Merge branch 'perf/urgent' into perf/core

Merge reason: queue up dependent patch, update to -rc4

Signed-off-by: Ingo Molnar <mingo@elte.hu>

11 files changed, 103 insertions, 48 deletions

diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h
index 60d2b2db0bc5..56f462cf22d2 100644
--- a/arch/x86/include/asm/acpi.h
+++ b/arch/x86/include/asm/acpi.h
@@ -142,6 +142,32 @@ static inline unsigned int acpi_processor_cstate_check(unsigned int max_cstate)
 		return max_cstate;
 }
 
+static inline bool arch_has_acpi_pdc(void)
+{
+	struct cpuinfo_x86 *c = &cpu_data(0);
+	return (c->x86_vendor == X86_VENDOR_INTEL ||
+		c->x86_vendor == X86_VENDOR_CENTAUR);
+}
+
+static inline void arch_acpi_set_pdc_bits(u32 *buf)
+{
+	struct cpuinfo_x86 *c = &cpu_data(0);
+
+	buf[2] |= ACPI_PDC_C_CAPABILITY_SMP;
+
+	if (cpu_has(c, X86_FEATURE_EST))
+		buf[2] |= ACPI_PDC_EST_CAPABILITY_SWSMP;
+
+	if (cpu_has(c, X86_FEATURE_ACPI))
+		buf[2] |= ACPI_PDC_T_FFH;
+
+	/*
+	 * If mwait/monitor is unsupported, C2/C3_FFH will be disabled
+	 */
+	if (!cpu_has(c, X86_FEATURE_MWAIT))
+		buf[2] &= ~(ACPI_PDC_C_C2C3_FFH);
+}
+
 #else /* !CONFIG_ACPI */
 
 #define acpi_lapic 0
diff --git a/arch/x86/include/asm/asm-offsets.h b/arch/x86/include/asm/asm-offsets.h
new file mode 100644
index 000000000000..d370ee36a182
--- /dev/null
+++ b/arch/x86/include/asm/asm-offsets.h
@@ -0,0 +1 @@
+#include <generated/asm-offsets.h>
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index 613700f27a4a..637e1ec963c3 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -153,6 +153,7 @@
 #define X86_FEATURE_SSE5	(6*32+11) /* SSE-5 */
 #define X86_FEATURE_SKINIT	(6*32+12) /* SKINIT/STGI instructions */
 #define X86_FEATURE_WDT		(6*32+13) /* Watchdog timer */
+#define X86_FEATURE_NODEID_MSR	(6*32+19) /* NodeId MSR */
 
 /*
  * Auxiliary flags: Linux defined - For features scattered in various
diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h
index 08c48a81841f..eeac829a0f44 100644
--- a/arch/x86/include/asm/hw_irq.h
+++ b/arch/x86/include/asm/hw_irq.h
@@ -103,7 +103,8 @@ extern int assign_irq_vector(int, struct irq_cfg *, const struct cpumask *);
 extern void send_cleanup_vector(struct irq_cfg *);
 
 struct irq_desc;
-extern unsigned int set_desc_affinity(struct irq_desc *, const struct cpumask *);
+extern unsigned int set_desc_affinity(struct irq_desc *, const struct cpumask *,
+				      unsigned int *dest_id);
 extern int IO_APIC_get_PCI_irq_vector(int bus, int devfn, int pin, struct io_apic_irq_attr *irq_attr);
 extern void setup_ioapic_dest(void);
 
diff --git a/arch/x86/include/asm/kvm.h b/arch/x86/include/asm/kvm.h
index 950df434763f..f46b79f6c16c 100644
--- a/arch/x86/include/asm/kvm.h
+++ b/arch/x86/include/asm/kvm.h
@@ -254,6 +254,10 @@ struct kvm_reinject_control {
 	__u8 reserved[31];
 };
 
+/* When set in flags, include corresponding fields on KVM_SET_VCPU_EVENTS */
+#define KVM_VCPUEVENT_VALID_NMI_PENDING	0x00000001
+#define KVM_VCPUEVENT_VALID_SIPI_VECTOR	0x00000002
+
 /* for KVM_GET/SET_VCPU_EVENTS */
 struct kvm_vcpu_events {
 	struct {
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 4ffe09b2ad75..1cd58cdbc03f 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -12,6 +12,7 @@
 #define MSR_FS_BASE		0xc0000100 /* 64bit FS base */
 #define MSR_GS_BASE		0xc0000101 /* 64bit GS base */
 #define MSR_KERNEL_GS_BASE	0xc0000102 /* SwapGS GS shadow */
+#define MSR_TSC_AUX		0xc0000103 /* Auxiliary TSC */
 
 /* EFER bits: */
 #define _EFER_SCE		0  /* SYSCALL/SYSRET */
@@ -123,6 +124,7 @@
 #define FAM10H_MMIO_CONF_BUSRANGE_SHIFT 2
 #define FAM10H_MMIO_CONF_BASE_MASK	0xfffffff
 #define FAM10H_MMIO_CONF_BASE_SHIFT	20
+#define MSR_FAM10H_NODE_ID		0xc001100c
 
 /* K8 MSRs */
 #define MSR_K8_TOP_MEM1			0xc001001a
diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h
index 2d228fc9b4b7..c5bc4c2d33f5 100644
--- a/arch/x86/include/asm/msr.h
+++ b/arch/x86/include/asm/msr.h
@@ -27,6 +27,18 @@ struct msr {
 	};
 };
 
+struct msr_info {
+	u32 msr_no;
+	struct msr reg;
+	struct msr *msrs;
+	int err;
+};
+
+struct msr_regs_info {
+	u32 *regs;
+	int err;
+};
+
 static inline unsigned long long native_read_tscp(unsigned int *aux)
 {
 	unsigned long low, high;
@@ -240,9 +252,9 @@ do {                                                            \
 #define checking_wrmsrl(msr, val) wrmsr_safe((msr), (u32)(val),		\
 					     (u32)((val) >> 32))
 
-#define write_tsc(val1, val2) wrmsr(0x10, (val1), (val2))
+#define write_tsc(val1, val2) wrmsr(MSR_IA32_TSC, (val1), (val2))
 
-#define write_rdtscp_aux(val) wrmsr(0xc0000103, (val), 0)
+#define write_rdtscp_aux(val) wrmsr(MSR_TSC_AUX, (val), 0)
 
 struct msr *msrs_alloc(void);
 void msrs_free(struct msr *msrs);
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 6f8ec1c37e0a..fc801bab1b3b 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -181,7 +181,7 @@ static inline void native_cpuid(unsigned int *eax, unsigned int *ebx,
 				unsigned int *ecx, unsigned int *edx)
 {
 	/* ecx is often an input as well as an output. */
-	asm("cpuid"
+	asm volatile("cpuid"
 	    : "=a" (*eax),
 	      "=b" (*ebx),
 	      "=c" (*ecx),
diff --git a/arch/x86/include/asm/uaccess_32.h b/arch/x86/include/asm/uaccess_32.h
index 0c9825e97f36..088d09fb1615 100644
--- a/arch/x86/include/asm/uaccess_32.h
+++ b/arch/x86/include/asm/uaccess_32.h
@@ -205,14 +205,13 @@ static inline unsigned long __must_check copy_from_user(void *to,
 					  unsigned long n)
 {
 	int sz = __compiletime_object_size(to);
-	int ret = -EFAULT;
 
 	if (likely(sz == -1 || sz >= n))
-		ret = _copy_from_user(to, from, n);
+		n = _copy_from_user(to, from, n);
 	else
 		copy_from_user_overflow();
 
-	return ret;
+	return n;
 }
 
 long __must_check strncpy_from_user(char *dst, const char __user *src,
diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h
index 46324c6a4f6e..535e421498f6 100644
--- a/arch/x86/include/asm/uaccess_64.h
+++ b/arch/x86/include/asm/uaccess_64.h
@@ -30,16 +30,15 @@ static inline unsigned long __must_check copy_from_user(void *to,
 					  unsigned long n)
 {
 	int sz = __compiletime_object_size(to);
-	int ret = -EFAULT;
 
 	might_fault();
 	if (likely(sz == -1 || sz >= n))
-		ret = _copy_from_user(to, from, n);
+		n = _copy_from_user(to, from, n);
 #ifdef CONFIG_DEBUG_VM
 	else
 		WARN(1, "Buffer overflow detected!\n");
 #endif
-	return ret;
+	return n;
 }
 
 static __always_inline __must_check
diff --git a/arch/x86/include/asm/uv/uv_hub.h b/arch/x86/include/asm/uv/uv_hub.h
index 811bfabc80b7..bc54fa965af3 100644
--- a/arch/x86/include/asm/uv/uv_hub.h
+++ b/arch/x86/include/asm/uv/uv_hub.h
@@ -31,20 +31,20 @@
  *		  contiguous (although various IO spaces may punch holes in
  *		  it)..
  *
- * 	N	- Number of bits in the node portion of a socket physical
- * 		  address.
+ *	N	- Number of bits in the node portion of a socket physical
+ *		  address.
  *
- * 	NASID   - network ID of a router, Mbrick or Cbrick. Nasid values of
- * 	 	  routers always have low bit of 1, C/MBricks have low bit
- * 		  equal to 0. Most addressing macros that target UV hub chips
- * 		  right shift the NASID by 1 to exclude the always-zero bit.
- * 		  NASIDs contain up to 15 bits.
+ *	NASID   - network ID of a router, Mbrick or Cbrick. Nasid values of
+ *		  routers always have low bit of 1, C/MBricks have low bit
+ *		  equal to 0. Most addressing macros that target UV hub chips
+ *		  right shift the NASID by 1 to exclude the always-zero bit.
+ *		  NASIDs contain up to 15 bits.
  *
  *	GNODE   - NASID right shifted by 1 bit. Most mmrs contain gnodes instead
  *		  of nasids.
  *
- * 	PNODE   - the low N bits of the GNODE. The PNODE is the most useful variant
- * 		  of the nasid for socket usage.
+ *	PNODE   - the low N bits of the GNODE. The PNODE is the most useful variant
+ *		  of the nasid for socket usage.
  *
  *
  *  NumaLink Global Physical Address Format:
@@ -71,12 +71,12 @@
  *
  *
  * APICID format
- * 	NOTE!!!!!! This is the current format of the APICID. However, code
- * 	should assume that this will change in the future. Use functions
- * 	in this file for all APICID bit manipulations and conversion.
+ *	NOTE!!!!!! This is the current format of the APICID. However, code
+ *	should assume that this will change in the future. Use functions
+ *	in this file for all APICID bit manipulations and conversion.
  *
- * 		1111110000000000
- * 		5432109876543210
+ *		1111110000000000
+ *		5432109876543210
  *		pppppppppplc0cch
  *		sssssssssss
  *
@@ -89,9 +89,9 @@
  *	Note: Processor only supports 12 bits in the APICID register. The ACPI
  *	      tables hold all 16 bits. Software needs to be aware of this.
  *
- * 	      Unless otherwise specified, all references to APICID refer to
- * 	      the FULL value contained in ACPI tables, not the subset in the
- * 	      processor APICID register.
+ *	      Unless otherwise specified, all references to APICID refer to
+ *	      the FULL value contained in ACPI tables, not the subset in the
+ *	      processor APICID register.
  */
 
 
@@ -151,16 +151,16 @@ struct uv_hub_info_s {
 };
 
 DECLARE_PER_CPU(struct uv_hub_info_s, __uv_hub_info);
-#define uv_hub_info 		(&__get_cpu_var(__uv_hub_info))
+#define uv_hub_info		(&__get_cpu_var(__uv_hub_info))
 #define uv_cpu_hub_info(cpu)	(&per_cpu(__uv_hub_info, cpu))
 
 /*
  * Local & Global MMR space macros.
- * 	Note: macros are intended to be used ONLY by inline functions
- * 	in this file - not by other kernel code.
- * 		n -  NASID (full 15-bit global nasid)
- * 		g -  GNODE (full 15-bit global nasid, right shifted 1)
- * 		p -  PNODE (local part of nsids, right shifted 1)
+ *	Note: macros are intended to be used ONLY by inline functions
+ *	in this file - not by other kernel code.
+ *		n -  NASID (full 15-bit global nasid)
+ *		g -  GNODE (full 15-bit global nasid, right shifted 1)
+ *		p -  PNODE (local part of nsids, right shifted 1)
  */
 #define UV_NASID_TO_PNODE(n)		(((n) >> 1) & uv_hub_info->pnode_mask)
 #define UV_PNODE_TO_GNODE(p)		((p) |uv_hub_info->gnode_extra)
@@ -215,8 +215,8 @@ DECLARE_PER_CPU(struct uv_hub_info_s, __uv_hub_info);
 /*
  * Macros for converting between kernel virtual addresses, socket local physical
  * addresses, and UV global physical addresses.
- * 	Note: use the standard __pa() & __va() macros for converting
- * 	      between socket virtual and socket physical addresses.
+ *	Note: use the standard __pa() & __va() macros for converting
+ *	      between socket virtual and socket physical addresses.
  */
 
 /* socket phys RAM --> UV global physical address */
@@ -287,21 +287,18 @@ static inline int uv_apicid_to_pnode(int apicid)
  * Access global MMRs using the low memory MMR32 space. This region supports
  * faster MMR access but not all MMRs are accessible in this space.
  */
-static inline unsigned long *uv_global_mmr32_address(int pnode,
-				unsigned long offset)
+static inline unsigned long *uv_global_mmr32_address(int pnode, unsigned long offset)
 {
 	return __va(UV_GLOBAL_MMR32_BASE |
 		       UV_GLOBAL_MMR32_PNODE_BITS(pnode) | offset);
 }
 
-static inline void uv_write_global_mmr32(int pnode, unsigned long offset,
-				 unsigned long val)
+static inline void uv_write_global_mmr32(int pnode, unsigned long offset, unsigned long val)
 {
 	writeq(val, uv_global_mmr32_address(pnode, offset));
 }
 
-static inline unsigned long uv_read_global_mmr32(int pnode,
-						 unsigned long offset)
+static inline unsigned long uv_read_global_mmr32(int pnode, unsigned long offset)
 {
 	return readq(uv_global_mmr32_address(pnode, offset));
 }
@@ -310,21 +307,18 @@ static inline unsigned long uv_read_global_mmr32(int pnode,
  * Access Global MMR space using the MMR space located at the top of physical
  * memory.
  */
-static inline unsigned long *uv_global_mmr64_address(int pnode,
-				unsigned long offset)
+static inline unsigned long *uv_global_mmr64_address(int pnode, unsigned long offset)
 {
 	return __va(UV_GLOBAL_MMR64_BASE |
 		    UV_GLOBAL_MMR64_PNODE_BITS(pnode) | offset);
 }
 
-static inline void uv_write_global_mmr64(int pnode, unsigned long offset,
-				unsigned long val)
+static inline void uv_write_global_mmr64(int pnode, unsigned long offset, unsigned long val)
 {
 	writeq(val, uv_global_mmr64_address(pnode, offset));
 }
 
-static inline unsigned long uv_read_global_mmr64(int pnode,
-						 unsigned long offset)
+static inline unsigned long uv_read_global_mmr64(int pnode, unsigned long offset)
 {
 	return readq(uv_global_mmr64_address(pnode, offset));
 }
@@ -338,6 +332,16 @@ static inline unsigned long uv_global_gru_mmr_address(int pnode, unsigned long o
 	return UV_GLOBAL_GRU_MMR_BASE | offset | (pnode << uv_hub_info->m_val);
 }
 
+static inline void uv_write_global_mmr8(int pnode, unsigned long offset, unsigned char val)
+{
+	writeb(val, uv_global_mmr64_address(pnode, offset));
+}
+
+static inline unsigned char uv_read_global_mmr8(int pnode, unsigned long offset)
+{
+	return readb(uv_global_mmr64_address(pnode, offset));
+}
+
 /*
  * Access hub local MMRs. Faster than using global space but only local MMRs
  * are accessible.
@@ -457,11 +461,17 @@ static inline void uv_set_scir_bits(unsigned char value)
 	}
 }
 
+static inline unsigned long uv_scir_offset(int apicid)
+{
+	return SCIR_LOCAL_MMR_BASE | (apicid & 0x3f);
+}
+
 static inline void uv_set_cpu_scir_bits(int cpu, unsigned char value)
 {
 	if (uv_cpu_hub_info(cpu)->scir.state != value) {
+		uv_write_global_mmr8(uv_cpu_to_pnode(cpu),
+				uv_cpu_hub_info(cpu)->scir.offset, value);
 		uv_cpu_hub_info(cpu)->scir.state = value;
-		uv_write_local_mmr8(uv_cpu_hub_info(cpu)->scir.offset, value);
 	}
 }