#ifdef CONFIG_PPC_BOOK3S
+ /*
+ * We only have to have statically allocated lppaca structs on
+ * legacy iSeries, which supports at most 64 cpus.
+ */
+ #ifdef CONFIG_PPC_ISERIES
+ #if NR_CPUS < 64
+ #define NR_LPPACAS NR_CPUS
+ #else
+ #define NR_LPPACAS 64
+ #endif
+ #else /* not iSeries */
+ #define NR_LPPACAS 1
+ #endif
+
/*
* The structure which the hypervisor knows about - this structure
* should not cross a page boundary. The vpa_init/register_vpa call
* will suffice to ensure that it doesn't cross a page boundary.
*/
struct lppaca lppaca[] = {
- [0 ... (NR_CPUS-1)] = {
+ [0 ... (NR_LPPACAS-1)] = {
.desc = 0xd397d781, /* "LpPa" */
.size = sizeof(struct lppaca),
.dyn_proc_status = 2,
},
};
+ static struct lppaca *extra_lppacas;
+ static long __initdata lppaca_size;
+
+ static void allocate_lppacas(int nr_cpus, unsigned long limit)
+ {
+ if (nr_cpus <= NR_LPPACAS)
+ return;
+
+ lppaca_size = PAGE_ALIGN(sizeof(struct lppaca) *
+ (nr_cpus - NR_LPPACAS));
+ extra_lppacas = __va(memblock_alloc_base(lppaca_size,
+ PAGE_SIZE, limit));
+ }
+
+ static struct lppaca *new_lppaca(int cpu)
+ {
+ struct lppaca *lp;
+
+ if (cpu < NR_LPPACAS)
+ return &lppaca[cpu];
+
+ lp = extra_lppacas + (cpu - NR_LPPACAS);
+ *lp = lppaca[0];
+
+ return lp;
+ }
+
+ static void free_lppacas(void)
+ {
+ long new_size = 0, nr;
+
+ if (!lppaca_size)
+ return;
+ nr = num_possible_cpus() - NR_LPPACAS;
+ if (nr > 0)
+ new_size = PAGE_ALIGN(nr * sizeof(struct lppaca));
+ if (new_size >= lppaca_size)
+ return;
+
+ memblock_free(__pa(extra_lppacas) + new_size, lppaca_size - new_size);
+ lppaca_size = new_size;
+ }
+
+ #else
+
+ static inline void allocate_lppacas(int nr_cpus, unsigned long limit) { }
+ static inline void free_lppacas(void) { }
+
#endif /* CONFIG_PPC_BOOK3S */
#ifdef CONFIG_PPC_STD_MMU_64
unsigned long kernel_toc = (unsigned long)(&__toc_start) + 0x8000UL;
#ifdef CONFIG_PPC_BOOK3S
- new_paca->lppaca_ptr = &lppaca[cpu];
+ new_paca->lppaca_ptr = new_lppaca(cpu);
#else
new_paca->kernel_pgd = swapper_pg_dir;
#endif
* the first segment. On iSeries they must be within the area mapped
* by the HV, which is HvPagesToMap * HVPAGESIZE bytes.
*/
- limit = min(0x10000000ULL, memblock.rmo_size);
+ limit = min(0x10000000ULL, ppc64_rma_size);
if (firmware_has_feature(FW_FEATURE_ISERIES))
limit = min(limit, HvPagesToMap * HVPAGESIZE);
printk(KERN_DEBUG "Allocated %u bytes for %d pacas at %p\n",
paca_size, nr_cpus, paca);
+ allocate_lppacas(nr_cpus, limit);
+
/* Can't use for_each_*_cpu, as they aren't functional yet */
for (cpu = 0; cpu < nr_cpus; cpu++)
initialise_paca(&paca[cpu], cpu);
paca_size - new_size);
paca_size = new_size;
+
+ free_lppacas();
}
#include <linux/posix-timers.h>
#include <linux/irq.h>
#include <linux/delay.h>
-#include <linux/perf_event.h>
+#include <linux/irq_work.h>
#include <asm/trace.h>
#include <asm/io.h>
static long timezone_offset;
unsigned long ppc_proc_freq;
- EXPORT_SYMBOL(ppc_proc_freq);
+ EXPORT_SYMBOL_GPL(ppc_proc_freq);
unsigned long ppc_tb_freq;
-
- static DEFINE_PER_CPU(u64, last_jiffy);
+ EXPORT_SYMBOL_GPL(ppc_tb_freq);
#ifdef CONFIG_VIRT_CPU_ACCOUNTING
/*
cputime_t cputime_one_jiffy;
+ void (*dtl_consumer)(struct dtl_entry *, u64);
+
static void calc_cputime_factors(void)
{
struct div_result res;
}
/*
- * Read the PURR on systems that have it, otherwise the timebase.
+ * Read the SPURR on systems that have it, otherwise the PURR,
+ * or if that doesn't exist return the timebase value passed in.
*/
- static u64 read_purr(void)
+ static u64 read_spurr(u64 tb)
{
+ if (cpu_has_feature(CPU_FTR_SPURR))
+ return mfspr(SPRN_SPURR);
if (cpu_has_feature(CPU_FTR_PURR))
return mfspr(SPRN_PURR);
- return mftb();
+ return tb;
}
+ #ifdef CONFIG_PPC_SPLPAR
+
/*
- * Read the SPURR on systems that have it, otherwise the purr
+ * Scan the dispatch trace log and count up the stolen time.
+ * Should be called with interrupts disabled.
*/
- static u64 read_spurr(u64 purr)
+ static u64 scan_dispatch_log(u64 stop_tb)
{
- /*
- * cpus without PURR won't have a SPURR
- * We already know the former when we use this, so tell gcc
- */
- if (cpu_has_feature(CPU_FTR_PURR) && cpu_has_feature(CPU_FTR_SPURR))
- return mfspr(SPRN_SPURR);
- return purr;
+ u64 i = local_paca->dtl_ridx;
+ struct dtl_entry *dtl = local_paca->dtl_curr;
+ struct dtl_entry *dtl_end = local_paca->dispatch_log_end;
+ struct lppaca *vpa = local_paca->lppaca_ptr;
+ u64 tb_delta;
+ u64 stolen = 0;
+ u64 dtb;
+
+ if (i == vpa->dtl_idx)
+ return 0;
+ while (i < vpa->dtl_idx) {
+ if (dtl_consumer)
+ dtl_consumer(dtl, i);
+ dtb = dtl->timebase;
+ tb_delta = dtl->enqueue_to_dispatch_time +
+ dtl->ready_to_enqueue_time;
+ barrier();
+ if (i + N_DISPATCH_LOG < vpa->dtl_idx) {
+ /* buffer has overflowed */
+ i = vpa->dtl_idx - N_DISPATCH_LOG;
+ dtl = local_paca->dispatch_log + (i % N_DISPATCH_LOG);
+ continue;
+ }
+ if (dtb > stop_tb)
+ break;
+ stolen += tb_delta;
+ ++i;
+ ++dtl;
+ if (dtl == dtl_end)
+ dtl = local_paca->dispatch_log;
+ }
+ local_paca->dtl_ridx = i;
+ local_paca->dtl_curr = dtl;
+ return stolen;
}
+ /*
+ * Accumulate stolen time by scanning the dispatch trace log.
+ * Called on entry from user mode.
+ */
+ void accumulate_stolen_time(void)
+ {
+ u64 sst, ust;
+
+ sst = scan_dispatch_log(get_paca()->starttime_user);
+ ust = scan_dispatch_log(get_paca()->starttime);
+ get_paca()->system_time -= sst;
+ get_paca()->user_time -= ust;
+ get_paca()->stolen_time += ust + sst;
+ }
+
+ static inline u64 calculate_stolen_time(u64 stop_tb)
+ {
+ u64 stolen = 0;
+
+ if (get_paca()->dtl_ridx != get_paca()->lppaca_ptr->dtl_idx) {
+ stolen = scan_dispatch_log(stop_tb);
+ get_paca()->system_time -= stolen;
+ }
+
+ stolen += get_paca()->stolen_time;
+ get_paca()->stolen_time = 0;
+ return stolen;
+ }
+
+ #else /* CONFIG_PPC_SPLPAR */
+ static inline u64 calculate_stolen_time(u64 stop_tb)
+ {
+ return 0;
+ }
+
+ #endif /* CONFIG_PPC_SPLPAR */
+
/*
* Account time for a transition between system, hard irq
* or soft irq state.
*/
void account_system_vtime(struct task_struct *tsk)
{
- u64 now, nowscaled, delta, deltascaled, sys_time;
+ u64 now, nowscaled, delta, deltascaled;
unsigned long flags;
+ u64 stolen, udelta, sys_scaled, user_scaled;
local_irq_save(flags);
- now = read_purr();
+ now = mftb();
nowscaled = read_spurr(now);
- delta = now - get_paca()->startpurr;
+ get_paca()->system_time += now - get_paca()->starttime;
+ get_paca()->starttime = now;
deltascaled = nowscaled - get_paca()->startspurr;
- get_paca()->startpurr = now;
get_paca()->startspurr = nowscaled;
- if (!in_interrupt()) {
- /* deltascaled includes both user and system time.
- * Hence scale it based on the purr ratio to estimate
- * the system time */
- sys_time = get_paca()->system_time;
- if (get_paca()->user_time)
- deltascaled = deltascaled * sys_time /
- (sys_time + get_paca()->user_time);
- delta += sys_time;
- get_paca()->system_time = 0;
+
+ stolen = calculate_stolen_time(now);
+
+ delta = get_paca()->system_time;
+ get_paca()->system_time = 0;
+ udelta = get_paca()->user_time - get_paca()->utime_sspurr;
+ get_paca()->utime_sspurr = get_paca()->user_time;
+
+ /*
+ * Because we don't read the SPURR on every kernel entry/exit,
+ * deltascaled includes both user and system SPURR ticks.
+ * Apportion these ticks to system SPURR ticks and user
+ * SPURR ticks in the same ratio as the system time (delta)
+ * and user time (udelta) values obtained from the timebase
+ * over the same interval. The system ticks get accounted here;
+ * the user ticks get saved up in paca->user_time_scaled to be
+ * used by account_process_tick.
+ */
+ sys_scaled = delta;
+ user_scaled = udelta;
+ if (deltascaled != delta + udelta) {
+ if (udelta) {
+ sys_scaled = deltascaled * delta / (delta + udelta);
+ user_scaled = deltascaled - sys_scaled;
+ } else {
+ sys_scaled = deltascaled;
+ }
+ }
+ get_paca()->user_time_scaled += user_scaled;
+
+ if (in_irq() || idle_task(smp_processor_id()) != tsk) {
+ account_system_time(tsk, 0, delta, sys_scaled);
+ if (stolen)
+ account_steal_time(stolen);
+ } else {
+ account_idle_time(delta + stolen);
}
- if (in_irq() || idle_task(smp_processor_id()) != tsk)
- account_system_time(tsk, 0, delta, deltascaled);
- else
- account_idle_time(delta);
- __get_cpu_var(cputime_last_delta) = delta;
- __get_cpu_var(cputime_scaled_last_delta) = deltascaled;
local_irq_restore(flags);
}
EXPORT_SYMBOL_GPL(account_system_vtime);
* by the exception entry and exit code to the generic process
* user and system time records.
* Must be called with interrupts disabled.
+ * Assumes that account_system_vtime() has been called recently
+ * (i.e. since the last entry from usermode) so that
+ * get_paca()->user_time_scaled is up to date.
*/
void account_process_tick(struct task_struct *tsk, int user_tick)
{
cputime_t utime, utimescaled;
utime = get_paca()->user_time;
+ utimescaled = get_paca()->user_time_scaled;
get_paca()->user_time = 0;
- utimescaled = cputime_to_scaled(utime);
+ get_paca()->user_time_scaled = 0;
+ get_paca()->utime_sspurr = 0;
account_user_time(tsk, utime, utimescaled);
}
- /*
- * Stuff for accounting stolen time.
- */
- struct cpu_purr_data {
- int initialized; /* thread is running */
- u64 tb; /* last TB value read */
- u64 purr; /* last PURR value read */
- u64 spurr; /* last SPURR value read */
- };
-
- /*
- * Each entry in the cpu_purr_data array is manipulated only by its
- * "owner" cpu -- usually in the timer interrupt but also occasionally
- * in process context for cpu online. As long as cpus do not touch
- * each others' cpu_purr_data, disabling local interrupts is
- * sufficient to serialize accesses.
- */
- static DEFINE_PER_CPU(struct cpu_purr_data, cpu_purr_data);
-
- static void snapshot_tb_and_purr(void *data)
- {
- unsigned long flags;
- struct cpu_purr_data *p = &__get_cpu_var(cpu_purr_data);
-
- local_irq_save(flags);
- p->tb = get_tb_or_rtc();
- p->purr = mfspr(SPRN_PURR);
- wmb();
- p->initialized = 1;
- local_irq_restore(flags);
- }
-
- /*
- * Called during boot when all cpus have come up.
- */
- void snapshot_timebases(void)
- {
- if (!cpu_has_feature(CPU_FTR_PURR))
- return;
- on_each_cpu(snapshot_tb_and_purr, NULL, 1);
- }
-
- /*
- * Must be called with interrupts disabled.
- */
- void calculate_steal_time(void)
- {
- u64 tb, purr;
- s64 stolen;
- struct cpu_purr_data *pme;
-
- pme = &__get_cpu_var(cpu_purr_data);
- if (!pme->initialized)
- return; /* !CPU_FTR_PURR or early in early boot */
- tb = mftb();
- purr = mfspr(SPRN_PURR);
- stolen = (tb - pme->tb) - (purr - pme->purr);
- if (stolen > 0) {
- if (idle_task(smp_processor_id()) != current)
- account_steal_time(stolen);
- else
- account_idle_time(stolen);
- }
- pme->tb = tb;
- pme->purr = purr;
- }
-
- #ifdef CONFIG_PPC_SPLPAR
- /*
- * Must be called before the cpu is added to the online map when
- * a cpu is being brought up at runtime.
- */
- static void snapshot_purr(void)
- {
- struct cpu_purr_data *pme;
- unsigned long flags;
-
- if (!cpu_has_feature(CPU_FTR_PURR))
- return;
- local_irq_save(flags);
- pme = &__get_cpu_var(cpu_purr_data);
- pme->tb = mftb();
- pme->purr = mfspr(SPRN_PURR);
- pme->initialized = 1;
- local_irq_restore(flags);
- }
-
- #endif /* CONFIG_PPC_SPLPAR */
-
#else /* ! CONFIG_VIRT_CPU_ACCOUNTING */
#define calc_cputime_factors()
- #define calculate_steal_time() do { } while (0)
#endif
- #if !(defined(CONFIG_VIRT_CPU_ACCOUNTING) && defined(CONFIG_PPC_SPLPAR))
- #define snapshot_purr() do { } while (0)
- #endif
-
- /*
- * Called when a cpu comes up after the system has finished booting,
- * i.e. as a result of a hotplug cpu action.
- */
- void snapshot_timebase(void)
- {
- __get_cpu_var(last_jiffy) = get_tb_or_rtc();
- snapshot_purr();
- }
-
void __delay(unsigned long loops)
{
unsigned long start;
}
#endif /* CONFIG_PPC_ISERIES */
-#ifdef CONFIG_PERF_EVENTS
+#ifdef CONFIG_IRQ_WORK
/*
* 64-bit uses a byte in the PACA, 32-bit uses a per-cpu variable...
*/
#ifdef CONFIG_PPC64
-static inline unsigned long test_perf_event_pending(void)
+static inline unsigned long test_irq_work_pending(void)
{
unsigned long x;
asm volatile("lbz %0,%1(13)"
: "=r" (x)
- : "i" (offsetof(struct paca_struct, perf_event_pending)));
+ : "i" (offsetof(struct paca_struct, irq_work_pending)));
return x;
}
-static inline void set_perf_event_pending_flag(void)
+static inline void set_irq_work_pending_flag(void)
{
asm volatile("stb %0,%1(13)" : :
"r" (1),
- "i" (offsetof(struct paca_struct, perf_event_pending)));
+ "i" (offsetof(struct paca_struct, irq_work_pending)));
}
-static inline void clear_perf_event_pending(void)
+static inline void clear_irq_work_pending(void)
{
asm volatile("stb %0,%1(13)" : :
"r" (0),
- "i" (offsetof(struct paca_struct, perf_event_pending)));
+ "i" (offsetof(struct paca_struct, irq_work_pending)));
}
#else /* 32-bit */
-DEFINE_PER_CPU(u8, perf_event_pending);
+DEFINE_PER_CPU(u8, irq_work_pending);
-#define set_perf_event_pending_flag() __get_cpu_var(perf_event_pending) = 1
-#define test_perf_event_pending() __get_cpu_var(perf_event_pending)
-#define clear_perf_event_pending() __get_cpu_var(perf_event_pending) = 0
+#define set_irq_work_pending_flag() __get_cpu_var(irq_work_pending) = 1
+#define test_irq_work_pending() __get_cpu_var(irq_work_pending)
+#define clear_irq_work_pending() __get_cpu_var(irq_work_pending) = 0
#endif /* 32 vs 64 bit */
-void set_perf_event_pending(void)
+void set_irq_work_pending(void)
{
preempt_disable();
- set_perf_event_pending_flag();
+ set_irq_work_pending_flag();
set_dec(1);
preempt_enable();
}
-#else /* CONFIG_PERF_EVENTS */
+#else /* CONFIG_IRQ_WORK */
-#define test_perf_event_pending() 0
-#define clear_perf_event_pending()
+#define test_irq_work_pending() 0
+#define clear_irq_work_pending()
-#endif /* CONFIG_PERF_EVENTS */
+#endif /* CONFIG_IRQ_WORK */
/*
* For iSeries shared processors, we have to let the hypervisor
old_regs = set_irq_regs(regs);
irq_enter();
- calculate_steal_time();
-
- if (test_perf_event_pending()) {
- clear_perf_event_pending();
- perf_event_do_pending();
+ if (test_irq_work_pending()) {
+ clear_irq_work_pending();
+ irq_work_run();
}
#ifdef CONFIG_PPC_ISERIES
static void setup_page_sizes(void)
{
- unsigned int tlb0cfg = mfspr(SPRN_TLB0CFG);
- unsigned int tlb0ps = mfspr(SPRN_TLB0PS);
- unsigned int eptcfg = mfspr(SPRN_EPTCFG);
+ unsigned int tlb0cfg;
+ unsigned int tlb0ps;
+ unsigned int eptcfg;
int i, psize;
+ #ifdef CONFIG_PPC_FSL_BOOK3E
+ unsigned int mmucfg = mfspr(SPRN_MMUCFG);
+
+ if (((mmucfg & MMUCFG_MAVN) == MMUCFG_MAVN_V1) &&
+ (mmu_has_feature(MMU_FTR_TYPE_FSL_E))) {
+ unsigned int tlb1cfg = mfspr(SPRN_TLB1CFG);
+ unsigned int min_pg, max_pg;
+
+ min_pg = (tlb1cfg & TLBnCFG_MINSIZE) >> TLBnCFG_MINSIZE_SHIFT;
+ max_pg = (tlb1cfg & TLBnCFG_MAXSIZE) >> TLBnCFG_MAXSIZE_SHIFT;
+
+ for (psize = 0; psize < MMU_PAGE_COUNT; ++psize) {
+ struct mmu_psize_def *def;
+ unsigned int shift;
+
+ def = &mmu_psize_defs[psize];
+ shift = def->shift;
+
+ if (shift == 0)
+ continue;
+
+ /* adjust to be in terms of 4^shift Kb */
+ shift = (shift - 10) >> 1;
+
+ if ((shift >= min_pg) && (shift <= max_pg))
+ def->flags |= MMU_PAGE_SIZE_DIRECT;
+ }
+
+ goto no_indirect;
+ }
+ #endif
+
+ tlb0cfg = mfspr(SPRN_TLB0CFG);
+ tlb0ps = mfspr(SPRN_TLB0PS);
+ eptcfg = mfspr(SPRN_EPTCFG);
+
/* Look for supported direct sizes */
for (psize = 0; psize < MMU_PAGE_COUNT; ++psize) {
struct mmu_psize_def *def = &mmu_psize_defs[psize];
*/
linear_map_top = memblock_end_of_DRAM();
+ #ifdef CONFIG_PPC_FSL_BOOK3E
+ if (mmu_has_feature(MMU_FTR_TYPE_FSL_E)) {
+ unsigned int num_cams;
+
+ /* use a quarter of the TLBCAM for bolted linear map */
+ num_cams = (mfspr(SPRN_TLB1CFG) & TLBnCFG_N_ENTRY) / 4;
+ linear_map_top = map_mem_in_cams(linear_map_top, num_cams);
+
+ /* limit memory so we dont have linear faults */
+ memblock_enforce_memory_limit(linear_map_top);
+ memblock_analyze();
+ }
+ #endif
+
/* A sync won't hurt us after mucking around with
* the MMU configuration
*/
mb();
+
+ memblock_set_current_limit(linear_map_top);
}
void __init early_init_mmu(void)
__early_init_mmu(0);
}
+void setup_initial_memory_limit(phys_addr_t first_memblock_base,
+ phys_addr_t first_memblock_size)
+{
+ /* On Embedded 64-bit, we adjust the RMA size to match
+ * the bolted TLB entry. We know for now that only 1G
+ * entries are supported though that may eventually
+ * change. We crop it to the size of the first MEMBLOCK to
+ * avoid going over total available memory just in case...
+ */
+ ppc64_rma_size = min_t(u64, first_memblock_size, 0x40000000);
+
+ /* Finally limit subsequent allocations */
+ memblock_set_current_limit(ppc64_memblock_base + ppc64_rma_size);
+}
#endif /* CONFIG_PPC64 */
projects / linux.git / commitdiff