpu;
 	union thread_xstate *state;
 };
 
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index bc817cd8b44..cfd8144d552 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -247,8 +247,6 @@ static inline struct thread_info *current_thread_info(void)
  * ever touches our thread-synchronous status, so we don't
  * have to worry about atomic accesses.
  */
-#define TS_USEDFPU		0x0001	/* FPU was used by this task
-					   this quantum (SMP) */
 #define TS_COMPAT		0x0002	/* 32bit syscall active (64BIT)*/
 #define TS_POLLING		0x0004	/* idle task polling need_resched,
 					   skip sending interrupt */
diff --git a/arch/x86/include/asm/unistd.h b/arch/x86/include/asm/unistd.h
index b4a3db7ce14..21f77b89e47 100644
--- a/arch/x86/include/asm/unistd.h
+++ b/arch/x86/include/asm/unistd.h
@@ -7,6 +7,7 @@
 #  include <asm/unistd_32.h>
 #  define __ARCH_WANT_IPC_PARSE_VERSION
 #  define __ARCH_WANT_STAT64
+#  define __ARCH_WANT_SYS_IPC
 #  define __ARCH_WANT_SYS_OLD_MMAP
 #  define __ARCH_WANT_SYS_OLD_SELECT
 
diff --git a/arch/x86/include/asm/uv/uv_bau.h b/arch/x86/include/asm/uv/uv_bau.h
index 8e862aaf0d9..becf47b8173 100644
--- a/arch/x86/include/asm/uv/uv_bau.h
+++ b/arch/x86/include/asm/uv/uv_bau.h
@@ -65,7 +65,7 @@
  * UV2: Bit 19 selects between
  *  (0): 10 microsecond timebase and
  *  (1): 80 microseconds
- *  we're using 655us, similar to UV1: 65 units of 10us
+ *  we're using 560us, similar to UV1: 65 units of 10us
  */
 #define UV1_INTD_SOFT_ACK_TIMEOUT_PERIOD (9UL)
 #define UV2_INTD_SOFT_ACK_TIMEOUT_PERIOD (15UL)
@@ -167,6 +167,7 @@
 #define FLUSH_RETRY_TIMEOUT		2
 #define FLUSH_GIVEUP			3
 #define FLUSH_COMPLETE			4
+#define FLUSH_RETRY_BUSYBUG		5
 
 /*
  * tuning the action when the numalink network is extremely delayed
@@ -235,10 +236,10 @@ struct bau_msg_payload {
 
 
 /*
- * Message header:  16 bytes (128 bits) (bytes 0x30-0x3f of descriptor)
+ * UV1 Message header:  16 bytes (128 bits) (bytes 0x30-0x3f of descriptor)
  * see table 4.2.3.0.1 in broacast_assist spec.
  */
-struct bau_msg_header {
+struct uv1_bau_msg_header {
 	unsigned int	dest_subnodeid:6;	/* must be 0x10, for the LB */
 	/* bits 5:0 */
 	unsigned int	base_dest_nasid:15;	/* nasid of the first bit */
@@ -318,19 +319,87 @@ struct bau_msg_header {
 };
 
 /*
+ * UV2 Message header:  16 bytes (128 bits) (bytes 0x30-0x3f of descriptor)
+ * see figure 9-2 of harp_sys.pdf
+ */
+struct uv2_bau_msg_header {
+	unsigned int	base_dest_nasid:15;	/* nasid of the first bit */
+	/* bits 14:0 */				/* in uvhub map */
+	unsigned int	dest_subnodeid:5;	/* must be 0x10, for the LB */
+	/* bits 19:15 */
+	unsigned int	rsvd_1:1;		/* must be zero */
+	/* bit 20 */
+	/* Address bits 59:21 */
+	/* bits 25:2 of address (44:21) are payload */
+	/* these next 24 bits become bytes 12-14 of msg */
+	/* bits 28:21 land in byte 12 */
+	unsigned int	replied_to:1;		/* sent as 0 by the source to
+						   byte 12 */
+	/* bit 21 */
+	unsigned int	msg_type:3;		/* software type of the
+						   message */
+	/* bits 24:22 */
+	unsigned int	canceled:1;		/* message canceled, resource
+						   is to be freed*/
+	/* bit 25 */
+	unsigned int	payload_1:3;		/* not currently used */
+	/* bits 28:26 */
+
+	/* bits 36:29 land in byte 13 */
+	unsigned int	payload_2a:3;		/* not currently used */
+	unsigned int	payload_2b:5;		/* not currently used */
+	/* bits 36:29 */
+
+	/* bits 44:37 land in byte 14 */
+	unsigned int	payload_3:8;		/* not currently used */
+	/* bits 44:37 */
+
+	unsigned int	rsvd_2:7;		/* reserved */
+	/* bits 51:45 */
+	unsigned int	swack_flag:1;		/* software acknowledge flag */
+	/* bit 52 */
+	unsigned int	rsvd_3a:3;		/* must be zero */
+	unsigned int	rsvd_3b:8;		/* must be zero */
+	unsigned int	rsvd_3c:8;		/* must be zero */
+	unsigned int	rsvd_3d:3;		/* must be zero */
+	/* bits 74:53 */
+	unsigned int	fairness:3;		/* usually zero */
+	/* bits 77:75 */
+
+	unsigned int	sequence:16;		/* message sequence number */
+	/* bits 93:78  Suppl_A  */
+	unsigned int	chaining:1;		/* next descriptor is part of
+						   this activation*/
+	/* bit 94 */
+	unsigned int	multilevel:1;		/* multi-level multicast
+						   format */
+	/* bit 95 */
+	unsigned int	rsvd_4:24;		/* ordered / source node /
+						   source subnode / aging
+						   must be zero */
+	/* bits 119:96 */
+	unsigned int	command:8;		/* message type */
+	/* bits 127:120 */
+};
+
+/*
  * The activation descriptor:
  * The format of the message to send, plus all accompanying control
  * Should be 64 bytes
  */
 struct bau_desc {
-	struct pnmask			distribution;
+	struct pnmask				distribution;
 	/*
 	 * message template, consisting of header and payload:
 	 */
-	struct bau_msg_header		header;
-	struct bau_msg_payload		payload;
+	union bau_msg_header {
+		struct uv1_bau_msg_header	uv1_hdr;
+		struct uv2_bau_msg_header	uv2_hdr;
+	} header;
+
+	struct bau_msg_payload			payload;
 };
-/*
+/* UV1:
  *   -payload--    ---------header------
  *   bytes 0-11    bits 41-56  bits 58-81
  *       A           B  (2)      C (3)
@@ -340,6 +409,16 @@ struct bau_desc {
  *   bytes 0-11  bytes 12-14  bytes 16-17  (byte 15 filled in by hw as vector)
  *   ------------payload queue-----------
  */
+/* UV2:
+ *   -payload--    ---------header------
+ *   bytes 0-11    bits 70-78  bits 21-44
+ *       A           B  (2)      C (3)
+ *
+ *            A/B/C are moved to:
+ *       A            C          B
+ *   bytes 0-11  bytes 12-14  bytes 16-17  (byte 15 filled in by hw as vector)
+ *   ------------payload queue-----------
+ */
 
 /*
  * The payload queue on the destination side is an array of these.
@@ -385,7 +464,6 @@ struct bau_pq_entry {
 struct msg_desc {
 	struct bau_pq_entry	*msg;
 	int			msg_slot;
-	int			swack_slot;
 	struct bau_pq_entry	*queue_first;
 	struct bau_pq_entry	*queue_last;
 };
@@ -405,6 +483,7 @@ struct ptc_stats {
 						   requests */
 	unsigned long	s_stimeout;		/* source side timeouts */
 	unsigned long	s_dtimeout;		/* destination side timeouts */
+	unsigned long	s_strongnacks;		/* number of strong nack's */
 	unsigned long	s_time;			/* time spent in sending side */
 	unsigned long	s_retriesok;		/* successful retries */
 	unsigned long	s_ntargcpu;		/* total number of cpu's
@@ -439,6 +518,9 @@ struct ptc_stats {
 	unsigned long	s_retry_messages;	/* retry broadcasts */
 	unsigned long	s_bau_reenabled;	/* for bau enable/disable */
 	unsigned long	s_bau_disabled;		/* for bau enable/disable */
+	unsigned long	s_uv2_wars;		/* uv2 workaround, perm. busy */
+	unsigned long	s_uv2_wars_hw;		/* uv2 workaround, hiwater */
+	unsigned long	s_uv2_war_waits;	/* uv2 workaround, long waits */
 	/* destination statistics */
 	unsigned long	d_alltlb;		/* times all tlb's on this
 						   cpu were flushed */
@@ -511,9 +593,12 @@ struct bau_control {
 	short			osnode;
 	short			uvhub_cpu;
 	short			uvhub;
+	short			uvhub_version;
 	short			cpus_in_socket;
 	short			cpus_in_uvhub;
 	short			partition_base_pnode;
+	short			using_desc; /* an index, like uvhub_cpu */
+	unsigned int		inuse_map;
 	unsigned short		message_number;
 	unsigned short		uvhub_quiesce;
 	short			socket_acknowledge_count[DEST_Q_SIZE];
@@ -531,6 +616,7 @@ struct bau_control {
 	int			cong_response_us;
 	int			cong_reps;
 	int			cong_period;
+	unsigned long		clocks_per_100_usec;
 	cycles_t		period_time;
 	long			period_requests;
 	struct hub_and_pnode	*thp;
@@ -591,6 +677,11 @@ static inline void write_mmr_sw_ack(unsigned long mr)
 	uv_write_local_mmr(UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_ALIAS, mr);
 }
 
+static inline void write_gmmr_sw_ack(int pnode, unsigned long mr)
+{
+	write_gmmr(pnode, UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_ALIAS, mr);
+}
+
 static inline unsigned long read_mmr_sw_ack(void)
 {
 	return read_lmmr(UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE);
diff --git a/arch/x86/include/asm/uv/uv_hub.h b/arch/x86/include/asm/uv/uv_hub.h
index 54a13aaebc4..21f7385badb 100644
--- a/arch/x86/include/asm/uv/uv_hub.h
+++ b/arch/x86/include/asm/uv/uv_hub.h
@@ -318,13 +318,13 @@ uv_gpa_in_mmr_space(unsigned long gpa)
 /* UV global physical address --> socket phys RAM */
 static inline unsigned long uv_gpa_to_soc_phys_ram(unsigned long gpa)
 {
-	unsigned long paddr = gpa & uv_hub_info->gpa_mask;
+	unsigned long paddr;
 	unsigned long remap_base = uv_hub_info->lowmem_remap_base;
 	unsigned long remap_top =  uv_hub_info->lowmem_remap_top;
 
 	gpa = ((gpa << uv_hub_info->m_shift) >> uv_hub_info->m_shift) |
 		((gpa >> uv_hub_info->n_lshift) << uv_hub_info->m_val);
-	gpa = gpa & uv_hub_info->gpa_mask;
+	paddr = gpa & uv_hub_info->gpa_mask;
 	if (paddr >= remap_base && paddr < remap_base + remap_top)
 		paddr -= remap_base;
 	return paddr;