Merge branch 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 fixes from Thomas Gleixner:
 "This lot contains:

   - Some fixups for the fallout of the topology consolidation which
     unearthed AMD/Intel inconsistencies
   - Documentation for the x86 topology management
   - Support for AMD advanced power management bits
   - Two simple cleanups removing duplicated code"

* 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/cpu: Add advanced power management bits
  x86/thread_info: Merge two !__ASSEMBLY__ sections
  x86/cpufreq: Remove duplicated TDP MSR macro definitions
  x86/Documentation: Start documenting x86 topology
  x86/cpu: Get rid of compute_unit_id
  perf/x86/amd: Cleanup Fam10h NB event constraints
  x86/topology: Fix AMD core count

12 files changed, 246 insertions, 30 deletions

diff --git a/Documentation/x86/topology.txt b/Documentation/x86/topology.txt
new file mode 100644
index 000000000000..06afac252f5b
--- /dev/null
+++ b/Documentation/x86/topology.txt
@@ -0,0 +1,208 @@
+x86 Topology
+============
+
+This documents and clarifies the main aspects of x86 topology modelling and
+representation in the kernel. Update/change when doing changes to the
+respective code.
+
+The architecture-agnostic topology definitions are in
+Documentation/cputopology.txt. This file holds x86-specific
+differences/specialities which must not necessarily apply to the generic
+definitions. Thus, the way to read up on Linux topology on x86 is to start
+with the generic one and look at this one in parallel for the x86 specifics.
+
+Needless to say, code should use the generic functions - this file is *only*
+here to *document* the inner workings of x86 topology.
+
+Started by Thomas Gleixner <tglx@linutronix.de> and Borislav Petkov <bp@alien8.de>.
+
+The main aim of the topology facilities is to present adequate interfaces to
+code which needs to know/query/use the structure of the running system wrt
+threads, cores, packages, etc.
+
+The kernel does not care about the concept of physical sockets because a
+socket has no relevance to software. It's an electromechanical component. In
+the past a socket always contained a single package (see below), but with the
+advent of Multi Chip Modules (MCM) a socket can hold more than one package. So
+there might be still references to sockets in the code, but they are of
+historical nature and should be cleaned up.
+
+The topology of a system is described in the units of:
+
+    - packages
+    - cores
+    - threads
+
+* Package:
+
+  Packages contain a number of cores plus shared resources, e.g. DRAM
+  controller, shared caches etc.
+
+  AMD nomenclature for package is 'Node'.
+
+  Package-related topology information in the kernel:
+
+  - cpuinfo_x86.x86_max_cores:
+
+    The number of cores in a package. This information is retrieved via CPUID.
+
+  - cpuinfo_x86.phys_proc_id:
+
+    The physical ID of the package. This information is retrieved via CPUID
+    and deduced from the APIC IDs of the cores in the package.
+
+  - cpuinfo_x86.logical_id:
+
+    The logical ID of the package. As we do not trust BIOSes to enumerate the
+    packages in a consistent way, we introduced the concept of logical package
+    ID so we can sanely calculate the number of maximum possible packages in
+    the system and have the packages enumerated linearly.
+
+  - topology_max_packages():
+
+    The maximum possible number of packages in the system. Helpful for per
+    package facilities to preallocate per package information.
+
+
+* Cores:
+
+  A core consists of 1 or more threads. It does not matter whether the threads
+  are SMT- or CMT-type threads.
+
+  AMDs nomenclature for a CMT core is "Compute Unit". The kernel always uses
+  "core".
+
+  Core-related topology information in the kernel:
+
+  - smp_num_siblings:
+
+    The number of threads in a core. The number of threads in a package can be
+    calculated by:
+
+	threads_per_package = cpuinfo_x86.x86_max_cores * smp_num_siblings
+
+
+* Threads:
+
+  A thread is a single scheduling unit. It's the equivalent to a logical Linux
+  CPU.
+
+  AMDs nomenclature for CMT threads is "Compute Unit Core". The kernel always
+  uses "thread".
+
+  Thread-related topology information in the kernel:
+
+  - topology_core_cpumask():
+
+    The cpumask contains all online threads in the package to which a thread
+    belongs.
+
+    The number of online threads is also printed in /proc/cpuinfo "siblings."
+
+  - topology_sibling_mask():
+
+    The cpumask contains all online threads in the core to which a thread
+    belongs.
+
+   - topology_logical_package_id():
+
+    The logical package ID to which a thread belongs.
+
+   - topology_physical_package_id():
+
+    The physical package ID to which a thread belongs.
+
+   - topology_core_id();
+
+    The ID of the core to which a thread belongs. It is also printed in /proc/cpuinfo
+    "core_id."
+
+
+
+System topology examples
+
+Note:
+
+The alternative Linux CPU enumeration depends on how the BIOS enumerates the
+threads. Many BIOSes enumerate all threads 0 first and then all threads 1.
+That has the "advantage" that the logical Linux CPU numbers of threads 0 stay
+the same whether threads are enabled or not. That's merely an implementation
+detail and has no practical impact.
+
+1) Single Package, Single Core
+
+   [package 0] -> [core 0] -> [thread 0] -> Linux CPU 0
+
+2) Single Package, Dual Core
+
+   a) One thread per core
+
+	[package 0] -> [core 0] -> [thread 0] -> Linux CPU 0
+		    -> [core 1] -> [thread 0] -> Linux CPU 1
+
+   b) Two threads per core
+
+	[package 0] -> [core 0] -> [thread 0] -> Linux CPU 0
+				-> [thread 1] -> Linux CPU 1
+		    -> [core 1] -> [thread 0] -> Linux CPU 2
+				-> [thread 1] -> Linux CPU 3
+
+      Alternative enumeration:
+
+	[package 0] -> [core 0] -> [thread 0] -> Linux CPU 0
+				-> [thread 1] -> Linux CPU 2
+		    -> [core 1] -> [thread 0] -> Linux CPU 1
+				-> [thread 1] -> Linux CPU 3
+
+      AMD nomenclature for CMT systems:
+
+	[node 0] -> [Compute Unit 0] -> [Compute Unit Core 0] -> Linux CPU 0
+				     -> [Compute Unit Core 1] -> Linux CPU 1
+		 -> [Compute Unit 1] -> [Compute Unit Core 0] -> Linux CPU 2
+				     -> [Compute Unit Core 1] -> Linux CPU 3
+
+4) Dual Package, Dual Core
+
+   a) One thread per core
+
+	[package 0] -> [core 0] -> [thread 0] -> Linux CPU 0
+		    -> [core 1] -> [thread 0] -> Linux CPU 1
+
+	[package 1] -> [core 0] -> [thread 0] -> Linux CPU 2
+		    -> [core 1] -> [thread 0] -> Linux CPU 3
+
+   b) Two threads per core
+
+	[package 0] -> [core 0] -> [thread 0] -> Linux CPU 0
+				-> [thread 1] -> Linux CPU 1
+		    -> [core 1] -> [thread 0] -> Linux CPU 2
+				-> [thread 1] -> Linux CPU 3
+
+	[package 1] -> [core 0] -> [thread 0] -> Linux CPU 4
+				-> [thread 1] -> Linux CPU 5
+		    -> [core 1] -> [thread 0] -> Linux CPU 6
+				-> [thread 1] -> Linux CPU 7
+
+      Alternative enumeration:
+
+	[package 0] -> [core 0] -> [thread 0] -> Linux CPU 0
+				-> [thread 1] -> Linux CPU 4
+		    -> [core 1] -> [thread 0] -> Linux CPU 1
+				-> [thread 1] -> Linux CPU 5
+
+	[package 1] -> [core 0] -> [thread 0] -> Linux CPU 2
+				-> [thread 1] -> Linux CPU 6
+		    -> [core 1] -> [thread 0] -> Linux CPU 3
+				-> [thread 1] -> Linux CPU 7
+
+      AMD nomenclature for CMT systems:
+
+	[node 0] -> [Compute Unit 0] -> [Compute Unit Core 0] -> Linux CPU 0
+				     -> [Compute Unit Core 1] -> Linux CPU 1
+		 -> [Compute Unit 1] -> [Compute Unit Core 0] -> Linux CPU 2
+				     -> [Compute Unit Core 1] -> Linux CPU 3
+
+	[node 1] -> [Compute Unit 0] -> [Compute Unit Core 0] -> Linux CPU 4
+				     -> [Compute Unit Core 1] -> Linux CPU 5
+		 -> [Compute Unit 1] -> [Compute Unit Core 0] -> Linux CPU 6
+				     -> [Compute Unit Core 1] -> Linux CPU 7
diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c
index 049ada8d4e9c..86a9bec18dab 100644
--- a/arch/x86/events/amd/core.c
+++ b/arch/x86/events/amd/core.c
@@ -369,7 +369,7 @@ static int amd_pmu_cpu_prepare(int cpu)
 
 	WARN_ON_ONCE(cpuc->amd_nb);
 
-	if (boot_cpu_data.x86_max_cores < 2)
+	if (!x86_pmu.amd_nb_constraints)
 		return NOTIFY_OK;
 
 	cpuc->amd_nb = amd_alloc_nb(cpu);
@@ -388,7 +388,7 @@ static void amd_pmu_cpu_starting(int cpu)
 
 	cpuc->perf_ctr_virt_mask = AMD64_EVENTSEL_HOSTONLY;
 
-	if (boot_cpu_data.x86_max_cores < 2)
+	if (!x86_pmu.amd_nb_constraints)
 		return;
 
 	nb_id = amd_get_nb_id(cpu);
@@ -414,7 +414,7 @@ static void amd_pmu_cpu_dead(int cpu)
 {
 	struct cpu_hw_events *cpuhw;
 
-	if (boot_cpu_data.x86_max_cores < 2)
+	if (!x86_pmu.amd_nb_constraints)
 		return;
 
 	cpuhw = &per_cpu(cpu_hw_events, cpu);
@@ -648,6 +648,8 @@ static __initconst const struct x86_pmu amd_pmu = {
 	.cpu_prepare		= amd_pmu_cpu_prepare,
 	.cpu_starting		= amd_pmu_cpu_starting,
 	.cpu_dead		= amd_pmu_cpu_dead,
+
+	.amd_nb_constraints	= 1,
 };
 
 static int __init amd_core_pmu_init(void)
@@ -674,6 +676,11 @@ static int __init amd_core_pmu_init(void)
 	x86_pmu.eventsel	= MSR_F15H_PERF_CTL;
 	x86_pmu.perfctr		= MSR_F15H_PERF_CTR;
 	x86_pmu.num_counters	= AMD64_NUM_COUNTERS_CORE;
+	/*
+	 * AMD Core perfctr has separate MSRs for the NB events, see
+	 * the amd/uncore.c driver.
+	 */
+	x86_pmu.amd_nb_constraints = 0;
 
 	pr_cont("core perfctr, ");
 	return 0;
@@ -693,6 +700,14 @@ __init int amd_pmu_init(void)
 	if (ret)
 		return ret;
 
+	if (num_possible_cpus() == 1) {
+		/*
+		 * No point in allocating data structures to serialize
+		 * against other CPUs, when there is only the one CPU.
+		 */
+		x86_pmu.amd_nb_constraints = 0;
+	}
+
 	/* Events are common for all AMDs */
 	memcpy(hw_cache_event_ids, amd_hw_cache_event_ids,
 	       sizeof(hw_cache_event_ids));
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index ba6ef18528c9..716d0482f5db 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -608,6 +608,11 @@ struct x86_pmu {
 	atomic_t	lbr_exclusive[x86_lbr_exclusive_max];
 
 	/*
+	 * AMD bits
+	 */
+	unsigned int	amd_nb_constraints : 1;
+
+	/*
 	 * Extra registers for events
 	 */
 	struct extra_reg *extra_regs;
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 2da46ac16e37..426e946ed0c0 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -190,6 +190,7 @@
 #define MSR_PP1_ENERGY_STATUS		0x00000641
 #define MSR_PP1_POLICY			0x00000642
 
+/* Config TDP MSRs */
 #define MSR_CONFIG_TDP_NOMINAL		0x00000648
 #define MSR_CONFIG_TDP_LEVEL_1		0x00000649
 #define MSR_CONFIG_TDP_LEVEL_2		0x0000064A
@@ -210,13 +211,6 @@
 #define MSR_GFX_PERF_LIMIT_REASONS	0x000006B0
 #define MSR_RING_PERF_LIMIT_REASONS	0x000006B1
 
-/* Config TDP MSRs */
-#define MSR_CONFIG_TDP_NOMINAL		0x00000648
-#define MSR_CONFIG_TDP_LEVEL1		0x00000649
-#define MSR_CONFIG_TDP_LEVEL2		0x0000064A
-#define MSR_CONFIG_TDP_CONTROL		0x0000064B
-#define MSR_TURBO_ACTIVATION_RATIO	0x0000064C
-
 /* Hardware P state interface */
 #define MSR_PPERF			0x0000064e
 #define MSR_PERF_LIMIT_REASONS		0x0000064f
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 983738ac014c..9264476f3d57 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -132,8 +132,6 @@ struct cpuinfo_x86 {
 	u16			logical_proc_id;
 	/* Core id: */
 	u16			cpu_core_id;
-	/* Compute unit id */
-	u8			compute_unit_id;
 	/* Index into per_cpu list: */
 	u16			cpu_index;
 	u32			microcode;
diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index 20a3de5cb3b0..66b057306f40 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -155,6 +155,7 @@ static inline int wbinvd_on_all_cpus(void)
 	wbinvd();
 	return 0;
 }
+#define smp_num_siblings	1
 #endif /* CONFIG_SMP */
 
 extern unsigned disabled_cpus;
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index 82866697fcf1..ffae84df8a93 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -276,11 +276,9 @@ static inline bool is_ia32_task(void)
  */
 #define force_iret() set_thread_flag(TIF_NOTIFY_RESUME)
 
-#endif	/* !__ASSEMBLY__ */
-
-#ifndef __ASSEMBLY__
 extern void arch_task_cache_init(void);
 extern int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src);
 extern void arch_release_task_struct(struct task_struct *tsk);
-#endif
+#endif	/* !__ASSEMBLY__ */
+
 #endif /* _ASM_X86_THREAD_INFO_H */
diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c
index 29fa475ec518..a147e676fc7b 100644
--- a/arch/x86/kernel/amd_nb.c
+++ b/arch/x86/kernel/amd_nb.c
@@ -170,15 +170,13 @@ int amd_get_subcaches(int cpu)
 {
 	struct pci_dev *link = node_to_amd_nb(amd_get_nb_id(cpu))->link;
 	unsigned int mask;
-	int cuid;
 
 	if (!amd_nb_has_feature(AMD_NB_L3_PARTITIONING))
 		return 0;
 
 	pci_read_config_dword(link, 0x1d4, &mask);
 
-	cuid = cpu_data(cpu).compute_unit_id;
-	return (mask >> (4 * cuid)) & 0xf;
+	return (mask >> (4 * cpu_data(cpu).cpu_core_id)) & 0xf;
 }
 
 int amd_set_subcaches(int cpu, unsigned long mask)
@@ -204,7 +202,7 @@ int amd_set_subcaches(int cpu, unsigned long mask)
 		pci_write_config_dword(nb->misc, 0x1b8, reg & ~0x180000);
 	}
 
-	cuid = cpu_data(cpu).compute_unit_id;
+	cuid = cpu_data(cpu).cpu_core_id;
 	mask <<= 4 * cuid;
 	mask |= (0xf ^ (1 << cuid)) << 26;
 
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 6e47e3a916f1..7b76eb67a9b3 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -300,7 +300,6 @@ static int nearby_node(int apicid)
 #ifdef CONFIG_SMP
 static void amd_get_topology(struct cpuinfo_x86 *c)
 {
-	u32 cores_per_cu = 1;
 	u8 node_id;
 	int cpu = smp_processor_id();
 
@@ -313,8 +312,8 @@ static void amd_get_topology(struct cpuinfo_x86 *c)
 
 		/* get compute unit information */
 		smp_num_siblings = ((ebx >> 8) & 3) + 1;
-		c->compute_unit_id = ebx & 0xff;
-		cores_per_cu += ((ebx >> 8) & 3);
+		c->x86_max_cores /= smp_num_siblings;
+		c->cpu_core_id = ebx & 0xff;
 	} else if (cpu_has(c, X86_FEATURE_NODEID_MSR)) {
 		u64 value;
 
@@ -325,19 +324,16 @@ static void amd_get_topology(struct cpuinfo_x86 *c)
 
 	/* fixup multi-node processor information */
 	if (nodes_per_socket > 1) {
-		u32 cores_per_node;
 		u32 cus_per_node;
 
 		set_cpu_cap(c, X86_FEATURE_AMD_DCM);
-		cores_per_node = c->x86_max_cores / nodes_per_socket;
-		cus_per_node = cores_per_node / cores_per_cu;
+		cus_per_node = c->x86_max_cores / nodes_per_socket;
 
 		/* store NodeID, use llc_shared_map to store sibling info */
 		per_cpu(cpu_llc_id, cpu) = node_id;
 
 		/* core id has to be in the [0 .. cores_per_node - 1] range */
-		c->cpu_core_id %= cores_per_node;
-		c->compute_unit_id %= cus_per_node;
+		c->cpu_core_id %= cus_per_node;
 	}
 }
 #endif
diff --git a/arch/x86/kernel/cpu/powerflags.c b/arch/x86/kernel/cpu/powerflags.c
index 31f0f335ed22..1dd8294fd730 100644
--- a/arch/x86/kernel/cpu/powerflags.c
+++ b/arch/x86/kernel/cpu/powerflags.c
@@ -18,4 +18,6 @@ const char *const x86_power_flags[32] = {
 	"",	/* tsc invariant mapped to constant_tsc */
 	"cpb",  /* core performance boost */
 	"eff_freq_ro", /* Readonly aperf/mperf */
+	"proc_feedback", /* processor feedback interface */
+	"acc_power", /* accumulated power mechanism */
 };
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index b2c99f811c3f..a2065d3b3b39 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -422,7 +422,7 @@ static bool match_smt(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
 
 		if (c->phys_proc_id == o->phys_proc_id &&
 		    per_cpu(cpu_llc_id, cpu1) == per_cpu(cpu_llc_id, cpu2) &&
-		    c->compute_unit_id == o->compute_unit_id)
+		    c->cpu_core_id == o->cpu_core_id)
 			return topology_sane(c, o, "smt");
 
 	} else if (c->phys_proc_id == o->phys_proc_id &&
diff --git a/arch/x86/ras/mce_amd_inj.c b/arch/x86/ras/mce_amd_inj.c
index 55d38cfa46c2..9e02dcaef683 100644
--- a/arch/x86/ras/mce_amd_inj.c
+++ b/arch/x86/ras/mce_amd_inj.c
@@ -20,6 +20,7 @@
 #include <linux/pci.h>
 
 #include <asm/mce.h>
+#include <asm/smp.h>
 #include <asm/amd_nb.h>
 #include <asm/irq_vectors.h>
 
@@ -206,7 +207,7 @@ static u32 get_nbc_for_node(int node_id)
 	struct cpuinfo_x86 *c = &boot_cpu_data;
 	u32 cores_per_node;
 
-	cores_per_node = c->x86_max_cores / amd_get_nodes_per_socket();
+	cores_per_node = (c->x86_max_cores * smp_num_siblings) / amd_get_nodes_per_socket();
 
 	return cores_per_node * node_id;
 }