unsigned long (*check_apicid_used)(physid_mask_t *map, int apicid);
unsigned long (*check_apicid_present)(int apicid);
- void (*vector_allocation_domain)(int cpu, struct cpumask *retmask);
+ void (*vector_allocation_domain)(int cpu, struct cpumask *retmask,
+ const struct cpumask *mask);
void (*init_apic_ldr)(void);
void (*ioapic_phys_id_map)(physid_mask_t *phys_map, physid_mask_t *retmap);
unsigned long (*set_apic_id)(unsigned int id);
unsigned long apic_id_mask;
- unsigned int (*cpu_mask_to_apicid)(const struct cpumask *cpumask);
- unsigned int (*cpu_mask_to_apicid_and)(const struct cpumask *cpumask,
- const struct cpumask *andmask);
+ int (*cpu_mask_to_apicid_and)(const struct cpumask *cpumask,
+ const struct cpumask *andmask,
+ unsigned int *apicid);
/* ipi */
void (*send_IPI_mask)(const struct cpumask *mask, int vector);
return apic->safe_wait_icr_idle();
}
+extern void __init apic_set_eoi_write(void (*eoi_write)(u32 reg, u32 v));
+
#else /* CONFIG_X86_LOCAL_APIC */
static inline u32 apic_read(u32 reg) { return 0; }
static inline void apic_icr_write(u32 low, u32 high) { }
static inline void apic_wait_icr_idle(void) { }
static inline u32 safe_apic_wait_icr_idle(void) { return 0; }
+static inline void apic_set_eoi_write(void (*eoi_write)(u32 reg, u32 v)) {}
#endif /* CONFIG_X86_LOCAL_APIC */
#endif
}
- DECLARE_EARLY_PER_CPU(u16, x86_bios_cpu_apicid);
+static inline const struct cpumask *online_target_cpus(void)
+{
+ return cpu_online_mask;
+}
+
+ DECLARE_EARLY_PER_CPU_READ_MOSTLY(u16, x86_bios_cpu_apicid);
static inline unsigned int read_apic_id(void)
#endif
-static inline unsigned int
-default_cpu_mask_to_apicid(const struct cpumask *cpumask)
+static inline int
+flat_cpu_mask_to_apicid_and(const struct cpumask *cpumask,
+ const struct cpumask *andmask,
+ unsigned int *apicid)
{
- return cpumask_bits(cpumask)[0] & APIC_ALL_CPUS;
+ unsigned long cpu_mask = cpumask_bits(cpumask)[0] &
+ cpumask_bits(andmask)[0] &
+ cpumask_bits(cpu_online_mask)[0] &
+ APIC_ALL_CPUS;
+
+ if (likely(cpu_mask)) {
+ *apicid = (unsigned int)cpu_mask;
+ return 0;
+ } else {
+ return -EINVAL;
+ }
}
-static inline unsigned int
+extern int
default_cpu_mask_to_apicid_and(const struct cpumask *cpumask,
- const struct cpumask *andmask)
+ const struct cpumask *andmask,
+ unsigned int *apicid);
+
+static inline void
+flat_vector_allocation_domain(int cpu, struct cpumask *retmask,
+ const struct cpumask *mask)
{
- unsigned long mask1 = cpumask_bits(cpumask)[0];
- unsigned long mask2 = cpumask_bits(andmask)[0];
- unsigned long mask3 = cpumask_bits(cpu_online_mask)[0];
+ /* Careful. Some cpus do not strictly honor the set of cpus
+ * specified in the interrupt destination when using lowest
+ * priority interrupt delivery mode.
+ *
+ * In particular there was a hyperthreading cpu observed to
+ * deliver interrupts to the wrong hyperthread when only one
+ * hyperthread was specified in the interrupt desitination.
+ */
+ cpumask_clear(retmask);
+ cpumask_bits(retmask)[0] = APIC_ALL_CPUS;
+}
- return (unsigned int)(mask1 & mask2 & mask3);
+static inline void
+default_vector_allocation_domain(int cpu, struct cpumask *retmask,
+ const struct cpumask *mask)
+{
+ cpumask_copy(retmask, cpumask_of(cpu));
}
static inline unsigned long default_check_apicid_used(physid_mask_t *map, int apicid)
return PVOP_CALL2(u64, pv_cpu_ops.read_msr, msr, err);
}
-static inline int paravirt_rdmsr_regs(u32 *regs)
-{
- return PVOP_CALL1(int, pv_cpu_ops.rdmsr_regs, regs);
-}
-
static inline int paravirt_write_msr(unsigned msr, unsigned low, unsigned high)
{
return PVOP_CALL3(int, pv_cpu_ops.write_msr, msr, low, high);
}
-static inline int paravirt_wrmsr_regs(u32 *regs)
-{
- return PVOP_CALL1(int, pv_cpu_ops.wrmsr_regs, regs);
-}
-
/* These should all do BUG_ON(_err), but our headers are too tangled. */
#define rdmsr(msr, val1, val2) \
do { \
_err; \
})
-#define rdmsr_safe_regs(regs) paravirt_rdmsr_regs(regs)
-#define wrmsr_safe_regs(regs) paravirt_wrmsr_regs(regs)
-
static inline int rdmsrl_safe(unsigned msr, unsigned long long *p)
{
int err;
*p = paravirt_read_msr(msr, &err);
return err;
}
-static inline int rdmsrl_amd_safe(unsigned msr, unsigned long long *p)
-{
- u32 gprs[8] = { 0 };
- int err;
-
- gprs[1] = msr;
- gprs[7] = 0x9c5a203a;
-
- err = paravirt_rdmsr_regs(gprs);
-
- *p = gprs[0] | ((u64)gprs[2] << 32);
-
- return err;
-}
-
-static inline int wrmsrl_amd_safe(unsigned msr, unsigned long long val)
-{
- u32 gprs[8] = { 0 };
-
- gprs[0] = (u32)val;
- gprs[1] = msr;
- gprs[2] = val >> 32;
- gprs[7] = 0x9c5a203a;
-
- return paravirt_wrmsr_regs(gprs);
-}
static inline u64 paravirt_read_tsc(void)
{
high = _l >> 32; \
} while (0)
+#define rdpmcl(counter, val) ((val) = paravirt_read_pmc(counter))
+
static inline unsigned long long paravirt_rdtscp(unsigned int *aux)
{
return PVOP_CALL1(u64, pv_cpu_ops.read_tscp, aux);
static inline void flush_tlb_others(const struct cpumask *cpumask,
struct mm_struct *mm,
- unsigned long va)
+ unsigned long start,
+ unsigned long end)
{
- PVOP_VCALL3(pv_mmu_ops.flush_tlb_others, cpumask, mm, va);
+ PVOP_VCALL4(pv_mmu_ops.flush_tlb_others, cpumask, mm, start, end);
}
static inline int paravirt_pgd_alloc(struct mm_struct *mm)
/* MSR, PMC and TSR operations.
err = 0/-EFAULT. wrmsr returns 0/-EFAULT. */
u64 (*read_msr)(unsigned int msr, int *err);
- int (*rdmsr_regs)(u32 *regs);
int (*write_msr)(unsigned int msr, unsigned low, unsigned high);
- int (*wrmsr_regs)(u32 *regs);
u64 (*read_tsc)(void);
u64 (*read_pmc)(int counter);
void (*flush_tlb_single)(unsigned long addr);
void (*flush_tlb_others)(const struct cpumask *cpus,
struct mm_struct *mm,
- unsigned long va);
+ unsigned long start,
+ unsigned long end);
/* Hooks for allocating and freeing a pagetable top-level */
int (*pgd_alloc)(struct mm_struct *mm);
return has_siblings;
}
- DECLARE_PER_CPU(cpumask_var_t, cpu_sibling_map);
- DECLARE_PER_CPU(cpumask_var_t, cpu_core_map);
+ DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_sibling_map);
+ DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_core_map);
/* cpus sharing the last level cache: */
- DECLARE_PER_CPU(cpumask_var_t, cpu_llc_shared_map);
- DECLARE_PER_CPU(u16, cpu_llc_id);
- DECLARE_PER_CPU(int, cpu_number);
+ DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_llc_shared_map);
+ DECLARE_PER_CPU_READ_MOSTLY(u16, cpu_llc_id);
+ DECLARE_PER_CPU_READ_MOSTLY(int, cpu_number);
static inline struct cpumask *cpu_sibling_mask(int cpu)
{
return per_cpu(cpu_llc_shared_map, cpu);
}
- DECLARE_EARLY_PER_CPU(u16, x86_cpu_to_apicid);
- DECLARE_EARLY_PER_CPU(u16, x86_bios_cpu_apicid);
+ DECLARE_EARLY_PER_CPU_READ_MOSTLY(u16, x86_cpu_to_apicid);
+ DECLARE_EARLY_PER_CPU_READ_MOSTLY(u16, x86_bios_cpu_apicid);
#if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86_32)
- DECLARE_EARLY_PER_CPU(int, x86_cpu_to_logical_apicid);
+ DECLARE_EARLY_PER_CPU_READ_MOSTLY(int, x86_cpu_to_logical_apicid);
#endif
/* Static state in head.S used to set up a CPU */
void smp_store_cpu_info(int id);
#define cpu_physical_id(cpu) per_cpu(x86_cpu_to_apicid, cpu)
-/* We don't mark CPUs online until __cpu_up(), so we need another measure */
-static inline int num_booting_cpus(void)
-{
- return cpumask_weight(cpu_callout_mask);
-}
#else /* !CONFIG_SMP */
#define wbinvd_on_cpu(cpu) wbinvd()
static inline int wbinvd_on_all_cpus(void)
/*
* Map cpu index to physical APIC ID
*/
- DEFINE_EARLY_PER_CPU(u16, x86_cpu_to_apicid, BAD_APICID);
- DEFINE_EARLY_PER_CPU(u16, x86_bios_cpu_apicid, BAD_APICID);
+ DEFINE_EARLY_PER_CPU_READ_MOSTLY(u16, x86_cpu_to_apicid, BAD_APICID);
+ DEFINE_EARLY_PER_CPU_READ_MOSTLY(u16, x86_bios_cpu_apicid, BAD_APICID);
EXPORT_EARLY_PER_CPU_SYMBOL(x86_cpu_to_apicid);
EXPORT_EARLY_PER_CPU_SYMBOL(x86_bios_cpu_apicid);
* used for the mapping. This is where the behaviors of x86_64 and 32
* actually diverge. Let's keep it ugly for now.
*/
- DEFINE_EARLY_PER_CPU(int, x86_cpu_to_logical_apicid, BAD_APICID);
+ DEFINE_EARLY_PER_CPU_READ_MOSTLY(int, x86_cpu_to_logical_apicid, BAD_APICID);
/*
* Knob to control our willingness to enable the local APIC.
apic_write(APIC_LDR, val);
}
+int default_cpu_mask_to_apicid_and(const struct cpumask *cpumask,
+ const struct cpumask *andmask,
+ unsigned int *apicid)
+{
+ unsigned int cpu;
+
+ for_each_cpu_and(cpu, cpumask, andmask) {
+ if (cpumask_test_cpu(cpu, cpu_online_mask))
+ break;
+ }
+
+ if (likely(cpu < nr_cpu_ids)) {
+ *apicid = per_cpu(x86_cpu_to_apicid, cpu);
+ return 0;
+ }
+
+ return -EINVAL;
+}
+
+/*
+ * Override the generic EOI implementation with an optimized version.
+ * Only called during early boot when only one CPU is active and with
+ * interrupts disabled, so we know this does not race with actual APIC driver
+ * use.
+ */
+void __init apic_set_eoi_write(void (*eoi_write)(u32 reg, u32 v))
+{
+ struct apic **drv;
+
+ for (drv = __apicdrivers; drv < __apicdrivers_end; drv++) {
+ /* Should happen once for each apic */
+ WARN_ON((*drv)->eoi_write == eoi_write);
+ (*drv)->eoi_write = eoi_write;
+ }
+}
+
/*
* Power management
*/
c->x86_cache_size = l2size;
}
+ u16 __read_mostly tlb_lli_4k[NR_INFO];
+ u16 __read_mostly tlb_lli_2m[NR_INFO];
+ u16 __read_mostly tlb_lli_4m[NR_INFO];
+ u16 __read_mostly tlb_lld_4k[NR_INFO];
+ u16 __read_mostly tlb_lld_2m[NR_INFO];
+ u16 __read_mostly tlb_lld_4m[NR_INFO];
+
+ /*
+ * tlb_flushall_shift shows the balance point in replacing cr3 write
+ * with multiple 'invlpg'. It will do this replacement when
+ * flush_tlb_lines <= active_lines/2^tlb_flushall_shift.
+ * If tlb_flushall_shift is -1, means the replacement will be disabled.
+ */
+ s8 __read_mostly tlb_flushall_shift = -1;
+
+ void __cpuinit cpu_detect_tlb(struct cpuinfo_x86 *c)
+ {
+ if (this_cpu->c_detect_tlb)
+ this_cpu->c_detect_tlb(c);
+
+ printk(KERN_INFO "Last level iTLB entries: 4KB %d, 2MB %d, 4MB %d\n" \
+ "Last level dTLB entries: 4KB %d, 2MB %d, 4MB %d\n" \
+ "tlb_flushall_shift is 0x%x\n",
+ tlb_lli_4k[ENTRIES], tlb_lli_2m[ENTRIES],
+ tlb_lli_4m[ENTRIES], tlb_lld_4k[ENTRIES],
+ tlb_lld_2m[ENTRIES], tlb_lld_4m[ENTRIES],
+ tlb_flushall_shift);
+ }
+
void __cpuinit detect_ht(struct cpuinfo_x86 *c)
{
#ifdef CONFIG_X86_HT
#else
vgetcpu_set_mode();
#endif
+ if (boot_cpu_data.cpuid_level >= 2)
+ cpu_detect_tlb(&boot_cpu_data);
}
void __cpuinit identify_secondary_cpu(struct cpuinfo_x86 *c)
index_max = msr_range_array[i].max;
for (index = index_min; index < index_max; index++) {
- if (rdmsrl_amd_safe(index, &val))
+ if (rdmsrl_safe(index, &val))
continue;
printk(KERN_INFO " MSR%08x: %016llx\n", index, val);
}
apicinterrupt X86_PLATFORM_IPI_VECTOR \
x86_platform_ipi smp_x86_platform_ipi
- #ifdef CONFIG_SMP
- ALIGN
- INTR_FRAME
- .irp idx,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15, \
- 16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31
- .if NUM_INVALIDATE_TLB_VECTORS > \idx
- ENTRY(invalidate_interrupt\idx)
- pushq_cfi $~(INVALIDATE_TLB_VECTOR_START+\idx)
- jmp .Lcommon_invalidate_interrupt0
- CFI_ADJUST_CFA_OFFSET -8
- END(invalidate_interrupt\idx)
- .endif
- .endr
- CFI_ENDPROC
- apicinterrupt INVALIDATE_TLB_VECTOR_START, \
- invalidate_interrupt0, smp_invalidate_interrupt
- #endif
-
apicinterrupt THRESHOLD_APIC_VECTOR \
threshold_interrupt smp_threshold_interrupt
apicinterrupt THERMAL_APIC_VECTOR \
*/
call save_paranoid
DEFAULT_FRAME 0
+
+ /*
+ * Save off the CR2 register. If we take a page fault in the NMI then
+ * it could corrupt the CR2 value. If the NMI preempts a page fault
+ * handler before it was able to read the CR2 register, and then the
+ * NMI itself takes a page fault, the page fault that was preempted
+ * will read the information from the NMI page fault and not the
+ * origin fault. Save it off and restore it if it changes.
+ * Use the r12 callee-saved register.
+ */
+ movq %cr2, %r12
+
/* paranoidentry do_nmi, 0; without TRACE_IRQS_OFF */
movq %rsp,%rdi
movq $-1,%rsi
call do_nmi
+
+ /* Did the NMI take a page fault? Restore cr2 if it did */
+ movq %cr2, %rcx
+ cmpq %rcx, %r12
+ je 1f
+ movq %r12, %cr2
+1:
+
testl %ebx,%ebx /* swapgs needed? */
jnz nmi_restore
nmi_swapgs:
-/*
+ /*
* x86 SMP booting functions
*
* (c) 1995 Alan Cox, Building #3 <alan@lxorguk.ukuu.org.uk>
* Glauber Costa : i386 and x86_64 integration
*/
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
#include <linux/init.h>
#include <linux/smp.h>
#include <linux/module.h>
EXPORT_SYMBOL(smp_num_siblings);
/* Last level cache ID of each logical CPU */
- DEFINE_PER_CPU(u16, cpu_llc_id) = BAD_APICID;
+ DEFINE_PER_CPU_READ_MOSTLY(u16, cpu_llc_id) = BAD_APICID;
/* representing HT siblings of each logical CPU */
- DEFINE_PER_CPU(cpumask_var_t, cpu_sibling_map);
+ DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_sibling_map);
EXPORT_PER_CPU_SYMBOL(cpu_sibling_map);
/* representing HT and core siblings of each logical CPU */
- DEFINE_PER_CPU(cpumask_var_t, cpu_core_map);
+ DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_core_map);
EXPORT_PER_CPU_SYMBOL(cpu_core_map);
- DEFINE_PER_CPU(cpumask_var_t, cpu_llc_shared_map);
+ DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_llc_shared_map);
/* Per CPU bogomips and other parameters */
DEFINE_PER_CPU_SHARED_ALIGNED(struct cpuinfo_x86, cpu_info);
* boards)
*/
- pr_debug("CALLIN, before setup_local_APIC().\n");
+ pr_debug("CALLIN, before setup_local_APIC()\n");
if (apic->smp_callin_clear_local_apic)
apic->smp_callin_clear_local_apic();
setup_local_APIC();
check_tsc_sync_target();
/*
- * We need to hold call_lock, so there is no inconsistency
- * between the time smp_call_function() determines number of
- * IPI recipients, and the time when the determination is made
- * for which cpus receive the IPI. Holding this
- * lock helps us to not include this cpu in a currently in progress
- * smp_call_function().
- *
* We need to hold vector_lock so there the set of online cpus
* does not change while we are assigning vectors to cpus. Holding
* this lock ensures we don't half assign or remove an irq from a cpu.
*/
- ipi_call_lock();
lock_vector_lock();
set_cpu_online(smp_processor_id(), true);
unlock_vector_lock();
- ipi_call_unlock();
per_cpu(cpu_state, smp_processor_id()) = CPU_ONLINE;
x86_platform.nmi_init();
static bool __cpuinit match_mc(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
{
- if (c->phys_proc_id == o->phys_proc_id)
- return topology_sane(c, o, "mc");
+ if (c->phys_proc_id == o->phys_proc_id) {
+ if (cpu_has(c, X86_FEATURE_AMD_DCM))
+ return true;
+ return topology_sane(c, o, "mc");
+ }
return false;
}
/*
* Allow the user to impress friends.
*/
- pr_debug("Before bogomips.\n");
+ pr_debug("Before bogomips\n");
for_each_possible_cpu(cpu)
if (cpumask_test_cpu(cpu, cpu_callout_mask))
bogosum += cpu_data(cpu).loops_per_jiffy;
- printk(KERN_INFO
- "Total of %d processors activated (%lu.%02lu BogoMIPS).\n",
+ pr_info("Total of %d processors activated (%lu.%02lu BogoMIPS)\n",
num_online_cpus(),
bogosum/(500000/HZ),
(bogosum/(5000/HZ))%100);
- pr_debug("Before bogocount - setting activated=1.\n");
+ pr_debug("Before bogocount - setting activated=1\n");
}
void __inquire_remote_apic(int apicid)
int timeout;
u32 status;
- printk(KERN_INFO "Inquiring remote APIC 0x%x...\n", apicid);
+ pr_info("Inquiring remote APIC 0x%x...\n", apicid);
for (i = 0; i < ARRAY_SIZE(regs); i++) {
- printk(KERN_INFO "... APIC 0x%x %s: ", apicid, names[i]);
+ pr_info("... APIC 0x%x %s: ", apicid, names[i]);
/*
* Wait for idle.
*/
status = safe_apic_wait_icr_idle();
if (status)
- printk(KERN_CONT
- "a previous APIC delivery may have failed\n");
+ pr_cont("a previous APIC delivery may have failed\n");
apic_icr_write(APIC_DM_REMRD | regs[i], apicid);
switch (status) {
case APIC_ICR_RR_VALID:
status = apic_read(APIC_RRR);
- printk(KERN_CONT "%08x\n", status);
+ pr_cont("%08x\n", status);
break;
default:
- printk(KERN_CONT "failed\n");
+ pr_cont("failed\n");
}
}
}
apic_write(APIC_ESR, 0);
accept_status = (apic_read(APIC_ESR) & 0xEF);
}
- pr_debug("NMI sent.\n");
+ pr_debug("NMI sent\n");
if (send_status)
- printk(KERN_ERR "APIC never delivered???\n");
+ pr_err("APIC never delivered???\n");
if (accept_status)
- printk(KERN_ERR "APIC delivery error (%lx).\n", accept_status);
+ pr_err("APIC delivery error (%lx)\n", accept_status);
return (send_status | accept_status);
}
apic_read(APIC_ESR);
}
- pr_debug("Asserting INIT.\n");
+ pr_debug("Asserting INIT\n");
/*
* Turn INIT on target chip
mdelay(10);
- pr_debug("Deasserting INIT.\n");
+ pr_debug("Deasserting INIT\n");
/* Target chip */
/* Send IPI */
/*
* Run STARTUP IPI loop.
*/
- pr_debug("#startup loops: %d.\n", num_starts);
+ pr_debug("#startup loops: %d\n", num_starts);
for (j = 1; j <= num_starts; j++) {
- pr_debug("Sending STARTUP #%d.\n", j);
+ pr_debug("Sending STARTUP #%d\n", j);
if (maxlvt > 3) /* Due to the Pentium erratum 3AP. */
apic_write(APIC_ESR, 0);
apic_read(APIC_ESR);
- pr_debug("After apic_write.\n");
+ pr_debug("After apic_write\n");
/*
* STARTUP IPI
*/
udelay(300);
- pr_debug("Startup point 1.\n");
+ pr_debug("Startup point 1\n");
pr_debug("Waiting for send to finish...\n");
send_status = safe_apic_wait_icr_idle();
if (send_status || accept_status)
break;
}
- pr_debug("After Startup.\n");
+ pr_debug("After Startup\n");
if (send_status)
- printk(KERN_ERR "APIC never delivered???\n");
+ pr_err("APIC never delivered???\n");
if (accept_status)
- printk(KERN_ERR "APIC delivery error (%lx).\n", accept_status);
+ pr_err("APIC delivery error (%lx)\n", accept_status);
return (send_status | accept_status);
}
if (system_state == SYSTEM_BOOTING) {
if (node != current_node) {
if (current_node > (-1))
- pr_cont(" Ok.\n");
+ pr_cont(" OK\n");
current_node = node;
pr_info("Booting Node %3d, Processors ", node);
}
- pr_cont(" #%d%s", cpu, cpu == (nr_cpu_ids - 1) ? " Ok.\n" : "");
+ pr_cont(" #%d%s", cpu, cpu == (nr_cpu_ids - 1) ? " OK\n" : "");
return;
} else
pr_info("Booting Node %d Processor %d APIC 0x%x\n",
/*
* allow APs to start initializing.
*/
- pr_debug("Before Callout %d.\n", cpu);
+ pr_debug("Before Callout %d\n", cpu);
cpumask_set_cpu(cpu, cpu_callout_mask);
- pr_debug("After Callout %d.\n", cpu);
+ pr_debug("After Callout %d\n", cpu);
/*
* Wait 5s total for a response
pr_err("CPU%d: Stuck ??\n", cpu);
else
/* trampoline code not run */
- pr_err("CPU%d: Not responding.\n", cpu);
+ pr_err("CPU%d: Not responding\n", cpu);
if (apic->inquire_remote_apic)
apic->inquire_remote_apic(apicid);
}
if (apicid == BAD_APICID || apicid == boot_cpu_physical_apicid ||
!physid_isset(apicid, phys_cpu_present_map) ||
!apic->apic_id_valid(apicid)) {
- printk(KERN_ERR "%s: bad cpu %d\n", __func__, cpu);
+ pr_err("%s: bad cpu %d\n", __func__, cpu);
return -EINVAL;
}
unsigned int cpu;
unsigned nr;
- printk(KERN_WARNING
- "More than 8 CPUs detected - skipping them.\n"
- "Use CONFIG_X86_BIGSMP.\n");
+ pr_warn("More than 8 CPUs detected - skipping them\n"
+ "Use CONFIG_X86_BIGSMP\n");
nr = 0;
for_each_present_cpu(cpu) {
#endif
if (!physid_isset(hard_smp_processor_id(), phys_cpu_present_map)) {
- printk(KERN_WARNING
- "weird, boot CPU (#%d) not listed by the BIOS.\n",
+ pr_warn("weird, boot CPU (#%d) not listed by the BIOS\n",
hard_smp_processor_id());
physid_set(hard_smp_processor_id(), phys_cpu_present_map);
*/
if (!smp_found_config && !acpi_lapic) {
preempt_enable();
- printk(KERN_NOTICE "SMP motherboard not detected.\n");
+ pr_notice("SMP motherboard not detected\n");
disable_smp();
if (APIC_init_uniprocessor())
- printk(KERN_NOTICE "Local APIC not detected."
- " Using dummy APIC emulation.\n");
+ pr_notice("Local APIC not detected. Using dummy APIC emulation.\n");
return -1;
}
* CPU too, but we do it for the sake of robustness anyway.
*/
if (!apic->check_phys_apicid_present(boot_cpu_physical_apicid)) {
- printk(KERN_NOTICE
- "weird, boot CPU (#%d) not listed by the BIOS.\n",
- boot_cpu_physical_apicid);
+ pr_notice("weird, boot CPU (#%d) not listed by the BIOS\n",
+ boot_cpu_physical_apicid);
physid_set(hard_smp_processor_id(), phys_cpu_present_map);
}
preempt_enable();
if (!disable_apic) {
pr_err("BIOS bug, local APIC #%d not detected!...\n",
boot_cpu_physical_apicid);
- pr_err("... forcing use of dummy APIC emulation."
- "(tell your hw vendor)\n");
+ pr_err("... forcing use of dummy APIC emulation (tell your hw vendor)\n");
}
smpboot_clear_io_apic();
disable_ioapic_support();
* If SMP should be disabled, then really disable it!
*/
if (!max_cpus) {
- printk(KERN_INFO "SMP mode deactivated.\n");
+ pr_info("SMP mode deactivated\n");
smpboot_clear_io_apic();
connect_bsp_APIC();
if (smp_sanity_check(max_cpus) < 0) {
- printk(KERN_INFO "SMP disabled\n");
+ pr_info("SMP disabled\n");
disable_smp();
goto out;
}
* Set up local APIC timer on boot CPU.
*/
- printk(KERN_INFO "CPU%d: ", 0);
+ pr_info("CPU%d: ", 0);
print_cpu_info(&cpu_data(0));
x86_init.timers.setup_percpu_clockev();
void __init native_smp_cpus_done(unsigned int max_cpus)
{
- pr_debug("Boot done.\n");
+ pr_debug("Boot done\n");
nmi_selftest();
impress_friends();
/* nr_cpu_ids could be reduced via nr_cpus= */
if (possible > nr_cpu_ids) {
- printk(KERN_WARNING
- "%d Processors exceeds NR_CPUS limit of %d\n",
+ pr_warn("%d Processors exceeds NR_CPUS limit of %d\n",
possible, nr_cpu_ids);
possible = nr_cpu_ids;
}
if (!setup_max_cpus)
#endif
if (possible > i) {
- printk(KERN_WARNING
- "%d Processors exceeds max_cpus limit of %u\n",
+ pr_warn("%d Processors exceeds max_cpus limit of %u\n",
possible, setup_max_cpus);
possible = i;
}
- printk(KERN_INFO "SMP: Allowing %d CPUs, %d hotplug CPUs\n",
+ pr_info("Allowing %d CPUs, %d hotplug CPUs\n",
possible, max_t(int, possible - num_processors, 0));
for (i = 0; i < possible; i++)
/*
* SGI UltraViolet TLB flush routines.
*
- * (c) 2008-2011 Cliff Wickman <cpw@sgi.com>, SGI.
+ * (c) 2008-2012 Cliff Wickman <cpw@sgi.com>, SGI.
*
* This code is released under the GNU General Public License version 2 or
* later.
static int timeout_us;
static int nobau;
-static int baudisabled;
-static spinlock_t disable_lock;
+static int nobau_perm;
static cycles_t congested_cycles;
/* tunables: */
static int max_concurr_const = MAX_BAU_CONCURRENT;
static int plugged_delay = PLUGGED_DELAY;
static int plugsb4reset = PLUGSB4RESET;
+static int giveup_limit = GIVEUP_LIMIT;
static int timeoutsb4reset = TIMEOUTSB4RESET;
static int ipi_reset_limit = IPI_RESET_LIMIT;
static int complete_threshold = COMPLETE_THRESHOLD;
static int congested_respns_us = CONGESTED_RESPONSE_US;
static int congested_reps = CONGESTED_REPS;
-static int congested_period = CONGESTED_PERIOD;
+static int disabled_period = DISABLED_PERIOD;
static struct tunables tunables[] = {
{&max_concurr, MAX_BAU_CONCURRENT}, /* must be [0] */
{&complete_threshold, COMPLETE_THRESHOLD},
{&congested_respns_us, CONGESTED_RESPONSE_US},
{&congested_reps, CONGESTED_REPS},
- {&congested_period, CONGESTED_PERIOD}
+ {&disabled_period, DISABLED_PERIOD},
+ {&giveup_limit, GIVEUP_LIMIT}
};
static struct dentry *tunables_dir;
static DEFINE_PER_CPU(struct bau_control, bau_control);
static DEFINE_PER_CPU(cpumask_var_t, uv_flush_tlb_mask);
+static void
+set_bau_on(void)
+{
+ int cpu;
+ struct bau_control *bcp;
+
+ if (nobau_perm) {
+ pr_info("BAU not initialized; cannot be turned on\n");
+ return;
+ }
+ nobau = 0;
+ for_each_present_cpu(cpu) {
+ bcp = &per_cpu(bau_control, cpu);
+ bcp->nobau = 0;
+ }
+ pr_info("BAU turned on\n");
+ return;
+}
+
+static void
+set_bau_off(void)
+{
+ int cpu;
+ struct bau_control *bcp;
+
+ nobau = 1;
+ for_each_present_cpu(cpu) {
+ bcp = &per_cpu(bau_control, cpu);
+ bcp->nobau = 1;
+ }
+ pr_info("BAU turned off\n");
+ return;
+}
+
/*
* Determine the first node on a uvhub. 'Nodes' are used for kernel
* memory allocation.
* Both sockets dump their completed count total into
* the message's count.
*/
- smaster->socket_acknowledge_count[mdp->msg_slot] = 0;
+ *sp = 0;
asp = (struct atomic_short *)&msg->acknowledge_count;
msg_ack_count = atom_asr(socket_ack_count, asp);
}
/*
- * UV2 has an extra bit of status in the ACTIVATION_STATUS_2 register.
+ * UV2 could have an extra bit of status in the ACTIVATION_STATUS_2 register.
+ * But not currently used.
*/
static unsigned long uv2_read_status(unsigned long offset, int rshft, int desc)
{
unsigned long descriptor_status;
- unsigned long descriptor_status2;
- descriptor_status = ((read_lmmr(offset) >> rshft) & UV_ACT_STATUS_MASK);
- descriptor_status2 = (read_mmr_uv2_status() >> desc) & 0x1UL;
- descriptor_status = (descriptor_status << 1) | descriptor_status2;
+ descriptor_status =
+ ((read_lmmr(offset) >> rshft) & UV_ACT_STATUS_MASK) << 1;
return descriptor_status;
}
*/
int handle_uv2_busy(struct bau_control *bcp)
{
- int busy_one = bcp->using_desc;
- int normal = bcp->uvhub_cpu;
- int selected = -1;
- int i;
- unsigned long descriptor_status;
- unsigned long status;
- int mmr_offset;
- struct bau_desc *bau_desc_old;
- struct bau_desc *bau_desc_new;
- struct bau_control *hmaster = bcp->uvhub_master;
struct ptc_stats *stat = bcp->statp;
- cycles_t ttm;
stat->s_uv2_wars++;
- spin_lock(&hmaster->uvhub_lock);
- /* try for the original first */
- if (busy_one != normal) {
- if (!normal_busy(bcp))
- selected = normal;
- }
- if (selected < 0) {
- /* can't use the normal, select an alternate */
- mmr_offset = UVH_LB_BAU_SB_ACTIVATION_STATUS_1;
- descriptor_status = read_lmmr(mmr_offset);
-
- /* scan available descriptors 32-63 */
- for (i = 0; i < UV_CPUS_PER_AS; i++) {
- if ((hmaster->inuse_map & (1 << i)) == 0) {
- status = ((descriptor_status >>
- (i * UV_ACT_STATUS_SIZE)) &
- UV_ACT_STATUS_MASK) << 1;
- if (status != UV2H_DESC_BUSY) {
- selected = i + UV_CPUS_PER_AS;
- break;
- }
- }
- }
- }
-
- if (busy_one != normal)
- /* mark the busy alternate as not in-use */
- hmaster->inuse_map &= ~(1 << (busy_one - UV_CPUS_PER_AS));
-
- if (selected >= 0) {
- /* switch to the selected descriptor */
- if (selected != normal) {
- /* set the selected alternate as in-use */
- hmaster->inuse_map |=
- (1 << (selected - UV_CPUS_PER_AS));
- if (selected > stat->s_uv2_wars_hw)
- stat->s_uv2_wars_hw = selected;
- }
- bau_desc_old = bcp->descriptor_base;
- bau_desc_old += (ITEMS_PER_DESC * busy_one);
- bcp->using_desc = selected;
- bau_desc_new = bcp->descriptor_base;
- bau_desc_new += (ITEMS_PER_DESC * selected);
- *bau_desc_new = *bau_desc_old;
- } else {
- /*
- * All are busy. Wait for the normal one for this cpu to
- * free up.
- */
- stat->s_uv2_war_waits++;
- spin_unlock(&hmaster->uvhub_lock);
- ttm = get_cycles();
- do {
- cpu_relax();
- } while (normal_busy(bcp));
- spin_lock(&hmaster->uvhub_lock);
- /* switch to the original descriptor */
- bcp->using_desc = normal;
- bau_desc_old = bcp->descriptor_base;
- bau_desc_old += (ITEMS_PER_DESC * bcp->using_desc);
- bcp->using_desc = (ITEMS_PER_DESC * normal);
- bau_desc_new = bcp->descriptor_base;
- bau_desc_new += (ITEMS_PER_DESC * normal);
- *bau_desc_new = *bau_desc_old; /* copy the entire descriptor */
- }
- spin_unlock(&hmaster->uvhub_lock);
- return FLUSH_RETRY_BUSYBUG;
+ bcp->busy = 1;
+ return FLUSH_GIVEUP;
}
static int uv2_wait_completion(struct bau_desc *bau_desc,
{
unsigned long descriptor_stat;
cycles_t ttm;
- int desc = bcp->using_desc;
+ int desc = bcp->uvhub_cpu;
long busy_reps = 0;
struct ptc_stats *stat = bcp->statp;
/* spin on the status MMR, waiting for it to go idle */
while (descriptor_stat != UV2H_DESC_IDLE) {
- /*
- * Our software ack messages may be blocked because
- * there are no swack resources available. As long
- * as none of them has timed out hardware will NACK
- * our message and its state will stay IDLE.
- */
- if ((descriptor_stat == UV2H_DESC_SOURCE_TIMEOUT) ||
- (descriptor_stat == UV2H_DESC_DEST_PUT_ERR)) {
+ if ((descriptor_stat == UV2H_DESC_SOURCE_TIMEOUT)) {
+ /*
+ * A h/w bug on the destination side may
+ * have prevented the message being marked
+ * pending, thus it doesn't get replied to
+ * and gets continually nacked until it times
+ * out with a SOURCE_TIMEOUT.
+ */
stat->s_stimeout++;
return FLUSH_GIVEUP;
- } else if (descriptor_stat == UV2H_DESC_DEST_STRONG_NACK) {
- stat->s_strongnacks++;
- bcp->conseccompletes = 0;
- return FLUSH_GIVEUP;
} else if (descriptor_stat == UV2H_DESC_DEST_TIMEOUT) {
+ ttm = get_cycles();
+
+ /*
+ * Our retries may be blocked by all destination
+ * swack resources being consumed, and a timeout
+ * pending. In that case hardware returns the
+ * ERROR that looks like a destination timeout.
+ * Without using the extended status we have to
+ * deduce from the short time that this was a
+ * strong nack.
+ */
+ if (cycles_2_us(ttm - bcp->send_message) < timeout_us) {
+ bcp->conseccompletes = 0;
+ stat->s_plugged++;
+ /* FLUSH_RETRY_PLUGGED causes hang on boot */
+ return FLUSH_GIVEUP;
+ }
stat->s_dtimeout++;
bcp->conseccompletes = 0;
- return FLUSH_RETRY_TIMEOUT;
+ /* FLUSH_RETRY_TIMEOUT causes hang on boot */
+ return FLUSH_GIVEUP;
} else {
busy_reps++;
if (busy_reps > 1000000) {
busy_reps = 0;
ttm = get_cycles();
if ((ttm - bcp->send_message) >
- (bcp->clocks_per_100_usec)) {
+ bcp->timeout_interval)
return handle_uv2_busy(bcp);
- }
}
/*
* descriptor_stat is still BUSY
{
int right_shift;
unsigned long mmr_offset;
- int desc = bcp->using_desc;
+ int desc = bcp->uvhub_cpu;
if (desc < UV_CPUS_PER_AS) {
mmr_offset = UVH_LB_BAU_SB_ACTIVATION_STATUS_0;
}
/*
- * Completions are taking a very long time due to a congested numalink
- * network.
+ * Stop all cpus on a uvhub from using the BAU for a period of time.
+ * This is reversed by check_enable.
*/
-static void disable_for_congestion(struct bau_control *bcp,
- struct ptc_stats *stat)
+static void disable_for_period(struct bau_control *bcp, struct ptc_stats *stat)
{
- /* let only one cpu do this disabling */
- spin_lock(&disable_lock);
-
- if (!baudisabled && bcp->period_requests &&
- ((bcp->period_time / bcp->period_requests) > congested_cycles)) {
- int tcpu;
- struct bau_control *tbcp;
- /* it becomes this cpu's job to turn on the use of the
- BAU again */
- baudisabled = 1;
- bcp->set_bau_off = 1;
- bcp->set_bau_on_time = get_cycles();
- bcp->set_bau_on_time += sec_2_cycles(bcp->cong_period);
+ int tcpu;
+ struct bau_control *tbcp;
+ struct bau_control *hmaster;
+ cycles_t tm1;
+
+ hmaster = bcp->uvhub_master;
+ spin_lock(&hmaster->disable_lock);
+ if (!bcp->baudisabled) {
stat->s_bau_disabled++;
+ tm1 = get_cycles();
for_each_present_cpu(tcpu) {
tbcp = &per_cpu(bau_control, tcpu);
- tbcp->baudisabled = 1;
+ if (tbcp->uvhub_master == hmaster) {
+ tbcp->baudisabled = 1;
+ tbcp->set_bau_on_time =
+ tm1 + bcp->disabled_period;
+ }
}
}
-
- spin_unlock(&disable_lock);
+ spin_unlock(&hmaster->disable_lock);
}
static void count_max_concurr(int stat, struct bau_control *bcp,
bcp->period_requests++;
bcp->period_time += elapsed;
if ((elapsed > congested_cycles) &&
- (bcp->period_requests > bcp->cong_reps))
- disable_for_congestion(bcp, stat);
+ (bcp->period_requests > bcp->cong_reps) &&
+ ((bcp->period_time / bcp->period_requests) >
+ congested_cycles)) {
+ stat->s_congested++;
+ disable_for_period(bcp, stat);
+ }
}
} else
stat->s_requestor--;
if (completion_status == FLUSH_COMPLETE && try > 1)
stat->s_retriesok++;
- else if (completion_status == FLUSH_GIVEUP)
+ else if (completion_status == FLUSH_GIVEUP) {
stat->s_giveup++;
+ if (get_cycles() > bcp->period_end)
+ bcp->period_giveups = 0;
+ bcp->period_giveups++;
+ if (bcp->period_giveups == 1)
+ bcp->period_end = get_cycles() + bcp->disabled_period;
+ if (bcp->period_giveups > bcp->giveup_limit) {
+ disable_for_period(bcp, stat);
+ stat->s_giveuplimit++;
+ }
+ }
}
/*
* Returns 1 if it gives up entirely and the original cpu mask is to be
* returned to the kernel.
*/
-int uv_flush_send_and_wait(struct cpumask *flush_mask, struct bau_control *bcp)
+int uv_flush_send_and_wait(struct cpumask *flush_mask, struct bau_control *bcp,
+ struct bau_desc *bau_desc)
{
int seq_number = 0;
int completion_stat = 0;
struct bau_control *hmaster = bcp->uvhub_master;
struct uv1_bau_msg_header *uv1_hdr = NULL;
struct uv2_bau_msg_header *uv2_hdr = NULL;
- struct bau_desc *bau_desc;
- if (bcp->uvhub_version == 1)
+ if (bcp->uvhub_version == 1) {
+ uv1 = 1;
uv1_throttle(hmaster, stat);
+ }
while (hmaster->uvhub_quiesce)
cpu_relax();
time1 = get_cycles();
+ if (uv1)
+ uv1_hdr = &bau_desc->header.uv1_hdr;
+ else
+ uv2_hdr = &bau_desc->header.uv2_hdr;
+
do {
- bau_desc = bcp->descriptor_base;
- bau_desc += (ITEMS_PER_DESC * bcp->using_desc);
- if (bcp->uvhub_version == 1) {
- uv1 = 1;
- uv1_hdr = &bau_desc->header.uv1_hdr;
- } else
- uv2_hdr = &bau_desc->header.uv2_hdr;
- if ((try == 0) || (completion_stat == FLUSH_RETRY_BUSYBUG)) {
+ if (try == 0) {
if (uv1)
uv1_hdr->msg_type = MSG_REGULAR;
else
uv1_hdr->sequence = seq_number;
else
uv2_hdr->sequence = seq_number;
- index = (1UL << AS_PUSH_SHIFT) | bcp->using_desc;
+ index = (1UL << AS_PUSH_SHIFT) | bcp->uvhub_cpu;
bcp->send_message = get_cycles();
write_mmr_activation(index);
try++;
completion_stat = wait_completion(bau_desc, bcp, try);
- /* UV2: wait_completion() may change the bcp->using_desc */
handle_cmplt(completion_stat, bau_desc, bcp, hmaster, stat);
if (bcp->ipi_attempts >= bcp->ipi_reset_limit) {
bcp->ipi_attempts = 0;
+ stat->s_overipilimit++;
completion_stat = FLUSH_GIVEUP;
break;
}
cpu_relax();
} while ((completion_stat == FLUSH_RETRY_PLUGGED) ||
- (completion_stat == FLUSH_RETRY_BUSYBUG) ||
(completion_stat == FLUSH_RETRY_TIMEOUT));
time2 = get_cycles();
}
/*
- * The BAU is disabled. When the disabled time period has expired, the cpu
- * that disabled it must re-enable it.
- * Return 0 if it is re-enabled for all cpus.
+ * The BAU is disabled for this uvhub. When the disabled time period has
+ * expired re-enable it.
+ * Return 0 if it is re-enabled for all cpus on this uvhub.
*/
static int check_enable(struct bau_control *bcp, struct ptc_stats *stat)
{
int tcpu;
struct bau_control *tbcp;
+ struct bau_control *hmaster;
- if (bcp->set_bau_off) {
- if (get_cycles() >= bcp->set_bau_on_time) {
- stat->s_bau_reenabled++;
- baudisabled = 0;
- for_each_present_cpu(tcpu) {
- tbcp = &per_cpu(bau_control, tcpu);
+ hmaster = bcp->uvhub_master;
+ spin_lock(&hmaster->disable_lock);
+ if (bcp->baudisabled && (get_cycles() >= bcp->set_bau_on_time)) {
+ stat->s_bau_reenabled++;
+ for_each_present_cpu(tcpu) {
+ tbcp = &per_cpu(bau_control, tcpu);
+ if (tbcp->uvhub_master == hmaster) {
tbcp->baudisabled = 0;
tbcp->period_requests = 0;
tbcp->period_time = 0;
+ tbcp->period_giveups = 0;
}
- return 0;
}
+ spin_unlock(&hmaster->disable_lock);
+ return 0;
}
+ spin_unlock(&hmaster->disable_lock);
return -1;
}
* done. The returned pointer is valid till preemption is re-enabled.
*/
const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask,
- struct mm_struct *mm, unsigned long va,
- unsigned int cpu)
+ struct mm_struct *mm, unsigned long start,
+ unsigned end, unsigned int cpu)
{
int locals = 0;
int remotes = 0;
struct cpumask *flush_mask;
struct ptc_stats *stat;
struct bau_control *bcp;
-
- /* kernel was booted 'nobau' */
- if (nobau)
- return cpumask;
+ unsigned long descriptor_status;
+ unsigned long status;
bcp = &per_cpu(bau_control, cpu);
stat = bcp->statp;
+ stat->s_enters++;
+
+ if (bcp->nobau)
+ return cpumask;
+
+ if (bcp->busy) {
+ descriptor_status =
+ read_lmmr(UVH_LB_BAU_SB_ACTIVATION_STATUS_0);
+ status = ((descriptor_status >> (bcp->uvhub_cpu *
+ UV_ACT_STATUS_SIZE)) & UV_ACT_STATUS_MASK) << 1;
+ if (status == UV2H_DESC_BUSY)
+ return cpumask;
+ bcp->busy = 0;
+ }
/* bau was disabled due to slow response */
if (bcp->baudisabled) {
- if (check_enable(bcp, stat))
+ if (check_enable(bcp, stat)) {
+ stat->s_ipifordisabled++;
return cpumask;
+ }
}
/*
stat->s_ntargself++;
bau_desc = bcp->descriptor_base;
- bau_desc += (ITEMS_PER_DESC * bcp->using_desc);
+ bau_desc += (ITEMS_PER_DESC * bcp->uvhub_cpu);
bau_uvhubs_clear(&bau_desc->distribution, UV_DISTRIBUTION_SIZE);
if (set_distrib_bits(flush_mask, bcp, bau_desc, &locals, &remotes))
return NULL;
record_send_statistics(stat, locals, hubs, remotes, bau_desc);
- bau_desc->payload.address = va;
+ bau_desc->payload.address = start;
bau_desc->payload.sending_cpu = cpu;
/*
* uv_flush_send_and_wait returns 0 if all cpu's were messaged,
* or 1 if it gave up and the original cpumask should be returned.
*/
- if (!uv_flush_send_and_wait(flush_mask, bcp))
+ if (!uv_flush_send_and_wait(flush_mask, bcp, bau_desc))
return NULL;
else
return cpumask;
}
/*
- * Search the message queue for any 'other' message with the same software
- * acknowledge resource bit vector.
+ * Search the message queue for any 'other' unprocessed message with the
+ * same software acknowledge resource bit vector as the 'msg' message.
*/
struct bau_pq_entry *find_another_by_swack(struct bau_pq_entry *msg,
- struct bau_control *bcp, unsigned char swack_vec)
+ struct bau_control *bcp)
{
struct bau_pq_entry *msg_next = msg + 1;
+ unsigned char swack_vec = msg->swack_vec;
if (msg_next > bcp->queue_last)
msg_next = bcp->queue_first;
- while ((msg_next->swack_vec != 0) && (msg_next != msg)) {
- if (msg_next->swack_vec == swack_vec)
+ while (msg_next != msg) {
+ if ((msg_next->canceled == 0) && (msg_next->replied_to == 0) &&
+ (msg_next->swack_vec == swack_vec))
return msg_next;
msg_next++;
if (msg_next > bcp->queue_last)
* This message was assigned a swack resource, but no
* reserved acknowlegment is pending.
* The bug has prevented this message from setting the MMR.
- * And no other message has used the same sw_ack resource.
- * Do the requested shootdown but do not reply to the msg.
- * (the 0 means make no acknowledge)
*/
- bau_process_message(mdp, bcp, 0);
- return;
- }
-
- /*
- * Some message has set the MMR 'pending' bit; it might have been
- * another message. Look for that message.
- */
- other_msg = find_another_by_swack(msg, bcp, msg->swack_vec);
- if (other_msg) {
- /* There is another. Do not ack the current one. */
- bau_process_message(mdp, bcp, 0);
/*
- * Let the natural processing of that message acknowledge
- * it. Don't get the processing of sw_ack's out of order.
+ * Some message has set the MMR 'pending' bit; it might have
+ * been another message. Look for that message.
*/
- return;
+ other_msg = find_another_by_swack(msg, bcp);
+ if (other_msg) {
+ /*
+ * There is another. Process this one but do not
+ * ack it.
+ */
+ bau_process_message(mdp, bcp, 0);
+ /*
+ * Let the natural processing of that other message
+ * acknowledge it. Don't get the processing of sw_ack's
+ * out of order.
+ */
+ return;
+ }
}
/*
- * There is no other message using this sw_ack, so it is safe to
- * acknowledge it.
+ * Either the MMR shows this one pending a reply or there is no
+ * other message using this sw_ack, so it is safe to acknowledge it.
*/
bau_process_message(mdp, bcp, 1);
*/
mmr_image |= (1L << SOFTACK_MSHIFT);
if (is_uv2_hub()) {
- mmr_image |= (1L << UV2_EXT_SHFT);
+ /* hw bug workaround; do not use extended status */
+ mmr_image &= ~(1L << UV2_EXT_SHFT);
}
write_mmr_misc_control(pnode, mmr_image);
}
static int ptc_seq_show(struct seq_file *file, void *data)
{
struct ptc_stats *stat;
+ struct bau_control *bcp;
int cpu;
cpu = *(loff_t *)data;
if (!cpu) {
seq_printf(file,
- "# cpu sent stime self locals remotes ncpus localhub ");
+ "# cpu bauoff sent stime self locals remotes ncpus localhub ");
seq_printf(file,
"remotehub numuvhubs numuvhubs16 numuvhubs8 ");
seq_printf(file,
- "numuvhubs4 numuvhubs2 numuvhubs1 dto snacks retries rok ");
+ "numuvhubs4 numuvhubs2 numuvhubs1 dto snacks retries ");
+ seq_printf(file,
+ "rok resetp resett giveup sto bz throt disable ");
seq_printf(file,
- "resetp resett giveup sto bz throt swack recv rtime ");
+ "enable wars warshw warwaits enters ipidis plugged ");
seq_printf(file,
- "all one mult none retry canc nocan reset rcan ");
+ "ipiover glim cong swack recv rtime all one mult ");
seq_printf(file,
- "disable enable wars warshw warwaits\n");
+ "none retry canc nocan reset rcan\n");
}
if (cpu < num_possible_cpus() && cpu_online(cpu)) {
- stat = &per_cpu(ptcstats, cpu);
+ bcp = &per_cpu(bau_control, cpu);
+ stat = bcp->statp;
/* source side statistics */
seq_printf(file,
- "cpu %d %ld %ld %ld %ld %ld %ld %ld %ld %ld %ld ",
- cpu, stat->s_requestor, cycles_2_us(stat->s_time),
+ "cpu %d %d %ld %ld %ld %ld %ld %ld %ld %ld %ld %ld ",
+ cpu, bcp->nobau, stat->s_requestor,
+ cycles_2_us(stat->s_time),
stat->s_ntargself, stat->s_ntarglocals,
stat->s_ntargremotes, stat->s_ntargcpu,
stat->s_ntarglocaluvhub, stat->s_ntargremoteuvhub,
stat->s_resets_plug, stat->s_resets_timeout,
stat->s_giveup, stat->s_stimeout,
stat->s_busy, stat->s_throttles);
+ seq_printf(file, "%ld %ld %ld %ld %ld %ld %ld %ld %ld %ld %ld ",
+ stat->s_bau_disabled, stat->s_bau_reenabled,
+ stat->s_uv2_wars, stat->s_uv2_wars_hw,
+ stat->s_uv2_war_waits, stat->s_enters,
+ stat->s_ipifordisabled, stat->s_plugged,
+ stat->s_overipilimit, stat->s_giveuplimit,
+ stat->s_congested);
/* destination side statistics */
seq_printf(file,
- "%lx %ld %ld %ld %ld %ld %ld %ld %ld %ld %ld %ld ",
+ "%lx %ld %ld %ld %ld %ld %ld %ld %ld %ld %ld %ld\n",
read_gmmr_sw_ack(uv_cpu_to_pnode(cpu)),
stat->d_requestee, cycles_2_us(stat->d_time),
stat->d_alltlb, stat->d_onetlb, stat->d_multmsg,
stat->d_nomsg, stat->d_retries, stat->d_canceled,
stat->d_nocanceled, stat->d_resets,
stat->d_rcanceled);
- seq_printf(file, "%ld %ld %ld %ld %ld\n",
- stat->s_bau_disabled, stat->s_bau_reenabled,
- stat->s_uv2_wars, stat->s_uv2_wars_hw,
- stat->s_uv2_war_waits);
}
return 0;
}
char *buf;
int ret;
- buf = kasprintf(GFP_KERNEL, "%s %s %s\n%d %d %d %d %d %d %d %d %d\n",
- "max_concur plugged_delay plugsb4reset",
- "timeoutsb4reset ipi_reset_limit complete_threshold",
- "congested_response_us congested_reps congested_period",
+ buf = kasprintf(GFP_KERNEL, "%s %s %s\n%d %d %d %d %d %d %d %d %d %d\n",
+ "max_concur plugged_delay plugsb4reset timeoutsb4reset",
+ "ipi_reset_limit complete_threshold congested_response_us",
+ "congested_reps disabled_period giveup_limit",
max_concurr, plugged_delay, plugsb4reset,
timeoutsb4reset, ipi_reset_limit, complete_threshold,
- congested_respns_us, congested_reps, congested_period);
+ congested_respns_us, congested_reps, disabled_period,
+ giveup_limit);
if (!buf)
return -ENOMEM;
return -EFAULT;
optstr[count - 1] = '\0';
+ if (!strcmp(optstr, "on")) {
+ set_bau_on();
+ return count;
+ } else if (!strcmp(optstr, "off")) {
+ set_bau_off();
+ return count;
+ }
+
if (strict_strtol(optstr, 10, &input_arg) < 0) {
printk(KERN_DEBUG "%s is invalid\n", optstr);
return -EINVAL;
bcp->complete_threshold = complete_threshold;
bcp->cong_response_us = congested_respns_us;
bcp->cong_reps = congested_reps;
- bcp->cong_period = congested_period;
+ bcp->disabled_period = sec_2_cycles(disabled_period);
+ bcp->giveup_limit = giveup_limit;
}
return count;
}
* fairness chaining multilevel count replied_to
*/
} else {
+ /*
+ * BIOS uses legacy mode, but UV2 hardware always
+ * uses native mode for selective broadcasts.
+ */
uv2_hdr = &bd2->header.uv2_hdr;
uv2_hdr->swack_flag = 1;
uv2_hdr->base_dest_nasid =
index = (mmr_image >> BAU_URGENCY_7_SHIFT) & BAU_URGENCY_7_MASK;
mmr_image = uv_read_local_mmr(UVH_TRANSACTION_TIMEOUT);
mult2 = (mmr_image >> BAU_TRANS_SHIFT) & BAU_TRANS_MASK;
- base = timeout_base_ns[index];
- ts_ns = base * mult1 * mult2;
+ ts_ns = timeout_base_ns[index];
+ ts_ns *= (mult1 * mult2);
ret = ts_ns / 1000;
} else {
/* 4 bits 0/1 for 10/80us base, 3 bits of multiplier */
for_each_present_cpu(cpu) {
bcp = &per_cpu(bau_control, cpu);
bcp->baudisabled = 0;
+ if (nobau)
+ bcp->nobau = 1;
bcp->statp = &per_cpu(ptcstats, cpu);
/* time interval to catch a hardware stay-busy bug */
bcp->timeout_interval = usec_2_cycles(2*timeout_us);
bcp->complete_threshold = complete_threshold;
bcp->cong_response_us = congested_respns_us;
bcp->cong_reps = congested_reps;
- bcp->cong_period = congested_period;
- bcp->clocks_per_100_usec = usec_2_cycles(100);
+ bcp->disabled_period = sec_2_cycles(disabled_period);
+ bcp->giveup_limit = giveup_limit;
spin_lock_init(&bcp->queue_lock);
spin_lock_init(&bcp->uvhub_lock);
+ spin_lock_init(&bcp->disable_lock);
}
}
}
bcp->uvhub_master = *hmasterp;
bcp->uvhub_cpu = uv_cpu_hub_info(cpu)->blade_processor_id;
- bcp->using_desc = bcp->uvhub_cpu;
if (bcp->uvhub_cpu >= MAX_CPUS_PER_UVHUB) {
printk(KERN_EMERG "%d cpus per uvhub invalid\n",
bcp->uvhub_cpu);
if (!is_uv_system())
return 0;
- if (nobau)
- return 0;
-
for_each_possible_cpu(cur_cpu) {
mask = &per_cpu(uv_flush_tlb_mask, cur_cpu);
zalloc_cpumask_var_node(mask, GFP_KERNEL, cpu_to_node(cur_cpu));
}
nuvhubs = uv_num_possible_blades();
- spin_lock_init(&disable_lock);
congested_cycles = usec_2_cycles(congested_respns_us);
uv_base_pnode = 0x7fffffff;
enable_timeouts();
if (init_per_cpu(nuvhubs, uv_base_pnode)) {
- nobau = 1;
+ set_bau_off();
+ nobau_perm = 1;
return 0;
}
static inline void __xen_set_pte(pte_t *ptep, pte_t pteval)
{
- if (!xen_batched_set_pte(ptep, pteval))
- native_set_pte(ptep, pteval);
+ if (!xen_batched_set_pte(ptep, pteval)) {
+ /*
+ * Could call native_set_pte() here and trap and
+ * emulate the PTE write but with 32-bit guests this
+ * needs two traps (one for each of the two 32-bit
+ * words in the PTE) so do one hypercall directly
+ * instead.
+ */
+ struct mmu_update u;
+
+ u.ptr = virt_to_machine(ptep).maddr | MMU_NORMAL_PT_UPDATE;
+ u.val = pte_val_ma(pteval);
+ HYPERVISOR_mmu_update(&u, 1, NULL, DOMID_SELF);
+ }
}
static void xen_set_pte(pte_t *ptep, pte_t pteval)
}
static void xen_flush_tlb_others(const struct cpumask *cpus,
- struct mm_struct *mm, unsigned long va)
+ struct mm_struct *mm, unsigned long start,
+ unsigned long end)
{
struct {
struct mmuext_op op;
} *args;
struct multicall_space mcs;
- trace_xen_mmu_flush_tlb_others(cpus, mm, va);
+ trace_xen_mmu_flush_tlb_others(cpus, mm, start, end);
if (cpumask_empty(cpus))
return; /* nothing to do */
cpumask_and(to_cpumask(args->mask), cpus, cpu_online_mask);
cpumask_clear_cpu(smp_processor_id(), to_cpumask(args->mask));
- if (va == TLB_FLUSH_ALL) {
- args->op.cmd = MMUEXT_TLB_FLUSH_MULTI;
- } else {
+ args->op.cmd = MMUEXT_TLB_FLUSH_MULTI;
+ if (start != TLB_FLUSH_ALL && (end - start) <= PAGE_SIZE) {
args->op.cmd = MMUEXT_INVLPG_MULTI;
- args->op.arg1.linear_addr = va;
+ args->op.arg1.linear_addr = start;
}
MULTI_mmuext_op(mcs.mc, &args->op, 1, NULL, DOMID_SELF);
}
#endif /* CONFIG_X86_64 */
-/* Init-time set_pte while constructing initial pagetables, which
- doesn't allow RO pagetable pages to be remapped RW */
+/*
+ * Init-time set_pte while constructing initial pagetables, which
+ * doesn't allow RO page table pages to be remapped RW.
+ *
+ * If there is no MFN for this PFN then this page is initially
+ * ballooned out so clear the PTE (as in decrease_reservation() in
+ * drivers/xen/balloon.c).
+ *
+ * Many of these PTE updates are done on unpinned and writable pages
+ * and doing a hypercall for these is unnecessary and expensive. At
+ * this point it is not possible to tell if a page is pinned or not,
+ * so always write the PTE directly and rely on Xen trapping and
+ * emulating any updates as necessary.
+ */
static void __init xen_set_pte_init(pte_t *ptep, pte_t pte)
{
- pte = mask_rw_pte(ptep, pte);
+ if (pte_mfn(pte) != INVALID_P2M_ENTRY)
+ pte = mask_rw_pte(ptep, pte);
+ else
+ pte = __pte_ma(0);
- xen_set_pte(ptep, pte);
+ native_set_pte(ptep, pte);
}
static void pin_pagetable_pfn(unsigned cmd, unsigned long pfn)
tlb->mm = mm;
tlb->fullmm = fullmm;
+ tlb->start = -1UL;
+ tlb->end = 0;
tlb->need_flush = 0;
tlb->fast_mode = (num_possible_cpus() == 1);
tlb->local.next = NULL;
{
struct mmu_gather_batch *batch, *next;
+ tlb->start = start;
+ tlb->end = end;
tlb_flush_mmu(tlb);
/* keep the page table cache within bounds */
*/
if (force_flush) {
force_flush = 0;
+
+ #ifdef HAVE_GENERIC_MMU_GATHER
+ tlb->start = addr;
+ tlb->end = end;
+ #endif
tlb_flush_mmu(tlb);
if (addr != end)
goto again;
next = pmd_addr_end(addr, end);
if (pmd_trans_huge(*pmd)) {
if (next - addr != HPAGE_PMD_SIZE) {
- VM_BUG_ON(!rwsem_is_locked(&tlb->mm->mmap_sem));
+#ifdef CONFIG_DEBUG_VM
+ if (!rwsem_is_locked(&tlb->mm->mmap_sem)) {
+ pr_err("%s: mmap_sem is unlocked! addr=0x%lx end=0x%lx vma->vm_start=0x%lx vma->vm_end=0x%lx\n",
+ __func__, addr, end,
+ vma->vm_start,
+ vma->vm_end);
+ BUG();
+ }
+#endif
split_huge_page_pmd(vma->vm_mm, pmd);
} else if (zap_huge_pmd(tlb, vma, pmd, addr))
goto next;
/**
* zap_page_range - remove user pages in a given range
* @vma: vm_area_struct holding the applicable pages
- * @address: starting address of pages to zap
+ * @start: starting address of pages to zap
* @size: number of bytes to zap
* @details: details of nonlinear truncation or shared cache invalidation
*