From cd34206e949b66d3c5fa3e4d2905aa4af29d1b85 Mon Sep 17 00:00:00 2001 From: Nishanth Aravamudan Date: Tue, 26 Oct 2010 17:35:12 +0000 Subject: powerpc: Add memory_hotplug_max() Add a function to get the maximum address that can be hotplug added. This is needed to calculate the size of the tce table needed to cover all memory in 1:1 mode. Signed-off-by: Milton Miller Signed-off-by: Nishanth Aravamudan Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/mm/numa.c | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) (limited to 'arch/powerpc/mm/numa.c') diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index 74505b24537..8c0944c465f 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -1247,4 +1247,30 @@ int hot_add_scn_to_nid(unsigned long scn_addr) return nid; } +static u64 hot_add_drconf_memory_max(void) +{ + struct device_node *memory = NULL; + unsigned int drconf_cell_cnt = 0; + u64 lmb_size = 0; + const u32 *dm = 0; + + memory = of_find_node_by_path("/ibm,dynamic-reconfiguration-memory"); + if (memory) { + drconf_cell_cnt = of_get_drconf_memory(memory, &dm); + lmb_size = of_get_lmb_size(memory); + of_node_put(memory); + } + return lmb_size * drconf_cell_cnt; +} + +/* + * memory_hotplug_max - return max address of memory that may be added + * + * This is currently only used on systems that support drconfig memory + * hotplug. + */ +u64 memory_hotplug_max(void) +{ + return max(hot_add_drconf_memory_max(), memblock_end_of_DRAM()); +} #endif /* CONFIG_MEMORY_HOTPLUG */ -- cgit v1.2.3 From 9eff1a38407c051273fe1a20f03f8155bd32de35 Mon Sep 17 00:00:00 2001 From: Jesse Larrew Date: Wed, 1 Dec 2010 12:31:15 +0000 Subject: powerpc/pseries: Poll VPA for topology changes and update NUMA maps This patch sets a timer during boot that will periodically poll the associativity change counters in the VPA. When a change in associativity is detected, it retrieves the new associativity domain information via the H_HOME_NODE_ASSOCIATIVITY hcall and updates the NUMA node maps and sysfs entries accordingly. Note that since the ibm,associativity device tree property does not exist on configurations with both NUMA and SPLPAR enabled, no device tree updates are necessary. Signed-off-by: Jesse Larrew Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/lppaca.h | 5 +- arch/powerpc/mm/numa.c | 277 ++++++++++++++++++++++++++++++++++++-- 2 files changed, 271 insertions(+), 11 deletions(-) (limited to 'arch/powerpc/mm/numa.c') diff --git a/arch/powerpc/include/asm/lppaca.h b/arch/powerpc/include/asm/lppaca.h index 7f5e0fefebb..380d48bacd1 100644 --- a/arch/powerpc/include/asm/lppaca.h +++ b/arch/powerpc/include/asm/lppaca.h @@ -62,7 +62,10 @@ struct lppaca { volatile u32 dyn_pir; // Dynamic ProcIdReg value x20-x23 u32 dsei_data; // DSEI data x24-x27 u64 sprg3; // SPRG3 value x28-x2F - u8 reserved3[80]; // Reserved x30-x7F + u8 reserved3[40]; // Reserved x30-x57 + volatile u8 vphn_assoc_counts[8]; // Virtual processor home node + // associativity change counters x58-x5F + u8 reserved4[32]; // Reserved x60-x7F //============================================================================= // CACHE_LINE_2 0x0080 - 0x00FF Contains local read-write data diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index 8c0944c465f..d644ba7e8ab 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -20,10 +20,14 @@ #include #include #include +#include +#include #include #include #include #include +#include +#include static int numa_enabled = 1; @@ -246,32 +250,41 @@ static void initialize_distance_lookup_table(int nid, /* Returns nid in the range [0..MAX_NUMNODES-1], or -1 if no useful numa * info is found. */ -static int of_node_to_nid_single(struct device_node *device) +static int associativity_to_nid(const unsigned int *associativity) { int nid = -1; - const unsigned int *tmp; if (min_common_depth == -1) goto out; - tmp = of_get_associativity(device); - if (!tmp) - goto out; - - if (tmp[0] >= min_common_depth) - nid = tmp[min_common_depth]; + if (associativity[0] >= min_common_depth) + nid = associativity[min_common_depth]; /* POWER4 LPAR uses 0xffff as invalid node */ if (nid == 0xffff || nid >= MAX_NUMNODES) nid = -1; - if (nid > 0 && tmp[0] >= distance_ref_points_depth) - initialize_distance_lookup_table(nid, tmp); + if (nid > 0 && associativity[0] >= distance_ref_points_depth) + initialize_distance_lookup_table(nid, associativity); out: return nid; } +/* Returns the nid associated with the given device tree node, + * or -1 if not found. + */ +static int of_node_to_nid_single(struct device_node *device) +{ + int nid = -1; + const unsigned int *tmp; + + tmp = of_get_associativity(device); + if (tmp) + nid = associativity_to_nid(tmp); + return nid; +} + /* Walk the device tree upwards, looking for an associativity id */ int of_node_to_nid(struct device_node *device) { @@ -1274,3 +1287,247 @@ u64 memory_hotplug_max(void) return max(hot_add_drconf_memory_max(), memblock_end_of_DRAM()); } #endif /* CONFIG_MEMORY_HOTPLUG */ + +/* Vrtual Processor Home Node (VPHN) support */ +#define VPHN_NR_CHANGE_CTRS (8) +static u8 vphn_cpu_change_counts[NR_CPUS][VPHN_NR_CHANGE_CTRS]; +static cpumask_t cpu_associativity_changes_mask; +static int vphn_enabled; +static void set_topology_timer(void); +int stop_topology_update(void); + +/* + * Store the current values of the associativity change counters in the + * hypervisor. + */ +static void setup_cpu_associativity_change_counters(void) +{ + int cpu = 0; + + for_each_possible_cpu(cpu) { + int i = 0; + u8 *counts = vphn_cpu_change_counts[cpu]; + volatile u8 *hypervisor_counts = lppaca[cpu].vphn_assoc_counts; + + for (i = 0; i < VPHN_NR_CHANGE_CTRS; i++) { + counts[i] = hypervisor_counts[i]; + } + } +} + +/* + * The hypervisor maintains a set of 8 associativity change counters in + * the VPA of each cpu that correspond to the associativity levels in the + * ibm,associativity-reference-points property. When an associativity + * level changes, the corresponding counter is incremented. + * + * Set a bit in cpu_associativity_changes_mask for each cpu whose home + * node associativity levels have changed. + * + * Returns the number of cpus with unhandled associativity changes. + */ +static int update_cpu_associativity_changes_mask(void) +{ + int cpu = 0, nr_cpus = 0; + cpumask_t *changes = &cpu_associativity_changes_mask; + + cpumask_clear(changes); + + for_each_possible_cpu(cpu) { + int i, changed = 0; + u8 *counts = vphn_cpu_change_counts[cpu]; + volatile u8 *hypervisor_counts = lppaca[cpu].vphn_assoc_counts; + + for (i = 0; i < VPHN_NR_CHANGE_CTRS; i++) { + if (hypervisor_counts[i] > counts[i]) { + counts[i] = hypervisor_counts[i]; + changed = 1; + } + } + if (changed) { + cpumask_set_cpu(cpu, changes); + nr_cpus++; + } + } + + return nr_cpus; +} + +/* 6 64-bit registers unpacked into 12 32-bit associativity values */ +#define VPHN_ASSOC_BUFSIZE (6*sizeof(u64)/sizeof(u32)) + +/* + * Convert the associativity domain numbers returned from the hypervisor + * to the sequence they would appear in the ibm,associativity property. + */ +static int vphn_unpack_associativity(const long *packed, unsigned int *unpacked) +{ + int i = 0; + int nr_assoc_doms = 0; + const u16 *field = (const u16*) packed; + +#define VPHN_FIELD_UNUSED (0xffff) +#define VPHN_FIELD_MSB (0x8000) +#define VPHN_FIELD_MASK (~VPHN_FIELD_MSB) + + for (i = 0; i < VPHN_ASSOC_BUFSIZE; i++) { + if (*field == VPHN_FIELD_UNUSED) { + /* All significant fields processed, and remaining + * fields contain the reserved value of all 1's. + * Just store them. + */ + unpacked[i] = *((u32*)field); + field += 2; + } + else if (*field & VPHN_FIELD_MSB) { + /* Data is in the lower 15 bits of this field */ + unpacked[i] = *field & VPHN_FIELD_MASK; + field++; + nr_assoc_doms++; + } + else { + /* Data is in the lower 15 bits of this field + * concatenated with the next 16 bit field + */ + unpacked[i] = *((u32*)field); + field += 2; + nr_assoc_doms++; + } + } + + return nr_assoc_doms; +} + +/* + * Retrieve the new associativity information for a virtual processor's + * home node. + */ +static long hcall_vphn(unsigned long cpu, unsigned int *associativity) +{ + long rc = 0; + long retbuf[PLPAR_HCALL9_BUFSIZE] = {0}; + u64 flags = 1; + int hwcpu = get_hard_smp_processor_id(cpu); + + rc = plpar_hcall9(H_HOME_NODE_ASSOCIATIVITY, retbuf, flags, hwcpu); + vphn_unpack_associativity(retbuf, associativity); + + return rc; +} + +static long vphn_get_associativity(unsigned long cpu, + unsigned int *associativity) +{ + long rc = 0; + + rc = hcall_vphn(cpu, associativity); + + switch (rc) { + case H_FUNCTION: + printk(KERN_INFO + "VPHN is not supported. Disabling polling...\n"); + stop_topology_update(); + break; + case H_HARDWARE: + printk(KERN_ERR + "hcall_vphn() experienced a hardware fault " + "preventing VPHN. Disabling polling...\n"); + stop_topology_update(); + } + + return rc; +} + +/* + * Update the node maps and sysfs entries for each cpu whose home node + * has changed. + */ +int arch_update_cpu_topology(void) +{ + int cpu = 0, nid = 0, old_nid = 0; + unsigned int associativity[VPHN_ASSOC_BUFSIZE] = {0}; + struct sys_device *sysdev = NULL; + + for_each_cpu_mask(cpu, cpu_associativity_changes_mask) { + vphn_get_associativity(cpu, associativity); + nid = associativity_to_nid(associativity); + + if (nid < 0 || !node_online(nid)) + nid = first_online_node; + + old_nid = numa_cpu_lookup_table[cpu]; + + /* Disable hotplug while we update the cpu + * masks and sysfs. + */ + get_online_cpus(); + unregister_cpu_under_node(cpu, old_nid); + unmap_cpu_from_node(cpu); + map_cpu_to_node(cpu, nid); + register_cpu_under_node(cpu, nid); + put_online_cpus(); + + sysdev = get_cpu_sysdev(cpu); + if (sysdev) + kobject_uevent(&sysdev->kobj, KOBJ_CHANGE); + } + + return 1; +} + +static void topology_work_fn(struct work_struct *work) +{ + rebuild_sched_domains(); +} +static DECLARE_WORK(topology_work, topology_work_fn); + +void topology_schedule_update(void) +{ + schedule_work(&topology_work); +} + +static void topology_timer_fn(unsigned long ignored) +{ + if (!vphn_enabled) + return; + if (update_cpu_associativity_changes_mask() > 0) + topology_schedule_update(); + set_topology_timer(); +} +static struct timer_list topology_timer = + TIMER_INITIALIZER(topology_timer_fn, 0, 0); + +static void set_topology_timer(void) +{ + topology_timer.data = 0; + topology_timer.expires = jiffies + 60 * HZ; + add_timer(&topology_timer); +} + +/* + * Start polling for VPHN associativity changes. + */ +int start_topology_update(void) +{ + int rc = 0; + + if (firmware_has_feature(FW_FEATURE_VPHN)) { + vphn_enabled = 1; + setup_cpu_associativity_change_counters(); + init_timer_deferrable(&topology_timer); + set_topology_timer(); + rc = 1; + } + + return rc; +} +__initcall(start_topology_update); + +/* + * Disable polling for VPHN associativity changes. + */ +int stop_topology_update(void) +{ + vphn_enabled = 0; + return del_timer_sync(&topology_timer); +} -- cgit v1.2.3 From 39bf990ead35c7263652ca5dd8262b2b2cd147ac Mon Sep 17 00:00:00 2001 From: Jesse Larrew Date: Fri, 17 Dec 2010 22:07:47 +0000 Subject: powerpc/pseries: Fix VPHN build errors on non-SMP systems The header asm/hvcall.h was previously included indirectly via smp.h. On non-SMP systems, however, these declarations are excluded and the build breaks. This is easily fixed by including asm/hvcall.h directly. The VPHN feature is only meaningful on NUMA systems that implement the SPLPAR option, so exclude the VPHN code on systems without SPLPAR enabled. Also, expose unmap_cpu_from_node() on systems with SPLPAR enabled, even if CONFIG_HOTPLUG_CPU is disabled. Lastly, map_cpu_to_node() is now needed by VPHN to manipulate the node masks after boot time, so remove the __cpuinit annotation to fix a section mismatch. Signed-off-by: Jesse Larrew --- arch/powerpc/include/asm/topology.h | 20 +++++++++++--------- arch/powerpc/mm/numa.c | 9 ++++++--- 2 files changed, 17 insertions(+), 12 deletions(-) (limited to 'arch/powerpc/mm/numa.c') diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h index aed188bd70d..fbfcfd04d25 100644 --- a/arch/powerpc/include/asm/topology.h +++ b/arch/powerpc/include/asm/topology.h @@ -93,9 +93,20 @@ extern void __init dump_numa_cpu_topology(void); extern int sysfs_add_device_to_node(struct sys_device *dev, int nid); extern void sysfs_remove_device_from_node(struct sys_device *dev, int nid); +#ifdef CONFIG_PPC_SPLPAR extern int start_topology_update(void); extern int stop_topology_update(void); #else +static inline int start_topology_update(void) +{ + return 0; +} +static inline int stop_topology_update(void) +{ + return 0; +} +#endif /* CONFIG_PPC_SPLPAR */ +#else static inline void dump_numa_cpu_topology(void) {} @@ -108,15 +119,6 @@ static inline void sysfs_remove_device_from_node(struct sys_device *dev, int nid) { } - -static inline int start_topology_update(void) -{ - return 0; -} -static inline int stop_topology_update(void) -{ - return 0; -} #endif /* CONFIG_NUMA */ #include diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index d644ba7e8ab..3c0d20c9161 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -28,6 +28,7 @@ #include #include #include +#include static int numa_enabled = 1; @@ -167,7 +168,7 @@ static void __init get_node_active_region(unsigned long start_pfn, work_with_active_regions(nid, get_active_region_work_fn, node_ar); } -static void __cpuinit map_cpu_to_node(int cpu, int node) +static void map_cpu_to_node(int cpu, int node) { numa_cpu_lookup_table[cpu] = node; @@ -177,7 +178,7 @@ static void __cpuinit map_cpu_to_node(int cpu, int node) cpumask_set_cpu(cpu, node_to_cpumask_map[node]); } -#ifdef CONFIG_HOTPLUG_CPU +#if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_PPC_SPLPAR) static void unmap_cpu_from_node(unsigned long cpu) { int node = numa_cpu_lookup_table[cpu]; @@ -191,7 +192,7 @@ static void unmap_cpu_from_node(unsigned long cpu) cpu, node); } } -#endif /* CONFIG_HOTPLUG_CPU */ +#endif /* CONFIG_HOTPLUG_CPU || CONFIG_PPC_SPLPAR */ /* must hold reference to node during call */ static const int *of_get_associativity(struct device_node *dev) @@ -1289,6 +1290,7 @@ u64 memory_hotplug_max(void) #endif /* CONFIG_MEMORY_HOTPLUG */ /* Vrtual Processor Home Node (VPHN) support */ +#ifdef CONFIG_PPC_SPLPAR #define VPHN_NR_CHANGE_CTRS (8) static u8 vphn_cpu_change_counts[NR_CPUS][VPHN_NR_CHANGE_CTRS]; static cpumask_t cpu_associativity_changes_mask; @@ -1531,3 +1533,4 @@ int stop_topology_update(void) vphn_enabled = 0; return del_timer_sync(&topology_timer); } +#endif /* CONFIG_PPC_SPLPAR */ -- cgit v1.2.3 From 5d7d8072edc11080a7cf6cc37c9f4e61ca1e93c9 Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Wed, 12 Jan 2011 10:56:29 +1100 Subject: powerpc/pseries: Fix build of topology stuff without CONFIG_NUMA Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/topology.h | 27 ++++++++++++++------------- arch/powerpc/mm/numa.c | 1 - 2 files changed, 14 insertions(+), 14 deletions(-) (limited to 'arch/powerpc/mm/numa.c') diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h index fbfcfd04d25..7ef0d90defc 100644 --- a/arch/powerpc/include/asm/topology.h +++ b/arch/powerpc/include/asm/topology.h @@ -93,19 +93,6 @@ extern void __init dump_numa_cpu_topology(void); extern int sysfs_add_device_to_node(struct sys_device *dev, int nid); extern void sysfs_remove_device_from_node(struct sys_device *dev, int nid); -#ifdef CONFIG_PPC_SPLPAR -extern int start_topology_update(void); -extern int stop_topology_update(void); -#else -static inline int start_topology_update(void) -{ - return 0; -} -static inline int stop_topology_update(void) -{ - return 0; -} -#endif /* CONFIG_PPC_SPLPAR */ #else static inline void dump_numa_cpu_topology(void) {} @@ -121,6 +108,20 @@ static inline void sysfs_remove_device_from_node(struct sys_device *dev, } #endif /* CONFIG_NUMA */ +#if defined(CONFIG_NUMA) && defined(CONFIG_PPC_SPLPAR) +extern int start_topology_update(void); +extern int stop_topology_update(void); +#else +static inline int start_topology_update(void) +{ + return 0; +} +static inline int stop_topology_update(void) +{ + return 0; +} +#endif /* CONFIG_NUMA && CONFIG_PPC_SPLPAR */ + #include #ifdef CONFIG_SMP diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index 3c0d20c9161..bf5cb91f07d 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -1296,7 +1296,6 @@ static u8 vphn_cpu_change_counts[NR_CPUS][VPHN_NR_CHANGE_CTRS]; static cpumask_t cpu_associativity_changes_mask; static int vphn_enabled; static void set_topology_timer(void); -int stop_topology_update(void); /* * Store the current values of the associativity change counters in the -- cgit v1.2.3